4014 files changed, 156945 insertions, 64914 deletions

diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 27e67a98b7be..1750fcef1ab4 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -287,6 +287,8 @@ local_ops.txt
 	- semantics and behavior of local atomic operations.
 lockdep-design.txt
 	- documentation on the runtime locking correctness validator.
+locking/
+	- directory with info about kernel locking primitives
 lockstat.txt
 	- info on collecting statistics on locks (and contention).
 lockup-watchdogs.txt
diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
index ce259c13c36a..5b2d0f08867c 100644
--- a/Documentation/ABI/stable/sysfs-devices-node
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -85,14 +85,6 @@ Description:
 		will be compacted. When it completes, memory will be freed
 		into blocks which have as many contiguous pages as possible
 
-What:		/sys/devices/system/node/nodeX/scan_unevictable_pages
-Date:		October 2008
-Contact:	Lee Schermerhorn <lee.schermerhorn@hp.com>
-Description:
-		When set, it triggers scanning the node's unevictable lists
-		and move any pages that have become evictable onto the respective
-		zone's inactive list. See mm/vmscan.c
-
 What:		/sys/devices/system/node/nodeX/hugepages/hugepages-<size>/
 Date:		December 2009
 Contact:	Lee Schermerhorn <lee.schermerhorn@hp.com>
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 279da08f7541..8df003963d99 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -53,6 +53,14 @@ Description:
 		512 bytes of data.
 
 
+What:		/sys/block/<disk>/integrity/device_is_integrity_capable
+Date:		July 2014
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Indicates whether a storage device is capable of storing
+		integrity metadata. Set if the device is T10 PI-capable.
+
+
 What:		/sys/block/<disk>/integrity/write_generate
 Date:		June 2008
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram
index 70ec992514d0..a6148eaf91e5 100644
--- a/Documentation/ABI/testing/sysfs-block-zram
+++ b/Documentation/ABI/testing/sysfs-block-zram
@@ -77,11 +77,14 @@ What:		/sys/block/zram<id>/notify_free
 Date:		August 2010
 Contact:	Nitin Gupta <ngupta@vflare.org>
 Description:
-		The notify_free file is read-only and specifies the number of
-		swap slot free notifications received by this device. These
-		notifications are sent to a swap block device when a swap slot
-		is freed. This statistic is applicable only when this disk is
-		being used as a swap disk.
+		The notify_free file is read-only. Depending on device usage
+		scenario it may account a) the number of pages freed because
+		of swap slot free notifications or b) the number of pages freed
+		because of REQ_DISCARD requests sent by bio. The former ones
+		are sent to a swap block device when a swap slot is freed, which
+		implies that this disk is being used as a swap disk. The latter
+		ones are sent by filesystem mounted with discard option,
+		whenever some data blocks are getting discarded.
 
 What:		/sys/block/zram<id>/zero_pages
 Date:		August 2010
@@ -119,3 +122,22 @@ Description:
 		efficiency can be calculated using compr_data_size and this
 		statistic.
 		Unit: bytes
+
+What:		/sys/block/zram<id>/mem_used_max
+Date:		August 2014
+Contact:	Minchan Kim <minchan@kernel.org>
+Description:
+		The mem_used_max file is read/write and specifies the amount
+		of maximum memory zram have consumed to store compressed data.
+		For resetting the value, you should write "0". Otherwise,
+		you could see -EINVAL.
+		Unit: bytes
+
+What:		/sys/block/zram<id>/mem_limit
+Date:		August 2014
+Contact:	Minchan Kim <minchan@kernel.org>
+Description:
+		The mem_limit file is read/write and specifies the maximum
+		amount of memory ZRAM can use to store the compressed data.  The
+		limit could be changed in run time and "0" means disable the
+		limit.  No limit is the initial state.  Unit: bytes
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7 b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
index e78ee798d7bd..32f3f5f8bba2 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_24x7
@@ -1,6 +1,6 @@
 What:		/sys/bus/event_source/devices/hv_24x7/interface/catalog
 Date:		February 2014
-Contact:	Cody P Schafer <cody@linux.vnet.ibm.com>
+Contact:	Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
 Description:
 		Provides access to the binary "24x7 catalog" provided by the
 		hypervisor on POWER7 and 8 systems. This catalog lists events
@@ -10,14 +10,14 @@ Description:
 
 What:		/sys/bus/event_source/devices/hv_24x7/interface/catalog_length
 Date:		February 2014
-Contact:	Cody P Schafer <cody@linux.vnet.ibm.com>
+Contact:	Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
 Description:
 		A number equal to the length in bytes of the catalog. This is
 		also extractable from the provided binary "catalog" sysfs entry.
 
 What:		/sys/bus/event_source/devices/hv_24x7/interface/catalog_version
 Date:		February 2014
-Contact:	Cody P Schafer <cody@linux.vnet.ibm.com>
+Contact:	Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
 Description:
 		Exposes the "version" field of the 24x7 catalog. This is also
 		extractable from the provided binary "catalog" sysfs entry.
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci
index 3fa58c23f13b..3ca4e554d2f9 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-hv_gpci
@@ -1,6 +1,6 @@
 What:		/sys/bus/event_source/devices/hv_gpci/interface/collect_privileged
 Date:		February 2014
-Contact:	Cody P Schafer <cody@linux.vnet.ibm.com>
+Contact:	Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
 Description:
 		'0' if the hypervisor is configured to forbid access to event
 		counters being accumulated by other guests and to physical
@@ -9,35 +9,35 @@ Description:
 
 What:		/sys/bus/event_source/devices/hv_gpci/interface/ga
 Date:		February 2014
-Contact:	Cody P Schafer <cody@linux.vnet.ibm.com>
+Contact:	Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
 Description:
 		0 or 1. Indicates whether we have access to "GA" events (listed
 		in arch/powerpc/perf/hv-gpci.h).
 
 What:		/sys/bus/event_source/devices/hv_gpci/interface/expanded
 Date:		February 2014
-Contact:	Cody P Schafer <cody@linux.vnet.ibm.com>
+Contact:	Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
 Description:
 		0 or 1. Indicates whether we have access to "EXPANDED" events (listed
 		in arch/powerpc/perf/hv-gpci.h).
 
 What:		/sys/bus/event_source/devices/hv_gpci/interface/lab
 Date:		February 2014
-Contact:	Cody P Schafer <cody@linux.vnet.ibm.com>
+Contact:	Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
 Description:
 		0 or 1. Indicates whether we have access to "LAB" events (listed
 		in arch/powerpc/perf/hv-gpci.h).
 
 What:		/sys/bus/event_source/devices/hv_gpci/interface/version
 Date:		February 2014
-Contact:	Cody P Schafer <cody@linux.vnet.ibm.com>
+Contact:	Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
 Description:
 		A number indicating the version of the gpci interface that the
 		hypervisor reports supporting.
 
 What:		/sys/bus/event_source/devices/hv_gpci/interface/kernel_version
 Date:		February 2014
-Contact:	Cody P Schafer <cody@linux.vnet.ibm.com>
+Contact:	Linux on PowerPC Developer List <linuxppc-dev@lists.ozlabs.org>
 Description:
 		A number indicating the latest version of the gpci interface
 		that the kernel is aware of.
diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
index 6615fda0abfb..ee6c04036492 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci
+++ b/Documentation/ABI/testing/sysfs-bus-pci
@@ -65,6 +65,16 @@ Description:
 		force a rescan of all PCI buses in the system, and
 		re-discover previously removed devices.
 
+What:		/sys/bus/pci/devices/.../msi_bus
+Date:		September 2014
+Contact:	Linux PCI developers <linux-pci@vger.kernel.org>
+Description:
+		Writing a zero value to this attribute disallows MSI and
+		MSI-X for any future drivers of the device.  If the device
+		is a bridge, MSI and MSI-X will be disallowed for future
+		drivers of all child devices under the bridge.  Drivers
+		must be reloaded for the new setting to take effect.
+
 What:		/sys/bus/pci/devices/.../msi_irqs/
 Date:		September, 2011
 Contact:	Neil Horman <nhorman@tuxdriver.com>
diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl
new file mode 100644
index 000000000000..554405ec1955
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-cxl
@@ -0,0 +1,129 @@
+Slave contexts (eg. /sys/class/cxl/afu0.0s):
+
+What:           /sys/class/cxl/<afu>/irqs_max
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read/write
+                Decimal value of maximum number of interrupts that can be
+                requested by userspace.  The default on probe is the maximum
+                that hardware can support (eg. 2037). Write values will limit
+                userspace applications to that many userspace interrupts. Must
+                be >= irqs_min.
+
+What:           /sys/class/cxl/<afu>/irqs_min
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the minimum number of interrupts that
+                userspace must request on a CXL_START_WORK ioctl. Userspace may
+                omit the num_interrupts field in the START_WORK IOCTL to get
+                this minimum automatically.
+
+What:           /sys/class/cxl/<afu>/mmio_size
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the size of the MMIO space that may be mmaped
+                by userspace.
+
+What:           /sys/class/cxl/<afu>/modes_supported
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                List of the modes this AFU supports. One per line.
+                Valid entries are: "dedicated_process" and "afu_directed"
+
+What:           /sys/class/cxl/<afu>/mode
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read/write
+                The current mode the AFU is using. Will be one of the modes
+                given in modes_supported. Writing will change the mode
+                provided that no user contexts are attached.
+
+
+What:           /sys/class/cxl/<afu>/prefault_mode
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read/write
+                Set the mode for prefaulting in segments into the segment table
+                when performing the START_WORK ioctl. Possible values:
+                        none: No prefaulting (default)
+                        work_element_descriptor: Treat the work element
+                                 descriptor as an effective address and
+                                 prefault what it points to.
+                        all: all segments process calling START_WORK maps.
+
+What:           /sys/class/cxl/<afu>/reset
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    write only
+                Writing 1 here will reset the AFU provided there are not
+                contexts active on the AFU.
+
+What:           /sys/class/cxl/<afu>/api_version
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the current version of the kernel/user API.
+
+What:           /sys/class/cxl/<afu>/api_version_com
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the the lowest version of the userspace API
+                this this kernel supports.
+
+
+
+Master contexts (eg. /sys/class/cxl/afu0.0m)
+
+What:           /sys/class/cxl/<afu>m/mmio_size
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the size of the MMIO space that may be mmaped
+                by userspace. This includes all slave contexts space also.
+
+What:           /sys/class/cxl/<afu>m/pp_mmio_len
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the Per Process MMIO space length.
+
+What:           /sys/class/cxl/<afu>m/pp_mmio_off
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Decimal value of the Per Process MMIO space offset.
+
+
+Card info (eg. /sys/class/cxl/card0)
+
+What:           /sys/class/cxl/<card>/caia_version
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Identifies the CAIA Version the card implements.
+
+What:           /sys/class/cxl/<card>/psl_version
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Identifies the revision level of the PSL.
+
+What:           /sys/class/cxl/<card>/base_image
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Identifies the revision level of the base image for devices
+                that support loadable PSLs. For FPGAs this field identifies
+                the image contained in the on-adapter flash which is loaded
+                during the initial program load.
+
+What:           /sys/class/cxl/<card>/image_loaded
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                Will return "user" or "factory" depending on the image loaded
+                onto the card.
diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power
index 78c7baca3587..909e7602c717 100644
--- a/Documentation/ABI/testing/sysfs-class-power
+++ b/Documentation/ABI/testing/sysfs-class-power
@@ -18,3 +18,17 @@ Description:
 		This file is writeable and can be used to set the assumed
 		battery 'full level'. As batteries age, this value has to be
 		amended over time.
+
+What:		/sys/class/power_supply/max14577-charger/device/fast_charge_timer
+Date:		October 2014
+KernelVersion:	3.18.0
+Contact:	Krzysztof Kozlowski <k.kozlowski@samsung.com>
+Description:
+		This entry shows and sets the maximum time the max14577
+		charger operates in fast-charge mode. When the timer expires
+		the device will terminate fast-charge mode (charging current
+		will drop to 0 A) and will trigger interrupt.
+
+		Valid values:
+		- 5, 6 or 7 (hours),
+		- 0: disabled.
diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory
index 7405de26ee60..deef3b5723cf 100644
--- a/Documentation/ABI/testing/sysfs-devices-memory
+++ b/Documentation/ABI/testing/sysfs-devices-memory
@@ -61,6 +61,14 @@ Users:		hotplug memory remove tools
 		http://www.ibm.com/developerworks/wikis/display/LinuxP/powerpc-utils
 
 
+What:           /sys/devices/system/memory/memoryX/valid_zones
+Date:           July 2014
+Contact:	Zhang Zhen <zhenzhang.zhang@huawei.com>
+Description:
+		The file /sys/devices/system/memory/memoryX/valid_zones	is
+		read-only and is designed to show which zone this memory
+		block can be onlined to.
+
 What:		/sys/devices/system/memoryX/nodeY
 Date:		October 2009
 Contact:	Linux Memory Management list <linux-mm@kvack.org>
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index bacefc5b222e..be35bc328b77 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -291,10 +291,9 @@ char *date;</synopsis>
       <title>Device Registration</title>
       <para>
         A number of functions are provided to help with device registration.
-        The functions deal with PCI, USB and platform devices, respectively.
+        The functions deal with PCI and platform devices, respectively.
       </para>
 !Edrivers/gpu/drm/drm_pci.c
-!Edrivers/gpu/drm/drm_usb.c
 !Edrivers/gpu/drm/drm_platform.c
       <para>
         New drivers that no longer rely on the services provided by the
@@ -3386,6 +3385,13 @@ void (*disable_vblank) (struct drm_device *dev, int crtc);</synopsis>
       by scheduling a timer. The delay is accessible through the vblankoffdelay
       module parameter or the <varname>drm_vblank_offdelay</varname> global
       variable and expressed in milliseconds. Its default value is 5000 ms.
+      Zero means never disable, and a negative value means disable immediately.
+      Drivers may override the behaviour by setting the
+      <structname>drm_device</structname>
+      <structfield>vblank_disable_immediate</structfield> flag, which when set
+      causes vblank interrupts to be disabled immediately regardless of the
+      drm_vblank_offdelay value. The flag should only be set if there's a
+      properly working hardware vblank counter present.
     </para>
     <para>
       When a vertical blanking interrupt occurs drivers only need to call the
@@ -3400,6 +3406,7 @@ void (*disable_vblank) (struct drm_device *dev, int crtc);</synopsis>
     <sect2>
       <title>Vertical Blanking and Interrupt Handling Functions Reference</title>
 !Edrivers/gpu/drm/drm_irq.c
+!Finclude/drm/drmP.h drm_crtc_vblank_waitqueue
     </sect2>
   </sect1>
 
@@ -3918,6 +3925,11 @@ int num_ioctls;</synopsis>
 !Pdrivers/gpu/drm/i915/i915_cmd_parser.c batch buffer command parser
 !Idrivers/gpu/drm/i915/i915_cmd_parser.c
       </sect2>
+      <sect2>
+        <title>Logical Rings, Logical Ring Contexts and Execlists</title>
+!Pdrivers/gpu/drm/i915/intel_lrc.c Logical Rings, Logical Ring Contexts and Execlists
+!Idrivers/gpu/drm/i915/intel_lrc.c
+      </sect2>
     </sect1>
   </chapter>
 </part>
diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl
index e584ee12a1e7..7c9cc4846cb6 100644
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/Documentation/DocBook/kernel-locking.tmpl
@@ -1972,7 +1972,7 @@ machines due to caching.
    <itemizedlist>
     <listitem>
      <para>
-       <filename>Documentation/spinlocks.txt</filename>: 
+       <filename>Documentation/locking/spinlocks.txt</filename>:
        Linus Torvalds' spinlocking tutorial in the kernel sources.
      </para>
     </listitem>
diff --git a/Documentation/DocBook/media/v4l/compat.xml b/Documentation/DocBook/media/v4l/compat.xml
index 3a626d1b8f2e..07ffc76553ba 100644
--- a/Documentation/DocBook/media/v4l/compat.xml
+++ b/Documentation/DocBook/media/v4l/compat.xml
@@ -2566,6 +2566,12 @@ fields changed from _s32 to _u32.
 	  <para>Added compound control types and &VIDIOC-QUERY-EXT-CTRL;.
 	  </para>
         </listitem>
+      <title>V4L2 in Linux 3.18</title>
+      <orderedlist>
+	<listitem>
+	  <para>Added <constant>V4L2_CID_PAN_SPEED</constant> and
+ <constant>V4L2_CID_TILT_SPEED</constant> camera controls.</para>
+	</listitem>
       </orderedlist>
     </section>
 
diff --git a/Documentation/DocBook/media/v4l/controls.xml b/Documentation/DocBook/media/v4l/controls.xml
index 9f5ffd85560b..e013e4bf244c 100644
--- a/Documentation/DocBook/media/v4l/controls.xml
+++ b/Documentation/DocBook/media/v4l/controls.xml
@@ -3965,6 +3965,27 @@ by exposure, white balance or focus controls.</entry>
 	  </row>
 	  <row><entry></entry></row>
 
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_PAN_SPEED</constant>&nbsp;</entry>
+	    <entry>integer</entry>
+	  </row><row><entry spanname="descr">This control turns the
+camera horizontally at the specific speed. The unit is undefined. A
+positive value moves the camera to the right (clockwise when viewed
+from above), a negative value to the left. A value of zero stops the motion
+if one is in progress and has no effect otherwise.</entry>
+	  </row>
+	  <row><entry></entry></row>
+
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_TILT_SPEED</constant>&nbsp;</entry>
+	    <entry>integer</entry>
+	  </row><row><entry spanname="descr">This control turns the
+camera vertically at the specified speed. The unit is undefined. A
+positive value moves the camera up, a negative value down. A value of zero
+stops the motion if one is in progress and has no effect otherwise.</entry>
+	  </row>
+	  <row><entry></entry></row>
+
 	</tbody>
       </tgroup>
     </table>
@@ -4790,6 +4811,40 @@ interface and may change in the future.</para>
 	    conversion.
 	    </entry>
 	  </row>
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_TEST_PATTERN_RED</constant></entry>
+	    <entry>integer</entry>
+	  </row>
+	  <row>
+	    <entry spanname="descr">Test pattern red colour component.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_TEST_PATTERN_GREENR</constant></entry>
+	    <entry>integer</entry>
+	  </row>
+	  <row>
+	    <entry spanname="descr">Test pattern green (next to red)
+	    colour component.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_TEST_PATTERN_BLUE</constant></entry>
+	    <entry>integer</entry>
+	  </row>
+	  <row>
+	    <entry spanname="descr">Test pattern blue colour component.
+	    </entry>
+	  </row>
+	  <row>
+	    <entry spanname="id"><constant>V4L2_CID_TEST_PATTERN_GREENB</constant></entry>
+	    <entry>integer</entry>
+	  </row>
+	  <row>
+	    <entry spanname="descr">Test pattern green (next to blue)
+	    colour component.
+	    </entry>
+	  </row>
 	  <row><entry></entry></row>
 	</tbody>
       </tgroup>
diff --git a/Documentation/DocBook/media/v4l/pixfmt-packed-rgb.xml b/Documentation/DocBook/media/v4l/pixfmt-packed-rgb.xml
index 2aae8e9452a4..6ab4f0f3db64 100644
--- a/Documentation/DocBook/media/v4l/pixfmt-packed-rgb.xml
+++ b/Documentation/DocBook/media/v4l/pixfmt-packed-rgb.xml
@@ -237,9 +237,9 @@ for a pixel lie next to each other in memory.</para>
 	    <entry>g<subscript>4</subscript></entry>
 	    <entry>g<subscript>3</subscript></entry>
 	  </row>
-	  <row id="V4L2-PIX-FMT-RGB555X">
-	    <entry><constant>V4L2_PIX_FMT_RGB555X</constant></entry>
-	    <entry>'RGBQ'</entry>
+	  <row id="V4L2-PIX-FMT-ARGB555X">
+	    <entry><constant>V4L2_PIX_FMT_ARGB555X</constant></entry>
+	    <entry>'AR15' | (1 &lt;&lt; 31)</entry>
 	    <entry></entry>
 	    <entry>a</entry>
 	    <entry>r<subscript>4</subscript></entry>
@@ -259,6 +259,28 @@ for a pixel lie next to each other in memory.</para>
 	    <entry>b<subscript>1</subscript></entry>
 	    <entry>b<subscript>0</subscript></entry>
 	  </row>
+	  <row id="V4L2-PIX-FMT-XRGB555X">
+	    <entry><constant>V4L2_PIX_FMT_XRGB555X</constant></entry>
+	    <entry>'XR15' | (1 &lt;&lt; 31)</entry>
+	    <entry></entry>
+	    <entry>-</entry>
+	    <entry>r<subscript>4</subscript></entry>
+	    <entry>r<subscript>3</subscript></entry>
+	    <entry>r<subscript>2</subscript></entry>
+	    <entry>r<subscript>1</subscript></entry>
+	    <entry>r<subscript>0</subscript></entry>
+	    <entry>g<subscript>4</subscript></entry>
+	    <entry>g<subscript>3</subscript></entry>
+	    <entry></entry>
+	    <entry>g<subscript>2</subscript></entry>
+	    <entry>g<subscript>1</subscript></entry>
+	    <entry>g<subscript>0</subscript></entry>
+	    <entry>b<subscript>4</subscript></entry>
+	    <entry>b<subscript>3</subscript></entry>
+	    <entry>b<subscript>2</subscript></entry>
+	    <entry>b<subscript>1</subscript></entry>
+	    <entry>b<subscript>0</subscript></entry>
+	  </row>
 	  <row id="V4L2-PIX-FMT-RGB565X">
 	    <entry><constant>V4L2_PIX_FMT_RGB565X</constant></entry>
 	    <entry>'RGBR'</entry>
@@ -464,7 +486,7 @@ for a pixel lie next to each other in memory.</para>
 	  </row>
 	  <row id="V4L2-PIX-FMT-ARGB32">
 	    <entry><constant>V4L2_PIX_FMT_ARGB32</constant></entry>
-	    <entry>'AX24'</entry>
+	    <entry>'BA24'</entry>
 	    <entry></entry>
 	    <entry>a<subscript>7</subscript></entry>
 	    <entry>a<subscript>6</subscript></entry>
@@ -800,6 +822,28 @@ image</title>
 	    <entry>g<subscript>4</subscript></entry>
 	    <entry>g<subscript>3</subscript></entry>
 	  </row>
+	  <row id="V4L2-PIX-FMT-RGB555X">
+	    <entry><constant>V4L2_PIX_FMT_RGB555X</constant></entry>
+	    <entry>'RGBQ'</entry>
+	    <entry></entry>
+	    <entry>a</entry>
+	    <entry>r<subscript>4</subscript></entry>
+	    <entry>r<subscript>3</subscript></entry>
+	    <entry>r<subscript>2</subscript></entry>
+	    <entry>r<subscript>1</subscript></entry>
+	    <entry>r<subscript>0</subscript></entry>
+	    <entry>g<subscript>4</subscript></entry>
+	    <entry>g<subscript>3</subscript></entry>
+	    <entry></entry>
+	    <entry>g<subscript>2</subscript></entry>
+	    <entry>g<subscript>1</subscript></entry>
+	    <entry>g<subscript>0</subscript></entry>
+	    <entry>b<subscript>4</subscript></entry>
+	    <entry>b<subscript>3</subscript></entry>
+	    <entry>b<subscript>2</subscript></entry>
+	    <entry>b<subscript>1</subscript></entry>
+	    <entry>b<subscript>0</subscript></entry>
+	  </row>
 	  <row id="V4L2-PIX-FMT-BGR32">
 	    <entry><constant>V4L2_PIX_FMT_BGR32</constant></entry>
 	    <entry>'BGR4'</entry>
diff --git a/Documentation/DocBook/media/v4l/vidioc-dqevent.xml b/Documentation/DocBook/media/v4l/vidioc-dqevent.xml
index cb7732582f03..b036f8963353 100644
--- a/Documentation/DocBook/media/v4l/vidioc-dqevent.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-dqevent.xml
@@ -76,21 +76,22 @@
 	    <entry></entry>
 	    <entry>&v4l2-event-vsync;</entry>
             <entry><structfield>vsync</structfield></entry>
-	    <entry>Event data for event V4L2_EVENT_VSYNC.
+	    <entry>Event data for event <constant>V4L2_EVENT_VSYNC</constant>.
             </entry>
 	  </row>
 	  <row>
 	    <entry></entry>
 	    <entry>&v4l2-event-ctrl;</entry>
             <entry><structfield>ctrl</structfield></entry>
-	    <entry>Event data for event V4L2_EVENT_CTRL.
+	    <entry>Event data for event <constant>V4L2_EVENT_CTRL</constant>.
             </entry>
 	  </row>
 	  <row>
 	    <entry></entry>
 	    <entry>&v4l2-event-frame-sync;</entry>
             <entry><structfield>frame_sync</structfield></entry>
-	    <entry>Event data for event V4L2_EVENT_FRAME_SYNC.</entry>
+	    <entry>Event data for event
+	    <constant>V4L2_EVENT_FRAME_SYNC</constant>.</entry>
 	  </row>
 	  <row>
 	    <entry></entry>
diff --git a/Documentation/DocBook/media/v4l/vidioc-g-edid.xml b/Documentation/DocBook/media/v4l/vidioc-g-edid.xml
index ce4563b87131..6df40db4c8ba 100644
--- a/Documentation/DocBook/media/v4l/vidioc-g-edid.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-g-edid.xml
@@ -24,7 +24,7 @@
 	<funcdef>int <function>ioctl</function></funcdef>
 	<paramdef>int <parameter>fd</parameter></paramdef>
 	<paramdef>int <parameter>request</parameter></paramdef>
-	<paramdef>const struct v4l2_edid *<parameter>argp</parameter></paramdef>
+	<paramdef>struct v4l2_edid *<parameter>argp</parameter></paramdef>
       </funcprototype>
     </funcsynopsis>
   </refsynopsisdiv>
@@ -125,17 +125,17 @@
 	    <structfield>blocks</structfield> is 0, then the EDID is disabled or erased.</entry>
 	  </row>
 	  <row>
-	    <entry>__u8&nbsp;*</entry>
-	    <entry><structfield>edid</structfield></entry>
-	    <entry>Pointer to memory that contains the EDID. The minimum size is
-	    <structfield>blocks</structfield>&nbsp;*&nbsp;128.</entry>
-	  </row>
-	  <row>
 	    <entry>__u32</entry>
 	    <entry><structfield>reserved</structfield>[5]</entry>
 	    <entry>Reserved for future extensions. Applications and drivers must
 	    set the array to zero.</entry>
 	  </row>
+	  <row>
+	    <entry>__u8&nbsp;*</entry>
+	    <entry><structfield>edid</structfield></entry>
+	    <entry>Pointer to memory that contains the EDID. The minimum size is
+	    <structfield>blocks</structfield>&nbsp;*&nbsp;128.</entry>
+	  </row>
 	</tbody>
       </tgroup>
     </table>
diff --git a/Documentation/DocBook/media/v4l/vidioc-subscribe-event.xml b/Documentation/DocBook/media/v4l/vidioc-subscribe-event.xml
index 9f6095608837..d7c9365ecdbe 100644
--- a/Documentation/DocBook/media/v4l/vidioc-subscribe-event.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-subscribe-event.xml
@@ -176,7 +176,7 @@
 	  </row>
 	  <row>
 	    <entry><constant>V4L2_EVENT_MOTION_DET</constant></entry>
-	    <entry>5</entry>
+	    <entry>6</entry>
 	    <entry>
 	      <para>Triggered whenever the motion detection state for one or more of the regions
 	      changes. This event has a &v4l2-event-motion-det; associated with it.</para>
diff --git a/Documentation/DocBook/writing-an-alsa-driver.tmpl b/Documentation/DocBook/writing-an-alsa-driver.tmpl
index 6f639d9530b5..784793df81ed 100644
--- a/Documentation/DocBook/writing-an-alsa-driver.tmpl
+++ b/Documentation/DocBook/writing-an-alsa-driver.tmpl
@@ -2742,7 +2742,9 @@ struct _snd_pcm_runtime {
 
         <para>
           Another note is that this callback is non-atomic
-        (schedulable). This is important, because the
+        (schedulable) as default, i.e. when no
+	<structfield>nonatomic</structfield> flag set.
+	This is important, because the
         <structfield>trigger</structfield> callback 
         is atomic (non-schedulable). That is, mutexes or any
         schedule-related functions are not available in
@@ -2900,8 +2902,9 @@ struct _snd_pcm_runtime {
         </para>
 
         <para>
-          As mentioned, this callback is atomic.  You cannot call
-	  functions which may sleep.
+          As mentioned, this callback is atomic as default unless
+	  <structfield>nonatomic</structfield> flag set, and
+	  you cannot call functions which may sleep.
 	  The trigger callback should be as minimal as possible,
 	  just really triggering the DMA.  The other stuff should be
 	  initialized hw_params and prepare callbacks properly
@@ -2936,7 +2939,7 @@ struct _snd_pcm_runtime {
         </para>
 
         <para>
-          This callback is also atomic.
+          This callback is also atomic as default.
         </para>
       </section>
 
@@ -2972,7 +2975,7 @@ struct _snd_pcm_runtime {
 	is useful only for such a purpose.
 	</para>
 	<para>
-	  This callback is atomic.
+	  This callback is atomic as default.
 	</para>
       </section>
 
@@ -3175,6 +3178,21 @@ struct _snd_pcm_runtime {
       called with local interrupts disabled.
       </para>
 
+      <para>
+      The recent changes in PCM core code, however, allow all PCM
+      operations to be non-atomic.  This assumes that the all caller
+      sides are in non-atomic contexts.  For example, the function
+      <function>snd_pcm_period_elapsed()</function> is called
+      typically from the interrupt handler.  But, if you set up the
+      driver to use a threaded interrupt handler, this call can be in
+      non-atomic context, too.  In such a case, you can set
+      <structfield>nonatomic</structfield> filed of
+      <structname>snd_pcm</structname> object after creating it.
+      When this flag is set, mutex and rwsem are used internally in
+      the PCM core instead of spin and rwlocks, so that you can call
+      all PCM functions safely in a non-atomic context.
+      </para>
+
     </section>
     <section id="pcm-interface-constraints">
       <title>Constraints</title>
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 68fe3ad27015..ef5a2fd4ff70 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -56,8 +56,20 @@ RCU_STALL_RAT_DELAY
 	two jiffies.  (This is a cpp macro, not a kernel configuration
 	parameter.)
 
-When a CPU detects that it is stalling, it will print a message similar
-to the following:
+rcupdate.rcu_task_stall_timeout
+
+	This boot/sysfs parameter controls the RCU-tasks stall warning
+	interval.  A value of zero or less suppresses RCU-tasks stall
+	warnings.  A positive value sets the stall-warning interval
+	in jiffies.  An RCU-tasks stall warning starts wtih the line:
+
+		INFO: rcu_tasks detected stalls on tasks:
+
+	And continues with the output of sched_show_task() for each
+	task stalling the current RCU-tasks grace period.
+
+For non-RCU-tasks flavors of RCU, when a CPU detects that it is stalling,
+it will print a message similar to the following:
 
 INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies)
 
@@ -174,8 +186,12 @@ o	A CPU looping with preemption disabled.  This condition can
 o	A CPU looping with bottom halves disabled.  This condition can
 	result in RCU-sched and RCU-bh stalls.
 
-o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
-	without invoking schedule().
+o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the
+	kernel without invoking schedule().  Note that cond_resched()
+	does not necessarily prevent RCU CPU stall warnings.  Therefore,
+	if the looping in the kernel is really expected and desirable
+	behavior, you might need to replace some of the cond_resched()
+	calls with calls to cond_resched_rcu_qs().
 
 o	A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
 	happen to preempt a low-priority task in the middle of an RCU
@@ -208,11 +224,10 @@ o	A hardware failure.  This is quite unlikely, but has occurred
 	This resulted in a series of RCU CPU stall warnings, eventually
 	leading the realization that the CPU had failed.
 
-The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning.
-SRCU does not have its own CPU stall warnings, but its calls to
-synchronize_sched() will result in RCU-sched detecting RCU-sched-related
-CPU stalls.  Please note that RCU only detects CPU stalls when there is
-a grace period in progress.  No grace period, no CPU stall warnings.
+The RCU, RCU-sched, RCU-bh, and RCU-tasks implementations have CPU stall
+warning.  Note that SRCU does -not- have CPU stall warnings.  Please note
+that RCU only detects CPU stalls when there is a grace period in progress.
+No grace period, no CPU stall warnings.
 
 To diagnose the cause of the stall, inspect the stack traces.
 The offending function will usually be near the top of the stack.
diff --git a/Documentation/acpi/enumeration.txt b/Documentation/acpi/enumeration.txt
index e182be5e3c83..b60d2ab69497 100644
--- a/Documentation/acpi/enumeration.txt
+++ b/Documentation/acpi/enumeration.txt
@@ -312,3 +312,30 @@ a code like this:
 
 There are also devm_* versions of these functions which release the
 descriptors once the device is released.
+
+MFD devices
+~~~~~~~~~~~
+The MFD devices register their children as platform devices. For the child
+devices there needs to be an ACPI handle that they can use to reference
+parts of the ACPI namespace that relate to them. In the Linux MFD subsystem
+we provide two ways:
+
+	o The children share the parent ACPI handle.
+	o The MFD cell can specify the ACPI id of the device.
+
+For the first case, the MFD drivers do not need to do anything. The
+resulting child platform device will have its ACPI_COMPANION() set to point
+to the parent device.
+
+If the ACPI namespace has a device that we can match using an ACPI id,
+the id should be set like:
+
+	static struct mfd_cell my_subdevice_cell = {
+		.name = "my_subdevice",
+		/* set the resources relative to the parent */
+		.acpi_pnpid = "XYZ0001",
+	};
+
+The ACPI id "XYZ0001" is then used to lookup an ACPI device directly under
+the MFD device and if found, that ACPI companion device is bound to the
+resulting child platform device.
diff --git a/Documentation/binfmt_misc.txt b/Documentation/binfmt_misc.txt
index c1ed6948ba80..6b1de7058371 100644
--- a/Documentation/binfmt_misc.txt
+++ b/Documentation/binfmt_misc.txt
@@ -15,39 +15,50 @@ First you must mount binfmt_misc:
 	mount binfmt_misc -t binfmt_misc /proc/sys/fs/binfmt_misc 
 
 To actually register a new binary type, you have to set up a string looking like
-:name:type:offset:magic:mask:interpreter:flags (where you can choose the ':' upon
-your needs) and echo it to /proc/sys/fs/binfmt_misc/register.
+:name:type:offset:magic:mask:interpreter:flags (where you can choose the ':'
+upon your needs) and echo it to /proc/sys/fs/binfmt_misc/register.
+
 Here is what the fields mean:
  - 'name' is an identifier string. A new /proc file will be created with this
-   name below /proc/sys/fs/binfmt_misc
+   name below /proc/sys/fs/binfmt_misc; cannot contain slashes '/' for obvious
+   reasons.
  - 'type' is the type of recognition. Give 'M' for magic and 'E' for extension.
  - 'offset' is the offset of the magic/mask in the file, counted in bytes. This
-   defaults to 0 if you omit it (i.e. you write ':name:type::magic...')
+   defaults to 0 if you omit it (i.e. you write ':name:type::magic...'). Ignored
+   when using filename extension matching.
  - 'magic' is the byte sequence binfmt_misc is matching for. The magic string
-   may contain hex-encoded characters like \x0a or \xA4. In a shell environment
-   you will have to write \\x0a to prevent the shell from eating your \.
+   may contain hex-encoded characters like \x0a or \xA4. Note that you must
+   escape any NUL bytes; parsing halts at the first one. In a shell environment
+   you might have to write \\x0a to prevent the shell from eating your \.
    If you chose filename extension matching, this is the extension to be
    recognised (without the '.', the \x0a specials are not allowed). Extension
-   matching is case sensitive!
+   matching is case sensitive, and slashes '/' are not allowed!
  - 'mask' is an (optional, defaults to all 0xff) mask. You can mask out some
    bits from matching by supplying a string like magic and as long as magic.
-   The mask is anded with the byte sequence of the file.
+   The mask is anded with the byte sequence of the file. Note that you must
+   escape any NUL bytes; parsing halts at the first one. Ignored when using
+   filename extension matching.
  - 'interpreter' is the program that should be invoked with the binary as first
    argument (specify the full path)
  - 'flags' is an optional field that controls several aspects of the invocation
-   of the interpreter. It is a string of capital letters, each controls a certain
-   aspect. The following flags are supported -
-      'P' - preserve-argv[0].  Legacy behavior of binfmt_misc is to overwrite the
-            original argv[0] with the full path to the binary.  When this flag is
-            included, binfmt_misc will add an argument to the argument vector for
-            this purpose, thus preserving the original argv[0].
+   of the interpreter. It is a string of capital letters, each controls a
+   certain aspect. The following flags are supported -
+      'P' - preserve-argv[0]. Legacy behavior of binfmt_misc is to overwrite
+            the original argv[0] with the full path to the binary. When this
+            flag is included, binfmt_misc will add an argument to the argument
+            vector for this purpose, thus preserving the original argv[0].
+            e.g. If your interp is set to /bin/foo and you run `blah` (which is
+            in /usr/local/bin), then the kernel will execute /bin/foo with
+            argv[] set to ["/bin/foo", "/usr/local/bin/blah", "blah"].  The
+            interp has to be aware of this so it can execute /usr/local/bin/blah
+            with argv[] set to ["blah"].
       'O' - open-binary. Legacy behavior of binfmt_misc is to pass the full path
             of the binary to the interpreter as an argument. When this flag is
             included, binfmt_misc will open the file for reading and pass its
             descriptor as an argument, instead of the full path, thus allowing
-            the interpreter to execute non-readable binaries. This feature should
-            be used with care - the interpreter has to be trusted not to emit
-            the contents of the non-readable binary.
+            the interpreter to execute non-readable binaries. This feature
+            should be used with care - the interpreter has to be trusted not to
+            emit the contents of the non-readable binary.
       'C' - credentials. Currently, the behavior of binfmt_misc is to calculate
             the credentials and security token of the new process according to
             the interpreter. When this flag is included, these attributes are
@@ -58,7 +69,7 @@ Here is what the fields mean:
 
 
 There are some restrictions:
- - the whole register string may not exceed 255 characters
+ - the whole register string may not exceed 1920 characters
  - the magic must reside in the first 128 bytes of the file, i.e.
    offset+size(magic) has to be less than 128
  - the interpreter string may not exceed 127 characters
@@ -110,7 +121,4 @@ passes it the full filename (or the file descriptor) to use.  Using $PATH can
 cause unexpected behaviour and can be a security hazard.
 
 
-There is a web page about binfmt_misc at
-http://www.tat.physik.uni-tuebingen.de
-
 Richard Günther <rguenth@tat.physik.uni-tuebingen.de>
diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt
index 2d735b0ae383..f56ec97f0d14 100644
--- a/Documentation/block/data-integrity.txt
+++ b/Documentation/block/data-integrity.txt
@@ -129,11 +129,11 @@ interface for this is being worked on.
 4.1 BIO
 
 The data integrity patches add a new field to struct bio when
-CONFIG_BLK_DEV_INTEGRITY is enabled.  bio->bi_integrity is a pointer
-to a struct bip which contains the bio integrity payload.  Essentially
-a bip is a trimmed down struct bio which holds a bio_vec containing
-the integrity metadata and the required housekeeping information (bvec
-pool, vector count, etc.)
+CONFIG_BLK_DEV_INTEGRITY is enabled.  bio_integrity(bio) returns a
+pointer to a struct bip which contains the bio integrity payload.
+Essentially a bip is a trimmed down struct bio which holds a bio_vec
+containing the integrity metadata and the required housekeeping
+information (bvec pool, vector count, etc.)
 
 A kernel subsystem can enable data integrity protection on a bio by
 calling bio_integrity_alloc(bio).  This will allocate and attach the
@@ -192,16 +192,6 @@ will require extra work due to the application tag.
     supported by the block device.
 
 
-    int bdev_integrity_enabled(block_device, int rw);
-
-      bdev_integrity_enabled() will return 1 if the block device
-      supports integrity metadata transfer for the data direction
-      specified in 'rw'.
-
-      bdev_integrity_enabled() honors the write_generate and
-      read_verify flags in sysfs and will respond accordingly.
-
-
     int bio_integrity_prep(bio);
 
       To generate IMD for WRITE and to set up buffers for READ, the
@@ -216,36 +206,6 @@ will require extra work due to the application tag.
       bio_integrity_enabled() returned 1.
 
 
-    int bio_integrity_tag_size(bio);
-
-      If the filesystem wants to use the application tag space it will
-      first have to find out how much storage space is available.
-      Because tag space is generally limited (usually 2 bytes per
-      sector regardless of sector size), the integrity framework
-      supports interleaving the information between the sectors in an
-      I/O.
-
-      Filesystems can call bio_integrity_tag_size(bio) to find out how
-      many bytes of storage are available for that particular bio.
-
-      Another option is bdev_get_tag_size(block_device) which will
-      return the number of available bytes per hardware sector.
-
-
-    int bio_integrity_set_tag(bio, void *tag_buf, len);
-
-      After a successful return from bio_integrity_prep(),
-      bio_integrity_set_tag() can be used to attach an opaque tag
-      buffer to a bio.  Obviously this only makes sense if the I/O is
-      a WRITE.
-
-
-    int bio_integrity_get_tag(bio, void *tag_buf, len);
-
-      Similarly, at READ I/O completion time the filesystem can
-      retrieve the tag buffer using bio_integrity_get_tag().
-
-
 5.3 PASSING EXISTING INTEGRITY METADATA
 
     Filesystems that either generate their own integrity metadata or
@@ -298,8 +258,6 @@ will require extra work due to the application tag.
             .name                   = "STANDARDSBODY-TYPE-VARIANT-CSUM",
             .generate_fn            = my_generate_fn,
        	    .verify_fn              = my_verify_fn,
-       	    .get_tag_fn             = my_get_tag_fn,
-       	    .set_tag_fn             = my_set_tag_fn,
 	    .tuple_size             = sizeof(struct my_tuple_size),
 	    .tag_size               = <tag bytes per hw sector>,
         };
@@ -321,7 +279,5 @@ will require extra work due to the application tag.
       are available per hardware sector.  For DIF this is either 2 or
       0 depending on the value of the Control Mode Page ATO bit.
 
-      See 6.2 for a description of get_tag_fn and set_tag_fn.
-
 ----------------------------------------------------------------------
 2007-12-24 Martin K. Petersen <martin.petersen@oracle.com>
diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt
index 0595c3f56ccf..7fcf9c6592ec 100644
--- a/Documentation/blockdev/zram.txt
+++ b/Documentation/blockdev/zram.txt
@@ -74,14 +74,30 @@ There is little point creating a zram of greater than twice the size of memory
 since we expect a 2:1 compression ratio. Note that zram uses about 0.1% of the
 size of the disk when not in use so a huge zram is wasteful.
 
-5) Activate:
+5) Set memory limit: Optional
+	Set memory limit by writing the value to sysfs node 'mem_limit'.
+	The value can be either in bytes or you can use mem suffixes.
+	In addition, you could change the value in runtime.
+	Examples:
+	    # limit /dev/zram0 with 50MB memory
+	    echo $((50*1024*1024)) > /sys/block/zram0/mem_limit
+
+	    # Using mem suffixes
+	    echo 256K > /sys/block/zram0/mem_limit
+	    echo 512M > /sys/block/zram0/mem_limit
+	    echo 1G > /sys/block/zram0/mem_limit
+
+	    # To disable memory limit
+	    echo 0 > /sys/block/zram0/mem_limit
+
+6) Activate:
 	mkswap /dev/zram0
 	swapon /dev/zram0
 
 	mkfs.ext4 /dev/zram1
 	mount /dev/zram1 /tmp
 
-6) Stats:
+7) Stats:
 	Per-device statistics are exported as various nodes under
 	/sys/block/zram<id>/
 		disksize
@@ -95,12 +111,13 @@ size of the disk when not in use so a huge zram is wasteful.
 		orig_data_size
 		compr_data_size
 		mem_used_total
+		mem_used_max
 
-7) Deactivate:
+8) Deactivate:
 	swapoff /dev/zram0
 	umount /dev/zram1
 
-8) Reset:
+9) Reset:
 	Write any positive value to 'reset' sysfs node
 	echo 1 > /sys/block/zram0/reset
 	echo 1 > /sys/block/zram1/reset
diff --git a/Documentation/devicetree/bindings/arm/exynos/power_domain.txt b/Documentation/devicetree/bindings/arm/exynos/power_domain.txt
index 8b4f7b7fe88b..abde1ea8a119 100644
--- a/Documentation/devicetree/bindings/arm/exynos/power_domain.txt
+++ b/Documentation/devicetree/bindings/arm/exynos/power_domain.txt
@@ -8,6 +8,8 @@ Required Properties:
     * samsung,exynos4210-pd - for exynos4210 type power domain.
 - reg: physical base address of the controller and length of memory mapped
     region.
+- #power-domain-cells: number of cells in power domain specifier;
+    must be 0.
 
 Optional Properties:
 - clocks: List of clock handles. The parent clocks of the input clocks to the
@@ -29,6 +31,7 @@ Example:
 	lcd0: power-domain-lcd0 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10023C00 0x10>;
+		#power-domain-cells = <0>;
 	};
 
 	mfc_pd: power-domain@10044060 {
@@ -37,12 +40,8 @@ Example:
 		clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MOUT_SW_ACLK333>,
 			<&clock CLK_MOUT_USER_ACLK333>;
 		clock-names = "oscclk", "pclk0", "clk0";
+		#power-domain-cells = <0>;
 	};
 
-Example of the node using power domain:
-
-	node {
-		/* ... */
-		samsung,power-domain = <&lcd0>;
-		/* ... */
-	};
+See Documentation/devicetree/bindings/power/power_domain.txt for description
+of consumer-side bindings.
diff --git a/Documentation/devicetree/bindings/ata/qcom-sata.txt b/Documentation/devicetree/bindings/ata/qcom-sata.txt
new file mode 100644
index 000000000000..094de91cd9fd
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/qcom-sata.txt
@@ -0,0 +1,48 @@
+* Qualcomm AHCI SATA Controller
+
+SATA nodes are defined to describe on-chip Serial ATA controllers.
+Each SATA controller should have its own node.
+
+Required properties:
+- compatible		: compatible list, must contain "generic-ahci"
+- interrupts		: <interrupt mapping for SATA IRQ>
+- reg			: <registers mapping>
+- phys			: Must contain exactly one entry as specified
+			  in phy-bindings.txt
+- phy-names		: Must be "sata-phy"
+
+Required properties for "qcom,ipq806x-ahci" compatible:
+- clocks		: Must contain an entry for each entry in clock-names.
+- clock-names		: Shall be:
+				"slave_iface" - Fabric port AHB clock for SATA
+				"iface" - AHB clock
+				"core" - core clock
+				"rxoob" - RX out-of-band clock
+				"pmalive" - Power Module Alive clock
+- assigned-clocks	: Shall be:
+				SATA_RXOOB_CLK
+				SATA_PMALIVE_CLK
+- assigned-clock-rates	: Shall be:
+				100Mhz (100000000) for SATA_RXOOB_CLK
+				100Mhz (100000000) for SATA_PMALIVE_CLK
+
+Example:
+	sata@29000000 {
+		compatible = "qcom,ipq806x-ahci", "generic-ahci";
+		reg = <0x29000000 0x180>;
+
+		interrupts = <0 209 0x0>;
+
+		clocks = <&gcc SFAB_SATA_S_H_CLK>,
+			 <&gcc SATA_H_CLK>,
+			 <&gcc SATA_A_CLK>,
+			 <&gcc SATA_RXOOB_CLK>,
+			 <&gcc SATA_PMALIVE_CLK>;
+		clock-names = "slave_iface", "iface", "core",
+				"rxoob", "pmalive";
+		assigned-clocks = <&gcc SATA_RXOOB_CLK>, <&gcc SATA_PMALIVE_CLK>;
+		assigned-clock-rates = <100000000>, <100000000>;
+
+		phys = <&sata_phy>;
+		phy-names = "sata-phy";
+	};
diff --git a/Documentation/devicetree/bindings/clock/exynos3250-clock.txt b/Documentation/devicetree/bindings/clock/exynos3250-clock.txt
index aadc9c59e2d1..f57d9dd9ea85 100644
--- a/Documentation/devicetree/bindings/clock/exynos3250-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos3250-clock.txt
@@ -7,6 +7,8 @@ Required Properties:
 
 - compatible: should be one of the following.
   - "samsung,exynos3250-cmu" - controller compatible with Exynos3250 SoC.
+  - "samsung,exynos3250-cmu-dmc" - controller compatible with
+    Exynos3250 SoC for Dynamic Memory Controller domain.
 
 - reg: physical base address of the controller and length of memory mapped
   region.
@@ -20,7 +22,7 @@ All available clocks are defined as preprocessor macros in
 dt-bindings/clock/exynos3250.h header and can be used in device
 tree sources.
 
-Example 1: An example of a clock controller node is listed below.
+Example 1: Examples of clock controller nodes are listed below.
 
 	cmu: clock-controller@10030000 {
 		compatible = "samsung,exynos3250-cmu";
@@ -28,6 +30,12 @@ Example 1: An example of a clock controller node is listed below.
 		#clock-cells = <1>;
 	};
 
+	cmu_dmc: clock-controller@105C0000 {
+		compatible = "samsung,exynos3250-cmu-dmc";
+		reg = <0x105C0000 0x2000>;
+		#clock-cells = <1>;
+	};
+
 Example 2: UART controller node that consumes the clock generated by the clock
 	   controller. Refer to the standard clock bindings for information
 	   about 'clocks' and 'clock-names' property.
diff --git a/Documentation/devicetree/bindings/clock/gpio-gate-clock.txt b/Documentation/devicetree/bindings/clock/gpio-gate-clock.txt
new file mode 100644
index 000000000000..d3379ff9b84b
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/gpio-gate-clock.txt
@@ -0,0 +1,21 @@
+Binding for simple gpio gated clock.
+
+This binding uses the common clock binding[1].
+
+[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Required properties:
+- compatible : shall be "gpio-gate-clock".
+- #clock-cells : from common clock binding; shall be set to 0.
+- enable-gpios : GPIO reference for enabling and disabling the clock.
+
+Optional properties:
+- clocks: Maximum of one parent clock is supported.
+
+Example:
+	clock {
+		compatible = "gpio-gate-clock";
+		clocks = <&parentclk>;
+		#clock-cells = <0>;
+		enable-gpios = <&gpio 1 GPIO_ACTIVE_HIGH>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/maxim,max77686.txt b/Documentation/devicetree/bindings/clock/maxim,max77686.txt
index 96ce71bbd745..9c40739a661a 100644
--- a/Documentation/devicetree/bindings/clock/maxim,max77686.txt
+++ b/Documentation/devicetree/bindings/clock/maxim,max77686.txt
@@ -9,13 +9,21 @@ The MAX77686 contains three 32.768khz clock outputs that can be controlled
 Following properties should be presend in main device node of the MFD chip.
 
 Required properties:
-- #clock-cells: simple one-cell clock specifier format is used, where the
-  only cell is used as an index of the clock inside the provider. Following
-  indices are allowed:
+
+- #clock-cells: from common clock binding; shall be set to 1.
+
+Optional properties:
+- clock-output-names: From common clock binding.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. Following indices are allowed:
     - 0: 32khz_ap clock,
     - 1: 32khz_cp clock,
     - 2: 32khz_pmic clock.
 
+Clocks are defined as preprocessor macros in dt-bindings/clock/maxim,max77686.h
+header and can be used in device tree sources.
+
 Example: Node of the MFD chip
 
 	max77686: max77686@09 {
@@ -34,5 +42,5 @@ Example: Clock consumer node
 		compatible = "bar,foo";
 		/* ... */
 		clock-names = "my-clock";
-		clocks = <&max77686 2>;
+		clocks = <&max77686 MAX77686_CLK_PMIC>;
 	};
diff --git a/Documentation/devicetree/bindings/clock/maxim,max77802.txt b/Documentation/devicetree/bindings/clock/maxim,max77802.txt
new file mode 100644
index 000000000000..c6dc7835f06c
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/maxim,max77802.txt
@@ -0,0 +1,44 @@
+Binding for Maxim MAX77802 32k clock generator block
+
+This is a part of device tree bindings of MAX77802 multi-function device.
+More information can be found in bindings/mfd/max77802.txt file.
+
+The MAX77802 contains two 32.768khz clock outputs that can be controlled
+(gated/ungated) over I2C.
+
+Following properties should be present in main device node of the MFD chip.
+
+Required properties:
+- #clock-cells: From common clock binding; shall be set to 1.
+
+Optional properties:
+- clock-output-names: From common clock binding.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. Following indices are allowed:
+     - 0: 32khz_ap clock,
+     - 1: 32khz_cp clock.
+
+Clocks are defined as preprocessor macros in dt-bindings/clock/maxim,max77802.h
+header and can be used in device tree sources.
+
+Example: Node of the MFD chip
+
+	max77802: max77802@09 {
+		compatible = "maxim,max77802";
+		interrupt-parent = <&wakeup_eint>;
+		interrupts = <26 0>;
+		reg = <0x09>;
+		#clock-cells = <1>;
+
+		/* ... */
+	};
+
+Example: Clock consumer node
+
+	foo@0 {
+		compatible = "bar,foo";
+		/* ... */
+		clock-names = "my-clock";
+		clocks = <&max77802 MAX77802_CLK_32K_AP>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/pxa-clock.txt b/Documentation/devicetree/bindings/clock/pxa-clock.txt
new file mode 100644
index 000000000000..4b4a9024bd99
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/pxa-clock.txt
@@ -0,0 +1,16 @@
+* Clock bindings for Marvell PXA chips
+
+Required properties:
+- compatible: Should be "marvell,pxa-clocks"
+- #clock-cells: Should be <1>
+
+The clock consumer should specify the desired clock by having the clock
+ID in its "clocks" phandle cell (see include/.../pxa-clock.h).
+
+Examples:
+
+pxa2xx_clks: pxa2xx_clks@41300004 {
+        compatible = "marvell,pxa-clocks";
+        #clock-cells = <1>;
+        status = "okay";
+};
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
index 8f1424f0fa43..a5f52238c80d 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
@@ -15,6 +15,7 @@ Required Properties:
     - "renesas,r8a7779-mstp-clocks" for R8A7779 (R-Car H1) MSTP gate clocks
     - "renesas,r8a7790-mstp-clocks" for R8A7790 (R-Car H2) MSTP gate clocks
     - "renesas,r8a7791-mstp-clocks" for R8A7791 (R-Car M2) MSTP gate clocks
+    - "renesas,r8a7794-mstp-clocks" for R8A7794 (R-Car E2) MSTP gate clocks
     - "renesas,sh73a0-mstp-clocks" for SH73A0 (SH-MobileAG5) MSTP gate clocks
     - "renesas,cpg-mstp-clock" for generic MSTP gate clocks
   - reg: Base address and length of the I/O mapped registers used by the MSTP
diff --git a/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
index 7b41c2fe54db..e6ad35b894f9 100644
--- a/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,rcar-gen2-cpg-clocks.txt
@@ -8,6 +8,7 @@ Required Properties:
   - compatible: Must be one of
     - "renesas,r8a7790-cpg-clocks" for the r8a7790 CPG
     - "renesas,r8a7791-cpg-clocks" for the r8a7791 CPG
+    - "renesas,r8a7794-cpg-clocks" for the r8a7794 CPG
     - "renesas,rcar-gen2-cpg-clocks" for the generic R-Car Gen2 CPG
 
   - reg: Base address and length of the memory resource used by the CPG
diff --git a/Documentation/devicetree/bindings/clock/sunxi.txt b/Documentation/devicetree/bindings/clock/sunxi.txt
index d3a5c3c6d677..ed116df9c3e7 100644
--- a/Documentation/devicetree/bindings/clock/sunxi.txt
+++ b/Documentation/devicetree/bindings/clock/sunxi.txt
@@ -46,7 +46,11 @@ Required properties:
 	"allwinner,sun6i-a31-apb2-div-clk" - for the APB2 gates on A31
 	"allwinner,sun6i-a31-apb2-gates-clk" - for the APB2 gates on A31
 	"allwinner,sun8i-a23-apb2-gates-clk" - for the APB2 gates on A23
+	"allwinner,sun5i-a13-mbus-clk" - for the MBUS clock on A13
+	"allwinner,sun4i-a10-mmc-output-clk" - for the MMC output clock on A10
+	"allwinner,sun4i-a10-mmc-sample-clk" - for the MMC sample clock on A10
 	"allwinner,sun4i-a10-mod0-clk" - for the module 0 family of clocks
+	"allwinner,sun8i-a23-mbus-clk" - for the MBUS clock on A23
 	"allwinner,sun7i-a20-out-clk" - for the external output clocks
 	"allwinner,sun7i-a20-gmac-clk" - for the GMAC clock module on A20/A31
 	"allwinner,sun4i-a10-usb-clk" - for usb gates + resets on A10 / A20
diff --git a/Documentation/devicetree/bindings/cpufreq/cpufreq-cpu0.txt b/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt
index 366690cb86a3..e41c98ffbccb 100644
--- a/Documentation/devicetree/bindings/cpufreq/cpufreq-cpu0.txt
+++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-dt.txt
@@ -1,8 +1,8 @@
-Generic CPU0 cpufreq driver
+Generic cpufreq driver
 
-It is a generic cpufreq driver for CPU0 frequency management.  It
-supports both uniprocessor (UP) and symmetric multiprocessor (SMP)
-systems which share clock and voltage across all CPUs.
+It is a generic DT based cpufreq driver for frequency management.  It supports
+both uniprocessor (UP) and symmetric multiprocessor (SMP) systems which share
+clock and voltage across all CPUs.
 
 Both required and optional properties listed below must be defined
 under node /cpus/cpu@0.
diff --git a/Documentation/devicetree/bindings/dma/qcom_adm.txt b/Documentation/devicetree/bindings/dma/qcom_adm.txt
new file mode 100644
index 000000000000..9bcab9115982
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/qcom_adm.txt
@@ -0,0 +1,62 @@
+QCOM ADM DMA Controller
+
+Required properties:
+- compatible: must contain "qcom,adm" for IPQ/APQ8064 and MSM8960
+- reg: Address range for DMA registers
+- interrupts: Should contain one interrupt shared by all channels
+- #dma-cells: must be <2>.  First cell denotes the channel number.  Second cell
+  denotes CRCI (client rate control interface) flow control assignment.
+- clocks: Should contain the core clock and interface clock.
+- clock-names: Must contain "core" for the core clock and "iface" for the
+  interface clock.
+- resets: Must contain an entry for each entry in reset names.
+- reset-names: Must include the following entries:
+  - clk
+  - c0
+  - c1
+  - c2
+- qcom,ee: indicates the security domain identifier used in the secure world.
+
+Example:
+		adm_dma: dma@18300000 {
+			compatible = "qcom,adm";
+			reg = <0x18300000 0x100000>;
+			interrupts = <0 170 0>;
+			#dma-cells = <2>;
+
+			clocks = <&gcc ADM0_CLK>, <&gcc ADM0_PBUS_CLK>;
+			clock-names = "core", "iface";
+
+			resets = <&gcc ADM0_RESET>,
+				<&gcc ADM0_C0_RESET>,
+				<&gcc ADM0_C1_RESET>,
+				<&gcc ADM0_C2_RESET>;
+			reset-names = "clk", "c0", "c1", "c2";
+			qcom,ee = <0>;
+		};
+
+DMA clients must use the format descripted in the dma.txt file, using a three
+cell specifier for each channel.
+
+Each dmas request consists of 3 cells:
+ 1. phandle pointing to the DMA controller
+ 2. channel number
+ 3. CRCI assignment, if applicable.  If no CRCI flow control is required, use 0.
+    The CRCI is used for flow control.  It identifies the peripheral device that
+    is the source/destination for the transferred data.
+
+Example:
+
+	spi4: spi@1a280000 {
+		status = "ok";
+		spi-max-frequency = <50000000>;
+
+		pinctrl-0 = <&spi_pins>;
+		pinctrl-names = "default";
+
+		cs-gpios = <&qcom_pinmux 20 0>;
+
+		dmas = <&adm_dma 6 9>,
+			<&adm_dma 5 10>;
+		dma-names = "rx", "tx";
+	};
diff --git a/Documentation/devicetree/bindings/dma/xilinx/xilinx_dma.txt b/Documentation/devicetree/bindings/dma/xilinx/xilinx_dma.txt
new file mode 100644
index 000000000000..2291c4098730
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/xilinx/xilinx_dma.txt
@@ -0,0 +1,65 @@
+Xilinx AXI DMA engine, it does transfers between memory and AXI4 stream
+target devices. It can be configured to have one channel or two channels.
+If configured as two channels, one is to transmit to the device and another
+is to receive from the device.
+
+Required properties:
+- compatible: Should be "xlnx,axi-dma-1.00.a"
+- #dma-cells: Should be <1>, see "dmas" property below
+- reg: Should contain DMA registers location and length.
+- dma-channel child node: Should have atleast one channel and can have upto
+	two channels per device. This node specifies the properties of each
+	DMA channel (see child node properties below).
+
+Optional properties:
+- xlnx,include-sg: Tells whether configured for Scatter-mode in
+	the hardware.
+
+Required child node properties:
+- compatible: It should be either "xlnx,axi-dma-mm2s-channel" or
+	"xlnx,axi-dma-s2mm-channel".
+- interrupts: Should contain per channel DMA interrupts.
+- xlnx,datawidth: Should contain the stream data width, take values
+	{32,64...1024}.
+
+Option child node properties:
+- xlnx,include-dre: Tells whether hardware is configured for Data
+	Realignment Engine.
+
+Example:
+++++++++
+
+axi_dma_0: axidma@40400000 {
+	compatible = "xlnx,axi-dma-1.00.a";
+	#dma_cells = <1>;
+	reg = < 0x40400000 0x10000 >;
+	dma-channel@40400000 {
+		compatible = "xlnx,axi-dma-mm2s-channel";
+		interrupts = < 0 59 4 >;
+		xlnx,datawidth = <0x40>;
+	} ;
+	dma-channel@40400030 {
+		compatible = "xlnx,axi-dma-s2mm-channel";
+		interrupts = < 0 58 4 >;
+		xlnx,datawidth = <0x40>;
+	} ;
+} ;
+
+
+* DMA client
+
+Required properties:
+- dmas: a list of <[DMA device phandle] [Channel ID]> pairs,
+	where Channel ID is '0' for write/tx and '1' for read/rx
+	channel.
+- dma-names: a list of DMA channel names, one per "dmas" entry
+
+Example:
+++++++++
+
+dmatest_0: dmatest@0 {
+	compatible ="xlnx,axi-dma-test-1.00.a";
+	dmas = <&axi_dma_0 0
+		&axi_dma_0 1>;
+	dma-names = "dma0", "dma1";
+} ;
diff --git a/Documentation/devicetree/bindings/drm/tilcdc/panel.txt b/Documentation/devicetree/bindings/drm/tilcdc/panel.txt
index 9301c330d1a6..4ab9e2300907 100644
--- a/Documentation/devicetree/bindings/drm/tilcdc/panel.txt
+++ b/Documentation/devicetree/bindings/drm/tilcdc/panel.txt
@@ -18,6 +18,10 @@ Required properties:
    Documentation/devicetree/bindings/video/display-timing.txt for display
    timing binding details.
 
+Optional properties:
+- backlight: phandle of the backlight device attached to the panel
+- enable-gpios: GPIO pin to enable or disable the panel
+
 Recommended properties:
  - pinctrl-names, pinctrl-0: the pincontrol settings to configure
    muxing properly for pins that connect to TFP410 device
@@ -29,6 +33,9 @@ Example:
 		compatible = "ti,tilcdc,panel";
 		pinctrl-names = "default";
 		pinctrl-0 = <&bone_lcd3_cape_lcd_pins>;
+		backlight = <&backlight>;
+		enable-gpios = <&gpio3 19 0>;
+
 		panel-info {
 			ac-bias           = <255>;
 			ac-bias-intrpt    = <0>;
diff --git a/Documentation/devicetree/bindings/gpio/gpio-dsp-keystone.txt b/Documentation/devicetree/bindings/gpio/gpio-dsp-keystone.txt
new file mode 100644
index 000000000000..6c7e6c7302f5
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-dsp-keystone.txt
@@ -0,0 +1,39 @@
+Keystone 2 DSP GPIO controller bindings
+
+HOST OS userland running on ARM can send interrupts to DSP cores using
+the DSP GPIO controller IP. It provides 28 IRQ signals per each DSP core.
+This is one of the component used by the IPC mechanism used on Keystone SOCs.
+
+For example TCI6638K2K SoC has 8 DSP GPIO controllers:
+ - 8 for C66x CorePacx CPUs 0-7
+
+Keystone 2 DSP GPIO controller has specific features:
+- each GPIO can be configured only as output pin;
+- setting GPIO value to 1 causes IRQ generation on target DSP core;
+- reading pin value returns 0 - if IRQ was handled or 1 - IRQ is still
+  pending.
+
+Required Properties:
+- compatible: should be "ti,keystone-dsp-gpio"
+- ti,syscon-dev: phandle/offset pair. The phandle to syscon used to
+  access device state control registers and the offset of device's specific
+  registers within device state control registers range.
+- gpio-controller: Marks the device node as a gpio controller.
+- #gpio-cells: Should be 2.
+
+Please refer to gpio.txt in this directory for details of the common GPIO
+bindings used by client devices.
+
+Example:
+	dspgpio0: keystone_dsp_gpio@02620240 {
+		compatible = "ti,keystone-dsp-gpio";
+		ti,syscon-dev = <&devctrl 0x240>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
+
+	dsp0: dsp0 {
+		compatible = "linux,rproc-user";
+		...
+		kick-gpio = <&dspgpio0 27>;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
new file mode 100644
index 000000000000..b9a42f294dd0
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
@@ -0,0 +1,39 @@
+* NXP PCA953x I2C GPIO multiplexer
+
+Required properties:
+ - compatible: Has to contain one of the following:
+	nxp,pca9505
+	nxp,pca9534
+	nxp,pca9535
+	nxp,pca9536
+	nxp,pca9537
+	nxp,pca9538
+	nxp,pca9539
+	nxp,pca9554
+	nxp,pca9555
+	nxp,pca9556
+	nxp,pca9557
+	nxp,pca9574
+	nxp,pca9575
+	nxp,pca9698
+	maxim,max7310
+	maxim,max7312
+	maxim,max7313
+	maxim,max7315
+	ti,pca6107
+	ti,tca6408
+	ti,tca6416
+	ti,tca6424
+	exar,xra1202
+
+Example:
+
+
+	gpio@20 {
+		compatible = "nxp,pca9505";
+		reg = <0x20>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_pca9505>;
+		interrupt-parent = <&gpio3>;
+		interrupts = <23 IRQ_TYPE_LEVEL_LOW>;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-restart.txt b/Documentation/devicetree/bindings/gpio/gpio-restart.txt
new file mode 100644
index 000000000000..af3701bc15c4
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-restart.txt
@@ -0,0 +1,54 @@
+Drive a GPIO line that can be used to restart the system from a restart
+handler.
+
+This binding supports level and edge triggered reset.  At driver load
+time, the driver will request the given gpio line and install a restart
+handler. If the optional properties 'open-source' is not found, the GPIO line
+will be driven in the inactive state.  Otherwise its not driven until
+the restart is initiated.
+
+When the system is restarted, the restart handler will be invoked in
+priority order.  The gpio is configured as an output, and driven active,
+triggering a level triggered reset condition. This will also cause an
+inactive->active edge condition, triggering positive edge triggered
+reset. After a delay specified by active-delay, the GPIO is set to
+inactive, thus causing an active->inactive edge, triggering negative edge
+triggered reset. After a delay specified by inactive-delay, the GPIO
+is driven active again.  After a delay specified by wait-delay, the
+restart handler completes allowing other restart handlers to be attempted.
+
+Required properties:
+- compatible : should be "gpio-restart".
+- gpios : The GPIO to set high/low, see "gpios property" in
+  Documentation/devicetree/bindings/gpio/gpio.txt. If the pin should be
+  low to reset the board set it to "Active Low", otherwise set
+  gpio to "Active High".
+
+Optional properties:
+- open-source : Treat the GPIO as being open source and defer driving
+  it to when the restart is initiated.  If this optional property is not
+  specified, the GPIO is initialized as an output in its inactive state.
+- priority : A priority ranging from 0 to 255 (default 128) according to
+  the following guidelines:
+	0:	Restart handler of last resort, with limited restart
+		capabilities
+	128:	Default restart handler; use if no other restart handler is
+		expected to be available, and/or if restart functionality is
+		sufficient to restart the entire system
+	255:	Highest priority restart handler, will preempt all other
+		restart handlers
+- active-delay: Delay (default 100) to wait after driving gpio active [ms]
+- inactive-delay: Delay (default 100) to wait after driving gpio inactive [ms]
+- wait-delay: Delay (default 3000) to wait after completing restart
+  sequence [ms]
+
+Examples:
+
+gpio-restart {
+	compatible = "gpio-restart";
+	gpios = <&gpio 4 0>;
+	priority = <128>;
+	active-delay = <100>;
+	inactive-delay = <100>;
+	wait-delay = <3000>;
+};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-xgene.txt b/Documentation/devicetree/bindings/gpio/gpio-xgene.txt
new file mode 100644
index 000000000000..86dbb05e7758
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-xgene.txt
@@ -0,0 +1,22 @@
+APM X-Gene SoC GPIO controller bindings
+
+This is a gpio controller that is part of the flash controller.
+This gpio controller controls a total of 48 gpios.
+
+Required properties:
+- compatible: "apm,xgene-gpio" for X-Gene GPIO controller
+- reg: Physical base address and size of the controller's registers
+- #gpio-cells: Should be two.
+	- first cell is the pin number
+	- second cell is used to specify the gpio polarity:
+		0 = active high
+		1 = active low
+- gpio-controller: Marks the device node as a GPIO controller.
+
+Example:
+	gpio0: gpio0@1701c000 {
+		compatible = "apm,xgene-gpio";
+		reg = <0x0 0x1701c000 0x0 0x40>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/mrvl-gpio.txt b/Documentation/devicetree/bindings/gpio/mrvl-gpio.txt
index 66416261e14d..b2afdb27adeb 100644
--- a/Documentation/devicetree/bindings/gpio/mrvl-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/mrvl-gpio.txt
@@ -19,7 +19,7 @@ Required properties:
 - gpio-controller : Marks the device node as a gpio controller.
 - #gpio-cells : Should be one.  It is the pin number.
 
-Example:
+Example for a MMP platform:
 
 	gpio: gpio@d4019000 {
 		compatible = "marvell,mmp-gpio";
@@ -32,6 +32,19 @@ Example:
 		#interrupt-cells = <1>;
       };
 
+Example for a PXA3xx platform:
+
+	gpio: gpio@40e00000 {
+		compatible = "intel,pxa3xx-gpio";
+		reg = <0x40e00000 0x10000>;
+		interrupt-names = "gpio0", "gpio1", "gpio_mux";
+		interrupts = <8 9 10>;
+		gpio-controller;
+		#gpio-cells = <0x2>;
+		interrupt-controller;
+		#interrupt-cells = <0x2>;
+	};
+
 * Marvell Orion GPIO Controller
 
 Required properties:
diff --git a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
index 2391e5c41999..fcca8e744f41 100644
--- a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
+++ b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
@@ -25,6 +25,9 @@ Requires node properties:
 - "io-channels"	Channel node of ADC to be used for
 		conversion.
 
+Optional node properties:
+- "#thermal-sensor-cells" Used to expose itself to thermal fw.
+
 Read more about iio bindings at
 	Documentation/devicetree/bindings/iio/iio-bindings.txt
 
diff --git a/Documentation/devicetree/bindings/i2c/ti,bq32k.txt b/Documentation/devicetree/bindings/i2c/ti,bq32k.txt
new file mode 100644
index 000000000000..e204906b9ad3
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/ti,bq32k.txt
@@ -0,0 +1,18 @@
+* TI BQ32000                I2C Serial Real-Time Clock
+
+Required properties:
+- compatible: Should contain "ti,bq32000".
+- reg: I2C address for chip
+
+Optional properties:
+- trickle-resistor-ohms : Selected resistor for trickle charger
+       Values usable are 1120 and 20180
+       Should be given if trickle charger should be enabled
+- trickle-diode-disable : Do not use internal trickle charger diode
+       Should be given if internal trickle charger diode should be disabled
+Example:
+       bq32000: rtc@68 {
+               compatible = "ti,bq32000";
+               trickle-resistor-ohms = <1120>;
+               reg = <0x68>;
+       };
diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
index 5af3d9df6ecb..fbde415078e6 100644
--- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt
+++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
@@ -35,7 +35,6 @@ catalyst,24c32		i2c serial eeprom
 cirrus,cs42l51		Cirrus Logic CS42L51 audio codec
 dallas,ds1307		64 x 8, Serial, I2C Real-Time Clock
 dallas,ds1338		I2C RTC with 56-Byte NV RAM
-dallas,ds1339		I2C Serial Real-Time Clock
 dallas,ds1340		I2C RTC with Trickle Charger
 dallas,ds1374		I2C, 32-Bit Binary Counter Watchdog RTC with Trickle Charger and Reset Input/Output
 dallas,ds1631		High-Precision Digital Thermometer
diff --git a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
index 2742e9cfd6b1..f292917fa00d 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
@@ -2,7 +2,7 @@
 
 Required properties:
 - compatible: Should be "atmel,<chip>-aic"
-  <chip> can be "at91rm9200" or "sama5d3"
+  <chip> can be "at91rm9200", "sama5d3" or "sama5d4"
 - interrupt-controller: Identifies the node as an interrupt controller.
 - interrupt-parent: For single AIC system, it is an empty property.
 - #interrupt-cells: The number of cells to define the interrupts. It should be 3.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.txt
new file mode 100644
index 000000000000..ff812a8a82bc
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.txt
@@ -0,0 +1,86 @@
+Broadcom BCM7120-style Level 2 interrupt controller
+
+This interrupt controller hardware is a second level interrupt controller that
+is hooked to a parent interrupt controller: e.g: ARM GIC for ARM-based
+platforms. It can be found on BCM7xxx products starting with BCM7120.
+
+Such an interrupt controller has the following hardware design:
+
+- outputs multiple interrupts signals towards its interrupt controller parent
+
+- controls how some of the interrupts will be flowing, whether they will
+  directly output an interrupt signal towards the interrupt controller parent,
+  or if they will output an interrupt signal at this 2nd level interrupt
+  controller, in particular for UARTs
+
+- not all 32-bits within the interrupt controller actually map to an interrupt
+
+The typical hardware layout for this controller is represented below:
+
+2nd level interrupt line		Outputs for the parent controller (e.g: ARM GIC)
+
+0 -----[ MUX ] ------------|==========> GIC interrupt 75
+          \-----------\
+                       |
+1 -----[ MUX ] --------)---|==========> GIC interrupt 76
+          \------------|
+                       |
+2 -----[ MUX ] --------)---|==========> GIC interrupt 77
+          \------------|
+                       |
+3 ---------------------|
+4 ---------------------|
+5 ---------------------|
+7 ---------------------|---|===========> GIC interrupt 66
+9 ---------------------|
+10 --------------------|
+11 --------------------/
+
+6 ------------------------\
+                           |===========> GIC interrupt 64
+8 ------------------------/
+
+12 ........................ X
+13 ........................ X 		(not connected)
+..
+31 ........................ X
+
+Required properties:
+
+- compatible: should be "brcm,bcm7120-l2-intc"
+- reg: specifies the base physical address and size of the registers
+- interrupt-controller: identifies the node as an interrupt controller
+- #interrupt-cells: specifies the number of cells needed to encode an interrupt
+  source, should be 1.
+- interrupt-parent: specifies the phandle to the parent interrupt controller
+  this one is cascaded from
+- interrupts: specifies the interrupt line(s) in the interrupt-parent controller
+  node, valid values depend on the type of parent interrupt controller
+- brcm,int-map-mask: 32-bits bit mask describing how many and which interrupts
+  are wired to this 2nd level interrupt controller, and how they match their
+  respective interrupt parents. Should match exactly the number of interrupts
+  specified in the 'interrupts' property.
+
+Optional properties:
+
+- brcm,irq-can-wake: if present, this means the L2 controller can be used as a
+  wakeup source for system suspend/resume.
+
+- brcm,int-fwd-mask: if present, a 32-bits bit mask to configure for the
+  interrupts which have a mux gate, typically UARTs. Setting these bits will
+  make their respective interrupts outputs bypass this 2nd level interrupt
+  controller completely, it completely transparent for the interrupt controller
+  parent
+
+Example:
+
+irq0_intc: interrupt-controller@f0406800 {
+	compatible = "brcm,bcm7120-l2-intc";
+	interrupt-parent = <&intc>;
+	#interrupt-cells = <1>;
+	reg = <0xf0406800 0x8>;
+	interrupt-controller;
+	interrupts = <0x0 0x42 0x0>, <0x0 0x40 0x0>;
+	brcm,int-map-mask = <0xeb8>, <0x140>;
+	brcm,int-fwd-mask = <0x7>;
+};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt
index 1f8b0c507c26..c73acd060093 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt
@@ -2,7 +2,13 @@ DT bindings for the R-/SH-Mobile irqpin controller
 
 Required properties:
 
-- compatible: has to be "renesas,intc-irqpin"
+- compatible: has to be "renesas,intc-irqpin-<soctype>", "renesas,intc-irqpin"
+  as fallback.
+  Examples with soctypes are:
+    - "renesas,intc-irqpin-r8a7740" (R-Mobile A1)
+    - "renesas,intc-irqpin-r8a7778" (R-Car M1A)
+    - "renesas,intc-irqpin-r8a7779" (R-Car H1)
+    - "renesas,intc-irqpin-sh73a0" (SH-Mobile AG5)
 - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
   interrupts.txt in this directory
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
new file mode 100644
index 000000000000..1a88e62228e5
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
@@ -0,0 +1,32 @@
+DT bindings for the R-Mobile/R-Car interrupt controller
+
+Required properties:
+
+- compatible: has to be "renesas,irqc-<soctype>", "renesas,irqc" as fallback.
+  Examples with soctypes are:
+    - "renesas,irqc-r8a73a4" (R-Mobile AP6)
+    - "renesas,irqc-r8a7790" (R-Car H2)
+    - "renesas,irqc-r8a7791" (R-Car M2-W)
+    - "renesas,irqc-r8a7792" (R-Car V2H)
+    - "renesas,irqc-r8a7793" (R-Car M2-N)
+    - "renesas,irqc-r8a7794" (R-Car E2)
+- #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
+  interrupts.txt in this directory
+
+Optional properties:
+
+- any properties, listed in interrupts.txt, and any standard resource allocation
+  properties
+
+Example:
+
+	irqc0: interrupt-controller@e61c0000 {
+		compatible = "renesas,irqc-r8a7790", "renesas,irqc";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		reg = <0 0xe61c0000 0 0x200>;
+		interrupts = <0 0 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 1 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 2 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 3 IRQ_TYPE_LEVEL_HIGH>;
+	};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,keystone-irq.txt b/Documentation/devicetree/bindings/interrupt-controller/ti,keystone-irq.txt
new file mode 100644
index 000000000000..d9bb106bdd16
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,keystone-irq.txt
@@ -0,0 +1,36 @@
+Keystone 2 IRQ controller IP
+
+On Keystone SOCs, DSP cores can send interrupts to ARM
+host using the IRQ controller IP. It provides 28 IRQ signals to ARM.
+The IRQ handler running on HOST OS can identify DSP signal source by
+analyzing SRCCx bits in IPCARx registers. This is one of the component
+used by the IPC mechanism used on Keystone SOCs.
+
+Required Properties:
+- compatible: should be "ti,keystone-irq"
+- ti,syscon-dev : phandle and offset pair. The phandle to syscon used to
+			access device control registers and the offset inside
+			device control registers range.
+- interrupt-controller : Identifies the node as an interrupt controller
+- #interrupt-cells : Specifies the number of cells needed to encode interrupt
+					 source should be 1.
+- interrupts: interrupt reference to primary interrupt controller
+
+Please refer to interrupts.txt in this directory for details of the common
+Interrupt Controllers bindings used by client devices.
+
+Example:
+	kirq0: keystone_irq0@026202a0 {
+		compatible = "ti,keystone-irq";
+		ti,syscon-dev = <&devctrl 0x2a0>;
+		interrupts = <GIC_SPI 4 IRQ_TYPE_EDGE_RISING>;
+		interrupt-controller;
+		#interrupt-cells = <1>;
+	};
+
+	dsp0: dsp0 {
+		compatible = "linux,rproc-user";
+		...
+		interrupt-parent = <&kirq0>;
+		interrupts = <10 2>;
+	};
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.txt b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
index 2d0f7cd867ea..06760503a819 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.txt
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
@@ -14,6 +14,7 @@ conditions.
                         "arm,smmu-v1"
                         "arm,smmu-v2"
                         "arm,mmu-400"
+                        "arm,mmu-401"
                         "arm,mmu-500"
 
                   depending on the particular implementation and/or the
diff --git a/Documentation/devicetree/bindings/media/hix5hd2-ir.txt b/Documentation/devicetree/bindings/media/hix5hd2-ir.txt
new file mode 100644
index 000000000000..fb5e7606643a
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/hix5hd2-ir.txt
@@ -0,0 +1,25 @@
+Device-Tree bindings for hix5hd2 ir IP
+
+Required properties:
+	- compatible: Should contain "hisilicon,hix5hd2-ir".
+	- reg: Base physical address of the controller and length of memory
+	  mapped region.
+	- interrupts: interrupt-specifier for the sole interrupt generated by
+	  the device. The interrupt specifier format depends on the interrupt
+	  controller parent.
+	- clocks: clock phandle and specifier pair.
+	- hisilicon,power-syscon: phandle of syscon used to control power.
+
+Optional properties:
+	- linux,rc-map-name : Remote control map name.
+
+Example node:
+
+	ir: ir@f8001000 {
+		compatible = "hisilicon,hix5hd2-ir";
+		reg = <0xf8001000 0x1000>;
+		interrupts = <0 47 4>;
+		clocks = <&clock HIX5HD2_FIXED_24M>;
+		hisilicon,power-syscon = <&sysctrl>;
+		linux,rc-map-name = "rc-tivo";
+	};
diff --git a/Documentation/devicetree/bindings/mfd/arizona.txt b/Documentation/devicetree/bindings/mfd/arizona.txt
index 5c7e7230984a..7bd1273f571a 100644
--- a/Documentation/devicetree/bindings/mfd/arizona.txt
+++ b/Documentation/devicetree/bindings/mfd/arizona.txt
@@ -42,6 +42,13 @@ Optional properties:
     the chip default will be used.  If present exactly five values must
     be specified.
 
+  - wlf,inmode : A list of INn_MODE register values, where n is the number
+    of input signals. Valid values are 0 (Differential), 1 (Single-ended) and
+    2 (Digital Microphone). If absent, INn_MODE registers set to 0 by default.
+    If present, values must be specified less than or equal to the number of
+    input singals. If values less than the number of input signals, elements
+    that has not been specifed are set to 0 by default.
+
   - DCVDD-supply, MICVDD-supply : Power supplies, only need to be specified if
     they are being externally supplied. As covered in
     Documentation/devicetree/bindings/regulator/regulator.txt
diff --git a/Documentation/devicetree/bindings/mfd/atmel-gpbr.txt b/Documentation/devicetree/bindings/mfd/atmel-gpbr.txt
new file mode 100644
index 000000000000..a28569540683
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/atmel-gpbr.txt
@@ -0,0 +1,15 @@
+* Device tree bindings for Atmel GPBR (General Purpose Backup Registers)
+
+The GPBR are a set of battery-backed registers.
+
+Required properties:
+- compatible:		"atmel,at91sam9260-gpbr", "syscon"
+- reg:			contains offset/length value of the GPBR memory
+			region.
+
+Example:
+
+gpbr: gpbr@fffffd50 {
+	compatible = "atmel,at91sam9260-gpbr", "syscon";
+	reg = <0xfffffd50 0x10>;
+};
diff --git a/Documentation/devicetree/bindings/mfd/hi6421.txt b/Documentation/devicetree/bindings/mfd/hi6421.txt
new file mode 100644
index 000000000000..0d5a4466a494
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/hi6421.txt
@@ -0,0 +1,38 @@
+* HI6421 Multi-Functional Device (MFD), by HiSilicon Ltd.
+
+Required parent device properties:
+- compatible	: contains "hisilicon,hi6421-pmic";
+- reg		: register range space of hi6421;
+
+Supported Hi6421 sub-devices include:
+
+Device                     IRQ Names              Supply Names   Description
+------                     ---------              ------------   -----------
+regulators               :  None                 : None         : Regulators
+
+Required child device properties:
+None.
+
+Example:
+	hi6421 {
+		compatible = "hisilicon,hi6421-pmic";
+		reg = <0xfcc00000 0x0180>; /* 0x60 << 2 */
+
+		regulators {
+			// supply for MLC NAND/ eMMC
+			hi6421_vout0_reg: hi6421_vout0 {
+				regulator-name = "VOUT0";
+				regulator-min-microvolt = <2850000>;
+				regulator-max-microvolt = <2850000>;
+			};
+
+			// supply for 26M Oscillator
+			hi6421_vout1_reg: hi6421_vout1 {
+				regulator-name = "VOUT1";
+				regulator-min-microvolt = <1700000>;
+				regulator-max-microvolt = <2000000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mfd/max14577.txt b/Documentation/devicetree/bindings/mfd/max14577.txt
new file mode 100644
index 000000000000..236264c10b92
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/max14577.txt
@@ -0,0 +1,146 @@
+Maxim MAX14577/77836 Multi-Function Device
+
+MAX14577 is a Multi-Function Device with Micro-USB Interface Circuit, Li+
+Battery Charger and SFOUT LDO output for powering USB devices. It is
+interfaced to host controller using I2C.
+
+MAX77836 additionally contains PMIC (with two LDO regulators) and Fuel Gauge.
+
+
+Required properties:
+- compatible : Must be "maxim,max14577" or "maxim,max77836".
+- reg : I2C slave address for the max14577 chip (0x25 for max14577/max77836)
+- interrupts : IRQ line for the chip.
+- interrupt-parent :  The parent interrupt controller.
+
+
+Required nodes:
+ - charger :
+	Node for configuring the charger driver.
+	Required properties:
+		- compatible : "maxim,max14577-charger"
+			or "maxim,max77836-charger"
+		- maxim,fast-charge-uamp : Current in uA for Fast Charge;
+			Valid values:
+			- for max14577: 90000 - 950000;
+			- for max77836: 45000 - 475000;
+		- maxim,eoc-uamp : Current in uA for End-Of-Charge mode;
+			Valid values:
+			- for max14577: 50000 - 200000;
+			- for max77836: 5000 - 100000;
+		- maxim,ovp-uvolt : OverVoltage Protection Threshold in uV;
+			In an overvoltage condition, INT asserts and charging
+			stops. Valid values:
+			- 6000000, 6500000, 7000000, 7500000;
+		- maxim,constant-uvolt : Battery Constant Voltage in uV;
+			Valid values:
+			- 4000000 - 4280000 (step by 20000);
+			- 4350000;
+
+
+Optional nodes:
+- max14577-muic/max77836-muic :
+	Node used only by extcon consumers.
+	Required properties:
+		- compatible : "maxim,max14577-muic" or "maxim,max77836-muic"
+
+- regulators :
+	Required properties:
+		- compatible : "maxim,max14577-regulator"
+			or "maxim,max77836-regulator"
+
+	May contain a sub-node per regulator from the list below. Each
+	sub-node should contain the constraints and initialization information
+	for that regulator. See regulator.txt for a description of standard
+	properties for these sub-nodes.
+
+	List of valid regulator names:
+	- for max14577: CHARGER, SAFEOUT.
+	- for max77836: CHARGER, SAFEOUT, LDO1, LDO2.
+
+	The SAFEOUT is a fixed voltage regulator so there is no need to specify
+	voltages for it.
+
+
+Example:
+
+#include <dt-bindings/interrupt-controller/irq.h>
+
+max14577@25 {
+	compatible = "maxim,max14577";
+	reg = <0x25>;
+	interrupt-parent = <&gpx1>;
+	interrupts = <5 IRQ_TYPE_NONE>;
+
+	muic: max14577-muic {
+		compatible = "maxim,max14577-muic";
+	};
+
+	regulators {
+		compatible = "maxim,max14577-regulator";
+
+		SAFEOUT {
+			regulator-name = "SAFEOUT";
+		};
+		CHARGER {
+			regulator-name = "CHARGER";
+			regulator-min-microamp = <90000>;
+			regulator-max-microamp = <950000>;
+			regulator-boot-on;
+		};
+	};
+
+	charger {
+		compatible = "maxim,max14577-charger";
+
+		maxim,constant-uvolt = <4350000>;
+		maxim,fast-charge-uamp = <450000>;
+		maxim,eoc-uamp = <50000>;
+		maxim,ovp-uvolt = <6500000>;
+	};
+};
+
+
+max77836@25 {
+	compatible = "maxim,max77836";
+	reg = <0x25>;
+	interrupt-parent = <&gpx1>;
+	interrupts = <5 IRQ_TYPE_NONE>;
+
+	muic: max77836-muic {
+		compatible = "maxim,max77836-muic";
+	};
+
+	regulators {
+		compatible = "maxim,max77836-regulator";
+
+		SAFEOUT {
+			regulator-name = "SAFEOUT";
+		};
+		CHARGER {
+			regulator-name = "CHARGER";
+			regulator-min-microamp = <90000>;
+			regulator-max-microamp = <950000>;
+			regulator-boot-on;
+		};
+		LDO1 {
+			regulator-name = "LDO1";
+			regulator-min-microvolt = <2700000>;
+			regulator-max-microvolt = <2700000>;
+		};
+		LDO2 {
+			regulator-name = "LDO2";
+			regulator-min-microvolt = <800000>;
+			regulator-max-microvolt = <3950000>;
+		};
+	};
+
+	charger {
+		compatible = "maxim,max77836-charger";
+
+		maxim,constant-uvolt = <4350000>;
+		maxim,fast-charge-uamp = <225000>;
+		maxim,eoc-uamp = <7500>;
+		maxim,ovp-uvolt = <6500000>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.txt b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.txt
new file mode 100644
index 000000000000..7182b8857f57
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.txt
@@ -0,0 +1,64 @@
+          Qualcomm SPMI PMICs multi-function device bindings
+
+The Qualcomm SPMI series presently includes PM8941, PM8841 and PMA8084
+PMICs.  These PMICs use a QPNP scheme through SPMI interface.
+QPNP is effectively a partitioning scheme for dividing the SPMI extended
+register space up into logical pieces, and set of fixed register
+locations/definitions within these regions, with some of these regions
+specifically used for interrupt handling.
+
+The QPNP PMICs are used with the Qualcomm Snapdragon series SoCs, and are
+interfaced to the chip via the SPMI (System Power Management Interface) bus.
+Support for multiple independent functions are implemented by splitting the
+16-bit SPMI slave address space into 256 smaller fixed-size regions, 256 bytes
+each. A function can consume one or more of these fixed-size register regions.
+
+Required properties:
+- compatible:      Should contain one of:
+                     "qcom,pm8941"
+                     "qcom,pm8841"
+                     "qcom,pma8084"
+                     or generalized "qcom,spmi-pmic".
+- reg:             Specifies the SPMI USID slave address for this device.
+                   For more information see:
+                   Documentation/devicetree/bindings/spmi/spmi.txt
+
+Required properties for peripheral child nodes:
+- compatible:      Should contain "qcom,xxx", where "xxx" is a peripheral name.
+
+Optional properties for peripheral child nodes:
+- interrupts:      Interrupts are specified as a 4-tuple. For more information
+                   see:
+                   Documentation/devicetree/bindings/spmi/qcom,spmi-pmic-arb.txt
+- interrupt-names: Corresponding interrupt name to the interrupts property
+
+Each child node of SPMI slave id represents a function of the PMIC. In the
+example below the rtc device node represents a peripheral of pm8941
+SID = 0. The regulator device node represents a peripheral of pm8941 SID = 1.
+
+Example:
+
+	spmi {
+		compatible = "qcom,spmi-pmic-arb";
+
+		pm8941@0 {
+			compatible = "qcom,pm8941", "qcom,spmi-pmic";
+			reg = <0x0 SPMI_USID>;
+
+			rtc {
+				compatible = "qcom,rtc";
+				interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>;
+				interrupt-names = "alarm";
+			};
+		};
+
+		pm8941@1 {
+			compatible = "qcom,pm8941", "qcom,spmi-pmic";
+			reg = <0x1 SPMI_USID>;
+
+			regulator {
+				compatible = "qcom,regulator";
+				regulator-name = "8941_boost";
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mfd/qcom,pm8xxx.txt b/Documentation/devicetree/bindings/mfd/qcom-pm8xxx.txt
index 03518dc8b6bd..f24f33409164 100644
--- a/Documentation/devicetree/bindings/mfd/qcom,pm8xxx.txt
+++ b/Documentation/devicetree/bindings/mfd/qcom-pm8xxx.txt
@@ -61,6 +61,7 @@ The below bindings specify the set of valid subnodes.
 	Definition: must be one of:
 		    "qcom,pm8058-rtc"
 		    "qcom,pm8921-rtc"
+		    "qcom,pm8941-rtc"
 
 - reg:
 	Usage: required
diff --git a/Documentation/devicetree/bindings/mfd/rk808.txt b/Documentation/devicetree/bindings/mfd/rk808.txt
new file mode 100644
index 000000000000..9e6e2592e5c8
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/rk808.txt
@@ -0,0 +1,177 @@
+RK808 Power Management Integrated Circuit
+
+Required properties:
+- compatible: "rockchip,rk808"
+- reg: I2C slave address
+- interrupt-parent: The parent interrupt controller.
+- interrupts: the interrupt outputs of the controller.
+- #clock-cells: from common clock binding; shall be set to 1 (multiple clock
+  outputs). See <dt-bindings/clock/rockchip,rk808.h> for clock IDs.
+
+Optional properties:
+- clock-output-names: From common clock binding to override the
+  default output clock name
+- rockchip,system-power-controller: Telling whether or not this pmic is controlling
+  the system power.
+- vcc1-supply:  The input supply for DCDC_REG1
+- vcc2-supply:  The input supply for DCDC_REG2
+- vcc3-supply:  The input supply for DCDC_REG3
+- vcc4-supply:  The input supply for DCDC_REG4
+- vcc6-supply:  The input supply for LDO_REG1 and LDO_REG2
+- vcc7-supply:  The input supply for LDO_REG3 and LDO_REG7
+- vcc8-supply:  The input supply for SWITCH_REG1
+- vcc9-supply:  The input supply for LDO_REG4 and LDO_REG5
+- vcc10-supply: The input supply for LDO_REG6
+- vcc11-supply: The input supply for LDO_REG8
+- vcc12-supply: The input supply for SWITCH_REG2
+
+Regulators: All the regulators of RK808 to be instantiated shall be
+listed in a child node named 'regulators'. Each regulator is represented
+by a child node of the 'regulators' node.
+
+	regulator-name {
+		/* standard regulator bindings here */
+	};
+
+Following regulators of the RK808 PMIC block are supported. Note that
+the 'n' in regulator name, as in DCDC_REGn or LDOn, represents the DCDC or LDO
+number as described in RK808 datasheet.
+
+	- DCDC_REGn
+		- valid values for n are 1 to 4.
+	- LDO_REGn
+		- valid values for n are 1 to 8.
+	- SWITCH_REGn
+		- valid values for n are 1 to 2
+
+Standard regulator bindings are used inside regulator subnodes. Check
+  Documentation/devicetree/bindings/regulator/regulator.txt
+for more details
+
+Example:
+	rk808: pmic@1b {
+		compatible = "rockchip,rk808";
+		clock-output-names = "xin32k", "rk808-clkout2";
+		interrupt-parent = <&gpio0>;
+		interrupts = <4 IRQ_TYPE_LEVEL_LOW>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pmic_int>;
+		reg = <0x1b>;
+		rockchip,system-power-controller;
+		wakeup-source;
+		#clock-cells = <1>;
+
+		vcc8-supply = <&vcc_18>;
+		vcc9-supply = <&vcc_io>;
+		vcc10-supply = <&vcc_io>;
+		vcc12-supply = <&vcc_io>;
+		vddio-supply = <&vccio_pmu>;
+
+		regulators {
+			vdd_cpu: DCDC_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <750000>;
+				regulator-max-microvolt = <1300000>;
+				regulator-name = "vdd_arm";
+			};
+
+			vdd_gpu: DCDC_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <850000>;
+				regulator-max-microvolt = <1250000>;
+				regulator-name = "vdd_gpu";
+			};
+
+			vcc_ddr: DCDC_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vcc_ddr";
+			};
+
+			vcc_io: DCDC_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc_io";
+			};
+
+			vccio_pmu: LDO_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_pmu";
+			};
+
+			vcc_tp: LDO_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcc_tp";
+			};
+
+			vdd_10: LDO_REG3 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-name = "vdd_10";
+			};
+
+			vcc18_lcd: LDO_REG4 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc18_lcd";
+			};
+
+			vccio_sd: LDO_REG5 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vccio_sd";
+			};
+
+			vdd10_lcd: LDO_REG6 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <1000000>;
+				regulator-name = "vdd10_lcd";
+			};
+
+			vcc_18: LDO_REG7 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-name = "vcc_18";
+			};
+
+			vcca_codec: LDO_REG8 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-name = "vcca_codec";
+			};
+
+			vcc_wl: SWITCH_REG1 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vcc_wl";
+			};
+
+			vcc_lcd: SWITCH_REG2 {
+				regulator-always-on;
+				regulator-boot-on;
+				regulator-name = "vcc_lcd";
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mfd/rn5t618.txt b/Documentation/devicetree/bindings/mfd/rn5t618.txt
new file mode 100644
index 000000000000..937785a3eddc
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/rn5t618.txt
@@ -0,0 +1,36 @@
+* Ricoh RN5T618 PMIC
+
+Ricoh RN5T618 is a power management IC which integrates 3 step-down
+DCDC converters, 7 low-dropout regulators, a Li-ion battery charger,
+fuel gauge, ADC, GPIOs and a watchdog timer. It can be controlled
+through a I2C interface.
+
+Required properties:
+ - compatible: should be "ricoh,rn5t618"
+ - reg: the I2C slave address of the device
+
+Sub-nodes:
+ - regulators: the node is required if the regulator functionality is
+   needed. The valid regulator names are: DCDC1, DCDC2, DCDC3, LDO1,
+   LDO2, LDO3, LDO4, LDO5, LDORTC1 and LDORTC2.
+   The common bindings for each individual regulator can be found in:
+   Documentation/devicetree/bindings/regulator/regulator.txt
+
+Example:
+
+	pmic@32 {
+		compatible = "ricoh,rn5t618";
+		reg = <0x32>;
+
+		regulators {
+			DCDC1 {
+				regulator-min-microvolt = <1050000>;
+				regulator-max-microvolt = <1050000>;
+			};
+
+			DCDC2 {
+				regulator-min-microvolt = <1175000>;
+				regulator-max-microvolt = <1175000>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mfd/stmpe.txt b/Documentation/devicetree/bindings/mfd/stmpe.txt
index 56edb5520685..3fb68bfefc8b 100644
--- a/Documentation/devicetree/bindings/mfd/stmpe.txt
+++ b/Documentation/devicetree/bindings/mfd/stmpe.txt
@@ -13,6 +13,7 @@ Optional properties:
  - interrupt-parent             : Specifies which IRQ controller we're connected to
  - wakeup-source                : Marks the input device as wakable
  - st,autosleep-timeout         : Valid entries (ms); 4, 16, 32, 64, 128, 256, 512 and 1024
+ - irq-gpio                     : If present, which GPIO to use for event IRQ
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mfd/twl4030-power.txt b/Documentation/devicetree/bindings/mfd/twl4030-power.txt
index b9ee7b98d3e2..3d19963312ce 100644
--- a/Documentation/devicetree/bindings/mfd/twl4030-power.txt
+++ b/Documentation/devicetree/bindings/mfd/twl4030-power.txt
@@ -23,8 +23,13 @@ down during off-idle. Note that this does not work on all boards
 depending on how the external oscillator is wired.
 
 Optional properties:
-- ti,use_poweroff: With this flag, the chip will initiates an ACTIVE-to-OFF or
-		   SLEEP-to-OFF transition when the system poweroffs.
+
+- ti,system-power-controller: This indicates that TWL4030 is the
+  power supply master of the system. With this flag, the chip will
+  initiate an ACTIVE-to-OFF or SLEEP-to-OFF transition when the
+  system poweroffs.
+
+- ti,use_poweroff: Deprecated name for ti,system-power-controller
 
 Example:
 &i2c1 {
diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt
index 431716e37a39..b52628b18a53 100644
--- a/Documentation/devicetree/bindings/mmc/mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc.txt
@@ -40,6 +40,8 @@ Optional properties:
 - mmc-hs200-1_2v: eMMC HS200 mode(1.2V I/O) is supported
 - mmc-hs400-1_8v: eMMC HS400 mode(1.8V I/O) is supported
 - mmc-hs400-1_2v: eMMC HS400 mode(1.2V I/O) is supported
+- dsr: Value the card's (optional) Driver Stage Register (DSR) should be
+  programmed with. Valid range: [0 .. 0xffff].
 
 *NOTE* on CD and WP polarity. To use common for all SD/MMC host controllers line
 polarity properties, we have to fix the meaning of the "normal" and "inverted"
diff --git a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
index c559f3f36309..c327c2d6f23d 100644
--- a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
@@ -10,12 +10,14 @@ extensions to the Synopsys Designware Mobile Storage Host Controller.
 Required Properties:
 
 * compatible: should be
-	- "rockchip,rk2928-dw-mshc": for Rockchip RK2928 and following
+	- "rockchip,rk2928-dw-mshc": for Rockchip RK2928 and following,
+							before RK3288
+	- "rockchip,rk3288-dw-mshc": for Rockchip RK3288
 
 Example:
 
 	rkdwmmc0@12200000 {
-		compatible = "rockchip,rk2928-dw-mshc";
+		compatible = "rockchip,rk3288-dw-mshc";
 		reg = <0x12200000 0x1000>;
 		interrupts = <0 75 0>;
 		#address-cells = <1>;
diff --git a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
index fa0f327cde01..400b640fabc7 100644
--- a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
@@ -19,6 +19,9 @@ Required properties:
 		"renesas,sdhi-r8a7779" - SDHI IP on R8A7779 SoC
 		"renesas,sdhi-r8a7790" - SDHI IP on R8A7790 SoC
 		"renesas,sdhi-r8a7791" - SDHI IP on R8A7791 SoC
+		"renesas,sdhi-r8a7792" - SDHI IP on R8A7792 SoC
+		"renesas,sdhi-r8a7793" - SDHI IP on R8A7793 SoC
+		"renesas,sdhi-r8a7794" - SDHI IP on R8A7794 SoC
 
 Optional properties:
 - toshiba,mmc-wrprotect-disable: write-protect detection is unavailable
diff --git a/Documentation/devicetree/bindings/mtd/atmel-nand.txt b/Documentation/devicetree/bindings/mtd/atmel-nand.txt
index c4728839d0c1..6edc3b616e98 100644
--- a/Documentation/devicetree/bindings/mtd/atmel-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/atmel-nand.txt
@@ -36,6 +36,7 @@ Optional properties:
     - reg : should specify the address and size used for NFC command registers,
             NFC registers and NFC Sram. NFC Sram address and size can be absent
             if don't want to use it.
+    - clocks: phandle to the peripheral clock
   - Optional properties:
     - atmel,write-by-sram: boolean to enable NFC write by sram.
 
@@ -98,6 +99,7 @@ nand0: nand@40000000 {
 		compatible = "atmel,sama5d3-nfc";
 		#address-cells = <1>;
 		#size-cells = <1>;
+		clocks = <&hsmc_clk>
 		reg = <
 			0x70000000 0x10000000	/* NFC Command Registers */
 			0xffffc000 0x00000070	/* NFC HSMC regs */
diff --git a/Documentation/devicetree/bindings/mtd/mtd-physmap.txt b/Documentation/devicetree/bindings/mtd/mtd-physmap.txt
index 61c5ec850f2f..6b9f680cb579 100644
--- a/Documentation/devicetree/bindings/mtd/mtd-physmap.txt
+++ b/Documentation/devicetree/bindings/mtd/mtd-physmap.txt
@@ -4,8 +4,8 @@ Flash chips (Memory Technology Devices) are often used for solid state
 file systems on embedded devices.
 
  - compatible : should contain the specific model of mtd chip(s)
-   used, if known, followed by either "cfi-flash", "jedec-flash"
-   or "mtd-ram".
+   used, if known, followed by either "cfi-flash", "jedec-flash",
+   "mtd-ram" or "mtd-rom".
  - reg : Address range(s) of the mtd chip(s)
    It's possible to (optionally) define multiple "reg" tuples so that
    non-identical chips can be described in one node.
diff --git a/Documentation/devicetree/bindings/panel/auo,b101xtn01.txt b/Documentation/devicetree/bindings/panel/auo,b101xtn01.txt
new file mode 100644
index 000000000000..889d511d66c9
--- /dev/null
+++ b/Documentation/devicetree/bindings/panel/auo,b101xtn01.txt
@@ -0,0 +1,7 @@
+AU Optronics Corporation 10.1" WXGA TFT LCD panel
+
+Required properties:
+- compatible: should be "auo,b101xtn01"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/pci/designware-pcie.txt b/Documentation/devicetree/bindings/pci/designware-pcie.txt
index ed0d9b9fff2b..9f4faa8e8d00 100644
--- a/Documentation/devicetree/bindings/pci/designware-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/designware-pcie.txt
@@ -23,3 +23,6 @@ Required properties:
 
 Optional properties:
 - reset-gpio: gpio pin number of power good signal
+- bus-range: PCI bus numbers covered (it is recommended for new devicetrees to
+  specify this property, to keep backwards compatibility a range of 0x00-0xff
+  is assumed if not present)
diff --git a/Documentation/devicetree/bindings/pci/fsl,pci.txt b/Documentation/devicetree/bindings/pci/fsl,pci.txt
new file mode 100644
index 000000000000..d8ac4a768e7e
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/fsl,pci.txt
@@ -0,0 +1,27 @@
+* Bus Enumeration by Freescale PCI-X Agent
+
+Typically any Freescale PCI-X bridge hardware strapped into Agent mode
+is prevented from enumerating the bus. The PrPMC form-factor requires
+all mezzanines to be PCI-X Agents, but one per system may still
+enumerate the bus.
+
+The property defined below will allow a PCI-X bridge to be used for bus
+enumeration despite being strapped into Agent mode.
+
+Required properties:
+- fsl,pci-agent-force-enum : There is no value associated with this
+  property. The property itself is treated as a boolean.
+
+Example:
+
+	/* PCI-X bridge known to be PrPMC Monarch */
+	pci0: pci@ef008000 {
+		fsl,pci-agent-force-enum;
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		compatible = "fsl,mpc8540-pcix", "fsl,mpc8540-pci";
+		device_type = "pci";
+		...
+		...
+	};
diff --git a/Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt b/Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt
index 0823362548dc..d763e047c6ae 100644
--- a/Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/nvidia,tegra20-pcie.txt
@@ -1,7 +1,10 @@
 NVIDIA Tegra PCIe controller
 
 Required properties:
-- compatible: "nvidia,tegra20-pcie" or "nvidia,tegra30-pcie"
+- compatible: Must be one of:
+  - "nvidia,tegra20-pcie"
+  - "nvidia,tegra30-pcie"
+  - "nvidia,tegra124-pcie"
 - device_type: Must be "pci"
 - reg: A list of physical base address and length for each set of controller
   registers. Must contain an entry for each entry in the reg-names property.
@@ -57,6 +60,11 @@ Required properties:
   - afi
   - pcie_x
 
+Required properties on Tegra124 and later:
+- phys: Must contain an entry for each entry in phy-names.
+- phy-names: Must include the following entries:
+  - pcie
+
 Power supplies for Tegra20:
 - avdd-pex-supply: Power supply for analog PCIe logic. Must supply 1.05 V.
 - vdd-pex-supply: Power supply for digital PCIe I/O. Must supply 1.05 V.
@@ -84,6 +92,21 @@ Power supplies for Tegra30:
     - avdd-pexb-supply: Power supply for analog PCIe logic. Must supply 1.05 V.
     - vdd-pexb-supply: Power supply for digital PCIe I/O. Must supply 1.05 V.
 
+Power supplies for Tegra124:
+- Required:
+  - avddio-pex-supply: Power supply for analog PCIe logic. Must supply 1.05 V.
+  - dvddio-pex-supply: Power supply for digital PCIe I/O. Must supply 1.05 V.
+  - avdd-pex-pll-supply: Power supply for dedicated (internal) PCIe PLL. Must
+    supply 1.05 V.
+  - hvdd-pex-supply: High-voltage supply for PCIe I/O and PCIe output clocks.
+    Must supply 3.3 V.
+  - hvdd-pex-pll-e-supply: High-voltage supply for PLLE (shared with USB3).
+    Must supply 3.3 V.
+  - vddio-pex-ctl-supply: Power supply for PCIe control I/O partition. Must
+    supply 2.8-3.3 V.
+  - avdd-pll-erefe-supply: Power supply for PLLE (shared with USB3). Must
+    supply 1.05 V.
+
 Root ports are defined as subnodes of the PCIe controller node.
 
 Required properties:
diff --git a/Documentation/devicetree/bindings/pci/pci-keystone.txt b/Documentation/devicetree/bindings/pci/pci-keystone.txt
new file mode 100644
index 000000000000..54eae2938174
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/pci-keystone.txt
@@ -0,0 +1,63 @@
+TI Keystone PCIe interface
+
+Keystone PCI host Controller is based on Designware PCI h/w version 3.65.
+It shares common functions with PCIe Designware core driver and inherit
+common properties defined in
+Documentation/devicetree/bindings/pci/designware-pci.txt
+
+Please refer to Documentation/devicetree/bindings/pci/designware-pci.txt
+for the details of Designware DT bindings.  Additional properties are
+described here as well as properties that are not applicable.
+
+Required Properties:-
+
+compatibility: "ti,keystone-pcie"
+reg:	index 1 is the base address and length of DW application registers.
+	index 2 is the base address and length of PCI device ID register.
+
+pcie_msi_intc : Interrupt controller device node for MSI IRQ chip
+	interrupt-cells: should be set to 1
+	interrupt-parent: Parent interrupt controller phandle
+	interrupts: GIC interrupt lines connected to PCI MSI interrupt lines
+
+ Example:
+	pcie_msi_intc: msi-interrupt-controller {
+			interrupt-controller;
+			#interrupt-cells = <1>;
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_SPI 30 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 31 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 32 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 33 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 34 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 35 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 36 IRQ_TYPE_EDGE_RISING>,
+					<GIC_SPI 37 IRQ_TYPE_EDGE_RISING>;
+	};
+
+pcie_intc: Interrupt controller device node for Legacy IRQ chip
+	interrupt-cells: should be set to 1
+	interrupt-parent: Parent interrupt controller phandle
+	interrupts: GIC interrupt lines connected to PCI Legacy interrupt lines
+
+ Example:
+	pcie_intc: legacy-interrupt-controller {
+		interrupt-controller;
+		#interrupt-cells = <1>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>,
+			<GIC_SPI 27 IRQ_TYPE_EDGE_RISING>,
+			<GIC_SPI 28 IRQ_TYPE_EDGE_RISING>,
+			<GIC_SPI 29 IRQ_TYPE_EDGE_RISING>;
+	};
+
+Optional properties:-
+	phys: phandle to Generic Keystone SerDes phy for PCI
+	phy-names: name of the Generic Keystine SerDes phy for PCI
+	  - If boot loader already does PCI link establishment, then phys and
+	    phy-names shouldn't be present.
+
+Designware DT Properties not applicable for Keystone PCI
+
+1. pcie_bus clock-names not used.  Instead, a phandle to phys is used.
+
diff --git a/Documentation/devicetree/bindings/pci/xgene-pci.txt b/Documentation/devicetree/bindings/pci/xgene-pci.txt
new file mode 100644
index 000000000000..1070b068c7c6
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/xgene-pci.txt
@@ -0,0 +1,57 @@
+* AppliedMicro X-Gene PCIe interface
+
+Required properties:
+- device_type: set to "pci"
+- compatible: should contain "apm,xgene-pcie" to identify the core.
+- reg: A list of physical base address and length for each set of controller
+       registers. Must contain an entry for each entry in the reg-names
+       property.
+- reg-names: Must include the following entries:
+  "csr": controller configuration registers.
+  "cfg": pcie configuration space registers.
+- #address-cells: set to <3>
+- #size-cells: set to <2>
+- ranges: ranges for the outbound memory, I/O regions.
+- dma-ranges: ranges for the inbound memory regions.
+- #interrupt-cells: set to <1>
+- interrupt-map-mask and interrupt-map: standard PCI properties
+	to define the mapping of the PCIe interface to interrupt
+	numbers.
+- clocks: from common clock binding: handle to pci clock.
+
+Optional properties:
+- status: Either "ok" or "disabled".
+- dma-coherent: Present if dma operations are coherent
+
+Example:
+
+SoC specific DT Entry:
+
+	pcie0: pcie@1f2b0000 {
+		status = "disabled";
+		device_type = "pci";
+		compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = < 0x00 0x1f2b0000 0x0 0x00010000   /* Controller registers */
+			0xe0 0xd0000000 0x0 0x00040000>; /* PCI config space */
+		reg-names = "csr", "cfg";
+		ranges = <0x01000000 0x00 0x00000000 0xe0 0x10000000 0x00 0x00010000   /* io */
+			  0x02000000 0x00 0x80000000 0xe1 0x80000000 0x00 0x80000000>; /* mem */
+		dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
+			      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
+		interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+		interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xc2 0x1
+				 0x0 0x0 0x0 0x2 &gic 0x0 0xc3 0x1
+				 0x0 0x0 0x0 0x3 &gic 0x0 0xc4 0x1
+				 0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>;
+		dma-coherent;
+		clocks = <&pcie0clk 0>;
+	};
+
+
+Board specific DT Entry:
+	&pcie0 {
+		status = "ok";
+	};
diff --git a/Documentation/devicetree/bindings/pci/xilinx-pcie.txt b/Documentation/devicetree/bindings/pci/xilinx-pcie.txt
new file mode 100644
index 000000000000..3e2c88d97ad4
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/xilinx-pcie.txt
@@ -0,0 +1,62 @@
+* Xilinx AXI PCIe Root Port Bridge DT description
+
+Required properties:
+- #address-cells: Address representation for root ports, set to <3>
+- #size-cells: Size representation for root ports, set to <2>
+- #interrupt-cells: specifies the number of cells needed to encode an
+	interrupt source. The value must be 1.
+- compatible: Should contain "xlnx,axi-pcie-host-1.00.a"
+- reg: Should contain AXI PCIe registers location and length
+- device_type: must be "pci"
+- interrupts: Should contain AXI PCIe interrupt
+- interrupt-map-mask,
+  interrupt-map: standard PCI properties to define the mapping of the
+	PCI interface to interrupt numbers.
+- ranges: ranges for the PCI memory regions (I/O space region is not
+	supported by hardware)
+	Please refer to the standard PCI bus binding document for a more
+	detailed explanation
+
+Optional properties:
+- bus-range: PCI bus numbers covered
+
+Interrupt controller child node
++++++++++++++++++++++++++++++++
+Required properties:
+- interrupt-controller: identifies the node as an interrupt controller
+- #address-cells: specifies the number of cells needed to encode an
+	address. The value must be 0.
+- #interrupt-cells: specifies the number of cells needed to encode an
+	interrupt source. The value must be 1.
+
+NOTE:
+The core provides a single interrupt for both INTx/MSI messages. So,
+created a interrupt controller node to support 'interrupt-map' DT
+functionality.  The driver will create an IRQ domain for this map, decode
+the four INTx interrupts in ISR and route them to this domain.
+
+
+Example:
+++++++++
+
+	pci_express: axi-pcie@50000000 {
+		#address-cells = <3>;
+		#size-cells = <2>;
+		#interrupt-cells = <1>;
+		compatible = "xlnx,axi-pcie-host-1.00.a";
+		reg = < 0x50000000 0x10000000 >;
+		device_type = "pci";
+		interrupts = < 0 52 4 >;
+		interrupt-map-mask = <0 0 0 7>;
+		interrupt-map = <0 0 0 1 &pcie_intc 1>,
+				<0 0 0 2 &pcie_intc 2>,
+				<0 0 0 3 &pcie_intc 3>,
+				<0 0 0 4 &pcie_intc 4>;
+		ranges = < 0x02000000 0 0x60000000 0x60000000 0 0x10000000 >;
+
+		pcie_intc: interrupt-controller {
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <1>;
+		}
+	};
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
new file mode 100644
index 000000000000..98c16672ab5f
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -0,0 +1,49 @@
+* Generic PM domains
+
+System on chip designs are often divided into multiple PM domains that can be
+used for power gating of selected IP blocks for power saving by reduced leakage
+current.
+
+This device tree binding can be used to bind PM domain consumer devices with
+their PM domains provided by PM domain providers. A PM domain provider can be
+represented by any node in the device tree and can provide one or more PM
+domains. A consumer node can refer to the provider by a phandle and a set of
+phandle arguments (so called PM domain specifiers) of length specified by the
+#power-domain-cells property in the PM domain provider node.
+
+==PM domain providers==
+
+Required properties:
+ - #power-domain-cells : Number of cells in a PM domain specifier;
+   Typically 0 for nodes representing a single PM domain and 1 for nodes
+   providing multiple PM domains (e.g. power controllers), but can be any value
+   as specified by device tree binding documentation of particular provider.
+
+Example:
+
+	power: power-controller@12340000 {
+		compatible = "foo,power-controller";
+		reg = <0x12340000 0x1000>;
+		#power-domain-cells = <1>;
+	};
+
+The node above defines a power controller that is a PM domain provider and
+expects one cell as its phandle argument.
+
+==PM domain consumers==
+
+Required properties:
+ - power-domains : A phandle and PM domain specifier as defined by bindings of
+                   the power controller specified by phandle.
+
+Example:
+
+	leaky-device@12350000 {
+		compatible = "foo,i-leak-current";
+		reg = <0x12350000 0x1000>;
+		power-domains = <&power 0>;
+	};
+
+The node above defines a typical PM domain consumer device, which is located
+inside a PM domain with index 0 of a power controller represented by a node
+with the label "power".
diff --git a/Documentation/devicetree/bindings/power/reset/ltc2952-poweroff.txt b/Documentation/devicetree/bindings/power/reset/ltc2952-poweroff.txt
new file mode 100644
index 000000000000..0c94c637f63b
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/reset/ltc2952-poweroff.txt
@@ -0,0 +1,26 @@
+Binding for the LTC2952 PowerPath controller
+
+This chip is used to externally trigger a system shut down. Once the trigger has
+been sent, the chips' watchdog has to be reset to gracefully shut down.
+If the Linux systems decides to shut down it powers off the platform via the
+kill signal.
+
+Required properties:
+
+- compatible:		Must contain: "lltc,ltc2952"
+- trigger-gpios:	phandle + gpio-specifier for the GPIO connected to the
+			chip's trigger line
+- watchdog-gpios:	phandle + gpio-specifier for the GPIO connected to the
+			chip's watchdog line
+- kill-gpios:		phandle + gpio-specifier for the GPIO connected to the
+			chip's kill line
+
+Example:
+
+ltc2952 {
+	compatible = "lltc,ltc2952";
+
+	trigger-gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
+	watchdog-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
+	kill-gpios = <&gpio0 2 GPIO_ACTIVE_LOW>;
+};
diff --git a/Documentation/devicetree/bindings/power/reset/st-reset.txt b/Documentation/devicetree/bindings/power/reset/st-reset.txt
new file mode 100644
index 000000000000..809af54f02f3
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/reset/st-reset.txt
@@ -0,0 +1,11 @@
+*Device-Tree bindings for ST SW reset functionality
+
+Required properties:
+- compatible: should be "st,<chip>-restart".
+- st,syscfg: should be a phandle of the syscfg node.
+
+Example node:
+	restart {
+		compatible = "st,stih416-restart";
+		st,syscfg = <&syscfg_sbc>;
+	};
diff --git a/Documentation/devicetree/bindings/power/reset/syscon-reboot.txt b/Documentation/devicetree/bindings/power/reset/syscon-reboot.txt
new file mode 100644
index 000000000000..11906316b43d
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/reset/syscon-reboot.txt
@@ -0,0 +1,23 @@
+Generic SYSCON mapped register reset driver
+
+This is a generic reset driver using syscon to map the reset register.
+The reset is generally performed with a write to the reset register
+defined by the register map pointed by syscon reference plus the offset
+with the mask defined in the reboot node.
+
+Required properties:
+- compatible: should contain "syscon-reboot"
+- regmap: this is phandle to the register map node
+- offset: offset in the register map for the reboot register (in bytes)
+- mask: the reset value written to the reboot register (32 bit access)
+
+Default will be little endian mode, 32 bit access only.
+
+Examples:
+
+	reboot {
+	   compatible = "syscon-reboot";
+	   regmap = <&regmapnode>;
+	   offset = <0x0>;
+	   mask = <0x1>;
+	};
diff --git a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
new file mode 100644
index 000000000000..6fbf6e7ecde6
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
@@ -0,0 +1,83 @@
+Rockchip SRAM for IO Voltage Domains:
+-------------------------------------
+
+IO domain voltages on some Rockchip SoCs are variable but need to be
+kept in sync between the regulators and the SoC using a special
+register.
+
+A specific example using rk3288:
+- If the regulator hooked up to a pin like SDMMC0_VDD is 3.3V then
+  bit 7 of GRF_IO_VSEL needs to be 0.  If the regulator hooked up to
+  that same pin is 1.8V then bit 7 of GRF_IO_VSEL needs to be 1.
+
+Said another way, this driver simply handles keeping bits in the SoC's
+general register file (GRF) in sync with the actual value of a voltage
+hooked up to the pins.
+
+Note that this driver specifically doesn't include:
+- any logic for deciding what voltage we should set regulators to
+- any logic for deciding whether regulators (or internal SoC blocks)
+  should have power or not have power
+
+If there were some other software that had the smarts of making
+decisions about regulators, it would work in conjunction with this
+driver.  When that other software adjusted a regulator's voltage then
+this driver would handle telling the SoC about it.  A good example is
+vqmmc for SD.  In that case the dw_mmc driver simply is told about a
+regulator.  It changes the regulator between 3.3V and 1.8V at the
+right time.  This driver notices the change and makes sure that the
+SoC is on the same page.
+
+
+Required properties:
+- compatible: should be one of:
+  - "rockchip,rk3188-io-voltage-domain" for rk3188
+  - "rockchip,rk3288-io-voltage-domain" for rk3288
+- rockchip,grf: phandle to the syscon managing the "general register files"
+
+
+You specify supplies using the standard regulator bindings by including
+a phandle the the relevant regulator.  All specified supplies must be able
+to report their voltage.  The IO Voltage Domain for any non-specified
+supplies will be not be touched.
+
+Possible supplies for rk3188:
+- ap0-supply:    The supply connected to AP0_VCC.
+- ap1-supply:    The supply connected to AP1_VCC.
+- cif-supply:    The supply connected to CIF_VCC.
+- flash-supply:  The supply connected to FLASH_VCC.
+- lcdc0-supply:  The supply connected to LCD0_VCC.
+- lcdc1-supply:  The supply connected to LCD1_VCC.
+- vccio0-supply: The supply connected to VCCIO0.
+- vccio1-supply: The supply connected to VCCIO1.
+                 Sometimes also labeled VCCIO1 and VCCIO2.
+
+Possible supplies for rk3288:
+- audio-supply:  The supply connected to APIO4_VDD.
+- bb-supply:     The supply connected to APIO5_VDD.
+- dvp-supply:    The supply connected to DVPIO_VDD.
+- flash0-supply: The supply connected to FLASH0_VDD.  Typically for eMMC
+- flash1-supply: The supply connected to FLASH1_VDD.  Also known as SDIO1.
+- gpio30-supply: The supply connected to APIO1_VDD.
+- gpio1830       The supply connected to APIO2_VDD.
+- lcdc-supply:   The supply connected to LCDC_VDD.
+- sdcard-supply: The supply connected to SDMMC0_VDD.
+- wifi-supply:   The supply connected to APIO3_VDD.  Also known as SDIO0.
+
+
+Example:
+
+	io-domains {
+		compatible = "rockchip,rk3288-io-voltage-domain";
+		rockchip,grf = <&grf>;
+
+		audio-supply = <&vcc18_codec>;
+		bb-supply = <&vcc33_io>;
+		dvp-supply = <&vcc_18>;
+		flash0-supply = <&vcc18_flashio>;
+		gpio1830-supply = <&vcc33_io>;
+		gpio30-supply = <&vcc33_pmuio>;
+		lcdc-supply = <&vcc33_lcd>;
+		sdcard-supply = <&vccio_sd>;
+		wifi-supply = <&vcc18_wl>;
+	};
diff --git a/Documentation/devicetree/bindings/rtc/dallas,ds1339.txt b/Documentation/devicetree/bindings/rtc/dallas,ds1339.txt
new file mode 100644
index 000000000000..916f57601a8f
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/dallas,ds1339.txt
@@ -0,0 +1,18 @@
+* Dallas DS1339		I2C Serial Real-Time Clock
+
+Required properties:
+- compatible: Should contain "dallas,ds1339".
+- reg: I2C address for chip
+
+Optional properties:
+- trickle-resistor-ohms : Selected resistor for trickle charger
+	Values usable for ds1339 are 250, 2000, 4000
+	Should be given if trickle charger should be enabled
+- trickle-diode-disable : Do not use internal trickle charger diode
+	Should be given if internal trickle charger diode should be disabled
+Example:
+	ds1339: rtc@68 {
+		compatible = "dallas,ds1339";
+		trickle-resistor-ohms = <250>;
+		reg = <0x68>;
+	};
diff --git a/Documentation/devicetree/bindings/rtc/s3c-rtc.txt b/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
index 7ac7259fe9ea..ab757b84daa7 100644
--- a/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/s3c-rtc.txt
@@ -3,7 +3,10 @@
 Required properties:
 - compatible: should be one of the following.
     * "samsung,s3c2410-rtc" - for controllers compatible with s3c2410 rtc.
+    * "samsung,s3c2416-rtc" - for controllers compatible with s3c2416 rtc.
+    * "samsung,s3c2443-rtc" - for controllers compatible with s3c2443 rtc.
     * "samsung,s3c6410-rtc" - for controllers compatible with s3c6410 rtc.
+    * "samsung,exynos3250-rtc" - for controllers compatible with exynos3250 rtc.
 - reg: physical base address of the controller and length of memory mapped
   region.
 - interrupts: Two interrupt numbers to the cpu should be specified. First
diff --git a/Documentation/devicetree/bindings/sound/adi,ssm2602.txt b/Documentation/devicetree/bindings/sound/adi,ssm2602.txt
new file mode 100644
index 000000000000..3b3302fe399b
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/adi,ssm2602.txt
@@ -0,0 +1,19 @@
+Analog Devices SSM2602, SSM2603 and SSM2604 I2S audio CODEC devices
+
+SSM2602 support both I2C and SPI as the configuration interface,
+the selection is made by the MODE strap-in pin.
+SSM2603 and SSM2604 only support I2C as the configuration interface.
+
+Required properties:
+
+  - compatible : One of "adi,ssm2602", "adi,ssm2603" or "adi,ssm2604"
+
+  - reg : the I2C address of the device for I2C, the chip select
+          number for SPI.
+
+ Example:
+
+	ssm2602: ssm2602@1a {
+		compatible = "adi,ssm2602";
+		reg = <0x1a>;
+	};
diff --git a/Documentation/devicetree/bindings/sound/cs35l32.txt b/Documentation/devicetree/bindings/sound/cs35l32.txt
new file mode 100644
index 000000000000..1417d3f5cc22
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/cs35l32.txt
@@ -0,0 +1,62 @@
+CS35L32 audio CODEC
+
+Required properties:
+
+  - compatible : "cirrus,cs35l32"
+
+  - reg : the I2C address of the device for I2C. Address is determined by the level
+  of the AD0 pin. Level 0 is 0x40 while Level 1 is 0x41.
+
+  - VA-supply, VP-supply : power supplies for the device,
+  as covered in Documentation/devicetree/bindings/regulator/regulator.txt.
+
+Optional properties:
+
+  - reset-gpios : a GPIO spec for the reset pin. If specified, it will be
+  deasserted before communication to the codec starts.
+
+  - cirrus,boost-manager : Boost voltage control.
+  0 = Automatically managed.  Boost-converter output voltage is the higher
+  of the two: Class G or adaptive LED voltage.
+  1 = Automatically managed irrespective of audio, adapting for low-power
+  dissipation when LEDs are ON, and operating in Fixed-Boost Bypass Mode
+  if LEDs are OFF (VBST = VP).
+  2 = (Default) Boost voltage fixed in Bypass Mode (VBST = VP).
+  3 = Boost voltage fixed at 5 V.
+
+  - cirrus,sdout-datacfg : Data configuration for dual CS35L32 applications only.
+  Determines the data packed in a two-CS35L32 configuration.
+  0 = Left/right channels VMON[11:0], IMON[11:0], VPMON[7:0].
+  1 = Left/right channels VMON[11:0], IMON[11:0], STATUS.
+  2 = (Default) left/right channels VMON[15:0], IMON [15:0].
+  3 = Left/right channels VPMON[7:0], STATUS.
+
+  - cirrus,sdout-share : SDOUT sharing. Determines whether one or two CS35L32
+  devices are on board sharing SDOUT.
+  0 = (Default) One IC.
+  1 = Two IC's.
+
+  - cirrus,battery-recovery : Low battery nominal recovery threshold, rising VP.
+  0 = 3.1V
+  1 = 3.2V
+  2 = 3.3V (Default)
+  3 = 3.4V
+
+  - cirrus,battery-threshold : Low battery nominal threshold, falling VP.
+  0 = 3.1V
+  1 = 3.2V
+  2 = 3.3V
+  3 = 3.4V (Default)
+  4 = 3.5V
+  5 = 3.6V
+
+Example:
+
+codec: codec@40 {
+	compatible = "cirrus,cs35l32";
+	reg = <0x40>;
+	reset-gpios = <&gpio 10 0>;
+	cirrus,boost-manager = <0x03>;
+	cirrus,sdout-datacfg = <0x02>;
+	VA-supply = <&reg_audio>;
+};
diff --git a/Documentation/devicetree/bindings/sound/es8328.txt b/Documentation/devicetree/bindings/sound/es8328.txt
new file mode 100644
index 000000000000..30ea8a318ae9
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/es8328.txt
@@ -0,0 +1,38 @@
+Everest ES8328 audio CODEC
+
+This device supports both I2C and SPI.
+
+Required properties:
+
+  - compatible : "everest,es8328"
+  - DVDD-supply : Regulator providing digital core supply voltage 1.8 - 3.6V
+  - AVDD-supply : Regulator providing analog supply voltage 3.3V
+  - PVDD-supply : Regulator providing digital IO supply voltage 1.8 - 3.6V
+  - IPVDD-supply : Regulator providing analog output voltage 3.3V
+  - clocks : A 22.5792 or 11.2896 MHz clock
+  - reg : the I2C address of the device for I2C, the chip select number for SPI
+
+Pins on the device (for linking into audio routes):
+
+  * LOUT1
+  * LOUT2
+  * ROUT1
+  * ROUT2
+  * LINPUT1
+  * RINPUT1
+  * LINPUT2
+  * RINPUT2
+  * Mic Bias
+
+
+Example:
+
+codec: es8328@11 {
+	compatible = "everest,es8328";
+	DVDD-supply = <&reg_3p3v>;
+	AVDD-supply = <&reg_3p3v>;
+	PVDD-supply = <&reg_3p3v>;
+	HPVDD-supply = <&reg_3p3v>;
+	clocks = <&clks 169>;
+	reg = <0x11>;
+};
diff --git a/Documentation/devicetree/bindings/sound/fsl,esai.txt b/Documentation/devicetree/bindings/sound/fsl,esai.txt
index aeb8c4a0b88d..52f5b6bf3e8e 100644
--- a/Documentation/devicetree/bindings/sound/fsl,esai.txt
+++ b/Documentation/devicetree/bindings/sound/fsl,esai.txt
@@ -7,7 +7,8 @@ other DSPs. It has up to six transmitters and four receivers.
 
 Required properties:
 
-  - compatible : Compatible list, must contain "fsl,imx35-esai".
+  - compatible : Compatible list, must contain "fsl,imx35-esai" or
+		 "fsl,vf610-esai"
 
   - reg : Offset and length of the register set for the device.
 
diff --git a/Documentation/devicetree/bindings/sound/fsl,ssi.txt b/Documentation/devicetree/bindings/sound/fsl,ssi.txt
index 3aa4a8f528f4..5b76be45d18b 100644
--- a/Documentation/devicetree/bindings/sound/fsl,ssi.txt
+++ b/Documentation/devicetree/bindings/sound/fsl,ssi.txt
@@ -58,13 +58,7 @@ Optional properties:
 		    Documentation/devicetree/bindings/dma/dma.txt.
 - dma-names:	    Two dmas have to be defined, "tx" and "rx", if fsl,imx-fiq
 		    is not defined.
-- fsl,mode:         The operating mode for the SSI interface.
-                    "i2s-slave" - I2S mode, SSI is clock slave
-                    "i2s-master" - I2S mode, SSI is clock master
-                    "lj-slave" - left-justified mode, SSI is clock slave
-                    "lj-master" - l.j. mode, SSI is clock master
-                    "rj-slave" - right-justified mode, SSI is clock slave
-                    "rj-master" - r.j., SSI is clock master
+- fsl,mode:         The operating mode for the AC97 interface only.
                     "ac97-slave" - AC97 mode, SSI is clock slave
                     "ac97-master" - AC97 mode, SSI is clock master
 
diff --git a/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
new file mode 100644
index 000000000000..a96774c194c8
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/fsl-asoc-card.txt
@@ -0,0 +1,82 @@
+Freescale Generic ASoC Sound Card with ASRC support
+
+The Freescale Generic ASoC Sound Card can be used, ideally, for all Freescale
+SoCs connecting with external CODECs.
+
+The idea of this generic sound card is a bit like ASoC Simple Card. However,
+for Freescale SoCs (especially those released in recent years), most of them
+have ASRC (Documentation/devicetree/bindings/sound/fsl,asrc.txt) inside. And
+this is a specific feature that might be painstakingly controlled and merged
+into the Simple Card.
+
+So having this generic sound card allows all Freescale SoC users to benefit
+from the simplification of a new card support and the capability of the wide
+sample rates support through ASRC.
+
+Note: The card is initially designed for those sound cards who use I2S and
+      PCM DAI formats. However, it'll be also possible to support those non
+      I2S/PCM type sound cards, such as S/PDIF audio and HDMI audio, as long
+      as the driver has been properly upgraded.
+
+
+The compatible list for this generic sound card currently:
+ "fsl,imx-audio-cs42888"
+
+ "fsl,imx-audio-wm8962"
+ (compatible with Documentation/devicetree/bindings/sound/imx-audio-wm8962.txt)
+
+ "fsl,imx-audio-sgtl5000"
+ (compatible with Documentation/devicetree/bindings/sound/imx-audio-sgtl5000.txt)
+
+Required properties:
+
+  - compatible		: Contains one of entries in the compatible list.
+
+  - model		: The user-visible name of this sound complex
+
+  - audio-cpu		: The phandle of an CPU DAI controller
+
+  - audio-codec		: The phandle of an audio codec
+
+  - audio-routing	: A list of the connections between audio components.
+			  Each entry is a pair of strings, the first being the
+			  connection's sink, the second being the connection's
+			  source. There're a few pre-designed board connectors:
+			   * Line Out Jack
+			   * Line In Jack
+			   * Headphone Jack
+			   * Mic Jack
+			   * Ext Spk
+			   * AMIC (stands for Analog Microphone Jack)
+			   * DMIC (stands for Digital Microphone Jack)
+
+			  Note: The "Mic Jack" and "AMIC" are redundant while
+			        coexsiting in order to support the old bindings
+				of wm8962 and sgtl5000.
+
+Optional properties:
+
+  - audio-asrc		: The phandle of ASRC. It can be absent if there's no
+			  need to add ASRC support via DPCM.
+
+Example:
+sound-cs42888 {
+	compatible = "fsl,imx-audio-cs42888";
+	model = "cs42888-audio";
+	audio-cpu = <&esai>;
+	audio-asrc = <&asrc>;
+	audio-codec = <&cs42888>;
+	audio-routing =
+		"Line Out Jack", "AOUT1L",
+		"Line Out Jack", "AOUT1R",
+		"Line Out Jack", "AOUT2L",
+		"Line Out Jack", "AOUT2R",
+		"Line Out Jack", "AOUT3L",
+		"Line Out Jack", "AOUT3R",
+		"Line Out Jack", "AOUT4L",
+		"Line Out Jack", "AOUT4R",
+		"AIN1L", "Line In Jack",
+		"AIN1R", "Line In Jack",
+		"AIN2L", "Line In Jack",
+		"AIN2R", "Line In Jack";
+};
diff --git a/Documentation/devicetree/bindings/sound/fsl-sai.txt b/Documentation/devicetree/bindings/sound/fsl-sai.txt
index 0f4e23828190..4956b14d4b06 100644
--- a/Documentation/devicetree/bindings/sound/fsl-sai.txt
+++ b/Documentation/devicetree/bindings/sound/fsl-sai.txt
@@ -18,12 +18,26 @@ Required properties:
 - pinctrl-names: Must contain a "default" entry.
 - pinctrl-NNN: One property must exist for each entry in pinctrl-names.
   See ../pinctrl/pinctrl-bindings.txt for details of the property values.
-- big-endian-regs: If this property is absent, the little endian mode will
-  be in use as default, or the big endian mode will be in use for all the
-  device registers.
-- big-endian-data: If this property is absent, the little endian mode will
-  be in use as default, or the big endian mode will be in use for all the
-  fifo data.
+- big-endian: Boolean property, required if all the FTM_PWM registers
+  are big-endian rather than little-endian.
+- lsb-first: Configures whether the LSB or the MSB is transmitted first for
+  the fifo data. If this property is absent, the MSB is transmitted first as
+  default, or the LSB is transmitted first.
+- fsl,sai-synchronous-rx: This is a boolean property. If present, indicating
+  that SAI will work in the synchronous mode (sync Tx with Rx) which means
+  both the transimitter and receiver will send and receive data by following
+  receiver's bit clocks and frame sync clocks.
+- fsl,sai-asynchronous: This is a boolean property. If present, indicating
+  that SAI will work in the asynchronous mode, which means both transimitter
+  and receiver will send and receive data by following their own bit clocks
+  and frame sync clocks separately.
+
+Note:
+- If both fsl,sai-asynchronous and fsl,sai-synchronous-rx are absent, the
+  default synchronous mode (sync Rx with Tx) will be used, which means both
+  transimitter and receiver will send and receive data by following clocks
+  of transimitter.
+- fsl,sai-asynchronous and fsl,sai-synchronous-rx are exclusive.
 
 Example:
 sai2: sai@40031000 {
@@ -38,6 +52,6 @@ sai2: sai@40031000 {
 	      dma-names = "tx", "rx";
 	      dmas = <&edma0 0 VF610_EDMA_MUXID0_SAI2_TX>,
 		   <&edma0 0 VF610_EDMA_MUXID0_SAI2_RX>;
-	      big-endian-regs;
-	      big-endian-data;
+	      big-endian;
+	      lsb-first;
 };
diff --git a/Documentation/devicetree/bindings/sound/imx-audio-es8328.txt b/Documentation/devicetree/bindings/sound/imx-audio-es8328.txt
new file mode 100644
index 000000000000..07b68ab206fb
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/imx-audio-es8328.txt
@@ -0,0 +1,60 @@
+Freescale i.MX audio complex with ES8328 codec
+
+Required properties:
+- compatible       : "fsl,imx-audio-es8328"
+- model            : The user-visible name of this sound complex
+- ssi-controller   : The phandle of the i.MX SSI controller
+- jack-gpio        : Optional GPIO for headphone jack
+- audio-amp-supply : Power regulator for speaker amps
+- audio-codec      : The phandle of the ES8328 audio codec
+- audio-routing    : A list of the connections between audio components.
+                     Each entry is a pair of strings, the first being the
+		     connection's sink, the second being the connection's
+		     source. Valid names could be power supplies, ES8328
+		     pins, and the jacks on the board:
+
+			Power supplies:
+			   * audio-amp
+
+			ES8328 pins:
+			   * LOUT1
+			   * LOUT2
+			   * ROUT1
+			   * ROUT2
+			   * LINPUT1
+			   * LINPUT2
+			   * RINPUT1
+			   * RINPUT2
+			   * Mic PGA
+
+			Board connectors:
+			   * Headphone
+			   * Speaker
+			   * Mic Jack
+- mux-int-port     : The internal port of the i.MX audio muxer (AUDMUX)
+- mux-ext-port     : The external port of the i.MX audio muxer (AUDMIX)
+
+Note: The AUDMUX port numbering should start at 1, which is consistent with
+hardware manual.
+
+Example:
+
+sound {
+	compatible = "fsl,imx-audio-es8328";
+	model = "imx-audio-es8328";
+	ssi-controller = <&ssi1>;
+	audio-codec = <&codec>;
+	jack-gpio = <&gpio5 15 0>;
+	audio-amp-supply = <&reg_audio_amp>;
+	audio-routing =
+		"Speaker", "LOUT2",
+		"Speaker", "ROUT2",
+		"Speaker", "audio-amp",
+		"Headphone", "ROUT1",
+		"Headphone", "LOUT1",
+		"LINPUT1", "Mic Jack",
+		"RINPUT1", "Mic Jack",
+		"Mic Jack", "Mic Bias";
+	mux-int-port = <1>;
+	mux-ext-port = <3>;
+};
diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max98090.txt b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max98090.txt
index 9c7c55c71370..c949abc2992f 100644
--- a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max98090.txt
+++ b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-max98090.txt
@@ -25,6 +25,7 @@ Required properties:
 
 Optional properties:
 - nvidia,hp-det-gpios : The GPIO that detect headphones are plugged in
+- nvidia,mic-det-gpios : The GPIO that detect microphones are plugged in
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/sound/rt5677.txt b/Documentation/devicetree/bindings/sound/rt5677.txt
new file mode 100644
index 000000000000..0701b834fc73
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/rt5677.txt
@@ -0,0 +1,59 @@
+RT5677 audio CODEC
+
+This device supports I2C only.
+
+Required properties:
+
+- compatible : "realtek,rt5677".
+
+- reg : The I2C address of the device.
+
+- interrupts : The CODEC's interrupt output.
+
+- gpio-controller : Indicates this device is a GPIO controller.
+
+- #gpio-cells : Should be two. The first cell is the pin number and the
+  second cell is used to specify optional parameters (currently unused).
+
+Optional properties:
+
+- realtek,pow-ldo2-gpio : The GPIO that controls the CODEC's POW_LDO2 pin.
+
+- realtek,in1-differential
+- realtek,in2-differential
+- realtek,lout1-differential
+- realtek,lout2-differential
+- realtek,lout3-differential
+  Boolean. Indicate MIC1/2 input and LOUT1/2/3 outputs are differential,
+  rather than single-ended.
+
+Pins on the device (for linking into audio routes):
+
+  * IN1P
+  * IN1N
+  * IN2P
+  * IN2N
+  * MICBIAS1
+  * DMIC1
+  * DMIC2
+  * DMIC3
+  * DMIC4
+  * LOUT1
+  * LOUT2
+  * LOUT3
+
+Example:
+
+rt5677 {
+	compatible = "realtek,rt5677";
+	reg = <0x2c>;
+	interrupt-parent = <&gpio>;
+	interrupts = <TEGRA_GPIO(W, 3) GPIO_ACTIVE_HIGH>;
+
+	gpio-controller;
+	#gpio-cells = <2>;
+
+	realtek,pow-ldo2-gpio =
+		<&gpio TEGRA_GPIO(V, 3) GPIO_ACTIVE_HIGH>;
+	realtek,in1-differential = "true";
+};
diff --git a/Documentation/devicetree/bindings/sound/simple-card.txt b/Documentation/devicetree/bindings/sound/simple-card.txt
index c2e9841dfce4..c3cba600bf11 100644
--- a/Documentation/devicetree/bindings/sound/simple-card.txt
+++ b/Documentation/devicetree/bindings/sound/simple-card.txt
@@ -17,6 +17,10 @@ Optional properties:
 					  source.
 - simple-audio-card,mclk-fs             : Multiplication factor between stream rate and codec
   					  mclk.
+- simple-audio-card,hp-det-gpio		: Reference to GPIO that signals when
+					  headphones are attached.
+- simple-audio-card,mic-det-gpio	: Reference to GPIO that signals when
+					  a microphone is attached.
 
 Optional subnodes:
 
diff --git a/Documentation/devicetree/bindings/sound/ssm4567.txt b/Documentation/devicetree/bindings/sound/ssm4567.txt
new file mode 100644
index 000000000000..ec3d9e7004b5
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/ssm4567.txt
@@ -0,0 +1,15 @@
+Analog Devices SSM4567 audio amplifier
+
+This device supports I2C only.
+
+Required properties:
+  - compatible : Must be "adi,ssm4567"
+  - reg : the I2C address of the device. This will either be 0x34 (LR_SEL/ADDR connected to AGND),
+	0x35 (LR_SEL/ADDR connected to IOVDD) or 0x36 (LR_SEL/ADDR open).
+
+Example:
+
+	ssm4567: ssm4567@34 {
+		compatible = "adi,ssm4567";
+		reg = <0x34>;
+	};
diff --git a/Documentation/devicetree/bindings/timer/amlogic,meson6-timer.txt b/Documentation/devicetree/bindings/timer/amlogic,meson6-timer.txt
new file mode 100644
index 000000000000..a092053f7902
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/amlogic,meson6-timer.txt
@@ -0,0 +1,15 @@
+Amlogic Meson6 SoCs Timer Controller
+
+Required properties:
+
+- compatible : should be "amlogic,meson6-timer"
+- reg : Specifies base physical address and size of the registers.
+- interrupts : The interrupt of the first timer
+
+Example:
+
+timer@c1109940 {
+	compatible = "amlogic,meson6-timer";
+	reg = <0xc1109940 0x14>;
+	interrupts = <0 10 1>;
+};
diff --git a/Documentation/devicetree/bindings/timer/renesas,cmt.txt b/Documentation/devicetree/bindings/timer/renesas,cmt.txt
index a17418b0ece3..1a05c1b243c1 100644
--- a/Documentation/devicetree/bindings/timer/renesas,cmt.txt
+++ b/Documentation/devicetree/bindings/timer/renesas,cmt.txt
@@ -11,15 +11,47 @@ datasheets.
 
 Required Properties:
 
-  - compatible: must contain one of the following.
-    - "renesas,cmt-32" for the 32-bit CMT
+  - compatible: must contain one or more of the following:
+    - "renesas,cmt-32-r8a7740" for the r8a7740 32-bit CMT
+		(CMT0)
+    - "renesas,cmt-32-sh7372" for the sh7372 32-bit CMT
+		(CMT0)
+    - "renesas,cmt-32-sh73a0" for the sh73a0 32-bit CMT
+		(CMT0)
+    - "renesas,cmt-32" for all 32-bit CMT without fast clock support
 		(CMT0 on sh7372, sh73a0 and r8a7740)
-    - "renesas,cmt-32-fast" for the 32-bit CMT with fast clock support
+		This is a fallback for the above renesas,cmt-32-* entries.
+
+    - "renesas,cmt-32-fast-r8a7740" for the r8a7740 32-bit CMT with fast
+		clock support (CMT[234])
+    - "renesas,cmt-32-fast-sh7372" for the sh7372 32-bit CMT with fast
+		clock support (CMT[234])
+    - "renesas,cmt-32-fast-sh73a0" for the sh73A0 32-bit CMT with fast
+		clock support (CMT[234])
+    - "renesas,cmt-32-fast" for all 32-bit CMT with fast clock support
 		(CMT[234] on sh7372, sh73a0 and r8a7740)
-    - "renesas,cmt-48" for the 48-bit CMT
+		This is a fallback for the above renesas,cmt-32-fast-* entries.
+
+    - "renesas,cmt-48-sh7372" for the sh7372 48-bit CMT
+		(CMT1)
+    - "renesas,cmt-48-sh73a0" for the sh73A0 48-bit CMT
+		(CMT1)
+    - "renesas,cmt-48-r8a7740" for the r8a7740 48-bit CMT
+		(CMT1)
+    - "renesas,cmt-48" for all non-second generation 48-bit CMT
 		(CMT1 on sh7372, sh73a0 and r8a7740)
-    - "renesas,cmt-48-gen2" for the second generation 48-bit CMT
+		This is a fallback for the above renesas,cmt-48-* entries.
+
+    - "renesas,cmt-48-r8a73a4" for the r8a73a4 48-bit CMT
+		(CMT[01])
+    - "renesas,cmt-48-r8a7790" for the r8a7790 48-bit CMT
+		(CMT[01])
+    - "renesas,cmt-48-r8a7791" for the r8a7791 48-bit CMT
+		(CMT[01])
+    - "renesas,cmt-48-gen2" for all second generation 48-bit CMT
 		(CMT[01] on r8a73a4, r8a7790 and r8a7791)
+		This is a fallback for the renesas,cmt-48-r8a73a4,
+		renesas,cmt-48-r8a7790 and renesas,cmt-48-r8a7791 entries.
 
   - reg: base address and length of the registers block for the timer module.
   - interrupts: interrupt-specifier for the timer, one per channel.
@@ -36,7 +68,7 @@ Example: R8A7790 (R-Car H2) CMT0 node
 	them channels 0 and 1 in the documentation.
 
 	cmt0: timer@ffca0000 {
-		compatible = "renesas,cmt-48-gen2";
+		compatible = "renesas,cmt-48-r8a7790", "renesas,cmt-48-gen2";
 		reg = <0 0xffca0000 0 0x1004>;
 		interrupts = <0 142 IRQ_TYPE_LEVEL_HIGH>,
 			     <0 142 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/Documentation/devicetree/bindings/timer/renesas,mtu2.txt b/Documentation/devicetree/bindings/timer/renesas,mtu2.txt
index 917453f826bc..d9a8d5af1a21 100644
--- a/Documentation/devicetree/bindings/timer/renesas,mtu2.txt
+++ b/Documentation/devicetree/bindings/timer/renesas,mtu2.txt
@@ -8,7 +8,10 @@ are independent. The MTU2 hardware supports five channels indexed from 0 to 4.
 
 Required Properties:
 
-  - compatible: must contain "renesas,mtu2"
+  - compatible: must be one or more of the following:
+    - "renesas,mtu2-r7s72100" for the r7s72100 MTU2
+    - "renesas,mtu2" for any MTU2
+      This is a fallback for the above renesas,mtu2-* entries
 
   - reg: base address and length of the registers block for the timer module.
 
@@ -26,7 +29,7 @@ Required Properties:
 Example: R7S72100 (RZ/A1H) MTU2 node
 
 	mtu2: timer@fcff0000 {
-		compatible = "renesas,mtu2";
+		compatible = "renesas,mtu2-r7s72100", "renesas,mtu2";
 		reg = <0xfcff0000 0x400>;
 		interrupts = <0 139 IRQ_TYPE_LEVEL_HIGH>,
 			     <0 146 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/Documentation/devicetree/bindings/timer/renesas,tmu.txt b/Documentation/devicetree/bindings/timer/renesas,tmu.txt
index 425d0c5f4aee..7db89fb25444 100644
--- a/Documentation/devicetree/bindings/timer/renesas,tmu.txt
+++ b/Documentation/devicetree/bindings/timer/renesas,tmu.txt
@@ -8,7 +8,10 @@ are independent. The TMU hardware supports up to three channels.
 
 Required Properties:
 
-  - compatible: must contain "renesas,tmu"
+  - compatible: must contain one or more of the following:
+    - "renesas,tmu-r8a7779" for the r8a7779 TMU
+    - "renesas,tmu" for any TMU.
+      This is a fallback for the above renesas,tmu-* entries
 
   - reg: base address and length of the registers block for the timer module.
 
@@ -27,7 +30,7 @@ Optional Properties:
 Example: R8A7779 (R-Car H1) TMU0 node
 
 	tmu0: timer@ffd80000 {
-		compatible = "renesas,tmu";
+		compatible = "renesas,tmu-r8a7779", "renesas,tmu";
 		reg = <0xffd80000 0x30>;
 		interrupts = <0 32 IRQ_TYPE_LEVEL_HIGH>,
 			     <0 33 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 653beaa392dc..c7bb11be15a3 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -46,11 +46,13 @@ dmo	Data Modul AG
 ebv	EBV Elektronik
 edt	Emerging Display Technologies
 emmicro	EM Microelectronic
+energymicro	Silicon Laboratories (formerly Energy Micro AS)
 epcos	EPCOS AG
 epfl	Ecole Polytechnique Fédérale de Lausanne
 epson	Seiko Epson Corp.
 est	ESTeem Wireless Modems
 eukrea  Eukréa Electromatique
+everest	Everest Semiconductor Co. Ltd.
 excito	Excito
 fcs	Fairchild Semiconductor
 fsl	Freescale Semiconductor
@@ -61,6 +63,7 @@ globalscale	Globalscale Technologies, Inc.
 gmt	Global Mixed-mode Technology, Inc.
 google	Google, Inc.
 gumstix	Gumstix, Inc.
+gw	Gateworks Corporation
 haoyu	Haoyu Microelectronic Co. Ltd.
 hisilicon	Hisilicon Limited.
 honeywell	Honeywell
@@ -70,6 +73,7 @@ ibm	International Business Machines (IBM)
 idt	Integrated Device Technologies, Inc.
 iom	Iomega Corporation
 img	Imagination Technologies Ltd.
+innolux	Innolux Corporation
 intel	Intel Corporation
 intercontrol	Inter Control Group
 isee	ISEE 2007 S.L.
@@ -88,6 +92,7 @@ maxim	Maxim Integrated Products
 mediatek	MediaTek Inc.
 micrel	Micrel Inc.
 microchip	Microchip Technology Inc.
+mitsubishi	Mitsubishi Electric Corporation
 mosaixtech	Mosaix Technologies, Inc.
 moxa	Moxa
 mpl	MPL AG
@@ -131,6 +136,7 @@ simtek
 sii	Seiko Instruments, Inc.
 silergy	Silergy Corp.
 sirf	SiRF Technology, Inc.
+sitronix	Sitronix Technology Corporation
 smsc	Standard Microsystems Corporation
 snps 	Synopsys, Inc.
 solidrun	SolidRun
@@ -139,6 +145,7 @@ st	STMicroelectronics
 ste	ST-Ericsson
 stericsson	ST-Ericsson
 synology	Synology, Inc.
+thine	THine Electronics, Inc.
 ti	Texas Instruments
 tlm	Trusted Logic Mobility
 toradex	Toradex AG
diff --git a/Documentation/devicetree/bindings/video/adi,adv7123.txt b/Documentation/devicetree/bindings/video/adi,adv7123.txt
new file mode 100644
index 000000000000..a6b2b2b8f3d9
--- /dev/null
+++ b/Documentation/devicetree/bindings/video/adi,adv7123.txt
@@ -0,0 +1,50 @@
+Analog Device ADV7123 Video DAC
+-------------------------------
+
+The ADV7123 is a digital-to-analog converter that outputs VGA signals from a
+parallel video input.
+
+Required properties:
+
+- compatible: Should be "adi,adv7123"
+
+Optional properties:
+
+- psave-gpios: Power save control GPIO
+
+Required nodes:
+
+The ADV7123 has two video ports. Their connections are modeled using the OF
+graph bindings specified in Documentation/devicetree/bindings/graph.txt.
+
+- Video port 0 for DPI input
+- Video port 1 for VGA output
+
+
+Example
+-------
+
+	adv7123: encoder@0 {
+		compatible = "adi,adv7123";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				adv7123_in: endpoint@0 {
+					remote-endpoint = <&dpi_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				adv7123_out: endpoint@0 {
+					remote-endpoint = <&vga_connector_in>;
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/video/atmel,lcdc.txt b/Documentation/devicetree/bindings/video/atmel,lcdc.txt
index 7d0c4a1ab811..f059dd0b3d28 100644
--- a/Documentation/devicetree/bindings/video/atmel,lcdc.txt
+++ b/Documentation/devicetree/bindings/video/atmel,lcdc.txt
@@ -20,6 +20,9 @@ Required nodes:
 - default-mode: a videomode within the display with timing parameters
 	as specified below.
 
+Optional properties:
+- lcd-supply: Regulator for LCD supply voltage.
+
 Example:
 
 	fb0: fb@0x00500000 {
diff --git a/Documentation/devicetree/bindings/video/exynos_dsim.txt b/Documentation/devicetree/bindings/video/exynos_dsim.txt
index 31036c667d54..e74243b4b317 100644
--- a/Documentation/devicetree/bindings/video/exynos_dsim.txt
+++ b/Documentation/devicetree/bindings/video/exynos_dsim.txt
@@ -2,6 +2,7 @@ Exynos MIPI DSI Master
 
 Required properties:
   - compatible: value should be one of the following
+		"samsung,exynos3250-mipi-dsi" /* for Exynos3250/3472 SoCs */
 		"samsung,exynos4210-mipi-dsi" /* for Exynos4 SoCs */
 		"samsung,exynos5410-mipi-dsi" /* for Exynos5410/5420/5440 SoCs */
   - reg: physical base address and length of the registers set for the device
diff --git a/Documentation/devicetree/bindings/video/renesas,du.txt b/Documentation/devicetree/bindings/video/renesas,du.txt
new file mode 100644
index 000000000000..5102830f2760
--- /dev/null
+++ b/Documentation/devicetree/bindings/video/renesas,du.txt
@@ -0,0 +1,84 @@
+* Renesas R-Car Display Unit (DU)
+
+Required Properties:
+
+  - compatible: must be one of the following.
+    - "renesas,du-r8a7779" for R8A7779 (R-Car H1) compatible DU
+    - "renesas,du-r8a7790" for R8A7790 (R-Car H2) compatible DU
+    - "renesas,du-r8a7791" for R8A7791 (R-Car M2) compatible DU
+
+  - reg: A list of base address and length of each memory resource, one for
+    each entry in the reg-names property.
+  - reg-names: Name of the memory resources. The DU requires one memory
+    resource for the DU core (named "du") and one memory resource for each
+    LVDS encoder (named "lvds.x" with "x" being the LVDS controller numerical
+    index).
+
+  - interrupt-parent: phandle of the parent interrupt controller.
+  - interrupts: Interrupt specifiers for the DU interrupts.
+
+  - clocks: A list of phandles + clock-specifier pairs, one for each entry in
+    the clock-names property.
+  - clock-names: Name of the clocks. This property is model-dependent.
+    - R8A7779 uses a single functional clock. The clock doesn't need to be
+      named.
+    - R8A7790 and R8A7791 use one functional clock per channel and one clock
+      per LVDS encoder. The functional clocks must be named "du.x" with "x"
+      being the channel numerical index. The LVDS clocks must be named
+      "lvds.x" with "x" being the LVDS encoder numerical index.
+
+Required nodes:
+
+The connections to the DU output video ports are modeled using the OF graph
+bindings specified in Documentation/devicetree/bindings/graph.txt.
+
+The following table lists for each supported model the port number
+corresponding to each DU output.
+
+		Port 0		Port1		Port2
+-----------------------------------------------------------------------------
+ R8A7779 (H1)	DPAD 0		DPAD 1		-
+ R8A7790 (H2)	DPAD		LVDS 0		LVDS 1
+ R8A7791 (M2)	DPAD		LVDS 0		-
+
+
+Example: R8A7790 (R-Car H2) DU
+
+	du: du@feb00000 {
+		compatible = "renesas,du-r8a7790";
+		reg = <0 0xfeb00000 0 0x70000>,
+		      <0 0xfeb90000 0 0x1c>,
+		      <0 0xfeb94000 0 0x1c>;
+		reg-names = "du", "lvds.0", "lvds.1";
+		interrupt-parent = <&gic>;
+		interrupts = <0 256 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 268 IRQ_TYPE_LEVEL_HIGH>,
+			     <0 269 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp7_clks R8A7790_CLK_DU0>,
+		         <&mstp7_clks R8A7790_CLK_DU1>,
+		         <&mstp7_clks R8A7790_CLK_DU2>,
+		         <&mstp7_clks R8A7790_CLK_LVDS0>,
+		         <&mstp7_clks R8A7790_CLK_LVDS1>;
+		clock-names = "du.0", "du.1", "du.2", "lvds.0", "lvds.1";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				du_out_rgb: endpoint {
+				};
+			};
+			port@1 {
+				reg = <1>;
+				du_out_lvds0: endpoint {
+				};
+			};
+			port@2 {
+				reg = <2>;
+				du_out_lvds1: endpoint {
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/video/samsung-fimd.txt b/Documentation/devicetree/bindings/video/samsung-fimd.txt
index ecc899b9817b..4e6c77c85546 100644
--- a/Documentation/devicetree/bindings/video/samsung-fimd.txt
+++ b/Documentation/devicetree/bindings/video/samsung-fimd.txt
@@ -9,6 +9,7 @@ Required properties:
 		"samsung,s3c2443-fimd"; /* for S3C24XX SoCs */
 		"samsung,s3c6400-fimd"; /* for S3C64XX SoCs */
 		"samsung,s5pv210-fimd"; /* for S5PV210 SoC */
+		"samsung,exynos3250-fimd"; /* for Exynos3250/3472 SoCs */
 		"samsung,exynos4210-fimd"; /* for Exynos4 SoCs */
 		"samsung,exynos5250-fimd"; /* for Exynos5 SoCs */
 
diff --git a/Documentation/devicetree/bindings/video/thine,thc63lvdm83d b/Documentation/devicetree/bindings/video/thine,thc63lvdm83d
new file mode 100644
index 000000000000..527e236e9a2a
--- /dev/null
+++ b/Documentation/devicetree/bindings/video/thine,thc63lvdm83d
@@ -0,0 +1,50 @@
+THine Electronics THC63LVDM83D LVDS serializer
+----------------------------------------------
+
+The THC63LVDM83D is an LVDS serializer designed to support pixel data
+transmission between a host and a flat panel.
+
+Required properties:
+
+- compatible: Should be "thine,thc63lvdm83d"
+
+Optional properties:
+
+- pwdn-gpios: Power down control GPIO
+
+Required nodes:
+
+The THC63LVDM83D has two video ports. Their connections are modeled using the
+OFgraph bindings specified in Documentation/devicetree/bindings/graph.txt.
+
+- Video port 0 for CMOS/TTL input
+- Video port 1 for LVDS output
+
+
+Example
+-------
+
+	lvds_enc: encoder@0 {
+		compatible = "thine,thc63lvdm83d";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				lvds_enc_in: endpoint@0 {
+					remote-endpoint = <&rgb_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				lvds_enc_out: endpoint@0 {
+					remote-endpoint = <&panel_in>;
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/video/vga-connector.txt b/Documentation/devicetree/bindings/video/vga-connector.txt
new file mode 100644
index 000000000000..c727f298e7ad
--- /dev/null
+++ b/Documentation/devicetree/bindings/video/vga-connector.txt
@@ -0,0 +1,36 @@
+VGA Connector
+=============
+
+Required properties:
+
+- compatible: "vga-connector"
+
+Optional properties:
+
+- label: a symbolic name for the connector corresponding to a hardware label
+- ddc-i2c-bus: phandle to the I2C bus that is connected to VGA DDC
+
+Required nodes:
+
+The VGA connector internal connections are modeled using the OF graph bindings
+specified in Documentation/devicetree/bindings/graph.txt.
+
+The VGA connector has a single port that must be connected to a video source
+port.
+
+
+Example
+-------
+
+vga0: connector@0 {
+	compatible = "vga-connector";
+	label = "vga";
+
+	ddc-i2c-bus = <&i2c3>;
+
+	port {
+		vga_connector_in: endpoint {
+			remote-endpoint = <&adv7123_out>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/booting-without-of.txt b/Documentation/devicetree/booting-without-of.txt
index 1f013bd0d320..77685185cf3b 100644
--- a/Documentation/devicetree/booting-without-of.txt
+++ b/Documentation/devicetree/booting-without-of.txt
@@ -51,6 +51,8 @@ Table of Contents
 
   VIII - Specifying device power management information (sleep property)
 
+  IX - Specifying dma bus information
+
   Appendix A - Sample SOC node for MPC8540
 
 
@@ -1332,6 +1334,57 @@ reasonably grouped in this manner, then create a virtual sleep controller
 (similar to an interrupt nexus, except that defining a standardized
 sleep-map should wait until its necessity is demonstrated).
 
+IX - Specifying dma bus information
+
+Some devices may have DMA memory range shifted relatively to the beginning of
+RAM, or even placed outside of kernel RAM. For example, the Keystone 2 SoC
+worked in LPAE mode with 4G memory has:
+- RAM range: [0x8 0000 0000, 0x8 FFFF FFFF]
+- DMA range: [  0x8000 0000,   0xFFFF FFFF]
+and DMA range is aliased into first 2G of RAM in HW.
+
+In such cases, DMA addresses translation should be performed between CPU phys
+and DMA addresses. The "dma-ranges" property is intended to be used
+for describing the configuration of such system in DT.
+
+In addition, each DMA master device on the DMA bus may or may not support
+coherent DMA operations. The "dma-coherent" property is intended to be used
+for identifying devices supported coherent DMA operations in DT.
+
+* DMA Bus master
+Optional property:
+- dma-ranges: <prop-encoded-array> encoded as arbitrary number of triplets of
+	(child-bus-address, parent-bus-address, length). Each triplet specified
+	describes a contiguous DMA address range.
+	The dma-ranges property is used to describe the direct memory access (DMA)
+	structure of a memory-mapped bus whose device tree parent can be accessed
+	from DMA operations originating from the bus. It provides a means of
+	defining a mapping or translation between the physical address space of
+	the bus and the physical address space of the parent of the bus.
+	(for more information see ePAPR specification)
+
+* DMA Bus child
+Optional property:
+- dma-ranges: <empty> value. if present - It means that DMA addresses
+	translation has to be enabled for this device.
+- dma-coherent: Present if dma operations are coherent
+
+Example:
+soc {
+		compatible = "ti,keystone","simple-bus";
+		ranges = <0x0 0x0 0x0 0xc0000000>;
+		dma-ranges = <0x80000000 0x8 0x00000000 0x80000000>;
+
+		[...]
+
+		usb: usb@2680000 {
+			compatible = "ti,keystone-dwc3";
+
+			[...]
+			dma-coherent;
+		};
+};
+
 Appendix A - Sample SOC node for MPC8540
 ========================================
 
diff --git a/Documentation/devicetree/dynamic-resolution-notes.txt b/Documentation/devicetree/dynamic-resolution-notes.txt
new file mode 100644
index 000000000000..083d23262abe
--- /dev/null
+++ b/Documentation/devicetree/dynamic-resolution-notes.txt
@@ -0,0 +1,25 @@
+Device Tree Dynamic Resolver Notes
+----------------------------------
+
+This document describes the implementation of the in-kernel
+Device Tree resolver, residing in drivers/of/resolver.c and is a
+companion document to Documentation/devicetree/dt-object-internal.txt[1]
+
+How the resolver works
+----------------------
+
+The resolver is given as an input an arbitrary tree compiled with the
+proper dtc option and having a /plugin/ tag. This generates the
+appropriate __fixups__ & __local_fixups__ nodes as described in [1].
+
+In sequence the resolver works by the following steps:
+
+1. Get the maximum device tree phandle value from the live tree + 1.
+2. Adjust all the local phandles of the tree to resolve by that amount.
+3. Using the __local__fixups__ node information adjust all local references
+   by the same amount.
+4. For each property in the __fixups__ node locate the node it references
+   in the live tree. This is the label used to tag the node.
+5. Retrieve the phandle of the target of the fixup.
+6. For each fixup in the property locate the node:property:offset location
+   and replace it with the phandle value.
diff --git a/Documentation/devicetree/of_selftest.txt b/Documentation/devicetree/of_selftest.txt
index 3a2f54d07fc5..1e3d5c92b5e3 100644
--- a/Documentation/devicetree/of_selftest.txt
+++ b/Documentation/devicetree/of_selftest.txt
@@ -67,14 +67,14 @@ struct device_node {
     ...
  };
 
-Figure 1, describes a generic structure of machine’s un-flattened device tree
+Figure 1, describes a generic structure of machine's un-flattened device tree
 considering only child and sibling pointers. There exists another pointer,
 *parent, that is used to traverse the tree in the reverse direction. So, at
 a particular level the child node and all the sibling nodes will have a parent
-pointer pointing to a common node (e.g. child1, sibling2, sibling3, sibling4’s
+pointer pointing to a common node (e.g. child1, sibling2, sibling3, sibling4's
 parent points to root node)
 
-root (‘/’)
+root ('/')
    |
 child1 -> sibling2 -> sibling3 -> sibling4 -> null
    |         |           |           |
@@ -113,8 +113,8 @@ via the following kernel symbols:
 __dtb_testcases_begin - address marking the start of test data blob
 __dtb_testcases_end   - address marking the end of test data blob
 
-Secondly, it calls of_fdt_unflatten_device_tree() to unflatten the flattened
-blob. And finally, if the machine’s device tree (i.e live tree) is present,
+Secondly, it calls of_fdt_unflatten_tree() to unflatten the flattened
+blob. And finally, if the machine's device tree (i.e live tree) is present,
 then it attaches the unflattened test data tree to the live tree, else it
 attaches itself as a live device tree.
 
@@ -122,7 +122,7 @@ attach_node_and_children() uses of_attach_node() to attach the nodes into the
 live tree as explained below. To explain the same, the test data tree described
  in Figure 2 is attached to the live tree described in Figure 1.
 
-root (‘/’)
+root ('/')
     |
  testcase-data
     |
@@ -138,8 +138,8 @@ root->testcase-data->test-child0->test-child01->test-sibling1->test-sibling2
 
 Figure 2: Example test data tree to be attached to live tree.
 
-According to the scenario above, the live tree is already present so it isn’t
-required to attach the root(‘/’) node. All other nodes are attached by calling
+According to the scenario above, the live tree is already present so it isn't
+required to attach the root('/') node. All other nodes are attached by calling
 of_attach_node() on each node.
 
 In the function of_attach_node(), the new node is attached as the child of the
@@ -148,7 +148,7 @@ replaces the current child and turns it into its sibling. So, when the testcase
 data node is attached to the live tree above (Figure 1), the final structure is
  as shown in Figure 3.
 
-root (‘/’)
+root ('/')
    |
 testcase-data -> child1 -> sibling2 -> sibling3 -> sibling4 -> null
    |               |          |           |           |
@@ -170,7 +170,7 @@ testcase-data -> child1 -> sibling2 -> sibling3 -> sibling4 -> null
                                           null
 -----------------------------------------------------------------------
 
-root (‘/’)
+root ('/')
    |
 testcase-data -> child1 -> sibling2 -> sibling3 -> sibling4 -> null
    |               |          |           |           |
@@ -191,8 +191,8 @@ test-child0 the test-sibling1 is attached that pushes the child node
  as mentioned above.
 
 If a duplicate node is found (i.e. if a node with same full_name property is
-already present in the live tree), then the node isn’t attached rather its
-properties are updated to the live tree’s node by calling the function
+already present in the live tree), then the node isn't attached rather its
+properties are updated to the live tree's node by calling the function
 update_node_properties().
 
 
@@ -205,7 +205,7 @@ whole tree). selftest_data_remove() calls detach_node_and_children() that uses
 of_detach_node() to detach the nodes from the live device tree.
 
 To detach a node, of_detach_node() first updates all_next linked list, by
-attaching the previous node’s allnext to current node’s allnext pointer. And
-then, it either updates the child pointer of given node’s parent to its
-sibling or attaches the previous sibling to the given node’s sibling, as
+attaching the previous node's allnext to current node's allnext pointer. And
+then, it either updates the child pointer of given node's parent to its
+sibling or attaches the previous sibling to the given node's sibling, as
 appropriate. That is it :)
diff --git a/Documentation/dmaengine.txt b/Documentation/dmaengine.txt
index 573e28ce9751..11fb87ff6cd0 100644
--- a/Documentation/dmaengine.txt
+++ b/Documentation/dmaengine.txt
@@ -98,7 +98,7 @@ The slave DMA usage consists of following steps:
 		unsigned long flags);
 
    The peripheral driver is expected to have mapped the scatterlist for
-   the DMA operation prior to calling device_prep_slave_sg, and must
+   the DMA operation prior to calling dmaengine_prep_slave_sg(), and must
    keep the scatterlist mapped until the DMA operation has completed.
    The scatterlist must be mapped using the DMA struct device.
    If a mapping needs to be synchronized later, dma_sync_*_for_*() must be
@@ -195,5 +195,5 @@ Further APIs:
    Note:
 	Not all DMA engine drivers can return reliable information for
 	a running DMA channel.  It is recommended that DMA engine users
-	pause or stop (via dmaengine_terminate_all) the channel before
+	pause or stop (via dmaengine_terminate_all()) the channel before
 	using this API.
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index 40677443c0c5..b5ab416cd53a 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -264,8 +264,10 @@ IIO
 IO region
   devm_release_mem_region()
   devm_release_region()
+  devm_release_resource()
   devm_request_mem_region()
   devm_request_region()
+  devm_request_resource()
 
 IOMAP
   devm_ioport_map()
diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware
index 26c623dd3aa3..91b43d2738c7 100755
--- a/Documentation/dvb/get_dvb_firmware
+++ b/Documentation/dvb/get_dvb_firmware
@@ -708,23 +708,25 @@ sub drxk_terratec_htc_stick {
 }
 
 sub it9135 {
-	my $sourcefile = "dvb-usb-it9135.zip";
-	my $url = "http://www.ite.com.tw/uploads/firmware/v3.6.0.0/$sourcefile";
-	my $hash = "1e55f6c8833f1d0ae067c2bb2953e6a9";
-	my $tmpdir = tempdir(DIR => "/tmp", CLEANUP => 0);
-	my $outfile = "dvb-usb-it9135.fw";
+	my $url = "http://www.ite.com.tw/uploads/firmware/v3.25.0.0/";
+	my $file1 = "dvb-usb-it9135-01.zip";
 	my $fwfile1 = "dvb-usb-it9135-01.fw";
+	my $hash1 = "02fcf11174eda84745dae7e61c5ff9ba";
+	my $file2 = "dvb-usb-it9135-02.zip";
 	my $fwfile2 = "dvb-usb-it9135-02.fw";
+	my $hash2 = "d5e1437dc24358578e07999475d4cac9";
 
 	checkstandard();
 
-	wgetfile($sourcefile, $url);
-	unzip($sourcefile, $tmpdir);
-	verify("$tmpdir/$outfile", $hash);
-	extract("$tmpdir/$outfile", 64, 8128, "$fwfile1");
-	extract("$tmpdir/$outfile", 12866, 5817, "$fwfile2");
+	wgetfile($file1, $url . $file1);
+	unzip($file1, "");
+	verify("$fwfile1", $hash1);
+
+	wgetfile($file2, $url . $file2);
+	unzip($file2, "");
+	verify("$fwfile2", $hash2);
 
-	"$fwfile1 $fwfile2"
+	"$file1 $file2"
 }
 
 sub tda10071 {
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index f1997e9da61f..94d93b1f8b53 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -464,15 +464,12 @@ prototypes:
 			size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
 			size_t, unsigned int);
-	int (*setlease)(struct file *, long, struct file_lock **);
+	int (*setlease)(struct file *, long, struct file_lock **, void **);
 	long (*fallocate)(struct file *, int, loff_t, loff_t);
 };
 
 locking rules:
-	All may block except for ->setlease.
-	No VFS locks held on entry except for ->setlease.
-
-->setlease has the file_list_lock held and must not sleep.
+	All may block.
 
 ->llseek() locking has moved from llseek to the individual llseek
 implementations.  If your fs is not using generic_file_llseek, you
@@ -496,6 +493,10 @@ components. And there are other reasons why the current interface is a mess...
 ->read on directories probably must go away - we should just enforce -EISDIR
 in sys_read() and friends.
 
+->setlease operations should call generic_setlease() before or after setting
+the lease within the individual filesystem to record the result of the
+operation
+
 --------------------------- dquot_operations -------------------------------
 prototypes:
 	int (*write_dquot) (struct dquot *);
diff --git a/Documentation/filesystems/autofs4.txt b/Documentation/filesystems/autofs4.txt
new file mode 100644
index 000000000000..39d02e19fb62
--- /dev/null
+++ b/Documentation/filesystems/autofs4.txt
@@ -0,0 +1,520 @@
+<head>
+<style> p { max-width:50em} ol, ul {max-width: 40em}</style>
+</head>
+
+autofs - how it works
+=====================
+
+Purpose
+-------
+
+The goal of autofs is to provide on-demand mounting and race free
+automatic unmounting of various other filesystems.  This provides two
+key advantages:
+
+1. There is no need to delay boot until all filesystems that
+   might be needed are mounted.  Processes that try to access those
+   slow filesystems might be delayed but other processes can
+   continue freely.  This is particularly important for
+   network filesystems (e.g. NFS) or filesystems stored on
+   media with a media-changing robot.
+
+2. The names and locations of filesystems can be stored in
+   a remote database and can change at any time.  The content
+   in that data base at the time of access will be used to provide
+   a target for the access.  The interpretation of names in the
+   filesystem can even be programmatic rather than database-backed,
+   allowing wildcards for example, and can vary based on the user who
+   first accessed a name.
+
+Context
+-------
+
+The "autofs4" filesystem module is only one part of an autofs system.
+There also needs to be a user-space program which looks up names
+and mounts filesystems.  This will often be the "automount" program,
+though other tools including "systemd" can make use of "autofs4".
+This document describes only the kernel module and the interactions
+required with any user-space program.  Subsequent text refers to this
+as the "automount daemon" or simply "the daemon".
+
+"autofs4" is a Linux kernel module with provides the "autofs"
+filesystem type.  Several "autofs" filesystems can be mounted and they
+can each be managed separately, or all managed by the same daemon.
+
+Content
+-------
+
+An autofs filesystem can contain 3 sorts of objects: directories,
+symbolic links and mount traps.  Mount traps are directories with
+extra properties as described in the next section.
+
+Objects can only be created by the automount daemon: symlinks are
+created with a regular `symlink` system call, while directories and
+mount traps are created with `mkdir`.  The determination of whether a
+directory should be a mount trap or not is quite _ad hoc_, largely for
+historical reasons, and is determined in part by the
+*direct*/*indirect*/*offset* mount options, and the *maxproto* mount option.
+
+If neither the *direct* or *offset* mount options are given (so the
+mount is considered to be *indirect*), then the root directory is
+always a regular directory, otherwise it is a mount trap when it is
+empty and a regular directory when not empty.  Note that *direct* and
+*offset* are treated identically so a concise summary is that the root
+directory is a mount trap only if the filesystem is mounted *direct*
+and the root is empty.
+
+Directories created in the root directory are mount traps only if the
+filesystem is mounted  *indirect* and they are empty.
+
+Directories further down the tree depend on the *maxproto* mount
+option and particularly whether it is less than five or not.
+When *maxproto* is five, no directories further down the
+tree are ever mount traps, they are always regular directories.  When
+the *maxproto* is four (or three), these directories are mount traps
+precisely when they are empty.
+
+So: non-empty (i.e. non-leaf) directories are never mount traps. Empty
+directories are sometimes mount traps, and sometimes not depending on
+where in the tree they are (root, top level, or lower), the *maxproto*,
+and whether the mount was *indirect* or not.
+
+Mount Traps
+---------------
+
+A core element of the implementation of autofs is the Mount Traps
+which are provided by the Linux VFS.  Any directory provided by a
+filesystem can be designated as a trap.  This involves two separate
+features that work together to allow autofs to do its job.
+
+**DCACHE_NEED_AUTOMOUNT**
+
+If a dentry has the DCACHE_NEED_AUTOMOUNT flag set (which gets set if
+the inode has S_AUTOMOUNT set, or can be set directly) then it is
+(potentially) a mount trap.  Any access to this directory beyond a
+"`stat`" will (normally) cause the `d_op->d_automount()` dentry operation
+to be called. The task of this method is to find the filesystem that
+should be mounted on the directory and to return it.  The VFS is
+responsible for actually mounting the root of this filesystem on the
+directory.
+
+autofs doesn't find the filesystem itself but sends a message to the
+automount daemon asking it to find and mount the filesystem.  The
+autofs `d_automount` method then waits for the daemon to report that
+everything is ready.  It will then return "`NULL`" indicating that the
+mount has already happened.  The VFS doesn't try to mount anything but
+follows down the mount that is already there.
+
+This functionality is sufficient for some users of mount traps such
+as NFS which creates traps so that mountpoints on the server can be
+reflected on the client.  However it is not sufficient for autofs.  As
+mounting onto a directory is considered to be "beyond a `stat`", the
+automount daemon would not be able to mount a filesystem on the 'trap'
+directory without some way to avoid getting caught in the trap.  For
+that purpose there is another flag.
+
+**DCACHE_MANAGE_TRANSIT**
+
+If a dentry has DCACHE_MANAGE_TRANSIT set then two very different but
+related behaviors are invoked, both using the `d_op->d_manage()`
+dentry operation.
+
+Firstly, before checking to see if any filesystem is mounted on the
+directory, d_manage() will be called with the `rcu_walk` parameter set
+to `false`.  It may return one of three things:
+
+-  A return value of zero indicates that there is nothing special
+   about this dentry and normal checks for mounts and automounts
+   should proceed.
+
+   autofs normally returns zero, but first waits for any
+   expiry (automatic unmounting of the mounted filesystem) to
+   complete.  This avoids races.
+
+-  A return value of `-EISDIR` tells the VFS to ignore any mounts
+   on the directory and to not consider calling `->d_automount()`.
+   This effectively disables the **DCACHE_NEED_AUTOMOUNT** flag
+   causing the directory not be a mount trap after all.
+
+   autofs returns this if it detects that the process performing the
+   lookup is the automount daemon and that the mount has been
+   requested but has not yet completed.  How it determines this is
+   discussed later.  This allows the automount daemon not to get
+   caught in the mount trap.
+
+   There is a subtlety here.  It is possible that a second autofs
+   filesystem can be mounted below the first and for both of them to
+   be managed by the same daemon.  For the daemon to be able to mount
+   something on the second it must be able to "walk" down past the
+   first.  This means that d_manage cannot *always* return -EISDIR for
+   the automount daemon.  It must only return it when a mount has
+   been requested, but has not yet completed.
+
+   `d_manage` also returns `-EISDIR` if the dentry shouldn't be a
+   mount trap, either because it is a symbolic link or because it is
+   not empty.
+
+-  Any other negative value is treated as an error and returned
+   to the caller.
+
+   autofs can return
+
+   - -ENOENT if the automount daemon failed to mount anything,
+   - -ENOMEM if it ran out of memory,
+   - -EINTR if a signal arrived while waiting for expiry to
+     complete
+   - or any other error sent down by the automount daemon.
+
+
+The second use case only occurs during an "RCU-walk" and so `rcu_walk`
+will be set.
+
+An RCU-walk is a fast and lightweight process for walking down a
+filename path (i.e. it is like running on tip-toes).  RCU-walk cannot
+cope with all situations so when it finds a difficulty it falls back
+to "REF-walk", which is slower but more robust.
+
+RCU-walk will never call `->d_automount`; the filesystems must already
+be mounted or RCU-walk cannot handle the path.
+To determine if a mount-trap is safe for RCU-walk mode it calls
+`->d_manage()` with `rcu_walk` set to `true`.
+
+In this case `d_manage()` must avoid blocking and should avoid taking
+spinlocks if at all possible.  Its sole purpose is to determine if it
+would be safe to follow down into any mounted directory and the only
+reason that it might not be is if an expiry of the mount is
+underway.
+
+In the `rcu_walk` case, `d_manage()` cannot return -EISDIR to tell the
+VFS that this is a directory that doesn't require d_automount.  If
+`rcu_walk` sees a dentry with DCACHE_NEED_AUTOMOUNT set but nothing
+mounted, it *will* fall back to REF-walk.  `d_manage()` cannot make the
+VFS remain in RCU-walk mode, but can only tell it to get out of
+RCU-walk mode by returning `-ECHILD`.
+
+So `d_manage()`, when called with `rcu_walk` set, should either return
+-ECHILD if there is any reason to believe it is unsafe to end the
+mounted filesystem, and otherwise should return 0.
+
+autofs will return `-ECHILD` if an expiry of the filesystem has been
+initiated or is being considered, otherwise it returns 0.
+
+
+Mountpoint expiry
+-----------------
+
+The VFS has a mechansim for automatically expiring unused mounts,
+much as it can expire any unused dentry information from the dcache.
+This is guided by the MNT_SHRINKABLE flag.  This  only applies to
+mounts that were created by `d_automount()` returning a filesystem to be
+mounted.  As autofs doesn't return such a filesystem but leaves the
+mounting to the automount daemon, it must involve the automount daemon
+in unmounting as well.  This also means that autofs has more control
+of expiry.
+
+The VFS also supports "expiry" of mounts using the MNT_EXPIRE flag to
+the `umount` system call.  Unmounting with MNT_EXPIRE will fail unless
+a previous attempt had been made, and the filesystem has been inactive
+and untouched since that previous attempt.  autofs4 does not depend on
+this but has its own internal tracking of whether filesystems were
+recently used.  This allows individual names in the autofs directory
+to expire separately.
+
+With version 4 of the protocol, the automount daemon can try to
+unmount any filesystems mounted on the autofs filesystem or remove any
+symbolic links or empty directories any time it likes.  If the unmount
+or removal is successful the filesystem will be returned to the state
+it was before the mount or creation, so that any access of the name
+will trigger normal auto-mount processing.  In particlar, `rmdir` and
+`unlink` do not leave negative entries in the dcache as a normal
+filesystem would, so an attempt to access a recently-removed object is
+passed to autofs for handling.
+
+With version 5, this is not safe except for unmounting from top-level
+directories.  As lower-level directories are never mount traps, other
+processes will see an empty directory as soon as the filesystem is
+unmounted.  So it is generally safest to use the autofs expiry
+protocol described below.
+
+Normally the daemon only wants to remove entries which haven't been
+used for a while.  For this purpose autofs maintains a "`last_used`"
+time stamp on each directory or symlink.  For symlinks it genuinely
+does record the last time the symlink was "used" or followed to find
+out where it points to.  For directories the field is a slight
+misnomer.  It actually records the last time that autofs checked if
+the directory or one of its descendents was busy and found that it
+was.  This is just as useful and doesn't require updating the field so
+often.
+
+The daemon is able to ask autofs if anything is due to be expired,
+using an `ioctl` as discussed later.  For a *direct* mount, autofs
+considers if the entire mount-tree can be unmounted or not.  For an
+*indirect* mount, autofs considers each of the names in the top level
+directory to determine if any of those can be unmounted and cleaned
+up.
+
+There is an option with indirect mounts to consider each of the leaves
+that has been mounted on instead of considering the top-level names.
+This is intended for compatability with version 4 of autofs and should
+be considered as deprecated.
+
+When autofs considers a directory it checks the `last_used` time and
+compares it with the "timeout" value set when the filesystem was
+mounted, though this check is ignored in some cases. It also checks if
+the directory or anything below it is in use.  For symbolic links,
+only the `last_used` time is ever considered.
+
+If both appear to support expiring the directory or symlink, an action
+is taken.
+
+There are two ways to ask autofs to consider expiry.  The first is to
+use the **AUTOFS_IOC_EXPIRE** ioctl.  This only works for indirect
+mounts.  If it finds something in the root directory to expire it will
+return the name of that thing.  Once a name has been returned the
+automount daemon needs to unmount any filesystems mounted below the
+name normally.  As described above, this is unsafe for non-toplevel
+mounts in a version-5 autofs.  For this reason the current `automountd`
+does not use this ioctl.
+
+The second mechanism uses either the **AUTOFS_DEV_IOCTL_EXPIRE_CMD** or
+the **AUTOFS_IOC_EXPIRE_MULTI** ioctl.  This will work for both direct and
+indirect mounts.  If it selects an object to expire, it will notify
+the daemon using the notification mechanism described below.  This
+will block until the daemon acknowledges the expiry notification.
+This implies that the "`EXPIRE`" ioctl must be sent from a different
+thread than the one which handles notification.
+
+While the ioctl is blocking, the entry is marked as "expiring" and
+`d_manage` will block until the daemon affirms that the unmount has
+completed (together with removing any directories that might have been
+necessary), or has been aborted.
+
+Communicating with autofs: detecting the daemon
+-----------------------------------------------
+
+There are several forms of communication between the automount daemon
+and the filesystem.  As we have already seen, the daemon can create and
+remove directories and symlinks using normal filesystem operations.
+autofs knows whether a process requesting some operation is the daemon
+or not based on its process-group id number (see getpgid(1)).
+
+When an autofs filesystem it mounted the pgid of the mounting
+processes is recorded unless the "pgrp=" option is given, in which
+case that number is recorded instead.  Any request arriving from a
+process in that process group is considered to come from the daemon.
+If the daemon ever has to be stopped and restarted a new pgid can be
+provided through an ioctl as will be described below.
+
+Communicating with autofs: the event pipe
+-----------------------------------------
+
+When an autofs filesystem is mounted, the 'write' end of a pipe must
+be passed using the 'fd=' mount option.  autofs will write
+notification messages to this pipe for the daemon to respond to.
+For version 5, the format of the message is:
+
+        struct autofs_v5_packet {
+                int proto_version;                /* Protocol version */
+                int type;                        /* Type of packet */
+                autofs_wqt_t wait_queue_token;
+                __u32 dev;
+                __u64 ino;
+                __u32 uid;
+                __u32 gid;
+                __u32 pid;
+                __u32 tgid;
+                __u32 len;
+                char name[NAME_MAX+1];
+        };
+
+where the type is one of
+
+        autofs_ptype_missing_indirect
+        autofs_ptype_expire_indirect
+        autofs_ptype_missing_direct
+        autofs_ptype_expire_direct
+
+so messages can indicate that a name is missing (something tried to
+access it but it isn't there) or that it has been selected for expiry.
+
+The pipe will be set to "packet mode" (equivalent to passing
+`O_DIRECT`) to _pipe2(2)_ so that a read from the pipe will return at
+most one packet, and any unread portion of a packet will be discarded.
+
+The `wait_queue_token` is a unique number which can identify a
+particular request to be acknowledged.  When a message is sent over
+the pipe the affected dentry is marked as either "active" or
+"expiring" and other accesses to it block until the message is
+acknowledged using one of the ioctls below and the relevant
+`wait_queue_token`.
+
+Communicating with autofs: root directory ioctls
+------------------------------------------------
+
+The root directory of an autofs filesystem will respond to a number of
+ioctls.   The process issuing the ioctl must have the CAP_SYS_ADMIN
+capability, or must be the automount daemon.
+
+The available ioctl commands are:
+
+- **AUTOFS_IOC_READY**: a notification has been handled.  The argument
+    to the ioctl command is the "wait_queue_token" number
+    corresponding to the notification being acknowledged.
+- **AUTOFS_IOC_FAIL**: similar to above, but indicates failure with
+    the error code `ENOENT`.
+- **AUTOFS_IOC_CATATONIC**: Causes the autofs to enter "catatonic"
+    mode meaning that it stops sending notifications to the daemon.
+    This mode is also entered if a write to the pipe fails.
+- **AUTOFS_IOC_PROTOVER**:  This returns the protocol version in use.
+- **AUTOFS_IOC_PROTOSUBVER**: Returns the protocol sub-version which
+    is really a version number for the implementation.  It is
+    currently 2.
+- **AUTOFS_IOC_SETTIMEOUT**:  This passes a pointer to an unsigned
+    long.  The value is used to set the timeout for expiry, and
+    the current timeout value is stored back through the pointer.
+- **AUTOFS_IOC_ASKUMOUNT**:  Returns, in the pointed-to `int`, 1 if
+    the filesystem could be unmounted.  This is only a hint as
+    the situation could change at any instant.  This call can be
+    use to avoid a more expensive full unmount attempt.
+- **AUTOFS_IOC_EXPIRE**: as described above, this asks if there is
+    anything suitable to expire.  A pointer to a packet:
+
+        struct autofs_packet_expire_multi {
+                int proto_version;              /* Protocol version */
+                int type;                       /* Type of packet */
+                autofs_wqt_t wait_queue_token;
+                int len;
+                char name[NAME_MAX+1];
+        };
+
+     is required.  This is filled in with the name of something
+     that can be unmounted or removed.  If nothing can be expired,
+     `errno` is set to `EAGAIN`.  Even though a `wait_queue_token`
+     is present in the structure, no "wait queue" is established
+     and no acknowledgment is needed.
+- **AUTOFS_IOC_EXPIRE_MULTI**:  This is similar to
+     **AUTOFS_IOC_EXPIRE** except that it causes notification to be
+     sent to the daemon, and it blocks until the daemon acknowledges.
+     The argument is an integer which can contain two different flags.
+
+     **AUTOFS_EXP_IMMEDIATE** causes `last_used` time to be ignored
+     and objects are expired if the are not in use.
+
+     **AUTOFS_EXP_LEAVES** will select a leaf rather than a top-level
+     name to expire.  This is only safe when *maxproto* is 4.
+
+Communicating with autofs: char-device ioctls
+---------------------------------------------
+
+It is not always possible to open the root of an autofs filesystem,
+particularly a *direct* mounted filesystem.  If the automount daemon
+is restarted there is no way for it to regain control of existing
+mounts using any of the above communication channels.  To address this
+need there is a "miscellaneous" character device (major 10, minor 235)
+which can be used to communicate directly with the autofs filesystem.
+It requires CAP_SYS_ADMIN for access.
+
+The `ioctl`s that can be used on this device are described in a separate
+document `autofs4-mount-control.txt`, and are summarized briefly here.
+Each ioctl is passed a pointer to an `autofs_dev_ioctl` structure:
+
+        struct autofs_dev_ioctl {
+                __u32 ver_major;
+                __u32 ver_minor;
+                __u32 size;             /* total size of data passed in
+                                         * including this struct */
+                __s32 ioctlfd;          /* automount command fd */
+
+                __u32 arg1;             /* Command parameters */
+                __u32 arg2;
+
+                char path[0];
+        };
+
+For the **OPEN_MOUNT** and **IS_MOUNTPOINT** commands, the target
+filesystem is identified by the `path`.  All other commands identify
+the filesystem by the `ioctlfd` which is a file descriptor open on the
+root, and which can be returned by **OPEN_MOUNT**.
+
+The `ver_major` and `ver_minor` are in/out parameters which check that
+the requested version is supported, and report the maximum version
+that the kernel module can support.
+
+Commands are:
+
+- **AUTOFS_DEV_IOCTL_VERSION_CMD**: does nothing, except validate and
+    set version numbers.
+- **AUTOFS_DEV_IOCTL_OPENMOUNT_CMD**: return an open file descriptor
+    on the root of an autofs filesystem.  The filesystem is identified
+    by name and device number, which is stored in `arg1`.  Device
+    numbers for existing filesystems can be found in
+    `/proc/self/mountinfo`.
+- **AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD**: same as `close(ioctlfd)`.
+- **AUTOFS_DEV_IOCTL_SETPIPEFD_CMD**: if the  filesystem is in
+    catatonic mode, this can provide the write end of a new pipe
+    in `arg1` to re-establish communication with a daemon.  The
+    process group of the calling process is used to identify the
+    daemon.
+- **AUTOFS_DEV_IOCTL_REQUESTER_CMD**: `path` should be a
+    name within the filesystem that has been auto-mounted on.
+    arg1 is the dev number of the underlying autofs.  On successful
+    return, `arg1` and `arg2` will be the UID and GID of the process
+    which triggered that mount.
+
+- **AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD**: Check if path is a
+    mountpoint of a particular type - see separate documentation for
+    details.
+
+- **AUTOFS_DEV_IOCTL_PROTOVER_CMD**:
+- **AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD**:
+- **AUTOFS_DEV_IOCTL_READY_CMD**:
+- **AUTOFS_DEV_IOCTL_FAIL_CMD**:
+- **AUTOFS_DEV_IOCTL_CATATONIC_CMD**:
+- **AUTOFS_DEV_IOCTL_TIMEOUT_CMD**:
+- **AUTOFS_DEV_IOCTL_EXPIRE_CMD**:
+- **AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD**:  These all have the same
+    function as the similarly named **AUTOFS_IOC** ioctls, except
+    that **FAIL** can be given an explicit error number in `arg1`
+    instead of assuming `ENOENT`, and this **EXPIRE** command
+    corresponds to **AUTOFS_IOC_EXPIRE_MULTI**.
+
+Catatonic mode
+--------------
+
+As mentioned, an autofs mount can enter "catatonic" mode.  This
+happens if a write to the notification pipe fails, or if it is
+explicitly requested by an `ioctl`.
+
+When entering catatonic mode, the pipe is closed and any pending
+notifications are acknowledged with the error `ENOENT`.
+
+Once in catatonic mode attempts to access non-existing names will
+result in `ENOENT` while attempts to access existing directories will
+be treated in the same way as if they came from the daemon, so mount
+traps will not fire.
+
+When the filesystem is mounted a _uid_ and _gid_ can be given which
+set the ownership of directories and symbolic links.  When the
+filesystem is in catatonic mode, any process with a matching UID can
+create directories or symlinks in the root directory, but not in other
+directories.
+
+Catatonic mode can only be left via the
+**AUTOFS_DEV_IOCTL_OPENMOUNT_CMD** ioctl on the `/dev/autofs`.
+
+autofs, name spaces, and shared mounts
+--------------------------------------
+
+With bind mounts and name spaces it is possible for an autofs
+filesystem to appear at multiple places in one or more filesystem
+name spaces.  For this to work sensibly, the autofs filesystem should
+always be mounted "shared". e.g.
+
+> `mount --make-shared /autofs/mount/point`
+
+The automount daemon is only able to mange a single mount location for
+an autofs filesystem and if mounts on that are not 'shared', other
+locations will not behave as expected.  In particular access to those
+other locations will likely result in the `ELOOP` error
+
+> Too many levels of symbolic links
diff --git a/Documentation/filesystems/ntfs.txt b/Documentation/filesystems/ntfs.txt
index 61947facfc07..553f10d03076 100644
--- a/Documentation/filesystems/ntfs.txt
+++ b/Documentation/filesystems/ntfs.txt
@@ -14,7 +14,6 @@ Table of contents
   - The Device-Mapper driver
   - The Software RAID / MD driver
   - Limitations when using the MD driver
-- ChangeLog
 
 
 Overview
@@ -450,270 +449,3 @@ number of sectors BEFORE attempting to use it.  You have been warned!
 
 Even better is to simply use the Device-Mapper for linear raid and then you do
 not have this problem with odd numbers of sectors.
-
-
-ChangeLog
-=========
-
-2.1.30:
-	- Fix writev() (it kept writing the first segment over and over again
-	  instead of moving onto subsequent segments).
-	- Fix crash in ntfs_mft_record_alloc() when mapping the new extent mft
-	  record failed.
-2.1.29:
-	- Fix a deadlock when mounting read-write.
-2.1.28:
-	- Fix a deadlock.
-2.1.27:
-	- Implement page migration support so the kernel can move memory used
-	  by NTFS files and directories around for management purposes.
-	- Add support for writing to sparse files created with Windows XP SP2.
-	- Many minor improvements and bug fixes.
-2.1.26:
-	- Implement support for sector sizes above 512 bytes (up to the maximum
-	  supported by NTFS which is 4096 bytes).
-	- Enhance support for NTFS volumes which were supported by Windows but
-	  not by Linux due to invalid attribute list attribute flags.
-	- A few minor updates and bug fixes.
-2.1.25:
-	- Write support is now extended with write(2) being able to both
-	  overwrite existing file data and to extend files.  Also, if a write
-	  to a sparse region occurs, write(2) will fill in the hole.  Note,
-	  mmap(2) based writes still do not support writing into holes or
-	  writing beyond the initialized size.
-	- Write support has a new feature and that is that truncate(2) and
-	  open(2) with O_TRUNC are now implemented thus files can be both made
-	  smaller and larger.
-	- Note: Both write(2) and truncate(2)/open(2) with O_TRUNC still have
-	  limitations in that they
-	  - only provide limited support for highly fragmented files.
-	  - only work on regular, i.e. uncompressed and unencrypted files.
-	  - never create sparse files although this will change once directory
-	    operations are implemented.
-	- Lots of bug fixes and enhancements across the board.
-2.1.24:
-	- Support journals ($LogFile) which have been modified by chkdsk.  This
-	  means users can boot into Windows after we marked the volume dirty.
-	  The Windows boot will run chkdsk and then reboot.  The user can then
-	  immediately boot into Linux rather than having to do a full Windows
-	  boot first before rebooting into Linux and we will recognize such a
-	  journal and empty it as it is clean by definition.
-	- Support journals ($LogFile) with only one restart page as well as
-	  journals with two different restart pages.  We sanity check both and
-	  either use the only sane one or the more recent one of the two in the
-	  case that both are valid.
-	- Lots of bug fixes and enhancements across the board.
-2.1.23:
-	- Stamp the user space journal, aka transaction log, aka $UsnJrnl, if
-	  it is present and active thus telling Windows and applications using
-	  the transaction log that changes can have happened on the volume
-	  which are not recorded in $UsnJrnl.
-	- Detect the case when Windows has been hibernated (suspended to disk)
-	  and if this is the case do not allow (re)mounting read-write to
-	  prevent data corruption when you boot back into the suspended
-	  Windows session.
-	- Implement extension of resident files using the normal file write
-	  code paths, i.e. most very small files can be extended to be a little
-	  bit bigger but not by much.
-	- Add new mount option "disable_sparse".  (See list of mount options
-	  above for details.)
-	- Improve handling of ntfs volumes with errors and strange boot sectors
-	  in particular.
-	- Fix various bugs including a nasty deadlock that appeared in recent
-	  kernels (around 2.6.11-2.6.12 timeframe).
-2.1.22:
-	- Improve handling of ntfs volumes with errors.
-	- Fix various bugs and race conditions.
-2.1.21:
-	- Fix several race conditions and various other bugs.
-	- Many internal cleanups, code reorganization, optimizations, and mft
-	  and index record writing code rewritten to fit in with the changes.
-	- Update Documentation/filesystems/ntfs.txt with instructions on how to
-	  use the Device-Mapper driver with NTFS ftdisk/LDM raid.
-2.1.20:
-	- Fix two stupid bugs introduced in 2.1.18 release.
-2.1.19:
-	- Minor bugfix in handling of the default upcase table.
-	- Many internal cleanups and improvements.  Many thanks to Linus
-	  Torvalds and Al Viro for the help and advice with the sparse
-	  annotations and cleanups.
-2.1.18:
-	- Fix scheduling latencies at mount time.  (Ingo Molnar)
-	- Fix endianness bug in a little traversed portion of the attribute
-	  lookup code.
-2.1.17:
-	- Fix bugs in mount time error code paths.
-2.1.16:
-	- Implement access time updates (including mtime and ctime).
-	- Implement fsync(2), fdatasync(2), and msync(2) system calls.
-	- Enable the readv(2) and writev(2) system calls.
-	- Enable access via the asynchronous io (aio) API by adding support for
-	  the aio_read(3) and aio_write(3) functions.
-2.1.15:
-	- Invalidate quotas when (re)mounting read-write.
-	  NOTE:  This now only leave user space journalling on the side.  (See
-	  note for version 2.1.13, below.)
-2.1.14:
-	- Fix an NFSd caused deadlock reported by several users.
-2.1.13:
-	- Implement writing of inodes (access time updates are not implemented
-	  yet so mounting with -o noatime,nodiratime is enforced).
-	- Enable writing out of resident files so you can now overwrite any
-	  uncompressed, unencrypted, nonsparse file as long as you do not
-	  change the file size.
-	- Add housekeeping of ntfs system files so that ntfsfix no longer needs
-	  to be run after writing to an NTFS volume.
-	  NOTE:  This still leaves quota tracking and user space journalling on
-	  the side but they should not cause data corruption.  In the worst
-	  case the charged quotas will be out of date ($Quota) and some
-	  userspace applications might get confused due to the out of date
-	  userspace journal ($UsnJrnl).
-2.1.12:
-	- Fix the second fix to the decompression engine from the 2.1.9 release
-	  and some further internals cleanups.
-2.1.11:
-	- Driver internal cleanups.
-2.1.10:
-	- Force read-only (re)mounting of volumes with unsupported volume
-	  flags and various cleanups.
-2.1.9:
-	- Fix two bugs in handling of corner cases in the decompression engine.
-2.1.8:
-	- Read the $MFT mirror and compare it to the $MFT and if the two do not
-	  match, force a read-only mount and do not allow read-write remounts.
-	- Read and parse the $LogFile journal and if it indicates that the
-	  volume was not shutdown cleanly, force a read-only mount and do not
-	  allow read-write remounts.  If the $LogFile indicates a clean
-	  shutdown and a read-write (re)mount is requested, empty $LogFile to
-	  ensure that Windows cannot cause data corruption by replaying a stale
-	  journal after Linux has written to the volume.
-	- Improve time handling so that the NTFS time is fully preserved when
-	  converted to kernel time and only up to 99 nano-seconds are lost when
-	  kernel time is converted to NTFS time.
-2.1.7:
-	- Enable NFS exporting of mounted NTFS volumes.
-2.1.6:
-	- Fix minor bug in handling of compressed directories that fixes the
-	  erroneous "du" and "stat" output people reported.
-2.1.5:
-	- Minor bug fix in attribute list attribute handling that fixes the
-	  I/O errors on "ls" of certain fragmented files found by at least two
-	  people running Windows XP.
-2.1.4:
-	- Minor update allowing compilation with all gcc versions (well, the
-	  ones the kernel can be compiled with anyway).
-2.1.3:
-	- Major bug fixes for reading files and volumes in corner cases which
-	  were being hit by Windows 2k/XP users.
-2.1.2:
-	- Major bug fixes alleviating the hangs in statfs experienced by some
-	  users.
-2.1.1:
-	- Update handling of compressed files so people no longer get the
-	  frequently reported warning messages about initialized_size !=
-	  data_size.
-2.1.0:
-	- Add configuration option for developmental write support.
-	- Initial implementation of file overwriting. (Writes to resident files
-	  are not written out to disk yet, so avoid writing to files smaller
-	  than about 1kiB.)
-	- Intercept/abort changes in file size as they are not implemented yet.
-2.0.25:
-	- Minor bugfixes in error code paths and small cleanups.
-2.0.24:
-	- Small internal cleanups.
-	- Support for sendfile system call. (Christoph Hellwig)
-2.0.23:
-	- Massive internal locking changes to mft record locking. Fixes
-	  various race conditions and deadlocks.
-	- Fix ntfs over loopback for compressed files by adding an
-	  optimization barrier. (gcc was screwing up otherwise ?)
-	Thanks go to Christoph Hellwig for pointing these two out:
-	- Remove now unused function fs/ntfs/malloc.h::vmalloc_nofs().
-	- Fix ntfs_free() for ia64 and parisc.
-2.0.22:
-	- Small internal cleanups.
-2.0.21:
-	These only affect 32-bit architectures:
-	- Check for, and refuse to mount too large volumes (maximum is 2TiB).
-	- Check for, and refuse to open too large files and directories
-	  (maximum is 16TiB).
-2.0.20:
-	- Support non-resident directory index bitmaps. This means we now cope
-	  with huge directories without problems.
-	- Fix a page leak that manifested itself in some cases when reading
-	  directory contents.
-	- Internal cleanups.
-2.0.19:
-	- Fix race condition and improvements in block i/o interface.
-	- Optimization when reading compressed files.
-2.0.18:
-	- Fix race condition in reading of compressed files.
-2.0.17:
-	- Cleanups and optimizations.
-2.0.16:
-	- Fix stupid bug introduced in 2.0.15 in new attribute inode API.
-	- Big internal cleanup replacing the mftbmp access hacks by using the
-	  new attribute inode API instead.
-2.0.15:
-	- Bug fix in parsing of remount options.
-	- Internal changes implementing attribute (fake) inodes allowing all
-	  attribute i/o to go via the page cache and to use all the normal
-	  vfs/mm functionality.
-2.0.14:
-	- Internal changes improving run list merging code and minor locking
-	  change to not rely on BKL in ntfs_statfs().
-2.0.13:
-	- Internal changes towards using iget5_locked() in preparation for
-	  fake inodes and small cleanups to ntfs_volume structure.
-2.0.12:
-	- Internal cleanups in address space operations made possible by the
-	  changes introduced in the previous release.
-2.0.11:
-	- Internal updates and cleanups introducing the first step towards
-	  fake inode based attribute i/o.
-2.0.10:
-	- Microsoft says that the maximum number of inodes is 2^32 - 1. Update
-	  the driver accordingly to only use 32-bits to store inode numbers on
-	  32-bit architectures. This improves the speed of the driver a little.
-2.0.9:
-	- Change decompression engine to use a single buffer. This should not
-	  affect performance except perhaps on the most heavy i/o on SMP
-	  systems when accessing multiple compressed files from multiple
-	  devices simultaneously.
-	- Minor updates and cleanups.
-2.0.8:
-	- Remove now obsolete show_inodes and posix mount option(s).
-	- Restore show_sys_files mount option.
-	- Add new mount option case_sensitive, to determine if the driver
-	  treats file names as case sensitive or not.
-	- Mostly drop support for short file names (for backwards compatibility
-	  we only support accessing files via their short file name if one
-	  exists).
-	- Fix dcache aliasing issues wrt short/long file names.
-	- Cleanups and minor fixes.
-2.0.7:
-	- Just cleanups.
-2.0.6:
-	- Major bugfix to make compatible with other kernel changes. This fixes
-	  the hangs/oopses on umount.
-	- Locking cleanup in directory operations (remove BKL usage).
-2.0.5:
-	- Major buffer overflow bug fix.
-	- Minor cleanups and updates for kernel 2.5.12.
-2.0.4:
-	- Cleanups and updates for kernel 2.5.11.
-2.0.3:
-	- Small bug fixes, cleanups, and performance improvements.
-2.0.2:
-	- Use default fmask of 0177 so that files are no executable by default.
-	  If you want owner executable files, just use fmask=0077.
-	- Update for kernel 2.5.9 but preserve backwards compatibility with
-	  kernel 2.5.7.
-	- Minor bug fixes, cleanups, and updates.
-2.0.1:
-	- Minor updates, primarily set the executable bit by default on files
-	  so they can be executed.
-2.0.0:
-	- Started ChangeLog.
-
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 61d65cc65c54..fceff7c00a3c 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -237,7 +237,7 @@ noted. This means that most methods can block safely. All methods are
 only called from a process context (i.e. not from an interrupt handler
 or bottom half).
 
-  alloc_inode: this method is called by inode_alloc() to allocate memory
+  alloc_inode: this method is called by alloc_inode() to allocate memory
  	for struct inode and initialize it.  If this function is not
  	defined, a simple 'struct inode' is allocated.  Normally
  	alloc_inode will be used to allocate a larger structure which
@@ -826,7 +826,7 @@ struct file_operations {
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, struct pipe_inode_info *, size_t, unsigned int);
-	int (*setlease)(struct file *, long arg, struct file_lock **);
+	int (*setlease)(struct file *, long arg, struct file_lock **, void **);
 	long (*fallocate)(struct file *, int mode, loff_t offset, loff_t len);
 	int (*show_fdinfo)(struct seq_file *m, struct file *f);
 };
@@ -895,8 +895,9 @@ otherwise noted.
   splice_read: called by the VFS to splice data from file to a pipe. This
 	       method is used by the splice(2) system call
 
-  setlease: called by the VFS to set or release a file lock lease.
-	    setlease has the file_lock_lock held and must not sleep.
+  setlease: called by the VFS to set or release a file lock lease. setlease
+	    implementations should call generic_setlease to record or remove
+	    the lease in the inode after setting it.
 
   fallocate: called by the VFS to preallocate blocks or punch a hole.
 
diff --git a/Documentation/gpio/driver.txt b/Documentation/gpio/driver.txt
index 18790c237977..31e0b5db55d8 100644
--- a/Documentation/gpio/driver.txt
+++ b/Documentation/gpio/driver.txt
@@ -124,7 +124,8 @@ symbol:
 * gpiochip_set_chained_irqchip(): sets up a chained irq handler for a
   gpio_chip from a parent IRQ and passes the struct gpio_chip* as handler
   data. (Notice handler data, since the irqchip data is likely used by the
-  parent irqchip!) This is for the chained type of chip.
+  parent irqchip!) This is for the chained type of chip. This is also used
+  to set up a nested irqchip if NULL is passed as handler.
 
 To use the helpers please keep the following in mind:
 
@@ -178,7 +179,8 @@ does not help since it pins the module to the kernel forever (it calls
 try_module_get()). A GPIO driver can use the following functions instead
 to request and free descriptors without being pinned to the kernel forever.
 
-	int gpiochip_request_own_desc(struct gpio_desc *desc, const char *label)
+	struct gpio_desc *gpiochip_request_own_desc(struct gpio_desc *desc,
+						    const char *label)
 
 	void gpiochip_free_own_desc(struct gpio_desc *desc)
 
diff --git a/Documentation/hwmon/k10temp b/Documentation/hwmon/k10temp
index ee6d30ec1522..254d2f55345a 100644
--- a/Documentation/hwmon/k10temp
+++ b/Documentation/hwmon/k10temp
@@ -11,7 +11,7 @@ Supported chips:
   Socket S1G2: Athlon (X2), Sempron (X2), Turion X2 (Ultra)
 * AMD Family 12h processors: "Llano" (E2/A4/A6/A8-Series)
 * AMD Family 14h processors: "Brazos" (C/E/G/Z-Series)
-* AMD Family 15h processors: "Bulldozer" (FX-Series), "Trinity", "Kaveri"
+* AMD Family 15h processors: "Bulldozer" (FX-Series), "Trinity", "Kaveri", "Carrizo"
 * AMD Family 16h processors: "Kabini", "Mullins"
 
   Prefix: 'k10temp'
diff --git a/Documentation/hwmon/menf21bmc b/Documentation/hwmon/menf21bmc
new file mode 100644
index 000000000000..2a273a065c5e
--- /dev/null
+++ b/Documentation/hwmon/menf21bmc
@@ -0,0 +1,50 @@
+Kernel driver menf21bmc_hwmon
+=============================
+
+Supported chips:
+	* MEN 14F021P00
+	  Prefix: 'menf21bmc_hwmon'
+	  Adresses scanned: -
+
+Author: Andreas Werner <andreas.werner@men.de>
+
+Description
+-----------
+
+The menf21bmc is a Board Management Controller (BMC) which provides an I2C
+interface to the host to access the features implemented in the BMC.
+
+This driver gives access to the voltage monitoring feature of the main
+voltages of the board.
+The voltage sensors are connected to the ADC inputs of the BMC which is
+a PIC16F917 Mikrocontroller.
+
+Usage Notes
+-----------
+
+This driver is part of the MFD driver named "menf21bmc" and does
+not auto-detect devices.
+You will have to instantiate the MFD driver explicitly.
+Please see Documentation/i2c/instantiating-devices for
+details.
+
+Sysfs entries
+-------------
+
+The following attributes are supported. All attributes are read only
+The Limits are read once by the driver.
+
+in0_input	+3.3V input voltage
+in1_input	+5.0V input voltage
+in2_input	+12.0V input voltage
+in3_input	+5V Standby input voltage
+in4_input	VBAT (on board battery)
+
+in[0-4]_min	Minimum voltage limit
+in[0-4]_max	Maximum voltage limit
+
+in0_label	"MON_3_3V"
+in1_label	"MON_5V"
+in2_label	"MON_12V"
+in3_label	"5V_STANDBY"
+in4_label	"VBAT"
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 7e240a7c9ab1..8136e1fd30fd 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -313,6 +313,7 @@ Code  Seq#(hex)	Include File		Comments
 0xB1	00-1F	PPPoX			<mailto:mostrows@styx.uwaterloo.ca>
 0xB3	00	linux/mmc/ioctl.h
 0xC0	00-0F	linux/usb/iowarrior.h
+0xCA	00-0F	uapi/misc/cxl.h
 0xCB	00-1F	CBM serial IEC bus	in development:
 					<mailto:michael.klein@puffin.lb.shuttle.de>
 0xCD	01	linux/reiserfs_fs.h
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index 764f5991a3fc..a311db829e9b 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -174,7 +174,7 @@ more details, with real examples.
 
 --- 3.3 Loadable module goals - obj-m
 
-	$(obj-m) specify object files which are built as loadable
+	$(obj-m) specifies object files which are built as loadable
 	kernel modules.
 
 	A module may be built from one source file or several source
@@ -277,7 +277,7 @@ more details, with real examples.
 	down in the ext2 directory.
 	Kbuild only uses this information to decide that it needs to visit
 	the directory, it is the Makefile in the subdirectory that
-	specifies what is modules and what is built-in.
+	specifies what is modular and what is built-in.
 
 	It is good practice to use a CONFIG_ variable when assigning directory
 	names. This allows kbuild to totally skip the directory if the
@@ -403,7 +403,7 @@ more details, with real examples.
 	echoing information to user in a rule is often a good practice
 	but when execution "make -s" one does not expect to see any output
 	except for warnings/errors.
-	To support this kbuild define $(kecho) which will echo out the
+	To support this kbuild defines $(kecho) which will echo out the
 	text following $(kecho) to stdout except if "make -s" is used.
 
 	Example:
@@ -417,7 +417,7 @@ more details, with real examples.
 
 	The kernel may be built with several different versions of
 	$(CC), each supporting a unique set of features and options.
-	kbuild provide basic support to check for valid options for $(CC).
+	kbuild provides basic support to check for valid options for $(CC).
 	$(CC) is usually the gcc compiler, but other alternatives are
 	available.
 
@@ -456,8 +456,8 @@ more details, with real examples.
 	Note: as-instr-option uses KBUILD_AFLAGS for $(AS) options
 
     cc-option
-	cc-option is used to check if $(CC) supports a given option, and not
-	supported to use an optional second option.
+	cc-option is used to check if $(CC) supports a given option, and if
+	not supported to use an optional second option.
 
 	Example:
 		#arch/x86/Makefile
@@ -557,8 +557,8 @@ more details, with real examples.
 			false ; \
 		fi
 
-	In this example for a specific GCC version the build will error out explaining
-	to the user why it stops.
+	In this example for a specific GCC version the build will error out
+	explaining to the user why it stops.
 
     cc-cross-prefix
 	cc-cross-prefix is used to check if there exists a $(CC) in path with
@@ -656,7 +656,7 @@ Both possibilities are described in the following.
 	In the example above the executable is composed of the C++ file
 	qconf.cc - identified by $(qconf-cxxobjs).
 
-	If qconf is composed by a mixture of .c and .cc files, then an
+	If qconf is composed of a mixture of .c and .cc files, then an
 	additional line can be used to identify this.
 
 	Example:
@@ -733,7 +733,7 @@ Both possibilities are described in the following.
 		hostprogs-$(CONFIG_KALLSYMS) += kallsyms
 
 	Kbuild knows about both 'y' for built-in and 'm' for module.
-	So if a config symbol evaluate to 'm', kbuild will still build
+	So if a config symbol evaluates to 'm', kbuild will still build
 	the binary. In other words, Kbuild handles hostprogs-m exactly
 	like hostprogs-y. But only hostprogs-y is recommended to be used
 	when no CONFIG symbols are involved.
@@ -754,8 +754,8 @@ Additional files can be specified in kbuild makefiles by use of $(clean-files).
 		#drivers/pci/Makefile
 		clean-files := devlist.h classlist.h
 
-When executing "make clean", the two files "devlist.h classlist.h" will
-be deleted. Kbuild will assume files to be in same relative directory as the
+When executing "make clean", the two files "devlist.h classlist.h" will be
+deleted. Kbuild will assume files to be in the same relative directory as the
 Makefile except if an absolute path is specified (path starting with '/').
 
 To delete a directory hierarchy use:
@@ -786,7 +786,7 @@ is not sufficient this sometimes needs to be explicit.
 The above assignment instructs kbuild to descend down in the
 directory compressed/ when "make clean" is executed.
 
-To support the clean infrastructure in the Makefiles that builds the
+To support the clean infrastructure in the Makefiles that build the
 final bootimage there is an optional target named archclean:
 
 	Example:
@@ -818,17 +818,16 @@ a few targets.
 When kbuild executes, the following steps are followed (roughly):
 1) Configuration of the kernel => produce .config
 2) Store kernel version in include/linux/version.h
-3) Symlink include/asm to include/asm-$(ARCH)
-4) Updating all other prerequisites to the target prepare:
+3) Updating all other prerequisites to the target prepare:
    - Additional prerequisites are specified in arch/$(ARCH)/Makefile
-5) Recursively descend down in all directories listed in
+4) Recursively descend down in all directories listed in
    init-* core* drivers-* net-* libs-* and build all targets.
    - The values of the above variables are expanded in arch/$(ARCH)/Makefile.
-6) All object files are then linked and the resulting file vmlinux is
+5) All object files are then linked and the resulting file vmlinux is
    located at the root of the obj tree.
    The very first objects linked are listed in head-y, assigned by
    arch/$(ARCH)/Makefile.
-7) Finally, the architecture-specific part does any required post processing
+6) Finally, the architecture-specific part does any required post processing
    and builds the final bootimage.
    - This includes building boot records
    - Preparing initrd images and the like
@@ -927,7 +926,7 @@ When kbuild executes, the following steps are followed (roughly):
 
     KBUILD_AFLAGS_MODULE   Options for $(AS) when building modules
 
-	$(KBUILD_AFLAGS_MODULE) is used to add arch specific options that
+	$(KBUILD_AFLAGS_MODULE) is used to add arch-specific options that
 	are used for $(AS).
 	From commandline AFLAGS_MODULE shall be used (see kbuild.txt).
 
@@ -938,13 +937,13 @@ When kbuild executes, the following steps are followed (roughly):
 
     KBUILD_CFLAGS_MODULE   Options for $(CC) when building modules
 
-	$(KBUILD_CFLAGS_MODULE) is used to add arch specific options that
+	$(KBUILD_CFLAGS_MODULE) is used to add arch-specific options that
 	are used for $(CC).
 	From commandline CFLAGS_MODULE shall be used (see kbuild.txt).
 
     KBUILD_LDFLAGS_MODULE   Options for $(LD) when linking modules
 
-	$(KBUILD_LDFLAGS_MODULE) is used to add arch specific options
+	$(KBUILD_LDFLAGS_MODULE) is used to add arch-specific options
 	used when linking modules. This is often a linker script.
 	From commandline LDFLAGS_MODULE shall be used (see kbuild.txt).
 
@@ -1066,7 +1065,7 @@ When kbuild executes, the following steps are followed (roughly):
 
     extra-y
 
-	extra-y specify additional targets created in the current
+	extra-y specifies additional targets created in the current
 	directory, in addition to any targets specified by obj-*.
 
 	Listing all targets in extra-y is required for two purposes:
@@ -1093,7 +1092,7 @@ When kbuild executes, the following steps are followed (roughly):
 
 	Usage:
 		target: source(s) FORCE
-			$(call if_changed,ld/objcopy/gzip)
+			$(call if_changed,ld/objcopy/gzip/...)
 
 	When the rule is evaluated, it is checked to see if any files
 	need an update, or the command line has changed since the last
@@ -1111,7 +1110,7 @@ When kbuild executes, the following steps are followed (roughly):
 	significant; for instance, the below will fail (note the extra space
 	after the comma):
 		target: source(s) FORCE
-	#WRONG!#	$(call if_changed, ld/objcopy/gzip)
+	#WRONG!#	$(call if_changed, ld/objcopy/gzip/...)
 
     ld
 	Link target. Often, LDFLAGS_$@ is used to set specific options to ld.
@@ -1142,8 +1141,8 @@ When kbuild executes, the following steps are followed (roughly):
 		2) delete target during make clean
 
 	The ": %: %.o" part of the prerequisite is a shorthand that
-	free us from listing the setup.o and bootsect.o files.
-	Note: It is a common mistake to forget the "target :=" assignment,
+	frees us from listing the setup.o and bootsect.o files.
+	Note: It is a common mistake to forget the "targets :=" assignment,
 	      resulting in the target file being recompiled for no
 	      obvious reason.
 
@@ -1164,29 +1163,6 @@ When kbuild executes, the following steps are followed (roughly):
 		clean-files += *.dtb
 		DTC_FLAGS ?= -p 1024
 
-    dtc_cpp
-	This is just like dtc as describe above, except that the C pre-
-	processor is invoked upon the .dtsp file before compiling the result
-	with dtc.
-
-	In order for build dependencies to work, all files compiled using
-	dtc_cpp must use the C pre-processor's #include functionality and not
-	dtc's /include/ functionality.
-
-	Using the C pre-processor allows use of #define to create named
-	constants. In turn, the #defines will typically appear in a header
-	file, which may be shared with regular C code. Since the dtc language
-	represents a data structure rather than code in C syntax, similar
-	restrictions are placed on a header file included by a device tree
-	file as for a header file included by an assembly language file.
-	In particular, the C pre-processor is passed -x assembler-with-cpp,
-	which sets macro __ASSEMBLY__. __DTS__ is also set. These allow header
-	files to restrict their content to that compatible with device tree
-	source.
-
-	A central rule exists to create $(obj)/%.dtb from $(src)/%.dtsp;
-	architecture Makefiles do no need to explicitly write out that rule.
-
 --- 6.8 Custom kbuild commands
 
 	When kbuild is executing with KBUILD_VERBOSE=0, then only a shorthand
@@ -1237,11 +1213,11 @@ When kbuild executes, the following steps are followed (roughly):
 	When building the *.lds target, kbuild uses the variables:
 	KBUILD_CPPFLAGS	: Set in top-level Makefile
 	cppflags-y	: May be set in the kbuild makefile
-	CPPFLAGS_$(@F)  : Target specific flags.
+	CPPFLAGS_$(@F)  : Target-specific flags.
 	                  Note that the full filename is used in this
 	                  assignment.
 
-	The kbuild infrastructure for *lds file are used in several
+	The kbuild infrastructure for *lds files is used in several
 	architecture-specific files.
 
 --- 6.10 Generic header files
@@ -1254,11 +1230,11 @@ When kbuild executes, the following steps are followed (roughly):
 
 === 7 Kbuild syntax for exported headers
 
-The kernel include a set of headers that is exported to userspace.
+The kernel includes a set of headers that is exported to userspace.
 Many headers can be exported as-is but other headers require a
 minimal pre-processing before they are ready for user-space.
 The pre-processing does:
-- drop kernel specific annotations
+- drop kernel-specific annotations
 - drop include of compiler.h
 - drop all sections that are kernel internal (guarded by ifdef __KERNEL__)
 
@@ -1268,7 +1244,7 @@ See subsequent chapter for the syntax of the Kbuild file.
 
 	--- 7.1 header-y
 
-	header-y specify header files to be exported.
+	header-y specifies header files to be exported.
 
 		Example:
 			#include/linux/Kbuild
@@ -1278,7 +1254,7 @@ See subsequent chapter for the syntax of the Kbuild file.
 	The convention is to list one file per line and
 	preferably in alphabetic order.
 
-	header-y also specify which subdirectories to visit.
+	header-y also specifies which subdirectories to visit.
 	A subdirectory is identified by a trailing '/' which
 	can be seen in the example above for the usb subdirectory.
 
@@ -1296,9 +1272,9 @@ See subsequent chapter for the syntax of the Kbuild file.
 
 	--- 7.3 destination-y
 
-	When an architecture have a set of exported headers that needs to be
+	When an architecture has a set of exported headers that needs to be
 	exported to a different directory destination-y is used.
-	destination-y specify the destination directory for all exported
+	destination-y specifies the destination directory for all exported
 	headers in the file where it is present.
 
 		Example:
@@ -1391,9 +1367,9 @@ The top Makefile exports the following variables:
 
     INSTALL_MOD_STRIP
 
-	If this variable is specified, will cause modules to be stripped
+	If this variable is specified, it will cause modules to be stripped
 	after they are installed.  If INSTALL_MOD_STRIP is '1', then the
-	default option --strip-debug will be used.  Otherwise,
+	default option --strip-debug will be used.  Otherwise, the
 	INSTALL_MOD_STRIP value will be used as the option(s) to the strip
 	command.
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index d9a452e8fb9b..b62bdcb1eb39 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -605,11 +605,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			See Documentation/s390/CommonIO for details.
 	clk_ignore_unused
 			[CLK]
-			Keep all clocks already enabled by bootloader on,
-			even if no driver has claimed them. This is useful
-			for debug and development, but should not be
-			needed on a platform with proper driver support.
-			For more information, see Documentation/clk.txt.
+			Prevents the clock framework from automatically gating
+			clocks that have not been explicitly enabled by a Linux
+			device driver but are enabled in hardware at reset or
+			by the bootloader/firmware. Note that this does not
+			force such clocks to be always-on nor does it reserve
+			those clocks in any way. This parameter is useful for
+			debug and development, but should not be needed on a
+			platform with proper driver support.  For more
+			information, see Documentation/clk.txt.
 
 	clock=		[BUGS=X86-32, HW] gettimeofday clocksource override.
 			[Deprecated]
@@ -656,7 +660,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Sets the size of kernel global memory area for
 			contiguous memory allocations and optionally the
 			placement constraint by the physical address range of
-			memory allocations. For more information, see
+			memory allocations. A value of 0 disables CMA
+			altogether. For more information, see
 			include/linux/dma-contiguous.h
 
 	cmo_free_hint=	[PPC] Format: { yes | no }
@@ -1322,7 +1327,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Set number of hash buckets for inode cache.
 
 	ima_appraise=	[IMA] appraise integrity measurements
-			Format: { "off" | "enforce" | "fix" }
+			Format: { "off" | "enforce" | "fix" | "log" }
 			default: "enforce"
 
 	ima_appraise_tcb [IMA]
@@ -1722,6 +1727,49 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	lockd.nlm_udpport=M	[NFS] Assign UDP port.
 			Format: <integer>
 
+	locktorture.nreaders_stress= [KNL]
+			Set the number of locking read-acquisition kthreads.
+			Defaults to being automatically set based on the
+			number of online CPUs.
+
+	locktorture.nwriters_stress= [KNL]
+			Set the number of locking write-acquisition kthreads.
+
+	locktorture.onoff_holdoff= [KNL]
+			Set time (s) after boot for CPU-hotplug testing.
+
+	locktorture.onoff_interval= [KNL]
+			Set time (s) between CPU-hotplug operations, or
+			zero to disable CPU-hotplug testing.
+
+	locktorture.shuffle_interval= [KNL]
+			Set task-shuffle interval (jiffies).  Shuffling
+			tasks allows some CPUs to go into dyntick-idle
+			mode during the locktorture test.
+
+	locktorture.shutdown_secs= [KNL]
+			Set time (s) after boot system shutdown.  This
+			is useful for hands-off automated testing.
+
+	locktorture.stat_interval= [KNL]
+			Time (s) between statistics printk()s.
+
+	locktorture.stutter= [KNL]
+			Time (s) to stutter testing, for example,
+			specifying five seconds causes the test to run for
+			five seconds, wait for five seconds, and so on.
+			This tests the locking primitive's ability to
+			transition abruptly to and from idle.
+
+	locktorture.torture_runnable= [BOOT]
+			Start locktorture running at boot time.
+
+	locktorture.torture_type= [KNL]
+			Specify the locking implementation to test.
+
+	locktorture.verbose= [KNL]
+			Enable additional printk() statements.
+
 	logibm.irq=	[HW,MOUSE] Logitech Bus Mouse Driver
 			Format: <irq>
 
@@ -2899,6 +2947,24 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Lazy RCU callbacks are those which RCU can
 			prove do nothing more than free memory.
 
+	rcutorture.cbflood_inter_holdoff= [KNL]
+			Set holdoff time (jiffies) between successive
+			callback-flood tests.
+
+	rcutorture.cbflood_intra_holdoff= [KNL]
+			Set holdoff time (jiffies) between successive
+			bursts of callbacks within a given callback-flood
+			test.
+
+	rcutorture.cbflood_n_burst= [KNL]
+			Set the number of bursts making up a given
+			callback-flood test.  Set this to zero to
+			disable callback-flood testing.
+
+	rcutorture.cbflood_n_per_burst= [KNL]
+			Set the number of callbacks to be registered
+			in a given burst of a callback-flood test.
+
 	rcutorture.fqs_duration= [KNL]
 			Set duration of force_quiescent_state bursts.
 
@@ -2938,7 +3004,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Set time (s) between CPU-hotplug operations, or
 			zero to disable CPU-hotplug testing.
 
-	rcutorture.rcutorture_runnable= [BOOT]
+	rcutorture.torture_runnable= [BOOT]
 			Start rcutorture running at boot time.
 
 	rcutorture.shuffle_interval= [KNL]
@@ -3000,6 +3066,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	rcupdate.rcu_cpu_stall_timeout= [KNL]
 			Set timeout for RCU CPU stall warning messages.
 
+	rcupdate.rcu_task_stall_timeout= [KNL]
+			Set timeout in jiffies for RCU task stall warning
+			messages.  Disable with a value less than or equal
+			to zero.
+
 	rdinit=		[KNL]
 			Format: <full_path>
 			Run specified binary instead of /init from the ramdisk,
@@ -3158,6 +3229,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	slram=		[HW,MTD]
 
+	slab_nomerge	[MM]
+			Disable merging of slabs with similar size. May be
+			necessary if there is some reason to distinguish
+			allocs to different slabs. Debug options disable
+			merging on their own.
+			For more information see Documentation/vm/slub.txt.
+
 	slab_max_order=	[MM, SLAB]
 			Determines the maximum allowed order for slabs.
 			A high setting may cause OOMs due to memory
@@ -3193,11 +3271,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			For more information see Documentation/vm/slub.txt.
 
 	slub_nomerge	[MM, SLUB]
-			Disable merging of slabs with similar size. May be
-			necessary if there is some reason to distinguish
-			allocs to different slabs. Debug options disable
-			merging on their own.
-			For more information see Documentation/vm/slub.txt.
+			Same with slab_nomerge. This is supported for legacy.
+			See slab_nomerge for more information.
 
 	smart2=		[HW]
 			Format: <io1>[,<io2>[,...,<io8>]]
@@ -3321,11 +3396,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	tdfx=		[HW,DRM]
 
-	test_suspend=	[SUSPEND]
+	test_suspend=	[SUSPEND][,N]
 			Specify "mem" (for Suspend-to-RAM) or "standby" (for
-			standby suspend) as the system sleep state to briefly
-			enter during system startup.  The system is woken from
-			this state using a wakeup-capable RTC alarm.
+			standby suspend) or "freeze" (for suspend type freeze)
+			as the system sleep state during system startup with
+			the optional capability to repeat N number of times.
+			The system is woken from this state using a
+			wakeup-capable RTC alarm.
 
 	thash_entries=	[KNL,NET]
 			Set number of hash buckets for TCP connection
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 4bbeca8483ed..4227ec2e3ab2 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -300,6 +300,7 @@ architectures:
 - arm
 - ppc
 - mips
+- s390
 
 3. Configuring Kprobes
 
diff --git a/Documentation/lockdep-design.txt b/Documentation/locking/lockdep-design.txt
index 5dbc99c04f6e..5dbc99c04f6e 100644
--- a/Documentation/lockdep-design.txt
+++ b/Documentation/locking/lockdep-design.txt
diff --git a/Documentation/lockstat.txt b/Documentation/locking/lockstat.txt
index 72d010689751..7428773a1e69 100644
--- a/Documentation/lockstat.txt
+++ b/Documentation/locking/lockstat.txt
@@ -12,7 +12,7 @@ Because things like lock contention can severely impact performance.
 - HOW
 
 Lockdep already has hooks in the lock functions and maps lock instances to
-lock classes. We build on that (see Documentation/lockdep-design.txt).
+lock classes. We build on that (see Documentation/lokcing/lockdep-design.txt).
 The graph below shows the relation between the lock functions and the various
 hooks therein.
 
diff --git a/Documentation/locking/locktorture.txt b/Documentation/locking/locktorture.txt
new file mode 100644
index 000000000000..619f2bb136a5
--- /dev/null
+++ b/Documentation/locking/locktorture.txt
@@ -0,0 +1,147 @@
+Kernel Lock Torture Test Operation
+
+CONFIG_LOCK_TORTURE_TEST
+
+The CONFIG LOCK_TORTURE_TEST config option provides a kernel module
+that runs torture tests on core kernel locking primitives. The kernel
+module, 'locktorture', may be built after the fact on the running
+kernel to be tested, if desired. The tests periodically output status
+messages via printk(), which can be examined via the dmesg (perhaps
+grepping for "torture").  The test is started when the module is loaded,
+and stops when the module is unloaded. This program is based on how RCU
+is tortured, via rcutorture.
+
+This torture test consists of creating a number of kernel threads which
+acquire the lock and hold it for specific amount of time, thus simulating
+different critical region behaviors. The amount of contention on the lock
+can be simulated by either enlarging this critical region hold time and/or
+creating more kthreads.
+
+
+MODULE PARAMETERS
+
+This module has the following parameters:
+
+
+	    ** Locktorture-specific **
+
+nwriters_stress   Number of kernel threads that will stress exclusive lock
+		  ownership (writers). The default value is twice the number
+		  of online CPUs.
+
+nreaders_stress   Number of kernel threads that will stress shared lock
+		  ownership (readers). The default is the same amount of writer
+		  locks. If the user did not specify nwriters_stress, then
+		  both readers and writers be the amount of online CPUs.
+
+torture_type	  Type of lock to torture. By default, only spinlocks will
+		  be tortured. This module can torture the following locks,
+		  with string values as follows:
+
+		     o "lock_busted": Simulates a buggy lock implementation.
+
+		     o "spin_lock": spin_lock() and spin_unlock() pairs.
+
+		     o "spin_lock_irq": spin_lock_irq() and spin_unlock_irq()
+					pairs.
+
+		     o "rw_lock": read/write lock() and unlock() rwlock pairs.
+
+		     o "rw_lock_irq": read/write lock_irq() and unlock_irq()
+				      rwlock pairs.
+
+		     o "mutex_lock": mutex_lock() and mutex_unlock() pairs.
+
+		     o "rwsem_lock": read/write down() and up() semaphore pairs.
+
+torture_runnable  Start locktorture at boot time in the case where the
+		  module is built into the kernel, otherwise wait for
+		  torture_runnable to be set via sysfs before starting.
+		  By default it will begin once the module is loaded.
+
+
+	    ** Torture-framework (RCU + locking) **
+
+shutdown_secs	  The number of seconds to run the test before terminating
+		  the test and powering off the system.  The default is
+		  zero, which disables test termination and system shutdown.
+		  This capability is useful for automated testing.
+
+onoff_interval	  The number of seconds between each attempt to execute a
+		  randomly selected CPU-hotplug operation.  Defaults
+		  to zero, which disables CPU hotplugging.  In
+		  CONFIG_HOTPLUG_CPU=n kernels, locktorture will silently
+		  refuse to do any CPU-hotplug operations regardless of
+		  what value is specified for onoff_interval.
+
+onoff_holdoff	  The number of seconds to wait until starting CPU-hotplug
+		  operations.  This would normally only be used when
+		  locktorture was built into the kernel and started
+		  automatically at boot time, in which case it is useful
+		  in order to avoid confusing boot-time code with CPUs
+		  coming and going. This parameter is only useful if
+		  CONFIG_HOTPLUG_CPU is enabled.
+
+stat_interval	  Number of seconds between statistics-related printk()s.
+		  By default, locktorture will report stats every 60 seconds.
+		  Setting the interval to zero causes the statistics to
+		  be printed -only- when the module is unloaded, and this
+		  is the default.
+
+stutter		  The length of time to run the test before pausing for this
+		  same period of time.  Defaults to "stutter=5", so as
+		  to run and pause for (roughly) five-second intervals.
+		  Specifying "stutter=0" causes the test to run continuously
+		  without pausing, which is the old default behavior.
+
+shuffle_interval  The number of seconds to keep the test threads affinitied
+		  to a particular subset of the CPUs, defaults to 3 seconds.
+		  Used in conjunction with test_no_idle_hz.
+
+verbose		  Enable verbose debugging printing, via printk(). Enabled
+		  by default. This extra information is mostly related to
+		  high-level errors and reports from the main 'torture'
+		  framework.
+
+
+STATISTICS
+
+Statistics are printed in the following format:
+
+spin_lock-torture: Writes:  Total: 93746064  Max/Min: 0/0   Fail: 0
+   (A)		    (B)		   (C)		  (D)	       (E)
+
+(A): Lock type that is being tortured -- torture_type parameter.
+
+(B): Number of writer lock acquisitions. If dealing with a read/write primitive
+     a second "Reads" statistics line is printed.
+
+(C): Number of times the lock was acquired.
+
+(D): Min and max number of times threads failed to acquire the lock.
+
+(E): true/false values if there were errors acquiring the lock. This should
+     -only- be positive if there is a bug in the locking primitive's
+     implementation. Otherwise a lock should never fail (i.e., spin_lock()).
+     Of course, the same applies for (C), above. A dummy example of this is
+     the "lock_busted" type.
+
+USAGE
+
+The following script may be used to torture locks:
+
+	#!/bin/sh
+
+	modprobe locktorture
+	sleep 3600
+	rmmod locktorture
+	dmesg | grep torture:
+
+The output can be manually inspected for the error flag of "!!!".
+One could of course create a more elaborate script that automatically
+checked for such errors.  The "rmmod" command forces a "SUCCESS",
+"FAILURE", or "RCU_HOTPLUG" indication to be printk()ed.  The first
+two are self-explanatory, while the last indicates that while there
+were no locking failures, CPU-hotplug problems were detected.
+
+Also see: Documentation/RCU/torture.txt
diff --git a/Documentation/mutex-design.txt b/Documentation/locking/mutex-design.txt
index ee231ed09ec6..60c482df1a38 100644
--- a/Documentation/mutex-design.txt
+++ b/Documentation/locking/mutex-design.txt
@@ -145,9 +145,9 @@ Disadvantages
 
 Unlike its original design and purpose, 'struct mutex' is larger than
 most locks in the kernel. E.g: on x86-64 it is 40 bytes, almost twice
-as large as 'struct semaphore' (24 bytes) and 8 bytes shy of the
-'struct rw_semaphore' variant. Larger structure sizes mean more CPU
-cache and memory footprint.
+as large as 'struct semaphore' (24 bytes) and tied, along with rwsems,
+for the largest lock in the kernel. Larger structure sizes mean more
+CPU cache and memory footprint.
 
 When to use mutexes
 -------------------
diff --git a/Documentation/rt-mutex-design.txt b/Documentation/locking/rt-mutex-design.txt
index 8666070d3189..8666070d3189 100644
--- a/Documentation/rt-mutex-design.txt
+++ b/Documentation/locking/rt-mutex-design.txt
diff --git a/Documentation/rt-mutex.txt b/Documentation/locking/rt-mutex.txt
index 243393d882ee..243393d882ee 100644
--- a/Documentation/rt-mutex.txt
+++ b/Documentation/locking/rt-mutex.txt
diff --git a/Documentation/spinlocks.txt b/Documentation/locking/spinlocks.txt
index 97eaf5727178..ff35e40bdf5b 100644
--- a/Documentation/spinlocks.txt
+++ b/Documentation/locking/spinlocks.txt
@@ -105,9 +105,9 @@ never used in interrupt handlers, you can use the non-irq versions:
 	spin_unlock(&lock);
 
 (and the equivalent read-write versions too, of course). The spinlock will
-guarantee the same kind of exclusive access, and it will be much faster. 
+guarantee the same kind of exclusive access, and it will be much faster.
 This is useful if you know that the data in question is only ever
-manipulated from a "process context", ie no interrupts involved. 
+manipulated from a "process context", ie no interrupts involved.
 
 The reasons you mustn't use these versions if you have interrupts that
 play with the spinlock is that you can get deadlocks:
@@ -122,21 +122,21 @@ the other interrupt happens on another CPU, but it is _not_ ok if the
 interrupt happens on the same CPU that already holds the lock, because the
 lock will obviously never be released (because the interrupt is waiting
 for the lock, and the lock-holder is interrupted by the interrupt and will
-not continue until the interrupt has been processed). 
+not continue until the interrupt has been processed).
 
 (This is also the reason why the irq-versions of the spinlocks only need
 to disable the _local_ interrupts - it's ok to use spinlocks in interrupts
 on other CPU's, because an interrupt on another CPU doesn't interrupt the
 CPU that holds the lock, so the lock-holder can continue and eventually
-releases the lock). 
+releases the lock).
 
 Note that you can be clever with read-write locks and interrupts. For
 example, if you know that the interrupt only ever gets a read-lock, then
 you can use a non-irq version of read locks everywhere - because they
-don't block on each other (and thus there is no dead-lock wrt interrupts. 
-But when you do the write-lock, you have to use the irq-safe version. 
+don't block on each other (and thus there is no dead-lock wrt interrupts.
+But when you do the write-lock, you have to use the irq-safe version.
 
-For an example of being clever with rw-locks, see the "waitqueue_lock" 
+For an example of being clever with rw-locks, see the "waitqueue_lock"
 handling in kernel/sched/core.c - nothing ever _changes_ a wait-queue from
 within an interrupt, they only read the queue in order to know whom to
 wake up. So read-locks are safe (which is good: they are very common
diff --git a/Documentation/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt
index 8a112dc304c3..8a112dc304c3 100644
--- a/Documentation/ww-mutex-design.txt
+++ b/Documentation/locking/ww-mutex-design.txt
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index a4de88fb55f0..22a969cdd476 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -574,30 +574,14 @@ However, stores are not speculated.  This means that ordering -is- provided
 in the following example:
 
 	q = ACCESS_ONCE(a);
-	if (ACCESS_ONCE(q)) {
-		ACCESS_ONCE(b) = p;
-	}
-
-Please note that ACCESS_ONCE() is not optional!  Without the ACCESS_ONCE(),
-the compiler is within its rights to transform this example:
-
-	q = a;
 	if (q) {
-		b = p;  /* BUG: Compiler can reorder!!! */
-		do_something();
-	} else {
-		b = p;  /* BUG: Compiler can reorder!!! */
-		do_something_else();
+		ACCESS_ONCE(b) = p;
 	}
 
-into this, which of course defeats the ordering:
-
-	b = p;
-	q = a;
-	if (q)
-		do_something();
-	else
-		do_something_else();
+Please note that ACCESS_ONCE() is not optional!  Without the
+ACCESS_ONCE(), might combine the load from 'a' with other loads from
+'a', and the store to 'b' with other stores to 'b', with possible highly
+counterintuitive effects on ordering.
 
 Worse yet, if the compiler is able to prove (say) that the value of
 variable 'a' is always non-zero, it would be well within its rights
@@ -605,11 +589,12 @@ to optimize the original example by eliminating the "if" statement
 as follows:
 
 	q = a;
-	b = p;  /* BUG: Compiler can reorder!!! */
-	do_something();
+	b = p;  /* BUG: Compiler and CPU can both reorder!!! */
+
+So don't leave out the ACCESS_ONCE().
 
-The solution is again ACCESS_ONCE() and barrier(), which preserves the
-ordering between the load from variable 'a' and the store to variable 'b':
+It is tempting to try to enforce ordering on identical stores on both
+branches of the "if" statement as follows:
 
 	q = ACCESS_ONCE(a);
 	if (q) {
@@ -622,18 +607,11 @@ ordering between the load from variable 'a' and the store to variable 'b':
 		do_something_else();
 	}
 
-The initial ACCESS_ONCE() is required to prevent the compiler from
-proving the value of 'a', and the pair of barrier() invocations are
-required to prevent the compiler from pulling the two identical stores
-to 'b' out from the legs of the "if" statement.
-
-It is important to note that control dependencies absolutely require a
-a conditional.  For example, the following "optimized" version of
-the above example breaks ordering, which is why the barrier() invocations
-are absolutely required if you have identical stores in both legs of
-the "if" statement:
+Unfortunately, current compilers will transform this as follows at high
+optimization levels:
 
 	q = ACCESS_ONCE(a);
+	barrier();
 	ACCESS_ONCE(b) = p;  /* BUG: No ordering vs. load from a!!! */
 	if (q) {
 		/* ACCESS_ONCE(b) = p; -- moved up, BUG!!! */
@@ -643,21 +621,36 @@ the "if" statement:
 		do_something_else();
 	}
 
-It is of course legal for the prior load to be part of the conditional,
-for example, as follows:
+Now there is no conditional between the load from 'a' and the store to
+'b', which means that the CPU is within its rights to reorder them:
+The conditional is absolutely required, and must be present in the
+assembly code even after all compiler optimizations have been applied.
+Therefore, if you need ordering in this example, you need explicit
+memory barriers, for example, smp_store_release():
 
-	if (ACCESS_ONCE(a) > 0) {
-		barrier();
-		ACCESS_ONCE(b) = q / 2;
+	q = ACCESS_ONCE(a);
+	if (q) {
+		smp_store_release(&b, p);
 		do_something();
 	} else {
-		barrier();
-		ACCESS_ONCE(b) = q / 3;
+		smp_store_release(&b, p);
+		do_something_else();
+	}
+
+In contrast, without explicit memory barriers, two-legged-if control
+ordering is guaranteed only when the stores differ, for example:
+
+	q = ACCESS_ONCE(a);
+	if (q) {
+		ACCESS_ONCE(b) = p;
+		do_something();
+	} else {
+		ACCESS_ONCE(b) = r;
 		do_something_else();
 	}
 
-This will again ensure that the load from variable 'a' is ordered before the
-stores to variable 'b'.
+The initial ACCESS_ONCE() is still required to prevent the compiler from
+proving the value of 'a'.
 
 In addition, you need to be careful what you do with the local variable 'q',
 otherwise the compiler might be able to guess the value and again remove
@@ -665,12 +658,10 @@ the needed conditional.  For example:
 
 	q = ACCESS_ONCE(a);
 	if (q % MAX) {
-		barrier();
 		ACCESS_ONCE(b) = p;
 		do_something();
 	} else {
-		barrier();
-		ACCESS_ONCE(b) = p;
+		ACCESS_ONCE(b) = r;
 		do_something_else();
 	}
 
@@ -682,9 +673,12 @@ transform the above code into the following:
 	ACCESS_ONCE(b) = p;
 	do_something_else();
 
-This transformation loses the ordering between the load from variable 'a'
-and the store to variable 'b'.  If you are relying on this ordering, you
-should do something like the following:
+Given this transformation, the CPU is not required to respect the ordering
+between the load from variable 'a' and the store to variable 'b'.  It is
+tempting to add a barrier(), but this does not help.  The conditional
+is gone, and the barrier won't bring it back.  Therefore, if you are
+relying on this ordering, you should make sure that MAX is greater than
+one, perhaps as follows:
 
 	q = ACCESS_ONCE(a);
 	BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
@@ -692,35 +686,45 @@ should do something like the following:
 		ACCESS_ONCE(b) = p;
 		do_something();
 	} else {
-		ACCESS_ONCE(b) = p;
+		ACCESS_ONCE(b) = r;
 		do_something_else();
 	}
 
+Please note once again that the stores to 'b' differ.  If they were
+identical, as noted earlier, the compiler could pull this store outside
+of the 'if' statement.
+
 Finally, control dependencies do -not- provide transitivity.  This is
-demonstrated by two related examples:
+demonstrated by two related examples, with the initial values of
+x and y both being zero:
 
 	CPU 0                     CPU 1
 	=====================     =====================
 	r1 = ACCESS_ONCE(x);      r2 = ACCESS_ONCE(y);
-	if (r1 >= 0)              if (r2 >= 0)
+	if (r1 > 0)               if (r2 > 0)
 	  ACCESS_ONCE(y) = 1;       ACCESS_ONCE(x) = 1;
 
 	assert(!(r1 == 1 && r2 == 1));
 
 The above two-CPU example will never trigger the assert().  However,
 if control dependencies guaranteed transitivity (which they do not),
-then adding the following two CPUs would guarantee a related assertion:
+then adding the following CPU would guarantee a related assertion:
 
-	CPU 2                     CPU 3
-	=====================     =====================
-	ACCESS_ONCE(x) = 2;       ACCESS_ONCE(y) = 2;
+	CPU 2
+	=====================
+	ACCESS_ONCE(x) = 2;
+
+	assert(!(r1 == 2 && r2 == 1 && x == 2)); /* FAILS!!! */
 
-	assert(!(r1 == 2 && r2 == 2 && x == 1 && y == 1)); /* FAILS!!! */
+But because control dependencies do -not- provide transitivity, the above
+assertion can fail after the combined three-CPU example completes.  If you
+need the three-CPU example to provide ordering, you will need smp_mb()
+between the loads and stores in the CPU 0 and CPU 1 code fragments,
+that is, just before or just after the "if" statements.
 
-But because control dependencies do -not- provide transitivity, the
-above assertion can fail after the combined four-CPU example completes.
-If you need the four-CPU example to provide ordering, you will need
-smp_mb() between the loads and stores in the CPU 0 and CPU 1 code fragments.
+These two examples are the LB and WWC litmus tests from this paper:
+http://www.cl.cam.ac.uk/users/pes20/ppc-supplemental/test6.pdf and this
+site: https://www.cl.cam.ac.uk/~pes20/ppcmem/index.html.
 
 In summary:
 
diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index 45134dc23854..ea03abfc97e9 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -155,6 +155,7 @@ Under each memory block, you can see 4 files:
 /sys/devices/system/memory/memoryXXX/phys_device
 /sys/devices/system/memory/memoryXXX/state
 /sys/devices/system/memory/memoryXXX/removable
+/sys/devices/system/memory/memoryXXX/valid_zones
 
 'phys_index'      : read-only and contains memory block id, same as XXX.
 'state'           : read-write
@@ -170,6 +171,15 @@ Under each memory block, you can see 4 files:
                     block is removable and a value of 0 indicates that
                     it is not removable. A memory block is removable only if
                     every section in the block is removable.
+'valid_zones'     : read-only: designed to show which zones this memory block
+		    can be onlined to.
+		    The first column shows it's default zone.
+		    "memory6/valid_zones: Normal Movable" shows this memoryblock
+		    can be onlined to ZONE_NORMAL by default and to ZONE_MOVABLE
+		    by online_movable.
+		    "memory7/valid_zones: Movable Normal" shows this memoryblock
+		    can be onlined to ZONE_MOVABLE by default and to ZONE_NORMAL
+		    by online_kernel.
 
 NOTE:
   These directories/files appear after physical memory hotplug phase.
@@ -408,7 +418,6 @@ node if necessary.
   - allowing memory hot-add to ZONE_MOVABLE. maybe we need some switch like
     sysctl or new control file.
   - showing memory block and physical device relationship.
-  - showing memory block is under ZONE_MOVABLE or not
   - test and make it better memory offlining.
   - support HugeTLB page migration and offlining.
   - memmap removing at memory offline.
diff --git a/Documentation/power/charger-manager.txt b/Documentation/power/charger-manager.txt
index b4f7f4b23f64..9ff1105e58d6 100644
--- a/Documentation/power/charger-manager.txt
+++ b/Documentation/power/charger-manager.txt
@@ -29,7 +29,7 @@ Charger Manager supports the following:
 	While the battery is being charged and the system is in suspend-to-RAM,
 	we may need to monitor the battery health by looking at the ambient or
 	battery temperature. We can accomplish this by waking up the system
-	periodically. However, such a method wakes up devices unncessary for
+	periodically. However, such a method wakes up devices unnecessarily for
 	monitoring the battery health and tasks, and user processes that are
 	supposed to be kept suspended. That, in turn, incurs unnecessary power
 	consumption and slow down charging process. Or even, such peak power
diff --git a/Documentation/power/power_supply_class.txt b/Documentation/power/power_supply_class.txt
index 48cff881cb8a..82dacc06e355 100644
--- a/Documentation/power/power_supply_class.txt
+++ b/Documentation/power/power_supply_class.txt
@@ -101,6 +101,10 @@ VOLTAGE_MAX, VOLTAGE_MIN - same as _DESIGN voltage values except that
 these ones should be used if hardware could only guess (measure and
 retain) the thresholds of a given power supply.
 
+VOLTAGE_BOOT - Reports the voltage measured during boot
+
+CURRENT_BOOT - Reports the current measured during boot
+
 CHARGE_FULL_DESIGN, CHARGE_EMPTY_DESIGN - design charge values, when
 battery considered full/empty.
 
@@ -123,6 +127,8 @@ the current drawn from a charging source.
 CHARGE_TERM_CURRENT - Charge termination current used to detect the end of charge
 condition.
 
+CALIBRATE - battery or coulomb counter calibration status
+
 CONSTANT_CHARGE_VOLTAGE - constant charge voltage programmed by charger.
 CONSTANT_CHARGE_VOLTAGE_MAX - maximum charge voltage supported by the
 power supply object.
diff --git a/Documentation/power/suspend-and-interrupts.txt b/Documentation/power/suspend-and-interrupts.txt
new file mode 100644
index 000000000000..69663640dea5
--- /dev/null
+++ b/Documentation/power/suspend-and-interrupts.txt
@@ -0,0 +1,123 @@
+System Suspend and Device Interrupts
+
+Copyright (C) 2014 Intel Corp.
+Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+
+
+Suspending and Resuming Device IRQs
+-----------------------------------
+
+Device interrupt request lines (IRQs) are generally disabled during system
+suspend after the "late" phase of suspending devices (that is, after all of the
+->prepare, ->suspend and ->suspend_late callbacks have been executed for all
+devices).  That is done by suspend_device_irqs().
+
+The rationale for doing so is that after the "late" phase of device suspend
+there is no legitimate reason why any interrupts from suspended devices should
+trigger and if any devices have not been suspended properly yet, it is better to
+block interrupts from them anyway.  Also, in the past we had problems with
+interrupt handlers for shared IRQs that device drivers implementing them were
+not prepared for interrupts triggering after their devices had been suspended.
+In some cases they would attempt to access, for example, memory address spaces
+of suspended devices and cause unpredictable behavior to ensue as a result.
+Unfortunately, such problems are very difficult to debug and the introduction
+of suspend_device_irqs(), along with the "noirq" phase of device suspend and
+resume, was the only practical way to mitigate them.
+
+Device IRQs are re-enabled during system resume, right before the "early" phase
+of resuming devices (that is, before starting to execute ->resume_early
+callbacks for devices).  The function doing that is resume_device_irqs().
+
+
+The IRQF_NO_SUSPEND Flag
+------------------------
+
+There are interrupts that can legitimately trigger during the entire system
+suspend-resume cycle, including the "noirq" phases of suspending and resuming
+devices as well as during the time when nonboot CPUs are taken offline and
+brought back online.  That applies to timer interrupts in the first place,
+but also to IPIs and to some other special-purpose interrupts.
+
+The IRQF_NO_SUSPEND flag is used to indicate that to the IRQ subsystem when
+requesting a special-purpose interrupt.  It causes suspend_device_irqs() to
+leave the corresponding IRQ enabled so as to allow the interrupt to work all
+the time as expected.
+
+Note that the IRQF_NO_SUSPEND flag affects the entire IRQ and not just one
+user of it.  Thus, if the IRQ is shared, all of the interrupt handlers installed
+for it will be executed as usual after suspend_device_irqs(), even if the
+IRQF_NO_SUSPEND flag was not passed to request_irq() (or equivalent) by some of
+the IRQ's users.  For this reason, using IRQF_NO_SUSPEND and IRQF_SHARED at the
+same time should be avoided.
+
+
+System Wakeup Interrupts, enable_irq_wake() and disable_irq_wake()
+------------------------------------------------------------------
+
+System wakeup interrupts generally need to be configured to wake up the system
+from sleep states, especially if they are used for different purposes (e.g. as
+I/O interrupts) in the working state.
+
+That may involve turning on a special signal handling logic within the platform
+(such as an SoC) so that signals from a given line are routed in a different way
+during system sleep so as to trigger a system wakeup when needed.  For example,
+the platform may include a dedicated interrupt controller used specifically for
+handling system wakeup events.  Then, if a given interrupt line is supposed to
+wake up the system from sleep sates, the corresponding input of that interrupt
+controller needs to be enabled to receive signals from the line in question.
+After wakeup, it generally is better to disable that input to prevent the
+dedicated controller from triggering interrupts unnecessarily.
+
+The IRQ subsystem provides two helper functions to be used by device drivers for
+those purposes.  Namely, enable_irq_wake() turns on the platform's logic for
+handling the given IRQ as a system wakeup interrupt line and disable_irq_wake()
+turns that logic off.
+
+Calling enable_irq_wake() causes suspend_device_irqs() to treat the given IRQ
+in a special way.  Namely, the IRQ remains enabled, by on the first interrupt
+it will be disabled, marked as pending and "suspended" so that it will be
+re-enabled by resume_device_irqs() during the subsequent system resume.  Also
+the PM core is notified about the event which casues the system suspend in
+progress to be aborted (that doesn't have to happen immediately, but at one
+of the points where the suspend thread looks for pending wakeup events).
+
+This way every interrupt from a wakeup interrupt source will either cause the
+system suspend currently in progress to be aborted or wake up the system if
+already suspended.  However, after suspend_device_irqs() interrupt handlers are
+not executed for system wakeup IRQs.  They are only executed for IRQF_NO_SUSPEND
+IRQs at that time, but those IRQs should not be configured for system wakeup
+using enable_irq_wake().
+
+
+Interrupts and Suspend-to-Idle
+------------------------------
+
+Suspend-to-idle (also known as the "freeze" sleep state) is a relatively new
+system sleep state that works by idling all of the processors and waiting for
+interrupts right after the "noirq" phase of suspending devices.
+
+Of course, this means that all of the interrupts with the IRQF_NO_SUSPEND flag
+set will bring CPUs out of idle while in that state, but they will not cause the
+IRQ subsystem to trigger a system wakeup.
+
+System wakeup interrupts, in turn, will trigger wakeup from suspend-to-idle in
+analogy with what they do in the full system suspend case.  The only difference
+is that the wakeup from suspend-to-idle is signaled using the usual working
+state interrupt delivery mechanisms and doesn't require the platform to use
+any special interrupt handling logic for it to work.
+
+
+IRQF_NO_SUSPEND and enable_irq_wake()
+-------------------------------------
+
+There are no valid reasons to use both enable_irq_wake() and the IRQF_NO_SUSPEND
+flag on the same IRQ.
+
+First of all, if the IRQ is not shared, the rules for handling IRQF_NO_SUSPEND
+interrupts (interrupt handlers are invoked after suspend_device_irqs()) are
+directly at odds with the rules for handling system wakeup interrupts (interrupt
+handlers are not invoked after suspend_device_irqs()).
+
+Second, both enable_irq_wake() and IRQF_NO_SUSPEND apply to entire IRQs and not
+to individual interrupt handlers, so sharing an IRQ between a system wakeup
+interrupt source and an IRQF_NO_SUSPEND interrupt source does not make sense.
diff --git a/Documentation/powerpc/00-INDEX b/Documentation/powerpc/00-INDEX
index a68784d0a1ee..6fd0e8bb8140 100644
--- a/Documentation/powerpc/00-INDEX
+++ b/Documentation/powerpc/00-INDEX
@@ -11,6 +11,8 @@ bootwrapper.txt
 cpu_features.txt
 	- info on how we support a variety of CPUs with minimal compile-time
 	options.
+cxl.txt
+	- Overview of the CXL driver.
 eeh-pci-error-recovery.txt
 	- info on PCI Bus EEH Error Recovery
 firmware-assisted-dump.txt
diff --git a/Documentation/powerpc/cxl.txt b/Documentation/powerpc/cxl.txt
new file mode 100644
index 000000000000..2c71ecc519d9
--- /dev/null
+++ b/Documentation/powerpc/cxl.txt
@@ -0,0 +1,379 @@
+Coherent Accelerator Interface (CXL)
+====================================
+
+Introduction
+============
+
+    The coherent accelerator interface is designed to allow the
+    coherent connection of accelerators (FPGAs and other devices) to a
+    POWER system. These devices need to adhere to the Coherent
+    Accelerator Interface Architecture (CAIA).
+
+    IBM refers to this as the Coherent Accelerator Processor Interface
+    or CAPI. In the kernel it's referred to by the name CXL to avoid
+    confusion with the ISDN CAPI subsystem.
+
+    Coherent in this context means that the accelerator and CPUs can
+    both access system memory directly and with the same effective
+    addresses.
+
+
+Hardware overview
+=================
+
+          POWER8               FPGA
+       +----------+        +---------+
+       |          |        |         |
+       |   CPU    |        |   AFU   |
+       |          |        |         |
+       |          |        |         |
+       |          |        |         |
+       +----------+        +---------+
+       |   PHB    |        |         |
+       |   +------+        |   PSL   |
+       |   | CAPP |<------>|         |
+       +---+------+  PCIE  +---------+
+
+    The POWER8 chip has a Coherently Attached Processor Proxy (CAPP)
+    unit which is part of the PCIe Host Bridge (PHB). This is managed
+    by Linux by calls into OPAL. Linux doesn't directly program the
+    CAPP.
+
+    The FPGA (or coherently attached device) consists of two parts.
+    The POWER Service Layer (PSL) and the Accelerator Function Unit
+    (AFU). The AFU is used to implement specific functionality behind
+    the PSL. The PSL, among other things, provides memory address
+    translation services to allow each AFU direct access to userspace
+    memory.
+
+    The AFU is the core part of the accelerator (eg. the compression,
+    crypto etc function). The kernel has no knowledge of the function
+    of the AFU. Only userspace interacts directly with the AFU.
+
+    The PSL provides the translation and interrupt services that the
+    AFU needs. This is what the kernel interacts with. For example, if
+    the AFU needs to read a particular effective address, it sends
+    that address to the PSL, the PSL then translates it, fetches the
+    data from memory and returns it to the AFU. If the PSL has a
+    translation miss, it interrupts the kernel and the kernel services
+    the fault. The context to which this fault is serviced is based on
+    who owns that acceleration function.
+
+
+AFU Modes
+=========
+
+    There are two programming modes supported by the AFU. Dedicated
+    and AFU directed. AFU may support one or both modes.
+
+    When using dedicated mode only one MMU context is supported. In
+    this mode, only one userspace process can use the accelerator at
+    time.
+
+    When using AFU directed mode, up to 16K simultaneous contexts can
+    be supported. This means up to 16K simultaneous userspace
+    applications may use the accelerator (although specific AFUs may
+    support fewer). In this mode, the AFU sends a 16 bit context ID
+    with each of its requests. This tells the PSL which context is
+    associated with each operation. If the PSL can't translate an
+    operation, the ID can also be accessed by the kernel so it can
+    determine the userspace context associated with an operation.
+
+
+MMIO space
+==========
+
+    A portion of the accelerator MMIO space can be directly mapped
+    from the AFU to userspace. Either the whole space can be mapped or
+    just a per context portion. The hardware is self describing, hence
+    the kernel can determine the offset and size of the per context
+    portion.
+
+
+Interrupts
+==========
+
+    AFUs may generate interrupts that are destined for userspace. These
+    are received by the kernel as hardware interrupts and passed onto
+    userspace by a read syscall documented below.
+
+    Data storage faults and error interrupts are handled by the kernel
+    driver.
+
+
+Work Element Descriptor (WED)
+=============================
+
+    The WED is a 64-bit parameter passed to the AFU when a context is
+    started. Its format is up to the AFU hence the kernel has no
+    knowledge of what it represents. Typically it will be the
+    effective address of a work queue or status block where the AFU
+    and userspace can share control and status information.
+
+
+
+
+User API
+========
+
+    For AFUs operating in AFU directed mode, two character device
+    files will be created. /dev/cxl/afu0.0m will correspond to a
+    master context and /dev/cxl/afu0.0s will correspond to a slave
+    context. Master contexts have access to the full MMIO space an
+    AFU provides. Slave contexts have access to only the per process
+    MMIO space an AFU provides.
+
+    For AFUs operating in dedicated process mode, the driver will
+    only create a single character device per AFU called
+    /dev/cxl/afu0.0d. This will have access to the entire MMIO space
+    that the AFU provides (like master contexts in AFU directed).
+
+    The types described below are defined in include/uapi/misc/cxl.h
+
+    The following file operations are supported on both slave and
+    master devices.
+
+
+open
+----
+
+    Opens the device and allocates a file descriptor to be used with
+    the rest of the API.
+
+    A dedicated mode AFU only has one context and only allows the
+    device to be opened once.
+
+    An AFU directed mode AFU can have many contexts, the device can be
+    opened once for each context that is available.
+
+    When all available contexts are allocated the open call will fail
+    and return -ENOSPC.
+
+    Note: IRQs need to be allocated for each context, which may limit
+          the number of contexts that can be created, and therefore
+          how many times the device can be opened. The POWER8 CAPP
+          supports 2040 IRQs and 3 are used by the kernel, so 2037 are
+          left. If 1 IRQ is needed per context, then only 2037
+          contexts can be allocated. If 4 IRQs are needed per context,
+          then only 2037/4 = 509 contexts can be allocated.
+
+
+ioctl
+-----
+
+    CXL_IOCTL_START_WORK:
+        Starts the AFU context and associates it with the current
+        process. Once this ioctl is successfully executed, all memory
+        mapped into this process is accessible to this AFU context
+        using the same effective addresses. No additional calls are
+        required to map/unmap memory. The AFU memory context will be
+        updated as userspace allocates and frees memory. This ioctl
+        returns once the AFU context is started.
+
+        Takes a pointer to a struct cxl_ioctl_start_work:
+
+                struct cxl_ioctl_start_work {
+                        __u64 flags;
+                        __u64 work_element_descriptor;
+                        __u64 amr;
+                        __s16 num_interrupts;
+                        __s16 reserved1;
+                        __s32 reserved2;
+                        __u64 reserved3;
+                        __u64 reserved4;
+                        __u64 reserved5;
+                        __u64 reserved6;
+                };
+
+            flags:
+                Indicates which optional fields in the structure are
+                valid.
+
+            work_element_descriptor:
+                The Work Element Descriptor (WED) is a 64-bit argument
+                defined by the AFU. Typically this is an effective
+                address pointing to an AFU specific structure
+                describing what work to perform.
+
+            amr:
+                Authority Mask Register (AMR), same as the powerpc
+                AMR. This field is only used by the kernel when the
+                corresponding CXL_START_WORK_AMR value is specified in
+                flags. If not specified the kernel will use a default
+                value of 0.
+
+            num_interrupts:
+                Number of userspace interrupts to request. This field
+                is only used by the kernel when the corresponding
+                CXL_START_WORK_NUM_IRQS value is specified in flags.
+                If not specified the minimum number required by the
+                AFU will be allocated. The min and max number can be
+                obtained from sysfs.
+
+            reserved fields:
+                For ABI padding and future extensions
+
+    CXL_IOCTL_GET_PROCESS_ELEMENT:
+        Get the current context id, also known as the process element.
+        The value is returned from the kernel as a __u32.
+
+
+mmap
+----
+
+    An AFU may have an MMIO space to facilitate communication with the
+    AFU. If it does, the MMIO space can be accessed via mmap. The size
+    and contents of this area are specific to the particular AFU. The
+    size can be discovered via sysfs.
+
+    In AFU directed mode, master contexts are allowed to map all of
+    the MMIO space and slave contexts are allowed to only map the per
+    process MMIO space associated with the context. In dedicated
+    process mode the entire MMIO space can always be mapped.
+
+    This mmap call must be done after the START_WORK ioctl.
+
+    Care should be taken when accessing MMIO space. Only 32 and 64-bit
+    accesses are supported by POWER8. Also, the AFU will be designed
+    with a specific endianness, so all MMIO accesses should consider
+    endianness (recommend endian(3) variants like: le64toh(),
+    be64toh() etc). These endian issues equally apply to shared memory
+    queues the WED may describe.
+
+
+read
+----
+
+    Reads events from the AFU. Blocks if no events are pending
+    (unless O_NONBLOCK is supplied). Returns -EIO in the case of an
+    unrecoverable error or if the card is removed.
+
+    read() will always return an integral number of events.
+
+    The buffer passed to read() must be at least 4K bytes.
+
+    The result of the read will be a buffer of one or more events,
+    each event is of type struct cxl_event, of varying size.
+
+            struct cxl_event {
+                    struct cxl_event_header header;
+                    union {
+                            struct cxl_event_afu_interrupt irq;
+                            struct cxl_event_data_storage fault;
+                            struct cxl_event_afu_error afu_error;
+                    };
+            };
+
+    The struct cxl_event_header is defined as:
+
+            struct cxl_event_header {
+                    __u16 type;
+                    __u16 size;
+                    __u16 process_element;
+                    __u16 reserved1;
+            };
+
+        type:
+            This defines the type of event. The type determines how
+            the rest of the event is structured. These types are
+            described below and defined by enum cxl_event_type.
+
+        size:
+            This is the size of the event in bytes including the
+            struct cxl_event_header. The start of the next event can
+            be found at this offset from the start of the current
+            event.
+
+        process_element:
+            Context ID of the event.
+
+        reserved field:
+            For future extensions and padding.
+
+    If the event type is CXL_EVENT_AFU_INTERRUPT then the event
+    structure is defined as:
+
+            struct cxl_event_afu_interrupt {
+                    __u16 flags;
+                    __u16 irq; /* Raised AFU interrupt number */
+                    __u32 reserved1;
+            };
+
+        flags:
+            These flags indicate which optional fields are present
+            in this struct. Currently all fields are mandatory.
+
+        irq:
+            The IRQ number sent by the AFU.
+
+        reserved field:
+            For future extensions and padding.
+
+    If the event type is CXL_EVENT_DATA_STORAGE then the event
+    structure is defined as:
+
+            struct cxl_event_data_storage {
+                    __u16 flags;
+                    __u16 reserved1;
+                    __u32 reserved2;
+                    __u64 addr;
+                    __u64 dsisr;
+                    __u64 reserved3;
+            };
+
+        flags:
+            These flags indicate which optional fields are present in
+            this struct. Currently all fields are mandatory.
+
+        address:
+            The address that the AFU unsuccessfully attempted to
+            access. Valid accesses will be handled transparently by the
+            kernel but invalid accesses will generate this event.
+
+        dsisr:
+            This field gives information on the type of fault. It is a
+            copy of the DSISR from the PSL hardware when the address
+            fault occurred. The form of the DSISR is as defined in the
+            CAIA.
+
+        reserved fields:
+            For future extensions
+
+    If the event type is CXL_EVENT_AFU_ERROR then the event structure
+    is defined as:
+
+            struct cxl_event_afu_error {
+                    __u16 flags;
+                    __u16 reserved1;
+                    __u32 reserved2;
+                    __u64 error;
+            };
+
+        flags:
+            These flags indicate which optional fields are present in
+            this struct. Currently all fields are Mandatory.
+
+        error:
+            Error status from the AFU. Defined by the AFU.
+
+        reserved fields:
+            For future extensions and padding
+
+Sysfs Class
+===========
+
+    A cxl sysfs class is added under /sys/class/cxl to facilitate
+    enumeration and tuning of the accelerators. Its layout is
+    described in Documentation/ABI/testing/sysfs-class-cxl
+
+Udev rules
+==========
+
+    The following udev rules could be used to create a symlink to the
+    most logical chardev to use in any programming mode (afuX.Yd for
+    dedicated, afuX.Ys for afu directed), since the API is virtually
+    identical for each:
+
+	SUBSYSTEM=="cxl", ATTRS{mode}=="dedicated_process", SYMLINK="cxl/%b"
+	SUBSYSTEM=="cxl", ATTRS{mode}=="afu_directed", \
+	                  KERNEL=="afu[0-9]*.[0-9]*s", SYMLINK="cxl/%b"
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index b4498218c474..5a615c14f75d 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -70,6 +70,38 @@ DMA addresses types dma_addr_t:
 	For printing a dma_addr_t type which can vary based on build options,
 	regardless of the width of the CPU data path. Passed by reference.
 
+Raw buffer as an escaped string:
+
+	%*pE[achnops]
+
+	For printing raw buffer as an escaped string. For the following buffer
+
+		1b 62 20 5c 43 07 22 90 0d 5d
+
+	few examples show how the conversion would be done (the result string
+	without surrounding quotes):
+
+		%*pE		"\eb \C\a"\220\r]"
+		%*pEhp		"\x1bb \C\x07"\x90\x0d]"
+		%*pEa		"\e\142\040\\\103\a\042\220\r\135"
+
+	The conversion rules are applied according to an optional combination
+	of flags (see string_escape_mem() kernel documentation for the
+	details):
+		a - ESCAPE_ANY
+		c - ESCAPE_SPECIAL
+		h - ESCAPE_HEX
+		n - ESCAPE_NULL
+		o - ESCAPE_OCTAL
+		p - ESCAPE_NP
+		s - ESCAPE_SPACE
+	By default ESCAPE_ANY_NP is used.
+
+	ESCAPE_ANY_NP is the sane choice for many cases, in particularly for
+	printing SSIDs.
+
+	If field width is omitted the 1 byte only will be escaped.
+
 Raw buffer as a hex string:
 	%*ph	00 01 02  ...  3f
 	%*phC	00:01:02: ... :3f
diff --git a/Documentation/scheduler/sched-deadline.txt b/Documentation/scheduler/sched-deadline.txt
index 18adc92a6b3b..21461a0441c1 100644
--- a/Documentation/scheduler/sched-deadline.txt
+++ b/Documentation/scheduler/sched-deadline.txt
@@ -15,6 +15,8 @@ CONTENTS
  5. Tasks CPU affinity
    5.1 SCHED_DEADLINE and cpusets HOWTO
  6. Future plans
+ A. Test suite
+ B. Minimal main()
 
 
 0. WARNING
@@ -38,24 +40,25 @@ CONTENTS
 ==================
 
  SCHED_DEADLINE uses three parameters, named "runtime", "period", and
- "deadline" to schedule tasks. A SCHED_DEADLINE task is guaranteed to receive
+ "deadline", to schedule tasks. A SCHED_DEADLINE task should receive
  "runtime" microseconds of execution time every "period" microseconds, and
  these "runtime" microseconds are available within "deadline" microseconds
  from the beginning of the period.  In order to implement this behaviour,
  every time the task wakes up, the scheduler computes a "scheduling deadline"
  consistent with the guarantee (using the CBS[2,3] algorithm). Tasks are then
  scheduled using EDF[1] on these scheduling deadlines (the task with the
- smallest scheduling deadline is selected for execution). Notice that this
- guaranteed is respected if a proper "admission control" strategy (see Section
- "4. Bandwidth management") is used.
+ earliest scheduling deadline is selected for execution). Notice that the
+ task actually receives "runtime" time units within "deadline" if a proper
+ "admission control" strategy (see Section "4. Bandwidth management") is used
+ (clearly, if the system is overloaded this guarantee cannot be respected).
 
  Summing up, the CBS[2,3] algorithms assigns scheduling deadlines to tasks so
  that each task runs for at most its runtime every period, avoiding any
  interference between different tasks (bandwidth isolation), while the EDF[1]
- algorithm selects the task with the smallest scheduling deadline as the one
- to be executed first.  Thanks to this feature, also tasks that do not
- strictly comply with the "traditional" real-time task model (see Section 3)
- can effectively use the new policy.
+ algorithm selects the task with the earliest scheduling deadline as the one
+ to be executed next. Thanks to this feature, tasks that do not strictly comply
+ with the "traditional" real-time task model (see Section 3) can effectively
+ use the new policy.
 
  In more details, the CBS algorithm assigns scheduling deadlines to
  tasks in the following way:
@@ -64,45 +67,45 @@ CONTENTS
     "deadline", and "period" parameters;
 
   - The state of the task is described by a "scheduling deadline", and
-    a "current runtime". These two parameters are initially set to 0;
+    a "remaining runtime". These two parameters are initially set to 0;
 
   - When a SCHED_DEADLINE task wakes up (becomes ready for execution),
     the scheduler checks if
 
-                    current runtime                runtime
-         ---------------------------------- > ----------------
-         scheduling deadline - current time         period
+                 remaining runtime                  runtime
+        ----------------------------------    >    ---------
+        scheduling deadline - current time           period
 
     then, if the scheduling deadline is smaller than the current time, or
     this condition is verified, the scheduling deadline and the
-    current budget are re-initialised as
+    remaining runtime are re-initialised as
 
          scheduling deadline = current time + deadline
-         current runtime = runtime
+         remaining runtime = runtime
 
-    otherwise, the scheduling deadline and the current runtime are
+    otherwise, the scheduling deadline and the remaining runtime are
     left unchanged;
 
   - When a SCHED_DEADLINE task executes for an amount of time t, its
-    current runtime is decreased as
+    remaining runtime is decreased as
 
-         current runtime = current runtime - t
+         remaining runtime = remaining runtime - t
 
     (technically, the runtime is decreased at every tick, or when the
     task is descheduled / preempted);
 
-  - When the current runtime becomes less or equal than 0, the task is
+  - When the remaining runtime becomes less or equal than 0, the task is
     said to be "throttled" (also known as "depleted" in real-time literature)
     and cannot be scheduled until its scheduling deadline. The "replenishment
     time" for this task (see next item) is set to be equal to the current
     value of the scheduling deadline;
 
   - When the current time is equal to the replenishment time of a
-    throttled task, the scheduling deadline and the current runtime are
+    throttled task, the scheduling deadline and the remaining runtime are
     updated as
 
          scheduling deadline = scheduling deadline + period
-         current runtime = current runtime + runtime
+         remaining runtime = remaining runtime + runtime
 
 
 3. Scheduling Real-Time Tasks
@@ -134,6 +137,50 @@ CONTENTS
  A real-time task can be periodic with period P if r_{j+1} = r_j + P, or
  sporadic with minimum inter-arrival time P is r_{j+1} >= r_j + P. Finally,
  d_j = r_j + D, where D is the task's relative deadline.
+ The utilisation of a real-time task is defined as the ratio between its
+ WCET and its period (or minimum inter-arrival time), and represents
+ the fraction of CPU time needed to execute the task.
+
+ If the total utilisation sum_i(WCET_i/P_i) is larger than M (with M equal
+ to the number of CPUs), then the scheduler is unable to respect all the
+ deadlines.
+ Note that total utilisation is defined as the sum of the utilisations
+ WCET_i/P_i over all the real-time tasks in the system. When considering
+ multiple real-time tasks, the parameters of the i-th task are indicated
+ with the "_i" suffix.
+ Moreover, if the total utilisation is larger than M, then we risk starving
+ non- real-time tasks by real-time tasks.
+ If, instead, the total utilisation is smaller than M, then non real-time
+ tasks will not be starved and the system might be able to respect all the
+ deadlines.
+ As a matter of fact, in this case it is possible to provide an upper bound
+ for tardiness (defined as the maximum between 0 and the difference
+ between the finishing time of a job and its absolute deadline).
+ More precisely, it can be proven that using a global EDF scheduler the
+ maximum tardiness of each task is smaller or equal than
+	((M − 1) · WCET_max − WCET_min)/(M − (M − 2) · U_max) + WCET_max
+ where WCET_max = max_i{WCET_i} is the maximum WCET, WCET_min=min_i{WCET_i}
+ is the minimum WCET, and U_max = max_i{WCET_i/P_i} is the maximum utilisation.
+
+ If M=1 (uniprocessor system), or in case of partitioned scheduling (each
+ real-time task is statically assigned to one and only one CPU), it is
+ possible to formally check if all the deadlines are respected.
+ If D_i = P_i for all tasks, then EDF is able to respect all the deadlines
+ of all the tasks executing on a CPU if and only if the total utilisation
+ of the tasks running on such a CPU is smaller or equal than 1.
+ If D_i != P_i for some task, then it is possible to define the density of
+ a task as C_i/min{D_i,T_i}, and EDF is able to respect all the deadlines
+ of all the tasks running on a CPU if the sum sum_i C_i/min{D_i,T_i} of the
+ densities of the tasks running on such a CPU is smaller or equal than 1
+ (notice that this condition is only sufficient, and not necessary).
+
+ On multiprocessor systems with global EDF scheduling (non partitioned
+ systems), a sufficient test for schedulability can not be based on the
+ utilisations (it can be shown that task sets with utilisations slightly
+ larger than 1 can miss deadlines regardless of the number of CPUs M).
+ However, as previously stated, enforcing that the total utilisation is smaller
+ than M is enough to guarantee that non real-time tasks are not starved and
+ that the tardiness of real-time tasks has an upper bound.
 
  SCHED_DEADLINE can be used to schedule real-time tasks guaranteeing that
  the jobs' deadlines of a task are respected. In order to do this, a task
@@ -147,6 +194,8 @@ CONTENTS
  and the absolute deadlines (d_j) coincide, so a proper admission control
  allows to respect the jobs' absolute deadlines for this task (this is what is
  called "hard schedulability property" and is an extension of Lemma 1 of [2]).
+ Notice that if runtime > deadline the admission control will surely reject
+ this task, as it is not possible to respect its temporal constraints.
 
  References:
   1 - C. L. Liu and J. W. Layland. Scheduling algorithms for multiprogram-
@@ -156,46 +205,57 @@ CONTENTS
       Real-Time Systems. Proceedings of the 19th IEEE Real-time Systems
       Symposium, 1998. http://retis.sssup.it/~giorgio/paps/1998/rtss98-cbs.pdf
   3 - L. Abeni. Server Mechanisms for Multimedia Applications. ReTiS Lab
-      Technical Report. http://xoomer.virgilio.it/lucabe72/pubs/tr-98-01.ps
+      Technical Report. http://disi.unitn.it/~abeni/tr-98-01.pdf
 
 4. Bandwidth management
 =======================
 
- In order for the -deadline scheduling to be effective and useful, it is
- important to have some method to keep the allocation of the available CPU
- bandwidth to the tasks under control.
- This is usually called "admission control" and if it is not performed at all,
+ As previously mentioned, in order for -deadline scheduling to be
+ effective and useful (that is, to be able to provide "runtime" time units
+ within "deadline"), it is important to have some method to keep the allocation
+ of the available fractions of CPU time to the various tasks under control.
+ This is usually called "admission control" and if it is not performed, then
  no guarantee can be given on the actual scheduling of the -deadline tasks.
 
- Since when RT-throttling has been introduced each task group has a bandwidth
- associated, calculated as a certain amount of runtime over a period.
- Moreover, to make it possible to manipulate such bandwidth, readable/writable
- controls have been added to both procfs (for system wide settings) and cgroupfs
- (for per-group settings).
- Therefore, the same interface is being used for controlling the bandwidth
- distrubution to -deadline tasks.
-
- However, more discussion is needed in order to figure out how we want to manage
- SCHED_DEADLINE bandwidth at the task group level. Therefore, SCHED_DEADLINE
- uses (for now) a less sophisticated, but actually very sensible, mechanism to
- ensure that a certain utilization cap is not overcome per each root_domain.
-
- Another main difference between deadline bandwidth management and RT-throttling
+ As already stated in Section 3, a necessary condition to be respected to
+ correctly schedule a set of real-time tasks is that the total utilisation
+ is smaller than M. When talking about -deadline tasks, this requires that
+ the sum of the ratio between runtime and period for all tasks is smaller
+ than M. Notice that the ratio runtime/period is equivalent to the utilisation
+ of a "traditional" real-time task, and is also often referred to as
+ "bandwidth".
+ The interface used to control the CPU bandwidth that can be allocated
+ to -deadline tasks is similar to the one already used for -rt
+ tasks with real-time group scheduling (a.k.a. RT-throttling - see
+ Documentation/scheduler/sched-rt-group.txt), and is based on readable/
+ writable control files located in procfs (for system wide settings).
+ Notice that per-group settings (controlled through cgroupfs) are still not
+ defined for -deadline tasks, because more discussion is needed in order to
+ figure out how we want to manage SCHED_DEADLINE bandwidth at the task group
+ level.
+
+ A main difference between deadline bandwidth management and RT-throttling
  is that -deadline tasks have bandwidth on their own (while -rt ones don't!),
- and thus we don't need an higher level throttling mechanism to enforce the
- desired bandwidth.
+ and thus we don't need a higher level throttling mechanism to enforce the
+ desired bandwidth. In other words, this means that interface parameters are
+ only used at admission control time (i.e., when the user calls
+ sched_setattr()). Scheduling is then performed considering actual tasks'
+ parameters, so that CPU bandwidth is allocated to SCHED_DEADLINE tasks
+ respecting their needs in terms of granularity. Therefore, using this simple
+ interface we can put a cap on total utilization of -deadline tasks (i.e.,
+ \Sum (runtime_i / period_i) < global_dl_utilization_cap).
 
 4.1 System wide settings
 ------------------------
 
  The system wide settings are configured under the /proc virtual file system.
 
- For now the -rt knobs are used for dl admission control and the -deadline
- runtime is accounted against the -rt runtime. We realise that this isn't
- entirely desirable; however, it is better to have a small interface for now,
- and be able to change it easily later. The ideal situation (see 5.) is to run
- -rt tasks from a -deadline server; in which case the -rt bandwidth is a direct
- subset of dl_bw.
+ For now the -rt knobs are used for -deadline admission control and the
+ -deadline runtime is accounted against the -rt runtime. We realise that this
+ isn't entirely desirable; however, it is better to have a small interface for
+ now, and be able to change it easily later. The ideal situation (see 5.) is to
+ run -rt tasks from a -deadline server; in which case the -rt bandwidth is a
+ direct subset of dl_bw.
 
  This means that, for a root_domain comprising M CPUs, -deadline tasks
  can be created while the sum of their bandwidths stays below:
@@ -231,8 +291,16 @@ CONTENTS
  950000. With rt_period equal to 1000000, by default, it means that -deadline
  tasks can use at most 95%, multiplied by the number of CPUs that compose the
  root_domain, for each root_domain.
+ This means that non -deadline tasks will receive at least 5% of the CPU time,
+ and that -deadline tasks will receive their runtime with a guaranteed
+ worst-case delay respect to the "deadline" parameter. If "deadline" = "period"
+ and the cpuset mechanism is used to implement partitioned scheduling (see
+ Section 5), then this simple setting of the bandwidth management is able to
+ deterministically guarantee that -deadline tasks will receive their runtime
+ in a period.
 
- A -deadline task cannot fork.
+ Finally, notice that in order not to jeopardize the admission control a
+ -deadline task cannot fork.
 
 5. Tasks CPU affinity
 =====================
@@ -279,3 +347,179 @@ CONTENTS
  throttling patches [https://lkml.org/lkml/2010/2/23/239] but we still are in
  the preliminary phases of the merge and we really seek feedback that would
  help us decide on the direction it should take.
+
+Appendix A. Test suite
+======================
+
+ The SCHED_DEADLINE policy can be easily tested using two applications that
+ are part of a wider Linux Scheduler validation suite. The suite is
+ available as a GitHub repository: https://github.com/scheduler-tools.
+
+ The first testing application is called rt-app and can be used to
+ start multiple threads with specific parameters. rt-app supports
+ SCHED_{OTHER,FIFO,RR,DEADLINE} scheduling policies and their related
+ parameters (e.g., niceness, priority, runtime/deadline/period). rt-app
+ is a valuable tool, as it can be used to synthetically recreate certain
+ workloads (maybe mimicking real use-cases) and evaluate how the scheduler
+ behaves under such workloads. In this way, results are easily reproducible.
+ rt-app is available at: https://github.com/scheduler-tools/rt-app.
+
+ Thread parameters can be specified from the command line, with something like
+ this:
+
+  # rt-app -t 100000:10000:d -t 150000:20000:f:10 -D5
+
+ The above creates 2 threads. The first one, scheduled by SCHED_DEADLINE,
+ executes for 10ms every 100ms. The second one, scheduled at SCHED_FIFO
+ priority 10, executes for 20ms every 150ms. The test will run for a total
+ of 5 seconds.
+
+ More interestingly, configurations can be described with a json file that
+ can be passed as input to rt-app with something like this:
+
+  # rt-app my_config.json
+
+ The parameters that can be specified with the second method are a superset
+ of the command line options. Please refer to rt-app documentation for more
+ details (<rt-app-sources>/doc/*.json).
+
+ The second testing application is a modification of schedtool, called
+ schedtool-dl, which can be used to setup SCHED_DEADLINE parameters for a
+ certain pid/application. schedtool-dl is available at:
+ https://github.com/scheduler-tools/schedtool-dl.git.
+
+ The usage is straightforward:
+
+  # schedtool -E -t 10000000:100000000 -e ./my_cpuhog_app
+
+ With this, my_cpuhog_app is put to run inside a SCHED_DEADLINE reservation
+ of 10ms every 100ms (note that parameters are expressed in microseconds).
+ You can also use schedtool to create a reservation for an already running
+ application, given that you know its pid:
+
+  # schedtool -E -t 10000000:100000000 my_app_pid
+
+Appendix B. Minimal main()
+==========================
+
+ We provide in what follows a simple (ugly) self-contained code snippet
+ showing how SCHED_DEADLINE reservations can be created by a real-time
+ application developer.
+
+ #define _GNU_SOURCE
+ #include <unistd.h>
+ #include <stdio.h>
+ #include <stdlib.h>
+ #include <string.h>
+ #include <time.h>
+ #include <linux/unistd.h>
+ #include <linux/kernel.h>
+ #include <linux/types.h>
+ #include <sys/syscall.h>
+ #include <pthread.h>
+
+ #define gettid() syscall(__NR_gettid)
+
+ #define SCHED_DEADLINE	6
+
+ /* XXX use the proper syscall numbers */
+ #ifdef __x86_64__
+ #define __NR_sched_setattr		314
+ #define __NR_sched_getattr		315
+ #endif
+
+ #ifdef __i386__
+ #define __NR_sched_setattr		351
+ #define __NR_sched_getattr		352
+ #endif
+
+ #ifdef __arm__
+ #define __NR_sched_setattr		380
+ #define __NR_sched_getattr		381
+ #endif
+
+ static volatile int done;
+
+ struct sched_attr {
+	__u32 size;
+
+	__u32 sched_policy;
+	__u64 sched_flags;
+
+	/* SCHED_NORMAL, SCHED_BATCH */
+	__s32 sched_nice;
+
+	/* SCHED_FIFO, SCHED_RR */
+	__u32 sched_priority;
+
+	/* SCHED_DEADLINE (nsec) */
+	__u64 sched_runtime;
+	__u64 sched_deadline;
+	__u64 sched_period;
+ };
+
+ int sched_setattr(pid_t pid,
+		  const struct sched_attr *attr,
+		  unsigned int flags)
+ {
+	return syscall(__NR_sched_setattr, pid, attr, flags);
+ }
+
+ int sched_getattr(pid_t pid,
+		  struct sched_attr *attr,
+		  unsigned int size,
+		  unsigned int flags)
+ {
+	return syscall(__NR_sched_getattr, pid, attr, size, flags);
+ }
+
+ void *run_deadline(void *data)
+ {
+	struct sched_attr attr;
+	int x = 0;
+	int ret;
+	unsigned int flags = 0;
+
+	printf("deadline thread started [%ld]\n", gettid());
+
+	attr.size = sizeof(attr);
+	attr.sched_flags = 0;
+	attr.sched_nice = 0;
+	attr.sched_priority = 0;
+
+	/* This creates a 10ms/30ms reservation */
+	attr.sched_policy = SCHED_DEADLINE;
+	attr.sched_runtime = 10 * 1000 * 1000;
+	attr.sched_period = attr.sched_deadline = 30 * 1000 * 1000;
+
+	ret = sched_setattr(0, &attr, flags);
+	if (ret < 0) {
+		done = 0;
+		perror("sched_setattr");
+		exit(-1);
+	}
+
+	while (!done) {
+		x++;
+	}
+
+	printf("deadline thread dies [%ld]\n", gettid());
+	return NULL;
+ }
+
+ int main (int argc, char **argv)
+ {
+	pthread_t thread;
+
+	printf("main thread [%ld]\n", gettid());
+
+	pthread_create(&thread, NULL, run_deadline, NULL);
+
+	sleep(10);
+
+	done = 1;
+	pthread_join(thread, NULL);
+
+	printf("main dies [%ld]\n", gettid());
+	return 0;
+ }
diff --git a/Documentation/security/keys.txt b/Documentation/security/keys.txt
index 8727c194ca16..821c936e1a63 100644
--- a/Documentation/security/keys.txt
+++ b/Documentation/security/keys.txt
@@ -888,11 +888,11 @@ payload contents" for more information.
 				const char *callout_info);
 
     This is used to request a key or keyring with a description that matches
-    the description specified according to the key type's match function. This
-    permits approximate matching to occur. If callout_string is not NULL, then
-    /sbin/request-key will be invoked in an attempt to obtain the key from
-    userspace. In that case, callout_string will be passed as an argument to
-    the program.
+    the description specified according to the key type's match_preparse()
+    method. This permits approximate matching to occur. If callout_string is
+    not NULL, then /sbin/request-key will be invoked in an attempt to obtain
+    the key from userspace. In that case, callout_string will be passed as an
+    argument to the program.
 
     Should the function fail error ENOKEY, EKEYEXPIRED or EKEYREVOKED will be
     returned.
@@ -1170,7 +1170,7 @@ The structure has a number of fields, some of which are mandatory:
      The method should return 0 if successful or a negative error code
      otherwise.
 
-     
+
  (*) void (*free_preparse)(struct key_preparsed_payload *prep);
 
      This method is only required if the preparse() method is provided,
@@ -1225,16 +1225,55 @@ The structure has a number of fields, some of which are mandatory:
      It is safe to sleep in this method.
 
 
- (*) int (*match)(const struct key *key, const void *desc);
+ (*) int (*match_preparse)(struct key_match_data *match_data);
+
+     This method is optional.  It is called when a key search is about to be
+     performed.  It is given the following structure:
 
-     This method is called to match a key against a description. It should
-     return non-zero if the two match, zero if they don't.
+	struct key_match_data {
+		bool (*cmp)(const struct key *key,
+			    const struct key_match_data *match_data);
+		const void	*raw_data;
+		void		*preparsed;
+		unsigned	lookup_type;
+	};
 
-     This method should not need to lock the key in any way. The type and
-     description can be considered invariant, and the payload should not be
-     accessed (the key may not yet be instantiated).
+     On entry, raw_data will be pointing to the criteria to be used in matching
+     a key by the caller and should not be modified.  (*cmp)() will be pointing
+     to the default matcher function (which does an exact description match
+     against raw_data) and lookup_type will be set to indicate a direct lookup.
 
-     It is not safe to sleep in this method; the caller may hold spinlocks.
+     The following lookup_type values are available:
+
+      [*] KEYRING_SEARCH_LOOKUP_DIRECT - A direct lookup hashes the type and
+      	  description to narrow down the search to a small number of keys.
+
+      [*] KEYRING_SEARCH_LOOKUP_ITERATE - An iterative lookup walks all the
+      	  keys in the keyring until one is matched.  This must be used for any
+      	  search that's not doing a simple direct match on the key description.
+
+     The method may set cmp to point to a function of its choice that does some
+     other form of match, may set lookup_type to KEYRING_SEARCH_LOOKUP_ITERATE
+     and may attach something to the preparsed pointer for use by (*cmp)().
+     (*cmp)() should return true if a key matches and false otherwise.
+
+     If preparsed is set, it may be necessary to use the match_free() method to
+     clean it up.
+
+     The method should return 0 if successful or a negative error code
+     otherwise.
+
+     It is permitted to sleep in this method, but (*cmp)() may not sleep as
+     locks will be held over it.
+
+     If match_preparse() is not provided, keys of this type will be matched
+     exactly by their description.
+
+
+ (*) void (*match_free)(struct key_match_data *match_data);
+
+     This method is optional.  If given, it called to clean up
+     match_data->preparsed after a successful call to match_preparse().
 
 
  (*) void (*revoke)(struct key *key);
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index f79eb9666379..57baff5bdb80 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -190,6 +190,8 @@ core_pattern is used to specify a core dumpfile pattern name.
 	%%	output one '%'
 	%p	pid
 	%P	global pid (init PID namespace)
+	%i	tid
+	%I	global tid (init PID namespace)
 	%u	uid
 	%g	gid
 	%d	dump mode, matches PR_SET_DUMPABLE and
diff --git a/Documentation/video4linux/vivid.txt b/Documentation/video4linux/vivid.txt
new file mode 100644
index 000000000000..eeb11a28e4fc
--- /dev/null
+++ b/Documentation/video4linux/vivid.txt
@@ -0,0 +1,1111 @@
+vivid: Virtual Video Test Driver
+================================
+
+This driver emulates video4linux hardware of various types: video capture, video
+output, vbi capture and output, radio receivers and transmitters and a software
+defined radio receiver. In addition a simple framebuffer device is available for
+testing capture and output overlays.
+
+Up to 64 vivid instances can be created, each with up to 16 inputs and 16 outputs.
+
+Each input can be a webcam, TV capture device, S-Video capture device or an HDMI
+capture device. Each output can be an S-Video output device or an HDMI output
+device.
+
+These inputs and outputs act exactly as a real hardware device would behave. This
+allows you to use this driver as a test input for application development, since
+you can test the various features without requiring special hardware.
+
+This document describes the features implemented by this driver:
+
+- Support for read()/write(), MMAP, USERPTR and DMABUF streaming I/O.
+- A large list of test patterns and variations thereof
+- Working brightness, contrast, saturation and hue controls
+- Support for the alpha color component
+- Full colorspace support, including limited/full RGB range
+- All possible control types are present
+- Support for various pixel aspect ratios and video aspect ratios
+- Error injection to test what happens if errors occur
+- Supports crop/compose/scale in any combination for both input and output
+- Can emulate up to 4K resolutions
+- All Field settings are supported for testing interlaced capturing
+- Supports all standard YUV and RGB formats, including two multiplanar YUV formats
+- Raw and Sliced VBI capture and output support
+- Radio receiver and transmitter support, including RDS support
+- Software defined radio (SDR) support
+- Capture and output overlay support
+
+These features will be described in more detail below.
+
+
+Table of Contents
+-----------------
+
+Section 1: Configuring the driver
+Section 2: Video Capture
+Section 2.1: Webcam Input
+Section 2.2: TV and S-Video Inputs
+Section 2.3: HDMI Input
+Section 3: Video Output
+Section 3.1: S-Video Output
+Section 3.2: HDMI Output
+Section 4: VBI Capture
+Section 5: VBI Output
+Section 6: Radio Receiver
+Section 7: Radio Transmitter
+Section 8: Software Defined Radio Receiver
+Section 9: Controls
+Section 9.1: User Controls - Test Controls
+Section 9.2: User Controls - Video Capture
+Section 9.3: User Controls - Audio
+Section 9.4: Vivid Controls
+Section 9.4.1: Test Pattern Controls
+Section 9.4.2: Capture Feature Selection Controls
+Section 9.4.3: Output Feature Selection Controls
+Section 9.4.4: Error Injection Controls
+Section 9.4.5: VBI Raw Capture Controls
+Section 9.5: Digital Video Controls
+Section 9.6: FM Radio Receiver Controls
+Section 9.7: FM Radio Modulator
+Section 10: Video, VBI and RDS Looping
+Section 10.1: Video and Sliced VBI looping
+Section 10.2: Radio & RDS Looping
+Section 11: Cropping, Composing, Scaling
+Section 12: Formats
+Section 13: Capture Overlay
+Section 14: Output Overlay
+Section 15: Some Future Improvements
+
+
+Section 1: Configuring the driver
+---------------------------------
+
+By default the driver will create a single instance that has a video capture
+device with webcam, TV, S-Video and HDMI inputs, a video output device with
+S-Video and HDMI outputs, one vbi capture device, one vbi output device, one
+radio receiver device, one radio transmitter device and one SDR device.
+
+The number of instances, devices, video inputs and outputs and their types are
+all configurable using the following module options:
+
+n_devs: number of driver instances to create. By default set to 1. Up to 64
+	instances can be created.
+
+node_types: which devices should each driver instance create. An array of
+	hexadecimal values, one for each instance. The default is 0x1d3d.
+	Each value is a bitmask with the following meaning:
+		bit 0: Video Capture node
+		bit 2-3: VBI Capture node: 0 = none, 1 = raw vbi, 2 = sliced vbi, 3 = both
+		bit 4: Radio Receiver node
+		bit 5: Software Defined Radio Receiver node
+		bit 8: Video Output node
+		bit 10-11: VBI Output node: 0 = none, 1 = raw vbi, 2 = sliced vbi, 3 = both
+		bit 12: Radio Transmitter node
+		bit 16: Framebuffer for testing overlays
+
+	So to create four instances, the first two with just one video capture
+	device, the second two with just one video output device you would pass
+	these module options to vivid:
+
+		n_devs=4 node_types=0x1,0x1,0x100,0x100
+
+num_inputs: the number of inputs, one for each instance. By default 4 inputs
+	are created for each video capture device. At most 16 inputs can be created,
+	and there must be at least one.
+
+input_types: the input types for each instance, the default is 0xe4. This defines
+	what the type of each input is when the inputs are created for each driver
+	instance. This is a hexadecimal value with up to 16 pairs of bits, each
+	pair gives the type and bits 0-1 map to input 0, bits 2-3 map to input 1,
+	30-31 map to input 15. Each pair of bits has the following meaning:
+
+		00: this is a webcam input
+		01: this is a TV tuner input
+		10: this is an S-Video input
+		11: this is an HDMI input
+
+	So to create a video capture device with 8 inputs where input 0 is a TV
+	tuner, inputs 1-3 are S-Video inputs and inputs 4-7 are HDMI inputs you
+	would use the following module options:
+
+		num_inputs=8 input_types=0xffa9
+
+num_outputs: the number of outputs, one for each instance. By default 2 outputs
+	are created for each video output device. At most 16 outputs can be
+	created, and there must be at least one.
+
+output_types: the output types for each instance, the default is 0x02. This defines
+	what the type of each output is when the outputs are created for each
+	driver instance. This is a hexadecimal value with up to 16 bits, each bit
+	gives the type and bit 0 maps to output 0, bit 1 maps to output 1, bit
+	15 maps to output 15. The meaning of each bit is as follows:
+
+		0: this is an S-Video output
+		1: this is an HDMI output
+
+	So to create a video output device with 8 outputs where outputs 0-3 are
+	S-Video outputs and outputs 4-7 are HDMI outputs you would use the
+	following module options:
+
+		num_outputs=8 output_types=0xf0
+
+vid_cap_nr: give the desired videoX start number for each video capture device.
+	The default is -1 which will just take the first free number. This allows
+	you to map capture video nodes to specific videoX device nodes. Example:
+
+		n_devs=4 vid_cap_nr=2,4,6,8
+
+	This will attempt to assign /dev/video2 for the video capture device of
+	the first vivid instance, video4 for the next up to video8 for the last
+	instance. If it can't succeed, then it will just take the next free
+	number.
+
+vid_out_nr: give the desired videoX start number for each video output device.
+        The default is -1 which will just take the first free number.
+
+vbi_cap_nr: give the desired vbiX start number for each vbi capture device.
+        The default is -1 which will just take the first free number.
+
+vbi_out_nr: give the desired vbiX start number for each vbi output device.
+        The default is -1 which will just take the first free number.
+
+radio_rx_nr: give the desired radioX start number for each radio receiver device.
+        The default is -1 which will just take the first free number.
+
+radio_tx_nr: give the desired radioX start number for each radio transmitter
+	device. The default is -1 which will just take the first free number.
+
+sdr_cap_nr: give the desired swradioX start number for each SDR capture device.
+        The default is -1 which will just take the first free number.
+
+ccs_cap_mode: specify the allowed video capture crop/compose/scaling combination
+	for each driver instance. Video capture devices can have any combination
+	of cropping, composing and scaling capabilities and this will tell the
+	vivid driver which of those is should emulate. By default the user can
+	select this through controls.
+
+	The value is either -1 (controlled by the user) or a set of three bits,
+	each enabling (1) or disabling (0) one of the features:
+
+		bit 0: Enable crop support. Cropping will take only part of the
+		       incoming picture.
+		bit 1: Enable compose support. Composing will copy the incoming
+		       picture into a larger buffer.
+		bit 2: Enable scaling support. Scaling can scale the incoming
+		       picture. The scaler of the vivid driver can enlarge up
+		       or down to four times the original size. The scaler is
+		       very simple and low-quality. Simplicity and speed were
+		       key, not quality.
+
+	Note that this value is ignored by webcam inputs: those enumerate
+	discrete framesizes and that is incompatible with cropping, composing
+	or scaling.
+
+ccs_out_mode: specify the allowed video output crop/compose/scaling combination
+	for each driver instance. Video output devices can have any combination
+	of cropping, composing and scaling capabilities and this will tell the
+	vivid driver which of those is should emulate. By default the user can
+	select this through controls.
+
+	The value is either -1 (controlled by the user) or a set of three bits,
+	each enabling (1) or disabling (0) one of the features:
+
+		bit 0: Enable crop support. Cropping will take only part of the
+		       outgoing buffer.
+		bit 1: Enable compose support. Composing will copy the incoming
+		       buffer into a larger picture frame.
+		bit 2: Enable scaling support. Scaling can scale the incoming
+		       buffer. The scaler of the vivid driver can enlarge up
+		       or down to four times the original size. The scaler is
+		       very simple and low-quality. Simplicity and speed were
+		       key, not quality.
+
+multiplanar: select whether each device instance supports multi-planar formats,
+	and thus the V4L2 multi-planar API. By default the first device instance
+	is single-planar, the second multi-planar, and it keeps alternating.
+
+	This module option can override that for each instance. Values are:
+
+		0: use alternating single and multi-planar devices.
+		1: this is a single-planar instance.
+		2: this is a multi-planar instance.
+
+vivid_debug: enable driver debugging info
+
+no_error_inj: if set disable the error injecting controls. This option is
+	needed in order to run a tool like v4l2-compliance. Tools like that
+	exercise all controls including a control like 'Disconnect' which
+	emulates a USB disconnect, making the device inaccessible and so
+	all tests that v4l2-compliance is doing will fail afterwards.
+
+	There may be other situations as well where you want to disable the
+	error injection support of vivid. When this option is set, then the
+	controls that select crop, compose and scale behavior are also
+	removed. Unless overridden by ccs_cap_mode and/or ccs_out_mode the
+	will default to enabling crop, compose and scaling.
+
+Taken together, all these module options allow you to precisely customize
+the driver behavior and test your application with all sorts of permutations.
+It is also very suitable to emulate hardware that is not yet available, e.g.
+when developing software for a new upcoming device.
+
+
+Section 2: Video Capture
+------------------------
+
+This is probably the most frequently used feature. The video capture device
+can be configured by using the module options num_inputs, input_types and
+ccs_cap_mode (see section 1 for more detailed information), but by default
+four inputs are configured: a webcam, a TV tuner, an S-Video and an HDMI
+input, one input for each input type. Those are described in more detail
+below.
+
+Special attention has been given to the rate at which new frames become
+available. The jitter will be around 1 jiffie (that depends on the HZ
+configuration of your kernel, so usually 1/100, 1/250 or 1/1000 of a second),
+but the long-term behavior is exactly following the framerate. So a
+framerate of 59.94 Hz is really different from 60 Hz. If the framerate
+exceeds your kernel's HZ value, then you will get dropped frames, but the
+frame/field sequence counting will keep track of that so the sequence
+count will skip whenever frames are dropped.
+
+
+Section 2.1: Webcam Input
+-------------------------
+
+The webcam input supports three framesizes: 320x180, 640x360 and 1280x720. It
+supports frames per second settings of 10, 15, 25, 30, 50 and 60 fps. Which ones
+are available depends on the chosen framesize: the larger the framesize, the
+lower the maximum frames per second.
+
+The initially selected colorspace when you switch to the webcam input will be
+sRGB.
+
+
+Section 2.2: TV and S-Video Inputs
+----------------------------------
+
+The only difference between the TV and S-Video input is that the TV has a
+tuner. Otherwise they behave identically.
+
+These inputs support audio inputs as well: one TV and one Line-In. They
+both support all TV standards. If the standard is queried, then the Vivid
+controls 'Standard Signal Mode' and 'Standard' determine what
+the result will be.
+
+These inputs support all combinations of the field setting. Special care has
+been taken to faithfully reproduce how fields are handled for the different
+TV standards. This is particularly noticable when generating a horizontally
+moving image so the temporal effect of using interlaced formats becomes clearly
+visible. For 50 Hz standards the top field is the oldest and the bottom field
+is the newest in time. For 60 Hz standards that is reversed: the bottom field
+is the oldest and the top field is the newest in time.
+
+When you start capturing in V4L2_FIELD_ALTERNATE mode the first buffer will
+contain the top field for 50 Hz standards and the bottom field for 60 Hz
+standards. This is what capture hardware does as well.
+
+Finally, for PAL/SECAM standards the first half of the top line contains noise.
+This simulates the Wide Screen Signal that is commonly placed there.
+
+The initially selected colorspace when you switch to the TV or S-Video input
+will be SMPTE-170M.
+
+The pixel aspect ratio will depend on the TV standard. The video aspect ratio
+can be selected through the 'Standard Aspect Ratio' Vivid control.
+Choices are '4x3', '16x9' which will give letterboxed widescreen video and
+'16x9 Anomorphic' which will give full screen squashed anamorphic widescreen
+video that will need to be scaled accordingly.
+
+The TV 'tuner' supports a frequency range of 44-958 MHz. Channels are available
+every 6 MHz, starting from 49.25 MHz. For each channel the generated image
+will be in color for the +/- 0.25 MHz around it, and in grayscale for
++/- 1 MHz around the channel. Beyond that it is just noise. The VIDIOC_G_TUNER
+ioctl will return 100% signal strength for +/- 0.25 MHz and 50% for +/- 1 MHz.
+It will also return correct afc values to show whether the frequency is too
+low or too high.
+
+The audio subchannels that are returned are MONO for the +/- 1 MHz range around
+a valid channel frequency. When the frequency is within +/- 0.25 MHz of the
+channel it will return either MONO, STEREO, either MONO | SAP (for NTSC) or
+LANG1 | LANG2 (for others), or STEREO | SAP.
+
+Which one is returned depends on the chosen channel, each next valid channel
+will cycle through the possible audio subchannel combinations. This allows
+you to test the various combinations by just switching channels..
+
+Finally, for these inputs the v4l2_timecode struct is filled in in the
+dequeued v4l2_buffer struct.
+
+
+Section 2.3: HDMI Input
+-----------------------
+
+The HDMI inputs supports all CEA-861 and DMT timings, both progressive and
+interlaced, for pixelclock frequencies between 25 and 600 MHz. The field
+mode for interlaced formats is always V4L2_FIELD_ALTERNATE. For HDMI the
+field order is always top field first, and when you start capturing an
+interlaced format you will receive the top field first.
+
+The initially selected colorspace when you switch to the HDMI input or
+select an HDMI timing is based on the format resolution: for resolutions
+less than or equal to 720x576 the colorspace is set to SMPTE-170M, for
+others it is set to REC-709 (CEA-861 timings) or sRGB (VESA DMT timings).
+
+The pixel aspect ratio will depend on the HDMI timing: for 720x480 is it
+set as for the NTSC TV standard, for 720x576 it is set as for the PAL TV
+standard, and for all others a 1:1 pixel aspect ratio is returned.
+
+The video aspect ratio can be selected through the 'DV Timings Aspect Ratio'
+Vivid control. Choices are 'Source Width x Height' (just use the
+same ratio as the chosen format), '4x3' or '16x9', either of which can
+result in pillarboxed or letterboxed video.
+
+For HDMI inputs it is possible to set the EDID. By default a simple EDID
+is provided. You can only set the EDID for HDMI inputs. Internally, however,
+the EDID is shared between all HDMI inputs.
+
+No interpretation is done of the EDID data.
+
+
+Section 3: Video Output
+-----------------------
+
+The video output device can be configured by using the module options
+num_outputs, output_types and ccs_out_mode (see section 1 for more detailed
+information), but by default two outputs are configured: an S-Video and an
+HDMI input, one output for each output type. Those are described in more detail
+below.
+
+Like with video capture the framerate is also exact in the long term.
+
+
+Section 3.1: S-Video Output
+---------------------------
+
+This output supports audio outputs as well: "Line-Out 1" and "Line-Out 2".
+The S-Video output supports all TV standards.
+
+This output supports all combinations of the field setting.
+
+The initially selected colorspace when you switch to the TV or S-Video input
+will be SMPTE-170M.
+
+
+Section 3.2: HDMI Output
+------------------------
+
+The HDMI output supports all CEA-861 and DMT timings, both progressive and
+interlaced, for pixelclock frequencies between 25 and 600 MHz. The field
+mode for interlaced formats is always V4L2_FIELD_ALTERNATE.
+
+The initially selected colorspace when you switch to the HDMI output or
+select an HDMI timing is based on the format resolution: for resolutions
+less than or equal to 720x576 the colorspace is set to SMPTE-170M, for
+others it is set to REC-709 (CEA-861 timings) or sRGB (VESA DMT timings).
+
+The pixel aspect ratio will depend on the HDMI timing: for 720x480 is it
+set as for the NTSC TV standard, for 720x576 it is set as for the PAL TV
+standard, and for all others a 1:1 pixel aspect ratio is returned.
+
+An HDMI output has a valid EDID which can be obtained through VIDIOC_G_EDID.
+
+
+Section 4: VBI Capture
+----------------------
+
+There are three types of VBI capture devices: those that only support raw
+(undecoded) VBI, those that only support sliced (decoded) VBI and those that
+support both. This is determined by the node_types module option. In all
+cases the driver will generate valid VBI data: for 60 Hz standards it will
+generate Closed Caption and XDS data. The closed caption stream will
+alternate between "Hello world!" and "Closed captions test" every second.
+The XDS stream will give the current time once a minute. For 50 Hz standards
+it will generate the Wide Screen Signal which is based on the actual Video
+Aspect Ratio control setting and teletext pages 100-159, one page per frame.
+
+The VBI device will only work for the S-Video and TV inputs, it will give
+back an error if the current input is a webcam or HDMI.
+
+
+Section 5: VBI Output
+---------------------
+
+There are three types of VBI output devices: those that only support raw
+(undecoded) VBI, those that only support sliced (decoded) VBI and those that
+support both. This is determined by the node_types module option.
+
+The sliced VBI output supports the Wide Screen Signal and the teletext signal
+for 50 Hz standards and Closed Captioning + XDS for 60 Hz standards.
+
+The VBI device will only work for the S-Video output, it will give
+back an error if the current output is HDMI.
+
+
+Section 6: Radio Receiver
+-------------------------
+
+The radio receiver emulates an FM/AM/SW receiver. The FM band also supports RDS.
+The frequency ranges are:
+
+	FM: 64 MHz - 108 MHz
+	AM: 520 kHz - 1710 kHz
+	SW: 2300 kHz - 26.1 MHz
+
+Valid channels are emulated every 1 MHz for FM and every 100 kHz for AM and SW.
+The signal strength decreases the further the frequency is from the valid
+frequency until it becomes 0% at +/- 50 kHz (FM) or 5 kHz (AM/SW) from the
+ideal frequency. The initial frequency when the driver is loaded is set to
+95 MHz.
+
+The FM receiver supports RDS as well, both using 'Block I/O' and 'Controls'
+modes. In the 'Controls' mode the RDS information is stored in read-only
+controls. These controls are updated every time the frequency is changed,
+or when the tuner status is requested. The Block I/O method uses the read()
+interface to pass the RDS blocks on to the application for decoding.
+
+The RDS signal is 'detected' for +/- 12.5 kHz around the channel frequency,
+and the further the frequency is away from the valid frequency the more RDS
+errors are randomly introduced into the block I/O stream, up to 50% of all
+blocks if you are +/- 12.5 kHz from the channel frequency. All four errors
+can occur in equal proportions: blocks marked 'CORRECTED', blocks marked
+'ERROR', blocks marked 'INVALID' and dropped blocks.
+
+The generated RDS stream contains all the standard fields contained in a
+0B group, and also radio text and the current time.
+
+The receiver supports HW frequency seek, either in Bounded mode, Wrap Around
+mode or both, which is configurable with the "Radio HW Seek Mode" control.
+
+
+Section 7: Radio Transmitter
+----------------------------
+
+The radio transmitter emulates an FM/AM/SW transmitter. The FM band also supports RDS.
+The frequency ranges are:
+
+	FM: 64 MHz - 108 MHz
+	AM: 520 kHz - 1710 kHz
+	SW: 2300 kHz - 26.1 MHz
+
+The initial frequency when the driver is loaded is 95.5 MHz.
+
+The FM transmitter supports RDS as well, both using 'Block I/O' and 'Controls'
+modes. In the 'Controls' mode the transmitted RDS information is configured
+using controls, and in 'Block I/O' mode the blocks are passed to the driver
+using write().
+
+
+Section 8: Software Defined Radio Receiver
+------------------------------------------
+
+The SDR receiver has three frequency bands for the ADC tuner:
+
+	- 300 kHz
+	- 900 kHz - 2800 kHz
+	- 3200 kHz
+
+The RF tuner supports 50 MHz - 2000 MHz.
+
+The generated data contains the In-phase and Quadrature components of a
+1 kHz tone that has an amplitude of sqrt(2).
+
+
+Section 9: Controls
+-------------------
+
+Different devices support different controls. The sections below will describe
+each control and which devices support them.
+
+
+Section 9.1: User Controls - Test Controls
+------------------------------------------
+
+The Button, Boolean, Integer 32 Bits, Integer 64 Bits, Menu, String, Bitmask and
+Integer Menu are controls that represent all possible control types. The Menu
+control and the Integer Menu control both have 'holes' in their menu list,
+meaning that one or more menu items return EINVAL when VIDIOC_QUERYMENU is called.
+Both menu controls also have a non-zero minimum control value.  These features
+allow you to check if your application can handle such things correctly.
+These controls are supported for every device type.
+
+
+Section 9.2: User Controls - Video Capture
+------------------------------------------
+
+The following controls are specific to video capture.
+
+The Brightness, Contrast, Saturation and Hue controls actually work and are
+standard. There is one special feature with the Brightness control: each
+video input has its own brightness value, so changing input will restore
+the brightness for that input. In addition, each video input uses a different
+brightness range (minimum and maximum control values). Switching inputs will
+cause a control event to be sent with the V4L2_EVENT_CTRL_CH_RANGE flag set.
+This allows you to test controls that can change their range.
+
+The 'Gain, Automatic' and Gain controls can be used to test volatile controls:
+if 'Gain, Automatic' is set, then the Gain control is volatile and changes
+constantly. If 'Gain, Automatic' is cleared, then the Gain control is a normal
+control.
+
+The 'Horizontal Flip' and 'Vertical Flip' controls can be used to flip the
+image. These combine with the 'Sensor Flipped Horizontally/Vertically' Vivid
+controls.
+
+The 'Alpha Component' control can be used to set the alpha component for
+formats containing an alpha channel.
+
+
+Section 9.3: User Controls - Audio
+----------------------------------
+
+The following controls are specific to video capture and output and radio
+receivers and transmitters.
+
+The 'Volume' and 'Mute' audio controls are typical for such devices to
+control the volume and mute the audio. They don't actually do anything in
+the vivid driver.
+
+
+Section 9.4: Vivid Controls
+---------------------------
+
+These vivid custom controls control the image generation, error injection, etc.
+
+
+Section 9.4.1: Test Pattern Controls
+------------------------------------
+
+The Test Pattern Controls are all specific to video capture.
+
+Test Pattern: selects which test pattern to use. Use the CSC Colorbar for
+	testing colorspace conversions: the colors used in that test pattern
+	map to valid colors in all colorspaces. The colorspace conversion
+	is disabled for the other test patterns.
+
+OSD Text Mode: selects whether the text superimposed on the
+	test pattern should be shown, and if so, whether only counters should
+	be displayed or the full text.
+
+Horizontal Movement: selects whether the test pattern should
+	move to the left or right and at what speed.
+
+Vertical Movement: does the same for the vertical direction.
+
+Show Border: show a two-pixel wide border at the edge of the actual image,
+	excluding letter or pillarboxing.
+
+Show Square: show a square in the middle of the image. If the image is
+	displayed with the correct pixel and image aspect ratio corrections,
+	then the width and height of the square on the monitor should be
+	the same.
+
+Insert SAV Code in Image: adds a SAV (Start of Active Video) code to the image.
+	This can be used to check if such codes in the image are inadvertently
+	interpreted instead of being ignored.
+
+Insert EAV Code in Image: does the same for the EAV (End of Active Video) code.
+
+
+Section 9.4.2: Capture Feature Selection Controls
+-------------------------------------------------
+
+These controls are all specific to video capture.
+
+Sensor Flipped Horizontally: the image is flipped horizontally and the
+	V4L2_IN_ST_HFLIP input status flag is set. This emulates the case where
+	a sensor is for example mounted upside down.
+
+Sensor Flipped Vertically: the image is flipped vertically and the
+	V4L2_IN_ST_VFLIP input status flag is set. This emulates the case where
+        a sensor is for example mounted upside down.
+
+Standard Aspect Ratio: selects if the image aspect ratio as used for the TV or
+	S-Video input should be 4x3, 16x9 or anamorphic widescreen. This may
+	introduce letterboxing.
+
+DV Timings Aspect Ratio: selects if the image aspect ratio as used for the HDMI
+	input should be the same as the source width and height ratio, or if
+	it should be 4x3 or 16x9. This may introduce letter or pillarboxing.
+
+Timestamp Source: selects when the timestamp for each buffer is taken.
+
+Colorspace: selects which colorspace should be used when generating the image.
+	This only applies if the CSC Colorbar test pattern is selected,
+	otherwise the test pattern will go through unconverted (except for
+	the so-called 'Transfer Function' corrections and the R'G'B' to Y'CbCr
+	conversion). This behavior is also what you want, since a 75% Colorbar
+	should really have 75% signal intensity and should not be affected
+	by colorspace conversions.
+
+	Changing the colorspace will result in the V4L2_EVENT_SOURCE_CHANGE
+	to be sent since it emulates a detected colorspace change.
+
+Limited RGB Range (16-235): selects if the RGB range of the HDMI source should
+	be limited or full range. This combines with the Digital Video 'Rx RGB
+	Quantization Range' control and can be used to test what happens if
+	a source provides you with the wrong quantization range information.
+	See the description of that control for more details.
+
+Apply Alpha To Red Only: apply the alpha channel as set by the 'Alpha Component'
+	user control to the red color of the test pattern only.
+
+Enable Capture Cropping: enables crop support. This control is only present if
+	the ccs_cap_mode module option is set to the default value of -1 and if
+	the no_error_inj module option is set to 0 (the default).
+
+Enable Capture Composing: enables composing support. This control is only
+	present if the ccs_cap_mode module option is set to the default value of
+	-1 and if the no_error_inj module option is set to 0 (the default).
+
+Enable Capture Scaler: enables support for a scaler (maximum 4 times upscaling
+	and downscaling). This control is only present if the ccs_cap_mode
+	module option is set to the default value of -1 and if the no_error_inj
+	module option is set to 0 (the default).
+
+Maximum EDID Blocks: determines how many EDID blocks the driver supports.
+	Note that the vivid driver does not actually interpret new EDID
+	data, it just stores it. It allows for up to 256 EDID blocks
+	which is the maximum supported by the standard.
+
+Fill Percentage of Frame: can be used to draw only the top X percent
+	of the image. Since each frame has to be drawn by the driver, this
+	demands a lot of the CPU. For large resolutions this becomes
+	problematic. By drawing only part of the image this CPU load can
+	be reduced.
+
+
+Section 9.4.3: Output Feature Selection Controls
+------------------------------------------------
+
+These controls are all specific to video output.
+
+Enable Output Cropping: enables crop support. This control is only present if
+	the ccs_out_mode module option is set to the default value of -1 and if
+	the no_error_inj module option is set to 0 (the default).
+
+Enable Output Composing: enables composing support. This control is only
+	present if the ccs_out_mode module option is set to the default value of
+	-1 and if the no_error_inj module option is set to 0 (the default).
+
+Enable Output Scaler: enables support for a scaler (maximum 4 times upscaling
+	and downscaling). This control is only present if the ccs_out_mode
+	module option is set to the default value of -1 and if the no_error_inj
+	module option is set to 0 (the default).
+
+
+Section 9.4.4: Error Injection Controls
+---------------------------------------
+
+The following two controls are only valid for video and vbi capture.
+
+Standard Signal Mode: selects the behavior of VIDIOC_QUERYSTD: what should
+	it return?
+
+	Changing this control will result in the V4L2_EVENT_SOURCE_CHANGE
+	to be sent since it emulates a changed input condition (e.g. a cable
+	was plugged in or out).
+
+Standard: selects the standard that VIDIOC_QUERYSTD should return if the
+	previous control is set to "Selected Standard".
+
+	Changing this control will result in the V4L2_EVENT_SOURCE_CHANGE
+	to be sent since it emulates a changed input standard.
+
+
+The following two controls are only valid for video capture.
+
+DV Timings Signal Mode: selects the behavior of VIDIOC_QUERY_DV_TIMINGS: what
+	should it return?
+
+	Changing this control will result in the V4L2_EVENT_SOURCE_CHANGE
+	to be sent since it emulates a changed input condition (e.g. a cable
+	was plugged in or out).
+
+DV Timings: selects the timings the VIDIOC_QUERY_DV_TIMINGS should return
+	if the previous control is set to "Selected DV Timings".
+
+	Changing this control will result in the V4L2_EVENT_SOURCE_CHANGE
+	to be sent since it emulates changed input timings.
+
+
+The following controls are only present if the no_error_inj module option
+is set to 0 (the default). These controls are valid for video and vbi
+capture and output streams and for the SDR capture device except for the
+Disconnect control which is valid for all devices.
+
+Wrap Sequence Number: test what happens when you wrap the sequence number in
+	struct v4l2_buffer around.
+
+Wrap Timestamp: test what happens when you wrap the timestamp in struct
+	v4l2_buffer around.
+
+Percentage of Dropped Buffers: sets the percentage of buffers that
+	are never returned by the driver (i.e., they are dropped).
+
+Disconnect: emulates a USB disconnect. The device will act as if it has
+	been disconnected. Only after all open filehandles to the device
+	node have been closed will the device become 'connected' again.
+
+Inject V4L2_BUF_FLAG_ERROR: when pressed, the next frame returned by
+	the driver will have the error flag set (i.e. the frame is marked
+	corrupt).
+
+Inject VIDIOC_REQBUFS Error: when pressed, the next REQBUFS or CREATE_BUFS
+	ioctl call will fail with an error. To be precise: the videobuf2
+	queue_setup() op will return -EINVAL.
+
+Inject VIDIOC_QBUF Error: when pressed, the next VIDIOC_QBUF or
+	VIDIOC_PREPARE_BUFFER ioctl call will fail with an error. To be
+	precise: the videobuf2 buf_prepare() op will return -EINVAL.
+
+Inject VIDIOC_STREAMON Error: when pressed, the next VIDIOC_STREAMON ioctl
+	call will fail with an error. To be precise: the videobuf2
+	start_streaming() op will return -EINVAL.
+
+Inject Fatal Streaming Error: when pressed, the streaming core will be
+	marked as having suffered a fatal error, the only way to recover
+	from that is to stop streaming. To be precise: the videobuf2
+	vb2_queue_error() function is called.
+
+
+Section 9.4.5: VBI Raw Capture Controls
+---------------------------------------
+
+Interlaced VBI Format: if set, then the raw VBI data will be interlaced instead
+	of providing it grouped by field.
+
+
+Section 9.5: Digital Video Controls
+-----------------------------------
+
+Rx RGB Quantization Range: sets the RGB quantization detection of the HDMI
+	input. This combines with the Vivid 'Limited RGB Range (16-235)'
+	control and can be used to test what happens if a source provides
+	you with the wrong quantization range information. This can be tested
+	by selecting an HDMI input, setting this control to Full or Limited
+	range and selecting the opposite in the 'Limited RGB Range (16-235)'
+	control. The effect is easy to see if the 'Gray Ramp' test pattern
+	is selected.
+
+Tx RGB Quantization Range: sets the RGB quantization detection of the HDMI
+	output. It is currently not used for anything in vivid, but most HDMI
+	transmitters would typically have this control.
+
+Transmit Mode: sets the transmit mode of the HDMI output to HDMI or DVI-D. This
+	affects the reported colorspace since DVI_D outputs will always use
+	sRGB.
+
+
+Section 9.6: FM Radio Receiver Controls
+---------------------------------------
+
+RDS Reception: set if the RDS receiver should be enabled.
+
+RDS Program Type:
+RDS PS Name:
+RDS Radio Text:
+RDS Traffic Announcement:
+RDS Traffic Program:
+RDS Music: these are all read-only controls. If RDS Rx I/O Mode is set to
+	"Block I/O", then they are inactive as well. If RDS Rx I/O Mode is set
+	to "Controls", then these controls report the received RDS data. Note
+	that the vivid implementation of this is pretty basic: they are only
+	updated when you set a new frequency or when you get the tuner status
+	(VIDIOC_G_TUNER).
+
+Radio HW Seek Mode: can be one of "Bounded", "Wrap Around" or "Both". This
+	determines if VIDIOC_S_HW_FREQ_SEEK will be bounded by the frequency
+	range or wrap-around or if it is selectable by the user.
+
+Radio Programmable HW Seek: if set, then the user can provide the lower and
+	upper bound of the HW Seek. Otherwise the frequency range boundaries
+	will be used.
+
+Generate RBDS Instead of RDS: if set, then generate RBDS (the US variant of
+	RDS) data instead of RDS (European-style RDS). This affects only the
+	PICODE and PTY codes.
+
+RDS Rx I/O Mode: this can be "Block I/O" where the RDS blocks have to be read()
+	by the application, or "Controls" where the RDS data is provided by
+	the RDS controls mentioned above.
+
+
+Section 9.7: FM Radio Modulator Controls
+----------------------------------------
+
+RDS Program ID:
+RDS Program Type:
+RDS PS Name:
+RDS Radio Text:
+RDS Stereo:
+RDS Artificial Head:
+RDS Compressed:
+RDS Dymanic PTY:
+RDS Traffic Announcement:
+RDS Traffic Program:
+RDS Music: these are all controls that set the RDS data that is transmitted by
+	the FM modulator.
+
+RDS Tx I/O Mode: this can be "Block I/O" where the application has to use write()
+	to pass the RDS blocks to the driver, or "Controls" where the RDS data is
+	provided by the RDS controls mentioned above.
+
+
+Section 10: Video, VBI and RDS Looping
+--------------------------------------
+
+The vivid driver supports looping of video output to video input, VBI output
+to VBI input and RDS output to RDS input. For video/VBI looping this emulates
+as if a cable was hooked up between the output and input connector. So video
+and VBI looping is only supported between S-Video and HDMI inputs and outputs.
+VBI is only valid for S-Video as it makes no sense for HDMI.
+
+Since radio is wireless this looping always happens if the radio receiver
+frequency is close to the radio transmitter frequency. In that case the radio
+transmitter will 'override' the emulated radio stations.
+
+Looping is currently supported only between devices created by the same
+vivid driver instance.
+
+
+Section 10.1: Video and Sliced VBI looping
+------------------------------------------
+
+The way to enable video/VBI looping is currently fairly crude. A 'Loop Video'
+control is available in the "Vivid" control class of the video
+output and VBI output devices. When checked the video looping will be enabled.
+Once enabled any video S-Video or HDMI input will show a static test pattern
+until the video output has started. At that time the video output will be
+looped to the video input provided that:
+
+- the input type matches the output type. So the HDMI input cannot receive
+  video from the S-Video output.
+
+- the video resolution of the video input must match that of the video output.
+  So it is not possible to loop a 50 Hz (720x576) S-Video output to a 60 Hz
+  (720x480) S-Video input, or a 720p60 HDMI output to a 1080p30 input.
+
+- the pixel formats must be identical on both sides. Otherwise the driver would
+  have to do pixel format conversion as well, and that's taking things too far.
+
+- the field settings must be identical on both sides. Same reason as above:
+  requiring the driver to convert from one field format to another complicated
+  matters too much. This also prohibits capturing with 'Field Top' or 'Field
+  Bottom' when the output video is set to 'Field Alternate'. This combination,
+  while legal, became too complicated to support. Both sides have to be 'Field
+  Alternate' for this to work. Also note that for this specific case the
+  sequence and field counting in struct v4l2_buffer on the capture side may not
+  be 100% accurate.
+
+- on the input side the "Standard Signal Mode" for the S-Video input or the
+  "DV Timings Signal Mode" for the HDMI input should be configured so that a
+  valid signal is passed to the video input.
+
+The framerates do not have to match, although this might change in the future.
+
+By default you will see the OSD text superimposed on top of the looped video.
+This can be turned off by changing the "OSD Text Mode" control of the video
+capture device.
+
+For VBI looping to work all of the above must be valid and in addition the vbi
+output must be configured for sliced VBI. The VBI capture side can be configured
+for either raw or sliced VBI. Note that at the moment only CC/XDS (60 Hz formats)
+and WSS (50 Hz formats) VBI data is looped. Teletext VBI data is not looped.
+
+
+Section 10.2: Radio & RDS Looping
+---------------------------------
+
+As mentioned in section 6 the radio receiver emulates stations are regular
+frequency intervals. Depending on the frequency of the radio receiver a
+signal strength value is calculated (this is returned by VIDIOC_G_TUNER).
+However, it will also look at the frequency set by the radio transmitter and
+if that results in a higher signal strength than the settings of the radio
+transmitter will be used as if it was a valid station. This also includes
+the RDS data (if any) that the transmitter 'transmits'. This is received
+faithfully on the receiver side. Note that when the driver is loaded the
+frequencies of the radio receiver and transmitter are not identical, so
+initially no looping takes place.
+
+
+Section 11: Cropping, Composing, Scaling
+----------------------------------------
+
+This driver supports cropping, composing and scaling in any combination. Normally
+which features are supported can be selected through the Vivid controls,
+but it is also possible to hardcode it when the module is loaded through the
+ccs_cap_mode and ccs_out_mode module options. See section 1 on the details of
+these module options.
+
+This allows you to test your application for all these variations.
+
+Note that the webcam input never supports cropping, composing or scaling. That
+only applies to the TV/S-Video/HDMI inputs and outputs. The reason is that
+webcams, including this virtual implementation, normally use
+VIDIOC_ENUM_FRAMESIZES to list a set of discrete framesizes that it supports.
+And that does not combine with cropping, composing or scaling. This is
+primarily a limitation of the V4L2 API which is carefully reproduced here.
+
+The minimum and maximum resolutions that the scaler can achieve are 16x16 and
+(4096 * 4) x (2160 x 4), but it can only scale up or down by a factor of 4 or
+less. So for a source resolution of 1280x720 the minimum the scaler can do is
+320x180 and the maximum is 5120x2880. You can play around with this using the
+qv4l2 test tool and you will see these dependencies.
+
+This driver also supports larger 'bytesperline' settings, something that
+VIDIOC_S_FMT allows but that few drivers implement.
+
+The scaler is a simple scaler that uses the Coarse Bresenham algorithm. It's
+designed for speed and simplicity, not quality.
+
+If the combination of crop, compose and scaling allows it, then it is possible
+to change crop and compose rectangles on the fly.
+
+
+Section 12: Formats
+-------------------
+
+The driver supports all the regular packed YUYV formats, 16, 24 and 32 RGB
+packed formats and two multiplanar formats (one luma and one chroma plane).
+
+The alpha component can be set through the 'Alpha Component' User control
+for those formats that support it. If the 'Apply Alpha To Red Only' control
+is set, then the alpha component is only used for the color red and set to
+0 otherwise.
+
+The driver has to be configured to support the multiplanar formats. By default
+the first driver instance is single-planar, the second is multi-planar, and it
+keeps alternating. This can be changed by setting the multiplanar module option,
+see section 1 for more details on that option.
+
+If the driver instance is using the multiplanar formats/API, then the first
+single planar format (YUYV) and the multiplanar NV16M and NV61M formats the
+will have a plane that has a non-zero data_offset of 128 bytes. It is rare for
+data_offset to be non-zero, so this is a useful feature for testing applications.
+
+Video output will also honor any data_offset that the application set.
+
+
+Section 13: Capture Overlay
+---------------------------
+
+Note: capture overlay support is implemented primarily to test the existing
+V4L2 capture overlay API. In practice few if any GPUs support such overlays
+anymore, and neither are they generally needed anymore since modern hardware
+is so much more capable. By setting flag 0x10000 in the node_types module
+option the vivid driver will create a simple framebuffer device that can be
+used for testing this API. Whether this API should be used for new drivers is
+questionable.
+
+This driver has support for a destructive capture overlay with bitmap clipping
+and list clipping (up to 16 rectangles) capabilities. Overlays are not
+supported for multiplanar formats. It also honors the struct v4l2_window field
+setting: if it is set to FIELD_TOP or FIELD_BOTTOM and the capture setting is
+FIELD_ALTERNATE, then only the top or bottom fields will be copied to the overlay.
+
+The overlay only works if you are also capturing at that same time. This is a
+vivid limitation since it copies from a buffer to the overlay instead of
+filling the overlay directly. And if you are not capturing, then no buffers
+are available to fill.
+
+In addition, the pixelformat of the capture format and that of the framebuffer
+must be the same for the overlay to work. Otherwise VIDIOC_OVERLAY will return
+an error.
+
+In order to really see what it going on you will need to create two vivid
+instances: the first with a framebuffer enabled. You configure the capture
+overlay of the second instance to use the framebuffer of the first, then
+you start capturing in the second instance. For the first instance you setup
+the output overlay for the video output, turn on video looping and capture
+to see the blended framebuffer overlay that's being written to by the second
+instance. This setup would require the following commands:
+
+	$ sudo modprobe vivid n_devs=2 node_types=0x10101,0x1 multiplanar=1,1
+	$ v4l2-ctl -d1 --find-fb
+	/dev/fb1 is the framebuffer associated with base address 0x12800000
+	$ sudo v4l2-ctl -d2 --set-fbuf fb=1
+	$ v4l2-ctl -d1 --set-fbuf fb=1
+	$ v4l2-ctl -d0 --set-fmt-video=pixelformat='AR15'
+	$ v4l2-ctl -d1 --set-fmt-video-out=pixelformat='AR15'
+	$ v4l2-ctl -d2 --set-fmt-video=pixelformat='AR15'
+	$ v4l2-ctl -d0 -i2
+	$ v4l2-ctl -d2 -i2
+	$ v4l2-ctl -d2 -c horizontal_movement=4
+	$ v4l2-ctl -d1 --overlay=1
+	$ v4l2-ctl -d1 -c loop_video=1
+	$ v4l2-ctl -d2 --stream-mmap --overlay=1
+
+And from another console:
+
+	$ v4l2-ctl -d1 --stream-out-mmap
+
+And yet another console:
+
+	$ qv4l2
+
+and start streaming.
+
+As you can see, this is not for the faint of heart...
+
+
+Section 14: Output Overlay
+--------------------------
+
+Note: output overlays are primarily implemented in order to test the existing
+V4L2 output overlay API. Whether this API should be used for new drivers is
+questionable.
+
+This driver has support for an output overlay and is capable of:
+
+	- bitmap clipping,
+	- list clipping (up to 16 rectangles)
+	- chromakey
+	- source chromakey
+	- global alpha
+	- local alpha
+	- local inverse alpha
+
+Output overlays are not supported for multiplanar formats. In addition, the
+pixelformat of the capture format and that of the framebuffer must be the
+same for the overlay to work. Otherwise VIDIOC_OVERLAY will return an error.
+
+Output overlays only work if the driver has been configured to create a
+framebuffer by setting flag 0x10000 in the node_types module option. The
+created framebuffer has a size of 720x576 and supports ARGB 1:5:5:5 and
+RGB 5:6:5.
+
+In order to see the effects of the various clipping, chromakeying or alpha
+processing capabilities you need to turn on video looping and see the results
+on the capture side. The use of the clipping, chromakeying or alpha processing
+capabilities will slow down the video loop considerably as a lot of checks have
+to be done per pixel.
+
+
+Section 15: Some Future Improvements
+------------------------------------
+
+Just as a reminder and in no particular order:
+
+- Add a virtual alsa driver to test audio
+- Add virtual sub-devices and media controller support
+- Some support for testing compressed video
+- Add support to loop raw VBI output to raw VBI input
+- Add support to loop teletext sliced VBI output to VBI input
+- Fix sequence/field numbering when looping of video with alternate fields
+- Add support for V4L2_CID_BG_COLOR for video outputs
+- Add ARGB888 overlay support: better testing of the alpha channel
+- Add custom DV timings support
+- Add support for V4L2_DV_FL_REDUCED_FPS
+- Improve pixel aspect support in the tpg code by passing a real v4l2_fract
+- Use per-queue locks and/or per-device locks to improve throughput
+- Add support to loop from a specific output to a specific input across
+  vivid instances
+- Add support for VIDIOC_EXPBUF once support for that has been added to vb2
+- The SDR radio should use the same 'frequencies' for stations as the normal
+  radio receiver, and give back noise if the frequency doesn't match up with
+  a station frequency
+- Improve the sine generation of the SDR radio.
+- Make a thread for the RDS generation, that would help in particular for the
+  "Controls" RDS Rx I/O Mode as the read-only RDS controls could be updated
+  in real-time.
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index afe68ddbe6a4..052ee643a32e 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -5,7 +5,7 @@ Virtual memory map with 4 level page tables:
 
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
 hole caused by [48:63] sign extension
-ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
+ffff800000000000 - ffff87ffffffffff (=43 bits) guard hole, reserved for hypervisor
 ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory
 ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole
 ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
diff --git a/MAINTAINERS b/MAINTAINERS
index 6dc0840c1aa2..33c0d433d554 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1338,8 +1338,7 @@ ARM/SAMSUNG MOBILE MACHINE SUPPORT
 M:	Kyungmin Park <kyungmin.park@samsung.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-F:	arch/arm/mach-s5pv210/mach-aquila.c
-F:	arch/arm/mach-s5pv210/mach-goni.c
+F:	arch/arm/mach-s5pv210/
 
 ARM/SAMSUNG S5P SERIES 2D GRAPHICS ACCELERATION (G2D) SUPPORT
 M:	Kyungmin Park <kyungmin.park@samsung.com>
@@ -1550,6 +1549,7 @@ T:	git git://git.xilinx.com/linux-xlnx.git
 S:	Supported
 F:	arch/arm/mach-zynq/
 F:	drivers/cpuidle/cpuidle-zynq.c
+F:	drivers/block/xsysace.c
 N:	zynq
 N:	xilinx
 F:	drivers/clocksource/cadence_ttc_timer.c
@@ -1738,6 +1738,12 @@ M:	Nicolas Ferre <nicolas.ferre@atmel.com>
 S:	Supported
 F:	drivers/net/ethernet/cadence/
 
+ATMEL NAND DRIVER
+M:	Josh Wu <josh.wu@atmel.com>
+L:	linux-mtd@lists.infradead.org
+S:	Supported
+F:	drivers/mtd/nand/atmel_nand*
+
 ATMEL SPI DRIVER
 M:	Nicolas Ferre <nicolas.ferre@atmel.com>
 S:	Supported
@@ -2760,6 +2766,18 @@ W:	http://www.chelsio.com
 S:	Supported
 F:	drivers/net/ethernet/chelsio/cxgb4vf/
 
+CXL (IBM Coherent Accelerator Processor Interface CAPI) DRIVER
+M:	Ian Munsie <imunsie@au1.ibm.com>
+M:	Michael Neuling <mikey@neuling.org>
+L:	linuxppc-dev@lists.ozlabs.org
+S:	Supported
+F:	drivers/misc/cxl/
+F:	include/misc/cxl.h
+F:	include/uapi/misc/cxl.h
+F:	Documentation/powerpc/cxl.txt
+F:	Documentation/powerpc/cxl.txt
+F:	Documentation/ABI/testing/sysfs-class-cxl
+
 STMMAC ETHERNET DRIVER
 M:	Giuseppe Cavallaro <peppe.cavallaro@st.com>
 L:	netdev@vger.kernel.org
@@ -3036,7 +3054,7 @@ M:	Sumit Semwal <sumit.semwal@linaro.org>
 S:	Maintained
 L:	linux-media@vger.kernel.org
 L:	dri-devel@lists.freedesktop.org
-L:	linaro-mm-sig@lists.linaro.org
+L:	linaro-mm-sig@lists.linaro.org (moderated for non-subscribers)
 F:	drivers/dma-buf/
 F:	include/linux/dma-buf*
 F:	include/linux/reservation.h
@@ -3067,14 +3085,13 @@ S:	Supported
 F:	drivers/acpi/dock.c
 
 DOCUMENTATION
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jonathan Corbet <corbet@lwn.net>
 L:	linux-doc@vger.kernel.org
 S:	Maintained
 F:	Documentation/
 X:	Documentation/ABI/
 X:	Documentation/devicetree/
 X:	Documentation/[a-z][a-z]_[A-Z][A-Z]/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/doc.git
 
 DOUBLETALK DRIVER
 M:	"James R. Van Zandt" <jrv@vanzandt.mv.com>
@@ -3146,7 +3163,7 @@ F:	include/drm/drm_panel.h
 F:	Documentation/devicetree/bindings/panel/
 
 INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets)
-M:	Daniel Vetter <daniel.vetter@ffwll.ch>
+M:	Daniel Vetter <daniel.vetter@intel.com>
 M:	Jani Nikula <jani.nikula@linux.intel.com>
 L:	intel-gfx@lists.freedesktop.org
 L:	dri-devel@lists.freedesktop.org
@@ -4232,6 +4249,16 @@ L:	linuxppc-dev@lists.ozlabs.org
 S:	Odd Fixes
 F:	drivers/tty/hvc/
 
+HACKRF MEDIA DRIVER
+M:	Antti Palosaari <crope@iki.fi>
+L:	linux-media@vger.kernel.org
+W:	http://linuxtv.org/
+W:	http://palosaari.fi/linux/
+Q:	http://patchwork.linuxtv.org/project/linux-media/list/
+T:	git git://linuxtv.org/anttip/media_tree.git
+S:	Maintained
+F:	drivers/media/usb/hackrf/
+
 HARDWARE MONITORING
 M:	Jean Delvare <jdelvare@suse.de>
 M:	Guenter Roeck <linux@roeck-us.net>
@@ -4275,9 +4302,8 @@ S:	Maintained
 F:	drivers/media/dvb-frontends/hd29l2*
 
 HEWLETT-PACKARD SMART2 RAID DRIVER
-M:	Chirag Kantharia <chirag.kantharia@hp.com>
 L:	iss_storagedev@hp.com
-S:	Maintained
+S:	Orphan
 F:	Documentation/blockdev/cpqarray.txt
 F:	drivers/block/cpqarray.*
 
@@ -5044,6 +5070,7 @@ L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
 T:	git git://git.infradead.org/users/jcooper/linux.git irqchip/core
+F:	Documentation/devicetree/bindings/interrupt-controller/
 F:	drivers/irqchip/
 
 IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY)
@@ -5129,7 +5156,7 @@ W:	http://palosaari.fi/linux/
 Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 T:	git git://linuxtv.org/anttip/media_tree.git
 S:	Maintained
-F:	drivers/media/tuners/tuner_it913x*
+F:	drivers/media/tuners/it913x*
 
 IVTV VIDEO4LINUX DRIVER
 M:	Andy Walls <awalls@md.metrocast.net>
@@ -5277,6 +5304,13 @@ F:	include/linux/lockd/
 F:	include/linux/sunrpc/
 F:	include/uapi/linux/sunrpc/
 
+KERNEL SELFTEST FRAMEWORK
+M:	Shuah Khan <shuahkh@osg.samsung.com>
+L:	linux-api@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/shuah/linux-kselftest
+S:	Maintained
+F:	tools/testing/selftests
+
 KERNEL VIRTUAL MACHINE (KVM)
 M:	Gleb Natapov <gleb@kernel.org>
 M:	Paolo Bonzini <pbonzini@redhat.com>
@@ -5657,8 +5691,8 @@ M:	Ingo Molnar <mingo@redhat.com>
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/locking
 S:	Maintained
-F:	Documentation/lockdep*.txt
-F:	Documentation/lockstat.txt
+F:	Documentation/locking/lockdep*.txt
+F:	Documentation/locking/lockstat.txt
 F:	include/linux/lockdep.h
 F:	kernel/locking/
 
@@ -5723,11 +5757,8 @@ T:	git git://github.com/linux-test-project/ltp.git
 S:	Maintained
 
 M32R ARCHITECTURE
-M:	Hirokazu Takata <takata@linux-m32r.org>
-L:	linux-m32r@ml.linux-m32r.org (moderated for non-subscribers)
-L:	linux-m32r-ja@ml.linux-m32r.org (in Japanese)
 W:	http://www.linux-m32r.org/
-S:	Maintained
+S:	Orphan
 F:	arch/m32r/
 
 M68K ARCHITECTURE
@@ -5961,6 +5992,7 @@ L:	linux-mtd@lists.infradead.org
 W:	http://www.linux-mtd.infradead.org/
 Q:	http://patchwork.ozlabs.org/project/linux-mtd/list/
 T:	git git://git.infradead.org/linux-mtd.git
+T:	git git://git.infradead.org/l2-mtd.git
 S:	Maintained
 F:	drivers/mtd/
 F:	include/linux/mtd/
@@ -5978,6 +6010,15 @@ S:	Supported
 F:	drivers/mcb/
 F:	include/linux/mcb.h
 
+MEN F21BMC (Board Management Controller)
+M:	Andreas Werner <andreas.werner@men.de>
+S:	Supported
+F:	drivers/mfd/menf21bmc.c
+F:	drivers/watchdog/menf21bmc_wdt.c
+F:	drivers/leds/leds-menf21bmc.c
+F:	drivers/hwmon/menf21bmc_hwmon.c
+F:	Documentation/hwmon/menf21bmc
+
 METAG ARCHITECTURE
 M:	James Hogan <james.hogan@imgtec.com>
 L:	linux-metag@vger.kernel.org
@@ -6604,10 +6645,9 @@ S:	Maintained
 F:	drivers/mmc/host/omap.c
 
 OMAP HS MMC SUPPORT
-M:	Balaji T K <balajitk@ti.com>
 L:	linux-mmc@vger.kernel.org
 L:	linux-omap@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/mmc/host/omap_hsmmc.c
 
 OMAP RANDOM NUMBER GENERATOR SUPPORT
@@ -6937,6 +6977,14 @@ F:	include/linux/pci*
 F:	arch/x86/pci/
 F:	arch/x86/kernel/quirks.c
 
+PCI DRIVER FOR APPLIEDMICRO XGENE
+M:	Tanmay Inamdar <tinamdar@apm.com>
+L:	linux-pci@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/pci/xgene-pci.txt
+F:	drivers/pci/host/pci-xgene.c
+
 PCI DRIVER FOR IMX6
 M:	Richard Zhu <r65037@freescale.com>
 M:	Lucas Stach <l.stach@pengutronix.de>
@@ -6945,6 +6993,13 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/pci/host/*imx6*
 
+PCI DRIVER FOR TI KEYSTONE
+M:	Murali Karicheri <m-karicheri2@ti.com>
+L:	linux-pci@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	drivers/pci/host/*keystone*
+
 PCI DRIVER FOR MVEBU (Marvell Armada 370 and Armada XP SOC support)
 M:	Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
 M:	Jason Cooper <jason@lakedaemon.net>
@@ -7347,6 +7402,14 @@ T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/usb/pwc/*
 
+PWM FAN DRIVER
+M:	Kamil Debski <k.debski@samsung.com>
+L:	lm-sensors@lm-sensors.org
+S:	Supported
+F:	Documentation/devicetree/bindings/hwmon/pwm-fan.txt
+F:	Documentation/hwmon/pwm-fan
+F:	drivers/hwmon/pwm-fan.c
+
 PWM SUBSYSTEM
 M:	Thierry Reding <thierry.reding@gmail.com>
 L:	linux-pwm@vger.kernel.org
@@ -7929,7 +7992,6 @@ S:	Supported
 F:	drivers/mfd/sec*.c
 F:	drivers/regulator/s2m*.c
 F:	drivers/regulator/s5m*.c
-F:	drivers/rtc/rtc-sec.c
 F:	include/linux/mfd/samsung/
 
 SAMSUNG S5P/EXYNOS4 SOC SERIES CAMERA SUBSYSTEM DRIVERS
@@ -8000,7 +8062,7 @@ SYNOPSYS DESIGNWARE DMAC DRIVER
 M:	Viresh Kumar <viresh.linux@gmail.com>
 M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 S:	Maintained
-F:	include/linux/dw_dmac.h
+F:	include/linux/platform_data/dma-dw.h
 F:	drivers/dma/dw/
 
 SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
@@ -8153,6 +8215,8 @@ F:	drivers/mmc/host/sdhci-pltfm.[ch]
 
 SECURE COMPUTING
 M:	Kees Cook <keescook@chromium.org>
+R:	Andy Lutomirski <luto@amacapital.net>
+R:	Will Drewry <wad@chromium.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git seccomp
 S:	Supported
 F:	kernel/seccomp.c
@@ -8473,11 +8537,11 @@ S:	Maintained
 F:	Documentation/security/Smack.txt
 F:	security/smack/
 
-SMARTREFLEX DRIVERS FOR ADAPTIVE VOLTAGE SCALING (AVS)
+DRIVERS FOR ADAPTIVE VOLTAGE SCALING (AVS)
 M:	Kevin Hilman <khilman@kernel.org>
 M:	Nishanth Menon <nm@ti.com>
 S:	Maintained
-F:	drivers/power/avs/smartreflex.c
+F:	drivers/power/avs/
 F:	include/linux/power/smartreflex.h
 L:	linux-pm@vger.kernel.org
 
@@ -8647,6 +8711,14 @@ F:	include/sound/dmaengine_pcm.h
 F:	sound/core/pcm_dmaengine.c
 F:	sound/soc/soc-generic-dmaengine-pcm.c
 
+SP2 MEDIA DRIVER
+M:	Olli Salonen <olli.salonen@iki.fi>
+L:	linux-media@vger.kernel.org
+W:	http://linuxtv.org/
+Q:	http://patchwork.linuxtv.org/project/linux-media/list/
+S:	Maintained
+F:	drivers/media/dvb-frontends/sp2*
+
 SPARC + UltraSPARC (sparc/sparc64)
 M:	"David S. Miller" <davem@davemloft.net>
 L:	sparclinux@vger.kernel.org
@@ -9350,6 +9422,14 @@ T:	git git://linuxtv.org/media_tree.git
 S:	Odd fixes
 F:	drivers/media/usb/tm6000/
 
+TW68 VIDEO4LINUX DRIVER
+M:	Hans Verkuil <hverkuil@xs4all.nl>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+W:	http://linuxtv.org
+S:	Odd Fixes
+F:	drivers/media/pci/tw68/
+
 TPM DEVICE DRIVER
 M:	Peter Huewe <peterhuewe@gmx.de>
 M:	Ashley Lai <ashley@ashleylai.com>
@@ -9371,6 +9451,7 @@ F:	include/*/ftrace.h
 F:	include/linux/trace*.h
 F:	include/trace/
 F:	kernel/trace/
+F:	tools/testing/selftests/ftrace/
 
 TRIVIAL PATCHES
 M:	Jiri Kosina <trivial@kernel.org>
@@ -10218,6 +10299,15 @@ S:	Supported
 F:	drivers/block/xen-blkback/*
 F:	drivers/block/xen*
 
+XEN PVSCSI DRIVERS
+M:	Juergen Gross <jgross@suse.com>
+L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
+L:	linux-scsi@vger.kernel.org
+S:	Supported
+F:	drivers/scsi/xen-scsifront.c
+F:	drivers/xen/xen-scsiback.c
+F:	include/xen/interface/io/vscsiif.h
+
 XEN SWIOTLB SUBSYSTEM
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
 L:	xen-devel@lists.xenproject.org (moderated for non-subscribers)
@@ -10242,10 +10332,6 @@ M:	John Linn <John.Linn@xilinx.com>
 S:	Maintained
 F:	drivers/net/ethernet/xilinx/xilinx_axienet*
 
-XILINX SYSTEMACE DRIVER
-S:	Orphan
-F:	drivers/block/xsysace.c
-
 XILINX UARTLITE SERIAL DRIVER
 M:	Peter Korsgaard <jacmet@sunsite.dk>
 L:	linux-serial@vger.kernel.org
diff --git a/Makefile b/Makefile
index 6127ca66ed98..36a77a3d156c 100644
--- a/Makefile
+++ b/Makefile
@@ -10,11 +10,9 @@ NAME = Shuffling Zombie Juror
 # Comments in this file are targeted only to the developer, do not
 # expect to learn how to build the kernel reading this file.
 
-# Do not:
-# o  use make's built-in rules and variables
-#    (this increases performance and avoids hard-to-debug behaviour);
-# o  print "Entering directory ...";
-MAKEFLAGS += -rR --no-print-directory
+# Do not use make's built-in rules and variables
+# (this increases performance and avoids hard-to-debug behaviour);
+MAKEFLAGS += -rR
 
 # Avoid funny character set dependencies
 unexport LC_ALL
@@ -97,34 +95,6 @@ endif
 
 export quiet Q KBUILD_VERBOSE
 
-# Call a source code checker (by default, "sparse") as part of the
-# C compilation.
-#
-# Use 'make C=1' to enable checking of only re-compiled files.
-# Use 'make C=2' to enable checking of *all* source files, regardless
-# of whether they are re-compiled or not.
-#
-# See the file "Documentation/sparse.txt" for more details, including
-# where to get the "sparse" utility.
-
-ifeq ("$(origin C)", "command line")
-  KBUILD_CHECKSRC = $(C)
-endif
-ifndef KBUILD_CHECKSRC
-  KBUILD_CHECKSRC = 0
-endif
-
-# Use make M=dir to specify directory of external module to build
-# Old syntax make ... SUBDIRS=$PWD is still supported
-# Setting the environment variable KBUILD_EXTMOD take precedence
-ifdef SUBDIRS
-  KBUILD_EXTMOD ?= $(SUBDIRS)
-endif
-
-ifeq ("$(origin M)", "command line")
-  KBUILD_EXTMOD := $(M)
-endif
-
 # kbuild supports saving output files in a separate directory.
 # To locate output files in a separate directory two syntaxes are supported.
 # In both cases the working directory must be the root of the kernel src.
@@ -140,7 +110,6 @@ endif
 # The O= assignment takes precedence over the KBUILD_OUTPUT environment
 # variable.
 
-
 # KBUILD_SRC is set on invocation of make in OBJ directory
 # KBUILD_SRC is not intended to be used by the regular user (for now)
 ifeq ($(KBUILD_SRC),)
@@ -172,17 +141,9 @@ PHONY += $(MAKECMDGOALS) sub-make
 $(filter-out _all sub-make $(CURDIR)/Makefile, $(MAKECMDGOALS)) _all: sub-make
 	@:
 
-# Fake the "Entering directory" message once, so that IDEs/editors are
-# able to understand relative filenames.
-       echodir := @echo
- quiet_echodir := @echo
-silent_echodir := @:
 sub-make: FORCE
-	$($(quiet)echodir) "make[1]: Entering directory \`$(KBUILD_OUTPUT)'"
-	$(if $(KBUILD_VERBOSE:1=),@)$(MAKE) -C $(KBUILD_OUTPUT) \
-	KBUILD_SRC=$(CURDIR) \
-	KBUILD_EXTMOD="$(KBUILD_EXTMOD)" -f $(CURDIR)/Makefile \
-	$(filter-out _all sub-make,$(MAKECMDGOALS))
+	$(Q)$(MAKE) -C $(KBUILD_OUTPUT) KBUILD_SRC=$(CURDIR) \
+	-f $(CURDIR)/Makefile $(filter-out _all sub-make,$(MAKECMDGOALS))
 
 # Leave processing to above invocation of make
 skip-makefile := 1
@@ -192,6 +153,39 @@ endif # ifeq ($(KBUILD_SRC),)
 # We process the rest of the Makefile if this is the final invocation of make
 ifeq ($(skip-makefile),)
 
+# Do not print "Entering directory ...",
+# but we want to display it when entering to the output directory
+# so that IDEs/editors are able to understand relative filenames.
+MAKEFLAGS += --no-print-directory
+
+# Call a source code checker (by default, "sparse") as part of the
+# C compilation.
+#
+# Use 'make C=1' to enable checking of only re-compiled files.
+# Use 'make C=2' to enable checking of *all* source files, regardless
+# of whether they are re-compiled or not.
+#
+# See the file "Documentation/sparse.txt" for more details, including
+# where to get the "sparse" utility.
+
+ifeq ("$(origin C)", "command line")
+  KBUILD_CHECKSRC = $(C)
+endif
+ifndef KBUILD_CHECKSRC
+  KBUILD_CHECKSRC = 0
+endif
+
+# Use make M=dir to specify directory of external module to build
+# Old syntax make ... SUBDIRS=$PWD is still supported
+# Setting the environment variable KBUILD_EXTMOD take precedence
+ifdef SUBDIRS
+  KBUILD_EXTMOD ?= $(SUBDIRS)
+endif
+
+ifeq ("$(origin M)", "command line")
+  KBUILD_EXTMOD := $(M)
+endif
+
 # If building an external module we do not care about the all: rule
 # but instead _all depend on modules
 PHONY += all
@@ -889,9 +883,7 @@ vmlinux-dirs	:= $(patsubst %/,%,$(filter %/, $(init-y) $(init-m) \
 		     $(net-y) $(net-m) $(libs-y) $(libs-m)))
 
 vmlinux-alldirs	:= $(sort $(vmlinux-dirs) $(patsubst %/,%,$(filter %/, \
-		     $(init-n) $(init-) \
-		     $(core-n) $(core-) $(drivers-n) $(drivers-) \
-		     $(net-n)  $(net-)  $(libs-n)    $(libs-))))
+		     $(init-) $(core-) $(drivers-) $(net-) $(libs-))))
 
 init-y		:= $(patsubst %/, %/built-in.o, $(init-y))
 core-y		:= $(patsubst %/, %/built-in.o, $(core-y))
@@ -1591,7 +1583,7 @@ endif
 # Shorthand for $(Q)$(MAKE) -f scripts/Makefile.clean obj=dir
 # Usage:
 # $(Q)$(MAKE) $(clean)=dir
-clean := -f $(if $(KBUILD_SRC),$(srctree)/)scripts/Makefile.clean obj
+clean := -f $(srctree)/scripts/Makefile.clean obj
 
 endif	# skip-makefile
 
diff --git a/arch/Kconfig b/arch/Kconfig
index 0eae9df35b88..05d7a8a458d5 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -323,6 +323,17 @@ config HAVE_ARCH_SECCOMP_FILTER
 	    results in the system call being skipped immediately.
 	  - seccomp syscall wired up
 
+	  For best performance, an arch should use seccomp_phase1 and
+	  seccomp_phase2 directly.  It should call seccomp_phase1 for all
+	  syscalls if TIF_SECCOMP is set, but seccomp_phase1 does not
+	  need to be called from a ptrace-safe context.  It must then
+	  call seccomp_phase2 if seccomp_phase1 returns anything other
+	  than SECCOMP_PHASE1_OK or SECCOMP_PHASE1_SKIP.
+
+	  As an additional optimization, an arch may provide seccomp_data
+	  directly to seccomp_phase1; this avoids multiple calls
+	  to the syscall_xyz helpers for every syscall.
+
 config SECCOMP_FILTER
 	def_bool y
 	depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index e858aa0ad8af..25b49725df07 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -4,7 +4,9 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
+generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index ed60a1ee1ed3..8f8eafbedd7c 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -17,8 +17,8 @@
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 
 #define atomic_set(v,i)		((v)->counter = (i))
 #define atomic64_set(v,i)	((v)->counter = (i))
@@ -29,145 +29,92 @@
  * branch back to restart the operation.
  */
 
-static __inline__ void atomic_add(int i, atomic_t * v)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"1:	ldl_l %0,%1\n"
-	"	addl %0,%2,%0\n"
-	"	stl_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter)
-	:"Ir" (i), "m" (v->counter));
-}
-
-static __inline__ void atomic64_add(long i, atomic64_t * v)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"1:	ldq_l %0,%1\n"
-	"	addq %0,%2,%0\n"
-	"	stq_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter)
-	:"Ir" (i), "m" (v->counter));
-}
-
-static __inline__ void atomic_sub(int i, atomic_t * v)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"1:	ldl_l %0,%1\n"
-	"	subl %0,%2,%0\n"
-	"	stl_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter)
-	:"Ir" (i), "m" (v->counter));
+#define ATOMIC_OP(op)							\
+static __inline__ void atomic_##op(int i, atomic_t * v)			\
+{									\
+	unsigned long temp;						\
+	__asm__ __volatile__(						\
+	"1:	ldl_l %0,%1\n"						\
+	"	" #op "l %0,%2,%0\n"					\
+	"	stl_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter)				\
+	:"Ir" (i), "m" (v->counter));					\
+}									\
+
+#define ATOMIC_OP_RETURN(op)						\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	long temp, result;						\
+	smp_mb();							\
+	__asm__ __volatile__(						\
+	"1:	ldl_l %0,%1\n"						\
+	"	" #op "l %0,%3,%2\n"					\
+	"	" #op "l %0,%3,%0\n"					\
+	"	stl_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
+	:"Ir" (i), "m" (v->counter) : "memory");			\
+	smp_mb();							\
+	return result;							\
 }
 
-static __inline__ void atomic64_sub(long i, atomic64_t * v)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"1:	ldq_l %0,%1\n"
-	"	subq %0,%2,%0\n"
-	"	stq_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter)
-	:"Ir" (i), "m" (v->counter));
-}
-
-
-/*
- * Same as above, but return the result value
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	long temp, result;
-	smp_mb();
-	__asm__ __volatile__(
-	"1:	ldl_l %0,%1\n"
-	"	addl %0,%3,%2\n"
-	"	addl %0,%3,%0\n"
-	"	stl_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter), "=&r" (result)
-	:"Ir" (i), "m" (v->counter) : "memory");
-	smp_mb();
-	return result;
+#define ATOMIC64_OP(op)							\
+static __inline__ void atomic64_##op(long i, atomic64_t * v)		\
+{									\
+	unsigned long temp;						\
+	__asm__ __volatile__(						\
+	"1:	ldq_l %0,%1\n"						\
+	"	" #op "q %0,%2,%0\n"					\
+	"	stq_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter)				\
+	:"Ir" (i), "m" (v->counter));					\
+}									\
+
+#define ATOMIC64_OP_RETURN(op)						\
+static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	\
+{									\
+	long temp, result;						\
+	smp_mb();							\
+	__asm__ __volatile__(						\
+	"1:	ldq_l %0,%1\n"						\
+	"	" #op "q %0,%3,%2\n"					\
+	"	" #op "q %0,%3,%0\n"					\
+	"	stq_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
+	:"Ir" (i), "m" (v->counter) : "memory");			\
+	smp_mb();							\
+	return result;							\
 }
 
-static __inline__ long atomic64_add_return(long i, atomic64_t * v)
-{
-	long temp, result;
-	smp_mb();
-	__asm__ __volatile__(
-	"1:	ldq_l %0,%1\n"
-	"	addq %0,%3,%2\n"
-	"	addq %0,%3,%0\n"
-	"	stq_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter), "=&r" (result)
-	:"Ir" (i), "m" (v->counter) : "memory");
-	smp_mb();
-	return result;
-}
+#define ATOMIC_OPS(opg)							\
+	ATOMIC_OP(opg)							\
+	ATOMIC_OP_RETURN(opg)						\
+	ATOMIC64_OP(opg)						\
+	ATOMIC64_OP_RETURN(opg)
 
-static __inline__ long atomic_sub_return(int i, atomic_t * v)
-{
-	long temp, result;
-	smp_mb();
-	__asm__ __volatile__(
-	"1:	ldl_l %0,%1\n"
-	"	subl %0,%3,%2\n"
-	"	subl %0,%3,%0\n"
-	"	stl_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter), "=&r" (result)
-	:"Ir" (i), "m" (v->counter) : "memory");
-	smp_mb();
-	return result;
-}
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
 
-static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
-{
-	long temp, result;
-	smp_mb();
-	__asm__ __volatile__(
-	"1:	ldq_l %0,%1\n"
-	"	subq %0,%3,%2\n"
-	"	subq %0,%3,%0\n"
-	"	stq_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter), "=&r" (result)
-	:"Ir" (i), "m" (v->counter) : "memory");
-	smp_mb();
-	return result;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 #define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
diff --git a/arch/alpha/include/asm/sections.h b/arch/alpha/include/asm/sections.h
deleted file mode 100644
index 43b40edd6e44..000000000000
--- a/arch/alpha/include/asm/sections.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _ALPHA_SECTIONS_H
-#define _ALPHA_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#endif
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 1402fcc11c2c..f9c732e18284 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -446,7 +446,8 @@ struct procfs_args {
  * unhappy with OSF UFS. [CHECKME]
  */
 static int
-osf_ufs_mount(const char *dirname, struct ufs_args __user *args, int flags)
+osf_ufs_mount(const char __user *dirname,
+	      struct ufs_args __user *args, int flags)
 {
 	int retval;
 	struct cdfs_args tmp;
@@ -466,7 +467,8 @@ osf_ufs_mount(const char *dirname, struct ufs_args __user *args, int flags)
 }
 
 static int
-osf_cdfs_mount(const char *dirname, struct cdfs_args __user *args, int flags)
+osf_cdfs_mount(const char __user *dirname,
+	       struct cdfs_args __user *args, int flags)
 {
 	int retval;
 	struct cdfs_args tmp;
@@ -486,7 +488,8 @@ osf_cdfs_mount(const char *dirname, struct cdfs_args __user *args, int flags)
 }
 
 static int
-osf_procfs_mount(const char *dirname, struct procfs_args __user *args, int flags)
+osf_procfs_mount(const char __user *dirname,
+		 struct procfs_args __user *args, int flags)
 {
 	struct procfs_args tmp;
 
@@ -500,28 +503,22 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, const char __user *, path,
 		int, flag, void __user *, data)
 {
 	int retval;
-	struct filename *name;
 
-	name = getname(path);
-	retval = PTR_ERR(name);
-	if (IS_ERR(name))
-		goto out;
 	switch (typenr) {
 	case 1:
-		retval = osf_ufs_mount(name->name, data, flag);
+		retval = osf_ufs_mount(path, data, flag);
 		break;
 	case 6:
-		retval = osf_cdfs_mount(name->name, data, flag);
+		retval = osf_cdfs_mount(path, data, flag);
 		break;
 	case 9:
-		retval = osf_procfs_mount(name->name, data, flag);
+		retval = osf_procfs_mount(path, data, flag);
 		break;
 	default:
 		retval = -EINVAL;
 		printk("osf_mount(%ld, %x)\n", typenr, flag);
 	}
-	putname(name);
- out:
+
 	return retval;
 }
 
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index c52e7f0ee5f6..5c218aa3f3df 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -431,7 +431,7 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc)
  */
 static int alpha_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int n0;
 	int ret;
@@ -483,7 +483,7 @@ static int alpha_pmu_add(struct perf_event *event, int flags)
  */
 static void alpha_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long irq_flags;
 	int j;
@@ -531,7 +531,7 @@ static void alpha_pmu_read(struct perf_event *event)
 static void alpha_pmu_stop(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!(hwc->state & PERF_HES_STOPPED)) {
 		cpuc->idx_mask &= ~(1UL<<hwc->idx);
@@ -551,7 +551,7 @@ static void alpha_pmu_stop(struct perf_event *event, int flags)
 static void alpha_pmu_start(struct perf_event *event, int flags)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
 		return;
@@ -724,7 +724,7 @@ static int alpha_pmu_event_init(struct perf_event *event)
  */
 static void alpha_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->enabled)
 		return;
@@ -750,7 +750,7 @@ static void alpha_pmu_enable(struct pmu *pmu)
 
 static void alpha_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!cpuc->enabled)
 		return;
@@ -814,8 +814,8 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	struct hw_perf_event *hwc;
 	int idx, j;
 
-	__get_cpu_var(irq_pmi_count)++;
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	__this_cpu_inc(irq_pmi_count);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/* Completely counting through the PMC's period to trigger a new PMC
 	 * overflow interrupt while in this interrupt routine is utterly
diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c
index ee39cee8064c..643a9dcdf093 100644
--- a/arch/alpha/kernel/time.c
+++ b/arch/alpha/kernel/time.c
@@ -56,9 +56,9 @@ unsigned long est_cycle_freq;
 
 DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_irq_work_pending_flag()  __get_cpu_var(irq_work_pending) = 1
-#define test_irq_work_pending()      __get_cpu_var(irq_work_pending)
-#define clear_irq_work_pending()     __get_cpu_var(irq_work_pending) = 0
+#define set_irq_work_pending_flag()  __this_cpu_write(irq_work_pending, 1)
+#define test_irq_work_pending()      __this_cpu_read(irq_work_pending)
+#define clear_irq_work_pending()     __this_cpu_write(irq_work_pending, 0)
 
 void arch_irq_work_raise(void)
 {
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index e76fd79f32b0..b8fffc1a2ac2 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -18,6 +18,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
 generic-y += local.h
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 83f03ca6caf6..173f303a868f 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -25,79 +25,36 @@
 
 #define atomic_set(v, i) (((v)->counter) = (i))
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	unsigned int temp;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	add     %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */
-	: "r"(&v->counter), "ir"(i)
-	: "cc");
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	unsigned int temp;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	sub     %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(temp)
-	: "r"(&v->counter), "ir"(i)
-	: "cc");
-}
-
-/* add and also return the new value */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned int temp;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	add     %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(temp)
-	: "r"(&v->counter), "ir"(i)
-	: "cc");
-
-	return temp;
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned int temp;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	sub     %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(temp)
-	: "r"(&v->counter), "ir"(i)
-	: "cc");
-
-	return temp;
-}
-
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
-{
-	unsigned int temp;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	bic     %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(temp)
-	: "r"(addr), "ir"(mask)
-	: "cc");
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned int temp;						\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock   %0, [%1]	\n"				\
+	"	" #asm_op " %0, %0, %2	\n"				\
+	"	scond   %0, [%1]	\n"				\
+	"	bnz     1b		\n"				\
+	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */	\
+	: "r"(&v->counter), "ir"(i)					\
+	: "cc");							\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned int temp;						\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock   %0, [%1]	\n"				\
+	"	" #asm_op " %0, %0, %2	\n"				\
+	"	scond   %0, [%1]	\n"				\
+	"	bnz     1b		\n"				\
+	: "=&r"(temp)							\
+	: "r"(&v->counter), "ir"(i)					\
+	: "cc");							\
+									\
+	return temp;							\
 }
 
 #else	/* !CONFIG_ARC_HAS_LLSC */
@@ -126,6 +83,7 @@ static inline void atomic_set(atomic_t *v, int i)
 	v->counter = i;
 	atomic_ops_unlock(flags);
 }
+
 #endif
 
 /*
@@ -133,62 +91,46 @@ static inline void atomic_set(atomic_t *v, int i)
  * Locking would change to irq-disabling only (UP) and spinlocks (SMP)
  */
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	unsigned long flags;
-
-	atomic_ops_lock(flags);
-	v->counter += i;
-	atomic_ops_unlock(flags);
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	atomic_ops_lock(flags);						\
+	v->counter c_op i;						\
+	atomic_ops_unlock(flags);					\
 }
 
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	unsigned long flags;
-
-	atomic_ops_lock(flags);
-	v->counter -= i;
-	atomic_ops_unlock(flags);
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	unsigned long temp;						\
+									\
+	atomic_ops_lock(flags);						\
+	temp = v->counter;						\
+	temp c_op i;							\
+	v->counter = temp;						\
+	atomic_ops_unlock(flags);					\
+									\
+	return temp;							\
 }
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	unsigned long temp;
-
-	atomic_ops_lock(flags);
-	temp = v->counter;
-	temp += i;
-	v->counter = temp;
-	atomic_ops_unlock(flags);
-
-	return temp;
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	unsigned long temp;
-
-	atomic_ops_lock(flags);
-	temp = v->counter;
-	temp -= i;
-	v->counter = temp;
-	atomic_ops_unlock(flags);
+#endif /* !CONFIG_ARC_HAS_LLSC */
 
-	return temp;
-}
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_OP_RETURN(op, c_op, asm_op)
 
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
-{
-	unsigned long flags;
+ATOMIC_OPS(add, +=, add)
+ATOMIC_OPS(sub, -=, sub)
+ATOMIC_OP(and, &=, and)
 
-	atomic_ops_lock(flags);
-	*addr &= ~mask;
-	atomic_ops_unlock(flags);
-}
+#define atomic_clear_mask(mask, v) atomic_and(~(mask), (v))
 
-#endif /* !CONFIG_ARC_HAS_LLSC */
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 /**
  * __atomic_add_unless - add unless the number is a given value
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 82dfdeac3595..89c4b5ccc68d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -14,6 +14,7 @@ config ARM
 	select CLONE_BACKWARDS
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select GENERIC_ALLOCATOR
 	select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
 	select GENERIC_IDLE_POLL_SETUP
@@ -24,6 +25,7 @@ config ARM
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
+	select HANDLE_DOMAIN_IRQ
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
@@ -60,6 +62,7 @@ config ARM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE)
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UID16
@@ -1658,6 +1661,10 @@ config ARCH_SELECT_MEMORY_MODEL
 config HAVE_ARCH_PFN_VALID
 	def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
 
+config HAVE_GENERIC_RCU_GUP
+	def_bool y
+	depends on ARM_LPAE
+
 config HIGHMEM
 	bool "High Memory Support"
 	depends on MMU
@@ -1772,7 +1779,7 @@ config XEN_DOM0
 	depends on XEN
 
 config XEN
-	bool "Xen guest support on ARM (EXPERIMENTAL)"
+	bool "Xen guest support on ARM"
 	depends on ARM && AEABI && OF
 	depends on CPU_V7 && !CPU_V6
 	depends on !GENERIC_ATOMIC64
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index dceb0441b1a6..034a94904d69 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -50,8 +50,6 @@ AS		+= -EL
 LD		+= -EL
 endif
 
-comma = ,
-
 # This selects which instruction set is used.
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index 1d52de6370d5..693a3275606f 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -132,6 +132,12 @@
 			reg = <0x10020000 0x4000>;
 		};
 
+		mipi_phy: video-phy@10020710 {
+			compatible = "samsung,s5pv210-mipi-video-phy";
+			reg = <0x10020710 8>;
+			#phy-cells = <1>;
+		};
+
 		pd_cam: cam-power-domain@10023C00 {
 			compatible = "samsung,exynos4210-pd";
 			reg = <0x10023C00 0x20>;
@@ -163,8 +169,14 @@
 			#clock-cells = <1>;
 		};
 
+		cmu_dmc: clock-controller@105C0000 {
+			compatible = "samsung,exynos3250-cmu-dmc";
+			reg = <0x105C0000 0x2000>;
+			#clock-cells = <1>;
+		};
+
 		rtc: rtc@10070000 {
-			compatible = "samsung,s3c6410-rtc";
+			compatible = "samsung,exynos3250-rtc";
 			reg = <0x10070000 0x100>;
 			interrupts = <0 73 0>, <0 74 0>;
 			status = "disabled";
@@ -216,6 +228,33 @@
 			interrupts = <0 240 0>;
 		};
 
+		fimd: fimd@11c00000 {
+			compatible = "samsung,exynos3250-fimd";
+			reg = <0x11c00000 0x30000>;
+			interrupt-names = "fifo", "vsync", "lcd_sys";
+			interrupts = <0 84 0>, <0 85 0>, <0 86 0>;
+			clocks = <&cmu CLK_SCLK_FIMD0>, <&cmu CLK_FIMD0>;
+			clock-names = "sclk_fimd", "fimd";
+			samsung,power-domain = <&pd_lcd0>;
+			samsung,sysreg = <&sys_reg>;
+			status = "disabled";
+		};
+
+		dsi_0: dsi@11C80000 {
+			compatible = "samsung,exynos3250-mipi-dsi";
+			reg = <0x11C80000 0x10000>;
+			interrupts = <0 83 0>;
+			samsung,phy-type = <0>;
+			samsung,power-domain = <&pd_lcd0>;
+			phys = <&mipi_phy 1>;
+			phy-names = "dsim";
+			clocks = <&cmu CLK_DSIM0>, <&cmu CLK_SCLK_MIPI0>;
+			clock-names = "bus_clk", "pll_clk";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			status = "disabled";
+		};
+
 		mshc_0: mshc@12510000 {
 			compatible = "samsung,exynos5250-dw-mshc";
 			reg = <0x12510000 0x1000>;
diff --git a/arch/arm/boot/dts/exynos5420-arndale-octa.dts b/arch/arm/boot/dts/exynos5420-arndale-octa.dts
index 70a559cf1a3d..4f2df61c1cfc 100644
--- a/arch/arm/boot/dts/exynos5420-arndale-octa.dts
+++ b/arch/arm/boot/dts/exynos5420-arndale-octa.dts
@@ -69,7 +69,8 @@
 		samsung,dw-mshc-ddr-timing = <1 2>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&sd2_clk &sd2_cmd &sd2_cd &sd2_bus4>;
-		vmmc-supply = <&ldo10_reg>;
+		vmmc-supply = <&ldo19_reg>;
+		vqmmc-supply = <&ldo13_reg>;
 		bus-width = <4>;
 		cap-sd-highspeed;
 	};
diff --git a/arch/arm/boot/dts/pxa27x.dtsi b/arch/arm/boot/dts/pxa27x.dtsi
index a70546945985..80fc5d7e9ef9 100644
--- a/arch/arm/boot/dts/pxa27x.dtsi
+++ b/arch/arm/boot/dts/pxa27x.dtsi
@@ -1,5 +1,6 @@
 /* The pxa3xx skeleton simply augments the 2xx version */
-/include/ "pxa2xx.dtsi"
+#include "pxa2xx.dtsi"
+#include "dt-bindings/clock/pxa2xx-clock.h"
 
 / {
 	model = "Marvell PXA27x familiy SoC";
@@ -35,4 +36,21 @@
 			#pwm-cells = <1>;
 		};
 	};
+
+	clocks {
+	       /*
+		* The muxing of external clocks/internal dividers for osc* clock
+		* sources has been hidden under the carpet by now.
+		*/
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges;
+
+		pxa2xx_clks: pxa2xx_clks@41300004 {
+			compatible = "marvell,pxa-clocks";
+			#clock-cells = <1>;
+			status = "okay";
+		};
+	};
+
 };
diff --git a/arch/arm/boot/dts/spear1310.dtsi b/arch/arm/boot/dts/spear1310.dtsi
index fa5f2bb5f106..9d342920695a 100644
--- a/arch/arm/boot/dts/spear1310.dtsi
+++ b/arch/arm/boot/dts/spear1310.dtsi
@@ -85,7 +85,8 @@
 
 		pcie0: pcie@b1000000 {
 			compatible = "st,spear1340-pcie", "snps,dw-pcie";
-			reg = <0xb1000000 0x4000>;
+			reg = <0xb1000000 0x4000>, <0x80000000 0x20000>;
+			reg-names = "dbi", "config";
 			interrupts = <0 68 0x4>;
 			interrupt-map-mask = <0 0 0 0>;
 			interrupt-map = <0x0 0 &gic 0 68 0x4>;
@@ -95,15 +96,15 @@
 			#address-cells = <3>;
 			#size-cells = <2>;
 			device_type = "pci";
-			ranges = <0x00000800 0 0x80000000 0x80000000 0 0x00020000   /* configuration space */
-				0x81000000 0 0	 0x80020000 0 0x00010000   /* downstream I/O */
+			ranges = <0x81000000 0 0	 0x80020000 0 0x00010000   /* downstream I/O */
 				0x82000000 0 0x80030000 0xc0030000 0 0x0ffd0000>; /* non-prefetchable memory */
 			status = "disabled";
 		};
 
 		pcie1: pcie@b1800000 {
 			compatible = "st,spear1340-pcie", "snps,dw-pcie";
-			reg = <0xb1800000 0x4000>;
+			reg = <0xb1800000 0x4000>, <0x90000000 0x20000>;
+			reg-names = "dbi", "config";
 			interrupts = <0 69 0x4>;
 			interrupt-map-mask = <0 0 0 0>;
 			interrupt-map = <0x0 0 &gic 0 69 0x4>;
@@ -113,15 +114,15 @@
 			#address-cells = <3>;
 			#size-cells = <2>;
 			device_type = "pci";
-			ranges = <0x00000800 0 0x90000000 0x90000000 0 0x00020000   /* configuration space */
-				0x81000000 0 0  0x90020000 0 0x00010000   /* downstream I/O */
+			ranges = <0x81000000 0 0  0x90020000 0 0x00010000   /* downstream I/O */
 				0x82000000 0 0x90030000 0x90030000 0 0x0ffd0000>; /* non-prefetchable memory */
 			status = "disabled";
 		};
 
 		pcie2: pcie@b4000000 {
 			compatible = "st,spear1340-pcie", "snps,dw-pcie";
-			reg = <0xb4000000 0x4000>;
+			reg = <0xb4000000 0x4000>, <0xc0000000 0x20000>;
+			reg-names = "dbi", "config";
 			interrupts = <0 70 0x4>;
 			interrupt-map-mask = <0 0 0 0>;
 			interrupt-map = <0x0 0 &gic 0 70 0x4>;
@@ -131,8 +132,7 @@
 			#address-cells = <3>;
 			#size-cells = <2>;
 			device_type = "pci";
-			ranges = <0x00000800 0 0xc0000000 0xc0000000 0 0x00020000   /* configuration space */
-				0x81000000 0 0	 0xc0020000 0 0x00010000   /* downstream I/O */
+			ranges = <0x81000000 0 0	 0xc0020000 0 0x00010000   /* downstream I/O */
 				0x82000000 0 0xc0030000 0xc0030000 0 0x0ffd0000>; /* non-prefetchable memory */
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi
index e71df0f2cb52..13e1aa33daa2 100644
--- a/arch/arm/boot/dts/spear1340.dtsi
+++ b/arch/arm/boot/dts/spear1340.dtsi
@@ -50,7 +50,8 @@
 
 		pcie0: pcie@b1000000 {
 			compatible = "st,spear1340-pcie", "snps,dw-pcie";
-			reg = <0xb1000000 0x4000>;
+			reg = <0xb1000000 0x4000>, <0x80000000 0x20000>;
+			reg-names = "dbi", "config";
 			interrupts = <0 68 0x4>;
 			interrupt-map-mask = <0 0 0 0>;
 			interrupt-map = <0x0 0 &gic 0 68 0x4>;
@@ -60,8 +61,7 @@
 			#address-cells = <3>;
 			#size-cells = <2>;
 			device_type = "pci";
-			ranges = <0x00000800 0 0x80000000 0x80000000 0 0x00020000   /* configuration space */
-				0x81000000 0 0	 0x80020000 0 0x00010000   /* downstream I/O */
+			ranges = <0x81000000 0 0	 0x80020000 0 0x00010000   /* downstream I/O */
 				0x82000000 0 0x80030000 0xc0030000 0 0x0ffd0000>; /* non-prefetchable memory */
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index d73a2287b37a..531272c0e526 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -287,7 +287,7 @@
 
 		mbus_clk: clk@01c2015c {
 			#clock-cells = <0>;
-			compatible = "allwinner,sun4i-a10-mod0-clk";
+			compatible = "allwinner,sun5i-a13-mbus-clk";
 			reg = <0x01c2015c 0x4>;
 			clocks = <&osc24M>, <&pll6 1>, <&pll5 1>;
 			clock-output-names = "mbus";
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index c4b5d7825b9f..b131068f4f35 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -285,7 +285,7 @@
 
 		mbus_clk: clk@01c2015c {
 			#clock-cells = <0>;
-			compatible = "allwinner,sun4i-a10-mod0-clk";
+			compatible = "allwinner,sun5i-a13-mbus-clk";
 			reg = <0x01c2015c 0x4>;
 			clocks = <&osc24M>, <&pll6 1>, <&pll5 1>;
 			clock-output-names = "mbus";
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index a96b99465069..82097c905c48 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -382,7 +382,7 @@
 
 		mbus_clk: clk@01c2015c {
 			#clock-cells = <0>;
-			compatible = "allwinner,sun4i-a10-mod0-clk";
+			compatible = "allwinner,sun5i-a13-mbus-clk";
 			reg = <0x01c2015c 0x4>;
 			clocks = <&osc24M>, <&pll6 2>, <&pll5 1>;
 			clock-output-names = "mbus";
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index a25c262326dc..322fd1519b09 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -38,6 +38,7 @@
 			compatible = "arm,cortex-a15";
 			reg = <0>;
 			cci-control-port = <&cci_control1>;
+			cpu-idle-states = <&CLUSTER_SLEEP_BIG>;
 		};
 
 		cpu1: cpu@1 {
@@ -45,6 +46,7 @@
 			compatible = "arm,cortex-a15";
 			reg = <1>;
 			cci-control-port = <&cci_control1>;
+			cpu-idle-states = <&CLUSTER_SLEEP_BIG>;
 		};
 
 		cpu2: cpu@2 {
@@ -52,6 +54,7 @@
 			compatible = "arm,cortex-a7";
 			reg = <0x100>;
 			cci-control-port = <&cci_control2>;
+			cpu-idle-states = <&CLUSTER_SLEEP_LITTLE>;
 		};
 
 		cpu3: cpu@3 {
@@ -59,6 +62,7 @@
 			compatible = "arm,cortex-a7";
 			reg = <0x101>;
 			cci-control-port = <&cci_control2>;
+			cpu-idle-states = <&CLUSTER_SLEEP_LITTLE>;
 		};
 
 		cpu4: cpu@4 {
@@ -66,6 +70,25 @@
 			compatible = "arm,cortex-a7";
 			reg = <0x102>;
 			cci-control-port = <&cci_control2>;
+			cpu-idle-states = <&CLUSTER_SLEEP_LITTLE>;
+		};
+
+		idle-states {
+			CLUSTER_SLEEP_BIG: cluster-sleep-big {
+				compatible = "arm,idle-state";
+				local-timer-stop;
+				entry-latency-us = <1000>;
+				exit-latency-us = <700>;
+				min-residency-us = <2000>;
+			};
+
+			CLUSTER_SLEEP_LITTLE: cluster-sleep-little {
+				compatible = "arm,idle-state";
+				local-timer-stop;
+				entry-latency-us = <1000>;
+				exit-latency-us = <500>;
+				min-residency-us = <2500>;
+			};
 		};
 	};
 
diff --git a/arch/arm/common/scoop.c b/arch/arm/common/scoop.c
index a20fa80776d3..45f4c21e393c 100644
--- a/arch/arm/common/scoop.c
+++ b/arch/arm/common/scoop.c
@@ -243,18 +243,12 @@ err_ioremap:
 static int scoop_remove(struct platform_device *pdev)
 {
 	struct scoop_dev *sdev = platform_get_drvdata(pdev);
-	int ret;
 
 	if (!sdev)
 		return -EINVAL;
 
-	if (sdev->gpio.base != -1) {
-		ret = gpiochip_remove(&sdev->gpio);
-		if (ret) {
-			dev_err(&pdev->dev, "Can't remove gpio chip: %d\n", ret);
-			return ret;
-		}
-	}
+	if (sdev->gpio.base != -1)
+		gpiochip_remove(&sdev->gpio);
 
 	platform_set_drvdata(pdev, NULL);
 	iounmap(sdev->base);
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 0704e0cf5571..92793ba69c40 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -99,31 +99,6 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 	asm volatile("mcr p15, 0, %0, c14, c1, 0" : : "r" (cntkctl));
 }
 
-static inline void arch_counter_set_user_access(void)
-{
-	u32 cntkctl = arch_timer_get_cntkctl();
-
-	/* Disable user access to both physical/virtual counters/timers */
-	/* Also disable virtual event stream */
-	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
-			| ARCH_TIMER_USR_VT_ACCESS_EN
-			| ARCH_TIMER_VIRT_EVT_EN
-			| ARCH_TIMER_USR_VCT_ACCESS_EN
-			| ARCH_TIMER_USR_PCT_ACCESS_EN);
-	arch_timer_set_cntkctl(cntkctl);
-}
-
-static inline void arch_timer_evtstrm_enable(int divider)
-{
-	u32 cntkctl = arch_timer_get_cntkctl();
-	cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK;
-	/* Set the divider and enable virtual event stream */
-	cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
-			| ARCH_TIMER_VIRT_EVT_EN;
-	arch_timer_set_cntkctl(cntkctl);
-	elf_hwcap |= HWCAP_EVTSTRM;
-}
-
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 3040359094d9..e22c11970b7b 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -27,7 +27,7 @@
  * strex/ldrex monitor on some implementations. The reason we can use it for
  * atomic_set() is the clrex or dummy strex done on every exception return.
  */
-#define atomic_read(v)	(*(volatile int *)&(v)->counter)
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
 #define atomic_set(v,i)	(((v)->counter) = (i))
 
 #if __LINUX_ARM_ARCH__ >= 6
@@ -37,84 +37,47 @@
  * store exclusive to ensure that these are atomic.  We may loop
  * to ensure that the update happens.
  */
-static inline void atomic_add(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
-
-	prefetchw(&v->counter);
-	__asm__ __volatile__("@ atomic_add\n"
-"1:	ldrex	%0, [%3]\n"
-"	add	%0, %0, %4\n"
-"	strex	%1, %0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "Ir" (i)
-	: "cc");
-}
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
-
-	smp_mb();
-	prefetchw(&v->counter);
-
-	__asm__ __volatile__("@ atomic_add_return\n"
-"1:	ldrex	%0, [%3]\n"
-"	add	%0, %0, %4\n"
-"	strex	%1, %0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "Ir" (i)
-	: "cc");
-
-	smp_mb();
-
-	return result;
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
-
-	prefetchw(&v->counter);
-	__asm__ __volatile__("@ atomic_sub\n"
-"1:	ldrex	%0, [%3]\n"
-"	sub	%0, %0, %4\n"
-"	strex	%1, %0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "Ir" (i)
-	: "cc");
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
-
-	smp_mb();
-	prefetchw(&v->counter);
-
-	__asm__ __volatile__("@ atomic_sub_return\n"
-"1:	ldrex	%0, [%3]\n"
-"	sub	%0, %0, %4\n"
-"	strex	%1, %0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "Ir" (i)
-	: "cc");
-
-	smp_mb();
-
-	return result;
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	prefetchw(&v->counter);						\
+	__asm__ __volatile__("@ atomic_" #op "\n"			\
+"1:	ldrex	%0, [%3]\n"						\
+"	" #asm_op "	%0, %0, %4\n"					\
+"	strex	%1, %0, [%3]\n"						\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "Ir" (i)					\
+	: "cc");							\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	smp_mb();							\
+	prefetchw(&v->counter);						\
+									\
+	__asm__ __volatile__("@ atomic_" #op "_return\n"		\
+"1:	ldrex	%0, [%3]\n"						\
+"	" #asm_op "	%0, %0, %4\n"					\
+"	strex	%1, %0, [%3]\n"						\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "Ir" (i)					\
+	: "cc");							\
+									\
+	smp_mb();							\
+									\
+	return result;							\
 }
 
 static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
@@ -174,33 +137,29 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #error SMP not supported on pre-ARMv6 CPUs
 #endif
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	int val;
-
-	raw_local_irq_save(flags);
-	val = v->counter;
-	v->counter = val += i;
-	raw_local_irq_restore(flags);
-
-	return val;
-}
-#define atomic_add(i, v)	(void) atomic_add_return(i, v)
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	int val;
-
-	raw_local_irq_save(flags);
-	val = v->counter;
-	v->counter = val -= i;
-	raw_local_irq_restore(flags);
-
-	return val;
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	raw_local_irq_save(flags);					\
+	v->counter c_op i;						\
+	raw_local_irq_restore(flags);					\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int val;							\
+									\
+	raw_local_irq_save(flags);					\
+	v->counter c_op i;						\
+	val = v->counter;						\
+	raw_local_irq_restore(flags);					\
+									\
+	return val;							\
 }
-#define atomic_sub(i, v)	(void) atomic_sub_return(i, v)
 
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
@@ -228,6 +187,17 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 #endif /* __LINUX_ARM_ARCH__ */
 
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_OP_RETURN(op, c_op, asm_op)
+
+ATOMIC_OPS(add, +=, add)
+ATOMIC_OPS(sub, -=, sub)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 #define atomic_inc(v)		atomic_add(1, v)
@@ -300,89 +270,60 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 }
 #endif
 
-static inline void atomic64_add(long long i, atomic64_t *v)
-{
-	long long result;
-	unsigned long tmp;
-
-	prefetchw(&v->counter);
-	__asm__ __volatile__("@ atomic64_add\n"
-"1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%Q0, %Q0, %Q4\n"
-"	adc	%R0, %R0, %R4\n"
-"	strexd	%1, %0, %H0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "r" (i)
-	: "cc");
-}
-
-static inline long long atomic64_add_return(long long i, atomic64_t *v)
-{
-	long long result;
-	unsigned long tmp;
-
-	smp_mb();
-	prefetchw(&v->counter);
-
-	__asm__ __volatile__("@ atomic64_add_return\n"
-"1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%Q0, %Q0, %Q4\n"
-"	adc	%R0, %R0, %R4\n"
-"	strexd	%1, %0, %H0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "r" (i)
-	: "cc");
-
-	smp_mb();
-
-	return result;
-}
-
-static inline void atomic64_sub(long long i, atomic64_t *v)
-{
-	long long result;
-	unsigned long tmp;
-
-	prefetchw(&v->counter);
-	__asm__ __volatile__("@ atomic64_sub\n"
-"1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%Q0, %Q0, %Q4\n"
-"	sbc	%R0, %R0, %R4\n"
-"	strexd	%1, %0, %H0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "r" (i)
-	: "cc");
+#define ATOMIC64_OP(op, op1, op2)					\
+static inline void atomic64_##op(long long i, atomic64_t *v)		\
+{									\
+	long long result;						\
+	unsigned long tmp;						\
+									\
+	prefetchw(&v->counter);						\
+	__asm__ __volatile__("@ atomic64_" #op "\n"			\
+"1:	ldrexd	%0, %H0, [%3]\n"					\
+"	" #op1 " %Q0, %Q0, %Q4\n"					\
+"	" #op2 " %R0, %R0, %R4\n"					\
+"	strexd	%1, %0, %H0, [%3]\n"					\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "r" (i)					\
+	: "cc");							\
+}									\
+
+#define ATOMIC64_OP_RETURN(op, op1, op2)				\
+static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
+{									\
+	long long result;						\
+	unsigned long tmp;						\
+									\
+	smp_mb();							\
+	prefetchw(&v->counter);						\
+									\
+	__asm__ __volatile__("@ atomic64_" #op "_return\n"		\
+"1:	ldrexd	%0, %H0, [%3]\n"					\
+"	" #op1 " %Q0, %Q0, %Q4\n"					\
+"	" #op2 " %R0, %R0, %R4\n"					\
+"	strexd	%1, %0, %H0, [%3]\n"					\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "r" (i)					\
+	: "cc");							\
+									\
+	smp_mb();							\
+									\
+	return result;							\
 }
 
-static inline long long atomic64_sub_return(long long i, atomic64_t *v)
-{
-	long long result;
-	unsigned long tmp;
-
-	smp_mb();
-	prefetchw(&v->counter);
-
-	__asm__ __volatile__("@ atomic64_sub_return\n"
-"1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%Q0, %Q0, %Q4\n"
-"	sbc	%R0, %R0, %R4\n"
-"	strexd	%1, %0, %H0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "r" (i)
-	: "cc");
+#define ATOMIC64_OPS(op, op1, op2)					\
+	ATOMIC64_OP(op, op1, op2)					\
+	ATOMIC64_OP_RETURN(op, op1, op2)
 
-	smp_mb();
+ATOMIC64_OPS(add, adds, adc)
+ATOMIC64_OPS(sub, subs, sbc)
 
-	return result;
-}
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
 
 static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
 					long long new)
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index c45b61a4b4a5..85738b200023 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -265,22 +265,6 @@ extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 			void *cpu_addr, dma_addr_t dma_addr, size_t size,
 			struct dma_attrs *attrs);
 
-static inline void *dma_alloc_writecombine(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
-{
-	DEFINE_DMA_ATTRS(attrs);
-	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
-	return dma_alloc_attrs(dev, size, dma_handle, flag, &attrs);
-}
-
-static inline void dma_free_writecombine(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
-{
-	DEFINE_DMA_ATTRS(attrs);
-	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
-	return dma_free_attrs(dev, size, cpu_addr, dma_handle, &attrs);
-}
-
 /*
  * This can be called during early boot to increase the size of the atomic
  * coherent DMA pool above the default value of 256KiB. It must be called
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 3d23418cbddd..180567408ee8 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -178,6 +178,7 @@ static inline void __iomem *__typesafe_io(unsigned long addr)
 
 /* PCI fixed i/o mapping */
 #define PCI_IO_VIRT_BASE	0xfee00000
+#define PCI_IOBASE		((void __iomem *)PCI_IO_VIRT_BASE)
 
 #if defined(CONFIG_PCI)
 void pci_ioremap_set_mem_type(int mem_type);
diff --git a/arch/arm/include/asm/irq_work.h b/arch/arm/include/asm/irq_work.h
new file mode 100644
index 000000000000..712d03e5973a
--- /dev/null
+++ b/arch/arm/include/asm/irq_work.h
@@ -0,0 +1,11 @@
+#ifndef __ASM_ARM_IRQ_WORK_H
+#define __ASM_ARM_IRQ_WORK_H
+
+#include <asm/smp_plat.h>
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return is_smp();
+}
+
+#endif /* _ASM_ARM_IRQ_WORK_H */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 3f688b458143..acb0d5712716 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -37,6 +37,11 @@
  */
 #define TRAMPOLINE_VA		UL(CONFIG_VECTORS_BASE)
 
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
+ */
+#define KVM_MMU_CACHE_MIN_PAGES	2
+
 #ifndef __ASSEMBLY__
 
 #include <asm/cacheflush.h>
@@ -50,7 +55,7 @@ void free_hyp_pgds(void);
 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
-			  phys_addr_t pa, unsigned long size);
+			  phys_addr_t pa, unsigned long size, bool writable);
 
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
 
@@ -83,6 +88,11 @@ static inline void kvm_clean_pgd(pgd_t *pgd)
 	clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
 }
 
+static inline void kvm_clean_pmd(pmd_t *pmd)
+{
+	clean_dcache_area(pmd, PTRS_PER_PMD * sizeof(pmd_t));
+}
+
 static inline void kvm_clean_pmd_entry(pmd_t *pmd)
 {
 	clean_pmd_entry(pmd);
@@ -123,10 +133,23 @@ static inline bool kvm_page_empty(void *ptr)
 }
 
 
-#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
-#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
-#define kvm_pud_table_empty(pudp) (0)
+#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
+#define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
+#define kvm_pud_table_empty(kvm, pudp) (0)
+
+#define KVM_PREALLOC_LEVEL	0
 
+static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
+{
+	return 0;
+}
+
+static inline void kvm_free_hwpgd(struct kvm *kvm) { }
+
+static inline void *kvm_get_hwpgd(struct kvm *kvm)
+{
+	return kvm->arch.pgd;
+}
 
 struct kvm;
 
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index 219ac88a9542..f0279411847d 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -182,6 +182,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pmd_addr_end(addr,end) (end)
 
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
+#define pte_special(pte)	(0)
+static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 
 /*
  * We don't have huge page support for short descriptors, for the moment
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 06e0bc0f8b00..a31ecdad4b59 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -213,10 +213,19 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define pmd_isclear(pmd, val)	(!(pmd_val(pmd) & (val)))
 
 #define pmd_young(pmd)		(pmd_isset((pmd), PMD_SECT_AF))
+#define pte_special(pte)	(pte_isset((pte), L_PTE_SPECIAL))
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	pte_val(pte) |= L_PTE_SPECIAL;
+	return pte;
+}
+#define	__HAVE_ARCH_PTE_SPECIAL
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		(pmd_isclear((pmd), L_PMD_SECT_RDONLY))
 #define pmd_dirty(pmd)		(pmd_isset((pmd), L_PMD_SECT_DIRTY))
+#define pud_page(pud)		pmd_page(__pmd(pud_val(pud)))
+#define pud_write(pud)		pmd_write(__pmd(pud_val(pud)))
 
 #define pmd_hugewillfault(pmd)	(!pmd_young(pmd) || !pmd_write(pmd))
 #define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
@@ -224,6 +233,12 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !pmd_table(pmd))
 #define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING))
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp);
+#endif
 #endif
 
 #define PMD_BIT_FUNC(fn,op) \
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 01baef07cd0c..3b30062975b2 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -100,7 +100,7 @@ extern pgprot_t		pgprot_s2_device;
 #define PAGE_HYP		_MOD_PROT(pgprot_kernel, L_PTE_HYP)
 #define PAGE_HYP_DEVICE		_MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
 #define PAGE_S2			_MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDWR)
+#define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY)
 
 #define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE)
 #define __PAGE_SHARED		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)
@@ -226,7 +226,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 #define pte_dirty(pte)		(pte_isset((pte), L_PTE_DIRTY))
 #define pte_young(pte)		(pte_isset((pte), L_PTE_YOUNG))
 #define pte_exec(pte)		(pte_isclear((pte), L_PTE_XN))
-#define pte_special(pte)	(0)
 
 #define pte_valid_user(pte)	\
 	(pte_valid(pte) && pte_isset((pte), L_PTE_USER) && pte_young(pte))
@@ -245,7 +244,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	unsigned long ext = 0;
 
 	if (addr < TASK_SIZE && pte_valid_user(pteval)) {
-		__sync_icache_dcache(pteval);
+		if (!pte_special(pteval))
+			__sync_icache_dcache(pteval);
 		ext |= PTE_EXT_NG;
 	}
 
@@ -264,8 +264,6 @@ PTE_BIT_FUNC(mkyoung,   |= L_PTE_YOUNG);
 PTE_BIT_FUNC(mkexec,   &= ~L_PTE_XN);
 PTE_BIT_FUNC(mknexec,   |= L_PTE_XN);
 
-static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER |
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index f1a0dace3efe..3cadb726ec88 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -35,12 +35,39 @@
 
 #define MMU_GATHER_BUNDLE	8
 
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+static inline void __tlb_remove_table(void *_table)
+{
+	free_page_and_swap_cache((struct page *)_table);
+}
+
+struct mmu_table_batch {
+	struct rcu_head		rcu;
+	unsigned int		nr;
+	void			*tables[0];
+};
+
+#define MAX_TABLE_BATCH		\
+	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
+
+extern void tlb_table_flush(struct mmu_gather *tlb);
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+
+#define tlb_remove_entry(tlb, entry)	tlb_remove_table(tlb, entry)
+#else
+#define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+
 /*
  * TLB handling.  This allows us to remove pages from the page
  * tables, and efficiently handle the TLB issues.
  */
 struct mmu_gather {
 	struct mm_struct	*mm;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	struct mmu_table_batch	*batch;
+	unsigned int		need_flush;
+#endif
 	unsigned int		fullmm;
 	struct vm_area_struct	*vma;
 	unsigned long		start, end;
@@ -101,6 +128,9 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
 	tlb_flush(tlb);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb_table_flush(tlb);
+#endif
 }
 
 static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
@@ -129,6 +159,10 @@ tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start
 	tlb->pages = tlb->local;
 	tlb->nr = 0;
 	__tlb_alloc_page(tlb);
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb->batch = NULL;
+#endif
 }
 
 static inline void
@@ -205,7 +239,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	tlb_add_flush(tlb, addr + SZ_1M);
 #endif
 
-	tlb_remove_page(tlb, pte);
+	tlb_remove_entry(tlb, pte);
 }
 
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
@@ -213,7 +247,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 {
 #ifdef CONFIG_ARM_LPAE
 	tlb_add_flush(tlb, addr);
-	tlb_remove_page(tlb, virt_to_page(pmdp));
+	tlb_remove_entry(tlb, virt_to_page(pmdp));
 #endif
 }
 
diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c
index bb8b79648643..c4cc50e58c13 100644
--- a/arch/arm/kernel/hibernate.c
+++ b/arch/arm/kernel/hibernate.c
@@ -21,8 +21,7 @@
 #include <asm/idmap.h>
 #include <asm/suspend.h>
 #include <asm/memory.h>
-
-extern const void __nosave_begin, __nosave_end;
+#include <asm/sections.h>
 
 int pfn_is_nosave(unsigned long pfn)
 {
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 88de943eebd6..7c81ec428b9b 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -65,24 +65,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
  */
 void handle_IRQ(unsigned int irq, struct pt_regs *regs)
 {
-	struct pt_regs *old_regs = set_irq_regs(regs);
-
-	irq_enter();
-
-	/*
-	 * Some hardware gives randomly wrong interrupts.  Rather
-	 * than crashing, do something sensible.
-	 */
-	if (unlikely(irq >= nr_irqs)) {
-		if (printk_ratelimit())
-			printk(KERN_WARNING "Bad IRQ%u\n", irq);
-		ack_bad_irq(irq);
-	} else {
-		generic_handle_irq(irq);
-	}
-
-	irq_exit();
-	set_irq_regs(old_regs);
+	__handle_domain_irq(NULL, irq, false, regs);
 }
 
 /*
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index a0a691d1cbee..fe972a2f3df3 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -114,18 +114,13 @@ void soft_restart(unsigned long addr)
 	BUG();
 }
 
-static void null_restart(enum reboot_mode reboot_mode, const char *cmd)
-{
-}
-
 /*
  * Function pointers to optional machine specific functions
  */
 void (*pm_power_off)(void);
 EXPORT_SYMBOL(pm_power_off);
 
-void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd) = null_restart;
-EXPORT_SYMBOL_GPL(arm_pm_restart);
+void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 
 /*
  * This is our default idle handler.
@@ -230,7 +225,10 @@ void machine_restart(char *cmd)
 	local_irq_disable();
 	smp_send_stop();
 
-	arm_pm_restart(reboot_mode, cmd);
+	if (arm_pm_restart)
+		arm_pm_restart(reboot_mode, cmd);
+	else
+		do_kernel_restart(cmd);
 
 	/* Give a grace period for failure to restart of 1s */
 	mdelay(1000);
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 0c27ed6f3f23..5e772a21ab97 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -933,8 +933,13 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno)
 	current_thread_info()->syscall = scno;
 
 	/* Do the secure computing check first; failures should be fast. */
-	if (secure_computing(scno) == -1)
+#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
+	if (secure_computing() == -1)
 		return -1;
+#else
+	/* XXX: remove this once OABI gets fixed */
+	secure_computing_strict(scno);
+#endif
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 39c74a2c3df9..13396d3d600e 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -499,7 +499,7 @@ void arch_send_call_function_single_ipi(int cpu)
 #ifdef CONFIG_IRQ_WORK
 void arch_irq_work_raise(void)
 {
-	if (is_smp())
+	if (arch_irq_work_has_interrupt())
 		smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
 }
 #endif
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index dfc32130bc44..93090213c71c 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -92,7 +92,7 @@ static int twd_timer_ack(void)
 
 static void twd_timer_stop(void)
 {
-	struct clock_event_device *clk = __this_cpu_ptr(twd_evt);
+	struct clock_event_device *clk = raw_cpu_ptr(twd_evt);
 
 	twd_set_mode(CLOCK_EVT_MODE_UNUSED, clk);
 	disable_percpu_irq(clk->irq);
@@ -108,7 +108,7 @@ static void twd_update_frequency(void *new_rate)
 {
 	twd_timer_rate = *((unsigned long *) new_rate);
 
-	clockevents_update_freq(__this_cpu_ptr(twd_evt), twd_timer_rate);
+	clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate);
 }
 
 static int twd_rate_change(struct notifier_block *nb,
@@ -134,7 +134,7 @@ static struct notifier_block twd_clk_nb = {
 
 static int twd_clk_init(void)
 {
-	if (twd_evt && __this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
+	if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
 		return clk_notifier_register(twd_clk, &twd_clk_nb);
 
 	return 0;
@@ -153,7 +153,7 @@ static void twd_update_frequency(void *data)
 {
 	twd_timer_rate = clk_get_rate(twd_clk);
 
-	clockevents_update_freq(__this_cpu_ptr(twd_evt), twd_timer_rate);
+	clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate);
 }
 
 static int twd_cpufreq_transition(struct notifier_block *nb,
@@ -179,7 +179,7 @@ static struct notifier_block twd_cpufreq_nb = {
 
 static int twd_cpufreq_init(void)
 {
-	if (twd_evt && __this_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
+	if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
 		return cpufreq_register_notifier(&twd_cpufreq_nb,
 			CPUFREQ_TRANSITION_NOTIFIER);
 
@@ -269,7 +269,7 @@ static void twd_get_clock(struct device_node *np)
  */
 static void twd_timer_setup(void)
 {
-	struct clock_event_device *clk = __this_cpu_ptr(twd_evt);
+	struct clock_event_device *clk = raw_cpu_ptr(twd_evt);
 	int cpu = smp_processor_id();
 
 	/*
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index e35d880f9773..89cfdd6e50cb 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -42,7 +42,7 @@
  */
 static DEFINE_PER_CPU(unsigned long, cpu_scale);
 
-unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
+unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 {
 	return per_cpu(cpu_scale, cpu);
 }
@@ -166,7 +166,7 @@ static void update_cpu_capacity(unsigned int cpu)
 	set_capacity_scale(cpu, cpu_capacity(cpu) / middle_capacity);
 
 	printk(KERN_INFO "CPU%u: update cpu_capacity %lu\n",
-		cpu, arch_scale_freq_capacity(NULL, cpu));
+		cpu, arch_scale_cpu_capacity(NULL, cpu));
 }
 
 #else
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 779605122f32..9e193c8a959e 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -409,7 +409,7 @@ static void update_vttbr(struct kvm *kvm)
 	kvm_next_vmid++;
 
 	/* update vttbr to be used with the new vmid */
-	pgd_phys = virt_to_phys(kvm->arch.pgd);
+	pgd_phys = virt_to_phys(kvm_get_hwpgd(kvm));
 	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
 	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK;
 	kvm->arch.vttbr = pgd_phys | vmid;
@@ -808,7 +808,8 @@ static int hyp_init_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_STARTING:
 	case CPU_STARTING_FROZEN:
-		cpu_init_hyp_mode(NULL);
+		if (__hyp_get_vectors() == hyp_default_vectors)
+			cpu_init_hyp_mode(NULL);
 		break;
 	}
 
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 98c8c5b9a87f..14d488388480 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -433,10 +433,17 @@ ARM_BE8(rev	r10, r10	)
 	str	r3, [r11, #VGIC_V2_CPU_HCR]
 	str	r4, [r11, #VGIC_V2_CPU_VMCR]
 	str	r5, [r11, #VGIC_V2_CPU_MISR]
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	str	r6, [r11, #(VGIC_V2_CPU_EISR + 4)]
+	str	r7, [r11, #VGIC_V2_CPU_EISR]
+	str	r8, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
+	str	r9, [r11, #VGIC_V2_CPU_ELRSR]
+#else
 	str	r6, [r11, #VGIC_V2_CPU_EISR]
 	str	r7, [r11, #(VGIC_V2_CPU_EISR + 4)]
 	str	r8, [r11, #VGIC_V2_CPU_ELRSR]
 	str	r9, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
+#endif
 	str	r10, [r11, #VGIC_V2_CPU_APR]
 
 	/* Clear GICH_HCR */
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index eea03069161b..57a403a5c22b 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -42,7 +42,7 @@ static unsigned long hyp_idmap_start;
 static unsigned long hyp_idmap_end;
 static phys_addr_t hyp_idmap_vector;
 
-#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
+#define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
 
 #define kvm_pmd_huge(_x)	(pmd_huge(_x) || pmd_trans_huge(_x))
 
@@ -134,7 +134,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
-	if (kvm_pte_table_empty(start_pte))
+	if (kvm_pte_table_empty(kvm, start_pte))
 		clear_pmd_entry(kvm, pmd, start_addr);
 }
 
@@ -158,7 +158,7 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud,
 		}
 	} while (pmd++, addr = next, addr != end);
 
-	if (kvm_pmd_table_empty(start_pmd))
+	if (kvm_pmd_table_empty(kvm, start_pmd))
 		clear_pud_entry(kvm, pud, start_addr);
 }
 
@@ -182,7 +182,7 @@ static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
 		}
 	} while (pud++, addr = next, addr != end);
 
-	if (kvm_pud_table_empty(start_pud))
+	if (kvm_pud_table_empty(kvm, start_pud))
 		clear_pgd_entry(kvm, pgd, start_addr);
 }
 
@@ -306,7 +306,7 @@ void free_boot_hyp_pgd(void)
 	if (boot_hyp_pgd) {
 		unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
 		unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-		free_pages((unsigned long)boot_hyp_pgd, pgd_order);
+		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
 		boot_hyp_pgd = NULL;
 	}
 
@@ -343,7 +343,7 @@ void free_hyp_pgds(void)
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
 			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
 
-		free_pages((unsigned long)hyp_pgd, pgd_order);
+		free_pages((unsigned long)hyp_pgd, hyp_pgd_order);
 		hyp_pgd = NULL;
 	}
 
@@ -401,13 +401,46 @@ static int create_hyp_pmd_mappings(pud_t *pud, unsigned long start,
 	return 0;
 }
 
+static int create_hyp_pud_mappings(pgd_t *pgd, unsigned long start,
+				   unsigned long end, unsigned long pfn,
+				   pgprot_t prot)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+	unsigned long addr, next;
+	int ret;
+
+	addr = start;
+	do {
+		pud = pud_offset(pgd, addr);
+
+		if (pud_none_or_clear_bad(pud)) {
+			pmd = pmd_alloc_one(NULL, addr);
+			if (!pmd) {
+				kvm_err("Cannot allocate Hyp pmd\n");
+				return -ENOMEM;
+			}
+			pud_populate(NULL, pud, pmd);
+			get_page(virt_to_page(pud));
+			kvm_flush_dcache_to_poc(pud, sizeof(*pud));
+		}
+
+		next = pud_addr_end(addr, end);
+		ret = create_hyp_pmd_mappings(pud, addr, next, pfn, prot);
+		if (ret)
+			return ret;
+		pfn += (next - addr) >> PAGE_SHIFT;
+	} while (addr = next, addr != end);
+
+	return 0;
+}
+
 static int __create_hyp_mappings(pgd_t *pgdp,
 				 unsigned long start, unsigned long end,
 				 unsigned long pfn, pgprot_t prot)
 {
 	pgd_t *pgd;
 	pud_t *pud;
-	pmd_t *pmd;
 	unsigned long addr, next;
 	int err = 0;
 
@@ -416,22 +449,21 @@ static int __create_hyp_mappings(pgd_t *pgdp,
 	end = PAGE_ALIGN(end);
 	do {
 		pgd = pgdp + pgd_index(addr);
-		pud = pud_offset(pgd, addr);
 
-		if (pud_none_or_clear_bad(pud)) {
-			pmd = pmd_alloc_one(NULL, addr);
-			if (!pmd) {
-				kvm_err("Cannot allocate Hyp pmd\n");
+		if (pgd_none(*pgd)) {
+			pud = pud_alloc_one(NULL, addr);
+			if (!pud) {
+				kvm_err("Cannot allocate Hyp pud\n");
 				err = -ENOMEM;
 				goto out;
 			}
-			pud_populate(NULL, pud, pmd);
-			get_page(virt_to_page(pud));
-			kvm_flush_dcache_to_poc(pud, sizeof(*pud));
+			pgd_populate(NULL, pgd, pud);
+			get_page(virt_to_page(pgd));
+			kvm_flush_dcache_to_poc(pgd, sizeof(*pgd));
 		}
 
 		next = pgd_addr_end(addr, end);
-		err = create_hyp_pmd_mappings(pud, addr, next, pfn, prot);
+		err = create_hyp_pud_mappings(pgd, addr, next, pfn, prot);
 		if (err)
 			goto out;
 		pfn += (next - addr) >> PAGE_SHIFT;
@@ -521,6 +553,7 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
  */
 int kvm_alloc_stage2_pgd(struct kvm *kvm)
 {
+	int ret;
 	pgd_t *pgd;
 
 	if (kvm->arch.pgd != NULL) {
@@ -528,15 +561,38 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 		return -EINVAL;
 	}
 
-	pgd = (pgd_t *)__get_free_pages(GFP_KERNEL, S2_PGD_ORDER);
+	if (KVM_PREALLOC_LEVEL > 0) {
+		/*
+		 * Allocate fake pgd for the page table manipulation macros to
+		 * work.  This is not used by the hardware and we have no
+		 * alignment requirement for this allocation.
+		 */
+		pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
+				       GFP_KERNEL | __GFP_ZERO);
+	} else {
+		/*
+		 * Allocate actual first-level Stage-2 page table used by the
+		 * hardware for Stage-2 page table walks.
+		 */
+		pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER);
+	}
+
 	if (!pgd)
 		return -ENOMEM;
 
-	memset(pgd, 0, PTRS_PER_S2_PGD * sizeof(pgd_t));
+	ret = kvm_prealloc_hwpgd(kvm, pgd);
+	if (ret)
+		goto out_err;
+
 	kvm_clean_pgd(pgd);
 	kvm->arch.pgd = pgd;
-
 	return 0;
+out_err:
+	if (KVM_PREALLOC_LEVEL > 0)
+		kfree(pgd);
+	else
+		free_pages((unsigned long)pgd, S2_PGD_ORDER);
+	return ret;
 }
 
 /**
@@ -572,19 +628,39 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
 		return;
 
 	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
-	free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
+	kvm_free_hwpgd(kvm);
+	if (KVM_PREALLOC_LEVEL > 0)
+		kfree(kvm->arch.pgd);
+	else
+		free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
 	kvm->arch.pgd = NULL;
 }
 
-static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 			     phys_addr_t addr)
 {
 	pgd_t *pgd;
 	pud_t *pud;
-	pmd_t *pmd;
 
 	pgd = kvm->arch.pgd + pgd_index(addr);
-	pud = pud_offset(pgd, addr);
+	if (WARN_ON(pgd_none(*pgd))) {
+		if (!cache)
+			return NULL;
+		pud = mmu_memory_cache_alloc(cache);
+		pgd_populate(NULL, pgd, pud);
+		get_page(virt_to_page(pgd));
+	}
+
+	return pud_offset(pgd, addr);
+}
+
+static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+			     phys_addr_t addr)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pud = stage2_get_pud(kvm, cache, addr);
 	if (pud_none(*pud)) {
 		if (!cache)
 			return NULL;
@@ -630,7 +706,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 	pmd_t *pmd;
 	pte_t *pte, old_pte;
 
-	/* Create stage-2 page table mapping - Level 1 */
+	/* Create stage-2 page table mapping - Levels 0 and 1 */
 	pmd = stage2_get_pmd(kvm, cache, addr);
 	if (!pmd) {
 		/*
@@ -675,7 +751,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
  * @size:	The size of the mapping
  */
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
-			  phys_addr_t pa, unsigned long size)
+			  phys_addr_t pa, unsigned long size, bool writable)
 {
 	phys_addr_t addr, end;
 	int ret = 0;
@@ -688,7 +764,11 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 	for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
 		pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);
 
-		ret = mmu_topup_memory_cache(&cache, 2, 2);
+		if (writable)
+			kvm_set_s2pte_writable(&pte);
+
+		ret = mmu_topup_memory_cache(&cache, KVM_MMU_CACHE_MIN_PAGES,
+						KVM_NR_MEM_OBJS);
 		if (ret)
 			goto out;
 		spin_lock(&kvm->mmu_lock);
@@ -777,6 +857,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	/* Let's check if we will get back a huge page backed by hugetlbfs */
 	down_read(&current->mm->mmap_sem);
 	vma = find_vma_intersection(current->mm, hva, hva + 1);
+	if (unlikely(!vma)) {
+		kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
+		up_read(&current->mm->mmap_sem);
+		return -EFAULT;
+	}
+
 	if (is_vm_hugetlb_page(vma)) {
 		hugetlb = true;
 		gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
@@ -797,7 +883,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	up_read(&current->mm->mmap_sem);
 
 	/* We need minimum second+third level pages */
-	ret = mmu_topup_memory_cache(memcache, 2, KVM_NR_MEM_OBJS);
+	ret = mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES,
+				     KVM_NR_MEM_OBJS);
 	if (ret)
 		return ret;
 
@@ -843,7 +930,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		}
 		coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
 		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
-				     mem_type == PAGE_S2_DEVICE);
+			pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
 	}
 
 
@@ -916,6 +1003,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		goto out_unlock;
 	}
 
+	/* Userspace should not be able to register out-of-bounds IPAs */
+	VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE);
+
 	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
 	if (ret == 0)
 		ret = 1;
@@ -1072,8 +1162,8 @@ int kvm_mmu_init(void)
 			 (unsigned long)phys_base);
 	}
 
-	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
-	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
+	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
 
 	if (!hyp_pgd || !boot_hyp_pgd) {
 		kvm_err("Hyp mode PGD not allocated\n");
@@ -1126,13 +1216,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   const struct kvm_memory_slot *old,
 				   enum kvm_mr_change change)
 {
-	gpa_t gpa = old->base_gfn << PAGE_SHIFT;
-	phys_addr_t size = old->npages << PAGE_SHIFT;
-	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
-		spin_lock(&kvm->mmu_lock);
-		unmap_stage2_range(kvm, gpa, size);
-		spin_unlock(&kvm->mmu_lock);
-	}
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -1140,7 +1223,77 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_userspace_memory_region *mem,
 				   enum kvm_mr_change change)
 {
-	return 0;
+	hva_t hva = mem->userspace_addr;
+	hva_t reg_end = hva + mem->memory_size;
+	bool writable = !(mem->flags & KVM_MEM_READONLY);
+	int ret = 0;
+
+	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE)
+		return 0;
+
+	/*
+	 * Prevent userspace from creating a memory region outside of the IPA
+	 * space addressable by the KVM guest IPA space.
+	 */
+	if (memslot->base_gfn + memslot->npages >=
+	    (KVM_PHYS_SIZE >> PAGE_SHIFT))
+		return -EFAULT;
+
+	/*
+	 * A memory region could potentially cover multiple VMAs, and any holes
+	 * between them, so iterate over all of them to find out if we can map
+	 * any of them right now.
+	 *
+	 *     +--------------------------------------------+
+	 * +---------------+----------------+   +----------------+
+	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
+	 * +---------------+----------------+   +----------------+
+	 *     |               memory region                |
+	 *     +--------------------------------------------+
+	 */
+	do {
+		struct vm_area_struct *vma = find_vma(current->mm, hva);
+		hva_t vm_start, vm_end;
+
+		if (!vma || vma->vm_start >= reg_end)
+			break;
+
+		/*
+		 * Mapping a read-only VMA is only allowed if the
+		 * memory region is configured as read-only.
+		 */
+		if (writable && !(vma->vm_flags & VM_WRITE)) {
+			ret = -EPERM;
+			break;
+		}
+
+		/*
+		 * Take the intersection of this VMA with the memory region
+		 */
+		vm_start = max(hva, vma->vm_start);
+		vm_end = min(reg_end, vma->vm_end);
+
+		if (vma->vm_flags & VM_PFNMAP) {
+			gpa_t gpa = mem->guest_phys_addr +
+				    (vm_start - mem->userspace_addr);
+			phys_addr_t pa = (vma->vm_pgoff << PAGE_SHIFT) +
+					 vm_start - vma->vm_start;
+
+			ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
+						    vm_end - vm_start,
+						    writable);
+			if (ret)
+				break;
+		}
+		hva = vm_end;
+	} while (hva < reg_end);
+
+	if (ret) {
+		spin_lock(&kvm->mmu_lock);
+		unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
+		spin_unlock(&kvm->mmu_lock);
+	}
+	return ret;
 }
 
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
@@ -1165,4 +1318,10 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
+	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = slot->npages << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	unmap_stage2_range(kvm, gpa, size);
+	spin_unlock(&kvm->mmu_lock);
 }
diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile
index ac99d87ffefe..1b9ae0257a6e 100644
--- a/arch/arm/mach-at91/Makefile
+++ b/arch/arm/mach-at91/Makefile
@@ -3,9 +3,6 @@
 #
 
 obj-y		:= gpio.o setup.o sysirq_mask.o
-obj-m		:=
-obj-n		:=
-obj-		:=
 
 obj-$(CONFIG_OLD_IRQ_AT91)	+= irq.o
 obj-$(CONFIG_OLD_CLK_AT91)	+= clock.o
diff --git a/arch/arm/mach-ebsa110/Makefile b/arch/arm/mach-ebsa110/Makefile
index 935e4af01a27..a7d68c13c1d1 100644
--- a/arch/arm/mach-ebsa110/Makefile
+++ b/arch/arm/mach-ebsa110/Makefile
@@ -5,6 +5,3 @@
 # Object file lists.
 
 obj-y			:= core.o io.o leds.o
-obj-m			:=
-obj-n			:=
-obj-			:=
diff --git a/arch/arm/mach-ep93xx/Makefile b/arch/arm/mach-ep93xx/Makefile
index 0dc51f9462de..78d427b34b1f 100644
--- a/arch/arm/mach-ep93xx/Makefile
+++ b/arch/arm/mach-ep93xx/Makefile
@@ -2,9 +2,6 @@
 # Makefile for the linux kernel.
 #
 obj-y			:= core.o clock.o
-obj-m			:=
-obj-n			:=
-obj-			:=
 
 obj-$(CONFIG_EP93XX_DMA)	+= dma.o
 
diff --git a/arch/arm/mach-exynos/Makefile b/arch/arm/mach-exynos/Makefile
index 788f26d21141..27ae6144679c 100644
--- a/arch/arm/mach-exynos/Makefile
+++ b/arch/arm/mach-exynos/Makefile
@@ -7,11 +7,6 @@
 
 ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include
 
-obj-y				:=
-obj-m				:=
-obj-n				:=
-obj-				:=
-
 # Core
 
 obj-$(CONFIG_ARCH_EXYNOS)	+= exynos.o pmu.o exynos-smc.o firmware.o
diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c
index 6a24e111d6e1..b89e5f35db84 100644
--- a/arch/arm/mach-exynos/exynos.c
+++ b/arch/arm/mach-exynos/exynos.c
@@ -193,7 +193,6 @@ static void __init exynos_init_late(void)
 		/* to be supported later */
 		return;
 
-	pm_genpd_poweroff_unused();
 	exynos_pm_init();
 }
 
diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c
index fd76e1b5a471..20f267121b3e 100644
--- a/arch/arm/mach-exynos/pm_domains.c
+++ b/arch/arm/mach-exynos/pm_domains.c
@@ -105,78 +105,6 @@ static int exynos_pd_power_off(struct generic_pm_domain *domain)
 	return exynos_pd_power(domain, false);
 }
 
-static void exynos_add_device_to_domain(struct exynos_pm_domain *pd,
-					 struct device *dev)
-{
-	int ret;
-
-	dev_dbg(dev, "adding to power domain %s\n", pd->pd.name);
-
-	while (1) {
-		ret = pm_genpd_add_device(&pd->pd, dev);
-		if (ret != -EAGAIN)
-			break;
-		cond_resched();
-	}
-
-	pm_genpd_dev_need_restore(dev, true);
-}
-
-static void exynos_remove_device_from_domain(struct device *dev)
-{
-	struct generic_pm_domain *genpd = dev_to_genpd(dev);
-	int ret;
-
-	dev_dbg(dev, "removing from power domain %s\n", genpd->name);
-
-	while (1) {
-		ret = pm_genpd_remove_device(genpd, dev);
-		if (ret != -EAGAIN)
-			break;
-		cond_resched();
-	}
-}
-
-static void exynos_read_domain_from_dt(struct device *dev)
-{
-	struct platform_device *pd_pdev;
-	struct exynos_pm_domain *pd;
-	struct device_node *node;
-
-	node = of_parse_phandle(dev->of_node, "samsung,power-domain", 0);
-	if (!node)
-		return;
-	pd_pdev = of_find_device_by_node(node);
-	if (!pd_pdev)
-		return;
-	pd = platform_get_drvdata(pd_pdev);
-	exynos_add_device_to_domain(pd, dev);
-}
-
-static int exynos_pm_notifier_call(struct notifier_block *nb,
-				    unsigned long event, void *data)
-{
-	struct device *dev = data;
-
-	switch (event) {
-	case BUS_NOTIFY_BIND_DRIVER:
-		if (dev->of_node)
-			exynos_read_domain_from_dt(dev);
-
-		break;
-
-	case BUS_NOTIFY_UNBOUND_DRIVER:
-		exynos_remove_device_from_domain(dev);
-
-		break;
-	}
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block platform_nb = {
-	.notifier_call = exynos_pm_notifier_call,
-};
-
 static __init int exynos4_pm_init_power_domain(void)
 {
 	struct platform_device *pdev;
@@ -202,7 +130,6 @@ static __init int exynos4_pm_init_power_domain(void)
 		pd->base = of_iomap(np, 0);
 		pd->pd.power_off = exynos_pd_power_off;
 		pd->pd.power_on = exynos_pd_power_on;
-		pd->pd.of_node = np;
 
 		pd->oscclk = clk_get(dev, "oscclk");
 		if (IS_ERR(pd->oscclk))
@@ -228,15 +155,12 @@ static __init int exynos4_pm_init_power_domain(void)
 			clk_put(pd->oscclk);
 
 no_clk:
-		platform_set_drvdata(pdev, pd);
-
 		on = __raw_readl(pd->base + 0x4) & INT_LOCAL_PWR_EN;
 
 		pm_genpd_init(&pd->pd, NULL, !on);
+		of_genpd_add_provider_simple(np, &pd->pd);
 	}
 
-	bus_register_notifier(&platform_bus_type, &platform_nb);
-
 	return 0;
 }
 arch_initcall(exynos4_pm_init_power_domain);
diff --git a/arch/arm/mach-footbridge/Makefile b/arch/arm/mach-footbridge/Makefile
index c3faa3bc84dd..e83d5c8396ff 100644
--- a/arch/arm/mach-footbridge/Makefile
+++ b/arch/arm/mach-footbridge/Makefile
@@ -5,9 +5,6 @@
 # Object file lists.
 
 obj-y			:= common.o dma.o isa-irq.o
-obj-m			:=
-obj-n			:=
-obj-			:=
 
 pci-y			+= dc21285.o
 pci-$(CONFIG_ARCH_CATS) += cats-pci.o
diff --git a/arch/arm/mach-imx/avic.c b/arch/arm/mach-imx/avic.c
index 24b103c67f82..1a8932335b21 100644
--- a/arch/arm/mach-imx/avic.c
+++ b/arch/arm/mach-imx/avic.c
@@ -144,7 +144,7 @@ static void __exception_irq_entry avic_handle_irq(struct pt_regs *regs)
 		if (nivector == 0xffff)
 			break;
 
-		handle_IRQ(irq_find_mapping(domain, nivector), regs);
+		handle_domain_irq(domain, nivector, regs);
 	} while (1);
 }
 
diff --git a/arch/arm/mach-imx/imx27-dt.c b/arch/arm/mach-imx/imx27-dt.c
index 080e66c6a1d0..dc8f1a6f45f2 100644
--- a/arch/arm/mach-imx/imx27-dt.c
+++ b/arch/arm/mach-imx/imx27-dt.c
@@ -20,7 +20,7 @@
 
 static void __init imx27_dt_init(void)
 {
-	struct platform_device_info devinfo = { .name = "cpufreq-cpu0", };
+	struct platform_device_info devinfo = { .name = "cpufreq-dt", };
 
 	mxc_arch_reset_init_dt();
 
diff --git a/arch/arm/mach-imx/mach-imx51.c b/arch/arm/mach-imx/mach-imx51.c
index c77deb3f0893..2c5fcaf8675b 100644
--- a/arch/arm/mach-imx/mach-imx51.c
+++ b/arch/arm/mach-imx/mach-imx51.c
@@ -51,7 +51,7 @@ static void __init imx51_ipu_mipi_setup(void)
 
 static void __init imx51_dt_init(void)
 {
-	struct platform_device_info devinfo = { .name = "cpufreq-cpu0", };
+	struct platform_device_info devinfo = { .name = "cpufreq-dt", };
 
 	mxc_arch_reset_init_dt();
 	imx51_ipu_mipi_setup();
diff --git a/arch/arm/mach-imx/tzic.c b/arch/arm/mach-imx/tzic.c
index 1d4f384ca773..4de65eeda1eb 100644
--- a/arch/arm/mach-imx/tzic.c
+++ b/arch/arm/mach-imx/tzic.c
@@ -141,8 +141,7 @@ static void __exception_irq_entry tzic_handle_irq(struct pt_regs *regs)
 			while (stat) {
 				handled = 1;
 				irqofs = fls(stat) - 1;
-				handle_IRQ(irq_find_mapping(domain,
-						irqofs + i * 32), regs);
+				handle_domain_irq(domain, irqofs + i * 32, regs);
 				stat &= ~(1 << irqofs);
 			}
 		}
diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c
index 05e1f73a1e8d..c186a17c2cff 100644
--- a/arch/arm/mach-integrator/pci_v3.c
+++ b/arch/arm/mach-integrator/pci_v3.c
@@ -660,6 +660,7 @@ static void __init pci_v3_preinit(void)
 {
 	unsigned long flags;
 	unsigned int temp;
+	phys_addr_t io_address = pci_pio_to_address(io_mem.start);
 
 	pcibios_min_mem = 0x00100000;
 
@@ -701,7 +702,7 @@ static void __init pci_v3_preinit(void)
 	/*
 	 * Setup window 2 - PCI IO
 	 */
-	v3_writel(V3_LB_BASE2, v3_addr_to_lb_base2(io_mem.start) |
+	v3_writel(V3_LB_BASE2, v3_addr_to_lb_base2(io_address) |
 			V3_LB_BASE_ENABLE);
 	v3_writew(V3_LB_MAP2, v3_addr_to_lb_map2(0));
 
@@ -742,6 +743,7 @@ static void __init pci_v3_preinit(void)
 static void __init pci_v3_postinit(void)
 {
 	unsigned int pci_cmd;
+	phys_addr_t io_address = pci_pio_to_address(io_mem.start);
 
 	pci_cmd = PCI_COMMAND_MEMORY |
 		  PCI_COMMAND_MASTER | PCI_COMMAND_INVALIDATE;
@@ -758,7 +760,7 @@ static void __init pci_v3_postinit(void)
 		       "interrupt: %d\n", ret);
 #endif
 
-	register_isa_ports(non_mem.start, io_mem.start, 0);
+	register_isa_ports(non_mem.start, io_address, 0);
 }
 
 /*
@@ -867,33 +869,32 @@ static int __init pci_v3_probe(struct platform_device *pdev)
 
 	for_each_of_pci_range(&parser, &range) {
 		if (!range.flags) {
-			of_pci_range_to_resource(&range, np, &conf_mem);
+			ret = of_pci_range_to_resource(&range, np, &conf_mem);
 			conf_mem.name = "PCIv3 config";
 		}
 		if (range.flags & IORESOURCE_IO) {
-			of_pci_range_to_resource(&range, np, &io_mem);
+			ret = of_pci_range_to_resource(&range, np, &io_mem);
 			io_mem.name = "PCIv3 I/O";
 		}
 		if ((range.flags & IORESOURCE_MEM) &&
 			!(range.flags & IORESOURCE_PREFETCH)) {
 			non_mem_pci = range.pci_addr;
 			non_mem_pci_sz = range.size;
-			of_pci_range_to_resource(&range, np, &non_mem);
+			ret = of_pci_range_to_resource(&range, np, &non_mem);
 			non_mem.name = "PCIv3 non-prefetched mem";
 		}
 		if ((range.flags & IORESOURCE_MEM) &&
 			(range.flags & IORESOURCE_PREFETCH)) {
 			pre_mem_pci = range.pci_addr;
 			pre_mem_pci_sz = range.size;
-			of_pci_range_to_resource(&range, np, &pre_mem);
+			ret = of_pci_range_to_resource(&range, np, &pre_mem);
 			pre_mem.name = "PCIv3 prefetched mem";
 		}
-	}
 
-	if (!conf_mem.start || !io_mem.start ||
-	    !non_mem.start || !pre_mem.start) {
-		dev_err(&pdev->dev, "missing ranges in device node\n");
-		return -EINVAL;
+		if (ret < 0) {
+			dev_err(&pdev->dev, "missing ranges in device node\n");
+			return ret;
+		}
 	}
 
 	pci_v3.map_irq = of_irq_parse_and_map_pci;
diff --git a/arch/arm/mach-iop13xx/Makefile b/arch/arm/mach-iop13xx/Makefile
index cad015fee12f..a3d9260e335f 100644
--- a/arch/arm/mach-iop13xx/Makefile
+++ b/arch/arm/mach-iop13xx/Makefile
@@ -1,8 +1,3 @@
-obj-y			:=
-obj-m			:=
-obj-n			:=
-obj-			:=
-
 obj-$(CONFIG_ARCH_IOP13XX) += setup.o
 obj-$(CONFIG_ARCH_IOP13XX) += irq.o
 obj-$(CONFIG_ARCH_IOP13XX) += pci.o
diff --git a/arch/arm/mach-iop32x/Makefile b/arch/arm/mach-iop32x/Makefile
index cfdf8a137c2b..2d4010abb82f 100644
--- a/arch/arm/mach-iop32x/Makefile
+++ b/arch/arm/mach-iop32x/Makefile
@@ -3,9 +3,6 @@
 #
 
 obj-y			:= irq.o
-obj-m			:=
-obj-n			:=
-obj-			:=
 
 obj-$(CONFIG_MACH_GLANTANK) += glantank.o
 obj-$(CONFIG_ARCH_IQ80321) += iq80321.o
diff --git a/arch/arm/mach-iop33x/Makefile b/arch/arm/mach-iop33x/Makefile
index 90081d8c9d16..e95db30d81d5 100644
--- a/arch/arm/mach-iop33x/Makefile
+++ b/arch/arm/mach-iop33x/Makefile
@@ -3,9 +3,6 @@
 #
 
 obj-y			:= irq.o uart.o
-obj-m			:=
-obj-n			:=
-obj-			:=
 
 obj-$(CONFIG_ARCH_IQ80331) += iq80331.o
 obj-$(CONFIG_MACH_IQ80332) += iq80332.o
diff --git a/arch/arm/mach-ks8695/Makefile b/arch/arm/mach-ks8695/Makefile
index e370caf0c91b..8ecb7973ae54 100644
--- a/arch/arm/mach-ks8695/Makefile
+++ b/arch/arm/mach-ks8695/Makefile
@@ -4,9 +4,6 @@
 #
 
 obj-y				:= cpu.o irq.o time.o devices.o
-obj-m				:=
-obj-n				:=
-obj-				:=
 
 # PCI support is optional
 obj-$(CONFIG_PCI)		+= pci.o
diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c
index 8a70a51533fd..bbd8664d1bac 100644
--- a/arch/arm/mach-mvebu/pmsu.c
+++ b/arch/arm/mach-mvebu/pmsu.c
@@ -644,7 +644,7 @@ static int __init armada_xp_pmsu_cpufreq_init(void)
 		}
 	}
 
-	platform_device_register_simple("cpufreq-generic", -1, NULL, 0);
+	platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
 	return 0;
 }
 
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index a4d52c42a438..5fa3755261ce 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -1440,6 +1440,8 @@ static int gpmc_probe_nand_child(struct platform_device *pdev,
 				break;
 			}
 
+	gpmc_nand_data->flash_bbt = of_get_nand_on_flash_bbt(child);
+
 	val = of_get_nand_bus_width(child);
 	if (val == 16)
 		gpmc_nand_data->devsize = NAND_BUSWIDTH_16;
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index b8ad045bcb8d..03cbb16898a3 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -723,8 +723,16 @@ int __init omap_clk_init(void)
 	ti_clk_init_features();
 
 	ret = of_prcm_init();
-	if (!ret)
-		ret = omap_clk_soc_init();
+	if (ret)
+		return ret;
+
+	of_clk_init(NULL);
+
+	ti_dt_clk_init_retry_clks();
+
+	ti_dt_clockdomains_setup();
+
+	ret = omap_clk_soc_init();
 
 	return ret;
 }
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 828aee9ea6a8..58920bc8807b 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -282,7 +282,7 @@ static inline void omap_init_cpufreq(void)
 	if (!of_have_populated_dt())
 		devinfo.name = "omap-cpufreq";
 	else
-		devinfo.name = "cpufreq-cpu0";
+		devinfo.name = "cpufreq-dt";
 	platform_device_register_full(&devinfo);
 }
 
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index 74054b813600..ee2b5222eac0 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -525,8 +525,6 @@ int __init of_prcm_init(void)
 		memmap_index++;
 	}
 
-	ti_dt_clockdomains_setup();
-
 	return 0;
 }
 
diff --git a/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h b/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
index ee6ced1cea7f..f1dd62946b36 100644
--- a/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
+++ b/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
@@ -143,6 +143,16 @@
 #define CCCR_M_MASK	0x0060	/* Memory Frequency to Run Mode Frequency Multiplier */
 #define CCCR_L_MASK	0x001f	/* Crystal Frequency to Memory Frequency Multiplier */
 
+#define CCCR_CPDIS_BIT	(31)
+#define CCCR_PPDIS_BIT	(30)
+#define CCCR_LCD_26_BIT	(27)
+#define CCCR_A_BIT	(25)
+
+#define CCSR_N2_MASK	CCCR_N_MASK
+#define CCSR_M_MASK	CCCR_M_MASK
+#define CCSR_L_MASK	CCCR_L_MASK
+#define CCSR_N2_SHIFT	7
+
 #define CKEN_AC97CONF   (31)    /* AC97 Controller Configuration */
 #define CKEN_CAMERA	(24)	/* Camera Interface Clock Enable */
 #define CKEN_SSP1	(23)	/* SSP1 Unit Clock Enable */
diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c
index 9f6ec167902a..ad777b353bd5 100644
--- a/arch/arm/mach-pxa/lpd270.c
+++ b/arch/arm/mach-pxa/lpd270.c
@@ -416,17 +416,17 @@ static struct pxafb_mach_info *lpd270_lcd_to_use;
 
 static int __init lpd270_set_lcd(char *str)
 {
-	if (!strnicmp(str, "lq057q3dc02", 11)) {
+	if (!strncasecmp(str, "lq057q3dc02", 11)) {
 		lpd270_lcd_to_use = &sharp_lq057q3dc02;
-	} else if (!strnicmp(str, "lq121s1dg31", 11)) {
+	} else if (!strncasecmp(str, "lq121s1dg31", 11)) {
 		lpd270_lcd_to_use = &sharp_lq121s1dg31;
-	} else if (!strnicmp(str, "lq036q1da01", 11)) {
+	} else if (!strncasecmp(str, "lq036q1da01", 11)) {
 		lpd270_lcd_to_use = &sharp_lq036q1da01;
-	} else if (!strnicmp(str, "lq64d343", 8)) {
+	} else if (!strncasecmp(str, "lq64d343", 8)) {
 		lpd270_lcd_to_use = &sharp_lq64d343;
-	} else if (!strnicmp(str, "lq10d368", 8)) {
+	} else if (!strncasecmp(str, "lq10d368", 8)) {
 		lpd270_lcd_to_use = &sharp_lq10d368;
-	} else if (!strnicmp(str, "lq035q7db02-20", 14)) {
+	} else if (!strncasecmp(str, "lq035q7db02-20", 14)) {
 		lpd270_lcd_to_use = &sharp_lq035q7db02_20;
 	} else {
 		printk(KERN_INFO "lpd270: unknown lcd panel [%s]\n", str);
diff --git a/arch/arm/mach-rpc/Makefile b/arch/arm/mach-rpc/Makefile
index 992e28b4ae9a..2ebc6875aeb8 100644
--- a/arch/arm/mach-rpc/Makefile
+++ b/arch/arm/mach-rpc/Makefile
@@ -5,7 +5,3 @@
 # Object file lists.
 
 obj-y			:= dma.o ecard.o fiq.o irq.o riscpc.o time.o
-obj-m			:=
-obj-n			:=
-obj-			:=
-
diff --git a/arch/arm/mach-s3c24xx/Makefile b/arch/arm/mach-s3c24xx/Makefile
index 2235d0d3b38d..b92071638733 100644
--- a/arch/arm/mach-s3c24xx/Makefile
+++ b/arch/arm/mach-s3c24xx/Makefile
@@ -7,11 +7,6 @@
 #
 # Licensed under GPLv2
 
-obj-y				:=
-obj-m				:=
-obj-n				:=
-obj-				:=
-
 # core
 
 obj-y				+= common.o
diff --git a/arch/arm/mach-s3c64xx/Makefile b/arch/arm/mach-s3c64xx/Makefile
index 58069a702a43..12f67b61ca5f 100644
--- a/arch/arm/mach-s3c64xx/Makefile
+++ b/arch/arm/mach-s3c64xx/Makefile
@@ -5,11 +5,6 @@
 #
 # Licensed under GPLv2
 
-obj-y				:=
-obj-m				:=
-obj-n				:=
-obj-				:=
-
 # Core
 
 obj-y				+= common.o
diff --git a/arch/arm/mach-s3c64xx/common.c b/arch/arm/mach-s3c64xx/common.c
index 5c45aae675b6..16547f2641a3 100644
--- a/arch/arm/mach-s3c64xx/common.c
+++ b/arch/arm/mach-s3c64xx/common.c
@@ -440,8 +440,3 @@ void s3c64xx_restart(enum reboot_mode mode, const char *cmd)
 	/* if all else fails, or mode was for soft, jump to 0 */
 	soft_restart(0);
 }
-
-void __init s3c64xx_init_late(void)
-{
-	s3c64xx_pm_late_initcall();
-}
diff --git a/arch/arm/mach-s3c64xx/common.h b/arch/arm/mach-s3c64xx/common.h
index 7043e7a3a67e..9eb864412911 100644
--- a/arch/arm/mach-s3c64xx/common.h
+++ b/arch/arm/mach-s3c64xx/common.h
@@ -23,7 +23,6 @@ void s3c64xx_init_irq(u32 vic0, u32 vic1);
 void s3c64xx_init_io(struct map_desc *mach_desc, int size);
 
 void s3c64xx_restart(enum reboot_mode mode, const char *cmd);
-void s3c64xx_init_late(void);
 
 void s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f,
 	unsigned long xusbxti_f, bool is_s3c6400, void __iomem *reg_base);
@@ -52,12 +51,6 @@ extern void s3c6410_map_io(void);
 #define s3c6410_init NULL
 #endif
 
-#ifdef CONFIG_PM
-int __init s3c64xx_pm_late_initcall(void);
-#else
-static inline int s3c64xx_pm_late_initcall(void) { return 0; }
-#endif
-
 #ifdef CONFIG_S3C64XX_PL080
 extern struct pl08x_platform_data s3c64xx_dma0_plat_data;
 extern struct pl08x_platform_data s3c64xx_dma1_plat_data;
diff --git a/arch/arm/mach-s3c64xx/mach-anw6410.c b/arch/arm/mach-s3c64xx/mach-anw6410.c
index 60576dfbea8d..6224c67f5061 100644
--- a/arch/arm/mach-s3c64xx/mach-anw6410.c
+++ b/arch/arm/mach-s3c64xx/mach-anw6410.c
@@ -233,7 +233,6 @@ MACHINE_START(ANW6410, "A&W6410")
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= anw6410_map_io,
 	.init_machine	= anw6410_machine_init,
-	.init_late	= s3c64xx_init_late,
 	.init_time	= samsung_timer_init,
 	.restart	= s3c64xx_restart,
 MACHINE_END
diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c
index fe116334afda..10b913baab28 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410.c
@@ -857,7 +857,6 @@ MACHINE_START(WLF_CRAGG_6410, "Wolfson Cragganmore 6410")
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= crag6410_map_io,
 	.init_machine	= crag6410_machine_init,
-	.init_late	= s3c64xx_init_late,
 	.init_time	= samsung_timer_init,
 	.restart	= s3c64xx_restart,
 MACHINE_END
diff --git a/arch/arm/mach-s3c64xx/mach-hmt.c b/arch/arm/mach-s3c64xx/mach-hmt.c
index 19e8feb908fd..e4b087c58ee6 100644
--- a/arch/arm/mach-s3c64xx/mach-hmt.c
+++ b/arch/arm/mach-s3c64xx/mach-hmt.c
@@ -277,7 +277,6 @@ MACHINE_START(HMT, "Airgoo-HMT")
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= hmt_map_io,
 	.init_machine	= hmt_machine_init,
-	.init_late	= s3c64xx_init_late,
 	.init_time	= samsung_timer_init,
 	.restart	= s3c64xx_restart,
 MACHINE_END
diff --git a/arch/arm/mach-s3c64xx/mach-mini6410.c b/arch/arm/mach-s3c64xx/mach-mini6410.c
index 9cbc07602ef3..ab61af50bfb9 100644
--- a/arch/arm/mach-s3c64xx/mach-mini6410.c
+++ b/arch/arm/mach-s3c64xx/mach-mini6410.c
@@ -366,7 +366,6 @@ MACHINE_START(MINI6410, "MINI6410")
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= mini6410_map_io,
 	.init_machine	= mini6410_machine_init,
-	.init_late	= s3c64xx_init_late,
 	.init_time	= samsung_timer_init,
 	.restart	= s3c64xx_restart,
 MACHINE_END
diff --git a/arch/arm/mach-s3c64xx/mach-ncp.c b/arch/arm/mach-s3c64xx/mach-ncp.c
index 4bae7dc49eea..80cb1446f69f 100644
--- a/arch/arm/mach-s3c64xx/mach-ncp.c
+++ b/arch/arm/mach-s3c64xx/mach-ncp.c
@@ -103,7 +103,6 @@ MACHINE_START(NCP, "NCP")
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= ncp_map_io,
 	.init_machine	= ncp_machine_init,
-	.init_late	= s3c64xx_init_late,
 	.init_time	= samsung_timer_init,
 	.restart	= s3c64xx_restart,
 MACHINE_END
diff --git a/arch/arm/mach-s3c64xx/mach-real6410.c b/arch/arm/mach-s3c64xx/mach-real6410.c
index fbad2af1ef16..85fa9598b980 100644
--- a/arch/arm/mach-s3c64xx/mach-real6410.c
+++ b/arch/arm/mach-s3c64xx/mach-real6410.c
@@ -335,7 +335,6 @@ MACHINE_START(REAL6410, "REAL6410")
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= real6410_map_io,
 	.init_machine	= real6410_machine_init,
-	.init_late	= s3c64xx_init_late,
 	.init_time	= samsung_timer_init,
 	.restart	= s3c64xx_restart,
 MACHINE_END
diff --git a/arch/arm/mach-s3c64xx/mach-smartq5.c b/arch/arm/mach-s3c64xx/mach-smartq5.c
index dec4c08e834f..33224ab36fac 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq5.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq5.c
@@ -156,7 +156,6 @@ MACHINE_START(SMARTQ5, "SmartQ 5")
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= smartq_map_io,
 	.init_machine	= smartq5_machine_init,
-	.init_late	= s3c64xx_init_late,
 	.init_time	= samsung_timer_init,
 	.restart	= s3c64xx_restart,
 MACHINE_END
diff --git a/arch/arm/mach-s3c64xx/mach-smartq7.c b/arch/arm/mach-s3c64xx/mach-smartq7.c
index 27b322069c7d..fc7fece22fb0 100644
--- a/arch/arm/mach-s3c64xx/mach-smartq7.c
+++ b/arch/arm/mach-s3c64xx/mach-smartq7.c
@@ -172,7 +172,6 @@ MACHINE_START(SMARTQ7, "SmartQ 7")
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= smartq_map_io,
 	.init_machine	= smartq7_machine_init,
-	.init_late	= s3c64xx_init_late,
 	.init_time	= samsung_timer_init,
 	.restart	= s3c64xx_restart,
 MACHINE_END
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6400.c b/arch/arm/mach-s3c64xx/mach-smdk6400.c
index 910749768340..6f425126a735 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6400.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6400.c
@@ -92,7 +92,6 @@ MACHINE_START(SMDK6400, "SMDK6400")
 	.init_irq	= s3c6400_init_irq,
 	.map_io		= smdk6400_map_io,
 	.init_machine	= smdk6400_machine_init,
-	.init_late	= s3c64xx_init_late,
 	.init_time	= samsung_timer_init,
 	.restart	= s3c64xx_restart,
 MACHINE_END
diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c
index 1dc86d76b530..661eb662d051 100644
--- a/arch/arm/mach-s3c64xx/mach-smdk6410.c
+++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c
@@ -705,7 +705,6 @@ MACHINE_START(SMDK6410, "SMDK6410")
 	.init_irq	= s3c6410_init_irq,
 	.map_io		= smdk6410_map_io,
 	.init_machine	= smdk6410_machine_init,
-	.init_late	= s3c64xx_init_late,
 	.init_time	= samsung_timer_init,
 	.restart	= s3c64xx_restart,
 MACHINE_END
diff --git a/arch/arm/mach-s3c64xx/pm.c b/arch/arm/mach-s3c64xx/pm.c
index 6b37694fa335..aaf7bea4032f 100644
--- a/arch/arm/mach-s3c64xx/pm.c
+++ b/arch/arm/mach-s3c64xx/pm.c
@@ -347,10 +347,3 @@ static __init int s3c64xx_pm_initcall(void)
 	return 0;
 }
 arch_initcall(s3c64xx_pm_initcall);
-
-int __init s3c64xx_pm_late_initcall(void)
-{
-	pm_genpd_poweroff_unused();
-
-	return 0;
-}
diff --git a/arch/arm/mach-s5pv210/Makefile b/arch/arm/mach-s5pv210/Makefile
index 7dc2d0e25a83..72b9e9671507 100644
--- a/arch/arm/mach-s5pv210/Makefile
+++ b/arch/arm/mach-s5pv210/Makefile
@@ -7,11 +7,6 @@
 
 ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include
 
-obj-y				:=
-obj-m				:=
-obj-n				:=
-obj-				:=
-
 # Core
 
 obj-$(CONFIG_PM_SLEEP)		+= pm.o sleep.o
diff --git a/arch/arm/mach-sa1100/Makefile b/arch/arm/mach-sa1100/Makefile
index 2732eef48966..f1114d11fe13 100644
--- a/arch/arm/mach-sa1100/Makefile
+++ b/arch/arm/mach-sa1100/Makefile
@@ -4,9 +4,6 @@
 
 # Common support
 obj-y := clock.o generic.o irq.o time.o #nmi-oopser.o
-obj-m :=
-obj-n :=
-obj-  :=
 
 # Specific board support
 obj-$(CONFIG_SA1100_ASSABET)		+= assabet.o
diff --git a/arch/arm/mach-shmobile/board-koelsch-reference.c b/arch/arm/mach-shmobile/board-koelsch-reference.c
index 9db5e6774fb7..46aa540133d6 100644
--- a/arch/arm/mach-shmobile/board-koelsch-reference.c
+++ b/arch/arm/mach-shmobile/board-koelsch-reference.c
@@ -41,16 +41,15 @@ static struct rcar_du_encoder_data koelsch_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-shmobile/board-koelsch.c b/arch/arm/mach-shmobile/board-koelsch.c
index b7d5bc7659cd..7111b5c1d67b 100644
--- a/arch/arm/mach-shmobile/board-koelsch.c
+++ b/arch/arm/mach-shmobile/board-koelsch.c
@@ -63,16 +63,15 @@ static struct rcar_du_encoder_data koelsch_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
@@ -331,7 +330,6 @@ SDHI_REGULATOR(2, RCAR_GP_PIN(7, 19), RCAR_GP_PIN(2, 26));
 static struct sh_mobile_sdhi_info sdhi0_info __initdata = {
 	.tmio_caps	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
 			  MMC_CAP_POWER_OFF_CARD,
-	.tmio_caps2	= MMC_CAP2_NO_MULTI_READ,
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT,
 };
 
@@ -344,7 +342,6 @@ static struct resource sdhi0_resources[] __initdata = {
 static struct sh_mobile_sdhi_info sdhi1_info __initdata = {
 	.tmio_caps	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
 			  MMC_CAP_POWER_OFF_CARD,
-	.tmio_caps2	= MMC_CAP2_NO_MULTI_READ,
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT,
 };
 
@@ -357,7 +354,6 @@ static struct resource sdhi1_resources[] __initdata = {
 static struct sh_mobile_sdhi_info sdhi2_info __initdata = {
 	.tmio_caps	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
 			  MMC_CAP_POWER_OFF_CARD,
-	.tmio_caps2	= MMC_CAP2_NO_MULTI_READ,
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT |
 			  TMIO_MMC_WRPROTECT_DISABLE,
 };
diff --git a/arch/arm/mach-shmobile/board-lager-reference.c b/arch/arm/mach-shmobile/board-lager-reference.c
index 2a05c02bec39..bc4b48357dde 100644
--- a/arch/arm/mach-shmobile/board-lager-reference.c
+++ b/arch/arm/mach-shmobile/board-lager-reference.c
@@ -43,16 +43,15 @@ static struct rcar_du_encoder_data lager_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-shmobile/board-lager.c b/arch/arm/mach-shmobile/board-lager.c
index e1d8215da0b0..571327b1c942 100644
--- a/arch/arm/mach-shmobile/board-lager.c
+++ b/arch/arm/mach-shmobile/board-lager.c
@@ -99,16 +99,15 @@ static struct rcar_du_encoder_data lager_du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
@@ -630,7 +629,6 @@ static void __init lager_add_rsnd_device(void)
 static struct sh_mobile_sdhi_info sdhi0_info __initdata = {
 	.tmio_caps	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
 			  MMC_CAP_POWER_OFF_CARD,
-	.tmio_caps2	= MMC_CAP2_NO_MULTI_READ,
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT |
 			  TMIO_MMC_WRPROTECT_DISABLE,
 };
@@ -644,7 +642,6 @@ static struct resource sdhi0_resources[] __initdata = {
 static struct sh_mobile_sdhi_info sdhi2_info __initdata = {
 	.tmio_caps	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |
 			  MMC_CAP_POWER_OFF_CARD,
-	.tmio_caps2	= MMC_CAP2_NO_MULTI_READ,
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT |
 			  TMIO_MMC_WRPROTECT_DISABLE,
 };
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index e5cf4201e769..ce33d7825c49 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -192,16 +192,15 @@ static struct rcar_du_encoder_data du_encoders[] = {
 			.width_mm = 210,
 			.height_mm = 158,
 			.mode = {
-				.clock = 65000,
-				.hdisplay = 1024,
-				.hsync_start = 1048,
-				.hsync_end = 1184,
-				.htotal = 1344,
-				.vdisplay = 768,
-				.vsync_start = 771,
-				.vsync_end = 777,
-				.vtotal = 806,
-				.flags = 0,
+				.pixelclock = 65000000,
+				.hactive = 1024,
+				.hfront_porch = 20,
+				.hback_porch = 160,
+				.hsync_len = 136,
+				.vactive = 768,
+				.vfront_porch = 3,
+				.vback_porch = 29,
+				.vsync_len = 6,
 			},
 		},
 	},
diff --git a/arch/arm/mach-shmobile/cpufreq.c b/arch/arm/mach-shmobile/cpufreq.c
index 8a24b2be46ae..57fbff024dcd 100644
--- a/arch/arm/mach-shmobile/cpufreq.c
+++ b/arch/arm/mach-shmobile/cpufreq.c
@@ -12,6 +12,6 @@
 
 int __init shmobile_cpufreq_init(void)
 {
-	platform_device_register_simple("cpufreq-cpu0", -1, NULL, 0);
+	platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
 	return 0;
 }
diff --git a/arch/arm/mach-shmobile/pm-r8a7779.c b/arch/arm/mach-shmobile/pm-r8a7779.c
index 69f70b7f7fb2..82fe3d7f9662 100644
--- a/arch/arm/mach-shmobile/pm-r8a7779.c
+++ b/arch/arm/mach-shmobile/pm-r8a7779.c
@@ -87,7 +87,6 @@ static void r8a7779_init_pm_domain(struct r8a7779_pm_domain *r8a7779_pd)
 	genpd->dev_ops.stop = pm_clk_suspend;
 	genpd->dev_ops.start = pm_clk_resume;
 	genpd->dev_ops.active_wakeup = pd_active_wakeup;
-	genpd->dev_irq_safe = true;
 	genpd->power_off = pd_power_down;
 	genpd->power_on = pd_power_up;
 
diff --git a/arch/arm/mach-shmobile/pm-rmobile.c b/arch/arm/mach-shmobile/pm-rmobile.c
index a88079af7914..717e6413d29c 100644
--- a/arch/arm/mach-shmobile/pm-rmobile.c
+++ b/arch/arm/mach-shmobile/pm-rmobile.c
@@ -110,7 +110,6 @@ static void rmobile_init_pm_domain(struct rmobile_pm_domain *rmobile_pd)
 	genpd->dev_ops.stop		= pm_clk_suspend;
 	genpd->dev_ops.start		= pm_clk_resume;
 	genpd->dev_ops.active_wakeup	= rmobile_pd_active_wakeup;
-	genpd->dev_irq_safe		= true;
 	genpd->power_off		= rmobile_pd_power_down;
 	genpd->power_on			= rmobile_pd_power_up;
 	__rmobile_pd_power_up(rmobile_pd, false);
diff --git a/arch/arm/mach-u300/Makefile b/arch/arm/mach-u300/Makefile
index 3ec74ac95bc1..87d37de054b6 100644
--- a/arch/arm/mach-u300/Makefile
+++ b/arch/arm/mach-u300/Makefile
@@ -3,9 +3,6 @@
 #
 
 obj-y		:= core.o
-obj-m		:=
-obj-n		:=
-obj-		:=
 
 obj-$(CONFIG_MACH_U300_SPIDUMMY)  += dummyspichip.o
 obj-$(CONFIG_REGULATOR_AB3100)    += regulator.o
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index 613c476872eb..26f92c28d22b 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -110,7 +110,7 @@ static void __init zynq_init_late(void)
  */
 static void __init zynq_init_machine(void)
 {
-	struct platform_device_info devinfo = { .name = "cpufreq-cpu0", };
+	struct platform_device_info devinfo = { .name = "cpufreq-dt", };
 	struct soc_device_attribute *soc_dev_attr;
 	struct soc_device *soc_dev;
 	struct device *parent = NULL;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7a996aaa061e..c245d903927f 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -12,6 +12,7 @@
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <linux/genalloc.h>
 #include <linux/gfp.h>
 #include <linux/errno.h>
 #include <linux/list.h>
@@ -298,57 +299,29 @@ static void *
 __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
 	const void *caller)
 {
-	struct vm_struct *area;
-	unsigned long addr;
-
 	/*
 	 * DMA allocation can be mapped to user space, so lets
 	 * set VM_USERMAP flags too.
 	 */
-	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-				  caller);
-	if (!area)
-		return NULL;
-	addr = (unsigned long)area->addr;
-	area->phys_addr = __pfn_to_phys(page_to_pfn(page));
-
-	if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) {
-		vunmap((void *)addr);
-		return NULL;
-	}
-	return (void *)addr;
+	return dma_common_contiguous_remap(page, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP,
+			prot, caller);
 }
 
 static void __dma_free_remap(void *cpu_addr, size_t size)
 {
-	unsigned int flags = VM_ARM_DMA_CONSISTENT | VM_USERMAP;
-	struct vm_struct *area = find_vm_area(cpu_addr);
-	if (!area || (area->flags & flags) != flags) {
-		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
-		return;
-	}
-	unmap_kernel_range((unsigned long)cpu_addr, size);
-	vunmap(cpu_addr);
+	dma_common_free_remap(cpu_addr, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
 }
 
 #define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256K
+static struct gen_pool *atomic_pool;
 
-struct dma_pool {
-	size_t size;
-	spinlock_t lock;
-	unsigned long *bitmap;
-	unsigned long nr_pages;
-	void *vaddr;
-	struct page **pages;
-};
-
-static struct dma_pool atomic_pool = {
-	.size = DEFAULT_DMA_COHERENT_POOL_SIZE,
-};
+static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE;
 
 static int __init early_coherent_pool(char *p)
 {
-	atomic_pool.size = memparse(p, &p);
+	atomic_pool_size = memparse(p, &p);
 	return 0;
 }
 early_param("coherent_pool", early_coherent_pool);
@@ -358,14 +331,14 @@ void __init init_dma_coherent_pool_size(unsigned long size)
 	/*
 	 * Catch any attempt to set the pool size too late.
 	 */
-	BUG_ON(atomic_pool.vaddr);
+	BUG_ON(atomic_pool);
 
 	/*
 	 * Set architecture specific coherent pool size only if
 	 * it has not been changed by kernel command line parameter.
 	 */
-	if (atomic_pool.size == DEFAULT_DMA_COHERENT_POOL_SIZE)
-		atomic_pool.size = size;
+	if (atomic_pool_size == DEFAULT_DMA_COHERENT_POOL_SIZE)
+		atomic_pool_size = size;
 }
 
 /*
@@ -373,52 +346,44 @@ void __init init_dma_coherent_pool_size(unsigned long size)
  */
 static int __init atomic_pool_init(void)
 {
-	struct dma_pool *pool = &atomic_pool;
 	pgprot_t prot = pgprot_dmacoherent(PAGE_KERNEL);
 	gfp_t gfp = GFP_KERNEL | GFP_DMA;
-	unsigned long nr_pages = pool->size >> PAGE_SHIFT;
-	unsigned long *bitmap;
 	struct page *page;
-	struct page **pages;
 	void *ptr;
-	int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long);
 
-	bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-	if (!bitmap)
-		goto no_bitmap;
-
-	pages = kzalloc(nr_pages * sizeof(struct page *), GFP_KERNEL);
-	if (!pages)
-		goto no_pages;
+	atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
+	if (!atomic_pool)
+		goto out;
 
 	if (dev_get_cma_area(NULL))
-		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
-					      atomic_pool_init);
+		ptr = __alloc_from_contiguous(NULL, atomic_pool_size, prot,
+					      &page, atomic_pool_init);
 	else
-		ptr = __alloc_remap_buffer(NULL, pool->size, gfp, prot, &page,
-					   atomic_pool_init);
+		ptr = __alloc_remap_buffer(NULL, atomic_pool_size, gfp, prot,
+					   &page, atomic_pool_init);
 	if (ptr) {
-		int i;
-
-		for (i = 0; i < nr_pages; i++)
-			pages[i] = page + i;
-
-		spin_lock_init(&pool->lock);
-		pool->vaddr = ptr;
-		pool->pages = pages;
-		pool->bitmap = bitmap;
-		pool->nr_pages = nr_pages;
-		pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n",
-		       (unsigned)pool->size / 1024);
+		int ret;
+
+		ret = gen_pool_add_virt(atomic_pool, (unsigned long)ptr,
+					page_to_phys(page),
+					atomic_pool_size, -1);
+		if (ret)
+			goto destroy_genpool;
+
+		gen_pool_set_algo(atomic_pool,
+				gen_pool_first_fit_order_align,
+				(void *)PAGE_SHIFT);
+		pr_info("DMA: preallocated %zd KiB pool for atomic coherent allocations\n",
+		       atomic_pool_size / 1024);
 		return 0;
 	}
 
-	kfree(pages);
-no_pages:
-	kfree(bitmap);
-no_bitmap:
-	pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
-	       (unsigned)pool->size / 1024);
+destroy_genpool:
+	gen_pool_destroy(atomic_pool);
+	atomic_pool = NULL;
+out:
+	pr_err("DMA: failed to allocate %zx KiB pool for atomic coherent allocation\n",
+	       atomic_pool_size / 1024);
 	return -ENOMEM;
 }
 /*
@@ -522,76 +487,36 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 
 static void *__alloc_from_pool(size_t size, struct page **ret_page)
 {
-	struct dma_pool *pool = &atomic_pool;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned int pageno;
-	unsigned long flags;
+	unsigned long val;
 	void *ptr = NULL;
-	unsigned long align_mask;
 
-	if (!pool->vaddr) {
+	if (!atomic_pool) {
 		WARN(1, "coherent pool not initialised!\n");
 		return NULL;
 	}
 
-	/*
-	 * Align the region allocation - allocations from pool are rather
-	 * small, so align them to their order in pages, minimum is a page
-	 * size. This helps reduce fragmentation of the DMA space.
-	 */
-	align_mask = (1 << get_order(size)) - 1;
-
-	spin_lock_irqsave(&pool->lock, flags);
-	pageno = bitmap_find_next_zero_area(pool->bitmap, pool->nr_pages,
-					    0, count, align_mask);
-	if (pageno < pool->nr_pages) {
-		bitmap_set(pool->bitmap, pageno, count);
-		ptr = pool->vaddr + PAGE_SIZE * pageno;
-		*ret_page = pool->pages[pageno];
-	} else {
-		pr_err_once("ERROR: %u KiB atomic DMA coherent pool is too small!\n"
-			    "Please increase it with coherent_pool= kernel parameter!\n",
-			    (unsigned)pool->size / 1024);
+	val = gen_pool_alloc(atomic_pool, size);
+	if (val) {
+		phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
+
+		*ret_page = phys_to_page(phys);
+		ptr = (void *)val;
 	}
-	spin_unlock_irqrestore(&pool->lock, flags);
 
 	return ptr;
 }
 
 static bool __in_atomic_pool(void *start, size_t size)
 {
-	struct dma_pool *pool = &atomic_pool;
-	void *end = start + size;
-	void *pool_start = pool->vaddr;
-	void *pool_end = pool->vaddr + pool->size;
-
-	if (start < pool_start || start >= pool_end)
-		return false;
-
-	if (end <= pool_end)
-		return true;
-
-	WARN(1, "Wrong coherent size(%p-%p) from atomic pool(%p-%p)\n",
-	     start, end - 1, pool_start, pool_end - 1);
-
-	return false;
+	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
 }
 
 static int __free_from_pool(void *start, size_t size)
 {
-	struct dma_pool *pool = &atomic_pool;
-	unsigned long pageno, count;
-	unsigned long flags;
-
 	if (!__in_atomic_pool(start, size))
 		return 0;
 
-	pageno = (start - pool->vaddr) >> PAGE_SHIFT;
-	count = size >> PAGE_SHIFT;
-
-	spin_lock_irqsave(&pool->lock, flags);
-	bitmap_clear(pool->bitmap, pageno, count);
-	spin_unlock_irqrestore(&pool->lock, flags);
+	gen_pool_free(atomic_pool, (unsigned long)start, size);
 
 	return 1;
 }
@@ -1271,29 +1196,8 @@ static void *
 __iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
 		    const void *caller)
 {
-	unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct vm_struct *area;
-	unsigned long p;
-
-	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-				  caller);
-	if (!area)
-		return NULL;
-
-	area->pages = pages;
-	area->nr_pages = nr_pages;
-	p = (unsigned long)area->addr;
-
-	for (i = 0; i < nr_pages; i++) {
-		phys_addr_t phys = __pfn_to_phys(page_to_pfn(pages[i]));
-		if (ioremap_page_range(p, p + PAGE_SIZE, phys, prot))
-			goto err;
-		p += PAGE_SIZE;
-	}
-	return area->addr;
-err:
-	unmap_kernel_range((unsigned long)area->addr, size);
-	vunmap(area->addr);
+	return dma_common_pages_remap(pages, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller);
 	return NULL;
 }
 
@@ -1355,11 +1259,13 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t si
 
 static struct page **__atomic_get_pages(void *addr)
 {
-	struct dma_pool *pool = &atomic_pool;
-	struct page **pages = pool->pages;
-	int offs = (addr - pool->vaddr) >> PAGE_SHIFT;
+	struct page *page;
+	phys_addr_t phys;
+
+	phys = gen_pool_virt_to_phys(atomic_pool, (unsigned long)addr);
+	page = phys_to_page(phys);
 
-	return pages + offs;
+	return (struct page **)page;
 }
 
 static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
@@ -1501,8 +1407,8 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	}
 
 	if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
-		unmap_kernel_range((unsigned long)cpu_addr, size);
-		vunmap(cpu_addr);
+		dma_common_free_remap(cpu_addr, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
 	}
 
 	__iommu_remove_mapping(dev, handle, size);
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 43d54f5b26b9..265b836b3bd1 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -400,3 +400,18 @@ void __flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned l
 	 */
 	__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
 }
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp)
+{
+	pmd_t pmd = pmd_mksplitting(*pmdp);
+	VM_BUG_ON(address & ~PMD_MASK);
+	set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+
+	/* dummy IPI to serialise against fast_gup */
+	kick_all_cpus_sync();
+}
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 9221645dd192..92bba32d9230 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -322,7 +322,7 @@ void __init arm_memblock_init(const struct machine_desc *mdesc)
 	 * reserve memory for DMA contigouos allocations,
 	 * must come from DMA area inside low memory
 	 */
-	dma_contiguous_reserve(min(arm_dma_limit, arm_lowmem_limit));
+	dma_contiguous_reserve(arm_dma_limit);
 
 	arm_memblock_steal_permitted = false;
 	memblock_dump_all();
diff --git a/arch/arm/plat-iop/Makefile b/arch/arm/plat-iop/Makefile
index 224e56c6049b..f2af203d601f 100644
--- a/arch/arm/plat-iop/Makefile
+++ b/arch/arm/plat-iop/Makefile
@@ -2,8 +2,6 @@
 # Makefile for the linux kernel.
 #
 
-obj-y :=
-
 # IOP32X
 obj-$(CONFIG_ARCH_IOP32X) += i2c.o
 obj-$(CONFIG_ARCH_IOP32X) += pci.o
@@ -27,7 +25,3 @@ obj-$(CONFIG_ARCH_IOP33X) += restart.o
 # IOP13XX
 obj-$(CONFIG_ARCH_IOP13XX) += cp6.o
 obj-$(CONFIG_ARCH_IOP13XX) += time.o
-
-obj-m                  :=
-obj-n                  :=
-obj-                   :=
diff --git a/arch/arm/plat-omap/Makefile b/arch/arm/plat-omap/Makefile
index 0b01b68fd033..97a50e8883f9 100644
--- a/arch/arm/plat-omap/Makefile
+++ b/arch/arm/plat-omap/Makefile
@@ -6,9 +6,6 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-omap/include
 
 # Common support
 obj-y := sram.o dma.o counter_32k.o
-obj-m :=
-obj-n :=
-obj-  :=
 
 # omap_device support (OMAP2+ only at the moment)
 
diff --git a/arch/arm/plat-samsung/Makefile b/arch/arm/plat-samsung/Makefile
index 5fe175017f07..f0a008496993 100644
--- a/arch/arm/plat-samsung/Makefile
+++ b/arch/arm/plat-samsung/Makefile
@@ -6,11 +6,6 @@
 
 ccflags-$(CONFIG_ARCH_MULTI_V7) += -I$(srctree)/$(src)/include
 
-obj-y				:=
-obj-m				:=
-obj-n				:= dummy.o
-obj-				:=
-
 # Objects we always build independent of SoC choice
 
 obj-y				+= init.o cpu.o
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index d0543d90db8d..ac9afde76dea 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -18,6 +18,7 @@ config ARM64
 	select COMMON_CLK
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS
+	select GENERIC_ALLOCATOR
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
 	select GENERIC_CPU_AUTOPROBE
@@ -30,6 +31,7 @@ config ARM64
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
+	select HANDLE_DOMAIN_IRQ
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
@@ -55,6 +57,7 @@ config ARM64
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_RCU_TABLE_FREE
 	select HAVE_SYSCALL_TRACEPOINTS
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
@@ -82,7 +85,7 @@ config MMU
 	def_bool y
 
 config NO_IOPORT_MAP
-	def_bool y
+	def_bool y if !PCI
 
 config STACKTRACE_SUPPORT
 	def_bool y
@@ -108,6 +111,9 @@ config GENERIC_CALIBRATE_DELAY
 config ZONE_DMA
 	def_bool y
 
+config HAVE_GENERIC_RCU_GUP
+	def_bool y
+
 config ARCH_DMA_ADDR_T_64BIT
 	def_bool y
 
@@ -162,6 +168,26 @@ menu "Bus support"
 config ARM_AMBA
 	bool
 
+config PCI
+	bool "PCI support"
+	help
+	  This feature enables support for PCI bus system. If you say Y
+	  here, the kernel will include drivers and infrastructure code
+	  to support PCI bus devices.
+
+config PCI_DOMAINS
+	def_bool PCI
+
+config PCI_DOMAINS_GENERIC
+	def_bool PCI
+
+config PCI_SYSCALL
+	def_bool PCI
+
+source "drivers/pci/Kconfig"
+source "drivers/pci/pcie/Kconfig"
+source "drivers/pci/hotplug/Kconfig"
+
 endmenu
 
 menu "Kernel Features"
@@ -323,7 +349,7 @@ config XEN_DOM0
 	depends on XEN
 
 config XEN
-	bool "Xen guest support on ARM64 (EXPERIMENTAL)"
+	bool "Xen guest support on ARM64"
 	depends on ARM64 && OF
 	select SWIOTLB_XEN
 	help
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 59c86b6b3052..20901ffed182 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -30,8 +30,6 @@ AS		+= -EL
 LD		+= -EL
 endif
 
-comma = ,
-
 CHECKFLAGS	+= -D__aarch64__
 
 # Default value
diff --git a/arch/arm64/boot/dts/apm-mustang.dts b/arch/arm64/boot/dts/apm-mustang.dts
index 71a1489619c2..2e25de0800b9 100644
--- a/arch/arm64/boot/dts/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm-mustang.dts
@@ -25,6 +25,14 @@
 	};
 };
 
+&pcie0clk {
+	status = "ok";
+};
+
+&pcie0 {
+	status = "ok";
+};
+
 &serial0 {
 	status = "ok";
 };
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
index f45bbfe116d8..295c72d52a1f 100644
--- a/arch/arm64/boot/dts/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -302,6 +302,171 @@
 				enable-mask = <0x10>;
 				clock-output-names = "rngpkaclk";
 			};
+
+			pcie0clk: pcie0clk@1f2bc000 {
+				status = "disabled";
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f2bc000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "pcie0clk";
+			};
+
+			pcie1clk: pcie1clk@1f2cc000 {
+				status = "disabled";
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f2cc000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "pcie1clk";
+			};
+
+			pcie2clk: pcie2clk@1f2dc000 {
+				status = "disabled";
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f2dc000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "pcie2clk";
+			};
+
+			pcie3clk: pcie3clk@1f50c000 {
+				status = "disabled";
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f50c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "pcie3clk";
+			};
+
+			pcie4clk: pcie4clk@1f51c000 {
+				status = "disabled";
+				compatible = "apm,xgene-device-clock";
+				#clock-cells = <1>;
+				clocks = <&socplldiv2 0>;
+				reg = <0x0 0x1f51c000 0x0 0x1000>;
+				reg-names = "csr-reg";
+				clock-output-names = "pcie4clk";
+			};
+		};
+
+		pcie0: pcie@1f2b0000 {
+			status = "disabled";
+			device_type = "pci";
+			compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			reg = < 0x00 0x1f2b0000 0x0 0x00010000   /* Controller registers */
+				0xe0 0xd0000000 0x0 0x00040000>; /* PCI config space */
+			reg-names = "csr", "cfg";
+			ranges = <0x01000000 0x00 0x00000000 0xe0 0x10000000 0x00 0x00010000   /* io */
+				  0x02000000 0x00 0x80000000 0xe1 0x80000000 0x00 0x80000000>; /* mem */
+			dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
+				      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xc2 0x1
+					 0x0 0x0 0x0 0x2 &gic 0x0 0xc3 0x1
+					 0x0 0x0 0x0 0x3 &gic 0x0 0xc4 0x1
+					 0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>;
+			dma-coherent;
+			clocks = <&pcie0clk 0>;
+		};
+
+		pcie1: pcie@1f2c0000 {
+			status = "disabled";
+			device_type = "pci";
+			compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			reg = < 0x00 0x1f2c0000 0x0 0x00010000   /* Controller registers */
+				0xd0 0xd0000000 0x0 0x00040000>; /* PCI config space */
+			reg-names = "csr", "cfg";
+			ranges = <0x01000000 0x0 0x00000000 0xd0 0x10000000 0x00 0x00010000   /* io  */
+				  0x02000000 0x0 0x80000000 0xd1 0x80000000 0x00 0x80000000>; /* mem */
+			dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
+				      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xc8 0x1
+					 0x0 0x0 0x0 0x2 &gic 0x0 0xc9 0x1
+					 0x0 0x0 0x0 0x3 &gic 0x0 0xca 0x1
+					 0x0 0x0 0x0 0x4 &gic 0x0 0xcb 0x1>;
+			dma-coherent;
+			clocks = <&pcie1clk 0>;
+		};
+
+		pcie2: pcie@1f2d0000 {
+			status = "disabled";
+			device_type = "pci";
+			compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			reg =  < 0x00 0x1f2d0000 0x0 0x00010000   /* Controller registers */
+				 0x90 0xd0000000 0x0 0x00040000>; /* PCI config space */
+			reg-names = "csr", "cfg";
+			ranges = <0x01000000 0x0 0x00000000 0x90 0x10000000 0x0 0x00010000   /* io  */
+				  0x02000000 0x0 0x80000000 0x91 0x80000000 0x0 0x80000000>; /* mem */
+			dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
+				      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xce 0x1
+					 0x0 0x0 0x0 0x2 &gic 0x0 0xcf 0x1
+					 0x0 0x0 0x0 0x3 &gic 0x0 0xd0 0x1
+					 0x0 0x0 0x0 0x4 &gic 0x0 0xd1 0x1>;
+			dma-coherent;
+			clocks = <&pcie2clk 0>;
+		};
+
+		pcie3: pcie@1f500000 {
+			status = "disabled";
+			device_type = "pci";
+			compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			reg = < 0x00 0x1f500000 0x0 0x00010000   /* Controller registers */
+				0xa0 0xd0000000 0x0 0x00040000>; /* PCI config space */
+			reg-names = "csr", "cfg";
+			ranges = <0x01000000 0x0 0x00000000 0xa0 0x10000000 0x0 0x00010000   /* io   */
+				  0x02000000 0x0 0x80000000 0xa1 0x80000000 0x0 0x80000000>; /* mem  */
+			dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
+				      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xd4 0x1
+					 0x0 0x0 0x0 0x2 &gic 0x0 0xd5 0x1
+					 0x0 0x0 0x0 0x3 &gic 0x0 0xd6 0x1
+					 0x0 0x0 0x0 0x4 &gic 0x0 0xd7 0x1>;
+			dma-coherent;
+			clocks = <&pcie3clk 0>;
+		};
+
+		pcie4: pcie@1f510000 {
+			status = "disabled";
+			device_type = "pci";
+			compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			reg = < 0x00 0x1f510000 0x0 0x00010000   /* Controller registers */
+				0xc0 0xd0000000 0x0 0x00200000>; /* PCI config space */
+			reg-names = "csr", "cfg";
+			ranges = <0x01000000 0x0 0x00000000 0xc0 0x10000000 0x0 0x00010000   /* io  */
+				  0x02000000 0x0 0x80000000 0xc1 0x80000000 0x0 0x80000000>; /* mem */
+			dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
+				      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xda 0x1
+					 0x0 0x0 0x0 0x2 &gic 0x0 0xdb 0x1
+					 0x0 0x0 0x0 0x3 &gic 0x0 0xdc 0x1
+					 0x0 0x0 0x0 0x4 &gic 0x0 0xdd 0x1>;
+			dma-coherent;
+			clocks = <&pcie4clk 0>;
 		};
 
 		serial0: serial@1c020000 {
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 0b3fcf86e6ba..dc770bd4f5a5 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -9,8 +9,9 @@ generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
-generic-y += emergency-restart.h
+generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
+generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += ftrace.h
 generic-y += hash.h
@@ -29,6 +30,7 @@ generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += pci.h
+generic-y += pci-bridge.h
 generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 9400596a0f39..f19097134b02 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -104,37 +104,6 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 	asm volatile("msr	cntkctl_el1, %0" : : "r" (cntkctl));
 }
 
-static inline void arch_counter_set_user_access(void)
-{
-	u32 cntkctl = arch_timer_get_cntkctl();
-
-	/* Disable user access to the timers and the physical counter */
-	/* Also disable virtual event stream */
-	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
-			| ARCH_TIMER_USR_VT_ACCESS_EN
-			| ARCH_TIMER_VIRT_EVT_EN
-			| ARCH_TIMER_USR_PCT_ACCESS_EN);
-
-	/* Enable user access to the virtual counter */
-	cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
-
-	arch_timer_set_cntkctl(cntkctl);
-}
-
-static inline void arch_timer_evtstrm_enable(int divider)
-{
-	u32 cntkctl = arch_timer_get_cntkctl();
-	cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK;
-	/* Set the divider and enable virtual event stream */
-	cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
-			| ARCH_TIMER_VIRT_EVT_EN;
-	arch_timer_set_cntkctl(cntkctl);
-	elf_hwcap |= HWCAP_EVTSTRM;
-#ifdef CONFIG_COMPAT
-	compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
-#endif
-}
-
 static inline u64 arch_counter_get_cntvct(void)
 {
 	u64 cval;
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 65f1569ac96e..7047051ded40 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -35,7 +35,7 @@
  * strex/ldrex monitor on some implementations. The reason we can use it for
  * atomic_set() is the clrex or dummy strex done on every exception return.
  */
-#define atomic_read(v)	(*(volatile int *)&(v)->counter)
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
 #define atomic_set(v,i)	(((v)->counter) = (i))
 
 /*
@@ -43,69 +43,51 @@
  * store exclusive to ensure that these are atomic.  We may loop
  * to ensure that the update happens.
  */
-static inline void atomic_add(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
-
-	asm volatile("// atomic_add\n"
-"1:	ldxr	%w0, %2\n"
-"	add	%w0, %w0, %w3\n"
-"	stxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i));
-}
-
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
-
-	asm volatile("// atomic_add_return\n"
-"1:	ldxr	%w0, %2\n"
-"	add	%w0, %w0, %w3\n"
-"	stlxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "memory");
-
-	smp_mb();
-	return result;
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
 
-	asm volatile("// atomic_sub\n"
-"1:	ldxr	%w0, %2\n"
-"	sub	%w0, %w0, %w3\n"
-"	stxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i));
+#define ATOMIC_OP(op, asm_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "\n"				\
+"1:	ldxr	%w0, %2\n"						\
+"	" #asm_op "	%w0, %w0, %w3\n"				\
+"	stxr	%w1, %w0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i));							\
+}									\
+
+#define ATOMIC_OP_RETURN(op, asm_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "_return\n"			\
+"1:	ldxr	%w0, %2\n"						\
+"	" #asm_op "	%w0, %w0, %w3\n"				\
+"	stlxr	%w1, %w0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i)							\
+	: "memory");							\
+									\
+	smp_mb();							\
+	return result;							\
 }
 
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
+#define ATOMIC_OPS(op, asm_op)						\
+	ATOMIC_OP(op, asm_op)						\
+	ATOMIC_OP_RETURN(op, asm_op)
 
-	asm volatile("// atomic_sub_return\n"
-"1:	ldxr	%w0, %2\n"
-"	sub	%w0, %w0, %w3\n"
-"	stlxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "memory");
+ATOMIC_OPS(add, add)
+ATOMIC_OPS(sub, sub)
 
-	smp_mb();
-	return result;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 {
@@ -157,72 +139,53 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
  */
 #define ATOMIC64_INIT(i) { (i) }
 
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 #define atomic64_set(v,i)	(((v)->counter) = (i))
 
-static inline void atomic64_add(u64 i, atomic64_t *v)
-{
-	long result;
-	unsigned long tmp;
-
-	asm volatile("// atomic64_add\n"
-"1:	ldxr	%0, %2\n"
-"	add	%0, %0, %3\n"
-"	stxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i));
+#define ATOMIC64_OP(op, asm_op)						\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	long result;							\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_" #op "\n"				\
+"1:	ldxr	%0, %2\n"						\
+"	" #asm_op "	%0, %0, %3\n"					\
+"	stxr	%w1, %0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i));							\
+}									\
+
+#define ATOMIC64_OP_RETURN(op, asm_op)					\
+static inline long atomic64_##op##_return(long i, atomic64_t *v)	\
+{									\
+	long result;							\
+	unsigned long tmp;						\
+									\
+	asm volatile("// atomic64_" #op "_return\n"			\
+"1:	ldxr	%0, %2\n"						\
+"	" #asm_op "	%0, %0, %3\n"					\
+"	stlxr	%w1, %0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i)							\
+	: "memory");							\
+									\
+	smp_mb();							\
+	return result;							\
 }
 
-static inline long atomic64_add_return(long i, atomic64_t *v)
-{
-	long result;
-	unsigned long tmp;
+#define ATOMIC64_OPS(op, asm_op)					\
+	ATOMIC64_OP(op, asm_op)						\
+	ATOMIC64_OP_RETURN(op, asm_op)
 
-	asm volatile("// atomic64_add_return\n"
-"1:	ldxr	%0, %2\n"
-"	add	%0, %0, %3\n"
-"	stlxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "memory");
+ATOMIC64_OPS(add, add)
+ATOMIC64_OPS(sub, sub)
 
-	smp_mb();
-	return result;
-}
-
-static inline void atomic64_sub(u64 i, atomic64_t *v)
-{
-	long result;
-	unsigned long tmp;
-
-	asm volatile("// atomic64_sub\n"
-"1:	ldxr	%0, %2\n"
-"	sub	%0, %0, %3\n"
-"	stxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i));
-}
-
-static inline long atomic64_sub_return(long i, atomic64_t *v)
-{
-	long result;
-	unsigned long tmp;
-
-	asm volatile("// atomic64_sub_return\n"
-"1:	ldxr	%0, %2\n"
-"	sub	%0, %0, %3\n"
-"	stlxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "memory");
-
-	smp_mb();
-	return result;
-}
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
 
 static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new)
 {
diff --git a/arch/arm64/include/asm/dma-contiguous.h b/arch/arm64/include/asm/dma-contiguous.h
deleted file mode 100644
index 14c4c0ca7f2a..000000000000
--- a/arch/arm64/include/asm/dma-contiguous.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright (c) 2013, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef _ASM_DMA_CONTIGUOUS_H
-#define _ASM_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-#ifdef CONFIG_DMA_CMA
-
-#include <linux/types.h>
-
-static inline void
-dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
-
-#endif
-#endif
-
-#endif
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 0be67821f9ce..e8a3268a891c 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -47,8 +47,6 @@ static inline void ack_bad_irq(unsigned int irq)
 	irq_err_count++;
 }
 
-extern void handle_IRQ(unsigned int, struct pt_regs *);
-
 /*
  * No arch-specific IRQ flags.
  */
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index f771e8bcad4a..79f1d519221f 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -121,7 +121,8 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 /*
  *  I/O port access primitives.
  */
-#define IO_SPACE_LIMIT		0xffff
+#define arch_has_dev_port()	(1)
+#define IO_SPACE_LIMIT		(SZ_32M - 1)
 #define PCI_IOBASE		((void __iomem *)(MODULES_VADDR - SZ_32M))
 
 static inline u8 inb(unsigned long addr)
diff --git a/arch/arm64/include/asm/irq_work.h b/arch/arm64/include/asm/irq_work.h
new file mode 100644
index 000000000000..8e24ef3f7c82
--- /dev/null
+++ b/arch/arm64/include/asm/irq_work.h
@@ -0,0 +1,11 @@
+#ifndef __ASM_IRQ_WORK_H
+#define __ASM_IRQ_WORK_H
+
+#include <asm/smp.h>
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return !!__smp_cross_call;
+}
+
+#endif /* __ASM_IRQ_WORK_H */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index a030d163840b..0caf7a59f6a1 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -41,6 +41,18 @@
  */
 #define TRAMPOLINE_VA		(HYP_PAGE_OFFSET_MASK & PAGE_MASK)
 
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation
+ * levels in addition to the PGD and potentially the PUD which are
+ * pre-allocated (we pre-allocate the fake PGD and the PUD when the Stage-2
+ * tables use one level of tables less than the kernel.
+ */
+#ifdef CONFIG_ARM64_64K_PAGES
+#define KVM_MMU_CACHE_MIN_PAGES	1
+#else
+#define KVM_MMU_CACHE_MIN_PAGES	2
+#endif
+
 #ifdef __ASSEMBLY__
 
 /*
@@ -53,6 +65,7 @@
 
 #else
 
+#include <asm/pgalloc.h>
 #include <asm/cachetype.h>
 #include <asm/cacheflush.h>
 
@@ -65,10 +78,6 @@
 #define KVM_PHYS_SIZE	(1UL << KVM_PHYS_SHIFT)
 #define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1UL)
 
-/* Make sure we get the right size, and thus the right alignment */
-#define PTRS_PER_S2_PGD (1 << (KVM_PHYS_SHIFT - PGDIR_SHIFT))
-#define S2_PGD_ORDER	get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
-
 int create_hyp_mappings(void *from, void *to);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_boot_hyp_pgd(void);
@@ -77,7 +86,7 @@ void free_hyp_pgds(void);
 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
-			  phys_addr_t pa, unsigned long size);
+			  phys_addr_t pa, unsigned long size, bool writable);
 
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
 
@@ -93,6 +102,7 @@ void kvm_clear_hyp_idmap(void);
 #define	kvm_set_pmd(pmdp, pmd)		set_pmd(pmdp, pmd)
 
 static inline void kvm_clean_pgd(pgd_t *pgd) {}
+static inline void kvm_clean_pmd(pmd_t *pmd) {}
 static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
 static inline void kvm_clean_pte(pte_t *pte) {}
 static inline void kvm_clean_pte_entry(pte_t *pte) {}
@@ -111,19 +121,116 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 #define kvm_pud_addr_end(addr, end)	pud_addr_end(addr, end)
 #define kvm_pmd_addr_end(addr, end)	pmd_addr_end(addr, end)
 
+/*
+ * In the case where PGDIR_SHIFT is larger than KVM_PHYS_SHIFT, we can address
+ * the entire IPA input range with a single pgd entry, and we would only need
+ * one pgd entry.  Note that in this case, the pgd is actually not used by
+ * the MMU for Stage-2 translations, but is merely a fake pgd used as a data
+ * structure for the kernel pgtable macros to work.
+ */
+#if PGDIR_SHIFT > KVM_PHYS_SHIFT
+#define PTRS_PER_S2_PGD_SHIFT	0
+#else
+#define PTRS_PER_S2_PGD_SHIFT	(KVM_PHYS_SHIFT - PGDIR_SHIFT)
+#endif
+#define PTRS_PER_S2_PGD		(1 << PTRS_PER_S2_PGD_SHIFT)
+#define S2_PGD_ORDER		get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
+
+/*
+ * If we are concatenating first level stage-2 page tables, we would have less
+ * than or equal to 16 pointers in the fake PGD, because that's what the
+ * architecture allows.  In this case, (4 - CONFIG_ARM64_PGTABLE_LEVELS)
+ * represents the first level for the host, and we add 1 to go to the next
+ * level (which uses contatenation) for the stage-2 tables.
+ */
+#if PTRS_PER_S2_PGD <= 16
+#define KVM_PREALLOC_LEVEL	(4 - CONFIG_ARM64_PGTABLE_LEVELS + 1)
+#else
+#define KVM_PREALLOC_LEVEL	(0)
+#endif
+
+/**
+ * kvm_prealloc_hwpgd - allocate inital table for VTTBR
+ * @kvm:	The KVM struct pointer for the VM.
+ * @pgd:	The kernel pseudo pgd
+ *
+ * When the kernel uses more levels of page tables than the guest, we allocate
+ * a fake PGD and pre-populate it to point to the next-level page table, which
+ * will be the real initial page table pointed to by the VTTBR.
+ *
+ * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and
+ * the kernel will use folded pud.  When KVM_PREALLOC_LEVEL==1, we
+ * allocate 2 consecutive PUD pages.
+ */
+static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
+{
+	unsigned int i;
+	unsigned long hwpgd;
+
+	if (KVM_PREALLOC_LEVEL == 0)
+		return 0;
+
+	hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT);
+	if (!hwpgd)
+		return -ENOMEM;
+
+	for (i = 0; i < PTRS_PER_S2_PGD; i++) {
+		if (KVM_PREALLOC_LEVEL == 1)
+			pgd_populate(NULL, pgd + i,
+				     (pud_t *)hwpgd + i * PTRS_PER_PUD);
+		else if (KVM_PREALLOC_LEVEL == 2)
+			pud_populate(NULL, pud_offset(pgd, 0) + i,
+				     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
+	}
+
+	return 0;
+}
+
+static inline void *kvm_get_hwpgd(struct kvm *kvm)
+{
+	pgd_t *pgd = kvm->arch.pgd;
+	pud_t *pud;
+
+	if (KVM_PREALLOC_LEVEL == 0)
+		return pgd;
+
+	pud = pud_offset(pgd, 0);
+	if (KVM_PREALLOC_LEVEL == 1)
+		return pud;
+
+	BUG_ON(KVM_PREALLOC_LEVEL != 2);
+	return pmd_offset(pud, 0);
+}
+
+static inline void kvm_free_hwpgd(struct kvm *kvm)
+{
+	if (KVM_PREALLOC_LEVEL > 0) {
+		unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm);
+		free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT);
+	}
+}
+
 static inline bool kvm_page_empty(void *ptr)
 {
 	struct page *ptr_page = virt_to_page(ptr);
 	return page_count(ptr_page) == 1;
 }
 
-#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
-#ifndef CONFIG_ARM64_64K_PAGES
-#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
+
+#ifdef __PAGETABLE_PMD_FOLDED
+#define kvm_pmd_table_empty(kvm, pmdp) (0)
+#else
+#define kvm_pmd_table_empty(kvm, pmdp) \
+	(kvm_page_empty(pmdp) && (!(kvm) || KVM_PREALLOC_LEVEL < 2))
+#endif
+
+#ifdef __PAGETABLE_PUD_FOLDED
+#define kvm_pud_table_empty(kvm, pudp) (0)
 #else
-#define kvm_pmd_table_empty(pmdp) (0)
+#define kvm_pud_table_empty(kvm, pudp) \
+	(kvm_page_empty(pudp) && (!(kvm) || KVM_PREALLOC_LEVEL < 1))
 #endif
-#define kvm_pud_table_empty(pudp) (0)
 
 
 struct kvm;
diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h
new file mode 100644
index 000000000000..872ba939fcb2
--- /dev/null
+++ b/arch/arm64/include/asm/pci.h
@@ -0,0 +1,37 @@
+#ifndef __ASM_PCI_H
+#define __ASM_PCI_H
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/io.h>
+#include <asm-generic/pci-bridge.h>
+#include <asm-generic/pci-dma-compat.h>
+
+#define PCIBIOS_MIN_IO		0x1000
+#define PCIBIOS_MIN_MEM		0
+
+/*
+ * Set to 1 if the kernel should re-assign all PCI bus numbers
+ */
+#define pcibios_assign_all_busses() \
+	(pci_has_flag(PCI_REASSIGN_ALL_BUS))
+
+/*
+ * PCI address space differs from physical memory address space
+ */
+#define PCI_DMA_BUS_IS_PHYS	(0)
+
+extern int isa_dma_bridge_buggy;
+
+#ifdef CONFIG_PCI
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+	return 1;
+}
+#endif  /* CONFIG_PCI */
+
+#endif  /* __KERNEL__ */
+#endif  /* __ASM_PCI_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index d58e40cde88e..41a43bf26492 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -79,7 +79,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
 
 #define PAGE_S2			__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDWR | PTE_UXN)
+#define PAGE_S2_DEVICE		__pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
 
 #define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
 #define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
@@ -244,6 +244,16 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_PTE_SPECIAL
 
+static inline pte_t pud_pte(pud_t pud)
+{
+	return __pte(pud_val(pud));
+}
+
+static inline pmd_t pud_pmd(pud_t pud)
+{
+	return __pmd(pud_val(pud));
+}
+
 static inline pte_t pmd_pte(pmd_t pmd)
 {
 	return __pte(pmd_val(pmd));
@@ -261,7 +271,13 @@ static inline pmd_t pte_pmd(pte_t pte)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
 #define pmd_trans_splitting(pmd)	pte_special(pmd_pte(pmd))
-#endif
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+struct vm_area_struct;
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp);
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
@@ -282,6 +298,7 @@ static inline pmd_t pte_pmd(pte_t pte)
 #define mk_pmd(page,prot)	pfn_pmd(page_to_pfn(page),prot)
 
 #define pmd_page(pmd)           pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
+#define pud_write(pud)		pte_write(pud_pte(pud))
 #define pud_pfn(pud)		(((pud_val(pud) & PUD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
 
 #define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
@@ -301,6 +318,8 @@ static inline int has_transparent_hugepage(void)
 	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN)
 #define pgprot_writecombine(prot) \
 	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
+#define pgprot_device(prot) \
+	__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN)
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 struct file;
 extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -381,6 +400,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
 }
 
+#define pud_page(pud)           pmd_page(pud_pmd(pud))
+
 #endif	/* CONFIG_ARM64_PGTABLE_LEVELS > 2 */
 
 #if CONFIG_ARM64_PGTABLE_LEVELS > 3
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index a498f2cd2c2a..780f82c827b6 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -48,6 +48,8 @@ extern void smp_init_cpus(void);
  */
 extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
 
+extern void (*__smp_cross_call)(const struct cpumask *, unsigned int);
+
 /*
  * Called from the secondary holding pen, this is the secondary CPU entry point.
  */
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 62731ef9749a..a82c0c5c8b52 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -23,6 +23,20 @@
 
 #include <asm-generic/tlb.h>
 
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+
+#define tlb_remove_entry(tlb, entry)	tlb_remove_table(tlb, entry)
+static inline void __tlb_remove_table(void *_table)
+{
+	free_page_and_swap_cache((struct page *)_table);
+}
+#else
+#define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+
 /*
  * There's three ways the TLB shootdown code is used:
  *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
@@ -88,7 +102,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 {
 	pgtable_page_dtor(pte);
 	tlb_add_flush(tlb, addr);
-	tlb_remove_page(tlb, pte);
+	tlb_remove_entry(tlb, pte);
 }
 
 #if CONFIG_ARM64_PGTABLE_LEVELS > 2
@@ -96,7 +110,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
 	tlb_add_flush(tlb, addr);
-	tlb_remove_page(tlb, virt_to_page(pmdp));
+	tlb_remove_entry(tlb, virt_to_page(pmdp));
 }
 #endif
 
@@ -105,7 +119,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
 	tlb_add_flush(tlb, addr);
-	tlb_remove_page(tlb, virt_to_page(pudp));
+	tlb_remove_entry(tlb, virt_to_page(pudp));
 }
 #endif
 
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 6e9538c2d28a..5bd029b43644 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -30,6 +30,7 @@ arm64-obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 arm64-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 arm64-obj-$(CONFIG_KGDB)		+= kgdb.o
 arm64-obj-$(CONFIG_EFI)			+= efi.o efi-stub.o efi-entry.o
+arm64-obj-$(CONFIG_PCI)			+= pci.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index dfa6e3e74fdd..071a6ec13bd8 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -40,33 +40,6 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	return 0;
 }
 
-/*
- * handle_IRQ handles all hardware IRQ's.  Decoded IRQs should
- * not come via this function.  Instead, they should provide their
- * own 'handler'.  Used by platform code implementing C-based 1st
- * level decoding.
- */
-void handle_IRQ(unsigned int irq, struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-
-	irq_enter();
-
-	/*
-	 * Some hardware gives randomly wrong interrupts.  Rather
-	 * than crashing, do something sensible.
-	 */
-	if (unlikely(irq >= nr_irqs)) {
-		pr_warn_ratelimited("Bad IRQ%u\n", irq);
-		ack_bad_irq(irq);
-	} else {
-		generic_handle_irq(irq);
-	}
-
-	irq_exit();
-	set_irq_regs(old_regs);
-}
-
 void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
 {
 	if (handle_arch_irq)
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
new file mode 100644
index 000000000000..ce5836c14ec1
--- /dev/null
+++ b/arch/arm64/kernel/pci.c
@@ -0,0 +1,70 @@
+/*
+ * Code borrowed from powerpc/kernel/pci-common.c
+ *
+ * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
+ * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/of_pci.h>
+#include <linux/of_platform.h>
+#include <linux/slab.h>
+
+#include <asm/pci-bridge.h>
+
+/*
+ * Called after each bus is probed, but before its children are examined
+ */
+void pcibios_fixup_bus(struct pci_bus *bus)
+{
+	/* nothing to do, expected to be removed in the future */
+}
+
+/*
+ * We don't have to worry about legacy ISA devices, so nothing to do here
+ */
+resource_size_t pcibios_align_resource(void *data, const struct resource *res,
+				resource_size_t size, resource_size_t align)
+{
+	return res->start;
+}
+
+/*
+ * Try to assign the IRQ number from DT when adding a new device
+ */
+int pcibios_add_device(struct pci_dev *dev)
+{
+	dev->irq = of_irq_parse_and_map_pci(dev, 0, 0);
+
+	return 0;
+}
+
+
+#ifdef CONFIG_PCI_DOMAINS_GENERIC
+static bool dt_domain_found = false;
+
+void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent)
+{
+	int domain = of_get_pci_domain_nr(parent->of_node);
+
+	if (domain >= 0) {
+		dt_domain_found = true;
+	} else if (dt_domain_found == true) {
+		dev_err(parent, "Node %s is missing \"linux,pci-domain\" property in DT\n",
+			parent->of_node->full_name);
+		return;
+	} else {
+		domain = pci_get_new_domain_nr();
+	}
+
+	bus->domain_nr = domain;
+}
+#endif
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 89f41f7d27dd..c3065dbc4fa2 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -72,7 +72,6 @@ void (*pm_power_off)(void);
 EXPORT_SYMBOL_GPL(pm_power_off);
 
 void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
-EXPORT_SYMBOL_GPL(arm_pm_restart);
 
 /*
  * This is our default idle handler.
@@ -154,6 +153,8 @@ void machine_restart(char *cmd)
 	/* Now call the architecture specific reboot code. */
 	if (arm_pm_restart)
 		arm_pm_restart(reboot_mode, cmd);
+	else
+		do_kernel_restart(cmd);
 
 	/*
 	 * Whoops - the architecture was unable to reboot.
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 474339718105..b06d1d90ee8c 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -470,7 +470,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	}
 }
 
-static void (*__smp_cross_call)(const struct cpumask *, unsigned int);
+void (*__smp_cross_call)(const struct cpumask *, unsigned int);
 
 void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
 {
diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S
index ae211772f991..f002fe1c3700 100644
--- a/arch/arm64/kvm/vgic-v2-switch.S
+++ b/arch/arm64/kvm/vgic-v2-switch.S
@@ -67,10 +67,14 @@ CPU_BE(	rev	w11, w11 )
 	str	w4, [x3, #VGIC_V2_CPU_HCR]
 	str	w5, [x3, #VGIC_V2_CPU_VMCR]
 	str	w6, [x3, #VGIC_V2_CPU_MISR]
-	str	w7, [x3, #VGIC_V2_CPU_EISR]
-	str	w8, [x3, #(VGIC_V2_CPU_EISR + 4)]
-	str	w9, [x3, #VGIC_V2_CPU_ELRSR]
-	str	w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)]
+CPU_LE(	str	w7, [x3, #VGIC_V2_CPU_EISR] )
+CPU_LE(	str	w8, [x3, #(VGIC_V2_CPU_EISR + 4)] )
+CPU_LE(	str	w9, [x3, #VGIC_V2_CPU_ELRSR] )
+CPU_LE(	str	w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)] )
+CPU_BE(	str	w7, [x3, #(VGIC_V2_CPU_EISR + 4)] )
+CPU_BE(	str	w8, [x3, #VGIC_V2_CPU_EISR] )
+CPU_BE(	str	w9, [x3, #(VGIC_V2_CPU_ELRSR + 4)] )
+CPU_BE(	str	w10, [x3, #VGIC_V2_CPU_ELRSR] )
 	str	w11, [x3, #VGIC_V2_CPU_APR]
 
 	/* Clear GICH_HCR */
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 2c71077cacfd..d92094203913 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -20,6 +20,7 @@
 #include <linux/gfp.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/genalloc.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 #include <linux/vmalloc.h>
@@ -38,6 +39,54 @@ static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
 	return prot;
 }
 
+static struct gen_pool *atomic_pool;
+
+#define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
+static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE;
+
+static int __init early_coherent_pool(char *p)
+{
+	atomic_pool_size = memparse(p, &p);
+	return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+static void *__alloc_from_pool(size_t size, struct page **ret_page)
+{
+	unsigned long val;
+	void *ptr = NULL;
+
+	if (!atomic_pool) {
+		WARN(1, "coherent pool not initialised!\n");
+		return NULL;
+	}
+
+	val = gen_pool_alloc(atomic_pool, size);
+	if (val) {
+		phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
+
+		*ret_page = phys_to_page(phys);
+		ptr = (void *)val;
+	}
+
+	return ptr;
+}
+
+static bool __in_atomic_pool(void *start, size_t size)
+{
+	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
+}
+
+static int __free_from_pool(void *start, size_t size)
+{
+	if (!__in_atomic_pool(start, size))
+		return 0;
+
+	gen_pool_free(atomic_pool, (unsigned long)start, size);
+
+	return 1;
+}
+
 static void *__dma_alloc_coherent(struct device *dev, size_t size,
 				  dma_addr_t *dma_handle, gfp_t flags,
 				  struct dma_attrs *attrs)
@@ -50,7 +99,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 	if (IS_ENABLED(CONFIG_ZONE_DMA) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
 		flags |= GFP_DMA;
-	if (IS_ENABLED(CONFIG_DMA_CMA)) {
+	if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) {
 		struct page *page;
 
 		size = PAGE_ALIGN(size);
@@ -70,50 +119,54 @@ static void __dma_free_coherent(struct device *dev, size_t size,
 				void *vaddr, dma_addr_t dma_handle,
 				struct dma_attrs *attrs)
 {
+	bool freed;
+	phys_addr_t paddr = dma_to_phys(dev, dma_handle);
+
 	if (dev == NULL) {
 		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
 		return;
 	}
 
-	if (IS_ENABLED(CONFIG_DMA_CMA)) {
-		phys_addr_t paddr = dma_to_phys(dev, dma_handle);
-
-		dma_release_from_contiguous(dev,
+	freed = dma_release_from_contiguous(dev,
 					phys_to_page(paddr),
 					size >> PAGE_SHIFT);
-	} else {
+	if (!freed)
 		swiotlb_free_coherent(dev, size, vaddr, dma_handle);
-	}
 }
 
 static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
 				     dma_addr_t *dma_handle, gfp_t flags,
 				     struct dma_attrs *attrs)
 {
-	struct page *page, **map;
+	struct page *page;
 	void *ptr, *coherent_ptr;
-	int order, i;
 
 	size = PAGE_ALIGN(size);
-	order = get_order(size);
+
+	if (!(flags & __GFP_WAIT)) {
+		struct page *page = NULL;
+		void *addr = __alloc_from_pool(size, &page);
+
+		if (addr)
+			*dma_handle = phys_to_dma(dev, page_to_phys(page));
+
+		return addr;
+
+	}
 
 	ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
 	if (!ptr)
 		goto no_mem;
-	map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA);
-	if (!map)
-		goto no_map;
 
 	/* remove any dirty cache lines on the kernel alias */
 	__dma_flush_range(ptr, ptr + size);
 
 	/* create a coherent mapping */
 	page = virt_to_page(ptr);
-	for (i = 0; i < (size >> PAGE_SHIFT); i++)
-		map[i] = page + i;
-	coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP,
-			    __get_dma_pgprot(attrs, __pgprot(PROT_NORMAL_NC), false));
-	kfree(map);
+	coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
+				__get_dma_pgprot(attrs,
+					__pgprot(PROT_NORMAL_NC), false),
+					NULL);
 	if (!coherent_ptr)
 		goto no_map;
 
@@ -132,6 +185,8 @@ static void __dma_free_noncoherent(struct device *dev, size_t size,
 {
 	void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
 
+	if (__free_from_pool(vaddr, size))
+		return;
 	vunmap(vaddr);
 	__dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
 }
@@ -307,6 +362,67 @@ EXPORT_SYMBOL(coherent_swiotlb_dma_ops);
 
 extern int swiotlb_late_init_with_default_size(size_t default_size);
 
+static int __init atomic_pool_init(void)
+{
+	pgprot_t prot = __pgprot(PROT_NORMAL_NC);
+	unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
+	struct page *page;
+	void *addr;
+	unsigned int pool_size_order = get_order(atomic_pool_size);
+
+	if (dev_get_cma_area(NULL))
+		page = dma_alloc_from_contiguous(NULL, nr_pages,
+							pool_size_order);
+	else
+		page = alloc_pages(GFP_DMA, pool_size_order);
+
+	if (page) {
+		int ret;
+		void *page_addr = page_address(page);
+
+		memset(page_addr, 0, atomic_pool_size);
+		__dma_flush_range(page_addr, page_addr + atomic_pool_size);
+
+		atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
+		if (!atomic_pool)
+			goto free_page;
+
+		addr = dma_common_contiguous_remap(page, atomic_pool_size,
+					VM_USERMAP, prot, atomic_pool_init);
+
+		if (!addr)
+			goto destroy_genpool;
+
+		ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr,
+					page_to_phys(page),
+					atomic_pool_size, -1);
+		if (ret)
+			goto remove_mapping;
+
+		gen_pool_set_algo(atomic_pool,
+				  gen_pool_first_fit_order_align,
+				  (void *)PAGE_SHIFT);
+
+		pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
+			atomic_pool_size / 1024);
+		return 0;
+	}
+	goto out;
+
+remove_mapping:
+	dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
+destroy_genpool:
+	gen_pool_destroy(atomic_pool);
+	atomic_pool = NULL;
+free_page:
+	if (!dma_release_from_contiguous(NULL, page, nr_pages))
+		__free_pages(page, pool_size_order);
+out:
+	pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n",
+		atomic_pool_size / 1024);
+	return -ENOMEM;
+}
+
 static int __init swiotlb_late_init(void)
 {
 	size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
@@ -315,7 +431,17 @@ static int __init swiotlb_late_init(void)
 
 	return swiotlb_late_init_with_default_size(swiotlb_size);
 }
-arch_initcall(swiotlb_late_init);
+
+static int __init arm64_dma_init(void)
+{
+	int ret = 0;
+
+	ret |= swiotlb_late_init();
+	ret |= atomic_pool_init();
+
+	return ret;
+}
+arch_initcall(arm64_dma_init);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES	4096
 
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 0d64089d28b5..b6f14e8d2121 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -104,3 +104,19 @@ EXPORT_SYMBOL(flush_dcache_page);
  */
 EXPORT_SYMBOL(flush_cache_all);
 EXPORT_SYMBOL(flush_icache_range);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp)
+{
+	pmd_t pmd = pmd_mksplitting(*pmdp);
+
+	VM_BUG_ON(address & ~PMD_MASK);
+	set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+
+	/* dummy IPI to serialise against fast_gup */
+	kick_all_cpus_sync();
+}
+#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index 00a0f3ccd6eb..2a71b1cb9848 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += exec.h
 generic-y += futex.h
 generic-y += hash.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
diff --git a/arch/avr32/include/asm/atomic.h b/arch/avr32/include/asm/atomic.h
index 0780f3f2415b..2d07ce1c5327 100644
--- a/arch/avr32/include/asm/atomic.h
+++ b/arch/avr32/include/asm/atomic.h
@@ -19,33 +19,46 @@
 
 #define ATOMIC_INIT(i)  { (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = i)
 
+#define ATOMIC_OP_RETURN(op, asm_op, asm_con)				\
+static inline int __atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	int result;							\
+									\
+	asm volatile(							\
+		"/* atomic_" #op "_return */\n"				\
+		"1:	ssrf	5\n"					\
+		"	ld.w	%0, %2\n"				\
+		"	" #asm_op "	%0, %3\n"			\
+		"	stcond	%1, %0\n"				\
+		"	brne	1b"					\
+		: "=&r" (result), "=o" (v->counter)			\
+		: "m" (v->counter), #asm_con (i)			\
+		: "cc");						\
+									\
+	return result;							\
+}
+
+ATOMIC_OP_RETURN(sub, sub, rKs21)
+ATOMIC_OP_RETURN(add, add, r)
+
+#undef ATOMIC_OP_RETURN
+
 /*
- * atomic_sub_return - subtract the atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
+ * Probably found the reason why we want to use sub with the signed 21-bit
+ * limit, it uses one less register than the add instruction that can add up to
+ * 32-bit values.
  *
- * Atomically subtracts @i from @v. Returns the resulting value.
+ * Both instructions are 32-bit, to use a 16-bit instruction the immediate is
+ * very small; 4 bit.
+ *
+ * sub 32-bit, type IV, takes a register and subtracts a 21-bit immediate.
+ * add 32-bit, type II, adds two register values together.
  */
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	int result;
-
-	asm volatile(
-		"/* atomic_sub_return */\n"
-		"1:	ssrf	5\n"
-		"	ld.w	%0, %2\n"
-		"	sub	%0, %3\n"
-		"	stcond	%1, %0\n"
-		"	brne	1b"
-		: "=&r"(result), "=o"(v->counter)
-		: "m"(v->counter), "rKs21"(i)
-		: "cc");
-
-	return result;
-}
+#define IS_21BIT_CONST(i)						\
+	(__builtin_constant_p(i) && ((i) >= -1048575) && ((i) <= 1048576))
 
 /*
  * atomic_add_return - add integer to atomic variable
@@ -56,51 +69,25 @@ static inline int atomic_sub_return(int i, atomic_t *v)
  */
 static inline int atomic_add_return(int i, atomic_t *v)
 {
-	int result;
-
-	if (__builtin_constant_p(i) && (i >= -1048575) && (i <= 1048576))
-		result = atomic_sub_return(-i, v);
-	else
-		asm volatile(
-			"/* atomic_add_return */\n"
-			"1:	ssrf	5\n"
-			"	ld.w	%0, %1\n"
-			"	add	%0, %3\n"
-			"	stcond	%2, %0\n"
-			"	brne	1b"
-			: "=&r"(result), "=o"(v->counter)
-			: "m"(v->counter), "r"(i)
-			: "cc", "memory");
+	if (IS_21BIT_CONST(i))
+		return __atomic_sub_return(-i, v);
 
-	return result;
+	return __atomic_add_return(i, v);
 }
 
 /*
- * atomic_sub_unless - sub unless the number is a given value
+ * atomic_sub_return - subtract the atomic variable
+ * @i: integer value to subtract
  * @v: pointer of type atomic_t
- * @a: the amount to subtract from v...
- * @u: ...unless v is equal to u.
  *
- * Atomically subtract @a from @v, so long as it was not @u.
- * Returns the old value of @v.
-*/
-static inline void atomic_sub_unless(atomic_t *v, int a, int u)
+ * Atomically subtracts @i from @v. Returns the resulting value.
+ */
+static inline int atomic_sub_return(int i, atomic_t *v)
 {
-	int tmp;
+	if (IS_21BIT_CONST(i))
+		return __atomic_sub_return(i, v);
 
-	asm volatile(
-		"/* atomic_sub_unless */\n"
-		"1:	ssrf	5\n"
-		"	ld.w	%0, %2\n"
-		"	cp.w	%0, %4\n"
-		"	breq	1f\n"
-		"	sub	%0, %3\n"
-		"	stcond	%1, %0\n"
-		"	brne	1b\n"
-		"1:"
-		: "=&r"(tmp), "=o"(v->counter)
-		: "m"(v->counter), "rKs21"(a), "rKs21"(u)
-		: "cc", "memory");
+	return __atomic_add_return(-i, v);
 }
 
 /*
@@ -116,9 +103,21 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
 	int tmp, old = atomic_read(v);
 
-	if (__builtin_constant_p(a) && (a >= -1048575) && (a <= 1048576))
-		atomic_sub_unless(v, -a, u);
-	else {
+	if (IS_21BIT_CONST(a)) {
+		asm volatile(
+			"/* __atomic_sub_unless */\n"
+			"1:	ssrf	5\n"
+			"	ld.w	%0, %2\n"
+			"	cp.w	%0, %4\n"
+			"	breq	1f\n"
+			"	sub	%0, %3\n"
+			"	stcond	%1, %0\n"
+			"	brne	1b\n"
+			"1:"
+			: "=&r"(tmp), "=o"(v->counter)
+			: "m"(v->counter), "rKs21"(-a), "rKs21"(u)
+			: "cc", "memory");
+	} else {
 		asm volatile(
 			"/* __atomic_add_unless */\n"
 			"1:	ssrf	5\n"
@@ -137,6 +136,8 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	return old;
 }
 
+#undef IS_21BIT_CONST
+
 /*
  * atomic_sub_if_positive - conditionally subtract integer from atomic variable
  * @i: integer value to subtract
diff --git a/arch/avr32/kernel/kprobes.c b/arch/avr32/kernel/kprobes.c
index f820e9f25520..a94ece4a72c8 100644
--- a/arch/avr32/kernel/kprobes.c
+++ b/arch/avr32/kernel/kprobes.c
@@ -104,7 +104,7 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
 
 static void __kprobes set_current_kprobe(struct kprobe *p)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 static int __kprobes kprobe_handler(struct pt_regs *regs)
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index db85b5ec3351..37b75602adf6 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -7,7 +7,7 @@
  */
 #include <linux/clk.h>
 #include <linux/delay.h>
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
@@ -1356,10 +1356,10 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
 		goto fail;
 
 	slave->sdata.dma_dev = &dw_dmac0_device.dev;
-	slave->sdata.cfg_hi = (DWC_CFGH_SRC_PER(0)
-				| DWC_CFGH_DST_PER(1));
-	slave->sdata.cfg_lo &= ~(DWC_CFGL_HS_DST_POL
-				| DWC_CFGL_HS_SRC_POL);
+	slave->sdata.src_id = 0;
+	slave->sdata.dst_id = 1;
+	slave->sdata.src_master = 1;
+	slave->sdata.dst_master = 0;
 
 	data->dma_slave = slave;
 
@@ -2052,8 +2052,7 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 	/* Check if DMA slave interface for capture should be configured. */
 	if (flags & AC97C_CAPTURE) {
 		rx_dws->dma_dev = &dw_dmac0_device.dev;
-		rx_dws->cfg_hi = DWC_CFGH_SRC_PER(3);
-		rx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+		rx_dws->src_id = 3;
 		rx_dws->src_master = 0;
 		rx_dws->dst_master = 1;
 	}
@@ -2061,8 +2060,7 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 	/* Check if DMA slave interface for playback should be configured. */
 	if (flags & AC97C_PLAYBACK) {
 		tx_dws->dma_dev = &dw_dmac0_device.dev;
-		tx_dws->cfg_hi = DWC_CFGH_DST_PER(4);
-		tx_dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+		tx_dws->dst_id = 4;
 		tx_dws->src_master = 0;
 		tx_dws->dst_master = 1;
 	}
@@ -2134,8 +2132,7 @@ at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data)
 	dws = &data->dws;
 
 	dws->dma_dev = &dw_dmac0_device.dev;
-	dws->cfg_hi = DWC_CFGH_DST_PER(2);
-	dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL);
+	dws->dst_id = 2;
 	dws->src_master = 0;
 	dws->dst_master = 1;
 
diff --git a/arch/avr32/mach-at32ap/include/mach/atmel-mci.h b/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
index 4bba58561d5c..11d7f4b28dc8 100644
--- a/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
+++ b/arch/avr32/mach-at32ap/include/mach/atmel-mci.h
@@ -1,7 +1,7 @@
 #ifndef __MACH_ATMEL_MCI_H
 #define __MACH_ATMEL_MCI_H
 
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 
 /**
  * struct mci_dma_data - DMA data for MCI interface
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 0d93b9a79ca9..46ed6bb9c679 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -15,6 +15,7 @@ generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
diff --git a/arch/blackfin/include/asm/ipipe.h b/arch/blackfin/include/asm/ipipe.h
index 17b5e92e3bc6..fe1160fbff91 100644
--- a/arch/blackfin/include/asm/ipipe.h
+++ b/arch/blackfin/include/asm/ipipe.h
@@ -157,7 +157,7 @@ static inline unsigned long __ipipe_ffnz(unsigned long ul)
 }
 
 #define __ipipe_do_root_xirq(ipd, irq)					\
-	((ipd)->irqs[irq].handler(irq, &__raw_get_cpu_var(__ipipe_tick_regs)))
+	((ipd)->irqs[irq].handler(irq, raw_cpu_ptr(&__ipipe_tick_regs)))
 
 #define __ipipe_run_irqtail(irq)  /* Must be a macro */			\
 	do {								\
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index ea2032013cc2..1e9c8b0bf486 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -300,7 +300,7 @@ again:
 
 static void bfin_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -318,7 +318,7 @@ static void bfin_pmu_stop(struct perf_event *event, int flags)
 
 static void bfin_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -335,7 +335,7 @@ static void bfin_pmu_start(struct perf_event *event, int flags)
 
 static void bfin_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	bfin_pmu_stop(event, PERF_EF_UPDATE);
 	__clear_bit(event->hw.idx, cpuc->used_mask);
@@ -345,7 +345,7 @@ static void bfin_pmu_del(struct perf_event *event, int flags)
 
 static int bfin_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 	int ret = -EAGAIN;
@@ -421,7 +421,7 @@ static int bfin_pmu_event_init(struct perf_event *event)
 
 static void bfin_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	int i;
diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537e.c b/arch/blackfin/mach-bf537/boards/cm_bf537e.c
index 1e7290ef3525..1e1014df5e9e 100644
--- a/arch/blackfin/mach-bf537/boards/cm_bf537e.c
+++ b/arch/blackfin/mach-bf537/boards/cm_bf537e.c
@@ -733,7 +733,6 @@ static struct platform_device bfin_mac_device = {
 
 static struct pata_platform_info bfin_pata_platform_data = {
 	.ioport_shift = 2,
-	.irq_type = IRQF_TRIGGER_HIGH,
 };
 
 static struct resource bfin_pata_resources[] = {
@@ -750,7 +749,7 @@ static struct resource bfin_pata_resources[] = {
 	{
 		.start = PATA_INT,
 		.end = PATA_INT,
-		.flags = IORESOURCE_IRQ,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 
diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537u.c b/arch/blackfin/mach-bf537/boards/cm_bf537u.c
index c7495dc74690..d056db9e5592 100644
--- a/arch/blackfin/mach-bf537/boards/cm_bf537u.c
+++ b/arch/blackfin/mach-bf537/boards/cm_bf537u.c
@@ -587,7 +587,6 @@ static struct platform_device bfin_mac_device = {
 
 static struct pata_platform_info bfin_pata_platform_data = {
 	.ioport_shift = 2,
-	.irq_type = IRQF_TRIGGER_HIGH,
 };
 
 static struct resource bfin_pata_resources[] = {
@@ -604,7 +603,7 @@ static struct resource bfin_pata_resources[] = {
 	{
 		.start = PATA_INT,
 		.end = PATA_INT,
-		.flags = IORESOURCE_IRQ,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 
diff --git a/arch/blackfin/mach-bf537/boards/stamp.c b/arch/blackfin/mach-bf537/boards/stamp.c
index de19b8a56007..88a19fc9844d 100644
--- a/arch/blackfin/mach-bf537/boards/stamp.c
+++ b/arch/blackfin/mach-bf537/boards/stamp.c
@@ -2462,7 +2462,6 @@ static struct platform_device bfin_sport0_device = {
 #define PATA_INT	IRQ_PF5
 static struct pata_platform_info bfin_pata_platform_data = {
 	.ioport_shift = 1,
-	.irq_flags = IRQF_TRIGGER_HIGH,
 };
 
 static struct resource bfin_pata_resources[] = {
@@ -2479,7 +2478,7 @@ static struct resource bfin_pata_resources[] = {
 	{
 		.start = PATA_INT,
 		.end = PATA_INT,
-		.flags = IORESOURCE_IRQ,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 #elif defined(CF_IDE_NAND_CARD_USE_CF_IN_COMMON_MEMORY_MODE)
diff --git a/arch/blackfin/mach-bf537/boards/tcm_bf537.c b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
index 6b988ad653d8..ed309c9a62b6 100644
--- a/arch/blackfin/mach-bf537/boards/tcm_bf537.c
+++ b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
@@ -589,7 +589,6 @@ static struct platform_device bfin_mac_device = {
 
 static struct pata_platform_info bfin_pata_platform_data = {
 	.ioport_shift = 2,
-	.irq_type = IRQF_TRIGGER_HIGH,
 };
 
 static struct resource bfin_pata_resources[] = {
@@ -606,7 +605,7 @@ static struct resource bfin_pata_resources[] = {
 	{
 		.start = PATA_INT,
 		.end = PATA_INT,
-		.flags = IORESOURCE_IRQ,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 
diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c
index e862f7823e68..c6db52ba3a06 100644
--- a/arch/blackfin/mach-bf561/boards/cm_bf561.c
+++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c
@@ -354,7 +354,6 @@ static struct platform_device bfin_sir0_device = {
 
 static struct pata_platform_info bfin_pata_platform_data = {
 	.ioport_shift = 2,
-	.irq_type = IRQF_TRIGGER_HIGH,
 };
 
 static struct resource bfin_pata_resources[] = {
@@ -371,7 +370,7 @@ static struct resource bfin_pata_resources[] = {
 	{
 		.start = PATA_INT,
 		.end = PATA_INT,
-		.flags = IORESOURCE_IRQ,
+		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
 	},
 };
 
diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c
index 694619365265..dd2af74aff80 100644
--- a/arch/blackfin/mach-common/ints-priority.c
+++ b/arch/blackfin/mach-common/ints-priority.c
@@ -1309,12 +1309,12 @@ asmlinkage int __ipipe_grab_irq(int vec, struct pt_regs *regs)
 		bfin_write_TIMER_STATUS(1); /* Latch TIMIL0 */
 #endif
 		/* This is basically what we need from the register frame. */
-		__raw_get_cpu_var(__ipipe_tick_regs).ipend = regs->ipend;
-		__raw_get_cpu_var(__ipipe_tick_regs).pc = regs->pc;
+		__this_cpu_write(__ipipe_tick_regs.ipend, regs->ipend);
+		__this_cpu_write(__ipipe_tick_regs.pc, regs->pc);
 		if (this_domain != ipipe_root_domain)
-			__raw_get_cpu_var(__ipipe_tick_regs).ipend &= ~0x10;
+			__this_cpu_and(__ipipe_tick_regs.ipend, ~0x10);
 		else
-			__raw_get_cpu_var(__ipipe_tick_regs).ipend |= 0x10;
+			__this_cpu_or(__ipipe_tick_regs.ipend, 0x10);
 	}
 
 	/*
diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c
index ba6c30d8534d..8ad3e90cc8fc 100644
--- a/arch/blackfin/mach-common/smp.c
+++ b/arch/blackfin/mach-common/smp.c
@@ -146,7 +146,7 @@ static irqreturn_t ipi_handler_int1(int irq, void *dev_instance)
 	platform_clear_ipi(cpu, IRQ_SUPPLE_1);
 
 	smp_rmb();
-	bfin_ipi_data = &__get_cpu_var(bfin_ipi);
+	bfin_ipi_data = this_cpu_ptr(&bfin_ipi);
 	while ((pending = atomic_xchg(&bfin_ipi_data->bits, 0)) != 0) {
 		msg = 0;
 		do {
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 8dbdce8421b0..e77e0c1dbe75 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -22,6 +22,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h
diff --git a/arch/cris/arch-v10/drivers/sync_serial.c b/arch/cris/arch-v10/drivers/sync_serial.c
index 29eb02ab3f25..0f3983241e60 100644
--- a/arch/cris/arch-v10/drivers/sync_serial.c
+++ b/arch/cris/arch-v10/drivers/sync_serial.c
@@ -1086,7 +1086,6 @@ static ssize_t sync_serial_write(struct file *file, const char *buf,
 	}
 	local_irq_restore(flags);
 	schedule();
-	set_current_state(TASK_RUNNING);
 	remove_wait_queue(&port->out_wait_q, &wait);
 	if (signal_pending(current))
 		return -EINTR;
diff --git a/arch/cris/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c
index bbb806b68838..5a149134cfb5 100644
--- a/arch/cris/arch-v32/drivers/sync_serial.c
+++ b/arch/cris/arch-v32/drivers/sync_serial.c
@@ -1089,7 +1089,6 @@ static ssize_t sync_serial_write(struct file *file, const char *buf,
 	}
 
 	schedule();
-	set_current_state(TASK_RUNNING);
 	remove_wait_queue(&port->out_wait_q, &wait);
 
 	if (signal_pending(current))
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index 31742dfadff9..2ca489eaadd3 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -8,12 +8,14 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += linkage.h
 generic-y += mcs_spinlock.h
 generic-y += module.h
 generic-y += preempt.h
 generic-y += scatterlist.h
+generic-y += sections.h
 generic-y += trace_clock.h
 generic-y += vga.h
 generic-y += xor.h
diff --git a/arch/cris/include/asm/atomic.h b/arch/cris/include/asm/atomic.h
index aa429baebaf9..279766a70664 100644
--- a/arch/cris/include/asm/atomic.h
+++ b/arch/cris/include/asm/atomic.h
@@ -17,48 +17,41 @@
 
 #define ATOMIC_INIT(i)  { (i) }
 
-#define atomic_read(v) (*(volatile int *)&(v)->counter)
+#define atomic_read(v) ACCESS_ONCE((v)->counter)
 #define atomic_set(v,i) (((v)->counter) = (i))
 
 /* These should be written in asm but we do it in C for now. */
 
-static inline void atomic_add(int i, volatile atomic_t *v)
-{
-	unsigned long flags;
-	cris_atomic_save(v, flags);
-	v->counter += i;
-	cris_atomic_restore(v, flags);
+#define ATOMIC_OP(op, c_op)						\
+static inline void atomic_##op(int i, volatile atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	cris_atomic_save(v, flags);					\
+	v->counter c_op i;						\
+	cris_atomic_restore(v, flags);					\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int atomic_##op##_return(int i, volatile atomic_t *v)	\
+{									\
+	unsigned long flags;						\
+	int retval;							\
+	cris_atomic_save(v, flags);					\
+	retval = (v->counter c_op i);					\
+	cris_atomic_restore(v, flags);					\
+	return retval;							\
 }
 
-static inline void atomic_sub(int i, volatile atomic_t *v)
-{
-	unsigned long flags;
-	cris_atomic_save(v, flags);
-	v->counter -= i;
-	cris_atomic_restore(v, flags);
-}
+#define ATOMIC_OPS(op, c_op) ATOMIC_OP(op, c_op) ATOMIC_OP_RETURN(op, c_op)
 
-static inline int atomic_add_return(int i, volatile atomic_t *v)
-{
-	unsigned long flags;
-	int retval;
-	cris_atomic_save(v, flags);
-	retval = (v->counter += i);
-	cris_atomic_restore(v, flags);
-	return retval;
-}
+ATOMIC_OPS(add, +=)
+ATOMIC_OPS(sub, -=)
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
-static inline int atomic_sub_return(int i, volatile atomic_t *v)
-{
-	unsigned long flags;
-	int retval;
-	cris_atomic_save(v, flags);
-	retval = (v->counter -= i);
-	cris_atomic_restore(v, flags);
-	return retval;
-}
+#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
 
 static inline int atomic_sub_and_test(int i, volatile atomic_t *v)
 {
diff --git a/arch/cris/include/asm/sections.h b/arch/cris/include/asm/sections.h
deleted file mode 100644
index 2c998ce8967b..000000000000
--- a/arch/cris/include/asm/sections.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _CRIS_SECTIONS_H
-#define _CRIS_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#endif
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 5b73921b6e9d..3caf05cabfc5 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -3,6 +3,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index f6c3a1690101..102190a61d65 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -31,7 +31,7 @@
  */
 
 #define ATOMIC_INIT(i)		{ (i) }
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = (i))
 
 #ifndef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h
index 6554e78893f2..ae8d423e79d9 100644
--- a/arch/frv/include/asm/processor.h
+++ b/arch/frv/include/asm/processor.h
@@ -35,22 +35,6 @@
 struct task_struct;
 
 /*
- *  CPU type and hardware bug flags. Kept separately for each CPU.
- */
-struct cpuinfo_frv {
-#ifdef CONFIG_MMU
-	unsigned long	*pgd_quick;
-	unsigned long	*pte_quick;
-	unsigned long	pgtable_cache_sz;
-#endif
-} __cacheline_aligned;
-
-extern struct cpuinfo_frv __nongprelbss boot_cpu_data;
-
-#define cpu_data		(&boot_cpu_data)
-#define current_cpu_data	boot_cpu_data
-
-/*
  * Bus types
  */
 #define EISA_bus 0
diff --git a/arch/frv/kernel/irq-mb93091.c b/arch/frv/kernel/irq-mb93091.c
index 2cc327a1ca44..091b2839be90 100644
--- a/arch/frv/kernel/irq-mb93091.c
+++ b/arch/frv/kernel/irq-mb93091.c
@@ -107,25 +107,25 @@ static irqreturn_t fpga_interrupt(int irq, void *_mask)
 static struct irqaction fpga_irq[4]  = {
 	[0] = {
 		.handler	= fpga_interrupt,
-		.flags		= IRQF_DISABLED | IRQF_SHARED,
+		.flags		= IRQF_SHARED,
 		.name		= "fpga.0",
 		.dev_id		= (void *) 0x0028UL,
 	},
 	[1] = {
 		.handler	= fpga_interrupt,
-		.flags		= IRQF_DISABLED | IRQF_SHARED,
+		.flags		= IRQF_SHARED,
 		.name		= "fpga.1",
 		.dev_id		= (void *) 0x0050UL,
 	},
 	[2] = {
 		.handler	= fpga_interrupt,
-		.flags		= IRQF_DISABLED | IRQF_SHARED,
+		.flags		= IRQF_SHARED,
 		.name		= "fpga.2",
 		.dev_id		= (void *) 0x1c00UL,
 	},
 	[3] = {
 		.handler	= fpga_interrupt,
-		.flags		= IRQF_DISABLED | IRQF_SHARED,
+		.flags		= IRQF_SHARED,
 		.name		= "fpga.3",
 		.dev_id		= (void *) 0x6386UL,
 	}
diff --git a/arch/frv/kernel/irq-mb93093.c b/arch/frv/kernel/irq-mb93093.c
index 95e4eb4f1f38..1f3015cf80f5 100644
--- a/arch/frv/kernel/irq-mb93093.c
+++ b/arch/frv/kernel/irq-mb93093.c
@@ -105,7 +105,6 @@ static irqreturn_t fpga_interrupt(int irq, void *_mask)
 static struct irqaction fpga_irq[1]  = {
 	[0] = {
 		.handler	= fpga_interrupt,
-		.flags		= IRQF_DISABLED,
 		.name		= "fpga.0",
 		.dev_id		= (void *) 0x0700UL,
 	}
diff --git a/arch/frv/kernel/irq-mb93493.c b/arch/frv/kernel/irq-mb93493.c
index ba648da0932d..8ca5aa4ff595 100644
--- a/arch/frv/kernel/irq-mb93493.c
+++ b/arch/frv/kernel/irq-mb93493.c
@@ -118,13 +118,13 @@ static irqreturn_t mb93493_interrupt(int irq, void *_piqsr)
 static struct irqaction mb93493_irq[2]  = {
 	[0] = {
 		.handler	= mb93493_interrupt,
-		.flags		= IRQF_DISABLED | IRQF_SHARED,
+		.flags		= IRQF_SHARED,
 		.name		= "mb93493.0",
 		.dev_id		= (void *) __addr_MB93493_IQSR(0),
 	},
 	[1] = {
 		.handler	= mb93493_interrupt,
-		.flags		= IRQF_DISABLED | IRQF_SHARED,
+		.flags		= IRQF_SHARED,
 		.name		= "mb93493.1",
 		.dev_id		= (void *) __addr_MB93493_IQSR(1),
 	}
diff --git a/arch/frv/kernel/setup.c b/arch/frv/kernel/setup.c
index 9f3a7a62d787..9f4a9a607dbe 100644
--- a/arch/frv/kernel/setup.c
+++ b/arch/frv/kernel/setup.c
@@ -104,8 +104,6 @@ unsigned long __nongprelbss dma_coherent_mem_end;
 unsigned long __initdata __sdram_old_base;
 unsigned long __initdata num_mappedpages;
 
-struct cpuinfo_frv __nongprelbss boot_cpu_data;
-
 char __initdata command_line[COMMAND_LINE_SIZE];
 char __initdata redboot_command_line[COMMAND_LINE_SIZE];
 
diff --git a/arch/frv/kernel/time.c b/arch/frv/kernel/time.c
index b457de496b70..332e00bf9d06 100644
--- a/arch/frv/kernel/time.c
+++ b/arch/frv/kernel/time.c
@@ -44,7 +44,6 @@ static irqreturn_t timer_interrupt(int irq, void *dummy);
 
 static struct irqaction timer_irq  = {
 	.handler = timer_interrupt,
-	.flags = IRQF_DISABLED,
 	.name = "timer",
 };
 
diff --git a/arch/frv/mm/extable.c b/arch/frv/mm/extable.c
index 6aea124f574d..2fb9b3ab57b9 100644
--- a/arch/frv/mm/extable.c
+++ b/arch/frv/mm/extable.c
@@ -6,8 +6,6 @@
 #include <linux/spinlock.h>
 #include <asm/uaccess.h>
 
-extern const struct exception_table_entry __attribute__((aligned(8))) __start___ex_table[];
-extern const struct exception_table_entry __attribute__((aligned(8))) __stop___ex_table[];
 extern const void __memset_end, __memset_user_error_lr, __memset_user_error_handler;
 extern const void __memcpy_end, __memcpy_user_error_lr, __memcpy_user_error_handler;
 extern spinlock_t modlist_lock;
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 0e69796b58c7..5f234a5a2320 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -23,6 +23,7 @@ generic-y += ioctls.h
 generic-y += iomap.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index de916b11bff5..93d07025f183 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -94,41 +94,47 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return __oldval;
 }
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	int output;
-
-	__asm__ __volatile__ (
-		"1:	%0 = memw_locked(%1);\n"
-		"	%0 = add(%0,%2);\n"
-		"	memw_locked(%1,P3)=%0;\n"
-		"	if !P3 jump 1b;\n"
-		: "=&r" (output)
-		: "r" (&v->counter), "r" (i)
-		: "memory", "p3"
-	);
-	return output;
-
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	int output;							\
+									\
+	__asm__ __volatile__ (						\
+		"1:	%0 = memw_locked(%1);\n"			\
+		"	%0 = "#op "(%0,%2);\n"				\
+		"	memw_locked(%1,P3)=%0;\n"			\
+		"	if !P3 jump 1b;\n"				\
+		: "=&r" (output)					\
+		: "r" (&v->counter), "r" (i)				\
+		: "memory", "p3"					\
+	);								\
+}									\
+
+#define ATOMIC_OP_RETURN(op)							\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	int output;							\
+									\
+	__asm__ __volatile__ (						\
+		"1:	%0 = memw_locked(%1);\n"			\
+		"	%0 = "#op "(%0,%2);\n"				\
+		"	memw_locked(%1,P3)=%0;\n"			\
+		"	if !P3 jump 1b;\n"				\
+		: "=&r" (output)					\
+		: "r" (&v->counter), "r" (i)				\
+		: "memory", "p3"					\
+	);								\
+	return output;							\
 }
 
-#define atomic_add(i, v) atomic_add_return(i, (v))
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
 
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	int output;
-	__asm__ __volatile__ (
-		"1:	%0 = memw_locked(%1);\n"
-		"	%0 = sub(%0,%2);\n"
-		"	memw_locked(%1,P3)=%0\n"
-		"	if !P3 jump 1b;\n"
-		: "=&r" (output)
-		: "r" (&v->counter), "r" (i)
-		: "memory", "p3"
-	);
-	return output;
-}
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
 
-#define atomic_sub(i, v) atomic_sub_return(i, (v))
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 /**
  * __atomic_add_unless - add unless the number is a given value
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index e8317d2d6c8d..747320be9d0e 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -2,6 +2,7 @@
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 0f8bf48dadf3..0bf03501fe5c 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -21,68 +21,100 @@
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 
 #define atomic_set(v,i)		(((v)->counter) = (i))
 #define atomic64_set(v,i)	(((v)->counter) = (i))
 
-static __inline__ int
-ia64_atomic_add (int i, atomic_t *v)
-{
-	__s32 old, new;
-	CMPXCHG_BUGCHECK_DECL
-
-	do {
-		CMPXCHG_BUGCHECK(v);
-		old = atomic_read(v);
-		new = old + i;
-	} while (ia64_cmpxchg(acq, v, old, new, sizeof(atomic_t)) != old);
-	return new;
+#define ATOMIC_OP(op, c_op)						\
+static __inline__ int							\
+ia64_atomic_##op (int i, atomic_t *v)					\
+{									\
+	__s32 old, new;							\
+	CMPXCHG_BUGCHECK_DECL						\
+									\
+	do {								\
+		CMPXCHG_BUGCHECK(v);					\
+		old = atomic_read(v);					\
+		new = old c_op i;					\
+	} while (ia64_cmpxchg(acq, v, old, new, sizeof(atomic_t)) != old); \
+	return new;							\
 }
 
-static __inline__ long
-ia64_atomic64_add (__s64 i, atomic64_t *v)
-{
-	__s64 old, new;
-	CMPXCHG_BUGCHECK_DECL
-
-	do {
-		CMPXCHG_BUGCHECK(v);
-		old = atomic64_read(v);
-		new = old + i;
-	} while (ia64_cmpxchg(acq, v, old, new, sizeof(atomic64_t)) != old);
-	return new;
-}
+ATOMIC_OP(add, +)
+ATOMIC_OP(sub, -)
 
-static __inline__ int
-ia64_atomic_sub (int i, atomic_t *v)
-{
-	__s32 old, new;
-	CMPXCHG_BUGCHECK_DECL
-
-	do {
-		CMPXCHG_BUGCHECK(v);
-		old = atomic_read(v);
-		new = old - i;
-	} while (ia64_cmpxchg(acq, v, old, new, sizeof(atomic_t)) != old);
-	return new;
-}
+#undef ATOMIC_OP
 
-static __inline__ long
-ia64_atomic64_sub (__s64 i, atomic64_t *v)
-{
-	__s64 old, new;
-	CMPXCHG_BUGCHECK_DECL
-
-	do {
-		CMPXCHG_BUGCHECK(v);
-		old = atomic64_read(v);
-		new = old - i;
-	} while (ia64_cmpxchg(acq, v, old, new, sizeof(atomic64_t)) != old);
-	return new;
+#define atomic_add_return(i,v)						\
+({									\
+	int __ia64_aar_i = (i);						\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
+	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
+	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
+	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
+		: ia64_atomic_add(__ia64_aar_i, v);			\
+})
+
+#define atomic_sub_return(i,v)						\
+({									\
+	int __ia64_asr_i = (i);						\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
+	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
+	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
+	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
+		: ia64_atomic_sub(__ia64_asr_i, v);			\
+})
+
+#define ATOMIC64_OP(op, c_op)						\
+static __inline__ long							\
+ia64_atomic64_##op (__s64 i, atomic64_t *v)				\
+{									\
+	__s64 old, new;							\
+	CMPXCHG_BUGCHECK_DECL						\
+									\
+	do {								\
+		CMPXCHG_BUGCHECK(v);					\
+		old = atomic64_read(v);					\
+		new = old c_op i;					\
+	} while (ia64_cmpxchg(acq, v, old, new, sizeof(atomic64_t)) != old); \
+	return new;							\
 }
 
+ATOMIC64_OP(add, +)
+ATOMIC64_OP(sub, -)
+
+#undef ATOMIC64_OP
+
+#define atomic64_add_return(i,v)					\
+({									\
+	long __ia64_aar_i = (i);					\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
+	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
+	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
+	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
+		: ia64_atomic64_add(__ia64_aar_i, v);			\
+})
+
+#define atomic64_sub_return(i,v)					\
+({									\
+	long __ia64_asr_i = (i);					\
+	(__builtin_constant_p(i)					\
+	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
+	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
+	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
+	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
+		: ia64_atomic64_sub(__ia64_asr_i, v);			\
+})
+
 #define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
@@ -123,30 +155,6 @@ static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u)
 
 #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
 
-#define atomic_add_return(i,v)						\
-({									\
-	int __ia64_aar_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
-		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
-		: ia64_atomic_add(__ia64_aar_i, v);			\
-})
-
-#define atomic64_add_return(i,v)					\
-({									\
-	long __ia64_aar_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
-		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
-		: ia64_atomic64_add(__ia64_aar_i, v);			\
-})
-
 /*
  * Atomically add I to V and return TRUE if the resulting value is
  * negative.
@@ -163,30 +171,6 @@ atomic64_add_negative (__s64 i, atomic64_t *v)
 	return atomic64_add_return(i, v) < 0;
 }
 
-#define atomic_sub_return(i,v)						\
-({									\
-	int __ia64_asr_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
-		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
-		: ia64_atomic_sub(__ia64_asr_i, v);			\
-})
-
-#define atomic64_sub_return(i,v)					\
-({									\
-	long __ia64_asr_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
-		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
-		: ia64_atomic64_sub(__ia64_asr_i, v);			\
-})
-
 #define atomic_dec_return(v)		atomic_sub_return(1, (v))
 #define atomic_inc_return(v)		atomic_add_return(1, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
@@ -199,13 +183,13 @@ atomic64_add_negative (__s64 i, atomic64_t *v)
 #define atomic64_dec_and_test(v)	(atomic64_sub_return(1, (v)) == 0)
 #define atomic64_inc_and_test(v)	(atomic64_add_return(1, (v)) == 0)
 
-#define atomic_add(i,v)			atomic_add_return((i), (v))
-#define atomic_sub(i,v)			atomic_sub_return((i), (v))
+#define atomic_add(i,v)			(void)atomic_add_return((i), (v))
+#define atomic_sub(i,v)			(void)atomic_sub_return((i), (v))
 #define atomic_inc(v)			atomic_add(1, (v))
 #define atomic_dec(v)			atomic_sub(1, (v))
 
-#define atomic64_add(i,v)		atomic64_add_return((i), (v))
-#define atomic64_sub(i,v)		atomic64_sub_return((i), (v))
+#define atomic64_add(i,v)		(void)atomic64_add_return((i), (v))
+#define atomic64_sub(i,v)		(void)atomic64_sub_return((i), (v))
 #define atomic64_inc(v)			atomic64_add(1, (v))
 #define atomic64_dec(v)			atomic64_sub(1, (v))
 
diff --git a/arch/ia64/include/asm/hw_irq.h b/arch/ia64/include/asm/hw_irq.h
index 029bab36cd91..668786e84af8 100644
--- a/arch/ia64/include/asm/hw_irq.h
+++ b/arch/ia64/include/asm/hw_irq.h
@@ -159,7 +159,7 @@ static inline ia64_vector __ia64_irq_to_vector(int irq)
 static inline unsigned int
 __ia64_local_vector_to_irq (ia64_vector vec)
 {
-	return __get_cpu_var(vector_irq)[vec];
+	return __this_cpu_read(vector_irq[vec]);
 }
 #endif
 
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index c7367130ab14..ce53c50d0ba4 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -19,7 +19,6 @@
 #include <asm/ptrace.h>
 #include <asm/ustack.h>
 
-#define __ARCH_WANT_UNLOCKED_CTXSW
 #define ARCH_HAS_PREFETCH_SWITCH_STACK
 
 #define IA64_NUM_PHYS_STACK_REG	96
diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h
index 1a873b36a4a1..2ab2003698ef 100644
--- a/arch/ia64/include/asm/sections.h
+++ b/arch/ia64/include/asm/sections.h
@@ -10,7 +10,7 @@
 #include <linux/uaccess.h>
 #include <asm-generic/sections.h>
 
-extern char __per_cpu_start[], __per_cpu_end[], __phys_per_cpu_start[];
+extern char __phys_per_cpu_start[];
 #ifdef	CONFIG_SMP
 extern char __cpu0_per_cpu[];
 #endif
diff --git a/arch/ia64/include/asm/sn/arch.h b/arch/ia64/include/asm/sn/arch.h
index 7caa1f44cd95..31eb784866f8 100644
--- a/arch/ia64/include/asm/sn/arch.h
+++ b/arch/ia64/include/asm/sn/arch.h
@@ -57,7 +57,7 @@ struct sn_hub_info_s {
 	u16 nasid_bitmask;
 };
 DECLARE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
-#define sn_hub_info 	(&__get_cpu_var(__sn_hub_info))
+#define sn_hub_info 	this_cpu_ptr(&__sn_hub_info)
 #define is_shub2()	(sn_hub_info->shub2)
 #define is_shub1()	(sn_hub_info->shub2 == 0)
 
@@ -72,7 +72,7 @@ DECLARE_PER_CPU(struct sn_hub_info_s, __sn_hub_info);
  * cpu.
  */
 DECLARE_PER_CPU(short, __sn_cnodeid_to_nasid[MAX_COMPACT_NODES]);
-#define sn_cnodeid_to_nasid	(&__get_cpu_var(__sn_cnodeid_to_nasid[0]))
+#define sn_cnodeid_to_nasid	this_cpu_ptr(&__sn_cnodeid_to_nasid[0])
 
 
 extern u8 sn_partition_id;
diff --git a/arch/ia64/include/asm/sn/nodepda.h b/arch/ia64/include/asm/sn/nodepda.h
index ee118b901de4..7c8b4710f071 100644
--- a/arch/ia64/include/asm/sn/nodepda.h
+++ b/arch/ia64/include/asm/sn/nodepda.h
@@ -70,7 +70,7 @@ typedef struct nodepda_s nodepda_t;
  */
 
 DECLARE_PER_CPU(struct nodepda_s *, __sn_nodepda);
-#define sn_nodepda		(__get_cpu_var(__sn_nodepda))
+#define sn_nodepda		__this_cpu_read(__sn_nodepda)
 #define	NODEPDA(cnodeid)	(sn_nodepda->pernode_pdaindr[cnodeid])
 
 /*
diff --git a/arch/ia64/include/asm/switch_to.h b/arch/ia64/include/asm/switch_to.h
index d38c7ea5eea5..e8f3585e7e7a 100644
--- a/arch/ia64/include/asm/switch_to.h
+++ b/arch/ia64/include/asm/switch_to.h
@@ -32,7 +32,7 @@ extern void ia64_load_extra (struct task_struct *task);
 
 #ifdef CONFIG_PERFMON
   DECLARE_PER_CPU(unsigned long, pfm_syst_info);
-# define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1)
+# define PERFMON_IS_SYSWIDE() (__this_cpu_read(pfm_syst_info) & 0x1)
 #else
 # define PERFMON_IS_SYSWIDE() (0)
 #endif
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index 10a14ead70b9..f3b51b57740a 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -11,7 +11,7 @@
 
 
 
-#define NR_syscalls			317 /* length of syscall table */
+#define NR_syscalls			318 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about
diff --git a/arch/ia64/include/asm/uv/uv_hub.h b/arch/ia64/include/asm/uv/uv_hub.h
index 53e9dfacd073..2a88c7204e52 100644
--- a/arch/ia64/include/asm/uv/uv_hub.h
+++ b/arch/ia64/include/asm/uv/uv_hub.h
@@ -108,7 +108,7 @@ struct uv_hub_info_s {
 	unsigned char	n_val;
 };
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info 		(&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info 		this_cpu_ptr(&__uv_hub_info)
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
 
 /*
diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h
index 18026b2eb582..4c2240c1b0cb 100644
--- a/arch/ia64/include/uapi/asm/unistd.h
+++ b/arch/ia64/include/uapi/asm/unistd.h
@@ -330,5 +330,6 @@
 #define __NR_renameat2			1338
 #define __NR_getrandom			1339
 #define __NR_memfd_create		1340
+#define __NR_bpf			1341
 
 #endif /* _UAPI_ASM_IA64_UNISTD_H */
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 01edf242eb29..f5e96dffc63c 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1778,6 +1778,7 @@ sys_call_table:
 	data8 sys_renameat2
 	data8 sys_getrandom
 	data8 sys_memfd_create			// 1340
+	data8 sys_bpf
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
 #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index f2c418281130..812a1e6b3179 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -42,7 +42,7 @@ ia64_vector __ia64_irq_to_vector(int irq)
 
 unsigned int __ia64_local_vector_to_irq (ia64_vector vec)
 {
-	return __get_cpu_var(vector_irq)[vec];
+	return __this_cpu_read(vector_irq[vec]);
 }
 #endif
 
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 03ea78ed64a9..698d8fefde6c 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -330,7 +330,7 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 		int irq;
 		struct irq_desc *desc;
 		struct irq_cfg *cfg;
-		irq = __get_cpu_var(vector_irq)[vector];
+		irq = __this_cpu_read(vector_irq[vector]);
 		if (irq < 0)
 			continue;
 
@@ -344,7 +344,7 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 			goto unlock;
 
 		spin_lock_irqsave(&vector_lock, flags);
-		__get_cpu_var(vector_irq)[vector] = -1;
+		__this_cpu_write(vector_irq[vector], -1);
 		cpu_clear(me, vector_table[vector]);
 		spin_unlock_irqrestore(&vector_lock, flags);
 		cfg->move_cleanup_count--;
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 074fde49c9e6..c7c51445c3be 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -396,7 +396,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
 	unsigned int i;
 	i = atomic_read(&kcb->prev_kprobe_index);
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe[i-1].kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe[i-1].kp);
 	kcb->kprobe_status = kcb->prev_kprobe[i-1].status;
 	atomic_sub(1, &kcb->prev_kprobe_index);
 }
@@ -404,7 +404,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void __kprobes set_current_kprobe(struct kprobe *p,
 			struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 static void kretprobe_trampoline(void)
@@ -823,7 +823,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 			/*
 			 * jprobe instrumented function just completed
 			 */
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs)) {
 				goto ss_probe;
 			}
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index db7b36bb068b..8bfd36af46f8 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1341,7 +1341,7 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
 		ia64_mlogbuf_finish(1);
 	}
 
-	if (__get_cpu_var(ia64_mca_tr_reload)) {
+	if (__this_cpu_read(ia64_mca_tr_reload)) {
 		mca_insert_tr(0x1); /*Reload dynamic itrs*/
 		mca_insert_tr(0x2); /*Reload dynamic itrs*/
 	}
@@ -1868,14 +1868,14 @@ ia64_mca_cpu_init(void *cpu_data)
 		"MCA", cpu);
 	format_mca_init_stack(data, offsetof(struct ia64_mca_cpu, init_stack),
 		"INIT", cpu);
-	__get_cpu_var(ia64_mca_data) = __per_cpu_mca[cpu] = __pa(data);
+	__this_cpu_write(ia64_mca_data, (__per_cpu_mca[cpu] = __pa(data)));
 
 	/*
 	 * Stash away a copy of the PTE needed to map the per-CPU page.
 	 * We may need it during MCA recovery.
 	 */
-	__get_cpu_var(ia64_mca_per_cpu_pte) =
-		pte_val(mk_pte_phys(__pa(cpu_data), PAGE_KERNEL));
+	__this_cpu_write(ia64_mca_per_cpu_pte,
+		pte_val(mk_pte_phys(__pa(cpu_data), PAGE_KERNEL)));
 
 	/*
 	 * Also, stash away a copy of the PAL address and the PTE
@@ -1884,10 +1884,10 @@ ia64_mca_cpu_init(void *cpu_data)
 	pal_vaddr = efi_get_pal_addr();
 	if (!pal_vaddr)
 		return;
-	__get_cpu_var(ia64_mca_pal_base) =
-		GRANULEROUNDDOWN((unsigned long) pal_vaddr);
-	__get_cpu_var(ia64_mca_pal_pte) = pte_val(mk_pte_phys(__pa(pal_vaddr),
-							      PAGE_KERNEL));
+	__this_cpu_write(ia64_mca_pal_base,
+		GRANULEROUNDDOWN((unsigned long) pal_vaddr));
+	__this_cpu_write(ia64_mca_pal_pte, pte_val(mk_pte_phys(__pa(pal_vaddr),
+							      PAGE_KERNEL)));
 }
 
 static void ia64_mca_cmc_vector_adjust(void *dummy)
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index c430f9198d1b..8c3730c3c63d 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -23,7 +23,7 @@ static int ia64_set_msi_irq_affinity(struct irq_data *idata,
 	if (irq_prepare_move(irq, cpu))
 		return -1;
 
-	get_cached_msi_msg(irq, &msg);
+	__get_cached_msi_msg(idata->msi_desc, &msg);
 
 	addr = msg.address_lo;
 	addr &= MSI_ADDR_DEST_ID_MASK;
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index deed6fa96bb0..b51514957620 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -215,7 +215,7 @@ static inline void play_dead(void)
 	unsigned int this_cpu = smp_processor_id();
 
 	/* Ack it */
-	__get_cpu_var(cpu_state) = CPU_DEAD;
+	__this_cpu_write(cpu_state, CPU_DEAD);
 
 	max_xtp();
 	local_irq_disable();
@@ -273,7 +273,7 @@ ia64_save_extra (struct task_struct *task)
 	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
 		pfm_save_regs(task);
 
-	info = __get_cpu_var(pfm_syst_info);
+	info = __this_cpu_read(pfm_syst_info);
 	if (info & PFM_CPUINFO_SYST_WIDE)
 		pfm_syst_wide_update_task(task, info, 0);
 #endif
@@ -293,7 +293,7 @@ ia64_load_extra (struct task_struct *task)
 	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
 		pfm_load_regs(task);
 
-	info = __get_cpu_var(pfm_syst_info);
+	info = __this_cpu_read(pfm_syst_info);
 	if (info & PFM_CPUINFO_SYST_WIDE) 
 		pfm_syst_wide_update_task(task, info, 1);
 #endif
diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c
index d3636e67a98e..6f7d4a4dcf24 100644
--- a/arch/ia64/kernel/traps.c
+++ b/arch/ia64/kernel/traps.c
@@ -299,7 +299,7 @@ handle_fpu_swa (int fp_fault, struct pt_regs *regs, unsigned long isr)
 
 	if (!(current->thread.flags & IA64_THREAD_FPEMU_NOPRINT))  {
 		unsigned long count, current_jiffies = jiffies;
-		struct fpu_swa_msg *cp = &__get_cpu_var(cpulast);
+		struct fpu_swa_msg *cp = this_cpu_ptr(&cpulast);
 
 		if (unlikely(current_jiffies > cp->time))
 			cp->count = 0;
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
index afc58d2799ad..446e7799928c 100644
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -175,8 +175,8 @@ static int sn_set_msi_irq_affinity(struct irq_data *data,
 	 * Release XIO resources for the old MSI PCI address
 	 */
 
-	get_cached_msi_msg(irq, &msg);
-        sn_pdev = (struct pcidev_info *)sn_irq_info->irq_pciioinfo;
+	__get_cached_msi_msg(data->msi_desc, &msg);
+	sn_pdev = (struct pcidev_info *)sn_irq_info->irq_pciioinfo;
 	pdev = sn_pdev->pdi_linux_pcidev;
 	provider = SN_PCIDEV_BUSPROVIDER(pdev);
 
diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c
index 36182c84363c..5f6b6b48c1d5 100644
--- a/arch/ia64/sn/kernel/setup.c
+++ b/arch/ia64/sn/kernel/setup.c
@@ -629,7 +629,7 @@ void sn_cpu_init(void)
 
 	cnode = nasid_to_cnodeid(nasid);
 
-	sn_nodepda = nodepdaindr[cnode];
+	__this_cpu_write(__sn_nodepda, nodepdaindr[cnode]);
 
 	pda->led_address =
 	    (typeof(pda->led_address)) (LED0 + (slice << LED_CPU_SHIFT));
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index 68c845411624..f9c8d9fc5939 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -134,8 +134,8 @@ sn2_ipi_flush_all_tlb(struct mm_struct *mm)
 	itc = ia64_get_itc();
 	smp_flush_tlb_cpumask(*mm_cpumask(mm));
 	itc = ia64_get_itc() - itc;
-	__get_cpu_var(ptcstats).shub_ipi_flushes_itc_clocks += itc;
-	__get_cpu_var(ptcstats).shub_ipi_flushes++;
+	__this_cpu_add(ptcstats.shub_ipi_flushes_itc_clocks, itc);
+	__this_cpu_inc(ptcstats.shub_ipi_flushes);
 }
 
 /**
@@ -199,14 +199,14 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 			start += (1UL << nbits);
 		} while (start < end);
 		ia64_srlz_i();
-		__get_cpu_var(ptcstats).ptc_l++;
+		__this_cpu_inc(ptcstats.ptc_l);
 		preempt_enable();
 		return;
 	}
 
 	if (atomic_read(&mm->mm_users) == 1 && mymm) {
 		flush_tlb_mm(mm);
-		__get_cpu_var(ptcstats).change_rid++;
+		__this_cpu_inc(ptcstats.change_rid);
 		preempt_enable();
 		return;
 	}
@@ -250,11 +250,11 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 	spin_lock_irqsave(PTC_LOCK(shub1), flags);
 	itc2 = ia64_get_itc();
 
-	__get_cpu_var(ptcstats).lock_itc_clocks += itc2 - itc;
-	__get_cpu_var(ptcstats).shub_ptc_flushes++;
-	__get_cpu_var(ptcstats).nodes_flushed += nix;
+	__this_cpu_add(ptcstats.lock_itc_clocks, itc2 - itc);
+	__this_cpu_inc(ptcstats.shub_ptc_flushes);
+	__this_cpu_add(ptcstats.nodes_flushed, nix);
 	if (!mymm)
-		 __get_cpu_var(ptcstats).shub_ptc_flushes_not_my_mm++;
+		 __this_cpu_inc(ptcstats.shub_ptc_flushes_not_my_mm);
 
 	if (use_cpu_ptcga && !mymm) {
 		old_rr = ia64_get_rr(start);
@@ -299,9 +299,9 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 
 done:
 	itc2 = ia64_get_itc() - itc2;
-	__get_cpu_var(ptcstats).shub_itc_clocks += itc2;
-	if (itc2 > __get_cpu_var(ptcstats).shub_itc_clocks_max)
-		__get_cpu_var(ptcstats).shub_itc_clocks_max = itc2;
+	__this_cpu_add(ptcstats.shub_itc_clocks, itc2);
+	if (itc2 > __this_cpu_read(ptcstats.shub_itc_clocks_max))
+		__this_cpu_write(ptcstats.shub_itc_clocks_max, itc2);
 
 	if (old_rr) {
 		ia64_set_rr(start, old_rr);
@@ -311,7 +311,7 @@ done:
 	spin_unlock_irqrestore(PTC_LOCK(shub1), flags);
 
 	if (flush_opt == 1 && deadlock) {
-		__get_cpu_var(ptcstats).deadlocks++;
+		__this_cpu_inc(ptcstats.deadlocks);
 		sn2_ipi_flush_all_tlb(mm);
 	}
 
@@ -334,7 +334,7 @@ sn2_ptc_deadlock_recovery(short *nasids, short ib, short ie, int mynasid,
 	short nasid, i;
 	unsigned long *piows, zeroval, n;
 
-	__get_cpu_var(ptcstats).deadlocks++;
+	__this_cpu_inc(ptcstats.deadlocks);
 
 	piows = (unsigned long *) pda->pio_write_status_addr;
 	zeroval = pda->pio_write_status_val;
@@ -349,7 +349,7 @@ sn2_ptc_deadlock_recovery(short *nasids, short ib, short ie, int mynasid,
 			ptc1 = CHANGE_NASID(nasid, ptc1);
 
 		n = sn2_ptc_deadlock_recovery_core(ptc0, data0, ptc1, data1, piows, zeroval);
-		__get_cpu_var(ptcstats).deadlocks2 += n;
+		__this_cpu_add(ptcstats.deadlocks2, n);
 	}
 
 }
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index accc10a3dc78..3796801d6e0c 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -3,8 +3,10 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += module.h
 generic-y += preempt.h
 generic-y += scatterlist.h
+generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/m32r/include/asm/atomic.h b/arch/m32r/include/asm/atomic.h
index 8ad0ed4182a5..31bb74adba08 100644
--- a/arch/m32r/include/asm/atomic.h
+++ b/arch/m32r/include/asm/atomic.h
@@ -28,7 +28,7 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)	(*(volatile int *)&(v)->counter)
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
 
 /**
  * atomic_set - set atomic variable
@@ -39,85 +39,64 @@
  */
 #define atomic_set(v,i)	(((v)->counter) = (i))
 
-/**
- * atomic_add_return - add integer to atomic variable and return it
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and return (@i + @v).
- */
-static __inline__ int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	int result;
-
-	local_irq_save(flags);
-	__asm__ __volatile__ (
-		"# atomic_add_return		\n\t"
-		DCACHE_CLEAR("%0", "r4", "%1")
-		M32R_LOCK" %0, @%1;		\n\t"
-		"add	%0, %2;			\n\t"
-		M32R_UNLOCK" %0, @%1;		\n\t"
-		: "=&r" (result)
-		: "r" (&v->counter), "r" (i)
-		: "memory"
 #ifdef CONFIG_CHIP_M32700_TS1
-		, "r4"
-#endif	/* CONFIG_CHIP_M32700_TS1 */
-	);
-	local_irq_restore(flags);
-
-	return result;
+#define __ATOMIC_CLOBBER	, "r4"
+#else
+#define __ATOMIC_CLOBBER
+#endif
+
+#define ATOMIC_OP(op)							\
+static __inline__ void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+	int result;							\
+									\
+	local_irq_save(flags);						\
+	__asm__ __volatile__ (						\
+		"# atomic_" #op "		\n\t"			\
+		DCACHE_CLEAR("%0", "r4", "%1")				\
+		M32R_LOCK" %0, @%1;		\n\t"			\
+		#op " %0, %2;			\n\t"			\
+		M32R_UNLOCK" %0, @%1;		\n\t"			\
+		: "=&r" (result)					\
+		: "r" (&v->counter), "r" (i)				\
+		: "memory"						\
+		__ATOMIC_CLOBBER					\
+	);								\
+	local_irq_restore(flags);					\
+}									\
+
+#define ATOMIC_OP_RETURN(op)						\
+static __inline__ int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int result;							\
+									\
+	local_irq_save(flags);						\
+	__asm__ __volatile__ (						\
+		"# atomic_" #op "_return	\n\t"			\
+		DCACHE_CLEAR("%0", "r4", "%1")				\
+		M32R_LOCK" %0, @%1;		\n\t"			\
+		#op " %0, %2;			\n\t"			\
+		M32R_UNLOCK" %0, @%1;		\n\t"			\
+		: "=&r" (result)					\
+		: "r" (&v->counter), "r" (i)				\
+		: "memory"						\
+		__ATOMIC_CLOBBER					\
+	);								\
+	local_irq_restore(flags);					\
+									\
+	return result;							\
 }
 
-/**
- * atomic_sub_return - subtract integer from atomic variable and return it
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and return (@v - @i).
- */
-static __inline__ int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	int result;
-
-	local_irq_save(flags);
-	__asm__ __volatile__ (
-		"# atomic_sub_return		\n\t"
-		DCACHE_CLEAR("%0", "r4", "%1")
-		M32R_LOCK" %0, @%1;		\n\t"
-		"sub	%0, %2;			\n\t"
-		M32R_UNLOCK" %0, @%1;		\n\t"
-		: "=&r" (result)
-		: "r" (&v->counter), "r" (i)
-		: "memory"
-#ifdef CONFIG_CHIP_M32700_TS1
-		, "r4"
-#endif	/* CONFIG_CHIP_M32700_TS1 */
-	);
-	local_irq_restore(flags);
-
-	return result;
-}
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
 
-/**
- * atomic_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v.
- */
-#define atomic_add(i,v) ((void) atomic_add_return((i), (v)))
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
 
-/**
- * atomic_sub - subtract the atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v.
- */
-#define atomic_sub(i,v) ((void) atomic_sub_return((i), (v)))
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 /**
  * atomic_sub_and_test - subtract value from variable and test result
@@ -151,9 +130,7 @@ static __inline__ int atomic_inc_return(atomic_t *v)
 		: "=&r" (result)
 		: "r" (&v->counter)
 		: "memory"
-#ifdef CONFIG_CHIP_M32700_TS1
-		, "r4"
-#endif	/* CONFIG_CHIP_M32700_TS1 */
+		__ATOMIC_CLOBBER
 	);
 	local_irq_restore(flags);
 
@@ -181,9 +158,7 @@ static __inline__ int atomic_dec_return(atomic_t *v)
 		: "=&r" (result)
 		: "r" (&v->counter)
 		: "memory"
-#ifdef CONFIG_CHIP_M32700_TS1
-		, "r4"
-#endif	/* CONFIG_CHIP_M32700_TS1 */
+		__ATOMIC_CLOBBER
 	);
 	local_irq_restore(flags);
 
@@ -280,9 +255,7 @@ static __inline__ void atomic_clear_mask(unsigned long  mask, atomic_t *addr)
 		: "=&r" (tmp)
 		: "r" (addr), "r" (~mask)
 		: "memory"
-#ifdef CONFIG_CHIP_M32700_TS1
-		, "r5"
-#endif	/* CONFIG_CHIP_M32700_TS1 */
+		__ATOMIC_CLOBBER
 	);
 	local_irq_restore(flags);
 }
@@ -302,9 +275,7 @@ static __inline__ void atomic_set_mask(unsigned long  mask, atomic_t *addr)
 		: "=&r" (tmp)
 		: "r" (addr), "r" (mask)
 		: "memory"
-#ifdef CONFIG_CHIP_M32700_TS1
-		, "r5"
-#endif	/* CONFIG_CHIP_M32700_TS1 */
+		__ATOMIC_CLOBBER
 	);
 	local_irq_restore(flags);
 }
diff --git a/arch/m32r/include/asm/sections.h b/arch/m32r/include/asm/sections.h
deleted file mode 100644
index 5e5d21c4908a..000000000000
--- a/arch/m32r/include/asm/sections.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _M32R_SECTIONS_H
-#define _M32R_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#endif	/* _M32R_SECTIONS_H */
diff --git a/arch/m32r/kernel/time.c b/arch/m32r/kernel/time.c
index 1a15f81ea1bd..093f2761aa51 100644
--- a/arch/m32r/kernel/time.c
+++ b/arch/m32r/kernel/time.c
@@ -134,7 +134,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction irq0 = {
 	.handler = timer_interrupt,
-	.flags = IRQF_DISABLED,
 	.name = "MFT2",
 };
 
diff --git a/arch/m68k/platform/68000/Makefile b/arch/m68k/68000/Makefile
index 1eab70c7194b..1eab70c7194b 100644
--- a/arch/m68k/platform/68000/Makefile
+++ b/arch/m68k/68000/Makefile
diff --git a/arch/m68k/platform/68000/bootlogo-vz.h b/arch/m68k/68000/bootlogo-vz.h
index b38e2b255142..b38e2b255142 100644
--- a/arch/m68k/platform/68000/bootlogo-vz.h
+++ b/arch/m68k/68000/bootlogo-vz.h
diff --git a/arch/m68k/platform/68000/bootlogo.h b/arch/m68k/68000/bootlogo.h
index b896c933fafc..b896c933fafc 100644
--- a/arch/m68k/platform/68000/bootlogo.h
+++ b/arch/m68k/68000/bootlogo.h
diff --git a/arch/m68k/platform/68000/entry.S b/arch/m68k/68000/entry.S
index 23ac054c6e1a..259b3661b614 100644
--- a/arch/m68k/platform/68000/entry.S
+++ b/arch/m68k/68000/entry.S
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/m68knommu/platform/68328/entry.S
+ *  entry.S -- non-mmu 68000 interrupt and exception entry points
  *
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *
diff --git a/arch/m68k/platform/68000/head.S b/arch/m68k/68000/head.S
index 536ef9616dad..536ef9616dad 100644
--- a/arch/m68k/platform/68000/head.S
+++ b/arch/m68k/68000/head.S
diff --git a/arch/m68k/platform/68000/ints.c b/arch/m68k/68000/ints.c
index cda49b12d7be..cda49b12d7be 100644
--- a/arch/m68k/platform/68000/ints.c
+++ b/arch/m68k/68000/ints.c
diff --git a/arch/m68k/platform/68000/m68328.c b/arch/m68k/68000/m68328.c
index e53caf4c3bfb..e53caf4c3bfb 100644
--- a/arch/m68k/platform/68000/m68328.c
+++ b/arch/m68k/68000/m68328.c
diff --git a/arch/m68k/platform/68000/m68EZ328.c b/arch/m68k/68000/m68EZ328.c
index 21952906e9e2..21952906e9e2 100644
--- a/arch/m68k/platform/68000/m68EZ328.c
+++ b/arch/m68k/68000/m68EZ328.c
diff --git a/arch/m68k/platform/68000/m68VZ328.c b/arch/m68k/68000/m68VZ328.c
index 0e5e5a10a021..0e5e5a10a021 100644
--- a/arch/m68k/platform/68000/m68VZ328.c
+++ b/arch/m68k/68000/m68VZ328.c
diff --git a/arch/m68k/platform/68000/romvec.S b/arch/m68k/68000/romvec.S
index 15c70cd6453f..15c70cd6453f 100644
--- a/arch/m68k/platform/68000/romvec.S
+++ b/arch/m68k/68000/romvec.S
diff --git a/arch/m68k/platform/68000/timers.c b/arch/m68k/68000/timers.c
index 99a98698bc95..99a98698bc95 100644
--- a/arch/m68k/platform/68000/timers.c
+++ b/arch/m68k/68000/timers.c
diff --git a/arch/m68k/platform/68360/Makefile b/arch/m68k/68360/Makefile
index f6f434383049..591ce42df3de 100644
--- a/arch/m68k/platform/68360/Makefile
+++ b/arch/m68k/68360/Makefile
@@ -1,5 +1,5 @@
 #
-# Makefile for arch/m68knommu/platform/68360.
+# Makefile for 68360 machines.
 #
 model-y			  := ram
 model-$(CONFIG_ROMKERNEL) := rom
diff --git a/arch/m68k/platform/68360/commproc.c b/arch/m68k/68360/commproc.c
index 315727b7ff40..315727b7ff40 100644
--- a/arch/m68k/platform/68360/commproc.c
+++ b/arch/m68k/68360/commproc.c
diff --git a/arch/m68k/platform/68360/config.c b/arch/m68k/68360/config.c
index d493ac43fe3f..17ec416fed9d 100644
--- a/arch/m68k/platform/68360/config.c
+++ b/arch/m68k/68360/config.c
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/m68knommu/platform/68360/config.c
+ *  config.c - non-mmu 68360 platform initialization code
  *
  *  Copyright (c) 2000 Michael Leslie <mleslie@lineo.com>
  *  Copyright (C) 1993 Hamish Macdonald
diff --git a/arch/m68k/platform/68360/entry.S b/arch/m68k/68360/entry.S
index 447c33ef37fd..22eb3022f9ee 100644
--- a/arch/m68k/platform/68360/entry.S
+++ b/arch/m68k/68360/entry.S
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/m68knommu/platform/68360/entry.S
+ *  entry.S - non-mmu 68360 interrupt and exceptions entry points
  *
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *  Copyright (C) 2001 SED Systems, a Division of Calian Ltd.
diff --git a/arch/m68k/platform/68360/head-ram.S b/arch/m68k/68360/head-ram.S
index acd213170d80..62bc56f41d57 100644
--- a/arch/m68k/platform/68360/head-ram.S
+++ b/arch/m68k/68360/head-ram.S
@@ -1,6 +1,5 @@
-/* arch/m68knommu/platform/68360/head-ram.S
- *
- * Startup code for Motorola 68360
+/*
+ * head-ram.S - startup code for Motorola 68360
  *
  * Copyright 2001 (C) SED Systems, a Division of Calian Ltd.
  * Based on: arch/m68knommu/platform/68328/pilot/crt0_rom.S
diff --git a/arch/m68k/platform/68360/head-rom.S b/arch/m68k/68360/head-rom.S
index dfc756d99886..b3a7e40f35e1 100644
--- a/arch/m68k/platform/68360/head-rom.S
+++ b/arch/m68k/68360/head-rom.S
@@ -1,6 +1,5 @@
-/* arch/m68knommu/platform/68360/head-rom.S
- *
- * Startup code for Motorola 68360
+/*
+ * head-rom.S - startup code for Motorola 68360
  *
  * Copyright (C) SED Systems, a Division of Calian Ltd.
  * Based on: arch/m68knommu/platform/68328/pilot/crt0_rom.S
diff --git a/arch/m68k/platform/68360/ints.c b/arch/m68k/68360/ints.c
index 8cd42692331b..2360fc046681 100644
--- a/arch/m68k/platform/68360/ints.c
+++ b/arch/m68k/68360/ints.c
@@ -1,5 +1,5 @@
 /*
- * linux/arch/$(ARCH)/platform/$(PLATFORM)/ints.c
+ * ints.c - first level interrupt handlers
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file COPYING in the main directory of this archive
diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
index 7f7830f2c5bc..0b29dcfef69f 100644
--- a/arch/m68k/Makefile
+++ b/arch/m68k/Makefile
@@ -92,9 +92,9 @@ endif
 #
 head-y				:= arch/m68k/kernel/head.o
 head-$(CONFIG_SUN3)		:= arch/m68k/kernel/sun3-head.o
-head-$(CONFIG_M68360)		:= arch/m68k/platform/68360/head.o
-head-$(CONFIG_M68000)		:= arch/m68k/platform/68000/head.o
-head-$(CONFIG_COLDFIRE)		:= arch/m68k/platform/coldfire/head.o
+head-$(CONFIG_M68360)		:= arch/m68k/68360/head.o
+head-$(CONFIG_M68000)		:= arch/m68k/68000/head.o
+head-$(CONFIG_COLDFIRE)		:= arch/m68k/coldfire/head.o
 
 core-y				+= arch/m68k/kernel/	arch/m68k/mm/
 libs-y				+= arch/m68k/lib/
@@ -114,9 +114,9 @@ core-$(CONFIG_NATFEAT)		+= arch/m68k/emu/
 core-$(CONFIG_M68040)		+= arch/m68k/fpsp040/
 core-$(CONFIG_M68060)		+= arch/m68k/ifpsp060/
 core-$(CONFIG_M68KFPU_EMU)	+= arch/m68k/math-emu/
-core-$(CONFIG_M68360)		+= arch/m68k/platform/68360/
-core-$(CONFIG_M68000)		+= arch/m68k/platform/68000/
-core-$(CONFIG_COLDFIRE)		+= arch/m68k/platform/coldfire/
+core-$(CONFIG_M68360)		+= arch/m68k/68360/
+core-$(CONFIG_M68000)		+= arch/m68k/68000/
+core-$(CONFIG_COLDFIRE)		+= arch/m68k/coldfire/
 
 
 all:	zImage
diff --git a/arch/m68k/platform/coldfire/Makefile b/arch/m68k/coldfire/Makefile
index 68f0fac60099..68f0fac60099 100644
--- a/arch/m68k/platform/coldfire/Makefile
+++ b/arch/m68k/coldfire/Makefile
diff --git a/arch/m68k/platform/coldfire/cache.c b/arch/m68k/coldfire/cache.c
index 71beeaf0c5c4..71beeaf0c5c4 100644
--- a/arch/m68k/platform/coldfire/cache.c
+++ b/arch/m68k/coldfire/cache.c
diff --git a/arch/m68k/platform/coldfire/clk.c b/arch/m68k/coldfire/clk.c
index fddfdccae63b..fddfdccae63b 100644
--- a/arch/m68k/platform/coldfire/clk.c
+++ b/arch/m68k/coldfire/clk.c
diff --git a/arch/m68k/platform/coldfire/device.c b/arch/m68k/coldfire/device.c
index 71ea4c02795d..71ea4c02795d 100644
--- a/arch/m68k/platform/coldfire/device.c
+++ b/arch/m68k/coldfire/device.c
diff --git a/arch/m68k/platform/coldfire/dma.c b/arch/m68k/coldfire/dma.c
index df5ce20d181c..df5ce20d181c 100644
--- a/arch/m68k/platform/coldfire/dma.c
+++ b/arch/m68k/coldfire/dma.c
diff --git a/arch/m68k/platform/coldfire/dma_timer.c b/arch/m68k/coldfire/dma_timer.c
index 235ad57c4707..235ad57c4707 100644
--- a/arch/m68k/platform/coldfire/dma_timer.c
+++ b/arch/m68k/coldfire/dma_timer.c
diff --git a/arch/m68k/platform/coldfire/entry.S b/arch/m68k/coldfire/entry.S
index 881ab8e379d4..52d312d5b4d4 100644
--- a/arch/m68k/platform/coldfire/entry.S
+++ b/arch/m68k/coldfire/entry.S
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/m68knommu/platform/5307/entry.S
+ *  entry.S  -- interrupt and exception processing for ColdFire
  *
  *  Copyright (C) 1999-2007, Greg Ungerer (gerg@snapgear.com)
  *  Copyright (C) 1998  D. Jeff Dionne <jeff@lineo.ca>,
diff --git a/arch/m68k/platform/coldfire/firebee.c b/arch/m68k/coldfire/firebee.c
index 46d50534f981..46d50534f981 100644
--- a/arch/m68k/platform/coldfire/firebee.c
+++ b/arch/m68k/coldfire/firebee.c
diff --git a/arch/m68k/platform/coldfire/gpio.c b/arch/m68k/coldfire/gpio.c
index e7e428681ec5..e7e428681ec5 100644
--- a/arch/m68k/platform/coldfire/gpio.c
+++ b/arch/m68k/coldfire/gpio.c
diff --git a/arch/m68k/platform/coldfire/head.S b/arch/m68k/coldfire/head.S
index fa31be297b85..fa31be297b85 100644
--- a/arch/m68k/platform/coldfire/head.S
+++ b/arch/m68k/coldfire/head.S
diff --git a/arch/m68k/platform/coldfire/intc-2.c b/arch/m68k/coldfire/intc-2.c
index 995093357c59..995093357c59 100644
--- a/arch/m68k/platform/coldfire/intc-2.c
+++ b/arch/m68k/coldfire/intc-2.c
diff --git a/arch/m68k/platform/coldfire/intc-5249.c b/arch/m68k/coldfire/intc-5249.c
index b0d1641053e4..b0d1641053e4 100644
--- a/arch/m68k/platform/coldfire/intc-5249.c
+++ b/arch/m68k/coldfire/intc-5249.c
diff --git a/arch/m68k/platform/coldfire/intc-525x.c b/arch/m68k/coldfire/intc-525x.c
index b23204d059ac..b23204d059ac 100644
--- a/arch/m68k/platform/coldfire/intc-525x.c
+++ b/arch/m68k/coldfire/intc-525x.c
diff --git a/arch/m68k/platform/coldfire/intc-5272.c b/arch/m68k/coldfire/intc-5272.c
index d7b695629a7e..d1e2fbad327c 100644
--- a/arch/m68k/platform/coldfire/intc-5272.c
+++ b/arch/m68k/coldfire/intc-5272.c
@@ -36,7 +36,7 @@
  * they also need acknowledging via acknowledge bits.
  */
 struct irqmap {
-	unsigned char	icr;
+	unsigned int	icr;
 	unsigned char	index;
 	unsigned char	ack;
 };
diff --git a/arch/m68k/platform/coldfire/intc-simr.c b/arch/m68k/coldfire/intc-simr.c
index 7cf2c156f72d..7cf2c156f72d 100644
--- a/arch/m68k/platform/coldfire/intc-simr.c
+++ b/arch/m68k/coldfire/intc-simr.c
diff --git a/arch/m68k/platform/coldfire/intc.c b/arch/m68k/coldfire/intc.c
index cce257420388..cce257420388 100644
--- a/arch/m68k/platform/coldfire/intc.c
+++ b/arch/m68k/coldfire/intc.c
diff --git a/arch/m68k/platform/coldfire/m5206.c b/arch/m68k/coldfire/m5206.c
index 0e55f449a88c..8945f5e7b39c 100644
--- a/arch/m68k/platform/coldfire/m5206.c
+++ b/arch/m68k/coldfire/m5206.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/5206/config.c
+ *	m5206.c  -- platform support for ColdFire 5206 based boards
  *
  *	Copyright (C) 1999-2002, Greg Ungerer (gerg@snapgear.com)
  * 	Copyright (C) 2000-2001, Lineo Inc. (www.lineo.com) 
diff --git a/arch/m68k/platform/coldfire/m520x.c b/arch/m68k/coldfire/m520x.c
index 4040a3c93733..173834f251eb 100644
--- a/arch/m68k/platform/coldfire/m520x.c
+++ b/arch/m68k/coldfire/m520x.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *  linux/arch/m68knommu/platform/520x/config.c
+ *  m520x.c  -- platform support for ColdFire 520x based boards
  *
  *  Copyright (C) 2005,      Freescale (www.freescale.com)
  *  Copyright (C) 2005,      Intec Automation (mike@steroidmicros.com)
diff --git a/arch/m68k/platform/coldfire/m523x.c b/arch/m68k/coldfire/m523x.c
index 6b7135e6d5b4..a191a467eff2 100644
--- a/arch/m68k/platform/coldfire/m523x.c
+++ b/arch/m68k/coldfire/m523x.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/523x/config.c
+ *	m523x.c  -- platform support for ColdFire 523x based boards
  *
  *	Sub-architcture dependent initialization code for the Freescale
  *	523x CPUs.
diff --git a/arch/m68k/platform/coldfire/m5249.c b/arch/m68k/coldfire/m5249.c
index f6253a3313b3..e48f55adc447 100644
--- a/arch/m68k/platform/coldfire/m5249.c
+++ b/arch/m68k/coldfire/m5249.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/5249/config.c
+ *	m5249.c  -- platform support for ColdFire 5249 based boards
  *
  *	Copyright (C) 2002, Greg Ungerer (gerg@snapgear.com)
  */
diff --git a/arch/m68k/platform/coldfire/m525x.c b/arch/m68k/coldfire/m525x.c
index 1adba3909035..3d8583e2187c 100644
--- a/arch/m68k/platform/coldfire/m525x.c
+++ b/arch/m68k/coldfire/m525x.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	525x.c
+ *	525x.c  -- platform support for ColdFire 525x based boards
  *
  *	Copyright (C) 2012, Steven King <sfking@fdwdc.com>
  */
diff --git a/arch/m68k/platform/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c
index 8a4d3cc322c6..b15219ed22bf 100644
--- a/arch/m68k/platform/coldfire/m5272.c
+++ b/arch/m68k/coldfire/m5272.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/5272/config.c
+ *	m5272.c  -- platform support for ColdFire 5272 based boards
  *
  *	Copyright (C) 1999-2002, Greg Ungerer (gerg@snapgear.com)
  *	Copyright (C) 2001-2002, SnapGear Inc. (www.snapgear.com)
diff --git a/arch/m68k/platform/coldfire/m527x.c b/arch/m68k/coldfire/m527x.c
index 62d81ef016f1..2ba470735bed 100644
--- a/arch/m68k/platform/coldfire/m527x.c
+++ b/arch/m68k/coldfire/m527x.c
@@ -1,10 +1,10 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/527x/config.c
+ *	m527x.c  -- platform support for ColdFire 527x based boards
  *
  *	Sub-architcture dependent initialization code for the Freescale
- *	5270/5271 CPUs.
+ *	5270/5271 and 5274/5275 CPUs.
  *
  *	Copyright (C) 1999-2004, Greg Ungerer (gerg@snapgear.com)
  *	Copyright (C) 2001-2004, SnapGear Inc. (www.snapgear.com)
diff --git a/arch/m68k/platform/coldfire/m528x.c b/arch/m68k/coldfire/m528x.c
index 21cd161d36f1..45e947aeade4 100644
--- a/arch/m68k/platform/coldfire/m528x.c
+++ b/arch/m68k/coldfire/m528x.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/528x/config.c
+ *	m528x.c  -- platform support for ColdFire 528x based boards
  *
  *	Sub-architcture dependent initialization code for the Freescale
  *	5280, 5281 and 5282 CPUs.
diff --git a/arch/m68k/platform/coldfire/m5307.c b/arch/m68k/coldfire/m5307.c
index 887435361386..2da1d146e344 100644
--- a/arch/m68k/platform/coldfire/m5307.c
+++ b/arch/m68k/coldfire/m5307.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/5307/config.c
+ *	m5307.c  -- platform support for ColdFire 5307 based boards
  *
  *	Copyright (C) 1999-2002, Greg Ungerer (gerg@snapgear.com)
  *	Copyright (C) 2000, Lineo (www.lineo.com)
diff --git a/arch/m68k/platform/coldfire/m53xx.c b/arch/m68k/coldfire/m53xx.c
index 80879a7fe3d5..80879a7fe3d5 100644
--- a/arch/m68k/platform/coldfire/m53xx.c
+++ b/arch/m68k/coldfire/m53xx.c
diff --git a/arch/m68k/platform/coldfire/m5407.c b/arch/m68k/coldfire/m5407.c
index 2fb3cdbfde30..738eba6be40e 100644
--- a/arch/m68k/platform/coldfire/m5407.c
+++ b/arch/m68k/coldfire/m5407.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/5407/config.c
+ *	m5407.c  -- platform support for ColdFire 5407 based boards
  *
  *	Copyright (C) 1999-2002, Greg Ungerer (gerg@snapgear.com)
  *	Copyright (C) 2000, Lineo (www.lineo.com)
diff --git a/arch/m68k/platform/coldfire/m5441x.c b/arch/m68k/coldfire/m5441x.c
index 98a13cce93d8..98a13cce93d8 100644
--- a/arch/m68k/platform/coldfire/m5441x.c
+++ b/arch/m68k/coldfire/m5441x.c
diff --git a/arch/m68k/platform/coldfire/m54xx.c b/arch/m68k/coldfire/m54xx.c
index 952da53aa0bc..075aaabd1360 100644
--- a/arch/m68k/platform/coldfire/m54xx.c
+++ b/arch/m68k/coldfire/m54xx.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/54xx/config.c
+ *	m54xx.c  -- platform support for ColdFire 54xx based boards
  *
  *	Copyright (C) 2010, Philippe De Muyter <phdm@macqel.be>
  */
@@ -23,7 +23,6 @@
 #include <asm/mcfuart.h>
 #include <asm/mcfclk.h>
 #include <asm/m54xxgpt.h>
-#include <asm/mcfclk.h>
 #ifdef CONFIG_MMU
 #include <asm/mmu_context.h>
 #endif
diff --git a/arch/m68k/platform/coldfire/mcf8390.c b/arch/m68k/coldfire/mcf8390.c
index 23a6874a3248..23a6874a3248 100644
--- a/arch/m68k/platform/coldfire/mcf8390.c
+++ b/arch/m68k/coldfire/mcf8390.c
diff --git a/arch/m68k/platform/coldfire/nettel.c b/arch/m68k/coldfire/nettel.c
index ddc48ec1b800..ddc48ec1b800 100644
--- a/arch/m68k/platform/coldfire/nettel.c
+++ b/arch/m68k/coldfire/nettel.c
diff --git a/arch/m68k/platform/coldfire/pci.c b/arch/m68k/coldfire/pci.c
index df9679238b6d..df9679238b6d 100644
--- a/arch/m68k/platform/coldfire/pci.c
+++ b/arch/m68k/coldfire/pci.c
diff --git a/arch/m68k/platform/coldfire/pit.c b/arch/m68k/coldfire/pit.c
index 493b3111d4c1..493b3111d4c1 100644
--- a/arch/m68k/platform/coldfire/pit.c
+++ b/arch/m68k/coldfire/pit.c
diff --git a/arch/m68k/platform/coldfire/reset.c b/arch/m68k/coldfire/reset.c
index f30952f0cbe6..f30952f0cbe6 100644
--- a/arch/m68k/platform/coldfire/reset.c
+++ b/arch/m68k/coldfire/reset.c
diff --git a/arch/m68k/platform/coldfire/sltimers.c b/arch/m68k/coldfire/sltimers.c
index 831a08cf6f40..831a08cf6f40 100644
--- a/arch/m68k/platform/coldfire/sltimers.c
+++ b/arch/m68k/coldfire/sltimers.c
diff --git a/arch/m68k/platform/coldfire/timers.c b/arch/m68k/coldfire/timers.c
index cd496a20fcc7..cd496a20fcc7 100644
--- a/arch/m68k/platform/coldfire/timers.c
+++ b/arch/m68k/coldfire/timers.c
diff --git a/arch/m68k/platform/coldfire/vectors.c b/arch/m68k/coldfire/vectors.c
index a4dbdecbec7a..08923fe600e0 100644
--- a/arch/m68k/platform/coldfire/vectors.c
+++ b/arch/m68k/coldfire/vectors.c
@@ -1,7 +1,7 @@
 /***************************************************************************/
 
 /*
- *	linux/arch/m68knommu/platform/coldfire/vectors.c
+ *	vectors.c  -- high level trap setup for ColdFire
  *
  *	Copyright (C) 1999-2007, Greg Ungerer <gerg@snapgear.com>
  */
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index c67c94a2d672..dbaf9f3065e8 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -11,6 +11,7 @@ generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 55695212a2ae..e85f047fb072 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -17,7 +17,7 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = i)
 
 /*
@@ -30,16 +30,57 @@
 #define	ASM_DI	"di"
 #endif
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	__asm__ __volatile__("addl %1,%0" : "+m" (*v) : ASM_DI (i));
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	__asm__ __volatile__(#asm_op "l %1,%0" : "+m" (*v) : ASM_DI (i));\
+}									\
+
+#ifdef CONFIG_RMW_INSNS
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	int t, tmp;							\
+									\
+	__asm__ __volatile__(						\
+			"1:	movel %2,%1\n"				\
+			"	" #asm_op "l %3,%1\n"			\
+			"	casl %2,%1,%0\n"			\
+			"	jne 1b"					\
+			: "+m" (*v), "=&d" (t), "=&d" (tmp)		\
+			: "g" (i), "2" (atomic_read(v)));		\
+	return t;							\
 }
 
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	__asm__ __volatile__("subl %1,%0" : "+m" (*v) : ASM_DI (i));
+#else
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int atomic_##op##_return(int i, atomic_t * v)		\
+{									\
+	unsigned long flags;						\
+	int t;								\
+									\
+	local_irq_save(flags);						\
+	t = (v->counter c_op i);					\
+	local_irq_restore(flags);					\
+									\
+	return t;							\
 }
 
+#endif /* CONFIG_RMW_INSNS */
+
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_OP_RETURN(op, c_op, asm_op)
+
+ATOMIC_OPS(add, +=, add)
+ATOMIC_OPS(sub, -=, sub)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
 static inline void atomic_inc(atomic_t *v)
 {
 	__asm__ __volatile__("addql #1,%0" : "+m" (*v));
@@ -76,67 +117,11 @@ static inline int atomic_inc_and_test(atomic_t *v)
 
 #ifdef CONFIG_RMW_INSNS
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	int t, tmp;
-
-	__asm__ __volatile__(
-			"1:	movel %2,%1\n"
-			"	addl %3,%1\n"
-			"	casl %2,%1,%0\n"
-			"	jne 1b"
-			: "+m" (*v), "=&d" (t), "=&d" (tmp)
-			: "g" (i), "2" (atomic_read(v)));
-	return t;
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	int t, tmp;
-
-	__asm__ __volatile__(
-			"1:	movel %2,%1\n"
-			"	subl %3,%1\n"
-			"	casl %2,%1,%0\n"
-			"	jne 1b"
-			: "+m" (*v), "=&d" (t), "=&d" (tmp)
-			: "g" (i), "2" (atomic_read(v)));
-	return t;
-}
-
 #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 #else /* !CONFIG_RMW_INSNS */
 
-static inline int atomic_add_return(int i, atomic_t * v)
-{
-	unsigned long flags;
-	int t;
-
-	local_irq_save(flags);
-	t = atomic_read(v);
-	t += i;
-	atomic_set(v, t);
-	local_irq_restore(flags);
-
-	return t;
-}
-
-static inline int atomic_sub_return(int i, atomic_t * v)
-{
-	unsigned long flags;
-	int t;
-
-	local_irq_save(flags);
-	t = atomic_read(v);
-	t -= i;
-	atomic_set(v, t);
-	local_irq_restore(flags);
-
-	return t;
-}
-
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	unsigned long flags;
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index 52f7e8499172..be4b5a813ad4 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -179,6 +179,15 @@ static inline void *ioremap_fullcache(unsigned long physaddr, unsigned long size
  */
 #define xlate_dev_kmem_ptr(p)	p
 
+static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
+{
+	return (void __iomem *) port;
+}
+
+static inline void ioport_unmap(void __iomem *p)
+{
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* _M68KNOMMU_IO_H */
diff --git a/arch/m68k/include/asm/m54xxpci.h b/arch/m68k/include/asm/m54xxpci.h
index 6fbf54f72f2e..4687f5aa3741 100644
--- a/arch/m68k/include/asm/m54xxpci.h
+++ b/arch/m68k/include/asm/m54xxpci.h
@@ -72,7 +72,7 @@
 #define	PCIRFWPR	(CONFIG_MBAR + 0x84d4)	/* RX FIFO write pointer */
 
 #define	PACR		(CONFIG_MBAR + 0xc00)	/* PCI arbiter control */
-#define	PASR		(COFNIG_MBAR + 0xc04)	/* PCI arbiter status */
+#define	PASR		(CONFIG_MBAR + 0xc04)	/* PCI arbiter status */
 
 /*
  *	Definitions for the Global status and control register.
diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c
index 3a480b3df0d6..9aa01adb407f 100644
--- a/arch/m68k/kernel/sys_m68k.c
+++ b/arch/m68k/kernel/sys_m68k.c
@@ -376,7 +376,6 @@ cache_flush_060 (unsigned long addr, int scope, int cache, unsigned long len)
 asmlinkage int
 sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
 {
-	struct vm_area_struct *vma;
 	int ret = -EINVAL;
 
 	if (scope < FLUSH_SCOPE_LINE || scope > FLUSH_SCOPE_ALL ||
@@ -389,17 +388,21 @@ sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
 		if (!capable(CAP_SYS_ADMIN))
 			goto out;
 	} else {
+		struct vm_area_struct *vma;
+
+		/* Check for overflow.  */
+		if (addr + len < addr)
+			goto out;
+
 		/*
 		 * Verify that the specified address region actually belongs
 		 * to this process.
 		 */
-		vma = find_vma (current->mm, addr);
 		ret = -EINVAL;
-		/* Check for overflow.  */
-		if (addr + len < addr)
-			goto out;
-		if (vma == NULL || addr < vma->vm_start || addr + len > vma->vm_end)
-			goto out;
+		down_read(&current->mm->mmap_sem);
+		vma = find_vma(current->mm, addr);
+		if (!vma || addr < vma->vm_start || addr + len > vma->vm_end)
+			goto out_unlock;
 	}
 
 	if (CPU_IS_020_OR_030) {
@@ -429,7 +432,7 @@ sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
 			__asm__ __volatile__ ("movec %0, %%cacr" : : "r" (cacr));
 		}
 		ret = 0;
-		goto out;
+		goto out_unlock;
 	} else {
 	    /*
 	     * 040 or 060: don't blindly trust 'scope', someone could
@@ -446,6 +449,8 @@ sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
 		ret = cache_flush_060 (addr, scope, cache, len);
 	    }
 	}
+out_unlock:
+	up_read(&current->mm->mmap_sem);
 out:
 	return ret;
 }
diff --git a/arch/m68k/platform/Makefile b/arch/m68k/platform/Makefile
deleted file mode 100644
index fc932bf65d34..000000000000
--- a/arch/m68k/platform/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-#
-# Makefile for the arch/m68knommu/platform.
-#
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index c29ead89a317..7b8111c8f937 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -19,6 +19,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
diff --git a/arch/metag/include/asm/atomic_lnkget.h b/arch/metag/include/asm/atomic_lnkget.h
index d2e60a18986c..948d8688643c 100644
--- a/arch/metag/include/asm/atomic_lnkget.h
+++ b/arch/metag/include/asm/atomic_lnkget.h
@@ -27,85 +27,56 @@ static inline int atomic_read(const atomic_t *v)
 	return temp;
 }
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	int temp;
-
-	asm volatile (
-		"1:	LNKGETD %0, [%1]\n"
-		"	ADD	%0, %0, %2\n"
-		"	LNKSETD [%1], %0\n"
-		"	DEFR	%0, TXSTAT\n"
-		"	ANDT	%0, %0, #HI(0x3f000000)\n"
-		"	CMPT	%0, #HI(0x02000000)\n"
-		"	BNZ	1b\n"
-		: "=&d" (temp)
-		: "da" (&v->counter), "bd" (i)
-		: "cc");
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	int temp;							\
+									\
+	asm volatile (							\
+		"1:	LNKGETD %0, [%1]\n"				\
+		"	" #op "	%0, %0, %2\n"				\
+		"	LNKSETD [%1], %0\n"				\
+		"	DEFR	%0, TXSTAT\n"				\
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"		\
+		"	CMPT	%0, #HI(0x02000000)\n"			\
+		"	BNZ	1b\n"					\
+		: "=&d" (temp)						\
+		: "da" (&v->counter), "bd" (i)				\
+		: "cc");						\
+}									\
+
+#define ATOMIC_OP_RETURN(op)						\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	int result, temp;						\
+									\
+	smp_mb();							\
+									\
+	asm volatile (							\
+		"1:	LNKGETD %1, [%2]\n"				\
+		"	" #op "	%1, %1, %3\n"				\
+		"	LNKSETD [%2], %1\n"				\
+		"	DEFR	%0, TXSTAT\n"				\
+		"	ANDT	%0, %0, #HI(0x3f000000)\n"		\
+		"	CMPT	%0, #HI(0x02000000)\n"			\
+		"	BNZ 1b\n"					\
+		: "=&d" (temp), "=&da" (result)				\
+		: "da" (&v->counter), "bd" (i)				\
+		: "cc");						\
+									\
+	smp_mb();							\
+									\
+	return result;							\
 }
 
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	int temp;
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
 
-	asm volatile (
-		"1:	LNKGETD %0, [%1]\n"
-		"	SUB	%0, %0, %2\n"
-		"	LNKSETD [%1], %0\n"
-		"	DEFR	%0, TXSTAT\n"
-		"	ANDT	%0, %0, #HI(0x3f000000)\n"
-		"	CMPT	%0, #HI(0x02000000)\n"
-		"	BNZ 1b\n"
-		: "=&d" (temp)
-		: "da" (&v->counter), "bd" (i)
-		: "cc");
-}
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	int result, temp;
-
-	smp_mb();
-
-	asm volatile (
-		"1:	LNKGETD %1, [%2]\n"
-		"	ADD	%1, %1, %3\n"
-		"	LNKSETD [%2], %1\n"
-		"	DEFR	%0, TXSTAT\n"
-		"	ANDT	%0, %0, #HI(0x3f000000)\n"
-		"	CMPT	%0, #HI(0x02000000)\n"
-		"	BNZ 1b\n"
-		: "=&d" (temp), "=&da" (result)
-		: "da" (&v->counter), "bd" (i)
-		: "cc");
-
-	smp_mb();
-
-	return result;
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	int result, temp;
-
-	smp_mb();
-
-	asm volatile (
-		"1:	LNKGETD %1, [%2]\n"
-		"	SUB	%1, %1, %3\n"
-		"	LNKSETD [%2], %1\n"
-		"	DEFR	%0, TXSTAT\n"
-		"	ANDT	%0, %0, #HI(0x3f000000)\n"
-		"	CMPT	%0, #HI(0x02000000)\n"
-		"	BNZ	1b\n"
-		: "=&d" (temp), "=&da" (result)
-		: "da" (&v->counter), "bd" (i)
-		: "cc");
-
-	smp_mb();
-
-	return result;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
 {
diff --git a/arch/metag/include/asm/atomic_lock1.h b/arch/metag/include/asm/atomic_lock1.h
index e578955e674b..f5d5898c1020 100644
--- a/arch/metag/include/asm/atomic_lock1.h
+++ b/arch/metag/include/asm/atomic_lock1.h
@@ -37,55 +37,41 @@ static inline int atomic_set(atomic_t *v, int i)
 	return i;
 }
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	unsigned long flags;
-
-	__global_lock1(flags);
-	fence();
-	v->counter += i;
-	__global_unlock1(flags);
+#define ATOMIC_OP(op, c_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	__global_lock1(flags);						\
+	fence();							\
+	v->counter c_op i;						\
+	__global_unlock1(flags);					\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long result;						\
+	unsigned long flags;						\
+									\
+	__global_lock1(flags);						\
+	result = v->counter;						\
+	result c_op i;							\
+	fence();							\
+	v->counter = result;						\
+	__global_unlock1(flags);					\
+									\
+	return result;							\
 }
 
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	unsigned long flags;
+#define ATOMIC_OPS(op, c_op) ATOMIC_OP(op, c_op) ATOMIC_OP_RETURN(op, c_op)
 
-	__global_lock1(flags);
-	fence();
-	v->counter -= i;
-	__global_unlock1(flags);
-}
-
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long result;
-	unsigned long flags;
+ATOMIC_OPS(add, +=)
+ATOMIC_OPS(sub, -=)
 
-	__global_lock1(flags);
-	result = v->counter;
-	result += i;
-	fence();
-	v->counter = result;
-	__global_unlock1(flags);
-
-	return result;
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long result;
-	unsigned long flags;
-
-	__global_lock1(flags);
-	result = v->counter;
-	result -= i;
-	fence();
-	v->counter = result;
-	__global_unlock1(flags);
-
-	return result;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
 {
diff --git a/arch/metag/kernel/perf/perf_event.c b/arch/metag/kernel/perf/perf_event.c
index 02c08737f6aa..2478ec6d23c9 100644
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -258,7 +258,7 @@ int metag_pmu_event_set_period(struct perf_event *event,
 
 static void metag_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -306,7 +306,7 @@ static void metag_pmu_stop(struct perf_event *event, int flags)
 
 static int metag_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = 0, ret = 0;
 
@@ -348,7 +348,7 @@ out:
 
 static void metag_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -597,7 +597,7 @@ static int _hw_perf_event_init(struct perf_event *event)
 
 static void metag_pmu_enable_counter(struct hw_perf_event *event, int idx)
 {
-	struct cpu_hw_events *events = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *events = this_cpu_ptr(&cpu_hw_events);
 	unsigned int config = event->config;
 	unsigned int tmp = config & 0xf0;
 	unsigned long flags;
@@ -670,7 +670,7 @@ unlock:
 
 static void metag_pmu_disable_counter(struct hw_perf_event *event, int idx)
 {
-	struct cpu_hw_events *events = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *events = this_cpu_ptr(&cpu_hw_events);
 	unsigned int tmp = 0;
 	unsigned long flags;
 
@@ -718,7 +718,7 @@ out:
 
 static void metag_pmu_write_counter(int idx, u32 val)
 {
-	struct cpu_hw_events *events = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *events = this_cpu_ptr(&cpu_hw_events);
 	u32 tmp = 0;
 	unsigned long flags;
 
@@ -751,7 +751,7 @@ static int metag_pmu_event_map(int idx)
 static irqreturn_t metag_pmu_counter_overflow(int irq, void *dev)
 {
 	int idx = (int)dev;
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event = cpuhw->events[idx];
 	struct hw_perf_event *hwc = &event->hw;
 	struct pt_regs *regs = get_irq_regs();
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 27a3acda6c19..448143b8cabd 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -5,6 +5,7 @@ generic-y += cputime.h
 generic-y += device.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 574c43000699..ad6badb6be71 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -29,6 +29,7 @@ config MIPS
 	select GENERIC_ATOMIC64 if !64BIT
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select HAVE_DMA_ATTRS
+	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DMA_API_DEBUG
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
@@ -353,6 +354,7 @@ config MIPS_SEAD3
 	bool "MIPS SEAD3 board"
 	select BOOT_ELF32
 	select BOOT_RAW
+	select BUILTIN_DTB
 	select CEVT_R4K
 	select CSRC_R4K
 	select CSRC_GIC
@@ -742,6 +744,7 @@ config CAVIUM_OCTEON_SOC
 	select ARCH_SPARSEMEM_ENABLE
 	select SYS_SUPPORTS_SMP
 	select NR_CPUS_DEFAULT_16
+	select BUILTIN_DTB
 	help
 	  This option supports all of the Octeon reference boards from Cavium
 	  Networks. It builds a kernel that dynamically determines the Octeon
@@ -2482,6 +2485,9 @@ config USE_OF
 	select OF_EARLY_FLATTREE
 	select IRQ_DOMAIN
 
+config BUILTIN_DTB
+	bool
+
 endmenu
 
 config LOCKDEP_SUPPORT
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index bbac51e11179..23cb94806fbc 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -333,6 +333,16 @@ endif
 
 CLEAN_FILES += vmlinux.32 vmlinux.64
 
+# device-trees
+core-$(CONFIG_BUILTIN_DTB) += arch/mips/boot/dts/
+
+%.dtb %.dtb.S %.dtb.o: | scripts
+	$(Q)$(MAKE) $(build)=arch/mips/boot/dts arch/mips/boot/dts/$@
+
+PHONY += dtbs
+dtbs: scripts
+	$(Q)$(MAKE) $(build)=arch/mips/boot/dts dtbs
+
 archprepare:
 ifdef CONFIG_MIPS32_N32
 	@echo '  Checking missing-syscalls for N32'
@@ -367,6 +377,7 @@ define archhelp
 	echo '  vmlinuz.srec         - SREC zboot image'
 	echo '  uImage               - U-Boot image'
 	echo '  uImage.gz            - U-Boot image (gzip)'
+	echo '  dtbs                 - Device-tree blobs for enabled boards'
 	echo
 	echo '  These will be default as appropriate for a configured platform.'
 endef
diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c
index ef93ee3f6a2c..1c64fdbe4c81 100644
--- a/arch/mips/alchemy/devboards/db1300.c
+++ b/arch/mips/alchemy/devboards/db1300.c
@@ -21,6 +21,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/platform_device.h>
 #include <linux/smsc911x.h>
+#include <linux/wm97xx.h>
 
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-au1x00/au1100_mmc.h>
@@ -711,6 +712,46 @@ static struct platform_device db1300_lcd_dev = {
 
 /**********************************************************************/
 
+static void db1300_wm97xx_irqen(struct wm97xx *wm, int enable)
+{
+	if (enable)
+		enable_irq(DB1300_AC97_PEN_INT);
+	else
+		disable_irq_nosync(DB1300_AC97_PEN_INT);
+}
+
+static struct wm97xx_mach_ops db1300_wm97xx_ops = {
+	.irq_enable	= db1300_wm97xx_irqen,
+	.irq_gpio	= WM97XX_GPIO_3,
+};
+
+static int db1300_wm97xx_probe(struct platform_device *pdev)
+{
+	struct wm97xx *wm = platform_get_drvdata(pdev);
+
+	/* external pendown indicator */
+	wm97xx_config_gpio(wm, WM97XX_GPIO_13, WM97XX_GPIO_IN,
+			   WM97XX_GPIO_POL_LOW, WM97XX_GPIO_STICKY,
+			   WM97XX_GPIO_WAKE);
+
+	/* internal "virtual" pendown gpio */
+	wm97xx_config_gpio(wm, WM97XX_GPIO_3, WM97XX_GPIO_OUT,
+			   WM97XX_GPIO_POL_LOW, WM97XX_GPIO_NOTSTICKY,
+			   WM97XX_GPIO_NOWAKE);
+
+	wm->pen_irq = DB1300_AC97_PEN_INT;
+
+	return wm97xx_register_mach_ops(wm, &db1300_wm97xx_ops);
+}
+
+static struct platform_driver db1300_wm97xx_driver = {
+	.driver.name	= "wm97xx-touch",
+	.driver.owner	= THIS_MODULE,
+	.probe		= db1300_wm97xx_probe,
+};
+
+/**********************************************************************/
+
 static struct platform_device *db1300_dev[] __initdata = {
 	&db1300_eth_dev,
 	&db1300_i2c_dev,
@@ -755,6 +796,9 @@ int __init db1300_dev_setup(void)
 	i2c_register_board_info(0, db1300_i2c_devs,
 				ARRAY_SIZE(db1300_i2c_devs));
 
+	if (platform_driver_register(&db1300_wm97xx_driver))
+		pr_warn("DB1300: failed to init touch pen irq support!\n");
+
 	/* Audio PSC clock is supplied by codecs (PSC1, 2) */
 	__raw_writel(PSC_SEL_CLK_SERCLK,
 	    (void __iomem *)KSEG1ADDR(AU1300_PSC1_PHYS_ADDR) + PSC_SEL_OFFSET);
@@ -762,9 +806,10 @@ int __init db1300_dev_setup(void)
 	__raw_writel(PSC_SEL_CLK_SERCLK,
 	    (void __iomem *)KSEG1ADDR(AU1300_PSC2_PHYS_ADDR) + PSC_SEL_OFFSET);
 	wmb();
-	/* I2C uses internal 48MHz EXTCLK1 */
+	/* I2C driver wants 50MHz, get as close as possible */
 	c = clk_get(NULL, "psc3_intclk");
 	if (!IS_ERR(c)) {
+		clk_set_rate(c, 50000000);
 		clk_prepare_enable(c);
 		clk_put(c);
 	}
diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c
index 7e89936f763e..0fd5177e35ab 100644
--- a/arch/mips/alchemy/devboards/db1550.c
+++ b/arch/mips/alchemy/devboards/db1550.c
@@ -34,12 +34,9 @@ static void __init db1550_hw_setup(void)
 	void __iomem *base;
 	unsigned long v;
 
-	/* complete SPI setup: link psc0_intclk to a 48MHz source,
-	 * and assign GPIO16 to PSC0_SYNC1 (SPI cs# line) as well as PSC1_SYNC
-	 * for AC97 on PB1550.
+	/* complete pin setup: assign GPIO16 to PSC0_SYNC1 (SPI cs# line)
+	 * as well as PSC1_SYNC for AC97 on PB1550.
 	 */
-	v = alchemy_rdsys(AU1000_SYS_CLKSRC);
-	alchemy_wrsys(v | 0x000001e0, AU1000_SYS_CLKSRC);
 	v = alchemy_rdsys(AU1000_SYS_PINFUNC);
 	alchemy_wrsys(v | 1 | SYS_PF_PSC1_S1, AU1000_SYS_PINFUNC);
 
@@ -586,11 +583,13 @@ int __init db1550_dev_setup(void)
 
 	c = clk_get(NULL, "psc0_intclk");
 	if (!IS_ERR(c)) {
+		clk_set_rate(c, 50000000);
 		clk_prepare_enable(c);
 		clk_put(c);
 	}
 	c = clk_get(NULL, "psc2_intclk");
 	if (!IS_ERR(c)) {
+		clk_set_rate(c, db1550_spi_platdata.mainclk_hz);
 		clk_prepare_enable(c);
 		clk_put(c);
 	}
diff --git a/arch/mips/alchemy/devboards/platform.c b/arch/mips/alchemy/devboards/platform.c
index 8df86eb94972..be139a0198b0 100644
--- a/arch/mips/alchemy/devboards/platform.c
+++ b/arch/mips/alchemy/devboards/platform.c
@@ -11,6 +11,7 @@
 #include <linux/pm.h>
 
 #include <asm/bootinfo.h>
+#include <asm/idle.h>
 #include <asm/reboot.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-db1x00/bcsr.h>
@@ -53,6 +54,8 @@ static void db1x_power_off(void)
 {
 	bcsr_write(BCSR_RESETS, 0);
 	bcsr_write(BCSR_SYSTEM, BCSR_SYSTEM_PWROFF | BCSR_SYSTEM_RESET);
+	while (1)		/* sit and spin */
+		cpu_wait();
 }
 
 static void db1x_reset(char *c)
diff --git a/arch/mips/boot/.gitignore b/arch/mips/boot/.gitignore
index a73d6e2c4f64..d3962cd5ce0c 100644
--- a/arch/mips/boot/.gitignore
+++ b/arch/mips/boot/.gitignore
@@ -5,3 +5,4 @@ zImage
 zImage.tmp
 calc_vmlinuz_load_addr
 uImage
+*.dtb
diff --git a/arch/mips/boot/dts/Makefile b/arch/mips/boot/dts/Makefile
new file mode 100644
index 000000000000..ca9c90e2cabf
--- /dev/null
+++ b/arch/mips/boot/dts/Makefile
@@ -0,0 +1,20 @@
+dtb-$(CONFIG_CAVIUM_OCTEON_SOC)		+= octeon_3xxx.dtb octeon_68xx.dtb
+dtb-$(CONFIG_DT_EASY50712)		+= easy50712.dtb
+dtb-$(CONFIG_DT_XLP_EVP)		+= xlp_evp.dtb
+dtb-$(CONFIG_DT_XLP_SVP)		+= xlp_svp.dtb
+dtb-$(CONFIG_DT_XLP_FVP)		+= xlp_fvp.dtb
+dtb-$(CONFIG_DT_XLP_GVP)		+= xlp_gvp.dtb
+dtb-$(CONFIG_DTB_RT2880_EVAL)		+= rt2880_eval.dtb
+dtb-$(CONFIG_DTB_RT305X_EVAL)		+= rt3052_eval.dtb
+dtb-$(CONFIG_DTB_RT3883_EVAL)		+= rt3883_eval.dtb
+dtb-$(CONFIG_DTB_MT7620A_EVAL)		+= mt7620a_eval.dtb
+dtb-$(CONFIG_MIPS_SEAD3)		+= sead3.dtb
+
+obj-y		+= $(patsubst %.dtb, %.dtb.o, $(dtb-y))
+
+targets		+= dtbs
+targets		+= $(dtb-y)
+
+dtbs: $(addprefix $(obj)/, $(dtb-y))
+
+clean-files	+= *.dtb *.dtb.S
diff --git a/arch/mips/lantiq/dts/danube.dtsi b/arch/mips/boot/dts/danube.dtsi
index d4c59e003708..d4c59e003708 100644
--- a/arch/mips/lantiq/dts/danube.dtsi
+++ b/arch/mips/boot/dts/danube.dtsi
diff --git a/arch/mips/lantiq/dts/easy50712.dts b/arch/mips/boot/dts/easy50712.dts
index 143b8a37b5e4..143b8a37b5e4 100644
--- a/arch/mips/lantiq/dts/easy50712.dts
+++ b/arch/mips/boot/dts/easy50712.dts
diff --git a/arch/mips/ralink/dts/mt7620a.dtsi b/arch/mips/boot/dts/mt7620a.dtsi
index 08bf24fefe9f..08bf24fefe9f 100644
--- a/arch/mips/ralink/dts/mt7620a.dtsi
+++ b/arch/mips/boot/dts/mt7620a.dtsi
diff --git a/arch/mips/ralink/dts/mt7620a_eval.dts b/arch/mips/boot/dts/mt7620a_eval.dts
index 709f58132f5c..709f58132f5c 100644
--- a/arch/mips/ralink/dts/mt7620a_eval.dts
+++ b/arch/mips/boot/dts/mt7620a_eval.dts
diff --git a/arch/mips/cavium-octeon/octeon_3xxx.dts b/arch/mips/boot/dts/octeon_3xxx.dts
index fa33115bde33..fa33115bde33 100644
--- a/arch/mips/cavium-octeon/octeon_3xxx.dts
+++ b/arch/mips/boot/dts/octeon_3xxx.dts
diff --git a/arch/mips/cavium-octeon/octeon_68xx.dts b/arch/mips/boot/dts/octeon_68xx.dts
index 79b46fcb0a11..79b46fcb0a11 100644
--- a/arch/mips/cavium-octeon/octeon_68xx.dts
+++ b/arch/mips/boot/dts/octeon_68xx.dts
diff --git a/arch/mips/ralink/dts/rt2880.dtsi b/arch/mips/boot/dts/rt2880.dtsi
index 182afde2f2e1..182afde2f2e1 100644
--- a/arch/mips/ralink/dts/rt2880.dtsi
+++ b/arch/mips/boot/dts/rt2880.dtsi
diff --git a/arch/mips/ralink/dts/rt2880_eval.dts b/arch/mips/boot/dts/rt2880_eval.dts
index 0a685db093d4..0a685db093d4 100644
--- a/arch/mips/ralink/dts/rt2880_eval.dts
+++ b/arch/mips/boot/dts/rt2880_eval.dts
diff --git a/arch/mips/ralink/dts/rt3050.dtsi b/arch/mips/boot/dts/rt3050.dtsi
index e3203d414fee..e3203d414fee 100644
--- a/arch/mips/ralink/dts/rt3050.dtsi
+++ b/arch/mips/boot/dts/rt3050.dtsi
diff --git a/arch/mips/ralink/dts/rt3052_eval.dts b/arch/mips/boot/dts/rt3052_eval.dts
index ec9e9a035541..ec9e9a035541 100644
--- a/arch/mips/ralink/dts/rt3052_eval.dts
+++ b/arch/mips/boot/dts/rt3052_eval.dts
diff --git a/arch/mips/ralink/dts/rt3883.dtsi b/arch/mips/boot/dts/rt3883.dtsi
index 3b131dd0d5ac..3b131dd0d5ac 100644
--- a/arch/mips/ralink/dts/rt3883.dtsi
+++ b/arch/mips/boot/dts/rt3883.dtsi
diff --git a/arch/mips/ralink/dts/rt3883_eval.dts b/arch/mips/boot/dts/rt3883_eval.dts
index e8df21a5d10d..e8df21a5d10d 100644
--- a/arch/mips/ralink/dts/rt3883_eval.dts
+++ b/arch/mips/boot/dts/rt3883_eval.dts
diff --git a/arch/mips/mti-sead3/sead3.dts b/arch/mips/boot/dts/sead3.dts
index e4b317d414f1..e4b317d414f1 100644
--- a/arch/mips/mti-sead3/sead3.dts
+++ b/arch/mips/boot/dts/sead3.dts
diff --git a/arch/mips/netlogic/dts/xlp_evp.dts b/arch/mips/boot/dts/xlp_evp.dts
index 89ad04808c02..89ad04808c02 100644
--- a/arch/mips/netlogic/dts/xlp_evp.dts
+++ b/arch/mips/boot/dts/xlp_evp.dts
diff --git a/arch/mips/netlogic/dts/xlp_fvp.dts b/arch/mips/boot/dts/xlp_fvp.dts
index 63e62b7bd758..63e62b7bd758 100644
--- a/arch/mips/netlogic/dts/xlp_fvp.dts
+++ b/arch/mips/boot/dts/xlp_fvp.dts
diff --git a/arch/mips/netlogic/dts/xlp_gvp.dts b/arch/mips/boot/dts/xlp_gvp.dts
index bb4ecd1d47fc..bb4ecd1d47fc 100644
--- a/arch/mips/netlogic/dts/xlp_gvp.dts
+++ b/arch/mips/boot/dts/xlp_gvp.dts
diff --git a/arch/mips/netlogic/dts/xlp_svp.dts b/arch/mips/boot/dts/xlp_svp.dts
index 1ebd00edaacc..1ebd00edaacc 100644
--- a/arch/mips/netlogic/dts/xlp_svp.dts
+++ b/arch/mips/boot/dts/xlp_svp.dts
diff --git a/arch/mips/cavium-octeon/.gitignore b/arch/mips/cavium-octeon/.gitignore
deleted file mode 100644
index 39c968605ff6..000000000000
--- a/arch/mips/cavium-octeon/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-*.dtb.S
-*.dtb
diff --git a/arch/mips/cavium-octeon/Makefile b/arch/mips/cavium-octeon/Makefile
index 4e952043c922..42f5f1a4b40a 100644
--- a/arch/mips/cavium-octeon/Makefile
+++ b/arch/mips/cavium-octeon/Makefile
@@ -20,13 +20,3 @@ obj-y += executive/
 obj-$(CONFIG_MTD)		      += flash_setup.o
 obj-$(CONFIG_SMP)		      += smp.o
 obj-$(CONFIG_OCTEON_ILM)	      += oct_ilm.o
-
-DTS_FILES = octeon_3xxx.dts octeon_68xx.dts
-DTB_FILES = $(patsubst %.dts, %.dtb, $(DTS_FILES))
-
-obj-y += $(patsubst %.dts, %.dtb.o, $(DTS_FILES))
-
-# Let's keep the .dtb files around in case we want to look at them.
-.SECONDARY:  $(addprefix $(obj)/, $(DTB_FILES))
-
-clean-files += $(DTB_FILES) $(patsubst %.dtb, %.dtb.S, $(DTB_FILES))
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 1b82ac6921e0..741734049675 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -264,13 +264,13 @@ static void octeon_irq_ciu_enable_local(struct irq_data *data)
 	unsigned long *pen;
 	unsigned long flags;
 	union octeon_ciu_chip_data cd;
-	raw_spinlock_t *lock = &__get_cpu_var(octeon_irq_ciu_spinlock);
+	raw_spinlock_t *lock = this_cpu_ptr(&octeon_irq_ciu_spinlock);
 
 	cd.p = irq_data_get_irq_chip_data(data);
 
 	raw_spin_lock_irqsave(lock, flags);
 	if (cd.s.line == 0) {
-		pen = &__get_cpu_var(octeon_irq_ciu0_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu0_en_mirror);
 		__set_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -279,7 +279,7 @@ static void octeon_irq_ciu_enable_local(struct irq_data *data)
 		wmb();
 		cvmx_write_csr(CVMX_CIU_INTX_EN0(cvmx_get_core_num() * 2), *pen);
 	} else {
-		pen = &__get_cpu_var(octeon_irq_ciu1_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu1_en_mirror);
 		__set_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -296,13 +296,13 @@ static void octeon_irq_ciu_disable_local(struct irq_data *data)
 	unsigned long *pen;
 	unsigned long flags;
 	union octeon_ciu_chip_data cd;
-	raw_spinlock_t *lock = &__get_cpu_var(octeon_irq_ciu_spinlock);
+	raw_spinlock_t *lock = this_cpu_ptr(&octeon_irq_ciu_spinlock);
 
 	cd.p = irq_data_get_irq_chip_data(data);
 
 	raw_spin_lock_irqsave(lock, flags);
 	if (cd.s.line == 0) {
-		pen = &__get_cpu_var(octeon_irq_ciu0_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu0_en_mirror);
 		__clear_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -311,7 +311,7 @@ static void octeon_irq_ciu_disable_local(struct irq_data *data)
 		wmb();
 		cvmx_write_csr(CVMX_CIU_INTX_EN0(cvmx_get_core_num() * 2), *pen);
 	} else {
-		pen = &__get_cpu_var(octeon_irq_ciu1_en_mirror);
+		pen = this_cpu_ptr(&octeon_irq_ciu1_en_mirror);
 		__clear_bit(cd.s.bit, pen);
 		/*
 		 * Must be visible to octeon_irq_ip{2,3}_ciu() before
@@ -431,11 +431,11 @@ static void octeon_irq_ciu_enable_local_v2(struct irq_data *data)
 
 	if (cd.s.line == 0) {
 		int index = cvmx_get_core_num() * 2;
-		set_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu0_en_mirror));
+		set_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu0_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN0_W1S(index), mask);
 	} else {
 		int index = cvmx_get_core_num() * 2 + 1;
-		set_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu1_en_mirror));
+		set_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu1_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN1_W1S(index), mask);
 	}
 }
@@ -450,11 +450,11 @@ static void octeon_irq_ciu_disable_local_v2(struct irq_data *data)
 
 	if (cd.s.line == 0) {
 		int index = cvmx_get_core_num() * 2;
-		clear_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu0_en_mirror));
+		clear_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu0_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN0_W1C(index), mask);
 	} else {
 		int index = cvmx_get_core_num() * 2 + 1;
-		clear_bit(cd.s.bit, &__get_cpu_var(octeon_irq_ciu1_en_mirror));
+		clear_bit(cd.s.bit, this_cpu_ptr(&octeon_irq_ciu1_en_mirror));
 		cvmx_write_csr(CVMX_CIU_INTX_EN1_W1C(index), mask);
 	}
 }
@@ -1063,7 +1063,7 @@ static void octeon_irq_ip2_ciu(void)
 	const unsigned long core_id = cvmx_get_core_num();
 	u64 ciu_sum = cvmx_read_csr(CVMX_CIU_INTX_SUM0(core_id * 2));
 
-	ciu_sum &= __get_cpu_var(octeon_irq_ciu0_en_mirror);
+	ciu_sum &= __this_cpu_read(octeon_irq_ciu0_en_mirror);
 	if (likely(ciu_sum)) {
 		int bit = fls64(ciu_sum) - 1;
 		int irq = octeon_irq_ciu_to_irq[0][bit];
@@ -1080,7 +1080,7 @@ static void octeon_irq_ip3_ciu(void)
 {
 	u64 ciu_sum = cvmx_read_csr(CVMX_CIU_INT_SUM1);
 
-	ciu_sum &= __get_cpu_var(octeon_irq_ciu1_en_mirror);
+	ciu_sum &= __this_cpu_read(octeon_irq_ciu1_en_mirror);
 	if (likely(ciu_sum)) {
 		int bit = fls64(ciu_sum) - 1;
 		int irq = octeon_irq_ciu_to_irq[1][bit];
@@ -1129,10 +1129,10 @@ static void octeon_irq_init_ciu_percpu(void)
 	int coreid = cvmx_get_core_num();
 
 
-	__get_cpu_var(octeon_irq_ciu0_en_mirror) = 0;
-	__get_cpu_var(octeon_irq_ciu1_en_mirror) = 0;
+	__this_cpu_write(octeon_irq_ciu0_en_mirror, 0);
+	__this_cpu_write(octeon_irq_ciu1_en_mirror, 0);
 	wmb();
-	raw_spin_lock_init(&__get_cpu_var(octeon_irq_ciu_spinlock));
+	raw_spin_lock_init(this_cpu_ptr(&octeon_irq_ciu_spinlock));
 	/*
 	 * Disable All CIU Interrupts. The ones we need will be
 	 * enabled later.  Read the SUM register so we know the write
diff --git a/arch/mips/configs/sead3_defconfig b/arch/mips/configs/sead3_defconfig
index 0abe681c11a0..dae9354b6256 100644
--- a/arch/mips/configs/sead3_defconfig
+++ b/arch/mips/configs/sead3_defconfig
@@ -31,8 +31,8 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
diff --git a/arch/mips/configs/sead3micro_defconfig b/arch/mips/configs/sead3micro_defconfig
index 2a0da5bf4b64..cd91a775c74e 100644
--- a/arch/mips/configs/sead3micro_defconfig
+++ b/arch/mips/configs/sead3micro_defconfig
@@ -32,8 +32,8 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 335e5290ec75..72e1cf1cab00 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -1,8 +1,10 @@
 # MIPS headers
 generic-y += cputime.h
 generic-y += current.h
+generic-y += dma-contiguous.h
 generic-y += emergency-restart.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mutex.h
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 37b2befe651a..6dd6bfc607e9 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -29,7 +29,7 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 
 /*
  * atomic_set - set atomic variable
@@ -40,195 +40,103 @@
  */
 #define atomic_set(v, i)		((v)->counter = (i))
 
-/*
- * atomic_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v.
- */
-static __inline__ void atomic_add(int i, atomic_t * v)
-{
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		int temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	ll	%0, %1		# atomic_add		\n"
-		"	addu	%0, %2					\n"
-		"	sc	%0, %1					\n"
-		"	beqzl	%0, 1b					\n"
-		"	.set	mips0					\n"
-		: "=&r" (temp), "+m" (v->counter)
-		: "Ir" (i));
-	} else if (kernel_uses_llsc) {
-		int temp;
-
-		do {
-			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
-			"	ll	%0, %1		# atomic_add	\n"
-			"	addu	%0, %2				\n"
-			"	sc	%0, %1				\n"
-			"	.set	mips0				\n"
-			: "=&r" (temp), "+m" (v->counter)
-			: "Ir" (i));
-		} while (unlikely(!temp));
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		v->counter += i;
-		raw_local_irq_restore(flags);
-	}
-}
-
-/*
- * atomic_sub - subtract the atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v.
- */
-static __inline__ void atomic_sub(int i, atomic_t * v)
-{
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		int temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	ll	%0, %1		# atomic_sub		\n"
-		"	subu	%0, %2					\n"
-		"	sc	%0, %1					\n"
-		"	beqzl	%0, 1b					\n"
-		"	.set	mips0					\n"
-		: "=&r" (temp), "+m" (v->counter)
-		: "Ir" (i));
-	} else if (kernel_uses_llsc) {
-		int temp;
-
-		do {
-			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
-			"	ll	%0, %1		# atomic_sub	\n"
-			"	subu	%0, %2				\n"
-			"	sc	%0, %1				\n"
-			"	.set	mips0				\n"
-			: "=&r" (temp), "+m" (v->counter)
-			: "Ir" (i));
-		} while (unlikely(!temp));
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		v->counter -= i;
-		raw_local_irq_restore(flags);
-	}
-}
-
-/*
- * Same as above, but return the result value
- */
-static __inline__ int atomic_add_return(int i, atomic_t * v)
-{
-	int result;
-
-	smp_mb__before_llsc();
-
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		int temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	ll	%1, %2		# atomic_add_return	\n"
-		"	addu	%0, %1, %3				\n"
-		"	sc	%0, %2					\n"
-		"	beqzl	%0, 1b					\n"
-		"	addu	%0, %1, %3				\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp), "+m" (v->counter)
-		: "Ir" (i));
-	} else if (kernel_uses_llsc) {
-		int temp;
-
-		do {
-			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
-			"	ll	%1, %2	# atomic_add_return	\n"
-			"	addu	%0, %1, %3			\n"
-			"	sc	%0, %2				\n"
-			"	.set	mips0				\n"
-			: "=&r" (result), "=&r" (temp), "+m" (v->counter)
-			: "Ir" (i));
-		} while (unlikely(!result));
-
-		result = temp + i;
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		result = v->counter;
-		result += i;
-		v->counter = result;
-		raw_local_irq_restore(flags);
-	}
-
-	smp_llsc_mb();
-
-	return result;
+#define ATOMIC_OP(op, c_op, asm_op)						\
+static __inline__ void atomic_##op(int i, atomic_t * v)				\
+{										\
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {				\
+		int temp;							\
+										\
+		__asm__ __volatile__(						\
+		"	.set	arch=r4000				\n"	\
+		"1:	ll	%0, %1		# atomic_" #op "	\n"	\
+		"	" #asm_op " %0, %2				\n"	\
+		"	sc	%0, %1					\n"	\
+		"	beqzl	%0, 1b					\n"	\
+		"	.set	mips0					\n"	\
+		: "=&r" (temp), "+m" (v->counter)				\
+		: "Ir" (i));							\
+	} else if (kernel_uses_llsc) {						\
+		int temp;							\
+										\
+		do {								\
+			__asm__ __volatile__(					\
+			"	.set	arch=r4000			\n"	\
+			"	ll	%0, %1		# atomic_" #op "\n"	\
+			"	" #asm_op " %0, %2			\n"	\
+			"	sc	%0, %1				\n"	\
+			"	.set	mips0				\n"	\
+			: "=&r" (temp), "+m" (v->counter)			\
+			: "Ir" (i));						\
+		} while (unlikely(!temp));					\
+	} else {								\
+		unsigned long flags;						\
+										\
+		raw_local_irq_save(flags);					\
+		v->counter c_op i;						\
+		raw_local_irq_restore(flags);					\
+	}									\
+}										\
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)					\
+static __inline__ int atomic_##op##_return(int i, atomic_t * v)			\
+{										\
+	int result;								\
+										\
+	smp_mb__before_llsc();							\
+										\
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {				\
+		int temp;							\
+										\
+		__asm__ __volatile__(						\
+		"	.set	arch=r4000				\n"	\
+		"1:	ll	%1, %2		# atomic_" #op "_return	\n"	\
+		"	" #asm_op " %0, %1, %3				\n"	\
+		"	sc	%0, %2					\n"	\
+		"	beqzl	%0, 1b					\n"	\
+		"	" #asm_op " %0, %1, %3				\n"	\
+		"	.set	mips0					\n"	\
+		: "=&r" (result), "=&r" (temp), "+m" (v->counter)		\
+		: "Ir" (i));							\
+	} else if (kernel_uses_llsc) {						\
+		int temp;							\
+										\
+		do {								\
+			__asm__ __volatile__(					\
+			"	.set	arch=r4000			\n"	\
+			"	ll	%1, %2	# atomic_" #op "_return	\n"	\
+			"	" #asm_op " %0, %1, %3			\n"	\
+			"	sc	%0, %2				\n"	\
+			"	.set	mips0				\n"	\
+			: "=&r" (result), "=&r" (temp), "+m" (v->counter)	\
+			: "Ir" (i));						\
+		} while (unlikely(!result));					\
+										\
+		result = temp; result c_op i;					\
+	} else {								\
+		unsigned long flags;						\
+										\
+		raw_local_irq_save(flags);					\
+		result = v->counter;						\
+		result c_op i;							\
+		v->counter = result;						\
+		raw_local_irq_restore(flags);					\
+	}									\
+										\
+	smp_llsc_mb();								\
+										\
+	return result;								\
 }
 
-static __inline__ int atomic_sub_return(int i, atomic_t * v)
-{
-	int result;
+#define ATOMIC_OPS(op, c_op, asm_op)						\
+	ATOMIC_OP(op, c_op, asm_op)						\
+	ATOMIC_OP_RETURN(op, c_op, asm_op)
 
-	smp_mb__before_llsc();
+ATOMIC_OPS(add, +=, addu)
+ATOMIC_OPS(sub, -=, subu)
 
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		int temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	ll	%1, %2		# atomic_sub_return	\n"
-		"	subu	%0, %1, %3				\n"
-		"	sc	%0, %2					\n"
-		"	beqzl	%0, 1b					\n"
-		"	subu	%0, %1, %3				\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
-		: "Ir" (i), "m" (v->counter)
-		: "memory");
-
-		result = temp - i;
-	} else if (kernel_uses_llsc) {
-		int temp;
-
-		do {
-			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
-			"	ll	%1, %2	# atomic_sub_return	\n"
-			"	subu	%0, %1, %3			\n"
-			"	sc	%0, %2				\n"
-			"	.set	mips0				\n"
-			: "=&r" (result), "=&r" (temp), "+m" (v->counter)
-			: "Ir" (i));
-		} while (unlikely(!result));
-
-		result = temp - i;
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		result = v->counter;
-		result -= i;
-		v->counter = result;
-		raw_local_irq_restore(flags);
-	}
-
-	smp_llsc_mb();
-
-	return result;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 /*
  * atomic_sub_if_positive - conditionally subtract integer from atomic variable
@@ -398,7 +306,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
  * @v: pointer of type atomic64_t
  *
  */
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 
 /*
  * atomic64_set - set atomic variable
@@ -407,195 +315,104 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
  */
 #define atomic64_set(v, i)	((v)->counter = (i))
 
-/*
- * atomic64_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic64_t
- *
- * Atomically adds @i to @v.
- */
-static __inline__ void atomic64_add(long i, atomic64_t * v)
-{
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		long temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	lld	%0, %1		# atomic64_add		\n"
-		"	daddu	%0, %2					\n"
-		"	scd	%0, %1					\n"
-		"	beqzl	%0, 1b					\n"
-		"	.set	mips0					\n"
-		: "=&r" (temp), "+m" (v->counter)
-		: "Ir" (i));
-	} else if (kernel_uses_llsc) {
-		long temp;
-
-		do {
-			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
-			"	lld	%0, %1		# atomic64_add	\n"
-			"	daddu	%0, %2				\n"
-			"	scd	%0, %1				\n"
-			"	.set	mips0				\n"
-			: "=&r" (temp), "+m" (v->counter)
-			: "Ir" (i));
-		} while (unlikely(!temp));
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		v->counter += i;
-		raw_local_irq_restore(flags);
-	}
+#define ATOMIC64_OP(op, c_op, asm_op)						\
+static __inline__ void atomic64_##op(long i, atomic64_t * v)			\
+{										\
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {				\
+		long temp;							\
+										\
+		__asm__ __volatile__(						\
+		"	.set	arch=r4000				\n"	\
+		"1:	lld	%0, %1		# atomic64_" #op "	\n"	\
+		"	" #asm_op " %0, %2				\n"	\
+		"	scd	%0, %1					\n"	\
+		"	beqzl	%0, 1b					\n"	\
+		"	.set	mips0					\n"	\
+		: "=&r" (temp), "+m" (v->counter)				\
+		: "Ir" (i));							\
+	} else if (kernel_uses_llsc) {						\
+		long temp;							\
+										\
+		do {								\
+			__asm__ __volatile__(					\
+			"	.set	arch=r4000			\n"	\
+			"	lld	%0, %1		# atomic64_" #op "\n"	\
+			"	" #asm_op " %0, %2			\n"	\
+			"	scd	%0, %1				\n"	\
+			"	.set	mips0				\n"	\
+			: "=&r" (temp), "+m" (v->counter)			\
+			: "Ir" (i));						\
+		} while (unlikely(!temp));					\
+	} else {								\
+		unsigned long flags;						\
+										\
+		raw_local_irq_save(flags);					\
+		v->counter c_op i;						\
+		raw_local_irq_restore(flags);					\
+	}									\
+}										\
+
+#define ATOMIC64_OP_RETURN(op, c_op, asm_op)					\
+static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)		\
+{										\
+	long result;								\
+										\
+	smp_mb__before_llsc();							\
+										\
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {				\
+		long temp;							\
+										\
+		__asm__ __volatile__(						\
+		"	.set	arch=r4000				\n"	\
+		"1:	lld	%1, %2		# atomic64_" #op "_return\n"	\
+		"	" #asm_op " %0, %1, %3				\n"	\
+		"	scd	%0, %2					\n"	\
+		"	beqzl	%0, 1b					\n"	\
+		"	" #asm_op " %0, %1, %3				\n"	\
+		"	.set	mips0					\n"	\
+		: "=&r" (result), "=&r" (temp), "+m" (v->counter)		\
+		: "Ir" (i));							\
+	} else if (kernel_uses_llsc) {						\
+		long temp;							\
+										\
+		do {								\
+			__asm__ __volatile__(					\
+			"	.set	arch=r4000			\n"	\
+			"	lld	%1, %2	# atomic64_" #op "_return\n"	\
+			"	" #asm_op " %0, %1, %3			\n"	\
+			"	scd	%0, %2				\n"	\
+			"	.set	mips0				\n"	\
+			: "=&r" (result), "=&r" (temp), "=m" (v->counter)	\
+			: "Ir" (i), "m" (v->counter)				\
+			: "memory");						\
+		} while (unlikely(!result));					\
+										\
+		result = temp; result c_op i;					\
+	} else {								\
+		unsigned long flags;						\
+										\
+		raw_local_irq_save(flags);					\
+		result = v->counter;						\
+		result c_op i;							\
+		v->counter = result;						\
+		raw_local_irq_restore(flags);					\
+	}									\
+										\
+	smp_llsc_mb();								\
+										\
+	return result;								\
 }
 
-/*
- * atomic64_sub - subtract the atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic64_t
- *
- * Atomically subtracts @i from @v.
- */
-static __inline__ void atomic64_sub(long i, atomic64_t * v)
-{
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		long temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	lld	%0, %1		# atomic64_sub		\n"
-		"	dsubu	%0, %2					\n"
-		"	scd	%0, %1					\n"
-		"	beqzl	%0, 1b					\n"
-		"	.set	mips0					\n"
-		: "=&r" (temp), "+m" (v->counter)
-		: "Ir" (i));
-	} else if (kernel_uses_llsc) {
-		long temp;
-
-		do {
-			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
-			"	lld	%0, %1		# atomic64_sub	\n"
-			"	dsubu	%0, %2				\n"
-			"	scd	%0, %1				\n"
-			"	.set	mips0				\n"
-			: "=&r" (temp), "+m" (v->counter)
-			: "Ir" (i));
-		} while (unlikely(!temp));
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		v->counter -= i;
-		raw_local_irq_restore(flags);
-	}
-}
-
-/*
- * Same as above, but return the result value
- */
-static __inline__ long atomic64_add_return(long i, atomic64_t * v)
-{
-	long result;
+#define ATOMIC64_OPS(op, c_op, asm_op)						\
+	ATOMIC64_OP(op, c_op, asm_op)						\
+	ATOMIC64_OP_RETURN(op, c_op, asm_op)
 
-	smp_mb__before_llsc();
+ATOMIC64_OPS(add, +=, daddu)
+ATOMIC64_OPS(sub, -=, dsubu)
 
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		long temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	lld	%1, %2		# atomic64_add_return	\n"
-		"	daddu	%0, %1, %3				\n"
-		"	scd	%0, %2					\n"
-		"	beqzl	%0, 1b					\n"
-		"	daddu	%0, %1, %3				\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp), "+m" (v->counter)
-		: "Ir" (i));
-	} else if (kernel_uses_llsc) {
-		long temp;
-
-		do {
-			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
-			"	lld	%1, %2	# atomic64_add_return	\n"
-			"	daddu	%0, %1, %3			\n"
-			"	scd	%0, %2				\n"
-			"	.set	mips0				\n"
-			: "=&r" (result), "=&r" (temp), "=m" (v->counter)
-			: "Ir" (i), "m" (v->counter)
-			: "memory");
-		} while (unlikely(!result));
-
-		result = temp + i;
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		result = v->counter;
-		result += i;
-		v->counter = result;
-		raw_local_irq_restore(flags);
-	}
-
-	smp_llsc_mb();
-
-	return result;
-}
-
-static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
-{
-	long result;
-
-	smp_mb__before_llsc();
-
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		long temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	lld	%1, %2		# atomic64_sub_return	\n"
-		"	dsubu	%0, %1, %3				\n"
-		"	scd	%0, %2					\n"
-		"	beqzl	%0, 1b					\n"
-		"	dsubu	%0, %1, %3				\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
-		: "Ir" (i), "m" (v->counter)
-		: "memory");
-	} else if (kernel_uses_llsc) {
-		long temp;
-
-		do {
-			__asm__ __volatile__(
-			"	.set	arch=r4000			\n"
-			"	lld	%1, %2	# atomic64_sub_return	\n"
-			"	dsubu	%0, %1, %3			\n"
-			"	scd	%0, %2				\n"
-			"	.set	mips0				\n"
-			: "=&r" (result), "=&r" (temp), "=m" (v->counter)
-			: "Ir" (i), "m" (v->counter)
-			: "memory");
-		} while (unlikely(!result));
-
-		result = temp - i;
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		result = v->counter;
-		result -= i;
-		v->counter = result;
-		raw_local_irq_restore(flags);
-	}
-
-	smp_llsc_mb();
-
-	return result;
-}
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
 
 /*
  * atomic64_sub_if_positive - conditionally subtract integer from atomic variable
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index e079598ae051..3325f3eb248c 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -231,6 +231,16 @@
 #define cpu_has_clo_clz	cpu_has_mips_r
 #endif
 
+/*
+ * MIPS32 R2, MIPS64 R2, Loongson 3A and Octeon have WSBH.
+ * MIPS64 R2, Loongson 3A and Octeon have WSBH, DSBH and DSHD.
+ * This indicates the availability of WSBH and in case of 64 bit CPUs also
+ * DSBH and DSHD.
+ */
+#ifndef cpu_has_wsbh
+#define cpu_has_wsbh		cpu_has_mips_r2
+#endif
+
 #ifndef cpu_has_dsp
 #define cpu_has_dsp		(cpu_data[0].ases & MIPS_ASE_DSP)
 #endif
diff --git a/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h
index d5f42c168001..a6c9ccb33c5c 100644
--- a/arch/mips/include/asm/cpu-info.h
+++ b/arch/mips/include/asm/cpu-info.h
@@ -79,6 +79,11 @@ struct cpuinfo_mips {
 #define NUM_WATCH_REGS 4
 	u16			watch_reg_masks[NUM_WATCH_REGS];
 	unsigned int		kscratch_mask; /* Usable KScratch mask. */
+	/*
+	 * Cache Coherency attribute for write-combine memory writes.
+	 * (shifted by _CACHE_SHIFT)
+	 */
+	unsigned int		writecombine;
 } __attribute__((aligned(SMP_CACHE_BYTES)));
 
 extern struct cpuinfo_mips cpu_data[];
diff --git a/arch/mips/include/asm/fpu_emulator.h b/arch/mips/include/asm/fpu_emulator.h
index 0195745b4b1b..3ee347713307 100644
--- a/arch/mips/include/asm/fpu_emulator.h
+++ b/arch/mips/include/asm/fpu_emulator.h
@@ -33,17 +33,17 @@
 #ifdef CONFIG_DEBUG_FS
 
 struct mips_fpu_emulator_stats {
-	local_t emulated;
-	local_t loads;
-	local_t stores;
-	local_t cp1ops;
-	local_t cp1xops;
-	local_t errors;
-	local_t ieee754_inexact;
-	local_t ieee754_underflow;
-	local_t ieee754_overflow;
-	local_t ieee754_zerodiv;
-	local_t ieee754_invalidop;
+	unsigned long emulated;
+	unsigned long loads;
+	unsigned long stores;
+	unsigned long cp1ops;
+	unsigned long cp1xops;
+	unsigned long errors;
+	unsigned long ieee754_inexact;
+	unsigned long ieee754_underflow;
+	unsigned long ieee754_overflow;
+	unsigned long ieee754_zerodiv;
+	unsigned long ieee754_invalidop;
 };
 
 DECLARE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats);
@@ -51,7 +51,7 @@ DECLARE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats);
 #define MIPS_FPU_EMU_INC_STATS(M)					\
 do {									\
 	preempt_disable();						\
-	__local_inc(&__get_cpu_var(fpuemustats).M);			\
+	__this_cpu_inc(fpuemustats.M);					\
 	preempt_enable();						\
 } while (0)
 
diff --git a/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h b/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h
index 09f45e6afade..c5b6eef0efa7 100644
--- a/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-au1x00/cpu-feature-overrides.h
@@ -8,6 +8,12 @@
 #define __ASM_MACH_AU1X00_CPU_FEATURE_OVERRIDES_H
 
 #define cpu_has_tlb			1
+#define cpu_has_tlbinv			0
+#define cpu_has_segments		0
+#define cpu_has_eva			0
+#define cpu_has_htw			0
+#define cpu_has_rixiex			0
+#define cpu_has_maar			0
 #define cpu_has_4kex			1
 #define cpu_has_3k_cache		0
 #define cpu_has_4k_cache		1
@@ -28,6 +34,8 @@
 #define cpu_has_mdmx			0
 #define cpu_has_mips3d			0
 #define cpu_has_smartmips		0
+#define cpu_has_rixi			0
+#define cpu_has_mmips			0
 #define cpu_has_vtag_icache		0
 #define cpu_has_dc_aliases		0
 #define cpu_has_ic_fills_f_dc		1
@@ -50,4 +58,8 @@
 #define cpu_dcache_line_size()		32
 #define cpu_icache_line_size()		32
 
+#define cpu_has_perf_cntr_intr_bit	0
+#define cpu_has_vz			0
+#define cpu_has_msa			0
+
 #endif /* __ASM_MACH_AU1X00_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
index cf8022872892..fa1f3cfbae8d 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
@@ -57,6 +57,7 @@
 #define cpu_has_vint		0
 #define cpu_has_veic		0
 #define cpu_hwrena_impl_bits	0xc0000000
+#define cpu_has_wsbh            1
 
 #define cpu_has_rixi		(cpu_data[0].cputype != CPU_CAVIUM_OCTEON)
 
diff --git a/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h
index c0f3ef45c2c1..7d28f95b0512 100644
--- a/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-loongson/cpu-feature-overrides.h
@@ -59,4 +59,6 @@
 #define cpu_has_watch		1
 #define cpu_has_local_ebase	0
 
+#define cpu_has_wsbh		IS_ENABLED(CONFIG_CPU_LOONGSON3)
+
 #endif /* __ASM_MACH_LOONGSON_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h
index e592f3687d6f..e747bfa0be7e 100644
--- a/arch/mips/include/asm/pgtable-bits.h
+++ b/arch/mips/include/asm/pgtable-bits.h
@@ -224,38 +224,52 @@ static inline uint64_t pte_to_entrylo(unsigned long pte_val)
 #if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
 
 #define _CACHE_CACHABLE_NONCOHERENT 0
+#define _CACHE_UNCACHED_ACCELERATED _CACHE_UNCACHED
 
 #elif defined(CONFIG_CPU_SB1)
 
 /* No penalty for being coherent on the SB1, so just
    use it for "noncoherent" spaces, too.  Shouldn't hurt. */
 
-#define _CACHE_UNCACHED		    (2<<_CACHE_SHIFT)
-#define _CACHE_CACHABLE_COW	    (5<<_CACHE_SHIFT)
 #define _CACHE_CACHABLE_NONCOHERENT (5<<_CACHE_SHIFT)
-#define _CACHE_UNCACHED_ACCELERATED (7<<_CACHE_SHIFT)
 
 #elif defined(CONFIG_CPU_LOONGSON3)
 
 /* Using COHERENT flag for NONCOHERENT doesn't hurt. */
 
-#define _CACHE_UNCACHED             (2<<_CACHE_SHIFT)  /* LOONGSON       */
 #define _CACHE_CACHABLE_NONCOHERENT (3<<_CACHE_SHIFT)  /* LOONGSON       */
 #define _CACHE_CACHABLE_COHERENT    (3<<_CACHE_SHIFT)  /* LOONGSON-3     */
-#define _CACHE_UNCACHED_ACCELERATED (7<<_CACHE_SHIFT)  /* LOONGSON       */
 
-#else
+#elif defined(CONFIG_MACH_JZ4740)
+
+/* Ingenic uses the WA bit to achieve write-combine memory writes */
+#define _CACHE_UNCACHED_ACCELERATED (1<<_CACHE_SHIFT)
 
-#define _CACHE_CACHABLE_NO_WA	    (0<<_CACHE_SHIFT)  /* R4600 only	  */
-#define _CACHE_CACHABLE_WA	    (1<<_CACHE_SHIFT)  /* R4600 only	  */
-#define _CACHE_UNCACHED		    (2<<_CACHE_SHIFT)  /* R4[0246]00	  */
-#define _CACHE_CACHABLE_NONCOHERENT (3<<_CACHE_SHIFT)  /* R4[0246]00	  */
-#define _CACHE_CACHABLE_CE	    (4<<_CACHE_SHIFT)  /* R4[04]00MC only */
-#define _CACHE_CACHABLE_COW	    (5<<_CACHE_SHIFT)  /* R4[04]00MC only */
-#define _CACHE_CACHABLE_COHERENT    (5<<_CACHE_SHIFT)  /* MIPS32R2 CMP	  */
-#define _CACHE_CACHABLE_CUW	    (6<<_CACHE_SHIFT)  /* R4[04]00MC only */
-#define _CACHE_UNCACHED_ACCELERATED (7<<_CACHE_SHIFT)  /* R10000 only	  */
+#endif
 
+#ifndef _CACHE_CACHABLE_NO_WA
+#define _CACHE_CACHABLE_NO_WA		(0<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_CACHABLE_WA
+#define _CACHE_CACHABLE_WA		(1<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_UNCACHED
+#define _CACHE_UNCACHED			(2<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_CACHABLE_NONCOHERENT
+#define _CACHE_CACHABLE_NONCOHERENT	(3<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_CACHABLE_CE
+#define _CACHE_CACHABLE_CE		(4<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_CACHABLE_COW
+#define _CACHE_CACHABLE_COW		(5<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_CACHABLE_CUW
+#define _CACHE_CACHABLE_CUW		(6<<_CACHE_SHIFT)
+#endif
+#ifndef _CACHE_UNCACHED_ACCELERATED
+#define _CACHE_UNCACHED_ACCELERATED	(7<<_CACHE_SHIFT)
 #endif
 
 #define __READABLE	(_PAGE_SILENT_READ | _PAGE_ACCESSED | (cpu_has_rixi ? 0 : _PAGE_READ))
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index df49a308085c..d6d1928539b1 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -366,6 +366,16 @@ static inline pgprot_t pgprot_noncached(pgprot_t _prot)
 	return __pgprot(prot);
 }
 
+static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
+{
+	unsigned long prot = pgprot_val(_prot);
+
+	/* cpu_data[0].writecombine is already shifted by _CACHE_SHIFT */
+	prot = (prot & ~_CACHE_MASK) | cpu_data[0].writecombine;
+
+	return __pgprot(prot);
+}
+
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 05f08438a7c4..f1df4cb4a286 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -397,12 +397,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define ARCH_HAS_PREFETCHW
 #define prefetchw(x) __builtin_prefetch((x), 1, 1)
 
-/*
- * See Documentation/scheduler/sched-arch.txt; prevents deadlock on SMP
- * systems.
- */
-#define __ARCH_WANT_UNLOCKED_CTXSW
-
 #endif
 
 #endif /* _ASM_PROCESSOR_H */
diff --git a/arch/mips/include/asm/suspend.h b/arch/mips/include/asm/suspend.h
deleted file mode 100644
index 3adac3b53d19..000000000000
--- a/arch/mips/include/asm/suspend.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __ASM_SUSPEND_H
-#define __ASM_SUSPEND_H
-
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
-#endif /* __ASM_SUSPEND_H */
diff --git a/arch/mips/include/uapi/asm/swab.h b/arch/mips/include/uapi/asm/swab.h
index ac9a8f9cd1fb..8f2d184dbe9f 100644
--- a/arch/mips/include/uapi/asm/swab.h
+++ b/arch/mips/include/uapi/asm/swab.h
@@ -13,12 +13,16 @@
 
 #define __SWAB_64_THRU_32__
 
-#if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
+#if (defined(__mips_isa_rev) && (__mips_isa_rev >= 2)) ||		\
+    defined(_MIPS_ARCH_LOONGSON3A)
 
 static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 {
 	__asm__(
+	"	.set	push			\n"
+	"	.set	arch=mips32r2		\n"
 	"	wsbh	%0, %1			\n"
+	"	.set	pop			\n"
 	: "=r" (x)
 	: "r" (x));
 
@@ -29,8 +33,11 @@ static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 {
 	__asm__(
+	"	.set	push			\n"
+	"	.set	arch=mips32r2		\n"
 	"	wsbh	%0, %1			\n"
 	"	rotr	%0, %0, 16		\n"
+	"	.set	pop			\n"
 	: "=r" (x)
 	: "r" (x));
 
@@ -46,8 +53,11 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 {
 	__asm__(
-	"	dsbh	%0, %1\n"
-	"	dshd	%0, %0"
+	"	.set	push			\n"
+	"	.set	arch=mips64r2		\n"
+	"	dsbh	%0, %1			\n"
+	"	dshd	%0, %0			\n"
+	"	.set	pop			\n"
 	: "=r" (x)
 	: "r" (x));
 
@@ -55,5 +65,5 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 }
 #define __arch_swab64 __arch_swab64
 #endif /* __mips64 */
-#endif /* MIPS R2 or newer  */
+#endif /* MIPS R2 or newer or Loongson 3A */
 #endif /* _ASM_SWAB_H */
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index e34b10be782e..94c4a0c0a577 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -27,6 +27,7 @@
 #include <asm/msa.h>
 #include <asm/watch.h>
 #include <asm/elf.h>
+#include <asm/pgtable-bits.h>
 #include <asm/spram.h>
 #include <asm/uaccess.h>
 
@@ -764,6 +765,7 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 			break;
 		case PRID_REV_LOONGSON3A:
 			c->cputype = CPU_LOONGSON3;
+			c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3a");
 			break;
@@ -798,67 +800,83 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 
 static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu)
 {
+	c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_4KC:
 		c->cputype = CPU_4KC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 4Kc";
 		break;
 	case PRID_IMP_4KEC:
 	case PRID_IMP_4KECR2:
 		c->cputype = CPU_4KEC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 4KEc";
 		break;
 	case PRID_IMP_4KSC:
 	case PRID_IMP_4KSD:
 		c->cputype = CPU_4KSC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 4KSc";
 		break;
 	case PRID_IMP_5KC:
 		c->cputype = CPU_5KC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 5Kc";
 		break;
 	case PRID_IMP_5KE:
 		c->cputype = CPU_5KE;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 5KE";
 		break;
 	case PRID_IMP_20KC:
 		c->cputype = CPU_20KC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 20Kc";
 		break;
 	case PRID_IMP_24K:
 		c->cputype = CPU_24K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 24Kc";
 		break;
 	case PRID_IMP_24KE:
 		c->cputype = CPU_24K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 24KEc";
 		break;
 	case PRID_IMP_25KF:
 		c->cputype = CPU_25KF;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 25Kc";
 		break;
 	case PRID_IMP_34K:
 		c->cputype = CPU_34K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 34Kc";
 		break;
 	case PRID_IMP_74K:
 		c->cputype = CPU_74K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 74Kc";
 		break;
 	case PRID_IMP_M14KC:
 		c->cputype = CPU_M14KC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS M14Kc";
 		break;
 	case PRID_IMP_M14KEC:
 		c->cputype = CPU_M14KEC;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS M14KEc";
 		break;
 	case PRID_IMP_1004K:
 		c->cputype = CPU_1004K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 1004Kc";
 		break;
 	case PRID_IMP_1074K:
 		c->cputype = CPU_1074K;
+		c->writecombine = _CACHE_UNCACHED;
 		__cpu_name[cpu] = "MIPS 1074Kc";
 		break;
 	case PRID_IMP_INTERAPTIV_UP:
@@ -932,6 +950,7 @@ static inline void cpu_probe_sibyte(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	decode_configs(c);
 
+	c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_SB1:
 		c->cputype = CPU_SB1;
@@ -1063,6 +1082,7 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu)
 	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_JZRISC:
 		c->cputype = CPU_JZRISC;
+		c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 		__cpu_name[cpu] = "Ingenic JZRISC";
 		break;
 	default:
@@ -1169,6 +1189,7 @@ void cpu_probe(void)
 	c->processor_id = PRID_IMP_UNKNOWN;
 	c->fpu_id	= FPIR_IMP_NONE;
 	c->cputype	= CPU_UNKNOWN;
+	c->writecombine = _CACHE_UNCACHED;
 
 	c->processor_id = read_c0_prid();
 	switch (c->processor_id & PRID_COMP_MASK) {
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index 1f8187ab0997..212f46f2014e 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -224,7 +224,7 @@ static void save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 	kcb->kprobe_old_SR = kcb->prev_kprobe.old_SR;
 	kcb->kprobe_saved_SR = kcb->prev_kprobe.saved_SR;
@@ -234,7 +234,7 @@ static void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 			       struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_SR = kcb->kprobe_old_SR = (regs->cp0_status & ST0_IE);
 	kcb->kprobe_saved_epc = regs->cp0_epc;
 }
@@ -385,7 +385,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				ret = 1;
 				goto no_kprobe;
 			}
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs))
 				goto ss_probe;
 		}
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index b63f2482f288..a8f9cdc6f8b0 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -340,7 +340,7 @@ static int mipsxx_pmu_alloc_counter(struct cpu_hw_events *cpuc,
 
 static void mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	WARN_ON(idx < 0 || idx >= mipspmu.num_counters);
 
@@ -360,7 +360,7 @@ static void mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
 
 static void mipsxx_pmu_disable_event(int idx)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long flags;
 
 	WARN_ON(idx < 0 || idx >= mipspmu.num_counters);
@@ -460,7 +460,7 @@ static void mipspmu_stop(struct perf_event *event, int flags)
 
 static int mipspmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx;
 	int err = 0;
@@ -496,7 +496,7 @@ out:
 
 static void mipspmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -1275,7 +1275,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 static void pause_local_counters(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int ctr = mipspmu.num_counters;
 	unsigned long flags;
 
@@ -1291,7 +1291,7 @@ static void pause_local_counters(void)
 
 static void resume_local_counters(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int ctr = mipspmu.num_counters;
 
 	do {
@@ -1302,7 +1302,7 @@ static void resume_local_counters(void)
 
 static int mipsxx_pmu_handle_shared_irq(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_sample_data data;
 	unsigned int counters = mipspmu.num_counters;
 	u64 counter;
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 645b3c4fcfba..f7aac5b57b4b 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -770,7 +770,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 	long ret = 0;
 	user_exit();
 
-	if (secure_computing(syscall) == -1)
+	if (secure_computing() == -1)
 		return -1;
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 7c1fe2b42d40..b3b8f0d9d4a7 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -24,6 +24,8 @@
 #include <linux/debugfs.h>
 #include <linux/kexec.h>
 #include <linux/sizes.h>
+#include <linux/device.h>
+#include <linux/dma-contiguous.h>
 
 #include <asm/addrspace.h>
 #include <asm/bootinfo.h>
@@ -476,6 +478,7 @@ static void __init bootmem_init(void)
  *  o bootmem_init()
  *  o sparse_init()
  *  o paging_init()
+ *  o dma_continguous_reserve()
  *
  * At this stage the bootmem allocator is ready to use.
  *
@@ -609,6 +612,7 @@ static void __init request_crashkernel(struct resource *res)
 
 static void __init arch_mem_init(char **cmdline_p)
 {
+	struct memblock_region *reg;
 	extern void plat_mem_setup(void);
 
 	/* call board setup routine */
@@ -675,6 +679,11 @@ static void __init arch_mem_init(char **cmdline_p)
 	sparse_init();
 	plat_swiotlb_setup();
 	paging_init();
+
+	dma_contiguous_reserve(PFN_PHYS(max_low_pfn));
+	/* Tell bootmem about cma reserved memblock section */
+	for_each_memblock(reserved, reg)
+		reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
 }
 
 static void __init resource_init(void)
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index df9e2bd9b2c2..06bb5ed6d80a 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -346,7 +346,7 @@ static irqreturn_t bmips43xx_ipi_interrupt(int irq, void *dev_id)
 	int action, cpu = irq - IPI0_IRQ;
 
 	spin_lock_irqsave(&ipi_lock, flags);
-	action = __get_cpu_var(ipi_action_mask);
+	action = __this_cpu_read(ipi_action_mask);
 	per_cpu(ipi_action_mask, cpu) = 0;
 	clear_c0_cause(cpu ? C_SW1 : C_SW0);
 	spin_unlock_irqrestore(&ipi_lock, flags);
diff --git a/arch/mips/lantiq/Kconfig b/arch/mips/lantiq/Kconfig
index c0021912131e..e10d33342b30 100644
--- a/arch/mips/lantiq/Kconfig
+++ b/arch/mips/lantiq/Kconfig
@@ -30,6 +30,7 @@ choice
 config DT_EASY50712
 	bool "Easy50712"
 	depends on SOC_XWAY
+	select BUILTIN_DTB
 endchoice
 
 config PCI_LANTIQ
diff --git a/arch/mips/lantiq/Makefile b/arch/mips/lantiq/Makefile
index d6bdc579419f..690257ab86d6 100644
--- a/arch/mips/lantiq/Makefile
+++ b/arch/mips/lantiq/Makefile
@@ -6,8 +6,6 @@
 
 obj-y := irq.o clk.o prom.o
 
-obj-y += dts/
-
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
 
 obj-$(CONFIG_SOC_TYPE_XWAY) += xway/
diff --git a/arch/mips/lantiq/dts/Makefile b/arch/mips/lantiq/dts/Makefile
deleted file mode 100644
index 6fa72dd641b2..000000000000
--- a/arch/mips/lantiq/dts/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-$(CONFIG_DT_EASY50712) := easy50712.dtb.o
diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index 9901237563c5..4c721e247ac9 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -277,9 +277,12 @@ LEAF(csum_partial)
 #endif
 
 	/* odd buffer alignment? */
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON3)
+	.set	push
+	.set	arch=mips32r2
 	wsbh	v1, sum
 	movn	sum, v1, t7
+	.set	pop
 #else
 	beqz	t7, 1f			/* odd buffer alignment? */
 	 lui	v1, 0x00ff
@@ -726,9 +729,12 @@ LEAF(csum_partial)
 	addu	sum, v1
 #endif
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_LOONGSON3)
+	.set	push
+	.set	arch=mips32r2
 	wsbh	v1, sum
 	movn	sum, v1, odd
+	.set	pop
 #else
 	beqz	odd, 1f			/* odd buffer alignment? */
 	 lui	v1, 0x00ff
diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c
index 74e827b4ec8f..d8c63af6c7cc 100644
--- a/arch/mips/loongson/loongson-3/smp.c
+++ b/arch/mips/loongson/loongson-3/smp.c
@@ -299,16 +299,16 @@ static void loongson3_init_secondary(void)
 	per_cpu(cpu_state, cpu) = CPU_ONLINE;
 
 	i = 0;
-	__get_cpu_var(core0_c0count) = 0;
+	__this_cpu_write(core0_c0count, 0);
 	loongson3_send_ipi_single(0, SMP_ASK_C0COUNT);
-	while (!__get_cpu_var(core0_c0count)) {
+	while (!__this_cpu_read(core0_c0count)) {
 		i++;
 		cpu_relax();
 	}
 
 	if (i > MAX_LOOPS)
 		i = MAX_LOOPS;
-	initcount = __get_cpu_var(core0_c0count) + i;
+	initcount = __this_cpu_read(core0_c0count) + i;
 	write_c0_count(initcount);
 }
 
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index 44b6dff5aba2..33ba3c558fe4 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -16,6 +16,7 @@
 #include <linux/string.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
+#include <linux/dma-contiguous.h>
 
 #include <asm/cache.h>
 #include <asm/cpu-type.h>
@@ -128,23 +129,30 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
 	dma_addr_t * dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
 	void *ret;
+	struct page *page = NULL;
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
 	if (dma_alloc_from_coherent(dev, size, dma_handle, &ret))
 		return ret;
 
 	gfp = massage_gfp_flags(dev, gfp);
 
-	ret = (void *) __get_free_pages(gfp, get_order(size));
-
-	if (ret) {
-		memset(ret, 0, size);
-		*dma_handle = plat_map_dma_mem(dev, ret, size);
-
-		if (!plat_device_is_coherent(dev)) {
-			dma_cache_wback_inv((unsigned long) ret, size);
-			if (!hw_coherentio)
-				ret = UNCAC_ADDR(ret);
-		}
+	if (IS_ENABLED(CONFIG_DMA_CMA) && !(gfp & GFP_ATOMIC))
+		page = dma_alloc_from_contiguous(dev,
+					count, get_order(size));
+	if (!page)
+		page = alloc_pages(gfp, get_order(size));
+
+	if (!page)
+		return NULL;
+
+	ret = page_address(page);
+	memset(ret, 0, size);
+	*dma_handle = plat_map_dma_mem(dev, ret, size);
+	if (!plat_device_is_coherent(dev)) {
+		dma_cache_wback_inv((unsigned long) ret, size);
+		if (!hw_coherentio)
+			ret = UNCAC_ADDR(ret);
 	}
 
 	return ret;
@@ -164,6 +172,8 @@ static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
 {
 	unsigned long addr = (unsigned long) vaddr;
 	int order = get_order(size);
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct page *page = NULL;
 
 	if (dma_release_from_coherent(dev, order, vaddr))
 		return;
@@ -173,7 +183,10 @@ static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
 	if (!plat_device_is_coherent(dev) && !hw_coherentio)
 		addr = CAC_ADDR(addr);
 
-	free_pages(addr, get_order(size));
+	page = virt_to_page((void *) addr);
+
+	if (!dma_release_from_contiguous(dev, page, count))
+		__free_pages(page, get_order(size));
 }
 
 static inline void __dma_sync_virtual(void *addr, size_t size,
diff --git a/arch/mips/mti-sead3/Makefile b/arch/mips/mti-sead3/Makefile
index 071786fa234b..febf4334545e 100644
--- a/arch/mips/mti-sead3/Makefile
+++ b/arch/mips/mti-sead3/Makefile
@@ -19,9 +19,5 @@ obj-y				+= sead3-i2c-dev.o sead3-i2c.o \
 
 obj-$(CONFIG_EARLY_PRINTK)	+= sead3-console.o
 obj-$(CONFIG_USB_EHCI_HCD)	+= sead3-ehci.o
-obj-$(CONFIG_OF)		+= sead3.dtb.o
 
 CFLAGS_sead3-setup.o = -I$(src)/../../../scripts/dtc/libfdt
-
-$(obj)/%.dtb: $(obj)/%.dts
-	$(call if_changed,dtc)
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 7edc08398c4a..9b55143d19db 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -163,6 +163,19 @@ do {							\
 	(ctx)->idx++;					\
 } while (0)
 
+/*
+ * Similar to emit_instr but it must be used when we need to emit
+ * 32-bit or 64-bit instructions
+ */
+#define emit_long_instr(ctx, func, ...)			\
+do {							\
+	if ((ctx)->target != NULL) {			\
+		u32 *p = &(ctx)->target[ctx->idx];	\
+		UASM_i_##func(&p, ##__VA_ARGS__);	\
+	}						\
+	(ctx)->idx++;					\
+} while (0)
+
 /* Determine if immediate is within the 16-bit signed range */
 static inline bool is_range16(s32 imm)
 {
@@ -218,13 +231,6 @@ static inline void emit_ori(unsigned int dst, unsigned src, u32 imm,
 	}
 }
 
-
-static inline void emit_daddu(unsigned int dst, unsigned int src1,
-			      unsigned int src2, struct jit_ctx *ctx)
-{
-	emit_instr(ctx, daddu, dst, src1, src2);
-}
-
 static inline void emit_daddiu(unsigned int dst, unsigned int src,
 			       int imm, struct jit_ctx *ctx)
 {
@@ -283,11 +289,7 @@ static inline void emit_xori(ptr dst, ptr src, u32 imm, struct jit_ctx *ctx)
 
 static inline void emit_stack_offset(int offset, struct jit_ctx *ctx)
 {
-	if (config_enabled(CONFIG_64BIT))
-		emit_instr(ctx, daddiu, r_sp, r_sp, offset);
-	else
-		emit_instr(ctx, addiu, r_sp, r_sp, offset);
-
+	emit_long_instr(ctx, ADDIU, r_sp, r_sp, offset);
 }
 
 static inline void emit_subu(unsigned int dst, unsigned int src1,
@@ -365,10 +367,7 @@ static inline void emit_store_stack_reg(ptr reg, ptr base,
 					unsigned int offset,
 					struct jit_ctx *ctx)
 {
-	if (config_enabled(CONFIG_64BIT))
-		emit_instr(ctx, sd, reg, offset, base);
-	else
-		emit_instr(ctx, sw, reg, offset, base);
+	emit_long_instr(ctx, SW, reg, offset, base);
 }
 
 static inline void emit_store(ptr reg, ptr base, unsigned int offset,
@@ -381,10 +380,7 @@ static inline void emit_load_stack_reg(ptr reg, ptr base,
 				       unsigned int offset,
 				       struct jit_ctx *ctx)
 {
-	if (config_enabled(CONFIG_64BIT))
-		emit_instr(ctx, ld, reg, offset, base);
-	else
-		emit_instr(ctx, lw, reg, offset, base);
+	emit_long_instr(ctx, LW, reg, offset, base);
 }
 
 static inline void emit_load(unsigned int reg, unsigned int base,
@@ -458,10 +454,7 @@ static inline void emit_load_ptr(unsigned int dst, unsigned int src,
 				     int imm, struct jit_ctx *ctx)
 {
 	/* src contains the base addr of the 32/64-pointer */
-	if (config_enabled(CONFIG_64BIT))
-		emit_instr(ctx, ld, dst, imm, src);
-	else
-		emit_instr(ctx, lw, dst, imm, src);
+	emit_long_instr(ctx, LW, dst, imm, src);
 }
 
 /* load a function pointer to register */
@@ -483,10 +476,7 @@ static inline void emit_load_func(unsigned int reg, ptr imm,
 /* Move to real MIPS register */
 static inline void emit_reg_move(ptr dst, ptr src, struct jit_ctx *ctx)
 {
-	if (config_enabled(CONFIG_64BIT))
-		emit_daddu(dst, src, r_zero, ctx);
-	else
-		emit_addu(dst, src, r_zero, ctx);
+	emit_long_instr(ctx, ADDU, dst, src, r_zero);
 }
 
 /* Move to JIT (32-bit) register */
@@ -623,10 +613,7 @@ static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset)
 	if (ctx->flags & SEEN_MEM) {
 		if (real_off % (RSIZE * 2))
 			real_off += RSIZE;
-		if (config_enabled(CONFIG_64BIT))
-			emit_daddiu(r_M, r_sp, real_off, ctx);
-		else
-			emit_addiu(r_M, r_sp, real_off, ctx);
+		emit_long_instr(ctx, ADDIU, r_M, r_sp, real_off);
 	}
 }
 
@@ -1241,7 +1228,7 @@ jmp_cmp:
 			emit_half_load(r_A, r_skb, off, ctx);
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
 			/* This needs little endian fixup */
-			if (cpu_has_mips_r2) {
+			if (cpu_has_wsbh) {
 				/* R2 and later have the wsbh instruction */
 				emit_wsbh(r_A, r_A, ctx);
 			} else {
diff --git a/arch/mips/netlogic/Kconfig b/arch/mips/netlogic/Kconfig
index 4eb683aef7d7..0823321c10e0 100644
--- a/arch/mips/netlogic/Kconfig
+++ b/arch/mips/netlogic/Kconfig
@@ -4,6 +4,7 @@ if NLM_XLP_BOARD
 config DT_XLP_EVP
 	bool "Built-in device tree for XLP EVP boards"
 	default y
+	select BUILTIN_DTB
 	help
 	  Add an FDT blob for XLP EVP boards into the kernel.
 	  This DTB will be used if the firmware does not pass in a DTB
@@ -13,6 +14,7 @@ config DT_XLP_EVP
 config DT_XLP_SVP
 	bool "Built-in device tree for XLP SVP boards"
 	default y
+	select BUILTIN_DTB
 	help
 	  Add an FDT blob for XLP VP boards into the kernel.
 	  This DTB will be used if the firmware does not pass in a DTB
@@ -22,6 +24,7 @@ config DT_XLP_SVP
 config DT_XLP_FVP
 	bool "Built-in device tree for XLP FVP boards"
 	default y
+	select BUILTIN_DTB
 	help
 	  Add an FDT blob for XLP FVP board into the kernel.
 	  This DTB will be used if the firmware does not pass in a DTB
@@ -31,6 +34,7 @@ config DT_XLP_FVP
 config DT_XLP_GVP
 	bool "Built-in device tree for XLP GVP boards"
 	default y
+	select BUILTIN_DTB
 	help
 	  Add an FDT blob for XLP GVP board into the kernel.
 	  This DTB will be used if the firmware does not pass in a DTB
diff --git a/arch/mips/netlogic/Makefile b/arch/mips/netlogic/Makefile
index 7602d1386614..36d169b2ca6d 100644
--- a/arch/mips/netlogic/Makefile
+++ b/arch/mips/netlogic/Makefile
@@ -1,4 +1,3 @@
 obj-$(CONFIG_NLM_COMMON)	+=	common/
 obj-$(CONFIG_CPU_XLR)		+=	xlr/
 obj-$(CONFIG_CPU_XLP)		+=	xlp/
-obj-$(CONFIG_CPU_XLP)		+=	dts/
diff --git a/arch/mips/netlogic/dts/Makefile b/arch/mips/netlogic/dts/Makefile
deleted file mode 100644
index 25c8e873ee25..000000000000
--- a/arch/mips/netlogic/dts/Makefile
+++ /dev/null
@@ -1,4 +0,0 @@
-obj-$(CONFIG_DT_XLP_EVP) := xlp_evp.dtb.o
-obj-$(CONFIG_DT_XLP_SVP) += xlp_svp.dtb.o
-obj-$(CONFIG_DT_XLP_FVP) += xlp_fvp.dtb.o
-obj-$(CONFIG_DT_XLP_GVP) += xlp_gvp.dtb.o
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index ab0c5d14c6f7..63bbe07a1ccd 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -73,8 +73,7 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
 	 * wants.  Most devices only want 1, which will give
 	 * configured_private_bits and request_private_bits equal 0.
 	 */
-	pci_read_config_word(dev, desc->msi_attrib.pos + PCI_MSI_FLAGS,
-			     &control);
+	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
 
 	/*
 	 * If the number of private bits has been configured then use
@@ -176,8 +175,7 @@ msi_irq_allocated:
 	/* Update the number of IRQs the device has available to it */
 	control &= ~PCI_MSI_FLAGS_QSIZE;
 	control |= request_private_bits << 4;
-	pci_write_config_word(dev, desc->msi_attrib.pos + PCI_MSI_FLAGS,
-			      control);
+	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
 
 	irq_set_msi_desc(irq, desc);
 	write_msi_msg(irq, &msg);
diff --git a/arch/mips/power/cpu.c b/arch/mips/power/cpu.c
index 521e5963df05..2129e67723ff 100644
--- a/arch/mips/power/cpu.c
+++ b/arch/mips/power/cpu.c
@@ -7,7 +7,7 @@
  * Author: Hu Hongbing <huhb@lemote.com>
  *	   Wu Zhangjin <wuzhangjin@gmail.com>
  */
-#include <asm/suspend.h>
+#include <asm/sections.h>
 #include <asm/fpu.h>
 #include <asm/dsp.h>
 
diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig
index 4a296655f446..77e8a9620e18 100644
--- a/arch/mips/ralink/Kconfig
+++ b/arch/mips/ralink/Kconfig
@@ -42,18 +42,22 @@ choice
 	config DTB_RT2880_EVAL
 		bool "RT2880 eval kit"
 		depends on SOC_RT288X
+		select BUILTIN_DTB
 
 	config DTB_RT305X_EVAL
 		bool "RT305x eval kit"
 		depends on SOC_RT305X
+		select BUILTIN_DTB
 
 	config DTB_RT3883_EVAL
 		bool "RT3883 eval kit"
 		depends on SOC_RT3883
+		select BUILTIN_DTB
 
 	config DTB_MT7620A_EVAL
 		bool "MT7620A eval kit"
 		depends on SOC_MT7620
+		select BUILTIN_DTB
 
 endchoice
 
diff --git a/arch/mips/ralink/Makefile b/arch/mips/ralink/Makefile
index 98ae349827be..2c09c8aa0ae2 100644
--- a/arch/mips/ralink/Makefile
+++ b/arch/mips/ralink/Makefile
@@ -16,5 +16,3 @@ obj-$(CONFIG_SOC_RT3883) += rt3883.o
 obj-$(CONFIG_SOC_MT7620) += mt7620.o
 
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
-
-obj-y += dts/
diff --git a/arch/mips/ralink/dts/Makefile b/arch/mips/ralink/dts/Makefile
deleted file mode 100644
index 18194fa93e80..000000000000
--- a/arch/mips/ralink/dts/Makefile
+++ /dev/null
@@ -1,4 +0,0 @@
-obj-$(CONFIG_DTB_RT2880_EVAL) := rt2880_eval.dtb.o
-obj-$(CONFIG_DTB_RT305X_EVAL) := rt3052_eval.dtb.o
-obj-$(CONFIG_DTB_RT3883_EVAL) := rt3883_eval.dtb.o
-obj-$(CONFIG_DTB_MT7620A_EVAL) := mt7620a_eval.dtb.o
diff --git a/arch/mips/ralink/timer.c b/arch/mips/ralink/timer.c
index e38692a44e69..5bb29b3790ff 100644
--- a/arch/mips/ralink/timer.c
+++ b/arch/mips/ralink/timer.c
@@ -58,7 +58,7 @@ static irqreturn_t rt_timer_irq(int irq, void *_rt)
 
 static int rt_timer_request(struct rt_timer *rt)
 {
-	int err = request_irq(rt->irq, rt_timer_irq, IRQF_DISABLED,
+	int err = request_irq(rt->irq, rt_timer_irq, 0,
 						dev_name(rt->dev), rt);
 	if (err) {
 		dev_err(rt->dev, "failed to request irq\n");
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 9ff200ae1c9a..2791b8641df6 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -789,11 +789,11 @@ void __init txx9_iocled_init(unsigned long baseaddr,
 	if (platform_device_add(pdev))
 		goto out_pdev;
 	return;
+
 out_pdev:
 	platform_device_put(pdev);
 out_gpio:
-	if (gpiochip_remove(&iocled->chip))
-		return;
+	gpiochip_remove(&iocled->chip);
 out_unmap:
 	iounmap(iocled->mmioaddr);
 out_free:
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index ecbd6676bd33..54a062cb9f2c 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -4,7 +4,9 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
+generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/mn10300/include/asm/atomic.h b/arch/mn10300/include/asm/atomic.h
index cadeb1e2cdfc..5be655e83e70 100644
--- a/arch/mn10300/include/asm/atomic.h
+++ b/arch/mn10300/include/asm/atomic.h
@@ -33,7 +33,6 @@
  * @v: pointer of type atomic_t
  *
  * Atomically reads the value of @v.  Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
  */
 #define atomic_read(v)	(ACCESS_ONCE((v)->counter))
 
@@ -43,102 +42,62 @@
  * @i: required value
  *
  * Atomically sets the value of @v to @i.  Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
  */
 #define atomic_set(v, i) (((v)->counter) = (i))
 
-/**
- * atomic_add_return - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and returns the result
- * Note that the guaranteed useful range of an atomic_t is only 24 bits.
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	int retval;
-#ifdef CONFIG_SMP
-	int status;
-
-	asm volatile(
-		"1:	mov	%4,(_AAR,%3)	\n"
-		"	mov	(_ADR,%3),%1	\n"
-		"	add	%5,%1		\n"
-		"	mov	%1,(_ADR,%3)	\n"
-		"	mov	(_ADR,%3),%0	\n"	/* flush */
-		"	mov	(_ASR,%3),%0	\n"
-		"	or	%0,%0		\n"
-		"	bne	1b		\n"
-		: "=&r"(status), "=&r"(retval), "=m"(v->counter)
-		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(&v->counter), "r"(i)
-		: "memory", "cc");
-
-#else
-	unsigned long flags;
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	int retval, status;						\
+									\
+	asm volatile(							\
+		"1:	mov	%4,(_AAR,%3)	\n"			\
+		"	mov	(_ADR,%3),%1	\n"			\
+		"	" #op "	%5,%1		\n"			\
+		"	mov	%1,(_ADR,%3)	\n"			\
+		"	mov	(_ADR,%3),%0	\n"	/* flush */	\
+		"	mov	(_ASR,%3),%0	\n"			\
+		"	or	%0,%0		\n"			\
+		"	bne	1b		\n"			\
+		: "=&r"(status), "=&r"(retval), "=m"(v->counter)	\
+		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(&v->counter), "r"(i)	\
+		: "memory", "cc");					\
+}
 
-	flags = arch_local_cli_save();
-	retval = v->counter;
-	retval += i;
-	v->counter = retval;
-	arch_local_irq_restore(flags);
-#endif
-	return retval;
+#define ATOMIC_OP_RETURN(op)						\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	int retval, status;						\
+									\
+	asm volatile(							\
+		"1:	mov	%4,(_AAR,%3)	\n"			\
+		"	mov	(_ADR,%3),%1	\n"			\
+		"	" #op "	%5,%1		\n"			\
+		"	mov	%1,(_ADR,%3)	\n"			\
+		"	mov	(_ADR,%3),%0	\n"	/* flush */	\
+		"	mov	(_ASR,%3),%0	\n"			\
+		"	or	%0,%0		\n"			\
+		"	bne	1b		\n"			\
+		: "=&r"(status), "=&r"(retval), "=m"(v->counter)	\
+		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(&v->counter), "r"(i)	\
+		: "memory", "cc");					\
+	return retval;							\
 }
 
-/**
- * atomic_sub_return - subtract integer from atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns the result
- * Note that the guaranteed useful range of an atomic_t is only 24 bits.
- */
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	int retval;
-#ifdef CONFIG_SMP
-	int status;
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
 
-	asm volatile(
-		"1:	mov	%4,(_AAR,%3)	\n"
-		"	mov	(_ADR,%3),%1	\n"
-		"	sub	%5,%1		\n"
-		"	mov	%1,(_ADR,%3)	\n"
-		"	mov	(_ADR,%3),%0	\n"	/* flush */
-		"	mov	(_ASR,%3),%0	\n"
-		"	or	%0,%0		\n"
-		"	bne	1b		\n"
-		: "=&r"(status), "=&r"(retval), "=m"(v->counter)
-		: "a"(ATOMIC_OPS_BASE_ADDR), "r"(&v->counter), "r"(i)
-		: "memory", "cc");
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
 
-#else
-	unsigned long flags;
-	flags = arch_local_cli_save();
-	retval = v->counter;
-	retval -= i;
-	v->counter = retval;
-	arch_local_irq_restore(flags);
-#endif
-	return retval;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
 	return atomic_add_return(i, v) < 0;
 }
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	atomic_add_return(i, v);
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	atomic_sub_return(i, v);
-}
-
 static inline void atomic_inc(atomic_t *v)
 {
 	atomic_add_return(1, v);
diff --git a/arch/mn10300/include/asm/sections.h b/arch/mn10300/include/asm/sections.h
deleted file mode 100644
index 2b8c5160388f..000000000000
--- a/arch/mn10300/include/asm/sections.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/sections.h>
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 88e83368bbf5..e5a693b16da2 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -8,6 +8,7 @@ config OPENRISC
 	select OF
 	select OF_EARLY_FLATTREE
 	select IRQ_DOMAIN
+	select HANDLE_DOMAIN_IRQ
 	select HAVE_MEMBLOCK
 	select ARCH_REQUIRE_GPIOLIB
         select HAVE_ARCH_TRACEHOOK
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 480af0d9c2f5..89b61d7dc790 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -31,6 +31,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
diff --git a/arch/openrisc/include/asm/irq.h b/arch/openrisc/include/asm/irq.h
index b84634cc95eb..d9eee0a2b7b4 100644
--- a/arch/openrisc/include/asm/irq.h
+++ b/arch/openrisc/include/asm/irq.h
@@ -24,7 +24,6 @@
 
 #define NO_IRQ		(-1)
 
-void handle_IRQ(unsigned int, struct pt_regs *);
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
 #endif /* __ASM_OPENRISC_IRQ_H__ */
diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c
index 967eb1430203..35e478a93116 100644
--- a/arch/openrisc/kernel/irq.c
+++ b/arch/openrisc/kernel/irq.c
@@ -48,18 +48,6 @@ void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
 	handle_arch_irq = handle_irq;
 }
 
-void handle_IRQ(unsigned int irq, struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-
-	irq_enter();
-
-	generic_handle_irq(irq);
-
-	irq_exit();
-	set_irq_regs(old_regs);
-}
-
 void __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	handle_arch_irq(regs);
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index ecf25e6678ad..ffb024b8423f 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -10,6 +10,7 @@ generic-y += exec.h
 generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kvm_para.h
 generic-y += local.h
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 0be2db2c7d44..226f8ca993f6 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -55,24 +55,7 @@ extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
  * are atomic, so a reader never sees inconsistent values.
  */
 
-/* It's possible to reduce all atomic operations to either
- * __atomic_add_return, atomic_set and atomic_read (the latter
- * is there only for consistency).
- */
-
-static __inline__ int __atomic_add_return(int i, atomic_t *v)
-{
-	int ret;
-	unsigned long flags;
-	_atomic_spin_lock_irqsave(v, flags);
-
-	ret = (v->counter += i);
-
-	_atomic_spin_unlock_irqrestore(v, flags);
-	return ret;
-}
-
-static __inline__ void atomic_set(atomic_t *v, int i) 
+static __inline__ void atomic_set(atomic_t *v, int i)
 {
 	unsigned long flags;
 	_atomic_spin_lock_irqsave(v, flags);
@@ -84,7 +67,7 @@ static __inline__ void atomic_set(atomic_t *v, int i)
 
 static __inline__ int atomic_read(const atomic_t *v)
 {
-	return (*(volatile int *)&(v)->counter);
+	return ACCESS_ONCE((v)->counter);
 }
 
 /* exported interface */
@@ -115,16 +98,43 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
+#define ATOMIC_OP(op, c_op)						\
+static __inline__ void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	_atomic_spin_lock_irqsave(v, flags);				\
+	v->counter c_op i;						\
+	_atomic_spin_unlock_irqrestore(v, flags);			\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static __inline__ int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int ret;							\
+									\
+	_atomic_spin_lock_irqsave(v, flags);				\
+	ret = (v->counter c_op i);					\
+	_atomic_spin_unlock_irqrestore(v, flags);			\
+									\
+	return ret;							\
+}
+
+#define ATOMIC_OPS(op, c_op) ATOMIC_OP(op, c_op) ATOMIC_OP_RETURN(op, c_op)
+
+ATOMIC_OPS(add, +=)
+ATOMIC_OPS(sub, -=)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
-#define atomic_add(i,v)	((void)(__atomic_add_return(        (i),(v))))
-#define atomic_sub(i,v)	((void)(__atomic_add_return(-((int) (i)),(v))))
-#define atomic_inc(v)	((void)(__atomic_add_return(   1,(v))))
-#define atomic_dec(v)	((void)(__atomic_add_return(  -1,(v))))
+#define atomic_inc(v)	(atomic_add(   1,(v)))
+#define atomic_dec(v)	(atomic_add(  -1,(v)))
 
-#define atomic_add_return(i,v)	(__atomic_add_return( (i),(v)))
-#define atomic_sub_return(i,v)	(__atomic_add_return(-(i),(v)))
-#define atomic_inc_return(v)	(__atomic_add_return(   1,(v)))
-#define atomic_dec_return(v)	(__atomic_add_return(  -1,(v)))
+#define atomic_inc_return(v)	(atomic_add_return(   1,(v)))
+#define atomic_dec_return(v)	(atomic_add_return(  -1,(v)))
 
 #define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
 
@@ -148,18 +158,37 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 
 #define ATOMIC64_INIT(i) { (i) }
 
-static __inline__ s64
-__atomic64_add_return(s64 i, atomic64_t *v)
-{
-	s64 ret;
-	unsigned long flags;
-	_atomic_spin_lock_irqsave(v, flags);
+#define ATOMIC64_OP(op, c_op)						\
+static __inline__ void atomic64_##op(s64 i, atomic64_t *v)		\
+{									\
+	unsigned long flags;						\
+									\
+	_atomic_spin_lock_irqsave(v, flags);				\
+	v->counter c_op i;						\
+	_atomic_spin_unlock_irqrestore(v, flags);			\
+}									\
+
+#define ATOMIC64_OP_RETURN(op, c_op)					\
+static __inline__ s64 atomic64_##op##_return(s64 i, atomic64_t *v)	\
+{									\
+	unsigned long flags;						\
+	s64 ret;							\
+									\
+	_atomic_spin_lock_irqsave(v, flags);				\
+	ret = (v->counter c_op i);					\
+	_atomic_spin_unlock_irqrestore(v, flags);			\
+									\
+	return ret;							\
+}
 
-	ret = (v->counter += i);
+#define ATOMIC64_OPS(op, c_op) ATOMIC64_OP(op, c_op) ATOMIC64_OP_RETURN(op, c_op)
 
-	_atomic_spin_unlock_irqrestore(v, flags);
-	return ret;
-}
+ATOMIC64_OPS(add, +=)
+ATOMIC64_OPS(sub, -=)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
 
 static __inline__ void
 atomic64_set(atomic64_t *v, s64 i)
@@ -175,18 +204,14 @@ atomic64_set(atomic64_t *v, s64 i)
 static __inline__ s64
 atomic64_read(const atomic64_t *v)
 {
-	return (*(volatile long *)&(v)->counter);
+	return ACCESS_ONCE((v)->counter);
 }
 
-#define atomic64_add(i,v)	((void)(__atomic64_add_return( ((s64)(i)),(v))))
-#define atomic64_sub(i,v)	((void)(__atomic64_add_return(-((s64)(i)),(v))))
-#define atomic64_inc(v)		((void)(__atomic64_add_return(   1,(v))))
-#define atomic64_dec(v)		((void)(__atomic64_add_return(  -1,(v))))
+#define atomic64_inc(v)		(atomic64_add(   1,(v)))
+#define atomic64_dec(v)		(atomic64_add(  -1,(v)))
 
-#define atomic64_add_return(i,v)	(__atomic64_add_return( ((s64)(i)),(v)))
-#define atomic64_sub_return(i,v)	(__atomic64_add_return(-((s64)(i)),(v)))
-#define atomic64_inc_return(v)		(__atomic64_add_return(   1,(v)))
-#define atomic64_dec_return(v)		(__atomic64_add_return(  -1,(v)))
+#define atomic64_inc_return(v)		(atomic64_add_return(   1,(v)))
+#define atomic64_dec_return(v)		(atomic64_add_return(  -1,(v)))
 
 #define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 
diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h
index f5645d6a89f2..10df7079f4cd 100644
--- a/arch/parisc/include/uapi/asm/signal.h
+++ b/arch/parisc/include/uapi/asm/signal.h
@@ -8,12 +8,12 @@
 #define SIGTRAP		 5
 #define SIGABRT		 6
 #define SIGIOT		 6
-#define SIGEMT		 7
+#define SIGSTKFLT	 7
 #define SIGFPE		 8
 #define SIGKILL		 9
 #define SIGBUS		10
 #define SIGSEGV		11
-#define SIGSYS		12 /* Linux doesn't use this */
+#define SIGXCPU		12
 #define SIGPIPE		13
 #define SIGALRM		14
 #define SIGTERM		15
@@ -32,16 +32,12 @@
 #define SIGTTIN		27
 #define SIGTTOU		28
 #define SIGURG		29
-#define SIGLOST		30 /* Linux doesn't use this either */
-#define	SIGUNUSED	31
-#define SIGRESERVE	SIGUNUSED
-
-#define SIGXCPU		33
-#define SIGXFSZ		34
-#define SIGSTKFLT	36
+#define SIGXFSZ		30
+#define SIGUNUSED	31
+#define SIGSYS		31 /* Linux doesn't use this */
 
 /* These should not be considered constants from userland.  */
-#define SIGRTMIN	37
+#define SIGRTMIN	32
 #define SIGRTMAX	_NSIG /* it's 44 under HP/UX */
 
 /*
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 4bc7b62fb4b6..88eace4e28c3 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -147,6 +147,7 @@ config PPC
 	select ARCH_USE_CMPXCHG_LOCKREF if PPC64
 	select HAVE_ARCH_AUDITSYSCALL
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
@@ -182,7 +183,7 @@ config SCHED_OMIT_FRAME_POINTER
 
 config ARCH_MAY_HAVE_PC_FDC
 	bool
-	default !PPC_PSERIES || PCI
+	default PCI
 
 config PPC_OF
 	def_bool y
@@ -287,6 +288,10 @@ config PPC_EMULATE_SSTEP
 	bool
 	default y if KPROBES || UPROBES || XMON || HAVE_HW_BREAKPOINT
 
+config ZONE_DMA32
+	bool
+	default y if PPC64
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
@@ -603,6 +608,10 @@ config PPC_SUBPAGE_PROT
 	  to set access permissions (read/write, readonly, or no access)
 	  on the 4k subpages of each 64k page.
 
+config PPC_COPRO_BASE
+	bool
+	default n
+
 config SCHED_SMT
 	bool "SMT (Hyperthreading) scheduler support"
 	depends on PPC64 && SMP
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 5687e299d0a5..132d9c681d6a 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -135,6 +135,7 @@ CFLAGS-$(CONFIG_POWER4_CPU) += $(call cc-option,-mcpu=power4)
 CFLAGS-$(CONFIG_POWER5_CPU) += $(call cc-option,-mcpu=power5)
 CFLAGS-$(CONFIG_POWER6_CPU) += $(call cc-option,-mcpu=power6)
 CFLAGS-$(CONFIG_POWER7_CPU) += $(call cc-option,-mcpu=power7)
+CFLAGS-$(CONFIG_POWER8_CPU) += $(call cc-option,-mcpu=power8)
 
 # Altivec option not allowed with e500mc64 in GCC.
 ifeq ($(CONFIG_ALTIVEC),y)
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index ccc25eddbcb8..8a5bc1cfc6aa 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -389,7 +389,12 @@ $(obj)/zImage:		$(addprefix $(obj)/, $(image-y))
 $(obj)/zImage.initrd:	$(addprefix $(obj)/, $(initrd-y))
 	@rm -f $@; ln $< $@
 
+# Only install the vmlinux
 install: $(CONFIGURE) $(addprefix $(obj)/, $(image-y))
+	sh -x $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" vmlinux System.map "$(INSTALL_PATH)"
+
+# Install the vmlinux and other built boot targets.
+zInstall: $(CONFIGURE) $(addprefix $(obj)/, $(image-y))
 	sh -x $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" vmlinux System.map "$(INSTALL_PATH)" $^
 
 # anything not in $(targets)
diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
index 97479f0ce630..aecee9690a88 100644
--- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
@@ -410,7 +410,7 @@
 /include/ "qoriq-gpio-3.dtsi"
 /include/ "qoriq-usb2-mph-0.dtsi"
 	usb0: usb@210000 {
-		compatible = "fsl-usb2-mph-v2.4", "fsl-usb2-mph";
+		compatible = "fsl-usb2-mph-v2.5", "fsl-usb2-mph";
 		fsl,iommu-parent = <&pamu1>;
 		fsl,liodn-reg = <&guts 0x520>; /* USB1LIODNR */
 		phy_type = "utmi";
@@ -418,7 +418,7 @@
 	};
 /include/ "qoriq-usb2-dr-0.dtsi"
 	usb1: usb@211000 {
-		compatible = "fsl-usb2-dr-v2.4", "fsl-usb2-dr";
+		compatible = "fsl-usb2-dr-v2.5", "fsl-usb2-dr";
 		fsl,iommu-parent = <&pamu1>;
 		fsl,liodn-reg = <&guts 0x524>; /* USB1LIODNR */
 		dr_mode = "host";
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
index a3d582e0361a..7e2fc7cdce48 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
@@ -498,13 +498,13 @@
 /include/ "qoriq-gpio-3.dtsi"
 /include/ "qoriq-usb2-mph-0.dtsi"
 		usb0: usb@210000 {
-			compatible = "fsl-usb2-mph-v2.4", "fsl-usb2-mph";
+			compatible = "fsl-usb2-mph-v2.5", "fsl-usb2-mph";
 			phy_type = "utmi";
 			port0;
 		};
 /include/ "qoriq-usb2-dr-0.dtsi"
 		usb1: usb@211000 {
-			compatible = "fsl-usb2-dr-v2.4", "fsl-usb2-dr";
+			compatible = "fsl-usb2-dr-v2.5", "fsl-usb2-dr";
 			dr_mode = "host";
 			phy_type = "utmi";
 		};
diff --git a/arch/powerpc/boot/dts/t1040rdb.dts b/arch/powerpc/boot/dts/t1040rdb.dts
new file mode 100644
index 000000000000..79a0bed04c1a
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1040rdb.dts
@@ -0,0 +1,48 @@
+/*
+ * T1040RDB Device Tree Source
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t104xsi-pre.dtsi"
+/include/ "t104xrdb.dtsi"
+
+/ {
+	model = "fsl,T1040RDB";
+	compatible = "fsl,T1040RDB";
+	ifc: localbus@ffe124000 {
+		cpld@3,0 {
+			compatible = "fsl,t1040rdb-cpld";
+		};
+	};
+};
+
+/include/ "fsl/t1040si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t1042rdb.dts b/arch/powerpc/boot/dts/t1042rdb.dts
new file mode 100644
index 000000000000..738c23790e94
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1042rdb.dts
@@ -0,0 +1,48 @@
+/*
+ * T1042RDB Device Tree Source
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t104xsi-pre.dtsi"
+/include/ "t104xrdb.dtsi"
+
+/ {
+	model = "fsl,T1042RDB";
+	compatible = "fsl,T1042RDB";
+	ifc: localbus@ffe124000 {
+		cpld@3,0 {
+			compatible = "fsl,t1042rdb-cpld";
+		};
+	};
+};
+
+/include/ "fsl/t1042si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t1042rdb_pi.dts b/arch/powerpc/boot/dts/t1042rdb_pi.dts
new file mode 100644
index 000000000000..634f751fa6d3
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1042rdb_pi.dts
@@ -0,0 +1,57 @@
+/*
+ * T1042RDB_PI Device Tree Source
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t104xsi-pre.dtsi"
+/include/ "t104xrdb.dtsi"
+
+/ {
+	model = "fsl,T1042RDB_PI";
+	compatible = "fsl,T1042RDB_PI";
+	ifc: localbus@ffe124000 {
+		cpld@3,0 {
+			compatible = "fsl,t1042rdb_pi-cpld";
+		};
+	};
+	soc: soc@ffe000000 {
+		i2c@118000 {
+			rtc@68 {
+				compatible = "dallas,ds1337";
+				reg = <0x68>;
+				interrupts = <0x2 0x1 0 0>;
+			};
+		};
+	};
+};
+
+/include/ "fsl/t1042si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t104xrdb.dtsi b/arch/powerpc/boot/dts/t104xrdb.dtsi
new file mode 100644
index 000000000000..1cf0f3c5f7e5
--- /dev/null
+++ b/arch/powerpc/boot/dts/t104xrdb.dtsi
@@ -0,0 +1,156 @@
+/*
+ * T1040RDB/T1042RDB Device Tree Source
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/ {
+
+	ifc: localbus@ffe124000 {
+		reg = <0xf 0xfe124000 0 0x2000>;
+		ranges = <0 0 0xf 0xe8000000 0x08000000
+			  2 0 0xf 0xff800000 0x00010000
+			  3 0 0xf 0xffdf0000 0x00008000>;
+
+		nor@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x8000000>;
+			bank-width = <2>;
+			device-width = <1>;
+		};
+
+		nand@2,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,ifc-nand";
+			reg = <0x2 0x0 0x10000>;
+		};
+
+		cpld@3,0 {
+			reg = <3 0 0x300>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+	};
+
+	dcsr: dcsr@f00000000 {
+		ranges = <0x00000000 0xf 0x00000000 0x01072000>;
+	};
+
+	soc: soc@ffe000000 {
+		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+		reg = <0xf 0xfe000000 0 0x00001000>;
+
+		spi@110000 {
+			flash@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "micron,n25q512a";
+				reg = <0>;
+				spi-max-frequency = <10000000>; /* input clock */
+			};
+		};
+
+		i2c@118100 {
+			pca9546@77 {
+				compatible = "nxp,pca9546";
+				reg = <0x77>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+
+	};
+
+	pci0: pcie@ffe240000 {
+		reg = <0xf 0xfe240000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci1: pcie@ffe250000 {
+		reg = <0xf 0xfe250000 0 0x10000>;
+		ranges = <0x02000000 0x0 0xe0000000 0xc 0x10000000 0x0 0x10000000
+			  0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci2: pcie@ffe260000 {
+		reg = <0xf 0xfe260000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci3: pcie@ffe270000 {
+		reg = <0xf 0xfe270000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x30000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8030000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+};
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index 45fd06cdc3e8..7a7b3c879f96 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -18,6 +18,7 @@ CONFIG_OPROFILE=m
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
+# CONFIG_PPC_POWERNV is not set
 # CONFIG_PPC_PSERIES is not set
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_PS3=y
diff --git a/arch/powerpc/configs/celleb_defconfig b/arch/powerpc/configs/celleb_defconfig
index 77d7bf3ca2ac..acccbfde8a50 100644
--- a/arch/powerpc/configs/celleb_defconfig
+++ b/arch/powerpc/configs/celleb_defconfig
@@ -15,6 +15,7 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
+# CONFIG_PPC_POWERNV is not set
 # CONFIG_PPC_PSERIES is not set
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_CELLEB=y
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index 6a3c58adf253..688e9e4d29a1 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -165,6 +165,8 @@ CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_CODEPAGE_850=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=m
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index 269d6e47c67d..6db97e4414b2 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -50,7 +50,6 @@ CONFIG_NET_IPIP=y
 CONFIG_IP_MROUTE=y
 CONFIG_IP_PIMSM_V1=y
 CONFIG_IP_PIMSM_V2=y
-CONFIG_ARPD=y
 CONFIG_INET_ESP=y
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_LRO is not set
@@ -60,33 +59,17 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_MTD=y
-CONFIG_MTD_OF_PARTS=y
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
-CONFIG_MTD_BLKDEVS=y
 CONFIG_MTD_BLOCK=y
 CONFIG_FTL=y
 CONFIG_MTD_CFI=y
-CONFIG_MTD_GEN_PROBE=y
-CONFIG_MTD_MAP_BANK_WIDTH_1=y
-CONFIG_MTD_MAP_BANK_WIDTH_2=y
-CONFIG_MTD_MAP_BANK_WIDTH_4=y
-CONFIG_MTD_CFI_I1=y
-CONFIG_MTD_CFI_I2=y
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_MTD_M25P80=y
-CONFIG_MTD_CFI_UTIL=y
-CONFIG_MTD_NAND_ECC=y
 CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_IDS=y
 CONFIG_MTD_NAND_FSL_ELBC=y
 CONFIG_MTD_NAND_FSL_IFC=y
 CONFIG_MTD_UBI=y
-CONFIG_MTD_UBI_WL_THRESHOLD=4096
-CONFIG_MTD_UBI_BEB_RESERVE=1
-CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=131072
@@ -102,6 +85,7 @@ CONFIG_INPUT_FF_MEMLESS=m
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
 CONFIG_SERIO_LIBPS2=y
+CONFIG_PPC_EPAPR_HV_BYTECHAN=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
@@ -115,7 +99,6 @@ CONFIG_SPI_GPIO=y
 CONFIG_SPI_FSL_SPI=y
 CONFIG_SPI_FSL_ESPI=y
 # CONFIG_HWMON is not set
-CONFIG_VIDEO_OUTPUT_CONTROL=y
 CONFIG_USB_HID=m
 CONFIG_USB=y
 CONFIG_USB_MON=y
@@ -124,14 +107,17 @@ CONFIG_USB_EHCI_FSL=y
 CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
+CONFIG_EDAC=y
+CONFIG_EDAC_MM_EDAC=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
 CONFIG_RTC_DRV_DS1374=y
 CONFIG_RTC_DRV_DS3232=y
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
 CONFIG_DMADEVICES=y
 CONFIG_FSL_DMA=y
+CONFIG_VIRT_DRIVERS=y
+CONFIG_FSL_HV_MANAGER=y
+CONFIG_FSL_CORENET_CF=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 CONFIG_ISO9660_FS=m
@@ -144,35 +130,24 @@ CONFIG_NTFS_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_HUGETLBFS=y
-CONFIG_MISC_FILESYSTEMS=y
 CONFIG_JFFS2_FS=y
 CONFIG_JFFS2_FS_DEBUG=1
-CONFIG_JFFS2_FS_WRITEBUFFER=y
-CONFIG_JFFS2_ZLIB=y
-CONFIG_JFFS2_RTIME=y
 CONFIG_UBIFS_FS=y
-CONFIG_UBIFS_FS_XATTR=y
-CONFIG_UBIFS_FS_LZO=y
-CONFIG_UBIFS_FS_ZLIB=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_CODEPAGE_850=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=m
 CONFIG_CRC_T10DIF=y
-CONFIG_CRC16=y
-CONFIG_ZLIB_DEFLATE=y
-CONFIG_LZO_COMPRESS=y
-CONFIG_LZO_DECOMPRESS=y
-CONFIG_CRYPTO_DEFLATE=y
-CONFIG_CRYPTO_LZO=y
+CONFIG_DEBUG_INFO=y
 CONFIG_FRAME_WARN=1024
-CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_FS=y
+CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_SHIRQ=y
 CONFIG_DETECT_HUNG_TASK=y
-CONFIG_DEBUG_INFO=y
 CONFIG_CRYPTO_NULL=y
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_MD4=y
@@ -180,4 +155,3 @@ CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_DEV_FSL_CAAM=y
-CONFIG_FSL_CORENET_CF=y
diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig
index 7594c5ac6481..6fab06f7f411 100644
--- a/arch/powerpc/configs/g5_defconfig
+++ b/arch/powerpc/configs/g5_defconfig
@@ -16,6 +16,7 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
+# CONFIG_PPC_POWERNV is not set
 # CONFIG_PPC_PSERIES is not set
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig
index c8b6a9ddb21b..fbd9e4163311 100644
--- a/arch/powerpc/configs/maple_defconfig
+++ b/arch/powerpc/configs/maple_defconfig
@@ -16,6 +16,7 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
 # CONFIG_BLK_DEV_BSG is not set
+# CONFIG_PPC_POWERNV is not set
 # CONFIG_PPC_PSERIES is not set
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_MAPLE=y
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index fa1bfd37f1ec..d2c415489f72 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -213,7 +213,6 @@ CONFIG_RTC_DRV_DS1307=y
 CONFIG_RTC_DRV_DS1374=y
 CONFIG_RTC_DRV_DS3232=y
 CONFIG_RTC_DRV_CMOS=y
-CONFIG_RTC_DRV_DS1307=y
 CONFIG_DMADEVICES=y
 CONFIG_FSL_DMA=y
 # CONFIG_NET_DMA is not set
@@ -227,6 +226,9 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_CODEPAGE_850=y
+CONFIG_NLS_ISO8859_1=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_HUGETLBFS=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index 0b452ebd8b3d..87460083dbc7 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -214,7 +214,6 @@ CONFIG_RTC_DRV_DS1307=y
 CONFIG_RTC_DRV_DS1374=y
 CONFIG_RTC_DRV_DS3232=y
 CONFIG_RTC_DRV_CMOS=y
-CONFIG_RTC_DRV_DS1307=y
 CONFIG_DMADEVICES=y
 CONFIG_FSL_DMA=y
 # CONFIG_NET_DMA is not set
@@ -228,6 +227,9 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_CODEPAGE_850=y
+CONFIG_NLS_ISO8859_1=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_HUGETLBFS=y
diff --git a/arch/powerpc/configs/mpc86xx_defconfig b/arch/powerpc/configs/mpc86xx_defconfig
index 35595ea74ff4..fc58aa8a89e4 100644
--- a/arch/powerpc/configs/mpc86xx_defconfig
+++ b/arch/powerpc/configs/mpc86xx_defconfig
@@ -145,6 +145,9 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=y
 CONFIG_NTFS_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_CODEPAGE_850=y
+CONFIG_NLS_ISO8859_1=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_ADFS_FS=m
diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index e5e7838af008..3e72c8c06a0d 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -14,6 +14,7 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_MAC_PARTITION=y
+# CONFIG_PPC_POWERNV is not set
 # CONFIG_PPC_PSERIES is not set
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_PASEMI=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 36518870e6b2..20bc5e2d368d 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -50,6 +50,7 @@ CONFIG_HZ_100=y
 CONFIG_BINFMT_MISC=m
 CONFIG_PPC_TRANSACTIONAL_MEM=y
 CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
 CONFIG_IRQ_ALL_CPUS=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_SCHED_SMT=y
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 7f23f162ce9c..31e8f59aff38 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -1,6 +1,7 @@
 
 generic-y += clkdev.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += rwsem.h
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 28992d012926..512d2782b043 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -26,76 +26,53 @@ static __inline__ void atomic_set(atomic_t *v, int i)
 	__asm__ __volatile__("stw%U0%X0 %1,%0" : "=m"(v->counter) : "r"(i));
 }
 
-static __inline__ void atomic_add(int a, atomic_t *v)
-{
-	int t;
-
-	__asm__ __volatile__(
-"1:	lwarx	%0,0,%3		# atomic_add\n\
-	add	%0,%2,%0\n"
-	PPC405_ERR77(0,%3)
-"	stwcx.	%0,0,%3 \n\
-	bne-	1b"
-	: "=&r" (t), "+m" (v->counter)
-	: "r" (a), "r" (&v->counter)
-	: "cc");
+#define ATOMIC_OP(op, asm_op)						\
+static __inline__ void atomic_##op(int a, atomic_t *v)			\
+{									\
+	int t;								\
+									\
+	__asm__ __volatile__(						\
+"1:	lwarx	%0,0,%3		# atomic_" #op "\n"			\
+	#asm_op " %0,%2,%0\n"						\
+	PPC405_ERR77(0,%3)						\
+"	stwcx.	%0,0,%3 \n"						\
+"	bne-	1b\n"							\
+	: "=&r" (t), "+m" (v->counter)					\
+	: "r" (a), "r" (&v->counter)					\
+	: "cc");							\
+}									\
+
+#define ATOMIC_OP_RETURN(op, asm_op)					\
+static __inline__ int atomic_##op##_return(int a, atomic_t *v)		\
+{									\
+	int t;								\
+									\
+	__asm__ __volatile__(						\
+	PPC_ATOMIC_ENTRY_BARRIER					\
+"1:	lwarx	%0,0,%2		# atomic_" #op "_return\n"		\
+	#asm_op " %0,%1,%0\n"						\
+	PPC405_ERR77(0,%2)						\
+"	stwcx.	%0,0,%2 \n"						\
+"	bne-	1b\n"							\
+	PPC_ATOMIC_EXIT_BARRIER						\
+	: "=&r" (t)							\
+	: "r" (a), "r" (&v->counter)					\
+	: "cc", "memory");						\
+									\
+	return t;							\
 }
 
-static __inline__ int atomic_add_return(int a, atomic_t *v)
-{
-	int t;
+#define ATOMIC_OPS(op, asm_op) ATOMIC_OP(op, asm_op) ATOMIC_OP_RETURN(op, asm_op)
 
-	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
-"1:	lwarx	%0,0,%2		# atomic_add_return\n\
-	add	%0,%1,%0\n"
-	PPC405_ERR77(0,%2)
-"	stwcx.	%0,0,%2 \n\
-	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
-	: "=&r" (t)
-	: "r" (a), "r" (&v->counter)
-	: "cc", "memory");
+ATOMIC_OPS(add, add)
+ATOMIC_OPS(sub, subf)
 
-	return t;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 #define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
 
-static __inline__ void atomic_sub(int a, atomic_t *v)
-{
-	int t;
-
-	__asm__ __volatile__(
-"1:	lwarx	%0,0,%3		# atomic_sub\n\
-	subf	%0,%2,%0\n"
-	PPC405_ERR77(0,%3)
-"	stwcx.	%0,0,%3 \n\
-	bne-	1b"
-	: "=&r" (t), "+m" (v->counter)
-	: "r" (a), "r" (&v->counter)
-	: "cc");
-}
-
-static __inline__ int atomic_sub_return(int a, atomic_t *v)
-{
-	int t;
-
-	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
-"1:	lwarx	%0,0,%2		# atomic_sub_return\n\
-	subf	%0,%1,%0\n"
-	PPC405_ERR77(0,%2)
-"	stwcx.	%0,0,%2 \n\
-	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
-	: "=&r" (t)
-	: "r" (a), "r" (&v->counter)
-	: "cc", "memory");
-
-	return t;
-}
-
 static __inline__ void atomic_inc(atomic_t *v)
 {
 	int t;
@@ -289,71 +266,50 @@ static __inline__ void atomic64_set(atomic64_t *v, long i)
 	__asm__ __volatile__("std%U0%X0 %1,%0" : "=m"(v->counter) : "r"(i));
 }
 
-static __inline__ void atomic64_add(long a, atomic64_t *v)
-{
-	long t;
-
-	__asm__ __volatile__(
-"1:	ldarx	%0,0,%3		# atomic64_add\n\
-	add	%0,%2,%0\n\
-	stdcx.	%0,0,%3 \n\
-	bne-	1b"
-	: "=&r" (t), "+m" (v->counter)
-	: "r" (a), "r" (&v->counter)
-	: "cc");
+#define ATOMIC64_OP(op, asm_op)						\
+static __inline__ void atomic64_##op(long a, atomic64_t *v)		\
+{									\
+	long t;								\
+									\
+	__asm__ __volatile__(						\
+"1:	ldarx	%0,0,%3		# atomic64_" #op "\n"			\
+	#asm_op " %0,%2,%0\n"						\
+"	stdcx.	%0,0,%3 \n"						\
+"	bne-	1b\n"							\
+	: "=&r" (t), "+m" (v->counter)					\
+	: "r" (a), "r" (&v->counter)					\
+	: "cc");							\
 }
 
-static __inline__ long atomic64_add_return(long a, atomic64_t *v)
-{
-	long t;
-
-	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
-"1:	ldarx	%0,0,%2		# atomic64_add_return\n\
-	add	%0,%1,%0\n\
-	stdcx.	%0,0,%2 \n\
-	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
-	: "=&r" (t)
-	: "r" (a), "r" (&v->counter)
-	: "cc", "memory");
-
-	return t;
+#define ATOMIC64_OP_RETURN(op, asm_op)					\
+static __inline__ long atomic64_##op##_return(long a, atomic64_t *v)	\
+{									\
+	long t;								\
+									\
+	__asm__ __volatile__(						\
+	PPC_ATOMIC_ENTRY_BARRIER					\
+"1:	ldarx	%0,0,%2		# atomic64_" #op "_return\n"		\
+	#asm_op " %0,%1,%0\n"						\
+"	stdcx.	%0,0,%2 \n"						\
+"	bne-	1b\n"							\
+	PPC_ATOMIC_EXIT_BARRIER						\
+	: "=&r" (t)							\
+	: "r" (a), "r" (&v->counter)					\
+	: "cc", "memory");						\
+									\
+	return t;							\
 }
 
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-
-static __inline__ void atomic64_sub(long a, atomic64_t *v)
-{
-	long t;
-
-	__asm__ __volatile__(
-"1:	ldarx	%0,0,%3		# atomic64_sub\n\
-	subf	%0,%2,%0\n\
-	stdcx.	%0,0,%3 \n\
-	bne-	1b"
-	: "=&r" (t), "+m" (v->counter)
-	: "r" (a), "r" (&v->counter)
-	: "cc");
-}
+#define ATOMIC64_OPS(op, asm_op) ATOMIC64_OP(op, asm_op) ATOMIC64_OP_RETURN(op, asm_op)
 
-static __inline__ long atomic64_sub_return(long a, atomic64_t *v)
-{
-	long t;
+ATOMIC64_OPS(add, add)
+ATOMIC64_OPS(sub, subf)
 
-	__asm__ __volatile__(
-	PPC_ATOMIC_ENTRY_BARRIER
-"1:	ldarx	%0,0,%2		# atomic64_sub_return\n\
-	subf	%0,%1,%0\n\
-	stdcx.	%0,0,%2 \n\
-	bne-	1b"
-	PPC_ATOMIC_EXIT_BARRIER
-	: "=&r" (t)
-	: "r" (a), "r" (&v->counter)
-	: "cc", "memory");
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
 
-	return t;
-}
+#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 
 static __inline__ void atomic64_inc(atomic64_t *v)
 {
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index 3eb53d741070..3a39283333c3 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -133,7 +133,6 @@ extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long);
 extern void bad_page_fault(struct pt_regs *, unsigned long, int);
 extern void _exception(int, struct pt_regs *, int, unsigned long);
 extern void die(const char *, struct pt_regs *, long);
-extern void print_backtrace(unsigned long *);
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/copro.h b/arch/powerpc/include/asm/copro.h
new file mode 100644
index 000000000000..ce216df31381
--- /dev/null
+++ b/arch/powerpc/include/asm/copro.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_POWERPC_COPRO_H
+#define _ASM_POWERPC_COPRO_H
+
+struct copro_slb
+{
+	u64 esid, vsid;
+};
+
+int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
+			  unsigned long dsisr, unsigned *flt);
+
+int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb);
+
+
+#ifdef CONFIG_PPC_COPRO_BASE
+void copro_flush_all_slbs(struct mm_struct *mm);
+#else
+static inline void copro_flush_all_slbs(struct mm_struct *mm) {}
+#endif
+#endif /* _ASM_POWERPC_COPRO_H */
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 607559ab271f..e2452550bcb1 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -32,6 +32,8 @@ static inline void setup_cputime_one_jiffy(void) { }
 typedef u64 __nocast cputime_t;
 typedef u64 __nocast cputime64_t;
 
+#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
+
 #ifdef __KERNEL__
 
 /*
@@ -56,10 +58,10 @@ static inline unsigned long cputime_to_jiffies(const cputime_t ct)
 static inline cputime_t cputime_to_scaled(const cputime_t ct)
 {
 	if (cpu_has_feature(CPU_FTR_SPURR) &&
-	    __get_cpu_var(cputime_last_delta))
+	    __this_cpu_read(cputime_last_delta))
 		return (__force u64) ct *
-			__get_cpu_var(cputime_scaled_last_delta) /
-			__get_cpu_var(cputime_last_delta);
+			__this_cpu_read(cputime_scaled_last_delta) /
+			__this_cpu_read(cputime_last_delta);
 	return ct;
 }
 
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 150866b2a3fe..894d538f3567 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -135,6 +135,7 @@ static inline int dma_supported(struct device *dev, u64 mask)
 
 extern int dma_set_mask(struct device *dev, u64 dma_mask);
 extern int __dma_set_mask(struct device *dev, u64 dma_mask);
+extern u64 __dma_get_required_mask(struct device *dev);
 
 #define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
 
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 9983c3d26bca..3b260efbfbf9 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -146,6 +146,11 @@ static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
 	return edev ? edev->pdev : NULL;
 }
 
+static inline struct eeh_pe *eeh_dev_to_pe(struct eeh_dev* edev)
+{
+	return edev ? edev->pe : NULL;
+}
+
 /* Return values from eeh_ops::next_error */
 enum {
 	EEH_NEXT_ERR_NONE = 0,
@@ -167,6 +172,7 @@ enum {
 #define EEH_OPT_ENABLE		1	/* EEH enable	*/
 #define EEH_OPT_THAW_MMIO	2	/* MMIO enable	*/
 #define EEH_OPT_THAW_DMA	3	/* DMA enable	*/
+#define EEH_OPT_FREEZE_PE	4	/* Freeze PE	*/
 #define EEH_STATE_UNAVAILABLE	(1 << 0)	/* State unavailable	*/
 #define EEH_STATE_NOT_SUPPORT	(1 << 1)	/* EEH not supported	*/
 #define EEH_STATE_RESET_ACTIVE	(1 << 2)	/* Active reset		*/
@@ -198,6 +204,8 @@ struct eeh_ops {
 	int (*wait_state)(struct eeh_pe *pe, int max_wait);
 	int (*get_log)(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len);
 	int (*configure_bridge)(struct eeh_pe *pe);
+	int (*err_inject)(struct eeh_pe *pe, int type, int func,
+			  unsigned long addr, unsigned long mask);
 	int (*read_config)(struct device_node *dn, int where, int size, u32 *val);
 	int (*write_config)(struct device_node *dn, int where, int size, u32 val);
 	int (*next_error)(struct eeh_pe **pe);
@@ -269,8 +277,7 @@ void eeh_dev_phb_init_dynamic(struct pci_controller *phb);
 int eeh_init(void);
 int __init eeh_ops_register(struct eeh_ops *ops);
 int __exit eeh_ops_unregister(const char *name);
-unsigned long eeh_check_failure(const volatile void __iomem *token,
-				unsigned long val);
+int eeh_check_failure(const volatile void __iomem *token);
 int eeh_dev_check_failure(struct eeh_dev *edev);
 void eeh_addr_cache_build(void);
 void eeh_add_device_early(struct device_node *);
@@ -279,6 +286,8 @@ void eeh_add_device_late(struct pci_dev *);
 void eeh_add_device_tree_late(struct pci_bus *);
 void eeh_add_sysfs_files(struct pci_bus *);
 void eeh_remove_device(struct pci_dev *);
+int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state);
+int eeh_pe_reset_and_recover(struct eeh_pe *pe);
 int eeh_dev_open(struct pci_dev *pdev);
 void eeh_dev_release(struct pci_dev *pdev);
 struct eeh_pe *eeh_iommu_group_to_pe(struct iommu_group *group);
@@ -321,9 +330,9 @@ static inline void *eeh_dev_init(struct device_node *dn, void *data)
 
 static inline void eeh_dev_phb_init_dynamic(struct pci_controller *phb) { }
 
-static inline unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
+static inline int eeh_check_failure(const volatile void __iomem *token)
 {
-	return val;
+	return 0;
 }
 
 #define eeh_dev_check_failure(x) (0)
@@ -354,7 +363,7 @@ static inline u8 eeh_readb(const volatile void __iomem *addr)
 {
 	u8 val = in_8(addr);
 	if (EEH_POSSIBLE_ERROR(val, u8))
-		return eeh_check_failure(addr, val);
+		eeh_check_failure(addr);
 	return val;
 }
 
@@ -362,7 +371,7 @@ static inline u16 eeh_readw(const volatile void __iomem *addr)
 {
 	u16 val = in_le16(addr);
 	if (EEH_POSSIBLE_ERROR(val, u16))
-		return eeh_check_failure(addr, val);
+		eeh_check_failure(addr);
 	return val;
 }
 
@@ -370,7 +379,7 @@ static inline u32 eeh_readl(const volatile void __iomem *addr)
 {
 	u32 val = in_le32(addr);
 	if (EEH_POSSIBLE_ERROR(val, u32))
-		return eeh_check_failure(addr, val);
+		eeh_check_failure(addr);
 	return val;
 }
 
@@ -378,7 +387,7 @@ static inline u64 eeh_readq(const volatile void __iomem *addr)
 {
 	u64 val = in_le64(addr);
 	if (EEH_POSSIBLE_ERROR(val, u64))
-		return eeh_check_failure(addr, val);
+		eeh_check_failure(addr);
 	return val;
 }
 
@@ -386,7 +395,7 @@ static inline u16 eeh_readw_be(const volatile void __iomem *addr)
 {
 	u16 val = in_be16(addr);
 	if (EEH_POSSIBLE_ERROR(val, u16))
-		return eeh_check_failure(addr, val);
+		eeh_check_failure(addr);
 	return val;
 }
 
@@ -394,7 +403,7 @@ static inline u32 eeh_readl_be(const volatile void __iomem *addr)
 {
 	u32 val = in_be32(addr);
 	if (EEH_POSSIBLE_ERROR(val, u32))
-		return eeh_check_failure(addr, val);
+		eeh_check_failure(addr);
 	return val;
 }
 
@@ -402,7 +411,7 @@ static inline u64 eeh_readq_be(const volatile void __iomem *addr)
 {
 	u64 val = in_be64(addr);
 	if (EEH_POSSIBLE_ERROR(val, u64))
-		return eeh_check_failure(addr, val);
+		eeh_check_failure(addr);
 	return val;
 }
 
@@ -416,7 +425,7 @@ static inline void eeh_memcpy_fromio(void *dest, const
 	 * were copied. Check all four bytes.
 	 */
 	if (n >= 4 && EEH_POSSIBLE_ERROR(*((u32 *)(dest + n - 4)), u32))
-		eeh_check_failure(src, *((u32 *)(dest + n - 4)));
+		eeh_check_failure(src);
 }
 
 /* in-string eeh macros */
@@ -425,7 +434,7 @@ static inline void eeh_readsb(const volatile void __iomem *addr, void * buf,
 {
 	_insb(addr, buf, ns);
 	if (EEH_POSSIBLE_ERROR((*(((u8*)buf)+ns-1)), u8))
-		eeh_check_failure(addr, *(u8*)buf);
+		eeh_check_failure(addr);
 }
 
 static inline void eeh_readsw(const volatile void __iomem *addr, void * buf,
@@ -433,7 +442,7 @@ static inline void eeh_readsw(const volatile void __iomem *addr, void * buf,
 {
 	_insw(addr, buf, ns);
 	if (EEH_POSSIBLE_ERROR((*(((u16*)buf)+ns-1)), u16))
-		eeh_check_failure(addr, *(u16*)buf);
+		eeh_check_failure(addr);
 }
 
 static inline void eeh_readsl(const volatile void __iomem *addr, void * buf,
@@ -441,7 +450,7 @@ static inline void eeh_readsl(const volatile void __iomem *addr, void * buf,
 {
 	_insl(addr, buf, nl);
 	if (EEH_POSSIBLE_ERROR((*(((u32*)buf)+nl-1)), u32))
-		eeh_check_failure(addr, *(u32*)buf);
+		eeh_check_failure(addr);
 }
 
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/include/asm/hydra.h b/arch/powerpc/include/asm/hydra.h
index 5b0c98bd46ab..1cb39c96d155 100644
--- a/arch/powerpc/include/asm/hydra.h
+++ b/arch/powerpc/include/asm/hydra.h
@@ -95,7 +95,6 @@ extern volatile struct Hydra __iomem *Hydra;
 #define HYDRA_INT_SPARE		19
 
 extern int hydra_init(void);
-extern void macio_adb_init(void);
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 41f13cec8a8f..e8e3a0a04eb0 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -31,11 +31,6 @@ extern atomic_t ppc_n_lost_interrupts;
 
 extern irq_hw_number_t virq_to_hw(unsigned int virq);
 
-/**
- * irq_early_init - Init irq remapping subsystem
- */
-extern void irq_early_init(void);
-
 static __inline__ int irq_canonicalize(int irq)
 {
 	return irq;
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 16d7e33d35e9..19c36cba37c4 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -81,7 +81,6 @@ extern void default_machine_crash_shutdown(struct pt_regs *regs);
 extern int crash_shutdown_register(crash_shutdown_t handler);
 extern int crash_shutdown_unregister(crash_shutdown_t handler);
 
-extern void machine_kexec_simple(struct kimage *image);
 extern void crash_kexec_secondary(struct pt_regs *regs);
 extern int overlaps_crashkernel(unsigned long start, unsigned long size);
 extern void reserve_crashkernel(void);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index b125ceab149c..307347f8ddbd 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -136,8 +136,6 @@ struct machdep_calls {
 	int		(*pci_setup_phb)(struct pci_controller *host);
 
 #ifdef CONFIG_PCI_MSI
-	int		(*msi_check_device)(struct pci_dev* dev,
-					    int nvec, int type);
 	int		(*setup_msi_irqs)(struct pci_dev *dev,
 					  int nvec, int type);
 	void		(*teardown_msi_irqs)(struct pci_dev *dev);
@@ -330,8 +328,6 @@ extern struct machdep_calls *machine_id;
 
 extern void probe_machine(void);
 
-extern char cmd_line[COMMAND_LINE_SIZE];
-
 #ifdef CONFIG_PPC_PMAC
 /*
  * Power macintoshes have either a CUDA, PMU or SMU controlling
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index d76514487d6f..aeebc94b2bce 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -190,6 +190,13 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
 
 #ifndef __ASSEMBLY__
 
+static inline int slb_vsid_shift(int ssize)
+{
+	if (ssize == MMU_SEGSIZE_256M)
+		return SLB_VSID_SHIFT;
+	return SLB_VSID_SHIFT_1T;
+}
+
 static inline int segment_shift(int ssize)
 {
 	if (ssize == MMU_SEGSIZE_256M)
@@ -317,6 +324,7 @@ extern int __hash_page_64K(unsigned long ea, unsigned long access,
 			   unsigned int local, int ssize);
 struct mm_struct;
 unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap);
+extern int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap);
 extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap);
 int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		     pte_t *ptep, unsigned long trap, int local, int ssize,
@@ -342,6 +350,8 @@ extern void hash_failure_debug(unsigned long ea, unsigned long access,
 extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 			     unsigned long pstart, unsigned long prot,
 			     int psize, int ssize);
+int htab_remove_mapping(unsigned long vstart, unsigned long vend,
+			int psize, int ssize);
 extern void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages);
 extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
 
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 86055e598269..9124b0ede1fc 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -135,6 +135,7 @@ struct opal_sg_list {
 #define OPAL_FLASH_MANAGE			77
 #define OPAL_FLASH_UPDATE			78
 #define OPAL_RESYNC_TIMEBASE			79
+#define OPAL_CHECK_TOKEN			80
 #define OPAL_DUMP_INIT				81
 #define OPAL_DUMP_INFO				82
 #define OPAL_DUMP_READ				83
@@ -146,7 +147,9 @@ struct opal_sg_list {
 #define OPAL_GET_PARAM				89
 #define OPAL_SET_PARAM				90
 #define OPAL_DUMP_RESEND			91
+#define OPAL_PCI_SET_PHB_CXL_MODE		93
 #define OPAL_DUMP_INFO2				94
+#define OPAL_PCI_ERR_INJECT			96
 #define OPAL_PCI_EEH_FREEZE_SET			97
 #define OPAL_HANDLE_HMI				98
 #define OPAL_REGISTER_DUMP_REGION		101
@@ -199,6 +202,35 @@ enum OpalPciErrorSeverity {
 	OPAL_EEH_SEV_INF	= 5
 };
 
+enum OpalErrinjectType {
+	OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR	= 0,
+	OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64	= 1,
+};
+
+enum OpalErrinjectFunc {
+	/* IOA bus specific errors */
+	OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR	= 0,
+	OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_DATA	= 1,
+	OPAL_ERR_INJECT_FUNC_IOA_LD_IO_ADDR	= 2,
+	OPAL_ERR_INJECT_FUNC_IOA_LD_IO_DATA	= 3,
+	OPAL_ERR_INJECT_FUNC_IOA_LD_CFG_ADDR	= 4,
+	OPAL_ERR_INJECT_FUNC_IOA_LD_CFG_DATA	= 5,
+	OPAL_ERR_INJECT_FUNC_IOA_ST_MEM_ADDR	= 6,
+	OPAL_ERR_INJECT_FUNC_IOA_ST_MEM_DATA	= 7,
+	OPAL_ERR_INJECT_FUNC_IOA_ST_IO_ADDR	= 8,
+	OPAL_ERR_INJECT_FUNC_IOA_ST_IO_DATA	= 9,
+	OPAL_ERR_INJECT_FUNC_IOA_ST_CFG_ADDR	= 10,
+	OPAL_ERR_INJECT_FUNC_IOA_ST_CFG_DATA	= 11,
+	OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_ADDR	= 12,
+	OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_DATA	= 13,
+	OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_MASTER	= 14,
+	OPAL_ERR_INJECT_FUNC_IOA_DMA_RD_TARGET	= 15,
+	OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_ADDR	= 16,
+	OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_DATA	= 17,
+	OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_MASTER	= 18,
+	OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET	= 19,
+};
+
 enum OpalShpcAction {
 	OPAL_SHPC_GET_LINK_STATE = 0,
 	OPAL_SHPC_GET_SLOT_STATE = 1
@@ -356,9 +388,12 @@ enum OpalM64EnableAction {
 };
 
 enum OpalPciResetScope {
-	OPAL_PHB_COMPLETE = 1, OPAL_PCI_LINK = 2, OPAL_PHB_ERROR = 3,
-	OPAL_PCI_HOT_RESET = 4, OPAL_PCI_FUNDAMENTAL_RESET = 5,
-	OPAL_PCI_IODA_TABLE_RESET = 6,
+	OPAL_RESET_PHB_COMPLETE		= 1,
+	OPAL_RESET_PCI_LINK		= 2,
+	OPAL_RESET_PHB_ERROR		= 3,
+	OPAL_RESET_PCI_HOT		= 4,
+	OPAL_RESET_PCI_FUNDAMENTAL	= 5,
+	OPAL_RESET_PCI_IODA_TABLE	= 6
 };
 
 enum OpalPciReinitScope {
@@ -819,6 +854,8 @@ int64_t opal_pci_eeh_freeze_clear(uint64_t phb_id, uint64_t pe_number,
 				  uint64_t eeh_action_token);
 int64_t opal_pci_eeh_freeze_set(uint64_t phb_id, uint64_t pe_number,
 				uint64_t eeh_action_token);
+int64_t opal_pci_err_inject(uint64_t phb_id, uint32_t pe_no, uint32_t type,
+			    uint32_t func, uint64_t addr, uint64_t mask);
 int64_t opal_pci_shpc(uint64_t phb_id, uint64_t shpc_action, uint8_t *state);
 
 
@@ -887,6 +924,7 @@ int64_t opal_pci_next_error(uint64_t phb_id, __be64 *first_frozen_pe,
 			    __be16 *pci_error_type, __be16 *severity);
 int64_t opal_pci_poll(uint64_t phb_id);
 int64_t opal_return_cpu(void);
+int64_t opal_check_token(uint64_t token);
 int64_t opal_reinit_cpus(uint64_t flags);
 
 int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val);
@@ -924,6 +962,7 @@ int64_t opal_sensor_read(uint32_t sensor_hndl, int token, __be32 *sensor_data);
 int64_t opal_handle_hmi(void);
 int64_t opal_register_dump_region(uint32_t id, uint64_t start, uint64_t end);
 int64_t opal_unregister_dump_region(uint32_t id);
+int64_t opal_pci_set_phb_cxl_mode(uint64_t phb_id, uint64_t mode, uint64_t pe_number);
 
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 88693cef4f3d..d908a46d05c0 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -42,20 +42,40 @@
 
 typedef unsigned long pte_basic_t;
 
-static __inline__ void clear_page(void *addr)
+static inline void clear_page(void *addr)
 {
-	unsigned long lines, line_size;
-
-	line_size = ppc64_caches.dline_size;
-	lines = ppc64_caches.dlines_per_page;
-
-	__asm__ __volatile__(
+	unsigned long iterations;
+	unsigned long onex, twox, fourx, eightx;
+
+	iterations = ppc64_caches.dlines_per_page / 8;
+
+	/*
+	 * Some verisions of gcc use multiply instructions to
+	 * calculate the offsets so lets give it a hand to
+	 * do better.
+	 */
+	onex = ppc64_caches.dline_size;
+	twox = onex << 1;
+	fourx = onex << 2;
+	eightx = onex << 3;
+
+	asm volatile(
 	"mtctr	%1	# clear_page\n\
-1:      dcbz	0,%0\n\
-	add	%0,%0,%3\n\
+	.balign	16\n\
+1:	dcbz	0,%0\n\
+	dcbz	%3,%0\n\
+	dcbz	%4,%0\n\
+	dcbz	%5,%0\n\
+	dcbz	%6,%0\n\
+	dcbz	%7,%0\n\
+	dcbz	%8,%0\n\
+	dcbz	%9,%0\n\
+	add	%0,%0,%10\n\
 	bdnz+	1b"
-        : "=r" (addr)
-        : "r" (lines), "0" (addr), "r" (line_size)
+	: "=&r" (addr)
+	: "r" (iterations), "0" (addr), "b" (onex), "b" (twox),
+		"b" (twox+onex), "b" (fourx), "b" (fourx+onex),
+		"b" (twox+fourx), "b" (eightx-onex), "r" (eightx)
 	: "ctr", "memory");
 }
 
@@ -104,7 +124,6 @@ extern unsigned long slice_get_unmapped_area(unsigned long addr,
 extern unsigned int get_slice_psize(struct mm_struct *mm,
 				    unsigned long addr);
 
-extern void slice_init_context(struct mm_struct *mm, unsigned int psize);
 extern void slice_set_user_psize(struct mm_struct *mm, unsigned int psize);
 extern void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
 				  unsigned long len, unsigned int psize);
diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/pgtable-ppc32.h
index 47edde8c3556..945e47adf7db 100644
--- a/arch/powerpc/include/asm/pgtable-ppc32.h
+++ b/arch/powerpc/include/asm/pgtable-ppc32.h
@@ -8,8 +8,6 @@
 #include <linux/threads.h>
 #include <asm/io.h>			/* For sub-arch specific PPC_PIN_SIZE */
 
-extern unsigned long va_to_phys(unsigned long address);
-extern pte_t *va_to_pte(unsigned long address);
 extern unsigned long ioremap_bot;
 
 #ifdef CONFIG_44x
@@ -50,10 +48,10 @@ extern int icache_44x_need_flush;
 #define FIRST_USER_ADDRESS	0
 
 #define pte_ERROR(e) \
-	printk("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \
+	pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \
 		(unsigned long long)pte_val(e))
 #define pgd_ERROR(e) \
-	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
 /*
  * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary
diff --git a/arch/powerpc/include/asm/pgtable-ppc64-4k.h b/arch/powerpc/include/asm/pgtable-ppc64-4k.h
index 12798c9d4b4b..7b935683f268 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64-4k.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64-4k.h
@@ -64,7 +64,7 @@
     (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)))
 
 #define pud_ERROR(e) \
-	printk("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e))
+	pr_err("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e))
 
 /*
  * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() */
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 7b3d54fae46f..ae153c40ab7c 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -328,11 +328,11 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 #define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)
 
 #define pte_ERROR(e) \
-	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
+	pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
 #define pmd_ERROR(e) \
-	printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+	pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
 #define pgd_ERROR(e) \
-	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
 /* Encode and de-code a swap entry */
 #define __swp_type(entry)	(((entry).val >> 1) & 0x3f)
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index d98c1ecc3266..316f9a5da173 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -4,6 +4,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/mmdebug.h>
+#include <linux/mmzone.h>
 #include <asm/processor.h>		/* For TASK_SIZE */
 #include <asm/mmu.h>
 #include <asm/page.h>
@@ -38,10 +39,9 @@ static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK)
 static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
 
 #ifdef CONFIG_NUMA_BALANCING
-
 static inline int pte_present(pte_t pte)
 {
-	return pte_val(pte) & (_PAGE_PRESENT | _PAGE_NUMA);
+	return pte_val(pte) & _PAGE_NUMA_MASK;
 }
 
 #define pte_present_nonuma pte_present_nonuma
@@ -50,37 +50,6 @@ static inline int pte_present_nonuma(pte_t pte)
 	return pte_val(pte) & (_PAGE_PRESENT);
 }
 
-#define pte_numa pte_numa
-static inline int pte_numa(pte_t pte)
-{
-	return (pte_val(pte) &
-		(_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
-}
-
-#define pte_mknonnuma pte_mknonnuma
-static inline pte_t pte_mknonnuma(pte_t pte)
-{
-	pte_val(pte) &= ~_PAGE_NUMA;
-	pte_val(pte) |=  _PAGE_PRESENT | _PAGE_ACCESSED;
-	return pte;
-}
-
-#define pte_mknuma pte_mknuma
-static inline pte_t pte_mknuma(pte_t pte)
-{
-	/*
-	 * We should not set _PAGE_NUMA on non present ptes. Also clear the
-	 * present bit so that hash_page will return 1 and we collect this
-	 * as numa fault.
-	 */
-	if (pte_present(pte)) {
-		pte_val(pte) |= _PAGE_NUMA;
-		pte_val(pte) &= ~_PAGE_PRESENT;
-	} else
-		VM_BUG_ON(1);
-	return pte;
-}
-
 #define ptep_set_numa ptep_set_numa
 static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep)
@@ -92,12 +61,6 @@ static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
 	return;
 }
 
-#define pmd_numa pmd_numa
-static inline int pmd_numa(pmd_t pmd)
-{
-	return pte_numa(pmd_pte(pmd));
-}
-
 #define pmdp_set_numa pmdp_set_numa
 static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
 				 pmd_t *pmdp)
@@ -109,16 +72,21 @@ static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
 	return;
 }
 
-#define pmd_mknonnuma pmd_mknonnuma
-static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+/*
+ * Generic NUMA pte helpers expect pteval_t and pmdval_t types to exist
+ * which was inherited from x86. For the purposes of powerpc pte_basic_t and
+ * pmd_t are equivalent
+ */
+#define pteval_t pte_basic_t
+#define pmdval_t pmd_t
+static inline pteval_t ptenuma_flags(pte_t pte)
 {
-	return pte_pmd(pte_mknonnuma(pmd_pte(pmd)));
+	return pte_val(pte) & _PAGE_NUMA_MASK;
 }
 
-#define pmd_mknuma pmd_mknuma
-static inline pmd_t pmd_mknuma(pmd_t pmd)
+static inline pmdval_t pmdnuma_flags(pmd_t pmd)
 {
-	return pte_pmd(pte_mknuma(pmd_pte(pmd)));
+	return pmd_val(pmd) & _PAGE_NUMA_MASK;
 }
 
 # else
@@ -281,6 +249,8 @@ extern unsigned long empty_zero_page[];
 
 extern pgd_t swapper_pg_dir[];
 
+void limit_zone_pfn(enum zone_type zone, unsigned long max_pfn);
+int dma_pfn_limit_to_zone(u64 pfn_limit);
 extern void paging_init(void);
 
 /*
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index 12c32c5f533d..67859edbf8fd 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -273,7 +273,7 @@ static inline long plpar_set_mode(unsigned long mflags, unsigned long resource,
 static inline long enable_reloc_on_exceptions(void)
 {
 	/* mflags = 3: Exceptions at 0xC000000000004000 */
-	return plpar_set_mode(3, 3, 0, 0);
+	return plpar_set_mode(3, H_SET_MODE_RESOURCE_ADDR_TRANS_MODE, 0, 0);
 }
 
 /*
@@ -284,7 +284,7 @@ static inline long enable_reloc_on_exceptions(void)
  * returns H_SUCCESS.
  */
 static inline long disable_reloc_on_exceptions(void) {
-	return plpar_set_mode(0, 3, 0, 0);
+	return plpar_set_mode(0, H_SET_MODE_RESOURCE_ADDR_TRANS_MODE, 0, 0);
 }
 
 /*
@@ -297,7 +297,7 @@ static inline long disable_reloc_on_exceptions(void) {
 static inline long enable_big_endian_exceptions(void)
 {
 	/* mflags = 0: big endian exceptions */
-	return plpar_set_mode(0, 4, 0, 0);
+	return plpar_set_mode(0, H_SET_MODE_RESOURCE_LE, 0, 0);
 }
 
 /*
@@ -310,17 +310,17 @@ static inline long enable_big_endian_exceptions(void)
 static inline long enable_little_endian_exceptions(void)
 {
 	/* mflags = 1: little endian exceptions */
-	return plpar_set_mode(1, 4, 0, 0);
+	return plpar_set_mode(1, H_SET_MODE_RESOURCE_LE, 0, 0);
 }
 
 static inline long plapr_set_ciabr(unsigned long ciabr)
 {
-	return plpar_set_mode(0, 1, ciabr, 0);
+	return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_CIABR, ciabr, 0);
 }
 
 static inline long plapr_set_watchpoint0(unsigned long dawr0, unsigned long dawrx0)
 {
-	return plpar_set_mode(0, 2, dawr0, dawrx0);
+	return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR, dawr0, dawrx0);
 }
 
 #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */
diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
new file mode 100644
index 000000000000..f09a22fa1bd7
--- /dev/null
+++ b/arch/powerpc/include/asm/pnv-pci.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_PNV_PCI_H
+#define _ASM_PNV_PCI_H
+
+#include <linux/pci.h>
+#include <misc/cxl.h>
+
+int pnv_phb_to_cxl(struct pci_dev *dev);
+int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
+			   unsigned int virq);
+int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num);
+void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num);
+int pnv_cxl_get_irq_count(struct pci_dev *dev);
+struct device_node *pnv_pci_to_phb_node(struct pci_dev *dev);
+
+#ifdef CONFIG_CXL_BASE
+int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
+			       struct pci_dev *dev, int num);
+void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
+				  struct pci_dev *dev);
+#endif
+
+#endif
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 74b79f07f041..7f436ba1b56f 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -76,8 +76,6 @@ void of_parse_dma_window(struct device_node *dn, const __be32 *dma_window,
 			 unsigned long *busno, unsigned long *phys,
 			 unsigned long *size);
 
-extern void kdump_move_device_tree(void);
-
 extern void of_instantiate_rtc(void);
 
 extern int of_get_ibm_chip_id(struct device_node *np);
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index 8d1569c29042..e040c3595129 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -98,6 +98,11 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
 			 _PAGE_USER | _PAGE_ACCESSED | \
 			 _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | _PAGE_EXEC)
 
+#ifdef CONFIG_NUMA_BALANCING
+/* Mask of bits that distinguish present and numa ptes */
+#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PRESENT)
+#endif
+
 /*
  * We define 2 sets of base prot bits, one for basic pages (ie,
  * cacheable kernel and user pages) and one for non cacheable
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 0c0505956a29..fe3f9488f321 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -947,7 +947,7 @@
  * 32-bit 8xx:
  *	- SPRG0 scratch for exception vectors
  *	- SPRG1 scratch for exception vectors
- *	- SPRG2 apparently unused but initialized
+ *	- SPRG2 scratch for exception vectors
  *
  */
 #ifdef CONFIG_PPC64
@@ -1057,6 +1057,7 @@
 #ifdef CONFIG_8xx
 #define SPRN_SPRG_SCRATCH0	SPRN_SPRG0
 #define SPRN_SPRG_SCRATCH1	SPRN_SPRG1
+#define SPRN_SPRG_SCRATCH2	SPRN_SPRG2
 #endif
 
 
diff --git a/arch/powerpc/include/asm/rio.h b/arch/powerpc/include/asm/rio.h
index b1d2deceeedb..ec800f28fec5 100644
--- a/arch/powerpc/include/asm/rio.h
+++ b/arch/powerpc/include/asm/rio.h
@@ -13,7 +13,6 @@
 #ifndef ASM_PPC_RIO_H
 #define ASM_PPC_RIO_H
 
-extern void platform_rio_init(void);
 #ifdef CONFIG_FSL_RIO
 extern int fsl_rio_mcheck_exception(struct pt_regs *);
 #else
diff --git a/arch/powerpc/include/asm/spu.h b/arch/powerpc/include/asm/spu.h
index 37b7ca39ec9f..a6e6e2bf9d15 100644
--- a/arch/powerpc/include/asm/spu.h
+++ b/arch/powerpc/include/asm/spu.h
@@ -27,6 +27,8 @@
 #include <linux/workqueue.h>
 #include <linux/device.h>
 #include <linux/mutex.h>
+#include <asm/reg.h>
+#include <asm/copro.h>
 
 #define LS_SIZE (256 * 1024)
 #define LS_ADDR_MASK (LS_SIZE - 1)
@@ -277,9 +279,6 @@ void spu_remove_dev_attr(struct device_attribute *attr);
 int spu_add_dev_attr_group(struct attribute_group *attrs);
 void spu_remove_dev_attr_group(struct attribute_group *attrs);
 
-int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
-		unsigned long dsisr, unsigned *flt);
-
 /*
  * Notifier blocks:
  *
diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h
index f593b0f9b627..d3a42cc45a82 100644
--- a/arch/powerpc/include/asm/sstep.h
+++ b/arch/powerpc/include/asm/sstep.h
@@ -25,3 +25,65 @@ struct pt_regs;
 
 /* Emulate instructions that cause a transfer of control. */
 extern int emulate_step(struct pt_regs *regs, unsigned int instr);
+
+enum instruction_type {
+	COMPUTE,		/* arith/logical/CR op, etc. */
+	LOAD,
+	LOAD_MULTI,
+	LOAD_FP,
+	LOAD_VMX,
+	LOAD_VSX,
+	STORE,
+	STORE_MULTI,
+	STORE_FP,
+	STORE_VMX,
+	STORE_VSX,
+	LARX,
+	STCX,
+	BRANCH,
+	MFSPR,
+	MTSPR,
+	CACHEOP,
+	BARRIER,
+	SYSCALL,
+	MFMSR,
+	MTMSR,
+	RFI,
+	INTERRUPT,
+	UNKNOWN
+};
+
+#define INSTR_TYPE_MASK	0x1f
+
+/* Load/store flags, ORed in with type */
+#define SIGNEXT		0x20
+#define UPDATE		0x40	/* matches bit in opcode 31 instructions */
+#define BYTEREV		0x80
+
+/* Cacheop values, ORed in with type */
+#define CACHEOP_MASK	0x700
+#define DCBST		0
+#define DCBF		0x100
+#define DCBTST		0x200
+#define DCBT		0x300
+#define ICBI		0x400
+
+/* Size field in type word */
+#define SIZE(n)		((n) << 8)
+#define GETSIZE(w)	((w) >> 8)
+
+#define MKOP(t, f, s)	((t) | (f) | SIZE(s))
+
+struct instruction_op {
+	int type;
+	int reg;
+	unsigned long val;
+	/* For LOAD/STORE/LARX/STCX */
+	unsigned long ea;
+	int update_reg;
+	/* For MFSPR */
+	int spr;
+};
+
+extern int analyse_instr(struct instruction_op *op, struct pt_regs *regs,
+			 unsigned int instr);
diff --git a/arch/powerpc/include/asm/tsi108.h b/arch/powerpc/include/asm/tsi108.h
index f8b60793b7a9..d531d9e173ef 100644
--- a/arch/powerpc/include/asm/tsi108.h
+++ b/arch/powerpc/include/asm/tsi108.h
@@ -84,10 +84,6 @@
 extern u32 tsi108_pci_cfg_base;
 /* Exported functions */
 
-extern int tsi108_bridge_init(struct pci_controller *hose, uint phys_csr_base);
-extern unsigned long tsi108_get_mem_size(void);
-extern unsigned long tsi108_get_cpu_clk(void);
-extern unsigned long tsi108_get_sdc_clk(void);
 extern int tsi108_direct_write_config(struct pci_bus *bus, unsigned int devfn,
 				      int offset, int len, u32 val);
 extern int tsi108_direct_read_config(struct pci_bus *bus, unsigned int devfn,
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index b51fba10e733..78f2675f2aac 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -52,7 +52,6 @@ extern void __init udbg_init_44x_as1(void);
 extern void __init udbg_init_40x_realmode(void);
 extern void __init udbg_init_cpm(void);
 extern void __init udbg_init_usbgecko(void);
-extern void __init udbg_init_wsp(void);
 extern void __init udbg_init_memcons(void);
 extern void __init udbg_init_ehv_bc(void);
 extern void __init udbg_init_ps3gelic(void);
diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h
index 9a5c928bb3c6..5b3a903adae6 100644
--- a/arch/powerpc/include/asm/word-at-a-time.h
+++ b/arch/powerpc/include/asm/word-at-a-time.h
@@ -42,32 +42,65 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct
 
 #else
 
+#ifdef CONFIG_64BIT
+
+/* unused */
 struct word_at_a_time {
-	const unsigned long one_bits, high_bits;
 };
 
-#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+#define WORD_AT_A_TIME_CONSTANTS { }
 
-#ifdef CONFIG_64BIT
+/* This will give us 0xff for a NULL char and 0x00 elsewhere */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+	unsigned long ret;
+	unsigned long zero = 0;
 
-/* Alan Modra's little-endian strlen tail for 64-bit */
-#define create_zero_mask(mask) (mask)
+	asm("cmpb %0,%1,%2" : "=r" (ret) : "r" (a), "r" (zero));
+	*bits = ret;
 
-static inline unsigned long find_zero(unsigned long mask)
+	return ret;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+/* Alan Modra's little-endian strlen tail for 64-bit */
+static inline unsigned long create_zero_mask(unsigned long bits)
 {
 	unsigned long leading_zero_bits;
 	long trailing_zero_bit_mask;
 
-	asm ("addi %1,%2,-1\n\t"
-	     "andc %1,%1,%2\n\t"
-	     "popcntd %0,%1"
-	     : "=r" (leading_zero_bits), "=&r" (trailing_zero_bit_mask)
-	     : "r" (mask));
-	return leading_zero_bits >> 3;
+	asm("addi	%1,%2,-1\n\t"
+	    "andc	%1,%1,%2\n\t"
+	    "popcntd	%0,%1"
+		: "=r" (leading_zero_bits), "=&r" (trailing_zero_bit_mask)
+		: "r" (bits));
+
+	return leading_zero_bits;
+}
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	return mask >> 3;
+}
+
+/* This assumes that we never ask for an all 1s bitmask */
+static inline unsigned long zero_bytemask(unsigned long mask)
+{
+	return (1UL << mask) - 1;
 }
 
 #else	/* 32-bit case */
 
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
 /*
  * This is largely generic for little-endian machines, but the
  * optimal byte mask counting is probably going to be something
@@ -96,8 +129,6 @@ static inline unsigned long find_zero(unsigned long mask)
 	return count_masked_bytes(mask);
 }
 
-#endif
-
 /* Return nonzero if it has a zero */
 static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
 {
@@ -114,6 +145,59 @@ static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits,
 /* The mask we created is directly usable as a bytemask */
 #define zero_bytemask(mask) (mask)
 
+#endif /* CONFIG_64BIT */
+
+#endif /* __BIG_ENDIAN__ */
+
+/*
+ * We use load_unaligned_zero() in a selftest, which builds a userspace
+ * program. Some linker scripts seem to discard the .fixup section, so allow
+ * the test code to use a different section name.
+ */
+#ifndef FIXUP_SECTION
+#define FIXUP_SECTION ".fixup"
+#endif
+
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long ret, offset, tmp;
+
+	asm(
+	"1:	" PPC_LL "%[ret], 0(%[addr])\n"
+	"2:\n"
+	".section " FIXUP_SECTION ",\"ax\"\n"
+	"3:	"
+#ifdef __powerpc64__
+	"clrrdi		%[tmp], %[addr], 3\n\t"
+	"clrlsldi	%[offset], %[addr], 61, 3\n\t"
+	"ld		%[ret], 0(%[tmp])\n\t"
+#ifdef __BIG_ENDIAN__
+	"sld		%[ret], %[ret], %[offset]\n\t"
+#else
+	"srd		%[ret], %[ret], %[offset]\n\t"
 #endif
+#else
+	"clrrwi		%[tmp], %[addr], 2\n\t"
+	"clrlslwi	%[offset], %[addr], 30, 3\n\t"
+	"lwz		%[ret], 0(%[tmp])\n\t"
+#ifdef __BIG_ENDIAN__
+	"slw		%[ret], %[ret], %[offset]\n\t"
+#else
+	"srw		%[ret], %[ret], %[offset]\n\t"
+#endif
+#endif
+	"b	2b\n"
+	".previous\n"
+	".section __ex_table,\"a\"\n\t"
+		PPC_LONG_ALIGN "\n\t"
+		PPC_LONG "1b,3b\n"
+	".previous"
+	: [tmp] "=&b" (tmp), [offset] "=&r" (offset), [ret] "=&r" (ret)
+	: [addr] "b" (addr), "m" (*(unsigned long *)addr));
+
+	return ret;
+}
+
+#undef FIXUP_SECTION
 
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index 282d43a0c855..0d050ea37a04 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -29,6 +29,7 @@
 /* Native ICP */
 #ifdef CONFIG_PPC_ICP_NATIVE
 extern int icp_native_init(void);
+extern void icp_native_flush_interrupt(void);
 #else
 static inline int icp_native_init(void) { return -ENODEV; }
 #endif
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 670c312d914e..502cf69b6c89 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -93,6 +93,9 @@ obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o
 obj-$(CONFIG_PPC64)		+= dma-iommu.o iommu.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_MODULES)		+= ppc_ksyms.o
+ifeq ($(CONFIG_PPC32),y)
+obj-$(CONFIG_MODULES)		+= ppc_ksyms_32.o
+endif
 obj-$(CONFIG_BOOTX_TEXT)	+= btext.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 7a13f378ca2c..c78e6dac4d7d 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -13,6 +13,7 @@
 
 #include <linux/crash_dump.h>
 #include <linux/bootmem.h>
+#include <linux/io.h>
 #include <linux/memblock.h>
 #include <asm/code-patching.h>
 #include <asm/kdump.h>
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index bd1a2aba599f..735979764cd4 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -106,10 +106,14 @@ int __init swiotlb_setup_bus_notifier(void)
 	return 0;
 }
 
-void swiotlb_detect_4g(void)
+void __init swiotlb_detect_4g(void)
 {
-	if ((memblock_end_of_DRAM() - 1) > 0xffffffff)
+	if ((memblock_end_of_DRAM() - 1) > 0xffffffff) {
 		ppc_swiotlb_enable = 1;
+#ifdef CONFIG_ZONE_DMA32
+		limit_zone_pfn(ZONE_DMA32, (1ULL << 32) >> PAGE_SHIFT);
+#endif
+	}
 }
 
 static int __init swiotlb_late_init(void)
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index ee78f6e49d64..adac9dc54aee 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -15,6 +15,7 @@
 #include <asm/vio.h>
 #include <asm/bug.h>
 #include <asm/machdep.h>
+#include <asm/swiotlb.h>
 
 /*
  * Generic direct DMA implementation
@@ -25,6 +26,18 @@
  * default the offset is PCI_DRAM_OFFSET.
  */
 
+static u64 __maybe_unused get_pfn_limit(struct device *dev)
+{
+	u64 pfn = (dev->coherent_dma_mask >> PAGE_SHIFT) + 1;
+	struct dev_archdata __maybe_unused *sd = &dev->archdata;
+
+#ifdef CONFIG_SWIOTLB
+	if (sd->max_direct_dma_addr && sd->dma_ops == &swiotlb_dma_ops)
+		pfn = min_t(u64, pfn, sd->max_direct_dma_addr >> PAGE_SHIFT);
+#endif
+
+	return pfn;
+}
 
 void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 				dma_addr_t *dma_handle, gfp_t flag,
@@ -40,6 +53,26 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 #else
 	struct page *page;
 	int node = dev_to_node(dev);
+	u64 pfn = get_pfn_limit(dev);
+	int zone;
+
+	zone = dma_pfn_limit_to_zone(pfn);
+	if (zone < 0) {
+		dev_err(dev, "%s: No suitable zone for pfn %#llx\n",
+			__func__, pfn);
+		return NULL;
+	}
+
+	switch (zone) {
+	case ZONE_DMA:
+		flag |= GFP_DMA;
+		break;
+#ifdef CONFIG_ZONE_DMA32
+	case ZONE_DMA32:
+		flag |= GFP_DMA32;
+		break;
+#endif
+	};
 
 	/* ignore region specifiers */
 	flag  &= ~(__GFP_HIGHMEM);
@@ -202,6 +235,7 @@ int __dma_set_mask(struct device *dev, u64 dma_mask)
 	*dev->dma_mask = dma_mask;
 	return 0;
 }
+
 int dma_set_mask(struct device *dev, u64 dma_mask)
 {
 	if (ppc_md.dma_set_mask)
@@ -210,13 +244,10 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
 }
 EXPORT_SYMBOL(dma_set_mask);
 
-u64 dma_get_required_mask(struct device *dev)
+u64 __dma_get_required_mask(struct device *dev)
 {
 	struct dma_map_ops *dma_ops = get_dma_ops(dev);
 
-	if (ppc_md.dma_get_required_mask)
-		return ppc_md.dma_get_required_mask(dev);
-
 	if (unlikely(dma_ops == NULL))
 		return 0;
 
@@ -225,6 +256,14 @@ u64 dma_get_required_mask(struct device *dev)
 
 	return DMA_BIT_MASK(8 * sizeof(dma_addr_t));
 }
+
+u64 dma_get_required_mask(struct device *dev)
+{
+	if (ppc_md.dma_get_required_mask)
+		return ppc_md.dma_get_required_mask(dev);
+
+	return __dma_get_required_mask(dev);
+}
 EXPORT_SYMBOL_GPL(dma_get_required_mask);
 
 static int __init dma_init(void)
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 59a64f8dc85f..d543e4179c18 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -117,7 +117,7 @@ static DEFINE_MUTEX(eeh_dev_mutex);
  * not dynamically alloced, so that it ends up in RMO where RTAS
  * can access it.
  */
-#define EEH_PCI_REGS_LOG_LEN 4096
+#define EEH_PCI_REGS_LOG_LEN 8192
 static unsigned char pci_regs_buf[EEH_PCI_REGS_LOG_LEN];
 
 /*
@@ -148,16 +148,12 @@ static int __init eeh_setup(char *str)
 }
 __setup("eeh=", eeh_setup);
 
-/**
- * eeh_gather_pci_data - Copy assorted PCI config space registers to buff
- * @edev: device to report data for
- * @buf: point to buffer in which to log
- * @len: amount of room in buffer
- *
- * This routine captures assorted PCI configuration space data,
- * and puts them into a buffer for RTAS error logging.
+/*
+ * This routine captures assorted PCI configuration space data
+ * for the indicated PCI device, and puts them into a buffer
+ * for RTAS error logging.
  */
-static size_t eeh_gather_pci_data(struct eeh_dev *edev, char *buf, size_t len)
+static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 {
 	struct device_node *dn = eeh_dev_to_of_node(edev);
 	u32 cfg;
@@ -255,6 +251,19 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char *buf, size_t len)
 	return n;
 }
 
+static void *eeh_dump_pe_log(void *data, void *flag)
+{
+	struct eeh_pe *pe = data;
+	struct eeh_dev *edev, *tmp;
+	size_t *plen = flag;
+
+	eeh_pe_for_each_dev(pe, edev, tmp)
+		*plen += eeh_dump_dev_log(edev, pci_regs_buf + *plen,
+					  EEH_PCI_REGS_LOG_LEN - *plen);
+
+	return NULL;
+}
+
 /**
  * eeh_slot_error_detail - Generate combined log including driver log and error log
  * @pe: EEH PE
@@ -268,7 +277,6 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char *buf, size_t len)
 void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 {
 	size_t loglen = 0;
-	struct eeh_dev *edev, *tmp;
 
 	/*
 	 * When the PHB is fenced or dead, it's pointless to collect
@@ -286,10 +294,7 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 		eeh_pe_restore_bars(pe);
 
 		pci_regs_buf[0] = 0;
-		eeh_pe_for_each_dev(pe, edev, tmp) {
-			loglen += eeh_gather_pci_data(edev, pci_regs_buf + loglen,
-						      EEH_PCI_REGS_LOG_LEN - loglen);
-		}
+		eeh_pe_traverse(pe, eeh_dump_pe_log, &loglen);
 	}
 
 	eeh_ops->get_log(pe, severity, pci_regs_buf, loglen);
@@ -410,7 +415,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	}
 	dn = eeh_dev_to_of_node(edev);
 	dev = eeh_dev_to_pci_dev(edev);
-	pe = edev->pe;
+	pe = eeh_dev_to_pe(edev);
 
 	/* Access to IO BARs might get this far and still not want checking. */
 	if (!pe) {
@@ -542,17 +547,16 @@ EXPORT_SYMBOL_GPL(eeh_dev_check_failure);
 
 /**
  * eeh_check_failure - Check if all 1's data is due to EEH slot freeze
- * @token: I/O token, should be address in the form 0xA....
- * @val: value, should be all 1's (XXX why do we need this arg??)
+ * @token: I/O address
  *
- * Check for an EEH failure at the given token address.  Call this
+ * Check for an EEH failure at the given I/O address. Call this
  * routine if the result of a read was all 0xff's and you want to
- * find out if this is due to an EEH slot freeze event.  This routine
+ * find out if this is due to an EEH slot freeze event. This routine
  * will query firmware for the EEH status.
  *
  * Note this routine is safe to call in an interrupt context.
  */
-unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
+int eeh_check_failure(const volatile void __iomem *token)
 {
 	unsigned long addr;
 	struct eeh_dev *edev;
@@ -562,13 +566,11 @@ unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned lon
 	edev = eeh_addr_cache_get_dev(addr);
 	if (!edev) {
 		eeh_stats.no_device++;
-		return val;
+		return 0;
 	}
 
-	eeh_dev_check_failure(edev);
-	return val;
+	return eeh_dev_check_failure(edev);
 }
-
 EXPORT_SYMBOL(eeh_check_failure);
 
 
@@ -582,25 +584,51 @@ EXPORT_SYMBOL(eeh_check_failure);
  */
 int eeh_pci_enable(struct eeh_pe *pe, int function)
 {
-	int rc, flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+	int active_flag, rc;
 
 	/*
 	 * pHyp doesn't allow to enable IO or DMA on unfrozen PE.
 	 * Also, it's pointless to enable them on unfrozen PE. So
-	 * we have the check here.
+	 * we have to check before enabling IO or DMA.
 	 */
-	if (function == EEH_OPT_THAW_MMIO ||
-	    function == EEH_OPT_THAW_DMA) {
+	switch (function) {
+	case EEH_OPT_THAW_MMIO:
+		active_flag = EEH_STATE_MMIO_ACTIVE;
+		break;
+	case EEH_OPT_THAW_DMA:
+		active_flag = EEH_STATE_DMA_ACTIVE;
+		break;
+	case EEH_OPT_DISABLE:
+	case EEH_OPT_ENABLE:
+	case EEH_OPT_FREEZE_PE:
+		active_flag = 0;
+		break;
+	default:
+		pr_warn("%s: Invalid function %d\n",
+			__func__, function);
+		return -EINVAL;
+	}
+
+	/*
+	 * Check if IO or DMA has been enabled before
+	 * enabling them.
+	 */
+	if (active_flag) {
 		rc = eeh_ops->get_state(pe, NULL);
 		if (rc < 0)
 			return rc;
 
-		/* Needn't to enable or already enabled */
-		if ((rc == EEH_STATE_NOT_SUPPORT) ||
-		    ((rc & flags) == flags))
+		/* Needn't enable it at all */
+		if (rc == EEH_STATE_NOT_SUPPORT)
+			return 0;
+
+		/* It's already enabled */
+		if (rc & active_flag)
 			return 0;
 	}
 
+
+	/* Issue the request */
 	rc = eeh_ops->set_option(pe, function);
 	if (rc)
 		pr_warn("%s: Unexpected state change %d on "
@@ -608,17 +636,17 @@ int eeh_pci_enable(struct eeh_pe *pe, int function)
 			__func__, function, pe->phb->global_number,
 			pe->addr, rc);
 
-	rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-	if (rc <= 0)
-		return rc;
+	/* Check if the request is finished successfully */
+	if (active_flag) {
+		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+		if (rc <= 0)
+			return rc;
 
-	if ((function == EEH_OPT_THAW_MMIO) &&
-	    (rc & EEH_STATE_MMIO_ENABLED))
-		return 0;
+		if (rc & active_flag)
+			return 0;
 
-	if ((function == EEH_OPT_THAW_DMA) &&
-	    (rc & EEH_STATE_DMA_ENABLED))
-		return 0;
+		return -EIO;
+	}
 
 	return rc;
 }
@@ -634,7 +662,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function)
 int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
 {
 	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
-	struct eeh_pe *pe = edev->pe;
+	struct eeh_pe *pe = eeh_dev_to_pe(edev);
 
 	if (!pe) {
 		pr_err("%s: No PE found on PCI device %s\n",
@@ -645,14 +673,18 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
 	switch (state) {
 	case pcie_deassert_reset:
 		eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
+		eeh_pe_state_clear(pe, EEH_PE_RESET);
 		break;
 	case pcie_hot_reset:
+		eeh_pe_state_mark(pe, EEH_PE_RESET);
 		eeh_ops->reset(pe, EEH_RESET_HOT);
 		break;
 	case pcie_warm_reset:
+		eeh_pe_state_mark(pe, EEH_PE_RESET);
 		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
 		break;
 	default:
+		eeh_pe_state_clear(pe, EEH_PE_RESET);
 		return -EINVAL;
 	};
 
@@ -1141,6 +1173,85 @@ void eeh_remove_device(struct pci_dev *dev)
 	edev->mode &= ~EEH_DEV_SYSFS;
 }
 
+int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state)
+{
+	int ret;
+
+	ret = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+	if (ret) {
+		pr_warn("%s: Failure %d enabling IO on PHB#%x-PE#%x\n",
+			__func__, ret, pe->phb->global_number, pe->addr);
+		return ret;
+	}
+
+	ret = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
+	if (ret) {
+		pr_warn("%s: Failure %d enabling DMA on PHB#%x-PE#%x\n",
+			__func__, ret, pe->phb->global_number, pe->addr);
+		return ret;
+	}
+
+	/* Clear software isolated state */
+	if (sw_state && (pe->state & EEH_PE_ISOLATED))
+		eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
+
+	return ret;
+}
+
+
+static struct pci_device_id eeh_reset_ids[] = {
+	{ PCI_DEVICE(0x19a2, 0x0710) },	/* Emulex, BE     */
+	{ PCI_DEVICE(0x10df, 0xe220) },	/* Emulex, Lancer */
+	{ 0 }
+};
+
+static int eeh_pe_change_owner(struct eeh_pe *pe)
+{
+	struct eeh_dev *edev, *tmp;
+	struct pci_dev *pdev;
+	struct pci_device_id *id;
+	int flags, ret;
+
+	/* Check PE state */
+	flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+	ret = eeh_ops->get_state(pe, NULL);
+	if (ret < 0 || ret == EEH_STATE_NOT_SUPPORT)
+		return 0;
+
+	/* Unfrozen PE, nothing to do */
+	if ((ret & flags) == flags)
+		return 0;
+
+	/* Frozen PE, check if it needs PE level reset */
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		pdev = eeh_dev_to_pci_dev(edev);
+		if (!pdev)
+			continue;
+
+		for (id = &eeh_reset_ids[0]; id->vendor != 0; id++) {
+			if (id->vendor != PCI_ANY_ID &&
+			    id->vendor != pdev->vendor)
+				continue;
+			if (id->device != PCI_ANY_ID &&
+			    id->device != pdev->device)
+				continue;
+			if (id->subvendor != PCI_ANY_ID &&
+			    id->subvendor != pdev->subsystem_vendor)
+				continue;
+			if (id->subdevice != PCI_ANY_ID &&
+			    id->subdevice != pdev->subsystem_device)
+				continue;
+
+			goto reset;
+		}
+	}
+
+	return eeh_unfreeze_pe(pe, true);
+
+reset:
+	return eeh_pe_reset_and_recover(pe);
+}
+
 /**
  * eeh_dev_open - Increase count of pass through devices for PE
  * @pdev: PCI device
@@ -1153,6 +1264,7 @@ void eeh_remove_device(struct pci_dev *dev)
 int eeh_dev_open(struct pci_dev *pdev)
 {
 	struct eeh_dev *edev;
+	int ret = -ENODEV;
 
 	mutex_lock(&eeh_dev_mutex);
 
@@ -1165,6 +1277,16 @@ int eeh_dev_open(struct pci_dev *pdev)
 	if (!edev || !edev->pe)
 		goto out;
 
+	/*
+	 * The PE might have been put into frozen state, but we
+	 * didn't detect that yet. The passed through PCI devices
+	 * in frozen PE won't work properly. Clear the frozen state
+	 * in advance.
+	 */
+	ret = eeh_pe_change_owner(edev->pe);
+	if (ret)
+		goto out;
+
 	/* Increase PE's pass through count */
 	atomic_inc(&edev->pe->pass_dev_cnt);
 	mutex_unlock(&eeh_dev_mutex);
@@ -1172,7 +1294,7 @@ int eeh_dev_open(struct pci_dev *pdev)
 	return 0;
 out:
 	mutex_unlock(&eeh_dev_mutex);
-	return -ENODEV;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(eeh_dev_open);
 
@@ -1202,6 +1324,7 @@ void eeh_dev_release(struct pci_dev *pdev)
 	/* Decrease PE's pass through count */
 	atomic_dec(&edev->pe->pass_dev_cnt);
 	WARN_ON(atomic_read(&edev->pe->pass_dev_cnt) < 0);
+	eeh_pe_change_owner(edev->pe);
 out:
 	mutex_unlock(&eeh_dev_mutex);
 }
@@ -1281,8 +1404,10 @@ int eeh_pe_set_option(struct eeh_pe *pe, int option)
 	 */
 	switch (option) {
 	case EEH_OPT_ENABLE:
-		if (eeh_enabled())
+		if (eeh_enabled()) {
+			ret = eeh_pe_change_owner(pe);
 			break;
+		}
 		ret = -EIO;
 		break;
 	case EEH_OPT_DISABLE:
@@ -1294,7 +1419,7 @@ int eeh_pe_set_option(struct eeh_pe *pe, int option)
 			break;
 		}
 
-		ret = eeh_ops->set_option(pe, option);
+		ret = eeh_pci_enable(pe, option);
 		break;
 	default:
 		pr_debug("%s: Option %d out of range (%d, %d)\n",
@@ -1345,6 +1470,36 @@ int eeh_pe_get_state(struct eeh_pe *pe)
 }
 EXPORT_SYMBOL_GPL(eeh_pe_get_state);
 
+static int eeh_pe_reenable_devices(struct eeh_pe *pe)
+{
+	struct eeh_dev *edev, *tmp;
+	struct pci_dev *pdev;
+	int ret = 0;
+
+	/* Restore config space */
+	eeh_pe_restore_bars(pe);
+
+	/*
+	 * Reenable PCI devices as the devices passed
+	 * through are always enabled before the reset.
+	 */
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		pdev = eeh_dev_to_pci_dev(edev);
+		if (!pdev)
+			continue;
+
+		ret = pci_reenable_device(pdev);
+		if (ret) {
+			pr_warn("%s: Failure %d reenabling %s\n",
+				__func__, ret, pci_name(pdev));
+			return ret;
+		}
+	}
+
+	/* The PE is still in frozen state */
+	return eeh_unfreeze_pe(pe, true);
+}
+
 /**
  * eeh_pe_reset - Issue PE reset according to specified type
  * @pe: EEH PE
@@ -1368,23 +1523,22 @@ int eeh_pe_reset(struct eeh_pe *pe, int option)
 	switch (option) {
 	case EEH_RESET_DEACTIVATE:
 		ret = eeh_ops->reset(pe, option);
+		eeh_pe_state_clear(pe, EEH_PE_RESET);
 		if (ret)
 			break;
 
-		/*
-		 * The PE is still in frozen state and we need to clear
-		 * that. It's good to clear frozen state after deassert
-		 * to avoid messy IO access during reset, which might
-		 * cause recursive frozen PE.
-		 */
-		ret = eeh_ops->set_option(pe, EEH_OPT_THAW_MMIO);
-		if (!ret)
-			ret = eeh_ops->set_option(pe, EEH_OPT_THAW_DMA);
-		if (!ret)
-			eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
+		ret = eeh_pe_reenable_devices(pe);
 		break;
 	case EEH_RESET_HOT:
 	case EEH_RESET_FUNDAMENTAL:
+		/*
+		 * Proactively freeze the PE to drop all MMIO access
+		 * during reset, which should be banned as it's always
+		 * cause recursive EEH error.
+		 */
+		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+
+		eeh_pe_state_mark(pe, EEH_PE_RESET);
 		ret = eeh_ops->reset(pe, option);
 		break;
 	default:
@@ -1413,9 +1567,6 @@ int eeh_pe_configure(struct eeh_pe *pe)
 	if (!pe)
 		return -ENODEV;
 
-	/* Restore config space for the affected devices */
-	eeh_pe_restore_bars(pe);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(eeh_pe_configure);
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 6a0dcee8e931..3fd514f8e4b2 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -180,6 +180,22 @@ static bool eeh_dev_removed(struct eeh_dev *edev)
 	return false;
 }
 
+static void *eeh_dev_save_state(void *data, void *userdata)
+{
+	struct eeh_dev *edev = data;
+	struct pci_dev *pdev;
+
+	if (!edev)
+		return NULL;
+
+	pdev = eeh_dev_to_pci_dev(edev);
+	if (!pdev)
+		return NULL;
+
+	pci_save_state(pdev);
+	return NULL;
+}
+
 /**
  * eeh_report_error - Report pci error to each device driver
  * @data: eeh device
@@ -303,6 +319,22 @@ static void *eeh_report_reset(void *data, void *userdata)
 	return NULL;
 }
 
+static void *eeh_dev_restore_state(void *data, void *userdata)
+{
+	struct eeh_dev *edev = data;
+	struct pci_dev *pdev;
+
+	if (!edev)
+		return NULL;
+
+	pdev = eeh_dev_to_pci_dev(edev);
+	if (!pdev)
+		return NULL;
+
+	pci_restore_state(pdev);
+	return NULL;
+}
+
 /**
  * eeh_report_resume - Tell device to resume normal operations
  * @data: eeh device
@@ -450,38 +482,82 @@ static void *eeh_pe_detach_dev(void *data, void *userdata)
 static void *__eeh_clear_pe_frozen_state(void *data, void *flag)
 {
 	struct eeh_pe *pe = (struct eeh_pe *)data;
-	int i, rc;
+	bool *clear_sw_state = flag;
+	int i, rc = 1;
 
-	for (i = 0; i < 3; i++) {
-		rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
-		if (rc)
-			continue;
-		rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
-		if (!rc)
-			break;
-	}
+	for (i = 0; rc && i < 3; i++)
+		rc = eeh_unfreeze_pe(pe, clear_sw_state);
 
-	/* The PE has been isolated, clear it */
+	/* Stop immediately on any errors */
 	if (rc) {
-		pr_warn("%s: Can't clear frozen PHB#%x-PE#%x (%d)\n",
-			__func__, pe->phb->global_number, pe->addr, rc);
+		pr_warn("%s: Failure %d unfreezing PHB#%x-PE#%x\n",
+			__func__, rc, pe->phb->global_number, pe->addr);
 		return (void *)pe;
 	}
 
 	return NULL;
 }
 
-static int eeh_clear_pe_frozen_state(struct eeh_pe *pe)
+static int eeh_clear_pe_frozen_state(struct eeh_pe *pe,
+				     bool clear_sw_state)
 {
 	void *rc;
 
-	rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, NULL);
+	rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, &clear_sw_state);
 	if (!rc)
 		eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
 
 	return rc ? -EIO : 0;
 }
 
+int eeh_pe_reset_and_recover(struct eeh_pe *pe)
+{
+	int result, ret;
+
+	/* Bail if the PE is being recovered */
+	if (pe->state & EEH_PE_RECOVERING)
+		return 0;
+
+	/* Put the PE into recovery mode */
+	eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+
+	/* Save states */
+	eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL);
+
+	/* Report error */
+	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
+
+	/* Issue reset */
+	eeh_pe_state_mark(pe, EEH_PE_RESET);
+	ret = eeh_reset_pe(pe);
+	if (ret) {
+		eeh_pe_state_clear(pe, EEH_PE_RECOVERING | EEH_PE_RESET);
+		return ret;
+	}
+	eeh_pe_state_clear(pe, EEH_PE_RESET);
+
+	/* Unfreeze the PE */
+	ret = eeh_clear_pe_frozen_state(pe, true);
+	if (ret) {
+		eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+		return ret;
+	}
+
+	/* Notify completion of reset */
+	eeh_pe_dev_traverse(pe, eeh_report_reset, &result);
+
+	/* Restore device state */
+	eeh_pe_dev_traverse(pe, eeh_dev_restore_state, NULL);
+
+	/* Resume */
+	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
+
+	/* Clear recovery mode */
+	eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+
+	return 0;
+}
+
 /**
  * eeh_reset_device - Perform actual reset of a pci slot
  * @pe: EEH PE
@@ -540,7 +616,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	eeh_pe_state_clear(pe, EEH_PE_RESET);
 
 	/* Clear frozen state */
-	rc = eeh_clear_pe_frozen_state(pe);
+	rc = eeh_clear_pe_frozen_state(pe, false);
 	if (rc)
 		return rc;
 
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 00e3844525a6..53dd0915e690 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -428,7 +428,7 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
 	}
 
 	/* Remove the EEH device */
-	pe = edev->pe;
+	pe = eeh_dev_to_pe(edev);
 	edev->pe = NULL;
 	list_del(&edev->list);
 
@@ -584,6 +584,8 @@ static void *__eeh_pe_state_clear(void *data, void *flag)
 {
 	struct eeh_pe *pe = (struct eeh_pe *)data;
 	int state = *((int *)flag);
+	struct eeh_dev *edev, *tmp;
+	struct pci_dev *pdev;
 
 	/* Keep the state of permanently removed PE intact */
 	if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) &&
@@ -592,9 +594,22 @@ static void *__eeh_pe_state_clear(void *data, void *flag)
 
 	pe->state &= ~state;
 
-	/* Clear check count since last isolation */
-	if (state & EEH_PE_ISOLATED)
-		pe->check_count = 0;
+	/*
+	 * Special treatment on clearing isolated state. Clear
+	 * check count since last isolation and put all affected
+	 * devices to normal state.
+	 */
+	if (!(state & EEH_PE_ISOLATED))
+		return NULL;
+
+	pe->check_count = 0;
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		pdev = eeh_dev_to_pci_dev(edev);
+		if (!pdev)
+			continue;
+
+		pdev->error_state = pci_channel_io_normal;
+	}
 
 	return NULL;
 }
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index e2595ba4b720..f19b1e5cb060 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -54,6 +54,43 @@ EEH_SHOW_ATTR(eeh_mode,            mode,            "0x%x");
 EEH_SHOW_ATTR(eeh_config_addr,     config_addr,     "0x%x");
 EEH_SHOW_ATTR(eeh_pe_config_addr,  pe_config_addr,  "0x%x");
 
+static ssize_t eeh_pe_state_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+	int state;
+
+	if (!edev || !edev->pe)
+		return -ENODEV;
+
+	state = eeh_ops->get_state(edev->pe, NULL);
+	return sprintf(buf, "%0x08x %0x08x\n",
+		       state, edev->pe->state);
+}
+
+static ssize_t eeh_pe_state_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+
+	if (!edev || !edev->pe)
+		return -ENODEV;
+
+	/* Nothing to do if it's not frozen */
+	if (!(edev->pe->state & EEH_PE_ISOLATED))
+		return count;
+
+	if (eeh_unfreeze_pe(edev->pe, true))
+		return -EIO;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(eeh_pe_state);
+
 void eeh_sysfs_add_device(struct pci_dev *pdev)
 {
 	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
@@ -68,9 +105,10 @@ void eeh_sysfs_add_device(struct pci_dev *pdev)
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode);
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_config_addr);
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
+	rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_state);
 
 	if (rc)
-		printk(KERN_WARNING "EEH: Unable to create sysfs entries\n");
+		pr_warn("EEH: Unable to create sysfs entries\n");
 	else if (edev)
 		edev->mode |= EEH_DEV_SYSFS;
 }
@@ -92,6 +130,7 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev)
 	device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
+	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_state);
 
 	if (edev)
 		edev->mode &= ~EEH_DEV_SYSFS;
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 7ee876d2adb5..fafff8dbd5d9 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -104,12 +104,15 @@ turn_on_mmu:
  * task's thread_struct.
  */
 #define EXCEPTION_PROLOG	\
-	mtspr	SPRN_SPRG_SCRATCH0,r10;	\
-	mtspr	SPRN_SPRG_SCRATCH1,r11;	\
-	mfcr	r10;		\
+	EXCEPTION_PROLOG_0;	\
 	EXCEPTION_PROLOG_1;	\
 	EXCEPTION_PROLOG_2
 
+#define EXCEPTION_PROLOG_0	\
+	mtspr	SPRN_SPRG_SCRATCH0,r10;	\
+	mtspr	SPRN_SPRG_SCRATCH1,r11;	\
+	mfcr	r10
+
 #define EXCEPTION_PROLOG_1	\
 	mfspr	r11,SPRN_SRR1;		/* check whether user or kernel */ \
 	andi.	r11,r11,MSR_PR;	\
@@ -145,6 +148,14 @@ turn_on_mmu:
 	SAVE_2GPRS(7, r11)
 
 /*
+ * Exception exit code.
+ */
+#define EXCEPTION_EPILOG_0	\
+	mtcr	r10;		\
+	mfspr	r10,SPRN_SPRG_SCRATCH0;	\
+	mfspr	r11,SPRN_SPRG_SCRATCH1
+
+/*
  * Note: code which follows this uses cr0.eq (set if from kernel),
  * r11, r12 (SRR0), and r9 (SRR1).
  *
@@ -293,16 +304,8 @@ InstructionTLBMiss:
 #ifdef CONFIG_8xx_CPU6
 	stw	r3, 8(r0)
 #endif
-	DO_8xx_CPU6(0x3f80, r3)
-	mtspr	SPRN_M_TW, r10	/* Save a couple of working registers */
-	mfcr	r10
-#ifdef CONFIG_8xx_CPU6
-	stw	r10, 0(r0)
-	stw	r11, 4(r0)
-#else
-	mtspr	SPRN_DAR, r10
-	mtspr	SPRN_SPRG2, r11
-#endif
+	EXCEPTION_PROLOG_0
+	mtspr	SPRN_SPRG_SCRATCH2, r10
 	mfspr	r10, SPRN_SRR0	/* Get effective address of fault */
 #ifdef CONFIG_8xx_CPU15
 	addi	r11, r10, 0x1000
@@ -359,18 +362,11 @@ InstructionTLBMiss:
 	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
 
 	/* Restore registers */
-#ifndef CONFIG_8xx_CPU6
-	mfspr	r10, SPRN_DAR
-	mtcr	r10
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
-	mfspr	r11, SPRN_SPRG2
-#else
-	lwz	r11, 0(r0)
-	mtcr	r11
-	lwz	r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
 	lwz	r3, 8(r0)
 #endif
-	mfspr	r10, SPRN_M_TW
+	mfspr	r10, SPRN_SPRG_SCRATCH2
+	EXCEPTION_EPILOG_0
 	rfi
 2:
 	mfspr	r11, SPRN_SRR1
@@ -381,19 +377,11 @@ InstructionTLBMiss:
 	mtspr	SPRN_SRR1, r11
 
 	/* Restore registers */
-#ifndef CONFIG_8xx_CPU6
-	mfspr	r10, SPRN_DAR
-	mtcr	r10
-	li	r11, 0x00f0
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
-	mfspr	r11, SPRN_SPRG2
-#else
-	lwz	r11, 0(r0)
-	mtcr	r11
-	lwz	r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
 	lwz	r3, 8(r0)
 #endif
-	mfspr	r10, SPRN_M_TW
+	mfspr	r10, SPRN_SPRG_SCRATCH2
+	EXCEPTION_EPILOG_0
 	b	InstructionAccess
 
 	. = 0x1200
@@ -401,16 +389,8 @@ DataStoreTLBMiss:
 #ifdef CONFIG_8xx_CPU6
 	stw	r3, 8(r0)
 #endif
-	DO_8xx_CPU6(0x3f80, r3)
-	mtspr	SPRN_M_TW, r10	/* Save a couple of working registers */
-	mfcr	r10
-#ifdef CONFIG_8xx_CPU6
-	stw	r10, 0(r0)
-	stw	r11, 4(r0)
-#else
-	mtspr	SPRN_DAR, r10
-	mtspr	SPRN_SPRG2, r11
-#endif
+	EXCEPTION_PROLOG_0
+	mtspr	SPRN_SPRG_SCRATCH2, r10
 	mfspr	r10, SPRN_M_TWB	/* Get level 1 table entry address */
 
 	/* If we are faulting a kernel address, we have to use the
@@ -483,19 +463,12 @@ DataStoreTLBMiss:
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
 
 	/* Restore registers */
-#ifndef CONFIG_8xx_CPU6
-	mfspr	r10, SPRN_DAR
-	mtcr	r10
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
-	mfspr	r11, SPRN_SPRG2
-#else
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
-	lwz	r11, 0(r0)
-	mtcr	r11
-	lwz	r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
 	lwz	r3, 8(r0)
 #endif
-	mfspr	r10, SPRN_M_TW
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r10, SPRN_SPRG_SCRATCH2
+	EXCEPTION_EPILOG_0
 	rfi
 
 /* This is an instruction TLB error on the MPC8xx.  This could be due
@@ -507,35 +480,18 @@ InstructionTLBError:
 	b	InstructionAccess
 
 /* This is the data TLB error on the MPC8xx.  This could be due to
- * many reasons, including a dirty update to a pte.  We can catch that
- * one here, but anything else is an error.  First, we track down the
- * Linux pte.  If it is valid, write access is allowed, but the
- * page dirty bit is not set, we will set it and reload the TLB.  For
- * any other case, we bail out to a higher level function that can
- * handle it.
+ * many reasons, including a dirty update to a pte.  We bail out to
+ * a higher level function that can handle it.
  */
 	. = 0x1400
 DataTLBError:
-#ifdef CONFIG_8xx_CPU6
-	stw	r3, 8(r0)
-#endif
-	DO_8xx_CPU6(0x3f80, r3)
-	mtspr	SPRN_M_TW, r10	/* Save a couple of working registers */
-	mfcr	r10
-	stw	r10, 0(r0)
-	stw	r11, 4(r0)
+	EXCEPTION_PROLOG_0
 
-	mfspr	r10, SPRN_DAR
-	cmpwi	cr0, r10, 0x00f0
+	mfspr	r11, SPRN_DAR
+	cmpwi	cr0, r11, 0x00f0
 	beq-	FixupDAR	/* must be a buggy dcbX, icbi insn. */
-DARFixed:/* Return from dcbx instruction bug workaround, r10 holds value of DAR */
-	mfspr	r10, SPRN_M_TW	/* Restore registers */
-	lwz	r11, 0(r0)
-	mtcr	r11
-	lwz	r11, 4(r0)
-#ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)
-#endif
+DARFixed:/* Return from dcbx instruction bug workaround */
+	EXCEPTION_EPILOG_0
 	b	DataAccess
 
 	EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE)
@@ -559,11 +515,15 @@ DARFixed:/* Return from dcbx instruction bug workaround, r10 holds value of DAR
 
 /* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions
  * by decoding the registers used by the dcbx instruction and adding them.
- * DAR is set to the calculated address and r10 also holds the EA on exit.
+ * DAR is set to the calculated address.
  */
  /* define if you don't want to use self modifying code */
 #define NO_SELF_MODIFYING_CODE
 FixupDAR:/* Entry point for dcbx workaround. */
+#ifdef CONFIG_8xx_CPU6
+	stw	r3, 8(r0)
+#endif
+	mtspr	SPRN_SPRG_SCRATCH2, r10
 	/* fetch instruction from memory. */
 	mfspr	r10, SPRN_SRR0
 	andis.	r11, r10, 0x8000	/* Address >= 0x80000000 */
@@ -579,16 +539,17 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
 	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
 	lwz	r11, 0(r11)	/* Get the pte */
+#ifdef CONFIG_8xx_CPU6
+	lwz	r3, 8(r0)	/* restore r3 from memory */
+#endif
 	/* concat physical page address(r11) and page offset(r10) */
 	rlwimi	r11, r10, 0, 20, 31
 	lwz	r11,0(r11)
 /* Check if it really is a dcbx instruction. */
 /* dcbt and dcbtst does not generate DTLB Misses/Errors,
  * no need to include them here */
-	srwi	r10, r11, 26	/* check if major OP code is 31 */
-	cmpwi	cr0, r10, 31
-	bne-	141f
-	rlwinm	r10, r11, 0, 21, 30
+	xoris	r10, r11, 0x7c00	/* check if major OP code is 31 */
+	rlwinm	r10, r10, 0, 21, 5
 	cmpwi	cr0, r10, 2028	/* Is dcbz? */
 	beq+	142f
 	cmpwi	cr0, r10, 940	/* Is dcbi? */
@@ -599,16 +560,13 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	beq+	142f
 	cmpwi	cr0, r10, 1964	/* Is icbi? */
 	beq+	142f
-141:	mfspr	r10, SPRN_DAR	/* r10 must hold DAR at exit */
+141:	mfspr	r10,SPRN_SPRG_SCRATCH2
 	b	DARFixed	/* Nope, go back to normal TLB processing */
 
 144:	mfspr	r10, SPRN_DSISR
 	rlwinm	r10, r10,0,7,5	/* Clear store bit for buggy dcbst insn */
 	mtspr	SPRN_DSISR, r10
 142:	/* continue, it was a dcbx, dcbi instruction. */
-#ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)	/* restore r3 from memory */
-#endif
 #ifndef NO_SELF_MODIFYING_CODE
 	andis.	r10,r11,0x1f	/* test if reg RA is r0 */
 	li	r10,modified_instr@l
@@ -619,14 +577,15 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	stw	r11,0(r10)	/* store add/and instruction */
 	dcbf	0,r10		/* flush new instr. to memory. */
 	icbi	0,r10		/* invalidate instr. cache line */
-	lwz	r11, 4(r0)	/* restore r11 from memory */
-	mfspr	r10, SPRN_M_TW	/* restore r10 from M_TW */
+	mfspr	r11, SPRN_SPRG_SCRATCH1	/* restore r11 */
+	mfspr	r10, SPRN_SPRG_SCRATCH0	/* restore r10 */
 	isync			/* Wait until new instr is loaded from memory */
 modified_instr:
 	.space	4		/* this is where the add instr. is stored */
 	bne+	143f
 	subf	r10,r0,r10	/* r10=r10-r0, only if reg RA is r0 */
 143:	mtdar	r10		/* store faulting EA in DAR */
+	mfspr	r10,SPRN_SPRG_SCRATCH2
 	b	DARFixed	/* Go back to normal TLB handling */
 #else
 	mfctr	r10
@@ -680,13 +639,16 @@ modified_instr:
 	mfdar	r11
 	mtctr	r11			/* restore ctr reg from DAR */
 	mtdar	r10			/* save fault EA to DAR */
+	mfspr	r10,SPRN_SPRG_SCRATCH2
 	b	DARFixed		/* Go back to normal TLB handling */
 
 	/* special handling for r10,r11 since these are modified already */
-153:	lwz	r11, 4(r0)	/* load r11 from memory */
-	b	155f
-154:	mfspr	r11, SPRN_M_TW	/* load r10 from M_TW */
-155:	add	r10, r10, r11	/* add it */
+153:	mfspr	r11, SPRN_SPRG_SCRATCH1	/* load r11 from SPRN_SPRG_SCRATCH1 */
+	add	r10, r10, r11	/* add it */
+	mfctr	r11		/* restore r11 */
+	b	151b
+154:	mfspr	r11, SPRN_SPRG_SCRATCH0	/* load r10 from SPRN_SPRG_SCRATCH0 */
+	add	r10, r10, r11	/* add it */
 	mfctr	r11		/* restore r11 */
 	b	151b
 #endif
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 0bb5918faaaf..1f7d84e2e8b2 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -293,7 +293,7 @@ out:
 /*
  * Handle single-step exceptions following a DABR hit.
  */
-int __kprobes single_step_dabr_instruction(struct die_args *args)
+static int __kprobes single_step_dabr_instruction(struct die_args *args)
 {
 	struct pt_regs *regs = args->regs;
 	struct perf_event *bp = NULL;
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 1114d13ac19f..ac86c53e2542 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -55,7 +55,7 @@ static struct device ibmebus_bus_device = { /* fake "parent" device */
 struct bus_type ibmebus_bus_type;
 
 /* These devices will automatically be added to the bus during init */
-static struct of_device_id __initdata ibmebus_matches[] = {
+static const struct of_device_id ibmebus_matches[] __initconst = {
 	{ .compatible = "IBM,lhca" },
 	{ .compatible = "IBM,lhea" },
 	{},
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index be05841396cf..c0754bbf8118 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -73,7 +73,7 @@ _GLOBAL(power7_powersave_common)
 
 	/* Check if something happened while soft-disabled */
 	lbz	r0,PACAIRQHAPPENED(r13)
-	cmpwi	cr0,r0,0
+	andi.	r0,r0,~PACA_IRQ_HARD_DIS@l
 	beq	1f
 	cmpwi	cr0,r4,0
 	beq	1f
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 4c5891de162e..8eb857f216c1 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -444,13 +444,13 @@ void migrate_irqs(void)
 
 		cpumask_and(mask, data->affinity, map);
 		if (cpumask_any(mask) >= nr_cpu_ids) {
-			printk("Breaking affinity for irq %i\n", irq);
+			pr_warn("Breaking affinity for irq %i\n", irq);
 			cpumask_copy(mask, map);
 		}
 		if (chip->irq_set_affinity)
 			chip->irq_set_affinity(data, mask, true);
 		else if (desc->action && !(warned++))
-			printk("Cannot set affinity for irq %i\n", irq);
+			pr_err("Cannot set affinity for irq %i\n", irq);
 	}
 
 	free_cpumask_var(mask);
@@ -470,7 +470,7 @@ static inline void check_stack_overflow(void)
 
 	/* check for stack overflow: is there less than 2KB free? */
 	if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
-		printk("do_IRQ: stack overflow: %ld\n",
+		pr_err("do_IRQ: stack overflow: %ld\n",
 			sp - sizeof(struct thread_info));
 		dump_stack();
 	}
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 936258881c98..7b750c4ed5c7 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -35,7 +35,7 @@ static struct legacy_serial_info {
 	phys_addr_t			taddr;
 } legacy_serial_infos[MAX_LEGACY_SERIAL_PORTS];
 
-static struct of_device_id legacy_serial_parents[] __initdata = {
+static const struct of_device_id legacy_serial_parents[] __initconst = {
 	{.type = "soc",},
 	{.type = "tsi-bridge",},
 	{.type = "opb", },
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 6cff040bf456..c94d2e018d84 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -15,6 +15,9 @@
     along with this program; if not, write to the Free Software
     Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleloader.h>
 #include <linux/elf.h>
@@ -28,12 +31,6 @@
 #include <linux/sort.h>
 #include <asm/setup.h>
 
-#if 0
-#define DEBUGP printk
-#else
-#define DEBUGP(fmt , ...)
-#endif
-
 /* Count how many different relocations (different symbol, different
    addend) */
 static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num)
@@ -121,8 +118,8 @@ static unsigned long get_plt_size(const Elf32_Ehdr *hdr,
 			continue;
 
 		if (sechdrs[i].sh_type == SHT_RELA) {
-			DEBUGP("Found relocations in section %u\n", i);
-			DEBUGP("Ptr: %p.  Number: %u\n",
+			pr_debug("Found relocations in section %u\n", i);
+			pr_debug("Ptr: %p.  Number: %u\n",
 			       (void *)hdr + sechdrs[i].sh_offset,
 			       sechdrs[i].sh_size / sizeof(Elf32_Rela));
 
@@ -161,7 +158,7 @@ int module_frob_arch_sections(Elf32_Ehdr *hdr,
 			me->arch.core_plt_section = i;
 	}
 	if (!me->arch.core_plt_section || !me->arch.init_plt_section) {
-		printk("Module doesn't contain .plt or .init.plt sections.\n");
+		pr_err("Module doesn't contain .plt or .init.plt sections.\n");
 		return -ENOEXEC;
 	}
 
@@ -189,7 +186,7 @@ static uint32_t do_plt_call(void *location,
 {
 	struct ppc_plt_entry *entry;
 
-	DEBUGP("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location);
+	pr_debug("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location);
 	/* Init, or core PLT? */
 	if (location >= mod->module_core
 	    && location < mod->module_core + mod->core_size)
@@ -208,7 +205,7 @@ static uint32_t do_plt_call(void *location,
 	entry->jump[2] = 0x7d8903a6;                    /* mtctr r12 */
 	entry->jump[3] = 0x4e800420;			/* bctr */
 
-	DEBUGP("Initialized plt for 0x%x at %p\n", val, entry);
+	pr_debug("Initialized plt for 0x%x at %p\n", val, entry);
 	return (uint32_t)entry;
 }
 
@@ -224,7 +221,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 	uint32_t *location;
 	uint32_t value;
 
-	DEBUGP("Applying ADD relocate section %u to %u\n", relsec,
+	pr_debug("Applying ADD relocate section %u to %u\n", relsec,
 	       sechdrs[relsec].sh_info);
 	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
 		/* This is where to make the change */
@@ -268,17 +265,17 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 						    sechdrs, module);
 
 			/* Only replace bits 2 through 26 */
-			DEBUGP("REL24 value = %08X. location = %08X\n",
+			pr_debug("REL24 value = %08X. location = %08X\n",
 			       value, (uint32_t)location);
-			DEBUGP("Location before: %08X.\n",
+			pr_debug("Location before: %08X.\n",
 			       *(uint32_t *)location);
 			*(uint32_t *)location
 				= (*(uint32_t *)location & ~0x03fffffc)
 				| ((value - (uint32_t)location)
 				   & 0x03fffffc);
-			DEBUGP("Location after: %08X.\n",
+			pr_debug("Location after: %08X.\n",
 			       *(uint32_t *)location);
-			DEBUGP("ie. jump to %08X+%08X = %08X\n",
+			pr_debug("ie. jump to %08X+%08X = %08X\n",
 			       *(uint32_t *)location & 0x03fffffc,
 			       (uint32_t)location,
 			       (*(uint32_t *)location & 0x03fffffc)
@@ -291,7 +288,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			break;
 
 		default:
-			printk("%s: unknown ADD relocation: %u\n",
+			pr_err("%s: unknown ADD relocation: %u\n",
 			       module->name,
 			       ELF32_R_TYPE(rela[i].r_info));
 			return -ENOEXEC;
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index d807ee626af9..68384514506b 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -15,6 +15,9 @@
     along with this program; if not, write to the Free Software
     Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/elf.h>
 #include <linux/moduleloader.h>
@@ -36,11 +39,6 @@
    Using a magic allocator which places modules within 32MB solves
    this, and makes other things simpler.  Anton?
    --RR.  */
-#if 0
-#define DEBUGP printk
-#else
-#define DEBUGP(fmt , ...)
-#endif
 
 #if defined(_CALL_ELF) && _CALL_ELF == 2
 #define R2_STACK_OFFSET 24
@@ -279,8 +277,8 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 	/* Every relocated section... */
 	for (i = 1; i < hdr->e_shnum; i++) {
 		if (sechdrs[i].sh_type == SHT_RELA) {
-			DEBUGP("Found relocations in section %u\n", i);
-			DEBUGP("Ptr: %p.  Number: %lu\n",
+			pr_debug("Found relocations in section %u\n", i);
+			pr_debug("Ptr: %p.  Number: %Lu\n",
 			       (void *)sechdrs[i].sh_addr,
 			       sechdrs[i].sh_size / sizeof(Elf64_Rela));
 
@@ -304,7 +302,7 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 	relocs++;
 #endif
 
-	DEBUGP("Looks like a total of %lu stubs, max\n", relocs);
+	pr_debug("Looks like a total of %lu stubs, max\n", relocs);
 	return relocs * sizeof(struct ppc64_stub_entry);
 }
 
@@ -390,7 +388,7 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
 	}
 
 	if (!me->arch.stubs_section) {
-		printk("%s: doesn't contain .stubs.\n", me->name);
+		pr_err("%s: doesn't contain .stubs.\n", me->name);
 		return -ENOEXEC;
 	}
 
@@ -434,11 +432,11 @@ static inline int create_stub(Elf64_Shdr *sechdrs,
 	/* Stub uses address relative to r2. */
 	reladdr = (unsigned long)entry - my_r2(sechdrs, me);
 	if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
-		printk("%s: Address %p of stub out of range of %p.\n",
+		pr_err("%s: Address %p of stub out of range of %p.\n",
 		       me->name, (void *)reladdr, (void *)my_r2);
 		return 0;
 	}
-	DEBUGP("Stub %p get data from reladdr %li\n", entry, reladdr);
+	pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr);
 
 	entry->jump[0] |= PPC_HA(reladdr);
 	entry->jump[1] |= PPC_LO(reladdr);
@@ -477,7 +475,7 @@ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
 static int restore_r2(u32 *instruction, struct module *me)
 {
 	if (*instruction != PPC_INST_NOP) {
-		printk("%s: Expect noop after relocate, got %08x\n",
+		pr_err("%s: Expect noop after relocate, got %08x\n",
 		       me->name, *instruction);
 		return 0;
 	}
@@ -498,7 +496,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 	unsigned long *location;
 	unsigned long value;
 
-	DEBUGP("Applying ADD relocate section %u to %u\n", relsec,
+	pr_debug("Applying ADD relocate section %u to %u\n", relsec,
 	       sechdrs[relsec].sh_info);
 
 	/* First time we're called, we can fix up .TOC. */
@@ -519,7 +517,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
 			+ ELF64_R_SYM(rela[i].r_info);
 
-		DEBUGP("RELOC at %p: %li-type as %s (%lu) + %li\n",
+		pr_debug("RELOC at %p: %li-type as %s (0x%lx) + %li\n",
 		       location, (long)ELF64_R_TYPE(rela[i].r_info),
 		       strtab + sym->st_name, (unsigned long)sym->st_value,
 		       (long)rela[i].r_addend);
@@ -546,7 +544,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			/* Subtract TOC pointer */
 			value -= my_r2(sechdrs, me);
 			if (value + 0x8000 > 0xffff) {
-				printk("%s: bad TOC16 relocation (%lu)\n",
+				pr_err("%s: bad TOC16 relocation (0x%lx)\n",
 				       me->name, value);
 				return -ENOEXEC;
 			}
@@ -567,7 +565,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			/* Subtract TOC pointer */
 			value -= my_r2(sechdrs, me);
 			if ((value & 3) != 0 || value + 0x8000 > 0xffff) {
-				printk("%s: bad TOC16_DS relocation (%lu)\n",
+				pr_err("%s: bad TOC16_DS relocation (0x%lx)\n",
 				       me->name, value);
 				return -ENOEXEC;
 			}
@@ -580,7 +578,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			/* Subtract TOC pointer */
 			value -= my_r2(sechdrs, me);
 			if ((value & 3) != 0) {
-				printk("%s: bad TOC16_LO_DS relocation (%lu)\n",
+				pr_err("%s: bad TOC16_LO_DS relocation (0x%lx)\n",
 				       me->name, value);
 				return -ENOEXEC;
 			}
@@ -613,7 +611,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			/* Convert value to relative */
 			value -= (unsigned long)location;
 			if (value + 0x2000000 > 0x3ffffff || (value & 3) != 0){
-				printk("%s: REL24 %li out of range!\n",
+				pr_err("%s: REL24 %li out of range!\n",
 				       me->name, (long int)value);
 				return -ENOEXEC;
 			}
@@ -655,7 +653,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			break;
 
 		default:
-			printk("%s: Unknown ADD relocation: %lu\n",
+			pr_err("%s: Unknown ADD relocation: %lu\n",
 			       me->name,
 			       (unsigned long)ELF64_R_TYPE(rela[i].r_info));
 			return -ENOEXEC;
diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c
index 8bbc12d20f5c..71bd161640cf 100644
--- a/arch/powerpc/kernel/msi.c
+++ b/arch/powerpc/kernel/msi.c
@@ -13,7 +13,7 @@
 
 #include <asm/machdep.h>
 
-int arch_msi_check_device(struct pci_dev* dev, int nvec, int type)
+int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
 	if (!ppc_md.setup_msi_irqs || !ppc_md.teardown_msi_irqs) {
 		pr_debug("msi: Platform doesn't provide MSI callbacks.\n");
@@ -24,16 +24,6 @@ int arch_msi_check_device(struct pci_dev* dev, int nvec, int type)
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
 		return 1;
 
-	if (ppc_md.msi_check_device) {
-		pr_debug("msi: Using platform check routine.\n");
-		return ppc_md.msi_check_device(dev, nvec, type);
-	}
-
-        return 0;
-}
-
-int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
 	return ppc_md.setup_msi_irqs(dev, nvec, type);
 }
 
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 28b898e68185..34f7c9b7cd96 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -567,7 +567,7 @@ static int __init nvram_init(void)
   	return rc;
 }
 
-void __exit nvram_cleanup(void)
+static void __exit nvram_cleanup(void)
 {
         misc_deregister( &nvram_dev );
 }
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index a7b743076720..f87bc1b4bdda 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -97,7 +97,7 @@ static int of_pci_phb_probe(struct platform_device *dev)
 	return 0;
 }
 
-static struct of_device_id of_pci_phb_ids[] = {
+static const struct of_device_id of_pci_phb_ids[] = {
 	{ .type = "pci", },
 	{ .type = "pcix", },
 	{ .type = "pcie", },
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index b2814e23e1ed..e5dad9a9edc0 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -747,7 +747,11 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 			break;
 		}
 		if (res != NULL) {
-			of_pci_range_to_resource(&range, dev, res);
+			res->name = dev->full_name;
+			res->flags = range.flags;
+			res->start = range.cpu_addr;
+			res->end = range.cpu_addr + range.size - 1;
+			res->parent = res->child = res->sibling = NULL;
 		}
 	}
 }
@@ -1140,7 +1144,7 @@ static int reparent_resources(struct resource *parent,
  *	    as well.
  */
 
-void pcibios_allocate_bus_resources(struct pci_bus *bus)
+static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 {
 	struct pci_bus *b;
 	int i;
@@ -1561,7 +1565,6 @@ EARLY_PCI_OP(write, byte, u8)
 EARLY_PCI_OP(write, word, u16)
 EARLY_PCI_OP(write, dword, u32)
 
-extern int pci_bus_find_capability (struct pci_bus *bus, unsigned int devfn, int cap);
 int early_find_capability(struct pci_controller *hose, int bus, int devfn,
 			  int cap)
 {
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 44562aa97f16..e6245e9c7d8d 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -38,7 +38,7 @@ static u32 get_int_prop(struct device_node *np, const char *name, u32 def)
  * @addr0: value of 1st cell of a device tree PCI address.
  * @bridge: Set this flag if the address is from a bridge 'ranges' property
  */
-unsigned int pci_parse_of_flags(u32 addr0, int bridge)
+static unsigned int pci_parse_of_flags(u32 addr0, int bridge)
 {
 	unsigned int flags = 0;
 
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 48d17d6fca5b..c4dfff6c2719 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -1,207 +1,41 @@
-#include <linux/export.h>
-#include <linux/threads.h>
-#include <linux/smp.h>
-#include <linux/sched.h>
-#include <linux/elfcore.h>
-#include <linux/string.h>
-#include <linux/interrupt.h>
-#include <linux/screen_info.h>
-#include <linux/vt_kern.h>
-#include <linux/nvram.h>
-#include <linux/irq.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
+#include <linux/ftrace.h>
+#include <linux/mm.h>
 
-#include <asm/page.h>
 #include <asm/processor.h>
-#include <asm/cacheflush.h>
-#include <asm/uaccess.h>
-#include <asm/io.h>
-#include <linux/atomic.h>
-#include <asm/checksum.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-#include <linux/adb.h>
-#include <linux/cuda.h>
-#include <linux/pmu.h>
-#include <asm/prom.h>
-#include <asm/pci-bridge.h>
-#include <asm/irq.h>
-#include <asm/pmac_feature.h>
-#include <asm/dma.h>
-#include <asm/machdep.h>
-#include <asm/hw_irq.h>
-#include <asm/nvram.h>
-#include <asm/mmu_context.h>
-#include <asm/backlight.h>
-#include <asm/time.h>
-#include <asm/cputable.h>
-#include <asm/btext.h>
-#include <asm/div64.h>
-#include <asm/signal.h>
-#include <asm/dcr.h>
-#include <asm/ftrace.h>
 #include <asm/switch_to.h>
+#include <asm/cacheflush.h>
 #include <asm/epapr_hcalls.h>
 
-#ifdef CONFIG_PPC32
-extern void transfer_to_handler(void);
-extern void do_IRQ(struct pt_regs *regs);
-extern void machine_check_exception(struct pt_regs *regs);
-extern void alignment_exception(struct pt_regs *regs);
-extern void program_check_exception(struct pt_regs *regs);
-extern void single_step_exception(struct pt_regs *regs);
-extern int sys_sigreturn(struct pt_regs *regs);
+EXPORT_SYMBOL(flush_dcache_range);
+EXPORT_SYMBOL(flush_icache_range);
 
-EXPORT_SYMBOL(clear_pages);
-EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
-EXPORT_SYMBOL(DMA_MODE_READ);
-EXPORT_SYMBOL(DMA_MODE_WRITE);
+EXPORT_SYMBOL(empty_zero_page);
 
-EXPORT_SYMBOL(transfer_to_handler);
-EXPORT_SYMBOL(do_IRQ);
-EXPORT_SYMBOL(machine_check_exception);
-EXPORT_SYMBOL(alignment_exception);
-EXPORT_SYMBOL(program_check_exception);
-EXPORT_SYMBOL(single_step_exception);
-EXPORT_SYMBOL(sys_sigreturn);
-#endif
+long long __bswapdi2(long long);
+EXPORT_SYMBOL(__bswapdi2);
 
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
 #endif
 
-EXPORT_SYMBOL(strcpy);
-EXPORT_SYMBOL(strncpy);
-EXPORT_SYMBOL(strcat);
-EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strcmp);
-EXPORT_SYMBOL(strncmp);
-
-#ifndef CONFIG_GENERIC_CSUM
-EXPORT_SYMBOL(csum_partial);
-EXPORT_SYMBOL(csum_partial_copy_generic);
-EXPORT_SYMBOL(ip_fast_csum);
-EXPORT_SYMBOL(csum_tcpudp_magic);
-#endif
-
-EXPORT_SYMBOL(__copy_tofrom_user);
-EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(copy_page);
-
-#if defined(CONFIG_PCI) && defined(CONFIG_PPC32)
-EXPORT_SYMBOL(isa_io_base);
-EXPORT_SYMBOL(isa_mem_base);
-EXPORT_SYMBOL(pci_dram_offset);
-#endif /* CONFIG_PCI */
-
-EXPORT_SYMBOL(start_thread);
-
 #ifdef CONFIG_PPC_FPU
 EXPORT_SYMBOL(giveup_fpu);
 EXPORT_SYMBOL(load_fp_state);
 EXPORT_SYMBOL(store_fp_state);
 #endif
+
 #ifdef CONFIG_ALTIVEC
 EXPORT_SYMBOL(giveup_altivec);
 EXPORT_SYMBOL(load_vr_state);
 EXPORT_SYMBOL(store_vr_state);
-#endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_VSX
-EXPORT_SYMBOL(giveup_vsx);
-EXPORT_SYMBOL_GPL(__giveup_vsx);
-#endif /* CONFIG_VSX */
-#ifdef CONFIG_SPE
-EXPORT_SYMBOL(giveup_spe);
-#endif /* CONFIG_SPE */
-
-#ifndef CONFIG_PPC64
-EXPORT_SYMBOL(flush_instruction_cache);
 #endif
-EXPORT_SYMBOL(flush_dcache_range);
-EXPORT_SYMBOL(flush_icache_range);
 
-#ifdef CONFIG_SMP
-#ifdef CONFIG_PPC32
-EXPORT_SYMBOL(smp_hw_index);
-#endif
-#endif
-
-#ifdef CONFIG_ADB
-EXPORT_SYMBOL(adb_request);
-EXPORT_SYMBOL(adb_register);
-EXPORT_SYMBOL(adb_unregister);
-EXPORT_SYMBOL(adb_poll);
-EXPORT_SYMBOL(adb_try_handler_change);
-#endif /* CONFIG_ADB */
-#ifdef CONFIG_ADB_CUDA
-EXPORT_SYMBOL(cuda_request);
-EXPORT_SYMBOL(cuda_poll);
-#endif /* CONFIG_ADB_CUDA */
-EXPORT_SYMBOL(to_tm);
-
-#ifdef CONFIG_PPC32
-long long __ashrdi3(long long, int);
-long long __ashldi3(long long, int);
-long long __lshrdi3(long long, int);
-EXPORT_SYMBOL(__ashrdi3);
-EXPORT_SYMBOL(__ashldi3);
-EXPORT_SYMBOL(__lshrdi3);
-int __ucmpdi2(unsigned long long, unsigned long long);
-EXPORT_SYMBOL(__ucmpdi2);
-int __cmpdi2(long long, long long);
-EXPORT_SYMBOL(__cmpdi2);
-#endif
-long long __bswapdi2(long long);
-EXPORT_SYMBOL(__bswapdi2);
-EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(memcmp);
-EXPORT_SYMBOL(memchr);
-
-#if defined(CONFIG_FB_VGA16_MODULE)
-EXPORT_SYMBOL(screen_info);
-#endif
-
-#ifdef CONFIG_PPC32
-EXPORT_SYMBOL(timer_interrupt);
-EXPORT_SYMBOL(tb_ticks_per_jiffy);
-EXPORT_SYMBOL(cacheable_memcpy);
-EXPORT_SYMBOL(cacheable_memzero);
-#endif
-
-#ifdef CONFIG_PPC32
-EXPORT_SYMBOL(switch_mmu_context);
-#endif
-
-#ifdef CONFIG_PPC_STD_MMU_32
-extern long mol_trampoline;
-EXPORT_SYMBOL(mol_trampoline); /* For MOL */
-EXPORT_SYMBOL(flush_hash_pages); /* For MOL */
-#ifdef CONFIG_SMP
-extern int mmu_hash_lock;
-EXPORT_SYMBOL(mmu_hash_lock); /* For MOL */
-#endif /* CONFIG_SMP */
-extern long *intercept_table;
-EXPORT_SYMBOL(intercept_table);
-#endif /* CONFIG_PPC_STD_MMU_32 */
-#ifdef CONFIG_PPC_DCR_NATIVE
-EXPORT_SYMBOL(__mtdcr);
-EXPORT_SYMBOL(__mfdcr);
-#endif
-EXPORT_SYMBOL(empty_zero_page);
-
-#ifdef CONFIG_PPC64
-EXPORT_SYMBOL(__arch_hweight8);
-EXPORT_SYMBOL(__arch_hweight16);
-EXPORT_SYMBOL(__arch_hweight32);
-EXPORT_SYMBOL(__arch_hweight64);
+#ifdef CONFIG_VSX
+EXPORT_SYMBOL_GPL(__giveup_vsx);
 #endif
 
-#ifdef CONFIG_PPC_BOOK3S_64
-EXPORT_SYMBOL_GPL(mmu_psize_defs);
+#ifdef CONFIG_SPE
+EXPORT_SYMBOL(giveup_spe);
 #endif
 
 #ifdef CONFIG_EPAPR_PARAVIRT
diff --git a/arch/powerpc/kernel/ppc_ksyms_32.c b/arch/powerpc/kernel/ppc_ksyms_32.c
new file mode 100644
index 000000000000..30ddd8a24eee
--- /dev/null
+++ b/arch/powerpc/kernel/ppc_ksyms_32.c
@@ -0,0 +1,61 @@
+#include <linux/export.h>
+#include <linux/smp.h>
+
+#include <asm/page.h>
+#include <asm/dma.h>
+#include <asm/io.h>
+#include <asm/hw_irq.h>
+#include <asm/time.h>
+#include <asm/mmu_context.h>
+#include <asm/pgtable.h>
+#include <asm/dcr.h>
+
+EXPORT_SYMBOL(clear_pages);
+EXPORT_SYMBOL(ISA_DMA_THRESHOLD);
+EXPORT_SYMBOL(DMA_MODE_READ);
+EXPORT_SYMBOL(DMA_MODE_WRITE);
+
+#if defined(CONFIG_PCI)
+EXPORT_SYMBOL(isa_io_base);
+EXPORT_SYMBOL(isa_mem_base);
+EXPORT_SYMBOL(pci_dram_offset);
+#endif
+
+#ifdef CONFIG_SMP
+EXPORT_SYMBOL(smp_hw_index);
+#endif
+
+long long __ashrdi3(long long, int);
+long long __ashldi3(long long, int);
+long long __lshrdi3(long long, int);
+int __ucmpdi2(unsigned long long, unsigned long long);
+int __cmpdi2(long long, long long);
+EXPORT_SYMBOL(__ashrdi3);
+EXPORT_SYMBOL(__ashldi3);
+EXPORT_SYMBOL(__lshrdi3);
+EXPORT_SYMBOL(__ucmpdi2);
+EXPORT_SYMBOL(__cmpdi2);
+
+EXPORT_SYMBOL(timer_interrupt);
+EXPORT_SYMBOL(tb_ticks_per_jiffy);
+
+EXPORT_SYMBOL(switch_mmu_context);
+
+#ifdef CONFIG_PPC_STD_MMU_32
+extern long mol_trampoline;
+EXPORT_SYMBOL(mol_trampoline); /* For MOL */
+EXPORT_SYMBOL(flush_hash_pages); /* For MOL */
+#ifdef CONFIG_SMP
+extern int mmu_hash_lock;
+EXPORT_SYMBOL(mmu_hash_lock); /* For MOL */
+#endif /* CONFIG_SMP */
+extern long *intercept_table;
+EXPORT_SYMBOL(intercept_table);
+#endif /* CONFIG_PPC_STD_MMU_32 */
+
+#ifdef CONFIG_PPC_DCR_NATIVE
+EXPORT_SYMBOL(__mtdcr);
+EXPORT_SYMBOL(__mfdcr);
+#endif
+
+EXPORT_SYMBOL(flush_instruction_cache);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index bf44ae962ab8..aa1df89c8b2a 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -228,6 +228,7 @@ void giveup_vsx(struct task_struct *tsk)
 	giveup_altivec_maybe_transactional(tsk);
 	__giveup_vsx(tsk);
 }
+EXPORT_SYMBOL(giveup_vsx);
 
 void flush_vsx_to_thread(struct task_struct *tsk)
 {
@@ -1316,6 +1317,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.tm_tfiar = 0;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 }
+EXPORT_SYMBOL(start_thread);
 
 #define PR_FP_ALL_EXCEPT (PR_FP_EXC_DIV | PR_FP_EXC_OVF | PR_FP_EXC_UND \
 		| PR_FP_EXC_RES | PR_FP_EXC_INV)
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 4e139f8a69ef..099f27e6d1b0 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -386,8 +386,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 	return 0;
 }
 
-int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname,
-					 int depth, void *data)
+static int __init early_init_dt_scan_chosen_ppc(unsigned long node,
+						const char *uname,
+						int depth, void *data)
 {
 	const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */
 
@@ -641,6 +642,10 @@ void __init early_init_devtree(void *params)
 
 	DBG(" -> early_init_devtree(%p)\n", params);
 
+	/* Too early to BUG_ON(), do it by hand */
+	if (!early_init_dt_verify(params))
+		panic("BUG: Failed verifying flat device tree, bad version?");
+
 	/* Setup flat device-tree pointer */
 	initial_boot_params = params;
 
@@ -663,14 +668,12 @@ void __init early_init_devtree(void *params)
 	 * device-tree, including the platform type, initrd location and
 	 * size, TCE reserve, and more ...
 	 */
-	of_scan_flat_dt(early_init_dt_scan_chosen_ppc, cmd_line);
+	of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line);
 
 	/* Scan memory nodes and rebuild MEMBLOCKs */
 	of_scan_flat_dt(early_init_dt_scan_root, NULL);
 	of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);
 
-	/* Save command line for /proc/cmdline and then parse parameters */
-	strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE);
 	parse_early_param();
 
 	/* make sure we've parsed cmdline for mem= before this */
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index fe8e54b9ef7d..12640f7e726b 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -50,24 +50,14 @@ do
 	done
 
 	# ignore register save/restore funcitons
-	if [ "${UNDEF:0:9}" = "_restgpr_" ]; then
+	case $UNDEF in
+	_restgpr_*|_restgpr0_*|_rest32gpr_*)
 		OK=1
-	fi
-	if [ "${UNDEF:0:10}" = "_restgpr0_" ]; then
-		OK=1
-	fi
-	if [ "${UNDEF:0:11}" = "_rest32gpr_" ]; then
-		OK=1
-	fi
-	if [ "${UNDEF:0:9}" = "_savegpr_" ]; then
+		;;
+	_savegpr_*|_savegpr0_*|_save32gpr_*)
 		OK=1
-	fi
-	if [ "${UNDEF:0:10}" = "_savegpr0_" ]; then
-		OK=1
-	fi
-	if [ "${UNDEF:0:11}" = "_save32gpr_" ]; then
-		OK=1
-	fi
+		;;
+	esac
 
 	if [ $OK -eq 0 ]; then
 		ERROR=1
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 2e3d2bf536c5..cdb404ea3468 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -932,7 +932,7 @@ void ptrace_triggered(struct perf_event *bp,
 }
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 
-int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
+static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 			       unsigned long data)
 {
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index e736387fee6a..5a2c049c1c61 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -286,7 +286,7 @@ static void prrn_work_fn(struct work_struct *work)
 
 static DECLARE_WORK(prrn_work, prrn_work_fn);
 
-void prrn_schedule_update(u32 scope)
+static void prrn_schedule_update(u32 scope)
 {
 	flush_work(&prrn_work);
 	prrn_update_scope = scope;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 1b0e26013a62..1362cd62b3fa 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -81,8 +81,6 @@ EXPORT_SYMBOL_GPL(boot_cpuid);
 
 unsigned long klimit = (unsigned long) _end;
 
-char cmd_line[COMMAND_LINE_SIZE];
-
 /*
  * This still seems to be needed... -- paulus
  */ 
@@ -94,6 +92,9 @@ struct screen_info screen_info = {
 	.orig_video_isVGA = 1,
 	.orig_video_points = 16
 };
+#if defined(CONFIG_FB_VGA16_MODULE)
+EXPORT_SYMBOL(screen_info);
+#endif
 
 /* Variables required to store legacy IO irq routing */
 int of_i8042_kbd_irq;
@@ -382,7 +383,7 @@ void __init check_for_initrd(void)
 		initrd_start = initrd_end = 0;
 
 	if (initrd_start)
-		printk("Found initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end);
+		pr_info("Found initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end);
 
 	DBG(" <- check_for_initrd()\n");
 #endif /* CONFIG_BLK_DEV_INITRD */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index ea4fda60e57b..07831ed0d9ef 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -268,7 +268,7 @@ static void __init exc_lvl_early_init(void)
 /* Warning, IO base is not yet inited */
 void __init setup_arch(char **cmdline_p)
 {
-	*cmdline_p = cmd_line;
+	*cmdline_p = boot_command_line;
 
 	/* so udelay does something sensible, assume <= 1000 bogomips */
 	loops_per_jiffy = 500000000 / HZ;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 75d62d63fe68..cd07d79ad21c 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -525,21 +525,31 @@ void __init setup_system(void)
 	printk("Starting Linux PPC64 %s\n", init_utsname()->version);
 
 	printk("-----------------------------------------------------\n");
-	printk("ppc64_pft_size                = 0x%llx\n", ppc64_pft_size);
-	printk("physicalMemorySize            = 0x%llx\n", memblock_phys_mem_size());
+	printk("ppc64_pft_size    = 0x%llx\n", ppc64_pft_size);
+	printk("phys_mem_size     = 0x%llx\n", memblock_phys_mem_size());
+
 	if (ppc64_caches.dline_size != 0x80)
-		printk("ppc64_caches.dcache_line_size = 0x%x\n",
-		       ppc64_caches.dline_size);
+		printk("dcache_line_size  = 0x%x\n", ppc64_caches.dline_size);
 	if (ppc64_caches.iline_size != 0x80)
-		printk("ppc64_caches.icache_line_size = 0x%x\n",
-		       ppc64_caches.iline_size);
+		printk("icache_line_size  = 0x%x\n", ppc64_caches.iline_size);
+
+	printk("cpu_features      = 0x%016lx\n", cur_cpu_spec->cpu_features);
+	printk("  possible        = 0x%016lx\n", CPU_FTRS_POSSIBLE);
+	printk("  always          = 0x%016lx\n", CPU_FTRS_ALWAYS);
+	printk("cpu_user_features = 0x%08x 0x%08x\n", cur_cpu_spec->cpu_user_features,
+		cur_cpu_spec->cpu_user_features2);
+	printk("mmu_features      = 0x%08x\n", cur_cpu_spec->mmu_features);
+	printk("firmware_features = 0x%016lx\n", powerpc_firmware_features);
+
 #ifdef CONFIG_PPC_STD_MMU_64
 	if (htab_address)
-		printk("htab_address                  = 0x%p\n", htab_address);
-	printk("htab_hash_mask                = 0x%lx\n", htab_hash_mask);
-#endif /* CONFIG_PPC_STD_MMU_64 */
+		printk("htab_address      = 0x%p\n", htab_address);
+
+	printk("htab_hash_mask    = 0x%lx\n", htab_hash_mask);
+#endif
+
 	if (PHYSICAL_START > 0)
-		printk("physical_start                = 0x%llx\n",
+		printk("physical_start    = 0x%llx\n",
 		       (unsigned long long)PHYSICAL_START);
 	printk("-----------------------------------------------------\n");
 
@@ -657,7 +667,7 @@ void __init setup_arch(char **cmdline_p)
 {
 	ppc64_boot_msg(0x12, "Setup Arch");
 
-	*cmdline_p = cmd_line;
+	*cmdline_p = boot_command_line;
 
 	/*
 	 * Set cache line size based on type of cpu as a default.
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index a0738af4aba6..71e186d5f331 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -52,6 +52,7 @@
 #endif
 #include <asm/vdso.h>
 #include <asm/debug.h>
+#include <asm/kexec.h>
 
 #ifdef DEBUG
 #include <asm/udbg.h>
@@ -379,8 +380,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		/*
 		 * numa_node_id() works after this.
 		 */
-		set_cpu_numa_node(cpu, numa_cpu_lookup_table[cpu]);
-		set_cpu_numa_mem(cpu, local_memory_node(numa_cpu_lookup_table[cpu]));
+		if (cpu_present(cpu)) {
+			set_cpu_numa_node(cpu, numa_cpu_lookup_table[cpu]);
+			set_cpu_numa_mem(cpu,
+				local_memory_node(numa_cpu_lookup_table[cpu]));
+		}
 	}
 
 	cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid));
@@ -728,6 +732,9 @@ void start_secondary(void *unused)
 	}
 	traverse_core_siblings(cpu, true);
 
+	set_numa_node(numa_cpu_lookup_table[cpu]);
+	set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu]));
+
 	smp_wmb();
 	notify_cpu_starting(cpu);
 	set_cpu_online(cpu, true);
diff --git a/arch/powerpc/kernel/suspend.c b/arch/powerpc/kernel/suspend.c
index 0167d53da30c..a531154cc0f3 100644
--- a/arch/powerpc/kernel/suspend.c
+++ b/arch/powerpc/kernel/suspend.c
@@ -9,9 +9,7 @@
 
 #include <linux/mm.h>
 #include <asm/page.h>
-
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
+#include <asm/sections.h>
 
 /*
  *	pfn_is_nosave - check if given pfn is in the 'nosave' section
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 368ab374d33c..7505599c2593 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -479,7 +479,7 @@ void arch_irq_work_raise(void)
 
 #endif /* CONFIG_IRQ_WORK */
 
-void __timer_interrupt(void)
+static void __timer_interrupt(void)
 {
 	struct pt_regs *regs = get_irq_regs();
 	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
@@ -643,7 +643,7 @@ static int __init get_freq(char *name, int cells, unsigned long *val)
 	return found;
 }
 
-void start_cpu_decrementer(void)
+static void start_cpu_decrementer(void)
 {
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
 	/* Clear any pending timer interrupts */
@@ -1024,6 +1024,7 @@ void to_tm(int tim, struct rtc_time * tm)
 	 */
 	GregorianDay(tm);
 }
+EXPORT_SYMBOL(to_tm);
 
 /*
  * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 59fa2de9546d..9f342f134ae4 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -10,7 +10,7 @@ CFLAGS_REMOVE_code-patching.o = -pg
 CFLAGS_REMOVE_feature-fixups.o = -pg
 
 obj-y			:= string.o alloc.o \
-			   crtsavres.o
+			   crtsavres.o ppc_ksyms.o
 obj-$(CONFIG_PPC32)	+= div64.o copy_32.o
 obj-$(CONFIG_HAS_IOMEM)	+= devres.o
 
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 7a8a7487cee8..7ce3870d7ddd 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -164,7 +164,7 @@ static long calc_offset(struct fixup_entry *entry, unsigned int *p)
 	return (unsigned long)p - (unsigned long)entry;
 }
 
-void test_basic_patching(void)
+static void test_basic_patching(void)
 {
 	extern unsigned int ftr_fixup_test1;
 	extern unsigned int end_ftr_fixup_test1;
diff --git a/arch/powerpc/lib/ppc_ksyms.c b/arch/powerpc/lib/ppc_ksyms.c
new file mode 100644
index 000000000000..f993959647b5
--- /dev/null
+++ b/arch/powerpc/lib/ppc_ksyms.c
@@ -0,0 +1,39 @@
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/bitops.h>
+#include <net/checksum.h>
+
+EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memmove);
+EXPORT_SYMBOL(memcmp);
+EXPORT_SYMBOL(memchr);
+#ifdef CONFIG_PPC32
+EXPORT_SYMBOL(cacheable_memcpy);
+EXPORT_SYMBOL(cacheable_memzero);
+#endif
+
+EXPORT_SYMBOL(strcpy);
+EXPORT_SYMBOL(strncpy);
+EXPORT_SYMBOL(strcat);
+EXPORT_SYMBOL(strlen);
+EXPORT_SYMBOL(strcmp);
+EXPORT_SYMBOL(strncmp);
+
+#ifndef CONFIG_GENERIC_CSUM
+EXPORT_SYMBOL(csum_partial);
+EXPORT_SYMBOL(csum_partial_copy_generic);
+EXPORT_SYMBOL(ip_fast_csum);
+EXPORT_SYMBOL(csum_tcpudp_magic);
+#endif
+
+EXPORT_SYMBOL(__copy_tofrom_user);
+EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(copy_page);
+
+#ifdef CONFIG_PPC64
+EXPORT_SYMBOL(__arch_hweight8);
+EXPORT_SYMBOL(__arch_hweight16);
+EXPORT_SYMBOL(__arch_hweight32);
+EXPORT_SYMBOL(__arch_hweight64);
+#endif
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 5c09f365c842..54651fc2d412 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -98,13 +98,8 @@ static unsigned long __kprobes dform_ea(unsigned int instr, struct pt_regs *regs
 
 	ra = (instr >> 16) & 0x1f;
 	ea = (signed short) instr;		/* sign-extend */
-	if (ra) {
+	if (ra)
 		ea += regs->gpr[ra];
-		if (instr & 0x04000000) {		/* update forms */
-			if ((instr>>26) != 47) 		/* stmw is not an update form */
-				regs->gpr[ra] = ea;
-		}
-	}
 
 	return truncate_if_32bit(regs->msr, ea);
 }
@@ -120,11 +115,8 @@ static unsigned long __kprobes dsform_ea(unsigned int instr, struct pt_regs *reg
 
 	ra = (instr >> 16) & 0x1f;
 	ea = (signed short) (instr & ~3);	/* sign-extend */
-	if (ra) {
+	if (ra)
 		ea += regs->gpr[ra];
-		if ((instr & 3) == 1)		/* update forms */
-			regs->gpr[ra] = ea;
-	}
 
 	return truncate_if_32bit(regs->msr, ea);
 }
@@ -133,8 +125,8 @@ static unsigned long __kprobes dsform_ea(unsigned int instr, struct pt_regs *reg
 /*
  * Calculate effective address for an X-form instruction
  */
-static unsigned long __kprobes xform_ea(unsigned int instr, struct pt_regs *regs,
-				     int do_update)
+static unsigned long __kprobes xform_ea(unsigned int instr,
+					struct pt_regs *regs)
 {
 	int ra, rb;
 	unsigned long ea;
@@ -142,11 +134,8 @@ static unsigned long __kprobes xform_ea(unsigned int instr, struct pt_regs *regs
 	ra = (instr >> 16) & 0x1f;
 	rb = (instr >> 11) & 0x1f;
 	ea = regs->gpr[rb];
-	if (ra) {
+	if (ra)
 		ea += regs->gpr[ra];
-		if (do_update)		/* update forms */
-			regs->gpr[ra] = ea;
-	}
 
 	return truncate_if_32bit(regs->msr, ea);
 }
@@ -611,6 +600,23 @@ static void __kprobes do_cmp_unsigned(struct pt_regs *regs, unsigned long v1,
 	regs->ccr = (regs->ccr & ~(0xf << shift)) | (crval << shift);
 }
 
+static int __kprobes trap_compare(long v1, long v2)
+{
+	int ret = 0;
+
+	if (v1 < v2)
+		ret |= 0x10;
+	else if (v1 > v2)
+		ret |= 0x08;
+	else
+		ret |= 0x04;
+	if ((unsigned long)v1 < (unsigned long)v2)
+		ret |= 0x02;
+	else if ((unsigned long)v1 > (unsigned long)v2)
+		ret |= 0x01;
+	return ret;
+}
+
 /*
  * Elements of 32-bit rotate and mask instructions.
  */
@@ -627,26 +633,27 @@ static void __kprobes do_cmp_unsigned(struct pt_regs *regs, unsigned long v1,
 #define ROTATE(x, n)	((n) ? (((x) << (n)) | ((x) >> (8 * sizeof(long) - (n)))) : (x))
 
 /*
- * Emulate instructions that cause a transfer of control,
- * loads and stores, and a few other instructions.
- * Returns 1 if the step was emulated, 0 if not,
- * or -1 if the instruction is one that should not be stepped,
- * such as an rfid, or a mtmsrd that would clear MSR_RI.
+ * Decode an instruction, and execute it if that can be done just by
+ * modifying *regs (i.e. integer arithmetic and logical instructions,
+ * branches, and barrier instructions).
+ * Returns 1 if the instruction has been executed, or 0 if not.
+ * Sets *op to indicate what the instruction does.
  */
-int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
+int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs,
+			    unsigned int instr)
 {
 	unsigned int opcode, ra, rb, rd, spr, u;
 	unsigned long int imm;
 	unsigned long int val, val2;
-	unsigned long int ea;
-	unsigned int cr, mb, me, sh;
-	int err;
-	unsigned long old_ra, val3;
+	unsigned int mb, me, sh;
 	long ival;
 
+	op->type = COMPUTE;
+
 	opcode = instr >> 26;
 	switch (opcode) {
 	case 16:	/* bc */
+		op->type = BRANCH;
 		imm = (signed short)(instr & 0xfffc);
 		if ((instr & 2) == 0)
 			imm += regs->nip;
@@ -659,26 +666,14 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		return 1;
 #ifdef CONFIG_PPC64
 	case 17:	/* sc */
-		/*
-		 * N.B. this uses knowledge about how the syscall
-		 * entry code works.  If that is changed, this will
-		 * need to be changed also.
-		 */
-		if (regs->gpr[0] == 0x1ebe &&
-		    cpu_has_feature(CPU_FTR_REAL_LE)) {
-			regs->msr ^= MSR_LE;
-			goto instr_done;
-		}
-		regs->gpr[9] = regs->gpr[13];
-		regs->gpr[10] = MSR_KERNEL;
-		regs->gpr[11] = regs->nip + 4;
-		regs->gpr[12] = regs->msr & MSR_MASK;
-		regs->gpr[13] = (unsigned long) get_paca();
-		regs->nip = (unsigned long) &system_call_common;
-		regs->msr = MSR_KERNEL;
-		return 1;
+		if ((instr & 0xfe2) == 2)
+			op->type = SYSCALL;
+		else
+			op->type = UNKNOWN;
+		return 0;
 #endif
 	case 18:	/* b */
+		op->type = BRANCH;
 		imm = instr & 0x03fffffc;
 		if (imm & 0x02000000)
 			imm -= 0x04000000;
@@ -691,8 +686,16 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		return 1;
 	case 19:
 		switch ((instr >> 1) & 0x3ff) {
+		case 0:		/* mcrf */
+			rd = (instr >> 21) & 0x1c;
+			ra = (instr >> 16) & 0x1c;
+			val = (regs->ccr >> ra) & 0xf;
+			regs->ccr = (regs->ccr & ~(0xfUL << rd)) | (val << rd);
+			goto instr_done;
+
 		case 16:	/* bclr */
 		case 528:	/* bcctr */
+			op->type = BRANCH;
 			imm = (instr & 0x400)? regs->ctr: regs->link;
 			regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4);
 			imm = truncate_if_32bit(regs->msr, imm);
@@ -703,9 +706,13 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			return 1;
 
 		case 18:	/* rfid, scary */
-			return -1;
+			if (regs->msr & MSR_PR)
+				goto priv;
+			op->type = RFI;
+			return 0;
 
 		case 150:	/* isync */
+			op->type = BARRIER;
 			isync();
 			goto instr_done;
 
@@ -731,6 +738,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 	case 31:
 		switch ((instr >> 1) & 0x3ff) {
 		case 598:	/* sync */
+			op->type = BARRIER;
 #ifdef __powerpc64__
 			switch ((instr >> 21) & 3) {
 			case 1:		/* lwsync */
@@ -745,6 +753,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			goto instr_done;
 
 		case 854:	/* eieio */
+			op->type = BARRIER;
 			eieio();
 			goto instr_done;
 		}
@@ -760,6 +769,17 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 	rb = (instr >> 11) & 0x1f;
 
 	switch (opcode) {
+#ifdef __powerpc64__
+	case 2:		/* tdi */
+		if (rd & trap_compare(regs->gpr[ra], (short) instr))
+			goto trap;
+		goto instr_done;
+#endif
+	case 3:		/* twi */
+		if (rd & trap_compare((int)regs->gpr[ra], (short) instr))
+			goto trap;
+		goto instr_done;
+
 	case 7:		/* mulli */
 		regs->gpr[rd] = regs->gpr[ra] * (short) instr;
 		goto instr_done;
@@ -908,35 +928,44 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 	case 31:
 		switch ((instr >> 1) & 0x3ff) {
+		case 4:		/* tw */
+			if (rd == 0x1f ||
+			    (rd & trap_compare((int)regs->gpr[ra],
+					       (int)regs->gpr[rb])))
+				goto trap;
+			goto instr_done;
+#ifdef __powerpc64__
+		case 68:	/* td */
+			if (rd & trap_compare(regs->gpr[ra], regs->gpr[rb]))
+				goto trap;
+			goto instr_done;
+#endif
 		case 83:	/* mfmsr */
 			if (regs->msr & MSR_PR)
-				break;
-			regs->gpr[rd] = regs->msr & MSR_MASK;
-			goto instr_done;
+				goto priv;
+			op->type = MFMSR;
+			op->reg = rd;
+			return 0;
 		case 146:	/* mtmsr */
 			if (regs->msr & MSR_PR)
-				break;
-			imm = regs->gpr[rd];
-			if ((imm & MSR_RI) == 0)
-				/* can't step mtmsr that would clear MSR_RI */
-				return -1;
-			regs->msr = imm;
-			goto instr_done;
+				goto priv;
+			op->type = MTMSR;
+			op->reg = rd;
+			op->val = 0xffffffff & ~(MSR_ME | MSR_LE);
+			return 0;
 #ifdef CONFIG_PPC64
 		case 178:	/* mtmsrd */
-			/* only MSR_EE and MSR_RI get changed if bit 15 set */
-			/* mtmsrd doesn't change MSR_HV and MSR_ME */
 			if (regs->msr & MSR_PR)
-				break;
-			imm = (instr & 0x10000)? 0x8002: 0xefffffffffffefffUL;
-			imm = (regs->msr & MSR_MASK & ~imm)
-				| (regs->gpr[rd] & imm);
-			if ((imm & MSR_RI) == 0)
-				/* can't step mtmsrd that would clear MSR_RI */
-				return -1;
-			regs->msr = imm;
-			goto instr_done;
+				goto priv;
+			op->type = MTMSR;
+			op->reg = rd;
+			/* only MSR_EE and MSR_RI get changed if bit 15 set */
+			/* mtmsrd doesn't change MSR_HV, MSR_ME or MSR_LE */
+			imm = (instr & 0x10000)? 0x8002: 0xefffffffffffeffeUL;
+			op->val = imm;
+			return 0;
 #endif
+
 		case 19:	/* mfcr */
 			regs->gpr[rd] = regs->ccr;
 			regs->gpr[rd] &= 0xffffffffUL;
@@ -954,33 +983,43 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			goto instr_done;
 
 		case 339:	/* mfspr */
-			spr = (instr >> 11) & 0x3ff;
+			spr = ((instr >> 16) & 0x1f) | ((instr >> 6) & 0x3e0);
 			switch (spr) {
-			case 0x20:	/* mfxer */
+			case SPRN_XER:	/* mfxer */
 				regs->gpr[rd] = regs->xer;
 				regs->gpr[rd] &= 0xffffffffUL;
 				goto instr_done;
-			case 0x100:	/* mflr */
+			case SPRN_LR:	/* mflr */
 				regs->gpr[rd] = regs->link;
 				goto instr_done;
-			case 0x120:	/* mfctr */
+			case SPRN_CTR:	/* mfctr */
 				regs->gpr[rd] = regs->ctr;
 				goto instr_done;
+			default:
+				op->type = MFSPR;
+				op->reg = rd;
+				op->spr = spr;
+				return 0;
 			}
 			break;
 
 		case 467:	/* mtspr */
-			spr = (instr >> 11) & 0x3ff;
+			spr = ((instr >> 16) & 0x1f) | ((instr >> 6) & 0x3e0);
 			switch (spr) {
-			case 0x20:	/* mtxer */
+			case SPRN_XER:	/* mtxer */
 				regs->xer = (regs->gpr[rd] & 0xffffffffUL);
 				goto instr_done;
-			case 0x100:	/* mtlr */
+			case SPRN_LR:	/* mtlr */
 				regs->link = regs->gpr[rd];
 				goto instr_done;
-			case 0x120:	/* mtctr */
+			case SPRN_CTR:	/* mtctr */
 				regs->ctr = regs->gpr[rd];
 				goto instr_done;
+			default:
+				op->type = MTSPR;
+				op->val = regs->gpr[rd];
+				op->spr = spr;
+				return 0;
 			}
 			break;
 
@@ -1257,294 +1296,242 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
  * Cache instructions
  */
 		case 54:	/* dcbst */
-			ea = xform_ea(instr, regs, 0);
-			if (!address_ok(regs, ea, 8))
-				return 0;
-			err = 0;
-			__cacheop_user_asmx(ea, err, "dcbst");
-			if (err)
-				return 0;
-			goto instr_done;
+			op->type = MKOP(CACHEOP, DCBST, 0);
+			op->ea = xform_ea(instr, regs);
+			return 0;
 
 		case 86:	/* dcbf */
-			ea = xform_ea(instr, regs, 0);
-			if (!address_ok(regs, ea, 8))
-				return 0;
-			err = 0;
-			__cacheop_user_asmx(ea, err, "dcbf");
-			if (err)
-				return 0;
-			goto instr_done;
+			op->type = MKOP(CACHEOP, DCBF, 0);
+			op->ea = xform_ea(instr, regs);
+			return 0;
 
 		case 246:	/* dcbtst */
-			if (rd == 0) {
-				ea = xform_ea(instr, regs, 0);
-				prefetchw((void *) ea);
-			}
-			goto instr_done;
+			op->type = MKOP(CACHEOP, DCBTST, 0);
+			op->ea = xform_ea(instr, regs);
+			op->reg = rd;
+			return 0;
 
 		case 278:	/* dcbt */
-			if (rd == 0) {
-				ea = xform_ea(instr, regs, 0);
-				prefetch((void *) ea);
-			}
-			goto instr_done;
+			op->type = MKOP(CACHEOP, DCBTST, 0);
+			op->ea = xform_ea(instr, regs);
+			op->reg = rd;
+			return 0;
 
+		case 982:	/* icbi */
+			op->type = MKOP(CACHEOP, ICBI, 0);
+			op->ea = xform_ea(instr, regs);
+			return 0;
 		}
 		break;
 	}
 
 	/*
-	 * Following cases are for loads and stores, so bail out
-	 * if we're in little-endian mode.
+	 * Loads and stores.
 	 */
-	if (regs->msr & MSR_LE)
-		return 0;
-
-	/*
-	 * Save register RA in case it's an update form load or store
-	 * and the access faults.
-	 */
-	old_ra = regs->gpr[ra];
+	op->type = UNKNOWN;
+	op->update_reg = ra;
+	op->reg = rd;
+	op->val = regs->gpr[rd];
+	u = (instr >> 20) & UPDATE;
 
 	switch (opcode) {
 	case 31:
-		u = instr & 0x40;
+		u = instr & UPDATE;
+		op->ea = xform_ea(instr, regs);
 		switch ((instr >> 1) & 0x3ff) {
 		case 20:	/* lwarx */
-			ea = xform_ea(instr, regs, 0);
-			if (ea & 3)
-				break;		/* can't handle misaligned */
-			err = -EFAULT;
-			if (!address_ok(regs, ea, 4))
-				goto ldst_done;
-			err = 0;
-			__get_user_asmx(val, ea, err, "lwarx");
-			if (!err)
-				regs->gpr[rd] = val;
-			goto ldst_done;
+			op->type = MKOP(LARX, 0, 4);
+			break;
 
 		case 150:	/* stwcx. */
-			ea = xform_ea(instr, regs, 0);
-			if (ea & 3)
-				break;		/* can't handle misaligned */
-			err = -EFAULT;
-			if (!address_ok(regs, ea, 4))
-				goto ldst_done;
-			err = 0;
-			__put_user_asmx(regs->gpr[rd], ea, err, "stwcx.", cr);
-			if (!err)
-				regs->ccr = (regs->ccr & 0x0fffffff) |
-					(cr & 0xe0000000) |
-					((regs->xer >> 3) & 0x10000000);
-			goto ldst_done;
+			op->type = MKOP(STCX, 0, 4);
+			break;
 
 #ifdef __powerpc64__
 		case 84:	/* ldarx */
-			ea = xform_ea(instr, regs, 0);
-			if (ea & 7)
-				break;		/* can't handle misaligned */
-			err = -EFAULT;
-			if (!address_ok(regs, ea, 8))
-				goto ldst_done;
-			err = 0;
-			__get_user_asmx(val, ea, err, "ldarx");
-			if (!err)
-				regs->gpr[rd] = val;
-			goto ldst_done;
+			op->type = MKOP(LARX, 0, 8);
+			break;
 
 		case 214:	/* stdcx. */
-			ea = xform_ea(instr, regs, 0);
-			if (ea & 7)
-				break;		/* can't handle misaligned */
-			err = -EFAULT;
-			if (!address_ok(regs, ea, 8))
-				goto ldst_done;
-			err = 0;
-			__put_user_asmx(regs->gpr[rd], ea, err, "stdcx.", cr);
-			if (!err)
-				regs->ccr = (regs->ccr & 0x0fffffff) |
-					(cr & 0xe0000000) |
-					((regs->xer >> 3) & 0x10000000);
-			goto ldst_done;
+			op->type = MKOP(STCX, 0, 8);
+			break;
 
 		case 21:	/* ldx */
 		case 53:	/* ldux */
-			err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
-				       8, regs);
-			goto ldst_done;
+			op->type = MKOP(LOAD, u, 8);
+			break;
 #endif
 
 		case 23:	/* lwzx */
 		case 55:	/* lwzux */
-			err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
-				       4, regs);
-			goto ldst_done;
+			op->type = MKOP(LOAD, u, 4);
+			break;
 
 		case 87:	/* lbzx */
 		case 119:	/* lbzux */
-			err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
-				       1, regs);
-			goto ldst_done;
+			op->type = MKOP(LOAD, u, 1);
+			break;
 
 #ifdef CONFIG_ALTIVEC
 		case 103:	/* lvx */
 		case 359:	/* lvxl */
 			if (!(regs->msr & MSR_VEC))
-				break;
-			ea = xform_ea(instr, regs, 0);
-			err = do_vec_load(rd, do_lvx, ea, regs);
-			goto ldst_done;
+				goto vecunavail;
+			op->type = MKOP(LOAD_VMX, 0, 16);
+			break;
 
 		case 231:	/* stvx */
 		case 487:	/* stvxl */
 			if (!(regs->msr & MSR_VEC))
-				break;
-			ea = xform_ea(instr, regs, 0);
-			err = do_vec_store(rd, do_stvx, ea, regs);
-			goto ldst_done;
+				goto vecunavail;
+			op->type = MKOP(STORE_VMX, 0, 16);
+			break;
 #endif /* CONFIG_ALTIVEC */
 
 #ifdef __powerpc64__
 		case 149:	/* stdx */
 		case 181:	/* stdux */
-			val = regs->gpr[rd];
-			err = write_mem(val, xform_ea(instr, regs, u), 8, regs);
-			goto ldst_done;
+			op->type = MKOP(STORE, u, 8);
+			break;
 #endif
 
 		case 151:	/* stwx */
 		case 183:	/* stwux */
-			val = regs->gpr[rd];
-			err = write_mem(val, xform_ea(instr, regs, u), 4, regs);
-			goto ldst_done;
+			op->type = MKOP(STORE, u, 4);
+			break;
 
 		case 215:	/* stbx */
 		case 247:	/* stbux */
-			val = regs->gpr[rd];
-			err = write_mem(val, xform_ea(instr, regs, u), 1, regs);
-			goto ldst_done;
+			op->type = MKOP(STORE, u, 1);
+			break;
 
 		case 279:	/* lhzx */
 		case 311:	/* lhzux */
-			err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
-				       2, regs);
-			goto ldst_done;
+			op->type = MKOP(LOAD, u, 2);
+			break;
 
 #ifdef __powerpc64__
 		case 341:	/* lwax */
 		case 373:	/* lwaux */
-			err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
-				       4, regs);
-			if (!err)
-				regs->gpr[rd] = (signed int) regs->gpr[rd];
-			goto ldst_done;
+			op->type = MKOP(LOAD, SIGNEXT | u, 4);
+			break;
 #endif
 
 		case 343:	/* lhax */
 		case 375:	/* lhaux */
-			err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
-				       2, regs);
-			if (!err)
-				regs->gpr[rd] = (signed short) regs->gpr[rd];
-			goto ldst_done;
+			op->type = MKOP(LOAD, SIGNEXT | u, 2);
+			break;
 
 		case 407:	/* sthx */
 		case 439:	/* sthux */
-			val = regs->gpr[rd];
-			err = write_mem(val, xform_ea(instr, regs, u), 2, regs);
-			goto ldst_done;
+			op->type = MKOP(STORE, u, 2);
+			break;
 
 #ifdef __powerpc64__
 		case 532:	/* ldbrx */
-			err = read_mem(&val, xform_ea(instr, regs, 0), 8, regs);
-			if (!err)
-				regs->gpr[rd] = byterev_8(val);
-			goto ldst_done;
+			op->type = MKOP(LOAD, BYTEREV, 8);
+			break;
 
 #endif
+		case 533:	/* lswx */
+			op->type = MKOP(LOAD_MULTI, 0, regs->xer & 0x7f);
+			break;
 
 		case 534:	/* lwbrx */
-			err = read_mem(&val, xform_ea(instr, regs, 0), 4, regs);
-			if (!err)
-				regs->gpr[rd] = byterev_4(val);
-			goto ldst_done;
+			op->type = MKOP(LOAD, BYTEREV, 4);
+			break;
+
+		case 597:	/* lswi */
+			if (rb == 0)
+				rb = 32;	/* # bytes to load */
+			op->type = MKOP(LOAD_MULTI, 0, rb);
+			op->ea = 0;
+			if (ra)
+				op->ea = truncate_if_32bit(regs->msr,
+							   regs->gpr[ra]);
+			break;
 
 #ifdef CONFIG_PPC_FPU
 		case 535:	/* lfsx */
 		case 567:	/* lfsux */
 			if (!(regs->msr & MSR_FP))
-				break;
-			ea = xform_ea(instr, regs, u);
-			err = do_fp_load(rd, do_lfs, ea, 4, regs);
-			goto ldst_done;
+				goto fpunavail;
+			op->type = MKOP(LOAD_FP, u, 4);
+			break;
 
 		case 599:	/* lfdx */
 		case 631:	/* lfdux */
 			if (!(regs->msr & MSR_FP))
-				break;
-			ea = xform_ea(instr, regs, u);
-			err = do_fp_load(rd, do_lfd, ea, 8, regs);
-			goto ldst_done;
+				goto fpunavail;
+			op->type = MKOP(LOAD_FP, u, 8);
+			break;
 
 		case 663:	/* stfsx */
 		case 695:	/* stfsux */
 			if (!(regs->msr & MSR_FP))
-				break;
-			ea = xform_ea(instr, regs, u);
-			err = do_fp_store(rd, do_stfs, ea, 4, regs);
-			goto ldst_done;
+				goto fpunavail;
+			op->type = MKOP(STORE_FP, u, 4);
+			break;
 
 		case 727:	/* stfdx */
 		case 759:	/* stfdux */
 			if (!(regs->msr & MSR_FP))
-				break;
-			ea = xform_ea(instr, regs, u);
-			err = do_fp_store(rd, do_stfd, ea, 8, regs);
-			goto ldst_done;
+				goto fpunavail;
+			op->type = MKOP(STORE_FP, u, 8);
+			break;
 #endif
 
 #ifdef __powerpc64__
 		case 660:	/* stdbrx */
-			val = byterev_8(regs->gpr[rd]);
-			err = write_mem(val, xform_ea(instr, regs, 0), 8, regs);
-			goto ldst_done;
+			op->type = MKOP(STORE, BYTEREV, 8);
+			op->val = byterev_8(regs->gpr[rd]);
+			break;
 
 #endif
+		case 661:	/* stswx */
+			op->type = MKOP(STORE_MULTI, 0, regs->xer & 0x7f);
+			break;
+
 		case 662:	/* stwbrx */
-			val = byterev_4(regs->gpr[rd]);
-			err = write_mem(val, xform_ea(instr, regs, 0), 4, regs);
-			goto ldst_done;
+			op->type = MKOP(STORE, BYTEREV, 4);
+			op->val = byterev_4(regs->gpr[rd]);
+			break;
+
+		case 725:
+			if (rb == 0)
+				rb = 32;	/* # bytes to store */
+			op->type = MKOP(STORE_MULTI, 0, rb);
+			op->ea = 0;
+			if (ra)
+				op->ea = truncate_if_32bit(regs->msr,
+							   regs->gpr[ra]);
+			break;
 
 		case 790:	/* lhbrx */
-			err = read_mem(&val, xform_ea(instr, regs, 0), 2, regs);
-			if (!err)
-				regs->gpr[rd] = byterev_2(val);
-			goto ldst_done;
+			op->type = MKOP(LOAD, BYTEREV, 2);
+			break;
 
 		case 918:	/* sthbrx */
-			val = byterev_2(regs->gpr[rd]);
-			err = write_mem(val, xform_ea(instr, regs, 0), 2, regs);
-			goto ldst_done;
+			op->type = MKOP(STORE, BYTEREV, 2);
+			op->val = byterev_2(regs->gpr[rd]);
+			break;
 
 #ifdef CONFIG_VSX
 		case 844:	/* lxvd2x */
 		case 876:	/* lxvd2ux */
 			if (!(regs->msr & MSR_VSX))
-				break;
-			rd |= (instr & 1) << 5;
-			ea = xform_ea(instr, regs, u);
-			err = do_vsx_load(rd, do_lxvd2x, ea, regs);
-			goto ldst_done;
+				goto vsxunavail;
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(LOAD_VSX, u, 16);
+			break;
 
 		case 972:	/* stxvd2x */
 		case 1004:	/* stxvd2ux */
 			if (!(regs->msr & MSR_VSX))
-				break;
-			rd |= (instr & 1) << 5;
-			ea = xform_ea(instr, regs, u);
-			err = do_vsx_store(rd, do_stxvd2x, ea, regs);
-			goto ldst_done;
+				goto vsxunavail;
+			op->reg = rd | ((instr & 1) << 5);
+			op->type = MKOP(STORE_VSX, u, 16);
+			break;
 
 #endif /* CONFIG_VSX */
 		}
@@ -1552,178 +1539,123 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 	case 32:	/* lwz */
 	case 33:	/* lwzu */
-		err = read_mem(&regs->gpr[rd], dform_ea(instr, regs), 4, regs);
-		goto ldst_done;
+		op->type = MKOP(LOAD, u, 4);
+		op->ea = dform_ea(instr, regs);
+		break;
 
 	case 34:	/* lbz */
 	case 35:	/* lbzu */
-		err = read_mem(&regs->gpr[rd], dform_ea(instr, regs), 1, regs);
-		goto ldst_done;
+		op->type = MKOP(LOAD, u, 1);
+		op->ea = dform_ea(instr, regs);
+		break;
 
 	case 36:	/* stw */
-		val = regs->gpr[rd];
-		err = write_mem(val, dform_ea(instr, regs), 4, regs);
-		goto ldst_done;
-
 	case 37:	/* stwu */
-		val = regs->gpr[rd];
-		val3 = dform_ea(instr, regs);
-		/*
-		 * For PPC32 we always use stwu to change stack point with r1. So
-		 * this emulated store may corrupt the exception frame, now we
-		 * have to provide the exception frame trampoline, which is pushed
-		 * below the kprobed function stack. So we only update gpr[1] but
-		 * don't emulate the real store operation. We will do real store
-		 * operation safely in exception return code by checking this flag.
-		 */
-		if ((ra == 1) && !(regs->msr & MSR_PR) \
-			&& (val3 >= (regs->gpr[1] - STACK_INT_FRAME_SIZE))) {
-#ifdef CONFIG_PPC32
-			/*
-			 * Check if we will touch kernel sack overflow
-			 */
-			if (val3 - STACK_INT_FRAME_SIZE <= current->thread.ksp_limit) {
-				printk(KERN_CRIT "Can't kprobe this since Kernel stack overflow.\n");
-				err = -EINVAL;
-				break;
-			}
-#endif /* CONFIG_PPC32 */
-			/*
-			 * Check if we already set since that means we'll
-			 * lose the previous value.
-			 */
-			WARN_ON(test_thread_flag(TIF_EMULATE_STACK_STORE));
-			set_thread_flag(TIF_EMULATE_STACK_STORE);
-			err = 0;
-		} else
-			err = write_mem(val, val3, 4, regs);
-		goto ldst_done;
+		op->type = MKOP(STORE, u, 4);
+		op->ea = dform_ea(instr, regs);
+		break;
 
 	case 38:	/* stb */
 	case 39:	/* stbu */
-		val = regs->gpr[rd];
-		err = write_mem(val, dform_ea(instr, regs), 1, regs);
-		goto ldst_done;
+		op->type = MKOP(STORE, u, 1);
+		op->ea = dform_ea(instr, regs);
+		break;
 
 	case 40:	/* lhz */
 	case 41:	/* lhzu */
-		err = read_mem(&regs->gpr[rd], dform_ea(instr, regs), 2, regs);
-		goto ldst_done;
+		op->type = MKOP(LOAD, u, 2);
+		op->ea = dform_ea(instr, regs);
+		break;
 
 	case 42:	/* lha */
 	case 43:	/* lhau */
-		err = read_mem(&regs->gpr[rd], dform_ea(instr, regs), 2, regs);
-		if (!err)
-			regs->gpr[rd] = (signed short) regs->gpr[rd];
-		goto ldst_done;
+		op->type = MKOP(LOAD, SIGNEXT | u, 2);
+		op->ea = dform_ea(instr, regs);
+		break;
 
 	case 44:	/* sth */
 	case 45:	/* sthu */
-		val = regs->gpr[rd];
-		err = write_mem(val, dform_ea(instr, regs), 2, regs);
-		goto ldst_done;
+		op->type = MKOP(STORE, u, 2);
+		op->ea = dform_ea(instr, regs);
+		break;
 
 	case 46:	/* lmw */
-		ra = (instr >> 16) & 0x1f;
 		if (ra >= rd)
 			break;		/* invalid form, ra in range to load */
-		ea = dform_ea(instr, regs);
-		do {
-			err = read_mem(&regs->gpr[rd], ea, 4, regs);
-			if (err)
-				return 0;
-			ea += 4;
-		} while (++rd < 32);
-		goto instr_done;
+		op->type = MKOP(LOAD_MULTI, 0, 4 * (32 - rd));
+		op->ea = dform_ea(instr, regs);
+		break;
 
 	case 47:	/* stmw */
-		ea = dform_ea(instr, regs);
-		do {
-			err = write_mem(regs->gpr[rd], ea, 4, regs);
-			if (err)
-				return 0;
-			ea += 4;
-		} while (++rd < 32);
-		goto instr_done;
+		op->type = MKOP(STORE_MULTI, 0, 4 * (32 - rd));
+		op->ea = dform_ea(instr, regs);
+		break;
 
 #ifdef CONFIG_PPC_FPU
 	case 48:	/* lfs */
 	case 49:	/* lfsu */
 		if (!(regs->msr & MSR_FP))
-			break;
-		ea = dform_ea(instr, regs);
-		err = do_fp_load(rd, do_lfs, ea, 4, regs);
-		goto ldst_done;
+			goto fpunavail;
+		op->type = MKOP(LOAD_FP, u, 4);
+		op->ea = dform_ea(instr, regs);
+		break;
 
 	case 50:	/* lfd */
 	case 51:	/* lfdu */
 		if (!(regs->msr & MSR_FP))
-			break;
-		ea = dform_ea(instr, regs);
-		err = do_fp_load(rd, do_lfd, ea, 8, regs);
-		goto ldst_done;
+			goto fpunavail;
+		op->type = MKOP(LOAD_FP, u, 8);
+		op->ea = dform_ea(instr, regs);
+		break;
 
 	case 52:	/* stfs */
 	case 53:	/* stfsu */
 		if (!(regs->msr & MSR_FP))
-			break;
-		ea = dform_ea(instr, regs);
-		err = do_fp_store(rd, do_stfs, ea, 4, regs);
-		goto ldst_done;
+			goto fpunavail;
+		op->type = MKOP(STORE_FP, u, 4);
+		op->ea = dform_ea(instr, regs);
+		break;
 
 	case 54:	/* stfd */
 	case 55:	/* stfdu */
 		if (!(regs->msr & MSR_FP))
-			break;
-		ea = dform_ea(instr, regs);
-		err = do_fp_store(rd, do_stfd, ea, 8, regs);
-		goto ldst_done;
+			goto fpunavail;
+		op->type = MKOP(STORE_FP, u, 8);
+		op->ea = dform_ea(instr, regs);
+		break;
 #endif
 
 #ifdef __powerpc64__
 	case 58:	/* ld[u], lwa */
+		op->ea = dsform_ea(instr, regs);
 		switch (instr & 3) {
 		case 0:		/* ld */
-			err = read_mem(&regs->gpr[rd], dsform_ea(instr, regs),
-				       8, regs);
-			goto ldst_done;
+			op->type = MKOP(LOAD, 0, 8);
+			break;
 		case 1:		/* ldu */
-			err = read_mem(&regs->gpr[rd], dsform_ea(instr, regs),
-				       8, regs);
-			goto ldst_done;
+			op->type = MKOP(LOAD, UPDATE, 8);
+			break;
 		case 2:		/* lwa */
-			err = read_mem(&regs->gpr[rd], dsform_ea(instr, regs),
-				       4, regs);
-			if (!err)
-				regs->gpr[rd] = (signed int) regs->gpr[rd];
-			goto ldst_done;
+			op->type = MKOP(LOAD, SIGNEXT, 4);
+			break;
 		}
 		break;
 
 	case 62:	/* std[u] */
-		val = regs->gpr[rd];
+		op->ea = dsform_ea(instr, regs);
 		switch (instr & 3) {
 		case 0:		/* std */
-			err = write_mem(val, dsform_ea(instr, regs), 8, regs);
-			goto ldst_done;
+			op->type = MKOP(STORE, 0, 8);
+			break;
 		case 1:		/* stdu */
-			err = write_mem(val, dsform_ea(instr, regs), 8, regs);
-			goto ldst_done;
+			op->type = MKOP(STORE, UPDATE, 8);
+			break;
 		}
 		break;
 #endif /* __powerpc64__ */
 
 	}
-	err = -EINVAL;
-
- ldst_done:
-	if (err) {
-		regs->gpr[ra] = old_ra;
-		return 0;	/* invoke DSI if -EFAULT? */
-	}
- instr_done:
-	regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4);
-	return 1;
+	return 0;
 
  logical_done:
 	if (instr & 1)
@@ -1733,5 +1665,349 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
  arith_done:
 	if (instr & 1)
 		set_cr0(regs, rd);
-	goto instr_done;
+
+ instr_done:
+	regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4);
+	return 1;
+
+ priv:
+	op->type = INTERRUPT | 0x700;
+	op->val = SRR1_PROGPRIV;
+	return 0;
+
+ trap:
+	op->type = INTERRUPT | 0x700;
+	op->val = SRR1_PROGTRAP;
+	return 0;
+
+#ifdef CONFIG_PPC_FPU
+ fpunavail:
+	op->type = INTERRUPT | 0x800;
+	return 0;
+#endif
+
+#ifdef CONFIG_ALTIVEC
+ vecunavail:
+	op->type = INTERRUPT | 0xf20;
+	return 0;
+#endif
+
+#ifdef CONFIG_VSX
+ vsxunavail:
+	op->type = INTERRUPT | 0xf40;
+	return 0;
+#endif
+}
+EXPORT_SYMBOL_GPL(analyse_instr);
+
+/*
+ * For PPC32 we always use stwu with r1 to change the stack pointer.
+ * So this emulated store may corrupt the exception frame, now we
+ * have to provide the exception frame trampoline, which is pushed
+ * below the kprobed function stack. So we only update gpr[1] but
+ * don't emulate the real store operation. We will do real store
+ * operation safely in exception return code by checking this flag.
+ */
+static __kprobes int handle_stack_update(unsigned long ea, struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC32
+	/*
+	 * Check if we will touch kernel stack overflow
+	 */
+	if (ea - STACK_INT_FRAME_SIZE <= current->thread.ksp_limit) {
+		printk(KERN_CRIT "Can't kprobe this since kernel stack would overflow.\n");
+		return -EINVAL;
+	}
+#endif /* CONFIG_PPC32 */
+	/*
+	 * Check if we already set since that means we'll
+	 * lose the previous value.
+	 */
+	WARN_ON(test_thread_flag(TIF_EMULATE_STACK_STORE));
+	set_thread_flag(TIF_EMULATE_STACK_STORE);
+	return 0;
+}
+
+static __kprobes void do_signext(unsigned long *valp, int size)
+{
+	switch (size) {
+	case 2:
+		*valp = (signed short) *valp;
+		break;
+	case 4:
+		*valp = (signed int) *valp;
+		break;
+	}
+}
+
+static __kprobes void do_byterev(unsigned long *valp, int size)
+{
+	switch (size) {
+	case 2:
+		*valp = byterev_2(*valp);
+		break;
+	case 4:
+		*valp = byterev_4(*valp);
+		break;
+#ifdef __powerpc64__
+	case 8:
+		*valp = byterev_8(*valp);
+		break;
+#endif
+	}
+}
+
+/*
+ * Emulate instructions that cause a transfer of control,
+ * loads and stores, and a few other instructions.
+ * Returns 1 if the step was emulated, 0 if not,
+ * or -1 if the instruction is one that should not be stepped,
+ * such as an rfid, or a mtmsrd that would clear MSR_RI.
+ */
+int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
+{
+	struct instruction_op op;
+	int r, err, size;
+	unsigned long val;
+	unsigned int cr;
+	int i, rd, nb;
+
+	r = analyse_instr(&op, regs, instr);
+	if (r != 0)
+		return r;
+
+	err = 0;
+	size = GETSIZE(op.type);
+	switch (op.type & INSTR_TYPE_MASK) {
+	case CACHEOP:
+		if (!address_ok(regs, op.ea, 8))
+			return 0;
+		switch (op.type & CACHEOP_MASK) {
+		case DCBST:
+			__cacheop_user_asmx(op.ea, err, "dcbst");
+			break;
+		case DCBF:
+			__cacheop_user_asmx(op.ea, err, "dcbf");
+			break;
+		case DCBTST:
+			if (op.reg == 0)
+				prefetchw((void *) op.ea);
+			break;
+		case DCBT:
+			if (op.reg == 0)
+				prefetch((void *) op.ea);
+			break;
+		case ICBI:
+			__cacheop_user_asmx(op.ea, err, "icbi");
+			break;
+		}
+		if (err)
+			return 0;
+		goto instr_done;
+
+	case LARX:
+		if (regs->msr & MSR_LE)
+			return 0;
+		if (op.ea & (size - 1))
+			break;		/* can't handle misaligned */
+		err = -EFAULT;
+		if (!address_ok(regs, op.ea, size))
+			goto ldst_done;
+		err = 0;
+		switch (size) {
+		case 4:
+			__get_user_asmx(val, op.ea, err, "lwarx");
+			break;
+		case 8:
+			__get_user_asmx(val, op.ea, err, "ldarx");
+			break;
+		default:
+			return 0;
+		}
+		if (!err)
+			regs->gpr[op.reg] = val;
+		goto ldst_done;
+
+	case STCX:
+		if (regs->msr & MSR_LE)
+			return 0;
+		if (op.ea & (size - 1))
+			break;		/* can't handle misaligned */
+		err = -EFAULT;
+		if (!address_ok(regs, op.ea, size))
+			goto ldst_done;
+		err = 0;
+		switch (size) {
+		case 4:
+			__put_user_asmx(op.val, op.ea, err, "stwcx.", cr);
+			break;
+		case 8:
+			__put_user_asmx(op.val, op.ea, err, "stdcx.", cr);
+			break;
+		default:
+			return 0;
+		}
+		if (!err)
+			regs->ccr = (regs->ccr & 0x0fffffff) |
+				(cr & 0xe0000000) |
+				((regs->xer >> 3) & 0x10000000);
+		goto ldst_done;
+
+	case LOAD:
+		if (regs->msr & MSR_LE)
+			return 0;
+		err = read_mem(&regs->gpr[op.reg], op.ea, size, regs);
+		if (!err) {
+			if (op.type & SIGNEXT)
+				do_signext(&regs->gpr[op.reg], size);
+			if (op.type & BYTEREV)
+				do_byterev(&regs->gpr[op.reg], size);
+		}
+		goto ldst_done;
+
+	case LOAD_FP:
+		if (regs->msr & MSR_LE)
+			return 0;
+		if (size == 4)
+			err = do_fp_load(op.reg, do_lfs, op.ea, size, regs);
+		else
+			err = do_fp_load(op.reg, do_lfd, op.ea, size, regs);
+		goto ldst_done;
+
+#ifdef CONFIG_ALTIVEC
+	case LOAD_VMX:
+		if (regs->msr & MSR_LE)
+			return 0;
+		err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs);
+		goto ldst_done;
+#endif
+#ifdef CONFIG_VSX
+	case LOAD_VSX:
+		if (regs->msr & MSR_LE)
+			return 0;
+		err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs);
+		goto ldst_done;
+#endif
+	case LOAD_MULTI:
+		if (regs->msr & MSR_LE)
+			return 0;
+		rd = op.reg;
+		for (i = 0; i < size; i += 4) {
+			nb = size - i;
+			if (nb > 4)
+				nb = 4;
+			err = read_mem(&regs->gpr[rd], op.ea, nb, regs);
+			if (err)
+				return 0;
+			if (nb < 4)	/* left-justify last bytes */
+				regs->gpr[rd] <<= 32 - 8 * nb;
+			op.ea += 4;
+			++rd;
+		}
+		goto instr_done;
+
+	case STORE:
+		if (regs->msr & MSR_LE)
+			return 0;
+		if ((op.type & UPDATE) && size == sizeof(long) &&
+		    op.reg == 1 && op.update_reg == 1 &&
+		    !(regs->msr & MSR_PR) &&
+		    op.ea >= regs->gpr[1] - STACK_INT_FRAME_SIZE) {
+			err = handle_stack_update(op.ea, regs);
+			goto ldst_done;
+		}
+		err = write_mem(op.val, op.ea, size, regs);
+		goto ldst_done;
+
+	case STORE_FP:
+		if (regs->msr & MSR_LE)
+			return 0;
+		if (size == 4)
+			err = do_fp_store(op.reg, do_stfs, op.ea, size, regs);
+		else
+			err = do_fp_store(op.reg, do_stfd, op.ea, size, regs);
+		goto ldst_done;
+
+#ifdef CONFIG_ALTIVEC
+	case STORE_VMX:
+		if (regs->msr & MSR_LE)
+			return 0;
+		err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs);
+		goto ldst_done;
+#endif
+#ifdef CONFIG_VSX
+	case STORE_VSX:
+		if (regs->msr & MSR_LE)
+			return 0;
+		err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs);
+		goto ldst_done;
+#endif
+	case STORE_MULTI:
+		if (regs->msr & MSR_LE)
+			return 0;
+		rd = op.reg;
+		for (i = 0; i < size; i += 4) {
+			val = regs->gpr[rd];
+			nb = size - i;
+			if (nb > 4)
+				nb = 4;
+			else
+				val >>= 32 - 8 * nb;
+			err = write_mem(val, op.ea, nb, regs);
+			if (err)
+				return 0;
+			op.ea += 4;
+			++rd;
+		}
+		goto instr_done;
+
+	case MFMSR:
+		regs->gpr[op.reg] = regs->msr & MSR_MASK;
+		goto instr_done;
+
+	case MTMSR:
+		val = regs->gpr[op.reg];
+		if ((val & MSR_RI) == 0)
+			/* can't step mtmsr[d] that would clear MSR_RI */
+			return -1;
+		/* here op.val is the mask of bits to change */
+		regs->msr = (regs->msr & ~op.val) | (val & op.val);
+		goto instr_done;
+
+#ifdef CONFIG_PPC64
+	case SYSCALL:	/* sc */
+		/*
+		 * N.B. this uses knowledge about how the syscall
+		 * entry code works.  If that is changed, this will
+		 * need to be changed also.
+		 */
+		if (regs->gpr[0] == 0x1ebe &&
+		    cpu_has_feature(CPU_FTR_REAL_LE)) {
+			regs->msr ^= MSR_LE;
+			goto instr_done;
+		}
+		regs->gpr[9] = regs->gpr[13];
+		regs->gpr[10] = MSR_KERNEL;
+		regs->gpr[11] = regs->nip + 4;
+		regs->gpr[12] = regs->msr & MSR_MASK;
+		regs->gpr[13] = (unsigned long) get_paca();
+		regs->nip = (unsigned long) &system_call_common;
+		regs->msr = MSR_KERNEL;
+		return 1;
+
+	case RFI:
+		return -1;
+#endif
+	}
+	return 0;
+
+ ldst_done:
+	if (err)
+		return 0;
+	if (op.type & UPDATE)
+		regs->gpr[op.update_reg] = op.ea;
+
+ instr_done:
+	regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4);
+	return 1;
 }
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index d0130fff20e5..325e861616a1 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -34,3 +34,4 @@ obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += hugepage-hash64.o
 obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage-prot.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
+obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
diff --git a/arch/powerpc/platforms/cell/spu_fault.c b/arch/powerpc/mm/copro_fault.c
index 641e7273d75a..0f9939e693df 100644
--- a/arch/powerpc/platforms/cell/spu_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -1,5 +1,5 @@
 /*
- * SPU mm fault handler
+ * CoProcessor (SPU/AFU) mm fault handler
  *
  * (C) Copyright IBM Deutschland Entwicklung GmbH 2007
  *
@@ -23,16 +23,17 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/export.h>
-
+#include <asm/reg.h>
+#include <asm/copro.h>
 #include <asm/spu.h>
-#include <asm/spu_csa.h>
+#include <misc/cxl.h>
 
 /*
  * This ought to be kept in sync with the powerpc specific do_page_fault
  * function. Currently, there are a few corner cases that we haven't had
  * to handle fortunately.
  */
-int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
+int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 		unsigned long dsisr, unsigned *flt)
 {
 	struct vm_area_struct *vma;
@@ -58,12 +59,12 @@ int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 			goto out_unlock;
 	}
 
-	is_write = dsisr & MFC_DSISR_ACCESS_PUT;
+	is_write = dsisr & DSISR_ISSTORE;
 	if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto out_unlock;
 	} else {
-		if (dsisr & MFC_DSISR_ACCESS_DENIED)
+		if (dsisr & DSISR_PROTFAULT)
 			goto out_unlock;
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto out_unlock;
@@ -91,4 +92,58 @@ out_unlock:
 	up_read(&mm->mmap_sem);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(spu_handle_mm_fault);
+EXPORT_SYMBOL_GPL(copro_handle_mm_fault);
+
+int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
+{
+	u64 vsid;
+	int psize, ssize;
+
+	slb->esid = (ea & ESID_MASK) | SLB_ESID_V;
+
+	switch (REGION_ID(ea)) {
+	case USER_REGION_ID:
+		pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
+		psize = get_slice_psize(mm, ea);
+		ssize = user_segment_size(ea);
+		vsid = get_vsid(mm->context.id, ea, ssize);
+		break;
+	case VMALLOC_REGION_ID:
+		pr_devel("%s: 0x%llx -- VMALLOC_REGION_ID\n", __func__, ea);
+		if (ea < VMALLOC_END)
+			psize = mmu_vmalloc_psize;
+		else
+			psize = mmu_io_psize;
+		ssize = mmu_kernel_ssize;
+		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+		break;
+	case KERNEL_REGION_ID:
+		pr_devel("%s: 0x%llx -- KERNEL_REGION_ID\n", __func__, ea);
+		psize = mmu_linear_psize;
+		ssize = mmu_kernel_ssize;
+		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+		break;
+	default:
+		pr_debug("%s: invalid region access at %016llx\n", __func__, ea);
+		return 1;
+	}
+
+	vsid = (vsid << slb_vsid_shift(ssize)) | SLB_VSID_USER;
+
+	vsid |= mmu_psize_defs[psize].sllp |
+		((ssize == MMU_SEGSIZE_1T) ? SLB_VSID_B_1T : 0);
+
+	slb->vsid = vsid;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(copro_calculate_slb);
+
+void copro_flush_all_slbs(struct mm_struct *mm)
+{
+#ifdef CONFIG_SPU_BASE
+	spu_flush_all_slbs(mm);
+#endif
+	cxl_slbia(mm);
+}
+EXPORT_SYMBOL_GPL(copro_flush_all_slbs);
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 51ab9e7e6c39..08d659a9fcdb 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -30,9 +30,9 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/perf_event.h>
-#include <linux/magic.h>
 #include <linux/ratelimit.h>
 #include <linux/context_tracking.h>
+#include <linux/hugetlb.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
@@ -114,22 +114,37 @@ static int store_updates_sp(struct pt_regs *regs)
 #define MM_FAULT_CONTINUE	-1
 #define MM_FAULT_ERR(sig)	(sig)
 
-static int do_sigbus(struct pt_regs *regs, unsigned long address)
+static int do_sigbus(struct pt_regs *regs, unsigned long address,
+		     unsigned int fault)
 {
 	siginfo_t info;
+	unsigned int lsb = 0;
 
 	up_read(&current->mm->mmap_sem);
 
-	if (user_mode(regs)) {
-		current->thread.trap_nr = BUS_ADRERR;
-		info.si_signo = SIGBUS;
-		info.si_errno = 0;
-		info.si_code = BUS_ADRERR;
-		info.si_addr = (void __user *)address;
-		force_sig_info(SIGBUS, &info, current);
-		return MM_FAULT_RETURN;
+	if (!user_mode(regs))
+		return MM_FAULT_ERR(SIGBUS);
+
+	current->thread.trap_nr = BUS_ADRERR;
+	info.si_signo = SIGBUS;
+	info.si_errno = 0;
+	info.si_code = BUS_ADRERR;
+	info.si_addr = (void __user *)address;
+#ifdef CONFIG_MEMORY_FAILURE
+	if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
+		pr_err("MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
+			current->comm, current->pid, address);
+		info.si_code = BUS_MCEERR_AR;
 	}
-	return MM_FAULT_ERR(SIGBUS);
+
+	if (fault & VM_FAULT_HWPOISON_LARGE)
+		lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+	if (fault & VM_FAULT_HWPOISON)
+		lsb = PAGE_SHIFT;
+#endif
+	info.si_addr_lsb = lsb;
+	force_sig_info(SIGBUS, &info, current);
+	return MM_FAULT_RETURN;
 }
 
 static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
@@ -170,11 +185,8 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
 		return MM_FAULT_RETURN;
 	}
 
-	/* Bus error. x86 handles HWPOISON here, we'll add this if/when
-	 * we support the feature in HW
-	 */
-	if (fault & VM_FAULT_SIGBUS)
-		return do_sigbus(regs, addr);
+	if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE))
+		return do_sigbus(regs, addr, fault);
 
 	/* We don't understand the fault code, this is fatal */
 	BUG();
@@ -508,7 +520,6 @@ bail:
 void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 {
 	const struct exception_table_entry *entry;
-	unsigned long *stackend;
 
 	/* Are we prepared to handle this fault?  */
 	if ((entry = search_exception_tables(regs->nip)) != NULL) {
@@ -537,8 +548,7 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 	printk(KERN_ALERT "Faulting instruction address: 0x%08lx\n",
 		regs->nip);
 
-	stackend = end_of_stack(current);
-	if (current != &init_task && *stackend != STACK_END_MAGIC)
+	if (task_stack_end_corrupted(current))
 		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
 
 	die("Kernel access of bad area", regs, sig);
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index afc0a8295f84..ae4962a06476 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -29,6 +29,8 @@
 #include <asm/kexec.h>
 #include <asm/ppc-opcode.h>
 
+#include <misc/cxl.h>
+
 #ifdef DEBUG_LOW
 #define DBG_LOW(fmt...) udbg_printf(fmt)
 #else
@@ -149,9 +151,11 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 static inline void tlbie(unsigned long vpn, int psize, int apsize,
 			 int ssize, int local)
 {
-	unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL);
+	unsigned int use_local;
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
 
+	use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) && !cxl_ctx_in_use();
+
 	if (use_local)
 		use_local = mmu_psize_defs[psize].tlbiel;
 	if (lock_tlbie && !use_local)
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index daee7f4e5a14..d5339a3b9945 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -51,7 +51,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cputable.h>
 #include <asm/sections.h>
-#include <asm/spu.h>
+#include <asm/copro.h>
 #include <asm/udbg.h>
 #include <asm/code-patching.h>
 #include <asm/fadump.h>
@@ -92,12 +92,14 @@ extern unsigned long dart_tablebase;
 
 static unsigned long _SDR1;
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
+EXPORT_SYMBOL_GPL(mmu_psize_defs);
 
 struct hash_pte *htab_address;
 unsigned long htab_size_bytes;
 unsigned long htab_hash_mask;
 EXPORT_SYMBOL_GPL(htab_hash_mask);
 int mmu_linear_psize = MMU_PAGE_4K;
+EXPORT_SYMBOL_GPL(mmu_linear_psize);
 int mmu_virtual_psize = MMU_PAGE_4K;
 int mmu_vmalloc_psize = MMU_PAGE_4K;
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
@@ -105,6 +107,7 @@ int mmu_vmemmap_psize = MMU_PAGE_4K;
 #endif
 int mmu_io_psize = MMU_PAGE_4K;
 int mmu_kernel_ssize = MMU_SEGSIZE_256M;
+EXPORT_SYMBOL_GPL(mmu_kernel_ssize);
 int mmu_highuser_ssize = MMU_SEGSIZE_256M;
 u16 mmu_slb_size = 64;
 EXPORT_SYMBOL_GPL(mmu_slb_size);
@@ -333,70 +336,69 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 		return 0;
 
 	prop = of_get_flat_dt_prop(node, "ibm,segment-page-sizes", &size);
-	if (prop != NULL) {
-		pr_info("Page sizes from device-tree:\n");
-		size /= 4;
-		cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
-		while(size > 0) {
-			unsigned int base_shift = be32_to_cpu(prop[0]);
-			unsigned int slbenc = be32_to_cpu(prop[1]);
-			unsigned int lpnum = be32_to_cpu(prop[2]);
-			struct mmu_psize_def *def;
-			int idx, base_idx;
-
-			size -= 3; prop += 3;
-			base_idx = get_idx_from_shift(base_shift);
-			if (base_idx < 0) {
-				/*
-				 * skip the pte encoding also
-				 */
-				prop += lpnum * 2; size -= lpnum * 2;
+	if (!prop)
+		return 0;
+
+	pr_info("Page sizes from device-tree:\n");
+	size /= 4;
+	cur_cpu_spec->mmu_features &= ~(MMU_FTR_16M_PAGE);
+	while(size > 0) {
+		unsigned int base_shift = be32_to_cpu(prop[0]);
+		unsigned int slbenc = be32_to_cpu(prop[1]);
+		unsigned int lpnum = be32_to_cpu(prop[2]);
+		struct mmu_psize_def *def;
+		int idx, base_idx;
+
+		size -= 3; prop += 3;
+		base_idx = get_idx_from_shift(base_shift);
+		if (base_idx < 0) {
+			/* skip the pte encoding also */
+			prop += lpnum * 2; size -= lpnum * 2;
+			continue;
+		}
+		def = &mmu_psize_defs[base_idx];
+		if (base_idx == MMU_PAGE_16M)
+			cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE;
+
+		def->shift = base_shift;
+		if (base_shift <= 23)
+			def->avpnm = 0;
+		else
+			def->avpnm = (1 << (base_shift - 23)) - 1;
+		def->sllp = slbenc;
+		/*
+		 * We don't know for sure what's up with tlbiel, so
+		 * for now we only set it for 4K and 64K pages
+		 */
+		if (base_idx == MMU_PAGE_4K || base_idx == MMU_PAGE_64K)
+			def->tlbiel = 1;
+		else
+			def->tlbiel = 0;
+
+		while (size > 0 && lpnum) {
+			unsigned int shift = be32_to_cpu(prop[0]);
+			int penc  = be32_to_cpu(prop[1]);
+
+			prop += 2; size -= 2;
+			lpnum--;
+
+			idx = get_idx_from_shift(shift);
+			if (idx < 0)
 				continue;
-			}
-			def = &mmu_psize_defs[base_idx];
-			if (base_idx == MMU_PAGE_16M)
-				cur_cpu_spec->mmu_features |= MMU_FTR_16M_PAGE;
-
-			def->shift = base_shift;
-			if (base_shift <= 23)
-				def->avpnm = 0;
-			else
-				def->avpnm = (1 << (base_shift - 23)) - 1;
-			def->sllp = slbenc;
-			/*
-			 * We don't know for sure what's up with tlbiel, so
-			 * for now we only set it for 4K and 64K pages
-			 */
-			if (base_idx == MMU_PAGE_4K || base_idx == MMU_PAGE_64K)
-				def->tlbiel = 1;
-			else
-				def->tlbiel = 0;
-
-			while (size > 0 && lpnum) {
-				unsigned int shift = be32_to_cpu(prop[0]);
-				int penc  = be32_to_cpu(prop[1]);
-
-				prop += 2; size -= 2;
-				lpnum--;
-
-				idx = get_idx_from_shift(shift);
-				if (idx < 0)
-					continue;
-
-				if (penc == -1)
-					pr_err("Invalid penc for base_shift=%d "
-					       "shift=%d\n", base_shift, shift);
-
-				def->penc[idx] = penc;
-				pr_info("base_shift=%d: shift=%d, sllp=0x%04lx,"
-					" avpnm=0x%08lx, tlbiel=%d, penc=%d\n",
-					base_shift, shift, def->sllp,
-					def->avpnm, def->tlbiel, def->penc[idx]);
-			}
+
+			if (penc == -1)
+				pr_err("Invalid penc for base_shift=%d "
+				       "shift=%d\n", base_shift, shift);
+
+			def->penc[idx] = penc;
+			pr_info("base_shift=%d: shift=%d, sllp=0x%04lx,"
+				" avpnm=0x%08lx, tlbiel=%d, penc=%d\n",
+				base_shift, shift, def->sllp,
+				def->avpnm, def->tlbiel, def->penc[idx]);
 		}
-		return 1;
 	}
-	return 0;
+
+	return 1;
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
@@ -867,7 +869,7 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
 }
 
 #ifdef CONFIG_PPC_MM_SLICES
-unsigned int get_paca_psize(unsigned long addr)
+static unsigned int get_paca_psize(unsigned long addr)
 {
 	u64 lpsizes;
 	unsigned char *hpsizes;
@@ -901,10 +903,8 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
 	if (get_slice_psize(mm, addr) == MMU_PAGE_4K)
 		return;
 	slice_set_range_psize(mm, addr, 1, MMU_PAGE_4K);
-#ifdef CONFIG_SPU_BASE
-	spu_flush_all_slbs(mm);
-#endif
-	if (get_paca_psize(addr) != MMU_PAGE_4K) {
+	copro_flush_all_slbs(mm);
+	if ((get_paca_psize(addr) != MMU_PAGE_4K) && (current->mm == mm)) {
 		get_paca()->context = mm->context;
 		slb_flush_and_rebolt();
 	}
@@ -989,12 +989,11 @@ static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
  * -1 - critical hash insertion error
  * -2 - access not permitted by subpage protection mechanism
  */
-int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
+int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long access, unsigned long trap)
 {
 	enum ctx_state prev_state = exception_enter();
 	pgd_t *pgdir;
 	unsigned long vsid;
-	struct mm_struct *mm;
 	pte_t *ptep;
 	unsigned hugeshift;
 	const struct cpumask *tmp;
@@ -1008,7 +1007,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
  	switch (REGION_ID(ea)) {
 	case USER_REGION_ID:
 		user_region = 1;
-		mm = current->mm;
 		if (! mm) {
 			DBG_LOW(" user region with no mm !\n");
 			rc = 1;
@@ -1019,7 +1017,6 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 		vsid = get_vsid(mm->context.id, ea, ssize);
 		break;
 	case VMALLOC_REGION_ID:
-		mm = &init_mm;
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
 		if (ea < VMALLOC_END)
 			psize = mmu_vmalloc_psize;
@@ -1104,7 +1101,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 			WARN_ON(1);
 		}
 #endif
-		check_paca_psize(ea, mm, psize, user_region);
+		if (current->mm == mm)
+			check_paca_psize(ea, mm, psize, user_region);
 
 		goto bail;
 	}
@@ -1141,13 +1139,12 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 			       "to 4kB pages because of "
 			       "non-cacheable mapping\n");
 			psize = mmu_vmalloc_psize = MMU_PAGE_4K;
-#ifdef CONFIG_SPU_BASE
-			spu_flush_all_slbs(mm);
-#endif
+			copro_flush_all_slbs(mm);
 		}
 	}
 
-	check_paca_psize(ea, mm, psize, user_region);
+	if (current->mm == mm)
+		check_paca_psize(ea, mm, psize, user_region);
 #endif /* CONFIG_PPC_64K_PAGES */
 
 #ifdef CONFIG_PPC_HAS_HASH_64K
@@ -1182,6 +1179,17 @@ bail:
 	exception_exit(prev_state);
 	return rc;
 }
+EXPORT_SYMBOL_GPL(hash_page_mm);
+
+int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
+{
+	struct mm_struct *mm = current->mm;
+
+	if (REGION_ID(ea) == VMALLOC_REGION_ID)
+		mm = &init_mm;
+
+	return hash_page_mm(mm, ea, access, trap);
+}
 EXPORT_SYMBOL_GPL(hash_page);
 
 void hash_preload(struct mm_struct *mm, unsigned long ea,
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index cff59f1bec23..cad68ff8eca5 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -106,11 +106,11 @@ unsigned long __max_low_memory = MAX_LOW_MEM;
 void MMU_setup(void)
 {
 	/* Check for nobats option (used in mapin_ram). */
-	if (strstr(cmd_line, "nobats")) {
+	if (strstr(boot_command_line, "nobats")) {
 		__map_without_bats = 1;
 	}
 
-	if (strstr(cmd_line, "noltlbs")) {
+	if (strstr(boot_command_line, "noltlbs")) {
 		__map_without_ltlbs = 1;
 	}
 #ifdef CONFIG_DEBUG_PAGEALLOC
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 253b4b971c8a..3481556a1880 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -233,9 +233,6 @@ static void __meminit vmemmap_create_mapping(unsigned long start,
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-extern int htab_remove_mapping(unsigned long vstart, unsigned long vend,
-			int psize, int ssize);
-
 static void vmemmap_remove_mapping(unsigned long start,
 				   unsigned long page_size)
 {
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index e0f7a189c48e..8ebaac75c940 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -260,6 +260,60 @@ static int __init mark_nonram_nosave(void)
 	}
 	return 0;
 }
+#else /* CONFIG_NEED_MULTIPLE_NODES */
+static int __init mark_nonram_nosave(void)
+{
+	return 0;
+}
+#endif
+
+static bool zone_limits_final;
+
+static unsigned long max_zone_pfns[MAX_NR_ZONES] = {
+	[0 ... MAX_NR_ZONES - 1] = ~0UL
+};
+
+/*
+ * Restrict the specified zone and all more restrictive zones
+ * to be below the specified pfn.  May not be called after
+ * paging_init().
+ */
+void __init limit_zone_pfn(enum zone_type zone, unsigned long pfn_limit)
+{
+	int i;
+
+	if (WARN_ON(zone_limits_final))
+		return;
+
+	for (i = zone; i >= 0; i--) {
+		if (max_zone_pfns[i] > pfn_limit)
+			max_zone_pfns[i] = pfn_limit;
+	}
+}
+
+/*
+ * Find the least restrictive zone that is entirely below the
+ * specified pfn limit.  Returns < 0 if no suitable zone is found.
+ *
+ * pfn_limit must be u64 because it can exceed 32 bits even on 32-bit
+ * systems -- the DMA limit can be higher than any possible real pfn.
+ */
+int dma_pfn_limit_to_zone(u64 pfn_limit)
+{
+	enum zone_type top_zone = ZONE_NORMAL;
+	int i;
+
+#ifdef CONFIG_HIGHMEM
+	top_zone = ZONE_HIGHMEM;
+#endif
+
+	for (i = top_zone; i >= 0; i--) {
+		if (max_zone_pfns[i] <= pfn_limit)
+			return i;
+	}
+
+	return -EPERM;
+}
 
 /*
  * paging_init() sets up the page tables - in fact we've already done this.
@@ -268,7 +322,7 @@ void __init paging_init(void)
 {
 	unsigned long long total_ram = memblock_phys_mem_size();
 	phys_addr_t top_of_ram = memblock_end_of_DRAM();
-	unsigned long max_zone_pfns[MAX_NR_ZONES];
+	enum zone_type top_zone;
 
 #ifdef CONFIG_PPC32
 	unsigned long v = __fix_to_virt(__end_of_fixed_addresses - 1);
@@ -290,18 +344,20 @@ void __init paging_init(void)
 	       (unsigned long long)top_of_ram, total_ram);
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (long int)((top_of_ram - total_ram) >> 20));
-	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+
 #ifdef CONFIG_HIGHMEM
-	max_zone_pfns[ZONE_DMA] = lowmem_end_addr >> PAGE_SHIFT;
-	max_zone_pfns[ZONE_HIGHMEM] = top_of_ram >> PAGE_SHIFT;
+	top_zone = ZONE_HIGHMEM;
+	limit_zone_pfn(ZONE_NORMAL, lowmem_end_addr >> PAGE_SHIFT);
 #else
-	max_zone_pfns[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
+	top_zone = ZONE_NORMAL;
 #endif
+
+	limit_zone_pfn(top_zone, top_of_ram >> PAGE_SHIFT);
+	zone_limits_final = true;
 	free_area_init_nodes(max_zone_pfns);
 
 	mark_nonram_nosave();
 }
-#endif /* ! CONFIG_NEED_MULTIPLE_NODES */
 
 static void __init register_page_bootmem_info(void)
 {
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index d7737a542fd7..649666d5d1c2 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -538,7 +538,7 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem,
  */
 static int numa_setup_cpu(unsigned long lcpu)
 {
-	int nid;
+	int nid = -1;
 	struct device_node *cpu;
 
 	/*
@@ -555,19 +555,21 @@ static int numa_setup_cpu(unsigned long lcpu)
 
 	if (!cpu) {
 		WARN_ON(1);
-		nid = 0;
-		goto out;
+		if (cpu_present(lcpu))
+			goto out_present;
+		else
+			goto out;
 	}
 
 	nid = of_node_to_nid_single(cpu);
 
+out_present:
 	if (nid < 0 || !node_online(nid))
 		nid = first_online_node;
-out:
-	map_cpu_to_node(lcpu, nid);
 
+	map_cpu_to_node(lcpu, nid);
 	of_node_put(cpu);
-
+out:
 	return nid;
 }
 
@@ -1127,20 +1129,11 @@ void __init do_init_bootmem(void)
 	 * even before we online them, so that we can use cpu_to_{node,mem}
 	 * early in boot, cf. smp_prepare_cpus().
 	 */
-	for_each_possible_cpu(cpu) {
-		cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE,
-				  (void *)(unsigned long)cpu);
+	for_each_present_cpu(cpu) {
+		numa_setup_cpu((unsigned long)cpu);
 	}
 }
 
-void __init paging_init(void)
-{
-	unsigned long max_zone_pfns[MAX_NR_ZONES];
-	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-	max_zone_pfns[ZONE_DMA] = memblock_end_of_DRAM() >> PAGE_SHIFT;
-	free_area_init_nodes(max_zone_pfns);
-}
-
 static int __init early_numa(char *p)
 {
 	if (!p)
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index c695943a513c..c90e602677c9 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -48,7 +48,7 @@ static inline int pte_looks_normal(pte_t pte)
 	    (_PAGE_PRESENT | _PAGE_USER);
 }
 
-struct page * maybe_pte_to_page(pte_t pte)
+static struct page *maybe_pte_to_page(pte_t pte)
 {
 	unsigned long pfn = pte_pfn(pte);
 	struct page *page;
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 0399a6702958..6e450ca66526 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -46,9 +46,6 @@ static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
 	return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | slot;
 }
 
-#define slb_vsid_shift(ssize)	\
-	((ssize) == MMU_SEGSIZE_256M? SLB_VSID_SHIFT: SLB_VSID_SHIFT_1T)
-
 static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
 					 unsigned long flags)
 {
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index b0c75cc15efc..8d7bda94d196 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -30,9 +30,11 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
+#include <linux/hugetlb.h>
 #include <asm/mman.h>
 #include <asm/mmu.h>
-#include <asm/spu.h>
+#include <asm/copro.h>
+#include <asm/hugetlb.h>
 
 /* some sanity checks */
 #if (PGTABLE_RANGE >> 43) > SLICE_MASK_SIZE
@@ -232,9 +234,7 @@ static void slice_convert(struct mm_struct *mm, struct slice_mask mask, int psiz
 
 	spin_unlock_irqrestore(&slice_convert_lock, flags);
 
-#ifdef CONFIG_SPU_BASE
-	spu_flush_all_slbs(mm);
-#endif
+	copro_flush_all_slbs(mm);
 }
 
 /*
@@ -671,9 +671,7 @@ void slice_set_psize(struct mm_struct *mm, unsigned long address,
 
 	spin_unlock_irqrestore(&slice_convert_lock, flags);
 
-#ifdef CONFIG_SPU_BASE
-	spu_flush_all_slbs(mm);
-#endif
+	copro_flush_all_slbs(mm);
 }
 
 void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c
index f75301f2c85f..6adf55fa5d88 100644
--- a/arch/powerpc/oprofile/backtrace.c
+++ b/arch/powerpc/oprofile/backtrace.c
@@ -12,6 +12,7 @@
 #include <asm/processor.h>
 #include <asm/uaccess.h>
 #include <asm/compat.h>
+#include <asm/oprofile_impl.h>
 
 #define STACK_SP(STACK)		*(STACK)
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index b7cd00b0171e..a6995d4e93d4 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -59,9 +59,9 @@ struct cpu_hw_events {
 	struct	perf_branch_entry	bhrb_entries[BHRB_MAX_ENTRIES];
 };
 
-DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
 
-struct power_pmu *ppmu;
+static struct power_pmu *ppmu;
 
 /*
  * Normally, to ignore kernel events we set the FCS (freeze counters
@@ -124,7 +124,7 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
 
 static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
 static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
-void power_pmu_flush_branch_stack(void) {}
+static void power_pmu_flush_branch_stack(void) {}
 static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
 static void pmao_restore_workaround(bool ebb) { }
 #endif /* CONFIG_PPC32 */
@@ -375,7 +375,7 @@ static void power_pmu_bhrb_disable(struct perf_event *event)
 /* Called from ctxsw to prevent one process's branch entries to
  * mingle with the other process's entries during context switch.
  */
-void power_pmu_flush_branch_stack(void)
+static void power_pmu_flush_branch_stack(void)
 {
 	if (ppmu->bhrb_nr)
 		power_pmu_bhrb_reset();
@@ -408,7 +408,7 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 }
 
 /* Processing BHRB entries */
-void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
+static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
 {
 	u64 val;
 	u64 addr;
@@ -1573,7 +1573,7 @@ static void power_pmu_stop(struct perf_event *event, int ef_flags)
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-void power_pmu_start_txn(struct pmu *pmu)
+static void power_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
@@ -1587,7 +1587,7 @@ void power_pmu_start_txn(struct pmu *pmu)
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-void power_pmu_cancel_txn(struct pmu *pmu)
+static void power_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
@@ -1600,7 +1600,7 @@ void power_pmu_cancel_txn(struct pmu *pmu)
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-int power_pmu_commit_txn(struct pmu *pmu)
+static int power_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	long i, n;
@@ -1888,7 +1888,7 @@ ssize_t power_events_sysfs_show(struct device *dev,
 	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
 }
 
-struct pmu power_pmu = {
+static struct pmu power_pmu = {
 	.pmu_enable	= power_pmu_enable,
 	.pmu_disable	= power_pmu_disable,
 	.event_init	= power_pmu_event_init,
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 70d4f748b54b..6c8710dd90c9 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -75,86 +75,6 @@ static struct attribute_group format_group = {
 
 static struct kmem_cache *hv_page_cache;
 
-/*
- * read_offset_data - copy data from one buffer to another while treating the
- *                    source buffer as a small view on the total avaliable
- *                    source data.
- *
- * @dest: buffer to copy into
- * @dest_len: length of @dest in bytes
- * @requested_offset: the offset within the source data we want. Must be > 0
- * @src: buffer to copy data from
- * @src_len: length of @src in bytes
- * @source_offset: the offset in the sorce data that (src,src_len) refers to.
- *                 Must be > 0
- *
- * returns the number of bytes copied.
- *
- * The following ascii art shows the various buffer possitioning we need to
- * handle, assigns some arbitrary varibles to points on the buffer, and then
- * shows how we fiddle with those values to get things we care about (copy
- * start in src and copy len)
- *
- * s = @src buffer
- * d = @dest buffer
- * '.' areas in d are written to.
- *
- *                       u
- *   x         w	 v  z
- * d           |.........|
- * s |----------------------|
- *
- *                      u
- *   x         w	z     v
- * d           |........------|
- * s |------------------|
- *
- *   x         w        u,z,v
- * d           |........|
- * s |------------------|
- *
- *   x,w                u,v,z
- * d |..................|
- * s |------------------|
- *
- *   x        u
- *   w        v		z
- * d |........|
- * s |------------------|
- *
- *   x      z   w      v
- * d            |------|
- * s |------|
- *
- * x = source_offset
- * w = requested_offset
- * z = source_offset + src_len
- * v = requested_offset + dest_len
- *
- * w_offset_in_s = w - x = requested_offset - source_offset
- * z_offset_in_s = z - x = src_len
- * v_offset_in_s = v - x = request_offset + dest_len - src_len
- */
-static ssize_t read_offset_data(void *dest, size_t dest_len,
-				loff_t requested_offset, void *src,
-				size_t src_len, loff_t source_offset)
-{
-	size_t w_offset_in_s = requested_offset - source_offset;
-	size_t z_offset_in_s = src_len;
-	size_t v_offset_in_s = requested_offset + dest_len - src_len;
-	size_t u_offset_in_s = min(z_offset_in_s, v_offset_in_s);
-	size_t copy_len = u_offset_in_s - w_offset_in_s;
-
-	if (requested_offset < 0 || source_offset < 0)
-		return -EINVAL;
-
-	if (z_offset_in_s <= w_offset_in_s)
-		return 0;
-
-	memcpy(dest, src + w_offset_in_s, copy_len);
-	return copy_len;
-}
-
 static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096,
 					      unsigned long version,
 					      unsigned long index)
@@ -183,8 +103,10 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
 {
 	unsigned long hret;
 	ssize_t ret = 0;
-	size_t catalog_len = 0, catalog_page_len = 0, page_count = 0;
+	size_t catalog_len = 0, catalog_page_len = 0;
 	loff_t page_offset = 0;
+	loff_t offset_in_page;
+	size_t copy_len;
 	uint64_t catalog_version_num = 0;
 	void *page = kmem_cache_alloc(hv_page_cache, GFP_USER);
 	struct hv_24x7_catalog_page_0 *page_0 = page;
@@ -202,7 +124,7 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
 	catalog_len = catalog_page_len * 4096;
 
 	page_offset = offset / 4096;
-	page_count  = count  / 4096;
+	offset_in_page = offset % 4096;
 
 	if (page_offset >= catalog_page_len)
 		goto e_free;
@@ -216,8 +138,13 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
 		}
 	}
 
-	ret = read_offset_data(buf, count, offset,
-				page, 4096, page_offset * 4096);
+	copy_len = 4096 - offset_in_page;
+	if (copy_len > count)
+		copy_len = count;
+
+	memcpy(buf, page+offset_in_page, copy_len);
+	ret = copy_len;
+
 e_free:
 	if (hret)
 		pr_err("h_get_24x7_catalog_page(ver=%lld, page=%lld) failed:"
@@ -225,9 +152,9 @@ e_free:
 		       catalog_version_num, page_offset, hret);
 	kmem_cache_free(hv_page_cache, page);
 
-	pr_devel("catalog_read: offset=%lld(%lld) count=%zu(%zu) catalog_len=%zu(%zu) => %zd\n",
-			offset, page_offset, count, page_count, catalog_len,
-			catalog_page_len, ret);
+	pr_devel("catalog_read: offset=%lld(%lld) count=%zu "
+			"catalog_len=%zu(%zu) => %zd\n", offset, page_offset,
+			count, catalog_len, catalog_page_len, ret);
 
 	return ret;
 }
@@ -294,7 +221,7 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
 					 u16 lpar, u64 *res,
 					 bool success_expected)
 {
-	unsigned long ret;
+	unsigned long ret = -ENOMEM;
 
 	/*
 	 * request_buffer and result_buffer are not required to be 4k aligned,
@@ -304,7 +231,27 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
 	struct reqb {
 		struct hv_24x7_request_buffer buf;
 		struct hv_24x7_request req;
-	} __packed __aligned(4096) request_buffer = {
+	} __packed *request_buffer;
+
+	struct {
+		struct hv_24x7_data_result_buffer buf;
+		struct hv_24x7_result res;
+		struct hv_24x7_result_element elem;
+		__be64 result;
+	} __packed *result_buffer;
+
+	BUILD_BUG_ON(sizeof(*request_buffer) > 4096);
+	BUILD_BUG_ON(sizeof(*result_buffer) > 4096);
+
+	request_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER);
+	if (!request_buffer)
+		goto out;
+
+	result_buffer = kmem_cache_zalloc(hv_page_cache, GFP_USER);
+	if (!result_buffer)
+		goto out_free_request_buffer;
+
+	*request_buffer = (struct reqb) {
 		.buf = {
 			.interface_version = HV_24X7_IF_VERSION_CURRENT,
 			.num_requests = 1,
@@ -320,28 +267,27 @@ static unsigned long single_24x7_request(u8 domain, u32 offset, u16 ix,
 		}
 	};
 
-	struct resb {
-		struct hv_24x7_data_result_buffer buf;
-		struct hv_24x7_result res;
-		struct hv_24x7_result_element elem;
-		__be64 result;
-	} __packed __aligned(4096) result_buffer = {};
-
 	ret = plpar_hcall_norets(H_GET_24X7_DATA,
-			virt_to_phys(&request_buffer), sizeof(request_buffer),
-			virt_to_phys(&result_buffer),  sizeof(result_buffer));
+			virt_to_phys(request_buffer), sizeof(*request_buffer),
+			virt_to_phys(result_buffer),  sizeof(*result_buffer));
 
 	if (ret) {
 		if (success_expected)
-			pr_err_ratelimited("hcall failed: %d %#x %#x %d => 0x%lx (%ld) detail=0x%x failing ix=%x\n",
-					domain, offset, ix, lpar,
-					ret, ret,
-					result_buffer.buf.detailed_rc,
-					result_buffer.buf.failing_request_ix);
-		return ret;
+			pr_err_ratelimited("hcall failed: %d %#x %#x %d => "
+				"0x%lx (%ld) detail=0x%x failing ix=%x\n",
+				domain, offset, ix, lpar, ret, ret,
+				result_buffer->buf.detailed_rc,
+				result_buffer->buf.failing_request_ix);
+		goto out_free_result_buffer;
 	}
 
-	*res = be64_to_cpu(result_buffer.result);
+	*res = be64_to_cpu(result_buffer->result);
+
+out_free_result_buffer:
+	kfree(result_buffer);
+out_free_request_buffer:
+	kfree(request_buffer);
+out:
 	return ret;
 }
 
diff --git a/arch/powerpc/platforms/40x/ep405.c b/arch/powerpc/platforms/40x/ep405.c
index b0389bbe4f94..ddc12a1926ef 100644
--- a/arch/powerpc/platforms/40x/ep405.c
+++ b/arch/powerpc/platforms/40x/ep405.c
@@ -49,7 +49,7 @@ static void __iomem *bcsr_regs;
 /* there's more, can't be bothered typing them tho */
 
 
-static __initdata struct of_device_id ep405_of_bus[] = {
+static const struct of_device_id ep405_of_bus[] __initconst = {
 	{ .compatible = "ibm,plb3", },
 	{ .compatible = "ibm,opb", },
 	{ .compatible = "ibm,ebc", },
diff --git a/arch/powerpc/platforms/40x/ppc40x_simple.c b/arch/powerpc/platforms/40x/ppc40x_simple.c
index 8f3920e5a046..b0c46375dd95 100644
--- a/arch/powerpc/platforms/40x/ppc40x_simple.c
+++ b/arch/powerpc/platforms/40x/ppc40x_simple.c
@@ -24,7 +24,7 @@
 #include <linux/init.h>
 #include <linux/of_platform.h>
 
-static __initdata struct of_device_id ppc40x_of_bus[] = {
+static const struct of_device_id ppc40x_of_bus[] __initconst = {
 	{ .compatible = "ibm,plb3", },
 	{ .compatible = "ibm,plb4", },
 	{ .compatible = "ibm,opb", },
diff --git a/arch/powerpc/platforms/40x/virtex.c b/arch/powerpc/platforms/40x/virtex.c
index d0fc6866b00c..9aa7ae2f4164 100644
--- a/arch/powerpc/platforms/40x/virtex.c
+++ b/arch/powerpc/platforms/40x/virtex.c
@@ -17,7 +17,7 @@
 #include <asm/xilinx_pci.h>
 #include <asm/ppc4xx.h>
 
-static struct of_device_id xilinx_of_bus_ids[] __initdata = {
+static const struct of_device_id xilinx_of_bus_ids[] __initconst = {
 	{ .compatible = "xlnx,plb-v46-1.00.a", },
 	{ .compatible = "xlnx,plb-v34-1.01.a", },
 	{ .compatible = "xlnx,plb-v34-1.02.a", },
diff --git a/arch/powerpc/platforms/40x/walnut.c b/arch/powerpc/platforms/40x/walnut.c
index 8b691df72f74..f7ac2d0fcb44 100644
--- a/arch/powerpc/platforms/40x/walnut.c
+++ b/arch/powerpc/platforms/40x/walnut.c
@@ -28,7 +28,7 @@
 #include <asm/pci-bridge.h>
 #include <asm/ppc4xx.h>
 
-static __initdata struct of_device_id walnut_of_bus[] = {
+static const struct of_device_id walnut_of_bus[] __initconst = {
 	{ .compatible = "ibm,plb3", },
 	{ .compatible = "ibm,opb", },
 	{ .compatible = "ibm,ebc", },
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index 4d88f6a19058..82f2da28cd27 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -215,9 +215,9 @@ config AKEBONO
 	select NET_VENDOR_IBM
 	select IBM_EMAC_EMAC4
 	select IBM_EMAC_RGMII_WOL
-	select USB
-	select USB_OHCI_HCD_PLATFORM
-	select USB_EHCI_HCD_PLATFORM
+	select USB if USB_SUPPORT
+	select USB_OHCI_HCD_PLATFORM if USB_OHCI_HCD
+	select USB_EHCI_HCD_PLATFORM if USB_EHCI_HCD
 	select MMC_SDHCI
 	select MMC_SDHCI_PLTFM
 	select MMC_SDHCI_OF_476GTR
diff --git a/arch/powerpc/platforms/44x/canyonlands.c b/arch/powerpc/platforms/44x/canyonlands.c
index e300dd4c89bf..22ca5430c9cb 100644
--- a/arch/powerpc/platforms/44x/canyonlands.c
+++ b/arch/powerpc/platforms/44x/canyonlands.c
@@ -33,7 +33,7 @@
 
 #define BCSR_USB_EN	0x11
 
-static __initdata struct of_device_id ppc460ex_of_bus[] = {
+static const struct of_device_id ppc460ex_of_bus[] __initconst = {
 	{ .compatible = "ibm,plb4", },
 	{ .compatible = "ibm,opb", },
 	{ .compatible = "ibm,ebc", },
diff --git a/arch/powerpc/platforms/44x/ebony.c b/arch/powerpc/platforms/44x/ebony.c
index 6a4232bbdf88..ae893226392d 100644
--- a/arch/powerpc/platforms/44x/ebony.c
+++ b/arch/powerpc/platforms/44x/ebony.c
@@ -28,7 +28,7 @@
 #include <asm/pci-bridge.h>
 #include <asm/ppc4xx.h>
 
-static __initdata struct of_device_id ebony_of_bus[] = {
+static const struct of_device_id ebony_of_bus[] __initconst = {
 	{ .compatible = "ibm,plb4", },
 	{ .compatible = "ibm,opb", },
 	{ .compatible = "ibm,ebc", },
diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c
index 4241bc825800..c7c6758b3cfe 100644
--- a/arch/powerpc/platforms/44x/iss4xx.c
+++ b/arch/powerpc/platforms/44x/iss4xx.c
@@ -32,7 +32,7 @@
 #include <asm/mpic.h>
 #include <asm/mmu.h>
 
-static __initdata struct of_device_id iss4xx_of_bus[] = {
+static const struct of_device_id iss4xx_of_bus[] __initconst = {
 	{ .compatible = "ibm,plb4", },
 	{ .compatible = "ibm,plb6", },
 	{ .compatible = "ibm,opb", },
diff --git a/arch/powerpc/platforms/44x/ppc44x_simple.c b/arch/powerpc/platforms/44x/ppc44x_simple.c
index 3ffb915446e3..573c3d2689c6 100644
--- a/arch/powerpc/platforms/44x/ppc44x_simple.c
+++ b/arch/powerpc/platforms/44x/ppc44x_simple.c
@@ -24,7 +24,7 @@
 #include <linux/init.h>
 #include <linux/of_platform.h>
 
-static __initdata struct of_device_id ppc44x_of_bus[] = {
+static const struct of_device_id ppc44x_of_bus[] __initconst = {
 	{ .compatible = "ibm,plb4", },
 	{ .compatible = "ibm,opb", },
 	{ .compatible = "ibm,ebc", },
diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c
index 33986c1a05da..58db9d083969 100644
--- a/arch/powerpc/platforms/44x/ppc476.c
+++ b/arch/powerpc/platforms/44x/ppc476.c
@@ -38,7 +38,7 @@
 #include <linux/pci.h>
 #include <linux/i2c.h>
 
-static struct of_device_id ppc47x_of_bus[] __initdata = {
+static const struct of_device_id ppc47x_of_bus[] __initconst = {
 	{ .compatible = "ibm,plb4", },
 	{ .compatible = "ibm,plb6", },
 	{ .compatible = "ibm,opb", },
diff --git a/arch/powerpc/platforms/44x/sam440ep.c b/arch/powerpc/platforms/44x/sam440ep.c
index 9e09b835758b..3ee4a03c1496 100644
--- a/arch/powerpc/platforms/44x/sam440ep.c
+++ b/arch/powerpc/platforms/44x/sam440ep.c
@@ -29,7 +29,7 @@
 #include <asm/ppc4xx.h>
 #include <linux/i2c.h>
 
-static __initdata struct of_device_id sam440ep_of_bus[] = {
+static const struct of_device_id sam440ep_of_bus[] __initconst = {
 	{ .compatible = "ibm,plb4", },
 	{ .compatible = "ibm,opb", },
 	{ .compatible = "ibm,ebc", },
diff --git a/arch/powerpc/platforms/44x/virtex.c b/arch/powerpc/platforms/44x/virtex.c
index cf96ccaa760c..ad272c17c640 100644
--- a/arch/powerpc/platforms/44x/virtex.c
+++ b/arch/powerpc/platforms/44x/virtex.c
@@ -21,7 +21,7 @@
 #include <asm/ppc4xx.h>
 #include "44x.h"
 
-static struct of_device_id xilinx_of_bus_ids[] __initdata = {
+static const struct of_device_id xilinx_of_bus_ids[] __initconst = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "xlnx,plb-v46-1.00.a", },
 	{ .compatible = "xlnx,plb-v46-1.02.a", },
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index 3a104284b338..501333cf42cf 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -28,7 +28,7 @@
 #include <asm/dma.h>
 
 
-static __initdata struct of_device_id warp_of_bus[] = {
+static const struct of_device_id warp_of_bus[] __initconst = {
 	{ .compatible = "ibm,plb4", },
 	{ .compatible = "ibm,opb", },
 	{ .compatible = "ibm,ebc", },
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index adb95f03d4d4..e996e007bc44 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -337,7 +337,7 @@ void __init mpc512x_init_IRQ(void)
 /*
  * Nodes to do bus probe on, soc and localbus
  */
-static struct of_device_id __initdata of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .compatible = "fsl,mpc5121-immr", },
 	{ .compatible = "fsl,mpc5121-localbus", },
 	{ .compatible = "fsl,mpc5121-mbx", },
diff --git a/arch/powerpc/platforms/52xx/lite5200.c b/arch/powerpc/platforms/52xx/lite5200.c
index 1843bc932011..7492de3cf6d0 100644
--- a/arch/powerpc/platforms/52xx/lite5200.c
+++ b/arch/powerpc/platforms/52xx/lite5200.c
@@ -34,13 +34,13 @@
  */
 
 /* mpc5200 device tree match tables */
-static struct of_device_id mpc5200_cdm_ids[] __initdata = {
+static const struct of_device_id mpc5200_cdm_ids[] __initconst = {
 	{ .compatible = "fsl,mpc5200-cdm", },
 	{ .compatible = "mpc5200-cdm", },
 	{}
 };
 
-static struct of_device_id mpc5200_gpio_ids[] __initdata = {
+static const struct of_device_id mpc5200_gpio_ids[] __initconst = {
 	{ .compatible = "fsl,mpc5200-gpio", },
 	{ .compatible = "mpc5200-gpio", },
 	{}
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 070d315dd6cd..32cae33c4266 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -30,7 +30,7 @@
 #include <asm/machdep.h>
 #include <asm/mpc52xx.h>
 
-static struct of_device_id mpc5200_gpio_ids[] __initdata = {
+static const struct of_device_id mpc5200_gpio_ids[] __initconst = {
 	{ .compatible = "fsl,mpc5200-gpio", },
 	{ .compatible = "mpc5200-gpio", },
 	{}
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c
index d7e94f49532a..26993826a797 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_common.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c
@@ -23,12 +23,12 @@
 #include <asm/mpc52xx.h>
 
 /* MPC5200 device tree match tables */
-static struct of_device_id mpc52xx_xlb_ids[] __initdata = {
+static const struct of_device_id mpc52xx_xlb_ids[] __initconst = {
 	{ .compatible = "fsl,mpc5200-xlb", },
 	{ .compatible = "mpc5200-xlb", },
 	{}
 };
-static struct of_device_id mpc52xx_bus_ids[] __initdata = {
+static const struct of_device_id mpc52xx_bus_ids[] __initconst = {
 	{ .compatible = "fsl,mpc5200-immr", },
 	{ .compatible = "fsl,mpc5200b-immr", },
 	{ .compatible = "simple-bus", },
@@ -108,21 +108,21 @@ void __init mpc52xx_declare_of_platform_devices(void)
 /*
  * match tables used by mpc52xx_map_common_devices()
  */
-static struct of_device_id mpc52xx_gpt_ids[] __initdata = {
+static const struct of_device_id mpc52xx_gpt_ids[] __initconst = {
 	{ .compatible = "fsl,mpc5200-gpt", },
 	{ .compatible = "mpc5200-gpt", }, /* old */
 	{}
 };
-static struct of_device_id mpc52xx_cdm_ids[] __initdata = {
+static const struct of_device_id mpc52xx_cdm_ids[] __initconst = {
 	{ .compatible = "fsl,mpc5200-cdm", },
 	{ .compatible = "mpc5200-cdm", }, /* old */
 	{}
 };
-static const struct of_device_id mpc52xx_gpio_simple[] = {
+static const struct of_device_id mpc52xx_gpio_simple[] __initconst = {
 	{ .compatible = "fsl,mpc5200-gpio", },
 	{}
 };
-static const struct of_device_id mpc52xx_gpio_wkup[] = {
+static const struct of_device_id mpc52xx_gpio_wkup[] __initconst = {
 	{ .compatible = "fsl,mpc5200-gpio-wkup", },
 	{}
 };
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
index 37f7a89c10f2..f8f0081759fb 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
@@ -564,7 +564,7 @@ static int mpc52xx_lpbfifo_remove(struct platform_device *op)
 	return 0;
 }
 
-static struct of_device_id mpc52xx_lpbfifo_match[] = {
+static const struct of_device_id mpc52xx_lpbfifo_match[] = {
 	{ .compatible = "fsl,mpc5200-lpbfifo", },
 	{},
 };
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index 2898b737deb7..2944bc84b9d6 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -119,12 +119,12 @@
 
 
 /* MPC5200 device tree match tables */
-static struct of_device_id mpc52xx_pic_ids[] __initdata = {
+static const struct of_device_id mpc52xx_pic_ids[] __initconst = {
 	{ .compatible = "fsl,mpc5200-pic", },
 	{ .compatible = "mpc5200-pic", },
 	{}
 };
-static struct of_device_id mpc52xx_sdma_ids[] __initdata = {
+static const struct of_device_id mpc52xx_sdma_ids[] __initconst = {
 	{ .compatible = "fsl,mpc5200-bestcomm", },
 	{ .compatible = "mpc5200-bestcomm", },
 	{}
diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c
index 79799b29ffe2..3d0c3a01143d 100644
--- a/arch/powerpc/platforms/82xx/ep8248e.c
+++ b/arch/powerpc/platforms/82xx/ep8248e.c
@@ -298,7 +298,7 @@ static void __init ep8248e_setup_arch(void)
 		ppc_md.progress("ep8248e_setup_arch(), finish", 0);
 }
 
-static  __initdata struct of_device_id of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "fsl,ep8248e-bcsr", },
 	{},
diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c
index 058cc1895c88..387b446f4161 100644
--- a/arch/powerpc/platforms/82xx/km82xx.c
+++ b/arch/powerpc/platforms/82xx/km82xx.c
@@ -180,7 +180,7 @@ static void __init km82xx_setup_arch(void)
 		ppc_md.progress("km82xx_setup_arch(), finish", 0);
 }
 
-static  __initdata struct of_device_id of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .compatible = "simple-bus", },
 	{},
 };
diff --git a/arch/powerpc/platforms/82xx/mpc8272_ads.c b/arch/powerpc/platforms/82xx/mpc8272_ads.c
index 6a14cf50f4a2..d24deacf07d0 100644
--- a/arch/powerpc/platforms/82xx/mpc8272_ads.c
+++ b/arch/powerpc/platforms/82xx/mpc8272_ads.c
@@ -181,7 +181,7 @@ static void __init mpc8272_ads_setup_arch(void)
 		ppc_md.progress("mpc8272_ads_setup_arch(), finish", 0);
 }
 
-static struct of_device_id __initdata of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .name = "soc", },
 	{ .name = "cpm", },
 	{ .name = "localbus", },
diff --git a/arch/powerpc/platforms/82xx/pq2fads.c b/arch/powerpc/platforms/82xx/pq2fads.c
index e5f82ec8df17..3a5164ad10ad 100644
--- a/arch/powerpc/platforms/82xx/pq2fads.c
+++ b/arch/powerpc/platforms/82xx/pq2fads.c
@@ -168,7 +168,7 @@ static int __init pq2fads_probe(void)
 	return of_flat_dt_is_compatible(root, "fsl,pq2fads");
 }
 
-static struct of_device_id __initdata of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .name = "soc", },
 	{ .name = "cpm", },
 	{ .name = "localbus", },
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index e238b6a55b15..463fa91ee5b6 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -141,7 +141,8 @@ static int mcu_gpiochip_add(struct mcu *mcu)
 
 static int mcu_gpiochip_remove(struct mcu *mcu)
 {
-	return gpiochip_remove(&mcu->gc);
+	gpiochip_remove(&mcu->gc);
+	return 0;
 }
 
 static int mcu_probe(struct i2c_client *client, const struct i2c_device_id *id)
@@ -213,7 +214,7 @@ static const struct i2c_device_id mcu_ids[] = {
 };
 MODULE_DEVICE_TABLE(i2c, mcu_ids);
 
-static struct of_device_id mcu_of_match_table[] = {
+static const struct of_device_id mcu_of_match_table[] = {
 	{ .compatible = "fsl,mcu-mpc8349emitx", },
 	{ },
 };
diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c
index 125336f750c6..ef9d01a049c1 100644
--- a/arch/powerpc/platforms/83xx/misc.c
+++ b/arch/powerpc/platforms/83xx/misc.c
@@ -114,7 +114,7 @@ void __init mpc83xx_ipic_and_qe_init_IRQ(void)
 }
 #endif /* CONFIG_QUICC_ENGINE */
 
-static struct of_device_id __initdata of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .type = "soc", },
 	{ .compatible = "soc", },
 	{ .compatible = "simple-bus" },
diff --git a/arch/powerpc/platforms/83xx/mpc834x_itx.c b/arch/powerpc/platforms/83xx/mpc834x_itx.c
index a494fa57bdf9..80aea8c4b5a3 100644
--- a/arch/powerpc/platforms/83xx/mpc834x_itx.c
+++ b/arch/powerpc/platforms/83xx/mpc834x_itx.c
@@ -38,7 +38,7 @@
 
 #include "mpc83xx.h"
 
-static struct of_device_id __initdata mpc834x_itx_ids[] = {
+static const struct of_device_id mpc834x_itx_ids[] __initconst = {
 	{ .compatible = "fsl,pq2pro-localbus", },
 	{},
 };
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index 4b4c081df94d..eeb80e25214d 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -321,7 +321,7 @@ static const struct platform_suspend_ops mpc83xx_suspend_ops = {
 	.end = mpc83xx_suspend_end,
 };
 
-static struct of_device_id pmc_match[];
+static const struct of_device_id pmc_match[];
 static int pmc_probe(struct platform_device *ofdev)
 {
 	const struct of_device_id *match;
@@ -420,7 +420,7 @@ static struct pmc_type pmc_types[] = {
 	}
 };
 
-static struct of_device_id pmc_match[] = {
+static const struct of_device_id pmc_match[] = {
 	{
 		.compatible = "fsl,mpc8313-pmc",
 		.data = &pmc_types[0],
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 0c1e6903597e..f22635a71d01 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -276,7 +276,7 @@ config CORENET_GENERIC
 	  For 64bit kernel, the following boards are supported:
 	    T208x QDS/RDB, T4240 QDS/RDB and B4 QDS
 	  The following boards are supported for both 32bit and 64bit kernel:
-	    P5020 DS, P5040 DS and T104xQDS
+	    P5020 DS, P5040 DS and T104xQDS/RDB
 
 endif # FSL_SOC_BOOKE
 
diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c
index b564b5e23f7c..4a9ad871a168 100644
--- a/arch/powerpc/platforms/85xx/common.c
+++ b/arch/powerpc/platforms/85xx/common.c
@@ -14,7 +14,7 @@
 
 #include "mpc85xx.h"
 
-static struct of_device_id __initdata mpc85xx_common_ids[] = {
+static const struct of_device_id mpc85xx_common_ids[] __initconst = {
 	{ .type = "soc", },
 	{ .compatible = "soc", },
 	{ .compatible = "simple-bus", },
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index d22dd85e50bf..e56b89a792ed 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -20,6 +20,7 @@
 #include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/pci-bridge.h>
+#include <asm/pgtable.h>
 #include <asm/ppc-pci.h>
 #include <mm/mmu_decl.h>
 #include <asm/prom.h>
@@ -67,6 +68,16 @@ void __init corenet_gen_setup_arch(void)
 
 	swiotlb_detect_4g();
 
+#if defined(CONFIG_FSL_PCI) && defined(CONFIG_ZONE_DMA32)
+	/*
+	 * Inbound windows don't cover the full lower 4 GiB
+	 * due to conflicts with PCICSRBAR and outbound windows,
+	 * so limit the DMA32 zone to 2 GiB, to allow consistent
+	 * allocations to succeed.
+	 */
+	limit_zone_pfn(ZONE_DMA32, 1UL << (31 - PAGE_SHIFT));
+#endif
+
 	pr_info("%s board\n", ppc_md.name);
 
 	mpc85xx_qe_init();
@@ -129,6 +140,9 @@ static const char * const boards[] __initconst = {
 	"fsl,B4220QDS",
 	"fsl,T1040QDS",
 	"fsl,T1042QDS",
+	"fsl,T1040RDB",
+	"fsl,T1042RDB",
+	"fsl,T1042RDB_PI",
 	"keymile,kmcoge4",
 	NULL
 };
diff --git a/arch/powerpc/platforms/85xx/ppa8548.c b/arch/powerpc/platforms/85xx/ppa8548.c
index 3daff7c63569..12019f17f297 100644
--- a/arch/powerpc/platforms/85xx/ppa8548.c
+++ b/arch/powerpc/platforms/85xx/ppa8548.c
@@ -59,7 +59,7 @@ static void ppa8548_show_cpuinfo(struct seq_file *m)
 	seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f));
 }
 
-static struct of_device_id __initdata of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .name = "soc", },
 	{ .type = "soc", },
 	{ .compatible = "simple-bus", },
diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c
index 7f2673293549..8ad2fe6f200a 100644
--- a/arch/powerpc/platforms/85xx/qemu_e500.c
+++ b/arch/powerpc/platforms/85xx/qemu_e500.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/of_fdt.h>
 #include <asm/machdep.h>
+#include <asm/pgtable.h>
 #include <asm/time.h>
 #include <asm/udbg.h>
 #include <asm/mpic.h>
@@ -44,6 +45,15 @@ static void __init qemu_e500_setup_arch(void)
 
 	fsl_pci_assign_primary();
 	swiotlb_detect_4g();
+#if defined(CONFIG_FSL_PCI) && defined(CONFIG_ZONE_DMA32)
+	/*
+	 * Inbound windows don't cover the full lower 4 GiB
+	 * due to conflicts with PCICSRBAR and outbound windows,
+	 * so limit the DMA32 zone to 2 GiB, to allow consistent
+	 * allocations to succeed.
+	 */
+	limit_zone_pfn(ZONE_DMA32, 1UL << (31 - PAGE_SHIFT));
+#endif
 	mpc85xx_smp_init();
 }
 
diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c
index bb75add67084..8162b0412117 100644
--- a/arch/powerpc/platforms/85xx/sgy_cts1000.c
+++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c
@@ -24,7 +24,7 @@
 
 static struct device_node *halt_node;
 
-static struct of_device_id child_match[] = {
+static const struct of_device_id child_match[] = {
 	{
 		.compatible = "sgy,gpio-halt",
 	},
@@ -147,7 +147,7 @@ static int gpio_halt_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct of_device_id gpio_halt_match[] = {
+static const struct of_device_id gpio_halt_match[] = {
 	/* We match on the gpio bus itself and scan the children since they
 	 * wont be matched against us. We know the bus wont match until it
 	 * has been registered too. */
diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c
index c23f3443880a..bf17933b20f3 100644
--- a/arch/powerpc/platforms/86xx/gef_ppc9a.c
+++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c
@@ -213,7 +213,7 @@ static long __init mpc86xx_time_init(void)
 	return 0;
 }
 
-static __initdata struct of_device_id of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "gianfar", },
 	{ .compatible = "fsl,mpc8641-pcie", },
diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c
index 8a6ac20686ea..8facf5873866 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc310.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc310.c
@@ -200,7 +200,7 @@ static long __init mpc86xx_time_init(void)
 	return 0;
 }
 
-static __initdata struct of_device_id of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "gianfar", },
 	{ .compatible = "fsl,mpc8641-pcie", },
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index 06c72636f299..8c9058df5642 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -190,7 +190,7 @@ static long __init mpc86xx_time_init(void)
 	return 0;
 }
 
-static __initdata struct of_device_id of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "gianfar", },
 	{ .compatible = "fsl,mpc8641-pcie", },
diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
index d479d68fbb2b..55413a547ea8 100644
--- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
+++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
@@ -85,7 +85,7 @@ static void __init mpc8610_suspend_init(void)
 static inline void mpc8610_suspend_init(void) { }
 #endif /* CONFIG_SUSPEND */
 
-static struct of_device_id __initdata mpc8610_ids[] = {
+static const struct of_device_id mpc8610_ids[] __initconst = {
 	{ .compatible = "fsl,mpc8610-immr", },
 	{ .compatible = "fsl,mpc8610-guts", },
 	{ .compatible = "simple-bus", },
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index e8bf3fae5606..07ccb1b0cc7d 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -127,7 +127,7 @@ mpc86xx_time_init(void)
 	return 0;
 }
 
-static __initdata struct of_device_id of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "fsl,srio", },
 	{ .compatible = "gianfar", },
diff --git a/arch/powerpc/platforms/86xx/sbc8641d.c b/arch/powerpc/platforms/86xx/sbc8641d.c
index b47a8fd0f3d3..6810b71d54a7 100644
--- a/arch/powerpc/platforms/86xx/sbc8641d.c
+++ b/arch/powerpc/platforms/86xx/sbc8641d.c
@@ -92,7 +92,7 @@ mpc86xx_time_init(void)
 	return 0;
 }
 
-static __initdata struct of_device_id of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "gianfar", },
 	{ .compatible = "fsl,mpc8641-pcie", },
diff --git a/arch/powerpc/platforms/8xx/adder875.c b/arch/powerpc/platforms/8xx/adder875.c
index 82363e98f50e..61cae4c1edb8 100644
--- a/arch/powerpc/platforms/8xx/adder875.c
+++ b/arch/powerpc/platforms/8xx/adder875.c
@@ -92,7 +92,7 @@ static int __init adder875_probe(void)
 	return of_flat_dt_is_compatible(root, "analogue-and-micro,adder875");
 }
 
-static __initdata struct of_device_id of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .compatible = "simple-bus", },
 	{},
 };
diff --git a/arch/powerpc/platforms/8xx/ep88xc.c b/arch/powerpc/platforms/8xx/ep88xc.c
index e62166681d08..2bedeb7d5f8f 100644
--- a/arch/powerpc/platforms/8xx/ep88xc.c
+++ b/arch/powerpc/platforms/8xx/ep88xc.c
@@ -147,7 +147,7 @@ static int __init ep88xc_probe(void)
 	return of_flat_dt_is_compatible(root, "fsl,ep88xc");
 }
 
-static struct of_device_id __initdata of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .name = "soc", },
 	{ .name = "cpm", },
 	{ .name = "localbus", },
diff --git a/arch/powerpc/platforms/8xx/mpc86xads_setup.c b/arch/powerpc/platforms/8xx/mpc86xads_setup.c
index 63084640c5c5..78180c5e73ff 100644
--- a/arch/powerpc/platforms/8xx/mpc86xads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc86xads_setup.c
@@ -122,7 +122,7 @@ static int __init mpc86xads_probe(void)
 	return of_flat_dt_is_compatible(root, "fsl,mpc866ads");
 }
 
-static struct of_device_id __initdata of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .name = "soc", },
 	{ .name = "cpm", },
 	{ .name = "localbus", },
diff --git a/arch/powerpc/platforms/8xx/mpc885ads_setup.c b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
index 5921dcb498fd..4d62bf9dc789 100644
--- a/arch/powerpc/platforms/8xx/mpc885ads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
@@ -197,7 +197,7 @@ static int __init mpc885ads_probe(void)
 	return of_flat_dt_is_compatible(root, "fsl,mpc885ads");
 }
 
-static struct of_device_id __initdata of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .name = "soc", },
 	{ .name = "cpm", },
 	{ .name = "localbus", },
diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
index dda607807def..bee47a2b23e6 100644
--- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
@@ -124,7 +124,7 @@ static int __init tqm8xx_probe(void)
 	return of_flat_dt_is_compatible(node, "tqc,tqm8xx");
 }
 
-static struct of_device_id __initdata of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .name = "soc", },
 	{ .name = "cpm", },
 	{ .name = "localbus", },
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 7d9ee3d8c618..76483e3acd60 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -116,6 +116,12 @@ config POWER6_CPU
 config POWER7_CPU
 	bool "POWER7"
 	depends on PPC_BOOK3S_64
+	select ARCH_HAS_FAST_MULTIPLIER
+
+config POWER8_CPU
+	bool "POWER8"
+	depends on PPC_BOOK3S_64
+	select ARCH_HAS_FAST_MULTIPLIER
 
 config E5500_CPU
 	bool "Freescale e5500"
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 9978f594cac0..870b6dbd4d18 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -86,6 +86,7 @@ config SPU_FS_64K_LS
 config SPU_BASE
 	bool
 	default n
+	select PPC_COPRO_BASE
 
 config CBE_RAS
 	bool "RAS features for bare metal Cell BE"
diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile
index fe053e7c73ee..2d16884f67b9 100644
--- a/arch/powerpc/platforms/cell/Makefile
+++ b/arch/powerpc/platforms/cell/Makefile
@@ -20,7 +20,7 @@ spu-manage-$(CONFIG_PPC_CELL_COMMON)	+= spu_manage.o
 
 obj-$(CONFIG_SPU_BASE)			+= spu_callbacks.o spu_base.o \
 					   spu_notify.o \
-					   spu_syscalls.o spu_fault.o \
+					   spu_syscalls.o \
 					   $(spu-priv1-y) \
 					   $(spu-manage-y) \
 					   spufs/
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 85825b5401e5..862b32702d29 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -199,14 +199,6 @@ out_error:
 	return msic;
 }
 
-static int axon_msi_check_device(struct pci_dev *dev, int nvec, int type)
-{
-	if (!find_msi_translator(dev))
-		return -ENODEV;
-
-	return 0;
-}
-
 static int setup_msi_msg_address(struct pci_dev *dev, struct msi_msg *msg)
 {
 	struct device_node *dn;
@@ -416,7 +408,6 @@ static int axon_msi_probe(struct platform_device *device)
 
 	ppc_md.setup_msi_irqs = axon_msi_setup_msi_irqs;
 	ppc_md.teardown_msi_irqs = axon_msi_teardown_msi_irqs;
-	ppc_md.msi_check_device = axon_msi_check_device;
 
 	axon_msi_debug_setup(dn, msic);
 
diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c
index 173568140a32..2b98a36ef8fb 100644
--- a/arch/powerpc/platforms/cell/celleb_pci.c
+++ b/arch/powerpc/platforms/cell/celleb_pci.c
@@ -454,7 +454,7 @@ static struct celleb_phb_spec celleb_fake_pci_spec __initdata = {
 	.setup = celleb_setup_fake_pci,
 };
 
-static struct of_device_id celleb_phb_match[] __initdata = {
+static const struct of_device_id celleb_phb_match[] __initconst = {
 	{
 		.name = "pci-pseudo",
 		.data = &celleb_fake_pci_spec,
diff --git a/arch/powerpc/platforms/cell/celleb_setup.c b/arch/powerpc/platforms/cell/celleb_setup.c
index 1d5a4d8ddad9..34e8ce2976aa 100644
--- a/arch/powerpc/platforms/cell/celleb_setup.c
+++ b/arch/powerpc/platforms/cell/celleb_setup.c
@@ -102,7 +102,7 @@ static void __init celleb_setup_arch_common(void)
 #endif
 }
 
-static struct of_device_id celleb_bus_ids[] __initdata = {
+static const struct of_device_id celleb_bus_ids[] __initconst = {
 	{ .type = "scc", },
 	{ .type = "ioif", },	/* old style */
 	{},
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 2930d1e81a05..ffcbd242e669 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -76,10 +76,6 @@ static LIST_HEAD(spu_full_list);
 static DEFINE_SPINLOCK(spu_full_list_lock);
 static DEFINE_MUTEX(spu_full_list_mutex);
 
-struct spu_slb {
-	u64 esid, vsid;
-};
-
 void spu_invalidate_slbs(struct spu *spu)
 {
 	struct spu_priv2 __iomem *priv2 = spu->priv2;
@@ -149,7 +145,7 @@ static void spu_restart_dma(struct spu *spu)
 	}
 }
 
-static inline void spu_load_slb(struct spu *spu, int slbe, struct spu_slb *slb)
+static inline void spu_load_slb(struct spu *spu, int slbe, struct copro_slb *slb)
 {
 	struct spu_priv2 __iomem *priv2 = spu->priv2;
 
@@ -167,45 +163,12 @@ static inline void spu_load_slb(struct spu *spu, int slbe, struct spu_slb *slb)
 
 static int __spu_trap_data_seg(struct spu *spu, unsigned long ea)
 {
-	struct mm_struct *mm = spu->mm;
-	struct spu_slb slb;
-	int psize;
-
-	pr_debug("%s\n", __func__);
-
-	slb.esid = (ea & ESID_MASK) | SLB_ESID_V;
+	struct copro_slb slb;
+	int ret;
 
-	switch(REGION_ID(ea)) {
-	case USER_REGION_ID:
-#ifdef CONFIG_PPC_MM_SLICES
-		psize = get_slice_psize(mm, ea);
-#else
-		psize = mm->context.user_psize;
-#endif
-		slb.vsid = (get_vsid(mm->context.id, ea, MMU_SEGSIZE_256M)
-				<< SLB_VSID_SHIFT) | SLB_VSID_USER;
-		break;
-	case VMALLOC_REGION_ID:
-		if (ea < VMALLOC_END)
-			psize = mmu_vmalloc_psize;
-		else
-			psize = mmu_io_psize;
-		slb.vsid = (get_kernel_vsid(ea, MMU_SEGSIZE_256M)
-				<< SLB_VSID_SHIFT) | SLB_VSID_KERNEL;
-		break;
-	case KERNEL_REGION_ID:
-		psize = mmu_linear_psize;
-		slb.vsid = (get_kernel_vsid(ea, MMU_SEGSIZE_256M)
-				<< SLB_VSID_SHIFT) | SLB_VSID_KERNEL;
-		break;
-	default:
-		/* Future: support kernel segments so that drivers
-		 * can use SPUs.
-		 */
-		pr_debug("invalid region access at %016lx\n", ea);
-		return 1;
-	}
-	slb.vsid |= mmu_psize_defs[psize].sllp;
+	ret = copro_calculate_slb(spu->mm, ea, &slb);
+	if (ret)
+		return ret;
 
 	spu_load_slb(spu, spu->slb_replace, &slb);
 
@@ -253,7 +216,7 @@ static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
 	return 0;
 }
 
-static void __spu_kernel_slb(void *addr, struct spu_slb *slb)
+static void __spu_kernel_slb(void *addr, struct copro_slb *slb)
 {
 	unsigned long ea = (unsigned long)addr;
 	u64 llp;
@@ -272,7 +235,7 @@ static void __spu_kernel_slb(void *addr, struct spu_slb *slb)
  * Given an array of @nr_slbs SLB entries, @slbs, return non-zero if the
  * address @new_addr is present.
  */
-static inline int __slb_present(struct spu_slb *slbs, int nr_slbs,
+static inline int __slb_present(struct copro_slb *slbs, int nr_slbs,
 		void *new_addr)
 {
 	unsigned long ea = (unsigned long)new_addr;
@@ -297,7 +260,7 @@ static inline int __slb_present(struct spu_slb *slbs, int nr_slbs,
 void spu_setup_kernel_slbs(struct spu *spu, struct spu_lscsa *lscsa,
 		void *code, int code_size)
 {
-	struct spu_slb slbs[4];
+	struct copro_slb slbs[4];
 	int i, nr_slbs = 0;
 	/* start and end addresses of both mappings */
 	void *addrs[] = {
diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c
index 8cb6260cc80f..e45894a08118 100644
--- a/arch/powerpc/platforms/cell/spufs/fault.c
+++ b/arch/powerpc/platforms/cell/spufs/fault.c
@@ -138,7 +138,7 @@ int spufs_handle_class1(struct spu_context *ctx)
 	if (ctx->state == SPU_STATE_RUNNABLE)
 		ctx->spu->stats.hash_flt++;
 
-	/* we must not hold the lock when entering spu_handle_mm_fault */
+	/* we must not hold the lock when entering copro_handle_mm_fault */
 	spu_release(ctx);
 
 	access = (_PAGE_PRESENT | _PAGE_USER);
@@ -149,7 +149,7 @@ int spufs_handle_class1(struct spu_context *ctx)
 
 	/* hashing failed, so try the actual fault handler */
 	if (ret)
-		ret = spu_handle_mm_fault(current->mm, ea, dsisr, &flt);
+		ret = copro_handle_mm_fault(current->mm, ea, dsisr, &flt);
 
 	/*
 	 * This is nasty: we need the state_mutex for all the bookkeeping even
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index 7044fd36197b..5b77b1919fd2 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -258,7 +258,7 @@ static void chrp_init_early(void)
 	struct device_node *node;
 	const char *property;
 
-	if (strstr(cmd_line, "console="))
+	if (strstr(boot_command_line, "console="))
 		return;
 	/* find the boot console from /chosen/stdout */
 	if (!of_chosen)
diff --git a/arch/powerpc/platforms/embedded6xx/gamecube.c b/arch/powerpc/platforms/embedded6xx/gamecube.c
index a138e14bad2e..bd4ba5d7d568 100644
--- a/arch/powerpc/platforms/embedded6xx/gamecube.c
+++ b/arch/powerpc/platforms/embedded6xx/gamecube.c
@@ -90,7 +90,7 @@ define_machine(gamecube) {
 };
 
 
-static struct of_device_id gamecube_of_bus[] = {
+static const struct of_device_id gamecube_of_bus[] = {
 	{ .compatible = "nintendo,flipper", },
 	{ },
 };
diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c
index 455e7c087422..168e1d80b2e5 100644
--- a/arch/powerpc/platforms/embedded6xx/linkstation.c
+++ b/arch/powerpc/platforms/embedded6xx/linkstation.c
@@ -21,7 +21,7 @@
 
 #include "mpc10x.h"
 
-static __initdata struct of_device_id of_bus_ids[] = {
+static const struct of_device_id of_bus_ids[] __initconst = {
 	{ .type = "soc", },
 	{ .compatible = "simple-bus", },
 	{},
diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c
index 25e3bfb64efb..1613303177e6 100644
--- a/arch/powerpc/platforms/embedded6xx/mvme5100.c
+++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c
@@ -149,7 +149,7 @@ static int __init mvme5100_add_bridge(struct device_node *dev)
 	return 0;
 }
 
-static struct of_device_id mvme5100_of_bus_ids[] __initdata = {
+static const struct of_device_id mvme5100_of_bus_ids[] __initconst = {
 	{ .compatible = "hawk-bridge", },
 	{},
 };
diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c b/arch/powerpc/platforms/embedded6xx/storcenter.c
index c458b60d14c4..d572833ebd00 100644
--- a/arch/powerpc/platforms/embedded6xx/storcenter.c
+++ b/arch/powerpc/platforms/embedded6xx/storcenter.c
@@ -24,7 +24,7 @@
 #include "mpc10x.h"
 
 
-static __initdata struct of_device_id storcenter_of_bus[] = {
+static const struct of_device_id storcenter_of_bus[] __initconst = {
 	{ .name = "soc", },
 	{},
 };
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index 6d8dadf19f0b..388e29bab8f6 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -235,7 +235,7 @@ define_machine(wii) {
 	.machine_shutdown	= wii_shutdown,
 };
 
-static struct of_device_id wii_of_bus[] = {
+static const struct of_device_id wii_of_bus[] = {
 	{ .compatible = "nintendo,hollywood", },
 	{ },
 };
diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c
index 15adee544638..ada33358950d 100644
--- a/arch/powerpc/platforms/pasemi/gpio_mdio.c
+++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c
@@ -290,7 +290,7 @@ static int gpio_mdio_remove(struct platform_device *dev)
 	return 0;
 }
 
-static struct of_device_id gpio_mdio_match[] =
+static const struct of_device_id gpio_mdio_match[] =
 {
 	{
 		.compatible      = "gpio-mdio",
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index 8c54de6d8ec4..d71b2c7e8403 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -393,7 +393,7 @@ static inline void pasemi_pcmcia_init(void)
 #endif
 
 
-static struct of_device_id pasemi_bus_ids[] = {
+static const struct of_device_id pasemi_bus_ids[] = {
 	/* Unfortunately needed for legacy firmwares */
 	{ .type = "localbus", },
 	{ .type = "sdc", },
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 141f8899a633..b127a29ac526 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -336,7 +336,7 @@ static void __init pmac_setup_arch(void)
 #endif
 
 #ifdef CONFIG_ADB
-	if (strstr(cmd_line, "adb_sync")) {
+	if (strstr(boot_command_line, "adb_sync")) {
 		extern int __adb_probe_sync;
 		__adb_probe_sync = 1;
 	}
@@ -460,7 +460,7 @@ pmac_halt(void)
 static void __init pmac_init_early(void)
 {
 	/* Enable early btext debug if requested */
-	if (strstr(cmd_line, "btextdbg")) {
+	if (strstr(boot_command_line, "btextdbg")) {
 		udbg_adb_init_early();
 		register_early_udbg_console();
 	}
@@ -469,8 +469,8 @@ static void __init pmac_init_early(void)
 	pmac_feature_init();
 
 	/* Initialize debug stuff */
-	udbg_scc_init(!!strstr(cmd_line, "sccdbg"));
-	udbg_adb_init(!!strstr(cmd_line, "btextdbg"));
+	udbg_scc_init(!!strstr(boot_command_line, "sccdbg"));
+	udbg_adb_init(!!strstr(boot_command_line, "btextdbg"));
 
 #ifdef CONFIG_PPC64
 	iommu_init_early_dart();
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index c945bed4dc9e..426814a2ede3 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -66,6 +66,54 @@ static struct notifier_block ioda_eeh_nb = {
 };
 
 #ifdef CONFIG_DEBUG_FS
+static ssize_t ioda_eeh_ei_write(struct file *filp,
+				 const char __user *user_buf,
+				 size_t count, loff_t *ppos)
+{
+	struct pci_controller *hose = filp->private_data;
+	struct pnv_phb *phb = hose->private_data;
+	struct eeh_dev *edev;
+	struct eeh_pe *pe;
+	int pe_no, type, func;
+	unsigned long addr, mask;
+	char buf[50];
+	int ret;
+
+	if (!phb->eeh_ops || !phb->eeh_ops->err_inject)
+		return -ENXIO;
+
+	ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count);
+	if (!ret)
+		return -EFAULT;
+
+	/* Retrieve parameters */
+	ret = sscanf(buf, "%x:%x:%x:%lx:%lx",
+		     &pe_no, &type, &func, &addr, &mask);
+	if (ret != 5)
+		return -EINVAL;
+
+	/* Retrieve PE */
+	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
+	if (!edev)
+		return -ENOMEM;
+	edev->phb = hose;
+	edev->pe_config_addr = pe_no;
+	pe = eeh_pe_get(edev);
+	kfree(edev);
+	if (!pe)
+		return -ENODEV;
+
+	/* Do error injection */
+	ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask);
+	return ret < 0 ? ret : count;
+}
+
+static const struct file_operations ioda_eeh_ei_fops = {
+	.open   = simple_open,
+	.llseek = no_llseek,
+	.write  = ioda_eeh_ei_write,
+};
+
 static int ioda_eeh_dbgfs_set(void *data, int offset, u64 val)
 {
 	struct pci_controller *hose = data;
@@ -152,6 +200,10 @@ static int ioda_eeh_post_init(struct pci_controller *hose)
 	if (!phb->has_dbgfs && phb->dbgfs) {
 		phb->has_dbgfs = 1;
 
+		debugfs_create_file("err_injct", 0200,
+				    phb->dbgfs, hose,
+				    &ioda_eeh_ei_fops);
+
 		debugfs_create_file("err_injct_outbound", 0600,
 				    phb->dbgfs, hose,
 				    &ioda_eeh_outb_dbgfs_ops);
@@ -189,6 +241,7 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
+	bool freeze_pe = false;
 	int enable, ret = 0;
 	s64 rc;
 
@@ -212,6 +265,10 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
 	case EEH_OPT_THAW_DMA:
 		enable = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA;
 		break;
+	case EEH_OPT_FREEZE_PE:
+		freeze_pe = true;
+		enable = OPAL_EEH_ACTION_SET_FREEZE_ALL;
+		break;
 	default:
 		pr_warn("%s: Invalid option %d\n",
 			__func__, option);
@@ -219,17 +276,35 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
 	}
 
 	/* If PHB supports compound PE, to handle it */
-	if (phb->unfreeze_pe) {
-		ret = phb->unfreeze_pe(phb, pe->addr, enable);
+	if (freeze_pe) {
+		if (phb->freeze_pe) {
+			phb->freeze_pe(phb, pe->addr);
+		} else {
+			rc = opal_pci_eeh_freeze_set(phb->opal_id,
+						     pe->addr,
+						     enable);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld freezing "
+					"PHB#%x-PE#%x\n",
+					__func__, rc,
+					phb->hose->global_number, pe->addr);
+				ret = -EIO;
+			}
+		}
 	} else {
-		rc = opal_pci_eeh_freeze_clear(phb->opal_id,
-					       pe->addr,
-					       enable);
-		if (rc != OPAL_SUCCESS) {
-			pr_warn("%s: Failure %lld enable %d for PHB#%x-PE#%x\n",
-				__func__, rc, option, phb->hose->global_number,
-				pe->addr);
-			ret = -EIO;
+		if (phb->unfreeze_pe) {
+			ret = phb->unfreeze_pe(phb, pe->addr, enable);
+		} else {
+			rc = opal_pci_eeh_freeze_clear(phb->opal_id,
+						       pe->addr,
+						       enable);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld enable %d "
+					"for PHB#%x-PE#%x\n",
+					__func__, rc, option,
+					phb->hose->global_number, pe->addr);
+				ret = -EIO;
+			}
 		}
 	}
 
@@ -439,11 +514,11 @@ int ioda_eeh_phb_reset(struct pci_controller *hose, int option)
 	if (option == EEH_RESET_FUNDAMENTAL ||
 	    option == EEH_RESET_HOT)
 		rc = opal_pci_reset(phb->opal_id,
-				OPAL_PHB_COMPLETE,
+				OPAL_RESET_PHB_COMPLETE,
 				OPAL_ASSERT_RESET);
 	else if (option == EEH_RESET_DEACTIVATE)
 		rc = opal_pci_reset(phb->opal_id,
-				OPAL_PHB_COMPLETE,
+				OPAL_RESET_PHB_COMPLETE,
 				OPAL_DEASSERT_RESET);
 	if (rc < 0)
 		goto out;
@@ -483,15 +558,15 @@ static int ioda_eeh_root_reset(struct pci_controller *hose, int option)
 	 */
 	if (option == EEH_RESET_FUNDAMENTAL)
 		rc = opal_pci_reset(phb->opal_id,
-				OPAL_PCI_FUNDAMENTAL_RESET,
+				OPAL_RESET_PCI_FUNDAMENTAL,
 				OPAL_ASSERT_RESET);
 	else if (option == EEH_RESET_HOT)
 		rc = opal_pci_reset(phb->opal_id,
-				OPAL_PCI_HOT_RESET,
+				OPAL_RESET_PCI_HOT,
 				OPAL_ASSERT_RESET);
 	else if (option == EEH_RESET_DEACTIVATE)
 		rc = opal_pci_reset(phb->opal_id,
-				OPAL_PCI_HOT_RESET,
+				OPAL_RESET_PCI_HOT,
 				OPAL_DEASSERT_RESET);
 	if (rc < 0)
 		goto out;
@@ -607,6 +682,31 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 	if (pe->type & EEH_PE_PHB) {
 		ret = ioda_eeh_phb_reset(hose, option);
 	} else {
+		struct pnv_phb *phb;
+		s64 rc;
+
+		/*
+		 * The frozen PE might be caused by PAPR error injection
+		 * registers, which are expected to be cleared after hitting
+		 * frozen PE as stated in the hardware spec. Unfortunately,
+		 * that's not true on P7IOC. So we have to clear it manually
+		 * to avoid recursive EEH errors during recovery.
+		 */
+		phb = hose->private_data;
+		if (phb->model == PNV_PHB_MODEL_P7IOC &&
+		    (option == EEH_RESET_HOT ||
+		    option == EEH_RESET_FUNDAMENTAL)) {
+			rc = opal_pci_reset(phb->opal_id,
+					    OPAL_RESET_PHB_ERROR,
+					    OPAL_ASSERT_RESET);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld clearing "
+					"error injection registers\n",
+					__func__, rc);
+				return -EIO;
+			}
+		}
+
 		bus = eeh_pe_bus_get(pe);
 		if (pci_is_root_bus(bus) ||
 		    pci_is_root_bus(bus->parent))
@@ -628,8 +728,8 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
  * Retrieve error log, which contains log from device driver
  * and firmware.
  */
-int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
-		     char *drv_log, unsigned long len)
+static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
+			    char *drv_log, unsigned long len)
 {
 	pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 
@@ -650,6 +750,49 @@ static int ioda_eeh_configure_bridge(struct eeh_pe *pe)
 	return 0;
 }
 
+static int ioda_eeh_err_inject(struct eeh_pe *pe, int type, int func,
+			       unsigned long addr, unsigned long mask)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	s64 ret;
+
+	/* Sanity check on error type */
+	if (type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR &&
+	    type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64) {
+		pr_warn("%s: Invalid error type %d\n",
+			__func__, type);
+		return -ERANGE;
+	}
+
+	if (func < OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR ||
+	    func > OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET) {
+		pr_warn("%s: Invalid error function %d\n",
+			__func__, func);
+		return -ERANGE;
+	}
+
+	/* Firmware supports error injection ? */
+	if (!opal_check_token(OPAL_PCI_ERR_INJECT)) {
+		pr_warn("%s: Firmware doesn't support error injection\n",
+			__func__);
+		return -ENXIO;
+	}
+
+	/* Do error injection */
+	ret = opal_pci_err_inject(phb->opal_id, pe->addr,
+				  type, func, addr, mask);
+	if (ret != OPAL_SUCCESS) {
+		pr_warn("%s: Failure %lld injecting error "
+			"%d-%d to PHB#%x-PE#%x\n",
+			__func__, ret, type, func,
+			hose->global_number, pe->addr);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data)
 {
 	/* GEM */
@@ -743,14 +886,12 @@ static int ioda_eeh_get_pe(struct pci_controller *hose,
 	 * the master PE because slave PE is invisible
 	 * to EEH core.
 	 */
-	if (phb->get_pe_state) {
-		pnv_pe = &phb->ioda.pe_array[pe_no];
-		if (pnv_pe->flags & PNV_IODA_PE_SLAVE) {
-			pnv_pe = pnv_pe->master;
-			WARN_ON(!pnv_pe ||
-				!(pnv_pe->flags & PNV_IODA_PE_MASTER));
-			pe_no = pnv_pe->pe_number;
-		}
+	pnv_pe = &phb->ioda.pe_array[pe_no];
+	if (pnv_pe->flags & PNV_IODA_PE_SLAVE) {
+		pnv_pe = pnv_pe->master;
+		WARN_ON(!pnv_pe ||
+			!(pnv_pe->flags & PNV_IODA_PE_MASTER));
+		pe_no = pnv_pe->pe_number;
 	}
 
 	/* Find the PE according to PE# */
@@ -761,15 +902,37 @@ static int ioda_eeh_get_pe(struct pci_controller *hose,
 	if (!dev_pe)
 		return -EEXIST;
 
-	/*
-	 * At this point, we're sure the compound PE should
-	 * be put into frozen state.
-	 */
+	/* Freeze the (compound) PE */
 	*pe = dev_pe;
-	if (phb->freeze_pe &&
-	    !(dev_pe->state & EEH_PE_ISOLATED))
+	if (!(dev_pe->state & EEH_PE_ISOLATED))
 		phb->freeze_pe(phb, pe_no);
 
+	/*
+	 * At this point, we're sure the (compound) PE should
+	 * have been frozen. However, we still need poke until
+	 * hitting the frozen PE on top level.
+	 */
+	dev_pe = dev_pe->parent;
+	while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) {
+		int ret;
+		int active_flags = (EEH_STATE_MMIO_ACTIVE |
+				    EEH_STATE_DMA_ACTIVE);
+
+		ret = eeh_ops->get_state(dev_pe, NULL);
+		if (ret <= 0 || (ret & active_flags) == active_flags) {
+			dev_pe = dev_pe->parent;
+			continue;
+		}
+
+		/* Frozen parent PE */
+		*pe = dev_pe;
+		if (!(dev_pe->state & EEH_PE_ISOLATED))
+			phb->freeze_pe(phb, dev_pe->addr);
+
+		/* Next one */
+		dev_pe = dev_pe->parent;
+	}
+
 	return 0;
 }
 
@@ -971,5 +1134,6 @@ struct pnv_eeh_ops ioda_eeh_ops = {
 	.reset			= ioda_eeh_reset,
 	.get_log		= ioda_eeh_get_log,
 	.configure_bridge	= ioda_eeh_configure_bridge,
+	.err_inject		= ioda_eeh_err_inject,
 	.next_error		= ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index fd7a16f855ed..3e89cbf55885 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -359,6 +359,31 @@ static int powernv_eeh_configure_bridge(struct eeh_pe *pe)
 }
 
 /**
+ * powernv_pe_err_inject - Inject specified error to the indicated PE
+ * @pe: the indicated PE
+ * @type: error type
+ * @func: specific error type
+ * @addr: address
+ * @mask: address mask
+ *
+ * The routine is called to inject specified error, which is
+ * determined by @type and @func, to the indicated PE for
+ * testing purpose.
+ */
+static int powernv_eeh_err_inject(struct eeh_pe *pe, int type, int func,
+				  unsigned long addr, unsigned long mask)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = -EEXIST;
+
+	if (phb->eeh_ops && phb->eeh_ops->err_inject)
+		ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask);
+
+	return ret;
+}
+
+/**
  * powernv_eeh_next_error - Retrieve next EEH error to handle
  * @pe: Affected PE
  *
@@ -414,6 +439,7 @@ static struct eeh_ops powernv_eeh_ops = {
 	.wait_state             = powernv_eeh_wait_state,
 	.get_log                = powernv_eeh_get_log,
 	.configure_bridge       = powernv_eeh_configure_bridge,
+	.err_inject		= powernv_eeh_err_inject,
 	.read_config            = pnv_pci_cfg_read,
 	.write_config           = pnv_pci_cfg_write,
 	.next_error		= powernv_eeh_next_error,
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 85bb8fff7947..23260f7dfa7a 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -112,7 +112,7 @@ static ssize_t init_dump_show(struct dump_obj *dump_obj,
 			      struct dump_attribute *attr,
 			      char *buf)
 {
-	return sprintf(buf, "1 - initiate dump\n");
+	return sprintf(buf, "1 - initiate Service Processor(FSP) dump\n");
 }
 
 static int64_t dump_fips_init(uint8_t type)
@@ -121,7 +121,7 @@ static int64_t dump_fips_init(uint8_t type)
 
 	rc = opal_dump_init(type);
 	if (rc)
-		pr_warn("%s: Failed to initiate FipS dump (%d)\n",
+		pr_warn("%s: Failed to initiate FSP dump (%d)\n",
 			__func__, rc);
 	return rc;
 }
@@ -131,8 +131,12 @@ static ssize_t init_dump_store(struct dump_obj *dump_obj,
 			       const char *buf,
 			       size_t count)
 {
-	dump_fips_init(DUMP_TYPE_FSP);
-	pr_info("%s: Initiated FSP dump\n", __func__);
+	int rc;
+
+	rc = dump_fips_init(DUMP_TYPE_FSP);
+	if (rc == OPAL_SUCCESS)
+		pr_info("%s: Initiated FSP dump\n", __func__);
+
 	return count;
 }
 
@@ -297,7 +301,7 @@ static ssize_t dump_attr_read(struct file *filep, struct kobject *kobj,
 			 * and rely on userspace to ask us to try
 			 * again.
 			 */
-			pr_info("%s: Platform dump partially read.ID = 0x%x\n",
+			pr_info("%s: Platform dump partially read. ID = 0x%x\n",
 				__func__, dump->id);
 			return -EIO;
 		}
@@ -423,6 +427,10 @@ void __init opal_platform_dump_init(void)
 {
 	int rc;
 
+	/* ELOG not supported by firmware */
+	if (!opal_check_token(OPAL_DUMP_READ))
+		return;
+
 	dump_kset = kset_create_and_add("dump", NULL, opal_kobj);
 	if (!dump_kset) {
 		pr_warn("%s: Failed to create dump kset\n", __func__);
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index bbdb3ffaab98..518fe95dbf24 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -295,6 +295,10 @@ int __init opal_elog_init(void)
 {
 	int rc = 0;
 
+	/* ELOG not supported by firmware */
+	if (!opal_check_token(OPAL_ELOG_READ))
+		return -1;
+
 	elog_kset = kset_create_and_add("elog", NULL, opal_kobj);
 	if (!elog_kset) {
 		pr_warn("%s: failed to create elog kset\n", __func__);
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index ad4b31df779a..dd2c285ad170 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -191,6 +191,7 @@ static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf,
 {
 	struct lpc_debugfs_entry *lpc = filp->private_data;
 	u32 data, pos, len, todo;
+	__be32 bedata;
 	int rc;
 
 	if (!access_ok(VERIFY_WRITE, ubuf, count))
@@ -213,9 +214,10 @@ static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf,
 				len = 2;
 		}
 		rc = opal_lpc_read(opal_lpc_chip_id, lpc->lpc_type, pos,
-				   &data, len);
+				   &bedata, len);
 		if (rc)
 			return -ENXIO;
+		data = be32_to_cpu(bedata);
 		switch(len) {
 		case 4:
 			rc = __put_user((u32)data, (u32 __user *)ubuf);
diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c
index acd9f7e96678..f9896fd5d04a 100644
--- a/arch/powerpc/platforms/powernv/opal-nvram.c
+++ b/arch/powerpc/platforms/powernv/opal-nvram.c
@@ -78,7 +78,7 @@ void __init opal_nvram_init(void)
 	}
 	nvram_size = be32_to_cpup(nbytes_p);
 
-	printk(KERN_INFO "OPAL nvram setup, %u bytes\n", nvram_size);
+	pr_info("OPAL nvram setup, %u bytes\n", nvram_size);
 	of_node_put(np);
 
 	ppc_md.nvram_read = opal_nvram_read;
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index b1885db8fdf3..499707ddaa9c 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -42,6 +42,9 @@ unsigned long __init opal_get_boot_time(void)
 	__be64 __h_m_s_ms;
 	long rc = OPAL_BUSY;
 
+	if (!opal_check_token(OPAL_RTC_READ))
+		goto out;
+
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
 		if (rc == OPAL_BUSY_EVENT)
@@ -49,16 +52,18 @@ unsigned long __init opal_get_boot_time(void)
 		else
 			mdelay(10);
 	}
-	if (rc != OPAL_SUCCESS) {
-		ppc_md.get_rtc_time = NULL;
-		ppc_md.set_rtc_time = NULL;
-		return 0;
-	}
+	if (rc != OPAL_SUCCESS)
+		goto out;
+
 	y_m_d = be32_to_cpu(__y_m_d);
 	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
 	opal_to_tm(y_m_d, h_m_s_ms, &tm);
 	return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
 		      tm.tm_hour, tm.tm_min, tm.tm_sec);
+out:
+	ppc_md.get_rtc_time = NULL;
+	ppc_md.set_rtc_time = NULL;
+	return 0;
 }
 
 void opal_get_rtc_time(struct rtc_time *tm)
diff --git a/arch/powerpc/platforms/powernv/opal-tracepoints.c b/arch/powerpc/platforms/powernv/opal-tracepoints.c
index d8a000a9988b..ae14c40b4b1c 100644
--- a/arch/powerpc/platforms/powernv/opal-tracepoints.c
+++ b/arch/powerpc/platforms/powernv/opal-tracepoints.c
@@ -2,7 +2,7 @@
 #include <linux/jump_label.h>
 #include <asm/trace.h>
 
-#ifdef CONFIG_JUMP_LABEL
+#ifdef HAVE_JUMP_LABEL
 struct static_key opal_tracepoint_key = STATIC_KEY_INIT;
 
 void opal_tracepoint_regfunc(void)
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 2e6ce1b8dc8f..e9e2450c1fdd 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -184,6 +184,7 @@ OPAL_CALL(opal_register_exception_handler,	OPAL_REGISTER_OPAL_EXCEPTION_HANDLER)
 OPAL_CALL(opal_pci_eeh_freeze_status,		OPAL_PCI_EEH_FREEZE_STATUS);
 OPAL_CALL(opal_pci_eeh_freeze_clear,		OPAL_PCI_EEH_FREEZE_CLEAR);
 OPAL_CALL(opal_pci_eeh_freeze_set,		OPAL_PCI_EEH_FREEZE_SET);
+OPAL_CALL(opal_pci_err_inject,			OPAL_PCI_ERR_INJECT);
 OPAL_CALL(opal_pci_shpc,			OPAL_PCI_SHPC);
 OPAL_CALL(opal_pci_phb_mmio_enable,		OPAL_PCI_PHB_MMIO_ENABLE);
 OPAL_CALL(opal_pci_set_phb_mem_window,		OPAL_PCI_SET_PHB_MEM_WINDOW);
@@ -232,6 +233,7 @@ OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
 OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
 OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
 OPAL_CALL(opal_resync_timebase,			OPAL_RESYNC_TIMEBASE);
+OPAL_CALL(opal_check_token,			OPAL_CHECK_TOKEN);
 OPAL_CALL(opal_dump_init,			OPAL_DUMP_INIT);
 OPAL_CALL(opal_dump_info,			OPAL_DUMP_INFO);
 OPAL_CALL(opal_dump_info2,			OPAL_DUMP_INFO2);
@@ -247,3 +249,4 @@ OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
 OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
 OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
 OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
+OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CXL_MODE);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 4b005ae5dc4b..b642b0562f5a 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -105,12 +105,12 @@ int __init early_init_dt_scan_opal(unsigned long node,
 	if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
 		powerpc_firmware_features |= FW_FEATURE_OPALv2;
 		powerpc_firmware_features |= FW_FEATURE_OPALv3;
-		printk("OPAL V3 detected !\n");
+		pr_info("OPAL V3 detected !\n");
 	} else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
 		powerpc_firmware_features |= FW_FEATURE_OPALv2;
-		printk("OPAL V2 detected !\n");
+		pr_info("OPAL V2 detected !\n");
 	} else {
-		printk("OPAL V1 detected !\n");
+		pr_info("OPAL V1 detected !\n");
 	}
 
 	/* Reinit all cores with the right endian */
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index df241b11d4f7..468a0f23c7f2 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -37,41 +37,43 @@
 #include <asm/xics.h>
 #include <asm/debug.h>
 #include <asm/firmware.h>
+#include <asm/pnv-pci.h>
+
+#include <misc/cxl.h>
 
 #include "powernv.h"
 #include "pci.h"
 
-#define define_pe_printk_level(func, kern_level)		\
-static int func(const struct pnv_ioda_pe *pe, const char *fmt, ...)	\
-{								\
-	struct va_format vaf;					\
-	va_list args;						\
-	char pfix[32];						\
-	int r;							\
-								\
-	va_start(args, fmt);					\
-								\
-	vaf.fmt = fmt;						\
-	vaf.va = &args;						\
-								\
-	if (pe->pdev)						\
-		strlcpy(pfix, dev_name(&pe->pdev->dev),		\
-			sizeof(pfix));				\
-	else							\
-		sprintf(pfix, "%04x:%02x     ",			\
-			pci_domain_nr(pe->pbus),		\
-			pe->pbus->number);			\
-	r = printk(kern_level "pci %s: [PE# %.3d] %pV",		\
-		   pfix, pe->pe_number, &vaf);			\
-								\
-	va_end(args);						\
-								\
-	return r;						\
-}								\
-
-define_pe_printk_level(pe_err, KERN_ERR);
-define_pe_printk_level(pe_warn, KERN_WARNING);
-define_pe_printk_level(pe_info, KERN_INFO);
+static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
+			    const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	char pfix[32];
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	if (pe->pdev)
+		strlcpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix));
+	else
+		sprintf(pfix, "%04x:%02x     ",
+			pci_domain_nr(pe->pbus), pe->pbus->number);
+
+	printk("%spci %s: [PE# %.3d] %pV",
+	       level, pfix, pe->pe_number, &vaf);
+
+	va_end(args);
+}
+
+#define pe_err(pe, fmt, ...)					\
+	pe_level_printk(pe, KERN_ERR, fmt, ##__VA_ARGS__)
+#define pe_warn(pe, fmt, ...)					\
+	pe_level_printk(pe, KERN_WARNING, fmt, ##__VA_ARGS__)
+#define pe_info(pe, fmt, ...)					\
+	pe_level_printk(pe, KERN_INFO, fmt, ##__VA_ARGS__)
 
 /*
  * stdcix is only supposed to be used in hypervisor real mode as per
@@ -385,7 +387,7 @@ static void pnv_ioda_freeze_pe(struct pnv_phb *phb, int pe_no)
 	}
 }
 
-int pnv_ioda_unfreeze_pe(struct pnv_phb *phb, int pe_no, int opt)
+static int pnv_ioda_unfreeze_pe(struct pnv_phb *phb, int pe_no, int opt)
 {
 	struct pnv_ioda_pe *pe, *slave;
 	s64 rc;
@@ -890,6 +892,28 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
 	return 0;
 }
 
+static u64 pnv_pci_ioda_dma_get_required_mask(struct pnv_phb *phb,
+					      struct pci_dev *pdev)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	struct pnv_ioda_pe *pe;
+	u64 end, mask;
+
+	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
+		return 0;
+
+	pe = &phb->ioda.pe_array[pdn->pe_number];
+	if (!pe->tce_bypass_enabled)
+		return __dma_get_required_mask(&pdev->dev);
+
+
+	end = pe->tce_bypass_base + memblock_end_of_DRAM();
+	mask = 1ULL << (fls64(end) - 1);
+	mask += mask - 1;
+
+	return mask;
+}
+
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
 				   struct pci_bus *bus,
 				   bool add_to_iommu_group)
@@ -1306,14 +1330,186 @@ static void pnv_ioda2_msi_eoi(struct irq_data *d)
 	icp_native_eoi(d);
 }
 
+
+static void set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
+{
+	struct irq_data *idata;
+	struct irq_chip *ichip;
+
+	if (phb->type != PNV_PHB_IODA2)
+		return;
+
+	if (!phb->ioda.irq_chip_init) {
+		/*
+		 * First time we setup an MSI IRQ, we need to setup the
+		 * corresponding IRQ chip to route correctly.
+		 */
+		idata = irq_get_irq_data(virq);
+		ichip = irq_data_get_irq_chip(idata);
+		phb->ioda.irq_chip_init = 1;
+		phb->ioda.irq_chip = *ichip;
+		phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
+	}
+	irq_set_chip(virq, &phb->ioda.irq_chip);
+}
+
+#ifdef CONFIG_CXL_BASE
+
+struct device_node *pnv_pci_to_phb_node(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+
+	return hose->dn;
+}
+EXPORT_SYMBOL(pnv_pci_to_phb_node);
+
+int pnv_phb_to_cxl(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pnv_ioda_pe *pe;
+	int rc;
+
+	pe = pnv_ioda_get_pe(dev);
+	if (!pe)
+		return -ENODEV;
+
+	pe_info(pe, "Switching PHB to CXL\n");
+
+	rc = opal_pci_set_phb_cxl_mode(phb->opal_id, 1, pe->pe_number);
+	if (rc)
+		dev_err(&dev->dev, "opal_pci_set_phb_cxl_mode failed: %i\n", rc);
+
+	return rc;
+}
+EXPORT_SYMBOL(pnv_phb_to_cxl);
+
+/* Find PHB for cxl dev and allocate MSI hwirqs?
+ * Returns the absolute hardware IRQ number
+ */
+int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, num);
+
+	if (hwirq < 0) {
+		dev_warn(&dev->dev, "Failed to find a free MSI\n");
+		return -ENOSPC;
+	}
+
+	return phb->msi_base + hwirq;
+}
+EXPORT_SYMBOL(pnv_cxl_alloc_hwirqs);
+
+void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, num);
+}
+EXPORT_SYMBOL(pnv_cxl_release_hwirqs);
+
+void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
+				  struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int i, hwirq;
+
+	for (i = 1; i < CXL_IRQ_RANGES; i++) {
+		if (!irqs->range[i])
+			continue;
+		pr_devel("cxl release irq range 0x%x: offset: 0x%lx  limit: %ld\n",
+			 i, irqs->offset[i],
+			 irqs->range[i]);
+		hwirq = irqs->offset[i] - phb->msi_base;
+		msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq,
+				       irqs->range[i]);
+	}
+}
+EXPORT_SYMBOL(pnv_cxl_release_hwirq_ranges);
+
+int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
+			       struct pci_dev *dev, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int i, hwirq, try;
+
+	memset(irqs, 0, sizeof(struct cxl_irq_ranges));
+
+	/* 0 is reserved for the multiplexed PSL DSI interrupt */
+	for (i = 1; i < CXL_IRQ_RANGES && num; i++) {
+		try = num;
+		while (try) {
+			hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, try);
+			if (hwirq >= 0)
+				break;
+			try /= 2;
+		}
+		if (!try)
+			goto fail;
+
+		irqs->offset[i] = phb->msi_base + hwirq;
+		irqs->range[i] = try;
+		pr_devel("cxl alloc irq range 0x%x: offset: 0x%lx  limit: %li\n",
+			 i, irqs->offset[i], irqs->range[i]);
+		num -= try;
+	}
+	if (num)
+		goto fail;
+
+	return 0;
+fail:
+	pnv_cxl_release_hwirq_ranges(irqs, dev);
+	return -ENOSPC;
+}
+EXPORT_SYMBOL(pnv_cxl_alloc_hwirq_ranges);
+
+int pnv_cxl_get_irq_count(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	return phb->msi_bmp.irq_count;
+}
+EXPORT_SYMBOL(pnv_cxl_get_irq_count);
+
+int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
+			   unsigned int virq)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	unsigned int xive_num = hwirq - phb->msi_base;
+	struct pnv_ioda_pe *pe;
+	int rc;
+
+	if (!(pe = pnv_ioda_get_pe(dev)))
+		return -ENODEV;
+
+	/* Assign XIVE to PE */
+	rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
+	if (rc) {
+		pe_warn(pe, "%s: OPAL error %d setting msi_base 0x%x "
+			"hwirq 0x%x XIVE 0x%x PE\n",
+			pci_name(dev), rc, phb->msi_base, hwirq, xive_num);
+		return -EIO;
+	}
+	set_msi_irq_chip(phb, virq);
+
+	return 0;
+}
+EXPORT_SYMBOL(pnv_cxl_ioda_msi_setup);
+#endif
+
 static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 				  unsigned int hwirq, unsigned int virq,
 				  unsigned int is_64, struct msi_msg *msg)
 {
 	struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
 	struct pci_dn *pdn = pci_get_pdn(dev);
-	struct irq_data *idata;
-	struct irq_chip *ichip;
 	unsigned int xive_num = hwirq - phb->msi_base;
 	__be32 data;
 	int rc;
@@ -1365,22 +1561,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 	}
 	msg->data = be32_to_cpu(data);
 
-	/*
-	 * Change the IRQ chip for the MSI interrupts on PHB3.
-	 * The corresponding IRQ chip should be populated for
-	 * the first time.
-	 */
-	if (phb->type == PNV_PHB_IODA2) {
-		if (!phb->ioda.irq_chip_init) {
-			idata = irq_get_irq_data(virq);
-			ichip = irq_data_get_irq_chip(idata);
-			phb->ioda.irq_chip_init = 1;
-			phb->ioda.irq_chip = *ichip;
-			phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
-		}
-
-		irq_set_chip(virq, &phb->ioda.irq_chip);
-	}
+	set_msi_irq_chip(phb, virq);
 
 	pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d),"
 		 " address=%x_%08x data=%x PE# %d\n",
@@ -1627,12 +1808,12 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
 
 static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
 {
-	opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET,
+	opal_pci_reset(phb->opal_id, OPAL_RESET_PCI_IODA_TABLE,
 		       OPAL_ASSERT_RESET);
 }
 
-void __init pnv_pci_init_ioda_phb(struct device_node *np,
-				  u64 hub_id, int ioda_type)
+static void __init pnv_pci_init_ioda_phb(struct device_node *np,
+					 u64 hub_id, int ioda_type)
 {
 	struct pci_controller *hose;
 	struct pnv_phb *phb;
@@ -1782,6 +1963,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
 	phb->dma_set_mask = pnv_pci_ioda_dma_set_mask;
+	phb->dma_get_required_mask = pnv_pci_ioda_dma_get_required_mask;
 
 	/* Setup shutdown function for kexec */
 	phb->shutdown = pnv_pci_ioda_shutdown;
@@ -1803,7 +1985,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 
 	/* Reset IODA tables to a clean state */
-	rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET);
+	rc = opal_pci_reset(phb_id, OPAL_RESET_PCI_IODA_TABLE, OPAL_ASSERT_RESET);
 	if (rc)
 		pr_warning("  OPAL Error %ld performing IODA table reset !\n", rc);
 
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b854b57ed5e1..b3ca77ddf36d 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -46,29 +46,21 @@
 //#define cfg_dbg(fmt...)	printk(fmt)
 
 #ifdef CONFIG_PCI_MSI
-static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type)
-{
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	struct pci_dn *pdn = pci_get_pdn(pdev);
-
-	if (pdn && pdn->force_32bit_msi && !phb->msi32_support)
-		return -ENODEV;
-
-	return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV;
-}
-
 static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
+	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct msi_desc *entry;
 	struct msi_msg msg;
 	int hwirq;
 	unsigned int virq;
 	int rc;
 
-	if (WARN_ON(!phb))
+	if (WARN_ON(!phb) || !phb->msi_bmp.bitmap)
+		return -ENODEV;
+
+	if (pdn && pdn->force_32bit_msi && !phb->msi32_support)
 		return -ENODEV;
 
 	list_for_each_entry(entry, &pdev->msi_list, list) {
@@ -761,6 +753,17 @@ int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 	return __dma_set_mask(&pdev->dev, dma_mask);
 }
 
+u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	if (phb && phb->dma_get_required_mask)
+		return phb->dma_get_required_mask(phb, pdev);
+
+	return __dma_get_required_mask(&pdev->dev);
+}
+
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
@@ -860,7 +863,6 @@ void __init pnv_pci_init(void)
 
 	/* Configure MSIs */
 #ifdef CONFIG_PCI_MSI
-	ppc_md.msi_check_device = pnv_msi_check_device;
 	ppc_md.setup_msi_irqs = pnv_setup_msi_irqs;
 	ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs;
 #endif
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 48494d4b6058..34d29eb2a4de 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -85,6 +85,8 @@ struct pnv_eeh_ops {
 	int (*get_log)(struct eeh_pe *pe, int severity,
 		       char *drv_log, unsigned long len);
 	int (*configure_bridge)(struct eeh_pe *pe);
+	int (*err_inject)(struct eeh_pe *pe, int type, int func,
+			  unsigned long addr, unsigned long mask);
 	int (*next_error)(struct eeh_pe **pe);
 };
 #endif /* CONFIG_EEH */
@@ -122,6 +124,8 @@ struct pnv_phb {
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
 	int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev,
 			    u64 dma_mask);
+	u64 (*dma_get_required_mask)(struct pnv_phb *phb,
+				     struct pci_dev *pdev);
 	void (*fixup_phb)(struct pci_controller *hose);
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
 	void (*shutdown)(struct pnv_phb *phb);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 75501bfede7f..6c8e2d188cd0 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -13,6 +13,7 @@ struct pci_dev;
 extern void pnv_pci_init(void);
 extern void pnv_pci_shutdown(void);
 extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask);
+extern u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev);
 #else
 static inline void pnv_pci_init(void) { }
 static inline void pnv_pci_shutdown(void) { }
@@ -21,6 +22,11 @@ static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 {
 	return -ENODEV;
 }
+
+static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
+{
+	return 0;
+}
 #endif
 
 extern void pnv_lpc_init(void);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 5a0e2dc6de5f..3f9546d8a51f 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -173,6 +173,14 @@ static int pnv_dma_set_mask(struct device *dev, u64 dma_mask)
 	return __dma_set_mask(dev, dma_mask);
 }
 
+static u64 pnv_dma_get_required_mask(struct device *dev)
+{
+	if (dev_is_pci(dev))
+		return pnv_pci_dma_get_required_mask(to_pci_dev(dev));
+
+	return __dma_get_required_mask(dev);
+}
+
 static void pnv_shutdown(void)
 {
 	/* Let the PCI code clear up IODA tables */
@@ -307,7 +315,7 @@ static int __init pnv_probe(void)
  * Returns the cpu frequency for 'cpu' in Hz. This is used by
  * /proc/cpuinfo
  */
-unsigned long pnv_get_proc_freq(unsigned int cpu)
+static unsigned long pnv_get_proc_freq(unsigned int cpu)
 {
 	unsigned long ret_freq;
 
@@ -335,6 +343,7 @@ define_machine(powernv) {
 	.power_save             = power7_idle,
 	.calibrate_decr		= generic_calibrate_decr,
 	.dma_set_mask		= pnv_dma_set_mask,
+	.dma_get_required_mask	= pnv_dma_get_required_mask,
 #ifdef CONFIG_KEXEC
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
 #endif
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 5fcfcf44e3a9..4753958cd509 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -54,7 +54,7 @@ static void pnv_smp_setup_cpu(int cpu)
 #endif
 }
 
-int pnv_smp_kick_cpu(int nr)
+static int pnv_smp_kick_cpu(int nr)
 {
 	unsigned int pcpu = get_hard_smp_processor_id(nr);
 	unsigned long start_here =
@@ -168,9 +168,9 @@ static void pnv_smp_cpu_kill_self(void)
 		power7_nap(1);
 		ppc64_runlatch_on();
 
-		/* Reenable IRQs briefly to clear the IPI that woke us */
-		local_irq_enable();
-		local_irq_disable();
+		/* Clear the IPI that woke us up */
+		icp_native_flush_interrupt();
+		local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
 		mb();
 
 		if (cpu_core_split_required())
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 894ecb3eb596..c87f96b79d1a 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -24,6 +24,7 @@
 #include <asm/smp.h>
 
 #include "subcore.h"
+#include "powernv.h"
 
 
 /*
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index 2d8bf15879fd..fc44ad0475f8 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -555,7 +555,6 @@ static int cmm_mem_going_offline(void *arg)
 				pa_last = pa_last->next;
 				free_page((unsigned long)cmm_page_list);
 				cmm_page_list = pa_last;
-				continue;
 			}
 		}
 		pa_curr = pa_curr->next;
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index a2450b8a50a5..fdf01b660d59 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include "offline_states.h"
+#include "pseries.h"
 
 #include <asm/prom.h>
 #include <asm/machdep.h>
@@ -363,7 +364,8 @@ static int dlpar_online_cpu(struct device_node *dn)
 	int rc = 0;
 	unsigned int cpu;
 	int len, nthreads, i;
-	const u32 *intserv;
+	const __be32 *intserv;
+	u32 thread;
 
 	intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
 	if (!intserv)
@@ -373,8 +375,9 @@ static int dlpar_online_cpu(struct device_node *dn)
 
 	cpu_maps_update_begin();
 	for (i = 0; i < nthreads; i++) {
+		thread = be32_to_cpu(intserv[i]);
 		for_each_present_cpu(cpu) {
-			if (get_hard_smp_processor_id(cpu) != intserv[i])
+			if (get_hard_smp_processor_id(cpu) != thread)
 				continue;
 			BUG_ON(get_cpu_current_state(cpu)
 					!= CPU_STATE_OFFLINE);
@@ -388,7 +391,7 @@ static int dlpar_online_cpu(struct device_node *dn)
 		}
 		if (cpu == num_possible_cpus())
 			printk(KERN_WARNING "Could not find cpu to online "
-			       "with physical id 0x%x\n", intserv[i]);
+			       "with physical id 0x%x\n", thread);
 	}
 	cpu_maps_update_done();
 
@@ -442,7 +445,8 @@ static int dlpar_offline_cpu(struct device_node *dn)
 	int rc = 0;
 	unsigned int cpu;
 	int len, nthreads, i;
-	const u32 *intserv;
+	const __be32 *intserv;
+	u32 thread;
 
 	intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
 	if (!intserv)
@@ -452,8 +456,9 @@ static int dlpar_offline_cpu(struct device_node *dn)
 
 	cpu_maps_update_begin();
 	for (i = 0; i < nthreads; i++) {
+		thread = be32_to_cpu(intserv[i]);
 		for_each_present_cpu(cpu) {
-			if (get_hard_smp_processor_id(cpu) != intserv[i])
+			if (get_hard_smp_processor_id(cpu) != thread)
 				continue;
 
 			if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE)
@@ -475,14 +480,14 @@ static int dlpar_offline_cpu(struct device_node *dn)
 			 * Upgrade it's state to CPU_STATE_OFFLINE.
 			 */
 			set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
-			BUG_ON(plpar_hcall_norets(H_PROD, intserv[i])
+			BUG_ON(plpar_hcall_norets(H_PROD, thread)
 								!= H_SUCCESS);
 			__cpu_die(cpu);
 			break;
 		}
 		if (cpu == num_possible_cpus())
 			printk(KERN_WARNING "Could not find cpu to offline "
-			       "with physical id 0x%x\n", intserv[i]);
+			       "with physical id 0x%x\n", thread);
 	}
 	cpu_maps_update_done();
 
@@ -494,15 +499,15 @@ out:
 static ssize_t dlpar_cpu_release(const char *buf, size_t count)
 {
 	struct device_node *dn;
-	const u32 *drc_index;
+	u32 drc_index;
 	int rc;
 
 	dn = of_find_node_by_path(buf);
 	if (!dn)
 		return -EINVAL;
 
-	drc_index = of_get_property(dn, "ibm,my-drc-index", NULL);
-	if (!drc_index) {
+	rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index);
+	if (rc) {
 		of_node_put(dn);
 		return -EINVAL;
 	}
@@ -513,7 +518,7 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count)
 		return -EINVAL;
 	}
 
-	rc = dlpar_release_drc(*drc_index);
+	rc = dlpar_release_drc(drc_index);
 	if (rc) {
 		of_node_put(dn);
 		return rc;
@@ -521,7 +526,7 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count)
 
 	rc = dlpar_detach_node(dn);
 	if (rc) {
-		dlpar_acquire_drc(*drc_index);
+		dlpar_acquire_drc(drc_index);
 		return rc;
 	}
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index b08053819d99..a6c7e19f5eb3 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -88,29 +88,14 @@ static int pseries_eeh_init(void)
 	 * and its variant since the old firmware probably support address
 	 * of domain/bus/slot/function for EEH RTAS operations.
 	 */
-	if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE) {
-		pr_warn("%s: RTAS service <ibm,set-eeh-option> invalid\n",
-			__func__);
-		return -EINVAL;
-	} else if (ibm_set_slot_reset == RTAS_UNKNOWN_SERVICE) {
-		pr_warn("%s: RTAS service <ibm,set-slot-reset> invalid\n",
-			__func__);
-		return -EINVAL;
-	} else if (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE &&
-		   ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE) {
-		pr_warn("%s: RTAS service <ibm,read-slot-reset-state2> and "
-			"<ibm,read-slot-reset-state> invalid\n",
-			__func__);
-		return -EINVAL;
-	} else if (ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE) {
-		pr_warn("%s: RTAS service <ibm,slot-error-detail> invalid\n",
-			__func__);
-		return -EINVAL;
-	} else if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE &&
-		   ibm_configure_bridge == RTAS_UNKNOWN_SERVICE) {
-		pr_warn("%s: RTAS service <ibm,configure-pe> and "
-			"<ibm,configure-bridge> invalid\n",
-			__func__);
+	if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE		||
+	    ibm_set_slot_reset == RTAS_UNKNOWN_SERVICE		||
+	    (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE &&
+	     ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE)	||
+	    ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE	||
+	    (ibm_configure_pe == RTAS_UNKNOWN_SERVICE		&&
+	     ibm_configure_bridge == RTAS_UNKNOWN_SERVICE)) {
+		pr_info("EEH functionality not supported\n");
 		return -EINVAL;
 	}
 
@@ -118,11 +103,11 @@ static int pseries_eeh_init(void)
 	spin_lock_init(&slot_errbuf_lock);
 	eeh_error_buf_size = rtas_token("rtas-error-log-max");
 	if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) {
-		pr_warn("%s: unknown EEH error log size\n",
+		pr_info("%s: unknown EEH error log size\n",
 			__func__);
 		eeh_error_buf_size = 1024;
 	} else if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) {
-		pr_warn("%s: EEH error log size %d exceeds the maximal %d\n",
+		pr_info("%s: EEH error log size %d exceeds the maximal %d\n",
 			__func__, eeh_error_buf_size, RTAS_ERROR_LOG_MAX);
 		eeh_error_buf_size = RTAS_ERROR_LOG_MAX;
 	}
@@ -349,7 +334,9 @@ static int pseries_eeh_set_option(struct eeh_pe *pe, int option)
 		if (pe->addr)
 			config_addr = pe->addr;
 		break;
-
+	case EEH_OPT_FREEZE_PE:
+		/* Not support */
+		return 0;
 	default:
 		pr_err("%s: Invalid option %d\n",
 			__func__, option);
@@ -729,6 +716,7 @@ static struct eeh_ops pseries_eeh_ops = {
 	.wait_state		= pseries_eeh_wait_state,
 	.get_log		= pseries_eeh_get_log,
 	.configure_bridge       = pseries_eeh_configure_bridge,
+	.err_inject		= NULL,
 	.read_config		= pseries_eeh_read_config,
 	.write_config		= pseries_eeh_write_config,
 	.next_error		= NULL,
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 20d62975856f..b174fa751d26 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -90,7 +90,7 @@ static void rtas_stop_self(void)
 {
 	static struct rtas_args args = {
 		.nargs = 0,
-		.nret = 1,
+		.nret = cpu_to_be32(1),
 		.rets = &args.args[0],
 	};
 
@@ -312,7 +312,8 @@ static void pseries_remove_processor(struct device_node *np)
 {
 	unsigned int cpu;
 	int len, nthreads, i;
-	const u32 *intserv;
+	const __be32 *intserv;
+	u32 thread;
 
 	intserv = of_get_property(np, "ibm,ppc-interrupt-server#s", &len);
 	if (!intserv)
@@ -322,8 +323,9 @@ static void pseries_remove_processor(struct device_node *np)
 
 	cpu_maps_update_begin();
 	for (i = 0; i < nthreads; i++) {
+		thread = be32_to_cpu(intserv[i]);
 		for_each_present_cpu(cpu) {
-			if (get_hard_smp_processor_id(cpu) != intserv[i])
+			if (get_hard_smp_processor_id(cpu) != thread)
 				continue;
 			BUG_ON(cpu_online(cpu));
 			set_cpu_present(cpu, false);
@@ -332,7 +334,7 @@ static void pseries_remove_processor(struct device_node *np)
 		}
 		if (cpu >= nr_cpu_ids)
 			printk(KERN_WARNING "Could not find cpu to remove "
-			       "with physical id 0x%x\n", intserv[i]);
+			       "with physical id 0x%x\n", thread);
 	}
 	cpu_maps_update_done();
 }
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 34064f50945e..3c4c0dcd90d3 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -20,6 +20,7 @@
 #include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/sparsemem.h>
+#include "pseries.h"
 
 unsigned long pseries_memory_block_size(void)
 {
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 4642d6a4d356..de1ec54a2a57 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -329,16 +329,16 @@ struct direct_window {
 
 /* Dynamic DMA Window support */
 struct ddw_query_response {
-	__be32 windows_available;
-	__be32 largest_available_block;
-	__be32 page_size;
-	__be32 migration_capable;
+	u32 windows_available;
+	u32 largest_available_block;
+	u32 page_size;
+	u32 migration_capable;
 };
 
 struct ddw_create_response {
-	__be32 liobn;
-	__be32 addr_hi;
-	__be32 addr_lo;
+	u32 liobn;
+	u32 addr_hi;
+	u32 addr_lo;
 };
 
 static LIST_HEAD(direct_window_list);
@@ -725,16 +725,18 @@ static void remove_ddw(struct device_node *np, bool remove_prop)
 {
 	struct dynamic_dma_window_prop *dwp;
 	struct property *win64;
-	const u32 *ddw_avail;
+	u32 ddw_avail[3];
 	u64 liobn;
-	int len, ret = 0;
+	int ret = 0;
+
+	ret = of_property_read_u32_array(np, "ibm,ddw-applicable",
+					 &ddw_avail[0], 3);
 
-	ddw_avail = of_get_property(np, "ibm,ddw-applicable", &len);
 	win64 = of_find_property(np, DIRECT64_PROPNAME, NULL);
 	if (!win64)
 		return;
 
-	if (!ddw_avail || len < 3 * sizeof(u32) || win64->length < sizeof(*dwp))
+	if (ret || win64->length < sizeof(*dwp))
 		goto delprop;
 
 	dwp = win64->value;
@@ -872,8 +874,9 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 
 	do {
 		/* extra outputs are LIOBN and dma-addr (hi, lo) */
-		ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, cfg_addr,
-				BUID_HI(buid), BUID_LO(buid), page_shift, window_shift);
+		ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create,
+				cfg_addr, BUID_HI(buid), BUID_LO(buid),
+				page_shift, window_shift);
 	} while (rtas_busy_delay(ret));
 	dev_info(&dev->dev,
 		"ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d "
@@ -910,7 +913,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	int page_shift;
 	u64 dma_addr, max_addr;
 	struct device_node *dn;
-	const u32 *uninitialized_var(ddw_avail);
+	u32 ddw_avail[3];
 	struct direct_window *window;
 	struct property *win64;
 	struct dynamic_dma_window_prop *ddwprop;
@@ -942,8 +945,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	 * for the given node in that order.
 	 * the property is actually in the parent, not the PE
 	 */
-	ddw_avail = of_get_property(pdn, "ibm,ddw-applicable", &len);
-	if (!ddw_avail || len < 3 * sizeof(u32))
+	ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable",
+					 &ddw_avail[0], 3);
+	if (ret)
 		goto out_failed;
 
        /*
@@ -966,11 +970,11 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		dev_dbg(&dev->dev, "no free dynamic windows");
 		goto out_failed;
 	}
-	if (be32_to_cpu(query.page_size) & 4) {
+	if (query.page_size & 4) {
 		page_shift = 24; /* 16MB */
-	} else if (be32_to_cpu(query.page_size) & 2) {
+	} else if (query.page_size & 2) {
 		page_shift = 16; /* 64kB */
-	} else if (be32_to_cpu(query.page_size) & 1) {
+	} else if (query.page_size & 1) {
 		page_shift = 12; /* 4kB */
 	} else {
 		dev_dbg(&dev->dev, "no supported direct page size in mask %x",
@@ -980,7 +984,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	/* verify the window * number of ptes will map the partition */
 	/* check largest block * page size > max memory hotplug addr */
 	max_addr = memory_hotplug_max();
-	if (be32_to_cpu(query.largest_available_block) < (max_addr >> page_shift)) {
+	if (query.largest_available_block < (max_addr >> page_shift)) {
 		dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u "
 			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
 			  1ULL << page_shift);
@@ -1006,8 +1010,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	if (ret != 0)
 		goto out_free_prop;
 
-	ddwprop->liobn = create.liobn;
-	ddwprop->dma_base = cpu_to_be64(of_read_number(&create.addr_hi, 2));
+	ddwprop->liobn = cpu_to_be32(create.liobn);
+	ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) |
+			create.addr_lo);
 	ddwprop->tce_shift = cpu_to_be32(page_shift);
 	ddwprop->window_shift = cpu_to_be32(len);
 
@@ -1039,7 +1044,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	list_add(&window->list, &direct_window_list);
 	spin_unlock(&direct_window_list_lock);
 
-	dma_addr = of_read_number(&create.addr_hi, 2);
+	dma_addr = be64_to_cpu(ddwprop->dma_base);
 	goto out_unlock;
 
 out_free_window:
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 34e64237fff9..8c509d5397c6 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -59,8 +59,6 @@ EXPORT_SYMBOL(plpar_hcall);
 EXPORT_SYMBOL(plpar_hcall9);
 EXPORT_SYMBOL(plpar_hcall_norets);
 
-extern void pSeries_find_serial_port(void);
-
 void vpa_init(int cpu)
 {
 	int hwcpu = get_hard_smp_processor_id(cpu);
@@ -642,7 +640,7 @@ EXPORT_SYMBOL(arch_free_page);
 #endif
 
 #ifdef CONFIG_TRACEPOINTS
-#ifdef CONFIG_JUMP_LABEL
+#ifdef HAVE_JUMP_LABEL
 struct static_key hcall_tracepoint_key = STATIC_KEY_INIT;
 
 void hcall_tracepoint_regfunc(void)
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 18ff4626d74e..8ab5add4ac82 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -336,26 +336,6 @@ out:
 	return request;
 }
 
-static int rtas_msi_check_device(struct pci_dev *pdev, int nvec, int type)
-{
-	int quota, rc;
-
-	if (type == PCI_CAP_ID_MSIX)
-		rc = check_req_msix(pdev, nvec);
-	else
-		rc = check_req_msi(pdev, nvec);
-
-	if (rc)
-		return rc;
-
-	quota = msi_quota_for_device(pdev, nvec);
-
-	if (quota && quota < nvec)
-		return quota;
-
-	return 0;
-}
-
 static int check_msix_entries(struct pci_dev *pdev)
 {
 	struct msi_desc *entry;
@@ -397,15 +377,24 @@ static void rtas_hack_32bit_msi_gen2(struct pci_dev *pdev)
 static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
 {
 	struct pci_dn *pdn;
-	int hwirq, virq, i, rc;
+	int hwirq, virq, i, quota, rc;
 	struct msi_desc *entry;
 	struct msi_msg msg;
 	int nvec = nvec_in;
 	int use_32bit_msi_hack = 0;
 
-	pdn = pci_get_pdn(pdev);
-	if (!pdn)
-		return -ENODEV;
+	if (type == PCI_CAP_ID_MSIX)
+		rc = check_req_msix(pdev, nvec);
+	else
+		rc = check_req_msi(pdev, nvec);
+
+	if (rc)
+		return rc;
+
+	quota = msi_quota_for_device(pdev, nvec);
+
+	if (quota && quota < nvec)
+		return quota;
 
 	if (type == PCI_CAP_ID_MSIX && check_msix_entries(pdev))
 		return -EINVAL;
@@ -416,12 +405,14 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
 	 */
 	if (type == PCI_CAP_ID_MSIX) {
 		int m = roundup_pow_of_two(nvec);
-		int quota = msi_quota_for_device(pdev, m);
+		quota = msi_quota_for_device(pdev, m);
 
 		if (quota >= m)
 			nvec = m;
 	}
 
+	pdn = pci_get_pdn(pdev);
+
 	/*
 	 * Try the new more explicit firmware interface, if that fails fall
 	 * back to the old interface. The old interface is known to never
@@ -485,7 +476,7 @@ again:
 		irq_set_msi_desc(virq, entry);
 
 		/* Read config space back so we can restore after reset */
-		read_msi_msg(virq, &msg);
+		__read_msi_msg(entry, &msg);
 		entry->msg = msg;
 	}
 
@@ -526,7 +517,6 @@ static int rtas_msi_init(void)
 	WARN_ON(ppc_md.setup_msi_irqs);
 	ppc_md.setup_msi_irqs = rtas_setup_msi_irqs;
 	ppc_md.teardown_msi_irqs = rtas_teardown_msi_irqs;
-	ppc_md.msi_check_device = rtas_msi_check_device;
 
 	WARN_ON(ppc_md.pci_irq_fixup);
 	ppc_md.pci_irq_fixup = rtas_msi_pci_irq_fixup;
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 0cc240b7f694..11a3b617ef5d 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -276,8 +276,10 @@ static ssize_t pSeries_nvram_get_size(void)
  * sequence #: The unique sequence # for each event. (until it wraps)
  * error log: The error log from event_scan
  */
-int nvram_write_os_partition(struct nvram_os_partition *part, char * buff,
-		int length, unsigned int err_type, unsigned int error_log_cnt)
+static int nvram_write_os_partition(struct nvram_os_partition *part,
+				    char *buff, int length,
+				    unsigned int err_type,
+				    unsigned int error_log_cnt)
 {
 	int rc;
 	loff_t tmp_index;
@@ -330,9 +332,9 @@ int nvram_write_error_log(char * buff, int length,
  *
  * Reads nvram partition for at most 'length'
  */
-int nvram_read_partition(struct nvram_os_partition *part, char *buff,
-			int length, unsigned int *err_type,
-			unsigned int *error_log_cnt)
+static int nvram_read_partition(struct nvram_os_partition *part, char *buff,
+				int length, unsigned int *err_type,
+				unsigned int *error_log_cnt)
 {
 	int rc;
 	loff_t tmp_index;
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index c413ec158ff5..67e48594040c 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -29,6 +29,7 @@
 #include <asm/pci-bridge.h>
 #include <asm/prom.h>
 #include <asm/ppc-pci.h>
+#include "pseries.h"
 
 #if 0
 void pcibios_name_device(struct pci_dev *dev)
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index dff05b9eb946..5a4d0fc03b03 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -126,7 +126,7 @@ struct epow_errorlog {
 #define EPOW_MAIN_ENCLOSURE		5
 #define EPOW_POWER_OFF			7
 
-void rtas_parse_epow_errlog(struct rtas_error_log *log)
+static void rtas_parse_epow_errlog(struct rtas_error_log *log)
 {
 	struct pseries_errorlog *pseries_log;
 	struct epow_errorlog *epow_log;
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index e724d3186e73..125c589eeef5 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -561,7 +561,7 @@ void pSeries_coalesce_init(void)
  * fw_cmo_feature_init - FW_FEATURE_CMO is not stored in ibm,hypertas-functions,
  * handle that here. (Stolen from parse_system_parameter_string)
  */
-void pSeries_cmo_feature_init(void)
+static void pSeries_cmo_feature_init(void)
 {
 	char *ptr, *key, *value, *end;
 	int call_status;
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index 47b6b9f81d43..ad56edc39919 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -314,7 +314,7 @@ axon_ram_remove(struct platform_device *device)
 	return 0;
 }
 
-static struct of_device_id axon_ram_device_id[] = {
+static const struct of_device_id axon_ram_device_id[] = {
 	{
 		.type	= "dma-memory"
 	},
diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c
index e9056e438575..2d8a101b6b9e 100644
--- a/arch/powerpc/sysdev/dcr.c
+++ b/arch/powerpc/sysdev/dcr.c
@@ -230,5 +230,6 @@ EXPORT_SYMBOL_GPL(dcr_unmap_mmio);
 
 #ifdef CONFIG_PPC_DCR_NATIVE
 DEFINE_SPINLOCK(dcr_ind_lock);
+EXPORT_SYMBOL_GPL(dcr_ind_lock);
 #endif	/* defined(CONFIG_PPC_DCR_NATIVE) */
 
diff --git a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
index afc2dbf37011..90545ad1626e 100644
--- a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
+++ b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
@@ -171,7 +171,7 @@ static int mpc85xx_l2ctlr_of_remove(struct platform_device *dev)
 	return 0;
 }
 
-static struct of_device_id mpc85xx_l2ctlr_of_match[] = {
+static const struct of_device_id mpc85xx_l2ctlr_of_match[] = {
 	{
 		.compatible = "fsl,p2020-l2-cache-controller",
 	},
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 77efbaec7b9c..de40b48b460e 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -18,6 +18,8 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/of_platform.h>
+#include <linux/interrupt.h>
+#include <linux/seq_file.h>
 #include <sysdev/fsl_soc.h>
 #include <asm/prom.h>
 #include <asm/hw_irq.h>
@@ -50,6 +52,7 @@ struct fsl_msi_feature {
 struct fsl_msi_cascade_data {
 	struct fsl_msi *msi_data;
 	int index;
+	int virq;
 };
 
 static inline u32 fsl_msi_read(u32 __iomem *base, unsigned int reg)
@@ -65,11 +68,24 @@ static void fsl_msi_end_irq(struct irq_data *d)
 {
 }
 
+static void fsl_msi_print_chip(struct irq_data *irqd, struct seq_file *p)
+{
+	struct fsl_msi *msi_data = irqd->domain->host_data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(irqd);
+	int cascade_virq, srs;
+
+	srs = (hwirq >> msi_data->srs_shift) & MSI_SRS_MASK;
+	cascade_virq = msi_data->cascade_array[srs]->virq;
+
+	seq_printf(p, " fsl-msi-%d", cascade_virq);
+}
+
+
 static struct irq_chip fsl_msi_chip = {
 	.irq_mask	= mask_msi_irq,
 	.irq_unmask	= unmask_msi_irq,
 	.irq_ack	= fsl_msi_end_irq,
-	.name		= "FSL-MSI",
+	.irq_print_chip = fsl_msi_print_chip,
 };
 
 static int fsl_msi_host_map(struct irq_domain *h, unsigned int virq,
@@ -109,14 +125,6 @@ static int fsl_msi_init_allocator(struct fsl_msi *msi_data)
 	return 0;
 }
 
-static int fsl_msi_check_device(struct pci_dev *pdev, int nvec, int type)
-{
-	if (type == PCI_CAP_ID_MSIX)
-		pr_debug("fslmsi: MSI-X untested, trying anyway.\n");
-
-	return 0;
-}
-
 static void fsl_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct msi_desc *entry;
@@ -173,6 +181,9 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 	struct msi_msg msg;
 	struct fsl_msi *msi_data;
 
+	if (type == PCI_CAP_ID_MSIX)
+		pr_debug("fslmsi: MSI-X untested, trying anyway.\n");
+
 	/*
 	 * If the PCI node has an fsl,msi property, then we need to use it
 	 * to find the specific MSI.
@@ -180,7 +191,8 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 	np = of_parse_phandle(hose->dn, "fsl,msi", 0);
 	if (np) {
 		if (of_device_is_compatible(np, "fsl,mpic-msi") ||
-		    of_device_is_compatible(np, "fsl,vmpic-msi"))
+		    of_device_is_compatible(np, "fsl,vmpic-msi") ||
+		    of_device_is_compatible(np, "fsl,vmpic-msi-v4.3"))
 			phandle = np->phandle;
 		else {
 			dev_err(&pdev->dev,
@@ -239,40 +251,24 @@ out_free:
 	return rc;
 }
 
-static void fsl_msi_cascade(unsigned int irq, struct irq_desc *desc)
+static irqreturn_t fsl_msi_cascade(int irq, void *data)
 {
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct irq_data *idata = irq_desc_get_irq_data(desc);
 	unsigned int cascade_irq;
 	struct fsl_msi *msi_data;
 	int msir_index = -1;
 	u32 msir_value = 0;
 	u32 intr_index;
 	u32 have_shift = 0;
-	struct fsl_msi_cascade_data *cascade_data;
+	struct fsl_msi_cascade_data *cascade_data = data;
+	irqreturn_t ret = IRQ_NONE;
 
-	cascade_data = irq_get_handler_data(irq);
 	msi_data = cascade_data->msi_data;
 
-	raw_spin_lock(&desc->lock);
-	if ((msi_data->feature &  FSL_PIC_IP_MASK) == FSL_PIC_IP_IPIC) {
-		if (chip->irq_mask_ack)
-			chip->irq_mask_ack(idata);
-		else {
-			chip->irq_mask(idata);
-			chip->irq_ack(idata);
-		}
-	}
-
-	if (unlikely(irqd_irq_inprogress(idata)))
-		goto unlock;
-
 	msir_index = cascade_data->index;
 
 	if (msir_index >= NR_MSI_REG_MAX)
 		cascade_irq = NO_IRQ;
 
-	irqd_set_chained_irq_inprogress(idata);
 	switch (msi_data->feature & FSL_PIC_IP_MASK) {
 	case FSL_PIC_IP_MPIC:
 		msir_value = fsl_msi_read(msi_data->msi_regs,
@@ -301,40 +297,32 @@ static void fsl_msi_cascade(unsigned int irq, struct irq_desc *desc)
 		cascade_irq = irq_linear_revmap(msi_data->irqhost,
 				msi_hwirq(msi_data, msir_index,
 					  intr_index + have_shift));
-		if (cascade_irq != NO_IRQ)
+		if (cascade_irq != NO_IRQ) {
 			generic_handle_irq(cascade_irq);
+			ret = IRQ_HANDLED;
+		}
 		have_shift += intr_index + 1;
 		msir_value = msir_value >> (intr_index + 1);
 	}
-	irqd_clr_chained_irq_inprogress(idata);
 
-	switch (msi_data->feature & FSL_PIC_IP_MASK) {
-	case FSL_PIC_IP_MPIC:
-	case FSL_PIC_IP_VMPIC:
-		chip->irq_eoi(idata);
-		break;
-	case FSL_PIC_IP_IPIC:
-		if (!irqd_irq_disabled(idata) && chip->irq_unmask)
-			chip->irq_unmask(idata);
-		break;
-	}
-unlock:
-	raw_spin_unlock(&desc->lock);
+	return ret;
 }
 
 static int fsl_of_msi_remove(struct platform_device *ofdev)
 {
 	struct fsl_msi *msi = platform_get_drvdata(ofdev);
 	int virq, i;
-	struct fsl_msi_cascade_data *cascade_data;
 
 	if (msi->list.prev != NULL)
 		list_del(&msi->list);
 	for (i = 0; i < NR_MSI_REG_MAX; i++) {
-		virq = msi->msi_virqs[i];
-		if (virq != NO_IRQ) {
-			cascade_data = irq_get_handler_data(virq);
-			kfree(cascade_data);
+		if (msi->cascade_array[i]) {
+			virq = msi->cascade_array[i]->virq;
+
+			BUG_ON(virq == NO_IRQ);
+
+			free_irq(virq, msi->cascade_array[i]);
+			kfree(msi->cascade_array[i]);
 			irq_dispose_mapping(virq);
 		}
 	}
@@ -353,7 +341,7 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 			       int offset, int irq_index)
 {
 	struct fsl_msi_cascade_data *cascade_data = NULL;
-	int virt_msir, i;
+	int virt_msir, i, ret;
 
 	virt_msir = irq_of_parse_and_map(dev->dev.of_node, irq_index);
 	if (virt_msir == NO_IRQ) {
@@ -368,11 +356,18 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 		return -ENOMEM;
 	}
 	irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class);
-	msi->msi_virqs[irq_index] = virt_msir;
 	cascade_data->index = offset;
 	cascade_data->msi_data = msi;
-	irq_set_handler_data(virt_msir, cascade_data);
-	irq_set_chained_handler(virt_msir, fsl_msi_cascade);
+	cascade_data->virq = virt_msir;
+	msi->cascade_array[irq_index] = cascade_data;
+
+	ret = request_irq(virt_msir, fsl_msi_cascade, 0,
+			  "fsl-msi-cascade", cascade_data);
+	if (ret) {
+		dev_err(&dev->dev, "failed to request_irq(%d), ret = %d\n",
+			virt_msir, ret);
+		return ret;
+	}
 
 	/* Release the hwirqs corresponding to this MSI register */
 	for (i = 0; i < IRQS_PER_MSI_REG; i++)
@@ -466,7 +461,8 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 
 	p = of_get_property(dev->dev.of_node, "msi-available-ranges", &len);
 
-	if (of_device_is_compatible(dev->dev.of_node, "fsl,mpic-msi-v4.3")) {
+	if (of_device_is_compatible(dev->dev.of_node, "fsl,mpic-msi-v4.3") ||
+	    of_device_is_compatible(dev->dev.of_node, "fsl,vmpic-msi-v4.3")) {
 		msi->srs_shift = MSIIR1_SRS_SHIFT;
 		msi->ibs_shift = MSIIR1_IBS_SHIFT;
 		if (p)
@@ -527,7 +523,6 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 	if (!ppc_md.setup_msi_irqs) {
 		ppc_md.setup_msi_irqs = fsl_setup_msi_irqs;
 		ppc_md.teardown_msi_irqs = fsl_teardown_msi_irqs;
-		ppc_md.msi_check_device = fsl_msi_check_device;
 	} else if (ppc_md.setup_msi_irqs != fsl_setup_msi_irqs) {
 		dev_err(&dev->dev, "Different MSI driver already installed!\n");
 		err = -ENODEV;
@@ -572,6 +567,10 @@ static const struct of_device_id fsl_of_msi_ids[] = {
 		.compatible = "fsl,vmpic-msi",
 		.data = &vmpic_msi_feature,
 	},
+	{
+		.compatible = "fsl,vmpic-msi-v4.3",
+		.data = &vmpic_msi_feature,
+	},
 #endif
 	{}
 };
diff --git a/arch/powerpc/sysdev/fsl_msi.h b/arch/powerpc/sysdev/fsl_msi.h
index df9aa9fe0933..420cfcbdac01 100644
--- a/arch/powerpc/sysdev/fsl_msi.h
+++ b/arch/powerpc/sysdev/fsl_msi.h
@@ -27,6 +27,8 @@
 #define FSL_PIC_IP_IPIC   0x00000002
 #define FSL_PIC_IP_VMPIC  0x00000003
 
+struct fsl_msi_cascade_data;
+
 struct fsl_msi {
 	struct irq_domain *irqhost;
 
@@ -37,7 +39,7 @@ struct fsl_msi {
 	u32 srs_shift; /* Shift of the shared interrupt register select */
 	void __iomem *msi_regs;
 	u32 feature;
-	int msi_virqs[NR_MSI_REG_MAX];
+	struct fsl_msi_cascade_data *cascade_array[NR_MSI_REG_MAX];
 
 	struct msi_bitmap bitmap;
 
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index c5077673bd94..65d2ed4549e6 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -522,7 +522,8 @@ int fsl_add_bridge(struct platform_device *pdev, int is_primary)
 	} else {
 		/* For PCI read PROG to identify controller mode */
 		early_read_config_byte(hose, 0, 0, PCI_CLASS_PROG, &progif);
-		if ((progif & 1) == 1)
+		if ((progif & 1) &&
+		    !of_property_read_bool(dev, "fsl,pci-agent-force-enum"))
 			goto no_bridge;
 	}
 
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index be33c9768ea1..89cec0ed6a58 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -960,7 +960,7 @@ void mpic_set_vector(unsigned int virq, unsigned int vector)
 	mpic_irq_write(src, MPIC_INFO(IRQ_VECTOR_PRI), vecpri);
 }
 
-void mpic_set_destination(unsigned int virq, unsigned int cpuid)
+static void mpic_set_destination(unsigned int virq, unsigned int cpuid)
 {
 	struct mpic *mpic = mpic_from_irq(virq);
 	unsigned int src = virq_to_hw(virq);
diff --git a/arch/powerpc/sysdev/mpic_pasemi_msi.c b/arch/powerpc/sysdev/mpic_pasemi_msi.c
index 38e62382070c..15dccd35fa11 100644
--- a/arch/powerpc/sysdev/mpic_pasemi_msi.c
+++ b/arch/powerpc/sysdev/mpic_pasemi_msi.c
@@ -63,14 +63,6 @@ static struct irq_chip mpic_pasemi_msi_chip = {
 	.name			= "PASEMI-MSI",
 };
 
-static int pasemi_msi_check_device(struct pci_dev *pdev, int nvec, int type)
-{
-	if (type == PCI_CAP_ID_MSIX)
-		pr_debug("pasemi_msi: MSI-X untested, trying anyway\n");
-
-	return 0;
-}
-
 static void pasemi_msi_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct msi_desc *entry;
@@ -97,6 +89,8 @@ static int pasemi_msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 	struct msi_msg msg;
 	int hwirq;
 
+	if (type == PCI_CAP_ID_MSIX)
+		pr_debug("pasemi_msi: MSI-X untested, trying anyway\n");
 	pr_debug("pasemi_msi_setup_msi_irqs, pdev %p nvec %d type %d\n",
 		 pdev, nvec, type);
 
@@ -169,7 +163,6 @@ int mpic_pasemi_msi_init(struct mpic *mpic)
 	WARN_ON(ppc_md.setup_msi_irqs);
 	ppc_md.setup_msi_irqs = pasemi_msi_setup_msi_irqs;
 	ppc_md.teardown_msi_irqs = pasemi_msi_teardown_msi_irqs;
-	ppc_md.msi_check_device = pasemi_msi_check_device;
 
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index 9a7aa0ed9c1c..623d7fba15b4 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -105,22 +105,6 @@ static u64 find_u4_magic_addr(struct pci_dev *pdev, unsigned int hwirq)
 	return 0;
 }
 
-static int u3msi_msi_check_device(struct pci_dev *pdev, int nvec, int type)
-{
-	if (type == PCI_CAP_ID_MSIX)
-		pr_debug("u3msi: MSI-X untested, trying anyway.\n");
-
-	/* If we can't find a magic address then MSI ain't gonna work */
-	if (find_ht_magic_addr(pdev, 0) == 0 &&
-	    find_u4_magic_addr(pdev, 0) == 0) {
-		pr_debug("u3msi: no magic address found for %s\n",
-			 pci_name(pdev));
-		return -ENXIO;
-	}
-
-	return 0;
-}
-
 static void u3msi_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct msi_desc *entry;
@@ -146,6 +130,17 @@ static int u3msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 	u64 addr;
 	int hwirq;
 
+	if (type == PCI_CAP_ID_MSIX)
+		pr_debug("u3msi: MSI-X untested, trying anyway.\n");
+
+	/* If we can't find a magic address then MSI ain't gonna work */
+	if (find_ht_magic_addr(pdev, 0) == 0 &&
+	    find_u4_magic_addr(pdev, 0) == 0) {
+		pr_debug("u3msi: no magic address found for %s\n",
+			 pci_name(pdev));
+		return -ENXIO;
+	}
+
 	list_for_each_entry(entry, &pdev->msi_list, list) {
 		hwirq = msi_bitmap_alloc_hwirqs(&msi_mpic->msi_bitmap, 1);
 		if (hwirq < 0) {
@@ -202,7 +197,6 @@ int mpic_u3msi_init(struct mpic *mpic)
 	WARN_ON(ppc_md.setup_msi_irqs);
 	ppc_md.setup_msi_irqs = u3msi_setup_msi_irqs;
 	ppc_md.teardown_msi_irqs = u3msi_teardown_msi_irqs;
-	ppc_md.msi_check_device = u3msi_msi_check_device;
 
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index 2ff630267e9e..0c75214b6f92 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -20,32 +20,37 @@ int msi_bitmap_alloc_hwirqs(struct msi_bitmap *bmp, int num)
 	int offset, order = get_count_order(num);
 
 	spin_lock_irqsave(&bmp->lock, flags);
-	/*
-	 * This is fast, but stricter than we need. We might want to add
-	 * a fallback routine which does a linear search with no alignment.
-	 */
-	offset = bitmap_find_free_region(bmp->bitmap, bmp->irq_count, order);
+
+	offset = bitmap_find_next_zero_area(bmp->bitmap, bmp->irq_count, 0,
+					    num, (1 << order) - 1);
+	if (offset > bmp->irq_count)
+		goto err;
+
+	bitmap_set(bmp->bitmap, offset, num);
 	spin_unlock_irqrestore(&bmp->lock, flags);
 
-	pr_debug("msi_bitmap: allocated 0x%x (2^%d) at offset 0x%x\n",
-		 num, order, offset);
+	pr_debug("msi_bitmap: allocated 0x%x at offset 0x%x\n", num, offset);
 
 	return offset;
+err:
+	spin_unlock_irqrestore(&bmp->lock, flags);
+	return -ENOMEM;
 }
+EXPORT_SYMBOL(msi_bitmap_alloc_hwirqs);
 
 void msi_bitmap_free_hwirqs(struct msi_bitmap *bmp, unsigned int offset,
 			    unsigned int num)
 {
 	unsigned long flags;
-	int order = get_count_order(num);
 
-	pr_debug("msi_bitmap: freeing 0x%x (2^%d) at offset 0x%x\n",
-		 num, order, offset);
+	pr_debug("msi_bitmap: freeing 0x%x at offset 0x%x\n",
+		 num, offset);
 
 	spin_lock_irqsave(&bmp->lock, flags);
-	bitmap_release_region(bmp->bitmap, offset, order);
+	bitmap_clear(bmp->bitmap, offset, num);
 	spin_unlock_irqrestore(&bmp->lock, flags);
 }
+EXPORT_SYMBOL(msi_bitmap_free_hwirqs);
 
 void msi_bitmap_reserve_hwirq(struct msi_bitmap *bmp, unsigned int hwirq)
 {
@@ -143,7 +148,7 @@ void msi_bitmap_free(struct msi_bitmap *bmp)
 #define check(x)	\
 	if (!(x)) printk("msi_bitmap: test failed at line %d\n", __LINE__);
 
-void __init test_basics(void)
+static void __init test_basics(void)
 {
 	struct msi_bitmap bmp;
 	int i, size = 512;
@@ -180,6 +185,15 @@ void __init test_basics(void)
 	msi_bitmap_free_hwirqs(&bmp, size / 2, 1);
 	check(msi_bitmap_alloc_hwirqs(&bmp, 1) == size / 2);
 
+	/* Check we get a naturally aligned offset */
+	check(msi_bitmap_alloc_hwirqs(&bmp, 2) % 2 == 0);
+	check(msi_bitmap_alloc_hwirqs(&bmp, 4) % 4 == 0);
+	check(msi_bitmap_alloc_hwirqs(&bmp, 8) % 8 == 0);
+	check(msi_bitmap_alloc_hwirqs(&bmp, 9) % 16 == 0);
+	check(msi_bitmap_alloc_hwirqs(&bmp, 3) % 4 == 0);
+	check(msi_bitmap_alloc_hwirqs(&bmp, 7) % 8 == 0);
+	check(msi_bitmap_alloc_hwirqs(&bmp, 121) % 128 == 0);
+
 	msi_bitmap_free(&bmp);
 
 	/* Clients may check bitmap == NULL for "not-allocated" */
@@ -188,7 +202,7 @@ void __init test_basics(void)
 	kfree(bmp.bitmap);
 }
 
-void __init test_of_node(void)
+static void __init test_of_node(void)
 {
 	u32 prop_data[] = { 10, 10, 25, 3, 40, 1, 100, 100, 200, 20 };
 	const char *expected_str = "0-9,20-24,28-39,41-99,220-255";
@@ -236,7 +250,7 @@ void __init test_of_node(void)
 	kfree(bmp.bitmap);
 }
 
-int __init msi_bitmap_selftest(void)
+static int __init msi_bitmap_selftest(void)
 {
 	printk(KERN_DEBUG "Running MSI bitmap self-tests ...\n");
 
diff --git a/arch/powerpc/sysdev/mv64x60_dev.c b/arch/powerpc/sysdev/mv64x60_dev.c
index c2dba7db71ad..026bbc3b2c47 100644
--- a/arch/powerpc/sysdev/mv64x60_dev.c
+++ b/arch/powerpc/sysdev/mv64x60_dev.c
@@ -23,7 +23,7 @@
 
 /* These functions provide the necessary setup for the mv64x60 drivers. */
 
-static struct of_device_id __initdata of_mv64x60_devices[] = {
+static const struct of_device_id of_mv64x60_devices[] __initconst = {
 	{ .compatible = "marvell,mv64306-devctrl", },
 	{}
 };
diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c
index 5aaf86c03893..13e67d93a7c1 100644
--- a/arch/powerpc/sysdev/pmi.c
+++ b/arch/powerpc/sysdev/pmi.c
@@ -101,7 +101,7 @@ out:
 }
 
 
-static struct of_device_id pmi_match[] = {
+static const struct of_device_id pmi_match[] = {
 	{ .type = "ibm,pmi", .name = "ibm,pmi" },
 	{ .type = "ibm,pmi" },
 	{},
diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
index 11c888416f0a..a6a4dbda9078 100644
--- a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
@@ -44,6 +44,12 @@ static int hsta_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	int irq, hwirq;
 	u64 addr;
 
+	/* We don't support MSI-X */
+	if (type == PCI_CAP_ID_MSIX) {
+		pr_debug("%s: MSI-X not supported.\n", __func__);
+		return -EINVAL;
+	}
+
 	list_for_each_entry(entry, &dev->msi_list, list) {
 		irq = msi_bitmap_alloc_hwirqs(&ppc4xx_hsta_msi.bmp, 1);
 		if (irq < 0) {
@@ -117,17 +123,6 @@ static void hsta_teardown_msi_irqs(struct pci_dev *dev)
 	}
 }
 
-static int hsta_msi_check_device(struct pci_dev *pdev, int nvec, int type)
-{
-	/* We don't support MSI-X */
-	if (type == PCI_CAP_ID_MSIX) {
-		pr_debug("%s: MSI-X not supported.\n", __func__);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static int hsta_msi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -178,7 +173,6 @@ static int hsta_msi_probe(struct platform_device *pdev)
 
 	ppc_md.setup_msi_irqs = hsta_setup_msi_irqs;
 	ppc_md.teardown_msi_irqs = hsta_teardown_msi_irqs;
-	ppc_md.msi_check_device = hsta_msi_check_device;
 	return 0;
 
 out2:
diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c
index 43948da837a7..22b5200636e7 100644
--- a/arch/powerpc/sysdev/ppc4xx_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_msi.c
@@ -85,8 +85,12 @@ static int ppc4xx_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	struct msi_desc *entry;
 	struct ppc4xx_msi *msi_data = &ppc4xx_msi;
 
-	msi_data->msi_virqs = kmalloc((msi_irqs) * sizeof(int),
-					    GFP_KERNEL);
+	dev_dbg(&dev->dev, "PCIE-MSI:%s called. vec %x type %d\n",
+		__func__, nvec, type);
+	if (type == PCI_CAP_ID_MSIX)
+		pr_debug("ppc4xx msi: MSI-X untested, trying anyway.\n");
+
+	msi_data->msi_virqs = kmalloc((msi_irqs) * sizeof(int), GFP_KERNEL);
 	if (!msi_data->msi_virqs)
 		return -ENOMEM;
 
@@ -134,16 +138,6 @@ void ppc4xx_teardown_msi_irqs(struct pci_dev *dev)
 	}
 }
 
-static int ppc4xx_msi_check_device(struct pci_dev *pdev, int nvec, int type)
-{
-	dev_dbg(&pdev->dev, "PCIE-MSI:%s called. vec %x type %d\n",
-		__func__, nvec, type);
-	if (type == PCI_CAP_ID_MSIX)
-		pr_debug("ppc4xx msi: MSI-X untested, trying anyway.\n");
-
-	return 0;
-}
-
 static int ppc4xx_setup_pcieh_hw(struct platform_device *dev,
 				 struct resource res, struct ppc4xx_msi *msi)
 {
@@ -259,7 +253,6 @@ static int ppc4xx_msi_probe(struct platform_device *dev)
 
 	ppc_md.setup_msi_irqs = ppc4xx_setup_msi_irqs;
 	ppc_md.teardown_msi_irqs = ppc4xx_teardown_msi_irqs;
-	ppc_md.msi_check_device = ppc4xx_msi_check_device;
 	return err;
 
 error_out:
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index de8d9483bbe8..2fc4cf1b7557 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -155,6 +155,31 @@ static void icp_native_cause_ipi(int cpu, unsigned long data)
 		icp_native_set_qirr(cpu, IPI_PRIORITY);
 }
 
+/*
+ * Called when an interrupt is received on an off-line CPU to
+ * clear the interrupt, so that the CPU can go back to nap mode.
+ */
+void icp_native_flush_interrupt(void)
+{
+	unsigned int xirr = icp_native_get_xirr();
+	unsigned int vec = xirr & 0x00ffffff;
+
+	if (vec == XICS_IRQ_SPURIOUS)
+		return;
+	if (vec == XICS_IPI) {
+		/* Clear pending IPI */
+		int cpu = smp_processor_id();
+		kvmppc_set_host_ipi(cpu, 0);
+		icp_native_set_qirr(cpu, 0xff);
+	} else {
+		pr_err("XICS: hw interrupt 0x%x to offline cpu, disabling\n",
+		       vec);
+		xics_mask_unknown_vec(vec);
+	}
+	/* EOI the interrupt */
+	icp_native_set_xirr(xirr);
+}
+
 void xics_wake_cpu(int cpu)
 {
 	icp_native_set_qirr(cpu, IPI_PRIORITY);
diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c
index 83f943a8e0db..56f0524e47a6 100644
--- a/arch/powerpc/sysdev/xilinx_intc.c
+++ b/arch/powerpc/sysdev/xilinx_intc.c
@@ -265,7 +265,7 @@ static void __init xilinx_i8259_setup_cascade(void)
 static inline void xilinx_i8259_setup_cascade(void) { return; }
 #endif /* defined(CONFIG_PPC_I8259) */
 
-static struct of_device_id xilinx_intc_match[] __initconst = {
+static const struct of_device_id xilinx_intc_match[] __initconst = {
 	{ .compatible = "xlnx,opb-intc-1.00.c", },
 	{ .compatible = "xlnx,xps-intc-1.00.a", },
 	{}
diff --git a/arch/powerpc/sysdev/xilinx_pci.c b/arch/powerpc/sysdev/xilinx_pci.c
index 1453b0eed220..fea5667699ed 100644
--- a/arch/powerpc/sysdev/xilinx_pci.c
+++ b/arch/powerpc/sysdev/xilinx_pci.c
@@ -27,7 +27,7 @@
 
 #define PCI_HOST_ENABLE_CMD PCI_COMMAND_SERR | PCI_COMMAND_PARITY | PCI_COMMAND_MASTER | PCI_COMMAND_MEMORY
 
-static struct of_device_id xilinx_pci_match[] = {
+static const struct of_device_id xilinx_pci_match[] = {
 	{ .compatible = "xlnx,plbv46-pci-1.03.a", },
 	{}
 };
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 05c78bb5f570..f2cf1f90295b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -58,6 +58,9 @@ config NO_IOPORT_MAP
 config PCI_QUIRKS
 	def_bool n
 
+config ARCH_SUPPORTS_UPROBES
+	def_bool 64BIT
+
 config S390
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
@@ -97,6 +100,7 @@ config S390
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS2
+	select DYNAMIC_FTRACE if FUNCTION_TRACER
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CPU_DEVICES if !SMP
 	select GENERIC_FIND_FIRST_BIT
@@ -113,10 +117,11 @@ config S390
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE if 64BIT
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS if 64BIT
 	select HAVE_FTRACE_MCOUNT_RECORD
-	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_GRAPH_TRACER if 64BIT
+	select HAVE_FUNCTION_TRACER if 64BIT
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
@@ -496,8 +501,8 @@ config QDIO
 
 menuconfig PCI
 	bool "PCI support"
-	default n
 	depends on 64BIT
+	select HAVE_DMA_ATTRS
 	select PCI_MSI
 	help
 	  Enable PCI support.
@@ -544,9 +549,6 @@ config HAS_DMA
 config NEED_SG_DMA_LENGTH
 	def_bool PCI
 
-config HAVE_DMA_ATTRS
-	def_bool PCI
-
 config NEED_DMA_MAP_STATE
 	def_bool PCI
 
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 874e6d6e9c5f..878e67973151 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -35,13 +35,16 @@ endif
 
 export LD_BFD
 
-cflags-$(CONFIG_MARCH_G5)     += -march=g5
-cflags-$(CONFIG_MARCH_Z900)   += -march=z900
-cflags-$(CONFIG_MARCH_Z990)   += -march=z990
-cflags-$(CONFIG_MARCH_Z9_109) += -march=z9-109
-cflags-$(CONFIG_MARCH_Z10)    += -march=z10
-cflags-$(CONFIG_MARCH_Z196)   += -march=z196
-cflags-$(CONFIG_MARCH_ZEC12)  += -march=zEC12
+mflags-$(CONFIG_MARCH_G5)     := -march=g5
+mflags-$(CONFIG_MARCH_Z900)   := -march=z900
+mflags-$(CONFIG_MARCH_Z990)   := -march=z990
+mflags-$(CONFIG_MARCH_Z9_109) := -march=z9-109
+mflags-$(CONFIG_MARCH_Z10)    := -march=z10
+mflags-$(CONFIG_MARCH_Z196)   := -march=z196
+mflags-$(CONFIG_MARCH_ZEC12)  := -march=zEC12
+
+aflags-y += $(mflags-y)
+cflags-y += $(mflags-y)
 
 cflags-$(CONFIG_MARCH_G5_TUNE)		+= -mtune=g5
 cflags-$(CONFIG_MARCH_Z900_TUNE)	+= -mtune=z900
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index b3fea0722ff1..773f86676588 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -2,6 +2,7 @@
 
 generic-y += clkdev.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 19ff956b752b..b5dce6544d76 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -15,11 +15,13 @@
 
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
 /* Fast-BCR without checkpoint synchronization */
-#define mb() do {  asm volatile("bcr 14,0" : : : "memory"); } while (0)
+#define __ASM_BARRIER "bcr 14,0\n"
 #else
-#define mb() do {  asm volatile("bcr 15,0" : : : "memory"); } while (0)
+#define __ASM_BARRIER "bcr 15,0\n"
 #endif
 
+#define mb() do {  asm volatile(__ASM_BARRIER : : : "memory"); } while (0)
+
 #define rmb()				mb()
 #define wmb()				mb()
 #define read_barrier_depends()		do { } while(0)
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index f65bd3634519..f8c196984853 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -8,8 +8,6 @@
 #define _S390_CPUTIME_H
 
 #include <linux/types.h>
-#include <linux/percpu.h>
-#include <linux/spinlock.h>
 #include <asm/div64.h>
 
 
@@ -18,6 +16,8 @@
 typedef unsigned long long __nocast cputime_t;
 typedef unsigned long long __nocast cputime64_t;
 
+#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
+
 static inline unsigned long __div(unsigned long long n, unsigned long base)
 {
 #ifndef CONFIG_64BIT
@@ -165,28 +165,8 @@ static inline clock_t cputime64_to_clock_t(cputime64_t cputime)
 	return clock;
 }
 
-struct s390_idle_data {
-	int nohz_delay;
-	unsigned int sequence;
-	unsigned long long idle_count;
-	unsigned long long idle_time;
-	unsigned long long clock_idle_enter;
-	unsigned long long clock_idle_exit;
-	unsigned long long timer_idle_enter;
-	unsigned long long timer_idle_exit;
-};
-
-DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
-
-cputime64_t s390_get_idle_time(int cpu);
-
-#define arch_idle_time(cpu) s390_get_idle_time(cpu)
-
-static inline int s390_nohz_delay(int cpu)
-{
-	return __get_cpu_var(s390_idle).nohz_delay != 0;
-}
+cputime64_t arch_cpu_idle_time(int cpu);
 
-#define arch_needs_cpu(cpu) s390_nohz_delay(cpu)
+#define arch_idle_time(cpu) arch_cpu_idle_time(cpu)
 
 #endif /* _S390_CPUTIME_H */
diff --git a/arch/s390/include/asm/dis.h b/arch/s390/include/asm/dis.h
index 04a83f5773cd..60323c21938b 100644
--- a/arch/s390/include/asm/dis.h
+++ b/arch/s390/include/asm/dis.h
@@ -13,12 +13,13 @@
 #define OPERAND_FPR	0x2	/* Operand printed as %fx */
 #define OPERAND_AR	0x4	/* Operand printed as %ax */
 #define OPERAND_CR	0x8	/* Operand printed as %cx */
-#define OPERAND_DISP	0x10	/* Operand printed as displacement */
-#define OPERAND_BASE	0x20	/* Operand printed as base register */
-#define OPERAND_INDEX	0x40	/* Operand printed as index register */
-#define OPERAND_PCREL	0x80	/* Operand printed as pc-relative symbol */
-#define OPERAND_SIGNED	0x100	/* Operand printed as signed value */
-#define OPERAND_LENGTH	0x200	/* Operand printed as length (+1) */
+#define OPERAND_VR	0x10	/* Operand printed as %vx */
+#define OPERAND_DISP	0x20	/* Operand printed as displacement */
+#define OPERAND_BASE	0x40	/* Operand printed as base register */
+#define OPERAND_INDEX	0x80	/* Operand printed as index register */
+#define OPERAND_PCREL	0x100	/* Operand printed as pc-relative symbol */
+#define OPERAND_SIGNED	0x200	/* Operand printed as signed value */
+#define OPERAND_LENGTH	0x400	/* Operand printed as length (+1) */
 
 
 struct s390_operand {
diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h
index 3fbc67d9e197..709955ddaa4d 100644
--- a/arch/s390/include/asm/dma-mapping.h
+++ b/arch/s390/include/asm/dma-mapping.h
@@ -56,24 +56,35 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 	return dma_addr == DMA_ERROR_CODE;
 }
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag)
+#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flags,
+				    struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
-	void *ret;
+	void *cpu_addr;
+
+	BUG_ON(!ops);
 
-	ret = ops->alloc(dev, size, dma_handle, flag, NULL);
-	debug_dma_alloc_coherent(dev, size, *dma_handle, ret);
-	return ret;
+	cpu_addr = ops->alloc(dev, size, dma_handle, flags, attrs);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+
+	return cpu_addr;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle)
+#define dma_free_coherent(d, s, c, h) dma_free_attrs(d, s, c, h, NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *cpu_addr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
-	struct dma_map_ops *dma_ops = get_dma_ops(dev);
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!ops);
 
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	dma_ops->free(dev, size, cpu_addr, dma_handle, NULL);
+	ops->free(dev, size, cpu_addr, dma_handle, attrs);
 }
 
 #endif /* _ASM_S390_DMA_MAPPING_H */
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 78f4f8711d58..f6e43d39e3d8 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -102,6 +102,7 @@
 #define HWCAP_S390_ETF3EH	256
 #define HWCAP_S390_HIGH_GPRS	512
 #define HWCAP_S390_TE		1024
+#define HWCAP_S390_VXRS		2048
 
 /*
  * These are used to set parameters in the core dumps.
@@ -225,6 +226,6 @@ int arch_setup_additional_pages(struct linux_binprm *, int);
 extern unsigned long arch_randomize_brk(struct mm_struct *mm);
 #define arch_randomize_brk arch_randomize_brk
 
-void *fill_cpu_elf_notes(void *ptr, struct save_area *sa);
+void *fill_cpu_elf_notes(void *ptr, struct save_area *sa, __vector128 *vxrs);
 
 #endif
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index bf246dae1367..3aef8afec336 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -4,6 +4,7 @@
 #ifndef __ASSEMBLY__
 
 extern void _mcount(void);
+extern char ftrace_graph_caller_end;
 
 struct dyn_arch_ftrace { };
 
@@ -17,10 +18,8 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 
 #endif /* __ASSEMBLY__ */
 
-#ifdef CONFIG_64BIT
-#define MCOUNT_INSN_SIZE  12
-#else
-#define MCOUNT_INSN_SIZE  22
-#endif
+#define MCOUNT_INSN_SIZE  18
+
+#define ARCH_SUPPORTS_FTRACE_OPS 1
 
 #endif /* _ASM_S390_FTRACE_H */
diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h
new file mode 100644
index 000000000000..6af037f574b8
--- /dev/null
+++ b/arch/s390/include/asm/idle.h
@@ -0,0 +1,26 @@
+/*
+ *  Copyright IBM Corp. 2014
+ *
+ *  Author: Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef _S390_IDLE_H
+#define _S390_IDLE_H
+
+#include <linux/types.h>
+#include <linux/device.h>
+
+struct s390_idle_data {
+	unsigned int sequence;
+	unsigned long long idle_count;
+	unsigned long long idle_time;
+	unsigned long long clock_idle_enter;
+	unsigned long long clock_idle_exit;
+	unsigned long long timer_idle_enter;
+	unsigned long long timer_idle_exit;
+};
+
+extern struct device_attribute dev_attr_idle_count;
+extern struct device_attribute dev_attr_idle_time_us;
+
+#endif /* _S390_IDLE_H */
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index c81661e756a0..ece606c2ee86 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -89,12 +89,12 @@ extern u32 ipl_flags;
 extern u32 dump_prefix_page;
 
 struct dump_save_areas {
-	struct save_area **areas;
+	struct save_area_ext **areas;
 	int count;
 };
 
 extern struct dump_save_areas dump_save_areas;
-struct save_area *dump_save_area_create(int cpu);
+struct save_area_ext *dump_save_area_create(int cpu);
 
 extern void do_reipl(void);
 extern void do_halt(void);
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index c4dd400a2791..b0d5f0a97a01 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -51,6 +51,7 @@ enum interruption_class {
 	IRQEXT_CMS,
 	IRQEXT_CMC,
 	IRQEXT_CMR,
+	IRQEXT_FTP,
 	IRQIO_CIO,
 	IRQIO_QAI,
 	IRQIO_DAS,
@@ -81,7 +82,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
 
 static __always_inline void inc_irq_stat(enum interruption_class irq)
 {
-	__get_cpu_var(irq_stat).irqs[irq]++;
+	__this_cpu_inc(irq_stat.irqs[irq]);
 }
 
 struct ext_code {
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 4176dfe0fba1..98629173ce3b 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -84,6 +84,10 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 int kprobe_exceptions_notify(struct notifier_block *self,
 	unsigned long val, void *data);
 
+int probe_is_prohibited_opcode(u16 *insn);
+int probe_get_fixup_type(u16 *insn);
+int probe_is_insn_relative_long(u16 *insn);
+
 #define flush_insn_slot(p)	do { } while (0)
 
 #endif	/* _ASM_S390_KPROBES_H */
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 4349197ab9df..6cc51fe84410 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <asm/ptrace.h>
 #include <asm/cpu.h>
+#include <asm/types.h>
 
 #ifdef CONFIG_32BIT
 
@@ -31,6 +32,11 @@ struct save_area {
 	u32	ctrl_regs[16];
 } __packed;
 
+struct save_area_ext {
+	struct save_area	sa;
+	__vector128		vx_regs[32];
+};
+
 struct _lowcore {
 	psw_t	restart_psw;			/* 0x0000 */
 	psw_t	restart_old_psw;		/* 0x0008 */
@@ -183,6 +189,11 @@ struct save_area {
 	u64	ctrl_regs[16];
 } __packed;
 
+struct save_area_ext {
+	struct save_area	sa;
+	__vector128		vx_regs[32];
+};
+
 struct _lowcore {
 	__u8	pad_0x0000[0x0014-0x0000];	/* 0x0000 */
 	__u32	ipl_parmblock_ptr;		/* 0x0014 */
@@ -310,7 +321,10 @@ struct _lowcore {
 
 	/* Extended facility list */
 	__u64	stfle_fac_list[32];		/* 0x0f00 */
-	__u8	pad_0x1000[0x11b8-0x1000];	/* 0x1000 */
+	__u8	pad_0x1000[0x11b0-0x1000];	/* 0x1000 */
+
+	/* Pointer to vector register save area */
+	__u64	vector_save_area_addr;		/* 0x11b0 */
 
 	/* 64 bit extparam used for pfault/diag 250: defined by architecture */
 	__u64	ext_params2;			/* 0x11B8 */
@@ -334,9 +348,10 @@ struct _lowcore {
 
 	/* Transaction abort diagnostic block */
 	__u8	pgm_tdb[256];			/* 0x1800 */
+	__u8	pad_0x1900[0x1c00-0x1900];	/* 0x1900 */
 
-	/* align to the top of the prefix area */
-	__u8	pad_0x1900[0x2000-0x1900];	/* 0x1900 */
+	/* Software defined save area for vector registers */
+	__u8	vector_save_area[1024];		/* 0x1c00 */
 } __packed;
 
 #endif /* CONFIG_32BIT */
diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h
index 35f8ec185616..3027a5a72b74 100644
--- a/arch/s390/include/asm/nmi.h
+++ b/arch/s390/include/asm/nmi.h
@@ -38,7 +38,7 @@ struct mci {
 	__u32 pm :  1; /* 22 psw program mask and cc validity */
 	__u32 ia :  1; /* 23 psw instruction address validity */
 	__u32 fa :  1; /* 24 failing storage address validity */
-	__u32	 :  1; /* 25 */
+	__u32 vr :  1; /* 25 vector register validity */
 	__u32 ec :  1; /* 26 external damage code validity */
 	__u32 fp :  1; /* 27 floating point register validity */
 	__u32 gr :  1; /* 28 general register validity */
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index fa91e0097458..933355e0d091 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -31,7 +31,7 @@
 	pcp_op_T__ old__, new__, prev__;				\
 	pcp_op_T__ *ptr__;						\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp));					\
+	ptr__ = raw_cpu_ptr(&(pcp));					\
 	prev__ = *ptr__;						\
 	do {								\
 		old__ = prev__;						\
@@ -70,7 +70,7 @@
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp)); 				\
+	ptr__ = raw_cpu_ptr(&(pcp)); 				\
 	if (__builtin_constant_p(val__) &&				\
 	    ((szcast)val__ > -129) && ((szcast)val__ < 128)) {		\
 		asm volatile(						\
@@ -97,7 +97,7 @@
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp)); 				\
+	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
@@ -116,7 +116,7 @@
 	pcp_op_T__ val__ = (val);					\
 	pcp_op_T__ old__, *ptr__;					\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp)); 				\
+	ptr__ = raw_cpu_ptr(&(pcp));	 				\
 	asm volatile(							\
 		op "    %[old__],%[val__],%[ptr__]\n"			\
 		: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)		\
@@ -138,7 +138,7 @@
 	pcp_op_T__ ret__;						\
 	pcp_op_T__ *ptr__;						\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp));					\
+	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = cmpxchg(ptr__, oval, nval);				\
 	preempt_enable();						\
 	ret__;								\
@@ -154,7 +154,7 @@
 	typeof(pcp) *ptr__;						\
 	typeof(pcp) ret__;						\
 	preempt_disable();						\
-	ptr__ = __this_cpu_ptr(&(pcp));					\
+	ptr__ = raw_cpu_ptr(&(pcp));					\
 	ret__ = xchg(ptr__, nval);					\
 	preempt_enable();						\
 	ret__;								\
@@ -173,8 +173,8 @@
 	typeof(pcp2) *p2__;						\
 	int ret__;							\
 	preempt_disable();						\
-	p1__ = __this_cpu_ptr(&(pcp1));					\
-	p2__ = __this_cpu_ptr(&(pcp2));					\
+	p1__ = raw_cpu_ptr(&(pcp1));					\
+	p2__ = raw_cpu_ptr(&(pcp2));					\
 	ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__);	\
 	preempt_enable();						\
 	ret__;								\
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index b7054356cc98..57c882761dea 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -217,7 +217,6 @@ extern unsigned long MODULES_END;
  */
 
 /* Hardware bits in the page table entry */
-#define _PAGE_CO	0x100		/* HW Change-bit override */
 #define _PAGE_PROTECT	0x200		/* HW read-only bit  */
 #define _PAGE_INVALID	0x400		/* HW invalid bit    */
 #define _PAGE_LARGE	0x800		/* Bit to mark a large pte */
@@ -234,8 +233,8 @@ extern unsigned long MODULES_END;
 #define __HAVE_ARCH_PTE_SPECIAL
 
 /* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK		(PAGE_MASK | _PAGE_SPECIAL | _PAGE_CO | \
-				 _PAGE_DIRTY | _PAGE_YOUNG)
+#define _PAGE_CHG_MASK		(PAGE_MASK | _PAGE_SPECIAL | _PAGE_DIRTY | \
+				 _PAGE_YOUNG)
 
 /*
  * handle_pte_fault uses pte_present, pte_none and pte_file to find out the
@@ -354,7 +353,6 @@ extern unsigned long MODULES_END;
 
 #define _REGION3_ENTRY_LARGE	0x400	/* RTTE-format control, large page  */
 #define _REGION3_ENTRY_RO	0x200	/* page protection bit		    */
-#define _REGION3_ENTRY_CO	0x100	/* change-recording override	    */
 
 /* Bits in the segment table entry */
 #define _SEGMENT_ENTRY_BITS	0xfffffffffffffe33UL
@@ -371,7 +369,6 @@ extern unsigned long MODULES_END;
 #define _SEGMENT_ENTRY_YOUNG	0x1000	/* SW segment young bit */
 #define _SEGMENT_ENTRY_SPLIT	0x0800	/* THP splitting bit */
 #define _SEGMENT_ENTRY_LARGE	0x0400	/* STE-format control, large page */
-#define _SEGMENT_ENTRY_CO	0x0100	/* change-recording override   */
 #define _SEGMENT_ENTRY_READ	0x0002	/* SW segment read bit */
 #define _SEGMENT_ENTRY_WRITE	0x0001	/* SW segment write bit */
 
@@ -873,8 +870,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 		pgste = pgste_set_pte(ptep, pgste, entry);
 		pgste_set_unlock(ptep, pgste);
 	} else {
-		if (!(pte_val(entry) & _PAGE_INVALID) && MACHINE_HAS_EDAT1)
-			pte_val(entry) |= _PAGE_CO;
 		*ptep = entry;
 	}
 }
@@ -1044,6 +1039,22 @@ static inline void __ptep_ipte_local(unsigned long address, pte_t *ptep)
 		: "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address));
 }
 
+static inline void __ptep_ipte_range(unsigned long address, int nr, pte_t *ptep)
+{
+	unsigned long pto = (unsigned long) ptep;
+
+#ifndef CONFIG_64BIT
+	/* pto in ESA mode must point to the start of the segment table */
+	pto &= 0x7ffffc00;
+#endif
+	/* Invalidate a range of ptes + global TLB flush of the ptes */
+	do {
+		asm volatile(
+			"	.insn rrf,0xb2210000,%2,%0,%1,0"
+			: "+a" (address), "+a" (nr) : "a" (pto) : "memory");
+	} while (nr != 255);
+}
+
 static inline void ptep_flush_direct(struct mm_struct *mm,
 				     unsigned long address, pte_t *ptep)
 {
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index e568fc8a7250..d559bdb03d18 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -13,9 +13,11 @@
 
 #define CIF_MCCK_PENDING	0	/* machine check handling is pending */
 #define CIF_ASCE		1	/* user asce needs fixup / uaccess */
+#define CIF_NOHZ_DELAY		2	/* delay HZ disable for a tick */
 
 #define _CIF_MCCK_PENDING	(1<<CIF_MCCK_PENDING)
 #define _CIF_ASCE		(1<<CIF_ASCE)
+#define _CIF_NOHZ_DELAY		(1<<CIF_NOHZ_DELAY)
 
 
 #ifndef __ASSEMBLY__
@@ -43,6 +45,8 @@ static inline int test_cpu_flag(int flag)
 	return !!(S390_lowcore.cpu_flags & (1U << flag));
 }
 
+#define arch_needs_cpu() test_cpu_flag(CIF_NOHZ_DELAY)
+
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter").
@@ -113,6 +117,7 @@ struct thread_struct {
 	int ri_signum;
 #ifdef CONFIG_64BIT
 	unsigned char trap_tdb[256];	/* Transaction abort diagnose block */
+	__vector128 *vxrs;		/* Vector register save area */
 #endif
 };
 
@@ -285,7 +290,12 @@ static inline unsigned long __rewind_psw(psw_t psw, unsigned long ilc)
 	return (psw.addr - ilc) & mask;
 #endif
 }
- 
+
+/*
+ * Function to stop a processor until the next interrupt occurs
+ */
+void enabled_wait(void);
+
 /*
  * Function to drop a processor into disabled wait state
  */
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 55d69dd7473c..be317feff7ac 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -161,6 +161,12 @@ static inline long regs_return_value(struct pt_regs *regs)
 	return regs->gprs[2];
 }
 
+static inline void instruction_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	regs->psw.addr = val | PSW_ADDR_AMODE;
+}
+
 int regs_query_register_offset(const char *name);
 const char *regs_query_register_name(unsigned int offset);
 unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset);
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 089a49814c50..7736fdd72595 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -55,8 +55,8 @@ extern void detect_memory_memblock(void);
 #define MACHINE_FLAG_LPP	(1UL << 13)
 #define MACHINE_FLAG_TOPOLOGY	(1UL << 14)
 #define MACHINE_FLAG_TE		(1UL << 15)
-#define MACHINE_FLAG_RRBM	(1UL << 16)
 #define MACHINE_FLAG_TLB_LC	(1UL << 17)
+#define MACHINE_FLAG_VX		(1UL << 18)
 
 #define MACHINE_IS_VM		(S390_lowcore.machine_flags & MACHINE_FLAG_VM)
 #define MACHINE_IS_KVM		(S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -78,8 +78,8 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_LPP		(0)
 #define MACHINE_HAS_TOPOLOGY	(0)
 #define MACHINE_HAS_TE		(0)
-#define MACHINE_HAS_RRBM	(0)
 #define MACHINE_HAS_TLB_LC	(0)
+#define MACHINE_HAS_VX		(0)
 #else /* CONFIG_64BIT */
 #define MACHINE_HAS_IEEE	(1)
 #define MACHINE_HAS_CSP		(1)
@@ -91,8 +91,8 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_LPP		(S390_lowcore.machine_flags & MACHINE_FLAG_LPP)
 #define MACHINE_HAS_TOPOLOGY	(S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY)
 #define MACHINE_HAS_TE		(S390_lowcore.machine_flags & MACHINE_FLAG_TE)
-#define MACHINE_HAS_RRBM	(S390_lowcore.machine_flags & MACHINE_FLAG_RRBM)
 #define MACHINE_HAS_TLB_LC	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC)
+#define MACHINE_HAS_VX		(S390_lowcore.machine_flags & MACHINE_FLAG_VX)
 #endif /* CONFIG_64BIT */
 
 /*
diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h
index bf9c823d4020..49576115dbb7 100644
--- a/arch/s390/include/asm/sigp.h
+++ b/arch/s390/include/asm/sigp.h
@@ -15,6 +15,7 @@
 #define SIGP_SET_ARCHITECTURE	     18
 #define SIGP_COND_EMERGENCY_SIGNAL   19
 #define SIGP_SENSE_RUNNING	     21
+#define SIGP_STORE_ADDITIONAL_STATUS 23
 
 /* SIGP condition codes */
 #define SIGP_CC_ORDER_CODE_ACCEPTED 0
@@ -33,9 +34,10 @@
 
 #ifndef __ASSEMBLY__
 
-static inline int __pcpu_sigp(u16 addr, u8 order, u32 parm, u32 *status)
+static inline int __pcpu_sigp(u16 addr, u8 order, unsigned long parm,
+			      u32 *status)
 {
-	register unsigned int reg1 asm ("1") = parm;
+	register unsigned long reg1 asm ("1") = parm;
 	int cc;
 
 	asm volatile(
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 4f1307962a95..762d4f88af5a 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -29,7 +29,6 @@ extern int smp_find_processor_id(u16 address);
 extern int smp_store_status(int cpu);
 extern int smp_vcpu_scheduled(int cpu);
 extern void smp_yield_cpu(int cpu);
-extern void smp_yield(void);
 extern void smp_cpu_set_polarization(int cpu, int val);
 extern int smp_cpu_get_polarization(int cpu);
 extern void smp_fill_possible_mask(void);
@@ -50,7 +49,6 @@ static inline int smp_find_processor_id(u16 address) { return 0; }
 static inline int smp_store_status(int cpu) { return 0; }
 static inline int smp_vcpu_scheduled(int cpu) { return 1; }
 static inline void smp_yield_cpu(int cpu) { }
-static inline void smp_yield(void) { }
 static inline void smp_fill_possible_mask(void) { }
 
 #endif /* CONFIG_SMP */
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 96879f7ad6da..d6bdf906caa5 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -37,11 +37,17 @@ _raw_compare_and_swap(unsigned int *lock, unsigned int old, unsigned int new)
  * (the type definitions are in asm/spinlock_types.h)
  */
 
+void arch_lock_relax(unsigned int cpu);
+
 void arch_spin_lock_wait(arch_spinlock_t *);
 int arch_spin_trylock_retry(arch_spinlock_t *);
-void arch_spin_relax(arch_spinlock_t *);
 void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);
 
+static inline void arch_spin_relax(arch_spinlock_t *lock)
+{
+	arch_lock_relax(lock->lock);
+}
+
 static inline u32 arch_spin_lockval(int cpu)
 {
 	return ~cpu;
@@ -64,11 +70,6 @@ static inline int arch_spin_trylock_once(arch_spinlock_t *lp)
 		      _raw_compare_and_swap(&lp->lock, 0, SPINLOCK_LOCKVAL));
 }
 
-static inline int arch_spin_tryrelease_once(arch_spinlock_t *lp)
-{
-	return _raw_compare_and_swap(&lp->lock, SPINLOCK_LOCKVAL, 0);
-}
-
 static inline void arch_spin_lock(arch_spinlock_t *lp)
 {
 	if (!arch_spin_trylock_once(lp))
@@ -91,7 +92,13 @@ static inline int arch_spin_trylock(arch_spinlock_t *lp)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lp)
 {
-	arch_spin_tryrelease_once(lp);
+	typecheck(unsigned int, lp->lock);
+	asm volatile(
+		__ASM_BARRIER
+		"st	%1,%0\n"
+		: "+Q" (lp->lock)
+		: "d" (0)
+		: "cc", "memory");
 }
 
 static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
@@ -123,13 +130,12 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
  */
 #define arch_write_can_lock(x) ((x)->lock == 0)
 
-extern void _raw_read_lock_wait(arch_rwlock_t *lp);
-extern void _raw_read_lock_wait_flags(arch_rwlock_t *lp, unsigned long flags);
 extern int _raw_read_trylock_retry(arch_rwlock_t *lp);
-extern void _raw_write_lock_wait(arch_rwlock_t *lp);
-extern void _raw_write_lock_wait_flags(arch_rwlock_t *lp, unsigned long flags);
 extern int _raw_write_trylock_retry(arch_rwlock_t *lp);
 
+#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
+#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
+
 static inline int arch_read_trylock_once(arch_rwlock_t *rw)
 {
 	unsigned int old = ACCESS_ONCE(rw->lock);
@@ -144,16 +150,82 @@ static inline int arch_write_trylock_once(arch_rwlock_t *rw)
 		      _raw_compare_and_swap(&rw->lock, 0, 0x80000000));
 }
 
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+
+#define __RAW_OP_OR	"lao"
+#define __RAW_OP_AND	"lan"
+#define __RAW_OP_ADD	"laa"
+
+#define __RAW_LOCK(ptr, op_val, op_string)		\
+({							\
+	unsigned int old_val;				\
+							\
+	typecheck(unsigned int *, ptr);			\
+	asm volatile(					\
+		op_string "	%0,%2,%1\n"		\
+		"bcr	14,0\n"				\
+		: "=d" (old_val), "+Q" (*ptr)		\
+		: "d" (op_val)				\
+		: "cc", "memory");			\
+	old_val;					\
+})
+
+#define __RAW_UNLOCK(ptr, op_val, op_string)		\
+({							\
+	unsigned int old_val;				\
+							\
+	typecheck(unsigned int *, ptr);			\
+	asm volatile(					\
+		"bcr	14,0\n"				\
+		op_string "	%0,%2,%1\n"		\
+		: "=d" (old_val), "+Q" (*ptr)		\
+		: "d" (op_val)				\
+		: "cc", "memory");			\
+	old_val;					\
+})
+
+extern void _raw_read_lock_wait(arch_rwlock_t *lp);
+extern void _raw_write_lock_wait(arch_rwlock_t *lp, unsigned int prev);
+
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
-	if (!arch_read_trylock_once(rw))
+	unsigned int old;
+
+	old = __RAW_LOCK(&rw->lock, 1, __RAW_OP_ADD);
+	if ((int) old < 0)
 		_raw_read_lock_wait(rw);
 }
 
-static inline void arch_read_lock_flags(arch_rwlock_t *rw, unsigned long flags)
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	__RAW_UNLOCK(&rw->lock, -1, __RAW_OP_ADD);
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned int old;
+
+	old = __RAW_LOCK(&rw->lock, 0x80000000, __RAW_OP_OR);
+	if (old != 0)
+		_raw_write_lock_wait(rw, old);
+	rw->owner = SPINLOCK_LOCKVAL;
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	rw->owner = 0;
+	__RAW_UNLOCK(&rw->lock, 0x7fffffff, __RAW_OP_AND);
+}
+
+#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
+
+extern void _raw_read_lock_wait(arch_rwlock_t *lp);
+extern void _raw_write_lock_wait(arch_rwlock_t *lp);
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	if (!arch_read_trylock_once(rw))
-		_raw_read_lock_wait_flags(rw, flags);
+		_raw_read_lock_wait(rw);
 }
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
@@ -169,19 +241,24 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	if (!arch_write_trylock_once(rw))
 		_raw_write_lock_wait(rw);
-}
-
-static inline void arch_write_lock_flags(arch_rwlock_t *rw, unsigned long flags)
-{
-	if (!arch_write_trylock_once(rw))
-		_raw_write_lock_wait_flags(rw, flags);
+	rw->owner = SPINLOCK_LOCKVAL;
 }
 
 static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
-	_raw_compare_and_swap(&rw->lock, 0x80000000, 0);
+	typecheck(unsigned int, rw->lock);
+
+	rw->owner = 0;
+	asm volatile(
+		__ASM_BARRIER
+		"st	%1,%0\n"
+		: "+Q" (rw->lock)
+		: "d" (0)
+		: "cc", "memory");
 }
 
+#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
+
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
 	if (!arch_read_trylock_once(rw))
@@ -191,12 +268,20 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-	if (!arch_write_trylock_once(rw))
-		return _raw_write_trylock_retry(rw);
+	if (!arch_write_trylock_once(rw) && !_raw_write_trylock_retry(rw))
+		return 0;
+	rw->owner = SPINLOCK_LOCKVAL;
 	return 1;
 }
 
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
+static inline void arch_read_relax(arch_rwlock_t *rw)
+{
+	arch_lock_relax(rw->owner);
+}
+
+static inline void arch_write_relax(arch_rwlock_t *rw)
+{
+	arch_lock_relax(rw->owner);
+}
 
 #endif /* __ASM_SPINLOCK_H */
diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h
index b2cd6ff7c2c5..d84b6939237c 100644
--- a/arch/s390/include/asm/spinlock_types.h
+++ b/arch/s390/include/asm/spinlock_types.h
@@ -13,6 +13,7 @@ typedef struct {
 
 typedef struct {
 	unsigned int lock;
+	unsigned int owner;
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index 18ea9e3f8142..2542a7e4c8b4 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -103,6 +103,61 @@ static inline void restore_fp_regs(freg_t *fprs)
 	asm volatile("ld 15,%0" : : "Q" (fprs[15]));
 }
 
+static inline void save_vx_regs(__vector128 *vxrs)
+{
+	typedef struct { __vector128 _[__NUM_VXRS]; } addrtype;
+
+	asm volatile(
+		"	la	1,%0\n"
+		"	.word	0xe70f,0x1000,0x003e\n"	/* vstm 0,15,0(1) */
+		"	.word	0xe70f,0x1100,0x0c3e\n"	/* vstm 16,31,256(1) */
+		: "=Q" (*(addrtype *) vxrs) : : "1");
+}
+
+static inline void save_vx_regs_safe(__vector128 *vxrs)
+{
+	unsigned long cr0, flags;
+
+	flags = arch_local_irq_save();
+	__ctl_store(cr0, 0, 0);
+	__ctl_set_bit(0, 17);
+	__ctl_set_bit(0, 18);
+	save_vx_regs(vxrs);
+	__ctl_load(cr0, 0, 0);
+	arch_local_irq_restore(flags);
+}
+
+static inline void restore_vx_regs(__vector128 *vxrs)
+{
+	typedef struct { __vector128 _[__NUM_VXRS]; } addrtype;
+
+	asm volatile(
+		"	la	1,%0\n"
+		"	.word	0xe70f,0x1000,0x0036\n"	/* vlm 0,15,0(1) */
+		"	.word	0xe70f,0x1100,0x0c36\n"	/* vlm 16,31,256(1) */
+		: : "Q" (*(addrtype *) vxrs) : "1");
+}
+
+static inline void save_fp_vx_regs(struct task_struct *task)
+{
+#ifdef CONFIG_64BIT
+	if (task->thread.vxrs)
+		save_vx_regs(task->thread.vxrs);
+	else
+#endif
+	save_fp_regs(task->thread.fp_regs.fprs);
+}
+
+static inline void restore_fp_vx_regs(struct task_struct *task)
+{
+#ifdef CONFIG_64BIT
+	if (task->thread.vxrs)
+		restore_vx_regs(task->thread.vxrs);
+	else
+#endif
+	restore_fp_regs(task->thread.fp_regs.fprs);
+}
+
 static inline void save_access_regs(unsigned int *acrs)
 {
 	typedef struct { int _[NUM_ACRS]; } acrstype;
@@ -120,16 +175,16 @@ static inline void restore_access_regs(unsigned int *acrs)
 #define switch_to(prev,next,last) do {					\
 	if (prev->mm) {							\
 		save_fp_ctl(&prev->thread.fp_regs.fpc);			\
-		save_fp_regs(prev->thread.fp_regs.fprs);		\
+		save_fp_vx_regs(prev);					\
 		save_access_regs(&prev->thread.acrs[0]);		\
 		save_ri_cb(prev->thread.ri_cb);				\
 	}								\
 	if (next->mm) {							\
+		update_cr_regs(next);					\
 		restore_fp_ctl(&next->thread.fp_regs.fpc);		\
-		restore_fp_regs(next->thread.fp_regs.fprs);		\
+		restore_fp_vx_regs(next);				\
 		restore_access_regs(&next->thread.acrs[0]);		\
 		restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb);	\
-		update_cr_regs(next);					\
 	}								\
 	prev = __switch_to(prev,next);					\
 } while (0)
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index b833e9c0bfbf..4d62fd5b56e5 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -84,11 +84,13 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_AUDIT	4	/* syscall auditing active */
 #define TIF_SECCOMP		5	/* secure computing */
 #define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
+#define TIF_UPROBE		7	/* breakpointed or single-stepping */
 #define TIF_31BIT		16	/* 32bit process */
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK	18	/* restore signal mask in do_signal() */
 #define TIF_SINGLE_STEP		19	/* This task is single stepped */
 #define TIF_BLOCK_STEP		20	/* This task is block stepped */
+#define TIF_UPROBE_SINGLESTEP	21	/* This task is uprobe single stepped */
 
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
@@ -97,6 +99,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
+#define _TIF_UPROBE		(1<<TIF_UPROBE)
 #define _TIF_31BIT		(1<<TIF_31BIT)
 #define _TIF_SINGLE_STEP	(1<<TIF_SINGLE_STEP)
 
diff --git a/arch/s390/include/asm/uprobes.h b/arch/s390/include/asm/uprobes.h
new file mode 100644
index 000000000000..1411dff7fea7
--- /dev/null
+++ b/arch/s390/include/asm/uprobes.h
@@ -0,0 +1,42 @@
+/*
+ *    User-space Probes (UProbes) for s390
+ *
+ *    Copyright IBM Corp. 2014
+ *    Author(s): Jan Willeke,
+ */
+
+#ifndef _ASM_UPROBES_H
+#define _ASM_UPROBES_H
+
+#include <linux/notifier.h>
+
+typedef u16 uprobe_opcode_t;
+
+#define UPROBE_XOL_SLOT_BYTES	256 /* cache aligned */
+
+#define UPROBE_SWBP_INSN	0x0002
+#define UPROBE_SWBP_INSN_SIZE	2
+
+struct arch_uprobe {
+	union{
+		uprobe_opcode_t insn[3];
+		uprobe_opcode_t ixol[3];
+	};
+	unsigned int saved_per : 1;
+	unsigned int saved_int_code;
+};
+
+struct arch_uprobe_task {
+};
+
+int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm,
+			     unsigned long addr);
+int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
+bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
+int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val,
+				 void *data);
+void arch_uprobe_abort_xol(struct arch_uprobe *ap, struct pt_regs *regs);
+unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline,
+						struct pt_regs *regs);
+#endif	/* _ASM_UPROBES_H */
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index bc9746a7d47c..a62526d09201 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -22,13 +22,17 @@ struct vdso_data {
 	__u64 xtime_tod_stamp;		/* TOD clock for xtime		0x08 */
 	__u64 xtime_clock_sec;		/* Kernel time			0x10 */
 	__u64 xtime_clock_nsec;		/*				0x18 */
-	__u64 wtom_clock_sec;		/* Wall to monotonic clock	0x20 */
-	__u64 wtom_clock_nsec;		/*				0x28 */
-	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x30 */
-	__u32 tz_dsttime;		/* Type of dst correction	0x34 */
-	__u32 ectg_available;		/* ECTG instruction present	0x38 */
-	__u32 tk_mult;			/* Mult. used for xtime_nsec	0x3c */
-	__u32 tk_shift;			/* Shift used for xtime_nsec	0x40 */
+	__u64 xtime_coarse_sec;		/* Coarse kernel time		0x20 */
+	__u64 xtime_coarse_nsec;	/*				0x28 */
+	__u64 wtom_clock_sec;		/* Wall to monotonic clock	0x30 */
+	__u64 wtom_clock_nsec;		/*				0x38 */
+	__u64 wtom_coarse_sec;		/* Coarse wall to monotonic	0x40 */
+	__u64 wtom_coarse_nsec;		/*				0x48 */
+	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x50 */
+	__u32 tz_dsttime;		/* Type of dst correction	0x54 */
+	__u32 ectg_available;		/* ECTG instruction present	0x58 */
+	__u32 tk_mult;			/* Mult. used for xtime_nsec	0x5c */
+	__u32 tk_shift;			/* Shift used for xtime_nsec	0x60 */
 };
 
 struct vdso_per_cpu_data {
diff --git a/arch/s390/include/asm/vtimer.h b/arch/s390/include/asm/vtimer.h
index bfe25d513ad2..10a179af62d8 100644
--- a/arch/s390/include/asm/vtimer.h
+++ b/arch/s390/include/asm/vtimer.h
@@ -28,6 +28,4 @@ extern int del_virt_timer(struct vtimer_list *timer);
 extern void init_cpu_vtimer(void);
 extern void vtime_init(void);
 
-extern void vtime_stop_cpu(void);
-
 #endif /* _ASM_S390_TIMER_H */
diff --git a/arch/s390/include/uapi/asm/sigcontext.h b/arch/s390/include/uapi/asm/sigcontext.h
index b30de9c01bbe..5f0b8d7ddb0b 100644
--- a/arch/s390/include/uapi/asm/sigcontext.h
+++ b/arch/s390/include/uapi/asm/sigcontext.h
@@ -7,10 +7,14 @@
 #define _ASM_S390_SIGCONTEXT_H
 
 #include <linux/compiler.h>
+#include <linux/types.h>
 
-#define __NUM_GPRS 16
-#define __NUM_FPRS 16
-#define __NUM_ACRS 16
+#define __NUM_GPRS		16
+#define __NUM_FPRS		16
+#define __NUM_ACRS		16
+#define __NUM_VXRS		32
+#define __NUM_VXRS_LOW		16
+#define __NUM_VXRS_HIGH		16
 
 #ifndef __s390x__
 
@@ -59,6 +63,16 @@ typedef struct
 	_s390_fp_regs     fpregs;
 } _sigregs;
 
+typedef struct
+{
+#ifndef __s390x__
+	unsigned long gprs_high[__NUM_GPRS];
+#endif
+	unsigned long long vxrs_low[__NUM_VXRS_LOW];
+	__vector128 vxrs_high[__NUM_VXRS_HIGH];
+	unsigned char __reserved[128];
+} _sigregs_ext;
+
 struct sigcontext
 {
 	unsigned long	oldmask[_SIGCONTEXT_NSIG_WORDS];
diff --git a/arch/s390/include/uapi/asm/types.h b/arch/s390/include/uapi/asm/types.h
index 038f2b9178a4..3c3951e3415b 100644
--- a/arch/s390/include/uapi/asm/types.h
+++ b/arch/s390/include/uapi/asm/types.h
@@ -17,6 +17,10 @@
 typedef unsigned long addr_t; 
 typedef __signed__ long saddr_t;
 
+typedef struct {
+	__u32 u[4];
+} __vector128;
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _UAPI_S390_TYPES_H */
diff --git a/arch/s390/include/uapi/asm/ucontext.h b/arch/s390/include/uapi/asm/ucontext.h
index 3e077b2a4705..64a69aa5dde0 100644
--- a/arch/s390/include/uapi/asm/ucontext.h
+++ b/arch/s390/include/uapi/asm/ucontext.h
@@ -7,10 +7,15 @@
 #ifndef _ASM_S390_UCONTEXT_H
 #define _ASM_S390_UCONTEXT_H
 
-#define UC_EXTENDED	0x00000001
-
-#ifndef __s390x__
+#define UC_GPRS_HIGH	1	/* uc_mcontext_ext has valid high gprs */
+#define UC_VXRS		2	/* uc_mcontext_ext has valid vector regs */
 
+/*
+ * The struct ucontext_extended describes how the registers are stored
+ * on a rt signal frame. Please note that the structure is not fixed,
+ * if new CPU registers are added to the user state the size of the
+ * struct ucontext_extended will increase.
+ */
 struct ucontext_extended {
 	unsigned long	  uc_flags;
 	struct ucontext  *uc_link;
@@ -19,11 +24,9 @@ struct ucontext_extended {
 	sigset_t	  uc_sigmask;
 	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
 	unsigned char	  __unused[128 - sizeof(sigset_t)];
-	unsigned long	  uc_gprs_high[16];
+	_sigregs_ext	  uc_mcontext_ext;
 };
 
-#endif
-
 struct ucontext {
 	unsigned long	  uc_flags;
 	struct ucontext  *uc_link;
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index a95c4ca99617..204c43a4c245 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -28,7 +28,7 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 CFLAGS_sysinfo.o += -Iinclude/math-emu -Iarch/s390/math-emu -w
 
-obj-y	:= traps.o time.o process.o base.o early.o setup.o vtime.o
+obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
 obj-y	+= debug.o irq.o ipl.o dis.o diag.o sclp.o vdso.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
@@ -52,11 +52,9 @@ obj-$(CONFIG_COMPAT)		+= compat_wrapper.o $(compat-obj-y)
 
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
-obj-$(CONFIG_FUNCTION_TRACER)	+= $(if $(CONFIG_64BIT),mcount64.o,mcount.o)
-obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
-obj-$(CONFIG_FTRACE_SYSCALLS)  += ftrace.o
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+obj-$(CONFIG_UPROBES)		+= uprobes.o
 
 ifdef CONFIG_64BIT
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o perf_cpum_sf.o \
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index afe1715a4eb7..ef279a136801 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -9,7 +9,7 @@
 #include <linux/kbuild.h>
 #include <linux/kvm_host.h>
 #include <linux/sched.h>
-#include <asm/cputime.h>
+#include <asm/idle.h>
 #include <asm/vdso.h>
 #include <asm/pgtable.h>
 
@@ -62,8 +62,12 @@ int main(void)
 	DEFINE(__VDSO_XTIME_STAMP, offsetof(struct vdso_data, xtime_tod_stamp));
 	DEFINE(__VDSO_XTIME_SEC, offsetof(struct vdso_data, xtime_clock_sec));
 	DEFINE(__VDSO_XTIME_NSEC, offsetof(struct vdso_data, xtime_clock_nsec));
+	DEFINE(__VDSO_XTIME_CRS_SEC, offsetof(struct vdso_data, xtime_coarse_sec));
+	DEFINE(__VDSO_XTIME_CRS_NSEC, offsetof(struct vdso_data, xtime_coarse_nsec));
 	DEFINE(__VDSO_WTOM_SEC, offsetof(struct vdso_data, wtom_clock_sec));
 	DEFINE(__VDSO_WTOM_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
+	DEFINE(__VDSO_WTOM_CRS_SEC, offsetof(struct vdso_data, wtom_coarse_sec));
+	DEFINE(__VDSO_WTOM_CRS_NSEC, offsetof(struct vdso_data, wtom_coarse_nsec));
 	DEFINE(__VDSO_TIMEZONE, offsetof(struct vdso_data, tz_minuteswest));
 	DEFINE(__VDSO_ECTG_OK, offsetof(struct vdso_data, ectg_available));
 	DEFINE(__VDSO_TK_MULT, offsetof(struct vdso_data, tk_mult));
@@ -73,8 +77,11 @@ int main(void)
 	/* constants used by the vdso */
 	DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME);
 	DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC);
+	DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
+	DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
 	DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID);
 	DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
+	DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC);
 	BLANK();
 	/* idle data offsets */
 	DEFINE(__CLOCK_IDLE_ENTER, offsetof(struct s390_idle_data, clock_idle_enter));
diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h
index 70d4b7c4beaa..a0a886c04977 100644
--- a/arch/s390/kernel/compat_linux.h
+++ b/arch/s390/kernel/compat_linux.h
@@ -50,6 +50,14 @@ typedef struct
 	_s390_fp_regs32     fpregs;
 } _sigregs32;
 
+typedef struct
+{
+	__u32 gprs_high[__NUM_GPRS];
+	__u64 vxrs_low[__NUM_VXRS_LOW];
+	__vector128 vxrs_high[__NUM_VXRS_HIGH];
+	__u8 __reserved[128];
+} _sigregs_ext32;
+
 #define _SIGCONTEXT_NSIG32	64
 #define _SIGCONTEXT_NSIG_BPW32	32
 #define __SIGNAL_FRAMESIZE32	96
@@ -72,6 +80,7 @@ struct ucontext32 {
 	compat_sigset_t		uc_sigmask;
 	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
 	unsigned char		__unused[128 - sizeof(compat_sigset_t)];
+	_sigregs_ext32		uc_mcontext_ext;
 };
 
 struct stat64_emu31;
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 598b0b42668b..009f5eb11125 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -36,17 +36,16 @@ typedef struct
 	struct sigcontext32 sc;
 	_sigregs32 sregs;
 	int signo;
-	__u32 gprs_high[NUM_GPRS];
-	__u8 retcode[S390_SYSCALL_SIZE];
+	_sigregs_ext32 sregs_ext;
+	__u16 svc_insn;		/* Offset of svc_insn is NOT fixed! */
 } sigframe32;
 
 typedef struct 
 {
 	__u8 callee_used_stack[__SIGNAL_FRAMESIZE32];
-	__u8 retcode[S390_SYSCALL_SIZE];
+	__u16 svc_insn;
 	compat_siginfo_t info;
 	struct ucontext32 uc;
-	__u32 gprs_high[NUM_GPRS];
 } rt_sigframe32;
 
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
@@ -151,6 +150,38 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 	return err ? -EFAULT : 0;
 }
 
+/* Store registers needed to create the signal frame */
+static void store_sigregs(void)
+{
+	int i;
+
+	save_access_regs(current->thread.acrs);
+	save_fp_ctl(&current->thread.fp_regs.fpc);
+	if (current->thread.vxrs) {
+		save_vx_regs(current->thread.vxrs);
+		for (i = 0; i < __NUM_FPRS; i++)
+			current->thread.fp_regs.fprs[i] =
+				*(freg_t *)(current->thread.vxrs + i);
+	} else
+		save_fp_regs(current->thread.fp_regs.fprs);
+}
+
+/* Load registers after signal return */
+static void load_sigregs(void)
+{
+	int i;
+
+	restore_access_regs(current->thread.acrs);
+	/* restore_fp_ctl is done in restore_sigregs */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_FPRS; i++)
+			*(freg_t *)(current->thread.vxrs + i) =
+				current->thread.fp_regs.fprs[i];
+		restore_vx_regs(current->thread.vxrs);
+	} else
+		restore_fp_regs(current->thread.fp_regs.fprs);
+}
+
 static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs)
 {
 	_sigregs32 user_sregs;
@@ -163,11 +194,8 @@ static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs)
 		(__u32)(regs->psw.mask & PSW_MASK_BA);
 	for (i = 0; i < NUM_GPRS; i++)
 		user_sregs.regs.gprs[i] = (__u32) regs->gprs[i];
-	save_access_regs(current->thread.acrs);
 	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
 	       sizeof(user_sregs.regs.acrs));
-	save_fp_ctl(&current->thread.fp_regs.fpc);
-	save_fp_regs(current->thread.fp_regs.fprs);
 	memcpy(&user_sregs.fpregs, &current->thread.fp_regs,
 	       sizeof(user_sregs.fpregs));
 	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs32)))
@@ -207,37 +235,67 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 		regs->gprs[i] = (__u64) user_sregs.regs.gprs[i];
 	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
 	       sizeof(current->thread.acrs));
-	restore_access_regs(current->thread.acrs);
 
 	memcpy(&current->thread.fp_regs, &user_sregs.fpregs,
 	       sizeof(current->thread.fp_regs));
 
-	restore_fp_regs(current->thread.fp_regs.fprs);
 	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
 }
 
-static int save_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs)
+static int save_sigregs_ext32(struct pt_regs *regs,
+			      _sigregs_ext32 __user *sregs_ext)
 {
 	__u32 gprs_high[NUM_GPRS];
+	__u64 vxrs[__NUM_VXRS_LOW];
 	int i;
 
+	/* Save high gprs to signal stack */
 	for (i = 0; i < NUM_GPRS; i++)
 		gprs_high[i] = regs->gprs[i] >> 32;
-	if (__copy_to_user(uregs, &gprs_high, sizeof(gprs_high)))
+	if (__copy_to_user(&sregs_ext->gprs_high, &gprs_high,
+			   sizeof(sregs_ext->gprs_high)))
 		return -EFAULT;
+
+	/* Save vector registers to signal stack */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(current->thread.vxrs + i) + 1);
+		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
+				   sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_to_user(&sregs_ext->vxrs_high,
+				   current->thread.vxrs + __NUM_VXRS_LOW,
+				   sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+	}
 	return 0;
 }
 
-static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs)
+static int restore_sigregs_ext32(struct pt_regs *regs,
+				 _sigregs_ext32 __user *sregs_ext)
 {
 	__u32 gprs_high[NUM_GPRS];
+	__u64 vxrs[__NUM_VXRS_LOW];
 	int i;
 
-	if (__copy_from_user(&gprs_high, uregs, sizeof(gprs_high)))
+	/* Restore high gprs from signal stack */
+	if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high,
+			     sizeof(&sregs_ext->gprs_high)))
 		return -EFAULT;
 	for (i = 0; i < NUM_GPRS; i++)
 		*(__u32 *)&regs->gprs[i] = gprs_high[i];
+
+	/* Restore vector registers from signal stack */
+	if (current->thread.vxrs) {
+		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
+				     sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_from_user(current->thread.vxrs + __NUM_VXRS_LOW,
+				     &sregs_ext->vxrs_high,
+				     sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(current->thread.vxrs + i) + 1) = vxrs[i];
+	}
 	return 0;
 }
 
@@ -252,8 +310,9 @@ COMPAT_SYSCALL_DEFINE0(sigreturn)
 	set_current_blocked(&set);
 	if (restore_sigregs32(regs, &frame->sregs))
 		goto badframe;
-	if (restore_sigregs_gprs_high(regs, frame->gprs_high))
+	if (restore_sigregs_ext32(regs, &frame->sregs_ext))
 		goto badframe;
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
@@ -269,12 +328,13 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
 	set_current_blocked(&set);
+	if (compat_restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
 	if (restore_sigregs32(regs, &frame->uc.uc_mcontext))
 		goto badframe;
-	if (restore_sigregs_gprs_high(regs, frame->gprs_high))
+	if (restore_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
 		goto badframe;
-	if (compat_restore_altstack(&frame->uc.uc_stack))
-		goto badframe; 
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
@@ -324,37 +384,64 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 			 struct pt_regs *regs)
 {
 	int sig = ksig->sig;
-	sigframe32 __user *frame = get_sigframe(&ksig->ka, regs, sizeof(sigframe32));
-
+	sigframe32 __user *frame;
+	struct sigcontext32 sc;
+	unsigned long restorer;
+	size_t frame_size;
+
+	/*
+	 * gprs_high are always present for 31-bit compat tasks.
+	 * The space for vector registers is only allocated if
+	 * the machine supports it
+	 */
+	frame_size = sizeof(*frame) - sizeof(frame->sregs_ext.__reserved);
+	if (!MACHINE_HAS_VX)
+		frame_size -= sizeof(frame->sregs_ext.vxrs_low) +
+			      sizeof(frame->sregs_ext.vxrs_high);
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (__copy_to_user(&frame->sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE32))
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (unsigned int __user *) frame))
+		return -EFAULT;
+
+	/* Create struct sigcontext32 on the signal stack */
+	memcpy(&sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE32);
+	sc.sregs = (__u32)(unsigned long __force) &frame->sregs;
+	if (__copy_to_user(&frame->sc, &sc, sizeof(frame->sc)))
 		return -EFAULT;
 
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create _sigregs32 on the signal stack */
 	if (save_sigregs32(regs, &frame->sregs))
 		return -EFAULT;
-	if (save_sigregs_gprs_high(regs, frame->gprs_high))
+
+	/* Place signal number on stack to allow backtrace from handler.  */
+	if (__put_user(regs->gprs[2], (int __force __user *) &frame->signo))
 		return -EFAULT;
-	if (__put_user((unsigned long) &frame->sregs, &frame->sc.sregs))
+
+	/* Create _sigregs_ext32 on the signal stack */
+	if (save_sigregs_ext32(regs, &frame->sregs_ext))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-		regs->gprs[14] = (__u64 __force) ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
+		restorer = (unsigned long __force)
+			ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
 	} else {
-		regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn,
-			       (u16 __force __user *)(frame->retcode)))
+		/* Signal frames without vectors registers are short ! */
+		__u16 __user *svc = (void *) frame + frame_size - 2;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long __force) svc | PSW32_ADDR_AMODE;
         }
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (unsigned int __user *) frame))
-		return -EFAULT;
-
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (__force __u64) frame;
 	/* Force 31 bit amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_BA |
@@ -375,50 +462,69 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 		regs->gprs[6] = task_thread_info(current)->last_break;
 	}
 
-	/* Place signal number on stack to allow backtrace from handler.  */
-	if (__put_user(regs->gprs[2], (int __force __user *) &frame->signo))
-		return -EFAULT;
 	return 0;
 }
 
 static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set,
 			    struct pt_regs *regs)
 {
-	int err = 0;
-	rt_sigframe32 __user *frame = get_sigframe(&ksig->ka, regs, sizeof(rt_sigframe32));
-
+	rt_sigframe32 __user *frame;
+	unsigned long restorer;
+	size_t frame_size;
+	u32 uc_flags;
+
+	frame_size = sizeof(*frame) -
+		     sizeof(frame->uc.uc_mcontext_ext.__reserved);
+	/*
+	 * gprs_high are always present for 31-bit compat tasks.
+	 * The space for vector registers is only allocated if
+	 * the machine supports it
+	 */
+	uc_flags = UC_GPRS_HIGH;
+	if (MACHINE_HAS_VX) {
+		if (current->thread.vxrs)
+			uc_flags |= UC_VXRS;
+	} else
+		frame_size -= sizeof(frame->uc.uc_mcontext_ext.vxrs_low) +
+			      sizeof(frame->uc.uc_mcontext_ext.vxrs_high);
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (copy_siginfo_to_user32(&frame->info, &ksig->info))
-		return -EFAULT;
-
-	/* Create the ucontext.  */
-	err |= __put_user(UC_EXTENDED, &frame->uc.uc_flags);
-	err |= __put_user(0, &frame->uc.uc_link);
-	err |= __compat_save_altstack(&frame->uc.uc_stack, regs->gprs[15]);
-	err |= save_sigregs32(regs, &frame->uc.uc_mcontext);
-	err |= save_sigregs_gprs_high(regs, frame->gprs_high);
-	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-	if (err)
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (unsigned int __force __user *) frame))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-		regs->gprs[14] = (__u64 __force) ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
+		restorer = (unsigned long __force)
+			ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE;
 	} else {
-		regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
-			       (u16 __force __user *)(frame->retcode)))
+		__u16 __user *svc = &frame->svc_insn;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long __force) svc | PSW32_ADDR_AMODE;
 	}
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (unsigned int __force __user *) frame))
+	/* Create siginfo on the signal stack */
+	if (copy_siginfo_to_user32(&frame->info, &ksig->info))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create ucontext on the signal stack. */
+	if (__put_user(uc_flags, &frame->uc.uc_flags) ||
+	    __put_user(0, &frame->uc.uc_link) ||
+	    __compat_save_altstack(&frame->uc.uc_stack, regs->gprs[15]) ||
+	    save_sigregs32(regs, &frame->uc.uc_mcontext) ||
+	    __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)) ||
+	    save_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
 		return -EFAULT;
 
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (__force __u64) frame;
 	/* Force 31 bit amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_BA |
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index a3b9150e6802..9f73c8059022 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -46,9 +46,9 @@ struct dump_save_areas dump_save_areas;
 /*
  * Allocate and add a save area for a CPU
  */
-struct save_area *dump_save_area_create(int cpu)
+struct save_area_ext *dump_save_area_create(int cpu)
 {
-	struct save_area **save_areas, *save_area;
+	struct save_area_ext **save_areas, *save_area;
 
 	save_area = kmalloc(sizeof(*save_area), GFP_KERNEL);
 	if (!save_area)
@@ -386,9 +386,45 @@ static void *nt_s390_prefix(void *ptr, struct save_area *sa)
 }
 
 /*
+ * Initialize vxrs high note (full 128 bit VX registers 16-31)
+ */
+static void *nt_s390_vx_high(void *ptr, __vector128 *vx_regs)
+{
+	return nt_init(ptr, NT_S390_VXRS_HIGH, &vx_regs[16],
+		       16 * sizeof(__vector128), KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize vxrs low note (lower halves of VX registers 0-15)
+ */
+static void *nt_s390_vx_low(void *ptr, __vector128 *vx_regs)
+{
+	Elf64_Nhdr *note;
+	u64 len;
+	int i;
+
+	note = (Elf64_Nhdr *)ptr;
+	note->n_namesz = strlen(KEXEC_CORE_NOTE_NAME) + 1;
+	note->n_descsz = 16 * 8;
+	note->n_type = NT_S390_VXRS_LOW;
+	len = sizeof(Elf64_Nhdr);
+
+	memcpy(ptr + len, KEXEC_CORE_NOTE_NAME, note->n_namesz);
+	len = roundup(len + note->n_namesz, 4);
+
+	ptr += len;
+	/* Copy lower halves of SIMD registers 0-15 */
+	for (i = 0; i < 16; i++) {
+		memcpy(ptr, &vx_regs[i], 8);
+		ptr += 8;
+	}
+	return ptr;
+}
+
+/*
  * Fill ELF notes for one CPU with save area registers
  */
-void *fill_cpu_elf_notes(void *ptr, struct save_area *sa)
+void *fill_cpu_elf_notes(void *ptr, struct save_area *sa, __vector128 *vx_regs)
 {
 	ptr = nt_prstatus(ptr, sa);
 	ptr = nt_fpregset(ptr, sa);
@@ -397,6 +433,10 @@ void *fill_cpu_elf_notes(void *ptr, struct save_area *sa)
 	ptr = nt_s390_tod_preg(ptr, sa);
 	ptr = nt_s390_ctrs(ptr, sa);
 	ptr = nt_s390_prefix(ptr, sa);
+	if (MACHINE_HAS_VX && vx_regs) {
+		ptr = nt_s390_vx_low(ptr, vx_regs);
+		ptr = nt_s390_vx_high(ptr, vx_regs);
+	}
 	return ptr;
 }
 
@@ -484,7 +524,7 @@ static int get_cpu_cnt(void)
 	int i, cpus = 0;
 
 	for (i = 0; i < dump_save_areas.count; i++) {
-		if (dump_save_areas.areas[i]->pref_reg == 0)
+		if (dump_save_areas.areas[i]->sa.pref_reg == 0)
 			continue;
 		cpus++;
 	}
@@ -530,17 +570,17 @@ static void loads_init(Elf64_Phdr *phdr, u64 loads_offset)
  */
 static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 {
-	struct save_area *sa;
+	struct save_area_ext *sa_ext;
 	void *ptr_start = ptr;
 	int i;
 
 	ptr = nt_prpsinfo(ptr);
 
 	for (i = 0; i < dump_save_areas.count; i++) {
-		sa = dump_save_areas.areas[i];
-		if (sa->pref_reg == 0)
+		sa_ext = dump_save_areas.areas[i];
+		if (sa_ext->sa.pref_reg == 0)
 			continue;
-		ptr = fill_cpu_elf_notes(ptr, sa);
+		ptr = fill_cpu_elf_notes(ptr, &sa_ext->sa, sa_ext->vx_regs);
 	}
 	ptr = nt_vmcoreinfo(ptr);
 	memset(phdr, 0, sizeof(*phdr));
@@ -581,7 +621,7 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 
 	mem_chunk_cnt = get_mem_chunk_cnt();
 
-	alloc_size = 0x1000 + get_cpu_cnt() * 0x300 +
+	alloc_size = 0x1000 + get_cpu_cnt() * 0x4a0 +
 		mem_chunk_cnt * sizeof(Elf64_Phdr);
 	hdr = kzalloc_panic(alloc_size);
 	/* Init elf header */
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 993efe6a887c..f3762937dd82 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -60,6 +60,11 @@ enum {
 	A_28,	/* Access reg. starting at position 28 */
 	C_8,	/* Control reg. starting at position 8 */
 	C_12,	/* Control reg. starting at position 12 */
+	V_8,	/* Vector reg. starting at position 8, extension bit at 36 */
+	V_12,	/* Vector reg. starting at position 12, extension bit at 37 */
+	V_16,	/* Vector reg. starting at position 16, extension bit at 38 */
+	V_32,	/* Vector reg. starting at position 32, extension bit at 39 */
+	W_12,	/* Vector reg. at bit 12, extension at bit 37, used as index */
 	B_16,	/* Base register starting at position 16 */
 	B_32,	/* Base register starting at position 32 */
 	X_12,	/* Index register starting at position 12 */
@@ -82,6 +87,8 @@ enum {
 	U8_24,	/* 8 bit unsigned value starting at 24 */
 	U8_32,	/* 8 bit unsigned value starting at 32 */
 	I8_8,	/* 8 bit signed value starting at 8 */
+	I8_16,	/* 8 bit signed value starting at 16 */
+	I8_24,	/* 8 bit signed value starting at 24 */
 	I8_32,	/* 8 bit signed value starting at 32 */
 	J12_12, /* PC relative offset at 12 */
 	I16_16,	/* 16 bit signed value starting at 16 */
@@ -96,6 +103,9 @@ enum {
 	U32_16,	/* 32 bit unsigned value starting at 16 */
 	M_16,	/* 4 bit optional mask starting at 16 */
 	M_20,	/* 4 bit optional mask starting at 20 */
+	M_24,	/* 4 bit optional mask starting at 24 */
+	M_28,	/* 4 bit optional mask starting at 28 */
+	M_32,	/* 4 bit optional mask starting at 32 */
 	RO_28,	/* optional GPR starting at position 28 */
 };
 
@@ -130,7 +140,7 @@ enum {
 	INSTR_RSY_RDRM,
 	INSTR_RS_AARD, INSTR_RS_CCRD, INSTR_RS_R0RD, INSTR_RS_RRRD,
 	INSTR_RS_RURD,
-	INSTR_RXE_FRRD, INSTR_RXE_RRRD,
+	INSTR_RXE_FRRD, INSTR_RXE_RRRD, INSTR_RXE_RRRDM,
 	INSTR_RXF_FRRDF,
 	INSTR_RXY_FRRD, INSTR_RXY_RRRD, INSTR_RXY_URRD,
 	INSTR_RX_FRRD, INSTR_RX_RRRD, INSTR_RX_URRD,
@@ -143,6 +153,17 @@ enum {
 	INSTR_SS_L0RDRD, INSTR_SS_LIRDRD, INSTR_SS_LLRDRD, INSTR_SS_RRRDRD,
 	INSTR_SS_RRRDRD2, INSTR_SS_RRRDRD3,
 	INSTR_S_00, INSTR_S_RD,
+	INSTR_VRI_V0IM, INSTR_VRI_V0I0, INSTR_VRI_V0IIM, INSTR_VRI_VVIM,
+	INSTR_VRI_VVV0IM, INSTR_VRI_VVV0I0, INSTR_VRI_VVIMM,
+	INSTR_VRR_VV00MMM, INSTR_VRR_VV000MM, INSTR_VRR_VV0000M,
+	INSTR_VRR_VV00000, INSTR_VRR_VVV0M0M, INSTR_VRR_VV00M0M,
+	INSTR_VRR_VVV000M, INSTR_VRR_VVV000V, INSTR_VRR_VVV0000,
+	INSTR_VRR_VVV0MMM, INSTR_VRR_VVV00MM, INSTR_VRR_VVVMM0V,
+	INSTR_VRR_VVVM0MV, INSTR_VRR_VVVM00V, INSTR_VRR_VRR0000,
+	INSTR_VRS_VVRDM, INSTR_VRS_VVRD0, INSTR_VRS_VRRDM, INSTR_VRS_VRRD0,
+	INSTR_VRS_RVRDM,
+	INSTR_VRV_VVRDM, INSTR_VRV_VWRDM,
+	INSTR_VRX_VRRDM, INSTR_VRX_VRRD0,
 };
 
 static const struct s390_operand operands[] =
@@ -168,6 +189,11 @@ static const struct s390_operand operands[] =
 	[A_28]	 = {  4, 28, OPERAND_AR },
 	[C_8]	 = {  4,  8, OPERAND_CR },
 	[C_12]	 = {  4, 12, OPERAND_CR },
+	[V_8]	 = {  4,  8, OPERAND_VR },
+	[V_12]	 = {  4, 12, OPERAND_VR },
+	[V_16]	 = {  4, 16, OPERAND_VR },
+	[V_32]	 = {  4, 32, OPERAND_VR },
+	[W_12]	 = {  4, 12, OPERAND_INDEX | OPERAND_VR },
 	[B_16]	 = {  4, 16, OPERAND_BASE | OPERAND_GPR },
 	[B_32]	 = {  4, 32, OPERAND_BASE | OPERAND_GPR },
 	[X_12]	 = {  4, 12, OPERAND_INDEX | OPERAND_GPR },
@@ -190,6 +216,11 @@ static const struct s390_operand operands[] =
 	[U8_24]  = {  8, 24, 0 },
 	[U8_32]  = {  8, 32, 0 },
 	[J12_12] = { 12, 12, OPERAND_PCREL },
+	[I8_8]	 = {  8,  8, OPERAND_SIGNED },
+	[I8_16]  = {  8, 16, OPERAND_SIGNED },
+	[I8_24]  = {  8, 24, OPERAND_SIGNED },
+	[I8_32]  = {  8, 32, OPERAND_SIGNED },
+	[I16_32] = { 16, 32, OPERAND_SIGNED },
 	[I16_16] = { 16, 16, OPERAND_SIGNED },
 	[U16_16] = { 16, 16, 0 },
 	[U16_32] = { 16, 32, 0 },
@@ -202,6 +233,9 @@ static const struct s390_operand operands[] =
 	[U32_16] = { 32, 16, 0 },
 	[M_16]	 = {  4, 16, 0 },
 	[M_20]	 = {  4, 20, 0 },
+	[M_24]	 = {  4, 24, 0 },
+	[M_28]	 = {  4, 28, 0 },
+	[M_32]	 = {  4, 32, 0 },
 	[RO_28]  = {  4, 28, OPERAND_GPR }
 };
 
@@ -283,6 +317,7 @@ static const unsigned char formats[][7] = {
 	[INSTR_RS_RURD]	  = { 0xff, R_8,U4_12,D_20,B_16,0,0 },
 	[INSTR_RXE_FRRD]  = { 0xff, F_8,D_20,X_12,B_16,0,0 },
 	[INSTR_RXE_RRRD]  = { 0xff, R_8,D_20,X_12,B_16,0,0 },
+	[INSTR_RXE_RRRDM] = { 0xff, R_8,D_20,X_12,B_16,M_32,0 },
 	[INSTR_RXF_FRRDF] = { 0xff, F_32,F_8,D_20,X_12,B_16,0 },
 	[INSTR_RXY_FRRD]  = { 0xff, F_8,D20_20,X_12,B_16,0,0 },
 	[INSTR_RXY_RRRD]  = { 0xff, R_8,D20_20,X_12,B_16,0,0 },
@@ -307,6 +342,37 @@ static const unsigned char formats[][7] = {
 	[INSTR_SS_RRRDRD] = { 0xff, D_20,R_8,B_16,D_36,B_32,R_12 },
 	[INSTR_S_00]	  = { 0xff, 0,0,0,0,0,0 },
 	[INSTR_S_RD]	  = { 0xff, D_20,B_16,0,0,0,0 },
+	[INSTR_VRI_V0IM]  = { 0xff, V_8,I16_16,M_32,0,0,0 },
+	[INSTR_VRI_V0I0]  = { 0xff, V_8,I16_16,0,0,0,0 },
+	[INSTR_VRI_V0IIM] = { 0xff, V_8,I8_16,I8_24,M_32,0,0 },
+	[INSTR_VRI_VVIM]  = { 0xff, V_8,I16_16,V_12,M_32,0,0 },
+	[INSTR_VRI_VVV0IM]= { 0xff, V_8,V_12,V_16,I8_24,M_32,0 },
+	[INSTR_VRI_VVV0I0]= { 0xff, V_8,V_12,V_16,I8_24,0,0 },
+	[INSTR_VRI_VVIMM] = { 0xff, V_8,V_12,I16_16,M_32,M_28,0 },
+	[INSTR_VRR_VV00MMM]={ 0xff, V_8,V_12,M_32,M_28,M_24,0 },
+	[INSTR_VRR_VV000MM]={ 0xff, V_8,V_12,M_32,M_28,0,0 },
+	[INSTR_VRR_VV0000M]={ 0xff, V_8,V_12,M_32,0,0,0 },
+	[INSTR_VRR_VV00000]={ 0xff, V_8,V_12,0,0,0,0 },
+	[INSTR_VRR_VVV0M0M]={ 0xff, V_8,V_12,V_16,M_32,M_24,0 },
+	[INSTR_VRR_VV00M0M]={ 0xff, V_8,V_12,M_32,M_24,0,0 },
+	[INSTR_VRR_VVV000M]={ 0xff, V_8,V_12,V_16,M_32,0,0 },
+	[INSTR_VRR_VVV000V]={ 0xff, V_8,V_12,V_16,V_32,0,0 },
+	[INSTR_VRR_VVV0000]={ 0xff, V_8,V_12,V_16,0,0,0 },
+	[INSTR_VRR_VVV0MMM]={ 0xff, V_8,V_12,V_16,M_32,M_28,M_24 },
+	[INSTR_VRR_VVV00MM]={ 0xff, V_8,V_12,V_16,M_32,M_28,0 },
+	[INSTR_VRR_VVVMM0V]={ 0xff, V_8,V_12,V_16,V_32,M_20,M_24 },
+	[INSTR_VRR_VVVM0MV]={ 0xff, V_8,V_12,V_16,V_32,M_28,M_20 },
+	[INSTR_VRR_VVVM00V]={ 0xff, V_8,V_12,V_16,V_32,M_20,0 },
+	[INSTR_VRR_VRR0000]={ 0xff, V_8,R_12,R_16,0,0,0 },
+	[INSTR_VRS_VVRDM] = { 0xff, V_8,V_12,D_20,B_16,M_32,0 },
+	[INSTR_VRS_VVRD0] = { 0xff, V_8,V_12,D_20,B_16,0,0 },
+	[INSTR_VRS_VRRDM] = { 0xff, V_8,R_12,D_20,B_16,M_32,0 },
+	[INSTR_VRS_VRRD0] = { 0xff, V_8,R_12,D_20,B_16,0,0 },
+	[INSTR_VRS_RVRDM] = { 0xff, R_8,V_12,D_20,B_16,M_32,0 },
+	[INSTR_VRV_VVRDM] = { 0xff, V_8,V_12,D_20,B_16,M_32,0 },
+	[INSTR_VRV_VWRDM] = { 0xff, V_8,D_20,W_12,B_16,M_32,0 },
+	[INSTR_VRX_VRRDM] = { 0xff, V_8,D_20,X_12,B_16,M_32,0 },
+	[INSTR_VRX_VRRD0] = { 0xff, V_8,D_20,X_12,B_16,0,0 },
 };
 
 enum {
@@ -381,6 +447,11 @@ enum {
 	LONG_INSN_MPCIFC,
 	LONG_INSN_STPCIFC,
 	LONG_INSN_PCISTB,
+	LONG_INSN_VPOPCT,
+	LONG_INSN_VERLLV,
+	LONG_INSN_VESRAV,
+	LONG_INSN_VESRLV,
+	LONG_INSN_VSBCBI
 };
 
 static char *long_insn_name[] = {
@@ -455,6 +526,11 @@ static char *long_insn_name[] = {
 	[LONG_INSN_MPCIFC] = "mpcifc",
 	[LONG_INSN_STPCIFC] = "stpcifc",
 	[LONG_INSN_PCISTB] = "pcistb",
+	[LONG_INSN_VPOPCT] = "vpopct",
+	[LONG_INSN_VERLLV] = "verllv",
+	[LONG_INSN_VESRAV] = "vesrav",
+	[LONG_INSN_VESRLV] = "vesrlv",
+	[LONG_INSN_VSBCBI] = "vsbcbi",
 };
 
 static struct s390_insn opcode[] = {
@@ -1369,6 +1445,150 @@ static struct s390_insn opcode_e5[] = {
 	{ "", 0, INSTR_INVALID }
 };
 
+static struct s390_insn opcode_e7[] = {
+#ifdef CONFIG_64BIT
+	{ "lcbb", 0x27, INSTR_RXE_RRRDM },
+	{ "vgef", 0x13, INSTR_VRV_VVRDM },
+	{ "vgeg", 0x12, INSTR_VRV_VVRDM },
+	{ "vgbm", 0x44, INSTR_VRI_V0I0 },
+	{ "vgm", 0x46, INSTR_VRI_V0IIM },
+	{ "vl", 0x06, INSTR_VRX_VRRD0 },
+	{ "vlr", 0x56, INSTR_VRR_VV00000 },
+	{ "vlrp", 0x05, INSTR_VRX_VRRDM },
+	{ "vleb", 0x00, INSTR_VRX_VRRDM },
+	{ "vleh", 0x01, INSTR_VRX_VRRDM },
+	{ "vlef", 0x03, INSTR_VRX_VRRDM },
+	{ "vleg", 0x02, INSTR_VRX_VRRDM },
+	{ "vleib", 0x40, INSTR_VRI_V0IM },
+	{ "vleih", 0x41, INSTR_VRI_V0IM },
+	{ "vleif", 0x43, INSTR_VRI_V0IM },
+	{ "vleig", 0x42, INSTR_VRI_V0IM },
+	{ "vlgv", 0x21, INSTR_VRS_RVRDM },
+	{ "vllez", 0x04, INSTR_VRX_VRRDM },
+	{ "vlm", 0x36, INSTR_VRS_VVRD0 },
+	{ "vlbb", 0x07, INSTR_VRX_VRRDM },
+	{ "vlvg", 0x22, INSTR_VRS_VRRDM },
+	{ "vlvgp", 0x62, INSTR_VRR_VRR0000 },
+	{ "vll", 0x37, INSTR_VRS_VRRD0 },
+	{ "vmrh", 0x61, INSTR_VRR_VVV000M },
+	{ "vmrl", 0x60, INSTR_VRR_VVV000M },
+	{ "vpk", 0x94, INSTR_VRR_VVV000M },
+	{ "vpks", 0x97, INSTR_VRR_VVV0M0M },
+	{ "vpkls", 0x95, INSTR_VRR_VVV0M0M },
+	{ "vperm", 0x8c, INSTR_VRR_VVV000V },
+	{ "vpdi", 0x84, INSTR_VRR_VVV000M },
+	{ "vrep", 0x4d, INSTR_VRI_VVIM },
+	{ "vrepi", 0x45, INSTR_VRI_V0IM },
+	{ "vscef", 0x1b, INSTR_VRV_VWRDM },
+	{ "vsceg", 0x1a, INSTR_VRV_VWRDM },
+	{ "vsel", 0x8d, INSTR_VRR_VVV000V },
+	{ "vseg", 0x5f, INSTR_VRR_VV0000M },
+	{ "vst", 0x0e, INSTR_VRX_VRRD0 },
+	{ "vsteb", 0x08, INSTR_VRX_VRRDM },
+	{ "vsteh", 0x09, INSTR_VRX_VRRDM },
+	{ "vstef", 0x0b, INSTR_VRX_VRRDM },
+	{ "vsteg", 0x0a, INSTR_VRX_VRRDM },
+	{ "vstm", 0x3e, INSTR_VRS_VVRD0 },
+	{ "vstl", 0x3f, INSTR_VRS_VRRD0 },
+	{ "vuph", 0xd7, INSTR_VRR_VV0000M },
+	{ "vuplh", 0xd5, INSTR_VRR_VV0000M },
+	{ "vupl", 0xd6, INSTR_VRR_VV0000M },
+	{ "vupll", 0xd4, INSTR_VRR_VV0000M },
+	{ "va", 0xf3, INSTR_VRR_VVV000M },
+	{ "vacc", 0xf1, INSTR_VRR_VVV000M },
+	{ "vac", 0xbb, INSTR_VRR_VVVM00V },
+	{ "vaccc", 0xb9, INSTR_VRR_VVVM00V },
+	{ "vn", 0x68, INSTR_VRR_VVV0000 },
+	{ "vnc", 0x69, INSTR_VRR_VVV0000 },
+	{ "vavg", 0xf2, INSTR_VRR_VVV000M },
+	{ "vavgl", 0xf0, INSTR_VRR_VVV000M },
+	{ "vcksm", 0x66, INSTR_VRR_VVV0000 },
+	{ "vec", 0xdb, INSTR_VRR_VV0000M },
+	{ "vecl", 0xd9, INSTR_VRR_VV0000M },
+	{ "vceq", 0xf8, INSTR_VRR_VVV0M0M },
+	{ "vch", 0xfb, INSTR_VRR_VVV0M0M },
+	{ "vchl", 0xf9, INSTR_VRR_VVV0M0M },
+	{ "vclz", 0x53, INSTR_VRR_VV0000M },
+	{ "vctz", 0x52, INSTR_VRR_VV0000M },
+	{ "vx", 0x6d, INSTR_VRR_VVV0000 },
+	{ "vgfm", 0xb4, INSTR_VRR_VVV000M },
+	{ "vgfma", 0xbc, INSTR_VRR_VVVM00V },
+	{ "vlc", 0xde, INSTR_VRR_VV0000M },
+	{ "vlp", 0xdf, INSTR_VRR_VV0000M },
+	{ "vmx", 0xff, INSTR_VRR_VVV000M },
+	{ "vmxl", 0xfd, INSTR_VRR_VVV000M },
+	{ "vmn", 0xfe, INSTR_VRR_VVV000M },
+	{ "vmnl", 0xfc, INSTR_VRR_VVV000M },
+	{ "vmal", 0xaa, INSTR_VRR_VVVM00V },
+	{ "vmae", 0xae, INSTR_VRR_VVVM00V },
+	{ "vmale", 0xac, INSTR_VRR_VVVM00V },
+	{ "vmah", 0xab, INSTR_VRR_VVVM00V },
+	{ "vmalh", 0xa9, INSTR_VRR_VVVM00V },
+	{ "vmao", 0xaf, INSTR_VRR_VVVM00V },
+	{ "vmalo", 0xad, INSTR_VRR_VVVM00V },
+	{ "vmh", 0xa3, INSTR_VRR_VVV000M },
+	{ "vmlh", 0xa1, INSTR_VRR_VVV000M },
+	{ "vml", 0xa2, INSTR_VRR_VVV000M },
+	{ "vme", 0xa6, INSTR_VRR_VVV000M },
+	{ "vmle", 0xa4, INSTR_VRR_VVV000M },
+	{ "vmo", 0xa7, INSTR_VRR_VVV000M },
+	{ "vmlo", 0xa5, INSTR_VRR_VVV000M },
+	{ "vno", 0x6b, INSTR_VRR_VVV0000 },
+	{ "vo", 0x6a, INSTR_VRR_VVV0000 },
+	{ { 0, LONG_INSN_VPOPCT }, 0x50, INSTR_VRR_VV0000M },
+	{ { 0, LONG_INSN_VERLLV }, 0x73, INSTR_VRR_VVV000M },
+	{ "verll", 0x33, INSTR_VRS_VVRDM },
+	{ "verim", 0x72, INSTR_VRI_VVV0IM },
+	{ "veslv", 0x70, INSTR_VRR_VVV000M },
+	{ "vesl", 0x30, INSTR_VRS_VVRDM },
+	{ { 0, LONG_INSN_VESRAV }, 0x7a, INSTR_VRR_VVV000M },
+	{ "vesra", 0x3a, INSTR_VRS_VVRDM },
+	{ { 0, LONG_INSN_VESRLV }, 0x78, INSTR_VRR_VVV000M },
+	{ "vesrl", 0x38, INSTR_VRS_VVRDM },
+	{ "vsl", 0x74, INSTR_VRR_VVV0000 },
+	{ "vslb", 0x75, INSTR_VRR_VVV0000 },
+	{ "vsldb", 0x77, INSTR_VRI_VVV0I0 },
+	{ "vsra", 0x7e, INSTR_VRR_VVV0000 },
+	{ "vsrab", 0x7f, INSTR_VRR_VVV0000 },
+	{ "vsrl", 0x7c, INSTR_VRR_VVV0000 },
+	{ "vsrlb", 0x7d, INSTR_VRR_VVV0000 },
+	{ "vs", 0xf7, INSTR_VRR_VVV000M },
+	{ "vscb", 0xf5, INSTR_VRR_VVV000M },
+	{ "vsb", 0xbf, INSTR_VRR_VVVM00V },
+	{ { 0, LONG_INSN_VSBCBI }, 0xbd, INSTR_VRR_VVVM00V },
+	{ "vsumg", 0x65, INSTR_VRR_VVV000M },
+	{ "vsumq", 0x67, INSTR_VRR_VVV000M },
+	{ "vsum", 0x64, INSTR_VRR_VVV000M },
+	{ "vtm", 0xd8, INSTR_VRR_VV00000 },
+	{ "vfae", 0x82, INSTR_VRR_VVV0M0M },
+	{ "vfee", 0x80, INSTR_VRR_VVV0M0M },
+	{ "vfene", 0x81, INSTR_VRR_VVV0M0M },
+	{ "vistr", 0x5c, INSTR_VRR_VV00M0M },
+	{ "vstrc", 0x8a, INSTR_VRR_VVVMM0V },
+	{ "vfa", 0xe3, INSTR_VRR_VVV00MM },
+	{ "wfc", 0xcb, INSTR_VRR_VV000MM },
+	{ "wfk", 0xca, INSTR_VRR_VV000MM },
+	{ "vfce", 0xe8, INSTR_VRR_VVV0MMM },
+	{ "vfch", 0xeb, INSTR_VRR_VVV0MMM },
+	{ "vfche", 0xea, INSTR_VRR_VVV0MMM },
+	{ "vcdg", 0xc3, INSTR_VRR_VV00MMM },
+	{ "vcdlg", 0xc1, INSTR_VRR_VV00MMM },
+	{ "vcgd", 0xc2, INSTR_VRR_VV00MMM },
+	{ "vclgd", 0xc0, INSTR_VRR_VV00MMM },
+	{ "vfd", 0xe5, INSTR_VRR_VVV00MM },
+	{ "vfi", 0xc7, INSTR_VRR_VV00MMM },
+	{ "vlde", 0xc4, INSTR_VRR_VV000MM },
+	{ "vled", 0xc5, INSTR_VRR_VV00MMM },
+	{ "vfm", 0xe7, INSTR_VRR_VVV00MM },
+	{ "vfma", 0x8f, INSTR_VRR_VVVM0MV },
+	{ "vfms", 0x8e, INSTR_VRR_VVVM0MV },
+	{ "vfpso", 0xcc, INSTR_VRR_VV00MMM },
+	{ "vfsq", 0xce, INSTR_VRR_VV000MM },
+	{ "vfs", 0xe2, INSTR_VRR_VVV00MM },
+	{ "vftci", 0x4a, INSTR_VRI_VVIMM },
+#endif
+};
+
 static struct s390_insn opcode_eb[] = {
 #ifdef CONFIG_64BIT
 	{ "lmg", 0x04, INSTR_RSY_RRRD },
@@ -1552,16 +1772,17 @@ static struct s390_insn opcode_ed[] = {
 static unsigned int extract_operand(unsigned char *code,
 				    const struct s390_operand *operand)
 {
+	unsigned char *cp;
 	unsigned int val;
 	int bits;
 
 	/* Extract fragments of the operand byte for byte.  */
-	code += operand->shift / 8;
+	cp = code + operand->shift / 8;
 	bits = (operand->shift & 7) + operand->bits;
 	val = 0;
 	do {
 		val <<= 8;
-		val |= (unsigned int) *code++;
+		val |= (unsigned int) *cp++;
 		bits -= 8;
 	} while (bits > 0);
 	val >>= -bits;
@@ -1571,6 +1792,18 @@ static unsigned int extract_operand(unsigned char *code,
 	if (operand->bits == 20 && operand->shift == 20)
 		val = (val & 0xff) << 12 | (val & 0xfff00) >> 8;
 
+	/* Check for register extensions bits for vector registers. */
+	if (operand->flags & OPERAND_VR) {
+		if (operand->shift == 8)
+			val |= (code[4] & 8) << 1;
+		else if (operand->shift == 12)
+			val |= (code[4] & 4) << 2;
+		else if (operand->shift == 16)
+			val |= (code[4] & 2) << 3;
+		else if (operand->shift == 32)
+			val |= (code[4] & 1) << 4;
+	}
+
 	/* Sign extend value if the operand is signed or pc relative.  */
 	if ((operand->flags & (OPERAND_SIGNED | OPERAND_PCREL)) &&
 	    (val & (1U << (operand->bits - 1))))
@@ -1639,6 +1872,10 @@ struct s390_insn *find_insn(unsigned char *code)
 	case 0xe5:
 		table = opcode_e5;
 		break;
+	case 0xe7:
+		table = opcode_e7;
+		opfrag = code[5];
+		break;
 	case 0xeb:
 		table = opcode_eb;
 		opfrag = code[5];
@@ -1734,6 +1971,8 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 				ptr += sprintf(ptr, "%%a%i", value);
 			else if (operand->flags & OPERAND_CR)
 				ptr += sprintf(ptr, "%%c%i", value);
+			else if (operand->flags & OPERAND_VR)
+				ptr += sprintf(ptr, "%%v%i", value);
 			else if (operand->flags & OPERAND_PCREL)
 				ptr += sprintf(ptr, "%lx", (signed int) value
 								      + addr);
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 0dff972a169c..cef2879edff3 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -390,10 +390,10 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_LPP;
 	if (test_facility(50) && test_facility(73))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TE;
-	if (test_facility(66))
-		S390_lowcore.machine_flags |= MACHINE_FLAG_RRBM;
 	if (test_facility(51))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_LC;
+	if (test_facility(129))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_VX;
 #endif
 }
 
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 1aad48398d06..0554b9771c9f 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -4,7 +4,7 @@
 #include <linux/types.h>
 #include <linux/signal.h>
 #include <asm/ptrace.h>
-#include <asm/cputime.h>
+#include <asm/idle.h>
 
 extern void *restart_stack;
 extern unsigned long suspend_zero_pages;
@@ -21,6 +21,8 @@ void psw_idle(struct s390_idle_data *, unsigned long);
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs);
 asmlinkage void do_syscall_trace_exit(struct pt_regs *regs);
 
+int alloc_vector_registers(struct task_struct *tsk);
+
 void do_protection_exception(struct pt_regs *regs);
 void do_dat_exception(struct pt_regs *regs);
 
@@ -43,8 +45,10 @@ void special_op_exception(struct pt_regs *regs);
 void specification_exception(struct pt_regs *regs);
 void transaction_exception(struct pt_regs *regs);
 void translation_exception(struct pt_regs *regs);
+void vector_exception(struct pt_regs *regs);
 
 void do_per_trap(struct pt_regs *regs);
+void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str);
 void syscall_trace(struct pt_regs *regs, int entryexit);
 void kernel_stack_overflow(struct pt_regs * regs);
 void do_signal(struct pt_regs *regs);
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index f2e674c702e1..7b2e03afd017 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -42,7 +42,8 @@ STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
 STACK_SIZE  = 1 << STACK_SHIFT
 STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE
 
-_TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED)
+_TIF_WORK	= (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
+		   _TIF_UPROBE)
 _TIF_TRACE	= (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 		   _TIF_SYSCALL_TRACEPOINT)
 _CIF_WORK	= (_CIF_MCCK_PENDING | _CIF_ASCE)
@@ -265,6 +266,10 @@ sysc_work:
 	jo	sysc_mcck_pending
 	tm	__TI_flags+7(%r12),_TIF_NEED_RESCHED
 	jo	sysc_reschedule
+#ifdef CONFIG_UPROBES
+	tm	__TI_flags+7(%r12),_TIF_UPROBE
+	jo	sysc_uprobe_notify
+#endif
 	tm	__PT_FLAGS+7(%r11),_PIF_PER_TRAP
 	jo	sysc_singlestep
 	tm	__TI_flags+7(%r12),_TIF_SIGPENDING
@@ -323,6 +328,16 @@ sysc_notify_resume:
 	jg	do_notify_resume
 
 #
+# _TIF_UPROBE is set, call uprobe_notify_resume
+#
+#ifdef CONFIG_UPROBES
+sysc_uprobe_notify:
+	lgr	%r2,%r11		# pass pointer to pt_regs
+	larl	%r14,sysc_return
+	jg	uprobe_notify_resume
+#endif
+
+#
 # _PIF_PER_TRAP is set, call do_per_trap
 #
 sysc_singlestep:
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 54d6493c4a56..51d14fe5eb9a 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -1,7 +1,7 @@
 /*
  * Dynamic function tracer architecture backend.
  *
- * Copyright IBM Corp. 2009
+ * Copyright IBM Corp. 2009,2014
  *
  *   Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
  *		Martin Schwidefsky <schwidefsky@de.ibm.com>
@@ -17,100 +17,76 @@
 #include <asm/asm-offsets.h>
 #include "entry.h"
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-
+void mcount_replace_code(void);
 void ftrace_disable_code(void);
 void ftrace_enable_insn(void);
 
-#ifdef CONFIG_64BIT
 /*
- * The 64-bit mcount code looks like this:
+ * The mcount code looks like this:
  *	stg	%r14,8(%r15)		# offset 0
- * >	larl	%r1,<&counter>		# offset 6
- * >	brasl	%r14,_mcount		# offset 12
+ *	larl	%r1,<&counter>		# offset 6
+ *	brasl	%r14,_mcount		# offset 12
  *	lg	%r14,8(%r15)		# offset 18
- * Total length is 24 bytes. The middle two instructions of the mcount
- * block get overwritten by ftrace_make_nop / ftrace_make_call.
- * The 64-bit enabled ftrace code block looks like this:
- *	stg	%r14,8(%r15)		# offset 0
+ * Total length is 24 bytes. The complete mcount block initially gets replaced
+ * by ftrace_make_nop. Subsequent calls to ftrace_make_call / ftrace_make_nop
+ * only patch the jg/lg instruction within the block.
+ * Note: we do not patch the first instruction to an unconditional branch,
+ * since that would break kprobes/jprobes. It is easier to leave the larl
+ * instruction in and only modify the second instruction.
+ * The enabled ftrace code block looks like this:
+ *	larl	%r0,.+24		# offset 0
  * >	lg	%r1,__LC_FTRACE_FUNC	# offset 6
- * >	lgr	%r0,%r0			# offset 12
- * >	basr	%r14,%r1		# offset 16
- *	lg	%r14,8(%15)		# offset 18
- * The return points of the mcount/ftrace function have the same offset 18.
- * The 64-bit disable ftrace code block looks like this:
- *	stg	%r14,8(%r15)		# offset 0
+ *	br	%r1			# offset 12
+ *	brcl	0,0			# offset 14
+ *	brc	0,0			# offset 20
+ * The ftrace function gets called with a non-standard C function call ABI
+ * where r0 contains the return address. It is also expected that the called
+ * function only clobbers r0 and r1, but restores r2-r15.
+ * The return point of the ftrace function has offset 24, so execution
+ * continues behind the mcount block.
+ *	larl	%r0,.+24		# offset 0
  * >	jg	.+18			# offset 6
- * >	lgr	%r0,%r0			# offset 12
- * >	basr	%r14,%r1		# offset 16
- *	lg	%r14,8(%15)		# offset 18
+ *	br	%r1			# offset 12
+ *	brcl	0,0			# offset 14
+ *	brc	0,0			# offset 20
  * The jg instruction branches to offset 24 to skip as many instructions
  * as possible.
  */
 asm(
 	"	.align	4\n"
+	"mcount_replace_code:\n"
+	"	larl	%r0,0f\n"
 	"ftrace_disable_code:\n"
 	"	jg	0f\n"
-	"	lgr	%r0,%r0\n"
-	"	basr	%r14,%r1\n"
+	"	br	%r1\n"
+	"	brcl	0,0\n"
+	"	brc	0,0\n"
 	"0:\n"
 	"	.align	4\n"
 	"ftrace_enable_insn:\n"
 	"	lg	%r1,"__stringify(__LC_FTRACE_FUNC)"\n");
 
+#define MCOUNT_BLOCK_SIZE	24
+#define MCOUNT_INSN_OFFSET	6
 #define FTRACE_INSN_SIZE	6
 
-#else /* CONFIG_64BIT */
-/*
- * The 31-bit mcount code looks like this:
- *	st	%r14,4(%r15)		# offset 0
- * >	bras	%r1,0f			# offset 4
- * >	.long	_mcount			# offset 8
- * >	.long	<&counter>		# offset 12
- * > 0:	l	%r14,0(%r1)		# offset 16
- * >	l	%r1,4(%r1)		# offset 20
- *	basr	%r14,%r14		# offset 24
- *	l	%r14,4(%r15)		# offset 26
- * Total length is 30 bytes. The twenty bytes starting from offset 4
- * to offset 24 get overwritten by ftrace_make_nop / ftrace_make_call.
- * The 31-bit enabled ftrace code block looks like this:
- *	st	%r14,4(%r15)		# offset 0
- * >	l	%r14,__LC_FTRACE_FUNC	# offset 4
- * >	j	0f			# offset 8
- * >	.fill	12,1,0x07		# offset 12
- *   0:	basr	%r14,%r14		# offset 24
- *	l	%r14,4(%r14)		# offset 26
- * The return points of the mcount/ftrace function have the same offset 26.
- * The 31-bit disabled ftrace code block looks like this:
- *	st	%r14,4(%r15)		# offset 0
- * >	j	.+26			# offset 4
- * >	j	0f			# offset 8
- * >	.fill	12,1,0x07		# offset 12
- *   0:	basr	%r14,%r14		# offset 24
- *	l	%r14,4(%r14)		# offset 26
- * The j instruction branches to offset 30 to skip as many instructions
- * as possible.
- */
-asm(
-	"	.align	4\n"
-	"ftrace_disable_code:\n"
-	"	j	1f\n"
-	"	j	0f\n"
-	"	.fill	12,1,0x07\n"
-	"0:	basr	%r14,%r14\n"
-	"1:\n"
-	"	.align	4\n"
-	"ftrace_enable_insn:\n"
-	"	l	%r14,"__stringify(__LC_FTRACE_FUNC)"\n");
-
-#define FTRACE_INSN_SIZE	4
-
-#endif /* CONFIG_64BIT */
-
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+		       unsigned long addr)
+{
+	return 0;
+}
 
 int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		    unsigned long addr)
 {
+	/* Initial replacement of the whole mcount block */
+	if (addr == MCOUNT_ADDR) {
+		if (probe_kernel_write((void *) rec->ip - MCOUNT_INSN_OFFSET,
+				       mcount_replace_code,
+				       MCOUNT_BLOCK_SIZE))
+			return -EPERM;
+		return 0;
+	}
 	if (probe_kernel_write((void *) rec->ip, ftrace_disable_code,
 			       MCOUNT_INSN_SIZE))
 		return -EPERM;
@@ -135,8 +111,6 @@ int __init ftrace_dyn_arch_init(void)
 	return 0;
 }
 
-#endif /* CONFIG_DYNAMIC_FTRACE */
-
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
  * Hook the return address and push it in the stack of return addresses
@@ -162,31 +136,26 @@ out:
 	return parent;
 }
 
-#ifdef CONFIG_DYNAMIC_FTRACE
 /*
  * Patch the kernel code at ftrace_graph_caller location. The instruction
- * there is branch relative and save to prepare_ftrace_return. To disable
- * the call to prepare_ftrace_return we patch the bras offset to point
- * directly after the instructions. To enable the call we calculate
- * the original offset to prepare_ftrace_return and put it back.
+ * there is branch relative on condition. To enable the ftrace graph code
+ * block, we simply patch the mask field of the instruction to zero and
+ * turn the instruction into a nop.
+ * To disable the ftrace graph code the mask field will be patched to
+ * all ones, which turns the instruction into an unconditional branch.
  */
 int ftrace_enable_ftrace_graph_caller(void)
 {
-	unsigned short offset;
+	u8 op = 0x04; /* set mask field to zero */
 
-	offset = ((void *) prepare_ftrace_return -
-		  (void *) ftrace_graph_caller) / 2;
-	return probe_kernel_write((void *) ftrace_graph_caller + 2,
-				  &offset, sizeof(offset));
+	return probe_kernel_write(__va(ftrace_graph_caller)+1, &op, sizeof(op));
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
-	static unsigned short offset = 0x0002;
+	u8 op = 0xf4; /* set mask field to all ones */
 
-	return probe_kernel_write((void *) ftrace_graph_caller + 2,
-				  &offset, sizeof(offset));
+	return probe_kernel_write(__va(ftrace_graph_caller)+1, &op, sizeof(op));
 }
 
-#endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index e88d35d74950..d62eee11f0b5 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -398,7 +398,7 @@ ENTRY(startup_kdump)
 	xc	__LC_STFL_FAC_LIST(8),__LC_STFL_FAC_LIST
 #ifndef CONFIG_MARCH_G5
 	# check capabilities against MARCH_{G5,Z900,Z990,Z9_109,Z10}
-	.insn	s,0xb2b10000,__LC_STFL_FAC_LIST	# store facility list
+	.insn	s,0xb2b10000,0		# store facilities @ __LC_STFL_FAC_LIST
 	tm	__LC_STFL_FAC_LIST,0x01	# stfle available ?
 	jz	0f
 	la	%r0,1
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
new file mode 100644
index 000000000000..7559f1beab29
--- /dev/null
+++ b/arch/s390/kernel/idle.c
@@ -0,0 +1,124 @@
+/*
+ * Idle functions for s390.
+ *
+ * Copyright IBM Corp. 2014
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/kprobes.h>
+#include <linux/notifier.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <asm/cputime.h>
+#include <asm/nmi.h>
+#include <asm/smp.h>
+#include "entry.h"
+
+static DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
+
+void __kprobes enabled_wait(void)
+{
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
+	unsigned long long idle_time;
+	unsigned long psw_mask;
+
+	trace_hardirqs_on();
+
+	/* Wait for external, I/O or machine check interrupt. */
+	psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT | PSW_MASK_DAT |
+		PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
+	clear_cpu_flag(CIF_NOHZ_DELAY);
+
+	/* Call the assembler magic in entry.S */
+	psw_idle(idle, psw_mask);
+
+	/* Account time spent with enabled wait psw loaded as idle time. */
+	idle->sequence++;
+	smp_wmb();
+	idle_time = idle->clock_idle_exit - idle->clock_idle_enter;
+	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
+	idle->idle_time += idle_time;
+	idle->idle_count++;
+	account_idle_time(idle_time);
+	smp_wmb();
+	idle->sequence++;
+}
+
+static ssize_t show_idle_count(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
+	unsigned long long idle_count;
+	unsigned int sequence;
+
+	do {
+		sequence = ACCESS_ONCE(idle->sequence);
+		idle_count = ACCESS_ONCE(idle->idle_count);
+		if (ACCESS_ONCE(idle->clock_idle_enter))
+			idle_count++;
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
+	return sprintf(buf, "%llu\n", idle_count);
+}
+DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
+
+static ssize_t show_idle_time(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
+	unsigned long long now, idle_time, idle_enter, idle_exit;
+	unsigned int sequence;
+
+	do {
+		now = get_tod_clock();
+		sequence = ACCESS_ONCE(idle->sequence);
+		idle_time = ACCESS_ONCE(idle->idle_time);
+		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
+		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
+	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
+	return sprintf(buf, "%llu\n", idle_time >> 12);
+}
+DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
+
+cputime64_t arch_cpu_idle_time(int cpu)
+{
+	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
+	unsigned long long now, idle_enter, idle_exit;
+	unsigned int sequence;
+
+	do {
+		now = get_tod_clock();
+		sequence = ACCESS_ONCE(idle->sequence);
+		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
+		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
+	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
+	return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
+}
+
+void arch_cpu_idle_enter(void)
+{
+	local_mcck_disable();
+}
+
+void arch_cpu_idle(void)
+{
+	if (!test_cpu_flag(CIF_MCCK_PENDING))
+		/* Halt the cpu and keep track of cpu time accounting. */
+		enabled_wait();
+	local_irq_enable();
+}
+
+void arch_cpu_idle_exit(void)
+{
+	local_mcck_enable();
+	if (test_cpu_flag(CIF_MCCK_PENDING))
+		s390_handle_mcck();
+}
+
+void arch_cpu_idle_dead(void)
+{
+	cpu_die();
+}
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 8eb82443cfbd..1b8a38ab7861 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -70,6 +70,7 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = {
 	{.irq = IRQEXT_CMS, .name = "CMS", .desc = "[EXT] CPU-Measurement: Sampling"},
 	{.irq = IRQEXT_CMC, .name = "CMC", .desc = "[EXT] CPU-Measurement: Counter"},
 	{.irq = IRQEXT_CMR, .name = "CMR", .desc = "[EXT] CPU-Measurement: RI"},
+	{.irq = IRQEXT_FTP, .name = "FTP", .desc = "[EXT] HMC FTP Service"},
 	{.irq = IRQIO_CIO,  .name = "CIO", .desc = "[I/O] Common I/O Layer Interrupt"},
 	{.irq = IRQIO_QAI,  .name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt"},
 	{.irq = IRQIO_DAS,  .name = "DAS", .desc = "[I/O] DASD"},
@@ -258,7 +259,7 @@ static irqreturn_t do_ext_interrupt(int irq, void *dummy)
 
 	ext_code = *(struct ext_code *) &regs->int_code;
 	if (ext_code.code != EXT_IRQ_CLK_COMP)
-		__get_cpu_var(s390_idle).nohz_delay = 1;
+		set_cpu_flag(CIF_NOHZ_DELAY);
 
 	index = ext_hash(ext_code.code);
 	rcu_read_lock();
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index bc71a7b95af5..014d4729b134 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -58,161 +58,13 @@ struct kprobe_insn_cache kprobe_dmainsn_slots = {
 	.insn_size = MAX_INSN_SIZE,
 };
 
-static int __kprobes is_prohibited_opcode(kprobe_opcode_t *insn)
-{
-	if (!is_known_insn((unsigned char *)insn))
-		return -EINVAL;
-	switch (insn[0] >> 8) {
-	case 0x0c:	/* bassm */
-	case 0x0b:	/* bsm	 */
-	case 0x83:	/* diag  */
-	case 0x44:	/* ex	 */
-	case 0xac:	/* stnsm */
-	case 0xad:	/* stosm */
-		return -EINVAL;
-	case 0xc6:
-		switch (insn[0] & 0x0f) {
-		case 0x00: /* exrl   */
-			return -EINVAL;
-		}
-	}
-	switch (insn[0]) {
-	case 0x0101:	/* pr	 */
-	case 0xb25a:	/* bsa	 */
-	case 0xb240:	/* bakr  */
-	case 0xb258:	/* bsg	 */
-	case 0xb218:	/* pc	 */
-	case 0xb228:	/* pt	 */
-	case 0xb98d:	/* epsw	 */
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int __kprobes get_fixup_type(kprobe_opcode_t *insn)
-{
-	/* default fixup method */
-	int fixup = FIXUP_PSW_NORMAL;
-
-	switch (insn[0] >> 8) {
-	case 0x05:	/* balr	*/
-	case 0x0d:	/* basr */
-		fixup = FIXUP_RETURN_REGISTER;
-		/* if r2 = 0, no branch will be taken */
-		if ((insn[0] & 0x0f) == 0)
-			fixup |= FIXUP_BRANCH_NOT_TAKEN;
-		break;
-	case 0x06:	/* bctr	*/
-	case 0x07:	/* bcr	*/
-		fixup = FIXUP_BRANCH_NOT_TAKEN;
-		break;
-	case 0x45:	/* bal	*/
-	case 0x4d:	/* bas	*/
-		fixup = FIXUP_RETURN_REGISTER;
-		break;
-	case 0x47:	/* bc	*/
-	case 0x46:	/* bct	*/
-	case 0x86:	/* bxh	*/
-	case 0x87:	/* bxle	*/
-		fixup = FIXUP_BRANCH_NOT_TAKEN;
-		break;
-	case 0x82:	/* lpsw	*/
-		fixup = FIXUP_NOT_REQUIRED;
-		break;
-	case 0xb2:	/* lpswe */
-		if ((insn[0] & 0xff) == 0xb2)
-			fixup = FIXUP_NOT_REQUIRED;
-		break;
-	case 0xa7:	/* bras	*/
-		if ((insn[0] & 0x0f) == 0x05)
-			fixup |= FIXUP_RETURN_REGISTER;
-		break;
-	case 0xc0:
-		if ((insn[0] & 0x0f) == 0x05)	/* brasl */
-			fixup |= FIXUP_RETURN_REGISTER;
-		break;
-	case 0xeb:
-		switch (insn[2] & 0xff) {
-		case 0x44: /* bxhg  */
-		case 0x45: /* bxleg */
-			fixup = FIXUP_BRANCH_NOT_TAKEN;
-			break;
-		}
-		break;
-	case 0xe3:	/* bctg	*/
-		if ((insn[2] & 0xff) == 0x46)
-			fixup = FIXUP_BRANCH_NOT_TAKEN;
-		break;
-	case 0xec:
-		switch (insn[2] & 0xff) {
-		case 0xe5: /* clgrb */
-		case 0xe6: /* cgrb  */
-		case 0xf6: /* crb   */
-		case 0xf7: /* clrb  */
-		case 0xfc: /* cgib  */
-		case 0xfd: /* cglib */
-		case 0xfe: /* cib   */
-		case 0xff: /* clib  */
-			fixup = FIXUP_BRANCH_NOT_TAKEN;
-			break;
-		}
-		break;
-	}
-	return fixup;
-}
-
-static int __kprobes is_insn_relative_long(kprobe_opcode_t *insn)
-{
-	/* Check if we have a RIL-b or RIL-c format instruction which
-	 * we need to modify in order to avoid instruction emulation. */
-	switch (insn[0] >> 8) {
-	case 0xc0:
-		if ((insn[0] & 0x0f) == 0x00) /* larl */
-			return true;
-		break;
-	case 0xc4:
-		switch (insn[0] & 0x0f) {
-		case 0x02: /* llhrl  */
-		case 0x04: /* lghrl  */
-		case 0x05: /* lhrl   */
-		case 0x06: /* llghrl */
-		case 0x07: /* sthrl  */
-		case 0x08: /* lgrl   */
-		case 0x0b: /* stgrl  */
-		case 0x0c: /* lgfrl  */
-		case 0x0d: /* lrl    */
-		case 0x0e: /* llgfrl */
-		case 0x0f: /* strl   */
-			return true;
-		}
-		break;
-	case 0xc6:
-		switch (insn[0] & 0x0f) {
-		case 0x02: /* pfdrl  */
-		case 0x04: /* cghrl  */
-		case 0x05: /* chrl   */
-		case 0x06: /* clghrl */
-		case 0x07: /* clhrl  */
-		case 0x08: /* cgrl   */
-		case 0x0a: /* clgrl  */
-		case 0x0c: /* cgfrl  */
-		case 0x0d: /* crl    */
-		case 0x0e: /* clgfrl */
-		case 0x0f: /* clrl   */
-			return true;
-		}
-		break;
-	}
-	return false;
-}
-
 static void __kprobes copy_instruction(struct kprobe *p)
 {
 	s64 disp, new_disp;
 	u64 addr, new_addr;
 
 	memcpy(p->ainsn.insn, p->addr, insn_length(p->opcode >> 8));
-	if (!is_insn_relative_long(p->ainsn.insn))
+	if (!probe_is_insn_relative_long(p->ainsn.insn))
 		return;
 	/*
 	 * For pc-relative instructions in RIL-b or RIL-c format patch the
@@ -276,7 +128,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	if ((unsigned long) p->addr & 0x01)
 		return -EINVAL;
 	/* Make sure the probe isn't going on a difficult instruction */
-	if (is_prohibited_opcode(p->addr))
+	if (probe_is_prohibited_opcode(p->addr))
 		return -EINVAL;
 	if (s390_get_insn_slot(p))
 		return -ENOMEM;
@@ -366,9 +218,9 @@ static void __kprobes disable_singlestep(struct kprobe_ctlblk *kcb,
  */
 static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p)
 {
-	kcb->prev_kprobe.kp = __get_cpu_var(current_kprobe);
+	kcb->prev_kprobe.kp = __this_cpu_read(current_kprobe);
 	kcb->prev_kprobe.status = kcb->kprobe_status;
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 /*
@@ -378,7 +230,7 @@ static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p)
  */
 static void __kprobes pop_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 }
 
@@ -459,7 +311,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 		enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
 		return 1;
 	} else if (kprobe_running()) {
-		p = __get_cpu_var(current_kprobe);
+		p = __this_cpu_read(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {
 			/*
 			 * Continuation after the jprobe completed and
@@ -605,7 +457,7 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	unsigned long ip = regs->psw.addr & PSW_ADDR_INSN;
-	int fixup = get_fixup_type(p->ainsn.insn);
+	int fixup = probe_get_fixup_type(p->ainsn.insn);
 
 	if (fixup & FIXUP_PSW_NORMAL)
 		ip += (unsigned long) p->addr - (unsigned long) p->ainsn.insn;
@@ -789,11 +641,6 @@ void __kprobes jprobe_return(void)
 	asm volatile(".word 0x0002");
 }
 
-static void __used __kprobes jprobe_return_end(void)
-{
-	asm volatile("bcr 0,0");
-}
-
 int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 719e27b2cf22..4685337fa7c6 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -25,6 +25,7 @@
 #include <asm/elf.h>
 #include <asm/asm-offsets.h>
 #include <asm/os_info.h>
+#include <asm/switch_to.h>
 
 typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long);
 
@@ -43,7 +44,7 @@ static void add_elf_notes(int cpu)
 
 	memcpy((void *) (4608UL + sa->pref_reg), sa, sizeof(*sa));
 	ptr = (u64 *) per_cpu_ptr(crash_notes, cpu);
-	ptr = fill_cpu_elf_notes(ptr, sa);
+	ptr = fill_cpu_elf_notes(ptr, sa, NULL);
 	memset(ptr, 0, sizeof(struct elf_note));
 }
 
@@ -53,8 +54,11 @@ static void add_elf_notes(int cpu)
 static void setup_regs(void)
 {
 	unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE;
+	struct _lowcore *lc;
 	int cpu, this_cpu;
 
+	/* Get lowcore pointer from store status of this CPU (absolute zero) */
+	lc = (struct _lowcore *)(unsigned long)S390_lowcore.prefixreg_save_area;
 	this_cpu = smp_find_processor_id(stap());
 	add_elf_notes(this_cpu);
 	for_each_online_cpu(cpu) {
@@ -64,6 +68,8 @@ static void setup_regs(void)
 			continue;
 		add_elf_notes(cpu);
 	}
+	if (MACHINE_HAS_VX)
+		save_vx_regs_safe((void *) lc->vector_save_area_addr);
 	/* Copy dump CPU store status info to absolute zero */
 	memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area));
 }
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 433c6dbfa442..4300ea374826 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -8,62 +8,72 @@
 #include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/ftrace.h>
+#include <asm/ptrace.h>
 
 	.section .kprobes.text, "ax"
 
 ENTRY(ftrace_stub)
 	br	%r14
 
+#define STACK_FRAME_SIZE  (STACK_FRAME_OVERHEAD + __PT_SIZE)
+#define STACK_PTREGS	  (STACK_FRAME_OVERHEAD)
+#define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS)
+#define STACK_PTREGS_PSW  (STACK_PTREGS + __PT_PSW)
+
 ENTRY(_mcount)
-#ifdef CONFIG_DYNAMIC_FTRACE
 	br	%r14
 
 ENTRY(ftrace_caller)
+	.globl	ftrace_regs_caller
+	.set	ftrace_regs_caller,ftrace_caller
+	lgr	%r1,%r15
+	aghi	%r15,-STACK_FRAME_SIZE
+	stg	%r1,__SF_BACKCHAIN(%r15)
+	stg	%r1,(STACK_PTREGS_GPRS+15*8)(%r15)
+	stg	%r0,(STACK_PTREGS_PSW+8)(%r15)
+	stmg	%r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15)
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+	aghik	%r2,%r0,-MCOUNT_INSN_SIZE
+	lgrl	%r4,function_trace_op
+	lgrl	%r1,ftrace_trace_function
+#else
+	lgr	%r2,%r0
+	aghi	%r2,-MCOUNT_INSN_SIZE
+	larl	%r4,function_trace_op
+	lg	%r4,0(%r4)
+	larl	%r1,ftrace_trace_function
+	lg	%r1,0(%r1)
 #endif
-	stm	%r2,%r5,16(%r15)
-	bras	%r1,1f
-0:	.long	ftrace_trace_function
-1:	st	%r14,56(%r15)
-	lr	%r0,%r15
-	ahi	%r15,-96
-	l	%r3,100(%r15)
-	la	%r2,0(%r14)
-	st	%r0,__SF_BACKCHAIN(%r15)
-	la	%r3,0(%r3)
-	ahi	%r2,-MCOUNT_INSN_SIZE
-	l	%r14,0b-0b(%r1)
-	l	%r14,0(%r14)
-	basr	%r14,%r14
+	lgr	%r3,%r14
+	la	%r5,STACK_PTREGS(%r15)
+	basr	%r14,%r1
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	l	%r2,100(%r15)
-	l	%r3,152(%r15)
+# The j instruction gets runtime patched to a nop instruction.
+# See ftrace_enable_ftrace_graph_caller.
 ENTRY(ftrace_graph_caller)
-# The bras instruction gets runtime patched to call prepare_ftrace_return.
-# See ftrace_enable_ftrace_graph_caller. The patched instruction is:
-#	bras	%r14,prepare_ftrace_return
-	bras	%r14,0f
-0:	st	%r2,100(%r15)
+	j	ftrace_graph_caller_end
+	lg	%r2,(STACK_PTREGS_GPRS+14*8)(%r15)
+	lg	%r3,(STACK_PTREGS_PSW+8)(%r15)
+	brasl	%r14,prepare_ftrace_return
+	stg	%r2,(STACK_PTREGS_GPRS+14*8)(%r15)
+ftrace_graph_caller_end:
+	.globl	ftrace_graph_caller_end
 #endif
-	ahi	%r15,96
-	l	%r14,56(%r15)
-	lm	%r2,%r5,16(%r15)
-	br	%r14
+	lg	%r1,(STACK_PTREGS_PSW+8)(%r15)
+	lmg	%r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15)
+	br	%r1
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 ENTRY(return_to_handler)
-	stm	%r2,%r5,16(%r15)
-	st	%r14,56(%r15)
-	lr	%r0,%r15
-	ahi	%r15,-96
-	st	%r0,__SF_BACKCHAIN(%r15)
-	bras	%r1,0f
-	.long	ftrace_return_to_handler
-0:	l	%r2,0b-0b(%r1)
-	basr	%r14,%r2
-	lr	%r14,%r2
-	ahi	%r15,96
-	lm	%r2,%r5,16(%r15)
+	stmg	%r2,%r5,32(%r15)
+	lgr	%r1,%r15
+	aghi	%r15,-STACK_FRAME_OVERHEAD
+	stg	%r1,__SF_BACKCHAIN(%r15)
+	brasl	%r14,ftrace_return_to_handler
+	aghi	%r15,STACK_FRAME_OVERHEAD
+	lgr	%r14,%r2
+	lmg	%r2,%r5,32(%r15)
 	br	%r14
 
 #endif
diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S
deleted file mode 100644
index c67a8bf0fd9a..000000000000
--- a/arch/s390/kernel/mcount64.S
+++ /dev/null
@@ -1,62 +0,0 @@
-/*
- * Copyright IBM Corp. 2008, 2009
- *
- *   Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
- *
- */
-
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/ftrace.h>
-
-	.section .kprobes.text, "ax"
-
-ENTRY(ftrace_stub)
-	br	%r14
-
-ENTRY(_mcount)
-#ifdef CONFIG_DYNAMIC_FTRACE
-	br	%r14
-
-ENTRY(ftrace_caller)
-#endif
-	stmg	%r2,%r5,32(%r15)
-	stg	%r14,112(%r15)
-	lgr	%r1,%r15
-	aghi	%r15,-160
-	stg	%r1,__SF_BACKCHAIN(%r15)
-	lgr	%r2,%r14
-	lg	%r3,168(%r15)
-	aghi	%r2,-MCOUNT_INSN_SIZE
-	larl	%r14,ftrace_trace_function
-	lg	%r14,0(%r14)
-	basr	%r14,%r14
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	lg	%r2,168(%r15)
-	lg	%r3,272(%r15)
-ENTRY(ftrace_graph_caller)
-# The bras instruction gets runtime patched to call prepare_ftrace_return.
-# See ftrace_enable_ftrace_graph_caller. The patched instruction is:
-#	bras	%r14,prepare_ftrace_return
-	bras	%r14,0f
-0:	stg	%r2,168(%r15)
-#endif
-	aghi	%r15,160
-	lmg	%r2,%r5,32(%r15)
-	lg	%r14,112(%r15)
-	br	%r14
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-
-ENTRY(return_to_handler)
-	stmg	%r2,%r5,32(%r15)
-	lgr	%r1,%r15
-	aghi	%r15,-160
-	stg	%r1,__SF_BACKCHAIN(%r15)
-	brasl	%r14,ftrace_return_to_handler
-	aghi	%r15,160
-	lgr	%r14,%r2
-	lmg	%r2,%r5,32(%r15)
-	br	%r14
-
-#endif
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 210e1285f75a..dd1c24ceda50 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -20,6 +20,7 @@
 #include <asm/cputime.h>
 #include <asm/nmi.h>
 #include <asm/crw.h>
+#include <asm/switch_to.h>
 
 struct mcck_struct {
 	int kill_task;
@@ -53,8 +54,12 @@ void s390_handle_mcck(void)
 	 */
 	local_irq_save(flags);
 	local_mcck_disable();
-	mcck = __get_cpu_var(cpu_mcck);
-	memset(&__get_cpu_var(cpu_mcck), 0, sizeof(struct mcck_struct));
+	/*
+	 * Ummm... Does this make sense at all? Copying the percpu struct
+	 * and then zapping it one statement later?
+	 */
+	memcpy(&mcck, this_cpu_ptr(&cpu_mcck), sizeof(mcck));
+	memset(&mcck, 0, sizeof(struct mcck_struct));
 	clear_cpu_flag(CIF_MCCK_PENDING);
 	local_mcck_enable();
 	local_irq_restore(flags);
@@ -163,6 +168,21 @@ static int notrace s390_revalidate_registers(struct mci *mci)
 			"	ld	15,120(%0)\n"
 			: : "a" (fpt_save_area));
 	}
+
+#ifdef CONFIG_64BIT
+	/* Revalidate vector registers */
+	if (MACHINE_HAS_VX && current->thread.vxrs) {
+		if (!mci->vr) {
+			/*
+			 * Vector registers can't be restored and therefore
+			 * the process needs to be terminated.
+			 */
+			kill_task = 1;
+		}
+		restore_vx_regs((__vector128 *)
+				S390_lowcore.vector_save_area_addr);
+	}
+#endif
 	/* Revalidate access registers */
 	asm volatile(
 		"	lam	0,15,0(%0)"
@@ -253,7 +273,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 	nmi_enter();
 	inc_irq_stat(NMI_NMI);
 	mci = (struct mci *) &S390_lowcore.mcck_interruption_code;
-	mcck = &__get_cpu_var(cpu_mcck);
+	mcck = this_cpu_ptr(&cpu_mcck);
 	umode = user_mode(regs);
 
 	if (mci->sd) {
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index d3194de7ae1e..56fdad479115 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -173,7 +173,7 @@ static int validate_ctr_auth(const struct hw_perf_event *hwc)
  */
 static void cpumf_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	int err;
 
 	if (cpuhw->flags & PMU_F_ENABLED)
@@ -196,7 +196,7 @@ static void cpumf_pmu_enable(struct pmu *pmu)
  */
 static void cpumf_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	int err;
 	u64 inactive;
 
@@ -230,7 +230,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
 		return;
 
 	inc_irq_stat(IRQEXT_CMC);
-	cpuhw = &__get_cpu_var(cpu_hw_events);
+	cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	/* Measurement alerts are shared and might happen when the PMU
 	 * is not reserved.  Ignore these alerts in this case. */
@@ -250,7 +250,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
 #define PMC_RELEASE   1
 static void setup_pmc_cpu(void *flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	switch (*((int *) flags)) {
 	case PMC_INIT:
@@ -475,7 +475,7 @@ static void cpumf_pmu_read(struct perf_event *event)
 
 static void cpumf_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
@@ -506,7 +506,7 @@ static void cpumf_pmu_start(struct perf_event *event, int flags)
 
 static void cpumf_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (!(hwc->state & PERF_HES_STOPPED)) {
@@ -527,7 +527,7 @@ static void cpumf_pmu_stop(struct perf_event *event, int flags)
 
 static int cpumf_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	/* Check authorization for the counter set to which this
 	 * counter belongs.
@@ -551,7 +551,7 @@ static int cpumf_pmu_add(struct perf_event *event, int flags)
 
 static void cpumf_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	cpumf_pmu_stop(event, PERF_EF_UPDATE);
 
@@ -575,7 +575,7 @@ static void cpumf_pmu_del(struct perf_event *event, int flags)
  */
 static void cpumf_pmu_start_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	perf_pmu_disable(pmu);
 	cpuhw->flags |= PERF_EVENT_TXN;
@@ -589,7 +589,7 @@ static void cpumf_pmu_start_txn(struct pmu *pmu)
  */
 static void cpumf_pmu_cancel_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	WARN_ON(cpuhw->tx_state != cpuhw->state);
 
@@ -604,7 +604,7 @@ static void cpumf_pmu_cancel_txn(struct pmu *pmu)
  */
 static int cpumf_pmu_commit_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	u64 state;
 
 	/* check if the updated state can be scheduled */
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index ea0c7b2ef030..08e761318c17 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -562,7 +562,7 @@ static DEFINE_MUTEX(pmc_reserve_mutex);
 static void setup_pmc_cpu(void *flags)
 {
 	int err;
-	struct cpu_hw_sf *cpusf = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpusf = this_cpu_ptr(&cpu_hw_sf);
 
 	err = 0;
 	switch (*((int *) flags)) {
@@ -849,7 +849,7 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 
 static void cpumsf_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 	struct hw_perf_event *hwc;
 	int err;
 
@@ -898,7 +898,7 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
 
 static void cpumsf_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 	struct hws_lsctl_request_block inactive;
 	struct hws_qsi_info_block si;
 	int err;
@@ -1306,7 +1306,7 @@ static void cpumsf_pmu_read(struct perf_event *event)
  */
 static void cpumsf_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
 		return;
@@ -1327,7 +1327,7 @@ static void cpumsf_pmu_start(struct perf_event *event, int flags)
  */
 static void cpumsf_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	if (event->hw.state & PERF_HES_STOPPED)
 		return;
@@ -1346,7 +1346,7 @@ static void cpumsf_pmu_stop(struct perf_event *event, int flags)
 
 static int cpumsf_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 	int err;
 
 	if (cpuhw->flags & PMU_F_IN_USE)
@@ -1397,7 +1397,7 @@ out:
 
 static void cpumsf_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	perf_pmu_disable(event->pmu);
 	cpumsf_pmu_stop(event, PERF_EF_UPDATE);
@@ -1470,7 +1470,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
 	if (!(alert & CPU_MF_INT_SF_MASK))
 		return;
 	inc_irq_stat(IRQEXT_CMS);
-	cpuhw = &__get_cpu_var(cpu_hw_sf);
+	cpuhw = this_cpu_ptr(&cpu_hw_sf);
 
 	/* Measurement alerts are shared and might happen when the PMU
 	 * is not reserved.  Ignore these alerts in this case. */
diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S
index 813ec7260878..f6f8886399f6 100644
--- a/arch/s390/kernel/pgm_check.S
+++ b/arch/s390/kernel/pgm_check.S
@@ -49,7 +49,7 @@ PGM_CHECK_DEFAULT			/* 17 */
 PGM_CHECK_64BIT(transaction_exception)	/* 18 */
 PGM_CHECK_DEFAULT			/* 19 */
 PGM_CHECK_DEFAULT			/* 1a */
-PGM_CHECK_DEFAULT			/* 1b */
+PGM_CHECK_64BIT(vector_exception)	/* 1b */
 PGM_CHECK(space_switch_exception)	/* 1c */
 PGM_CHECK(hfp_sqrt_exception)		/* 1d */
 PGM_CHECK_DEFAULT			/* 1e */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 93b9ca42e5c0..ed84cc224899 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -61,30 +61,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 	return sf->gprs[8];
 }
 
-void arch_cpu_idle(void)
-{
-	local_mcck_disable();
-	if (test_cpu_flag(CIF_MCCK_PENDING)) {
-		local_mcck_enable();
-		local_irq_enable();
-		return;
-	}
-	/* Halt the cpu and keep track of cpu time accounting. */
-	vtime_stop_cpu();
-	local_irq_enable();
-}
-
-void arch_cpu_idle_exit(void)
-{
-	if (test_cpu_flag(CIF_MCCK_PENDING))
-		s390_handle_mcck();
-}
-
-void arch_cpu_idle_dead(void)
-{
-	cpu_die();
-}
-
 extern void __kprobes kernel_thread_starter(void);
 
 /*
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 24612029f450..dbdd33ee0102 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -23,15 +23,13 @@ static DEFINE_PER_CPU(struct cpuid, cpu_id);
  */
 void cpu_init(void)
 {
-	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
-	struct cpuid *id = &__get_cpu_var(cpu_id);
+	struct cpuid *id = this_cpu_ptr(&cpu_id);
 
 	get_cpu_id(id);
 	atomic_inc(&init_mm.mm_count);
 	current->active_mm = &init_mm;
 	BUG_ON(current->mm);
 	enter_lazy_tlb(&init_mm, current);
-	memset(idle, 0, sizeof(*idle));
 }
 
 /*
@@ -41,7 +39,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	static const char *hwcap_str[] = {
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
-		"edat", "etf3eh", "highgprs", "te"
+		"edat", "etf3eh", "highgprs", "te", "vx"
 	};
 	unsigned long n = (unsigned long) v - 1;
 	int i;
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 5dc7ad9e2fbf..f537e937a988 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -38,15 +38,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
-enum s390_regset {
-	REGSET_GENERAL,
-	REGSET_FP,
-	REGSET_LAST_BREAK,
-	REGSET_TDB,
-	REGSET_SYSTEM_CALL,
-	REGSET_GENERAL_EXTENDED,
-};
-
 void update_cr_regs(struct task_struct *task)
 {
 	struct pt_regs *regs = task_pt_regs(task);
@@ -55,27 +46,39 @@ void update_cr_regs(struct task_struct *task)
 
 #ifdef CONFIG_64BIT
 	/* Take care of the enable/disable of transactional execution. */
-	if (MACHINE_HAS_TE) {
+	if (MACHINE_HAS_TE || MACHINE_HAS_VX) {
 		unsigned long cr, cr_new;
 
 		__ctl_store(cr, 0, 0);
-		/* Set or clear transaction execution TXC bit 8. */
-		cr_new = cr | (1UL << 55);
-		if (task->thread.per_flags & PER_FLAG_NO_TE)
-			cr_new &= ~(1UL << 55);
+		cr_new = cr;
+		if (MACHINE_HAS_TE) {
+			/* Set or clear transaction execution TXC bit 8. */
+			cr_new |= (1UL << 55);
+			if (task->thread.per_flags & PER_FLAG_NO_TE)
+				cr_new &= ~(1UL << 55);
+		}
+		if (MACHINE_HAS_VX) {
+			/* Enable/disable of vector extension */
+			cr_new &= ~(1UL << 17);
+			if (task->thread.vxrs)
+				cr_new |= (1UL << 17);
+		}
 		if (cr_new != cr)
 			__ctl_load(cr_new, 0, 0);
-		/* Set or clear transaction execution TDC bits 62 and 63. */
-		__ctl_store(cr, 2, 2);
-		cr_new = cr & ~3UL;
-		if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
-			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND_TEND)
-				cr_new |= 1UL;
-			else
-				cr_new |= 2UL;
+		if (MACHINE_HAS_TE) {
+			/* Set/clear transaction execution TDC bits 62/63. */
+			__ctl_store(cr, 2, 2);
+			cr_new = cr & ~3UL;
+			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
+				if (task->thread.per_flags &
+				    PER_FLAG_TE_ABORT_RAND_TEND)
+					cr_new |= 1UL;
+				else
+					cr_new |= 2UL;
+			}
+			if (cr_new != cr)
+				__ctl_load(cr_new, 2, 2);
 		}
-		if (cr_new != cr)
-			__ctl_load(cr_new, 2, 2);
 	}
 #endif
 	/* Copy user specified PER registers */
@@ -84,7 +87,8 @@ void update_cr_regs(struct task_struct *task)
 	new.end = thread->per_user.end;
 
 	/* merge TIF_SINGLE_STEP into user specified PER registers. */
-	if (test_tsk_thread_flag(task, TIF_SINGLE_STEP)) {
+	if (test_tsk_thread_flag(task, TIF_SINGLE_STEP) ||
+	    test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP)) {
 		if (test_tsk_thread_flag(task, TIF_BLOCK_STEP))
 			new.control |= PER_EVENT_BRANCH;
 		else
@@ -93,6 +97,8 @@ void update_cr_regs(struct task_struct *task)
 		new.control |= PER_CONTROL_SUSPENSION;
 		new.control |= PER_EVENT_TRANSACTION_END;
 #endif
+		if (test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP))
+			new.control |= PER_EVENT_IFETCH;
 		new.start = 0;
 		new.end = PSW_ADDR_INSN;
 	}
@@ -803,7 +809,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	long ret = 0;
 
 	/* Do the secure computing check first. */
-	if (secure_computing(regs->gprs[2])) {
+	if (secure_computing()) {
 		/* seccomp failures shouldn't expose any additional code. */
 		ret = -1;
 		goto out;
@@ -923,7 +929,15 @@ static int s390_fpregs_get(struct task_struct *target,
 		save_fp_ctl(&target->thread.fp_regs.fpc);
 		save_fp_regs(target->thread.fp_regs.fprs);
 	}
+#ifdef CONFIG_64BIT
+	else if (target->thread.vxrs) {
+		int i;
 
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			target->thread.fp_regs.fprs[i] =
+				*(freg_t *)(target->thread.vxrs + i);
+	}
+#endif
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				   &target->thread.fp_regs, 0, -1);
 }
@@ -957,9 +971,20 @@ static int s390_fpregs_set(struct task_struct *target,
 					target->thread.fp_regs.fprs,
 					offsetof(s390_fp_regs, fprs), -1);
 
-	if (rc == 0 && target == current) {
-		restore_fp_ctl(&target->thread.fp_regs.fpc);
-		restore_fp_regs(target->thread.fp_regs.fprs);
+	if (rc == 0) {
+		if (target == current) {
+			restore_fp_ctl(&target->thread.fp_regs.fpc);
+			restore_fp_regs(target->thread.fp_regs.fprs);
+		}
+#ifdef CONFIG_64BIT
+		else if (target->thread.vxrs) {
+			int i;
+
+			for (i = 0; i < __NUM_VXRS_LOW; i++)
+				*(freg_t *)(target->thread.vxrs + i) =
+					target->thread.fp_regs.fprs[i];
+		}
+#endif
 	}
 
 	return rc;
@@ -1015,6 +1040,95 @@ static int s390_tdb_set(struct task_struct *target,
 	return 0;
 }
 
+static int s390_vxrs_active(struct task_struct *target,
+			      const struct user_regset *regset)
+{
+	return !!target->thread.vxrs;
+}
+
+static int s390_vxrs_low_get(struct task_struct *target,
+			     const struct user_regset *regset,
+			     unsigned int pos, unsigned int count,
+			     void *kbuf, void __user *ubuf)
+{
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	if (target->thread.vxrs) {
+		if (target == current)
+			save_vx_regs(target->thread.vxrs);
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(target->thread.vxrs + i) + 1);
+	} else
+		memset(vxrs, 0, sizeof(vxrs));
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+}
+
+static int s390_vxrs_low_set(struct task_struct *target,
+			     const struct user_regset *regset,
+			     unsigned int pos, unsigned int count,
+			     const void *kbuf, const void __user *ubuf)
+{
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i, rc;
+
+	if (!target->thread.vxrs) {
+		rc = alloc_vector_registers(target);
+		if (rc)
+			return rc;
+	} else if (target == current)
+		save_vx_regs(target->thread.vxrs);
+
+	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+	if (rc == 0) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(target->thread.vxrs + i) + 1) = vxrs[i];
+		if (target == current)
+			restore_vx_regs(target->thread.vxrs);
+	}
+
+	return rc;
+}
+
+static int s390_vxrs_high_get(struct task_struct *target,
+			      const struct user_regset *regset,
+			      unsigned int pos, unsigned int count,
+			      void *kbuf, void __user *ubuf)
+{
+	__vector128 vxrs[__NUM_VXRS_HIGH];
+
+	if (target->thread.vxrs) {
+		if (target == current)
+			save_vx_regs(target->thread.vxrs);
+		memcpy(vxrs, target->thread.vxrs + __NUM_VXRS_LOW,
+		       sizeof(vxrs));
+	} else
+		memset(vxrs, 0, sizeof(vxrs));
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
+}
+
+static int s390_vxrs_high_set(struct task_struct *target,
+			      const struct user_regset *regset,
+			      unsigned int pos, unsigned int count,
+			      const void *kbuf, const void __user *ubuf)
+{
+	int rc;
+
+	if (!target->thread.vxrs) {
+		rc = alloc_vector_registers(target);
+		if (rc)
+			return rc;
+	} else if (target == current)
+		save_vx_regs(target->thread.vxrs);
+
+	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				target->thread.vxrs + __NUM_VXRS_LOW, 0, -1);
+	if (rc == 0 && target == current)
+		restore_vx_regs(target->thread.vxrs);
+
+	return rc;
+}
+
 #endif
 
 static int s390_system_call_get(struct task_struct *target,
@@ -1038,7 +1152,7 @@ static int s390_system_call_set(struct task_struct *target,
 }
 
 static const struct user_regset s390_regsets[] = {
-	[REGSET_GENERAL] = {
+	{
 		.core_note_type = NT_PRSTATUS,
 		.n = sizeof(s390_regs) / sizeof(long),
 		.size = sizeof(long),
@@ -1046,7 +1160,7 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_regs_get,
 		.set = s390_regs_set,
 	},
-	[REGSET_FP] = {
+	{
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(s390_fp_regs) / sizeof(long),
 		.size = sizeof(long),
@@ -1054,8 +1168,16 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_fpregs_get,
 		.set = s390_fpregs_set,
 	},
+	{
+		.core_note_type = NT_S390_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(unsigned int),
+		.align = sizeof(unsigned int),
+		.get = s390_system_call_get,
+		.set = s390_system_call_set,
+	},
 #ifdef CONFIG_64BIT
-	[REGSET_LAST_BREAK] = {
+	{
 		.core_note_type = NT_S390_LAST_BREAK,
 		.n = 1,
 		.size = sizeof(long),
@@ -1063,7 +1185,7 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_last_break_get,
 		.set = s390_last_break_set,
 	},
-	[REGSET_TDB] = {
+	{
 		.core_note_type = NT_S390_TDB,
 		.n = 1,
 		.size = 256,
@@ -1071,15 +1193,25 @@ static const struct user_regset s390_regsets[] = {
 		.get = s390_tdb_get,
 		.set = s390_tdb_set,
 	},
-#endif
-	[REGSET_SYSTEM_CALL] = {
-		.core_note_type = NT_S390_SYSTEM_CALL,
-		.n = 1,
-		.size = sizeof(unsigned int),
-		.align = sizeof(unsigned int),
-		.get = s390_system_call_get,
-		.set = s390_system_call_set,
+	{
+		.core_note_type = NT_S390_VXRS_LOW,
+		.n = __NUM_VXRS_LOW,
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_low_get,
+		.set = s390_vxrs_low_set,
 	},
+	{
+		.core_note_type = NT_S390_VXRS_HIGH,
+		.n = __NUM_VXRS_HIGH,
+		.size = sizeof(__vector128),
+		.align = sizeof(__vector128),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_high_get,
+		.set = s390_vxrs_high_set,
+	},
+#endif
 };
 
 static const struct user_regset_view user_s390_view = {
@@ -1244,7 +1376,7 @@ static int s390_compat_last_break_set(struct task_struct *target,
 }
 
 static const struct user_regset s390_compat_regsets[] = {
-	[REGSET_GENERAL] = {
+	{
 		.core_note_type = NT_PRSTATUS,
 		.n = sizeof(s390_compat_regs) / sizeof(compat_long_t),
 		.size = sizeof(compat_long_t),
@@ -1252,7 +1384,7 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_compat_regs_get,
 		.set = s390_compat_regs_set,
 	},
-	[REGSET_FP] = {
+	{
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(s390_fp_regs) / sizeof(compat_long_t),
 		.size = sizeof(compat_long_t),
@@ -1260,7 +1392,15 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_fpregs_get,
 		.set = s390_fpregs_set,
 	},
-	[REGSET_LAST_BREAK] = {
+	{
+		.core_note_type = NT_S390_SYSTEM_CALL,
+		.n = 1,
+		.size = sizeof(compat_uint_t),
+		.align = sizeof(compat_uint_t),
+		.get = s390_system_call_get,
+		.set = s390_system_call_set,
+	},
+	{
 		.core_note_type = NT_S390_LAST_BREAK,
 		.n = 1,
 		.size = sizeof(long),
@@ -1268,7 +1408,7 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_compat_last_break_get,
 		.set = s390_compat_last_break_set,
 	},
-	[REGSET_TDB] = {
+	{
 		.core_note_type = NT_S390_TDB,
 		.n = 1,
 		.size = 256,
@@ -1276,15 +1416,25 @@ static const struct user_regset s390_compat_regsets[] = {
 		.get = s390_tdb_get,
 		.set = s390_tdb_set,
 	},
-	[REGSET_SYSTEM_CALL] = {
-		.core_note_type = NT_S390_SYSTEM_CALL,
-		.n = 1,
-		.size = sizeof(compat_uint_t),
-		.align = sizeof(compat_uint_t),
-		.get = s390_system_call_get,
-		.set = s390_system_call_set,
+	{
+		.core_note_type = NT_S390_VXRS_LOW,
+		.n = __NUM_VXRS_LOW,
+		.size = sizeof(__u64),
+		.align = sizeof(__u64),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_low_get,
+		.set = s390_vxrs_low_set,
+	},
+	{
+		.core_note_type = NT_S390_VXRS_HIGH,
+		.n = __NUM_VXRS_HIGH,
+		.size = sizeof(__vector128),
+		.align = sizeof(__vector128),
+		.active = s390_vxrs_active,
+		.get = s390_vxrs_high_get,
+		.set = s390_vxrs_high_set,
 	},
-	[REGSET_GENERAL_EXTENDED] = {
+	{
 		.core_note_type = NT_S390_HIGH_GPRS,
 		.n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t),
 		.size = sizeof(compat_long_t),
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 82bc113e8c1d..e80d9ff9a56d 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -343,6 +343,9 @@ static void __init setup_lowcore(void)
 		__ctl_set_bit(14, 29);
 	}
 #else
+	if (MACHINE_HAS_VX)
+		lc->vector_save_area_addr =
+			(unsigned long) &lc->vector_save_area;
 	lc->vdso_per_cpu_data = (unsigned long) &lc->paste[0];
 #endif
 	lc->sync_enter_timer = S390_lowcore.sync_enter_timer;
@@ -452,8 +455,8 @@ static void __init setup_memory_end(void)
 #ifdef CONFIG_64BIT
 	vmalloc_size = VMALLOC_END ?: (128UL << 30) - MODULES_LEN;
 	tmp = (memory_end ?: max_physmem_end) / PAGE_SIZE;
-	tmp = tmp * (sizeof(struct page) + PAGE_SIZE) + vmalloc_size;
-	if (tmp <= (1UL << 42))
+	tmp = tmp * (sizeof(struct page) + PAGE_SIZE);
+	if (tmp + vmalloc_size + MODULES_LEN <= (1UL << 42))
 		vmax = 1UL << 42;	/* 3-level kernel page table */
 	else
 		vmax = 1UL << 53;	/* 4-level kernel page table */
@@ -765,6 +768,12 @@ static void __init setup_hwcaps(void)
 	 */
 	if (test_facility(50) && test_facility(73))
 		elf_hwcap |= HWCAP_S390_TE;
+
+	/*
+	 * Vector extension HWCAP_S390_VXRS is bit 11.
+	 */
+	if (test_facility(129))
+		elf_hwcap |= HWCAP_S390_VXRS;
 #endif
 
 	get_cpu_id(&cpu_id);
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 469c4c6d9182..0c1a0ff0a558 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -31,30 +31,117 @@
 #include <asm/switch_to.h>
 #include "entry.h"
 
-typedef struct 
+/*
+ * Layout of an old-style signal-frame:
+ *	-----------------------------------------
+ *	| save area (_SIGNAL_FRAMESIZE)		|
+ *	-----------------------------------------
+ *	| struct sigcontext			|
+ *	|	oldmask				|
+ *	|	_sigregs *			|
+ *	-----------------------------------------
+ *	| _sigregs with				|
+ *	|	_s390_regs_common		|
+ *	|	_s390_fp_regs			|
+ *	-----------------------------------------
+ *	| int signo				|
+ *	-----------------------------------------
+ *	| _sigregs_ext with			|
+ *	|	gprs_high 64 byte (opt)		|
+ *	|	vxrs_low 128 byte (opt)		|
+ *	|	vxrs_high 256 byte (opt)	|
+ *	|	reserved 128 byte (opt)		|
+ *	-----------------------------------------
+ *	| __u16 svc_insn			|
+ *	-----------------------------------------
+ * The svc_insn entry with the sigreturn system call opcode does not
+ * have a fixed position and moves if gprs_high or vxrs exist.
+ * Future extensions will be added to _sigregs_ext.
+ */
+struct sigframe
 {
 	__u8 callee_used_stack[__SIGNAL_FRAMESIZE];
 	struct sigcontext sc;
 	_sigregs sregs;
 	int signo;
-	__u8 retcode[S390_SYSCALL_SIZE];
-} sigframe;
+	_sigregs_ext sregs_ext;
+	__u16 svc_insn;		/* Offset of svc_insn is NOT fixed! */
+};
 
-typedef struct 
+/*
+ * Layout of an rt signal-frame:
+ *	-----------------------------------------
+ *	| save area (_SIGNAL_FRAMESIZE)		|
+ *	-----------------------------------------
+ *	| svc __NR_rt_sigreturn 2 byte		|
+ *	-----------------------------------------
+ *	| struct siginfo			|
+ *	-----------------------------------------
+ *	| struct ucontext_extended with		|
+ *	|	unsigned long uc_flags		|
+ *	|	struct ucontext *uc_link	|
+ *	|	stack_t uc_stack		|
+ *	|	_sigregs uc_mcontext with	|
+ *	|		_s390_regs_common	|
+ *	|		_s390_fp_regs		|
+ *	|	sigset_t uc_sigmask		|
+ *	|	_sigregs_ext uc_mcontext_ext	|
+ *	|		gprs_high 64 byte (opt)	|
+ *	|		vxrs_low 128 byte (opt)	|
+ *	|		vxrs_high 256 byte (opt)|
+ *	|		reserved 128 byte (opt)	|
+ *	-----------------------------------------
+ * Future extensions will be added to _sigregs_ext.
+ */
+struct rt_sigframe
 {
 	__u8 callee_used_stack[__SIGNAL_FRAMESIZE];
-	__u8 retcode[S390_SYSCALL_SIZE];
+	__u16 svc_insn;
 	struct siginfo info;
-	struct ucontext uc;
-} rt_sigframe;
+	struct ucontext_extended uc;
+};
+
+/* Store registers needed to create the signal frame */
+static void store_sigregs(void)
+{
+	save_access_regs(current->thread.acrs);
+	save_fp_ctl(&current->thread.fp_regs.fpc);
+#ifdef CONFIG_64BIT
+	if (current->thread.vxrs) {
+		int i;
+
+		save_vx_regs(current->thread.vxrs);
+		for (i = 0; i < __NUM_FPRS; i++)
+			current->thread.fp_regs.fprs[i] =
+				*(freg_t *)(current->thread.vxrs + i);
+	} else
+#endif
+		save_fp_regs(current->thread.fp_regs.fprs);
+}
+
+/* Load registers after signal return */
+static void load_sigregs(void)
+{
+	restore_access_regs(current->thread.acrs);
+	/* restore_fp_ctl is done in restore_sigregs */
+#ifdef CONFIG_64BIT
+	if (current->thread.vxrs) {
+		int i;
+
+		for (i = 0; i < __NUM_FPRS; i++)
+			*(freg_t *)(current->thread.vxrs + i) =
+				current->thread.fp_regs.fprs[i];
+		restore_vx_regs(current->thread.vxrs);
+	} else
+#endif
+		restore_fp_regs(current->thread.fp_regs.fprs);
+}
 
 /* Returns non-zero on fault. */
 static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 {
 	_sigregs user_sregs;
 
-	save_access_regs(current->thread.acrs);
-
 	/* Copy a 'clean' PSW mask to the user to avoid leaking
 	   information about whether PER is currently on.  */
 	user_sregs.regs.psw.mask = PSW_USER_BITS |
@@ -63,12 +150,6 @@ static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	memcpy(&user_sregs.regs.gprs, &regs->gprs, sizeof(sregs->regs.gprs));
 	memcpy(&user_sregs.regs.acrs, current->thread.acrs,
 	       sizeof(user_sregs.regs.acrs));
-	/* 
-	 * We have to store the fp registers to current->thread.fp_regs
-	 * to merge them with the emulated registers.
-	 */
-	save_fp_ctl(&current->thread.fp_regs.fpc);
-	save_fp_regs(current->thread.fp_regs.fprs);
 	memcpy(&user_sregs.fpregs, &current->thread.fp_regs,
 	       sizeof(user_sregs.fpregs));
 	if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs)))
@@ -107,20 +188,64 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	memcpy(&regs->gprs, &user_sregs.regs.gprs, sizeof(sregs->regs.gprs));
 	memcpy(&current->thread.acrs, &user_sregs.regs.acrs,
 	       sizeof(current->thread.acrs));
-	restore_access_regs(current->thread.acrs);
 
 	memcpy(&current->thread.fp_regs, &user_sregs.fpregs,
 	       sizeof(current->thread.fp_regs));
 
-	restore_fp_regs(current->thread.fp_regs.fprs);
 	clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */
 	return 0;
 }
 
+/* Returns non-zero on fault. */
+static int save_sigregs_ext(struct pt_regs *regs,
+			    _sigregs_ext __user *sregs_ext)
+{
+#ifdef CONFIG_64BIT
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	/* Save vector registers to signal stack */
+	if (current->thread.vxrs) {
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			vxrs[i] = *((__u64 *)(current->thread.vxrs + i) + 1);
+		if (__copy_to_user(&sregs_ext->vxrs_low, vxrs,
+				   sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_to_user(&sregs_ext->vxrs_high,
+				   current->thread.vxrs + __NUM_VXRS_LOW,
+				   sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+	}
+#endif
+	return 0;
+}
+
+static int restore_sigregs_ext(struct pt_regs *regs,
+			       _sigregs_ext __user *sregs_ext)
+{
+#ifdef CONFIG_64BIT
+	__u64 vxrs[__NUM_VXRS_LOW];
+	int i;
+
+	/* Restore vector registers from signal stack */
+	if (current->thread.vxrs) {
+		if (__copy_from_user(vxrs, &sregs_ext->vxrs_low,
+				     sizeof(sregs_ext->vxrs_low)) ||
+		    __copy_from_user(current->thread.vxrs + __NUM_VXRS_LOW,
+				     &sregs_ext->vxrs_high,
+				     sizeof(sregs_ext->vxrs_high)))
+			return -EFAULT;
+		for (i = 0; i < __NUM_VXRS_LOW; i++)
+			*((__u64 *)(current->thread.vxrs + i) + 1) = vxrs[i];
+	}
+#endif
+	return 0;
+}
+
 SYSCALL_DEFINE0(sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
-	sigframe __user *frame = (sigframe __user *)regs->gprs[15];
+	struct sigframe __user *frame =
+		(struct sigframe __user *) regs->gprs[15];
 	sigset_t set;
 
 	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE))
@@ -128,6 +253,9 @@ SYSCALL_DEFINE0(sigreturn)
 	set_current_blocked(&set);
 	if (restore_sigregs(regs, &frame->sregs))
 		goto badframe;
+	if (restore_sigregs_ext(regs, &frame->sregs_ext))
+		goto badframe;
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
@@ -137,16 +265,20 @@ badframe:
 SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
-	rt_sigframe __user *frame = (rt_sigframe __user *)regs->gprs[15];
+	struct rt_sigframe __user *frame =
+		(struct rt_sigframe __user *)regs->gprs[15];
 	sigset_t set;
 
 	if (__copy_from_user(&set.sig, &frame->uc.uc_sigmask, sizeof(set)))
 		goto badframe;
 	set_current_blocked(&set);
+	if (restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
 	if (restore_sigregs(regs, &frame->uc.uc_mcontext))
 		goto badframe;
-	if (restore_altstack(&frame->uc.uc_stack))
+	if (restore_sigregs_ext(regs, &frame->uc.uc_mcontext_ext))
 		goto badframe;
+	load_sigregs();
 	return regs->gprs[2];
 badframe:
 	force_sig(SIGSEGV, current);
@@ -154,11 +286,6 @@ badframe:
 }
 
 /*
- * Set up a signal frame.
- */
-
-
-/*
  * Determine which stack to use..
  */
 static inline void __user *
@@ -195,39 +322,63 @@ static inline int map_signal(int sig)
 static int setup_frame(int sig, struct k_sigaction *ka,
 		       sigset_t *set, struct pt_regs * regs)
 {
-	sigframe __user *frame;
-
-	frame = get_sigframe(ka, regs, sizeof(sigframe));
+	struct sigframe __user *frame;
+	struct sigcontext sc;
+	unsigned long restorer;
+	size_t frame_size;
 
+	/*
+	 * gprs_high are only present for a 31-bit task running on
+	 * a 64-bit kernel (see compat_signal.c) but the space for
+	 * gprs_high need to be allocated if vector registers are
+	 * included in the signal frame on a 31-bit system.
+	 */
+	frame_size = sizeof(*frame) - sizeof(frame->sregs_ext);
+	if (MACHINE_HAS_VX)
+		frame_size += sizeof(frame->sregs_ext);
+	frame = get_sigframe(ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (__copy_to_user(&frame->sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE))
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
 		return -EFAULT;
 
+	/* Create struct sigcontext on the signal stack */
+	memcpy(&sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE);
+	sc.sregs = (_sigregs __user __force *) &frame->sregs;
+	if (__copy_to_user(&frame->sc, &sc, sizeof(frame->sc)))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create _sigregs on the signal stack */
 	if (save_sigregs(regs, &frame->sregs))
 		return -EFAULT;
-	if (__put_user(&frame->sregs, &frame->sc.sregs))
+
+	/* Place signal number on stack to allow backtrace from handler.  */
+	if (__put_user(regs->gprs[2], (int __user *) &frame->signo))
+		return -EFAULT;
+
+	/* Create _sigregs_ext on the signal stack */
+	if (save_sigregs_ext(regs, &frame->sregs_ext))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ka->sa.sa_flags & SA_RESTORER) {
-                regs->gprs[14] = (unsigned long)
-			ka->sa.sa_restorer | PSW_ADDR_AMODE;
+		restorer = (unsigned long) ka->sa.sa_restorer | PSW_ADDR_AMODE;
 	} else {
-                regs->gprs[14] = (unsigned long)
-			frame->retcode | PSW_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn,
-	                       (u16 __user *)(frame->retcode)))
+		/* Signal frame without vector registers are short ! */
+		__u16 __user *svc = (void *) frame + frame_size - 2;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
 	}
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
-		return -EFAULT;
-
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (unsigned long) frame;
 	/* Force default amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
@@ -247,54 +398,69 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 		regs->gprs[5] = regs->int_parm_long;
 		regs->gprs[6] = task_thread_info(current)->last_break;
 	}
-
-	/* Place signal number on stack to allow backtrace from handler.  */
-	if (__put_user(regs->gprs[2], (int __user *) &frame->signo))
-		return -EFAULT;
 	return 0;
 }
 
 static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 			  struct pt_regs *regs)
 {
-	int err = 0;
-	rt_sigframe __user *frame;
-
-	frame = get_sigframe(&ksig->ka, regs, sizeof(rt_sigframe));
+	struct rt_sigframe __user *frame;
+	unsigned long uc_flags, restorer;
+	size_t frame_size;
 
+	frame_size = sizeof(struct rt_sigframe) - sizeof(_sigregs_ext);
+	/*
+	 * gprs_high are only present for a 31-bit task running on
+	 * a 64-bit kernel (see compat_signal.c) but the space for
+	 * gprs_high need to be allocated if vector registers are
+	 * included in the signal frame on a 31-bit system.
+	 */
+	uc_flags = 0;
+#ifdef CONFIG_64BIT
+	if (MACHINE_HAS_VX) {
+		frame_size += sizeof(_sigregs_ext);
+		if (current->thread.vxrs)
+			uc_flags |= UC_VXRS;
+	}
+#endif
+	frame = get_sigframe(&ksig->ka, regs, frame_size);
 	if (frame == (void __user *) -1UL)
 		return -EFAULT;
 
-	if (copy_siginfo_to_user(&frame->info, &ksig->info))
-		return -EFAULT;
-
-	/* Create the ucontext.  */
-	err |= __put_user(0, &frame->uc.uc_flags);
-	err |= __put_user(NULL, &frame->uc.uc_link);
-	err |= __save_altstack(&frame->uc.uc_stack, regs->gprs[15]);
-	err |= save_sigregs(regs, &frame->uc.uc_mcontext);
-	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-	if (err)
+	/* Set up backchain. */
+	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
 		return -EFAULT;
 
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-                regs->gprs[14] = (unsigned long)
+		restorer = (unsigned long)
 			ksig->ka.sa.sa_restorer | PSW_ADDR_AMODE;
 	} else {
-                regs->gprs[14] = (unsigned long)
-			frame->retcode | PSW_ADDR_AMODE;
-		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
-			       (u16 __user *)(frame->retcode)))
+		__u16 __user *svc = &frame->svc_insn;
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc))
 			return -EFAULT;
+		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
 	}
 
-	/* Set up backchain. */
-	if (__put_user(regs->gprs[15], (addr_t __user *) frame))
+	/* Create siginfo on the signal stack */
+	if (copy_siginfo_to_user(&frame->info, &ksig->info))
+		return -EFAULT;
+
+	/* Store registers needed to create the signal frame */
+	store_sigregs();
+
+	/* Create ucontext on the signal stack. */
+	if (__put_user(uc_flags, &frame->uc.uc_flags) ||
+	    __put_user(NULL, &frame->uc.uc_link) ||
+	    __save_altstack(&frame->uc.uc_stack, regs->gprs[15]) ||
+	    save_sigregs(regs, &frame->uc.uc_mcontext) ||
+	    __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)) ||
+	    save_sigregs_ext(regs, &frame->uc.uc_mcontext_ext))
 		return -EFAULT;
 
 	/* Set up registers for signal handler */
+	regs->gprs[14] = restorer;
 	regs->gprs[15] = (unsigned long) frame;
 	/* Force default amode and default user address space control. */
 	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 243c7e512600..6fd9e60101f1 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -45,6 +45,7 @@
 #include <asm/debug.h>
 #include <asm/os_info.h>
 #include <asm/sigp.h>
+#include <asm/idle.h>
 #include "entry.h"
 
 enum {
@@ -82,7 +83,8 @@ DEFINE_MUTEX(smp_cpu_state_mutex);
 /*
  * Signal processor helper functions.
  */
-static inline int __pcpu_sigp_relax(u16 addr, u8 order, u32 parm, u32 *status)
+static inline int __pcpu_sigp_relax(u16 addr, u8 order, unsigned long parm,
+				    u32 *status)
 {
 	int cc;
 
@@ -178,6 +180,9 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
 			goto out;
 	}
 #else
+	if (MACHINE_HAS_VX)
+		lc->vector_save_area_addr =
+			(unsigned long) &lc->vector_save_area;
 	if (vdso_alloc_per_cpu(lc))
 		goto out;
 #endif
@@ -333,12 +338,6 @@ int smp_vcpu_scheduled(int cpu)
 	return pcpu_running(pcpu_devices + cpu);
 }
 
-void smp_yield(void)
-{
-	if (MACHINE_HAS_DIAG44)
-		asm volatile("diag 0,0,0x44");
-}
-
 void smp_yield_cpu(int cpu)
 {
 	if (MACHINE_HAS_DIAG9C)
@@ -517,35 +516,53 @@ EXPORT_SYMBOL(smp_ctl_clear_bit);
 static void __init smp_get_save_area(int cpu, u16 address)
 {
 	void *lc = pcpu_devices[0].lowcore;
-	struct save_area *save_area;
+	struct save_area_ext *sa_ext;
+	unsigned long vx_sa;
 
 	if (is_kdump_kernel())
 		return;
 	if (!OLDMEM_BASE && (address == boot_cpu_address ||
 			     ipl_info.type != IPL_TYPE_FCP_DUMP))
 		return;
-	save_area = dump_save_area_create(cpu);
-	if (!save_area)
+	sa_ext = dump_save_area_create(cpu);
+	if (!sa_ext)
 		panic("could not allocate memory for save area\n");
 	if (address == boot_cpu_address) {
 		/* Copy the registers of the boot cpu. */
-		copy_oldmem_page(1, (void *) save_area, sizeof(*save_area),
+		copy_oldmem_page(1, (void *) &sa_ext->sa, sizeof(sa_ext->sa),
 				 SAVE_AREA_BASE - PAGE_SIZE, 0);
+		if (MACHINE_HAS_VX)
+			save_vx_regs_safe(sa_ext->vx_regs);
 		return;
 	}
 	/* Get the registers of a non-boot cpu. */
 	__pcpu_sigp_relax(address, SIGP_STOP_AND_STORE_STATUS, 0, NULL);
-	memcpy_real(save_area, lc + SAVE_AREA_BASE, sizeof(*save_area));
+	memcpy_real(&sa_ext->sa, lc + SAVE_AREA_BASE, sizeof(sa_ext->sa));
+	if (!MACHINE_HAS_VX)
+		return;
+	/* Get the VX registers */
+	vx_sa = __get_free_page(GFP_KERNEL);
+	if (!vx_sa)
+		panic("could not allocate memory for VX save area\n");
+	__pcpu_sigp_relax(address, SIGP_STORE_ADDITIONAL_STATUS, vx_sa, NULL);
+	memcpy(sa_ext->vx_regs, (void *) vx_sa, sizeof(sa_ext->vx_regs));
+	free_page(vx_sa);
 }
 
 int smp_store_status(int cpu)
 {
+	unsigned long vx_sa;
 	struct pcpu *pcpu;
 
 	pcpu = pcpu_devices + cpu;
 	if (__pcpu_sigp_relax(pcpu->address, SIGP_STOP_AND_STORE_STATUS,
 			      0, NULL) != SIGP_CC_ORDER_CODE_ACCEPTED)
 		return -EIO;
+	if (!MACHINE_HAS_VX)
+		return 0;
+	vx_sa = __pa(pcpu->lowcore->vector_save_area_addr);
+	__pcpu_sigp_relax(pcpu->address, SIGP_STORE_ADDITIONAL_STATUS,
+			  vx_sa, NULL);
 	return 0;
 }
 
@@ -667,7 +684,7 @@ static void smp_start_secondary(void *cpuvoid)
 	cpu_init();
 	preempt_disable();
 	init_cpu_timer();
-	init_cpu_vtimer();
+	vtime_init();
 	pfault_init();
 	notify_cpu_starting(smp_processor_id());
 	set_cpu_online(smp_processor_id(), true);
@@ -726,6 +743,7 @@ int __cpu_disable(void)
 	cregs[6]  &= ~0xff000000UL;	/* disable all I/O interrupts */
 	cregs[14] &= ~0x1f000000UL;	/* disable most machine checks */
 	__ctl_load(cregs, 0, 15);
+	clear_cpu_flag(CIF_NOHZ_DELAY);
 	return 0;
 }
 
@@ -898,42 +916,6 @@ static struct attribute_group cpu_common_attr_group = {
 	.attrs = cpu_common_attrs,
 };
 
-static ssize_t show_idle_count(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
-	unsigned long long idle_count;
-	unsigned int sequence;
-
-	do {
-		sequence = ACCESS_ONCE(idle->sequence);
-		idle_count = ACCESS_ONCE(idle->idle_count);
-		if (ACCESS_ONCE(idle->clock_idle_enter))
-			idle_count++;
-	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
-	return sprintf(buf, "%llu\n", idle_count);
-}
-static DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
-
-static ssize_t show_idle_time(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
-	unsigned long long now, idle_time, idle_enter, idle_exit;
-	unsigned int sequence;
-
-	do {
-		now = get_tod_clock();
-		sequence = ACCESS_ONCE(idle->sequence);
-		idle_time = ACCESS_ONCE(idle->idle_time);
-		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
-		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
-	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
-	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
-	return sprintf(buf, "%llu\n", idle_time >> 12);
-}
-static DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
-
 static struct attribute *cpu_online_attrs[] = {
 	&dev_attr_idle_count.attr,
 	&dev_attr_idle_time_us.attr,
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index a7a7537ce1e7..1c4c5accd220 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -13,14 +13,10 @@
 #include <asm/ipl.h>
 #include <asm/cio.h>
 #include <asm/pci.h>
+#include <asm/sections.h>
 #include "entry.h"
 
 /*
- * References to section boundaries
- */
-extern const void __nosave_begin, __nosave_end;
-
-/*
  * The restore of the saved pages in an hibernation image will set
  * the change and referenced bits in the storage key for each page.
  * Overindication of the referenced bits after an hibernation cycle
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 4cef607f3711..005d665fe4a5 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -92,7 +92,7 @@ void clock_comparator_work(void)
 	struct clock_event_device *cd;
 
 	S390_lowcore.clock_comparator = -1ULL;
-	cd = &__get_cpu_var(comparators);
+	cd = this_cpu_ptr(&comparators);
 	cd->event_handler(cd);
 }
 
@@ -232,6 +232,19 @@ void update_vsyscall(struct timekeeper *tk)
 		vdso_data->wtom_clock_nsec -= nsecps;
 		vdso_data->wtom_clock_sec++;
 	}
+
+	vdso_data->xtime_coarse_sec = tk->xtime_sec;
+	vdso_data->xtime_coarse_nsec =
+		(long)(tk->tkr.xtime_nsec >> tk->tkr.shift);
+	vdso_data->wtom_coarse_sec =
+		vdso_data->xtime_coarse_sec + tk->wall_to_monotonic.tv_sec;
+	vdso_data->wtom_coarse_nsec =
+		vdso_data->xtime_coarse_nsec + tk->wall_to_monotonic.tv_nsec;
+	while (vdso_data->wtom_coarse_nsec >= NSEC_PER_SEC) {
+		vdso_data->wtom_coarse_nsec -= NSEC_PER_SEC;
+		vdso_data->wtom_coarse_sec++;
+	}
+
 	vdso_data->tk_mult = tk->tkr.mult;
 	vdso_data->tk_shift = tk->tkr.shift;
 	smp_wmb();
@@ -360,7 +373,7 @@ EXPORT_SYMBOL(get_sync_clock);
  */
 static void disable_sync_clock(void *dummy)
 {
-	atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word);
+	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
 	/*
 	 * Clear the in-sync bit 2^31. All get_sync_clock calls will
 	 * fail until the sync bit is turned back on. In addition
@@ -377,7 +390,7 @@ static void disable_sync_clock(void *dummy)
  */
 static void enable_sync_clock(void)
 {
-	atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word);
+	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
 	atomic_set_mask(0x80000000, sw_ptr);
 }
 
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 355a16c55702..b93bed76ea94 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -464,15 +464,17 @@ static struct sched_domain_topology_level s390_topology[] = {
 
 static int __init topology_init(void)
 {
-	if (!MACHINE_HAS_TOPOLOGY) {
+	if (MACHINE_HAS_TOPOLOGY)
+		set_topology_timer();
+	else
 		topology_update_polarization_simple();
-		goto out;
-	}
-	set_topology_timer();
-out:
-
-	set_sched_topology(s390_topology);
-
 	return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching);
 }
 device_initcall(topology_init);
+
+static int __init early_topology_init(void)
+{
+	set_sched_topology(s390_topology);
+	return 0;
+}
+early_initcall(early_topology_init);
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index c5762324d9ee..9ff5ecba26ab 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -18,6 +18,8 @@
 #include <linux/ptrace.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/switch_to.h>
 #include "entry.h"
 
 int show_unhandled_signals = 1;
@@ -58,15 +60,10 @@ int is_valid_bugaddr(unsigned long addr)
 	return 1;
 }
 
-static void __kprobes do_trap(struct pt_regs *regs,
-			      int si_signo, int si_code, char *str)
+void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 {
 	siginfo_t info;
 
-	if (notify_die(DIE_TRAP, str, regs, 0,
-		       regs->int_code, si_signo) == NOTIFY_STOP)
-		return;
-
 	if (user_mode(regs)) {
 		info.si_signo = si_signo;
 		info.si_errno = 0;
@@ -90,6 +87,15 @@ static void __kprobes do_trap(struct pt_regs *regs,
         }
 }
 
+static void __kprobes do_trap(struct pt_regs *regs, int si_signo, int si_code,
+			      char *str)
+{
+	if (notify_die(DIE_TRAP, str, regs, 0,
+		       regs->int_code, si_signo) == NOTIFY_STOP)
+		return;
+	do_report_trap(regs, si_signo, si_code, str);
+}
+
 void __kprobes do_per_trap(struct pt_regs *regs)
 {
 	siginfo_t info;
@@ -178,6 +184,7 @@ void __kprobes illegal_op(struct pt_regs *regs)
 	siginfo_t info;
         __u8 opcode[6];
 	__u16 __user *location;
+	int is_uprobe_insn = 0;
 	int signal = 0;
 
 	location = get_trap_ip(regs);
@@ -194,6 +201,10 @@ void __kprobes illegal_op(struct pt_regs *regs)
 				force_sig_info(SIGTRAP, &info, current);
 			} else
 				signal = SIGILL;
+#ifdef CONFIG_UPROBES
+		} else if (*((__u16 *) opcode) == UPROBE_SWBP_INSN) {
+			is_uprobe_insn = 1;
+#endif
 #ifdef CONFIG_MATHEMU
 		} else if (opcode[0] == 0xb3) {
 			if (get_user(*((__u16 *) (opcode+2)), location+1))
@@ -219,11 +230,13 @@ void __kprobes illegal_op(struct pt_regs *regs)
 #endif
 		} else
 			signal = SIGILL;
-	} else {
-		/*
-		 * If we get an illegal op in kernel mode, send it through the
-		 * kprobes notifier. If kprobes doesn't pick it up, SIGILL
-		 */
+	}
+	/*
+	 * We got either an illegal op in kernel mode, or user space trapped
+	 * on a uprobes illegal instruction. See if kprobes or uprobes picks
+	 * it up. If not, SIGILL.
+	 */
+	if (is_uprobe_insn || !user_mode(regs)) {
 		if (notify_die(DIE_BPT, "bpt", regs, 0,
 			       3, SIGTRAP) != NOTIFY_STOP)
 			signal = SIGILL;
@@ -292,6 +305,74 @@ DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN,
 	      "specification exception");
 #endif
 
+#ifdef CONFIG_64BIT
+int alloc_vector_registers(struct task_struct *tsk)
+{
+	__vector128 *vxrs;
+	int i;
+
+	/* Allocate vector register save area. */
+	vxrs = kzalloc(sizeof(__vector128) * __NUM_VXRS,
+		       GFP_KERNEL|__GFP_REPEAT);
+	if (!vxrs)
+		return -ENOMEM;
+	preempt_disable();
+	if (tsk == current)
+		save_fp_regs(tsk->thread.fp_regs.fprs);
+	/* Copy the 16 floating point registers */
+	for (i = 0; i < 16; i++)
+		*(freg_t *) &vxrs[i] = tsk->thread.fp_regs.fprs[i];
+	tsk->thread.vxrs = vxrs;
+	if (tsk == current) {
+		__ctl_set_bit(0, 17);
+		restore_vx_regs(vxrs);
+	}
+	preempt_enable();
+	return 0;
+}
+
+void vector_exception(struct pt_regs *regs)
+{
+	int si_code, vic;
+
+	if (!MACHINE_HAS_VX) {
+		do_trap(regs, SIGILL, ILL_ILLOPN, "illegal operation");
+		return;
+	}
+
+	/* get vector interrupt code from fpc */
+	asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
+	vic = (current->thread.fp_regs.fpc & 0xf00) >> 8;
+	switch (vic) {
+	case 1: /* invalid vector operation */
+		si_code = FPE_FLTINV;
+		break;
+	case 2: /* division by zero */
+		si_code = FPE_FLTDIV;
+		break;
+	case 3: /* overflow */
+		si_code = FPE_FLTOVF;
+		break;
+	case 4: /* underflow */
+		si_code = FPE_FLTUND;
+		break;
+	case 5:	/* inexact */
+		si_code = FPE_FLTRES;
+		break;
+	default: /* unknown cause */
+		si_code = 0;
+	}
+	do_trap(regs, SIGFPE, si_code, "vector exception");
+}
+
+static int __init disable_vector_extension(char *str)
+{
+	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
+	return 1;
+}
+__setup("novx", disable_vector_extension);
+#endif
+
 void data_exception(struct pt_regs *regs)
 {
 	__u16 __user *location;
@@ -357,6 +438,18 @@ void data_exception(struct pt_regs *regs)
                 }
         }
 #endif 
+#ifdef CONFIG_64BIT
+	/* Check for vector register enablement */
+	if (MACHINE_HAS_VX && !current->thread.vxrs &&
+	    (current->thread.fp_regs.fpc & FPC_DXC_MASK) == 0xfe00) {
+		alloc_vector_registers(current);
+		/* Vector data exception is suppressing, rewind psw. */
+		regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16);
+		clear_pt_regs_flag(regs, PIF_PER_TRAP);
+		return;
+	}
+#endif
+
 	if (current->thread.fp_regs.fpc & FPC_DXC_MASK)
 		signal = SIGFPE;
 	else
diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c
new file mode 100644
index 000000000000..956f4f7a591c
--- /dev/null
+++ b/arch/s390/kernel/uprobes.c
@@ -0,0 +1,332 @@
+/*
+ *  User-space Probes (UProbes) for s390
+ *
+ *    Copyright IBM Corp. 2014
+ *    Author(s): Jan Willeke,
+ */
+
+#include <linux/kprobes.h>
+#include <linux/uaccess.h>
+#include <linux/uprobes.h>
+#include <linux/compat.h>
+#include <linux/kdebug.h>
+#include <asm/switch_to.h>
+#include <asm/facility.h>
+#include <asm/dis.h>
+#include "entry.h"
+
+#define	UPROBE_TRAP_NR	UINT_MAX
+
+int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
+			     unsigned long addr)
+{
+	return probe_is_prohibited_opcode(auprobe->insn);
+}
+
+int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	if (psw_bits(regs->psw).eaba == PSW_AMODE_24BIT)
+		return -EINVAL;
+	if (!is_compat_task() && psw_bits(regs->psw).eaba == PSW_AMODE_31BIT)
+		return -EINVAL;
+	clear_pt_regs_flag(regs, PIF_PER_TRAP);
+	auprobe->saved_per = psw_bits(regs->psw).r;
+	auprobe->saved_int_code = regs->int_code;
+	regs->int_code = UPROBE_TRAP_NR;
+	regs->psw.addr = current->utask->xol_vaddr;
+	set_tsk_thread_flag(current, TIF_UPROBE_SINGLESTEP);
+	update_cr_regs(current);
+	return 0;
+}
+
+bool arch_uprobe_xol_was_trapped(struct task_struct *tsk)
+{
+	struct pt_regs *regs = task_pt_regs(tsk);
+
+	if (regs->int_code != UPROBE_TRAP_NR)
+		return true;
+	return false;
+}
+
+int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	int fixup = probe_get_fixup_type(auprobe->insn);
+	struct uprobe_task *utask = current->utask;
+
+	clear_tsk_thread_flag(current, TIF_UPROBE_SINGLESTEP);
+	update_cr_regs(current);
+	psw_bits(regs->psw).r = auprobe->saved_per;
+	regs->int_code = auprobe->saved_int_code;
+
+	if (fixup & FIXUP_PSW_NORMAL)
+		regs->psw.addr += utask->vaddr - utask->xol_vaddr;
+	if (fixup & FIXUP_RETURN_REGISTER) {
+		int reg = (auprobe->insn[0] & 0xf0) >> 4;
+
+		regs->gprs[reg] += utask->vaddr - utask->xol_vaddr;
+	}
+	if (fixup & FIXUP_BRANCH_NOT_TAKEN) {
+		int ilen = insn_length(auprobe->insn[0] >> 8);
+
+		if (regs->psw.addr - utask->xol_vaddr == ilen)
+			regs->psw.addr = utask->vaddr + ilen;
+	}
+	/* If per tracing was active generate trap */
+	if (regs->psw.mask & PSW_MASK_PER)
+		do_per_trap(regs);
+	return 0;
+}
+
+int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val,
+				 void *data)
+{
+	struct die_args *args = data;
+	struct pt_regs *regs = args->regs;
+
+	if (!user_mode(regs))
+		return NOTIFY_DONE;
+	if (regs->int_code & 0x200) /* Trap during transaction */
+		return NOTIFY_DONE;
+	switch (val) {
+	case DIE_BPT:
+		if (uprobe_pre_sstep_notifier(regs))
+			return NOTIFY_STOP;
+		break;
+	case DIE_SSTEP:
+		if (uprobe_post_sstep_notifier(regs))
+			return NOTIFY_STOP;
+	default:
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	clear_thread_flag(TIF_UPROBE_SINGLESTEP);
+	regs->int_code = auprobe->saved_int_code;
+	regs->psw.addr = current->utask->vaddr;
+}
+
+unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline,
+						struct pt_regs *regs)
+{
+	unsigned long orig;
+
+	orig = regs->gprs[14];
+	regs->gprs[14] = trampoline;
+	return orig;
+}
+
+/* Instruction Emulation */
+
+static void adjust_psw_addr(psw_t *psw, unsigned long len)
+{
+	psw->addr = __rewind_psw(*psw, -len);
+}
+
+#define EMU_ILLEGAL_OP		1
+#define EMU_SPECIFICATION	2
+#define EMU_ADDRESSING		3
+
+#define emu_load_ril(ptr, output)			\
+({							\
+	unsigned int mask = sizeof(*(ptr)) - 1;		\
+	__typeof__(*(ptr)) input;			\
+	int __rc = 0;					\
+							\
+	if (!test_facility(34))				\
+		__rc = EMU_ILLEGAL_OP;			\
+	else if ((u64 __force)ptr & mask)		\
+		__rc = EMU_SPECIFICATION;		\
+	else if (get_user(input, ptr))			\
+		__rc = EMU_ADDRESSING;			\
+	else						\
+		*(output) = input;			\
+	__rc;						\
+})
+
+#define emu_store_ril(ptr, input)			\
+({							\
+	unsigned int mask = sizeof(*(ptr)) - 1;		\
+	int __rc = 0;					\
+							\
+	if (!test_facility(34))				\
+		__rc = EMU_ILLEGAL_OP;			\
+	else if ((u64 __force)ptr & mask)		\
+		__rc = EMU_SPECIFICATION;		\
+	else if (put_user(*(input), ptr))		\
+		__rc = EMU_ADDRESSING;			\
+	__rc;						\
+})
+
+#define emu_cmp_ril(regs, ptr, cmp)			\
+({							\
+	unsigned int mask = sizeof(*(ptr)) - 1;		\
+	__typeof__(*(ptr)) input;			\
+	int __rc = 0;					\
+							\
+	if (!test_facility(34))				\
+		__rc = EMU_ILLEGAL_OP;			\
+	else if ((u64 __force)ptr & mask)		\
+		__rc = EMU_SPECIFICATION;		\
+	else if (get_user(input, ptr))			\
+		__rc = EMU_ADDRESSING;			\
+	else if (input > *(cmp))			\
+		psw_bits((regs)->psw).cc = 1;		\
+	else if (input < *(cmp))			\
+		psw_bits((regs)->psw).cc = 2;		\
+	else						\
+		psw_bits((regs)->psw).cc = 0;		\
+	__rc;						\
+})
+
+struct insn_ril {
+	u8 opc0;
+	u8 reg	: 4;
+	u8 opc1 : 4;
+	s32 disp;
+} __packed;
+
+union split_register {
+	u64 u64;
+	u32 u32[2];
+	u16 u16[4];
+	s64 s64;
+	s32 s32[2];
+	s16 s16[4];
+};
+
+/*
+ * pc relative instructions are emulated, since parameters may not be
+ * accessible from the xol area due to range limitations.
+ */
+static void handle_insn_ril(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	union split_register *rx;
+	struct insn_ril *insn;
+	unsigned int ilen;
+	void *uptr;
+	int rc = 0;
+
+	insn = (struct insn_ril *) &auprobe->insn;
+	rx = (union split_register *) &regs->gprs[insn->reg];
+	uptr = (void *)(regs->psw.addr + (insn->disp * 2));
+	ilen = insn_length(insn->opc0);
+
+	switch (insn->opc0) {
+	case 0xc0:
+		switch (insn->opc1) {
+		case 0x00: /* larl */
+			rx->u64 = (unsigned long)uptr;
+			break;
+		}
+		break;
+	case 0xc4:
+		switch (insn->opc1) {
+		case 0x02: /* llhrl */
+			rc = emu_load_ril((u16 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x04: /* lghrl */
+			rc = emu_load_ril((s16 __user *)uptr, &rx->u64);
+			break;
+		case 0x05: /* lhrl */
+			rc = emu_load_ril((s16 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x06: /* llghrl */
+			rc = emu_load_ril((u16 __user *)uptr, &rx->u64);
+			break;
+		case 0x08: /* lgrl */
+			rc = emu_load_ril((u64 __user *)uptr, &rx->u64);
+			break;
+		case 0x0c: /* lgfrl */
+			rc = emu_load_ril((s32 __user *)uptr, &rx->u64);
+			break;
+		case 0x0d: /* lrl */
+			rc = emu_load_ril((u32 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x0e: /* llgfrl */
+			rc = emu_load_ril((u32 __user *)uptr, &rx->u64);
+			break;
+		case 0x07: /* sthrl */
+			rc = emu_store_ril((u16 __user *)uptr, &rx->u16[3]);
+			break;
+		case 0x0b: /* stgrl */
+			rc = emu_store_ril((u64 __user *)uptr, &rx->u64);
+			break;
+		case 0x0f: /* strl */
+			rc = emu_store_ril((u32 __user *)uptr, &rx->u32[1]);
+			break;
+		}
+		break;
+	case 0xc6:
+		switch (insn->opc1) {
+		case 0x02: /* pfdrl */
+			if (!test_facility(34))
+				rc = EMU_ILLEGAL_OP;
+			break;
+		case 0x04: /* cghrl */
+			rc = emu_cmp_ril(regs, (s16 __user *)uptr, &rx->s64);
+			break;
+		case 0x05: /* chrl */
+			rc = emu_cmp_ril(regs, (s16 __user *)uptr, &rx->s32[1]);
+			break;
+		case 0x06: /* clghrl */
+			rc = emu_cmp_ril(regs, (u16 __user *)uptr, &rx->u64);
+			break;
+		case 0x07: /* clhrl */
+			rc = emu_cmp_ril(regs, (u16 __user *)uptr, &rx->u32[1]);
+			break;
+		case 0x08: /* cgrl */
+			rc = emu_cmp_ril(regs, (s64 __user *)uptr, &rx->s64);
+			break;
+		case 0x0a: /* clgrl */
+			rc = emu_cmp_ril(regs, (u64 __user *)uptr, &rx->u64);
+			break;
+		case 0x0c: /* cgfrl */
+			rc = emu_cmp_ril(regs, (s32 __user *)uptr, &rx->s64);
+			break;
+		case 0x0d: /* crl */
+			rc = emu_cmp_ril(regs, (s32 __user *)uptr, &rx->s32[1]);
+			break;
+		case 0x0e: /* clgfrl */
+			rc = emu_cmp_ril(regs, (u32 __user *)uptr, &rx->u64);
+			break;
+		case 0x0f: /* clrl */
+			rc = emu_cmp_ril(regs, (u32 __user *)uptr, &rx->u32[1]);
+			break;
+		}
+		break;
+	}
+	adjust_psw_addr(&regs->psw, ilen);
+	switch (rc) {
+	case EMU_ILLEGAL_OP:
+		regs->int_code = ilen << 16 | 0x0001;
+		do_report_trap(regs, SIGILL, ILL_ILLOPC, NULL);
+		break;
+	case EMU_SPECIFICATION:
+		regs->int_code = ilen << 16 | 0x0006;
+		do_report_trap(regs, SIGILL, ILL_ILLOPC , NULL);
+		break;
+	case EMU_ADDRESSING:
+		regs->int_code = ilen << 16 | 0x0005;
+		do_report_trap(regs, SIGSEGV, SEGV_MAPERR, NULL);
+		break;
+	}
+}
+
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	if ((psw_bits(regs->psw).eaba == PSW_AMODE_24BIT) ||
+	    ((psw_bits(regs->psw).eaba == PSW_AMODE_31BIT) &&
+	     !is_compat_task())) {
+		regs->psw.addr = __rewind_psw(regs->psw, UPROBE_SWBP_INSN_SIZE);
+		do_report_trap(regs, SIGILL, ILL_ILLADR, NULL);
+		return true;
+	}
+	if (probe_is_insn_relative_long(auprobe->insn)) {
+		handle_insn_ril(auprobe, regs);
+		return true;
+	}
+	return false;
+}
diff --git a/arch/s390/kernel/vdso32/clock_getres.S b/arch/s390/kernel/vdso32/clock_getres.S
index 36aaa25d05da..eca3f001f081 100644
--- a/arch/s390/kernel/vdso32/clock_getres.S
+++ b/arch/s390/kernel/vdso32/clock_getres.S
@@ -19,14 +19,20 @@
 	.type  __kernel_clock_getres,@function
 __kernel_clock_getres:
 	.cfi_startproc
+	basr	%r1,0
+	la	%r1,4f-.(%r1)
 	chi	%r2,__CLOCK_REALTIME
 	je	0f
 	chi	%r2,__CLOCK_MONOTONIC
+	je	0f
+	la	%r1,5f-4f(%r1)
+	chi	%r2,__CLOCK_REALTIME_COARSE
+	je	0f
+	chi	%r2,__CLOCK_MONOTONIC_COARSE
 	jne	3f
 0:	ltr	%r3,%r3
 	jz	2f				/* res == NULL */
-	basr	%r1,0
-1:	l	%r0,4f-1b(%r1)
+1:	l	%r0,0(%r1)
 	xc	0(4,%r3),0(%r3)			/* set tp->tv_sec to zero */
 	st	%r0,4(%r3)			/* store tp->tv_usec */
 2:	lhi	%r2,0
@@ -35,5 +41,6 @@ __kernel_clock_getres:
 	svc	0
 	br	%r14
 4:	.long	__CLOCK_REALTIME_RES
+5:	.long	__CLOCK_COARSE_RES
 	.cfi_endproc
 	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S
index 7cf18f8d4cb4..48c2206a3956 100644
--- a/arch/s390/kernel/vdso32/clock_gettime.S
+++ b/arch/s390/kernel/vdso32/clock_gettime.S
@@ -21,8 +21,12 @@ __kernel_clock_gettime:
 	.cfi_startproc
 	basr	%r5,0
 0:	al	%r5,21f-0b(%r5)			/* get &_vdso_data */
+	chi	%r2,__CLOCK_REALTIME_COARSE
+	je	10f
 	chi	%r2,__CLOCK_REALTIME
 	je	11f
+	chi	%r2,__CLOCK_MONOTONIC_COARSE
+	je	9f
 	chi	%r2,__CLOCK_MONOTONIC
 	jne	19f
 
@@ -30,8 +34,8 @@ __kernel_clock_gettime:
 1:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
 	tml	%r4,0x0001			/* pending update ? loop */
 	jnz	1b
-	stck	24(%r15)			/* Store TOD clock */
-	lm	%r0,%r1,24(%r15)
+	stcke	24(%r15)			/* Store TOD clock */
+	lm	%r0,%r1,25(%r15)
 	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,2f
@@ -68,12 +72,32 @@ __kernel_clock_gettime:
 	lhi	%r2,0
 	br	%r14
 
+	/* CLOCK_MONOTONIC_COARSE */
+9:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	9b
+	l	%r2,__VDSO_WTOM_CRS_SEC+4(%r5)
+	l	%r1,__VDSO_WTOM_CRS_NSEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	9b
+	j	8b
+
+	/* CLOCK_REALTIME_COARSE */
+10:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	10b
+	l	%r2,__VDSO_XTIME_CRS_SEC+4(%r5)
+	l	%r1,__VDSO_XTIME_CRS_NSEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	10b
+	j	17f
+
 	/* CLOCK_REALTIME */
 11:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
 	tml	%r4,0x0001			/* pending update ? loop */
 	jnz	11b
-	stck	24(%r15)			/* Store TOD clock */
-	lm	%r0,%r1,24(%r15)
+	stcke	24(%r15)			/* Store TOD clock */
+	lm	%r0,%r1,25(%r15)
 	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,12f
diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S
index fd621a950f7c..60def5f562db 100644
--- a/arch/s390/kernel/vdso32/gettimeofday.S
+++ b/arch/s390/kernel/vdso32/gettimeofday.S
@@ -29,8 +29,8 @@ __kernel_gettimeofday:
 	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
 	tml	%r4,0x0001			/* pending update ? loop */
 	jnz	1b
-	stck	24(%r15)			/* Store TOD clock */
-	lm	%r0,%r1,24(%r15)
+	stcke	24(%r15)			/* Store TOD clock */
+	lm	%r0,%r1,25(%r15)
 	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
 	brc	3,3f
diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S
index 34deba7c7ed1..c8513deb8c66 100644
--- a/arch/s390/kernel/vdso64/clock_getres.S
+++ b/arch/s390/kernel/vdso64/clock_getres.S
@@ -19,6 +19,12 @@
 	.type  __kernel_clock_getres,@function
 __kernel_clock_getres:
 	.cfi_startproc
+	larl	%r1,4f
+	cghi	%r2,__CLOCK_REALTIME_COARSE
+	je	0f
+	cghi	%r2,__CLOCK_MONOTONIC_COARSE
+	je	0f
+	larl	%r1,3f
 	cghi	%r2,__CLOCK_REALTIME
 	je	0f
 	cghi	%r2,__CLOCK_MONOTONIC
@@ -32,7 +38,6 @@ __kernel_clock_getres:
 	jz	2f
 0:	ltgr	%r3,%r3
 	jz	1f				/* res == NULL */
-	larl	%r1,3f
 	lg	%r0,0(%r1)
 	xc	0(8,%r3),0(%r3)			/* set tp->tv_sec to zero */
 	stg	%r0,8(%r3)			/* store tp->tv_usec */
@@ -42,5 +47,6 @@ __kernel_clock_getres:
 	svc	0
 	br	%r14
 3:	.quad	__CLOCK_REALTIME_RES
+4:	.quad	__CLOCK_COARSE_RES
 	.cfi_endproc
 	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S
index 3f34e09db5f4..9d9761f8e110 100644
--- a/arch/s390/kernel/vdso64/clock_gettime.S
+++ b/arch/s390/kernel/vdso64/clock_gettime.S
@@ -20,12 +20,16 @@
 __kernel_clock_gettime:
 	.cfi_startproc
 	larl	%r5,_vdso_data
+	cghi	%r2,__CLOCK_REALTIME_COARSE
+	je	4f
 	cghi	%r2,__CLOCK_REALTIME
 	je	5f
 	cghi	%r2,__CLOCK_THREAD_CPUTIME_ID
 	je	9f
 	cghi	%r2,-2		/* Per-thread CPUCLOCK with PID=0, VIRT=1 */
 	je	9f
+	cghi	%r2,__CLOCK_MONOTONIC_COARSE
+	je	3f
 	cghi	%r2,__CLOCK_MONOTONIC
 	jne	12f
 
@@ -33,10 +37,10 @@ __kernel_clock_gettime:
 0:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
 	tmll	%r4,0x0001			/* pending update ? loop */
 	jnz	0b
-	stck	48(%r15)			/* Store TOD clock */
+	stcke	48(%r15)			/* Store TOD clock */
 	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
 	lg	%r0,__VDSO_WTOM_SEC(%r5)
-	lg	%r1,48(%r15)
+	lg	%r1,49(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
 	alg	%r1,__VDSO_WTOM_NSEC(%r5)
@@ -54,13 +58,33 @@ __kernel_clock_gettime:
 	lghi	%r2,0
 	br	%r14
 
+	/* CLOCK_MONOTONIC_COARSE */
+3:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	3b
+	lg	%r0,__VDSO_WTOM_CRS_SEC(%r5)
+	lg	%r1,__VDSO_WTOM_CRS_NSEC(%r5)
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	3b
+	j	2b
+
+	/* CLOCK_REALTIME_COARSE */
+4:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	4b
+	lg	%r0,__VDSO_XTIME_CRS_SEC(%r5)
+	lg	%r1,__VDSO_XTIME_CRS_NSEC(%r5)
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	4b
+	j	7f
+
 	/* CLOCK_REALTIME */
 5:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
 	tmll	%r4,0x0001			/* pending update ? loop */
 	jnz	5b
-	stck	48(%r15)			/* Store TOD clock */
+	stcke	48(%r15)			/* Store TOD clock */
 	lgf	%r2,__VDSO_TK_SHIFT(%r5)	/* Timekeeper shift */
-	lg	%r1,48(%r15)
+	lg	%r1,49(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S
index d0860d1d0ccc..7a344995a97f 100644
--- a/arch/s390/kernel/vdso64/gettimeofday.S
+++ b/arch/s390/kernel/vdso64/gettimeofday.S
@@ -28,8 +28,8 @@ __kernel_gettimeofday:
 	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
 	tmll	%r4,0x0001			/* pending update ? loop */
 	jnz	0b
-	stck	48(%r15)			/* Store TOD clock */
-	lg	%r1,48(%r15)
+	stcke	48(%r15)			/* Store TOD clock */
+	lg	%r1,49(%r15)
 	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
 	msgf	%r1,__VDSO_TK_MULT(%r5)		/*  * tk->mult */
 	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + tk->xtime_nsec */
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 8c34363d6f1e..416f2a323ba5 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -6,27 +6,18 @@
  */
 
 #include <linux/kernel_stat.h>
-#include <linux/notifier.h>
-#include <linux/kprobes.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/timex.h>
 #include <linux/types.h>
 #include <linux/time.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
 
-#include <asm/irq_regs.h>
 #include <asm/cputime.h>
 #include <asm/vtimer.h>
 #include <asm/vtime.h>
-#include <asm/irq.h>
-#include "entry.h"
 
 static void virt_timer_expire(void);
 
-DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
-
 static LIST_HEAD(virt_timer_list);
 static DEFINE_SPINLOCK(virt_timer_lock);
 static atomic64_t virt_timer_current;
@@ -152,49 +143,6 @@ void vtime_account_system(struct task_struct *tsk)
 __attribute__((alias("vtime_account_irq_enter")));
 EXPORT_SYMBOL_GPL(vtime_account_system);
 
-void __kprobes vtime_stop_cpu(void)
-{
-	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
-	unsigned long long idle_time;
-	unsigned long psw_mask;
-
-	trace_hardirqs_on();
-
-	/* Wait for external, I/O or machine check interrupt. */
-	psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT | PSW_MASK_DAT |
-		PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
-	idle->nohz_delay = 0;
-
-	/* Call the assembler magic in entry.S */
-	psw_idle(idle, psw_mask);
-
-	/* Account time spent with enabled wait psw loaded as idle time. */
-	idle->sequence++;
-	smp_wmb();
-	idle_time = idle->clock_idle_exit - idle->clock_idle_enter;
-	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
-	idle->idle_time += idle_time;
-	idle->idle_count++;
-	account_idle_time(idle_time);
-	smp_wmb();
-	idle->sequence++;
-}
-
-cputime64_t s390_get_idle_time(int cpu)
-{
-	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
-	unsigned long long now, idle_enter, idle_exit;
-	unsigned int sequence;
-
-	do {
-		now = get_tod_clock();
-		sequence = ACCESS_ONCE(idle->sequence);
-		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
-		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
-	} while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
-	return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
-}
-
 /*
  * Sorted add to a list. List is linear searched until first bigger
  * element is found.
@@ -372,31 +320,8 @@ EXPORT_SYMBOL(del_virt_timer);
 /*
  * Start the virtual CPU timer on the current CPU.
  */
-void init_cpu_vtimer(void)
+void vtime_init(void)
 {
 	/* set initial cpu timer */
 	set_vtimer(VTIMER_MAX_SLICE);
 }
-
-static int s390_nohz_notify(struct notifier_block *self, unsigned long action,
-			    void *hcpu)
-{
-	struct s390_idle_data *idle;
-	long cpu = (long) hcpu;
-
-	idle = &per_cpu(s390_idle, cpu);
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_DYING:
-		idle->nohz_delay = 0;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-void __init vtime_init(void)
-{
-	/* Enable cpu timer interrupts on the boot cpu. */
-	init_cpu_vtimer();
-	cpu_notifier(s390_nohz_notify, 0);
-}
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index c6d752e8bf28..a01df233856f 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -6,3 +6,5 @@ lib-y += delay.o string.o uaccess.o find.o
 obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o mem32.o
 obj-$(CONFIG_64BIT) += mem64.o
 lib-$(CONFIG_SMP) += spinlock.o
+lib-$(CONFIG_KPROBES) += probes.o
+lib-$(CONFIG_UPROBES) += probes.o
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index a9f3d0042d58..16dc42d83f93 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -43,7 +43,7 @@ static void __udelay_disabled(unsigned long long usecs)
 	lockdep_off();
 	do {
 		set_clock_comparator(end);
-		vtime_stop_cpu();
+		enabled_wait();
 	} while (get_tod_clock_fast() < end);
 	lockdep_on();
 	__ctl_load(cr0, 0, 0);
@@ -62,7 +62,7 @@ static void __udelay_enabled(unsigned long long usecs)
 			clock_saved = local_tick_disable();
 			set_clock_comparator(end);
 		}
-		vtime_stop_cpu();
+		enabled_wait();
 		if (clock_saved)
 			local_tick_enable(clock_saved);
 	} while (get_tod_clock_fast() < end);
diff --git a/arch/s390/lib/probes.c b/arch/s390/lib/probes.c
new file mode 100644
index 000000000000..c5d64a099719
--- /dev/null
+++ b/arch/s390/lib/probes.c
@@ -0,0 +1,159 @@
+/*
+ *    Common helper functions for kprobes and uprobes
+ *
+ *    Copyright IBM Corp. 2014
+ */
+
+#include <linux/kprobes.h>
+#include <asm/dis.h>
+
+int probe_is_prohibited_opcode(u16 *insn)
+{
+	if (!is_known_insn((unsigned char *)insn))
+		return -EINVAL;
+	switch (insn[0] >> 8) {
+	case 0x0c:	/* bassm */
+	case 0x0b:	/* bsm	 */
+	case 0x83:	/* diag  */
+	case 0x44:	/* ex	 */
+	case 0xac:	/* stnsm */
+	case 0xad:	/* stosm */
+		return -EINVAL;
+	case 0xc6:
+		switch (insn[0] & 0x0f) {
+		case 0x00: /* exrl   */
+			return -EINVAL;
+		}
+	}
+	switch (insn[0]) {
+	case 0x0101:	/* pr	 */
+	case 0xb25a:	/* bsa	 */
+	case 0xb240:	/* bakr  */
+	case 0xb258:	/* bsg	 */
+	case 0xb218:	/* pc	 */
+	case 0xb228:	/* pt	 */
+	case 0xb98d:	/* epsw	 */
+	case 0xe560:	/* tbegin */
+	case 0xe561:	/* tbeginc */
+	case 0xb2f8:	/* tend	 */
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int probe_get_fixup_type(u16 *insn)
+{
+	/* default fixup method */
+	int fixup = FIXUP_PSW_NORMAL;
+
+	switch (insn[0] >> 8) {
+	case 0x05:	/* balr	*/
+	case 0x0d:	/* basr */
+		fixup = FIXUP_RETURN_REGISTER;
+		/* if r2 = 0, no branch will be taken */
+		if ((insn[0] & 0x0f) == 0)
+			fixup |= FIXUP_BRANCH_NOT_TAKEN;
+		break;
+	case 0x06:	/* bctr	*/
+	case 0x07:	/* bcr	*/
+		fixup = FIXUP_BRANCH_NOT_TAKEN;
+		break;
+	case 0x45:	/* bal	*/
+	case 0x4d:	/* bas	*/
+		fixup = FIXUP_RETURN_REGISTER;
+		break;
+	case 0x47:	/* bc	*/
+	case 0x46:	/* bct	*/
+	case 0x86:	/* bxh	*/
+	case 0x87:	/* bxle	*/
+		fixup = FIXUP_BRANCH_NOT_TAKEN;
+		break;
+	case 0x82:	/* lpsw	*/
+		fixup = FIXUP_NOT_REQUIRED;
+		break;
+	case 0xb2:	/* lpswe */
+		if ((insn[0] & 0xff) == 0xb2)
+			fixup = FIXUP_NOT_REQUIRED;
+		break;
+	case 0xa7:	/* bras	*/
+		if ((insn[0] & 0x0f) == 0x05)
+			fixup |= FIXUP_RETURN_REGISTER;
+		break;
+	case 0xc0:
+		if ((insn[0] & 0x0f) == 0x05)	/* brasl */
+			fixup |= FIXUP_RETURN_REGISTER;
+		break;
+	case 0xeb:
+		switch (insn[2] & 0xff) {
+		case 0x44: /* bxhg  */
+		case 0x45: /* bxleg */
+			fixup = FIXUP_BRANCH_NOT_TAKEN;
+			break;
+		}
+		break;
+	case 0xe3:	/* bctg	*/
+		if ((insn[2] & 0xff) == 0x46)
+			fixup = FIXUP_BRANCH_NOT_TAKEN;
+		break;
+	case 0xec:
+		switch (insn[2] & 0xff) {
+		case 0xe5: /* clgrb */
+		case 0xe6: /* cgrb  */
+		case 0xf6: /* crb   */
+		case 0xf7: /* clrb  */
+		case 0xfc: /* cgib  */
+		case 0xfd: /* cglib */
+		case 0xfe: /* cib   */
+		case 0xff: /* clib  */
+			fixup = FIXUP_BRANCH_NOT_TAKEN;
+			break;
+		}
+		break;
+	}
+	return fixup;
+}
+
+int probe_is_insn_relative_long(u16 *insn)
+{
+	/* Check if we have a RIL-b or RIL-c format instruction which
+	 * we need to modify in order to avoid instruction emulation. */
+	switch (insn[0] >> 8) {
+	case 0xc0:
+		if ((insn[0] & 0x0f) == 0x00) /* larl */
+			return true;
+		break;
+	case 0xc4:
+		switch (insn[0] & 0x0f) {
+		case 0x02: /* llhrl  */
+		case 0x04: /* lghrl  */
+		case 0x05: /* lhrl   */
+		case 0x06: /* llghrl */
+		case 0x07: /* sthrl  */
+		case 0x08: /* lgrl   */
+		case 0x0b: /* stgrl  */
+		case 0x0c: /* lgfrl  */
+		case 0x0d: /* lrl    */
+		case 0x0e: /* llgfrl */
+		case 0x0f: /* strl   */
+			return true;
+		}
+		break;
+	case 0xc6:
+		switch (insn[0] & 0x0f) {
+		case 0x02: /* pfdrl  */
+		case 0x04: /* cghrl  */
+		case 0x05: /* chrl   */
+		case 0x06: /* clghrl */
+		case 0x07: /* clhrl  */
+		case 0x08: /* cgrl   */
+		case 0x0a: /* clgrl  */
+		case 0x0c: /* cgfrl  */
+		case 0x0d: /* crl    */
+		case 0x0e: /* clgfrl */
+		case 0x0f: /* clrl   */
+			return true;
+		}
+		break;
+	}
+	return false;
+}
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index 5b0e445bc3f3..034a35a3e9c1 100644
--- a/arch/s390/lib/spinlock.c
+++ b/arch/s390/lib/spinlock.c
@@ -98,17 +98,6 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 }
 EXPORT_SYMBOL(arch_spin_lock_wait_flags);
 
-void arch_spin_relax(arch_spinlock_t *lp)
-{
-	unsigned int cpu = lp->lock;
-	if (cpu != 0) {
-		if (MACHINE_IS_VM || MACHINE_IS_KVM ||
-		    !smp_vcpu_scheduled(~cpu))
-			smp_yield_cpu(~cpu);
-	}
-}
-EXPORT_SYMBOL(arch_spin_relax);
-
 int arch_spin_trylock_retry(arch_spinlock_t *lp)
 {
 	int count;
@@ -122,15 +111,21 @@ EXPORT_SYMBOL(arch_spin_trylock_retry);
 
 void _raw_read_lock_wait(arch_rwlock_t *rw)
 {
-	unsigned int old;
+	unsigned int owner, old;
 	int count = spin_retry;
 
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+	__RAW_LOCK(&rw->lock, -1, __RAW_OP_ADD);
+#endif
+	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			smp_yield();
+			if (owner && !smp_vcpu_scheduled(~owner))
+				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
 		old = ACCESS_ONCE(rw->lock);
+		owner = ACCESS_ONCE(rw->owner);
 		if ((int) old < 0)
 			continue;
 		if (_raw_compare_and_swap(&rw->lock, old, old + 1))
@@ -139,28 +134,6 @@ void _raw_read_lock_wait(arch_rwlock_t *rw)
 }
 EXPORT_SYMBOL(_raw_read_lock_wait);
 
-void _raw_read_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags)
-{
-	unsigned int old;
-	int count = spin_retry;
-
-	local_irq_restore(flags);
-	while (1) {
-		if (count-- <= 0) {
-			smp_yield();
-			count = spin_retry;
-		}
-		old = ACCESS_ONCE(rw->lock);
-		if ((int) old < 0)
-			continue;
-		local_irq_disable();
-		if (_raw_compare_and_swap(&rw->lock, old, old + 1))
-			return;
-		local_irq_restore(flags);
-	}
-}
-EXPORT_SYMBOL(_raw_read_lock_wait_flags);
-
 int _raw_read_trylock_retry(arch_rwlock_t *rw)
 {
 	unsigned int old;
@@ -177,46 +150,62 @@ int _raw_read_trylock_retry(arch_rwlock_t *rw)
 }
 EXPORT_SYMBOL(_raw_read_trylock_retry);
 
-void _raw_write_lock_wait(arch_rwlock_t *rw)
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+
+void _raw_write_lock_wait(arch_rwlock_t *rw, unsigned int prev)
 {
-	unsigned int old;
+	unsigned int owner, old;
 	int count = spin_retry;
 
+	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			smp_yield();
+			if (owner && !smp_vcpu_scheduled(~owner))
+				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
 		old = ACCESS_ONCE(rw->lock);
-		if (old)
-			continue;
-		if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000))
-			return;
+		owner = ACCESS_ONCE(rw->owner);
+		smp_rmb();
+		if ((int) old >= 0) {
+			prev = __RAW_LOCK(&rw->lock, 0x80000000, __RAW_OP_OR);
+			old = prev;
+		}
+		if ((old & 0x7fffffff) == 0 && (int) prev >= 0)
+			break;
 	}
 }
 EXPORT_SYMBOL(_raw_write_lock_wait);
 
-void _raw_write_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags)
+#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
+
+void _raw_write_lock_wait(arch_rwlock_t *rw)
 {
-	unsigned int old;
+	unsigned int owner, old, prev;
 	int count = spin_retry;
 
-	local_irq_restore(flags);
+	prev = 0x80000000;
+	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			smp_yield();
+			if (owner && !smp_vcpu_scheduled(~owner))
+				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
 		old = ACCESS_ONCE(rw->lock);
-		if (old)
-			continue;
-		local_irq_disable();
-		if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000))
-			return;
-		local_irq_restore(flags);
+		owner = ACCESS_ONCE(rw->owner);
+		if ((int) old >= 0 &&
+		    _raw_compare_and_swap(&rw->lock, old, old | 0x80000000))
+			prev = old;
+		else
+			smp_rmb();
+		if ((old & 0x7fffffff) == 0 && (int) prev >= 0)
+			break;
 	}
 }
-EXPORT_SYMBOL(_raw_write_lock_wait_flags);
+EXPORT_SYMBOL(_raw_write_lock_wait);
+
+#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
 
 int _raw_write_trylock_retry(arch_rwlock_t *rw)
 {
@@ -233,3 +222,13 @@ int _raw_write_trylock_retry(arch_rwlock_t *rw)
 	return 0;
 }
 EXPORT_SYMBOL(_raw_write_trylock_retry);
+
+void arch_lock_relax(unsigned int cpu)
+{
+	if (!cpu)
+		return;
+	if (MACHINE_IS_LPAR && smp_vcpu_scheduled(~cpu))
+		return;
+	smp_yield_cpu(~cpu);
+}
+EXPORT_SYMBOL(arch_lock_relax);
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index 46d517c3c763..d46cadeda204 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -54,7 +54,6 @@ static void print_prot(struct seq_file *m, unsigned int pr, int level)
 		return;
 	}
 	seq_printf(m, "%s", pr & _PAGE_PROTECT ? "RO " : "RW ");
-	seq_printf(m, "%s", pr & _PAGE_CO ? "CO " : "   ");
 	seq_putc(m, '\n');
 }
 
@@ -129,7 +128,7 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st,
 }
 
 #ifdef CONFIG_64BIT
-#define _PMD_PROT_MASK (_SEGMENT_ENTRY_PROTECT | _SEGMENT_ENTRY_CO)
+#define _PMD_PROT_MASK _SEGMENT_ENTRY_PROTECT
 #else
 #define _PMD_PROT_MASK 0
 #endif
@@ -157,7 +156,7 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st,
 }
 
 #ifdef CONFIG_64BIT
-#define _PUD_PROT_MASK (_REGION3_ENTRY_RO | _REGION3_ENTRY_CO)
+#define _PUD_PROT_MASK _REGION3_ENTRY_RO
 #else
 #define _PUD_PROT_MASK 0
 #endif
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 389bc17934b7..3c80d2e38f03 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -88,7 +88,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN;
 		pmd_val(pmd) |= pte_page(pte)[1].index;
 	} else
-		pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO;
+		pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE;
 	*(pmd_t *) ptep = pmd;
 }
 
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index 8400f494623f..3fef3b299665 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -6,6 +6,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <asm/cacheflush.h>
+#include <asm/facility.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
 
@@ -103,27 +104,50 @@ int set_memory_x(unsigned long addr, int numpages)
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
+
+static void ipte_range(pte_t *pte, unsigned long address, int nr)
+{
+	int i;
+
+	if (test_facility(13) && IS_ENABLED(CONFIG_64BIT)) {
+		__ptep_ipte_range(address, nr - 1, pte);
+		return;
+	}
+	for (i = 0; i < nr; i++) {
+		__ptep_ipte(address, pte);
+		address += PAGE_SIZE;
+		pte++;
+	}
+}
+
 void kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	unsigned long address;
+	int nr, i, j;
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
-	int i;
 
-	for (i = 0; i < numpages; i++) {
+	for (i = 0; i < numpages;) {
 		address = page_to_phys(page + i);
 		pgd = pgd_offset_k(address);
 		pud = pud_offset(pgd, address);
 		pmd = pmd_offset(pud, address);
 		pte = pte_offset_kernel(pmd, address);
-		if (!enable) {
-			__ptep_ipte(address, pte);
-			pte_val(*pte) = _PAGE_INVALID;
-			continue;
+		nr = (unsigned long)pte >> ilog2(sizeof(long));
+		nr = PTRS_PER_PTE - (nr & (PTRS_PER_PTE - 1));
+		nr = min(numpages - i, nr);
+		if (enable) {
+			for (j = 0; j < nr; j++) {
+				pte_val(*pte) = __pa(address);
+				address += PAGE_SIZE;
+				pte++;
+			}
+		} else {
+			ipte_range(pte, address, nr);
 		}
-		pte_val(*pte) = __pa(address);
+		i += nr;
 	}
 }
 
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index fdbd7888cb07..b1593c2f751a 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -236,8 +236,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 				if (!new_page)
 					goto out;
 				pmd_val(*pm_dir) = __pa(new_page) |
-					_SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE |
-					_SEGMENT_ENTRY_CO;
+					_SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE;
 				address = (address + PMD_SIZE) & PMD_MASK;
 				continue;
 			}
@@ -253,9 +252,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 
 		pt_dir = pte_offset_kernel(pm_dir, address);
 		if (pte_none(*pt_dir)) {
-			unsigned long new_page;
+			void *new_page;
 
-			new_page =__pa(vmem_alloc_pages(0));
+			new_page = vmemmap_alloc_block(PAGE_SIZE, node);
 			if (!new_page)
 				goto out;
 			pte_val(*pt_dir) =
@@ -263,7 +262,6 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 		}
 		address += PAGE_SIZE;
 	}
-	memset((void *)start, 0, end - start);
 	ret = 0;
 out:
 	return ret;
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index e53c6f268807..ff9b4eb34589 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -178,7 +178,7 @@ static int smp_ctl_qsi(int cpu)
 static void hws_ext_handler(struct ext_code ext_code,
 			    unsigned int param32, unsigned long param64)
 {
-	struct hws_cpu_buffer *cb = &__get_cpu_var(sampler_cpu_buffer);
+	struct hws_cpu_buffer *cb = this_cpu_ptr(&sampler_cpu_buffer);
 
 	if (!(param32 & CPU_MF_INT_SF_MASK))
 		return;
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index d26c48fc93c9..46461c19f284 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -6,9 +6,11 @@ generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += hash.h
+generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
 generic-y += scatterlist.h
+generic-y += sections.h
 generic-y += trace_clock.h
 generic-y += xor.h
 generic-y += serial.h
diff --git a/arch/score/include/asm/sections.h b/arch/score/include/asm/sections.h
deleted file mode 100644
index 9441d23af005..000000000000
--- a/arch/score/include/asm/sections.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_SCORE_SECTIONS_H
-#define _ASM_SCORE_SECTIONS_H
-
-#include <asm-generic/sections.h>
-
-#endif /* _ASM_SCORE_SECTIONS_H */
diff --git a/arch/sh/boards/mach-x3proto/gpio.c b/arch/sh/boards/mach-x3proto/gpio.c
index 3ea65e9b56e8..f035a7ac6456 100644
--- a/arch/sh/boards/mach-x3proto/gpio.c
+++ b/arch/sh/boards/mach-x3proto/gpio.c
@@ -128,10 +128,8 @@ int __init x3proto_gpio_setup(void)
 	return 0;
 
 err_irq:
-	ret = gpiochip_remove(&x3proto_gpio_chip);
-	if (unlikely(ret))
-		pr_err("Failed deregistering GPIO\n");
-
+	gpiochip_remove(&x3proto_gpio_chip);
+	ret = 0;
 err_gpio:
 	synchronize_irq(ilsel);
 
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index c19e47dacb31..5a6c9acff0d2 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -12,6 +12,7 @@ generic-y += hash.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
diff --git a/arch/sh/include/asm/atomic-grb.h b/arch/sh/include/asm/atomic-grb.h
index a273c88578fc..97a5fda83450 100644
--- a/arch/sh/include/asm/atomic-grb.h
+++ b/arch/sh/include/asm/atomic-grb.h
@@ -1,85 +1,56 @@
 #ifndef __ASM_SH_ATOMIC_GRB_H
 #define __ASM_SH_ATOMIC_GRB_H
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	int tmp;
-
-	__asm__ __volatile__ (
-		"   .align 2              \n\t"
-		"   mova    1f,   r0      \n\t" /* r0 = end point */
-		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
-		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */
-		"   mov.l  @%1,   %0      \n\t" /* load  old value */
-		"   add     %2,   %0      \n\t" /* add */
-		"   mov.l   %0,   @%1     \n\t" /* store new value */
-		"1: mov     r1,   r15     \n\t" /* LOGOUT */
-		: "=&r" (tmp),
-		  "+r"  (v)
-		: "r"   (i)
-		: "memory" , "r0", "r1");
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	int tmp;
-
-	__asm__ __volatile__ (
-		"   .align 2              \n\t"
-		"   mova    1f,   r0      \n\t" /* r0 = end point */
-		"   mov     r15,  r1      \n\t" /* r1 = saved sp */
-		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */
-		"   mov.l  @%1,   %0      \n\t" /* load  old value */
-		"   sub     %2,   %0      \n\t" /* sub */
-		"   mov.l   %0,   @%1     \n\t" /* store new value */
-		"1: mov     r1,   r15     \n\t" /* LOGOUT */
-		: "=&r" (tmp),
-		  "+r"  (v)
-		: "r"   (i)
-		: "memory" , "r0", "r1");
-}
-
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	int tmp;
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	int tmp;							\
+									\
+	__asm__ __volatile__ (						\
+		"   .align 2              \n\t"				\
+		"   mova    1f,   r0      \n\t" /* r0 = end point */	\
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */	\
+		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */	\
+		"   mov.l  @%1,   %0      \n\t" /* load  old value */	\
+		" " #op "   %2,   %0      \n\t" /* $op */		\
+		"   mov.l   %0,   @%1     \n\t" /* store new value */	\
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */		\
+		: "=&r" (tmp),						\
+		  "+r"  (v)						\
+		: "r"   (i)						\
+		: "memory" , "r0", "r1");				\
+}									\
 
-	__asm__ __volatile__ (
-		"   .align 2              \n\t"
-		"   mova    1f,   r0      \n\t" /* r0 = end point */
-		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
-		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */
-		"   mov.l  @%1,   %0      \n\t" /* load  old value */
-		"   add     %2,   %0      \n\t" /* add */
-		"   mov.l   %0,   @%1     \n\t" /* store new value */
-		"1: mov     r1,   r15     \n\t" /* LOGOUT */
-		: "=&r" (tmp),
-		  "+r"  (v)
-		: "r"   (i)
-		: "memory" , "r0", "r1");
-
-	return tmp;
+#define ATOMIC_OP_RETURN(op)						\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	int tmp;							\
+									\
+	__asm__ __volatile__ (						\
+		"   .align 2              \n\t"				\
+		"   mova    1f,   r0      \n\t" /* r0 = end point */	\
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */	\
+		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */	\
+		"   mov.l  @%1,   %0      \n\t" /* load  old value */	\
+		" " #op "   %2,   %0      \n\t" /* $op */		\
+		"   mov.l   %0,   @%1     \n\t" /* store new value */	\
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */		\
+		: "=&r" (tmp),						\
+		  "+r"  (v)						\
+		: "r"   (i)						\
+		: "memory" , "r0", "r1");				\
+									\
+	return tmp;							\
 }
 
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	int tmp;
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
 
-	__asm__ __volatile__ (
-		"   .align 2              \n\t"
-		"   mova    1f,   r0      \n\t" /* r0 = end point */
-		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
-		"   mov    #-6,   r15     \n\t" /* LOGIN: r15 = size */
-		"   mov.l  @%1,   %0      \n\t" /* load  old value */
-		"   sub     %2,   %0      \n\t" /* sub */
-		"   mov.l   %0,   @%1     \n\t" /* store new value */
-		"1: mov     r1,   r15     \n\t" /* LOGOUT */
-		: "=&r" (tmp),
-		  "+r"  (v)
-		: "r"   (i)
-		: "memory", "r0", "r1");
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
 
-	return tmp;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
 {
diff --git a/arch/sh/include/asm/atomic-irq.h b/arch/sh/include/asm/atomic-irq.h
index 9f7c56609e53..61d107523f06 100644
--- a/arch/sh/include/asm/atomic-irq.h
+++ b/arch/sh/include/asm/atomic-irq.h
@@ -8,49 +8,39 @@
  * forward to code at the end of this object's .text section, then
  * branch back to restart the operation.
  */
-static inline void atomic_add(int i, atomic_t *v)
-{
-	unsigned long flags;
-
-	raw_local_irq_save(flags);
-	v->counter += i;
-	raw_local_irq_restore(flags);
-}
 
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	unsigned long flags;
-
-	raw_local_irq_save(flags);
-	v->counter -= i;
-	raw_local_irq_restore(flags);
+#define ATOMIC_OP(op, c_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	raw_local_irq_save(flags);					\
+	v->counter c_op i;						\
+	raw_local_irq_restore(flags);					\
 }
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long temp, flags;
-
-	raw_local_irq_save(flags);
-	temp = v->counter;
-	temp += i;
-	v->counter = temp;
-	raw_local_irq_restore(flags);
-
-	return temp;
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long temp, flags;					\
+									\
+	raw_local_irq_save(flags);					\
+	temp = v->counter;						\
+	temp c_op i;							\
+	v->counter = temp;						\
+	raw_local_irq_restore(flags);					\
+									\
+	return temp;							\
 }
 
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long temp, flags;
+#define ATOMIC_OPS(op, c_op) ATOMIC_OP(op, c_op) ATOMIC_OP_RETURN(op, c_op)
 
-	raw_local_irq_save(flags);
-	temp = v->counter;
-	temp -= i;
-	v->counter = temp;
-	raw_local_irq_restore(flags);
+ATOMIC_OPS(add, +=)
+ATOMIC_OPS(sub, -=)
 
-	return temp;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
 {
diff --git a/arch/sh/include/asm/atomic-llsc.h b/arch/sh/include/asm/atomic-llsc.h
index 4b00b78e3f4f..8575dccb9ef7 100644
--- a/arch/sh/include/asm/atomic-llsc.h
+++ b/arch/sh/include/asm/atomic-llsc.h
@@ -2,39 +2,6 @@
 #define __ASM_SH_ATOMIC_LLSC_H
 
 /*
- * To get proper branch prediction for the main line, we must branch
- * forward to code at the end of this object's .text section, then
- * branch back to restart the operation.
- */
-static inline void atomic_add(int i, atomic_t *v)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_add	\n"
-"	add	%1, %0				\n"
-"	movco.l	%0, @%2				\n"
-"	bf	1b				\n"
-	: "=&z" (tmp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_sub	\n"
-"	sub	%1, %0				\n"
-"	movco.l	%0, @%2				\n"
-"	bf	1b				\n"
-	: "=&z" (tmp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
-}
-
-/*
  * SH-4A note:
  *
  * We basically get atomic_xxx_return() for free compared with
@@ -42,39 +9,53 @@ static inline void atomic_sub(int i, atomic_t *v)
  * encoding, so the retval is automatically set without having to
  * do any special work.
  */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long temp;
+/*
+ * To get proper branch prediction for the main line, we must branch
+ * forward to code at the end of this object's .text section, then
+ * branch back to restart the operation.
+ */
 
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_add_return	\n"
-"	add	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-"	synco						\n"
-	: "=&z" (temp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long tmp;						\
+									\
+	__asm__ __volatile__ (						\
+"1:	movli.l @%2, %0		! atomic_" #op "\n"			\
+"	" #op "	%1, %0				\n"			\
+"	movco.l	%0, @%2				\n"			\
+"	bf	1b				\n"			\
+	: "=&z" (tmp)							\
+	: "r" (i), "r" (&v->counter)					\
+	: "t");								\
+}
 
-	return temp;
+#define ATOMIC_OP_RETURN(op)						\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long temp;						\
+									\
+	__asm__ __volatile__ (						\
+"1:	movli.l @%2, %0		! atomic_" #op "_return	\n"		\
+"	" #op "	%1, %0					\n"		\
+"	movco.l	%0, @%2					\n"		\
+"	bf	1b					\n"		\
+"	synco						\n"		\
+	: "=&z" (temp)							\
+	: "r" (i), "r" (&v->counter)					\
+	: "t");								\
+									\
+	return temp;							\
 }
 
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long temp;
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
 
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_sub_return	\n"
-"	sub	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-"	synco						\n"
-	: "=&z" (temp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
 
-	return temp;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
 {
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index f57b8a6743b3..05b9f74ce2d5 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -14,7 +14,7 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 #define atomic_set(v,i)		((v)->counter = (i))
 
 #if defined(CONFIG_GUSA_RB)
diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h
index 1b6199740e98..7a99e6af6372 100644
--- a/arch/sh/include/asm/sections.h
+++ b/arch/sh/include/asm/sections.h
@@ -3,7 +3,6 @@
 
 #include <asm-generic/sections.h>
 
-extern long __nosave_begin, __nosave_end;
 extern long __machvec_start, __machvec_end;
 extern char __uncached_start, __uncached_end;
 extern char __start_eh_frame[], __stop_eh_frame[];
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index a537816613f9..96ac69c5eba0 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -67,6 +67,7 @@ config SPARC64
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_DEBUG_KMEMLEAK
+	select SPARSE_IRQ
 	select RTC_DRV_CMOS
 	select RTC_DRV_BQ4802
 	select RTC_DRV_SUN4V
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index cdd1b447bb6c..f5f94ce1692c 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -8,6 +8,7 @@ generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += hash.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 7aed2be45b44..765c1776ec9f 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -20,23 +20,22 @@
 
 #define ATOMIC_INIT(i)  { (i) }
 
-int __atomic_add_return(int, atomic_t *);
+int atomic_add_return(int, atomic_t *);
 int atomic_cmpxchg(atomic_t *, int, int);
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 int __atomic_add_unless(atomic_t *, int, int);
 void atomic_set(atomic_t *, int);
 
-#define atomic_read(v)          (*(volatile int *)&(v)->counter)
+#define atomic_read(v)          ACCESS_ONCE((v)->counter)
 
-#define atomic_add(i, v)	((void)__atomic_add_return( (int)(i), (v)))
-#define atomic_sub(i, v)	((void)__atomic_add_return(-(int)(i), (v)))
-#define atomic_inc(v)		((void)__atomic_add_return(        1, (v)))
-#define atomic_dec(v)		((void)__atomic_add_return(       -1, (v)))
+#define atomic_add(i, v)	((void)atomic_add_return( (int)(i), (v)))
+#define atomic_sub(i, v)	((void)atomic_add_return(-(int)(i), (v)))
+#define atomic_inc(v)		((void)atomic_add_return(        1, (v)))
+#define atomic_dec(v)		((void)atomic_add_return(       -1, (v)))
 
-#define atomic_add_return(i, v)	(__atomic_add_return( (int)(i), (v)))
-#define atomic_sub_return(i, v)	(__atomic_add_return(-(int)(i), (v)))
-#define atomic_inc_return(v)	(__atomic_add_return(        1, (v)))
-#define atomic_dec_return(v)	(__atomic_add_return(       -1, (v)))
+#define atomic_sub_return(i, v)	(atomic_add_return(-(int)(i), (v)))
+#define atomic_inc_return(v)	(atomic_add_return(        1, (v)))
+#define atomic_dec_return(v)	(atomic_add_return(       -1, (v)))
 
 #define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
 
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index bb894c8bec56..4082749913ce 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -14,33 +14,34 @@
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 
 #define atomic_set(v, i)	(((v)->counter) = i)
 #define atomic64_set(v, i)	(((v)->counter) = i)
 
-void atomic_add(int, atomic_t *);
-void atomic64_add(long, atomic64_t *);
-void atomic_sub(int, atomic_t *);
-void atomic64_sub(long, atomic64_t *);
+#define ATOMIC_OP(op)							\
+void atomic_##op(int, atomic_t *);					\
+void atomic64_##op(long, atomic64_t *);
 
-int atomic_add_ret(int, atomic_t *);
-long atomic64_add_ret(long, atomic64_t *);
-int atomic_sub_ret(int, atomic_t *);
-long atomic64_sub_ret(long, atomic64_t *);
+#define ATOMIC_OP_RETURN(op)						\
+int atomic_##op##_return(int, atomic_t *);				\
+long atomic64_##op##_return(long, atomic64_t *);
 
-#define atomic_dec_return(v) atomic_sub_ret(1, v)
-#define atomic64_dec_return(v) atomic64_sub_ret(1, v)
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
 
-#define atomic_inc_return(v) atomic_add_ret(1, v)
-#define atomic64_inc_return(v) atomic64_add_ret(1, v)
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
 
-#define atomic_sub_return(i, v) atomic_sub_ret(i, v)
-#define atomic64_sub_return(i, v) atomic64_sub_ret(i, v)
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
-#define atomic_add_return(i, v) atomic_add_ret(i, v)
-#define atomic64_add_return(i, v) atomic64_add_ret(i, v)
+#define atomic_dec_return(v)   atomic_sub_return(1, v)
+#define atomic64_dec_return(v) atomic64_sub_return(1, v)
+
+#define atomic_inc_return(v)   atomic_add_return(1, v)
+#define atomic64_inc_return(v) atomic64_add_return(1, v)
 
 /*
  * atomic_inc_and_test - increment and test
@@ -53,11 +54,11 @@ long atomic64_sub_ret(long, atomic64_t *);
 #define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
 #define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
 
-#define atomic_sub_and_test(i, v) (atomic_sub_ret(i, v) == 0)
-#define atomic64_sub_and_test(i, v) (atomic64_sub_ret(i, v) == 0)
+#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
+#define atomic64_sub_and_test(i, v) (atomic64_sub_return(i, v) == 0)
 
-#define atomic_dec_and_test(v) (atomic_sub_ret(1, v) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_ret(1, v) == 0)
+#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
+#define atomic64_dec_and_test(v) (atomic64_sub_return(1, v) == 0)
 
 #define atomic_inc(v) atomic_add(1, v)
 #define atomic64_inc(v) atomic64_add(1, v)
@@ -65,8 +66,8 @@ long atomic64_sub_ret(long, atomic64_t *);
 #define atomic_dec(v) atomic_sub(1, v)
 #define atomic64_dec(v) atomic64_sub(1, v)
 
-#define atomic_add_negative(i, v) (atomic_add_ret(i, v) < 0)
-#define atomic64_add_negative(i, v) (atomic64_add_ret(i, v) < 0)
+#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0)
+#define atomic64_add_negative(i, v) (atomic64_add_return(i, v) < 0)
 
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
diff --git a/arch/sparc/include/asm/cpudata_32.h b/arch/sparc/include/asm/cpudata_32.h
index 0300d94c25b3..05f366379f53 100644
--- a/arch/sparc/include/asm/cpudata_32.h
+++ b/arch/sparc/include/asm/cpudata_32.h
@@ -26,6 +26,6 @@ typedef struct {
 
 DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
 #define cpu_data(__cpu) per_cpu(__cpu_data, (__cpu))
-#define local_cpu_data() __get_cpu_var(__cpu_data)
+#define local_cpu_data() (*this_cpu_ptr(&__cpu_data))
 
 #endif /* _SPARC_CPUDATA_H */
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index 0e594076912c..a6e424d185d0 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -30,7 +30,7 @@ typedef struct {
 
 DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
 #define cpu_data(__cpu)		per_cpu(__cpu_data, (__cpu))
-#define local_cpu_data()	__get_cpu_var(__cpu_data)
+#define local_cpu_data()	(*this_cpu_ptr(&__cpu_data))
 
 #endif /* !(__ASSEMBLY__) */
 
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 1ee02710b2dc..5b1b52a04ad6 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -20,10 +20,12 @@ extern struct bus_type pci_bus_type;
 
 static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-#if defined(CONFIG_SPARC32) && defined(CONFIG_PCI)
+#ifdef CONFIG_SPARC_LEON
 	if (sparc_cpu_model == sparc_leon)
 		return leon_dma_ops;
-	else if (dev->bus == &pci_bus_type)
+#endif
+#if defined(CONFIG_SPARC32) && defined(CONFIG_PCI)
+	if (dev->bus == &pci_bus_type)
 		return &pci32_dma_ops;
 #endif
 	return dma_ops;
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index 94b39caea3eb..4f6725ff4c33 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -2947,6 +2947,16 @@ unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
 				   unsigned long reg_val);
 #endif
 
+#define	HV_FAST_T5_GET_PERFREG		0x1a8
+#define	HV_FAST_T5_SET_PERFREG		0x1a9
+
+#ifndef	__ASSEMBLY__
+unsigned long sun4v_t5_get_perfreg(unsigned long reg_num,
+				   unsigned long *reg_val);
+unsigned long sun4v_t5_set_perfreg(unsigned long reg_num,
+				   unsigned long reg_val);
+#endif
+
 /* Function numbers for HV_CORE_TRAP.  */
 #define HV_CORE_SET_VER			0x00
 #define HV_CORE_PUTCHAR			0x01
@@ -2978,6 +2988,7 @@ unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
 #define HV_GRP_VF_CPU			0x0205
 #define HV_GRP_KT_CPU			0x0209
 #define HV_GRP_VT_CPU			0x020c
+#define HV_GRP_T5_CPU			0x0211
 #define HV_GRP_DIAG			0x0300
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h
index 91d219381306..3f70f900e834 100644
--- a/arch/sparc/include/asm/irq_64.h
+++ b/arch/sparc/include/asm/irq_64.h
@@ -37,7 +37,7 @@
  *
  * ino_bucket->irq allocation is made during {sun4v_,}build_irq().
  */
-#define NR_IRQS    255
+#define NR_IRQS		(2048)
 
 void irq_install_pre_handler(int irq,
 			     void (*func)(unsigned int, void *, void *),
@@ -57,11 +57,8 @@ unsigned int sun4u_build_msi(u32 portid, unsigned int *irq_p,
 			     unsigned long iclr_base);
 void sun4u_destroy_msi(unsigned int irq);
 
-unsigned char irq_alloc(unsigned int dev_handle,
-			unsigned int dev_ino);
-#ifdef CONFIG_PCI_MSI
+unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino);
 void irq_free(unsigned int irq);
-#endif
 
 void __init init_IRQ(void);
 void fixup_irqs(void);
diff --git a/arch/sparc/include/asm/ldc.h b/arch/sparc/include/asm/ldc.h
index c8c67f621f4f..58ab64de25d2 100644
--- a/arch/sparc/include/asm/ldc.h
+++ b/arch/sparc/include/asm/ldc.h
@@ -53,13 +53,14 @@ struct ldc_channel;
 /* Allocate state for a channel.  */
 struct ldc_channel *ldc_alloc(unsigned long id,
 			      const struct ldc_channel_config *cfgp,
-			      void *event_arg);
+			      void *event_arg,
+			      const char *name);
 
 /* Shut down and free state for a channel.  */
 void ldc_free(struct ldc_channel *lp);
 
 /* Register TX and RX queues of the link with the hypervisor.  */
-int ldc_bind(struct ldc_channel *lp, const char *name);
+int ldc_bind(struct ldc_channel *lp);
 
 /* For non-RAW protocols we need to complete a handshake before
  * communication can proceed.  ldc_connect() does that, if the
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index bf109984a032..8c2a8c937540 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -57,18 +57,21 @@ void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topa
 typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long iopte; } iopte_t;
 typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pud; } pud_t;
 typedef struct { unsigned long pgd; } pgd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
 
 #define pte_val(x)	((x).pte)
 #define iopte_val(x)	((x).iopte)
 #define pmd_val(x)      ((x).pmd)
+#define pud_val(x)      ((x).pud)
 #define pgd_val(x)	((x).pgd)
 #define pgprot_val(x)	((x).pgprot)
 
 #define __pte(x)	((pte_t) { (x) } )
 #define __iopte(x)	((iopte_t) { (x) } )
 #define __pmd(x)        ((pmd_t) { (x) } )
+#define __pud(x)        ((pud_t) { (x) } )
 #define __pgd(x)	((pgd_t) { (x) } )
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
@@ -77,18 +80,21 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 typedef unsigned long pte_t;
 typedef unsigned long iopte_t;
 typedef unsigned long pmd_t;
+typedef unsigned long pud_t;
 typedef unsigned long pgd_t;
 typedef unsigned long pgprot_t;
 
 #define pte_val(x)	(x)
 #define iopte_val(x)	(x)
 #define pmd_val(x)      (x)
+#define pud_val(x)      (x)
 #define pgd_val(x)	(x)
 #define pgprot_val(x)	(x)
 
 #define __pte(x)	(x)
 #define __iopte(x)	(x)
 #define __pmd(x)        (x)
+#define __pud(x)        (x)
 #define __pgd(x)	(x)
 #define __pgprot(x)	(x)
 
@@ -96,21 +102,14 @@ typedef unsigned long pgprot_t;
 
 typedef pte_t *pgtable_t;
 
-/* These two values define the virtual address space range in which we
- * must forbid 64-bit user processes from making mappings.  It used to
- * represent precisely the virtual address space hole present in most
- * early sparc64 chips including UltraSPARC-I.  But now it also is
- * further constrained by the limits of our page tables, which is
- * 43-bits of virtual address.
- */
-#define SPARC64_VA_HOLE_TOP	_AC(0xfffffc0000000000,UL)
-#define SPARC64_VA_HOLE_BOTTOM	_AC(0x0000040000000000,UL)
+extern unsigned long sparc64_va_hole_top;
+extern unsigned long sparc64_va_hole_bottom;
 
 /* The next two defines specify the actual exclusion region we
  * enforce, wherein we use a 4GB red zone on each side of the VA hole.
  */
-#define VA_EXCLUDE_START (SPARC64_VA_HOLE_BOTTOM - (1UL << 32UL))
-#define VA_EXCLUDE_END   (SPARC64_VA_HOLE_TOP + (1UL << 32UL))
+#define VA_EXCLUDE_START (sparc64_va_hole_bottom - (1UL << 32UL))
+#define VA_EXCLUDE_END   (sparc64_va_hole_top + (1UL << 32UL))
 
 #define TASK_UNMAPPED_BASE	(test_thread_flag(TIF_32BIT) ? \
 				 _AC(0x0000000070000000,UL) : \
@@ -118,20 +117,16 @@ typedef pte_t *pgtable_t;
 
 #include <asm-generic/memory_model.h>
 
-#define PAGE_OFFSET_BY_BITS(X)	(-(_AC(1,UL) << (X)))
 extern unsigned long PAGE_OFFSET;
 
 #endif /* !(__ASSEMBLY__) */
 
-/* The maximum number of physical memory address bits we support, this
- * is used to size various tables used to manage kernel TLB misses and
- * also the sparsemem code.
+/* The maximum number of physical memory address bits we support.  The
+ * largest value we can support is whatever "KPGD_SHIFT + KPTE_BITS"
+ * evaluates to.
  */
-#define MAX_PHYS_ADDRESS_BITS	47
+#define MAX_PHYS_ADDRESS_BITS	53
 
-/* These two shift counts are used when indexing sparc64_valid_addr_bitmap
- * and kpte_linear_bitmap.
- */
 #define ILOG2_4MB		22
 #define ILOG2_256MB		28
 
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index 39a7ac49b00c..5e3187185b4a 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -15,6 +15,13 @@
 
 extern struct kmem_cache *pgtable_cache;
 
+static inline void __pgd_populate(pgd_t *pgd, pud_t *pud)
+{
+	pgd_set(pgd, pud);
+}
+
+#define pgd_populate(MM, PGD, PUD)	__pgd_populate(PGD, PUD)
+
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	return kmem_cache_alloc(pgtable_cache, GFP_KERNEL);
@@ -25,7 +32,23 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 	kmem_cache_free(pgtable_cache, pgd);
 }
 
-#define pud_populate(MM, PUD, PMD)	pud_set(PUD, PMD)
+static inline void __pud_populate(pud_t *pud, pmd_t *pmd)
+{
+	pud_set(pud, pmd);
+}
+
+#define pud_populate(MM, PUD, PMD)	__pud_populate(PUD, PMD)
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return kmem_cache_alloc(pgtable_cache,
+				GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	kmem_cache_free(pgtable_cache, pud);
+}
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
@@ -91,4 +114,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pte_t *pte,
 #define __pmd_free_tlb(tlb, pmd, addr)		      \
 	pgtable_free_tlb(tlb, pmd, false)
 
+#define __pud_free_tlb(tlb, pud, addr)		      \
+	pgtable_free_tlb(tlb, pud, false)
+
 #endif /* _SPARC64_PGALLOC_H */
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 3770bf5c6e1b..bfeb626085ac 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -20,8 +20,6 @@
 #include <asm/page.h>
 #include <asm/processor.h>
 
-#include <asm-generic/pgtable-nopud.h>
-
 /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB).
  * The page copy blockops can use 0x6000000 to 0x8000000.
  * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range.
@@ -42,10 +40,7 @@
 #define LOW_OBP_ADDRESS		_AC(0x00000000f0000000,UL)
 #define HI_OBP_ADDRESS		_AC(0x0000000100000000,UL)
 #define VMALLOC_START		_AC(0x0000000100000000,UL)
-#define VMALLOC_END		_AC(0x0000010000000000,UL)
-#define VMEMMAP_BASE		_AC(0x0000010000000000,UL)
-
-#define vmemmap			((struct page *)VMEMMAP_BASE)
+#define VMEMMAP_BASE		VMALLOC_END
 
 /* PMD_SHIFT determines the size of the area a second-level page
  * table can map
@@ -55,13 +50,25 @@
 #define PMD_MASK	(~(PMD_SIZE-1))
 #define PMD_BITS	(PAGE_SHIFT - 3)
 
-/* PGDIR_SHIFT determines what a third-level page table entry can map */
-#define PGDIR_SHIFT	(PAGE_SHIFT + (PAGE_SHIFT-3) + PMD_BITS)
+/* PUD_SHIFT determines the size of the area a third-level page
+ * table can map
+ */
+#define PUD_SHIFT	(PMD_SHIFT + PMD_BITS)
+#define PUD_SIZE	(_AC(1,UL) << PUD_SHIFT)
+#define PUD_MASK	(~(PUD_SIZE-1))
+#define PUD_BITS	(PAGE_SHIFT - 3)
+
+/* PGDIR_SHIFT determines what a fourth-level page table entry can map */
+#define PGDIR_SHIFT	(PUD_SHIFT + PUD_BITS)
 #define PGDIR_SIZE	(_AC(1,UL) << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 #define PGDIR_BITS	(PAGE_SHIFT - 3)
 
-#if (PGDIR_SHIFT + PGDIR_BITS) != 43
+#if (MAX_PHYS_ADDRESS_BITS > PGDIR_SHIFT + PGDIR_BITS)
+#error MAX_PHYS_ADDRESS_BITS exceeds what kernel page tables can support
+#endif
+
+#if (PGDIR_SHIFT + PGDIR_BITS) != 53
 #error Page table parameters do not cover virtual address space properly.
 #endif
 
@@ -71,28 +78,18 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/sched.h>
-
-extern unsigned long sparc64_valid_addr_bitmap[];
+extern unsigned long VMALLOC_END;
 
-/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
-static inline bool __kern_addr_valid(unsigned long paddr)
-{
-	if ((paddr >> MAX_PHYS_ADDRESS_BITS) != 0UL)
-		return false;
-	return test_bit(paddr >> ILOG2_4MB, sparc64_valid_addr_bitmap);
-}
+#define vmemmap			((struct page *)VMEMMAP_BASE)
 
-static inline bool kern_addr_valid(unsigned long addr)
-{
-	unsigned long paddr = __pa(addr);
+#include <linux/sched.h>
 
-	return __kern_addr_valid(paddr);
-}
+bool kern_addr_valid(unsigned long addr);
 
 /* Entries per page directory level. */
 #define PTRS_PER_PTE	(1UL << (PAGE_SHIFT-3))
 #define PTRS_PER_PMD	(1UL << PMD_BITS)
+#define PTRS_PER_PUD	(1UL << PUD_BITS)
 #define PTRS_PER_PGD	(1UL << PGDIR_BITS)
 
 /* Kernel has a separate 44bit address space. */
@@ -101,6 +98,9 @@ static inline bool kern_addr_valid(unsigned long addr)
 #define pmd_ERROR(e)							\
 	pr_err("%s:%d: bad pmd %p(%016lx) seen at (%pS)\n",		\
 	       __FILE__, __LINE__, &(e), pmd_val(e), __builtin_return_address(0))
+#define pud_ERROR(e)							\
+	pr_err("%s:%d: bad pud %p(%016lx) seen at (%pS)\n",		\
+	       __FILE__, __LINE__, &(e), pud_val(e), __builtin_return_address(0))
 #define pgd_ERROR(e)							\
 	pr_err("%s:%d: bad pgd %p(%016lx) seen at (%pS)\n",		\
 	       __FILE__, __LINE__, &(e), pgd_val(e), __builtin_return_address(0))
@@ -112,6 +112,7 @@ static inline bool kern_addr_valid(unsigned long addr)
 #define _PAGE_R	  	  _AC(0x8000000000000000,UL) /* Keep ref bit uptodate*/
 #define _PAGE_SPECIAL     _AC(0x0200000000000000,UL) /* Special page         */
 #define _PAGE_PMD_HUGE    _AC(0x0100000000000000,UL) /* Huge page            */
+#define _PAGE_PUD_HUGE    _PAGE_PMD_HUGE
 
 /* Advertise support for _PAGE_SPECIAL */
 #define __HAVE_ARCH_PTE_SPECIAL
@@ -658,26 +659,26 @@ static inline unsigned long pmd_large(pmd_t pmd)
 	return pte_val(pte) & _PAGE_PMD_HUGE;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline unsigned long pmd_young(pmd_t pmd)
+static inline unsigned long pmd_pfn(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_young(pte);
+	return pte_pfn(pte);
 }
 
-static inline unsigned long pmd_write(pmd_t pmd)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long pmd_young(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_write(pte);
+	return pte_young(pte);
 }
 
-static inline unsigned long pmd_pfn(pmd_t pmd)
+static inline unsigned long pmd_write(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_pfn(pte);
+	return pte_write(pte);
 }
 
 static inline unsigned long pmd_trans_huge(pmd_t pmd)
@@ -771,13 +772,15 @@ static inline int pmd_present(pmd_t pmd)
  * the top bits outside of the range of any physical address size we
  * support are clear as well.  We also validate the physical itself.
  */
-#define pmd_bad(pmd)			((pmd_val(pmd) & ~PAGE_MASK) || \
-					 !__kern_addr_valid(pmd_val(pmd)))
+#define pmd_bad(pmd)			(pmd_val(pmd) & ~PAGE_MASK)
 
 #define pud_none(pud)			(!pud_val(pud))
 
-#define pud_bad(pud)			((pud_val(pud) & ~PAGE_MASK) || \
-					 !__kern_addr_valid(pud_val(pud)))
+#define pud_bad(pud)			(pud_val(pud) & ~PAGE_MASK)
+
+#define pgd_none(pgd)			(!pgd_val(pgd))
+
+#define pgd_bad(pgd)			(pgd_val(pgd) & ~PAGE_MASK)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void set_pmd_at(struct mm_struct *mm, unsigned long addr,
@@ -815,10 +818,31 @@ static inline unsigned long __pmd_page(pmd_t pmd)
 #define pmd_clear(pmdp)			(pmd_val(*(pmdp)) = 0UL)
 #define pud_present(pud)		(pud_val(pud) != 0U)
 #define pud_clear(pudp)			(pud_val(*(pudp)) = 0UL)
+#define pgd_page_vaddr(pgd)		\
+	((unsigned long) __va(pgd_val(pgd)))
+#define pgd_present(pgd)		(pgd_val(pgd) != 0U)
+#define pgd_clear(pgdp)			(pgd_val(*(pgd)) = 0UL)
+
+static inline unsigned long pud_large(pud_t pud)
+{
+	pte_t pte = __pte(pud_val(pud));
+
+	return pte_val(pte) & _PAGE_PMD_HUGE;
+}
+
+static inline unsigned long pud_pfn(pud_t pud)
+{
+	pte_t pte = __pte(pud_val(pud));
+
+	return pte_pfn(pte);
+}
 
 /* Same in both SUN4V and SUN4U.  */
 #define pte_none(pte) 			(!pte_val(pte))
 
+#define pgd_set(pgdp, pudp)	\
+	(pgd_val(*(pgdp)) = (__pa((unsigned long) (pudp))))
+
 /* to find an entry in a page-table-directory. */
 #define pgd_index(address)	(((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
 #define pgd_offset(mm, address)	((mm)->pgd + pgd_index(address))
@@ -826,6 +850,11 @@ static inline unsigned long __pmd_page(pmd_t pmd)
 /* to find an entry in a kernel page-table-directory */
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
 
+/* Find an entry in the third-level page table.. */
+#define pud_index(address)	(((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+#define pud_offset(pgdp, address)	\
+	((pud_t *) pgd_page_vaddr(*(pgdp)) + pud_index(address))
+
 /* Find an entry in the second-level page table.. */
 #define pmd_offset(pudp, address)	\
 	((pmd_t *) pud_page_vaddr(*(pudp)) + \
@@ -898,7 +927,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 #endif
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-extern pmd_t swapper_low_pmd_dir[PTRS_PER_PMD];
 
 void paging_init(void);
 unsigned long find_ecache_flush_span(unsigned long size);
diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h
index 3fc58691dbd0..56f933816144 100644
--- a/arch/sparc/include/asm/spitfire.h
+++ b/arch/sparc/include/asm/spitfire.h
@@ -45,6 +45,8 @@
 #define SUN4V_CHIP_NIAGARA3	0x03
 #define SUN4V_CHIP_NIAGARA4	0x04
 #define SUN4V_CHIP_NIAGARA5	0x05
+#define SUN4V_CHIP_SPARC_M6	0x06
+#define SUN4V_CHIP_SPARC_M7	0x07
 #define SUN4V_CHIP_SPARC64X	0x8a
 #define SUN4V_CHIP_UNKNOWN	0xff
 
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index a5f01ac6d0f1..f85dc8512ab3 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -102,6 +102,7 @@ struct thread_info {
 #define FAULT_CODE_ITLB		0x04	/* Miss happened in I-TLB	   */
 #define FAULT_CODE_WINFIXUP	0x08	/* Miss happened during spill/fill */
 #define FAULT_CODE_BLKCOMMIT	0x10	/* Use blk-commit ASI in copy_page */
+#define	FAULT_CODE_BAD_RA	0x20	/* Bad RA for sun4v		   */
 
 #if PAGE_SHIFT == 13
 #define THREAD_SIZE (2*PAGE_SIZE)
diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index 90916f955cac..ecb49cfa3be9 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -133,9 +133,24 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	sub	TSB, 0x8, TSB;   \
 	TSB_STORE(TSB, TAG);
 
-	/* Do a kernel page table walk.  Leaves physical PTE pointer in
-	 * REG1.  Jumps to FAIL_LABEL on early page table walk termination.
-	 * VADDR will not be clobbered, but REG2 will.
+	/* Do a kernel page table walk.  Leaves valid PTE value in
+	 * REG1.  Jumps to FAIL_LABEL on early page table walk
+	 * termination.  VADDR will not be clobbered, but REG2 will.
+	 *
+	 * There are two masks we must apply to propagate bits from
+	 * the virtual address into the PTE physical address field
+	 * when dealing with huge pages.  This is because the page
+	 * table boundaries do not match the huge page size(s) the
+	 * hardware supports.
+	 *
+	 * In these cases we propagate the bits that are below the
+	 * page table level where we saw the huge page mapping, but
+	 * are still within the relevant physical bits for the huge
+	 * page size in question.  So for PMD mappings (which fall on
+	 * bit 23, for 8MB per PMD) we must propagate bit 22 for a
+	 * 4MB huge page.  For huge PUDs (which fall on bit 33, for
+	 * 8GB per PUD), we have to accomodate 256MB and 2GB huge
+	 * pages.  So for those we propagate bits 32 to 28.
 	 */
 #define KERN_PGTABLE_WALK(VADDR, REG1, REG2, FAIL_LABEL)	\
 	sethi		%hi(swapper_pg_dir), REG1; \
@@ -145,15 +160,40 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	andn		REG2, 0x7, REG2; \
 	ldx		[REG1 + REG2], REG1; \
 	brz,pn		REG1, FAIL_LABEL; \
-	 sllx		VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \
+	 sllx		VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
 	andn		REG2, 0x7, REG2; \
 	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
 	brz,pn		REG1, FAIL_LABEL; \
-	 sllx		VADDR, 64 - PMD_SHIFT, REG2; \
+	sethi		%uhi(_PAGE_PUD_HUGE), REG2; \
+	brz,pn		REG1, FAIL_LABEL; \
+	 sllx		REG2, 32, REG2; \
+	andcc		REG1, REG2, %g0; \
+	sethi		%hi(0xf8000000), REG2; \
+	bne,pt		%xcc, 697f; \
+	 sllx		REG2, 1, REG2; \
+	sllx		VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
 	andn		REG2, 0x7, REG2; \
-	add		REG1, REG2, REG1;
+	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
+	sethi		%uhi(_PAGE_PMD_HUGE), REG2; \
+	brz,pn		REG1, FAIL_LABEL; \
+	 sllx		REG2, 32, REG2; \
+	andcc		REG1, REG2, %g0; \
+	be,pn		%xcc, 698f; \
+	 sethi		%hi(0x400000), REG2; \
+697:	brgez,pn	REG1, FAIL_LABEL; \
+	 andn		REG1, REG2, REG1; \
+	and		VADDR, REG2, REG2; \
+	ba,pt		%xcc, 699f; \
+	 or		REG1, REG2, REG1; \
+698:	sllx		VADDR, 64 - PMD_SHIFT, REG2; \
+	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
+	andn		REG2, 0x7, REG2; \
+	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
+	brgez,pn	REG1, FAIL_LABEL; \
+	 nop; \
+699:
 
 	/* PMD has been loaded into REG1, interpret the value, seeing
 	 * if it is a HUGE PMD or a normal one.  If it is not valid
@@ -198,6 +238,11 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	andn		REG2, 0x7, REG2; \
 	ldxa		[PHYS_PGD + REG2] ASI_PHYS_USE_EC, REG1; \
 	brz,pn		REG1, FAIL_LABEL; \
+	 sllx		VADDR, 64 - (PUD_SHIFT + PUD_BITS), REG2; \
+	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
+	andn		REG2, 0x7, REG2; \
+	ldxa		[REG1 + REG2] ASI_PHYS_USE_EC, REG1; \
+	brz,pn		REG1, FAIL_LABEL; \
 	 sllx		VADDR, 64 - (PMD_SHIFT + PMD_BITS), REG2; \
 	srlx		REG2, 64 - PAGE_SHIFT, REG2; \
 	andn		REG2, 0x7, REG2; \
@@ -246,8 +291,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	(KERNEL_TSB_SIZE_BYTES / 16)
 #define KERNEL_TSB4M_NENTRIES	4096
 
-#define KTSB_PHYS_SHIFT		15
-
 	/* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL
 	 * on TSB hit.  REG1, REG2, REG3, and REG4 are used as temporaries
 	 * and the found TTE will be left in REG1.  REG3 and REG4 must
@@ -256,17 +299,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * VADDR and TAG will be preserved and not clobbered by this macro.
 	 */
 #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-661:	sethi		%hi(swapper_tsb), REG1;			\
-	or		REG1, %lo(swapper_tsb), REG1; \
+661:	sethi		%uhi(swapper_tsb), REG1; \
+	sethi		%hi(swapper_tsb), REG2; \
+	or		REG1, %ulo(swapper_tsb), REG1; \
+	or		REG2, %lo(swapper_tsb), REG2; \
 	.section	.swapper_tsb_phys_patch, "ax"; \
 	.word		661b; \
 	.previous; \
-661:	nop; \
-	.section	.tsb_ldquad_phys_patch, "ax"; \
-	.word		661b; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	.previous; \
+	sllx		REG1, 32, REG1; \
+	or		REG1, REG2, REG1; \
 	srlx		VADDR, PAGE_SHIFT, REG2; \
 	and		REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
@@ -281,17 +322,15 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	 * we can make use of that for the index computation.
 	 */
 #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \
-661:	sethi		%hi(swapper_4m_tsb), REG1;	     \
-	or		REG1, %lo(swapper_4m_tsb), REG1; \
+661:	sethi		%uhi(swapper_4m_tsb), REG1; \
+	sethi		%hi(swapper_4m_tsb), REG2; \
+	or		REG1, %ulo(swapper_4m_tsb), REG1; \
+	or		REG2, %lo(swapper_4m_tsb), REG2; \
 	.section	.swapper_4m_tsb_phys_patch, "ax"; \
 	.word		661b; \
 	.previous; \
-661:	nop; \
-	.section	.tsb_ldquad_phys_patch, "ax"; \
-	.word		661b; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	sllx		REG1, KTSB_PHYS_SHIFT, REG1; \
-	.previous; \
+	sllx		REG1, 32, REG1; \
+	or		REG1, REG2, REG1; \
 	and		TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \
 	sllx		REG2, 4, REG2; \
 	add		REG1, REG2, REG2; \
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 6b135a8ab07b..d758c8d8f47d 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -121,12 +121,18 @@ struct vio_disk_attr_info {
 	u8			vdisk_type;
 #define VD_DISK_TYPE_SLICE	0x01 /* Slice in block device	*/
 #define VD_DISK_TYPE_DISK	0x02 /* Entire block device	*/
-	u16			resv1;
+	u8			vdisk_mtype;		/* v1.1 */
+#define VD_MEDIA_TYPE_FIXED	0x01 /* Fixed device */
+#define VD_MEDIA_TYPE_CD	0x02 /* CD Device    */
+#define VD_MEDIA_TYPE_DVD	0x03 /* DVD Device   */
+	u8			resv1;
 	u32			vdisk_block_size;
 	u64			operations;
-	u64			vdisk_size;
+	u64			vdisk_size;		/* v1.1 */
 	u64			max_xfer_size;
-	u64			resv2[2];
+	u32			phys_block_size;	/* v1.2 */
+	u32			resv2;
+	u64			resv3[1];
 };
 
 struct vio_disk_desc {
@@ -272,7 +278,7 @@ static inline u32 vio_dring_avail(struct vio_dring_state *dr,
 				  unsigned int ring_size)
 {
 	return (dr->pending -
-		((dr->prod - dr->cons) & (ring_size - 1)));
+		((dr->prod - dr->cons) & (ring_size - 1)) - 1);
 }
 
 #define VIO_MAX_TYPE_LEN	32
@@ -292,6 +298,7 @@ struct vio_dev {
 
 	unsigned int		tx_irq;
 	unsigned int		rx_irq;
+	u64			rx_ino;
 
 	struct device		dev;
 };
@@ -447,5 +454,6 @@ int vio_driver_init(struct vio_driver_state *vio, struct vio_dev *vdev,
 		    char *name);
 
 void vio_port_up(struct vio_driver_state *vio);
+int vio_set_intr(unsigned long dev_ino, int state);
 
 #endif /* _SPARC64_VIO_H */
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index b26673759283..1f0aa2024e94 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -39,6 +39,14 @@
 297:	wr		%o5, FPRS_FEF, %fprs;		\
 298:
 
+#define VISEntryHalfFast(fail_label)			\
+	rd		%fprs, %o5;			\
+	andcc		%o5, FPRS_FEF, %g0;		\
+	be,pt		%icc, 297f;			\
+	 nop;						\
+	ba,a,pt		%xcc, fail_label;		\
+297:	wr		%o5, FPRS_FEF, %fprs;
+
 #define VISExitHalf					\
 	wr		%o5, 0, %fprs;
 
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index 82a3a71c451e..dfad8b1aea9f 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -494,6 +494,18 @@ static void __init sun4v_cpu_probe(void)
 		sparc_pmu_type = "niagara5";
 		break;
 
+	case SUN4V_CHIP_SPARC_M6:
+		sparc_cpu_type = "SPARC-M6";
+		sparc_fpu_type = "SPARC-M6 integrated FPU";
+		sparc_pmu_type = "sparc-m6";
+		break;
+
+	case SUN4V_CHIP_SPARC_M7:
+		sparc_cpu_type = "SPARC-M7";
+		sparc_fpu_type = "SPARC-M7 integrated FPU";
+		sparc_pmu_type = "sparc-m7";
+		break;
+
 	case SUN4V_CHIP_SPARC64X:
 		sparc_cpu_type = "SPARC64-X";
 		sparc_fpu_type = "SPARC64-X integrated FPU";
diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c
index de1c844dfabc..e69ec0e3f155 100644
--- a/arch/sparc/kernel/cpumap.c
+++ b/arch/sparc/kernel/cpumap.c
@@ -326,6 +326,8 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
 	case SUN4V_CHIP_NIAGARA3:
 	case SUN4V_CHIP_NIAGARA4:
 	case SUN4V_CHIP_NIAGARA5:
+	case SUN4V_CHIP_SPARC_M6:
+	case SUN4V_CHIP_SPARC_M7:
 	case SUN4V_CHIP_SPARC64X:
 		rover_inc_table = niagara_iterate_method;
 		break;
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index dff60abbea01..f87a55d77094 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -1200,14 +1200,14 @@ static int ds_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	ds_cfg.tx_irq = vdev->tx_irq;
 	ds_cfg.rx_irq = vdev->rx_irq;
 
-	lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp);
+	lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp, "DS");
 	if (IS_ERR(lp)) {
 		err = PTR_ERR(lp);
 		goto out_free_ds_states;
 	}
 	dp->lp = lp;
 
-	err = ldc_bind(lp, "DS");
+	err = ldc_bind(lp);
 	if (err)
 		goto out_free_ldc;
 
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 452f04fe8da6..4fdeb8040d4d 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -427,6 +427,12 @@ sun4v_chip_type:
 	cmp	%g2, '5'
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA5, %g4
+	cmp	%g2, '6'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_SPARC_M6, %g4
+	cmp	%g2, '7'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_SPARC_M7, %g4
 	ba,pt	%xcc, 49f
 	 nop
 
@@ -585,6 +591,12 @@ niagara_tlb_fixup:
 	cmp	%g1, SUN4V_CHIP_NIAGARA5
 	be,pt	%xcc, niagara4_patch
 	 nop
+	cmp	%g1, SUN4V_CHIP_SPARC_M6
+	be,pt	%xcc, niagara4_patch
+	 nop
+	cmp	%g1, SUN4V_CHIP_SPARC_M7
+	be,pt	%xcc, niagara4_patch
+	 nop
 
 	call	generic_patch_copyops
 	 nop
diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index c0a2de0fd624..5c55145bfbf0 100644
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@@ -46,6 +46,7 @@ static struct api_info api_table[] = {
 	{ .group = HV_GRP_VF_CPU,				},
 	{ .group = HV_GRP_KT_CPU,				},
 	{ .group = HV_GRP_VT_CPU,				},
+	{ .group = HV_GRP_T5_CPU,				},
 	{ .group = HV_GRP_DIAG,		.flags = FLAG_PRE_API	},
 };
 
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index f3ab509b76a8..caedf8320416 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -821,3 +821,19 @@ ENTRY(sun4v_vt_set_perfreg)
 	retl
 	 nop
 ENDPROC(sun4v_vt_set_perfreg)
+
+ENTRY(sun4v_t5_get_perfreg)
+	mov	%o1, %o4
+	mov	HV_FAST_T5_GET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	stx	%o1, [%o4]
+	retl
+	 nop
+ENDPROC(sun4v_t5_get_perfreg)
+
+ENTRY(sun4v_t5_set_perfreg)
+	mov	HV_FAST_T5_SET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(sun4v_t5_set_perfreg)
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 7f08ec8a7c68..28fed53b13a0 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -278,7 +278,8 @@ static void *sbus_alloc_coherent(struct device *dev, size_t len,
 	}
 
 	order = get_order(len_total);
-	if ((va = __get_free_pages(GFP_KERNEL|__GFP_COMP, order)) == 0)
+	va = __get_free_pages(gfp, order);
+	if (va == 0)
 		goto err_nopages;
 
 	if ((res = kzalloc(sizeof(struct resource), GFP_KERNEL)) == NULL)
@@ -443,7 +444,7 @@ static void *pci32_alloc_coherent(struct device *dev, size_t len,
 	}
 
 	order = get_order(len_total);
-	va = (void *) __get_free_pages(GFP_KERNEL, order);
+	va = (void *) __get_free_pages(gfp, order);
 	if (va == NULL) {
 		printk("pci_alloc_consistent: no %ld pages\n", len_total>>PAGE_SHIFT);
 		goto err_nopages;
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 666193f4e8bb..4033c23bdfa6 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -47,8 +47,6 @@
 #include "cpumap.h"
 #include "kstack.h"
 
-#define NUM_IVECS	(IMAP_INR + 1)
-
 struct ino_bucket *ivector_table;
 unsigned long ivector_table_pa;
 
@@ -107,55 +105,196 @@ static void bucket_set_irq(unsigned long bucket_pa, unsigned int irq)
 
 #define irq_work_pa(__cpu)	&(trap_block[(__cpu)].irq_worklist_pa)
 
-static struct {
-	unsigned int dev_handle;
-	unsigned int dev_ino;
-	unsigned int in_use;
-} irq_table[NR_IRQS];
-static DEFINE_SPINLOCK(irq_alloc_lock);
+static unsigned long hvirq_major __initdata;
+static int __init early_hvirq_major(char *p)
+{
+	int rc = kstrtoul(p, 10, &hvirq_major);
+
+	return rc;
+}
+early_param("hvirq", early_hvirq_major);
+
+static int hv_irq_version;
+
+/* Major version 2.0 of HV_GRP_INTR added support for the VIRQ cookie
+ * based interfaces, but:
+ *
+ * 1) Several OSs, Solaris and Linux included, use them even when only
+ *    negotiating version 1.0 (or failing to negotiate at all).  So the
+ *    hypervisor has a workaround that provides the VIRQ interfaces even
+ *    when only verion 1.0 of the API is in use.
+ *
+ * 2) Second, and more importantly, with major version 2.0 these VIRQ
+ *    interfaces only were actually hooked up for LDC interrupts, even
+ *    though the Hypervisor specification clearly stated:
+ *
+ *	The new interrupt API functions will be available to a guest
+ *	when it negotiates version 2.0 in the interrupt API group 0x2. When
+ *	a guest negotiates version 2.0, all interrupt sources will only
+ *	support using the cookie interface, and any attempt to use the
+ *	version 1.0 interrupt APIs numbered 0xa0 to 0xa6 will result in the
+ *	ENOTSUPPORTED error being returned.
+ *
+ *   with an emphasis on "all interrupt sources".
+ *
+ * To correct this, major version 3.0 was created which does actually
+ * support VIRQs for all interrupt sources (not just LDC devices).  So
+ * if we want to move completely over the cookie based VIRQs we must
+ * negotiate major version 3.0 or later of HV_GRP_INTR.
+ */
+static bool sun4v_cookie_only_virqs(void)
+{
+	if (hv_irq_version >= 3)
+		return true;
+	return false;
+}
 
-unsigned char irq_alloc(unsigned int dev_handle, unsigned int dev_ino)
+static void __init irq_init_hv(void)
 {
-	unsigned long flags;
-	unsigned char ent;
+	unsigned long hv_error, major, minor = 0;
+
+	if (tlb_type != hypervisor)
+		return;
 
-	BUILD_BUG_ON(NR_IRQS >= 256);
+	if (hvirq_major)
+		major = hvirq_major;
+	else
+		major = 3;
 
-	spin_lock_irqsave(&irq_alloc_lock, flags);
+	hv_error = sun4v_hvapi_register(HV_GRP_INTR, major, &minor);
+	if (!hv_error)
+		hv_irq_version = major;
+	else
+		hv_irq_version = 1;
 
-	for (ent = 1; ent < NR_IRQS; ent++) {
-		if (!irq_table[ent].in_use)
+	pr_info("SUN4V: Using IRQ API major %d, cookie only virqs %s\n",
+		hv_irq_version,
+		sun4v_cookie_only_virqs() ? "enabled" : "disabled");
+}
+
+/* This function is for the timer interrupt.*/
+int __init arch_probe_nr_irqs(void)
+{
+	return 1;
+}
+
+#define DEFAULT_NUM_IVECS	(0xfffU)
+static unsigned int nr_ivec = DEFAULT_NUM_IVECS;
+#define NUM_IVECS (nr_ivec)
+
+static unsigned int __init size_nr_ivec(void)
+{
+	if (tlb_type == hypervisor) {
+		switch (sun4v_chip_type) {
+		/* Athena's devhandle|devino is large.*/
+		case SUN4V_CHIP_SPARC64X:
+			nr_ivec = 0xffff;
 			break;
+		}
 	}
-	if (ent >= NR_IRQS) {
-		printk(KERN_ERR "IRQ: Out of virtual IRQs.\n");
-		ent = 0;
-	} else {
-		irq_table[ent].dev_handle = dev_handle;
-		irq_table[ent].dev_ino = dev_ino;
-		irq_table[ent].in_use = 1;
-	}
+	return nr_ivec;
+}
+
+struct irq_handler_data {
+	union {
+		struct {
+			unsigned int dev_handle;
+			unsigned int dev_ino;
+		};
+		unsigned long sysino;
+	};
+	struct ino_bucket bucket;
+	unsigned long	iclr;
+	unsigned long	imap;
+};
+
+static inline unsigned int irq_data_to_handle(struct irq_data *data)
+{
+	struct irq_handler_data *ihd = data->handler_data;
+
+	return ihd->dev_handle;
+}
+
+static inline unsigned int irq_data_to_ino(struct irq_data *data)
+{
+	struct irq_handler_data *ihd = data->handler_data;
 
-	spin_unlock_irqrestore(&irq_alloc_lock, flags);
+	return ihd->dev_ino;
+}
+
+static inline unsigned long irq_data_to_sysino(struct irq_data *data)
+{
+	struct irq_handler_data *ihd = data->handler_data;
 
-	return ent;
+	return ihd->sysino;
 }
 
-#ifdef CONFIG_PCI_MSI
 void irq_free(unsigned int irq)
 {
-	unsigned long flags;
+	void *data = irq_get_handler_data(irq);
 
-	if (irq >= NR_IRQS)
-		return;
+	kfree(data);
+	irq_set_handler_data(irq, NULL);
+	irq_free_descs(irq, 1);
+}
 
-	spin_lock_irqsave(&irq_alloc_lock, flags);
+unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino)
+{
+	int irq;
 
-	irq_table[irq].in_use = 0;
+	irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL);
+	if (irq <= 0)
+		goto out;
 
-	spin_unlock_irqrestore(&irq_alloc_lock, flags);
+	return irq;
+out:
+	return 0;
+}
+
+static unsigned int cookie_exists(u32 devhandle, unsigned int devino)
+{
+	unsigned long hv_err, cookie;
+	struct ino_bucket *bucket;
+	unsigned int irq = 0U;
+
+	hv_err = sun4v_vintr_get_cookie(devhandle, devino, &cookie);
+	if (hv_err) {
+		pr_err("HV get cookie failed hv_err = %ld\n", hv_err);
+		goto out;
+	}
+
+	if (cookie & ((1UL << 63UL))) {
+		cookie = ~cookie;
+		bucket = (struct ino_bucket *) __va(cookie);
+		irq = bucket->__irq;
+	}
+out:
+	return irq;
+}
+
+static unsigned int sysino_exists(u32 devhandle, unsigned int devino)
+{
+	unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino);
+	struct ino_bucket *bucket;
+	unsigned int irq;
+
+	bucket = &ivector_table[sysino];
+	irq = bucket_get_irq(__pa(bucket));
+
+	return irq;
+}
+
+void ack_bad_irq(unsigned int irq)
+{
+	pr_crit("BAD IRQ ack %d\n", irq);
+}
+
+void irq_install_pre_handler(int irq,
+			     void (*func)(unsigned int, void *, void *),
+			     void *arg1, void *arg2)
+{
+	pr_warn("IRQ pre handler NOT supported.\n");
 }
-#endif
 
 /*
  * /proc/interrupts printing:
@@ -206,15 +345,6 @@ static unsigned int sun4u_compute_tid(unsigned long imap, unsigned long cpuid)
 	return tid;
 }
 
-struct irq_handler_data {
-	unsigned long	iclr;
-	unsigned long	imap;
-
-	void		(*pre_handler)(unsigned int, void *, void *);
-	void		*arg1;
-	void		*arg2;
-};
-
 #ifdef CONFIG_SMP
 static int irq_choose_cpu(unsigned int irq, const struct cpumask *affinity)
 {
@@ -316,8 +446,8 @@ static void sun4u_irq_eoi(struct irq_data *data)
 
 static void sun4v_irq_enable(struct irq_data *data)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
 	unsigned long cpuid = irq_choose_cpu(data->irq, data->affinity);
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_settarget(ino, cpuid);
@@ -337,8 +467,8 @@ static void sun4v_irq_enable(struct irq_data *data)
 static int sun4v_set_affinity(struct irq_data *data,
 			       const struct cpumask *mask, bool force)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
 	unsigned long cpuid = irq_choose_cpu(data->irq, mask);
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_settarget(ino, cpuid);
@@ -351,7 +481,7 @@ static int sun4v_set_affinity(struct irq_data *data,
 
 static void sun4v_irq_disable(struct irq_data *data)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_setenabled(ino, HV_INTR_DISABLED);
@@ -362,7 +492,7 @@ static void sun4v_irq_disable(struct irq_data *data)
 
 static void sun4v_irq_eoi(struct irq_data *data)
 {
-	unsigned int ino = irq_table[data->irq].dev_ino;
+	unsigned int ino = irq_data_to_sysino(data);
 	int err;
 
 	err = sun4v_intr_setstate(ino, HV_INTR_STATE_IDLE);
@@ -373,14 +503,13 @@ static void sun4v_irq_eoi(struct irq_data *data)
 
 static void sun4v_virq_enable(struct irq_data *data)
 {
-	unsigned long cpuid, dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
+	unsigned long cpuid;
 	int err;
 
 	cpuid = irq_choose_cpu(data->irq, data->affinity);
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
-
 	err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid);
 	if (err != HV_EOK)
 		printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): "
@@ -403,14 +532,13 @@ static void sun4v_virq_enable(struct irq_data *data)
 static int sun4v_virt_set_affinity(struct irq_data *data,
 				    const struct cpumask *mask, bool force)
 {
-	unsigned long cpuid, dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
+	unsigned long cpuid;
 	int err;
 
 	cpuid = irq_choose_cpu(data->irq, mask);
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
-
 	err = sun4v_vintr_set_target(dev_handle, dev_ino, cpuid);
 	if (err != HV_EOK)
 		printk(KERN_ERR "sun4v_vintr_set_target(%lx,%lx,%lu): "
@@ -422,11 +550,10 @@ static int sun4v_virt_set_affinity(struct irq_data *data,
 
 static void sun4v_virq_disable(struct irq_data *data)
 {
-	unsigned long dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
 	int err;
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
 
 	err = sun4v_vintr_set_valid(dev_handle, dev_ino,
 				    HV_INTR_DISABLED);
@@ -438,12 +565,10 @@ static void sun4v_virq_disable(struct irq_data *data)
 
 static void sun4v_virq_eoi(struct irq_data *data)
 {
-	unsigned long dev_handle, dev_ino;
+	unsigned long dev_handle = irq_data_to_handle(data);
+	unsigned long dev_ino = irq_data_to_ino(data);
 	int err;
 
-	dev_handle = irq_table[data->irq].dev_handle;
-	dev_ino = irq_table[data->irq].dev_ino;
-
 	err = sun4v_vintr_set_state(dev_handle, dev_ino,
 				    HV_INTR_STATE_IDLE);
 	if (err != HV_EOK)
@@ -479,31 +604,10 @@ static struct irq_chip sun4v_virq = {
 	.flags			= IRQCHIP_EOI_IF_HANDLED,
 };
 
-static void pre_flow_handler(struct irq_data *d)
-{
-	struct irq_handler_data *handler_data = irq_data_get_irq_handler_data(d);
-	unsigned int ino = irq_table[d->irq].dev_ino;
-
-	handler_data->pre_handler(ino, handler_data->arg1, handler_data->arg2);
-}
-
-void irq_install_pre_handler(int irq,
-			     void (*func)(unsigned int, void *, void *),
-			     void *arg1, void *arg2)
-{
-	struct irq_handler_data *handler_data = irq_get_handler_data(irq);
-
-	handler_data->pre_handler = func;
-	handler_data->arg1 = arg1;
-	handler_data->arg2 = arg2;
-
-	__irq_set_preflow_handler(irq, pre_flow_handler);
-}
-
 unsigned int build_irq(int inofixup, unsigned long iclr, unsigned long imap)
 {
-	struct ino_bucket *bucket;
 	struct irq_handler_data *handler_data;
+	struct ino_bucket *bucket;
 	unsigned int irq;
 	int ino;
 
@@ -537,119 +641,166 @@ out:
 	return irq;
 }
 
-static unsigned int sun4v_build_common(unsigned long sysino,
-				       struct irq_chip *chip)
+static unsigned int sun4v_build_common(u32 devhandle, unsigned int devino,
+		void (*handler_data_init)(struct irq_handler_data *data,
+		u32 devhandle, unsigned int devino),
+		struct irq_chip *chip)
 {
-	struct ino_bucket *bucket;
-	struct irq_handler_data *handler_data;
+	struct irq_handler_data *data;
 	unsigned int irq;
 
-	BUG_ON(tlb_type != hypervisor);
+	irq = irq_alloc(devhandle, devino);
+	if (!irq)
+		goto out;
 
-	bucket = &ivector_table[sysino];
-	irq = bucket_get_irq(__pa(bucket));
-	if (!irq) {
-		irq = irq_alloc(0, sysino);
-		bucket_set_irq(__pa(bucket), irq);
-		irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq,
-					      "IVEC");
+	data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC);
+	if (unlikely(!data)) {
+		pr_err("IRQ handler data allocation failed.\n");
+		irq_free(irq);
+		irq = 0;
+		goto out;
 	}
 
-	handler_data = irq_get_handler_data(irq);
-	if (unlikely(handler_data))
-		goto out;
+	irq_set_handler_data(irq, data);
+	handler_data_init(data, devhandle, devino);
+	irq_set_chip_and_handler_name(irq, chip, handle_fasteoi_irq, "IVEC");
+	data->imap = ~0UL;
+	data->iclr = ~0UL;
+out:
+	return irq;
+}
 
-	handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC);
-	if (unlikely(!handler_data)) {
-		prom_printf("IRQ: kzalloc(irq_handler_data) failed.\n");
-		prom_halt();
-	}
-	irq_set_handler_data(irq, handler_data);
+static unsigned long cookie_assign(unsigned int irq, u32 devhandle,
+		unsigned int devino)
+{
+	struct irq_handler_data *ihd = irq_get_handler_data(irq);
+	unsigned long hv_error, cookie;
 
-	/* Catch accidental accesses to these things.  IMAP/ICLR handling
-	 * is done by hypervisor calls on sun4v platforms, not by direct
-	 * register accesses.
+	/* handler_irq needs to find the irq. cookie is seen signed in
+	 * sun4v_dev_mondo and treated as a non ivector_table delivery.
 	 */
-	handler_data->imap = ~0UL;
-	handler_data->iclr = ~0UL;
+	ihd->bucket.__irq = irq;
+	cookie = ~__pa(&ihd->bucket);
 
-out:
-	return irq;
+	hv_error = sun4v_vintr_set_cookie(devhandle, devino, cookie);
+	if (hv_error)
+		pr_err("HV vintr set cookie failed = %ld\n", hv_error);
+
+	return hv_error;
 }
 
-unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino)
+static void cookie_handler_data(struct irq_handler_data *data,
+				u32 devhandle, unsigned int devino)
 {
-	unsigned long sysino = sun4v_devino_to_sysino(devhandle, devino);
+	data->dev_handle = devhandle;
+	data->dev_ino = devino;
+}
 
-	return sun4v_build_common(sysino, &sun4v_irq);
+static unsigned int cookie_build_irq(u32 devhandle, unsigned int devino,
+				     struct irq_chip *chip)
+{
+	unsigned long hv_error;
+	unsigned int irq;
+
+	irq = sun4v_build_common(devhandle, devino, cookie_handler_data, chip);
+
+	hv_error = cookie_assign(irq, devhandle, devino);
+	if (hv_error) {
+		irq_free(irq);
+		irq = 0;
+	}
+
+	return irq;
 }
 
-unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino)
+static unsigned int sun4v_build_cookie(u32 devhandle, unsigned int devino)
 {
-	struct irq_handler_data *handler_data;
-	unsigned long hv_err, cookie;
-	struct ino_bucket *bucket;
 	unsigned int irq;
 
-	bucket = kzalloc(sizeof(struct ino_bucket), GFP_ATOMIC);
-	if (unlikely(!bucket))
-		return 0;
+	irq = cookie_exists(devhandle, devino);
+	if (irq)
+		goto out;
 
-	/* The only reference we store to the IRQ bucket is
-	 * by physical address which kmemleak can't see, tell
-	 * it that this object explicitly is not a leak and
-	 * should be scanned.
-	 */
-	kmemleak_not_leak(bucket);
+	irq = cookie_build_irq(devhandle, devino, &sun4v_virq);
 
-	__flush_dcache_range((unsigned long) bucket,
-			     ((unsigned long) bucket +
-			      sizeof(struct ino_bucket)));
+out:
+	return irq;
+}
 
-	irq = irq_alloc(devhandle, devino);
+static void sysino_set_bucket(unsigned int irq)
+{
+	struct irq_handler_data *ihd = irq_get_handler_data(irq);
+	struct ino_bucket *bucket;
+	unsigned long sysino;
+
+	sysino = sun4v_devino_to_sysino(ihd->dev_handle, ihd->dev_ino);
+	BUG_ON(sysino >= nr_ivec);
+	bucket = &ivector_table[sysino];
 	bucket_set_irq(__pa(bucket), irq);
+}
 
-	irq_set_chip_and_handler_name(irq, &sun4v_virq, handle_fasteoi_irq,
-				      "IVEC");
+static void sysino_handler_data(struct irq_handler_data *data,
+				u32 devhandle, unsigned int devino)
+{
+	unsigned long sysino;
 
-	handler_data = kzalloc(sizeof(struct irq_handler_data), GFP_ATOMIC);
-	if (unlikely(!handler_data))
-		return 0;
+	sysino = sun4v_devino_to_sysino(devhandle, devino);
+	data->sysino = sysino;
+}
 
-	/* In order to make the LDC channel startup sequence easier,
-	 * especially wrt. locking, we do not let request_irq() enable
-	 * the interrupt.
-	 */
-	irq_set_status_flags(irq, IRQ_NOAUTOEN);
-	irq_set_handler_data(irq, handler_data);
+static unsigned int sysino_build_irq(u32 devhandle, unsigned int devino,
+				     struct irq_chip *chip)
+{
+	unsigned int irq;
 
-	/* Catch accidental accesses to these things.  IMAP/ICLR handling
-	 * is done by hypervisor calls on sun4v platforms, not by direct
-	 * register accesses.
-	 */
-	handler_data->imap = ~0UL;
-	handler_data->iclr = ~0UL;
+	irq = sun4v_build_common(devhandle, devino, sysino_handler_data, chip);
+	if (!irq)
+		goto out;
 
-	cookie = ~__pa(bucket);
-	hv_err = sun4v_vintr_set_cookie(devhandle, devino, cookie);
-	if (hv_err) {
-		prom_printf("IRQ: Fatal, cannot set cookie for [%x:%x] "
-			    "err=%lu\n", devhandle, devino, hv_err);
-		prom_halt();
-	}
+	sysino_set_bucket(irq);
+out:
+	return irq;
+}
 
+static int sun4v_build_sysino(u32 devhandle, unsigned int devino)
+{
+	int irq;
+
+	irq = sysino_exists(devhandle, devino);
+	if (irq)
+		goto out;
+
+	irq = sysino_build_irq(devhandle, devino, &sun4v_irq);
+out:
 	return irq;
 }
 
-void ack_bad_irq(unsigned int irq)
+unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino)
 {
-	unsigned int ino = irq_table[irq].dev_ino;
+	unsigned int irq;
 
-	if (!ino)
-		ino = 0xdeadbeef;
+	if (sun4v_cookie_only_virqs())
+		irq = sun4v_build_cookie(devhandle, devino);
+	else
+		irq = sun4v_build_sysino(devhandle, devino);
 
-	printk(KERN_CRIT "Unexpected IRQ from ino[%x] irq[%u]\n",
-	       ino, irq);
+	return irq;
+}
+
+unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino)
+{
+	int irq;
+
+	irq = cookie_build_irq(devhandle, devino, &sun4v_virq);
+	if (!irq)
+		goto out;
+
+	/* This is borrowed from the original function.
+	 */
+	irq_set_status_flags(irq, IRQ_NOAUTOEN);
+
+out:
+	return irq;
 }
 
 void *hardirq_stack[NR_CPUS];
@@ -720,9 +871,12 @@ void fixup_irqs(void)
 
 	for (irq = 0; irq < NR_IRQS; irq++) {
 		struct irq_desc *desc = irq_to_desc(irq);
-		struct irq_data *data = irq_desc_get_irq_data(desc);
+		struct irq_data *data;
 		unsigned long flags;
 
+		if (!desc)
+			continue;
+		data = irq_desc_get_irq_data(desc);
 		raw_spin_lock_irqsave(&desc->lock, flags);
 		if (desc->action && !irqd_is_per_cpu(data)) {
 			if (data->chip->irq_set_affinity)
@@ -922,16 +1076,22 @@ static struct irqaction timer_irq_action = {
 	.name = "timer",
 };
 
-/* Only invoked on boot processor. */
-void __init init_IRQ(void)
+static void __init irq_ivector_init(void)
 {
-	unsigned long size;
+	unsigned long size, order;
+	unsigned int ivecs;
 
-	map_prom_timers();
-	kill_prom_timer();
+	/* If we are doing cookie only VIRQs then we do not need the ivector
+	 * table to process interrupts.
+	 */
+	if (sun4v_cookie_only_virqs())
+		return;
 
-	size = sizeof(struct ino_bucket) * NUM_IVECS;
-	ivector_table = kzalloc(size, GFP_KERNEL);
+	ivecs = size_nr_ivec();
+	size = sizeof(struct ino_bucket) * ivecs;
+	order = get_order(size);
+	ivector_table = (struct ino_bucket *)
+		__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
 	if (!ivector_table) {
 		prom_printf("Fatal error, cannot allocate ivector_table\n");
 		prom_halt();
@@ -940,6 +1100,15 @@ void __init init_IRQ(void)
 			     ((unsigned long) ivector_table) + size);
 
 	ivector_table_pa = __pa(ivector_table);
+}
+
+/* Only invoked on boot processor.*/
+void __init init_IRQ(void)
+{
+	irq_init_hv();
+	irq_ivector_init();
+	map_prom_timers();
+	kill_prom_timer();
 
 	if (tlb_type == hypervisor)
 		sun4v_init_mondo_queues();
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index 98d712843413..cd83be527586 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -83,7 +83,7 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 	kcb->kprobe_orig_tnpc = kcb->prev_kprobe.orig_tnpc;
 	kcb->kprobe_orig_tstate_pil = kcb->prev_kprobe.orig_tstate_pil;
@@ -92,7 +92,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 				struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_orig_tnpc = regs->tnpc;
 	kcb->kprobe_orig_tstate_pil = (regs->tstate & TSTATE_PIL);
 }
@@ -155,7 +155,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				ret = 1;
 				goto no_kprobe;
 			}
-			p = __get_cpu_var(current_kprobe);
+			p = __this_cpu_read(current_kprobe);
 			if (p->break_handler && p->break_handler(p, regs))
 				goto ss_probe;
 		}
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index 605d49204580..ef0d8e9e1210 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -47,14 +47,6 @@ kvmap_itlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath)
 
 	TSB_LOCK_TAG(%g1, %g2, %g7)
-
-	/* Load and check PTE.  */
-	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
-	mov		1, %g7
-	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
-	brgez,a,pn	%g5, kvmap_itlb_longpath
-	 TSB_STORE(%g1, %g7)
-
 	TSB_WRITE(%g1, %g5, %g6)
 
 	/* fallthrough to TLB load */
@@ -118,6 +110,12 @@ kvmap_dtlb_obp:
 	ba,pt		%xcc, kvmap_dtlb_load
 	 nop
 
+kvmap_linear_early:
+	sethi		%hi(kern_linear_pte_xor), %g7
+	ldx		[%g7 + %lo(kern_linear_pte_xor)], %g2
+	ba,pt		%xcc, kvmap_dtlb_tsb4m_load
+	 xor		%g2, %g4, %g5
+
 	.align		32
 kvmap_dtlb_tsb4m_load:
 	TSB_LOCK_TAG(%g1, %g2, %g7)
@@ -146,105 +144,17 @@ kvmap_dtlb_4v:
 	/* Correct TAG_TARGET is already in %g6, check 4mb TSB.  */
 	KERN_TSB4M_LOOKUP_TL1(%g6, %g5, %g1, %g2, %g3, kvmap_dtlb_load)
 #endif
-	/* TSB entry address left in %g1, lookup linear PTE.
-	 * Must preserve %g1 and %g6 (TAG).
-	 */
-kvmap_dtlb_tsb4m_miss:
-	/* Clear the PAGE_OFFSET top virtual bits, shift
-	 * down to get PFN, and make sure PFN is in range.
-	 */
-661:	sllx		%g4, 0, %g5
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	/* Check to see if we know about valid memory at the 4MB
-	 * chunk this physical address will reside within.
+	/* Linear mapping TSB lookup failed.  Fallthrough to kernel
+	 * page table based lookup.
 	 */
-661:	srlx		%g5, MAX_PHYS_ADDRESS_BITS, %g2
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	brnz,pn		%g2, kvmap_dtlb_longpath
-	 nop
-
-	/* This unconditional branch and delay-slot nop gets patched
-	 * by the sethi sequence once the bitmap is properly setup.
-	 */
-	.globl		valid_addr_bitmap_insn
-valid_addr_bitmap_insn:
-	ba,pt		%xcc, 2f
-	 nop
-	.subsection	2
-	.globl		valid_addr_bitmap_patch
-valid_addr_bitmap_patch:
-	sethi		%hi(sparc64_valid_addr_bitmap), %g7
-	or		%g7, %lo(sparc64_valid_addr_bitmap), %g7
-	.previous
-
-661:	srlx		%g5, ILOG2_4MB, %g2
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	srlx		%g2, 6, %g5
-	and		%g2, 63, %g2
-	sllx		%g5, 3, %g5
-	ldx		[%g7 + %g5], %g5
-	mov		1, %g7
-	sllx		%g7, %g2, %g7
-	andcc		%g5, %g7, %g0
-	be,pn		%xcc, kvmap_dtlb_longpath
-
-2:	 sethi		%hi(kpte_linear_bitmap), %g2
-
-	/* Get the 256MB physical address index. */
-661:	sllx		%g4, 0, %g5
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	or		%g2, %lo(kpte_linear_bitmap), %g2
-
-661:	srlx		%g5, ILOG2_256MB, %g5
-	.section	.page_offset_shift_patch, "ax"
-	.word		661b
-	.previous
-
-	and		%g5, (32 - 1), %g7
-
-	/* Divide by 32 to get the offset into the bitmask.  */
-	srlx		%g5, 5, %g5
-	add		%g7, %g7, %g7
-	sllx		%g5, 3, %g5
-
-	/* kern_linear_pte_xor[(mask >> shift) & 3)] */
-	ldx		[%g2 + %g5], %g2
-	srlx		%g2, %g7, %g7
-	sethi		%hi(kern_linear_pte_xor), %g5
-	and		%g7, 3, %g7
-	or		%g5, %lo(kern_linear_pte_xor), %g5
-	sllx		%g7, 3, %g7
-	ldx		[%g5 + %g7], %g2
-
 	.globl		kvmap_linear_patch
 kvmap_linear_patch:
-	ba,pt		%xcc, kvmap_dtlb_tsb4m_load
-	 xor		%g2, %g4, %g5
+	ba,a,pt		%xcc, kvmap_linear_early
 
 kvmap_dtlb_vmalloc_addr:
 	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)
 
 	TSB_LOCK_TAG(%g1, %g2, %g7)
-
-	/* Load and check PTE.  */
-	ldxa		[%g5] ASI_PHYS_USE_EC, %g5
-	mov		1, %g7
-	sllx		%g7, TSB_TAG_INVALID_BIT, %g7
-	brgez,a,pn	%g5, kvmap_dtlb_longpath
-	 TSB_STORE(%g1, %g7)
-
 	TSB_WRITE(%g1, %g5, %g6)
 
 	/* fallthrough to TLB load */
@@ -276,13 +186,8 @@ kvmap_dtlb_load:
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 kvmap_vmemmap:
-	sub		%g4, %g5, %g5
-	srlx		%g5, ILOG2_4MB, %g5
-	sethi		%hi(vmemmap_table), %g1
-	sllx		%g5, 3, %g5
-	or		%g1, %lo(vmemmap_table), %g1
-	ba,pt		%xcc, kvmap_dtlb_load
-	 ldx		[%g1 + %g5], %g5
+	KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath)
+	ba,a,pt		%xcc, kvmap_dtlb_load
 #endif
 
 kvmap_dtlb_nonlinear:
@@ -294,8 +199,8 @@ kvmap_dtlb_nonlinear:
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 	/* Do not use the TSB for vmemmap.  */
-	mov		(VMEMMAP_BASE >> 40), %g5
-	sllx		%g5, 40, %g5
+	sethi		%hi(VMEMMAP_BASE), %g5
+	ldx		[%g5 + %lo(VMEMMAP_BASE)], %g5
 	cmp		%g4,%g5
 	bgeu,pn		%xcc, kvmap_vmemmap
 	 nop
@@ -307,8 +212,8 @@ kvmap_dtlb_tsbmiss:
 	sethi		%hi(MODULES_VADDR), %g5
 	cmp		%g4, %g5
 	blu,pn		%xcc, kvmap_dtlb_longpath
-	 mov		(VMALLOC_END >> 40), %g5
-	sllx		%g5, 40, %g5
+	 sethi		%hi(VMALLOC_END), %g5
+	ldx		[%g5 + %lo(VMALLOC_END)], %g5
 	cmp		%g4, %g5
 	bgeu,pn		%xcc, kvmap_dtlb_longpath
 	 nop
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 0af28b984695..4310332872d4 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1078,7 +1078,8 @@ static void ldc_iommu_release(struct ldc_channel *lp)
 
 struct ldc_channel *ldc_alloc(unsigned long id,
 			      const struct ldc_channel_config *cfgp,
-			      void *event_arg)
+			      void *event_arg,
+			      const char *name)
 {
 	struct ldc_channel *lp;
 	const struct ldc_mode_ops *mops;
@@ -1093,6 +1094,8 @@ struct ldc_channel *ldc_alloc(unsigned long id,
 	err = -EINVAL;
 	if (!cfgp)
 		goto out_err;
+	if (!name)
+		goto out_err;
 
 	switch (cfgp->mode) {
 	case LDC_MODE_RAW:
@@ -1185,6 +1188,21 @@ struct ldc_channel *ldc_alloc(unsigned long id,
 
 	INIT_HLIST_HEAD(&lp->mh_list);
 
+	snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name);
+	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
+
+	err = request_irq(lp->cfg.rx_irq, ldc_rx, 0,
+			  lp->rx_irq_name, lp);
+	if (err)
+		goto out_free_txq;
+
+	err = request_irq(lp->cfg.tx_irq, ldc_tx, 0,
+			  lp->tx_irq_name, lp);
+	if (err) {
+		free_irq(lp->cfg.rx_irq, lp);
+		goto out_free_txq;
+	}
+
 	return lp;
 
 out_free_txq:
@@ -1237,31 +1255,14 @@ EXPORT_SYMBOL(ldc_free);
  * state.  This does not initiate a handshake, ldc_connect() does
  * that.
  */
-int ldc_bind(struct ldc_channel *lp, const char *name)
+int ldc_bind(struct ldc_channel *lp)
 {
 	unsigned long hv_err, flags;
 	int err = -EINVAL;
 
-	if (!name ||
-	    (lp->state != LDC_STATE_INIT))
+	if (lp->state != LDC_STATE_INIT)
 		return -EINVAL;
 
-	snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name);
-	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
-
-	err = request_irq(lp->cfg.rx_irq, ldc_rx, 0,
-			  lp->rx_irq_name, lp);
-	if (err)
-		return err;
-
-	err = request_irq(lp->cfg.tx_irq, ldc_tx, 0,
-			  lp->tx_irq_name, lp);
-	if (err) {
-		free_irq(lp->cfg.rx_irq, lp);
-		return err;
-	}
-
-
 	spin_lock_irqsave(&lp->lock, flags);
 
 	enable_irq(lp->cfg.rx_irq);
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index 683c4af999de..9bbb8f2bbfcc 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -37,6 +37,7 @@ unsigned long amba_system_id;
 static DEFINE_SPINLOCK(leon_irq_lock);
 
 static unsigned long leon3_gptimer_idx; /* Timer Index (0..6) within Timer Core */
+static unsigned long leon3_gptimer_ackmask; /* For clearing pending bit */
 unsigned long leon3_gptimer_irq; /* interrupt controller irq number */
 unsigned int sparc_leon_eirq;
 #define LEON_IMASK(cpu) (&leon3_irqctrl_regs->mask[cpu])
@@ -260,11 +261,19 @@ void leon_update_virq_handling(unsigned int virq,
 
 static u32 leon_cycles_offset(void)
 {
-	u32 rld, val, off;
+	u32 rld, val, ctrl, off;
+
 	rld = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].rld);
 	val = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].val);
-	off = rld - val;
-	return rld - val;
+	ctrl = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl);
+	if (LEON3_GPTIMER_CTRL_ISPENDING(ctrl)) {
+		val = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].val);
+		off = 2 * rld - val;
+	} else {
+		off = rld - val;
+	}
+
+	return off;
 }
 
 #ifdef CONFIG_SMP
@@ -302,6 +311,7 @@ void __init leon_init_timers(void)
 	int ampopts;
 	int err;
 	u32 config;
+	u32 ctrl;
 
 	sparc_config.get_cycles_offset = leon_cycles_offset;
 	sparc_config.cs_period = 1000000 / HZ;
@@ -374,6 +384,16 @@ void __init leon_init_timers(void)
 	if (!(leon3_gptimer_regs && leon3_irqctrl_regs && leon3_gptimer_irq))
 		goto bad;
 
+	ctrl = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl);
+	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl,
+			      ctrl | LEON3_GPTIMER_CTRL_PENDING);
+	ctrl = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl);
+
+	if ((ctrl & LEON3_GPTIMER_CTRL_PENDING) != 0)
+		leon3_gptimer_ackmask = ~LEON3_GPTIMER_CTRL_PENDING;
+	else
+		leon3_gptimer_ackmask = ~0;
+
 	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].val, 0);
 	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].rld,
 				(((1000000 / HZ) - 1)));
@@ -452,6 +472,11 @@ bad:
 
 static void leon_clear_clock_irq(void)
 {
+	u32 ctrl;
+
+	ctrl = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl);
+	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl,
+			      ctrl & leon3_gptimer_ackmask);
 }
 
 static void leon_load_profile_irq(int cpu, unsigned int limit)
diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c
index 018ef11f57df..ea2bad306f93 100644
--- a/arch/sparc/kernel/leon_smp.c
+++ b/arch/sparc/kernel/leon_smp.c
@@ -343,7 +343,7 @@ static void leon_ipi_resched(int cpu)
 
 void leonsmp_ipi_interrupt(void)
 {
-	struct leon_ipi_work *work = &__get_cpu_var(leon_ipi_work);
+	struct leon_ipi_work *work = this_cpu_ptr(&leon_ipi_work);
 
 	if (work->single) {
 		work->single = 0;
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index 5b1151dcba13..a9973bb4a1b2 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -100,20 +100,20 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
 		pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
 
 	sum = local_cpu_data().irq0_irqs;
-	if (__get_cpu_var(nmi_touch)) {
-		__get_cpu_var(nmi_touch) = 0;
+	if (__this_cpu_read(nmi_touch)) {
+		__this_cpu_write(nmi_touch, 0);
 		touched = 1;
 	}
-	if (!touched && __get_cpu_var(last_irq_sum) == sum) {
+	if (!touched && __this_cpu_read(last_irq_sum) == sum) {
 		__this_cpu_inc(alert_counter);
 		if (__this_cpu_read(alert_counter) == 30 * nmi_hz)
 			die_nmi("BUG: NMI Watchdog detected LOCKUP",
 				regs, panic_on_timeout);
 	} else {
-		__get_cpu_var(last_irq_sum) = sum;
+		__this_cpu_write(last_irq_sum, sum);
 		__this_cpu_write(alert_counter, 0);
 	}
-	if (__get_cpu_var(wd_enabled)) {
+	if (__this_cpu_read(wd_enabled)) {
 		pcr_ops->write_pic(0, pcr_ops->nmi_picl_value(nmi_hz));
 		pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_enable);
 	}
@@ -154,7 +154,7 @@ static void report_broken_nmi(int cpu, int *prev_nmi_count)
 void stop_nmi_watchdog(void *unused)
 {
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
-	__get_cpu_var(wd_enabled) = 0;
+	__this_cpu_write(wd_enabled, 0);
 	atomic_dec(&nmi_active);
 }
 
@@ -207,7 +207,7 @@ error:
 
 void start_nmi_watchdog(void *unused)
 {
-	__get_cpu_var(wd_enabled) = 1;
+	__this_cpu_write(wd_enabled, 1);
 	atomic_inc(&nmi_active);
 
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
@@ -218,7 +218,7 @@ void start_nmi_watchdog(void *unused)
 
 static void nmi_adjust_hz_one(void *unused)
 {
-	if (!__get_cpu_var(wd_enabled))
+	if (!__this_cpu_read(wd_enabled))
 		return;
 
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index d07f6b29aed8..49d33b178793 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -48,7 +48,7 @@ static int iommu_batch_initialized;
 /* Interrupts must be disabled.  */
 static inline void iommu_batch_start(struct device *dev, unsigned long prot, unsigned long entry)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	p->dev		= dev;
 	p->prot		= prot;
@@ -94,7 +94,7 @@ static long iommu_batch_flush(struct iommu_batch *p)
 
 static inline void iommu_batch_new_entry(unsigned long entry)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	if (p->entry + p->npages == entry)
 		return;
@@ -106,7 +106,7 @@ static inline void iommu_batch_new_entry(unsigned long entry)
 /* Interrupts must be disabled.  */
 static inline long iommu_batch_add(u64 phys_page)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	BUG_ON(p->npages >= PGLIST_NENTS);
 
@@ -120,7 +120,7 @@ static inline long iommu_batch_add(u64 phys_page)
 /* Interrupts must be disabled.  */
 static inline long iommu_batch_end(void)
 {
-	struct iommu_batch *p = &__get_cpu_var(iommu_batch);
+	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	BUG_ON(p->npages >= PGLIST_NENTS);
 
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index 269af58497aa..7e967c8018c8 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -191,12 +191,41 @@ static const struct pcr_ops n4_pcr_ops = {
 	.pcr_nmi_disable	= PCR_N4_PICNPT,
 };
 
+static u64 n5_pcr_read(unsigned long reg_num)
+{
+	unsigned long val;
+
+	(void) sun4v_t5_get_perfreg(reg_num, &val);
+
+	return val;
+}
+
+static void n5_pcr_write(unsigned long reg_num, u64 val)
+{
+	(void) sun4v_t5_set_perfreg(reg_num, val);
+}
+
+static const struct pcr_ops n5_pcr_ops = {
+	.read_pcr		= n5_pcr_read,
+	.write_pcr		= n5_pcr_write,
+	.read_pic		= n4_pic_read,
+	.write_pic		= n4_pic_write,
+	.nmi_picl_value		= n4_picl_value,
+	.pcr_nmi_enable		= (PCR_N4_PICNPT | PCR_N4_STRACE |
+				   PCR_N4_UTRACE | PCR_N4_TOE |
+				   (26 << PCR_N4_SL_SHIFT)),
+	.pcr_nmi_disable	= PCR_N4_PICNPT,
+};
+
+
 static unsigned long perf_hsvc_group;
 static unsigned long perf_hsvc_major;
 static unsigned long perf_hsvc_minor;
 
 static int __init register_perf_hsvc(void)
 {
+	unsigned long hverror;
+
 	if (tlb_type == hypervisor) {
 		switch (sun4v_chip_type) {
 		case SUN4V_CHIP_NIAGARA1:
@@ -215,6 +244,10 @@ static int __init register_perf_hsvc(void)
 			perf_hsvc_group = HV_GRP_VT_CPU;
 			break;
 
+		case SUN4V_CHIP_NIAGARA5:
+			perf_hsvc_group = HV_GRP_T5_CPU;
+			break;
+
 		default:
 			return -ENODEV;
 		}
@@ -222,10 +255,12 @@ static int __init register_perf_hsvc(void)
 
 		perf_hsvc_major = 1;
 		perf_hsvc_minor = 0;
-		if (sun4v_hvapi_register(perf_hsvc_group,
-					 perf_hsvc_major,
-					 &perf_hsvc_minor)) {
-			printk("perfmon: Could not register hvapi.\n");
+		hverror = sun4v_hvapi_register(perf_hsvc_group,
+					       perf_hsvc_major,
+					       &perf_hsvc_minor);
+		if (hverror) {
+			pr_err("perfmon: Could not register hvapi(0x%lx).\n",
+			       hverror);
 			return -ENODEV;
 		}
 	}
@@ -254,6 +289,10 @@ static int __init setup_sun4v_pcr_ops(void)
 		pcr_ops = &n4_pcr_ops;
 		break;
 
+	case SUN4V_CHIP_NIAGARA5:
+		pcr_ops = &n5_pcr_ops;
+		break;
+
 	default:
 		ret = -ENODEV;
 		break;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index d35c490a91cb..46a5e4508752 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1013,7 +1013,7 @@ static void update_pcrs_for_enable(struct cpu_hw_events *cpuc)
 
 static void sparc_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	if (cpuc->enabled)
@@ -1031,7 +1031,7 @@ static void sparc_pmu_enable(struct pmu *pmu)
 
 static void sparc_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	if (!cpuc->enabled)
@@ -1065,7 +1065,7 @@ static int active_event_index(struct cpu_hw_events *cpuc,
 
 static void sparc_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 
 	if (flags & PERF_EF_RELOAD) {
@@ -1080,7 +1080,7 @@ static void sparc_pmu_start(struct perf_event *event, int flags)
 
 static void sparc_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 
 	if (!(event->hw.state & PERF_HES_STOPPED)) {
@@ -1096,7 +1096,7 @@ static void sparc_pmu_stop(struct perf_event *event, int flags)
 
 static void sparc_pmu_del(struct perf_event *event, int _flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long flags;
 	int i;
 
@@ -1133,7 +1133,7 @@ static void sparc_pmu_del(struct perf_event *event, int _flags)
 
 static void sparc_pmu_read(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = active_event_index(cpuc, event);
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -1145,7 +1145,7 @@ static DEFINE_MUTEX(pmc_grab_mutex);
 
 static void perf_stop_nmi_watchdog(void *unused)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	stop_nmi_watchdog(NULL);
@@ -1356,7 +1356,7 @@ static int collect_events(struct perf_event *group, int max_count,
 
 static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int n0, ret = -EAGAIN;
 	unsigned long flags;
 
@@ -1498,7 +1498,7 @@ static int sparc_pmu_event_init(struct perf_event *event)
  */
 static void sparc_pmu_start_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
@@ -1511,7 +1511,7 @@ static void sparc_pmu_start_txn(struct pmu *pmu)
  */
 static void sparc_pmu_cancel_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
 	perf_pmu_enable(pmu);
@@ -1524,13 +1524,13 @@ static void sparc_pmu_cancel_txn(struct pmu *pmu)
  */
 static int sparc_pmu_commit_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int n;
 
 	if (!sparc_pmu)
 		return -EINVAL;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 	n = cpuc->n_events;
 	if (check_excludes(cpuc->event, 0, n))
 		return -EINVAL;
@@ -1601,7 +1601,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 
 	regs = args->regs;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/* If the PMU has the TOE IRQ enable bits, we need to do a
 	 * dummy write to the %pcr to clear the overflow bits and thus
@@ -1662,7 +1662,8 @@ static bool __init supported_pmu(void)
 		sparc_pmu = &niagara2_pmu;
 		return true;
 	}
-	if (!strcmp(sparc_pmu_type, "niagara4")) {
+	if (!strcmp(sparc_pmu_type, "niagara4") ||
+	    !strcmp(sparc_pmu_type, "niagara5")) {
 		sparc_pmu = &niagara4_pmu;
 		return true;
 	}
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 3fdb455e3318..e629b8377587 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -141,21 +141,9 @@ static void __init boot_flags_init(char *commands)
 				process_switch(*commands++);
 			continue;
 		}
-		if (!strncmp(commands, "mem=", 4)) {
-			/*
-			 * "mem=XXX[kKmM]" overrides the PROM-reported
-			 * memory size.
-			 */
-			cmdline_memory_size = simple_strtoul(commands + 4,
-							     &commands, 0);
-			if (*commands == 'K' || *commands == 'k') {
-				cmdline_memory_size <<= 10;
-				commands++;
-			} else if (*commands=='M' || *commands=='m') {
-				cmdline_memory_size <<= 20;
-				commands++;
-			}
-		}
+		if (!strncmp(commands, "mem=", 4))
+			cmdline_memory_size = memparse(commands + 4, &commands);
+
 		while (*commands && *commands != ' ')
 			commands++;
 	}
@@ -500,12 +488,16 @@ static void __init init_sparc64_elf_hwcap(void)
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_BLKINIT;
 		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_N2;
 	}
@@ -533,6 +525,8 @@ static void __init init_sparc64_elf_hwcap(void)
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
 					AV_SPARC_ASI_BLK_INIT |
@@ -540,6 +534,8 @@ static void __init init_sparc64_elf_hwcap(void)
 			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |
 					AV_SPARC_FMAF);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index f7ba87543e5f..302c476413d5 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1138,7 +1138,7 @@ static unsigned long penguins_are_doing_time;
 
 void smp_capture(void)
 {
-	int result = atomic_add_ret(1, &smp_capture_depth);
+	int result = atomic_add_return(1, &smp_capture_depth);
 
 	if (result == 1) {
 		int ncpus = num_online_cpus();
@@ -1467,6 +1467,13 @@ static void __init pcpu_populate_pte(unsigned long addr)
 	pud_t *pud;
 	pmd_t *pmd;
 
+	if (pgd_none(*pgd)) {
+		pud_t *new;
+
+		new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+		pgd_populate(&init_mm, pgd, new);
+	}
+
 	pud = pud_offset(pgd, addr);
 	if (pud_none(*pud)) {
 		pmd_t *new;
diff --git a/arch/sparc/kernel/sun4d_smp.c b/arch/sparc/kernel/sun4d_smp.c
index d5c319553fd0..9d98e5002a09 100644
--- a/arch/sparc/kernel/sun4d_smp.c
+++ b/arch/sparc/kernel/sun4d_smp.c
@@ -204,7 +204,7 @@ static void __init smp4d_ipi_init(void)
 
 void sun4d_ipi_interrupt(void)
 {
-	struct sun4d_ipi_work *work = &__get_cpu_var(sun4d_ipi_work);
+	struct sun4d_ipi_work *work = this_cpu_ptr(&sun4d_ipi_work);
 
 	if (work->single) {
 		work->single = 0;
diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S
index e0c09bf85610..6179e19bc9b9 100644
--- a/arch/sparc/kernel/sun4v_tlb_miss.S
+++ b/arch/sparc/kernel/sun4v_tlb_miss.S
@@ -195,6 +195,11 @@ sun4v_tsb_miss_common:
 	 ldx	[%g2 + TRAP_PER_CPU_PGD_PADDR], %g7
 
 sun4v_itlb_error:
+	rdpr	%tl, %g1
+	cmp	%g1, 1
+	ble,pt	%icc, sun4v_bad_ra
+	 or	%g0, FAULT_CODE_BAD_RA | FAULT_CODE_ITLB, %g1
+
 	sethi	%hi(sun4v_err_itlb_vaddr), %g1
 	stx	%g4, [%g1 + %lo(sun4v_err_itlb_vaddr)]
 	sethi	%hi(sun4v_err_itlb_ctx), %g1
@@ -206,15 +211,10 @@ sun4v_itlb_error:
 	sethi	%hi(sun4v_err_itlb_error), %g1
 	stx	%o0, [%g1 + %lo(sun4v_err_itlb_error)]
 
+	sethi	%hi(1f), %g7
 	rdpr	%tl, %g4
-	cmp	%g4, 1
-	ble,pt	%icc, 1f
-	 sethi	%hi(2f), %g7
 	ba,pt	%xcc, etraptl1
-	 or	%g7, %lo(2f), %g7
-
-1:	ba,pt	%xcc, etrap
-2:	 or	%g7, %lo(2b), %g7
+1:	 or	%g7, %lo(1f), %g7
 	mov	%l4, %o1
 	call	sun4v_itlb_error_report
 	 add	%sp, PTREGS_OFF, %o0
@@ -222,6 +222,11 @@ sun4v_itlb_error:
 	/* NOTREACHED */
 
 sun4v_dtlb_error:
+	rdpr	%tl, %g1
+	cmp	%g1, 1
+	ble,pt	%icc, sun4v_bad_ra
+	 or	%g0, FAULT_CODE_BAD_RA | FAULT_CODE_DTLB, %g1
+
 	sethi	%hi(sun4v_err_dtlb_vaddr), %g1
 	stx	%g4, [%g1 + %lo(sun4v_err_dtlb_vaddr)]
 	sethi	%hi(sun4v_err_dtlb_ctx), %g1
@@ -233,21 +238,23 @@ sun4v_dtlb_error:
 	sethi	%hi(sun4v_err_dtlb_error), %g1
 	stx	%o0, [%g1 + %lo(sun4v_err_dtlb_error)]
 
+	sethi	%hi(1f), %g7
 	rdpr	%tl, %g4
-	cmp	%g4, 1
-	ble,pt	%icc, 1f
-	 sethi	%hi(2f), %g7
 	ba,pt	%xcc, etraptl1
-	 or	%g7, %lo(2f), %g7
-
-1:	ba,pt	%xcc, etrap
-2:	 or	%g7, %lo(2b), %g7
+1:	 or	%g7, %lo(1f), %g7
 	mov	%l4, %o1
 	call	sun4v_dtlb_error_report
 	 add	%sp, PTREGS_OFF, %o0
 
 	/* NOTREACHED */
 
+sun4v_bad_ra:
+	or	%g0, %g4, %g5
+	ba,pt	%xcc, sparc64_realfault_common
+	 or	%g1, %g0, %g4
+
+	/* NOTREACHED */
+
 	/* Instruction Access Exception, tl0. */
 sun4v_iacc:
 	ldxa	[%g0] ASI_SCRATCHPAD, %g2
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 3fddf64c7fc6..59da0c3ea788 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -765,7 +765,7 @@ void setup_sparc64_timer(void)
 			     : /* no outputs */
 			     : "r" (pstate));
 
-	sevt = &__get_cpu_var(sparc64_events);
+	sevt = this_cpu_ptr(&sparc64_events);
 
 	memcpy(sevt, &sparc64_clockevent, sizeof(*sevt));
 	sevt->cpumask = cpumask_of(smp_processor_id());
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index fb6640ec8557..981a769b9558 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2104,6 +2104,11 @@ void sun4v_nonresum_overflow(struct pt_regs *regs)
 	atomic_inc(&sun4v_nonresum_oflow_cnt);
 }
 
+static void sun4v_tlb_error(struct pt_regs *regs)
+{
+	die_if_kernel("TLB/TSB error", regs);
+}
+
 unsigned long sun4v_err_itlb_vaddr;
 unsigned long sun4v_err_itlb_ctx;
 unsigned long sun4v_err_itlb_pte;
@@ -2111,8 +2116,7 @@ unsigned long sun4v_err_itlb_error;
 
 void sun4v_itlb_error_report(struct pt_regs *regs, int tl)
 {
-	if (tl > 1)
-		dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
+	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
 
 	printk(KERN_EMERG "SUN4V-ITLB: Error at TPC[%lx], tl %d\n",
 	       regs->tpc, tl);
@@ -2125,7 +2129,7 @@ void sun4v_itlb_error_report(struct pt_regs *regs, int tl)
 	       sun4v_err_itlb_vaddr, sun4v_err_itlb_ctx,
 	       sun4v_err_itlb_pte, sun4v_err_itlb_error);
 
-	prom_halt();
+	sun4v_tlb_error(regs);
 }
 
 unsigned long sun4v_err_dtlb_vaddr;
@@ -2135,8 +2139,7 @@ unsigned long sun4v_err_dtlb_error;
 
 void sun4v_dtlb_error_report(struct pt_regs *regs, int tl)
 {
-	if (tl > 1)
-		dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
+	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
 
 	printk(KERN_EMERG "SUN4V-DTLB: Error at TPC[%lx], tl %d\n",
 	       regs->tpc, tl);
@@ -2149,7 +2152,7 @@ void sun4v_dtlb_error_report(struct pt_regs *regs, int tl)
 	       sun4v_err_dtlb_vaddr, sun4v_err_dtlb_ctx,
 	       sun4v_err_dtlb_pte, sun4v_err_dtlb_error);
 
-	prom_halt();
+	sun4v_tlb_error(regs);
 }
 
 void hypervisor_tlbop_error(unsigned long err, unsigned long op)
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index 8647fcc5ca6c..cb5789c9f961 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -180,8 +180,10 @@ static void vio_fill_channel_info(struct mdesc_handle *hp, u64 mp,
 			vdev->tx_irq = sun4v_build_virq(cdev_cfg_handle, *irq);
 
 		irq = mdesc_get_property(hp, target, "rx-ino", NULL);
-		if (irq)
+		if (irq) {
 			vdev->rx_irq = sun4v_build_virq(cdev_cfg_handle, *irq);
+			vdev->rx_ino = *irq;
+		}
 
 		chan_id = mdesc_get_property(hp, target, "id", NULL);
 		if (chan_id)
@@ -189,6 +191,15 @@ static void vio_fill_channel_info(struct mdesc_handle *hp, u64 mp,
 	}
 }
 
+int vio_set_intr(unsigned long dev_ino, int state)
+{
+	int err;
+
+	err = sun4v_vintr_set_valid(cdev_cfg_handle, dev_ino, state);
+	return err;
+}
+EXPORT_SYMBOL(vio_set_intr);
+
 static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
 				      struct device *parent)
 {
diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c
index 7ef081a185b1..526fcb5d8ce9 100644
--- a/arch/sparc/kernel/viohs.c
+++ b/arch/sparc/kernel/viohs.c
@@ -724,7 +724,7 @@ int vio_ldc_alloc(struct vio_driver_state *vio,
 	cfg.tx_irq = vio->vdev->tx_irq;
 	cfg.rx_irq = vio->vdev->rx_irq;
 
-	lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg);
+	lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg, vio->name);
 	if (IS_ERR(lp))
 		return PTR_ERR(lp);
 
@@ -756,7 +756,7 @@ void vio_port_up(struct vio_driver_state *vio)
 
 	err = 0;
 	if (state == LDC_STATE_INIT) {
-		err = ldc_bind(vio->lp, vio->name);
+		err = ldc_bind(vio->lp);
 		if (err)
 			printk(KERN_WARNING "%s: Port %lu bind failed, "
 			       "err=%d\n",
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 932ff90fd760..09243057cb0b 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -35,8 +35,9 @@ jiffies = jiffies_64;
 
 SECTIONS
 {
-	/* swapper_low_pmd_dir is sparc64 only */
-	swapper_low_pmd_dir = 0x0000000000402000;
+#ifdef CONFIG_SPARC64
+	swapper_pg_dir = 0x0000000000402000;
+#endif
 	. = INITIAL_ADDRESS;
 	.text TEXTSTART :
 	{
@@ -122,11 +123,6 @@ SECTIONS
 		*(.swapper_4m_tsb_phys_patch)
 		__swapper_4m_tsb_phys_patch_end = .;
 	}
-	.page_offset_shift_patch : {
-		__page_offset_shift_patch = .;
-		*(.page_offset_shift_patch)
-		__page_offset_shift_patch_end = .;
-	}
 	.popc_3insn_patch : {
 		__popc_3insn_patch = .;
 		*(.popc_3insn_patch)
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 9cf2ee01cee3..140527a20e7d 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -41,6 +41,10 @@
 #endif
 #endif
 
+#if !defined(EX_LD) && !defined(EX_ST)
+#define NON_USER_COPY
+#endif
+
 #ifndef EX_LD
 #define EX_LD(x)	x
 #endif
@@ -197,9 +201,13 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 mov		EX_RETVAL(%o3), %o0
 
 .Llarge_src_unaligned:
+#ifdef NON_USER_COPY
+	VISEntryHalfFast(.Lmedium_vis_entry_fail)
+#else
+	VISEntryHalf
+#endif
 	andn		%o2, 0x3f, %o4
 	sub		%o2, %o4, %o2
-	VISEntryHalf
 	alignaddr	%o1, %g0, %g1
 	add		%o1, %o4, %o1
 	EX_LD(LOAD(ldd, %g1 + 0x00, %f0))
@@ -240,6 +248,10 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 nop
 	ba,a,pt		%icc, .Lmedium_unaligned
 
+#ifdef NON_USER_COPY
+.Lmedium_vis_entry_fail:
+	 or		%o0, %o1, %g2
+#endif
 .Lmedium:
 	LOAD(prefetch, %o1 + 0x40, #n_reads_strong)
 	andcc		%g2, 0x7, %g0
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 1d32b54089aa..a7c418ac26af 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -27,18 +27,23 @@ static DEFINE_SPINLOCK(dummy);
 
 #endif /* SMP */
 
-int __atomic_add_return(int i, atomic_t *v)
-{
-	int ret;
-	unsigned long flags;
-	spin_lock_irqsave(ATOMIC_HASH(v), flags);
-
-	ret = (v->counter += i);
-
-	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
-	return ret;
-}
-EXPORT_SYMBOL(__atomic_add_return);
+#define ATOMIC_OP(op, cop)						\
+int atomic_##op##_return(int i, atomic_t *v)				\
+{									\
+	int ret;							\
+	unsigned long flags;						\
+	spin_lock_irqsave(ATOMIC_HASH(v), flags);			\
+									\
+	ret = (v->counter cop i);					\
+									\
+	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);			\
+	return ret;							\
+}									\
+EXPORT_SYMBOL(atomic_##op##_return);
+
+ATOMIC_OP(add, +=)
+
+#undef ATOMIC_OP
 
 int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
diff --git a/arch/sparc/lib/atomic_64.S b/arch/sparc/lib/atomic_64.S
index 85c233d0a340..05dac43907d1 100644
--- a/arch/sparc/lib/atomic_64.S
+++ b/arch/sparc/lib/atomic_64.S
@@ -14,109 +14,80 @@
 	 * memory barriers, and a second which returns
 	 * a value and does the barriers.
 	 */
-ENTRY(atomic_add) /* %o0 = increment, %o1 = atomic_ptr */
-	BACKOFF_SETUP(%o2)
-1:	lduw	[%o1], %g1
-	add	%g1, %o0, %g7
-	cas	[%o1], %g1, %g7
-	cmp	%g1, %g7
-	bne,pn	%icc, BACKOFF_LABEL(2f, 1b)
-	 nop
-	retl
-	 nop
-2:	BACKOFF_SPIN(%o2, %o3, 1b)
-ENDPROC(atomic_add)
 
-ENTRY(atomic_sub) /* %o0 = decrement, %o1 = atomic_ptr */
-	BACKOFF_SETUP(%o2)
-1:	lduw	[%o1], %g1
-	sub	%g1, %o0, %g7
-	cas	[%o1], %g1, %g7
-	cmp	%g1, %g7
-	bne,pn	%icc, BACKOFF_LABEL(2f, 1b)
-	 nop
-	retl
-	 nop
-2:	BACKOFF_SPIN(%o2, %o3, 1b)
-ENDPROC(atomic_sub)
+#define ATOMIC_OP(op)							\
+ENTRY(atomic_##op) /* %o0 = increment, %o1 = atomic_ptr */		\
+	BACKOFF_SETUP(%o2);						\
+1:	lduw	[%o1], %g1;						\
+	op	%g1, %o0, %g7;						\
+	cas	[%o1], %g1, %g7;					\
+	cmp	%g1, %g7;						\
+	bne,pn	%icc, BACKOFF_LABEL(2f, 1b);				\
+	 nop;								\
+	retl;								\
+	 nop;								\
+2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
+ENDPROC(atomic_##op);							\
 
-ENTRY(atomic_add_ret) /* %o0 = increment, %o1 = atomic_ptr */
-	BACKOFF_SETUP(%o2)
-1:	lduw	[%o1], %g1
-	add	%g1, %o0, %g7
-	cas	[%o1], %g1, %g7
-	cmp	%g1, %g7
-	bne,pn	%icc, BACKOFF_LABEL(2f, 1b)
-	 add	%g1, %o0, %g1
-	retl
-	 sra	%g1, 0, %o0
-2:	BACKOFF_SPIN(%o2, %o3, 1b)
-ENDPROC(atomic_add_ret)
+#define ATOMIC_OP_RETURN(op)						\
+ENTRY(atomic_##op##_return) /* %o0 = increment, %o1 = atomic_ptr */	\
+	BACKOFF_SETUP(%o2);						\
+1:	lduw	[%o1], %g1;						\
+	op	%g1, %o0, %g7;						\
+	cas	[%o1], %g1, %g7;					\
+	cmp	%g1, %g7;						\
+	bne,pn	%icc, BACKOFF_LABEL(2f, 1b);				\
+	 op	%g1, %o0, %g1;						\
+	retl;								\
+	 sra	%g1, 0, %o0;						\
+2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
+ENDPROC(atomic_##op##_return);
 
-ENTRY(atomic_sub_ret) /* %o0 = decrement, %o1 = atomic_ptr */
-	BACKOFF_SETUP(%o2)
-1:	lduw	[%o1], %g1
-	sub	%g1, %o0, %g7
-	cas	[%o1], %g1, %g7
-	cmp	%g1, %g7
-	bne,pn	%icc, BACKOFF_LABEL(2f, 1b)
-	 sub	%g1, %o0, %g1
-	retl
-	 sra	%g1, 0, %o0
-2:	BACKOFF_SPIN(%o2, %o3, 1b)
-ENDPROC(atomic_sub_ret)
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
 
-ENTRY(atomic64_add) /* %o0 = increment, %o1 = atomic_ptr */
-	BACKOFF_SETUP(%o2)
-1:	ldx	[%o1], %g1
-	add	%g1, %o0, %g7
-	casx	[%o1], %g1, %g7
-	cmp	%g1, %g7
-	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b)
-	 nop
-	retl
-	 nop
-2:	BACKOFF_SPIN(%o2, %o3, 1b)
-ENDPROC(atomic64_add)
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
 
-ENTRY(atomic64_sub) /* %o0 = decrement, %o1 = atomic_ptr */
-	BACKOFF_SETUP(%o2)
-1:	ldx	[%o1], %g1
-	sub	%g1, %o0, %g7
-	casx	[%o1], %g1, %g7
-	cmp	%g1, %g7
-	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b)
-	 nop
-	retl
-	 nop
-2:	BACKOFF_SPIN(%o2, %o3, 1b)
-ENDPROC(atomic64_sub)
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
-ENTRY(atomic64_add_ret) /* %o0 = increment, %o1 = atomic_ptr */
-	BACKOFF_SETUP(%o2)
-1:	ldx	[%o1], %g1
-	add	%g1, %o0, %g7
-	casx	[%o1], %g1, %g7
-	cmp	%g1, %g7
-	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b)
-	 nop
-	retl
-	 add	%g1, %o0, %o0
-2:	BACKOFF_SPIN(%o2, %o3, 1b)
-ENDPROC(atomic64_add_ret)
+#define ATOMIC64_OP(op)							\
+ENTRY(atomic64_##op) /* %o0 = increment, %o1 = atomic_ptr */		\
+	BACKOFF_SETUP(%o2);						\
+1:	ldx	[%o1], %g1;						\
+	op	%g1, %o0, %g7;						\
+	casx	[%o1], %g1, %g7;					\
+	cmp	%g1, %g7;						\
+	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b);				\
+	 nop;								\
+	retl;								\
+	 nop;								\
+2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
+ENDPROC(atomic64_##op);							\
 
-ENTRY(atomic64_sub_ret) /* %o0 = decrement, %o1 = atomic_ptr */
-	BACKOFF_SETUP(%o2)
-1:	ldx	[%o1], %g1
-	sub	%g1, %o0, %g7
-	casx	[%o1], %g1, %g7
-	cmp	%g1, %g7
-	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b)
-	 nop
-	retl
-	 sub	%g1, %o0, %o0
-2:	BACKOFF_SPIN(%o2, %o3, 1b)
-ENDPROC(atomic64_sub_ret)
+#define ATOMIC64_OP_RETURN(op)						\
+ENTRY(atomic64_##op##_return) /* %o0 = increment, %o1 = atomic_ptr */	\
+	BACKOFF_SETUP(%o2);						\
+1:	ldx	[%o1], %g1;						\
+	op	%g1, %o0, %g7;						\
+	casx	[%o1], %g1, %g7;					\
+	cmp	%g1, %g7;						\
+	bne,pn	%xcc, BACKOFF_LABEL(2f, 1b);				\
+	 nop;								\
+	retl;								\
+	 op	%g1, %o0, %o0;						\
+2:	BACKOFF_SPIN(%o2, %o3, 1b);					\
+ENDPROC(atomic64_##op##_return);
+
+#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op)
+
+ATOMIC64_OPS(add)
+ATOMIC64_OPS(sub)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
 
 ENTRY(atomic64_dec_if_positive) /* %o0 = atomic_ptr */
 	BACKOFF_SETUP(%o2)
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 323335b9cd2b..1d649a95660c 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -99,14 +99,23 @@ EXPORT_SYMBOL(___copy_in_user);
 EXPORT_SYMBOL(__clear_user);
 
 /* Atomic counter implementation. */
-EXPORT_SYMBOL(atomic_add);
-EXPORT_SYMBOL(atomic_add_ret);
-EXPORT_SYMBOL(atomic_sub);
-EXPORT_SYMBOL(atomic_sub_ret);
-EXPORT_SYMBOL(atomic64_add);
-EXPORT_SYMBOL(atomic64_add_ret);
-EXPORT_SYMBOL(atomic64_sub);
-EXPORT_SYMBOL(atomic64_sub_ret);
+#define ATOMIC_OP(op)							\
+EXPORT_SYMBOL(atomic_##op);						\
+EXPORT_SYMBOL(atomic64_##op);
+
+#define ATOMIC_OP_RETURN(op)						\
+EXPORT_SYMBOL(atomic_##op##_return);					\
+EXPORT_SYMBOL(atomic64_##op##_return);
+
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
+
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
 EXPORT_SYMBOL(atomic64_dec_if_positive);
 
 /* Atomic bit operations. */
diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index 99c017be8719..f75e6906df14 100644
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -3,8 +3,9 @@
  * Copyright (C) 1996,1997 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
  * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
  *
- * Returns 0, if ok, and number of bytes not yet set if exception
- * occurs and we were called as clear_user.
+ * Calls to memset returns initial %o0. Calls to bzero returns 0, if ok, and
+ * number of bytes not yet set if exception occurs and we were called as
+ * clear_user.
  */
 
 #include <asm/ptrace.h>
@@ -65,6 +66,8 @@ __bzero_begin:
 	.globl	__memset_start, __memset_end
 __memset_start:
 memset:
+	mov	%o0, %g1
+	mov	1, %g4
 	and	%o1, 0xff, %g3
 	sll	%g3, 8, %g2
 	or	%g3, %g2, %g3
@@ -89,6 +92,7 @@ memset:
 	 sub	%o0, %o2, %o0
 
 __bzero:
+	clr	%g4
 	mov	%g0, %g3
 1:
 	cmp	%o1, 7
@@ -151,8 +155,8 @@ __bzero:
 	bne,a	8f
 	 EX(stb	%g3, [%o0], and %o1, 1)
 8:
-	retl
-	 clr	%o0
+	b	0f
+	 nop
 7:
 	be	13b
 	 orcc	%o1, 0, %g0
@@ -164,6 +168,12 @@ __bzero:
 	bne	8b
 	 EX(stb	%g3, [%o0 - 1], add %o1, 1)
 0:
+	andcc	%g4, 1, %g0
+	be	5f
+	 nop
+	retl
+	 mov	%g1, %o0
+5:
 	retl
 	 clr	%o0
 __memset_end:
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 587cd0565128..18fcd7167095 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -346,6 +346,9 @@ retry:
 		down_read(&mm->mmap_sem);
 	}
 
+	if (fault_code & FAULT_CODE_BAD_RA)
+		goto do_sigbus;
+
 	vma = find_vma(mm, address);
 	if (!vma)
 		goto bad_area;
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 98ac8e80adae..2d91c62f7f5f 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -75,7 +75,6 @@ unsigned long kern_linear_pte_xor[4] __read_mostly;
  * 'cpu' properties, but we need to have this table setup before the
  * MDESC is initialized.
  */
-unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];
 
 #ifndef CONFIG_DEBUG_PAGEALLOC
 /* A special kernel TSB for 4MB, 256MB, 2GB and 16GB linear mappings.
@@ -84,10 +83,11 @@ unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];
  */
 extern struct tsb swapper_4m_tsb[KERNEL_TSB4M_NENTRIES];
 #endif
+extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
 
 static unsigned long cpu_pgsz_mask;
 
-#define MAX_BANKS	32
+#define MAX_BANKS	1024
 
 static struct linux_prom64_registers pavail[MAX_BANKS];
 static int pavail_ents;
@@ -165,10 +165,6 @@ static void __init read_obp_memory(const char *property,
 	     cmp_p64, NULL);
 }
 
-unsigned long sparc64_valid_addr_bitmap[VALID_ADDR_BITMAP_BYTES /
-					sizeof(unsigned long)];
-EXPORT_SYMBOL(sparc64_valid_addr_bitmap);
-
 /* Kernel physical address base and size in bytes.  */
 unsigned long kern_base __read_mostly;
 unsigned long kern_size __read_mostly;
@@ -840,7 +836,10 @@ static int find_node(unsigned long addr)
 		if ((addr & p->mask) == p->val)
 			return i;
 	}
-	return -1;
+	/* The following condition has been observed on LDOM guests.*/
+	WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node"
+		" rule. Some physical memory will be owned by node 0.");
+	return 0;
 }
 
 static u64 memblock_nid_range(u64 start, u64 end, int *nid)
@@ -1366,9 +1365,144 @@ static unsigned long __init bootmem_init(unsigned long phys_base)
 static struct linux_prom64_registers pall[MAX_BANKS] __initdata;
 static int pall_ents __initdata;
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
+static unsigned long max_phys_bits = 40;
+
+bool kern_addr_valid(unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	if ((long)addr < 0L) {
+		unsigned long pa = __pa(addr);
+
+		if ((addr >> max_phys_bits) != 0UL)
+			return false;
+
+		return pfn_valid(pa >> PAGE_SHIFT);
+	}
+
+	if (addr >= (unsigned long) KERNBASE &&
+	    addr < (unsigned long)&_end)
+		return true;
+
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd))
+		return 0;
+
+	pud = pud_offset(pgd, addr);
+	if (pud_none(*pud))
+		return 0;
+
+	if (pud_large(*pud))
+		return pfn_valid(pud_pfn(*pud));
+
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return 0;
+
+	if (pmd_large(*pmd))
+		return pfn_valid(pmd_pfn(*pmd));
+
+	pte = pte_offset_kernel(pmd, addr);
+	if (pte_none(*pte))
+		return 0;
+
+	return pfn_valid(pte_pfn(*pte));
+}
+EXPORT_SYMBOL(kern_addr_valid);
+
+static unsigned long __ref kernel_map_hugepud(unsigned long vstart,
+					      unsigned long vend,
+					      pud_t *pud)
+{
+	const unsigned long mask16gb = (1UL << 34) - 1UL;
+	u64 pte_val = vstart;
+
+	/* Each PUD is 8GB */
+	if ((vstart & mask16gb) ||
+	    (vend - vstart <= mask16gb)) {
+		pte_val ^= kern_linear_pte_xor[2];
+		pud_val(*pud) = pte_val | _PAGE_PUD_HUGE;
+
+		return vstart + PUD_SIZE;
+	}
+
+	pte_val ^= kern_linear_pte_xor[3];
+	pte_val |= _PAGE_PUD_HUGE;
+
+	vend = vstart + mask16gb + 1UL;
+	while (vstart < vend) {
+		pud_val(*pud) = pte_val;
+
+		pte_val += PUD_SIZE;
+		vstart += PUD_SIZE;
+		pud++;
+	}
+	return vstart;
+}
+
+static bool kernel_can_map_hugepud(unsigned long vstart, unsigned long vend,
+				   bool guard)
+{
+	if (guard && !(vstart & ~PUD_MASK) && (vend - vstart) >= PUD_SIZE)
+		return true;
+
+	return false;
+}
+
+static unsigned long __ref kernel_map_hugepmd(unsigned long vstart,
+					      unsigned long vend,
+					      pmd_t *pmd)
+{
+	const unsigned long mask256mb = (1UL << 28) - 1UL;
+	const unsigned long mask2gb = (1UL << 31) - 1UL;
+	u64 pte_val = vstart;
+
+	/* Each PMD is 8MB */
+	if ((vstart & mask256mb) ||
+	    (vend - vstart <= mask256mb)) {
+		pte_val ^= kern_linear_pte_xor[0];
+		pmd_val(*pmd) = pte_val | _PAGE_PMD_HUGE;
+
+		return vstart + PMD_SIZE;
+	}
+
+	if ((vstart & mask2gb) ||
+	    (vend - vstart <= mask2gb)) {
+		pte_val ^= kern_linear_pte_xor[1];
+		pte_val |= _PAGE_PMD_HUGE;
+		vend = vstart + mask256mb + 1UL;
+	} else {
+		pte_val ^= kern_linear_pte_xor[2];
+		pte_val |= _PAGE_PMD_HUGE;
+		vend = vstart + mask2gb + 1UL;
+	}
+
+	while (vstart < vend) {
+		pmd_val(*pmd) = pte_val;
+
+		pte_val += PMD_SIZE;
+		vstart += PMD_SIZE;
+		pmd++;
+	}
+
+	return vstart;
+}
+
+static bool kernel_can_map_hugepmd(unsigned long vstart, unsigned long vend,
+				   bool guard)
+{
+	if (guard && !(vstart & ~PMD_MASK) && (vend - vstart) >= PMD_SIZE)
+		return true;
+
+	return false;
+}
+
 static unsigned long __ref kernel_map_range(unsigned long pstart,
-					    unsigned long pend, pgprot_t prot)
+					    unsigned long pend, pgprot_t prot,
+					    bool use_huge)
 {
 	unsigned long vstart = PAGE_OFFSET + pstart;
 	unsigned long vend = PAGE_OFFSET + pend;
@@ -1387,19 +1521,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart,
 		pmd_t *pmd;
 		pte_t *pte;
 
+		if (pgd_none(*pgd)) {
+			pud_t *new;
+
+			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+			alloc_bytes += PAGE_SIZE;
+			pgd_populate(&init_mm, pgd, new);
+		}
 		pud = pud_offset(pgd, vstart);
 		if (pud_none(*pud)) {
 			pmd_t *new;
 
+			if (kernel_can_map_hugepud(vstart, vend, use_huge)) {
+				vstart = kernel_map_hugepud(vstart, vend, pud);
+				continue;
+			}
 			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
 			alloc_bytes += PAGE_SIZE;
 			pud_populate(&init_mm, pud, new);
 		}
 
 		pmd = pmd_offset(pud, vstart);
-		if (!pmd_present(*pmd)) {
+		if (pmd_none(*pmd)) {
 			pte_t *new;
 
+			if (kernel_can_map_hugepmd(vstart, vend, use_huge)) {
+				vstart = kernel_map_hugepmd(vstart, vend, pmd);
+				continue;
+			}
 			new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
 			alloc_bytes += PAGE_SIZE;
 			pmd_populate_kernel(&init_mm, pmd, new);
@@ -1422,100 +1571,34 @@ static unsigned long __ref kernel_map_range(unsigned long pstart,
 	return alloc_bytes;
 }
 
-extern unsigned int kvmap_linear_patch[1];
-#endif /* CONFIG_DEBUG_PAGEALLOC */
-
-static void __init kpte_set_val(unsigned long index, unsigned long val)
-{
-	unsigned long *ptr = kpte_linear_bitmap;
-
-	val <<= ((index % (BITS_PER_LONG / 2)) * 2);
-	ptr += (index / (BITS_PER_LONG / 2));
-
-	*ptr |= val;
-}
-
-static const unsigned long kpte_shift_min = 28; /* 256MB */
-static const unsigned long kpte_shift_max = 34; /* 16GB */
-static const unsigned long kpte_shift_incr = 3;
-
-static unsigned long kpte_mark_using_shift(unsigned long start, unsigned long end,
-					   unsigned long shift)
+static void __init flush_all_kernel_tsbs(void)
 {
-	unsigned long size = (1UL << shift);
-	unsigned long mask = (size - 1UL);
-	unsigned long remains = end - start;
-	unsigned long val;
-
-	if (remains < size || (start & mask))
-		return start;
-
-	/* VAL maps:
-	 *
-	 *	shift 28 --> kern_linear_pte_xor index 1
-	 *	shift 31 --> kern_linear_pte_xor index 2
-	 *	shift 34 --> kern_linear_pte_xor index 3
-	 */
-	val = ((shift - kpte_shift_min) / kpte_shift_incr) + 1;
-
-	remains &= ~mask;
-	if (shift != kpte_shift_max)
-		remains = size;
-
-	while (remains) {
-		unsigned long index = start >> kpte_shift_min;
+	int i;
 
-		kpte_set_val(index, val);
+	for (i = 0; i < KERNEL_TSB_NENTRIES; i++) {
+		struct tsb *ent = &swapper_tsb[i];
 
-		start += 1UL << kpte_shift_min;
-		remains -= 1UL << kpte_shift_min;
+		ent->tag = (1UL << TSB_TAG_INVALID_BIT);
 	}
+#ifndef CONFIG_DEBUG_PAGEALLOC
+	for (i = 0; i < KERNEL_TSB4M_NENTRIES; i++) {
+		struct tsb *ent = &swapper_4m_tsb[i];
 
-	return start;
-}
-
-static void __init mark_kpte_bitmap(unsigned long start, unsigned long end)
-{
-	unsigned long smallest_size, smallest_mask;
-	unsigned long s;
-
-	smallest_size = (1UL << kpte_shift_min);
-	smallest_mask = (smallest_size - 1UL);
-
-	while (start < end) {
-		unsigned long orig_start = start;
-
-		for (s = kpte_shift_max; s >= kpte_shift_min; s -= kpte_shift_incr) {
-			start = kpte_mark_using_shift(start, end, s);
-
-			if (start != orig_start)
-				break;
-		}
-
-		if (start == orig_start)
-			start = (start + smallest_size) & ~smallest_mask;
+		ent->tag = (1UL << TSB_TAG_INVALID_BIT);
 	}
+#endif
 }
 
-static void __init init_kpte_bitmap(void)
-{
-	unsigned long i;
-
-	for (i = 0; i < pall_ents; i++) {
-		unsigned long phys_start, phys_end;
-
-		phys_start = pall[i].phys_addr;
-		phys_end = phys_start + pall[i].reg_size;
-
-		mark_kpte_bitmap(phys_start, phys_end);
-	}
-}
+extern unsigned int kvmap_linear_patch[1];
 
 static void __init kernel_physical_mapping_init(void)
 {
-#ifdef CONFIG_DEBUG_PAGEALLOC
 	unsigned long i, mem_alloced = 0UL;
+	bool use_huge = true;
 
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	use_huge = false;
+#endif
 	for (i = 0; i < pall_ents; i++) {
 		unsigned long phys_start, phys_end;
 
@@ -1523,7 +1606,7 @@ static void __init kernel_physical_mapping_init(void)
 		phys_end = phys_start + pall[i].reg_size;
 
 		mem_alloced += kernel_map_range(phys_start, phys_end,
-						PAGE_KERNEL);
+						PAGE_KERNEL, use_huge);
 	}
 
 	printk("Allocated %ld bytes for kernel page tables.\n",
@@ -1532,8 +1615,9 @@ static void __init kernel_physical_mapping_init(void)
 	kvmap_linear_patch[0] = 0x01000000; /* nop */
 	flushi(&kvmap_linear_patch[0]);
 
+	flush_all_kernel_tsbs();
+
 	__flush_tlb_all();
-#endif
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
@@ -1543,7 +1627,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 	unsigned long phys_end = phys_start + (numpages * PAGE_SIZE);
 
 	kernel_map_range(phys_start, phys_end,
-			 (enable ? PAGE_KERNEL : __pgprot(0)));
+			 (enable ? PAGE_KERNEL : __pgprot(0)), false);
 
 	flush_tsb_kernel_range(PAGE_OFFSET + phys_start,
 			       PAGE_OFFSET + phys_end);
@@ -1571,76 +1655,56 @@ unsigned long __init find_ecache_flush_span(unsigned long size)
 unsigned long PAGE_OFFSET;
 EXPORT_SYMBOL(PAGE_OFFSET);
 
-static void __init page_offset_shift_patch_one(unsigned int *insn, unsigned long phys_bits)
-{
-	unsigned long final_shift;
-	unsigned int val = *insn;
-	unsigned int cnt;
-
-	/* We are patching in ilog2(max_supported_phys_address), and
-	 * we are doing so in a manner similar to a relocation addend.
-	 * That is, we are adding the shift value to whatever value
-	 * is in the shift instruction count field already.
-	 */
-	cnt = (val & 0x3f);
-	val &= ~0x3f;
-
-	/* If we are trying to shift >= 64 bits, clear the destination
-	 * register.  This can happen when phys_bits ends up being equal
-	 * to MAX_PHYS_ADDRESS_BITS.
-	 */
-	final_shift = (cnt + (64 - phys_bits));
-	if (final_shift >= 64) {
-		unsigned int rd = (val >> 25) & 0x1f;
-
-		val = 0x80100000 | (rd << 25);
-	} else {
-		val |= final_shift;
-	}
-	*insn = val;
-
-	__asm__ __volatile__("flush	%0"
-			     : /* no outputs */
-			     : "r" (insn));
-}
-
-static void __init page_offset_shift_patch(unsigned long phys_bits)
-{
-	extern unsigned int __page_offset_shift_patch;
-	extern unsigned int __page_offset_shift_patch_end;
-	unsigned int *p;
-
-	p = &__page_offset_shift_patch;
-	while (p < &__page_offset_shift_patch_end) {
-		unsigned int *insn = (unsigned int *)(unsigned long)*p;
+unsigned long VMALLOC_END   = 0x0000010000000000UL;
+EXPORT_SYMBOL(VMALLOC_END);
 
-		page_offset_shift_patch_one(insn, phys_bits);
-
-		p++;
-	}
-}
+unsigned long sparc64_va_hole_top =    0xfffff80000000000UL;
+unsigned long sparc64_va_hole_bottom = 0x0000080000000000UL;
 
 static void __init setup_page_offset(void)
 {
-	unsigned long max_phys_bits = 40;
-
 	if (tlb_type == cheetah || tlb_type == cheetah_plus) {
+		/* Cheetah/Panther support a full 64-bit virtual
+		 * address, so we can use all that our page tables
+		 * support.
+		 */
+		sparc64_va_hole_top =    0xfff0000000000000UL;
+		sparc64_va_hole_bottom = 0x0010000000000000UL;
+
 		max_phys_bits = 42;
 	} else if (tlb_type == hypervisor) {
 		switch (sun4v_chip_type) {
 		case SUN4V_CHIP_NIAGARA1:
 		case SUN4V_CHIP_NIAGARA2:
+			/* T1 and T2 support 48-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xffff800000000000UL;
+			sparc64_va_hole_bottom = 0x0000800000000000UL;
+
 			max_phys_bits = 39;
 			break;
 		case SUN4V_CHIP_NIAGARA3:
+			/* T3 supports 48-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xffff800000000000UL;
+			sparc64_va_hole_bottom = 0x0000800000000000UL;
+
 			max_phys_bits = 43;
 			break;
 		case SUN4V_CHIP_NIAGARA4:
 		case SUN4V_CHIP_NIAGARA5:
 		case SUN4V_CHIP_SPARC64X:
-		default:
+		case SUN4V_CHIP_SPARC_M6:
+			/* T4 and later support 52-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xfff8000000000000UL;
+			sparc64_va_hole_bottom = 0x0008000000000000UL;
 			max_phys_bits = 47;
 			break;
+		case SUN4V_CHIP_SPARC_M7:
+		default:
+			/* M7 and later support 52-bit virtual addresses.  */
+			sparc64_va_hole_top =    0xfff8000000000000UL;
+			sparc64_va_hole_bottom = 0x0008000000000000UL;
+			max_phys_bits = 49;
+			break;
 		}
 	}
 
@@ -1650,12 +1714,16 @@ static void __init setup_page_offset(void)
 		prom_halt();
 	}
 
-	PAGE_OFFSET = PAGE_OFFSET_BY_BITS(max_phys_bits);
+	PAGE_OFFSET = sparc64_va_hole_top;
+	VMALLOC_END = ((sparc64_va_hole_bottom >> 1) +
+		       (sparc64_va_hole_bottom >> 2));
 
-	pr_info("PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n",
+	pr_info("MM: PAGE_OFFSET is 0x%016lx (max_phys_bits == %lu)\n",
 		PAGE_OFFSET, max_phys_bits);
-
-	page_offset_shift_patch(max_phys_bits);
+	pr_info("MM: VMALLOC [0x%016lx --> 0x%016lx]\n",
+		VMALLOC_START, VMALLOC_END);
+	pr_info("MM: VMEMMAP [0x%016lx --> 0x%016lx]\n",
+		VMEMMAP_BASE, VMEMMAP_BASE << 1);
 }
 
 static void __init tsb_phys_patch(void)
@@ -1700,21 +1768,42 @@ static void __init tsb_phys_patch(void)
 #define NUM_KTSB_DESCR	1
 #endif
 static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR];
-extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
+
+/* The swapper TSBs are loaded with a base sequence of:
+ *
+ *	sethi	%uhi(SYMBOL), REG1
+ *	sethi	%hi(SYMBOL), REG2
+ *	or	REG1, %ulo(SYMBOL), REG1
+ *	or	REG2, %lo(SYMBOL), REG2
+ *	sllx	REG1, 32, REG1
+ *	or	REG1, REG2, REG1
+ *
+ * When we use physical addressing for the TSB accesses, we patch the
+ * first four instructions in the above sequence.
+ */
 
 static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa)
 {
-	pa >>= KTSB_PHYS_SHIFT;
+	unsigned long high_bits, low_bits;
+
+	high_bits = (pa >> 32) & 0xffffffff;
+	low_bits = (pa >> 0) & 0xffffffff;
 
 	while (start < end) {
 		unsigned int *ia = (unsigned int *)(unsigned long)*start;
 
-		ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10);
+		ia[0] = (ia[0] & ~0x3fffff) | (high_bits >> 10);
 		__asm__ __volatile__("flush	%0" : : "r" (ia));
 
-		ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff);
+		ia[1] = (ia[1] & ~0x3fffff) | (low_bits >> 10);
 		__asm__ __volatile__("flush	%0" : : "r" (ia + 1));
 
+		ia[2] = (ia[2] & ~0x1fff) | (high_bits & 0x3ff);
+		__asm__ __volatile__("flush	%0" : : "r" (ia + 2));
+
+		ia[3] = (ia[3] & ~0x1fff) | (low_bits & 0x3ff);
+		__asm__ __volatile__("flush	%0" : : "r" (ia + 3));
+
 		start++;
 	}
 }
@@ -1853,11 +1942,56 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 /* paging_init() sets up the page tables */
 
 static unsigned long last_valid_pfn;
-pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
 static void sun4u_pgprot_init(void);
 static void sun4v_pgprot_init(void);
 
+static phys_addr_t __init available_memory(void)
+{
+	phys_addr_t available = 0ULL;
+	phys_addr_t pa_start, pa_end;
+	u64 i;
+
+	for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL)
+		available = available + (pa_end  - pa_start);
+
+	return available;
+}
+
+/* We need to exclude reserved regions. This exclusion will include
+ * vmlinux and initrd. To be more precise the initrd size could be used to
+ * compute a new lower limit because it is freed later during initialization.
+ */
+static void __init reduce_memory(phys_addr_t limit_ram)
+{
+	phys_addr_t avail_ram = available_memory();
+	phys_addr_t pa_start, pa_end;
+	u64 i;
+
+	if (limit_ram >= avail_ram)
+		return;
+
+	for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL) {
+		phys_addr_t region_size = pa_end - pa_start;
+		phys_addr_t clip_start = pa_start;
+
+		avail_ram = avail_ram - region_size;
+		/* Are we consuming too much? */
+		if (avail_ram < limit_ram) {
+			phys_addr_t give_back = limit_ram - avail_ram;
+
+			region_size = region_size - give_back;
+			clip_start = clip_start + give_back;
+		}
+
+		memblock_remove(clip_start, region_size);
+
+		if (avail_ram <= limit_ram)
+			break;
+		i = 0UL;
+	}
+}
+
 void __init paging_init(void)
 {
 	unsigned long end_pfn, shift, phys_base;
@@ -1937,7 +2071,8 @@ void __init paging_init(void)
 
 	find_ramdisk(phys_base);
 
-	memblock_enforce_memory_limit(cmdline_memory_size);
+	if (cmdline_memory_size)
+		reduce_memory(cmdline_memory_size);
 
 	memblock_allow_resize();
 	memblock_dump_all();
@@ -1956,16 +2091,10 @@ void __init paging_init(void)
 	 */
 	init_mm.pgd += ((shift) / (sizeof(pgd_t)));
 	
-	memset(swapper_low_pmd_dir, 0, sizeof(swapper_low_pmd_dir));
+	memset(swapper_pg_dir, 0, sizeof(swapper_pg_dir));
 
-	/* Now can init the kernel/bad page tables. */
-	pud_set(pud_offset(&swapper_pg_dir[0], 0),
-		swapper_low_pmd_dir + (shift / sizeof(pgd_t)));
-	
 	inherit_prom_mappings();
 	
-	init_kpte_bitmap();
-
 	/* Ok, we can use our TLB miss and window trap handlers safely.  */
 	setup_tba();
 
@@ -2072,70 +2201,6 @@ int page_in_phys_avail(unsigned long paddr)
 	return 0;
 }
 
-static struct linux_prom64_registers pavail_rescan[MAX_BANKS] __initdata;
-static int pavail_rescan_ents __initdata;
-
-/* Certain OBP calls, such as fetching "available" properties, can
- * claim physical memory.  So, along with initializing the valid
- * address bitmap, what we do here is refetch the physical available
- * memory list again, and make sure it provides at least as much
- * memory as 'pavail' does.
- */
-static void __init setup_valid_addr_bitmap_from_pavail(unsigned long *bitmap)
-{
-	int i;
-
-	read_obp_memory("available", &pavail_rescan[0], &pavail_rescan_ents);
-
-	for (i = 0; i < pavail_ents; i++) {
-		unsigned long old_start, old_end;
-
-		old_start = pavail[i].phys_addr;
-		old_end = old_start + pavail[i].reg_size;
-		while (old_start < old_end) {
-			int n;
-
-			for (n = 0; n < pavail_rescan_ents; n++) {
-				unsigned long new_start, new_end;
-
-				new_start = pavail_rescan[n].phys_addr;
-				new_end = new_start +
-					pavail_rescan[n].reg_size;
-
-				if (new_start <= old_start &&
-				    new_end >= (old_start + PAGE_SIZE)) {
-					set_bit(old_start >> ILOG2_4MB, bitmap);
-					goto do_next_page;
-				}
-			}
-
-			prom_printf("mem_init: Lost memory in pavail\n");
-			prom_printf("mem_init: OLD start[%lx] size[%lx]\n",
-				    pavail[i].phys_addr,
-				    pavail[i].reg_size);
-			prom_printf("mem_init: NEW start[%lx] size[%lx]\n",
-				    pavail_rescan[i].phys_addr,
-				    pavail_rescan[i].reg_size);
-			prom_printf("mem_init: Cannot continue, aborting.\n");
-			prom_halt();
-
-		do_next_page:
-			old_start += PAGE_SIZE;
-		}
-	}
-}
-
-static void __init patch_tlb_miss_handler_bitmap(void)
-{
-	extern unsigned int valid_addr_bitmap_insn[];
-	extern unsigned int valid_addr_bitmap_patch[];
-
-	valid_addr_bitmap_insn[1] = valid_addr_bitmap_patch[1];
-	mb();
-	valid_addr_bitmap_insn[0] = valid_addr_bitmap_patch[0];
-	flushi(&valid_addr_bitmap_insn[0]);
-}
-
 static void __init register_page_bootmem_info(void)
 {
 #ifdef CONFIG_NEED_MULTIPLE_NODES
@@ -2148,18 +2213,6 @@ static void __init register_page_bootmem_info(void)
 }
 void __init mem_init(void)
 {
-	unsigned long addr, last;
-
-	addr = PAGE_OFFSET + kern_base;
-	last = PAGE_ALIGN(kern_size) + addr;
-	while (addr < last) {
-		set_bit(__pa(addr) >> ILOG2_4MB, sparc64_valid_addr_bitmap);
-		addr += PAGE_SIZE;
-	}
-
-	setup_valid_addr_bitmap_from_pavail(sparc64_valid_addr_bitmap);
-	patch_tlb_miss_handler_bitmap();
-
 	high_memory = __va(last_valid_pfn << PAGE_SHIFT);
 
 	register_page_bootmem_info();
@@ -2249,18 +2302,9 @@ unsigned long _PAGE_CACHE __read_mostly;
 EXPORT_SYMBOL(_PAGE_CACHE);
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-unsigned long vmemmap_table[VMEMMAP_SIZE];
-
-static long __meminitdata addr_start, addr_end;
-static int __meminitdata node_start;
-
 int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 			       int node)
 {
-	unsigned long phys_start = (vstart - VMEMMAP_BASE);
-	unsigned long phys_end = (vend - VMEMMAP_BASE);
-	unsigned long addr = phys_start & VMEMMAP_CHUNK_MASK;
-	unsigned long end = VMEMMAP_ALIGN(phys_end);
 	unsigned long pte_base;
 
 	pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4U |
@@ -2271,47 +2315,52 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 			    _PAGE_CP_4V | _PAGE_CV_4V |
 			    _PAGE_P_4V | _PAGE_W_4V);
 
-	for (; addr < end; addr += VMEMMAP_CHUNK) {
-		unsigned long *vmem_pp =
-			vmemmap_table + (addr >> VMEMMAP_CHUNK_SHIFT);
-		void *block;
+	pte_base |= _PAGE_PMD_HUGE;
 
-		if (!(*vmem_pp & _PAGE_VALID)) {
-			block = vmemmap_alloc_block(1UL << ILOG2_4MB, node);
-			if (!block)
+	vstart = vstart & PMD_MASK;
+	vend = ALIGN(vend, PMD_SIZE);
+	for (; vstart < vend; vstart += PMD_SIZE) {
+		pgd_t *pgd = pgd_offset_k(vstart);
+		unsigned long pte;
+		pud_t *pud;
+		pmd_t *pmd;
+
+		if (pgd_none(*pgd)) {
+			pud_t *new = vmemmap_alloc_block(PAGE_SIZE, node);
+
+			if (!new)
 				return -ENOMEM;
+			pgd_populate(&init_mm, pgd, new);
+		}
 
-			*vmem_pp = pte_base | __pa(block);
+		pud = pud_offset(pgd, vstart);
+		if (pud_none(*pud)) {
+			pmd_t *new = vmemmap_alloc_block(PAGE_SIZE, node);
 
-			/* check to see if we have contiguous blocks */
-			if (addr_end != addr || node_start != node) {
-				if (addr_start)
-					printk(KERN_DEBUG " [%lx-%lx] on node %d\n",
-					       addr_start, addr_end-1, node_start);
-				addr_start = addr;
-				node_start = node;
-			}
-			addr_end = addr + VMEMMAP_CHUNK;
+			if (!new)
+				return -ENOMEM;
+			pud_populate(&init_mm, pud, new);
 		}
-	}
-	return 0;
-}
 
-void __meminit vmemmap_populate_print_last(void)
-{
-	if (addr_start) {
-		printk(KERN_DEBUG " [%lx-%lx] on node %d\n",
-		       addr_start, addr_end-1, node_start);
-		addr_start = 0;
-		addr_end = 0;
-		node_start = 0;
+		pmd = pmd_offset(pud, vstart);
+
+		pte = pmd_val(*pmd);
+		if (!(pte & _PAGE_VALID)) {
+			void *block = vmemmap_alloc_block(PMD_SIZE, node);
+
+			if (!block)
+				return -ENOMEM;
+
+			pmd_val(*pmd) = pte_base | __pa(block);
+		}
 	}
+
+	return 0;
 }
 
 void vmemmap_free(unsigned long start, unsigned long end)
 {
 }
-
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 static void prot_init_common(unsigned long page_none,
@@ -2787,8 +2836,8 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 			do_flush_tlb_kernel_range(start, LOW_OBP_ADDRESS);
 		}
 		if (end > HI_OBP_ADDRESS) {
-			flush_tsb_kernel_range(end, HI_OBP_ADDRESS);
-			do_flush_tlb_kernel_range(end, HI_OBP_ADDRESS);
+			flush_tsb_kernel_range(HI_OBP_ADDRESS, end);
+			do_flush_tlb_kernel_range(HI_OBP_ADDRESS, end);
 		}
 	} else {
 		flush_tsb_kernel_range(start, end);
diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h
index 0668b364f44d..a4c09603b05c 100644
--- a/arch/sparc/mm/init_64.h
+++ b/arch/sparc/mm/init_64.h
@@ -8,15 +8,8 @@
  */
 
 #define MAX_PHYS_ADDRESS	(1UL << MAX_PHYS_ADDRESS_BITS)
-#define KPTE_BITMAP_CHUNK_SZ		(256UL * 1024UL * 1024UL)
-#define KPTE_BITMAP_BYTES	\
-	((MAX_PHYS_ADDRESS / KPTE_BITMAP_CHUNK_SZ) / 4)
-#define VALID_ADDR_BITMAP_CHUNK_SZ	(4UL * 1024UL * 1024UL)
-#define VALID_ADDR_BITMAP_BYTES	\
-	((MAX_PHYS_ADDRESS / VALID_ADDR_BITMAP_CHUNK_SZ) / 8)
 
 extern unsigned long kern_linear_pte_xor[4];
-extern unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];
 extern unsigned int sparc64_highest_unlocked_tlb_ent;
 extern unsigned long sparc64_kern_pri_context;
 extern unsigned long sparc64_kern_pri_nuc_bits;
@@ -38,15 +31,4 @@ extern unsigned long kern_locked_tte_data;
 
 void prom_world(int enter);
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-#define VMEMMAP_CHUNK_SHIFT	22
-#define VMEMMAP_CHUNK		(1UL << VMEMMAP_CHUNK_SHIFT)
-#define VMEMMAP_CHUNK_MASK	~(VMEMMAP_CHUNK - 1UL)
-#define VMEMMAP_ALIGN(x)	(((x)+VMEMMAP_CHUNK-1UL)&VMEMMAP_CHUNK_MASK)
-
-#define VMEMMAP_SIZE	((((1UL << MAX_PHYSADDR_BITS) >> PAGE_SHIFT) * \
-			  sizeof(struct page)) >> VMEMMAP_CHUNK_SHIFT)
-extern unsigned long vmemmap_table[VMEMMAP_SIZE];
-#endif
-
 #endif /* _SPARC64_MM_INIT_H */
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index b89aba217e3b..9df2190c097e 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -52,14 +52,14 @@ out:
 
 void arch_enter_lazy_mmu_mode(void)
 {
-	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+	struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
 
 	tb->active = 1;
 }
 
 void arch_leave_lazy_mmu_mode(void)
 {
-	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+	struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
 
 	if (tb->tlb_nr)
 		flush_tlb_pending();
diff --git a/arch/sparc/power/hibernate.c b/arch/sparc/power/hibernate.c
index 42b0b8ce699a..17bd2e167e07 100644
--- a/arch/sparc/power/hibernate.c
+++ b/arch/sparc/power/hibernate.c
@@ -9,11 +9,9 @@
 #include <asm/hibernate.h>
 #include <asm/visasm.h>
 #include <asm/page.h>
+#include <asm/sections.h>
 #include <asm/tlb.h>
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
 struct saved_context saved_context;
 
 /*
diff --git a/arch/sparc/power/hibernate_asm.S b/arch/sparc/power/hibernate_asm.S
index 79942166df84..d7d9017dcb15 100644
--- a/arch/sparc/power/hibernate_asm.S
+++ b/arch/sparc/power/hibernate_asm.S
@@ -54,8 +54,8 @@ ENTRY(swsusp_arch_resume)
 	 nop
 
 	/* Write PAGE_OFFSET to %g7 */
-	sethi	%uhi(PAGE_OFFSET), %g7
-	sllx	%g7, 32, %g7
+	sethi	%hi(PAGE_OFFSET), %g7
+	ldx	[%g7 + %lo(PAGE_OFFSET)], %g7
 
 	setuw	(PAGE_SIZE-8), %g3
 
diff --git a/arch/sparc/prom/bootstr_64.c b/arch/sparc/prom/bootstr_64.c
index ab9ccc63b388..7149e77714a4 100644
--- a/arch/sparc/prom/bootstr_64.c
+++ b/arch/sparc/prom/bootstr_64.c
@@ -14,7 +14,10 @@
  *          the .bss section or it will break things.
  */
 
-#define BARG_LEN  256
+/* We limit BARG_LEN to 1024 because this is the size of the
+ * 'barg_out' command line buffer in the SILO bootloader.
+ */
+#define BARG_LEN 1024
 struct {
 	int bootstr_len;
 	int bootstr_valid;
diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c
index e58b81726319..b2340f008ae0 100644
--- a/arch/sparc/prom/p1275.c
+++ b/arch/sparc/prom/p1275.c
@@ -9,6 +9,7 @@
 #include <linux/smp.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
+#include <linux/irqflags.h>
 
 #include <asm/openprom.h>
 #include <asm/oplib.h>
@@ -36,8 +37,8 @@ void p1275_cmd_direct(unsigned long *args)
 {
 	unsigned long flags;
 
-	raw_local_save_flags(flags);
-	raw_local_irq_restore((unsigned long)PIL_NMI);
+	local_save_flags(flags);
+	local_irq_restore((unsigned long)PIL_NMI);
 	raw_spin_lock(&prom_entry_lock);
 
 	prom_world(1);
@@ -45,7 +46,7 @@ void p1275_cmd_direct(unsigned long *args)
 	prom_world(0);
 
 	raw_spin_unlock(&prom_entry_lock);
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 }
 
 void prom_cif_init(void *cif_handler, void *cif_stack)
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index 0aa5675e7025..e6462b8a6284 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -17,6 +17,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h
index 71af5747874d..60d62a292fce 100644
--- a/arch/tile/include/asm/irqflags.h
+++ b/arch/tile/include/asm/irqflags.h
@@ -140,12 +140,12 @@ extern unsigned int debug_smp_processor_id(void);
 
 /*
  * Read the set of maskable interrupts.
- * We avoid the preemption warning here via __this_cpu_ptr since even
+ * We avoid the preemption warning here via raw_cpu_ptr since even
  * if irqs are already enabled, it's harmless to read the wrong cpu's
  * enabled mask.
  */
 #define arch_local_irqs_enabled() \
-	(*__this_cpu_ptr(&interrupts_enabled_mask))
+	(*raw_cpu_ptr(&interrupts_enabled_mask))
 
 /* Re-enable all maskable interrupts. */
 #define arch_local_irq_enable() \
diff --git a/arch/tile/include/asm/mmu_context.h b/arch/tile/include/asm/mmu_context.h
index 4734215e2ad4..f67753db1f78 100644
--- a/arch/tile/include/asm/mmu_context.h
+++ b/arch/tile/include/asm/mmu_context.h
@@ -84,7 +84,7 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *t)
 	 * clear any pending DMA interrupts.
 	 */
 	if (current->thread.tile_dma_state.enabled)
-		install_page_table(mm->pgd, __get_cpu_var(current_asid));
+		install_page_table(mm->pgd, __this_cpu_read(current_asid));
 #endif
 }
 
@@ -96,12 +96,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		int cpu = smp_processor_id();
 
 		/* Pick new ASID. */
-		int asid = __get_cpu_var(current_asid) + 1;
+		int asid = __this_cpu_read(current_asid) + 1;
 		if (asid > max_asid) {
 			asid = min_asid;
 			local_flush_tlb();
 		}
-		__get_cpu_var(current_asid) = asid;
+		__this_cpu_write(current_asid, asid);
 
 		/* Clear cpu from the old mm, and set it in the new one. */
 		cpumask_clear_cpu(cpu, mm_cpumask(prev));
diff --git a/arch/tile/kernel/irq.c b/arch/tile/kernel/irq.c
index 637f2ffaa5f5..ba85765e1436 100644
--- a/arch/tile/kernel/irq.c
+++ b/arch/tile/kernel/irq.c
@@ -73,7 +73,7 @@ static DEFINE_PER_CPU(int, irq_depth);
  */
 void tile_dev_intr(struct pt_regs *regs, int intnum)
 {
-	int depth = __get_cpu_var(irq_depth)++;
+	int depth = __this_cpu_inc_return(irq_depth);
 	unsigned long original_irqs;
 	unsigned long remaining_irqs;
 	struct pt_regs *old_regs;
@@ -120,7 +120,7 @@ void tile_dev_intr(struct pt_regs *regs, int intnum)
 
 		/* Count device irqs; Linux IPIs are counted elsewhere. */
 		if (irq != IRQ_RESCHEDULE)
-			__get_cpu_var(irq_stat).irq_dev_intr_count++;
+			__this_cpu_inc(irq_stat.irq_dev_intr_count);
 
 		generic_handle_irq(irq);
 	}
@@ -130,10 +130,10 @@ void tile_dev_intr(struct pt_regs *regs, int intnum)
 	 * including any that were reenabled during interrupt
 	 * handling.
 	 */
-	if (depth == 0)
-		unmask_irqs(~__get_cpu_var(irq_disable_mask));
+	if (depth == 1)
+		unmask_irqs(~__this_cpu_read(irq_disable_mask));
 
-	__get_cpu_var(irq_depth)--;
+	__this_cpu_dec(irq_depth);
 
 	/*
 	 * Track time spent against the current process again and
@@ -151,7 +151,7 @@ void tile_dev_intr(struct pt_regs *regs, int intnum)
 static void tile_irq_chip_enable(struct irq_data *d)
 {
 	get_cpu_var(irq_disable_mask) &= ~(1UL << d->irq);
-	if (__get_cpu_var(irq_depth) == 0)
+	if (__this_cpu_read(irq_depth) == 0)
 		unmask_irqs(1UL << d->irq);
 	put_cpu_var(irq_disable_mask);
 }
@@ -197,7 +197,7 @@ static void tile_irq_chip_ack(struct irq_data *d)
  */
 static void tile_irq_chip_eoi(struct irq_data *d)
 {
-	if (!(__get_cpu_var(irq_disable_mask) & (1UL << d->irq)))
+	if (!(__this_cpu_read(irq_disable_mask) & (1UL << d->irq)))
 		unmask_irqs(1UL << d->irq);
 }
 
diff --git a/arch/tile/kernel/messaging.c b/arch/tile/kernel/messaging.c
index 7867266f9716..ac950be1318e 100644
--- a/arch/tile/kernel/messaging.c
+++ b/arch/tile/kernel/messaging.c
@@ -28,7 +28,7 @@ static DEFINE_PER_CPU(HV_MsgState, msg_state);
 void init_messaging(void)
 {
 	/* Allocate storage for messages in kernel space */
-	HV_MsgState *state = &__get_cpu_var(msg_state);
+	HV_MsgState *state = this_cpu_ptr(&msg_state);
 	int rc = hv_register_message_state(state);
 	if (rc != HV_OK)
 		panic("hv_register_message_state: error %d", rc);
@@ -96,7 +96,7 @@ void hv_message_intr(struct pt_regs *regs, int intnum)
 			struct hv_driver_cb *cb =
 				(struct hv_driver_cb *)him->intarg;
 			cb->callback(cb, him->intdata);
-			__get_cpu_var(irq_stat).irq_hv_msg_count++;
+			__this_cpu_inc(irq_stat.irq_hv_msg_count);
 		}
 	}
 
diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c
index 2bf6c9c135c1..bb509cee3b59 100644
--- a/arch/tile/kernel/perf_event.c
+++ b/arch/tile/kernel/perf_event.c
@@ -590,7 +590,7 @@ static int tile_event_set_period(struct perf_event *event)
  */
 static void tile_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -616,7 +616,7 @@ static void tile_pmu_stop(struct perf_event *event, int flags)
  */
 static void tile_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = event->hw.idx;
 
 	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
@@ -650,7 +650,7 @@ static void tile_pmu_start(struct perf_event *event, int flags)
  */
 static int tile_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc;
 	unsigned long mask;
 	int b, max_cnt;
@@ -706,7 +706,7 @@ static int tile_pmu_add(struct perf_event *event, int flags)
  */
 static void tile_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	/*
@@ -880,14 +880,14 @@ static struct pmu tilera_pmu = {
 int tile_pmu_handle_irq(struct pt_regs *regs, int fault)
 {
 	struct perf_sample_data data;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	u64 val;
 	unsigned long status;
 	int bit;
 
-	__get_cpu_var(perf_irqs)++;
+	__this_cpu_inc(perf_irqs);
 
 	if (!atomic_read(&tile_active_events))
 		return 0;
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 16ed58948757..0050cbc1d9de 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -64,7 +64,7 @@ early_param("idle", idle_setup);
 
 void arch_cpu_idle(void)
 {
-	__get_cpu_var(irq_stat).idle_timestamp = jiffies;
+	__this_cpu_write(irq_stat.idle_timestamp, jiffies);
 	_cpu_idle();
 }
 
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 112ababa9e55..b9736ded06f2 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -1218,7 +1218,8 @@ static void __init validate_hv(void)
 	 * various asid variables to their appropriate initial states.
 	 */
 	asid_range = hv_inquire_asid(0);
-	__get_cpu_var(current_asid) = min_asid = asid_range.start;
+	min_asid = asid_range.start;
+	__this_cpu_write(current_asid, min_asid);
 	max_asid = asid_range.start + asid_range.size - 1;
 
 	if (hv_confstr(HV_CONFSTR_CHIP_MODEL, (HV_VirtAddr)chip_model,
diff --git a/arch/tile/kernel/single_step.c b/arch/tile/kernel/single_step.c
index de07fa7d1315..6cb2ce31b5a2 100644
--- a/arch/tile/kernel/single_step.c
+++ b/arch/tile/kernel/single_step.c
@@ -740,7 +740,7 @@ static DEFINE_PER_CPU(unsigned long, ss_saved_pc);
 
 void gx_singlestep_handle(struct pt_regs *regs, int fault_num)
 {
-	unsigned long *ss_pc = &__get_cpu_var(ss_saved_pc);
+	unsigned long *ss_pc = this_cpu_ptr(&ss_saved_pc);
 	struct thread_info *info = (void *)current_thread_info();
 	int is_single_step = test_ti_thread_flag(info, TIF_SINGLESTEP);
 	unsigned long control = __insn_mfspr(SPR_SINGLE_STEP_CONTROL_K);
@@ -766,7 +766,7 @@ void gx_singlestep_handle(struct pt_regs *regs, int fault_num)
 
 void single_step_once(struct pt_regs *regs)
 {
-	unsigned long *ss_pc = &__get_cpu_var(ss_saved_pc);
+	unsigned long *ss_pc = this_cpu_ptr(&ss_saved_pc);
 	unsigned long control = __insn_mfspr(SPR_SINGLE_STEP_CONTROL_K);
 
 	*ss_pc = regs->pc;
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index 19eaa62d456a..d3c4ed780ce2 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -189,7 +189,7 @@ EXPORT_SYMBOL(flush_icache_range);
 /* Called when smp_send_reschedule() triggers IRQ_RESCHEDULE. */
 static irqreturn_t handle_reschedule_ipi(int irq, void *token)
 {
-	__get_cpu_var(irq_stat).irq_resched_count++;
+	__this_cpu_inc(irq_stat.irq_resched_count);
 	scheduler_ipi();
 
 	return IRQ_HANDLED;
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index 732e9d138661..0d59a1b60c74 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -41,7 +41,7 @@ void __init smp_prepare_boot_cpu(void)
 	int cpu = smp_processor_id();
 	set_cpu_online(cpu, 1);
 	set_cpu_present(cpu, 1);
-	__get_cpu_var(cpu_state) = CPU_ONLINE;
+	__this_cpu_write(cpu_state, CPU_ONLINE);
 
 	init_messaging();
 }
@@ -158,7 +158,7 @@ static void start_secondary(void)
 	/* printk(KERN_DEBUG "Initializing CPU#%d\n", cpuid); */
 
 	/* Initialize the current asid for our first page table. */
-	__get_cpu_var(current_asid) = min_asid;
+	__this_cpu_write(current_asid, min_asid);
 
 	/* Set up this thread as another owner of the init_mm */
 	atomic_inc(&init_mm.mm_count);
@@ -201,7 +201,7 @@ void online_secondary(void)
 	notify_cpu_starting(smp_processor_id());
 
 	set_cpu_online(smp_processor_id(), 1);
-	__get_cpu_var(cpu_state) = CPU_ONLINE;
+	__this_cpu_write(cpu_state, CPU_ONLINE);
 
 	/* Set up tile-specific state for this cpu. */
 	setup_cpu(0);
diff --git a/arch/tile/kernel/time.c b/arch/tile/kernel/time.c
index c1b362277fb7..b854a1cd0079 100644
--- a/arch/tile/kernel/time.c
+++ b/arch/tile/kernel/time.c
@@ -162,7 +162,7 @@ static DEFINE_PER_CPU(struct clock_event_device, tile_timer) = {
 
 void setup_tile_timer(void)
 {
-	struct clock_event_device *evt = &__get_cpu_var(tile_timer);
+	struct clock_event_device *evt = this_cpu_ptr(&tile_timer);
 
 	/* Fill in fields that are speed-specific. */
 	clockevents_calc_mult_shift(evt, cycles_per_sec, TILE_MINSEC);
@@ -182,7 +182,7 @@ void setup_tile_timer(void)
 void do_timer_interrupt(struct pt_regs *regs, int fault_num)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct clock_event_device *evt = &__get_cpu_var(tile_timer);
+	struct clock_event_device *evt = this_cpu_ptr(&tile_timer);
 
 	/*
 	 * Mask the timer interrupt here, since we are a oneshot timer
@@ -194,7 +194,7 @@ void do_timer_interrupt(struct pt_regs *regs, int fault_num)
 	irq_enter();
 
 	/* Track interrupt count. */
-	__get_cpu_var(irq_stat).irq_timer_count++;
+	__this_cpu_inc(irq_stat.irq_timer_count);
 
 	/* Call the generic timer handler */
 	evt->event_handler(evt);
@@ -235,7 +235,7 @@ cycles_t ns2cycles(unsigned long nsecs)
 	 * We do not have to disable preemption here as each core has the same
 	 * clock frequency.
 	 */
-	struct clock_event_device *dev = &__raw_get_cpu_var(tile_timer);
+	struct clock_event_device *dev = raw_cpu_ptr(&tile_timer);
 
 	/*
 	 * as in clocksource.h and x86's timer.h, we split the calculation
diff --git a/arch/tile/mm/highmem.c b/arch/tile/mm/highmem.c
index 0dc218294770..6aa2f2625447 100644
--- a/arch/tile/mm/highmem.c
+++ b/arch/tile/mm/highmem.c
@@ -103,7 +103,7 @@ static void kmap_atomic_register(struct page *page, int type,
 	spin_lock(&amp_lock);
 
 	/* With interrupts disabled, now fill in the per-cpu info. */
-	amp = &__get_cpu_var(amps).per_type[type];
+	amp = this_cpu_ptr(&amps.per_type[type]);
 	amp->page = page;
 	amp->cpu = smp_processor_id();
 	amp->va = va;
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index a092e393bd20..caa270165f86 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -593,14 +593,14 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base)
 	interrupt_mask_set_mask(-1ULL);
 	rc = flush_and_install_context(__pa(pgtables),
 				       init_pgprot((unsigned long)pgtables),
-				       __get_cpu_var(current_asid),
+				       __this_cpu_read(current_asid),
 				       cpumask_bits(my_cpu_mask));
 	interrupt_mask_restore_mask(irqmask);
 	BUG_ON(rc != 0);
 
 	/* Copy the page table back to the normal swapper_pg_dir. */
 	memcpy(pgd_base, pgtables, sizeof(pgtables));
-	__install_page_table(pgd_base, __get_cpu_var(current_asid),
+	__install_page_table(pgd_base, __this_cpu_read(current_asid),
 			     swapper_pgprot);
 
 	/*
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index 6915d28cf118..87bc86821bc9 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -39,7 +39,8 @@ config LOCKDEP_SUPPORT
 
 config STACKTRACE_SUPPORT
 	bool
-	default n
+	default y
+	select STACKTRACE
 
 config GENERIC_CALIBRATE_DELAY
 	bool
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 7d26d9c0b2fb..f70dd540655d 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -659,10 +659,6 @@ static int __init eth_setup(char *str)
 	}
 
 	new = alloc_bootmem(sizeof(*new));
-	if (new == NULL) {
-		printk(KERN_ERR "eth_init : alloc_bootmem failed\n");
-		return 1;
-	}
 
 	INIT_LIST_HEAD(&new->list);
 	new->index = n;
diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c
index 9e3a72205827..dd16c902ff70 100644
--- a/arch/um/drivers/random.c
+++ b/arch/um/drivers/random.c
@@ -79,7 +79,6 @@ static ssize_t rng_dev_read (struct file *filp, char __user *buf, size_t size,
 			set_task_state(current, TASK_INTERRUPTIBLE);
 
 			schedule();
-			set_task_state(current, TASK_RUNNING);
 			remove_wait_queue(&host_read_wait, &wait);
 
 			if (atomic_dec_and_test(&host_sleep_count)) {
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 3716e6952554..e8ab93c3e638 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -1277,7 +1277,7 @@ static void do_ubd_request(struct request_queue *q)
 
 	while(1){
 		struct ubd *dev = q->queuedata;
-		if(dev->end_sg == 0){
+		if(dev->request == NULL){
 			struct request *req = blk_fetch_request(q);
 			if(req == NULL)
 				return;
@@ -1299,7 +1299,8 @@ static void do_ubd_request(struct request_queue *q)
 				return;
 			}
 			prepare_flush_request(req, io_req);
-			submit_request(io_req, dev);
+			if (submit_request(io_req, dev) == false)
+				return;
 		}
 
 		while(dev->start_sg < dev->end_sg){
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 7bd64aa2e94a..244b12c8cb39 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -14,6 +14,7 @@ generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += io.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += mcs_spinlock.h
 generic-y += mutex.h
diff --git a/arch/um/include/asm/stacktrace.h b/arch/um/include/asm/stacktrace.h
new file mode 100644
index 000000000000..9a864328c67f
--- /dev/null
+++ b/arch/um/include/asm/stacktrace.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_UML_STACKTRACE_H
+#define _ASM_UML_STACKTRACE_H
+
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+
+struct stack_frame {
+	struct stack_frame *next_frame;
+	unsigned long return_address;
+};
+
+struct stacktrace_ops {
+	void (*address)(void *data, unsigned long address, int reliable);
+};
+
+#ifdef CONFIG_FRAME_POINTER
+static inline unsigned long
+get_frame_pointer(struct task_struct *task, struct pt_regs *segv_regs)
+{
+	if (!task || task == current)
+		return segv_regs ? PT_REGS_BP(segv_regs) : current_bp();
+	return KSTK_EBP(task);
+}
+#else
+static inline unsigned long
+get_frame_pointer(struct task_struct *task, struct pt_regs *segv_regs)
+{
+	return 0;
+}
+#endif
+
+static inline unsigned long
+*get_stack_pointer(struct task_struct *task, struct pt_regs *segv_regs)
+{
+	if (!task || task == current)
+		return segv_regs ? (unsigned long *)PT_REGS_SP(segv_regs) : current_sp();
+	return (unsigned long *)KSTK_ESP(task);
+}
+
+void dump_trace(struct task_struct *tsk, const struct stacktrace_ops *ops, void *data);
+
+#endif /* _ASM_UML_STACKTRACE_H */
diff --git a/arch/um/include/shared/mem_user.h b/arch/um/include/shared/mem_user.h
index 46384acd547b..cb84414e3e66 100644
--- a/arch/um/include/shared/mem_user.h
+++ b/arch/um/include/shared/mem_user.h
@@ -49,7 +49,7 @@ extern int iomem_size;
 extern int init_mem_user(void);
 extern void setup_memory(void *entry);
 extern unsigned long find_iomem(char *driver, unsigned long *len_out);
-extern int init_maps(unsigned long physmem, unsigned long iomem,
+extern void mem_total_pages(unsigned long physmem, unsigned long iomem,
 		     unsigned long highmem);
 extern unsigned long get_vm(unsigned long len);
 extern void setup_physmem(unsigned long start, unsigned long usable,
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index d8b78a03855c..2d840a070c8b 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
 obj-$(CONFIG_GPROF)	+= gprof_syms.o
 obj-$(CONFIG_GCOV)	+= gmon_syms.o
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
+obj-$(CONFIG_STACKTRACE) += stacktrace.o
 
 USER_OBJS := config.o
 
diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c
index 30fdd5d0067b..549ecf3f5857 100644
--- a/arch/um/kernel/physmem.c
+++ b/arch/um/kernel/physmem.c
@@ -22,39 +22,19 @@ EXPORT_SYMBOL(high_physmem);
 
 extern unsigned long long physmem_size;
 
-int __init init_maps(unsigned long physmem, unsigned long iomem,
+void __init mem_total_pages(unsigned long physmem, unsigned long iomem,
 		     unsigned long highmem)
 {
-	struct page *p, *map;
-	unsigned long phys_len, phys_pages, highmem_len, highmem_pages;
-	unsigned long iomem_len, iomem_pages, total_len, total_pages;
-	int i;
-
-	phys_pages = physmem >> PAGE_SHIFT;
-	phys_len = phys_pages * sizeof(struct page);
-
-	iomem_pages = iomem >> PAGE_SHIFT;
-	iomem_len = iomem_pages * sizeof(struct page);
+	unsigned long phys_pages, highmem_pages;
+	unsigned long iomem_pages, total_pages;
 
+	phys_pages    = physmem >> PAGE_SHIFT;
+	iomem_pages   = iomem   >> PAGE_SHIFT;
 	highmem_pages = highmem >> PAGE_SHIFT;
-	highmem_len = highmem_pages * sizeof(struct page);
-
-	total_pages = phys_pages + iomem_pages + highmem_pages;
-	total_len = phys_len + iomem_len + highmem_len;
 
-	map = alloc_bootmem_low_pages(total_len);
-	if (map == NULL)
-		return -ENOMEM;
-
-	for (i = 0; i < total_pages; i++) {
-		p = &map[i];
-		memset(p, 0, sizeof(struct page));
-		SetPageReserved(p);
-		INIT_LIST_HEAD(&p->lru);
-	}
+	total_pages   = phys_pages + iomem_pages + highmem_pages;
 
 	max_mapnr = total_pages;
-	return 0;
 }
 
 void map_memory(unsigned long virt, unsigned long phys, unsigned long len,
diff --git a/arch/um/kernel/stacktrace.c b/arch/um/kernel/stacktrace.c
new file mode 100644
index 000000000000..ebe7bcf62684
--- /dev/null
+++ b/arch/um/kernel/stacktrace.c
@@ -0,0 +1,80 @@
+/*
+ * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Copyright (C) 2013 Richard Weinberger <richard@nod.at>
+ * Copyright (C) 2014 Google Inc., Author: Daniel Walter <dwalter@google.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kallsyms.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/stacktrace.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <asm/stacktrace.h>
+
+void dump_trace(struct task_struct *tsk,
+		const struct stacktrace_ops *ops,
+		void *data)
+{
+	int reliable = 0;
+	unsigned long *sp, bp, addr;
+	struct pt_regs *segv_regs = tsk->thread.segv_regs;
+	struct stack_frame *frame;
+
+	bp = get_frame_pointer(tsk, segv_regs);
+	sp = get_stack_pointer(tsk, segv_regs);
+
+	frame = (struct stack_frame *)bp;
+	while (((long) sp & (THREAD_SIZE-1)) != 0) {
+		addr = *sp;
+		if (__kernel_text_address(addr)) {
+			reliable = 0;
+			if ((unsigned long) sp == bp + sizeof(long)) {
+				frame = frame ? frame->next_frame : NULL;
+				bp = (unsigned long)frame;
+				reliable = 1;
+			}
+			ops->address(data, addr, reliable);
+		}
+		sp++;
+	}
+}
+
+static void save_addr(void *data, unsigned long address, int reliable)
+{
+	struct stack_trace *trace = data;
+
+	if (!reliable)
+		return;
+	if (trace->nr_entries >= trace->max_entries)
+		return;
+
+	trace->entries[trace->nr_entries++] = address;
+}
+
+static const struct stacktrace_ops dump_ops = {
+	.address = save_addr
+};
+
+static void __save_stack_trace(struct task_struct *tsk, struct stack_trace *trace)
+{
+	dump_trace(tsk, &dump_ops, trace);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	__save_stack_trace(current, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	__save_stack_trace(tsk, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c
index 799d7e413bf5..894c8d303cda 100644
--- a/arch/um/kernel/sysrq.c
+++ b/arch/um/kernel/sysrq.c
@@ -12,57 +12,20 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <asm/sysrq.h>
+#include <asm/stacktrace.h>
 #include <os.h>
 
-struct stack_frame {
-	struct stack_frame *next_frame;
-	unsigned long return_address;
-};
-
-static void do_stack_trace(unsigned long *sp, unsigned long bp)
+static void _print_addr(void *data, unsigned long address, int reliable)
 {
-	int reliable;
-	unsigned long addr;
-	struct stack_frame *frame = (struct stack_frame *)bp;
-
-	printk(KERN_INFO "Call Trace:\n");
-	while (((long) sp & (THREAD_SIZE-1)) != 0) {
-		addr = *sp;
-		if (__kernel_text_address(addr)) {
-			reliable = 0;
-			if ((unsigned long) sp == bp + sizeof(long)) {
-				frame = frame ? frame->next_frame : NULL;
-				bp = (unsigned long)frame;
-				reliable = 1;
-			}
-
-			printk(KERN_INFO " [<%08lx>]", addr);
-			printk(KERN_CONT " %s", reliable ? "" : "? ");
-			print_symbol(KERN_CONT "%s", addr);
-			printk(KERN_CONT "\n");
-		}
-		sp++;
-	}
-	printk(KERN_INFO "\n");
+	pr_info(" [<%08lx>]", address);
+	pr_cont(" %s", reliable ? "" : "? ");
+	print_symbol("%s", address);
+	pr_cont("\n");
 }
 
-static unsigned long get_frame_pointer(struct task_struct *task,
-				       struct pt_regs *segv_regs)
-{
-	if (!task || task == current)
-		return segv_regs ? PT_REGS_BP(segv_regs) : current_bp();
-	else
-		return KSTK_EBP(task);
-}
-
-static unsigned long *get_stack_pointer(struct task_struct *task,
-					struct pt_regs *segv_regs)
-{
-	if (!task || task == current)
-		return segv_regs ? (unsigned long *)PT_REGS_SP(segv_regs) : current_sp();
-	else
-		return (unsigned long *)KSTK_ESP(task);
-}
+static const struct stacktrace_ops stackops = {
+	.address = _print_addr
+};
 
 void show_stack(struct task_struct *task, unsigned long *stack)
 {
@@ -71,7 +34,7 @@ void show_stack(struct task_struct *task, unsigned long *stack)
 	int i;
 
 	if (!segv_regs && os_is_signal_stack()) {
-		printk(KERN_ERR "Received SIGSEGV in SIGSEGV handler,"
+		pr_err("Received SIGSEGV in SIGSEGV handler,"
 				" aborting stack trace!\n");
 		return;
 	}
@@ -83,16 +46,18 @@ void show_stack(struct task_struct *task, unsigned long *stack)
 	if (!stack)
 		sp = get_stack_pointer(task, segv_regs);
 
-	printk(KERN_INFO "Stack:\n");
+	pr_info("Stack:\n");
 	stack = sp;
 	for (i = 0; i < 3 * STACKSLOTS_PER_LINE; i++) {
 		if (kstack_end(stack))
 			break;
 		if (i && ((i % STACKSLOTS_PER_LINE) == 0))
-			printk(KERN_CONT "\n");
-		printk(KERN_CONT " %08lx", *stack++);
+			pr_cont("\n");
+		pr_cont(" %08lx", *stack++);
 	}
-	printk(KERN_CONT "\n");
+	pr_cont("\n");
 
-	do_stack_trace(sp, bp);
+	pr_info("Call Trace:\n");
+	dump_trace(current, &stackops, NULL);
+	pr_info("\n");
 }
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 016adf0985d5..9274eae6ae7b 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -348,12 +348,7 @@ int __init linux_main(int argc, char **argv)
 	start_vm = VMALLOC_START;
 
 	setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem);
-	if (init_maps(physmem_size, iomem_size, highmem)) {
-		printf("Failed to allocate mem_map for %Lu bytes of physical "
-		       "memory and %Lu bytes of highmem\n", physmem_size,
-		       highmem);
-		exit(1);
-	}
+	mem_total_pages(physmem_size, iomem_size, highmem);
 
 	virtmem_size = physmem_size;
 	stack = (unsigned long) argv;
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 1e5fb872a4aa..5a2bb53faa42 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -22,6 +22,7 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h
diff --git a/arch/unicore32/include/mach/pm.h b/arch/unicore32/include/mach/pm.h
index 4dcd34ae194c..77b522694e74 100644
--- a/arch/unicore32/include/mach/pm.h
+++ b/arch/unicore32/include/mach/pm.h
@@ -36,8 +36,5 @@ extern int puv3_pm_enter(suspend_state_t state);
 /* Defined in hibernate_asm.S */
 extern int restore_image(pgd_t *resume_pg_dir, struct pbe *restore_pblist);
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
 extern struct pbe *restore_pblist;
 #endif
diff --git a/arch/unicore32/kernel/hibernate.c b/arch/unicore32/kernel/hibernate.c
index d75ef8b6cb56..9969ec374abb 100644
--- a/arch/unicore32/kernel/hibernate.c
+++ b/arch/unicore32/kernel/hibernate.c
@@ -18,6 +18,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
+#include <asm/sections.h>
 #include <asm/suspend.h>
 
 #include "mach/pm.h"
diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore
index 7cab8c08e6d1..aff152c87cf4 100644
--- a/arch/x86/.gitignore
+++ b/arch/x86/.gitignore
@@ -1,4 +1,6 @@
 boot/compressed/vmlinux
 tools/test_get_len
 tools/insn_sanity
+purgatory/kexec-purgatory.c
+purgatory/purgatory.ro
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e4b1f431c7ed..f2327e88e07c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -30,7 +30,6 @@ config X86
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
 	select ARCH_SUPPORTS_INT128 if X86_64
-	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_PCSPKR_PLATFORM
@@ -492,6 +491,36 @@ config X86_INTEL_LPSS
 	  things like clock tree (common clock framework) and pincontrol
 	  which are needed by the LPSS peripheral drivers.
 
+config IOSF_MBI
+	tristate "Intel SoC IOSF Sideband support for SoC platforms"
+	depends on PCI
+	---help---
+	  This option enables sideband register access support for Intel SoC
+	  platforms. On these platforms the IOSF sideband is used in lieu of
+	  MSR's for some register accesses, mostly but not limited to thermal
+	  and power. Drivers may query the availability of this device to
+	  determine if they need the sideband in order to work on these
+	  platforms. The sideband is available on the following SoC products.
+	  This list is not meant to be exclusive.
+	   - BayTrail
+	   - Braswell
+	   - Quark
+
+	  You should say Y if you are running a kernel on one of these SoC's.
+
+config IOSF_MBI_DEBUG
+	bool "Enable IOSF sideband access through debugfs"
+	depends on IOSF_MBI && DEBUG_FS
+	---help---
+	  Select this option to expose the IOSF sideband access registers (MCR,
+	  MDR, MCRX) through debugfs to write and read register information from
+	  different units on the SoC. This is most useful for obtaining device
+	  state information for debug and analysis. As this is a general access
+	  mechanism, users of this option would have specific knowledge of the
+	  device they want to access.
+
+	  If you don't require the option or are in doubt, say N.
+
 config X86_RDC321X
 	bool "RDC R-321x SoC"
 	depends on X86_32
@@ -2455,11 +2484,6 @@ config X86_DMA_REMAP
 	bool
 	depends on STA2X11
 
-config IOSF_MBI
-	tristate
-	default m
-	depends on PCI
-
 config PMC_ATOM
 	def_bool y
         depends on PCI
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5692d6ac0f18..920e6160c535 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -50,9 +50,6 @@ ifeq ($(CONFIG_X86_32),y)
 
         KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
 
-        # Don't autogenerate MMX or SSE instructions
-        KBUILD_CFLAGS += -mno-mmx -mno-sse
-
         # Never want PIC in a 32-bit kernel, prevent breakage with GCC built
         # with nonstandard options
         KBUILD_CFLAGS += -fno-pic
@@ -80,8 +77,7 @@ else
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
-        # Don't autogenerate traditional x87, MMX or SSE instructions
-        KBUILD_CFLAGS += -mno-mmx -mno-sse
+        # Don't autogenerate traditional x87 instructions
         KBUILD_CFLAGS += $(call cc-option,-mno-80387)
         KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
 
@@ -168,7 +164,7 @@ KBUILD_CFLAGS += -Wno-sign-compare
 #
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 # prevent gcc from generating any FP code by mistake
-KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
+KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
 KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
 
 KBUILD_CFLAGS += $(mflags-y)
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 7c68808edeb7..bb1376381985 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -194,7 +194,7 @@ static bool mem_avoid_overlap(struct mem_vector *img)
 	while (ptr) {
 		struct mem_vector avoid;
 
-		avoid.start = (u64)ptr;
+		avoid.start = (unsigned long)ptr;
 		avoid.size = sizeof(*ptr) + ptr->len;
 
 		if (mem_overlaps(img, &avoid))
diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c
index 4579eff0ef4d..637097e66a62 100644
--- a/arch/x86/boot/mkcpustr.c
+++ b/arch/x86/boot/mkcpustr.c
@@ -16,6 +16,7 @@
 #include <stdio.h>
 
 #include "../include/asm/required-features.h"
+#include "../include/asm/disabled-features.h"
 #include "../include/asm/cpufeature.h"
 #include "../kernel/cpu/capflags.c"
 
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index d21ff89207cd..df91466f973d 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -308,11 +308,8 @@ static int load_aout_binary(struct linux_binprm *bprm)
 		(current->mm->start_brk = N_BSSADDR(ex));
 
 	retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
-	if (retval < 0) {
-		/* Someone check-me: is this error path enough? */
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		return retval;
-	}
 
 	install_exec_creds(bprm);
 
@@ -324,17 +321,13 @@ static int load_aout_binary(struct linux_binprm *bprm)
 
 		error = vm_brk(text_addr & PAGE_MASK, map_size);
 
-		if (error != (text_addr & PAGE_MASK)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != (text_addr & PAGE_MASK))
 			return error;
-		}
 
 		error = read_code(bprm->file, text_addr, 32,
 				  ex.a_text + ex.a_data);
-		if ((signed long)error < 0) {
-			send_sig(SIGKILL, current, 0);
+		if ((signed long)error < 0)
 			return error;
-		}
 	} else {
 #ifdef WARN_OLD
 		static unsigned long error_time, error_time2;
@@ -368,20 +361,16 @@ static int load_aout_binary(struct linux_binprm *bprm)
 				MAP_EXECUTABLE | MAP_32BIT,
 				fd_offset);
 
-		if (error != N_TXTADDR(ex)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != N_TXTADDR(ex))
 			return error;
-		}
 
 		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
 				PROT_READ | PROT_WRITE | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
 				MAP_EXECUTABLE | MAP_32BIT,
 				fd_offset + ex.a_text);
-		if (error != N_DATADDR(ex)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != N_DATADDR(ex))
 			return error;
-		}
 	}
 beyond_if:
 	set_binfmt(&aout_format);
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 4299eb05023c..711de084ab57 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -151,6 +151,16 @@ ENTRY(ia32_sysenter_target)
 1:	movl	(%rbp),%ebp
 	_ASM_EXTABLE(1b,ia32_badarg)
 	ASM_CLAC
+
+	/*
+	 * Sysenter doesn't filter flags, so we need to clear NT
+	 * ourselves.  To save a few cycles, we can check whether
+	 * NT was set instead of doing an unconditional popfq.
+	 */
+	testl $X86_EFLAGS_NT,EFLAGS(%rsp)	/* saved EFLAGS match cpu */
+	jnz sysenter_fix_flags
+sysenter_flags_fixed:
+
 	orl     $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	testl   $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	CFI_REMEMBER_STATE
@@ -184,6 +194,8 @@ sysexit_from_sys_call:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS_SYSEXIT32
 
+	CFI_RESTORE_STATE
+
 #ifdef CONFIG_AUDITSYSCALL
 	.macro auditsys_entry_common
 	movl %esi,%r9d			/* 6th arg: 4th syscall arg */
@@ -226,7 +238,6 @@ sysexit_from_sys_call:
 	.endm
 
 sysenter_auditsys:
-	CFI_RESTORE_STATE
 	auditsys_entry_common
 	movl %ebp,%r9d			/* reload 6th syscall arg */
 	jmp sysenter_dispatch
@@ -235,6 +246,11 @@ sysexit_audit:
 	auditsys_exit sysexit_from_sys_call
 #endif
 
+sysenter_fix_flags:
+	pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+	popfq_cfi
+	jmp sysenter_flags_fixed
+
 sysenter_tracesys:
 #ifdef CONFIG_AUDITSYSCALL
 	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 3bf000fab0ae..d55a210a49bf 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -6,6 +6,7 @@ genhdr-y += unistd_x32.h
 
 generic-y += clkdev.h
 generic-y += cputime.h
+generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += mcs_spinlock.h
 generic-y += scatterlist.h
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 6dd1c7dd0473..5e5cd123fdfb 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -24,7 +24,7 @@
  */
 static inline int atomic_read(const atomic_t *v)
 {
-	return (*(volatile int *)&(v)->counter);
+	return ACCESS_ONCE((v)->counter);
 }
 
 /**
@@ -219,21 +219,6 @@ static inline short int atomic_inc_short(short int *v)
 	return *v;
 }
 
-#ifdef CONFIG_X86_64
-/**
- * atomic_or_long - OR of two long integers
- * @v1: pointer to type unsigned long
- * @v2: pointer to type unsigned long
- *
- * Atomically ORs @v1 and @v2
- * Returns the result of the OR
- */
-static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
-{
-	asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
-}
-#endif
-
 /* These are x86-specific, used by some header files */
 #define atomic_clear_mask(mask, addr)				\
 	asm volatile(LOCK_PREFIX "andl %0,%1"			\
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 46e9052bbd28..f8d273e18516 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -18,7 +18,7 @@
  */
 static inline long atomic64_read(const atomic64_t *v)
 {
-	return (*(volatile long *)&(v)->counter);
+	return ACCESS_ONCE((v)->counter);
 }
 
 /**
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index cb4c73bfeb48..76659b67fd11 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -85,7 +85,7 @@ For 32-bit we have the following conventions - kernel is built with
 #define ARGOFFSET	R11
 #define SWFRAME		ORIG_RAX
 
-	.macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1
+	.macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1, rax_enosys=0
 	subq  $9*8+\addskip, %rsp
 	CFI_ADJUST_CFA_OFFSET	9*8+\addskip
 	movq_cfi rdi, 8*8
@@ -96,7 +96,11 @@ For 32-bit we have the following conventions - kernel is built with
 	movq_cfi rcx, 5*8
 	.endif
 
+	.if \rax_enosys
+	movq $-ENOSYS, 4*8(%rsp)
+	.else
 	movq_cfi rax, 4*8
+	.endif
 
 	.if \save_r891011
 	movq_cfi r8,  3*8
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 094292a63e74..0bb1335313b2 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -8,6 +8,10 @@
 #include <asm/required-features.h>
 #endif
 
+#ifndef _ASM_X86_DISABLED_FEATURES_H
+#include <asm/disabled-features.h>
+#endif
+
 #define NCAPINTS	11	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
@@ -282,6 +286,18 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) ||	\
 	   (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
 
+#define DISABLED_MASK_BIT_SET(bit)					\
+	 ( (((bit)>>5)==0 && (1UL<<((bit)&31) & DISABLED_MASK0)) ||	\
+	   (((bit)>>5)==1 && (1UL<<((bit)&31) & DISABLED_MASK1)) ||	\
+	   (((bit)>>5)==2 && (1UL<<((bit)&31) & DISABLED_MASK2)) ||	\
+	   (((bit)>>5)==3 && (1UL<<((bit)&31) & DISABLED_MASK3)) ||	\
+	   (((bit)>>5)==4 && (1UL<<((bit)&31) & DISABLED_MASK4)) ||	\
+	   (((bit)>>5)==5 && (1UL<<((bit)&31) & DISABLED_MASK5)) ||	\
+	   (((bit)>>5)==6 && (1UL<<((bit)&31) & DISABLED_MASK6)) ||	\
+	   (((bit)>>5)==7 && (1UL<<((bit)&31) & DISABLED_MASK7)) ||	\
+	   (((bit)>>5)==8 && (1UL<<((bit)&31) & DISABLED_MASK8)) ||	\
+	   (((bit)>>5)==9 && (1UL<<((bit)&31) & DISABLED_MASK9)) )
+
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
 	 test_cpu_cap(c, bit))
@@ -290,6 +306,18 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : 	\
 	 x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
 
+/*
+ * This macro is for detection of features which need kernel
+ * infrastructure to be used.  It may *not* directly test the CPU
+ * itself.  Use the cpu_has() family if you want true runtime
+ * testing of CPU features, like in hypervisor code where you are
+ * supporting a possible guest feature where host support for it
+ * is not relevant.
+ */
+#define cpu_feature_enabled(bit)	\
+	(__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 :	\
+	 cpu_has(&boot_cpu_data, bit))
+
 #define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
 
 #define set_cpu_cap(c, bit)	set_bit(bit, (unsigned long *)((c)->x86_capability))
@@ -304,11 +332,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 } while (0)
 
 #define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
-#define cpu_has_vme		boot_cpu_has(X86_FEATURE_VME)
 #define cpu_has_de		boot_cpu_has(X86_FEATURE_DE)
 #define cpu_has_pse		boot_cpu_has(X86_FEATURE_PSE)
 #define cpu_has_tsc		boot_cpu_has(X86_FEATURE_TSC)
-#define cpu_has_pae		boot_cpu_has(X86_FEATURE_PAE)
 #define cpu_has_pge		boot_cpu_has(X86_FEATURE_PGE)
 #define cpu_has_apic		boot_cpu_has(X86_FEATURE_APIC)
 #define cpu_has_sep		boot_cpu_has(X86_FEATURE_SEP)
@@ -324,9 +350,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define cpu_has_avx2		boot_cpu_has(X86_FEATURE_AVX2)
 #define cpu_has_ht		boot_cpu_has(X86_FEATURE_HT)
 #define cpu_has_nx		boot_cpu_has(X86_FEATURE_NX)
-#define cpu_has_k6_mtrr		boot_cpu_has(X86_FEATURE_K6_MTRR)
-#define cpu_has_cyrix_arr	boot_cpu_has(X86_FEATURE_CYRIX_ARR)
-#define cpu_has_centaur_mcr	boot_cpu_has(X86_FEATURE_CENTAUR_MCR)
 #define cpu_has_xstore		boot_cpu_has(X86_FEATURE_XSTORE)
 #define cpu_has_xstore_enabled	boot_cpu_has(X86_FEATURE_XSTORE_EN)
 #define cpu_has_xcrypt		boot_cpu_has(X86_FEATURE_XCRYPT)
@@ -361,25 +384,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define cpu_has_eager_fpu	boot_cpu_has(X86_FEATURE_EAGER_FPU)
 #define cpu_has_topoext		boot_cpu_has(X86_FEATURE_TOPOEXT)
 
-#ifdef CONFIG_X86_64
-
-#undef  cpu_has_vme
-#define cpu_has_vme		0
-
-#undef  cpu_has_pae
-#define cpu_has_pae		___BUG___
-
-#undef  cpu_has_k6_mtrr
-#define cpu_has_k6_mtrr		0
-
-#undef  cpu_has_cyrix_arr
-#define cpu_has_cyrix_arr	0
-
-#undef  cpu_has_centaur_mcr
-#define cpu_has_centaur_mcr	0
-
-#endif /* CONFIG_X86_64 */
-
 #if __GNUC__ >= 4
 extern void warn_pre_alternatives(void);
 extern bool __static_cpu_has_safe(u16 bit);
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 4b528a970bd4..61fd18b83b6c 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -97,11 +97,11 @@ extern void hw_breakpoint_restore(void);
 DECLARE_PER_CPU(int, debug_stack_usage);
 static inline void debug_stack_usage_inc(void)
 {
-	__get_cpu_var(debug_stack_usage)++;
+	__this_cpu_inc(debug_stack_usage);
 }
 static inline void debug_stack_usage_dec(void)
 {
-	__get_cpu_var(debug_stack_usage)--;
+	__this_cpu_dec(debug_stack_usage);
 }
 int is_debug_stack(unsigned long addr);
 void debug_stack_set_zero(void);
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
new file mode 100644
index 000000000000..97534a7d38e3
--- /dev/null
+++ b/arch/x86/include/asm/disabled-features.h
@@ -0,0 +1,39 @@
+#ifndef _ASM_X86_DISABLED_FEATURES_H
+#define _ASM_X86_DISABLED_FEATURES_H
+
+/* These features, although they might be available in a CPU
+ * will not be used because the compile options to support
+ * them are not present.
+ *
+ * This code allows them to be checked and disabled at
+ * compile time without an explicit #ifdef.  Use
+ * cpu_feature_enabled().
+ */
+
+#ifdef CONFIG_X86_64
+# define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
+# define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
+# define DISABLE_CYRIX_ARR	(1<<(X86_FEATURE_CYRIX_ARR & 31))
+# define DISABLE_CENTAUR_MCR	(1<<(X86_FEATURE_CENTAUR_MCR & 31))
+#else
+# define DISABLE_VME		0
+# define DISABLE_K6_MTRR	0
+# define DISABLE_CYRIX_ARR	0
+# define DISABLE_CENTAUR_MCR	0
+#endif /* CONFIG_X86_64 */
+
+/*
+ * Make sure to add features to the correct mask
+ */
+#define DISABLED_MASK0	(DISABLE_VME)
+#define DISABLED_MASK1	0
+#define DISABLED_MASK2	0
+#define DISABLED_MASK3	(DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
+#define DISABLED_MASK4	0
+#define DISABLED_MASK5	0
+#define DISABLED_MASK6	0
+#define DISABLED_MASK7	0
+#define DISABLED_MASK8	0
+#define DISABLED_MASK9	0
+
+#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1a055c81d864..ca3347a9dab5 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -160,8 +160,9 @@ do {						\
 #define elf_check_arch(x)			\
 	((x)->e_machine == EM_X86_64)
 
-#define compat_elf_check_arch(x)		\
-	(elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+#define compat_elf_check_arch(x)					\
+	(elf_check_arch_ia32(x) ||					\
+	 (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64))
 
 #if __USER32_DS != __USER_DS
 # error "The following code assumes __USER32_DS == __USER_DS"
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 412ececa00b9..e97622f57722 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -344,7 +344,7 @@ static inline void __thread_fpu_end(struct task_struct *tsk)
 
 static inline void __thread_fpu_begin(struct task_struct *tsk)
 {
-	if (!static_cpu_has_safe(X86_FEATURE_EAGER_FPU))
+	if (!use_eager_fpu())
 		clts();
 	__thread_set_has_fpu(tsk);
 }
diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h
new file mode 100644
index 000000000000..78162f8e248b
--- /dev/null
+++ b/arch/x86/include/asm/irq_work.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_IRQ_WORK_H
+#define _ASM_IRQ_WORK_H
+
+#include <asm/processor.h>
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return cpu_has_apic;
+}
+
+#endif /* _ASM_IRQ_WORK_H */
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index 9067166409bf..bbe296e0bce1 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -43,7 +43,7 @@ struct extended_sigtable {
 #define DWSIZE			(sizeof(u32))
 
 #define get_totalsize(mc) \
-	(((struct microcode_intel *)mc)->hdr.totalsize ? \
+	(((struct microcode_intel *)mc)->hdr.datasize ? \
 	 ((struct microcode_intel *)mc)->hdr.totalsize : \
 	 DEFAULT_UCODE_TOTALSIZE)
 
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 4064acae625d..01b493e5a99b 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -9,7 +9,6 @@
 #ifdef CONFIG_NUMA
 
 #define NR_NODE_MEMBLKS		(MAX_NUMNODES*2)
-#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
 
 /*
  * Too small node sizes may confuse the VM badly. Usually they
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8249df45d2f2..8dfc9fd094a3 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -51,6 +51,14 @@
 	 ARCH_PERFMON_EVENTSEL_EDGE  |	\
 	 ARCH_PERFMON_EVENTSEL_INV   |	\
 	 ARCH_PERFMON_EVENTSEL_CMASK)
+#define X86_ALL_EVENT_FLAGS  			\
+	(ARCH_PERFMON_EVENTSEL_EDGE |  		\
+	 ARCH_PERFMON_EVENTSEL_INV | 		\
+	 ARCH_PERFMON_EVENTSEL_CMASK | 		\
+	 ARCH_PERFMON_EVENTSEL_ANY | 		\
+	 ARCH_PERFMON_EVENTSEL_PIN_CONTROL | 	\
+	 HSW_IN_TX | 				\
+	 HSW_IN_TX_CHECKPOINTED)
 #define AMD64_RAW_EVENT_MASK		\
 	(X86_RAW_EVENT_MASK          |  \
 	 AMD64_EVENTSEL_EVENT)
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 85e13ccf15c4..d725382c2ae0 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -189,7 +189,7 @@ static inline int p4_ht_thread(int cpu)
 {
 #ifdef CONFIG_SMP
 	if (smp_num_siblings == 2)
-		return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+		return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
 #endif
 	return 0;
 }
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 9ee322103c6d..b6c0b404898a 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -32,9 +32,6 @@ static inline void pgtable_cache_init(void) { }
 static inline void check_pgt_cache(void) { }
 void paging_init(void);
 
-extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
-
-
 /*
  * Define this if things work differently on an i386 and an i486:
  * it will (on an i486) warn about kernel memory accesses that are
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 3874693c0e53..4572b2f30237 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -116,7 +116,8 @@ static inline void native_pgd_clear(pgd_t *pgd)
 	native_set_pgd(pgd, native_make_pgd(0));
 }
 
-extern void sync_global_pgds(unsigned long start, unsigned long end);
+extern void sync_global_pgds(unsigned long start, unsigned long end,
+			     int removed);
 
 /*
  * Conversion functions: convert a page and protection to a page entry,
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index f216963760e5..07789647bf33 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -23,7 +23,6 @@
 #define _PAGE_BIT_SPECIAL	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_SPLITTING	_PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */
-#define _PAGE_BIT_IOMAP		_PAGE_BIT_SOFTW2 /* flag used to indicate IO mapping */
 #define _PAGE_BIT_HIDDEN	_PAGE_BIT_SOFTW3 /* hidden by kmemcheck */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
@@ -52,7 +51,7 @@
 #define _PAGE_PSE	(_AT(pteval_t, 1) << _PAGE_BIT_PSE)
 #define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
 #define _PAGE_SOFTW1	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
-#define _PAGE_IOMAP	(_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
+#define _PAGE_SOFTW2	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2)
 #define _PAGE_PAT	(_AT(pteval_t, 1) << _PAGE_BIT_PAT)
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
@@ -168,10 +167,10 @@
 #define __PAGE_KERNEL_LARGE_NOCACHE	(__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
 #define __PAGE_KERNEL_LARGE_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)
 
-#define __PAGE_KERNEL_IO		(__PAGE_KERNEL | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_NOCACHE	(__PAGE_KERNEL_NOCACHE | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_UC_MINUS	(__PAGE_KERNEL_UC_MINUS | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_WC		(__PAGE_KERNEL_WC | _PAGE_IOMAP)
+#define __PAGE_KERNEL_IO		(__PAGE_KERNEL)
+#define __PAGE_KERNEL_IO_NOCACHE	(__PAGE_KERNEL_NOCACHE)
+#define __PAGE_KERNEL_IO_UC_MINUS	(__PAGE_KERNEL_UC_MINUS)
+#define __PAGE_KERNEL_IO_WC		(__PAGE_KERNEL_WC)
 
 #define PAGE_KERNEL			__pgprot(__PAGE_KERNEL)
 #define PAGE_KERNEL_RO			__pgprot(__PAGE_KERNEL_RO)
@@ -325,6 +324,20 @@ static inline pteval_t pte_flags(pte_t pte)
 	return native_pte_val(pte) & PTE_FLAGS_MASK;
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+/* Set of bits that distinguishes present, prot_none and numa ptes */
+#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)
+static inline pteval_t ptenuma_flags(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_NUMA_MASK;
+}
+
+static inline pmdval_t pmdnuma_flags(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_NUMA_MASK;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 #define pgprot_val(x)	((x).pgprot)
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6205f0c434db..86fc2bb82287 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -75,6 +75,11 @@ convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
 extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 			 int error_code, int si_code);
 
+
+extern unsigned long syscall_trace_enter_phase1(struct pt_regs *, u32 arch);
+extern long syscall_trace_enter_phase2(struct pt_regs *, u32 arch,
+				       unsigned long phase1_result);
+
 extern long syscall_trace_enter(struct pt_regs *);
 extern void syscall_trace_leave(struct pt_regs *);
 
diff --git a/arch/x86/include/asm/rwlock.h b/arch/x86/include/asm/rwlock.h
deleted file mode 100644
index a5370a03d90c..000000000000
--- a/arch/x86/include/asm/rwlock.h
+++ /dev/null
@@ -1,49 +0,0 @@
-#ifndef _ASM_X86_RWLOCK_H
-#define _ASM_X86_RWLOCK_H
-
-#include <asm/asm.h>
-
-#if CONFIG_NR_CPUS <= 2048
-
-#ifndef __ASSEMBLY__
-typedef union {
-	s32 lock;
-	s32 write;
-} arch_rwlock_t;
-#endif
-
-#define RW_LOCK_BIAS		0x00100000
-#define READ_LOCK_SIZE(insn)	__ASM_FORM(insn##l)
-#define READ_LOCK_ATOMIC(n)	atomic_##n
-#define WRITE_LOCK_ADD(n)	__ASM_FORM_COMMA(addl n)
-#define WRITE_LOCK_SUB(n)	__ASM_FORM_COMMA(subl n)
-#define WRITE_LOCK_CMP		RW_LOCK_BIAS
-
-#else /* CONFIG_NR_CPUS > 2048 */
-
-#include <linux/const.h>
-
-#ifndef __ASSEMBLY__
-typedef union {
-	s64 lock;
-	struct {
-		u32 read;
-		s32 write;
-	};
-} arch_rwlock_t;
-#endif
-
-#define RW_LOCK_BIAS		(_AC(1,L) << 32)
-#define READ_LOCK_SIZE(insn)	__ASM_FORM(insn##q)
-#define READ_LOCK_ATOMIC(n)	atomic64_##n
-#define WRITE_LOCK_ADD(n)	__ASM_FORM(incl)
-#define WRITE_LOCK_SUB(n)	__ASM_FORM(decl)
-#define WRITE_LOCK_CMP		1
-
-#endif /* CONFIG_NR_CPUS */
-
-#define __ARCH_RW_LOCK_UNLOCKED		{ RW_LOCK_BIAS }
-
-/* Actual code is in asm/spinlock.h or in arch/x86/lib/rwlock.S */
-
-#endif /* _ASM_X86_RWLOCK_H */
diff --git a/arch/x86/include/asm/serial.h b/arch/x86/include/asm/serial.h
index 628c801535ea..460b84f64556 100644
--- a/arch/x86/include/asm/serial.h
+++ b/arch/x86/include/asm/serial.h
@@ -6,24 +6,24 @@
  *
  * It'd be nice if someone built a serial card with a 24.576 MHz
  * clock, since the 16550A is capable of handling a top speed of 1.5
- * megabits/second; but this requires the faster clock.
+ * megabits/second; but this requires a faster clock.
  */
-#define BASE_BAUD ( 1843200 / 16 )
+#define BASE_BAUD (1843200/16)
 
 /* Standard COM flags (except for COM4, because of the 8514 problem) */
 #ifdef CONFIG_SERIAL_DETECT_IRQ
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
-#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
+# define STD_COMX_FLAGS	(ASYNC_BOOT_AUTOCONF |	ASYNC_SKIP_TEST	| ASYNC_AUTO_IRQ)
+# define STD_COM4_FLAGS	(ASYNC_BOOT_AUTOCONF |	0		| ASYNC_AUTO_IRQ)
 #else
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
-#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
+# define STD_COMX_FLAGS	(ASYNC_BOOT_AUTOCONF |	ASYNC_SKIP_TEST	| 0		)
+# define STD_COM4_FLAGS	(ASYNC_BOOT_AUTOCONF |	0		| 0		)
 #endif
 
-#define SERIAL_PORT_DFNS			\
-	/* UART CLK   PORT IRQ     FLAGS        */			\
-	{ 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS },	/* ttyS0 */	\
-	{ 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS },	/* ttyS1 */	\
-	{ 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS },	/* ttyS2 */	\
-	{ 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS },	/* ttyS3 */
+#define SERIAL_PORT_DFNS								\
+	/* UART		CLK		PORT	IRQ	FLAGS			    */	\
+	{ .uart = 0,	BASE_BAUD,	0x3F8,	4,	STD_COMX_FLAGS	}, /* ttyS0 */	\
+	{ .uart = 0,	BASE_BAUD,	0x2F8,	3,	STD_COMX_FLAGS	}, /* ttyS1 */	\
+	{ .uart = 0,	BASE_BAUD,	0x3E8,	4,	STD_COMX_FLAGS	}, /* ttyS2 */	\
+	{ .uart = 0,	BASE_BAUD,	0x2E8,	3,	STD_COM4_FLAGS	}, /* ttyS3 */
 
 #endif /* _ASM_X86_SERIAL_H */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 54f1c8068c02..9295016485c9 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -187,7 +187,6 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 		cpu_relax();
 }
 
-#ifndef CONFIG_QUEUE_RWLOCK
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.
@@ -198,91 +197,15 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
  * irq-safe write-lock, but readers can get non-irqsafe
  * read-locks.
  *
- * On x86, we implement read-write locks as a 32-bit counter
- * with the high bit (sign) being the "contended" bit.
+ * On x86, we implement read-write locks using the generic qrwlock with
+ * x86 specific optimization.
  */
 
-/**
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static inline int arch_read_can_lock(arch_rwlock_t *lock)
-{
-	return lock->lock > 0;
-}
-
-/**
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static inline int arch_write_can_lock(arch_rwlock_t *lock)
-{
-	return lock->write == WRITE_LOCK_CMP;
-}
-
-static inline void arch_read_lock(arch_rwlock_t *rw)
-{
-	asm volatile(LOCK_PREFIX READ_LOCK_SIZE(dec) " (%0)\n\t"
-		     "jns 1f\n"
-		     "call __read_lock_failed\n\t"
-		     "1:\n"
-		     ::LOCK_PTR_REG (rw) : "memory");
-}
-
-static inline void arch_write_lock(arch_rwlock_t *rw)
-{
-	asm volatile(LOCK_PREFIX WRITE_LOCK_SUB(%1) "(%0)\n\t"
-		     "jz 1f\n"
-		     "call __write_lock_failed\n\t"
-		     "1:\n"
-		     ::LOCK_PTR_REG (&rw->write), "i" (RW_LOCK_BIAS)
-		     : "memory");
-}
-
-static inline int arch_read_trylock(arch_rwlock_t *lock)
-{
-	READ_LOCK_ATOMIC(t) *count = (READ_LOCK_ATOMIC(t) *)lock;
-
-	if (READ_LOCK_ATOMIC(dec_return)(count) >= 0)
-		return 1;
-	READ_LOCK_ATOMIC(inc)(count);
-	return 0;
-}
-
-static inline int arch_write_trylock(arch_rwlock_t *lock)
-{
-	atomic_t *count = (atomic_t *)&lock->write;
-
-	if (atomic_sub_and_test(WRITE_LOCK_CMP, count))
-		return 1;
-	atomic_add(WRITE_LOCK_CMP, count);
-	return 0;
-}
-
-static inline void arch_read_unlock(arch_rwlock_t *rw)
-{
-	asm volatile(LOCK_PREFIX READ_LOCK_SIZE(inc) " %0"
-		     :"+m" (rw->lock) : : "memory");
-}
-
-static inline void arch_write_unlock(arch_rwlock_t *rw)
-{
-	asm volatile(LOCK_PREFIX WRITE_LOCK_ADD(%1) "%0"
-		     : "+m" (rw->write) : "i" (RW_LOCK_BIAS) : "memory");
-}
-#else
 #include <asm/qrwlock.h>
-#endif /* CONFIG_QUEUE_RWLOCK */
 
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
 
-#undef READ_LOCK_SIZE
-#undef READ_LOCK_ATOMIC
-#undef WRITE_LOCK_ADD
-#undef WRITE_LOCK_SUB
-#undef WRITE_LOCK_CMP
-
 #define arch_spin_relax(lock)	cpu_relax()
 #define arch_read_relax(lock)	cpu_relax()
 #define arch_write_relax(lock)	cpu_relax()
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 73c4c007200f..5f9d7572d82b 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -34,10 +34,6 @@ typedef struct arch_spinlock {
 
 #define __ARCH_SPIN_LOCK_UNLOCKED	{ { 0 } }
 
-#ifdef CONFIG_QUEUE_RWLOCK
 #include <asm-generic/qrwlock_types.h>
-#else
-#include <asm/rwlock.h>
-#endif
 
 #endif /* _ASM_X86_SPINLOCK_TYPES_H */
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index c63e925fd6b7..a00ad8f2a657 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -164,7 +164,7 @@ struct uv_hub_info_s {
 };
 
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info		(&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info		this_cpu_ptr(&__uv_hub_info)
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
 
 /*
@@ -601,16 +601,16 @@ struct uv_hub_nmi_s {
 
 struct uv_cpu_nmi_s {
 	struct uv_hub_nmi_s	*hub;
-	atomic_t		state;
-	atomic_t		pinging;
+	int			state;
+	int			pinging;
 	int			queries;
 	int			pings;
 };
 
-DECLARE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi);
-#define uv_cpu_nmi			(__get_cpu_var(__uv_cpu_nmi))
+DECLARE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
+
 #define uv_hub_nmi			(uv_cpu_nmi.hub)
-#define uv_cpu_nmi_per(cpu)		(per_cpu(__uv_cpu_nmi, cpu))
+#define uv_cpu_nmi_per(cpu)		(per_cpu(uv_cpu_nmi, cpu))
 #define uv_hub_nmi_per(cpu)		(uv_cpu_nmi_per(cpu).hub)
 
 /* uv_cpu_nmi_states */
diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h
index bbae02470701..d993e33f5236 100644
--- a/arch/x86/include/uapi/asm/e820.h
+++ b/arch/x86/include/uapi/asm/e820.h
@@ -21,11 +21,6 @@
  * this size.
  */
 
-/*
- * Odd: 'make headers_check' complains about numa.h if I try
- * to collapse the next two #ifdef lines to a single line:
- *	#if defined(__KERNEL__) && defined(CONFIG_EFI)
- */
 #ifndef __KERNEL__
 #define E820_X_MAX E820MAX
 #endif
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index ada2e2d6be3e..8f1e77440b2b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -39,8 +39,6 @@ obj-y			+= tsc.o tsc_msr.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
 
-obj-$(CONFIG_PREEMPT)	+= preempt.o
-
 obj-y				+= process.o
 obj-y				+= i387.o xsave.o
 obj-y				+= ptrace.o
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index af5b08ab3b71..5972b108f15a 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -146,7 +146,7 @@ static inline int is_apbt_capable(void)
 static int __init apbt_clockevent_register(void)
 {
 	struct sfi_timer_table_entry *mtmr;
-	struct apbt_dev *adev = &__get_cpu_var(cpu_apbt_dev);
+	struct apbt_dev *adev = this_cpu_ptr(&cpu_apbt_dev);
 
 	mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM);
 	if (mtmr == NULL) {
@@ -200,7 +200,7 @@ void apbt_setup_secondary_clock(void)
 	if (!cpu)
 		return;
 
-	adev = &__get_cpu_var(cpu_apbt_dev);
+	adev = this_cpu_ptr(&cpu_apbt_dev);
 	if (!adev->timer) {
 		adev->timer = dw_apb_clockevent_init(cpu, adev->name,
 			APBT_CLOCKEVENT_RATING, adev_virt_addr(adev),
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 67760275544b..00853b254ab0 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -561,7 +561,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
  */
 static void setup_APIC_timer(void)
 {
-	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+	struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
 
 	if (this_cpu_has(X86_FEATURE_ARAT)) {
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
@@ -696,7 +696,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 
 static int __init calibrate_APIC_clock(void)
 {
-	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+	struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
 	void (*real_handler)(struct clock_event_device *dev);
 	unsigned long deltaj;
 	long delta, deltatsc;
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index ae915391ebec..4128b5fcb559 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -32,7 +32,7 @@
 
 static int numachip_system __read_mostly;
 
-static const struct apic apic_numachip __read_mostly;
+static const struct apic apic_numachip;
 
 static unsigned int get_apic_id(unsigned long x)
 {
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 337ce5a9b15c..1183d545da1e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2623,6 +2623,7 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_eoi		= ack_apic_level,
 	.irq_set_affinity	= native_ioapic_set_affinity,
 	.irq_retrigger		= ioapic_retrigger_irq,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
 static inline void init_IO_APIC_traps(void)
@@ -3173,6 +3174,7 @@ static struct irq_chip msi_chip = {
 	.irq_ack		= ack_apic_edge,
 	.irq_set_affinity	= msi_set_affinity,
 	.irq_retrigger		= ioapic_retrigger_irq,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
 int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
@@ -3271,6 +3273,7 @@ static struct irq_chip dmar_msi_type = {
 	.irq_ack		= ack_apic_edge,
 	.irq_set_affinity	= dmar_msi_set_affinity,
 	.irq_retrigger		= ioapic_retrigger_irq,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
 int arch_setup_dmar_msi(unsigned int irq)
@@ -3321,6 +3324,7 @@ static struct irq_chip hpet_msi_type = {
 	.irq_ack = ack_apic_edge,
 	.irq_set_affinity = hpet_msi_set_affinity,
 	.irq_retrigger = ioapic_retrigger_irq,
+	.flags = IRQCHIP_SKIP_SET_WAKE,
 };
 
 int default_setup_hpet_msi(unsigned int irq, unsigned int id)
@@ -3384,6 +3388,7 @@ static struct irq_chip ht_irq_chip = {
 	.irq_ack		= ack_apic_edge,
 	.irq_set_affinity	= ht_set_affinity,
 	.irq_retrigger		= ioapic_retrigger_irq,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 6ce600f9bc78..e658f21681c8 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -42,7 +42,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 	 * We are to modify mask, so we need an own copy
 	 * and be sure it's manipulated with irq off.
 	 */
-	ipi_mask_ptr = __raw_get_cpu_var(ipi_mask);
+	ipi_mask_ptr = this_cpu_cpumask_var_ptr(ipi_mask);
 	cpumask_copy(ipi_mask_ptr, mask);
 
 	/*
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 004f017aa7b9..8e9dcfd630e4 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -204,7 +204,6 @@ EXPORT_SYMBOL(sn_rtc_cycles_per_second);
 
 static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 {
-#ifdef CONFIG_SMP
 	unsigned long val;
 	int pnode;
 
@@ -223,7 +222,6 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 
 	atomic_set(&init_deasserted, 1);
-#endif
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 77dcab277710..01d5453b5502 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -39,7 +39,9 @@ obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd_iommu.o
 endif
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_p6.o perf_event_knc.o perf_event_p4.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o perf_event_intel_rapl.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o perf_event_intel_uncore_snb.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore_snbep.o perf_event_intel_uncore_nhmex.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_rapl.o
 endif
 
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c649f236e288..4b4f78c9ba19 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -964,6 +964,7 @@ static void vgetcpu_set_mode(void)
 		vgetcpu_mode = VGETCPU_LSL;
 }
 
+#ifdef CONFIG_IA32_EMULATION
 /* May not be __init: called during resume */
 static void syscall32_cpu_init(void)
 {
@@ -975,7 +976,8 @@ static void syscall32_cpu_init(void)
 
 	wrmsrl(MSR_CSTAR, ia32_cstar_target);
 }
-#endif
+#endif		/* CONFIG_IA32_EMULATION */
+#endif		/* CONFIG_X86_64 */
 
 #ifdef CONFIG_X86_32
 void enable_sep_cpu(void)
@@ -1184,7 +1186,7 @@ void syscall_init(void)
 	/* Flags to clear on syscall */
 	wrmsrl(MSR_SYSCALL_MASK,
 	       X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
-	       X86_EFLAGS_IOPL|X86_EFLAGS_AC);
+	       X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
 }
 
 /*
@@ -1198,9 +1200,9 @@ DEFINE_PER_CPU(int, debug_stack_usage);
 
 int is_debug_stack(unsigned long addr)
 {
-	return __get_cpu_var(debug_stack_usage) ||
-		(addr <= __get_cpu_var(debug_stack_addr) &&
-		 addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ));
+	return __this_cpu_read(debug_stack_usage) ||
+		(addr <= __this_cpu_read(debug_stack_addr) &&
+		 addr > (__this_cpu_read(debug_stack_addr) - DEBUG_STKSZ));
 }
 NOKPROBE_SYMBOL(is_debug_stack);
 
@@ -1266,6 +1268,19 @@ static void dbg_restore_debug_regs(void)
 #define dbg_restore_debug_regs()
 #endif /* ! CONFIG_KGDB */
 
+static void wait_for_master_cpu(int cpu)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * wait for ACK from master CPU before continuing
+	 * with AP initialization
+	 */
+	WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask));
+	while (!cpumask_test_cpu(cpu, cpu_callout_mask))
+		cpu_relax();
+#endif
+}
+
 /*
  * cpu_init() initializes state that is per-CPU. Some data is already
  * initialized (naturally) in the bootstrap process, such as the GDT
@@ -1281,16 +1296,17 @@ void cpu_init(void)
 	struct task_struct *me;
 	struct tss_struct *t;
 	unsigned long v;
-	int cpu;
+	int cpu = stack_smp_processor_id();
 	int i;
 
+	wait_for_master_cpu(cpu);
+
 	/*
 	 * Load microcode on this cpu if a valid microcode is available.
 	 * This is early microcode loading procedure.
 	 */
 	load_ucode_ap();
 
-	cpu = stack_smp_processor_id();
 	t = &per_cpu(init_tss, cpu);
 	oist = &per_cpu(orig_ist, cpu);
 
@@ -1302,9 +1318,6 @@ void cpu_init(void)
 
 	me = current;
 
-	if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask))
-		panic("CPU#%d already initialized!\n", cpu);
-
 	pr_debug("Initializing CPU#%d\n", cpu);
 
 	clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
@@ -1381,17 +1394,13 @@ void cpu_init(void)
 	struct tss_struct *t = &per_cpu(init_tss, cpu);
 	struct thread_struct *thread = &curr->thread;
 
-	show_ucode_info_early();
+	wait_for_master_cpu(cpu);
 
-	if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) {
-		printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
-		for (;;)
-			local_irq_enable();
-	}
+	show_ucode_info_early();
 
 	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
 
-	if (cpu_has_vme || cpu_has_tsc || cpu_has_de)
+	if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de)
 		clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
 	load_current_idt();
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 74e804ddc5c7..1ef456273172 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -144,6 +144,21 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 			setup_clear_cpu_cap(X86_FEATURE_ERMS);
 		}
 	}
+
+	/*
+	 * Intel Quark Core DevMan_001.pdf section 6.4.11
+	 * "The operating system also is required to invalidate (i.e., flush)
+	 *  the TLB when any changes are made to any of the page table entries.
+	 *  The operating system must reload CR3 to cause the TLB to be flushed"
+	 *
+	 * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
+	 * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+	 * to be modified
+	 */
+	if (c->x86 == 5 && c->x86_model == 9) {
+		pr_info("Disabling PGE capability bit\n");
+		setup_clear_cpu_cap(X86_FEATURE_PGE);
+	}
 }
 
 #ifdef CONFIG_X86_32
@@ -382,6 +397,13 @@ static void init_intel(struct cpuinfo_x86 *c)
 	}
 
 	l2 = init_intel_cacheinfo(c);
+
+	/* Detect legacy cache sizes if init_intel_cacheinfo did not */
+	if (l2 == 0) {
+		cpu_detect_cache_sizes(c);
+		l2 = c->x86_cache_size;
+	}
+
 	if (c->cpuid_level > 9) {
 		unsigned eax = cpuid_eax(10);
 		/* Check for version and the number of counters */
@@ -485,6 +507,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 	 */
 	if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0))
 		size = 256;
+
+	/*
+	 * Intel Quark SoC X1000 contains a 4-way set associative
+	 * 16K cache with a 16 byte cache line and 256 lines per tag
+	 */
+	if ((c->x86 == 5) && (c->x86_model == 9))
+		size = 16;
 	return size;
 }
 #endif
@@ -686,7 +715,8 @@ static const struct cpu_dev intel_cpu_dev = {
 			  [3] = "OverDrive PODP5V83",
 			  [4] = "Pentium MMX",
 			  [7] = "Mobile Pentium 75 - 200",
-			  [8] = "Mobile Pentium MMX"
+			  [8] = "Mobile Pentium MMX",
+			  [9] = "Quark SoC X1000",
 		  }
 		},
 		{ .family = 6, .model_names =
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 5ac2d1fb28bc..4cfba4371a71 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -83,7 +83,7 @@ static DEFINE_MUTEX(mce_inject_mutex);
 static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
 {
 	int cpu = smp_processor_id();
-	struct mce *m = &__get_cpu_var(injectm);
+	struct mce *m = this_cpu_ptr(&injectm);
 	if (!cpumask_test_cpu(cpu, mce_inject_cpumask))
 		return NMI_DONE;
 	cpumask_clear_cpu(cpu, mce_inject_cpumask);
@@ -97,7 +97,7 @@ static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
 static void mce_irq_ipi(void *info)
 {
 	int cpu = smp_processor_id();
-	struct mce *m = &__get_cpu_var(injectm);
+	struct mce *m = this_cpu_ptr(&injectm);
 
 	if (cpumask_test_cpu(cpu, mce_inject_cpumask) &&
 			m->inject_flags & MCJ_EXCEPTION) {
@@ -109,7 +109,7 @@ static void mce_irq_ipi(void *info)
 /* Inject mce on current CPU */
 static int raise_local(void)
 {
-	struct mce *m = &__get_cpu_var(injectm);
+	struct mce *m = this_cpu_ptr(&injectm);
 	int context = MCJ_CTX(m->inject_flags);
 	int ret = 0;
 	int cpu = m->extcpu;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index bd9ccda8087f..61a9668cebfd 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -400,7 +400,7 @@ static u64 mce_rdmsrl(u32 msr)
 
 		if (offset < 0)
 			return 0;
-		return *(u64 *)((char *)&__get_cpu_var(injectm) + offset);
+		return *(u64 *)((char *)this_cpu_ptr(&injectm) + offset);
 	}
 
 	if (rdmsrl_safe(msr, &v)) {
@@ -422,7 +422,7 @@ static void mce_wrmsrl(u32 msr, u64 v)
 		int offset = msr_to_offset(msr);
 
 		if (offset >= 0)
-			*(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v;
+			*(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v;
 		return;
 	}
 	wrmsrl(msr, v);
@@ -478,7 +478,7 @@ static DEFINE_PER_CPU(struct mce_ring, mce_ring);
 /* Runs with CPU affinity in workqueue */
 static int mce_ring_empty(void)
 {
-	struct mce_ring *r = &__get_cpu_var(mce_ring);
+	struct mce_ring *r = this_cpu_ptr(&mce_ring);
 
 	return r->start == r->end;
 }
@@ -490,7 +490,7 @@ static int mce_ring_get(unsigned long *pfn)
 
 	*pfn = 0;
 	get_cpu();
-	r = &__get_cpu_var(mce_ring);
+	r = this_cpu_ptr(&mce_ring);
 	if (r->start == r->end)
 		goto out;
 	*pfn = r->ring[r->start];
@@ -504,7 +504,7 @@ out:
 /* Always runs in MCE context with preempt off */
 static int mce_ring_add(unsigned long pfn)
 {
-	struct mce_ring *r = &__get_cpu_var(mce_ring);
+	struct mce_ring *r = this_cpu_ptr(&mce_ring);
 	unsigned next;
 
 	next = (r->end + 1) % MCE_RING_SIZE;
@@ -526,7 +526,7 @@ int mce_available(struct cpuinfo_x86 *c)
 static void mce_schedule_work(void)
 {
 	if (!mce_ring_empty())
-		schedule_work(&__get_cpu_var(mce_work));
+		schedule_work(this_cpu_ptr(&mce_work));
 }
 
 DEFINE_PER_CPU(struct irq_work, mce_irq_work);
@@ -551,7 +551,7 @@ static void mce_report_event(struct pt_regs *regs)
 		return;
 	}
 
-	irq_work_queue(&__get_cpu_var(mce_irq_work));
+	irq_work_queue(this_cpu_ptr(&mce_irq_work));
 }
 
 /*
@@ -1045,7 +1045,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	mce_gather_info(&m, regs);
 
-	final = &__get_cpu_var(mces_seen);
+	final = this_cpu_ptr(&mces_seen);
 	*final = m;
 
 	memset(valid_banks, 0, sizeof(valid_banks));
@@ -1278,22 +1278,22 @@ static unsigned long (*mce_adjust_timer)(unsigned long interval) =
 
 static int cmc_error_seen(void)
 {
-	unsigned long *v = &__get_cpu_var(mce_polled_error);
+	unsigned long *v = this_cpu_ptr(&mce_polled_error);
 
 	return test_and_clear_bit(0, v);
 }
 
 static void mce_timer_fn(unsigned long data)
 {
-	struct timer_list *t = &__get_cpu_var(mce_timer);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned long iv;
 	int notify;
 
 	WARN_ON(smp_processor_id() != data);
 
-	if (mce_available(__this_cpu_ptr(&cpu_info))) {
+	if (mce_available(this_cpu_ptr(&cpu_info))) {
 		machine_check_poll(MCP_TIMESTAMP,
-				&__get_cpu_var(mce_poll_banks));
+				this_cpu_ptr(&mce_poll_banks));
 		mce_intel_cmci_poll();
 	}
 
@@ -1323,7 +1323,7 @@ static void mce_timer_fn(unsigned long data)
  */
 void mce_timer_kick(unsigned long interval)
 {
-	struct timer_list *t = &__get_cpu_var(mce_timer);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned long when = jiffies + interval;
 	unsigned long iv = __this_cpu_read(mce_next_interval);
 
@@ -1659,7 +1659,7 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t)
 
 static void __mcheck_cpu_init_timer(void)
 {
-	struct timer_list *t = &__get_cpu_var(mce_timer);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned int cpu = smp_processor_id();
 
 	setup_timer(t, mce_timer_fn, cpu);
@@ -1702,8 +1702,8 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_timer();
-	INIT_WORK(&__get_cpu_var(mce_work), mce_process_work);
-	init_irq_work(&__get_cpu_var(mce_irq_work), &mce_irq_work_cb);
+	INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work);
+	init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb);
 }
 
 /*
@@ -1955,7 +1955,7 @@ static struct miscdevice mce_chrdev_device = {
 static void __mce_disable_bank(void *arg)
 {
 	int bank = *((int *)arg);
-	__clear_bit(bank, __get_cpu_var(mce_poll_banks));
+	__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
 	cmci_disable_bank(bank);
 }
 
@@ -2065,7 +2065,7 @@ static void mce_syscore_shutdown(void)
 static void mce_syscore_resume(void)
 {
 	__mcheck_cpu_init_generic();
-	__mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
+	__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
 }
 
 static struct syscore_ops mce_syscore_ops = {
@@ -2080,7 +2080,7 @@ static struct syscore_ops mce_syscore_ops = {
 
 static void mce_cpu_restart(void *data)
 {
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_timer();
@@ -2096,14 +2096,14 @@ static void mce_restart(void)
 /* Toggle features for corrected errors */
 static void mce_disable_cmci(void *data)
 {
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	cmci_clear();
 }
 
 static void mce_enable_ce(void *all)
 {
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	cmci_reenable();
 	cmci_recheck();
@@ -2336,7 +2336,7 @@ static void mce_disable_cpu(void *h)
 	unsigned long action = *(unsigned long *)h;
 	int i;
 
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
 	if (!(action & CPU_TASKS_FROZEN))
@@ -2354,7 +2354,7 @@ static void mce_reenable_cpu(void *h)
 	unsigned long action = *(unsigned long *)h;
 	int i;
 
-	if (!mce_available(__this_cpu_ptr(&cpu_info)))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
 	if (!(action & CPU_TASKS_FROZEN))
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 1e49f8f41276..5d4999f95aec 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -310,7 +310,7 @@ static void amd_threshold_interrupt(void)
 			 * event.
 			 */
 			machine_check_poll(MCP_TIMESTAMP,
-					&__get_cpu_var(mce_poll_banks));
+					this_cpu_ptr(&mce_poll_banks));
 
 			if (high & MASK_OVERFLOW_HI) {
 				rdmsrl(address, m.misc);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 3bdb95ae8c43..b3c97bafc123 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -86,7 +86,7 @@ void mce_intel_cmci_poll(void)
 {
 	if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
 		return;
-	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
 }
 
 void mce_intel_hcpu_update(unsigned long cpu)
@@ -145,7 +145,7 @@ static void cmci_storm_disable_banks(void)
 	u64 val;
 
 	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
-	owned = __get_cpu_var(mce_banks_owned);
+	owned = this_cpu_ptr(mce_banks_owned);
 	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
 		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
 		val &= ~MCI_CTL2_CMCI_EN;
@@ -195,7 +195,7 @@ static void intel_threshold_interrupt(void)
 {
 	if (cmci_storm_detect())
 		return;
-	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
 	mce_notify_irq();
 }
 
@@ -206,7 +206,7 @@ static void intel_threshold_interrupt(void)
  */
 static void cmci_discover(int banks)
 {
-	unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
+	unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned);
 	unsigned long flags;
 	int i;
 	int bios_wrong_thresh = 0;
@@ -228,7 +228,7 @@ static void cmci_discover(int banks)
 		/* Already owned by someone else? */
 		if (val & MCI_CTL2_CMCI_EN) {
 			clear_bit(i, owned);
-			__clear_bit(i, __get_cpu_var(mce_poll_banks));
+			__clear_bit(i, this_cpu_ptr(mce_poll_banks));
 			continue;
 		}
 
@@ -252,7 +252,7 @@ static void cmci_discover(int banks)
 		/* Did the enable bit stick? -- the bank supports CMCI */
 		if (val & MCI_CTL2_CMCI_EN) {
 			set_bit(i, owned);
-			__clear_bit(i, __get_cpu_var(mce_poll_banks));
+			__clear_bit(i, this_cpu_ptr(mce_poll_banks));
 			/*
 			 * We are able to set thresholds for some banks that
 			 * had a threshold of 0. This means the BIOS has not
@@ -263,7 +263,7 @@ static void cmci_discover(int banks)
 					(val & MCI_CTL2_CMCI_THRESHOLD_MASK))
 				bios_wrong_thresh = 1;
 		} else {
-			WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
+			WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks)));
 		}
 	}
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
@@ -284,10 +284,10 @@ void cmci_recheck(void)
 	unsigned long flags;
 	int banks;
 
-	if (!mce_available(__this_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
+	if (!mce_available(raw_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
 		return;
 	local_irq_save(flags);
-	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+	machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
 	local_irq_restore(flags);
 }
 
@@ -296,12 +296,12 @@ static void __cmci_disable_bank(int bank)
 {
 	u64 val;
 
-	if (!test_bit(bank, __get_cpu_var(mce_banks_owned)))
+	if (!test_bit(bank, this_cpu_ptr(mce_banks_owned)))
 		return;
 	rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
 	val &= ~MCI_CTL2_CMCI_EN;
 	wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
-	__clear_bit(bank, __get_cpu_var(mce_banks_owned));
+	__clear_bit(bank, this_cpu_ptr(mce_banks_owned));
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 36a1bb6d1ee0..1af51b1586d7 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -498,8 +498,8 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
 
 
 	if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
-		printk(KERN_DEBUG
-		       "CPU%d: Thermal monitoring handled by SMI\n", cpu);
+		if (system_state == SYSTEM_BOOTING)
+			printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n", cpu);
 		return;
 	}
 
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 617a9e284245..7aa1acc79789 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -27,7 +27,7 @@ static u32 ucode_new_rev;
 u8 amd_ucode_patch[PATCH_MAX_SIZE];
 static u16 this_equiv_id;
 
-struct cpio_data ucode_cpio;
+static struct cpio_data ucode_cpio;
 
 /*
  * Microcode patch container file is prepended to the initrd in cpio format.
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index a276fa75d9b5..c6826d1e8082 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -127,7 +127,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu)
 	return get_matching_microcode(csig, cpf, mc_intel, crev);
 }
 
-int apply_microcode(int cpu)
+static int apply_microcode_intel(int cpu)
 {
 	struct microcode_intel *mc_intel;
 	struct ucode_cpu_info *uci;
@@ -314,7 +314,7 @@ static struct microcode_ops microcode_intel_ops = {
 	.request_microcode_user		  = request_microcode_user,
 	.request_microcode_fw             = request_microcode_fw,
 	.collect_cpu_info                 = collect_cpu_info,
-	.apply_microcode                  = apply_microcode,
+	.apply_microcode                  = apply_microcode_intel,
 	.microcode_fini_cpu               = microcode_fini_cpu,
 };
 
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index 18f739129e72..b88343f7a3b3 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -28,8 +28,8 @@
 #include <asm/tlbflush.h>
 #include <asm/setup.h>
 
-unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT];
-struct mc_saved_data {
+static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT];
+static struct mc_saved_data {
 	unsigned int mc_saved_count;
 	struct microcode_intel **mc_saved;
 } mc_saved_data;
@@ -415,7 +415,7 @@ static void __ref show_saved_mc(void)
 	struct ucode_cpu_info uci;
 
 	if (mc_saved_data.mc_saved_count == 0) {
-		pr_debug("no micorcode data saved.\n");
+		pr_debug("no microcode data saved.\n");
 		return;
 	}
 	pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count);
@@ -506,7 +506,7 @@ int save_mc_for_early(u8 *mc)
 
 	if (mc_saved && mc_saved_count)
 		memcpy(mc_saved_tmp, mc_saved,
-		       mc_saved_count * sizeof(struct mirocode_intel *));
+		       mc_saved_count * sizeof(struct microcode_intel *));
 	/*
 	 * Save the microcode patch mc in mc_save_tmp structure if it's a newer
 	 * version.
@@ -526,7 +526,7 @@ int save_mc_for_early(u8 *mc)
 	show_saved_mc();
 
 	/*
-	 * Free old saved microcod data.
+	 * Free old saved microcode data.
 	 */
 	if (mc_saved) {
 		for (i = 0; i < mc_saved_count_init; i++)
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index f961de9964c7..ea5f363a1948 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -707,7 +707,7 @@ void __init mtrr_bp_init(void)
 	} else {
 		switch (boot_cpu_data.x86_vendor) {
 		case X86_VENDOR_AMD:
-			if (cpu_has_k6_mtrr) {
+			if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) {
 				/* Pre-Athlon (K6) AMD CPU MTRRs */
 				mtrr_if = mtrr_ops[X86_VENDOR_AMD];
 				size_or_mask = SIZE_OR_MASK_BITS(32);
@@ -715,14 +715,14 @@ void __init mtrr_bp_init(void)
 			}
 			break;
 		case X86_VENDOR_CENTAUR:
-			if (cpu_has_centaur_mcr) {
+			if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) {
 				mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR];
 				size_or_mask = SIZE_OR_MASK_BITS(32);
 				size_and_mask = 0;
 			}
 			break;
 		case X86_VENDOR_CYRIX:
-			if (cpu_has_cyrix_arr) {
+			if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) {
 				mtrr_if = mtrr_ops[X86_VENDOR_CYRIX];
 				size_or_mask = SIZE_OR_MASK_BITS(32);
 				size_and_mask = 0;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2879ecdaac43..1b8299dd3d91 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -243,7 +243,8 @@ static bool check_hw_exists(void)
 
 msr_fail:
 	printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
-	printk(KERN_ERR "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new);
+	printk(boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR
+	       "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new);
 
 	return false;
 }
@@ -387,7 +388,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 			precise++;
 
 			/* Support for IP fixup */
-			if (x86_pmu.lbr_nr)
+			if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2)
 				precise++;
 		}
 
@@ -443,6 +444,12 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == PERF_TYPE_RAW)
 		event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
 
+	if (event->attr.sample_period && x86_pmu.limit_period) {
+		if (x86_pmu.limit_period(event, event->attr.sample_period) >
+				event->attr.sample_period)
+			return -EINVAL;
+	}
+
 	return x86_setup_perfctr(event);
 }
 
@@ -487,7 +494,7 @@ static int __x86_pmu_event_init(struct perf_event *event)
 
 void x86_pmu_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -505,7 +512,7 @@ void x86_pmu_disable_all(void)
 
 static void x86_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!x86_pmu_initialized())
 		return;
@@ -522,7 +529,7 @@ static void x86_pmu_disable(struct pmu *pmu)
 
 void x86_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -869,7 +876,7 @@ static void x86_pmu_start(struct perf_event *event, int flags);
 
 static void x86_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	int i, added = cpuc->n_added;
@@ -980,6 +987,9 @@ int x86_perf_event_set_period(struct perf_event *event)
 	if (left > x86_pmu.max_period)
 		left = x86_pmu.max_period;
 
+	if (x86_pmu.limit_period)
+		left = x86_pmu.limit_period(event, left);
+
 	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
 	/*
@@ -1020,7 +1030,7 @@ void x86_pmu_enable_event(struct perf_event *event)
  */
 static int x86_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc;
 	int assign[X86_PMC_IDX_MAX];
 	int n, n0, ret;
@@ -1071,7 +1081,7 @@ out:
 
 static void x86_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx = event->hw.idx;
 
 	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
@@ -1150,7 +1160,7 @@ void perf_event_print_debug(void)
 
 void x86_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
@@ -1172,7 +1182,7 @@ void x86_pmu_stop(struct perf_event *event, int flags)
 
 static void x86_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 
 	/*
@@ -1227,7 +1237,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/*
 	 * Some chipsets need to unmask the LVTPC in a particular spot
@@ -1636,7 +1646,7 @@ static void x86_pmu_cancel_txn(struct pmu *pmu)
  */
 static int x86_pmu_commit_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int assign[X86_PMC_IDX_MAX];
 	int n, ret;
 
@@ -1995,7 +2005,7 @@ static unsigned long get_segment_base(unsigned int segment)
 		if (idx > GDT_ENTRIES)
 			return 0;
 
-		desc = __this_cpu_ptr(&gdt_page.gdt[0]);
+		desc = raw_cpu_ptr(gdt_page.gdt);
 	}
 
 	return get_desc_base(desc + idx);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8ade93111e03..d98a34d435d7 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -67,8 +67,10 @@ struct event_constraint {
  */
 #define PERF_X86_EVENT_PEBS_LDLAT	0x1 /* ld+ldlat data address sampling */
 #define PERF_X86_EVENT_PEBS_ST		0x2 /* st data address sampling */
-#define PERF_X86_EVENT_PEBS_ST_HSW	0x4 /* haswell style st data sampling */
+#define PERF_X86_EVENT_PEBS_ST_HSW	0x4 /* haswell style datala, store */
 #define PERF_X86_EVENT_COMMITTED	0x8 /* event passed commit_txn */
+#define PERF_X86_EVENT_PEBS_LD_HSW	0x10 /* haswell style datala, load */
+#define PERF_X86_EVENT_PEBS_NA_HSW	0x20 /* haswell style datala, unknown */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -252,18 +254,52 @@ struct cpu_hw_events {
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
 
 #define INTEL_PLD_CONSTRAINT(c, n)	\
-	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			   HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
 
 #define INTEL_PST_CONSTRAINT(c, n)	\
-	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
 
-/* DataLA version of store sampling without extra enable bit. */
-#define INTEL_PST_HSW_CONSTRAINT(c, n)	\
-	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+/* Event constraint, but match on all event flags too. */
+#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
+	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
+/* Check only flags, but allow all event/umask */
+#define INTEL_ALL_EVENT_CONSTRAINT(code, n)	\
+	EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
+
+/* Check flags and event code, and set the HSW store flag */
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_ST(code, n) \
+	__EVENT_CONSTRAINT(code, n, 			\
+			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
+
+/* Check flags and event code, and set the HSW load flag */
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(code, n) \
+	__EVENT_CONSTRAINT(code, n, 			\
+			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
+/* Check flags and event code/umask, and set the HSW store flag */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(code, n) \
+	__EVENT_CONSTRAINT(code, n, 			\
+			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
 
+/* Check flags and event code/umask, and set the HSW load flag */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(code, n) \
+	__EVENT_CONSTRAINT(code, n, 			\
+			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
+/* Check flags and event code/umask, and set the HSW N/A flag */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
+	__EVENT_CONSTRAINT(code, n, 			\
+			  INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
+
+
 /*
  * We define the end marker as having a weight of -1
  * to enable blacklisting of events using a counter bitmask
@@ -409,6 +445,7 @@ struct x86_pmu {
 	struct x86_pmu_quirk *quirks;
 	int		perfctr_second_write;
 	bool		late_ack;
+	unsigned	(*limit_period)(struct perf_event *event, unsigned l);
 
 	/*
 	 * sysfs attrs
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index beeb7cc07044..28926311aac1 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -699,7 +699,7 @@ __init int amd_pmu_init(void)
 
 void amd_pmu_enable_virt(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	cpuc->perf_ctr_virt_mask = 0;
 
@@ -711,7 +711,7 @@ EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
 
 void amd_pmu_disable_virt(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/*
 	 * We only mask out the Host-only bit so that host-only counting works
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 2502d0d9d246..a73947c53b65 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -220,6 +220,15 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+static struct event_constraint intel_bdw_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
+	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	EVENT_CONSTRAINT_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -415,6 +424,126 @@ static __initconst const u64 snb_hw_cache_event_ids
 
 };
 
+static __initconst const u64 hsw_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x151, 	/* L1D.REPLACEMENT */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x280, 	/* ICACHE.MISSES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x1b7,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x108, 	/* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x149, 	/* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x6085, 	/* ITLB_MISSES.STLB_HIT */
+		[ C(RESULT_MISS)   ] = 0x185, 	/* ITLB_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0xc4, 	/* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0xc5, 	/* BR_MISP_RETIRED.ALL_BRANCHES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static __initconst const u64 hsw_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x2d5,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc0202d5ull,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x122, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc020122ull,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+};
+
 static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -1045,7 +1174,7 @@ static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
 
 static void intel_pmu_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 
@@ -1058,7 +1187,7 @@ static void intel_pmu_disable_all(void)
 
 static void intel_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	intel_pmu_pebs_enable_all();
 	intel_pmu_lbr_enable_all();
@@ -1092,7 +1221,7 @@ static void intel_pmu_enable_all(int added)
  */
 static void intel_pmu_nhm_workaround(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	static const unsigned long nhm_magic[4] = {
 		0x4300B5,
 		0x4300D2,
@@ -1191,7 +1320,7 @@ static inline bool event_is_checkpointed(struct perf_event *event)
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
 		intel_pmu_disable_bts();
@@ -1255,7 +1384,7 @@ static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
 		if (!__this_cpu_read(cpu_hw_events.enabled))
@@ -1349,7 +1478,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	u64 status;
 	int handled;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	/*
 	 * No known reason to not always do late ACK,
@@ -1781,7 +1910,7 @@ EXPORT_SYMBOL_GPL(perf_guest_get_msrs);
 
 static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
 
 	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
@@ -1802,7 +1931,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
 
 static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
 	int idx;
 
@@ -1836,7 +1965,7 @@ static void core_pmu_enable_event(struct perf_event *event)
 
 static void core_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -1905,6 +2034,24 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	return c;
 }
 
+/*
+ * Broadwell:
+ * The INST_RETIRED.ALL period always needs to have lowest
+ * 6bits cleared (BDM57). It shall not use a period smaller
+ * than 100 (BDM11). We combine the two to enforce
+ * a min-period of 128.
+ */
+static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
+{
+	if ((event->hw.config & INTEL_ARCH_EVENT_MASK) ==
+			X86_CONFIG(.event=0xc0, .umask=0x01)) {
+		if (left < 128)
+			left = 128;
+		left &= ~0x3fu;
+	}
+	return left;
+}
+
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -2367,15 +2514,15 @@ __init int intel_pmu_init(void)
 	 * Install the hw-cache-events table:
 	 */
 	switch (boot_cpu_data.x86_model) {
-	case 14: /* 65 nm core solo/duo, "Yonah" */
+	case 14: /* 65nm Core "Yonah" */
 		pr_cont("Core events, ");
 		break;
 
-	case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
+	case 15: /* 65nm Core2 "Merom"          */
 		x86_add_quirk(intel_clovertown_quirk);
-	case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
-	case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
-	case 29: /* six-core 45 nm xeon "Dunnington" */
+	case 22: /* 65nm Core2 "Merom-L"        */
+	case 23: /* 45nm Core2 "Penryn"         */
+	case 29: /* 45nm Core2 "Dunnington (MP) */
 		memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -2386,9 +2533,9 @@ __init int intel_pmu_init(void)
 		pr_cont("Core2 events, ");
 		break;
 
-	case 26: /* 45 nm nehalem, "Bloomfield" */
-	case 30: /* 45 nm nehalem, "Lynnfield" */
-	case 46: /* 45 nm nehalem-ex, "Beckton" */
+	case 30: /* 45nm Nehalem    */
+	case 26: /* 45nm Nehalem-EP */
+	case 46: /* 45nm Nehalem-EX */
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -2415,11 +2562,11 @@ __init int intel_pmu_init(void)
 		pr_cont("Nehalem events, ");
 		break;
 
-	case 28: /* Atom */
-	case 38: /* Lincroft */
-	case 39: /* Penwell */
-	case 53: /* Cloverview */
-	case 54: /* Cedarview */
+	case 28: /* 45nm Atom "Pineview"   */
+	case 38: /* 45nm Atom "Lincroft"   */
+	case 39: /* 32nm Atom "Penwell"    */
+	case 53: /* 32nm Atom "Cloverview" */
+	case 54: /* 32nm Atom "Cedarview"  */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -2430,8 +2577,8 @@ __init int intel_pmu_init(void)
 		pr_cont("Atom events, ");
 		break;
 
-	case 55: /* Atom 22nm "Silvermont" */
-	case 77: /* Avoton "Silvermont" */
+	case 55: /* 22nm Atom "Silvermont"                */
+	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -2446,9 +2593,9 @@ __init int intel_pmu_init(void)
 		pr_cont("Silvermont events, ");
 		break;
 
-	case 37: /* 32 nm nehalem, "Clarkdale" */
-	case 44: /* 32 nm nehalem, "Gulftown" */
-	case 47: /* 32 nm Xeon E7 */
+	case 37: /* 32nm Westmere    */
+	case 44: /* 32nm Westmere-EP */
+	case 47: /* 32nm Westmere-EX */
 		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -2474,8 +2621,8 @@ __init int intel_pmu_init(void)
 		pr_cont("Westmere events, ");
 		break;
 
-	case 42: /* SandyBridge */
-	case 45: /* SandyBridge, "Romely-EP" */
+	case 42: /* 32nm SandyBridge         */
+	case 45: /* 32nm SandyBridge-E/EN/EP */
 		x86_add_quirk(intel_sandybridge_quirk);
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
@@ -2506,8 +2653,9 @@ __init int intel_pmu_init(void)
 
 		pr_cont("SandyBridge events, ");
 		break;
-	case 58: /* IvyBridge */
-	case 62: /* IvyBridge EP */
+
+	case 58: /* 22nm IvyBridge       */
+	case 62: /* 22nm IvyBridge-EP/EX */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		/* dTLB-load-misses on IVB is different than SNB */
@@ -2539,20 +2687,19 @@ __init int intel_pmu_init(void)
 		break;
 
 
-	case 60: /* Haswell Client */
-	case 70:
-	case 71:
-	case 63:
-	case 69:
+	case 60: /* 22nm Haswell Core */
+	case 63: /* 22nm Haswell Server */
+	case 69: /* 22nm Haswell ULT */
+	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
 		x86_pmu.late_ack = true;
-		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
-		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
 
 		intel_pmu_lbr_init_snb();
 
 		x86_pmu.event_constraints = intel_hsw_event_constraints;
 		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
-		x86_pmu.extra_regs = intel_snb_extra_regs;
+		x86_pmu.extra_regs = intel_snbep_extra_regs;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
@@ -2565,6 +2712,28 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
+	case 61: /* 14nm Broadwell Core-M */
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_bdw_event_constraints;
+		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_snbep_extra_regs;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = hsw_get_event_constraints;
+		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.limit_period = bdw_limit_period;
+		pr_cont("Broadwell events, ");
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 696ade311ded..46211bcc813e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -108,14 +108,16 @@ static u64 precise_store_data(u64 status)
 	return val;
 }
 
-static u64 precise_store_data_hsw(struct perf_event *event, u64 status)
+static u64 precise_datala_hsw(struct perf_event *event, u64 status)
 {
 	union perf_mem_data_src dse;
-	u64 cfg = event->hw.config & INTEL_ARCH_EVENT_MASK;
 
-	dse.val = 0;
-	dse.mem_op = PERF_MEM_OP_STORE;
-	dse.mem_lvl = PERF_MEM_LVL_NA;
+	dse.val = PERF_MEM_NA;
+
+	if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
+		dse.mem_op = PERF_MEM_OP_STORE;
+	else if (event->hw.flags & PERF_X86_EVENT_PEBS_LD_HSW)
+		dse.mem_op = PERF_MEM_OP_LOAD;
 
 	/*
 	 * L1 info only valid for following events:
@@ -125,15 +127,12 @@ static u64 precise_store_data_hsw(struct perf_event *event, u64 status)
 	 * MEM_UOPS_RETIRED.SPLIT_STORES
 	 * MEM_UOPS_RETIRED.ALL_STORES
 	 */
-	if (cfg != 0x12d0 && cfg != 0x22d0 && cfg != 0x42d0 && cfg != 0x82d0)
-		return dse.mem_lvl;
-
-	if (status & 1)
-		dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
-	else
-		dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS;
-
-	/* Nothing else supported. Sorry. */
+	if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) {
+		if (status & 1)
+			dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
+		else
+			dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS;
+	}
 	return dse.val;
 }
 
@@ -475,7 +474,7 @@ void intel_pmu_enable_bts(u64 config)
 
 void intel_pmu_disable_bts(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long debugctlmsr;
 
 	if (!cpuc->ds)
@@ -492,7 +491,7 @@ void intel_pmu_disable_bts(void)
 
 int intel_pmu_drain_bts_buffer(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
 	struct bts_record {
 		u64	from;
@@ -569,28 +568,10 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_slm_pebs_event_constraints[] = {
-	INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */
-	INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */
-	INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */
-	INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */
-	INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */
-	INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */
-	INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */
-	INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */
-	INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */
-	INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */
-	INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */
-	INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */
-	INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */
-	INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */
-	INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */
-	INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */
-	INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */
-	INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */
-	INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */
-	INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */
-	INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */
-	INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */
+	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
 	EVENT_CONSTRAINT_END
 };
 
@@ -626,68 +607,44 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = {
 
 struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
-	INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
-	INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
-	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
 	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
 	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
-	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xd3, 0xf),    /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
+	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
 	EVENT_CONSTRAINT_END
 };
 
 struct event_constraint intel_ivb_pebs_event_constraints[] = {
         INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
-        INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
-        INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
-        INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
         INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
 	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
-        INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xd3, 0xf),    /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
         EVENT_CONSTRAINT_END
 };
 
 struct event_constraint intel_hsw_pebs_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
-	INTEL_PST_HSW_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
-	INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
-	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */
-	INTEL_UEVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */
-	INTEL_UEVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.NEAR_TAKEN */
-	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.* */
-	/* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf),
-	/* MEM_UOPS_RETIRED.STLB_MISS_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
-	/* MEM_UOPS_RETIRED.SPLIT_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
-	INTEL_PST_HSW_CONSTRAINT(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */
-	INTEL_UEVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */
-	INTEL_UEVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L3_HIT */
-	/* MEM_LOAD_UOPS_RETIRED.HIT_LFB */
-	INTEL_UEVENT_CONSTRAINT(0x40d1, 0xf),
-	/* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */
-	INTEL_UEVENT_CONSTRAINT(0x01d2, 0xf),
-	/* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */
-	INTEL_UEVENT_CONSTRAINT(0x02d2, 0xf),
-	/* MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM */
-	INTEL_UEVENT_CONSTRAINT(0x01d3, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x04c8, 0xf), /* HLE_RETIRED.Abort */
-	INTEL_UEVENT_CONSTRAINT(0x04c9, 0xf), /* RTM_RETIRED.Abort */
-
+	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
+	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf),    /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf),    /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
 	EVENT_CONSTRAINT_END
 };
 
@@ -712,7 +669,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
@@ -727,7 +684,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 
 void intel_pmu_pebs_disable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
@@ -745,7 +702,7 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 
 void intel_pmu_pebs_enable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->pebs_enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
@@ -753,7 +710,7 @@ void intel_pmu_pebs_enable_all(void)
 
 void intel_pmu_pebs_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->pebs_enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
@@ -761,7 +718,7 @@ void intel_pmu_pebs_disable_all(void)
 
 static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned long from = cpuc->lbr_entries[0].from;
 	unsigned long old_to, to = cpuc->lbr_entries[0].to;
 	unsigned long ip = regs->ip;
@@ -864,51 +821,53 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
 static void __intel_pmu_pebs_event(struct perf_event *event,
 				   struct pt_regs *iregs, void *__pebs)
 {
+#define PERF_X86_EVENT_PEBS_HSW_PREC \
+		(PERF_X86_EVENT_PEBS_ST_HSW | \
+		 PERF_X86_EVENT_PEBS_LD_HSW | \
+		 PERF_X86_EVENT_PEBS_NA_HSW)
 	/*
 	 * We cast to the biggest pebs_record but are careful not to
 	 * unconditionally access the 'extra' entries.
 	 */
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_record_hsw *pebs = __pebs;
 	struct perf_sample_data data;
 	struct pt_regs regs;
 	u64 sample_type;
-	int fll, fst;
+	int fll, fst, dsrc;
+	int fl = event->hw.flags;
 
 	if (!intel_pmu_save_and_restart(event))
 		return;
 
-	fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
-	fst = event->hw.flags & (PERF_X86_EVENT_PEBS_ST |
-				 PERF_X86_EVENT_PEBS_ST_HSW);
+	sample_type = event->attr.sample_type;
+	dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
+
+	fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
+	fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
 
 	perf_sample_data_init(&data, 0, event->hw.last_period);
 
 	data.period = event->hw.last_period;
-	sample_type = event->attr.sample_type;
 
 	/*
-	 * if PEBS-LL or PreciseStore
+	 * Use latency for weight (only avail with PEBS-LL)
 	 */
-	if (fll || fst) {
-		/*
-		 * Use latency for weight (only avail with PEBS-LL)
-		 */
-		if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
-			data.weight = pebs->lat;
-
-		/*
-		 * data.data_src encodes the data source
-		 */
-		if (sample_type & PERF_SAMPLE_DATA_SRC) {
-			if (fll)
-				data.data_src.val = load_latency_data(pebs->dse);
-			else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
-				data.data_src.val =
-					precise_store_data_hsw(event, pebs->dse);
-			else
-				data.data_src.val = precise_store_data(pebs->dse);
-		}
+	if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
+		data.weight = pebs->lat;
+
+	/*
+	 * data.data_src encodes the data source
+	 */
+	if (dsrc) {
+		u64 val = PERF_MEM_NA;
+		if (fll)
+			val = load_latency_data(pebs->dse);
+		else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
+			val = precise_datala_hsw(event, pebs->dse);
+		else if (fst)
+			val = precise_store_data(pebs->dse);
+		data.data_src.val = val;
 	}
 
 	/*
@@ -935,16 +894,16 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	else
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
-	if ((event->attr.sample_type & PERF_SAMPLE_ADDR) &&
+	if ((sample_type & PERF_SAMPLE_ADDR) &&
 	    x86_pmu.intel_cap.pebs_format >= 1)
 		data.addr = pebs->dla;
 
 	if (x86_pmu.intel_cap.pebs_format >= 2) {
 		/* Only set the TSX weight when no memory weight. */
-		if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) && !fll)
+		if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
 			data.weight = intel_hsw_weight(pebs);
 
-		if (event->attr.sample_type & PERF_SAMPLE_TRANSACTION)
+		if (sample_type & PERF_SAMPLE_TRANSACTION)
 			data.txn = intel_hsw_transaction(pebs);
 	}
 
@@ -957,7 +916,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event = cpuc->events[0]; /* PMC0 only */
 	struct pebs_record_core *at, *top;
@@ -998,7 +957,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 
 static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event = NULL;
 	void *at, *top;
@@ -1055,7 +1014,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
  * BTS, PEBS probe and setup
  */
 
-void intel_ds_init(void)
+void __init intel_ds_init(void)
 {
 	/*
 	 * No support for 32bit formats
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 9dd2459a4c73..45fa730a5283 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -133,7 +133,7 @@ static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
 static void __intel_pmu_lbr_enable(void)
 {
 	u64 debugctl;
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->lbr_sel)
 		wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
@@ -183,7 +183,7 @@ void intel_pmu_lbr_reset(void)
 
 void intel_pmu_lbr_enable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!x86_pmu.lbr_nr)
 		return;
@@ -203,7 +203,7 @@ void intel_pmu_lbr_enable(struct perf_event *event)
 
 void intel_pmu_lbr_disable(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!x86_pmu.lbr_nr)
 		return;
@@ -220,7 +220,7 @@ void intel_pmu_lbr_disable(struct perf_event *event)
 
 void intel_pmu_lbr_enable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->lbr_users)
 		__intel_pmu_lbr_enable();
@@ -228,7 +228,7 @@ void intel_pmu_lbr_enable_all(void)
 
 void intel_pmu_lbr_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->lbr_users)
 		__intel_pmu_lbr_disable();
@@ -332,7 +332,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 
 void intel_pmu_lbr_read(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!cpuc->lbr_users)
 		return;
@@ -697,7 +697,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
 };
 
 /* core */
-void intel_pmu_lbr_init_core(void)
+void __init intel_pmu_lbr_init_core(void)
 {
 	x86_pmu.lbr_nr     = 4;
 	x86_pmu.lbr_tos    = MSR_LBR_TOS;
@@ -712,7 +712,7 @@ void intel_pmu_lbr_init_core(void)
 }
 
 /* nehalem/westmere */
-void intel_pmu_lbr_init_nhm(void)
+void __init intel_pmu_lbr_init_nhm(void)
 {
 	x86_pmu.lbr_nr     = 16;
 	x86_pmu.lbr_tos    = MSR_LBR_TOS;
@@ -733,7 +733,7 @@ void intel_pmu_lbr_init_nhm(void)
 }
 
 /* sandy bridge */
-void intel_pmu_lbr_init_snb(void)
+void __init intel_pmu_lbr_init_snb(void)
 {
 	x86_pmu.lbr_nr	 = 16;
 	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
@@ -753,7 +753,7 @@ void intel_pmu_lbr_init_snb(void)
 }
 
 /* atom */
-void intel_pmu_lbr_init_atom(void)
+void __init intel_pmu_lbr_init_atom(void)
 {
 	/*
 	 * only models starting at stepping 10 seems
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 619f7699487a..d64f275fe274 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -135,7 +135,7 @@ static inline u64 rapl_scale(u64 v)
 	 * or use ldexp(count, -32).
 	 * Watts = Joules/Time delta
 	 */
-	return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit);
+	return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
 }
 
 static u64 rapl_event_update(struct perf_event *event)
@@ -187,7 +187,7 @@ static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
 
 static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	struct perf_event *event;
 	unsigned long flags;
 
@@ -234,7 +234,7 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
 
 static void rapl_pmu_event_start(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	unsigned long flags;
 
 	spin_lock_irqsave(&pmu->lock, flags);
@@ -244,7 +244,7 @@ static void rapl_pmu_event_start(struct perf_event *event, int mode)
 
 static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
@@ -278,7 +278,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 
 static int rapl_pmu_event_add(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
@@ -696,7 +696,7 @@ static int __init rapl_pmu_init(void)
 		return -1;
 	}
 
-	pmu = __get_cpu_var(rapl_pmu);
+	pmu = __this_cpu_read(rapl_pmu);
 
 	pr_info("RAPL PMU detected, hw unit 2^-%d Joules,"
 		" API unit is 2^-32 Joules,"
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 0939f86f543d..9762dbd9f3f7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -1,83 +1,39 @@
 #include "perf_event_intel_uncore.h"
 
 static struct intel_uncore_type *empty_uncore[] = { NULL, };
-static struct intel_uncore_type **msr_uncores = empty_uncore;
-static struct intel_uncore_type **pci_uncores = empty_uncore;
-/* pci bus to socket mapping */
-static int pcibus_to_physid[256] = { [0 ... 255] = -1, };
+struct intel_uncore_type **uncore_msr_uncores = empty_uncore;
+struct intel_uncore_type **uncore_pci_uncores = empty_uncore;
 
-static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+static bool pcidrv_registered;
+struct pci_driver *uncore_pci_driver;
+/* pci bus to socket mapping */
+int uncore_pcibus_to_physid[256] = { [0 ... 255] = -1, };
+struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
 
 static DEFINE_RAW_SPINLOCK(uncore_box_lock);
-
 /* mask of cpus that collect uncore events */
 static cpumask_t uncore_cpu_mask;
 
 /* constraint for the fixed counter */
-static struct event_constraint constraint_fixed =
+static struct event_constraint uncore_constraint_fixed =
 	EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL);
-static struct event_constraint constraint_empty =
+struct event_constraint uncore_constraint_empty =
 	EVENT_CONSTRAINT(0, 0, 0);
 
-#define __BITS_VALUE(x, i, n)  ((typeof(x))(((x) >> ((i) * (n))) & \
-				((1ULL << (n)) - 1)))
-
-DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
-DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
-DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
-DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
-DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
-DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
-DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28");
-DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31");
-DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
-DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
-DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
-DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
-DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
-DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
-DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
-DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
-DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
-DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
-DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
-DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
-DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
-DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51");
-DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35");
-DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31");
-DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17");
-DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12");
-DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8");
-DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4");
-DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63");
-DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51");
-DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35");
-DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31");
-DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17");
-DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12");
-DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8");
-DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
-DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
-
-static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
-static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
-static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
-static void uncore_pmu_event_read(struct perf_event *event);
-
-static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
+ssize_t uncore_event_show(struct kobject *kobj,
+			  struct kobj_attribute *attr, char *buf)
+{
+	struct uncore_event_desc *event =
+		container_of(attr, struct uncore_event_desc, attr);
+	return sprintf(buf, "%s", event->config);
+}
+
+struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
 {
 	return container_of(event->pmu, struct intel_uncore_pmu, pmu);
 }
 
-static struct intel_uncore_box *
-uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
+struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
 {
 	struct intel_uncore_box *box;
 
@@ -86,6 +42,9 @@ uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
 		return box;
 
 	raw_spin_lock(&uncore_box_lock);
+	/* Recheck in lock to handle races. */
+	if (*per_cpu_ptr(pmu->box, cpu))
+		goto out;
 	list_for_each_entry(box, &pmu->box_list, list) {
 		if (box->phys_id == topology_physical_package_id(cpu)) {
 			atomic_inc(&box->refcnt);
@@ -93,12 +52,13 @@ uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
 			break;
 		}
 	}
+out:
 	raw_spin_unlock(&uncore_box_lock);
 
 	return *per_cpu_ptr(pmu->box, cpu);
 }
 
-static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
+struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
 {
 	/*
 	 * perf core schedules event on the basis of cpu, uncore events are
@@ -107,7 +67,7 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
 	return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
 }
 
-static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
 {
 	u64 count;
 
@@ -119,7 +79,7 @@ static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_eve
 /*
  * generic get constraint function for shared match/mask registers.
  */
-static struct event_constraint *
+struct event_constraint *
 uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct intel_uncore_extra_reg *er;
@@ -154,10 +114,10 @@ uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
 		return NULL;
 	}
 
-	return &constraint_empty;
+	return &uncore_constraint_empty;
 }
 
-static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct intel_uncore_extra_reg *er;
 	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
@@ -178,7 +138,7 @@ static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_even
 	reg1->alloc = 0;
 }
 
-static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
+u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
 {
 	struct intel_uncore_extra_reg *er;
 	unsigned long flags;
@@ -193,2936 +153,6 @@ static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
 	return config;
 }
 
-/* Sandy Bridge-EP uncore support */
-static struct intel_uncore_type snbep_uncore_cbox;
-static struct intel_uncore_type snbep_uncore_pcu;
-
-static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	int box_ctl = uncore_pci_box_ctl(box);
-	u32 config = 0;
-
-	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
-		config |= SNBEP_PMON_BOX_CTL_FRZ;
-		pci_write_config_dword(pdev, box_ctl, config);
-	}
-}
-
-static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	int box_ctl = uncore_pci_box_ctl(box);
-	u32 config = 0;
-
-	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
-		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
-		pci_write_config_dword(pdev, box_ctl, config);
-	}
-}
-
-static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-
-	pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-
-	pci_write_config_dword(pdev, hwc->config_base, hwc->config);
-}
-
-static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-	u64 count = 0;
-
-	pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
-	pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
-
-	return count;
-}
-
-static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
-{
-	struct pci_dev *pdev = box->pci_dev;
-
-	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT);
-}
-
-static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
-{
-	u64 config;
-	unsigned msr;
-
-	msr = uncore_msr_box_ctl(box);
-	if (msr) {
-		rdmsrl(msr, config);
-		config |= SNBEP_PMON_BOX_CTL_FRZ;
-		wrmsrl(msr, config);
-	}
-}
-
-static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
-{
-	u64 config;
-	unsigned msr;
-
-	msr = uncore_msr_box_ctl(box);
-	if (msr) {
-		rdmsrl(msr, config);
-		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
-		wrmsrl(msr, config);
-	}
-}
-
-static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-
-	if (reg1->idx != EXTRA_REG_NONE)
-		wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0));
-
-	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	wrmsrl(hwc->config_base, hwc->config);
-}
-
-static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
-{
-	unsigned msr = uncore_msr_box_ctl(box);
-
-	if (msr)
-		wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
-}
-
-static struct attribute *snbep_uncore_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	NULL,
-};
-
-static struct attribute *snbep_uncore_ubox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh5.attr,
-	NULL,
-};
-
-static struct attribute *snbep_uncore_cbox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_tid_en.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	&format_attr_filter_tid.attr,
-	&format_attr_filter_nid.attr,
-	&format_attr_filter_state.attr,
-	&format_attr_filter_opc.attr,
-	NULL,
-};
-
-static struct attribute *snbep_uncore_pcu_formats_attr[] = {
-	&format_attr_event_ext.attr,
-	&format_attr_occ_sel.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh5.attr,
-	&format_attr_occ_invert.attr,
-	&format_attr_occ_edge.attr,
-	&format_attr_filter_band0.attr,
-	&format_attr_filter_band1.attr,
-	&format_attr_filter_band2.attr,
-	&format_attr_filter_band3.attr,
-	NULL,
-};
-
-static struct attribute *snbep_uncore_qpi_formats_attr[] = {
-	&format_attr_event_ext.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	&format_attr_match_rds.attr,
-	&format_attr_match_rnid30.attr,
-	&format_attr_match_rnid4.attr,
-	&format_attr_match_dnid.attr,
-	&format_attr_match_mc.attr,
-	&format_attr_match_opc.attr,
-	&format_attr_match_vnw.attr,
-	&format_attr_match0.attr,
-	&format_attr_match1.attr,
-	&format_attr_mask_rds.attr,
-	&format_attr_mask_rnid30.attr,
-	&format_attr_mask_rnid4.attr,
-	&format_attr_mask_dnid.attr,
-	&format_attr_mask_mc.attr,
-	&format_attr_mask_opc.attr,
-	&format_attr_mask_vnw.attr,
-	&format_attr_mask0.attr,
-	&format_attr_mask1.attr,
-	NULL,
-};
-
-static struct uncore_event_desc snbep_uncore_imc_events[] = {
-	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0xff,umask=0x00"),
-	INTEL_UNCORE_EVENT_DESC(cas_count_read,  "event=0x04,umask=0x03"),
-	INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
-	{ /* end: all zeroes */ },
-};
-
-static struct uncore_event_desc snbep_uncore_qpi_events[] = {
-	INTEL_UNCORE_EVENT_DESC(clockticks,       "event=0x14"),
-	INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
-	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x102,umask=0x08"),
-	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x103,umask=0x04"),
-	{ /* end: all zeroes */ },
-};
-
-static struct attribute_group snbep_uncore_format_group = {
-	.name = "format",
-	.attrs = snbep_uncore_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_ubox_format_group = {
-	.name = "format",
-	.attrs = snbep_uncore_ubox_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_cbox_format_group = {
-	.name = "format",
-	.attrs = snbep_uncore_cbox_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_pcu_format_group = {
-	.name = "format",
-	.attrs = snbep_uncore_pcu_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_qpi_format_group = {
-	.name = "format",
-	.attrs = snbep_uncore_qpi_formats_attr,
-};
-
-#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
-	.init_box	= snbep_uncore_msr_init_box,		\
-	.disable_box	= snbep_uncore_msr_disable_box,		\
-	.enable_box	= snbep_uncore_msr_enable_box,		\
-	.disable_event	= snbep_uncore_msr_disable_event,	\
-	.enable_event	= snbep_uncore_msr_enable_event,	\
-	.read_counter	= uncore_msr_read_counter
-
-static struct intel_uncore_ops snbep_uncore_msr_ops = {
-	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
-};
-
-#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT()			\
-	.init_box	= snbep_uncore_pci_init_box,		\
-	.disable_box	= snbep_uncore_pci_disable_box,		\
-	.enable_box	= snbep_uncore_pci_enable_box,		\
-	.disable_event	= snbep_uncore_pci_disable_event,	\
-	.read_counter	= snbep_uncore_pci_read_counter
-
-static struct intel_uncore_ops snbep_uncore_pci_ops = {
-	SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
-	.enable_event	= snbep_uncore_pci_enable_event,	\
-};
-
-static struct event_constraint snbep_uncore_cbox_constraints[] = {
-	UNCORE_EVENT_CONSTRAINT(0x01, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x02, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x04, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x05, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x07, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x09, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x13, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x1b, 0xc),
-	UNCORE_EVENT_CONSTRAINT(0x1c, 0xc),
-	UNCORE_EVENT_CONSTRAINT(0x1d, 0xc),
-	UNCORE_EVENT_CONSTRAINT(0x1e, 0xc),
-	EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff),
-	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x35, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x3b, 0x1),
-	EVENT_CONSTRAINT_END
-};
-
-static struct event_constraint snbep_uncore_r2pcie_constraints[] = {
-	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x12, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
-	EVENT_CONSTRAINT_END
-};
-
-static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
-	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2a, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2b, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x30, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
-	EVENT_CONSTRAINT_END
-};
-
-static struct intel_uncore_type snbep_uncore_ubox = {
-	.name		= "ubox",
-	.num_counters   = 2,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 44,
-	.fixed_ctr_bits	= 48,
-	.perf_ctr	= SNBEP_U_MSR_PMON_CTR0,
-	.event_ctl	= SNBEP_U_MSR_PMON_CTL0,
-	.event_mask	= SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
-	.fixed_ctr	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
-	.fixed_ctl	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
-	.ops		= &snbep_uncore_msr_ops,
-	.format_group	= &snbep_uncore_ubox_format_group,
-};
-
-static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
-	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
-				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2),
-	EVENT_EXTRA_END
-};
-
-static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
-	int i;
-
-	if (uncore_box_is_fake(box))
-		return;
-
-	for (i = 0; i < 5; i++) {
-		if (reg1->alloc & (0x1 << i))
-			atomic_sub(1 << (i * 6), &er->ref);
-	}
-	reg1->alloc = 0;
-}
-
-static struct event_constraint *
-__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event,
-			    u64 (*cbox_filter_mask)(int fields))
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
-	int i, alloc = 0;
-	unsigned long flags;
-	u64 mask;
-
-	if (reg1->idx == EXTRA_REG_NONE)
-		return NULL;
-
-	raw_spin_lock_irqsave(&er->lock, flags);
-	for (i = 0; i < 5; i++) {
-		if (!(reg1->idx & (0x1 << i)))
-			continue;
-		if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
-			continue;
-
-		mask = cbox_filter_mask(0x1 << i);
-		if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) ||
-		    !((reg1->config ^ er->config) & mask)) {
-			atomic_add(1 << (i * 6), &er->ref);
-			er->config &= ~mask;
-			er->config |= reg1->config & mask;
-			alloc |= (0x1 << i);
-		} else {
-			break;
-		}
-	}
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-	if (i < 5)
-		goto fail;
-
-	if (!uncore_box_is_fake(box))
-		reg1->alloc |= alloc;
-
-	return NULL;
-fail:
-	for (; i >= 0; i--) {
-		if (alloc & (0x1 << i))
-			atomic_sub(1 << (i * 6), &er->ref);
-	}
-	return &constraint_empty;
-}
-
-static u64 snbep_cbox_filter_mask(int fields)
-{
-	u64 mask = 0;
-
-	if (fields & 0x1)
-		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID;
-	if (fields & 0x2)
-		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID;
-	if (fields & 0x4)
-		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE;
-	if (fields & 0x8)
-		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC;
-
-	return mask;
-}
-
-static struct event_constraint *
-snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask);
-}
-
-static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct extra_reg *er;
-	int idx = 0;
-
-	for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) {
-		if (er->event != (event->hw.config & er->config_mask))
-			continue;
-		idx |= er->idx;
-	}
-
-	if (idx) {
-		reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
-			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
-		reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx);
-		reg1->idx = idx;
-	}
-	return 0;
-}
-
-static struct intel_uncore_ops snbep_uncore_cbox_ops = {
-	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
-	.hw_config		= snbep_cbox_hw_config,
-	.get_constraint		= snbep_cbox_get_constraint,
-	.put_constraint		= snbep_cbox_put_constraint,
-};
-
-static struct intel_uncore_type snbep_uncore_cbox = {
-	.name			= "cbox",
-	.num_counters		= 4,
-	.num_boxes		= 8,
-	.perf_ctr_bits		= 44,
-	.event_ctl		= SNBEP_C0_MSR_PMON_CTL0,
-	.perf_ctr		= SNBEP_C0_MSR_PMON_CTR0,
-	.event_mask		= SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_C0_MSR_PMON_BOX_CTL,
-	.msr_offset		= SNBEP_CBO_MSR_OFFSET,
-	.num_shared_regs	= 1,
-	.constraints		= snbep_uncore_cbox_constraints,
-	.ops			= &snbep_uncore_cbox_ops,
-	.format_group		= &snbep_uncore_cbox_format_group,
-};
-
-static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	u64 config = reg1->config;
-
-	if (new_idx > reg1->idx)
-		config <<= 8 * (new_idx - reg1->idx);
-	else
-		config >>= 8 * (reg1->idx - new_idx);
-
-	if (modify) {
-		hwc->config += new_idx - reg1->idx;
-		reg1->config = config;
-		reg1->idx = new_idx;
-	}
-	return config;
-}
-
-static struct event_constraint *
-snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
-	unsigned long flags;
-	int idx = reg1->idx;
-	u64 mask, config1 = reg1->config;
-	bool ok = false;
-
-	if (reg1->idx == EXTRA_REG_NONE ||
-	    (!uncore_box_is_fake(box) && reg1->alloc))
-		return NULL;
-again:
-	mask = 0xffULL << (idx * 8);
-	raw_spin_lock_irqsave(&er->lock, flags);
-	if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) ||
-	    !((config1 ^ er->config) & mask)) {
-		atomic_add(1 << (idx * 8), &er->ref);
-		er->config &= ~mask;
-		er->config |= config1 & mask;
-		ok = true;
-	}
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-
-	if (!ok) {
-		idx = (idx + 1) % 4;
-		if (idx != reg1->idx) {
-			config1 = snbep_pcu_alter_er(event, idx, false);
-			goto again;
-		}
-		return &constraint_empty;
-	}
-
-	if (!uncore_box_is_fake(box)) {
-		if (idx != reg1->idx)
-			snbep_pcu_alter_er(event, idx, true);
-		reg1->alloc = 1;
-	}
-	return NULL;
-}
-
-static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
-
-	if (uncore_box_is_fake(box) || !reg1->alloc)
-		return;
-
-	atomic_sub(1 << (reg1->idx * 8), &er->ref);
-	reg1->alloc = 0;
-}
-
-static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
-
-	if (ev_sel >= 0xb && ev_sel <= 0xe) {
-		reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
-		reg1->idx = ev_sel - 0xb;
-		reg1->config = event->attr.config1 & (0xff << reg1->idx);
-	}
-	return 0;
-}
-
-static struct intel_uncore_ops snbep_uncore_pcu_ops = {
-	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
-	.hw_config		= snbep_pcu_hw_config,
-	.get_constraint		= snbep_pcu_get_constraint,
-	.put_constraint		= snbep_pcu_put_constraint,
-};
-
-static struct intel_uncore_type snbep_uncore_pcu = {
-	.name			= "pcu",
-	.num_counters		= 4,
-	.num_boxes		= 1,
-	.perf_ctr_bits		= 48,
-	.perf_ctr		= SNBEP_PCU_MSR_PMON_CTR0,
-	.event_ctl		= SNBEP_PCU_MSR_PMON_CTL0,
-	.event_mask		= SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_PCU_MSR_PMON_BOX_CTL,
-	.num_shared_regs	= 1,
-	.ops			= &snbep_uncore_pcu_ops,
-	.format_group		= &snbep_uncore_pcu_format_group,
-};
-
-static struct intel_uncore_type *snbep_msr_uncores[] = {
-	&snbep_uncore_ubox,
-	&snbep_uncore_cbox,
-	&snbep_uncore_pcu,
-	NULL,
-};
-
-enum {
-	SNBEP_PCI_QPI_PORT0_FILTER,
-	SNBEP_PCI_QPI_PORT1_FILTER,
-};
-
-static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
-	if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) {
-		reg1->idx = 0;
-		reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0;
-		reg1->config = event->attr.config1;
-		reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0;
-		reg2->config = event->attr.config2;
-	}
-	return 0;
-}
-
-static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
-	if (reg1->idx != EXTRA_REG_NONE) {
-		int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
-		struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx];
-		WARN_ON_ONCE(!filter_pdev);
-		if (filter_pdev) {
-			pci_write_config_dword(filter_pdev, reg1->reg,
-						(u32)reg1->config);
-			pci_write_config_dword(filter_pdev, reg1->reg + 4,
-						(u32)(reg1->config >> 32));
-			pci_write_config_dword(filter_pdev, reg2->reg,
-						(u32)reg2->config);
-			pci_write_config_dword(filter_pdev, reg2->reg + 4,
-						(u32)(reg2->config >> 32));
-		}
-	}
-
-	pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static struct intel_uncore_ops snbep_uncore_qpi_ops = {
-	SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
-	.enable_event		= snbep_qpi_enable_event,
-	.hw_config		= snbep_qpi_hw_config,
-	.get_constraint		= uncore_get_constraint,
-	.put_constraint		= uncore_put_constraint,
-};
-
-#define SNBEP_UNCORE_PCI_COMMON_INIT()				\
-	.perf_ctr	= SNBEP_PCI_PMON_CTR0,			\
-	.event_ctl	= SNBEP_PCI_PMON_CTL0,			\
-	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,		\
-	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,		\
-	.ops		= &snbep_uncore_pci_ops,		\
-	.format_group	= &snbep_uncore_format_group
-
-static struct intel_uncore_type snbep_uncore_ha = {
-	.name		= "ha",
-	.num_counters   = 4,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 48,
-	SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type snbep_uncore_imc = {
-	.name		= "imc",
-	.num_counters   = 4,
-	.num_boxes	= 4,
-	.perf_ctr_bits	= 48,
-	.fixed_ctr_bits	= 48,
-	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
-	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
-	.event_descs	= snbep_uncore_imc_events,
-	SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type snbep_uncore_qpi = {
-	.name			= "qpi",
-	.num_counters		= 4,
-	.num_boxes		= 2,
-	.perf_ctr_bits		= 48,
-	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
-	.event_ctl		= SNBEP_PCI_PMON_CTL0,
-	.event_mask		= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
-	.num_shared_regs	= 1,
-	.ops			= &snbep_uncore_qpi_ops,
-	.event_descs		= snbep_uncore_qpi_events,
-	.format_group		= &snbep_uncore_qpi_format_group,
-};
-
-
-static struct intel_uncore_type snbep_uncore_r2pcie = {
-	.name		= "r2pcie",
-	.num_counters   = 4,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 44,
-	.constraints	= snbep_uncore_r2pcie_constraints,
-	SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type snbep_uncore_r3qpi = {
-	.name		= "r3qpi",
-	.num_counters   = 3,
-	.num_boxes	= 2,
-	.perf_ctr_bits	= 44,
-	.constraints	= snbep_uncore_r3qpi_constraints,
-	SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-enum {
-	SNBEP_PCI_UNCORE_HA,
-	SNBEP_PCI_UNCORE_IMC,
-	SNBEP_PCI_UNCORE_QPI,
-	SNBEP_PCI_UNCORE_R2PCIE,
-	SNBEP_PCI_UNCORE_R3QPI,
-};
-
-static struct intel_uncore_type *snbep_pci_uncores[] = {
-	[SNBEP_PCI_UNCORE_HA]		= &snbep_uncore_ha,
-	[SNBEP_PCI_UNCORE_IMC]		= &snbep_uncore_imc,
-	[SNBEP_PCI_UNCORE_QPI]		= &snbep_uncore_qpi,
-	[SNBEP_PCI_UNCORE_R2PCIE]	= &snbep_uncore_r2pcie,
-	[SNBEP_PCI_UNCORE_R3QPI]	= &snbep_uncore_r3qpi,
-	NULL,
-};
-
-static const struct pci_device_id snbep_uncore_pci_ids[] = {
-	{ /* Home Agent */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0),
-	},
-	{ /* MC Channel 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0),
-	},
-	{ /* MC Channel 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1),
-	},
-	{ /* MC Channel 2 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2),
-	},
-	{ /* MC Channel 3 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3),
-	},
-	{ /* QPI Port 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0),
-	},
-	{ /* QPI Port 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1),
-	},
-	{ /* R2PCIe */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0),
-	},
-	{ /* R3QPI Link 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0),
-	},
-	{ /* R3QPI Link 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1),
-	},
-	{ /* QPI Port 0 filter  */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
-						   SNBEP_PCI_QPI_PORT0_FILTER),
-	},
-	{ /* QPI Port 0 filter  */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
-						   SNBEP_PCI_QPI_PORT1_FILTER),
-	},
-	{ /* end: all zeroes */ }
-};
-
-static struct pci_driver snbep_uncore_pci_driver = {
-	.name		= "snbep_uncore",
-	.id_table	= snbep_uncore_pci_ids,
-};
-
-/*
- * build pci bus to socket mapping
- */
-static int snbep_pci2phy_map_init(int devid)
-{
-	struct pci_dev *ubox_dev = NULL;
-	int i, bus, nodeid;
-	int err = 0;
-	u32 config = 0;
-
-	while (1) {
-		/* find the UBOX device */
-		ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev);
-		if (!ubox_dev)
-			break;
-		bus = ubox_dev->bus->number;
-		/* get the Node ID of the local register */
-		err = pci_read_config_dword(ubox_dev, 0x40, &config);
-		if (err)
-			break;
-		nodeid = config;
-		/* get the Node ID mapping */
-		err = pci_read_config_dword(ubox_dev, 0x54, &config);
-		if (err)
-			break;
-		/*
-		 * every three bits in the Node ID mapping register maps
-		 * to a particular node.
-		 */
-		for (i = 0; i < 8; i++) {
-			if (nodeid == ((config >> (3 * i)) & 0x7)) {
-				pcibus_to_physid[bus] = i;
-				break;
-			}
-		}
-	}
-
-	if (!err) {
-		/*
-		 * For PCI bus with no UBOX device, find the next bus
-		 * that has UBOX device and use its mapping.
-		 */
-		i = -1;
-		for (bus = 255; bus >= 0; bus--) {
-			if (pcibus_to_physid[bus] >= 0)
-				i = pcibus_to_physid[bus];
-			else
-				pcibus_to_physid[bus] = i;
-		}
-	}
-
-	if (ubox_dev)
-		pci_dev_put(ubox_dev);
-
-	return err ? pcibios_err_to_errno(err) : 0;
-}
-/* end of Sandy Bridge-EP uncore support */
-
-/* IvyTown uncore support */
-static void ivt_uncore_msr_init_box(struct intel_uncore_box *box)
-{
-	unsigned msr = uncore_msr_box_ctl(box);
-	if (msr)
-		wrmsrl(msr, IVT_PMON_BOX_CTL_INT);
-}
-
-static void ivt_uncore_pci_init_box(struct intel_uncore_box *box)
-{
-	struct pci_dev *pdev = box->pci_dev;
-
-	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVT_PMON_BOX_CTL_INT);
-}
-
-#define IVT_UNCORE_MSR_OPS_COMMON_INIT()			\
-	.init_box	= ivt_uncore_msr_init_box,		\
-	.disable_box	= snbep_uncore_msr_disable_box,		\
-	.enable_box	= snbep_uncore_msr_enable_box,		\
-	.disable_event	= snbep_uncore_msr_disable_event,	\
-	.enable_event	= snbep_uncore_msr_enable_event,	\
-	.read_counter	= uncore_msr_read_counter
-
-static struct intel_uncore_ops ivt_uncore_msr_ops = {
-	IVT_UNCORE_MSR_OPS_COMMON_INIT(),
-};
-
-static struct intel_uncore_ops ivt_uncore_pci_ops = {
-	.init_box	= ivt_uncore_pci_init_box,
-	.disable_box	= snbep_uncore_pci_disable_box,
-	.enable_box	= snbep_uncore_pci_enable_box,
-	.disable_event	= snbep_uncore_pci_disable_event,
-	.enable_event	= snbep_uncore_pci_enable_event,
-	.read_counter	= snbep_uncore_pci_read_counter,
-};
-
-#define IVT_UNCORE_PCI_COMMON_INIT()				\
-	.perf_ctr	= SNBEP_PCI_PMON_CTR0,			\
-	.event_ctl	= SNBEP_PCI_PMON_CTL0,			\
-	.event_mask	= IVT_PMON_RAW_EVENT_MASK,		\
-	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,		\
-	.ops		= &ivt_uncore_pci_ops,			\
-	.format_group	= &ivt_uncore_format_group
-
-static struct attribute *ivt_uncore_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	NULL,
-};
-
-static struct attribute *ivt_uncore_ubox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh5.attr,
-	NULL,
-};
-
-static struct attribute *ivt_uncore_cbox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_tid_en.attr,
-	&format_attr_thresh8.attr,
-	&format_attr_filter_tid.attr,
-	&format_attr_filter_link.attr,
-	&format_attr_filter_state2.attr,
-	&format_attr_filter_nid2.attr,
-	&format_attr_filter_opc2.attr,
-	NULL,
-};
-
-static struct attribute *ivt_uncore_pcu_formats_attr[] = {
-	&format_attr_event_ext.attr,
-	&format_attr_occ_sel.attr,
-	&format_attr_edge.attr,
-	&format_attr_thresh5.attr,
-	&format_attr_occ_invert.attr,
-	&format_attr_occ_edge.attr,
-	&format_attr_filter_band0.attr,
-	&format_attr_filter_band1.attr,
-	&format_attr_filter_band2.attr,
-	&format_attr_filter_band3.attr,
-	NULL,
-};
-
-static struct attribute *ivt_uncore_qpi_formats_attr[] = {
-	&format_attr_event_ext.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_thresh8.attr,
-	&format_attr_match_rds.attr,
-	&format_attr_match_rnid30.attr,
-	&format_attr_match_rnid4.attr,
-	&format_attr_match_dnid.attr,
-	&format_attr_match_mc.attr,
-	&format_attr_match_opc.attr,
-	&format_attr_match_vnw.attr,
-	&format_attr_match0.attr,
-	&format_attr_match1.attr,
-	&format_attr_mask_rds.attr,
-	&format_attr_mask_rnid30.attr,
-	&format_attr_mask_rnid4.attr,
-	&format_attr_mask_dnid.attr,
-	&format_attr_mask_mc.attr,
-	&format_attr_mask_opc.attr,
-	&format_attr_mask_vnw.attr,
-	&format_attr_mask0.attr,
-	&format_attr_mask1.attr,
-	NULL,
-};
-
-static struct attribute_group ivt_uncore_format_group = {
-	.name = "format",
-	.attrs = ivt_uncore_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_ubox_format_group = {
-	.name = "format",
-	.attrs = ivt_uncore_ubox_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_cbox_format_group = {
-	.name = "format",
-	.attrs = ivt_uncore_cbox_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_pcu_format_group = {
-	.name = "format",
-	.attrs = ivt_uncore_pcu_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_qpi_format_group = {
-	.name = "format",
-	.attrs = ivt_uncore_qpi_formats_attr,
-};
-
-static struct intel_uncore_type ivt_uncore_ubox = {
-	.name		= "ubox",
-	.num_counters   = 2,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 44,
-	.fixed_ctr_bits	= 48,
-	.perf_ctr	= SNBEP_U_MSR_PMON_CTR0,
-	.event_ctl	= SNBEP_U_MSR_PMON_CTL0,
-	.event_mask	= IVT_U_MSR_PMON_RAW_EVENT_MASK,
-	.fixed_ctr	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
-	.fixed_ctl	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
-	.ops		= &ivt_uncore_msr_ops,
-	.format_group	= &ivt_uncore_ubox_format_group,
-};
-
-static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
-	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
-				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
-
-	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8),
-	EVENT_EXTRA_END
-};
-
-static u64 ivt_cbox_filter_mask(int fields)
-{
-	u64 mask = 0;
-
-	if (fields & 0x1)
-		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_TID;
-	if (fields & 0x2)
-		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_LINK;
-	if (fields & 0x4)
-		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_STATE;
-	if (fields & 0x8)
-		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_NID;
-	if (fields & 0x10)
-		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_OPC;
-
-	return mask;
-}
-
-static struct event_constraint *
-ivt_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	return __snbep_cbox_get_constraint(box, event, ivt_cbox_filter_mask);
-}
-
-static int ivt_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct extra_reg *er;
-	int idx = 0;
-
-	for (er = ivt_uncore_cbox_extra_regs; er->msr; er++) {
-		if (er->event != (event->hw.config & er->config_mask))
-			continue;
-		idx |= er->idx;
-	}
-
-	if (idx) {
-		reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
-			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
-		reg1->config = event->attr.config1 & ivt_cbox_filter_mask(idx);
-		reg1->idx = idx;
-	}
-	return 0;
-}
-
-static void ivt_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-
-	if (reg1->idx != EXTRA_REG_NONE) {
-		u64 filter = uncore_shared_reg_config(box, 0);
-		wrmsrl(reg1->reg, filter & 0xffffffff);
-		wrmsrl(reg1->reg + 6, filter >> 32);
-	}
-
-	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static struct intel_uncore_ops ivt_uncore_cbox_ops = {
-	.init_box		= ivt_uncore_msr_init_box,
-	.disable_box		= snbep_uncore_msr_disable_box,
-	.enable_box		= snbep_uncore_msr_enable_box,
-	.disable_event		= snbep_uncore_msr_disable_event,
-	.enable_event		= ivt_cbox_enable_event,
-	.read_counter		= uncore_msr_read_counter,
-	.hw_config		= ivt_cbox_hw_config,
-	.get_constraint		= ivt_cbox_get_constraint,
-	.put_constraint		= snbep_cbox_put_constraint,
-};
-
-static struct intel_uncore_type ivt_uncore_cbox = {
-	.name			= "cbox",
-	.num_counters		= 4,
-	.num_boxes		= 15,
-	.perf_ctr_bits		= 44,
-	.event_ctl		= SNBEP_C0_MSR_PMON_CTL0,
-	.perf_ctr		= SNBEP_C0_MSR_PMON_CTR0,
-	.event_mask		= IVT_CBO_MSR_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_C0_MSR_PMON_BOX_CTL,
-	.msr_offset		= SNBEP_CBO_MSR_OFFSET,
-	.num_shared_regs	= 1,
-	.constraints		= snbep_uncore_cbox_constraints,
-	.ops			= &ivt_uncore_cbox_ops,
-	.format_group		= &ivt_uncore_cbox_format_group,
-};
-
-static struct intel_uncore_ops ivt_uncore_pcu_ops = {
-	IVT_UNCORE_MSR_OPS_COMMON_INIT(),
-	.hw_config		= snbep_pcu_hw_config,
-	.get_constraint		= snbep_pcu_get_constraint,
-	.put_constraint		= snbep_pcu_put_constraint,
-};
-
-static struct intel_uncore_type ivt_uncore_pcu = {
-	.name			= "pcu",
-	.num_counters		= 4,
-	.num_boxes		= 1,
-	.perf_ctr_bits		= 48,
-	.perf_ctr		= SNBEP_PCU_MSR_PMON_CTR0,
-	.event_ctl		= SNBEP_PCU_MSR_PMON_CTL0,
-	.event_mask		= IVT_PCU_MSR_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_PCU_MSR_PMON_BOX_CTL,
-	.num_shared_regs	= 1,
-	.ops			= &ivt_uncore_pcu_ops,
-	.format_group		= &ivt_uncore_pcu_format_group,
-};
-
-static struct intel_uncore_type *ivt_msr_uncores[] = {
-	&ivt_uncore_ubox,
-	&ivt_uncore_cbox,
-	&ivt_uncore_pcu,
-	NULL,
-};
-
-static struct intel_uncore_type ivt_uncore_ha = {
-	.name		= "ha",
-	.num_counters   = 4,
-	.num_boxes	= 2,
-	.perf_ctr_bits	= 48,
-	IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type ivt_uncore_imc = {
-	.name		= "imc",
-	.num_counters   = 4,
-	.num_boxes	= 8,
-	.perf_ctr_bits	= 48,
-	.fixed_ctr_bits	= 48,
-	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
-	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
-	IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-/* registers in IRP boxes are not properly aligned */
-static unsigned ivt_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4};
-static unsigned ivt_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0};
-
-static void ivt_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-
-	pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx],
-			       hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static void ivt_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-
-	pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], hwc->config);
-}
-
-static u64 ivt_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-	u64 count = 0;
-
-	pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx], (u32 *)&count);
-	pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1);
-
-	return count;
-}
-
-static struct intel_uncore_ops ivt_uncore_irp_ops = {
-	.init_box	= ivt_uncore_pci_init_box,
-	.disable_box	= snbep_uncore_pci_disable_box,
-	.enable_box	= snbep_uncore_pci_enable_box,
-	.disable_event	= ivt_uncore_irp_disable_event,
-	.enable_event	= ivt_uncore_irp_enable_event,
-	.read_counter	= ivt_uncore_irp_read_counter,
-};
-
-static struct intel_uncore_type ivt_uncore_irp = {
-	.name			= "irp",
-	.num_counters		= 4,
-	.num_boxes		= 1,
-	.perf_ctr_bits		= 48,
-	.event_mask		= IVT_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
-	.ops			= &ivt_uncore_irp_ops,
-	.format_group		= &ivt_uncore_format_group,
-};
-
-static struct intel_uncore_ops ivt_uncore_qpi_ops = {
-	.init_box	= ivt_uncore_pci_init_box,
-	.disable_box	= snbep_uncore_pci_disable_box,
-	.enable_box	= snbep_uncore_pci_enable_box,
-	.disable_event	= snbep_uncore_pci_disable_event,
-	.enable_event	= snbep_qpi_enable_event,
-	.read_counter	= snbep_uncore_pci_read_counter,
-	.hw_config	= snbep_qpi_hw_config,
-	.get_constraint	= uncore_get_constraint,
-	.put_constraint	= uncore_put_constraint,
-};
-
-static struct intel_uncore_type ivt_uncore_qpi = {
-	.name			= "qpi",
-	.num_counters		= 4,
-	.num_boxes		= 3,
-	.perf_ctr_bits		= 48,
-	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
-	.event_ctl		= SNBEP_PCI_PMON_CTL0,
-	.event_mask		= IVT_QPI_PCI_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
-	.num_shared_regs	= 1,
-	.ops			= &ivt_uncore_qpi_ops,
-	.format_group		= &ivt_uncore_qpi_format_group,
-};
-
-static struct intel_uncore_type ivt_uncore_r2pcie = {
-	.name		= "r2pcie",
-	.num_counters   = 4,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 44,
-	.constraints	= snbep_uncore_r2pcie_constraints,
-	IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type ivt_uncore_r3qpi = {
-	.name		= "r3qpi",
-	.num_counters   = 3,
-	.num_boxes	= 2,
-	.perf_ctr_bits	= 44,
-	.constraints	= snbep_uncore_r3qpi_constraints,
-	IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-enum {
-	IVT_PCI_UNCORE_HA,
-	IVT_PCI_UNCORE_IMC,
-	IVT_PCI_UNCORE_IRP,
-	IVT_PCI_UNCORE_QPI,
-	IVT_PCI_UNCORE_R2PCIE,
-	IVT_PCI_UNCORE_R3QPI,
-};
-
-static struct intel_uncore_type *ivt_pci_uncores[] = {
-	[IVT_PCI_UNCORE_HA]	= &ivt_uncore_ha,
-	[IVT_PCI_UNCORE_IMC]	= &ivt_uncore_imc,
-	[IVT_PCI_UNCORE_IRP]	= &ivt_uncore_irp,
-	[IVT_PCI_UNCORE_QPI]	= &ivt_uncore_qpi,
-	[IVT_PCI_UNCORE_R2PCIE]	= &ivt_uncore_r2pcie,
-	[IVT_PCI_UNCORE_R3QPI]	= &ivt_uncore_r3qpi,
-	NULL,
-};
-
-static const struct pci_device_id ivt_uncore_pci_ids[] = {
-	{ /* Home Agent 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0),
-	},
-	{ /* Home Agent 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1),
-	},
-	{ /* MC0 Channel 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0),
-	},
-	{ /* MC0 Channel 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1),
-	},
-	{ /* MC0 Channel 3 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2),
-	},
-	{ /* MC0 Channel 4 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3),
-	},
-	{ /* MC1 Channel 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4),
-	},
-	{ /* MC1 Channel 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5),
-	},
-	{ /* MC1 Channel 3 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6),
-	},
-	{ /* MC1 Channel 4 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7),
-	},
-	{ /* IRP */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IRP, 0),
-	},
-	{ /* QPI0 Port 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0),
-	},
-	{ /* QPI0 Port 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1),
-	},
-	{ /* QPI1 Port 2 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2),
-	},
-	{ /* R2PCIe */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0),
-	},
-	{ /* R3QPI0 Link 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0),
-	},
-	{ /* R3QPI0 Link 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1),
-	},
-	{ /* R3QPI1 Link 2 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2),
-	},
-	{ /* QPI Port 0 filter  */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
-						   SNBEP_PCI_QPI_PORT0_FILTER),
-	},
-	{ /* QPI Port 0 filter  */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
-						   SNBEP_PCI_QPI_PORT1_FILTER),
-	},
-	{ /* end: all zeroes */ }
-};
-
-static struct pci_driver ivt_uncore_pci_driver = {
-	.name		= "ivt_uncore",
-	.id_table	= ivt_uncore_pci_ids,
-};
-/* end of IvyTown uncore support */
-
-/* Sandy Bridge uncore support */
-static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
-		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
-	else
-		wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
-}
-
-static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	wrmsrl(event->hw.config_base, 0);
-}
-
-static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
-{
-	if (box->pmu->pmu_idx == 0) {
-		wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
-			SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
-	}
-}
-
-static struct uncore_event_desc snb_uncore_events[] = {
-	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
-	{ /* end: all zeroes */ },
-};
-
-static struct attribute *snb_uncore_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_cmask5.attr,
-	NULL,
-};
-
-static struct attribute_group snb_uncore_format_group = {
-	.name		= "format",
-	.attrs		= snb_uncore_formats_attr,
-};
-
-static struct intel_uncore_ops snb_uncore_msr_ops = {
-	.init_box	= snb_uncore_msr_init_box,
-	.disable_event	= snb_uncore_msr_disable_event,
-	.enable_event	= snb_uncore_msr_enable_event,
-	.read_counter	= uncore_msr_read_counter,
-};
-
-static struct event_constraint snb_uncore_cbox_constraints[] = {
-	UNCORE_EVENT_CONSTRAINT(0x80, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x83, 0x1),
-	EVENT_CONSTRAINT_END
-};
-
-static struct intel_uncore_type snb_uncore_cbox = {
-	.name		= "cbox",
-	.num_counters   = 2,
-	.num_boxes	= 4,
-	.perf_ctr_bits	= 44,
-	.fixed_ctr_bits	= 48,
-	.perf_ctr	= SNB_UNC_CBO_0_PER_CTR0,
-	.event_ctl	= SNB_UNC_CBO_0_PERFEVTSEL0,
-	.fixed_ctr	= SNB_UNC_FIXED_CTR,
-	.fixed_ctl	= SNB_UNC_FIXED_CTR_CTRL,
-	.single_fixed	= 1,
-	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
-	.msr_offset	= SNB_UNC_CBO_MSR_OFFSET,
-	.constraints	= snb_uncore_cbox_constraints,
-	.ops		= &snb_uncore_msr_ops,
-	.format_group	= &snb_uncore_format_group,
-	.event_descs	= snb_uncore_events,
-};
-
-static struct intel_uncore_type *snb_msr_uncores[] = {
-	&snb_uncore_cbox,
-	NULL,
-};
-
-enum {
-	SNB_PCI_UNCORE_IMC,
-};
-
-static struct uncore_event_desc snb_uncore_imc_events[] = {
-	INTEL_UNCORE_EVENT_DESC(data_reads,  "event=0x01"),
-	INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"),
-	INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"),
-
-	INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"),
-	INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"),
-	INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"),
-
-	{ /* end: all zeroes */ },
-};
-
-#define SNB_UNCORE_PCI_IMC_EVENT_MASK		0xff
-#define SNB_UNCORE_PCI_IMC_BAR_OFFSET		0x48
-
-/* page size multiple covering all config regs */
-#define SNB_UNCORE_PCI_IMC_MAP_SIZE		0x6000
-
-#define SNB_UNCORE_PCI_IMC_DATA_READS		0x1
-#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE	0x5050
-#define SNB_UNCORE_PCI_IMC_DATA_WRITES		0x2
-#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE	0x5054
-#define SNB_UNCORE_PCI_IMC_CTR_BASE		SNB_UNCORE_PCI_IMC_DATA_READS_BASE
-
-static struct attribute *snb_uncore_imc_formats_attr[] = {
-	&format_attr_event.attr,
-	NULL,
-};
-
-static struct attribute_group snb_uncore_imc_format_group = {
-	.name = "format",
-	.attrs = snb_uncore_imc_formats_attr,
-};
-
-static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET;
-	resource_size_t addr;
-	u32 pci_dword;
-
-	pci_read_config_dword(pdev, where, &pci_dword);
-	addr = pci_dword;
-
-#ifdef CONFIG_PHYS_ADDR_T_64BIT
-	pci_read_config_dword(pdev, where + 4, &pci_dword);
-	addr |= ((resource_size_t)pci_dword << 32);
-#endif
-
-	addr &= ~(PAGE_SIZE - 1);
-
-	box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
-	box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
-}
-
-static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
-{}
-
-static void snb_uncore_imc_disable_box(struct intel_uncore_box *box)
-{}
-
-static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{}
-
-static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{}
-
-static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
-}
-
-/*
- * custom event_init() function because we define our own fixed, free
- * running counters, so we do not want to conflict with generic uncore
- * logic. Also simplifies processing
- */
-static int snb_uncore_imc_event_init(struct perf_event *event)
-{
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box;
-	struct hw_perf_event *hwc = &event->hw;
-	u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK;
-	int idx, base;
-
-	if (event->attr.type != event->pmu->type)
-		return -ENOENT;
-
-	pmu = uncore_event_to_pmu(event);
-	/* no device found for this pmu */
-	if (pmu->func_id < 0)
-		return -ENOENT;
-
-	/* Sampling not supported yet */
-	if (hwc->sample_period)
-		return -EINVAL;
-
-	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest  ||
-	    event->attr.sample_period) /* no sampling */
-		return -EINVAL;
-
-	/*
-	 * Place all uncore events for a particular physical package
-	 * onto a single cpu
-	 */
-	if (event->cpu < 0)
-		return -EINVAL;
-
-	/* check only supported bits are set */
-	if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK)
-		return -EINVAL;
-
-	box = uncore_pmu_to_box(pmu, event->cpu);
-	if (!box || box->cpu < 0)
-		return -EINVAL;
-
-	event->cpu = box->cpu;
-
-	event->hw.idx = -1;
-	event->hw.last_tag = ~0ULL;
-	event->hw.extra_reg.idx = EXTRA_REG_NONE;
-	event->hw.branch_reg.idx = EXTRA_REG_NONE;
-	/*
-	 * check event is known (whitelist, determines counter)
-	 */
-	switch (cfg) {
-	case SNB_UNCORE_PCI_IMC_DATA_READS:
-		base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
-		idx = UNCORE_PMC_IDX_FIXED;
-		break;
-	case SNB_UNCORE_PCI_IMC_DATA_WRITES:
-		base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
-		idx = UNCORE_PMC_IDX_FIXED + 1;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* must be done before validate_group */
-	event->hw.event_base = base;
-	event->hw.config = cfg;
-	event->hw.idx = idx;
-
-	/* no group validation needed, we have free running counters */
-
-	return 0;
-}
-
-static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	return 0;
-}
-
-static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	u64 count;
-
-	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
-		return;
-
-	event->hw.state = 0;
-	box->n_active++;
-
-	list_add_tail(&event->active_entry, &box->active_list);
-
-	count = snb_uncore_imc_read_counter(box, event);
-	local64_set(&event->hw.prev_count, count);
-
-	if (box->n_active == 1)
-		uncore_pmu_start_hrtimer(box);
-}
-
-static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (!(hwc->state & PERF_HES_STOPPED)) {
-		box->n_active--;
-
-		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
-		hwc->state |= PERF_HES_STOPPED;
-
-		list_del(&event->active_entry);
-
-		if (box->n_active == 0)
-			uncore_pmu_cancel_hrtimer(box);
-	}
-
-	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
-		/*
-		 * Drain the remaining delta count out of a event
-		 * that we are disabling:
-		 */
-		uncore_perf_event_update(box, event);
-		hwc->state |= PERF_HES_UPTODATE;
-	}
-}
-
-static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (!box)
-		return -ENODEV;
-
-	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
-	if (!(flags & PERF_EF_START))
-		hwc->state |= PERF_HES_ARCH;
-
-	snb_uncore_imc_event_start(event, 0);
-
-	box->n_events++;
-
-	return 0;
-}
-
-static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	int i;
-
-	snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
-
-	for (i = 0; i < box->n_events; i++) {
-		if (event == box->event_list[i]) {
-			--box->n_events;
-			break;
-		}
-	}
-}
-
-static int snb_pci2phy_map_init(int devid)
-{
-	struct pci_dev *dev = NULL;
-	int bus;
-
-	dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
-	if (!dev)
-		return -ENOTTY;
-
-	bus = dev->bus->number;
-
-	pcibus_to_physid[bus] = 0;
-
-	pci_dev_put(dev);
-
-	return 0;
-}
-
-static struct pmu snb_uncore_imc_pmu = {
-	.task_ctx_nr	= perf_invalid_context,
-	.event_init	= snb_uncore_imc_event_init,
-	.add		= snb_uncore_imc_event_add,
-	.del		= snb_uncore_imc_event_del,
-	.start		= snb_uncore_imc_event_start,
-	.stop		= snb_uncore_imc_event_stop,
-	.read		= uncore_pmu_event_read,
-};
-
-static struct intel_uncore_ops snb_uncore_imc_ops = {
-	.init_box	= snb_uncore_imc_init_box,
-	.enable_box	= snb_uncore_imc_enable_box,
-	.disable_box	= snb_uncore_imc_disable_box,
-	.disable_event	= snb_uncore_imc_disable_event,
-	.enable_event	= snb_uncore_imc_enable_event,
-	.hw_config	= snb_uncore_imc_hw_config,
-	.read_counter	= snb_uncore_imc_read_counter,
-};
-
-static struct intel_uncore_type snb_uncore_imc = {
-	.name		= "imc",
-	.num_counters   = 2,
-	.num_boxes	= 1,
-	.fixed_ctr_bits	= 32,
-	.fixed_ctr	= SNB_UNCORE_PCI_IMC_CTR_BASE,
-	.event_descs	= snb_uncore_imc_events,
-	.format_group	= &snb_uncore_imc_format_group,
-	.perf_ctr	= SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
-	.event_mask	= SNB_UNCORE_PCI_IMC_EVENT_MASK,
-	.ops		= &snb_uncore_imc_ops,
-	.pmu		= &snb_uncore_imc_pmu,
-};
-
-static struct intel_uncore_type *snb_pci_uncores[] = {
-	[SNB_PCI_UNCORE_IMC]	= &snb_uncore_imc,
-	NULL,
-};
-
-static const struct pci_device_id snb_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* end: all zeroes */ },
-};
-
-static const struct pci_device_id ivb_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* end: all zeroes */ },
-};
-
-static const struct pci_device_id hsw_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* end: all zeroes */ },
-};
-
-static struct pci_driver snb_uncore_pci_driver = {
-	.name		= "snb_uncore",
-	.id_table	= snb_uncore_pci_ids,
-};
-
-static struct pci_driver ivb_uncore_pci_driver = {
-	.name		= "ivb_uncore",
-	.id_table	= ivb_uncore_pci_ids,
-};
-
-static struct pci_driver hsw_uncore_pci_driver = {
-	.name		= "hsw_uncore",
-	.id_table	= hsw_uncore_pci_ids,
-};
-
-/* end of Sandy Bridge uncore support */
-
-/* Nehalem uncore support */
-static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
-{
-	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
-}
-
-static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
-{
-	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
-}
-
-static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
-		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
-	else
-		wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
-}
-
-static struct attribute *nhm_uncore_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_cmask8.attr,
-	NULL,
-};
-
-static struct attribute_group nhm_uncore_format_group = {
-	.name = "format",
-	.attrs = nhm_uncore_formats_attr,
-};
-
-static struct uncore_event_desc nhm_uncore_events[] = {
-	INTEL_UNCORE_EVENT_DESC(clockticks,                "event=0xff,umask=0x00"),
-	INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any,       "event=0x2f,umask=0x0f"),
-	INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any,      "event=0x2c,umask=0x0f"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads,     "event=0x20,umask=0x01"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes,    "event=0x20,umask=0x02"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads,  "event=0x20,umask=0x04"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads,   "event=0x20,umask=0x10"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes,  "event=0x20,umask=0x20"),
-	{ /* end: all zeroes */ },
-};
-
-static struct intel_uncore_ops nhm_uncore_msr_ops = {
-	.disable_box	= nhm_uncore_msr_disable_box,
-	.enable_box	= nhm_uncore_msr_enable_box,
-	.disable_event	= snb_uncore_msr_disable_event,
-	.enable_event	= nhm_uncore_msr_enable_event,
-	.read_counter	= uncore_msr_read_counter,
-};
-
-static struct intel_uncore_type nhm_uncore = {
-	.name		= "",
-	.num_counters   = 8,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 48,
-	.fixed_ctr_bits	= 48,
-	.event_ctl	= NHM_UNC_PERFEVTSEL0,
-	.perf_ctr	= NHM_UNC_UNCORE_PMC0,
-	.fixed_ctr	= NHM_UNC_FIXED_CTR,
-	.fixed_ctl	= NHM_UNC_FIXED_CTR_CTRL,
-	.event_mask	= NHM_UNC_RAW_EVENT_MASK,
-	.event_descs	= nhm_uncore_events,
-	.ops		= &nhm_uncore_msr_ops,
-	.format_group	= &nhm_uncore_format_group,
-};
-
-static struct intel_uncore_type *nhm_msr_uncores[] = {
-	&nhm_uncore,
-	NULL,
-};
-/* end of Nehalem uncore support */
-
-/* Nehalem-EX uncore support */
-DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
-DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
-DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
-DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
-
-static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
-{
-	wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
-}
-
-static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
-{
-	unsigned msr = uncore_msr_box_ctl(box);
-	u64 config;
-
-	if (msr) {
-		rdmsrl(msr, config);
-		config &= ~((1ULL << uncore_num_counters(box)) - 1);
-		/* WBox has a fixed counter */
-		if (uncore_msr_fixed_ctl(box))
-			config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN;
-		wrmsrl(msr, config);
-	}
-}
-
-static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box)
-{
-	unsigned msr = uncore_msr_box_ctl(box);
-	u64 config;
-
-	if (msr) {
-		rdmsrl(msr, config);
-		config |= (1ULL << uncore_num_counters(box)) - 1;
-		/* WBox has a fixed counter */
-		if (uncore_msr_fixed_ctl(box))
-			config |= NHMEX_W_PMON_GLOBAL_FIXED_EN;
-		wrmsrl(msr, config);
-	}
-}
-
-static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	wrmsrl(event->hw.config_base, 0);
-}
-
-static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
-		wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
-	else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
-		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
-	else
-		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
-}
-
-#define NHMEX_UNCORE_OPS_COMMON_INIT()				\
-	.init_box	= nhmex_uncore_msr_init_box,		\
-	.disable_box	= nhmex_uncore_msr_disable_box,		\
-	.enable_box	= nhmex_uncore_msr_enable_box,		\
-	.disable_event	= nhmex_uncore_msr_disable_event,	\
-	.read_counter	= uncore_msr_read_counter
-
-static struct intel_uncore_ops nhmex_uncore_ops = {
-	NHMEX_UNCORE_OPS_COMMON_INIT(),
-	.enable_event	= nhmex_uncore_msr_enable_event,
-};
-
-static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_edge.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_ubox_format_group = {
-	.name		= "format",
-	.attrs		= nhmex_uncore_ubox_formats_attr,
-};
-
-static struct intel_uncore_type nhmex_uncore_ubox = {
-	.name		= "ubox",
-	.num_counters	= 1,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 48,
-	.event_ctl	= NHMEX_U_MSR_PMON_EV_SEL,
-	.perf_ctr	= NHMEX_U_MSR_PMON_CTR,
-	.event_mask	= NHMEX_U_PMON_RAW_EVENT_MASK,
-	.box_ctl	= NHMEX_U_MSR_PMON_GLOBAL_CTL,
-	.ops		= &nhmex_uncore_ops,
-	.format_group	= &nhmex_uncore_ubox_format_group
-};
-
-static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_cbox_format_group = {
-	.name = "format",
-	.attrs = nhmex_uncore_cbox_formats_attr,
-};
-
-/* msr offset for each instance of cbox */
-static unsigned nhmex_cbox_msr_offsets[] = {
-	0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0,
-};
-
-static struct intel_uncore_type nhmex_uncore_cbox = {
-	.name			= "cbox",
-	.num_counters		= 6,
-	.num_boxes		= 10,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_C0_MSR_PMON_EV_SEL0,
-	.perf_ctr		= NHMEX_C0_MSR_PMON_CTR0,
-	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_C0_MSR_PMON_GLOBAL_CTL,
-	.msr_offsets		= nhmex_cbox_msr_offsets,
-	.pair_ctr_ctl		= 1,
-	.ops			= &nhmex_uncore_ops,
-	.format_group		= &nhmex_uncore_cbox_format_group
-};
-
-static struct uncore_event_desc nhmex_uncore_wbox_events[] = {
-	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"),
-	{ /* end: all zeroes */ },
-};
-
-static struct intel_uncore_type nhmex_uncore_wbox = {
-	.name			= "wbox",
-	.num_counters		= 4,
-	.num_boxes		= 1,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_W_MSR_PMON_CNT0,
-	.perf_ctr		= NHMEX_W_MSR_PMON_EVT_SEL0,
-	.fixed_ctr		= NHMEX_W_MSR_PMON_FIXED_CTR,
-	.fixed_ctl		= NHMEX_W_MSR_PMON_FIXED_CTL,
-	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_W_MSR_GLOBAL_CTL,
-	.pair_ctr_ctl		= 1,
-	.event_descs		= nhmex_uncore_wbox_events,
-	.ops			= &nhmex_uncore_ops,
-	.format_group		= &nhmex_uncore_cbox_format_group
-};
-
-static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-	int ctr, ev_sel;
-
-	ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >>
-		NHMEX_B_PMON_CTR_SHIFT;
-	ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >>
-		  NHMEX_B_PMON_CTL_EV_SEL_SHIFT;
-
-	/* events that do not use the match/mask registers */
-	if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) ||
-	    (ctr == 2 && ev_sel != 0x4) || ctr == 3)
-		return 0;
-
-	if (box->pmu->pmu_idx == 0)
-		reg1->reg = NHMEX_B0_MSR_MATCH;
-	else
-		reg1->reg = NHMEX_B1_MSR_MATCH;
-	reg1->idx = 0;
-	reg1->config = event->attr.config1;
-	reg2->config = event->attr.config2;
-	return 0;
-}
-
-static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
-	if (reg1->idx != EXTRA_REG_NONE) {
-		wrmsrl(reg1->reg, reg1->config);
-		wrmsrl(reg1->reg + 1, reg2->config);
-	}
-	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
-		(hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK));
-}
-
-/*
- * The Bbox has 4 counters, but each counter monitors different events.
- * Use bits 6-7 in the event config to select counter.
- */
-static struct event_constraint nhmex_uncore_bbox_constraints[] = {
-	EVENT_CONSTRAINT(0 , 1, 0xc0),
-	EVENT_CONSTRAINT(0x40, 2, 0xc0),
-	EVENT_CONSTRAINT(0x80, 4, 0xc0),
-	EVENT_CONSTRAINT(0xc0, 8, 0xc0),
-	EVENT_CONSTRAINT_END,
-};
-
-static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
-	&format_attr_event5.attr,
-	&format_attr_counter.attr,
-	&format_attr_match.attr,
-	&format_attr_mask.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_bbox_format_group = {
-	.name = "format",
-	.attrs = nhmex_uncore_bbox_formats_attr,
-};
-
-static struct intel_uncore_ops nhmex_uncore_bbox_ops = {
-	NHMEX_UNCORE_OPS_COMMON_INIT(),
-	.enable_event		= nhmex_bbox_msr_enable_event,
-	.hw_config		= nhmex_bbox_hw_config,
-	.get_constraint		= uncore_get_constraint,
-	.put_constraint		= uncore_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_bbox = {
-	.name			= "bbox",
-	.num_counters		= 4,
-	.num_boxes		= 2,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_B0_MSR_PMON_CTL0,
-	.perf_ctr		= NHMEX_B0_MSR_PMON_CTR0,
-	.event_mask		= NHMEX_B_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_B0_MSR_PMON_GLOBAL_CTL,
-	.msr_offset		= NHMEX_B_MSR_OFFSET,
-	.pair_ctr_ctl		= 1,
-	.num_shared_regs	= 1,
-	.constraints		= nhmex_uncore_bbox_constraints,
-	.ops			= &nhmex_uncore_bbox_ops,
-	.format_group		= &nhmex_uncore_bbox_format_group
-};
-
-static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
-	/* only TO_R_PROG_EV event uses the match/mask register */
-	if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) !=
-	    NHMEX_S_EVENT_TO_R_PROG_EV)
-		return 0;
-
-	if (box->pmu->pmu_idx == 0)
-		reg1->reg = NHMEX_S0_MSR_MM_CFG;
-	else
-		reg1->reg = NHMEX_S1_MSR_MM_CFG;
-	reg1->idx = 0;
-	reg1->config = event->attr.config1;
-	reg2->config = event->attr.config2;
-	return 0;
-}
-
-static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
-	if (reg1->idx != EXTRA_REG_NONE) {
-		wrmsrl(reg1->reg, 0);
-		wrmsrl(reg1->reg + 1, reg1->config);
-		wrmsrl(reg1->reg + 2, reg2->config);
-		wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
-	}
-	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
-}
-
-static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	&format_attr_match.attr,
-	&format_attr_mask.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_sbox_format_group = {
-	.name			= "format",
-	.attrs			= nhmex_uncore_sbox_formats_attr,
-};
-
-static struct intel_uncore_ops nhmex_uncore_sbox_ops = {
-	NHMEX_UNCORE_OPS_COMMON_INIT(),
-	.enable_event		= nhmex_sbox_msr_enable_event,
-	.hw_config		= nhmex_sbox_hw_config,
-	.get_constraint		= uncore_get_constraint,
-	.put_constraint		= uncore_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_sbox = {
-	.name			= "sbox",
-	.num_counters		= 4,
-	.num_boxes		= 2,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_S0_MSR_PMON_CTL0,
-	.perf_ctr		= NHMEX_S0_MSR_PMON_CTR0,
-	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_S0_MSR_PMON_GLOBAL_CTL,
-	.msr_offset		= NHMEX_S_MSR_OFFSET,
-	.pair_ctr_ctl		= 1,
-	.num_shared_regs	= 1,
-	.ops			= &nhmex_uncore_sbox_ops,
-	.format_group		= &nhmex_uncore_sbox_format_group
-};
-
-enum {
-	EXTRA_REG_NHMEX_M_FILTER,
-	EXTRA_REG_NHMEX_M_DSP,
-	EXTRA_REG_NHMEX_M_ISS,
-	EXTRA_REG_NHMEX_M_MAP,
-	EXTRA_REG_NHMEX_M_MSC_THR,
-	EXTRA_REG_NHMEX_M_PGT,
-	EXTRA_REG_NHMEX_M_PLD,
-	EXTRA_REG_NHMEX_M_ZDP_CTL_FVC,
-};
-
-static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
-	MBOX_INC_SEL_EXTAR_REG(0x0, DSP),
-	MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR),
-	MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR),
-	MBOX_INC_SEL_EXTAR_REG(0x9, ISS),
-	/* event 0xa uses two extra registers */
-	MBOX_INC_SEL_EXTAR_REG(0xa, ISS),
-	MBOX_INC_SEL_EXTAR_REG(0xa, PLD),
-	MBOX_INC_SEL_EXTAR_REG(0xb, PLD),
-	/* events 0xd ~ 0x10 use the same extra register */
-	MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC),
-	MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC),
-	MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC),
-	MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC),
-	MBOX_INC_SEL_EXTAR_REG(0x16, PGT),
-	MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP),
-	MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS),
-	MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT),
-	MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP),
-	EVENT_EXTRA_END
-};
-
-/* Nehalem-EX or Westmere-EX ? */
-static bool uncore_nhmex;
-
-static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
-{
-	struct intel_uncore_extra_reg *er;
-	unsigned long flags;
-	bool ret = false;
-	u64 mask;
-
-	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
-		er = &box->shared_regs[idx];
-		raw_spin_lock_irqsave(&er->lock, flags);
-		if (!atomic_read(&er->ref) || er->config == config) {
-			atomic_inc(&er->ref);
-			er->config = config;
-			ret = true;
-		}
-		raw_spin_unlock_irqrestore(&er->lock, flags);
-
-		return ret;
-	}
-	/*
-	 * The ZDP_CTL_FVC MSR has 4 fields which are used to control
-	 * events 0xd ~ 0x10. Besides these 4 fields, there are additional
-	 * fields which are shared.
-	 */
-	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-	if (WARN_ON_ONCE(idx >= 4))
-		return false;
-
-	/* mask of the shared fields */
-	if (uncore_nhmex)
-		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
-	else
-		mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK;
-	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
-
-	raw_spin_lock_irqsave(&er->lock, flags);
-	/* add mask of the non-shared field if it's in use */
-	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) {
-		if (uncore_nhmex)
-			mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-		else
-			mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-	}
-
-	if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
-		atomic_add(1 << (idx * 8), &er->ref);
-		if (uncore_nhmex)
-			mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
-				NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-		else
-			mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK |
-				WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-		er->config &= ~mask;
-		er->config |= (config & mask);
-		ret = true;
-	}
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-
-	return ret;
-}
-
-static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx)
-{
-	struct intel_uncore_extra_reg *er;
-
-	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
-		er = &box->shared_regs[idx];
-		atomic_dec(&er->ref);
-		return;
-	}
-
-	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
-	atomic_sub(1 << (idx * 8), &er->ref);
-}
-
-static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8);
-	u64 config = reg1->config;
-
-	/* get the non-shared control bits and shift them */
-	idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-	if (uncore_nhmex)
-		config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-	else
-		config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-	if (new_idx > orig_idx) {
-		idx = new_idx - orig_idx;
-		config <<= 3 * idx;
-	} else {
-		idx = orig_idx - new_idx;
-		config >>= 3 * idx;
-	}
-
-	/* add the shared control bits back */
-	if (uncore_nhmex)
-		config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
-	else
-		config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
-	config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
-	if (modify) {
-		/* adjust the main event selector */
-		if (new_idx > orig_idx)
-			hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
-		else
-			hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
-		reg1->config = config;
-		reg1->idx = ~0xff | new_idx;
-	}
-	return config;
-}
-
-static struct event_constraint *
-nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-	int i, idx[2], alloc = 0;
-	u64 config1 = reg1->config;
-
-	idx[0] = __BITS_VALUE(reg1->idx, 0, 8);
-	idx[1] = __BITS_VALUE(reg1->idx, 1, 8);
-again:
-	for (i = 0; i < 2; i++) {
-		if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
-			idx[i] = 0xff;
-
-		if (idx[i] == 0xff)
-			continue;
-
-		if (!nhmex_mbox_get_shared_reg(box, idx[i],
-				__BITS_VALUE(config1, i, 32)))
-			goto fail;
-		alloc |= (0x1 << i);
-	}
-
-	/* for the match/mask registers */
-	if (reg2->idx != EXTRA_REG_NONE &&
-	    (uncore_box_is_fake(box) || !reg2->alloc) &&
-	    !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
-		goto fail;
-
-	/*
-	 * If it's a fake box -- as per validate_{group,event}() we
-	 * shouldn't touch event state and we can avoid doing so
-	 * since both will only call get_event_constraints() once
-	 * on each event, this avoids the need for reg->alloc.
-	 */
-	if (!uncore_box_is_fake(box)) {
-		if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
-			nhmex_mbox_alter_er(event, idx[0], true);
-		reg1->alloc |= alloc;
-		if (reg2->idx != EXTRA_REG_NONE)
-			reg2->alloc = 1;
-	}
-	return NULL;
-fail:
-	if (idx[0] != 0xff && !(alloc & 0x1) &&
-	    idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
-		/*
-		 * events 0xd ~ 0x10 are functional identical, but are
-		 * controlled by different fields in the ZDP_CTL_FVC
-		 * register. If we failed to take one field, try the
-		 * rest 3 choices.
-		 */
-		BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff);
-		idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-		idx[0] = (idx[0] + 1) % 4;
-		idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-		if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) {
-			config1 = nhmex_mbox_alter_er(event, idx[0], false);
-			goto again;
-		}
-	}
-
-	if (alloc & 0x1)
-		nhmex_mbox_put_shared_reg(box, idx[0]);
-	if (alloc & 0x2)
-		nhmex_mbox_put_shared_reg(box, idx[1]);
-	return &constraint_empty;
-}
-
-static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-
-	if (uncore_box_is_fake(box))
-		return;
-
-	if (reg1->alloc & 0x1)
-		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8));
-	if (reg1->alloc & 0x2)
-		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8));
-	reg1->alloc = 0;
-
-	if (reg2->alloc) {
-		nhmex_mbox_put_shared_reg(box, reg2->idx);
-		reg2->alloc = 0;
-	}
-}
-
-static int nhmex_mbox_extra_reg_idx(struct extra_reg *er)
-{
-	if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
-		return er->idx;
-	return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd;
-}
-
-static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct intel_uncore_type *type = box->pmu->type;
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-	struct extra_reg *er;
-	unsigned msr;
-	int reg_idx = 0;
-	/*
-	 * The mbox events may require 2 extra MSRs at the most. But only
-	 * the lower 32 bits in these MSRs are significant, so we can use
-	 * config1 to pass two MSRs' config.
-	 */
-	for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) {
-		if (er->event != (event->hw.config & er->config_mask))
-			continue;
-		if (event->attr.config1 & ~er->valid_mask)
-			return -EINVAL;
-
-		msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
-		if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
-			return -EINVAL;
-
-		/* always use the 32~63 bits to pass the PLD config */
-		if (er->idx == EXTRA_REG_NHMEX_M_PLD)
-			reg_idx = 1;
-		else if (WARN_ON_ONCE(reg_idx > 0))
-			return -EINVAL;
-
-		reg1->idx &= ~(0xff << (reg_idx * 8));
-		reg1->reg &= ~(0xffff << (reg_idx * 16));
-		reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8);
-		reg1->reg |= msr << (reg_idx * 16);
-		reg1->config = event->attr.config1;
-		reg_idx++;
-	}
-	/*
-	 * The mbox only provides ability to perform address matching
-	 * for the PLD events.
-	 */
-	if (reg_idx == 2) {
-		reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
-		if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
-			reg2->config = event->attr.config2;
-		else
-			reg2->config = ~0ULL;
-		if (box->pmu->pmu_idx == 0)
-			reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
-		else
-			reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
-	}
-	return 0;
-}
-
-static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx)
-{
-	struct intel_uncore_extra_reg *er;
-	unsigned long flags;
-	u64 config;
-
-	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
-		return box->shared_regs[idx].config;
-
-	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
-	raw_spin_lock_irqsave(&er->lock, flags);
-	config = er->config;
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-	return config;
-}
-
-static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-	int idx;
-
-	idx = __BITS_VALUE(reg1->idx, 0, 8);
-	if (idx != 0xff)
-		wrmsrl(__BITS_VALUE(reg1->reg, 0, 16),
-			nhmex_mbox_shared_reg_config(box, idx));
-	idx = __BITS_VALUE(reg1->idx, 1, 8);
-	if (idx != 0xff)
-		wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
-			nhmex_mbox_shared_reg_config(box, idx));
-
-	if (reg2->idx != EXTRA_REG_NONE) {
-		wrmsrl(reg2->reg, 0);
-		if (reg2->config != ~0ULL) {
-			wrmsrl(reg2->reg + 1,
-				reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
-			wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
-				(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
-			wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
-		}
-	}
-
-	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
-}
-
-DEFINE_UNCORE_FORMAT_ATTR(count_mode,		count_mode,	"config:2-3");
-DEFINE_UNCORE_FORMAT_ATTR(storage_mode,		storage_mode,	"config:4-5");
-DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,		wrap_mode,	"config:6");
-DEFINE_UNCORE_FORMAT_ATTR(flag_mode,		flag_mode,	"config:7");
-DEFINE_UNCORE_FORMAT_ATTR(inc_sel,		inc_sel,	"config:9-13");
-DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,		set_flag_sel,	"config:19-21");
-DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en,	filter_cfg_en,	"config2:63");
-DEFINE_UNCORE_FORMAT_ATTR(filter_match,		filter_match,	"config2:0-33");
-DEFINE_UNCORE_FORMAT_ATTR(filter_mask,		filter_mask,	"config2:34-61");
-DEFINE_UNCORE_FORMAT_ATTR(dsp,			dsp,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(thr,			thr,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(fvc,			fvc,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pgt,			pgt,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(map,			map,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(iss,			iss,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pld,			pld,		"config1:32-63");
-
-static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
-	&format_attr_count_mode.attr,
-	&format_attr_storage_mode.attr,
-	&format_attr_wrap_mode.attr,
-	&format_attr_flag_mode.attr,
-	&format_attr_inc_sel.attr,
-	&format_attr_set_flag_sel.attr,
-	&format_attr_filter_cfg_en.attr,
-	&format_attr_filter_match.attr,
-	&format_attr_filter_mask.attr,
-	&format_attr_dsp.attr,
-	&format_attr_thr.attr,
-	&format_attr_fvc.attr,
-	&format_attr_pgt.attr,
-	&format_attr_map.attr,
-	&format_attr_iss.attr,
-	&format_attr_pld.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_mbox_format_group = {
-	.name		= "format",
-	.attrs		= nhmex_uncore_mbox_formats_attr,
-};
-
-static struct uncore_event_desc nhmex_uncore_mbox_events[] = {
-	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"),
-	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"),
-	{ /* end: all zeroes */ },
-};
-
-static struct uncore_event_desc wsmex_uncore_mbox_events[] = {
-	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"),
-	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"),
-	{ /* end: all zeroes */ },
-};
-
-static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
-	NHMEX_UNCORE_OPS_COMMON_INIT(),
-	.enable_event	= nhmex_mbox_msr_enable_event,
-	.hw_config	= nhmex_mbox_hw_config,
-	.get_constraint	= nhmex_mbox_get_constraint,
-	.put_constraint	= nhmex_mbox_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_mbox = {
-	.name			= "mbox",
-	.num_counters		= 6,
-	.num_boxes		= 2,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_M0_MSR_PMU_CTL0,
-	.perf_ctr		= NHMEX_M0_MSR_PMU_CNT0,
-	.event_mask		= NHMEX_M_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_M0_MSR_GLOBAL_CTL,
-	.msr_offset		= NHMEX_M_MSR_OFFSET,
-	.pair_ctr_ctl		= 1,
-	.num_shared_regs	= 8,
-	.event_descs		= nhmex_uncore_mbox_events,
-	.ops			= &nhmex_uncore_mbox_ops,
-	.format_group		= &nhmex_uncore_mbox_format_group,
-};
-
-static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-
-	/* adjust the main event selector and extra register index */
-	if (reg1->idx % 2) {
-		reg1->idx--;
-		hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
-	} else {
-		reg1->idx++;
-		hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
-	}
-
-	/* adjust extra register config */
-	switch (reg1->idx % 6) {
-	case 2:
-		/* shift the 8~15 bits to the 0~7 bits */
-		reg1->config >>= 8;
-		break;
-	case 3:
-		/* shift the 0~7 bits to the 8~15 bits */
-		reg1->config <<= 8;
-		break;
-	};
-}
-
-/*
- * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7.
- * An event set consists of 6 events, the 3rd and 4th events in
- * an event set use the same extra register. So an event set uses
- * 5 extra registers.
- */
-static struct event_constraint *
-nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-	struct intel_uncore_extra_reg *er;
-	unsigned long flags;
-	int idx, er_idx;
-	u64 config1;
-	bool ok = false;
-
-	if (!uncore_box_is_fake(box) && reg1->alloc)
-		return NULL;
-
-	idx = reg1->idx % 6;
-	config1 = reg1->config;
-again:
-	er_idx = idx;
-	/* the 3rd and 4th events use the same extra register */
-	if (er_idx > 2)
-		er_idx--;
-	er_idx += (reg1->idx / 6) * 5;
-
-	er = &box->shared_regs[er_idx];
-	raw_spin_lock_irqsave(&er->lock, flags);
-	if (idx < 2) {
-		if (!atomic_read(&er->ref) || er->config == reg1->config) {
-			atomic_inc(&er->ref);
-			er->config = reg1->config;
-			ok = true;
-		}
-	} else if (idx == 2 || idx == 3) {
-		/*
-		 * these two events use different fields in a extra register,
-		 * the 0~7 bits and the 8~15 bits respectively.
-		 */
-		u64 mask = 0xff << ((idx - 2) * 8);
-		if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) ||
-				!((er->config ^ config1) & mask)) {
-			atomic_add(1 << ((idx - 2) * 8), &er->ref);
-			er->config &= ~mask;
-			er->config |= config1 & mask;
-			ok = true;
-		}
-	} else {
-		if (!atomic_read(&er->ref) ||
-				(er->config == (hwc->config >> 32) &&
-				 er->config1 == reg1->config &&
-				 er->config2 == reg2->config)) {
-			atomic_inc(&er->ref);
-			er->config = (hwc->config >> 32);
-			er->config1 = reg1->config;
-			er->config2 = reg2->config;
-			ok = true;
-		}
-	}
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-
-	if (!ok) {
-		/*
-		 * The Rbox events are always in pairs. The paired
-		 * events are functional identical, but use different
-		 * extra registers. If we failed to take an extra
-		 * register, try the alternative.
-		 */
-		idx ^= 1;
-		if (idx != reg1->idx % 6) {
-			if (idx == 2)
-				config1 >>= 8;
-			else if (idx == 3)
-				config1 <<= 8;
-			goto again;
-		}
-	} else {
-		if (!uncore_box_is_fake(box)) {
-			if (idx != reg1->idx % 6)
-				nhmex_rbox_alter_er(box, event);
-			reg1->alloc = 1;
-		}
-		return NULL;
-	}
-	return &constraint_empty;
-}
-
-static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct intel_uncore_extra_reg *er;
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	int idx, er_idx;
-
-	if (uncore_box_is_fake(box) || !reg1->alloc)
-		return;
-
-	idx = reg1->idx % 6;
-	er_idx = idx;
-	if (er_idx > 2)
-		er_idx--;
-	er_idx += (reg1->idx / 6) * 5;
-
-	er = &box->shared_regs[er_idx];
-	if (idx == 2 || idx == 3)
-		atomic_sub(1 << ((idx - 2) * 8), &er->ref);
-	else
-		atomic_dec(&er->ref);
-
-	reg1->alloc = 0;
-}
-
-static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-	int idx;
-
-	idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
-		NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
-	if (idx >= 0x18)
-		return -EINVAL;
-
-	reg1->idx = idx;
-	reg1->config = event->attr.config1;
-
-	switch (idx % 6) {
-	case 4:
-	case 5:
-		hwc->config |= event->attr.config & (~0ULL << 32);
-		reg2->config = event->attr.config2;
-		break;
-	};
-	return 0;
-}
-
-static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-	int idx, port;
-
-	idx = reg1->idx;
-	port = idx / 6 + box->pmu->pmu_idx * 4;
-
-	switch (idx % 6) {
-	case 0:
-		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
-		break;
-	case 1:
-		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
-		break;
-	case 2:
-	case 3:
-		wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
-			uncore_shared_reg_config(box, 2 + (idx / 6) * 5));
-		break;
-	case 4:
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
-			hwc->config >> 32);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
-		break;
-	case 5:
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
-			hwc->config >> 32);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
-		break;
-	};
-
-	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
-		(hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
-}
-
-DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63");
-DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63");
-DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
-DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
-DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
-
-static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
-	&format_attr_event5.attr,
-	&format_attr_xbr_mm_cfg.attr,
-	&format_attr_xbr_match.attr,
-	&format_attr_xbr_mask.attr,
-	&format_attr_qlx_cfg.attr,
-	&format_attr_iperf_cfg.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_rbox_format_group = {
-	.name = "format",
-	.attrs = nhmex_uncore_rbox_formats_attr,
-};
-
-static struct uncore_event_desc nhmex_uncore_rbox_events[] = {
-	INTEL_UNCORE_EVENT_DESC(qpi0_flit_send,		"event=0x0,iperf_cfg=0x80000000"),
-	INTEL_UNCORE_EVENT_DESC(qpi1_filt_send,		"event=0x6,iperf_cfg=0x80000000"),
-	INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt,		"event=0x0,iperf_cfg=0x40000000"),
-	INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt,		"event=0x6,iperf_cfg=0x40000000"),
-	INTEL_UNCORE_EVENT_DESC(qpi0_date_response,	"event=0x0,iperf_cfg=0xc4"),
-	INTEL_UNCORE_EVENT_DESC(qpi1_date_response,	"event=0x6,iperf_cfg=0xc4"),
-	{ /* end: all zeroes */ },
-};
-
-static struct intel_uncore_ops nhmex_uncore_rbox_ops = {
-	NHMEX_UNCORE_OPS_COMMON_INIT(),
-	.enable_event		= nhmex_rbox_msr_enable_event,
-	.hw_config		= nhmex_rbox_hw_config,
-	.get_constraint		= nhmex_rbox_get_constraint,
-	.put_constraint		= nhmex_rbox_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_rbox = {
-	.name			= "rbox",
-	.num_counters		= 8,
-	.num_boxes		= 2,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_R_MSR_PMON_CTL0,
-	.perf_ctr		= NHMEX_R_MSR_PMON_CNT0,
-	.event_mask		= NHMEX_R_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_R_MSR_GLOBAL_CTL,
-	.msr_offset		= NHMEX_R_MSR_OFFSET,
-	.pair_ctr_ctl		= 1,
-	.num_shared_regs	= 20,
-	.event_descs		= nhmex_uncore_rbox_events,
-	.ops			= &nhmex_uncore_rbox_ops,
-	.format_group		= &nhmex_uncore_rbox_format_group
-};
-
-static struct intel_uncore_type *nhmex_msr_uncores[] = {
-	&nhmex_uncore_ubox,
-	&nhmex_uncore_cbox,
-	&nhmex_uncore_bbox,
-	&nhmex_uncore_sbox,
-	&nhmex_uncore_mbox,
-	&nhmex_uncore_rbox,
-	&nhmex_uncore_wbox,
-	NULL,
-};
-/* end of Nehalem-EX uncore support */
-
 static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -3140,7 +170,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_eve
 	hwc->event_base  = uncore_perf_ctr(box, hwc->idx);
 }
 
-static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event)
+void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event)
 {
 	u64 prev_count, new_count, delta;
 	int shift;
@@ -3201,14 +231,14 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
-static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
+void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
 {
 	__hrtimer_start_range_ns(&box->hrtimer,
 			ns_to_ktime(box->hrtimer_duration), 0,
 			HRTIMER_MODE_REL_PINNED, 0);
 }
 
-static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
+void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
 {
 	hrtimer_cancel(&box->hrtimer);
 }
@@ -3291,7 +321,7 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve
 	}
 
 	if (event->attr.config == UNCORE_FIXED_EVENT)
-		return &constraint_fixed;
+		return &uncore_constraint_fixed;
 
 	if (type->constraints) {
 		for_each_event_constraint(c, type->constraints) {
@@ -3496,7 +526,7 @@ static void uncore_pmu_event_del(struct perf_event *event, int flags)
 	event->hw.last_tag = ~0ULL;
 }
 
-static void uncore_pmu_event_read(struct perf_event *event)
+void uncore_pmu_event_read(struct perf_event *event)
 {
 	struct intel_uncore_box *box = uncore_event_to_box(event);
 	uncore_perf_event_update(box, event);
@@ -3635,7 +665,7 @@ static struct attribute_group uncore_pmu_attr_group = {
 	.attrs = uncore_pmu_attrs,
 };
 
-static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu)
+static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 {
 	int ret;
 
@@ -3758,9 +788,6 @@ fail:
 	return ret;
 }
 
-static struct pci_driver *uncore_pci_driver;
-static bool pcidrv_registered;
-
 /*
  * add a pci uncore device
  */
@@ -3770,18 +797,20 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	struct intel_uncore_box *box;
 	struct intel_uncore_type *type;
 	int phys_id;
+	bool first_box = false;
 
-	phys_id = pcibus_to_physid[pdev->bus->number];
+	phys_id = uncore_pcibus_to_physid[pdev->bus->number];
 	if (phys_id < 0)
 		return -ENODEV;
 
 	if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
-		extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev;
+		int idx = UNCORE_PCI_DEV_IDX(id->driver_data);
+		uncore_extra_pci_dev[phys_id][idx] = pdev;
 		pci_set_drvdata(pdev, NULL);
 		return 0;
 	}
 
-	type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
+	type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
 	box = uncore_alloc_box(type, NUMA_NO_NODE);
 	if (!box)
 		return -ENOMEM;
@@ -3803,9 +832,13 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	pci_set_drvdata(pdev, box);
 
 	raw_spin_lock(&uncore_box_lock);
+	if (list_empty(&pmu->box_list))
+		first_box = true;
 	list_add_tail(&box->list, &pmu->box_list);
 	raw_spin_unlock(&uncore_box_lock);
 
+	if (first_box)
+		uncore_pmu_register(pmu);
 	return 0;
 }
 
@@ -3813,13 +846,14 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 {
 	struct intel_uncore_box *box = pci_get_drvdata(pdev);
 	struct intel_uncore_pmu *pmu;
-	int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+	int i, cpu, phys_id = uncore_pcibus_to_physid[pdev->bus->number];
+	bool last_box = false;
 
 	box = pci_get_drvdata(pdev);
 	if (!box) {
 		for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
-			if (extra_pci_dev[phys_id][i] == pdev) {
-				extra_pci_dev[phys_id][i] = NULL;
+			if (uncore_extra_pci_dev[phys_id][i] == pdev) {
+				uncore_extra_pci_dev[phys_id][i] = NULL;
 				break;
 			}
 		}
@@ -3835,6 +869,8 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 
 	raw_spin_lock(&uncore_box_lock);
 	list_del(&box->list);
+	if (list_empty(&pmu->box_list))
+		last_box = true;
 	raw_spin_unlock(&uncore_box_lock);
 
 	for_each_possible_cpu(cpu) {
@@ -3846,6 +882,9 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 
 	WARN_ON_ONCE(atomic_read(&box->refcnt) != 1);
 	kfree(box);
+
+	if (last_box)
+		perf_pmu_unregister(&pmu->pmu);
 }
 
 static int __init uncore_pci_init(void)
@@ -3854,46 +893,32 @@ static int __init uncore_pci_init(void)
 
 	switch (boot_cpu_data.x86_model) {
 	case 45: /* Sandy Bridge-EP */
-		ret = snbep_pci2phy_map_init(0x3ce0);
-		if (ret)
-			return ret;
-		pci_uncores = snbep_pci_uncores;
-		uncore_pci_driver = &snbep_uncore_pci_driver;
+		ret = snbep_uncore_pci_init();
 		break;
-	case 62: /* IvyTown */
-		ret = snbep_pci2phy_map_init(0x0e1e);
-		if (ret)
-			return ret;
-		pci_uncores = ivt_pci_uncores;
-		uncore_pci_driver = &ivt_uncore_pci_driver;
+	case 62: /* Ivy Bridge-EP */
+		ret = ivbep_uncore_pci_init();
+		break;
+	case 63: /* Haswell-EP */
+		ret = hswep_uncore_pci_init();
 		break;
 	case 42: /* Sandy Bridge */
-		ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC);
-		if (ret)
-			return ret;
-		pci_uncores = snb_pci_uncores;
-		uncore_pci_driver = &snb_uncore_pci_driver;
+		ret = snb_uncore_pci_init();
 		break;
 	case 58: /* Ivy Bridge */
-		ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC);
-		if (ret)
-			return ret;
-		pci_uncores = snb_pci_uncores;
-		uncore_pci_driver = &ivb_uncore_pci_driver;
+		ret = ivb_uncore_pci_init();
 		break;
 	case 60: /* Haswell */
 	case 69: /* Haswell Celeron */
-		ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC);
-		if (ret)
-			return ret;
-		pci_uncores = snb_pci_uncores;
-		uncore_pci_driver = &hsw_uncore_pci_driver;
+		ret = hsw_uncore_pci_init();
 		break;
 	default:
 		return 0;
 	}
 
-	ret = uncore_types_init(pci_uncores);
+	if (ret)
+		return ret;
+
+	ret = uncore_types_init(uncore_pci_uncores);
 	if (ret)
 		return ret;
 
@@ -3904,7 +929,7 @@ static int __init uncore_pci_init(void)
 	if (ret == 0)
 		pcidrv_registered = true;
 	else
-		uncore_types_exit(pci_uncores);
+		uncore_types_exit(uncore_pci_uncores);
 
 	return ret;
 }
@@ -3914,7 +939,7 @@ static void __init uncore_pci_exit(void)
 	if (pcidrv_registered) {
 		pcidrv_registered = false;
 		pci_unregister_driver(uncore_pci_driver);
-		uncore_types_exit(pci_uncores);
+		uncore_types_exit(uncore_pci_uncores);
 	}
 }
 
@@ -3940,8 +965,8 @@ static void uncore_cpu_dying(int cpu)
 	struct intel_uncore_box *box;
 	int i, j;
 
-	for (i = 0; msr_uncores[i]; i++) {
-		type = msr_uncores[i];
+	for (i = 0; uncore_msr_uncores[i]; i++) {
+		type = uncore_msr_uncores[i];
 		for (j = 0; j < type->num_boxes; j++) {
 			pmu = &type->pmus[j];
 			box = *per_cpu_ptr(pmu->box, cpu);
@@ -3961,8 +986,8 @@ static int uncore_cpu_starting(int cpu)
 
 	phys_id = topology_physical_package_id(cpu);
 
-	for (i = 0; msr_uncores[i]; i++) {
-		type = msr_uncores[i];
+	for (i = 0; uncore_msr_uncores[i]; i++) {
+		type = uncore_msr_uncores[i];
 		for (j = 0; j < type->num_boxes; j++) {
 			pmu = &type->pmus[j];
 			box = *per_cpu_ptr(pmu->box, cpu);
@@ -4002,8 +1027,8 @@ static int uncore_cpu_prepare(int cpu, int phys_id)
 	struct intel_uncore_box *box;
 	int i, j;
 
-	for (i = 0; msr_uncores[i]; i++) {
-		type = msr_uncores[i];
+	for (i = 0; uncore_msr_uncores[i]; i++) {
+		type = uncore_msr_uncores[i];
 		for (j = 0; j < type->num_boxes; j++) {
 			pmu = &type->pmus[j];
 			if (pmu->func_id < 0)
@@ -4083,8 +1108,8 @@ static void uncore_event_exit_cpu(int cpu)
 	if (target >= 0)
 		cpumask_set_cpu(target, &uncore_cpu_mask);
 
-	uncore_change_context(msr_uncores, cpu, target);
-	uncore_change_context(pci_uncores, cpu, target);
+	uncore_change_context(uncore_msr_uncores, cpu, target);
+	uncore_change_context(uncore_pci_uncores, cpu, target);
 }
 
 static void uncore_event_init_cpu(int cpu)
@@ -4099,8 +1124,8 @@ static void uncore_event_init_cpu(int cpu)
 
 	cpumask_set_cpu(cpu, &uncore_cpu_mask);
 
-	uncore_change_context(msr_uncores, -1, cpu);
-	uncore_change_context(pci_uncores, -1, cpu);
+	uncore_change_context(uncore_msr_uncores, -1, cpu);
+	uncore_change_context(uncore_pci_uncores, -1, cpu);
 }
 
 static int uncore_cpu_notifier(struct notifier_block *self,
@@ -4160,47 +1185,37 @@ static void __init uncore_cpu_setup(void *dummy)
 
 static int __init uncore_cpu_init(void)
 {
-	int ret, max_cores;
+	int ret;
 
-	max_cores = boot_cpu_data.x86_max_cores;
 	switch (boot_cpu_data.x86_model) {
 	case 26: /* Nehalem */
 	case 30:
 	case 37: /* Westmere */
 	case 44:
-		msr_uncores = nhm_msr_uncores;
+		nhm_uncore_cpu_init();
 		break;
 	case 42: /* Sandy Bridge */
 	case 58: /* Ivy Bridge */
-		if (snb_uncore_cbox.num_boxes > max_cores)
-			snb_uncore_cbox.num_boxes = max_cores;
-		msr_uncores = snb_msr_uncores;
+		snb_uncore_cpu_init();
 		break;
 	case 45: /* Sandy Bridge-EP */
-		if (snbep_uncore_cbox.num_boxes > max_cores)
-			snbep_uncore_cbox.num_boxes = max_cores;
-		msr_uncores = snbep_msr_uncores;
+		snbep_uncore_cpu_init();
 		break;
 	case 46: /* Nehalem-EX */
-		uncore_nhmex = true;
 	case 47: /* Westmere-EX aka. Xeon E7 */
-		if (!uncore_nhmex)
-			nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
-		if (nhmex_uncore_cbox.num_boxes > max_cores)
-			nhmex_uncore_cbox.num_boxes = max_cores;
-		msr_uncores = nhmex_msr_uncores;
+		nhmex_uncore_cpu_init();
 		break;
-	case 62: /* IvyTown */
-		if (ivt_uncore_cbox.num_boxes > max_cores)
-			ivt_uncore_cbox.num_boxes = max_cores;
-		msr_uncores = ivt_msr_uncores;
+	case 62: /* Ivy Bridge-EP */
+		ivbep_uncore_cpu_init();
+		break;
+	case 63: /* Haswell-EP */
+		hswep_uncore_cpu_init();
 		break;
-
 	default:
 		return 0;
 	}
 
-	ret = uncore_types_init(msr_uncores);
+	ret = uncore_types_init(uncore_msr_uncores);
 	if (ret)
 		return ret;
 
@@ -4213,16 +1228,8 @@ static int __init uncore_pmus_register(void)
 	struct intel_uncore_type *type;
 	int i, j;
 
-	for (i = 0; msr_uncores[i]; i++) {
-		type = msr_uncores[i];
-		for (j = 0; j < type->num_boxes; j++) {
-			pmu = &type->pmus[j];
-			uncore_pmu_register(pmu);
-		}
-	}
-
-	for (i = 0; pci_uncores[i]; i++) {
-		type = pci_uncores[i];
+	for (i = 0; uncore_msr_uncores[i]; i++) {
+		type = uncore_msr_uncores[i];
 		for (j = 0; j < type->num_boxes; j++) {
 			pmu = &type->pmus[j];
 			uncore_pmu_register(pmu);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 90236f0c94a9..18eb78bbdd10 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -24,395 +24,6 @@
 
 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
 
-/* SNB event control */
-#define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
-#define SNB_UNC_CTL_UMASK_MASK			0x0000ff00
-#define SNB_UNC_CTL_EDGE_DET			(1 << 18)
-#define SNB_UNC_CTL_EN				(1 << 22)
-#define SNB_UNC_CTL_INVERT			(1 << 23)
-#define SNB_UNC_CTL_CMASK_MASK			0x1f000000
-#define NHM_UNC_CTL_CMASK_MASK			0xff000000
-#define NHM_UNC_FIXED_CTR_CTL_EN		(1 << 0)
-
-#define SNB_UNC_RAW_EVENT_MASK			(SNB_UNC_CTL_EV_SEL_MASK | \
-						 SNB_UNC_CTL_UMASK_MASK | \
-						 SNB_UNC_CTL_EDGE_DET | \
-						 SNB_UNC_CTL_INVERT | \
-						 SNB_UNC_CTL_CMASK_MASK)
-
-#define NHM_UNC_RAW_EVENT_MASK			(SNB_UNC_CTL_EV_SEL_MASK | \
-						 SNB_UNC_CTL_UMASK_MASK | \
-						 SNB_UNC_CTL_EDGE_DET | \
-						 SNB_UNC_CTL_INVERT | \
-						 NHM_UNC_CTL_CMASK_MASK)
-
-/* SNB global control register */
-#define SNB_UNC_PERF_GLOBAL_CTL                 0x391
-#define SNB_UNC_FIXED_CTR_CTRL                  0x394
-#define SNB_UNC_FIXED_CTR                       0x395
-
-/* SNB uncore global control */
-#define SNB_UNC_GLOBAL_CTL_CORE_ALL             ((1 << 4) - 1)
-#define SNB_UNC_GLOBAL_CTL_EN                   (1 << 29)
-
-/* SNB Cbo register */
-#define SNB_UNC_CBO_0_PERFEVTSEL0               0x700
-#define SNB_UNC_CBO_0_PER_CTR0                  0x706
-#define SNB_UNC_CBO_MSR_OFFSET                  0x10
-
-/* NHM global control register */
-#define NHM_UNC_PERF_GLOBAL_CTL                 0x391
-#define NHM_UNC_FIXED_CTR                       0x394
-#define NHM_UNC_FIXED_CTR_CTRL                  0x395
-
-/* NHM uncore global control */
-#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL            ((1ULL << 8) - 1)
-#define NHM_UNC_GLOBAL_CTL_EN_FC                (1ULL << 32)
-
-/* NHM uncore register */
-#define NHM_UNC_PERFEVTSEL0                     0x3c0
-#define NHM_UNC_UNCORE_PMC0                     0x3b0
-
-/* SNB-EP Box level control */
-#define SNBEP_PMON_BOX_CTL_RST_CTRL	(1 << 0)
-#define SNBEP_PMON_BOX_CTL_RST_CTRS	(1 << 1)
-#define SNBEP_PMON_BOX_CTL_FRZ		(1 << 8)
-#define SNBEP_PMON_BOX_CTL_FRZ_EN	(1 << 16)
-#define SNBEP_PMON_BOX_CTL_INT		(SNBEP_PMON_BOX_CTL_RST_CTRL | \
-					 SNBEP_PMON_BOX_CTL_RST_CTRS | \
-					 SNBEP_PMON_BOX_CTL_FRZ_EN)
-/* SNB-EP event control */
-#define SNBEP_PMON_CTL_EV_SEL_MASK	0x000000ff
-#define SNBEP_PMON_CTL_UMASK_MASK	0x0000ff00
-#define SNBEP_PMON_CTL_RST		(1 << 17)
-#define SNBEP_PMON_CTL_EDGE_DET		(1 << 18)
-#define SNBEP_PMON_CTL_EV_SEL_EXT	(1 << 21)
-#define SNBEP_PMON_CTL_EN		(1 << 22)
-#define SNBEP_PMON_CTL_INVERT		(1 << 23)
-#define SNBEP_PMON_CTL_TRESH_MASK	0xff000000
-#define SNBEP_PMON_RAW_EVENT_MASK	(SNBEP_PMON_CTL_EV_SEL_MASK | \
-					 SNBEP_PMON_CTL_UMASK_MASK | \
-					 SNBEP_PMON_CTL_EDGE_DET | \
-					 SNBEP_PMON_CTL_INVERT | \
-					 SNBEP_PMON_CTL_TRESH_MASK)
-
-/* SNB-EP Ubox event control */
-#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK		0x1f000000
-#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK		\
-				(SNBEP_PMON_CTL_EV_SEL_MASK | \
-				 SNBEP_PMON_CTL_UMASK_MASK | \
-				 SNBEP_PMON_CTL_EDGE_DET | \
-				 SNBEP_PMON_CTL_INVERT | \
-				 SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
-
-#define SNBEP_CBO_PMON_CTL_TID_EN		(1 << 19)
-#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK	(SNBEP_PMON_RAW_EVENT_MASK | \
-						 SNBEP_CBO_PMON_CTL_TID_EN)
-
-/* SNB-EP PCU event control */
-#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK	0x0000c000
-#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK	0x1f000000
-#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT	(1 << 30)
-#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET	(1 << 31)
-#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK	\
-				(SNBEP_PMON_CTL_EV_SEL_MASK | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
-				 SNBEP_PMON_CTL_EDGE_DET | \
-				 SNBEP_PMON_CTL_EV_SEL_EXT | \
-				 SNBEP_PMON_CTL_INVERT | \
-				 SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
-
-#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK	\
-				(SNBEP_PMON_RAW_EVENT_MASK | \
-				 SNBEP_PMON_CTL_EV_SEL_EXT)
-
-/* SNB-EP pci control register */
-#define SNBEP_PCI_PMON_BOX_CTL			0xf4
-#define SNBEP_PCI_PMON_CTL0			0xd8
-/* SNB-EP pci counter register */
-#define SNBEP_PCI_PMON_CTR0			0xa0
-
-/* SNB-EP home agent register */
-#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0	0x40
-#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1	0x44
-#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH	0x48
-/* SNB-EP memory controller register */
-#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL		0xf0
-#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR		0xd0
-/* SNB-EP QPI register */
-#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0		0x228
-#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1		0x22c
-#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0		0x238
-#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1		0x23c
-
-/* SNB-EP Ubox register */
-#define SNBEP_U_MSR_PMON_CTR0			0xc16
-#define SNBEP_U_MSR_PMON_CTL0			0xc10
-
-#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL		0xc08
-#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR		0xc09
-
-/* SNB-EP Cbo register */
-#define SNBEP_C0_MSR_PMON_CTR0			0xd16
-#define SNBEP_C0_MSR_PMON_CTL0			0xd10
-#define SNBEP_C0_MSR_PMON_BOX_CTL		0xd04
-#define SNBEP_C0_MSR_PMON_BOX_FILTER		0xd14
-#define SNBEP_CBO_MSR_OFFSET			0x20
-
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID	0x1f
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID	0x3fc00
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE	0x7c0000
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC	0xff800000
-
-#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) {	\
-	.event = (e),				\
-	.msr = SNBEP_C0_MSR_PMON_BOX_FILTER,	\
-	.config_mask = (m),			\
-	.idx = (i)				\
-}
-
-/* SNB-EP PCU register */
-#define SNBEP_PCU_MSR_PMON_CTR0			0xc36
-#define SNBEP_PCU_MSR_PMON_CTL0			0xc30
-#define SNBEP_PCU_MSR_PMON_BOX_CTL		0xc24
-#define SNBEP_PCU_MSR_PMON_BOX_FILTER		0xc34
-#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK	0xffffffff
-#define SNBEP_PCU_MSR_CORE_C3_CTR		0x3fc
-#define SNBEP_PCU_MSR_CORE_C6_CTR		0x3fd
-
-/* IVT event control */
-#define IVT_PMON_BOX_CTL_INT		(SNBEP_PMON_BOX_CTL_RST_CTRL | \
-					 SNBEP_PMON_BOX_CTL_RST_CTRS)
-#define IVT_PMON_RAW_EVENT_MASK		(SNBEP_PMON_CTL_EV_SEL_MASK | \
-					 SNBEP_PMON_CTL_UMASK_MASK | \
-					 SNBEP_PMON_CTL_EDGE_DET | \
-					 SNBEP_PMON_CTL_TRESH_MASK)
-/* IVT Ubox */
-#define IVT_U_MSR_PMON_GLOBAL_CTL		0xc00
-#define IVT_U_PMON_GLOBAL_FRZ_ALL		(1 << 31)
-#define IVT_U_PMON_GLOBAL_UNFRZ_ALL		(1 << 29)
-
-#define IVT_U_MSR_PMON_RAW_EVENT_MASK	\
-				(SNBEP_PMON_CTL_EV_SEL_MASK | \
-				 SNBEP_PMON_CTL_UMASK_MASK | \
-				 SNBEP_PMON_CTL_EDGE_DET | \
-				 SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
-/* IVT Cbo */
-#define IVT_CBO_MSR_PMON_RAW_EVENT_MASK		(IVT_PMON_RAW_EVENT_MASK | \
-						 SNBEP_CBO_PMON_CTL_TID_EN)
-
-#define IVT_CB0_MSR_PMON_BOX_FILTER_TID		(0x1fULL << 0)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_LINK	(0xfULL << 5)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_STATE	(0x3fULL << 17)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_NID		(0xffffULL << 32)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_OPC		(0x1ffULL << 52)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_C6		(0x1ULL << 61)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_NC		(0x1ULL << 62)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_IOSC	(0x1ULL << 63)
-
-/* IVT home agent */
-#define IVT_HA_PCI_PMON_CTL_Q_OCC_RST		(1 << 16)
-#define IVT_HA_PCI_PMON_RAW_EVENT_MASK		\
-				(IVT_PMON_RAW_EVENT_MASK | \
-				 IVT_HA_PCI_PMON_CTL_Q_OCC_RST)
-/* IVT PCU */
-#define IVT_PCU_MSR_PMON_RAW_EVENT_MASK	\
-				(SNBEP_PMON_CTL_EV_SEL_MASK | \
-				 SNBEP_PMON_CTL_EV_SEL_EXT | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
-				 SNBEP_PMON_CTL_EDGE_DET | \
-				 SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
-/* IVT QPI */
-#define IVT_QPI_PCI_PMON_RAW_EVENT_MASK	\
-				(IVT_PMON_RAW_EVENT_MASK | \
-				 SNBEP_PMON_CTL_EV_SEL_EXT)
-
-/* NHM-EX event control */
-#define NHMEX_PMON_CTL_EV_SEL_MASK	0x000000ff
-#define NHMEX_PMON_CTL_UMASK_MASK	0x0000ff00
-#define NHMEX_PMON_CTL_EN_BIT0		(1 << 0)
-#define NHMEX_PMON_CTL_EDGE_DET		(1 << 18)
-#define NHMEX_PMON_CTL_PMI_EN		(1 << 20)
-#define NHMEX_PMON_CTL_EN_BIT22		(1 << 22)
-#define NHMEX_PMON_CTL_INVERT		(1 << 23)
-#define NHMEX_PMON_CTL_TRESH_MASK	0xff000000
-#define NHMEX_PMON_RAW_EVENT_MASK	(NHMEX_PMON_CTL_EV_SEL_MASK | \
-					 NHMEX_PMON_CTL_UMASK_MASK | \
-					 NHMEX_PMON_CTL_EDGE_DET | \
-					 NHMEX_PMON_CTL_INVERT | \
-					 NHMEX_PMON_CTL_TRESH_MASK)
-
-/* NHM-EX Ubox */
-#define NHMEX_U_MSR_PMON_GLOBAL_CTL		0xc00
-#define NHMEX_U_MSR_PMON_CTR			0xc11
-#define NHMEX_U_MSR_PMON_EV_SEL			0xc10
-
-#define NHMEX_U_PMON_GLOBAL_EN			(1 << 0)
-#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL	0x0000001e
-#define NHMEX_U_PMON_GLOBAL_EN_ALL		(1 << 28)
-#define NHMEX_U_PMON_GLOBAL_RST_ALL		(1 << 29)
-#define NHMEX_U_PMON_GLOBAL_FRZ_ALL		(1 << 31)
-
-#define NHMEX_U_PMON_RAW_EVENT_MASK		\
-		(NHMEX_PMON_CTL_EV_SEL_MASK |	\
-		 NHMEX_PMON_CTL_EDGE_DET)
-
-/* NHM-EX Cbox */
-#define NHMEX_C0_MSR_PMON_GLOBAL_CTL		0xd00
-#define NHMEX_C0_MSR_PMON_CTR0			0xd11
-#define NHMEX_C0_MSR_PMON_EV_SEL0		0xd10
-#define NHMEX_C_MSR_OFFSET			0x20
-
-/* NHM-EX Bbox */
-#define NHMEX_B0_MSR_PMON_GLOBAL_CTL		0xc20
-#define NHMEX_B0_MSR_PMON_CTR0			0xc31
-#define NHMEX_B0_MSR_PMON_CTL0			0xc30
-#define NHMEX_B_MSR_OFFSET			0x40
-#define NHMEX_B0_MSR_MATCH			0xe45
-#define NHMEX_B0_MSR_MASK			0xe46
-#define NHMEX_B1_MSR_MATCH			0xe4d
-#define NHMEX_B1_MSR_MASK			0xe4e
-
-#define NHMEX_B_PMON_CTL_EN			(1 << 0)
-#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT		1
-#define NHMEX_B_PMON_CTL_EV_SEL_MASK		\
-		(0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT)
-#define NHMEX_B_PMON_CTR_SHIFT		6
-#define NHMEX_B_PMON_CTR_MASK		\
-		(0x3 << NHMEX_B_PMON_CTR_SHIFT)
-#define NHMEX_B_PMON_RAW_EVENT_MASK		\
-		(NHMEX_B_PMON_CTL_EV_SEL_MASK | \
-		 NHMEX_B_PMON_CTR_MASK)
-
-/* NHM-EX Sbox */
-#define NHMEX_S0_MSR_PMON_GLOBAL_CTL		0xc40
-#define NHMEX_S0_MSR_PMON_CTR0			0xc51
-#define NHMEX_S0_MSR_PMON_CTL0			0xc50
-#define NHMEX_S_MSR_OFFSET			0x80
-#define NHMEX_S0_MSR_MM_CFG			0xe48
-#define NHMEX_S0_MSR_MATCH			0xe49
-#define NHMEX_S0_MSR_MASK			0xe4a
-#define NHMEX_S1_MSR_MM_CFG			0xe58
-#define NHMEX_S1_MSR_MATCH			0xe59
-#define NHMEX_S1_MSR_MASK			0xe5a
-
-#define NHMEX_S_PMON_MM_CFG_EN			(0x1ULL << 63)
-#define NHMEX_S_EVENT_TO_R_PROG_EV		0
-
-/* NHM-EX Mbox */
-#define NHMEX_M0_MSR_GLOBAL_CTL			0xca0
-#define NHMEX_M0_MSR_PMU_DSP			0xca5
-#define NHMEX_M0_MSR_PMU_ISS			0xca6
-#define NHMEX_M0_MSR_PMU_MAP			0xca7
-#define NHMEX_M0_MSR_PMU_MSC_THR		0xca8
-#define NHMEX_M0_MSR_PMU_PGT			0xca9
-#define NHMEX_M0_MSR_PMU_PLD			0xcaa
-#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC		0xcab
-#define NHMEX_M0_MSR_PMU_CTL0			0xcb0
-#define NHMEX_M0_MSR_PMU_CNT0			0xcb1
-#define NHMEX_M_MSR_OFFSET			0x40
-#define NHMEX_M0_MSR_PMU_MM_CFG			0xe54
-#define NHMEX_M1_MSR_PMU_MM_CFG			0xe5c
-
-#define NHMEX_M_PMON_MM_CFG_EN			(1ULL << 63)
-#define NHMEX_M_PMON_ADDR_MATCH_MASK		0x3ffffffffULL
-#define NHMEX_M_PMON_ADDR_MASK_MASK		0x7ffffffULL
-#define NHMEX_M_PMON_ADDR_MASK_SHIFT		34
-
-#define NHMEX_M_PMON_CTL_EN			(1 << 0)
-#define NHMEX_M_PMON_CTL_PMI_EN			(1 << 1)
-#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT	2
-#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK	\
-	(0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT)
-#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT	4
-#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK	\
-	(0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT)
-#define NHMEX_M_PMON_CTL_WRAP_MODE		(1 << 6)
-#define NHMEX_M_PMON_CTL_FLAG_MODE		(1 << 7)
-#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT		9
-#define NHMEX_M_PMON_CTL_INC_SEL_MASK		\
-	(0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
-#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT	19
-#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK	\
-	(0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT)
-#define NHMEX_M_PMON_RAW_EVENT_MASK			\
-		(NHMEX_M_PMON_CTL_COUNT_MODE_MASK |	\
-		 NHMEX_M_PMON_CTL_STORAGE_MODE_MASK |	\
-		 NHMEX_M_PMON_CTL_WRAP_MODE |		\
-		 NHMEX_M_PMON_CTL_FLAG_MODE |		\
-		 NHMEX_M_PMON_CTL_INC_SEL_MASK |	\
-		 NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
-
-#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 11) - 1) | (1 << 23))
-#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7ULL << (11 + 3 * (n)))
-
-#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 12) - 1) | (1 << 24))
-#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7ULL << (12 + 3 * (n)))
-
-/*
- * use the 9~13 bits to select event If the 7th bit is not set,
- * otherwise use the 19~21 bits to select event.
- */
-#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
-#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \
-				NHMEX_M_PMON_CTL_FLAG_MODE)
-#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \
-			   NHMEX_M_PMON_CTL_FLAG_MODE)
-#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \
-				NHMEX_M_PMON_CTL_FLAG_MODE)
-#define MBOX_INC_SEL_EXTAR_REG(c, r) \
-		EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \
-				MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r)
-#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \
-		EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \
-				MBOX_SET_FLAG_SEL_MASK, \
-				(u64)-1, NHMEX_M_##r)
-
-/* NHM-EX Rbox */
-#define NHMEX_R_MSR_GLOBAL_CTL			0xe00
-#define NHMEX_R_MSR_PMON_CTL0			0xe10
-#define NHMEX_R_MSR_PMON_CNT0			0xe11
-#define NHMEX_R_MSR_OFFSET			0x20
-
-#define NHMEX_R_MSR_PORTN_QLX_CFG(n)		\
-		((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4))
-#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n)		(0xe04 + (n))
-#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n)		(0xe24 + (n))
-#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n)		\
-		(((n) < 4 ? 0 : 0x10) + (n) * 4)
-#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n)	\
-		(0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
-#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n)	\
-		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1)
-#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n)	\
-		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2)
-#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n)	\
-		(0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
-#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n)	\
-		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1)
-#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n)	\
-		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2)
-
-#define NHMEX_R_PMON_CTL_EN			(1 << 0)
-#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT		1
-#define NHMEX_R_PMON_CTL_EV_SEL_MASK		\
-		(0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT)
-#define NHMEX_R_PMON_CTL_PMI_EN			(1 << 6)
-#define NHMEX_R_PMON_RAW_EVENT_MASK		NHMEX_R_PMON_CTL_EV_SEL_MASK
-
-/* NHM-EX Wbox */
-#define NHMEX_W_MSR_GLOBAL_CTL			0xc80
-#define NHMEX_W_MSR_PMON_CNT0			0xc90
-#define NHMEX_W_MSR_PMON_EVT_SEL0		0xc91
-#define NHMEX_W_MSR_PMON_FIXED_CTR		0x394
-#define NHMEX_W_MSR_PMON_FIXED_CTL		0x395
-
-#define NHMEX_W_PMON_GLOBAL_FIXED_EN		(1ULL << 31)
-
 struct intel_uncore_ops;
 struct intel_uncore_pmu;
 struct intel_uncore_box;
@@ -505,6 +116,9 @@ struct uncore_event_desc {
 	const char *config;
 };
 
+ssize_t uncore_event_show(struct kobject *kobj,
+			  struct kobj_attribute *attr, char *buf);
+
 #define INTEL_UNCORE_EVENT_DESC(_name, _config)			\
 {								\
 	.attr	= __ATTR(_name, 0444, uncore_event_show, NULL),	\
@@ -522,15 +136,6 @@ static ssize_t __uncore_##_var##_show(struct kobject *kobj,		\
 static struct kobj_attribute format_attr_##_var =			\
 	__ATTR(_name, 0444, __uncore_##_var##_show, NULL)
 
-
-static ssize_t uncore_event_show(struct kobject *kobj,
-				struct kobj_attribute *attr, char *buf)
-{
-	struct uncore_event_desc *event =
-		container_of(attr, struct uncore_event_desc, attr);
-	return sprintf(buf, "%s", event->config);
-}
-
 static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
 {
 	return box->pmu->type->box_ctl;
@@ -694,3 +299,41 @@ static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
 {
 	return (box->phys_id < 0);
 }
+
+struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event);
+struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu);
+struct intel_uncore_box *uncore_event_to_box(struct perf_event *event);
+u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
+void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
+void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
+void uncore_pmu_event_read(struct perf_event *event);
+void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
+struct event_constraint *
+uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event);
+void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event);
+u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx);
+
+extern struct intel_uncore_type **uncore_msr_uncores;
+extern struct intel_uncore_type **uncore_pci_uncores;
+extern struct pci_driver *uncore_pci_driver;
+extern int uncore_pcibus_to_physid[256];
+extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+extern struct event_constraint uncore_constraint_empty;
+
+/* perf_event_intel_uncore_snb.c */
+int snb_uncore_pci_init(void);
+int ivb_uncore_pci_init(void);
+int hsw_uncore_pci_init(void);
+void snb_uncore_cpu_init(void);
+void nhm_uncore_cpu_init(void);
+
+/* perf_event_intel_uncore_snbep.c */
+int snbep_uncore_pci_init(void);
+void snbep_uncore_cpu_init(void);
+int ivbep_uncore_pci_init(void);
+void ivbep_uncore_cpu_init(void);
+int hswep_uncore_pci_init(void);
+void hswep_uncore_cpu_init(void);
+
+/* perf_event_intel_uncore_nhmex.c */
+void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c
new file mode 100644
index 000000000000..2749965afed0
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c
@@ -0,0 +1,1221 @@
+/* Nehalem-EX/Westmere-EX uncore support */
+#include "perf_event_intel_uncore.h"
+
+/* NHM-EX event control */
+#define NHMEX_PMON_CTL_EV_SEL_MASK	0x000000ff
+#define NHMEX_PMON_CTL_UMASK_MASK	0x0000ff00
+#define NHMEX_PMON_CTL_EN_BIT0		(1 << 0)
+#define NHMEX_PMON_CTL_EDGE_DET		(1 << 18)
+#define NHMEX_PMON_CTL_PMI_EN		(1 << 20)
+#define NHMEX_PMON_CTL_EN_BIT22		(1 << 22)
+#define NHMEX_PMON_CTL_INVERT		(1 << 23)
+#define NHMEX_PMON_CTL_TRESH_MASK	0xff000000
+#define NHMEX_PMON_RAW_EVENT_MASK	(NHMEX_PMON_CTL_EV_SEL_MASK | \
+					 NHMEX_PMON_CTL_UMASK_MASK | \
+					 NHMEX_PMON_CTL_EDGE_DET | \
+					 NHMEX_PMON_CTL_INVERT | \
+					 NHMEX_PMON_CTL_TRESH_MASK)
+
+/* NHM-EX Ubox */
+#define NHMEX_U_MSR_PMON_GLOBAL_CTL		0xc00
+#define NHMEX_U_MSR_PMON_CTR			0xc11
+#define NHMEX_U_MSR_PMON_EV_SEL			0xc10
+
+#define NHMEX_U_PMON_GLOBAL_EN			(1 << 0)
+#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL	0x0000001e
+#define NHMEX_U_PMON_GLOBAL_EN_ALL		(1 << 28)
+#define NHMEX_U_PMON_GLOBAL_RST_ALL		(1 << 29)
+#define NHMEX_U_PMON_GLOBAL_FRZ_ALL		(1 << 31)
+
+#define NHMEX_U_PMON_RAW_EVENT_MASK		\
+		(NHMEX_PMON_CTL_EV_SEL_MASK |	\
+		 NHMEX_PMON_CTL_EDGE_DET)
+
+/* NHM-EX Cbox */
+#define NHMEX_C0_MSR_PMON_GLOBAL_CTL		0xd00
+#define NHMEX_C0_MSR_PMON_CTR0			0xd11
+#define NHMEX_C0_MSR_PMON_EV_SEL0		0xd10
+#define NHMEX_C_MSR_OFFSET			0x20
+
+/* NHM-EX Bbox */
+#define NHMEX_B0_MSR_PMON_GLOBAL_CTL		0xc20
+#define NHMEX_B0_MSR_PMON_CTR0			0xc31
+#define NHMEX_B0_MSR_PMON_CTL0			0xc30
+#define NHMEX_B_MSR_OFFSET			0x40
+#define NHMEX_B0_MSR_MATCH			0xe45
+#define NHMEX_B0_MSR_MASK			0xe46
+#define NHMEX_B1_MSR_MATCH			0xe4d
+#define NHMEX_B1_MSR_MASK			0xe4e
+
+#define NHMEX_B_PMON_CTL_EN			(1 << 0)
+#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT		1
+#define NHMEX_B_PMON_CTL_EV_SEL_MASK		\
+		(0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_B_PMON_CTR_SHIFT		6
+#define NHMEX_B_PMON_CTR_MASK		\
+		(0x3 << NHMEX_B_PMON_CTR_SHIFT)
+#define NHMEX_B_PMON_RAW_EVENT_MASK		\
+		(NHMEX_B_PMON_CTL_EV_SEL_MASK | \
+		 NHMEX_B_PMON_CTR_MASK)
+
+/* NHM-EX Sbox */
+#define NHMEX_S0_MSR_PMON_GLOBAL_CTL		0xc40
+#define NHMEX_S0_MSR_PMON_CTR0			0xc51
+#define NHMEX_S0_MSR_PMON_CTL0			0xc50
+#define NHMEX_S_MSR_OFFSET			0x80
+#define NHMEX_S0_MSR_MM_CFG			0xe48
+#define NHMEX_S0_MSR_MATCH			0xe49
+#define NHMEX_S0_MSR_MASK			0xe4a
+#define NHMEX_S1_MSR_MM_CFG			0xe58
+#define NHMEX_S1_MSR_MATCH			0xe59
+#define NHMEX_S1_MSR_MASK			0xe5a
+
+#define NHMEX_S_PMON_MM_CFG_EN			(0x1ULL << 63)
+#define NHMEX_S_EVENT_TO_R_PROG_EV		0
+
+/* NHM-EX Mbox */
+#define NHMEX_M0_MSR_GLOBAL_CTL			0xca0
+#define NHMEX_M0_MSR_PMU_DSP			0xca5
+#define NHMEX_M0_MSR_PMU_ISS			0xca6
+#define NHMEX_M0_MSR_PMU_MAP			0xca7
+#define NHMEX_M0_MSR_PMU_MSC_THR		0xca8
+#define NHMEX_M0_MSR_PMU_PGT			0xca9
+#define NHMEX_M0_MSR_PMU_PLD			0xcaa
+#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC		0xcab
+#define NHMEX_M0_MSR_PMU_CTL0			0xcb0
+#define NHMEX_M0_MSR_PMU_CNT0			0xcb1
+#define NHMEX_M_MSR_OFFSET			0x40
+#define NHMEX_M0_MSR_PMU_MM_CFG			0xe54
+#define NHMEX_M1_MSR_PMU_MM_CFG			0xe5c
+
+#define NHMEX_M_PMON_MM_CFG_EN			(1ULL << 63)
+#define NHMEX_M_PMON_ADDR_MATCH_MASK		0x3ffffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_MASK		0x7ffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_SHIFT		34
+
+#define NHMEX_M_PMON_CTL_EN			(1 << 0)
+#define NHMEX_M_PMON_CTL_PMI_EN			(1 << 1)
+#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT	2
+#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK	\
+	(0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT	4
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK	\
+	(0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_WRAP_MODE		(1 << 6)
+#define NHMEX_M_PMON_CTL_FLAG_MODE		(1 << 7)
+#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT		9
+#define NHMEX_M_PMON_CTL_INC_SEL_MASK		\
+	(0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT	19
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK	\
+	(0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT)
+#define NHMEX_M_PMON_RAW_EVENT_MASK			\
+		(NHMEX_M_PMON_CTL_COUNT_MODE_MASK |	\
+		 NHMEX_M_PMON_CTL_STORAGE_MODE_MASK |	\
+		 NHMEX_M_PMON_CTL_WRAP_MODE |		\
+		 NHMEX_M_PMON_CTL_FLAG_MODE |		\
+		 NHMEX_M_PMON_CTL_INC_SEL_MASK |	\
+		 NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
+
+#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 11) - 1) | (1 << 23))
+#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7ULL << (11 + 3 * (n)))
+
+#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 12) - 1) | (1 << 24))
+#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7ULL << (12 + 3 * (n)))
+
+/*
+ * use the 9~13 bits to select event If the 7th bit is not set,
+ * otherwise use the 19~21 bits to select event.
+ */
+#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \
+				NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \
+			   NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \
+				NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_EXTAR_REG(c, r) \
+		EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+				MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r)
+#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \
+		EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+				MBOX_SET_FLAG_SEL_MASK, \
+				(u64)-1, NHMEX_M_##r)
+
+/* NHM-EX Rbox */
+#define NHMEX_R_MSR_GLOBAL_CTL			0xe00
+#define NHMEX_R_MSR_PMON_CTL0			0xe10
+#define NHMEX_R_MSR_PMON_CNT0			0xe11
+#define NHMEX_R_MSR_OFFSET			0x20
+
+#define NHMEX_R_MSR_PORTN_QLX_CFG(n)		\
+		((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n)		(0xe04 + (n))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n)		(0xe24 + (n))
+#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n)		\
+		(((n) < 4 ? 0 : 0x10) + (n) * 4)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n)	\
+		(0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n)	\
+		(0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2)
+
+#define NHMEX_R_PMON_CTL_EN			(1 << 0)
+#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT		1
+#define NHMEX_R_PMON_CTL_EV_SEL_MASK		\
+		(0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_R_PMON_CTL_PMI_EN			(1 << 6)
+#define NHMEX_R_PMON_RAW_EVENT_MASK		NHMEX_R_PMON_CTL_EV_SEL_MASK
+
+/* NHM-EX Wbox */
+#define NHMEX_W_MSR_GLOBAL_CTL			0xc80
+#define NHMEX_W_MSR_PMON_CNT0			0xc90
+#define NHMEX_W_MSR_PMON_EVT_SEL0		0xc91
+#define NHMEX_W_MSR_PMON_FIXED_CTR		0x394
+#define NHMEX_W_MSR_PMON_FIXED_CTL		0x395
+
+#define NHMEX_W_PMON_GLOBAL_FIXED_EN		(1ULL << 31)
+
+#define __BITS_VALUE(x, i, n)  ((typeof(x))(((x) >> ((i) * (n))) & \
+				((1ULL << (n)) - 1)))
+
+DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
+DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
+DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
+
+static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
+}
+
+static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+	u64 config;
+
+	if (msr) {
+		rdmsrl(msr, config);
+		config &= ~((1ULL << uncore_num_counters(box)) - 1);
+		/* WBox has a fixed counter */
+		if (uncore_msr_fixed_ctl(box))
+			config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN;
+		wrmsrl(msr, config);
+	}
+}
+
+static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+	u64 config;
+
+	if (msr) {
+		rdmsrl(msr, config);
+		config |= (1ULL << uncore_num_counters(box)) - 1;
+		/* WBox has a fixed counter */
+		if (uncore_msr_fixed_ctl(box))
+			config |= NHMEX_W_PMON_GLOBAL_FIXED_EN;
+		wrmsrl(msr, config);
+	}
+}
+
+static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	wrmsrl(event->hw.config_base, 0);
+}
+
+static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
+		wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
+	else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
+		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+	else
+		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+#define NHMEX_UNCORE_OPS_COMMON_INIT()				\
+	.init_box	= nhmex_uncore_msr_init_box,		\
+	.disable_box	= nhmex_uncore_msr_disable_box,		\
+	.enable_box	= nhmex_uncore_msr_enable_box,		\
+	.disable_event	= nhmex_uncore_msr_disable_event,	\
+	.read_counter	= uncore_msr_read_counter
+
+static struct intel_uncore_ops nhmex_uncore_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event	= nhmex_uncore_msr_enable_event,
+};
+
+static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_edge.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_ubox_format_group = {
+	.name		= "format",
+	.attrs		= nhmex_uncore_ubox_formats_attr,
+};
+
+static struct intel_uncore_type nhmex_uncore_ubox = {
+	.name		= "ubox",
+	.num_counters	= 1,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	.event_ctl	= NHMEX_U_MSR_PMON_EV_SEL,
+	.perf_ctr	= NHMEX_U_MSR_PMON_CTR,
+	.event_mask	= NHMEX_U_PMON_RAW_EVENT_MASK,
+	.box_ctl	= NHMEX_U_MSR_PMON_GLOBAL_CTL,
+	.ops		= &nhmex_uncore_ops,
+	.format_group	= &nhmex_uncore_ubox_format_group
+};
+
+static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_cbox_format_group = {
+	.name = "format",
+	.attrs = nhmex_uncore_cbox_formats_attr,
+};
+
+/* msr offset for each instance of cbox */
+static unsigned nhmex_cbox_msr_offsets[] = {
+	0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0,
+};
+
+static struct intel_uncore_type nhmex_uncore_cbox = {
+	.name			= "cbox",
+	.num_counters		= 6,
+	.num_boxes		= 10,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_C0_MSR_PMON_EV_SEL0,
+	.perf_ctr		= NHMEX_C0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_C0_MSR_PMON_GLOBAL_CTL,
+	.msr_offsets		= nhmex_cbox_msr_offsets,
+	.pair_ctr_ctl		= 1,
+	.ops			= &nhmex_uncore_ops,
+	.format_group		= &nhmex_uncore_cbox_format_group
+};
+
+static struct uncore_event_desc nhmex_uncore_wbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type nhmex_uncore_wbox = {
+	.name			= "wbox",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_W_MSR_PMON_CNT0,
+	.perf_ctr		= NHMEX_W_MSR_PMON_EVT_SEL0,
+	.fixed_ctr		= NHMEX_W_MSR_PMON_FIXED_CTR,
+	.fixed_ctl		= NHMEX_W_MSR_PMON_FIXED_CTL,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_W_MSR_GLOBAL_CTL,
+	.pair_ctr_ctl		= 1,
+	.event_descs		= nhmex_uncore_wbox_events,
+	.ops			= &nhmex_uncore_ops,
+	.format_group		= &nhmex_uncore_cbox_format_group
+};
+
+static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int ctr, ev_sel;
+
+	ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >>
+		NHMEX_B_PMON_CTR_SHIFT;
+	ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >>
+		  NHMEX_B_PMON_CTL_EV_SEL_SHIFT;
+
+	/* events that do not use the match/mask registers */
+	if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) ||
+	    (ctr == 2 && ev_sel != 0x4) || ctr == 3)
+		return 0;
+
+	if (box->pmu->pmu_idx == 0)
+		reg1->reg = NHMEX_B0_MSR_MATCH;
+	else
+		reg1->reg = NHMEX_B1_MSR_MATCH;
+	reg1->idx = 0;
+	reg1->config = event->attr.config1;
+	reg2->config = event->attr.config2;
+	return 0;
+}
+
+static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg1->reg, reg1->config);
+		wrmsrl(reg1->reg + 1, reg2->config);
+	}
+	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+		(hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK));
+}
+
+/*
+ * The Bbox has 4 counters, but each counter monitors different events.
+ * Use bits 6-7 in the event config to select counter.
+ */
+static struct event_constraint nhmex_uncore_bbox_constraints[] = {
+	EVENT_CONSTRAINT(0 , 1, 0xc0),
+	EVENT_CONSTRAINT(0x40, 2, 0xc0),
+	EVENT_CONSTRAINT(0x80, 4, 0xc0),
+	EVENT_CONSTRAINT(0xc0, 8, 0xc0),
+	EVENT_CONSTRAINT_END,
+};
+
+static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
+	&format_attr_event5.attr,
+	&format_attr_counter.attr,
+	&format_attr_match.attr,
+	&format_attr_mask.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_bbox_format_group = {
+	.name = "format",
+	.attrs = nhmex_uncore_bbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_bbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_bbox_msr_enable_event,
+	.hw_config		= nhmex_bbox_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_bbox = {
+	.name			= "bbox",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_B0_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_B0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_B_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_B0_MSR_PMON_GLOBAL_CTL,
+	.msr_offset		= NHMEX_B_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 1,
+	.constraints		= nhmex_uncore_bbox_constraints,
+	.ops			= &nhmex_uncore_bbox_ops,
+	.format_group		= &nhmex_uncore_bbox_format_group
+};
+
+static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	/* only TO_R_PROG_EV event uses the match/mask register */
+	if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) !=
+	    NHMEX_S_EVENT_TO_R_PROG_EV)
+		return 0;
+
+	if (box->pmu->pmu_idx == 0)
+		reg1->reg = NHMEX_S0_MSR_MM_CFG;
+	else
+		reg1->reg = NHMEX_S1_MSR_MM_CFG;
+	reg1->idx = 0;
+	reg1->config = event->attr.config1;
+	reg2->config = event->attr.config2;
+	return 0;
+}
+
+static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg1->reg, 0);
+		wrmsrl(reg1->reg + 1, reg1->config);
+		wrmsrl(reg1->reg + 2, reg2->config);
+		wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
+	}
+	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+}
+
+static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_match.attr,
+	&format_attr_mask.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_sbox_format_group = {
+	.name			= "format",
+	.attrs			= nhmex_uncore_sbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_sbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_sbox_msr_enable_event,
+	.hw_config		= nhmex_sbox_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_sbox = {
+	.name			= "sbox",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_S0_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_S0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_S0_MSR_PMON_GLOBAL_CTL,
+	.msr_offset		= NHMEX_S_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 1,
+	.ops			= &nhmex_uncore_sbox_ops,
+	.format_group		= &nhmex_uncore_sbox_format_group
+};
+
+enum {
+	EXTRA_REG_NHMEX_M_FILTER,
+	EXTRA_REG_NHMEX_M_DSP,
+	EXTRA_REG_NHMEX_M_ISS,
+	EXTRA_REG_NHMEX_M_MAP,
+	EXTRA_REG_NHMEX_M_MSC_THR,
+	EXTRA_REG_NHMEX_M_PGT,
+	EXTRA_REG_NHMEX_M_PLD,
+	EXTRA_REG_NHMEX_M_ZDP_CTL_FVC,
+};
+
+static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
+	MBOX_INC_SEL_EXTAR_REG(0x0, DSP),
+	MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR),
+	MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR),
+	MBOX_INC_SEL_EXTAR_REG(0x9, ISS),
+	/* event 0xa uses two extra registers */
+	MBOX_INC_SEL_EXTAR_REG(0xa, ISS),
+	MBOX_INC_SEL_EXTAR_REG(0xa, PLD),
+	MBOX_INC_SEL_EXTAR_REG(0xb, PLD),
+	/* events 0xd ~ 0x10 use the same extra register */
+	MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0x16, PGT),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP),
+	EVENT_EXTRA_END
+};
+
+/* Nehalem-EX or Westmere-EX ? */
+static bool uncore_nhmex;
+
+static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
+{
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	bool ret = false;
+	u64 mask;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		er = &box->shared_regs[idx];
+		raw_spin_lock_irqsave(&er->lock, flags);
+		if (!atomic_read(&er->ref) || er->config == config) {
+			atomic_inc(&er->ref);
+			er->config = config;
+			ret = true;
+		}
+		raw_spin_unlock_irqrestore(&er->lock, flags);
+
+		return ret;
+	}
+	/*
+	 * The ZDP_CTL_FVC MSR has 4 fields which are used to control
+	 * events 0xd ~ 0x10. Besides these 4 fields, there are additional
+	 * fields which are shared.
+	 */
+	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	if (WARN_ON_ONCE(idx >= 4))
+		return false;
+
+	/* mask of the shared fields */
+	if (uncore_nhmex)
+		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	else
+		mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+
+	raw_spin_lock_irqsave(&er->lock, flags);
+	/* add mask of the non-shared field if it's in use */
+	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) {
+		if (uncore_nhmex)
+			mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		else
+			mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	}
+
+	if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
+		atomic_add(1 << (idx * 8), &er->ref);
+		if (uncore_nhmex)
+			mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
+				NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		else
+			mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK |
+				WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		er->config &= ~mask;
+		er->config |= (config & mask);
+		ret = true;
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	return ret;
+}
+
+static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx)
+{
+	struct intel_uncore_extra_reg *er;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		er = &box->shared_regs[idx];
+		atomic_dec(&er->ref);
+		return;
+	}
+
+	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+	atomic_sub(1 << (idx * 8), &er->ref);
+}
+
+static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8);
+	u64 config = reg1->config;
+
+	/* get the non-shared control bits and shift them */
+	idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	if (uncore_nhmex)
+		config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	else
+		config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	if (new_idx > orig_idx) {
+		idx = new_idx - orig_idx;
+		config <<= 3 * idx;
+	} else {
+		idx = orig_idx - new_idx;
+		config >>= 3 * idx;
+	}
+
+	/* add the shared control bits back */
+	if (uncore_nhmex)
+		config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+	else
+		config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+	config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+	if (modify) {
+		/* adjust the main event selector */
+		if (new_idx > orig_idx)
+			hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+		else
+			hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+		reg1->config = config;
+		reg1->idx = ~0xff | new_idx;
+	}
+	return config;
+}
+
+static struct event_constraint *
+nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	int i, idx[2], alloc = 0;
+	u64 config1 = reg1->config;
+
+	idx[0] = __BITS_VALUE(reg1->idx, 0, 8);
+	idx[1] = __BITS_VALUE(reg1->idx, 1, 8);
+again:
+	for (i = 0; i < 2; i++) {
+		if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
+			idx[i] = 0xff;
+
+		if (idx[i] == 0xff)
+			continue;
+
+		if (!nhmex_mbox_get_shared_reg(box, idx[i],
+				__BITS_VALUE(config1, i, 32)))
+			goto fail;
+		alloc |= (0x1 << i);
+	}
+
+	/* for the match/mask registers */
+	if (reg2->idx != EXTRA_REG_NONE &&
+	    (uncore_box_is_fake(box) || !reg2->alloc) &&
+	    !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
+		goto fail;
+
+	/*
+	 * If it's a fake box -- as per validate_{group,event}() we
+	 * shouldn't touch event state and we can avoid doing so
+	 * since both will only call get_event_constraints() once
+	 * on each event, this avoids the need for reg->alloc.
+	 */
+	if (!uncore_box_is_fake(box)) {
+		if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
+			nhmex_mbox_alter_er(event, idx[0], true);
+		reg1->alloc |= alloc;
+		if (reg2->idx != EXTRA_REG_NONE)
+			reg2->alloc = 1;
+	}
+	return NULL;
+fail:
+	if (idx[0] != 0xff && !(alloc & 0x1) &&
+	    idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		/*
+		 * events 0xd ~ 0x10 are functional identical, but are
+		 * controlled by different fields in the ZDP_CTL_FVC
+		 * register. If we failed to take one field, try the
+		 * rest 3 choices.
+		 */
+		BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff);
+		idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+		idx[0] = (idx[0] + 1) % 4;
+		idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+		if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) {
+			config1 = nhmex_mbox_alter_er(event, idx[0], false);
+			goto again;
+		}
+	}
+
+	if (alloc & 0x1)
+		nhmex_mbox_put_shared_reg(box, idx[0]);
+	if (alloc & 0x2)
+		nhmex_mbox_put_shared_reg(box, idx[1]);
+	return &uncore_constraint_empty;
+}
+
+static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+
+	if (uncore_box_is_fake(box))
+		return;
+
+	if (reg1->alloc & 0x1)
+		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8));
+	if (reg1->alloc & 0x2)
+		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8));
+	reg1->alloc = 0;
+
+	if (reg2->alloc) {
+		nhmex_mbox_put_shared_reg(box, reg2->idx);
+		reg2->alloc = 0;
+	}
+}
+
+static int nhmex_mbox_extra_reg_idx(struct extra_reg *er)
+{
+	if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+		return er->idx;
+	return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd;
+}
+
+static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct intel_uncore_type *type = box->pmu->type;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	struct extra_reg *er;
+	unsigned msr;
+	int reg_idx = 0;
+	/*
+	 * The mbox events may require 2 extra MSRs at the most. But only
+	 * the lower 32 bits in these MSRs are significant, so we can use
+	 * config1 to pass two MSRs' config.
+	 */
+	for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		if (event->attr.config1 & ~er->valid_mask)
+			return -EINVAL;
+
+		msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
+		if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
+			return -EINVAL;
+
+		/* always use the 32~63 bits to pass the PLD config */
+		if (er->idx == EXTRA_REG_NHMEX_M_PLD)
+			reg_idx = 1;
+		else if (WARN_ON_ONCE(reg_idx > 0))
+			return -EINVAL;
+
+		reg1->idx &= ~(0xff << (reg_idx * 8));
+		reg1->reg &= ~(0xffff << (reg_idx * 16));
+		reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8);
+		reg1->reg |= msr << (reg_idx * 16);
+		reg1->config = event->attr.config1;
+		reg_idx++;
+	}
+	/*
+	 * The mbox only provides ability to perform address matching
+	 * for the PLD events.
+	 */
+	if (reg_idx == 2) {
+		reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
+		if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
+			reg2->config = event->attr.config2;
+		else
+			reg2->config = ~0ULL;
+		if (box->pmu->pmu_idx == 0)
+			reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
+		else
+			reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
+	}
+	return 0;
+}
+
+static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx)
+{
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	u64 config;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+		return box->shared_regs[idx].config;
+
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+	raw_spin_lock_irqsave(&er->lock, flags);
+	config = er->config;
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+	return config;
+}
+
+static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int idx;
+
+	idx = __BITS_VALUE(reg1->idx, 0, 8);
+	if (idx != 0xff)
+		wrmsrl(__BITS_VALUE(reg1->reg, 0, 16),
+			nhmex_mbox_shared_reg_config(box, idx));
+	idx = __BITS_VALUE(reg1->idx, 1, 8);
+	if (idx != 0xff)
+		wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
+			nhmex_mbox_shared_reg_config(box, idx));
+
+	if (reg2->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg2->reg, 0);
+		if (reg2->config != ~0ULL) {
+			wrmsrl(reg2->reg + 1,
+				reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
+			wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
+				(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
+			wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+		}
+	}
+
+	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(count_mode,		count_mode,	"config:2-3");
+DEFINE_UNCORE_FORMAT_ATTR(storage_mode,		storage_mode,	"config:4-5");
+DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,		wrap_mode,	"config:6");
+DEFINE_UNCORE_FORMAT_ATTR(flag_mode,		flag_mode,	"config:7");
+DEFINE_UNCORE_FORMAT_ATTR(inc_sel,		inc_sel,	"config:9-13");
+DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,		set_flag_sel,	"config:19-21");
+DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en,	filter_cfg_en,	"config2:63");
+DEFINE_UNCORE_FORMAT_ATTR(filter_match,		filter_match,	"config2:0-33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_mask,		filter_mask,	"config2:34-61");
+DEFINE_UNCORE_FORMAT_ATTR(dsp,			dsp,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(thr,			thr,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(fvc,			fvc,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pgt,			pgt,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(map,			map,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(iss,			iss,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pld,			pld,		"config1:32-63");
+
+static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
+	&format_attr_count_mode.attr,
+	&format_attr_storage_mode.attr,
+	&format_attr_wrap_mode.attr,
+	&format_attr_flag_mode.attr,
+	&format_attr_inc_sel.attr,
+	&format_attr_set_flag_sel.attr,
+	&format_attr_filter_cfg_en.attr,
+	&format_attr_filter_match.attr,
+	&format_attr_filter_mask.attr,
+	&format_attr_dsp.attr,
+	&format_attr_thr.attr,
+	&format_attr_fvc.attr,
+	&format_attr_pgt.attr,
+	&format_attr_map.attr,
+	&format_attr_iss.attr,
+	&format_attr_pld.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_mbox_format_group = {
+	.name		= "format",
+	.attrs		= nhmex_uncore_mbox_formats_attr,
+};
+
+static struct uncore_event_desc nhmex_uncore_mbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"),
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"),
+	{ /* end: all zeroes */ },
+};
+
+static struct uncore_event_desc wsmex_uncore_mbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"),
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event	= nhmex_mbox_msr_enable_event,
+	.hw_config	= nhmex_mbox_hw_config,
+	.get_constraint	= nhmex_mbox_get_constraint,
+	.put_constraint	= nhmex_mbox_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_mbox = {
+	.name			= "mbox",
+	.num_counters		= 6,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_M0_MSR_PMU_CTL0,
+	.perf_ctr		= NHMEX_M0_MSR_PMU_CNT0,
+	.event_mask		= NHMEX_M_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_M0_MSR_GLOBAL_CTL,
+	.msr_offset		= NHMEX_M_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 8,
+	.event_descs		= nhmex_uncore_mbox_events,
+	.ops			= &nhmex_uncore_mbox_ops,
+	.format_group		= &nhmex_uncore_mbox_format_group,
+};
+
+static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+	/* adjust the main event selector and extra register index */
+	if (reg1->idx % 2) {
+		reg1->idx--;
+		hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	} else {
+		reg1->idx++;
+		hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	}
+
+	/* adjust extra register config */
+	switch (reg1->idx % 6) {
+	case 2:
+		/* shift the 8~15 bits to the 0~7 bits */
+		reg1->config >>= 8;
+		break;
+	case 3:
+		/* shift the 0~7 bits to the 8~15 bits */
+		reg1->config <<= 8;
+		break;
+	}
+}
+
+/*
+ * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7.
+ * An event set consists of 6 events, the 3rd and 4th events in
+ * an event set use the same extra register. So an event set uses
+ * 5 extra registers.
+ */
+static struct event_constraint *
+nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	int idx, er_idx;
+	u64 config1;
+	bool ok = false;
+
+	if (!uncore_box_is_fake(box) && reg1->alloc)
+		return NULL;
+
+	idx = reg1->idx % 6;
+	config1 = reg1->config;
+again:
+	er_idx = idx;
+	/* the 3rd and 4th events use the same extra register */
+	if (er_idx > 2)
+		er_idx--;
+	er_idx += (reg1->idx / 6) * 5;
+
+	er = &box->shared_regs[er_idx];
+	raw_spin_lock_irqsave(&er->lock, flags);
+	if (idx < 2) {
+		if (!atomic_read(&er->ref) || er->config == reg1->config) {
+			atomic_inc(&er->ref);
+			er->config = reg1->config;
+			ok = true;
+		}
+	} else if (idx == 2 || idx == 3) {
+		/*
+		 * these two events use different fields in a extra register,
+		 * the 0~7 bits and the 8~15 bits respectively.
+		 */
+		u64 mask = 0xff << ((idx - 2) * 8);
+		if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) ||
+				!((er->config ^ config1) & mask)) {
+			atomic_add(1 << ((idx - 2) * 8), &er->ref);
+			er->config &= ~mask;
+			er->config |= config1 & mask;
+			ok = true;
+		}
+	} else {
+		if (!atomic_read(&er->ref) ||
+				(er->config == (hwc->config >> 32) &&
+				 er->config1 == reg1->config &&
+				 er->config2 == reg2->config)) {
+			atomic_inc(&er->ref);
+			er->config = (hwc->config >> 32);
+			er->config1 = reg1->config;
+			er->config2 = reg2->config;
+			ok = true;
+		}
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	if (!ok) {
+		/*
+		 * The Rbox events are always in pairs. The paired
+		 * events are functional identical, but use different
+		 * extra registers. If we failed to take an extra
+		 * register, try the alternative.
+		 */
+		idx ^= 1;
+		if (idx != reg1->idx % 6) {
+			if (idx == 2)
+				config1 >>= 8;
+			else if (idx == 3)
+				config1 <<= 8;
+			goto again;
+		}
+	} else {
+		if (!uncore_box_is_fake(box)) {
+			if (idx != reg1->idx % 6)
+				nhmex_rbox_alter_er(box, event);
+			reg1->alloc = 1;
+		}
+		return NULL;
+	}
+	return &uncore_constraint_empty;
+}
+
+static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct intel_uncore_extra_reg *er;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	int idx, er_idx;
+
+	if (uncore_box_is_fake(box) || !reg1->alloc)
+		return;
+
+	idx = reg1->idx % 6;
+	er_idx = idx;
+	if (er_idx > 2)
+		er_idx--;
+	er_idx += (reg1->idx / 6) * 5;
+
+	er = &box->shared_regs[er_idx];
+	if (idx == 2 || idx == 3)
+		atomic_sub(1 << ((idx - 2) * 8), &er->ref);
+	else
+		atomic_dec(&er->ref);
+
+	reg1->alloc = 0;
+}
+
+static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	int idx;
+
+	idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
+		NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	if (idx >= 0x18)
+		return -EINVAL;
+
+	reg1->idx = idx;
+	reg1->config = event->attr.config1;
+
+	switch (idx % 6) {
+	case 4:
+	case 5:
+		hwc->config |= event->attr.config & (~0ULL << 32);
+		reg2->config = event->attr.config2;
+		break;
+	}
+	return 0;
+}
+
+static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int idx, port;
+
+	idx = reg1->idx;
+	port = idx / 6 + box->pmu->pmu_idx * 4;
+
+	switch (idx % 6) {
+	case 0:
+		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
+		break;
+	case 1:
+		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
+		break;
+	case 2:
+	case 3:
+		wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
+			uncore_shared_reg_config(box, 2 + (idx / 6) * 5));
+		break;
+	case 4:
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
+			hwc->config >> 32);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
+		break;
+	case 5:
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
+			hwc->config >> 32);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
+		break;
+	}
+
+	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+		(hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
+DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
+
+static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
+	&format_attr_event5.attr,
+	&format_attr_xbr_mm_cfg.attr,
+	&format_attr_xbr_match.attr,
+	&format_attr_xbr_mask.attr,
+	&format_attr_qlx_cfg.attr,
+	&format_attr_iperf_cfg.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_rbox_format_group = {
+	.name = "format",
+	.attrs = nhmex_uncore_rbox_formats_attr,
+};
+
+static struct uncore_event_desc nhmex_uncore_rbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(qpi0_flit_send,		"event=0x0,iperf_cfg=0x80000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_filt_send,		"event=0x6,iperf_cfg=0x80000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt,		"event=0x0,iperf_cfg=0x40000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt,		"event=0x6,iperf_cfg=0x40000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi0_date_response,	"event=0x0,iperf_cfg=0xc4"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_date_response,	"event=0x6,iperf_cfg=0xc4"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhmex_uncore_rbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_rbox_msr_enable_event,
+	.hw_config		= nhmex_rbox_hw_config,
+	.get_constraint		= nhmex_rbox_get_constraint,
+	.put_constraint		= nhmex_rbox_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_rbox = {
+	.name			= "rbox",
+	.num_counters		= 8,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_R_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_R_MSR_PMON_CNT0,
+	.event_mask		= NHMEX_R_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_R_MSR_GLOBAL_CTL,
+	.msr_offset		= NHMEX_R_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 20,
+	.event_descs		= nhmex_uncore_rbox_events,
+	.ops			= &nhmex_uncore_rbox_ops,
+	.format_group		= &nhmex_uncore_rbox_format_group
+};
+
+static struct intel_uncore_type *nhmex_msr_uncores[] = {
+	&nhmex_uncore_ubox,
+	&nhmex_uncore_cbox,
+	&nhmex_uncore_bbox,
+	&nhmex_uncore_sbox,
+	&nhmex_uncore_mbox,
+	&nhmex_uncore_rbox,
+	&nhmex_uncore_wbox,
+	NULL,
+};
+
+void nhmex_uncore_cpu_init(void)
+{
+	if (boot_cpu_data.x86_model == 46)
+		uncore_nhmex = true;
+	else
+		nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
+	if (nhmex_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		nhmex_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	uncore_msr_uncores = nhmex_msr_uncores;
+}
+/* end of Nehalem-EX uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
new file mode 100644
index 000000000000..3001015b755c
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -0,0 +1,636 @@
+/* Nehalem/SandBridge/Haswell uncore support */
+#include "perf_event_intel_uncore.h"
+
+/* SNB event control */
+#define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
+#define SNB_UNC_CTL_UMASK_MASK			0x0000ff00
+#define SNB_UNC_CTL_EDGE_DET			(1 << 18)
+#define SNB_UNC_CTL_EN				(1 << 22)
+#define SNB_UNC_CTL_INVERT			(1 << 23)
+#define SNB_UNC_CTL_CMASK_MASK			0x1f000000
+#define NHM_UNC_CTL_CMASK_MASK			0xff000000
+#define NHM_UNC_FIXED_CTR_CTL_EN		(1 << 0)
+
+#define SNB_UNC_RAW_EVENT_MASK			(SNB_UNC_CTL_EV_SEL_MASK | \
+						 SNB_UNC_CTL_UMASK_MASK | \
+						 SNB_UNC_CTL_EDGE_DET | \
+						 SNB_UNC_CTL_INVERT | \
+						 SNB_UNC_CTL_CMASK_MASK)
+
+#define NHM_UNC_RAW_EVENT_MASK			(SNB_UNC_CTL_EV_SEL_MASK | \
+						 SNB_UNC_CTL_UMASK_MASK | \
+						 SNB_UNC_CTL_EDGE_DET | \
+						 SNB_UNC_CTL_INVERT | \
+						 NHM_UNC_CTL_CMASK_MASK)
+
+/* SNB global control register */
+#define SNB_UNC_PERF_GLOBAL_CTL                 0x391
+#define SNB_UNC_FIXED_CTR_CTRL                  0x394
+#define SNB_UNC_FIXED_CTR                       0x395
+
+/* SNB uncore global control */
+#define SNB_UNC_GLOBAL_CTL_CORE_ALL             ((1 << 4) - 1)
+#define SNB_UNC_GLOBAL_CTL_EN                   (1 << 29)
+
+/* SNB Cbo register */
+#define SNB_UNC_CBO_0_PERFEVTSEL0               0x700
+#define SNB_UNC_CBO_0_PER_CTR0                  0x706
+#define SNB_UNC_CBO_MSR_OFFSET                  0x10
+
+/* NHM global control register */
+#define NHM_UNC_PERF_GLOBAL_CTL                 0x391
+#define NHM_UNC_FIXED_CTR                       0x394
+#define NHM_UNC_FIXED_CTR_CTRL                  0x395
+
+/* NHM uncore global control */
+#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL            ((1ULL << 8) - 1)
+#define NHM_UNC_GLOBAL_CTL_EN_FC                (1ULL << 32)
+
+/* NHM uncore register */
+#define NHM_UNC_PERFEVTSEL0                     0x3c0
+#define NHM_UNC_UNCORE_PMC0                     0x3b0
+
+DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28");
+DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31");
+
+/* Sandy Bridge uncore support */
+static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+	else
+		wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
+}
+
+static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	wrmsrl(event->hw.config_base, 0);
+}
+
+static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	if (box->pmu->pmu_idx == 0) {
+		wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+			SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
+	}
+}
+
+static struct uncore_event_desc snb_uncore_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+	{ /* end: all zeroes */ },
+};
+
+static struct attribute *snb_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask5.attr,
+	NULL,
+};
+
+static struct attribute_group snb_uncore_format_group = {
+	.name		= "format",
+	.attrs		= snb_uncore_formats_attr,
+};
+
+static struct intel_uncore_ops snb_uncore_msr_ops = {
+	.init_box	= snb_uncore_msr_init_box,
+	.disable_event	= snb_uncore_msr_disable_event,
+	.enable_event	= snb_uncore_msr_enable_event,
+	.read_counter	= uncore_msr_read_counter,
+};
+
+static struct event_constraint snb_uncore_cbox_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x80, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x83, 0x1),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type snb_uncore_cbox = {
+	.name		= "cbox",
+	.num_counters   = 2,
+	.num_boxes	= 4,
+	.perf_ctr_bits	= 44,
+	.fixed_ctr_bits	= 48,
+	.perf_ctr	= SNB_UNC_CBO_0_PER_CTR0,
+	.event_ctl	= SNB_UNC_CBO_0_PERFEVTSEL0,
+	.fixed_ctr	= SNB_UNC_FIXED_CTR,
+	.fixed_ctl	= SNB_UNC_FIXED_CTR_CTRL,
+	.single_fixed	= 1,
+	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
+	.msr_offset	= SNB_UNC_CBO_MSR_OFFSET,
+	.constraints	= snb_uncore_cbox_constraints,
+	.ops		= &snb_uncore_msr_ops,
+	.format_group	= &snb_uncore_format_group,
+	.event_descs	= snb_uncore_events,
+};
+
+static struct intel_uncore_type *snb_msr_uncores[] = {
+	&snb_uncore_cbox,
+	NULL,
+};
+
+void snb_uncore_cpu_init(void)
+{
+	uncore_msr_uncores = snb_msr_uncores;
+	if (snb_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		snb_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+}
+
+enum {
+	SNB_PCI_UNCORE_IMC,
+};
+
+static struct uncore_event_desc snb_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(data_reads,  "event=0x01"),
+	INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"),
+
+	INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"),
+	INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"),
+
+	{ /* end: all zeroes */ },
+};
+
+#define SNB_UNCORE_PCI_IMC_EVENT_MASK		0xff
+#define SNB_UNCORE_PCI_IMC_BAR_OFFSET		0x48
+
+/* page size multiple covering all config regs */
+#define SNB_UNCORE_PCI_IMC_MAP_SIZE		0x6000
+
+#define SNB_UNCORE_PCI_IMC_DATA_READS		0x1
+#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE	0x5050
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES		0x2
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE	0x5054
+#define SNB_UNCORE_PCI_IMC_CTR_BASE		SNB_UNCORE_PCI_IMC_DATA_READS_BASE
+
+static struct attribute *snb_uncore_imc_formats_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group snb_uncore_imc_format_group = {
+	.name = "format",
+	.attrs = snb_uncore_imc_formats_attr,
+};
+
+static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET;
+	resource_size_t addr;
+	u32 pci_dword;
+
+	pci_read_config_dword(pdev, where, &pci_dword);
+	addr = pci_dword;
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+	pci_read_config_dword(pdev, where + 4, &pci_dword);
+	addr |= ((resource_size_t)pci_dword << 32);
+#endif
+
+	addr &= ~(PAGE_SIZE - 1);
+
+	box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+	box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
+}
+
+static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_disable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
+}
+
+/*
+ * custom event_init() function because we define our own fixed, free
+ * running counters, so we do not want to conflict with generic uncore
+ * logic. Also simplifies processing
+ */
+static int snb_uncore_imc_event_init(struct perf_event *event)
+{
+	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_box *box;
+	struct hw_perf_event *hwc = &event->hw;
+	u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK;
+	int idx, base;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	pmu = uncore_event_to_pmu(event);
+	/* no device found for this pmu */
+	if (pmu->func_id < 0)
+		return -ENOENT;
+
+	/* Sampling not supported yet */
+	if (hwc->sample_period)
+		return -EINVAL;
+
+	/* unsupported modes and filters */
+	if (event->attr.exclude_user   ||
+	    event->attr.exclude_kernel ||
+	    event->attr.exclude_hv     ||
+	    event->attr.exclude_idle   ||
+	    event->attr.exclude_host   ||
+	    event->attr.exclude_guest  ||
+	    event->attr.sample_period) /* no sampling */
+		return -EINVAL;
+
+	/*
+	 * Place all uncore events for a particular physical package
+	 * onto a single cpu
+	 */
+	if (event->cpu < 0)
+		return -EINVAL;
+
+	/* check only supported bits are set */
+	if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK)
+		return -EINVAL;
+
+	box = uncore_pmu_to_box(pmu, event->cpu);
+	if (!box || box->cpu < 0)
+		return -EINVAL;
+
+	event->cpu = box->cpu;
+
+	event->hw.idx = -1;
+	event->hw.last_tag = ~0ULL;
+	event->hw.extra_reg.idx = EXTRA_REG_NONE;
+	event->hw.branch_reg.idx = EXTRA_REG_NONE;
+	/*
+	 * check event is known (whitelist, determines counter)
+	 */
+	switch (cfg) {
+	case SNB_UNCORE_PCI_IMC_DATA_READS:
+		base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
+		idx = UNCORE_PMC_IDX_FIXED;
+		break;
+	case SNB_UNCORE_PCI_IMC_DATA_WRITES:
+		base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
+		idx = UNCORE_PMC_IDX_FIXED + 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* must be done before validate_group */
+	event->hw.event_base = base;
+	event->hw.config = cfg;
+	event->hw.idx = idx;
+
+	/* no group validation needed, we have free running counters */
+
+	return 0;
+}
+
+static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return 0;
+}
+
+static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	u64 count;
+
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
+	event->hw.state = 0;
+	box->n_active++;
+
+	list_add_tail(&event->active_entry, &box->active_list);
+
+	count = snb_uncore_imc_read_counter(box, event);
+	local64_set(&event->hw.prev_count, count);
+
+	if (box->n_active == 1)
+		uncore_pmu_start_hrtimer(box);
+}
+
+static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		box->n_active--;
+
+		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+		hwc->state |= PERF_HES_STOPPED;
+
+		list_del(&event->active_entry);
+
+		if (box->n_active == 0)
+			uncore_pmu_cancel_hrtimer(box);
+	}
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		/*
+		 * Drain the remaining delta count out of a event
+		 * that we are disabling:
+		 */
+		uncore_perf_event_update(box, event);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+}
+
+static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!box)
+		return -ENODEV;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_ARCH;
+
+	snb_uncore_imc_event_start(event, 0);
+
+	box->n_events++;
+
+	return 0;
+}
+
+static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	int i;
+
+	snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
+
+	for (i = 0; i < box->n_events; i++) {
+		if (event == box->event_list[i]) {
+			--box->n_events;
+			break;
+		}
+	}
+}
+
+static int snb_pci2phy_map_init(int devid)
+{
+	struct pci_dev *dev = NULL;
+	int bus;
+
+	dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
+	if (!dev)
+		return -ENOTTY;
+
+	bus = dev->bus->number;
+
+	uncore_pcibus_to_physid[bus] = 0;
+
+	pci_dev_put(dev);
+
+	return 0;
+}
+
+static struct pmu snb_uncore_imc_pmu = {
+	.task_ctx_nr	= perf_invalid_context,
+	.event_init	= snb_uncore_imc_event_init,
+	.add		= snb_uncore_imc_event_add,
+	.del		= snb_uncore_imc_event_del,
+	.start		= snb_uncore_imc_event_start,
+	.stop		= snb_uncore_imc_event_stop,
+	.read		= uncore_pmu_event_read,
+};
+
+static struct intel_uncore_ops snb_uncore_imc_ops = {
+	.init_box	= snb_uncore_imc_init_box,
+	.enable_box	= snb_uncore_imc_enable_box,
+	.disable_box	= snb_uncore_imc_disable_box,
+	.disable_event	= snb_uncore_imc_disable_event,
+	.enable_event	= snb_uncore_imc_enable_event,
+	.hw_config	= snb_uncore_imc_hw_config,
+	.read_counter	= snb_uncore_imc_read_counter,
+};
+
+static struct intel_uncore_type snb_uncore_imc = {
+	.name		= "imc",
+	.num_counters   = 2,
+	.num_boxes	= 1,
+	.fixed_ctr_bits	= 32,
+	.fixed_ctr	= SNB_UNCORE_PCI_IMC_CTR_BASE,
+	.event_descs	= snb_uncore_imc_events,
+	.format_group	= &snb_uncore_imc_format_group,
+	.perf_ctr	= SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
+	.event_mask	= SNB_UNCORE_PCI_IMC_EVENT_MASK,
+	.ops		= &snb_uncore_imc_ops,
+	.pmu		= &snb_uncore_imc_pmu,
+};
+
+static struct intel_uncore_type *snb_pci_uncores[] = {
+	[SNB_PCI_UNCORE_IMC]	= &snb_uncore_imc,
+	NULL,
+};
+
+static const struct pci_device_id snb_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
+static const struct pci_device_id ivb_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_E3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
+static const struct pci_device_id hsw_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
+static struct pci_driver snb_uncore_pci_driver = {
+	.name		= "snb_uncore",
+	.id_table	= snb_uncore_pci_ids,
+};
+
+static struct pci_driver ivb_uncore_pci_driver = {
+	.name		= "ivb_uncore",
+	.id_table	= ivb_uncore_pci_ids,
+};
+
+static struct pci_driver hsw_uncore_pci_driver = {
+	.name		= "hsw_uncore",
+	.id_table	= hsw_uncore_pci_ids,
+};
+
+struct imc_uncore_pci_dev {
+	__u32 pci_id;
+	struct pci_driver *driver;
+};
+#define IMC_DEV(a, d) \
+	{ .pci_id = PCI_DEVICE_ID_INTEL_##a, .driver = (d) }
+
+static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
+	IMC_DEV(SNB_IMC, &snb_uncore_pci_driver),
+	IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver),    /* 3rd Gen Core processor */
+	IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
+	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
+	{  /* end marker */ }
+};
+
+
+#define for_each_imc_pci_id(x, t) \
+	for (x = (t); (x)->pci_id; x++)
+
+static struct pci_driver *imc_uncore_find_dev(void)
+{
+	const struct imc_uncore_pci_dev *p;
+	int ret;
+
+	for_each_imc_pci_id(p, desktop_imc_pci_ids) {
+		ret = snb_pci2phy_map_init(p->pci_id);
+		if (ret == 0)
+			return p->driver;
+	}
+	return NULL;
+}
+
+static int imc_uncore_pci_init(void)
+{
+	struct pci_driver *imc_drv = imc_uncore_find_dev();
+
+	if (!imc_drv)
+		return -ENODEV;
+
+	uncore_pci_uncores = snb_pci_uncores;
+	uncore_pci_driver = imc_drv;
+
+	return 0;
+}
+
+int snb_uncore_pci_init(void)
+{
+	return imc_uncore_pci_init();
+}
+
+int ivb_uncore_pci_init(void)
+{
+	return imc_uncore_pci_init();
+}
+int hsw_uncore_pci_init(void)
+{
+	return imc_uncore_pci_init();
+}
+
+/* end of Sandy Bridge uncore support */
+
+/* Nehalem uncore support */
+static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
+}
+
+static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
+}
+
+static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+	else
+		wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
+}
+
+static struct attribute *nhm_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask8.attr,
+	NULL,
+};
+
+static struct attribute_group nhm_uncore_format_group = {
+	.name = "format",
+	.attrs = nhm_uncore_formats_attr,
+};
+
+static struct uncore_event_desc nhm_uncore_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,                "event=0xff,umask=0x00"),
+	INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any,       "event=0x2f,umask=0x0f"),
+	INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any,      "event=0x2c,umask=0x0f"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads,     "event=0x20,umask=0x01"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes,    "event=0x20,umask=0x02"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads,  "event=0x20,umask=0x04"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads,   "event=0x20,umask=0x10"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes,  "event=0x20,umask=0x20"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhm_uncore_msr_ops = {
+	.disable_box	= nhm_uncore_msr_disable_box,
+	.enable_box	= nhm_uncore_msr_enable_box,
+	.disable_event	= snb_uncore_msr_disable_event,
+	.enable_event	= nhm_uncore_msr_enable_event,
+	.read_counter	= uncore_msr_read_counter,
+};
+
+static struct intel_uncore_type nhm_uncore = {
+	.name		= "",
+	.num_counters   = 8,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	.fixed_ctr_bits	= 48,
+	.event_ctl	= NHM_UNC_PERFEVTSEL0,
+	.perf_ctr	= NHM_UNC_UNCORE_PMC0,
+	.fixed_ctr	= NHM_UNC_FIXED_CTR,
+	.fixed_ctl	= NHM_UNC_FIXED_CTR_CTRL,
+	.event_mask	= NHM_UNC_RAW_EVENT_MASK,
+	.event_descs	= nhm_uncore_events,
+	.ops		= &nhm_uncore_msr_ops,
+	.format_group	= &nhm_uncore_format_group,
+};
+
+static struct intel_uncore_type *nhm_msr_uncores[] = {
+	&nhm_uncore,
+	NULL,
+};
+
+void nhm_uncore_cpu_init(void)
+{
+	uncore_msr_uncores = nhm_msr_uncores;
+}
+
+/* end of Nehalem uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
new file mode 100644
index 000000000000..adf138eac85c
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -0,0 +1,2258 @@
+/* SandyBridge-EP/IvyTown uncore support */
+#include "perf_event_intel_uncore.h"
+
+
+/* SNB-EP Box level control */
+#define SNBEP_PMON_BOX_CTL_RST_CTRL	(1 << 0)
+#define SNBEP_PMON_BOX_CTL_RST_CTRS	(1 << 1)
+#define SNBEP_PMON_BOX_CTL_FRZ		(1 << 8)
+#define SNBEP_PMON_BOX_CTL_FRZ_EN	(1 << 16)
+#define SNBEP_PMON_BOX_CTL_INT		(SNBEP_PMON_BOX_CTL_RST_CTRL | \
+					 SNBEP_PMON_BOX_CTL_RST_CTRS | \
+					 SNBEP_PMON_BOX_CTL_FRZ_EN)
+/* SNB-EP event control */
+#define SNBEP_PMON_CTL_EV_SEL_MASK	0x000000ff
+#define SNBEP_PMON_CTL_UMASK_MASK	0x0000ff00
+#define SNBEP_PMON_CTL_RST		(1 << 17)
+#define SNBEP_PMON_CTL_EDGE_DET		(1 << 18)
+#define SNBEP_PMON_CTL_EV_SEL_EXT	(1 << 21)
+#define SNBEP_PMON_CTL_EN		(1 << 22)
+#define SNBEP_PMON_CTL_INVERT		(1 << 23)
+#define SNBEP_PMON_CTL_TRESH_MASK	0xff000000
+#define SNBEP_PMON_RAW_EVENT_MASK	(SNBEP_PMON_CTL_EV_SEL_MASK | \
+					 SNBEP_PMON_CTL_UMASK_MASK | \
+					 SNBEP_PMON_CTL_EDGE_DET | \
+					 SNBEP_PMON_CTL_INVERT | \
+					 SNBEP_PMON_CTL_TRESH_MASK)
+
+/* SNB-EP Ubox event control */
+#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK		0x1f000000
+#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK		\
+				(SNBEP_PMON_CTL_EV_SEL_MASK | \
+				 SNBEP_PMON_CTL_UMASK_MASK | \
+				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_PMON_CTL_INVERT | \
+				 SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
+
+#define SNBEP_CBO_PMON_CTL_TID_EN		(1 << 19)
+#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK	(SNBEP_PMON_RAW_EVENT_MASK | \
+						 SNBEP_CBO_PMON_CTL_TID_EN)
+
+/* SNB-EP PCU event control */
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK	0x0000c000
+#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK	0x1f000000
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT	(1 << 30)
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET	(1 << 31)
+#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_CTL_EV_SEL_MASK | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT | \
+				 SNBEP_PMON_CTL_INVERT | \
+				 SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
+
+#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_RAW_EVENT_MASK | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT)
+
+/* SNB-EP pci control register */
+#define SNBEP_PCI_PMON_BOX_CTL			0xf4
+#define SNBEP_PCI_PMON_CTL0			0xd8
+/* SNB-EP pci counter register */
+#define SNBEP_PCI_PMON_CTR0			0xa0
+
+/* SNB-EP home agent register */
+#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0	0x40
+#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1	0x44
+#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH	0x48
+/* SNB-EP memory controller register */
+#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL		0xf0
+#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR		0xd0
+/* SNB-EP QPI register */
+#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0		0x228
+#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1		0x22c
+#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0		0x238
+#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1		0x23c
+
+/* SNB-EP Ubox register */
+#define SNBEP_U_MSR_PMON_CTR0			0xc16
+#define SNBEP_U_MSR_PMON_CTL0			0xc10
+
+#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL		0xc08
+#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR		0xc09
+
+/* SNB-EP Cbo register */
+#define SNBEP_C0_MSR_PMON_CTR0			0xd16
+#define SNBEP_C0_MSR_PMON_CTL0			0xd10
+#define SNBEP_C0_MSR_PMON_BOX_CTL		0xd04
+#define SNBEP_C0_MSR_PMON_BOX_FILTER		0xd14
+#define SNBEP_CBO_MSR_OFFSET			0x20
+
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID	0x1f
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID	0x3fc00
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE	0x7c0000
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC	0xff800000
+
+#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) {	\
+	.event = (e),				\
+	.msr = SNBEP_C0_MSR_PMON_BOX_FILTER,	\
+	.config_mask = (m),			\
+	.idx = (i)				\
+}
+
+/* SNB-EP PCU register */
+#define SNBEP_PCU_MSR_PMON_CTR0			0xc36
+#define SNBEP_PCU_MSR_PMON_CTL0			0xc30
+#define SNBEP_PCU_MSR_PMON_BOX_CTL		0xc24
+#define SNBEP_PCU_MSR_PMON_BOX_FILTER		0xc34
+#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK	0xffffffff
+#define SNBEP_PCU_MSR_CORE_C3_CTR		0x3fc
+#define SNBEP_PCU_MSR_CORE_C6_CTR		0x3fd
+
+/* IVBEP event control */
+#define IVBEP_PMON_BOX_CTL_INT		(SNBEP_PMON_BOX_CTL_RST_CTRL | \
+					 SNBEP_PMON_BOX_CTL_RST_CTRS)
+#define IVBEP_PMON_RAW_EVENT_MASK		(SNBEP_PMON_CTL_EV_SEL_MASK | \
+					 SNBEP_PMON_CTL_UMASK_MASK | \
+					 SNBEP_PMON_CTL_EDGE_DET | \
+					 SNBEP_PMON_CTL_TRESH_MASK)
+/* IVBEP Ubox */
+#define IVBEP_U_MSR_PMON_GLOBAL_CTL		0xc00
+#define IVBEP_U_PMON_GLOBAL_FRZ_ALL		(1 << 31)
+#define IVBEP_U_PMON_GLOBAL_UNFRZ_ALL		(1 << 29)
+
+#define IVBEP_U_MSR_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_CTL_EV_SEL_MASK | \
+				 SNBEP_PMON_CTL_UMASK_MASK | \
+				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
+/* IVBEP Cbo */
+#define IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK		(IVBEP_PMON_RAW_EVENT_MASK | \
+						 SNBEP_CBO_PMON_CTL_TID_EN)
+
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_TID		(0x1fULL << 0)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK	(0xfULL << 5)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE	(0x3fULL << 17)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NID		(0xffffULL << 32)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC		(0x1ffULL << 52)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_C6		(0x1ULL << 61)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NC		(0x1ULL << 62)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_ISOC	(0x1ULL << 63)
+
+/* IVBEP home agent */
+#define IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST		(1 << 16)
+#define IVBEP_HA_PCI_PMON_RAW_EVENT_MASK		\
+				(IVBEP_PMON_RAW_EVENT_MASK | \
+				 IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST)
+/* IVBEP PCU */
+#define IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_CTL_EV_SEL_MASK | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
+/* IVBEP QPI */
+#define IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK	\
+				(IVBEP_PMON_RAW_EVENT_MASK | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT)
+
+#define __BITS_VALUE(x, i, n)  ((typeof(x))(((x) >> ((i) * (n))) & \
+				((1ULL << (n)) - 1)))
+
+/* Haswell-EP Ubox */
+#define HSWEP_U_MSR_PMON_CTR0			0x705
+#define HSWEP_U_MSR_PMON_CTL0			0x709
+#define HSWEP_U_MSR_PMON_FILTER			0x707
+
+#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL		0x703
+#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTR		0x704
+
+#define HSWEP_U_MSR_PMON_BOX_FILTER_TID		(0x1 << 0)
+#define HSWEP_U_MSR_PMON_BOX_FILTER_CID		(0x1fULL << 1)
+#define HSWEP_U_MSR_PMON_BOX_FILTER_MASK \
+					(HSWEP_U_MSR_PMON_BOX_FILTER_TID | \
+					 HSWEP_U_MSR_PMON_BOX_FILTER_CID)
+
+/* Haswell-EP CBo */
+#define HSWEP_C0_MSR_PMON_CTR0			0xe08
+#define HSWEP_C0_MSR_PMON_CTL0			0xe01
+#define HSWEP_C0_MSR_PMON_BOX_CTL			0xe00
+#define HSWEP_C0_MSR_PMON_BOX_FILTER0		0xe05
+#define HSWEP_CBO_MSR_OFFSET			0x10
+
+
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_TID		(0x3fULL << 0)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_LINK	(0xfULL << 6)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_STATE	(0x7fULL << 17)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_NID		(0xffffULL << 32)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_OPC		(0x1ffULL << 52)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_C6		(0x1ULL << 61)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_NC		(0x1ULL << 62)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_ISOC	(0x1ULL << 63)
+
+
+/* Haswell-EP Sbox */
+#define HSWEP_S0_MSR_PMON_CTR0			0x726
+#define HSWEP_S0_MSR_PMON_CTL0			0x721
+#define HSWEP_S0_MSR_PMON_BOX_CTL			0x720
+#define HSWEP_SBOX_MSR_OFFSET			0xa
+#define HSWEP_S_MSR_PMON_RAW_EVENT_MASK		(SNBEP_PMON_RAW_EVENT_MASK | \
+						 SNBEP_CBO_PMON_CTL_TID_EN)
+
+/* Haswell-EP PCU */
+#define HSWEP_PCU_MSR_PMON_CTR0			0x717
+#define HSWEP_PCU_MSR_PMON_CTL0			0x711
+#define HSWEP_PCU_MSR_PMON_BOX_CTL		0x710
+#define HSWEP_PCU_MSR_PMON_BOX_FILTER		0x715
+
+
+DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
+DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
+DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
+DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
+DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
+DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5");
+DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5");
+DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62");
+DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61");
+DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31");
+DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31");
+DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
+
+static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	int box_ctl = uncore_pci_box_ctl(box);
+	u32 config = 0;
+
+	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+		config |= SNBEP_PMON_BOX_CTL_FRZ;
+		pci_write_config_dword(pdev, box_ctl, config);
+	}
+}
+
+static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	int box_ctl = uncore_pci_box_ctl(box);
+	u32 config = 0;
+
+	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+		pci_write_config_dword(pdev, box_ctl, config);
+	}
+}
+
+static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+
+	pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+
+	pci_write_config_dword(pdev, hwc->config_base, hwc->config);
+}
+
+static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+	u64 count = 0;
+
+	pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
+	pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
+
+	return count;
+}
+
+static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+
+	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT);
+}
+
+static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+	u64 config;
+	unsigned msr;
+
+	msr = uncore_msr_box_ctl(box);
+	if (msr) {
+		rdmsrl(msr, config);
+		config |= SNBEP_PMON_BOX_CTL_FRZ;
+		wrmsrl(msr, config);
+	}
+}
+
+static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	u64 config;
+	unsigned msr;
+
+	msr = uncore_msr_box_ctl(box);
+	if (msr) {
+		rdmsrl(msr, config);
+		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+		wrmsrl(msr, config);
+	}
+}
+
+static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE)
+		wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0));
+
+	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
+					struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	wrmsrl(hwc->config_base, hwc->config);
+}
+
+static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+
+	if (msr)
+		wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
+}
+
+static struct attribute *snbep_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute *snbep_uncore_ubox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh5.attr,
+	NULL,
+};
+
+static struct attribute *snbep_uncore_cbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_tid_en.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_filter_tid.attr,
+	&format_attr_filter_nid.attr,
+	&format_attr_filter_state.attr,
+	&format_attr_filter_opc.attr,
+	NULL,
+};
+
+static struct attribute *snbep_uncore_pcu_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_occ_sel.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh5.attr,
+	&format_attr_occ_invert.attr,
+	&format_attr_occ_edge.attr,
+	&format_attr_filter_band0.attr,
+	&format_attr_filter_band1.attr,
+	&format_attr_filter_band2.attr,
+	&format_attr_filter_band3.attr,
+	NULL,
+};
+
+static struct attribute *snbep_uncore_qpi_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_match_rds.attr,
+	&format_attr_match_rnid30.attr,
+	&format_attr_match_rnid4.attr,
+	&format_attr_match_dnid.attr,
+	&format_attr_match_mc.attr,
+	&format_attr_match_opc.attr,
+	&format_attr_match_vnw.attr,
+	&format_attr_match0.attr,
+	&format_attr_match1.attr,
+	&format_attr_mask_rds.attr,
+	&format_attr_mask_rnid30.attr,
+	&format_attr_mask_rnid4.attr,
+	&format_attr_mask_dnid.attr,
+	&format_attr_mask_mc.attr,
+	&format_attr_mask_opc.attr,
+	&format_attr_mask_vnw.attr,
+	&format_attr_mask0.attr,
+	&format_attr_mask1.attr,
+	NULL,
+};
+
+static struct uncore_event_desc snbep_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0xff,umask=0x00"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read,  "event=0x04,umask=0x03"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+	{ /* end: all zeroes */ },
+};
+
+static struct uncore_event_desc snbep_uncore_qpi_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,       "event=0x14"),
+	INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
+	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x102,umask=0x08"),
+	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x103,umask=0x04"),
+	{ /* end: all zeroes */ },
+};
+
+static struct attribute_group snbep_uncore_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_ubox_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_ubox_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_cbox_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_cbox_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_pcu_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_pcu_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_qpi_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_qpi_formats_attr,
+};
+
+#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
+	.init_box	= snbep_uncore_msr_init_box,		\
+	.disable_box	= snbep_uncore_msr_disable_box,		\
+	.enable_box	= snbep_uncore_msr_enable_box,		\
+	.disable_event	= snbep_uncore_msr_disable_event,	\
+	.enable_event	= snbep_uncore_msr_enable_event,	\
+	.read_counter	= uncore_msr_read_counter
+
+static struct intel_uncore_ops snbep_uncore_msr_ops = {
+	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+};
+
+#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT()			\
+	.init_box	= snbep_uncore_pci_init_box,		\
+	.disable_box	= snbep_uncore_pci_disable_box,		\
+	.enable_box	= snbep_uncore_pci_enable_box,		\
+	.disable_event	= snbep_uncore_pci_disable_event,	\
+	.read_counter	= snbep_uncore_pci_read_counter
+
+static struct intel_uncore_ops snbep_uncore_pci_ops = {
+	SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+	.enable_event	= snbep_uncore_pci_enable_event,	\
+};
+
+static struct event_constraint snbep_uncore_cbox_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x01, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x02, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x04, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x05, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x07, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x09, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x13, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x1b, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0x1c, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0x1d, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0x1e, 0xc),
+	EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff),
+	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x35, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x3b, 0x1),
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint snbep_uncore_r2pcie_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x12, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2a, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2b, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x30, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type snbep_uncore_ubox = {
+	.name		= "ubox",
+	.num_counters   = 2,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 44,
+	.fixed_ctr_bits	= 48,
+	.perf_ctr	= SNBEP_U_MSR_PMON_CTR0,
+	.event_ctl	= SNBEP_U_MSR_PMON_CTL0,
+	.event_mask	= SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
+	.fixed_ctr	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
+	.fixed_ctl	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
+	.ops		= &snbep_uncore_msr_ops,
+	.format_group	= &snbep_uncore_ubox_format_group,
+};
+
+static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
+	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2),
+	EVENT_EXTRA_END
+};
+
+static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+	int i;
+
+	if (uncore_box_is_fake(box))
+		return;
+
+	for (i = 0; i < 5; i++) {
+		if (reg1->alloc & (0x1 << i))
+			atomic_sub(1 << (i * 6), &er->ref);
+	}
+	reg1->alloc = 0;
+}
+
+static struct event_constraint *
+__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event,
+			    u64 (*cbox_filter_mask)(int fields))
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+	int i, alloc = 0;
+	unsigned long flags;
+	u64 mask;
+
+	if (reg1->idx == EXTRA_REG_NONE)
+		return NULL;
+
+	raw_spin_lock_irqsave(&er->lock, flags);
+	for (i = 0; i < 5; i++) {
+		if (!(reg1->idx & (0x1 << i)))
+			continue;
+		if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
+			continue;
+
+		mask = cbox_filter_mask(0x1 << i);
+		if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) ||
+		    !((reg1->config ^ er->config) & mask)) {
+			atomic_add(1 << (i * 6), &er->ref);
+			er->config &= ~mask;
+			er->config |= reg1->config & mask;
+			alloc |= (0x1 << i);
+		} else {
+			break;
+		}
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+	if (i < 5)
+		goto fail;
+
+	if (!uncore_box_is_fake(box))
+		reg1->alloc |= alloc;
+
+	return NULL;
+fail:
+	for (; i >= 0; i--) {
+		if (alloc & (0x1 << i))
+			atomic_sub(1 << (i * 6), &er->ref);
+	}
+	return &uncore_constraint_empty;
+}
+
+static u64 snbep_cbox_filter_mask(int fields)
+{
+	u64 mask = 0;
+
+	if (fields & 0x1)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID;
+	if (fields & 0x2)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID;
+	if (fields & 0x4)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE;
+	if (fields & 0x8)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC;
+
+	return mask;
+}
+
+static struct event_constraint *
+snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask);
+}
+
+static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct extra_reg *er;
+	int idx = 0;
+
+	for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		idx |= er->idx;
+	}
+
+	if (idx) {
+		reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+		reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx);
+		reg1->idx = idx;
+	}
+	return 0;
+}
+
+static struct intel_uncore_ops snbep_uncore_cbox_ops = {
+	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= snbep_cbox_hw_config,
+	.get_constraint		= snbep_cbox_get_constraint,
+	.put_constraint		= snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type snbep_uncore_cbox = {
+	.name			= "cbox",
+	.num_counters		= 4,
+	.num_boxes		= 8,
+	.perf_ctr_bits		= 44,
+	.event_ctl		= SNBEP_C0_MSR_PMON_CTL0,
+	.perf_ctr		= SNBEP_C0_MSR_PMON_CTR0,
+	.event_mask		= SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_C0_MSR_PMON_BOX_CTL,
+	.msr_offset		= SNBEP_CBO_MSR_OFFSET,
+	.num_shared_regs	= 1,
+	.constraints		= snbep_uncore_cbox_constraints,
+	.ops			= &snbep_uncore_cbox_ops,
+	.format_group		= &snbep_uncore_cbox_format_group,
+};
+
+static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	u64 config = reg1->config;
+
+	if (new_idx > reg1->idx)
+		config <<= 8 * (new_idx - reg1->idx);
+	else
+		config >>= 8 * (reg1->idx - new_idx);
+
+	if (modify) {
+		hwc->config += new_idx - reg1->idx;
+		reg1->config = config;
+		reg1->idx = new_idx;
+	}
+	return config;
+}
+
+static struct event_constraint *
+snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+	unsigned long flags;
+	int idx = reg1->idx;
+	u64 mask, config1 = reg1->config;
+	bool ok = false;
+
+	if (reg1->idx == EXTRA_REG_NONE ||
+	    (!uncore_box_is_fake(box) && reg1->alloc))
+		return NULL;
+again:
+	mask = 0xffULL << (idx * 8);
+	raw_spin_lock_irqsave(&er->lock, flags);
+	if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) ||
+	    !((config1 ^ er->config) & mask)) {
+		atomic_add(1 << (idx * 8), &er->ref);
+		er->config &= ~mask;
+		er->config |= config1 & mask;
+		ok = true;
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	if (!ok) {
+		idx = (idx + 1) % 4;
+		if (idx != reg1->idx) {
+			config1 = snbep_pcu_alter_er(event, idx, false);
+			goto again;
+		}
+		return &uncore_constraint_empty;
+	}
+
+	if (!uncore_box_is_fake(box)) {
+		if (idx != reg1->idx)
+			snbep_pcu_alter_er(event, idx, true);
+		reg1->alloc = 1;
+	}
+	return NULL;
+}
+
+static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+
+	if (uncore_box_is_fake(box) || !reg1->alloc)
+		return;
+
+	atomic_sub(1 << (reg1->idx * 8), &er->ref);
+	reg1->alloc = 0;
+}
+
+static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
+
+	if (ev_sel >= 0xb && ev_sel <= 0xe) {
+		reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
+		reg1->idx = ev_sel - 0xb;
+		reg1->config = event->attr.config1 & (0xff << (reg1->idx * 8));
+	}
+	return 0;
+}
+
+static struct intel_uncore_ops snbep_uncore_pcu_ops = {
+	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= snbep_pcu_hw_config,
+	.get_constraint		= snbep_pcu_get_constraint,
+	.put_constraint		= snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type snbep_uncore_pcu = {
+	.name			= "pcu",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCU_MSR_PMON_CTR0,
+	.event_ctl		= SNBEP_PCU_MSR_PMON_CTL0,
+	.event_mask		= SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCU_MSR_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &snbep_uncore_pcu_ops,
+	.format_group		= &snbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *snbep_msr_uncores[] = {
+	&snbep_uncore_ubox,
+	&snbep_uncore_cbox,
+	&snbep_uncore_pcu,
+	NULL,
+};
+
+void snbep_uncore_cpu_init(void)
+{
+	if (snbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		snbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	uncore_msr_uncores = snbep_msr_uncores;
+}
+
+enum {
+	SNBEP_PCI_QPI_PORT0_FILTER,
+	SNBEP_PCI_QPI_PORT1_FILTER,
+};
+
+static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) {
+		reg1->idx = 0;
+		reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0;
+		reg1->config = event->attr.config1;
+		reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0;
+		reg2->config = event->attr.config2;
+	}
+	return 0;
+}
+
+static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
+		struct pci_dev *filter_pdev = uncore_extra_pci_dev[box->phys_id][idx];
+		if (filter_pdev) {
+			pci_write_config_dword(filter_pdev, reg1->reg,
+						(u32)reg1->config);
+			pci_write_config_dword(filter_pdev, reg1->reg + 4,
+						(u32)(reg1->config >> 32));
+			pci_write_config_dword(filter_pdev, reg2->reg,
+						(u32)reg2->config);
+			pci_write_config_dword(filter_pdev, reg2->reg + 4,
+						(u32)(reg2->config >> 32));
+		}
+	}
+
+	pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops snbep_uncore_qpi_ops = {
+	SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+	.enable_event		= snbep_qpi_enable_event,
+	.hw_config		= snbep_qpi_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
+#define SNBEP_UNCORE_PCI_COMMON_INIT()				\
+	.perf_ctr	= SNBEP_PCI_PMON_CTR0,			\
+	.event_ctl	= SNBEP_PCI_PMON_CTL0,			\
+	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,		\
+	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,		\
+	.ops		= &snbep_uncore_pci_ops,		\
+	.format_group	= &snbep_uncore_format_group
+
+static struct intel_uncore_type snbep_uncore_ha = {
+	.name		= "ha",
+	.num_counters   = 4,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_imc = {
+	.name		= "imc",
+	.num_counters   = 4,
+	.num_boxes	= 4,
+	.perf_ctr_bits	= 48,
+	.fixed_ctr_bits	= 48,
+	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+	.event_descs	= snbep_uncore_imc_events,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_qpi = {
+	.name			= "qpi",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
+	.event_ctl		= SNBEP_PCI_PMON_CTL0,
+	.event_mask		= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &snbep_uncore_qpi_ops,
+	.event_descs		= snbep_uncore_qpi_events,
+	.format_group		= &snbep_uncore_qpi_format_group,
+};
+
+
+static struct intel_uncore_type snbep_uncore_r2pcie = {
+	.name		= "r2pcie",
+	.num_counters   = 4,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 44,
+	.constraints	= snbep_uncore_r2pcie_constraints,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_r3qpi = {
+	.name		= "r3qpi",
+	.num_counters   = 3,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 44,
+	.constraints	= snbep_uncore_r3qpi_constraints,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+enum {
+	SNBEP_PCI_UNCORE_HA,
+	SNBEP_PCI_UNCORE_IMC,
+	SNBEP_PCI_UNCORE_QPI,
+	SNBEP_PCI_UNCORE_R2PCIE,
+	SNBEP_PCI_UNCORE_R3QPI,
+};
+
+static struct intel_uncore_type *snbep_pci_uncores[] = {
+	[SNBEP_PCI_UNCORE_HA]		= &snbep_uncore_ha,
+	[SNBEP_PCI_UNCORE_IMC]		= &snbep_uncore_imc,
+	[SNBEP_PCI_UNCORE_QPI]		= &snbep_uncore_qpi,
+	[SNBEP_PCI_UNCORE_R2PCIE]	= &snbep_uncore_r2pcie,
+	[SNBEP_PCI_UNCORE_R3QPI]	= &snbep_uncore_r3qpi,
+	NULL,
+};
+
+static const struct pci_device_id snbep_uncore_pci_ids[] = {
+	{ /* Home Agent */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0),
+	},
+	{ /* MC Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0),
+	},
+	{ /* MC Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1),
+	},
+	{ /* MC Channel 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2),
+	},
+	{ /* MC Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3),
+	},
+	{ /* QPI Port 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0),
+	},
+	{ /* QPI Port 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1),
+	},
+	{ /* R2PCIe */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0),
+	},
+	{ /* R3QPI Link 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0),
+	},
+	{ /* R3QPI Link 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT0_FILTER),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT1_FILTER),
+	},
+	{ /* end: all zeroes */ }
+};
+
+static struct pci_driver snbep_uncore_pci_driver = {
+	.name		= "snbep_uncore",
+	.id_table	= snbep_uncore_pci_ids,
+};
+
+/*
+ * build pci bus to socket mapping
+ */
+static int snbep_pci2phy_map_init(int devid)
+{
+	struct pci_dev *ubox_dev = NULL;
+	int i, bus, nodeid;
+	int err = 0;
+	u32 config = 0;
+
+	while (1) {
+		/* find the UBOX device */
+		ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev);
+		if (!ubox_dev)
+			break;
+		bus = ubox_dev->bus->number;
+		/* get the Node ID of the local register */
+		err = pci_read_config_dword(ubox_dev, 0x40, &config);
+		if (err)
+			break;
+		nodeid = config;
+		/* get the Node ID mapping */
+		err = pci_read_config_dword(ubox_dev, 0x54, &config);
+		if (err)
+			break;
+		/*
+		 * every three bits in the Node ID mapping register maps
+		 * to a particular node.
+		 */
+		for (i = 0; i < 8; i++) {
+			if (nodeid == ((config >> (3 * i)) & 0x7)) {
+				uncore_pcibus_to_physid[bus] = i;
+				break;
+			}
+		}
+	}
+
+	if (!err) {
+		/*
+		 * For PCI bus with no UBOX device, find the next bus
+		 * that has UBOX device and use its mapping.
+		 */
+		i = -1;
+		for (bus = 255; bus >= 0; bus--) {
+			if (uncore_pcibus_to_physid[bus] >= 0)
+				i = uncore_pcibus_to_physid[bus];
+			else
+				uncore_pcibus_to_physid[bus] = i;
+		}
+	}
+
+	if (ubox_dev)
+		pci_dev_put(ubox_dev);
+
+	return err ? pcibios_err_to_errno(err) : 0;
+}
+
+int snbep_uncore_pci_init(void)
+{
+	int ret = snbep_pci2phy_map_init(0x3ce0);
+	if (ret)
+		return ret;
+	uncore_pci_uncores = snbep_pci_uncores;
+	uncore_pci_driver = &snbep_uncore_pci_driver;
+	return 0;
+}
+/* end of Sandy Bridge-EP uncore support */
+
+/* IvyTown uncore support */
+static void ivbep_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+	if (msr)
+		wrmsrl(msr, IVBEP_PMON_BOX_CTL_INT);
+}
+
+static void ivbep_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+
+	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT);
+}
+
+#define IVBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
+	.init_box	= ivbep_uncore_msr_init_box,		\
+	.disable_box	= snbep_uncore_msr_disable_box,		\
+	.enable_box	= snbep_uncore_msr_enable_box,		\
+	.disable_event	= snbep_uncore_msr_disable_event,	\
+	.enable_event	= snbep_uncore_msr_enable_event,	\
+	.read_counter	= uncore_msr_read_counter
+
+static struct intel_uncore_ops ivbep_uncore_msr_ops = {
+	IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+};
+
+static struct intel_uncore_ops ivbep_uncore_pci_ops = {
+	.init_box	= ivbep_uncore_pci_init_box,
+	.disable_box	= snbep_uncore_pci_disable_box,
+	.enable_box	= snbep_uncore_pci_enable_box,
+	.disable_event	= snbep_uncore_pci_disable_event,
+	.enable_event	= snbep_uncore_pci_enable_event,
+	.read_counter	= snbep_uncore_pci_read_counter,
+};
+
+#define IVBEP_UNCORE_PCI_COMMON_INIT()				\
+	.perf_ctr	= SNBEP_PCI_PMON_CTR0,			\
+	.event_ctl	= SNBEP_PCI_PMON_CTL0,			\
+	.event_mask	= IVBEP_PMON_RAW_EVENT_MASK,		\
+	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,		\
+	.ops		= &ivbep_uncore_pci_ops,			\
+	.format_group	= &ivbep_uncore_format_group
+
+static struct attribute *ivbep_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute *ivbep_uncore_ubox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh5.attr,
+	NULL,
+};
+
+static struct attribute *ivbep_uncore_cbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_tid_en.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_filter_tid.attr,
+	&format_attr_filter_link.attr,
+	&format_attr_filter_state2.attr,
+	&format_attr_filter_nid2.attr,
+	&format_attr_filter_opc2.attr,
+	&format_attr_filter_nc.attr,
+	&format_attr_filter_c6.attr,
+	&format_attr_filter_isoc.attr,
+	NULL,
+};
+
+static struct attribute *ivbep_uncore_pcu_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_occ_sel.attr,
+	&format_attr_edge.attr,
+	&format_attr_thresh5.attr,
+	&format_attr_occ_invert.attr,
+	&format_attr_occ_edge.attr,
+	&format_attr_filter_band0.attr,
+	&format_attr_filter_band1.attr,
+	&format_attr_filter_band2.attr,
+	&format_attr_filter_band3.attr,
+	NULL,
+};
+
+static struct attribute *ivbep_uncore_qpi_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_match_rds.attr,
+	&format_attr_match_rnid30.attr,
+	&format_attr_match_rnid4.attr,
+	&format_attr_match_dnid.attr,
+	&format_attr_match_mc.attr,
+	&format_attr_match_opc.attr,
+	&format_attr_match_vnw.attr,
+	&format_attr_match0.attr,
+	&format_attr_match1.attr,
+	&format_attr_mask_rds.attr,
+	&format_attr_mask_rnid30.attr,
+	&format_attr_mask_rnid4.attr,
+	&format_attr_mask_dnid.attr,
+	&format_attr_mask_mc.attr,
+	&format_attr_mask_opc.attr,
+	&format_attr_mask_vnw.attr,
+	&format_attr_mask0.attr,
+	&format_attr_mask1.attr,
+	NULL,
+};
+
+static struct attribute_group ivbep_uncore_format_group = {
+	.name = "format",
+	.attrs = ivbep_uncore_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_ubox_format_group = {
+	.name = "format",
+	.attrs = ivbep_uncore_ubox_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_cbox_format_group = {
+	.name = "format",
+	.attrs = ivbep_uncore_cbox_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_pcu_format_group = {
+	.name = "format",
+	.attrs = ivbep_uncore_pcu_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_qpi_format_group = {
+	.name = "format",
+	.attrs = ivbep_uncore_qpi_formats_attr,
+};
+
+static struct intel_uncore_type ivbep_uncore_ubox = {
+	.name		= "ubox",
+	.num_counters   = 2,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 44,
+	.fixed_ctr_bits	= 48,
+	.perf_ctr	= SNBEP_U_MSR_PMON_CTR0,
+	.event_ctl	= SNBEP_U_MSR_PMON_CTL0,
+	.event_mask	= IVBEP_U_MSR_PMON_RAW_EVENT_MASK,
+	.fixed_ctr	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
+	.fixed_ctl	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
+	.ops		= &ivbep_uncore_msr_ops,
+	.format_group	= &ivbep_uncore_ubox_format_group,
+};
+
+static struct extra_reg ivbep_uncore_cbox_extra_regs[] = {
+	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8),
+	EVENT_EXTRA_END
+};
+
+static u64 ivbep_cbox_filter_mask(int fields)
+{
+	u64 mask = 0;
+
+	if (fields & 0x1)
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_TID;
+	if (fields & 0x2)
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK;
+	if (fields & 0x4)
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE;
+	if (fields & 0x8)
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_NID;
+	if (fields & 0x10) {
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC;
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_NC;
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_C6;
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_ISOC;
+	}
+
+	return mask;
+}
+
+static struct event_constraint *
+ivbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return __snbep_cbox_get_constraint(box, event, ivbep_cbox_filter_mask);
+}
+
+static int ivbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct extra_reg *er;
+	int idx = 0;
+
+	for (er = ivbep_uncore_cbox_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		idx |= er->idx;
+	}
+
+	if (idx) {
+		reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+		reg1->config = event->attr.config1 & ivbep_cbox_filter_mask(idx);
+		reg1->idx = idx;
+	}
+	return 0;
+}
+
+static void ivbep_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		u64 filter = uncore_shared_reg_config(box, 0);
+		wrmsrl(reg1->reg, filter & 0xffffffff);
+		wrmsrl(reg1->reg + 6, filter >> 32);
+	}
+
+	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops ivbep_uncore_cbox_ops = {
+	.init_box		= ivbep_uncore_msr_init_box,
+	.disable_box		= snbep_uncore_msr_disable_box,
+	.enable_box		= snbep_uncore_msr_enable_box,
+	.disable_event		= snbep_uncore_msr_disable_event,
+	.enable_event		= ivbep_cbox_enable_event,
+	.read_counter		= uncore_msr_read_counter,
+	.hw_config		= ivbep_cbox_hw_config,
+	.get_constraint		= ivbep_cbox_get_constraint,
+	.put_constraint		= snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type ivbep_uncore_cbox = {
+	.name			= "cbox",
+	.num_counters		= 4,
+	.num_boxes		= 15,
+	.perf_ctr_bits		= 44,
+	.event_ctl		= SNBEP_C0_MSR_PMON_CTL0,
+	.perf_ctr		= SNBEP_C0_MSR_PMON_CTR0,
+	.event_mask		= IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_C0_MSR_PMON_BOX_CTL,
+	.msr_offset		= SNBEP_CBO_MSR_OFFSET,
+	.num_shared_regs	= 1,
+	.constraints		= snbep_uncore_cbox_constraints,
+	.ops			= &ivbep_uncore_cbox_ops,
+	.format_group		= &ivbep_uncore_cbox_format_group,
+};
+
+static struct intel_uncore_ops ivbep_uncore_pcu_ops = {
+	IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= snbep_pcu_hw_config,
+	.get_constraint		= snbep_pcu_get_constraint,
+	.put_constraint		= snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type ivbep_uncore_pcu = {
+	.name			= "pcu",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCU_MSR_PMON_CTR0,
+	.event_ctl		= SNBEP_PCU_MSR_PMON_CTL0,
+	.event_mask		= IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCU_MSR_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &ivbep_uncore_pcu_ops,
+	.format_group		= &ivbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *ivbep_msr_uncores[] = {
+	&ivbep_uncore_ubox,
+	&ivbep_uncore_cbox,
+	&ivbep_uncore_pcu,
+	NULL,
+};
+
+void ivbep_uncore_cpu_init(void)
+{
+	if (ivbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		ivbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	uncore_msr_uncores = ivbep_msr_uncores;
+}
+
+static struct intel_uncore_type ivbep_uncore_ha = {
+	.name		= "ha",
+	.num_counters   = 4,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 48,
+	IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivbep_uncore_imc = {
+	.name		= "imc",
+	.num_counters   = 4,
+	.num_boxes	= 8,
+	.perf_ctr_bits	= 48,
+	.fixed_ctr_bits	= 48,
+	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+	.event_descs	= snbep_uncore_imc_events,
+	IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+/* registers in IRP boxes are not properly aligned */
+static unsigned ivbep_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4};
+static unsigned ivbep_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0};
+
+static void ivbep_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+
+	pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx],
+			       hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void ivbep_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+
+	pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx], hwc->config);
+}
+
+static u64 ivbep_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+	u64 count = 0;
+
+	pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx], (u32 *)&count);
+	pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1);
+
+	return count;
+}
+
+static struct intel_uncore_ops ivbep_uncore_irp_ops = {
+	.init_box	= ivbep_uncore_pci_init_box,
+	.disable_box	= snbep_uncore_pci_disable_box,
+	.enable_box	= snbep_uncore_pci_enable_box,
+	.disable_event	= ivbep_uncore_irp_disable_event,
+	.enable_event	= ivbep_uncore_irp_enable_event,
+	.read_counter	= ivbep_uncore_irp_read_counter,
+};
+
+static struct intel_uncore_type ivbep_uncore_irp = {
+	.name			= "irp",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.event_mask		= IVBEP_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
+	.ops			= &ivbep_uncore_irp_ops,
+	.format_group		= &ivbep_uncore_format_group,
+};
+
+static struct intel_uncore_ops ivbep_uncore_qpi_ops = {
+	.init_box	= ivbep_uncore_pci_init_box,
+	.disable_box	= snbep_uncore_pci_disable_box,
+	.enable_box	= snbep_uncore_pci_enable_box,
+	.disable_event	= snbep_uncore_pci_disable_event,
+	.enable_event	= snbep_qpi_enable_event,
+	.read_counter	= snbep_uncore_pci_read_counter,
+	.hw_config	= snbep_qpi_hw_config,
+	.get_constraint	= uncore_get_constraint,
+	.put_constraint	= uncore_put_constraint,
+};
+
+static struct intel_uncore_type ivbep_uncore_qpi = {
+	.name			= "qpi",
+	.num_counters		= 4,
+	.num_boxes		= 3,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
+	.event_ctl		= SNBEP_PCI_PMON_CTL0,
+	.event_mask		= IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &ivbep_uncore_qpi_ops,
+	.format_group		= &ivbep_uncore_qpi_format_group,
+};
+
+static struct intel_uncore_type ivbep_uncore_r2pcie = {
+	.name		= "r2pcie",
+	.num_counters   = 4,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 44,
+	.constraints	= snbep_uncore_r2pcie_constraints,
+	IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivbep_uncore_r3qpi = {
+	.name		= "r3qpi",
+	.num_counters   = 3,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 44,
+	.constraints	= snbep_uncore_r3qpi_constraints,
+	IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+enum {
+	IVBEP_PCI_UNCORE_HA,
+	IVBEP_PCI_UNCORE_IMC,
+	IVBEP_PCI_UNCORE_IRP,
+	IVBEP_PCI_UNCORE_QPI,
+	IVBEP_PCI_UNCORE_R2PCIE,
+	IVBEP_PCI_UNCORE_R3QPI,
+};
+
+static struct intel_uncore_type *ivbep_pci_uncores[] = {
+	[IVBEP_PCI_UNCORE_HA]	= &ivbep_uncore_ha,
+	[IVBEP_PCI_UNCORE_IMC]	= &ivbep_uncore_imc,
+	[IVBEP_PCI_UNCORE_IRP]	= &ivbep_uncore_irp,
+	[IVBEP_PCI_UNCORE_QPI]	= &ivbep_uncore_qpi,
+	[IVBEP_PCI_UNCORE_R2PCIE]	= &ivbep_uncore_r2pcie,
+	[IVBEP_PCI_UNCORE_R3QPI]	= &ivbep_uncore_r3qpi,
+	NULL,
+};
+
+static const struct pci_device_id ivbep_uncore_pci_ids[] = {
+	{ /* Home Agent 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 0),
+	},
+	{ /* Home Agent 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 1),
+	},
+	{ /* MC0 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 0),
+	},
+	{ /* MC0 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 1),
+	},
+	{ /* MC0 Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 2),
+	},
+	{ /* MC0 Channel 4 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 3),
+	},
+	{ /* MC1 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 4),
+	},
+	{ /* MC1 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 5),
+	},
+	{ /* MC1 Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 6),
+	},
+	{ /* MC1 Channel 4 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 7),
+	},
+	{ /* IRP */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IRP, 0),
+	},
+	{ /* QPI0 Port 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 0),
+	},
+	{ /* QPI0 Port 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 1),
+	},
+	{ /* QPI1 Port 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 2),
+	},
+	{ /* R2PCIe */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R2PCIE, 0),
+	},
+	{ /* R3QPI0 Link 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 0),
+	},
+	{ /* R3QPI0 Link 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 1),
+	},
+	{ /* R3QPI1 Link 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 2),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT0_FILTER),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT1_FILTER),
+	},
+	{ /* end: all zeroes */ }
+};
+
+static struct pci_driver ivbep_uncore_pci_driver = {
+	.name		= "ivbep_uncore",
+	.id_table	= ivbep_uncore_pci_ids,
+};
+
+int ivbep_uncore_pci_init(void)
+{
+	int ret = snbep_pci2phy_map_init(0x0e1e);
+	if (ret)
+		return ret;
+	uncore_pci_uncores = ivbep_pci_uncores;
+	uncore_pci_driver = &ivbep_uncore_pci_driver;
+	return 0;
+}
+/* end of IvyTown uncore support */
+
+/* Haswell-EP uncore support */
+static struct attribute *hswep_uncore_ubox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh5.attr,
+	&format_attr_filter_tid2.attr,
+	&format_attr_filter_cid.attr,
+	NULL,
+};
+
+static struct attribute_group hswep_uncore_ubox_format_group = {
+	.name = "format",
+	.attrs = hswep_uncore_ubox_formats_attr,
+};
+
+static int hswep_ubox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	reg1->reg = HSWEP_U_MSR_PMON_FILTER;
+	reg1->config = event->attr.config1 & HSWEP_U_MSR_PMON_BOX_FILTER_MASK;
+	reg1->idx = 0;
+	return 0;
+}
+
+static struct intel_uncore_ops hswep_uncore_ubox_ops = {
+	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= hswep_ubox_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
+static struct intel_uncore_type hswep_uncore_ubox = {
+	.name			= "ubox",
+	.num_counters		= 2,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 44,
+	.fixed_ctr_bits		= 48,
+	.perf_ctr		= HSWEP_U_MSR_PMON_CTR0,
+	.event_ctl		= HSWEP_U_MSR_PMON_CTL0,
+	.event_mask		= SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
+	.fixed_ctr		= HSWEP_U_MSR_PMON_UCLK_FIXED_CTR,
+	.fixed_ctl		= HSWEP_U_MSR_PMON_UCLK_FIXED_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &hswep_uncore_ubox_ops,
+	.format_group		= &hswep_uncore_ubox_format_group,
+};
+
+static struct attribute *hswep_uncore_cbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_tid_en.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_filter_tid3.attr,
+	&format_attr_filter_link2.attr,
+	&format_attr_filter_state3.attr,
+	&format_attr_filter_nid2.attr,
+	&format_attr_filter_opc2.attr,
+	&format_attr_filter_nc.attr,
+	&format_attr_filter_c6.attr,
+	&format_attr_filter_isoc.attr,
+	NULL,
+};
+
+static struct attribute_group hswep_uncore_cbox_format_group = {
+	.name = "format",
+	.attrs = hswep_uncore_cbox_formats_attr,
+};
+
+static struct event_constraint hswep_uncore_cbox_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x01, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x09, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x3b, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x3e, 0x1),
+	EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg hswep_uncore_cbox_extra_regs[] = {
+	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2134, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4028, 0x40ff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4032, 0x40ff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4029, 0x40ff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4033, 0x40ff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x402A, 0x40ff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x12),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8),
+	EVENT_EXTRA_END
+};
+
+static u64 hswep_cbox_filter_mask(int fields)
+{
+	u64 mask = 0;
+	if (fields & 0x1)
+		mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_TID;
+	if (fields & 0x2)
+		mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_LINK;
+	if (fields & 0x4)
+		mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_STATE;
+	if (fields & 0x8)
+		mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_NID;
+	if (fields & 0x10) {
+		mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_OPC;
+		mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_NC;
+		mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_C6;
+		mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_ISOC;
+	}
+	return mask;
+}
+
+static struct event_constraint *
+hswep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return __snbep_cbox_get_constraint(box, event, hswep_cbox_filter_mask);
+}
+
+static int hswep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct extra_reg *er;
+	int idx = 0;
+
+	for (er = hswep_uncore_cbox_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		idx |= er->idx;
+	}
+
+	if (idx) {
+		reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 +
+			    HSWEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+		reg1->config = event->attr.config1 & hswep_cbox_filter_mask(idx);
+		reg1->idx = idx;
+	}
+	return 0;
+}
+
+static void hswep_cbox_enable_event(struct intel_uncore_box *box,
+				  struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		u64 filter = uncore_shared_reg_config(box, 0);
+		wrmsrl(reg1->reg, filter & 0xffffffff);
+		wrmsrl(reg1->reg + 1, filter >> 32);
+	}
+
+	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops hswep_uncore_cbox_ops = {
+	.init_box		= snbep_uncore_msr_init_box,
+	.disable_box		= snbep_uncore_msr_disable_box,
+	.enable_box		= snbep_uncore_msr_enable_box,
+	.disable_event		= snbep_uncore_msr_disable_event,
+	.enable_event		= hswep_cbox_enable_event,
+	.read_counter		= uncore_msr_read_counter,
+	.hw_config		= hswep_cbox_hw_config,
+	.get_constraint		= hswep_cbox_get_constraint,
+	.put_constraint		= snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type hswep_uncore_cbox = {
+	.name			= "cbox",
+	.num_counters		= 4,
+	.num_boxes		= 18,
+	.perf_ctr_bits		= 44,
+	.event_ctl		= HSWEP_C0_MSR_PMON_CTL0,
+	.perf_ctr		= HSWEP_C0_MSR_PMON_CTR0,
+	.event_mask		= SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= HSWEP_C0_MSR_PMON_BOX_CTL,
+	.msr_offset		= HSWEP_CBO_MSR_OFFSET,
+	.num_shared_regs	= 1,
+	.constraints		= hswep_uncore_cbox_constraints,
+	.ops			= &hswep_uncore_cbox_ops,
+	.format_group		= &hswep_uncore_cbox_format_group,
+};
+
+static struct attribute *hswep_uncore_sbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_tid_en.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute_group hswep_uncore_sbox_format_group = {
+	.name = "format",
+	.attrs = hswep_uncore_sbox_formats_attr,
+};
+
+static struct intel_uncore_type hswep_uncore_sbox = {
+	.name			= "sbox",
+	.num_counters		= 4,
+	.num_boxes		= 4,
+	.perf_ctr_bits		= 44,
+	.event_ctl		= HSWEP_S0_MSR_PMON_CTL0,
+	.perf_ctr		= HSWEP_S0_MSR_PMON_CTR0,
+	.event_mask		= HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= HSWEP_S0_MSR_PMON_BOX_CTL,
+	.msr_offset		= HSWEP_SBOX_MSR_OFFSET,
+	.ops			= &snbep_uncore_msr_ops,
+	.format_group		= &hswep_uncore_sbox_format_group,
+};
+
+static int hswep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
+
+	if (ev_sel >= 0xb && ev_sel <= 0xe) {
+		reg1->reg = HSWEP_PCU_MSR_PMON_BOX_FILTER;
+		reg1->idx = ev_sel - 0xb;
+		reg1->config = event->attr.config1 & (0xff << reg1->idx);
+	}
+	return 0;
+}
+
+static struct intel_uncore_ops hswep_uncore_pcu_ops = {
+	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= hswep_pcu_hw_config,
+	.get_constraint		= snbep_pcu_get_constraint,
+	.put_constraint		= snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type hswep_uncore_pcu = {
+	.name			= "pcu",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= HSWEP_PCU_MSR_PMON_CTR0,
+	.event_ctl		= HSWEP_PCU_MSR_PMON_CTL0,
+	.event_mask		= SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= HSWEP_PCU_MSR_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &hswep_uncore_pcu_ops,
+	.format_group		= &snbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *hswep_msr_uncores[] = {
+	&hswep_uncore_ubox,
+	&hswep_uncore_cbox,
+	&hswep_uncore_sbox,
+	&hswep_uncore_pcu,
+	NULL,
+};
+
+void hswep_uncore_cpu_init(void)
+{
+	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	uncore_msr_uncores = hswep_msr_uncores;
+}
+
+static struct intel_uncore_type hswep_uncore_ha = {
+	.name		= "ha",
+	.num_counters   = 5,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 48,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct uncore_event_desc hswep_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0x00,umask=0x00"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read,  "event=0x04,umask=0x03"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type hswep_uncore_imc = {
+	.name		= "imc",
+	.num_counters   = 5,
+	.num_boxes	= 8,
+	.perf_ctr_bits	= 48,
+	.fixed_ctr_bits	= 48,
+	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+	.event_descs	= hswep_uncore_imc_events,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_ops hswep_uncore_irp_ops = {
+	.init_box	= snbep_uncore_pci_init_box,
+	.disable_box	= snbep_uncore_pci_disable_box,
+	.enable_box	= snbep_uncore_pci_enable_box,
+	.disable_event	= ivbep_uncore_irp_disable_event,
+	.enable_event	= ivbep_uncore_irp_enable_event,
+	.read_counter	= ivbep_uncore_irp_read_counter,
+};
+
+static struct intel_uncore_type hswep_uncore_irp = {
+	.name			= "irp",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.event_mask		= SNBEP_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
+	.ops			= &hswep_uncore_irp_ops,
+	.format_group		= &snbep_uncore_format_group,
+};
+
+static struct intel_uncore_type hswep_uncore_qpi = {
+	.name			= "qpi",
+	.num_counters		= 5,
+	.num_boxes		= 3,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
+	.event_ctl		= SNBEP_PCI_PMON_CTL0,
+	.event_mask		= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &snbep_uncore_qpi_ops,
+	.format_group		= &snbep_uncore_qpi_format_group,
+};
+
+static struct event_constraint hswep_uncore_r2pcie_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x24, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x25, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x27, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2a, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x2b, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x35, 0x3),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type hswep_uncore_r2pcie = {
+	.name		= "r2pcie",
+	.num_counters   = 4,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	.constraints	= hswep_uncore_r2pcie_constraints,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct event_constraint hswep_uncore_r3qpi_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x01, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x07, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x08, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x09, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x0a, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x0e, 0x7),
+	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x14, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x15, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x1f, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type hswep_uncore_r3qpi = {
+	.name		= "r3qpi",
+	.num_counters   = 4,
+	.num_boxes	= 3,
+	.perf_ctr_bits	= 44,
+	.constraints	= hswep_uncore_r3qpi_constraints,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+enum {
+	HSWEP_PCI_UNCORE_HA,
+	HSWEP_PCI_UNCORE_IMC,
+	HSWEP_PCI_UNCORE_IRP,
+	HSWEP_PCI_UNCORE_QPI,
+	HSWEP_PCI_UNCORE_R2PCIE,
+	HSWEP_PCI_UNCORE_R3QPI,
+};
+
+static struct intel_uncore_type *hswep_pci_uncores[] = {
+	[HSWEP_PCI_UNCORE_HA]	= &hswep_uncore_ha,
+	[HSWEP_PCI_UNCORE_IMC]	= &hswep_uncore_imc,
+	[HSWEP_PCI_UNCORE_IRP]	= &hswep_uncore_irp,
+	[HSWEP_PCI_UNCORE_QPI]	= &hswep_uncore_qpi,
+	[HSWEP_PCI_UNCORE_R2PCIE]	= &hswep_uncore_r2pcie,
+	[HSWEP_PCI_UNCORE_R3QPI]	= &hswep_uncore_r3qpi,
+	NULL,
+};
+
+static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = {
+	{ /* Home Agent 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f30),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 0),
+	},
+	{ /* Home Agent 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f38),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 1),
+	},
+	{ /* MC0 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb0),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 0),
+	},
+	{ /* MC0 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb1),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 1),
+	},
+	{ /* MC0 Channel 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb4),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 2),
+	},
+	{ /* MC0 Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb5),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 3),
+	},
+	{ /* MC1 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd0),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 4),
+	},
+	{ /* MC1 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd1),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 5),
+	},
+	{ /* MC1 Channel 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd4),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 6),
+	},
+	{ /* MC1 Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd5),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 7),
+	},
+	{ /* IRP */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f39),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IRP, 0),
+	},
+	{ /* QPI0 Port 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f32),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 0),
+	},
+	{ /* QPI0 Port 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f33),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 1),
+	},
+	{ /* QPI1 Port 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f3a),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 2),
+	},
+	{ /* R2PCIe */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f34),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R2PCIE, 0),
+	},
+	{ /* R3QPI0 Link 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f36),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 0),
+	},
+	{ /* R3QPI0 Link 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f37),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 1),
+	},
+	{ /* R3QPI1 Link 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f3e),
+		.driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 2),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f86),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT0_FILTER),
+	},
+	{ /* QPI Port 1 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f96),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT1_FILTER),
+	},
+	{ /* end: all zeroes */ }
+};
+
+static struct pci_driver hswep_uncore_pci_driver = {
+	.name		= "hswep_uncore",
+	.id_table	= hswep_uncore_pci_ids,
+};
+
+int hswep_uncore_pci_init(void)
+{
+	int ret = snbep_pci2phy_map_init(0x2f1e);
+	if (ret)
+		return ret;
+	uncore_pci_uncores = hswep_pci_uncores;
+	uncore_pci_driver = &hswep_uncore_pci_driver;
+	return 0;
+}
+/* end of Haswell-EP uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
index 838fa8772c62..5b0c232d1ee6 100644
--- a/arch/x86/kernel/cpu/perf_event_knc.c
+++ b/arch/x86/kernel/cpu/perf_event_knc.c
@@ -217,7 +217,7 @@ static int knc_pmu_handle_irq(struct pt_regs *regs)
 	int bit, loops;
 	u64 status;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	knc_pmu_disable_all();
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 5d466b7d8609..f2e56783af3d 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -915,7 +915,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
 
 static void p4_pmu_disable_all(void)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -984,7 +984,7 @@ static void p4_pmu_enable_event(struct perf_event *event)
 
 static void p4_pmu_enable_all(int added)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -1004,7 +1004,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		int overflow;
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index a618fcd2c07d..f5ab56d14287 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -237,7 +237,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced,
 	ced->max_nr_ranges++;
 
 	/* If crashk_low_res is not 0, another range split possible */
-	if (crashk_low_res.end != 0)
+	if (crashk_low_res.end)
 		ced->max_nr_ranges++;
 }
 
@@ -335,9 +335,11 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced,
 	if (ret)
 		return ret;
 
-	ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
-	if (ret)
-		return ret;
+	if (crashk_low_res.end) {
+		ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
+		if (ret)
+			return ret;
+	}
 
 	/* Exclude GART region */
 	if (ced->gart_end) {
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 988c00a1f60d..49f886481615 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -682,15 +682,14 @@ void __init parse_e820_ext(u64 phys_addr, u32 data_len)
  * hibernation (32 bit) or software suspend and suspend to RAM (64 bit).
  *
  * This function requires the e820 map to be sorted and without any
- * overlapping entries and assumes the first e820 area to be RAM.
+ * overlapping entries.
  */
 void __init e820_mark_nosave_regions(unsigned long limit_pfn)
 {
 	int i;
-	unsigned long pfn;
+	unsigned long pfn = 0;
 
-	pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size);
-	for (i = 1; i < e820.nr_map; i++) {
+	for (i = 0; i < e820.nr_map; i++) {
 		struct e820entry *ei = &e820.map[i];
 
 		if (pfn < PFN_UP(ei->addr))
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 2fac1343a90b..df088bb03fb3 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -404,8 +404,8 @@ GLOBAL(system_call_after_swapgs)
 	 * and short:
 	 */
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	SAVE_ARGS 8,0
-	movq  %rax,ORIG_RAX-ARGOFFSET(%rsp)
+	SAVE_ARGS 8, 0, rax_enosys=1
+	movq_cfi rax,(ORIG_RAX-ARGOFFSET)
 	movq  %rcx,RIP-ARGOFFSET(%rsp)
 	CFI_REL_OFFSET rip,RIP-ARGOFFSET
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
@@ -417,7 +417,7 @@ system_call_fastpath:
 	andl $__SYSCALL_MASK,%eax
 	cmpl $__NR_syscall_max,%eax
 #endif
-	ja badsys
+	ja ret_from_sys_call  /* and return regs->ax */
 	movq %r10,%rcx
 	call *sys_call_table(,%rax,8)  # XXX:	 rip relative
 	movq %rax,RAX-ARGOFFSET(%rsp)
@@ -476,28 +476,8 @@ sysret_signal:
 	FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
 	jmp int_check_syscall_exit_work
 
-badsys:
-	movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
-	jmp ret_from_sys_call
-
 #ifdef CONFIG_AUDITSYSCALL
 	/*
-	 * Fast path for syscall audit without full syscall trace.
-	 * We just call __audit_syscall_entry() directly, and then
-	 * jump back to the normal fast path.
-	 */
-auditsys:
-	movq %r10,%r9			/* 6th arg: 4th syscall arg */
-	movq %rdx,%r8			/* 5th arg: 3rd syscall arg */
-	movq %rsi,%rcx			/* 4th arg: 2nd syscall arg */
-	movq %rdi,%rdx			/* 3rd arg: 1st syscall arg */
-	movq %rax,%rsi			/* 2nd arg: syscall number */
-	movl $AUDIT_ARCH_X86_64,%edi	/* 1st arg: audit arch */
-	call __audit_syscall_entry
-	LOAD_ARGS 0		/* reload call-clobbered registers */
-	jmp system_call_fastpath
-
-	/*
 	 * Return fast path for syscall audit.  Call __audit_syscall_exit()
 	 * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT
 	 * masked off.
@@ -514,18 +494,25 @@ sysret_audit:
 
 	/* Do syscall tracing */
 tracesys:
-#ifdef CONFIG_AUDITSYSCALL
-	testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
-	jz auditsys
-#endif
+	leaq -REST_SKIP(%rsp), %rdi
+	movq $AUDIT_ARCH_X86_64, %rsi
+	call syscall_trace_enter_phase1
+	test %rax, %rax
+	jnz tracesys_phase2		/* if needed, run the slow path */
+	LOAD_ARGS 0			/* else restore clobbered regs */
+	jmp system_call_fastpath	/*      and return to the fast path */
+
+tracesys_phase2:
 	SAVE_REST
-	movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
 	FIXUP_TOP_OF_STACK %rdi
-	movq %rsp,%rdi
-	call syscall_trace_enter
+	movq %rsp, %rdi
+	movq $AUDIT_ARCH_X86_64, %rsi
+	movq %rax,%rdx
+	call syscall_trace_enter_phase2
+
 	/*
 	 * Reload arg registers from stack in case ptrace changed them.
-	 * We don't reload %rax because syscall_trace_enter() returned
+	 * We don't reload %rax because syscall_trace_entry_phase2() returned
 	 * the value it wants us to use in the table lookup.
 	 */
 	LOAD_ARGS ARGOFFSET, 1
@@ -536,7 +523,7 @@ tracesys:
 	andl $__SYSCALL_MASK,%eax
 	cmpl $__NR_syscall_max,%eax
 #endif
-	ja   int_ret_from_sys_call	/* RAX(%rsp) set to -ENOSYS above */
+	ja   int_ret_from_sys_call	/* RAX(%rsp) is already set */
 	movq %r10,%rcx	/* fixup for C */
 	call *sys_call_table(,%rax,8)
 	movq %rax,RAX-ARGOFFSET(%rsp)
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 5f9cf20cdb68..3d5fb509bdeb 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -108,7 +108,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	int i;
 
 	for (i = 0; i < HBP_NUM; i++) {
-		struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]);
+		struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]);
 
 		if (!*slot) {
 			*slot = bp;
@@ -122,7 +122,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	set_debugreg(info->address, i);
 	__this_cpu_write(cpu_debugreg[i], info->address);
 
-	dr7 = &__get_cpu_var(cpu_dr7);
+	dr7 = this_cpu_ptr(&cpu_dr7);
 	*dr7 |= encode_dr7(i, info->len, info->type);
 
 	set_debugreg(*dr7, 7);
@@ -146,7 +146,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	int i;
 
 	for (i = 0; i < HBP_NUM; i++) {
-		struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]);
+		struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]);
 
 		if (*slot == bp) {
 			*slot = NULL;
@@ -157,7 +157,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot"))
 		return;
 
-	dr7 = &__get_cpu_var(cpu_dr7);
+	dr7 = this_cpu_ptr(&cpu_dr7);
 	*dr7 &= ~__encode_dr7(i, info->len, info->type);
 
 	set_debugreg(*dr7, 7);
diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c
index 9030e83db6ee..82f8d02f0df2 100644
--- a/arch/x86/kernel/iosf_mbi.c
+++ b/arch/x86/kernel/iosf_mbi.c
@@ -22,10 +22,13 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/pci.h>
+#include <linux/debugfs.h>
+#include <linux/capability.h>
 
 #include <asm/iosf_mbi.h>
 
 #define PCI_DEVICE_ID_BAYTRAIL		0x0F00
+#define PCI_DEVICE_ID_BRASWELL		0x2280
 #define PCI_DEVICE_ID_QUARK_X1000	0x0958
 
 static DEFINE_SPINLOCK(iosf_mbi_lock);
@@ -187,6 +190,89 @@ bool iosf_mbi_available(void)
 }
 EXPORT_SYMBOL(iosf_mbi_available);
 
+#ifdef CONFIG_IOSF_MBI_DEBUG
+static u32	dbg_mdr;
+static u32	dbg_mcr;
+static u32	dbg_mcrx;
+
+static int mcr_get(void *data, u64 *val)
+{
+	*val = *(u32 *)data;
+	return 0;
+}
+
+static int mcr_set(void *data, u64 val)
+{
+	u8 command = ((u32)val & 0xFF000000) >> 24,
+	   port	   = ((u32)val & 0x00FF0000) >> 16,
+	   offset  = ((u32)val & 0x0000FF00) >> 8;
+	int err;
+
+	*(u32 *)data = val;
+
+	if (!capable(CAP_SYS_RAWIO))
+		return -EACCES;
+
+	if (command & 1u)
+		err = iosf_mbi_write(port,
+			       command,
+			       dbg_mcrx | offset,
+			       dbg_mdr);
+	else
+		err = iosf_mbi_read(port,
+			      command,
+			      dbg_mcrx | offset,
+			      &dbg_mdr);
+
+	return err;
+}
+DEFINE_SIMPLE_ATTRIBUTE(iosf_mcr_fops, mcr_get, mcr_set , "%llx\n");
+
+static struct dentry *iosf_dbg;
+
+static void iosf_sideband_debug_init(void)
+{
+	struct dentry *d;
+
+	iosf_dbg = debugfs_create_dir("iosf_sb", NULL);
+	if (IS_ERR_OR_NULL(iosf_dbg))
+		return;
+
+	/* mdr */
+	d = debugfs_create_x32("mdr", 0660, iosf_dbg, &dbg_mdr);
+	if (IS_ERR_OR_NULL(d))
+		goto cleanup;
+
+	/* mcrx */
+	debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx);
+	if (IS_ERR_OR_NULL(d))
+		goto cleanup;
+
+	/* mcr - initiates mailbox tranaction */
+	debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops);
+	if (IS_ERR_OR_NULL(d))
+		goto cleanup;
+
+	return;
+
+cleanup:
+	debugfs_remove_recursive(d);
+}
+
+static void iosf_debugfs_init(void)
+{
+	iosf_sideband_debug_init();
+}
+
+static void iosf_debugfs_remove(void)
+{
+	debugfs_remove_recursive(iosf_dbg);
+}
+#else
+static inline void iosf_debugfs_init(void) { }
+static inline void iosf_debugfs_remove(void) { }
+#endif /* CONFIG_IOSF_MBI_DEBUG */
+
 static int iosf_mbi_probe(struct pci_dev *pdev,
 			  const struct pci_device_id *unused)
 {
@@ -204,6 +290,7 @@ static int iosf_mbi_probe(struct pci_dev *pdev,
 
 static const struct pci_device_id iosf_mbi_pci_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) },
 	{ 0, },
 };
@@ -217,11 +304,15 @@ static struct pci_driver iosf_mbi_pci_driver = {
 
 static int __init iosf_mbi_init(void)
 {
+	iosf_debugfs_init();
+
 	return pci_register_driver(&iosf_mbi_pci_driver);
 }
 
 static void __exit iosf_mbi_exit(void)
 {
+	iosf_debugfs_remove();
+
 	pci_unregister_driver(&iosf_mbi_pci_driver);
 	if (mbi_pdev) {
 		pci_dev_put(mbi_pdev);
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 4d1c746892eb..e4b503d5558c 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -52,13 +52,13 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 	    regs->sp <= curbase + THREAD_SIZE)
 		return;
 
-	irq_stack_top = (u64)__get_cpu_var(irq_stack_union.irq_stack) +
+	irq_stack_top = (u64)this_cpu_ptr(irq_stack_union.irq_stack) +
 			STACK_TOP_MARGIN;
-	irq_stack_bottom = (u64)__get_cpu_var(irq_stack_ptr);
+	irq_stack_bottom = (u64)__this_cpu_read(irq_stack_ptr);
 	if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
 		return;
 
-	oist = &__get_cpu_var(orig_ist);
+	oist = this_cpu_ptr(&orig_ist);
 	estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
 	estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
 	if (regs->sp >= estack_top && regs->sp <= estack_bottom)
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index 1de84e3ab4e0..15d741ddfeeb 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -41,7 +41,7 @@ __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
 void arch_irq_work_raise(void)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
-	if (!cpu_has_apic)
+	if (!arch_irq_work_has_interrupt())
 		return;
 
 	apic->send_IPI_self(IRQ_WORK_VECTOR);
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 9642b9b33655..ca05f86481aa 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -26,6 +26,7 @@
 #include <asm/setup.h>
 #include <asm/crash.h>
 #include <asm/efi.h>
+#include <asm/kexec-bzimage64.h>
 
 #define MAX_ELFCOREHDR_STR_LEN	30	/* elfcorehdr=0x<64bit-value> */
 
@@ -267,7 +268,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
 	return ret;
 }
 
-int bzImage64_probe(const char *buf, unsigned long len)
+static int bzImage64_probe(const char *buf, unsigned long len)
 {
 	int ret = -ENOEXEC;
 	struct setup_header *header;
@@ -325,10 +326,10 @@ int bzImage64_probe(const char *buf, unsigned long len)
 	return ret;
 }
 
-void *bzImage64_load(struct kimage *image, char *kernel,
-		     unsigned long kernel_len, char *initrd,
-		     unsigned long initrd_len, char *cmdline,
-		     unsigned long cmdline_len)
+static void *bzImage64_load(struct kimage *image, char *kernel,
+			    unsigned long kernel_len, char *initrd,
+			    unsigned long initrd_len, char *cmdline,
+			    unsigned long cmdline_len)
 {
 
 	struct setup_header *header;
@@ -514,7 +515,7 @@ out_free_params:
 }
 
 /* This cleanup function is called after various segments have been loaded */
-int bzImage64_cleanup(void *loader_data)
+static int bzImage64_cleanup(void *loader_data)
 {
 	struct bzimage64_data *ldata = loader_data;
 
@@ -528,7 +529,7 @@ int bzImage64_cleanup(void *loader_data)
 }
 
 #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG
-int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
+static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
 {
 	bool trusted;
 	int ret;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 3dd8e2c4d74a..f6945bef2cd1 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/kprobes.h>
 #include <linux/debugfs.h>
+#include <linux/nmi.h>
 #include <asm/timer.h>
 #include <asm/cpu.h>
 #include <asm/traps.h>
@@ -243,9 +244,9 @@ u32 kvm_read_and_reset_pf_reason(void)
 {
 	u32 reason = 0;
 
-	if (__get_cpu_var(apf_reason).enabled) {
-		reason = __get_cpu_var(apf_reason).reason;
-		__get_cpu_var(apf_reason).reason = 0;
+	if (__this_cpu_read(apf_reason.enabled)) {
+		reason = __this_cpu_read(apf_reason.reason);
+		__this_cpu_write(apf_reason.reason, 0);
 	}
 
 	return reason;
@@ -318,7 +319,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val)
 	 * there's no need for lock or memory barriers.
 	 * An optimization barrier is implied in apic write.
 	 */
-	if (__test_and_clear_bit(KVM_PV_EOI_BIT, &__get_cpu_var(kvm_apic_eoi)))
+	if (__test_and_clear_bit(KVM_PV_EOI_BIT, this_cpu_ptr(&kvm_apic_eoi)))
 		return;
 	apic_write(APIC_EOI, APIC_EOI_ACK);
 }
@@ -329,13 +330,13 @@ void kvm_guest_cpu_init(void)
 		return;
 
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
-		u64 pa = slow_virt_to_phys(&__get_cpu_var(apf_reason));
+		u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
 
 #ifdef CONFIG_PREEMPT
 		pa |= KVM_ASYNC_PF_SEND_ALWAYS;
 #endif
 		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
-		__get_cpu_var(apf_reason).enabled = 1;
+		__this_cpu_write(apf_reason.enabled, 1);
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
 		       smp_processor_id());
 	}
@@ -344,8 +345,8 @@ void kvm_guest_cpu_init(void)
 		unsigned long pa;
 		/* Size alignment is implied but just to make it explicit. */
 		BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4);
-		__get_cpu_var(kvm_apic_eoi) = 0;
-		pa = slow_virt_to_phys(&__get_cpu_var(kvm_apic_eoi))
+		__this_cpu_write(kvm_apic_eoi, 0);
+		pa = slow_virt_to_phys(this_cpu_ptr(&kvm_apic_eoi))
 			| KVM_MSR_ENABLED;
 		wrmsrl(MSR_KVM_PV_EOI_EN, pa);
 	}
@@ -356,11 +357,11 @@ void kvm_guest_cpu_init(void)
 
 static void kvm_pv_disable_apf(void)
 {
-	if (!__get_cpu_var(apf_reason).enabled)
+	if (!__this_cpu_read(apf_reason.enabled))
 		return;
 
 	wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
-	__get_cpu_var(apf_reason).enabled = 0;
+	__this_cpu_write(apf_reason.enabled, 0);
 
 	printk(KERN_INFO"Unregister pv shared memory for cpu %d\n",
 	       smp_processor_id());
@@ -499,6 +500,13 @@ void __init kvm_guest_init(void)
 #else
 	kvm_guest_cpu_init();
 #endif
+
+	/*
+	 * Hard lockup detection is enabled by default. Disable it, as guests
+	 * can get false positives too easily, for example if the host is
+	 * overcommitted.
+	 */
+	watchdog_enable_hardlockup_detector(false);
 }
 
 static noinline uint32_t __kvm_cpuid_base(void)
@@ -716,7 +724,7 @@ __visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 	if (in_nmi())
 		return;
 
-	w = &__get_cpu_var(klock_waiting);
+	w = this_cpu_ptr(&klock_waiting);
 	cpu = smp_processor_id();
 	start = spin_time_start();
 
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 1667b1de8d5d..72e8e310258d 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -247,7 +247,8 @@ void machine_kexec(struct kimage *image)
 	/* now call it */
 	image->start = relocate_kernel_ptr((unsigned long)image->head,
 					   (unsigned long)page_list,
-					   image->start, cpu_has_pae,
+					   image->start,
+					   boot_cpu_has(X86_FEATURE_PAE),
 					   image->preserve_context);
 
 #ifdef CONFIG_KEXEC_JUMP
diff --git a/arch/x86/kernel/pmc_atom.c b/arch/x86/kernel/pmc_atom.c
index 0c424a67985d..0ee5025e0fa4 100644
--- a/arch/x86/kernel/pmc_atom.c
+++ b/arch/x86/kernel/pmc_atom.c
@@ -235,6 +235,11 @@ err:
 	pmc_dbgfs_unregister(pmc);
 	return -ENODEV;
 }
+#else
+static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev)
+{
+	return 0;
+}
 #endif /* CONFIG_DEBUG_FS */
 
 static int pmc_setup_dev(struct pci_dev *pdev)
@@ -262,14 +267,12 @@ static int pmc_setup_dev(struct pci_dev *pdev)
 	/* PMC hardware registers setup */
 	pmc_hw_reg_setup(pmc);
 
-#ifdef CONFIG_DEBUG_FS
 	ret = pmc_dbgfs_register(pmc, pdev);
 	if (ret) {
 		iounmap(pmc->regmap);
-		return ret;
 	}
-#endif /* CONFIG_DEBUG_FS */
-	return 0;
+
+	return ret;
 }
 
 /*
diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S
deleted file mode 100644
index ca7f0d58a87d..000000000000
--- a/arch/x86/kernel/preempt.S
+++ /dev/null
@@ -1,25 +0,0 @@
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/asm.h>
-#include <asm/calling.h>
-
-ENTRY(___preempt_schedule)
-	CFI_STARTPROC
-	SAVE_ALL
-	call preempt_schedule
-	RESTORE_ALL
-	ret
-	CFI_ENDPROC
-
-#ifdef CONFIG_CONTEXT_TRACKING
-
-ENTRY(___preempt_schedule_context)
-	CFI_STARTPROC
-	SAVE_ALL
-	call preempt_schedule_context
-	RESTORE_ALL
-	ret
-	CFI_ENDPROC
-
-#endif
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f804dc935d2a..e127ddaa2d5a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -64,14 +64,16 @@ EXPORT_SYMBOL_GPL(task_xstate_cachep);
  */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	int ret;
-
 	*dst = *src;
-	if (fpu_allocated(&src->thread.fpu)) {
-		memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu));
-		ret = fpu_alloc(&dst->thread.fpu);
-		if (ret)
-			return ret;
+
+	dst->thread.fpu_counter = 0;
+	dst->thread.fpu.has_fpu = 0;
+	dst->thread.fpu.last_cpu = ~0;
+	dst->thread.fpu.state = NULL;
+	if (tsk_used_math(src)) {
+		int err = fpu_alloc(&dst->thread.fpu);
+		if (err)
+			return err;
 		fpu_copy(dst, src);
 	}
 	return 0;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 7bc86bbe7485..8f3ebfe710d0 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -138,6 +138,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	p->thread.sp = (unsigned long) childregs;
 	p->thread.sp0 = (unsigned long) (childregs+1);
+	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
 
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		/* kernel thread */
@@ -152,9 +153,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		childregs->orig_ax = -1;
 		childregs->cs = __KERNEL_CS | get_kernel_rpl();
 		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
-		p->thread.fpu_counter = 0;
 		p->thread.io_bitmap_ptr = NULL;
-		memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
 		return 0;
 	}
 	*childregs = *current_pt_regs();
@@ -165,13 +164,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	p->thread.ip = (unsigned long) ret_from_fork;
 	task_user_gs(p) = get_user_gs(current_pt_regs());
 
-	p->thread.fpu_counter = 0;
 	p->thread.io_bitmap_ptr = NULL;
 	tsk = current;
 	err = -ENOMEM;
 
-	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
-
 	if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
 		p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
 						IO_BITMAP_BYTES, GFP_KERNEL);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ca5b02d405c3..3ed4a68d4013 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -163,7 +163,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	p->thread.sp = (unsigned long) childregs;
 	p->thread.usersp = me->thread.usersp;
 	set_tsk_thread_flag(p, TIF_FORK);
-	p->thread.fpu_counter = 0;
 	p->thread.io_bitmap_ptr = NULL;
 
 	savesegment(gs, p->thread.gsindex);
@@ -193,8 +192,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		childregs->sp = sp;
 
 	err = -ENOMEM;
-	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
-
 	if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
 		p->thread.io_bitmap_ptr = kmemdup(me->thread.io_bitmap_ptr,
 						  IO_BITMAP_BYTES, GFP_KERNEL);
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 678c0ada3b3c..29576c244699 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1441,24 +1441,126 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 	force_sig_info(SIGTRAP, &info, tsk);
 }
 
-
-#ifdef CONFIG_X86_32
-# define IS_IA32	1
-#elif defined CONFIG_IA32_EMULATION
-# define IS_IA32	is_compat_task()
-#else
-# define IS_IA32	0
+static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
+{
+#ifdef CONFIG_X86_64
+	if (arch == AUDIT_ARCH_X86_64) {
+		audit_syscall_entry(arch, regs->orig_ax, regs->di,
+				    regs->si, regs->dx, regs->r10);
+	} else
 #endif
+	{
+		audit_syscall_entry(arch, regs->orig_ax, regs->bx,
+				    regs->cx, regs->dx, regs->si);
+	}
+}
 
 /*
- * We must return the syscall number to actually look up in the table.
- * This can be -1L to skip running any syscall at all.
+ * We can return 0 to resume the syscall or anything else to go to phase
+ * 2.  If we resume the syscall, we need to put something appropriate in
+ * regs->orig_ax.
+ *
+ * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax
+ * are fully functional.
+ *
+ * For phase 2's benefit, our return value is:
+ * 0:			resume the syscall
+ * 1:			go to phase 2; no seccomp phase 2 needed
+ * anything else:	go to phase 2; pass return value to seccomp
  */
-long syscall_trace_enter(struct pt_regs *regs)
+unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
+{
+	unsigned long ret = 0;
+	u32 work;
+
+	BUG_ON(regs != task_pt_regs(current));
+
+	work = ACCESS_ONCE(current_thread_info()->flags) &
+		_TIF_WORK_SYSCALL_ENTRY;
+
+	/*
+	 * If TIF_NOHZ is set, we are required to call user_exit() before
+	 * doing anything that could touch RCU.
+	 */
+	if (work & _TIF_NOHZ) {
+		user_exit();
+		work &= ~TIF_NOHZ;
+	}
+
+#ifdef CONFIG_SECCOMP
+	/*
+	 * Do seccomp first -- it should minimize exposure of other
+	 * code, and keeping seccomp fast is probably more valuable
+	 * than the rest of this.
+	 */
+	if (work & _TIF_SECCOMP) {
+		struct seccomp_data sd;
+
+		sd.arch = arch;
+		sd.nr = regs->orig_ax;
+		sd.instruction_pointer = regs->ip;
+#ifdef CONFIG_X86_64
+		if (arch == AUDIT_ARCH_X86_64) {
+			sd.args[0] = regs->di;
+			sd.args[1] = regs->si;
+			sd.args[2] = regs->dx;
+			sd.args[3] = regs->r10;
+			sd.args[4] = regs->r8;
+			sd.args[5] = regs->r9;
+		} else
+#endif
+		{
+			sd.args[0] = regs->bx;
+			sd.args[1] = regs->cx;
+			sd.args[2] = regs->dx;
+			sd.args[3] = regs->si;
+			sd.args[4] = regs->di;
+			sd.args[5] = regs->bp;
+		}
+
+		BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0);
+		BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1);
+
+		ret = seccomp_phase1(&sd);
+		if (ret == SECCOMP_PHASE1_SKIP) {
+			regs->orig_ax = -1;
+			ret = 0;
+		} else if (ret != SECCOMP_PHASE1_OK) {
+			return ret;  /* Go directly to phase 2 */
+		}
+
+		work &= ~_TIF_SECCOMP;
+	}
+#endif
+
+	/* Do our best to finish without phase 2. */
+	if (work == 0)
+		return ret;  /* seccomp and/or nohz only (ret == 0 here) */
+
+#ifdef CONFIG_AUDITSYSCALL
+	if (work == _TIF_SYSCALL_AUDIT) {
+		/*
+		 * If there is no more work to be done except auditing,
+		 * then audit in phase 1.  Phase 2 always audits, so, if
+		 * we audit here, then we can't go on to phase 2.
+		 */
+		do_audit_syscall_entry(regs, arch);
+		return 0;
+	}
+#endif
+
+	return 1;  /* Something is enabled that we can't handle in phase 1 */
+}
+
+/* Returns the syscall nr to run (which should match regs->orig_ax). */
+long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch,
+				unsigned long phase1_result)
 {
 	long ret = 0;
+	u32 work = ACCESS_ONCE(current_thread_info()->flags) &
+		_TIF_WORK_SYSCALL_ENTRY;
 
-	user_exit();
+	BUG_ON(regs != task_pt_regs(current));
 
 	/*
 	 * If we stepped into a sysenter/syscall insn, it trapped in
@@ -1467,17 +1569,21 @@ long syscall_trace_enter(struct pt_regs *regs)
 	 * do_debug() and we need to set it again to restore the user
 	 * state.  If we entered on the slow path, TF was already set.
 	 */
-	if (test_thread_flag(TIF_SINGLESTEP))
+	if (work & _TIF_SINGLESTEP)
 		regs->flags |= X86_EFLAGS_TF;
 
-	/* do the secure computing check first */
-	if (secure_computing(regs->orig_ax)) {
+#ifdef CONFIG_SECCOMP
+	/*
+	 * Call seccomp_phase2 before running the other hooks so that
+	 * they can see any changes made by a seccomp tracer.
+	 */
+	if (phase1_result > 1 && seccomp_phase2(phase1_result)) {
 		/* seccomp failures shouldn't expose any additional code. */
-		ret = -1L;
-		goto out;
+		return -1;
 	}
+#endif
 
-	if (unlikely(test_thread_flag(TIF_SYSCALL_EMU)))
+	if (unlikely(work & _TIF_SYSCALL_EMU))
 		ret = -1L;
 
 	if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) &&
@@ -1487,23 +1593,22 @@ long syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->orig_ax);
 
-	if (IS_IA32)
-		audit_syscall_entry(AUDIT_ARCH_I386,
-				    regs->orig_ax,
-				    regs->bx, regs->cx,
-				    regs->dx, regs->si);
-#ifdef CONFIG_X86_64
-	else
-		audit_syscall_entry(AUDIT_ARCH_X86_64,
-				    regs->orig_ax,
-				    regs->di, regs->si,
-				    regs->dx, regs->r10);
-#endif
+	do_audit_syscall_entry(regs, arch);
 
-out:
 	return ret ?: regs->orig_ax;
 }
 
+long syscall_trace_enter(struct pt_regs *regs)
+{
+	u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
+	unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch);
+
+	if (phase1_result == 0)
+		return regs->orig_ax;
+	else
+		return syscall_trace_enter_phase2(regs, arch, phase1_result);
+}
+
 void syscall_trace_leave(struct pt_regs *regs)
 {
 	bool step;
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index ff898bbf579d..176a0f99d4da 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -498,6 +498,24 @@ void force_hpet_resume(void)
 }
 
 /*
+ * According to the datasheet e6xx systems have the HPET hardwired to
+ * 0xfed00000
+ */
+static void e6xx_force_enable_hpet(struct pci_dev *dev)
+{
+	if (hpet_address || force_hpet_address)
+		return;
+
+	force_hpet_address = 0xFED00000;
+	force_hpet_resume_type = NONE_FORCE_HPET_RESUME;
+	dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at "
+		"0x%lx\n", force_hpet_address);
+	return;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E6XX_CU,
+			 e6xx_force_enable_hpet);
+
+/*
  * HPET MSI on some boards (ATI SB700/SB800) has side effect on
  * floppy DMA. Disable HPET MSI on such platforms.
  * See erratum #27 (Misinterpreted MSI Requests May Result in
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 41ead8d3bc0b..235cfd39e0d7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -879,6 +879,15 @@ void __init setup_arch(char **cmdline_p)
 			KERNEL_PGD_PTRS);
 
 	load_cr3(swapper_pg_dir);
+	/*
+	 * Note: Quark X1000 CPUs advertise PGE incorrectly and require
+	 * a cr3 based tlb flush, so the following __flush_tlb_all()
+	 * will not flush anything because the cpu quirk which clears
+	 * X86_FEATURE_PGE has not been invoked yet. Though due to the
+	 * load_cr3() above the TLB has been flushed already. The
+	 * quirk is invoked before subsequent calls to __flush_tlb_all()
+	 * so proper operation is guaranteed.
+	 */
 	__flush_tlb_all();
 #else
 	printk(KERN_INFO "Command line: %s\n", boot_command_line);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 2851d63c1202..ed37a768d0fc 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -675,6 +675,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		 * handler too.
 		 */
 		regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF);
+		/*
+		 * Ensure the signal handler starts with the new fpu state.
+		 */
+		if (used_math())
+			drop_init_fpu(current);
 	}
 	signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 42a2dca984b3..2d5200e56357 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -102,6 +102,8 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
 
+static DEFINE_PER_CPU(struct completion, die_complete);
+
 atomic_t init_deasserted;
 
 /*
@@ -111,7 +113,6 @@ atomic_t init_deasserted;
 static void smp_callin(void)
 {
 	int cpuid, phys_id;
-	unsigned long timeout;
 
 	/*
 	 * If waken up by an INIT in an 82489DX configuration
@@ -130,37 +131,6 @@ static void smp_callin(void)
 	 * (This works even if the APIC is not enabled.)
 	 */
 	phys_id = read_apic_id();
-	if (cpumask_test_cpu(cpuid, cpu_callin_mask)) {
-		panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
-					phys_id, cpuid);
-	}
-	pr_debug("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id);
-
-	/*
-	 * STARTUP IPIs are fragile beasts as they might sometimes
-	 * trigger some glue motherboard logic. Complete APIC bus
-	 * silence for 1 second, this overestimates the time the
-	 * boot CPU is spending to send the up to 2 STARTUP IPIs
-	 * by a factor of two. This should be enough.
-	 */
-
-	/*
-	 * Waiting 2s total for startup (udelay is not yet working)
-	 */
-	timeout = jiffies + 2*HZ;
-	while (time_before(jiffies, timeout)) {
-		/*
-		 * Has the boot CPU finished it's STARTUP sequence?
-		 */
-		if (cpumask_test_cpu(cpuid, cpu_callout_mask))
-			break;
-		cpu_relax();
-	}
-
-	if (!time_before(jiffies, timeout)) {
-		panic("%s: CPU%d started up but did not get a callout!\n",
-		      __func__, cpuid);
-	}
 
 	/*
 	 * the boot CPU has finished the init stage and is spinning
@@ -296,11 +266,19 @@ void smp_store_cpu_info(int id)
 }
 
 static bool
+topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+
+	return (cpu_to_node(cpu1) == cpu_to_node(cpu2));
+}
+
+static bool
 topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name)
 {
 	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
-	return !WARN_ONCE(cpu_to_node(cpu1) != cpu_to_node(cpu2),
+	return !WARN_ONCE(!topology_same_node(c, o),
 		"sched: CPU #%d's %s-sibling CPU #%d is not on the same node! "
 		"[node: %d != %d]. Ignoring dependency.\n",
 		cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2));
@@ -341,17 +319,44 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 	return false;
 }
 
-static bool match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+/*
+ * Unlike the other levels, we do not enforce keeping a
+ * multicore group inside a NUMA node.  If this happens, we will
+ * discard the MC level of the topology later.
+ */
+static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
-	if (c->phys_proc_id == o->phys_proc_id) {
-		if (cpu_has(c, X86_FEATURE_AMD_DCM))
-			return true;
-
-		return topology_sane(c, o, "mc");
-	}
+	if (c->phys_proc_id == o->phys_proc_id)
+		return true;
 	return false;
 }
 
+static struct sched_domain_topology_level numa_inside_package_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+	{ NULL, },
+};
+/*
+ * set_sched_topology() sets the topology internal to a CPU.  The
+ * NUMA topologies are layered on top of it to build the full
+ * system topology.
+ *
+ * If NUMA nodes are observed to occur within a CPU package, this
+ * function should be called.  It forces the sched domain code to
+ * only use the SMT level for the CPU portion of the topology.
+ * This essentially falls back to relying on NUMA information
+ * from the SRAT table to describe the entire system topology
+ * (except for hyperthreads).
+ */
+static void primarily_use_numa_for_topology(void)
+{
+	set_sched_topology(numa_inside_package_topology);
+}
+
 void set_cpu_sibling_map(int cpu)
 {
 	bool has_smt = smp_num_siblings > 1;
@@ -388,7 +393,7 @@ void set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
-		if ((i == cpu) || (has_mp && match_mc(c, o))) {
+		if ((i == cpu) || (has_mp && match_die(c, o))) {
 			link_mask(core, cpu, i);
 
 			/*
@@ -410,6 +415,8 @@ void set_cpu_sibling_map(int cpu)
 			} else if (i != cpu && !c->booted_cores)
 				c->booted_cores = cpu_data(i).booted_cores;
 		}
+		if (match_die(c, o) && !topology_same_node(c, o))
+			primarily_use_numa_for_topology();
 	}
 }
 
@@ -753,8 +760,8 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	unsigned long start_ip = real_mode_header->trampoline_start;
 
 	unsigned long boot_error = 0;
-	int timeout;
 	int cpu0_nmi_registered = 0;
+	unsigned long timeout;
 
 	/* Just in case we booted with a single CPU. */
 	alternatives_enable_smp();
@@ -802,6 +809,15 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	}
 
 	/*
+	 * AP might wait on cpu_callout_mask in cpu_init() with
+	 * cpu_initialized_mask set if previous attempt to online
+	 * it timed-out. Clear cpu_initialized_mask so that after
+	 * INIT/SIPI it could start with a clean state.
+	 */
+	cpumask_clear_cpu(cpu, cpu_initialized_mask);
+	smp_mb();
+
+	/*
 	 * Wake up a CPU in difference cases:
 	 * - Use the method in the APIC driver if it's defined
 	 * Otherwise,
@@ -815,53 +831,38 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 
 	if (!boot_error) {
 		/*
-		 * allow APs to start initializing.
+		 * Wait 10s total for a response from AP
 		 */
-		pr_debug("Before Callout %d\n", cpu);
-		cpumask_set_cpu(cpu, cpu_callout_mask);
-		pr_debug("After Callout %d\n", cpu);
+		boot_error = -1;
+		timeout = jiffies + 10*HZ;
+		while (time_before(jiffies, timeout)) {
+			if (cpumask_test_cpu(cpu, cpu_initialized_mask)) {
+				/*
+				 * Tell AP to proceed with initialization
+				 */
+				cpumask_set_cpu(cpu, cpu_callout_mask);
+				boot_error = 0;
+				break;
+			}
+			udelay(100);
+			schedule();
+		}
+	}
 
+	if (!boot_error) {
 		/*
-		 * Wait 5s total for a response
+		 * Wait till AP completes initial initialization
 		 */
-		for (timeout = 0; timeout < 50000; timeout++) {
-			if (cpumask_test_cpu(cpu, cpu_callin_mask))
-				break;	/* It has booted */
-			udelay(100);
+		while (!cpumask_test_cpu(cpu, cpu_callin_mask)) {
 			/*
 			 * Allow other tasks to run while we wait for the
 			 * AP to come online. This also gives a chance
 			 * for the MTRR work(triggered by the AP coming online)
 			 * to be completed in the stop machine context.
 			 */
+			udelay(100);
 			schedule();
 		}
-
-		if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
-			print_cpu_msr(&cpu_data(cpu));
-			pr_debug("CPU%d: has booted.\n", cpu);
-		} else {
-			boot_error = 1;
-			if (*trampoline_status == 0xA5A5A5A5)
-				/* trampoline started but...? */
-				pr_err("CPU%d: Stuck ??\n", cpu);
-			else
-				/* trampoline code not run */
-				pr_err("CPU%d: Not responding\n", cpu);
-			if (apic->inquire_remote_apic)
-				apic->inquire_remote_apic(apicid);
-		}
-	}
-
-	if (boot_error) {
-		/* Try to put things back the way they were before ... */
-		numa_remove_cpu(cpu); /* was set by numa_add_cpu */
-
-		/* was set by do_boot_cpu() */
-		cpumask_clear_cpu(cpu, cpu_callout_mask);
-
-		/* was set by cpu_init() */
-		cpumask_clear_cpu(cpu, cpu_initialized_mask);
 	}
 
 	/* mark "stuck" area as not stuck */
@@ -1326,26 +1327,24 @@ int native_cpu_disable(void)
 		return ret;
 
 	clear_local_APIC();
-
+	init_completion(&per_cpu(die_complete, smp_processor_id()));
 	cpu_disable_common();
+
 	return 0;
 }
 
 void native_cpu_die(unsigned int cpu)
 {
 	/* We don't do anything here: idle task is faking death itself. */
-	unsigned int i;
+	wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ);
 
-	for (i = 0; i < 10; i++) {
-		/* They ack this in play_dead by setting CPU_DEAD */
-		if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
-			if (system_state == SYSTEM_RUNNING)
-				pr_info("CPU %u is now offline\n", cpu);
-			return;
-		}
-		msleep(100);
+	/* They ack this in play_dead() by setting CPU_DEAD */
+	if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
+		if (system_state == SYSTEM_RUNNING)
+			pr_info("CPU %u is now offline\n", cpu);
+	} else {
+		pr_err("CPU %u didn't die...\n", cpu);
 	}
-	pr_err("CPU %u didn't die...\n", cpu);
 }
 
 void play_dead_common(void)
@@ -1357,6 +1356,7 @@ void play_dead_common(void)
 	mb();
 	/* Ack it */
 	__this_cpu_write(cpu_state, CPU_DEAD);
+	complete(&per_cpu(die_complete, smp_processor_id()));
 
 	/*
 	 * With physical CPU hotplug, we should halt the cpu
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index e1e1e80fc6a6..957779f4eb40 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -216,7 +216,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 	 */
 	regs->orig_ax = syscall_nr;
 	regs->ax = -ENOSYS;
-	tmp = secure_computing(syscall_nr);
+	tmp = secure_computing();
 	if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
 		warn_bad_vsyscall(KERN_DEBUG, regs,
 				  "seccomp tried to change syscall nr or ip");
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 940b142cc11f..4c540c4719d8 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -271,8 +271,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
 		return -1;
 
-	drop_init_fpu(tsk);	/* trigger finit */
-
 	return 0;
 }
 
@@ -402,8 +400,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 			set_used_math();
 		}
 
-		if (use_eager_fpu())
+		if (use_eager_fpu()) {
+			preempt_disable();
 			math_state_restore();
+			preempt_enable();
+		}
 
 		return err;
 	} else {
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 3201e93ebd07..ac1c4de3a484 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4549,7 +4549,7 @@ int kvm_mmu_module_init(void)
 	if (!mmu_page_header_cache)
 		goto nomem;
 
-	if (percpu_counter_init(&kvm_total_used_mmu_pages, 0))
+	if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL))
 		goto nomem;
 
 	register_shrinker(&mmu_shrinker);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index f7f6a4a157a6..65510f624dfe 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -670,7 +670,7 @@ static int svm_hardware_enable(void)
 
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
 		wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
-		__get_cpu_var(current_tsc_ratio) = TSC_RATIO_DEFAULT;
+		__this_cpu_write(current_tsc_ratio, TSC_RATIO_DEFAULT);
 	}
 
 
@@ -1313,8 +1313,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
 
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR) &&
-	    svm->tsc_ratio != __get_cpu_var(current_tsc_ratio)) {
-		__get_cpu_var(current_tsc_ratio) = svm->tsc_ratio;
+	    svm->tsc_ratio != __this_cpu_read(current_tsc_ratio)) {
+		__this_cpu_write(current_tsc_ratio, svm->tsc_ratio);
 		wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio);
 	}
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 04fa1b8298c8..0acac81f198b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -472,6 +472,7 @@ struct vcpu_vmx {
 		int           gs_ldt_reload_needed;
 		int           fs_reload_needed;
 		u64           msr_host_bndcfgs;
+		unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	} host_state;
 	struct {
 		int vm86_active;
@@ -1626,7 +1627,7 @@ static void reload_tss(void)
 	/*
 	 * VT restores TR but not its size.  Useless.
 	 */
-	struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+	struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
 	struct desc_struct *descs;
 
 	descs = (void *)gdt->address;
@@ -1672,7 +1673,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 
 static unsigned long segment_base(u16 selector)
 {
-	struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+	struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
 	struct desc_struct *d;
 	unsigned long table_base;
 	unsigned long v;
@@ -1802,7 +1803,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 	 */
 	if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
 		stts();
-	load_gdt(&__get_cpu_var(host_gdt));
+	load_gdt(this_cpu_ptr(&host_gdt));
 }
 
 static void vmx_load_host_state(struct vcpu_vmx *vmx)
@@ -1832,7 +1833,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	}
 
 	if (vmx->loaded_vmcs->cpu != cpu) {
-		struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+		struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
 		unsigned long sysenter_esp;
 
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
@@ -2771,7 +2772,7 @@ static int hardware_enable(void)
 		ept_sync_global();
 	}
 
-	native_store_gdt(&__get_cpu_var(host_gdt));
+	native_store_gdt(this_cpu_ptr(&host_gdt));
 
 	return 0;
 }
@@ -4267,11 +4268,16 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 	u32 low32, high32;
 	unsigned long tmpl;
 	struct desc_ptr dt;
+	unsigned long cr4;
 
 	vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS);  /* 22.2.3 */
-	vmcs_writel(HOST_CR4, read_cr4());  /* 22.2.3, 22.2.5 */
 	vmcs_writel(HOST_CR3, read_cr3());  /* 22.2.3  FIXME: shadow tables */
 
+	/* Save the most likely value for this task's CR4 in the VMCS. */
+	cr4 = read_cr4();
+	vmcs_writel(HOST_CR4, cr4);			/* 22.2.3, 22.2.5 */
+	vmx->host_state.vmcs_host_cr4 = cr4;
+
 	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
 #ifdef CONFIG_X86_64
 	/*
@@ -7514,7 +7520,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long debugctlmsr;
+	unsigned long debugctlmsr, cr4;
 
 	/* Record the guest's net vcpu time for enforced NMI injections. */
 	if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
@@ -7540,6 +7546,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
+	cr4 = read_cr4();
+	if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+		vmcs_writel(HOST_CR4, cr4);
+		vmx->host_state.vmcs_host_cr4 = cr4;
+	}
+
 	/* When single-stepping over STI and MOV SS, we must clear the
 	 * corresponding interruptibility bits in the guest state. Otherwise
 	 * vmentry fails as it then expects bit 14 (BS) in pending debug
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5430e4b0af29..34c8f94331f8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1559,7 +1559,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
-	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+	this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
 	if (unlikely(this_tsc_khz == 0)) {
 		local_irq_restore(flags);
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 4d4f96a27638..db92793b7e23 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -20,7 +20,6 @@ lib-y := delay.o misc.o cmdline.o
 lib-y += thunk_$(BITS).o
 lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
-lib-$(CONFIG_SMP) += rwlock.o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
 
@@ -39,7 +38,7 @@ endif
 else
         obj-y += iomap_copy_64.o
         lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
-        lib-y += thunk_64.o clear_page_64.o copy_page_64.o
+        lib-y += clear_page_64.o copy_page_64.o
         lib-y += memmove_64.o memset_64.o
         lib-y += copy_user_64.o copy_user_nocache_64.o
 	lib-y += cmpxchg16b_emu.o
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 1e572c507d06..40a172541ee2 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -6,15 +6,8 @@
  *
  */
 #include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
 #include <asm/dwarf2.h>
-
-#ifdef CONFIG_SMP
-#define SEG_PREFIX %gs:
-#else
-#define SEG_PREFIX
-#endif
+#include <asm/percpu.h>
 
 .text
 
@@ -39,24 +32,25 @@ CFI_STARTPROC
 # *atomic* on a single cpu (as provided by the this_cpu_xx class of
 # macros).
 #
-this_cpu_cmpxchg16b_emu:
-	pushf
+	pushfq_cfi
 	cli
 
-	cmpq SEG_PREFIX(%rsi), %rax
-	jne not_same
-	cmpq SEG_PREFIX 8(%rsi), %rdx
-	jne not_same
+	cmpq PER_CPU_VAR((%rsi)), %rax
+	jne .Lnot_same
+	cmpq PER_CPU_VAR(8(%rsi)), %rdx
+	jne .Lnot_same
 
-	movq %rbx, SEG_PREFIX(%rsi)
-	movq %rcx, SEG_PREFIX 8(%rsi)
+	movq %rbx, PER_CPU_VAR((%rsi))
+	movq %rcx, PER_CPU_VAR(8(%rsi))
 
-	popf
+	CFI_REMEMBER_STATE
+	popfq_cfi
 	mov $1, %al
 	ret
 
- not_same:
-	popf
+	CFI_RESTORE_STATE
+.Lnot_same:
+	popfq_cfi
 	xor %al,%al
 	ret
 
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 828cb710dec2..b4807fce5177 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,11 +7,8 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
 #include <asm/dwarf2.h>
 
-
 .text
 
 /*
@@ -30,27 +27,28 @@ CFI_STARTPROC
 # set the whole ZF thing (caller will just compare
 # eax:edx with the expected value)
 #
-cmpxchg8b_emu:
-	pushfl
+	pushfl_cfi
 	cli
 
 	cmpl  (%esi), %eax
-	jne not_same
+	jne .Lnot_same
 	cmpl 4(%esi), %edx
-	jne half_same
+	jne .Lhalf_same
 
 	movl %ebx,  (%esi)
 	movl %ecx, 4(%esi)
 
-	popfl
+	CFI_REMEMBER_STATE
+	popfl_cfi
 	ret
 
- not_same:
+	CFI_RESTORE_STATE
+.Lnot_same:
 	movl  (%esi), %eax
- half_same:
+.Lhalf_same:
 	movl 4(%esi), %edx
 
-	popfl
+	popfl_cfi
 	ret
 
 CFI_ENDPROC
diff --git a/arch/x86/lib/rwlock.S b/arch/x86/lib/rwlock.S
deleted file mode 100644
index 1cad22139c88..000000000000
--- a/arch/x86/lib/rwlock.S
+++ /dev/null
@@ -1,44 +0,0 @@
-/* Slow paths of read/write spinlocks. */
-
-#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
-#include <asm/rwlock.h>
-
-#ifdef CONFIG_X86_32
-# define __lock_ptr eax
-#else
-# define __lock_ptr rdi
-#endif
-
-ENTRY(__write_lock_failed)
-	CFI_STARTPROC
-	FRAME
-0:	LOCK_PREFIX
-	WRITE_LOCK_ADD($RW_LOCK_BIAS) (%__lock_ptr)
-1:	rep; nop
-	cmpl	$WRITE_LOCK_CMP, (%__lock_ptr)
-	jne	1b
-	LOCK_PREFIX
-	WRITE_LOCK_SUB($RW_LOCK_BIAS) (%__lock_ptr)
-	jnz	0b
-	ENDFRAME
-	ret
-	CFI_ENDPROC
-END(__write_lock_failed)
-
-ENTRY(__read_lock_failed)
-	CFI_STARTPROC
-	FRAME
-0:	LOCK_PREFIX
-	READ_LOCK_SIZE(inc) (%__lock_ptr)
-1:	rep; nop
-	READ_LOCK_SIZE(cmp) $1, (%__lock_ptr)
-	js	1b
-	LOCK_PREFIX
-	READ_LOCK_SIZE(dec) (%__lock_ptr)
-	js	0b
-	ENDFRAME
-	ret
-	CFI_ENDPROC
-END(__read_lock_failed)
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S
index 28f85c916712..e28cdaf5ac2c 100644
--- a/arch/x86/lib/thunk_32.S
+++ b/arch/x86/lib/thunk_32.S
@@ -6,25 +6,46 @@
  */
 	#include <linux/linkage.h>
 	#include <asm/asm.h>
+	#include <asm/dwarf2.h>
 
-#ifdef CONFIG_TRACE_IRQFLAGS
 	/* put return address in eax (arg1) */
-	.macro thunk_ra name,func
+	.macro THUNK name, func, put_ret_addr_in_eax=0
 	.globl \name
 \name:
-	pushl %eax
-	pushl %ecx
-	pushl %edx
+	CFI_STARTPROC
+	pushl_cfi %eax
+	CFI_REL_OFFSET eax, 0
+	pushl_cfi %ecx
+	CFI_REL_OFFSET ecx, 0
+	pushl_cfi %edx
+	CFI_REL_OFFSET edx, 0
+
+	.if \put_ret_addr_in_eax
 	/* Place EIP in the arg1 */
 	movl 3*4(%esp), %eax
+	.endif
+
 	call \func
-	popl %edx
-	popl %ecx
-	popl %eax
+	popl_cfi %edx
+	CFI_RESTORE edx
+	popl_cfi %ecx
+	CFI_RESTORE ecx
+	popl_cfi %eax
+	CFI_RESTORE eax
 	ret
+	CFI_ENDPROC
 	_ASM_NOKPROBE(\name)
 	.endm
 
-	thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
-	thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller
+#ifdef CONFIG_TRACE_IRQFLAGS
+	THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
+	THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
+#endif
+
+#ifdef CONFIG_PREEMPT
+	THUNK ___preempt_schedule, preempt_schedule
+#ifdef CONFIG_CONTEXT_TRACKING
+	THUNK ___preempt_schedule_context, preempt_schedule_context
 #endif
+#endif
+
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index 92d9feaff42b..b30b5ebd614a 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -38,6 +38,13 @@
 	THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
 #endif
 
+#ifdef CONFIG_PREEMPT
+	THUNK ___preempt_schedule, preempt_schedule
+#ifdef CONFIG_CONTEXT_TRACKING
+	THUNK ___preempt_schedule_context, preempt_schedule_context
+#endif
+#endif
+
 	/* SAVE_ARGS below is used only for the .cfi directives it contains. */
 	CFI_STARTPROC
 	SAVE_ARGS
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a24194681513..d973e61e450d 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -3,7 +3,6 @@
  *  Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
  *  Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
  */
-#include <linux/magic.h>		/* STACK_END_MAGIC		*/
 #include <linux/sched.h>		/* test_thread_flag(), ...	*/
 #include <linux/kdebug.h>		/* oops_begin/end, ...		*/
 #include <linux/module.h>		/* search_exception_table	*/
@@ -350,7 +349,7 @@ out:
 
 void vmalloc_sync_all(void)
 {
-	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
+	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END, 0);
 }
 
 /*
@@ -649,7 +648,6 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	   unsigned long address, int signal, int si_code)
 {
 	struct task_struct *tsk = current;
-	unsigned long *stackend;
 	unsigned long flags;
 	int sig;
 
@@ -709,8 +707,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 	show_fault_oops(regs, error_code, address);
 
-	stackend = end_of_stack(tsk);
-	if (tsk != &init_task && *stackend != STACK_END_MAGIC)
+	if (task_stack_end_corrupted(tsk))
 		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
 
 	tsk->thread.cr2		= address;
@@ -933,8 +930,17 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte)
  * cross-processor TLB flush, even if no stale TLB entries exist
  * on other processors.
  *
+ * Spurious faults may only occur if the TLB contains an entry with
+ * fewer permission than the page table entry.  Non-present (P = 0)
+ * and reserved bit (R = 1) faults are never spurious.
+ *
  * There are no security implications to leaving a stale TLB when
  * increasing the permissions on a page.
+ *
+ * Returns non-zero if a spurious fault was handled, zero otherwise.
+ *
+ * See Intel Developer's Manual Vol 3 Section 4.10.4.3, bullet 3
+ * (Optional Invalidation).
  */
 static noinline int
 spurious_fault(unsigned long error_code, unsigned long address)
@@ -945,8 +951,17 @@ spurious_fault(unsigned long error_code, unsigned long address)
 	pte_t *pte;
 	int ret;
 
-	/* Reserved-bit violation or user access to kernel space? */
-	if (error_code & (PF_USER | PF_RSVD))
+	/*
+	 * Only writes to RO or instruction fetches from NX may cause
+	 * spurious faults.
+	 *
+	 * These could be from user or supervisor accesses but the TLB
+	 * is only lazily flushed after a kernel mapping protection
+	 * change, so user accesses are not expected to cause spurious
+	 * faults.
+	 */
+	if (error_code != (PF_WRITE | PF_PROT)
+	    && error_code != (PF_INSTR | PF_PROT))
 		return 0;
 
 	pgd = init_mm.pgd + pgd_index(address);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 7d05565ba781..c8140e12816a 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -537,7 +537,7 @@ static void __init pagetable_init(void)
 	permanent_kmaps_init(pgd_base);
 }
 
-pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
+pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL);
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
 /* user-defined highmem size */
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5621c47d7a1a..4cb8763868fc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -151,7 +151,7 @@ early_param("gbpages", parse_direct_gbpages_on);
  * around without checking the pgd every time.
  */
 
-pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
+pteval_t __supported_pte_mask __read_mostly = ~0;
 EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
 int force_personality32;
@@ -178,7 +178,7 @@ __setup("noexec32=", nonx32_setup);
  * When memory was added/removed make sure all the processes MM have
  * suitable PGD entries in the local PGD level page.
  */
-void sync_global_pgds(unsigned long start, unsigned long end)
+void sync_global_pgds(unsigned long start, unsigned long end, int removed)
 {
 	unsigned long address;
 
@@ -186,7 +186,12 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 		const pgd_t *pgd_ref = pgd_offset_k(address);
 		struct page *page;
 
-		if (pgd_none(*pgd_ref))
+		/*
+		 * When it is called after memory hot remove, pgd_none()
+		 * returns true. In this case (removed == 1), we must clear
+		 * the PGD entries in the local PGD level page.
+		 */
+		if (pgd_none(*pgd_ref) && !removed)
 			continue;
 
 		spin_lock(&pgd_lock);
@@ -199,12 +204,18 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
 			spin_lock(pgt_lock);
 
-			if (pgd_none(*pgd))
-				set_pgd(pgd, *pgd_ref);
-			else
+			if (!pgd_none(*pgd_ref) && !pgd_none(*pgd))
 				BUG_ON(pgd_page_vaddr(*pgd)
 				       != pgd_page_vaddr(*pgd_ref));
 
+			if (removed) {
+				if (pgd_none(*pgd_ref) && !pgd_none(*pgd))
+					pgd_clear(pgd);
+			} else {
+				if (pgd_none(*pgd))
+					set_pgd(pgd, *pgd_ref);
+			}
+
 			spin_unlock(pgt_lock);
 		}
 		spin_unlock(&pgd_lock);
@@ -633,7 +644,7 @@ kernel_physical_mapping_init(unsigned long start,
 	}
 
 	if (pgd_changed)
-		sync_global_pgds(addr, end - 1);
+		sync_global_pgds(addr, end - 1, 0);
 
 	__flush_tlb_all();
 
@@ -976,25 +987,26 @@ static void __meminit
 remove_pagetable(unsigned long start, unsigned long end, bool direct)
 {
 	unsigned long next;
+	unsigned long addr;
 	pgd_t *pgd;
 	pud_t *pud;
 	bool pgd_changed = false;
 
-	for (; start < end; start = next) {
-		next = pgd_addr_end(start, end);
+	for (addr = start; addr < end; addr = next) {
+		next = pgd_addr_end(addr, end);
 
-		pgd = pgd_offset_k(start);
+		pgd = pgd_offset_k(addr);
 		if (!pgd_present(*pgd))
 			continue;
 
 		pud = (pud_t *)pgd_page_vaddr(*pgd);
-		remove_pud_table(pud, start, next, direct);
+		remove_pud_table(pud, addr, next, direct);
 		if (free_pud_table(pud, pgd))
 			pgd_changed = true;
 	}
 
 	if (pgd_changed)
-		sync_global_pgds(start, end - 1);
+		sync_global_pgds(start, end - 1, 1);
 
 	flush_tlb_all();
 }
@@ -1341,7 +1353,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 	else
 		err = vmemmap_populate_basepages(start, end, node);
 	if (!err)
-		sync_global_pgds(start, end - 1);
+		sync_global_pgds(start, end - 1, 0);
 	return err;
 }
 
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index baff1da354e0..af78e50ca6ce 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -86,6 +86,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	pgprot_t prot;
 	int retval;
 	void __iomem *ret_addr;
+	int ram_region;
 
 	/* Don't allow wraparound or zero size */
 	last_addr = phys_addr + size - 1;
@@ -108,12 +109,23 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
-	pfn      = phys_addr >> PAGE_SHIFT;
-	last_pfn = last_addr >> PAGE_SHIFT;
-	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
-				  __ioremap_check_ram) == 1)
+	/* First check if whole region can be identified as RAM or not */
+	ram_region = region_is_ram(phys_addr, size);
+	if (ram_region > 0) {
+		WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n",
+				(unsigned long int)phys_addr,
+				(unsigned long int)last_addr);
 		return NULL;
+	}
 
+	/* If could not be identified(-1), check page by page */
+	if (ram_region < 0) {
+		pfn      = phys_addr >> PAGE_SHIFT;
+		last_pfn = last_addr >> PAGE_SHIFT;
+		if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+					  __ioremap_check_ram) == 1)
+			return NULL;
+	}
 	/*
 	 * Mappings have to be page-aligned
 	 */
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index dd89a13f1051..b4f2e7e9e907 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -140,7 +140,7 @@ static DEFINE_PER_CPU(struct kmemcheck_context, kmemcheck_context);
 
 bool kmemcheck_active(struct pt_regs *regs)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	return data->balance > 0;
 }
@@ -148,7 +148,7 @@ bool kmemcheck_active(struct pt_regs *regs)
 /* Save an address that needs to be shown/hidden */
 static void kmemcheck_save_addr(unsigned long addr)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	BUG_ON(data->n_addrs >= ARRAY_SIZE(data->addr));
 	data->addr[data->n_addrs++] = addr;
@@ -156,7 +156,7 @@ static void kmemcheck_save_addr(unsigned long addr)
 
 static unsigned int kmemcheck_show_all(void)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 	unsigned int i;
 	unsigned int n;
 
@@ -169,7 +169,7 @@ static unsigned int kmemcheck_show_all(void)
 
 static unsigned int kmemcheck_hide_all(void)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 	unsigned int i;
 	unsigned int n;
 
@@ -185,7 +185,7 @@ static unsigned int kmemcheck_hide_all(void)
  */
 void kmemcheck_show(struct pt_regs *regs)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	BUG_ON(!irqs_disabled());
 
@@ -226,7 +226,7 @@ void kmemcheck_show(struct pt_regs *regs)
  */
 void kmemcheck_hide(struct pt_regs *regs)
 {
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 	int n;
 
 	BUG_ON(!irqs_disabled());
@@ -528,7 +528,7 @@ static void kmemcheck_access(struct pt_regs *regs,
 	const uint8_t *insn_primary;
 	unsigned int size;
 
-	struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+	struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
 
 	/* Recursive fault -- ouch. */
 	if (data->busy) {
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index a32b706c401a..1a883705a12a 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -185,8 +185,8 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 	return numa_add_memblk_to(nid, start, end, &numa_meminfo);
 }
 
-/* Initialize NODE_DATA for a node on the local memory */
-static void __init setup_node_data(int nid, u64 start, u64 end)
+/* Allocate NODE_DATA for a node on the local memory */
+static void __init alloc_node_data(int nid)
 {
 	const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	u64 nd_pa;
@@ -194,18 +194,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	int tnid;
 
 	/*
-	 * Don't confuse VM with a node that doesn't have the
-	 * minimum amount of memory:
-	 */
-	if (end && (end - start) < NODE_MIN_SIZE)
-		return;
-
-	start = roundup(start, ZONE_ALIGN);
-
-	printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
-	       nid, start, end - 1);
-
-	/*
 	 * Allocate node data.  Try node-local memory and then any node.
 	 * Never allocate in DMA zone.
 	 */
@@ -222,7 +210,7 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	nd = __va(nd_pa);
 
 	/* report and initialize */
-	printk(KERN_INFO "  NODE_DATA [mem %#010Lx-%#010Lx]\n",
+	printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid,
 	       nd_pa, nd_pa + nd_size - 1);
 	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
 	if (tnid != nid)
@@ -230,9 +218,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 
 	node_data[nid] = nd;
 	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
-	NODE_DATA(nid)->node_id = nid;
-	NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT;
-	NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT;
 
 	node_set_online(nid);
 }
@@ -478,6 +463,42 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
 	return true;
 }
 
+static void __init numa_clear_kernel_node_hotplug(void)
+{
+	int i, nid;
+	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
+	unsigned long start, end;
+	struct memblock_region *r;
+
+	/*
+	 * At this time, all memory regions reserved by memblock are
+	 * used by the kernel. Set the nid in memblock.reserved will
+	 * mark out all the nodes the kernel resides in.
+	 */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		struct numa_memblk *mb = &numa_meminfo.blk[i];
+
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.reserved, mb->nid);
+	}
+
+	/* Mark all kernel nodes. */
+	for_each_memblock(reserved, r)
+		node_set(r->nid, numa_kernel_nodes);
+
+	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		nid = numa_meminfo.blk[i].nid;
+		if (!node_isset(nid, numa_kernel_nodes))
+			continue;
+
+		start = numa_meminfo.blk[i].start;
+		end = numa_meminfo.blk[i].end;
+
+		memblock_clear_hotplug(start, end - start);
+	}
+}
+
 static int __init numa_register_memblks(struct numa_meminfo *mi)
 {
 	unsigned long uninitialized_var(pfn_align);
@@ -496,6 +517,15 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 	}
 
 	/*
+	 * At very early time, the kernel have to use some memory such as
+	 * loading the kernel image. We cannot prevent this anyway. So any
+	 * node the kernel resides in should be un-hotpluggable.
+	 *
+	 * And when we come here, alloc node data won't fail.
+	 */
+	numa_clear_kernel_node_hotplug();
+
+	/*
 	 * If sections array is gonna be used for pfn -> nid mapping, check
 	 * whether its granularity is fine enough.
 	 */
@@ -523,8 +553,17 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 			end = max(mi->blk[i].end, end);
 		}
 
-		if (start < end)
-			setup_node_data(nid, start, end);
+		if (start >= end)
+			continue;
+
+		/*
+		 * Don't confuse VM with a node that doesn't have the
+		 * minimum amount of memory:
+		 */
+		if (end && (end - start) < NODE_MIN_SIZE)
+			continue;
+
+		alloc_node_data(nid);
 	}
 
 	/* Dump memblock with node info and return. */
@@ -554,41 +593,6 @@ static void __init numa_init_array(void)
 	}
 }
 
-static void __init numa_clear_kernel_node_hotplug(void)
-{
-	int i, nid;
-	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	unsigned long start, end;
-	struct memblock_region *r;
-
-	/*
-	 * At this time, all memory regions reserved by memblock are
-	 * used by the kernel. Set the nid in memblock.reserved will
-	 * mark out all the nodes the kernel resides in.
-	 */
-	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		struct numa_memblk *mb = &numa_meminfo.blk[i];
-		memblock_set_node(mb->start, mb->end - mb->start,
-				  &memblock.reserved, mb->nid);
-	}
-
-	/* Mark all kernel nodes. */
-	for_each_memblock(reserved, r)
-		node_set(r->nid, numa_kernel_nodes);
-
-	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
-	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		nid = numa_meminfo.blk[i].nid;
-		if (!node_isset(nid, numa_kernel_nodes))
-			continue;
-
-		start = numa_meminfo.blk[i].start;
-		end = numa_meminfo.blk[i].end;
-
-		memblock_clear_hotplug(start, end - start);
-	}
-}
-
 static int __init numa_init(int (*init_func)(void))
 {
 	int i;
@@ -643,15 +647,6 @@ static int __init numa_init(int (*init_func)(void))
 	}
 	numa_init_array();
 
-	/*
-	 * At very early time, the kernel have to use some memory such as
-	 * loading the kernel image. We cannot prevent this anyway. So any
-	 * node the kernel resides in should be un-hotpluggable.
-	 *
-	 * And when we come here, numa_init() won't fail.
-	 */
-	numa_clear_kernel_node_hotplug();
-
 	return 0;
 }
 
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 4dd8cf652579..75cc0978d45d 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -59,41 +59,6 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
 	__flush_tlb_one(vaddr);
 }
 
-/*
- * Associate a large virtual page frame with a given physical page frame 
- * and protection flags for that frame. pfn is for the base of the page,
- * vaddr is what the page gets mapped to - both must be properly aligned. 
- * The pmd must already be instantiated. Assumes PAE mode.
- */ 
-void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-
-	if (vaddr & (PMD_SIZE-1)) {		/* vaddr is misaligned */
-		printk(KERN_WARNING "set_pmd_pfn: vaddr misaligned\n");
-		return; /* BUG(); */
-	}
-	if (pfn & (PTRS_PER_PTE-1)) {		/* pfn is misaligned */
-		printk(KERN_WARNING "set_pmd_pfn: pfn misaligned\n");
-		return; /* BUG(); */
-	}
-	pgd = swapper_pg_dir + pgd_index(vaddr);
-	if (pgd_none(*pgd)) {
-		printk(KERN_WARNING "set_pmd_pfn: pgd_none\n");
-		return; /* BUG(); */
-	}
-	pud = pud_offset(pgd, vaddr);
-	pmd = pmd_offset(pud, vaddr);
-	set_pmd(pmd, pfn_pmd(pfn, flags));
-	/*
-	 * It's enough to flush this one mapping.
-	 * (PGE mappings get flushed as well)
-	 */
-	__flush_tlb_one(vaddr);
-}
-
 unsigned long __FIXADDR_TOP = 0xfffff000;
 EXPORT_SYMBOL(__FIXADDR_TOP);
 
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 379e8bd0deea..1d2e6392f5fa 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -64,11 +64,11 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
 static int profile_exceptions_notify(unsigned int val, struct pt_regs *regs)
 {
 	if (ctr_running)
-		model->check_ctrs(regs, &__get_cpu_var(cpu_msrs));
+		model->check_ctrs(regs, this_cpu_ptr(&cpu_msrs));
 	else if (!nmi_enabled)
 		return NMI_DONE;
 	else
-		model->stop(&__get_cpu_var(cpu_msrs));
+		model->stop(this_cpu_ptr(&cpu_msrs));
 	return NMI_HANDLED;
 }
 
@@ -91,7 +91,7 @@ static void nmi_cpu_save_registers(struct op_msrs *msrs)
 
 static void nmi_cpu_start(void *dummy)
 {
-	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
+	struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs);
 	if (!msrs->controls)
 		WARN_ON_ONCE(1);
 	else
@@ -111,7 +111,7 @@ static int nmi_start(void)
 
 static void nmi_cpu_stop(void *dummy)
 {
-	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
+	struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs);
 	if (!msrs->controls)
 		WARN_ON_ONCE(1);
 	else
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 98ab13058f89..ad1d91f475ab 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -372,7 +372,7 @@ static unsigned int get_stagger(void)
 {
 #ifdef CONFIG_SMP
 	int cpu = smp_processor_id();
-	return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+	return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
 #endif
 	return 0;
 }
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 059a76c29739..7b20bccf3648 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -81,14 +81,14 @@ struct pci_ops pci_root_ops = {
  */
 DEFINE_RAW_SPINLOCK(pci_config_lock);
 
-static int can_skip_ioresource_align(const struct dmi_system_id *d)
+static int __init can_skip_ioresource_align(const struct dmi_system_id *d)
 {
 	pci_probe |= PCI_CAN_SKIP_ISA_ALIGN;
 	printk(KERN_INFO "PCI: %s detected, can skip ISA alignment\n", d->ident);
 	return 0;
 }
 
-static const struct dmi_system_id can_skip_pciprobe_dmi_table[] = {
+static const struct dmi_system_id can_skip_pciprobe_dmi_table[] __initconst = {
 /*
  * Systems where PCI IO resource ISA alignment can be skipped
  * when the ISA enable bit in the bridge control is not set
@@ -186,7 +186,7 @@ void pcibios_remove_bus(struct pci_bus *bus)
  * on the kernel command line (which was parsed earlier).
  */
 
-static int set_bf_sort(const struct dmi_system_id *d)
+static int __init set_bf_sort(const struct dmi_system_id *d)
 {
 	if (pci_bf_sort == pci_bf_sort_default) {
 		pci_bf_sort = pci_dmi_bf;
@@ -195,8 +195,8 @@ static int set_bf_sort(const struct dmi_system_id *d)
 	return 0;
 }
 
-static void read_dmi_type_b1(const struct dmi_header *dm,
-				       void *private_data)
+static void __init read_dmi_type_b1(const struct dmi_header *dm,
+				    void *private_data)
 {
 	u8 *d = (u8 *)dm + 4;
 
@@ -217,7 +217,7 @@ static void read_dmi_type_b1(const struct dmi_header *dm,
 	}
 }
 
-static int find_sort_method(const struct dmi_system_id *d)
+static int __init find_sort_method(const struct dmi_system_id *d)
 {
 	dmi_walk(read_dmi_type_b1, NULL);
 
@@ -232,7 +232,7 @@ static int find_sort_method(const struct dmi_system_id *d)
  * Enable renumbering of PCI bus# ranges to reach all PCI busses (Cardbus)
  */
 #ifdef __i386__
-static int assign_all_busses(const struct dmi_system_id *d)
+static int __init assign_all_busses(const struct dmi_system_id *d)
 {
 	pci_probe |= PCI_ASSIGN_ALL_BUSSES;
 	printk(KERN_INFO "%s detected: enabling PCI bus# renumbering"
@@ -241,7 +241,7 @@ static int assign_all_busses(const struct dmi_system_id *d)
 }
 #endif
 
-static int set_scan_all(const struct dmi_system_id *d)
+static int __init set_scan_all(const struct dmi_system_id *d)
 {
 	printk(KERN_INFO "PCI: %s detected, enabling pci=pcie_scan_all\n",
 	       d->ident);
@@ -249,7 +249,7 @@ static int set_scan_all(const struct dmi_system_id *d)
 	return 0;
 }
 
-static const struct dmi_system_id pciprobe_dmi_table[] = {
+static const struct dmi_system_id pciprobe_dmi_table[] __initconst = {
 #ifdef __i386__
 /*
  * Laptops which need pci=assign-busses to see Cardbus cards
@@ -512,7 +512,7 @@ int __init pcibios_init(void)
 	return 0;
 }
 
-char * __init pcibios_setup(char *str)
+char *__init pcibios_setup(char *str)
 {
 	if (!strcmp(str, "off")) {
 		pci_probe = 0;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 2ae525e0d8ba..37c1435889ce 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -442,8 +442,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 		 */
 		prot |= _PAGE_CACHE_UC_MINUS;
 
-	prot |= _PAGE_IOMAP;	/* creating a mapping for IO */
-
 	vma->vm_page_prot = __pgprot(prot);
 
 	if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 248642f4bab7..326198a4434e 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -31,7 +31,7 @@ static DEFINE_MUTEX(pci_mmcfg_lock);
 
 LIST_HEAD(pci_mmcfg_list);
 
-static __init void pci_mmconfig_remove(struct pci_mmcfg_region *cfg)
+static void __init pci_mmconfig_remove(struct pci_mmcfg_region *cfg)
 {
 	if (cfg->res.parent)
 		release_resource(&cfg->res);
@@ -39,7 +39,7 @@ static __init void pci_mmconfig_remove(struct pci_mmcfg_region *cfg)
 	kfree(cfg);
 }
 
-static __init void free_all_mmcfg(void)
+static void __init free_all_mmcfg(void)
 {
 	struct pci_mmcfg_region *cfg, *tmp;
 
@@ -93,7 +93,7 @@ static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start,
 	return new;
 }
 
-static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start,
+static struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start,
 							int end, u64 addr)
 {
 	struct pci_mmcfg_region *new;
@@ -125,7 +125,7 @@ struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus)
 	return NULL;
 }
 
-static const char __init *pci_mmcfg_e7520(void)
+static const char *__init pci_mmcfg_e7520(void)
 {
 	u32 win;
 	raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0xce, 2, &win);
@@ -140,7 +140,7 @@ static const char __init *pci_mmcfg_e7520(void)
 	return "Intel Corporation E7520 Memory Controller Hub";
 }
 
-static const char __init *pci_mmcfg_intel_945(void)
+static const char *__init pci_mmcfg_intel_945(void)
 {
 	u32 pciexbar, mask = 0, len = 0;
 
@@ -184,7 +184,7 @@ static const char __init *pci_mmcfg_intel_945(void)
 	return "Intel Corporation 945G/GZ/P/PL Express Memory Controller Hub";
 }
 
-static const char __init *pci_mmcfg_amd_fam10h(void)
+static const char *__init pci_mmcfg_amd_fam10h(void)
 {
 	u32 low, high, address;
 	u64 base, msr;
@@ -235,21 +235,25 @@ static const char __init *pci_mmcfg_amd_fam10h(void)
 }
 
 static bool __initdata mcp55_checked;
-static const char __init *pci_mmcfg_nvidia_mcp55(void)
+static const char *__init pci_mmcfg_nvidia_mcp55(void)
 {
 	int bus;
 	int mcp55_mmconf_found = 0;
 
-	static const u32 extcfg_regnum		= 0x90;
-	static const u32 extcfg_regsize		= 4;
-	static const u32 extcfg_enable_mask	= 1<<31;
-	static const u32 extcfg_start_mask	= 0xff<<16;
-	static const int extcfg_start_shift	= 16;
-	static const u32 extcfg_size_mask	= 0x3<<28;
-	static const int extcfg_size_shift	= 28;
-	static const int extcfg_sizebus[]	= {0x100, 0x80, 0x40, 0x20};
-	static const u32 extcfg_base_mask[]	= {0x7ff8, 0x7ffc, 0x7ffe, 0x7fff};
-	static const int extcfg_base_lshift	= 25;
+	static const u32 extcfg_regnum __initconst	= 0x90;
+	static const u32 extcfg_regsize __initconst	= 4;
+	static const u32 extcfg_enable_mask __initconst	= 1 << 31;
+	static const u32 extcfg_start_mask __initconst	= 0xff << 16;
+	static const int extcfg_start_shift __initconst	= 16;
+	static const u32 extcfg_size_mask __initconst	= 0x3 << 28;
+	static const int extcfg_size_shift __initconst	= 28;
+	static const int extcfg_sizebus[] __initconst	= {
+		0x100, 0x80, 0x40, 0x20
+	};
+	static const u32 extcfg_base_mask[] __initconst	= {
+		0x7ff8, 0x7ffc, 0x7ffe, 0x7fff
+	};
+	static const int extcfg_base_lshift __initconst	= 25;
 
 	/*
 	 * do check if amd fam10h already took over
@@ -302,7 +306,7 @@ struct pci_mmcfg_hostbridge_probe {
 	const char *(*probe)(void);
 };
 
-static struct pci_mmcfg_hostbridge_probe pci_mmcfg_probes[] __initdata = {
+static const struct pci_mmcfg_hostbridge_probe pci_mmcfg_probes[] __initconst = {
 	{ 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_INTEL,
 	  PCI_DEVICE_ID_INTEL_E7520_MCH, pci_mmcfg_e7520 },
 	{ 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_INTEL,
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index c77b24a8b2da..9b83b9051ae7 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -79,13 +79,13 @@ union bios32 {
 static struct {
 	unsigned long address;
 	unsigned short segment;
-} bios32_indirect = { 0, __KERNEL_CS };
+} bios32_indirect __initdata = { 0, __KERNEL_CS };
 
 /*
  * Returns the entry point for the given service, NULL on error
  */
 
-static unsigned long bios32_service(unsigned long service)
+static unsigned long __init bios32_service(unsigned long service)
 {
 	unsigned char return_code;	/* %al */
 	unsigned long address;		/* %ebx */
@@ -124,7 +124,7 @@ static struct {
 
 static int pci_bios_present;
 
-static int check_pcibios(void)
+static int __init check_pcibios(void)
 {
 	u32 signature, eax, ebx, ecx;
 	u8 status, major_ver, minor_ver, hw_mech;
@@ -312,7 +312,7 @@ static const struct pci_raw_ops pci_bios_access = {
  * Try to find PCI BIOS.
  */
 
-static const struct pci_raw_ops *pci_find_bios(void)
+static const struct pci_raw_ops *__init pci_find_bios(void)
 {
 	union bios32 *check;
 	unsigned char sum;
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index c89c93320c12..c6b146e67116 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -63,8 +63,8 @@
 
 static struct uv_hub_nmi_s **uv_hub_nmi_list;
 
-DEFINE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi);
-EXPORT_PER_CPU_SYMBOL_GPL(__uv_cpu_nmi);
+DEFINE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
+EXPORT_PER_CPU_SYMBOL_GPL(uv_cpu_nmi);
 
 static unsigned long nmi_mmr;
 static unsigned long nmi_mmr_clear;
@@ -215,7 +215,7 @@ static int uv_check_nmi(struct uv_hub_nmi_s *hub_nmi)
 	int nmi = 0;
 
 	local64_inc(&uv_nmi_count);
-	uv_cpu_nmi.queries++;
+	this_cpu_inc(uv_cpu_nmi.queries);
 
 	do {
 		nmi = atomic_read(&hub_nmi->in_nmi);
@@ -293,7 +293,7 @@ static void uv_nmi_nr_cpus_ping(void)
 	int cpu;
 
 	for_each_cpu(cpu, uv_nmi_cpu_mask)
-		atomic_set(&uv_cpu_nmi_per(cpu).pinging, 1);
+		uv_cpu_nmi_per(cpu).pinging = 1;
 
 	apic->send_IPI_mask(uv_nmi_cpu_mask, APIC_DM_NMI);
 }
@@ -304,8 +304,8 @@ static void uv_nmi_cleanup_mask(void)
 	int cpu;
 
 	for_each_cpu(cpu, uv_nmi_cpu_mask) {
-		atomic_set(&uv_cpu_nmi_per(cpu).pinging, 0);
-		atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_OUT);
+		uv_cpu_nmi_per(cpu).pinging =  0;
+		uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_OUT;
 		cpumask_clear_cpu(cpu, uv_nmi_cpu_mask);
 	}
 }
@@ -328,7 +328,7 @@ static int uv_nmi_wait_cpus(int first)
 		int loop_delay = uv_nmi_loop_delay;
 
 		for_each_cpu(j, uv_nmi_cpu_mask) {
-			if (atomic_read(&uv_cpu_nmi_per(j).state)) {
+			if (uv_cpu_nmi_per(j).state) {
 				cpumask_clear_cpu(j, uv_nmi_cpu_mask);
 				if (++k >= n)
 					break;
@@ -359,7 +359,7 @@ static int uv_nmi_wait_cpus(int first)
 static void uv_nmi_wait(int master)
 {
 	/* indicate this cpu is in */
-	atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_IN);
+	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_IN);
 
 	/* if not the first cpu in (the master), then we are a slave cpu */
 	if (!master)
@@ -419,7 +419,7 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs)
 			"UV:%sNMI process trace for CPU %d\n", dots, cpu);
 		show_regs(regs);
 	}
-	atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE);
+	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE);
 }
 
 /* Trigger a slave cpu to dump it's state */
@@ -427,20 +427,20 @@ static void uv_nmi_trigger_dump(int cpu)
 {
 	int retry = uv_nmi_trigger_delay;
 
-	if (atomic_read(&uv_cpu_nmi_per(cpu).state) != UV_NMI_STATE_IN)
+	if (uv_cpu_nmi_per(cpu).state != UV_NMI_STATE_IN)
 		return;
 
-	atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_DUMP);
+	uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP;
 	do {
 		cpu_relax();
 		udelay(10);
-		if (atomic_read(&uv_cpu_nmi_per(cpu).state)
+		if (uv_cpu_nmi_per(cpu).state
 				!= UV_NMI_STATE_DUMP)
 			return;
 	} while (--retry > 0);
 
 	pr_crit("UV: CPU %d stuck in process dump function\n", cpu);
-	atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_DUMP_DONE);
+	uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP_DONE;
 }
 
 /* Wait until all cpus ready to exit */
@@ -488,7 +488,7 @@ static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master)
 	} else {
 		while (!atomic_read(&uv_nmi_slave_continue))
 			cpu_relax();
-		while (atomic_read(&uv_cpu_nmi.state) != UV_NMI_STATE_DUMP)
+		while (this_cpu_read(uv_cpu_nmi.state) != UV_NMI_STATE_DUMP)
 			cpu_relax();
 		uv_nmi_dump_state_cpu(cpu, regs);
 	}
@@ -615,7 +615,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 	local_irq_save(flags);
 
 	/* If not a UV System NMI, ignore */
-	if (!atomic_read(&uv_cpu_nmi.pinging) && !uv_check_nmi(hub_nmi)) {
+	if (!this_cpu_read(uv_cpu_nmi.pinging) && !uv_check_nmi(hub_nmi)) {
 		local_irq_restore(flags);
 		return NMI_DONE;
 	}
@@ -639,7 +639,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 		uv_call_kgdb_kdb(cpu, regs, master);
 
 	/* Clear per_cpu "in nmi" flag */
-	atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_OUT);
+	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_OUT);
 
 	/* Clear MMR NMI flag on each hub */
 	uv_clear_nmi(cpu);
@@ -666,16 +666,16 @@ static int uv_handle_nmi_ping(unsigned int reason, struct pt_regs *regs)
 {
 	int ret;
 
-	uv_cpu_nmi.queries++;
-	if (!atomic_read(&uv_cpu_nmi.pinging)) {
+	this_cpu_inc(uv_cpu_nmi.queries);
+	if (!this_cpu_read(uv_cpu_nmi.pinging)) {
 		local64_inc(&uv_nmi_ping_misses);
 		return NMI_DONE;
 	}
 
-	uv_cpu_nmi.pings++;
+	this_cpu_inc(uv_cpu_nmi.pings);
 	local64_inc(&uv_nmi_ping_count);
 	ret = uv_handle_nmi(reason, regs);
-	atomic_set(&uv_cpu_nmi.pinging, 0);
+	this_cpu_write(uv_cpu_nmi.pinging, 0);
 	return ret;
 }
 
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 5c86786bbfd2..a244237f3cfa 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -365,7 +365,7 @@ __setup("uvrtcevt", uv_enable_evt_rtc);
 
 static __init void uv_rtc_register_clockevents(struct work_struct *dummy)
 {
-	struct clock_event_device *ced = &__get_cpu_var(cpu_ced);
+	struct clock_event_device *ced = this_cpu_ptr(&cpu_ced);
 
 	*ced = clock_event_device_uv;
 	ced->cpumask = cpumask_of(smp_processor_id());
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 7d28c885d238..291226b952a9 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -13,13 +13,11 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmzone.h>
+#include <asm/sections.h>
 
 /* Defined in hibernate_asm_32.S */
 extern int restore_image(void);
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
 /* Pointer to the temporary resume page tables */
 pgd_t *resume_pg_dir;
 
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 35e2bb6c0f37..009947d419a6 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -17,11 +17,9 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mtrr.h>
+#include <asm/sections.h>
 #include <asm/suspend.h>
 
-/* References to section boundaries */
-extern __visible const void __nosave_begin, __nosave_end;
-
 /* Defined in hibernate_asm_64.S */
 extern asmlinkage __visible int restore_image(void);
 
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 899dd2454256..f52e033557c9 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -18,8 +18,9 @@ $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 
 targets += kexec-purgatory.c
 
+CMD_BIN2C = $(objtree)/scripts/basic/bin2c
 quiet_cmd_bin2c = BIN2C   $@
-      cmd_bin2c = cat $(obj)/purgatory.ro | $(objtree)/scripts/basic/bin2c kexec_purgatory > $(obj)/kexec-purgatory.c
+      cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@
 
 $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
 	$(call if_changed,bin2c)
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index bbb1d2259ecf..a5efb21d5228 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -695,7 +695,7 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
  *
  */
 static int per_cpu_shndx	= -1;
-Elf_Addr per_cpu_load_addr;
+static Elf_Addr per_cpu_load_addr;
 
 static void percpu_init(void)
 {
diff --git a/arch/x86/um/checksum_32.S b/arch/x86/um/checksum_32.S
index 8d0c420465cc..fa4b8b9841ff 100644
--- a/arch/x86/um/checksum_32.S
+++ b/arch/x86/um/checksum_32.S
@@ -214,242 +214,3 @@ csum_partial:
 	ret
 				
 #endif
-
-/*
-unsigned int csum_partial_copy_generic (const char *src, char *dst,
-				  int len, int sum, int *src_err_ptr, int *dst_err_ptr)
- */ 
-
-/*
- * Copy from ds while checksumming, otherwise like csum_partial
- *
- * The macros SRC and DST specify the type of access for the instruction.
- * thus we can call a custom exception handler for all access types.
- *
- * FIXME: could someone double-check whether I haven't mixed up some SRC and
- *	  DST definitions? It's damn hard to trigger all cases.  I hope I got
- *	  them all but there's no guarantee.
- */
-
-#define SRC(y...)			\
-	9999: y;			\
-	_ASM_EXTABLE(9999b, 6001f)
-
-#define DST(y...)			\
-	9999: y;			\
-	_ASM_EXTABLE(9999b, 6002f)
-
-.align 4
-
-#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
-
-#define ARGBASE 16		
-#define FP		12
-
-csum_partial_copy_generic_i386:
-	subl  $4,%esp	
-	pushl %edi
-	pushl %esi
-	pushl %ebx
-	movl ARGBASE+16(%esp),%eax	# sum
-	movl ARGBASE+12(%esp),%ecx	# len
-	movl ARGBASE+4(%esp),%esi	# src
-	movl ARGBASE+8(%esp),%edi	# dst
-
-	testl $2, %edi			# Check alignment. 
-	jz 2f				# Jump if alignment is ok.
-	subl $2, %ecx			# Alignment uses up two bytes.
-	jae 1f				# Jump if we had at least two bytes.
-	addl $2, %ecx			# ecx was < 2.  Deal with it.
-	jmp 4f
-SRC(1:	movw (%esi), %bx	)
-	addl $2, %esi
-DST(	movw %bx, (%edi)	)
-	addl $2, %edi
-	addw %bx, %ax	
-	adcl $0, %eax
-2:
-	movl %ecx, FP(%esp)
-	shrl $5, %ecx
-	jz 2f
-	testl %esi, %esi
-SRC(1:	movl (%esi), %ebx	)
-SRC(	movl 4(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, (%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 4(%edi)	)
-
-SRC(	movl 8(%esi), %ebx	)
-SRC(	movl 12(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, 8(%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 12(%edi)	)
-
-SRC(	movl 16(%esi), %ebx 	)
-SRC(	movl 20(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, 16(%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 20(%edi)	)
-
-SRC(	movl 24(%esi), %ebx	)
-SRC(	movl 28(%esi), %edx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, 24(%edi)	)
-	adcl %edx, %eax
-DST(	movl %edx, 28(%edi)	)
-
-	lea 32(%esi), %esi
-	lea 32(%edi), %edi
-	dec %ecx
-	jne 1b
-	adcl $0, %eax
-2:	movl FP(%esp), %edx
-	movl %edx, %ecx
-	andl $0x1c, %edx
-	je 4f
-	shrl $2, %edx			# This clears CF
-SRC(3:	movl (%esi), %ebx	)
-	adcl %ebx, %eax
-DST(	movl %ebx, (%edi)	)
-	lea 4(%esi), %esi
-	lea 4(%edi), %edi
-	dec %edx
-	jne 3b
-	adcl $0, %eax
-4:	andl $3, %ecx
-	jz 7f
-	cmpl $2, %ecx
-	jb 5f
-SRC(	movw (%esi), %cx	)
-	leal 2(%esi), %esi
-DST(	movw %cx, (%edi)	)
-	leal 2(%edi), %edi
-	je 6f
-	shll $16,%ecx
-SRC(5:	movb (%esi), %cl	)
-DST(	movb %cl, (%edi)	)
-6:	addl %ecx, %eax
-	adcl $0, %eax
-7:
-5000:
-
-# Exception handler:
-.section .fixup, "ax"							
-
-6001:
-	movl ARGBASE+20(%esp), %ebx	# src_err_ptr
-	movl $-EFAULT, (%ebx)
-
-	# zero the complete destination - computing the rest
-	# is too much work 
-	movl ARGBASE+8(%esp), %edi	# dst
-	movl ARGBASE+12(%esp), %ecx	# len
-	xorl %eax,%eax
-	rep ; stosb
-
-	jmp 5000b
-
-6002:
-	movl ARGBASE+24(%esp), %ebx	# dst_err_ptr
-	movl $-EFAULT,(%ebx)
-	jmp 5000b
-
-.previous
-
-	popl %ebx
-	popl %esi
-	popl %edi
-	popl %ecx			# equivalent to addl $4,%esp
-	ret	
-
-#else
-
-/* Version for PentiumII/PPro */
-
-#define ROUND1(x) \
-	SRC(movl x(%esi), %ebx	)	;	\
-	addl %ebx, %eax			;	\
-	DST(movl %ebx, x(%edi)	)	; 
-
-#define ROUND(x) \
-	SRC(movl x(%esi), %ebx	)	;	\
-	adcl %ebx, %eax			;	\
-	DST(movl %ebx, x(%edi)	)	;
-
-#define ARGBASE 12
-		
-csum_partial_copy_generic_i386:
-	pushl %ebx
-	pushl %edi
-	pushl %esi
-	movl ARGBASE+4(%esp),%esi	#src
-	movl ARGBASE+8(%esp),%edi	#dst	
-	movl ARGBASE+12(%esp),%ecx	#len
-	movl ARGBASE+16(%esp),%eax	#sum
-#	movl %ecx, %edx  
-	movl %ecx, %ebx  
-	movl %esi, %edx
-	shrl $6, %ecx     
-	andl $0x3c, %ebx  
-	negl %ebx
-	subl %ebx, %esi  
-	subl %ebx, %edi  
-	lea  -1(%esi),%edx
-	andl $-32,%edx
-	lea 3f(%ebx,%ebx), %ebx
-	testl %esi, %esi 
-	jmp *%ebx
-1:	addl $64,%esi
-	addl $64,%edi 
-	SRC(movb -32(%edx),%bl)	; SRC(movb (%edx),%bl)
-	ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52)	
-	ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36)	
-	ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20)	
-	ROUND (-16) ROUND(-12) ROUND(-8)  ROUND(-4)	
-3:	adcl $0,%eax
-	addl $64, %edx
-	dec %ecx
-	jge 1b
-4:	movl ARGBASE+12(%esp),%edx	#len
-	andl $3, %edx
-	jz 7f
-	cmpl $2, %edx
-	jb 5f
-SRC(	movw (%esi), %dx         )
-	leal 2(%esi), %esi
-DST(	movw %dx, (%edi)         )
-	leal 2(%edi), %edi
-	je 6f
-	shll $16,%edx
-5:
-SRC(	movb (%esi), %dl         )
-DST(	movb %dl, (%edi)         )
-6:	addl %edx, %eax
-	adcl $0, %eax
-7:
-.section .fixup, "ax"
-6001:	movl	ARGBASE+20(%esp), %ebx	# src_err_ptr	
-	movl $-EFAULT, (%ebx)
-	# zero the complete destination (computing the rest is too much work)
-	movl ARGBASE+8(%esp),%edi	# dst
-	movl ARGBASE+12(%esp),%ecx	# len
-	xorl %eax,%eax
-	rep; stosb
-	jmp 7b
-6002:	movl ARGBASE+24(%esp), %ebx	# dst_err_ptr
-	movl $-EFAULT, (%ebx)
-	jmp  7b			
-.previous				
-
-	popl %esi
-	popl %edi
-	popl %ebx
-	ret
-				
-#undef ROUND
-#undef ROUND1		
-		
-#endif
diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/vdso/vdso2c.h
index fd57829b30d8..0224987556ce 100644
--- a/arch/x86/vdso/vdso2c.h
+++ b/arch/x86/vdso/vdso2c.h
@@ -109,16 +109,18 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 
 	/* Validate mapping addresses. */
 	for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) {
-		if (!syms[i])
+		INT_BITS symval = syms[special_pages[i]];
+
+		if (!symval)
 			continue;  /* The mapping isn't used; ignore it. */
 
-		if (syms[i] % 4096)
+		if (symval % 4096)
 			fail("%s must be a multiple of 4096\n",
 			     required_syms[i].name);
-		if (syms[sym_vvar_start] > syms[i] + 4096)
-			fail("%s underruns begin_vvar\n",
+		if (symval + 4096 < syms[sym_vvar_start])
+			fail("%s underruns vvar_start\n",
 			     required_syms[i].name);
-		if (syms[i] + 4096 > 0)
+		if (symval + 4096 > 0)
 			fail("%s is on the wrong side of the vdso text\n",
 			     required_syms[i].name);
 	}
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index a02e09e18f57..be14cc3e48d5 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -15,12 +15,14 @@
  * with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/bitops.h>
 #include <linux/efi.h>
 #include <linux/init.h>
 #include <linux/string.h>
 
 #include <xen/xen-ops.h>
 
+#include <asm/page.h>
 #include <asm/setup.h>
 
 void __init xen_efi_init(void)
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c0cb11fb5008..1a3f0445432a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -821,7 +821,7 @@ static void xen_convert_trap_info(const struct desc_ptr *desc,
 
 void xen_copy_trap_info(struct trap_info *traps)
 {
-	const struct desc_ptr *desc = &__get_cpu_var(idt_desc);
+	const struct desc_ptr *desc = this_cpu_ptr(&idt_desc);
 
 	xen_convert_trap_info(desc, traps);
 }
@@ -838,7 +838,7 @@ static void xen_load_idt(const struct desc_ptr *desc)
 
 	spin_lock(&lock);
 
-	__get_cpu_var(idt_desc) = *desc;
+	memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc));
 
 	xen_convert_trap_info(desc, traps);
 
@@ -1463,6 +1463,7 @@ static void __ref xen_setup_gdt(int cpu)
 	pv_cpu_ops.load_gdt = xen_load_gdt;
 }
 
+#ifdef CONFIG_XEN_PVH
 /*
  * A PV guest starts with default flags that are not set for PVH, set them
  * here asap.
@@ -1508,17 +1509,21 @@ static void __init xen_pvh_early_guest_init(void)
 		return;
 
 	xen_have_vector_callback = 1;
+
+	xen_pvh_early_cpu_init(0, false);
 	xen_pvh_set_cr_flags(0);
 
 #ifdef CONFIG_X86_32
 	BUG(); /* PVH: Implement proper support. */
 #endif
 }
+#endif    /* CONFIG_XEN_PVH */
 
 /* First C function to be called on Xen boot */
 asmlinkage __visible void __init xen_start_kernel(void)
 {
 	struct physdev_set_iopl set_iopl;
+	unsigned long initrd_start = 0;
 	int rc;
 
 	if (!xen_start_info)
@@ -1527,7 +1532,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	xen_domain_type = XEN_PV_DOMAIN;
 
 	xen_setup_features();
+#ifdef CONFIG_XEN_PVH
 	xen_pvh_early_guest_init();
+#endif
 	xen_setup_machphys_mapping();
 
 	/* Install Xen paravirt ops */
@@ -1559,8 +1566,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #endif
 		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
 
-	__supported_pte_mask |= _PAGE_IOMAP;
-
 	/*
 	 * Prevent page tables from being allocated in highmem, even
 	 * if CONFIG_HIGHPTE is enabled.
@@ -1667,10 +1672,16 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	new_cpu_data.x86_capability[0] = cpuid_edx(1);
 #endif
 
+	if (xen_start_info->mod_start) {
+	    if (xen_start_info->flags & SIF_MOD_START_PFN)
+		initrd_start = PFN_PHYS(xen_start_info->mod_start);
+	    else
+		initrd_start = __pa(xen_start_info->mod_start);
+	}
+
 	/* Poke various useful things into boot_params */
 	boot_params.hdr.type_of_loader = (9 << 4) | 0;
-	boot_params.hdr.ramdisk_image = xen_start_info->mod_start
-		? __pa(xen_start_info->mod_start) : 0;
+	boot_params.hdr.ramdisk_image = initrd_start;
 	boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
 	boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 16fb0099b7f2..f62af7647ec9 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -399,38 +399,14 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
 		if (unlikely(mfn == INVALID_P2M_ENTRY)) {
 			mfn = 0;
 			flags = 0;
-		} else {
-			/*
-			 * Paramount to do this test _after_ the
-			 * INVALID_P2M_ENTRY as INVALID_P2M_ENTRY &
-			 * IDENTITY_FRAME_BIT resolves to true.
-			 */
-			mfn &= ~FOREIGN_FRAME_BIT;
-			if (mfn & IDENTITY_FRAME_BIT) {
-				mfn &= ~IDENTITY_FRAME_BIT;
-				flags |= _PAGE_IOMAP;
-			}
-		}
+		} else
+			mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
 		val = ((pteval_t)mfn << PAGE_SHIFT) | flags;
 	}
 
 	return val;
 }
 
-static pteval_t iomap_pte(pteval_t val)
-{
-	if (val & _PAGE_PRESENT) {
-		unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
-		pteval_t flags = val & PTE_FLAGS_MASK;
-
-		/* We assume the pte frame number is a MFN, so
-		   just use it as-is. */
-		val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
-	}
-
-	return val;
-}
-
 __visible pteval_t xen_pte_val(pte_t pte)
 {
 	pteval_t pteval = pte.pte;
@@ -441,9 +417,6 @@ __visible pteval_t xen_pte_val(pte_t pte)
 		pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT;
 	}
 #endif
-	if (xen_initial_domain() && (pteval & _PAGE_IOMAP))
-		return pteval;
-
 	return pte_mfn_to_pfn(pteval);
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val);
@@ -481,7 +454,6 @@ void xen_set_pat(u64 pat)
 
 __visible pte_t xen_make_pte(pteval_t pte)
 {
-	phys_addr_t addr = (pte & PTE_PFN_MASK);
 #if 0
 	/* If Linux is trying to set a WC pte, then map to the Xen WC.
 	 * If _PAGE_PAT is set, then it probably means it is really
@@ -496,19 +468,7 @@ __visible pte_t xen_make_pte(pteval_t pte)
 			pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT;
 	}
 #endif
-	/*
-	 * Unprivileged domains are allowed to do IOMAPpings for
-	 * PCI passthrough, but not map ISA space.  The ISA
-	 * mappings are just dummy local mappings to keep other
-	 * parts of the kernel happy.
-	 */
-	if (unlikely(pte & _PAGE_IOMAP) &&
-	    (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
-		pte = iomap_pte(pte);
-	} else {
-		pte &= ~_PAGE_IOMAP;
-		pte = pte_pfn_to_mfn(pte);
-	}
+	pte = pte_pfn_to_mfn(pte);
 
 	return native_make_pte(pte);
 }
@@ -2091,7 +2051,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 
 	default:
 		/* By default, set_fixmap is used for hardware mappings */
-		pte = mfn_pte(phys, __pgprot(pgprot_val(prot) | _PAGE_IOMAP));
+		pte = mfn_pte(phys, prot);
 		break;
 	}
 
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 0d82003e76ad..ea54a08d8301 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -54,7 +54,7 @@ DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
 
 void xen_mc_flush(void)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct multicall_entry *mc;
 	int ret = 0;
 	unsigned long flags;
@@ -131,7 +131,7 @@ void xen_mc_flush(void)
 
 struct multicall_space __xen_mc_entry(size_t args)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct multicall_space ret;
 	unsigned argidx = roundup(b->argidx, sizeof(u64));
 
@@ -162,7 +162,7 @@ struct multicall_space __xen_mc_entry(size_t args)
 
 struct multicall_space xen_mc_extend_args(unsigned long op, size_t size)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct multicall_space ret = { NULL, NULL };
 
 	BUG_ON(preemptible());
@@ -192,7 +192,7 @@ out:
 
 void xen_mc_callback(void (*fn)(void *), void *data)
 {
-	struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+	struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
 	struct callback *cb;
 
 	if (b->cbidx == MC_BATCH) {
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 3172692381ae..9f5983b01ed9 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -173,6 +173,7 @@
 #include <xen/balloon.h>
 #include <xen/grant_table.h>
 
+#include "p2m.h"
 #include "multicalls.h"
 #include "xen-ops.h"
 
@@ -180,12 +181,6 @@ static void __init m2p_override_init(void);
 
 unsigned long xen_max_p2m_pfn __read_mostly;
 
-#define P2M_PER_PAGE		(PAGE_SIZE / sizeof(unsigned long))
-#define P2M_MID_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long *))
-#define P2M_TOP_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long **))
-
-#define MAX_P2M_PFN		(P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)
-
 /* Placeholders for holes in the address space */
 static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE);
 static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE);
@@ -202,16 +197,12 @@ static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_identity_mfn, P2M_MID_PER_PAGE);
 RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
 RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
 
-/* We might hit two boundary violations at the start and end, at max each
- * boundary violation will require three middle nodes. */
-RESERVE_BRK(p2m_mid_extra, PAGE_SIZE * 2 * 3);
-
-/* When we populate back during bootup, the amount of pages can vary. The
- * max we have is seen is 395979, but that does not mean it can't be more.
- * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle
- * it can re-use Xen provided mfn_list array, so we only need to allocate at
- * most three P2M top nodes. */
-RESERVE_BRK(p2m_populated, PAGE_SIZE * 3);
+/* For each I/O range remapped we may lose up to two leaf pages for the boundary
+ * violations and three mid pages to cover up to 3GB. With
+ * early_can_reuse_p2m_middle() most of the leaf pages will be reused by the
+ * remapped region.
+ */
+RESERVE_BRK(p2m_identity_remap, PAGE_SIZE * 2 * 3 * MAX_REMAP_RANGES);
 
 static inline unsigned p2m_top_index(unsigned long pfn)
 {
diff --git a/arch/x86/xen/p2m.h b/arch/x86/xen/p2m.h
new file mode 100644
index 000000000000..ad8aee24ab72
--- /dev/null
+++ b/arch/x86/xen/p2m.h
@@ -0,0 +1,15 @@
+#ifndef _XEN_P2M_H
+#define _XEN_P2M_H
+
+#define P2M_PER_PAGE        (PAGE_SIZE / sizeof(unsigned long))
+#define P2M_MID_PER_PAGE    (PAGE_SIZE / sizeof(unsigned long *))
+#define P2M_TOP_PER_PAGE    (PAGE_SIZE / sizeof(unsigned long **))
+
+#define MAX_P2M_PFN         (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)
+
+#define MAX_REMAP_RANGES    10
+
+extern unsigned long __init set_phys_range_identity(unsigned long pfn_s,
+                                      unsigned long pfn_e);
+
+#endif  /* _XEN_P2M_H */
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 2e555163c2fe..af7216128d93 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -29,6 +29,7 @@
 #include <xen/features.h>
 #include "xen-ops.h"
 #include "vdso.h"
+#include "p2m.h"
 
 /* These are code, but not functions.  Defined in entry.S */
 extern const char xen_hypervisor_callback[];
@@ -46,6 +47,9 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 /* Number of pages released from the initial allocation. */
 unsigned long xen_released_pages;
 
+/* Buffer used to remap identity mapped pages */
+unsigned long xen_remap_buf[P2M_PER_PAGE] __initdata;
+
 /* 
  * The maximum amount of extra memory compared to the base size.  The
  * main scaling factor is the size of struct page.  At extreme ratios
@@ -151,107 +155,325 @@ static unsigned long __init xen_do_chunk(unsigned long start,
 	return len;
 }
 
-static unsigned long __init xen_release_chunk(unsigned long start,
-					      unsigned long end)
-{
-	return xen_do_chunk(start, end, true);
-}
-
-static unsigned long __init xen_populate_chunk(
+/*
+ * Finds the next RAM pfn available in the E820 map after min_pfn.
+ * This function updates min_pfn with the pfn found and returns
+ * the size of that range or zero if not found.
+ */
+static unsigned long __init xen_find_pfn_range(
 	const struct e820entry *list, size_t map_size,
-	unsigned long max_pfn, unsigned long *last_pfn,
-	unsigned long credits_left)
+	unsigned long *min_pfn)
 {
 	const struct e820entry *entry;
 	unsigned int i;
 	unsigned long done = 0;
-	unsigned long dest_pfn;
 
 	for (i = 0, entry = list; i < map_size; i++, entry++) {
 		unsigned long s_pfn;
 		unsigned long e_pfn;
-		unsigned long pfns;
-		long capacity;
-
-		if (credits_left <= 0)
-			break;
 
 		if (entry->type != E820_RAM)
 			continue;
 
 		e_pfn = PFN_DOWN(entry->addr + entry->size);
 
-		/* We only care about E820 after the xen_start_info->nr_pages */
-		if (e_pfn <= max_pfn)
+		/* We only care about E820 after this */
+		if (e_pfn < *min_pfn)
 			continue;
 
 		s_pfn = PFN_UP(entry->addr);
-		/* If the E820 falls within the nr_pages, we want to start
-		 * at the nr_pages PFN.
-		 * If that would mean going past the E820 entry, skip it
+
+		/* If min_pfn falls within the E820 entry, we want to start
+		 * at the min_pfn PFN.
 		 */
-		if (s_pfn <= max_pfn) {
-			capacity = e_pfn - max_pfn;
-			dest_pfn = max_pfn;
+		if (s_pfn <= *min_pfn) {
+			done = e_pfn - *min_pfn;
 		} else {
-			capacity = e_pfn - s_pfn;
-			dest_pfn = s_pfn;
+			done = e_pfn - s_pfn;
+			*min_pfn = s_pfn;
 		}
+		break;
+	}
 
-		if (credits_left < capacity)
-			capacity = credits_left;
+	return done;
+}
 
-		pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false);
-		done += pfns;
-		*last_pfn = (dest_pfn + pfns);
-		if (pfns < capacity)
-			break;
-		credits_left -= pfns;
+/*
+ * This releases a chunk of memory and then does the identity map. It's used as
+ * as a fallback if the remapping fails.
+ */
+static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
+	unsigned long end_pfn, unsigned long nr_pages, unsigned long *identity,
+	unsigned long *released)
+{
+	WARN_ON(start_pfn > end_pfn);
+
+	/* Need to release pages first */
+	*released += xen_do_chunk(start_pfn, min(end_pfn, nr_pages), true);
+	*identity += set_phys_range_identity(start_pfn, end_pfn);
+}
+
+/*
+ * Helper function to update both the p2m and m2p tables.
+ */
+static unsigned long __init xen_update_mem_tables(unsigned long pfn,
+						  unsigned long mfn)
+{
+	struct mmu_update update = {
+		.ptr = ((unsigned long long)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE,
+		.val = pfn
+	};
+
+	/* Update p2m */
+	if (!early_set_phys_to_machine(pfn, mfn)) {
+		WARN(1, "Failed to set p2m mapping for pfn=%ld mfn=%ld\n",
+		     pfn, mfn);
+		return false;
 	}
-	return done;
+
+	/* Update m2p */
+	if (HYPERVISOR_mmu_update(&update, 1, NULL, DOMID_SELF) < 0) {
+		WARN(1, "Failed to set m2p mapping for mfn=%ld pfn=%ld\n",
+		     mfn, pfn);
+		return false;
+	}
+
+	return true;
 }
 
-static void __init xen_set_identity_and_release_chunk(
-	unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
-	unsigned long *released, unsigned long *identity)
+/*
+ * This function updates the p2m and m2p tables with an identity map from
+ * start_pfn to start_pfn+size and remaps the underlying RAM of the original
+ * allocation at remap_pfn. It must do so carefully in P2M_PER_PAGE sized blocks
+ * to not exhaust the reserved brk space. Doing it in properly aligned blocks
+ * ensures we only allocate the minimum required leaf pages in the p2m table. It
+ * copies the existing mfns from the p2m table under the 1:1 map, overwrites
+ * them with the identity map and then updates the p2m and m2p tables with the
+ * remapped memory.
+ */
+static unsigned long __init xen_do_set_identity_and_remap_chunk(
+        unsigned long start_pfn, unsigned long size, unsigned long remap_pfn)
 {
-	unsigned long pfn;
+	unsigned long ident_pfn_iter, remap_pfn_iter;
+	unsigned long ident_start_pfn_align, remap_start_pfn_align;
+	unsigned long ident_end_pfn_align, remap_end_pfn_align;
+	unsigned long ident_boundary_pfn, remap_boundary_pfn;
+	unsigned long ident_cnt = 0;
+	unsigned long remap_cnt = 0;
+	unsigned long left = size;
+	unsigned long mod;
+	int i;
+
+	WARN_ON(size == 0);
+
+	BUG_ON(xen_feature(XENFEAT_auto_translated_physmap));
 
 	/*
-	 * If the PFNs are currently mapped, clear the mappings
-	 * (except for the ISA region which must be 1:1 mapped) to
-	 * release the refcounts (in Xen) on the original frames.
+	 * Determine the proper alignment to remap memory in P2M_PER_PAGE sized
+	 * blocks. We need to keep track of both the existing pfn mapping and
+	 * the new pfn remapping.
 	 */
-	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
-		pte_t pte = __pte_ma(0);
+	mod = start_pfn % P2M_PER_PAGE;
+	ident_start_pfn_align =
+		mod ? (start_pfn - mod + P2M_PER_PAGE) : start_pfn;
+	mod = remap_pfn % P2M_PER_PAGE;
+	remap_start_pfn_align =
+		mod ? (remap_pfn - mod + P2M_PER_PAGE) : remap_pfn;
+	mod = (start_pfn + size) % P2M_PER_PAGE;
+	ident_end_pfn_align = start_pfn + size - mod;
+	mod = (remap_pfn + size) % P2M_PER_PAGE;
+	remap_end_pfn_align = remap_pfn + size - mod;
+
+	/* Iterate over each p2m leaf node in each range */
+	for (ident_pfn_iter = ident_start_pfn_align, remap_pfn_iter = remap_start_pfn_align;
+	     ident_pfn_iter < ident_end_pfn_align && remap_pfn_iter < remap_end_pfn_align;
+	     ident_pfn_iter += P2M_PER_PAGE, remap_pfn_iter += P2M_PER_PAGE) {
+		/* Check we aren't past the end */
+		BUG_ON(ident_pfn_iter + P2M_PER_PAGE > start_pfn + size);
+		BUG_ON(remap_pfn_iter + P2M_PER_PAGE > remap_pfn + size);
+
+		/* Save p2m mappings */
+		for (i = 0; i < P2M_PER_PAGE; i++)
+			xen_remap_buf[i] = pfn_to_mfn(ident_pfn_iter + i);
+
+		/* Set identity map which will free a p2m leaf */
+		ident_cnt += set_phys_range_identity(ident_pfn_iter,
+			ident_pfn_iter + P2M_PER_PAGE);
+
+#ifdef DEBUG
+		/* Helps verify a p2m leaf has been freed */
+		for (i = 0; i < P2M_PER_PAGE; i++) {
+			unsigned int pfn = ident_pfn_iter + i;
+			BUG_ON(pfn_to_mfn(pfn) != pfn);
+		}
+#endif
+		/* Now remap memory */
+		for (i = 0; i < P2M_PER_PAGE; i++) {
+			unsigned long mfn = xen_remap_buf[i];
+
+			/* This will use the p2m leaf freed above */
+			if (!xen_update_mem_tables(remap_pfn_iter + i, mfn)) {
+				WARN(1, "Failed to update mem mapping for pfn=%ld mfn=%ld\n",
+					remap_pfn_iter + i, mfn);
+				return 0;
+			}
+
+			remap_cnt++;
+		}
 
-		if (pfn < PFN_UP(ISA_END_ADDRESS))
-			pte = mfn_pte(pfn, PAGE_KERNEL_IO);
+		left -= P2M_PER_PAGE;
+	}
 
-		(void)HYPERVISOR_update_va_mapping(
-			(unsigned long)__va(pfn << PAGE_SHIFT), pte, 0);
+	/* Max boundary space possible */
+	BUG_ON(left > (P2M_PER_PAGE - 1) * 2);
+
+	/* Now handle the boundary conditions */
+	ident_boundary_pfn = start_pfn;
+	remap_boundary_pfn = remap_pfn;
+	for (i = 0; i < left; i++) {
+		unsigned long mfn;
+
+		/* These two checks move from the start to end boundaries */
+		if (ident_boundary_pfn == ident_start_pfn_align)
+			ident_boundary_pfn = ident_pfn_iter;
+		if (remap_boundary_pfn == remap_start_pfn_align)
+			remap_boundary_pfn = remap_pfn_iter;
+
+		/* Check we aren't past the end */
+		BUG_ON(ident_boundary_pfn >= start_pfn + size);
+		BUG_ON(remap_boundary_pfn >= remap_pfn + size);
+
+		mfn = pfn_to_mfn(ident_boundary_pfn);
+
+		if (!xen_update_mem_tables(remap_boundary_pfn, mfn)) {
+			WARN(1, "Failed to update mem mapping for pfn=%ld mfn=%ld\n",
+				remap_pfn_iter + i, mfn);
+			return 0;
+		}
+		remap_cnt++;
+
+		ident_boundary_pfn++;
+		remap_boundary_pfn++;
 	}
 
-	if (start_pfn < nr_pages)
-		*released += xen_release_chunk(
-			start_pfn, min(end_pfn, nr_pages));
+	/* Finish up the identity map */
+	if (ident_start_pfn_align >= ident_end_pfn_align) {
+		/*
+                 * In this case we have an identity range which does not span an
+                 * aligned block so everything needs to be identity mapped here.
+                 * If we didn't check this we might remap too many pages since
+                 * the align boundaries are not meaningful in this case.
+	         */
+		ident_cnt += set_phys_range_identity(start_pfn,
+			start_pfn + size);
+	} else {
+		/* Remapped above so check each end of the chunk */
+		if (start_pfn < ident_start_pfn_align)
+			ident_cnt += set_phys_range_identity(start_pfn,
+				ident_start_pfn_align);
+		if (start_pfn + size > ident_pfn_iter)
+			ident_cnt += set_phys_range_identity(ident_pfn_iter,
+				start_pfn + size);
+	}
 
-	*identity += set_phys_range_identity(start_pfn, end_pfn);
+	BUG_ON(ident_cnt != size);
+	BUG_ON(remap_cnt != size);
+
+	return size;
 }
 
-static unsigned long __init xen_set_identity_and_release(
-	const struct e820entry *list, size_t map_size, unsigned long nr_pages)
+/*
+ * This function takes a contiguous pfn range that needs to be identity mapped
+ * and:
+ *
+ *  1) Finds a new range of pfns to use to remap based on E820 and remap_pfn.
+ *  2) Calls the do_ function to actually do the mapping/remapping work.
+ *
+ * The goal is to not allocate additional memory but to remap the existing
+ * pages. In the case of an error the underlying memory is simply released back
+ * to Xen and not remapped.
+ */
+static unsigned long __init xen_set_identity_and_remap_chunk(
+        const struct e820entry *list, size_t map_size, unsigned long start_pfn,
+	unsigned long end_pfn, unsigned long nr_pages, unsigned long remap_pfn,
+	unsigned long *identity, unsigned long *remapped,
+	unsigned long *released)
+{
+	unsigned long pfn;
+	unsigned long i = 0;
+	unsigned long n = end_pfn - start_pfn;
+
+	while (i < n) {
+		unsigned long cur_pfn = start_pfn + i;
+		unsigned long left = n - i;
+		unsigned long size = left;
+		unsigned long remap_range_size;
+
+		/* Do not remap pages beyond the current allocation */
+		if (cur_pfn >= nr_pages) {
+			/* Identity map remaining pages */
+			*identity += set_phys_range_identity(cur_pfn,
+				cur_pfn + size);
+			break;
+		}
+		if (cur_pfn + size > nr_pages)
+			size = nr_pages - cur_pfn;
+
+		remap_range_size = xen_find_pfn_range(list, map_size,
+						      &remap_pfn);
+		if (!remap_range_size) {
+			pr_warning("Unable to find available pfn range, not remapping identity pages\n");
+			xen_set_identity_and_release_chunk(cur_pfn,
+				cur_pfn + left, nr_pages, identity, released);
+			break;
+		}
+		/* Adjust size to fit in current e820 RAM region */
+		if (size > remap_range_size)
+			size = remap_range_size;
+
+		if (!xen_do_set_identity_and_remap_chunk(cur_pfn, size, remap_pfn)) {
+			WARN(1, "Failed to remap 1:1 memory cur_pfn=%ld size=%ld remap_pfn=%ld\n",
+				cur_pfn, size, remap_pfn);
+			xen_set_identity_and_release_chunk(cur_pfn,
+				cur_pfn + left, nr_pages, identity, released);
+			break;
+		}
+
+		/* Update variables to reflect new mappings. */
+		i += size;
+		remap_pfn += size;
+		*identity += size;
+		*remapped += size;
+	}
+
+	/*
+	 * If the PFNs are currently mapped, the VA mapping also needs
+	 * to be updated to be 1:1.
+	 */
+	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++)
+		(void)HYPERVISOR_update_va_mapping(
+			(unsigned long)__va(pfn << PAGE_SHIFT),
+			mfn_pte(pfn, PAGE_KERNEL_IO), 0);
+
+	return remap_pfn;
+}
+
+static unsigned long __init xen_set_identity_and_remap(
+	const struct e820entry *list, size_t map_size, unsigned long nr_pages,
+	unsigned long *released)
 {
 	phys_addr_t start = 0;
-	unsigned long released = 0;
 	unsigned long identity = 0;
+	unsigned long remapped = 0;
+	unsigned long last_pfn = nr_pages;
 	const struct e820entry *entry;
+	unsigned long num_released = 0;
 	int i;
 
 	/*
 	 * Combine non-RAM regions and gaps until a RAM region (or the
 	 * end of the map) is reached, then set the 1:1 map and
-	 * release the pages (if available) in those non-RAM regions.
+	 * remap the memory in those non-RAM regions.
 	 *
 	 * The combined non-RAM regions are rounded to a whole number
 	 * of pages so any partial pages are accessible via the 1:1
@@ -269,22 +491,24 @@ static unsigned long __init xen_set_identity_and_release(
 				end_pfn = PFN_UP(entry->addr);
 
 			if (start_pfn < end_pfn)
-				xen_set_identity_and_release_chunk(
-					start_pfn, end_pfn, nr_pages,
-					&released, &identity);
-
+				last_pfn = xen_set_identity_and_remap_chunk(
+						list, map_size, start_pfn,
+						end_pfn, nr_pages, last_pfn,
+						&identity, &remapped,
+						&num_released);
 			start = end;
 		}
 	}
 
-	if (released)
-		printk(KERN_INFO "Released %lu pages of unused memory\n", released);
-	if (identity)
-		printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
+	*released = num_released;
 
-	return released;
-}
+	pr_info("Set %ld page(s) to 1-1 mapping\n", identity);
+	pr_info("Remapped %ld page(s), last_pfn=%ld\n", remapped,
+		last_pfn);
+	pr_info("Released %ld page(s)\n", num_released);
 
+	return last_pfn;
+}
 static unsigned long __init xen_get_max_pages(void)
 {
 	unsigned long max_pages = MAX_DOMAIN_PAGES;
@@ -347,7 +571,6 @@ char * __init xen_memory_setup(void)
 	unsigned long max_pages;
 	unsigned long last_pfn = 0;
 	unsigned long extra_pages = 0;
-	unsigned long populated;
 	int i;
 	int op;
 
@@ -392,20 +615,11 @@ char * __init xen_memory_setup(void)
 		extra_pages += max_pages - max_pfn;
 
 	/*
-	 * Set P2M for all non-RAM pages and E820 gaps to be identity
-	 * type PFNs.  Any RAM pages that would be made inaccesible by
-	 * this are first released.
+	 * Set identity map on non-RAM pages and remap the underlying RAM.
 	 */
-	xen_released_pages = xen_set_identity_and_release(
-		map, memmap.nr_entries, max_pfn);
-
-	/*
-	 * Populate back the non-RAM pages and E820 gaps that had been
-	 * released. */
-	populated = xen_populate_chunk(map, memmap.nr_entries,
-			max_pfn, &last_pfn, xen_released_pages);
+	last_pfn = xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn,
+					      &xen_released_pages);
 
-	xen_released_pages -= populated;
 	extra_pages += xen_released_pages;
 
 	if (last_pfn > max_pfn) {
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 7005974c3ff3..8650cdb53209 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -37,6 +37,7 @@
 #include <xen/hvc-console.h>
 #include "xen-ops.h"
 #include "mmu.h"
+#include "smp.h"
 
 cpumask_var_t xen_cpu_initialized_map;
 
@@ -99,10 +100,14 @@ static void cpu_bringup(void)
 	wmb();			/* make sure everything is out */
 }
 
-/* Note: cpu parameter is only relevant for PVH */
-static void cpu_bringup_and_idle(int cpu)
+/*
+ * Note: cpu parameter is only relevant for PVH. The reason for passing it
+ * is we can't do smp_processor_id until the percpu segments are loaded, for
+ * which we need the cpu number! So we pass it in rdi as first parameter.
+ */
+asmlinkage __visible void cpu_bringup_and_idle(int cpu)
 {
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_XEN_PVH
 	if (xen_feature(XENFEAT_auto_translated_physmap) &&
 	    xen_feature(XENFEAT_supervisor_mode_kernel))
 		xen_pvh_secondary_vcpu_init(cpu);
@@ -360,6 +365,8 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	struct desc_struct *gdt;
 	unsigned long gdt_mfn;
 
+	/* used to tell cpu_init() that it can proceed with initialization */
+	cpumask_set_cpu(cpu, cpu_callout_mask);
 	if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map))
 		return 0;
 
@@ -374,11 +381,10 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	ctxt->user_regs.fs = __KERNEL_PERCPU;
 	ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
 #endif
-	ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
-
 	memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
 
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+		ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
 		ctxt->flags = VGCF_IN_KERNEL;
 		ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
 		ctxt->user_regs.ds = __USER_DS;
@@ -413,15 +419,18 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 					(unsigned long)xen_failsafe_callback;
 		ctxt->user_regs.cs = __KERNEL_CS;
 		per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
-#ifdef CONFIG_X86_32
 	}
-#else
-	} else
-		/* N.B. The user_regs.eip (cpu_bringup_and_idle) is called with
-		 * %rdi having the cpu number - which means are passing in
-		 * as the first parameter the cpu. Subtle!
+#ifdef CONFIG_XEN_PVH
+	else {
+		/*
+		 * The vcpu comes on kernel page tables which have the NX pte
+		 * bit set. This means before DS/SS is touched, NX in
+		 * EFER must be set. Hence the following assembly glue code.
 		 */
+		ctxt->user_regs.eip = (unsigned long)xen_pvh_early_cpu_init;
 		ctxt->user_regs.rdi = cpu;
+		ctxt->user_regs.rsi = true;  /* entry == true */
+	}
 #endif
 	ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
 	ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir));
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index c7c2d89efd76..963d62a35c82 100644
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -8,4 +8,12 @@ extern void xen_send_IPI_allbutself(int vector);
 extern void xen_send_IPI_all(int vector);
 extern void xen_send_IPI_self(int vector);
 
+#ifdef CONFIG_XEN_PVH
+extern void xen_pvh_early_cpu_init(int cpu, bool entry);
+#else
+static inline void xen_pvh_early_cpu_init(int cpu, bool entry)
+{
+}
+#endif
+
 #endif
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 0ba5f3b967f0..23b45eb9a89c 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -109,7 +109,7 @@ static bool xen_pvspin = true;
 __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 {
 	int irq = __this_cpu_read(lock_kicker_irq);
-	struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting);
+	struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting);
 	int cpu = smp_processor_id();
 	u64 start;
 	unsigned long flags;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 5718b0b58b60..a1d430b112b3 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -80,7 +80,7 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
 
 	BUG_ON(preemptible());
 
-	state = &__get_cpu_var(xen_runstate);
+	state = this_cpu_ptr(&xen_runstate);
 
 	/*
 	 * The runstate info is always updated by the hypervisor on
@@ -123,7 +123,7 @@ static void do_stolen_accounting(void)
 
 	WARN_ON(state.state != RUNSTATE_running);
 
-	snap = &__get_cpu_var(xen_runstate_snapshot);
+	snap = this_cpu_ptr(&xen_runstate_snapshot);
 
 	/* work out how much time the VCPU has not been runn*ing*  */
 	runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable];
@@ -158,7 +158,7 @@ cycle_t xen_clocksource_read(void)
 	cycle_t ret;
 
 	preempt_disable_notrace();
-	src = &__get_cpu_var(xen_vcpu)->time;
+	src = this_cpu_ptr(&xen_vcpu->time);
 	ret = pvclock_clocksource_read(src);
 	preempt_enable_notrace();
 	return ret;
@@ -397,7 +397,7 @@ static DEFINE_PER_CPU(struct xen_clock_event_device, xen_clock_events) = { .evt.
 
 static irqreturn_t xen_timer_interrupt(int irq, void *dev_id)
 {
-	struct clock_event_device *evt = &__get_cpu_var(xen_clock_events).evt;
+	struct clock_event_device *evt = this_cpu_ptr(&xen_clock_events.evt);
 	irqreturn_t ret;
 
 	ret = IRQ_NONE;
@@ -460,7 +460,7 @@ void xen_setup_cpu_clockevents(void)
 {
 	BUG_ON(preemptible());
 
-	clockevents_register_device(&__get_cpu_var(xen_clock_events).evt);
+	clockevents_register_device(this_cpu_ptr(&xen_clock_events.evt));
 }
 
 void xen_timer_resume(void)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 485b69585540..674b222544b7 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -47,6 +47,41 @@ ENTRY(startup_xen)
 
 	__FINIT
 
+#ifdef CONFIG_XEN_PVH
+/*
+ * xen_pvh_early_cpu_init() - early PVH VCPU initialization
+ * @cpu:   this cpu number (%rdi)
+ * @entry: true if this is a secondary vcpu coming up on this entry
+ *         point, false if this is the boot CPU being initialized for
+ *         the first time (%rsi)
+ *
+ * Note: This is called as a function on the boot CPU, and is the entry point
+ *       on the secondary CPU.
+ */
+ENTRY(xen_pvh_early_cpu_init)
+	mov     %rsi, %r11
+
+	/* Gather features to see if NX implemented. */
+	mov     $0x80000001, %eax
+	cpuid
+	mov     %edx, %esi
+
+	mov     $MSR_EFER, %ecx
+	rdmsr
+	bts     $_EFER_SCE, %eax
+
+	bt      $20, %esi
+	jnc     1f      	/* No NX, skip setting it */
+	bts     $_EFER_NX, %eax
+1:	wrmsr
+#ifdef CONFIG_SMP
+	cmp     $0, %r11b
+	jne     cpu_bringup_and_idle
+#endif
+	ret
+
+#endif /* CONFIG_XEN_PVH */
+
 .pushsection .text
 	.balign PAGE_SIZE
 ENTRY(hypercall_page)
@@ -124,6 +159,7 @@ NEXT_HYPERCALL(arch_6)
 	ELFNOTE(Xen, XEN_ELFNOTE_L1_MFN_VALID,
 		.quad _PAGE_PRESENT; .quad _PAGE_PRESENT)
 	ELFNOTE(Xen, XEN_ELFNOTE_SUSPEND_CANCEL, .long 1)
+	ELFNOTE(Xen, XEN_ELFNOTE_MOD_START_PFN,  .long 1)
 	ELFNOTE(Xen, XEN_ELFNOTE_HV_START_LOW,   _ASM_PTR __HYPERVISOR_VIRT_START)
 	ELFNOTE(Xen, XEN_ELFNOTE_PADDR_OFFSET,   _ASM_PTR 0)
 
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index c3d20ba6eb86..105d38922c44 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -12,6 +12,7 @@ generic-y += hardirq.h
 generic-y += hash.h
 generic-y += ioctl.h
 generic-y += irq_regs.h
+generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index e5103b47a8ce..00b7d46b35b8 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -47,7 +47,7 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
 
 /**
  * atomic_set - set atomic variable
@@ -58,165 +58,96 @@
  */
 #define atomic_set(v,i)		((v)->counter = (i))
 
-/**
- * atomic_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v.
- */
-static inline void atomic_add(int i, atomic_t * v)
-{
 #if XCHAL_HAVE_S32C1I
-	unsigned long tmp;
-	int result;
-
-	__asm__ __volatile__(
-			"1:     l32i    %1, %3, 0\n"
-			"       wsr     %1, scompare1\n"
-			"       add     %0, %1, %2\n"
-			"       s32c1i  %0, %3, 0\n"
-			"       bne     %0, %1, 1b\n"
-			: "=&a" (result), "=&a" (tmp)
-			: "a" (i), "a" (v)
-			: "memory"
-			);
-#else
-	unsigned int vval;
-
-	__asm__ __volatile__(
-			"       rsil    a15, "__stringify(LOCKLEVEL)"\n"
-			"       l32i    %0, %2, 0\n"
-			"       add     %0, %0, %1\n"
-			"       s32i    %0, %2, 0\n"
-			"       wsr     a15, ps\n"
-			"       rsync\n"
-			: "=&a" (vval)
-			: "a" (i), "a" (v)
-			: "a15", "memory"
-			);
-#endif
-}
-
-/**
- * atomic_sub - subtract the atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v.
- */
-static inline void atomic_sub(int i, atomic_t *v)
-{
-#if XCHAL_HAVE_S32C1I
-	unsigned long tmp;
-	int result;
-
-	__asm__ __volatile__(
-			"1:     l32i    %1, %3, 0\n"
-			"       wsr     %1, scompare1\n"
-			"       sub     %0, %1, %2\n"
-			"       s32c1i  %0, %3, 0\n"
-			"       bne     %0, %1, 1b\n"
-			: "=&a" (result), "=&a" (tmp)
-			: "a" (i), "a" (v)
-			: "memory"
-			);
-#else
-	unsigned int vval;
-
-	__asm__ __volatile__(
-			"       rsil    a15, "__stringify(LOCKLEVEL)"\n"
-			"       l32i    %0, %2, 0\n"
-			"       sub     %0, %0, %1\n"
-			"       s32i    %0, %2, 0\n"
-			"       wsr     a15, ps\n"
-			"       rsync\n"
-			: "=&a" (vval)
-			: "a" (i), "a" (v)
-			: "a15", "memory"
-			);
-#endif
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t * v)			\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	__asm__ __volatile__(						\
+			"1:     l32i    %1, %3, 0\n"			\
+			"       wsr     %1, scompare1\n"		\
+			"       " #op " %0, %1, %2\n"			\
+			"       s32c1i  %0, %3, 0\n"			\
+			"       bne     %0, %1, 1b\n"			\
+			: "=&a" (result), "=&a" (tmp)			\
+			: "a" (i), "a" (v)				\
+			: "memory"					\
+			);						\
+}									\
+
+#define ATOMIC_OP_RETURN(op)						\
+static inline int atomic_##op##_return(int i, atomic_t * v)		\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	__asm__ __volatile__(						\
+			"1:     l32i    %1, %3, 0\n"			\
+			"       wsr     %1, scompare1\n"		\
+			"       " #op " %0, %1, %2\n"			\
+			"       s32c1i  %0, %3, 0\n"			\
+			"       bne     %0, %1, 1b\n"			\
+			"       " #op " %0, %0, %2\n"			\
+			: "=&a" (result), "=&a" (tmp)			\
+			: "a" (i), "a" (v)				\
+			: "memory"					\
+			);						\
+									\
+	return result;							\
 }
 
-/*
- * We use atomic_{add|sub}_return to define other functions.
- */
-
-static inline int atomic_add_return(int i, atomic_t * v)
-{
-#if XCHAL_HAVE_S32C1I
-	unsigned long tmp;
-	int result;
-
-	__asm__ __volatile__(
-			"1:     l32i    %1, %3, 0\n"
-			"       wsr     %1, scompare1\n"
-			"       add     %0, %1, %2\n"
-			"       s32c1i  %0, %3, 0\n"
-			"       bne     %0, %1, 1b\n"
-			"       add     %0, %0, %2\n"
-			: "=&a" (result), "=&a" (tmp)
-			: "a" (i), "a" (v)
-			: "memory"
-			);
-
-	return result;
-#else
-	unsigned int vval;
-
-	__asm__ __volatile__(
-			"       rsil    a15,"__stringify(LOCKLEVEL)"\n"
-			"       l32i    %0, %2, 0\n"
-			"       add     %0, %0, %1\n"
-			"       s32i    %0, %2, 0\n"
-			"       wsr     a15, ps\n"
-			"       rsync\n"
-			: "=&a" (vval)
-			: "a" (i), "a" (v)
-			: "a15", "memory"
-			);
-
-	return vval;
-#endif
+#else /* XCHAL_HAVE_S32C1I */
+
+#define ATOMIC_OP(op)							\
+static inline void atomic_##op(int i, atomic_t * v)			\
+{									\
+	unsigned int vval;						\
+									\
+	__asm__ __volatile__(						\
+			"       rsil    a15, "__stringify(LOCKLEVEL)"\n"\
+			"       l32i    %0, %2, 0\n"			\
+			"       " #op " %0, %0, %1\n"			\
+			"       s32i    %0, %2, 0\n"			\
+			"       wsr     a15, ps\n"			\
+			"       rsync\n"				\
+			: "=&a" (vval)					\
+			: "a" (i), "a" (v)				\
+			: "a15", "memory"				\
+			);						\
+}									\
+
+#define ATOMIC_OP_RETURN(op)						\
+static inline int atomic_##op##_return(int i, atomic_t * v)		\
+{									\
+	unsigned int vval;						\
+									\
+	__asm__ __volatile__(						\
+			"       rsil    a15,"__stringify(LOCKLEVEL)"\n"	\
+			"       l32i    %0, %2, 0\n"			\
+			"       " #op " %0, %0, %1\n"			\
+			"       s32i    %0, %2, 0\n"			\
+			"       wsr     a15, ps\n"			\
+			"       rsync\n"				\
+			: "=&a" (vval)					\
+			: "a" (i), "a" (v)				\
+			: "a15", "memory"				\
+			);						\
+									\
+	return vval;							\
 }
 
-static inline int atomic_sub_return(int i, atomic_t * v)
-{
-#if XCHAL_HAVE_S32C1I
-	unsigned long tmp;
-	int result;
+#endif /* XCHAL_HAVE_S32C1I */
 
-	__asm__ __volatile__(
-			"1:     l32i    %1, %3, 0\n"
-			"       wsr     %1, scompare1\n"
-			"       sub     %0, %1, %2\n"
-			"       s32c1i  %0, %3, 0\n"
-			"       bne     %0, %1, 1b\n"
-			"       sub     %0, %0, %2\n"
-			: "=&a" (result), "=&a" (tmp)
-			: "a" (i), "a" (v)
-			: "memory"
-			);
+#define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op)
 
-	return result;
-#else
-	unsigned int vval;
-
-	__asm__ __volatile__(
-			"       rsil    a15,"__stringify(LOCKLEVEL)"\n"
-			"       l32i    %0, %2, 0\n"
-			"       sub     %0, %0, %1\n"
-			"       s32i    %0, %2, 0\n"
-			"       wsr     a15, ps\n"
-			"       rsync\n"
-			: "=&a" (vval)
-			: "a" (i), "a" (v)
-			: "a15", "memory"
-			);
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
 
-	return vval;
-#endif
-}
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 /**
  * atomic_sub_and_test - subtract value from variable and test result
diff --git a/block/Kconfig b/block/Kconfig
index 2429515c05c2..161491d0a879 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -77,6 +77,7 @@ config BLK_DEV_BSGLIB
 
 config BLK_DEV_INTEGRITY
 	bool "Block layer data integrity support"
+	select CRC_T10DIF if BLK_DEV_INTEGRITY
 	---help---
 	Some storage devices allow extra information to be
 	stored/retrieved to help protect the data.  The block layer
diff --git a/block/Makefile b/block/Makefile
index a2ce6ac935ec..00ecc97629db 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -20,6 +20,6 @@ obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
-obj-$(CONFIG_BLK_DEV_INTEGRITY)	+= blk-integrity.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
-obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o
+obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
+
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index f14b4abbebd8..0984232e429f 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -79,6 +79,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	bip->bip_slab = idx;
 	bip->bip_bio = bio;
 	bio->bi_integrity = bip;
+	bio->bi_rw |= REQ_INTEGRITY;
 
 	return bip;
 err:
@@ -96,11 +97,12 @@ EXPORT_SYMBOL(bio_integrity_alloc);
  */
 void bio_integrity_free(struct bio *bio)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_set *bs = bio->bi_pool;
 
-	if (bip->bip_owns_buf)
-		kfree(bip->bip_buf);
+	if (bip->bip_flags & BIP_BLOCK_INTEGRITY)
+		kfree(page_address(bip->bip_vec->bv_page) +
+		      bip->bip_vec->bv_offset);
 
 	if (bs) {
 		if (bip->bip_slab != BIO_POOL_NONE)
@@ -128,7 +130,7 @@ EXPORT_SYMBOL(bio_integrity_free);
 int bio_integrity_add_page(struct bio *bio, struct page *page,
 			   unsigned int len, unsigned int offset)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_vec *iv;
 
 	if (bip->bip_vcnt >= bip->bip_max_vcnt) {
@@ -147,24 +149,6 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_integrity_add_page);
 
-static int bdev_integrity_enabled(struct block_device *bdev, int rw)
-{
-	struct blk_integrity *bi = bdev_get_integrity(bdev);
-
-	if (bi == NULL)
-		return 0;
-
-	if (rw == READ && bi->verify_fn != NULL &&
-	    (bi->flags & INTEGRITY_FLAG_READ))
-		return 1;
-
-	if (rw == WRITE && bi->generate_fn != NULL &&
-	    (bi->flags & INTEGRITY_FLAG_WRITE))
-		return 1;
-
-	return 0;
-}
-
 /**
  * bio_integrity_enabled - Check whether integrity can be passed
  * @bio:	bio to check
@@ -174,171 +158,86 @@ static int bdev_integrity_enabled(struct block_device *bdev, int rw)
  * set prior to calling.  The functions honors the write_generate and
  * read_verify flags in sysfs.
  */
-int bio_integrity_enabled(struct bio *bio)
+bool bio_integrity_enabled(struct bio *bio)
 {
+	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
+
 	if (!bio_is_rw(bio))
-		return 0;
+		return false;
 
 	/* Already protected? */
 	if (bio_integrity(bio))
-		return 0;
+		return false;
+
+	if (bi == NULL)
+		return false;
+
+	if (bio_data_dir(bio) == READ && bi->verify_fn != NULL &&
+	    (bi->flags & BLK_INTEGRITY_VERIFY))
+		return true;
+
+	if (bio_data_dir(bio) == WRITE && bi->generate_fn != NULL &&
+	    (bi->flags & BLK_INTEGRITY_GENERATE))
+		return true;
 
-	return bdev_integrity_enabled(bio->bi_bdev, bio_data_dir(bio));
+	return false;
 }
 EXPORT_SYMBOL(bio_integrity_enabled);
 
 /**
- * bio_integrity_hw_sectors - Convert 512b sectors to hardware ditto
+ * bio_integrity_intervals - Return number of integrity intervals for a bio
  * @bi:		blk_integrity profile for device
- * @sectors:	Number of 512 sectors to convert
+ * @sectors:	Size of the bio in 512-byte sectors
  *
  * Description: The block layer calculates everything in 512 byte
- * sectors but integrity metadata is done in terms of the hardware
- * sector size of the storage device.  Convert the block layer sectors
- * to physical sectors.
+ * sectors but integrity metadata is done in terms of the data integrity
+ * interval size of the storage device.  Convert the block layer sectors
+ * to the appropriate number of integrity intervals.
  */
-static inline unsigned int bio_integrity_hw_sectors(struct blk_integrity *bi,
-						    unsigned int sectors)
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
 {
-	/* At this point there are only 512b or 4096b DIF/EPP devices */
-	if (bi->sector_size == 4096)
-		return sectors >>= 3;
-
-	return sectors;
+	return sectors >> (ilog2(bi->interval) - 9);
 }
 
 static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 					       unsigned int sectors)
 {
-	return bio_integrity_hw_sectors(bi, sectors) * bi->tuple_size;
+	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
 }
 
 /**
- * bio_integrity_tag_size - Retrieve integrity tag space
- * @bio:	bio to inspect
- *
- * Description: Returns the maximum number of tag bytes that can be
- * attached to this bio. Filesystems can use this to determine how
- * much metadata to attach to an I/O.
- */
-unsigned int bio_integrity_tag_size(struct bio *bio)
-{
-	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-
-	BUG_ON(bio->bi_iter.bi_size == 0);
-
-	return bi->tag_size * (bio->bi_iter.bi_size / bi->sector_size);
-}
-EXPORT_SYMBOL(bio_integrity_tag_size);
-
-static int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len,
-			     int set)
-{
-	struct bio_integrity_payload *bip = bio->bi_integrity;
-	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-	unsigned int nr_sectors;
-
-	BUG_ON(bip->bip_buf == NULL);
-
-	if (bi->tag_size == 0)
-		return -1;
-
-	nr_sectors = bio_integrity_hw_sectors(bi,
-					DIV_ROUND_UP(len, bi->tag_size));
-
-	if (nr_sectors * bi->tuple_size > bip->bip_iter.bi_size) {
-		printk(KERN_ERR "%s: tag too big for bio: %u > %u\n", __func__,
-		       nr_sectors * bi->tuple_size, bip->bip_iter.bi_size);
-		return -1;
-	}
-
-	if (set)
-		bi->set_tag_fn(bip->bip_buf, tag_buf, nr_sectors);
-	else
-		bi->get_tag_fn(bip->bip_buf, tag_buf, nr_sectors);
-
-	return 0;
-}
-
-/**
- * bio_integrity_set_tag - Attach a tag buffer to a bio
- * @bio:	bio to attach buffer to
- * @tag_buf:	Pointer to a buffer containing tag data
- * @len:	Length of the included buffer
- *
- * Description: Use this function to tag a bio by leveraging the extra
- * space provided by devices formatted with integrity protection.  The
- * size of the integrity buffer must be <= to the size reported by
- * bio_integrity_tag_size().
- */
-int bio_integrity_set_tag(struct bio *bio, void *tag_buf, unsigned int len)
-{
-	BUG_ON(bio_data_dir(bio) != WRITE);
-
-	return bio_integrity_tag(bio, tag_buf, len, 1);
-}
-EXPORT_SYMBOL(bio_integrity_set_tag);
-
-/**
- * bio_integrity_get_tag - Retrieve a tag buffer from a bio
- * @bio:	bio to retrieve buffer from
- * @tag_buf:	Pointer to a buffer for the tag data
- * @len:	Length of the target buffer
- *
- * Description: Use this function to retrieve the tag buffer from a
- * completed I/O. The size of the integrity buffer must be <= to the
- * size reported by bio_integrity_tag_size().
- */
-int bio_integrity_get_tag(struct bio *bio, void *tag_buf, unsigned int len)
-{
-	BUG_ON(bio_data_dir(bio) != READ);
-
-	return bio_integrity_tag(bio, tag_buf, len, 0);
-}
-EXPORT_SYMBOL(bio_integrity_get_tag);
-
-/**
- * bio_integrity_generate_verify - Generate/verify integrity metadata for a bio
+ * bio_integrity_process - Process integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
- * @operate:	operate number, 1 for generate, 0 for verify
+ * @proc_fn:	Pointer to the relevant processing function
  */
-static int bio_integrity_generate_verify(struct bio *bio, int operate)
+static int bio_integrity_process(struct bio *bio,
+				 integrity_processing_fn *proc_fn)
 {
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
-	struct blk_integrity_exchg bix;
+	struct blk_integrity_iter iter;
 	struct bio_vec *bv;
-	sector_t sector;
-	unsigned int sectors, ret = 0, i;
-	void *prot_buf = bio->bi_integrity->bip_buf;
-
-	if (operate)
-		sector = bio->bi_iter.bi_sector;
-	else
-		sector = bio->bi_integrity->bip_iter.bi_sector;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	unsigned int i, ret = 0;
+	void *prot_buf = page_address(bip->bip_vec->bv_page) +
+		bip->bip_vec->bv_offset;
 
-	bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
-	bix.sector_size = bi->sector_size;
+	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
+	iter.interval = bi->interval;
+	iter.seed = bip_get_seed(bip);
+	iter.prot_buf = prot_buf;
 
 	bio_for_each_segment_all(bv, bio, i) {
 		void *kaddr = kmap_atomic(bv->bv_page);
-		bix.data_buf = kaddr + bv->bv_offset;
-		bix.data_size = bv->bv_len;
-		bix.prot_buf = prot_buf;
-		bix.sector = sector;
-
-		if (operate)
-			bi->generate_fn(&bix);
-		else {
-			ret = bi->verify_fn(&bix);
-			if (ret) {
-				kunmap_atomic(kaddr);
-				return ret;
-			}
-		}
 
-		sectors = bv->bv_len / bi->sector_size;
-		sector += sectors;
-		prot_buf += sectors * bi->tuple_size;
+		iter.data_buf = kaddr + bv->bv_offset;
+		iter.data_size = bv->bv_len;
+
+		ret = proc_fn(&iter);
+		if (ret) {
+			kunmap_atomic(kaddr);
+			return ret;
+		}
 
 		kunmap_atomic(kaddr);
 	}
@@ -346,28 +245,6 @@ static int bio_integrity_generate_verify(struct bio *bio, int operate)
 }
 
 /**
- * bio_integrity_generate - Generate integrity metadata for a bio
- * @bio:	bio to generate integrity metadata for
- *
- * Description: Generates integrity metadata for a bio by calling the
- * block device's generation callback function.  The bio must have a
- * bip attached with enough room to accommodate the generated
- * integrity metadata.
- */
-static void bio_integrity_generate(struct bio *bio)
-{
-	bio_integrity_generate_verify(bio, 1);
-}
-
-static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi)
-{
-	if (bi)
-		return bi->tuple_size;
-
-	return 0;
-}
-
-/**
  * bio_integrity_prep - Prepare bio for integrity I/O
  * @bio:	bio to prepare
  *
@@ -387,17 +264,17 @@ int bio_integrity_prep(struct bio *bio)
 	unsigned long start, end;
 	unsigned int len, nr_pages;
 	unsigned int bytes, offset, i;
-	unsigned int sectors;
+	unsigned int intervals;
 
 	bi = bdev_get_integrity(bio->bi_bdev);
 	q = bdev_get_queue(bio->bi_bdev);
 	BUG_ON(bi == NULL);
 	BUG_ON(bio_integrity(bio));
 
-	sectors = bio_integrity_hw_sectors(bi, bio_sectors(bio));
+	intervals = bio_integrity_intervals(bi, bio_sectors(bio));
 
 	/* Allocate kernel buffer for protection data */
-	len = sectors * blk_integrity_tuple_size(bi);
+	len = intervals * bi->tuple_size;
 	buf = kmalloc(len, GFP_NOIO | q->bounce_gfp);
 	if (unlikely(buf == NULL)) {
 		printk(KERN_ERR "could not allocate integrity buffer\n");
@@ -416,10 +293,12 @@ int bio_integrity_prep(struct bio *bio)
 		return -EIO;
 	}
 
-	bip->bip_owns_buf = 1;
-	bip->bip_buf = buf;
+	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
 	bip->bip_iter.bi_size = len;
-	bip->bip_iter.bi_sector = bio->bi_iter.bi_sector;
+	bip_set_seed(bip, bio->bi_iter.bi_sector);
+
+	if (bi->flags & BLK_INTEGRITY_IP_CHECKSUM)
+		bip->bip_flags |= BIP_IP_CHECKSUM;
 
 	/* Map it */
 	offset = offset_in_page(buf);
@@ -455,26 +334,13 @@ int bio_integrity_prep(struct bio *bio)
 
 	/* Auto-generate integrity metadata if this is a write */
 	if (bio_data_dir(bio) == WRITE)
-		bio_integrity_generate(bio);
+		bio_integrity_process(bio, bi->generate_fn);
 
 	return 0;
 }
 EXPORT_SYMBOL(bio_integrity_prep);
 
 /**
- * bio_integrity_verify - Verify integrity metadata for a bio
- * @bio:	bio to verify
- *
- * Description: This function is called to verify the integrity of a
- * bio.	 The data in the bio io_vec is compared to the integrity
- * metadata returned by the HBA.
- */
-static int bio_integrity_verify(struct bio *bio)
-{
-	return bio_integrity_generate_verify(bio, 0);
-}
-
-/**
  * bio_integrity_verify_fn - Integrity I/O completion worker
  * @work:	Work struct stored in bio to be verified
  *
@@ -487,9 +353,10 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	struct bio_integrity_payload *bip =
 		container_of(work, struct bio_integrity_payload, bip_work);
 	struct bio *bio = bip->bip_bio;
+	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 	int error;
 
-	error = bio_integrity_verify(bio);
+	error = bio_integrity_process(bio, bi->verify_fn);
 
 	/* Restore original bio completion handler */
 	bio->bi_end_io = bip->bip_end_io;
@@ -510,7 +377,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
  */
 void bio_integrity_endio(struct bio *bio, int error)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 
 	BUG_ON(bip->bip_bio != bio);
 
@@ -541,7 +408,7 @@ EXPORT_SYMBOL(bio_integrity_endio);
  */
 void bio_integrity_advance(struct bio *bio, unsigned int bytes_done)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 	unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9);
 
@@ -563,7 +430,7 @@ EXPORT_SYMBOL(bio_integrity_advance);
 void bio_integrity_trim(struct bio *bio, unsigned int offset,
 			unsigned int sectors)
 {
-	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 
 	bio_integrity_advance(bio, offset << 9);
@@ -582,7 +449,7 @@ EXPORT_SYMBOL(bio_integrity_trim);
 int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 			gfp_t gfp_mask)
 {
-	struct bio_integrity_payload *bip_src = bio_src->bi_integrity;
+	struct bio_integrity_payload *bip_src = bio_integrity(bio_src);
 	struct bio_integrity_payload *bip;
 
 	BUG_ON(bip_src == NULL);
@@ -646,6 +513,4 @@ void __init bio_integrity_init(void)
 				     sizeof(struct bio_integrity_payload) +
 				     sizeof(struct bio_vec) * BIP_INLINE_VECS,
 				     0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
-	if (!bip_slab)
-		panic("Failed to create slab\n");
 }
diff --git a/block/bio.c b/block/bio.c
index 3e6331d25d90..3e6e1986a5b2 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -428,6 +428,9 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		front_pad = 0;
 		inline_vecs = nr_iovecs;
 	} else {
+		/* should not use nobvec bioset for nr_iovecs > 0 */
+		if (WARN_ON_ONCE(!bs->bvec_pool && nr_iovecs > 0))
+			return NULL;
 		/*
 		 * generic_make_request() converts recursion to iteration; this
 		 * means if we're running beneath it, any bios we allocate and
@@ -1900,20 +1903,9 @@ void bioset_free(struct bio_set *bs)
 }
 EXPORT_SYMBOL(bioset_free);
 
-/**
- * bioset_create  - Create a bio_set
- * @pool_size:	Number of bio and bio_vecs to cache in the mempool
- * @front_pad:	Number of bytes to allocate in front of the returned bio
- *
- * Description:
- *    Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
- *    to ask for a number of bytes to be allocated in front of the bio.
- *    Front pad allocation is useful for embedding the bio inside
- *    another structure, to avoid allocating extra data to go with the bio.
- *    Note that the bio must be embedded at the END of that structure always,
- *    or things will break badly.
- */
-struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
+static struct bio_set *__bioset_create(unsigned int pool_size,
+				       unsigned int front_pad,
+				       bool create_bvec_pool)
 {
 	unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
 	struct bio_set *bs;
@@ -1938,9 +1930,11 @@ struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
 	if (!bs->bio_pool)
 		goto bad;
 
-	bs->bvec_pool = biovec_create_pool(pool_size);
-	if (!bs->bvec_pool)
-		goto bad;
+	if (create_bvec_pool) {
+		bs->bvec_pool = biovec_create_pool(pool_size);
+		if (!bs->bvec_pool)
+			goto bad;
+	}
 
 	bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
 	if (!bs->rescue_workqueue)
@@ -1951,8 +1945,41 @@ bad:
 	bioset_free(bs);
 	return NULL;
 }
+
+/**
+ * bioset_create  - Create a bio_set
+ * @pool_size:	Number of bio and bio_vecs to cache in the mempool
+ * @front_pad:	Number of bytes to allocate in front of the returned bio
+ *
+ * Description:
+ *    Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
+ *    to ask for a number of bytes to be allocated in front of the bio.
+ *    Front pad allocation is useful for embedding the bio inside
+ *    another structure, to avoid allocating extra data to go with the bio.
+ *    Note that the bio must be embedded at the END of that structure always,
+ *    or things will break badly.
+ */
+struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
+{
+	return __bioset_create(pool_size, front_pad, true);
+}
 EXPORT_SYMBOL(bioset_create);
 
+/**
+ * bioset_create_nobvec  - Create a bio_set without bio_vec mempool
+ * @pool_size:	Number of bio to cache in the mempool
+ * @front_pad:	Number of bytes to allocate in front of the returned bio
+ *
+ * Description:
+ *    Same functionality as bioset_create() except that mempool is not
+ *    created for bio_vecs. Saving some memory for bio_clone_fast() users.
+ */
+struct bio_set *bioset_create_nobvec(unsigned int pool_size, unsigned int front_pad)
+{
+	return __bioset_create(pool_size, front_pad, false);
+}
+EXPORT_SYMBOL(bioset_create_nobvec);
+
 #ifdef CONFIG_BLK_CGROUP
 /**
  * bio_associate_current - associate a bio with %current
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index e17da947f6bd..0ac817b750db 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -822,7 +822,6 @@ static void blkcg_css_free(struct cgroup_subsys_state *css)
 static struct cgroup_subsys_state *
 blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 {
-	static atomic64_t id_seq = ATOMIC64_INIT(0);
 	struct blkcg *blkcg;
 
 	if (!parent_css) {
@@ -836,7 +835,6 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	blkcg->cfq_weight = CFQ_WEIGHT_DEFAULT;
 	blkcg->cfq_leaf_weight = CFQ_WEIGHT_DEFAULT;
-	blkcg->id = atomic64_inc_return(&id_seq); /* root is 0, start from 1 */
 done:
 	spin_lock_init(&blkcg->lock);
 	INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_ATOMIC);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index d3fd7aa3d2a3..c567865b5f1d 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -50,9 +50,6 @@ struct blkcg {
 	struct blkcg_gq			*blkg_hint;
 	struct hlist_head		blkg_list;
 
-	/* for policies to test whether associated blkcg has changed */
-	uint64_t			id;
-
 	/* TODO: per-policy storage in blkcg */
 	unsigned int			cfq_weight;	/* belongs to cfq */
 	unsigned int			cfq_leaf_weight;
diff --git a/block/blk-core.c b/block/blk-core.c
index 9c888bd22b00..0421b53e6431 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -83,18 +83,14 @@ void blk_queue_congestion_threshold(struct request_queue *q)
  * @bdev:	device
  *
  * Locates the passed device's request queue and returns the address of its
- * backing_dev_info
- *
- * Will return NULL if the request queue cannot be located.
+ * backing_dev_info.  This function can only be called if @bdev is opened
+ * and the return value is never NULL.
  */
 struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
 {
-	struct backing_dev_info *ret = NULL;
 	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (q)
-		ret = &q->backing_dev_info;
-	return ret;
+	return &q->backing_dev_info;
 }
 EXPORT_SYMBOL(blk_get_backing_dev_info);
 
@@ -394,11 +390,13 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all)
 		 * be drained.  Check all the queues and counters.
 		 */
 		if (drain_all) {
+			struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
 			drain |= !list_empty(&q->queue_head);
 			for (i = 0; i < 2; i++) {
 				drain |= q->nr_rqs[i];
 				drain |= q->in_flight[i];
-				drain |= !list_empty(&q->flush_queue[i]);
+				if (fq)
+				    drain |= !list_empty(&fq->flush_queue[i]);
 			}
 		}
 
@@ -604,9 +602,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 #ifdef CONFIG_BLK_CGROUP
 	INIT_LIST_HEAD(&q->blkg_list);
 #endif
-	INIT_LIST_HEAD(&q->flush_queue[0]);
-	INIT_LIST_HEAD(&q->flush_queue[1]);
-	INIT_LIST_HEAD(&q->flush_data_in_flight);
 	INIT_DELAYED_WORK(&q->delay_work, blk_delay_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
@@ -709,8 +704,8 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	if (!q)
 		return NULL;
 
-	q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
-	if (!q->flush_rq)
+	q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, 0);
+	if (!q->fq)
 		return NULL;
 
 	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
@@ -746,7 +741,7 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	return q;
 
 fail:
-	kfree(q->flush_rq);
+	blk_free_flush_queue(q->fq);
 	return NULL;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -934,8 +929,8 @@ static struct io_context *rq_ioc(struct bio *bio)
  * pressure or if @q is dead.
  *
  * Must be called with @q->queue_lock held and,
- * Returns %NULL on failure, with @q->queue_lock held.
- * Returns !%NULL on success, with @q->queue_lock *not held*.
+ * Returns ERR_PTR on failure, with @q->queue_lock held.
+ * Returns request pointer on success, with @q->queue_lock *not held*.
  */
 static struct request *__get_request(struct request_list *rl, int rw_flags,
 				     struct bio *bio, gfp_t gfp_mask)
@@ -949,7 +944,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 	int may_queue;
 
 	if (unlikely(blk_queue_dying(q)))
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	may_queue = elv_may_queue(q, rw_flags);
 	if (may_queue == ELV_MQUEUE_NO)
@@ -974,7 +969,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 					 * process is not a "batcher", and not
 					 * exempted by the IO scheduler
 					 */
-					return NULL;
+					return ERR_PTR(-ENOMEM);
 				}
 			}
 		}
@@ -992,7 +987,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
 	 * allocated with any setting of ->nr_requests
 	 */
 	if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	q->nr_rqs[is_sync]++;
 	rl->count[is_sync]++;
@@ -1065,8 +1060,8 @@ fail_elvpriv:
 	 * shouldn't stall IO.  Treat this request as !elvpriv.  This will
 	 * disturb iosched and blkcg but weird is bettern than dead.
 	 */
-	printk_ratelimited(KERN_WARNING "%s: request aux data allocation failed, iosched may be disturbed\n",
-			   dev_name(q->backing_dev_info.dev));
+	printk_ratelimited(KERN_WARNING "%s: dev %s: request aux data allocation failed, iosched may be disturbed\n",
+			   __func__, dev_name(q->backing_dev_info.dev));
 
 	rq->cmd_flags &= ~REQ_ELVPRIV;
 	rq->elv.icq = NULL;
@@ -1097,7 +1092,7 @@ fail_alloc:
 rq_starved:
 	if (unlikely(rl->count[is_sync] == 0))
 		rl->starved[is_sync] = 1;
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 
 /**
@@ -1111,8 +1106,8 @@ rq_starved:
  * function keeps retrying under memory pressure and fails iff @q is dead.
  *
  * Must be called with @q->queue_lock held and,
- * Returns %NULL on failure, with @q->queue_lock held.
- * Returns !%NULL on success, with @q->queue_lock *not held*.
+ * Returns ERR_PTR on failure, with @q->queue_lock held.
+ * Returns request pointer on success, with @q->queue_lock *not held*.
  */
 static struct request *get_request(struct request_queue *q, int rw_flags,
 				   struct bio *bio, gfp_t gfp_mask)
@@ -1125,12 +1120,12 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
 	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
 retry:
 	rq = __get_request(rl, rw_flags, bio, gfp_mask);
-	if (rq)
+	if (!IS_ERR(rq))
 		return rq;
 
 	if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) {
 		blk_put_rl(rl);
-		return NULL;
+		return rq;
 	}
 
 	/* wait on @rl and retry */
@@ -1167,7 +1162,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 
 	spin_lock_irq(q->queue_lock);
 	rq = get_request(q, rw, NULL, gfp_mask);
-	if (!rq)
+	if (IS_ERR(rq))
 		spin_unlock_irq(q->queue_lock);
 	/* q->queue_lock is unlocked at this point */
 
@@ -1219,8 +1214,8 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 {
 	struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);
 
-	if (unlikely(!rq))
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(rq))
+		return rq;
 
 	blk_rq_set_block_pc(rq);
 
@@ -1614,8 +1609,8 @@ get_rq:
 	 * Returns with the queue unlocked.
 	 */
 	req = get_request(q, rw_flags, bio, GFP_NOIO);
-	if (unlikely(!req)) {
-		bio_endio(bio, -ENODEV);	/* @q is dead */
+	if (IS_ERR(req)) {
+		bio_endio(bio, PTR_ERR(req));	/* @q is dead */
 		goto out_unlock;
 	}
 
@@ -2405,11 +2400,11 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 {
 	int total_bytes;
 
+	trace_block_rq_complete(req->q, req, nr_bytes);
+
 	if (!req->bio)
 		return false;
 
-	trace_block_rq_complete(req->q, req, nr_bytes);
-
 	/*
 	 * For fs requests, rq is just carrier of independent bio's
 	 * and each partial completion should be handled separately.
@@ -2449,8 +2444,8 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 			error_type = "I/O";
 			break;
 		}
-		printk_ratelimited(KERN_ERR "end_request: %s error, dev %s, sector %llu\n",
-				   error_type, req->rq_disk ?
+		printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu\n",
+				   __func__, error_type, req->rq_disk ?
 				   req->rq_disk->disk_name : "?",
 				   (unsigned long long)blk_rq_pos(req));
 
@@ -2931,7 +2926,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 	blk_rq_init(NULL, rq);
 
 	__rq_for_each_bio(bio_src, rq_src) {
-		bio = bio_clone_bioset(bio_src, gfp_mask, bs);
+		bio = bio_clone_fast(bio_src, gfp_mask, bs);
 		if (!bio)
 			goto free_and_out;
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 3cb5e9e7108a..20badd7b9d1b 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -28,7 +28,7 @@
  *
  * The actual execution of flush is double buffered.  Whenever a request
  * needs to execute PRE or POSTFLUSH, it queues at
- * q->flush_queue[q->flush_pending_idx].  Once certain criteria are met, a
+ * fq->flush_queue[fq->flush_pending_idx].  Once certain criteria are met, a
  * flush is issued and the pending_idx is toggled.  When the flush
  * completes, all the requests which were pending are proceeded to the next
  * step.  This allows arbitrary merging of different types of FLUSH/FUA
@@ -91,7 +91,8 @@ enum {
 	FLUSH_PENDING_TIMEOUT	= 5 * HZ,
 };
 
-static bool blk_kick_flush(struct request_queue *q);
+static bool blk_kick_flush(struct request_queue *q,
+			   struct blk_flush_queue *fq);
 
 static unsigned int blk_flush_policy(unsigned int fflags, struct request *rq)
 {
@@ -126,8 +127,6 @@ static void blk_flush_restore_request(struct request *rq)
 	/* make @rq a normal request */
 	rq->cmd_flags &= ~REQ_FLUSH_SEQ;
 	rq->end_io = rq->flush.saved_end_io;
-
-	blk_clear_rq_complete(rq);
 }
 
 static bool blk_flush_queue_rq(struct request *rq, bool add_front)
@@ -150,6 +149,7 @@ static bool blk_flush_queue_rq(struct request *rq, bool add_front)
 /**
  * blk_flush_complete_seq - complete flush sequence
  * @rq: FLUSH/FUA request being sequenced
+ * @fq: flush queue
  * @seq: sequences to complete (mask of %REQ_FSEQ_*, can be zero)
  * @error: whether an error occurred
  *
@@ -157,16 +157,17 @@ static bool blk_flush_queue_rq(struct request *rq, bool add_front)
  * completion and trigger the next step.
  *
  * CONTEXT:
- * spin_lock_irq(q->queue_lock or q->mq_flush_lock)
+ * spin_lock_irq(q->queue_lock or fq->mq_flush_lock)
  *
  * RETURNS:
  * %true if requests were added to the dispatch queue, %false otherwise.
  */
-static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
-				   int error)
+static bool blk_flush_complete_seq(struct request *rq,
+				   struct blk_flush_queue *fq,
+				   unsigned int seq, int error)
 {
 	struct request_queue *q = rq->q;
-	struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
+	struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
 	bool queued = false, kicked;
 
 	BUG_ON(rq->flush.seq & seq);
@@ -182,12 +183,12 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 	case REQ_FSEQ_POSTFLUSH:
 		/* queue for flush */
 		if (list_empty(pending))
-			q->flush_pending_since = jiffies;
+			fq->flush_pending_since = jiffies;
 		list_move_tail(&rq->flush.list, pending);
 		break;
 
 	case REQ_FSEQ_DATA:
-		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
+		list_move_tail(&rq->flush.list, &fq->flush_data_in_flight);
 		queued = blk_flush_queue_rq(rq, true);
 		break;
 
@@ -202,7 +203,7 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 		list_del_init(&rq->flush.list);
 		blk_flush_restore_request(rq);
 		if (q->mq_ops)
-			blk_mq_end_io(rq, error);
+			blk_mq_end_request(rq, error);
 		else
 			__blk_end_request_all(rq, error);
 		break;
@@ -211,7 +212,7 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 		BUG();
 	}
 
-	kicked = blk_kick_flush(q);
+	kicked = blk_kick_flush(q, fq);
 	return kicked | queued;
 }
 
@@ -222,17 +223,18 @@ static void flush_end_io(struct request *flush_rq, int error)
 	bool queued = false;
 	struct request *rq, *n;
 	unsigned long flags = 0;
+	struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx);
 
 	if (q->mq_ops) {
-		spin_lock_irqsave(&q->mq_flush_lock, flags);
-		q->flush_rq->tag = -1;
+		spin_lock_irqsave(&fq->mq_flush_lock, flags);
+		flush_rq->tag = -1;
 	}
 
-	running = &q->flush_queue[q->flush_running_idx];
-	BUG_ON(q->flush_pending_idx == q->flush_running_idx);
+	running = &fq->flush_queue[fq->flush_running_idx];
+	BUG_ON(fq->flush_pending_idx == fq->flush_running_idx);
 
 	/* account completion of the flush request */
-	q->flush_running_idx ^= 1;
+	fq->flush_running_idx ^= 1;
 
 	if (!q->mq_ops)
 		elv_completed_request(q, flush_rq);
@@ -242,7 +244,7 @@ static void flush_end_io(struct request *flush_rq, int error)
 		unsigned int seq = blk_flush_cur_seq(rq);
 
 		BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH);
-		queued |= blk_flush_complete_seq(rq, seq, error);
+		queued |= blk_flush_complete_seq(rq, fq, seq, error);
 	}
 
 	/*
@@ -256,71 +258,81 @@ static void flush_end_io(struct request *flush_rq, int error)
 	 * directly into request_fn may confuse the driver.  Always use
 	 * kblockd.
 	 */
-	if (queued || q->flush_queue_delayed) {
+	if (queued || fq->flush_queue_delayed) {
 		WARN_ON(q->mq_ops);
 		blk_run_queue_async(q);
 	}
-	q->flush_queue_delayed = 0;
+	fq->flush_queue_delayed = 0;
 	if (q->mq_ops)
-		spin_unlock_irqrestore(&q->mq_flush_lock, flags);
+		spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
 }
 
 /**
  * blk_kick_flush - consider issuing flush request
  * @q: request_queue being kicked
+ * @fq: flush queue
  *
  * Flush related states of @q have changed, consider issuing flush request.
  * Please read the comment at the top of this file for more info.
  *
  * CONTEXT:
- * spin_lock_irq(q->queue_lock or q->mq_flush_lock)
+ * spin_lock_irq(q->queue_lock or fq->mq_flush_lock)
  *
  * RETURNS:
  * %true if flush was issued, %false otherwise.
  */
-static bool blk_kick_flush(struct request_queue *q)
+static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 {
-	struct list_head *pending = &q->flush_queue[q->flush_pending_idx];
+	struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
 	struct request *first_rq =
 		list_first_entry(pending, struct request, flush.list);
+	struct request *flush_rq = fq->flush_rq;
 
 	/* C1 described at the top of this file */
-	if (q->flush_pending_idx != q->flush_running_idx || list_empty(pending))
+	if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending))
 		return false;
 
 	/* C2 and C3 */
-	if (!list_empty(&q->flush_data_in_flight) &&
+	if (!list_empty(&fq->flush_data_in_flight) &&
 	    time_before(jiffies,
-			q->flush_pending_since + FLUSH_PENDING_TIMEOUT))
+			fq->flush_pending_since + FLUSH_PENDING_TIMEOUT))
 		return false;
 
 	/*
 	 * Issue flush and toggle pending_idx.  This makes pending_idx
 	 * different from running_idx, which means flush is in flight.
 	 */
-	q->flush_pending_idx ^= 1;
+	fq->flush_pending_idx ^= 1;
 
-	blk_rq_init(q, q->flush_rq);
-	if (q->mq_ops)
-		blk_mq_clone_flush_request(q->flush_rq, first_rq);
+	blk_rq_init(q, flush_rq);
+
+	/*
+	 * Borrow tag from the first request since they can't
+	 * be in flight at the same time.
+	 */
+	if (q->mq_ops) {
+		flush_rq->mq_ctx = first_rq->mq_ctx;
+		flush_rq->tag = first_rq->tag;
+	}
 
-	q->flush_rq->cmd_type = REQ_TYPE_FS;
-	q->flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
-	q->flush_rq->rq_disk = first_rq->rq_disk;
-	q->flush_rq->end_io = flush_end_io;
+	flush_rq->cmd_type = REQ_TYPE_FS;
+	flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ;
+	flush_rq->rq_disk = first_rq->rq_disk;
+	flush_rq->end_io = flush_end_io;
 
-	return blk_flush_queue_rq(q->flush_rq, false);
+	return blk_flush_queue_rq(flush_rq, false);
 }
 
 static void flush_data_end_io(struct request *rq, int error)
 {
 	struct request_queue *q = rq->q;
+	struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
 
 	/*
 	 * After populating an empty queue, kick it to avoid stall.  Read
 	 * the comment in flush_end_io().
 	 */
-	if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error))
+	if (blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error))
 		blk_run_queue_async(q);
 }
 
@@ -328,20 +340,20 @@ static void mq_flush_data_end_io(struct request *rq, int error)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	unsigned long flags;
+	struct blk_flush_queue *fq = blk_get_flush_queue(q, ctx);
 
-	ctx = rq->mq_ctx;
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
 	/*
 	 * After populating an empty queue, kick it to avoid stall.  Read
 	 * the comment in flush_end_io().
 	 */
-	spin_lock_irqsave(&q->mq_flush_lock, flags);
-	if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error))
+	spin_lock_irqsave(&fq->mq_flush_lock, flags);
+	if (blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error))
 		blk_mq_run_hw_queue(hctx, true);
-	spin_unlock_irqrestore(&q->mq_flush_lock, flags);
+	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
 }
 
 /**
@@ -361,6 +373,7 @@ void blk_insert_flush(struct request *rq)
 	struct request_queue *q = rq->q;
 	unsigned int fflags = q->flush_flags;	/* may change, cache */
 	unsigned int policy = blk_flush_policy(fflags, rq);
+	struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx);
 
 	/*
 	 * @policy now records what operations need to be done.  Adjust
@@ -378,7 +391,7 @@ void blk_insert_flush(struct request *rq)
 	 */
 	if (!policy) {
 		if (q->mq_ops)
-			blk_mq_end_io(rq, 0);
+			blk_mq_end_request(rq, 0);
 		else
 			__blk_end_bidi_request(rq, 0, 0, 0);
 		return;
@@ -411,14 +424,14 @@ void blk_insert_flush(struct request *rq)
 	if (q->mq_ops) {
 		rq->end_io = mq_flush_data_end_io;
 
-		spin_lock_irq(&q->mq_flush_lock);
-		blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0);
-		spin_unlock_irq(&q->mq_flush_lock);
+		spin_lock_irq(&fq->mq_flush_lock);
+		blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0);
+		spin_unlock_irq(&fq->mq_flush_lock);
 		return;
 	}
 	rq->end_io = flush_data_end_io;
 
-	blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0);
+	blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0);
 }
 
 /**
@@ -474,7 +487,43 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 }
 EXPORT_SYMBOL(blkdev_issue_flush);
 
-void blk_mq_init_flush(struct request_queue *q)
+struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
+		int node, int cmd_size)
+{
+	struct blk_flush_queue *fq;
+	int rq_sz = sizeof(struct request);
+
+	fq = kzalloc_node(sizeof(*fq), GFP_KERNEL, node);
+	if (!fq)
+		goto fail;
+
+	if (q->mq_ops) {
+		spin_lock_init(&fq->mq_flush_lock);
+		rq_sz = round_up(rq_sz + cmd_size, cache_line_size());
+	}
+
+	fq->flush_rq = kzalloc_node(rq_sz, GFP_KERNEL, node);
+	if (!fq->flush_rq)
+		goto fail_rq;
+
+	INIT_LIST_HEAD(&fq->flush_queue[0]);
+	INIT_LIST_HEAD(&fq->flush_queue[1]);
+	INIT_LIST_HEAD(&fq->flush_data_in_flight);
+
+	return fq;
+
+ fail_rq:
+	kfree(fq);
+ fail:
+	return NULL;
+}
+
+void blk_free_flush_queue(struct blk_flush_queue *fq)
 {
-	spin_lock_init(&q->mq_flush_lock);
+	/* bio based request queue hasn't flush queue */
+	if (!fq)
+		return;
+
+	kfree(fq->flush_rq);
+	kfree(fq);
 }
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 7fbab84399e6..79ffb4855af0 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -154,10 +154,10 @@ int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
 	if (!b1 || !b2)
 		return -1;
 
-	if (b1->sector_size != b2->sector_size) {
-		printk(KERN_ERR "%s: %s/%s sector sz %u != %u\n", __func__,
-		       gd1->disk_name, gd2->disk_name,
-		       b1->sector_size, b2->sector_size);
+	if (b1->interval != b2->interval) {
+		pr_err("%s: %s/%s protection interval %u != %u\n",
+		       __func__, gd1->disk_name, gd2->disk_name,
+		       b1->interval, b2->interval);
 		return -1;
 	}
 
@@ -186,37 +186,53 @@ int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
 }
 EXPORT_SYMBOL(blk_integrity_compare);
 
-int blk_integrity_merge_rq(struct request_queue *q, struct request *req,
-			   struct request *next)
+bool blk_integrity_merge_rq(struct request_queue *q, struct request *req,
+			    struct request *next)
 {
-	if (blk_integrity_rq(req) != blk_integrity_rq(next))
-		return -1;
+	if (blk_integrity_rq(req) == 0 && blk_integrity_rq(next) == 0)
+		return true;
+
+	if (blk_integrity_rq(req) == 0 || blk_integrity_rq(next) == 0)
+		return false;
+
+	if (bio_integrity(req->bio)->bip_flags !=
+	    bio_integrity(next->bio)->bip_flags)
+		return false;
 
 	if (req->nr_integrity_segments + next->nr_integrity_segments >
 	    q->limits.max_integrity_segments)
-		return -1;
+		return false;
 
-	return 0;
+	return true;
 }
 EXPORT_SYMBOL(blk_integrity_merge_rq);
 
-int blk_integrity_merge_bio(struct request_queue *q, struct request *req,
-			    struct bio *bio)
+bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
+			     struct bio *bio)
 {
 	int nr_integrity_segs;
 	struct bio *next = bio->bi_next;
 
+	if (blk_integrity_rq(req) == 0 && bio_integrity(bio) == NULL)
+		return true;
+
+	if (blk_integrity_rq(req) == 0 || bio_integrity(bio) == NULL)
+		return false;
+
+	if (bio_integrity(req->bio)->bip_flags != bio_integrity(bio)->bip_flags)
+		return false;
+
 	bio->bi_next = NULL;
 	nr_integrity_segs = blk_rq_count_integrity_sg(q, bio);
 	bio->bi_next = next;
 
 	if (req->nr_integrity_segments + nr_integrity_segs >
 	    q->limits.max_integrity_segments)
-		return -1;
+		return false;
 
 	req->nr_integrity_segments += nr_integrity_segs;
 
-	return 0;
+	return true;
 }
 EXPORT_SYMBOL(blk_integrity_merge_bio);
 
@@ -269,42 +285,48 @@ static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page)
 		return sprintf(page, "0\n");
 }
 
-static ssize_t integrity_read_store(struct blk_integrity *bi,
-				    const char *page, size_t count)
+static ssize_t integrity_verify_store(struct blk_integrity *bi,
+				      const char *page, size_t count)
 {
 	char *p = (char *) page;
 	unsigned long val = simple_strtoul(p, &p, 10);
 
 	if (val)
-		bi->flags |= INTEGRITY_FLAG_READ;
+		bi->flags |= BLK_INTEGRITY_VERIFY;
 	else
-		bi->flags &= ~INTEGRITY_FLAG_READ;
+		bi->flags &= ~BLK_INTEGRITY_VERIFY;
 
 	return count;
 }
 
-static ssize_t integrity_read_show(struct blk_integrity *bi, char *page)
+static ssize_t integrity_verify_show(struct blk_integrity *bi, char *page)
 {
-	return sprintf(page, "%d\n", (bi->flags & INTEGRITY_FLAG_READ) != 0);
+	return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_VERIFY) != 0);
 }
 
-static ssize_t integrity_write_store(struct blk_integrity *bi,
-				     const char *page, size_t count)
+static ssize_t integrity_generate_store(struct blk_integrity *bi,
+					const char *page, size_t count)
 {
 	char *p = (char *) page;
 	unsigned long val = simple_strtoul(p, &p, 10);
 
 	if (val)
-		bi->flags |= INTEGRITY_FLAG_WRITE;
+		bi->flags |= BLK_INTEGRITY_GENERATE;
 	else
-		bi->flags &= ~INTEGRITY_FLAG_WRITE;
+		bi->flags &= ~BLK_INTEGRITY_GENERATE;
 
 	return count;
 }
 
-static ssize_t integrity_write_show(struct blk_integrity *bi, char *page)
+static ssize_t integrity_generate_show(struct blk_integrity *bi, char *page)
+{
+	return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_GENERATE) != 0);
+}
+
+static ssize_t integrity_device_show(struct blk_integrity *bi, char *page)
 {
-	return sprintf(page, "%d\n", (bi->flags & INTEGRITY_FLAG_WRITE) != 0);
+	return sprintf(page, "%u\n",
+		       (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) != 0);
 }
 
 static struct integrity_sysfs_entry integrity_format_entry = {
@@ -317,23 +339,29 @@ static struct integrity_sysfs_entry integrity_tag_size_entry = {
 	.show = integrity_tag_size_show,
 };
 
-static struct integrity_sysfs_entry integrity_read_entry = {
+static struct integrity_sysfs_entry integrity_verify_entry = {
 	.attr = { .name = "read_verify", .mode = S_IRUGO | S_IWUSR },
-	.show = integrity_read_show,
-	.store = integrity_read_store,
+	.show = integrity_verify_show,
+	.store = integrity_verify_store,
 };
 
-static struct integrity_sysfs_entry integrity_write_entry = {
+static struct integrity_sysfs_entry integrity_generate_entry = {
 	.attr = { .name = "write_generate", .mode = S_IRUGO | S_IWUSR },
-	.show = integrity_write_show,
-	.store = integrity_write_store,
+	.show = integrity_generate_show,
+	.store = integrity_generate_store,
+};
+
+static struct integrity_sysfs_entry integrity_device_entry = {
+	.attr = { .name = "device_is_integrity_capable", .mode = S_IRUGO },
+	.show = integrity_device_show,
 };
 
 static struct attribute *integrity_attrs[] = {
 	&integrity_format_entry.attr,
 	&integrity_tag_size_entry.attr,
-	&integrity_read_entry.attr,
-	&integrity_write_entry.attr,
+	&integrity_verify_entry.attr,
+	&integrity_generate_entry.attr,
+	&integrity_device_entry.attr,
 	NULL,
 };
 
@@ -406,8 +434,8 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 
 		kobject_uevent(&bi->kobj, KOBJ_ADD);
 
-		bi->flags |= INTEGRITY_FLAG_READ | INTEGRITY_FLAG_WRITE;
-		bi->sector_size = queue_logical_block_size(disk->queue);
+		bi->flags |= BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE;
+		bi->interval = queue_logical_block_size(disk->queue);
 		disk->integrity = bi;
 	} else
 		bi = disk->integrity;
@@ -418,9 +446,8 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 		bi->generate_fn = template->generate_fn;
 		bi->verify_fn = template->verify_fn;
 		bi->tuple_size = template->tuple_size;
-		bi->set_tag_fn = template->set_tag_fn;
-		bi->get_tag_fn = template->get_tag_fn;
 		bi->tag_size = template->tag_size;
+		bi->flags |= template->flags;
 	} else
 		bi->name = bi_unsupported_name;
 
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 77881798f793..ba99351c0f58 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -97,14 +97,18 @@ void blk_recalc_rq_segments(struct request *rq)
 
 void blk_recount_segments(struct request_queue *q, struct bio *bio)
 {
-	if (test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags) &&
+	bool no_sg_merge = !!test_bit(QUEUE_FLAG_NO_SG_MERGE,
+			&q->queue_flags);
+
+	if (no_sg_merge && !bio_flagged(bio, BIO_CLONED) &&
 			bio->bi_vcnt < queue_max_segments(q))
 		bio->bi_phys_segments = bio->bi_vcnt;
 	else {
 		struct bio *nxt = bio->bi_next;
 
 		bio->bi_next = NULL;
-		bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio, false);
+		bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio,
+				no_sg_merge);
 		bio->bi_next = nxt;
 	}
 
@@ -313,7 +317,7 @@ static inline int ll_new_hw_segment(struct request_queue *q,
 	if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q))
 		goto no_merge;
 
-	if (bio_integrity(bio) && blk_integrity_merge_bio(q, req, bio))
+	if (blk_integrity_merge_bio(q, req, bio) == false)
 		goto no_merge;
 
 	/*
@@ -410,7 +414,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	if (total_phys_segments > queue_max_segments(q))
 		return 0;
 
-	if (blk_integrity_rq(req) && blk_integrity_merge_rq(q, req, next))
+	if (blk_integrity_merge_rq(q, req, next) == false)
 		return 0;
 
 	/* Merge is OK... */
@@ -590,7 +594,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 		return false;
 
 	/* only merge integrity protected bio into ditto rq */
-	if (bio_integrity(bio) != blk_integrity_rq(rq))
+	if (blk_integrity_merge_bio(rq->q, rq, bio) == false)
 		return false;
 
 	/* must be using the same buffer */
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index ed5217867555..371d8800b48a 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -402,6 +402,12 @@ static void blk_mq_sysfs_init(struct request_queue *q)
 	}
 }
 
+/* see blk_register_queue() */
+void blk_mq_finish_init(struct request_queue *q)
+{
+	percpu_ref_switch_to_percpu(&q->mq_usage_counter);
+}
+
 int blk_mq_register_disk(struct gendisk *disk)
 {
 	struct device *dev = disk_to_dev(disk);
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index c1b92426c95e..8317175a3009 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -351,15 +351,12 @@ static void bt_clear_tag(struct blk_mq_bitmap_tags *bt, unsigned int tag)
 		return;
 
 	wait_cnt = atomic_dec_return(&bs->wait_cnt);
+	if (unlikely(wait_cnt < 0))
+		wait_cnt = atomic_inc_return(&bs->wait_cnt);
 	if (wait_cnt == 0) {
-wake:
 		atomic_add(bt->wake_cnt, &bs->wait_cnt);
 		bt_index_atomic_inc(&bt->wake_index);
 		wake_up(&bs->wait);
-	} else if (wait_cnt < 0) {
-		wait_cnt = atomic_inc_return(&bs->wait_cnt);
-		if (!wait_cnt)
-			goto wake;
 	}
 }
 
@@ -392,45 +389,37 @@ void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, unsigned int tag,
 		__blk_mq_put_reserved_tag(tags, tag);
 }
 
-static void bt_for_each_free(struct blk_mq_bitmap_tags *bt,
-			     unsigned long *free_map, unsigned int off)
+static void bt_for_each(struct blk_mq_hw_ctx *hctx,
+		struct blk_mq_bitmap_tags *bt, unsigned int off,
+		busy_iter_fn *fn, void *data, bool reserved)
 {
-	int i;
+	struct request *rq;
+	int bit, i;
 
 	for (i = 0; i < bt->map_nr; i++) {
 		struct blk_align_bitmap *bm = &bt->map[i];
-		int bit = 0;
 
-		do {
-			bit = find_next_zero_bit(&bm->word, bm->depth, bit);
-			if (bit >= bm->depth)
-				break;
-
-			__set_bit(bit + off, free_map);
-			bit++;
-		} while (1);
+		for (bit = find_first_bit(&bm->word, bm->depth);
+		     bit < bm->depth;
+		     bit = find_next_bit(&bm->word, bm->depth, bit + 1)) {
+		     	rq = blk_mq_tag_to_rq(hctx->tags, off + bit);
+			if (rq->q == hctx->queue)
+				fn(hctx, rq, data, reserved);
+		}
 
 		off += (1 << bt->bits_per_word);
 	}
 }
 
-void blk_mq_tag_busy_iter(struct blk_mq_tags *tags,
-			  void (*fn)(void *, unsigned long *), void *data)
+void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
+		void *priv)
 {
-	unsigned long *tag_map;
-	size_t map_size;
-
-	map_size = ALIGN(tags->nr_tags, BITS_PER_LONG) / BITS_PER_LONG;
-	tag_map = kzalloc(map_size * sizeof(unsigned long), GFP_ATOMIC);
-	if (!tag_map)
-		return;
+	struct blk_mq_tags *tags = hctx->tags;
 
-	bt_for_each_free(&tags->bitmap_tags, tag_map, tags->nr_reserved_tags);
 	if (tags->nr_reserved_tags)
-		bt_for_each_free(&tags->breserved_tags, tag_map, 0);
-
-	fn(data, tag_map);
-	kfree(tag_map);
+		bt_for_each(hctx, &tags->breserved_tags, 0, fn, priv, true);
+	bt_for_each(hctx, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv,
+			false);
 }
 EXPORT_SYMBOL(blk_mq_tag_busy_iter);
 
@@ -463,8 +452,8 @@ static void bt_update_count(struct blk_mq_bitmap_tags *bt,
 	}
 
 	bt->wake_cnt = BT_WAIT_BATCH;
-	if (bt->wake_cnt > depth / 4)
-		bt->wake_cnt = max(1U, depth / 4);
+	if (bt->wake_cnt > depth / BT_WAIT_QUEUES)
+		bt->wake_cnt = max(1U, depth / BT_WAIT_QUEUES);
 
 	bt->depth = depth;
 }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index df8e1e09dd17..68929bad9a6a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -20,6 +20,7 @@
 #include <linux/cache.h>
 #include <linux/sched/sysctl.h>
 #include <linux/delay.h>
+#include <linux/crash_dump.h>
 
 #include <trace/events/block.h>
 
@@ -119,16 +120,7 @@ void blk_mq_freeze_queue(struct request_queue *q)
 	spin_unlock_irq(q->queue_lock);
 
 	if (freeze) {
-		/*
-		 * XXX: Temporary kludge to work around SCSI blk-mq stall.
-		 * SCSI synchronously creates and destroys many queues
-		 * back-to-back during probe leading to lengthy stalls.
-		 * This will be fixed by keeping ->mq_usage_counter in
-		 * atomic mode until genhd registration, but, for now,
-		 * let's work around using expedited synchronization.
-		 */
-		__percpu_ref_kill_expedited(&q->mq_usage_counter);
-
+		percpu_ref_kill(&q->mq_usage_counter);
 		blk_mq_run_queues(q, false);
 	}
 	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter));
@@ -232,9 +224,11 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp,
 	struct blk_mq_hw_ctx *hctx;
 	struct request *rq;
 	struct blk_mq_alloc_data alloc_data;
+	int ret;
 
-	if (blk_mq_queue_enter(q))
-		return NULL;
+	ret = blk_mq_queue_enter(q);
+	if (ret)
+		return ERR_PTR(ret);
 
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
@@ -254,6 +248,8 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp,
 		ctx = alloc_data.ctx;
 	}
 	blk_mq_put_ctx(ctx);
+	if (!rq)
+		return ERR_PTR(-EWOULDBLOCK);
 	return rq;
 }
 EXPORT_SYMBOL(blk_mq_alloc_request);
@@ -285,27 +281,7 @@ void blk_mq_free_request(struct request *rq)
 	__blk_mq_free_request(hctx, ctx, rq);
 }
 
-/*
- * Clone all relevant state from a request that has been put on hold in
- * the flush state machine into the preallocated flush request that hangs
- * off the request queue.
- *
- * For a driver the flush request should be invisible, that's why we are
- * impersonating the original request here.
- */
-void blk_mq_clone_flush_request(struct request *flush_rq,
-		struct request *orig_rq)
-{
-	struct blk_mq_hw_ctx *hctx =
-		orig_rq->q->mq_ops->map_queue(orig_rq->q, orig_rq->mq_ctx->cpu);
-
-	flush_rq->mq_ctx = orig_rq->mq_ctx;
-	flush_rq->tag = orig_rq->tag;
-	memcpy(blk_mq_rq_to_pdu(flush_rq), blk_mq_rq_to_pdu(orig_rq),
-		hctx->cmd_size);
-}
-
-inline void __blk_mq_end_io(struct request *rq, int error)
+inline void __blk_mq_end_request(struct request *rq, int error)
 {
 	blk_account_io_done(rq);
 
@@ -317,15 +293,15 @@ inline void __blk_mq_end_io(struct request *rq, int error)
 		blk_mq_free_request(rq);
 	}
 }
-EXPORT_SYMBOL(__blk_mq_end_io);
+EXPORT_SYMBOL(__blk_mq_end_request);
 
-void blk_mq_end_io(struct request *rq, int error)
+void blk_mq_end_request(struct request *rq, int error)
 {
 	if (blk_update_request(rq, error, blk_rq_bytes(rq)))
 		BUG();
-	__blk_mq_end_io(rq, error);
+	__blk_mq_end_request(rq, error);
 }
-EXPORT_SYMBOL(blk_mq_end_io);
+EXPORT_SYMBOL(blk_mq_end_request);
 
 static void __blk_mq_complete_request_remote(void *data)
 {
@@ -365,7 +341,7 @@ void __blk_mq_complete_request(struct request *rq)
 	struct request_queue *q = rq->q;
 
 	if (!q->softirq_done_fn)
-		blk_mq_end_io(rq, rq->errors);
+		blk_mq_end_request(rq, rq->errors);
 	else
 		blk_mq_ipi_complete_request(rq);
 }
@@ -389,7 +365,7 @@ void blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
-static void blk_mq_start_request(struct request *rq, bool last)
+void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
@@ -426,35 +402,24 @@ static void blk_mq_start_request(struct request *rq, bool last)
 		 */
 		rq->nr_phys_segments++;
 	}
-
-	/*
-	 * Flag the last request in the series so that drivers know when IO
-	 * should be kicked off, if they don't do it on a per-request basis.
-	 *
-	 * Note: the flag isn't the only condition drivers should do kick off.
-	 * If drive is busy, the last request might not have the bit set.
-	 */
-	if (last)
-		rq->cmd_flags |= REQ_END;
 }
+EXPORT_SYMBOL(blk_mq_start_request);
 
 static void __blk_mq_requeue_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
 	trace_block_rq_requeue(q, rq);
-	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
 
-	rq->cmd_flags &= ~REQ_END;
-
-	if (q->dma_drain_size && blk_rq_bytes(rq))
-		rq->nr_phys_segments--;
+	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
+		if (q->dma_drain_size && blk_rq_bytes(rq))
+			rq->nr_phys_segments--;
+	}
 }
 
 void blk_mq_requeue_request(struct request *rq)
 {
 	__blk_mq_requeue_request(rq);
-	blk_clear_rq_complete(rq);
 
 	BUG_ON(blk_queued_rq(rq));
 	blk_mq_add_to_requeue_list(rq, true);
@@ -523,78 +488,35 @@ void blk_mq_kick_requeue_list(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_mq_kick_requeue_list);
 
-static inline bool is_flush_request(struct request *rq, unsigned int tag)
+static inline bool is_flush_request(struct request *rq,
+		struct blk_flush_queue *fq, unsigned int tag)
 {
 	return ((rq->cmd_flags & REQ_FLUSH_SEQ) &&
-			rq->q->flush_rq->tag == tag);
+			fq->flush_rq->tag == tag);
 }
 
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
 {
 	struct request *rq = tags->rqs[tag];
+	/* mq_ctx of flush rq is always cloned from the corresponding req */
+	struct blk_flush_queue *fq = blk_get_flush_queue(rq->q, rq->mq_ctx);
 
-	if (!is_flush_request(rq, tag))
+	if (!is_flush_request(rq, fq, tag))
 		return rq;
 
-	return rq->q->flush_rq;
+	return fq->flush_rq;
 }
 EXPORT_SYMBOL(blk_mq_tag_to_rq);
 
 struct blk_mq_timeout_data {
-	struct blk_mq_hw_ctx *hctx;
-	unsigned long *next;
-	unsigned int *next_set;
+	unsigned long next;
+	unsigned int next_set;
 };
 
-static void blk_mq_timeout_check(void *__data, unsigned long *free_tags)
-{
-	struct blk_mq_timeout_data *data = __data;
-	struct blk_mq_hw_ctx *hctx = data->hctx;
-	unsigned int tag;
-
-	 /* It may not be in flight yet (this is where
-	 * the REQ_ATOMIC_STARTED flag comes in). The requests are
-	 * statically allocated, so we know it's always safe to access the
-	 * memory associated with a bit offset into ->rqs[].
-	 */
-	tag = 0;
-	do {
-		struct request *rq;
-
-		tag = find_next_zero_bit(free_tags, hctx->tags->nr_tags, tag);
-		if (tag >= hctx->tags->nr_tags)
-			break;
-
-		rq = blk_mq_tag_to_rq(hctx->tags, tag++);
-		if (rq->q != hctx->queue)
-			continue;
-		if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
-			continue;
-
-		blk_rq_check_expired(rq, data->next, data->next_set);
-	} while (1);
-}
-
-static void blk_mq_hw_ctx_check_timeout(struct blk_mq_hw_ctx *hctx,
-					unsigned long *next,
-					unsigned int *next_set)
-{
-	struct blk_mq_timeout_data data = {
-		.hctx		= hctx,
-		.next		= next,
-		.next_set	= next_set,
-	};
-
-	/*
-	 * Ask the tagging code to iterate busy requests, so we can
-	 * check them for timeout.
-	 */
-	blk_mq_tag_busy_iter(hctx->tags, blk_mq_timeout_check, &data);
-}
-
-static enum blk_eh_timer_return blk_mq_rq_timed_out(struct request *rq)
+void blk_mq_rq_timed_out(struct request *req, bool reserved)
 {
-	struct request_queue *q = rq->q;
+	struct blk_mq_ops *ops = req->q->mq_ops;
+	enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
 
 	/*
 	 * We know that complete is set at this point. If STARTED isn't set
@@ -605,21 +527,54 @@ static enum blk_eh_timer_return blk_mq_rq_timed_out(struct request *rq)
 	 * we both flags will get cleared. So check here again, and ignore
 	 * a timeout event with a request that isn't active.
 	 */
-	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
-		return BLK_EH_NOT_HANDLED;
+	if (!test_bit(REQ_ATOM_STARTED, &req->atomic_flags))
+		return;
 
-	if (!q->mq_ops->timeout)
-		return BLK_EH_RESET_TIMER;
+	if (ops->timeout)
+		ret = ops->timeout(req, reserved);
+
+	switch (ret) {
+	case BLK_EH_HANDLED:
+		__blk_mq_complete_request(req);
+		break;
+	case BLK_EH_RESET_TIMER:
+		blk_add_timer(req);
+		blk_clear_rq_complete(req);
+		break;
+	case BLK_EH_NOT_HANDLED:
+		break;
+	default:
+		printk(KERN_ERR "block: bad eh return: %d\n", ret);
+		break;
+	}
+}
+		
+static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
+		struct request *rq, void *priv, bool reserved)
+{
+	struct blk_mq_timeout_data *data = priv;
 
-	return q->mq_ops->timeout(rq);
+	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+		return;
+
+	if (time_after_eq(jiffies, rq->deadline)) {
+		if (!blk_mark_rq_complete(rq))
+			blk_mq_rq_timed_out(rq, reserved);
+	} else if (!data->next_set || time_after(data->next, rq->deadline)) {
+		data->next = rq->deadline;
+		data->next_set = 1;
+	}
 }
 
-static void blk_mq_rq_timer(unsigned long data)
+static void blk_mq_rq_timer(unsigned long priv)
 {
-	struct request_queue *q = (struct request_queue *) data;
+	struct request_queue *q = (struct request_queue *)priv;
+	struct blk_mq_timeout_data data = {
+		.next		= 0,
+		.next_set	= 0,
+	};
 	struct blk_mq_hw_ctx *hctx;
-	unsigned long next = 0;
-	int i, next_set = 0;
+	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		/*
@@ -629,12 +584,12 @@ static void blk_mq_rq_timer(unsigned long data)
 		if (!hctx->nr_ctx || !hctx->tags)
 			continue;
 
-		blk_mq_hw_ctx_check_timeout(hctx, &next, &next_set);
+		blk_mq_tag_busy_iter(hctx, blk_mq_check_expired, &data);
 	}
 
-	if (next_set) {
-		next = blk_rq_timeout(round_jiffies_up(next));
-		mod_timer(&q->timeout, next);
+	if (data.next_set) {
+		data.next = blk_rq_timeout(round_jiffies_up(data.next));
+		mod_timer(&q->timeout, data.next);
 	} else {
 		queue_for_each_hw_ctx(q, hctx, i)
 			blk_mq_tag_idle(hctx);
@@ -760,9 +715,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		rq = list_first_entry(&rq_list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 
-		blk_mq_start_request(rq, list_empty(&rq_list));
-
-		ret = q->mq_ops->queue_rq(hctx, rq);
+		ret = q->mq_ops->queue_rq(hctx, rq, list_empty(&rq_list));
 		switch (ret) {
 		case BLK_MQ_RQ_QUEUE_OK:
 			queued++;
@@ -775,7 +728,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 			pr_err("blk-mq: bad return on queue: %d\n", ret);
 		case BLK_MQ_RQ_QUEUE_ERROR:
 			rq->errors = -EIO;
-			blk_mq_end_io(rq, rq->errors);
+			blk_mq_end_request(rq, rq->errors);
 			break;
 		}
 
@@ -1203,14 +1156,13 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		int ret;
 
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_start_request(rq, true);
 
 		/*
 		 * For OK queue, we are done. For error, kill it. Any other
 		 * error (busy), just add it to our list as we previously
 		 * would have done
 		 */
-		ret = q->mq_ops->queue_rq(data.hctx, rq);
+		ret = q->mq_ops->queue_rq(data.hctx, rq, true);
 		if (ret == BLK_MQ_RQ_QUEUE_OK)
 			goto done;
 		else {
@@ -1218,7 +1170,7 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 			if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
 				rq->errors = -EIO;
-				blk_mq_end_io(rq, rq->errors);
+				blk_mq_end_request(rq, rq->errors);
 				goto done;
 			}
 		}
@@ -1540,6 +1492,28 @@ static int blk_mq_hctx_notify(void *data, unsigned long action,
 	return NOTIFY_OK;
 }
 
+static void blk_mq_exit_hctx(struct request_queue *q,
+		struct blk_mq_tag_set *set,
+		struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
+{
+	unsigned flush_start_tag = set->queue_depth;
+
+	blk_mq_tag_idle(hctx);
+
+	if (set->ops->exit_request)
+		set->ops->exit_request(set->driver_data,
+				       hctx->fq->flush_rq, hctx_idx,
+				       flush_start_tag + hctx_idx);
+
+	if (set->ops->exit_hctx)
+		set->ops->exit_hctx(hctx, hctx_idx);
+
+	blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
+	blk_free_flush_queue(hctx->fq);
+	kfree(hctx->ctxs);
+	blk_mq_free_bitmap(&hctx->ctx_map);
+}
+
 static void blk_mq_exit_hw_queues(struct request_queue *q,
 		struct blk_mq_tag_set *set, int nr_queue)
 {
@@ -1549,17 +1523,8 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (i == nr_queue)
 			break;
-
-		blk_mq_tag_idle(hctx);
-
-		if (set->ops->exit_hctx)
-			set->ops->exit_hctx(hctx, i);
-
-		blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
-		kfree(hctx->ctxs);
-		blk_mq_free_bitmap(&hctx->ctx_map);
+		blk_mq_exit_hctx(q, set, hctx, i);
 	}
-
 }
 
 static void blk_mq_free_hw_queues(struct request_queue *q,
@@ -1574,53 +1539,88 @@ static void blk_mq_free_hw_queues(struct request_queue *q,
 	}
 }
 
-static int blk_mq_init_hw_queues(struct request_queue *q,
-		struct blk_mq_tag_set *set)
+static int blk_mq_init_hctx(struct request_queue *q,
+		struct blk_mq_tag_set *set,
+		struct blk_mq_hw_ctx *hctx, unsigned hctx_idx)
 {
-	struct blk_mq_hw_ctx *hctx;
-	unsigned int i;
+	int node;
+	unsigned flush_start_tag = set->queue_depth;
+
+	node = hctx->numa_node;
+	if (node == NUMA_NO_NODE)
+		node = hctx->numa_node = set->numa_node;
+
+	INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
+	INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn);
+	spin_lock_init(&hctx->lock);
+	INIT_LIST_HEAD(&hctx->dispatch);
+	hctx->queue = q;
+	hctx->queue_num = hctx_idx;
+	hctx->flags = set->flags;
+	hctx->cmd_size = set->cmd_size;
+
+	blk_mq_init_cpu_notifier(&hctx->cpu_notifier,
+					blk_mq_hctx_notify, hctx);
+	blk_mq_register_cpu_notifier(&hctx->cpu_notifier);
+
+	hctx->tags = set->tags[hctx_idx];
 
 	/*
-	 * Initialize hardware queues
+	 * Allocate space for all possible cpus to avoid allocation at
+	 * runtime
 	 */
-	queue_for_each_hw_ctx(q, hctx, i) {
-		int node;
+	hctx->ctxs = kmalloc_node(nr_cpu_ids * sizeof(void *),
+					GFP_KERNEL, node);
+	if (!hctx->ctxs)
+		goto unregister_cpu_notifier;
 
-		node = hctx->numa_node;
-		if (node == NUMA_NO_NODE)
-			node = hctx->numa_node = set->numa_node;
+	if (blk_mq_alloc_bitmap(&hctx->ctx_map, node))
+		goto free_ctxs;
 
-		INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
-		INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn);
-		spin_lock_init(&hctx->lock);
-		INIT_LIST_HEAD(&hctx->dispatch);
-		hctx->queue = q;
-		hctx->queue_num = i;
-		hctx->flags = set->flags;
-		hctx->cmd_size = set->cmd_size;
+	hctx->nr_ctx = 0;
 
-		blk_mq_init_cpu_notifier(&hctx->cpu_notifier,
-						blk_mq_hctx_notify, hctx);
-		blk_mq_register_cpu_notifier(&hctx->cpu_notifier);
+	if (set->ops->init_hctx &&
+	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
+		goto free_bitmap;
 
-		hctx->tags = set->tags[i];
+	hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size);
+	if (!hctx->fq)
+		goto exit_hctx;
 
-		/*
-		 * Allocate space for all possible cpus to avoid allocation at
-		 * runtime
-		 */
-		hctx->ctxs = kmalloc_node(nr_cpu_ids * sizeof(void *),
-						GFP_KERNEL, node);
-		if (!hctx->ctxs)
-			break;
+	if (set->ops->init_request &&
+	    set->ops->init_request(set->driver_data,
+				   hctx->fq->flush_rq, hctx_idx,
+				   flush_start_tag + hctx_idx, node))
+		goto free_fq;
 
-		if (blk_mq_alloc_bitmap(&hctx->ctx_map, node))
-			break;
+	return 0;
 
-		hctx->nr_ctx = 0;
+ free_fq:
+	kfree(hctx->fq);
+ exit_hctx:
+	if (set->ops->exit_hctx)
+		set->ops->exit_hctx(hctx, hctx_idx);
+ free_bitmap:
+	blk_mq_free_bitmap(&hctx->ctx_map);
+ free_ctxs:
+	kfree(hctx->ctxs);
+ unregister_cpu_notifier:
+	blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
 
-		if (set->ops->init_hctx &&
-		    set->ops->init_hctx(hctx, set->driver_data, i))
+	return -1;
+}
+
+static int blk_mq_init_hw_queues(struct request_queue *q,
+		struct blk_mq_tag_set *set)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	/*
+	 * Initialize hardware queues
+	 */
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (blk_mq_init_hctx(q, set, hctx, i))
 			break;
 	}
 
@@ -1774,6 +1774,16 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	if (!ctx)
 		return ERR_PTR(-ENOMEM);
 
+	/*
+	 * If a crashdump is active, then we are potentially in a very
+	 * memory constrained environment. Limit us to 1 queue and
+	 * 64 tags to prevent using too much memory.
+	 */
+	if (is_kdump_kernel()) {
+		set->nr_hw_queues = 1;
+		set->queue_depth = min(64U, set->queue_depth);
+	}
+
 	hctxs = kmalloc_node(set->nr_hw_queues * sizeof(*hctxs), GFP_KERNEL,
 			set->numa_node);
 
@@ -1792,7 +1802,8 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 		if (!hctxs[i])
 			goto err_hctxs;
 
-		if (!zalloc_cpumask_var(&hctxs[i]->cpumask, GFP_KERNEL))
+		if (!zalloc_cpumask_var_node(&hctxs[i]->cpumask, GFP_KERNEL,
+						node))
 			goto err_hctxs;
 
 		atomic_set(&hctxs[i]->nr_active, 0);
@@ -1804,7 +1815,12 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	if (!q)
 		goto err_hctxs;
 
-	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release))
+	/*
+	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
+	 * See blk_register_queue() for details.
+	 */
+	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
+			    PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
 		goto err_map;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
@@ -1834,7 +1850,6 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	else
 		blk_queue_make_request(q, blk_sq_make_request);
 
-	blk_queue_rq_timed_out(q, blk_mq_rq_timed_out);
 	if (set->timeout)
 		blk_queue_rq_timeout(q, set->timeout);
 
@@ -1846,17 +1861,10 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 	if (set->ops->complete)
 		blk_queue_softirq_done(q, set->ops->complete);
 
-	blk_mq_init_flush(q);
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 
-	q->flush_rq = kzalloc(round_up(sizeof(struct request) +
-				set->cmd_size, cache_line_size()),
-				GFP_KERNEL);
-	if (!q->flush_rq)
-		goto err_hw;
-
 	if (blk_mq_init_hw_queues(q, set))
-		goto err_flush_rq;
+		goto err_hw;
 
 	mutex_lock(&all_q_mutex);
 	list_add_tail(&q->all_q_node, &all_q_list);
@@ -1868,8 +1876,6 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 
 	return q;
 
-err_flush_rq:
-	kfree(q->flush_rq);
 err_hw:
 	blk_cleanup_queue(q);
 err_hctxs:
diff --git a/block/blk-mq.h b/block/blk-mq.h
index ca4964a6295d..d567d5283ffa 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -27,7 +27,6 @@ struct blk_mq_ctx {
 
 void __blk_mq_complete_request(struct request *rq);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
-void blk_mq_init_flush(struct request_queue *q);
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_free_queue(struct request_queue *q);
 void blk_mq_clone_flush_request(struct request *flush_rq,
@@ -60,6 +59,8 @@ extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
 extern int blk_mq_sysfs_register(struct request_queue *q);
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
 
+extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
+
 /*
  * Basic implementation of sparser bitmap, allowing the user to spread
  * the bits over more cachelines.
diff --git a/block/blk-settings.c b/block/blk-settings.c
index f1a1795a5683..aa02247d227e 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -574,7 +574,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		bottom = max(b->physical_block_size, b->io_min) + alignment;
 
 		/* Verify that top and bottom intervals line up */
-		if (max(top, bottom) & (min(top, bottom) - 1)) {
+		if (max(top, bottom) % min(top, bottom)) {
 			t->misaligned = 1;
 			ret = -1;
 		}
@@ -619,7 +619,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	/* Find lowest common alignment_offset */
 	t->alignment_offset = lcm(t->alignment_offset, alignment)
-		& (max(t->physical_block_size, t->io_min) - 1);
+		% max(t->physical_block_size, t->io_min);
 
 	/* Verify that new alignment_offset is on a logical block boundary */
 	if (t->alignment_offset & (t->logical_block_size - 1)) {
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 17f5c84ce7bf..1fac43408911 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -519,8 +519,8 @@ static void blk_release_queue(struct kobject *kobj)
 
 	if (q->mq_ops)
 		blk_mq_free_queue(q);
-
-	kfree(q->flush_rq);
+	else
+		blk_free_flush_queue(q->fq);
 
 	blk_trace_shutdown(q);
 
@@ -551,12 +551,19 @@ int blk_register_queue(struct gendisk *disk)
 		return -ENXIO;
 
 	/*
-	 * Initialization must be complete by now.  Finish the initial
-	 * bypass from queue allocation.
+	 * SCSI probing may synchronously create and destroy a lot of
+	 * request_queues for non-existent devices.  Shutting down a fully
+	 * functional queue takes measureable wallclock time as RCU grace
+	 * periods are involved.  To avoid excessive latency in these
+	 * cases, a request_queue starts out in a degraded mode which is
+	 * faster to shut down and is made fully functional here as
+	 * request_queues for non-existent devices never get registered.
 	 */
 	if (!blk_queue_init_done(q)) {
 		queue_flag_set_unlocked(QUEUE_FLAG_INIT_DONE, q);
 		blk_queue_bypass_end(q);
+		if (q->mq_ops)
+			blk_mq_finish_init(q);
 	}
 
 	ret = blk_trace_init_sysfs(dev);
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 95a09590ccfd..56c025894cdf 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -90,10 +90,7 @@ static void blk_rq_timed_out(struct request *req)
 	switch (ret) {
 	case BLK_EH_HANDLED:
 		/* Can we use req->errors here? */
-		if (q->mq_ops)
-			__blk_mq_complete_request(req);
-		else
-			__blk_complete_request(req);
+		__blk_complete_request(req);
 		break;
 	case BLK_EH_RESET_TIMER:
 		blk_add_timer(req);
@@ -113,7 +110,7 @@ static void blk_rq_timed_out(struct request *req)
 	}
 }
 
-void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
+static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
 			  unsigned int *next_set)
 {
 	if (time_after_eq(jiffies, rq->deadline)) {
@@ -162,7 +159,10 @@ void blk_abort_request(struct request *req)
 	if (blk_mark_rq_complete(req))
 		return;
 	blk_delete_timer(req);
-	blk_rq_timed_out(req);
+	if (req->q->mq_ops)
+		blk_mq_rq_timed_out(req, false);
+	else
+		blk_rq_timed_out(req);
 }
 EXPORT_SYMBOL_GPL(blk_abort_request);
 
@@ -190,7 +190,8 @@ void blk_add_timer(struct request *req)
 	struct request_queue *q = req->q;
 	unsigned long expiry;
 
-	if (!q->rq_timed_out_fn)
+	/* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */
+	if (!q->mq_ops && !q->rq_timed_out_fn)
 		return;
 
 	BUG_ON(!list_empty(&req->timeout_list));
diff --git a/block/blk.h b/block/blk.h
index 6748c4f8d7a1..43b036185712 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -2,6 +2,8 @@
 #define BLK_INTERNAL_H
 
 #include <linux/idr.h>
+#include <linux/blk-mq.h>
+#include "blk-mq.h"
 
 /* Amount of time in which a process may batch requests */
 #define BLK_BATCH_TIME	(HZ/50UL)
@@ -12,16 +14,44 @@
 /* Max future timer expiry for timeouts */
 #define BLK_MAX_TIMEOUT		(5 * HZ)
 
+struct blk_flush_queue {
+	unsigned int		flush_queue_delayed:1;
+	unsigned int		flush_pending_idx:1;
+	unsigned int		flush_running_idx:1;
+	unsigned long		flush_pending_since;
+	struct list_head	flush_queue[2];
+	struct list_head	flush_data_in_flight;
+	struct request		*flush_rq;
+	spinlock_t		mq_flush_lock;
+};
+
 extern struct kmem_cache *blk_requestq_cachep;
 extern struct kmem_cache *request_cachep;
 extern struct kobj_type blk_queue_ktype;
 extern struct ida blk_queue_ida;
 
+static inline struct blk_flush_queue *blk_get_flush_queue(
+		struct request_queue *q, struct blk_mq_ctx *ctx)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	if (!q->mq_ops)
+		return q->fq;
+
+	hctx = q->mq_ops->map_queue(q, ctx->cpu);
+
+	return hctx->fq;
+}
+
 static inline void __blk_get_queue(struct request_queue *q)
 {
 	kobject_get(&q->kobj);
 }
 
+struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
+		int node, int cmd_size);
+void blk_free_flush_queue(struct blk_flush_queue *q);
+
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask);
 void blk_exit_rl(struct request_list *rl);
@@ -38,8 +68,6 @@ bool __blk_end_bidi_request(struct request *rq, int error,
 			    unsigned int nr_bytes, unsigned int bidi_bytes);
 
 void blk_rq_timed_out_timer(unsigned long data);
-void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
-			  unsigned int *next_set);
 unsigned long blk_rq_timeout(unsigned long timeout);
 void blk_add_timer(struct request *req);
 void blk_delete_timer(struct request *);
@@ -88,6 +116,7 @@ void blk_insert_flush(struct request *rq);
 static inline struct request *__elv_next_request(struct request_queue *q)
 {
 	struct request *rq;
+	struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
 
 	while (1) {
 		if (!list_empty(&q->queue_head)) {
@@ -110,9 +139,9 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 		 * should be restarted later. Please see flush_end_io() for
 		 * details.
 		 */
-		if (q->flush_pending_idx != q->flush_running_idx &&
+		if (fq->flush_pending_idx != fq->flush_running_idx &&
 				!queue_flush_queueable(q)) {
-			q->flush_queue_delayed = 1;
+			fq->flush_queue_delayed = 1;
 			return NULL;
 		}
 		if (unlikely(blk_queue_bypass(q)) ||
diff --git a/block/bsg.c b/block/bsg.c
index ff46addde5d8..276e869e686c 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -270,8 +270,8 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 	 * map scatter-gather elements separately and string them to request
 	 */
 	rq = blk_get_request(q, rw, GFP_KERNEL);
-	if (!rq)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(rq))
+		return rq;
 	blk_rq_set_block_pc(rq);
 
 	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm);
@@ -285,8 +285,9 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 		}
 
 		next_rq = blk_get_request(q, READ, GFP_KERNEL);
-		if (!next_rq) {
-			ret = -ENOMEM;
+		if (IS_ERR(next_rq)) {
+			ret = PTR_ERR(next_rq);
+			next_rq = NULL;
 			goto out;
 		}
 		rq->next_rq = next_rq;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 3f31cf9508e6..6f2751d305de 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -299,7 +299,7 @@ struct cfq_io_cq {
 	struct cfq_ttime	ttime;
 	int			ioprio;		/* the current ioprio */
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
-	uint64_t		blkcg_id;	/* the current blkcg ID */
+	uint64_t		blkcg_serial_nr; /* the current blkcg serial */
 #endif
 };
 
@@ -3547,17 +3547,17 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 {
 	struct cfq_data *cfqd = cic_to_cfqd(cic);
 	struct cfq_queue *sync_cfqq;
-	uint64_t id;
+	uint64_t serial_nr;
 
 	rcu_read_lock();
-	id = bio_blkcg(bio)->id;
+	serial_nr = bio_blkcg(bio)->css.serial_nr;
 	rcu_read_unlock();
 
 	/*
 	 * Check whether blkcg has changed.  The condition may trigger
 	 * spuriously on a newly created cic but there's no harm.
 	 */
-	if (unlikely(!cfqd) || likely(cic->blkcg_id == id))
+	if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr))
 		return;
 
 	sync_cfqq = cic_to_cfqq(cic, 1);
@@ -3571,7 +3571,7 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 		cfq_put_queue(sync_cfqq);
 	}
 
-	cic->blkcg_id = id;
+	cic->blkcg_serial_nr = serial_nr;
 }
 #else
 static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { }
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 18b282ce361e..f678c733df40 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -709,8 +709,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		if (!arg)
 			return -EINVAL;
 		bdi = blk_get_backing_dev_info(bdev);
-		if (bdi == NULL)
-			return -ENOTTY;
 		return compat_put_long(arg,
 				       (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
 	case BLKROGET: /* compatible */
@@ -731,8 +729,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
 		bdi = blk_get_backing_dev_info(bdev);
-		if (bdi == NULL)
-			return -ENOTTY;
 		bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
 		return 0;
 	case BLKGETSIZE:
diff --git a/block/ioctl.c b/block/ioctl.c
index d6cda8147c91..6c7bf903742f 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -356,8 +356,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		if (!arg)
 			return -EINVAL;
 		bdi = blk_get_backing_dev_info(bdev);
-		if (bdi == NULL)
-			return -ENOTTY;
 		return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
 	case BLKROGET:
 		return put_int(arg, bdev_read_only(bdev) != 0);
@@ -386,8 +384,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		if(!capable(CAP_SYS_ADMIN))
 			return -EACCES;
 		bdi = blk_get_backing_dev_info(bdev);
-		if (bdi == NULL)
-			return -ENOTTY;
 		bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
 		return 0;
 	case BLKBSZSET:
diff --git a/block/partitions/mac.c b/block/partitions/mac.c
index 76d8ba6379a9..c2c48ec64b27 100644
--- a/block/partitions/mac.c
+++ b/block/partitions/mac.c
@@ -81,7 +81,7 @@ int mac_partition(struct parsed_partitions *state)
 			be32_to_cpu(part->start_block) * (secsize/512),
 			be32_to_cpu(part->block_count) * (secsize/512));
 
-		if (!strnicmp(part->type, "Linux_RAID", 10))
+		if (!strncasecmp(part->type, "Linux_RAID", 10))
 			state->parts[slot].flags = ADDPART_FLAG_RAID;
 #ifdef CONFIG_PPC_PMAC
 		/*
@@ -100,7 +100,7 @@ int mac_partition(struct parsed_partitions *state)
 				goodness++;
 
 			if (strcasecmp(part->type, "Apple_UNIX_SVR2") == 0
-			    || (strnicmp(part->type, "Linux", 5) == 0
+			    || (strncasecmp(part->type, "Linux", 5) == 0
 			        && strcasecmp(part->type, "Linux_swap") != 0)) {
 				int i, l;
 
@@ -109,13 +109,13 @@ int mac_partition(struct parsed_partitions *state)
 				if (strcmp(part->name, "/") == 0)
 					goodness++;
 				for (i = 0; i <= l - 4; ++i) {
-					if (strnicmp(part->name + i, "root",
+					if (strncasecmp(part->name + i, "root",
 						     4) == 0) {
 						goodness += 2;
 						break;
 					}
 				}
-				if (strnicmp(part->name, "swap", 4) == 0)
+				if (strncasecmp(part->name, "swap", 4) == 0)
 					goodness--;
 			}
 
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 9b8eaeca6a79..abb2e65b24cc 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -316,8 +316,8 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 
 	ret = -ENOMEM;
 	rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
-	if (!rq)
-		goto out;
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
 	blk_rq_set_block_pc(rq);
 
 	if (hdr->cmd_len > BLK_MAX_CDB) {
@@ -387,7 +387,6 @@ out_free_cdb:
 		kfree(rq->cmd);
 out_put_request:
 	blk_put_request(rq);
-out:
 	return ret;
 }
 
@@ -457,8 +456,8 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 	}
 
 	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT);
-	if (!rq) {
-		err = -ENOMEM;
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
 		goto error;
 	}
 	blk_rq_set_block_pc(rq);
@@ -548,6 +547,8 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	int err;
 
 	rq = blk_get_request(q, WRITE, __GFP_WAIT);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
 	blk_rq_set_block_pc(rq);
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
 	rq->cmd[0] = cmd;
diff --git a/block/t10-pi.c b/block/t10-pi.c
new file mode 100644
index 000000000000..24d6e9715318
--- /dev/null
+++ b/block/t10-pi.c
@@ -0,0 +1,197 @@
+/*
+ * t10_pi.c - Functions for generating and verifying T10 Protection
+ *	      Information.
+ *
+ * Copyright (C) 2007, 2008, 2014 Oracle Corporation
+ * Written by: Martin K. Petersen <martin.petersen@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
+ * USA.
+ *
+ */
+
+#include <linux/t10-pi.h>
+#include <linux/blkdev.h>
+#include <linux/crc-t10dif.h>
+#include <net/checksum.h>
+
+typedef __be16 (csum_fn) (void *, unsigned int);
+
+static const __be16 APP_ESCAPE = (__force __be16) 0xffff;
+static const __be32 REF_ESCAPE = (__force __be32) 0xffffffff;
+
+static __be16 t10_pi_crc_fn(void *data, unsigned int len)
+{
+	return cpu_to_be16(crc_t10dif(data, len));
+}
+
+static __be16 t10_pi_ip_fn(void *data, unsigned int len)
+{
+	return (__force __be16)ip_compute_csum(data, len);
+}
+
+/*
+ * Type 1 and Type 2 protection use the same format: 16 bit guard tag,
+ * 16 bit app tag, 32 bit reference tag. Type 3 does not define the ref
+ * tag.
+ */
+static int t10_pi_generate(struct blk_integrity_iter *iter, csum_fn *fn,
+			   unsigned int type)
+{
+	unsigned int i;
+
+	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
+		struct t10_pi_tuple *pi = iter->prot_buf;
+
+		pi->guard_tag = fn(iter->data_buf, iter->interval);
+		pi->app_tag = 0;
+
+		if (type == 1)
+			pi->ref_tag = cpu_to_be32(lower_32_bits(iter->seed));
+		else
+			pi->ref_tag = 0;
+
+		iter->data_buf += iter->interval;
+		iter->prot_buf += sizeof(struct t10_pi_tuple);
+		iter->seed++;
+	}
+
+	return 0;
+}
+
+static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn,
+				unsigned int type)
+{
+	unsigned int i;
+
+	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
+		struct t10_pi_tuple *pi = iter->prot_buf;
+		__be16 csum;
+
+		switch (type) {
+		case 1:
+		case 2:
+			if (pi->app_tag == APP_ESCAPE)
+				goto next;
+
+			if (be32_to_cpu(pi->ref_tag) !=
+			    lower_32_bits(iter->seed)) {
+				pr_err("%s: ref tag error at location %llu " \
+				       "(rcvd %u)\n", iter->disk_name,
+				       (unsigned long long)
+				       iter->seed, be32_to_cpu(pi->ref_tag));
+				return -EILSEQ;
+			}
+			break;
+		case 3:
+			if (pi->app_tag == APP_ESCAPE &&
+			    pi->ref_tag == REF_ESCAPE)
+				goto next;
+			break;
+		}
+
+		csum = fn(iter->data_buf, iter->interval);
+
+		if (pi->guard_tag != csum) {
+			pr_err("%s: guard tag error at sector %llu " \
+			       "(rcvd %04x, want %04x)\n", iter->disk_name,
+			       (unsigned long long)iter->seed,
+			       be16_to_cpu(pi->guard_tag), be16_to_cpu(csum));
+			return -EILSEQ;
+		}
+
+next:
+		iter->data_buf += iter->interval;
+		iter->prot_buf += sizeof(struct t10_pi_tuple);
+		iter->seed++;
+	}
+
+	return 0;
+}
+
+static int t10_pi_type1_generate_crc(struct blk_integrity_iter *iter)
+{
+	return t10_pi_generate(iter, t10_pi_crc_fn, 1);
+}
+
+static int t10_pi_type1_generate_ip(struct blk_integrity_iter *iter)
+{
+	return t10_pi_generate(iter, t10_pi_ip_fn, 1);
+}
+
+static int t10_pi_type1_verify_crc(struct blk_integrity_iter *iter)
+{
+	return t10_pi_verify(iter, t10_pi_crc_fn, 1);
+}
+
+static int t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
+{
+	return t10_pi_verify(iter, t10_pi_ip_fn, 1);
+}
+
+static int t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
+{
+	return t10_pi_generate(iter, t10_pi_crc_fn, 3);
+}
+
+static int t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
+{
+	return t10_pi_generate(iter, t10_pi_ip_fn, 3);
+}
+
+static int t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
+{
+	return t10_pi_verify(iter, t10_pi_crc_fn, 3);
+}
+
+static int t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
+{
+	return t10_pi_verify(iter, t10_pi_ip_fn, 3);
+}
+
+struct blk_integrity t10_pi_type1_crc = {
+	.name			= "T10-DIF-TYPE1-CRC",
+	.generate_fn		= t10_pi_type1_generate_crc,
+	.verify_fn		= t10_pi_type1_verify_crc,
+	.tuple_size		= sizeof(struct t10_pi_tuple),
+	.tag_size		= 0,
+};
+EXPORT_SYMBOL(t10_pi_type1_crc);
+
+struct blk_integrity t10_pi_type1_ip = {
+	.name			= "T10-DIF-TYPE1-IP",
+	.generate_fn		= t10_pi_type1_generate_ip,
+	.verify_fn		= t10_pi_type1_verify_ip,
+	.tuple_size		= sizeof(struct t10_pi_tuple),
+	.tag_size		= 0,
+};
+EXPORT_SYMBOL(t10_pi_type1_ip);
+
+struct blk_integrity t10_pi_type3_crc = {
+	.name			= "T10-DIF-TYPE3-CRC",
+	.generate_fn		= t10_pi_type3_generate_crc,
+	.verify_fn		= t10_pi_type3_verify_crc,
+	.tuple_size		= sizeof(struct t10_pi_tuple),
+	.tag_size		= 0,
+};
+EXPORT_SYMBOL(t10_pi_type3_crc);
+
+struct blk_integrity t10_pi_type3_ip = {
+	.name			= "T10-DIF-TYPE3-IP",
+	.generate_fn		= t10_pi_type3_generate_ip,
+	.verify_fn		= t10_pi_type3_verify_ip,
+	.tuple_size		= sizeof(struct t10_pi_tuple),
+	.tag_size		= 0,
+};
+EXPORT_SYMBOL(t10_pi_type3_ip);
diff --git a/crypto/asymmetric_keys/asymmetric_keys.h b/crypto/asymmetric_keys/asymmetric_keys.h
index a63c551c6557..f97330886d58 100644
--- a/crypto/asymmetric_keys/asymmetric_keys.h
+++ b/crypto/asymmetric_keys/asymmetric_keys.h
@@ -9,9 +9,10 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
-int asymmetric_keyid_match(const char *kid, const char *id);
+extern struct asymmetric_key_id *asymmetric_key_hex_to_key_id(const char *id);
 
-static inline const char *asymmetric_key_id(const struct key *key)
+static inline
+const struct asymmetric_key_ids *asymmetric_key_ids(const struct key *key)
 {
 	return key->type_data.p[1];
 }
diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
index eb8cd46961a5..bcbbbd794e1d 100644
--- a/crypto/asymmetric_keys/asymmetric_type.c
+++ b/crypto/asymmetric_keys/asymmetric_type.c
@@ -15,6 +15,7 @@
 #include <linux/seq_file.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/ctype.h>
 #include "asymmetric_keys.h"
 
 MODULE_LICENSE("GPL");
@@ -22,85 +23,209 @@ MODULE_LICENSE("GPL");
 static LIST_HEAD(asymmetric_key_parsers);
 static DECLARE_RWSEM(asymmetric_key_parsers_sem);
 
-/*
- * Match asymmetric key id with partial match
- * @id:		key id to match in a form "id:<id>"
+/**
+ * asymmetric_key_generate_id: Construct an asymmetric key ID
+ * @val_1: First binary blob
+ * @len_1: Length of first binary blob
+ * @val_2: Second binary blob
+ * @len_2: Length of second binary blob
+ *
+ * Construct an asymmetric key ID from a pair of binary blobs.
  */
-int asymmetric_keyid_match(const char *kid, const char *id)
+struct asymmetric_key_id *asymmetric_key_generate_id(const void *val_1,
+						     size_t len_1,
+						     const void *val_2,
+						     size_t len_2)
 {
-	size_t idlen, kidlen;
+	struct asymmetric_key_id *kid;
+
+	kid = kmalloc(sizeof(struct asymmetric_key_id) + len_1 + len_2,
+		      GFP_KERNEL);
+	if (!kid)
+		return ERR_PTR(-ENOMEM);
+	kid->len = len_1 + len_2;
+	memcpy(kid->data, val_1, len_1);
+	memcpy(kid->data + len_1, val_2, len_2);
+	return kid;
+}
+EXPORT_SYMBOL_GPL(asymmetric_key_generate_id);
 
-	if (!kid || !id)
-		return 0;
+/**
+ * asymmetric_key_id_same - Return true if two asymmetric keys IDs are the same.
+ * @kid_1, @kid_2: The key IDs to compare
+ */
+bool asymmetric_key_id_same(const struct asymmetric_key_id *kid1,
+			    const struct asymmetric_key_id *kid2)
+{
+	if (!kid1 || !kid2)
+		return false;
+	if (kid1->len != kid2->len)
+		return false;
+	return memcmp(kid1->data, kid2->data, kid1->len) == 0;
+}
+EXPORT_SYMBOL_GPL(asymmetric_key_id_same);
 
-	/* make it possible to use id as in the request: "id:<id>" */
-	if (strncmp(id, "id:", 3) == 0)
-		id += 3;
+/**
+ * asymmetric_key_id_partial - Return true if two asymmetric keys IDs
+ * partially match
+ * @kid_1, @kid_2: The key IDs to compare
+ */
+bool asymmetric_key_id_partial(const struct asymmetric_key_id *kid1,
+			       const struct asymmetric_key_id *kid2)
+{
+	if (!kid1 || !kid2)
+		return false;
+	if (kid1->len < kid2->len)
+		return false;
+	return memcmp(kid1->data + (kid1->len - kid2->len),
+		      kid2->data, kid2->len) == 0;
+}
+EXPORT_SYMBOL_GPL(asymmetric_key_id_partial);
 
-	/* Anything after here requires a partial match on the ID string */
-	idlen = strlen(id);
-	kidlen = strlen(kid);
-	if (idlen > kidlen)
-		return 0;
+/**
+ * asymmetric_match_key_ids - Search asymmetric key IDs
+ * @kids: The list of key IDs to check
+ * @match_id: The key ID we're looking for
+ * @match: The match function to use
+ */
+static bool asymmetric_match_key_ids(
+	const struct asymmetric_key_ids *kids,
+	const struct asymmetric_key_id *match_id,
+	bool (*match)(const struct asymmetric_key_id *kid1,
+		      const struct asymmetric_key_id *kid2))
+{
+	int i;
+
+	if (!kids || !match_id)
+		return false;
+	for (i = 0; i < ARRAY_SIZE(kids->id); i++)
+		if (match(kids->id[i], match_id))
+			return true;
+	return false;
+}
 
-	kid += kidlen - idlen;
-	if (strcasecmp(id, kid) != 0)
-		return 0;
+/**
+ * asymmetric_key_hex_to_key_id - Convert a hex string into a key ID.
+ * @id: The ID as a hex string.
+ */
+struct asymmetric_key_id *asymmetric_key_hex_to_key_id(const char *id)
+{
+	struct asymmetric_key_id *match_id;
+	size_t hexlen;
+	int ret;
 
-	return 1;
+	if (!*id)
+		return ERR_PTR(-EINVAL);
+	hexlen = strlen(id);
+	if (hexlen & 1)
+		return ERR_PTR(-EINVAL);
+
+	match_id = kmalloc(sizeof(struct asymmetric_key_id) + hexlen / 2,
+			   GFP_KERNEL);
+	if (!match_id)
+		return ERR_PTR(-ENOMEM);
+	match_id->len = hexlen / 2;
+	ret = hex2bin(match_id->data, id, hexlen / 2);
+	if (ret < 0) {
+		kfree(match_id);
+		return ERR_PTR(-EINVAL);
+	}
+	return match_id;
 }
-EXPORT_SYMBOL_GPL(asymmetric_keyid_match);
 
 /*
- * Match asymmetric keys on (part of) their name
- * We have some shorthand methods for matching keys.  We allow:
- *
- *	"<desc>"	- request a key by description
- *	"id:<id>"	- request a key matching the ID
- *	"<subtype>:<id>" - request a key of a subtype
+ * Match asymmetric keys by an exact match on an ID.
  */
-static int asymmetric_key_match(const struct key *key, const void *description)
+static bool asymmetric_key_cmp(const struct key *key,
+			       const struct key_match_data *match_data)
 {
-	const struct asymmetric_key_subtype *subtype = asymmetric_key_subtype(key);
-	const char *spec = description;
-	const char *id;
-	ptrdiff_t speclen;
+	const struct asymmetric_key_ids *kids = asymmetric_key_ids(key);
+	const struct asymmetric_key_id *match_id = match_data->preparsed;
 
-	if (!subtype || !spec || !*spec)
-		return 0;
+	return asymmetric_match_key_ids(kids, match_id,
+					asymmetric_key_id_same);
+}
 
-	/* See if the full key description matches as is */
-	if (key->description && strcmp(key->description, description) == 0)
-		return 1;
+/*
+ * Match asymmetric keys by a partial match on an IDs.
+ */
+static bool asymmetric_key_cmp_partial(const struct key *key,
+				       const struct key_match_data *match_data)
+{
+	const struct asymmetric_key_ids *kids = asymmetric_key_ids(key);
+	const struct asymmetric_key_id *match_id = match_data->preparsed;
 
-	/* All tests from here on break the criterion description into a
-	 * specifier, a colon and then an identifier.
-	 */
-	id = strchr(spec, ':');
-	if (!id)
-		return 0;
+	return asymmetric_match_key_ids(kids, match_id,
+					asymmetric_key_id_partial);
+}
+
+/*
+ * Preparse the match criterion.  If we don't set lookup_type and cmp,
+ * the default will be an exact match on the key description.
+ *
+ * There are some specifiers for matching key IDs rather than by the key
+ * description:
+ *
+ *	"id:<id>" - find a key by partial match on any available ID
+ *	"ex:<id>" - find a key by exact match on any available ID
+ *
+ * These have to be searched by iteration rather than by direct lookup because
+ * the key is hashed according to its description.
+ */
+static int asymmetric_key_match_preparse(struct key_match_data *match_data)
+{
+	struct asymmetric_key_id *match_id;
+	const char *spec = match_data->raw_data;
+	const char *id;
+	bool (*cmp)(const struct key *, const struct key_match_data *) =
+		asymmetric_key_cmp;
 
-	speclen = id - spec;
-	id++;
+	if (!spec || !*spec)
+		return -EINVAL;
+	if (spec[0] == 'i' &&
+	    spec[1] == 'd' &&
+	    spec[2] == ':') {
+		id = spec + 3;
+		cmp = asymmetric_key_cmp_partial;
+	} else if (spec[0] == 'e' &&
+		   spec[1] == 'x' &&
+		   spec[2] == ':') {
+		id = spec + 3;
+	} else {
+		goto default_match;
+	}
 
-	if (speclen == 2 && memcmp(spec, "id", 2) == 0)
-		return asymmetric_keyid_match(asymmetric_key_id(key), id);
+	match_id = asymmetric_key_hex_to_key_id(id);
+	if (IS_ERR(match_id))
+		return PTR_ERR(match_id);
 
-	if (speclen == subtype->name_len &&
-	    memcmp(spec, subtype->name, speclen) == 0)
-		return 1;
+	match_data->preparsed = match_id;
+	match_data->cmp = cmp;
+	match_data->lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE;
+	return 0;
 
+default_match:
 	return 0;
 }
 
 /*
+ * Free the preparsed the match criterion.
+ */
+static void asymmetric_key_match_free(struct key_match_data *match_data)
+{
+	kfree(match_data->preparsed);
+}
+
+/*
  * Describe the asymmetric key
  */
 static void asymmetric_key_describe(const struct key *key, struct seq_file *m)
 {
 	const struct asymmetric_key_subtype *subtype = asymmetric_key_subtype(key);
-	const char *kid = asymmetric_key_id(key);
-	size_t n;
+	const struct asymmetric_key_ids *kids = asymmetric_key_ids(key);
+	const struct asymmetric_key_id *kid;
+	const unsigned char *p;
+	int n;
 
 	seq_puts(m, key->description);
 
@@ -108,13 +233,16 @@ static void asymmetric_key_describe(const struct key *key, struct seq_file *m)
 		seq_puts(m, ": ");
 		subtype->describe(key, m);
 
-		if (kid) {
+		if (kids && kids->id[1]) {
+			kid = kids->id[1];
 			seq_putc(m, ' ');
-			n = strlen(kid);
-			if (n <= 8)
-				seq_puts(m, kid);
-			else
-				seq_puts(m, kid + n - 8);
+			n = kid->len;
+			p = kid->data;
+			if (n > 4) {
+				p += n - 4;
+				n = 4;
+			}
+			seq_printf(m, "%*phN", n, p);
 		}
 
 		seq_puts(m, " [");
@@ -165,6 +293,8 @@ static int asymmetric_key_preparse(struct key_preparsed_payload *prep)
 static void asymmetric_key_free_preparse(struct key_preparsed_payload *prep)
 {
 	struct asymmetric_key_subtype *subtype = prep->type_data[0];
+	struct asymmetric_key_ids *kids = prep->type_data[1];
+	int i;
 
 	pr_devel("==>%s()\n", __func__);
 
@@ -172,7 +302,11 @@ static void asymmetric_key_free_preparse(struct key_preparsed_payload *prep)
 		subtype->destroy(prep->payload[0]);
 		module_put(subtype->owner);
 	}
-	kfree(prep->type_data[1]);
+	if (kids) {
+		for (i = 0; i < ARRAY_SIZE(kids->id); i++)
+			kfree(kids->id[i]);
+		kfree(kids);
+	}
 	kfree(prep->description);
 }
 
@@ -182,13 +316,20 @@ static void asymmetric_key_free_preparse(struct key_preparsed_payload *prep)
 static void asymmetric_key_destroy(struct key *key)
 {
 	struct asymmetric_key_subtype *subtype = asymmetric_key_subtype(key);
+	struct asymmetric_key_ids *kids = key->type_data.p[1];
+
 	if (subtype) {
 		subtype->destroy(key->payload.data);
 		module_put(subtype->owner);
 		key->type_data.p[0] = NULL;
 	}
-	kfree(key->type_data.p[1]);
-	key->type_data.p[1] = NULL;
+
+	if (kids) {
+		kfree(kids->id[0]);
+		kfree(kids->id[1]);
+		kfree(kids);
+		key->type_data.p[1] = NULL;
+	}
 }
 
 struct key_type key_type_asymmetric = {
@@ -196,10 +337,10 @@ struct key_type key_type_asymmetric = {
 	.preparse	= asymmetric_key_preparse,
 	.free_preparse	= asymmetric_key_free_preparse,
 	.instantiate	= generic_key_instantiate,
-	.match		= asymmetric_key_match,
+	.match_preparse	= asymmetric_key_match_preparse,
+	.match_free	= asymmetric_key_match_free,
 	.destroy	= asymmetric_key_destroy,
 	.describe	= asymmetric_key_describe,
-	.def_lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE,
 };
 EXPORT_SYMBOL_GPL(key_type_asymmetric);
 
diff --git a/crypto/asymmetric_keys/pkcs7_key_type.c b/crypto/asymmetric_keys/pkcs7_key_type.c
index 3de5fb011de0..751f8fd7335d 100644
--- a/crypto/asymmetric_keys/pkcs7_key_type.c
+++ b/crypto/asymmetric_keys/pkcs7_key_type.c
@@ -72,11 +72,9 @@ error:
  */
 static struct key_type key_type_pkcs7 = {
 	.name			= "pkcs7_test",
-	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	.preparse		= pkcs7_preparse,
 	.free_preparse		= user_free_preparse,
 	.instantiate		= generic_key_instantiate,
-	.match			= user_match,
 	.revoke			= user_revoke,
 	.destroy		= user_destroy,
 	.describe		= user_describe,
diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c
index 42e56aa7d277..3bd5a1e4c493 100644
--- a/crypto/asymmetric_keys/pkcs7_parser.c
+++ b/crypto/asymmetric_keys/pkcs7_parser.c
@@ -29,8 +29,25 @@ struct pkcs7_parse_context {
 	enum OID	last_oid;		/* Last OID encountered */
 	unsigned	x509_index;
 	unsigned	sinfo_index;
+	const void	*raw_serial;
+	unsigned	raw_serial_size;
+	unsigned	raw_issuer_size;
+	const void	*raw_issuer;
 };
 
+/*
+ * Free a signed information block.
+ */
+static void pkcs7_free_signed_info(struct pkcs7_signed_info *sinfo)
+{
+	if (sinfo) {
+		mpi_free(sinfo->sig.mpi[0]);
+		kfree(sinfo->sig.digest);
+		kfree(sinfo->signing_cert_id);
+		kfree(sinfo);
+	}
+}
+
 /**
  * pkcs7_free_message - Free a PKCS#7 message
  * @pkcs7: The PKCS#7 message to free
@@ -54,9 +71,7 @@ void pkcs7_free_message(struct pkcs7_message *pkcs7)
 		while (pkcs7->signed_infos) {
 			sinfo = pkcs7->signed_infos;
 			pkcs7->signed_infos = sinfo->next;
-			mpi_free(sinfo->sig.mpi[0]);
-			kfree(sinfo->sig.digest);
-			kfree(sinfo);
+			pkcs7_free_signed_info(sinfo);
 		}
 		kfree(pkcs7);
 	}
@@ -71,51 +86,46 @@ EXPORT_SYMBOL_GPL(pkcs7_free_message);
 struct pkcs7_message *pkcs7_parse_message(const void *data, size_t datalen)
 {
 	struct pkcs7_parse_context *ctx;
-	struct pkcs7_message *msg;
-	long ret;
+	struct pkcs7_message *msg = ERR_PTR(-ENOMEM);
+	int ret;
 
-	ret = -ENOMEM;
-	msg = kzalloc(sizeof(struct pkcs7_message), GFP_KERNEL);
-	if (!msg)
-		goto error_no_sig;
 	ctx = kzalloc(sizeof(struct pkcs7_parse_context), GFP_KERNEL);
 	if (!ctx)
-		goto error_no_ctx;
+		goto out_no_ctx;
+	ctx->msg = kzalloc(sizeof(struct pkcs7_message), GFP_KERNEL);
+	if (!ctx->msg)
+		goto out_no_msg;
 	ctx->sinfo = kzalloc(sizeof(struct pkcs7_signed_info), GFP_KERNEL);
 	if (!ctx->sinfo)
-		goto error_no_sinfo;
+		goto out_no_sinfo;
 
-	ctx->msg = msg;
 	ctx->data = (unsigned long)data;
 	ctx->ppcerts = &ctx->certs;
 	ctx->ppsinfo = &ctx->msg->signed_infos;
 
 	/* Attempt to decode the signature */
 	ret = asn1_ber_decoder(&pkcs7_decoder, ctx, data, datalen);
-	if (ret < 0)
-		goto error_decode;
+	if (ret < 0) {
+		msg = ERR_PTR(ret);
+		goto out;
+	}
 
+	msg = ctx->msg;
+	ctx->msg = NULL;
+
+out:
 	while (ctx->certs) {
 		struct x509_certificate *cert = ctx->certs;
 		ctx->certs = cert->next;
 		x509_free_certificate(cert);
 	}
-	mpi_free(ctx->sinfo->sig.mpi[0]);
-	kfree(ctx->sinfo->sig.digest);
-	kfree(ctx->sinfo);
+	pkcs7_free_signed_info(ctx->sinfo);
+out_no_sinfo:
+	pkcs7_free_message(ctx->msg);
+out_no_msg:
 	kfree(ctx);
+out_no_ctx:
 	return msg;
-
-error_decode:
-	mpi_free(ctx->sinfo->sig.mpi[0]);
-	kfree(ctx->sinfo->sig.digest);
-	kfree(ctx->sinfo);
-error_no_sinfo:
-	kfree(ctx);
-error_no_ctx:
-	pkcs7_free_message(msg);
-error_no_sig:
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(pkcs7_parse_message);
 
@@ -246,10 +256,10 @@ int pkcs7_extract_cert(void *context, size_t hdrlen,
 	if (IS_ERR(x509))
 		return PTR_ERR(x509);
 
-	pr_debug("Got cert for %s\n", x509->subject);
-	pr_debug("- fingerprint %s\n", x509->fingerprint);
-
 	x509->index = ++ctx->x509_index;
+	pr_debug("Got cert %u for %s\n", x509->index, x509->subject);
+	pr_debug("- fingerprint %*phN\n", x509->id->len, x509->id->data);
+
 	*ctx->ppcerts = x509;
 	ctx->ppcerts = &x509->next;
 	return 0;
@@ -338,8 +348,8 @@ int pkcs7_sig_note_serial(void *context, size_t hdrlen,
 			  const void *value, size_t vlen)
 {
 	struct pkcs7_parse_context *ctx = context;
-	ctx->sinfo->raw_serial = value;
-	ctx->sinfo->raw_serial_size = vlen;
+	ctx->raw_serial = value;
+	ctx->raw_serial_size = vlen;
 	return 0;
 }
 
@@ -351,8 +361,8 @@ int pkcs7_sig_note_issuer(void *context, size_t hdrlen,
 			  const void *value, size_t vlen)
 {
 	struct pkcs7_parse_context *ctx = context;
-	ctx->sinfo->raw_issuer = value;
-	ctx->sinfo->raw_issuer_size = vlen;
+	ctx->raw_issuer = value;
+	ctx->raw_issuer_size = vlen;
 	return 0;
 }
 
@@ -385,10 +395,21 @@ int pkcs7_note_signed_info(void *context, size_t hdrlen,
 			   const void *value, size_t vlen)
 {
 	struct pkcs7_parse_context *ctx = context;
-
-	ctx->sinfo->index = ++ctx->sinfo_index;
-	*ctx->ppsinfo = ctx->sinfo;
-	ctx->ppsinfo = &ctx->sinfo->next;
+	struct pkcs7_signed_info *sinfo = ctx->sinfo;
+	struct asymmetric_key_id *kid;
+
+	/* Generate cert issuer + serial number key ID */
+	kid = asymmetric_key_generate_id(ctx->raw_serial,
+					 ctx->raw_serial_size,
+					 ctx->raw_issuer,
+					 ctx->raw_issuer_size);
+	if (IS_ERR(kid))
+		return PTR_ERR(kid);
+
+	sinfo->signing_cert_id = kid;
+	sinfo->index = ++ctx->sinfo_index;
+	*ctx->ppsinfo = sinfo;
+	ctx->ppsinfo = &sinfo->next;
 	ctx->sinfo = kzalloc(sizeof(struct pkcs7_signed_info), GFP_KERNEL);
 	if (!ctx->sinfo)
 		return -ENOMEM;
diff --git a/crypto/asymmetric_keys/pkcs7_parser.h b/crypto/asymmetric_keys/pkcs7_parser.h
index d25f4d15370f..efc7dc9b8f9c 100644
--- a/crypto/asymmetric_keys/pkcs7_parser.h
+++ b/crypto/asymmetric_keys/pkcs7_parser.h
@@ -23,6 +23,7 @@ struct pkcs7_signed_info {
 	struct x509_certificate *signer; /* Signing certificate (in msg->certs) */
 	unsigned index;
 	bool trusted;
+	bool unsupported_crypto;	/* T if not usable due to missing crypto */
 
 	/* Message digest - the digest of the Content Data (or NULL) */
 	const void	*msgdigest;
@@ -33,10 +34,7 @@ struct pkcs7_signed_info {
 	const void	*authattrs;
 
 	/* Issuing cert serial number and issuer's name */
-	const void	*raw_serial;
-	unsigned	raw_serial_size;
-	unsigned	raw_issuer_size;
-	const void	*raw_issuer;
+	struct asymmetric_key_id *signing_cert_id;
 
 	/* Message signature.
 	 *
diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c
index e666eb011a85..1d29376072da 100644
--- a/crypto/asymmetric_keys/pkcs7_trust.c
+++ b/crypto/asymmetric_keys/pkcs7_trust.c
@@ -23,9 +23,9 @@
 /**
  * Check the trust on one PKCS#7 SignedInfo block.
  */
-int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
-			     struct pkcs7_signed_info *sinfo,
-			     struct key *trust_keyring)
+static int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
+				    struct pkcs7_signed_info *sinfo,
+				    struct key *trust_keyring)
 {
 	struct public_key_signature *sig = &sinfo->sig;
 	struct x509_certificate *x509, *last = NULL, *p;
@@ -35,6 +35,11 @@ int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 
 	kenter(",%u,", sinfo->index);
 
+	if (sinfo->unsupported_crypto) {
+		kleave(" = -ENOPKG [cached]");
+		return -ENOPKG;
+	}
+
 	for (x509 = sinfo->signer; x509; x509 = x509->signer) {
 		if (x509->seen) {
 			if (x509->verified) {
@@ -49,15 +54,18 @@ int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 		/* Look to see if this certificate is present in the trusted
 		 * keys.
 		 */
-		key = x509_request_asymmetric_key(trust_keyring, x509->subject,
-						  x509->fingerprint);
-		if (!IS_ERR(key))
+		key = x509_request_asymmetric_key(trust_keyring, x509->id,
+						  false);
+		if (!IS_ERR(key)) {
 			/* One of the X.509 certificates in the PKCS#7 message
 			 * is apparently the same as one we already trust.
 			 * Verify that the trusted variant can also validate
 			 * the signature on the descendant.
 			 */
+			pr_devel("sinfo %u: Cert %u as key %x\n",
+				 sinfo->index, x509->index, key_serial(key));
 			goto matched;
+		}
 		if (key == ERR_PTR(-ENOMEM))
 			return -ENOMEM;
 
@@ -77,16 +85,36 @@ int pkcs7_validate_trust_one(struct pkcs7_message *pkcs7,
 	/* No match - see if the root certificate has a signer amongst the
 	 * trusted keys.
 	 */
-	if (!last || !last->issuer || !last->authority) {
-		kleave(" = -ENOKEY [no backref]");
-		return -ENOKEY;
+	if (last && last->authority) {
+		key = x509_request_asymmetric_key(trust_keyring, last->authority,
+						  false);
+		if (!IS_ERR(key)) {
+			x509 = last;
+			pr_devel("sinfo %u: Root cert %u signer is key %x\n",
+				 sinfo->index, x509->index, key_serial(key));
+			goto matched;
+		}
+		if (PTR_ERR(key) != -ENOKEY)
+			return PTR_ERR(key);
+	}
+
+	/* As a last resort, see if we have a trusted public key that matches
+	 * the signed info directly.
+	 */
+	key = x509_request_asymmetric_key(trust_keyring,
+					  sinfo->signing_cert_id,
+					  false);
+	if (!IS_ERR(key)) {
+		pr_devel("sinfo %u: Direct signer is key %x\n",
+			 sinfo->index, key_serial(key));
+		x509 = NULL;
+		goto matched;
 	}
+	if (PTR_ERR(key) != -ENOKEY)
+		return PTR_ERR(key);
 
-	key = x509_request_asymmetric_key(trust_keyring, last->issuer,
-					  last->authority);
-	if (IS_ERR(key))
-		return PTR_ERR(key) == -ENOMEM ? -ENOMEM : -ENOKEY;
-	x509 = last;
+	kleave(" = -ENOKEY [no backref]");
+	return -ENOKEY;
 
 matched:
 	ret = verify_signature(key, sig);
@@ -100,10 +128,12 @@ matched:
 	}
 
 verified:
-	x509->verified = true;
-	for (p = sinfo->signer; p != x509; p = p->signer) {
-		p->verified = true;
-		p->trusted = trusted;
+	if (x509) {
+		x509->verified = true;
+		for (p = sinfo->signer; p != x509; p = p->signer) {
+			p->verified = true;
+			p->trusted = trusted;
+		}
 	}
 	sinfo->trusted = trusted;
 	kleave(" = 0");
@@ -141,24 +171,28 @@ int pkcs7_validate_trust(struct pkcs7_message *pkcs7,
 {
 	struct pkcs7_signed_info *sinfo;
 	struct x509_certificate *p;
-	int cached_ret = 0, ret;
+	int cached_ret = -ENOKEY;
+	int ret;
 
 	for (p = pkcs7->certs; p; p = p->next)
 		p->seen = false;
 
 	for (sinfo = pkcs7->signed_infos; sinfo; sinfo = sinfo->next) {
 		ret = pkcs7_validate_trust_one(pkcs7, sinfo, trust_keyring);
-		if (ret < 0) {
-			if (ret == -ENOPKG) {
+		switch (ret) {
+		case -ENOKEY:
+			continue;
+		case -ENOPKG:
+			if (cached_ret == -ENOKEY)
 				cached_ret = -ENOPKG;
-			} else if (ret == -ENOKEY) {
-				if (cached_ret == 0)
-					cached_ret = -ENOKEY;
-			} else {
-				return ret;
-			}
+			continue;
+		case 0:
+			*_trusted |= sinfo->trusted;
+			cached_ret = 0;
+			continue;
+		default:
+			return ret;
 		}
-		*_trusted |= sinfo->trusted;
 	}
 
 	return cached_ret;
diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c
index c62cf8006e1f..cd455450b069 100644
--- a/crypto/asymmetric_keys/pkcs7_verify.c
+++ b/crypto/asymmetric_keys/pkcs7_verify.c
@@ -131,8 +131,7 @@ static int pkcs7_find_key(struct pkcs7_message *pkcs7,
 	struct x509_certificate *x509;
 	unsigned certix = 1;
 
-	kenter("%u,%u,%u",
-	       sinfo->index, sinfo->raw_serial_size, sinfo->raw_issuer_size);
+	kenter("%u", sinfo->index);
 
 	for (x509 = pkcs7->certs; x509; x509 = x509->next, certix++) {
 		/* I'm _assuming_ that the generator of the PKCS#7 message will
@@ -140,21 +139,11 @@ static int pkcs7_find_key(struct pkcs7_message *pkcs7,
 		 * PKCS#7 message - but I can't be 100% sure of that.  It's
 		 * possible this will need element-by-element comparison.
 		 */
-		if (x509->raw_serial_size != sinfo->raw_serial_size ||
-		    memcmp(x509->raw_serial, sinfo->raw_serial,
-			   sinfo->raw_serial_size) != 0)
+		if (!asymmetric_key_id_same(x509->id, sinfo->signing_cert_id))
 			continue;
 		pr_devel("Sig %u: Found cert serial match X.509[%u]\n",
 			 sinfo->index, certix);
 
-		if (x509->raw_issuer_size != sinfo->raw_issuer_size ||
-		    memcmp(x509->raw_issuer, sinfo->raw_issuer,
-			   sinfo->raw_issuer_size) != 0) {
-			pr_warn("Sig %u: X.509 subject and PKCS#7 issuer don't match\n",
-				sinfo->index);
-			continue;
-		}
-
 		if (x509->pub->pkey_algo != sinfo->sig.pkey_algo) {
 			pr_warn("Sig %u: X.509 algo and PKCS#7 sig algo don't match\n",
 				sinfo->index);
@@ -164,9 +153,14 @@ static int pkcs7_find_key(struct pkcs7_message *pkcs7,
 		sinfo->signer = x509;
 		return 0;
 	}
-	pr_warn("Sig %u: Issuing X.509 cert not found (#%*ph)\n",
-		sinfo->index, sinfo->raw_serial_size, sinfo->raw_serial);
-	return -ENOKEY;
+
+	/* The relevant X.509 cert isn't found here, but it might be found in
+	 * the trust keyring.
+	 */
+	pr_debug("Sig %u: Issuing X.509 cert not found (#%*phN)\n",
+		 sinfo->index,
+		 sinfo->signing_cert_id->len, sinfo->signing_cert_id->data);
+	return 0;
 }
 
 /*
@@ -184,15 +178,18 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 		p->seen = false;
 
 	for (;;) {
-		pr_debug("verify %s: %s\n", x509->subject, x509->fingerprint);
+		pr_debug("verify %s: %*phN\n",
+			 x509->subject,
+			 x509->raw_serial_size, x509->raw_serial);
 		x509->seen = true;
 		ret = x509_get_sig_params(x509);
 		if (ret < 0)
-			return ret;
+			goto maybe_missing_crypto_in_x509;
 
 		pr_debug("- issuer %s\n", x509->issuer);
 		if (x509->authority)
-			pr_debug("- authkeyid %s\n", x509->authority);
+			pr_debug("- authkeyid %*phN\n",
+				 x509->authority->len, x509->authority->data);
 
 		if (!x509->authority ||
 		    strcmp(x509->subject, x509->issuer) == 0) {
@@ -209,7 +206,7 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 
 			ret = x509_check_signature(x509->pub, x509);
 			if (ret < 0)
-				return ret;
+				goto maybe_missing_crypto_in_x509;
 			x509->signer = x509;
 			pr_debug("- self-signed\n");
 			return 0;
@@ -218,13 +215,14 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 		/* Look through the X.509 certificates in the PKCS#7 message's
 		 * list to see if the next one is there.
 		 */
-		pr_debug("- want %s\n", x509->authority);
+		pr_debug("- want %*phN\n",
+			 x509->authority->len, x509->authority->data);
 		for (p = pkcs7->certs; p; p = p->next) {
-			pr_debug("- cmp [%u] %s\n", p->index, p->fingerprint);
-			if (p->raw_subject_size == x509->raw_issuer_size &&
-			    strcmp(p->fingerprint, x509->authority) == 0 &&
-			    memcmp(p->raw_subject, x509->raw_issuer,
-				   x509->raw_issuer_size) == 0)
+			if (!p->skid)
+				continue;
+			pr_debug("- cmp [%u] %*phN\n",
+				 p->index, p->skid->len, p->skid->data);
+			if (asymmetric_key_id_same(p->skid, x509->authority))
 				goto found_issuer;
 		}
 
@@ -233,7 +231,7 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 		return 0;
 
 	found_issuer:
-		pr_debug("- issuer %s\n", p->subject);
+		pr_debug("- subject %s\n", p->subject);
 		if (p->seen) {
 			pr_warn("Sig %u: X.509 chain contains loop\n",
 				sinfo->index);
@@ -250,6 +248,17 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7,
 		x509 = p;
 		might_sleep();
 	}
+
+maybe_missing_crypto_in_x509:
+	/* Just prune the certificate chain at this point if we lack some
+	 * crypto module to go further.  Note, however, we don't want to set
+	 * sinfo->missing_crypto as the signed info block may still be
+	 * validatable against an X.509 cert lower in the chain that we have a
+	 * trusted copy of.
+	 */
+	if (ret == -ENOPKG)
+		return 0;
+	return ret;
 }
 
 /*
@@ -269,11 +278,14 @@ static int pkcs7_verify_one(struct pkcs7_message *pkcs7,
 	if (ret < 0)
 		return ret;
 
-	/* Find the key for the signature */
+	/* Find the key for the signature if there is one */
 	ret = pkcs7_find_key(pkcs7, sinfo);
 	if (ret < 0)
 		return ret;
 
+	if (!sinfo->signer)
+		return 0;
+
 	pr_devel("Using X.509[%u] for sig %u\n",
 		 sinfo->signer->index, sinfo->index);
 
@@ -291,11 +303,33 @@ static int pkcs7_verify_one(struct pkcs7_message *pkcs7,
 /**
  * pkcs7_verify - Verify a PKCS#7 message
  * @pkcs7: The PKCS#7 message to be verified
+ *
+ * Verify a PKCS#7 message is internally consistent - that is, the data digest
+ * matches the digest in the AuthAttrs and any signature in the message or one
+ * of the X.509 certificates it carries that matches another X.509 cert in the
+ * message can be verified.
+ *
+ * This does not look to match the contents of the PKCS#7 message against any
+ * external public keys.
+ *
+ * Returns, in order of descending priority:
+ *
+ *  (*) -EKEYREJECTED if a signature failed to match for which we found an
+ *	appropriate X.509 certificate, or:
+ *
+ *  (*) -EBADMSG if some part of the message was invalid, or:
+ *
+ *  (*) -ENOPKG if none of the signature chains are verifiable because suitable
+ *	crypto modules couldn't be found, or:
+ *
+ *  (*) 0 if all the signature chains that don't incur -ENOPKG can be verified
+ *	(note that a signature chain may be of zero length), or:
  */
 int pkcs7_verify(struct pkcs7_message *pkcs7)
 {
 	struct pkcs7_signed_info *sinfo;
 	struct x509_certificate *x509;
+	int enopkg = -ENOPKG;
 	int ret, n;
 
 	kenter("");
@@ -304,18 +338,24 @@ int pkcs7_verify(struct pkcs7_message *pkcs7)
 		ret = x509_get_sig_params(x509);
 		if (ret < 0)
 			return ret;
-		pr_debug("X.509[%u] %s\n", n, x509->authority);
+		pr_debug("X.509[%u] %*phN\n",
+			 n, x509->authority->len, x509->authority->data);
 	}
 
 	for (sinfo = pkcs7->signed_infos; sinfo; sinfo = sinfo->next) {
 		ret = pkcs7_verify_one(pkcs7, sinfo);
 		if (ret < 0) {
+			if (ret == -ENOPKG) {
+				sinfo->unsupported_crypto = true;
+				continue;
+			}
 			kleave(" = %d", ret);
 			return ret;
 		}
+		enopkg = 0;
 	}
 
-	kleave(" = 0");
-	return 0;
+	kleave(" = %d", enopkg);
+	return enopkg;
 }
 EXPORT_SYMBOL_GPL(pkcs7_verify);
diff --git a/crypto/asymmetric_keys/signature.c b/crypto/asymmetric_keys/signature.c
index 50b3f880b4ff..7525fd183574 100644
--- a/crypto/asymmetric_keys/signature.c
+++ b/crypto/asymmetric_keys/signature.c
@@ -11,6 +11,7 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) "SIG: "fmt
 #include <keys/asymmetric-subtype.h>
 #include <linux/module.h>
 #include <linux/err.h>
diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index ac72348c186a..a668d90302d3 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -46,7 +46,8 @@ void x509_free_certificate(struct x509_certificate *cert)
 		public_key_destroy(cert->pub);
 		kfree(cert->issuer);
 		kfree(cert->subject);
-		kfree(cert->fingerprint);
+		kfree(cert->id);
+		kfree(cert->skid);
 		kfree(cert->authority);
 		kfree(cert->sig.digest);
 		mpi_free(cert->sig.rsa.s);
@@ -62,6 +63,7 @@ struct x509_certificate *x509_cert_parse(const void *data, size_t datalen)
 {
 	struct x509_certificate *cert;
 	struct x509_parse_context *ctx;
+	struct asymmetric_key_id *kid;
 	long ret;
 
 	ret = -ENOMEM;
@@ -89,6 +91,17 @@ struct x509_certificate *x509_cert_parse(const void *data, size_t datalen)
 	if (ret < 0)
 		goto error_decode;
 
+	/* Generate cert issuer + serial number key ID */
+	kid = asymmetric_key_generate_id(cert->raw_serial,
+					 cert->raw_serial_size,
+					 cert->raw_issuer,
+					 cert->raw_issuer_size);
+	if (IS_ERR(kid)) {
+		ret = PTR_ERR(kid);
+		goto error_decode;
+	}
+	cert->id = kid;
+
 	kfree(ctx);
 	return cert;
 
@@ -407,36 +420,36 @@ int x509_process_extension(void *context, size_t hdrlen,
 			   const void *value, size_t vlen)
 {
 	struct x509_parse_context *ctx = context;
+	struct asymmetric_key_id *kid;
 	const unsigned char *v = value;
-	char *f;
 	int i;
 
 	pr_debug("Extension: %u\n", ctx->last_oid);
 
 	if (ctx->last_oid == OID_subjectKeyIdentifier) {
 		/* Get hold of the key fingerprint */
-		if (vlen < 3)
+		if (ctx->cert->skid || vlen < 3)
 			return -EBADMSG;
 		if (v[0] != ASN1_OTS || v[1] != vlen - 2)
 			return -EBADMSG;
 		v += 2;
 		vlen -= 2;
 
-		f = kmalloc(vlen * 2 + 1, GFP_KERNEL);
-		if (!f)
-			return -ENOMEM;
-		for (i = 0; i < vlen; i++)
-			sprintf(f + i * 2, "%02x", v[i]);
-		pr_debug("fingerprint %s\n", f);
-		ctx->cert->fingerprint = f;
+		ctx->cert->raw_skid_size = vlen;
+		ctx->cert->raw_skid = v;
+		kid = asymmetric_key_generate_id(ctx->cert->raw_subject,
+						 ctx->cert->raw_subject_size,
+						 v, vlen);
+		if (IS_ERR(kid))
+			return PTR_ERR(kid);
+		ctx->cert->skid = kid;
+		pr_debug("subjkeyid %*phN\n", kid->len, kid->data);
 		return 0;
 	}
 
 	if (ctx->last_oid == OID_authorityKeyIdentifier) {
-		size_t key_len;
-
 		/* Get hold of the CA key fingerprint */
-		if (vlen < 5)
+		if (ctx->cert->authority || vlen < 5)
 			return -EBADMSG;
 
 		/* Authority Key Identifier must be a Constructed SEQUENCE */
@@ -454,7 +467,7 @@ int x509_process_extension(void *context, size_t hdrlen,
 			    v[3] > vlen - 4)
 				return -EBADMSG;
 
-			key_len = v[3];
+			vlen = v[3];
 			v += 4;
 		} else {
 			/* Long Form length */
@@ -476,17 +489,17 @@ int x509_process_extension(void *context, size_t hdrlen,
 			    v[sub + 1] > vlen - 4 - sub)
 				return -EBADMSG;
 
-			key_len = v[sub + 1];
+			vlen = v[sub + 1];
 			v += (sub + 2);
 		}
 
-		f = kmalloc(key_len * 2 + 1, GFP_KERNEL);
-		if (!f)
-			return -ENOMEM;
-		for (i = 0; i < key_len; i++)
-			sprintf(f + i * 2, "%02x", v[i]);
-		pr_debug("authority   %s\n", f);
-		ctx->cert->authority = f;
+		kid = asymmetric_key_generate_id(ctx->cert->raw_issuer,
+						 ctx->cert->raw_issuer_size,
+						 v, vlen);
+		if (IS_ERR(kid))
+			return PTR_ERR(kid);
+		pr_debug("authkeyid %*phN\n", kid->len, kid->data);
+		ctx->cert->authority = kid;
 		return 0;
 	}
 
diff --git a/crypto/asymmetric_keys/x509_parser.h b/crypto/asymmetric_keys/x509_parser.h
index 1b76f207c1f3..3dfe6b5d6f0b 100644
--- a/crypto/asymmetric_keys/x509_parser.h
+++ b/crypto/asymmetric_keys/x509_parser.h
@@ -19,8 +19,9 @@ struct x509_certificate {
 	struct public_key_signature sig;	/* Signature parameters */
 	char		*issuer;		/* Name of certificate issuer */
 	char		*subject;		/* Name of certificate subject */
-	char		*fingerprint;		/* Key fingerprint as hex */
-	char		*authority;		/* Authority key fingerprint as hex */
+	struct asymmetric_key_id *id;		/* Serial number + issuer */
+	struct asymmetric_key_id *skid;		/* Subject + subjectKeyId (optional) */
+	struct asymmetric_key_id *authority;	/* Authority key identifier (optional) */
 	struct tm	valid_from;
 	struct tm	valid_to;
 	const void	*tbs;			/* Signed data */
@@ -33,10 +34,13 @@ struct x509_certificate {
 	const void	*raw_issuer;		/* Raw issuer name in ASN.1 */
 	const void	*raw_subject;		/* Raw subject name in ASN.1 */
 	unsigned	raw_subject_size;
+	unsigned	raw_skid_size;
+	const void	*raw_skid;		/* Raw subjectKeyId in ASN.1 */
 	unsigned	index;
 	bool		seen;			/* Infinite recursion prevention */
 	bool		verified;
 	bool		trusted;
+	bool		unsupported_crypto;	/* T if can't be verified due to missing crypto */
 };
 
 /*
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index f3d62307e6ee..a6c42031628e 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -25,7 +25,7 @@
 #include "x509_parser.h"
 
 static bool use_builtin_keys;
-static char *ca_keyid;
+static struct asymmetric_key_id *ca_keyid;
 
 #ifndef MODULE
 static int __init ca_keys_setup(char *str)
@@ -33,10 +33,16 @@ static int __init ca_keys_setup(char *str)
 	if (!str)		/* default system keyring */
 		return 1;
 
-	if (strncmp(str, "id:", 3) == 0)
-		ca_keyid = str;	/* owner key 'id:xxxxxx' */
-	else if (strcmp(str, "builtin") == 0)
+	if (strncmp(str, "id:", 3) == 0) {
+		struct asymmetric_key_id *p;
+		p = asymmetric_key_hex_to_key_id(str + 3);
+		if (p == ERR_PTR(-EINVAL))
+			pr_err("Unparsable hex string in ca_keys\n");
+		else if (!IS_ERR(p))
+			ca_keyid = p;	/* owner key 'id:xxxxxx' */
+	} else if (strcmp(str, "builtin") == 0) {
 		use_builtin_keys = true;
+	}
 
 	return 1;
 }
@@ -46,31 +52,35 @@ __setup("ca_keys=", ca_keys_setup);
 /**
  * x509_request_asymmetric_key - Request a key by X.509 certificate params.
  * @keyring: The keys to search.
- * @subject: The name of the subject to whom the key belongs.
- * @key_id: The subject key ID as a hex string.
+ * @kid: The key ID.
+ * @partial: Use partial match if true, exact if false.
  *
  * Find a key in the given keyring by subject name and key ID.  These might,
  * for instance, be the issuer name and the authority key ID of an X.509
  * certificate that needs to be verified.
  */
 struct key *x509_request_asymmetric_key(struct key *keyring,
-					const char *subject,
-					const char *key_id)
+					const struct asymmetric_key_id *kid,
+					bool partial)
 {
 	key_ref_t key;
-	size_t subject_len = strlen(subject), key_id_len = strlen(key_id);
-	char *id;
+	char *id, *p;
 
-	/* Construct an identifier "<subjname>:<keyid>". */
-	id = kmalloc(subject_len + 2 + key_id_len + 1, GFP_KERNEL);
+	/* Construct an identifier "id:<keyid>". */
+	p = id = kmalloc(2 + 1 + kid->len * 2 + 1, GFP_KERNEL);
 	if (!id)
 		return ERR_PTR(-ENOMEM);
 
-	memcpy(id, subject, subject_len);
-	id[subject_len + 0] = ':';
-	id[subject_len + 1] = ' ';
-	memcpy(id + subject_len + 2, key_id, key_id_len);
-	id[subject_len + 2 + key_id_len] = 0;
+	if (partial) {
+		*p++ = 'i';
+		*p++ = 'd';
+	} else {
+		*p++ = 'e';
+		*p++ = 'x';
+	}
+	*p++ = ':';
+	p = bin2hex(p, kid->data, kid->len);
+	*p = 0;
 
 	pr_debug("Look up: \"%s\"\n", id);
 
@@ -112,6 +122,8 @@ int x509_get_sig_params(struct x509_certificate *cert)
 
 	pr_devel("==>%s()\n", __func__);
 
+	if (cert->unsupported_crypto)
+		return -ENOPKG;
 	if (cert->sig.rsa.s)
 		return 0;
 
@@ -124,8 +136,13 @@ int x509_get_sig_params(struct x509_certificate *cert)
 	 * big the hash operational data will be.
 	 */
 	tfm = crypto_alloc_shash(hash_algo_name[cert->sig.pkey_hash_algo], 0, 0);
-	if (IS_ERR(tfm))
-		return (PTR_ERR(tfm) == -ENOENT) ? -ENOPKG : PTR_ERR(tfm);
+	if (IS_ERR(tfm)) {
+		if (PTR_ERR(tfm) == -ENOENT) {
+			cert->unsupported_crypto = true;
+			return -ENOPKG;
+		}
+		return PTR_ERR(tfm);
+	}
 
 	desc_size = crypto_shash_descsize(tfm) + sizeof(*desc);
 	digest_size = crypto_shash_digestsize(tfm);
@@ -172,6 +189,8 @@ int x509_check_signature(const struct public_key *pub,
 		return ret;
 
 	ret = public_key_verify_signature(pub, &cert->sig);
+	if (ret == -ENOPKG)
+		cert->unsupported_crypto = true;
 	pr_debug("Cert Verification: %d\n", ret);
 	return ret;
 }
@@ -195,11 +214,11 @@ static int x509_validate_trust(struct x509_certificate *cert,
 	if (!trust_keyring)
 		return -EOPNOTSUPP;
 
-	if (ca_keyid && !asymmetric_keyid_match(cert->authority, ca_keyid))
+	if (ca_keyid && !asymmetric_key_id_partial(cert->authority, ca_keyid))
 		return -EPERM;
 
-	key = x509_request_asymmetric_key(trust_keyring,
-					  cert->issuer, cert->authority);
+	key = x509_request_asymmetric_key(trust_keyring, cert->authority,
+					  false);
 	if (!IS_ERR(key))  {
 		if (!use_builtin_keys
 		    || test_bit(KEY_FLAG_BUILTIN, &key->flags))
@@ -214,9 +233,11 @@ static int x509_validate_trust(struct x509_certificate *cert,
  */
 static int x509_key_preparse(struct key_preparsed_payload *prep)
 {
+	struct asymmetric_key_ids *kids;
 	struct x509_certificate *cert;
+	const char *q;
 	size_t srlen, sulen;
-	char *desc = NULL;
+	char *desc = NULL, *p;
 	int ret;
 
 	cert = x509_cert_parse(prep->data, prep->datalen);
@@ -249,19 +270,12 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 		 pkey_algo_name[cert->sig.pkey_algo],
 		 hash_algo_name[cert->sig.pkey_hash_algo]);
 
-	if (!cert->fingerprint) {
-		pr_warn("Cert for '%s' must have a SubjKeyId extension\n",
-			cert->subject);
-		ret = -EKEYREJECTED;
-		goto error_free_cert;
-	}
-
 	cert->pub->algo = pkey_algo[cert->pub->pkey_algo];
 	cert->pub->id_type = PKEY_ID_X509;
 
 	/* Check the signature on the key if it appears to be self-signed */
 	if (!cert->authority ||
-	    strcmp(cert->fingerprint, cert->authority) == 0) {
+	    asymmetric_key_id_same(cert->skid, cert->authority)) {
 		ret = x509_check_signature(cert->pub, cert); /* self-signed */
 		if (ret < 0)
 			goto error_free_cert;
@@ -273,31 +287,52 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 
 	/* Propose a description */
 	sulen = strlen(cert->subject);
-	srlen = strlen(cert->fingerprint);
+	if (cert->raw_skid) {
+		srlen = cert->raw_skid_size;
+		q = cert->raw_skid;
+	} else {
+		srlen = cert->raw_serial_size;
+		q = cert->raw_serial;
+	}
+	if (srlen > 1 && *q == 0) {
+		srlen--;
+		q++;
+	}
+
 	ret = -ENOMEM;
-	desc = kmalloc(sulen + 2 + srlen + 1, GFP_KERNEL);
+	desc = kmalloc(sulen + 2 + srlen * 2 + 1, GFP_KERNEL);
 	if (!desc)
 		goto error_free_cert;
-	memcpy(desc, cert->subject, sulen);
-	desc[sulen] = ':';
-	desc[sulen + 1] = ' ';
-	memcpy(desc + sulen + 2, cert->fingerprint, srlen);
-	desc[sulen + 2 + srlen] = 0;
+	p = memcpy(desc, cert->subject, sulen);
+	p += sulen;
+	*p++ = ':';
+	*p++ = ' ';
+	p = bin2hex(p, q, srlen);
+	*p = 0;
+
+	kids = kmalloc(sizeof(struct asymmetric_key_ids), GFP_KERNEL);
+	if (!kids)
+		goto error_free_desc;
+	kids->id[0] = cert->id;
+	kids->id[1] = cert->skid;
 
 	/* We're pinning the module by being linked against it */
 	__module_get(public_key_subtype.owner);
 	prep->type_data[0] = &public_key_subtype;
-	prep->type_data[1] = cert->fingerprint;
+	prep->type_data[1] = kids;
 	prep->payload[0] = cert->pub;
 	prep->description = desc;
 	prep->quotalen = 100;
 
 	/* We've finished with the certificate */
 	cert->pub = NULL;
-	cert->fingerprint = NULL;
+	cert->id = NULL;
+	cert->skid = NULL;
 	desc = NULL;
 	ret = 0;
 
+error_free_desc:
+	kfree(desc);
 error_free_cert:
 	x509_free_certificate(cert);
 	return ret;
diff --git a/crypto/hmac.c b/crypto/hmac.c
index 8d9544cf8169..e392219ddc61 100644
--- a/crypto/hmac.c
+++ b/crypto/hmac.c
@@ -52,20 +52,17 @@ static int hmac_setkey(struct crypto_shash *parent,
 	struct hmac_ctx *ctx = align_ptr(opad + ss,
 					 crypto_tfm_ctx_alignment());
 	struct crypto_shash *hash = ctx->hash;
-	struct {
-		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(hash)];
-	} desc;
+	SHASH_DESC_ON_STACK(shash, hash);
 	unsigned int i;
 
-	desc.shash.tfm = hash;
-	desc.shash.flags = crypto_shash_get_flags(parent) &
-			    CRYPTO_TFM_REQ_MAY_SLEEP;
+	shash->tfm = hash;
+	shash->flags = crypto_shash_get_flags(parent)
+		& CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	if (keylen > bs) {
 		int err;
 
-		err = crypto_shash_digest(&desc.shash, inkey, keylen, ipad);
+		err = crypto_shash_digest(shash, inkey, keylen, ipad);
 		if (err)
 			return err;
 
@@ -81,12 +78,12 @@ static int hmac_setkey(struct crypto_shash *parent,
 		opad[i] ^= 0x5c;
 	}
 
-	return crypto_shash_init(&desc.shash) ?:
-	       crypto_shash_update(&desc.shash, ipad, bs) ?:
-	       crypto_shash_export(&desc.shash, ipad) ?:
-	       crypto_shash_init(&desc.shash) ?:
-	       crypto_shash_update(&desc.shash, opad, bs) ?:
-	       crypto_shash_export(&desc.shash, opad);
+	return crypto_shash_init(shash) ?:
+	       crypto_shash_update(shash, ipad, bs) ?:
+	       crypto_shash_export(shash, ipad) ?:
+	       crypto_shash_init(shash) ?:
+	       crypto_shash_update(shash, opad, bs) ?:
+	       crypto_shash_export(shash, opad);
 }
 
 static int hmac_export(struct shash_desc *pdesc, void *out)
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 9459dfd7357f..29a0cbdd0d19 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -1678,16 +1678,14 @@ static int alg_test_crc32c(const struct alg_test_desc *desc,
 	}
 
 	do {
-		struct {
-			struct shash_desc shash;
-			char ctx[crypto_shash_descsize(tfm)];
-		} sdesc;
+		SHASH_DESC_ON_STACK(shash, tfm);
+		u32 *ctx = (u32 *)shash_desc_ctx(shash);
 
-		sdesc.shash.tfm = tfm;
-		sdesc.shash.flags = 0;
+		shash->tfm = tfm;
+		shash->flags = 0;
 
-		*(u32 *)sdesc.ctx = le32_to_cpu(420553207);
-		err = crypto_shash_final(&sdesc.shash, (u8 *)&val);
+		*ctx = le32_to_cpu(420553207);
+		err = crypto_shash_final(shash, (u8 *)&val);
 		if (err) {
 			printk(KERN_ERR "alg: crc32c: Operation failed for "
 			       "%s: %d\n", driver, err);
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index b0ea767c8696..93d160661f4c 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -54,55 +54,58 @@ ACPI_MODULE_NAME("acpi_lpss");
 
 #define LPSS_PRV_REG_COUNT		9
 
-struct lpss_shared_clock {
-	const char *name;
-	unsigned long rate;
-	struct clk *clk;
-};
+/* LPSS Flags */
+#define LPSS_CLK			BIT(0)
+#define LPSS_CLK_GATE			BIT(1)
+#define LPSS_CLK_DIVIDER		BIT(2)
+#define LPSS_LTR			BIT(3)
+#define LPSS_SAVE_CTX			BIT(4)
 
 struct lpss_private_data;
 
 struct lpss_device_desc {
-	bool clk_required;
-	const char *clkdev_name;
-	bool ltr_required;
+	unsigned int flags;
 	unsigned int prv_offset;
 	size_t prv_size_override;
-	bool clk_divider;
-	bool clk_gate;
-	bool save_ctx;
-	struct lpss_shared_clock *shared_clock;
 	void (*setup)(struct lpss_private_data *pdata);
 };
 
 static struct lpss_device_desc lpss_dma_desc = {
-	.clk_required = true,
-	.clkdev_name = "hclk",
+	.flags = LPSS_CLK,
 };
 
 struct lpss_private_data {
 	void __iomem *mmio_base;
 	resource_size_t mmio_size;
+	unsigned int fixed_clk_rate;
 	struct clk *clk;
 	const struct lpss_device_desc *dev_desc;
 	u32 prv_reg_ctx[LPSS_PRV_REG_COUNT];
 };
 
+/* UART Component Parameter Register */
+#define LPSS_UART_CPR			0xF4
+#define LPSS_UART_CPR_AFCE		BIT(4)
+
 static void lpss_uart_setup(struct lpss_private_data *pdata)
 {
 	unsigned int offset;
-	u32 reg;
+	u32 val;
 
 	offset = pdata->dev_desc->prv_offset + LPSS_TX_INT;
-	reg = readl(pdata->mmio_base + offset);
-	writel(reg | LPSS_TX_INT_MASK, pdata->mmio_base + offset);
-
-	offset = pdata->dev_desc->prv_offset + LPSS_GENERAL;
-	reg = readl(pdata->mmio_base + offset);
-	writel(reg | LPSS_GENERAL_UART_RTS_OVRD, pdata->mmio_base + offset);
+	val = readl(pdata->mmio_base + offset);
+	writel(val | LPSS_TX_INT_MASK, pdata->mmio_base + offset);
+
+	val = readl(pdata->mmio_base + LPSS_UART_CPR);
+	if (!(val & LPSS_UART_CPR_AFCE)) {
+		offset = pdata->dev_desc->prv_offset + LPSS_GENERAL;
+		val = readl(pdata->mmio_base + offset);
+		val |= LPSS_GENERAL_UART_RTS_OVRD;
+		writel(val, pdata->mmio_base + offset);
+	}
 }
 
-static void lpss_i2c_setup(struct lpss_private_data *pdata)
+static void byt_i2c_setup(struct lpss_private_data *pdata)
 {
 	unsigned int offset;
 	u32 val;
@@ -111,100 +114,56 @@ static void lpss_i2c_setup(struct lpss_private_data *pdata)
 	val = readl(pdata->mmio_base + offset);
 	val |= LPSS_RESETS_RESET_APB | LPSS_RESETS_RESET_FUNC;
 	writel(val, pdata->mmio_base + offset);
-}
 
-static struct lpss_device_desc wpt_dev_desc = {
-	.clk_required = true,
-	.prv_offset = 0x800,
-	.ltr_required = true,
-	.clk_divider = true,
-	.clk_gate = true,
-};
+	if (readl(pdata->mmio_base + pdata->dev_desc->prv_offset))
+		pdata->fixed_clk_rate = 133000000;
+}
 
 static struct lpss_device_desc lpt_dev_desc = {
-	.clk_required = true,
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR,
 	.prv_offset = 0x800,
-	.ltr_required = true,
-	.clk_divider = true,
-	.clk_gate = true,
 };
 
 static struct lpss_device_desc lpt_i2c_dev_desc = {
-	.clk_required = true,
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_LTR,
 	.prv_offset = 0x800,
-	.ltr_required = true,
-	.clk_gate = true,
 };
 
 static struct lpss_device_desc lpt_uart_dev_desc = {
-	.clk_required = true,
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR,
 	.prv_offset = 0x800,
-	.ltr_required = true,
-	.clk_divider = true,
-	.clk_gate = true,
 	.setup = lpss_uart_setup,
 };
 
 static struct lpss_device_desc lpt_sdio_dev_desc = {
+	.flags = LPSS_LTR,
 	.prv_offset = 0x1000,
 	.prv_size_override = 0x1018,
-	.ltr_required = true,
-};
-
-static struct lpss_shared_clock pwm_clock = {
-	.name = "pwm_clk",
-	.rate = 25000000,
 };
 
 static struct lpss_device_desc byt_pwm_dev_desc = {
-	.clk_required = true,
-	.save_ctx = true,
-	.shared_clock = &pwm_clock,
+	.flags = LPSS_SAVE_CTX,
 };
 
 static struct lpss_device_desc byt_uart_dev_desc = {
-	.clk_required = true,
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
 	.prv_offset = 0x800,
-	.clk_divider = true,
-	.clk_gate = true,
-	.save_ctx = true,
 	.setup = lpss_uart_setup,
 };
 
 static struct lpss_device_desc byt_spi_dev_desc = {
-	.clk_required = true,
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
 	.prv_offset = 0x400,
-	.clk_divider = true,
-	.clk_gate = true,
-	.save_ctx = true,
 };
 
 static struct lpss_device_desc byt_sdio_dev_desc = {
-	.clk_required = true,
-};
-
-static struct lpss_shared_clock i2c_clock = {
-	.name = "i2c_clk",
-	.rate = 100000000,
+	.flags = LPSS_CLK,
 };
 
 static struct lpss_device_desc byt_i2c_dev_desc = {
-	.clk_required = true,
+	.flags = LPSS_CLK | LPSS_SAVE_CTX,
 	.prv_offset = 0x800,
-	.save_ctx = true,
-	.shared_clock = &i2c_clock,
-	.setup = lpss_i2c_setup,
-};
-
-static struct lpss_shared_clock bsw_pwm_clock = {
-	.name = "pwm_clk",
-	.rate = 19200000,
-};
-
-static struct lpss_device_desc bsw_pwm_dev_desc = {
-	.clk_required = true,
-	.save_ctx = true,
-	.shared_clock = &bsw_pwm_clock,
+	.setup = byt_i2c_setup,
 };
 
 #else
@@ -237,7 +196,7 @@ static const struct acpi_device_id acpi_lpss_device_ids[] = {
 	{ "INT33FC", },
 
 	/* Braswell LPSS devices */
-	{ "80862288", LPSS_ADDR(bsw_pwm_dev_desc) },
+	{ "80862288", LPSS_ADDR(byt_pwm_dev_desc) },
 	{ "8086228A", LPSS_ADDR(byt_uart_dev_desc) },
 	{ "8086228E", LPSS_ADDR(byt_spi_dev_desc) },
 	{ "808622C1", LPSS_ADDR(byt_i2c_dev_desc) },
@@ -251,7 +210,8 @@ static const struct acpi_device_id acpi_lpss_device_ids[] = {
 	{ "INT3436", LPSS_ADDR(lpt_sdio_dev_desc) },
 	{ "INT3437", },
 
-	{ "INT3438", LPSS_ADDR(wpt_dev_desc) },
+	/* Wildcat Point LPSS devices */
+	{ "INT3438", LPSS_ADDR(lpt_dev_desc) },
 
 	{ }
 };
@@ -276,7 +236,6 @@ static int register_device_clock(struct acpi_device *adev,
 				 struct lpss_private_data *pdata)
 {
 	const struct lpss_device_desc *dev_desc = pdata->dev_desc;
-	struct lpss_shared_clock *shared_clock = dev_desc->shared_clock;
 	const char *devname = dev_name(&adev->dev);
 	struct clk *clk = ERR_PTR(-ENODEV);
 	struct lpss_clk_data *clk_data;
@@ -289,12 +248,7 @@ static int register_device_clock(struct acpi_device *adev,
 	clk_data = platform_get_drvdata(lpss_clk_dev);
 	if (!clk_data)
 		return -ENODEV;
-
-	if (dev_desc->clkdev_name) {
-		clk_register_clkdev(clk_data->clk, dev_desc->clkdev_name,
-				    devname);
-		return 0;
-	}
+	clk = clk_data->clk;
 
 	if (!pdata->mmio_base
 	    || pdata->mmio_size < dev_desc->prv_offset + LPSS_CLK_SIZE)
@@ -303,24 +257,19 @@ static int register_device_clock(struct acpi_device *adev,
 	parent = clk_data->name;
 	prv_base = pdata->mmio_base + dev_desc->prv_offset;
 
-	if (shared_clock) {
-		clk = shared_clock->clk;
-		if (!clk) {
-			clk = clk_register_fixed_rate(NULL, shared_clock->name,
-						      "lpss_clk", 0,
-						      shared_clock->rate);
-			shared_clock->clk = clk;
-		}
-		parent = shared_clock->name;
+	if (pdata->fixed_clk_rate) {
+		clk = clk_register_fixed_rate(NULL, devname, parent, 0,
+					      pdata->fixed_clk_rate);
+		goto out;
 	}
 
-	if (dev_desc->clk_gate) {
+	if (dev_desc->flags & LPSS_CLK_GATE) {
 		clk = clk_register_gate(NULL, devname, parent, 0,
 					prv_base, 0, 0, NULL);
 		parent = devname;
 	}
 
-	if (dev_desc->clk_divider) {
+	if (dev_desc->flags & LPSS_CLK_DIVIDER) {
 		/* Prevent division by zero */
 		if (!readl(prv_base))
 			writel(LPSS_CLK_DIVIDER_DEF_MASK, prv_base);
@@ -344,7 +293,7 @@ static int register_device_clock(struct acpi_device *adev,
 		kfree(parent);
 		kfree(clk_name);
 	}
-
+out:
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
@@ -392,7 +341,10 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 
 	pdata->dev_desc = dev_desc;
 
-	if (dev_desc->clk_required) {
+	if (dev_desc->setup)
+		dev_desc->setup(pdata);
+
+	if (dev_desc->flags & LPSS_CLK) {
 		ret = register_device_clock(adev, pdata);
 		if (ret) {
 			/* Skip the device, but continue the namespace scan. */
@@ -413,9 +365,6 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 		goto err_out;
 	}
 
-	if (dev_desc->setup)
-		dev_desc->setup(pdata);
-
 	adev->driver_data = pdata;
 	pdev = acpi_create_platform_device(adev);
 	if (!IS_ERR_OR_NULL(pdev)) {
@@ -692,19 +641,19 @@ static int acpi_lpss_platform_notify(struct notifier_block *nb,
 
 	switch (action) {
 	case BUS_NOTIFY_BOUND_DRIVER:
-		if (pdata->dev_desc->save_ctx)
+		if (pdata->dev_desc->flags & LPSS_SAVE_CTX)
 			pdev->dev.pm_domain = &acpi_lpss_pm_domain;
 		break;
 	case BUS_NOTIFY_UNBOUND_DRIVER:
-		if (pdata->dev_desc->save_ctx)
+		if (pdata->dev_desc->flags & LPSS_SAVE_CTX)
 			pdev->dev.pm_domain = NULL;
 		break;
 	case BUS_NOTIFY_ADD_DEVICE:
-		if (pdata->dev_desc->ltr_required)
+		if (pdata->dev_desc->flags & LPSS_LTR)
 			return sysfs_create_group(&pdev->dev.kobj,
 						  &lpss_attr_group);
 	case BUS_NOTIFY_DEL_DEVICE:
-		if (pdata->dev_desc->ltr_required)
+		if (pdata->dev_desc->flags & LPSS_LTR)
 			sysfs_remove_group(&pdev->dev.kobj, &lpss_attr_group);
 	default:
 		break;
@@ -721,7 +670,7 @@ static void acpi_lpss_bind(struct device *dev)
 {
 	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
 
-	if (!pdata || !pdata->mmio_base || !pdata->dev_desc->ltr_required)
+	if (!pdata || !pdata->mmio_base || !(pdata->dev_desc->flags & LPSS_LTR))
 		return;
 
 	if (pdata->mmio_size >= pdata->dev_desc->prv_offset + LPSS_LTR_SIZE)
diff --git a/drivers/acpi/acpi_pnp.c b/drivers/acpi/acpi_pnp.c
index 1f8b20496f32..b193f8425999 100644
--- a/drivers/acpi/acpi_pnp.c
+++ b/drivers/acpi/acpi_pnp.c
@@ -130,10 +130,6 @@ static const struct acpi_device_id acpi_pnp_device_ids[] = {
 	{"PNP0401"},		/* ECP Printer Port */
 	/* apple-gmux */
 	{"APP000B"},
-	/* fujitsu-laptop.c */
-	{"FUJ02bf"},
-	{"FUJ02B1"},
-	{"FUJ02E3"},
 	/* system */
 	{"PNP0c02"},		/* General ID for reserving resources */
 	{"PNP0c01"},		/* memory controller */
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index 0cf159cc6e6d..56710a03c9b0 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -596,6 +596,38 @@ acpi_status acpi_enable_all_runtime_gpes(void)
 
 ACPI_EXPORT_SYMBOL(acpi_enable_all_runtime_gpes)
 
+/******************************************************************************
+ *
+ * FUNCTION:    acpi_enable_all_wakeup_gpes
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Enable all "wakeup" GPEs and disable all of the other GPEs, in
+ *              all GPE blocks.
+ *
+ ******************************************************************************/
+
+acpi_status acpi_enable_all_wakeup_gpes(void)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_enable_all_wakeup_gpes);
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_EVENTS);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	status = acpi_hw_enable_all_wakeup_gpes();
+	(void)acpi_ut_release_mutex(ACPI_MTX_EVENTS);
+
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_enable_all_wakeup_gpes)
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_install_gpe_block
diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c
index 2e6caabba07a..ea62d40fd161 100644
--- a/drivers/acpi/acpica/hwgpe.c
+++ b/drivers/acpi/acpica/hwgpe.c
@@ -396,11 +396,11 @@ acpi_hw_enable_wakeup_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 	/* Examine each GPE Register within the block */
 
 	for (i = 0; i < gpe_block->register_count; i++) {
-		if (!gpe_block->register_info[i].enable_for_wake) {
-			continue;
-		}
 
-		/* Enable all "wake" GPEs in this register */
+		/*
+		 * Enable all "wake" GPEs in this register and disable the
+		 * remaining ones.
+		 */
 
 		status =
 		    acpi_hw_write(gpe_block->register_info[i].enable_for_wake,
diff --git a/drivers/acpi/acpica/utresrc.c b/drivers/acpi/acpica/utresrc.c
index 14cb6c0c8be2..5cd017c7ac0e 100644
--- a/drivers/acpi/acpica/utresrc.c
+++ b/drivers/acpi/acpica/utresrc.c
@@ -87,7 +87,9 @@ const char *acpi_gbl_io_decode[] = {
 
 const char *acpi_gbl_ll_decode[] = {
 	"ActiveHigh",
-	"ActiveLow"
+	"ActiveLow",
+	"ActiveBoth",
+	"Reserved"
 };
 
 const char *acpi_gbl_max_decode[] = {
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 5fdfe65fe165..8ec8a89a20ab 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -695,7 +695,7 @@ static void acpi_battery_quirks(struct acpi_battery *battery)
 	if (battery->power_unit && dmi_name_in_vendors("LENOVO")) {
 		const char *s;
 		s = dmi_get_system_info(DMI_PRODUCT_VERSION);
-		if (s && !strnicmp(s, "ThinkPad", 8)) {
+		if (s && !strncasecmp(s, "ThinkPad", 8)) {
 			dmi_walk(find_battery, battery);
 			if (test_bit(ACPI_BATTERY_QUIRK_THINKPAD_MAH,
 				     &battery->flags) &&
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index 36eb42e3b0bb..ed122e17636e 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -247,8 +247,8 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 	},
 
 	/*
-	 * These machines will power on immediately after shutdown when
-	 * reporting the Windows 2012 OSI.
+	 * The wireless hotkey does not work on those machines when
+	 * returning true for _OSI("Windows 2012")
 	 */
 	{
 	.callback = dmi_disable_osi_win8,
@@ -258,6 +258,38 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 		    DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7737"),
 		},
 	},
+	{
+	.callback = dmi_disable_osi_win8,
+	.ident = "Dell Inspiron 7537",
+	.matches = {
+		    DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		    DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7537"),
+		},
+	},
+	{
+	.callback = dmi_disable_osi_win8,
+	.ident = "Dell Inspiron 5437",
+	.matches = {
+		    DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		    DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5437"),
+		},
+	},
+	{
+	.callback = dmi_disable_osi_win8,
+	.ident = "Dell Inspiron 3437",
+	.matches = {
+		    DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		    DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 3437"),
+		},
+	},
+	{
+	.callback = dmi_disable_osi_win8,
+	.ident = "Dell Vostro 3446",
+	.matches = {
+		    DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		    DMI_MATCH(DMI_PRODUCT_NAME, "Vostro 3446"),
+		},
+	},
 
 	/*
 	 * BIOS invocation of _OSI(Linux) is almost always a BIOS bug.
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 67075f800e34..bea6896be122 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -1041,6 +1041,40 @@ static struct dev_pm_domain acpi_general_pm_domain = {
 };
 
 /**
+ * acpi_dev_pm_detach - Remove ACPI power management from the device.
+ * @dev: Device to take care of.
+ * @power_off: Whether or not to try to remove power from the device.
+ *
+ * Remove the device from the general ACPI PM domain and remove its wakeup
+ * notifier.  If @power_off is set, additionally remove power from the device if
+ * possible.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ */
+static void acpi_dev_pm_detach(struct device *dev, bool power_off)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+
+	if (adev && dev->pm_domain == &acpi_general_pm_domain) {
+		dev->pm_domain = NULL;
+		acpi_remove_pm_notifier(adev);
+		if (power_off) {
+			/*
+			 * If the device's PM QoS resume latency limit or flags
+			 * have been exposed to user space, they have to be
+			 * hidden at this point, so that they don't affect the
+			 * choice of the low-power state to put the device into.
+			 */
+			dev_pm_qos_hide_latency_limit(dev);
+			dev_pm_qos_hide_flags(dev);
+			acpi_device_wakeup(adev, ACPI_STATE_S0, false);
+			acpi_dev_pm_low_power(dev, adev, ACPI_STATE_S0);
+		}
+	}
+}
+
+/**
  * acpi_dev_pm_attach - Prepare device for ACPI power management.
  * @dev: Device to prepare.
  * @power_on: Whether or not to power on the device.
@@ -1072,42 +1106,9 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 		acpi_dev_pm_full_power(adev);
 		acpi_device_wakeup(adev, ACPI_STATE_S0, false);
 	}
+
+	dev->pm_domain->detach = acpi_dev_pm_detach;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
-
-/**
- * acpi_dev_pm_detach - Remove ACPI power management from the device.
- * @dev: Device to take care of.
- * @power_off: Whether or not to try to remove power from the device.
- *
- * Remove the device from the general ACPI PM domain and remove its wakeup
- * notifier.  If @power_off is set, additionally remove power from the device if
- * possible.
- *
- * Callers must ensure proper synchronization of this function with power
- * management callbacks.
- */
-void acpi_dev_pm_detach(struct device *dev, bool power_off)
-{
-	struct acpi_device *adev = ACPI_COMPANION(dev);
-
-	if (adev && dev->pm_domain == &acpi_general_pm_domain) {
-		dev->pm_domain = NULL;
-		acpi_remove_pm_notifier(adev);
-		if (power_off) {
-			/*
-			 * If the device's PM QoS resume latency limit or flags
-			 * have been exposed to user space, they have to be
-			 * hidden at this point, so that they don't affect the
-			 * choice of the low-power state to put the device into.
-			 */
-			dev_pm_qos_hide_latency_limit(dev);
-			dev_pm_qos_hide_flags(dev);
-			acpi_device_wakeup(adev, ACPI_STATE_S0, false);
-			acpi_dev_pm_low_power(dev, adev, ACPI_STATE_S0);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(acpi_dev_pm_detach);
 #endif /* CONFIG_PM */
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 8acf53e62966..5328b1090e08 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -27,12 +27,10 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/types.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/thermal.h>
 #include <linux/acpi.h>
 
-#define PREFIX "ACPI: "
-
 #define ACPI_FAN_CLASS			"fan"
 #define ACPI_FAN_FILE_STATE		"state"
 
@@ -127,8 +125,9 @@ static const struct thermal_cooling_device_ops fan_cooling_ops = {
 };
 
 /* --------------------------------------------------------------------------
-                                 Driver Interface
-   -------------------------------------------------------------------------- */
+ *                               Driver Interface
+ * --------------------------------------------------------------------------
+*/
 
 static int acpi_fan_add(struct acpi_device *device)
 {
@@ -143,7 +142,7 @@ static int acpi_fan_add(struct acpi_device *device)
 
 	result = acpi_bus_update_power(device->handle, NULL);
 	if (result) {
-		printk(KERN_ERR PREFIX "Setting initial power state\n");
+		dev_err(&device->dev, "Setting initial power state\n");
 		goto end;
 	}
 
@@ -168,10 +167,9 @@ static int acpi_fan_add(struct acpi_device *device)
 				   &device->dev.kobj,
 				   "device");
 	if (result)
-		dev_err(&device->dev, "Failed to create sysfs link "
-			"'device'\n");
+		dev_err(&device->dev, "Failed to create sysfs link 'device'\n");
 
-	printk(KERN_INFO PREFIX "%s [%s] (%s)\n",
+	dev_info(&device->dev, "ACPI: %s [%s] (%s)\n",
 	       acpi_device_name(device), acpi_device_bid(device),
 	       !device->power.state ? "on" : "off");
 
@@ -217,7 +215,7 @@ static int acpi_fan_resume(struct device *dev)
 
 	result = acpi_bus_update_power(to_acpi_device(dev)->handle, NULL);
 	if (result)
-		printk(KERN_ERR PREFIX "Error updating fan power state\n");
+		dev_err(dev, "Error updating fan power state\n");
 
 	return result;
 }
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 3abe9b223ba7..9964f70be98d 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -152,6 +152,16 @@ static u32 acpi_osi_handler(acpi_string interface, u32 supported)
 			osi_linux.dmi ? " via DMI" : "");
 	}
 
+	if (!strcmp("Darwin", interface)) {
+		/*
+		 * Apple firmware will behave poorly if it receives positive
+		 * answers to "Darwin" and any other OS. Respond positively
+		 * to Darwin and then disable all other vendor strings.
+		 */
+		acpi_update_interfaces(ACPI_DISABLE_ALL_VENDOR_STRINGS);
+		supported = ACPI_UINT32_MAX;
+	}
+
 	return supported;
 }
 
@@ -825,7 +835,7 @@ acpi_os_install_interrupt_handler(u32 gsi, acpi_osd_handler handler,
 
 	acpi_irq_handler = handler;
 	acpi_irq_context = context;
-	if (request_irq(irq, acpi_irq, IRQF_SHARED | IRQF_NO_SUSPEND, "acpi", acpi_irq)) {
+	if (request_irq(irq, acpi_irq, IRQF_SHARED, "acpi", acpi_irq)) {
 		printk(KERN_ERR PREFIX "SCI (IRQ%d) allocation failed\n", irq);
 		acpi_irq_handler = NULL;
 		return AE_NOT_ACQUIRED;
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index e6ae603ed1a1..cd4de7e038ea 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -35,6 +35,7 @@
 #include <linux/pci-aspm.h>
 #include <linux/acpi.h>
 #include <linux/slab.h>
+#include <linux/dmi.h>
 #include <acpi/apei.h>	/* for acpi_hest_init() */
 
 #include "internal.h"
@@ -430,6 +431,19 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm,
 	acpi_handle handle = device->handle;
 
 	/*
+	 * Apple always return failure on _OSC calls when _OSI("Darwin") has
+	 * been called successfully. We know the feature set supported by the
+	 * platform, so avoid calling _OSC at all
+	 */
+
+	if (dmi_match(DMI_SYS_VENDOR, "Apple Inc.")) {
+		root->osc_control_set = ~OSC_PCI_EXPRESS_PME_CONTROL;
+		decode_osc_control(root, "OS assumes control of",
+				   root->osc_control_set);
+		return;
+	}
+
+	/*
 	 * All supported architectures that use ACPI have support for
 	 * PCI domains, so we indicate this in _OSC support capabilities.
 	 */
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index e32321ce9a5c..ef58f46c8442 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -16,7 +16,7 @@ static int map_lapic_id(struct acpi_subtable_header *entry,
 		 u32 acpi_id, int *apic_id)
 {
 	struct acpi_madt_local_apic *lapic =
-		(struct acpi_madt_local_apic *)entry;
+		container_of(entry, struct acpi_madt_local_apic, header);
 
 	if (!(lapic->lapic_flags & ACPI_MADT_ENABLED))
 		return -ENODEV;
@@ -32,7 +32,7 @@ static int map_x2apic_id(struct acpi_subtable_header *entry,
 			 int device_declaration, u32 acpi_id, int *apic_id)
 {
 	struct acpi_madt_local_x2apic *apic =
-		(struct acpi_madt_local_x2apic *)entry;
+		container_of(entry, struct acpi_madt_local_x2apic, header);
 
 	if (!(apic->lapic_flags & ACPI_MADT_ENABLED))
 		return -ENODEV;
@@ -49,7 +49,7 @@ static int map_lsapic_id(struct acpi_subtable_header *entry,
 		int device_declaration, u32 acpi_id, int *apic_id)
 {
 	struct acpi_madt_local_sapic *lsapic =
-		(struct acpi_madt_local_sapic *)entry;
+		container_of(entry, struct acpi_madt_local_sapic, header);
 
 	if (!(lsapic->lapic_flags & ACPI_MADT_ENABLED))
 		return -ENODEV;
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index 366ca40a6f70..a7a3edd28beb 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -35,6 +35,7 @@
 #include <linux/jiffies.h>
 #include <linux/delay.h>
 #include <linux/power_supply.h>
+#include <linux/dmi.h>
 
 #include "sbshc.h"
 #include "battery.h"
@@ -61,6 +62,8 @@ static unsigned int cache_time = 1000;
 module_param(cache_time, uint, 0644);
 MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
 
+static bool sbs_manager_broken;
+
 #define MAX_SBS_BAT			4
 #define ACPI_SBS_BLOCK_MAX		32
 
@@ -109,6 +112,7 @@ struct acpi_sbs {
 	u8 batteries_supported:4;
 	u8 manager_present:1;
 	u8 charger_present:1;
+	u8 charger_exists:1;
 };
 
 #define to_acpi_sbs(x) container_of(x, struct acpi_sbs, charger)
@@ -429,9 +433,19 @@ static int acpi_ac_get_present(struct acpi_sbs *sbs)
 
 	result = acpi_smbus_read(sbs->hc, SMBUS_READ_WORD, ACPI_SBS_CHARGER,
 				 0x13, (u8 *) & status);
-	if (!result)
-		sbs->charger_present = (status >> 15) & 0x1;
-	return result;
+
+	if (result)
+		return result;
+
+	/*
+	 * The spec requires that bit 4 always be 1. If it's not set, assume
+	 * that the implementation doesn't support an SBS charger
+	 */
+	if (!((status >> 4) & 0x1))
+		return -ENODEV;
+
+	sbs->charger_present = (status >> 15) & 0x1;
+	return 0;
 }
 
 static ssize_t acpi_battery_alarm_show(struct device *dev,
@@ -483,16 +497,21 @@ static int acpi_battery_read(struct acpi_battery *battery)
 				  ACPI_SBS_MANAGER, 0x01, (u8 *)&state, 2);
 	} else if (battery->id == 0)
 		battery->present = 1;
+
 	if (result || !battery->present)
 		return result;
 
 	if (saved_present != battery->present) {
 		battery->update_time = 0;
 		result = acpi_battery_get_info(battery);
-		if (result)
+		if (result) {
+			battery->present = 0;
 			return result;
+		}
 	}
 	result = acpi_battery_get_state(battery);
+	if (result)
+		battery->present = 0;
 	return result;
 }
 
@@ -524,6 +543,7 @@ static int acpi_battery_add(struct acpi_sbs *sbs, int id)
 	result = power_supply_register(&sbs->device->dev, &battery->bat);
 	if (result)
 		goto end;
+
 	result = device_create_file(battery->bat.dev, &alarm_attr);
 	if (result)
 		goto end;
@@ -554,6 +574,7 @@ static int acpi_charger_add(struct acpi_sbs *sbs)
 	if (result)
 		goto end;
 
+	sbs->charger_exists = 1;
 	sbs->charger.name = "sbs-charger";
 	sbs->charger.type = POWER_SUPPLY_TYPE_MAINS;
 	sbs->charger.properties = sbs_ac_props;
@@ -580,9 +601,12 @@ static void acpi_sbs_callback(void *context)
 	struct acpi_battery *bat;
 	u8 saved_charger_state = sbs->charger_present;
 	u8 saved_battery_state;
-	acpi_ac_get_present(sbs);
-	if (sbs->charger_present != saved_charger_state)
-		kobject_uevent(&sbs->charger.dev->kobj, KOBJ_CHANGE);
+
+	if (sbs->charger_exists) {
+		acpi_ac_get_present(sbs);
+		if (sbs->charger_present != saved_charger_state)
+			kobject_uevent(&sbs->charger.dev->kobj, KOBJ_CHANGE);
+	}
 
 	if (sbs->manager_present) {
 		for (id = 0; id < MAX_SBS_BAT; ++id) {
@@ -598,12 +622,31 @@ static void acpi_sbs_callback(void *context)
 	}
 }
 
+static int disable_sbs_manager(const struct dmi_system_id *d)
+{
+	sbs_manager_broken = true;
+	return 0;
+}
+
+static struct dmi_system_id acpi_sbs_dmi_table[] = {
+	{
+		.callback = disable_sbs_manager,
+		.ident = "Apple",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc.")
+		},
+	},
+	{ },
+};
+
 static int acpi_sbs_add(struct acpi_device *device)
 {
 	struct acpi_sbs *sbs;
 	int result = 0;
 	int id;
 
+	dmi_check_system(acpi_sbs_dmi_table);
+
 	sbs = kzalloc(sizeof(struct acpi_sbs), GFP_KERNEL);
 	if (!sbs) {
 		result = -ENOMEM;
@@ -619,17 +662,24 @@ static int acpi_sbs_add(struct acpi_device *device)
 	device->driver_data = sbs;
 
 	result = acpi_charger_add(sbs);
-	if (result)
+	if (result && result != -ENODEV)
 		goto end;
 
-	result = acpi_manager_get_info(sbs);
-	if (!result) {
-		sbs->manager_present = 1;
-		for (id = 0; id < MAX_SBS_BAT; ++id)
-			if ((sbs->batteries_supported & (1 << id)))
-				acpi_battery_add(sbs, id);
-	} else
+	result = 0;
+
+	if (!sbs_manager_broken) {
+		result = acpi_manager_get_info(sbs);
+		if (!result) {
+			sbs->manager_present = 0;
+			for (id = 0; id < MAX_SBS_BAT; ++id)
+				if ((sbs->batteries_supported & (1 << id)))
+					acpi_battery_add(sbs, id);
+		}
+	}
+
+	if (!sbs->manager_present)
 		acpi_battery_add(sbs, 0);
+
 	acpi_smbus_register_callback(sbs->hc, acpi_sbs_callback, sbs);
       end:
 	if (result)
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 54da4a3fe65e..05a31b573fc3 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -14,6 +14,7 @@
 #include <linux/irq.h>
 #include <linux/dmi.h>
 #include <linux/device.h>
+#include <linux/interrupt.h>
 #include <linux/suspend.h>
 #include <linux/reboot.h>
 #include <linux/acpi.h>
@@ -626,6 +627,19 @@ static int acpi_freeze_begin(void)
 	return 0;
 }
 
+static int acpi_freeze_prepare(void)
+{
+	acpi_enable_all_wakeup_gpes();
+	enable_irq_wake(acpi_gbl_FADT.sci_interrupt);
+	return 0;
+}
+
+static void acpi_freeze_restore(void)
+{
+	disable_irq_wake(acpi_gbl_FADT.sci_interrupt);
+	acpi_enable_all_runtime_gpes();
+}
+
 static void acpi_freeze_end(void)
 {
 	acpi_scan_lock_release();
@@ -633,6 +647,8 @@ static void acpi_freeze_end(void)
 
 static const struct platform_freeze_ops acpi_freeze_ops = {
 	.begin = acpi_freeze_begin,
+	.prepare = acpi_freeze_prepare,
+	.restore = acpi_freeze_restore,
 	.end = acpi_freeze_end,
 };
 
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 07c8c5a5ee95..834f35c4bf8d 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -661,7 +661,6 @@ EXPORT_SYMBOL(acpi_evaluate_dsm);
  * @uuid: UUID of requested functions, should be 16 bytes at least
  * @rev: revision number of requested functions
  * @funcs: bitmap of requested functions
- * @exclude: excluding special value, used to support i915 and nouveau
  *
  * Evaluate device's _DSM method to check whether it supports requested
  * functions. Currently only support 64 functions at maximum, should be
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index 8e7e18567ae6..807a88a0f394 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -411,12 +411,6 @@ static int __init video_set_bqc_offset(const struct dmi_system_id *d)
 	return 0;
 }
 
-static int __init video_set_use_native_backlight(const struct dmi_system_id *d)
-{
-	use_native_backlight_dmi = true;
-	return 0;
-}
-
 static int __init video_disable_native_backlight(const struct dmi_system_id *d)
 {
 	use_native_backlight_dmi = false;
@@ -467,265 +461,6 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7720"),
 		},
 	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "ThinkPad X230",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X230"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "ThinkPad T430 and T430s",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "ThinkPad T430",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "2349D15"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "ThinkPad T431s",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "20AACTO1WW"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "ThinkPad Edge E530",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "3259A2G"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "ThinkPad Edge E530",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "3259CTO"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "ThinkPad Edge E530",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "3259HJG"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "ThinkPad W530",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W530"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	.ident = "ThinkPad X1 Carbon",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X1 Carbon"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "Lenovo Yoga 13",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo IdeaPad Yoga 13"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "Lenovo Yoga 2 11",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Yoga 2 11"),
-		},
-	},
-	{
-	.callback = video_set_use_native_backlight,
-	.ident = "Thinkpad Helix",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "Dell Inspiron 7520",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7520"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "Acer Aspire 5733Z",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5733Z"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "Acer Aspire 5742G",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5742G"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "Acer Aspire V5-171",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "V5-171"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "Acer Aspire V5-431",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire V5-431"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "Acer Aspire V5-471G",
-	 .matches = {
-		DMI_MATCH(DMI_BOARD_VENDOR, "Acer"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire V5-471G"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "Acer TravelMate B113",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate B113"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "Acer Aspire V5-572G",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Acer Aspire"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "V5-572G/Dazzle_CX"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "Acer Aspire V5-573G",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Acer Aspire"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "V5-573G/Dazzle_HW"),
-		},
-	},
-	{
-	 .callback = video_set_use_native_backlight,
-	 .ident = "ASUS Zenbook Prime UX31A",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "UX31A"),
-		},
-	},
-	{
-	.callback = video_set_use_native_backlight,
-	.ident = "HP ProBook 4340s",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "HP ProBook 4340s"),
-		},
-	},
-	{
-	.callback = video_set_use_native_backlight,
-	.ident = "HP ProBook 4540s",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "HP ProBook 4540s"),
-		},
-	},
-	{
-	.callback = video_set_use_native_backlight,
-	.ident = "HP ProBook 2013 models",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook "),
-		DMI_MATCH(DMI_PRODUCT_NAME, " G1"),
-		},
-	},
-	{
-	.callback = video_set_use_native_backlight,
-	.ident = "HP EliteBook 2013 models",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook "),
-		DMI_MATCH(DMI_PRODUCT_NAME, " G1"),
-		},
-	},
-	{
-	.callback = video_set_use_native_backlight,
-	.ident = "HP EliteBook 2014 models",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook "),
-		DMI_MATCH(DMI_PRODUCT_NAME, " G2"),
-		},
-	},
-	{
-	.callback = video_set_use_native_backlight,
-	.ident = "HP ZBook 14",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 14"),
-		},
-	},
-	{
-	.callback = video_set_use_native_backlight,
-	.ident = "HP ZBook 15",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 15"),
-		},
-	},
-	{
-	.callback = video_set_use_native_backlight,
-	.ident = "HP ZBook 17",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 17"),
-		},
-	},
-	{
-	.callback = video_set_use_native_backlight,
-	.ident = "HP EliteBook 8470p",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8470p"),
-		},
-	},
-	{
-	.callback = video_set_use_native_backlight,
-	.ident = "HP EliteBook 8780w",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8780w"),
-		},
-	},
 
 	/*
 	 * These models have a working acpi_video backlight control, and using
@@ -1419,6 +1154,23 @@ acpi_video_device_bind(struct acpi_video_bus *video,
 	}
 }
 
+static bool acpi_video_device_in_dod(struct acpi_video_device *device)
+{
+	struct acpi_video_bus *video = device->video;
+	int i;
+
+	/* If we have a broken _DOD, no need to test */
+	if (!video->attached_count)
+		return true;
+
+	for (i = 0; i < video->attached_count; i++) {
+		if (video->attached_array[i].bind_info == device)
+			return true;
+	}
+
+	return false;
+}
+
 /*
  *  Arg:
  *	video	: video bus device
@@ -1858,6 +1610,15 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device)
 	static int count;
 	char *name;
 
+	/*
+	 * Do not create backlight device for video output
+	 * device that is not in the enumerated list.
+	 */
+	if (!acpi_video_device_in_dod(device)) {
+		dev_dbg(&device->dev->dev, "not in _DOD list, ignore\n");
+		return;
+	}
+
 	result = acpi_video_init_brightness(device);
 	if (result)
 		return;
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index c42feb2bacd0..27c43499977a 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -174,6 +174,14 @@ static struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5737"),
 		},
 	},
+	{
+	.callback = video_detect_force_vendor,
+	.ident = "Lenovo IdeaPad Z570",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "Ideapad Z570"),
+		},
+	},
 	{ },
 };
 
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 3cf61a127ee5..47bbdc1b5be3 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -15,6 +15,7 @@
 #include <linux/io.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/amba/bus.h>
 #include <linux/sizes.h>
 
@@ -182,9 +183,15 @@ static int amba_probe(struct device *dev)
 	int ret;
 
 	do {
+		ret = dev_pm_domain_attach(dev, true);
+		if (ret == -EPROBE_DEFER)
+			break;
+
 		ret = amba_get_enable_pclk(pcdev);
-		if (ret)
+		if (ret) {
+			dev_pm_domain_detach(dev, true);
 			break;
+		}
 
 		pm_runtime_get_noresume(dev);
 		pm_runtime_set_active(dev);
@@ -199,6 +206,7 @@ static int amba_probe(struct device *dev)
 		pm_runtime_put_noidle(dev);
 
 		amba_put_disable_pclk(pcdev);
+		dev_pm_domain_detach(dev, true);
 	} while (0);
 
 	return ret;
@@ -220,6 +228,7 @@ static int amba_remove(struct device *dev)
 	pm_runtime_put_noidle(dev);
 
 	amba_put_disable_pclk(pcdev);
+	dev_pm_domain_detach(dev, true);
 
 	return ret;
 }
diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c
index 25d0ac32e721..c962886d7e71 100644
--- a/drivers/ata/acard-ahci.c
+++ b/drivers/ata/acard-ahci.c
@@ -498,8 +498,7 @@ static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id
 	acard_ahci_pci_print_info(host);
 
 	pci_set_master(pdev);
-	return ata_host_activate(host, pdev->irq, ahci_interrupt, IRQF_SHARED,
-				 &acard_ahci_sht);
+	return ahci_host_activate(host, pdev->irq, &acard_ahci_sht);
 }
 
 module_pci_driver(acard_ahci_pci_driver);
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index a0cc0edafc78..5f039f191067 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -790,7 +790,7 @@ static void ahci_pci_print_info(struct ata_host *host)
  */
 static void ahci_p5wdh_workaround(struct ata_host *host)
 {
-	static struct dmi_system_id sysids[] = {
+	static const struct dmi_system_id sysids[] = {
 		{
 			.ident = "P5W DH Deluxe",
 			.matches = {
@@ -1221,6 +1221,9 @@ static int ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports,
 		goto single_msi;
 	}
 
+	if (nvec > 1)
+		hpriv->flags |= AHCI_HFLAG_MULTI_MSI;
+
 	return nvec;
 
 single_msi:
@@ -1233,71 +1236,6 @@ intx:
 	return 0;
 }
 
-/**
- *	ahci_host_activate - start AHCI host, request IRQs and register it
- *	@host: target ATA host
- *	@irq: base IRQ number to request
- *	@n_msis: number of MSIs allocated for this host
- *	@irq_handler: irq_handler used when requesting IRQs
- *	@irq_flags: irq_flags used when requesting IRQs
- *
- *	Similar to ata_host_activate, but requests IRQs according to AHCI-1.1
- *	when multiple MSIs were allocated. That is one MSI per port, starting
- *	from @irq.
- *
- *	LOCKING:
- *	Inherited from calling layer (may sleep).
- *
- *	RETURNS:
- *	0 on success, -errno otherwise.
- */
-int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis)
-{
-	int i, rc;
-
-	/* Sharing Last Message among several ports is not supported */
-	if (n_msis < host->n_ports)
-		return -EINVAL;
-
-	rc = ata_host_start(host);
-	if (rc)
-		return rc;
-
-	for (i = 0; i < host->n_ports; i++) {
-		struct ahci_port_priv *pp = host->ports[i]->private_data;
-
-		/* Do not receive interrupts sent by dummy ports */
-		if (!pp) {
-			disable_irq(irq + i);
-			continue;
-		}
-
-		rc = devm_request_threaded_irq(host->dev, irq + i,
-					       ahci_hw_interrupt,
-					       ahci_thread_fn, IRQF_SHARED,
-					       pp->irq_desc, host->ports[i]);
-		if (rc)
-			goto out_free_irqs;
-	}
-
-	for (i = 0; i < host->n_ports; i++)
-		ata_port_desc(host->ports[i], "irq %d", irq + i);
-
-	rc = ata_host_register(host, &ahci_sht);
-	if (rc)
-		goto out_free_all_irqs;
-
-	return 0;
-
-out_free_all_irqs:
-	i = host->n_ports;
-out_free_irqs:
-	for (i--; i >= 0; i--)
-		devm_free_irq(host->dev, irq + i, host->ports[i]);
-
-	return rc;
-}
-
 static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	unsigned int board_id = ent->driver_data;
@@ -1306,7 +1244,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct device *dev = &pdev->dev;
 	struct ahci_host_priv *hpriv;
 	struct ata_host *host;
-	int n_ports, n_msis, i, rc;
+	int n_ports, i, rc;
 	int ahci_pci_bar = AHCI_PCI_BAR_STANDARD;
 
 	VPRINTK("ENTER\n");
@@ -1459,9 +1397,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 */
 	n_ports = max(ahci_nr_ports(hpriv->cap), fls(hpriv->port_map));
 
-	n_msis = ahci_init_interrupts(pdev, n_ports, hpriv);
-	if (n_msis > 1)
-		hpriv->flags |= AHCI_HFLAG_MULTI_MSI;
+	ahci_init_interrupts(pdev, n_ports, hpriv);
 
 	host = ata_host_alloc_pinfo(&pdev->dev, ppi, n_ports);
 	if (!host)
@@ -1513,11 +1449,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_master(pdev);
 
-	if (hpriv->flags & AHCI_HFLAG_MULTI_MSI)
-		return ahci_host_activate(host, pdev->irq, n_msis);
-
-	return ata_host_activate(host, pdev->irq, ahci_interrupt, IRQF_SHARED,
-				 &ahci_sht);
+	return ahci_host_activate(host, pdev->irq, &ahci_sht);
 }
 
 module_pci_driver(ahci_pci_driver);
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 59ae0ee00149..40f0e34f17af 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -53,7 +53,7 @@
 
 enum {
 	AHCI_MAX_PORTS		= 32,
-	AHCI_MAX_CLKS		= 4,
+	AHCI_MAX_CLKS		= 5,
 	AHCI_MAX_SG		= 168, /* hardware max is 64K */
 	AHCI_DMA_BOUNDARY	= 0xffffffff,
 	AHCI_MAX_CMDS		= 32,
@@ -304,7 +304,7 @@ struct ahci_port_priv {
 	unsigned int		ncq_saw_d2h:1;
 	unsigned int		ncq_saw_dmas:1;
 	unsigned int		ncq_saw_sdb:1;
-	u32			intr_status;	/* interrupts to handle */
+	atomic_t		intr_status;	/* interrupts to handle */
 	spinlock_t		lock;		/* protects parent ata_port */
 	u32 			intr_mask;	/* interrupts to enable */
 	bool			fbs_supported;	/* set iff FBS is supported */
@@ -388,11 +388,9 @@ int ahci_port_resume(struct ata_port *ap);
 void ahci_set_em_messages(struct ahci_host_priv *hpriv,
 			  struct ata_port_info *pi);
 int ahci_reset_em(struct ata_host *host);
-irqreturn_t ahci_interrupt(int irq, void *dev_instance);
-irqreturn_t ahci_hw_interrupt(int irq, void *dev_instance);
-irqreturn_t ahci_thread_fn(int irq, void *dev_instance);
 void ahci_print_info(struct ata_host *host, const char *scc_s);
-int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis);
+int ahci_host_activate(struct ata_host *host, int irq,
+		       struct scsi_host_template *sht);
 void ahci_error_handler(struct ata_port *ap);
 
 static inline void __iomem *__ahci_port_base(struct ata_host *host,
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index f61ddb9146d6..06f1d59fa678 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -32,7 +32,6 @@ static const struct ata_port_info ahci_port_info = {
 static int ahci_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct ahci_platform_data *pdata = dev_get_platdata(dev);
 	struct ahci_host_priv *hpriv;
 	int rc;
 
@@ -44,29 +43,14 @@ static int ahci_probe(struct platform_device *pdev)
 	if (rc)
 		return rc;
 
-	/*
-	 * Some platforms might need to prepare for mmio region access,
-	 * which could be done in the following init call. So, the mmio
-	 * region shouldn't be accessed before init (if provided) has
-	 * returned successfully.
-	 */
-	if (pdata && pdata->init) {
-		rc = pdata->init(dev, hpriv->mmio);
-		if (rc)
-			goto disable_resources;
-	}
-
 	if (of_device_is_compatible(dev->of_node, "hisilicon,hisi-ahci"))
 		hpriv->flags |= AHCI_HFLAG_NO_FBS | AHCI_HFLAG_NO_NCQ;
 
 	rc = ahci_platform_init_host(pdev, hpriv, &ahci_port_info);
 	if (rc)
-		goto pdata_exit;
+		goto disable_resources;
 
 	return 0;
-pdata_exit:
-	if (pdata && pdata->exit)
-		pdata->exit(dev);
 disable_resources:
 	ahci_platform_disable_resources(hpriv);
 	return rc;
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index f03aab187f4d..0f8538f238b6 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -434,7 +434,7 @@ static int xgene_ahci_mux_select(struct xgene_ahci_context *ctx)
 	u32 val;
 
 	/* Check for optional MUX resource */
-	if (IS_ERR(ctx->csr_mux))
+	if (!ctx->csr_mux)
 		return 0;
 
 	val = readl(ctx->csr_mux + SATA_ENET_CONFIG_REG);
@@ -484,7 +484,13 @@ static int xgene_ahci_probe(struct platform_device *pdev)
 
 	/* Retrieve the optional IP mux resource */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 4);
-	ctx->csr_mux = devm_ioremap_resource(dev, res);
+	if (res) {
+		void __iomem *csr = devm_ioremap_resource(dev, res);
+		if (IS_ERR(csr))
+			return PTR_ERR(csr);
+
+		ctx->csr_mux = csr;
+	}
 
 	dev_dbg(dev, "VAddr 0x%p Mmio VAddr 0x%p\n", ctx->csr_core,
 		hpriv->mmio);
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index b784e9de426a..5eb61c9e63da 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1778,30 +1778,28 @@ static void ahci_handle_port_interrupt(struct ata_port *ap,
 	}
 }
 
-static void ahci_port_intr(struct ata_port *ap)
+static void ahci_update_intr_status(struct ata_port *ap)
 {
 	void __iomem *port_mmio = ahci_port_base(ap);
+	struct ahci_port_priv *pp = ap->private_data;
 	u32 status;
 
 	status = readl(port_mmio + PORT_IRQ_STAT);
 	writel(status, port_mmio + PORT_IRQ_STAT);
 
-	ahci_handle_port_interrupt(ap, port_mmio, status);
+	atomic_or(status, &pp->intr_status);
 }
 
-irqreturn_t ahci_thread_fn(int irq, void *dev_instance)
+static irqreturn_t ahci_port_thread_fn(int irq, void *dev_instance)
 {
 	struct ata_port *ap = dev_instance;
 	struct ahci_port_priv *pp = ap->private_data;
 	void __iomem *port_mmio = ahci_port_base(ap);
-	unsigned long flags;
 	u32 status;
 
-	spin_lock_irqsave(&ap->host->lock, flags);
-	status = pp->intr_status;
-	if (status)
-		pp->intr_status = 0;
-	spin_unlock_irqrestore(&ap->host->lock, flags);
+	status = atomic_xchg(&pp->intr_status, 0);
+	if (!status)
+		return IRQ_NONE;
 
 	spin_lock_bh(ap->lock);
 	ahci_handle_port_interrupt(ap, port_mmio, status);
@@ -1809,47 +1807,13 @@ irqreturn_t ahci_thread_fn(int irq, void *dev_instance)
 
 	return IRQ_HANDLED;
 }
-EXPORT_SYMBOL_GPL(ahci_thread_fn);
-
-static void ahci_hw_port_interrupt(struct ata_port *ap)
-{
-	void __iomem *port_mmio = ahci_port_base(ap);
-	struct ahci_port_priv *pp = ap->private_data;
-	u32 status;
-
-	status = readl(port_mmio + PORT_IRQ_STAT);
-	writel(status, port_mmio + PORT_IRQ_STAT);
 
-	pp->intr_status |= status;
-}
-
-irqreturn_t ahci_hw_interrupt(int irq, void *dev_instance)
+irqreturn_t ahci_thread_fn(int irq, void *dev_instance)
 {
-	struct ata_port *ap_this = dev_instance;
-	struct ahci_port_priv *pp = ap_this->private_data;
-	struct ata_host *host = ap_this->host;
+	struct ata_host *host = dev_instance;
 	struct ahci_host_priv *hpriv = host->private_data;
-	void __iomem *mmio = hpriv->mmio;
+	u32 irq_masked = hpriv->port_map;
 	unsigned int i;
-	u32 irq_stat, irq_masked;
-
-	VPRINTK("ENTER\n");
-
-	spin_lock(&host->lock);
-
-	irq_stat = readl(mmio + HOST_IRQ_STAT);
-
-	if (!irq_stat) {
-		u32 status = pp->intr_status;
-
-		spin_unlock(&host->lock);
-
-		VPRINTK("EXIT\n");
-
-		return status ? IRQ_WAKE_THREAD : IRQ_NONE;
-	}
-
-	irq_masked = irq_stat & hpriv->port_map;
 
 	for (i = 0; i < host->n_ports; i++) {
 		struct ata_port *ap;
@@ -1859,7 +1823,7 @@ irqreturn_t ahci_hw_interrupt(int irq, void *dev_instance)
 
 		ap = host->ports[i];
 		if (ap) {
-			ahci_hw_port_interrupt(ap);
+			ahci_port_thread_fn(irq, ap);
 			VPRINTK("port %u\n", i);
 		} else {
 			VPRINTK("port %u (no irq)\n", i);
@@ -1869,17 +1833,29 @@ irqreturn_t ahci_hw_interrupt(int irq, void *dev_instance)
 		}
 	}
 
-	writel(irq_stat, mmio + HOST_IRQ_STAT);
+	return IRQ_HANDLED;
+}
 
-	spin_unlock(&host->lock);
+static irqreturn_t ahci_multi_irqs_intr(int irq, void *dev_instance)
+{
+	struct ata_port *ap = dev_instance;
+	void __iomem *port_mmio = ahci_port_base(ap);
+	struct ahci_port_priv *pp = ap->private_data;
+	u32 status;
+
+	VPRINTK("ENTER\n");
+
+	status = readl(port_mmio + PORT_IRQ_STAT);
+	writel(status, port_mmio + PORT_IRQ_STAT);
+
+	atomic_or(status, &pp->intr_status);
 
 	VPRINTK("EXIT\n");
 
 	return IRQ_WAKE_THREAD;
 }
-EXPORT_SYMBOL_GPL(ahci_hw_interrupt);
 
-irqreturn_t ahci_interrupt(int irq, void *dev_instance)
+static irqreturn_t ahci_single_irq_intr(int irq, void *dev_instance)
 {
 	struct ata_host *host = dev_instance;
 	struct ahci_host_priv *hpriv;
@@ -1899,8 +1875,6 @@ irqreturn_t ahci_interrupt(int irq, void *dev_instance)
 
 	irq_masked = irq_stat & hpriv->port_map;
 
-	spin_lock(&host->lock);
-
 	for (i = 0; i < host->n_ports; i++) {
 		struct ata_port *ap;
 
@@ -1909,7 +1883,7 @@ irqreturn_t ahci_interrupt(int irq, void *dev_instance)
 
 		ap = host->ports[i];
 		if (ap) {
-			ahci_port_intr(ap);
+			ahci_update_intr_status(ap);
 			VPRINTK("port %u\n", i);
 		} else {
 			VPRINTK("port %u (no irq)\n", i);
@@ -1932,13 +1906,10 @@ irqreturn_t ahci_interrupt(int irq, void *dev_instance)
 	 */
 	writel(irq_stat, mmio + HOST_IRQ_STAT);
 
-	spin_unlock(&host->lock);
-
 	VPRINTK("EXIT\n");
 
-	return IRQ_RETVAL(handled);
+	return handled ? IRQ_WAKE_THREAD : IRQ_NONE;
 }
-EXPORT_SYMBOL_GPL(ahci_interrupt);
 
 unsigned int ahci_qc_issue(struct ata_queued_cmd *qc)
 {
@@ -2349,13 +2320,8 @@ static int ahci_port_start(struct ata_port *ap)
 	 */
 	pp->intr_mask = DEF_PORT_IRQ;
 
-	/*
-	 * Switch to per-port locking in case each port has its own MSI vector.
-	 */
-	if ((hpriv->flags & AHCI_HFLAG_MULTI_MSI)) {
-		spin_lock_init(&pp->lock);
-		ap->lock = &pp->lock;
-	}
+	spin_lock_init(&pp->lock);
+	ap->lock = &pp->lock;
 
 	ap->private_data = pp;
 
@@ -2472,6 +2438,105 @@ void ahci_set_em_messages(struct ahci_host_priv *hpriv,
 }
 EXPORT_SYMBOL_GPL(ahci_set_em_messages);
 
+static int ahci_host_activate_multi_irqs(struct ata_host *host, int irq,
+					 struct scsi_host_template *sht)
+{
+	int i, rc;
+
+	rc = ata_host_start(host);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < host->n_ports; i++) {
+		struct ahci_port_priv *pp = host->ports[i]->private_data;
+
+		/* Do not receive interrupts sent by dummy ports */
+		if (!pp) {
+			disable_irq(irq + i);
+			continue;
+		}
+
+		rc = devm_request_threaded_irq(host->dev, irq + i,
+					       ahci_multi_irqs_intr,
+					       ahci_port_thread_fn, IRQF_SHARED,
+					       pp->irq_desc, host->ports[i]);
+		if (rc)
+			goto out_free_irqs;
+	}
+
+	for (i = 0; i < host->n_ports; i++)
+		ata_port_desc(host->ports[i], "irq %d", irq + i);
+
+	rc = ata_host_register(host, sht);
+	if (rc)
+		goto out_free_all_irqs;
+
+	return 0;
+
+out_free_all_irqs:
+	i = host->n_ports;
+out_free_irqs:
+	for (i--; i >= 0; i--)
+		devm_free_irq(host->dev, irq + i, host->ports[i]);
+
+	return rc;
+}
+
+static int ahci_host_activate_single_irq(struct ata_host *host, int irq,
+					 struct scsi_host_template *sht)
+{
+	int i, rc;
+
+	rc = ata_host_start(host);
+	if (rc)
+		return rc;
+
+	rc = devm_request_threaded_irq(host->dev, irq, ahci_single_irq_intr,
+				       ahci_thread_fn, IRQF_SHARED,
+				       dev_driver_string(host->dev), host);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < host->n_ports; i++)
+		ata_port_desc(host->ports[i], "irq %d", irq);
+
+	rc = ata_host_register(host, sht);
+	if (rc)
+		devm_free_irq(host->dev, irq, host);
+
+	return rc;
+}
+
+/**
+ *	ahci_host_activate - start AHCI host, request IRQs and register it
+ *	@host: target ATA host
+ *	@irq: base IRQ number to request
+ *	@sht: scsi_host_template to use when registering the host
+ *
+ *	Similar to ata_host_activate, but requests IRQs according to AHCI-1.1
+ *	when multiple MSIs were allocated. That is one MSI per port, starting
+ *	from @irq.
+ *
+ *	LOCKING:
+ *	Inherited from calling layer (may sleep).
+ *
+ *	RETURNS:
+ *	0 on success, -errno otherwise.
+ */
+int ahci_host_activate(struct ata_host *host, int irq,
+		       struct scsi_host_template *sht)
+{
+	struct ahci_host_priv *hpriv = host->private_data;
+	int rc;
+
+	if (hpriv->flags & AHCI_HFLAG_MULTI_MSI)
+		rc = ahci_host_activate_multi_irqs(host, irq, sht);
+	else
+		rc = ahci_host_activate_single_irq(host, irq, sht);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ahci_host_activate);
+
 MODULE_AUTHOR("Jeff Garzik");
 MODULE_DESCRIPTION("Common AHCI SATA low-level routines");
 MODULE_LICENSE("GPL");
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index 5b92c290e6c6..0b03f9056692 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -49,7 +49,7 @@ static struct scsi_host_template ahci_platform_sht = {
  * RETURNS:
  * 0 on success otherwise a negative error code
  */
-int ahci_platform_enable_phys(struct ahci_host_priv *hpriv)
+static int ahci_platform_enable_phys(struct ahci_host_priv *hpriv)
 {
 	int rc, i;
 
@@ -77,7 +77,6 @@ disable_phys:
 	}
 	return rc;
 }
-EXPORT_SYMBOL_GPL(ahci_platform_enable_phys);
 
 /**
  * ahci_platform_disable_phys - Disable PHYs
@@ -85,7 +84,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_enable_phys);
  *
  * This function disables all PHYs found in hpriv->phys.
  */
-void ahci_platform_disable_phys(struct ahci_host_priv *hpriv)
+static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv)
 {
 	int i;
 
@@ -97,7 +96,6 @@ void ahci_platform_disable_phys(struct ahci_host_priv *hpriv)
 		phy_exit(hpriv->phys[i]);
 	}
 }
-EXPORT_SYMBOL_GPL(ahci_platform_disable_phys);
 
 /**
  * ahci_platform_enable_clks - Enable platform clocks
@@ -495,20 +493,14 @@ int ahci_platform_init_host(struct platform_device *pdev,
 	ahci_init_controller(host);
 	ahci_print_info(host, "platform");
 
-	return ata_host_activate(host, irq, ahci_interrupt, IRQF_SHARED,
-				 &ahci_platform_sht);
+	return ahci_host_activate(host, irq, &ahci_platform_sht);
 }
 EXPORT_SYMBOL_GPL(ahci_platform_init_host);
 
 static void ahci_host_stop(struct ata_host *host)
 {
-	struct device *dev = host->dev;
-	struct ahci_platform_data *pdata = dev_get_platdata(dev);
 	struct ahci_host_priv *hpriv = host->private_data;
 
-	if (pdata && pdata->exit)
-		pdata->exit(dev);
-
 	ahci_platform_disable_resources(hpriv);
 }
 
@@ -592,7 +584,6 @@ EXPORT_SYMBOL_GPL(ahci_platform_resume_host);
  */
 int ahci_platform_suspend(struct device *dev)
 {
-	struct ahci_platform_data *pdata = dev_get_platdata(dev);
 	struct ata_host *host = dev_get_drvdata(dev);
 	struct ahci_host_priv *hpriv = host->private_data;
 	int rc;
@@ -601,19 +592,9 @@ int ahci_platform_suspend(struct device *dev)
 	if (rc)
 		return rc;
 
-	if (pdata && pdata->suspend) {
-		rc = pdata->suspend(dev);
-		if (rc)
-			goto resume_host;
-	}
-
 	ahci_platform_disable_resources(hpriv);
 
 	return 0;
-
-resume_host:
-	ahci_platform_resume_host(dev);
-	return rc;
 }
 EXPORT_SYMBOL_GPL(ahci_platform_suspend);
 
@@ -629,7 +610,6 @@ EXPORT_SYMBOL_GPL(ahci_platform_suspend);
  */
 int ahci_platform_resume(struct device *dev)
 {
-	struct ahci_platform_data *pdata = dev_get_platdata(dev);
 	struct ata_host *host = dev_get_drvdata(dev);
 	struct ahci_host_priv *hpriv = host->private_data;
 	int rc;
@@ -638,12 +618,6 @@ int ahci_platform_resume(struct device *dev)
 	if (rc)
 		return rc;
 
-	if (pdata && pdata->resume) {
-		rc = pdata->resume(dev);
-		if (rc)
-			goto disable_resources;
-	}
-
 	rc = ahci_platform_resume_host(dev);
 	if (rc)
 		goto disable_resources;
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index f3e7b9f894cd..c5ba15af87d3 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4261,10 +4261,10 @@ static unsigned long ata_dev_blacklisted(const struct ata_device *dev)
 	ata_id_c_string(dev->id, model_rev, ATA_ID_FW_REV, sizeof(model_rev));
 
 	while (ad->model_num) {
-		if (glob_match(model_num, ad->model_num)) {
+		if (glob_match(ad->model_num, model_num)) {
 			if (ad->model_rev == NULL)
 				return ad->horkage;
-			if (glob_match(model_rev, ad->model_rev))
+			if (glob_match(ad->model_rev, model_rev))
 				return ad->horkage;
 		}
 		ad++;
@@ -6227,7 +6227,7 @@ int ata_host_activate(struct ata_host *host, int irq,
 	}
 
 	rc = devm_request_irq(host->dev, irq, irq_handler, irq_flags,
-			      dev_driver_string(host->dev), host);
+			      dev_name(host->dev), host);
 	if (rc)
 		return rc;
 
@@ -6772,32 +6772,28 @@ const struct ata_port_info ata_dummy_port_info = {
 /*
  * Utility print functions
  */
-int ata_port_printk(const struct ata_port *ap, const char *level,
-		    const char *fmt, ...)
+void ata_port_printk(const struct ata_port *ap, const char *level,
+		     const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, fmt);
 
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	r = printk("%sata%u: %pV", level, ap->print_id, &vaf);
+	printk("%sata%u: %pV", level, ap->print_id, &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(ata_port_printk);
 
-int ata_link_printk(const struct ata_link *link, const char *level,
-		    const char *fmt, ...)
+void ata_link_printk(const struct ata_link *link, const char *level,
+		     const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, fmt);
 
@@ -6805,37 +6801,32 @@ int ata_link_printk(const struct ata_link *link, const char *level,
 	vaf.va = &args;
 
 	if (sata_pmp_attached(link->ap) || link->ap->slave_link)
-		r = printk("%sata%u.%02u: %pV",
-			   level, link->ap->print_id, link->pmp, &vaf);
+		printk("%sata%u.%02u: %pV",
+		       level, link->ap->print_id, link->pmp, &vaf);
 	else
-		r = printk("%sata%u: %pV",
-			   level, link->ap->print_id, &vaf);
+		printk("%sata%u: %pV",
+		       level, link->ap->print_id, &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(ata_link_printk);
 
-int ata_dev_printk(const struct ata_device *dev, const char *level,
+void ata_dev_printk(const struct ata_device *dev, const char *level,
 		    const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, fmt);
 
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	r = printk("%sata%u.%02u: %pV",
-		   level, dev->link->ap->print_id, dev->link->pmp + dev->devno,
-		   &vaf);
+	printk("%sata%u.%02u: %pV",
+	       level, dev->link->ap->print_id, dev->link->pmp + dev->devno,
+	       &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(ata_dev_printk);
 
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 1121153f1ecd..db90aa35cb71 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -2008,13 +2008,15 @@ static int ata_bus_softreset(struct ata_port *ap, unsigned int devmask,
 
 	DPRINTK("ata%u: bus reset via SRST\n", ap->print_id);
 
-	/* software reset.  causes dev0 to be selected */
-	iowrite8(ap->ctl, ioaddr->ctl_addr);
-	udelay(20);	/* FIXME: flush */
-	iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr);
-	udelay(20);	/* FIXME: flush */
-	iowrite8(ap->ctl, ioaddr->ctl_addr);
-	ap->last_ctl = ap->ctl;
+	if (ap->ioaddr.ctl_addr) {
+		/* software reset.  causes dev0 to be selected */
+		iowrite8(ap->ctl, ioaddr->ctl_addr);
+		udelay(20);	/* FIXME: flush */
+		iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr);
+		udelay(20);	/* FIXME: flush */
+		iowrite8(ap->ctl, ioaddr->ctl_addr);
+		ap->last_ctl = ap->ctl;
+	}
 
 	/* wait the port to become ready */
 	return ata_sff_wait_after_reset(&ap->link, devmask, deadline);
@@ -2215,10 +2217,6 @@ void ata_sff_error_handler(struct ata_port *ap)
 
 	spin_unlock_irqrestore(ap->lock, flags);
 
-	/* ignore ata_sff_softreset if ctl isn't accessible */
-	if (softreset == ata_sff_softreset && !ap->ioaddr.ctl_addr)
-		softreset = NULL;
-
 	/* ignore built-in hardresets if SCR access is not available */
 	if ((hardreset == sata_std_hardreset ||
 	     hardreset == sata_sff_hardreset) && !sata_scr_valid(&ap->link))
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index 4edb1a81f63f..38216b991474 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -420,7 +420,7 @@ dma_xfer(struct arasan_cf_dev *acdev, dma_addr_t src, dma_addr_t dest, u32 len)
 
 	/* Wait for DMA to complete */
 	if (!wait_for_completion_timeout(&acdev->dma_completion, TIMEOUT)) {
-		chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
+		dmaengine_terminate_all(chan);
 		dev_err(acdev->host->dev, "wait_for_completion_timeout\n");
 		return -ETIMEDOUT;
 	}
@@ -928,8 +928,7 @@ static int arasan_cf_suspend(struct device *dev)
 	struct arasan_cf_dev *acdev = host->ports[0]->private_data;
 
 	if (acdev->dma_chan)
-		acdev->dma_chan->device->device_control(acdev->dma_chan,
-				DMA_TERMINATE_ALL, 0);
+		dmaengine_terminate_all(acdev->dma_chan);
 
 	cf_exit(acdev);
 	return ata_host_suspend(host, PMSG_SUSPEND);
diff --git a/drivers/ata/pata_imx.c b/drivers/ata/pata_imx.c
index af424573c2ff..989ff5ac69ec 100644
--- a/drivers/ata/pata_imx.c
+++ b/drivers/ata/pata_imx.c
@@ -221,13 +221,10 @@ static int pata_imx_resume(struct device *dev)
 
 	return 0;
 }
-
-static const struct dev_pm_ops pata_imx_pm_ops = {
-	.suspend	= pata_imx_suspend,
-	.resume		= pata_imx_resume,
-};
 #endif
 
+static SIMPLE_DEV_PM_OPS(pata_imx_pm_ops, pata_imx_suspend, pata_imx_resume);
+
 static const struct of_device_id imx_pata_dt_ids[] = {
 	{
 		.compatible = "fsl,imx27-pata",
@@ -244,9 +241,7 @@ static struct platform_driver pata_imx_driver = {
 		.name		= DRV_NAME,
 		.of_match_table	= imx_pata_dt_ids,
 		.owner		= THIS_MODULE,
-#ifdef CONFIG_PM_SLEEP
 		.pm		= &pata_imx_pm_ops,
-#endif
 	},
 };
 
diff --git a/drivers/ata/pata_of_platform.c b/drivers/ata/pata_of_platform.c
index a7e95a54c782..64965398914a 100644
--- a/drivers/ata/pata_of_platform.c
+++ b/drivers/ata/pata_of_platform.c
@@ -35,25 +35,14 @@ static int pata_of_platform_probe(struct platform_device *ofdev)
 		return -EINVAL;
 	}
 
-	if (of_device_is_compatible(dn, "electra-ide")) {
-		/* Altstatus is really at offset 0x3f6 from the primary window
-		 * on electra-ide. Adjust ctl_res and io_res accordingly.
-		 */
-		ctl_res = io_res;
-		ctl_res.start = ctl_res.start+0x3f6;
-		io_res.end = ctl_res.start-1;
-	} else {
-		ret = of_address_to_resource(dn, 1, &ctl_res);
-		if (ret) {
-			dev_err(&ofdev->dev, "can't get CTL address from "
-				"device tree\n");
-			return -EINVAL;
-		}
+	ret = of_address_to_resource(dn, 1, &ctl_res);
+	if (ret) {
+		dev_err(&ofdev->dev, "can't get CTL address from "
+			"device tree\n");
+		return -EINVAL;
 	}
 
 	irq_res = platform_get_resource(ofdev, IORESOURCE_IRQ, 0);
-	if (irq_res)
-		irq_res->flags = 0;
 
 	prop = of_get_property(dn, "reg-shift", NULL);
 	if (prop)
@@ -79,8 +68,7 @@ static int pata_of_platform_probe(struct platform_device *ofdev)
 
 static struct of_device_id pata_of_platform_match[] = {
 	{ .compatible = "ata-generic", },
-	{ .compatible = "electra-ide", },
-	{},
+	{ },
 };
 MODULE_DEVICE_TABLE(of, pata_of_platform_match);
 
diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c
index a5579b55e332..f8cff3e247c5 100644
--- a/drivers/ata/pata_platform.c
+++ b/drivers/ata/pata_platform.c
@@ -118,7 +118,7 @@ int __pata_platform_probe(struct device *dev, struct resource *io_res,
 	 */
 	if (irq_res && irq_res->start > 0) {
 		irq = irq_res->start;
-		irq_flags = irq_res->flags;
+		irq_flags = irq_res->flags & IRQF_TRIGGER_MASK;
 	}
 
 	/*
@@ -213,8 +213,6 @@ static int pata_platform_probe(struct platform_device *pdev)
 	 * And the IRQ
 	 */
 	irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (irq_res)
-		irq_res->flags = pp_info ? pp_info->irq_flags : 0;
 
 	return __pata_platform_probe(&pdev->dev, io_res, ctl_res, irq_res,
 				     pp_info ? pp_info->ioport_shift : 0,
diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c
index fc5f31d4828e..57de02123c4c 100644
--- a/drivers/ata/pata_serverworks.c
+++ b/drivers/ata/pata_serverworks.c
@@ -251,12 +251,18 @@ static void serverworks_set_dmamode(struct ata_port *ap, struct ata_device *adev
 	pci_write_config_byte(pdev, 0x54, ultra_cfg);
 }
 
-static struct scsi_host_template serverworks_sht = {
+static struct scsi_host_template serverworks_osb4_sht = {
+	ATA_BMDMA_SHT(DRV_NAME),
+	.sg_tablesize	= LIBATA_DUMB_MAX_PRD,
+};
+
+static struct scsi_host_template serverworks_csb_sht = {
 	ATA_BMDMA_SHT(DRV_NAME),
 };
 
 static struct ata_port_operations serverworks_osb4_port_ops = {
 	.inherits	= &ata_bmdma_port_ops,
+	.qc_prep	= ata_bmdma_dumb_qc_prep,
 	.cable_detect	= serverworks_cable_detect,
 	.mode_filter	= serverworks_osb4_filter,
 	.set_piomode	= serverworks_set_piomode,
@@ -265,6 +271,7 @@ static struct ata_port_operations serverworks_osb4_port_ops = {
 
 static struct ata_port_operations serverworks_csb_port_ops = {
 	.inherits	= &serverworks_osb4_port_ops,
+	.qc_prep	= ata_bmdma_qc_prep,
 	.mode_filter	= serverworks_csb_filter,
 };
 
@@ -404,6 +411,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id
 		}
 	};
 	const struct ata_port_info *ppi[] = { &info[id->driver_data], NULL };
+	struct scsi_host_template *sht = &serverworks_csb_sht;
 	int rc;
 
 	rc = pcim_enable_device(pdev);
@@ -417,6 +425,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id
 		/* Select non UDMA capable OSB4 if we can't do fixups */
 		if (rc < 0)
 			ppi[0] = &info[1];
+		sht = &serverworks_osb4_sht;
 	}
 	/* setup CSB5/CSB6 : South Bridge and IDE option RAID */
 	else if ((pdev->device == PCI_DEVICE_ID_SERVERWORKS_CSB5IDE) ||
@@ -433,7 +442,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id
 			ppi[1] = &ata_dummy_port_info;
 	}
 
-	return ata_pci_bmdma_init_one(pdev, ppi, &serverworks_sht, NULL, 0);
+	return ata_pci_bmdma_init_one(pdev, ppi, sht, NULL, 0);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c
index da3bc2709c63..ce2b99a1ed70 100644
--- a/drivers/ata/sata_highbank.c
+++ b/drivers/ata/sata_highbank.c
@@ -568,8 +568,7 @@ static int ahci_highbank_probe(struct platform_device *pdev)
 	ahci_init_controller(host);
 	ahci_print_info(host, "platform");
 
-	rc = ata_host_activate(host, irq, ahci_interrupt, 0,
-					&ahci_highbank_platform_sht);
+	rc = ahci_host_activate(host, irq, &ahci_highbank_platform_sht);
 	if (rc)
 		goto err0;
 
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 134f763d90fd..61a33f4ba608 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -252,6 +252,9 @@ config DMA_CMA
 	  to allocate big physically-contiguous blocks of memory for use with
 	  hardware components that do not support I/O map nor scatter-gather.
 
+	  You can disable CMA by specifying "cma=0" on the kernel's command
+	  line.
+
 	  For more information see <include/linux/dma-contiguous.h>.
 	  If unsure, say "n".
 
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 28b808c73e8e..14d162952c3b 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1211,6 +1211,9 @@ void device_del(struct device *dev)
 	 */
 	if (platform_notify_remove)
 		platform_notify_remove(dev);
+	if (dev->bus)
+		blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
+					     BUS_NOTIFY_REMOVED_DEVICE, dev);
 	kobject_uevent(&dev->kobj, KOBJ_REMOVE);
 	cleanup_device_parent(dev);
 	kobject_del(&dev->kobj);
diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c
index 7d6e84a51424..55b83983a9c0 100644
--- a/drivers/base/dma-coherent.c
+++ b/drivers/base/dma-coherent.c
@@ -14,11 +14,14 @@ struct dma_coherent_mem {
 	int		size;
 	int		flags;
 	unsigned long	*bitmap;
+	spinlock_t	spinlock;
 };
 
-int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
-				dma_addr_t device_addr, size_t size, int flags)
+static int dma_init_coherent_memory(phys_addr_t phys_addr, dma_addr_t device_addr,
+			     size_t size, int flags,
+			     struct dma_coherent_mem **mem)
 {
+	struct dma_coherent_mem *dma_mem = NULL;
 	void __iomem *mem_base = NULL;
 	int pages = size >> PAGE_SHIFT;
 	int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
@@ -27,40 +30,77 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 		goto out;
 	if (!size)
 		goto out;
-	if (dev->dma_mem)
-		goto out;
-
-	/* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
 
 	mem_base = ioremap(phys_addr, size);
 	if (!mem_base)
 		goto out;
 
-	dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
-	if (!dev->dma_mem)
+	dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+	if (!dma_mem)
 		goto out;
-	dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-	if (!dev->dma_mem->bitmap)
-		goto free1_out;
+	dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!dma_mem->bitmap)
+		goto out;
+
+	dma_mem->virt_base = mem_base;
+	dma_mem->device_base = device_addr;
+	dma_mem->pfn_base = PFN_DOWN(phys_addr);
+	dma_mem->size = pages;
+	dma_mem->flags = flags;
+	spin_lock_init(&dma_mem->spinlock);
 
-	dev->dma_mem->virt_base = mem_base;
-	dev->dma_mem->device_base = device_addr;
-	dev->dma_mem->pfn_base = PFN_DOWN(phys_addr);
-	dev->dma_mem->size = pages;
-	dev->dma_mem->flags = flags;
+	*mem = dma_mem;
 
 	if (flags & DMA_MEMORY_MAP)
 		return DMA_MEMORY_MAP;
 
 	return DMA_MEMORY_IO;
 
- free1_out:
-	kfree(dev->dma_mem);
- out:
+out:
+	kfree(dma_mem);
 	if (mem_base)
 		iounmap(mem_base);
 	return 0;
 }
+
+static void dma_release_coherent_memory(struct dma_coherent_mem *mem)
+{
+	if (!mem)
+		return;
+	iounmap(mem->virt_base);
+	kfree(mem->bitmap);
+	kfree(mem);
+}
+
+static int dma_assign_coherent_memory(struct device *dev,
+				      struct dma_coherent_mem *mem)
+{
+	if (dev->dma_mem)
+		return -EBUSY;
+
+	dev->dma_mem = mem;
+	/* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
+
+	return 0;
+}
+
+int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+				dma_addr_t device_addr, size_t size, int flags)
+{
+	struct dma_coherent_mem *mem;
+	int ret;
+
+	ret = dma_init_coherent_memory(phys_addr, device_addr, size, flags,
+				       &mem);
+	if (ret == 0)
+		return 0;
+
+	if (dma_assign_coherent_memory(dev, mem) == 0)
+		return ret;
+
+	dma_release_coherent_memory(mem);
+	return 0;
+}
 EXPORT_SYMBOL(dma_declare_coherent_memory);
 
 void dma_release_declared_memory(struct device *dev)
@@ -69,10 +109,8 @@ void dma_release_declared_memory(struct device *dev)
 
 	if (!mem)
 		return;
+	dma_release_coherent_memory(mem);
 	dev->dma_mem = NULL;
-	iounmap(mem->virt_base);
-	kfree(mem->bitmap);
-	kfree(mem);
 }
 EXPORT_SYMBOL(dma_release_declared_memory);
 
@@ -80,6 +118,7 @@ void *dma_mark_declared_memory_occupied(struct device *dev,
 					dma_addr_t device_addr, size_t size)
 {
 	struct dma_coherent_mem *mem = dev->dma_mem;
+	unsigned long flags;
 	int pos, err;
 
 	size += device_addr & ~PAGE_MASK;
@@ -87,8 +126,11 @@ void *dma_mark_declared_memory_occupied(struct device *dev,
 	if (!mem)
 		return ERR_PTR(-EINVAL);
 
+	spin_lock_irqsave(&mem->spinlock, flags);
 	pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
 	err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
+	spin_unlock_irqrestore(&mem->spinlock, flags);
+
 	if (err != 0)
 		return ERR_PTR(err);
 	return mem->virt_base + (pos << PAGE_SHIFT);
@@ -115,6 +157,7 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 {
 	struct dma_coherent_mem *mem;
 	int order = get_order(size);
+	unsigned long flags;
 	int pageno;
 
 	if (!dev)
@@ -124,6 +167,7 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 		return 0;
 
 	*ret = NULL;
+	spin_lock_irqsave(&mem->spinlock, flags);
 
 	if (unlikely(size > (mem->size << PAGE_SHIFT)))
 		goto err;
@@ -138,10 +182,12 @@ int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 	*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
 	*ret = mem->virt_base + (pageno << PAGE_SHIFT);
 	memset(*ret, 0, size);
+	spin_unlock_irqrestore(&mem->spinlock, flags);
 
 	return 1;
 
 err:
+	spin_unlock_irqrestore(&mem->spinlock, flags);
 	/*
 	 * In the case where the allocation can not be satisfied from the
 	 * per-device area, try to fall back to generic memory if the
@@ -171,8 +217,11 @@ int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
 	if (mem && vaddr >= mem->virt_base && vaddr <
 		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
 		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+		unsigned long flags;
 
+		spin_lock_irqsave(&mem->spinlock, flags);
 		bitmap_release_region(mem->bitmap, page, order);
+		spin_unlock_irqrestore(&mem->spinlock, flags);
 		return 1;
 	}
 	return 0;
@@ -218,3 +267,61 @@ int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
 	return 0;
 }
 EXPORT_SYMBOL(dma_mmap_from_coherent);
+
+/*
+ * Support for reserved memory regions defined in device tree
+ */
+#ifdef CONFIG_OF_RESERVED_MEM
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+
+static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
+{
+	struct dma_coherent_mem *mem = rmem->priv;
+
+	if (!mem &&
+	    dma_init_coherent_memory(rmem->base, rmem->base, rmem->size,
+				     DMA_MEMORY_MAP | DMA_MEMORY_EXCLUSIVE,
+				     &mem) != DMA_MEMORY_MAP) {
+		pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
+			&rmem->base, (unsigned long)rmem->size / SZ_1M);
+		return -ENODEV;
+	}
+	rmem->priv = mem;
+	dma_assign_coherent_memory(dev, mem);
+	return 0;
+}
+
+static void rmem_dma_device_release(struct reserved_mem *rmem,
+				    struct device *dev)
+{
+	dev->dma_mem = NULL;
+}
+
+static const struct reserved_mem_ops rmem_dma_ops = {
+	.device_init	= rmem_dma_device_init,
+	.device_release	= rmem_dma_device_release,
+};
+
+static int __init rmem_dma_setup(struct reserved_mem *rmem)
+{
+	unsigned long node = rmem->fdt_node;
+
+	if (of_get_flat_dt_prop(node, "reusable", NULL))
+		return -EINVAL;
+
+#ifdef CONFIG_ARM
+	if (!of_get_flat_dt_prop(node, "no-map", NULL)) {
+		pr_err("Reserved memory: regions without no-map are not yet supported\n");
+		return -EINVAL;
+	}
+#endif
+
+	rmem->ops = &rmem_dma_ops;
+	pr_info("Reserved memory: created DMA memory pool at %pa, size %ld MiB\n",
+		&rmem->base, (unsigned long)rmem->size / SZ_1M);
+	return 0;
+}
+RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup);
+#endif
diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 6606abdf880c..473ff4892401 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -211,3 +211,69 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 {
 	return cma_release(dev_get_cma_area(dev), pages, count);
 }
+
+/*
+ * Support for reserved memory regions defined in device tree
+ */
+#ifdef CONFIG_OF_RESERVED_MEM
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) fmt
+
+static void rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
+{
+	dev_set_cma_area(dev, rmem->priv);
+}
+
+static void rmem_cma_device_release(struct reserved_mem *rmem,
+				    struct device *dev)
+{
+	dev_set_cma_area(dev, NULL);
+}
+
+static const struct reserved_mem_ops rmem_cma_ops = {
+	.device_init	= rmem_cma_device_init,
+	.device_release = rmem_cma_device_release,
+};
+
+static int __init rmem_cma_setup(struct reserved_mem *rmem)
+{
+	phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+	phys_addr_t mask = align - 1;
+	unsigned long node = rmem->fdt_node;
+	struct cma *cma;
+	int err;
+
+	if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
+	    of_get_flat_dt_prop(node, "no-map", NULL))
+		return -EINVAL;
+
+	if ((rmem->base & mask) || (rmem->size & mask)) {
+		pr_err("Reserved memory: incorrect alignment of CMA region\n");
+		return -EINVAL;
+	}
+
+	err = cma_init_reserved_mem(rmem->base, rmem->size, 0, &cma);
+	if (err) {
+		pr_err("Reserved memory: unable to setup CMA region\n");
+		return err;
+	}
+	/* Architecture specific contiguous memory fixup. */
+	dma_contiguous_early_fixup(rmem->base, rmem->size);
+
+	if (of_get_flat_dt_prop(node, "linux,cma-default", NULL))
+		dma_contiguous_set_default(cma);
+
+	rmem->ops = &rmem_cma_ops;
+	rmem->priv = cma;
+
+	pr_info("Reserved memory: created CMA memory pool at %pa, size %ld MiB\n",
+		&rmem->base, (unsigned long)rmem->size / SZ_1M);
+
+	return 0;
+}
+RESERVEDMEM_OF_DECLARE(cma, "shared-dma-pool", rmem_cma_setup);
+#endif
diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c
index 6cd08e145bfa..9e8bbdd470ca 100644
--- a/drivers/base/dma-mapping.c
+++ b/drivers/base/dma-mapping.c
@@ -10,6 +10,8 @@
 #include <linux/dma-mapping.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <asm-generic/dma-coherent.h>
 
 /*
@@ -267,3 +269,73 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 EXPORT_SYMBOL(dma_common_mmap);
+
+#ifdef CONFIG_MMU
+/*
+ * remaps an array of PAGE_SIZE pages into another vm_area
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller)
+{
+	struct vm_struct *area;
+
+	area = get_vm_area_caller(size, vm_flags, caller);
+	if (!area)
+		return NULL;
+
+	area->pages = pages;
+
+	if (map_vm_area(area, prot, pages)) {
+		vunmap(area->addr);
+		return NULL;
+	}
+
+	return area->addr;
+}
+
+/*
+ * remaps an allocated contiguous region into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller)
+{
+	int i;
+	struct page **pages;
+	void *ptr;
+	unsigned long pfn;
+
+	pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
+	if (!pages)
+		return NULL;
+
+	for (i = 0, pfn = page_to_pfn(page); i < (size >> PAGE_SHIFT); i++)
+		pages[i] = pfn_to_page(pfn + i);
+
+	ptr = dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+
+	kfree(pages);
+
+	return ptr;
+}
+
+/*
+ * unmaps a range previously mapped by dma_common_*_remap
+ */
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
+{
+	struct vm_struct *area = find_vm_area(cpu_addr);
+
+	if (!area || (area->flags & vm_flags) != vm_flags) {
+		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+		return;
+	}
+
+	unmap_kernel_range((unsigned long)cpu_addr, size);
+	vunmap(cpu_addr);
+}
+#endif
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index a2e13e250bba..7c5d87191b28 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -373,6 +373,45 @@ static ssize_t show_phys_device(struct device *dev,
 	return sprintf(buf, "%d\n", mem->phys_device);
 }
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
+static ssize_t show_valid_zones(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct memory_block *mem = to_memory_block(dev);
+	unsigned long start_pfn, end_pfn;
+	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
+	struct page *first_page;
+	struct zone *zone;
+
+	start_pfn = section_nr_to_pfn(mem->start_section_nr);
+	end_pfn = start_pfn + nr_pages;
+	first_page = pfn_to_page(start_pfn);
+
+	/* The block contains more than one zone can not be offlined. */
+	if (!test_pages_in_a_zone(start_pfn, end_pfn))
+		return sprintf(buf, "none\n");
+
+	zone = page_zone(first_page);
+
+	if (zone_idx(zone) == ZONE_MOVABLE - 1) {
+		/*The mem block is the last memoryblock of this zone.*/
+		if (end_pfn == zone_end_pfn(zone))
+			return sprintf(buf, "%s %s\n",
+					zone->name, (zone + 1)->name);
+	}
+
+	if (zone_idx(zone) == ZONE_MOVABLE) {
+		/*The mem block is the first memoryblock of ZONE_MOVABLE.*/
+		if (start_pfn == zone->zone_start_pfn)
+			return sprintf(buf, "%s %s\n",
+					zone->name, (zone - 1)->name);
+	}
+
+	return sprintf(buf, "%s\n", zone->name);
+}
+static DEVICE_ATTR(valid_zones, 0444, show_valid_zones, NULL);
+#endif
+
 static DEVICE_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
 static DEVICE_ATTR(state, 0644, show_mem_state, store_mem_state);
 static DEVICE_ATTR(phys_device, 0444, show_phys_device, NULL);
@@ -523,6 +562,9 @@ static struct attribute *memory_memblk_attrs[] = {
 	&dev_attr_state.attr,
 	&dev_attr_phys_device.attr,
 	&dev_attr_removable.attr,
+#ifdef CONFIG_MEMORY_HOTREMOVE
+	&dev_attr_valid_zones.attr,
+#endif
 	NULL
 };
 
diff --git a/drivers/base/node.c b/drivers/base/node.c
index d51c49c9bafa..472168cd0c97 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -289,8 +289,6 @@ static int register_node(struct node *node, int num, struct node *parent)
 		device_create_file(&node->dev, &dev_attr_distance);
 		device_create_file(&node->dev, &dev_attr_vmstat);
 
-		scan_unevictable_register_node(node);
-
 		hugetlb_register_node(node);
 
 		compaction_register_node(node);
@@ -314,7 +312,6 @@ void unregister_node(struct node *node)
 	device_remove_file(&node->dev, &dev_attr_distance);
 	device_remove_file(&node->dev, &dev_attr_vmstat);
 
-	scan_unevictable_unregister_node(node);
 	hugetlb_unregister_node(node);		/* no-op, if memoryless node */
 
 	device_unregister(&node->dev);
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index ab4f4ce02722..b2afc29403f9 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -21,6 +21,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/idr.h>
 #include <linux/acpi.h>
 #include <linux/clk/clk-conf.h>
@@ -506,11 +507,12 @@ static int platform_drv_probe(struct device *_dev)
 	if (ret < 0)
 		return ret;
 
-	acpi_dev_pm_attach(_dev, true);
-
-	ret = drv->probe(dev);
-	if (ret)
-		acpi_dev_pm_detach(_dev, true);
+	ret = dev_pm_domain_attach(_dev, true);
+	if (ret != -EPROBE_DEFER) {
+		ret = drv->probe(dev);
+		if (ret)
+			dev_pm_domain_detach(_dev, true);
+	}
 
 	if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) {
 		dev_warn(_dev, "probe deferral not supported\n");
@@ -532,7 +534,7 @@ static int platform_drv_remove(struct device *_dev)
 	int ret;
 
 	ret = drv->remove(dev);
-	acpi_dev_pm_detach(_dev, true);
+	dev_pm_domain_detach(_dev, true);
 
 	return ret;
 }
@@ -543,7 +545,7 @@ static void platform_drv_shutdown(struct device *_dev)
 	struct platform_device *dev = to_platform_device(_dev);
 
 	drv->shutdown(dev);
-	acpi_dev_pm_detach(_dev, true);
+	dev_pm_domain_detach(_dev, true);
 }
 
 /**
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index b99e6c06ee67..78369305e069 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -368,8 +368,13 @@ int pm_clk_suspend(struct device *dev)
 
 	spin_lock_irqsave(&psd->lock, flags);
 
-	list_for_each_entry_reverse(ce, &psd->clock_list, node)
-		clk_disable(ce->clk);
+	list_for_each_entry_reverse(ce, &psd->clock_list, node) {
+		if (ce->status < PCE_STATUS_ERROR) {
+			if (ce->status == PCE_STATUS_ENABLED)
+				clk_disable(ce->clk);
+			ce->status = PCE_STATUS_ACQUIRED;
+		}
+	}
 
 	spin_unlock_irqrestore(&psd->lock, flags);
 
@@ -385,6 +390,7 @@ int pm_clk_resume(struct device *dev)
 	struct pm_subsys_data *psd = dev_to_psd(dev);
 	struct pm_clock_entry *ce;
 	unsigned long flags;
+	int ret;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -394,8 +400,13 @@ int pm_clk_resume(struct device *dev)
 
 	spin_lock_irqsave(&psd->lock, flags);
 
-	list_for_each_entry(ce, &psd->clock_list, node)
-		__pm_clk_enable(dev, ce->clk);
+	list_for_each_entry(ce, &psd->clock_list, node) {
+		if (ce->status < PCE_STATUS_ERROR) {
+			ret = __pm_clk_enable(dev, ce->clk);
+			if (!ret)
+				ce->status = PCE_STATUS_ENABLED;
+		}
+	}
 
 	spin_unlock_irqrestore(&psd->lock, flags);
 
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index df2e5eeaeb05..b0f138806bbc 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -11,6 +11,8 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/pm_clock.h>
+#include <linux/acpi.h>
+#include <linux/pm_domain.h>
 
 /**
  * dev_pm_get_subsys_data - Create or refcount power.subsys_data for device.
@@ -82,3 +84,53 @@ int dev_pm_put_subsys_data(struct device *dev)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
+
+/**
+ * dev_pm_domain_attach - Attach a device to its PM domain.
+ * @dev: Device to attach.
+ * @power_on: Used to indicate whether we should power on the device.
+ *
+ * The @dev may only be attached to a single PM domain. By iterating through
+ * the available alternatives we try to find a valid PM domain for the device.
+ * As attachment succeeds, the ->detach() callback in the struct dev_pm_domain
+ * should be assigned by the corresponding attach function.
+ *
+ * This function should typically be invoked from subsystem level code during
+ * the probe phase. Especially for those that holds devices which requires
+ * power management through PM domains.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ *
+ * Returns 0 on successfully attached PM domain or negative error code.
+ */
+int dev_pm_domain_attach(struct device *dev, bool power_on)
+{
+	int ret;
+
+	ret = acpi_dev_pm_attach(dev, power_on);
+	if (ret)
+		ret = genpd_dev_pm_attach(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach);
+
+/**
+ * dev_pm_domain_detach - Detach a device from its PM domain.
+ * @dev: Device to attach.
+ * @power_off: Used to indicate whether we should power off the device.
+ *
+ * This functions will reverse the actions from dev_pm_domain_attach() and thus
+ * try to detach the @dev from its PM domain. Typically it should be invoked
+ * from subsystem level code during the remove phase.
+ *
+ * Callers must ensure proper synchronization of this function with power
+ * management callbacks.
+ */
+void dev_pm_domain_detach(struct device *dev, bool power_off)
+{
+	if (dev->pm_domain && dev->pm_domain->detach)
+		dev->pm_domain->detach(dev, power_off);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_detach);
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index eee55c1e5fde..40bc2f4072cc 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -8,6 +8,7 @@
 
 #include <linux/kernel.h>
 #include <linux/io.h>
+#include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
@@ -25,10 +26,6 @@
 	__routine = genpd->dev_ops.callback; 			\
 	if (__routine) {					\
 		__ret = __routine(dev); 			\
-	} else {						\
-		__routine = dev_gpd_data(dev)->ops.callback;	\
-		if (__routine) 					\
-			__ret = __routine(dev);			\
 	}							\
 	__ret;							\
 })
@@ -70,8 +67,6 @@ static struct generic_pm_domain *pm_genpd_lookup_name(const char *domain_name)
 	return genpd;
 }
 
-#ifdef CONFIG_PM
-
 struct generic_pm_domain *dev_to_genpd(struct device *dev)
 {
 	if (IS_ERR_OR_NULL(dev->pm_domain))
@@ -147,13 +142,13 @@ static void genpd_recalc_cpu_exit_latency(struct generic_pm_domain *genpd)
 {
 	s64 usecs64;
 
-	if (!genpd->cpu_data)
+	if (!genpd->cpuidle_data)
 		return;
 
 	usecs64 = genpd->power_on_latency_ns;
 	do_div(usecs64, NSEC_PER_USEC);
-	usecs64 += genpd->cpu_data->saved_exit_latency;
-	genpd->cpu_data->idle_state->exit_latency = usecs64;
+	usecs64 += genpd->cpuidle_data->saved_exit_latency;
+	genpd->cpuidle_data->idle_state->exit_latency = usecs64;
 }
 
 /**
@@ -193,9 +188,9 @@ static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
 		return 0;
 	}
 
-	if (genpd->cpu_data) {
+	if (genpd->cpuidle_data) {
 		cpuidle_pause_and_lock();
-		genpd->cpu_data->idle_state->disabled = true;
+		genpd->cpuidle_data->idle_state->disabled = true;
 		cpuidle_resume_and_unlock();
 		goto out;
 	}
@@ -285,8 +280,6 @@ int pm_genpd_name_poweron(const char *domain_name)
 	return genpd ? pm_genpd_poweron(genpd) : -EINVAL;
 }
 
-#endif /* CONFIG_PM */
-
 #ifdef CONFIG_PM_RUNTIME
 
 static int genpd_start_dev_no_timing(struct generic_pm_domain *genpd,
@@ -430,7 +423,7 @@ static bool genpd_abort_poweroff(struct generic_pm_domain *genpd)
  * Queue up the execution of pm_genpd_poweroff() unless it's already been done
  * before.
  */
-void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
+static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
 {
 	queue_work(pm_wq, &genpd->power_off_work);
 }
@@ -520,17 +513,17 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		}
 	}
 
-	if (genpd->cpu_data) {
+	if (genpd->cpuidle_data) {
 		/*
-		 * If cpu_data is set, cpuidle should turn the domain off when
-		 * the CPU in it is idle.  In that case we don't decrement the
-		 * subdomain counts of the master domains, so that power is not
-		 * removed from the current domain prematurely as a result of
-		 * cutting off the masters' power.
+		 * If cpuidle_data is set, cpuidle should turn the domain off
+		 * when the CPU in it is idle.  In that case we don't decrement
+		 * the subdomain counts of the master domains, so that power is
+		 * not removed from the current domain prematurely as a result
+		 * of cutting off the masters' power.
 		 */
 		genpd->status = GPD_STATE_POWER_OFF;
 		cpuidle_pause_and_lock();
-		genpd->cpu_data->idle_state->disabled = false;
+		genpd->cpuidle_data->idle_state->disabled = false;
 		cpuidle_resume_and_unlock();
 		goto out;
 	}
@@ -619,8 +612,6 @@ static int pm_genpd_runtime_suspend(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	might_sleep_if(!genpd->dev_irq_safe);
-
 	stop_ok = genpd->gov ? genpd->gov->stop_ok : NULL;
 	if (stop_ok && !stop_ok(dev))
 		return -EBUSY;
@@ -665,8 +656,6 @@ static int pm_genpd_runtime_resume(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	might_sleep_if(!genpd->dev_irq_safe);
-
 	/* If power.irq_safe, the PM domain is never powered off. */
 	if (dev->power.irq_safe)
 		return genpd_start_dev_no_timing(genpd, dev);
@@ -733,6 +722,13 @@ void pm_genpd_poweroff_unused(void)
 	mutex_unlock(&gpd_list_lock);
 }
 
+static int __init genpd_poweroff_unused(void)
+{
+	pm_genpd_poweroff_unused();
+	return 0;
+}
+late_initcall(genpd_poweroff_unused);
+
 #else
 
 static inline int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
@@ -741,6 +737,9 @@ static inline int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
+static inline void
+genpd_queue_power_off_work(struct generic_pm_domain *genpd) {}
+
 static inline void genpd_power_off_work_fn(struct work_struct *work) {}
 
 #define pm_genpd_runtime_suspend	NULL
@@ -774,46 +773,6 @@ static bool genpd_dev_active_wakeup(struct generic_pm_domain *genpd,
 	return GENPD_DEV_CALLBACK(genpd, bool, active_wakeup, dev);
 }
 
-static int genpd_suspend_dev(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, suspend, dev);
-}
-
-static int genpd_suspend_late(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, suspend_late, dev);
-}
-
-static int genpd_resume_early(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, resume_early, dev);
-}
-
-static int genpd_resume_dev(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, resume, dev);
-}
-
-static int genpd_freeze_dev(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, freeze, dev);
-}
-
-static int genpd_freeze_late(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, freeze_late, dev);
-}
-
-static int genpd_thaw_early(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, thaw_early, dev);
-}
-
-static int genpd_thaw_dev(struct generic_pm_domain *genpd, struct device *dev)
-{
-	return GENPD_DEV_CALLBACK(genpd, int, thaw, dev);
-}
-
 /**
  * pm_genpd_sync_poweroff - Synchronously power off a PM domain and its masters.
  * @genpd: PM domain to power off, if possible.
@@ -995,7 +954,7 @@ static int pm_genpd_suspend(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_suspend_dev(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_suspend(dev);
 }
 
 /**
@@ -1016,7 +975,7 @@ static int pm_genpd_suspend_late(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_suspend_late(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_suspend_late(dev);
 }
 
 /**
@@ -1103,7 +1062,7 @@ static int pm_genpd_resume_early(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_resume_early(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_resume_early(dev);
 }
 
 /**
@@ -1124,7 +1083,7 @@ static int pm_genpd_resume(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_resume_dev(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_resume(dev);
 }
 
 /**
@@ -1145,7 +1104,7 @@ static int pm_genpd_freeze(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_freeze_dev(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_freeze(dev);
 }
 
 /**
@@ -1167,7 +1126,7 @@ static int pm_genpd_freeze_late(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_freeze_late(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_freeze_late(dev);
 }
 
 /**
@@ -1231,7 +1190,7 @@ static int pm_genpd_thaw_early(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_thaw_early(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_thaw_early(dev);
 }
 
 /**
@@ -1252,7 +1211,7 @@ static int pm_genpd_thaw(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	return genpd->suspend_power_off ? 0 : genpd_thaw_dev(genpd, dev);
+	return genpd->suspend_power_off ? 0 : pm_generic_thaw(dev);
 }
 
 /**
@@ -1344,13 +1303,13 @@ static void pm_genpd_complete(struct device *dev)
 }
 
 /**
- * pm_genpd_syscore_switch - Switch power during system core suspend or resume.
+ * genpd_syscore_switch - Switch power during system core suspend or resume.
  * @dev: Device that normally is marked as "always on" to switch power for.
  *
  * This routine may only be called during the system core (syscore) suspend or
  * resume phase for devices whose "always on" flags are set.
  */
-void pm_genpd_syscore_switch(struct device *dev, bool suspend)
+static void genpd_syscore_switch(struct device *dev, bool suspend)
 {
 	struct generic_pm_domain *genpd;
 
@@ -1366,7 +1325,18 @@ void pm_genpd_syscore_switch(struct device *dev, bool suspend)
 		genpd->suspended_count--;
 	}
 }
-EXPORT_SYMBOL_GPL(pm_genpd_syscore_switch);
+
+void pm_genpd_syscore_poweroff(struct device *dev)
+{
+	genpd_syscore_switch(dev, true);
+}
+EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweroff);
+
+void pm_genpd_syscore_poweron(struct device *dev)
+{
+	genpd_syscore_switch(dev, false);
+}
+EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
 
 #else
 
@@ -1466,6 +1436,9 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 
 	spin_unlock_irq(&dev->power.lock);
 
+	if (genpd->attach_dev)
+		genpd->attach_dev(dev);
+
 	mutex_lock(&gpd_data->lock);
 	gpd_data->base.dev = dev;
 	list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
@@ -1484,39 +1457,6 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 }
 
 /**
- * __pm_genpd_of_add_device - Add a device to an I/O PM domain.
- * @genpd_node: Device tree node pointer representing a PM domain to which the
- *   the device is added to.
- * @dev: Device to be added.
- * @td: Set of PM QoS timing parameters to attach to the device.
- */
-int __pm_genpd_of_add_device(struct device_node *genpd_node, struct device *dev,
-			     struct gpd_timing_data *td)
-{
-	struct generic_pm_domain *genpd = NULL, *gpd;
-
-	dev_dbg(dev, "%s()\n", __func__);
-
-	if (IS_ERR_OR_NULL(genpd_node) || IS_ERR_OR_NULL(dev))
-		return -EINVAL;
-
-	mutex_lock(&gpd_list_lock);
-	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
-		if (gpd->of_node == genpd_node) {
-			genpd = gpd;
-			break;
-		}
-	}
-	mutex_unlock(&gpd_list_lock);
-
-	if (!genpd)
-		return -EINVAL;
-
-	return __pm_genpd_add_device(genpd, dev, td);
-}
-
-
-/**
  * __pm_genpd_name_add_device - Find I/O PM domain and add a device to it.
  * @domain_name: Name of the PM domain to add the device to.
  * @dev: Device to be added.
@@ -1558,6 +1498,9 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 	genpd->device_count--;
 	genpd->max_off_time_changed = true;
 
+	if (genpd->detach_dev)
+		genpd->detach_dev(dev);
+
 	spin_lock_irq(&dev->power.lock);
 
 	dev->pm_domain = NULL;
@@ -1744,112 +1687,6 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 }
 
 /**
- * pm_genpd_add_callbacks - Add PM domain callbacks to a given device.
- * @dev: Device to add the callbacks to.
- * @ops: Set of callbacks to add.
- * @td: Timing data to add to the device along with the callbacks (optional).
- *
- * Every call to this routine should be balanced with a call to
- * __pm_genpd_remove_callbacks() and they must not be nested.
- */
-int pm_genpd_add_callbacks(struct device *dev, struct gpd_dev_ops *ops,
-			   struct gpd_timing_data *td)
-{
-	struct generic_pm_domain_data *gpd_data_new, *gpd_data = NULL;
-	int ret = 0;
-
-	if (!(dev && ops))
-		return -EINVAL;
-
-	gpd_data_new = __pm_genpd_alloc_dev_data(dev);
-	if (!gpd_data_new)
-		return -ENOMEM;
-
-	pm_runtime_disable(dev);
-	device_pm_lock();
-
-	ret = dev_pm_get_subsys_data(dev);
-	if (ret)
-		goto out;
-
-	spin_lock_irq(&dev->power.lock);
-
-	if (dev->power.subsys_data->domain_data) {
-		gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
-	} else {
-		gpd_data = gpd_data_new;
-		dev->power.subsys_data->domain_data = &gpd_data->base;
-	}
-	gpd_data->refcount++;
-	gpd_data->ops = *ops;
-	if (td)
-		gpd_data->td = *td;
-
-	spin_unlock_irq(&dev->power.lock);
-
- out:
-	device_pm_unlock();
-	pm_runtime_enable(dev);
-
-	if (gpd_data != gpd_data_new)
-		__pm_genpd_free_dev_data(dev, gpd_data_new);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(pm_genpd_add_callbacks);
-
-/**
- * __pm_genpd_remove_callbacks - Remove PM domain callbacks from a given device.
- * @dev: Device to remove the callbacks from.
- * @clear_td: If set, clear the device's timing data too.
- *
- * This routine can only be called after pm_genpd_add_callbacks().
- */
-int __pm_genpd_remove_callbacks(struct device *dev, bool clear_td)
-{
-	struct generic_pm_domain_data *gpd_data = NULL;
-	bool remove = false;
-	int ret = 0;
-
-	if (!(dev && dev->power.subsys_data))
-		return -EINVAL;
-
-	pm_runtime_disable(dev);
-	device_pm_lock();
-
-	spin_lock_irq(&dev->power.lock);
-
-	if (dev->power.subsys_data->domain_data) {
-		gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
-		gpd_data->ops = (struct gpd_dev_ops){ NULL };
-		if (clear_td)
-			gpd_data->td = (struct gpd_timing_data){ 0 };
-
-		if (--gpd_data->refcount == 0) {
-			dev->power.subsys_data->domain_data = NULL;
-			remove = true;
-		}
-	} else {
-		ret = -EINVAL;
-	}
-
-	spin_unlock_irq(&dev->power.lock);
-
-	device_pm_unlock();
-	pm_runtime_enable(dev);
-
-	if (ret)
-		return ret;
-
-	dev_pm_put_subsys_data(dev);
-	if (remove)
-		__pm_genpd_free_dev_data(dev, gpd_data);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(__pm_genpd_remove_callbacks);
-
-/**
  * pm_genpd_attach_cpuidle - Connect the given PM domain with cpuidle.
  * @genpd: PM domain to be connected with cpuidle.
  * @state: cpuidle state this domain can disable/enable.
@@ -1861,7 +1698,7 @@ EXPORT_SYMBOL_GPL(__pm_genpd_remove_callbacks);
 int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 {
 	struct cpuidle_driver *cpuidle_drv;
-	struct gpd_cpu_data *cpu_data;
+	struct gpd_cpuidle_data *cpuidle_data;
 	struct cpuidle_state *idle_state;
 	int ret = 0;
 
@@ -1870,12 +1707,12 @@ int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 
 	genpd_acquire_lock(genpd);
 
-	if (genpd->cpu_data) {
+	if (genpd->cpuidle_data) {
 		ret = -EEXIST;
 		goto out;
 	}
-	cpu_data = kzalloc(sizeof(*cpu_data), GFP_KERNEL);
-	if (!cpu_data) {
+	cpuidle_data = kzalloc(sizeof(*cpuidle_data), GFP_KERNEL);
+	if (!cpuidle_data) {
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1893,9 +1730,9 @@ int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 		ret = -EAGAIN;
 		goto err;
 	}
-	cpu_data->idle_state = idle_state;
-	cpu_data->saved_exit_latency = idle_state->exit_latency;
-	genpd->cpu_data = cpu_data;
+	cpuidle_data->idle_state = idle_state;
+	cpuidle_data->saved_exit_latency = idle_state->exit_latency;
+	genpd->cpuidle_data = cpuidle_data;
 	genpd_recalc_cpu_exit_latency(genpd);
 
  out:
@@ -1906,7 +1743,7 @@ int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state)
 	cpuidle_driver_unref();
 
  err_drv:
-	kfree(cpu_data);
+	kfree(cpuidle_data);
 	goto out;
 }
 
@@ -1929,7 +1766,7 @@ int pm_genpd_name_attach_cpuidle(const char *name, int state)
  */
 int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd)
 {
-	struct gpd_cpu_data *cpu_data;
+	struct gpd_cpuidle_data *cpuidle_data;
 	struct cpuidle_state *idle_state;
 	int ret = 0;
 
@@ -1938,20 +1775,20 @@ int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd)
 
 	genpd_acquire_lock(genpd);
 
-	cpu_data = genpd->cpu_data;
-	if (!cpu_data) {
+	cpuidle_data = genpd->cpuidle_data;
+	if (!cpuidle_data) {
 		ret = -ENODEV;
 		goto out;
 	}
-	idle_state = cpu_data->idle_state;
+	idle_state = cpuidle_data->idle_state;
 	if (!idle_state->disabled) {
 		ret = -EAGAIN;
 		goto out;
 	}
-	idle_state->exit_latency = cpu_data->saved_exit_latency;
+	idle_state->exit_latency = cpuidle_data->saved_exit_latency;
 	cpuidle_driver_unref();
-	genpd->cpu_data = NULL;
-	kfree(cpu_data);
+	genpd->cpuidle_data = NULL;
+	kfree(cpuidle_data);
 
  out:
 	genpd_release_lock(genpd);
@@ -1970,17 +1807,13 @@ int pm_genpd_name_detach_cpuidle(const char *name)
 /* Default device callbacks for generic PM domains. */
 
 /**
- * pm_genpd_default_save_state - Default "save device state" for PM domians.
+ * pm_genpd_default_save_state - Default "save device state" for PM domains.
  * @dev: Device to handle.
  */
 static int pm_genpd_default_save_state(struct device *dev)
 {
 	int (*cb)(struct device *__dev);
 
-	cb = dev_gpd_data(dev)->ops.save_state;
-	if (cb)
-		return cb(dev);
-
 	if (dev->type && dev->type->pm)
 		cb = dev->type->pm->runtime_suspend;
 	else if (dev->class && dev->class->pm)
@@ -1997,17 +1830,13 @@ static int pm_genpd_default_save_state(struct device *dev)
 }
 
 /**
- * pm_genpd_default_restore_state - Default PM domians "restore device state".
+ * pm_genpd_default_restore_state - Default PM domains "restore device state".
  * @dev: Device to handle.
  */
 static int pm_genpd_default_restore_state(struct device *dev)
 {
 	int (*cb)(struct device *__dev);
 
-	cb = dev_gpd_data(dev)->ops.restore_state;
-	if (cb)
-		return cb(dev);
-
 	if (dev->type && dev->type->pm)
 		cb = dev->type->pm->runtime_resume;
 	else if (dev->class && dev->class->pm)
@@ -2023,109 +1852,6 @@ static int pm_genpd_default_restore_state(struct device *dev)
 	return cb ? cb(dev) : 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-
-/**
- * pm_genpd_default_suspend - Default "device suspend" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_suspend(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.suspend;
-
-	return cb ? cb(dev) : pm_generic_suspend(dev);
-}
-
-/**
- * pm_genpd_default_suspend_late - Default "late device suspend" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_suspend_late(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.suspend_late;
-
-	return cb ? cb(dev) : pm_generic_suspend_late(dev);
-}
-
-/**
- * pm_genpd_default_resume_early - Default "early device resume" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_resume_early(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.resume_early;
-
-	return cb ? cb(dev) : pm_generic_resume_early(dev);
-}
-
-/**
- * pm_genpd_default_resume - Default "device resume" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_resume(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.resume;
-
-	return cb ? cb(dev) : pm_generic_resume(dev);
-}
-
-/**
- * pm_genpd_default_freeze - Default "device freeze" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_freeze(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.freeze;
-
-	return cb ? cb(dev) : pm_generic_freeze(dev);
-}
-
-/**
- * pm_genpd_default_freeze_late - Default "late device freeze" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_freeze_late(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.freeze_late;
-
-	return cb ? cb(dev) : pm_generic_freeze_late(dev);
-}
-
-/**
- * pm_genpd_default_thaw_early - Default "early device thaw" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_thaw_early(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.thaw_early;
-
-	return cb ? cb(dev) : pm_generic_thaw_early(dev);
-}
-
-/**
- * pm_genpd_default_thaw - Default "device thaw" for PM domians.
- * @dev: Device to handle.
- */
-static int pm_genpd_default_thaw(struct device *dev)
-{
-	int (*cb)(struct device *__dev) = dev_gpd_data(dev)->ops.thaw;
-
-	return cb ? cb(dev) : pm_generic_thaw(dev);
-}
-
-#else /* !CONFIG_PM_SLEEP */
-
-#define pm_genpd_default_suspend	NULL
-#define pm_genpd_default_suspend_late	NULL
-#define pm_genpd_default_resume_early	NULL
-#define pm_genpd_default_resume		NULL
-#define pm_genpd_default_freeze		NULL
-#define pm_genpd_default_freeze_late	NULL
-#define pm_genpd_default_thaw_early	NULL
-#define pm_genpd_default_thaw		NULL
-
-#endif /* !CONFIG_PM_SLEEP */
-
 /**
  * pm_genpd_init - Initialize a generic I/O PM domain object.
  * @genpd: PM domain object to initialize.
@@ -2177,15 +1903,452 @@ void pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->domain.ops.complete = pm_genpd_complete;
 	genpd->dev_ops.save_state = pm_genpd_default_save_state;
 	genpd->dev_ops.restore_state = pm_genpd_default_restore_state;
-	genpd->dev_ops.suspend = pm_genpd_default_suspend;
-	genpd->dev_ops.suspend_late = pm_genpd_default_suspend_late;
-	genpd->dev_ops.resume_early = pm_genpd_default_resume_early;
-	genpd->dev_ops.resume = pm_genpd_default_resume;
-	genpd->dev_ops.freeze = pm_genpd_default_freeze;
-	genpd->dev_ops.freeze_late = pm_genpd_default_freeze_late;
-	genpd->dev_ops.thaw_early = pm_genpd_default_thaw_early;
-	genpd->dev_ops.thaw = pm_genpd_default_thaw;
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
 }
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+/*
+ * Device Tree based PM domain providers.
+ *
+ * The code below implements generic device tree based PM domain providers that
+ * bind device tree nodes with generic PM domains registered in the system.
+ *
+ * Any driver that registers generic PM domains and needs to support binding of
+ * devices to these domains is supposed to register a PM domain provider, which
+ * maps a PM domain specifier retrieved from the device tree to a PM domain.
+ *
+ * Two simple mapping functions have been provided for convenience:
+ *  - __of_genpd_xlate_simple() for 1:1 device tree node to PM domain mapping.
+ *  - __of_genpd_xlate_onecell() for mapping of multiple PM domains per node by
+ *    index.
+ */
+
+/**
+ * struct of_genpd_provider - PM domain provider registration structure
+ * @link: Entry in global list of PM domain providers
+ * @node: Pointer to device tree node of PM domain provider
+ * @xlate: Provider-specific xlate callback mapping a set of specifier cells
+ *         into a PM domain.
+ * @data: context pointer to be passed into @xlate callback
+ */
+struct of_genpd_provider {
+	struct list_head link;
+	struct device_node *node;
+	genpd_xlate_t xlate;
+	void *data;
+};
+
+/* List of registered PM domain providers. */
+static LIST_HEAD(of_genpd_providers);
+/* Mutex to protect the list above. */
+static DEFINE_MUTEX(of_genpd_mutex);
+
+/**
+ * __of_genpd_xlate_simple() - Xlate function for direct node-domain mapping
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct generic_pm_domain
+ *
+ * This is a generic xlate function that can be used to model PM domains that
+ * have their own device tree nodes. The private data of xlate function needs
+ * to be a valid pointer to struct generic_pm_domain.
+ */
+struct generic_pm_domain *__of_genpd_xlate_simple(
+					struct of_phandle_args *genpdspec,
+					void *data)
+{
+	if (genpdspec->args_count != 0)
+		return ERR_PTR(-EINVAL);
+	return data;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_simple);
+
+/**
+ * __of_genpd_xlate_onecell() - Xlate function using a single index.
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct genpd_onecell_data
+ *
+ * This is a generic xlate function that can be used to model simple PM domain
+ * controllers that have one device tree node and provide multiple PM domains.
+ * A single cell is used as an index into an array of PM domains specified in
+ * the genpd_onecell_data struct when registering the provider.
+ */
+struct generic_pm_domain *__of_genpd_xlate_onecell(
+					struct of_phandle_args *genpdspec,
+					void *data)
+{
+	struct genpd_onecell_data *genpd_data = data;
+	unsigned int idx = genpdspec->args[0];
+
+	if (genpdspec->args_count != 1)
+		return ERR_PTR(-EINVAL);
+
+	if (idx >= genpd_data->num_domains) {
+		pr_err("%s: invalid domain index %u\n", __func__, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!genpd_data->domains[idx])
+		return ERR_PTR(-ENOENT);
+
+	return genpd_data->domains[idx];
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_onecell);
+
+/**
+ * __of_genpd_add_provider() - Register a PM domain provider for a node
+ * @np: Device node pointer associated with the PM domain provider.
+ * @xlate: Callback for decoding PM domain from phandle arguments.
+ * @data: Context pointer for @xlate callback.
+ */
+int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+			void *data)
+{
+	struct of_genpd_provider *cp;
+
+	cp = kzalloc(sizeof(*cp), GFP_KERNEL);
+	if (!cp)
+		return -ENOMEM;
+
+	cp->node = of_node_get(np);
+	cp->data = data;
+	cp->xlate = xlate;
+
+	mutex_lock(&of_genpd_mutex);
+	list_add(&cp->link, &of_genpd_providers);
+	mutex_unlock(&of_genpd_mutex);
+	pr_debug("Added domain provider from %s\n", np->full_name);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_add_provider);
+
+/**
+ * of_genpd_del_provider() - Remove a previously registered PM domain provider
+ * @np: Device node pointer associated with the PM domain provider
+ */
+void of_genpd_del_provider(struct device_node *np)
+{
+	struct of_genpd_provider *cp;
+
+	mutex_lock(&of_genpd_mutex);
+	list_for_each_entry(cp, &of_genpd_providers, link) {
+		if (cp->node == np) {
+			list_del(&cp->link);
+			of_node_put(cp->node);
+			kfree(cp);
+			break;
+		}
+	}
+	mutex_unlock(&of_genpd_mutex);
+}
+EXPORT_SYMBOL_GPL(of_genpd_del_provider);
+
+/**
+ * of_genpd_get_from_provider() - Look-up PM domain
+ * @genpdspec: OF phandle args to use for look-up
+ *
+ * Looks for a PM domain provider under the node specified by @genpdspec and if
+ * found, uses xlate function of the provider to map phandle args to a PM
+ * domain.
+ *
+ * Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR()
+ * on failure.
+ */
+static struct generic_pm_domain *of_genpd_get_from_provider(
+					struct of_phandle_args *genpdspec)
+{
+	struct generic_pm_domain *genpd = ERR_PTR(-ENOENT);
+	struct of_genpd_provider *provider;
+
+	mutex_lock(&of_genpd_mutex);
+
+	/* Check if we have such a provider in our array */
+	list_for_each_entry(provider, &of_genpd_providers, link) {
+		if (provider->node == genpdspec->np)
+			genpd = provider->xlate(genpdspec, provider->data);
+		if (!IS_ERR(genpd))
+			break;
+	}
+
+	mutex_unlock(&of_genpd_mutex);
+
+	return genpd;
+}
+
+/**
+ * genpd_dev_pm_detach - Detach a device from its PM domain.
+ * @dev: Device to attach.
+ * @power_off: Currently not used
+ *
+ * Try to locate a corresponding generic PM domain, which the device was
+ * attached to previously. If such is found, the device is detached from it.
+ */
+static void genpd_dev_pm_detach(struct device *dev, bool power_off)
+{
+	struct generic_pm_domain *pd = NULL, *gpd;
+	int ret = 0;
+
+	if (!dev->pm_domain)
+		return;
+
+	mutex_lock(&gpd_list_lock);
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+		if (&gpd->domain == dev->pm_domain) {
+			pd = gpd;
+			break;
+		}
+	}
+	mutex_unlock(&gpd_list_lock);
+
+	if (!pd)
+		return;
+
+	dev_dbg(dev, "removing from PM domain %s\n", pd->name);
+
+	while (1) {
+		ret = pm_genpd_remove_device(pd, dev);
+		if (ret != -EAGAIN)
+			break;
+		cond_resched();
+	}
+
+	if (ret < 0) {
+		dev_err(dev, "failed to remove from PM domain %s: %d",
+			pd->name, ret);
+		return;
+	}
+
+	/* Check if PM domain can be powered off after removing this device. */
+	genpd_queue_power_off_work(pd);
+}
+
+/**
+ * genpd_dev_pm_attach - Attach a device to its PM domain using DT.
+ * @dev: Device to attach.
+ *
+ * Parse device's OF node to find a PM domain specifier. If such is found,
+ * attaches the device to retrieved pm_domain ops.
+ *
+ * Both generic and legacy Samsung-specific DT bindings are supported to keep
+ * backwards compatibility with existing DTBs.
+ *
+ * Returns 0 on successfully attached PM domain or negative error code.
+ */
+int genpd_dev_pm_attach(struct device *dev)
+{
+	struct of_phandle_args pd_args;
+	struct generic_pm_domain *pd;
+	int ret;
+
+	if (!dev->of_node)
+		return -ENODEV;
+
+	if (dev->pm_domain)
+		return -EEXIST;
+
+	ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
+					"#power-domain-cells", 0, &pd_args);
+	if (ret < 0) {
+		if (ret != -ENOENT)
+			return ret;
+
+		/*
+		 * Try legacy Samsung-specific bindings
+		 * (for backwards compatibility of DT ABI)
+		 */
+		pd_args.args_count = 0;
+		pd_args.np = of_parse_phandle(dev->of_node,
+						"samsung,power-domain", 0);
+		if (!pd_args.np)
+			return -ENOENT;
+	}
+
+	pd = of_genpd_get_from_provider(&pd_args);
+	if (IS_ERR(pd)) {
+		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
+			__func__, PTR_ERR(pd));
+		of_node_put(dev->of_node);
+		return PTR_ERR(pd);
+	}
+
+	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
+
+	while (1) {
+		ret = pm_genpd_add_device(pd, dev);
+		if (ret != -EAGAIN)
+			break;
+		cond_resched();
+	}
+
+	if (ret < 0) {
+		dev_err(dev, "failed to add to PM domain %s: %d",
+			pd->name, ret);
+		of_node_put(dev->of_node);
+		return ret;
+	}
+
+	dev->pm_domain->detach = genpd_dev_pm_detach;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
+#endif
+
+
+/***        debugfs support        ***/
+
+#ifdef CONFIG_PM_ADVANCED_DEBUG
+#include <linux/pm.h>
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/kobject.h>
+static struct dentry *pm_genpd_debugfs_dir;
+
+/*
+ * TODO: This function is a slightly modified version of rtpm_status_show
+ * from sysfs.c, but dependencies between PM_GENERIC_DOMAINS and PM_RUNTIME
+ * are too loose to generalize it.
+ */
+#ifdef CONFIG_PM_RUNTIME
+static void rtpm_status_str(struct seq_file *s, struct device *dev)
+{
+	static const char * const status_lookup[] = {
+		[RPM_ACTIVE] = "active",
+		[RPM_RESUMING] = "resuming",
+		[RPM_SUSPENDED] = "suspended",
+		[RPM_SUSPENDING] = "suspending"
+	};
+	const char *p = "";
+
+	if (dev->power.runtime_error)
+		p = "error";
+	else if (dev->power.disable_depth)
+		p = "unsupported";
+	else if (dev->power.runtime_status < ARRAY_SIZE(status_lookup))
+		p = status_lookup[dev->power.runtime_status];
+	else
+		WARN_ON(1);
+
+	seq_puts(s, p);
+}
+#else
+static void rtpm_status_str(struct seq_file *s, struct device *dev)
+{
+	seq_puts(s, "active");
+}
+#endif
+
+static int pm_genpd_summary_one(struct seq_file *s,
+		struct generic_pm_domain *gpd)
+{
+	static const char * const status_lookup[] = {
+		[GPD_STATE_ACTIVE] = "on",
+		[GPD_STATE_WAIT_MASTER] = "wait-master",
+		[GPD_STATE_BUSY] = "busy",
+		[GPD_STATE_REPEAT] = "off-in-progress",
+		[GPD_STATE_POWER_OFF] = "off"
+	};
+	struct pm_domain_data *pm_data;
+	const char *kobj_path;
+	struct gpd_link *link;
+	int ret;
+
+	ret = mutex_lock_interruptible(&gpd->lock);
+	if (ret)
+		return -ERESTARTSYS;
+
+	if (WARN_ON(gpd->status >= ARRAY_SIZE(status_lookup)))
+		goto exit;
+	seq_printf(s, "%-30s  %-15s  ", gpd->name, status_lookup[gpd->status]);
+
+	/*
+	 * Modifications on the list require holding locks on both
+	 * master and slave, so we are safe.
+	 * Also gpd->name is immutable.
+	 */
+	list_for_each_entry(link, &gpd->master_links, master_node) {
+		seq_printf(s, "%s", link->slave->name);
+		if (!list_is_last(&link->master_node, &gpd->master_links))
+			seq_puts(s, ", ");
+	}
+
+	list_for_each_entry(pm_data, &gpd->dev_list, list_node) {
+		kobj_path = kobject_get_path(&pm_data->dev->kobj, GFP_KERNEL);
+		if (kobj_path == NULL)
+			continue;
+
+		seq_printf(s, "\n    %-50s  ", kobj_path);
+		rtpm_status_str(s, pm_data->dev);
+		kfree(kobj_path);
+	}
+
+	seq_puts(s, "\n");
+exit:
+	mutex_unlock(&gpd->lock);
+
+	return 0;
+}
+
+static int pm_genpd_summary_show(struct seq_file *s, void *data)
+{
+	struct generic_pm_domain *gpd;
+	int ret = 0;
+
+	seq_puts(s, "    domain                      status         slaves\n");
+	seq_puts(s, "           /device                                      runtime status\n");
+	seq_puts(s, "----------------------------------------------------------------------\n");
+
+	ret = mutex_lock_interruptible(&gpd_list_lock);
+	if (ret)
+		return -ERESTARTSYS;
+
+	list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+		ret = pm_genpd_summary_one(s, gpd);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&gpd_list_lock);
+
+	return ret;
+}
+
+static int pm_genpd_summary_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, pm_genpd_summary_show, NULL);
+}
+
+static const struct file_operations pm_genpd_summary_fops = {
+	.open = pm_genpd_summary_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init pm_genpd_debug_init(void)
+{
+	struct dentry *d;
+
+	pm_genpd_debugfs_dir = debugfs_create_dir("pm_genpd", NULL);
+
+	if (!pm_genpd_debugfs_dir)
+		return -ENOMEM;
+
+	d = debugfs_create_file("pm_genpd_summary", S_IRUGO,
+			pm_genpd_debugfs_dir, NULL, &pm_genpd_summary_fops);
+	if (!d)
+		return -ENOMEM;
+
+	return 0;
+}
+late_initcall(pm_genpd_debug_init);
+
+static void __exit pm_genpd_debug_exit(void)
+{
+	debugfs_remove_recursive(pm_genpd_debugfs_dir);
+}
+__exitcall(pm_genpd_debug_exit);
+#endif /* CONFIG_PM_ADVANCED_DEBUG */
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index a089e3bcdfbc..d88a62e104d4 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -42,7 +42,7 @@ static int dev_update_qos_constraint(struct device *dev, void *data)
  * default_stop_ok - Default PM domain governor routine for stopping devices.
  * @dev: Device to check.
  */
-bool default_stop_ok(struct device *dev)
+static bool default_stop_ok(struct device *dev)
 {
 	struct gpd_timing_data *td = &dev_gpd_data(dev)->td;
 	unsigned long flags;
@@ -229,10 +229,7 @@ static bool always_on_power_down_ok(struct dev_pm_domain *domain)
 
 #else /* !CONFIG_PM_RUNTIME */
 
-bool default_stop_ok(struct device *dev)
-{
-	return false;
-}
+static inline bool default_stop_ok(struct device *dev) { return false; }
 
 #define default_power_down_ok	NULL
 #define always_on_power_down_ok	NULL
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index b67d9aef9fe4..44973196d3fd 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -540,7 +540,7 @@ static void async_resume_noirq(void *data, async_cookie_t cookie)
  * Call the "noirq" resume handlers for all devices in dpm_noirq_list and
  * enable device drivers to receive interrupts.
  */
-static void dpm_resume_noirq(pm_message_t state)
+void dpm_resume_noirq(pm_message_t state)
 {
 	struct device *dev;
 	ktime_t starttime = ktime_get();
@@ -662,7 +662,7 @@ static void async_resume_early(void *data, async_cookie_t cookie)
  * dpm_resume_early - Execute "early resume" callbacks for all devices.
  * @state: PM transition of the system being carried out.
  */
-static void dpm_resume_early(pm_message_t state)
+void dpm_resume_early(pm_message_t state)
 {
 	struct device *dev;
 	ktime_t starttime = ktime_get();
@@ -1093,7 +1093,7 @@ static int device_suspend_noirq(struct device *dev)
  * Prevent device drivers from receiving interrupts and call the "noirq" suspend
  * handlers for all non-sysdev devices.
  */
-static int dpm_suspend_noirq(pm_message_t state)
+int dpm_suspend_noirq(pm_message_t state)
 {
 	ktime_t starttime = ktime_get();
 	int error = 0;
@@ -1232,7 +1232,7 @@ static int device_suspend_late(struct device *dev)
  * dpm_suspend_late - Execute "late suspend" callbacks for all devices.
  * @state: PM transition of the system being carried out.
  */
-static int dpm_suspend_late(pm_message_t state)
+int dpm_suspend_late(pm_message_t state)
 {
 	ktime_t starttime = ktime_get();
 	int error = 0;
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index 95b181d1ca6d..a9d26ed11bf4 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -92,9 +92,6 @@
  *	wakeup_count - Report the number of wakeup events related to the device
  */
 
-static const char enabled[] = "enabled";
-static const char disabled[] = "disabled";
-
 const char power_group_name[] = "power";
 EXPORT_SYMBOL_GPL(power_group_name);
 
@@ -336,11 +333,14 @@ static DEVICE_ATTR(pm_qos_remote_wakeup, 0644,
 #endif /* CONFIG_PM_RUNTIME */
 
 #ifdef CONFIG_PM_SLEEP
+static const char _enabled[] = "enabled";
+static const char _disabled[] = "disabled";
+
 static ssize_t
 wake_show(struct device * dev, struct device_attribute *attr, char * buf)
 {
 	return sprintf(buf, "%s\n", device_can_wakeup(dev)
-		? (device_may_wakeup(dev) ? enabled : disabled)
+		? (device_may_wakeup(dev) ? _enabled : _disabled)
 		: "");
 }
 
@@ -357,11 +357,11 @@ wake_store(struct device * dev, struct device_attribute *attr,
 	cp = memchr(buf, '\n', n);
 	if (cp)
 		len = cp - buf;
-	if (len == sizeof enabled - 1
-			&& strncmp(buf, enabled, sizeof enabled - 1) == 0)
+	if (len == sizeof _enabled - 1
+			&& strncmp(buf, _enabled, sizeof _enabled - 1) == 0)
 		device_set_wakeup_enable(dev, 1);
-	else if (len == sizeof disabled - 1
-			&& strncmp(buf, disabled, sizeof disabled - 1) == 0)
+	else if (len == sizeof _disabled - 1
+			&& strncmp(buf, _disabled, sizeof _disabled - 1) == 0)
 		device_set_wakeup_enable(dev, 0);
 	else
 		return -EINVAL;
@@ -570,7 +570,8 @@ static ssize_t async_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
 {
 	return sprintf(buf, "%s\n",
-			device_async_suspend_enabled(dev) ? enabled : disabled);
+			device_async_suspend_enabled(dev) ?
+				_enabled : _disabled);
 }
 
 static ssize_t async_store(struct device *dev, struct device_attribute *attr,
@@ -582,9 +583,10 @@ static ssize_t async_store(struct device *dev, struct device_attribute *attr,
 	cp = memchr(buf, '\n', n);
 	if (cp)
 		len = cp - buf;
-	if (len == sizeof enabled - 1 && strncmp(buf, enabled, len) == 0)
+	if (len == sizeof _enabled - 1 && strncmp(buf, _enabled, len) == 0)
 		device_enable_async_suspend(dev);
-	else if (len == sizeof disabled - 1 && strncmp(buf, disabled, len) == 0)
+	else if (len == sizeof _disabled - 1 &&
+		 strncmp(buf, _disabled, len) == 0)
 		device_disable_async_suspend(dev);
 	else
 		return -EINVAL;
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index eb1bd2ecad8b..c2744b30d5d9 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -24,6 +24,9 @@
  */
 bool events_check_enabled __read_mostly;
 
+/* If set and the system is suspending, terminate the suspend. */
+static bool pm_abort_suspend __read_mostly;
+
 /*
  * Combined counters of registered wakeup events and wakeup events in progress.
  * They need to be modified together atomically, so it's better to use one
@@ -719,7 +722,18 @@ bool pm_wakeup_pending(void)
 		pm_print_active_wakeup_sources();
 	}
 
-	return ret;
+	return ret || pm_abort_suspend;
+}
+
+void pm_system_wakeup(void)
+{
+	pm_abort_suspend = true;
+	freeze_wake();
+}
+
+void pm_wakeup_clear(void)
+{
+	pm_abort_suspend = false;
 }
 
 /**
diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c
index dbb8350ea8dc..8d98a329f6ea 100644
--- a/drivers/base/syscore.c
+++ b/drivers/base/syscore.c
@@ -9,7 +9,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
-#include <linux/interrupt.h>
+#include <linux/suspend.h>
 #include <trace/events/power.h>
 
 static LIST_HEAD(syscore_ops_list);
@@ -54,9 +54,8 @@ int syscore_suspend(void)
 	pr_debug("Checking wakeup interrupts\n");
 
 	/* Return error code if there are any wakeup interrupts pending. */
-	ret = check_wakeup_irqs();
-	if (ret)
-		return ret;
+	if (pm_wakeup_pending())
+		return -EBUSY;
 
 	WARN_ONCE(!irqs_disabled(),
 		"Interrupts enabled before system core suspend.\n");
diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c
index 57ce5fe65364..706b9ae0dcfb 100644
--- a/drivers/bcma/driver_gpio.c
+++ b/drivers/bcma/driver_gpio.c
@@ -255,5 +255,6 @@ int bcma_gpio_init(struct bcma_drv_cc *cc)
 int bcma_gpio_unregister(struct bcma_drv_cc *cc)
 {
 	bcma_gpio_irq_domain_exit(cc);
-	return gpiochip_remove(&cc->gpio);
+	gpiochip_remove(&cc->gpio);
+	return 0;
 }
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index d26a3fa63688..a2dfa169237d 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -158,14 +158,14 @@ static int _drbd_md_sync_page_io(struct drbd_device *device,
 	if (bio_add_page(bio, device->md_io.page, size, 0) != size)
 		goto out;
 	bio->bi_private = device;
-	bio->bi_end_io = drbd_md_io_complete;
+	bio->bi_end_io = drbd_md_endio;
 	bio->bi_rw = rw;
 
 	if (!(rw & WRITE) && device->state.disk == D_DISKLESS && device->ldev == NULL)
 		/* special case, drbd_md_read() during drbd_adm_attach(): no get_ldev */
 		;
 	else if (!get_ldev_if_state(device, D_ATTACHING)) {
-		/* Corresponding put_ldev in drbd_md_io_complete() */
+		/* Corresponding put_ldev in drbd_md_endio() */
 		drbd_err(device, "ASSERT FAILED: get_ldev_if_state() == 1 in _drbd_md_sync_page_io()\n");
 		err = -ENODEV;
 		goto out;
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 426c97aef900..434c77dcc99e 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -941,7 +941,7 @@ static void drbd_bm_aio_ctx_destroy(struct kref *kref)
 }
 
 /* bv_page may be a copy, or may be the original */
-static void bm_async_io_complete(struct bio *bio, int error)
+static void drbd_bm_endio(struct bio *bio, int error)
 {
 	struct drbd_bm_aio_ctx *ctx = bio->bi_private;
 	struct drbd_device *device = ctx->device;
@@ -1027,7 +1027,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
 	 * according to api.  Do we want to assert that? */
 	bio_add_page(bio, page, len, 0);
 	bio->bi_private = ctx;
-	bio->bi_end_io = bm_async_io_complete;
+	bio->bi_end_io = drbd_bm_endio;
 
 	if (drbd_insert_fault(device, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD)) {
 		bio->bi_rw |= rw;
@@ -1125,7 +1125,7 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
 	}
 
 	/*
-	 * We initialize ctx->in_flight to one to make sure bm_async_io_complete
+	 * We initialize ctx->in_flight to one to make sure drbd_bm_endio
 	 * will not set ctx->done early, and decrement / test it here.  If there
 	 * are still some bios in flight, we need to wait for them here.
 	 * If all IO is done already (or nothing had been submitted), there is
diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c
index 5c20b18540b8..900d4d3272d1 100644
--- a/drivers/block/drbd/drbd_debugfs.c
+++ b/drivers/block/drbd/drbd_debugfs.c
@@ -695,7 +695,7 @@ static void resync_dump_detail(struct seq_file *m, struct lc_element *e)
 {
        struct bm_extent *bme = lc_entry(e, struct bm_extent, lce);
 
-       seq_printf(m, "%5d %s %s %s\n", bme->rs_left,
+       seq_printf(m, "%5d %s %s %s", bme->rs_left,
 		  test_bit(BME_NO_WRITES, &bme->flags) ? "NO_WRITES" : "---------",
 		  test_bit(BME_LOCKED, &bme->flags) ? "LOCKED" : "------",
 		  test_bit(BME_PRIORITY, &bme->flags) ? "PRIORITY" : "--------"
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 1a000016ccdf..9b22f8f01b57 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -61,8 +61,6 @@
 # define __must_hold(x)
 #endif
 
-#define __no_warn(lock, stmt) do { __acquire(lock); stmt; __release(lock); } while (0)
-
 /* module parameter, defined in drbd_main.c */
 extern unsigned int minor_count;
 extern bool disable_sendpage;
@@ -1483,7 +1481,7 @@ extern int drbd_khelper(struct drbd_device *device, char *cmd);
 
 /* drbd_worker.c */
 /* bi_end_io handlers */
-extern void drbd_md_io_complete(struct bio *bio, int error);
+extern void drbd_md_endio(struct bio *bio, int error);
 extern void drbd_peer_request_endio(struct bio *bio, int error);
 extern void drbd_request_endio(struct bio *bio, int error);
 extern int drbd_worker(struct drbd_thread *thi);
@@ -2100,16 +2098,19 @@ static inline bool is_sync_state(enum drbd_conns connection_state)
 
 /**
  * get_ldev() - Increase the ref count on device->ldev. Returns 0 if there is no ldev
- * @M:		DRBD device.
+ * @_device:		DRBD device.
+ * @_min_state:		Minimum device state required for success.
  *
  * You have to call put_ldev() when finished working with device->ldev.
  */
-#define get_ldev(M) __cond_lock(local, _get_ldev_if_state(M,D_INCONSISTENT))
-#define get_ldev_if_state(M,MINS) __cond_lock(local, _get_ldev_if_state(M,MINS))
+#define get_ldev_if_state(_device, _min_state)				\
+	(_get_ldev_if_state((_device), (_min_state)) ?			\
+	 ({ __acquire(x); true; }) : false)
+#define get_ldev(_device) get_ldev_if_state(_device, D_INCONSISTENT)
 
 static inline void put_ldev(struct drbd_device *device)
 {
-	enum drbd_disk_state ds = device->state.disk;
+	enum drbd_disk_state disk_state = device->state.disk;
 	/* We must check the state *before* the atomic_dec becomes visible,
 	 * or we have a theoretical race where someone hitting zero,
 	 * while state still D_FAILED, will then see D_DISKLESS in the
@@ -2122,10 +2123,10 @@ static inline void put_ldev(struct drbd_device *device)
 	__release(local);
 	D_ASSERT(device, i >= 0);
 	if (i == 0) {
-		if (ds == D_DISKLESS)
+		if (disk_state == D_DISKLESS)
 			/* even internal references gone, safe to destroy */
 			drbd_device_post_work(device, DESTROY_DISK);
-		if (ds == D_FAILED)
+		if (disk_state == D_FAILED)
 			/* all application IO references gone. */
 			if (!test_and_set_bit(GOING_DISKLESS, &device->flags))
 				drbd_device_post_work(device, GO_DISKLESS);
diff --git a/drivers/block/drbd/drbd_interval.c b/drivers/block/drbd/drbd_interval.c
index 89c497c630b4..51b25ad85251 100644
--- a/drivers/block/drbd/drbd_interval.c
+++ b/drivers/block/drbd/drbd_interval.c
@@ -37,40 +37,8 @@ compute_subtree_last(struct drbd_interval *node)
 	return max;
 }
 
-static void augment_propagate(struct rb_node *rb, struct rb_node *stop)
-{
-	while (rb != stop) {
-		struct drbd_interval *node = rb_entry(rb, struct drbd_interval, rb);
-		sector_t subtree_last = compute_subtree_last(node);
-		if (node->end == subtree_last)
-			break;
-		node->end = subtree_last;
-		rb = rb_parent(&node->rb);
-	}
-}
-
-static void augment_copy(struct rb_node *rb_old, struct rb_node *rb_new)
-{
-	struct drbd_interval *old = rb_entry(rb_old, struct drbd_interval, rb);
-	struct drbd_interval *new = rb_entry(rb_new, struct drbd_interval, rb);
-
-	new->end = old->end;
-}
-
-static void augment_rotate(struct rb_node *rb_old, struct rb_node *rb_new)
-{
-	struct drbd_interval *old = rb_entry(rb_old, struct drbd_interval, rb);
-	struct drbd_interval *new = rb_entry(rb_new, struct drbd_interval, rb);
-
-	new->end = old->end;
-	old->end = compute_subtree_last(old);
-}
-
-static const struct rb_augment_callbacks augment_callbacks = {
-	augment_propagate,
-	augment_copy,
-	augment_rotate,
-};
+RB_DECLARE_CALLBACKS(static, augment_callbacks, struct drbd_interval, rb,
+		     sector_t, end, compute_subtree_last);
 
 /**
  * drbd_insert_interval  -  insert a new interval into a tree
@@ -79,6 +47,7 @@ bool
 drbd_insert_interval(struct rb_root *root, struct drbd_interval *this)
 {
 	struct rb_node **new = &root->rb_node, *parent = NULL;
+	sector_t this_end = this->sector + (this->size >> 9);
 
 	BUG_ON(!IS_ALIGNED(this->size, 512));
 
@@ -87,6 +56,8 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this)
 			rb_entry(*new, struct drbd_interval, rb);
 
 		parent = *new;
+		if (here->end < this_end)
+			here->end = this_end;
 		if (this->sector < here->sector)
 			new = &(*new)->rb_left;
 		else if (this->sector > here->sector)
@@ -99,6 +70,7 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this)
 			return false;
 	}
 
+	this->end = this_end;
 	rb_link_node(&this->rb, parent, new);
 	rb_insert_augmented(&this->rb, root, &augment_callbacks);
 	return true;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 9b465bb68487..973c185c9cfe 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1622,13 +1622,13 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request *
 	struct drbd_socket *sock;
 	struct p_data *p;
 	unsigned int dp_flags = 0;
-	int dgs;
+	int digest_size;
 	int err;
 
 	sock = &peer_device->connection->data;
 	p = drbd_prepare_command(peer_device, sock);
-	dgs = peer_device->connection->integrity_tfm ?
-	      crypto_hash_digestsize(peer_device->connection->integrity_tfm) : 0;
+	digest_size = peer_device->connection->integrity_tfm ?
+		      crypto_hash_digestsize(peer_device->connection->integrity_tfm) : 0;
 
 	if (!p)
 		return -EIO;
@@ -1659,9 +1659,9 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request *
 
 	/* our digest is still only over the payload.
 	 * TRIM does not carry any payload. */
-	if (dgs)
+	if (digest_size)
 		drbd_csum_bio(peer_device->connection->integrity_tfm, req->master_bio, p + 1);
-	err = __send_command(peer_device->connection, device->vnr, sock, P_DATA, sizeof(*p) + dgs, NULL, req->i.size);
+	err = __send_command(peer_device->connection, device->vnr, sock, P_DATA, sizeof(*p) + digest_size, NULL, req->i.size);
 	if (!err) {
 		/* For protocol A, we have to memcpy the payload into
 		 * socket buffers, as we may complete right away
@@ -1674,23 +1674,23 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request *
 		 * out ok after sending on this side, but does not fit on the
 		 * receiving side, we sure have detected corruption elsewhere.
 		 */
-		if (!(req->rq_state & (RQ_EXP_RECEIVE_ACK | RQ_EXP_WRITE_ACK)) || dgs)
+		if (!(req->rq_state & (RQ_EXP_RECEIVE_ACK | RQ_EXP_WRITE_ACK)) || digest_size)
 			err = _drbd_send_bio(peer_device, req->master_bio);
 		else
 			err = _drbd_send_zc_bio(peer_device, req->master_bio);
 
 		/* double check digest, sometimes buffers have been modified in flight. */
-		if (dgs > 0 && dgs <= 64) {
+		if (digest_size > 0 && digest_size <= 64) {
 			/* 64 byte, 512 bit, is the largest digest size
 			 * currently supported in kernel crypto. */
 			unsigned char digest[64];
 			drbd_csum_bio(peer_device->connection->integrity_tfm, req->master_bio, digest);
-			if (memcmp(p + 1, digest, dgs)) {
+			if (memcmp(p + 1, digest, digest_size)) {
 				drbd_warn(device,
 					"Digest mismatch, buffer modified by upper layers during write: %llus +%u\n",
 					(unsigned long long)req->i.sector, req->i.size);
 			}
-		} /* else if (dgs > 64) {
+		} /* else if (digest_size > 64) {
 		     ... Be noisy about digest too large ...
 		} */
 	}
@@ -1711,13 +1711,13 @@ int drbd_send_block(struct drbd_peer_device *peer_device, enum drbd_packet cmd,
 	struct drbd_socket *sock;
 	struct p_data *p;
 	int err;
-	int dgs;
+	int digest_size;
 
 	sock = &peer_device->connection->data;
 	p = drbd_prepare_command(peer_device, sock);
 
-	dgs = peer_device->connection->integrity_tfm ?
-	      crypto_hash_digestsize(peer_device->connection->integrity_tfm) : 0;
+	digest_size = peer_device->connection->integrity_tfm ?
+		      crypto_hash_digestsize(peer_device->connection->integrity_tfm) : 0;
 
 	if (!p)
 		return -EIO;
@@ -1725,9 +1725,9 @@ int drbd_send_block(struct drbd_peer_device *peer_device, enum drbd_packet cmd,
 	p->block_id = peer_req->block_id;
 	p->seq_num = 0;  /* unused */
 	p->dp_flags = 0;
-	if (dgs)
+	if (digest_size)
 		drbd_csum_ee(peer_device->connection->integrity_tfm, peer_req, p + 1);
-	err = __send_command(peer_device->connection, device->vnr, sock, cmd, sizeof(*p) + dgs, NULL, peer_req->i.size);
+	err = __send_command(peer_device->connection, device->vnr, sock, cmd, sizeof(*p) + digest_size, NULL, peer_req->i.size);
 	if (!err)
 		err = _drbd_send_zc_ee(peer_device, peer_req);
 	mutex_unlock(&sock->mutex);  /* locked by drbd_prepare_command() */
diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c
index 06e6147c7601..3b10fa6cb039 100644
--- a/drivers/block/drbd/drbd_proc.c
+++ b/drivers/block/drbd/drbd_proc.c
@@ -142,10 +142,12 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se
 			    (unsigned long) Bit2KB(rs_left >> 10),
 			    (unsigned long) Bit2KB(rs_total >> 10));
 	else
-		seq_printf(seq, "(%lu/%lu)K\n\t",
+		seq_printf(seq, "(%lu/%lu)K",
 			    (unsigned long) Bit2KB(rs_left),
 			    (unsigned long) Bit2KB(rs_total));
 
+	seq_printf(seq, "\n\t");
+
 	/* see drivers/md/md.c
 	 * We do not want to overflow, so the order of operands and
 	 * the * 100 / 100 trick are important. We do a +1 to be
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 9342b8da73ab..6960fb064731 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1371,9 +1371,9 @@ int drbd_submit_peer_request(struct drbd_device *device,
 	struct bio *bio;
 	struct page *page = peer_req->pages;
 	sector_t sector = peer_req->i.sector;
-	unsigned ds = peer_req->i.size;
+	unsigned data_size = peer_req->i.size;
 	unsigned n_bios = 0;
-	unsigned nr_pages = (ds + PAGE_SIZE -1) >> PAGE_SHIFT;
+	unsigned nr_pages = (data_size + PAGE_SIZE -1) >> PAGE_SHIFT;
 	int err = -ENOMEM;
 
 	if (peer_req->flags & EE_IS_TRIM_USE_ZEROOUT) {
@@ -1388,7 +1388,7 @@ int drbd_submit_peer_request(struct drbd_device *device,
 		list_add_tail(&peer_req->w.list, &device->active_ee);
 		spin_unlock_irq(&device->resource->req_lock);
 		if (blkdev_issue_zeroout(device->ldev->backing_bdev,
-			sector, ds >> 9, GFP_NOIO))
+			sector, data_size >> 9, GFP_NOIO))
 			peer_req->flags |= EE_WAS_ERROR;
 		drbd_endio_write_sec_final(peer_req);
 		return 0;
@@ -1426,12 +1426,12 @@ next_bio:
 	++n_bios;
 
 	if (rw & REQ_DISCARD) {
-		bio->bi_iter.bi_size = ds;
+		bio->bi_iter.bi_size = data_size;
 		goto submit;
 	}
 
 	page_chain_for_each(page) {
-		unsigned len = min_t(unsigned, ds, PAGE_SIZE);
+		unsigned len = min_t(unsigned, data_size, PAGE_SIZE);
 		if (!bio_add_page(bio, page, len, 0)) {
 			/* A single page must always be possible!
 			 * But in case it fails anyways,
@@ -1446,11 +1446,11 @@ next_bio:
 			}
 			goto next_bio;
 		}
-		ds -= len;
+		data_size -= len;
 		sector += len >> 9;
 		--nr_pages;
 	}
-	D_ASSERT(device, ds == 0);
+	D_ASSERT(device, data_size == 0);
 submit:
 	D_ASSERT(device, page == NULL);
 
@@ -1591,24 +1591,24 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
 	const sector_t capacity = drbd_get_capacity(device->this_bdev);
 	struct drbd_peer_request *peer_req;
 	struct page *page;
-	int dgs, ds, err;
-	unsigned int data_size = pi->size;
+	int digest_size, err;
+	unsigned int data_size = pi->size, ds;
 	void *dig_in = peer_device->connection->int_dig_in;
 	void *dig_vv = peer_device->connection->int_dig_vv;
 	unsigned long *data;
 	struct p_trim *trim = (pi->cmd == P_TRIM) ? pi->data : NULL;
 
-	dgs = 0;
+	digest_size = 0;
 	if (!trim && peer_device->connection->peer_integrity_tfm) {
-		dgs = crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm);
+		digest_size = crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm);
 		/*
 		 * FIXME: Receive the incoming digest into the receive buffer
 		 *	  here, together with its struct p_data?
 		 */
-		err = drbd_recv_all_warn(peer_device->connection, dig_in, dgs);
+		err = drbd_recv_all_warn(peer_device->connection, dig_in, digest_size);
 		if (err)
 			return NULL;
-		data_size -= dgs;
+		data_size -= digest_size;
 	}
 
 	if (trim) {
@@ -1661,16 +1661,16 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector,
 		ds -= len;
 	}
 
-	if (dgs) {
+	if (digest_size) {
 		drbd_csum_ee(peer_device->connection->peer_integrity_tfm, peer_req, dig_vv);
-		if (memcmp(dig_in, dig_vv, dgs)) {
+		if (memcmp(dig_in, dig_vv, digest_size)) {
 			drbd_err(device, "Digest integrity check FAILED: %llus +%u\n",
 				(unsigned long long)sector, data_size);
 			drbd_free_peer_req(device, peer_req);
 			return NULL;
 		}
 	}
-	device->recv_cnt += data_size>>9;
+	device->recv_cnt += data_size >> 9;
 	return peer_req;
 }
 
@@ -1708,17 +1708,17 @@ static int recv_dless_read(struct drbd_peer_device *peer_device, struct drbd_req
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 	struct bio *bio;
-	int dgs, err, expect;
+	int digest_size, err, expect;
 	void *dig_in = peer_device->connection->int_dig_in;
 	void *dig_vv = peer_device->connection->int_dig_vv;
 
-	dgs = 0;
+	digest_size = 0;
 	if (peer_device->connection->peer_integrity_tfm) {
-		dgs = crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm);
-		err = drbd_recv_all_warn(peer_device->connection, dig_in, dgs);
+		digest_size = crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm);
+		err = drbd_recv_all_warn(peer_device->connection, dig_in, digest_size);
 		if (err)
 			return err;
-		data_size -= dgs;
+		data_size -= digest_size;
 	}
 
 	/* optimistically update recv_cnt.  if receiving fails below,
@@ -1738,9 +1738,9 @@ static int recv_dless_read(struct drbd_peer_device *peer_device, struct drbd_req
 		data_size -= expect;
 	}
 
-	if (dgs) {
+	if (digest_size) {
 		drbd_csum_bio(peer_device->connection->peer_integrity_tfm, bio, dig_vv);
-		if (memcmp(dig_in, dig_vv, dgs)) {
+		if (memcmp(dig_in, dig_vv, digest_size)) {
 			drbd_err(peer_device, "Digest integrity check FAILED. Broken NICs?\n");
 			return -EINVAL;
 		}
@@ -5561,6 +5561,7 @@ int drbd_asender(struct drbd_thread *thi)
 		 * rv <  expected: "woken" by signal during receive
 		 * rv == 0	 : "connection shut down by peer"
 		 */
+received_more:
 		if (likely(rv > 0)) {
 			received += rv;
 			buf	 += rv;
@@ -5636,6 +5637,11 @@ int drbd_asender(struct drbd_thread *thi)
 			expect	 = header_size;
 			cmd	 = NULL;
 		}
+		if (test_bit(SEND_PING, &connection->flags))
+			continue;
+		rv = drbd_recv_short(connection->meta.socket, buf, expect-received, MSG_DONTWAIT);
+		if (rv > 0)
+			goto received_more;
 	}
 
 	if (0) {
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index c67717d572d1..5a01c53dddeb 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1645,6 +1645,6 @@ void request_timer_fn(unsigned long data)
 		? oldest_submit_jif + dt : now + et;
 	nt = time_before(ent, dt) ? ent : dt;
 out:
-	spin_unlock_irq(&connection->resource->req_lock);
+	spin_unlock_irq(&device->resource->req_lock);
 	mod_timer(&device->request_timer, nt);
 }
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index c35c0f001bb7..84b11f887d73 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -136,50 +136,50 @@ enum drbd_role conn_highest_peer(struct drbd_connection *connection)
 
 enum drbd_disk_state conn_highest_disk(struct drbd_connection *connection)
 {
-	enum drbd_disk_state ds = D_DISKLESS;
+	enum drbd_disk_state disk_state = D_DISKLESS;
 	struct drbd_peer_device *peer_device;
 	int vnr;
 
 	rcu_read_lock();
 	idr_for_each_entry(&connection->peer_devices, peer_device, vnr) {
 		struct drbd_device *device = peer_device->device;
-		ds = max_t(enum drbd_disk_state, ds, device->state.disk);
+		disk_state = max_t(enum drbd_disk_state, disk_state, device->state.disk);
 	}
 	rcu_read_unlock();
 
-	return ds;
+	return disk_state;
 }
 
 enum drbd_disk_state conn_lowest_disk(struct drbd_connection *connection)
 {
-	enum drbd_disk_state ds = D_MASK;
+	enum drbd_disk_state disk_state = D_MASK;
 	struct drbd_peer_device *peer_device;
 	int vnr;
 
 	rcu_read_lock();
 	idr_for_each_entry(&connection->peer_devices, peer_device, vnr) {
 		struct drbd_device *device = peer_device->device;
-		ds = min_t(enum drbd_disk_state, ds, device->state.disk);
+		disk_state = min_t(enum drbd_disk_state, disk_state, device->state.disk);
 	}
 	rcu_read_unlock();
 
-	return ds;
+	return disk_state;
 }
 
 enum drbd_disk_state conn_highest_pdsk(struct drbd_connection *connection)
 {
-	enum drbd_disk_state ds = D_DISKLESS;
+	enum drbd_disk_state disk_state = D_DISKLESS;
 	struct drbd_peer_device *peer_device;
 	int vnr;
 
 	rcu_read_lock();
 	idr_for_each_entry(&connection->peer_devices, peer_device, vnr) {
 		struct drbd_device *device = peer_device->device;
-		ds = max_t(enum drbd_disk_state, ds, device->state.pdsk);
+		disk_state = max_t(enum drbd_disk_state, disk_state, device->state.pdsk);
 	}
 	rcu_read_unlock();
 
-	return ds;
+	return disk_state;
 }
 
 enum drbd_conns conn_lowest_conn(struct drbd_connection *connection)
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 50776b362828..d2d1f97511bd 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -43,10 +43,10 @@ static int make_ov_request(struct drbd_device *, int);
 static int make_resync_request(struct drbd_device *, int);
 
 /* endio handlers:
- *   drbd_md_io_complete (defined here)
+ *   drbd_md_endio (defined here)
  *   drbd_request_endio (defined here)
  *   drbd_peer_request_endio (defined here)
- *   bm_async_io_complete (defined in drbd_bitmap.c)
+ *   drbd_bm_endio (defined in drbd_bitmap.c)
  *
  * For all these callbacks, note the following:
  * The callbacks will be called in irq context by the IDE drivers,
@@ -65,7 +65,7 @@ rwlock_t global_state_lock;
 /* used for synchronous meta data and bitmap IO
  * submitted by drbd_md_sync_page_io()
  */
-void drbd_md_io_complete(struct bio *bio, int error)
+void drbd_md_endio(struct bio *bio, int error)
 {
 	struct drbd_device *device;
 
@@ -1853,9 +1853,12 @@ static void drbd_ldev_destroy(struct drbd_device *device)
 	device->resync = NULL;
 	lc_destroy(device->act_log);
 	device->act_log = NULL;
-	__no_warn(local,
-		drbd_free_ldev(device->ldev);
-		device->ldev = NULL;);
+
+	__acquire(local);
+	drbd_free_ldev(device->ldev);
+	device->ldev = NULL;
+	__release(local);
+
 	clear_bit(GOING_DISKLESS, &device->flags);
 	wake_up(&device->misc_wait);
 }
@@ -1928,19 +1931,18 @@ void __update_timing_details(
 	++(*cb_nr);
 }
 
-#define WORK_PENDING(work_bit, todo)	(todo & (1UL << work_bit))
 static void do_device_work(struct drbd_device *device, const unsigned long todo)
 {
-	if (WORK_PENDING(MD_SYNC, todo))
+	if (test_bit(MD_SYNC, &todo))
 		do_md_sync(device);
-	if (WORK_PENDING(RS_DONE, todo) ||
-	    WORK_PENDING(RS_PROGRESS, todo))
-		update_on_disk_bitmap(device, WORK_PENDING(RS_DONE, todo));
-	if (WORK_PENDING(GO_DISKLESS, todo))
+	if (test_bit(RS_DONE, &todo) ||
+	    test_bit(RS_PROGRESS, &todo))
+		update_on_disk_bitmap(device, test_bit(RS_DONE, &todo));
+	if (test_bit(GO_DISKLESS, &todo))
 		go_diskless(device);
-	if (WORK_PENDING(DESTROY_DISK, todo))
+	if (test_bit(DESTROY_DISK, &todo))
 		drbd_ldev_destroy(device);
-	if (WORK_PENDING(RS_START, todo))
+	if (test_bit(RS_START, &todo))
 		do_start_resync(device);
 }
 
@@ -1992,22 +1994,13 @@ static bool dequeue_work_batch(struct drbd_work_queue *queue, struct list_head *
 	return !list_empty(work_list);
 }
 
-static bool dequeue_work_item(struct drbd_work_queue *queue, struct list_head *work_list)
-{
-	spin_lock_irq(&queue->q_lock);
-	if (!list_empty(&queue->q))
-		list_move(queue->q.next, work_list);
-	spin_unlock_irq(&queue->q_lock);
-	return !list_empty(work_list);
-}
-
 static void wait_for_work(struct drbd_connection *connection, struct list_head *work_list)
 {
 	DEFINE_WAIT(wait);
 	struct net_conf *nc;
 	int uncork, cork;
 
-	dequeue_work_item(&connection->sender_work, work_list);
+	dequeue_work_batch(&connection->sender_work, work_list);
 	if (!list_empty(work_list))
 		return;
 
@@ -2033,8 +2026,6 @@ static void wait_for_work(struct drbd_connection *connection, struct list_head *
 		prepare_to_wait(&connection->sender_work.q_wait, &wait, TASK_INTERRUPTIBLE);
 		spin_lock_irq(&connection->resource->req_lock);
 		spin_lock(&connection->sender_work.q_lock);	/* FIXME get rid of this one? */
-		/* dequeue single item only,
-		 * we still use drbd_queue_work_front() in some places */
 		if (!list_empty(&connection->sender_work.q))
 			list_splice_tail_init(&connection->sender_work.q, work_list);
 		spin_unlock(&connection->sender_work.q_lock);	/* FIXME get rid of this one? */
@@ -2121,7 +2112,7 @@ int drbd_worker(struct drbd_thread *thi)
 		if (get_t_state(thi) != RUNNING)
 			break;
 
-		while (!list_empty(&work_list)) {
+		if (!list_empty(&work_list)) {
 			w = list_first_entry(&work_list, struct drbd_work, list);
 			list_del_init(&w->list);
 			update_worker_timing_details(connection, w->cb);
@@ -2137,13 +2128,13 @@ int drbd_worker(struct drbd_thread *thi)
 			update_worker_timing_details(connection, do_unqueued_work);
 			do_unqueued_work(connection);
 		}
-		while (!list_empty(&work_list)) {
+		if (!list_empty(&work_list)) {
 			w = list_first_entry(&work_list, struct drbd_work, list);
 			list_del_init(&w->list);
 			update_worker_timing_details(connection, w->cb);
 			w->cb(w, 1);
-		}
-		dequeue_work_batch(&connection->sender_work, &work_list);
+		} else
+			dequeue_work_batch(&connection->sender_work, &work_list);
 	} while (!list_empty(&work_list) || test_bit(DEVICE_WORK_PENDING, &connection->flags));
 
 	rcu_read_lock();
diff --git a/drivers/block/hd.c b/drivers/block/hd.c
index 8a290c08262f..3abb121825bc 100644
--- a/drivers/block/hd.c
+++ b/drivers/block/hd.c
@@ -694,16 +694,6 @@ static const struct block_device_operations hd_fops = {
 	.getgeo =	hd_getgeo,
 };
 
-/*
- * This is the hard disk IRQ description. The IRQF_DISABLED in sa_flags
- * means we run the IRQ-handler with interrupts disabled:  this is bad for
- * interrupt latency, but anything else has led to problems on some
- * machines.
- *
- * We enable interrupts in some of the routines after making sure it's
- * safe.
- */
-
 static int __init hd_init(void)
 {
 	int drive;
@@ -761,7 +751,7 @@ static int __init hd_init(void)
 			p->cyl, p->head, p->sect);
 	}
 
-	if (request_irq(HD_IRQ, hd_interrupt, IRQF_DISABLED, "hd", NULL)) {
+	if (request_irq(HD_IRQ, hd_interrupt, 0, "hd", NULL)) {
 		printk("hd: unable to get IRQ%d for the hard disk driver\n",
 			HD_IRQ);
 		goto out1;
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 5c8e7fe07745..1bd5f523f8fd 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -247,7 +247,7 @@ static void mtip_async_complete(struct mtip_port *port,
 	if (unlikely(cmd->unaligned))
 		up(&port->cmd_slot_unal);
 
-	blk_mq_end_io(rq, status ? -EIO : 0);
+	blk_mq_end_request(rq, status ? -EIO : 0);
 }
 
 /*
@@ -3739,7 +3739,7 @@ static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
 		int err;
 
 		err = mtip_send_trim(dd, blk_rq_pos(rq), blk_rq_sectors(rq));
-		blk_mq_end_io(rq, err);
+		blk_mq_end_request(rq, err);
 		return 0;
 	}
 
@@ -3775,13 +3775,16 @@ static bool mtip_check_unal_depth(struct blk_mq_hw_ctx *hctx,
 	return false;
 }
 
-static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq,
+		bool last)
 {
 	int ret;
 
 	if (unlikely(mtip_check_unal_depth(hctx, rq)))
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
+	blk_mq_start_request(rq);
+
 	ret = mtip_submit_request(hctx, rq);
 	if (likely(!ret))
 		return BLK_MQ_RQ_QUEUE_OK;
@@ -3951,6 +3954,7 @@ skip_create_disk:
 
 	/* Set device limits. */
 	set_bit(QUEUE_FLAG_NONROT, &dd->queue->queue_flags);
+	clear_bit(QUEUE_FLAG_ADD_RANDOM, &dd->queue->queue_flags);
 	blk_queue_max_segments(dd->queue, MTIP_MAX_SG);
 	blk_queue_physical_block_size(dd->queue, 4096);
 	blk_queue_max_hw_sectors(dd->queue, 0xffff);
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index fb31b8ee4372..4bc2a5cb9935 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -847,6 +847,7 @@ static int __init nbd_init(void)
 		 * Tell the block layer that we are not a rotational device
 		 */
 		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, disk->queue);
+		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue);
 		disk->queue->limits.discard_granularity = 512;
 		disk->queue->limits.max_discard_sectors = UINT_MAX;
 		disk->queue->limits.discard_zeroes_data = 0;
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 00d469c7f9f7..2671a3f02f0c 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -177,7 +177,7 @@ static void end_cmd(struct nullb_cmd *cmd)
 {
 	switch (queue_mode)  {
 	case NULL_Q_MQ:
-		blk_mq_end_io(cmd->rq, 0);
+		blk_mq_end_request(cmd->rq, 0);
 		return;
 	case NULL_Q_RQ:
 		INIT_LIST_HEAD(&cmd->rq->queuelist);
@@ -313,13 +313,16 @@ static void null_request_fn(struct request_queue *q)
 	}
 }
 
-static int null_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static int null_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq,
+		bool last)
 {
 	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
 	cmd->rq = rq;
 	cmd->nq = hctx->driver_data;
 
+	blk_mq_start_request(rq);
+
 	null_handle_cmd(cmd);
 	return BLK_MQ_RQ_QUEUE_OK;
 }
@@ -518,6 +521,7 @@ static int null_add_dev(void)
 
 	nullb->q->queuedata = nullb;
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q);
+	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q);
 
 	disk = nullb->disk = alloc_disk_node(1, home_node);
 	if (!disk) {
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 02351e217165..e2bb8afbeae5 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -1916,6 +1916,7 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 	ns->queue->queue_flags = QUEUE_FLAG_DEFAULT;
 	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
+	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, ns->queue);
 	blk_queue_make_request(ns->queue, nvme_make_request);
 	ns->dev = dev;
 	ns->queue->queuedata = ns;
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index fea7e76a00de..d48715b287e6 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -722,6 +722,8 @@ static int pd_special_command(struct pd_unit *disk,
 	int err = 0;
 
 	rq = blk_get_request(disk->gd->queue, READ, __GFP_WAIT);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
 
 	rq->cmd_type = REQ_TYPE_SPECIAL;
 	rq->special = func;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 758ac442c5b5..09e628dafd9d 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -704,6 +704,8 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 
 	rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
 			     WRITE : READ, __GFP_WAIT);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
 	blk_rq_set_block_pc(rq);
 
 	if (cgc->buflen) {
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 4b97baf8afa3..0a54c588e433 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -210,6 +210,12 @@ enum obj_request_type {
 	OBJ_REQUEST_NODATA, OBJ_REQUEST_BIO, OBJ_REQUEST_PAGES
 };
 
+enum obj_operation_type {
+	OBJ_OP_WRITE,
+	OBJ_OP_READ,
+	OBJ_OP_DISCARD,
+};
+
 enum obj_req_flags {
 	OBJ_REQ_DONE,		/* completion flag: not done = 0, done = 1 */
 	OBJ_REQ_IMG_DATA,	/* object usage: standalone = 0, image = 1 */
@@ -276,6 +282,7 @@ enum img_req_flags {
 	IMG_REQ_WRITE,		/* I/O direction: read = 0, write = 1 */
 	IMG_REQ_CHILD,		/* initiator: block = 0, child image = 1 */
 	IMG_REQ_LAYERED,	/* ENOENT handling: normal = 0, layered = 1 */
+	IMG_REQ_DISCARD,	/* discard: normal = 0, discard request = 1 */
 };
 
 struct rbd_img_request {
@@ -785,6 +792,20 @@ static int parse_rbd_opts_token(char *c, void *private)
 	return 0;
 }
 
+static char* obj_op_name(enum obj_operation_type op_type)
+{
+	switch (op_type) {
+	case OBJ_OP_READ:
+		return "read";
+	case OBJ_OP_WRITE:
+		return "write";
+	case OBJ_OP_DISCARD:
+		return "discard";
+	default:
+		return "???";
+	}
+}
+
 /*
  * Get a ceph client with specific addr and configuration, if one does
  * not exist create it.  Either way, ceph_opts is consumed by this
@@ -1600,6 +1621,21 @@ static bool img_request_write_test(struct rbd_img_request *img_request)
 	return test_bit(IMG_REQ_WRITE, &img_request->flags) != 0;
 }
 
+/*
+ * Set the discard flag when the img_request is an discard request
+ */
+static void img_request_discard_set(struct rbd_img_request *img_request)
+{
+	set_bit(IMG_REQ_DISCARD, &img_request->flags);
+	smp_mb();
+}
+
+static bool img_request_discard_test(struct rbd_img_request *img_request)
+{
+	smp_mb();
+	return test_bit(IMG_REQ_DISCARD, &img_request->flags) != 0;
+}
+
 static void img_request_child_set(struct rbd_img_request *img_request)
 {
 	set_bit(IMG_REQ_CHILD, &img_request->flags);
@@ -1636,6 +1672,17 @@ static bool img_request_layered_test(struct rbd_img_request *img_request)
 	return test_bit(IMG_REQ_LAYERED, &img_request->flags) != 0;
 }
 
+static enum obj_operation_type
+rbd_img_request_op_type(struct rbd_img_request *img_request)
+{
+	if (img_request_write_test(img_request))
+		return OBJ_OP_WRITE;
+	else if (img_request_discard_test(img_request))
+		return OBJ_OP_DISCARD;
+	else
+		return OBJ_OP_READ;
+}
+
 static void
 rbd_img_obj_request_read_callback(struct rbd_obj_request *obj_request)
 {
@@ -1722,6 +1769,21 @@ static void rbd_osd_write_callback(struct rbd_obj_request *obj_request)
 	obj_request_done_set(obj_request);
 }
 
+static void rbd_osd_discard_callback(struct rbd_obj_request *obj_request)
+{
+	dout("%s: obj %p result %d %llu\n", __func__, obj_request,
+		obj_request->result, obj_request->length);
+	/*
+	 * There is no such thing as a successful short discard.  Set
+	 * it to our originally-requested length.
+	 */
+	obj_request->xferred = obj_request->length;
+	/* discarding a non-existent object is not a problem */
+	if (obj_request->result == -ENOENT)
+		obj_request->result = 0;
+	obj_request_done_set(obj_request);
+}
+
 /*
  * For a simple stat call there's nothing to do.  We'll do more if
  * this is part of a write sequence for a layered image.
@@ -1773,6 +1835,11 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 	case CEPH_OSD_OP_STAT:
 		rbd_osd_stat_callback(obj_request);
 		break;
+	case CEPH_OSD_OP_DELETE:
+	case CEPH_OSD_OP_TRUNCATE:
+	case CEPH_OSD_OP_ZERO:
+		rbd_osd_discard_callback(obj_request);
+		break;
 	case CEPH_OSD_OP_CALL:
 	case CEPH_OSD_OP_NOTIFY_ACK:
 	case CEPH_OSD_OP_WATCH:
@@ -1823,7 +1890,7 @@ static void rbd_osd_req_format_write(struct rbd_obj_request *obj_request)
  */
 static struct ceph_osd_request *rbd_osd_req_create(
 					struct rbd_device *rbd_dev,
-					bool write_request,
+					enum obj_operation_type op_type,
 					unsigned int num_ops,
 					struct rbd_obj_request *obj_request)
 {
@@ -1831,16 +1898,18 @@ static struct ceph_osd_request *rbd_osd_req_create(
 	struct ceph_osd_client *osdc;
 	struct ceph_osd_request *osd_req;
 
-	if (obj_request_img_data_test(obj_request)) {
+	if (obj_request_img_data_test(obj_request) &&
+		(op_type == OBJ_OP_DISCARD || op_type == OBJ_OP_WRITE)) {
 		struct rbd_img_request *img_request = obj_request->img_request;
-
-		rbd_assert(write_request ==
-				img_request_write_test(img_request));
-		if (write_request)
-			snapc = img_request->snapc;
+		if (op_type == OBJ_OP_WRITE) {
+			rbd_assert(img_request_write_test(img_request));
+		} else {
+			rbd_assert(img_request_discard_test(img_request));
+		}
+		snapc = img_request->snapc;
 	}
 
-	rbd_assert(num_ops == 1 || (write_request && num_ops == 2));
+	rbd_assert(num_ops == 1 || ((op_type == OBJ_OP_WRITE) && num_ops == 2));
 
 	/* Allocate and initialize the request, for the num_ops ops */
 
@@ -1850,7 +1919,7 @@ static struct ceph_osd_request *rbd_osd_req_create(
 	if (!osd_req)
 		return NULL;	/* ENOMEM */
 
-	if (write_request)
+	if (op_type == OBJ_OP_WRITE || op_type == OBJ_OP_DISCARD)
 		osd_req->r_flags = CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK;
 	else
 		osd_req->r_flags = CEPH_OSD_FLAG_READ;
@@ -1865,9 +1934,10 @@ static struct ceph_osd_request *rbd_osd_req_create(
 }
 
 /*
- * Create a copyup osd request based on the information in the
- * object request supplied.  A copyup request has three osd ops,
- * a copyup method call, a hint op, and a write op.
+ * Create a copyup osd request based on the information in the object
+ * request supplied.  A copyup request has two or three osd ops, a
+ * copyup method call, potentially a hint op, and a write or truncate
+ * or zero op.
  */
 static struct ceph_osd_request *
 rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request)
@@ -1877,18 +1947,24 @@ rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request)
 	struct rbd_device *rbd_dev;
 	struct ceph_osd_client *osdc;
 	struct ceph_osd_request *osd_req;
+	int num_osd_ops = 3;
 
 	rbd_assert(obj_request_img_data_test(obj_request));
 	img_request = obj_request->img_request;
 	rbd_assert(img_request);
-	rbd_assert(img_request_write_test(img_request));
+	rbd_assert(img_request_write_test(img_request) ||
+			img_request_discard_test(img_request));
+
+	if (img_request_discard_test(img_request))
+		num_osd_ops = 2;
 
-	/* Allocate and initialize the request, for the three ops */
+	/* Allocate and initialize the request, for all the ops */
 
 	snapc = img_request->snapc;
 	rbd_dev = img_request->rbd_dev;
 	osdc = &rbd_dev->rbd_client->client->osdc;
-	osd_req = ceph_osdc_alloc_request(osdc, snapc, 3, false, GFP_ATOMIC);
+	osd_req = ceph_osdc_alloc_request(osdc, snapc, num_osd_ops,
+						false, GFP_ATOMIC);
 	if (!osd_req)
 		return NULL;	/* ENOMEM */
 
@@ -2057,7 +2133,8 @@ static bool rbd_dev_parent_get(struct rbd_device *rbd_dev)
 static struct rbd_img_request *rbd_img_request_create(
 					struct rbd_device *rbd_dev,
 					u64 offset, u64 length,
-					bool write_request)
+					enum obj_operation_type op_type,
+					struct ceph_snap_context *snapc)
 {
 	struct rbd_img_request *img_request;
 
@@ -2065,20 +2142,17 @@ static struct rbd_img_request *rbd_img_request_create(
 	if (!img_request)
 		return NULL;
 
-	if (write_request) {
-		down_read(&rbd_dev->header_rwsem);
-		ceph_get_snap_context(rbd_dev->header.snapc);
-		up_read(&rbd_dev->header_rwsem);
-	}
-
 	img_request->rq = NULL;
 	img_request->rbd_dev = rbd_dev;
 	img_request->offset = offset;
 	img_request->length = length;
 	img_request->flags = 0;
-	if (write_request) {
+	if (op_type == OBJ_OP_DISCARD) {
+		img_request_discard_set(img_request);
+		img_request->snapc = snapc;
+	} else if (op_type == OBJ_OP_WRITE) {
 		img_request_write_set(img_request);
-		img_request->snapc = rbd_dev->header.snapc;
+		img_request->snapc = snapc;
 	} else {
 		img_request->snap_id = rbd_dev->spec->snap_id;
 	}
@@ -2093,8 +2167,7 @@ static struct rbd_img_request *rbd_img_request_create(
 	kref_init(&img_request->kref);
 
 	dout("%s: rbd_dev %p %s %llu/%llu -> img %p\n", __func__, rbd_dev,
-		write_request ? "write" : "read", offset, length,
-		img_request);
+		obj_op_name(op_type), offset, length, img_request);
 
 	return img_request;
 }
@@ -2118,7 +2191,8 @@ static void rbd_img_request_destroy(struct kref *kref)
 		rbd_dev_parent_put(img_request->rbd_dev);
 	}
 
-	if (img_request_write_test(img_request))
+	if (img_request_write_test(img_request) ||
+		img_request_discard_test(img_request))
 		ceph_put_snap_context(img_request->snapc);
 
 	kmem_cache_free(rbd_img_request_cache, img_request);
@@ -2134,8 +2208,8 @@ static struct rbd_img_request *rbd_parent_request_create(
 	rbd_assert(obj_request->img_request);
 	rbd_dev = obj_request->img_request->rbd_dev;
 
-	parent_request = rbd_img_request_create(rbd_dev->parent,
-						img_offset, length, false);
+	parent_request = rbd_img_request_create(rbd_dev->parent, img_offset,
+						length, OBJ_OP_READ, NULL);
 	if (!parent_request)
 		return NULL;
 
@@ -2176,11 +2250,18 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request)
 	result = obj_request->result;
 	if (result) {
 		struct rbd_device *rbd_dev = img_request->rbd_dev;
+		enum obj_operation_type op_type;
+
+		if (img_request_discard_test(img_request))
+			op_type = OBJ_OP_DISCARD;
+		else if (img_request_write_test(img_request))
+			op_type = OBJ_OP_WRITE;
+		else
+			op_type = OBJ_OP_READ;
 
 		rbd_warn(rbd_dev, "%s %llx at %llx (%llx)",
-			img_request_write_test(img_request) ? "write" : "read",
-			obj_request->length, obj_request->img_offset,
-			obj_request->offset);
+			obj_op_name(op_type), obj_request->length,
+			obj_request->img_offset, obj_request->offset);
 		rbd_warn(rbd_dev, "  result %d xferred %x",
 			result, xferred);
 		if (!img_request->result)
@@ -2245,6 +2326,67 @@ out:
 }
 
 /*
+ * Add individual osd ops to the given ceph_osd_request and prepare
+ * them for submission. num_ops is the current number of
+ * osd operations already to the object request.
+ */
+static void rbd_img_obj_request_fill(struct rbd_obj_request *obj_request,
+				struct ceph_osd_request *osd_request,
+				enum obj_operation_type op_type,
+				unsigned int num_ops)
+{
+	struct rbd_img_request *img_request = obj_request->img_request;
+	struct rbd_device *rbd_dev = img_request->rbd_dev;
+	u64 object_size = rbd_obj_bytes(&rbd_dev->header);
+	u64 offset = obj_request->offset;
+	u64 length = obj_request->length;
+	u64 img_end;
+	u16 opcode;
+
+	if (op_type == OBJ_OP_DISCARD) {
+		if (!offset && length == object_size &&
+		    (!img_request_layered_test(img_request) ||
+		     !obj_request_overlaps_parent(obj_request))) {
+			opcode = CEPH_OSD_OP_DELETE;
+		} else if ((offset + length == object_size)) {
+			opcode = CEPH_OSD_OP_TRUNCATE;
+		} else {
+			down_read(&rbd_dev->header_rwsem);
+			img_end = rbd_dev->header.image_size;
+			up_read(&rbd_dev->header_rwsem);
+
+			if (obj_request->img_offset + length == img_end)
+				opcode = CEPH_OSD_OP_TRUNCATE;
+			else
+				opcode = CEPH_OSD_OP_ZERO;
+		}
+	} else if (op_type == OBJ_OP_WRITE) {
+		opcode = CEPH_OSD_OP_WRITE;
+		osd_req_op_alloc_hint_init(osd_request, num_ops,
+					object_size, object_size);
+		num_ops++;
+	} else {
+		opcode = CEPH_OSD_OP_READ;
+	}
+
+	osd_req_op_extent_init(osd_request, num_ops, opcode, offset, length,
+				0, 0);
+	if (obj_request->type == OBJ_REQUEST_BIO)
+		osd_req_op_extent_osd_data_bio(osd_request, num_ops,
+					obj_request->bio_list, length);
+	else if (obj_request->type == OBJ_REQUEST_PAGES)
+		osd_req_op_extent_osd_data_pages(osd_request, num_ops,
+					obj_request->pages, length,
+					offset & ~PAGE_MASK, false, false);
+
+	/* Discards are also writes */
+	if (op_type == OBJ_OP_WRITE || op_type == OBJ_OP_DISCARD)
+		rbd_osd_req_format_write(obj_request);
+	else
+		rbd_osd_req_format_read(obj_request);
+}
+
+/*
  * Split up an image request into one or more object requests, each
  * to a different object.  The "type" parameter indicates whether
  * "data_desc" is the pointer to the head of a list of bio
@@ -2259,28 +2401,26 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 	struct rbd_device *rbd_dev = img_request->rbd_dev;
 	struct rbd_obj_request *obj_request = NULL;
 	struct rbd_obj_request *next_obj_request;
-	bool write_request = img_request_write_test(img_request);
 	struct bio *bio_list = NULL;
 	unsigned int bio_offset = 0;
 	struct page **pages = NULL;
+	enum obj_operation_type op_type;
 	u64 img_offset;
 	u64 resid;
-	u16 opcode;
 
 	dout("%s: img %p type %d data_desc %p\n", __func__, img_request,
 		(int)type, data_desc);
 
-	opcode = write_request ? CEPH_OSD_OP_WRITE : CEPH_OSD_OP_READ;
 	img_offset = img_request->offset;
 	resid = img_request->length;
 	rbd_assert(resid > 0);
+	op_type = rbd_img_request_op_type(img_request);
 
 	if (type == OBJ_REQUEST_BIO) {
 		bio_list = data_desc;
 		rbd_assert(img_offset ==
 			   bio_list->bi_iter.bi_sector << SECTOR_SHIFT);
-	} else {
-		rbd_assert(type == OBJ_REQUEST_PAGES);
+	} else if (type == OBJ_REQUEST_PAGES) {
 		pages = data_desc;
 	}
 
@@ -2289,7 +2429,6 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 		const char *object_name;
 		u64 offset;
 		u64 length;
-		unsigned int which = 0;
 
 		object_name = rbd_segment_name(rbd_dev, img_offset);
 		if (!object_name)
@@ -2321,7 +2460,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 								GFP_ATOMIC);
 			if (!obj_request->bio_list)
 				goto out_unwind;
-		} else {
+		} else if (type == OBJ_REQUEST_PAGES) {
 			unsigned int page_count;
 
 			obj_request->pages = pages;
@@ -2332,38 +2471,19 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 			pages += page_count;
 		}
 
-		osd_req = rbd_osd_req_create(rbd_dev, write_request,
-					     (write_request ? 2 : 1),
-					     obj_request);
+		osd_req = rbd_osd_req_create(rbd_dev, op_type,
+					(op_type == OBJ_OP_WRITE) ? 2 : 1,
+					obj_request);
 		if (!osd_req)
 			goto out_unwind;
+
 		obj_request->osd_req = osd_req;
 		obj_request->callback = rbd_img_obj_callback;
-		rbd_img_request_get(img_request);
-
-		if (write_request) {
-			osd_req_op_alloc_hint_init(osd_req, which,
-					     rbd_obj_bytes(&rbd_dev->header),
-					     rbd_obj_bytes(&rbd_dev->header));
-			which++;
-		}
-
-		osd_req_op_extent_init(osd_req, which, opcode, offset, length,
-				       0, 0);
-		if (type == OBJ_REQUEST_BIO)
-			osd_req_op_extent_osd_data_bio(osd_req, which,
-					obj_request->bio_list, length);
-		else
-			osd_req_op_extent_osd_data_pages(osd_req, which,
-					obj_request->pages, length,
-					offset & ~PAGE_MASK, false, false);
+		obj_request->img_offset = img_offset;
 
-		if (write_request)
-			rbd_osd_req_format_write(obj_request);
-		else
-			rbd_osd_req_format_read(obj_request);
+		rbd_img_obj_request_fill(obj_request, osd_req, op_type, 0);
 
-		obj_request->img_offset = img_offset;
+		rbd_img_request_get(img_request);
 
 		img_offset += length;
 		resid -= length;
@@ -2386,7 +2506,8 @@ rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request)
 	struct page **pages;
 	u32 page_count;
 
-	rbd_assert(obj_request->type == OBJ_REQUEST_BIO);
+	rbd_assert(obj_request->type == OBJ_REQUEST_BIO ||
+		obj_request->type == OBJ_REQUEST_NODATA);
 	rbd_assert(obj_request_img_data_test(obj_request));
 	img_request = obj_request->img_request;
 	rbd_assert(img_request);
@@ -2424,11 +2545,10 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request)
 	struct ceph_osd_client *osdc;
 	struct rbd_device *rbd_dev;
 	struct page **pages;
+	enum obj_operation_type op_type;
 	u32 page_count;
 	int img_result;
 	u64 parent_length;
-	u64 offset;
-	u64 length;
 
 	rbd_assert(img_request_child_test(img_request));
 
@@ -2492,26 +2612,10 @@ rbd_img_obj_parent_read_full_callback(struct rbd_img_request *img_request)
 	osd_req_op_cls_request_data_pages(osd_req, 0, pages, parent_length, 0,
 						false, false);
 
-	/* Then the hint op */
+	/* Add the other op(s) */
 
-	osd_req_op_alloc_hint_init(osd_req, 1, rbd_obj_bytes(&rbd_dev->header),
-				   rbd_obj_bytes(&rbd_dev->header));
-
-	/* And the original write request op */
-
-	offset = orig_request->offset;
-	length = orig_request->length;
-	osd_req_op_extent_init(osd_req, 2, CEPH_OSD_OP_WRITE,
-					offset, length, 0, 0);
-	if (orig_request->type == OBJ_REQUEST_BIO)
-		osd_req_op_extent_osd_data_bio(osd_req, 2,
-					orig_request->bio_list, length);
-	else
-		osd_req_op_extent_osd_data_pages(osd_req, 2,
-					orig_request->pages, length,
-					offset & ~PAGE_MASK, false, false);
-
-	rbd_osd_req_format_write(orig_request);
+	op_type = rbd_img_request_op_type(orig_request->img_request);
+	rbd_img_obj_request_fill(orig_request, osd_req, op_type, 1);
 
 	/* All set, send it off. */
 
@@ -2728,7 +2832,7 @@ static int rbd_img_obj_exists_submit(struct rbd_obj_request *obj_request)
 
 	rbd_assert(obj_request->img_request);
 	rbd_dev = obj_request->img_request->rbd_dev;
-	stat_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+	stat_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_READ, 1,
 						   stat_request);
 	if (!stat_request->osd_req)
 		goto out;
@@ -2748,11 +2852,10 @@ out:
 	return ret;
 }
 
-static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
+static bool img_obj_request_simple(struct rbd_obj_request *obj_request)
 {
 	struct rbd_img_request *img_request;
 	struct rbd_device *rbd_dev;
-	bool known;
 
 	rbd_assert(obj_request_img_data_test(obj_request));
 
@@ -2760,22 +2863,44 @@ static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
 	rbd_assert(img_request);
 	rbd_dev = img_request->rbd_dev;
 
+	/* Reads */
+	if (!img_request_write_test(img_request) &&
+	    !img_request_discard_test(img_request))
+		return true;
+
+	/* Non-layered writes */
+	if (!img_request_layered_test(img_request))
+		return true;
+
+	/*
+	 * Layered writes outside of the parent overlap range don't
+	 * share any data with the parent.
+	 */
+	if (!obj_request_overlaps_parent(obj_request))
+		return true;
+
 	/*
-	 * Only writes to layered images need special handling.
-	 * Reads and non-layered writes are simple object requests.
-	 * Layered writes that start beyond the end of the overlap
-	 * with the parent have no parent data, so they too are
-	 * simple object requests.  Finally, if the target object is
-	 * known to already exist, its parent data has already been
-	 * copied, so a write to the object can also be handled as a
-	 * simple object request.
+	 * Entire-object layered writes - we will overwrite whatever
+	 * parent data there is anyway.
 	 */
-	if (!img_request_write_test(img_request) ||
-		!img_request_layered_test(img_request) ||
-		!obj_request_overlaps_parent(obj_request) ||
-		((known = obj_request_known_test(obj_request)) &&
-			obj_request_exists_test(obj_request))) {
+	if (!obj_request->offset &&
+	    obj_request->length == rbd_obj_bytes(&rbd_dev->header))
+		return true;
+
+	/*
+	 * If the object is known to already exist, its parent data has
+	 * already been copied.
+	 */
+	if (obj_request_known_test(obj_request) &&
+	    obj_request_exists_test(obj_request))
+		return true;
+
+	return false;
+}
 
+static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
+{
+	if (img_obj_request_simple(obj_request)) {
 		struct rbd_device *rbd_dev;
 		struct ceph_osd_client *osdc;
 
@@ -2791,7 +2916,7 @@ static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
 	 * start by reading the data for the full target object from
 	 * the parent so we can use it for a copyup to the target.
 	 */
-	if (known)
+	if (obj_request_known_test(obj_request))
 		return rbd_img_obj_parent_read_full(obj_request);
 
 	/* We don't know whether the target exists.  Go find out. */
@@ -2932,7 +3057,7 @@ static int rbd_obj_notify_ack_sync(struct rbd_device *rbd_dev, u64 notify_id)
 		return -ENOMEM;
 
 	ret = -ENOMEM;
-	obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+	obj_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_READ, 1,
 						  obj_request);
 	if (!obj_request->osd_req)
 		goto out;
@@ -2995,7 +3120,7 @@ static struct rbd_obj_request *rbd_obj_watch_request_helper(
 	if (!obj_request)
 		return ERR_PTR(-ENOMEM);
 
-	obj_request->osd_req = rbd_osd_req_create(rbd_dev, true, 1,
+	obj_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_WRITE, 1,
 						  obj_request);
 	if (!obj_request->osd_req) {
 		ret = -ENOMEM;
@@ -3133,7 +3258,7 @@ static int rbd_obj_method_sync(struct rbd_device *rbd_dev,
 	obj_request->pages = pages;
 	obj_request->page_count = page_count;
 
-	obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+	obj_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_READ, 1,
 						  obj_request);
 	if (!obj_request->osd_req)
 		goto out;
@@ -3183,11 +3308,20 @@ out:
 static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
 {
 	struct rbd_img_request *img_request;
+	struct ceph_snap_context *snapc = NULL;
 	u64 offset = (u64)blk_rq_pos(rq) << SECTOR_SHIFT;
 	u64 length = blk_rq_bytes(rq);
-	bool wr = rq_data_dir(rq) == WRITE;
+	enum obj_operation_type op_type;
+	u64 mapping_size;
 	int result;
 
+	if (rq->cmd_flags & REQ_DISCARD)
+		op_type = OBJ_OP_DISCARD;
+	else if (rq->cmd_flags & REQ_WRITE)
+		op_type = OBJ_OP_WRITE;
+	else
+		op_type = OBJ_OP_READ;
+
 	/* Ignore/skip any zero-length requests */
 
 	if (!length) {
@@ -3196,9 +3330,9 @@ static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
 		goto err_rq;
 	}
 
-	/* Disallow writes to a read-only device */
+	/* Only reads are allowed to a read-only device */
 
-	if (wr) {
+	if (op_type != OBJ_OP_READ) {
 		if (rbd_dev->mapping.read_only) {
 			result = -EROFS;
 			goto err_rq;
@@ -3226,21 +3360,35 @@ static void rbd_handle_request(struct rbd_device *rbd_dev, struct request *rq)
 		goto err_rq;	/* Shouldn't happen */
 	}
 
-	if (offset + length > rbd_dev->mapping.size) {
+	down_read(&rbd_dev->header_rwsem);
+	mapping_size = rbd_dev->mapping.size;
+	if (op_type != OBJ_OP_READ) {
+		snapc = rbd_dev->header.snapc;
+		ceph_get_snap_context(snapc);
+	}
+	up_read(&rbd_dev->header_rwsem);
+
+	if (offset + length > mapping_size) {
 		rbd_warn(rbd_dev, "beyond EOD (%llu~%llu > %llu)", offset,
-			 length, rbd_dev->mapping.size);
+			 length, mapping_size);
 		result = -EIO;
 		goto err_rq;
 	}
 
-	img_request = rbd_img_request_create(rbd_dev, offset, length, wr);
+	img_request = rbd_img_request_create(rbd_dev, offset, length, op_type,
+					     snapc);
 	if (!img_request) {
 		result = -ENOMEM;
 		goto err_rq;
 	}
 	img_request->rq = rq;
 
-	result = rbd_img_request_fill(img_request, OBJ_REQUEST_BIO, rq->bio);
+	if (op_type == OBJ_OP_DISCARD)
+		result = rbd_img_request_fill(img_request, OBJ_REQUEST_NODATA,
+					      NULL);
+	else
+		result = rbd_img_request_fill(img_request, OBJ_REQUEST_BIO,
+					      rq->bio);
 	if (result)
 		goto err_img_request;
 
@@ -3255,7 +3403,9 @@ err_img_request:
 err_rq:
 	if (result)
 		rbd_warn(rbd_dev, "%s %llx at %llx result %d",
-			 wr ? "write" : "read", length, offset, result);
+			 obj_op_name(op_type), length, offset, result);
+	if (snapc)
+		ceph_put_snap_context(snapc);
 	blk_end_request_all(rq, result);
 }
 
@@ -3393,7 +3543,7 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev,
 	obj_request->pages = pages;
 	obj_request->page_count = page_count;
 
-	obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, 1,
+	obj_request->osd_req = rbd_osd_req_create(rbd_dev, OBJ_OP_READ, 1,
 						  obj_request);
 	if (!obj_request->osd_req)
 		goto out;
@@ -3610,6 +3760,13 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	blk_queue_io_min(q, segment_size);
 	blk_queue_io_opt(q, segment_size);
 
+	/* enable the discard support */
+	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+	q->limits.discard_granularity = segment_size;
+	q->limits.discard_alignment = segment_size;
+	q->limits.max_discard_sectors = segment_size / SECTOR_SIZE;
+	q->limits.discard_zeroes_data = 1;
+
 	blk_queue_merge_bvec(q, rbd_merge_bvec);
 	disk->queue = q;
 
@@ -4924,7 +5081,7 @@ static int rbd_dev_image_id(struct rbd_device *rbd_dev)
 		ret = image_id ? 0 : -ENOMEM;
 		if (!ret)
 			rbd_dev->image_format = 1;
-	} else if (ret > sizeof (__le32)) {
+	} else if (ret >= 0) {
 		void *p = response;
 
 		image_id = ceph_extract_encoded_string(&p, p + ret,
@@ -4932,8 +5089,6 @@ static int rbd_dev_image_id(struct rbd_device *rbd_dev)
 		ret = PTR_ERR_OR_ZERO(image_id);
 		if (!ret)
 			rbd_dev->image_format = 2;
-	} else {
-		ret = -EINVAL;
 	}
 
 	if (!ret) {
@@ -5087,7 +5242,8 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
 	set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
 	set_disk_ro(rbd_dev->disk, rbd_dev->mapping.read_only);
 
-	rbd_dev->rq_wq = alloc_workqueue("%s", 0, 0, rbd_dev->disk->disk_name);
+	rbd_dev->rq_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
+					 rbd_dev->disk->disk_name);
 	if (!rbd_dev->rq_wq) {
 		ret = -ENOMEM;
 		goto err_out_mapping;
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 820b4009d5f7..d8b2488aaade 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -62,12 +62,6 @@ static DEFINE_SPINLOCK(rsxx_ida_lock);
 
 /* --------------------Debugfs Setup ------------------- */
 
-struct rsxx_cram {
-	u32 f_pos;
-	u32 offset;
-	void *i_private;
-};
-
 static int rsxx_attr_pci_regs_show(struct seq_file *m, void *p)
 {
 	struct rsxx_cardinfo *card = m->private;
@@ -184,93 +178,50 @@ static int rsxx_attr_pci_regs_open(struct inode *inode, struct file *file)
 static ssize_t rsxx_cram_read(struct file *fp, char __user *ubuf,
 			      size_t cnt, loff_t *ppos)
 {
-	struct rsxx_cram *info = fp->private_data;
-	struct rsxx_cardinfo *card = info->i_private;
+	struct rsxx_cardinfo *card = file_inode(fp)->i_private;
 	char *buf;
-	int st;
+	ssize_t st;
 
-	buf = kzalloc(sizeof(*buf) * cnt, GFP_KERNEL);
+	buf = kzalloc(cnt, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	info->f_pos = (u32)*ppos + info->offset;
-
-	st = rsxx_creg_read(card, CREG_ADD_CRAM + info->f_pos, cnt, buf, 1);
-	if (st)
-		return st;
-
-	st = copy_to_user(ubuf, buf, cnt);
+	st = rsxx_creg_read(card, CREG_ADD_CRAM + (u32)*ppos, cnt, buf, 1);
+	if (!st)
+		st = copy_to_user(ubuf, buf, cnt);
+	kfree(buf);
 	if (st)
 		return st;
-
-	info->offset += cnt;
-
-	kfree(buf);
-
+	*ppos += cnt;
 	return cnt;
 }
 
 static ssize_t rsxx_cram_write(struct file *fp, const char __user *ubuf,
 			       size_t cnt, loff_t *ppos)
 {
-	struct rsxx_cram *info = fp->private_data;
-	struct rsxx_cardinfo *card = info->i_private;
+	struct rsxx_cardinfo *card = file_inode(fp)->i_private;
 	char *buf;
-	int st;
+	ssize_t st;
 
-	buf = kzalloc(sizeof(*buf) * cnt, GFP_KERNEL);
+	buf = kzalloc(cnt, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
 	st = copy_from_user(buf, ubuf, cnt);
+	if (!st)
+		st = rsxx_creg_write(card, CREG_ADD_CRAM + (u32)*ppos, cnt,
+				     buf, 1);
+	kfree(buf);
 	if (st)
 		return st;
-
-	info->f_pos = (u32)*ppos + info->offset;
-
-	st = rsxx_creg_write(card, CREG_ADD_CRAM + info->f_pos, cnt, buf, 1);
-	if (st)
-		return st;
-
-	info->offset += cnt;
-
-	kfree(buf);
-
+	*ppos += cnt;
 	return cnt;
 }
 
-static int rsxx_cram_open(struct inode *inode, struct file *file)
-{
-	struct rsxx_cram *info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	info->i_private = inode->i_private;
-	info->f_pos = file->f_pos;
-	file->private_data = info;
-
-	return 0;
-}
-
-static int rsxx_cram_release(struct inode *inode, struct file *file)
-{
-	struct rsxx_cram *info = file->private_data;
-
-	if (!info)
-		return 0;
-
-	kfree(info);
-	file->private_data = NULL;
-
-	return 0;
-}
-
 static const struct file_operations debugfs_cram_fops = {
 	.owner		= THIS_MODULE,
-	.open		= rsxx_cram_open,
 	.read		= rsxx_cram_read,
 	.write		= rsxx_cram_write,
-	.release	= rsxx_cram_release,
 };
 
 static const struct file_operations debugfs_stats_fops = {
@@ -886,7 +837,7 @@ static int rsxx_pci_probe(struct pci_dev *dev,
 				"Failed to enable MSI\n");
 	}
 
-	st = request_irq(dev->irq, rsxx_isr, IRQF_DISABLED | IRQF_SHARED,
+	st = request_irq(dev->irq, rsxx_isr, IRQF_SHARED,
 			 DRIVER_NAME, card);
 	if (st) {
 		dev_err(CARD_TO_DEV(card),
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 2839d37e5af7..40ee7705df63 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -307,6 +307,7 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card)
 	blk_queue_physical_block_size(card->queue, RSXX_HW_BLK_SIZE);
 
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, card->queue);
+	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, card->queue);
 	if (rsxx_discard_supported(card)) {
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, card->queue);
 		blk_queue_max_discard_sectors(card->queue,
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index 8fcdcfb4b472..1e46eb2305c0 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -4426,6 +4426,7 @@ static int skd_cons_disk(struct skd_device *skdev)
 	q->limits.discard_zeroes_data = 1;
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
+	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q);
 
 	spin_lock_irqsave(&skdev->lock, flags);
 	pr_debug("%s:%s:%d stopping %s queue\n",
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 5814deb6963d..756b8ec00f16 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -9,6 +9,7 @@
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
 #include <linux/genhd.h>
+#include <linux/cdrom.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
@@ -22,8 +23,8 @@
 
 #define DRV_MODULE_NAME		"sunvdc"
 #define PFX DRV_MODULE_NAME	": "
-#define DRV_MODULE_VERSION	"1.0"
-#define DRV_MODULE_RELDATE	"June 25, 2007"
+#define DRV_MODULE_VERSION	"1.1"
+#define DRV_MODULE_RELDATE	"February 13, 2013"
 
 static char version[] =
 	DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
@@ -32,7 +33,7 @@ MODULE_DESCRIPTION("Sun LDOM virtual disk client driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_MODULE_VERSION);
 
-#define VDC_TX_RING_SIZE	256
+#define VDC_TX_RING_SIZE	512
 
 #define WAITING_FOR_LINK_UP	0x01
 #define WAITING_FOR_TX_SPACE	0x02
@@ -65,10 +66,10 @@ struct vdc_port {
 	u64			operations;
 	u32			vdisk_size;
 	u8			vdisk_type;
+	u8			vdisk_mtype;
 
 	char			disk_name[32];
 
-	struct vio_disk_geom	geom;
 	struct vio_disk_vtoc	label;
 };
 
@@ -79,9 +80,16 @@ static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)
 
 /* Ordered from largest major to lowest */
 static struct vio_version vdc_versions[] = {
+	{ .major = 1, .minor = 1 },
 	{ .major = 1, .minor = 0 },
 };
 
+static inline int vdc_version_supported(struct vdc_port *port,
+					u16 major, u16 minor)
+{
+	return port->vio.ver.major == major && port->vio.ver.minor >= minor;
+}
+
 #define VDCBLK_NAME	"vdisk"
 static int vdc_major;
 #define PARTITION_SHIFT	3
@@ -94,18 +102,54 @@ static inline u32 vdc_tx_dring_avail(struct vio_dring_state *dr)
 static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	struct vdc_port *port = disk->private_data;
+	sector_t nsect = get_capacity(disk);
+	sector_t cylinders = nsect;
 
-	geo->heads = (u8) port->geom.num_hd;
-	geo->sectors = (u8) port->geom.num_sec;
-	geo->cylinders = port->geom.num_cyl;
+	geo->heads = 0xff;
+	geo->sectors = 0x3f;
+	sector_div(cylinders, geo->heads * geo->sectors);
+	geo->cylinders = cylinders;
+	if ((sector_t)(geo->cylinders + 1) * geo->heads * geo->sectors < nsect)
+		geo->cylinders = 0xffff;
 
 	return 0;
 }
 
+/* Add ioctl/CDROM_GET_CAPABILITY to support cdrom_id in udev
+ * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD.
+ * Needed to be able to install inside an ldom from an iso image.
+ */
+static int vdc_ioctl(struct block_device *bdev, fmode_t mode,
+		     unsigned command, unsigned long argument)
+{
+	int i;
+	struct gendisk *disk;
+
+	switch (command) {
+	case CDROMMULTISESSION:
+		pr_debug(PFX "Multisession CDs not supported\n");
+		for (i = 0; i < sizeof(struct cdrom_multisession); i++)
+			if (put_user(0, (char __user *)(argument + i)))
+				return -EFAULT;
+		return 0;
+
+	case CDROM_GET_CAPABILITY:
+		disk = bdev->bd_disk;
+
+		if (bdev->bd_disk && (disk->flags & GENHD_FL_CD))
+			return 0;
+		return -EINVAL;
+
+	default:
+		pr_debug(PFX "ioctl %08x not supported\n", command);
+		return -EINVAL;
+	}
+}
+
 static const struct block_device_operations vdc_fops = {
 	.owner		= THIS_MODULE,
 	.getgeo		= vdc_getgeo,
+	.ioctl		= vdc_ioctl,
 };
 
 static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for)
@@ -165,9 +209,9 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
 	struct vio_disk_attr_info *pkt = arg;
 
 	viodbg(HS, "GOT ATTR stype[0x%x] ops[%llx] disk_size[%llu] disk_type[%x] "
-	       "xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
+	       "mtype[0x%x] xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
 	       pkt->tag.stype, pkt->operations,
-	       pkt->vdisk_size, pkt->vdisk_type,
+	       pkt->vdisk_size, pkt->vdisk_type, pkt->vdisk_mtype,
 	       pkt->xfer_mode, pkt->vdisk_block_size,
 	       pkt->max_xfer_size);
 
@@ -192,8 +236,11 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
 		}
 
 		port->operations = pkt->operations;
-		port->vdisk_size = pkt->vdisk_size;
 		port->vdisk_type = pkt->vdisk_type;
+		if (vdc_version_supported(port, 1, 1)) {
+			port->vdisk_size = pkt->vdisk_size;
+			port->vdisk_mtype = pkt->vdisk_mtype;
+		}
 		if (pkt->max_xfer_size < port->max_xfer_size)
 			port->max_xfer_size = pkt->max_xfer_size;
 		port->vdisk_block_size = pkt->vdisk_block_size;
@@ -236,7 +283,9 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
 
 	__blk_end_request(req, (desc->status ? -EIO : 0), desc->size);
 
-	if (blk_queue_stopped(port->disk->queue))
+	/* restart blk queue when ring is half emptied */
+	if (blk_queue_stopped(port->disk->queue) &&
+	    vdc_tx_dring_avail(dr) * 100 / VDC_TX_RING_SIZE >= 50)
 		blk_start_queue(port->disk->queue);
 }
 
@@ -388,12 +437,6 @@ static int __send_request(struct request *req)
 	for (i = 0; i < nsg; i++)
 		len += sg[i].length;
 
-	if (unlikely(vdc_tx_dring_avail(dr) < 1)) {
-		blk_stop_queue(port->disk->queue);
-		err = -ENOMEM;
-		goto out;
-	}
-
 	desc = vio_dring_cur(dr);
 
 	err = ldc_map_sg(port->vio.lp, sg, nsg,
@@ -433,21 +476,32 @@ static int __send_request(struct request *req)
 		port->req_id++;
 		dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1);
 	}
-out:
 
 	return err;
 }
 
-static void do_vdc_request(struct request_queue *q)
+static void do_vdc_request(struct request_queue *rq)
 {
-	while (1) {
-		struct request *req = blk_fetch_request(q);
+	struct request *req;
 
-		if (!req)
-			break;
+	while ((req = blk_peek_request(rq)) != NULL) {
+		struct vdc_port *port;
+		struct vio_dring_state *dr;
+
+		port = req->rq_disk->private_data;
+		dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+		if (unlikely(vdc_tx_dring_avail(dr) < 1))
+			goto wait;
+
+		blk_start_request(req);
 
-		if (__send_request(req) < 0)
-			__blk_end_request_all(req, -EIO);
+		if (__send_request(req) < 0) {
+			blk_requeue_request(rq, req);
+wait:
+			/* Avoid pointless unplugs. */
+			blk_stop_queue(rq);
+			break;
+		}
 	}
 }
 
@@ -663,18 +717,27 @@ static int probe_disk(struct vdc_port *port)
 		return err;
 	}
 
-	err = generic_request(port, VD_OP_GET_DISKGEOM,
-			      &port->geom, sizeof(port->geom));
-	if (err < 0) {
-		printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
-		       "error %d\n", err);
-		return err;
+	if (vdc_version_supported(port, 1, 1)) {
+		/* vdisk_size should be set during the handshake, if it wasn't
+		 * then the underlying disk is reserved by another system
+		 */
+		if (port->vdisk_size == -1)
+			return -ENODEV;
+	} else {
+		struct vio_disk_geom geom;
+
+		err = generic_request(port, VD_OP_GET_DISKGEOM,
+				      &geom, sizeof(geom));
+		if (err < 0) {
+			printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
+			       "error %d\n", err);
+			return err;
+		}
+		port->vdisk_size = ((u64)geom.num_cyl *
+				    (u64)geom.num_hd *
+				    (u64)geom.num_sec);
 	}
 
-	port->vdisk_size = ((u64)port->geom.num_cyl *
-			    (u64)port->geom.num_hd *
-			    (u64)port->geom.num_sec);
-
 	q = blk_init_queue(do_vdc_request, &port->vio.lock);
 	if (!q) {
 		printk(KERN_ERR PFX "%s: Could not allocate queue.\n",
@@ -691,6 +754,10 @@ static int probe_disk(struct vdc_port *port)
 
 	port->disk = g;
 
+	/* Each segment in a request is up to an aligned page in size. */
+	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
+	blk_queue_max_segment_size(q, PAGE_SIZE);
+
 	blk_queue_max_segments(q, port->ring_cookies);
 	blk_queue_max_hw_sectors(q, port->max_xfer_size);
 	g->major = vdc_major;
@@ -704,9 +771,32 @@ static int probe_disk(struct vdc_port *port)
 
 	set_capacity(g, port->vdisk_size);
 
-	printk(KERN_INFO PFX "%s: %u sectors (%u MB)\n",
+	if (vdc_version_supported(port, 1, 1)) {
+		switch (port->vdisk_mtype) {
+		case VD_MEDIA_TYPE_CD:
+			pr_info(PFX "Virtual CDROM %s\n", port->disk_name);
+			g->flags |= GENHD_FL_CD;
+			g->flags |= GENHD_FL_REMOVABLE;
+			set_disk_ro(g, 1);
+			break;
+
+		case VD_MEDIA_TYPE_DVD:
+			pr_info(PFX "Virtual DVD %s\n", port->disk_name);
+			g->flags |= GENHD_FL_CD;
+			g->flags |= GENHD_FL_REMOVABLE;
+			set_disk_ro(g, 1);
+			break;
+
+		case VD_MEDIA_TYPE_FIXED:
+			pr_info(PFX "Virtual Hard disk %s\n", port->disk_name);
+			break;
+		}
+	}
+
+	pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n",
 	       g->disk_name,
-	       port->vdisk_size, (port->vdisk_size >> (20 - 9)));
+	       port->vdisk_size, (port->vdisk_size >> (20 - 9)),
+	       port->vio.ver.major, port->vio.ver.minor);
 
 	add_disk(g);
 
@@ -765,6 +855,7 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	else
 		snprintf(port->disk_name, sizeof(port->disk_name),
 			 VDCBLK_NAME "%c", 'a' + ((int)vdev->dev_no % 26));
+	port->vdisk_size = -1;
 
 	err = vio_driver_init(&port->vio, vdev, VDEV_DISK,
 			      vdc_versions, ARRAY_SIZE(vdc_versions),
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index d5e2d12b9d9e..5d552857de41 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -568,7 +568,7 @@ static struct carm_request *carm_get_special(struct carm_host *host)
 		return NULL;
 
 	rq = blk_get_request(host->oob_q, WRITE /* bogus */, GFP_KERNEL);
-	if (!rq) {
+	if (IS_ERR(rq)) {
 		spin_lock_irqsave(&host->lock, flags);
 		carm_put_request(host, crq);
 		spin_unlock_irqrestore(&host->lock, flags);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 0a581400de0f..c6a27d54ad62 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -41,12 +41,6 @@ struct virtio_blk
 	/* Process context for config space updates */
 	struct work_struct config_work;
 
-	/* Lock for config space updates */
-	struct mutex config_lock;
-
-	/* enable config space updates */
-	bool config_enable;
-
 	/* What host tells us, plus 2 for header & tailer. */
 	unsigned int sg_elems;
 
@@ -135,7 +129,7 @@ static inline void virtblk_request_done(struct request *req)
 		req->errors = (error != 0);
 	}
 
-	blk_mq_end_io(req, error);
+	blk_mq_end_request(req, error);
 }
 
 static void virtblk_done(struct virtqueue *vq)
@@ -164,14 +158,14 @@ static void virtblk_done(struct virtqueue *vq)
 	spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
 }
 
-static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
+static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
+		bool last)
 {
 	struct virtio_blk *vblk = hctx->queue->queuedata;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 	unsigned long flags;
 	unsigned int num;
 	int qid = hctx->queue_num;
-	const bool last = (req->cmd_flags & REQ_END) != 0;
 	int err;
 	bool notify = false;
 
@@ -205,6 +199,8 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 		}
 	}
 
+	blk_mq_start_request(req);
+
 	num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
 	if (num) {
 		if (rq_data_dir(vbr->req) == WRITE)
@@ -347,10 +343,6 @@ static void virtblk_config_changed_work(struct work_struct *work)
 	char *envp[] = { "RESIZE=1", NULL };
 	u64 capacity, size;
 
-	mutex_lock(&vblk->config_lock);
-	if (!vblk->config_enable)
-		goto done;
-
 	/* Host must always specify the capacity. */
 	virtio_cread(vdev, struct virtio_blk_config, capacity, &capacity);
 
@@ -374,8 +366,6 @@ static void virtblk_config_changed_work(struct work_struct *work)
 	set_capacity(vblk->disk, capacity);
 	revalidate_disk(vblk->disk);
 	kobject_uevent_env(&disk_to_dev(vblk->disk)->kobj, KOBJ_CHANGE, envp);
-done:
-	mutex_unlock(&vblk->config_lock);
 }
 
 static void virtblk_config_changed(struct virtio_device *vdev)
@@ -606,10 +596,8 @@ static int virtblk_probe(struct virtio_device *vdev)
 
 	vblk->vdev = vdev;
 	vblk->sg_elems = sg_elems;
-	mutex_init(&vblk->config_lock);
 
 	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
-	vblk->config_enable = true;
 
 	err = init_vq(vblk);
 	if (err)
@@ -733,6 +721,8 @@ static int virtblk_probe(struct virtio_device *vdev)
 	if (!err && opt_io_size)
 		blk_queue_io_opt(q, blk_size * opt_io_size);
 
+	virtio_device_ready(vdev);
+
 	add_disk(vblk->disk);
 	err = device_create_file(disk_to_dev(vblk->disk), &dev_attr_serial);
 	if (err)
@@ -771,10 +761,8 @@ static void virtblk_remove(struct virtio_device *vdev)
 	int index = vblk->index;
 	int refc;
 
-	/* Prevent config work handler from accessing the device. */
-	mutex_lock(&vblk->config_lock);
-	vblk->config_enable = false;
-	mutex_unlock(&vblk->config_lock);
+	/* Make sure no work handler is accessing the device. */
+	flush_work(&vblk->config_work);
 
 	del_gendisk(vblk->disk);
 	blk_cleanup_queue(vblk->disk->queue);
@@ -784,8 +772,6 @@ static void virtblk_remove(struct virtio_device *vdev)
 	/* Stop all the virtqueues. */
 	vdev->config->reset(vdev);
 
-	flush_work(&vblk->config_work);
-
 	refc = atomic_read(&disk_to_dev(vblk->disk)->kobj.kref.refcount);
 	put_disk(vblk->disk);
 	vdev->config->del_vqs(vdev);
@@ -805,11 +791,7 @@ static int virtblk_freeze(struct virtio_device *vdev)
 	/* Ensure we don't receive any more interrupts */
 	vdev->config->reset(vdev);
 
-	/* Prevent config work handler from accessing the device. */
-	mutex_lock(&vblk->config_lock);
-	vblk->config_enable = false;
-	mutex_unlock(&vblk->config_lock);
-
+	/* Make sure no work handler is accessing the device. */
 	flush_work(&vblk->config_work);
 
 	blk_mq_stop_hw_queues(vblk->disk->queue);
@@ -823,12 +805,14 @@ static int virtblk_restore(struct virtio_device *vdev)
 	struct virtio_blk *vblk = vdev->priv;
 	int ret;
 
-	vblk->config_enable = true;
 	ret = init_vq(vdev->priv);
-	if (!ret)
-		blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);
+	if (ret)
+		return ret;
+
+	virtio_device_ready(vdev);
 
-	return ret;
+	blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);
+	return 0;
 }
 #endif
 
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 64c60edcdfbc..63fc7f06a014 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -763,6 +763,7 @@ again:
 			BUG_ON(new_map_idx >= segs_to_map);
 			if (unlikely(map[new_map_idx].status != 0)) {
 				pr_debug(DRV_PFX "invalid buffer -- could not remap it\n");
+				put_free_pages(blkif, &pages[seg_idx]->page, 1);
 				pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE;
 				ret |= 1;
 				goto next;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 3a8b810b4980..630a489e757d 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -270,6 +270,9 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif)
 		blkif->blk_rings.common.sring = NULL;
 	}
 
+	/* Remove all persistent grants and the cache of ballooned pages. */
+	xen_blkbk_free_caches(blkif);
+
 	return 0;
 }
 
@@ -281,9 +284,6 @@ static void xen_blkif_free(struct xen_blkif *blkif)
 	xen_blkif_disconnect(blkif);
 	xen_vbd_free(&blkif->vbd);
 
-	/* Remove all persistent grants and the cache of ballooned pages. */
-	xen_blkbk_free_caches(blkif);
-
 	/* Make sure everything is drained before shutting down */
 	BUG_ON(blkif->persistent_gnt_c != 0);
 	BUG_ON(atomic_read(&blkif->persistent_gnt_in_use) != 0);
@@ -907,22 +907,17 @@ static int connect_ring(struct backend_info *be)
 	return 0;
 }
 
-
-/* ** Driver Registration ** */
-
-
 static const struct xenbus_device_id xen_blkbk_ids[] = {
 	{ "vbd" },
 	{ "" }
 };
 
-
-static DEFINE_XENBUS_DRIVER(xen_blkbk, ,
+static struct xenbus_driver xen_blkbk_driver = {
+	.ids  = xen_blkbk_ids,
 	.probe = xen_blkbk_probe,
 	.remove = xen_blkbk_remove,
 	.otherend_changed = frontend_changed
-);
-
+};
 
 int xen_blkif_xenbus_init(void)
 {
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 5deb235bd18f..5ac312f6e0be 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -582,6 +582,14 @@ static inline void flush_requests(struct blkfront_info *info)
 		notify_remote_via_irq(info->irq);
 }
 
+static inline bool blkif_request_flush_valid(struct request *req,
+					     struct blkfront_info *info)
+{
+	return ((req->cmd_type != REQ_TYPE_FS) ||
+		((req->cmd_flags & (REQ_FLUSH | REQ_FUA)) &&
+		!info->flush_op));
+}
+
 /*
  * do_blkif_request
  *  read a block; request is in a request queue
@@ -604,9 +612,7 @@ static void do_blkif_request(struct request_queue *rq)
 
 		blk_start_request(req);
 
-		if ((req->cmd_type != REQ_TYPE_FS) ||
-		    ((req->cmd_flags & (REQ_FLUSH | REQ_FUA)) &&
-		    !info->flush_op)) {
+		if (blkif_request_flush_valid(req, info)) {
 			__blk_end_request_all(req, -EIO);
 			continue;
 		}
@@ -2055,13 +2061,14 @@ static const struct xenbus_device_id blkfront_ids[] = {
 	{ "" }
 };
 
-static DEFINE_XENBUS_DRIVER(blkfront, ,
+static struct xenbus_driver blkfront_driver = {
+	.ids  = blkfront_ids,
 	.probe = blkfront_probe,
 	.remove = blkfront_remove,
 	.resume = blkfront_resume,
 	.otherend_changed = blkback_changed,
 	.is_ready = blkfront_is_ready,
-);
+};
 
 static int __init xlblk_init(void)
 {
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index d00831c3d731..0e63e8aa8279 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -103,10 +103,10 @@ static ssize_t mem_used_total_show(struct device *dev,
 
 	down_read(&zram->init_lock);
 	if (init_done(zram))
-		val = zs_get_total_size_bytes(meta->mem_pool);
+		val = zs_get_total_pages(meta->mem_pool);
 	up_read(&zram->init_lock);
 
-	return scnprintf(buf, PAGE_SIZE, "%llu\n", val);
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
 }
 
 static ssize_t max_comp_streams_show(struct device *dev,
@@ -122,6 +122,72 @@ static ssize_t max_comp_streams_show(struct device *dev,
 	return scnprintf(buf, PAGE_SIZE, "%d\n", val);
 }
 
+static ssize_t mem_limit_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	u64 val;
+	struct zram *zram = dev_to_zram(dev);
+
+	down_read(&zram->init_lock);
+	val = zram->limit_pages;
+	up_read(&zram->init_lock);
+
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t mem_limit_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	u64 limit;
+	char *tmp;
+	struct zram *zram = dev_to_zram(dev);
+
+	limit = memparse(buf, &tmp);
+	if (buf == tmp) /* no chars parsed, invalid input */
+		return -EINVAL;
+
+	down_write(&zram->init_lock);
+	zram->limit_pages = PAGE_ALIGN(limit) >> PAGE_SHIFT;
+	up_write(&zram->init_lock);
+
+	return len;
+}
+
+static ssize_t mem_used_max_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	u64 val = 0;
+	struct zram *zram = dev_to_zram(dev);
+
+	down_read(&zram->init_lock);
+	if (init_done(zram))
+		val = atomic_long_read(&zram->stats.max_used_pages);
+	up_read(&zram->init_lock);
+
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t mem_used_max_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	int err;
+	unsigned long val;
+	struct zram *zram = dev_to_zram(dev);
+	struct zram_meta *meta = zram->meta;
+
+	err = kstrtoul(buf, 10, &val);
+	if (err || val != 0)
+		return -EINVAL;
+
+	down_read(&zram->init_lock);
+	if (init_done(zram))
+		atomic_long_set(&zram->stats.max_used_pages,
+				zs_get_total_pages(meta->mem_pool));
+	up_read(&zram->init_lock);
+
+	return len;
+}
+
 static ssize_t max_comp_streams_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
@@ -434,6 +500,21 @@ out_cleanup:
 	return ret;
 }
 
+static inline void update_used_max(struct zram *zram,
+					const unsigned long pages)
+{
+	int old_max, cur_max;
+
+	old_max = atomic_long_read(&zram->stats.max_used_pages);
+
+	do {
+		cur_max = old_max;
+		if (pages > cur_max)
+			old_max = atomic_long_cmpxchg(
+				&zram->stats.max_used_pages, cur_max, pages);
+	} while (old_max != cur_max);
+}
+
 static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 			   int offset)
 {
@@ -445,6 +526,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	struct zram_meta *meta = zram->meta;
 	struct zcomp_strm *zstrm;
 	bool locked = false;
+	unsigned long alloced_pages;
 
 	page = bvec->bv_page;
 	if (is_partial_io(bvec)) {
@@ -513,6 +595,16 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		ret = -ENOMEM;
 		goto out;
 	}
+
+	alloced_pages = zs_get_total_pages(meta->mem_pool);
+	if (zram->limit_pages && alloced_pages > zram->limit_pages) {
+		zs_free(meta->mem_pool, handle);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	update_used_max(zram, alloced_pages);
+
 	cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
 
 	if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
@@ -606,6 +698,7 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 		bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 		zram_free_page(zram, index);
 		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+		atomic64_inc(&zram->stats.notify_free);
 		index++;
 		n -= PAGE_SIZE;
 	}
@@ -617,6 +710,9 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity)
 	struct zram_meta *meta;
 
 	down_write(&zram->init_lock);
+
+	zram->limit_pages = 0;
+
 	if (!init_done(zram)) {
 		up_write(&zram->init_lock);
 		return;
@@ -857,6 +953,10 @@ static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
 static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
 static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
 static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
+static DEVICE_ATTR(mem_limit, S_IRUGO | S_IWUSR, mem_limit_show,
+		mem_limit_store);
+static DEVICE_ATTR(mem_used_max, S_IRUGO | S_IWUSR, mem_used_max_show,
+		mem_used_max_store);
 static DEVICE_ATTR(max_comp_streams, S_IRUGO | S_IWUSR,
 		max_comp_streams_show, max_comp_streams_store);
 static DEVICE_ATTR(comp_algorithm, S_IRUGO | S_IWUSR,
@@ -885,6 +985,8 @@ static struct attribute *zram_disk_attrs[] = {
 	&dev_attr_orig_data_size.attr,
 	&dev_attr_compr_data_size.attr,
 	&dev_attr_mem_used_total.attr,
+	&dev_attr_mem_limit.attr,
+	&dev_attr_mem_used_max.attr,
 	&dev_attr_max_comp_streams.attr,
 	&dev_attr_comp_algorithm.attr,
 	NULL,
@@ -929,6 +1031,7 @@ static int create_device(struct zram *zram, int device_id)
 	set_capacity(zram->disk, 0);
 	/* zram devices sort of resembles non-rotational disks */
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
+	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue);
 	/*
 	 * To ensure that we always get PAGE_SIZE aligned
 	 * and n*PAGE_SIZED sized I/O requests.
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index e0f725c87cc6..c6ee271317f5 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -90,6 +90,7 @@ struct zram_stats {
 	atomic64_t notify_free;	/* no. of swap slot free notifications */
 	atomic64_t zero_pages;		/* no. of zero filled pages */
 	atomic64_t pages_stored;	/* no. of pages currently stored */
+	atomic_long_t max_used_pages;	/* no. of maximum pages stored */
 };
 
 struct zram_meta {
@@ -112,6 +113,11 @@ struct zram {
 	u64 disksize;	/* bytes */
 	int max_comp_streams;
 	struct zram_stats stats;
+	/*
+	 * the number of pages zram can consume for storing compressed data
+	 */
+	unsigned long limit_pages;
+
 	char compressor[10];
 };
 #endif
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index 5bb5872ffee6..6653473f2757 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -160,13 +160,11 @@ static int vhci_create_device(struct vhci_data *data, __u8 opcode)
 }
 
 static inline ssize_t vhci_get_user(struct vhci_data *data,
-				    const struct iovec *iov,
-				    unsigned long count)
+				    struct iov_iter *from)
 {
-	size_t len = iov_length(iov, count);
+	size_t len = iov_iter_count(from);
 	struct sk_buff *skb;
 	__u8 pkt_type, opcode;
-	unsigned long i;
 	int ret;
 
 	if (len < 2 || len > HCI_MAX_FRAME_SIZE)
@@ -176,12 +174,9 @@ static inline ssize_t vhci_get_user(struct vhci_data *data,
 	if (!skb)
 		return -ENOMEM;
 
-	for (i = 0; i < count; i++) {
-		if (copy_from_user(skb_put(skb, iov[i].iov_len),
-				   iov[i].iov_base, iov[i].iov_len)) {
-			kfree_skb(skb);
-			return -EFAULT;
-		}
+	if (copy_from_iter(skb_put(skb, len), len, from) != len) {
+		kfree_skb(skb);
+		return -EFAULT;
 	}
 
 	pkt_type = *((__u8 *) skb->data);
@@ -294,13 +289,12 @@ static ssize_t vhci_read(struct file *file,
 	return ret;
 }
 
-static ssize_t vhci_write(struct kiocb *iocb, const struct iovec *iov,
-			  unsigned long count, loff_t pos)
+static ssize_t vhci_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct vhci_data *data = file->private_data;
 
-	return vhci_get_user(data, iov, count);
+	return vhci_get_user(data, from);
 }
 
 static unsigned int vhci_poll(struct file *file, poll_table *wait)
@@ -365,7 +359,7 @@ static int vhci_release(struct inode *inode, struct file *file)
 static const struct file_operations vhci_fops = {
 	.owner		= THIS_MODULE,
 	.read		= vhci_read,
-	.aio_write	= vhci_write,
+	.write_iter	= vhci_write,
 	.poll		= vhci_poll,
 	.open		= vhci_open,
 	.release	= vhci_release,
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 898b84bba28a..5d28a45d2960 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2180,8 +2180,8 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 		len = nr * CD_FRAMESIZE_RAW;
 
 		rq = blk_get_request(q, READ, GFP_KERNEL);
-		if (!rq) {
-			ret = -ENOMEM;
+		if (IS_ERR(rq)) {
+			ret = PTR_ERR(rq);
 			break;
 		}
 		blk_rq_set_block_pc(rq);
diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c
index 132c9ccfdc62..72295ea2fd1c 100644
--- a/drivers/char/hw_random/virtio-rng.c
+++ b/drivers/char/hw_random/virtio-rng.c
@@ -109,8 +109,8 @@ static int probe_common(struct virtio_device *vdev)
 
 	vi->index = index = ida_simple_get(&rng_index_ida, 0, 0, GFP_KERNEL);
 	if (index < 0) {
-		kfree(vi);
-		return index;
+		err = index;
+		goto err_ida;
 	}
 	sprintf(vi->name, "virtio_rng.%d", index);
 	init_completion(&vi->have_data);
@@ -128,13 +128,16 @@ static int probe_common(struct virtio_device *vdev)
 	vi->vq = virtio_find_single_vq(vdev, random_recv_done, "input");
 	if (IS_ERR(vi->vq)) {
 		err = PTR_ERR(vi->vq);
-		vi->vq = NULL;
-		kfree(vi);
-		ida_simple_remove(&rng_index_ida, index);
-		return err;
+		goto err_find;
 	}
 
 	return 0;
+
+err_find:
+	ida_simple_remove(&rng_index_ida, index);
+err_ida:
+	kfree(vi);
+	return err;
 }
 
 static void remove_common(struct virtio_device *vdev)
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 917403fe10da..524b707894ef 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -622,53 +622,23 @@ static ssize_t splice_write_null(struct pipe_inode_info *pipe, struct file *out,
 	return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_null);
 }
 
-static ssize_t read_zero(struct file *file, char __user *buf,
-			 size_t count, loff_t *ppos)
+static ssize_t read_iter_zero(struct kiocb *iocb, struct iov_iter *iter)
 {
-	size_t written;
-
-	if (!count)
-		return 0;
-
-	if (!access_ok(VERIFY_WRITE, buf, count))
-		return -EFAULT;
-
-	written = 0;
-	while (count) {
-		unsigned long unwritten;
-		size_t chunk = count;
+	size_t written = 0;
 
+	while (iov_iter_count(iter)) {
+		size_t chunk = iov_iter_count(iter), n;
 		if (chunk > PAGE_SIZE)
 			chunk = PAGE_SIZE;	/* Just for latency reasons */
-		unwritten = __clear_user(buf, chunk);
-		written += chunk - unwritten;
-		if (unwritten)
-			break;
+		n = iov_iter_zero(chunk, iter);
+		if (!n && iov_iter_count(iter))
+			return written ? written : -EFAULT;
+		written += n;
 		if (signal_pending(current))
 			return written ? written : -ERESTARTSYS;
-		buf += chunk;
-		count -= chunk;
 		cond_resched();
 	}
-	return written ? written : -EFAULT;
-}
-
-static ssize_t aio_read_zero(struct kiocb *iocb, const struct iovec *iov,
-			     unsigned long nr_segs, loff_t pos)
-{
-	size_t written = 0;
-	unsigned long i;
-	ssize_t ret;
-
-	for (i = 0; i < nr_segs; i++) {
-		ret = read_zero(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len,
-				&pos);
-		if (ret < 0)
-			break;
-		written += ret;
-	}
-
-	return written ? written : -EFAULT;
+	return written;
 }
 
 static int mmap_zero(struct file *file, struct vm_area_struct *vma)
@@ -738,7 +708,6 @@ static int open_port(struct inode *inode, struct file *filp)
 #define zero_lseek	null_lseek
 #define full_lseek      null_lseek
 #define write_zero	write_null
-#define read_full       read_zero
 #define aio_write_zero	aio_write_null
 #define open_mem	open_port
 #define open_kmem	open_mem
@@ -783,9 +752,9 @@ static const struct file_operations port_fops = {
 
 static const struct file_operations zero_fops = {
 	.llseek		= zero_lseek,
-	.read		= read_zero,
+	.read		= new_sync_read,
 	.write		= write_zero,
-	.aio_read	= aio_read_zero,
+	.read_iter	= read_iter_zero,
 	.aio_write	= aio_write_zero,
 	.mmap		= mmap_zero,
 };
@@ -802,7 +771,8 @@ static struct backing_dev_info zero_bdi = {
 
 static const struct file_operations full_fops = {
 	.llseek		= full_lseek,
-	.read		= read_full,
+	.read		= new_sync_read,
+	.read_iter	= read_iter_zero,
 	.write		= write_full,
 };
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index c18d41db83d8..82759cef9043 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -874,7 +874,7 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
 void add_interrupt_randomness(int irq, int irq_flags)
 {
 	struct entropy_store	*r;
-	struct fast_pool	*fast_pool = &__get_cpu_var(irq_randomness);
+	struct fast_pool	*fast_pool = this_cpu_ptr(&irq_randomness);
 	struct pt_regs		*regs = get_irq_regs();
 	unsigned long		now = jiffies;
 	cycles_t		cycles = random_get_entropy();
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
index 2064b4527040..441b44e54226 100644
--- a/drivers/char/tpm/xen-tpmfront.c
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -367,12 +367,13 @@ static const struct xenbus_device_id tpmfront_ids[] = {
 };
 MODULE_ALIAS("xen:vtpm");
 
-static DEFINE_XENBUS_DRIVER(tpmfront, ,
-		.probe = tpmfront_probe,
-		.remove = tpmfront_remove,
-		.resume = tpmfront_resume,
-		.otherend_changed = backend_changed,
-	);
+static struct xenbus_driver tpmfront_driver = {
+	.ids = tpmfront_ids,
+	.probe = tpmfront_probe,
+	.remove = tpmfront_remove,
+	.resume = tpmfront_resume,
+	.otherend_changed = backend_changed,
+};
 
 static int __init xen_tpmfront_init(void)
 {
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index b585b4789822..bfa640023e64 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1449,6 +1449,8 @@ static int add_port(struct ports_device *portdev, u32 id)
 	spin_lock_init(&port->outvq_lock);
 	init_waitqueue_head(&port->waitqueue);
 
+	virtio_device_ready(portdev->vdev);
+
 	/* Fill the in_vq with buffers so the host can send us data. */
 	nr_added_bufs = fill_queue(port->in_vq, &port->inbuf_lock);
 	if (!nr_added_bufs) {
@@ -2182,6 +2184,8 @@ static int virtcons_restore(struct virtio_device *vdev)
 	if (ret)
 		return ret;
 
+	virtio_device_ready(portdev->vdev);
+
 	if (use_multiport(portdev))
 		fill_queue(portdev->c_ivq, &portdev->c_ivq_lock);
 
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index cfd3af7b2cbd..455fd17d938e 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -32,12 +32,32 @@ config COMMON_CLK_WM831X
 
 source "drivers/clk/versatile/Kconfig"
 
+config COMMON_CLK_MAX_GEN
+        bool
+
 config COMMON_CLK_MAX77686
 	tristate "Clock driver for Maxim 77686 MFD"
 	depends on MFD_MAX77686
+	select COMMON_CLK_MAX_GEN
 	---help---
 	  This driver supports Maxim 77686 crystal oscillator clock. 
 
+config COMMON_CLK_MAX77802
+	tristate "Clock driver for Maxim 77802 PMIC"
+	depends on MFD_MAX77686
+	select COMMON_CLK_MAX_GEN
+	---help---
+	  This driver supports Maxim 77802 crystal oscillator clock.
+
+config COMMON_CLK_RK808
+	tristate "Clock driver for RK808"
+	depends on MFD_RK808
+	---help---
+	  This driver supports RK808 crystal oscillator clock. These
+	  multi-function devices have two fixed-rate oscillators,
+	  clocked at 32KHz each. Clkout1 is always on, Clkout2 can off
+	  by control register.
+
 config COMMON_CLK_SI5351
 	tristate "Clock driver for SiLabs 5351A/B/C"
 	depends on I2C
@@ -109,6 +129,11 @@ config COMMON_CLK_PALMAS
 	  This driver supports TI Palmas devices 32KHz output KG and KG_AUDIO
 	  using common clock framework.
 
+config COMMON_CLK_PXA
+	def_bool COMMON_CLK && ARCH_PXA
+	---help---
+	  Sypport for the Marvell PXA SoC.
+
 source "drivers/clk/qcom/Kconfig"
 
 endmenu
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index f537a0b1f798..d5fba5bc6e1b 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_COMMON_CLK)	+= clk-gate.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-mux.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-composite.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-fractional-divider.o
+obj-$(CONFIG_COMMON_CLK)	+= clk-gpio-gate.o
 ifeq ($(CONFIG_OF), y)
 obj-$(CONFIG_COMMON_CLK)	+= clk-conf.o
 endif
@@ -22,12 +23,15 @@ obj-$(CONFIG_ARCH_CLPS711X)		+= clk-clps711x.o
 obj-$(CONFIG_ARCH_EFM32)		+= clk-efm32gg.o
 obj-$(CONFIG_ARCH_HIGHBANK)		+= clk-highbank.o
 obj-$(CONFIG_MACH_LOONGSON1)		+= clk-ls1x.o
+obj-$(CONFIG_COMMON_CLK_MAX_GEN)	+= clk-max-gen.o
 obj-$(CONFIG_COMMON_CLK_MAX77686)	+= clk-max77686.o
+obj-$(CONFIG_COMMON_CLK_MAX77802)	+= clk-max77802.o
 obj-$(CONFIG_ARCH_MOXART)		+= clk-moxart.o
 obj-$(CONFIG_ARCH_NOMADIK)		+= clk-nomadik.o
 obj-$(CONFIG_ARCH_NSPIRE)		+= clk-nspire.o
 obj-$(CONFIG_COMMON_CLK_PALMAS)		+= clk-palmas.o
 obj-$(CONFIG_CLK_PPC_CORENET)		+= clk-ppc-corenet.o
+obj-$(CONFIG_COMMON_CLK_RK808)		+= clk-rk808.o
 obj-$(CONFIG_COMMON_CLK_S2MPS11)	+= clk-s2mps11.o
 obj-$(CONFIG_COMMON_CLK_SI5351)		+= clk-si5351.o
 obj-$(CONFIG_COMMON_CLK_SI570)		+= clk-si570.o
@@ -48,6 +52,7 @@ obj-$(CONFIG_ARCH_MMP)			+= mmp/
 endif
 obj-$(CONFIG_PLAT_ORION)		+= mvebu/
 obj-$(CONFIG_ARCH_MXS)			+= mxs/
+obj-$(CONFIG_COMMON_CLK_PXA)		+= pxa/
 obj-$(CONFIG_COMMON_CLK_QCOM)		+= qcom/
 obj-$(CONFIG_ARCH_ROCKCHIP)		+= rockchip/
 obj-$(CONFIG_COMMON_CLK_SAMSUNG)	+= samsung/
diff --git a/drivers/clk/at91/clk-pll.c b/drivers/clk/at91/clk-pll.c
index cf6ed023504c..6ec79dbc0840 100644
--- a/drivers/clk/at91/clk-pll.c
+++ b/drivers/clk/at91/clk-pll.c
@@ -15,6 +15,7 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/io.h>
+#include <linux/kernel.h>
 #include <linux/wait.h>
 #include <linux/sched.h>
 #include <linux/interrupt.h>
@@ -29,9 +30,12 @@
 #define PLL_DIV(reg)		((reg) & PLL_DIV_MASK)
 #define PLL_MUL(reg, layout)	(((reg) >> (layout)->mul_shift) & \
 				 (layout)->mul_mask)
+#define PLL_MUL_MIN		2
+#define PLL_MUL_MASK(layout)	((layout)->mul_mask)
+#define PLL_MUL_MAX(layout)	(PLL_MUL_MASK(layout) + 1)
 #define PLL_ICPR_SHIFT(id)	((id) * 16)
 #define PLL_ICPR_MASK(id)	(0xffff << PLL_ICPR_SHIFT(id))
-#define PLL_MAX_COUNT		0x3ff
+#define PLL_MAX_COUNT		0x3f
 #define PLL_COUNT_SHIFT		8
 #define PLL_OUT_SHIFT		14
 #define PLL_MAX_ID		1
@@ -147,115 +151,113 @@ static unsigned long clk_pll_recalc_rate(struct clk_hw *hw,
 					 unsigned long parent_rate)
 {
 	struct clk_pll *pll = to_clk_pll(hw);
-	const struct clk_pll_layout *layout = pll->layout;
-	struct at91_pmc *pmc = pll->pmc;
-	int offset = PLL_REG(pll->id);
-	u32 tmp = pmc_read(pmc, offset) & layout->pllr_mask;
-	u8 div = PLL_DIV(tmp);
-	u16 mul = PLL_MUL(tmp, layout);
-	if (!div || !mul)
+
+	if (!pll->div || !pll->mul)
 		return 0;
 
-	return (parent_rate * (mul + 1)) / div;
+	return (parent_rate / pll->div) * (pll->mul + 1);
 }
 
 static long clk_pll_get_best_div_mul(struct clk_pll *pll, unsigned long rate,
 				     unsigned long parent_rate,
 				     u32 *div, u32 *mul,
 				     u32 *index) {
-	unsigned long maxrate;
-	unsigned long minrate;
-	unsigned long divrate;
-	unsigned long bestdiv = 1;
-	unsigned long bestmul;
-	unsigned long tmpdiv;
-	unsigned long roundup;
-	unsigned long rounddown;
-	unsigned long remainder;
-	unsigned long bestremainder;
-	unsigned long maxmul;
-	unsigned long maxdiv;
-	unsigned long mindiv;
-	int i = 0;
 	const struct clk_pll_layout *layout = pll->layout;
 	const struct clk_pll_characteristics *characteristics =
 							pll->characteristics;
+	unsigned long bestremainder = ULONG_MAX;
+	unsigned long maxdiv, mindiv, tmpdiv;
+	long bestrate = -ERANGE;
+	unsigned long bestdiv;
+	unsigned long bestmul;
+	int i = 0;
 
-	/* Minimum divider = 1 */
-	/* Maximum multiplier = max_mul */
-	maxmul = layout->mul_mask + 1;
-	maxrate = (parent_rate * maxmul) / 1;
-
-	/* Maximum divider = max_div */
-	/* Minimum multiplier = 2 */
-	maxdiv = PLL_DIV_MAX;
-	minrate = (parent_rate * 2) / maxdiv;
-
+	/* Check if parent_rate is a valid input rate */
 	if (parent_rate < characteristics->input.min ||
-	    parent_rate < characteristics->input.max)
-		return -ERANGE;
-
-	if (parent_rate < minrate || parent_rate > maxrate)
+	    parent_rate > characteristics->input.max)
 		return -ERANGE;
 
-	for (i = 0; i < characteristics->num_output; i++) {
-		if (parent_rate >= characteristics->output[i].min &&
-		    parent_rate <= characteristics->output[i].max)
-			break;
-	}
-
-	if (i >= characteristics->num_output)
-		return -ERANGE;
-
-	bestmul = rate / parent_rate;
-	rounddown = parent_rate % rate;
-	roundup = rate - rounddown;
-	bestremainder = roundup < rounddown ? roundup : rounddown;
-
-	if (!bestremainder) {
-		if (div)
-			*div = bestdiv;
-		if (mul)
-			*mul = bestmul;
-		if (index)
-			*index = i;
-		return rate;
-	}
-
-	maxdiv = 255 / (bestmul + 1);
-	if (parent_rate / maxdiv < characteristics->input.min)
-		maxdiv = parent_rate / characteristics->input.min;
-	mindiv = parent_rate / characteristics->input.max;
-	if (parent_rate % characteristics->input.max)
-		mindiv++;
-
-	for (tmpdiv = mindiv; tmpdiv < maxdiv; tmpdiv++) {
-		divrate = parent_rate / tmpdiv;
-
-		rounddown = rate % divrate;
-		roundup = divrate - rounddown;
-		remainder = roundup < rounddown ? roundup : rounddown;
-
+	/*
+	 * Calculate minimum divider based on the minimum multiplier, the
+	 * parent_rate and the requested rate.
+	 * Should always be 2 according to the input and output characteristics
+	 * of the PLL blocks.
+	 */
+	mindiv = (parent_rate * PLL_MUL_MIN) / rate;
+	if (!mindiv)
+		mindiv = 1;
+
+	/*
+	 * Calculate the maximum divider which is limited by PLL register
+	 * layout (limited by the MUL or DIV field size).
+	 */
+	maxdiv = DIV_ROUND_UP(parent_rate * PLL_MUL_MAX(layout), rate);
+	if (maxdiv > PLL_DIV_MAX)
+		maxdiv = PLL_DIV_MAX;
+
+	/*
+	 * Iterate over the acceptable divider values to find the best
+	 * divider/multiplier pair (the one that generates the closest
+	 * rate to the requested one).
+	 */
+	for (tmpdiv = mindiv; tmpdiv <= maxdiv; tmpdiv++) {
+		unsigned long remainder;
+		unsigned long tmprate;
+		unsigned long tmpmul;
+
+		/*
+		 * Calculate the multiplier associated with the current
+		 * divider that provide the closest rate to the requested one.
+		 */
+		tmpmul = DIV_ROUND_CLOSEST(rate, parent_rate / tmpdiv);
+		tmprate = (parent_rate / tmpdiv) * tmpmul;
+		if (tmprate > rate)
+			remainder = tmprate - rate;
+		else
+			remainder = rate - tmprate;
+
+		/*
+		 * Compare the remainder with the best remainder found until
+		 * now and elect a new best multiplier/divider pair if the
+		 * current remainder is smaller than the best one.
+		 */
 		if (remainder < bestremainder) {
 			bestremainder = remainder;
-			bestmul = rate / divrate;
 			bestdiv = tmpdiv;
+			bestmul = tmpmul;
+			bestrate = tmprate;
 		}
 
+		/*
+		 * We've found a perfect match!
+		 * Stop searching now and use this multiplier/divider pair.
+		 */
 		if (!remainder)
 			break;
 	}
 
-	rate = (parent_rate / bestdiv) * bestmul;
+	/* We haven't found any multiplier/divider pair => return -ERANGE */
+	if (bestrate < 0)
+		return bestrate;
+
+	/* Check if bestrate is a valid output rate  */
+	for (i = 0; i < characteristics->num_output; i++) {
+		if (bestrate >= characteristics->output[i].min &&
+		    bestrate <= characteristics->output[i].max)
+			break;
+	}
+
+	if (i >= characteristics->num_output)
+		return -ERANGE;
 
 	if (div)
 		*div = bestdiv;
 	if (mul)
-		*mul = bestmul;
+		*mul = bestmul - 1;
 	if (index)
 		*index = i;
 
-	return rate;
+	return bestrate;
 }
 
 static long clk_pll_round_rate(struct clk_hw *hw, unsigned long rate,
diff --git a/drivers/clk/at91/clk-usb.c b/drivers/clk/at91/clk-usb.c
index 7d1d26a4bd04..24b5b020753a 100644
--- a/drivers/clk/at91/clk-usb.c
+++ b/drivers/clk/at91/clk-usb.c
@@ -238,16 +238,22 @@ static long at91rm9200_clk_usb_round_rate(struct clk_hw *hw, unsigned long rate,
 					  unsigned long *parent_rate)
 {
 	struct at91rm9200_clk_usb *usb = to_at91rm9200_clk_usb(hw);
+	struct clk *parent = __clk_get_parent(hw->clk);
 	unsigned long bestrate = 0;
 	int bestdiff = -1;
 	unsigned long tmprate;
 	int tmpdiff;
 	int i = 0;
 
-	for (i = 0; i < 4; i++) {
+	for (i = 0; i < RM9200_USB_DIV_TAB_SIZE; i++) {
+		unsigned long tmp_parent_rate;
+
 		if (!usb->divisors[i])
 			continue;
-		tmprate = *parent_rate / usb->divisors[i];
+
+		tmp_parent_rate = rate * usb->divisors[i];
+		tmp_parent_rate = __clk_round_rate(parent, tmp_parent_rate);
+		tmprate = tmp_parent_rate / usb->divisors[i];
 		if (tmprate < rate)
 			tmpdiff = rate - tmprate;
 		else
@@ -256,6 +262,7 @@ static long at91rm9200_clk_usb_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (bestdiff < 0 || bestdiff > tmpdiff) {
 			bestrate = tmprate;
 			bestdiff = tmpdiff;
+			*parent_rate = tmp_parent_rate;
 		}
 
 		if (!bestdiff)
@@ -272,10 +279,13 @@ static int at91rm9200_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate,
 	int i;
 	struct at91rm9200_clk_usb *usb = to_at91rm9200_clk_usb(hw);
 	struct at91_pmc *pmc = usb->pmc;
-	unsigned long div = parent_rate / rate;
+	unsigned long div;
 
-	if (parent_rate % rate)
+	if (!rate || parent_rate % rate)
 		return -EINVAL;
+
+	div = parent_rate / rate;
+
 	for (i = 0; i < RM9200_USB_DIV_TAB_SIZE; i++) {
 		if (usb->divisors[i] == div) {
 			tmp = pmc_read(pmc, AT91_CKGR_PLLBR) &
@@ -311,7 +321,7 @@ at91rm9200_clk_register_usb(struct at91_pmc *pmc, const char *name,
 	init.ops = &at91rm9200_usb_ops;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
-	init.flags = 0;
+	init.flags = CLK_SET_RATE_PARENT;
 
 	usb->hw.init = &init;
 	usb->pmc = pmc;
diff --git a/drivers/clk/clk-axi-clkgen.c b/drivers/clk/clk-axi-clkgen.c
index 1127ee46b802..e619285c6def 100644
--- a/drivers/clk/clk-axi-clkgen.c
+++ b/drivers/clk/clk-axi-clkgen.c
@@ -544,7 +544,6 @@ static int axi_clkgen_remove(struct platform_device *pdev)
 static struct platform_driver axi_clkgen_driver = {
 	.driver = {
 		.name = "adi-axi-clkgen",
-		.owner = THIS_MODULE,
 		.of_match_table = axi_clkgen_ids,
 	},
 	.probe = axi_clkgen_probe,
diff --git a/drivers/clk/clk-fractional-divider.c b/drivers/clk/clk-fractional-divider.c
index ede685ca0d20..82a59d0086cc 100644
--- a/drivers/clk/clk-fractional-divider.c
+++ b/drivers/clk/clk-fractional-divider.c
@@ -36,7 +36,7 @@ static unsigned long clk_fd_recalc_rate(struct clk_hw *hw,
 	m = (val & fd->mmask) >> fd->mshift;
 	n = (val & fd->nmask) >> fd->nshift;
 
-	ret = parent_rate * m;
+	ret = (u64)parent_rate * m;
 	do_div(ret, n);
 
 	return ret;
diff --git a/drivers/clk/clk-gate.c b/drivers/clk/clk-gate.c
index 4a58c55255bd..51fd87fb7ba6 100644
--- a/drivers/clk/clk-gate.c
+++ b/drivers/clk/clk-gate.c
@@ -45,7 +45,7 @@ static void clk_gate_endisable(struct clk_hw *hw, int enable)
 {
 	struct clk_gate *gate = to_clk_gate(hw);
 	int set = gate->flags & CLK_GATE_SET_TO_DISABLE ? 1 : 0;
-	unsigned long flags = 0;
+	unsigned long uninitialized_var(flags);
 	u32 reg;
 
 	set ^= enable;
diff --git a/drivers/clk/clk-gpio-gate.c b/drivers/clk/clk-gpio-gate.c
new file mode 100644
index 000000000000..08e43224fd52
--- /dev/null
+++ b/drivers/clk/clk-gpio-gate.c
@@ -0,0 +1,205 @@
+/*
+ * Copyright (C) 2013 - 2014 Texas Instruments Incorporated - http://www.ti.com
+ * Author: Jyri Sarha <jsarha@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Gpio gated clock implementation
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of_gpio.h>
+#include <linux/err.h>
+#include <linux/device.h>
+
+/**
+ * DOC: basic gpio gated clock which can be enabled and disabled
+ *      with gpio output
+ * Traits of this clock:
+ * prepare - clk_(un)prepare only ensures parent is (un)prepared
+ * enable - clk_enable and clk_disable are functional & control gpio
+ * rate - inherits rate from parent.  No clk_set_rate support
+ * parent - fixed parent.  No clk_set_parent support
+ */
+
+#define to_clk_gpio(_hw) container_of(_hw, struct clk_gpio, hw)
+
+static int clk_gpio_gate_enable(struct clk_hw *hw)
+{
+	struct clk_gpio *clk = to_clk_gpio(hw);
+
+	gpiod_set_value(clk->gpiod, 1);
+
+	return 0;
+}
+
+static void clk_gpio_gate_disable(struct clk_hw *hw)
+{
+	struct clk_gpio *clk = to_clk_gpio(hw);
+
+	gpiod_set_value(clk->gpiod, 0);
+}
+
+static int clk_gpio_gate_is_enabled(struct clk_hw *hw)
+{
+	struct clk_gpio *clk = to_clk_gpio(hw);
+
+	return gpiod_get_value(clk->gpiod);
+}
+
+const struct clk_ops clk_gpio_gate_ops = {
+	.enable = clk_gpio_gate_enable,
+	.disable = clk_gpio_gate_disable,
+	.is_enabled = clk_gpio_gate_is_enabled,
+};
+EXPORT_SYMBOL_GPL(clk_gpio_gate_ops);
+
+/**
+ * clk_register_gpio - register a gpip clock with the clock framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_name: name of this clock's parent
+ * @gpiod: gpio descriptor to gate this clock
+ */
+struct clk *clk_register_gpio_gate(struct device *dev, const char *name,
+		const char *parent_name, struct gpio_desc *gpiod,
+		unsigned long flags)
+{
+	struct clk_gpio *clk_gpio = NULL;
+	struct clk *clk = ERR_PTR(-EINVAL);
+	struct clk_init_data init = { NULL };
+	unsigned long gpio_flags;
+	int err;
+
+	if (gpiod_is_active_low(gpiod))
+		gpio_flags = GPIOF_OUT_INIT_HIGH;
+	else
+		gpio_flags = GPIOF_OUT_INIT_LOW;
+
+	if (dev)
+		err = devm_gpio_request_one(dev, desc_to_gpio(gpiod),
+					    gpio_flags, name);
+	else
+		err = gpio_request_one(desc_to_gpio(gpiod), gpio_flags, name);
+
+	if (err) {
+		pr_err("%s: %s: Error requesting clock control gpio %u\n",
+		       __func__, name, desc_to_gpio(gpiod));
+		return ERR_PTR(err);
+	}
+
+	if (dev)
+		clk_gpio = devm_kzalloc(dev, sizeof(struct clk_gpio),
+					GFP_KERNEL);
+	else
+		clk_gpio = kzalloc(sizeof(struct clk_gpio), GFP_KERNEL);
+
+	if (!clk_gpio) {
+		clk = ERR_PTR(-ENOMEM);
+		goto clk_register_gpio_gate_err;
+	}
+
+	init.name = name;
+	init.ops = &clk_gpio_gate_ops;
+	init.flags = flags | CLK_IS_BASIC;
+	init.parent_names = (parent_name ? &parent_name : NULL);
+	init.num_parents = (parent_name ? 1 : 0);
+
+	clk_gpio->gpiod = gpiod;
+	clk_gpio->hw.init = &init;
+
+	clk = clk_register(dev, &clk_gpio->hw);
+
+	if (!IS_ERR(clk))
+		return clk;
+
+	if (!dev)
+		kfree(clk_gpio);
+
+clk_register_gpio_gate_err:
+	gpiod_put(gpiod);
+
+	return clk;
+}
+EXPORT_SYMBOL_GPL(clk_register_gpio_gate);
+
+#ifdef CONFIG_OF
+/**
+ * The clk_register_gpio_gate has to be delayed, because the EPROBE_DEFER
+ * can not be handled properly at of_clk_init() call time.
+ */
+
+struct clk_gpio_gate_delayed_register_data {
+	struct device_node *node;
+	struct mutex lock;
+	struct clk *clk;
+};
+
+static struct clk *of_clk_gpio_gate_delayed_register_get(
+		struct of_phandle_args *clkspec,
+		void *_data)
+{
+	struct clk_gpio_gate_delayed_register_data *data = _data;
+	struct clk *clk;
+	const char *clk_name = data->node->name;
+	const char *parent_name;
+	struct gpio_desc *gpiod;
+	int gpio;
+
+	mutex_lock(&data->lock);
+
+	if (data->clk) {
+		mutex_unlock(&data->lock);
+		return data->clk;
+	}
+
+	gpio = of_get_named_gpio_flags(data->node, "enable-gpios", 0, NULL);
+	if (gpio < 0) {
+		mutex_unlock(&data->lock);
+		if (gpio != -EPROBE_DEFER)
+			pr_err("%s: %s: Can't get 'enable-gpios' DT property\n",
+			       __func__, clk_name);
+		return ERR_PTR(gpio);
+	}
+	gpiod = gpio_to_desc(gpio);
+
+	parent_name = of_clk_get_parent_name(data->node, 0);
+
+	clk = clk_register_gpio_gate(NULL, clk_name, parent_name, gpiod, 0);
+	if (IS_ERR(clk)) {
+		mutex_unlock(&data->lock);
+		return clk;
+	}
+
+	data->clk = clk;
+	mutex_unlock(&data->lock);
+
+	return clk;
+}
+
+/**
+ * of_gpio_gate_clk_setup() - Setup function for gpio controlled clock
+ */
+void __init of_gpio_gate_clk_setup(struct device_node *node)
+{
+	struct clk_gpio_gate_delayed_register_data *data;
+
+	data = kzalloc(sizeof(struct clk_gpio_gate_delayed_register_data),
+		       GFP_KERNEL);
+	if (!data)
+		return;
+
+	data->node = node;
+	mutex_init(&data->lock);
+
+	of_clk_add_provider(node, of_clk_gpio_gate_delayed_register_get, data);
+}
+EXPORT_SYMBOL_GPL(of_gpio_gate_clk_setup);
+CLK_OF_DECLARE(gpio_gate_clk, "gpio-gate-clock", of_gpio_gate_clk_setup);
+#endif
diff --git a/drivers/clk/clk-max-gen.c b/drivers/clk/clk-max-gen.c
new file mode 100644
index 000000000000..6505049d50f1
--- /dev/null
+++ b/drivers/clk/clk-max-gen.c
@@ -0,0 +1,192 @@
+/*
+ * clk-max-gen.c - Generic clock driver for Maxim PMICs clocks
+ *
+ * Copyright (C) 2014 Google, Inc
+ *
+ * Copyright (C) 2012 Samsung Electornics
+ * Jonghwa Lee <jonghwa3.lee@samsung.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * This driver is based on clk-max77686.c
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/regmap.h>
+#include <linux/platform_device.h>
+#include <linux/clk-provider.h>
+#include <linux/mutex.h>
+#include <linux/clkdev.h>
+#include <linux/of.h>
+#include <linux/export.h>
+
+struct max_gen_clk {
+	struct regmap *regmap;
+	u32 mask;
+	u32 reg;
+	struct clk_hw hw;
+};
+
+static struct max_gen_clk *to_max_gen_clk(struct clk_hw *hw)
+{
+	return container_of(hw, struct max_gen_clk, hw);
+}
+
+static int max_gen_clk_prepare(struct clk_hw *hw)
+{
+	struct max_gen_clk *max_gen = to_max_gen_clk(hw);
+
+	return regmap_update_bits(max_gen->regmap, max_gen->reg,
+				  max_gen->mask, max_gen->mask);
+}
+
+static void max_gen_clk_unprepare(struct clk_hw *hw)
+{
+	struct max_gen_clk *max_gen = to_max_gen_clk(hw);
+
+	regmap_update_bits(max_gen->regmap, max_gen->reg,
+			   max_gen->mask, ~max_gen->mask);
+}
+
+static int max_gen_clk_is_prepared(struct clk_hw *hw)
+{
+	struct max_gen_clk *max_gen = to_max_gen_clk(hw);
+	int ret;
+	u32 val;
+
+	ret = regmap_read(max_gen->regmap, max_gen->reg, &val);
+
+	if (ret < 0)
+		return -EINVAL;
+
+	return val & max_gen->mask;
+}
+
+static unsigned long max_gen_recalc_rate(struct clk_hw *hw,
+					 unsigned long parent_rate)
+{
+	return 32768;
+}
+
+struct clk_ops max_gen_clk_ops = {
+	.prepare	= max_gen_clk_prepare,
+	.unprepare	= max_gen_clk_unprepare,
+	.is_prepared	= max_gen_clk_is_prepared,
+	.recalc_rate	= max_gen_recalc_rate,
+};
+EXPORT_SYMBOL_GPL(max_gen_clk_ops);
+
+static struct clk *max_gen_clk_register(struct device *dev,
+					struct max_gen_clk *max_gen)
+{
+	struct clk *clk;
+	struct clk_hw *hw = &max_gen->hw;
+	int ret;
+
+	clk = devm_clk_register(dev, hw);
+	if (IS_ERR(clk))
+		return clk;
+
+	ret = clk_register_clkdev(clk, hw->init->name, NULL);
+
+	if (ret)
+		return ERR_PTR(ret);
+
+	return clk;
+}
+
+int max_gen_clk_probe(struct platform_device *pdev, struct regmap *regmap,
+		      u32 reg, struct clk_init_data *clks_init, int num_init)
+{
+	int i, ret;
+	struct max_gen_clk *max_gen_clks;
+	struct clk **clocks;
+	struct device *dev = pdev->dev.parent;
+	const char *clk_name;
+	struct clk_init_data *init;
+
+	clocks = devm_kzalloc(dev, sizeof(struct clk *) * num_init, GFP_KERNEL);
+	if (!clocks)
+		return -ENOMEM;
+
+	max_gen_clks = devm_kzalloc(dev, sizeof(struct max_gen_clk)
+				    * num_init, GFP_KERNEL);
+	if (!max_gen_clks)
+		return -ENOMEM;
+
+	for (i = 0; i < num_init; i++) {
+		max_gen_clks[i].regmap = regmap;
+		max_gen_clks[i].mask = 1 << i;
+		max_gen_clks[i].reg = reg;
+
+		init = devm_kzalloc(dev, sizeof(*init), GFP_KERNEL);
+		if (!init)
+			return -ENOMEM;
+
+		if (dev->of_node &&
+		    !of_property_read_string_index(dev->of_node,
+						   "clock-output-names",
+						   i, &clk_name))
+			init->name = clk_name;
+		else
+			init->name = clks_init[i].name;
+
+		init->ops = clks_init[i].ops;
+		init->flags = clks_init[i].flags;
+
+		max_gen_clks[i].hw.init = init;
+
+		clocks[i] = max_gen_clk_register(dev, &max_gen_clks[i]);
+		if (IS_ERR(clocks[i])) {
+			ret = PTR_ERR(clocks[i]);
+			dev_err(dev, "failed to register %s\n",
+				max_gen_clks[i].hw.init->name);
+			return ret;
+		}
+	}
+
+	platform_set_drvdata(pdev, clocks);
+
+	if (dev->of_node) {
+		struct clk_onecell_data *of_data;
+
+		of_data = devm_kzalloc(dev, sizeof(*of_data), GFP_KERNEL);
+		if (!of_data)
+			return -ENOMEM;
+
+		of_data->clks = clocks;
+		of_data->clk_num = num_init;
+		ret = of_clk_add_provider(dev->of_node, of_clk_src_onecell_get,
+					  of_data);
+
+		if (ret) {
+			dev_err(dev, "failed to register OF clock provider\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(max_gen_clk_probe);
+
+int max_gen_clk_remove(struct platform_device *pdev, int num_init)
+{
+	struct device *dev = pdev->dev.parent;
+
+	if (dev->of_node)
+		of_clk_del_provider(dev->of_node);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(max_gen_clk_remove);
diff --git a/drivers/clk/clk-max-gen.h b/drivers/clk/clk-max-gen.h
new file mode 100644
index 000000000000..997e86fc3f4d
--- /dev/null
+++ b/drivers/clk/clk-max-gen.h
@@ -0,0 +1,32 @@
+/*
+ * clk-max-gen.h - Generic clock driver for Maxim PMICs clocks
+ *
+ * Copyright (C) 2014 Google, Inc
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __CLK_MAX_GEN_H__
+#define __CLK_MAX_GEN_H__
+
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/clkdev.h>
+#include <linux/regmap.h>
+#include <linux/platform_device.h>
+
+int max_gen_clk_probe(struct platform_device *pdev, struct regmap *regmap,
+		      u32 reg, struct clk_init_data *clks_init, int num_init);
+int max_gen_clk_remove(struct platform_device *pdev, int num_init);
+extern struct clk_ops max_gen_clk_ops;
+
+#endif /* __CLK_MAX_GEN_H__ */
diff --git a/drivers/clk/clk-max77686.c b/drivers/clk/clk-max77686.c
index 3d7e8dd8fd58..86cdb3a28629 100644
--- a/drivers/clk/clk-max77686.c
+++ b/drivers/clk/clk-max77686.c
@@ -30,193 +30,38 @@
 #include <linux/mutex.h>
 #include <linux/clkdev.h>
 
-enum {
-	MAX77686_CLK_AP = 0,
-	MAX77686_CLK_CP,
-	MAX77686_CLK_PMIC,
-	MAX77686_CLKS_NUM,
-};
-
-struct max77686_clk {
-	struct max77686_dev *iodev;
-	u32 mask;
-	struct clk_hw hw;
-	struct clk_lookup *lookup;
-};
-
-static struct max77686_clk *to_max77686_clk(struct clk_hw *hw)
-{
-	return container_of(hw, struct max77686_clk, hw);
-}
-
-static int max77686_clk_prepare(struct clk_hw *hw)
-{
-	struct max77686_clk *max77686 = to_max77686_clk(hw);
-
-	return regmap_update_bits(max77686->iodev->regmap,
-				  MAX77686_REG_32KHZ, max77686->mask,
-				  max77686->mask);
-}
-
-static void max77686_clk_unprepare(struct clk_hw *hw)
-{
-	struct max77686_clk *max77686 = to_max77686_clk(hw);
-
-	regmap_update_bits(max77686->iodev->regmap,
-		MAX77686_REG_32KHZ, max77686->mask, ~max77686->mask);
-}
-
-static int max77686_clk_is_prepared(struct clk_hw *hw)
-{
-	struct max77686_clk *max77686 = to_max77686_clk(hw);
-	int ret;
-	u32 val;
-
-	ret = regmap_read(max77686->iodev->regmap,
-				MAX77686_REG_32KHZ, &val);
-
-	if (ret < 0)
-		return -EINVAL;
-
-	return val & max77686->mask;
-}
-
-static unsigned long max77686_recalc_rate(struct clk_hw *hw,
-					  unsigned long parent_rate)
-{
-	return 32768;
-}
-
-static struct clk_ops max77686_clk_ops = {
-	.prepare	= max77686_clk_prepare,
-	.unprepare	= max77686_clk_unprepare,
-	.is_prepared	= max77686_clk_is_prepared,
-	.recalc_rate	= max77686_recalc_rate,
-};
+#include <dt-bindings/clock/maxim,max77686.h>
+#include "clk-max-gen.h"
 
 static struct clk_init_data max77686_clks_init[MAX77686_CLKS_NUM] = {
 	[MAX77686_CLK_AP] = {
 		.name = "32khz_ap",
-		.ops = &max77686_clk_ops,
+		.ops = &max_gen_clk_ops,
 		.flags = CLK_IS_ROOT,
 	},
 	[MAX77686_CLK_CP] = {
 		.name = "32khz_cp",
-		.ops = &max77686_clk_ops,
+		.ops = &max_gen_clk_ops,
 		.flags = CLK_IS_ROOT,
 	},
 	[MAX77686_CLK_PMIC] = {
 		.name = "32khz_pmic",
-		.ops = &max77686_clk_ops,
+		.ops = &max_gen_clk_ops,
 		.flags = CLK_IS_ROOT,
 	},
 };
 
-static struct clk *max77686_clk_register(struct device *dev,
-				struct max77686_clk *max77686)
-{
-	struct clk *clk;
-	struct clk_hw *hw = &max77686->hw;
-
-	clk = clk_register(dev, hw);
-	if (IS_ERR(clk))
-		return clk;
-
-	max77686->lookup = kzalloc(sizeof(struct clk_lookup), GFP_KERNEL);
-	if (!max77686->lookup)
-		return ERR_PTR(-ENOMEM);
-
-	max77686->lookup->con_id = hw->init->name;
-	max77686->lookup->clk = clk;
-
-	clkdev_add(max77686->lookup);
-
-	return clk;
-}
-
 static int max77686_clk_probe(struct platform_device *pdev)
 {
 	struct max77686_dev *iodev = dev_get_drvdata(pdev->dev.parent);
-	struct max77686_clk *max77686_clks[MAX77686_CLKS_NUM];
-	struct clk **clocks;
-	int i, ret;
-
-	clocks = devm_kzalloc(&pdev->dev, sizeof(struct clk *)
-					* MAX77686_CLKS_NUM, GFP_KERNEL);
-	if (!clocks)
-		return -ENOMEM;
-
-	for (i = 0; i < MAX77686_CLKS_NUM; i++) {
-		max77686_clks[i] = devm_kzalloc(&pdev->dev,
-					sizeof(struct max77686_clk), GFP_KERNEL);
-		if (!max77686_clks[i])
-			return -ENOMEM;
-	}
-
-	for (i = 0; i < MAX77686_CLKS_NUM; i++) {
-		max77686_clks[i]->iodev = iodev;
-		max77686_clks[i]->mask = 1 << i;
-		max77686_clks[i]->hw.init = &max77686_clks_init[i];
-
-		clocks[i] = max77686_clk_register(&pdev->dev, max77686_clks[i]);
-		if (IS_ERR(clocks[i])) {
-			ret = PTR_ERR(clocks[i]);
-			dev_err(&pdev->dev, "failed to register %s\n",
-				max77686_clks[i]->hw.init->name);
-			goto err_clocks;
-		}
-	}
-
-	platform_set_drvdata(pdev, clocks);
-
-	if (iodev->dev->of_node) {
-		struct clk_onecell_data *of_data;
 
-		of_data = devm_kzalloc(&pdev->dev,
-					sizeof(*of_data), GFP_KERNEL);
-		if (!of_data) {
-			ret = -ENOMEM;
-			goto err_clocks;
-		}
-
-		of_data->clks = clocks;
-		of_data->clk_num = MAX77686_CLKS_NUM;
-		ret = of_clk_add_provider(iodev->dev->of_node,
-					of_clk_src_onecell_get, of_data);
-		if (ret) {
-			dev_err(&pdev->dev, "failed to register OF clock provider\n");
-			goto err_clocks;
-		}
-	}
-
-	return 0;
-
-err_clocks:
-	for (--i; i >= 0; --i) {
-		clkdev_drop(max77686_clks[i]->lookup);
-		clk_unregister(max77686_clks[i]->hw.clk);
-	}
-
-	return ret;
+	return max_gen_clk_probe(pdev, iodev->regmap, MAX77686_REG_32KHZ,
+				 max77686_clks_init, MAX77686_CLKS_NUM);
 }
 
 static int max77686_clk_remove(struct platform_device *pdev)
 {
-	struct max77686_dev *iodev = dev_get_drvdata(pdev->dev.parent);
-	struct clk **clocks = platform_get_drvdata(pdev);
-	int i;
-
-	if (iodev->dev->of_node)
-		of_clk_del_provider(iodev->dev->of_node);
-
-	for (i = 0; i < MAX77686_CLKS_NUM; i++) {
-		struct clk_hw *hw = __clk_get_hw(clocks[i]);
-		struct max77686_clk *max77686 = to_max77686_clk(hw);
-
-		clkdev_drop(max77686->lookup);
-		clk_unregister(clocks[i]);
-	}
-	return 0;
+	return max_gen_clk_remove(pdev, MAX77686_CLKS_NUM);
 }
 
 static const struct platform_device_id max77686_clk_id[] = {
@@ -228,24 +73,13 @@ MODULE_DEVICE_TABLE(platform, max77686_clk_id);
 static struct platform_driver max77686_clk_driver = {
 	.driver = {
 		.name  = "max77686-clk",
-		.owner = THIS_MODULE,
 	},
 	.probe = max77686_clk_probe,
 	.remove = max77686_clk_remove,
 	.id_table = max77686_clk_id,
 };
 
-static int __init max77686_clk_init(void)
-{
-	return platform_driver_register(&max77686_clk_driver);
-}
-subsys_initcall(max77686_clk_init);
-
-static void __init max77686_clk_cleanup(void)
-{
-	platform_driver_unregister(&max77686_clk_driver);
-}
-module_exit(max77686_clk_cleanup);
+module_platform_driver(max77686_clk_driver);
 
 MODULE_DESCRIPTION("MAXIM 77686 Clock Driver");
 MODULE_AUTHOR("Jonghwa Lee <jonghwa3.lee@samsung.com>");
diff --git a/drivers/clk/clk-max77802.c b/drivers/clk/clk-max77802.c
new file mode 100644
index 000000000000..0729dc723a8f
--- /dev/null
+++ b/drivers/clk/clk-max77802.c
@@ -0,0 +1,97 @@
+/*
+ * clk-max77802.c - Clock driver for Maxim 77802
+ *
+ * Copyright (C) 2014 Google, Inc
+ *
+ * Copyright (C) 2012 Samsung Electornics
+ * Jonghwa Lee <jonghwa3.lee@samsung.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * This driver is based on clk-max77686.c
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/max77686-private.h>
+#include <linux/clk-provider.h>
+#include <linux/mutex.h>
+#include <linux/clkdev.h>
+
+#include <dt-bindings/clock/maxim,max77802.h>
+#include "clk-max-gen.h"
+
+#define MAX77802_CLOCK_OPMODE_MASK	0x1
+#define MAX77802_CLOCK_LOW_JITTER_SHIFT 0x3
+
+static struct clk_init_data max77802_clks_init[MAX77802_CLKS_NUM] = {
+	[MAX77802_CLK_32K_AP] = {
+		.name = "32khz_ap",
+		.ops = &max_gen_clk_ops,
+		.flags = CLK_IS_ROOT,
+	},
+	[MAX77802_CLK_32K_CP] = {
+		.name = "32khz_cp",
+		.ops = &max_gen_clk_ops,
+		.flags = CLK_IS_ROOT,
+	},
+};
+
+static int max77802_clk_probe(struct platform_device *pdev)
+{
+	struct max77686_dev *iodev = dev_get_drvdata(pdev->dev.parent);
+	int ret;
+
+	ret = max_gen_clk_probe(pdev, iodev->regmap, MAX77802_REG_32KHZ,
+				max77802_clks_init, MAX77802_CLKS_NUM);
+
+	if (ret) {
+		dev_err(&pdev->dev, "generic probe failed %d\n", ret);
+		return ret;
+	}
+
+	/* Enable low-jitter mode on the 32khz clocks. */
+	ret = regmap_update_bits(iodev->regmap, MAX77802_REG_32KHZ,
+				 1 << MAX77802_CLOCK_LOW_JITTER_SHIFT,
+				 1 << MAX77802_CLOCK_LOW_JITTER_SHIFT);
+	if (ret < 0)
+		dev_err(&pdev->dev, "failed to enable low-jitter mode\n");
+
+	return ret;
+}
+
+static int max77802_clk_remove(struct platform_device *pdev)
+{
+	return max_gen_clk_remove(pdev, MAX77802_CLKS_NUM);
+}
+
+static const struct platform_device_id max77802_clk_id[] = {
+	{ "max77802-clk", 0},
+	{ },
+};
+MODULE_DEVICE_TABLE(platform, max77802_clk_id);
+
+static struct platform_driver max77802_clk_driver = {
+	.driver = {
+		.name  = "max77802-clk",
+	},
+	.probe = max77802_clk_probe,
+	.remove = max77802_clk_remove,
+	.id_table = max77802_clk_id,
+};
+
+module_platform_driver(max77802_clk_driver);
+
+MODULE_DESCRIPTION("MAXIM 77802 Clock Driver");
+MODULE_AUTHOR("Javier Martinez Canillas <javier.martinez@collabora.co.uk>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/clk/clk-palmas.c b/drivers/clk/clk-palmas.c
index 781630e1372b..8d459923a15f 100644
--- a/drivers/clk/clk-palmas.c
+++ b/drivers/clk/clk-palmas.c
@@ -292,7 +292,6 @@ static int palmas_clks_remove(struct platform_device *pdev)
 static struct platform_driver palmas_clks_driver = {
 	.driver = {
 		.name = "palmas-clk",
-		.owner = THIS_MODULE,
 		.of_match_table = palmas_clks_of_match,
 	},
 	.probe = palmas_clks_probe,
diff --git a/drivers/clk/clk-rk808.c b/drivers/clk/clk-rk808.c
new file mode 100644
index 000000000000..83902b9cd49e
--- /dev/null
+++ b/drivers/clk/clk-rk808.c
@@ -0,0 +1,170 @@
+/*
+ * Clkout driver for Rockchip RK808
+ *
+ * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * Author:Chris Zhong <zyw@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/rk808.h>
+#include <linux/i2c.h>
+
+#define RK808_NR_OUTPUT 2
+
+struct rk808_clkout {
+	struct rk808 *rk808;
+	struct clk_onecell_data clk_data;
+	struct clk_hw		clkout1_hw;
+	struct clk_hw		clkout2_hw;
+};
+
+static unsigned long rk808_clkout_recalc_rate(struct clk_hw *hw,
+					      unsigned long parent_rate)
+{
+	return 32768;
+}
+
+static int rk808_clkout2_enable(struct clk_hw *hw, bool enable)
+{
+	struct rk808_clkout *rk808_clkout = container_of(hw,
+							 struct rk808_clkout,
+							 clkout2_hw);
+	struct rk808 *rk808 = rk808_clkout->rk808;
+
+	return regmap_update_bits(rk808->regmap, RK808_CLK32OUT_REG,
+				  CLK32KOUT2_EN, enable ? CLK32KOUT2_EN : 0);
+}
+
+static int rk808_clkout2_prepare(struct clk_hw *hw)
+{
+	return rk808_clkout2_enable(hw, true);
+}
+
+static void rk808_clkout2_unprepare(struct clk_hw *hw)
+{
+	rk808_clkout2_enable(hw, false);
+}
+
+static int rk808_clkout2_is_prepared(struct clk_hw *hw)
+{
+	struct rk808_clkout *rk808_clkout = container_of(hw,
+							 struct rk808_clkout,
+							 clkout2_hw);
+	struct rk808 *rk808 = rk808_clkout->rk808;
+	uint32_t val;
+
+	int ret = regmap_read(rk808->regmap, RK808_CLK32OUT_REG, &val);
+
+	if (ret < 0)
+		return ret;
+
+	return (val & CLK32KOUT2_EN) ? 1 : 0;
+}
+
+static const struct clk_ops rk808_clkout1_ops = {
+	.recalc_rate = rk808_clkout_recalc_rate,
+};
+
+static const struct clk_ops rk808_clkout2_ops = {
+	.prepare = rk808_clkout2_prepare,
+	.unprepare = rk808_clkout2_unprepare,
+	.is_prepared = rk808_clkout2_is_prepared,
+	.recalc_rate = rk808_clkout_recalc_rate,
+};
+
+static int rk808_clkout_probe(struct platform_device *pdev)
+{
+	struct rk808 *rk808 = dev_get_drvdata(pdev->dev.parent);
+	struct i2c_client *client = rk808->i2c;
+	struct device_node *node = client->dev.of_node;
+	struct clk_init_data init = {};
+	struct clk **clk_table;
+	struct rk808_clkout *rk808_clkout;
+
+	rk808_clkout = devm_kzalloc(&client->dev,
+				    sizeof(*rk808_clkout), GFP_KERNEL);
+	if (!rk808_clkout)
+		return -ENOMEM;
+
+	rk808_clkout->rk808 = rk808;
+
+	clk_table = devm_kcalloc(&client->dev, RK808_NR_OUTPUT,
+				 sizeof(struct clk *), GFP_KERNEL);
+	if (!clk_table)
+		return -ENOMEM;
+
+	init.flags = CLK_IS_ROOT;
+	init.parent_names = NULL;
+	init.num_parents = 0;
+	init.name = "rk808-clkout1";
+	init.ops = &rk808_clkout1_ops;
+	rk808_clkout->clkout1_hw.init = &init;
+
+	/* optional override of the clockname */
+	of_property_read_string_index(node, "clock-output-names",
+				      0, &init.name);
+
+	clk_table[0] = devm_clk_register(&client->dev,
+					 &rk808_clkout->clkout1_hw);
+	if (IS_ERR(clk_table[0]))
+		return PTR_ERR(clk_table[0]);
+
+	init.name = "rk808-clkout2";
+	init.ops = &rk808_clkout2_ops;
+	rk808_clkout->clkout2_hw.init = &init;
+
+	/* optional override of the clockname */
+	of_property_read_string_index(node, "clock-output-names",
+				      1, &init.name);
+
+	clk_table[1] = devm_clk_register(&client->dev,
+					 &rk808_clkout->clkout2_hw);
+	if (IS_ERR(clk_table[1]))
+		return PTR_ERR(clk_table[1]);
+
+	rk808_clkout->clk_data.clks = clk_table;
+	rk808_clkout->clk_data.clk_num = RK808_NR_OUTPUT;
+
+	return of_clk_add_provider(node, of_clk_src_onecell_get,
+				   &rk808_clkout->clk_data);
+}
+
+static int rk808_clkout_remove(struct platform_device *pdev)
+{
+	struct rk808 *rk808 = dev_get_drvdata(pdev->dev.parent);
+	struct i2c_client *client = rk808->i2c;
+	struct device_node *node = client->dev.of_node;
+
+	of_clk_del_provider(node);
+
+	return 0;
+}
+
+static struct platform_driver rk808_clkout_driver = {
+	.probe = rk808_clkout_probe,
+	.remove = rk808_clkout_remove,
+	.driver		= {
+		.name	= "rk808-clkout",
+	},
+};
+
+module_platform_driver(rk808_clkout_driver);
+
+MODULE_DESCRIPTION("Clkout driver for the rk808 series PMICs");
+MODULE_AUTHOR("Chris Zhong <zyw@rock-chips.com>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:rk808-clkout");
diff --git a/drivers/clk/clk-twl6040.c b/drivers/clk/clk-twl6040.c
index 1ada79a28052..4a755135bcd3 100644
--- a/drivers/clk/clk-twl6040.c
+++ b/drivers/clk/clk-twl6040.c
@@ -112,7 +112,6 @@ static int twl6040_clk_remove(struct platform_device *pdev)
 static struct platform_driver twl6040_clk_driver = {
 	.driver = {
 		.name = "twl6040-clk",
-		.owner = THIS_MODULE,
 	},
 	.probe = twl6040_clk_probe,
 	.remove = twl6040_clk_remove,
diff --git a/drivers/clk/clk-wm831x.c b/drivers/clk/clk-wm831x.c
index b131041c8f48..ef67719f4e52 100644
--- a/drivers/clk/clk-wm831x.c
+++ b/drivers/clk/clk-wm831x.c
@@ -395,7 +395,6 @@ static struct platform_driver wm831x_clk_driver = {
 	.probe = wm831x_clk_probe,
 	.driver		= {
 		.name	= "wm831x-clk",
-		.owner	= THIS_MODULE,
 	},
 };
 
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index bacc06ff939b..4896ae9e23da 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -100,6 +100,8 @@ static void clk_enable_unlock(unsigned long flags)
 
 static struct dentry *rootdir;
 static int inited = 0;
+static DEFINE_MUTEX(clk_debug_lock);
+static HLIST_HEAD(clk_debug_list);
 
 static struct hlist_head *all_lists[] = {
 	&clk_root_list,
@@ -117,11 +119,11 @@ static void clk_summary_show_one(struct seq_file *s, struct clk *c, int level)
 	if (!c)
 		return;
 
-	seq_printf(s, "%*s%-*s %11d %12d %11lu %10lu\n",
+	seq_printf(s, "%*s%-*s %11d %12d %11lu %10lu %-3d\n",
 		   level * 3 + 1, "",
 		   30 - level * 3, c->name,
 		   c->enable_count, c->prepare_count, clk_get_rate(c),
-		   clk_get_accuracy(c));
+		   clk_get_accuracy(c), clk_get_phase(c));
 }
 
 static void clk_summary_show_subtree(struct seq_file *s, struct clk *c,
@@ -143,8 +145,8 @@ static int clk_summary_show(struct seq_file *s, void *data)
 	struct clk *c;
 	struct hlist_head **lists = (struct hlist_head **)s->private;
 
-	seq_puts(s, "   clock                         enable_cnt  prepare_cnt        rate   accuracy\n");
-	seq_puts(s, "--------------------------------------------------------------------------------\n");
+	seq_puts(s, "   clock                         enable_cnt  prepare_cnt        rate   accuracy   phase\n");
+	seq_puts(s, "----------------------------------------------------------------------------------------\n");
 
 	clk_prepare_lock();
 
@@ -180,6 +182,7 @@ static void clk_dump_one(struct seq_file *s, struct clk *c, int level)
 	seq_printf(s, "\"prepare_count\": %d,", c->prepare_count);
 	seq_printf(s, "\"rate\": %lu", clk_get_rate(c));
 	seq_printf(s, "\"accuracy\": %lu", clk_get_accuracy(c));
+	seq_printf(s, "\"phase\": %d", clk_get_phase(c));
 }
 
 static void clk_dump_subtree(struct seq_file *s, struct clk *c, int level)
@@ -264,6 +267,11 @@ static int clk_debug_create_one(struct clk *clk, struct dentry *pdentry)
 	if (!d)
 		goto err_out;
 
+	d = debugfs_create_u32("clk_phase", S_IRUGO, clk->dentry,
+			(u32 *)&clk->phase);
+	if (!d)
+		goto err_out;
+
 	d = debugfs_create_x32("clk_flags", S_IRUGO, clk->dentry,
 			(u32 *)&clk->flags);
 	if (!d)
@@ -300,28 +308,6 @@ out:
 	return ret;
 }
 
-/* caller must hold prepare_lock */
-static int clk_debug_create_subtree(struct clk *clk, struct dentry *pdentry)
-{
-	struct clk *child;
-	int ret = -EINVAL;;
-
-	if (!clk || !pdentry)
-		goto out;
-
-	ret = clk_debug_create_one(clk, pdentry);
-
-	if (ret)
-		goto out;
-
-	hlist_for_each_entry(child, &clk->children, child_node)
-		clk_debug_create_subtree(child, pdentry);
-
-	ret = 0;
-out:
-	return ret;
-}
-
 /**
  * clk_debug_register - add a clk node to the debugfs clk tree
  * @clk: the clk being added to the debugfs clk tree
@@ -329,20 +315,21 @@ out:
  * Dynamically adds a clk to the debugfs clk tree if debugfs has been
  * initialized.  Otherwise it bails out early since the debugfs clk tree
  * will be created lazily by clk_debug_init as part of a late_initcall.
- *
- * Caller must hold prepare_lock.  Only clk_init calls this function (so
- * far) so this is taken care.
  */
 static int clk_debug_register(struct clk *clk)
 {
 	int ret = 0;
 
+	mutex_lock(&clk_debug_lock);
+	hlist_add_head(&clk->debug_node, &clk_debug_list);
+
 	if (!inited)
-		goto out;
+		goto unlock;
 
-	ret = clk_debug_create_subtree(clk, rootdir);
+	ret = clk_debug_create_one(clk, rootdir);
+unlock:
+	mutex_unlock(&clk_debug_lock);
 
-out:
 	return ret;
 }
 
@@ -353,12 +340,18 @@ out:
  * Dynamically removes a clk and all it's children clk nodes from the
  * debugfs clk tree if clk->dentry points to debugfs created by
  * clk_debug_register in __clk_init.
- *
- * Caller must hold prepare_lock.
  */
 static void clk_debug_unregister(struct clk *clk)
 {
+	mutex_lock(&clk_debug_lock);
+	if (!clk->dentry)
+		goto out;
+
+	hlist_del_init(&clk->debug_node);
 	debugfs_remove_recursive(clk->dentry);
+	clk->dentry = NULL;
+out:
+	mutex_unlock(&clk_debug_lock);
 }
 
 struct dentry *clk_debugfs_add_file(struct clk *clk, char *name, umode_t mode,
@@ -415,17 +408,12 @@ static int __init clk_debug_init(void)
 	if (!d)
 		return -ENOMEM;
 
-	clk_prepare_lock();
-
-	hlist_for_each_entry(clk, &clk_root_list, child_node)
-		clk_debug_create_subtree(clk, rootdir);
-
-	hlist_for_each_entry(clk, &clk_orphan_list, child_node)
-		clk_debug_create_subtree(clk, rootdir);
+	mutex_lock(&clk_debug_lock);
+	hlist_for_each_entry(clk, &clk_debug_list, debug_node)
+		clk_debug_create_one(clk, rootdir);
 
 	inited = 1;
-
-	clk_prepare_unlock();
+	mutex_unlock(&clk_debug_lock);
 
 	return 0;
 }
@@ -1744,6 +1732,77 @@ out:
 EXPORT_SYMBOL_GPL(clk_set_parent);
 
 /**
+ * clk_set_phase - adjust the phase shift of a clock signal
+ * @clk: clock signal source
+ * @degrees: number of degrees the signal is shifted
+ *
+ * Shifts the phase of a clock signal by the specified
+ * degrees. Returns 0 on success, -EERROR otherwise.
+ *
+ * This function makes no distinction about the input or reference
+ * signal that we adjust the clock signal phase against. For example
+ * phase locked-loop clock signal generators we may shift phase with
+ * respect to feedback clock signal input, but for other cases the
+ * clock phase may be shifted with respect to some other, unspecified
+ * signal.
+ *
+ * Additionally the concept of phase shift does not propagate through
+ * the clock tree hierarchy, which sets it apart from clock rates and
+ * clock accuracy. A parent clock phase attribute does not have an
+ * impact on the phase attribute of a child clock.
+ */
+int clk_set_phase(struct clk *clk, int degrees)
+{
+	int ret = 0;
+
+	if (!clk)
+		goto out;
+
+	/* sanity check degrees */
+	degrees %= 360;
+	if (degrees < 0)
+		degrees += 360;
+
+	clk_prepare_lock();
+
+	if (!clk->ops->set_phase)
+		goto out_unlock;
+
+	ret = clk->ops->set_phase(clk->hw, degrees);
+
+	if (!ret)
+		clk->phase = degrees;
+
+out_unlock:
+	clk_prepare_unlock();
+
+out:
+	return ret;
+}
+
+/**
+ * clk_get_phase - return the phase shift of a clock signal
+ * @clk: clock signal source
+ *
+ * Returns the phase shift of a clock node in degrees, otherwise returns
+ * -EERROR.
+ */
+int clk_get_phase(struct clk *clk)
+{
+	int ret = 0;
+
+	if (!clk)
+		goto out;
+
+	clk_prepare_lock();
+	ret = clk->phase;
+	clk_prepare_unlock();
+
+out:
+	return ret;
+}
+
+/**
  * __clk_init - initialize the data structures in a struct clk
  * @dev:	device initializing this clk, placeholder for now
  * @clk:	clk being initialized
@@ -1862,6 +1921,16 @@ int __clk_init(struct device *dev, struct clk *clk)
 		clk->accuracy = 0;
 
 	/*
+	 * Set clk's phase.
+	 * Since a phase is by definition relative to its parent, just
+	 * query the current clock phase, or just assume it's in phase.
+	 */
+	if (clk->ops->get_phase)
+		clk->phase = clk->ops->get_phase(clk->hw);
+	else
+		clk->phase = 0;
+
+	/*
 	 * Set clk's rate.  The preferred method is to use .recalc_rate.  For
 	 * simple clocks and lazy developers the default fallback is to use the
 	 * parent's rate.  If a clock doesn't have a parent (or is orphaned)
@@ -2092,14 +2161,16 @@ void clk_unregister(struct clk *clk)
 {
 	unsigned long flags;
 
-       if (!clk || WARN_ON_ONCE(IS_ERR(clk)))
-               return;
+	if (!clk || WARN_ON_ONCE(IS_ERR(clk)))
+		return;
+
+	clk_debug_unregister(clk);
 
 	clk_prepare_lock();
 
 	if (clk->ops == &clk_nodrv_ops) {
 		pr_err("%s: unregistered clock: %s\n", __func__, clk->name);
-		goto out;
+		return;
 	}
 	/*
 	 * Assign empty clock ops for consumers that might still hold
@@ -2118,16 +2189,13 @@ void clk_unregister(struct clk *clk)
 			clk_set_parent(child, NULL);
 	}
 
-	clk_debug_unregister(clk);
-
 	hlist_del_init(&clk->child_node);
 
 	if (clk->prepare_count)
 		pr_warn("%s: unregistering prepared clock: %s\n",
 					__func__, clk->name);
-
 	kref_put(&clk->ref, __clk_release);
-out:
+
 	clk_prepare_unlock();
 }
 EXPORT_SYMBOL_GPL(clk_unregister);
diff --git a/drivers/clk/hisilicon/clk-hix5hd2.c b/drivers/clk/hisilicon/clk-hix5hd2.c
index e5fcfb4e32ef..3f369c60fe56 100644
--- a/drivers/clk/hisilicon/clk-hix5hd2.c
+++ b/drivers/clk/hisilicon/clk-hix5hd2.c
@@ -9,6 +9,8 @@
 
 #include <linux/of_address.h>
 #include <dt-bindings/clock/hix5hd2-clock.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
 #include "clk.h"
 
 static struct hisi_fixed_rate_clock hix5hd2_fixed_rate_clks[] __initdata = {
@@ -48,9 +50,9 @@ static const char *sfc_mux_p[] __initconst = {
 		"24m", "150m", "200m", "100m", "75m", };
 static u32 sfc_mux_table[] = {0, 4, 5, 6, 7};
 
-static const char *sdio1_mux_p[] __initconst = {
+static const char *sdio_mux_p[] __initconst = {
 		"75m", "100m", "50m", "15m", };
-static u32 sdio1_mux_table[] = {0, 1, 2, 3};
+static u32 sdio_mux_table[] = {0, 1, 2, 3};
 
 static const char *fephy_mux_p[] __initconst = { "25m", "125m"};
 static u32 fephy_mux_table[] = {0, 1};
@@ -59,28 +61,243 @@ static u32 fephy_mux_table[] = {0, 1};
 static struct hisi_mux_clock hix5hd2_mux_clks[] __initdata = {
 	{ HIX5HD2_SFC_MUX, "sfc_mux", sfc_mux_p, ARRAY_SIZE(sfc_mux_p),
 		CLK_SET_RATE_PARENT, 0x5c, 8, 3, 0, sfc_mux_table, },
-	{ HIX5HD2_MMC_MUX, "mmc_mux", sdio1_mux_p, ARRAY_SIZE(sdio1_mux_p),
-		CLK_SET_RATE_PARENT, 0xa0, 8, 2, 0, sdio1_mux_table, },
+	{ HIX5HD2_MMC_MUX, "mmc_mux", sdio_mux_p, ARRAY_SIZE(sdio_mux_p),
+		CLK_SET_RATE_PARENT, 0xa0, 8, 2, 0, sdio_mux_table, },
+	{ HIX5HD2_SD_MUX, "sd_mux", sdio_mux_p, ARRAY_SIZE(sdio_mux_p),
+		CLK_SET_RATE_PARENT, 0x9c, 8, 2, 0, sdio_mux_table, },
 	{ HIX5HD2_FEPHY_MUX, "fephy_mux",
 		fephy_mux_p, ARRAY_SIZE(fephy_mux_p),
 		CLK_SET_RATE_PARENT, 0x120, 8, 2, 0, fephy_mux_table, },
 };
 
 static struct hisi_gate_clock hix5hd2_gate_clks[] __initdata = {
-	/*sfc*/
+	/* sfc */
 	{ HIX5HD2_SFC_CLK, "clk_sfc", "sfc_mux",
 		CLK_SET_RATE_PARENT, 0x5c, 0, 0, },
 	{ HIX5HD2_SFC_RST, "rst_sfc", "clk_sfc",
 		CLK_SET_RATE_PARENT, 0x5c, 4, CLK_GATE_SET_TO_DISABLE, },
-	/*sdio1*/
+	/* sdio0 */
+	{ HIX5HD2_SD_BIU_CLK, "clk_sd_biu", "200m",
+		CLK_SET_RATE_PARENT, 0x9c, 0, 0, },
+	{ HIX5HD2_SD_CIU_CLK, "clk_sd_ciu", "sd_mux",
+		CLK_SET_RATE_PARENT, 0x9c, 1, 0, },
+	{ HIX5HD2_SD_CIU_RST, "rst_sd_ciu", "clk_sd_ciu",
+		CLK_SET_RATE_PARENT, 0x9c, 4, CLK_GATE_SET_TO_DISABLE, },
+	/* sdio1 */
 	{ HIX5HD2_MMC_BIU_CLK, "clk_mmc_biu", "200m",
 		CLK_SET_RATE_PARENT, 0xa0, 0, 0, },
 	{ HIX5HD2_MMC_CIU_CLK, "clk_mmc_ciu", "mmc_mux",
 		CLK_SET_RATE_PARENT, 0xa0, 1, 0, },
 	{ HIX5HD2_MMC_CIU_RST, "rst_mmc_ciu", "clk_mmc_ciu",
 		CLK_SET_RATE_PARENT, 0xa0, 4, CLK_GATE_SET_TO_DISABLE, },
+	/* gsf */
+	{ HIX5HD2_FWD_BUS_CLK, "clk_fwd_bus", NULL, 0, 0xcc, 0, 0, },
+	{ HIX5HD2_FWD_SYS_CLK, "clk_fwd_sys", "clk_fwd_bus", 0, 0xcc, 5, 0, },
+	{ HIX5HD2_MAC0_PHY_CLK, "clk_fephy", "clk_fwd_sys",
+		 CLK_SET_RATE_PARENT, 0x120, 0, 0, },
+	/* wdg0 */
+	{ HIX5HD2_WDG0_CLK, "clk_wdg0", "24m",
+		CLK_SET_RATE_PARENT, 0x178, 0, 0, },
+	{ HIX5HD2_WDG0_RST, "rst_wdg0", "clk_wdg0",
+		CLK_SET_RATE_PARENT, 0x178, 4, CLK_GATE_SET_TO_DISABLE, },
+	/* I2C */
+	{HIX5HD2_I2C0_CLK, "clk_i2c0", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 4, 0, },
+	{HIX5HD2_I2C0_RST, "rst_i2c0", "clk_i2c0",
+		 CLK_SET_RATE_PARENT, 0x06c, 5, CLK_GATE_SET_TO_DISABLE, },
+	{HIX5HD2_I2C1_CLK, "clk_i2c1", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 8, 0, },
+	{HIX5HD2_I2C1_RST, "rst_i2c1", "clk_i2c1",
+		 CLK_SET_RATE_PARENT, 0x06c, 9, CLK_GATE_SET_TO_DISABLE, },
+	{HIX5HD2_I2C2_CLK, "clk_i2c2", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 12, 0, },
+	{HIX5HD2_I2C2_RST, "rst_i2c2", "clk_i2c2",
+		 CLK_SET_RATE_PARENT, 0x06c, 13, CLK_GATE_SET_TO_DISABLE, },
+	{HIX5HD2_I2C3_CLK, "clk_i2c3", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 16, 0, },
+	{HIX5HD2_I2C3_RST, "rst_i2c3", "clk_i2c3",
+		 CLK_SET_RATE_PARENT, 0x06c, 17, CLK_GATE_SET_TO_DISABLE, },
+	{HIX5HD2_I2C4_CLK, "clk_i2c4", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 20, 0, },
+	{HIX5HD2_I2C4_RST, "rst_i2c4", "clk_i2c4",
+		 CLK_SET_RATE_PARENT, 0x06c, 21, CLK_GATE_SET_TO_DISABLE, },
+	{HIX5HD2_I2C5_CLK, "clk_i2c5", "100m",
+		 CLK_SET_RATE_PARENT, 0x06c, 0, 0, },
+	{HIX5HD2_I2C5_RST, "rst_i2c5", "clk_i2c5",
+		 CLK_SET_RATE_PARENT, 0x06c, 1, CLK_GATE_SET_TO_DISABLE, },
 };
 
+enum hix5hd2_clk_type {
+	TYPE_COMPLEX,
+	TYPE_ETHER,
+};
+
+struct hix5hd2_complex_clock {
+	const char	*name;
+	const char	*parent_name;
+	u32		id;
+	u32		ctrl_reg;
+	u32		ctrl_clk_mask;
+	u32		ctrl_rst_mask;
+	u32		phy_reg;
+	u32		phy_clk_mask;
+	u32		phy_rst_mask;
+	enum hix5hd2_clk_type type;
+};
+
+struct hix5hd2_clk_complex {
+	struct clk_hw	hw;
+	u32		id;
+	void __iomem	*ctrl_reg;
+	u32		ctrl_clk_mask;
+	u32		ctrl_rst_mask;
+	void __iomem	*phy_reg;
+	u32		phy_clk_mask;
+	u32		phy_rst_mask;
+};
+
+static struct hix5hd2_complex_clock hix5hd2_complex_clks[] __initdata = {
+	{"clk_mac0", "clk_fephy", HIX5HD2_MAC0_CLK,
+		0xcc, 0xa, 0x500, 0x120, 0, 0x10, TYPE_ETHER},
+	{"clk_mac1", "clk_fwd_sys", HIX5HD2_MAC1_CLK,
+		0xcc, 0x14, 0xa00, 0x168, 0x2, 0, TYPE_ETHER},
+	{"clk_sata", NULL, HIX5HD2_SATA_CLK,
+		0xa8, 0x1f, 0x300, 0xac, 0x1, 0x0, TYPE_COMPLEX},
+	{"clk_usb", NULL, HIX5HD2_USB_CLK,
+		0xb8, 0xff, 0x3f000, 0xbc, 0x7, 0x3f00, TYPE_COMPLEX},
+};
+
+#define to_complex_clk(_hw) container_of(_hw, struct hix5hd2_clk_complex, hw)
+
+static int clk_ether_prepare(struct clk_hw *hw)
+{
+	struct hix5hd2_clk_complex *clk = to_complex_clk(hw);
+	u32 val;
+
+	val = readl_relaxed(clk->ctrl_reg);
+	val |= clk->ctrl_clk_mask | clk->ctrl_rst_mask;
+	writel_relaxed(val, clk->ctrl_reg);
+	val &= ~(clk->ctrl_rst_mask);
+	writel_relaxed(val, clk->ctrl_reg);
+
+	val = readl_relaxed(clk->phy_reg);
+	val |= clk->phy_clk_mask;
+	val &= ~(clk->phy_rst_mask);
+	writel_relaxed(val, clk->phy_reg);
+	mdelay(10);
+
+	val &= ~(clk->phy_clk_mask);
+	val |= clk->phy_rst_mask;
+	writel_relaxed(val, clk->phy_reg);
+	mdelay(10);
+
+	val |= clk->phy_clk_mask;
+	val &= ~(clk->phy_rst_mask);
+	writel_relaxed(val, clk->phy_reg);
+	mdelay(30);
+	return 0;
+}
+
+static void clk_ether_unprepare(struct clk_hw *hw)
+{
+	struct hix5hd2_clk_complex *clk = to_complex_clk(hw);
+	u32 val;
+
+	val = readl_relaxed(clk->ctrl_reg);
+	val &= ~(clk->ctrl_clk_mask);
+	writel_relaxed(val, clk->ctrl_reg);
+}
+
+static struct clk_ops clk_ether_ops = {
+	.prepare = clk_ether_prepare,
+	.unprepare = clk_ether_unprepare,
+};
+
+static int clk_complex_enable(struct clk_hw *hw)
+{
+	struct hix5hd2_clk_complex *clk = to_complex_clk(hw);
+	u32 val;
+
+	val = readl_relaxed(clk->ctrl_reg);
+	val |= clk->ctrl_clk_mask;
+	val &= ~(clk->ctrl_rst_mask);
+	writel_relaxed(val, clk->ctrl_reg);
+
+	val = readl_relaxed(clk->phy_reg);
+	val |= clk->phy_clk_mask;
+	val &= ~(clk->phy_rst_mask);
+	writel_relaxed(val, clk->phy_reg);
+
+	return 0;
+}
+
+static void clk_complex_disable(struct clk_hw *hw)
+{
+	struct hix5hd2_clk_complex *clk = to_complex_clk(hw);
+	u32 val;
+
+	val = readl_relaxed(clk->ctrl_reg);
+	val |= clk->ctrl_rst_mask;
+	val &= ~(clk->ctrl_clk_mask);
+	writel_relaxed(val, clk->ctrl_reg);
+
+	val = readl_relaxed(clk->phy_reg);
+	val |= clk->phy_rst_mask;
+	val &= ~(clk->phy_clk_mask);
+	writel_relaxed(val, clk->phy_reg);
+}
+
+static struct clk_ops clk_complex_ops = {
+	.enable = clk_complex_enable,
+	.disable = clk_complex_disable,
+};
+
+void __init hix5hd2_clk_register_complex(struct hix5hd2_complex_clock *clks,
+					 int nums, struct hisi_clock_data *data)
+{
+	void __iomem *base = data->base;
+	int i;
+
+	for (i = 0; i < nums; i++) {
+		struct hix5hd2_clk_complex *p_clk;
+		struct clk *clk;
+		struct clk_init_data init;
+
+		p_clk = kzalloc(sizeof(*p_clk), GFP_KERNEL);
+		if (!p_clk)
+			return;
+
+		init.name = clks[i].name;
+		if (clks[i].type == TYPE_ETHER)
+			init.ops = &clk_ether_ops;
+		else
+			init.ops = &clk_complex_ops;
+
+		init.flags = CLK_IS_BASIC;
+		init.parent_names =
+			(clks[i].parent_name ? &clks[i].parent_name : NULL);
+		init.num_parents = (clks[i].parent_name ? 1 : 0);
+
+		p_clk->ctrl_reg = base + clks[i].ctrl_reg;
+		p_clk->ctrl_clk_mask = clks[i].ctrl_clk_mask;
+		p_clk->ctrl_rst_mask = clks[i].ctrl_rst_mask;
+		p_clk->phy_reg = base + clks[i].phy_reg;
+		p_clk->phy_clk_mask = clks[i].phy_clk_mask;
+		p_clk->phy_rst_mask = clks[i].phy_rst_mask;
+		p_clk->hw.init = &init;
+
+		clk = clk_register(NULL, &p_clk->hw);
+		if (IS_ERR(clk)) {
+			kfree(p_clk);
+			pr_err("%s: failed to register clock %s\n",
+			       __func__, clks[i].name);
+			continue;
+		}
+
+		data->clk_data.clks[clks[i].id] = clk;
+	}
+}
+
 static void __init hix5hd2_clk_init(struct device_node *np)
 {
 	struct hisi_clock_data *clk_data;
@@ -96,6 +313,9 @@ static void __init hix5hd2_clk_init(struct device_node *np)
 					clk_data);
 	hisi_clk_register_gate(hix5hd2_gate_clks,
 			ARRAY_SIZE(hix5hd2_gate_clks), clk_data);
+	hix5hd2_clk_register_complex(hix5hd2_complex_clks,
+				     ARRAY_SIZE(hix5hd2_complex_clks),
+				     clk_data);
 }
 
 CLK_OF_DECLARE(hix5hd2_clk, "hisilicon,hix5hd2-clock", hix5hd2_clk_init);
diff --git a/drivers/clk/mvebu/armada-370.c b/drivers/clk/mvebu/armada-370.c
index bef198a83863..756f0f39d6a3 100644
--- a/drivers/clk/mvebu/armada-370.c
+++ b/drivers/clk/mvebu/armada-370.c
@@ -23,6 +23,7 @@
  */
 
 #define SARL				0	/* Low part [0:31] */
+#define	 SARL_A370_SSCG_ENABLE		BIT(10)
 #define	 SARL_A370_PCLK_FREQ_OPT	11
 #define	 SARL_A370_PCLK_FREQ_OPT_MASK	0xF
 #define	 SARL_A370_FAB_FREQ_OPT		15
@@ -133,10 +134,17 @@ static void __init a370_get_clk_ratio(
 	}
 }
 
+static bool a370_is_sscg_enabled(void __iomem *sar)
+{
+	return !(readl(sar) & SARL_A370_SSCG_ENABLE);
+}
+
 static const struct coreclk_soc_desc a370_coreclks = {
 	.get_tclk_freq = a370_get_tclk_freq,
 	.get_cpu_freq = a370_get_cpu_freq,
 	.get_clk_ratio = a370_get_clk_ratio,
+	.is_sscg_enabled = a370_is_sscg_enabled,
+	.fix_sscg_deviation = kirkwood_fix_sscg_deviation,
 	.ratios = a370_coreclk_ratios,
 	.num_ratios = ARRAY_SIZE(a370_coreclk_ratios),
 };
diff --git a/drivers/clk/mvebu/armada-375.c b/drivers/clk/mvebu/armada-375.c
index c991a4d95e10..c7af2242b796 100644
--- a/drivers/clk/mvebu/armada-375.c
+++ b/drivers/clk/mvebu/armada-375.c
@@ -27,14 +27,14 @@
  * all modified at the same time, and not separately as for the Armada
  * 370 or the Armada XP SoCs.
  *
- * SAR0[21:17]   : CPU frequency    DDR frequency   L2 frequency
+ * SAR1[21:17]   : CPU frequency    DDR frequency   L2 frequency
  *		 6   =  400 MHz	    400 MHz	    200 MHz
  *		 15  =  600 MHz	    600 MHz	    300 MHz
  *		 21  =  800 MHz	    534 MHz	    400 MHz
  *		 25  = 1000 MHz	    500 MHz	    500 MHz
  *		 others reserved.
  *
- * SAR0[22]   : TCLK frequency
+ * SAR1[22]   : TCLK frequency
  *		 0 = 166 MHz
  *		 1 = 200 MHz
  */
diff --git a/drivers/clk/mvebu/common.c b/drivers/clk/mvebu/common.c
index 25ceccf939ad..b7fcb469c87a 100644
--- a/drivers/clk/mvebu/common.c
+++ b/drivers/clk/mvebu/common.c
@@ -26,8 +26,85 @@
  * Core Clocks
  */
 
+#define SSCG_CONF_MODE(reg)	(((reg) >> 16) & 0x3)
+#define SSCG_SPREAD_DOWN	0x0
+#define SSCG_SPREAD_UP		0x1
+#define SSCG_SPREAD_CENTRAL	0x2
+#define SSCG_CONF_LOW(reg)	(((reg) >> 8) & 0xFF)
+#define SSCG_CONF_HIGH(reg)	((reg) & 0xFF)
+
 static struct clk_onecell_data clk_data;
 
+/*
+ * This function can be used by the Kirkwood, the Armada 370, the
+ * Armada XP and the Armada 375 SoC. The name of the function was
+ * chosen following the dt convention: using the first known SoC
+ * compatible with it.
+ */
+u32 kirkwood_fix_sscg_deviation(u32 system_clk)
+{
+	struct device_node *sscg_np = NULL;
+	void __iomem *sscg_map;
+	u32 sscg_reg;
+	s32 low_bound, high_bound;
+	u64 freq_swing_half;
+
+	sscg_np = of_find_node_by_name(NULL, "sscg");
+	if (sscg_np == NULL) {
+		pr_err("cannot get SSCG register node\n");
+		return system_clk;
+	}
+
+	sscg_map = of_iomap(sscg_np, 0);
+	if (sscg_map == NULL) {
+		pr_err("cannot map SSCG register\n");
+		goto out;
+	}
+
+	sscg_reg = readl(sscg_map);
+	high_bound = SSCG_CONF_HIGH(sscg_reg);
+	low_bound = SSCG_CONF_LOW(sscg_reg);
+
+	if ((high_bound - low_bound) <= 0)
+		goto out;
+	/*
+	 * From Marvell engineer we got the following formula (when
+	 * this code was written, the datasheet was erroneous)
+	 * Spread percentage = 1/96 * (H - L) / H
+	 * H = SSCG_High_Boundary
+	 * L = SSCG_Low_Boundary
+	 *
+	 * As the deviation is half of spread then it lead to the
+	 * following formula in the code.
+	 *
+	 * To avoid an overflow and not lose any significant digit in
+	 * the same time we have to use a 64 bit integer.
+	 */
+
+	freq_swing_half = (((u64)high_bound - (u64)low_bound)
+			* (u64)system_clk);
+	do_div(freq_swing_half, (2 * 96 * high_bound));
+
+	switch (SSCG_CONF_MODE(sscg_reg)) {
+	case SSCG_SPREAD_DOWN:
+		system_clk -= freq_swing_half;
+		break;
+	case SSCG_SPREAD_UP:
+		system_clk += freq_swing_half;
+		break;
+	case SSCG_SPREAD_CENTRAL:
+	default:
+		break;
+	}
+
+	iounmap(sscg_map);
+
+out:
+	of_node_put(sscg_np);
+
+	return system_clk;
+}
+
 void __init mvebu_coreclk_setup(struct device_node *np,
 				const struct coreclk_soc_desc *desc)
 {
@@ -62,6 +139,11 @@ void __init mvebu_coreclk_setup(struct device_node *np,
 	of_property_read_string_index(np, "clock-output-names", 1,
 				      &cpuclk_name);
 	rate = desc->get_cpu_freq(base);
+
+	if (desc->is_sscg_enabled && desc->fix_sscg_deviation
+		&& desc->is_sscg_enabled(base))
+		rate = desc->fix_sscg_deviation(rate);
+
 	clk_data.clks[1] = clk_register_fixed_rate(NULL, cpuclk_name, NULL,
 						   CLK_IS_ROOT, rate);
 	WARN_ON(IS_ERR(clk_data.clks[1]));
@@ -89,8 +171,10 @@ void __init mvebu_coreclk_setup(struct device_node *np,
  * Clock Gating Control
  */
 
+DEFINE_SPINLOCK(ctrl_gating_lock);
+
 struct clk_gating_ctrl {
-	spinlock_t lock;
+	spinlock_t *lock;
 	struct clk **gates;
 	int num_gates;
 };
@@ -138,7 +222,8 @@ void __init mvebu_clk_gating_setup(struct device_node *np,
 	if (WARN_ON(!ctrl))
 		goto ctrl_out;
 
-	spin_lock_init(&ctrl->lock);
+	/* lock must already be initialized */
+	ctrl->lock = &ctrl_gating_lock;
 
 	/* Count, allocate, and register clock gates */
 	for (n = 0; desc[n].name;)
@@ -155,7 +240,7 @@ void __init mvebu_clk_gating_setup(struct device_node *np,
 			(desc[n].parent) ? desc[n].parent : default_parent;
 		ctrl->gates[n] = clk_register_gate(NULL, desc[n].name, parent,
 					desc[n].flags, base, desc[n].bit_idx,
-					0, &ctrl->lock);
+					0, ctrl->lock);
 		WARN_ON(IS_ERR(ctrl->gates[n]));
 	}
 
diff --git a/drivers/clk/mvebu/common.h b/drivers/clk/mvebu/common.h
index f968b4d9df92..783b5631a453 100644
--- a/drivers/clk/mvebu/common.h
+++ b/drivers/clk/mvebu/common.h
@@ -17,6 +17,8 @@
 
 #include <linux/kernel.h>
 
+extern spinlock_t ctrl_gating_lock;
+
 struct device_node;
 
 struct coreclk_ratio {
@@ -28,6 +30,8 @@ struct coreclk_soc_desc {
 	u32 (*get_tclk_freq)(void __iomem *sar);
 	u32 (*get_cpu_freq)(void __iomem *sar);
 	void (*get_clk_ratio)(void __iomem *sar, int id, int *mult, int *div);
+	bool (*is_sscg_enabled)(void __iomem *sar);
+	u32 (*fix_sscg_deviation)(u32 system_clk);
 	const struct coreclk_ratio *ratios;
 	int num_ratios;
 };
@@ -45,4 +49,9 @@ void __init mvebu_coreclk_setup(struct device_node *np,
 void __init mvebu_clk_gating_setup(struct device_node *np,
 				   const struct clk_gating_soc_desc *desc);
 
+/*
+ * This function is shared among the Kirkwood, Armada 370, Armada XP
+ * and Armada 375 SoC
+ */
+u32 kirkwood_fix_sscg_deviation(u32 system_clk);
 #endif
diff --git a/drivers/clk/mvebu/kirkwood.c b/drivers/clk/mvebu/kirkwood.c
index ddb666a86500..99550f25975e 100644
--- a/drivers/clk/mvebu/kirkwood.c
+++ b/drivers/clk/mvebu/kirkwood.c
@@ -13,9 +13,11 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include "common.h"
 
 /*
@@ -214,7 +216,6 @@ static const struct clk_gating_soc_desc kirkwood_gating_desc[] __initconst = {
 	{ "runit", NULL, 7, 0 },
 	{ "xor0", NULL, 8, 0 },
 	{ "audio", NULL, 9, 0 },
-	{ "powersave", "cpuclk", 11, 0 },
 	{ "sata0", NULL, 14, 0 },
 	{ "sata1", NULL, 15, 0 },
 	{ "xor1", NULL, 16, 0 },
@@ -225,6 +226,101 @@ static const struct clk_gating_soc_desc kirkwood_gating_desc[] __initconst = {
 	{ }
 };
 
+
+/*
+ * Clock Muxing Control
+ */
+
+struct clk_muxing_soc_desc {
+	const char *name;
+	const char **parents;
+	int num_parents;
+	int shift;
+	int width;
+	unsigned long flags;
+};
+
+struct clk_muxing_ctrl {
+	spinlock_t *lock;
+	struct clk **muxes;
+	int num_muxes;
+};
+
+static const char *powersave_parents[] = {
+	"cpuclk",
+	"ddrclk",
+};
+
+static const struct clk_muxing_soc_desc kirkwood_mux_desc[] __initconst = {
+	{ "powersave", powersave_parents, ARRAY_SIZE(powersave_parents),
+		11, 1, 0 },
+};
+
+#define to_clk_mux(_hw) container_of(_hw, struct clk_mux, hw)
+
+static struct clk *clk_muxing_get_src(
+	struct of_phandle_args *clkspec, void *data)
+{
+	struct clk_muxing_ctrl *ctrl = (struct clk_muxing_ctrl *)data;
+	int n;
+
+	if (clkspec->args_count < 1)
+		return ERR_PTR(-EINVAL);
+
+	for (n = 0; n < ctrl->num_muxes; n++) {
+		struct clk_mux *mux =
+			to_clk_mux(__clk_get_hw(ctrl->muxes[n]));
+		if (clkspec->args[0] == mux->shift)
+			return ctrl->muxes[n];
+	}
+	return ERR_PTR(-ENODEV);
+}
+
+static void __init kirkwood_clk_muxing_setup(struct device_node *np,
+				   const struct clk_muxing_soc_desc *desc)
+{
+	struct clk_muxing_ctrl *ctrl;
+	void __iomem *base;
+	int n;
+
+	base = of_iomap(np, 0);
+	if (WARN_ON(!base))
+		return;
+
+	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
+	if (WARN_ON(!ctrl))
+		goto ctrl_out;
+
+	/* lock must already be initialized */
+	ctrl->lock = &ctrl_gating_lock;
+
+	/* Count, allocate, and register clock muxes */
+	for (n = 0; desc[n].name;)
+		n++;
+
+	ctrl->num_muxes = n;
+	ctrl->muxes = kcalloc(ctrl->num_muxes, sizeof(struct clk *),
+			GFP_KERNEL);
+	if (WARN_ON(!ctrl->muxes))
+		goto muxes_out;
+
+	for (n = 0; n < ctrl->num_muxes; n++) {
+		ctrl->muxes[n] = clk_register_mux(NULL, desc[n].name,
+				desc[n].parents, desc[n].num_parents,
+				desc[n].flags, base, desc[n].shift,
+				desc[n].width, desc[n].flags, ctrl->lock);
+		WARN_ON(IS_ERR(ctrl->muxes[n]));
+	}
+
+	of_clk_add_provider(np, clk_muxing_get_src, ctrl);
+
+	return;
+muxes_out:
+	kfree(ctrl);
+ctrl_out:
+	iounmap(base);
+}
+
 static void __init kirkwood_clk_init(struct device_node *np)
 {
 	struct device_node *cgnp =
@@ -236,8 +332,10 @@ static void __init kirkwood_clk_init(struct device_node *np)
 	else
 		mvebu_coreclk_setup(np, &kirkwood_coreclks);
 
-	if (cgnp)
+	if (cgnp) {
 		mvebu_clk_gating_setup(cgnp, kirkwood_gating_desc);
+		kirkwood_clk_muxing_setup(cgnp, kirkwood_mux_desc);
+	}
 }
 CLK_OF_DECLARE(kirkwood_clk, "marvell,kirkwood-core-clock",
 	       kirkwood_clk_init);
diff --git a/drivers/clk/pxa/Makefile b/drivers/clk/pxa/Makefile
new file mode 100644
index 000000000000..4ff2abcd500b
--- /dev/null
+++ b/drivers/clk/pxa/Makefile
@@ -0,0 +1,2 @@
+obj-y				+= clk-pxa.o
+obj-$(CONFIG_PXA27x)		+= clk-pxa27x.o
diff --git a/drivers/clk/pxa/clk-pxa.c b/drivers/clk/pxa/clk-pxa.c
new file mode 100644
index 000000000000..ef3c05389c0a
--- /dev/null
+++ b/drivers/clk/pxa/clk-pxa.c
@@ -0,0 +1,97 @@
+/*
+ * Marvell PXA family clocks
+ *
+ * Copyright (C) 2014 Robert Jarzmik
+ *
+ * Common clock code for PXA clocks ("CKEN" type clocks + DT)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ */
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/of.h>
+
+#include <dt-bindings/clock/pxa-clock.h>
+#include "clk-pxa.h"
+
+DEFINE_SPINLOCK(lock);
+
+static struct clk *pxa_clocks[CLK_MAX];
+static struct clk_onecell_data onecell_data = {
+	.clks = pxa_clocks,
+	.clk_num = CLK_MAX,
+};
+
+#define to_pxa_clk(_hw) container_of(_hw, struct pxa_clk_cken, hw)
+
+static unsigned long cken_recalc_rate(struct clk_hw *hw,
+				      unsigned long parent_rate)
+{
+	struct pxa_clk_cken *pclk = to_pxa_clk(hw);
+	struct clk_fixed_factor *fix;
+
+	if (!pclk->is_in_low_power || pclk->is_in_low_power())
+		fix = &pclk->lp;
+	else
+		fix = &pclk->hp;
+	fix->hw.clk = hw->clk;
+	return clk_fixed_factor_ops.recalc_rate(&fix->hw, parent_rate);
+}
+
+static struct clk_ops cken_rate_ops = {
+	.recalc_rate = cken_recalc_rate,
+};
+
+static u8 cken_get_parent(struct clk_hw *hw)
+{
+	struct pxa_clk_cken *pclk = to_pxa_clk(hw);
+
+	if (!pclk->is_in_low_power)
+		return 0;
+	return pclk->is_in_low_power() ? 0 : 1;
+}
+
+static struct clk_ops cken_mux_ops = {
+	.get_parent = cken_get_parent,
+	.set_parent = dummy_clk_set_parent,
+};
+
+void __init clkdev_pxa_register(int ckid, const char *con_id,
+				const char *dev_id, struct clk *clk)
+{
+	if (!IS_ERR(clk) && (ckid != CLK_NONE))
+		pxa_clocks[ckid] = clk;
+	if (!IS_ERR(clk))
+		clk_register_clkdev(clk, con_id, dev_id);
+}
+
+int __init clk_pxa_cken_init(struct pxa_clk_cken *clks, int nb_clks)
+{
+	int i;
+	struct pxa_clk_cken *pclk;
+	struct clk *clk;
+
+	for (i = 0; i < nb_clks; i++) {
+		pclk = clks + i;
+		pclk->gate.lock = &lock;
+		clk = clk_register_composite(NULL, pclk->name,
+					     pclk->parent_names, 2,
+					     &pclk->hw, &cken_mux_ops,
+					     &pclk->hw, &cken_rate_ops,
+					     &pclk->gate.hw, &clk_gate_ops,
+					     pclk->flags);
+		clkdev_pxa_register(pclk->ckid, pclk->con_id, pclk->dev_id,
+				    clk);
+	}
+	return 0;
+}
+
+static void __init pxa_dt_clocks_init(struct device_node *np)
+{
+	of_clk_add_provider(np, of_clk_src_onecell_get, &onecell_data);
+}
+CLK_OF_DECLARE(pxa_clks, "marvell,pxa-clocks", pxa_dt_clocks_init);
diff --git a/drivers/clk/pxa/clk-pxa.h b/drivers/clk/pxa/clk-pxa.h
new file mode 100644
index 000000000000..5fe219d06b49
--- /dev/null
+++ b/drivers/clk/pxa/clk-pxa.h
@@ -0,0 +1,107 @@
+/*
+ * Marvell PXA family clocks
+ *
+ * Copyright (C) 2014 Robert Jarzmik
+ *
+ * Common clock code for PXA clocks ("CKEN" type clocks + DT)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ */
+#ifndef _CLK_PXA_
+#define _CLK_PXA_
+
+#define PARENTS(name) \
+	static const char *name ## _parents[] __initconst
+#define MUX_RO_RATE_RO_OPS(name, clk_name)			\
+	static struct clk_hw name ## _mux_hw;			\
+	static struct clk_hw name ## _rate_hw;			\
+	static struct clk_ops name ## _mux_ops = {		\
+		.get_parent = name ## _get_parent,		\
+		.set_parent = dummy_clk_set_parent,		\
+	};							\
+	static struct clk_ops name ## _rate_ops = {		\
+		.recalc_rate = name ## _get_rate,		\
+	};							\
+	static struct clk *clk_register_ ## name(void)		\
+	{							\
+		return clk_register_composite(NULL, clk_name,	\
+			name ## _parents,			\
+			ARRAY_SIZE(name ## _parents),		\
+			&name ## _mux_hw, &name ## _mux_ops,	\
+			&name ## _rate_hw, &name ## _rate_ops,	\
+			NULL, NULL, CLK_GET_RATE_NOCACHE);	\
+	}
+
+#define RATE_RO_OPS(name, clk_name)			\
+	static struct clk_hw name ## _rate_hw;			\
+	static struct clk_ops name ## _rate_ops = {		\
+		.recalc_rate = name ## _get_rate,		\
+	};							\
+	static struct clk *clk_register_ ## name(void)		\
+	{							\
+		return clk_register_composite(NULL, clk_name,	\
+			name ## _parents,			\
+			ARRAY_SIZE(name ## _parents),		\
+			NULL, NULL,				\
+			&name ## _rate_hw, &name ## _rate_ops,	\
+			NULL, NULL, CLK_GET_RATE_NOCACHE);	\
+	}
+
+/*
+ * CKEN clock type
+ * This clock takes it source from 2 possible parents :
+ *  - a low power parent
+ *  - a normal parent
+ *
+ *  +------------+     +-----------+
+ *  |  Low Power | --- | x mult_lp |
+ *  |    Clock   |     | / div_lp  |\
+ *  +------------+     +-----------+ \+-----+   +-----------+
+ *                                    | Mux |---| CKEN gate |
+ *  +------------+     +-----------+ /+-----+   +-----------+
+ *  | High Power |     | x mult_hp |/
+ *  |    Clock   | --- | / div_hp  |
+ *  +------------+     +-----------+
+ */
+struct pxa_clk_cken {
+	struct clk_hw hw;
+	int ckid;
+	const char *name;
+	const char *dev_id;
+	const char *con_id;
+	const char **parent_names;
+	struct clk_fixed_factor lp;
+	struct clk_fixed_factor hp;
+	struct clk_gate gate;
+	bool (*is_in_low_power)(void);
+	const unsigned long flags;
+};
+
+#define PXA_CKEN(_dev_id, _con_id, _name, parents, _mult_lp, _div_lp,	\
+		 _mult_hp, _div_hp, is_lp, _cken_reg, _cken_bit, flag)	\
+	{ .ckid = CLK_ ## _name, .name = #_name,			\
+	  .dev_id = _dev_id, .con_id = _con_id,	.parent_names = parents,\
+	  .lp = { .mult = _mult_lp, .div = _div_lp },			\
+	  .hp = { .mult = _mult_hp, .div = _div_hp },			\
+	  .is_in_low_power = is_lp,					\
+	  .gate = { .reg = (void __iomem *)_cken_reg, .bit_idx = _cken_bit }, \
+	  .flags = flag,						\
+	}
+#define PXA_CKEN_1RATE(dev_id, con_id, name, parents, cken_reg,		\
+			    cken_bit, flag)				\
+	PXA_CKEN(dev_id, con_id, name, parents, 1, 1, 1, 1,		\
+		 NULL, cken_reg, cken_bit, flag)
+
+static int dummy_clk_set_parent(struct clk_hw *hw, u8 index)
+{
+	return 0;
+}
+
+extern void clkdev_pxa_register(int ckid, const char *con_id,
+				const char *dev_id, struct clk *clk);
+extern int clk_pxa_cken_init(struct pxa_clk_cken *clks, int nb_clks);
+
+#endif
diff --git a/drivers/clk/pxa/clk-pxa27x.c b/drivers/clk/pxa/clk-pxa27x.c
new file mode 100644
index 000000000000..b345cc791e5d
--- /dev/null
+++ b/drivers/clk/pxa/clk-pxa27x.c
@@ -0,0 +1,370 @@
+/*
+ * Marvell PXA27x family clocks
+ *
+ * Copyright (C) 2014 Robert Jarzmik
+ *
+ * Heavily inspired from former arch/arm/mach-pxa/clock.c.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ */
+#include <linux/clk-provider.h>
+#include <mach/pxa2xx-regs.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/of.h>
+
+#include <dt-bindings/clock/pxa-clock.h>
+#include "clk-pxa.h"
+
+#define KHz 1000
+#define MHz (1000 * 1000)
+
+enum {
+	PXA_CORE_13Mhz = 0,
+	PXA_CORE_RUN,
+	PXA_CORE_TURBO,
+};
+
+enum {
+	PXA_BUS_13Mhz = 0,
+	PXA_BUS_RUN,
+};
+
+enum {
+	PXA_LCD_13Mhz = 0,
+	PXA_LCD_RUN,
+};
+
+enum {
+	PXA_MEM_13Mhz = 0,
+	PXA_MEM_SYSTEM_BUS,
+	PXA_MEM_RUN,
+};
+
+static const char * const get_freq_khz[] = {
+	"core", "run", "cpll", "memory",
+	"system_bus"
+};
+
+/*
+ * Get the clock frequency as reflected by CCSR and the turbo flag.
+ * We assume these values have been applied via a fcs.
+ * If info is not 0 we also display the current settings.
+ */
+unsigned int pxa27x_get_clk_frequency_khz(int info)
+{
+	struct clk *clk;
+	unsigned long clks[5];
+	int i;
+
+	for (i = 0; i < 5; i++) {
+		clk = clk_get(NULL, get_freq_khz[i]);
+		if (IS_ERR(clk)) {
+			clks[i] = 0;
+		} else {
+			clks[i] = clk_get_rate(clk);
+			clk_put(clk);
+		}
+	}
+	if (info) {
+		pr_info("Run Mode clock: %ld.%02ldMHz\n",
+			clks[1] / 1000000, (clks[1] % 1000000) / 10000);
+		pr_info("Turbo Mode clock: %ld.%02ldMHz\n",
+			clks[2] / 1000000, (clks[2] % 1000000) / 10000);
+		pr_info("Memory clock: %ld.%02ldMHz\n",
+			clks[3] / 1000000, (clks[3] % 1000000) / 10000);
+		pr_info("System bus clock: %ld.%02ldMHz\n",
+			clks[4] / 1000000, (clks[4] % 1000000) / 10000);
+	}
+	return (unsigned int)clks[0];
+}
+
+bool pxa27x_is_ppll_disabled(void)
+{
+	unsigned long ccsr = CCSR;
+
+	return ccsr & (1 << CCCR_PPDIS_BIT);
+}
+
+#define PXA27X_CKEN(dev_id, con_id, parents, mult_hp, div_hp,		\
+		    bit, is_lp, flags)					\
+	PXA_CKEN(dev_id, con_id, bit, parents, 1, 1, mult_hp, div_hp,	\
+		 is_lp,  &CKEN, CKEN_ ## bit, flags)
+#define PXA27X_PBUS_CKEN(dev_id, con_id, bit, mult_hp, div_hp, delay)	\
+	PXA27X_CKEN(dev_id, con_id, pxa27x_pbus_parents, mult_hp,	\
+		    div_hp, bit, pxa27x_is_ppll_disabled, 0)
+
+PARENTS(pxa27x_pbus) = { "osc_13mhz", "ppll_312mhz" };
+PARENTS(pxa27x_sbus) = { "system_bus", "system_bus" };
+PARENTS(pxa27x_32Mhz_bus) = { "osc_32_768khz", "osc_32_768khz" };
+PARENTS(pxa27x_lcd_bus) = { "lcd_base", "lcd_base" };
+PARENTS(pxa27x_membus) = { "lcd_base", "lcd_base" };
+
+#define PXA27X_CKEN_1RATE(dev_id, con_id, bit, parents, delay)		\
+	PXA_CKEN_1RATE(dev_id, con_id, bit, parents,			\
+		       &CKEN, CKEN_ ## bit, 0)
+#define PXA27X_CKEN_1RATE_AO(dev_id, con_id, bit, parents, delay)	\
+	PXA_CKEN_1RATE(dev_id, con_id, bit, parents,			\
+		       &CKEN, CKEN_ ## bit, CLK_IGNORE_UNUSED)
+
+static struct pxa_clk_cken pxa27x_clocks[] = {
+	PXA27X_PBUS_CKEN("pxa2xx-uart.0", NULL, FFUART, 2, 42, 1),
+	PXA27X_PBUS_CKEN("pxa2xx-uart.1", NULL, BTUART, 2, 42, 1),
+	PXA27X_PBUS_CKEN("pxa2xx-uart.2", NULL, STUART, 2, 42, 1),
+	PXA27X_PBUS_CKEN("pxa2xx-i2s", NULL, I2S, 2, 51, 0),
+	PXA27X_PBUS_CKEN("pxa2xx-i2c.0", NULL, I2C, 2, 19, 0),
+	PXA27X_PBUS_CKEN("pxa27x-udc", NULL, USB, 2, 13, 5),
+	PXA27X_PBUS_CKEN("pxa2xx-mci.0", NULL, MMC, 2, 32, 0),
+	PXA27X_PBUS_CKEN("pxa2xx-ir", "FICPCLK", FICP, 2, 13, 0),
+	PXA27X_PBUS_CKEN("pxa27x-ohci", NULL, USBHOST, 2, 13, 0),
+	PXA27X_PBUS_CKEN("pxa2xx-i2c.1", NULL, PWRI2C, 1, 24, 0),
+	PXA27X_PBUS_CKEN("pxa27x-ssp.0", NULL, SSP1, 1, 24, 0),
+	PXA27X_PBUS_CKEN("pxa27x-ssp.1", NULL, SSP2, 1, 24, 0),
+	PXA27X_PBUS_CKEN("pxa27x-ssp.2", NULL, SSP3, 1, 24, 0),
+	PXA27X_PBUS_CKEN("pxa27x-pwm.0", NULL, PWM0, 1, 24, 0),
+	PXA27X_PBUS_CKEN("pxa27x-pwm.1", NULL, PWM1, 1, 24, 0),
+	PXA27X_PBUS_CKEN(NULL, "MSLCLK", MSL, 2, 13, 0),
+	PXA27X_PBUS_CKEN(NULL, "USIMCLK", USIM, 2, 13, 0),
+	PXA27X_PBUS_CKEN(NULL, "MSTKCLK", MEMSTK, 2, 32, 0),
+	PXA27X_PBUS_CKEN(NULL, "AC97CLK", AC97, 1, 1, 0),
+	PXA27X_PBUS_CKEN(NULL, "AC97CONFCLK", AC97CONF, 1, 1, 0),
+	PXA27X_PBUS_CKEN(NULL, "OSTIMER0", OSTIMER, 1, 96, 0),
+
+	PXA27X_CKEN_1RATE("pxa27x-keypad", NULL, KEYPAD,
+			  pxa27x_32Mhz_bus_parents, 0),
+	PXA27X_CKEN_1RATE(NULL, "IMCLK", IM, pxa27x_sbus_parents, 0),
+	PXA27X_CKEN_1RATE("pxa2xx-fb", NULL, LCD, pxa27x_lcd_bus_parents, 0),
+	PXA27X_CKEN_1RATE("pxa27x-camera.0", NULL, CAMERA,
+			  pxa27x_lcd_bus_parents, 0),
+	PXA27X_CKEN_1RATE_AO("pxa2xx-pcmcia", NULL, MEMC,
+			     pxa27x_membus_parents, 0),
+
+};
+
+static unsigned long clk_pxa27x_cpll_get_rate(struct clk_hw *hw,
+	unsigned long parent_rate)
+{
+	unsigned long clkcfg;
+	unsigned int t, ht;
+	unsigned int l, L, n2, N;
+	unsigned long ccsr = CCSR;
+
+	asm("mrc\tp14, 0, %0, c6, c0, 0" : "=r" (clkcfg));
+	t  = clkcfg & (1 << 0);
+	ht = clkcfg & (1 << 2);
+
+	l  = ccsr & CCSR_L_MASK;
+	n2 = (ccsr & CCSR_N2_MASK) >> CCSR_N2_SHIFT;
+	L  = l * parent_rate;
+	N  = (L * n2) / 2;
+
+	return t ? N : L;
+}
+PARENTS(clk_pxa27x_cpll) = { "osc_13mhz" };
+RATE_RO_OPS(clk_pxa27x_cpll, "cpll");
+
+static unsigned long clk_pxa27x_lcd_base_get_rate(struct clk_hw *hw,
+						  unsigned long parent_rate)
+{
+	unsigned int l, osc_forced;
+	unsigned long ccsr = CCSR;
+	unsigned long cccr = CCCR;
+
+	l  = ccsr & CCSR_L_MASK;
+	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
+	if (osc_forced) {
+		if (cccr & (1 << CCCR_LCD_26_BIT))
+			return parent_rate * 2;
+		else
+			return parent_rate;
+	}
+
+	if (l <= 7)
+		return parent_rate;
+	if (l <= 16)
+		return parent_rate / 2;
+	return parent_rate / 4;
+}
+
+static u8 clk_pxa27x_lcd_base_get_parent(struct clk_hw *hw)
+{
+	unsigned int osc_forced;
+	unsigned long ccsr = CCSR;
+
+	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
+	if (osc_forced)
+		return PXA_LCD_13Mhz;
+	else
+		return PXA_LCD_RUN;
+}
+
+PARENTS(clk_pxa27x_lcd_base) = { "osc_13mhz", "run" };
+MUX_RO_RATE_RO_OPS(clk_pxa27x_lcd_base, "lcd_base");
+
+static void __init pxa27x_register_plls(void)
+{
+	clk_register_fixed_rate(NULL, "osc_13mhz", NULL,
+				CLK_GET_RATE_NOCACHE | CLK_IS_ROOT,
+				13 * MHz);
+	clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
+				CLK_GET_RATE_NOCACHE | CLK_IS_ROOT,
+				32768 * KHz);
+	clk_register_fixed_rate(NULL, "clk_dummy", NULL, CLK_IS_ROOT, 0);
+	clk_register_fixed_factor(NULL, "ppll_312mhz", "osc_13mhz", 0, 24, 1);
+}
+
+static unsigned long clk_pxa27x_core_get_rate(struct clk_hw *hw,
+					      unsigned long parent_rate)
+{
+	unsigned long clkcfg;
+	unsigned int t, ht, b, osc_forced;
+	unsigned long ccsr = CCSR;
+
+	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
+	asm("mrc\tp14, 0, %0, c6, c0, 0" : "=r" (clkcfg));
+	t  = clkcfg & (1 << 0);
+	ht = clkcfg & (1 << 2);
+	b  = clkcfg & (1 << 3);
+
+	if (osc_forced)
+		return parent_rate;
+	if (ht)
+		return parent_rate / 2;
+	else
+		return parent_rate;
+}
+
+static u8 clk_pxa27x_core_get_parent(struct clk_hw *hw)
+{
+	unsigned long clkcfg;
+	unsigned int t, ht, b, osc_forced;
+	unsigned long ccsr = CCSR;
+
+	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
+	if (osc_forced)
+		return PXA_CORE_13Mhz;
+
+	asm("mrc\tp14, 0, %0, c6, c0, 0" : "=r" (clkcfg));
+	t  = clkcfg & (1 << 0);
+	ht = clkcfg & (1 << 2);
+	b  = clkcfg & (1 << 3);
+
+	if (ht || t)
+		return PXA_CORE_TURBO;
+	return PXA_CORE_RUN;
+}
+PARENTS(clk_pxa27x_core) = { "osc_13mhz", "run", "cpll" };
+MUX_RO_RATE_RO_OPS(clk_pxa27x_core, "core");
+
+static unsigned long clk_pxa27x_run_get_rate(struct clk_hw *hw,
+					     unsigned long parent_rate)
+{
+	unsigned long ccsr = CCSR;
+	unsigned int n2 = (ccsr & CCSR_N2_MASK) >> CCSR_N2_SHIFT;
+
+	return (parent_rate / n2) * 2;
+}
+PARENTS(clk_pxa27x_run) = { "cpll" };
+RATE_RO_OPS(clk_pxa27x_run, "run");
+
+static void __init pxa27x_register_core(void)
+{
+	clk_register_clk_pxa27x_cpll();
+	clk_register_clk_pxa27x_run();
+
+	clkdev_pxa_register(CLK_CORE, "core", NULL,
+			    clk_register_clk_pxa27x_core());
+}
+
+static unsigned long clk_pxa27x_system_bus_get_rate(struct clk_hw *hw,
+						    unsigned long parent_rate)
+{
+	unsigned long clkcfg;
+	unsigned int b, osc_forced;
+	unsigned long ccsr = CCSR;
+
+	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
+	asm("mrc\tp14, 0, %0, c6, c0, 0" : "=r" (clkcfg));
+	b  = clkcfg & (1 << 3);
+
+	if (osc_forced)
+		return parent_rate;
+	if (b)
+		return parent_rate / 2;
+	else
+		return parent_rate;
+}
+
+static u8 clk_pxa27x_system_bus_get_parent(struct clk_hw *hw)
+{
+	unsigned int osc_forced;
+	unsigned long ccsr = CCSR;
+
+	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
+	if (osc_forced)
+		return PXA_BUS_13Mhz;
+	else
+		return PXA_BUS_RUN;
+}
+
+PARENTS(clk_pxa27x_system_bus) = { "osc_13mhz", "run" };
+MUX_RO_RATE_RO_OPS(clk_pxa27x_system_bus, "system_bus");
+
+static unsigned long clk_pxa27x_memory_get_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
+{
+	unsigned int a, l, osc_forced;
+	unsigned long cccr = CCCR;
+	unsigned long ccsr = CCSR;
+
+	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
+	a = cccr & CCCR_A_BIT;
+	l  = ccsr & CCSR_L_MASK;
+
+	if (osc_forced || a)
+		return parent_rate;
+	if (l <= 10)
+		return parent_rate;
+	if (l <= 20)
+		return parent_rate / 2;
+	return parent_rate / 4;
+}
+
+static u8 clk_pxa27x_memory_get_parent(struct clk_hw *hw)
+{
+	unsigned int osc_forced, a;
+	unsigned long cccr = CCCR;
+	unsigned long ccsr = CCSR;
+
+	osc_forced = ccsr & (1 << CCCR_CPDIS_BIT);
+	a = cccr & CCCR_A_BIT;
+	if (osc_forced)
+		return PXA_MEM_13Mhz;
+	if (a)
+		return PXA_MEM_SYSTEM_BUS;
+	else
+		return PXA_MEM_RUN;
+}
+
+PARENTS(clk_pxa27x_memory) = { "osc_13mhz", "system_bus", "run" };
+MUX_RO_RATE_RO_OPS(clk_pxa27x_memory, "memory");
+
+static void __init pxa27x_base_clocks_init(void)
+{
+	pxa27x_register_plls();
+	pxa27x_register_core();
+	clk_register_clk_pxa27x_system_bus();
+	clk_register_clk_pxa27x_memory();
+	clk_register_clk_pxa27x_lcd_base();
+}
+
+static int __init pxa27x_clocks_init(void)
+{
+	pxa27x_base_clocks_init();
+	return clk_pxa_cken_init(pxa27x_clocks, ARRAY_SIZE(pxa27x_clocks));
+}
+postcore_initcall(pxa27x_clocks_init);
diff --git a/drivers/clk/qcom/clk-pll.c b/drivers/clk/qcom/clk-pll.c
index 9db03d3b1657..b823bc3b6250 100644
--- a/drivers/clk/qcom/clk-pll.c
+++ b/drivers/clk/qcom/clk-pll.c
@@ -97,7 +97,7 @@ static unsigned long
 clk_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 {
 	struct clk_pll *pll = to_clk_pll(hw);
-	u32 l, m, n;
+	u32 l, m, n, config;
 	unsigned long rate;
 	u64 tmp;
 
@@ -116,13 +116,79 @@ clk_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 		do_div(tmp, n);
 		rate += tmp;
 	}
+	if (pll->post_div_width) {
+		regmap_read(pll->clkr.regmap, pll->config_reg, &config);
+		config >>= pll->post_div_shift;
+		config &= BIT(pll->post_div_width) - 1;
+		rate /= config + 1;
+	}
+
 	return rate;
 }
 
+static const
+struct pll_freq_tbl *find_freq(const struct pll_freq_tbl *f, unsigned long rate)
+{
+	if (!f)
+		return NULL;
+
+	for (; f->freq; f++)
+		if (rate <= f->freq)
+			return f;
+
+	return NULL;
+}
+
+static long
+clk_pll_determine_rate(struct clk_hw *hw, unsigned long rate,
+		       unsigned long *p_rate, struct clk **p)
+{
+	struct clk_pll *pll = to_clk_pll(hw);
+	const struct pll_freq_tbl *f;
+
+	f = find_freq(pll->freq_tbl, rate);
+	if (!f)
+		return clk_pll_recalc_rate(hw, *p_rate);
+
+	return f->freq;
+}
+
+static int
+clk_pll_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long p_rate)
+{
+	struct clk_pll *pll = to_clk_pll(hw);
+	const struct pll_freq_tbl *f;
+	bool enabled;
+	u32 mode;
+	u32 enable_mask = PLL_OUTCTRL | PLL_BYPASSNL | PLL_RESET_N;
+
+	f = find_freq(pll->freq_tbl, rate);
+	if (!f)
+		return -EINVAL;
+
+	regmap_read(pll->clkr.regmap, pll->mode_reg, &mode);
+	enabled = (mode & enable_mask) == enable_mask;
+
+	if (enabled)
+		clk_pll_disable(hw);
+
+	regmap_update_bits(pll->clkr.regmap, pll->l_reg, 0x3ff, f->l);
+	regmap_update_bits(pll->clkr.regmap, pll->m_reg, 0x7ffff, f->m);
+	regmap_update_bits(pll->clkr.regmap, pll->n_reg, 0x7ffff, f->n);
+	regmap_write(pll->clkr.regmap, pll->config_reg, f->ibits);
+
+	if (enabled)
+		clk_pll_enable(hw);
+
+	return 0;
+}
+
 const struct clk_ops clk_pll_ops = {
 	.enable = clk_pll_enable,
 	.disable = clk_pll_disable,
 	.recalc_rate = clk_pll_recalc_rate,
+	.determine_rate = clk_pll_determine_rate,
+	.set_rate = clk_pll_set_rate,
 };
 EXPORT_SYMBOL_GPL(clk_pll_ops);
 
diff --git a/drivers/clk/qcom/clk-pll.h b/drivers/clk/qcom/clk-pll.h
index 3003e9962472..c9c0cda306d0 100644
--- a/drivers/clk/qcom/clk-pll.h
+++ b/drivers/clk/qcom/clk-pll.h
@@ -18,6 +18,21 @@
 #include "clk-regmap.h"
 
 /**
+ * struct pll_freq_tbl - PLL frequency table
+ * @l: L value
+ * @m: M value
+ * @n: N value
+ * @ibits: internal values
+ */
+struct pll_freq_tbl {
+	unsigned long freq;
+	u16 l;
+	u16 m;
+	u16 n;
+	u32 ibits;
+};
+
+/**
  * struct clk_pll - phase locked loop (PLL)
  * @l_reg: L register
  * @m_reg: M register
@@ -26,6 +41,7 @@
  * @mode_reg: mode register
  * @status_reg: status register
  * @status_bit: ANDed with @status_reg to determine if PLL is enabled
+ * @freq_tbl: PLL frequency table
  * @hw: handle between common and hardware-specific interfaces
  */
 struct clk_pll {
@@ -36,6 +52,10 @@ struct clk_pll {
 	u32	mode_reg;
 	u32	status_reg;
 	u8	status_bit;
+	u8	post_div_width;
+	u8	post_div_shift;
+
+	const struct pll_freq_tbl *freq_tbl;
 
 	struct clk_regmap clkr;
 };
diff --git a/drivers/clk/qcom/clk-rcg.c b/drivers/clk/qcom/clk-rcg.c
index b638c5846dbf..b6e6959e89aa 100644
--- a/drivers/clk/qcom/clk-rcg.c
+++ b/drivers/clk/qcom/clk-rcg.c
@@ -21,6 +21,7 @@
 #include <asm/div64.h>
 
 #include "clk-rcg.h"
+#include "common.h"
 
 static u32 ns_to_src(struct src_sel *s, u32 ns)
 {
@@ -67,16 +68,16 @@ static u8 clk_dyn_rcg_get_parent(struct clk_hw *hw)
 {
 	struct clk_dyn_rcg *rcg = to_clk_dyn_rcg(hw);
 	int num_parents = __clk_get_num_parents(hw->clk);
-	u32 ns, ctl;
+	u32 ns, reg;
 	int bank;
 	int i;
 	struct src_sel *s;
 
-	regmap_read(rcg->clkr.regmap, rcg->clkr.enable_reg, &ctl);
-	bank = reg_to_bank(rcg, ctl);
+	regmap_read(rcg->clkr.regmap, rcg->bank_reg, &reg);
+	bank = reg_to_bank(rcg, reg);
 	s = &rcg->s[bank];
 
-	regmap_read(rcg->clkr.regmap, rcg->ns_reg, &ns);
+	regmap_read(rcg->clkr.regmap, rcg->ns_reg[bank], &ns);
 	ns = ns_to_src(s, ns);
 
 	for (i = 0; i < num_parents; i++)
@@ -192,90 +193,93 @@ static u32 mn_to_reg(struct mn *mn, u32 m, u32 n, u32 val)
 
 static void configure_bank(struct clk_dyn_rcg *rcg, const struct freq_tbl *f)
 {
-	u32 ns, md, ctl, *regp;
+	u32 ns, md, reg;
 	int bank, new_bank;
 	struct mn *mn;
 	struct pre_div *p;
 	struct src_sel *s;
 	bool enabled;
-	u32 md_reg;
-	u32 bank_reg;
+	u32 md_reg, ns_reg;
 	bool banked_mn = !!rcg->mn[1].width;
+	bool banked_p = !!rcg->p[1].pre_div_width;
 	struct clk_hw *hw = &rcg->clkr.hw;
 
 	enabled = __clk_is_enabled(hw->clk);
 
-	regmap_read(rcg->clkr.regmap, rcg->ns_reg, &ns);
-	regmap_read(rcg->clkr.regmap, rcg->clkr.enable_reg, &ctl);
-
-	if (banked_mn) {
-		regp = &ctl;
-		bank_reg = rcg->clkr.enable_reg;
-	} else {
-		regp = &ns;
-		bank_reg = rcg->ns_reg;
-	}
-
-	bank = reg_to_bank(rcg, *regp);
+	regmap_read(rcg->clkr.regmap, rcg->bank_reg, &reg);
+	bank = reg_to_bank(rcg, reg);
 	new_bank = enabled ? !bank : bank;
 
+	ns_reg = rcg->ns_reg[new_bank];
+	regmap_read(rcg->clkr.regmap, ns_reg, &ns);
+
 	if (banked_mn) {
 		mn = &rcg->mn[new_bank];
 		md_reg = rcg->md_reg[new_bank];
 
 		ns |= BIT(mn->mnctr_reset_bit);
-		regmap_write(rcg->clkr.regmap, rcg->ns_reg, ns);
+		regmap_write(rcg->clkr.regmap, ns_reg, ns);
 
 		regmap_read(rcg->clkr.regmap, md_reg, &md);
 		md = mn_to_md(mn, f->m, f->n, md);
 		regmap_write(rcg->clkr.regmap, md_reg, md);
 
 		ns = mn_to_ns(mn, f->m, f->n, ns);
-		regmap_write(rcg->clkr.regmap, rcg->ns_reg, ns);
+		regmap_write(rcg->clkr.regmap, ns_reg, ns);
 
-		ctl = mn_to_reg(mn, f->m, f->n, ctl);
-		regmap_write(rcg->clkr.regmap, rcg->clkr.enable_reg, ctl);
+		/* Two NS registers means mode control is in NS register */
+		if (rcg->ns_reg[0] != rcg->ns_reg[1]) {
+			ns = mn_to_reg(mn, f->m, f->n, ns);
+			regmap_write(rcg->clkr.regmap, ns_reg, ns);
+		} else {
+			reg = mn_to_reg(mn, f->m, f->n, reg);
+			regmap_write(rcg->clkr.regmap, rcg->bank_reg, reg);
+		}
 
 		ns &= ~BIT(mn->mnctr_reset_bit);
-		regmap_write(rcg->clkr.regmap, rcg->ns_reg, ns);
-	} else {
+		regmap_write(rcg->clkr.regmap, ns_reg, ns);
+	}
+
+	if (banked_p) {
 		p = &rcg->p[new_bank];
 		ns = pre_div_to_ns(p, f->pre_div - 1, ns);
 	}
 
 	s = &rcg->s[new_bank];
 	ns = src_to_ns(s, s->parent_map[f->src], ns);
-	regmap_write(rcg->clkr.regmap, rcg->ns_reg, ns);
+	regmap_write(rcg->clkr.regmap, ns_reg, ns);
 
 	if (enabled) {
-		*regp ^= BIT(rcg->mux_sel_bit);
-		regmap_write(rcg->clkr.regmap, bank_reg, *regp);
+		regmap_read(rcg->clkr.regmap, rcg->bank_reg, &reg);
+		reg ^= BIT(rcg->mux_sel_bit);
+		regmap_write(rcg->clkr.regmap, rcg->bank_reg, reg);
 	}
 }
 
 static int clk_dyn_rcg_set_parent(struct clk_hw *hw, u8 index)
 {
 	struct clk_dyn_rcg *rcg = to_clk_dyn_rcg(hw);
-	u32 ns, ctl, md, reg;
+	u32 ns, md, reg;
 	int bank;
 	struct freq_tbl f = { 0 };
 	bool banked_mn = !!rcg->mn[1].width;
+	bool banked_p = !!rcg->p[1].pre_div_width;
 
-	regmap_read(rcg->clkr.regmap, rcg->ns_reg, &ns);
-	regmap_read(rcg->clkr.regmap, rcg->clkr.enable_reg, &ctl);
-	reg = banked_mn ? ctl : ns;
-
+	regmap_read(rcg->clkr.regmap, rcg->bank_reg, &reg);
 	bank = reg_to_bank(rcg, reg);
 
+	regmap_read(rcg->clkr.regmap, rcg->ns_reg[bank], &ns);
+
 	if (banked_mn) {
 		regmap_read(rcg->clkr.regmap, rcg->md_reg[bank], &md);
 		f.m = md_to_m(&rcg->mn[bank], md);
 		f.n = ns_m_to_n(&rcg->mn[bank], ns, f.m);
-	} else {
-		f.pre_div = ns_to_pre_div(&rcg->p[bank], ns) + 1;
 	}
-	f.src = index;
 
+	if (banked_p)
+		f.pre_div = ns_to_pre_div(&rcg->p[bank], ns) + 1;
+
+	f.src = index;
 	configure_bank(rcg, &f);
 
 	return 0;
@@ -336,41 +340,30 @@ clk_dyn_rcg_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	u32 m, n, pre_div, ns, md, mode, reg;
 	int bank;
 	struct mn *mn;
+	bool banked_p = !!rcg->p[1].pre_div_width;
 	bool banked_mn = !!rcg->mn[1].width;
 
-	regmap_read(rcg->clkr.regmap, rcg->ns_reg, &ns);
-
-	if (banked_mn)
-		regmap_read(rcg->clkr.regmap, rcg->clkr.enable_reg, &reg);
-	else
-		reg = ns;
-
+	regmap_read(rcg->clkr.regmap, rcg->bank_reg, &reg);
 	bank = reg_to_bank(rcg, reg);
 
+	regmap_read(rcg->clkr.regmap, rcg->ns_reg[bank], &ns);
+	m = n = pre_div = mode = 0;
+
 	if (banked_mn) {
 		mn = &rcg->mn[bank];
 		regmap_read(rcg->clkr.regmap, rcg->md_reg[bank], &md);
 		m = md_to_m(mn, md);
 		n = ns_m_to_n(mn, ns, m);
+		/* Two NS registers means mode control is in NS register */
+		if (rcg->ns_reg[0] != rcg->ns_reg[1])
+			reg = ns;
 		mode = reg_to_mnctr_mode(mn, reg);
-		return calc_rate(parent_rate, m, n, mode, 0);
-	} else {
-		pre_div = ns_to_pre_div(&rcg->p[bank], ns);
-		return calc_rate(parent_rate, 0, 0, 0, pre_div);
 	}
-}
 
-static const
-struct freq_tbl *find_freq(const struct freq_tbl *f, unsigned long rate)
-{
-	if (!f)
-		return NULL;
-
-	for (; f->freq; f++)
-		if (rate <= f->freq)
-			return f;
+	if (banked_p)
+		pre_div = ns_to_pre_div(&rcg->p[bank], ns);
 
-	return NULL;
+	return calc_rate(parent_rate, m, n, mode, pre_div);
 }
 
 static long _freq_tbl_determine_rate(struct clk_hw *hw,
@@ -379,7 +372,7 @@ static long _freq_tbl_determine_rate(struct clk_hw *hw,
 {
 	unsigned long clk_flags;
 
-	f = find_freq(f, rate);
+	f = qcom_find_freq(f, rate);
 	if (!f)
 		return -EINVAL;
 
@@ -477,7 +470,7 @@ static int clk_rcg_set_rate(struct clk_hw *hw, unsigned long rate,
 	struct clk_rcg *rcg = to_clk_rcg(hw);
 	const struct freq_tbl *f;
 
-	f = find_freq(rcg->freq_tbl, rate);
+	f = qcom_find_freq(rcg->freq_tbl, rate);
 	if (!f)
 		return -EINVAL;
 
@@ -497,7 +490,7 @@ static int __clk_dyn_rcg_set_rate(struct clk_hw *hw, unsigned long rate)
 	struct clk_dyn_rcg *rcg = to_clk_dyn_rcg(hw);
 	const struct freq_tbl *f;
 
-	f = find_freq(rcg->freq_tbl, rate);
+	f = qcom_find_freq(rcg->freq_tbl, rate);
 	if (!f)
 		return -EINVAL;
 
diff --git a/drivers/clk/qcom/clk-rcg.h b/drivers/clk/qcom/clk-rcg.h
index ba0523cefd2e..687e41f91d7c 100644
--- a/drivers/clk/qcom/clk-rcg.h
+++ b/drivers/clk/qcom/clk-rcg.h
@@ -103,8 +103,9 @@ extern const struct clk_ops clk_rcg_bypass_ops;
  * struct clk_dyn_rcg - root clock generator with glitch free mux
  *
  * @mux_sel_bit: bit to switch glitch free mux
- * @ns_reg: NS register
+ * @ns_reg: NS0 and NS1 register
  * @md_reg: MD0 and MD1 register
+ * @bank_reg: register to XOR @mux_sel_bit into to switch glitch free mux
  * @mn: mn counter (banked)
  * @s: source selector (banked)
  * @freq_tbl: frequency table
@@ -113,8 +114,9 @@ extern const struct clk_ops clk_rcg_bypass_ops;
  *
  */
 struct clk_dyn_rcg {
-	u32	ns_reg;
+	u32	ns_reg[2];
 	u32	md_reg[2];
+	u32	bank_reg;
 
 	u8	mux_sel_bit;
 
diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index cd185d5cc67a..cfa9eb4fe9ca 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -24,6 +24,7 @@
 #include <asm/div64.h>
 
 #include "clk-rcg.h"
+#include "common.h"
 
 #define CMD_REG			0x0
 #define CMD_UPDATE		BIT(0)
@@ -172,27 +173,13 @@ clk_rcg2_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
 	return calc_rate(parent_rate, m, n, mode, hid_div);
 }
 
-static const
-struct freq_tbl *find_freq(const struct freq_tbl *f, unsigned long rate)
-{
-	if (!f)
-		return NULL;
-
-	for (; f->freq; f++)
-		if (rate <= f->freq)
-			return f;
-
-	/* Default to our fastest rate */
-	return f - 1;
-}
-
 static long _freq_tbl_determine_rate(struct clk_hw *hw,
 		const struct freq_tbl *f, unsigned long rate,
 		unsigned long *p_rate, struct clk **p)
 {
 	unsigned long clk_flags;
 
-	f = find_freq(f, rate);
+	f = qcom_find_freq(f, rate);
 	if (!f)
 		return -EINVAL;
 
@@ -268,7 +255,7 @@ static int __clk_rcg2_set_rate(struct clk_hw *hw, unsigned long rate)
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	const struct freq_tbl *f;
 
-	f = find_freq(rcg->freq_tbl, rate);
+	f = qcom_find_freq(rcg->freq_tbl, rate);
 	if (!f)
 		return -EINVAL;
 
diff --git a/drivers/clk/qcom/common.c b/drivers/clk/qcom/common.c
index eeb3eea01f4c..e20d947db3e5 100644
--- a/drivers/clk/qcom/common.c
+++ b/drivers/clk/qcom/common.c
@@ -18,6 +18,7 @@
 #include <linux/reset-controller.h>
 
 #include "common.h"
+#include "clk-rcg.h"
 #include "clk-regmap.h"
 #include "reset.h"
 
@@ -27,6 +28,21 @@ struct qcom_cc {
 	struct clk *clks[];
 };
 
+const
+struct freq_tbl *qcom_find_freq(const struct freq_tbl *f, unsigned long rate)
+{
+	if (!f)
+		return NULL;
+
+	for (; f->freq; f++)
+		if (rate <= f->freq)
+			return f;
+
+	/* Default to our fastest rate */
+	return f - 1;
+}
+EXPORT_SYMBOL_GPL(qcom_find_freq);
+
 struct regmap *
 qcom_cc_map(struct platform_device *pdev, const struct qcom_cc_desc *desc)
 {
diff --git a/drivers/clk/qcom/common.h b/drivers/clk/qcom/common.h
index 2765e9d3da97..f519322acdf3 100644
--- a/drivers/clk/qcom/common.h
+++ b/drivers/clk/qcom/common.h
@@ -18,6 +18,7 @@ struct regmap_config;
 struct clk_regmap;
 struct qcom_reset_map;
 struct regmap;
+struct freq_tbl;
 
 struct qcom_cc_desc {
 	const struct regmap_config *config;
@@ -27,6 +28,9 @@ struct qcom_cc_desc {
 	size_t num_resets;
 };
 
+extern const struct freq_tbl *qcom_find_freq(const struct freq_tbl *f,
+					     unsigned long rate);
+
 extern struct regmap *qcom_cc_map(struct platform_device *pdev,
 				  const struct qcom_cc_desc *desc);
 extern int qcom_cc_really_probe(struct platform_device *pdev,
diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c
index 3b83b7dd78c7..5cd62a709ac7 100644
--- a/drivers/clk/qcom/gcc-ipq806x.c
+++ b/drivers/clk/qcom/gcc-ipq806x.c
@@ -32,6 +32,33 @@
 #include "clk-branch.h"
 #include "reset.h"
 
+static struct clk_pll pll0 = {
+	.l_reg = 0x30c4,
+	.m_reg = 0x30c8,
+	.n_reg = 0x30cc,
+	.config_reg = 0x30d4,
+	.mode_reg = 0x30c0,
+	.status_reg = 0x30d8,
+	.status_bit = 16,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pll0",
+		.parent_names = (const char *[]){ "pxo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_regmap pll0_vote = {
+	.enable_reg = 0x34c0,
+	.enable_mask = BIT(0),
+	.hw.init = &(struct clk_init_data){
+		.name = "pll0_vote",
+		.parent_names = (const char *[]){ "pll0" },
+		.num_parents = 1,
+		.ops = &clk_pll_vote_ops,
+	},
+};
+
 static struct clk_pll pll3 = {
 	.l_reg = 0x3164,
 	.m_reg = 0x3168,
@@ -154,7 +181,7 @@ static const u8 gcc_pxo_pll8_pll0[] = {
 static const char *gcc_pxo_pll8_pll0_map[] = {
 	"pxo",
 	"pll8_vote",
-	"pll0",
+	"pll0_vote",
 };
 
 static struct freq_tbl clk_tbl_gsbi_uart[] = {
@@ -2133,6 +2160,8 @@ static struct clk_branch usb_fs1_h_clk = {
 };
 
 static struct clk_regmap *gcc_ipq806x_clks[] = {
+	[PLL0] = &pll0.clkr,
+	[PLL0_VOTE] = &pll0_vote,
 	[PLL3] = &pll3.clkr,
 	[PLL8] = &pll8.clkr,
 	[PLL8_VOTE] = &pll8_vote,
diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c
index 751eea376a2b..dab988ab8cf1 100644
--- a/drivers/clk/qcom/mmcc-apq8084.c
+++ b/drivers/clk/qcom/mmcc-apq8084.c
@@ -3341,7 +3341,6 @@ static struct platform_driver mmcc_apq8084_driver = {
 	.remove		= mmcc_apq8084_remove,
 	.driver		= {
 		.name	= "mmcc-apq8084",
-		.owner	= THIS_MODULE,
 		.of_match_table = mmcc_apq8084_match_table,
 	},
 };
diff --git a/drivers/clk/qcom/mmcc-msm8960.c b/drivers/clk/qcom/mmcc-msm8960.c
index 2e80a219b8ea..e8b33bbc362f 100644
--- a/drivers/clk/qcom/mmcc-msm8960.c
+++ b/drivers/clk/qcom/mmcc-msm8960.c
@@ -773,9 +773,11 @@ static struct freq_tbl clk_tbl_gfx2d[] = {
 };
 
 static struct clk_dyn_rcg gfx2d0_src = {
-	.ns_reg = 0x0070,
+	.ns_reg[0] = 0x0070,
+	.ns_reg[1] = 0x0070,
 	.md_reg[0] = 0x0064,
 	.md_reg[1] = 0x0068,
+	.bank_reg = 0x0060,
 	.mn[0] = {
 		.mnctr_en_bit = 8,
 		.mnctr_reset_bit = 25,
@@ -831,9 +833,11 @@ static struct clk_branch gfx2d0_clk = {
 };
 
 static struct clk_dyn_rcg gfx2d1_src = {
-	.ns_reg = 0x007c,
+	.ns_reg[0] = 0x007c,
+	.ns_reg[1] = 0x007c,
 	.md_reg[0] = 0x0078,
 	.md_reg[1] = 0x006c,
+	.bank_reg = 0x0074,
 	.mn[0] = {
 		.mnctr_en_bit = 8,
 		.mnctr_reset_bit = 25,
@@ -930,9 +934,11 @@ static struct freq_tbl clk_tbl_gfx3d_8064[] = {
 };
 
 static struct clk_dyn_rcg gfx3d_src = {
-	.ns_reg = 0x008c,
+	.ns_reg[0] = 0x008c,
+	.ns_reg[1] = 0x008c,
 	.md_reg[0] = 0x0084,
 	.md_reg[1] = 0x0088,
+	.bank_reg = 0x0080,
 	.mn[0] = {
 		.mnctr_en_bit = 8,
 		.mnctr_reset_bit = 25,
@@ -1006,9 +1012,11 @@ static struct freq_tbl clk_tbl_vcap[] = {
 };
 
 static struct clk_dyn_rcg vcap_src = {
-	.ns_reg = 0x021c,
+	.ns_reg[0] = 0x021c,
+	.ns_reg[1] = 0x021c,
 	.md_reg[0] = 0x01ec,
 	.md_reg[1] = 0x0218,
+	.bank_reg = 0x0178,
 	.mn[0] = {
 		.mnctr_en_bit = 8,
 		.mnctr_reset_bit = 23,
@@ -1211,9 +1219,11 @@ static struct freq_tbl clk_tbl_mdp[] = {
 };
 
 static struct clk_dyn_rcg mdp_src = {
-	.ns_reg = 0x00d0,
+	.ns_reg[0] = 0x00d0,
+	.ns_reg[1] = 0x00d0,
 	.md_reg[0] = 0x00c4,
 	.md_reg[1] = 0x00c8,
+	.bank_reg = 0x00c0,
 	.mn[0] = {
 		.mnctr_en_bit = 8,
 		.mnctr_reset_bit = 31,
@@ -1318,7 +1328,9 @@ static struct freq_tbl clk_tbl_rot[] = {
 };
 
 static struct clk_dyn_rcg rot_src = {
-	.ns_reg = 0x00e8,
+	.ns_reg[0] = 0x00e8,
+	.ns_reg[1] = 0x00e8,
+	.bank_reg = 0x00e8,
 	.p[0] = {
 		.pre_div_shift = 22,
 		.pre_div_width = 4,
@@ -1542,9 +1554,11 @@ static struct freq_tbl clk_tbl_vcodec[] = {
 };
 
 static struct clk_dyn_rcg vcodec_src = {
-	.ns_reg = 0x0100,
+	.ns_reg[0] = 0x0100,
+	.ns_reg[1] = 0x0100,
 	.md_reg[0] = 0x00fc,
 	.md_reg[1] = 0x0128,
+	.bank_reg = 0x00f8,
 	.mn[0] = {
 		.mnctr_en_bit = 5,
 		.mnctr_reset_bit = 31,
@@ -2679,7 +2693,6 @@ static struct platform_driver mmcc_msm8960_driver = {
 	.remove		= mmcc_msm8960_remove,
 	.driver		= {
 		.name	= "mmcc-msm8960",
-		.owner	= THIS_MODULE,
 		.of_match_table = mmcc_msm8960_match_table,
 	},
 };
diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c
index bc8f519c47aa..be94c54a9a4f 100644
--- a/drivers/clk/qcom/mmcc-msm8974.c
+++ b/drivers/clk/qcom/mmcc-msm8974.c
@@ -2570,7 +2570,6 @@ static struct platform_driver mmcc_msm8974_driver = {
 	.remove		= mmcc_msm8974_remove,
 	.driver		= {
 		.name	= "mmcc-msm8974",
-		.owner	= THIS_MODULE,
 		.of_match_table = mmcc_msm8974_match_table,
 	},
 };
diff --git a/drivers/clk/rockchip/Makefile b/drivers/clk/rockchip/Makefile
index ee6b077381e1..bd8514d63634 100644
--- a/drivers/clk/rockchip/Makefile
+++ b/drivers/clk/rockchip/Makefile
@@ -5,6 +5,7 @@
 obj-y	+= clk-rockchip.o
 obj-y	+= clk.o
 obj-y	+= clk-pll.o
+obj-y	+= clk-cpu.o
 obj-$(CONFIG_RESET_CONTROLLER)	+= softrst.o
 
 obj-y	+= clk-rk3188.o
diff --git a/drivers/clk/rockchip/clk-cpu.c b/drivers/clk/rockchip/clk-cpu.c
new file mode 100644
index 000000000000..75c8c45ef728
--- /dev/null
+++ b/drivers/clk/rockchip/clk-cpu.c
@@ -0,0 +1,329 @@
+/*
+ * Copyright (c) 2014 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * based on clk/samsung/clk-cpu.c
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Thomas Abraham <thomas.ab@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * A CPU clock is defined as a clock supplied to a CPU or a group of CPUs.
+ * The CPU clock is typically derived from a hierarchy of clock
+ * blocks which includes mux and divider blocks. There are a number of other
+ * auxiliary clocks supplied to the CPU domain such as the debug blocks and AXI
+ * clock for CPU domain. The rates of these auxiliary clocks are related to the
+ * CPU clock rate and this relation is usually specified in the hardware manual
+ * of the SoC or supplied after the SoC characterization.
+ *
+ * The below implementation of the CPU clock allows the rate changes of the CPU
+ * clock and the corresponding rate changes of the auxillary clocks of the CPU
+ * domain. The platform clock driver provides a clock register configuration
+ * for each configurable rate which is then used to program the clock hardware
+ * registers to acheive a fast co-oridinated rate change for all the CPU domain
+ * clocks.
+ *
+ * On a rate change request for the CPU clock, the rate change is propagated
+ * upto the PLL supplying the clock to the CPU domain clock blocks. While the
+ * CPU domain PLL is reconfigured, the CPU domain clocks are driven using an
+ * alternate clock source. If required, the alternate clock source is divided
+ * down in order to keep the output clock rate within the previous OPP limits.
+ */
+
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/clk-provider.h>
+#include "clk.h"
+
+/**
+ * struct rockchip_cpuclk: information about clock supplied to a CPU core.
+ * @hw:		handle between ccf and cpu clock.
+ * @alt_parent:	alternate parent clock to use when switching the speed
+ *		of the primary parent clock.
+ * @reg_base:	base register for cpu-clock values.
+ * @clk_nb:	clock notifier registered for changes in clock speed of the
+ *		primary parent clock.
+ * @rate_count:	number of rates in the rate_table
+ * @rate_table:	pll-rates and their associated dividers
+ * @reg_data:	cpu-specific register settings
+ * @lock:	clock lock
+ */
+struct rockchip_cpuclk {
+	struct clk_hw				hw;
+
+	struct clk_mux				cpu_mux;
+	const struct clk_ops			*cpu_mux_ops;
+
+	struct clk				*alt_parent;
+	void __iomem				*reg_base;
+	struct notifier_block			clk_nb;
+	unsigned int				rate_count;
+	struct rockchip_cpuclk_rate_table	*rate_table;
+	const struct rockchip_cpuclk_reg_data	*reg_data;
+	spinlock_t				*lock;
+};
+
+#define to_rockchip_cpuclk_hw(hw) container_of(hw, struct rockchip_cpuclk, hw)
+#define to_rockchip_cpuclk_nb(nb) \
+			container_of(nb, struct rockchip_cpuclk, clk_nb)
+
+static const struct rockchip_cpuclk_rate_table *rockchip_get_cpuclk_settings(
+			    struct rockchip_cpuclk *cpuclk, unsigned long rate)
+{
+	const struct rockchip_cpuclk_rate_table *rate_table =
+							cpuclk->rate_table;
+	int i;
+
+	for (i = 0; i < cpuclk->rate_count; i++) {
+		if (rate == rate_table[i].prate)
+			return &rate_table[i];
+	}
+
+	return NULL;
+}
+
+static unsigned long rockchip_cpuclk_recalc_rate(struct clk_hw *hw,
+					unsigned long parent_rate)
+{
+	struct rockchip_cpuclk *cpuclk = to_rockchip_cpuclk_hw(hw);
+	const struct rockchip_cpuclk_reg_data *reg_data = cpuclk->reg_data;
+	u32 clksel0 = readl_relaxed(cpuclk->reg_base + reg_data->core_reg);
+
+	clksel0 >>= reg_data->div_core_shift;
+	clksel0 &= reg_data->div_core_mask;
+	return parent_rate / (clksel0 + 1);
+}
+
+static const struct clk_ops rockchip_cpuclk_ops = {
+	.recalc_rate = rockchip_cpuclk_recalc_rate,
+};
+
+static void rockchip_cpuclk_set_dividers(struct rockchip_cpuclk *cpuclk,
+				const struct rockchip_cpuclk_rate_table *rate)
+{
+	int i;
+
+	/* alternate parent is active now. set the dividers */
+	for (i = 0; i < ARRAY_SIZE(rate->divs); i++) {
+		const struct rockchip_cpuclk_clksel *clksel = &rate->divs[i];
+
+		if (!clksel->reg)
+			continue;
+
+		pr_debug("%s: setting reg 0x%x to 0x%x\n",
+			 __func__, clksel->reg, clksel->val);
+		writel(clksel->val , cpuclk->reg_base + clksel->reg);
+	}
+}
+
+static int rockchip_cpuclk_pre_rate_change(struct rockchip_cpuclk *cpuclk,
+					   struct clk_notifier_data *ndata)
+{
+	const struct rockchip_cpuclk_reg_data *reg_data = cpuclk->reg_data;
+	unsigned long alt_prate, alt_div;
+
+	alt_prate = clk_get_rate(cpuclk->alt_parent);
+
+	spin_lock(cpuclk->lock);
+
+	/*
+	 * If the old parent clock speed is less than the clock speed
+	 * of the alternate parent, then it should be ensured that at no point
+	 * the armclk speed is more than the old_rate until the dividers are
+	 * set.
+	 */
+	if (alt_prate > ndata->old_rate) {
+		/* calculate dividers */
+		alt_div =  DIV_ROUND_UP(alt_prate, ndata->old_rate) - 1;
+		if (alt_div > reg_data->div_core_mask) {
+			pr_warn("%s: limiting alt-divider %lu to %d\n",
+				__func__, alt_div, reg_data->div_core_mask);
+			alt_div = reg_data->div_core_mask;
+		}
+
+		/*
+		 * Change parents and add dividers in a single transaction.
+		 *
+		 * NOTE: we do this in a single transaction so we're never
+		 * dividing the primary parent by the extra dividers that were
+		 * needed for the alt.
+		 */
+		pr_debug("%s: setting div %lu as alt-rate %lu > old-rate %lu\n",
+			 __func__, alt_div, alt_prate, ndata->old_rate);
+
+		writel(HIWORD_UPDATE(alt_div, reg_data->div_core_mask,
+					      reg_data->div_core_shift) |
+		       HIWORD_UPDATE(1, 1, reg_data->mux_core_shift),
+		       cpuclk->reg_base + reg_data->core_reg);
+	} else {
+		/* select alternate parent */
+		writel(HIWORD_UPDATE(1, 1, reg_data->mux_core_shift),
+			cpuclk->reg_base + reg_data->core_reg);
+	}
+
+	spin_unlock(cpuclk->lock);
+	return 0;
+}
+
+static int rockchip_cpuclk_post_rate_change(struct rockchip_cpuclk *cpuclk,
+					    struct clk_notifier_data *ndata)
+{
+	const struct rockchip_cpuclk_reg_data *reg_data = cpuclk->reg_data;
+	const struct rockchip_cpuclk_rate_table *rate;
+
+	rate = rockchip_get_cpuclk_settings(cpuclk, ndata->new_rate);
+	if (!rate) {
+		pr_err("%s: Invalid rate : %lu for cpuclk\n",
+		       __func__, ndata->new_rate);
+		return -EINVAL;
+	}
+
+	spin_lock(cpuclk->lock);
+
+	if (ndata->old_rate < ndata->new_rate)
+		rockchip_cpuclk_set_dividers(cpuclk, rate);
+
+	/*
+	 * post-rate change event, re-mux to primary parent and remove dividers.
+	 *
+	 * NOTE: we do this in a single transaction so we're never dividing the
+	 * primary parent by the extra dividers that were needed for the alt.
+	 */
+
+	writel(HIWORD_UPDATE(0, reg_data->div_core_mask,
+				reg_data->div_core_shift) |
+	       HIWORD_UPDATE(0, 1, reg_data->mux_core_shift),
+	       cpuclk->reg_base + reg_data->core_reg);
+
+	if (ndata->old_rate > ndata->new_rate)
+		rockchip_cpuclk_set_dividers(cpuclk, rate);
+
+	spin_unlock(cpuclk->lock);
+	return 0;
+}
+
+/*
+ * This clock notifier is called when the frequency of the parent clock
+ * of cpuclk is to be changed. This notifier handles the setting up all
+ * the divider clocks, remux to temporary parent and handling the safe
+ * frequency levels when using temporary parent.
+ */
+static int rockchip_cpuclk_notifier_cb(struct notifier_block *nb,
+					unsigned long event, void *data)
+{
+	struct clk_notifier_data *ndata = data;
+	struct rockchip_cpuclk *cpuclk = to_rockchip_cpuclk_nb(nb);
+	int ret = 0;
+
+	pr_debug("%s: event %lu, old_rate %lu, new_rate: %lu\n",
+		 __func__, event, ndata->old_rate, ndata->new_rate);
+	if (event == PRE_RATE_CHANGE)
+		ret = rockchip_cpuclk_pre_rate_change(cpuclk, ndata);
+	else if (event == POST_RATE_CHANGE)
+		ret = rockchip_cpuclk_post_rate_change(cpuclk, ndata);
+
+	return notifier_from_errno(ret);
+}
+
+struct clk *rockchip_clk_register_cpuclk(const char *name,
+			const char **parent_names, u8 num_parents,
+			const struct rockchip_cpuclk_reg_data *reg_data,
+			const struct rockchip_cpuclk_rate_table *rates,
+			int nrates, void __iomem *reg_base, spinlock_t *lock)
+{
+	struct rockchip_cpuclk *cpuclk;
+	struct clk_init_data init;
+	struct clk *clk, *cclk;
+	int ret;
+
+	if (num_parents != 2) {
+		pr_err("%s: needs two parent clocks\n", __func__);
+		return ERR_PTR(-EINVAL);
+	}
+
+	cpuclk = kzalloc(sizeof(*cpuclk), GFP_KERNEL);
+	if (!cpuclk)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.parent_names = &parent_names[0];
+	init.num_parents = 1;
+	init.ops = &rockchip_cpuclk_ops;
+
+	/* only allow rate changes when we have a rate table */
+	init.flags = (nrates > 0) ? CLK_SET_RATE_PARENT : 0;
+
+	/* disallow automatic parent changes by ccf */
+	init.flags |= CLK_SET_RATE_NO_REPARENT;
+
+	init.flags |= CLK_GET_RATE_NOCACHE;
+
+	cpuclk->reg_base = reg_base;
+	cpuclk->lock = lock;
+	cpuclk->reg_data = reg_data;
+	cpuclk->clk_nb.notifier_call = rockchip_cpuclk_notifier_cb;
+	cpuclk->hw.init = &init;
+
+	cpuclk->alt_parent = __clk_lookup(parent_names[1]);
+	if (!cpuclk->alt_parent) {
+		pr_err("%s: could not lookup alternate parent\n",
+		       __func__);
+		ret = -EINVAL;
+		goto free_cpuclk;
+	}
+
+	ret = clk_prepare_enable(cpuclk->alt_parent);
+	if (ret) {
+		pr_err("%s: could not enable alternate parent\n",
+		       __func__);
+		goto free_cpuclk;
+	}
+
+	clk = __clk_lookup(parent_names[0]);
+	if (!clk) {
+		pr_err("%s: could not lookup parent clock %s\n",
+		       __func__, parent_names[0]);
+		ret = -EINVAL;
+		goto free_cpuclk;
+	}
+
+	ret = clk_notifier_register(clk, &cpuclk->clk_nb);
+	if (ret) {
+		pr_err("%s: failed to register clock notifier for %s\n",
+				__func__, name);
+		goto free_cpuclk;
+	}
+
+	if (nrates > 0) {
+		cpuclk->rate_count = nrates;
+		cpuclk->rate_table = kmemdup(rates,
+					     sizeof(*rates) * nrates,
+					     GFP_KERNEL);
+		if (!cpuclk->rate_table) {
+			pr_err("%s: could not allocate memory for cpuclk rates\n",
+			       __func__);
+			ret = -ENOMEM;
+			goto unregister_notifier;
+		}
+	}
+
+	cclk = clk_register(NULL, &cpuclk->hw);
+	if (IS_ERR(clk)) {
+		pr_err("%s: could not register cpuclk %s\n", __func__,	name);
+		ret = PTR_ERR(clk);
+		goto free_rate_table;
+	}
+
+	return cclk;
+
+free_rate_table:
+	kfree(cpuclk->rate_table);
+unregister_notifier:
+	clk_notifier_unregister(clk, &cpuclk->clk_nb);
+free_cpuclk:
+	kfree(cpuclk);
+	return ERR_PTR(ret);
+}
diff --git a/drivers/clk/rockchip/clk-pll.c b/drivers/clk/rockchip/clk-pll.c
index f2a1c7abf4d9..a3e886a38480 100644
--- a/drivers/clk/rockchip/clk-pll.c
+++ b/drivers/clk/rockchip/clk-pll.c
@@ -34,7 +34,6 @@ struct rockchip_clk_pll {
 	const struct clk_ops	*pll_mux_ops;
 
 	struct notifier_block	clk_nb;
-	bool			rate_change_remuxed;
 
 	void __iomem		*reg_base;
 	int			lock_offset;
@@ -109,38 +108,6 @@ static int rockchip_pll_wait_lock(struct rockchip_clk_pll *pll)
 }
 
 /**
- * Set pll mux when changing the pll rate.
- * This makes sure to move the pll mux away from the actual pll before
- * changing its rate and back to the original parent after the change.
- */
-static int rockchip_pll_notifier_cb(struct notifier_block *nb,
-					unsigned long event, void *data)
-{
-	struct rockchip_clk_pll *pll = to_rockchip_clk_pll_nb(nb);
-	struct clk_mux *pll_mux = &pll->pll_mux;
-	const struct clk_ops *pll_mux_ops = pll->pll_mux_ops;
-	int cur_parent;
-
-	switch (event) {
-	case PRE_RATE_CHANGE:
-		cur_parent = pll_mux_ops->get_parent(&pll_mux->hw);
-		if (cur_parent == PLL_MODE_NORM) {
-			pll_mux_ops->set_parent(&pll_mux->hw, PLL_MODE_SLOW);
-			pll->rate_change_remuxed = 1;
-		}
-		break;
-	case POST_RATE_CHANGE:
-		if (pll->rate_change_remuxed) {
-			pll_mux_ops->set_parent(&pll_mux->hw, PLL_MODE_NORM);
-			pll->rate_change_remuxed = 0;
-		}
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-/**
  * PLL used in RK3066, RK3188 and RK3288
  */
 
@@ -194,6 +161,10 @@ static int rockchip_rk3066_pll_set_rate(struct clk_hw *hw, unsigned long drate,
 	const struct rockchip_pll_rate_table *rate;
 	unsigned long old_rate = rockchip_rk3066_pll_recalc_rate(hw, prate);
 	struct regmap *grf = rockchip_clk_get_grf();
+	struct clk_mux *pll_mux = &pll->pll_mux;
+	const struct clk_ops *pll_mux_ops = pll->pll_mux_ops;
+	int rate_change_remuxed = 0;
+	int cur_parent;
 	int ret;
 
 	if (IS_ERR(grf)) {
@@ -216,6 +187,12 @@ static int rockchip_rk3066_pll_set_rate(struct clk_hw *hw, unsigned long drate,
 	pr_debug("%s: rate settings for %lu (nr, no, nf): (%d, %d, %d)\n",
 		 __func__, rate->rate, rate->nr, rate->no, rate->nf);
 
+	cur_parent = pll_mux_ops->get_parent(&pll_mux->hw);
+	if (cur_parent == PLL_MODE_NORM) {
+		pll_mux_ops->set_parent(&pll_mux->hw, PLL_MODE_SLOW);
+		rate_change_remuxed = 1;
+	}
+
 	/* enter reset mode */
 	writel(HIWORD_UPDATE(RK3066_PLLCON3_RESET, RK3066_PLLCON3_RESET, 0),
 	       pll->reg_base + RK3066_PLLCON(3));
@@ -247,6 +224,9 @@ static int rockchip_rk3066_pll_set_rate(struct clk_hw *hw, unsigned long drate,
 		rockchip_rk3066_pll_set_rate(hw, old_rate, prate);
 	}
 
+	if (rate_change_remuxed)
+		pll_mux_ops->set_parent(&pll_mux->hw, PLL_MODE_NORM);
+
 	return ret;
 }
 
@@ -310,7 +290,6 @@ struct clk *rockchip_clk_register_pll(enum rockchip_pll_type pll_type,
 	struct clk_mux *pll_mux;
 	struct clk *pll_clk, *mux_clk;
 	char pll_name[20];
-	int ret;
 
 	if (num_parents != 2) {
 		pr_err("%s: needs two parent clocks\n", __func__);
@@ -367,7 +346,6 @@ struct clk *rockchip_clk_register_pll(enum rockchip_pll_type pll_type,
 	pll->lock_offset = grf_lock_offset;
 	pll->lock_shift = lock_shift;
 	pll->lock = lock;
-	pll->clk_nb.notifier_call = rockchip_pll_notifier_cb;
 
 	pll_clk = clk_register(NULL, &pll->hw);
 	if (IS_ERR(pll_clk)) {
@@ -377,14 +355,6 @@ struct clk *rockchip_clk_register_pll(enum rockchip_pll_type pll_type,
 		goto err_pll;
 	}
 
-	ret = clk_notifier_register(pll_clk, &pll->clk_nb);
-	if (ret) {
-		pr_err("%s: failed to register clock notifier for %s : %d\n",
-				__func__, name, ret);
-		mux_clk = ERR_PTR(ret);
-		goto err_pll_notifier;
-	}
-
 	/* create the mux on top of the real pll */
 	pll->pll_mux_ops = &clk_mux_ops;
 	pll_mux = &pll->pll_mux;
@@ -417,13 +387,6 @@ struct clk *rockchip_clk_register_pll(enum rockchip_pll_type pll_type,
 	return mux_clk;
 
 err_mux:
-	ret = clk_notifier_unregister(pll_clk, &pll->clk_nb);
-	if (ret) {
-		pr_err("%s: could not unregister clock notifier in error path : %d\n",
-		       __func__, ret);
-		return mux_clk;
-	}
-err_pll_notifier:
 	clk_unregister(pll_clk);
 err_pll:
 	kfree(pll);
diff --git a/drivers/clk/rockchip/clk-rk3188.c b/drivers/clk/rockchip/clk-rk3188.c
index a83a6d8d0fb6..beed49c79126 100644
--- a/drivers/clk/rockchip/clk-rk3188.c
+++ b/drivers/clk/rockchip/clk-rk3188.c
@@ -19,6 +19,7 @@
 #include <dt-bindings/clock/rk3188-cru-common.h>
 #include "clk.h"
 
+#define RK3066_GRF_SOC_STATUS	0x15c
 #define RK3188_GRF_SOC_STATUS	0xac
 
 enum rk3188_plls {
@@ -100,6 +101,98 @@ struct rockchip_pll_rate_table rk3188_pll_rates[] = {
 	{ /* sentinel */ },
 };
 
+#define RK3066_DIV_CORE_PERIPH_MASK	0x3
+#define RK3066_DIV_CORE_PERIPH_SHIFT	6
+#define RK3066_DIV_ACLK_CORE_MASK	0x7
+#define RK3066_DIV_ACLK_CORE_SHIFT	0
+#define RK3066_DIV_ACLK_HCLK_MASK	0x3
+#define RK3066_DIV_ACLK_HCLK_SHIFT	8
+#define RK3066_DIV_ACLK_PCLK_MASK	0x3
+#define RK3066_DIV_ACLK_PCLK_SHIFT	12
+#define RK3066_DIV_AHB2APB_MASK		0x3
+#define RK3066_DIV_AHB2APB_SHIFT	14
+
+#define RK3066_CLKSEL0(_core_peri)					\
+	{								\
+		.reg = RK2928_CLKSEL_CON(0),				\
+		.val = HIWORD_UPDATE(_core_peri, RK3066_DIV_CORE_PERIPH_MASK, \
+				RK3066_DIV_CORE_PERIPH_SHIFT)		\
+	}
+#define RK3066_CLKSEL1(_aclk_core, _aclk_hclk, _aclk_pclk, _ahb2apb)	\
+	{								\
+		.reg = RK2928_CLKSEL_CON(1),				\
+		.val = HIWORD_UPDATE(_aclk_core, RK3066_DIV_ACLK_CORE_MASK, \
+				RK3066_DIV_ACLK_CORE_SHIFT) |		\
+		       HIWORD_UPDATE(_aclk_hclk, RK3066_DIV_ACLK_HCLK_MASK, \
+				RK3066_DIV_ACLK_HCLK_SHIFT) |		\
+		       HIWORD_UPDATE(_aclk_pclk, RK3066_DIV_ACLK_PCLK_MASK, \
+				RK3066_DIV_ACLK_PCLK_SHIFT) |		\
+		       HIWORD_UPDATE(_ahb2apb, RK3066_DIV_AHB2APB_MASK,	\
+				RK3066_DIV_AHB2APB_SHIFT),		\
+	}
+
+#define RK3066_CPUCLK_RATE(_prate, _core_peri, _acore, _ahclk, _apclk, _h2p) \
+	{								\
+		.prate = _prate,					\
+		.divs = {						\
+			RK3066_CLKSEL0(_core_peri),			\
+			RK3066_CLKSEL1(_acore, _ahclk, _apclk, _h2p),	\
+		},							\
+	}
+
+static struct rockchip_cpuclk_rate_table rk3066_cpuclk_rates[] __initdata = {
+	RK3066_CPUCLK_RATE(1416000000, 2, 3, 1, 2, 1),
+	RK3066_CPUCLK_RATE(1200000000, 2, 3, 1, 2, 1),
+	RK3066_CPUCLK_RATE(1008000000, 2, 2, 1, 2, 1),
+	RK3066_CPUCLK_RATE( 816000000, 2, 2, 1, 2, 1),
+	RK3066_CPUCLK_RATE( 600000000, 1, 2, 1, 2, 1),
+	RK3066_CPUCLK_RATE( 504000000, 1, 1, 1, 2, 1),
+	RK3066_CPUCLK_RATE( 312000000, 0, 1, 1, 1, 0),
+};
+
+static const struct rockchip_cpuclk_reg_data rk3066_cpuclk_data = {
+	.core_reg = RK2928_CLKSEL_CON(0),
+	.div_core_shift = 0,
+	.div_core_mask = 0x1f,
+	.mux_core_shift = 8,
+};
+
+#define RK3188_DIV_ACLK_CORE_MASK	0x7
+#define RK3188_DIV_ACLK_CORE_SHIFT	3
+
+#define RK3188_CLKSEL1(_aclk_core)		\
+	{					\
+		.reg = RK2928_CLKSEL_CON(1),	\
+		.val = HIWORD_UPDATE(_aclk_core, RK3188_DIV_ACLK_CORE_MASK,\
+				 RK3188_DIV_ACLK_CORE_SHIFT) \
+	}
+#define RK3188_CPUCLK_RATE(_prate, _core_peri, _aclk_core)	\
+	{							\
+		.prate = _prate,				\
+		.divs = {					\
+			RK3066_CLKSEL0(_core_peri),		\
+			RK3188_CLKSEL1(_aclk_core),		\
+		},						\
+	}
+
+static struct rockchip_cpuclk_rate_table rk3188_cpuclk_rates[] __initdata = {
+	RK3188_CPUCLK_RATE(1608000000, 2, 3),
+	RK3188_CPUCLK_RATE(1416000000, 2, 3),
+	RK3188_CPUCLK_RATE(1200000000, 2, 3),
+	RK3188_CPUCLK_RATE(1008000000, 2, 3),
+	RK3188_CPUCLK_RATE( 816000000, 2, 3),
+	RK3188_CPUCLK_RATE( 600000000, 1, 3),
+	RK3188_CPUCLK_RATE( 504000000, 1, 3),
+	RK3188_CPUCLK_RATE( 312000000, 0, 1),
+};
+
+static const struct rockchip_cpuclk_reg_data rk3188_cpuclk_data = {
+	.core_reg = RK2928_CLKSEL_CON(0),
+	.div_core_shift = 9,
+	.div_core_mask = 0x1f,
+	.mux_core_shift = 8,
+};
+
 PNAME(mux_pll_p)		= { "xin24m", "xin32k" };
 PNAME(mux_armclk_p)		= { "apll", "gpll_armclk" };
 PNAME(mux_ddrphy_p)		= { "dpll", "gpll_ddr" };
@@ -173,17 +266,10 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 	GATE(0, "aclk_cpu", "aclk_cpu_pre", 0,
 			RK2928_CLKGATE_CON(0), 3, GFLAGS),
 
-	DIV(0, "pclk_cpu_pre", "aclk_cpu_pre", 0,
-			RK2928_CLKSEL_CON(1), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO),
 	GATE(0, "atclk_cpu", "pclk_cpu_pre", 0,
 			RK2928_CLKGATE_CON(0), 6, GFLAGS),
 	GATE(0, "pclk_cpu", "pclk_cpu_pre", 0,
 			RK2928_CLKGATE_CON(0), 5, GFLAGS),
-	DIV(0, "hclk_cpu_pre", "aclk_cpu_pre", 0,
-			RK2928_CLKSEL_CON(1), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO),
-	COMPOSITE_NOMUX(0, "hclk_ahb2apb", "hclk_cpu_pre", 0,
-			RK2928_CLKSEL_CON(1), 14, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
-			RK2928_CLKGATE_CON(4), 9, GFLAGS),
 	GATE(0, "hclk_cpu", "hclk_cpu_pre", 0,
 			RK2928_CLKGATE_CON(0), 4, GFLAGS),
 
@@ -412,10 +498,18 @@ static struct clk_div_table div_aclk_cpu_t[] = {
 };
 
 static struct rockchip_clk_branch rk3066a_clk_branches[] __initdata = {
-	COMPOSITE_NOGATE(0, "armclk", mux_armclk_p, 0,
-			RK2928_CLKSEL_CON(0), 8, 1, MFLAGS, 0, 5, DFLAGS),
 	DIVTBL(0, "aclk_cpu_pre", "armclk", 0,
-			RK2928_CLKSEL_CON(1), 0, 3, DFLAGS, div_aclk_cpu_t),
+			RK2928_CLKSEL_CON(1), 0, 3, DFLAGS | CLK_DIVIDER_READ_ONLY, div_aclk_cpu_t),
+	DIV(0, "pclk_cpu_pre", "aclk_cpu_pre", 0,
+			RK2928_CLKSEL_CON(1), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO
+							    | CLK_DIVIDER_READ_ONLY),
+	DIV(0, "hclk_cpu_pre", "aclk_cpu_pre", 0,
+			RK2928_CLKSEL_CON(1), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO
+							   | CLK_DIVIDER_READ_ONLY),
+	COMPOSITE_NOMUX(0, "hclk_ahb2apb", "hclk_cpu_pre", 0,
+			RK2928_CLKSEL_CON(1), 14, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO
+							    | CLK_DIVIDER_READ_ONLY,
+			RK2928_CLKGATE_CON(4), 9, GFLAGS),
 
 	GATE(CORE_L2C, "core_l2c", "aclk_cpu", 0,
 			RK2928_CLKGATE_CON(9), 4, GFLAGS),
@@ -524,8 +618,6 @@ PNAME(mux_hsicphy_p)		= { "sclk_otgphy0", "sclk_otgphy1",
 				    "gpll", "cpll" };
 
 static struct rockchip_clk_branch rk3188_clk_branches[] __initdata = {
-	COMPOSITE_NOGATE(0, "armclk", mux_armclk_p, 0,
-			RK2928_CLKSEL_CON(0), 8, 1, MFLAGS, 9, 5, DFLAGS),
 	COMPOSITE_NOMUX_DIVTBL(0, "aclk_core", "armclk", 0,
 			RK2928_CLKSEL_CON(1), 3, 3, DFLAGS | CLK_DIVIDER_READ_ONLY,
 			div_rk3188_aclk_core_t, RK2928_CLKGATE_CON(0), 7, GFLAGS),
@@ -533,6 +625,13 @@ static struct rockchip_clk_branch rk3188_clk_branches[] __initdata = {
 	/* do not source aclk_cpu_pre from the apll, to keep complexity down */
 	COMPOSITE_NOGATE(0, "aclk_cpu_pre", mux_aclk_cpu_p, CLK_SET_RATE_NO_REPARENT,
 			RK2928_CLKSEL_CON(0), 5, 1, MFLAGS, 0, 5, DFLAGS),
+	DIV(0, "pclk_cpu_pre", "aclk_cpu_pre", 0,
+			RK2928_CLKSEL_CON(1), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO),
+	DIV(0, "hclk_cpu_pre", "aclk_cpu_pre", 0,
+			RK2928_CLKSEL_CON(1), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO),
+	COMPOSITE_NOMUX(0, "hclk_ahb2apb", "hclk_cpu_pre", 0,
+			RK2928_CLKSEL_CON(1), 14, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
+			RK2928_CLKGATE_CON(4), 9, GFLAGS),
 
 	GATE(CORE_L2C, "core_l2c", "armclk", 0,
 			RK2928_CLKGATE_CON(9), 4, GFLAGS),
@@ -599,6 +698,12 @@ static struct rockchip_clk_branch rk3188_clk_branches[] __initdata = {
 	GATE(ACLK_GPS, "aclk_gps", "aclk_peri", 0, RK2928_CLKGATE_CON(8), 13, GFLAGS),
 };
 
+static const char *rk3188_critical_clocks[] __initconst = {
+	"aclk_cpu",
+	"aclk_peri",
+	"hclk_peri",
+};
+
 static void __init rk3188_common_clk_init(struct device_node *np)
 {
 	void __iomem *reg_base;
@@ -623,29 +728,65 @@ static void __init rk3188_common_clk_init(struct device_node *np)
 		pr_warn("%s: could not register clock usb480m: %ld\n",
 			__func__, PTR_ERR(clk));
 
-	rockchip_clk_register_plls(rk3188_pll_clks,
-				   ARRAY_SIZE(rk3188_pll_clks),
-				   RK3188_GRF_SOC_STATUS);
 	rockchip_clk_register_branches(common_clk_branches,
 				  ARRAY_SIZE(common_clk_branches));
+	rockchip_clk_protect_critical(rk3188_critical_clocks,
+				      ARRAY_SIZE(rk3188_critical_clocks));
 
 	rockchip_register_softrst(np, 9, reg_base + RK2928_SOFTRST_CON(0),
 				  ROCKCHIP_SOFTRST_HIWORD_MASK);
+
+	rockchip_register_restart_notifier(RK2928_GLB_SRST_FST);
 }
 
 static void __init rk3066a_clk_init(struct device_node *np)
 {
 	rk3188_common_clk_init(np);
+	rockchip_clk_register_plls(rk3188_pll_clks,
+				   ARRAY_SIZE(rk3188_pll_clks),
+				   RK3066_GRF_SOC_STATUS);
 	rockchip_clk_register_branches(rk3066a_clk_branches,
 				  ARRAY_SIZE(rk3066a_clk_branches));
+	rockchip_clk_register_armclk(ARMCLK, "armclk",
+			mux_armclk_p, ARRAY_SIZE(mux_armclk_p),
+			&rk3066_cpuclk_data, rk3066_cpuclk_rates,
+			ARRAY_SIZE(rk3066_cpuclk_rates));
 }
 CLK_OF_DECLARE(rk3066a_cru, "rockchip,rk3066a-cru", rk3066a_clk_init);
 
 static void __init rk3188a_clk_init(struct device_node *np)
 {
+	struct clk *clk1, *clk2;
+	unsigned long rate;
+	int ret;
+
 	rk3188_common_clk_init(np);
+	rockchip_clk_register_plls(rk3188_pll_clks,
+				   ARRAY_SIZE(rk3188_pll_clks),
+				   RK3188_GRF_SOC_STATUS);
 	rockchip_clk_register_branches(rk3188_clk_branches,
 				  ARRAY_SIZE(rk3188_clk_branches));
+	rockchip_clk_register_armclk(ARMCLK, "armclk",
+				  mux_armclk_p, ARRAY_SIZE(mux_armclk_p),
+				  &rk3188_cpuclk_data, rk3188_cpuclk_rates,
+				  ARRAY_SIZE(rk3188_cpuclk_rates));
+
+	/* reparent aclk_cpu_pre from apll */
+	clk1 = __clk_lookup("aclk_cpu_pre");
+	clk2 = __clk_lookup("gpll");
+	if (clk1 && clk2) {
+		rate = clk_get_rate(clk1);
+
+		ret = clk_set_parent(clk1, clk2);
+		if (ret < 0)
+			pr_warn("%s: could not reparent aclk_cpu_pre to gpll\n",
+				__func__);
+
+		clk_set_rate(clk1, rate);
+	} else {
+		pr_warn("%s: missing clocks to reparent aclk_cpu_pre to gpll\n",
+			__func__);
+	}
 }
 CLK_OF_DECLARE(rk3188a_cru, "rockchip,rk3188a-cru", rk3188a_clk_init);
 
diff --git a/drivers/clk/rockchip/clk-rk3288.c b/drivers/clk/rockchip/clk-rk3288.c
index b22a2d2f21e9..23278291da44 100644
--- a/drivers/clk/rockchip/clk-rk3288.c
+++ b/drivers/clk/rockchip/clk-rk3288.c
@@ -20,7 +20,7 @@
 #include "clk.h"
 
 #define RK3288_GRF_SOC_CON(x)	(0x244 + x * 4)
-#define RK3288_GRF_SOC_STATUS	0x280
+#define RK3288_GRF_SOC_STATUS1	0x284
 
 enum rk3288_plls {
 	apll, dpll, cpll, gpll, npll,
@@ -101,6 +101,70 @@ struct rockchip_pll_rate_table rk3288_pll_rates[] = {
 	{ /* sentinel */ },
 };
 
+#define RK3288_DIV_ACLK_CORE_M0_MASK	0xf
+#define RK3288_DIV_ACLK_CORE_M0_SHIFT	0
+#define RK3288_DIV_ACLK_CORE_MP_MASK	0xf
+#define RK3288_DIV_ACLK_CORE_MP_SHIFT	4
+#define RK3288_DIV_L2RAM_MASK		0x7
+#define RK3288_DIV_L2RAM_SHIFT		0
+#define RK3288_DIV_ATCLK_MASK		0x1f
+#define RK3288_DIV_ATCLK_SHIFT		4
+#define RK3288_DIV_PCLK_DBGPRE_MASK	0x1f
+#define RK3288_DIV_PCLK_DBGPRE_SHIFT	9
+
+#define RK3288_CLKSEL0(_core_m0, _core_mp)				\
+	{								\
+		.reg = RK3288_CLKSEL_CON(0),				\
+		.val = HIWORD_UPDATE(_core_m0, RK3288_DIV_ACLK_CORE_M0_MASK, \
+				RK3288_DIV_ACLK_CORE_M0_SHIFT) |	\
+		       HIWORD_UPDATE(_core_mp, RK3288_DIV_ACLK_CORE_MP_MASK, \
+				RK3288_DIV_ACLK_CORE_MP_SHIFT),		\
+	}
+#define RK3288_CLKSEL37(_l2ram, _atclk, _pclk_dbg_pre)			\
+	{								\
+		.reg = RK3288_CLKSEL_CON(37),				\
+		.val = HIWORD_UPDATE(_l2ram, RK3288_DIV_L2RAM_MASK,	\
+				RK3288_DIV_L2RAM_SHIFT) |		\
+		       HIWORD_UPDATE(_atclk, RK3288_DIV_ATCLK_MASK,	\
+				RK3288_DIV_ATCLK_SHIFT) |		\
+		       HIWORD_UPDATE(_pclk_dbg_pre,			\
+				RK3288_DIV_PCLK_DBGPRE_MASK,		\
+				RK3288_DIV_PCLK_DBGPRE_SHIFT),		\
+	}
+
+#define RK3288_CPUCLK_RATE(_prate, _core_m0, _core_mp, _l2ram, _atclk, _pdbg) \
+	{								\
+		.prate = _prate,					\
+		.divs = {						\
+			RK3288_CLKSEL0(_core_m0, _core_mp),		\
+			RK3288_CLKSEL37(_l2ram, _atclk, _pdbg),		\
+		},							\
+	}
+
+static struct rockchip_cpuclk_rate_table rk3288_cpuclk_rates[] __initdata = {
+	RK3288_CPUCLK_RATE(1800000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE(1704000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE(1608000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE(1512000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE(1416000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE(1200000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE(1008000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE( 816000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE( 696000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE( 600000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE( 408000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE( 312000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE( 216000000, 2, 4, 2, 4, 4),
+	RK3288_CPUCLK_RATE( 126000000, 2, 4, 2, 4, 4),
+};
+
+static const struct rockchip_cpuclk_reg_data rk3288_cpuclk_data = {
+	.core_reg = RK3288_CLKSEL_CON(0),
+	.div_core_shift = 8,
+	.div_core_mask = 0x1f,
+	.mux_core_shift = 15,
+};
+
 PNAME(mux_pll_p)		= { "xin24m", "xin32k" };
 PNAME(mux_armclk_p)		= { "apll_core", "gpll_core" };
 PNAME(mux_ddrphy_p)		= { "dpll_ddr", "gpll_ddr" };
@@ -143,7 +207,7 @@ static struct rockchip_pll_clock rk3288_pll_clks[] __initdata = {
 	[gpll] = PLL(pll_rk3066, PLL_GPLL, "gpll", mux_pll_p, 0, RK3288_PLL_CON(12),
 		     RK3288_MODE_CON, 12, 8, rk3288_pll_rates),
 	[npll] = PLL(pll_rk3066, PLL_NPLL, "npll",  mux_pll_p, 0, RK3288_PLL_CON(16),
-		     RK3288_MODE_CON, 14, 9, NULL),
+		     RK3288_MODE_CON, 14, 9, rk3288_pll_rates),
 };
 
 static struct clk_div_table div_hclk_cpu_t[] = {
@@ -166,35 +230,33 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 			RK3288_CLKGATE_CON(0), 1, GFLAGS),
 	GATE(0, "gpll_core", "gpll", 0,
 			RK3288_CLKGATE_CON(0), 2, GFLAGS),
-	COMPOSITE_NOGATE(0, "armclk", mux_armclk_p, 0,
-			RK3288_CLKSEL_CON(0), 15, 1, MFLAGS, 8, 5, DFLAGS),
 
 	COMPOSITE_NOMUX(0, "armcore0", "armclk", 0,
-			RK3288_CLKSEL_CON(36), 0, 3, DFLAGS,
+			RK3288_CLKSEL_CON(36), 0, 3, DFLAGS | CLK_DIVIDER_READ_ONLY,
 			RK3288_CLKGATE_CON(12), 0, GFLAGS),
 	COMPOSITE_NOMUX(0, "armcore1", "armclk", 0,
-			RK3288_CLKSEL_CON(36), 4, 3, DFLAGS,
+			RK3288_CLKSEL_CON(36), 4, 3, DFLAGS | CLK_DIVIDER_READ_ONLY,
 			RK3288_CLKGATE_CON(12), 1, GFLAGS),
 	COMPOSITE_NOMUX(0, "armcore2", "armclk", 0,
-			RK3288_CLKSEL_CON(36), 8, 3, DFLAGS,
+			RK3288_CLKSEL_CON(36), 8, 3, DFLAGS | CLK_DIVIDER_READ_ONLY,
 			RK3288_CLKGATE_CON(12), 2, GFLAGS),
 	COMPOSITE_NOMUX(0, "armcore3", "armclk", 0,
-			RK3288_CLKSEL_CON(36), 12, 3, DFLAGS,
+			RK3288_CLKSEL_CON(36), 12, 3, DFLAGS | CLK_DIVIDER_READ_ONLY,
 			RK3288_CLKGATE_CON(12), 3, GFLAGS),
 	COMPOSITE_NOMUX(0, "l2ram", "armclk", 0,
-			RK3288_CLKSEL_CON(37), 0, 3, DFLAGS,
+			RK3288_CLKSEL_CON(37), 0, 3, DFLAGS | CLK_DIVIDER_READ_ONLY,
 			RK3288_CLKGATE_CON(12), 4, GFLAGS),
 	COMPOSITE_NOMUX(0, "aclk_core_m0", "armclk", 0,
-			RK3288_CLKSEL_CON(0), 0, 4, DFLAGS,
+			RK3288_CLKSEL_CON(0), 0, 4, DFLAGS | CLK_DIVIDER_READ_ONLY,
 			RK3288_CLKGATE_CON(12), 5, GFLAGS),
 	COMPOSITE_NOMUX(0, "aclk_core_mp", "armclk", 0,
-			RK3288_CLKSEL_CON(0), 4, 4, DFLAGS,
+			RK3288_CLKSEL_CON(0), 4, 4, DFLAGS | CLK_DIVIDER_READ_ONLY,
 			RK3288_CLKGATE_CON(12), 6, GFLAGS),
 	COMPOSITE_NOMUX(0, "atclk", "armclk", 0,
-			RK3288_CLKSEL_CON(37), 4, 5, DFLAGS,
+			RK3288_CLKSEL_CON(37), 4, 5, DFLAGS | CLK_DIVIDER_READ_ONLY,
 			RK3288_CLKGATE_CON(12), 7, GFLAGS),
 	COMPOSITE_NOMUX(0, "pclk_dbg_pre", "armclk", 0,
-			RK3288_CLKSEL_CON(37), 9, 5, DFLAGS,
+			RK3288_CLKSEL_CON(37), 9, 5, DFLAGS | CLK_DIVIDER_READ_ONLY,
 			RK3288_CLKGATE_CON(12), 8, GFLAGS),
 	GATE(0, "pclk_dbg", "pclk_dbg_pre", 0,
 			RK3288_CLKGATE_CON(12), 9, GFLAGS),
@@ -219,12 +281,12 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 			RK3288_CLKSEL_CON(1), 15, 1, MFLAGS, 3, 5, DFLAGS),
 	DIV(0, "aclk_cpu_pre", "aclk_cpu_src", 0,
 			RK3288_CLKSEL_CON(1), 0, 3, DFLAGS),
-	GATE(0, "aclk_cpu", "aclk_cpu_pre", 0,
+	GATE(ACLK_CPU, "aclk_cpu", "aclk_cpu_pre", 0,
 			RK3288_CLKGATE_CON(0), 3, GFLAGS),
-	COMPOSITE_NOMUX(0, "pclk_cpu", "aclk_cpu_pre", 0,
+	COMPOSITE_NOMUX(PCLK_CPU, "pclk_cpu", "aclk_cpu_pre", 0,
 			RK3288_CLKSEL_CON(1), 12, 3, DFLAGS,
 			RK3288_CLKGATE_CON(0), 5, GFLAGS),
-	COMPOSITE_NOMUX_DIVTBL(0, "hclk_cpu", "aclk_cpu_pre", 0,
+	COMPOSITE_NOMUX_DIVTBL(HCLK_CPU, "hclk_cpu", "aclk_cpu_pre", 0,
 			RK3288_CLKSEL_CON(1), 8, 2, DFLAGS, div_hclk_cpu_t,
 			RK3288_CLKGATE_CON(0), 4, GFLAGS),
 	GATE(0, "c2c_host", "aclk_cpu_src", 0,
@@ -238,15 +300,15 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	COMPOSITE(0, "i2s_src", mux_pll_src_cpll_gpll_p, 0,
 			RK3288_CLKSEL_CON(4), 15, 1, MFLAGS, 0, 7, DFLAGS,
 			RK3288_CLKGATE_CON(4), 1, GFLAGS),
-	COMPOSITE_FRAC(0, "i2s_frac", "i2s_src", 0,
+	COMPOSITE_FRAC(0, "i2s_frac", "i2s_src", CLK_SET_RATE_PARENT,
 			RK3288_CLKSEL_CON(8), 0,
 			RK3288_CLKGATE_CON(4), 2, GFLAGS),
-	MUX(0, "i2s_pre", mux_i2s_pre_p, 0,
+	MUX(0, "i2s_pre", mux_i2s_pre_p, CLK_SET_RATE_PARENT,
 			RK3288_CLKSEL_CON(4), 8, 2, MFLAGS),
-	COMPOSITE_NODIV(0, "i2s0_clkout", mux_i2s_clkout_p, 0,
+	COMPOSITE_NODIV(0, "i2s0_clkout", mux_i2s_clkout_p, CLK_SET_RATE_PARENT,
 			RK3288_CLKSEL_CON(4), 12, 1, MFLAGS,
 			RK3288_CLKGATE_CON(4), 0, GFLAGS),
-	GATE(SCLK_I2S0, "sclk_i2s0", "i2s_pre", 0,
+	GATE(SCLK_I2S0, "sclk_i2s0", "i2s_pre", CLK_SET_RATE_PARENT,
 			RK3288_CLKGATE_CON(4), 3, GFLAGS),
 
 	MUX(0, "spdif_src", mux_pll_src_cpll_gpll_p, 0,
@@ -296,6 +358,20 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_usb480m_p, 0,
 			RK3288_CLKSEL_CON(32), 14, 2, MFLAGS, 8, 5, DFLAGS,
 			RK3288_CLKGATE_CON(3), 11, GFLAGS),
+	/*
+	 * We use aclk_vdpu by default GRF_SOC_CON0[7] setting in system,
+	 * so we ignore the mux and make clocks nodes as following,
+	 */
+	GATE(ACLK_VCODEC, "aclk_vcodec", "aclk_vdpu", 0,
+		RK3288_CLKGATE_CON(9), 0, GFLAGS),
+	/*
+	 * We introduce a virtul node of hclk_vodec_pre_v to split one clock
+	 * struct with a gate and a fix divider into two node in software.
+	 */
+	GATE(0, "hclk_vcodec_pre_v", "aclk_vdpu", 0,
+		RK3288_CLKGATE_CON(3), 10, GFLAGS),
+	GATE(HCLK_VCODEC, "hclk_vcodec", "hclk_vcodec_pre", 0,
+		RK3288_CLKGATE_CON(9), 1, GFLAGS),
 
 	COMPOSITE(0, "aclk_vio0", mux_pll_src_cpll_gpll_usb480m_p, 0,
 			RK3288_CLKSEL_CON(31), 6, 2, MFLAGS, 0, 5, DFLAGS,
@@ -309,7 +385,7 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	COMPOSITE(0, "aclk_rga_pre", mux_pll_src_cpll_gpll_usb480m_p, 0,
 			RK3288_CLKSEL_CON(30), 6, 2, MFLAGS, 0, 5, DFLAGS,
 			RK3288_CLKGATE_CON(3), 5, GFLAGS),
-	COMPOSITE(0, "sclk_rga", mux_pll_src_cpll_gpll_usb480m_p, 0,
+	COMPOSITE(SCLK_RGA, "sclk_rga", mux_pll_src_cpll_gpll_usb480m_p, 0,
 			RK3288_CLKSEL_CON(30), 14, 2, MFLAGS, 8, 5, DFLAGS,
 			RK3288_CLKGATE_CON(3), 4, GFLAGS),
 
@@ -320,35 +396,35 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 			RK3288_CLKSEL_CON(29), 6, 2, MFLAGS, 8, 8, DFLAGS,
 			RK3288_CLKGATE_CON(3), 3, GFLAGS),
 
-	COMPOSITE_NODIV(0, "sclk_edp_24m", mux_edp_24m_p, 0,
+	COMPOSITE_NODIV(SCLK_EDP_24M, "sclk_edp_24m", mux_edp_24m_p, 0,
 			RK3288_CLKSEL_CON(28), 15, 1, MFLAGS,
 			RK3288_CLKGATE_CON(3), 12, GFLAGS),
-	COMPOSITE(0, "sclk_edp", mux_pll_src_cpll_gpll_npll_p, 0,
+	COMPOSITE(SCLK_EDP, "sclk_edp", mux_pll_src_cpll_gpll_npll_p, 0,
 			RK3288_CLKSEL_CON(28), 6, 2, MFLAGS, 0, 6, DFLAGS,
 			RK3288_CLKGATE_CON(3), 13, GFLAGS),
 
-	COMPOSITE(0, "sclk_isp", mux_pll_src_cpll_gpll_npll_p, 0,
+	COMPOSITE(SCLK_ISP, "sclk_isp", mux_pll_src_cpll_gpll_npll_p, 0,
 			RK3288_CLKSEL_CON(6), 6, 2, MFLAGS, 0, 6, DFLAGS,
 			RK3288_CLKGATE_CON(3), 14, GFLAGS),
-	COMPOSITE(0, "sclk_isp_jpe", mux_pll_src_cpll_gpll_npll_p, 0,
+	COMPOSITE(SCLK_ISP_JPE, "sclk_isp_jpe", mux_pll_src_cpll_gpll_npll_p, 0,
 			RK3288_CLKSEL_CON(6), 14, 2, MFLAGS, 8, 6, DFLAGS,
 			RK3288_CLKGATE_CON(3), 15, GFLAGS),
 
-	GATE(0, "sclk_hdmi_hdcp", "xin24m", 0,
+	GATE(SCLK_HDMI_HDCP, "sclk_hdmi_hdcp", "xin24m", 0,
 			RK3288_CLKGATE_CON(5), 12, GFLAGS),
-	GATE(0, "sclk_hdmi_cec", "xin32k", 0,
+	GATE(SCLK_HDMI_CEC, "sclk_hdmi_cec", "xin32k", 0,
 			RK3288_CLKGATE_CON(5), 11, GFLAGS),
 
-	COMPOSITE(0, "aclk_hevc", mux_pll_src_cpll_gpll_npll_p, 0,
+	COMPOSITE(ACLK_HEVC, "aclk_hevc", mux_pll_src_cpll_gpll_npll_p, 0,
 			RK3288_CLKSEL_CON(39), 14, 2, MFLAGS, 8, 5, DFLAGS,
 			RK3288_CLKGATE_CON(13), 13, GFLAGS),
-	DIV(0, "hclk_hevc", "aclk_hevc", 0,
+	DIV(HCLK_HEVC, "hclk_hevc", "aclk_hevc", 0,
 			RK3288_CLKSEL_CON(40), 12, 2, DFLAGS),
 
-	COMPOSITE(0, "sclk_hevc_cabac", mux_pll_src_cpll_gpll_npll_p, 0,
+	COMPOSITE(SCLK_HEVC_CABAC, "sclk_hevc_cabac", mux_pll_src_cpll_gpll_npll_p, 0,
 			RK3288_CLKSEL_CON(42), 6, 2, MFLAGS, 0, 5, DFLAGS,
 			RK3288_CLKGATE_CON(13), 14, GFLAGS),
-	COMPOSITE(0, "sclk_hevc_core", mux_pll_src_cpll_gpll_npll_p, 0,
+	COMPOSITE(SCLK_HEVC_CORE, "sclk_hevc_core", mux_pll_src_cpll_gpll_npll_p, 0,
 			RK3288_CLKSEL_CON(42), 14, 2, MFLAGS, 8, 5, DFLAGS,
 			RK3288_CLKGATE_CON(13), 15, GFLAGS),
 
@@ -371,13 +447,13 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	COMPOSITE(0, "aclk_peri_src", mux_pll_src_cpll_gpll_p, 0,
 			RK3288_CLKSEL_CON(10), 15, 1, MFLAGS, 0, 5, DFLAGS,
 			RK3288_CLKGATE_CON(2), 0, GFLAGS),
-	COMPOSITE_NOMUX(0, "pclk_peri", "aclk_peri_src", 0,
+	COMPOSITE_NOMUX(PCLK_PERI, "pclk_peri", "aclk_peri_src", 0,
 			RK3288_CLKSEL_CON(10), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
 			RK3288_CLKGATE_CON(2), 3, GFLAGS),
-	COMPOSITE_NOMUX(0, "hclk_peri", "aclk_peri_src", 0,
+	COMPOSITE_NOMUX(HCLK_PERI, "hclk_peri", "aclk_peri_src", 0,
 			RK3288_CLKSEL_CON(10), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
 			RK3288_CLKGATE_CON(2), 2, GFLAGS),
-	GATE(0, "aclk_peri", "aclk_peri_src", 0,
+	GATE(ACLK_PERI, "aclk_peri", "aclk_peri_src", 0,
 			RK3288_CLKGATE_CON(2), 1, GFLAGS),
 
 	/*
@@ -643,34 +719,34 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	GATE(HCLK_RGA, "hclk_rga", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 1, GFLAGS),
 	GATE(HCLK_VOP0, "hclk_vop0", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 6, GFLAGS),
 	GATE(HCLK_VOP1, "hclk_vop1", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 8, GFLAGS),
-	GATE(0, "hclk_vio_ahb_arbi", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 9, GFLAGS),
-	GATE(0, "hclk_vio_niu", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 10, GFLAGS),
-	GATE(0, "hclk_vip", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 15, GFLAGS),
+	GATE(HCLK_VIO_AHB_ARBI, "hclk_vio_ahb_arbi", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 9, GFLAGS),
+	GATE(HCLK_VIO_NIU, "hclk_vio_niu", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 10, GFLAGS),
+	GATE(HCLK_VIP, "hclk_vip", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 15, GFLAGS),
 	GATE(HCLK_IEP, "hclk_iep", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 3, GFLAGS),
 	GATE(HCLK_ISP, "hclk_isp", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 1, GFLAGS),
-	GATE(0, "hclk_vio2_h2p", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 10, GFLAGS),
-	GATE(0, "pclk_mipi_dsi0", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 4, GFLAGS),
-	GATE(0, "pclk_mipi_dsi1", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 5, GFLAGS),
-	GATE(0, "pclk_mipi_csi", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 6, GFLAGS),
-	GATE(0, "pclk_lvds_phy", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 7, GFLAGS),
-	GATE(0, "pclk_edp_ctrl", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 8, GFLAGS),
-	GATE(0, "pclk_hdmi_ctrl", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 9, GFLAGS),
-	GATE(0, "pclk_vio2_h2p", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 11, GFLAGS),
+	GATE(HCLK_VIO2_H2P, "hclk_vio2_h2p", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 10, GFLAGS),
+	GATE(PCLK_MIPI_DSI0, "pclk_mipi_dsi0", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 4, GFLAGS),
+	GATE(PCLK_MIPI_DSI1, "pclk_mipi_dsi1", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 5, GFLAGS),
+	GATE(PCLK_MIPI_CSI, "pclk_mipi_csi", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 6, GFLAGS),
+	GATE(PCLK_LVDS_PHY, "pclk_lvds_phy", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 7, GFLAGS),
+	GATE(PCLK_EDP_CTRL, "pclk_edp_ctrl", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 8, GFLAGS),
+	GATE(PCLK_HDMI_CTRL, "pclk_hdmi_ctrl", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 9, GFLAGS),
+	GATE(PCLK_VIO2_H2P, "pclk_vio2_h2p", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 11, GFLAGS),
 
 	/* aclk_vio0 gates */
 	GATE(ACLK_VOP0, "aclk_vop0", "aclk_vio0", 0, RK3288_CLKGATE_CON(15), 5, GFLAGS),
-	GATE(0, "aclk_iep", "aclk_vio0", 0, RK3288_CLKGATE_CON(15), 2, GFLAGS),
-	GATE(0, "aclk_vio0_niu", "aclk_vio0", 0, RK3288_CLKGATE_CON(15), 11, GFLAGS),
-	GATE(0, "aclk_vip", "aclk_vio0", 0, RK3288_CLKGATE_CON(15), 14, GFLAGS),
+	GATE(ACLK_IEP, "aclk_iep", "aclk_vio0", 0, RK3288_CLKGATE_CON(15), 2, GFLAGS),
+	GATE(ACLK_VIO0_NIU, "aclk_vio0_niu", "aclk_vio0", 0, RK3288_CLKGATE_CON(15), 11, GFLAGS),
+	GATE(ACLK_VIP, "aclk_vip", "aclk_vio0", 0, RK3288_CLKGATE_CON(15), 14, GFLAGS),
 
 	/* aclk_vio1 gates */
 	GATE(ACLK_VOP1, "aclk_vop1", "aclk_vio1", 0, RK3288_CLKGATE_CON(15), 7, GFLAGS),
-	GATE(0, "aclk_isp", "aclk_vio1", 0, RK3288_CLKGATE_CON(16), 2, GFLAGS),
-	GATE(0, "aclk_vio1_niu", "aclk_vio1", 0, RK3288_CLKGATE_CON(15), 12, GFLAGS),
+	GATE(ACLK_ISP, "aclk_isp", "aclk_vio1", 0, RK3288_CLKGATE_CON(16), 2, GFLAGS),
+	GATE(ACLK_VIO1_NIU, "aclk_vio1_niu", "aclk_vio1", 0, RK3288_CLKGATE_CON(15), 12, GFLAGS),
 
 	/* aclk_rga_pre gates */
 	GATE(ACLK_RGA, "aclk_rga", "aclk_rga_pre", 0, RK3288_CLKGATE_CON(15), 0, GFLAGS),
-	GATE(0, "aclk_rga_niu", "aclk_rga_pre", 0, RK3288_CLKGATE_CON(15), 13, GFLAGS),
+	GATE(ACLK_RGA_NIU, "aclk_rga_niu", "aclk_rga_pre", 0, RK3288_CLKGATE_CON(15), 13, GFLAGS),
 
 	/*
 	 * Other ungrouped clocks.
@@ -680,6 +756,12 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
 	GATE(0, "pclk_isp_in", "ext_isp", 0, RK3288_CLKGATE_CON(16), 3, GFLAGS),
 };
 
+static const char *rk3288_critical_clocks[] __initconst = {
+	"aclk_cpu",
+	"aclk_peri",
+	"hclk_peri",
+};
+
 static void __init rk3288_clk_init(struct device_node *np)
 {
 	void __iomem *reg_base;
@@ -705,13 +787,28 @@ static void __init rk3288_clk_init(struct device_node *np)
 		pr_warn("%s: could not register clock usb480m: %ld\n",
 			__func__, PTR_ERR(clk));
 
+	clk = clk_register_fixed_factor(NULL, "hclk_vcodec_pre",
+					"hclk_vcodec_pre_v", 0, 1, 4);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock hclk_vcodec_pre: %ld\n",
+			__func__, PTR_ERR(clk));
+
 	rockchip_clk_register_plls(rk3288_pll_clks,
 				   ARRAY_SIZE(rk3288_pll_clks),
-				   RK3288_GRF_SOC_STATUS);
+				   RK3288_GRF_SOC_STATUS1);
 	rockchip_clk_register_branches(rk3288_clk_branches,
 				  ARRAY_SIZE(rk3288_clk_branches));
+	rockchip_clk_protect_critical(rk3288_critical_clocks,
+				      ARRAY_SIZE(rk3288_critical_clocks));
 
-	rockchip_register_softrst(np, 9, reg_base + RK3288_SOFTRST_CON(0),
+	rockchip_clk_register_armclk(ARMCLK, "armclk",
+			mux_armclk_p, ARRAY_SIZE(mux_armclk_p),
+			&rk3288_cpuclk_data, rk3288_cpuclk_rates,
+			ARRAY_SIZE(rk3288_cpuclk_rates));
+
+	rockchip_register_softrst(np, 12, reg_base + RK3288_SOFTRST_CON(0),
 				  ROCKCHIP_SOFTRST_HIWORD_MASK);
+
+	rockchip_register_restart_notifier(RK3288_GLB_SRST_FST);
 }
 CLK_OF_DECLARE(rk3288_cru, "rockchip,rk3288-cru", rk3288_clk_init);
diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c
index 278cf9dd1e23..1e68bff481b8 100644
--- a/drivers/clk/rockchip/clk.c
+++ b/drivers/clk/rockchip/clk.c
@@ -25,6 +25,7 @@
 #include <linux/clk-provider.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
+#include <linux/reboot.h>
 #include "clk.h"
 
 /**
@@ -37,7 +38,7 @@
  *
  * sometimes without one of those components.
  */
-struct clk *rockchip_clk_register_branch(const char *name,
+static struct clk *rockchip_clk_register_branch(const char *name,
 		const char **parent_names, u8 num_parents, void __iomem *base,
 		int muxdiv_offset, u8 mux_shift, u8 mux_width, u8 mux_flags,
 		u8 div_shift, u8 div_width, u8 div_flags,
@@ -103,6 +104,54 @@ struct clk *rockchip_clk_register_branch(const char *name,
 	return clk;
 }
 
+static struct clk *rockchip_clk_register_frac_branch(const char *name,
+		const char **parent_names, u8 num_parents, void __iomem *base,
+		int muxdiv_offset, u8 div_flags,
+		int gate_offset, u8 gate_shift, u8 gate_flags,
+		unsigned long flags, spinlock_t *lock)
+{
+	struct clk *clk;
+	struct clk_gate *gate = NULL;
+	struct clk_fractional_divider *div = NULL;
+	const struct clk_ops *div_ops = NULL, *gate_ops = NULL;
+
+	if (gate_offset >= 0) {
+		gate = kzalloc(sizeof(*gate), GFP_KERNEL);
+		if (!gate)
+			return ERR_PTR(-ENOMEM);
+
+		gate->flags = gate_flags;
+		gate->reg = base + gate_offset;
+		gate->bit_idx = gate_shift;
+		gate->lock = lock;
+		gate_ops = &clk_gate_ops;
+	}
+
+	if (muxdiv_offset < 0)
+		return ERR_PTR(-EINVAL);
+
+	div = kzalloc(sizeof(*div), GFP_KERNEL);
+	if (!div)
+		return ERR_PTR(-ENOMEM);
+
+	div->flags = div_flags;
+	div->reg = base + muxdiv_offset;
+	div->mshift = 16;
+	div->mmask = 0xffff0000;
+	div->nshift = 0;
+	div->nmask = 0xffff;
+	div->lock = lock;
+	div_ops = &clk_fractional_divider_ops;
+
+	clk = clk_register_composite(NULL, name, parent_names, num_parents,
+				     NULL, NULL,
+				     &div->hw, div_ops,
+				     gate ? &gate->hw : NULL, gate_ops,
+				     flags);
+
+	return clk;
+}
+
 static DEFINE_SPINLOCK(clk_lock);
 static struct clk **clk_table;
 static void __iomem *reg_base;
@@ -197,8 +246,14 @@ void __init rockchip_clk_register_branches(
 					list->div_flags, &clk_lock);
 			break;
 		case branch_fraction_divider:
-			/* unimplemented */
-			continue;
+			/* keep all gates untouched for now */
+			flags |= CLK_IGNORE_UNUSED;
+
+			clk = rockchip_clk_register_frac_branch(list->name,
+				list->parent_names, list->num_parents,
+				reg_base, list->muxdiv_offset, list->div_flags,
+				list->gate_offset, list->gate_shift,
+				list->gate_flags, flags, &clk_lock);
 			break;
 		case branch_gate:
 			flags |= CLK_SET_RATE_PARENT;
@@ -242,3 +297,61 @@ void __init rockchip_clk_register_branches(
 		rockchip_clk_add_lookup(clk, list->id);
 	}
 }
+
+void __init rockchip_clk_register_armclk(unsigned int lookup_id,
+			const char *name, const char **parent_names,
+			u8 num_parents,
+			const struct rockchip_cpuclk_reg_data *reg_data,
+			const struct rockchip_cpuclk_rate_table *rates,
+			int nrates)
+{
+	struct clk *clk;
+
+	clk = rockchip_clk_register_cpuclk(name, parent_names, num_parents,
+					   reg_data, rates, nrates, reg_base,
+					   &clk_lock);
+	if (IS_ERR(clk)) {
+		pr_err("%s: failed to register clock %s: %ld\n",
+		       __func__, name, PTR_ERR(clk));
+		return;
+	}
+
+	rockchip_clk_add_lookup(clk, lookup_id);
+}
+
+void __init rockchip_clk_protect_critical(const char *clocks[], int nclocks)
+{
+	int i;
+
+	/* Protect the clocks that needs to stay on */
+	for (i = 0; i < nclocks; i++) {
+		struct clk *clk = __clk_lookup(clocks[i]);
+
+		if (clk)
+			clk_prepare_enable(clk);
+	}
+}
+
+static unsigned int reg_restart;
+static int rockchip_restart_notify(struct notifier_block *this,
+				   unsigned long mode, void *cmd)
+{
+	writel(0xfdb9, reg_base + reg_restart);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block rockchip_restart_handler = {
+	.notifier_call = rockchip_restart_notify,
+	.priority = 128,
+};
+
+void __init rockchip_register_restart_notifier(unsigned int reg)
+{
+	int ret;
+
+	reg_restart = reg;
+	ret = register_restart_handler(&rockchip_restart_handler);
+	if (ret)
+		pr_err("%s: cannot register restart handler, %d\n",
+		       __func__, ret);
+}
diff --git a/drivers/clk/rockchip/clk.h b/drivers/clk/rockchip/clk.h
index 887cbdeca2aa..ca009ab0a33a 100644
--- a/drivers/clk/rockchip/clk.h
+++ b/drivers/clk/rockchip/clk.h
@@ -120,6 +120,38 @@ struct clk *rockchip_clk_register_pll(enum rockchip_pll_type pll_type,
 		struct rockchip_pll_rate_table *rate_table,
 		spinlock_t *lock);
 
+struct rockchip_cpuclk_clksel {
+	int reg;
+	u32 val;
+};
+
+#define ROCKCHIP_CPUCLK_NUM_DIVIDERS	2
+struct rockchip_cpuclk_rate_table {
+	unsigned long prate;
+	struct rockchip_cpuclk_clksel divs[ROCKCHIP_CPUCLK_NUM_DIVIDERS];
+};
+
+/**
+ * struct rockchip_cpuclk_reg_data: describes register offsets and masks of the cpuclock
+ * @core_reg:		register offset of the core settings register
+ * @div_core_shift:	core divider offset used to divide the pll value
+ * @div_core_mask:	core divider mask
+ * @mux_core_shift:	offset of the core multiplexer
+ */
+struct rockchip_cpuclk_reg_data {
+	int		core_reg;
+	u8		div_core_shift;
+	u32		div_core_mask;
+	int		mux_core_reg;
+	u8		mux_core_shift;
+};
+
+struct clk *rockchip_clk_register_cpuclk(const char *name,
+			const char **parent_names, u8 num_parents,
+			const struct rockchip_cpuclk_reg_data *reg_data,
+			const struct rockchip_cpuclk_rate_table *rates,
+			int nrates, void __iomem *reg_base, spinlock_t *lock);
+
 #define PNAME(x) static const char *x[] __initconst
 
 enum rockchip_clk_branch_type {
@@ -329,6 +361,13 @@ void rockchip_clk_register_branches(struct rockchip_clk_branch *clk_list,
 				    unsigned int nr_clk);
 void rockchip_clk_register_plls(struct rockchip_pll_clock *pll_list,
 				unsigned int nr_pll, int grf_lock_offset);
+void rockchip_clk_register_armclk(unsigned int lookup_id, const char *name,
+			const char **parent_names, u8 num_parents,
+			const struct rockchip_cpuclk_reg_data *reg_data,
+			const struct rockchip_cpuclk_rate_table *rates,
+			int nrates);
+void rockchip_clk_protect_critical(const char *clocks[], int nclocks);
+void rockchip_register_restart_notifier(unsigned int reg);
 
 #define ROCKCHIP_SOFTRST_HIWORD_MASK	BIT(0)
 
diff --git a/drivers/clk/samsung/clk-exynos3250.c b/drivers/clk/samsung/clk-exynos3250.c
index dc85f8e7a2d7..6e6cca392082 100644
--- a/drivers/clk/samsung/clk-exynos3250.c
+++ b/drivers/clk/samsung/clk-exynos3250.c
@@ -110,7 +110,14 @@ enum exynos3250_plls {
 	nr_plls
 };
 
+/* list of PLLs in DMC block to be registered */
+enum exynos3250_dmc_plls {
+	bpll, epll,
+	nr_dmc_plls
+};
+
 static void __iomem *reg_base;
+static void __iomem *dmc_reg_base;
 
 /*
  * Support for CMU save/restore across system suspends
@@ -266,6 +273,7 @@ PNAME(group_sclk_cam_blk_p)	= { "xxti", "xusbxti",
 				    "none", "none", "none",
 				    "none", "div_mpll_pre",
 				    "mout_epll_user", "mout_vpll",
+				    "none", "none", "none",
 				    "div_cam_blk_320", };
 PNAME(group_sclk_fimd0_p)	= { "xxti", "xusbxti",
 				    "m_bitclkhsdiv4_2l", "none",
@@ -353,8 +361,8 @@ static struct samsung_mux_clock mux_clks[] __initdata = {
 
 	/* SRC_FSYS */
 	MUX(CLK_MOUT_TSADC, "mout_tsadc", group_sclk_p, SRC_FSYS, 28, 4),
-	MUX(CLK_MOUT_MMC1, "mout_mmc1", group_sclk_p, SRC_FSYS, 4, 3),
-	MUX(CLK_MOUT_MMC0, "mout_mmc0", group_sclk_p, SRC_FSYS, 0, 3),
+	MUX(CLK_MOUT_MMC1, "mout_mmc1", group_sclk_p, SRC_FSYS, 4, 4),
+	MUX(CLK_MOUT_MMC0, "mout_mmc0", group_sclk_p, SRC_FSYS, 0, 4),
 
 	/* SRC_PERIL0 */
 	MUX(CLK_MOUT_UART1, "mout_uart1", group_sclk_p, SRC_PERIL0, 4, 4),
@@ -423,7 +431,7 @@ static struct samsung_div_clock div_clks[] __initdata = {
 	DIV(CLK_DIV_SPI1_ISP, "div_spi1_isp", "mout_spi1_isp", DIV_ISP, 16, 4),
 	DIV_F(CLK_DIV_SPI0_ISP_PRE, "div_spi0_isp_pre", "div_spi0_isp",
 		DIV_ISP, 8, 8, CLK_SET_RATE_PARENT, 0),
-	DIV(CLK_DIV_SPI0_ISP, "div_spi0_isp", "mout_spi0_isp", DIV_ISP, 0, 4),
+	DIV(CLK_DIV_SPI0_ISP, "div_spi0_isp", "mout_spi0_isp", DIV_ISP, 4, 4),
 
 	/* DIV_FSYS0 */
 	DIV_F(CLK_DIV_TSADC_PRE, "div_tsadc_pre", "div_tsadc", DIV_FSYS0, 8, 8,
@@ -724,6 +732,25 @@ static struct samsung_pll_rate_table exynos3250_pll_rates[] = {
 	{ /* sentinel */ }
 };
 
+/* EPLL */
+static struct samsung_pll_rate_table exynos3250_epll_rates[] = {
+	PLL_36XX_RATE(800000000, 200, 3, 1,     0),
+	PLL_36XX_RATE(288000000,  96, 2, 2,     0),
+	PLL_36XX_RATE(192000000, 128, 2, 3,     0),
+	PLL_36XX_RATE(144000000,  96, 2, 3,     0),
+	PLL_36XX_RATE( 96000000, 128, 2, 4,     0),
+	PLL_36XX_RATE( 84000000, 112, 2, 4,     0),
+	PLL_36XX_RATE( 80000004, 106, 2, 4, 43691),
+	PLL_36XX_RATE( 73728000,  98, 2, 4, 19923),
+	PLL_36XX_RATE( 67737598, 270, 3, 5, 62285),
+	PLL_36XX_RATE( 65535999, 174, 2, 5, 49982),
+	PLL_36XX_RATE( 50000000, 200, 3, 5,     0),
+	PLL_36XX_RATE( 49152002, 131, 2, 5,  4719),
+	PLL_36XX_RATE( 48000000, 128, 2, 5,     0),
+	PLL_36XX_RATE( 45158401, 180, 3, 5, 41524),
+	{ /* sentinel */ }
+};
+
 /* VPLL */
 static struct samsung_pll_rate_table exynos3250_vpll_rates[] = {
 	PLL_36XX_RATE(600000000, 100, 2, 1,     0),
@@ -821,3 +848,172 @@ static void __init exynos3250_cmu_init(struct device_node *np)
 	samsung_clk_of_add_provider(np, ctx);
 }
 CLK_OF_DECLARE(exynos3250_cmu, "samsung,exynos3250-cmu", exynos3250_cmu_init);
+
+/*
+ * CMU DMC
+ */
+
+#define BPLL_LOCK		0x0118
+#define BPLL_CON0		0x0218
+#define BPLL_CON1		0x021c
+#define BPLL_CON2		0x0220
+#define SRC_DMC			0x0300
+#define DIV_DMC1		0x0504
+#define GATE_BUS_DMC0		0x0700
+#define GATE_BUS_DMC1		0x0704
+#define GATE_BUS_DMC2		0x0708
+#define GATE_BUS_DMC3		0x070c
+#define GATE_SCLK_DMC		0x0800
+#define GATE_IP_DMC0		0x0900
+#define GATE_IP_DMC1		0x0904
+#define EPLL_LOCK		0x1110
+#define EPLL_CON0		0x1114
+#define EPLL_CON1		0x1118
+#define EPLL_CON2		0x111c
+#define SRC_EPLL		0x1120
+
+/*
+ * Support for CMU save/restore across system suspends
+ */
+#ifdef CONFIG_PM_SLEEP
+static struct samsung_clk_reg_dump *exynos3250_dmc_clk_regs;
+
+static unsigned long exynos3250_cmu_dmc_clk_regs[] __initdata = {
+	BPLL_LOCK,
+	BPLL_CON0,
+	BPLL_CON1,
+	BPLL_CON2,
+	SRC_DMC,
+	DIV_DMC1,
+	GATE_BUS_DMC0,
+	GATE_BUS_DMC1,
+	GATE_BUS_DMC2,
+	GATE_BUS_DMC3,
+	GATE_SCLK_DMC,
+	GATE_IP_DMC0,
+	GATE_IP_DMC1,
+	EPLL_LOCK,
+	EPLL_CON0,
+	EPLL_CON1,
+	EPLL_CON2,
+	SRC_EPLL,
+};
+
+static int exynos3250_dmc_clk_suspend(void)
+{
+	samsung_clk_save(dmc_reg_base, exynos3250_dmc_clk_regs,
+				ARRAY_SIZE(exynos3250_cmu_dmc_clk_regs));
+	return 0;
+}
+
+static void exynos3250_dmc_clk_resume(void)
+{
+	samsung_clk_restore(dmc_reg_base, exynos3250_dmc_clk_regs,
+				ARRAY_SIZE(exynos3250_cmu_dmc_clk_regs));
+}
+
+static struct syscore_ops exynos3250_dmc_clk_syscore_ops = {
+	.suspend = exynos3250_dmc_clk_suspend,
+	.resume = exynos3250_dmc_clk_resume,
+};
+
+static void exynos3250_dmc_clk_sleep_init(void)
+{
+	exynos3250_dmc_clk_regs =
+		samsung_clk_alloc_reg_dump(exynos3250_cmu_dmc_clk_regs,
+				   ARRAY_SIZE(exynos3250_cmu_dmc_clk_regs));
+	if (!exynos3250_dmc_clk_regs) {
+		pr_warn("%s: Failed to allocate sleep save data\n", __func__);
+		goto err;
+	}
+
+	register_syscore_ops(&exynos3250_dmc_clk_syscore_ops);
+	return;
+err:
+	kfree(exynos3250_dmc_clk_regs);
+}
+#else
+static inline void exynos3250_dmc_clk_sleep_init(void) { }
+#endif
+
+PNAME(mout_epll_p)	= { "fin_pll", "fout_epll", };
+PNAME(mout_bpll_p)	= { "fin_pll", "fout_bpll", };
+PNAME(mout_mpll_mif_p)	= { "fin_pll", "sclk_mpll_mif", };
+PNAME(mout_dphy_p)	= { "mout_mpll_mif", "mout_bpll", };
+
+static struct samsung_mux_clock dmc_mux_clks[] __initdata = {
+	/*
+	 * NOTE: Following table is sorted by register address in ascending
+	 * order and then bitfield shift in descending order, as it is done
+	 * in the User's Manual. When adding new entries, please make sure
+	 * that the order is preserved, to avoid merge conflicts and make
+	 * further work with defined data easier.
+	 */
+
+	/* SRC_DMC */
+	MUX(CLK_MOUT_MPLL_MIF, "mout_mpll_mif", mout_mpll_mif_p, SRC_DMC, 12, 1),
+	MUX(CLK_MOUT_BPLL, "mout_bpll", mout_bpll_p, SRC_DMC, 10, 1),
+	MUX(CLK_MOUT_DPHY, "mout_dphy", mout_dphy_p, SRC_DMC, 8, 1),
+	MUX(CLK_MOUT_DMC_BUS, "mout_dmc_bus", mout_dphy_p, SRC_DMC,  4, 1),
+
+	/* SRC_EPLL */
+	MUX(CLK_MOUT_EPLL, "mout_epll", mout_epll_p, SRC_EPLL, 4, 1),
+};
+
+static struct samsung_div_clock dmc_div_clks[] __initdata = {
+	/*
+	 * NOTE: Following table is sorted by register address in ascending
+	 * order and then bitfield shift in descending order, as it is done
+	 * in the User's Manual. When adding new entries, please make sure
+	 * that the order is preserved, to avoid merge conflicts and make
+	 * further work with defined data easier.
+	 */
+
+	/* DIV_DMC1 */
+	DIV(CLK_DIV_DMC, "div_dmc", "div_dmc_pre", DIV_DMC1, 27, 3),
+	DIV(CLK_DIV_DPHY, "div_dphy", "mout_dphy", DIV_DMC1, 23, 3),
+	DIV(CLK_DIV_DMC_PRE, "div_dmc_pre", "mout_dmc_bus", DIV_DMC1, 19, 2),
+	DIV(CLK_DIV_DMCP, "div_dmcp", "div_dmcd", DIV_DMC1, 15, 3),
+	DIV(CLK_DIV_DMCD, "div_dmcd", "div_dmc", DIV_DMC1, 11, 3),
+};
+
+static struct samsung_pll_clock exynos3250_dmc_plls[nr_dmc_plls] __initdata = {
+	[bpll] = PLL(pll_35xx, CLK_FOUT_BPLL, "fout_bpll", "fin_pll",
+			BPLL_LOCK, BPLL_CON0, NULL),
+	[epll] = PLL(pll_36xx, CLK_FOUT_EPLL, "fout_epll", "fin_pll",
+			EPLL_LOCK, EPLL_CON0, NULL),
+};
+
+static void __init exynos3250_cmu_dmc_init(struct device_node *np)
+{
+	struct samsung_clk_provider *ctx;
+
+	dmc_reg_base = of_iomap(np, 0);
+	if (!dmc_reg_base)
+		panic("%s: failed to map registers\n", __func__);
+
+	ctx = samsung_clk_init(np, dmc_reg_base, NR_CLKS_DMC);
+	if (!ctx)
+		panic("%s: unable to allocate context.\n", __func__);
+
+	exynos3250_dmc_plls[bpll].rate_table = exynos3250_pll_rates;
+	exynos3250_dmc_plls[epll].rate_table = exynos3250_epll_rates;
+
+	pr_err("CLK registering epll bpll: %d, %d, %d, %d\n",
+			exynos3250_dmc_plls[bpll].rate_table[0].rate,
+			exynos3250_dmc_plls[bpll].rate_table[0].mdiv,
+			exynos3250_dmc_plls[bpll].rate_table[0].pdiv,
+			exynos3250_dmc_plls[bpll].rate_table[0].sdiv
+	      );
+	samsung_clk_register_pll(ctx, exynos3250_dmc_plls,
+				ARRAY_SIZE(exynos3250_dmc_plls), dmc_reg_base);
+
+	samsung_clk_register_mux(ctx, dmc_mux_clks, ARRAY_SIZE(dmc_mux_clks));
+	samsung_clk_register_div(ctx, dmc_div_clks, ARRAY_SIZE(dmc_div_clks));
+
+	exynos3250_dmc_clk_sleep_init();
+
+	samsung_clk_of_add_provider(np, ctx);
+}
+CLK_OF_DECLARE(exynos3250_cmu_dmc, "samsung,exynos3250-cmu-dmc",
+		exynos3250_cmu_dmc_init);
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index ac163d7f5bc3..940f02837b82 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -517,7 +517,7 @@ static struct samsung_fixed_factor_clock exynos4_fixed_factor_clks[] __initdata
 	FFACTOR(0, "sclk_apll_div_2", "sclk_apll", 1, 2, 0),
 	FFACTOR(0, "fout_mpll_div_2", "fout_mpll", 1, 2, 0),
 	FFACTOR(0, "fout_apll_div_2", "fout_apll", 1, 2, 0),
-	FFACTOR(0, "arm_clk_div_2", "arm_clk", 1, 2, 0),
+	FFACTOR(0, "arm_clk_div_2", "div_core2", 1, 2, 0),
 };
 
 static struct samsung_fixed_factor_clock exynos4210_fixed_factor_clks[] __initdata = {
@@ -535,7 +535,7 @@ static struct samsung_fixed_factor_clock exynos4x12_fixed_factor_clks[] __initda
 static struct samsung_mux_clock exynos4_mux_clks[] __initdata = {
 	MUX_FA(CLK_MOUT_APLL, "mout_apll", mout_apll_p, SRC_CPU, 0, 1,
 			CLK_SET_RATE_PARENT, 0, "mout_apll"),
-	MUX(0, "mout_hdmi", mout_hdmi_p, SRC_TV, 0, 1),
+	MUX(CLK_MOUT_HDMI, "mout_hdmi", mout_hdmi_p, SRC_TV, 0, 1),
 	MUX(0, "mout_mfc1", sclk_evpll_p, SRC_MFC, 4, 1),
 	MUX(0, "mout_mfc", mout_mfc_p, SRC_MFC, 8, 1),
 	MUX_F(CLK_MOUT_G3D1, "mout_g3d1", sclk_evpll_p, SRC_G3D, 4, 1,
@@ -569,7 +569,7 @@ static struct samsung_mux_clock exynos4210_mux_clks[] __initdata = {
 	MUX(0, "mout_aclk100", sclk_ampll_p4210, SRC_TOP0, 16, 1),
 	MUX(0, "mout_aclk160", sclk_ampll_p4210, SRC_TOP0, 20, 1),
 	MUX(0, "mout_aclk133", sclk_ampll_p4210, SRC_TOP0, 24, 1),
-	MUX(0, "mout_mixer", mout_mixer_p4210, SRC_TV, 4, 1),
+	MUX(CLK_MOUT_MIXER, "mout_mixer", mout_mixer_p4210, SRC_TV, 4, 1),
 	MUX(0, "mout_dac", mout_dac_p4210, SRC_TV, 8, 1),
 	MUX(0, "mout_g2d0", sclk_ampll_p4210, E4210_SRC_IMAGE, 0, 1),
 	MUX(0, "mout_g2d1", sclk_evpll_p, E4210_SRC_IMAGE, 4, 1),
@@ -719,7 +719,7 @@ static struct samsung_div_clock exynos4_div_clks[] __initdata = {
 	DIV(0, "div_periph", "div_core2", DIV_CPU0, 12, 3),
 	DIV(0, "div_atb", "mout_core", DIV_CPU0, 16, 3),
 	DIV(0, "div_pclk_dbg", "div_atb", DIV_CPU0, 20, 3),
-	DIV(0, "div_core2", "div_core", DIV_CPU0, 28, 3),
+	DIV(CLK_ARM_CLK, "div_core2", "div_core", DIV_CPU0, 28, 3),
 	DIV(0, "div_copy", "mout_hpm", DIV_CPU1, 0, 3),
 	DIV(0, "div_hpm", "div_copy", DIV_CPU1, 4, 3),
 	DIV(0, "div_clkout_cpu", "mout_clkout_cpu", CLKOUT_CMU_CPU, 8, 6),
@@ -733,8 +733,7 @@ static struct samsung_div_clock exynos4_div_clks[] __initdata = {
 	DIV(0, "div_csis0", "mout_csis0", DIV_CAM, 24, 4),
 	DIV(0, "div_csis1", "mout_csis1", DIV_CAM, 28, 4),
 	DIV(CLK_SCLK_MFC, "sclk_mfc", "mout_mfc", DIV_MFC, 0, 4),
-	DIV_F(0, "div_g3d", "mout_g3d", DIV_G3D, 0, 4,
-			CLK_SET_RATE_PARENT, 0),
+	DIV(CLK_SCLK_G3D, "sclk_g3d", "mout_g3d", DIV_G3D, 0, 4),
 	DIV(0, "div_fimd0", "mout_fimd0", DIV_LCD0, 0, 4),
 	DIV(0, "div_mipi0", "mout_mipi0", DIV_LCD0, 16, 4),
 	DIV(0, "div_audio0", "mout_audio0", DIV_MAUDIO, 0, 4),
@@ -769,7 +768,6 @@ static struct samsung_div_clock exynos4_div_clks[] __initdata = {
 	DIV(0, "div_spi_pre2", "div_spi2", DIV_PERIL2, 8, 8),
 	DIV(0, "div_audio1", "mout_audio1", DIV_PERIL4, 0, 4),
 	DIV(0, "div_audio2", "mout_audio2", DIV_PERIL4, 16, 4),
-	DIV(CLK_ARM_CLK, "arm_clk", "div_core2", DIV_CPU0, 28, 3),
 	DIV(CLK_SCLK_APLL, "sclk_apll", "mout_apll", DIV_CPU0, 24, 3),
 	DIV_F(0, "div_mipi_pre0", "div_mipi0", DIV_LCD0, 20, 4,
 			CLK_SET_RATE_PARENT, 0),
@@ -857,8 +855,7 @@ static struct samsung_gate_clock exynos4_gate_clks[] __initdata = {
 		0),
 	GATE(CLK_TSI, "tsi", "aclk133", GATE_IP_FSYS, 4, 0, 0),
 	GATE(CLK_SROMC, "sromc", "aclk133", GATE_IP_FSYS, 11, 0, 0),
-	GATE(CLK_SCLK_G3D, "sclk_g3d", "div_g3d", GATE_IP_G3D, 0,
-			CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_G3D, "g3d", "aclk200", GATE_IP_G3D, 0, 0, 0),
 	GATE(CLK_PPMUG3D, "ppmug3d", "aclk200", GATE_IP_G3D, 1, 0, 0),
 	GATE(CLK_USB_DEVICE, "usb_device", "aclk133", GATE_IP_FSYS, 13, 0, 0),
 	GATE(CLK_ONENAND, "onenand", "aclk133", GATE_IP_FSYS, 15, 0, 0),
@@ -1183,6 +1180,7 @@ static struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
 	GATE(CLK_SPI1_ISP, "spi1_isp", "aclk200", E4X12_GATE_ISP1, 13,
 			CLK_IGNORE_UNUSED | CLK_GET_RATE_NOCACHE, 0),
 	GATE(CLK_G2D, "g2d", "aclk200", GATE_IP_DMC, 23, 0, 0),
+	GATE(CLK_SMMU_G2D, "smmu_g2d", "aclk200", GATE_IP_DMC, 24, 0, 0),
 	GATE(CLK_TMU_APBIF, "tmu_apbif", "aclk100", E4X12_GATE_IP_PERIR, 17, 0,
 		0),
 };
@@ -1486,7 +1484,7 @@ static void __init exynos4_clk_init(struct device_node *np,
 		exynos4_soc == EXYNOS4210 ? "Exynos4210" : "Exynos4x12",
 		_get_rate("sclk_apll"),	_get_rate("sclk_mpll"),
 		_get_rate("sclk_epll"), _get_rate("sclk_vpll"),
-		_get_rate("arm_clk"));
+		_get_rate("div_core2"));
 }
 
 
diff --git a/drivers/clk/samsung/clk-exynos5260.c b/drivers/clk/samsung/clk-exynos5260.c
index ce3de97e5f11..2527e39aadcf 100644
--- a/drivers/clk/samsung/clk-exynos5260.c
+++ b/drivers/clk/samsung/clk-exynos5260.c
@@ -1581,7 +1581,7 @@ struct samsung_fixed_rate_clock fixed_rate_clks[] __initdata = {
 	FRATE(PHYCLK_HDMI_LINK_O_TMDS_CLKHI, "phyclk_hdmi_link_o_tmds_clkhi",
 			NULL, CLK_IS_ROOT, 125000000),
 	FRATE(PHYCLK_MIPI_DPHY_4L_M_TXBYTECLKHS,
-			"phyclk_mipi_dphy_4l_m_txbyteclkhs" , NULL,
+			"phyclk_mipi_dphy_4l_m_txbyte_clkhs" , NULL,
 			CLK_IS_ROOT, 187500000),
 	FRATE(PHYCLK_DPTX_PHY_O_REF_CLK_24M, "phyclk_dptx_phy_o_ref_clk_24m",
 			NULL, CLK_IS_ROOT, 24000000),
diff --git a/drivers/clk/samsung/clk-s3c2410-dclk.c b/drivers/clk/samsung/clk-s3c2410-dclk.c
index 0449cc0458ed..f4f29ed6bd25 100644
--- a/drivers/clk/samsung/clk-s3c2410-dclk.c
+++ b/drivers/clk/samsung/clk-s3c2410-dclk.c
@@ -426,7 +426,6 @@ MODULE_DEVICE_TABLE(platform, s3c24xx_dclk_driver_ids);
 static struct platform_driver s3c24xx_dclk_driver = {
 	.driver = {
 		.name		= "s3c24xx-dclk",
-		.owner		= THIS_MODULE,
 		.pm		= &s3c24xx_dclk_pm_ops,
 	},
 	.probe = s3c24xx_dclk_probe,
diff --git a/drivers/clk/samsung/clk-s3c2412.c b/drivers/clk/samsung/clk-s3c2412.c
index 34af09f6a155..2ceedaf8ce18 100644
--- a/drivers/clk/samsung/clk-s3c2412.c
+++ b/drivers/clk/samsung/clk-s3c2412.c
@@ -14,6 +14,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/syscore_ops.h>
+#include <linux/reboot.h>
 
 #include <dt-bindings/clock/s3c2412.h>
 
@@ -26,6 +27,7 @@
 #define CLKCON		0x0c
 #define CLKDIVN		0x14
 #define CLKSRC		0x1c
+#define SWRST		0x30
 
 /* list of PLLs to be registered */
 enum s3c2412_plls {
@@ -204,6 +206,28 @@ struct samsung_clock_alias s3c2412_aliases[] __initdata = {
 	ALIAS(MSYSCLK, NULL, "fclk"),
 };
 
+static int s3c2412_restart(struct notifier_block *this,
+			   unsigned long mode, void *cmd)
+{
+	/* errata "Watch-dog/Software Reset Problem" specifies that
+	 * this reset must be done with the SYSCLK sourced from
+	 * EXTCLK instead of FOUT to avoid a glitch in the reset
+	 * mechanism.
+	 *
+	 * See the watchdog section of the S3C2412 manual for more
+	 * information on this fix.
+	 */
+
+	__raw_writel(0x00, reg_base + CLKSRC);
+	__raw_writel(0x533C2412, reg_base + SWRST);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block s3c2412_restart_handler = {
+	.notifier_call = s3c2412_restart,
+	.priority = 129,
+};
+
 /*
  * fixed rate clocks generated outside the soc
  * Only necessary until the devicetree-move is complete
@@ -233,6 +257,7 @@ void __init s3c2412_common_clk_init(struct device_node *np, unsigned long xti_f,
 				    unsigned long ext_f, void __iomem *base)
 {
 	struct samsung_clk_provider *ctx;
+	int ret;
 	reg_base = base;
 
 	if (np) {
@@ -267,6 +292,10 @@ void __init s3c2412_common_clk_init(struct device_node *np, unsigned long xti_f,
 	s3c2412_clk_sleep_init();
 
 	samsung_clk_of_add_provider(np, ctx);
+
+	ret = register_restart_handler(&s3c2412_restart_handler);
+	if (ret)
+		pr_warn("cannot register restart handler, %d\n", ret);
 }
 
 static void __init s3c2412_clk_init(struct device_node *np)
diff --git a/drivers/clk/samsung/clk-s3c2443.c b/drivers/clk/samsung/clk-s3c2443.c
index c92f853fca9f..0c3c182b902a 100644
--- a/drivers/clk/samsung/clk-s3c2443.c
+++ b/drivers/clk/samsung/clk-s3c2443.c
@@ -14,6 +14,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/syscore_ops.h>
+#include <linux/reboot.h>
 
 #include <dt-bindings/clock/s3c2443.h>
 
@@ -33,6 +34,7 @@
 #define HCLKCON		0x30
 #define PCLKCON		0x34
 #define SCLKCON		0x38
+#define SWRST		0x44
 
 /* the soc types */
 enum supported_socs {
@@ -354,6 +356,18 @@ struct samsung_clock_alias s3c2450_aliases[] __initdata = {
 	ALIAS(PCLK_I2C1, "s3c2410-i2c.1", "i2c"),
 };
 
+static int s3c2443_restart(struct notifier_block *this,
+			   unsigned long mode, void *cmd)
+{
+	__raw_writel(0x533c2443, reg_base + SWRST);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block s3c2443_restart_handler = {
+	.notifier_call = s3c2443_restart,
+	.priority = 129,
+};
+
 /*
  * fixed rate clocks generated outside the soc
  * Only necessary until the devicetree-move is complete
@@ -378,6 +392,7 @@ void __init s3c2443_common_clk_init(struct device_node *np, unsigned long xti_f,
 				    void __iomem *base)
 {
 	struct samsung_clk_provider *ctx;
+	int ret;
 	reg_base = base;
 
 	if (np) {
@@ -447,6 +462,10 @@ void __init s3c2443_common_clk_init(struct device_node *np, unsigned long xti_f,
 	s3c2443_clk_sleep_init();
 
 	samsung_clk_of_add_provider(np, ctx);
+
+	ret = register_restart_handler(&s3c2443_restart_handler);
+	if (ret)
+		pr_warn("cannot register restart handler, %d\n", ret);
 }
 
 static void __init s3c2416_clk_init(struct device_node *np)
diff --git a/drivers/clk/shmobile/Makefile b/drivers/clk/shmobile/Makefile
index 531d4f6c7050..960bf22d42ae 100644
--- a/drivers/clk/shmobile/Makefile
+++ b/drivers/clk/shmobile/Makefile
@@ -7,5 +7,3 @@ obj-$(CONFIG_ARCH_R8A7791)		+= clk-rcar-gen2.o
 obj-$(CONFIG_ARCH_R8A7794)		+= clk-rcar-gen2.o
 obj-$(CONFIG_ARCH_SHMOBILE_MULTI)	+= clk-div6.o
 obj-$(CONFIG_ARCH_SHMOBILE_MULTI)	+= clk-mstp.o
-# for emply built-in.o
-obj-n	:= dummy
diff --git a/drivers/clk/shmobile/clk-rcar-gen2.c b/drivers/clk/shmobile/clk-rcar-gen2.c
index dff7f79a19b9..e996425d06a9 100644
--- a/drivers/clk/shmobile/clk-rcar-gen2.c
+++ b/drivers/clk/shmobile/clk-rcar-gen2.c
@@ -202,6 +202,7 @@ static const struct clk_div_table cpg_sdh_div_table[] = {
 };
 
 static const struct clk_div_table cpg_sd01_div_table[] = {
+	{  4,  8 },
 	{  5, 12 }, {  6, 16 }, {  7, 18 }, {  8, 24 },
 	{ 10, 36 }, { 11, 48 }, { 12, 10 }, {  0,  0 },
 };
diff --git a/drivers/clk/sunxi/Makefile b/drivers/clk/sunxi/Makefile
index 6850cba35871..7ddc2b553846 100644
--- a/drivers/clk/sunxi/Makefile
+++ b/drivers/clk/sunxi/Makefile
@@ -5,6 +5,8 @@
 obj-y += clk-sunxi.o clk-factors.o
 obj-y += clk-a10-hosc.o
 obj-y += clk-a20-gmac.o
+obj-y += clk-mod0.o
+obj-y += clk-sun8i-mbus.o
 
 obj-$(CONFIG_MFD_SUN6I_PRCM) += \
 	clk-sun6i-ar100.o clk-sun6i-apb0.o clk-sun6i-apb0-gates.o \
diff --git a/drivers/clk/sunxi/clk-factors.c b/drivers/clk/sunxi/clk-factors.c
index 2057c8ac648f..f83ba097126c 100644
--- a/drivers/clk/sunxi/clk-factors.c
+++ b/drivers/clk/sunxi/clk-factors.c
@@ -9,18 +9,18 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/io.h>
 #include <linux/module.h>
+#include <linux/of_address.h>
 #include <linux/slab.h>
-#include <linux/io.h>
-#include <linux/err.h>
 #include <linux/string.h>
 
-#include <linux/delay.h>
-
 #include "clk-factors.h"
 
 /*
- * DOC: basic adjustable factor-based clock that cannot gate
+ * DOC: basic adjustable factor-based clock
  *
  * Traits of this clock:
  * prepare - clk_prepare only ensures that parents are prepared
@@ -32,6 +32,8 @@
 
 #define to_clk_factors(_hw) container_of(_hw, struct clk_factors, hw)
 
+#define FACTORS_MAX_PARENTS		5
+
 #define SETMASK(len, pos)		(((1U << (len)) - 1) << (pos))
 #define CLRMASK(len, pos)		(~(SETMASK(len, pos)))
 #define FACTOR_GET(bit, len, reg)	(((reg) & SETMASK(len, bit)) >> (bit))
@@ -147,9 +149,96 @@ static int clk_factors_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
-const struct clk_ops clk_factors_ops = {
+static const struct clk_ops clk_factors_ops = {
 	.determine_rate = clk_factors_determine_rate,
 	.recalc_rate = clk_factors_recalc_rate,
 	.round_rate = clk_factors_round_rate,
 	.set_rate = clk_factors_set_rate,
 };
+
+struct clk * __init sunxi_factors_register(struct device_node *node,
+					   const struct factors_data *data,
+					   spinlock_t *lock)
+{
+	struct clk *clk;
+	struct clk_factors *factors;
+	struct clk_gate *gate = NULL;
+	struct clk_mux *mux = NULL;
+	struct clk_hw *gate_hw = NULL;
+	struct clk_hw *mux_hw = NULL;
+	const char *clk_name = node->name;
+	const char *parents[FACTORS_MAX_PARENTS];
+	void __iomem *reg;
+	int i = 0;
+
+	reg = of_iomap(node, 0);
+
+	/* if we have a mux, we will have >1 parents */
+	while (i < FACTORS_MAX_PARENTS &&
+	       (parents[i] = of_clk_get_parent_name(node, i)) != NULL)
+		i++;
+
+	/*
+	 * some factor clocks, such as pll5 and pll6, may have multiple
+	 * outputs, and have their name designated in factors_data
+	 */
+	if (data->name)
+		clk_name = data->name;
+	else
+		of_property_read_string(node, "clock-output-names", &clk_name);
+
+	factors = kzalloc(sizeof(struct clk_factors), GFP_KERNEL);
+	if (!factors)
+		return NULL;
+
+	/* set up factors properties */
+	factors->reg = reg;
+	factors->config = data->table;
+	factors->get_factors = data->getter;
+	factors->lock = lock;
+
+	/* Add a gate if this factor clock can be gated */
+	if (data->enable) {
+		gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
+		if (!gate) {
+			kfree(factors);
+			return NULL;
+		}
+
+		/* set up gate properties */
+		gate->reg = reg;
+		gate->bit_idx = data->enable;
+		gate->lock = factors->lock;
+		gate_hw = &gate->hw;
+	}
+
+	/* Add a mux if this factor clock can be muxed */
+	if (data->mux) {
+		mux = kzalloc(sizeof(struct clk_mux), GFP_KERNEL);
+		if (!mux) {
+			kfree(factors);
+			kfree(gate);
+			return NULL;
+		}
+
+		/* set up gate properties */
+		mux->reg = reg;
+		mux->shift = data->mux;
+		mux->mask = SUNXI_FACTORS_MUX_MASK;
+		mux->lock = factors->lock;
+		mux_hw = &mux->hw;
+	}
+
+	clk = clk_register_composite(NULL, clk_name,
+			parents, i,
+			mux_hw, &clk_mux_ops,
+			&factors->hw, &clk_factors_ops,
+			gate_hw, &clk_gate_ops, 0);
+
+	if (!IS_ERR(clk)) {
+		of_clk_add_provider(node, of_clk_src_simple_get, clk);
+		clk_register_clkdev(clk, clk_name, NULL);
+	}
+
+	return clk;
+}
diff --git a/drivers/clk/sunxi/clk-factors.h b/drivers/clk/sunxi/clk-factors.h
index d2d0efa39379..9913840018d3 100644
--- a/drivers/clk/sunxi/clk-factors.h
+++ b/drivers/clk/sunxi/clk-factors.h
@@ -3,9 +3,12 @@
 
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
+#include <linux/spinlock.h>
 
 #define SUNXI_FACTORS_NOT_APPLICABLE	(0)
 
+#define SUNXI_FACTORS_MUX_MASK 0x3
+
 struct clk_factors_config {
 	u8 nshift;
 	u8 nwidth;
@@ -18,6 +21,14 @@ struct clk_factors_config {
 	u8 n_start;
 };
 
+struct factors_data {
+	int enable;
+	int mux;
+	struct clk_factors_config *table;
+	void (*getter) (u32 *rate, u32 parent_rate, u8 *n, u8 *k, u8 *m, u8 *p);
+	const char *name;
+};
+
 struct clk_factors {
 	struct clk_hw hw;
 	void __iomem *reg;
@@ -26,5 +37,8 @@ struct clk_factors {
 	spinlock_t *lock;
 };
 
-extern const struct clk_ops clk_factors_ops;
+struct clk * __init sunxi_factors_register(struct device_node *node,
+					   const struct factors_data *data,
+					   spinlock_t *lock);
+
 #endif
diff --git a/drivers/clk/sunxi/clk-mod0.c b/drivers/clk/sunxi/clk-mod0.c
new file mode 100644
index 000000000000..4a563850ee6e
--- /dev/null
+++ b/drivers/clk/sunxi/clk-mod0.c
@@ -0,0 +1,283 @@
+/*
+ * Copyright 2013 Emilio López
+ *
+ * Emilio López <emilio@elopez.com.ar>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/of_address.h>
+
+#include "clk-factors.h"
+
+/**
+ * sun4i_get_mod0_factors() - calculates m, n factors for MOD0-style clocks
+ * MOD0 rate is calculated as follows
+ * rate = (parent_rate >> p) / (m + 1);
+ */
+
+static void sun4i_a10_get_mod0_factors(u32 *freq, u32 parent_rate,
+				       u8 *n, u8 *k, u8 *m, u8 *p)
+{
+	u8 div, calcm, calcp;
+
+	/* These clocks can only divide, so we will never be able to achieve
+	 * frequencies higher than the parent frequency */
+	if (*freq > parent_rate)
+		*freq = parent_rate;
+
+	div = DIV_ROUND_UP(parent_rate, *freq);
+
+	if (div < 16)
+		calcp = 0;
+	else if (div / 2 < 16)
+		calcp = 1;
+	else if (div / 4 < 16)
+		calcp = 2;
+	else
+		calcp = 3;
+
+	calcm = DIV_ROUND_UP(div, 1 << calcp);
+
+	*freq = (parent_rate >> calcp) / calcm;
+
+	/* we were called to round the frequency, we can now return */
+	if (n == NULL)
+		return;
+
+	*m = calcm - 1;
+	*p = calcp;
+}
+
+/* user manual says "n" but it's really "p" */
+static struct clk_factors_config sun4i_a10_mod0_config = {
+	.mshift = 0,
+	.mwidth = 4,
+	.pshift = 16,
+	.pwidth = 2,
+};
+
+static const struct factors_data sun4i_a10_mod0_data __initconst = {
+	.enable = 31,
+	.mux = 24,
+	.table = &sun4i_a10_mod0_config,
+	.getter = sun4i_a10_get_mod0_factors,
+};
+
+static DEFINE_SPINLOCK(sun4i_a10_mod0_lock);
+
+static void __init sun4i_a10_mod0_setup(struct device_node *node)
+{
+	sunxi_factors_register(node, &sun4i_a10_mod0_data, &sun4i_a10_mod0_lock);
+}
+CLK_OF_DECLARE(sun4i_a10_mod0, "allwinner,sun4i-a10-mod0-clk", sun4i_a10_mod0_setup);
+
+static DEFINE_SPINLOCK(sun5i_a13_mbus_lock);
+
+static void __init sun5i_a13_mbus_setup(struct device_node *node)
+{
+	struct clk *mbus = sunxi_factors_register(node, &sun4i_a10_mod0_data, &sun5i_a13_mbus_lock);
+
+	/* The MBUS clocks needs to be always enabled */
+	__clk_get(mbus);
+	clk_prepare_enable(mbus);
+}
+CLK_OF_DECLARE(sun5i_a13_mbus, "allwinner,sun5i-a13-mbus-clk", sun5i_a13_mbus_setup);
+
+struct mmc_phase_data {
+	u8	offset;
+};
+
+struct mmc_phase {
+	struct clk_hw		hw;
+	void __iomem		*reg;
+	struct mmc_phase_data	*data;
+	spinlock_t		*lock;
+};
+
+#define to_mmc_phase(_hw) container_of(_hw, struct mmc_phase, hw)
+
+static int mmc_get_phase(struct clk_hw *hw)
+{
+	struct clk *mmc, *mmc_parent, *clk = hw->clk;
+	struct mmc_phase *phase = to_mmc_phase(hw);
+	unsigned int mmc_rate, mmc_parent_rate;
+	u16 step, mmc_div;
+	u32 value;
+	u8 delay;
+
+	value = readl(phase->reg);
+	delay = (value >> phase->data->offset) & 0x3;
+
+	if (!delay)
+		return 180;
+
+	/* Get the main MMC clock */
+	mmc = clk_get_parent(clk);
+	if (!mmc)
+		return -EINVAL;
+
+	/* And its rate */
+	mmc_rate = clk_get_rate(mmc);
+	if (!mmc_rate)
+		return -EINVAL;
+
+	/* Now, get the MMC parent (most likely some PLL) */
+	mmc_parent = clk_get_parent(mmc);
+	if (!mmc_parent)
+		return -EINVAL;
+
+	/* And its rate */
+	mmc_parent_rate = clk_get_rate(mmc_parent);
+	if (!mmc_parent_rate)
+		return -EINVAL;
+
+	/* Get MMC clock divider */
+	mmc_div = mmc_parent_rate / mmc_rate;
+
+	step = DIV_ROUND_CLOSEST(360, mmc_div);
+	return delay * step;
+}
+
+static int mmc_set_phase(struct clk_hw *hw, int degrees)
+{
+	struct clk *mmc, *mmc_parent, *clk = hw->clk;
+	struct mmc_phase *phase = to_mmc_phase(hw);
+	unsigned int mmc_rate, mmc_parent_rate;
+	unsigned long flags;
+	u32 value;
+	u8 delay;
+
+	/* Get the main MMC clock */
+	mmc = clk_get_parent(clk);
+	if (!mmc)
+		return -EINVAL;
+
+	/* And its rate */
+	mmc_rate = clk_get_rate(mmc);
+	if (!mmc_rate)
+		return -EINVAL;
+
+	/* Now, get the MMC parent (most likely some PLL) */
+	mmc_parent = clk_get_parent(mmc);
+	if (!mmc_parent)
+		return -EINVAL;
+
+	/* And its rate */
+	mmc_parent_rate = clk_get_rate(mmc_parent);
+	if (!mmc_parent_rate)
+		return -EINVAL;
+
+	if (degrees != 180) {
+		u16 step, mmc_div;
+
+		/* Get MMC clock divider */
+		mmc_div = mmc_parent_rate / mmc_rate;
+
+		/*
+		 * We can only outphase the clocks by multiple of the
+		 * PLL's period.
+		 *
+		 * Since the MMC clock in only a divider, and the
+		 * formula to get the outphasing in degrees is deg =
+		 * 360 * delta / period
+		 *
+		 * If we simplify this formula, we can see that the
+		 * only thing that we're concerned about is the number
+		 * of period we want to outphase our clock from, and
+		 * the divider set by the MMC clock.
+		 */
+		step = DIV_ROUND_CLOSEST(360, mmc_div);
+		delay = DIV_ROUND_CLOSEST(degrees, step);
+	} else {
+		delay = 0;
+	}
+
+	spin_lock_irqsave(phase->lock, flags);
+	value = readl(phase->reg);
+	value &= ~GENMASK(phase->data->offset + 3, phase->data->offset);
+	value |= delay << phase->data->offset;
+	writel(value, phase->reg);
+	spin_unlock_irqrestore(phase->lock, flags);
+
+	return 0;
+}
+
+static const struct clk_ops mmc_clk_ops = {
+	.get_phase	= mmc_get_phase,
+	.set_phase	= mmc_set_phase,
+};
+
+static void __init sun4i_a10_mmc_phase_setup(struct device_node *node,
+					     struct mmc_phase_data *data)
+{
+	const char *parent_names[1] = { of_clk_get_parent_name(node, 0) };
+	struct clk_init_data init = {
+		.num_parents	= 1,
+		.parent_names	= parent_names,
+		.ops		= &mmc_clk_ops,
+	};
+
+	struct mmc_phase *phase;
+	struct clk *clk;
+
+	phase = kmalloc(sizeof(*phase), GFP_KERNEL);
+	if (!phase)
+		return;
+
+	phase->hw.init = &init;
+
+	phase->reg = of_iomap(node, 0);
+	if (!phase->reg)
+		goto err_free;
+
+	phase->data = data;
+	phase->lock = &sun4i_a10_mod0_lock;
+
+	if (of_property_read_string(node, "clock-output-names", &init.name))
+		init.name = node->name;
+
+	clk = clk_register(NULL, &phase->hw);
+	if (IS_ERR(clk))
+		goto err_unmap;
+
+	of_clk_add_provider(node, of_clk_src_simple_get, clk);
+
+	return;
+
+err_unmap:
+	iounmap(phase->reg);
+err_free:
+	kfree(phase);
+}
+
+
+static struct mmc_phase_data mmc_output_clk = {
+	.offset	= 8,
+};
+
+static struct mmc_phase_data mmc_sample_clk = {
+	.offset	= 20,
+};
+
+static void __init sun4i_a10_mmc_output_setup(struct device_node *node)
+{
+	sun4i_a10_mmc_phase_setup(node, &mmc_output_clk);
+}
+CLK_OF_DECLARE(sun4i_a10_mmc_output, "allwinner,sun4i-a10-mmc-output-clk", sun4i_a10_mmc_output_setup);
+
+static void __init sun4i_a10_mmc_sample_setup(struct device_node *node)
+{
+	sun4i_a10_mmc_phase_setup(node, &mmc_sample_clk);
+}
+CLK_OF_DECLARE(sun4i_a10_mmc_sample, "allwinner,sun4i-a10-mmc-sample-clk", sun4i_a10_mmc_sample_setup);
diff --git a/drivers/clk/sunxi/clk-sun6i-apb0-gates.c b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
index e10d0521ec76..64f3e46d383c 100644
--- a/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
+++ b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
@@ -99,7 +99,6 @@ static int sun6i_a31_apb0_gates_clk_probe(struct platform_device *pdev)
 static struct platform_driver sun6i_a31_apb0_gates_clk_driver = {
 	.driver = {
 		.name = "sun6i-a31-apb0-gates-clk",
-		.owner = THIS_MODULE,
 		.of_match_table = sun6i_a31_apb0_gates_clk_dt_ids,
 	},
 	.probe = sun6i_a31_apb0_gates_clk_probe,
diff --git a/drivers/clk/sunxi/clk-sun6i-apb0.c b/drivers/clk/sunxi/clk-sun6i-apb0.c
index 1fa23371c8c6..70763600aeae 100644
--- a/drivers/clk/sunxi/clk-sun6i-apb0.c
+++ b/drivers/clk/sunxi/clk-sun6i-apb0.c
@@ -65,7 +65,6 @@ static const struct of_device_id sun6i_a31_apb0_clk_dt_ids[] = {
 static struct platform_driver sun6i_a31_apb0_clk_driver = {
 	.driver = {
 		.name = "sun6i-a31-apb0-clk",
-		.owner = THIS_MODULE,
 		.of_match_table = sun6i_a31_apb0_clk_dt_ids,
 	},
 	.probe = sun6i_a31_apb0_clk_probe,
diff --git a/drivers/clk/sunxi/clk-sun6i-ar100.c b/drivers/clk/sunxi/clk-sun6i-ar100.c
index eca8ca025b6a..acca53290be2 100644
--- a/drivers/clk/sunxi/clk-sun6i-ar100.c
+++ b/drivers/clk/sunxi/clk-sun6i-ar100.c
@@ -221,7 +221,6 @@ static const struct of_device_id sun6i_a31_ar100_clk_dt_ids[] = {
 static struct platform_driver sun6i_a31_ar100_clk_driver = {
 	.driver = {
 		.name = "sun6i-a31-ar100-clk",
-		.owner = THIS_MODULE,
 		.of_match_table = sun6i_a31_ar100_clk_dt_ids,
 	},
 	.probe = sun6i_a31_ar100_clk_probe,
diff --git a/drivers/clk/sunxi/clk-sun8i-apb0.c b/drivers/clk/sunxi/clk-sun8i-apb0.c
index 1f5ba9b4b8cd..155d0022194f 100644
--- a/drivers/clk/sunxi/clk-sun8i-apb0.c
+++ b/drivers/clk/sunxi/clk-sun8i-apb0.c
@@ -56,7 +56,6 @@ static const struct of_device_id sun8i_a23_apb0_clk_dt_ids[] = {
 static struct platform_driver sun8i_a23_apb0_clk_driver = {
 	.driver = {
 		.name = "sun8i-a23-apb0-clk",
-		.owner = THIS_MODULE,
 		.of_match_table = sun8i_a23_apb0_clk_dt_ids,
 	},
 	.probe = sun8i_a23_apb0_clk_probe,
diff --git a/drivers/clk/sunxi/clk-sun8i-mbus.c b/drivers/clk/sunxi/clk-sun8i-mbus.c
new file mode 100644
index 000000000000..8e49b44cee41
--- /dev/null
+++ b/drivers/clk/sunxi/clk-sun8i-mbus.c
@@ -0,0 +1,78 @@
+/*
+ * Copyright 2014 Chen-Yu Tsai
+ *
+ * Chen-Yu Tsai <wens@csie.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/of_address.h>
+
+#include "clk-factors.h"
+
+/**
+ * sun8i_a23_get_mbus_factors() - calculates m factor for MBUS clocks
+ * MBUS rate is calculated as follows
+ * rate = parent_rate / (m + 1);
+ */
+
+static void sun8i_a23_get_mbus_factors(u32 *freq, u32 parent_rate,
+				       u8 *n, u8 *k, u8 *m, u8 *p)
+{
+	u8 div;
+
+	/*
+	 * These clocks can only divide, so we will never be able to
+	 * achieve frequencies higher than the parent frequency
+	 */
+	if (*freq > parent_rate)
+		*freq = parent_rate;
+
+	div = DIV_ROUND_UP(parent_rate, *freq);
+
+	if (div > 8)
+		div = 8;
+
+	*freq = parent_rate / div;
+
+	/* we were called to round the frequency, we can now return */
+	if (m == NULL)
+		return;
+
+	*m = div - 1;
+}
+
+static struct clk_factors_config sun8i_a23_mbus_config = {
+	.mshift = 0,
+	.mwidth = 3,
+};
+
+static const struct factors_data sun8i_a23_mbus_data __initconst = {
+	.enable = 31,
+	.mux = 24,
+	.table = &sun8i_a23_mbus_config,
+	.getter = sun8i_a23_get_mbus_factors,
+};
+
+static DEFINE_SPINLOCK(sun8i_a23_mbus_lock);
+
+static void __init sun8i_a23_mbus_setup(struct device_node *node)
+{
+	struct clk *mbus = sunxi_factors_register(node, &sun8i_a23_mbus_data,
+						  &sun8i_a23_mbus_lock);
+
+	/* The MBUS clocks needs to be always enabled */
+	__clk_get(mbus);
+	clk_prepare_enable(mbus);
+}
+CLK_OF_DECLARE(sun8i_a23_mbus, "allwinner,sun8i-a23-mbus-clk", sun8i_a23_mbus_setup);
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index b654b7b1d137..d5dc951264ca 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -19,6 +19,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/reset-controller.h>
+#include <linux/spinlock.h>
 
 #include "clk-factors.h"
 
@@ -319,46 +320,6 @@ static void sun4i_get_apb1_factors(u32 *freq, u32 parent_rate,
 
 
 
-/**
- * sun4i_get_mod0_factors() - calculates m, n factors for MOD0-style clocks
- * MOD0 rate is calculated as follows
- * rate = (parent_rate >> p) / (m + 1);
- */
-
-static void sun4i_get_mod0_factors(u32 *freq, u32 parent_rate,
-				   u8 *n, u8 *k, u8 *m, u8 *p)
-{
-	u8 div, calcm, calcp;
-
-	/* These clocks can only divide, so we will never be able to achieve
-	 * frequencies higher than the parent frequency */
-	if (*freq > parent_rate)
-		*freq = parent_rate;
-
-	div = DIV_ROUND_UP(parent_rate, *freq);
-
-	if (div < 16)
-		calcp = 0;
-	else if (div / 2 < 16)
-		calcp = 1;
-	else if (div / 4 < 16)
-		calcp = 2;
-	else
-		calcp = 3;
-
-	calcm = DIV_ROUND_UP(div, 1 << calcp);
-
-	*freq = (parent_rate >> calcp) / calcm;
-
-	/* we were called to round the frequency, we can now return */
-	if (n == NULL)
-		return;
-
-	*m = calcm - 1;
-	*p = calcp;
-}
-
-
 
 /**
  * sun7i_a20_get_out_factors() - calculates m, p factors for CLK_OUT_A/B
@@ -440,16 +401,6 @@ EXPORT_SYMBOL(clk_sunxi_mmc_phase_control);
  * sunxi_factors_clk_setup() - Setup function for factor clocks
  */
 
-#define SUNXI_FACTORS_MUX_MASK 0x3
-
-struct factors_data {
-	int enable;
-	int mux;
-	struct clk_factors_config *table;
-	void (*getter) (u32 *rate, u32 parent_rate, u8 *n, u8 *k, u8 *m, u8 *p);
-	const char *name;
-};
-
 static struct clk_factors_config sun4i_pll1_config = {
 	.nshift = 8,
 	.nwidth = 5,
@@ -504,14 +455,6 @@ static struct clk_factors_config sun4i_apb1_config = {
 };
 
 /* user manual says "n" but it's really "p" */
-static struct clk_factors_config sun4i_mod0_config = {
-	.mshift = 0,
-	.mwidth = 4,
-	.pshift = 16,
-	.pwidth = 2,
-};
-
-/* user manual says "n" but it's really "p" */
 static struct clk_factors_config sun7i_a20_out_config = {
 	.mshift = 8,
 	.mwidth = 5,
@@ -568,13 +511,6 @@ static const struct factors_data sun4i_apb1_data __initconst = {
 	.getter = sun4i_get_apb1_factors,
 };
 
-static const struct factors_data sun4i_mod0_data __initconst = {
-	.enable = 31,
-	.mux = 24,
-	.table = &sun4i_mod0_config,
-	.getter = sun4i_get_mod0_factors,
-};
-
 static const struct factors_data sun7i_a20_out_data __initconst = {
 	.enable = 31,
 	.mux = 24,
@@ -583,89 +519,9 @@ static const struct factors_data sun7i_a20_out_data __initconst = {
 };
 
 static struct clk * __init sunxi_factors_clk_setup(struct device_node *node,
-						const struct factors_data *data)
+						   const struct factors_data *data)
 {
-	struct clk *clk;
-	struct clk_factors *factors;
-	struct clk_gate *gate = NULL;
-	struct clk_mux *mux = NULL;
-	struct clk_hw *gate_hw = NULL;
-	struct clk_hw *mux_hw = NULL;
-	const char *clk_name = node->name;
-	const char *parents[SUNXI_MAX_PARENTS];
-	void __iomem *reg;
-	int i = 0;
-
-	reg = of_iomap(node, 0);
-
-	/* if we have a mux, we will have >1 parents */
-	while (i < SUNXI_MAX_PARENTS &&
-	       (parents[i] = of_clk_get_parent_name(node, i)) != NULL)
-		i++;
-
-	/*
-	 * some factor clocks, such as pll5 and pll6, may have multiple
-	 * outputs, and have their name designated in factors_data
-	 */
-	if (data->name)
-		clk_name = data->name;
-	else
-		of_property_read_string(node, "clock-output-names", &clk_name);
-
-	factors = kzalloc(sizeof(struct clk_factors), GFP_KERNEL);
-	if (!factors)
-		return NULL;
-
-	/* Add a gate if this factor clock can be gated */
-	if (data->enable) {
-		gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
-		if (!gate) {
-			kfree(factors);
-			return NULL;
-		}
-
-		/* set up gate properties */
-		gate->reg = reg;
-		gate->bit_idx = data->enable;
-		gate->lock = &clk_lock;
-		gate_hw = &gate->hw;
-	}
-
-	/* Add a mux if this factor clock can be muxed */
-	if (data->mux) {
-		mux = kzalloc(sizeof(struct clk_mux), GFP_KERNEL);
-		if (!mux) {
-			kfree(factors);
-			kfree(gate);
-			return NULL;
-		}
-
-		/* set up gate properties */
-		mux->reg = reg;
-		mux->shift = data->mux;
-		mux->mask = SUNXI_FACTORS_MUX_MASK;
-		mux->lock = &clk_lock;
-		mux_hw = &mux->hw;
-	}
-
-	/* set up factors properties */
-	factors->reg = reg;
-	factors->config = data->table;
-	factors->get_factors = data->getter;
-	factors->lock = &clk_lock;
-
-	clk = clk_register_composite(NULL, clk_name,
-			parents, i,
-			mux_hw, &clk_mux_ops,
-			&factors->hw, &clk_factors_ops,
-			gate_hw, &clk_gate_ops, 0);
-
-	if (!IS_ERR(clk)) {
-		of_clk_add_provider(node, of_clk_src_simple_get, clk);
-		clk_register_clkdev(clk, clk_name, NULL);
-	}
-
-	return clk;
+	return sunxi_factors_register(node, data, &clk_lock);
 }
 
 
@@ -762,10 +618,19 @@ static const struct div_data sun4i_ahb_data __initconst = {
 	.width	= 2,
 };
 
+static const struct clk_div_table sun4i_apb0_table[] __initconst = {
+	{ .val = 0, .div = 2 },
+	{ .val = 1, .div = 2 },
+	{ .val = 2, .div = 4 },
+	{ .val = 3, .div = 8 },
+	{ } /* sentinel */
+};
+
 static const struct div_data sun4i_apb0_data __initconst = {
 	.shift	= 8,
 	.pow	= 1,
 	.width	= 2,
+	.table	= sun4i_apb0_table,
 };
 
 static const struct div_data sun6i_a31_apb2_div_data __initconst = {
@@ -1199,7 +1064,6 @@ static const struct of_device_id clk_factors_match[] __initconst = {
 	{.compatible = "allwinner,sun7i-a20-pll4-clk", .data = &sun7i_a20_pll4_data,},
 	{.compatible = "allwinner,sun6i-a31-pll6-clk", .data = &sun6i_a31_pll6_data,},
 	{.compatible = "allwinner,sun4i-a10-apb1-clk", .data = &sun4i_apb1_data,},
-	{.compatible = "allwinner,sun4i-a10-mod0-clk", .data = &sun4i_mod0_data,},
 	{.compatible = "allwinner,sun7i-a20-out-clk", .data = &sun7i_a20_out_data,},
 	{}
 };
@@ -1311,7 +1175,6 @@ static void __init sun4i_a10_init_clocks(struct device_node *node)
 CLK_OF_DECLARE(sun4i_a10_clk_init, "allwinner,sun4i-a10", sun4i_a10_init_clocks);
 
 static const char *sun5i_critical_clocks[] __initdata = {
-	"mbus",
 	"pll5_ddr",
 	"ahb_sdram",
 };
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index 9525c684d149..e3a85842ce0c 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -1166,6 +1166,12 @@ static void __init tegra124_pll_init(void __iomem *clk_base,
 	clk_register_clkdev(clk, "pll_c_out1", NULL);
 	clks[TEGRA124_CLK_PLL_C_OUT1] = clk;
 
+	/* PLLC_UD */
+	clk = clk_register_fixed_factor(NULL, "pll_c_ud", "pll_c",
+					CLK_SET_RATE_PARENT, 1, 1);
+	clk_register_clkdev(clk, "pll_c_ud", NULL);
+	clks[TEGRA124_CLK_PLL_C_UD] = clk;
+
 	/* PLLC2 */
 	clk = tegra_clk_register_pllc("pll_c2", "pll_ref", clk_base, pmc, 0,
 			     &pll_c2_params, NULL);
@@ -1198,6 +1204,8 @@ static void __init tegra124_pll_init(void __iomem *clk_base,
 	/* PLLM_UD */
 	clk = clk_register_fixed_factor(NULL, "pll_m_ud", "pll_m",
 					CLK_SET_RATE_PARENT, 1, 1);
+	clk_register_clkdev(clk, "pll_m_ud", NULL);
+	clks[TEGRA124_CLK_PLL_M_UD] = clk;
 
 	/* PLLU */
 	val = readl(clk_base + pll_u_params.base_reg);
diff --git a/drivers/clk/tegra/clk.c b/drivers/clk/tegra/clk.c
index f87c609e8f72..97dc8595c3cd 100644
--- a/drivers/clk/tegra/clk.c
+++ b/drivers/clk/tegra/clk.c
@@ -207,8 +207,13 @@ void __init tegra_init_from_table(struct tegra_clk_init_table *tbl,
 
 	for (; tbl->clk_id < clk_max; tbl++) {
 		clk = clks[tbl->clk_id];
-		if (IS_ERR_OR_NULL(clk))
-			return;
+		if (IS_ERR_OR_NULL(clk)) {
+			pr_err("%s: invalid entry %ld in clks array for id %d\n",
+			       __func__, PTR_ERR(clk), tbl->clk_id);
+			WARN_ON(1);
+
+			continue;
+		}
 
 		if (tbl->parent_id < clk_max) {
 			struct clk *parent = clks[tbl->parent_id];
diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c
index af29359677da..59bb4b39d12e 100644
--- a/drivers/clk/ti/clk-dra7-atl.c
+++ b/drivers/clk/ti/clk-dra7-atl.c
@@ -203,6 +203,7 @@ static void __init of_dra7_atl_clock_setup(struct device_node *node)
 
 	if (!IS_ERR(clk)) {
 		of_clk_add_provider(node, of_clk_src_simple_get, clk);
+		kfree(parent_names);
 		return;
 	}
 cleanup:
@@ -228,6 +229,7 @@ static int of_dra7_atl_clk_probe(struct platform_device *pdev)
 	cinfo->iobase = of_iomap(node, 0);
 	cinfo->dev = &pdev->dev;
 	pm_runtime_enable(cinfo->dev);
+	pm_runtime_irq_safe(cinfo->dev);
 
 	pm_runtime_get_sync(cinfo->dev);
 	atl_write(cinfo, DRA7_ATL_PCLKMUX_REG(0), DRA7_ATL_PCLKMUX);
@@ -301,7 +303,6 @@ MODULE_DEVICE_TABLE(of, of_dra7_atl_clk_match_tbl);
 static struct platform_driver dra7_atl_clk_driver = {
 	.driver = {
 		.name = "dra7-atl",
-		.owner = THIS_MODULE,
 		.of_match_table = of_dra7_atl_clk_match_tbl,
 	},
 	.probe = of_dra7_atl_clk_probe,
diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c
index b1a6f7144f3f..337abe5909e1 100644
--- a/drivers/clk/ti/clk.c
+++ b/drivers/clk/ti/clk.c
@@ -25,8 +25,8 @@
 #undef pr_fmt
 #define pr_fmt(fmt) "%s: " fmt, __func__
 
-static int ti_dt_clk_memmap_index;
 struct ti_clk_ll_ops *ti_clk_ll_ops;
+static struct device_node *clocks_node_ptr[CLK_MAX_MEMMAPS];
 
 /**
  * ti_dt_clocks_register - register DT alias clocks during boot
@@ -108,9 +108,21 @@ void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index)
 	struct clk_omap_reg *reg;
 	u32 val;
 	u32 tmp;
+	int i;
 
 	reg = (struct clk_omap_reg *)&tmp;
-	reg->index = ti_dt_clk_memmap_index;
+
+	for (i = 0; i < CLK_MAX_MEMMAPS; i++) {
+		if (clocks_node_ptr[i] == node->parent)
+			break;
+	}
+
+	if (i == CLK_MAX_MEMMAPS) {
+		pr_err("clk-provider not found for %s!\n", node->name);
+		return NULL;
+	}
+
+	reg->index = i;
 
 	if (of_property_read_u32_index(node, "reg", index, &val)) {
 		pr_err("%s must have reg[%d]!\n", node->name, index);
@@ -127,20 +139,14 @@ void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index)
  * @parent: master node
  * @index: internal index for clk_reg_ops
  *
- * Initializes a master clock IP block and its child clock nodes.
- * Regmap is provided for accessing the register space for the
- * IP block and all the clocks under it.
+ * Initializes a master clock IP block. This basically sets up the
+ * mapping from clocks node to the memory map index. All the clocks
+ * are then initialized through the common of_clk_init call, and the
+ * clocks will access their memory maps based on the node layout.
  */
 void ti_dt_clk_init_provider(struct device_node *parent, int index)
 {
-	const struct of_device_id *match;
-	struct device_node *np;
 	struct device_node *clocks;
-	of_clk_init_cb_t clk_init_cb;
-	struct clk_init_item *retry;
-	struct clk_init_item *tmp;
-
-	ti_dt_clk_memmap_index = index;
 
 	/* get clocks for this parent */
 	clocks = of_get_child_by_name(parent, "clocks");
@@ -149,19 +155,31 @@ void ti_dt_clk_init_provider(struct device_node *parent, int index)
 		return;
 	}
 
-	for_each_child_of_node(clocks, np) {
-		match = of_match_node(&__clk_of_table, np);
-		if (!match)
-			continue;
-		clk_init_cb = (of_clk_init_cb_t)match->data;
-		pr_debug("%s: initializing: %s\n", __func__, np->name);
-		clk_init_cb(np);
-	}
+	/* add clocks node info */
+	clocks_node_ptr[index] = clocks;
+}
 
-	list_for_each_entry_safe(retry, tmp, &retry_list, link) {
-		pr_debug("retry-init: %s\n", retry->node->name);
-		retry->func(retry->hw, retry->node);
-		list_del(&retry->link);
-		kfree(retry);
+/**
+ * ti_dt_clk_init_retry_clks - init clocks from the retry list
+ *
+ * Initializes any clocks that have failed to initialize before,
+ * reasons being missing parent node(s) during earlier init. This
+ * typically happens only for DPLLs which need to have both of their
+ * parent clocks ready during init.
+ */
+void ti_dt_clk_init_retry_clks(void)
+{
+	struct clk_init_item *retry;
+	struct clk_init_item *tmp;
+	int retries = 5;
+
+	while (!list_empty(&retry_list) && retries) {
+		list_for_each_entry_safe(retry, tmp, &retry_list, link) {
+			pr_debug("retry-init: %s\n", retry->node->name);
+			retry->func(retry->hw, retry->node);
+			list_del(&retry->link);
+			kfree(retry);
+		}
+		retries--;
 	}
 }
diff --git a/drivers/clk/ti/clockdomain.c b/drivers/clk/ti/clockdomain.c
index f1e0038d76ac..b4c5faccaece 100644
--- a/drivers/clk/ti/clockdomain.c
+++ b/drivers/clk/ti/clockdomain.c
@@ -36,6 +36,11 @@ static void __init of_ti_clockdomain_setup(struct device_node *node)
 
 	for (i = 0; i < num_clks; i++) {
 		clk = of_clk_get(node, i);
+		if (IS_ERR(clk)) {
+			pr_err("%s: Failed get %s' clock nr %d (%ld)\n",
+			       __func__, node->full_name, i, PTR_ERR(clk));
+			continue;
+		}
 		if (__clk_get_flags(clk) & CLK_IS_BASIC) {
 			pr_warn("can't setup clkdm for basic clk %s\n",
 				__clk_get_name(clk));
diff --git a/drivers/clk/ti/divider.c b/drivers/clk/ti/divider.c
index a837f703be65..bff2b5b8ff59 100644
--- a/drivers/clk/ti/divider.c
+++ b/drivers/clk/ti/divider.c
@@ -300,8 +300,8 @@ static struct clk *_register_divider(struct device *dev, const char *name,
 	return clk;
 }
 
-static struct clk_div_table
-__init *ti_clk_get_div_table(struct device_node *node)
+static struct clk_div_table *
+__init ti_clk_get_div_table(struct device_node *node)
 {
 	struct clk_div_table *table;
 	const __be32 *divspec;
diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c
index 246cf1226eaa..9037bebd69f7 100644
--- a/drivers/clk/zynq/clkc.c
+++ b/drivers/clk/zynq/clkc.c
@@ -85,24 +85,22 @@ static DEFINE_SPINLOCK(canmioclk_lock);
 static DEFINE_SPINLOCK(dbgclk_lock);
 static DEFINE_SPINLOCK(aperclk_lock);
 
-static const char dummy_nm[] __initconst = "dummy_name";
-
-static const char *armpll_parents[] __initdata = {"armpll_int", "ps_clk"};
-static const char *ddrpll_parents[] __initdata = {"ddrpll_int", "ps_clk"};
-static const char *iopll_parents[] __initdata = {"iopll_int", "ps_clk"};
-static const char *gem0_mux_parents[] __initdata = {"gem0_div1", dummy_nm};
-static const char *gem1_mux_parents[] __initdata = {"gem1_div1", dummy_nm};
-static const char *can0_mio_mux2_parents[] __initdata = {"can0_gate",
+static const char *armpll_parents[] __initconst = {"armpll_int", "ps_clk"};
+static const char *ddrpll_parents[] __initconst = {"ddrpll_int", "ps_clk"};
+static const char *iopll_parents[] __initconst = {"iopll_int", "ps_clk"};
+static const char *gem0_mux_parents[] __initconst = {"gem0_div1", "dummy_name"};
+static const char *gem1_mux_parents[] __initconst = {"gem1_div1", "dummy_name"};
+static const char *can0_mio_mux2_parents[] __initconst = {"can0_gate",
 	"can0_mio_mux"};
-static const char *can1_mio_mux2_parents[] __initdata = {"can1_gate",
+static const char *can1_mio_mux2_parents[] __initconst = {"can1_gate",
 	"can1_mio_mux"};
-static const char *dbg_emio_mux_parents[] __initdata = {"dbg_div",
-	dummy_nm};
+static const char *dbg_emio_mux_parents[] __initconst = {"dbg_div",
+	"dummy_name"};
 
-static const char *dbgtrc_emio_input_names[] __initdata = {"trace_emio_clk"};
-static const char *gem0_emio_input_names[] __initdata = {"gem0_emio_clk"};
-static const char *gem1_emio_input_names[] __initdata = {"gem1_emio_clk"};
-static const char *swdt_ext_clk_input_names[] __initdata = {"swdt_ext_clk"};
+static const char *dbgtrc_emio_input_names[] __initconst = {"trace_emio_clk"};
+static const char *gem0_emio_input_names[] __initconst = {"gem0_emio_clk"};
+static const char *gem1_emio_input_names[] __initconst = {"gem1_emio_clk"};
+static const char *swdt_ext_clk_input_names[] __initconst = {"swdt_ext_clk"};
 
 static void __init zynq_clk_register_fclk(enum zynq_clk fclk,
 		const char *clk_name, void __iomem *fclk_ctrl_reg,
@@ -230,6 +228,7 @@ static void __init zynq_clk_setup(struct device_node *np)
 	const char *periph_parents[4];
 	const char *swdt_ext_clk_mux_parents[2];
 	const char *can_mio_mux_parents[NUM_MIO_PINS];
+	const char *dummy_nm = "dummy_name";
 
 	pr_info("Zynq clock init\n");
 
@@ -619,5 +618,4 @@ void __init zynq_clock_init(void)
 np_err:
 	of_node_put(np);
 	BUG();
-	return;
 }
diff --git a/drivers/clk/zynq/pll.c b/drivers/clk/zynq/pll.c
index cec97596fe65..00d72fb5c036 100644
--- a/drivers/clk/zynq/pll.c
+++ b/drivers/clk/zynq/pll.c
@@ -211,10 +211,8 @@ struct clk *clk_register_zynq_pll(const char *name, const char *parent,
 	};
 
 	pll = kmalloc(sizeof(*pll), GFP_KERNEL);
-	if (!pll) {
-		pr_err("%s: Could not allocate Zynq PLL clk.\n", __func__);
+	if (!pll)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	/* Populate the struct */
 	pll->hw.init = &initd;
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 82a2ebe41e27..90420600e1eb 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -30,6 +30,9 @@ config ARMADA_370_XP_TIMER
 	bool
 	select CLKSRC_OF
 
+config MESON6_TIMER
+	bool
+
 config ORION_TIMER
 	select CLKSRC_OF
 	select CLKSRC_MMIO
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index e566f6c7ded4..756f6f10efa0 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_ARCH_PRIMA2)	+= timer-prima2.o
 obj-$(CONFIG_ARCH_U300)		+= timer-u300.o
 obj-$(CONFIG_SUN4I_TIMER)	+= sun4i_timer.o
 obj-$(CONFIG_SUN5I_HSTIMER)	+= timer-sun5i.o
+obj-$(CONFIG_MESON6_TIMER)	+= meson6_timer.o
 obj-$(CONFIG_ARCH_TEGRA)	+= tegra20_timer.o
 obj-$(CONFIG_VT8500_TIMER)	+= vt8500_timer.o
 obj-$(CONFIG_ARCH_NSPIRE)	+= zevio-timer.o
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 5163ec13429d..2133f9d59d06 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -299,6 +299,21 @@ static void __arch_timer_setup(unsigned type,
 	clockevents_config_and_register(clk, arch_timer_rate, 0xf, 0x7fffffff);
 }
 
+static void arch_timer_evtstrm_enable(int divider)
+{
+	u32 cntkctl = arch_timer_get_cntkctl();
+
+	cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK;
+	/* Set the divider and enable virtual event stream */
+	cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
+			| ARCH_TIMER_VIRT_EVT_EN;
+	arch_timer_set_cntkctl(cntkctl);
+	elf_hwcap |= HWCAP_EVTSTRM;
+#ifdef CONFIG_COMPAT
+	compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
+#endif
+}
+
 static void arch_timer_configure_evtstream(void)
 {
 	int evt_stream_div, pos;
@@ -312,6 +327,23 @@ static void arch_timer_configure_evtstream(void)
 	arch_timer_evtstrm_enable(min(pos, 15));
 }
 
+static void arch_counter_set_user_access(void)
+{
+	u32 cntkctl = arch_timer_get_cntkctl();
+
+	/* Disable user access to the timers and the physical counter */
+	/* Also disable virtual event stream */
+	cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
+			| ARCH_TIMER_USR_VT_ACCESS_EN
+			| ARCH_TIMER_VIRT_EVT_EN
+			| ARCH_TIMER_USR_PCT_ACCESS_EN);
+
+	/* Enable user access to the virtual counter */
+	cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+
+	arch_timer_set_cntkctl(cntkctl);
+}
+
 static int arch_timer_setup(struct clock_event_device *clk)
 {
 	__arch_timer_setup(ARCH_CP15_TIMER, clk);
@@ -429,11 +461,19 @@ static void __init arch_counter_register(unsigned type)
 	u64 start_count;
 
 	/* Register the CP15 based counter if we have one */
-	if (type & ARCH_CP15_TIMER)
+	if (type & ARCH_CP15_TIMER) {
 		arch_timer_read_counter = arch_counter_get_cntvct;
-	else
+	} else {
 		arch_timer_read_counter = arch_counter_get_cntvct_mem;
 
+		/* If the clocksource name is "arch_sys_counter" the
+		 * VDSO will attempt to read the CP15-based counter.
+		 * Ensure this does not happen when CP15-based
+		 * counter is not available.
+		 */
+		clocksource_counter.name = "arch_mem_counter";
+	}
+
 	start_count = arch_timer_read_counter();
 	clocksource_register_hz(&clocksource_counter, arch_timer_rate);
 	cyclecounter.mult = clocksource_counter.mult;
@@ -616,17 +656,29 @@ static const struct of_device_id arch_timer_mem_of_match[] __initconst = {
 	{},
 };
 
+static bool __init
+arch_timer_probed(int type, const struct of_device_id *matches)
+{
+	struct device_node *dn;
+	bool probed = false;
+
+	dn = of_find_matching_node(NULL, matches);
+	if (dn && of_device_is_available(dn) && (arch_timers_present & type))
+		probed = true;
+	of_node_put(dn);
+
+	return probed;
+}
+
 static void __init arch_timer_common_init(void)
 {
 	unsigned mask = ARCH_CP15_TIMER | ARCH_MEM_TIMER;
 
 	/* Wait until both nodes are probed if we have two timers */
 	if ((arch_timers_present & mask) != mask) {
-		if (of_find_matching_node(NULL, arch_timer_mem_of_match) &&
-				!(arch_timers_present & ARCH_MEM_TIMER))
+		if (!arch_timer_probed(ARCH_MEM_TIMER, arch_timer_mem_of_match))
 			return;
-		if (of_find_matching_node(NULL, arch_timer_of_match) &&
-				!(arch_timers_present & ARCH_CP15_TIMER))
+		if (!arch_timer_probed(ARCH_CP15_TIMER, arch_timer_of_match))
 			return;
 	}
 
diff --git a/drivers/clocksource/cadence_ttc_timer.c b/drivers/clocksource/cadence_ttc_timer.c
index 7a08811df9aa..510c8a1d37b3 100644
--- a/drivers/clocksource/cadence_ttc_timer.c
+++ b/drivers/clocksource/cadence_ttc_timer.c
@@ -25,7 +25,7 @@
 #include <linux/sched_clock.h>
 
 /*
- * This driver configures the 2 16-bit count-up timers as follows:
+ * This driver configures the 2 16/32-bit count-up timers as follows:
  *
  * T1: Timer 1, clocksource for generic timekeeping
  * T2: Timer 2, clockevent source for hrtimers
@@ -321,7 +321,8 @@ static int ttc_rate_change_clocksource_cb(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
-static void __init ttc_setup_clocksource(struct clk *clk, void __iomem *base)
+static void __init ttc_setup_clocksource(struct clk *clk, void __iomem *base,
+					 u32 timer_width)
 {
 	struct ttc_timer_clocksource *ttccs;
 	int err;
@@ -351,7 +352,7 @@ static void __init ttc_setup_clocksource(struct clk *clk, void __iomem *base)
 	ttccs->cs.name = "ttc_clocksource";
 	ttccs->cs.rating = 200;
 	ttccs->cs.read = __ttc_clocksource_read;
-	ttccs->cs.mask = CLOCKSOURCE_MASK(16);
+	ttccs->cs.mask = CLOCKSOURCE_MASK(timer_width);
 	ttccs->cs.flags = CLOCK_SOURCE_IS_CONTINUOUS;
 
 	/*
@@ -372,7 +373,8 @@ static void __init ttc_setup_clocksource(struct clk *clk, void __iomem *base)
 	}
 
 	ttc_sched_clock_val_reg = base + TTC_COUNT_VAL_OFFSET;
-	sched_clock_register(ttc_sched_clock_read, 16, ttccs->ttc.freq / PRESCALE);
+	sched_clock_register(ttc_sched_clock_read, timer_width,
+			     ttccs->ttc.freq / PRESCALE);
 }
 
 static int ttc_rate_change_clockevent_cb(struct notifier_block *nb,
@@ -467,6 +469,7 @@ static void __init ttc_timer_init(struct device_node *timer)
 	struct clk *clk_cs, *clk_ce;
 	static int initialized;
 	int clksel;
+	u32 timer_width = 16;
 
 	if (initialized)
 		return;
@@ -490,6 +493,8 @@ static void __init ttc_timer_init(struct device_node *timer)
 		BUG();
 	}
 
+	of_property_read_u32(timer, "timer-width", &timer_width);
+
 	clksel = readl_relaxed(timer_baseaddr + TTC_CLK_CNTRL_OFFSET);
 	clksel = !!(clksel & TTC_CLK_CNTRL_CSRC_MASK);
 	clk_cs = of_clk_get(timer, clksel);
@@ -506,7 +511,7 @@ static void __init ttc_timer_init(struct device_node *timer)
 		BUG();
 	}
 
-	ttc_setup_clocksource(clk_cs, timer_baseaddr);
+	ttc_setup_clocksource(clk_cs, timer_baseaddr, timer_width);
 	ttc_setup_clockevent(clk_ce, timer_baseaddr + 4, irq);
 
 	pr_info("%s #0 at %p, irq=%d\n", timer->name, timer_baseaddr, irq);
diff --git a/drivers/clocksource/dummy_timer.c b/drivers/clocksource/dummy_timer.c
index ad3572541728..31990600fcff 100644
--- a/drivers/clocksource/dummy_timer.c
+++ b/drivers/clocksource/dummy_timer.c
@@ -28,7 +28,7 @@ static void dummy_timer_set_mode(enum clock_event_mode mode,
 static void dummy_timer_setup(void)
 {
 	int cpu = smp_processor_id();
-	struct clock_event_device *evt = __this_cpu_ptr(&dummy_timer_evt);
+	struct clock_event_device *evt = raw_cpu_ptr(&dummy_timer_evt);
 
 	evt->name	= "dummy_timer";
 	evt->features	= CLOCK_EVT_FEAT_PERIODIC |
diff --git a/drivers/clocksource/meson6_timer.c b/drivers/clocksource/meson6_timer.c
new file mode 100644
index 000000000000..5c15cba41dca
--- /dev/null
+++ b/drivers/clocksource/meson6_timer.c
@@ -0,0 +1,167 @@
+/*
+ * Amlogic Meson6 SoCs timer handling.
+ *
+ * Copyright (C) 2014 Carlo Caione <carlo@caione.org>
+ *
+ * Based on code from Amlogic, Inc
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqreturn.h>
+#include <linux/sched_clock.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#define CED_ID			0
+#define CSD_ID			4
+
+#define TIMER_ISA_MUX		0
+#define TIMER_ISA_VAL(t)	(((t) + 1) << 2)
+
+#define TIMER_INPUT_BIT(t)	(2 * (t))
+#define TIMER_ENABLE_BIT(t)	(16 + (t))
+#define TIMER_PERIODIC_BIT(t)	(12 + (t))
+
+#define TIMER_CED_INPUT_MASK	(3UL << TIMER_INPUT_BIT(CED_ID))
+#define TIMER_CSD_INPUT_MASK	(7UL << TIMER_INPUT_BIT(CSD_ID))
+
+#define TIMER_CED_UNIT_1US	0
+#define TIMER_CSD_UNIT_1US	1
+
+static void __iomem *timer_base;
+
+static u64 notrace meson6_timer_sched_read(void)
+{
+	return (u64)readl(timer_base + TIMER_ISA_VAL(CSD_ID));
+}
+
+static void meson6_clkevt_time_stop(unsigned char timer)
+{
+	u32 val = readl(timer_base + TIMER_ISA_MUX);
+
+	writel(val & ~TIMER_ENABLE_BIT(timer), timer_base + TIMER_ISA_MUX);
+}
+
+static void meson6_clkevt_time_setup(unsigned char timer, unsigned long delay)
+{
+	writel(delay, timer_base + TIMER_ISA_VAL(timer));
+}
+
+static void meson6_clkevt_time_start(unsigned char timer, bool periodic)
+{
+	u32 val = readl(timer_base + TIMER_ISA_MUX);
+
+	if (periodic)
+		val |= TIMER_PERIODIC_BIT(timer);
+	else
+		val &= ~TIMER_PERIODIC_BIT(timer);
+
+	writel(val | TIMER_ENABLE_BIT(timer), timer_base + TIMER_ISA_MUX);
+}
+
+static void meson6_clkevt_mode(enum clock_event_mode mode,
+			       struct clock_event_device *clk)
+{
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		meson6_clkevt_time_stop(CED_ID);
+		meson6_clkevt_time_setup(CED_ID, USEC_PER_SEC/HZ - 1);
+		meson6_clkevt_time_start(CED_ID, true);
+		break;
+	case CLOCK_EVT_MODE_ONESHOT:
+		meson6_clkevt_time_stop(CED_ID);
+		meson6_clkevt_time_start(CED_ID, false);
+		break;
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	default:
+		meson6_clkevt_time_stop(CED_ID);
+		break;
+	}
+}
+
+static int meson6_clkevt_next_event(unsigned long evt,
+				    struct clock_event_device *unused)
+{
+	meson6_clkevt_time_stop(CED_ID);
+	meson6_clkevt_time_setup(CED_ID, evt);
+	meson6_clkevt_time_start(CED_ID, false);
+
+	return 0;
+}
+
+static struct clock_event_device meson6_clockevent = {
+	.name		= "meson6_tick",
+	.rating		= 400,
+	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.set_mode	= meson6_clkevt_mode,
+	.set_next_event	= meson6_clkevt_next_event,
+};
+
+static irqreturn_t meson6_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = (struct clock_event_device *)dev_id;
+
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction meson6_timer_irq = {
+	.name		= "meson6_timer",
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
+	.handler	= meson6_timer_interrupt,
+	.dev_id		= &meson6_clockevent,
+};
+
+static void __init meson6_timer_init(struct device_node *node)
+{
+	u32 val;
+	int ret, irq;
+
+	timer_base = of_io_request_and_map(node, 0, "meson6-timer");
+	if (IS_ERR(timer_base))
+		panic("Can't map registers");
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (irq <= 0)
+		panic("Can't parse IRQ");
+
+	/* Set 1us for timer E */
+	val = readl(timer_base + TIMER_ISA_MUX);
+	val &= ~TIMER_CSD_INPUT_MASK;
+	val |= TIMER_CSD_UNIT_1US << TIMER_INPUT_BIT(CSD_ID);
+	writel(val, timer_base + TIMER_ISA_MUX);
+
+	sched_clock_register(meson6_timer_sched_read, 32, USEC_PER_SEC);
+	clocksource_mmio_init(timer_base + TIMER_ISA_VAL(CSD_ID), node->name,
+			      1000 * 1000, 300, 32, clocksource_mmio_readl_up);
+
+	/* Timer A base 1us */
+	val &= ~TIMER_CED_INPUT_MASK;
+	val |= TIMER_CED_UNIT_1US << TIMER_INPUT_BIT(CED_ID);
+	writel(val, timer_base + TIMER_ISA_MUX);
+
+	/* Stop the timer A */
+	meson6_clkevt_time_stop(CED_ID);
+
+	ret = setup_irq(irq, &meson6_timer_irq);
+	if (ret)
+		pr_warn("failed to setup irq %d\n", irq);
+
+	meson6_clockevent.cpumask = cpu_possible_mask;
+	meson6_clockevent.irq = irq;
+
+	clockevents_config_and_register(&meson6_clockevent, USEC_PER_SEC,
+					1, 0xfffe);
+}
+CLOCKSOURCE_OF_DECLARE(meson6, "amlogic,meson6-timer",
+		       meson6_timer_init);
diff --git a/drivers/clocksource/metag_generic.c b/drivers/clocksource/metag_generic.c
index 9e4db41abe3c..b7384b853e5a 100644
--- a/drivers/clocksource/metag_generic.c
+++ b/drivers/clocksource/metag_generic.c
@@ -90,7 +90,7 @@ static struct clocksource clocksource_metag = {
 
 static irqreturn_t metag_timer_interrupt(int irq, void *dummy)
 {
-	struct clock_event_device *evt = &__get_cpu_var(local_clockevent);
+	struct clock_event_device *evt = this_cpu_ptr(&local_clockevent);
 
 	evt->event_handler(evt);
 
diff --git a/drivers/clocksource/qcom-timer.c b/drivers/clocksource/qcom-timer.c
index 8d115db1e651..098c542e5c53 100644
--- a/drivers/clocksource/qcom-timer.c
+++ b/drivers/clocksource/qcom-timer.c
@@ -219,7 +219,7 @@ static void __init msm_timer_init(u32 dgt_hz, int sched_bits, int irq,
 		}
 
 		/* Immediately configure the timer on the boot CPU */
-		msm_local_timer_setup(__this_cpu_ptr(msm_evt));
+		msm_local_timer_setup(raw_cpu_ptr(msm_evt));
 	}
 
 err:
diff --git a/drivers/clocksource/timer-marco.c b/drivers/clocksource/timer-marco.c
index 330e93064692..caf7a2030461 100644
--- a/drivers/clocksource/timer-marco.c
+++ b/drivers/clocksource/timer-marco.c
@@ -63,7 +63,7 @@ static inline void sirfsoc_timer_count_disable(int idx)
 /* enable count and interrupt */
 static inline void sirfsoc_timer_count_enable(int idx)
 {
-	writel_relaxed(readl_relaxed(sirfsoc_timer_base + SIRFSOC_TIMER_32COUNTER_0_CTRL + 4 * idx) | 0x7,
+	writel_relaxed(readl_relaxed(sirfsoc_timer_base + SIRFSOC_TIMER_32COUNTER_0_CTRL + 4 * idx) | 0x3,
 		sirfsoc_timer_base + SIRFSOC_TIMER_32COUNTER_0_CTRL + 4 * idx);
 }
 
@@ -103,6 +103,9 @@ static int sirfsoc_timer_set_next_event(unsigned long delta,
 {
 	int cpu = smp_processor_id();
 
+	/* disable timer first, then modify the related registers */
+	sirfsoc_timer_count_disable(cpu);
+
 	writel_relaxed(0, sirfsoc_timer_base + SIRFSOC_TIMER_COUNTER_0 +
 		4 * cpu);
 	writel_relaxed(delta, sirfsoc_timer_base + SIRFSOC_TIMER_MATCH_0 +
diff --git a/drivers/clocksource/vf_pit_timer.c b/drivers/clocksource/vf_pit_timer.c
index a918bc481c52..b45ac6229b57 100644
--- a/drivers/clocksource/vf_pit_timer.c
+++ b/drivers/clocksource/vf_pit_timer.c
@@ -93,6 +93,10 @@ static void pit_set_mode(enum clock_event_mode mode,
 	case CLOCK_EVT_MODE_PERIODIC:
 		pit_set_next_event(cycle_per_jiffy, evt);
 		break;
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	case CLOCK_EVT_MODE_UNUSED:
+		pit_timer_disable();
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index ffe350f86bca..3489f8f5fada 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -183,14 +183,14 @@ config CPU_FREQ_GOV_CONSERVATIVE
 
 	  If in doubt, say N.
 
-config GENERIC_CPUFREQ_CPU0
-	tristate "Generic CPU0 cpufreq driver"
+config CPUFREQ_DT
+	tristate "Generic DT based cpufreq driver"
 	depends on HAVE_CLK && OF
-	# if CPU_THERMAL is on and THERMAL=m, CPU0 cannot be =y:
+	# if CPU_THERMAL is on and THERMAL=m, CPUFREQ_DT cannot be =y:
 	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
-	  This adds a generic cpufreq driver for CPU0 frequency management.
+	  This adds a generic DT based cpufreq driver for frequency management.
 	  It supports both uniprocessor (UP) and symmetric multiprocessor (SMP)
 	  systems which share clock and voltage across all CPUs.
 
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 28c666c80149..83a75dc84761 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -92,7 +92,7 @@ config ARM_EXYNOS_CPU_FREQ_BOOST_SW
 
 config ARM_HIGHBANK_CPUFREQ
 	tristate "Calxeda Highbank-based"
-	depends on ARCH_HIGHBANK && GENERIC_CPUFREQ_CPU0 && REGULATOR
+	depends on ARCH_HIGHBANK && CPUFREQ_DT && REGULATOR
 	default m
 	help
 	  This adds the CPUFreq driver for Calxeda Highbank SoC
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index db6d9a2fea4d..40c53dc1937e 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND)	+= cpufreq_ondemand.o
 obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o
 obj-$(CONFIG_CPU_FREQ_GOV_COMMON)		+= cpufreq_governor.o
 
-obj-$(CONFIG_GENERIC_CPUFREQ_CPU0)	+= cpufreq-cpu0.o
+obj-$(CONFIG_CPUFREQ_DT)		+= cpufreq-dt.o
 
 ##################################################################################
 # x86 drivers.
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
deleted file mode 100644
index 0d2172b07765..000000000000
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ /dev/null
@@ -1,248 +0,0 @@
-/*
- * Copyright (C) 2012 Freescale Semiconductor, Inc.
- *
- * The OPP code in function cpu0_set_target() is reused from
- * drivers/cpufreq/omap-cpufreq.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
-
-#include <linux/clk.h>
-#include <linux/cpu.h>
-#include <linux/cpu_cooling.h>
-#include <linux/cpufreq.h>
-#include <linux/cpumask.h>
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/pm_opp.h>
-#include <linux/platform_device.h>
-#include <linux/regulator/consumer.h>
-#include <linux/slab.h>
-#include <linux/thermal.h>
-
-static unsigned int transition_latency;
-static unsigned int voltage_tolerance; /* in percentage */
-
-static struct device *cpu_dev;
-static struct clk *cpu_clk;
-static struct regulator *cpu_reg;
-static struct cpufreq_frequency_table *freq_table;
-static struct thermal_cooling_device *cdev;
-
-static int cpu0_set_target(struct cpufreq_policy *policy, unsigned int index)
-{
-	struct dev_pm_opp *opp;
-	unsigned long volt = 0, volt_old = 0, tol = 0;
-	unsigned int old_freq, new_freq;
-	long freq_Hz, freq_exact;
-	int ret;
-
-	freq_Hz = clk_round_rate(cpu_clk, freq_table[index].frequency * 1000);
-	if (freq_Hz <= 0)
-		freq_Hz = freq_table[index].frequency * 1000;
-
-	freq_exact = freq_Hz;
-	new_freq = freq_Hz / 1000;
-	old_freq = clk_get_rate(cpu_clk) / 1000;
-
-	if (!IS_ERR(cpu_reg)) {
-		rcu_read_lock();
-		opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_Hz);
-		if (IS_ERR(opp)) {
-			rcu_read_unlock();
-			pr_err("failed to find OPP for %ld\n", freq_Hz);
-			return PTR_ERR(opp);
-		}
-		volt = dev_pm_opp_get_voltage(opp);
-		rcu_read_unlock();
-		tol = volt * voltage_tolerance / 100;
-		volt_old = regulator_get_voltage(cpu_reg);
-	}
-
-	pr_debug("%u MHz, %ld mV --> %u MHz, %ld mV\n",
-		 old_freq / 1000, volt_old ? volt_old / 1000 : -1,
-		 new_freq / 1000, volt ? volt / 1000 : -1);
-
-	/* scaling up?  scale voltage before frequency */
-	if (!IS_ERR(cpu_reg) && new_freq > old_freq) {
-		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
-		if (ret) {
-			pr_err("failed to scale voltage up: %d\n", ret);
-			return ret;
-		}
-	}
-
-	ret = clk_set_rate(cpu_clk, freq_exact);
-	if (ret) {
-		pr_err("failed to set clock rate: %d\n", ret);
-		if (!IS_ERR(cpu_reg))
-			regulator_set_voltage_tol(cpu_reg, volt_old, tol);
-		return ret;
-	}
-
-	/* scaling down?  scale voltage after frequency */
-	if (!IS_ERR(cpu_reg) && new_freq < old_freq) {
-		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
-		if (ret) {
-			pr_err("failed to scale voltage down: %d\n", ret);
-			clk_set_rate(cpu_clk, old_freq * 1000);
-		}
-	}
-
-	return ret;
-}
-
-static int cpu0_cpufreq_init(struct cpufreq_policy *policy)
-{
-	policy->clk = cpu_clk;
-	return cpufreq_generic_init(policy, freq_table, transition_latency);
-}
-
-static struct cpufreq_driver cpu0_cpufreq_driver = {
-	.flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
-	.verify = cpufreq_generic_frequency_table_verify,
-	.target_index = cpu0_set_target,
-	.get = cpufreq_generic_get,
-	.init = cpu0_cpufreq_init,
-	.name = "generic_cpu0",
-	.attr = cpufreq_generic_attr,
-};
-
-static int cpu0_cpufreq_probe(struct platform_device *pdev)
-{
-	struct device_node *np;
-	int ret;
-
-	cpu_dev = get_cpu_device(0);
-	if (!cpu_dev) {
-		pr_err("failed to get cpu0 device\n");
-		return -ENODEV;
-	}
-
-	np = of_node_get(cpu_dev->of_node);
-	if (!np) {
-		pr_err("failed to find cpu0 node\n");
-		return -ENOENT;
-	}
-
-	cpu_reg = regulator_get_optional(cpu_dev, "cpu0");
-	if (IS_ERR(cpu_reg)) {
-		/*
-		 * If cpu0 regulator supply node is present, but regulator is
-		 * not yet registered, we should try defering probe.
-		 */
-		if (PTR_ERR(cpu_reg) == -EPROBE_DEFER) {
-			dev_dbg(cpu_dev, "cpu0 regulator not ready, retry\n");
-			ret = -EPROBE_DEFER;
-			goto out_put_node;
-		}
-		pr_warn("failed to get cpu0 regulator: %ld\n",
-			PTR_ERR(cpu_reg));
-	}
-
-	cpu_clk = clk_get(cpu_dev, NULL);
-	if (IS_ERR(cpu_clk)) {
-		ret = PTR_ERR(cpu_clk);
-		pr_err("failed to get cpu0 clock: %d\n", ret);
-		goto out_put_reg;
-	}
-
-	/* OPPs might be populated at runtime, don't check for error here */
-	of_init_opp_table(cpu_dev);
-
-	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
-	if (ret) {
-		pr_err("failed to init cpufreq table: %d\n", ret);
-		goto out_put_clk;
-	}
-
-	of_property_read_u32(np, "voltage-tolerance", &voltage_tolerance);
-
-	if (of_property_read_u32(np, "clock-latency", &transition_latency))
-		transition_latency = CPUFREQ_ETERNAL;
-
-	if (!IS_ERR(cpu_reg)) {
-		struct dev_pm_opp *opp;
-		unsigned long min_uV, max_uV;
-		int i;
-
-		/*
-		 * OPP is maintained in order of increasing frequency, and
-		 * freq_table initialised from OPP is therefore sorted in the
-		 * same order.
-		 */
-		for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++)
-			;
-		rcu_read_lock();
-		opp = dev_pm_opp_find_freq_exact(cpu_dev,
-				freq_table[0].frequency * 1000, true);
-		min_uV = dev_pm_opp_get_voltage(opp);
-		opp = dev_pm_opp_find_freq_exact(cpu_dev,
-				freq_table[i-1].frequency * 1000, true);
-		max_uV = dev_pm_opp_get_voltage(opp);
-		rcu_read_unlock();
-		ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV);
-		if (ret > 0)
-			transition_latency += ret * 1000;
-	}
-
-	ret = cpufreq_register_driver(&cpu0_cpufreq_driver);
-	if (ret) {
-		pr_err("failed register driver: %d\n", ret);
-		goto out_free_table;
-	}
-
-	/*
-	 * For now, just loading the cooling device;
-	 * thermal DT code takes care of matching them.
-	 */
-	if (of_find_property(np, "#cooling-cells", NULL)) {
-		cdev = of_cpufreq_cooling_register(np, cpu_present_mask);
-		if (IS_ERR(cdev))
-			pr_err("running cpufreq without cooling device: %ld\n",
-			       PTR_ERR(cdev));
-	}
-
-	of_node_put(np);
-	return 0;
-
-out_free_table:
-	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
-out_put_clk:
-	if (!IS_ERR(cpu_clk))
-		clk_put(cpu_clk);
-out_put_reg:
-	if (!IS_ERR(cpu_reg))
-		regulator_put(cpu_reg);
-out_put_node:
-	of_node_put(np);
-	return ret;
-}
-
-static int cpu0_cpufreq_remove(struct platform_device *pdev)
-{
-	cpufreq_cooling_unregister(cdev);
-	cpufreq_unregister_driver(&cpu0_cpufreq_driver);
-	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
-
-	return 0;
-}
-
-static struct platform_driver cpu0_cpufreq_platdrv = {
-	.driver = {
-		.name	= "cpufreq-cpu0",
-		.owner	= THIS_MODULE,
-	},
-	.probe		= cpu0_cpufreq_probe,
-	.remove		= cpu0_cpufreq_remove,
-};
-module_platform_driver(cpu0_cpufreq_platdrv);
-
-MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>");
-MODULE_DESCRIPTION("Generic CPU0 cpufreq driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
new file mode 100644
index 000000000000..6bbb8b913446
--- /dev/null
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -0,0 +1,364 @@
+/*
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ *
+ * Copyright (C) 2014 Linaro.
+ * Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * The OPP code in function set_target() is reused from
+ * drivers/cpufreq/omap-cpufreq.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/cpu_cooling.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pm_opp.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+
+struct private_data {
+	struct device *cpu_dev;
+	struct regulator *cpu_reg;
+	struct thermal_cooling_device *cdev;
+	unsigned int voltage_tolerance; /* in percentage */
+};
+
+static int set_target(struct cpufreq_policy *policy, unsigned int index)
+{
+	struct dev_pm_opp *opp;
+	struct cpufreq_frequency_table *freq_table = policy->freq_table;
+	struct clk *cpu_clk = policy->clk;
+	struct private_data *priv = policy->driver_data;
+	struct device *cpu_dev = priv->cpu_dev;
+	struct regulator *cpu_reg = priv->cpu_reg;
+	unsigned long volt = 0, volt_old = 0, tol = 0;
+	unsigned int old_freq, new_freq;
+	long freq_Hz, freq_exact;
+	int ret;
+
+	freq_Hz = clk_round_rate(cpu_clk, freq_table[index].frequency * 1000);
+	if (freq_Hz <= 0)
+		freq_Hz = freq_table[index].frequency * 1000;
+
+	freq_exact = freq_Hz;
+	new_freq = freq_Hz / 1000;
+	old_freq = clk_get_rate(cpu_clk) / 1000;
+
+	if (!IS_ERR(cpu_reg)) {
+		rcu_read_lock();
+		opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_Hz);
+		if (IS_ERR(opp)) {
+			rcu_read_unlock();
+			dev_err(cpu_dev, "failed to find OPP for %ld\n",
+				freq_Hz);
+			return PTR_ERR(opp);
+		}
+		volt = dev_pm_opp_get_voltage(opp);
+		rcu_read_unlock();
+		tol = volt * priv->voltage_tolerance / 100;
+		volt_old = regulator_get_voltage(cpu_reg);
+	}
+
+	dev_dbg(cpu_dev, "%u MHz, %ld mV --> %u MHz, %ld mV\n",
+		old_freq / 1000, volt_old ? volt_old / 1000 : -1,
+		new_freq / 1000, volt ? volt / 1000 : -1);
+
+	/* scaling up?  scale voltage before frequency */
+	if (!IS_ERR(cpu_reg) && new_freq > old_freq) {
+		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
+		if (ret) {
+			dev_err(cpu_dev, "failed to scale voltage up: %d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	ret = clk_set_rate(cpu_clk, freq_exact);
+	if (ret) {
+		dev_err(cpu_dev, "failed to set clock rate: %d\n", ret);
+		if (!IS_ERR(cpu_reg))
+			regulator_set_voltage_tol(cpu_reg, volt_old, tol);
+		return ret;
+	}
+
+	/* scaling down?  scale voltage after frequency */
+	if (!IS_ERR(cpu_reg) && new_freq < old_freq) {
+		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
+		if (ret) {
+			dev_err(cpu_dev, "failed to scale voltage down: %d\n",
+				ret);
+			clk_set_rate(cpu_clk, old_freq * 1000);
+		}
+	}
+
+	return ret;
+}
+
+static int allocate_resources(int cpu, struct device **cdev,
+			      struct regulator **creg, struct clk **cclk)
+{
+	struct device *cpu_dev;
+	struct regulator *cpu_reg;
+	struct clk *cpu_clk;
+	int ret = 0;
+	char *reg_cpu0 = "cpu0", *reg_cpu = "cpu", *reg;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev) {
+		pr_err("failed to get cpu%d device\n", cpu);
+		return -ENODEV;
+	}
+
+	/* Try "cpu0" for older DTs */
+	if (!cpu)
+		reg = reg_cpu0;
+	else
+		reg = reg_cpu;
+
+try_again:
+	cpu_reg = regulator_get_optional(cpu_dev, reg);
+	if (IS_ERR(cpu_reg)) {
+		/*
+		 * If cpu's regulator supply node is present, but regulator is
+		 * not yet registered, we should try defering probe.
+		 */
+		if (PTR_ERR(cpu_reg) == -EPROBE_DEFER) {
+			dev_dbg(cpu_dev, "cpu%d regulator not ready, retry\n",
+				cpu);
+			return -EPROBE_DEFER;
+		}
+
+		/* Try with "cpu-supply" */
+		if (reg == reg_cpu0) {
+			reg = reg_cpu;
+			goto try_again;
+		}
+
+		dev_warn(cpu_dev, "failed to get cpu%d regulator: %ld\n",
+			 cpu, PTR_ERR(cpu_reg));
+	}
+
+	cpu_clk = clk_get(cpu_dev, NULL);
+	if (IS_ERR(cpu_clk)) {
+		/* put regulator */
+		if (!IS_ERR(cpu_reg))
+			regulator_put(cpu_reg);
+
+		ret = PTR_ERR(cpu_clk);
+
+		/*
+		 * If cpu's clk node is present, but clock is not yet
+		 * registered, we should try defering probe.
+		 */
+		if (ret == -EPROBE_DEFER)
+			dev_dbg(cpu_dev, "cpu%d clock not ready, retry\n", cpu);
+		else
+			dev_err(cpu_dev, "failed to get cpu%d clock: %d\n", ret,
+				cpu);
+	} else {
+		*cdev = cpu_dev;
+		*creg = cpu_reg;
+		*cclk = cpu_clk;
+	}
+
+	return ret;
+}
+
+static int cpufreq_init(struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *freq_table;
+	struct thermal_cooling_device *cdev;
+	struct device_node *np;
+	struct private_data *priv;
+	struct device *cpu_dev;
+	struct regulator *cpu_reg;
+	struct clk *cpu_clk;
+	unsigned int transition_latency;
+	int ret;
+
+	ret = allocate_resources(policy->cpu, &cpu_dev, &cpu_reg, &cpu_clk);
+	if (ret) {
+		pr_err("%s: Failed to allocate resources\n: %d", __func__, ret);
+		return ret;
+	}
+
+	np = of_node_get(cpu_dev->of_node);
+	if (!np) {
+		dev_err(cpu_dev, "failed to find cpu%d node\n", policy->cpu);
+		ret = -ENOENT;
+		goto out_put_reg_clk;
+	}
+
+	/* OPPs might be populated at runtime, don't check for error here */
+	of_init_opp_table(cpu_dev);
+
+	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
+	if (ret) {
+		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
+		goto out_put_node;
+	}
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		ret = -ENOMEM;
+		goto out_free_table;
+	}
+
+	of_property_read_u32(np, "voltage-tolerance", &priv->voltage_tolerance);
+
+	if (of_property_read_u32(np, "clock-latency", &transition_latency))
+		transition_latency = CPUFREQ_ETERNAL;
+
+	if (!IS_ERR(cpu_reg)) {
+		struct dev_pm_opp *opp;
+		unsigned long min_uV, max_uV;
+		int i;
+
+		/*
+		 * OPP is maintained in order of increasing frequency, and
+		 * freq_table initialised from OPP is therefore sorted in the
+		 * same order.
+		 */
+		for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++)
+			;
+		rcu_read_lock();
+		opp = dev_pm_opp_find_freq_exact(cpu_dev,
+				freq_table[0].frequency * 1000, true);
+		min_uV = dev_pm_opp_get_voltage(opp);
+		opp = dev_pm_opp_find_freq_exact(cpu_dev,
+				freq_table[i-1].frequency * 1000, true);
+		max_uV = dev_pm_opp_get_voltage(opp);
+		rcu_read_unlock();
+		ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV);
+		if (ret > 0)
+			transition_latency += ret * 1000;
+	}
+
+	/*
+	 * For now, just loading the cooling device;
+	 * thermal DT code takes care of matching them.
+	 */
+	if (of_find_property(np, "#cooling-cells", NULL)) {
+		cdev = of_cpufreq_cooling_register(np, cpu_present_mask);
+		if (IS_ERR(cdev))
+			dev_err(cpu_dev,
+				"running cpufreq without cooling device: %ld\n",
+				PTR_ERR(cdev));
+		else
+			priv->cdev = cdev;
+	}
+
+	priv->cpu_dev = cpu_dev;
+	priv->cpu_reg = cpu_reg;
+	policy->driver_data = priv;
+
+	policy->clk = cpu_clk;
+	ret = cpufreq_generic_init(policy, freq_table, transition_latency);
+	if (ret)
+		goto out_cooling_unregister;
+
+	of_node_put(np);
+
+	return 0;
+
+out_cooling_unregister:
+	cpufreq_cooling_unregister(priv->cdev);
+	kfree(priv);
+out_free_table:
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
+out_put_node:
+	of_node_put(np);
+out_put_reg_clk:
+	clk_put(cpu_clk);
+	if (!IS_ERR(cpu_reg))
+		regulator_put(cpu_reg);
+
+	return ret;
+}
+
+static int cpufreq_exit(struct cpufreq_policy *policy)
+{
+	struct private_data *priv = policy->driver_data;
+
+	cpufreq_cooling_unregister(priv->cdev);
+	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
+	clk_put(policy->clk);
+	if (!IS_ERR(priv->cpu_reg))
+		regulator_put(priv->cpu_reg);
+	kfree(priv);
+
+	return 0;
+}
+
+static struct cpufreq_driver dt_cpufreq_driver = {
+	.flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.verify = cpufreq_generic_frequency_table_verify,
+	.target_index = set_target,
+	.get = cpufreq_generic_get,
+	.init = cpufreq_init,
+	.exit = cpufreq_exit,
+	.name = "cpufreq-dt",
+	.attr = cpufreq_generic_attr,
+};
+
+static int dt_cpufreq_probe(struct platform_device *pdev)
+{
+	struct device *cpu_dev;
+	struct regulator *cpu_reg;
+	struct clk *cpu_clk;
+	int ret;
+
+	/*
+	 * All per-cluster (CPUs sharing clock/voltages) initialization is done
+	 * from ->init(). In probe(), we just need to make sure that clk and
+	 * regulators are available. Else defer probe and retry.
+	 *
+	 * FIXME: Is checking this only for CPU0 sufficient ?
+	 */
+	ret = allocate_resources(0, &cpu_dev, &cpu_reg, &cpu_clk);
+	if (ret)
+		return ret;
+
+	clk_put(cpu_clk);
+	if (!IS_ERR(cpu_reg))
+		regulator_put(cpu_reg);
+
+	ret = cpufreq_register_driver(&dt_cpufreq_driver);
+	if (ret)
+		dev_err(cpu_dev, "failed register driver: %d\n", ret);
+
+	return ret;
+}
+
+static int dt_cpufreq_remove(struct platform_device *pdev)
+{
+	cpufreq_unregister_driver(&dt_cpufreq_driver);
+	return 0;
+}
+
+static struct platform_driver dt_cpufreq_platdrv = {
+	.driver = {
+		.name	= "cpufreq-dt",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= dt_cpufreq_probe,
+	.remove		= dt_cpufreq_remove,
+};
+module_platform_driver(dt_cpufreq_platdrv);
+
+MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
+MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>");
+MODULE_DESCRIPTION("Generic cpufreq driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 61190f6b4829..24bf76fba141 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -437,7 +437,7 @@ static struct cpufreq_governor *__find_governor(const char *str_governor)
 	struct cpufreq_governor *t;
 
 	list_for_each_entry(t, &cpufreq_governor_list, governor_list)
-		if (!strnicmp(str_governor, t->name, CPUFREQ_NAME_LEN))
+		if (!strncasecmp(str_governor, t->name, CPUFREQ_NAME_LEN))
 			return t;
 
 	return NULL;
@@ -455,10 +455,10 @@ static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
 		goto out;
 
 	if (cpufreq_driver->setpolicy) {
-		if (!strnicmp(str_governor, "performance", CPUFREQ_NAME_LEN)) {
+		if (!strncasecmp(str_governor, "performance", CPUFREQ_NAME_LEN)) {
 			*policy = CPUFREQ_POLICY_PERFORMANCE;
 			err = 0;
-		} else if (!strnicmp(str_governor, "powersave",
+		} else if (!strncasecmp(str_governor, "powersave",
 						CPUFREQ_NAME_LEN)) {
 			*policy = CPUFREQ_POLICY_POWERSAVE;
 			err = 0;
@@ -1382,7 +1382,7 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 		if (!cpufreq_suspended)
 			pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n",
 				 __func__, new_cpu, cpu);
-	} else if (cpufreq_driver->stop_cpu && cpufreq_driver->setpolicy) {
+	} else if (cpufreq_driver->stop_cpu) {
 		cpufreq_driver->stop_cpu(policy);
 	}
 
diff --git a/drivers/cpufreq/exynos4210-cpufreq.c b/drivers/cpufreq/exynos4210-cpufreq.c
index 61a54310a1b9..843ec824fd91 100644
--- a/drivers/cpufreq/exynos4210-cpufreq.c
+++ b/drivers/cpufreq/exynos4210-cpufreq.c
@@ -127,7 +127,7 @@ int exynos4210_cpufreq_init(struct exynos_dvfs_info *info)
 	 * dependencies on platform headers. It is necessary to enable
 	 * Exynos multi-platform support and will be removed together with
 	 * this whole driver as soon as Exynos gets migrated to use
-	 * cpufreq-cpu0 driver.
+	 * cpufreq-dt driver.
 	 */
 	np = of_find_compatible_node(NULL, NULL, "samsung,exynos4210-clock");
 	if (!np) {
diff --git a/drivers/cpufreq/exynos4x12-cpufreq.c b/drivers/cpufreq/exynos4x12-cpufreq.c
index 351a2074cfea..9e78a850e29f 100644
--- a/drivers/cpufreq/exynos4x12-cpufreq.c
+++ b/drivers/cpufreq/exynos4x12-cpufreq.c
@@ -174,7 +174,7 @@ int exynos4x12_cpufreq_init(struct exynos_dvfs_info *info)
 	 * dependencies on platform headers. It is necessary to enable
 	 * Exynos multi-platform support and will be removed together with
 	 * this whole driver as soon as Exynos gets migrated to use
-	 * cpufreq-cpu0 driver.
+	 * cpufreq-dt driver.
 	 */
 	np = of_find_compatible_node(NULL, NULL, "samsung,exynos4412-clock");
 	if (!np) {
diff --git a/drivers/cpufreq/exynos5250-cpufreq.c b/drivers/cpufreq/exynos5250-cpufreq.c
index c91ce69dc631..3eafdc7ba787 100644
--- a/drivers/cpufreq/exynos5250-cpufreq.c
+++ b/drivers/cpufreq/exynos5250-cpufreq.c
@@ -153,7 +153,7 @@ int exynos5250_cpufreq_init(struct exynos_dvfs_info *info)
 	 * dependencies on platform headers. It is necessary to enable
 	 * Exynos multi-platform support and will be removed together with
 	 * this whole driver as soon as Exynos gets migrated to use
-	 * cpufreq-cpu0 driver.
+	 * cpufreq-dt driver.
 	 */
 	np = of_find_compatible_node(NULL, NULL, "samsung,exynos5250-clock");
 	if (!np) {
diff --git a/drivers/cpufreq/highbank-cpufreq.c b/drivers/cpufreq/highbank-cpufreq.c
index bf8902a0866d..ec399ad2f059 100644
--- a/drivers/cpufreq/highbank-cpufreq.c
+++ b/drivers/cpufreq/highbank-cpufreq.c
@@ -6,7 +6,7 @@
  * published by the Free Software Foundation.
  *
  * This driver provides the clk notifier callbacks that are used when
- * the cpufreq-cpu0 driver changes to frequency to alert the highbank
+ * the cpufreq-dt driver changes to frequency to alert the highbank
  * EnergyCore Management Engine (ECME) about the need to change
  * voltage. The ECME interfaces with the actual voltage regulators.
  */
@@ -60,7 +60,7 @@ static struct notifier_block hb_cpufreq_clk_nb = {
 
 static int hb_cpufreq_driver_init(void)
 {
-	struct platform_device_info devinfo = { .name = "cpufreq-cpu0", };
+	struct platform_device_info devinfo = { .name = "cpufreq-dt", };
 	struct device *cpu_dev;
 	struct clk *cpu_clk;
 	struct device_node *np;
@@ -95,7 +95,7 @@ static int hb_cpufreq_driver_init(void)
 		goto out_put_node;
 	}
 
-	/* Instantiate cpufreq-cpu0 */
+	/* Instantiate cpufreq-dt */
 	platform_device_register_full(&devinfo);
 
 out_put_node:
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index 37a480680cd0..7906d4acfe40 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/clk.h>
-#include <linux/clk-provider.h>
 #include <linux/cpufreq.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
@@ -39,8 +38,7 @@ static struct priv
  * - cpu clk
  * - ddr clk
  *
- * The frequencies are set at runtime before registering this *
- * table.
+ * The frequencies are set at runtime before registering this table.
  */
 static struct cpufreq_frequency_table kirkwood_freq_table[] = {
 	{0, STATE_CPU_FREQ,	0}, /* CPU uses cpuclk */
@@ -50,9 +48,7 @@ static struct cpufreq_frequency_table kirkwood_freq_table[] = {
 
 static unsigned int kirkwood_cpufreq_get_cpu_frequency(unsigned int cpu)
 {
-	if (__clk_is_enabled(priv.powersave_clk))
-		return kirkwood_freq_table[1].frequency;
-	return kirkwood_freq_table[0].frequency;
+	return clk_get_rate(priv.powersave_clk) / 1000;
 }
 
 static int kirkwood_cpufreq_target(struct cpufreq_policy *policy,
@@ -70,10 +66,10 @@ static int kirkwood_cpufreq_target(struct cpufreq_policy *policy,
 
 	switch (state) {
 	case STATE_CPU_FREQ:
-		clk_disable(priv.powersave_clk);
+		clk_set_parent(priv.powersave_clk, priv.cpu_clk);
 		break;
 	case STATE_DDR_FREQ:
-		clk_enable(priv.powersave_clk);
+		clk_set_parent(priv.powersave_clk, priv.ddr_clk);
 		break;
 	}
 
@@ -150,7 +146,7 @@ static int kirkwood_cpufreq_probe(struct platform_device *pdev)
 		err = PTR_ERR(priv.powersave_clk);
 		goto out_ddr;
 	}
-	clk_prepare(priv.powersave_clk);
+	clk_prepare_enable(priv.powersave_clk);
 
 	of_node_put(np);
 	np = NULL;
diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c
index 7615180d7ee3..1f49d97a70ea 100644
--- a/drivers/cpufreq/pmac32-cpufreq.c
+++ b/drivers/cpufreq/pmac32-cpufreq.c
@@ -611,7 +611,7 @@ static int __init pmac_cpufreq_setup(void)
 	struct device_node	*cpunode;
 	const u32		*value;
 
-	if (strstr(cmd_line, "nocpufreq"))
+	if (strstr(boot_command_line, "nocpufreq"))
 		return 0;
 
 	/* Get first CPU node */
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 379c0837f5a9..2dfd4fdb5a52 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -26,6 +26,7 @@
 #include <linux/cpufreq.h>
 #include <linux/smp.h>
 #include <linux/of.h>
+#include <linux/reboot.h>
 
 #include <asm/cputhreads.h>
 #include <asm/firmware.h>
@@ -35,6 +36,7 @@
 #define POWERNV_MAX_PSTATES	256
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
+static bool rebooting;
 
 /*
  * Note: The set of pstates consists of contiguous integers, the
@@ -284,6 +286,15 @@ static void set_pstate(void *freq_data)
 }
 
 /*
+ * get_nominal_index: Returns the index corresponding to the nominal
+ * pstate in the cpufreq table
+ */
+static inline unsigned int get_nominal_index(void)
+{
+	return powernv_pstate_info.max - powernv_pstate_info.nominal;
+}
+
+/*
  * powernv_cpufreq_target_index: Sets the frequency corresponding to
  * the cpufreq table entry indexed by new_index on the cpus in the
  * mask policy->cpus
@@ -293,6 +304,9 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 {
 	struct powernv_smp_call_data freq_data;
 
+	if (unlikely(rebooting) && new_index != get_nominal_index())
+		return 0;
+
 	freq_data.pstate_id = powernv_freqs[new_index].driver_data;
 
 	/*
@@ -317,6 +331,33 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	return cpufreq_table_validate_and_show(policy, powernv_freqs);
 }
 
+static int powernv_cpufreq_reboot_notifier(struct notifier_block *nb,
+				unsigned long action, void *unused)
+{
+	int cpu;
+	struct cpufreq_policy cpu_policy;
+
+	rebooting = true;
+	for_each_online_cpu(cpu) {
+		cpufreq_get_policy(&cpu_policy, cpu);
+		powernv_cpufreq_target_index(&cpu_policy, get_nominal_index());
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block powernv_cpufreq_reboot_nb = {
+	.notifier_call = powernv_cpufreq_reboot_notifier,
+};
+
+static void powernv_cpufreq_stop_cpu(struct cpufreq_policy *policy)
+{
+	struct powernv_smp_call_data freq_data;
+
+	freq_data.pstate_id = powernv_pstate_info.min;
+	smp_call_function_single(policy->cpu, set_pstate, &freq_data, 1);
+}
+
 static struct cpufreq_driver powernv_cpufreq_driver = {
 	.name		= "powernv-cpufreq",
 	.flags		= CPUFREQ_CONST_LOOPS,
@@ -324,6 +365,7 @@ static struct cpufreq_driver powernv_cpufreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= powernv_cpufreq_target_index,
 	.get		= powernv_cpufreq_get,
+	.stop_cpu	= powernv_cpufreq_stop_cpu,
 	.attr		= powernv_cpu_freq_attr,
 };
 
@@ -342,12 +384,14 @@ static int __init powernv_cpufreq_init(void)
 		return rc;
 	}
 
+	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
 	return cpufreq_register_driver(&powernv_cpufreq_driver);
 }
 module_init(powernv_cpufreq_init);
 
 static void __exit powernv_cpufreq_exit(void)
 {
+	unregister_reboot_notifier(&powernv_cpufreq_reboot_nb);
 	cpufreq_unregister_driver(&powernv_cpufreq_driver);
 }
 module_exit(powernv_cpufreq_exit);
diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c
index 3607070797af..bee5df7794d3 100644
--- a/drivers/cpufreq/ppc-corenet-cpufreq.c
+++ b/drivers/cpufreq/ppc-corenet-cpufreq.c
@@ -199,7 +199,6 @@ static int corenet_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	data->table = table;
-	per_cpu(cpu_data, cpu) = data;
 
 	/* update ->cpus if we have cluster, no harm if not */
 	cpumask_copy(policy->cpus, per_cpu(cpu_mask, cpu));
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index 3f9791f07b8e..567caa6313ff 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -597,7 +597,7 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev)
 	 * and dependencies on platform headers. It is necessary to enable
 	 * S5PV210 multi-platform support and will be removed together with
 	 * this whole driver as soon as S5PV210 gets migrated to use
-	 * cpufreq-cpu0 driver.
+	 * cpufreq-dt driver.
 	 */
 	np = of_find_compatible_node(NULL, NULL, "samsung,s5pv210-clock");
 	if (!np) {
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index 32748c36c477..c5029c1209b4 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -25,11 +25,19 @@ config CPU_IDLE_GOV_MENU
 	bool "Menu governor (for tickless system)"
 	default y
 
+config DT_IDLE_STATES
+	bool
+
 menu "ARM CPU Idle Drivers"
 depends on ARM
 source "drivers/cpuidle/Kconfig.arm"
 endmenu
 
+menu "ARM64 CPU Idle Drivers"
+depends on ARM64
+source "drivers/cpuidle/Kconfig.arm64"
+endmenu
+
 menu "MIPS CPU Idle Drivers"
 depends on MIPS
 source "drivers/cpuidle/Kconfig.mips"
diff --git a/drivers/cpuidle/Kconfig.arm b/drivers/cpuidle/Kconfig.arm
index 58bcd0d166ec..8c16ab20fb15 100644
--- a/drivers/cpuidle/Kconfig.arm
+++ b/drivers/cpuidle/Kconfig.arm
@@ -7,6 +7,7 @@ config ARM_BIG_LITTLE_CPUIDLE
 	depends on MCPM
 	select ARM_CPU_SUSPEND
 	select CPU_IDLE_MULTIPLE_DRIVERS
+	select DT_IDLE_STATES
 	help
 	  Select this option to enable CPU idle driver for big.LITTLE based
 	  ARM systems. Driver manages CPUs coordination through MCPM and
diff --git a/drivers/cpuidle/Kconfig.arm64 b/drivers/cpuidle/Kconfig.arm64
new file mode 100644
index 000000000000..d0a08ed1b2ee
--- /dev/null
+++ b/drivers/cpuidle/Kconfig.arm64
@@ -0,0 +1,14 @@
+#
+# ARM64 CPU Idle drivers
+#
+
+config ARM64_CPUIDLE
+	bool "Generic ARM64 CPU idle Driver"
+	select ARM64_CPU_SUSPEND
+	select DT_IDLE_STATES
+	help
+	  Select this to enable generic cpuidle driver for ARM64.
+	  It provides a generic idle driver whose idle states are configured
+	  at run-time through DT nodes. The CPUidle suspend backend is
+	  initialized by calling the CPU operations init idle hook
+	  provided by architecture code.
diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile
index 11edb31c55e9..4d177b916f75 100644
--- a/drivers/cpuidle/Makefile
+++ b/drivers/cpuidle/Makefile
@@ -4,6 +4,7 @@
 
 obj-y += cpuidle.o driver.o governor.o sysfs.o governors/
 obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o
+obj-$(CONFIG_DT_IDLE_STATES)		  += dt_idle_states.o
 
 ##################################################################################
 # ARM SoC drivers
@@ -22,6 +23,10 @@ obj-$(CONFIG_ARM_EXYNOS_CPUIDLE)        += cpuidle-exynos.o
 obj-$(CONFIG_MIPS_CPS_CPUIDLE)		+= cpuidle-cps.o
 
 ###############################################################################
+# ARM64 drivers
+obj-$(CONFIG_ARM64_CPUIDLE)		+= cpuidle-arm64.o
+
+###############################################################################
 # POWERPC drivers
 obj-$(CONFIG_PSERIES_CPUIDLE)		+= cpuidle-pseries.o
 obj-$(CONFIG_POWERNV_CPUIDLE)		+= cpuidle-powernv.o
diff --git a/drivers/cpuidle/cpuidle-arm64.c b/drivers/cpuidle/cpuidle-arm64.c
new file mode 100644
index 000000000000..50997ea942fc
--- /dev/null
+++ b/drivers/cpuidle/cpuidle-arm64.c
@@ -0,0 +1,133 @@
+/*
+ * ARM64 generic CPU idle driver.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) "CPUidle arm64: " fmt
+
+#include <linux/cpuidle.h>
+#include <linux/cpumask.h>
+#include <linux/cpu_pm.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+
+#include <asm/cpuidle.h>
+#include <asm/suspend.h>
+
+#include "dt_idle_states.h"
+
+/*
+ * arm64_enter_idle_state - Programs CPU to enter the specified state
+ *
+ * dev: cpuidle device
+ * drv: cpuidle driver
+ * idx: state index
+ *
+ * Called from the CPUidle framework to program the device to the
+ * specified target state selected by the governor.
+ */
+static int arm64_enter_idle_state(struct cpuidle_device *dev,
+				  struct cpuidle_driver *drv, int idx)
+{
+	int ret;
+
+	if (!idx) {
+		cpu_do_idle();
+		return idx;
+	}
+
+	ret = cpu_pm_enter();
+	if (!ret) {
+		/*
+		 * Pass idle state index to cpu_suspend which in turn will
+		 * call the CPU ops suspend protocol with idle index as a
+		 * parameter.
+		 */
+		ret = cpu_suspend(idx);
+
+		cpu_pm_exit();
+	}
+
+	return ret ? -1 : idx;
+}
+
+static struct cpuidle_driver arm64_idle_driver = {
+	.name = "arm64_idle",
+	.owner = THIS_MODULE,
+	/*
+	 * State at index 0 is standby wfi and considered standard
+	 * on all ARM platforms. If in some platforms simple wfi
+	 * can't be used as "state 0", DT bindings must be implemented
+	 * to work around this issue and allow installing a special
+	 * handler for idle state index 0.
+	 */
+	.states[0] = {
+		.enter                  = arm64_enter_idle_state,
+		.exit_latency           = 1,
+		.target_residency       = 1,
+		.power_usage		= UINT_MAX,
+		.flags                  = CPUIDLE_FLAG_TIME_VALID,
+		.name                   = "WFI",
+		.desc                   = "ARM64 WFI",
+	}
+};
+
+static const struct of_device_id arm64_idle_state_match[] __initconst = {
+	{ .compatible = "arm,idle-state",
+	  .data = arm64_enter_idle_state },
+	{ },
+};
+
+/*
+ * arm64_idle_init
+ *
+ * Registers the arm64 specific cpuidle driver with the cpuidle
+ * framework. It relies on core code to parse the idle states
+ * and initialize them using driver data structures accordingly.
+ */
+static int __init arm64_idle_init(void)
+{
+	int cpu, ret;
+	struct cpuidle_driver *drv = &arm64_idle_driver;
+
+	/*
+	 * Initialize idle states data, starting at index 1.
+	 * This driver is DT only, if no DT idle states are detected (ret == 0)
+	 * let the driver initialization fail accordingly since there is no
+	 * reason to initialize the idle driver if only wfi is supported.
+	 */
+	ret = dt_init_idle_driver(drv, arm64_idle_state_match, 1);
+	if (ret <= 0) {
+		if (ret)
+			pr_err("failed to initialize idle states\n");
+		return ret ? : -ENODEV;
+	}
+
+	/*
+	 * Call arch CPU operations in order to initialize
+	 * idle states suspend back-end specific data
+	 */
+	for_each_possible_cpu(cpu) {
+		ret = cpu_init_idle(cpu);
+		if (ret) {
+			pr_err("CPU %d failed to init idle CPU ops\n", cpu);
+			return ret;
+		}
+	}
+
+	ret = cpuidle_register(drv, NULL);
+	if (ret) {
+		pr_err("failed to register cpuidle driver\n");
+		return ret;
+	}
+
+	return 0;
+}
+device_initcall(arm64_idle_init);
diff --git a/drivers/cpuidle/cpuidle-big_little.c b/drivers/cpuidle/cpuidle-big_little.c
index ef94c3b81f18..fbc00a1d3c48 100644
--- a/drivers/cpuidle/cpuidle-big_little.c
+++ b/drivers/cpuidle/cpuidle-big_little.c
@@ -24,6 +24,8 @@
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
 
+#include "dt_idle_states.h"
+
 static int bl_enter_powerdown(struct cpuidle_device *dev,
 			      struct cpuidle_driver *drv, int idx);
 
@@ -73,6 +75,12 @@ static struct cpuidle_driver bl_idle_little_driver = {
 	.state_count = 2,
 };
 
+static const struct of_device_id bl_idle_state_match[] __initconst = {
+	{ .compatible = "arm,idle-state",
+	  .data = bl_enter_powerdown },
+	{ },
+};
+
 static struct cpuidle_driver bl_idle_big_driver = {
 	.name = "big_idle",
 	.owner = THIS_MODULE,
@@ -159,6 +167,7 @@ static int __init bl_idle_driver_init(struct cpuidle_driver *drv, int part_id)
 static const struct of_device_id compatible_machine_match[] = {
 	{ .compatible = "arm,vexpress,v2p-ca15_a7" },
 	{ .compatible = "samsung,exynos5420" },
+	{ .compatible = "samsung,exynos5800" },
 	{},
 };
 
@@ -190,6 +199,17 @@ static int __init bl_idle_init(void)
 	if (ret)
 		goto out_uninit_little;
 
+	/* Start at index 1, index 0 standard WFI */
+	ret = dt_init_idle_driver(&bl_idle_big_driver, bl_idle_state_match, 1);
+	if (ret < 0)
+		goto out_uninit_big;
+
+	/* Start at index 1, index 0 standard WFI */
+	ret = dt_init_idle_driver(&bl_idle_little_driver,
+				  bl_idle_state_match, 1);
+	if (ret < 0)
+		goto out_uninit_big;
+
 	ret = cpuidle_register(&bl_idle_little_driver, NULL);
 	if (ret)
 		goto out_uninit_big;
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index ee9df5e3f5eb..125150dc6e81 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -223,8 +223,14 @@ void cpuidle_uninstall_idle_handler(void)
 {
 	if (enabled_devices) {
 		initialized = 0;
-		kick_all_cpus_sync();
+		wake_up_all_idle_cpus();
 	}
+
+	/*
+	 * Make sure external observers (such as the scheduler)
+	 * are done looking at pointed idle states.
+	 */
+	synchronize_rcu();
 }
 
 /**
@@ -530,11 +536,6 @@ EXPORT_SYMBOL_GPL(cpuidle_register);
 
 #ifdef CONFIG_SMP
 
-static void smp_callback(void *v)
-{
-	/* we already woke the CPU up, nothing more to do */
-}
-
 /*
  * This function gets called when a part of the kernel has a new latency
  * requirement.  This means we need to get all processors out of their C-state,
@@ -544,7 +545,7 @@ static void smp_callback(void *v)
 static int cpuidle_latency_notify(struct notifier_block *b,
 		unsigned long l, void *v)
 {
-	smp_call_function(smp_callback, NULL, 1);
+	wake_up_all_idle_cpus();
 	return NOTIFY_OK;
 }
 
diff --git a/drivers/cpuidle/dt_idle_states.c b/drivers/cpuidle/dt_idle_states.c
new file mode 100644
index 000000000000..52f4d11bbf3f
--- /dev/null
+++ b/drivers/cpuidle/dt_idle_states.c
@@ -0,0 +1,213 @@
+/*
+ * DT idle states parsing code.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) "DT idle-states: " fmt
+
+#include <linux/cpuidle.h>
+#include <linux/cpumask.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+#include "dt_idle_states.h"
+
+static int init_state_node(struct cpuidle_state *idle_state,
+			   const struct of_device_id *matches,
+			   struct device_node *state_node)
+{
+	int err;
+	const struct of_device_id *match_id;
+
+	match_id = of_match_node(matches, state_node);
+	if (!match_id)
+		return -ENODEV;
+	/*
+	 * CPUidle drivers are expected to initialize the const void *data
+	 * pointer of the passed in struct of_device_id array to the idle
+	 * state enter function.
+	 */
+	idle_state->enter = match_id->data;
+
+	err = of_property_read_u32(state_node, "wakeup-latency-us",
+				   &idle_state->exit_latency);
+	if (err) {
+		u32 entry_latency, exit_latency;
+
+		err = of_property_read_u32(state_node, "entry-latency-us",
+					   &entry_latency);
+		if (err) {
+			pr_debug(" * %s missing entry-latency-us property\n",
+				 state_node->full_name);
+			return -EINVAL;
+		}
+
+		err = of_property_read_u32(state_node, "exit-latency-us",
+					   &exit_latency);
+		if (err) {
+			pr_debug(" * %s missing exit-latency-us property\n",
+				 state_node->full_name);
+			return -EINVAL;
+		}
+		/*
+		 * If wakeup-latency-us is missing, default to entry+exit
+		 * latencies as defined in idle states bindings
+		 */
+		idle_state->exit_latency = entry_latency + exit_latency;
+	}
+
+	err = of_property_read_u32(state_node, "min-residency-us",
+				   &idle_state->target_residency);
+	if (err) {
+		pr_debug(" * %s missing min-residency-us property\n",
+			     state_node->full_name);
+		return -EINVAL;
+	}
+
+	idle_state->flags = CPUIDLE_FLAG_TIME_VALID;
+	if (of_property_read_bool(state_node, "local-timer-stop"))
+		idle_state->flags |= CPUIDLE_FLAG_TIMER_STOP;
+	/*
+	 * TODO:
+	 *	replace with kstrdup and pointer assignment when name
+	 *	and desc become string pointers
+	 */
+	strncpy(idle_state->name, state_node->name, CPUIDLE_NAME_LEN - 1);
+	strncpy(idle_state->desc, state_node->name, CPUIDLE_DESC_LEN - 1);
+	return 0;
+}
+
+/*
+ * Check that the idle state is uniform across all CPUs in the CPUidle driver
+ * cpumask
+ */
+static bool idle_state_valid(struct device_node *state_node, unsigned int idx,
+			     const cpumask_t *cpumask)
+{
+	int cpu;
+	struct device_node *cpu_node, *curr_state_node;
+	bool valid = true;
+
+	/*
+	 * Compare idle state phandles for index idx on all CPUs in the
+	 * CPUidle driver cpumask. Start from next logical cpu following
+	 * cpumask_first(cpumask) since that's the CPU state_node was
+	 * retrieved from. If a mismatch is found bail out straight
+	 * away since we certainly hit a firmware misconfiguration.
+	 */
+	for (cpu = cpumask_next(cpumask_first(cpumask), cpumask);
+	     cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpumask)) {
+		cpu_node = of_cpu_device_node_get(cpu);
+		curr_state_node = of_parse_phandle(cpu_node, "cpu-idle-states",
+						   idx);
+		if (state_node != curr_state_node)
+			valid = false;
+
+		of_node_put(curr_state_node);
+		of_node_put(cpu_node);
+		if (!valid)
+			break;
+	}
+
+	return valid;
+}
+
+/**
+ * dt_init_idle_driver() - Parse the DT idle states and initialize the
+ *			   idle driver states array
+ * @drv:	  Pointer to CPU idle driver to be initialized
+ * @matches:	  Array of of_device_id match structures to search in for
+ *		  compatible idle state nodes. The data pointer for each valid
+ *		  struct of_device_id entry in the matches array must point to
+ *		  a function with the following signature, that corresponds to
+ *		  the CPUidle state enter function signature:
+ *
+ *		  int (*)(struct cpuidle_device *dev,
+ *			  struct cpuidle_driver *drv,
+ *			  int index);
+ *
+ * @start_idx:    First idle state index to be initialized
+ *
+ * If DT idle states are detected and are valid the state count and states
+ * array entries in the cpuidle driver are initialized accordingly starting
+ * from index start_idx.
+ *
+ * Return: number of valid DT idle states parsed, <0 on failure
+ */
+int dt_init_idle_driver(struct cpuidle_driver *drv,
+			const struct of_device_id *matches,
+			unsigned int start_idx)
+{
+	struct cpuidle_state *idle_state;
+	struct device_node *state_node, *cpu_node;
+	int i, err = 0;
+	const cpumask_t *cpumask;
+	unsigned int state_idx = start_idx;
+
+	if (state_idx >= CPUIDLE_STATE_MAX)
+		return -EINVAL;
+	/*
+	 * We get the idle states for the first logical cpu in the
+	 * driver mask (or cpu_possible_mask if the driver cpumask is not set)
+	 * and we check through idle_state_valid() if they are uniform
+	 * across CPUs, otherwise we hit a firmware misconfiguration.
+	 */
+	cpumask = drv->cpumask ? : cpu_possible_mask;
+	cpu_node = of_cpu_device_node_get(cpumask_first(cpumask));
+
+	for (i = 0; ; i++) {
+		state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
+		if (!state_node)
+			break;
+
+		if (!idle_state_valid(state_node, i, cpumask)) {
+			pr_warn("%s idle state not valid, bailing out\n",
+				state_node->full_name);
+			err = -EINVAL;
+			break;
+		}
+
+		if (state_idx == CPUIDLE_STATE_MAX) {
+			pr_warn("State index reached static CPU idle driver states array size\n");
+			break;
+		}
+
+		idle_state = &drv->states[state_idx++];
+		err = init_state_node(idle_state, matches, state_node);
+		if (err) {
+			pr_err("Parsing idle state node %s failed with err %d\n",
+			       state_node->full_name, err);
+			err = -EINVAL;
+			break;
+		}
+		of_node_put(state_node);
+	}
+
+	of_node_put(state_node);
+	of_node_put(cpu_node);
+	if (err)
+		return err;
+	/*
+	 * Update the driver state count only if some valid DT idle states
+	 * were detected
+	 */
+	if (i)
+		drv->state_count = state_idx;
+
+	/*
+	 * Return the number of present and valid DT idle states, which can
+	 * also be 0 on platforms with missing DT idle states or legacy DT
+	 * configuration predating the DT idle states bindings.
+	 */
+	return i;
+}
+EXPORT_SYMBOL_GPL(dt_init_idle_driver);
diff --git a/drivers/cpuidle/dt_idle_states.h b/drivers/cpuidle/dt_idle_states.h
new file mode 100644
index 000000000000..4818134bc65b
--- /dev/null
+++ b/drivers/cpuidle/dt_idle_states.h
@@ -0,0 +1,7 @@
+#ifndef __DT_IDLE_STATES
+#define __DT_IDLE_STATES
+
+int dt_init_idle_driver(struct cpuidle_driver *drv,
+			const struct of_device_id *matches,
+			unsigned int start_idx);
+#endif
diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c
index ca89412f5122..fb9f511cca23 100644
--- a/drivers/cpuidle/governor.c
+++ b/drivers/cpuidle/governor.c
@@ -28,7 +28,7 @@ static struct cpuidle_governor * __cpuidle_find_governor(const char *str)
 	struct cpuidle_governor *gov;
 
 	list_for_each_entry(gov, &cpuidle_governors, governor_list)
-		if (!strnicmp(str, gov->name, CPUIDLE_NAME_LEN))
+		if (!strncasecmp(str, gov->name, CPUIDLE_NAME_LEN))
 			return gov;
 
 	return NULL;
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index 044ee0df5871..06b57c4c4d80 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -66,7 +66,7 @@ static inline void ladder_do_selection(struct ladder_device *ldev,
 static int ladder_select_state(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev)
 {
-	struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
+	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
 	struct ladder_device_state *last_state;
 	int last_residency, last_idx = ldev->last_state_idx;
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
@@ -170,7 +170,7 @@ static int ladder_enable_device(struct cpuidle_driver *drv,
  */
 static void ladder_reflect(struct cpuidle_device *dev, int index)
 {
-	struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
+	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
 	if (index > 0)
 		ldev->last_state_idx = index;
 }
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 34db2fb3ef1e..710a233b9b0d 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -289,7 +289,7 @@ again:
  */
 static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
-	struct menu_device *data = &__get_cpu_var(menu_devices);
+	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 	int i;
 	unsigned int interactivity_req;
@@ -372,7 +372,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
  */
 static void menu_reflect(struct cpuidle_device *dev, int index)
 {
-	struct menu_device *data = &__get_cpu_var(menu_devices);
+	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	data->last_state_idx = index;
 	if (index >= 0)
 		data->needs_update = 1;
@@ -385,7 +385,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index)
  */
 static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
-	struct menu_device *data = &__get_cpu_var(menu_devices);
+	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	int last_idx = data->last_state_idx;
 	struct cpuidle_state *target = &drv->states[last_idx];
 	unsigned int measured_us;
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index 873f23425245..96531571f7cf 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -198,10 +198,9 @@ static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 {
 	struct ccp_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
 	struct crypto_shash *shash = ctx->u.sha.hmac_tfm;
-	struct {
-		struct shash_desc sdesc;
-		char ctx[crypto_shash_descsize(shash)];
-	} desc;
+
+	SHASH_DESC_ON_STACK(sdesc, shash);
+
 	unsigned int block_size = crypto_shash_blocksize(shash);
 	unsigned int digest_size = crypto_shash_digestsize(shash);
 	int i, ret;
@@ -216,11 +215,11 @@ static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 
 	if (key_len > block_size) {
 		/* Must hash the input key */
-		desc.sdesc.tfm = shash;
-		desc.sdesc.flags = crypto_ahash_get_flags(tfm) &
+		sdesc->tfm = shash;
+		sdesc->flags = crypto_ahash_get_flags(tfm) &
 			CRYPTO_TFM_REQ_MAY_SLEEP;
 
-		ret = crypto_shash_digest(&desc.sdesc, key, key_len,
+		ret = crypto_shash_digest(sdesc, key, key_len,
 					  ctx->u.sha.key);
 		if (ret) {
 			crypto_ahash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
diff --git a/drivers/crypto/mv_cesa.c b/drivers/crypto/mv_cesa.c
index 29d0ee504907..032c72c1f953 100644
--- a/drivers/crypto/mv_cesa.c
+++ b/drivers/crypto/mv_cesa.c
@@ -402,26 +402,23 @@ static int mv_hash_final_fallback(struct ahash_request *req)
 {
 	const struct mv_tfm_hash_ctx *tfm_ctx = crypto_tfm_ctx(req->base.tfm);
 	struct mv_req_hash_ctx *req_ctx = ahash_request_ctx(req);
-	struct {
-		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(tfm_ctx->fallback)];
-	} desc;
+	SHASH_DESC_ON_STACK(shash, tfm_ctx->fallback);
 	int rc;
 
-	desc.shash.tfm = tfm_ctx->fallback;
-	desc.shash.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	shash->tfm = tfm_ctx->fallback;
+	shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	if (unlikely(req_ctx->first_hash)) {
-		crypto_shash_init(&desc.shash);
-		crypto_shash_update(&desc.shash, req_ctx->buffer,
+		crypto_shash_init(shash);
+		crypto_shash_update(shash, req_ctx->buffer,
 				    req_ctx->extra_bytes);
 	} else {
 		/* only SHA1 for now....
 		 */
-		rc = mv_hash_import_sha1_ctx(req_ctx, &desc.shash);
+		rc = mv_hash_import_sha1_ctx(req_ctx, shash);
 		if (rc)
 			goto out;
 	}
-	rc = crypto_shash_final(&desc.shash, req->result);
+	rc = crypto_shash_final(shash, req->result);
 out:
 	return rc;
 }
@@ -794,23 +791,21 @@ static int mv_hash_setkey(struct crypto_ahash *tfm, const u8 * key,
 	ss = crypto_shash_statesize(ctx->base_hash);
 
 	{
-		struct {
-			struct shash_desc shash;
-			char ctx[crypto_shash_descsize(ctx->base_hash)];
-		} desc;
+		SHASH_DESC_ON_STACK(shash, ctx->base_hash);
+
 		unsigned int i;
 		char ipad[ss];
 		char opad[ss];
 
-		desc.shash.tfm = ctx->base_hash;
-		desc.shash.flags = crypto_shash_get_flags(ctx->base_hash) &
+		shash->tfm = ctx->base_hash;
+		shash->flags = crypto_shash_get_flags(ctx->base_hash) &
 		    CRYPTO_TFM_REQ_MAY_SLEEP;
 
 		if (keylen > bs) {
 			int err;
 
 			err =
-			    crypto_shash_digest(&desc.shash, key, keylen, ipad);
+			    crypto_shash_digest(shash, key, keylen, ipad);
 			if (err)
 				return err;
 
@@ -826,12 +821,12 @@ static int mv_hash_setkey(struct crypto_ahash *tfm, const u8 * key,
 			opad[i] ^= 0x5c;
 		}
 
-		rc = crypto_shash_init(&desc.shash) ? :
-		    crypto_shash_update(&desc.shash, ipad, bs) ? :
-		    crypto_shash_export(&desc.shash, ipad) ? :
-		    crypto_shash_init(&desc.shash) ? :
-		    crypto_shash_update(&desc.shash, opad, bs) ? :
-		    crypto_shash_export(&desc.shash, opad);
+		rc = crypto_shash_init(shash) ? :
+		    crypto_shash_update(shash, ipad, bs) ? :
+		    crypto_shash_export(shash, ipad) ? :
+		    crypto_shash_init(shash) ? :
+		    crypto_shash_update(shash, opad, bs) ? :
+		    crypto_shash_export(shash, opad);
 
 		if (rc == 0)
 			mv_hash_init_ivs(ctx, ipad, opad);
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index 7263c10a56ee..f8e3207fecb1 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -445,10 +445,7 @@ static int n2_hmac_async_setkey(struct crypto_ahash *tfm, const u8 *key,
 	struct n2_hmac_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct crypto_shash *child_shash = ctx->child_shash;
 	struct crypto_ahash *fallback_tfm;
-	struct {
-		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(child_shash)];
-	} desc;
+	SHASH_DESC_ON_STACK(shash, child_shash);
 	int err, bs, ds;
 
 	fallback_tfm = ctx->base.fallback_tfm;
@@ -456,15 +453,15 @@ static int n2_hmac_async_setkey(struct crypto_ahash *tfm, const u8 *key,
 	if (err)
 		return err;
 
-	desc.shash.tfm = child_shash;
-	desc.shash.flags = crypto_ahash_get_flags(tfm) &
+	shash->tfm = child_shash;
+	shash->flags = crypto_ahash_get_flags(tfm) &
 		CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	bs = crypto_shash_blocksize(child_shash);
 	ds = crypto_shash_digestsize(child_shash);
 	BUG_ON(ds > N2_HASH_KEY_MAX);
 	if (keylen > bs) {
-		err = crypto_shash_digest(&desc.shash, key, keylen,
+		err = crypto_shash_digest(shash, key, keylen,
 					  ctx->hash_key);
 		if (err)
 			return err;
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index 710d86386965..24ef48965e45 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -949,17 +949,14 @@ static int omap_sham_finish_hmac(struct ahash_request *req)
 	struct omap_sham_hmac_ctx *bctx = tctx->base;
 	int bs = crypto_shash_blocksize(bctx->shash);
 	int ds = crypto_shash_digestsize(bctx->shash);
-	struct {
-		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(bctx->shash)];
-	} desc;
+	SHASH_DESC_ON_STACK(shash, bctx->shash);
 
-	desc.shash.tfm = bctx->shash;
-	desc.shash.flags = 0; /* not CRYPTO_TFM_REQ_MAY_SLEEP */
+	shash->tfm = bctx->shash;
+	shash->flags = 0; /* not CRYPTO_TFM_REQ_MAY_SLEEP */
 
-	return crypto_shash_init(&desc.shash) ?:
-	       crypto_shash_update(&desc.shash, bctx->opad, bs) ?:
-	       crypto_shash_finup(&desc.shash, req->result, ds, req->result);
+	return crypto_shash_init(shash) ?:
+	       crypto_shash_update(shash, bctx->opad, bs) ?:
+	       crypto_shash_finup(shash, req->result, ds, req->result);
 }
 
 static int omap_sham_finish(struct ahash_request *req)
@@ -1118,18 +1115,15 @@ static int omap_sham_update(struct ahash_request *req)
 	return omap_sham_enqueue(req, OP_UPDATE);
 }
 
-static int omap_sham_shash_digest(struct crypto_shash *shash, u32 flags,
+static int omap_sham_shash_digest(struct crypto_shash *tfm, u32 flags,
 				  const u8 *data, unsigned int len, u8 *out)
 {
-	struct {
-		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(shash)];
-	} desc;
+	SHASH_DESC_ON_STACK(shash, tfm);
 
-	desc.shash.tfm = shash;
-	desc.shash.flags = flags & CRYPTO_TFM_REQ_MAY_SLEEP;
+	shash->tfm = tfm;
+	shash->flags = flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 
-	return crypto_shash_digest(&desc.shash, data, len, out);
+	return crypto_shash_digest(shash, data, len, out);
 }
 
 static int omap_sham_final_shash(struct ahash_request *req)
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 3e26fa2b293f..f2e2f158cfbe 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -149,10 +149,7 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 				  unsigned int auth_keylen)
 {
 	struct qat_auth_state auth_state;
-	struct {
-		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(ctx->hash_tfm)];
-	} desc;
+	SHASH_DESC_ON_STACK(shash, ctx->hash_tfm);
 	struct sha1_state sha1;
 	struct sha256_state sha256;
 	struct sha512_state sha512;
@@ -165,12 +162,12 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 	int i, offset;
 
 	memset(auth_state.data, '\0', MAX_AUTH_STATE_SIZE + 64);
-	desc.shash.tfm = ctx->hash_tfm;
-	desc.shash.flags = 0x0;
+	shash->tfm = ctx->hash_tfm;
+	shash->flags = 0x0;
 
 	if (auth_keylen > block_size) {
 		char buff[SHA512_BLOCK_SIZE];
-		int ret = crypto_shash_digest(&desc.shash, auth_key,
+		int ret = crypto_shash_digest(shash, auth_key,
 					      auth_keylen, buff);
 		if (ret)
 			return ret;
@@ -193,10 +190,10 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 		*opad_ptr ^= 0x5C;
 	}
 
-	if (crypto_shash_init(&desc.shash))
+	if (crypto_shash_init(shash))
 		return -EFAULT;
 
-	if (crypto_shash_update(&desc.shash, ipad, block_size))
+	if (crypto_shash_update(shash, ipad, block_size))
 		return -EFAULT;
 
 	hash_state_out = (__be32 *)hash->sha.state1;
@@ -204,19 +201,19 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 
 	switch (ctx->qat_hash_alg) {
 	case ICP_QAT_HW_AUTH_ALGO_SHA1:
-		if (crypto_shash_export(&desc.shash, &sha1))
+		if (crypto_shash_export(shash, &sha1))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
 			*hash_state_out = cpu_to_be32(*(sha1.state + i));
 		break;
 	case ICP_QAT_HW_AUTH_ALGO_SHA256:
-		if (crypto_shash_export(&desc.shash, &sha256))
+		if (crypto_shash_export(shash, &sha256))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
 			*hash_state_out = cpu_to_be32(*(sha256.state + i));
 		break;
 	case ICP_QAT_HW_AUTH_ALGO_SHA512:
-		if (crypto_shash_export(&desc.shash, &sha512))
+		if (crypto_shash_export(shash, &sha512))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 3; i++, hash512_state_out++)
 			*hash512_state_out = cpu_to_be64(*(sha512.state + i));
@@ -225,10 +222,10 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 		return -EFAULT;
 	}
 
-	if (crypto_shash_init(&desc.shash))
+	if (crypto_shash_init(shash))
 		return -EFAULT;
 
-	if (crypto_shash_update(&desc.shash, opad, block_size))
+	if (crypto_shash_update(shash, opad, block_size))
 		return -EFAULT;
 
 	offset = round_up(qat_get_inter_state_size(ctx->qat_hash_alg), 8);
@@ -237,19 +234,19 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 
 	switch (ctx->qat_hash_alg) {
 	case ICP_QAT_HW_AUTH_ALGO_SHA1:
-		if (crypto_shash_export(&desc.shash, &sha1))
+		if (crypto_shash_export(shash, &sha1))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
 			*hash_state_out = cpu_to_be32(*(sha1.state + i));
 		break;
 	case ICP_QAT_HW_AUTH_ALGO_SHA256:
-		if (crypto_shash_export(&desc.shash, &sha256))
+		if (crypto_shash_export(shash, &sha256))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
 			*hash_state_out = cpu_to_be32(*(sha256.state + i));
 		break;
 	case ICP_QAT_HW_AUTH_ALGO_SHA512:
-		if (crypto_shash_export(&desc.shash, &sha512))
+		if (crypto_shash_export(shash, &sha512))
 			return -EFAULT;
 		for (i = 0; i < digest_size >> 3; i++, hash512_state_out++)
 			*hash512_state_out = cpu_to_be64(*(sha512.state + i));
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index 3dced0a9eae3..faf4e70c42e0 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -78,9 +78,8 @@ config ARM_EXYNOS4_BUS_DEVFREQ
 	  This does not yet operate with optimal voltages.
 
 config ARM_EXYNOS5_BUS_DEVFREQ
-	bool "ARM Exynos5250 Bus DEVFREQ Driver"
+	tristate "ARM Exynos5250 Bus DEVFREQ Driver"
 	depends on SOC_EXYNOS5250
-	select ARCH_HAS_OPP
 	select DEVFREQ_GOV_SIMPLE_ONDEMAND
 	select PM_OPP
 	help
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 9f90369dd6bd..30b538d8cc90 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -1119,6 +1119,7 @@ struct dev_pm_opp *devfreq_recommended_opp(struct device *dev,
 
 	return opp;
 }
+EXPORT_SYMBOL(devfreq_recommended_opp);
 
 /**
  * devfreq_register_opp_notifier() - Helper function to get devfreq notified
@@ -1142,6 +1143,7 @@ int devfreq_register_opp_notifier(struct device *dev, struct devfreq *devfreq)
 
 	return ret;
 }
+EXPORT_SYMBOL(devfreq_register_opp_notifier);
 
 /**
  * devfreq_unregister_opp_notifier() - Helper function to stop getting devfreq
@@ -1168,6 +1170,7 @@ int devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq)
 
 	return ret;
 }
+EXPORT_SYMBOL(devfreq_unregister_opp_notifier);
 
 static void devm_devfreq_opp_release(struct device *dev, void *res)
 {
diff --git a/drivers/devfreq/exynos/exynos_ppmu.c b/drivers/devfreq/exynos/exynos_ppmu.c
index 75fcc5140ffb..97b75e513d29 100644
--- a/drivers/devfreq/exynos/exynos_ppmu.c
+++ b/drivers/devfreq/exynos/exynos_ppmu.c
@@ -73,6 +73,7 @@ void busfreq_mon_reset(struct busfreq_ppmu_data *ppmu_data)
 		exynos_ppmu_start(ppmu_base);
 	}
 }
+EXPORT_SYMBOL(busfreq_mon_reset);
 
 void exynos_read_ppmu(struct busfreq_ppmu_data *ppmu_data)
 {
@@ -97,6 +98,7 @@ void exynos_read_ppmu(struct busfreq_ppmu_data *ppmu_data)
 
 	busfreq_mon_reset(ppmu_data);
 }
+EXPORT_SYMBOL(exynos_read_ppmu);
 
 int exynos_get_busier_ppmu(struct busfreq_ppmu_data *ppmu_data)
 {
@@ -114,3 +116,4 @@ int exynos_get_busier_ppmu(struct busfreq_ppmu_data *ppmu_data)
 
 	return busy;
 }
+EXPORT_SYMBOL(exynos_get_busier_ppmu);
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index f3014c448e1e..5be225c2ba98 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -799,7 +799,7 @@ static int dma_buf_describe(struct seq_file *s)
 		seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\n",
 				buf_obj->size,
 				buf_obj->file->f_flags, buf_obj->file->f_mode,
-				(long)(buf_obj->file->f_count.counter),
+				file_count(buf_obj->file),
 				buf_obj->exp_name);
 
 		seq_puts(s, "\tAttached Devices:\n");
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index a016490c95ae..de469821bc1b 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -270,7 +270,7 @@ config IMX_SDMA
 	select DMA_ENGINE
 	help
 	  Support the i.MX SDMA engine. This engine is integrated into
-	  Freescale i.MX25/31/35/51/53 chips.
+	  Freescale i.MX25/31/35/51/53/6 chips.
 
 config IMX_DMA
 	tristate "i.MX DMA support"
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index 3c6716e0b78e..e88588d8ecd3 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -2156,7 +2156,7 @@ coh901318_free_chan_resources(struct dma_chan *chan)
 
 	spin_unlock_irqrestore(&cohc->lock, flags);
 
-	chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
+	dmaengine_terminate_all(chan);
 }
 
 
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index 8f8b0b608875..a58eec3b2cad 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -938,7 +938,7 @@ static int cppi41_dma_probe(struct platform_device *pdev)
 	if (!glue_info)
 		return -EINVAL;
 
-	cdd = kzalloc(sizeof(*cdd), GFP_KERNEL);
+	cdd = devm_kzalloc(&pdev->dev, sizeof(*cdd), GFP_KERNEL);
 	if (!cdd)
 		return -ENOMEM;
 
@@ -959,10 +959,8 @@ static int cppi41_dma_probe(struct platform_device *pdev)
 	cdd->qmgr_mem = of_iomap(dev->of_node, 3);
 
 	if (!cdd->usbss_mem || !cdd->ctrl_mem || !cdd->sched_mem ||
-			!cdd->qmgr_mem) {
-		ret = -ENXIO;
-		goto err_remap;
-	}
+			!cdd->qmgr_mem)
+		return -ENXIO;
 
 	pm_runtime_enable(dev);
 	ret = pm_runtime_get_sync(dev);
@@ -989,7 +987,7 @@ static int cppi41_dma_probe(struct platform_device *pdev)
 
 	cppi_writel(USBSS_IRQ_PD_COMP, cdd->usbss_mem + USBSS_IRQ_ENABLER);
 
-	ret = request_irq(irq, glue_info->isr, IRQF_SHARED,
+	ret = devm_request_irq(&pdev->dev, irq, glue_info->isr, IRQF_SHARED,
 			dev_name(dev), cdd);
 	if (ret)
 		goto err_irq;
@@ -1009,7 +1007,6 @@ static int cppi41_dma_probe(struct platform_device *pdev)
 err_of:
 	dma_async_device_unregister(&cdd->ddev);
 err_dma_reg:
-	free_irq(irq, cdd);
 err_irq:
 	cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
 	cleanup_chans(cdd);
@@ -1023,8 +1020,6 @@ err_get_sync:
 	iounmap(cdd->ctrl_mem);
 	iounmap(cdd->sched_mem);
 	iounmap(cdd->qmgr_mem);
-err_remap:
-	kfree(cdd);
 	return ret;
 }
 
@@ -1036,7 +1031,7 @@ static int cppi41_dma_remove(struct platform_device *pdev)
 	dma_async_device_unregister(&cdd->ddev);
 
 	cppi_writel(0, cdd->usbss_mem + USBSS_IRQ_CLEARR);
-	free_irq(cdd->irq, cdd);
+	devm_free_irq(&pdev->dev, cdd->irq, cdd);
 	cleanup_chans(cdd);
 	deinit_cppi41(&pdev->dev, cdd);
 	iounmap(cdd->usbss_mem);
@@ -1045,7 +1040,6 @@ static int cppi41_dma_remove(struct platform_device *pdev)
 	iounmap(cdd->qmgr_mem);
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	kfree(cdd);
 	return 0;
 }
 
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 1af731b83b3f..244722170410 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -11,7 +11,6 @@
  */
 
 #include <linux/bitops.h>
-#include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
@@ -37,24 +36,6 @@
  * support descriptor writeback.
  */
 
-static inline bool is_request_line_unset(struct dw_dma_chan *dwc)
-{
-	return dwc->request_line == (typeof(dwc->request_line))~0;
-}
-
-static inline void dwc_set_masters(struct dw_dma_chan *dwc)
-{
-	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
-	struct dw_dma_slave *dws = dwc->chan.private;
-	unsigned char mmax = dw->nr_masters - 1;
-
-	if (!is_request_line_unset(dwc))
-		return;
-
-	dwc->src_master = min_t(unsigned char, mmax, dwc_get_sms(dws));
-	dwc->dst_master = min_t(unsigned char, mmax, dwc_get_dms(dws));
-}
-
 #define DWC_DEFAULT_CTLLO(_chan) ({				\
 		struct dw_dma_chan *_dwc = to_dw_dma_chan(_chan);	\
 		struct dma_slave_config	*_sconfig = &_dwc->dma_sconfig;	\
@@ -155,13 +136,11 @@ static void dwc_initialize(struct dw_dma_chan *dwc)
 		 */
 		BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev);
 
-		cfghi = dws->cfg_hi;
-		cfglo |= dws->cfg_lo & ~DWC_CFGL_CH_PRIOR_MASK;
+		cfghi |= DWC_CFGH_DST_PER(dws->dst_id);
+		cfghi |= DWC_CFGH_SRC_PER(dws->src_id);
 	} else {
-		if (dwc->direction == DMA_MEM_TO_DEV)
-			cfghi = DWC_CFGH_DST_PER(dwc->request_line);
-		else if (dwc->direction == DMA_DEV_TO_MEM)
-			cfghi = DWC_CFGH_SRC_PER(dwc->request_line);
+		cfghi |= DWC_CFGH_DST_PER(dwc->dst_id);
+		cfghi |= DWC_CFGH_SRC_PER(dwc->src_id);
 	}
 
 	channel_writel(dwc, CFG_LO, cfglo);
@@ -939,6 +918,26 @@ err_desc_get:
 	return NULL;
 }
 
+bool dw_dma_filter(struct dma_chan *chan, void *param)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+	struct dw_dma_slave *dws = param;
+
+	if (!dws || dws->dma_dev != chan->device->dev)
+		return false;
+
+	/* We have to copy data since dws can be temporary storage */
+
+	dwc->src_id = dws->src_id;
+	dwc->dst_id = dws->dst_id;
+
+	dwc->src_master = dws->src_master;
+	dwc->dst_master = dws->dst_master;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(dw_dma_filter);
+
 /*
  * Fix sconfig's burst size according to dw_dmac. We need to convert them as:
  * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
@@ -967,10 +966,6 @@ set_runtime_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
 	memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
 	dwc->direction = sconfig->direction;
 
-	/* Take the request line from slave_id member */
-	if (is_request_line_unset(dwc))
-		dwc->request_line = sconfig->slave_id;
-
 	convert_burst(&dwc->dma_sconfig.src_maxburst);
 	convert_burst(&dwc->dma_sconfig.dst_maxburst);
 
@@ -1099,6 +1094,31 @@ static void dwc_issue_pending(struct dma_chan *chan)
 	spin_unlock_irqrestore(&dwc->lock, flags);
 }
 
+/*----------------------------------------------------------------------*/
+
+static void dw_dma_off(struct dw_dma *dw)
+{
+	int i;
+
+	dma_writel(dw, CFG, 0);
+
+	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask);
+	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
+
+	while (dma_readl(dw, CFG) & DW_CFG_DMA_EN)
+		cpu_relax();
+
+	for (i = 0; i < dw->dma.chancnt; i++)
+		dw->chan[i].initialized = false;
+}
+
+static void dw_dma_on(struct dw_dma *dw)
+{
+	dma_writel(dw, CFG, DW_CFG_DMA_EN);
+}
+
 static int dwc_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
@@ -1123,7 +1143,10 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 	 * doesn't mean what you think it means), and status writeback.
 	 */
 
-	dwc_set_masters(dwc);
+	/* Enable controller here if needed */
+	if (!dw->in_use)
+		dw_dma_on(dw);
+	dw->in_use |= dwc->mask;
 
 	spin_lock_irqsave(&dwc->lock, flags);
 	i = dwc->descs_allocated;
@@ -1182,7 +1205,6 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	list_splice_init(&dwc->free_list, &list);
 	dwc->descs_allocated = 0;
 	dwc->initialized = false;
-	dwc->request_line = ~0;
 
 	/* Disable interrupts */
 	channel_clear_bit(dw, MASK.XFER, dwc->mask);
@@ -1190,6 +1212,11 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
+	/* Disable controller in case it was a last user */
+	dw->in_use &= ~dwc->mask;
+	if (!dw->in_use)
+		dw_dma_off(dw);
+
 	list_for_each_entry_safe(desc, _desc, &list, desc_node) {
 		dev_vdbg(chan2dev(chan), "  freeing descriptor %p\n", desc);
 		dma_pool_free(dw->desc_pool, desc, desc->txd.phys);
@@ -1460,24 +1487,6 @@ EXPORT_SYMBOL(dw_dma_cyclic_free);
 
 /*----------------------------------------------------------------------*/
 
-static void dw_dma_off(struct dw_dma *dw)
-{
-	int i;
-
-	dma_writel(dw, CFG, 0);
-
-	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask);
-	channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask);
-
-	while (dma_readl(dw, CFG) & DW_CFG_DMA_EN)
-		cpu_relax();
-
-	for (i = 0; i < dw->dma.chancnt; i++)
-		dw->chan[i].initialized = false;
-}
-
 int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 {
 	struct dw_dma		*dw;
@@ -1495,13 +1504,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	dw->regs = chip->regs;
 	chip->dw = dw;
 
-	dw->clk = devm_clk_get(chip->dev, "hclk");
-	if (IS_ERR(dw->clk))
-		return PTR_ERR(dw->clk);
-	err = clk_prepare_enable(dw->clk);
-	if (err)
-		return err;
-
 	dw_params = dma_read_byaddr(chip->regs, DW_PARAMS);
 	autocfg = dw_params >> DW_PARAMS_EN & 0x1;
 
@@ -1604,7 +1606,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 		channel_clear_bit(dw, CH_EN, dwc->mask);
 
 		dwc->direction = DMA_TRANS_NONE;
-		dwc->request_line = ~0;
 
 		/* Hardware configuration */
 		if (autocfg) {
@@ -1659,8 +1660,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	dw->dma.device_tx_status = dwc_tx_status;
 	dw->dma.device_issue_pending = dwc_issue_pending;
 
-	dma_writel(dw, CFG, DW_CFG_DMA_EN);
-
 	err = dma_async_device_register(&dw->dma);
 	if (err)
 		goto err_dma_register;
@@ -1673,7 +1672,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 err_dma_register:
 	free_irq(chip->irq, dw);
 err_pdata:
-	clk_disable_unprepare(dw->clk);
 	return err;
 }
 EXPORT_SYMBOL_GPL(dw_dma_probe);
@@ -1695,46 +1693,27 @@ int dw_dma_remove(struct dw_dma_chip *chip)
 		channel_clear_bit(dw, CH_EN, dwc->mask);
 	}
 
-	clk_disable_unprepare(dw->clk);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dw_dma_remove);
 
-void dw_dma_shutdown(struct dw_dma_chip *chip)
-{
-	struct dw_dma *dw = chip->dw;
-
-	dw_dma_off(dw);
-	clk_disable_unprepare(dw->clk);
-}
-EXPORT_SYMBOL_GPL(dw_dma_shutdown);
-
-#ifdef CONFIG_PM_SLEEP
-
-int dw_dma_suspend(struct dw_dma_chip *chip)
+int dw_dma_disable(struct dw_dma_chip *chip)
 {
 	struct dw_dma *dw = chip->dw;
 
 	dw_dma_off(dw);
-	clk_disable_unprepare(dw->clk);
-
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dw_dma_suspend);
+EXPORT_SYMBOL_GPL(dw_dma_disable);
 
-int dw_dma_resume(struct dw_dma_chip *chip)
+int dw_dma_enable(struct dw_dma_chip *chip)
 {
 	struct dw_dma *dw = chip->dw;
 
-	clk_prepare_enable(dw->clk);
-	dma_writel(dw, CFG, DW_CFG_DMA_EN);
-
+	dw_dma_on(dw);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dw_dma_resume);
-
-#endif /* CONFIG_PM_SLEEP */
+EXPORT_SYMBOL_GPL(dw_dma_enable);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller core driver");
diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h
index 32667f9e0dda..41439732ff6b 100644
--- a/drivers/dma/dw/internal.h
+++ b/drivers/dma/dw/internal.h
@@ -8,63 +8,16 @@
  * published by the Free Software Foundation.
  */
 
-#ifndef _DW_DMAC_INTERNAL_H
-#define _DW_DMAC_INTERNAL_H
+#ifndef _DMA_DW_INTERNAL_H
+#define _DMA_DW_INTERNAL_H
 
-#include <linux/device.h>
-#include <linux/dw_dmac.h>
+#include <linux/dma/dw.h>
 
 #include "regs.h"
 
-/**
- * struct dw_dma_chip - representation of DesignWare DMA controller hardware
- * @dev:		struct device of the DMA controller
- * @irq:		irq line
- * @regs:		memory mapped I/O space
- * @dw:			struct dw_dma that is filed by dw_dma_probe()
- */
-struct dw_dma_chip {
-	struct device	*dev;
-	int		irq;
-	void __iomem	*regs;
-	struct dw_dma	*dw;
-};
-
-/* Export to the platform drivers */
-int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata);
-int dw_dma_remove(struct dw_dma_chip *chip);
-
-void dw_dma_shutdown(struct dw_dma_chip *chip);
-
-#ifdef CONFIG_PM_SLEEP
-
-int dw_dma_suspend(struct dw_dma_chip *chip);
-int dw_dma_resume(struct dw_dma_chip *chip);
-
-#endif /* CONFIG_PM_SLEEP */
+int dw_dma_disable(struct dw_dma_chip *chip);
+int dw_dma_enable(struct dw_dma_chip *chip);
 
-/**
- * dwc_get_dms - get destination master
- * @slave:	pointer to the custom slave configuration
- *
- * Returns destination master in the custom slave configuration if defined, or
- * default value otherwise.
- */
-static inline unsigned int dwc_get_dms(struct dw_dma_slave *slave)
-{
-	return slave ? slave->dst_master : 0;
-}
-
-/**
- * dwc_get_sms - get source master
- * @slave:	pointer to the custom slave configuration
- *
- * Returns source master in the custom slave configuration if defined, or
- * default value otherwise.
- */
-static inline unsigned int dwc_get_sms(struct dw_dma_slave *slave)
-{
-	return slave ? slave->src_master : 1;
-}
+extern bool dw_dma_filter(struct dma_chan *chan, void *param);
 
-#endif /* _DW_DMAC_INTERNAL_H */
+#endif /* _DMA_DW_INTERNAL_H */
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
index 39e30c3c7a9d..b144706b3d85 100644
--- a/drivers/dma/dw/pci.c
+++ b/drivers/dma/dw/pci.c
@@ -82,7 +82,7 @@ static int dw_pci_suspend_late(struct device *dev)
 	struct pci_dev *pci = to_pci_dev(dev);
 	struct dw_dma_chip *chip = pci_get_drvdata(pci);
 
-	return dw_dma_suspend(chip);
+	return dw_dma_disable(chip);
 };
 
 static int dw_pci_resume_early(struct device *dev)
@@ -90,7 +90,7 @@ static int dw_pci_resume_early(struct device *dev)
 	struct pci_dev *pci = to_pci_dev(dev);
 	struct dw_dma_chip *chip = pci_get_drvdata(pci);
 
-	return dw_dma_resume(chip);
+	return dw_dma_enable(chip);
 };
 
 #endif /* CONFIG_PM_SLEEP */
@@ -108,6 +108,10 @@ static const struct pci_device_id dw_pci_id_table[] = {
 	{ PCI_VDEVICE(INTEL, 0x0f06), (kernel_ulong_t)&dw_pci_pdata },
 	{ PCI_VDEVICE(INTEL, 0x0f40), (kernel_ulong_t)&dw_pci_pdata },
 
+	/* Braswell */
+	{ PCI_VDEVICE(INTEL, 0x2286), (kernel_ulong_t)&dw_pci_pdata },
+	{ PCI_VDEVICE(INTEL, 0x22c0), (kernel_ulong_t)&dw_pci_pdata },
+
 	/* Haswell */
 	{ PCI_VDEVICE(INTEL, 0x9c60), (kernel_ulong_t)&dw_pci_pdata },
 	{ }
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index c5b339af6be5..a630161473a4 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -25,72 +25,49 @@
 
 #include "internal.h"
 
-struct dw_dma_of_filter_args {
-	struct dw_dma *dw;
-	unsigned int req;
-	unsigned int src;
-	unsigned int dst;
-};
-
-static bool dw_dma_of_filter(struct dma_chan *chan, void *param)
-{
-	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
-	struct dw_dma_of_filter_args *fargs = param;
-
-	/* Ensure the device matches our channel */
-	if (chan->device != &fargs->dw->dma)
-		return false;
-
-	dwc->request_line = fargs->req;
-	dwc->src_master	= fargs->src;
-	dwc->dst_master	= fargs->dst;
-
-	return true;
-}
-
 static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
 					struct of_dma *ofdma)
 {
 	struct dw_dma *dw = ofdma->of_dma_data;
-	struct dw_dma_of_filter_args fargs = {
-		.dw = dw,
+	struct dw_dma_slave slave = {
+		.dma_dev = dw->dma.dev,
 	};
 	dma_cap_mask_t cap;
 
 	if (dma_spec->args_count != 3)
 		return NULL;
 
-	fargs.req = dma_spec->args[0];
-	fargs.src = dma_spec->args[1];
-	fargs.dst = dma_spec->args[2];
+	slave.src_id = dma_spec->args[0];
+	slave.dst_id = dma_spec->args[0];
+	slave.src_master = dma_spec->args[1];
+	slave.dst_master = dma_spec->args[2];
 
-	if (WARN_ON(fargs.req >= DW_DMA_MAX_NR_REQUESTS ||
-		    fargs.src >= dw->nr_masters ||
-		    fargs.dst >= dw->nr_masters))
+	if (WARN_ON(slave.src_id >= DW_DMA_MAX_NR_REQUESTS ||
+		    slave.dst_id >= DW_DMA_MAX_NR_REQUESTS ||
+		    slave.src_master >= dw->nr_masters ||
+		    slave.dst_master >= dw->nr_masters))
 		return NULL;
 
 	dma_cap_zero(cap);
 	dma_cap_set(DMA_SLAVE, cap);
 
 	/* TODO: there should be a simpler way to do this */
-	return dma_request_channel(cap, dw_dma_of_filter, &fargs);
+	return dma_request_channel(cap, dw_dma_filter, &slave);
 }
 
 #ifdef CONFIG_ACPI
 static bool dw_dma_acpi_filter(struct dma_chan *chan, void *param)
 {
-	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
 	struct acpi_dma_spec *dma_spec = param;
+	struct dw_dma_slave slave = {
+		.dma_dev = dma_spec->dev,
+		.src_id = dma_spec->slave_id,
+		.dst_id = dma_spec->slave_id,
+		.src_master = 1,
+		.dst_master = 0,
+	};
 
-	if (chan->device->dev != dma_spec->dev ||
-	    chan->chan_id != dma_spec->chan_id)
-		return false;
-
-	dwc->request_line = dma_spec->slave_id;
-	dwc->src_master = dwc_get_sms(NULL);
-	dwc->dst_master = dwc_get_dms(NULL);
-
-	return true;
+	return dw_dma_filter(chan, &slave);
 }
 
 static void dw_dma_acpi_controller_register(struct dw_dma *dw)
@@ -201,10 +178,17 @@ static int dw_probe(struct platform_device *pdev)
 
 	chip->dev = dev;
 
-	err = dw_dma_probe(chip, pdata);
+	chip->clk = devm_clk_get(chip->dev, "hclk");
+	if (IS_ERR(chip->clk))
+		return PTR_ERR(chip->clk);
+	err = clk_prepare_enable(chip->clk);
 	if (err)
 		return err;
 
+	err = dw_dma_probe(chip, pdata);
+	if (err)
+		goto err_dw_dma_probe;
+
 	platform_set_drvdata(pdev, chip);
 
 	if (pdev->dev.of_node) {
@@ -219,6 +203,10 @@ static int dw_probe(struct platform_device *pdev)
 		dw_dma_acpi_controller_register(chip->dw);
 
 	return 0;
+
+err_dw_dma_probe:
+	clk_disable_unprepare(chip->clk);
+	return err;
 }
 
 static int dw_remove(struct platform_device *pdev)
@@ -228,14 +216,18 @@ static int dw_remove(struct platform_device *pdev)
 	if (pdev->dev.of_node)
 		of_dma_controller_free(pdev->dev.of_node);
 
-	return dw_dma_remove(chip);
+	dw_dma_remove(chip);
+	clk_disable_unprepare(chip->clk);
+
+	return 0;
 }
 
 static void dw_shutdown(struct platform_device *pdev)
 {
 	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
 
-	dw_dma_shutdown(chip);
+	dw_dma_disable(chip);
+	clk_disable_unprepare(chip->clk);
 }
 
 #ifdef CONFIG_OF
@@ -261,7 +253,10 @@ static int dw_suspend_late(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
 
-	return dw_dma_suspend(chip);
+	dw_dma_disable(chip);
+	clk_disable_unprepare(chip->clk);
+
+	return 0;
 }
 
 static int dw_resume_early(struct device *dev)
@@ -269,7 +264,8 @@ static int dw_resume_early(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
 
-	return dw_dma_resume(chip);
+	clk_prepare_enable(chip->clk);
+	return dw_dma_enable(chip);
 }
 
 #endif /* CONFIG_PM_SLEEP */
@@ -281,7 +277,7 @@ static const struct dev_pm_ops dw_dev_pm_ops = {
 static struct platform_driver dw_driver = {
 	.probe		= dw_probe,
 	.remove		= dw_remove,
-	.shutdown	= dw_shutdown,
+	.shutdown       = dw_shutdown,
 	.driver = {
 		.name	= "dw_dmac",
 		.pm	= &dw_dev_pm_ops,
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index bb98d3e91e8b..848e232f7cc7 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -11,7 +11,6 @@
 
 #include <linux/interrupt.h>
 #include <linux/dmaengine.h>
-#include <linux/dw_dmac.h>
 
 #define DW_DMA_MAX_NR_CHANNELS	8
 #define DW_DMA_MAX_NR_REQUESTS	16
@@ -132,6 +131,18 @@ struct dw_dma_regs {
 /* Bitfields in DWC_PARAMS */
 #define DWC_PARAMS_MBLK_EN	11		/* multi block transfer */
 
+/* bursts size */
+enum dw_dma_msize {
+	DW_DMA_MSIZE_1,
+	DW_DMA_MSIZE_4,
+	DW_DMA_MSIZE_8,
+	DW_DMA_MSIZE_16,
+	DW_DMA_MSIZE_32,
+	DW_DMA_MSIZE_64,
+	DW_DMA_MSIZE_128,
+	DW_DMA_MSIZE_256,
+};
+
 /* Bitfields in CTL_LO */
 #define DWC_CTLL_INT_EN		(1 << 0)	/* irqs enabled? */
 #define DWC_CTLL_DST_WIDTH(n)	((n)<<1)	/* bytes per element */
@@ -161,20 +172,35 @@ struct dw_dma_regs {
 #define DWC_CTLH_DONE		0x00001000
 #define DWC_CTLH_BLOCK_TS_MASK	0x00000fff
 
-/* Bitfields in CFG_LO. Platform-configurable bits are in <linux/dw_dmac.h> */
+/* Bitfields in CFG_LO */
 #define DWC_CFGL_CH_PRIOR_MASK	(0x7 << 5)	/* priority mask */
 #define DWC_CFGL_CH_PRIOR(x)	((x) << 5)	/* priority */
 #define DWC_CFGL_CH_SUSP	(1 << 8)	/* pause xfer */
 #define DWC_CFGL_FIFO_EMPTY	(1 << 9)	/* pause xfer */
 #define DWC_CFGL_HS_DST		(1 << 10)	/* handshake w/dst */
 #define DWC_CFGL_HS_SRC		(1 << 11)	/* handshake w/src */
+#define DWC_CFGL_LOCK_CH_XFER	(0 << 12)	/* scope of LOCK_CH */
+#define DWC_CFGL_LOCK_CH_BLOCK	(1 << 12)
+#define DWC_CFGL_LOCK_CH_XACT	(2 << 12)
+#define DWC_CFGL_LOCK_BUS_XFER	(0 << 14)	/* scope of LOCK_BUS */
+#define DWC_CFGL_LOCK_BUS_BLOCK	(1 << 14)
+#define DWC_CFGL_LOCK_BUS_XACT	(2 << 14)
+#define DWC_CFGL_LOCK_CH	(1 << 15)	/* channel lockout */
+#define DWC_CFGL_LOCK_BUS	(1 << 16)	/* busmaster lockout */
+#define DWC_CFGL_HS_DST_POL	(1 << 18)	/* dst handshake active low */
+#define DWC_CFGL_HS_SRC_POL	(1 << 19)	/* src handshake active low */
 #define DWC_CFGL_MAX_BURST(x)	((x) << 20)
 #define DWC_CFGL_RELOAD_SAR	(1 << 30)
 #define DWC_CFGL_RELOAD_DAR	(1 << 31)
 
-/* Bitfields in CFG_HI. Platform-configurable bits are in <linux/dw_dmac.h> */
+/* Bitfields in CFG_HI */
+#define DWC_CFGH_FCMODE		(1 << 0)
+#define DWC_CFGH_FIFO_MODE	(1 << 1)
+#define DWC_CFGH_PROTCTL(x)	((x) << 2)
 #define DWC_CFGH_DS_UPD_EN	(1 << 5)
 #define DWC_CFGH_SS_UPD_EN	(1 << 6)
+#define DWC_CFGH_SRC_PER(x)	((x) << 7)
+#define DWC_CFGH_DST_PER(x)	((x) << 11)
 
 /* Bitfields in SGR */
 #define DWC_SGR_SGI(x)		((x) << 0)
@@ -221,9 +247,10 @@ struct dw_dma_chan {
 	bool			nollp;
 
 	/* custom slave configuration */
-	unsigned int		request_line;
-	unsigned char		src_master;
-	unsigned char		dst_master;
+	u8			src_id;
+	u8			dst_id;
+	u8			src_master;
+	u8			dst_master;
 
 	/* configuration passed via DMA_SLAVE_CONFIG */
 	struct dma_slave_config dma_sconfig;
@@ -250,11 +277,11 @@ struct dw_dma {
 	void __iomem		*regs;
 	struct dma_pool		*desc_pool;
 	struct tasklet_struct	tasklet;
-	struct clk		*clk;
 
 	/* channels */
 	struct dw_dma_chan	*chan;
 	u8			all_chan_mask;
+	u8			in_use;
 
 	/* hardware configuration */
 	unsigned char		nr_masters;
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 7b65633f495e..123f578d6dd3 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -288,7 +288,7 @@ static int edma_slave_config(struct edma_chan *echan,
 static int edma_dma_pause(struct edma_chan *echan)
 {
 	/* Pause/Resume only allowed with cyclic mode */
-	if (!echan->edesc->cyclic)
+	if (!echan->edesc || !echan->edesc->cyclic)
 		return -EINVAL;
 
 	edma_pause(echan->ch_num);
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index d5d6885ab341..994bcb2c6b92 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -36,7 +36,7 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
-
+#include <linux/fsldma.h>
 #include "dmaengine.h"
 #include "fsldma.h"
 
@@ -367,6 +367,20 @@ static void fsl_chan_toggle_ext_start(struct fsldma_chan *chan, int enable)
 		chan->feature &= ~FSL_DMA_CHAN_START_EXT;
 }
 
+int fsl_dma_external_start(struct dma_chan *dchan, int enable)
+{
+	struct fsldma_chan *chan;
+
+	if (!dchan)
+		return -EINVAL;
+
+	chan = to_fsl_chan(dchan);
+
+	fsl_chan_toggle_ext_start(chan, enable);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fsl_dma_external_start);
+
 static void append_ld_queue(struct fsldma_chan *chan, struct fsl_desc_sw *desc)
 {
 	struct fsl_desc_sw *tail = to_fsl_desc(chan->ld_pending.prev);
@@ -998,15 +1012,6 @@ static int fsl_dma_device_control(struct dma_chan *dchan,
 		chan->set_request_count(chan, size);
 		return 0;
 
-	case FSLDMA_EXTERNAL_START:
-
-		/* make sure the channel supports external start */
-		if (!chan->toggle_ext_start)
-			return -ENXIO;
-
-		chan->toggle_ext_start(chan, arg);
-		return 0;
-
 	default:
 		return -ENXIO;
 	}
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index f7626e37d0b8..88afc48c2ca7 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1334,7 +1334,7 @@ err_firmware:
 	release_firmware(fw);
 }
 
-static int __init sdma_get_firmware(struct sdma_engine *sdma,
+static int sdma_get_firmware(struct sdma_engine *sdma,
 		const char *fw_name)
 {
 	int ret;
@@ -1448,7 +1448,7 @@ static struct dma_chan *sdma_xlate(struct of_phandle_args *dma_spec,
 	return dma_request_channel(mask, sdma_filter_fn, &data);
 }
 
-static int __init sdma_probe(struct platform_device *pdev)
+static int sdma_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id =
 			of_match_device(sdma_dt_ids, &pdev->dev);
@@ -1603,6 +1603,8 @@ static int __init sdma_probe(struct platform_device *pdev)
 	sdma->dma_device.dev->dma_parms = &sdma->dma_parms;
 	dma_set_max_seg_size(sdma->dma_device.dev, 65535);
 
+	platform_set_drvdata(pdev, sdma);
+
 	ret = dma_async_device_register(&sdma->dma_device);
 	if (ret) {
 		dev_err(&pdev->dev, "unable to register\n");
@@ -1640,7 +1642,27 @@ err_irq:
 
 static int sdma_remove(struct platform_device *pdev)
 {
-	return -EBUSY;
+	struct sdma_engine *sdma = platform_get_drvdata(pdev);
+	struct resource *iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	int irq = platform_get_irq(pdev, 0);
+	int i;
+
+	dma_async_device_unregister(&sdma->dma_device);
+	kfree(sdma->script_addrs);
+	free_irq(irq, sdma);
+	iounmap(sdma->regs);
+	release_mem_region(iores->start, resource_size(iores));
+	/* Kill the tasklet */
+	for (i = 0; i < MAX_DMA_CHANNELS; i++) {
+		struct sdma_channel *sdmac = &sdma->channel[i];
+
+		tasklet_kill(&sdmac->tasklet);
+	}
+	kfree(sdma);
+
+	platform_set_drvdata(pdev, NULL);
+	dev_info(&pdev->dev, "Removed...\n");
+	return 0;
 }
 
 static struct platform_driver sdma_driver = {
@@ -1650,13 +1672,10 @@ static struct platform_driver sdma_driver = {
 	},
 	.id_table	= sdma_devtypes,
 	.remove		= sdma_remove,
+	.probe		= sdma_probe,
 };
 
-static int __init sdma_module_init(void)
-{
-	return platform_driver_probe(&sdma_driver, sdma_probe);
-}
-module_init(sdma_module_init);
+module_platform_driver(sdma_driver);
 
 MODULE_AUTHOR("Sascha Hauer, Pengutronix <s.hauer@pengutronix.de>");
 MODULE_DESCRIPTION("i.MX SDMA driver");
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index 6ad30e2c5038..c6bd015b7165 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -148,10 +148,16 @@ static void mmp_tdma_chan_set_desc(struct mmp_tdma_chan *tdmac, dma_addr_t phys)
 					tdmac->reg_base + TDCR);
 }
 
+static void mmp_tdma_enable_irq(struct mmp_tdma_chan *tdmac, bool enable)
+{
+	if (enable)
+		writel(TDIMR_COMP, tdmac->reg_base + TDIMR);
+	else
+		writel(0, tdmac->reg_base + TDIMR);
+}
+
 static void mmp_tdma_enable_chan(struct mmp_tdma_chan *tdmac)
 {
-	/* enable irq */
-	writel(TDIMR_COMP, tdmac->reg_base + TDIMR);
 	/* enable dma chan */
 	writel(readl(tdmac->reg_base + TDCR) | TDCR_CHANEN,
 					tdmac->reg_base + TDCR);
@@ -163,9 +169,6 @@ static void mmp_tdma_disable_chan(struct mmp_tdma_chan *tdmac)
 	writel(readl(tdmac->reg_base + TDCR) & ~TDCR_CHANEN,
 					tdmac->reg_base + TDCR);
 
-	/* disable irq */
-	writel(0, tdmac->reg_base + TDIMR);
-
 	tdmac->status = DMA_COMPLETE;
 }
 
@@ -434,6 +437,10 @@ static struct dma_async_tx_descriptor *mmp_tdma_prep_dma_cyclic(
 		i++;
 	}
 
+	/* enable interrupt */
+	if (flags & DMA_PREP_INTERRUPT)
+		mmp_tdma_enable_irq(tdmac, true);
+
 	tdmac->buf_len = buf_len;
 	tdmac->period_len = period_len;
 	tdmac->pos = 0;
@@ -455,6 +462,8 @@ static int mmp_tdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
 	switch (cmd) {
 	case DMA_TERMINATE_ALL:
 		mmp_tdma_disable_chan(tdmac);
+		/* disable interrupt */
+		mmp_tdma_enable_irq(tdmac, false);
 		break;
 	case DMA_PAUSE:
 		mmp_tdma_pause_chan(tdmac);
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 7938272f2edf..a63837ca1410 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -45,19 +45,18 @@ static void mv_xor_issue_pending(struct dma_chan *chan);
 #define mv_chan_to_devp(chan)           \
 	((chan)->dmadev.dev)
 
-static void mv_desc_init(struct mv_xor_desc_slot *desc, unsigned long flags)
+static void mv_desc_init(struct mv_xor_desc_slot *desc,
+			 dma_addr_t addr, u32 byte_count,
+			 enum dma_ctrl_flags flags)
 {
 	struct mv_xor_desc *hw_desc = desc->hw_desc;
 
-	hw_desc->status = (1 << 31);
+	hw_desc->status = XOR_DESC_DMA_OWNED;
 	hw_desc->phy_next_desc = 0;
-	hw_desc->desc_command = (1 << 31);
-}
-
-static void mv_desc_set_byte_count(struct mv_xor_desc_slot *desc,
-				   u32 byte_count)
-{
-	struct mv_xor_desc *hw_desc = desc->hw_desc;
+	/* Enable end-of-descriptor interrupts only for DMA_PREP_INTERRUPT */
+	hw_desc->desc_command = (flags & DMA_PREP_INTERRUPT) ?
+				XOR_DESC_EOD_INT_EN : 0;
+	hw_desc->phy_dest_addr = addr;
 	hw_desc->byte_count = byte_count;
 }
 
@@ -75,20 +74,6 @@ static void mv_desc_clear_next_desc(struct mv_xor_desc_slot *desc)
 	hw_desc->phy_next_desc = 0;
 }
 
-static void mv_desc_set_dest_addr(struct mv_xor_desc_slot *desc,
-				  dma_addr_t addr)
-{
-	struct mv_xor_desc *hw_desc = desc->hw_desc;
-	hw_desc->phy_dest_addr = addr;
-}
-
-static int mv_chan_memset_slot_count(size_t len)
-{
-	return 1;
-}
-
-#define mv_chan_memcpy_slot_count(c) mv_chan_memset_slot_count(c)
-
 static void mv_desc_set_src_addr(struct mv_xor_desc_slot *desc,
 				 int index, dma_addr_t addr)
 {
@@ -123,17 +108,12 @@ static u32 mv_chan_get_intr_cause(struct mv_xor_chan *chan)
 	return intr_cause;
 }
 
-static int mv_is_err_intr(u32 intr_cause)
-{
-	if (intr_cause & ((1<<4)|(1<<5)|(1<<6)|(1<<7)|(1<<8)|(1<<9)))
-		return 1;
-
-	return 0;
-}
-
 static void mv_xor_device_clear_eoc_cause(struct mv_xor_chan *chan)
 {
-	u32 val = ~(1 << (chan->idx * 16));
+	u32 val;
+
+	val = XOR_INT_END_OF_DESC | XOR_INT_END_OF_CHAIN | XOR_INT_STOPPED;
+	val = ~(val << (chan->idx * 16));
 	dev_dbg(mv_chan_to_devp(chan), "%s, val 0x%08x\n", __func__, val);
 	writel_relaxed(val, XOR_INTR_CAUSE(chan));
 }
@@ -144,17 +124,6 @@ static void mv_xor_device_clear_err_status(struct mv_xor_chan *chan)
 	writel_relaxed(val, XOR_INTR_CAUSE(chan));
 }
 
-static int mv_can_chain(struct mv_xor_desc_slot *desc)
-{
-	struct mv_xor_desc_slot *chain_old_tail = list_entry(
-		desc->chain_node.prev, struct mv_xor_desc_slot, chain_node);
-
-	if (chain_old_tail->type != desc->type)
-		return 0;
-
-	return 1;
-}
-
 static void mv_set_mode(struct mv_xor_chan *chan,
 			       enum dma_transaction_type type)
 {
@@ -206,11 +175,6 @@ static char mv_chan_is_busy(struct mv_xor_chan *chan)
 	return (state == 1) ? 1 : 0;
 }
 
-static int mv_chan_xor_slot_count(size_t len, int src_cnt)
-{
-	return 1;
-}
-
 /**
  * mv_xor_free_slots - flags descriptor slots for reuse
  * @slot: Slot to free
@@ -222,7 +186,7 @@ static void mv_xor_free_slots(struct mv_xor_chan *mv_chan,
 	dev_dbg(mv_chan_to_devp(mv_chan), "%s %d slot %p\n",
 		__func__, __LINE__, slot);
 
-	slot->slots_per_op = 0;
+	slot->slot_used = 0;
 
 }
 
@@ -236,13 +200,11 @@ static void mv_xor_start_new_chain(struct mv_xor_chan *mv_chan,
 {
 	dev_dbg(mv_chan_to_devp(mv_chan), "%s %d: sw_desc %p\n",
 		__func__, __LINE__, sw_desc);
-	if (sw_desc->type != mv_chan->current_type)
-		mv_set_mode(mv_chan, sw_desc->type);
 
 	/* set the hardware chain */
 	mv_chan_set_next_descriptor(mv_chan, sw_desc->async_tx.phys);
 
-	mv_chan->pending += sw_desc->slot_cnt;
+	mv_chan->pending++;
 	mv_xor_issue_pending(&mv_chan->dmachan);
 }
 
@@ -263,8 +225,6 @@ mv_xor_run_tx_complete_actions(struct mv_xor_desc_slot *desc,
 				desc->async_tx.callback_param);
 
 		dma_descriptor_unmap(&desc->async_tx);
-		if (desc->group_head)
-			desc->group_head = NULL;
 	}
 
 	/* run dependent operations */
@@ -377,19 +337,16 @@ static void mv_xor_tasklet(unsigned long data)
 }
 
 static struct mv_xor_desc_slot *
-mv_xor_alloc_slots(struct mv_xor_chan *mv_chan, int num_slots,
-		    int slots_per_op)
+mv_xor_alloc_slot(struct mv_xor_chan *mv_chan)
 {
-	struct mv_xor_desc_slot *iter, *_iter, *alloc_start = NULL;
-	LIST_HEAD(chain);
-	int slots_found, retry = 0;
+	struct mv_xor_desc_slot *iter, *_iter;
+	int retry = 0;
 
 	/* start search from the last allocated descrtiptor
 	 * if a contiguous allocation can not be found start searching
 	 * from the beginning of the list
 	 */
 retry:
-	slots_found = 0;
 	if (retry == 0)
 		iter = mv_chan->last_used;
 	else
@@ -399,55 +356,29 @@ retry:
 
 	list_for_each_entry_safe_continue(
 		iter, _iter, &mv_chan->all_slots, slot_node) {
+
 		prefetch(_iter);
 		prefetch(&_iter->async_tx);
-		if (iter->slots_per_op) {
+		if (iter->slot_used) {
 			/* give up after finding the first busy slot
 			 * on the second pass through the list
 			 */
 			if (retry)
 				break;
-
-			slots_found = 0;
 			continue;
 		}
 
-		/* start the allocation if the slot is correctly aligned */
-		if (!slots_found++)
-			alloc_start = iter;
-
-		if (slots_found == num_slots) {
-			struct mv_xor_desc_slot *alloc_tail = NULL;
-			struct mv_xor_desc_slot *last_used = NULL;
-			iter = alloc_start;
-			while (num_slots) {
-				int i;
-
-				/* pre-ack all but the last descriptor */
-				async_tx_ack(&iter->async_tx);
-
-				list_add_tail(&iter->chain_node, &chain);
-				alloc_tail = iter;
-				iter->async_tx.cookie = 0;
-				iter->slot_cnt = num_slots;
-				iter->xor_check_result = NULL;
-				for (i = 0; i < slots_per_op; i++) {
-					iter->slots_per_op = slots_per_op - i;
-					last_used = iter;
-					iter = list_entry(iter->slot_node.next,
-						struct mv_xor_desc_slot,
-						slot_node);
-				}
-				num_slots -= slots_per_op;
-			}
-			alloc_tail->group_head = alloc_start;
-			alloc_tail->async_tx.cookie = -EBUSY;
-			list_splice(&chain, &alloc_tail->tx_list);
-			mv_chan->last_used = last_used;
-			mv_desc_clear_next_desc(alloc_start);
-			mv_desc_clear_next_desc(alloc_tail);
-			return alloc_tail;
-		}
+		/* pre-ack descriptor */
+		async_tx_ack(&iter->async_tx);
+
+		iter->slot_used = 1;
+		INIT_LIST_HEAD(&iter->chain_node);
+		iter->async_tx.cookie = -EBUSY;
+		mv_chan->last_used = iter;
+		mv_desc_clear_next_desc(iter);
+
+		return iter;
+
 	}
 	if (!retry++)
 		goto retry;
@@ -464,7 +395,7 @@ mv_xor_tx_submit(struct dma_async_tx_descriptor *tx)
 {
 	struct mv_xor_desc_slot *sw_desc = to_mv_xor_slot(tx);
 	struct mv_xor_chan *mv_chan = to_mv_xor_chan(tx->chan);
-	struct mv_xor_desc_slot *grp_start, *old_chain_tail;
+	struct mv_xor_desc_slot *old_chain_tail;
 	dma_cookie_t cookie;
 	int new_hw_chain = 1;
 
@@ -472,30 +403,24 @@ mv_xor_tx_submit(struct dma_async_tx_descriptor *tx)
 		"%s sw_desc %p: async_tx %p\n",
 		__func__, sw_desc, &sw_desc->async_tx);
 
-	grp_start = sw_desc->group_head;
-
 	spin_lock_bh(&mv_chan->lock);
 	cookie = dma_cookie_assign(tx);
 
 	if (list_empty(&mv_chan->chain))
-		list_splice_init(&sw_desc->tx_list, &mv_chan->chain);
+		list_add_tail(&sw_desc->chain_node, &mv_chan->chain);
 	else {
 		new_hw_chain = 0;
 
 		old_chain_tail = list_entry(mv_chan->chain.prev,
 					    struct mv_xor_desc_slot,
 					    chain_node);
-		list_splice_init(&grp_start->tx_list,
-				 &old_chain_tail->chain_node);
-
-		if (!mv_can_chain(grp_start))
-			goto submit_done;
+		list_add_tail(&sw_desc->chain_node, &mv_chan->chain);
 
 		dev_dbg(mv_chan_to_devp(mv_chan), "Append to last desc %pa\n",
 			&old_chain_tail->async_tx.phys);
 
 		/* fix up the hardware chain */
-		mv_desc_set_next_desc(old_chain_tail, grp_start->async_tx.phys);
+		mv_desc_set_next_desc(old_chain_tail, sw_desc->async_tx.phys);
 
 		/* if the channel is not busy */
 		if (!mv_chan_is_busy(mv_chan)) {
@@ -510,9 +435,8 @@ mv_xor_tx_submit(struct dma_async_tx_descriptor *tx)
 	}
 
 	if (new_hw_chain)
-		mv_xor_start_new_chain(mv_chan, grp_start);
+		mv_xor_start_new_chain(mv_chan, sw_desc);
 
-submit_done:
 	spin_unlock_bh(&mv_chan->lock);
 
 	return cookie;
@@ -533,8 +457,9 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 	while (idx < num_descs_in_pool) {
 		slot = kzalloc(sizeof(*slot), GFP_KERNEL);
 		if (!slot) {
-			printk(KERN_INFO "MV XOR Channel only initialized"
-				" %d descriptor slots", idx);
+			dev_info(mv_chan_to_devp(mv_chan),
+				 "channel only initialized %d descriptor slots",
+				 idx);
 			break;
 		}
 		virt_desc = mv_chan->dma_desc_pool_virt;
@@ -544,7 +469,6 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 		slot->async_tx.tx_submit = mv_xor_tx_submit;
 		INIT_LIST_HEAD(&slot->chain_node);
 		INIT_LIST_HEAD(&slot->slot_node);
-		INIT_LIST_HEAD(&slot->tx_list);
 		dma_desc = mv_chan->dma_desc_pool;
 		slot->async_tx.phys = dma_desc + idx * MV_XOR_SLOT_SIZE;
 		slot->idx = idx++;
@@ -568,51 +492,11 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 }
 
 static struct dma_async_tx_descriptor *
-mv_xor_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
-		size_t len, unsigned long flags)
-{
-	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
-	struct mv_xor_desc_slot *sw_desc, *grp_start;
-	int slot_cnt;
-
-	dev_dbg(mv_chan_to_devp(mv_chan),
-		"%s dest: %pad src %pad len: %u flags: %ld\n",
-		__func__, &dest, &src, len, flags);
-	if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
-		return NULL;
-
-	BUG_ON(len > MV_XOR_MAX_BYTE_COUNT);
-
-	spin_lock_bh(&mv_chan->lock);
-	slot_cnt = mv_chan_memcpy_slot_count(len);
-	sw_desc = mv_xor_alloc_slots(mv_chan, slot_cnt, 1);
-	if (sw_desc) {
-		sw_desc->type = DMA_MEMCPY;
-		sw_desc->async_tx.flags = flags;
-		grp_start = sw_desc->group_head;
-		mv_desc_init(grp_start, flags);
-		mv_desc_set_byte_count(grp_start, len);
-		mv_desc_set_dest_addr(sw_desc->group_head, dest);
-		mv_desc_set_src_addr(grp_start, 0, src);
-		sw_desc->unmap_src_cnt = 1;
-		sw_desc->unmap_len = len;
-	}
-	spin_unlock_bh(&mv_chan->lock);
-
-	dev_dbg(mv_chan_to_devp(mv_chan),
-		"%s sw_desc %p async_tx %p\n",
-		__func__, sw_desc, sw_desc ? &sw_desc->async_tx : NULL);
-
-	return sw_desc ? &sw_desc->async_tx : NULL;
-}
-
-static struct dma_async_tx_descriptor *
 mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 		    unsigned int src_cnt, size_t len, unsigned long flags)
 {
 	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
-	struct mv_xor_desc_slot *sw_desc, *grp_start;
-	int slot_cnt;
+	struct mv_xor_desc_slot *sw_desc;
 
 	if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
 		return NULL;
@@ -624,20 +508,13 @@ mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 		__func__, src_cnt, len, &dest, flags);
 
 	spin_lock_bh(&mv_chan->lock);
-	slot_cnt = mv_chan_xor_slot_count(len, src_cnt);
-	sw_desc = mv_xor_alloc_slots(mv_chan, slot_cnt, 1);
+	sw_desc = mv_xor_alloc_slot(mv_chan);
 	if (sw_desc) {
 		sw_desc->type = DMA_XOR;
 		sw_desc->async_tx.flags = flags;
-		grp_start = sw_desc->group_head;
-		mv_desc_init(grp_start, flags);
-		/* the byte count field is the same as in memcpy desc*/
-		mv_desc_set_byte_count(grp_start, len);
-		mv_desc_set_dest_addr(sw_desc->group_head, dest);
-		sw_desc->unmap_src_cnt = src_cnt;
-		sw_desc->unmap_len = len;
+		mv_desc_init(sw_desc, dest, len, flags);
 		while (src_cnt--)
-			mv_desc_set_src_addr(grp_start, src_cnt, src[src_cnt]);
+			mv_desc_set_src_addr(sw_desc, src_cnt, src[src_cnt]);
 	}
 	spin_unlock_bh(&mv_chan->lock);
 	dev_dbg(mv_chan_to_devp(mv_chan),
@@ -646,6 +523,35 @@ mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 	return sw_desc ? &sw_desc->async_tx : NULL;
 }
 
+static struct dma_async_tx_descriptor *
+mv_xor_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
+		size_t len, unsigned long flags)
+{
+	/*
+	 * A MEMCPY operation is identical to an XOR operation with only
+	 * a single source address.
+	 */
+	return mv_xor_prep_dma_xor(chan, dest, &src, 1, len, flags);
+}
+
+static struct dma_async_tx_descriptor *
+mv_xor_prep_dma_interrupt(struct dma_chan *chan, unsigned long flags)
+{
+	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
+	dma_addr_t src, dest;
+	size_t len;
+
+	src = mv_chan->dummy_src_addr;
+	dest = mv_chan->dummy_dst_addr;
+	len = MV_XOR_MIN_BYTE_COUNT;
+
+	/*
+	 * We implement the DMA_INTERRUPT operation as a minimum sized
+	 * XOR operation with a single dummy source address.
+	 */
+	return mv_xor_prep_dma_xor(chan, dest, &src, 1, len, flags);
+}
+
 static void mv_xor_free_chan_resources(struct dma_chan *chan)
 {
 	struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan);
@@ -733,18 +639,16 @@ static void mv_dump_xor_regs(struct mv_xor_chan *chan)
 static void mv_xor_err_interrupt_handler(struct mv_xor_chan *chan,
 					 u32 intr_cause)
 {
-	if (intr_cause & (1 << 4)) {
-	     dev_dbg(mv_chan_to_devp(chan),
-		     "ignore this error\n");
-	     return;
+	if (intr_cause & XOR_INT_ERR_DECODE) {
+		dev_dbg(mv_chan_to_devp(chan), "ignoring address decode error\n");
+		return;
 	}
 
-	dev_err(mv_chan_to_devp(chan),
-		"error on chan %d. intr cause 0x%08x\n",
+	dev_err(mv_chan_to_devp(chan), "error on chan %d. intr cause 0x%08x\n",
 		chan->idx, intr_cause);
 
 	mv_dump_xor_regs(chan);
-	BUG();
+	WARN_ON(1);
 }
 
 static irqreturn_t mv_xor_interrupt_handler(int irq, void *data)
@@ -754,7 +658,7 @@ static irqreturn_t mv_xor_interrupt_handler(int irq, void *data)
 
 	dev_dbg(mv_chan_to_devp(chan), "intr cause %x\n", intr_cause);
 
-	if (mv_is_err_intr(intr_cause))
+	if (intr_cause & XOR_INTR_ERRORS)
 		mv_xor_err_interrupt_handler(chan, intr_cause);
 
 	tasklet_schedule(&chan->irq_tasklet);
@@ -1041,6 +945,10 @@ static int mv_xor_channel_remove(struct mv_xor_chan *mv_chan)
 
 	dma_free_coherent(dev, MV_XOR_POOL_SIZE,
 			  mv_chan->dma_desc_pool_virt, mv_chan->dma_desc_pool);
+	dma_unmap_single(dev, mv_chan->dummy_src_addr,
+			 MV_XOR_MIN_BYTE_COUNT, DMA_FROM_DEVICE);
+	dma_unmap_single(dev, mv_chan->dummy_dst_addr,
+			 MV_XOR_MIN_BYTE_COUNT, DMA_TO_DEVICE);
 
 	list_for_each_entry_safe(chan, _chan, &mv_chan->dmadev.channels,
 				 device_node) {
@@ -1070,6 +978,16 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 
 	dma_dev = &mv_chan->dmadev;
 
+	/*
+	 * These source and destination dummy buffers are used to implement
+	 * a DMA_INTERRUPT operation as a minimum-sized XOR operation.
+	 * Hence, we only need to map the buffers at initialization-time.
+	 */
+	mv_chan->dummy_src_addr = dma_map_single(dma_dev->dev,
+		mv_chan->dummy_src, MV_XOR_MIN_BYTE_COUNT, DMA_FROM_DEVICE);
+	mv_chan->dummy_dst_addr = dma_map_single(dma_dev->dev,
+		mv_chan->dummy_dst, MV_XOR_MIN_BYTE_COUNT, DMA_TO_DEVICE);
+
 	/* allocate coherent memory for hardware descriptors
 	 * note: writecombine gives slightly better performance, but
 	 * requires that we explicitly flush the writes
@@ -1094,6 +1012,8 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	dma_dev->dev = &pdev->dev;
 
 	/* set prep routines based on capability */
+	if (dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask))
+		dma_dev->device_prep_dma_interrupt = mv_xor_prep_dma_interrupt;
 	if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask))
 		dma_dev->device_prep_dma_memcpy = mv_xor_prep_dma_memcpy;
 	if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) {
@@ -1116,7 +1036,7 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 
 	mv_chan_unmask_interrupts(mv_chan);
 
-	mv_set_mode(mv_chan, DMA_MEMCPY);
+	mv_set_mode(mv_chan, DMA_XOR);
 
 	spin_lock_init(&mv_chan->lock);
 	INIT_LIST_HEAD(&mv_chan->chain);
diff --git a/drivers/dma/mv_xor.h b/drivers/dma/mv_xor.h
index d0749229c875..78edc7e44569 100644
--- a/drivers/dma/mv_xor.h
+++ b/drivers/dma/mv_xor.h
@@ -23,17 +23,22 @@
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
 
-#define USE_TIMER
 #define MV_XOR_POOL_SIZE		PAGE_SIZE
 #define MV_XOR_SLOT_SIZE		64
 #define MV_XOR_THRESHOLD		1
 #define MV_XOR_MAX_CHANNELS             2
 
+#define MV_XOR_MIN_BYTE_COUNT		SZ_128
+#define MV_XOR_MAX_BYTE_COUNT		(SZ_16M - 1)
+
 /* Values for the XOR_CONFIG register */
 #define XOR_OPERATION_MODE_XOR		0
 #define XOR_OPERATION_MODE_MEMCPY	2
 #define XOR_DESCRIPTOR_SWAP		BIT(14)
 
+#define XOR_DESC_DMA_OWNED		BIT(31)
+#define XOR_DESC_EOD_INT_EN		BIT(31)
+
 #define XOR_CURR_DESC(chan)	(chan->mmr_high_base + 0x10 + (chan->idx * 4))
 #define XOR_NEXT_DESC(chan)	(chan->mmr_high_base + 0x00 + (chan->idx * 4))
 #define XOR_BYTE_COUNT(chan)	(chan->mmr_high_base + 0x20 + (chan->idx * 4))
@@ -48,7 +53,24 @@
 #define XOR_INTR_MASK(chan)	(chan->mmr_base + 0x40)
 #define XOR_ERROR_CAUSE(chan)	(chan->mmr_base + 0x50)
 #define XOR_ERROR_ADDR(chan)	(chan->mmr_base + 0x60)
-#define XOR_INTR_MASK_VALUE	0x3F5
+
+#define XOR_INT_END_OF_DESC	BIT(0)
+#define XOR_INT_END_OF_CHAIN	BIT(1)
+#define XOR_INT_STOPPED		BIT(2)
+#define XOR_INT_PAUSED		BIT(3)
+#define XOR_INT_ERR_DECODE	BIT(4)
+#define XOR_INT_ERR_RDPROT	BIT(5)
+#define XOR_INT_ERR_WRPROT	BIT(6)
+#define XOR_INT_ERR_OWN		BIT(7)
+#define XOR_INT_ERR_PAR		BIT(8)
+#define XOR_INT_ERR_MBUS	BIT(9)
+
+#define XOR_INTR_ERRORS		(XOR_INT_ERR_DECODE | XOR_INT_ERR_RDPROT | \
+				 XOR_INT_ERR_WRPROT | XOR_INT_ERR_OWN    | \
+				 XOR_INT_ERR_PAR    | XOR_INT_ERR_MBUS)
+
+#define XOR_INTR_MASK_VALUE	(XOR_INT_END_OF_DESC | XOR_INT_END_OF_CHAIN | \
+				 XOR_INT_STOPPED     | XOR_INTR_ERRORS)
 
 #define WINDOW_BASE(w)		(0x50 + ((w) << 2))
 #define WINDOW_SIZE(w)		(0x70 + ((w) << 2))
@@ -97,10 +119,9 @@ struct mv_xor_chan {
 	struct list_head	all_slots;
 	int			slots_allocated;
 	struct tasklet_struct	irq_tasklet;
-#ifdef USE_TIMER
-	unsigned long		cleanup_time;
-	u32			current_on_last_cleanup;
-#endif
+	char			dummy_src[MV_XOR_MIN_BYTE_COUNT];
+	char			dummy_dst[MV_XOR_MIN_BYTE_COUNT];
+	dma_addr_t		dummy_src_addr, dummy_dst_addr;
 };
 
 /**
@@ -110,16 +131,10 @@ struct mv_xor_chan {
  * @completed_node: node on the mv_xor_chan.completed_slots list
  * @hw_desc: virtual address of the hardware descriptor chain
  * @phys: hardware address of the hardware descriptor chain
- * @group_head: first operation in a transaction
- * @slot_cnt: total slots used in an transaction (group of operations)
- * @slots_per_op: number of slots per operation
+ * @slot_used: slot in use or not
  * @idx: pool index
- * @unmap_src_cnt: number of xor sources
- * @unmap_len: transaction bytecount
  * @tx_list: list of slots that make up a multi-descriptor transaction
  * @async_tx: support for the async_tx api
- * @xor_check_result: result of zero sum
- * @crc32_result: result crc calculation
  */
 struct mv_xor_desc_slot {
 	struct list_head	slot_node;
@@ -127,23 +142,9 @@ struct mv_xor_desc_slot {
 	struct list_head	completed_node;
 	enum dma_transaction_type	type;
 	void			*hw_desc;
-	struct mv_xor_desc_slot	*group_head;
-	u16			slot_cnt;
-	u16			slots_per_op;
+	u16			slot_used;
 	u16			idx;
-	u16			unmap_src_cnt;
-	u32			value;
-	size_t			unmap_len;
-	struct list_head	tx_list;
 	struct dma_async_tx_descriptor	async_tx;
-	union {
-		u32		*xor_check_result;
-		u32		*crc32_result;
-	};
-#ifdef USE_TIMER
-	unsigned long		arrival_time;
-	struct timer_list	timeout;
-#endif
 };
 
 /*
@@ -189,9 +190,4 @@ struct mv_xor_desc {
 #define mv_hw_desc_slot_idx(hw_desc, idx)	\
 	((void *)(((unsigned long)hw_desc) + ((idx) << 5)))
 
-#define MV_XOR_MIN_BYTE_COUNT	(128)
-#define XOR_MAX_BYTE_COUNT	((16 * 1024 * 1024) - 1)
-#define MV_XOR_MAX_BYTE_COUNT	XOR_MAX_BYTE_COUNT
-
-
 #endif
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index d5149aacd2fe..4839bfa74a10 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1367,17 +1367,10 @@ static int pl330_submit_req(struct pl330_thread *thrd,
 	struct pl330_dmac *pl330 = thrd->dmac;
 	struct _xfer_spec xs;
 	unsigned long flags;
-	void __iomem *regs;
 	unsigned idx;
 	u32 ccr;
 	int ret = 0;
 
-	/* No Req or Unacquired Channel or DMAC */
-	if (!desc || !thrd || thrd->free)
-		return -EINVAL;
-
-	regs = thrd->dmac->base;
-
 	if (pl330->state == DYING
 		|| pl330->dmac_tbd.reset_chan & (1 << thrd->id)) {
 		dev_info(thrd->dmac->ddma.dev, "%s:%d\n",
@@ -2755,8 +2748,10 @@ probe_err3:
 		list_del(&pch->chan.device_node);
 
 		/* Flush the channel */
-		pl330_control(&pch->chan, DMA_TERMINATE_ALL, 0);
-		pl330_free_chan_resources(&pch->chan);
+		if (pch->thread) {
+			pl330_control(&pch->chan, DMA_TERMINATE_ALL, 0);
+			pl330_free_chan_resources(&pch->chan);
+		}
 	}
 probe_err2:
 	pl330_del(pl330);
@@ -2782,8 +2777,10 @@ static int pl330_remove(struct amba_device *adev)
 		list_del(&pch->chan.device_node);
 
 		/* Flush the channel */
-		pl330_control(&pch->chan, DMA_TERMINATE_ALL, 0);
-		pl330_free_chan_resources(&pch->chan);
+		if (pch->thread) {
+			pl330_control(&pch->chan, DMA_TERMINATE_ALL, 0);
+			pl330_free_chan_resources(&pch->chan);
+		}
 	}
 
 	pl330_del(pl330);
diff --git a/drivers/dma/sh/rcar-audmapp.c b/drivers/dma/sh/rcar-audmapp.c
index dabbf0aba2e9..80fd2aeb4870 100644
--- a/drivers/dma/sh/rcar-audmapp.c
+++ b/drivers/dma/sh/rcar-audmapp.c
@@ -117,7 +117,7 @@ static void audmapp_start_xfer(struct shdma_chan *schan,
 	audmapp_write(auchan, chcr,	PDMACHCR);
 }
 
-static void audmapp_get_config(struct audmapp_chan *auchan, int slave_id,
+static int audmapp_get_config(struct audmapp_chan *auchan, int slave_id,
 			      u32 *chcr, dma_addr_t *dst)
 {
 	struct audmapp_device *audev = to_dev(auchan);
@@ -131,20 +131,22 @@ static void audmapp_get_config(struct audmapp_chan *auchan, int slave_id,
 	if (!pdata) { /* DT */
 		*chcr = ((u32)slave_id) << 16;
 		auchan->shdma_chan.slave_id = (slave_id) >> 8;
-		return;
+		return 0;
 	}
 
 	/* non-DT */
 
 	if (slave_id >= AUDMAPP_SLAVE_NUMBER)
-		return;
+		return -ENXIO;
 
 	for (i = 0, cfg = pdata->slave; i < pdata->slave_num; i++, cfg++)
 		if (cfg->slave_id == slave_id) {
 			*chcr	= cfg->chcr;
 			*dst	= cfg->dst;
-			break;
+			return 0;
 		}
+
+	return -ENXIO;
 }
 
 static int audmapp_set_slave(struct shdma_chan *schan, int slave_id,
@@ -153,8 +155,11 @@ static int audmapp_set_slave(struct shdma_chan *schan, int slave_id,
 	struct audmapp_chan *auchan = to_chan(schan);
 	u32 chcr;
 	dma_addr_t dst;
+	int ret;
 
-	audmapp_get_config(auchan, slave_id, &chcr, &dst);
+	ret = audmapp_get_config(auchan, slave_id, &chcr, &dst);
+	if (ret < 0)
+		return ret;
 
 	if (try)
 		return 0;
diff --git a/drivers/dma/sun6i-dma.c b/drivers/dma/sun6i-dma.c
index 1f92a56fd2b6..3aa10b328254 100644
--- a/drivers/dma/sun6i-dma.c
+++ b/drivers/dma/sun6i-dma.c
@@ -862,7 +862,6 @@ static int sun6i_dma_probe(struct platform_device *pdev)
 {
 	struct sun6i_dma_dev *sdc;
 	struct resource *res;
-	struct clk *mux, *pll6;
 	int ret, i;
 
 	sdc = devm_kzalloc(&pdev->dev, sizeof(*sdc), GFP_KERNEL);
@@ -886,28 +885,6 @@ static int sun6i_dma_probe(struct platform_device *pdev)
 		return PTR_ERR(sdc->clk);
 	}
 
-	mux = clk_get(NULL, "ahb1_mux");
-	if (IS_ERR(mux)) {
-		dev_err(&pdev->dev, "Couldn't get AHB1 Mux\n");
-		return PTR_ERR(mux);
-	}
-
-	pll6 = clk_get(NULL, "pll6");
-	if (IS_ERR(pll6)) {
-		dev_err(&pdev->dev, "Couldn't get PLL6\n");
-		clk_put(mux);
-		return PTR_ERR(pll6);
-	}
-
-	ret = clk_set_parent(mux, pll6);
-	clk_put(pll6);
-	clk_put(mux);
-
-	if (ret) {
-		dev_err(&pdev->dev, "Couldn't reparent AHB1 on PLL6\n");
-		return ret;
-	}
-
 	sdc->rstc = devm_reset_control_get(&pdev->dev, NULL);
 	if (IS_ERR(sdc->rstc)) {
 		dev_err(&pdev->dev, "No reset controller specified\n");
diff --git a/drivers/dma/xilinx/xilinx_vdma.c b/drivers/dma/xilinx/xilinx_vdma.c
index 42a13e8d4607..a6e64767186e 100644
--- a/drivers/dma/xilinx/xilinx_vdma.c
+++ b/drivers/dma/xilinx/xilinx_vdma.c
@@ -1365,7 +1365,6 @@ static const struct of_device_id xilinx_vdma_of_ids[] = {
 static struct platform_driver xilinx_vdma_driver = {
 	.driver = {
 		.name = "xilinx-vdma",
-		.owner = THIS_MODULE,
 		.of_match_table = xilinx_vdma_of_ids,
 	},
 	.probe = xilinx_vdma_probe,
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 0034c4844428..e9bb1af67c8d 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -52,36 +52,6 @@ static int probed;
 #define GET_BITFIELD(v, lo, hi)	\
 	(((v) & GENMASK_ULL(hi, lo)) >> (lo))
 
-/*
- * sbridge Memory Controller Registers
- */
-
-/*
- * FIXME: For now, let's order by device function, as it makes
- * easier for driver's development process. This table should be
- * moved to pci_id.h when submitted upstream
- */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0	0x3cf4	/* 12.6 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1	0x3cf6	/* 12.7 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_BR		0x3cf5	/* 13.6 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0	0x3ca0	/* 14.0 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA	0x3ca8	/* 15.0 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS	0x3c71	/* 15.1 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0	0x3caa	/* 15.2 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1	0x3cab	/* 15.3 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2	0x3cac	/* 15.4 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3	0x3cad	/* 15.5 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO	0x3cb8	/* 17.0 */
-
-	/*
-	 * Currently, unused, but will be needed in the future
-	 * implementations, as they hold the error counters
-	 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR0	0x3c72	/* 16.2 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR1	0x3c73	/* 16.3 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR2	0x3c76	/* 16.6 */
-#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR3	0x3c77	/* 16.7 */
-
 /* Devices 12 Function 6, Offsets 0x80 to 0xcc */
 static const u32 sbridge_dram_rule[] = {
 	0x80, 0x88, 0x90, 0x98, 0xa0,
@@ -283,8 +253,9 @@ static const u32 correrrthrsld[] = {
  * sbridge structs
  */
 
-#define NUM_CHANNELS	4
-#define MAX_DIMMS	3		/* Max DIMMS per channel */
+#define NUM_CHANNELS		4
+#define MAX_DIMMS		3	/* Max DIMMS per channel */
+#define CHANNEL_UNSPECIFIED	0xf	/* Intel IA32 SDM 15-14 */
 
 enum type {
 	SANDY_BRIDGE,
@@ -529,7 +500,7 @@ static const struct pci_id_table pci_dev_descr_haswell_table[] = {
  *	pci_device_id	table for which devices we are looking for
  */
 static const struct pci_device_id sbridge_pci_tbl[] = {
-	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA)},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HASWELL_IMC_HA0)},
 	{0,}			/* 0 terminated list. */
@@ -1991,6 +1962,9 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
 
 	/* FIXME: need support for channel mask */
 
+	if (channel == CHANNEL_UNSPECIFIED)
+		channel = -1;
+
 	/* Call the helper to output message */
 	edac_mc_handle_error(tp_event, mci, core_err_cnt,
 			     m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0,
diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c
index 79f18e6d9c4f..cc016c615c19 100644
--- a/drivers/firmware/memmap.c
+++ b/drivers/firmware/memmap.c
@@ -184,6 +184,9 @@ static int add_sysfs_fw_map_entry(struct firmware_map_entry *entry)
 	static int map_entries_nr;
 	static struct kset *mmap_kset;
 
+	if (entry->kobj.state_in_sysfs)
+		return -EEXIST;
+
 	if (!mmap_kset) {
 		mmap_kset = kset_create_and_add("memmap", NULL, firmware_kobj);
 		if (!mmap_kset)
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 9de1515e5808..0959ca9b6b27 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -136,7 +136,6 @@ config GPIO_DWAPB
 	tristate "Synopsys DesignWare APB GPIO driver"
 	select GPIO_GENERIC
 	select GENERIC_IRQ_CHIP
-	depends on OF_GPIO
 	help
 	  Say Y or M here to build support for the Synopsys DesignWare APB
 	  GPIO block.
@@ -334,6 +333,15 @@ config GPIO_TZ1090_PDC
 	help
 	  Say yes here to support Toumaz Xenif TZ1090 PDC GPIOs.
 
+config GPIO_XGENE
+	bool "APM X-Gene GPIO controller support"
+	depends on ARM64 && OF_GPIO
+	help
+	  This driver is to support the GPIO block within the APM X-Gene SoC
+	  platform's generic flash controller. The GPIO pins are muxed with
+	  the generic flash controller's address and data pins. Say yes
+	  here to enable the GFC GPIO functionality.
+
 config GPIO_XILINX
 	bool "Xilinx GPIO support"
 	depends on PPC_OF || MICROBLAZE || ARCH_ZYNQ
@@ -681,6 +689,7 @@ config GPIO_ADP5588_IRQ
 config GPIO_ADNP
 	tristate "Avionic Design N-bit GPIO expander"
 	depends on I2C && OF_GPIO
+	select GPIOLIB_IRQCHIP
 	help
 	  This option enables support for N GPIOs found on Avionic Design
 	  I2C GPIO expanders. The register space will be extended by powers
@@ -796,7 +805,6 @@ config GPIO_MAX7301
 
 config GPIO_MCP23S08
 	tristate "Microchip MCP23xxx I/O expander"
-	depends on OF_GPIO
 	depends on (SPI_MASTER && !I2C) || I2C
 	help
 	  SPI/I2C driver for Microchip MCP23S08/MCP23S17/MCP23008/MCP23017
@@ -880,7 +888,7 @@ config GPIO_MSIC
 
 config GPIO_BCM_KONA
 	bool "Broadcom Kona GPIO"
-	depends on OF_GPIO
+	depends on OF_GPIO && (ARCH_BCM_MOBILE || COMPILE_TEST)
 	help
 	  Turn on GPIO support for Broadcom "Kona" chips.
 
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 5d024e396622..e5d346cf3b6e 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -101,6 +101,7 @@ obj-$(CONFIG_GPIO_VX855)	+= gpio-vx855.o
 obj-$(CONFIG_GPIO_WM831X)	+= gpio-wm831x.o
 obj-$(CONFIG_GPIO_WM8350)	+= gpio-wm8350.o
 obj-$(CONFIG_GPIO_WM8994)	+= gpio-wm8994.o
+obj-$(CONFIG_GPIO_XGENE)	+= gpio-xgene.o
 obj-$(CONFIG_GPIO_XILINX)	+= gpio-xilinx.o
 obj-$(CONFIG_GPIO_XTENSA)	+= gpio-xtensa.o
 obj-$(CONFIG_GPIO_ZEVIO)	+= gpio-zevio.o
diff --git a/drivers/gpio/gpio-adnp.c b/drivers/gpio/gpio-adnp.c
index 416b2200d4f1..d3d0a90fe542 100644
--- a/drivers/gpio/gpio-adnp.c
+++ b/drivers/gpio/gpio-adnp.c
@@ -6,10 +6,9 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
-#include <linux/irqdomain.h>
 #include <linux/module.h>
 #include <linux/of_irq.h>
 #include <linux/seq_file.h>
@@ -27,8 +26,6 @@ struct adnp {
 	unsigned int reg_shift;
 
 	struct mutex i2c_lock;
-
-	struct irq_domain *domain;
 	struct mutex irq_lock;
 
 	u8 *irq_enable;
@@ -253,6 +250,7 @@ static void adnp_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 static int adnp_gpio_setup(struct adnp *adnp, unsigned int num_gpios)
 {
 	struct gpio_chip *chip = &adnp->gpio;
+	int err;
 
 	adnp->reg_shift = get_count_order(num_gpios) - 3;
 
@@ -272,6 +270,10 @@ static int adnp_gpio_setup(struct adnp *adnp, unsigned int num_gpios)
 	chip->of_node = chip->dev->of_node;
 	chip->owner = THIS_MODULE;
 
+	err = gpiochip_add(chip);
+	if (err)
+		return err;
+
 	return 0;
 }
 
@@ -326,7 +328,8 @@ static irqreturn_t adnp_irq(int irq, void *data)
 
 		for_each_set_bit(bit, &pending, 8) {
 			unsigned int child_irq;
-			child_irq = irq_find_mapping(adnp->domain, base + bit);
+			child_irq = irq_find_mapping(adnp->gpio.irqdomain,
+						     base + bit);
 			handle_nested_irq(child_irq);
 		}
 	}
@@ -334,35 +337,32 @@ static irqreturn_t adnp_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int adnp_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
-{
-	struct adnp *adnp = to_adnp(chip);
-	return irq_create_mapping(adnp->domain, offset);
-}
-
-static void adnp_irq_mask(struct irq_data *data)
+static void adnp_irq_mask(struct irq_data *d)
 {
-	struct adnp *adnp = irq_data_get_irq_chip_data(data);
-	unsigned int reg = data->hwirq >> adnp->reg_shift;
-	unsigned int pos = data->hwirq & 7;
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct adnp *adnp = to_adnp(gc);
+	unsigned int reg = d->hwirq >> adnp->reg_shift;
+	unsigned int pos = d->hwirq & 7;
 
 	adnp->irq_enable[reg] &= ~BIT(pos);
 }
 
-static void adnp_irq_unmask(struct irq_data *data)
+static void adnp_irq_unmask(struct irq_data *d)
 {
-	struct adnp *adnp = irq_data_get_irq_chip_data(data);
-	unsigned int reg = data->hwirq >> adnp->reg_shift;
-	unsigned int pos = data->hwirq & 7;
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct adnp *adnp = to_adnp(gc);
+	unsigned int reg = d->hwirq >> adnp->reg_shift;
+	unsigned int pos = d->hwirq & 7;
 
 	adnp->irq_enable[reg] |= BIT(pos);
 }
 
-static int adnp_irq_set_type(struct irq_data *data, unsigned int type)
+static int adnp_irq_set_type(struct irq_data *d, unsigned int type)
 {
-	struct adnp *adnp = irq_data_get_irq_chip_data(data);
-	unsigned int reg = data->hwirq >> adnp->reg_shift;
-	unsigned int pos = data->hwirq & 7;
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct adnp *adnp = to_adnp(gc);
+	unsigned int reg = d->hwirq >> adnp->reg_shift;
+	unsigned int pos = d->hwirq & 7;
 
 	if (type & IRQ_TYPE_EDGE_RISING)
 		adnp->irq_rise[reg] |= BIT(pos);
@@ -387,16 +387,18 @@ static int adnp_irq_set_type(struct irq_data *data, unsigned int type)
 	return 0;
 }
 
-static void adnp_irq_bus_lock(struct irq_data *data)
+static void adnp_irq_bus_lock(struct irq_data *d)
 {
-	struct adnp *adnp = irq_data_get_irq_chip_data(data);
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct adnp *adnp = to_adnp(gc);
 
 	mutex_lock(&adnp->irq_lock);
 }
 
-static void adnp_irq_bus_unlock(struct irq_data *data)
+static void adnp_irq_bus_unlock(struct irq_data *d)
 {
-	struct adnp *adnp = irq_data_get_irq_chip_data(data);
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct adnp *adnp = to_adnp(gc);
 	unsigned int num_regs = 1 << adnp->reg_shift, i;
 
 	mutex_lock(&adnp->i2c_lock);
@@ -408,26 +410,6 @@ static void adnp_irq_bus_unlock(struct irq_data *data)
 	mutex_unlock(&adnp->irq_lock);
 }
 
-static int adnp_irq_reqres(struct irq_data *data)
-{
-	struct adnp *adnp = irq_data_get_irq_chip_data(data);
-
-	if (gpio_lock_as_irq(&adnp->gpio, data->hwirq)) {
-		dev_err(adnp->gpio.dev,
-			"unable to lock HW IRQ %lu for IRQ\n",
-			data->hwirq);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static void adnp_irq_relres(struct irq_data *data)
-{
-	struct adnp *adnp = irq_data_get_irq_chip_data(data);
-
-	gpio_unlock_as_irq(&adnp->gpio, data->hwirq);
-}
-
 static struct irq_chip adnp_irq_chip = {
 	.name = "gpio-adnp",
 	.irq_mask = adnp_irq_mask,
@@ -435,29 +417,6 @@ static struct irq_chip adnp_irq_chip = {
 	.irq_set_type = adnp_irq_set_type,
 	.irq_bus_lock = adnp_irq_bus_lock,
 	.irq_bus_sync_unlock = adnp_irq_bus_unlock,
-	.irq_request_resources = adnp_irq_reqres,
-	.irq_release_resources = adnp_irq_relres,
-};
-
-static int adnp_irq_map(struct irq_domain *domain, unsigned int irq,
-			irq_hw_number_t hwirq)
-{
-	irq_set_chip_data(irq, domain->host_data);
-	irq_set_chip(irq, &adnp_irq_chip);
-	irq_set_nested_thread(irq, true);
-
-#ifdef CONFIG_ARM
-	set_irq_flags(irq, IRQF_VALID);
-#else
-	irq_set_noprobe(irq);
-#endif
-
-	return 0;
-}
-
-static const struct irq_domain_ops adnp_irq_domain_ops = {
-	.map = adnp_irq_map,
-	.xlate = irq_domain_xlate_twocell,
 };
 
 static int adnp_irq_setup(struct adnp *adnp)
@@ -503,35 +462,28 @@ static int adnp_irq_setup(struct adnp *adnp)
 		adnp->irq_enable[i] = 0x00;
 	}
 
-	adnp->domain = irq_domain_add_linear(chip->of_node, chip->ngpio,
-					     &adnp_irq_domain_ops, adnp);
-
-	err = request_threaded_irq(adnp->client->irq, NULL, adnp_irq,
-				   IRQF_TRIGGER_RISING | IRQF_ONESHOT,
-				   dev_name(chip->dev), adnp);
+	err = devm_request_threaded_irq(chip->dev, adnp->client->irq,
+					NULL, adnp_irq,
+					IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+					dev_name(chip->dev), adnp);
 	if (err != 0) {
 		dev_err(chip->dev, "can't request IRQ#%d: %d\n",
 			adnp->client->irq, err);
 		return err;
 	}
 
-	chip->to_irq = adnp_gpio_to_irq;
-	return 0;
-}
-
-static void adnp_irq_teardown(struct adnp *adnp)
-{
-	unsigned int irq, i;
-
-	free_irq(adnp->client->irq, adnp);
-
-	for (i = 0; i < adnp->gpio.ngpio; i++) {
-		irq = irq_find_mapping(adnp->domain, i);
-		if (irq > 0)
-			irq_dispose_mapping(irq);
+	err = gpiochip_irqchip_add(chip,
+				   &adnp_irq_chip,
+				   0,
+				   handle_simple_irq,
+				   IRQ_TYPE_NONE);
+	if (err) {
+		dev_err(chip->dev,
+			"could not connect irqchip to gpiochip\n");
+		return err;
 	}
 
-	irq_domain_remove(adnp->domain);
+	return 0;
 }
 
 static int adnp_i2c_probe(struct i2c_client *client,
@@ -558,38 +510,25 @@ static int adnp_i2c_probe(struct i2c_client *client,
 	adnp->client = client;
 
 	err = adnp_gpio_setup(adnp, num_gpios);
-	if (err < 0)
+	if (err)
 		return err;
 
 	if (of_find_property(np, "interrupt-controller", NULL)) {
 		err = adnp_irq_setup(adnp);
-		if (err < 0)
-			goto teardown;
+		if (err)
+			return err;
 	}
 
-	err = gpiochip_add(&adnp->gpio);
-	if (err < 0)
-		goto teardown;
-
 	i2c_set_clientdata(client, adnp);
-	return 0;
 
-teardown:
-	if (of_find_property(np, "interrupt-controller", NULL))
-		adnp_irq_teardown(adnp);
-
-	return err;
+	return 0;
 }
 
 static int adnp_i2c_remove(struct i2c_client *client)
 {
 	struct adnp *adnp = i2c_get_clientdata(client);
-	struct device_node *np = client->dev.of_node;
 
 	gpiochip_remove(&adnp->gpio);
-	if (of_find_property(np, "interrupt-controller", NULL))
-		adnp_irq_teardown(adnp);
-
 	return 0;
 }
 
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 3f6b33ce9bd4..de0801e9767a 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -496,7 +496,7 @@ static struct irq_chip bcm_gpio_irq_chip = {
 	.irq_release_resources = bcm_kona_gpio_irq_relres,
 };
 
-static struct __initconst of_device_id bcm_kona_gpio_of_match[] = {
+static struct of_device_id const bcm_kona_gpio_of_match[] = {
 	{ .compatible = "brcm,kona-gpio" },
 	{}
 };
diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c
index 934462f5bd22..bbfe7f508502 100644
--- a/drivers/gpio/gpio-crystalcove.c
+++ b/drivers/gpio/gpio-crystalcove.c
@@ -24,6 +24,7 @@
 #include <linux/mfd/intel_soc_pmic.h>
 
 #define CRYSTALCOVE_GPIO_NUM	16
+#define CRYSTALCOVE_VGPIO_NUM	94
 
 #define UPDATE_IRQ_TYPE		BIT(0)
 #define UPDATE_IRQ_MASK		BIT(1)
@@ -130,6 +131,9 @@ static int crystalcove_gpio_dir_in(struct gpio_chip *chip, unsigned gpio)
 {
 	struct crystalcove_gpio *cg = to_cg(chip);
 
+	if (gpio > CRYSTALCOVE_VGPIO_NUM)
+		return 0;
+
 	return regmap_write(cg->regmap, to_reg(gpio, CTRL_OUT),
 			    CTLO_INPUT_SET);
 }
@@ -139,6 +143,9 @@ static int crystalcove_gpio_dir_out(struct gpio_chip *chip, unsigned gpio,
 {
 	struct crystalcove_gpio *cg = to_cg(chip);
 
+	if (gpio > CRYSTALCOVE_VGPIO_NUM)
+		return 0;
+
 	return regmap_write(cg->regmap, to_reg(gpio, CTRL_OUT),
 			    CTLO_OUTPUT_SET | value);
 }
@@ -149,6 +156,9 @@ static int crystalcove_gpio_get(struct gpio_chip *chip, unsigned gpio)
 	int ret;
 	unsigned int val;
 
+	if (gpio > CRYSTALCOVE_VGPIO_NUM)
+		return 0;
+
 	ret = regmap_read(cg->regmap, to_reg(gpio, CTRL_IN), &val);
 	if (ret)
 		return ret;
@@ -161,6 +171,9 @@ static void crystalcove_gpio_set(struct gpio_chip *chip,
 {
 	struct crystalcove_gpio *cg = to_cg(chip);
 
+	if (gpio > CRYSTALCOVE_VGPIO_NUM)
+		return;
+
 	if (value)
 		regmap_update_bits(cg->regmap, to_reg(gpio, CTRL_OUT), 1, 1);
 	else
@@ -256,7 +269,7 @@ static irqreturn_t crystalcove_gpio_irq_handler(int irq, void *data)
 
 	pending = p0 | p1 << 8;
 
-	for (gpio = 0; gpio < cg->chip.ngpio; gpio++) {
+	for (gpio = 0; gpio < CRYSTALCOVE_GPIO_NUM; gpio++) {
 		if (pending & BIT(gpio)) {
 			virq = irq_find_mapping(cg->chip.irqdomain, gpio);
 			generic_handle_irq(virq);
@@ -273,7 +286,7 @@ static void crystalcove_gpio_dbg_show(struct seq_file *s,
 	int gpio, offset;
 	unsigned int ctlo, ctli, mirqs0, mirqsx, irq;
 
-	for (gpio = 0; gpio < cg->chip.ngpio; gpio++) {
+	for (gpio = 0; gpio < CRYSTALCOVE_GPIO_NUM; gpio++) {
 		regmap_read(cg->regmap, to_reg(gpio, CTRL_OUT), &ctlo);
 		regmap_read(cg->regmap, to_reg(gpio, CTRL_IN), &ctli);
 		regmap_read(cg->regmap, gpio < 8 ? MGPIO0IRQS0 : MGPIO1IRQS0,
@@ -320,7 +333,7 @@ static int crystalcove_gpio_probe(struct platform_device *pdev)
 	cg->chip.get = crystalcove_gpio_get;
 	cg->chip.set = crystalcove_gpio_set;
 	cg->chip.base = -1;
-	cg->chip.ngpio = CRYSTALCOVE_GPIO_NUM;
+	cg->chip.ngpio = CRYSTALCOVE_VGPIO_NUM;
 	cg->chip.can_sleep = true;
 	cg->chip.dev = dev;
 	cg->chip.dbg_show = crystalcove_gpio_dbg_show;
@@ -346,7 +359,7 @@ static int crystalcove_gpio_probe(struct platform_device *pdev)
 	return 0;
 
 out_remove_gpio:
-	WARN_ON(gpiochip_remove(&cg->chip));
+	gpiochip_remove(&cg->chip);
 	return retval;
 }
 
@@ -354,14 +367,11 @@ static int crystalcove_gpio_remove(struct platform_device *pdev)
 {
 	struct crystalcove_gpio *cg = platform_get_drvdata(pdev);
 	int irq = platform_get_irq(pdev, 0);
-	int err;
-
-	err = gpiochip_remove(&cg->chip);
 
+	gpiochip_remove(&cg->chip);
 	if (irq >= 0)
 		free_irq(irq, cg);
-
-	return err;
+	return 0;
 }
 
 static struct platform_driver crystalcove_gpio_driver = {
diff --git a/drivers/gpio/gpio-cs5535.c b/drivers/gpio/gpio-cs5535.c
index 92ec58fa9236..668127fe90ef 100644
--- a/drivers/gpio/gpio-cs5535.c
+++ b/drivers/gpio/gpio-cs5535.c
@@ -201,7 +201,8 @@ EXPORT_SYMBOL_GPL(cs5535_gpio_setup_event);
 
 static int chip_gpio_request(struct gpio_chip *c, unsigned offset)
 {
-	struct cs5535_gpio_chip *chip = (struct cs5535_gpio_chip *) c;
+	struct cs5535_gpio_chip *chip =
+		container_of(c, struct cs5535_gpio_chip, chip);
 	unsigned long flags;
 
 	spin_lock_irqsave(&chip->lock, flags);
@@ -241,7 +242,8 @@ static void chip_gpio_set(struct gpio_chip *chip, unsigned offset, int val)
 
 static int chip_direction_input(struct gpio_chip *c, unsigned offset)
 {
-	struct cs5535_gpio_chip *chip = (struct cs5535_gpio_chip *) c;
+	struct cs5535_gpio_chip *chip =
+		container_of(c, struct cs5535_gpio_chip, chip);
 	unsigned long flags;
 
 	spin_lock_irqsave(&chip->lock, flags);
@@ -254,7 +256,8 @@ static int chip_direction_input(struct gpio_chip *c, unsigned offset)
 
 static int chip_direction_output(struct gpio_chip *c, unsigned offset, int val)
 {
-	struct cs5535_gpio_chip *chip = (struct cs5535_gpio_chip *) c;
+	struct cs5535_gpio_chip *chip =
+		container_of(c, struct cs5535_gpio_chip, chip);
 	unsigned long flags;
 
 	spin_lock_irqsave(&chip->lock, flags);
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index d6618a6e2399..b43cd84b61f1 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -21,6 +21,8 @@
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/spinlock.h>
+#include <linux/platform_data/gpio-dwapb.h>
+#include <linux/slab.h>
 
 #define GPIO_SWPORTA_DR		0x00
 #define GPIO_SWPORTA_DDR	0x04
@@ -35,6 +37,7 @@
 #define GPIO_INTTYPE_LEVEL	0x38
 #define GPIO_INT_POLARITY	0x3c
 #define GPIO_INTSTATUS		0x40
+#define GPIO_PORTA_DEBOUNCE	0x48
 #define GPIO_PORTA_EOI		0x4c
 #define GPIO_EXT_PORTA		0x50
 #define GPIO_EXT_PORTB		0x54
@@ -48,10 +51,28 @@
 
 struct dwapb_gpio;
 
+#ifdef CONFIG_PM_SLEEP
+/* Store GPIO context across system-wide suspend/resume transitions */
+struct dwapb_context {
+	u32 data;
+	u32 dir;
+	u32 ext;
+	u32 int_en;
+	u32 int_mask;
+	u32 int_type;
+	u32 int_pol;
+	u32 int_deb;
+};
+#endif
+
 struct dwapb_gpio_port {
 	struct bgpio_chip	bgc;
 	bool			is_registered;
 	struct dwapb_gpio	*gpio;
+#ifdef CONFIG_PM_SLEEP
+	struct dwapb_context	*ctx;
+#endif
+	unsigned int		idx;
 };
 
 struct dwapb_gpio {
@@ -62,11 +83,33 @@ struct dwapb_gpio {
 	struct irq_domain	*domain;
 };
 
+static inline struct dwapb_gpio_port *
+to_dwapb_gpio_port(struct bgpio_chip *bgc)
+{
+	return container_of(bgc, struct dwapb_gpio_port, bgc);
+}
+
+static inline u32 dwapb_read(struct dwapb_gpio *gpio, unsigned int offset)
+{
+	struct bgpio_chip *bgc	= &gpio->ports[0].bgc;
+	void __iomem *reg_base	= gpio->regs;
+
+	return bgc->read_reg(reg_base + offset);
+}
+
+static inline void dwapb_write(struct dwapb_gpio *gpio, unsigned int offset,
+			       u32 val)
+{
+	struct bgpio_chip *bgc	= &gpio->ports[0].bgc;
+	void __iomem *reg_base	= gpio->regs;
+
+	bgc->write_reg(reg_base + offset, val);
+}
+
 static int dwapb_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
 {
 	struct bgpio_chip *bgc = to_bgpio_chip(gc);
-	struct dwapb_gpio_port *port = container_of(bgc, struct
-						    dwapb_gpio_port, bgc);
+	struct dwapb_gpio_port *port = to_dwapb_gpio_port(bgc);
 	struct dwapb_gpio *gpio = port->gpio;
 
 	return irq_find_mapping(gpio->domain, offset);
@@ -74,21 +117,20 @@ static int dwapb_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
 
 static void dwapb_toggle_trigger(struct dwapb_gpio *gpio, unsigned int offs)
 {
-	u32 v = readl(gpio->regs + GPIO_INT_POLARITY);
+	u32 v = dwapb_read(gpio, GPIO_INT_POLARITY);
 
 	if (gpio_get_value(gpio->ports[0].bgc.gc.base + offs))
 		v &= ~BIT(offs);
 	else
 		v |= BIT(offs);
 
-	writel(v, gpio->regs + GPIO_INT_POLARITY);
+	dwapb_write(gpio, GPIO_INT_POLARITY, v);
 }
 
-static void dwapb_irq_handler(u32 irq, struct irq_desc *desc)
+static u32 dwapb_do_irq(struct dwapb_gpio *gpio)
 {
-	struct dwapb_gpio *gpio = irq_get_handler_data(irq);
-	struct irq_chip *chip = irq_desc_get_chip(desc);
 	u32 irq_status = readl_relaxed(gpio->regs + GPIO_INTSTATUS);
+	u32 ret = irq_status;
 
 	while (irq_status) {
 		int hwirq = fls(irq_status) - 1;
@@ -102,6 +144,16 @@ static void dwapb_irq_handler(u32 irq, struct irq_desc *desc)
 			dwapb_toggle_trigger(gpio, hwirq);
 	}
 
+	return ret;
+}
+
+static void dwapb_irq_handler(u32 irq, struct irq_desc *desc)
+{
+	struct dwapb_gpio *gpio = irq_get_handler_data(irq);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	dwapb_do_irq(gpio);
+
 	if (chip->irq_eoi)
 		chip->irq_eoi(irq_desc_get_irq_data(desc));
 }
@@ -115,9 +167,9 @@ static void dwapb_irq_enable(struct irq_data *d)
 	u32 val;
 
 	spin_lock_irqsave(&bgc->lock, flags);
-	val = readl(gpio->regs + GPIO_INTEN);
+	val = dwapb_read(gpio, GPIO_INTEN);
 	val |= BIT(d->hwirq);
-	writel(val, gpio->regs + GPIO_INTEN);
+	dwapb_write(gpio, GPIO_INTEN, val);
 	spin_unlock_irqrestore(&bgc->lock, flags);
 }
 
@@ -130,9 +182,9 @@ static void dwapb_irq_disable(struct irq_data *d)
 	u32 val;
 
 	spin_lock_irqsave(&bgc->lock, flags);
-	val = readl(gpio->regs + GPIO_INTEN);
+	val = dwapb_read(gpio, GPIO_INTEN);
 	val &= ~BIT(d->hwirq);
-	writel(val, gpio->regs + GPIO_INTEN);
+	dwapb_write(gpio, GPIO_INTEN, val);
 	spin_unlock_irqrestore(&bgc->lock, flags);
 }
 
@@ -172,8 +224,8 @@ static int dwapb_irq_set_type(struct irq_data *d, u32 type)
 		return -EINVAL;
 
 	spin_lock_irqsave(&bgc->lock, flags);
-	level = readl(gpio->regs + GPIO_INTTYPE_LEVEL);
-	polarity = readl(gpio->regs + GPIO_INT_POLARITY);
+	level = dwapb_read(gpio, GPIO_INTTYPE_LEVEL);
+	polarity = dwapb_read(gpio, GPIO_INT_POLARITY);
 
 	switch (type) {
 	case IRQ_TYPE_EDGE_BOTH:
@@ -200,29 +252,55 @@ static int dwapb_irq_set_type(struct irq_data *d, u32 type)
 
 	irq_setup_alt_chip(d, type);
 
-	writel(level, gpio->regs + GPIO_INTTYPE_LEVEL);
-	writel(polarity, gpio->regs + GPIO_INT_POLARITY);
+	dwapb_write(gpio, GPIO_INTTYPE_LEVEL, level);
+	dwapb_write(gpio, GPIO_INT_POLARITY, polarity);
+	spin_unlock_irqrestore(&bgc->lock, flags);
+
+	return 0;
+}
+
+static int dwapb_gpio_set_debounce(struct gpio_chip *gc,
+				   unsigned offset, unsigned debounce)
+{
+	struct bgpio_chip *bgc = to_bgpio_chip(gc);
+	struct dwapb_gpio_port *port = to_dwapb_gpio_port(bgc);
+	struct dwapb_gpio *gpio = port->gpio;
+	unsigned long flags, val_deb;
+	unsigned long mask = bgc->pin2mask(bgc, offset);
+
+	spin_lock_irqsave(&bgc->lock, flags);
+
+	val_deb = dwapb_read(gpio, GPIO_PORTA_DEBOUNCE);
+	if (debounce)
+		dwapb_write(gpio, GPIO_PORTA_DEBOUNCE, val_deb | mask);
+	else
+		dwapb_write(gpio, GPIO_PORTA_DEBOUNCE, val_deb & ~mask);
+
 	spin_unlock_irqrestore(&bgc->lock, flags);
 
 	return 0;
 }
 
+static irqreturn_t dwapb_irq_handler_mfd(int irq, void *dev_id)
+{
+	u32 worked;
+	struct dwapb_gpio *gpio = dev_id;
+
+	worked = dwapb_do_irq(gpio);
+
+	return worked ? IRQ_HANDLED : IRQ_NONE;
+}
+
 static void dwapb_configure_irqs(struct dwapb_gpio *gpio,
-				 struct dwapb_gpio_port *port)
+				 struct dwapb_gpio_port *port,
+				 struct dwapb_port_property *pp)
 {
 	struct gpio_chip *gc = &port->bgc.gc;
-	struct device_node *node =  gc->of_node;
-	struct irq_chip_generic	*irq_gc;
+	struct device_node *node = pp->node;
+	struct irq_chip_generic	*irq_gc = NULL;
 	unsigned int hwirq, ngpio = gc->ngpio;
 	struct irq_chip_type *ct;
-	int err, irq, i;
-
-	irq = irq_of_parse_and_map(node, 0);
-	if (!irq) {
-		dev_warn(gpio->dev, "no irq for bank %s\n",
-			port->bgc.gc.of_node->full_name);
-		return;
-	}
+	int err, i;
 
 	gpio->domain = irq_domain_add_linear(node, ngpio,
 					     &irq_generic_chip_ops, gpio);
@@ -269,8 +347,24 @@ static void dwapb_configure_irqs(struct dwapb_gpio *gpio,
 	irq_gc->chip_types[1].type = IRQ_TYPE_EDGE_BOTH;
 	irq_gc->chip_types[1].handler = handle_edge_irq;
 
-	irq_set_chained_handler(irq, dwapb_irq_handler);
-	irq_set_handler_data(irq, gpio);
+	if (!pp->irq_shared) {
+		irq_set_chained_handler(pp->irq, dwapb_irq_handler);
+		irq_set_handler_data(pp->irq, gpio);
+	} else {
+		/*
+		 * Request a shared IRQ since where MFD would have devices
+		 * using the same irq pin
+		 */
+		err = devm_request_irq(gpio->dev, pp->irq,
+				       dwapb_irq_handler_mfd,
+				       IRQF_SHARED, "gpio-dwapb-mfd", gpio);
+		if (err) {
+			dev_err(gpio->dev, "error requesting IRQ\n");
+			irq_domain_remove(gpio->domain);
+			gpio->domain = NULL;
+			return;
+		}
+	}
 
 	for (hwirq = 0 ; hwirq < ngpio ; hwirq++)
 		irq_create_mapping(gpio->domain, hwirq);
@@ -296,57 +390,53 @@ static void dwapb_irq_teardown(struct dwapb_gpio *gpio)
 }
 
 static int dwapb_gpio_add_port(struct dwapb_gpio *gpio,
-			       struct device_node *port_np,
+			       struct dwapb_port_property *pp,
 			       unsigned int offs)
 {
 	struct dwapb_gpio_port *port;
-	u32 port_idx, ngpio;
 	void __iomem *dat, *set, *dirout;
 	int err;
 
-	if (of_property_read_u32(port_np, "reg", &port_idx) ||
-		port_idx >= DWAPB_MAX_PORTS) {
-		dev_err(gpio->dev, "missing/invalid port index for %s\n",
-			port_np->full_name);
-		return -EINVAL;
-	}
-
 	port = &gpio->ports[offs];
 	port->gpio = gpio;
+	port->idx = pp->idx;
 
-	if (of_property_read_u32(port_np, "snps,nr-gpios", &ngpio)) {
-		dev_info(gpio->dev, "failed to get number of gpios for %s\n",
-			 port_np->full_name);
-		ngpio = 32;
-	}
+#ifdef CONFIG_PM_SLEEP
+	port->ctx = devm_kzalloc(gpio->dev, sizeof(*port->ctx), GFP_KERNEL);
+	if (!port->ctx)
+		return -ENOMEM;
+#endif
 
-	dat = gpio->regs + GPIO_EXT_PORTA + (port_idx * GPIO_EXT_PORT_SIZE);
-	set = gpio->regs + GPIO_SWPORTA_DR + (port_idx * GPIO_SWPORT_DR_SIZE);
+	dat = gpio->regs + GPIO_EXT_PORTA + (pp->idx * GPIO_EXT_PORT_SIZE);
+	set = gpio->regs + GPIO_SWPORTA_DR + (pp->idx * GPIO_SWPORT_DR_SIZE);
 	dirout = gpio->regs + GPIO_SWPORTA_DDR +
-		(port_idx * GPIO_SWPORT_DDR_SIZE);
+		(pp->idx * GPIO_SWPORT_DDR_SIZE);
 
 	err = bgpio_init(&port->bgc, gpio->dev, 4, dat, set, NULL, dirout,
 			 NULL, false);
 	if (err) {
 		dev_err(gpio->dev, "failed to init gpio chip for %s\n",
-			port_np->full_name);
+			pp->name);
 		return err;
 	}
 
-	port->bgc.gc.ngpio = ngpio;
-	port->bgc.gc.of_node = port_np;
+#ifdef CONFIG_OF_GPIO
+	port->bgc.gc.of_node = pp->node;
+#endif
+	port->bgc.gc.ngpio = pp->ngpio;
+	port->bgc.gc.base = pp->gpio_base;
 
-	/*
-	 * Only port A can provide interrupts in all configurations of the IP.
-	 */
-	if (port_idx == 0 &&
-	    of_property_read_bool(port_np, "interrupt-controller"))
-		dwapb_configure_irqs(gpio, port);
+	/* Only port A support debounce */
+	if (pp->idx == 0)
+		port->bgc.gc.set_debounce = dwapb_gpio_set_debounce;
+
+	if (pp->irq)
+		dwapb_configure_irqs(gpio, port, pp);
 
 	err = gpiochip_add(&port->bgc.gc);
 	if (err)
 		dev_err(gpio->dev, "failed to register gpiochip for %s\n",
-			port_np->full_name);
+			pp->name);
 	else
 		port->is_registered = true;
 
@@ -362,25 +452,116 @@ static void dwapb_gpio_unregister(struct dwapb_gpio *gpio)
 			gpiochip_remove(&gpio->ports[m].bgc.gc);
 }
 
+static struct dwapb_platform_data *
+dwapb_gpio_get_pdata_of(struct device *dev)
+{
+	struct device_node *node, *port_np;
+	struct dwapb_platform_data *pdata;
+	struct dwapb_port_property *pp;
+	int nports;
+	int i;
+
+	node = dev->of_node;
+	if (!IS_ENABLED(CONFIG_OF_GPIO) || !node)
+		return ERR_PTR(-ENODEV);
+
+	nports = of_get_child_count(node);
+	if (nports == 0)
+		return ERR_PTR(-ENODEV);
+
+	pdata = kzalloc(sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	pdata->properties = kcalloc(nports, sizeof(*pp), GFP_KERNEL);
+	if (!pdata->properties) {
+		kfree(pdata);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	pdata->nports = nports;
+
+	i = 0;
+	for_each_child_of_node(node, port_np) {
+		pp = &pdata->properties[i++];
+		pp->node = port_np;
+
+		if (of_property_read_u32(port_np, "reg", &pp->idx) ||
+		    pp->idx >= DWAPB_MAX_PORTS) {
+			dev_err(dev, "missing/invalid port index for %s\n",
+				port_np->full_name);
+			kfree(pdata->properties);
+			kfree(pdata);
+			return ERR_PTR(-EINVAL);
+		}
+
+		if (of_property_read_u32(port_np, "snps,nr-gpios",
+					 &pp->ngpio)) {
+			dev_info(dev, "failed to get number of gpios for %s\n",
+				 port_np->full_name);
+			pp->ngpio = 32;
+		}
+
+		/*
+		 * Only port A can provide interrupts in all configurations of
+		 * the IP.
+		 */
+		if (pp->idx == 0 &&
+		    of_property_read_bool(port_np, "interrupt-controller")) {
+			pp->irq = irq_of_parse_and_map(port_np, 0);
+			if (!pp->irq) {
+				dev_warn(dev, "no irq for bank %s\n",
+					 port_np->full_name);
+			}
+		}
+
+		pp->irq_shared	= false;
+		pp->gpio_base	= -1;
+		pp->name	= port_np->full_name;
+	}
+
+	return pdata;
+}
+
+static inline void dwapb_free_pdata_of(struct dwapb_platform_data *pdata)
+{
+	if (!IS_ENABLED(CONFIG_OF_GPIO) || !pdata)
+		return;
+
+	kfree(pdata->properties);
+	kfree(pdata);
+}
+
 static int dwapb_gpio_probe(struct platform_device *pdev)
 {
+	unsigned int i;
 	struct resource *res;
 	struct dwapb_gpio *gpio;
-	struct device_node *np;
 	int err;
-	unsigned int offs = 0;
+	struct device *dev = &pdev->dev;
+	struct dwapb_platform_data *pdata = dev_get_platdata(dev);
+	bool is_pdata_alloc = !pdata;
+
+	if (is_pdata_alloc) {
+		pdata = dwapb_gpio_get_pdata_of(dev);
+		if (IS_ERR(pdata))
+			return PTR_ERR(pdata);
+	}
 
-	gpio = devm_kzalloc(&pdev->dev, sizeof(*gpio), GFP_KERNEL);
-	if (!gpio)
-		return -ENOMEM;
-	gpio->dev = &pdev->dev;
+	if (!pdata->nports) {
+		err = -ENODEV;
+		goto out_err;
+	}
 
-	gpio->nr_ports = of_get_child_count(pdev->dev.of_node);
-	if (!gpio->nr_ports) {
-		err = -EINVAL;
+	gpio = devm_kzalloc(&pdev->dev, sizeof(*gpio), GFP_KERNEL);
+	if (!gpio) {
+		err = -ENOMEM;
 		goto out_err;
 	}
-	gpio->ports = devm_kzalloc(&pdev->dev, gpio->nr_ports *
+	gpio->dev = &pdev->dev;
+	gpio->nr_ports = pdata->nports;
+
+	gpio->ports = devm_kcalloc(&pdev->dev, gpio->nr_ports,
 				   sizeof(*gpio->ports), GFP_KERNEL);
 	if (!gpio->ports) {
 		err = -ENOMEM;
@@ -394,20 +575,23 @@ static int dwapb_gpio_probe(struct platform_device *pdev)
 		goto out_err;
 	}
 
-	for_each_child_of_node(pdev->dev.of_node, np) {
-		err = dwapb_gpio_add_port(gpio, np, offs++);
+	for (i = 0; i < gpio->nr_ports; i++) {
+		err = dwapb_gpio_add_port(gpio, &pdata->properties[i], i);
 		if (err)
 			goto out_unregister;
 	}
 	platform_set_drvdata(pdev, gpio);
 
-	return 0;
+	goto out_err;
 
 out_unregister:
 	dwapb_gpio_unregister(gpio);
 	dwapb_irq_teardown(gpio);
 
 out_err:
+	if (is_pdata_alloc)
+		dwapb_free_pdata_of(pdata);
+
 	return err;
 }
 
@@ -427,10 +611,100 @@ static const struct of_device_id dwapb_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, dwapb_of_match);
 
+#ifdef CONFIG_PM_SLEEP
+static int dwapb_gpio_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dwapb_gpio *gpio = platform_get_drvdata(pdev);
+	struct bgpio_chip *bgc	= &gpio->ports[0].bgc;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&bgc->lock, flags);
+	for (i = 0; i < gpio->nr_ports; i++) {
+		unsigned int offset;
+		unsigned int idx = gpio->ports[i].idx;
+		struct dwapb_context *ctx = gpio->ports[i].ctx;
+
+		BUG_ON(!ctx);
+
+		offset = GPIO_SWPORTA_DDR + idx * GPIO_SWPORT_DDR_SIZE;
+		ctx->dir = dwapb_read(gpio, offset);
+
+		offset = GPIO_SWPORTA_DR + idx * GPIO_SWPORT_DR_SIZE;
+		ctx->data = dwapb_read(gpio, offset);
+
+		offset = GPIO_EXT_PORTA + idx * GPIO_EXT_PORT_SIZE;
+		ctx->ext = dwapb_read(gpio, offset);
+
+		/* Only port A can provide interrupts */
+		if (idx == 0) {
+			ctx->int_mask	= dwapb_read(gpio, GPIO_INTMASK);
+			ctx->int_en	= dwapb_read(gpio, GPIO_INTEN);
+			ctx->int_pol	= dwapb_read(gpio, GPIO_INT_POLARITY);
+			ctx->int_type	= dwapb_read(gpio, GPIO_INTTYPE_LEVEL);
+			ctx->int_deb	= dwapb_read(gpio, GPIO_PORTA_DEBOUNCE);
+
+			/* Mask out interrupts */
+			dwapb_write(gpio, GPIO_INTMASK, 0xffffffff);
+		}
+	}
+	spin_unlock_irqrestore(&bgc->lock, flags);
+
+	return 0;
+}
+
+static int dwapb_gpio_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dwapb_gpio *gpio = platform_get_drvdata(pdev);
+	struct bgpio_chip *bgc	= &gpio->ports[0].bgc;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&bgc->lock, flags);
+	for (i = 0; i < gpio->nr_ports; i++) {
+		unsigned int offset;
+		unsigned int idx = gpio->ports[i].idx;
+		struct dwapb_context *ctx = gpio->ports[i].ctx;
+
+		BUG_ON(!ctx);
+
+		offset = GPIO_SWPORTA_DR + idx * GPIO_SWPORT_DR_SIZE;
+		dwapb_write(gpio, offset, ctx->data);
+
+		offset = GPIO_SWPORTA_DDR + idx * GPIO_SWPORT_DDR_SIZE;
+		dwapb_write(gpio, offset, ctx->dir);
+
+		offset = GPIO_EXT_PORTA + idx * GPIO_EXT_PORT_SIZE;
+		dwapb_write(gpio, offset, ctx->ext);
+
+		/* Only port A can provide interrupts */
+		if (idx == 0) {
+			dwapb_write(gpio, GPIO_INTTYPE_LEVEL, ctx->int_type);
+			dwapb_write(gpio, GPIO_INT_POLARITY, ctx->int_pol);
+			dwapb_write(gpio, GPIO_PORTA_DEBOUNCE, ctx->int_deb);
+			dwapb_write(gpio, GPIO_INTEN, ctx->int_en);
+			dwapb_write(gpio, GPIO_INTMASK, ctx->int_mask);
+
+			/* Clear out spurious interrupts */
+			dwapb_write(gpio, GPIO_PORTA_EOI, 0xffffffff);
+		}
+	}
+	spin_unlock_irqrestore(&bgc->lock, flags);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(dwapb_gpio_pm_ops, dwapb_gpio_suspend,
+			 dwapb_gpio_resume);
+
 static struct platform_driver dwapb_gpio_driver = {
 	.driver		= {
 		.name	= "gpio-dwapb",
 		.owner	= THIS_MODULE,
+		.pm	= &dwapb_gpio_pm_ops,
 		.of_match_table = of_match_ptr(dwapb_of_match),
 	},
 	.probe		= dwapb_gpio_probe,
diff --git a/drivers/gpio/gpio-ks8695.c b/drivers/gpio/gpio-ks8695.c
index 464a83de0d6a..cc09b237e88c 100644
--- a/drivers/gpio/gpio-ks8695.c
+++ b/drivers/gpio/gpio-ks8695.c
@@ -265,29 +265,27 @@ static int ks8695_gpio_show(struct seq_file *s, void *unused)
 				seq_printf(s, "EXT%i ", i);
 
 				switch ((ctrl & intmask[i]) >> (4 * i)) {
-					case IOPC_TM_LOW:
-						seq_printf(s, "(Low)");		break;
-					case IOPC_TM_HIGH:
-						seq_printf(s, "(High)");	break;
-					case IOPC_TM_RISING:
-						seq_printf(s, "(Rising)");	break;
-					case IOPC_TM_FALLING:
-						seq_printf(s, "(Falling)");	break;
-					case IOPC_TM_EDGE:
-						seq_printf(s, "(Edges)");	break;
+				case IOPC_TM_LOW:
+					seq_printf(s, "(Low)");		break;
+				case IOPC_TM_HIGH:
+					seq_printf(s, "(High)");	break;
+				case IOPC_TM_RISING:
+					seq_printf(s, "(Rising)");	break;
+				case IOPC_TM_FALLING:
+					seq_printf(s, "(Falling)");	break;
+				case IOPC_TM_EDGE:
+					seq_printf(s, "(Edges)");	break;
 				}
-			}
-			else
+			} else
 				seq_printf(s, "GPIO\t");
-		}
-		else if (i <= KS8695_GPIO_5) {
+		} else if (i <= KS8695_GPIO_5) {
 			if (ctrl & enable[i])
 				seq_printf(s, "TOUT%i\t", i - KS8695_GPIO_4);
 			else
 				seq_printf(s, "GPIO\t");
-		}
-		else
+		} else {
 			seq_printf(s, "GPIO\t");
+		}
 
 		seq_printf(s, "\t");
 
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index 6f183d9b487e..8488e2fd307c 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -479,7 +479,7 @@ static int mcp23s08_irq_setup(struct mcp23s08 *mcp)
 
 	mutex_init(&mcp->irq_lock);
 
-	mcp->irq_domain = irq_domain_add_linear(chip->of_node, chip->ngpio,
+	mcp->irq_domain = irq_domain_add_linear(chip->dev->of_node, chip->ngpio,
 						&irq_domain_simple_ops, mcp);
 	if (!mcp->irq_domain)
 		return -ENODEV;
@@ -581,7 +581,7 @@ done:
 
 static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
 			      void *data, unsigned addr, unsigned type,
-			      unsigned base, unsigned pullups)
+			      struct mcp23s08_platform_data *pdata, int cs)
 {
 	int status;
 	bool mirror = false;
@@ -635,7 +635,7 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
 		return -EINVAL;
 	}
 
-	mcp->chip.base = base;
+	mcp->chip.base = pdata->base;
 	mcp->chip.can_sleep = true;
 	mcp->chip.dev = dev;
 	mcp->chip.owner = THIS_MODULE;
@@ -648,11 +648,9 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
 	if (status < 0)
 		goto fail;
 
-	mcp->irq_controller = of_property_read_bool(mcp->chip.of_node,
-						"interrupt-controller");
+	mcp->irq_controller = pdata->irq_controller;
 	if (mcp->irq && mcp->irq_controller && (type == MCP_TYPE_017))
-		mirror = of_property_read_bool(mcp->chip.of_node,
-						"microchip,irq-mirror");
+		mirror = pdata->mirror;
 
 	if ((status & IOCON_SEQOP) || !(status & IOCON_HAEN) || mirror) {
 		/* mcp23s17 has IOCON twice, make sure they are in sync */
@@ -668,7 +666,7 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
 	}
 
 	/* configure ~100K pullups */
-	status = mcp->ops->write(mcp, MCP_GPPU, pullups);
+	status = mcp->ops->write(mcp, MCP_GPPU, pdata->chip[cs].pullups);
 	if (status < 0)
 		goto fail;
 
@@ -768,25 +766,29 @@ MODULE_DEVICE_TABLE(of, mcp23s08_i2c_of_match);
 static int mcp230xx_probe(struct i2c_client *client,
 				    const struct i2c_device_id *id)
 {
-	struct mcp23s08_platform_data *pdata;
+	struct mcp23s08_platform_data *pdata, local_pdata;
 	struct mcp23s08 *mcp;
-	int status, base, pullups;
+	int status;
 	const struct of_device_id *match;
 
 	match = of_match_device(of_match_ptr(mcp23s08_i2c_of_match),
 					&client->dev);
-	pdata = dev_get_platdata(&client->dev);
-	if (match || !pdata) {
-		base = -1;
-		pullups = 0;
+	if (match) {
+		pdata = &local_pdata;
+		pdata->base = -1;
+		pdata->chip[0].pullups = 0;
+		pdata->irq_controller =	of_property_read_bool(
+					client->dev.of_node,
+					"interrupt-controller");
+		pdata->mirror = of_property_read_bool(client->dev.of_node,
+						      "microchip,irq-mirror");
 		client->irq = irq_of_parse_and_map(client->dev.of_node, 0);
 	} else {
-		if (!gpio_is_valid(pdata->base)) {
+		pdata = dev_get_platdata(&client->dev);
+		if (!pdata || !gpio_is_valid(pdata->base)) {
 			dev_dbg(&client->dev, "invalid platform data\n");
 			return -EINVAL;
 		}
-		base = pdata->base;
-		pullups = pdata->chip[0].pullups;
 	}
 
 	mcp = kzalloc(sizeof(*mcp), GFP_KERNEL);
@@ -795,7 +797,7 @@ static int mcp230xx_probe(struct i2c_client *client,
 
 	mcp->irq = client->irq;
 	status = mcp23s08_probe_one(mcp, &client->dev, client, client->addr,
-				    id->driver_data, base, pullups);
+				    id->driver_data, pdata, 0);
 	if (status)
 		goto fail;
 
@@ -863,14 +865,12 @@ static void mcp23s08_i2c_exit(void) { }
 
 static int mcp23s08_probe(struct spi_device *spi)
 {
-	struct mcp23s08_platform_data	*pdata;
+	struct mcp23s08_platform_data	*pdata, local_pdata;
 	unsigned			addr;
 	int				chips = 0;
 	struct mcp23s08_driver_data	*data;
 	int				status, type;
-	unsigned			base = -1,
-					ngpio = 0,
-					pullups[ARRAY_SIZE(pdata->chip)];
+	unsigned			ngpio = 0;
 	const struct			of_device_id *match;
 	u32				spi_present_mask = 0;
 
@@ -893,11 +893,18 @@ static int mcp23s08_probe(struct spi_device *spi)
 			return -ENODEV;
 		}
 
+		pdata = &local_pdata;
+		pdata->base = -1;
 		for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++) {
-			pullups[addr] = 0;
+			pdata->chip[addr].pullups = 0;
 			if (spi_present_mask & (1 << addr))
 				chips++;
 		}
+		pdata->irq_controller =	of_property_read_bool(
+					spi->dev.of_node,
+					"interrupt-controller");
+		pdata->mirror = of_property_read_bool(spi->dev.of_node,
+						      "microchip,irq-mirror");
 	} else {
 		type = spi_get_device_id(spi)->driver_data;
 		pdata = dev_get_platdata(&spi->dev);
@@ -917,10 +924,7 @@ static int mcp23s08_probe(struct spi_device *spi)
 				return -EINVAL;
 			}
 			spi_present_mask |= 1 << addr;
-			pullups[addr] = pdata->chip[addr].pullups;
 		}
-
-		base = pdata->base;
 	}
 
 	if (!chips)
@@ -938,13 +942,13 @@ static int mcp23s08_probe(struct spi_device *spi)
 		chips--;
 		data->mcp[addr] = &data->chip[chips];
 		status = mcp23s08_probe_one(data->mcp[addr], &spi->dev, spi,
-					    0x40 | (addr << 1), type, base,
-					    pullups[addr]);
+					    0x40 | (addr << 1), type, pdata,
+					    addr);
 		if (status < 0)
 			goto fail;
 
-		if (base != -1)
-			base += (type == MCP_TYPE_S17) ? 16 : 8;
+		if (pdata->base != -1)
+			pdata->base += (type == MCP_TYPE_S17) ? 16 : 8;
 		ngpio += (type == MCP_TYPE_S17) ? 16 : 8;
 	}
 	data->ngpio = ngpio;
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 174932165fcb..415682f69214 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -857,16 +857,6 @@ static void omap_gpio_unmask_irq(struct irq_data *d)
 	spin_unlock_irqrestore(&bank->lock, flags);
 }
 
-static struct irq_chip gpio_irq_chip = {
-	.name		= "GPIO",
-	.irq_shutdown	= omap_gpio_irq_shutdown,
-	.irq_ack	= omap_gpio_ack_irq,
-	.irq_mask	= omap_gpio_mask_irq,
-	.irq_unmask	= omap_gpio_unmask_irq,
-	.irq_set_type	= omap_gpio_irq_type,
-	.irq_set_wake	= omap_gpio_wake_enable,
-};
-
 /*---------------------------------------------------------------------*/
 
 static int omap_mpuio_suspend_noirq(struct device *dev)
@@ -1088,7 +1078,7 @@ omap_mpuio_alloc_gc(struct gpio_bank *bank, unsigned int irq_start,
 			       IRQ_NOREQUEST | IRQ_NOPROBE, 0);
 }
 
-static int omap_gpio_chip_init(struct gpio_bank *bank)
+static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
 {
 	int j;
 	static int gpio;
@@ -1137,17 +1127,17 @@ static int omap_gpio_chip_init(struct gpio_bank *bank)
 	}
 #endif
 
-	ret = gpiochip_irqchip_add(&bank->chip, &gpio_irq_chip,
+	ret = gpiochip_irqchip_add(&bank->chip, irqc,
 				   irq_base, omap_gpio_irq_handler,
 				   IRQ_TYPE_NONE);
 
 	if (ret) {
 		dev_err(bank->dev, "Couldn't add irqchip to gpiochip %d\n", ret);
-		ret = gpiochip_remove(&bank->chip);
+		gpiochip_remove(&bank->chip);
 		return -ENODEV;
 	}
 
-	gpiochip_set_chained_irqchip(&bank->chip, &gpio_irq_chip,
+	gpiochip_set_chained_irqchip(&bank->chip, irqc,
 				     bank->irq, omap_gpio_irq_handler);
 
 	for (j = 0; j < bank->width; j++) {
@@ -1172,6 +1162,7 @@ static int omap_gpio_probe(struct platform_device *pdev)
 	const struct omap_gpio_platform_data *pdata;
 	struct resource *res;
 	struct gpio_bank *bank;
+	struct irq_chip *irqc;
 	int ret;
 
 	match = of_match_device(of_match_ptr(omap_gpio_match), dev);
@@ -1186,6 +1177,18 @@ static int omap_gpio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	irqc = devm_kzalloc(dev, sizeof(*irqc), GFP_KERNEL);
+	if (!irqc)
+		return -ENOMEM;
+
+	irqc->irq_shutdown = omap_gpio_irq_shutdown,
+	irqc->irq_ack = omap_gpio_ack_irq,
+	irqc->irq_mask = omap_gpio_mask_irq,
+	irqc->irq_unmask = omap_gpio_unmask_irq,
+	irqc->irq_set_type = omap_gpio_irq_type,
+	irqc->irq_set_wake = omap_gpio_wake_enable,
+	irqc->name = dev_name(&pdev->dev);
+
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (unlikely(!res)) {
 		dev_err(dev, "Invalid IRQ resource\n");
@@ -1241,7 +1244,7 @@ static int omap_gpio_probe(struct platform_device *pdev)
 
 	omap_gpio_mod_init(bank);
 
-	ret = omap_gpio_chip_init(bank);
+	ret = omap_gpio_chip_init(bank, irqc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index f9961eea2120..e2da64abbccd 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -520,7 +520,7 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 	struct i2c_client *client = chip->client;
 	int ret, i, offset = 0;
 
-	if (irq_base != -1
+	if (client->irq && irq_base != -1
 			&& (id->driver_data & PCA_INT)) {
 
 		switch (chip->chip_type) {
@@ -586,50 +586,6 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 }
 #endif
 
-/*
- * Handlers for alternative sources of platform_data
- */
-#ifdef CONFIG_OF_GPIO
-/*
- * Translate OpenFirmware node properties into platform_data
- * WARNING: This is DEPRECATED and will be removed eventually!
- */
-static void
-pca953x_get_alt_pdata(struct i2c_client *client, int *gpio_base, u32 *invert)
-{
-	struct device_node *node;
-	const __be32 *val;
-	int size;
-
-	*gpio_base = -1;
-
-	node = client->dev.of_node;
-	if (node == NULL)
-		return;
-
-	val = of_get_property(node, "linux,gpio-base", &size);
-	WARN(val, "%s: device-tree property 'linux,gpio-base' is deprecated!", __func__);
-	if (val) {
-		if (size != sizeof(*val))
-			dev_warn(&client->dev, "%s: wrong linux,gpio-base\n",
-				 node->full_name);
-		else
-			*gpio_base = be32_to_cpup(val);
-	}
-
-	val = of_get_property(node, "polarity", NULL);
-	WARN(val, "%s: device-tree property 'polarity' is deprecated!", __func__);
-	if (val)
-		*invert = *val;
-}
-#else
-static void
-pca953x_get_alt_pdata(struct i2c_client *client, int *gpio_base, u32 *invert)
-{
-	*gpio_base = -1;
-}
-#endif
-
 static int device_pca953x_init(struct pca953x_chip *chip, u32 invert)
 {
 	int ret;
@@ -704,12 +660,8 @@ static int pca953x_probe(struct i2c_client *client,
 		invert = pdata->invert;
 		chip->names = pdata->names;
 	} else {
-		pca953x_get_alt_pdata(client, &chip->gpio_start, &invert);
-#ifdef CONFIG_OF_GPIO
-		/* If I2C node has no interrupts property, disable GPIO interrupts */
-		if (of_find_property(client->dev.of_node, "interrupts", NULL) == NULL)
-			irq_base = -1;
-#endif
+		chip->gpio_start = -1;
+		irq_base = 0;
 	}
 
 	chip->client = client;
diff --git a/drivers/gpio/gpio-pch.c b/drivers/gpio/gpio-pch.c
index e0ac549dccb5..2d9a950ca2d4 100644
--- a/drivers/gpio/gpio-pch.c
+++ b/drivers/gpio/gpio-pch.c
@@ -171,6 +171,7 @@ static int pch_gpio_direction_input(struct gpio_chip *gpio, unsigned nr)
 	return 0;
 }
 
+#ifdef CONFIG_PM
 /*
  * Save register configuration and disable interrupts.
  */
@@ -206,6 +207,7 @@ static void pch_gpio_restore_reg_conf(struct pch_gpio *chip)
 		iowrite32(chip->pch_gpio_reg.gpio_use_sel_reg,
 			  &chip->reg->gpio_use_sel);
 }
+#endif
 
 static int pch_gpio_to_irq(struct gpio_chip *gpio, unsigned offset)
 {
diff --git a/drivers/gpio/gpio-samsung.c b/drivers/gpio/gpio-samsung.c
index 3810da47043f..7c288ba4dc87 100644
--- a/drivers/gpio/gpio-samsung.c
+++ b/drivers/gpio/gpio-samsung.c
@@ -1309,56 +1309,6 @@ samsung_gpio_pull_t s3c_gpio_getpull(unsigned int pin)
 }
 EXPORT_SYMBOL(s3c_gpio_getpull);
 
-#ifdef CONFIG_S5P_GPIO_DRVSTR
-s5p_gpio_drvstr_t s5p_gpio_get_drvstr(unsigned int pin)
-{
-	struct samsung_gpio_chip *chip = samsung_gpiolib_getchip(pin);
-	unsigned int off;
-	void __iomem *reg;
-	int shift;
-	u32 drvstr;
-
-	if (!chip)
-		return -EINVAL;
-
-	off = pin - chip->chip.base;
-	shift = off * 2;
-	reg = chip->base + 0x0C;
-
-	drvstr = __raw_readl(reg);
-	drvstr = drvstr >> shift;
-	drvstr &= 0x3;
-
-	return (__force s5p_gpio_drvstr_t)drvstr;
-}
-EXPORT_SYMBOL(s5p_gpio_get_drvstr);
-
-int s5p_gpio_set_drvstr(unsigned int pin, s5p_gpio_drvstr_t drvstr)
-{
-	struct samsung_gpio_chip *chip = samsung_gpiolib_getchip(pin);
-	unsigned int off;
-	void __iomem *reg;
-	int shift;
-	u32 tmp;
-
-	if (!chip)
-		return -EINVAL;
-
-	off = pin - chip->chip.base;
-	shift = off * 2;
-	reg = chip->base + 0x0C;
-
-	tmp = __raw_readl(reg);
-	tmp &= ~(0x3 << shift);
-	tmp |= drvstr << shift;
-
-	__raw_writel(tmp, reg);
-
-	return 0;
-}
-EXPORT_SYMBOL(s5p_gpio_set_drvstr);
-#endif	/* CONFIG_S5P_GPIO_DRVSTR */
-
 #ifdef CONFIG_PLAT_S3C24XX
 unsigned int s3c2410_modify_misccr(unsigned int clear, unsigned int change)
 {
diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index 845025a57240..85c5b1974294 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -13,6 +13,7 @@
 #include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/mfd/stmpe.h>
+#include <linux/seq_file.h>
 
 /*
  * These registers are modified under the irq bus lock and cached to avoid
@@ -127,19 +128,19 @@ static int stmpe_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	int regoffset = offset / 8;
 	int mask = 1 << (offset % 8);
 
-	if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_LEVEL_HIGH)
+	if (type & IRQ_TYPE_LEVEL_LOW || type & IRQ_TYPE_LEVEL_HIGH)
 		return -EINVAL;
 
 	/* STMPE801 doesn't have RE and FE registers */
 	if (stmpe_gpio->stmpe->partnum == STMPE801)
 		return 0;
 
-	if (type == IRQ_TYPE_EDGE_RISING)
+	if (type & IRQ_TYPE_EDGE_RISING)
 		stmpe_gpio->regs[REG_RE][regoffset] |= mask;
 	else
 		stmpe_gpio->regs[REG_RE][regoffset] &= ~mask;
 
-	if (type == IRQ_TYPE_EDGE_FALLING)
+	if (type & IRQ_TYPE_EDGE_FALLING)
 		stmpe_gpio->regs[REG_FE][regoffset] |= mask;
 	else
 		stmpe_gpio->regs[REG_FE][regoffset] &= ~mask;
@@ -211,6 +212,77 @@ static void stmpe_gpio_irq_unmask(struct irq_data *d)
 	stmpe_gpio->regs[REG_IE][regoffset] |= mask;
 }
 
+static void stmpe_dbg_show_one(struct seq_file *s,
+			       struct gpio_chip *gc,
+			       unsigned offset, unsigned gpio)
+{
+	struct stmpe_gpio *stmpe_gpio = to_stmpe_gpio(gc);
+	struct stmpe *stmpe = stmpe_gpio->stmpe;
+	const char *label = gpiochip_is_requested(gc, offset);
+	int num_banks = DIV_ROUND_UP(stmpe->num_gpios, 8);
+	bool val = !!stmpe_gpio_get(gc, offset);
+	u8 dir_reg = stmpe->regs[STMPE_IDX_GPDR_LSB] - (offset / 8);
+	u8 mask = 1 << (offset % 8);
+	int ret;
+	u8 dir;
+
+	ret = stmpe_reg_read(stmpe, dir_reg);
+	if (ret < 0)
+		return;
+	dir = !!(ret & mask);
+
+	if (dir) {
+		seq_printf(s, " gpio-%-3d (%-20.20s) out %s",
+			   gpio, label ?: "(none)",
+			   val ? "hi" : "lo");
+	} else {
+		u8 edge_det_reg = stmpe->regs[STMPE_IDX_GPEDR_MSB] + num_banks - 1 - (offset / 8);
+		u8 rise_reg = stmpe->regs[STMPE_IDX_GPRER_LSB] - (offset / 8);
+		u8 fall_reg = stmpe->regs[STMPE_IDX_GPFER_LSB] - (offset / 8);
+		u8 irqen_reg = stmpe->regs[STMPE_IDX_IEGPIOR_LSB] - (offset / 8);
+		bool edge_det;
+		bool rise;
+		bool fall;
+		bool irqen;
+
+		ret = stmpe_reg_read(stmpe, edge_det_reg);
+		if (ret < 0)
+			return;
+		edge_det = !!(ret & mask);
+		ret = stmpe_reg_read(stmpe, rise_reg);
+		if (ret < 0)
+			return;
+		rise = !!(ret & mask);
+		ret = stmpe_reg_read(stmpe, fall_reg);
+		if (ret < 0)
+			return;
+		fall = !!(ret & mask);
+		ret = stmpe_reg_read(stmpe, irqen_reg);
+		if (ret < 0)
+			return;
+		irqen = !!(ret & mask);
+
+		seq_printf(s, " gpio-%-3d (%-20.20s) in  %s %s %s%s%s",
+			   gpio, label ?: "(none)",
+			   val ? "hi" : "lo",
+			   edge_det ? "edge-asserted" : "edge-inactive",
+			   irqen ? "IRQ-enabled" : "",
+			   rise ? " rising-edge-detection" : "",
+			   fall ? " falling-edge-detection" : "");
+	}
+}
+
+static void stmpe_dbg_show(struct seq_file *s, struct gpio_chip *gc)
+{
+	unsigned i;
+	unsigned gpio = gc->base;
+
+	for (i = 0; i < gc->ngpio; i++, gpio++) {
+		stmpe_dbg_show_one(s, gc, i, gpio);
+		seq_printf(s, "\n");
+	}
+}
+
 static struct irq_chip stmpe_gpio_irq_chip = {
 	.name			= "stmpe-gpio",
 	.irq_bus_lock		= stmpe_gpio_irq_lock,
@@ -293,6 +365,9 @@ static int stmpe_gpio_probe(struct platform_device *pdev)
 #endif
 	stmpe_gpio->chip.base = -1;
 
+	if (IS_ENABLED(CONFIG_DEBUG_FS))
+                stmpe_gpio->chip.dbg_show = stmpe_dbg_show;
+
 	if (pdata)
 		stmpe_gpio->norequest_mask = pdata->norequest_mask;
 	else if (np)
@@ -308,6 +383,12 @@ static int stmpe_gpio_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_free;
 
+	ret = gpiochip_add(&stmpe_gpio->chip);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to add gpiochip: %d\n", ret);
+		goto out_disable;
+	}
+
 	if (irq > 0) {
 		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
 				stmpe_gpio_irq, IRQF_ONESHOT,
@@ -324,14 +405,13 @@ static int stmpe_gpio_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev,
 				"could not connect irqchip to gpiochip\n");
-			return ret;
+			goto out_disable;
 		}
-	}
 
-	ret = gpiochip_add(&stmpe_gpio->chip);
-	if (ret) {
-		dev_err(&pdev->dev, "unable to add gpiochip: %d\n", ret);
-		goto out_disable;
+		gpiochip_set_chained_irqchip(&stmpe_gpio->chip,
+					     &stmpe_gpio_irq_chip,
+					     irq,
+					     NULL);
 	}
 
 	if (pdata && pdata->setup)
@@ -343,6 +423,7 @@ static int stmpe_gpio_probe(struct platform_device *pdev)
 
 out_disable:
 	stmpe_disable(stmpe, STMPE_BLOCK_GPIO);
+	gpiochip_remove(&stmpe_gpio->chip);
 out_free:
 	kfree(stmpe_gpio);
 	return ret;
diff --git a/drivers/gpio/gpio-stp-xway.c b/drivers/gpio/gpio-stp-xway.c
index 04882a911b65..7e359b7cce1b 100644
--- a/drivers/gpio/gpio-stp-xway.c
+++ b/drivers/gpio/gpio-stp-xway.c
@@ -292,7 +292,7 @@ static struct platform_driver xway_stp_driver = {
 	},
 };
 
-int __init xway_stp_init(void)
+static int __init xway_stp_init(void)
 {
 	return platform_driver_register(&xway_stp_driver);
 }
diff --git a/drivers/gpio/gpio-syscon.c b/drivers/gpio/gpio-syscon.c
index 30884fbc750d..e82fde4b6898 100644
--- a/drivers/gpio/gpio-syscon.c
+++ b/drivers/gpio/gpio-syscon.c
@@ -37,6 +37,8 @@
  * dat_bit_offset:	Offset (in bits) to the first GPIO bit.
  * dir_bit_offset:	Optional offset (in bits) to the first bit to switch
  *			GPIO direction (Used with GPIO_SYSCON_FEAT_DIR flag).
+ * set:		HW specific callback to assigns output value
+ *			for signal "offset"
  */
 
 struct syscon_gpio_data {
@@ -45,12 +47,16 @@ struct syscon_gpio_data {
 	unsigned int	bit_count;
 	unsigned int	dat_bit_offset;
 	unsigned int	dir_bit_offset;
+	void		(*set)(struct gpio_chip *chip,
+			       unsigned offset, int value);
 };
 
 struct syscon_gpio_priv {
 	struct gpio_chip		chip;
 	struct regmap			*syscon;
 	const struct syscon_gpio_data	*data;
+	u32				dreg_offset;
+	u32				dir_reg_offset;
 };
 
 static inline struct syscon_gpio_priv *to_syscon_gpio(struct gpio_chip *chip)
@@ -61,9 +67,11 @@ static inline struct syscon_gpio_priv *to_syscon_gpio(struct gpio_chip *chip)
 static int syscon_gpio_get(struct gpio_chip *chip, unsigned offset)
 {
 	struct syscon_gpio_priv *priv = to_syscon_gpio(chip);
-	unsigned int val, offs = priv->data->dat_bit_offset + offset;
+	unsigned int val, offs;
 	int ret;
 
+	offs = priv->dreg_offset + priv->data->dat_bit_offset + offset;
+
 	ret = regmap_read(priv->syscon,
 			  (offs / SYSCON_REG_BITS) * SYSCON_REG_SIZE, &val);
 	if (ret)
@@ -75,7 +83,9 @@ static int syscon_gpio_get(struct gpio_chip *chip, unsigned offset)
 static void syscon_gpio_set(struct gpio_chip *chip, unsigned offset, int val)
 {
 	struct syscon_gpio_priv *priv = to_syscon_gpio(chip);
-	unsigned int offs = priv->data->dat_bit_offset + offset;
+	unsigned int offs;
+
+	offs = priv->dreg_offset + priv->data->dat_bit_offset + offset;
 
 	regmap_update_bits(priv->syscon,
 			   (offs / SYSCON_REG_BITS) * SYSCON_REG_SIZE,
@@ -88,7 +98,10 @@ static int syscon_gpio_dir_in(struct gpio_chip *chip, unsigned offset)
 	struct syscon_gpio_priv *priv = to_syscon_gpio(chip);
 
 	if (priv->data->flags & GPIO_SYSCON_FEAT_DIR) {
-		unsigned int offs = priv->data->dir_bit_offset + offset;
+		unsigned int offs;
+
+		offs = priv->dir_reg_offset +
+		       priv->data->dir_bit_offset + offset;
 
 		regmap_update_bits(priv->syscon,
 				   (offs / SYSCON_REG_BITS) * SYSCON_REG_SIZE,
@@ -103,7 +116,10 @@ static int syscon_gpio_dir_out(struct gpio_chip *chip, unsigned offset, int val)
 	struct syscon_gpio_priv *priv = to_syscon_gpio(chip);
 
 	if (priv->data->flags & GPIO_SYSCON_FEAT_DIR) {
-		unsigned int offs = priv->data->dir_bit_offset + offset;
+		unsigned int offs;
+
+		offs = priv->dir_reg_offset +
+		       priv->data->dir_bit_offset + offset;
 
 		regmap_update_bits(priv->syscon,
 				   (offs / SYSCON_REG_BITS) * SYSCON_REG_SIZE,
@@ -111,7 +127,7 @@ static int syscon_gpio_dir_out(struct gpio_chip *chip, unsigned offset, int val)
 				   BIT(offs % SYSCON_REG_BITS));
 	}
 
-	syscon_gpio_set(chip, offset, val);
+	priv->data->set(chip, offset, val);
 
 	return 0;
 }
@@ -124,11 +140,46 @@ static const struct syscon_gpio_data clps711x_mctrl_gpio = {
 	.dat_bit_offset	= 0x40 * 8 + 8,
 };
 
+#define KEYSTONE_LOCK_BIT BIT(0)
+
+static void keystone_gpio_set(struct gpio_chip *chip, unsigned offset, int val)
+{
+	struct syscon_gpio_priv *priv = to_syscon_gpio(chip);
+	unsigned int offs;
+	int ret;
+
+	offs = priv->dreg_offset + priv->data->dat_bit_offset + offset;
+
+	if (!val)
+		return;
+
+	ret = regmap_update_bits(
+			priv->syscon,
+			(offs / SYSCON_REG_BITS) * SYSCON_REG_SIZE,
+			BIT(offs % SYSCON_REG_BITS) | KEYSTONE_LOCK_BIT,
+			BIT(offs % SYSCON_REG_BITS) | KEYSTONE_LOCK_BIT);
+	if (ret < 0)
+		dev_err(chip->dev, "gpio write failed ret(%d)\n", ret);
+}
+
+static const struct syscon_gpio_data keystone_dsp_gpio = {
+	/* ARM Keystone 2 */
+	.compatible	= NULL,
+	.flags		= GPIO_SYSCON_FEAT_OUT,
+	.bit_count	= 28,
+	.dat_bit_offset	= 4,
+	.set		= keystone_gpio_set,
+};
+
 static const struct of_device_id syscon_gpio_ids[] = {
 	{
 		.compatible	= "cirrus,clps711x-mctrl-gpio",
 		.data		= &clps711x_mctrl_gpio,
 	},
+	{
+		.compatible	= "ti,keystone-dsp-gpio",
+		.data		= &keystone_dsp_gpio,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, syscon_gpio_ids);
@@ -138,6 +189,8 @@ static int syscon_gpio_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	const struct of_device_id *of_id = of_match_device(syscon_gpio_ids, dev);
 	struct syscon_gpio_priv *priv;
+	struct device_node *np = dev->of_node;
+	int ret;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -145,10 +198,31 @@ static int syscon_gpio_probe(struct platform_device *pdev)
 
 	priv->data = of_id->data;
 
-	priv->syscon =
-		syscon_regmap_lookup_by_compatible(priv->data->compatible);
-	if (IS_ERR(priv->syscon))
-		return PTR_ERR(priv->syscon);
+	if (priv->data->compatible) {
+		priv->syscon = syscon_regmap_lookup_by_compatible(
+					priv->data->compatible);
+		if (IS_ERR(priv->syscon))
+			return PTR_ERR(priv->syscon);
+	} else {
+		priv->syscon =
+			syscon_regmap_lookup_by_phandle(np, "gpio,syscon-dev");
+		if (IS_ERR(priv->syscon))
+			return PTR_ERR(priv->syscon);
+
+		ret = of_property_read_u32_index(np, "gpio,syscon-dev", 1,
+						 &priv->dreg_offset);
+		if (ret)
+			dev_err(dev, "can't read the data register offset!\n");
+
+		priv->dreg_offset <<= 3;
+
+		ret = of_property_read_u32_index(np, "gpio,syscon-dev", 2,
+						 &priv->dir_reg_offset);
+		if (ret)
+			dev_err(dev, "can't read the dir register offset!\n");
+
+		priv->dir_reg_offset <<= 3;
+	}
 
 	priv->chip.dev = dev;
 	priv->chip.owner = THIS_MODULE;
@@ -159,7 +233,7 @@ static int syscon_gpio_probe(struct platform_device *pdev)
 	if (priv->data->flags & GPIO_SYSCON_FEAT_IN)
 		priv->chip.direction_input = syscon_gpio_dir_in;
 	if (priv->data->flags & GPIO_SYSCON_FEAT_OUT) {
-		priv->chip.set = syscon_gpio_set;
+		priv->chip.set = priv->data->set ? : syscon_gpio_set;
 		priv->chip.direction_output = syscon_gpio_dir_out;
 	}
 
diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c
index 7324869c38e0..ae0f6466eb09 100644
--- a/drivers/gpio/gpio-tc3589x.c
+++ b/drivers/gpio/gpio-tc3589x.c
@@ -300,6 +300,11 @@ static int tc3589x_gpio_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	gpiochip_set_chained_irqchip(&tc3589x_gpio->chip,
+				     &tc3589x_gpio_irq_chip,
+				     irq,
+				     NULL);
+
 	if (pdata && pdata->setup)
 		pdata->setup(tc3589x, tc3589x_gpio->chip.base);
 
diff --git a/drivers/gpio/gpio-xgene.c b/drivers/gpio/gpio-xgene.c
new file mode 100644
index 000000000000..7d489221dc1f
--- /dev/null
+++ b/drivers/gpio/gpio-xgene.c
@@ -0,0 +1,244 @@
+/*
+ * AppliedMicro X-Gene SoC GPIO Driver
+ *
+ * Copyright (c) 2014, Applied Micro Circuits Corporation
+ * Author: Feng Kan <fkan@apm.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/platform_device.h>
+#include <linux/gpio/driver.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+
+#define GPIO_SET_DR_OFFSET	0x0C
+#define GPIO_DATA_OFFSET	0x14
+#define GPIO_BANK_STRIDE	0x0C
+
+#define XGENE_GPIOS_PER_BANK	16
+#define XGENE_MAX_GPIO_BANKS	3
+#define XGENE_MAX_GPIOS		(XGENE_GPIOS_PER_BANK * XGENE_MAX_GPIO_BANKS)
+
+#define GPIO_BIT_OFFSET(x)	(x % XGENE_GPIOS_PER_BANK)
+#define GPIO_BANK_OFFSET(x)	((x / XGENE_GPIOS_PER_BANK) * GPIO_BANK_STRIDE)
+
+struct xgene_gpio {
+	struct gpio_chip	chip;
+	void __iomem		*base;
+	spinlock_t		lock;
+#ifdef CONFIG_PM
+	u32			set_dr_val[XGENE_MAX_GPIO_BANKS];
+#endif
+};
+
+static inline struct xgene_gpio *to_xgene_gpio(struct gpio_chip *chip)
+{
+	return container_of(chip, struct xgene_gpio, chip);
+}
+
+static int xgene_gpio_get(struct gpio_chip *gc, unsigned int offset)
+{
+	struct xgene_gpio *chip = to_xgene_gpio(gc);
+	unsigned long bank_offset;
+	u32 bit_offset;
+
+	bank_offset = GPIO_DATA_OFFSET + GPIO_BANK_OFFSET(offset);
+	bit_offset = GPIO_BIT_OFFSET(offset);
+	return !!(ioread32(chip->base + bank_offset) & BIT(bit_offset));
+}
+
+static void __xgene_gpio_set(struct gpio_chip *gc, unsigned int offset, int val)
+{
+	struct xgene_gpio *chip = to_xgene_gpio(gc);
+	unsigned long bank_offset;
+	u32 setval, bit_offset;
+
+	bank_offset = GPIO_SET_DR_OFFSET + GPIO_BANK_OFFSET(offset);
+	bit_offset = GPIO_BIT_OFFSET(offset) + XGENE_GPIOS_PER_BANK;
+
+	setval = ioread32(chip->base + bank_offset);
+	if (val)
+		setval |= BIT(bit_offset);
+	else
+		setval &= ~BIT(bit_offset);
+	iowrite32(setval, chip->base + bank_offset);
+}
+
+static void xgene_gpio_set(struct gpio_chip *gc, unsigned int offset, int val)
+{
+	struct xgene_gpio *chip = to_xgene_gpio(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	__xgene_gpio_set(gc, offset, val);
+	spin_unlock_irqrestore(&chip->lock, flags);
+}
+
+static int xgene_gpio_dir_in(struct gpio_chip *gc, unsigned int offset)
+{
+	struct xgene_gpio *chip = to_xgene_gpio(gc);
+	unsigned long flags, bank_offset;
+	u32 dirval, bit_offset;
+
+	bank_offset = GPIO_SET_DR_OFFSET + GPIO_BANK_OFFSET(offset);
+	bit_offset = GPIO_BIT_OFFSET(offset);
+
+	spin_lock_irqsave(&chip->lock, flags);
+
+	dirval = ioread32(chip->base + bank_offset);
+	dirval |= BIT(bit_offset);
+	iowrite32(dirval, chip->base + bank_offset);
+
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	return 0;
+}
+
+static int xgene_gpio_dir_out(struct gpio_chip *gc,
+					unsigned int offset, int val)
+{
+	struct xgene_gpio *chip = to_xgene_gpio(gc);
+	unsigned long flags, bank_offset;
+	u32 dirval, bit_offset;
+
+	bank_offset = GPIO_SET_DR_OFFSET + GPIO_BANK_OFFSET(offset);
+	bit_offset = GPIO_BIT_OFFSET(offset);
+
+	spin_lock_irqsave(&chip->lock, flags);
+
+	dirval = ioread32(chip->base + bank_offset);
+	dirval &= ~BIT(bit_offset);
+	iowrite32(dirval, chip->base + bank_offset);
+	__xgene_gpio_set(gc, offset, val);
+
+	spin_unlock_irqrestore(&chip->lock, flags);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int xgene_gpio_suspend(struct device *dev)
+{
+	struct xgene_gpio *gpio = dev_get_drvdata(dev);
+	unsigned long bank_offset;
+	unsigned int bank;
+
+	for (bank = 0; bank < XGENE_MAX_GPIO_BANKS; bank++) {
+		bank_offset = GPIO_SET_DR_OFFSET + bank * GPIO_BANK_STRIDE;
+		gpio->set_dr_val[bank] = ioread32(gpio->base + bank_offset);
+	}
+	return 0;
+}
+
+static int xgene_gpio_resume(struct device *dev)
+{
+	struct xgene_gpio *gpio = dev_get_drvdata(dev);
+	unsigned long bank_offset;
+	unsigned int bank;
+
+	for (bank = 0; bank < XGENE_MAX_GPIO_BANKS; bank++) {
+		bank_offset = GPIO_SET_DR_OFFSET + bank * GPIO_BANK_STRIDE;
+		iowrite32(gpio->set_dr_val[bank], gpio->base + bank_offset);
+	}
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(xgene_gpio_pm, xgene_gpio_suspend, xgene_gpio_resume);
+#define XGENE_GPIO_PM_OPS	(&xgene_gpio_pm)
+#else
+#define XGENE_GPIO_PM_OPS	NULL
+#endif
+
+static int xgene_gpio_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	struct xgene_gpio *gpio;
+	int err = 0;
+
+	gpio = devm_kzalloc(&pdev->dev, sizeof(*gpio), GFP_KERNEL);
+	if (!gpio) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	gpio->base = devm_ioremap_nocache(&pdev->dev, res->start,
+							resource_size(res));
+	if (!gpio->base) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	gpio->chip.ngpio = XGENE_MAX_GPIOS;
+
+	spin_lock_init(&gpio->lock);
+	gpio->chip.dev = &pdev->dev;
+	gpio->chip.direction_input = xgene_gpio_dir_in;
+	gpio->chip.direction_output = xgene_gpio_dir_out;
+	gpio->chip.get = xgene_gpio_get;
+	gpio->chip.set = xgene_gpio_set;
+	gpio->chip.label = dev_name(&pdev->dev);
+	gpio->chip.base = -1;
+
+	platform_set_drvdata(pdev, gpio);
+
+	err = gpiochip_add(&gpio->chip);
+	if (err) {
+		dev_err(&pdev->dev,
+			"failed to register gpiochip.\n");
+		goto err;
+	}
+
+	dev_info(&pdev->dev, "X-Gene GPIO driver registered.\n");
+	return 0;
+err:
+	dev_err(&pdev->dev, "X-Gene GPIO driver registration failed.\n");
+	return err;
+}
+
+static int xgene_gpio_remove(struct platform_device *pdev)
+{
+	struct xgene_gpio *gpio = platform_get_drvdata(pdev);
+
+	gpiochip_remove(&gpio->chip);
+	return 0;
+}
+
+static const struct of_device_id xgene_gpio_of_match[] = {
+	{ .compatible = "apm,xgene-gpio", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, xgene_gpio_of_match);
+
+static struct platform_driver xgene_gpio_driver = {
+	.driver = {
+		.name = "xgene-gpio",
+		.owner = THIS_MODULE,
+		.of_match_table = xgene_gpio_of_match,
+		.pm     = XGENE_GPIO_PM_OPS,
+	},
+	.probe = xgene_gpio_probe,
+	.remove = xgene_gpio_remove,
+};
+
+module_platform_driver(xgene_gpio_driver);
+
+MODULE_AUTHOR("Feng Kan <fkan@apm.com>");
+MODULE_DESCRIPTION("APM X-Gene GPIO driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c
index 12481867daf1..ba18b06c9a21 100644
--- a/drivers/gpio/gpio-xilinx.c
+++ b/drivers/gpio/gpio-xilinx.c
@@ -197,6 +197,7 @@ static int xgpio_of_probe(struct device_node *np)
 	struct xgpio_instance *chip;
 	int status = 0;
 	const u32 *tree_info;
+	u32 ngpio;
 
 	chip = kzalloc(sizeof(*chip), GFP_KERNEL);
 	if (!chip)
@@ -211,12 +212,13 @@ static int xgpio_of_probe(struct device_node *np)
 	/* Update GPIO direction shadow register with default value */
 	of_property_read_u32(np, "xlnx,tri-default", &chip->gpio_dir);
 
-	/* By default assume full GPIO controller */
-	chip->mmchip.gc.ngpio = 32;
-
-	/* Check device node and parent device node for device width */
-	of_property_read_u32(np, "xlnx,gpio-width",
-			      (u32 *)&chip->mmchip.gc.ngpio);
+	/*
+	 * Check device node and parent device node for device width
+	 * and assume default width of 32
+	 */
+	if (of_property_read_u32(np, "xlnx,gpio-width", &ngpio))
+		ngpio = 32;
+	chip->mmchip.gc.ngpio = (u16)ngpio;
 
 	spin_lock_init(&chip->gpio_lock);
 
@@ -258,12 +260,13 @@ static int xgpio_of_probe(struct device_node *np)
 		/* Update GPIO direction shadow register with default value */
 		of_property_read_u32(np, "xlnx,tri-default-2", &chip->gpio_dir);
 
-		/* By default assume full GPIO controller */
-		chip->mmchip.gc.ngpio = 32;
-
-		/* Check device node and parent device node for device width */
-		of_property_read_u32(np, "xlnx,gpio2-width",
-				     (u32 *)&chip->mmchip.gc.ngpio);
+		/*
+		 * Check device node and parent device node for device width
+		 * and assume default width of 32
+		 */
+		if (of_property_read_u32(np, "xlnx,gpio2-width", &ngpio))
+			ngpio = 32;
+		chip->mmchip.gc.ngpio = (u16)ngpio;
 
 		spin_lock_init(&chip->gpio_lock);
 
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index 31ad5df5dbc9..74cd480bf8de 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -88,16 +88,17 @@
  * @chip:	instance of the gpio_chip
  * @base_addr:	base address of the GPIO device
  * @clk:	clock resource for this controller
+ * @irq:	interrupt for the GPIO device
  */
 struct zynq_gpio {
 	struct gpio_chip chip;
 	void __iomem *base_addr;
 	struct clk *clk;
+	int irq;
 };
 
 static struct irq_chip zynq_gpio_level_irqchip;
 static struct irq_chip zynq_gpio_edge_irqchip;
-
 /**
  * zynq_gpio_get_bank_pin - Get the bank number and pin number within that bank
  * for a given pin in the GPIO device
@@ -138,6 +139,13 @@ static inline void zynq_gpio_get_bank_pin(unsigned int pin_num,
 	}
 }
 
+static const unsigned int zynq_gpio_bank_offset[] = {
+	ZYNQ_GPIO_BANK0_PIN_MIN,
+	ZYNQ_GPIO_BANK1_PIN_MIN,
+	ZYNQ_GPIO_BANK2_PIN_MIN,
+	ZYNQ_GPIO_BANK3_PIN_MIN,
+};
+
 /**
  * zynq_gpio_get_value - Get the state of the specified pin of GPIO device
  * @chip:	gpio_chip instance to be worked on
@@ -427,10 +435,9 @@ static int zynq_gpio_set_irq_type(struct irq_data *irq_data, unsigned int type)
 
 static int zynq_gpio_set_wake(struct irq_data *data, unsigned int on)
 {
-	if (on)
-		zynq_gpio_irq_unmask(data);
-	else
-		zynq_gpio_irq_mask(data);
+	struct zynq_gpio *gpio = irq_data_get_irq_chip_data(data);
+
+	irq_set_irq_wake(gpio->irq, on);
 
 	return 0;
 }
@@ -444,7 +451,8 @@ static struct irq_chip zynq_gpio_level_irqchip = {
 	.irq_unmask	= zynq_gpio_irq_unmask,
 	.irq_set_type	= zynq_gpio_set_irq_type,
 	.irq_set_wake	= zynq_gpio_set_wake,
-	.flags		= IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED,
+	.flags		= IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED |
+			  IRQCHIP_MASK_ON_SUSPEND,
 };
 
 static struct irq_chip zynq_gpio_edge_irqchip = {
@@ -455,8 +463,28 @@ static struct irq_chip zynq_gpio_edge_irqchip = {
 	.irq_unmask	= zynq_gpio_irq_unmask,
 	.irq_set_type	= zynq_gpio_set_irq_type,
 	.irq_set_wake	= zynq_gpio_set_wake,
+	.flags		= IRQCHIP_MASK_ON_SUSPEND,
 };
 
+static void zynq_gpio_handle_bank_irq(struct zynq_gpio *gpio,
+				      unsigned int bank_num,
+				      unsigned long pending)
+{
+	unsigned int bank_offset = zynq_gpio_bank_offset[bank_num];
+	struct irq_domain *irqdomain = gpio->chip.irqdomain;
+	int offset;
+
+	if (!pending)
+		return;
+
+	for_each_set_bit(offset, &pending, 32) {
+		unsigned int gpio_irq;
+
+		gpio_irq = irq_find_mapping(irqdomain, offset + bank_offset);
+		generic_handle_irq(gpio_irq);
+	}
+}
+
 /**
  * zynq_gpio_irqhandler - IRQ handler for the gpio banks of a gpio device
  * @irq:	irq number of the gpio bank where interrupt has occurred
@@ -482,18 +510,7 @@ static void zynq_gpio_irqhandler(unsigned int irq, struct irq_desc *desc)
 					ZYNQ_GPIO_INTSTS_OFFSET(bank_num));
 		int_enb = readl_relaxed(gpio->base_addr +
 					ZYNQ_GPIO_INTMASK_OFFSET(bank_num));
-		int_sts &= ~int_enb;
-		if (int_sts) {
-			int offset;
-			unsigned long pending = int_sts;
-
-			for_each_set_bit(offset, &pending, 32) {
-				unsigned int gpio_irq =
-					irq_find_mapping(gpio->chip.irqdomain,
-							offset);
-				generic_handle_irq(gpio_irq);
-			}
-		}
+		zynq_gpio_handle_bank_irq(gpio, bank_num, int_sts & ~int_enb);
 	}
 
 	chained_irq_exit(irqchip, desc);
@@ -501,7 +518,11 @@ static void zynq_gpio_irqhandler(unsigned int irq, struct irq_desc *desc)
 
 static int __maybe_unused zynq_gpio_suspend(struct device *dev)
 {
-	if (!device_may_wakeup(dev))
+	struct platform_device *pdev = to_platform_device(dev);
+	int irq = platform_get_irq(pdev, 0);
+	struct irq_data *data = irq_get_irq_data(irq);
+
+	if (!irqd_is_wakeup_set(data))
 		return pm_runtime_force_suspend(dev);
 
 	return 0;
@@ -509,7 +530,11 @@ static int __maybe_unused zynq_gpio_suspend(struct device *dev)
 
 static int __maybe_unused zynq_gpio_resume(struct device *dev)
 {
-	if (!device_may_wakeup(dev))
+	struct platform_device *pdev = to_platform_device(dev);
+	int irq = platform_get_irq(pdev, 0);
+	struct irq_data *data = irq_get_irq_data(irq);
+
+	if (!irqd_is_wakeup_set(data))
 		return pm_runtime_force_resume(dev);
 
 	return 0;
@@ -570,7 +595,7 @@ static const struct dev_pm_ops zynq_gpio_dev_pm_ops = {
  */
 static int zynq_gpio_probe(struct platform_device *pdev)
 {
-	int ret, bank_num, irq;
+	int ret, bank_num;
 	struct zynq_gpio *gpio;
 	struct gpio_chip *chip;
 	struct resource *res;
@@ -586,10 +611,10 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 	if (IS_ERR(gpio->base_addr))
 		return PTR_ERR(gpio->base_addr);
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
+	gpio->irq = platform_get_irq(pdev, 0);
+	if (gpio->irq < 0) {
 		dev_err(&pdev->dev, "invalid IRQ\n");
-		return irq;
+		return gpio->irq;
 	}
 
 	/* configure the gpio chip */
@@ -637,19 +662,16 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 		goto err_rm_gpiochip;
 	}
 
-	gpiochip_set_chained_irqchip(chip, &zynq_gpio_edge_irqchip, irq,
+	gpiochip_set_chained_irqchip(chip, &zynq_gpio_edge_irqchip, gpio->irq,
 				     zynq_gpio_irqhandler);
 
 	pm_runtime_set_active(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
-	device_set_wakeup_capable(&pdev->dev, 1);
-
 	return 0;
 
 err_rm_gpiochip:
-	if (gpiochip_remove(chip))
-		dev_err(&pdev->dev, "Failed to remove gpio chip\n");
+	gpiochip_remove(chip);
 err_disable_clk:
 	clk_disable_unprepare(gpio->clk);
 
@@ -664,16 +686,10 @@ err_disable_clk:
  */
 static int zynq_gpio_remove(struct platform_device *pdev)
 {
-	int ret;
 	struct zynq_gpio *gpio = platform_get_drvdata(pdev);
 
 	pm_runtime_get_sync(&pdev->dev);
-
-	ret = gpiochip_remove(&gpio->chip);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to remove gpio chip\n");
-		return ret;
-	}
+	gpiochip_remove(&gpio->chip);
 	clk_disable_unprepare(gpio->clk);
 	device_set_wakeup_capable(&pdev->dev, 0);
 	return 0;
@@ -688,7 +704,6 @@ MODULE_DEVICE_TABLE(of, zynq_gpio_of_match);
 static struct platform_driver zynq_gpio_driver = {
 	.driver	= {
 		.name = DRIVER_NAME,
-		.owner = THIS_MODULE,
 		.pm = &zynq_gpio_dev_pm_ops,
 		.of_match_table = zynq_gpio_of_match,
 	},
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 687476fb39e3..05c6275da224 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -25,10 +25,12 @@ struct acpi_gpio_event {
 	acpi_handle handle;
 	unsigned int pin;
 	unsigned int irq;
+	struct gpio_desc *desc;
 };
 
 struct acpi_gpio_connection {
 	struct list_head node;
+	unsigned int pin;
 	struct gpio_desc *desc;
 };
 
@@ -143,14 +145,8 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 	if (!handler)
 		return AE_BAD_PARAMETER;
 
-	desc = gpiochip_get_desc(chip, pin);
+	desc = gpiochip_request_own_desc(chip, pin, "ACPI:Event");
 	if (IS_ERR(desc)) {
-		dev_err(chip->dev, "Failed to get GPIO descriptor\n");
-		return AE_ERROR;
-	}
-
-	ret = gpiochip_request_own_desc(desc, "ACPI:Event");
-	if (ret) {
 		dev_err(chip->dev, "Failed to request GPIO\n");
 		return AE_ERROR;
 	}
@@ -197,6 +193,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 	event->handle = evt_handle;
 	event->irq = irq;
 	event->pin = pin;
+	event->desc = desc;
 
 	ret = request_threaded_irq(event->irq, NULL, handler, irqflags,
 				   "ACPI:Event", event);
@@ -280,7 +277,7 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip)
 		struct gpio_desc *desc;
 
 		free_irq(event->irq, event);
-		desc = gpiochip_get_desc(chip, event->pin);
+		desc = event->desc;
 		if (WARN_ON(IS_ERR(desc)))
 			continue;
 		gpio_unlock_as_irq(chip, event->pin);
@@ -409,26 +406,20 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address,
 		struct gpio_desc *desc;
 		bool found;
 
-		desc = gpiochip_get_desc(chip, pin);
-		if (IS_ERR(desc)) {
-			status = AE_ERROR;
-			goto out;
-		}
-
 		mutex_lock(&achip->conn_lock);
 
 		found = false;
 		list_for_each_entry(conn, &achip->conns, node) {
-			if (conn->desc == desc) {
+			if (conn->pin == pin) {
 				found = true;
+				desc = conn->desc;
 				break;
 			}
 		}
 		if (!found) {
-			int ret;
-
-			ret = gpiochip_request_own_desc(desc, "ACPI:OpRegion");
-			if (ret) {
+			desc = gpiochip_request_own_desc(chip, pin,
+							 "ACPI:OpRegion");
+			if (IS_ERR(desc)) {
 				status = AE_ERROR;
 				mutex_unlock(&achip->conn_lock);
 				goto out;
@@ -465,6 +456,7 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address,
 				goto out;
 			}
 
+			conn->pin = pin;
 			conn->desc = desc;
 			list_add_tail(&conn->node, &achip->conns);
 		}
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index c68d037de656..e8e98ca25ec7 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -308,10 +308,9 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
  *
  * A gpio_chip with any GPIOs still requested may not be removed.
  */
-int gpiochip_remove(struct gpio_chip *chip)
+void gpiochip_remove(struct gpio_chip *chip)
 {
 	unsigned long	flags;
-	int		status = 0;
 	unsigned	id;
 
 	acpi_gpiochip_remove(chip);
@@ -323,24 +322,15 @@ int gpiochip_remove(struct gpio_chip *chip)
 	of_gpiochip_remove(chip);
 
 	for (id = 0; id < chip->ngpio; id++) {
-		if (test_bit(FLAG_REQUESTED, &chip->desc[id].flags)) {
-			status = -EBUSY;
-			break;
-		}
-	}
-	if (status == 0) {
-		for (id = 0; id < chip->ngpio; id++)
-			chip->desc[id].chip = NULL;
-
-		list_del(&chip->list);
+		if (test_bit(FLAG_REQUESTED, &chip->desc[id].flags))
+			dev_crit(chip->dev, "REMOVING GPIOCHIP WITH GPIOS STILL REQUESTED\n");
 	}
+	for (id = 0; id < chip->ngpio; id++)
+		chip->desc[id].chip = NULL;
 
+	list_del(&chip->list);
 	spin_unlock_irqrestore(&gpio_lock, flags);
-
-	if (status == 0)
-		gpiochip_unexport(chip);
-
-	return status;
+	gpiochip_unexport(chip);
 }
 EXPORT_SYMBOL_GPL(gpiochip_remove);
 
@@ -395,30 +385,47 @@ static struct gpio_chip *find_chip_by_name(const char *name)
  */
 
 /**
- * gpiochip_add_chained_irqchip() - adds a chained irqchip to a gpiochip
- * @gpiochip: the gpiochip to add the irqchip to
- * @irqchip: the irqchip to add to the gpiochip
+ * gpiochip_set_chained_irqchip() - sets a chained irqchip to a gpiochip
+ * @gpiochip: the gpiochip to set the irqchip chain to
+ * @irqchip: the irqchip to chain to the gpiochip
  * @parent_irq: the irq number corresponding to the parent IRQ for this
  * chained irqchip
  * @parent_handler: the parent interrupt handler for the accumulated IRQ
- * coming out of the gpiochip
+ * coming out of the gpiochip. If the interrupt is nested rather than
+ * cascaded, pass NULL in this handler argument
  */
 void gpiochip_set_chained_irqchip(struct gpio_chip *gpiochip,
 				  struct irq_chip *irqchip,
 				  int parent_irq,
 				  irq_flow_handler_t parent_handler)
 {
-	if (gpiochip->can_sleep) {
-		chip_err(gpiochip, "you cannot have chained interrupts on a chip that may sleep\n");
+	unsigned int offset;
+
+	if (!gpiochip->irqdomain) {
+		chip_err(gpiochip, "called %s before setting up irqchip\n",
+			 __func__);
 		return;
 	}
 
-	/*
-	 * The parent irqchip is already using the chip_data for this
-	 * irqchip, so our callbacks simply use the handler_data.
-	 */
-	irq_set_handler_data(parent_irq, gpiochip);
-	irq_set_chained_handler(parent_irq, parent_handler);
+	if (parent_handler) {
+		if (gpiochip->can_sleep) {
+			chip_err(gpiochip,
+				 "you cannot have chained interrupts on a "
+				 "chip that may sleep\n");
+			return;
+		}
+		/*
+		 * The parent irqchip is already using the chip_data for this
+		 * irqchip, so our callbacks simply use the handler_data.
+		 */
+		irq_set_handler_data(parent_irq, gpiochip);
+		irq_set_chained_handler(parent_irq, parent_handler);
+	}
+
+	/* Set the parent IRQ for all affected IRQs */
+	for (offset = 0; offset < gpiochip->ngpio; offset++)
+		irq_set_parent(irq_find_mapping(gpiochip->irqdomain, offset),
+			       parent_irq);
 }
 EXPORT_SYMBOL_GPL(gpiochip_set_chained_irqchip);
 
@@ -447,7 +454,7 @@ static int gpiochip_irq_map(struct irq_domain *d, unsigned int irq,
 	irq_set_lockdep_class(irq, &gpiochip_irq_lock_class);
 	irq_set_chip_and_handler(irq, chip->irqchip, chip->irq_handler);
 	/* Chips that can sleep need nested thread handlers */
-	if (chip->can_sleep)
+	if (chip->can_sleep && !chip->irq_not_threaded)
 		irq_set_nested_thread(irq, 1);
 #ifdef CONFIG_ARM
 	set_irq_flags(irq, IRQF_VALID);
@@ -524,7 +531,8 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip)
 	/* Remove all IRQ mappings and delete the domain */
 	if (gpiochip->irqdomain) {
 		for (offset = 0; offset < gpiochip->ngpio; offset++)
-			irq_dispose_mapping(gpiochip->irq_base + offset);
+			irq_dispose_mapping(
+				irq_find_mapping(gpiochip->irqdomain, offset));
 		irq_domain_remove(gpiochip->irqdomain);
 	}
 
@@ -895,12 +903,22 @@ EXPORT_SYMBOL_GPL(gpiochip_is_requested);
  * allows the GPIO chip module to be unloaded as needed (we assume that the
  * GPIO chip driver handles freeing the GPIOs it has requested).
  */
-int gpiochip_request_own_desc(struct gpio_desc *desc, const char *label)
+struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *chip, u16 hwnum,
+					    const char *label)
 {
-	if (!desc || !desc->chip)
-		return -EINVAL;
+	struct gpio_desc *desc = gpiochip_get_desc(chip, hwnum);
+	int err;
 
-	return __gpiod_request(desc, label);
+	if (IS_ERR(desc)) {
+		chip_err(chip, "failed to get GPIO descriptor\n");
+		return desc;
+	}
+
+	err = __gpiod_request(desc, label);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	return desc;
 }
 EXPORT_SYMBOL_GPL(gpiochip_request_own_desc);
 
@@ -1652,7 +1670,7 @@ struct gpio_desc *__must_check __gpiod_get_index(struct device *dev,
 	 * a result. In that case, use platform lookup as a fallback.
 	 */
 	if (!desc || desc == ERR_PTR(-ENOENT)) {
-		dev_dbg(dev, "using lookup tables for GPIO lookup");
+		dev_dbg(dev, "using lookup tables for GPIO lookup\n");
 		desc = gpiod_find(dev, con_id, idx, &lookupflags);
 	}
 
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index b066bb3ca01a..e3b4b0f02b3d 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -8,6 +8,7 @@ menuconfig DRM
 	tristate "Direct Rendering Manager (XFree86 4.1.0 and higher DRI support)"
 	depends on (AGP || AGP=n) && !EMULATED_CMPXCHG && MMU && HAS_DMA
 	select HDMI
+	select FB_CMDLINE
 	select I2C
 	select I2C_ALGOBIT
 	select DMA_SHARED_BUFFER
@@ -24,12 +25,6 @@ config DRM_MIPI_DSI
 	bool
 	depends on DRM
 
-config DRM_USB
-	tristate
-	depends on DRM
-	depends on USB_SUPPORT && USB_ARCH_HAS_HCD
-	select USB
-
 config DRM_KMS_HELPER
 	tristate
 	depends on DRM
@@ -115,6 +110,7 @@ config DRM_RADEON
 	select HWMON
 	select BACKLIGHT_CLASS_DEVICE
 	select INTERVAL_TREE
+	select MMU_NOTIFIER
 	help
 	  Choose this option if you have an ATI Radeon graphics card.  There
 	  are both PCI and AGP versions.  You don't need to choose this to
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 4a55d59ccd22..9292a761ea6d 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -4,7 +4,7 @@
 
 ccflags-y := -Iinclude/drm
 
-drm-y       :=	drm_auth.o drm_buffer.o drm_bufs.o drm_cache.o \
+drm-y       :=	drm_auth.o drm_bufs.o drm_cache.o \
 		drm_context.o drm_dma.o \
 		drm_fops.o drm_gem.o drm_ioctl.o drm_irq.o \
 		drm_lock.o drm_memory.o drm_drv.o drm_vm.o \
@@ -22,8 +22,6 @@ drm-$(CONFIG_PCI) += ati_pcigart.o
 drm-$(CONFIG_DRM_PANEL) += drm_panel.o
 drm-$(CONFIG_OF) += drm_of.o
 
-drm-usb-y   := drm_usb.o
-
 drm_kms_helper-y := drm_crtc_helper.o drm_dp_helper.o drm_probe_helper.o \
 		drm_plane_helper.o drm_dp_mst_topology.o
 drm_kms_helper-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o
@@ -36,7 +34,6 @@ CFLAGS_drm_trace_points.o := -I$(src)
 
 obj-$(CONFIG_DRM)	+= drm.o
 obj-$(CONFIG_DRM_MIPI_DSI) += drm_mipi_dsi.o
-obj-$(CONFIG_DRM_USB)   += drm_usb.o
 obj-$(CONFIG_DRM_TTM)	+= ttm/
 obj-$(CONFIG_DRM_TDFX)	+= tdfx/
 obj-$(CONFIG_DRM_R128)	+= r128/
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index e2d5792b140f..f672e6ad8afa 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -308,6 +308,7 @@ static struct drm_driver armada_drm_driver = {
 	.postclose		= NULL,
 	.lastclose		= armada_drm_lastclose,
 	.unload			= armada_drm_unload,
+	.set_busid		= drm_platform_set_busid,
 	.get_vblank_counter	= drm_vblank_count,
 	.enable_vblank		= armada_drm_enable_vblank,
 	.disable_vblank		= armada_drm_disable_vblank,
diff --git a/drivers/gpu/drm/armada/armada_gem.h b/drivers/gpu/drm/armada/armada_gem.h
index 00b6cd461a03..b000ea3a829a 100644
--- a/drivers/gpu/drm/armada/armada_gem.h
+++ b/drivers/gpu/drm/armada/armada_gem.h
@@ -8,6 +8,8 @@
 #ifndef ARMADA_GEM_H
 #define ARMADA_GEM_H
 
+#include <drm/drm_gem.h>
+
 /* GEM */
 struct armada_gem_object {
 	struct drm_gem_object	obj;
diff --git a/drivers/gpu/drm/ast/ast_dp501.c b/drivers/gpu/drm/ast/ast_dp501.c
index 5da4b62285fa..76f07f38b941 100644
--- a/drivers/gpu/drm/ast/ast_dp501.c
+++ b/drivers/gpu/drm/ast/ast_dp501.c
@@ -379,11 +379,39 @@ static bool ast_init_dvo(struct drm_device *dev)
 	return true;
 }
 
+
+static void ast_init_analog(struct drm_device *dev)
+{
+	struct ast_private *ast = dev->dev_private;
+	u32 data;
+
+	/*
+	 * Set DAC source to VGA mode in SCU2C via the P2A
+	 * bridge. First configure the P2U to target the SCU
+	 * in case it isn't at this stage.
+	 */
+	ast_write32(ast, 0xf004, 0x1e6e0000);
+	ast_write32(ast, 0xf000, 0x1);
+
+	/* Then unlock the SCU with the magic password */
+	ast_write32(ast, 0x12000, 0x1688a8a8);
+	ast_write32(ast, 0x12000, 0x1688a8a8);
+	ast_write32(ast, 0x12000, 0x1688a8a8);
+
+	/* Finally, clear bits [17:16] of SCU2c */
+	data = ast_read32(ast, 0x1202c);
+	data &= 0xfffcffff;
+	ast_write32(ast, 0, data);
+
+	/* Disable DVO */
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xcf, 0x00);
+}
+
 void ast_init_3rdtx(struct drm_device *dev)
 {
 	struct ast_private *ast = dev->dev_private;
 	u8 jreg;
-	u32 data;
+
 	if (ast->chip == AST2300 || ast->chip == AST2400) {
 		jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd1, 0xff);
 		switch (jreg & 0x0e) {
@@ -399,12 +427,8 @@ void ast_init_3rdtx(struct drm_device *dev)
 		default:
 			if (ast->tx_chip_type == AST_TX_SIL164)
 				ast_init_dvo(dev);
-			else {
-				ast_write32(ast, 0x12000, 0x1688a8a8);
-				data = ast_read32(ast, 0x1202c);
-				data &= 0xfffcffff;
-				ast_write32(ast, 0, data);
-			}
+			else
+				ast_init_analog(dev);
 		}
 	}
 }
diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index f19682a93c24..9a32d9dfdd26 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -199,6 +199,7 @@ static struct drm_driver driver = {
 
 	.load = ast_driver_load,
 	.unload = ast_driver_unload,
+	.set_busid = drm_pci_set_busid,
 
 	.fops = &ast_fops,
 	.name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 957d4fabf1e1..86205a28e56b 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -36,6 +36,8 @@
 #include <drm/ttm/ttm_memory.h>
 #include <drm/ttm/ttm_module.h>
 
+#include <drm/drm_gem.h>
+
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 
@@ -125,8 +127,9 @@ struct ast_gem_object;
 
 #define AST_IO_AR_PORT_WRITE		(0x40)
 #define AST_IO_MISC_PORT_WRITE		(0x42)
+#define AST_IO_VGA_ENABLE_PORT		(0x43)
 #define AST_IO_SEQ_PORT			(0x44)
-#define AST_DAC_INDEX_READ		(0x3c7)
+#define AST_IO_DAC_INDEX_READ		(0x47)
 #define AST_IO_DAC_INDEX_WRITE		(0x48)
 #define AST_IO_DAC_DATA		        (0x49)
 #define AST_IO_GR_PORT			(0x4E)
@@ -134,6 +137,8 @@ struct ast_gem_object;
 #define AST_IO_INPUT_STATUS1_READ	(0x5A)
 #define AST_IO_MISC_PORT_READ		(0x4C)
 
+#define AST_IO_MM_OFFSET		(0x380)
+
 #define __ast_read(x) \
 static inline u##x ast_read##x(struct ast_private *ast, u32 reg) { \
 u##x val = 0;\
@@ -316,7 +321,7 @@ struct ast_bo {
 	struct ttm_placement placement;
 	struct ttm_bo_kmap_obj kmap;
 	struct drm_gem_object gem;
-	u32 placements[3];
+	struct ttm_place placements[3];
 	int pin_count;
 };
 #define gem_to_ast_bo(gobj) container_of((gobj), struct ast_bo, gem)
@@ -381,6 +386,9 @@ int ast_bo_push_sysram(struct ast_bo *bo);
 int ast_mmap(struct file *filp, struct vm_area_struct *vma);
 
 /* ast post */
+void ast_enable_vga(struct drm_device *dev);
+void ast_enable_mmio(struct drm_device *dev);
+bool ast_is_vga_enabled(struct drm_device *dev);
 void ast_post_gpu(struct drm_device *dev);
 u32 ast_mindwm(struct ast_private *ast, u32 r);
 void ast_moutdwm(struct ast_private *ast, u32 r, u32 v);
diff --git a/drivers/gpu/drm/ast/ast_fb.c b/drivers/gpu/drm/ast/ast_fb.c
index cba45c774552..5c60ae524c45 100644
--- a/drivers/gpu/drm/ast/ast_fb.c
+++ b/drivers/gpu/drm/ast/ast_fb.c
@@ -186,7 +186,8 @@ static int astfb_create_object(struct ast_fbdev *afbdev,
 static int astfb_create(struct drm_fb_helper *helper,
 			struct drm_fb_helper_surface_size *sizes)
 {
-	struct ast_fbdev *afbdev = (struct ast_fbdev *)helper;
+	struct ast_fbdev *afbdev =
+		container_of(helper, struct ast_fbdev, helper);
 	struct drm_device *dev = afbdev->helper.dev;
 	struct drm_mode_fb_cmd2 mode_cmd;
 	struct drm_framebuffer *fb;
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index b792194e0d9c..035dacc93382 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -63,7 +63,7 @@ uint8_t ast_get_index_reg_mask(struct ast_private *ast,
 }
 
 
-static int ast_detect_chip(struct drm_device *dev)
+static int ast_detect_chip(struct drm_device *dev, bool *need_post)
 {
 	struct ast_private *ast = dev->dev_private;
 	uint32_t data, jreg;
@@ -110,6 +110,21 @@ static int ast_detect_chip(struct drm_device *dev)
 		}
 	}
 
+	/*
+	 * If VGA isn't enabled, we need to enable now or subsequent
+	 * access to the scratch registers will fail. We also inform
+	 * our caller that it needs to POST the chip
+	 * (Assumption: VGA not enabled -> need to POST)
+	 */
+	if (!ast_is_vga_enabled(dev)) {
+		ast_enable_vga(dev);
+		ast_enable_mmio(dev);
+		DRM_INFO("VGA not enabled on entry, requesting chip POST\n");
+		*need_post = true;
+	} else
+		*need_post = false;
+
+	/* Check if we support wide screen */
 	switch (ast->chip) {
 	case AST1180:
 		ast->support_wide_screen = true;
@@ -125,6 +140,7 @@ static int ast_detect_chip(struct drm_device *dev)
 			ast->support_wide_screen = true;
 		else {
 			ast->support_wide_screen = false;
+			/* Read SCU7c (silicon revision register) */
 			ast_write32(ast, 0xf004, 0x1e6e0000);
 			ast_write32(ast, 0xf000, 0x1);
 			data = ast_read32(ast, 0x1207c);
@@ -137,11 +153,29 @@ static int ast_detect_chip(struct drm_device *dev)
 		break;
 	}
 
+	/* Check 3rd Tx option (digital output afaik) */
 	ast->tx_chip_type = AST_TX_NONE;
-	jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xff);
-	if (jreg & 0x80)
-		ast->tx_chip_type = AST_TX_SIL164;
+
+	/*
+	 * VGACRA3 Enhanced Color Mode Register, check if DVO is already
+	 * enabled, in that case, assume we have a SIL164 TMDS transmitter
+	 *
+	 * Don't make that assumption if we the chip wasn't enabled and
+	 * is at power-on reset, otherwise we'll incorrectly "detect" a
+	 * SIL164 when there is none.
+	 */
+	if (!*need_post) {
+		jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xff);
+		if (jreg & 0x80)
+			ast->tx_chip_type = AST_TX_SIL164;
+	}
+
 	if ((ast->chip == AST2300) || (ast->chip == AST2400)) {
+		/*
+		 * On AST2300 and 2400, look the configuration set by the SoC in
+		 * the SOC scratch register #1 bits 11:8 (interestingly marked
+		 * as "reserved" in the spec)
+		 */
 		jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd1, 0xff);
 		switch (jreg) {
 		case 0x04:
@@ -162,6 +196,17 @@ static int ast_detect_chip(struct drm_device *dev)
 		}
 	}
 
+	/* Print stuff for diagnostic purposes */
+	switch(ast->tx_chip_type) {
+	case AST_TX_SIL164:
+		DRM_INFO("Using Sil164 TMDS transmitter\n");
+		break;
+	case AST_TX_DP501:
+		DRM_INFO("Using DP501 DisplayPort transmitter\n");
+		break;
+	default:
+		DRM_INFO("Analog VGA only\n");
+	}
 	return 0;
 }
 
@@ -346,6 +391,7 @@ static u32 ast_get_vram_info(struct drm_device *dev)
 int ast_driver_load(struct drm_device *dev, unsigned long flags)
 {
 	struct ast_private *ast;
+	bool need_post;
 	int ret = 0;
 
 	ast = kzalloc(sizeof(struct ast_private), GFP_KERNEL);
@@ -360,13 +406,27 @@ int ast_driver_load(struct drm_device *dev, unsigned long flags)
 		ret = -EIO;
 		goto out_free;
 	}
-	ast->ioregs = pci_iomap(dev->pdev, 2, 0);
+
+	/*
+	 * If we don't have IO space at all, use MMIO now and
+	 * assume the chip has MMIO enabled by default (rev 0x20
+	 * and higher).
+	 */
+	if (!(pci_resource_flags(dev->pdev, 2) & IORESOURCE_IO)) {
+		DRM_INFO("platform has no IO space, trying MMIO\n");
+		ast->ioregs = ast->regs + AST_IO_MM_OFFSET;
+	}
+
+	/* "map" IO regs if the above hasn't done so already */
 	if (!ast->ioregs) {
-		ret = -EIO;
-		goto out_free;
+		ast->ioregs = pci_iomap(dev->pdev, 2, 0);
+		if (!ast->ioregs) {
+			ret = -EIO;
+			goto out_free;
+		}
 	}
 
-	ast_detect_chip(dev);
+	ast_detect_chip(dev, &need_post);
 
 	if (ast->chip != AST1180) {
 		ast_get_dram_info(dev);
@@ -374,6 +434,9 @@ int ast_driver_load(struct drm_device *dev, unsigned long flags)
 		DRM_INFO("dram %d %d %d %08x\n", ast->mclk, ast->dram_type, ast->dram_bus_width, ast->vram_size);
 	}
 
+	if (need_post)
+		ast_post_gpu(dev);
+
 	ret = ast_mm_init(ast);
 	if (ret)
 		goto out_free;
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 5389350244f2..9dc0fd5c1ea4 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -80,6 +80,8 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 	struct ast_private *ast = crtc->dev->dev_private;
 	u32 refresh_rate_index = 0, mode_id, color_index, refresh_rate;
 	u32 hborder, vborder;
+	bool check_sync;
+	struct ast_vbios_enhtable *best = NULL;
 
 	switch (crtc->primary->fb->bits_per_pixel) {
 	case 8:
@@ -141,14 +143,34 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 	}
 
 	refresh_rate = drm_mode_vrefresh(mode);
-	while (vbios_mode->enh_table->refresh_rate < refresh_rate) {
-		vbios_mode->enh_table++;
-		if ((vbios_mode->enh_table->refresh_rate > refresh_rate) ||
-		    (vbios_mode->enh_table->refresh_rate == 0xff)) {
-			vbios_mode->enh_table--;
-			break;
+	check_sync = vbios_mode->enh_table->flags & WideScreenMode;
+	do {
+		struct ast_vbios_enhtable *loop = vbios_mode->enh_table;
+
+		while (loop->refresh_rate != 0xff) {
+			if ((check_sync) &&
+			    (((mode->flags & DRM_MODE_FLAG_NVSYNC)  &&
+			      (loop->flags & PVSync))  ||
+			     ((mode->flags & DRM_MODE_FLAG_PVSYNC)  &&
+			      (loop->flags & NVSync))  ||
+			     ((mode->flags & DRM_MODE_FLAG_NHSYNC)  &&
+			      (loop->flags & PHSync))  ||
+			     ((mode->flags & DRM_MODE_FLAG_PHSYNC)  &&
+			      (loop->flags & NHSync)))) {
+				loop++;
+				continue;
+			}
+			if (loop->refresh_rate <= refresh_rate
+			    && (!best || loop->refresh_rate > best->refresh_rate))
+				best = loop;
+			loop++;
 		}
-	}
+		if (best || !check_sync)
+			break;
+		check_sync = 0;
+	} while (1);
+	if (best)
+		vbios_mode->enh_table = best;
 
 	hborder = (vbios_mode->enh_table->flags & HBorder) ? 8 : 0;
 	vborder = (vbios_mode->enh_table->flags & VBorder) ? 8 : 0;
@@ -419,8 +441,10 @@ static void ast_set_sync_reg(struct drm_device *dev, struct drm_display_mode *mo
 	struct ast_private *ast = dev->dev_private;
 	u8 jreg;
 
-	jreg = ast_io_read8(ast, AST_IO_MISC_PORT_READ);
-	jreg |= (vbios_mode->enh_table->flags & SyncNN);
+	jreg  = ast_io_read8(ast, AST_IO_MISC_PORT_READ);
+	jreg &= ~0xC0;
+	if (vbios_mode->enh_table->flags & NVSync) jreg |= 0x80;
+	if (vbios_mode->enh_table->flags & NHSync) jreg |= 0x40;
 	ast_io_write8(ast, AST_IO_MISC_PORT_WRITE, jreg);
 }
 
@@ -1080,8 +1104,8 @@ static u32 copy_cursor_image(u8 *src, u8 *dst, int width, int height)
 			srcdata32[1].ul = *((u32 *)(srcxor + 4)) & 0xf0f0f0f0;
 			data32.b[0] = srcdata32[0].b[1] | (srcdata32[0].b[0] >> 4);
 			data32.b[1] = srcdata32[0].b[3] | (srcdata32[0].b[2] >> 4);
-			data32.b[2] = srcdata32[0].b[1] | (srcdata32[1].b[0] >> 4);
-			data32.b[3] = srcdata32[0].b[3] | (srcdata32[1].b[2] >> 4);
+			data32.b[2] = srcdata32[1].b[1] | (srcdata32[1].b[0] >> 4);
+			data32.b[3] = srcdata32[1].b[3] | (srcdata32[1].b[2] >> 4);
 
 			writel(data32.ul, dstxor);
 			csum += data32.ul;
diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c
index 38d437f3a267..810c51d92b99 100644
--- a/drivers/gpu/drm/ast/ast_post.c
+++ b/drivers/gpu/drm/ast/ast_post.c
@@ -33,18 +33,23 @@
 
 static void ast_init_dram_2300(struct drm_device *dev);
 
-static void
-ast_enable_vga(struct drm_device *dev)
+void ast_enable_vga(struct drm_device *dev)
+{
+	struct ast_private *ast = dev->dev_private;
+
+	ast_io_write8(ast, AST_IO_VGA_ENABLE_PORT, 0x01);
+	ast_io_write8(ast, AST_IO_MISC_PORT_WRITE, 0x01);
+}
+
+void ast_enable_mmio(struct drm_device *dev)
 {
 	struct ast_private *ast = dev->dev_private;
 
-	ast_io_write8(ast, 0x43, 0x01);
-	ast_io_write8(ast, 0x42, 0x01);
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa1, 0xff, 0x04);
 }
 
-#if 0 /* will use later */
-static bool
-ast_is_vga_enabled(struct drm_device *dev)
+
+bool ast_is_vga_enabled(struct drm_device *dev)
 {
 	struct ast_private *ast = dev->dev_private;
 	u8 ch;
@@ -52,7 +57,7 @@ ast_is_vga_enabled(struct drm_device *dev)
 	if (ast->chip == AST1180) {
 		/* TODO 1180 */
 	} else {
-		ch = ast_io_read8(ast, 0x43);
+		ch = ast_io_read8(ast, AST_IO_VGA_ENABLE_PORT);
 		if (ch) {
 			ast_open_key(ast);
 			ch = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb6, 0xff);
@@ -61,7 +66,6 @@ ast_is_vga_enabled(struct drm_device *dev)
 	}
 	return 0;
 }
-#endif
 
 static const u8 extreginfo[] = { 0x0f, 0x04, 0x1c, 0xff };
 static const u8 extreginfo_ast2300a0[] = { 0x0f, 0x04, 0x1c, 0xff };
@@ -371,6 +375,7 @@ void ast_post_gpu(struct drm_device *dev)
 	pci_write_config_dword(ast->dev->pdev, 0x04, reg);
 
 	ast_enable_vga(dev);
+	ast_enable_mmio(dev);
 	ast_open_key(ast);
 	ast_set_def_ext_reg(dev);
 
diff --git a/drivers/gpu/drm/ast/ast_tables.h b/drivers/gpu/drm/ast/ast_tables.h
index 05c01ea85294..3608d5aa7451 100644
--- a/drivers/gpu/drm/ast/ast_tables.h
+++ b/drivers/gpu/drm/ast/ast_tables.h
@@ -35,14 +35,18 @@
 #define HalfDCLK                0x00000002
 #define DoubleScanMode          0x00000004
 #define LineCompareOff          0x00000008
-#define SyncPP                  0x00000000
-#define SyncPN                  0x00000040
-#define SyncNP                  0x00000080
-#define SyncNN                  0x000000C0
 #define HBorder                 0x00000020
 #define VBorder                 0x00000010
 #define WideScreenMode		0x00000100
 #define NewModeInfo		0x00000200
+#define NHSync			0x00000400
+#define PHSync			0x00000800
+#define NVSync			0x00001000
+#define PVSync			0x00002000
+#define SyncPP			(PVSync | PHSync)
+#define SyncPN			(PVSync | NHSync)
+#define SyncNP			(NVSync | PHSync)
+#define SyncNN			(NVSync | NHSync)
 
 /* DCLK Index */
 #define VCLK25_175     		0x00
@@ -72,6 +76,7 @@
 #define VCLK119     		0x17
 #define VCLK85_5     		0x18
 #define VCLK97_75     		0x19
+#define VCLK118_25			0x1A
 
 static struct ast_vbios_dclk_info dclk_table[] = {
 	{0x2C, 0xE7, 0x03},					/* 00: VCLK25_175	*/
@@ -100,6 +105,7 @@ static struct ast_vbios_dclk_info dclk_table[] = {
 	{0x77, 0x58, 0x80},					/* 17: VCLK119      */
 	{0x32, 0x67, 0x80},				    /* 18: VCLK85_5     */
 	{0x6a, 0x6d, 0x80},					/* 19: VCLK97_75	*/
+	{0x3b, 0x2c, 0x81},					/* 1A: VCLK118_25	*/
 };
 
 static struct ast_vbios_stdtable vbios_stdtable[] = {
@@ -246,8 +252,10 @@ static struct ast_vbios_enhtable res_1360x768[] = {
 static struct ast_vbios_enhtable res_1600x900[] = {
 	{1760, 1600, 48, 32, 926,  900, 3, 5, VCLK97_75,	/* 60Hz CVT RB */
 	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x3A },
-	{1760, 1600, 48, 32, 926,  900, 3, 5, VCLK97_75,	/* end */
-	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x3A }
+	{2112, 1600, 88,168, 934,  900, 3, 5, VCLK118_25,	/* 60Hz CVT */
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 2, 0x3A },
+	{2112, 1600, 88,168, 934,  900, 3, 5, VCLK118_25,	/* 60Hz CVT */
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 2, 0x3A },
 };
 
 static struct ast_vbios_enhtable res_1920x1080[] = {
@@ -261,11 +269,11 @@ static struct ast_vbios_enhtable res_1920x1080[] = {
 /* 16:10 */
 static struct ast_vbios_enhtable res_1280x800[] = {
 	{1440, 1280, 48, 32,  823,  800, 3, 6, VCLK71,	/* 60Hz RB */
-	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 35 },
+	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x35 },
 	{1680, 1280, 72,128,  831,  800, 3, 6, VCLK83_5,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x35 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 2, 0x35 },
 	{1680, 1280, 72,128,  831,  800, 3, 6, VCLK83_5,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x35 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 2, 0x35 },
 
 };
 
@@ -273,24 +281,24 @@ static struct ast_vbios_enhtable res_1440x900[] = {
 	{1600, 1440, 48, 32,  926,  900, 3, 6, VCLK88_75,	/* 60Hz RB */
 	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x36 },
 	{1904, 1440, 80,152,  934,  900, 3, 6, VCLK106_5,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x36 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 2, 0x36 },
 	{1904, 1440, 80,152,  934,  900, 3, 6, VCLK106_5,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x36 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 2, 0x36 },
 };
 
 static struct ast_vbios_enhtable res_1680x1050[] = {
 	{1840, 1680, 48, 32, 1080, 1050, 3, 6, VCLK119,	/* 60Hz RB */
 	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x37 },
 	{2240, 1680,104,176, 1089, 1050, 3, 6, VCLK146_25,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x37 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 2, 0x37 },
 	{2240, 1680,104,176, 1089, 1050, 3, 6, VCLK146_25,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x37 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 2, 0x37 },
 };
 
 static struct ast_vbios_enhtable res_1920x1200[] = {
-	{2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154,	/* 60Hz */
+	{2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154,	/* 60Hz RB*/
 	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x34 },
-	{2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154,	/* 60Hz */
+	{2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154,	/* 60Hz RB */
 	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x34 },
 };
 
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index b8246227bab0..08f82eae6939 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -293,18 +293,22 @@ void ast_mm_fini(struct ast_private *ast)
 void ast_ttm_placement(struct ast_bo *bo, int domain)
 {
 	u32 c = 0;
-	bo->placement.fpfn = 0;
-	bo->placement.lpfn = 0;
+	unsigned i;
+
 	bo->placement.placement = bo->placements;
 	bo->placement.busy_placement = bo->placements;
 	if (domain & TTM_PL_FLAG_VRAM)
-		bo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
+		bo->placements[c++].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
 	if (domain & TTM_PL_FLAG_SYSTEM)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_SYSTEM;
 	if (!c)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_SYSTEM;
 	bo->placement.num_placement = c;
 	bo->placement.num_busy_placement = c;
+	for (i = 0; i < c; ++i) {
+		bo->placements[i].fpfn = 0;
+		bo->placements[i].lpfn = 0;
+	}
 }
 
 int ast_bo_create(struct drm_device *dev, int size, int align,
@@ -335,7 +339,7 @@ int ast_bo_create(struct drm_device *dev, int size, int align,
 	ret = ttm_bo_init(&ast->ttm.bdev, &astbo->bo, size,
 			  ttm_bo_type_device, &astbo->placement,
 			  align >> PAGE_SHIFT, false, NULL, acc_size,
-			  NULL, ast_bo_ttm_destroy);
+			  NULL, NULL, ast_bo_ttm_destroy);
 	if (ret)
 		return ret;
 
@@ -360,7 +364,7 @@ int ast_bo_pin(struct ast_bo *bo, u32 pl_flag, u64 *gpu_addr)
 
 	ast_ttm_placement(bo, pl_flag);
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -383,7 +387,7 @@ int ast_bo_unpin(struct ast_bo *bo)
 		return 0;
 
 	for (i = 0; i < bo->placement.num_placement ; i++)
-		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -407,7 +411,7 @@ int ast_bo_push_sysram(struct ast_bo *bo)
 
 	ast_ttm_placement(bo, TTM_PL_FLAG_SYSTEM);
 	for (i = 0; i < bo->placement.num_placement ; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret) {
@@ -423,7 +427,7 @@ int ast_mmap(struct file *filp, struct vm_area_struct *vma)
 	struct ast_private *ast;
 
 	if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET))
-		return drm_mmap(filp, vma);
+		return -EINVAL;
 
 	file_priv = filp->private_data;
 	ast = file_priv->minor->dev->dev_private;
diff --git a/drivers/gpu/drm/ati_pcigart.c b/drivers/gpu/drm/ati_pcigart.c
index c399dea27a3b..6c4d4b6eba80 100644
--- a/drivers/gpu/drm/ati_pcigart.c
+++ b/drivers/gpu/drm/ati_pcigart.c
@@ -34,6 +34,8 @@
 #include <linux/export.h>
 #include <drm/drmP.h>
 
+#include <drm/ati_pcigart.h>
+
 # define ATI_PCIGART_PAGE_SIZE		4096	/**< PCI GART page size */
 
 static int drm_ati_alloc_pcigart_table(struct drm_device *dev,
diff --git a/drivers/gpu/drm/bochs/bochs.h b/drivers/gpu/drm/bochs/bochs.h
index 7eb52dd44b01..71f2687fc3cc 100644
--- a/drivers/gpu/drm/bochs/bochs.h
+++ b/drivers/gpu/drm/bochs/bochs.h
@@ -7,6 +7,8 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 
+#include <drm/drm_gem.h>
+
 #include <ttm/ttm_bo_driver.h>
 #include <ttm/ttm_page_alloc.h>
 
@@ -99,7 +101,7 @@ struct bochs_bo {
 	struct ttm_placement placement;
 	struct ttm_bo_kmap_obj kmap;
 	struct drm_gem_object gem;
-	u32 placements[3];
+	struct ttm_place placements[3];
 	int pin_count;
 };
 
diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c
index 9738e9b14708..98837bde2d25 100644
--- a/drivers/gpu/drm/bochs/bochs_drv.c
+++ b/drivers/gpu/drm/bochs/bochs_drv.c
@@ -82,6 +82,7 @@ static struct drm_driver bochs_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET,
 	.load			= bochs_load,
 	.unload			= bochs_unload,
+	.set_busid		= drm_pci_set_busid,
 	.fops			= &bochs_fops,
 	.name			= "bochs-drm",
 	.desc			= "bochs dispi vga interface (qemu stdvga)",
diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c
index 1728a1b0b813..66286ff518d4 100644
--- a/drivers/gpu/drm/bochs/bochs_mm.c
+++ b/drivers/gpu/drm/bochs/bochs_mm.c
@@ -257,20 +257,26 @@ void bochs_mm_fini(struct bochs_device *bochs)
 
 static void bochs_ttm_placement(struct bochs_bo *bo, int domain)
 {
+	unsigned i;
 	u32 c = 0;
-	bo->placement.fpfn = 0;
-	bo->placement.lpfn = 0;
 	bo->placement.placement = bo->placements;
 	bo->placement.busy_placement = bo->placements;
 	if (domain & TTM_PL_FLAG_VRAM) {
-		bo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED
+		bo->placements[c++].flags = TTM_PL_FLAG_WC
+			| TTM_PL_FLAG_UNCACHED
 			| TTM_PL_FLAG_VRAM;
 	}
 	if (domain & TTM_PL_FLAG_SYSTEM) {
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING
+			| TTM_PL_FLAG_SYSTEM;
 	}
 	if (!c) {
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING
+			| TTM_PL_FLAG_SYSTEM;
+	}
+	for (i = 0; i < c; ++i) {
+		bo->placements[i].fpfn = 0;
+		bo->placements[i].lpfn = 0;
 	}
 	bo->placement.num_placement = c;
 	bo->placement.num_busy_placement = c;
@@ -294,7 +300,7 @@ int bochs_bo_pin(struct bochs_bo *bo, u32 pl_flag, u64 *gpu_addr)
 
 	bochs_ttm_placement(bo, pl_flag);
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -319,7 +325,7 @@ int bochs_bo_unpin(struct bochs_bo *bo)
 		return 0;
 
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -333,7 +339,7 @@ int bochs_mmap(struct file *filp, struct vm_area_struct *vma)
 	struct bochs_device *bochs;
 
 	if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET))
-		return drm_mmap(filp, vma);
+		return -EINVAL;
 
 	file_priv = filp->private_data;
 	bochs = file_priv->minor->dev->dev_private;
@@ -371,7 +377,7 @@ static int bochs_bo_create(struct drm_device *dev, int size, int align,
 	ret = ttm_bo_init(&bochs->ttm.bdev, &bochsbo->bo, size,
 			  ttm_bo_type_device, &bochsbo->placement,
 			  align >> PAGE_SHIFT, false, NULL, acc_size,
-			  NULL, bochs_bo_ttm_destroy);
+			  NULL, NULL, bochs_bo_ttm_destroy);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index 919c73b94447..e705335101a5 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -128,6 +128,7 @@ static struct drm_driver driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM,
 	.load = cirrus_driver_load,
 	.unload = cirrus_driver_unload,
+	.set_busid = drm_pci_set_busid,
 	.fops = &cirrus_driver_fops,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h
index 401c890b6c6a..d44e69daa239 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.h
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.h
@@ -21,6 +21,8 @@
 #include <drm/ttm/ttm_memory.h>
 #include <drm/ttm/ttm_module.h>
 
+#include <drm/drm_gem.h>
+
 #define DRIVER_AUTHOR		"Matthew Garrett"
 
 #define DRIVER_NAME		"cirrus"
@@ -163,7 +165,7 @@ struct cirrus_bo {
 	struct ttm_placement placement;
 	struct ttm_bo_kmap_obj kmap;
 	struct drm_gem_object gem;
-	u32 placements[3];
+	struct ttm_place placements[3];
 	int pin_count;
 };
 #define gem_to_cirrus_bo(gobj) container_of((gobj), struct cirrus_bo, gem)
diff --git a/drivers/gpu/drm/cirrus/cirrus_fbdev.c b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
index 2a135f253e29..d231b1c317af 100644
--- a/drivers/gpu/drm/cirrus/cirrus_fbdev.c
+++ b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
@@ -160,7 +160,8 @@ static int cirrusfb_create_object(struct cirrus_fbdev *afbdev,
 static int cirrusfb_create(struct drm_fb_helper *helper,
 			   struct drm_fb_helper_surface_size *sizes)
 {
-	struct cirrus_fbdev *gfbdev = (struct cirrus_fbdev *)helper;
+	struct cirrus_fbdev *gfbdev =
+		container_of(helper, struct cirrus_fbdev, helper);
 	struct drm_device *dev = gfbdev->helper.dev;
 	struct cirrus_device *cdev = gfbdev->helper.dev->dev_private;
 	struct fb_info *info;
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index 92e6b7786097..dfffd528517a 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -298,18 +298,21 @@ void cirrus_mm_fini(struct cirrus_device *cirrus)
 void cirrus_ttm_placement(struct cirrus_bo *bo, int domain)
 {
 	u32 c = 0;
-	bo->placement.fpfn = 0;
-	bo->placement.lpfn = 0;
+	unsigned i;
 	bo->placement.placement = bo->placements;
 	bo->placement.busy_placement = bo->placements;
 	if (domain & TTM_PL_FLAG_VRAM)
-		bo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
+		bo->placements[c++].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
 	if (domain & TTM_PL_FLAG_SYSTEM)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	if (!c)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	bo->placement.num_placement = c;
 	bo->placement.num_busy_placement = c;
+	for (i = 0; i < c; ++i) {
+		bo->placements[i].fpfn = 0;
+		bo->placements[i].lpfn = 0;
+	}
 }
 
 int cirrus_bo_create(struct drm_device *dev, int size, int align,
@@ -340,7 +343,7 @@ int cirrus_bo_create(struct drm_device *dev, int size, int align,
 	ret = ttm_bo_init(&cirrus->ttm.bdev, &cirrusbo->bo, size,
 			  ttm_bo_type_device, &cirrusbo->placement,
 			  align >> PAGE_SHIFT, false, NULL, acc_size,
-			  NULL, cirrus_bo_ttm_destroy);
+			  NULL, NULL, cirrus_bo_ttm_destroy);
 	if (ret)
 		return ret;
 
@@ -365,7 +368,7 @@ int cirrus_bo_pin(struct cirrus_bo *bo, u32 pl_flag, u64 *gpu_addr)
 
 	cirrus_ttm_placement(bo, pl_flag);
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -392,7 +395,7 @@ int cirrus_bo_push_sysram(struct cirrus_bo *bo)
 
 	cirrus_ttm_placement(bo, TTM_PL_FLAG_SYSTEM);
 	for (i = 0; i < bo->placement.num_placement ; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret) {
@@ -408,7 +411,7 @@ int cirrus_mmap(struct file *filp, struct vm_area_struct *vma)
 	struct cirrus_device *cirrus;
 
 	if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET))
-		return drm_mmap(filp, vma);
+		return -EINVAL;
 
 	file_priv = filp->private_data;
 	cirrus = file_priv->minor->dev->dev_private;
diff --git a/drivers/gpu/drm/drm_agpsupport.c b/drivers/gpu/drm/drm_agpsupport.c
index dde205cef384..4b2b4aa5033b 100644
--- a/drivers/gpu/drm/drm_agpsupport.c
+++ b/drivers/gpu/drm/drm_agpsupport.c
@@ -34,6 +34,7 @@
 #include <drm/drmP.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include "drm_legacy.h"
 
 #if __OS_HAS_AGP
 
diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c
index 3cedae12b3c1..fc8e8aaa34fb 100644
--- a/drivers/gpu/drm/drm_auth.c
+++ b/drivers/gpu/drm/drm_auth.c
@@ -34,6 +34,13 @@
  */
 
 #include <drm/drmP.h>
+#include "drm_internal.h"
+
+struct drm_magic_entry {
+	struct list_head head;
+	struct drm_hash_item hash_item;
+	struct drm_file *priv;
+};
 
 /**
  * Find the file with the given magic number.
diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index 61acb8f6756d..569064a00693 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -1,18 +1,13 @@
-/**
- * \file drm_bufs.c
- * Generic buffer template
- *
- * \author Rickard E. (Rik) Faith <faith@valinux.com>
- * \author Gareth Hughes <gareth@valinux.com>
- */
-
 /*
- * Created: Thu Nov 23 03:10:50 2000 by gareth@valinux.com
+ * Legacy: Generic DRM Buffer Management
  *
  * Copyright 1999, 2000 Precision Insight, Inc., Cedar Park, Texas.
  * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
  * All Rights Reserved.
  *
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
+ * Author: Gareth Hughes <gareth@valinux.com>
+ *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
  * to deal in the Software without restriction, including without limitation
@@ -39,6 +34,7 @@
 #include <linux/export.h>
 #include <asm/shmparam.h>
 #include <drm/drmP.h>
+#include "drm_legacy.h"
 
 static struct drm_map_list *drm_find_matching_map(struct drm_device *dev,
 						  struct drm_local_map *map)
@@ -365,9 +361,9 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset,
 	return 0;
 }
 
-int drm_addmap(struct drm_device * dev, resource_size_t offset,
-	       unsigned int size, enum drm_map_type type,
-	       enum drm_map_flags flags, struct drm_local_map ** map_ptr)
+int drm_legacy_addmap(struct drm_device * dev, resource_size_t offset,
+		      unsigned int size, enum drm_map_type type,
+		      enum drm_map_flags flags, struct drm_local_map **map_ptr)
 {
 	struct drm_map_list *list;
 	int rc;
@@ -377,8 +373,7 @@ int drm_addmap(struct drm_device * dev, resource_size_t offset,
 		*map_ptr = list->map;
 	return rc;
 }
-
-EXPORT_SYMBOL(drm_addmap);
+EXPORT_SYMBOL(drm_legacy_addmap);
 
 /**
  * Ioctl to specify a range of memory that is available for mapping by a
@@ -391,8 +386,8 @@ EXPORT_SYMBOL(drm_addmap);
  * \return zero on success or a negative value on error.
  *
  */
-int drm_addmap_ioctl(struct drm_device *dev, void *data,
-		     struct drm_file *file_priv)
+int drm_legacy_addmap_ioctl(struct drm_device *dev, void *data,
+			    struct drm_file *file_priv)
 {
 	struct drm_map *map = data;
 	struct drm_map_list *maplist;
@@ -429,9 +424,9 @@ int drm_addmap_ioctl(struct drm_device *dev, void *data,
  * its being used, and free any associate resource (such as MTRR's) if it's not
  * being on use.
  *
- * \sa drm_addmap
+ * \sa drm_legacy_addmap
  */
-int drm_rmmap_locked(struct drm_device *dev, struct drm_local_map *map)
+int drm_legacy_rmmap_locked(struct drm_device *dev, struct drm_local_map *map)
 {
 	struct drm_map_list *r_list = NULL, *list_t;
 	drm_dma_handle_t dmah;
@@ -478,26 +473,26 @@ int drm_rmmap_locked(struct drm_device *dev, struct drm_local_map *map)
 		dmah.vaddr = map->handle;
 		dmah.busaddr = map->offset;
 		dmah.size = map->size;
-		__drm_pci_free(dev, &dmah);
+		__drm_legacy_pci_free(dev, &dmah);
 		break;
 	}
 	kfree(map);
 
 	return 0;
 }
-EXPORT_SYMBOL(drm_rmmap_locked);
+EXPORT_SYMBOL(drm_legacy_rmmap_locked);
 
-int drm_rmmap(struct drm_device *dev, struct drm_local_map *map)
+int drm_legacy_rmmap(struct drm_device *dev, struct drm_local_map *map)
 {
 	int ret;
 
 	mutex_lock(&dev->struct_mutex);
-	ret = drm_rmmap_locked(dev, map);
+	ret = drm_legacy_rmmap_locked(dev, map);
 	mutex_unlock(&dev->struct_mutex);
 
 	return ret;
 }
-EXPORT_SYMBOL(drm_rmmap);
+EXPORT_SYMBOL(drm_legacy_rmmap);
 
 /* The rmmap ioctl appears to be unnecessary.  All mappings are torn down on
  * the last close of the device, and this is necessary for cleanup when things
@@ -514,8 +509,8 @@ EXPORT_SYMBOL(drm_rmmap);
  * \param arg pointer to a struct drm_map structure.
  * \return zero on success or a negative value on error.
  */
-int drm_rmmap_ioctl(struct drm_device *dev, void *data,
-		    struct drm_file *file_priv)
+int drm_legacy_rmmap_ioctl(struct drm_device *dev, void *data,
+			   struct drm_file *file_priv)
 {
 	struct drm_map *request = data;
 	struct drm_local_map *map = NULL;
@@ -546,7 +541,7 @@ int drm_rmmap_ioctl(struct drm_device *dev, void *data,
 		return 0;
 	}
 
-	ret = drm_rmmap_locked(dev, map);
+	ret = drm_legacy_rmmap_locked(dev, map);
 
 	mutex_unlock(&dev->struct_mutex);
 
@@ -599,7 +594,8 @@ static void drm_cleanup_buf_error(struct drm_device * dev,
  * reallocates the buffer list of the same size order to accommodate the new
  * buffers.
  */
-int drm_addbufs_agp(struct drm_device * dev, struct drm_buf_desc * request)
+int drm_legacy_addbufs_agp(struct drm_device *dev,
+			   struct drm_buf_desc *request)
 {
 	struct drm_device_dma *dma = dev->dma;
 	struct drm_buf_entry *entry;
@@ -759,10 +755,11 @@ int drm_addbufs_agp(struct drm_device * dev, struct drm_buf_desc * request)
 	atomic_dec(&dev->buf_alloc);
 	return 0;
 }
-EXPORT_SYMBOL(drm_addbufs_agp);
+EXPORT_SYMBOL(drm_legacy_addbufs_agp);
 #endif				/* __OS_HAS_AGP */
 
-int drm_addbufs_pci(struct drm_device * dev, struct drm_buf_desc * request)
+int drm_legacy_addbufs_pci(struct drm_device *dev,
+			   struct drm_buf_desc *request)
 {
 	struct drm_device_dma *dma = dev->dma;
 	int count;
@@ -964,9 +961,10 @@ int drm_addbufs_pci(struct drm_device * dev, struct drm_buf_desc * request)
 	return 0;
 
 }
-EXPORT_SYMBOL(drm_addbufs_pci);
+EXPORT_SYMBOL(drm_legacy_addbufs_pci);
 
-static int drm_addbufs_sg(struct drm_device * dev, struct drm_buf_desc * request)
+static int drm_legacy_addbufs_sg(struct drm_device *dev,
+				 struct drm_buf_desc *request)
 {
 	struct drm_device_dma *dma = dev->dma;
 	struct drm_buf_entry *entry;
@@ -1135,8 +1133,8 @@ static int drm_addbufs_sg(struct drm_device * dev, struct drm_buf_desc * request
  * addbufs_sg() or addbufs_pci() for AGP, scatter-gather or consistent
  * PCI memory respectively.
  */
-int drm_addbufs(struct drm_device *dev, void *data,
-		struct drm_file *file_priv)
+int drm_legacy_addbufs(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
 {
 	struct drm_buf_desc *request = data;
 	int ret;
@@ -1149,15 +1147,15 @@ int drm_addbufs(struct drm_device *dev, void *data,
 
 #if __OS_HAS_AGP
 	if (request->flags & _DRM_AGP_BUFFER)
-		ret = drm_addbufs_agp(dev, request);
+		ret = drm_legacy_addbufs_agp(dev, request);
 	else
 #endif
 	if (request->flags & _DRM_SG_BUFFER)
-		ret = drm_addbufs_sg(dev, request);
+		ret = drm_legacy_addbufs_sg(dev, request);
 	else if (request->flags & _DRM_FB_BUFFER)
 		ret = -EINVAL;
 	else
-		ret = drm_addbufs_pci(dev, request);
+		ret = drm_legacy_addbufs_pci(dev, request);
 
 	return ret;
 }
@@ -1179,8 +1177,8 @@ int drm_addbufs(struct drm_device *dev, void *data,
  * lock, preventing of allocating more buffers after this call. Information
  * about each requested buffer is then copied into user space.
  */
-int drm_infobufs(struct drm_device *dev, void *data,
-		 struct drm_file *file_priv)
+int drm_legacy_infobufs(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
 {
 	struct drm_device_dma *dma = dev->dma;
 	struct drm_buf_info *request = data;
@@ -1260,8 +1258,8 @@ int drm_infobufs(struct drm_device *dev, void *data,
  *
  * \note This ioctl is deprecated and mostly never used.
  */
-int drm_markbufs(struct drm_device *dev, void *data,
-		 struct drm_file *file_priv)
+int drm_legacy_markbufs(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
 {
 	struct drm_device_dma *dma = dev->dma;
 	struct drm_buf_desc *request = data;
@@ -1307,8 +1305,8 @@ int drm_markbufs(struct drm_device *dev, void *data,
  * Calls free_buffer() for each used buffer.
  * This function is primarily used for debugging.
  */
-int drm_freebufs(struct drm_device *dev, void *data,
-		 struct drm_file *file_priv)
+int drm_legacy_freebufs(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
 {
 	struct drm_device_dma *dma = dev->dma;
 	struct drm_buf_free *request = data;
@@ -1340,7 +1338,7 @@ int drm_freebufs(struct drm_device *dev, void *data,
 				  task_pid_nr(current));
 			return -EINVAL;
 		}
-		drm_free_buffer(dev, buf);
+		drm_legacy_free_buffer(dev, buf);
 	}
 
 	return 0;
@@ -1360,8 +1358,8 @@ int drm_freebufs(struct drm_device *dev, void *data,
  * offset equal to 0, which drm_mmap() interpretes as PCI buffers and calls
  * drm_mmap_dma().
  */
-int drm_mapbufs(struct drm_device *dev, void *data,
-	        struct drm_file *file_priv)
+int drm_legacy_mapbufs(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
 {
 	struct drm_device_dma *dma = dev->dma;
 	int retcode = 0;
@@ -1448,7 +1446,7 @@ int drm_mapbufs(struct drm_device *dev, void *data,
 	return retcode;
 }
 
-int drm_dma_ioctl(struct drm_device *dev, void *data,
+int drm_legacy_dma_ioctl(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
 {
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
@@ -1460,7 +1458,7 @@ int drm_dma_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 }
 
-struct drm_local_map *drm_getsarea(struct drm_device *dev)
+struct drm_local_map *drm_legacy_getsarea(struct drm_device *dev)
 {
 	struct drm_map_list *entry;
 
@@ -1472,4 +1470,4 @@ struct drm_local_map *drm_getsarea(struct drm_device *dev)
 	}
 	return NULL;
 }
-EXPORT_SYMBOL(drm_getsarea);
+EXPORT_SYMBOL(drm_legacy_getsarea);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 90e773019eac..e79c8d3700d8 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -40,106 +40,12 @@
 #include <drm/drm_modeset_lock.h>
 
 #include "drm_crtc_internal.h"
+#include "drm_internal.h"
 
 static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
 							struct drm_mode_fb_cmd2 *r,
 							struct drm_file *file_priv);
 
-/**
- * drm_modeset_lock_all - take all modeset locks
- * @dev: drm device
- *
- * This function takes all modeset locks, suitable where a more fine-grained
- * scheme isn't (yet) implemented. Locks must be dropped with
- * drm_modeset_unlock_all.
- */
-void drm_modeset_lock_all(struct drm_device *dev)
-{
-	struct drm_mode_config *config = &dev->mode_config;
-	struct drm_modeset_acquire_ctx *ctx;
-	int ret;
-
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
-	if (WARN_ON(!ctx))
-		return;
-
-	mutex_lock(&config->mutex);
-
-	drm_modeset_acquire_init(ctx, 0);
-
-retry:
-	ret = drm_modeset_lock(&config->connection_mutex, ctx);
-	if (ret)
-		goto fail;
-	ret = drm_modeset_lock_all_crtcs(dev, ctx);
-	if (ret)
-		goto fail;
-
-	WARN_ON(config->acquire_ctx);
-
-	/* now we hold the locks, so now that it is safe, stash the
-	 * ctx for drm_modeset_unlock_all():
-	 */
-	config->acquire_ctx = ctx;
-
-	drm_warn_on_modeset_not_all_locked(dev);
-
-	return;
-
-fail:
-	if (ret == -EDEADLK) {
-		drm_modeset_backoff(ctx);
-		goto retry;
-	}
-}
-EXPORT_SYMBOL(drm_modeset_lock_all);
-
-/**
- * drm_modeset_unlock_all - drop all modeset locks
- * @dev: device
- *
- * This function drop all modeset locks taken by drm_modeset_lock_all.
- */
-void drm_modeset_unlock_all(struct drm_device *dev)
-{
-	struct drm_mode_config *config = &dev->mode_config;
-	struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx;
-
-	if (WARN_ON(!ctx))
-		return;
-
-	config->acquire_ctx = NULL;
-	drm_modeset_drop_locks(ctx);
-	drm_modeset_acquire_fini(ctx);
-
-	kfree(ctx);
-
-	mutex_unlock(&dev->mode_config.mutex);
-}
-EXPORT_SYMBOL(drm_modeset_unlock_all);
-
-/**
- * drm_warn_on_modeset_not_all_locked - check that all modeset locks are locked
- * @dev: device
- *
- * Useful as a debug assert.
- */
-void drm_warn_on_modeset_not_all_locked(struct drm_device *dev)
-{
-	struct drm_crtc *crtc;
-
-	/* Locking is currently fubar in the panic handler. */
-	if (oops_in_progress)
-		return;
-
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
-		WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
-
-	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
-	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
-}
-EXPORT_SYMBOL(drm_warn_on_modeset_not_all_locked);
-
 /* Avoid boilerplate.  I'm tired of typing. */
 #define DRM_ENUM_NAME_FN(fnname, list)				\
 	const char *fnname(int val)				\
@@ -515,9 +421,6 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb,
 	if (ret)
 		goto out;
 
-	/* Grab the idr reference. */
-	drm_framebuffer_reference(fb);
-
 	dev->mode_config.num_fb++;
 	list_add(&fb->head, &dev->mode_config.fb_list);
 out:
@@ -527,10 +430,34 @@ out:
 }
 EXPORT_SYMBOL(drm_framebuffer_init);
 
+/* dev->mode_config.fb_lock must be held! */
+static void __drm_framebuffer_unregister(struct drm_device *dev,
+					 struct drm_framebuffer *fb)
+{
+	mutex_lock(&dev->mode_config.idr_mutex);
+	idr_remove(&dev->mode_config.crtc_idr, fb->base.id);
+	mutex_unlock(&dev->mode_config.idr_mutex);
+
+	fb->base.id = 0;
+}
+
 static void drm_framebuffer_free(struct kref *kref)
 {
 	struct drm_framebuffer *fb =
 			container_of(kref, struct drm_framebuffer, refcount);
+	struct drm_device *dev = fb->dev;
+
+	/*
+	 * The lookup idr holds a weak reference, which has not necessarily been
+	 * removed at this point. Check for that.
+	 */
+	mutex_lock(&dev->mode_config.fb_lock);
+	if (fb->base.id) {
+		/* Mark fb as reaped and drop idr ref. */
+		__drm_framebuffer_unregister(dev, fb);
+	}
+	mutex_unlock(&dev->mode_config.fb_lock);
+
 	fb->funcs->destroy(fb);
 }
 
@@ -567,8 +494,10 @@ struct drm_framebuffer *drm_framebuffer_lookup(struct drm_device *dev,
 
 	mutex_lock(&dev->mode_config.fb_lock);
 	fb = __drm_framebuffer_lookup(dev, id);
-	if (fb)
-		drm_framebuffer_reference(fb);
+	if (fb) {
+		if (!kref_get_unless_zero(&fb->refcount))
+			fb = NULL;
+	}
 	mutex_unlock(&dev->mode_config.fb_lock);
 
 	return fb;
@@ -612,19 +541,6 @@ static void __drm_framebuffer_unreference(struct drm_framebuffer *fb)
 	kref_put(&fb->refcount, drm_framebuffer_free_bug);
 }
 
-/* dev->mode_config.fb_lock must be held! */
-static void __drm_framebuffer_unregister(struct drm_device *dev,
-					 struct drm_framebuffer *fb)
-{
-	mutex_lock(&dev->mode_config.idr_mutex);
-	idr_remove(&dev->mode_config.crtc_idr, fb->base.id);
-	mutex_unlock(&dev->mode_config.idr_mutex);
-
-	fb->base.id = 0;
-
-	__drm_framebuffer_unreference(fb);
-}
-
 /**
  * drm_framebuffer_unregister_private - unregister a private fb from the lookup idr
  * @fb: fb to unregister
@@ -764,11 +680,7 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 	crtc->funcs = funcs;
 	crtc->invert_dimensions = false;
 
-	drm_modeset_lock_all(dev);
 	drm_modeset_lock_init(&crtc->mutex);
-	/* dropped by _unlock_all(): */
-	drm_modeset_lock(&crtc->mutex, config->acquire_ctx);
-
 	ret = drm_mode_object_get(dev, &crtc->base, DRM_MODE_OBJECT_CRTC);
 	if (ret)
 		goto out;
@@ -786,7 +698,6 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 		cursor->possible_crtcs = 1 << drm_crtc_index(crtc);
 
  out:
-	drm_modeset_unlock_all(dev);
 
 	return ret;
 }
@@ -853,6 +764,59 @@ static void drm_mode_remove(struct drm_connector *connector,
 }
 
 /**
+ * drm_connector_get_cmdline_mode - reads the user's cmdline mode
+ * @connector: connector to quwery
+ * @mode: returned mode
+ *
+ * The kernel supports per-connector configration of its consoles through
+ * use of the video= parameter. This function parses that option and
+ * extracts the user's specified mode (or enable/disable status) for a
+ * particular connector. This is typically only used during the early fbdev
+ * setup.
+ */
+static void drm_connector_get_cmdline_mode(struct drm_connector *connector)
+{
+	struct drm_cmdline_mode *mode = &connector->cmdline_mode;
+	char *option = NULL;
+
+	if (fb_get_options(connector->name, &option))
+		return;
+
+	if (!drm_mode_parse_command_line_for_connector(option,
+						       connector,
+						       mode))
+		return;
+
+	if (mode->force) {
+		const char *s;
+
+		switch (mode->force) {
+		case DRM_FORCE_OFF:
+			s = "OFF";
+			break;
+		case DRM_FORCE_ON_DIGITAL:
+			s = "ON - dig";
+			break;
+		default:
+		case DRM_FORCE_ON:
+			s = "ON";
+			break;
+		}
+
+		DRM_INFO("forcing %s connector %s\n", connector->name, s);
+		connector->force = mode->force;
+	}
+
+	DRM_DEBUG_KMS("cmdline mode for connector %s %dx%d@%dHz%s%s%s\n",
+		      connector->name,
+		      mode->xres, mode->yres,
+		      mode->refresh_specified ? mode->refresh : 60,
+		      mode->rb ? " reduced blanking" : "",
+		      mode->margins ? " with margins" : "",
+		      mode->interlace ?  " interlaced" : "");
+}
+
+/**
  * drm_connector_init - Init a preallocated connector
  * @dev: DRM device
  * @connector: the connector to init
@@ -904,6 +868,8 @@ int drm_connector_init(struct drm_device *dev,
 	connector->edid_blob_ptr = NULL;
 	connector->status = connector_status_unknown;
 
+	drm_connector_get_cmdline_mode(connector);
+
 	list_add_tail(&connector->head, &dev->mode_config.connector_list);
 	dev->mode_config.num_connector++;
 
@@ -957,6 +923,29 @@ void drm_connector_cleanup(struct drm_connector *connector)
 EXPORT_SYMBOL(drm_connector_cleanup);
 
 /**
+ * drm_connector_index - find the index of a registered connector
+ * @connector: connector to find index for
+ *
+ * Given a registered connector, return the index of that connector within a DRM
+ * device's list of connectors.
+ */
+unsigned int drm_connector_index(struct drm_connector *connector)
+{
+	unsigned int index = 0;
+	struct drm_connector *tmp;
+
+	list_for_each_entry(tmp, &connector->dev->mode_config.connector_list, head) {
+		if (tmp == connector)
+			return index;
+
+		index++;
+	}
+
+	BUG();
+}
+EXPORT_SYMBOL(drm_connector_index);
+
+/**
  * drm_connector_register - register a connector
  * @connector: the connector to register
  *
@@ -1261,6 +1250,29 @@ void drm_plane_cleanup(struct drm_plane *plane)
 EXPORT_SYMBOL(drm_plane_cleanup);
 
 /**
+ * drm_plane_index - find the index of a registered plane
+ * @plane: plane to find index for
+ *
+ * Given a registered plane, return the index of that CRTC within a DRM
+ * device's list of planes.
+ */
+unsigned int drm_plane_index(struct drm_plane *plane)
+{
+	unsigned int index = 0;
+	struct drm_plane *tmp;
+
+	list_for_each_entry(tmp, &plane->dev->mode_config.plane_list, head) {
+		if (tmp == plane)
+			return index;
+
+		index++;
+	}
+
+	BUG();
+}
+EXPORT_SYMBOL(drm_plane_index);
+
+/**
  * drm_plane_force_disable - Forcibly disable a plane
  * @plane: plane to disable
  *
@@ -1271,19 +1283,21 @@ EXPORT_SYMBOL(drm_plane_cleanup);
  */
 void drm_plane_force_disable(struct drm_plane *plane)
 {
-	struct drm_framebuffer *old_fb = plane->fb;
 	int ret;
 
-	if (!old_fb)
+	if (!plane->fb)
 		return;
 
+	plane->old_fb = plane->fb;
 	ret = plane->funcs->disable_plane(plane);
 	if (ret) {
 		DRM_ERROR("failed to disable plane with busy fb\n");
+		plane->old_fb = NULL;
 		return;
 	}
 	/* disconnect the plane from the fb and crtc: */
-	__drm_framebuffer_unreference(old_fb);
+	__drm_framebuffer_unreference(plane->old_fb);
+	plane->old_fb = NULL;
 	plane->fb = NULL;
 	plane->crtc = NULL;
 }
@@ -2249,33 +2263,29 @@ out:
  *
  * src_{x,y,w,h} are provided in 16.16 fixed point format
  */
-static int setplane_internal(struct drm_plane *plane,
-			     struct drm_crtc *crtc,
-			     struct drm_framebuffer *fb,
-			     int32_t crtc_x, int32_t crtc_y,
-			     uint32_t crtc_w, uint32_t crtc_h,
-			     /* src_{x,y,w,h} values are 16.16 fixed point */
-			     uint32_t src_x, uint32_t src_y,
-			     uint32_t src_w, uint32_t src_h)
+static int __setplane_internal(struct drm_plane *plane,
+			       struct drm_crtc *crtc,
+			       struct drm_framebuffer *fb,
+			       int32_t crtc_x, int32_t crtc_y,
+			       uint32_t crtc_w, uint32_t crtc_h,
+			       /* src_{x,y,w,h} values are 16.16 fixed point */
+			       uint32_t src_x, uint32_t src_y,
+			       uint32_t src_w, uint32_t src_h)
 {
-	struct drm_device *dev = plane->dev;
-	struct drm_framebuffer *old_fb = NULL;
 	int ret = 0;
 	unsigned int fb_width, fb_height;
 	int i;
 
 	/* No fb means shut it down */
 	if (!fb) {
-		drm_modeset_lock_all(dev);
-		old_fb = plane->fb;
+		plane->old_fb = plane->fb;
 		ret = plane->funcs->disable_plane(plane);
 		if (!ret) {
 			plane->crtc = NULL;
 			plane->fb = NULL;
 		} else {
-			old_fb = NULL;
+			plane->old_fb = NULL;
 		}
-		drm_modeset_unlock_all(dev);
 		goto out;
 	}
 
@@ -2315,8 +2325,7 @@ static int setplane_internal(struct drm_plane *plane,
 		goto out;
 	}
 
-	drm_modeset_lock_all(dev);
-	old_fb = plane->fb;
+	plane->old_fb = plane->fb;
 	ret = plane->funcs->update_plane(plane, crtc, fb,
 					 crtc_x, crtc_y, crtc_w, crtc_h,
 					 src_x, src_y, src_w, src_h);
@@ -2325,18 +2334,37 @@ static int setplane_internal(struct drm_plane *plane,
 		plane->fb = fb;
 		fb = NULL;
 	} else {
-		old_fb = NULL;
+		plane->old_fb = NULL;
 	}
-	drm_modeset_unlock_all(dev);
 
 out:
 	if (fb)
 		drm_framebuffer_unreference(fb);
-	if (old_fb)
-		drm_framebuffer_unreference(old_fb);
+	if (plane->old_fb)
+		drm_framebuffer_unreference(plane->old_fb);
+	plane->old_fb = NULL;
 
 	return ret;
+}
+
+static int setplane_internal(struct drm_plane *plane,
+			     struct drm_crtc *crtc,
+			     struct drm_framebuffer *fb,
+			     int32_t crtc_x, int32_t crtc_y,
+			     uint32_t crtc_w, uint32_t crtc_h,
+			     /* src_{x,y,w,h} values are 16.16 fixed point */
+			     uint32_t src_x, uint32_t src_y,
+			     uint32_t src_w, uint32_t src_h)
+{
+	int ret;
+
+	drm_modeset_lock_all(plane->dev);
+	ret = __setplane_internal(plane, crtc, fb,
+				  crtc_x, crtc_y, crtc_w, crtc_h,
+				  src_x, src_y, src_w, src_h);
+	drm_modeset_unlock_all(plane->dev);
 
+	return ret;
 }
 
 /**
@@ -2440,7 +2468,7 @@ int drm_mode_set_config_internal(struct drm_mode_set *set)
 	 * crtcs. Atomic modeset will have saner semantics ...
 	 */
 	list_for_each_entry(tmp, &crtc->dev->mode_config.crtc_list, head)
-		tmp->old_fb = tmp->primary->fb;
+		tmp->primary->old_fb = tmp->primary->fb;
 
 	fb = set->fb;
 
@@ -2453,8 +2481,9 @@ int drm_mode_set_config_internal(struct drm_mode_set *set)
 	list_for_each_entry(tmp, &crtc->dev->mode_config.crtc_list, head) {
 		if (tmp->primary->fb)
 			drm_framebuffer_reference(tmp->primary->fb);
-		if (tmp->old_fb)
-			drm_framebuffer_unreference(tmp->old_fb);
+		if (tmp->primary->old_fb)
+			drm_framebuffer_unreference(tmp->primary->old_fb);
+		tmp->primary->old_fb = NULL;
 	}
 
 	return ret;
@@ -2701,6 +2730,7 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 	int ret = 0;
 
 	BUG_ON(!crtc->cursor);
+	WARN_ON(crtc->cursor->crtc != crtc && crtc->cursor->crtc != NULL);
 
 	/*
 	 * Obtain fb we'll be using (either new or existing) and take an extra
@@ -2720,11 +2750,9 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 			fb = NULL;
 		}
 	} else {
-		mutex_lock(&dev->mode_config.mutex);
 		fb = crtc->cursor->fb;
 		if (fb)
 			drm_framebuffer_reference(fb);
-		mutex_unlock(&dev->mode_config.mutex);
 	}
 
 	if (req->flags & DRM_MODE_CURSOR_MOVE) {
@@ -2746,7 +2774,7 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 	 * setplane_internal will take care of deref'ing either the old or new
 	 * framebuffer depending on success.
 	 */
-	ret = setplane_internal(crtc->cursor, crtc, fb,
+	ret = __setplane_internal(crtc->cursor, crtc, fb,
 				crtc_x, crtc_y, crtc_w, crtc_h,
 				0, 0, src_w, src_h);
 
@@ -2782,10 +2810,12 @@ static int drm_mode_cursor_common(struct drm_device *dev,
 	 * If this crtc has a universal cursor plane, call that plane's update
 	 * handler rather than using legacy cursor handlers.
 	 */
-	if (crtc->cursor)
-		return drm_mode_cursor_universal(crtc, req, file_priv);
+	drm_modeset_lock_crtc(crtc);
+	if (crtc->cursor) {
+		ret = drm_mode_cursor_universal(crtc, req, file_priv);
+		goto out;
+	}
 
-	drm_modeset_lock(&crtc->mutex, NULL);
 	if (req->flags & DRM_MODE_CURSOR_BO) {
 		if (!crtc->funcs->cursor_set && !crtc->funcs->cursor_set2) {
 			ret = -ENXIO;
@@ -2809,7 +2839,7 @@ static int drm_mode_cursor_common(struct drm_device *dev,
 		}
 	}
 out:
-	drm_modeset_unlock(&crtc->mutex);
+	drm_modeset_unlock_crtc(crtc);
 
 	return ret;
 
@@ -3370,7 +3400,16 @@ void drm_fb_release(struct drm_file *priv)
 	struct drm_device *dev = priv->minor->dev;
 	struct drm_framebuffer *fb, *tfb;
 
-	mutex_lock(&priv->fbs_lock);
+	/*
+	 * When the file gets released that means no one else can access the fb
+	 * list any more, so no need to grab fpriv->fbs_lock. And we need to to
+	 * avoid upsetting lockdep since the universal cursor code adds a
+	 * framebuffer while holding mutex locks.
+	 *
+	 * Note that a real deadlock between fpriv->fbs_lock and the modeset
+	 * locks is impossible here since no one else but this function can get
+	 * at it any more.
+	 */
 	list_for_each_entry_safe(fb, tfb, &priv->fbs, filp_head) {
 
 		mutex_lock(&dev->mode_config.fb_lock);
@@ -3383,7 +3422,6 @@ void drm_fb_release(struct drm_file *priv)
 		/* This will also drop the fpriv->fbs reference. */
 		drm_framebuffer_remove(fb);
 	}
-	mutex_unlock(&priv->fbs_lock);
 }
 
 /**
@@ -3495,9 +3533,10 @@ EXPORT_SYMBOL(drm_property_create_enum);
  * @flags: flags specifying the property type
  * @name: name of the property
  * @props: enumeration lists with property bitflags
- * @num_values: number of pre-defined values
+ * @num_props: size of the @props array
+ * @supported_bits: bitmask of all supported enumeration values
  *
- * This creates a new generic drm property which can then be attached to a drm
+ * This creates a new bitmask drm property which can then be attached to a drm
  * object with drm_object_attach_property. The returned property object must be
  * freed with drm_property_destroy.
  *
@@ -4157,12 +4196,25 @@ static int drm_mode_crtc_set_obj_prop(struct drm_mode_object *obj,
 	return ret;
 }
 
-static int drm_mode_plane_set_obj_prop(struct drm_mode_object *obj,
-				      struct drm_property *property,
-				      uint64_t value)
+/**
+ * drm_mode_plane_set_obj_prop - set the value of a property
+ * @plane: drm plane object to set property value for
+ * @property: property to set
+ * @value: value the property should be set to
+ *
+ * This functions sets a given property on a given plane object. This function
+ * calls the driver's ->set_property callback and changes the software state of
+ * the property if the callback succeeds.
+ *
+ * Returns:
+ * Zero on success, error code on failure.
+ */
+int drm_mode_plane_set_obj_prop(struct drm_plane *plane,
+				struct drm_property *property,
+				uint64_t value)
 {
 	int ret = -EINVAL;
-	struct drm_plane *plane = obj_to_plane(obj);
+	struct drm_mode_object *obj = &plane->base;
 
 	if (plane->funcs->set_property)
 		ret = plane->funcs->set_property(plane, property, value);
@@ -4171,6 +4223,7 @@ static int drm_mode_plane_set_obj_prop(struct drm_mode_object *obj,
 
 	return ret;
 }
+EXPORT_SYMBOL(drm_mode_plane_set_obj_prop);
 
 /**
  * drm_mode_getproperty_ioctl - get the current value of a object's property
@@ -4309,7 +4362,8 @@ int drm_mode_obj_set_property_ioctl(struct drm_device *dev, void *data,
 		ret = drm_mode_crtc_set_obj_prop(arg_obj, property, arg->value);
 		break;
 	case DRM_MODE_OBJECT_PLANE:
-		ret = drm_mode_plane_set_obj_prop(arg_obj, property, arg->value);
+		ret = drm_mode_plane_set_obj_prop(obj_to_plane(arg_obj),
+						  property, arg->value);
 		break;
 	}
 
@@ -4529,7 +4583,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 {
 	struct drm_mode_crtc_page_flip *page_flip = data;
 	struct drm_crtc *crtc;
-	struct drm_framebuffer *fb = NULL, *old_fb = NULL;
+	struct drm_framebuffer *fb = NULL;
 	struct drm_pending_vblank_event *e = NULL;
 	unsigned long flags;
 	int ret = -EINVAL;
@@ -4545,7 +4599,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 	if (!crtc)
 		return -ENOENT;
 
-	drm_modeset_lock(&crtc->mutex, NULL);
+	drm_modeset_lock_crtc(crtc);
 	if (crtc->primary->fb == NULL) {
 		/* The framebuffer is currently unbound, presumably
 		 * due to a hotplug event, that userspace has not
@@ -4601,7 +4655,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 			(void (*) (struct drm_pending_event *)) kfree;
 	}
 
-	old_fb = crtc->primary->fb;
+	crtc->primary->old_fb = crtc->primary->fb;
 	ret = crtc->funcs->page_flip(crtc, fb, e, page_flip->flags);
 	if (ret) {
 		if (page_flip->flags & DRM_MODE_PAGE_FLIP_EVENT) {
@@ -4611,7 +4665,7 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 			kfree(e);
 		}
 		/* Keep the old fb, don't unref it. */
-		old_fb = NULL;
+		crtc->primary->old_fb = NULL;
 	} else {
 		/*
 		 * Warn if the driver hasn't properly updated the crtc->fb
@@ -4627,9 +4681,10 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 out:
 	if (fb)
 		drm_framebuffer_unreference(fb);
-	if (old_fb)
-		drm_framebuffer_unreference(old_fb);
-	drm_modeset_unlock(&crtc->mutex);
+	if (crtc->primary->old_fb)
+		drm_framebuffer_unreference(crtc->primary->old_fb);
+	crtc->primary->old_fb = NULL;
+	drm_modeset_unlock_crtc(crtc);
 
 	return ret;
 }
@@ -4645,9 +4700,14 @@ out:
 void drm_mode_config_reset(struct drm_device *dev)
 {
 	struct drm_crtc *crtc;
+	struct drm_plane *plane;
 	struct drm_encoder *encoder;
 	struct drm_connector *connector;
 
+	list_for_each_entry(plane, &dev->mode_config.plane_list, head)
+		if (plane->funcs->reset)
+			plane->funcs->reset(plane);
+
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
 		if (crtc->funcs->reset)
 			crtc->funcs->reset(crtc);
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index 13bd42923dd4..3bcf8e6a85b3 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -36,6 +36,7 @@
 #include <linux/export.h>
 #include <drm/drmP.h>
 #include <drm/drm_edid.h>
+#include "drm_internal.h"
 
 #if defined(CONFIG_DEBUG_FS)
 
@@ -49,9 +50,7 @@ static const struct drm_info_list drm_debugfs_list[] = {
 	{"clients", drm_clients_info, 0},
 	{"bufs", drm_bufs_info, 0},
 	{"gem_names", drm_gem_name_info, DRIVER_GEM},
-#if DRM_DEBUG_CODE
 	{"vma", drm_vma_info, 0},
-#endif
 };
 #define DRM_DEBUGFS_ENTRIES ARRAY_SIZE(drm_debugfs_list)
 
diff --git a/drivers/gpu/drm/drm_dma.c b/drivers/gpu/drm/drm_dma.c
index 8a140a953754..ea481800ef56 100644
--- a/drivers/gpu/drm/drm_dma.c
+++ b/drivers/gpu/drm/drm_dma.c
@@ -35,6 +35,7 @@
 
 #include <linux/export.h>
 #include <drm/drmP.h>
+#include "drm_legacy.h"
 
 /**
  * Initialize the DMA data.
@@ -124,7 +125,7 @@ void drm_legacy_dma_takedown(struct drm_device *dev)
  *
  * Resets the fields of \p buf.
  */
-void drm_free_buffer(struct drm_device *dev, struct drm_buf * buf)
+void drm_legacy_free_buffer(struct drm_device *dev, struct drm_buf * buf)
 {
 	if (!buf)
 		return;
@@ -142,8 +143,8 @@ void drm_free_buffer(struct drm_device *dev, struct drm_buf * buf)
  *
  * Frees each buffer associated with \p file_priv not already on the hardware.
  */
-void drm_core_reclaim_buffers(struct drm_device *dev,
-			      struct drm_file *file_priv)
+void drm_legacy_reclaim_buffers(struct drm_device *dev,
+				struct drm_file *file_priv)
 {
 	struct drm_device_dma *dma = dev->dma;
 	int i;
@@ -154,7 +155,7 @@ void drm_core_reclaim_buffers(struct drm_device *dev,
 		if (dma->buflist[i]->file_priv == file_priv) {
 			switch (dma->buflist[i]->list) {
 			case DRM_LIST_NONE:
-				drm_free_buffer(dev, dma->buflist[i]);
+				drm_legacy_free_buffer(dev, dma->buflist[i]);
 				break;
 			case DRM_LIST_WAIT:
 				dma->buflist[i]->list = DRM_LIST_RECLAIM;
@@ -166,5 +167,3 @@ void drm_core_reclaim_buffers(struct drm_device *dev,
 		}
 	}
 }
-
-EXPORT_SYMBOL(drm_core_reclaim_buffers);
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index ac3c2738db94..070f913d2dba 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -682,7 +682,7 @@ static int build_allocate_payload(struct drm_dp_sideband_msg_tx *msg, int port_n
 static int drm_dp_mst_assign_payload_id(struct drm_dp_mst_topology_mgr *mgr,
 					struct drm_dp_vcpi *vcpi)
 {
-	int ret;
+	int ret, vcpi_ret;
 
 	mutex_lock(&mgr->payload_lock);
 	ret = find_first_zero_bit(&mgr->payload_mask, mgr->max_payloads + 1);
@@ -692,8 +692,16 @@ static int drm_dp_mst_assign_payload_id(struct drm_dp_mst_topology_mgr *mgr,
 		goto out_unlock;
 	}
 
+	vcpi_ret = find_first_zero_bit(&mgr->vcpi_mask, mgr->max_payloads + 1);
+	if (vcpi_ret > mgr->max_payloads) {
+		ret = -EINVAL;
+		DRM_DEBUG_KMS("out of vcpi ids %d\n", ret);
+		goto out_unlock;
+	}
+
 	set_bit(ret, &mgr->payload_mask);
-	vcpi->vcpi = ret;
+	set_bit(vcpi_ret, &mgr->vcpi_mask);
+	vcpi->vcpi = vcpi_ret + 1;
 	mgr->proposed_vcpis[ret - 1] = vcpi;
 out_unlock:
 	mutex_unlock(&mgr->payload_lock);
@@ -701,15 +709,23 @@ out_unlock:
 }
 
 static void drm_dp_mst_put_payload_id(struct drm_dp_mst_topology_mgr *mgr,
-				      int id)
+				      int vcpi)
 {
-	if (id == 0)
+	int i;
+	if (vcpi == 0)
 		return;
 
 	mutex_lock(&mgr->payload_lock);
-	DRM_DEBUG_KMS("putting payload %d\n", id);
-	clear_bit(id, &mgr->payload_mask);
-	mgr->proposed_vcpis[id - 1] = NULL;
+	DRM_DEBUG_KMS("putting payload %d\n", vcpi);
+	clear_bit(vcpi - 1, &mgr->vcpi_mask);
+
+	for (i = 0; i < mgr->max_payloads; i++) {
+		if (mgr->proposed_vcpis[i])
+			if (mgr->proposed_vcpis[i]->vcpi == vcpi) {
+				mgr->proposed_vcpis[i] = NULL;
+				clear_bit(i + 1, &mgr->payload_mask);
+			}
+	}
 	mutex_unlock(&mgr->payload_lock);
 }
 
@@ -1563,7 +1579,7 @@ static int drm_dp_destroy_payload_step1(struct drm_dp_mst_topology_mgr *mgr,
 	}
 
 	drm_dp_dpcd_write_payload(mgr, id, payload);
-	payload->payload_state = 0;
+	payload->payload_state = DP_PAYLOAD_DELETE_LOCAL;
 	return 0;
 }
 
@@ -1590,7 +1606,7 @@ static int drm_dp_destroy_payload_step2(struct drm_dp_mst_topology_mgr *mgr,
  */
 int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 {
-	int i;
+	int i, j;
 	int cur_slots = 1;
 	struct drm_dp_payload req_payload;
 	struct drm_dp_mst_port *port;
@@ -1607,26 +1623,46 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 			port = NULL;
 			req_payload.num_slots = 0;
 		}
+
+		if (mgr->payloads[i].start_slot != req_payload.start_slot) {
+			mgr->payloads[i].start_slot = req_payload.start_slot;
+		}
 		/* work out what is required to happen with this payload */
-		if (mgr->payloads[i].start_slot != req_payload.start_slot ||
-		    mgr->payloads[i].num_slots != req_payload.num_slots) {
+		if (mgr->payloads[i].num_slots != req_payload.num_slots) {
 
 			/* need to push an update for this payload */
 			if (req_payload.num_slots) {
-				drm_dp_create_payload_step1(mgr, i + 1, &req_payload);
+				drm_dp_create_payload_step1(mgr, mgr->proposed_vcpis[i]->vcpi, &req_payload);
 				mgr->payloads[i].num_slots = req_payload.num_slots;
 			} else if (mgr->payloads[i].num_slots) {
 				mgr->payloads[i].num_slots = 0;
-				drm_dp_destroy_payload_step1(mgr, port, i + 1, &mgr->payloads[i]);
+				drm_dp_destroy_payload_step1(mgr, port, port->vcpi.vcpi, &mgr->payloads[i]);
 				req_payload.payload_state = mgr->payloads[i].payload_state;
-			} else
-				req_payload.payload_state = 0;
-
-			mgr->payloads[i].start_slot = req_payload.start_slot;
+				mgr->payloads[i].start_slot = 0;
+			}
 			mgr->payloads[i].payload_state = req_payload.payload_state;
 		}
 		cur_slots += req_payload.num_slots;
 	}
+
+	for (i = 0; i < mgr->max_payloads; i++) {
+		if (mgr->payloads[i].payload_state == DP_PAYLOAD_DELETE_LOCAL) {
+			DRM_DEBUG_KMS("removing payload %d\n", i);
+			for (j = i; j < mgr->max_payloads - 1; j++) {
+				memcpy(&mgr->payloads[j], &mgr->payloads[j + 1], sizeof(struct drm_dp_payload));
+				mgr->proposed_vcpis[j] = mgr->proposed_vcpis[j + 1];
+				if (mgr->proposed_vcpis[j] && mgr->proposed_vcpis[j]->num_slots) {
+					set_bit(j + 1, &mgr->payload_mask);
+				} else {
+					clear_bit(j + 1, &mgr->payload_mask);
+				}
+			}
+			memset(&mgr->payloads[mgr->max_payloads - 1], 0, sizeof(struct drm_dp_payload));
+			mgr->proposed_vcpis[mgr->max_payloads - 1] = NULL;
+			clear_bit(mgr->max_payloads, &mgr->payload_mask);
+
+		}
+	}
 	mutex_unlock(&mgr->payload_lock);
 
 	return 0;
@@ -1657,9 +1693,9 @@ int drm_dp_update_payload_part2(struct drm_dp_mst_topology_mgr *mgr)
 
 		DRM_DEBUG_KMS("payload %d %d\n", i, mgr->payloads[i].payload_state);
 		if (mgr->payloads[i].payload_state == DP_PAYLOAD_LOCAL) {
-			ret = drm_dp_create_payload_step2(mgr, port, i + 1, &mgr->payloads[i]);
+			ret = drm_dp_create_payload_step2(mgr, port, mgr->proposed_vcpis[i]->vcpi, &mgr->payloads[i]);
 		} else if (mgr->payloads[i].payload_state == DP_PAYLOAD_DELETE_LOCAL) {
-			ret = drm_dp_destroy_payload_step2(mgr, i + 1, &mgr->payloads[i]);
+			ret = drm_dp_destroy_payload_step2(mgr, mgr->proposed_vcpis[i]->vcpi, &mgr->payloads[i]);
 		}
 		if (ret) {
 			mutex_unlock(&mgr->payload_lock);
@@ -1772,7 +1808,7 @@ static int drm_dp_get_vc_payload_bw(int dp_link_bw, int dp_link_count)
 	case DP_LINK_BW_5_4:
 		return 10 * dp_link_count;
 	}
-	return 0;
+	BUG();
 }
 
 /**
@@ -1861,6 +1897,7 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms
 		memset(mgr->payloads, 0, mgr->max_payloads * sizeof(struct drm_dp_payload));
 		mgr->payload_mask = 0;
 		set_bit(0, &mgr->payload_mask);
+		mgr->vcpi_mask = 0;
 	}
 
 out_unlock:
@@ -2071,6 +2108,7 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
  * drm_dp_mst_hpd_irq() - MST hotplug IRQ notify
  * @mgr: manager to notify irq for.
  * @esi: 4 bytes from SINK_COUNT_ESI
+ * @handled: whether the hpd interrupt was consumed or not
  *
  * This should be called from the driver when it detects a short IRQ,
  * along with the value of the DEVICE_SERVICE_IRQ_VECTOR_ESI0. The
@@ -2474,7 +2512,7 @@ void drm_dp_mst_dump_topology(struct seq_file *m,
 	mutex_unlock(&mgr->lock);
 
 	mutex_lock(&mgr->payload_lock);
-	seq_printf(m, "vcpi: %lx\n", mgr->payload_mask);
+	seq_printf(m, "vcpi: %lx %lx\n", mgr->payload_mask, mgr->vcpi_mask);
 
 	for (i = 0; i < mgr->max_payloads; i++) {
 		if (mgr->proposed_vcpis[i]) {
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 3242e208c0d0..bc3da32d4585 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -35,32 +35,20 @@
 #include <drm/drmP.h>
 #include <drm/drm_core.h>
 #include "drm_legacy.h"
+#include "drm_internal.h"
 
 unsigned int drm_debug = 0;	/* 1 to enable debug output */
 EXPORT_SYMBOL(drm_debug);
 
-unsigned int drm_vblank_offdelay = 5000;    /* Default to 5000 msecs. */
-
-unsigned int drm_timestamp_precision = 20;  /* Default to 20 usecs. */
-
-/*
- * Default to use monotonic timestamps for wait-for-vblank and page-flip
- * complete events.
- */
-unsigned int drm_timestamp_monotonic = 1;
-
 MODULE_AUTHOR(CORE_AUTHOR);
 MODULE_DESCRIPTION(CORE_DESC);
 MODULE_LICENSE("GPL and additional rights");
 MODULE_PARM_DESC(debug, "Enable debug output");
-MODULE_PARM_DESC(vblankoffdelay, "Delay until vblank irq auto-disable [msecs]");
+MODULE_PARM_DESC(vblankoffdelay, "Delay until vblank irq auto-disable [msecs] (0: never disable, <0: disable immediately)");
 MODULE_PARM_DESC(timestamp_precision_usec, "Max. error on timestamps [usecs]");
 MODULE_PARM_DESC(timestamp_monotonic, "Use monotonic timestamps");
 
 module_param_named(debug, drm_debug, int, 0600);
-module_param_named(vblankoffdelay, drm_vblank_offdelay, int, 0600);
-module_param_named(timestamp_precision_usec, drm_timestamp_precision, int, 0600);
-module_param_named(timestamp_monotonic, drm_timestamp_monotonic, int, 0600);
 
 static DEFINE_SPINLOCK(drm_minor_lock);
 static struct idr drm_minors_idr;
@@ -68,22 +56,19 @@ static struct idr drm_minors_idr;
 struct class *drm_class;
 static struct dentry *drm_debugfs_root;
 
-int drm_err(const char *func, const char *format, ...)
+void drm_err(const char *func, const char *format, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int r;
 
 	va_start(args, format);
 
 	vaf.fmt = format;
 	vaf.va = &args;
 
-	r = printk(KERN_ERR "[" DRM_NAME ":%s] *ERROR* %pV", func, &vaf);
+	printk(KERN_ERR "[" DRM_NAME ":%s] *ERROR* %pV", func, &vaf);
 
 	va_end(args);
-
-	return r;
 }
 EXPORT_SYMBOL(drm_err);
 
@@ -102,6 +87,8 @@ void drm_ut_debug_printk(const char *function_name, const char *format, ...)
 }
 EXPORT_SYMBOL(drm_ut_debug_printk);
 
+#define DRM_MAGIC_HASH_ORDER  4  /**< Size of key hash table. Must be power of 2. */
+
 struct drm_master *drm_master_create(struct drm_minor *minor)
 {
 	struct drm_master *master;
@@ -133,7 +120,6 @@ EXPORT_SYMBOL(drm_master_get);
 static void drm_master_destroy(struct kref *kref)
 {
 	struct drm_master *master = container_of(kref, struct drm_master, refcount);
-	struct drm_magic_entry *pt, *next;
 	struct drm_device *dev = master->minor->dev;
 	struct drm_map_list *r_list, *list_temp;
 
@@ -143,7 +129,7 @@ static void drm_master_destroy(struct kref *kref)
 
 	list_for_each_entry_safe(r_list, list_temp, &dev->maplist, head) {
 		if (r_list->master == master) {
-			drm_rmmap_locked(dev, r_list->map);
+			drm_legacy_rmmap_locked(dev, r_list->map);
 			r_list = NULL;
 		}
 	}
@@ -154,12 +140,6 @@ static void drm_master_destroy(struct kref *kref)
 		master->unique_len = 0;
 	}
 
-	list_for_each_entry_safe(pt, next, &master->magicfree, head) {
-		list_del(&pt->head);
-		drm_ht_remove_item(&master->magiclist, &pt->hash_item);
-		kfree(pt);
-	}
-
 	drm_ht_remove(&master->magiclist);
 
 	mutex_unlock(&dev->struct_mutex);
@@ -615,7 +595,7 @@ struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 		goto err_ht;
 	}
 
-	if (driver->driver_features & DRIVER_GEM) {
+	if (drm_core_check_feature(dev, DRIVER_GEM)) {
 		ret = drm_gem_init(dev);
 		if (ret) {
 			DRM_ERROR("Cannot initialize graphics execution manager (GEM)\n");
@@ -645,7 +625,7 @@ static void drm_dev_release(struct kref *ref)
 {
 	struct drm_device *dev = container_of(ref, struct drm_device, ref);
 
-	if (dev->driver->driver_features & DRIVER_GEM)
+	if (drm_core_check_feature(dev, DRIVER_GEM))
 		drm_gem_destroy(dev);
 
 	drm_legacy_ctxbitmap_cleanup(dev);
@@ -779,7 +759,7 @@ void drm_dev_unregister(struct drm_device *dev)
 	drm_vblank_cleanup(dev);
 
 	list_for_each_entry_safe(r_list, list_temp, &dev->maplist, head)
-		drm_rmmap(dev, r_list->map);
+		drm_legacy_rmmap(dev, r_list->map);
 
 	drm_minor_unregister(dev, DRM_MINOR_LEGACY);
 	drm_minor_unregister(dev, DRM_MINOR_RENDER);
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 1dbf3bc4c6a3..3bf999134bcc 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -632,27 +632,27 @@ static const struct drm_display_mode edid_cea_modes[] = {
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC |
 			DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 6 - 1440x480i@60Hz */
-	{ DRM_MODE("1440x480i", DRM_MODE_TYPE_DRIVER, 27000, 1440, 1478,
-		   1602, 1716, 0, 480, 488, 494, 525, 0,
+	/* 6 - 720(1440)x480i@60Hz */
+	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
+		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 7 - 1440x480i@60Hz */
-	{ DRM_MODE("1440x480i", DRM_MODE_TYPE_DRIVER, 27000, 1440, 1478,
-		   1602, 1716, 0, 480, 488, 494, 525, 0,
+	/* 7 - 720(1440)x480i@60Hz */
+	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
+		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 8 - 1440x240@60Hz */
-	{ DRM_MODE("1440x240", DRM_MODE_TYPE_DRIVER, 27000, 1440, 1478,
-		   1602, 1716, 0, 240, 244, 247, 262, 0,
+	/* 8 - 720(1440)x240@60Hz */
+	{ DRM_MODE("720x240", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
+		   801, 858, 0, 240, 244, 247, 262, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 9 - 1440x240@60Hz */
-	{ DRM_MODE("1440x240", DRM_MODE_TYPE_DRIVER, 27000, 1440, 1478,
-		   1602, 1716, 0, 240, 244, 247, 262, 0,
+	/* 9 - 720(1440)x240@60Hz */
+	{ DRM_MODE("720x240", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
+		   801, 858, 0, 240, 244, 247, 262, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
@@ -714,27 +714,27 @@ static const struct drm_display_mode edid_cea_modes[] = {
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC |
 			DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 21 - 1440x576i@50Hz */
-	{ DRM_MODE("1440x576i", DRM_MODE_TYPE_DRIVER, 27000, 1440, 1464,
-		   1590, 1728, 0, 576, 580, 586, 625, 0,
+	/* 21 - 720(1440)x576i@50Hz */
+	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
+		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 22 - 1440x576i@50Hz */
-	{ DRM_MODE("1440x576i", DRM_MODE_TYPE_DRIVER, 27000, 1440, 1464,
-		   1590, 1728, 0, 576, 580, 586, 625, 0,
+	/* 22 - 720(1440)x576i@50Hz */
+	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
+		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 23 - 1440x288@50Hz */
-	{ DRM_MODE("1440x288", DRM_MODE_TYPE_DRIVER, 27000, 1440, 1464,
-		   1590, 1728, 0, 288, 290, 293, 312, 0,
+	/* 23 - 720(1440)x288@50Hz */
+	{ DRM_MODE("720x288", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
+		   795, 864, 0, 288, 290, 293, 312, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 24 - 1440x288@50Hz */
-	{ DRM_MODE("1440x288", DRM_MODE_TYPE_DRIVER, 27000, 1440, 1464,
-		   1590, 1728, 0, 288, 290, 293, 312, 0,
+	/* 24 - 720(1440)x288@50Hz */
+	{ DRM_MODE("720x288", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
+		   795, 864, 0, 288, 290, 293, 312, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
@@ -837,17 +837,17 @@ static const struct drm_display_mode edid_cea_modes[] = {
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 44 - 1440x576i@100Hz */
-	{ DRM_MODE("1440x576", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1464,
-		   1590, 1728, 0, 576, 580, 586, 625, 0,
+	/* 44 - 720(1440)x576i@100Hz */
+	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 27000, 720, 732,
+		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_DBLCLK),
+			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 45 - 1440x576i@100Hz */
-	{ DRM_MODE("1440x576", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1464,
-		   1590, 1728, 0, 576, 580, 586, 625, 0,
+	/* 45 - 720(1440)x576i@100Hz */
+	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 27000, 720, 732,
+		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_DBLCLK),
+			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
 	/* 46 - 1920x1080i@120Hz */
 	{ DRM_MODE("1920x1080i", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2008,
@@ -870,15 +870,15 @@ static const struct drm_display_mode edid_cea_modes[] = {
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 50 - 1440x480i@120Hz */
-	{ DRM_MODE("1440x480i", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1478,
-		   1602, 1716, 0, 480, 488, 494, 525, 0,
+	/* 50 - 720(1440)x480i@120Hz */
+	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 27000, 720, 739,
+		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 51 - 1440x480i@120Hz */
-	{ DRM_MODE("1440x480i", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1478,
-		   1602, 1716, 0, 480, 488, 494, 525, 0,
+	/* 51 - 720(1440)x480i@120Hz */
+	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 27000, 720, 739,
+		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
@@ -892,15 +892,15 @@ static const struct drm_display_mode edid_cea_modes[] = {
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 200, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 54 - 1440x576i@200Hz */
-	{ DRM_MODE("1440x576i", DRM_MODE_TYPE_DRIVER, 108000, 1440, 1464,
-		   1590, 1728, 0, 576, 580, 586, 625, 0,
+	/* 54 - 720(1440)x576i@200Hz */
+	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 54000, 720, 732,
+		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 200, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 55 - 1440x576i@200Hz */
-	{ DRM_MODE("1440x576i", DRM_MODE_TYPE_DRIVER, 108000, 1440, 1464,
-		   1590, 1728, 0, 576, 580, 586, 625, 0,
+	/* 55 - 720(1440)x576i@200Hz */
+	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 54000, 720, 732,
+		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 200, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
@@ -914,15 +914,15 @@ static const struct drm_display_mode edid_cea_modes[] = {
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 240, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 58 - 1440x480i@240 */
-	{ DRM_MODE("1440x480i", DRM_MODE_TYPE_DRIVER, 108000, 1440, 1478,
-		   1602, 1716, 0, 480, 488, 494, 525, 0,
+	/* 58 - 720(1440)x480i@240 */
+	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 54000, 720, 739,
+		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 240, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 59 - 1440x480i@240 */
-	{ DRM_MODE("1440x480i", DRM_MODE_TYPE_DRIVER, 108000, 1440, 1478,
-		   1602, 1716, 0, 480, 488, 494, 525, 0,
+	/* 59 - 720(1440)x480i@240 */
+	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 54000, 720, 739,
+		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
 			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 240, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
@@ -2103,7 +2103,8 @@ static int
 add_inferred_modes(struct drm_connector *connector, struct edid *edid)
 {
 	struct detailed_mode_closure closure = {
-		connector, edid, 0, 0, 0
+		.connector = connector,
+		.edid = edid,
 	};
 
 	if (version_greater(edid, 1, 0))
@@ -2169,7 +2170,8 @@ add_established_modes(struct drm_connector *connector, struct edid *edid)
 		((edid->established_timings.mfg_rsvd & 0x80) << 9);
 	int i, modes = 0;
 	struct detailed_mode_closure closure = {
-		connector, edid, 0, 0, 0
+		.connector = connector,
+		.edid = edid,
 	};
 
 	for (i = 0; i <= EDID_EST_TIMINGS; i++) {
@@ -2227,7 +2229,8 @@ add_standard_modes(struct drm_connector *connector, struct edid *edid)
 {
 	int i, modes = 0;
 	struct detailed_mode_closure closure = {
-		connector, edid, 0, 0, 0
+		.connector = connector,
+		.edid = edid,
 	};
 
 	for (i = 0; i < EDID_STD_TIMINGS; i++) {
@@ -2313,7 +2316,8 @@ static int
 add_cvt_modes(struct drm_connector *connector, struct edid *edid)
 {	
 	struct detailed_mode_closure closure = {
-		connector, edid, 0, 0, 0
+		.connector = connector,
+		.edid = edid,
 	};
 
 	if (version_greater(edid, 1, 2))
@@ -2357,11 +2361,10 @@ add_detailed_modes(struct drm_connector *connector, struct edid *edid,
 		   u32 quirks)
 {
 	struct detailed_mode_closure closure = {
-		connector,
-		edid,
-		1,
-		quirks,
-		0
+		.connector = connector,
+		.edid = edid,
+		.preferred = 1,
+		.quirks = quirks,
 	};
 
 	if (closure.preferred && !version_greater(edid, 1, 3))
@@ -3433,10 +3436,10 @@ EXPORT_SYMBOL(drm_rgb_quant_range_selectable);
 /**
  * drm_assign_hdmi_deep_color_info - detect whether monitor supports
  * hdmi deep color modes and update drm_display_info if so.
- *
  * @edid: monitor EDID information
  * @info: Updated with maximum supported deep color bpc and color format
  *        if deep color supported.
+ * @connector: DRM connector, used only for debug output
  *
  * Parse the CEA extension according to CEA-861-B.
  * Return true if HDMI deep color supported, false if not or unknown.
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 3144db9dc0f1..0c0c39bac23d 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -126,7 +126,7 @@ int drm_fb_helper_add_one_connector(struct drm_fb_helper *fb_helper, struct drm_
 
 	WARN_ON(!mutex_is_locked(&fb_helper->dev->mode_config.mutex));
 	if (fb_helper->connector_count + 1 > fb_helper->connector_info_alloc_count) {
-		temp = krealloc(fb_helper->connector_info, sizeof(struct drm_fb_helper_connector) * (fb_helper->connector_count + 1), GFP_KERNEL);
+		temp = krealloc(fb_helper->connector_info, sizeof(struct drm_fb_helper_connector *) * (fb_helper->connector_count + 1), GFP_KERNEL);
 		if (!temp)
 			return -ENOMEM;
 
@@ -171,60 +171,6 @@ int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper,
 }
 EXPORT_SYMBOL(drm_fb_helper_remove_one_connector);
 
-static int drm_fb_helper_parse_command_line(struct drm_fb_helper *fb_helper)
-{
-	struct drm_fb_helper_connector *fb_helper_conn;
-	int i;
-
-	for (i = 0; i < fb_helper->connector_count; i++) {
-		struct drm_cmdline_mode *mode;
-		struct drm_connector *connector;
-		char *option = NULL;
-
-		fb_helper_conn = fb_helper->connector_info[i];
-		connector = fb_helper_conn->connector;
-		mode = &fb_helper_conn->cmdline_mode;
-
-		/* do something on return - turn off connector maybe */
-		if (fb_get_options(connector->name, &option))
-			continue;
-
-		if (drm_mode_parse_command_line_for_connector(option,
-							      connector,
-							      mode)) {
-			if (mode->force) {
-				const char *s;
-				switch (mode->force) {
-				case DRM_FORCE_OFF:
-					s = "OFF";
-					break;
-				case DRM_FORCE_ON_DIGITAL:
-					s = "ON - dig";
-					break;
-				default:
-				case DRM_FORCE_ON:
-					s = "ON";
-					break;
-				}
-
-				DRM_INFO("forcing %s connector %s\n",
-					 connector->name, s);
-				connector->force = mode->force;
-			}
-
-			DRM_DEBUG_KMS("cmdline mode for connector %s %dx%d@%dHz%s%s%s\n",
-				      connector->name,
-				      mode->xres, mode->yres,
-				      mode->refresh_specified ? mode->refresh : 60,
-				      mode->rb ? " reduced blanking" : "",
-				      mode->margins ? " with margins" : "",
-				      mode->interlace ?  " interlaced" : "");
-		}
-
-	}
-	return 0;
-}
-
 static void drm_fb_helper_save_lut_atomic(struct drm_crtc *crtc, struct drm_fb_helper *helper)
 {
 	uint16_t *r_base, *g_base, *b_base;
@@ -345,10 +291,17 @@ static bool restore_fbdev_mode(struct drm_fb_helper *fb_helper)
 
 	drm_warn_on_modeset_not_all_locked(dev);
 
-	list_for_each_entry(plane, &dev->mode_config.plane_list, head)
+	list_for_each_entry(plane, &dev->mode_config.plane_list, head) {
 		if (plane->type != DRM_PLANE_TYPE_PRIMARY)
 			drm_plane_force_disable(plane);
 
+		if (dev->mode_config.rotation_property) {
+			drm_mode_plane_set_obj_prop(plane,
+						    dev->mode_config.rotation_property,
+						    BIT(DRM_ROTATE_0));
+		}
+	}
+
 	for (i = 0; i < fb_helper->crtc_count; i++) {
 		struct drm_mode_set *mode_set = &fb_helper->crtc_info[i].mode_set;
 		struct drm_crtc *crtc = mode_set->crtc;
@@ -419,11 +372,11 @@ static bool drm_fb_helper_force_kernel_mode(void)
 		if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 			continue;
 
-		/* NOTE: we use lockless flag below to avoid grabbing other
-		 * modeset locks.  So just trylock the underlying mutex
-		 * directly:
+		/*
+		 * NOTE: Use trylock mode to avoid deadlocks and sleeping in
+		 * panic context.
 		 */
-		if (!mutex_trylock(&dev->mode_config.mutex)) {
+		if (__drm_modeset_lock_all(dev, true) != 0) {
 			error = true;
 			continue;
 		}
@@ -432,7 +385,7 @@ static bool drm_fb_helper_force_kernel_mode(void)
 		if (ret)
 			error = true;
 
-		mutex_unlock(&dev->mode_config.mutex);
+		drm_modeset_unlock_all(dev);
 	}
 	return error;
 }
@@ -1013,7 +966,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 		struct drm_fb_helper_connector *fb_helper_conn = fb_helper->connector_info[i];
 		struct drm_cmdline_mode *cmdline_mode;
 
-		cmdline_mode = &fb_helper_conn->cmdline_mode;
+		cmdline_mode = &fb_helper_conn->connector->cmdline_mode;
 
 		if (cmdline_mode->bpp_specified) {
 			switch (cmdline_mode->bpp) {
@@ -1260,9 +1213,7 @@ EXPORT_SYMBOL(drm_has_preferred_mode);
 
 static bool drm_has_cmdline_mode(struct drm_fb_helper_connector *fb_connector)
 {
-	struct drm_cmdline_mode *cmdline_mode;
-	cmdline_mode = &fb_connector->cmdline_mode;
-	return cmdline_mode->specified;
+	return fb_connector->connector->cmdline_mode.specified;
 }
 
 struct drm_display_mode *drm_pick_cmdline_mode(struct drm_fb_helper_connector *fb_helper_conn,
@@ -1272,7 +1223,7 @@ struct drm_display_mode *drm_pick_cmdline_mode(struct drm_fb_helper_connector *f
 	struct drm_display_mode *mode = NULL;
 	bool prefer_non_interlace;
 
-	cmdline_mode = &fb_helper_conn->cmdline_mode;
+	cmdline_mode = &fb_helper_conn->connector->cmdline_mode;
 	if (cmdline_mode->specified == false)
 		return mode;
 
@@ -1657,8 +1608,6 @@ bool drm_fb_helper_initial_config(struct drm_fb_helper *fb_helper, int bpp_sel)
 	struct drm_device *dev = fb_helper->dev;
 	int count = 0;
 
-	drm_fb_helper_parse_command_line(fb_helper);
-
 	mutex_lock(&dev->mode_config.mutex);
 	count = drm_fb_helper_probe_connector_modes(fb_helper,
 						    dev->mode_config.max_width,
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 79d5221c6e41..ed7bc68f7e87 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -39,10 +39,10 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include "drm_legacy.h"
+#include "drm_internal.h"
 
 /* from BKL pushdown */
 DEFINE_MUTEX(drm_global_mutex);
-EXPORT_SYMBOL(drm_global_mutex);
 
 static int drm_open_helper(struct file *filp, struct drm_minor *minor);
 
@@ -171,7 +171,7 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 	init_waitqueue_head(&priv->event_wait);
 	priv->event_space = 4096; /* set aside 4k for event buffer */
 
-	if (dev->driver->driver_features & DRIVER_GEM)
+	if (drm_core_check_feature(dev, DRIVER_GEM))
 		drm_gem_open(dev, priv);
 
 	if (drm_core_check_feature(dev, DRIVER_PRIME))
@@ -256,7 +256,7 @@ out_close:
 out_prime_destroy:
 	if (drm_core_check_feature(dev, DRIVER_PRIME))
 		drm_prime_destroy_file_private(&priv->prime);
-	if (dev->driver->driver_features & DRIVER_GEM)
+	if (drm_core_check_feature(dev, DRIVER_GEM))
 		drm_gem_release(dev, priv);
 	put_pid(priv->pid);
 	kfree(priv);
@@ -268,11 +268,11 @@ static void drm_master_release(struct drm_device *dev, struct file *filp)
 {
 	struct drm_file *file_priv = filp->private_data;
 
-	if (drm_i_have_hw_lock(dev, file_priv)) {
+	if (drm_legacy_i_have_hw_lock(dev, file_priv)) {
 		DRM_DEBUG("File %p released, freeing lock for context %d\n",
 			  filp, _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock));
-		drm_lock_free(&file_priv->master->lock,
-			      _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock));
+		drm_legacy_lock_free(&file_priv->master->lock,
+				     _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock));
 	}
 }
 
@@ -330,8 +330,6 @@ static void drm_legacy_dev_reinit(struct drm_device *dev)
  */
 int drm_lastclose(struct drm_device * dev)
 {
-	struct drm_vma_entry *vma, *vma_temp;
-
 	DRM_DEBUG("\n");
 
 	if (dev->driver->lastclose)
@@ -346,13 +344,7 @@ int drm_lastclose(struct drm_device * dev)
 	drm_agp_clear(dev);
 
 	drm_legacy_sg_cleanup(dev);
-
-	/* Clear vma list (only built for debugging) */
-	list_for_each_entry_safe(vma, vma_temp, &dev->vmalist, head) {
-		list_del(&vma->head);
-		kfree(vma);
-	}
-
+	drm_legacy_vma_flush(dev);
 	drm_legacy_dma_takedown(dev);
 
 	mutex_unlock(&dev->struct_mutex);
@@ -412,14 +404,14 @@ int drm_release(struct inode *inode, struct file *filp)
 		drm_master_release(dev, filp);
 
 	if (drm_core_check_feature(dev, DRIVER_HAVE_DMA))
-		drm_core_reclaim_buffers(dev, file_priv);
+		drm_legacy_reclaim_buffers(dev, file_priv);
 
 	drm_events_release(file_priv);
 
-	if (dev->driver->driver_features & DRIVER_MODESET)
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		drm_fb_release(file_priv);
 
-	if (dev->driver->driver_features & DRIVER_GEM)
+	if (drm_core_check_feature(dev, DRIVER_GEM))
 		drm_gem_release(dev, file_priv);
 
 	drm_legacy_ctxbitmap_flush(dev, file_priv);
@@ -464,6 +456,8 @@ int drm_release(struct inode *inode, struct file *filp)
 	if (drm_core_check_feature(dev, DRIVER_PRIME))
 		drm_prime_destroy_file_private(&file_priv->prime);
 
+	WARN_ON(!list_empty(&file_priv->event_list));
+
 	put_pid(file_priv->pid);
 	kfree(file_priv);
 
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 6adee4c2afc0..f6ca51259fa3 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -38,6 +38,8 @@
 #include <linux/dma-buf.h>
 #include <drm/drmP.h>
 #include <drm/drm_vma_manager.h>
+#include <drm/drm_gem.h>
+#include "drm_internal.h"
 
 /** @file drm_gem.c
  *
@@ -146,7 +148,7 @@ int drm_gem_object_init(struct drm_device *dev,
 EXPORT_SYMBOL(drm_gem_object_init);
 
 /**
- * drm_gem_object_init - initialize an allocated private GEM object
+ * drm_gem_private_object_init - initialize an allocated private GEM object
  * @dev: drm_device the object should be initialized for
  * @obj: drm_gem_object to initialize
  * @size: object size
@@ -579,7 +581,7 @@ drm_gem_close_ioctl(struct drm_device *dev, void *data,
 	struct drm_gem_close *args = data;
 	int ret;
 
-	if (!(dev->driver->driver_features & DRIVER_GEM))
+	if (!drm_core_check_feature(dev, DRIVER_GEM))
 		return -ENODEV;
 
 	ret = drm_gem_handle_delete(file_priv, args->handle);
@@ -606,7 +608,7 @@ drm_gem_flink_ioctl(struct drm_device *dev, void *data,
 	struct drm_gem_object *obj;
 	int ret;
 
-	if (!(dev->driver->driver_features & DRIVER_GEM))
+	if (!drm_core_check_feature(dev, DRIVER_GEM))
 		return -ENODEV;
 
 	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
@@ -659,7 +661,7 @@ drm_gem_open_ioctl(struct drm_device *dev, void *data,
 	int ret;
 	u32 handle;
 
-	if (!(dev->driver->driver_features & DRIVER_GEM))
+	if (!drm_core_check_feature(dev, DRIVER_GEM))
 		return -ENODEV;
 
 	mutex_lock(&dev->object_name_lock);
@@ -887,7 +889,7 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 					   vma_pages(vma));
 	if (!node) {
 		mutex_unlock(&dev->struct_mutex);
-		return drm_mmap(filp, vma);
+		return -EINVAL;
 	} else if (!drm_vma_node_is_allowed(node, filp)) {
 		mutex_unlock(&dev->struct_mutex);
 		return -EACCES;
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index e467e67af6e7..0316310e2cc4 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -316,7 +316,8 @@ out:
 EXPORT_SYMBOL_GPL(drm_gem_cma_prime_get_sg_table);
 
 struct drm_gem_object *
-drm_gem_cma_prime_import_sg_table(struct drm_device *dev, size_t size,
+drm_gem_cma_prime_import_sg_table(struct drm_device *dev,
+				  struct dma_buf_attachment *attach,
 				  struct sg_table *sgt)
 {
 	struct drm_gem_cma_object *cma_obj;
@@ -325,14 +326,14 @@ drm_gem_cma_prime_import_sg_table(struct drm_device *dev, size_t size,
 		return ERR_PTR(-EINVAL);
 
 	/* Create a CMA GEM buffer. */
-	cma_obj = __drm_gem_cma_create(dev, size);
+	cma_obj = __drm_gem_cma_create(dev, attach->dmabuf->size);
 	if (IS_ERR(cma_obj))
 		return ERR_CAST(cma_obj);
 
 	cma_obj->paddr = sg_dma_address(sgt->sgl);
 	cma_obj->sgt = sgt;
 
-	DRM_DEBUG_PRIME("dma_addr = %pad, size = %zu\n", &cma_obj->paddr, size);
+	DRM_DEBUG_PRIME("dma_addr = %pad, size = %zu\n", &cma_obj->paddr, attach->dmabuf->size);
 
 	return &cma_obj->base;
 }
diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index ecaf0fa2eec8..51efebd434f3 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/drivers/gpu/drm/drm_info.c
@@ -35,6 +35,9 @@
 
 #include <linux/seq_file.h>
 #include <drm/drmP.h>
+#include <drm/drm_gem.h>
+
+#include "drm_legacy.h"
 
 /**
  * Called when "/proc/dri/.../name" is read.
@@ -183,15 +186,32 @@ int drm_clients_info(struct seq_file *m, void *data)
 	struct drm_device *dev = node->minor->dev;
 	struct drm_file *priv;
 
+	seq_printf(m,
+		   "%20s %5s %3s master a %5s %10s\n",
+		   "command",
+		   "pid",
+		   "dev",
+		   "uid",
+		   "magic");
+
+	/* dev->filelist is sorted youngest first, but we want to present
+	 * oldest first (i.e. kernel, servers, clients), so walk backwardss.
+	 */
 	mutex_lock(&dev->struct_mutex);
-	seq_printf(m, "a dev	pid    uid	magic\n\n");
-	list_for_each_entry(priv, &dev->filelist, lhead) {
-		seq_printf(m, "%c %3d %5d %5d %10u\n",
-			   priv->authenticated ? 'y' : 'n',
-			   priv->minor->index,
+	list_for_each_entry_reverse(priv, &dev->filelist, lhead) {
+		struct task_struct *task;
+
+		rcu_read_lock(); /* locks pid_task()->comm */
+		task = pid_task(priv->pid, PIDTYPE_PID);
+		seq_printf(m, "%20s %5d %3d   %c    %c %5d %10u\n",
+			   task ? task->comm : "<unknown>",
 			   pid_vnr(priv->pid),
+			   priv->minor->index,
+			   priv->is_master ? 'y' : 'n',
+			   priv->authenticated ? 'y' : 'n',
 			   from_kuid_munged(seq_user_ns(m), priv->uid),
 			   priv->magic);
+		rcu_read_unlock();
 	}
 	mutex_unlock(&dev->struct_mutex);
 	return 0;
@@ -223,62 +243,3 @@ int drm_gem_name_info(struct seq_file *m, void *data)
 
 	return 0;
 }
-
-#if DRM_DEBUG_CODE
-
-int drm_vma_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct drm_vma_entry *pt;
-	struct vm_area_struct *vma;
-	unsigned long vma_count = 0;
-#if defined(__i386__)
-	unsigned int pgprot;
-#endif
-
-	mutex_lock(&dev->struct_mutex);
-	list_for_each_entry(pt, &dev->vmalist, head)
-		vma_count++;
-
-	seq_printf(m, "vma use count: %lu, high_memory = %pK, 0x%pK\n",
-		   vma_count, high_memory,
-		   (void *)(unsigned long)virt_to_phys(high_memory));
-
-	list_for_each_entry(pt, &dev->vmalist, head) {
-		vma = pt->vma;
-		if (!vma)
-			continue;
-		seq_printf(m,
-			   "\n%5d 0x%pK-0x%pK %c%c%c%c%c%c 0x%08lx000",
-			   pt->pid,
-			   (void *)vma->vm_start, (void *)vma->vm_end,
-			   vma->vm_flags & VM_READ ? 'r' : '-',
-			   vma->vm_flags & VM_WRITE ? 'w' : '-',
-			   vma->vm_flags & VM_EXEC ? 'x' : '-',
-			   vma->vm_flags & VM_MAYSHARE ? 's' : 'p',
-			   vma->vm_flags & VM_LOCKED ? 'l' : '-',
-			   vma->vm_flags & VM_IO ? 'i' : '-',
-			   vma->vm_pgoff);
-
-#if defined(__i386__)
-		pgprot = pgprot_val(vma->vm_page_prot);
-		seq_printf(m, " %c%c%c%c%c%c%c%c%c",
-			   pgprot & _PAGE_PRESENT ? 'p' : '-',
-			   pgprot & _PAGE_RW ? 'w' : 'r',
-			   pgprot & _PAGE_USER ? 'u' : 's',
-			   pgprot & _PAGE_PWT ? 't' : 'b',
-			   pgprot & _PAGE_PCD ? 'u' : 'c',
-			   pgprot & _PAGE_ACCESSED ? 'a' : '-',
-			   pgprot & _PAGE_DIRTY ? 'd' : '-',
-			   pgprot & _PAGE_PSE ? 'm' : 'k',
-			   pgprot & _PAGE_GLOBAL ? 'g' : 'l');
-#endif
-		seq_printf(m, "\n");
-	}
-	mutex_unlock(&dev->struct_mutex);
-	return 0;
-}
-
-#endif
-
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
new file mode 100644
index 000000000000..7cc0a3516871
--- /dev/null
+++ b/drivers/gpu/drm/drm_internal.h
@@ -0,0 +1,132 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *   Daniel Vetter <daniel.vetter@ffwll.ch>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/* drm_irq.c */
+extern unsigned int drm_timestamp_monotonic;
+
+/* drm_fops.c */
+extern struct mutex drm_global_mutex;
+int drm_lastclose(struct drm_device *dev);
+
+/* drm_pci.c */
+int drm_pci_set_unique(struct drm_device *dev,
+		       struct drm_master *master,
+		       struct drm_unique *u);
+int drm_irq_by_busid(struct drm_device *dev, void *data,
+		     struct drm_file *file_priv);
+
+/* drm_vm.c */
+int drm_vma_info(struct seq_file *m, void *data);
+void drm_vm_open_locked(struct drm_device *dev, struct vm_area_struct *vma);
+void drm_vm_close_locked(struct drm_device *dev, struct vm_area_struct *vma);
+
+/* drm_prime.c */
+int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv);
+int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv);
+
+void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv);
+void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv);
+void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
+					struct dma_buf *dma_buf);
+
+/* drm_info.c */
+int drm_name_info(struct seq_file *m, void *data);
+int drm_vm_info(struct seq_file *m, void *data);
+int drm_bufs_info(struct seq_file *m, void *data);
+int drm_vblank_info(struct seq_file *m, void *data);
+int drm_clients_info(struct seq_file *m, void* data);
+int drm_gem_name_info(struct seq_file *m, void *data);
+
+/* drm_irq.c */
+int drm_control(struct drm_device *dev, void *data,
+		struct drm_file *file_priv);
+int drm_modeset_ctl(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv);
+
+/* drm_auth.c */
+int drm_getmagic(struct drm_device *dev, void *data,
+		 struct drm_file *file_priv);
+int drm_authmagic(struct drm_device *dev, void *data,
+		  struct drm_file *file_priv);
+int drm_remove_magic(struct drm_master *master, drm_magic_t magic);
+
+/* drm_sysfs.c */
+extern struct class *drm_class;
+
+struct class *drm_sysfs_create(struct module *owner, char *name);
+void drm_sysfs_destroy(void);
+struct device *drm_sysfs_minor_alloc(struct drm_minor *minor);
+int drm_sysfs_connector_add(struct drm_connector *connector);
+void drm_sysfs_connector_remove(struct drm_connector *connector);
+
+/* drm_gem.c */
+int drm_gem_init(struct drm_device *dev);
+void drm_gem_destroy(struct drm_device *dev);
+int drm_gem_handle_create_tail(struct drm_file *file_priv,
+			       struct drm_gem_object *obj,
+			       u32 *handlep);
+int drm_gem_close_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int drm_gem_flink_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int drm_gem_open_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv);
+void drm_gem_open(struct drm_device *dev, struct drm_file *file_private);
+void drm_gem_release(struct drm_device *dev, struct drm_file *file_private);
+
+/* drm_drv.c */
+int drm_setmaster_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
+			 struct drm_file *file_priv);
+struct drm_master *drm_master_create(struct drm_minor *minor);
+
+/* drm_debugfs.c */
+#if defined(CONFIG_DEBUG_FS)
+int drm_debugfs_init(struct drm_minor *minor, int minor_id,
+		     struct dentry *root);
+int drm_debugfs_cleanup(struct drm_minor *minor);
+int drm_debugfs_connector_add(struct drm_connector *connector);
+void drm_debugfs_connector_remove(struct drm_connector *connector);
+#else
+static inline int drm_debugfs_init(struct drm_minor *minor, int minor_id,
+				   struct dentry *root)
+{
+	return 0;
+}
+
+static inline int drm_debugfs_cleanup(struct drm_minor *minor)
+{
+	return 0;
+}
+
+static inline int drm_debugfs_connector_add(struct drm_connector *connector)
+{
+	return 0;
+}
+static inline void drm_debugfs_connector_remove(struct drm_connector *connector)
+{
+}
+#endif
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 40be746b7e68..00587a1e3c83 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -31,6 +31,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_core.h>
 #include "drm_legacy.h"
+#include "drm_internal.h"
 
 #include <linux/pci.h>
 #include <linux/export.h>
@@ -41,121 +42,6 @@
 static int drm_version(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
 
-#define DRM_IOCTL_DEF(ioctl, _func, _flags) \
-	[DRM_IOCTL_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, .cmd_drv = 0, .name = #ioctl}
-
-/** Ioctl table */
-static const struct drm_ioctl_desc drm_ioctls[] = {
-	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, 0),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, 0),
-	DRM_IOCTL_DEF(DRM_IOCTL_IRQ_BUSID, drm_irq_by_busid, DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAP, drm_getmap, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_CLIENT, drm_getclient, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_STATS, drm_getstats, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_CAP, drm_getcap, DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_CLIENT_CAP, drm_setclientcap, 0),
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_VERSION, drm_setversion, DRM_MASTER),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_UNIQUE, drm_setunique, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_BLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_UNBLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AUTH_MAGIC, drm_authmagic, DRM_AUTH|DRM_MASTER),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_ADD_MAP, drm_addmap_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_RM_MAP, drm_rmmap_ioctl, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_SAREA_CTX, drm_legacy_setsareactx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_SAREA_CTX, drm_legacy_getsareactx, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_SET_MASTER, drm_setmaster_ioctl, DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_DROP_MASTER, drm_dropmaster_ioctl, DRM_ROOT_ONLY),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_ADD_CTX, drm_legacy_addctx, DRM_AUTH|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_RM_CTX, drm_legacy_rmctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_MOD_CTX, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_GET_CTX, drm_legacy_getctx, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_SWITCH_CTX, drm_legacy_switchctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_NEW_CTX, drm_legacy_newctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_RES_CTX, drm_legacy_resctx, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_ADD_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_RM_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_LOCK, drm_lock, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_UNLOCK, drm_unlock, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_FINISH, drm_noop, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_ADD_BUFS, drm_addbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_MARK_BUFS, drm_markbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_INFO_BUFS, drm_infobufs, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_MAP_BUFS, drm_mapbufs, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_FREE_BUFS, drm_freebufs, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_DMA, drm_dma_ioctl, DRM_AUTH),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_CONTROL, drm_control, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-
-#if __OS_HAS_AGP
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ACQUIRE, drm_agp_acquire_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_RELEASE, drm_agp_release_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ENABLE, drm_agp_enable_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_INFO, drm_agp_info_ioctl, DRM_AUTH),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ALLOC, drm_agp_alloc_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_FREE, drm_agp_free_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_BIND, drm_agp_bind_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_AGP_UNBIND, drm_agp_unbind_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-#endif
-
-	DRM_IOCTL_DEF(DRM_IOCTL_SG_ALLOC, drm_sg_alloc, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-	DRM_IOCTL_DEF(DRM_IOCTL_SG_FREE, drm_sg_free, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_WAIT_VBLANK, drm_wait_vblank, DRM_UNLOCKED),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_MODESET_CTL, drm_modeset_ctl, 0),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_UPDATE_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_GEM_CLOSE, drm_gem_close_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF(DRM_IOCTL_GEM_FLINK, drm_gem_flink_ioctl, DRM_AUTH|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_GEM_OPEN, drm_gem_open_ioctl, DRM_AUTH|DRM_UNLOCKED),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
-
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETCRTC, drm_mode_setcrtc, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANE, drm_mode_getplane, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPLANE, drm_mode_setplane, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR, drm_mode_cursor_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETGAMMA, drm_mode_gamma_get_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETGAMMA, drm_mode_gamma_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETENCODER, drm_mode_getencoder, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCONNECTOR, drm_mode_getconnector, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATTACHMODE, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DETACHMODE, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPERTY, drm_mode_getproperty_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_mode_connector_property_set_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB2, drm_mode_addfb2, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_RMFB, drm_mode_rmfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_PAGE_FLIP, drm_mode_page_flip_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DIRTYFB, drm_mode_dirtyfb_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_DUMB, drm_mode_create_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_MAP_DUMB, drm_mode_mmap_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DESTROY_DUMB, drm_mode_destroy_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_GETPROPERTIES, drm_mode_obj_get_properties_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_SETPROPERTY, drm_mode_obj_set_property_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR2, drm_mode_cursor2_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-};
-
-#define DRM_CORE_IOCTL_COUNT	ARRAY_SIZE( drm_ioctls )
-
 /**
  * Get the bus id.
  *
@@ -167,7 +53,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
  *
  * Copies the bus id from drm_device::unique into user space.
  */
-int drm_getunique(struct drm_device *dev, void *data,
+static int drm_getunique(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
 {
 	struct drm_unique *u = data;
@@ -189,7 +75,6 @@ drm_unset_busid(struct drm_device *dev,
 	kfree(master->unique);
 	master->unique = NULL;
 	master->unique_len = 0;
-	master->unique_size = 0;
 }
 
 /**
@@ -207,7 +92,7 @@ drm_unset_busid(struct drm_device *dev,
  * version 1.1 or greater. Also note that KMS is all version 1.1 and later and
  * UMS was only ever supported on pci devices.
  */
-int drm_setunique(struct drm_device *dev, void *data,
+static int drm_setunique(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
 {
 	struct drm_unique *u = data;
@@ -245,15 +130,15 @@ static int drm_set_busid(struct drm_device *dev, struct drm_file *file_priv)
 	if (master->unique != NULL)
 		drm_unset_busid(dev, master);
 
-	if (dev->driver->bus && dev->driver->bus->set_busid) {
-		ret = dev->driver->bus->set_busid(dev, master);
+	if (dev->driver->set_busid) {
+		ret = dev->driver->set_busid(dev, master);
 		if (ret) {
 			drm_unset_busid(dev, master);
 			return ret;
 		}
 	} else {
 		if (WARN(dev->unique == NULL,
-			 "No drm_bus.set_busid() implementation provided by "
+			 "No drm_driver.set_busid() implementation provided by "
 			 "%ps. Use drm_dev_set_unique() to set the unique "
 			 "name explicitly.", dev->driver))
 			return -EINVAL;
@@ -279,7 +164,7 @@ static int drm_set_busid(struct drm_device *dev, struct drm_file *file_priv)
  * Searches for the mapping with the specified offset and copies its information
  * into userspace
  */
-int drm_getmap(struct drm_device *dev, void *data,
+static int drm_getmap(struct drm_device *dev, void *data,
 	       struct drm_file *file_priv)
 {
 	struct drm_map *map = data;
@@ -340,7 +225,7 @@ int drm_getmap(struct drm_device *dev, void *data,
  * Searches for the client with the specified index and copies its information
  * into userspace
  */
-int drm_getclient(struct drm_device *dev, void *data,
+static int drm_getclient(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
 {
 	struct drm_client *client = data;
@@ -380,7 +265,7 @@ int drm_getclient(struct drm_device *dev, void *data,
  *
  * \return zero on success or a negative number on failure.
  */
-int drm_getstats(struct drm_device *dev, void *data,
+static int drm_getstats(struct drm_device *dev, void *data,
 		 struct drm_file *file_priv)
 {
 	struct drm_stats *stats = data;
@@ -394,7 +279,7 @@ int drm_getstats(struct drm_device *dev, void *data,
 /**
  * Get device/driver capabilities
  */
-int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
+static int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
 	struct drm_get_cap *req = data;
 
@@ -444,7 +329,7 @@ int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 /**
  * Set device/driver capabilities
  */
-int
+static int
 drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
 	struct drm_set_client_cap *req = data;
@@ -478,7 +363,7 @@ drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
  *
  * Sets the requested interface version
  */
-int drm_setversion(struct drm_device *dev, void *data, struct drm_file *file_priv)
+static int drm_setversion(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
 	struct drm_set_version *sv = data;
 	int if_version, retcode = 0;
@@ -624,6 +509,121 @@ static int drm_ioctl_permit(u32 flags, struct drm_file *file_priv)
 	return 0;
 }
 
+#define DRM_IOCTL_DEF(ioctl, _func, _flags) \
+	[DRM_IOCTL_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, .cmd_drv = 0, .name = #ioctl}
+
+/** Ioctl table */
+static const struct drm_ioctl_desc drm_ioctls[] = {
+	DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, 0),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, 0),
+	DRM_IOCTL_DEF(DRM_IOCTL_IRQ_BUSID, drm_irq_by_busid, DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_MAP, drm_getmap, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_CLIENT, drm_getclient, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_STATS, drm_getstats, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_CAP, drm_getcap, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_CLIENT_CAP, drm_setclientcap, 0),
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_VERSION, drm_setversion, DRM_MASTER),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_UNIQUE, drm_setunique, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_BLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_UNBLOCK, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AUTH_MAGIC, drm_authmagic, DRM_AUTH|DRM_MASTER),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_ADD_MAP, drm_legacy_addmap_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_RM_MAP, drm_legacy_rmmap_ioctl, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_SAREA_CTX, drm_legacy_setsareactx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_SAREA_CTX, drm_legacy_getsareactx, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_SET_MASTER, drm_setmaster_ioctl, DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_DROP_MASTER, drm_dropmaster_ioctl, DRM_ROOT_ONLY),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_ADD_CTX, drm_legacy_addctx, DRM_AUTH|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_RM_CTX, drm_legacy_rmctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_MOD_CTX, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_GET_CTX, drm_legacy_getctx, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_SWITCH_CTX, drm_legacy_switchctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_NEW_CTX, drm_legacy_newctx, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_RES_CTX, drm_legacy_resctx, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_ADD_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_RM_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_LOCK, drm_legacy_lock, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_UNLOCK, drm_legacy_unlock, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_FINISH, drm_noop, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_ADD_BUFS, drm_legacy_addbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_MARK_BUFS, drm_legacy_markbufs, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_INFO_BUFS, drm_legacy_infobufs, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_MAP_BUFS, drm_legacy_mapbufs, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_FREE_BUFS, drm_legacy_freebufs, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_DMA, drm_legacy_dma_ioctl, DRM_AUTH),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_CONTROL, drm_control, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+
+#if __OS_HAS_AGP
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ACQUIRE, drm_agp_acquire_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_RELEASE, drm_agp_release_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ENABLE, drm_agp_enable_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_INFO, drm_agp_info_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_ALLOC, drm_agp_alloc_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_FREE, drm_agp_free_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_BIND, drm_agp_bind_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_AGP_UNBIND, drm_agp_unbind_ioctl, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+#endif
+
+	DRM_IOCTL_DEF(DRM_IOCTL_SG_ALLOC, drm_legacy_sg_alloc, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_IOCTL_SG_FREE, drm_legacy_sg_free, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_WAIT_VBLANK, drm_wait_vblank, DRM_UNLOCKED),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_MODESET_CTL, drm_modeset_ctl, 0),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_UPDATE_DRAW, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_GEM_CLOSE, drm_gem_close_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_GEM_FLINK, drm_gem_flink_ioctl, DRM_AUTH|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_GEM_OPEN, drm_gem_open_ioctl, DRM_AUTH|DRM_UNLOCKED),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETCRTC, drm_mode_setcrtc, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANE, drm_mode_getplane, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPLANE, drm_mode_setplane, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR, drm_mode_cursor_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETGAMMA, drm_mode_gamma_get_ioctl, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETGAMMA, drm_mode_gamma_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETENCODER, drm_mode_getencoder, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCONNECTOR, drm_mode_getconnector, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATTACHMODE, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DETACHMODE, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPERTY, drm_mode_getproperty_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_mode_connector_property_set_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB2, drm_mode_addfb2, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_RMFB, drm_mode_rmfb, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_PAGE_FLIP, drm_mode_page_flip_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DIRTYFB, drm_mode_dirtyfb_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_DUMB, drm_mode_create_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_MAP_DUMB, drm_mode_mmap_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DESTROY_DUMB, drm_mode_destroy_dumb_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_GETPROPERTIES, drm_mode_obj_get_properties_ioctl, DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_OBJ_SETPROPERTY, drm_mode_obj_set_property_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CURSOR2, drm_mode_cursor2_ioctl, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+};
+
+#define DRM_CORE_IOCTL_COUNT	ARRAY_SIZE( drm_ioctls )
+
 /**
  * Called whenever a process performs an ioctl on /dev/drm.
  *
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 08ba1209228e..5ef03c216a27 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -34,6 +34,7 @@
 
 #include <drm/drmP.h>
 #include "drm_trace.h"
+#include "drm_internal.h"
 
 #include <linux/interrupt.h>	/* For task queue support */
 #include <linux/slab.h>
@@ -55,12 +56,91 @@
  */
 #define DRM_REDUNDANT_VBLIRQ_THRESH_NS 1000000
 
+static bool
+drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
+			  struct timeval *tvblank, unsigned flags);
+
+static unsigned int drm_timestamp_precision = 20;  /* Default to 20 usecs. */
+
 /*
- * Clear vblank timestamp buffer for a crtc.
+ * Default to use monotonic timestamps for wait-for-vblank and page-flip
+ * complete events.
+ */
+unsigned int drm_timestamp_monotonic = 1;
+
+static int drm_vblank_offdelay = 5000;    /* Default to 5000 msecs. */
+
+module_param_named(vblankoffdelay, drm_vblank_offdelay, int, 0600);
+module_param_named(timestamp_precision_usec, drm_timestamp_precision, int, 0600);
+module_param_named(timestamp_monotonic, drm_timestamp_monotonic, int, 0600);
+
+/**
+ * drm_update_vblank_count - update the master vblank counter
+ * @dev: DRM device
+ * @crtc: counter to update
+ *
+ * Call back into the driver to update the appropriate vblank counter
+ * (specified by @crtc).  Deal with wraparound, if it occurred, and
+ * update the last read value so we can deal with wraparound on the next
+ * call if necessary.
+ *
+ * Only necessary when going from off->on, to account for frames we
+ * didn't get an interrupt for.
+ *
+ * Note: caller must hold dev->vbl_lock since this reads & writes
+ * device vblank fields.
  */
-static void clear_vblank_timestamps(struct drm_device *dev, int crtc)
+static void drm_update_vblank_count(struct drm_device *dev, int crtc)
 {
-	memset(dev->vblank[crtc].time, 0, sizeof(dev->vblank[crtc].time));
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
+	u32 cur_vblank, diff, tslot;
+	bool rc;
+	struct timeval t_vblank;
+
+	/*
+	 * Interrupts were disabled prior to this call, so deal with counter
+	 * wrap if needed.
+	 * NOTE!  It's possible we lost a full dev->max_vblank_count events
+	 * here if the register is small or we had vblank interrupts off for
+	 * a long time.
+	 *
+	 * We repeat the hardware vblank counter & timestamp query until
+	 * we get consistent results. This to prevent races between gpu
+	 * updating its hardware counter while we are retrieving the
+	 * corresponding vblank timestamp.
+	 */
+	do {
+		cur_vblank = dev->driver->get_vblank_counter(dev, crtc);
+		rc = drm_get_last_vbltimestamp(dev, crtc, &t_vblank, 0);
+	} while (cur_vblank != dev->driver->get_vblank_counter(dev, crtc));
+
+	/* Deal with counter wrap */
+	diff = cur_vblank - vblank->last;
+	if (cur_vblank < vblank->last) {
+		diff += dev->max_vblank_count;
+
+		DRM_DEBUG("last_vblank[%d]=0x%x, cur_vblank=0x%x => diff=0x%x\n",
+			  crtc, vblank->last, cur_vblank, diff);
+	}
+
+	DRM_DEBUG("updating vblank count on crtc %d, missed %d\n",
+		  crtc, diff);
+
+	if (diff == 0)
+		return;
+
+	/* Reinitialize corresponding vblank timestamp if high-precision query
+	 * available. Skip this step if query unsupported or failed. Will
+	 * reinitialize delayed at next vblank interrupt in that case.
+	 */
+	if (rc) {
+		tslot = atomic_read(&vblank->count) + diff;
+		vblanktimestamp(dev, crtc, tslot) = t_vblank;
+	}
+
+	smp_mb__before_atomic();
+	atomic_add(diff, &vblank->count);
+	smp_mb__after_atomic();
 }
 
 /*
@@ -71,10 +151,11 @@ static void clear_vblank_timestamps(struct drm_device *dev, int crtc)
  */
 static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 {
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
 	unsigned long irqflags;
 	u32 vblcount;
 	s64 diff_ns;
-	int vblrc;
+	bool vblrc;
 	struct timeval tvblank;
 	int count = DRM_TIMESTAMP_MAXRETRIES;
 
@@ -84,8 +165,28 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	 */
 	spin_lock_irqsave(&dev->vblank_time_lock, irqflags);
 
+	/*
+	 * If the vblank interrupt was already disbled update the count
+	 * and timestamp to maintain the appearance that the counter
+	 * has been ticking all along until this time. This makes the
+	 * count account for the entire time between drm_vblank_on() and
+	 * drm_vblank_off().
+	 *
+	 * But only do this if precise vblank timestamps are available.
+	 * Otherwise we might read a totally bogus timestamp since drivers
+	 * lacking precise timestamp support rely upon sampling the system clock
+	 * at vblank interrupt time. Which obviously won't work out well if the
+	 * vblank interrupt is disabled.
+	 */
+	if (!vblank->enabled &&
+	    drm_get_last_vbltimestamp(dev, crtc, &tvblank, 0)) {
+		drm_update_vblank_count(dev, crtc);
+		spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags);
+		return;
+	}
+
 	dev->driver->disable_vblank(dev, crtc);
-	dev->vblank[crtc].enabled = false;
+	vblank->enabled = false;
 
 	/* No further vblank irq's will be processed after
 	 * this point. Get current hardware vblank count and
@@ -100,9 +201,9 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	 * delayed gpu counter increment.
 	 */
 	do {
-		dev->vblank[crtc].last = dev->driver->get_vblank_counter(dev, crtc);
+		vblank->last = dev->driver->get_vblank_counter(dev, crtc);
 		vblrc = drm_get_last_vbltimestamp(dev, crtc, &tvblank, 0);
-	} while (dev->vblank[crtc].last != dev->driver->get_vblank_counter(dev, crtc) && (--count) && vblrc);
+	} while (vblank->last != dev->driver->get_vblank_counter(dev, crtc) && (--count) && vblrc);
 
 	if (!count)
 		vblrc = 0;
@@ -110,7 +211,7 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	/* Compute time difference to stored timestamp of last vblank
 	 * as updated by last invocation of drm_handle_vblank() in vblank irq.
 	 */
-	vblcount = atomic_read(&dev->vblank[crtc].count);
+	vblcount = atomic_read(&vblank->count);
 	diff_ns = timeval_to_ns(&tvblank) -
 		  timeval_to_ns(&vblanktimestamp(dev, crtc, vblcount));
 
@@ -126,14 +227,18 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	 * available. In that case we can't account for this and just
 	 * hope for the best.
 	 */
-	if ((vblrc > 0) && (abs64(diff_ns) > 1000000)) {
-		atomic_inc(&dev->vblank[crtc].count);
+	if (vblrc && (abs64(diff_ns) > 1000000)) {
+		/* Store new timestamp in ringbuffer. */
+		vblanktimestamp(dev, crtc, vblcount + 1) = tvblank;
+
+		/* Increment cooked vblank count. This also atomically commits
+		 * the timestamp computed above.
+		 */
+		smp_mb__before_atomic();
+		atomic_inc(&vblank->count);
 		smp_mb__after_atomic();
 	}
 
-	/* Invalidate all timestamps while vblank irq's are off. */
-	clear_vblank_timestamps(dev, crtc);
-
 	spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags);
 }
 
@@ -164,14 +269,20 @@ static void vblank_disable_fn(unsigned long arg)
 void drm_vblank_cleanup(struct drm_device *dev)
 {
 	int crtc;
+	unsigned long irqflags;
 
 	/* Bail if the driver didn't call drm_vblank_init() */
 	if (dev->num_crtcs == 0)
 		return;
 
 	for (crtc = 0; crtc < dev->num_crtcs; crtc++) {
-		del_timer_sync(&dev->vblank[crtc].disable_timer);
-		vblank_disable_fn((unsigned long)&dev->vblank[crtc]);
+		struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
+
+		del_timer_sync(&vblank->disable_timer);
+
+		spin_lock_irqsave(&dev->vbl_lock, irqflags);
+		vblank_disable_and_save(dev, crtc);
+		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 	}
 
 	kfree(dev->vblank);
@@ -204,11 +315,13 @@ int drm_vblank_init(struct drm_device *dev, int num_crtcs)
 		goto err;
 
 	for (i = 0; i < num_crtcs; i++) {
-		dev->vblank[i].dev = dev;
-		dev->vblank[i].crtc = i;
-		init_waitqueue_head(&dev->vblank[i].queue);
-		setup_timer(&dev->vblank[i].disable_timer, vblank_disable_fn,
-			    (unsigned long)&dev->vblank[i]);
+		struct drm_vblank_crtc *vblank = &dev->vblank[i];
+
+		vblank->dev = dev;
+		vblank->crtc = i;
+		init_waitqueue_head(&vblank->queue);
+		setup_timer(&vblank->disable_timer, vblank_disable_fn,
+			    (unsigned long)vblank);
 	}
 
 	DRM_INFO("Supports vblank timestamp caching Rev 2 (21.10.2013).\n");
@@ -224,7 +337,7 @@ int drm_vblank_init(struct drm_device *dev, int num_crtcs)
 	return 0;
 
 err:
-	drm_vblank_cleanup(dev);
+	dev->num_crtcs = 0;
 	return ret;
 }
 EXPORT_SYMBOL(drm_vblank_init);
@@ -360,9 +473,11 @@ int drm_irq_uninstall(struct drm_device *dev)
 	if (dev->num_crtcs) {
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
 		for (i = 0; i < dev->num_crtcs; i++) {
-			wake_up(&dev->vblank[i].queue);
-			dev->vblank[i].enabled = false;
-			dev->vblank[i].last =
+			struct drm_vblank_crtc *vblank = &dev->vblank[i];
+
+			wake_up(&vblank->queue);
+			vblank->enabled = false;
+			vblank->last =
 				dev->driver->get_vblank_counter(dev, i);
 		}
 		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
@@ -617,7 +732,7 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
 	 * within vblank area, counting down the number of lines until
 	 * start of scanout.
 	 */
-	invbl = vbl_status & DRM_SCANOUTPOS_INVBL;
+	invbl = vbl_status & DRM_SCANOUTPOS_IN_VBLANK;
 
 	/* Convert scanout position into elapsed time at raw_time query
 	 * since start of scanout at first display scanline. delta_ns
@@ -647,7 +762,7 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc,
 
 	vbl_status = DRM_VBLANKTIME_SCANOUTPOS_METHOD;
 	if (invbl)
-		vbl_status |= DRM_VBLANKTIME_INVBL;
+		vbl_status |= DRM_VBLANKTIME_IN_VBLANK;
 
 	return vbl_status;
 }
@@ -679,10 +794,11 @@ static struct timeval get_drm_timestamp(void)
  * call, i.e., it isn't very precisely locked to the true vblank.
  *
  * Returns:
- * Non-zero if timestamp is considered to be very precise, zero otherwise.
+ * True if timestamp is considered to be very precise, false otherwise.
  */
-u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
-			      struct timeval *tvblank, unsigned flags)
+static bool
+drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
+			  struct timeval *tvblank, unsigned flags)
 {
 	int ret;
 
@@ -694,7 +810,7 @@ u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
 		ret = dev->driver->get_vblank_timestamp(dev, crtc, &max_error,
 							tvblank, flags);
 		if (ret > 0)
-			return (u32) ret;
+			return true;
 	}
 
 	/* GPU high precision timestamp query unsupported or failed.
@@ -702,9 +818,8 @@ u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
 	 */
 	*tvblank = get_drm_timestamp();
 
-	return 0;
+	return false;
 }
-EXPORT_SYMBOL(drm_get_last_vbltimestamp);
 
 /**
  * drm_vblank_count - retrieve "cooked" vblank counter value
@@ -720,7 +835,11 @@ EXPORT_SYMBOL(drm_get_last_vbltimestamp);
  */
 u32 drm_vblank_count(struct drm_device *dev, int crtc)
 {
-	return atomic_read(&dev->vblank[crtc].count);
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
+
+	if (WARN_ON(crtc >= dev->num_crtcs))
+		return 0;
+	return atomic_read(&vblank->count);
 }
 EXPORT_SYMBOL(drm_vblank_count);
 
@@ -740,18 +859,22 @@ EXPORT_SYMBOL(drm_vblank_count);
 u32 drm_vblank_count_and_time(struct drm_device *dev, int crtc,
 			      struct timeval *vblanktime)
 {
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
 	u32 cur_vblank;
 
+	if (WARN_ON(crtc >= dev->num_crtcs))
+		return 0;
+
 	/* Read timestamp from slot of _vblank_time ringbuffer
 	 * that corresponds to current vblank count. Retry if
 	 * count has incremented during readout. This works like
 	 * a seqlock.
 	 */
 	do {
-		cur_vblank = atomic_read(&dev->vblank[crtc].count);
+		cur_vblank = atomic_read(&vblank->count);
 		*vblanktime = vblanktimestamp(dev, crtc, cur_vblank);
 		smp_rmb();
-	} while (cur_vblank != atomic_read(&dev->vblank[crtc].count));
+	} while (cur_vblank != atomic_read(&vblank->count));
 
 	return cur_vblank;
 }
@@ -800,83 +923,20 @@ void drm_send_vblank_event(struct drm_device *dev, int crtc,
 EXPORT_SYMBOL(drm_send_vblank_event);
 
 /**
- * drm_update_vblank_count - update the master vblank counter
- * @dev: DRM device
- * @crtc: counter to update
- *
- * Call back into the driver to update the appropriate vblank counter
- * (specified by @crtc).  Deal with wraparound, if it occurred, and
- * update the last read value so we can deal with wraparound on the next
- * call if necessary.
- *
- * Only necessary when going from off->on, to account for frames we
- * didn't get an interrupt for.
- *
- * Note: caller must hold dev->vbl_lock since this reads & writes
- * device vblank fields.
- */
-static void drm_update_vblank_count(struct drm_device *dev, int crtc)
-{
-	u32 cur_vblank, diff, tslot, rc;
-	struct timeval t_vblank;
-
-	/*
-	 * Interrupts were disabled prior to this call, so deal with counter
-	 * wrap if needed.
-	 * NOTE!  It's possible we lost a full dev->max_vblank_count events
-	 * here if the register is small or we had vblank interrupts off for
-	 * a long time.
-	 *
-	 * We repeat the hardware vblank counter & timestamp query until
-	 * we get consistent results. This to prevent races between gpu
-	 * updating its hardware counter while we are retrieving the
-	 * corresponding vblank timestamp.
-	 */
-	do {
-		cur_vblank = dev->driver->get_vblank_counter(dev, crtc);
-		rc = drm_get_last_vbltimestamp(dev, crtc, &t_vblank, 0);
-	} while (cur_vblank != dev->driver->get_vblank_counter(dev, crtc));
-
-	/* Deal with counter wrap */
-	diff = cur_vblank - dev->vblank[crtc].last;
-	if (cur_vblank < dev->vblank[crtc].last) {
-		diff += dev->max_vblank_count;
-
-		DRM_DEBUG("last_vblank[%d]=0x%x, cur_vblank=0x%x => diff=0x%x\n",
-			  crtc, dev->vblank[crtc].last, cur_vblank, diff);
-	}
-
-	DRM_DEBUG("enabling vblank interrupts on crtc %d, missed %d\n",
-		  crtc, diff);
-
-	/* Reinitialize corresponding vblank timestamp if high-precision query
-	 * available. Skip this step if query unsupported or failed. Will
-	 * reinitialize delayed at next vblank interrupt in that case.
-	 */
-	if (rc) {
-		tslot = atomic_read(&dev->vblank[crtc].count) + diff;
-		vblanktimestamp(dev, crtc, tslot) = t_vblank;
-	}
-
-	smp_mb__before_atomic();
-	atomic_add(diff, &dev->vblank[crtc].count);
-	smp_mb__after_atomic();
-}
-
-/**
  * drm_vblank_enable - enable the vblank interrupt on a CRTC
  * @dev: DRM device
  * @crtc: CRTC in question
  */
 static int drm_vblank_enable(struct drm_device *dev, int crtc)
 {
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
 	int ret = 0;
 
 	assert_spin_locked(&dev->vbl_lock);
 
 	spin_lock(&dev->vblank_time_lock);
 
-	if (!dev->vblank[crtc].enabled) {
+	if (!vblank->enabled) {
 		/*
 		 * Enable vblank irqs under vblank_time_lock protection.
 		 * All vblank count & timestamp updates are held off
@@ -887,9 +947,9 @@ static int drm_vblank_enable(struct drm_device *dev, int crtc)
 		ret = dev->driver->enable_vblank(dev, crtc);
 		DRM_DEBUG("enabling vblank on crtc %d, ret: %d\n", crtc, ret);
 		if (ret)
-			atomic_dec(&dev->vblank[crtc].refcount);
+			atomic_dec(&vblank->refcount);
 		else {
-			dev->vblank[crtc].enabled = true;
+			vblank->enabled = true;
 			drm_update_vblank_count(dev, crtc);
 		}
 	}
@@ -914,16 +974,20 @@ static int drm_vblank_enable(struct drm_device *dev, int crtc)
  */
 int drm_vblank_get(struct drm_device *dev, int crtc)
 {
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
 	unsigned long irqflags;
 	int ret = 0;
 
+	if (WARN_ON(crtc >= dev->num_crtcs))
+		return -EINVAL;
+
 	spin_lock_irqsave(&dev->vbl_lock, irqflags);
 	/* Going from 0->1 means we have to enable interrupts again */
-	if (atomic_add_return(1, &dev->vblank[crtc].refcount) == 1) {
+	if (atomic_add_return(1, &vblank->refcount) == 1) {
 		ret = drm_vblank_enable(dev, crtc);
 	} else {
-		if (!dev->vblank[crtc].enabled) {
-			atomic_dec(&dev->vblank[crtc].refcount);
+		if (!vblank->enabled) {
+			atomic_dec(&vblank->refcount);
 			ret = -EINVAL;
 		}
 	}
@@ -963,13 +1027,23 @@ EXPORT_SYMBOL(drm_crtc_vblank_get);
  */
 void drm_vblank_put(struct drm_device *dev, int crtc)
 {
-	BUG_ON(atomic_read(&dev->vblank[crtc].refcount) == 0);
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
+
+	BUG_ON(atomic_read(&vblank->refcount) == 0);
+
+	if (WARN_ON(crtc >= dev->num_crtcs))
+		return;
 
 	/* Last user schedules interrupt disable */
-	if (atomic_dec_and_test(&dev->vblank[crtc].refcount) &&
-	    (drm_vblank_offdelay > 0))
-		mod_timer(&dev->vblank[crtc].disable_timer,
-			  jiffies + ((drm_vblank_offdelay * HZ)/1000));
+	if (atomic_dec_and_test(&vblank->refcount)) {
+		if (drm_vblank_offdelay == 0)
+			return;
+		else if (dev->vblank_disable_immediate || drm_vblank_offdelay < 0)
+			vblank_disable_fn((unsigned long)vblank);
+		else
+			mod_timer(&vblank->disable_timer,
+				  jiffies + ((drm_vblank_offdelay * HZ)/1000));
+	}
 }
 EXPORT_SYMBOL(drm_vblank_put);
 
@@ -989,6 +1063,50 @@ void drm_crtc_vblank_put(struct drm_crtc *crtc)
 EXPORT_SYMBOL(drm_crtc_vblank_put);
 
 /**
+ * drm_wait_one_vblank - wait for one vblank
+ * @dev: DRM device
+ * @crtc: crtc index
+ *
+ * This waits for one vblank to pass on @crtc, using the irq driver interfaces.
+ * It is a failure to call this when the vblank irq for @crtc is disabled, e.g.
+ * due to lack of driver support or because the crtc is off.
+ */
+void drm_wait_one_vblank(struct drm_device *dev, int crtc)
+{
+	int ret;
+	u32 last;
+
+	ret = drm_vblank_get(dev, crtc);
+	if (WARN(ret, "vblank not available on crtc %i, ret=%i\n", crtc, ret))
+		return;
+
+	last = drm_vblank_count(dev, crtc);
+
+	ret = wait_event_timeout(dev->vblank[crtc].queue,
+				 last != drm_vblank_count(dev, crtc),
+				 msecs_to_jiffies(100));
+
+	WARN(ret == 0, "vblank wait timed out on crtc %i\n", crtc);
+
+	drm_vblank_put(dev, crtc);
+}
+EXPORT_SYMBOL(drm_wait_one_vblank);
+
+/**
+ * drm_crtc_wait_one_vblank - wait for one vblank
+ * @crtc: DRM crtc
+ *
+ * This waits for one vblank to pass on @crtc, using the irq driver interfaces.
+ * It is a failure to call this when the vblank irq for @crtc is disabled, e.g.
+ * due to lack of driver support or because the crtc is off.
+ */
+void drm_crtc_wait_one_vblank(struct drm_crtc *crtc)
+{
+	drm_wait_one_vblank(crtc->dev, drm_crtc_index(crtc));
+}
+EXPORT_SYMBOL(drm_crtc_wait_one_vblank);
+
+/**
  * drm_vblank_off - disable vblank events on a CRTC
  * @dev: DRM device
  * @crtc: CRTC in question
@@ -1004,19 +1122,34 @@ EXPORT_SYMBOL(drm_crtc_vblank_put);
  */
 void drm_vblank_off(struct drm_device *dev, int crtc)
 {
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
 	struct drm_pending_vblank_event *e, *t;
 	struct timeval now;
 	unsigned long irqflags;
 	unsigned int seq;
 
-	spin_lock_irqsave(&dev->vbl_lock, irqflags);
+	if (WARN_ON(crtc >= dev->num_crtcs))
+		return;
+
+	spin_lock_irqsave(&dev->event_lock, irqflags);
+
+	spin_lock(&dev->vbl_lock);
 	vblank_disable_and_save(dev, crtc);
-	wake_up(&dev->vblank[crtc].queue);
+	wake_up(&vblank->queue);
+
+	/*
+	 * Prevent subsequent drm_vblank_get() from re-enabling
+	 * the vblank interrupt by bumping the refcount.
+	 */
+	if (!vblank->inmodeset) {
+		atomic_inc(&vblank->refcount);
+		vblank->inmodeset = 1;
+	}
+	spin_unlock(&dev->vbl_lock);
 
 	/* Send any queued vblank events, lest the natives grow disquiet */
 	seq = drm_vblank_count_and_time(dev, crtc, &now);
 
-	spin_lock(&dev->event_lock);
 	list_for_each_entry_safe(e, t, &dev->vblank_event_list, base.link) {
 		if (e->pipe != crtc)
 			continue;
@@ -1027,9 +1160,7 @@ void drm_vblank_off(struct drm_device *dev, int crtc)
 		drm_vblank_put(dev, e->pipe);
 		send_vblank_event(dev, e, seq, &now);
 	}
-	spin_unlock(&dev->event_lock);
-
-	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
+	spin_unlock_irqrestore(&dev->event_lock, irqflags);
 }
 EXPORT_SYMBOL(drm_vblank_off);
 
@@ -1066,11 +1197,35 @@ EXPORT_SYMBOL(drm_crtc_vblank_off);
  */
 void drm_vblank_on(struct drm_device *dev, int crtc)
 {
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
 	unsigned long irqflags;
 
+	if (WARN_ON(crtc >= dev->num_crtcs))
+		return;
+
 	spin_lock_irqsave(&dev->vbl_lock, irqflags);
-	/* re-enable interrupts if there's are users left */
-	if (atomic_read(&dev->vblank[crtc].refcount) != 0)
+	/* Drop our private "prevent drm_vblank_get" refcount */
+	if (vblank->inmodeset) {
+		atomic_dec(&vblank->refcount);
+		vblank->inmodeset = 0;
+	}
+
+	/*
+	 * sample the current counter to avoid random jumps
+	 * when drm_vblank_enable() applies the diff
+	 *
+	 * -1 to make sure user will never see the same
+	 * vblank counter value before and after a modeset
+	 */
+	vblank->last =
+		(dev->driver->get_vblank_counter(dev, crtc) - 1) &
+		dev->max_vblank_count;
+	/*
+	 * re-enable interrupts if there are users left, or the
+	 * user wishes vblank interrupts to be enabled all the time.
+	 */
+	if (atomic_read(&vblank->refcount) != 0 ||
+	    (!dev->vblank_disable_immediate && drm_vblank_offdelay == 0))
 		WARN_ON(drm_vblank_enable(dev, crtc));
 	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 }
@@ -1118,9 +1273,15 @@ EXPORT_SYMBOL(drm_crtc_vblank_on);
  */
 void drm_vblank_pre_modeset(struct drm_device *dev, int crtc)
 {
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
+
 	/* vblank is not initialized (IRQ not installed ?), or has been freed */
 	if (!dev->num_crtcs)
 		return;
+
+	if (WARN_ON(crtc >= dev->num_crtcs))
+		return;
+
 	/*
 	 * To avoid all the problems that might happen if interrupts
 	 * were enabled/disabled around or between these calls, we just
@@ -1128,10 +1289,10 @@ void drm_vblank_pre_modeset(struct drm_device *dev, int crtc)
 	 * to avoid corrupting the count if multiple, mismatch calls occur),
 	 * so that interrupts remain enabled in the interim.
 	 */
-	if (!dev->vblank[crtc].inmodeset) {
-		dev->vblank[crtc].inmodeset = 0x1;
+	if (!vblank->inmodeset) {
+		vblank->inmodeset = 0x1;
 		if (drm_vblank_get(dev, crtc) == 0)
-			dev->vblank[crtc].inmodeset |= 0x2;
+			vblank->inmodeset |= 0x2;
 	}
 }
 EXPORT_SYMBOL(drm_vblank_pre_modeset);
@@ -1146,21 +1307,22 @@ EXPORT_SYMBOL(drm_vblank_pre_modeset);
  */
 void drm_vblank_post_modeset(struct drm_device *dev, int crtc)
 {
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
 	unsigned long irqflags;
 
 	/* vblank is not initialized (IRQ not installed ?), or has been freed */
 	if (!dev->num_crtcs)
 		return;
 
-	if (dev->vblank[crtc].inmodeset) {
+	if (vblank->inmodeset) {
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
 		dev->vblank_disable_allowed = true;
 		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 
-		if (dev->vblank[crtc].inmodeset & 0x2)
+		if (vblank->inmodeset & 0x2)
 			drm_vblank_put(dev, crtc);
 
-		dev->vblank[crtc].inmodeset = 0;
+		vblank->inmodeset = 0;
 	}
 }
 EXPORT_SYMBOL(drm_vblank_post_modeset);
@@ -1212,6 +1374,7 @@ static int drm_queue_vblank_event(struct drm_device *dev, int pipe,
 				  union drm_wait_vblank *vblwait,
 				  struct drm_file *file_priv)
 {
+	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
 	struct drm_pending_vblank_event *e;
 	struct timeval now;
 	unsigned long flags;
@@ -1235,6 +1398,18 @@ static int drm_queue_vblank_event(struct drm_device *dev, int pipe,
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 
+	/*
+	 * drm_vblank_off() might have been called after we called
+	 * drm_vblank_get(). drm_vblank_off() holds event_lock
+	 * around the vblank disable, so no need for further locking.
+	 * The reference from drm_vblank_get() protects against
+	 * vblank disable from another source.
+	 */
+	if (!vblank->enabled) {
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+
 	if (file_priv->event_space < sizeof e->event) {
 		ret = -EBUSY;
 		goto err_unlock;
@@ -1295,6 +1470,7 @@ err_put:
 int drm_wait_vblank(struct drm_device *dev, void *data,
 		    struct drm_file *file_priv)
 {
+	struct drm_vblank_crtc *vblank;
 	union drm_wait_vblank *vblwait = data;
 	int ret;
 	unsigned int flags, seq, crtc, high_crtc;
@@ -1324,6 +1500,8 @@ int drm_wait_vblank(struct drm_device *dev, void *data,
 	if (crtc >= dev->num_crtcs)
 		return -EINVAL;
 
+	vblank = &dev->vblank[crtc];
+
 	ret = drm_vblank_get(dev, crtc);
 	if (ret) {
 		DRM_DEBUG("failed to acquire vblank counter, %d\n", ret);
@@ -1356,11 +1534,11 @@ int drm_wait_vblank(struct drm_device *dev, void *data,
 
 	DRM_DEBUG("waiting on vblank count %d, crtc %d\n",
 		  vblwait->request.sequence, crtc);
-	dev->vblank[crtc].last_wait = vblwait->request.sequence;
-	DRM_WAIT_ON(ret, dev->vblank[crtc].queue, 3 * HZ,
+	vblank->last_wait = vblwait->request.sequence;
+	DRM_WAIT_ON(ret, vblank->queue, 3 * HZ,
 		    (((drm_vblank_count(dev, crtc) -
 		       vblwait->request.sequence) <= (1 << 23)) ||
-		     !dev->vblank[crtc].enabled ||
+		     !vblank->enabled ||
 		     !dev->irq_enabled));
 
 	if (ret != -EINTR) {
@@ -1385,12 +1563,11 @@ static void drm_handle_vblank_events(struct drm_device *dev, int crtc)
 {
 	struct drm_pending_vblank_event *e, *t;
 	struct timeval now;
-	unsigned long flags;
 	unsigned int seq;
 
-	seq = drm_vblank_count_and_time(dev, crtc, &now);
+	assert_spin_locked(&dev->event_lock);
 
-	spin_lock_irqsave(&dev->event_lock, flags);
+	seq = drm_vblank_count_and_time(dev, crtc, &now);
 
 	list_for_each_entry_safe(e, t, &dev->vblank_event_list, base.link) {
 		if (e->pipe != crtc)
@@ -1406,8 +1583,6 @@ static void drm_handle_vblank_events(struct drm_device *dev, int crtc)
 		send_vblank_event(dev, e, seq, &now);
 	}
 
-	spin_unlock_irqrestore(&dev->event_lock, flags);
-
 	trace_drm_vblank_event(crtc, seq);
 }
 
@@ -1421,6 +1596,7 @@ static void drm_handle_vblank_events(struct drm_device *dev, int crtc)
  */
 bool drm_handle_vblank(struct drm_device *dev, int crtc)
 {
+	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
 	u32 vblcount;
 	s64 diff_ns;
 	struct timeval tvblank;
@@ -1429,15 +1605,21 @@ bool drm_handle_vblank(struct drm_device *dev, int crtc)
 	if (!dev->num_crtcs)
 		return false;
 
+	if (WARN_ON(crtc >= dev->num_crtcs))
+		return false;
+
+	spin_lock_irqsave(&dev->event_lock, irqflags);
+
 	/* Need timestamp lock to prevent concurrent execution with
 	 * vblank enable/disable, as this would cause inconsistent
 	 * or corrupted timestamps and vblank counts.
 	 */
-	spin_lock_irqsave(&dev->vblank_time_lock, irqflags);
+	spin_lock(&dev->vblank_time_lock);
 
 	/* Vblank irq handling disabled. Nothing to do. */
-	if (!dev->vblank[crtc].enabled) {
-		spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags);
+	if (!vblank->enabled) {
+		spin_unlock(&dev->vblank_time_lock);
+		spin_unlock_irqrestore(&dev->event_lock, irqflags);
 		return false;
 	}
 
@@ -1446,7 +1628,7 @@ bool drm_handle_vblank(struct drm_device *dev, int crtc)
 	 */
 
 	/* Get current timestamp and count. */
-	vblcount = atomic_read(&dev->vblank[crtc].count);
+	vblcount = atomic_read(&vblank->count);
 	drm_get_last_vbltimestamp(dev, crtc, &tvblank, DRM_CALLED_FROM_VBLIRQ);
 
 	/* Compute time difference to timestamp of last vblank */
@@ -1470,17 +1652,20 @@ bool drm_handle_vblank(struct drm_device *dev, int crtc)
 		 * the timestamp computed above.
 		 */
 		smp_mb__before_atomic();
-		atomic_inc(&dev->vblank[crtc].count);
+		atomic_inc(&vblank->count);
 		smp_mb__after_atomic();
 	} else {
 		DRM_DEBUG("crtc %d: Redundant vblirq ignored. diff_ns = %d\n",
 			  crtc, (int) diff_ns);
 	}
 
-	wake_up(&dev->vblank[crtc].queue);
+	spin_unlock(&dev->vblank_time_lock);
+
+	wake_up(&vblank->queue);
 	drm_handle_vblank_events(dev, crtc);
 
-	spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags);
+	spin_unlock_irqrestore(&dev->event_lock, irqflags);
+
 	return true;
 }
 EXPORT_SYMBOL(drm_handle_vblank);
diff --git a/drivers/gpu/drm/drm_legacy.h b/drivers/gpu/drm/drm_legacy.h
index d34f20a79b7c..c1dc61473db5 100644
--- a/drivers/gpu/drm/drm_legacy.h
+++ b/drivers/gpu/drm/drm_legacy.h
@@ -23,6 +23,15 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
+/*
+ * This file contains legacy interfaces that modern drm drivers
+ * should no longer be using. They cannot be removed as legacy
+ * drivers use them, and removing them are API breaks.
+ */
+#include <linux/list.h>
+#include <drm/drm_legacy.h>
+
+struct agp_memory;
 struct drm_device;
 struct drm_file;
 
@@ -48,4 +57,57 @@ int drm_legacy_rmctx(struct drm_device *d, void *v, struct drm_file *f);
 int drm_legacy_setsareactx(struct drm_device *d, void *v, struct drm_file *f);
 int drm_legacy_getsareactx(struct drm_device *d, void *v, struct drm_file *f);
 
+/*
+ * Generic Buffer Management
+ */
+
+#define DRM_MAP_HASH_OFFSET 0x10000000
+
+int drm_legacy_addmap_ioctl(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_rmmap_ioctl(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_addbufs(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_infobufs(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_markbufs(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_freebufs(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_mapbufs(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_dma_ioctl(struct drm_device *d, void *v, struct drm_file *f);
+
+void drm_legacy_vma_flush(struct drm_device *d);
+
+/*
+ * AGP Support
+ */
+
+struct drm_agp_mem {
+	unsigned long handle;
+	struct agp_memory *memory;
+	unsigned long bound;
+	int pages;
+	struct list_head head;
+};
+
+/*
+ * Generic Userspace Locking-API
+ */
+
+int drm_legacy_i_have_hw_lock(struct drm_device *d, struct drm_file *f);
+int drm_legacy_lock(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_unlock(struct drm_device *d, void *v, struct drm_file *f);
+int drm_legacy_lock_free(struct drm_lock_data *lock, unsigned int ctx);
+
+/* DMA support */
+int drm_legacy_dma_setup(struct drm_device *dev);
+void drm_legacy_dma_takedown(struct drm_device *dev);
+void drm_legacy_free_buffer(struct drm_device *dev,
+			    struct drm_buf * buf);
+void drm_legacy_reclaim_buffers(struct drm_device *dev,
+				struct drm_file *filp);
+
+/* Scatter Gather Support */
+void drm_legacy_sg_cleanup(struct drm_device *dev);
+int drm_legacy_sg_alloc(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int drm_legacy_sg_free(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv);
+
 #endif /* __DRM_LEGACY_H__ */
diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index e26b59e385ff..f861361a635e 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -36,6 +36,7 @@
 #include <linux/export.h>
 #include <drm/drmP.h>
 #include "drm_legacy.h"
+#include "drm_internal.h"
 
 static int drm_notifier(void *priv);
 
@@ -52,7 +53,8 @@ static int drm_lock_take(struct drm_lock_data *lock_data, unsigned int context);
  *
  * Add the current task to the lock wait queue, and attempt to take to lock.
  */
-int drm_lock(struct drm_device *dev, void *data, struct drm_file *file_priv)
+int drm_legacy_lock(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv)
 {
 	DECLARE_WAITQUEUE(entry, current);
 	struct drm_lock *lock = data;
@@ -120,7 +122,7 @@ int drm_lock(struct drm_device *dev, void *data, struct drm_file *file_priv)
 		sigaddset(&dev->sigmask, SIGTTOU);
 		dev->sigdata.context = lock->context;
 		dev->sigdata.lock = master->lock.hw_lock;
-		block_all_signals(drm_notifier, &dev->sigdata, &dev->sigmask);
+		block_all_signals(drm_notifier, dev, &dev->sigmask);
 	}
 
 	if (dev->driver->dma_quiescent && (lock->flags & _DRM_LOCK_QUIESCENT))
@@ -146,7 +148,7 @@ int drm_lock(struct drm_device *dev, void *data, struct drm_file *file_priv)
  *
  * Transfer and free the lock.
  */
-int drm_unlock(struct drm_device *dev, void *data, struct drm_file *file_priv)
+int drm_legacy_unlock(struct drm_device *dev, void *data, struct drm_file *file_priv)
 {
 	struct drm_lock *lock = data;
 	struct drm_master *master = file_priv->master;
@@ -157,7 +159,7 @@ int drm_unlock(struct drm_device *dev, void *data, struct drm_file *file_priv)
 		return -EINVAL;
 	}
 
-	if (drm_lock_free(&master->lock, lock->context)) {
+	if (drm_legacy_lock_free(&master->lock, lock->context)) {
 		/* FIXME: Should really bail out here. */
 	}
 
@@ -250,7 +252,7 @@ static int drm_lock_transfer(struct drm_lock_data *lock_data,
  * Marks the lock as not held, via the \p cmpxchg instruction. Wakes any task
  * waiting on the lock queue.
  */
-int drm_lock_free(struct drm_lock_data *lock_data, unsigned int context)
+int drm_legacy_lock_free(struct drm_lock_data *lock_data, unsigned int context)
 {
 	unsigned int old, new, prev;
 	volatile unsigned int *lock = &lock_data->hw_lock->lock;
@@ -286,26 +288,27 @@ int drm_lock_free(struct drm_lock_data *lock_data, unsigned int context)
  * If the lock is not held, then let the signal proceed as usual.  If the lock
  * is held, then set the contended flag and keep the signal blocked.
  *
- * \param priv pointer to a drm_sigdata structure.
+ * \param priv pointer to a drm_device structure.
  * \return one if the signal should be delivered normally, or zero if the
  * signal should be blocked.
  */
 static int drm_notifier(void *priv)
 {
-	struct drm_sigdata *s = (struct drm_sigdata *) priv;
+	struct drm_device *dev = priv;
+	struct drm_hw_lock *lock = dev->sigdata.lock;
 	unsigned int old, new, prev;
 
 	/* Allow signal delivery if lock isn't held */
-	if (!s->lock || !_DRM_LOCK_IS_HELD(s->lock->lock)
-	    || _DRM_LOCKING_CONTEXT(s->lock->lock) != s->context)
+	if (!lock || !_DRM_LOCK_IS_HELD(lock->lock)
+	    || _DRM_LOCKING_CONTEXT(lock->lock) != dev->sigdata.context)
 		return 1;
 
 	/* Otherwise, set flag to force call to
 	   drmUnlock */
 	do {
-		old = s->lock->lock;
+		old = lock->lock;
 		new = old | _DRM_LOCK_CONT;
-		prev = cmpxchg(&s->lock->lock, old, new);
+		prev = cmpxchg(&lock->lock, old, new);
 	} while (prev != old);
 	return 0;
 }
@@ -323,7 +326,7 @@ static int drm_notifier(void *priv)
  * having to worry about starvation.
  */
 
-void drm_idlelock_take(struct drm_lock_data *lock_data)
+void drm_legacy_idlelock_take(struct drm_lock_data *lock_data)
 {
 	int ret;
 
@@ -340,9 +343,9 @@ void drm_idlelock_take(struct drm_lock_data *lock_data)
 	}
 	spin_unlock_bh(&lock_data->spinlock);
 }
-EXPORT_SYMBOL(drm_idlelock_take);
+EXPORT_SYMBOL(drm_legacy_idlelock_take);
 
-void drm_idlelock_release(struct drm_lock_data *lock_data)
+void drm_legacy_idlelock_release(struct drm_lock_data *lock_data)
 {
 	unsigned int old, prev;
 	volatile unsigned int *lock = &lock_data->hw_lock->lock;
@@ -360,9 +363,10 @@ void drm_idlelock_release(struct drm_lock_data *lock_data)
 	}
 	spin_unlock_bh(&lock_data->spinlock);
 }
-EXPORT_SYMBOL(drm_idlelock_release);
+EXPORT_SYMBOL(drm_legacy_idlelock_release);
 
-int drm_i_have_hw_lock(struct drm_device *dev, struct drm_file *file_priv)
+int drm_legacy_i_have_hw_lock(struct drm_device *dev,
+			      struct drm_file *file_priv)
 {
 	struct drm_master *master = file_priv->master;
 	return (file_priv->lock_count && master->lock.hw_lock &&
diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c
index 00c67c0f2381..a521ef6ff807 100644
--- a/drivers/gpu/drm/drm_memory.c
+++ b/drivers/gpu/drm/drm_memory.c
@@ -36,8 +36,20 @@
 #include <linux/highmem.h>
 #include <linux/export.h>
 #include <drm/drmP.h>
+#include "drm_legacy.h"
 
 #if __OS_HAS_AGP
+
+#ifdef HAVE_PAGE_AGP
+# include <asm/agp.h>
+#else
+# ifdef __powerpc__
+#  define PAGE_AGP	__pgprot(_PAGE_KERNEL | _PAGE_NO_CACHE)
+# else
+#  define PAGE_AGP	PAGE_KERNEL
+# endif
+#endif
+
 static void *agp_remap(unsigned long offset, unsigned long size,
 		       struct drm_device * dev)
 {
@@ -108,25 +120,25 @@ static inline void *agp_remap(unsigned long offset, unsigned long size,
 
 #endif				/* agp */
 
-void drm_core_ioremap(struct drm_local_map *map, struct drm_device *dev)
+void drm_legacy_ioremap(struct drm_local_map *map, struct drm_device *dev)
 {
 	if (dev->agp && dev->agp->cant_use_aperture && map->type == _DRM_AGP)
 		map->handle = agp_remap(map->offset, map->size, dev);
 	else
 		map->handle = ioremap(map->offset, map->size);
 }
-EXPORT_SYMBOL(drm_core_ioremap);
+EXPORT_SYMBOL(drm_legacy_ioremap);
 
-void drm_core_ioremap_wc(struct drm_local_map *map, struct drm_device *dev)
+void drm_legacy_ioremap_wc(struct drm_local_map *map, struct drm_device *dev)
 {
 	if (dev->agp && dev->agp->cant_use_aperture && map->type == _DRM_AGP)
 		map->handle = agp_remap(map->offset, map->size, dev);
 	else
 		map->handle = ioremap_wc(map->offset, map->size);
 }
-EXPORT_SYMBOL(drm_core_ioremap_wc);
+EXPORT_SYMBOL(drm_legacy_ioremap_wc);
 
-void drm_core_ioremapfree(struct drm_local_map *map, struct drm_device *dev)
+void drm_legacy_ioremapfree(struct drm_local_map *map, struct drm_device *dev)
 {
 	if (!map->handle || !map->size)
 		return;
@@ -136,4 +148,4 @@ void drm_core_ioremapfree(struct drm_local_map *map, struct drm_device *dev)
 	else
 		iounmap(map->handle);
 }
-EXPORT_SYMBOL(drm_core_ioremapfree);
+EXPORT_SYMBOL(drm_legacy_ioremapfree);
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index 6aa6a9e95570..eb6dfe52cab2 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -231,6 +231,9 @@ ssize_t mipi_dsi_dcs_write(struct mipi_dsi_device *dsi, const void *data,
 		break;
 	}
 
+	if (dsi->mode_flags & MIPI_DSI_MODE_LPM)
+		msg.flags = MIPI_DSI_MSG_USE_LPM;
+
 	return ops->transfer(dsi->host, &msg);
 }
 EXPORT_SYMBOL(mipi_dsi_dcs_write);
@@ -260,6 +263,9 @@ ssize_t mipi_dsi_dcs_read(struct mipi_dsi_device *dsi, u8 cmd, void *data,
 	if (!ops || !ops->transfer)
 		return -ENOSYS;
 
+	if (dsi->mode_flags & MIPI_DSI_MODE_LPM)
+		msg.flags = MIPI_DSI_MSG_USE_LPM;
+
 	return ops->transfer(dsi->host, &msg);
 }
 EXPORT_SYMBOL(mipi_dsi_dcs_read);
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index bedf1894e17e..d1b7d2006529 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1259,6 +1259,7 @@ drm_mode_create_from_cmdline_mode(struct drm_device *dev,
 	if (!mode)
 		return NULL;
 
+	mode->type |= DRM_MODE_TYPE_USERDEF;
 	drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V);
 	return mode;
 }
diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c
index 0dc57d5ecd10..474e4d12a2d8 100644
--- a/drivers/gpu/drm/drm_modeset_lock.c
+++ b/drivers/gpu/drm/drm_modeset_lock.c
@@ -35,7 +35,7 @@
  * of extra utility/tracking out of our acquire-ctx.  This is provided
  * by drm_modeset_lock / drm_modeset_acquire_ctx.
  *
- * For basic principles of ww_mutex, see: Documentation/ww-mutex-design.txt
+ * For basic principles of ww_mutex, see: Documentation/locking/ww-mutex-design.txt
  *
  * The basic usage pattern is to:
  *
@@ -57,6 +57,212 @@
 
 
 /**
+ * __drm_modeset_lock_all - internal helper to grab all modeset locks
+ * @dev: DRM device
+ * @trylock: trylock mode for atomic contexts
+ *
+ * This is a special version of drm_modeset_lock_all() which can also be used in
+ * atomic contexts. Then @trylock must be set to true.
+ *
+ * Returns:
+ * 0 on success or negative error code on failure.
+ */
+int __drm_modeset_lock_all(struct drm_device *dev,
+			   bool trylock)
+{
+	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_modeset_acquire_ctx *ctx;
+	int ret;
+
+	ctx = kzalloc(sizeof(*ctx),
+		      trylock ? GFP_ATOMIC : GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	if (trylock) {
+		if (!mutex_trylock(&config->mutex))
+			return -EBUSY;
+	} else {
+		mutex_lock(&config->mutex);
+	}
+
+	drm_modeset_acquire_init(ctx, 0);
+	ctx->trylock_only = trylock;
+
+retry:
+	ret = drm_modeset_lock(&config->connection_mutex, ctx);
+	if (ret)
+		goto fail;
+	ret = drm_modeset_lock_all_crtcs(dev, ctx);
+	if (ret)
+		goto fail;
+
+	WARN_ON(config->acquire_ctx);
+
+	/* now we hold the locks, so now that it is safe, stash the
+	 * ctx for drm_modeset_unlock_all():
+	 */
+	config->acquire_ctx = ctx;
+
+	drm_warn_on_modeset_not_all_locked(dev);
+
+	return 0;
+
+fail:
+	if (ret == -EDEADLK) {
+		drm_modeset_backoff(ctx);
+		goto retry;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(__drm_modeset_lock_all);
+
+/**
+ * drm_modeset_lock_all - take all modeset locks
+ * @dev: drm device
+ *
+ * This function takes all modeset locks, suitable where a more fine-grained
+ * scheme isn't (yet) implemented. Locks must be dropped with
+ * drm_modeset_unlock_all.
+ */
+void drm_modeset_lock_all(struct drm_device *dev)
+{
+	WARN_ON(__drm_modeset_lock_all(dev, false) != 0);
+}
+EXPORT_SYMBOL(drm_modeset_lock_all);
+
+/**
+ * drm_modeset_unlock_all - drop all modeset locks
+ * @dev: device
+ *
+ * This function drop all modeset locks taken by drm_modeset_lock_all.
+ */
+void drm_modeset_unlock_all(struct drm_device *dev)
+{
+	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx;
+
+	if (WARN_ON(!ctx))
+		return;
+
+	config->acquire_ctx = NULL;
+	drm_modeset_drop_locks(ctx);
+	drm_modeset_acquire_fini(ctx);
+
+	kfree(ctx);
+
+	mutex_unlock(&dev->mode_config.mutex);
+}
+EXPORT_SYMBOL(drm_modeset_unlock_all);
+
+/**
+ * drm_modeset_lock_crtc - lock crtc with hidden acquire ctx
+ * @crtc: drm crtc
+ *
+ * This function locks the given crtc using a hidden acquire context. This is
+ * necessary so that drivers internally using the atomic interfaces can grab
+ * further locks with the lock acquire context.
+ */
+void drm_modeset_lock_crtc(struct drm_crtc *crtc)
+{
+	struct drm_modeset_acquire_ctx *ctx;
+	int ret;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (WARN_ON(!ctx))
+		return;
+
+	drm_modeset_acquire_init(ctx, 0);
+
+retry:
+	ret = drm_modeset_lock(&crtc->mutex, ctx);
+	if (ret)
+		goto fail;
+
+	WARN_ON(crtc->acquire_ctx);
+
+	/* now we hold the locks, so now that it is safe, stash the
+	 * ctx for drm_modeset_unlock_crtc():
+	 */
+	crtc->acquire_ctx = ctx;
+
+	return;
+
+fail:
+	if (ret == -EDEADLK) {
+		drm_modeset_backoff(ctx);
+		goto retry;
+	}
+}
+EXPORT_SYMBOL(drm_modeset_lock_crtc);
+
+/**
+ * drm_modeset_legacy_acquire_ctx - find acquire ctx for legacy ioctls
+ * @crtc: drm crtc
+ *
+ * Legacy ioctl operations like cursor updates or page flips only have per-crtc
+ * locking, and store the acquire ctx in the corresponding crtc. All other
+ * legacy operations take all locks and use a global acquire context. This
+ * function grabs the right one.
+ */
+struct drm_modeset_acquire_ctx *
+drm_modeset_legacy_acquire_ctx(struct drm_crtc *crtc)
+{
+	if (crtc->acquire_ctx)
+		return crtc->acquire_ctx;
+
+	WARN_ON(!crtc->dev->mode_config.acquire_ctx);
+
+	return crtc->dev->mode_config.acquire_ctx;
+}
+EXPORT_SYMBOL(drm_modeset_legacy_acquire_ctx);
+
+/**
+ * drm_modeset_unlock_crtc - drop crtc lock
+ * @crtc: drm crtc
+ *
+ * This drops the crtc lock acquire with drm_modeset_lock_crtc() and all other
+ * locks acquired through the hidden context.
+ */
+void drm_modeset_unlock_crtc(struct drm_crtc *crtc)
+{
+	struct drm_modeset_acquire_ctx *ctx = crtc->acquire_ctx;
+
+	if (WARN_ON(!ctx))
+		return;
+
+	crtc->acquire_ctx = NULL;
+	drm_modeset_drop_locks(ctx);
+	drm_modeset_acquire_fini(ctx);
+
+	kfree(ctx);
+}
+EXPORT_SYMBOL(drm_modeset_unlock_crtc);
+
+/**
+ * drm_warn_on_modeset_not_all_locked - check that all modeset locks are locked
+ * @dev: device
+ *
+ * Useful as a debug assert.
+ */
+void drm_warn_on_modeset_not_all_locked(struct drm_device *dev)
+{
+	struct drm_crtc *crtc;
+
+	/* Locking is currently fubar in the panic handler. */
+	if (oops_in_progress)
+		return;
+
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
+		WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
+
+	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
+}
+EXPORT_SYMBOL(drm_warn_on_modeset_not_all_locked);
+
+/**
  * drm_modeset_acquire_init - initialize acquire context
  * @ctx: the acquire context
  * @flags: for future
@@ -108,7 +314,12 @@ static inline int modeset_lock(struct drm_modeset_lock *lock,
 
 	WARN_ON(ctx->contended);
 
-	if (interruptible && slow) {
+	if (ctx->trylock_only) {
+		if (!ww_mutex_trylock(&lock->mutex))
+			return -EBUSY;
+		else
+			return 0;
+	} else if (interruptible && slow) {
 		ret = ww_mutex_lock_slow_interruptible(&lock->mutex, &ctx->ww_ctx);
 	} else if (interruptible) {
 		ret = ww_mutex_lock_interruptible(&lock->mutex, &ctx->ww_ctx);
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 020cfd934854..fd29f03645b8 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -27,6 +27,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/export.h>
 #include <drm/drmP.h>
+#include "drm_legacy.h"
 
 /**
  * drm_pci_alloc - Allocate a PCI consistent memory block, for DMA.
@@ -81,7 +82,7 @@ EXPORT_SYMBOL(drm_pci_alloc);
  *
  * This function is for internal use in the Linux-specific DRM core code.
  */
-void __drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
+void __drm_legacy_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 {
 	unsigned long addr;
 	size_t sz;
@@ -105,7 +106,7 @@ void __drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
  */
 void drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 {
-	__drm_pci_free(dev, dmah);
+	__drm_legacy_pci_free(dev, dmah);
 	kfree(dmah);
 }
 
@@ -127,34 +128,20 @@ static int drm_get_pci_domain(struct drm_device *dev)
 	return pci_domain_nr(dev->pdev->bus);
 }
 
-static int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master)
+int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master)
 {
-	int len, ret;
-	master->unique_len = 40;
-	master->unique_size = master->unique_len;
-	master->unique = kmalloc(master->unique_size, GFP_KERNEL);
-	if (master->unique == NULL)
+	master->unique = kasprintf(GFP_KERNEL, "pci:%04x:%02x:%02x.%d",
+					drm_get_pci_domain(dev),
+					dev->pdev->bus->number,
+					PCI_SLOT(dev->pdev->devfn),
+					PCI_FUNC(dev->pdev->devfn));
+	if (!master->unique)
 		return -ENOMEM;
 
-
-	len = snprintf(master->unique, master->unique_len,
-		       "pci:%04x:%02x:%02x.%d",
-		       drm_get_pci_domain(dev),
-		       dev->pdev->bus->number,
-		       PCI_SLOT(dev->pdev->devfn),
-		       PCI_FUNC(dev->pdev->devfn));
-
-	if (len >= master->unique_len) {
-		DRM_ERROR("buffer overflow");
-		ret = -EINVAL;
-		goto err;
-	} else
-		master->unique_len = len;
-
+	master->unique_len = strlen(master->unique);
 	return 0;
-err:
-	return ret;
 }
+EXPORT_SYMBOL(drm_pci_set_busid);
 
 int drm_pci_set_unique(struct drm_device *dev,
 		       struct drm_master *master,
@@ -163,8 +150,7 @@ int drm_pci_set_unique(struct drm_device *dev,
 	int domain, bus, slot, func, ret;
 
 	master->unique_len = u->unique_len;
-	master->unique_size = u->unique_len + 1;
-	master->unique = kmalloc(master->unique_size, GFP_KERNEL);
+	master->unique = kmalloc(master->unique_len + 1, GFP_KERNEL);
 	if (!master->unique) {
 		ret = -ENOMEM;
 		goto err;
@@ -269,10 +255,6 @@ void drm_pci_agp_destroy(struct drm_device *dev)
 	}
 }
 
-static struct drm_bus drm_pci_bus = {
-	.set_busid = drm_pci_set_busid,
-};
-
 /**
  * drm_get_pci_dev - Register a PCI device with the DRM subsystem
  * @pdev: PCI device
@@ -353,8 +335,6 @@ int drm_pci_init(struct drm_driver *driver, struct pci_driver *pdriver)
 
 	DRM_DEBUG("\n");
 
-	driver->bus = &drm_pci_bus;
-
 	if (driver->driver_features & DRIVER_MODESET)
 		return pci_register_driver(pdriver);
 
diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c
index d5b76f148c12..5314c9d5fef4 100644
--- a/drivers/gpu/drm/drm_platform.c
+++ b/drivers/gpu/drm/drm_platform.c
@@ -68,42 +68,23 @@ err_free:
 	return ret;
 }
 
-static int drm_platform_set_busid(struct drm_device *dev, struct drm_master *master)
+int drm_platform_set_busid(struct drm_device *dev, struct drm_master *master)
 {
-	int len, ret, id;
-
-	master->unique_len = 13 + strlen(dev->platformdev->name);
-	master->unique_size = master->unique_len;
-	master->unique = kmalloc(master->unique_len + 1, GFP_KERNEL);
-
-	if (master->unique == NULL)
-		return -ENOMEM;
+	int id;
 
 	id = dev->platformdev->id;
-
-	/* if only a single instance of the platform device, id will be
-	 * set to -1.. use 0 instead to avoid a funny looking bus-id:
-	 */
-	if (id == -1)
+	if (id < 0)
 		id = 0;
 
-	len = snprintf(master->unique, master->unique_len,
-			"platform:%s:%02d", dev->platformdev->name, id);
-
-	if (len > master->unique_len) {
-		DRM_ERROR("Unique buffer overflowed\n");
-		ret = -EINVAL;
-		goto err;
-	}
+	master->unique = kasprintf(GFP_KERNEL, "platform:%s:%02d",
+						dev->platformdev->name, id);
+	if (!master->unique)
+		return -ENOMEM;
 
+	master->unique_len = strlen(master->unique);
 	return 0;
-err:
-	return ret;
 }
-
-static struct drm_bus drm_platform_bus = {
-	.set_busid = drm_platform_set_busid,
-};
+EXPORT_SYMBOL(drm_platform_set_busid);
 
 /**
  * drm_platform_init - Register a platform device with the DRM subsystem
@@ -120,7 +101,6 @@ int drm_platform_init(struct drm_driver *driver, struct platform_device *platfor
 {
 	DRM_DEBUG("\n");
 
-	driver->bus = &drm_platform_bus;
 	return drm_get_platform_dev(platform_device, driver);
 }
 EXPORT_SYMBOL(drm_platform_init);
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 99d578bad17e..78ca30808422 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -29,6 +29,9 @@
 #include <linux/export.h>
 #include <linux/dma-buf.h>
 #include <drm/drmP.h>
+#include <drm/drm_gem.h>
+
+#include "drm_internal.h"
 
 /*
  * DMA-BUF/GEM Object references and lifetime overview:
@@ -522,7 +525,7 @@ struct drm_gem_object *drm_gem_prime_import(struct drm_device *dev,
 		goto fail_detach;
 	}
 
-	obj = dev->driver->gem_prime_import_sg_table(dev, dma_buf->size, sgt);
+	obj = dev->driver->gem_prime_import_sg_table(dev, attach, sgt);
 	if (IS_ERR(obj)) {
 		ret = PTR_ERR(obj);
 		goto fail_unmap;
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index db7d250f7ac7..6857e9ad6339 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -82,6 +82,22 @@ static void drm_mode_validate_flag(struct drm_connector *connector,
 	return;
 }
 
+static int drm_helper_probe_add_cmdline_mode(struct drm_connector *connector)
+{
+	struct drm_display_mode *mode;
+
+	if (!connector->cmdline_mode.specified)
+		return 0;
+
+	mode = drm_mode_create_from_cmdline_mode(connector->dev,
+						 &connector->cmdline_mode);
+	if (mode == NULL)
+		return 0;
+
+	drm_mode_probed_add(connector, mode);
+	return 1;
+}
+
 static int drm_helper_probe_single_connector_modes_merge_bits(struct drm_connector *connector,
 							      uint32_t maxX, uint32_t maxY, bool merge_type_bits)
 {
@@ -141,6 +157,7 @@ static int drm_helper_probe_single_connector_modes_merge_bits(struct drm_connect
 
 	if (count == 0 && connector->status == connector_status_connected)
 		count = drm_add_modes_noedid(connector, 1024, 768);
+	count += drm_helper_probe_add_cmdline_mode(connector);
 	if (count == 0)
 		goto prune;
 
diff --git a/drivers/gpu/drm/drm_scatter.c b/drivers/gpu/drm/drm_scatter.c
index 1c78406f6e71..4f0f3b36d537 100644
--- a/drivers/gpu/drm/drm_scatter.c
+++ b/drivers/gpu/drm/drm_scatter.c
@@ -34,6 +34,7 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <drm/drmP.h>
+#include "drm_legacy.h"
 
 #define DEBUG_SCATTER 0
 
@@ -78,8 +79,8 @@ void drm_legacy_sg_cleanup(struct drm_device *dev)
 # define ScatterHandle(x) (unsigned int)(x)
 #endif
 
-int drm_sg_alloc(struct drm_device *dev, void *data,
-		 struct drm_file *file_priv)
+int drm_legacy_sg_alloc(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
 {
 	struct drm_scatter_gather *request = data;
 	struct drm_sg_mem *entry;
@@ -194,8 +195,8 @@ int drm_sg_alloc(struct drm_device *dev, void *data,
 	return -ENOMEM;
 }
 
-int drm_sg_free(struct drm_device *dev, void *data,
-		struct drm_file *file_priv)
+int drm_legacy_sg_free(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
 {
 	struct drm_scatter_gather *request = data;
 	struct drm_sg_mem *entry;
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index ab1a5f6dde8a..cc3d6d6d67e0 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -21,6 +21,7 @@
 #include <drm/drm_sysfs.h>
 #include <drm/drm_core.h>
 #include <drm/drmP.h>
+#include "drm_internal.h"
 
 #define to_drm_minor(d) dev_get_drvdata(d)
 #define to_drm_connector(d) dev_get_drvdata(d)
diff --git a/drivers/gpu/drm/drm_usb.c b/drivers/gpu/drm/drm_usb.c
deleted file mode 100644
index f2fe94aab901..000000000000
--- a/drivers/gpu/drm/drm_usb.c
+++ /dev/null
@@ -1,88 +0,0 @@
-#include <drm/drmP.h>
-#include <drm/drm_usb.h>
-#include <linux/usb.h>
-#include <linux/module.h>
-
-int drm_get_usb_dev(struct usb_interface *interface,
-		    const struct usb_device_id *id,
-		    struct drm_driver *driver)
-{
-	struct drm_device *dev;
-	int ret;
-
-	DRM_DEBUG("\n");
-
-	dev = drm_dev_alloc(driver, &interface->dev);
-	if (!dev)
-		return -ENOMEM;
-
-	dev->usbdev = interface_to_usbdev(interface);
-	usb_set_intfdata(interface, dev);
-
-	ret = drm_dev_register(dev, 0);
-	if (ret)
-		goto err_free;
-
-	DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n",
-		 driver->name, driver->major, driver->minor, driver->patchlevel,
-		 driver->date, dev->primary->index);
-
-	return 0;
-
-err_free:
-	drm_dev_unref(dev);
-	return ret;
-
-}
-EXPORT_SYMBOL(drm_get_usb_dev);
-
-static int drm_usb_set_busid(struct drm_device *dev,
-			       struct drm_master *master)
-{
-	return 0;
-}
-
-static struct drm_bus drm_usb_bus = {
-	.set_busid = drm_usb_set_busid,
-};
-
-/**
- * drm_usb_init - Register matching USB devices with the DRM subsystem
- * @driver: DRM device driver
- * @udriver: USB device driver
- *
- * Registers one or more devices matched by a USB driver with the DRM
- * subsystem.
- *
- * Return: 0 on success or a negative error code on failure.
- */
-int drm_usb_init(struct drm_driver *driver, struct usb_driver *udriver)
-{
-	int res;
-	DRM_DEBUG("\n");
-
-	driver->bus = &drm_usb_bus;
-
-	res = usb_register(udriver);
-	return res;
-}
-EXPORT_SYMBOL(drm_usb_init);
-
-/**
- * drm_usb_exit - Unregister matching USB devices from the DRM subsystem
- * @driver: DRM device driver
- * @udriver: USB device driver
- *
- * Unregisters one or more devices matched by a USB driver from the DRM
- * subsystem.
- */
-void drm_usb_exit(struct drm_driver *driver,
-		  struct usb_driver *udriver)
-{
-	usb_deregister(udriver);
-}
-EXPORT_SYMBOL(drm_usb_exit);
-
-MODULE_AUTHOR("David Airlie");
-MODULE_DESCRIPTION("USB DRM support");
-MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index 24e045c4f531..4a2c328959e5 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -35,10 +35,19 @@
 
 #include <drm/drmP.h>
 #include <linux/export.h>
+#include <linux/seq_file.h>
 #if defined(__ia64__)
 #include <linux/efi.h>
 #include <linux/slab.h>
 #endif
+#include <asm/pgtable.h>
+#include "drm_legacy.h"
+
+struct drm_vma_entry {
+	struct list_head head;
+	struct vm_area_struct *vma;
+	pid_t pid;
+};
 
 static void drm_vm_open(struct vm_area_struct *vma);
 static void drm_vm_close(struct vm_area_struct *vma);
@@ -48,15 +57,11 @@ static pgprot_t drm_io_prot(struct drm_local_map *map,
 {
 	pgprot_t tmp = vm_get_page_prot(vma->vm_flags);
 
-#if defined(__i386__) || defined(__x86_64__)
+#if defined(__i386__) || defined(__x86_64__) || defined(__powerpc__)
 	if (map->type == _DRM_REGISTERS && !(map->flags & _DRM_WRITE_COMBINING))
 		tmp = pgprot_noncached(tmp);
 	else
 		tmp = pgprot_writecombine(tmp);
-#elif defined(__powerpc__)
-	pgprot_val(tmp) |= _PAGE_NO_CACHE;
-	if (map->type == _DRM_REGISTERS)
-		pgprot_val(tmp) |= _PAGE_GUARDED;
 #elif defined(__ia64__)
 	if (efi_range_is_wc(vma->vm_start, vma->vm_end -
 				    vma->vm_start))
@@ -263,7 +268,7 @@ static void drm_vm_shm_close(struct vm_area_struct *vma)
 				dmah.vaddr = map->handle;
 				dmah.busaddr = map->offset;
 				dmah.size = map->size;
-				__drm_pci_free(dev, &dmah);
+				__drm_legacy_pci_free(dev, &dmah);
 				break;
 			}
 			kfree(map);
@@ -412,7 +417,6 @@ void drm_vm_open_locked(struct drm_device *dev,
 		list_add(&vma_entry->head, &dev->vmalist);
 	}
 }
-EXPORT_SYMBOL_GPL(drm_vm_open_locked);
 
 static void drm_vm_open(struct vm_area_struct *vma)
 {
@@ -532,7 +536,7 @@ static resource_size_t drm_core_get_reg_ofs(struct drm_device *dev)
  * according to the mapping type and remaps the pages. Finally sets the file
  * pointer and calls vm_open().
  */
-int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma)
+static int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma)
 {
 	struct drm_file *priv = filp->private_data;
 	struct drm_device *dev = priv->minor->dev;
@@ -646,7 +650,7 @@ int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma)
 	return 0;
 }
 
-int drm_mmap(struct file *filp, struct vm_area_struct *vma)
+int drm_legacy_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct drm_file *priv = filp->private_data;
 	struct drm_device *dev = priv->minor->dev;
@@ -661,4 +665,69 @@ int drm_mmap(struct file *filp, struct vm_area_struct *vma)
 
 	return ret;
 }
-EXPORT_SYMBOL(drm_mmap);
+EXPORT_SYMBOL(drm_legacy_mmap);
+
+void drm_legacy_vma_flush(struct drm_device *dev)
+{
+	struct drm_vma_entry *vma, *vma_temp;
+
+	/* Clear vma list (only needed for legacy drivers) */
+	list_for_each_entry_safe(vma, vma_temp, &dev->vmalist, head) {
+		list_del(&vma->head);
+		kfree(vma);
+	}
+}
+
+int drm_vma_info(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_vma_entry *pt;
+	struct vm_area_struct *vma;
+	unsigned long vma_count = 0;
+#if defined(__i386__)
+	unsigned int pgprot;
+#endif
+
+	mutex_lock(&dev->struct_mutex);
+	list_for_each_entry(pt, &dev->vmalist, head)
+		vma_count++;
+
+	seq_printf(m, "vma use count: %lu, high_memory = %pK, 0x%pK\n",
+		   vma_count, high_memory,
+		   (void *)(unsigned long)virt_to_phys(high_memory));
+
+	list_for_each_entry(pt, &dev->vmalist, head) {
+		vma = pt->vma;
+		if (!vma)
+			continue;
+		seq_printf(m,
+			   "\n%5d 0x%pK-0x%pK %c%c%c%c%c%c 0x%08lx000",
+			   pt->pid,
+			   (void *)vma->vm_start, (void *)vma->vm_end,
+			   vma->vm_flags & VM_READ ? 'r' : '-',
+			   vma->vm_flags & VM_WRITE ? 'w' : '-',
+			   vma->vm_flags & VM_EXEC ? 'x' : '-',
+			   vma->vm_flags & VM_MAYSHARE ? 's' : 'p',
+			   vma->vm_flags & VM_LOCKED ? 'l' : '-',
+			   vma->vm_flags & VM_IO ? 'i' : '-',
+			   vma->vm_pgoff);
+
+#if defined(__i386__)
+		pgprot = pgprot_val(vma->vm_page_prot);
+		seq_printf(m, " %c%c%c%c%c%c%c%c%c",
+			   pgprot & _PAGE_PRESENT ? 'p' : '-',
+			   pgprot & _PAGE_RW ? 'w' : 'r',
+			   pgprot & _PAGE_USER ? 'u' : 's',
+			   pgprot & _PAGE_PWT ? 't' : 'b',
+			   pgprot & _PAGE_PCD ? 'u' : 'c',
+			   pgprot & _PAGE_ACCESSED ? 'a' : '-',
+			   pgprot & _PAGE_DIRTY ? 'd' : '-',
+			   pgprot & _PAGE_PSE ? 'm' : 'k',
+			   pgprot & _PAGE_GLOBAL ? 'g' : 'l');
+#endif
+		seq_printf(m, "\n");
+	}
+	mutex_unlock(&dev->struct_mutex);
+	return 0;
+}
diff --git a/drivers/gpu/drm/exynos/exynos_dp_core.c b/drivers/gpu/drm/exynos/exynos_dp_core.c
index 4f3c7eb2d37d..cd50ece31601 100644
--- a/drivers/gpu/drm/exynos/exynos_dp_core.c
+++ b/drivers/gpu/drm/exynos/exynos_dp_core.c
@@ -329,8 +329,8 @@ static int exynos_dp_link_start(struct exynos_dp_device *dp)
 		return retval;
 
 	for (lane = 0; lane < lane_count; lane++)
-		buf[lane] = DP_TRAIN_PRE_EMPHASIS_0 |
-			    DP_TRAIN_VOLTAGE_SWING_400;
+		buf[lane] = DP_TRAIN_PRE_EMPH_LEVEL_0 |
+			    DP_TRAIN_VOLTAGE_SWING_LEVEL_0;
 
 	retval = exynos_dp_write_bytes_to_dpcd(dp, DP_TRAINING_LANE0_SET,
 			lane_count, buf);
@@ -937,6 +937,8 @@ static enum drm_connector_status exynos_dp_detect(
 
 static void exynos_dp_connector_destroy(struct drm_connector *connector)
 {
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
 }
 
 static struct drm_connector_funcs exynos_dp_connector_funcs = {
@@ -1358,8 +1360,8 @@ static void exynos_dp_unbind(struct device *dev, struct device *master,
 
 	exynos_dp_dpms(display, DRM_MODE_DPMS_OFF);
 
+	exynos_dp_connector_destroy(&dp->connector);
 	encoder->funcs->destroy(encoder);
-	drm_connector_cleanup(&dp->connector);
 }
 
 static const struct component_ops exynos_dp_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index b68e58f78cd1..8e38e9f8e542 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -32,7 +32,6 @@ enum exynos_crtc_mode {
  * Exynos specific crtc structure.
  *
  * @drm_crtc: crtc object.
- * @drm_plane: pointer of private plane object for this crtc
  * @manager: the manager associated with this crtc
  * @pipe: a crtc index created at load() with a new crtc object creation
  *	and the crtc object would be set to private->crtc array
@@ -46,7 +45,6 @@ enum exynos_crtc_mode {
  */
 struct exynos_drm_crtc {
 	struct drm_crtc			drm_crtc;
-	struct drm_plane		*plane;
 	struct exynos_drm_manager	*manager;
 	unsigned int			pipe;
 	unsigned int			dpms;
@@ -94,12 +92,12 @@ static void exynos_drm_crtc_commit(struct drm_crtc *crtc)
 
 	exynos_drm_crtc_dpms(crtc, DRM_MODE_DPMS_ON);
 
-	exynos_plane_commit(exynos_crtc->plane);
+	exynos_plane_commit(crtc->primary);
 
 	if (manager->ops->commit)
 		manager->ops->commit(manager);
 
-	exynos_plane_dpms(exynos_crtc->plane, DRM_MODE_DPMS_ON);
+	exynos_plane_dpms(crtc->primary, DRM_MODE_DPMS_ON);
 }
 
 static bool
@@ -123,10 +121,9 @@ exynos_drm_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode,
 {
 	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
 	struct exynos_drm_manager *manager = exynos_crtc->manager;
-	struct drm_plane *plane = exynos_crtc->plane;
+	struct drm_framebuffer *fb = crtc->primary->fb;
 	unsigned int crtc_w;
 	unsigned int crtc_h;
-	int ret;
 
 	/*
 	 * copy the mode data adjusted by mode_fixup() into crtc->mode
@@ -134,29 +131,21 @@ exynos_drm_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode,
 	 */
 	memcpy(&crtc->mode, adjusted_mode, sizeof(*adjusted_mode));
 
-	crtc_w = crtc->primary->fb->width - x;
-	crtc_h = crtc->primary->fb->height - y;
+	crtc_w = fb->width - x;
+	crtc_h = fb->height - y;
 
 	if (manager->ops->mode_set)
 		manager->ops->mode_set(manager, &crtc->mode);
 
-	ret = exynos_plane_mode_set(plane, crtc, crtc->primary->fb, 0, 0, crtc_w, crtc_h,
-				    x, y, crtc_w, crtc_h);
-	if (ret)
-		return ret;
-
-	plane->crtc = crtc;
-	plane->fb = crtc->primary->fb;
-	drm_framebuffer_reference(plane->fb);
-
-	return 0;
+	return exynos_plane_mode_set(crtc->primary, crtc, fb, 0, 0,
+				     crtc_w, crtc_h, x, y, crtc_w, crtc_h);
 }
 
 static int exynos_drm_crtc_mode_set_commit(struct drm_crtc *crtc, int x, int y,
 					  struct drm_framebuffer *old_fb)
 {
 	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
-	struct drm_plane *plane = exynos_crtc->plane;
+	struct drm_framebuffer *fb = crtc->primary->fb;
 	unsigned int crtc_w;
 	unsigned int crtc_h;
 	int ret;
@@ -167,11 +156,11 @@ static int exynos_drm_crtc_mode_set_commit(struct drm_crtc *crtc, int x, int y,
 		return -EPERM;
 	}
 
-	crtc_w = crtc->primary->fb->width - x;
-	crtc_h = crtc->primary->fb->height - y;
+	crtc_w = fb->width - x;
+	crtc_h = fb->height - y;
 
-	ret = exynos_plane_mode_set(plane, crtc, crtc->primary->fb, 0, 0, crtc_w, crtc_h,
-				    x, y, crtc_w, crtc_h);
+	ret = exynos_plane_mode_set(crtc->primary, crtc, fb, 0, 0,
+				    crtc_w, crtc_h, x, y, crtc_w, crtc_h);
 	if (ret)
 		return ret;
 
@@ -304,8 +293,7 @@ static int exynos_drm_crtc_set_property(struct drm_crtc *crtc,
 			exynos_drm_crtc_commit(crtc);
 			break;
 		case CRTC_MODE_BLANK:
-			exynos_plane_dpms(exynos_crtc->plane,
-					  DRM_MODE_DPMS_OFF);
+			exynos_plane_dpms(crtc->primary, DRM_MODE_DPMS_OFF);
 			break;
 		default:
 			break;
@@ -351,8 +339,10 @@ static void exynos_drm_crtc_attach_mode_property(struct drm_crtc *crtc)
 int exynos_drm_crtc_create(struct exynos_drm_manager *manager)
 {
 	struct exynos_drm_crtc *exynos_crtc;
+	struct drm_plane *plane;
 	struct exynos_drm_private *private = manager->drm_dev->dev_private;
 	struct drm_crtc *crtc;
+	int ret;
 
 	exynos_crtc = kzalloc(sizeof(*exynos_crtc), GFP_KERNEL);
 	if (!exynos_crtc)
@@ -364,11 +354,11 @@ int exynos_drm_crtc_create(struct exynos_drm_manager *manager)
 	exynos_crtc->dpms = DRM_MODE_DPMS_OFF;
 	exynos_crtc->manager = manager;
 	exynos_crtc->pipe = manager->pipe;
-	exynos_crtc->plane = exynos_plane_init(manager->drm_dev,
-				1 << manager->pipe, true);
-	if (!exynos_crtc->plane) {
-		kfree(exynos_crtc);
-		return -ENOMEM;
+	plane = exynos_plane_init(manager->drm_dev, 1 << manager->pipe,
+				  DRM_PLANE_TYPE_PRIMARY);
+	if (IS_ERR(plane)) {
+		ret = PTR_ERR(plane);
+		goto err_plane;
 	}
 
 	manager->crtc = &exynos_crtc->drm_crtc;
@@ -376,12 +366,22 @@ int exynos_drm_crtc_create(struct exynos_drm_manager *manager)
 
 	private->crtc[manager->pipe] = crtc;
 
-	drm_crtc_init(manager->drm_dev, crtc, &exynos_crtc_funcs);
+	ret = drm_crtc_init_with_planes(manager->drm_dev, crtc, plane, NULL,
+					&exynos_crtc_funcs);
+	if (ret < 0)
+		goto err_crtc;
+
 	drm_crtc_helper_add(crtc, &exynos_crtc_helper_funcs);
 
 	exynos_drm_crtc_attach_mode_property(crtc);
 
 	return 0;
+
+err_crtc:
+	plane->funcs->destroy(plane);
+err_plane:
+	kfree(exynos_crtc);
+	return ret;
 }
 
 int exynos_drm_crtc_enable_vblank(struct drm_device *dev, int pipe)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
index fa08f05e3e34..96c87db388fb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
@@ -342,8 +342,12 @@ int exynos_dpi_remove(struct device *dev)
 	struct exynos_dpi *ctx = exynos_dpi_display.ctx;
 
 	exynos_dpi_dpms(&exynos_dpi_display, DRM_MODE_DPMS_OFF);
+
+	exynos_dpi_connector_destroy(&ctx->connector);
 	encoder->funcs->destroy(encoder);
-	drm_connector_cleanup(&ctx->connector);
+
+	if (ctx->panel)
+		drm_panel_detach(ctx->panel);
 
 	exynos_drm_component_del(dev, EXYNOS_DEVICE_TYPE_CONNECTOR);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 0d74e9b99c4e..443a2069858a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -15,7 +15,6 @@
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 
-#include <linux/anon_inodes.h>
 #include <linux/component.h>
 
 #include <drm/exynos_drm.h>
@@ -86,8 +85,9 @@ static int exynos_drm_load(struct drm_device *dev, unsigned long flags)
 		struct drm_plane *plane;
 		unsigned long possible_crtcs = (1 << MAX_CRTC) - 1;
 
-		plane = exynos_plane_init(dev, possible_crtcs, false);
-		if (!plane)
+		plane = exynos_plane_init(dev, possible_crtcs,
+					  DRM_PLANE_TYPE_OVERLAY);
+		if (IS_ERR(plane))
 			goto err_mode_config_cleanup;
 	}
 
@@ -116,6 +116,23 @@ static int exynos_drm_load(struct drm_device *dev, unsigned long flags)
 	/* force connectors detection */
 	drm_helper_hpd_irq_event(dev);
 
+	/*
+	 * enable drm irq mode.
+	 * - with irq_enabled = true, we can use the vblank feature.
+	 *
+	 * P.S. note that we wouldn't use drm irq handler but
+	 *	just specific driver own one instead because
+	 *	drm framework supports only one irq handler.
+	 */
+	dev->irq_enabled = true;
+
+	/*
+	 * with vblank_disable_allowed = true, vblank interrupt will be disabled
+	 * by drm timer once a current process gives up ownership of
+	 * vblank event.(after drm_vblank_put function is called)
+	 */
+	dev->vblank_disable_allowed = true;
+
 	return 0;
 
 err_unbind_all:
@@ -136,23 +153,19 @@ static int exynos_drm_unload(struct drm_device *dev)
 	exynos_drm_device_subdrv_remove(dev);
 
 	exynos_drm_fbdev_fini(dev);
-	drm_vblank_cleanup(dev);
 	drm_kms_helper_poll_fini(dev);
-	drm_mode_config_cleanup(dev);
 
+	component_unbind_all(dev->dev, dev);
+	drm_vblank_cleanup(dev);
+	drm_mode_config_cleanup(dev);
 	drm_release_iommu_mapping(dev);
-	kfree(dev->dev_private);
 
-	component_unbind_all(dev->dev, dev);
+	kfree(dev->dev_private);
 	dev->dev_private = NULL;
 
 	return 0;
 }
 
-static const struct file_operations exynos_drm_gem_fops = {
-	.mmap = exynos_drm_gem_mmap_buffer,
-};
-
 static int exynos_drm_suspend(struct drm_device *dev, pm_message_t state)
 {
 	struct drm_connector *connector;
@@ -191,7 +204,6 @@ static int exynos_drm_resume(struct drm_device *dev)
 static int exynos_drm_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv;
-	struct file *anon_filp;
 	int ret;
 
 	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
@@ -204,21 +216,8 @@ static int exynos_drm_open(struct drm_device *dev, struct drm_file *file)
 	if (ret)
 		goto err_file_priv_free;
 
-	anon_filp = anon_inode_getfile("exynos_gem", &exynos_drm_gem_fops,
-					NULL, 0);
-	if (IS_ERR(anon_filp)) {
-		ret = PTR_ERR(anon_filp);
-		goto err_subdrv_close;
-	}
-
-	anon_filp->f_mode = FMODE_READ | FMODE_WRITE;
-	file_priv->anon_filp = anon_filp;
-
 	return ret;
 
-err_subdrv_close:
-	exynos_drm_subdrv_close(dev, file);
-
 err_file_priv_free:
 	kfree(file_priv);
 	file->driver_priv = NULL;
@@ -234,7 +233,6 @@ static void exynos_drm_preclose(struct drm_device *dev,
 static void exynos_drm_postclose(struct drm_device *dev, struct drm_file *file)
 {
 	struct exynos_drm_private *private = dev->dev_private;
-	struct drm_exynos_file_private *file_priv;
 	struct drm_pending_vblank_event *v, *vt;
 	struct drm_pending_event *e, *et;
 	unsigned long flags;
@@ -260,10 +258,6 @@ static void exynos_drm_postclose(struct drm_device *dev, struct drm_file *file)
 	}
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 
-	file_priv = file->driver_priv;
-	if (file_priv->anon_filp)
-		fput(file_priv->anon_filp);
-
 	kfree(file->driver_priv);
 	file->driver_priv = NULL;
 }
@@ -282,11 +276,6 @@ static const struct vm_operations_struct exynos_drm_gem_vm_ops = {
 static const struct drm_ioctl_desc exynos_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_CREATE, exynos_drm_gem_create_ioctl,
 			DRM_UNLOCKED | DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_MAP_OFFSET,
-			exynos_drm_gem_map_offset_ioctl, DRM_UNLOCKED |
-			DRM_AUTH),
-	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_MMAP,
-			exynos_drm_gem_mmap_ioctl, DRM_UNLOCKED | DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(EXYNOS_GEM_GET,
 			exynos_drm_gem_get_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(EXYNOS_VIDI_CONNECTION,
@@ -330,6 +319,7 @@ static struct drm_driver exynos_drm_driver = {
 	.preclose		= exynos_drm_preclose,
 	.lastclose		= exynos_drm_lastclose,
 	.postclose		= exynos_drm_postclose,
+	.set_busid		= drm_platform_set_busid,
 	.get_vblank_counter	= drm_vblank_count,
 	.enable_vblank		= exynos_drm_crtc_enable_vblank,
 	.disable_vblank		= exynos_drm_crtc_disable_vblank,
@@ -485,21 +475,20 @@ void exynos_drm_component_del(struct device *dev,
 	mutex_unlock(&drm_component_lock);
 }
 
-static int compare_of(struct device *dev, void *data)
+static int compare_dev(struct device *dev, void *data)
 {
 	return dev == (struct device *)data;
 }
 
-static int exynos_drm_add_components(struct device *dev, struct master *m)
+static struct component_match *exynos_drm_match_add(struct device *dev)
 {
+	struct component_match *match = NULL;
 	struct component_dev *cdev;
 	unsigned int attach_cnt = 0;
 
 	mutex_lock(&drm_component_lock);
 
 	list_for_each_entry(cdev, &drm_component_list, list) {
-		int ret;
-
 		/*
 		 * Add components to master only in case that crtc and
 		 * encoder/connector device objects exist.
@@ -514,16 +503,10 @@ static int exynos_drm_add_components(struct device *dev, struct master *m)
 		/*
 		 * fimd and dpi modules have same device object so add
 		 * only crtc device object in this case.
-		 *
-		 * TODO. if dpi module follows driver-model driver then
-		 * below codes can be removed.
 		 */
 		if (cdev->crtc_dev == cdev->conn_dev) {
-			ret = component_master_add_child(m, compare_of,
-					cdev->crtc_dev);
-			if (ret < 0)
-				return ret;
-
+			component_match_add(dev, &match, compare_dev,
+						cdev->crtc_dev);
 			goto out_lock;
 		}
 
@@ -533,11 +516,8 @@ static int exynos_drm_add_components(struct device *dev, struct master *m)
 		 * connector/encoder need pipe number of crtc when they
 		 * are created.
 		 */
-		ret = component_master_add_child(m, compare_of, cdev->crtc_dev);
-		ret |= component_master_add_child(m, compare_of,
-							cdev->conn_dev);
-		if (ret < 0)
-			return ret;
+		component_match_add(dev, &match, compare_dev, cdev->crtc_dev);
+		component_match_add(dev, &match, compare_dev, cdev->conn_dev);
 
 out_lock:
 		mutex_lock(&drm_component_lock);
@@ -545,7 +525,7 @@ out_lock:
 
 	mutex_unlock(&drm_component_lock);
 
-	return attach_cnt ? 0 : -ENODEV;
+	return attach_cnt ? match : ERR_PTR(-EPROBE_DEFER);
 }
 
 static int exynos_drm_bind(struct device *dev)
@@ -559,13 +539,13 @@ static void exynos_drm_unbind(struct device *dev)
 }
 
 static const struct component_master_ops exynos_drm_ops = {
-	.add_components = exynos_drm_add_components,
 	.bind		= exynos_drm_bind,
 	.unbind		= exynos_drm_unbind,
 };
 
 static int exynos_drm_platform_probe(struct platform_device *pdev)
 {
+	struct component_match *match;
 	int ret;
 
 	pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
@@ -632,13 +612,23 @@ static int exynos_drm_platform_probe(struct platform_device *pdev)
 		goto err_unregister_ipp_drv;
 #endif
 
-	ret = component_master_add(&pdev->dev, &exynos_drm_ops);
+	match = exynos_drm_match_add(&pdev->dev);
+	if (IS_ERR(match)) {
+		ret = PTR_ERR(match);
+		goto err_unregister_resources;
+	}
+
+	ret = component_master_add_with_match(&pdev->dev, &exynos_drm_ops,
+						match);
 	if (ret < 0)
-		DRM_DEBUG_KMS("re-tried by last sub driver probed later.\n");
+		goto err_unregister_resources;
 
-	return 0;
+	return ret;
+
+err_unregister_resources:
 
 #ifdef CONFIG_DRM_EXYNOS_IPP
+	exynos_platform_device_ipp_unregister();
 err_unregister_ipp_drv:
 	platform_driver_unregister(&ipp_driver);
 err_unregister_gsc_drv:
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index 69a6fa397d75..d22e640f59a0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -240,7 +240,6 @@ struct exynos_drm_g2d_private {
 struct drm_exynos_file_private {
 	struct exynos_drm_g2d_private	*g2d_priv;
 	struct device			*ipp_dev;
-	struct file			*anon_filp;
 };
 
 /*
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 442aa2d00132..24741d8758e8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -114,6 +114,8 @@
 #define DSIM_SYNC_INFORM		(1 << 27)
 #define DSIM_EOT_DISABLE		(1 << 28)
 #define DSIM_MFLUSH_VS			(1 << 29)
+/* This flag is valid only for exynos3250/3472/4415/5260/5430 */
+#define DSIM_CLKLANE_STOP		(1 << 30)
 
 /* DSIM_ESCMODE */
 #define DSIM_TX_TRIGGER_RST		(1 << 4)
@@ -262,6 +264,7 @@ struct exynos_dsi_driver_data {
 	unsigned int plltmr_reg;
 
 	unsigned int has_freqband:1;
+	unsigned int has_clklane_stop:1;
 };
 
 struct exynos_dsi {
@@ -301,9 +304,16 @@ struct exynos_dsi {
 #define host_to_dsi(host) container_of(host, struct exynos_dsi, dsi_host)
 #define connector_to_dsi(c) container_of(c, struct exynos_dsi, connector)
 
+static struct exynos_dsi_driver_data exynos3_dsi_driver_data = {
+	.plltmr_reg = 0x50,
+	.has_freqband = 1,
+	.has_clklane_stop = 1,
+};
+
 static struct exynos_dsi_driver_data exynos4_dsi_driver_data = {
 	.plltmr_reg = 0x50,
 	.has_freqband = 1,
+	.has_clklane_stop = 1,
 };
 
 static struct exynos_dsi_driver_data exynos5_dsi_driver_data = {
@@ -311,6 +321,8 @@ static struct exynos_dsi_driver_data exynos5_dsi_driver_data = {
 };
 
 static struct of_device_id exynos_dsi_of_match[] = {
+	{ .compatible = "samsung,exynos3250-mipi-dsi",
+	  .data = &exynos3_dsi_driver_data },
 	{ .compatible = "samsung,exynos4210-mipi-dsi",
 	  .data = &exynos4_dsi_driver_data },
 	{ .compatible = "samsung,exynos5410-mipi-dsi",
@@ -421,7 +433,7 @@ static unsigned long exynos_dsi_set_pll(struct exynos_dsi *dsi,
 	if (!fout) {
 		dev_err(dsi->dev,
 			"failed to find PLL PMS for requested frequency\n");
-		return -EFAULT;
+		return 0;
 	}
 	dev_dbg(dsi->dev, "PLL freq %lu, (p %d, m %d, s %d)\n", fout, p, m, s);
 
@@ -453,7 +465,7 @@ static unsigned long exynos_dsi_set_pll(struct exynos_dsi *dsi,
 	do {
 		if (timeout-- == 0) {
 			dev_err(dsi->dev, "PLL failed to stabilize\n");
-			return -EFAULT;
+			return 0;
 		}
 		reg = readl(dsi->reg_base + DSIM_STATUS_REG);
 	} while ((reg & DSIM_PLL_STABLE) == 0);
@@ -569,6 +581,7 @@ static void exynos_dsi_disable_clock(struct exynos_dsi *dsi)
 
 static int exynos_dsi_init_link(struct exynos_dsi *dsi)
 {
+	struct exynos_dsi_driver_data *driver_data = dsi->driver_data;
 	int timeout;
 	u32 reg;
 	u32 lanes_mask;
@@ -650,6 +663,20 @@ static int exynos_dsi_init_link(struct exynos_dsi *dsi)
 	reg |= DSIM_LANE_EN(lanes_mask);
 	writel(reg, dsi->reg_base + DSIM_CONFIG_REG);
 
+	/*
+	 * Use non-continuous clock mode if the periparal wants and
+	 * host controller supports
+	 *
+	 * In non-continous clock mode, host controller will turn off
+	 * the HS clock between high-speed transmissions to reduce
+	 * power consumption.
+	 */
+	if (driver_data->has_clklane_stop &&
+			dsi->mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS) {
+		reg |= DSIM_CLKLANE_STOP;
+		writel(reg, dsi->reg_base + DSIM_CONFIG_REG);
+	}
+
 	/* Check clock and data lane state are stop state */
 	timeout = 100;
 	do {
@@ -1414,6 +1441,9 @@ exynos_dsi_detect(struct drm_connector *connector, bool force)
 
 static void exynos_dsi_connector_destroy(struct drm_connector *connector)
 {
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
+	connector->dev = NULL;
 }
 
 static struct drm_connector_funcs exynos_dsi_connector_funcs = {
@@ -1634,10 +1664,10 @@ static void exynos_dsi_unbind(struct device *dev, struct device *master,
 
 	exynos_dsi_dpms(&exynos_dsi_display, DRM_MODE_DPMS_OFF);
 
-	mipi_dsi_host_unregister(&dsi->dsi_host);
-
+	exynos_dsi_connector_destroy(&dsi->connector);
 	encoder->funcs->destroy(encoder);
-	drm_connector_cleanup(&dsi->connector);
+
+	mipi_dsi_host_unregister(&dsi->dsi_host);
 }
 
 static const struct component_ops exynos_dsi_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 65a22cad7b36..d346d1e6eda0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -165,6 +165,7 @@ exynos_drm_framebuffer_init(struct drm_device *dev,
 
 	ret = drm_framebuffer_init(dev, &exynos_fb->fb, &exynos_drm_fb_funcs);
 	if (ret) {
+		kfree(exynos_fb);
 		DRM_ERROR("failed to initialize framebuffer\n");
 		return ERR_PTR(ret);
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index 32e63f60e1d1..e12ea90c6237 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -123,6 +123,7 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper,
 
 	fbi->screen_base = buffer->kvaddr + offset;
 	fbi->screen_size = size;
+	fbi->fix.smem_len = size;
 
 	return 0;
 }
@@ -353,9 +354,6 @@ void exynos_drm_fbdev_fini(struct drm_device *dev)
 
 	fbdev = to_exynos_fbdev(private->fb_helper);
 
-	if (fbdev->exynos_gem_obj)
-		exynos_drm_gem_destroy(fbdev->exynos_gem_obj);
-
 	exynos_drm_fbdev_destroy(dev, private->fb_helper);
 	kfree(fbdev);
 	private->fb_helper = NULL;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index ec7cc9ea50df..68d38eb6774d 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -336,9 +336,6 @@ static bool fimc_check_ovf(struct fimc_context *ctx)
 		fimc_set_bits(ctx, EXYNOS_CIWDOFST,
 			EXYNOS_CIWDOFST_CLROVFIY | EXYNOS_CIWDOFST_CLROVFICB |
 			EXYNOS_CIWDOFST_CLROVFICR);
-		fimc_clear_bits(ctx, EXYNOS_CIWDOFST,
-			EXYNOS_CIWDOFST_CLROVFIY | EXYNOS_CIWDOFST_CLROVFICB |
-			EXYNOS_CIWDOFST_CLROVFICR);
 
 		dev_err(ippdrv->dev, "occurred overflow at %d, status 0x%x.\n",
 			ctx->id, status);
@@ -718,24 +715,24 @@ static int fimc_src_set_addr(struct device *dev,
 	case IPP_BUF_ENQUEUE:
 		config = &property->config[EXYNOS_DRM_OPS_SRC];
 		fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_Y],
-			EXYNOS_CIIYSA(buf_id));
+			EXYNOS_CIIYSA0);
 
 		if (config->fmt == DRM_FORMAT_YVU420) {
 			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CR],
-				EXYNOS_CIICBSA(buf_id));
+				EXYNOS_CIICBSA0);
 			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CB],
-				EXYNOS_CIICRSA(buf_id));
+				EXYNOS_CIICRSA0);
 		} else {
 			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CB],
-				EXYNOS_CIICBSA(buf_id));
+				EXYNOS_CIICBSA0);
 			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CR],
-				EXYNOS_CIICRSA(buf_id));
+				EXYNOS_CIICRSA0);
 		}
 		break;
 	case IPP_BUF_DEQUEUE:
-		fimc_write(ctx, 0x0, EXYNOS_CIIYSA(buf_id));
-		fimc_write(ctx, 0x0, EXYNOS_CIICBSA(buf_id));
-		fimc_write(ctx, 0x0, EXYNOS_CIICRSA(buf_id));
+		fimc_write(ctx, 0x0, EXYNOS_CIIYSA0);
+		fimc_write(ctx, 0x0, EXYNOS_CIICBSA0);
+		fimc_write(ctx, 0x0, EXYNOS_CIICRSA0);
 		break;
 	default:
 		/* bypass */
@@ -1122,67 +1119,34 @@ static int fimc_dst_set_size(struct device *dev, int swap,
 	return 0;
 }
 
-static int fimc_dst_get_buf_count(struct fimc_context *ctx)
-{
-	u32 cfg, buf_num;
-
-	cfg = fimc_read(ctx, EXYNOS_CIFCNTSEQ);
-
-	buf_num = hweight32(cfg);
-
-	DRM_DEBUG_KMS("buf_num[%d]\n", buf_num);
-
-	return buf_num;
-}
-
-static int fimc_dst_set_buf_seq(struct fimc_context *ctx, u32 buf_id,
+static void fimc_dst_set_buf_seq(struct fimc_context *ctx, u32 buf_id,
 		enum drm_exynos_ipp_buf_type buf_type)
 {
-	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	bool enable;
-	u32 cfg;
-	u32 mask = 0x00000001 << buf_id;
-	int ret = 0;
 	unsigned long flags;
+	u32 buf_num;
+	u32 cfg;
 
 	DRM_DEBUG_KMS("buf_id[%d]buf_type[%d]\n", buf_id, buf_type);
 
 	spin_lock_irqsave(&ctx->lock, flags);
 
-	/* mask register set */
 	cfg = fimc_read(ctx, EXYNOS_CIFCNTSEQ);
 
-	switch (buf_type) {
-	case IPP_BUF_ENQUEUE:
-		enable = true;
-		break;
-	case IPP_BUF_DEQUEUE:
-		enable = false;
-		break;
-	default:
-		dev_err(ippdrv->dev, "invalid buf ctrl parameter.\n");
-		ret =  -EINVAL;
-		goto err_unlock;
-	}
+	if (buf_type == IPP_BUF_ENQUEUE)
+		cfg |= (1 << buf_id);
+	else
+		cfg &= ~(1 << buf_id);
 
-	/* sequence id */
-	cfg &= ~mask;
-	cfg |= (enable << buf_id);
 	fimc_write(ctx, cfg, EXYNOS_CIFCNTSEQ);
 
-	/* interrupt enable */
-	if (buf_type == IPP_BUF_ENQUEUE &&
-	    fimc_dst_get_buf_count(ctx) >= FIMC_BUF_START)
-		fimc_mask_irq(ctx, true);
+	buf_num = hweight32(cfg);
 
-	/* interrupt disable */
-	if (buf_type == IPP_BUF_DEQUEUE &&
-	    fimc_dst_get_buf_count(ctx) <= FIMC_BUF_STOP)
+	if (buf_type == IPP_BUF_ENQUEUE && buf_num >= FIMC_BUF_START)
+		fimc_mask_irq(ctx, true);
+	else if (buf_type == IPP_BUF_DEQUEUE && buf_num <= FIMC_BUF_STOP)
 		fimc_mask_irq(ctx, false);
 
-err_unlock:
 	spin_unlock_irqrestore(&ctx->lock, flags);
-	return ret;
 }
 
 static int fimc_dst_set_addr(struct device *dev,
@@ -1240,7 +1204,9 @@ static int fimc_dst_set_addr(struct device *dev,
 		break;
 	}
 
-	return fimc_dst_set_buf_seq(ctx, buf_id, buf_type);
+	fimc_dst_set_buf_seq(ctx, buf_id, buf_type);
+
+	return 0;
 }
 
 static struct exynos_drm_ipp_ops fimc_dst_ops = {
@@ -1291,14 +1257,11 @@ static irqreturn_t fimc_irq_handler(int irq, void *dev_id)
 
 	DRM_DEBUG_KMS("buf_id[%d]\n", buf_id);
 
-	if (fimc_dst_set_buf_seq(ctx, buf_id, IPP_BUF_DEQUEUE) < 0) {
-		DRM_ERROR("failed to dequeue.\n");
-		return IRQ_HANDLED;
-	}
+	fimc_dst_set_buf_seq(ctx, buf_id, IPP_BUF_DEQUEUE);
 
 	event_work->ippdrv = ippdrv;
 	event_work->buf_id[EXYNOS_DRM_OPS_DST] = buf_id;
-	queue_work(ippdrv->event_workq, (struct work_struct *)event_work);
+	queue_work(ippdrv->event_workq, &event_work->work);
 
 	return IRQ_HANDLED;
 }
@@ -1590,11 +1553,8 @@ static int fimc_ippdrv_start(struct device *dev, enum drm_exynos_ipp_cmd cmd)
 
 	fimc_clear_bits(ctx, EXYNOS_CIOCTRL, EXYNOS_CIOCTRL_WEAVE_MASK);
 
-	if (cmd == IPP_CMD_M2M) {
-		fimc_set_bits(ctx, EXYNOS_MSCTRL, EXYNOS_MSCTRL_ENVID);
-
+	if (cmd == IPP_CMD_M2M)
 		fimc_set_bits(ctx, EXYNOS_MSCTRL, EXYNOS_MSCTRL_ENVID);
-	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 5d09e33fef87..085b066a9993 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -104,6 +104,14 @@ static struct fimd_driver_data s3c64xx_fimd_driver_data = {
 	.has_limited_fmt = 1,
 };
 
+static struct fimd_driver_data exynos3_fimd_driver_data = {
+	.timing_base = 0x20000,
+	.lcdblk_offset = 0x210,
+	.lcdblk_bypass_shift = 1,
+	.has_shadowcon = 1,
+	.has_vidoutcon = 1,
+};
+
 static struct fimd_driver_data exynos4_fimd_driver_data = {
 	.timing_base = 0x0,
 	.lcdblk_offset = 0x210,
@@ -168,6 +176,8 @@ struct fimd_context {
 static const struct of_device_id fimd_driver_dt_match[] = {
 	{ .compatible = "samsung,s3c6400-fimd",
 	  .data = &s3c64xx_fimd_driver_data },
+	{ .compatible = "samsung,exynos3250-fimd",
+	  .data = &exynos3_fimd_driver_data },
 	{ .compatible = "samsung,exynos4210-fimd",
 	  .data = &exynos4_fimd_driver_data },
 	{ .compatible = "samsung,exynos5250-fimd",
@@ -204,7 +214,6 @@ static void fimd_wait_for_vblank(struct exynos_drm_manager *mgr)
 		DRM_DEBUG_KMS("vblank wait timed out.\n");
 }
 
-
 static void fimd_clear_channel(struct exynos_drm_manager *mgr)
 {
 	struct fimd_context *ctx = mgr->ctx;
@@ -214,17 +223,31 @@ static void fimd_clear_channel(struct exynos_drm_manager *mgr)
 
 	/* Check if any channel is enabled. */
 	for (win = 0; win < WINDOWS_NR; win++) {
-		u32 val = readl(ctx->regs + SHADOWCON);
-		if (val & SHADOWCON_CHx_ENABLE(win)) {
-			val &= ~SHADOWCON_CHx_ENABLE(win);
-			writel(val, ctx->regs + SHADOWCON);
+		u32 val = readl(ctx->regs + WINCON(win));
+
+		if (val & WINCONx_ENWIN) {
+			/* wincon */
+			val &= ~WINCONx_ENWIN;
+			writel(val, ctx->regs + WINCON(win));
+
+			/* unprotect windows */
+			if (ctx->driver_data->has_shadowcon) {
+				val = readl(ctx->regs + SHADOWCON);
+				val &= ~SHADOWCON_CHx_ENABLE(win);
+				writel(val, ctx->regs + SHADOWCON);
+			}
 			ch_enabled = 1;
 		}
 	}
 
 	/* Wait for vsync, as disable channel takes effect at next vsync */
-	if (ch_enabled)
+	if (ch_enabled) {
+		unsigned int state = ctx->suspended;
+
+		ctx->suspended = 0;
 		fimd_wait_for_vblank(mgr);
+		ctx->suspended = state;
+	}
 }
 
 static int fimd_mgr_initialize(struct exynos_drm_manager *mgr,
@@ -237,23 +260,6 @@ static int fimd_mgr_initialize(struct exynos_drm_manager *mgr,
 	mgr->drm_dev = ctx->drm_dev = drm_dev;
 	mgr->pipe = ctx->pipe = priv->pipe++;
 
-	/*
-	 * enable drm irq mode.
-	 * - with irq_enabled = true, we can use the vblank feature.
-	 *
-	 * P.S. note that we wouldn't use drm irq handler but
-	 *	just specific driver own one instead because
-	 *	drm framework supports only one irq handler.
-	 */
-	drm_dev->irq_enabled = true;
-
-	/*
-	 * with vblank_disable_allowed = true, vblank interrupt will be disabled
-	 * by drm timer once a current process gives up ownership of
-	 * vblank event.(after drm_vblank_put function is called)
-	 */
-	drm_dev->vblank_disable_allowed = true;
-
 	/* attach this sub driver to iommu mapping if supported. */
 	if (is_drm_iommu_supported(ctx->drm_dev)) {
 		/*
@@ -1051,7 +1057,6 @@ static void fimd_unbind(struct device *dev, struct device *master,
 {
 	struct exynos_drm_manager *mgr = dev_get_drvdata(dev);
 	struct fimd_context *ctx = fimd_manager.ctx;
-	struct drm_crtc *crtc = mgr->crtc;
 
 	fimd_dpms(mgr, DRM_MODE_DPMS_OFF);
 
@@ -1059,8 +1064,6 @@ static void fimd_unbind(struct device *dev, struct device *master,
 		exynos_dpi_remove(dev);
 
 	fimd_mgr_remove(mgr);
-
-	crtc->funcs->destroy(crtc);
 }
 
 static const struct component_ops fimd_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 15db80138382..0d5b9698d384 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -318,40 +318,16 @@ void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
 	drm_gem_object_unreference_unlocked(obj);
 }
 
-int exynos_drm_gem_map_offset_ioctl(struct drm_device *dev, void *data,
-				    struct drm_file *file_priv)
-{
-	struct drm_exynos_gem_map_off *args = data;
-
-	DRM_DEBUG_KMS("handle = 0x%x, offset = 0x%lx\n",
-			args->handle, (unsigned long)args->offset);
-
-	if (!(dev->driver->driver_features & DRIVER_GEM)) {
-		DRM_ERROR("does not support GEM.\n");
-		return -ENODEV;
-	}
-
-	return exynos_drm_gem_dumb_map_offset(file_priv, dev, args->handle,
-			&args->offset);
-}
-
-int exynos_drm_gem_mmap_buffer(struct file *filp,
+int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem_obj *exynos_gem_obj,
 				      struct vm_area_struct *vma)
 {
-	struct drm_gem_object *obj = filp->private_data;
-	struct exynos_drm_gem_obj *exynos_gem_obj = to_exynos_gem_obj(obj);
-	struct drm_device *drm_dev = obj->dev;
+	struct drm_device *drm_dev = exynos_gem_obj->base.dev;
 	struct exynos_drm_gem_buf *buffer;
 	unsigned long vm_size;
 	int ret;
 
-	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
-
-	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
-	vma->vm_private_data = obj;
-	vma->vm_ops = drm_dev->driver->gem_vm_ops;
-
-	update_vm_cache_attr(exynos_gem_obj, vma);
+	vma->vm_flags &= ~VM_PFNMAP;
+	vma->vm_pgoff = 0;
 
 	vm_size = vma->vm_end - vma->vm_start;
 
@@ -373,60 +349,6 @@ int exynos_drm_gem_mmap_buffer(struct file *filp,
 		return ret;
 	}
 
-	/*
-	 * take a reference to this mapping of the object. And this reference
-	 * is unreferenced by the corresponding vm_close call.
-	 */
-	drm_gem_object_reference(obj);
-
-	drm_vm_open_locked(drm_dev, vma);
-
-	return 0;
-}
-
-int exynos_drm_gem_mmap_ioctl(struct drm_device *dev, void *data,
-			      struct drm_file *file_priv)
-{
-	struct drm_exynos_file_private *exynos_file_priv;
-	struct drm_exynos_gem_mmap *args = data;
-	struct drm_gem_object *obj;
-	struct file *anon_filp;
-	unsigned long addr;
-
-	if (!(dev->driver->driver_features & DRIVER_GEM)) {
-		DRM_ERROR("does not support GEM.\n");
-		return -ENODEV;
-	}
-
-	mutex_lock(&dev->struct_mutex);
-
-	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
-	if (!obj) {
-		DRM_ERROR("failed to lookup gem object.\n");
-		mutex_unlock(&dev->struct_mutex);
-		return -EINVAL;
-	}
-
-	exynos_file_priv = file_priv->driver_priv;
-	anon_filp = exynos_file_priv->anon_filp;
-	anon_filp->private_data = obj;
-
-	addr = vm_mmap(anon_filp, 0, args->size, PROT_READ | PROT_WRITE,
-			MAP_SHARED, 0);
-
-	drm_gem_object_unreference(obj);
-
-	if (IS_ERR_VALUE(addr)) {
-		mutex_unlock(&dev->struct_mutex);
-		return (int)addr;
-	}
-
-	mutex_unlock(&dev->struct_mutex);
-
-	args->mapped = addr;
-
-	DRM_DEBUG_KMS("mapped = 0x%lx\n", (unsigned long)args->mapped);
-
 	return 0;
 }
 
@@ -710,16 +632,20 @@ int exynos_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	exynos_gem_obj = to_exynos_gem_obj(obj);
 
 	ret = check_gem_flags(exynos_gem_obj->flags);
-	if (ret) {
-		drm_gem_vm_close(vma);
-		drm_gem_free_mmap_offset(obj);
-		return ret;
-	}
-
-	vma->vm_flags &= ~VM_PFNMAP;
-	vma->vm_flags |= VM_MIXEDMAP;
+	if (ret)
+		goto err_close_vm;
 
 	update_vm_cache_attr(exynos_gem_obj, vma);
 
+	ret = exynos_drm_gem_mmap_buffer(exynos_gem_obj, vma);
+	if (ret)
+		goto err_close_vm;
+
+	return ret;
+
+err_close_vm:
+	drm_gem_vm_close(vma);
+	drm_gem_free_mmap_offset(obj);
+
 	return ret;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 1592c0ba7de8..ec58fe9c40df 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -12,6 +12,8 @@
 #ifndef _EXYNOS_DRM_GEM_H_
 #define _EXYNOS_DRM_GEM_H_
 
+#include <drm/drm_gem.h>
+
 #define to_exynos_gem_obj(x)	container_of(x,\
 			struct exynos_drm_gem_obj, base)
 
@@ -111,20 +113,6 @@ void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
 					unsigned int gem_handle,
 					struct drm_file *filp);
 
-/* get buffer offset to map to user space. */
-int exynos_drm_gem_map_offset_ioctl(struct drm_device *dev, void *data,
-				    struct drm_file *file_priv);
-
-/*
- * mmap the physically continuous memory that a gem object contains
- * to user space.
- */
-int exynos_drm_gem_mmap_ioctl(struct drm_device *dev, void *data,
-			      struct drm_file *file_priv);
-
-int exynos_drm_gem_mmap_buffer(struct file *filp,
-				      struct vm_area_struct *vma);
-
 /* map user space allocated by malloc to pages. */
 int exynos_drm_gem_userptr_ioctl(struct drm_device *dev, void *data,
 				      struct drm_file *file_priv);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 9e3ff1672965..c6a013fc321c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -1326,8 +1326,7 @@ static irqreturn_t gsc_irq_handler(int irq, void *dev_id)
 			buf_id[EXYNOS_DRM_OPS_SRC];
 		event_work->buf_id[EXYNOS_DRM_OPS_DST] =
 			buf_id[EXYNOS_DRM_OPS_DST];
-		queue_work(ippdrv->event_workq,
-			(struct work_struct *)event_work);
+		queue_work(ippdrv->event_workq, &event_work->work);
 	}
 
 	return IRQ_HANDLED;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index c411399070d6..00d74b18f7cb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -75,7 +75,6 @@ struct drm_exynos_ipp_mem_node {
 	u32	prop_id;
 	u32	buf_id;
 	struct drm_exynos_ipp_buf_info	buf_info;
-	struct drm_file		*filp;
 };
 
 /*
@@ -319,44 +318,6 @@ static void ipp_print_property(struct drm_exynos_ipp_property *property,
 		sz->hsize, sz->vsize, config->flip, config->degree);
 }
 
-static int ipp_find_and_set_property(struct drm_exynos_ipp_property *property)
-{
-	struct exynos_drm_ippdrv *ippdrv;
-	struct drm_exynos_ipp_cmd_node *c_node;
-	u32 prop_id = property->prop_id;
-
-	DRM_DEBUG_KMS("prop_id[%d]\n", prop_id);
-
-	ippdrv = ipp_find_drv_by_handle(prop_id);
-	if (IS_ERR(ippdrv)) {
-		DRM_ERROR("failed to get ipp driver.\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * Find command node using command list in ippdrv.
-	 * when we find this command no using prop_id.
-	 * return property information set in this command node.
-	 */
-	mutex_lock(&ippdrv->cmd_lock);
-	list_for_each_entry(c_node, &ippdrv->cmd_list, list) {
-		if ((c_node->property.prop_id == prop_id) &&
-		    (c_node->state == IPP_STATE_STOP)) {
-			mutex_unlock(&ippdrv->cmd_lock);
-			DRM_DEBUG_KMS("found cmd[%d]ippdrv[0x%x]\n",
-				property->cmd, (int)ippdrv);
-
-			c_node->property = *property;
-			return 0;
-		}
-	}
-	mutex_unlock(&ippdrv->cmd_lock);
-
-	DRM_ERROR("failed to search property.\n");
-
-	return -EINVAL;
-}
-
 static struct drm_exynos_ipp_cmd_work *ipp_create_cmd_work(void)
 {
 	struct drm_exynos_ipp_cmd_work *cmd_work;
@@ -392,6 +353,7 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
 	struct drm_exynos_ipp_property *property = data;
 	struct exynos_drm_ippdrv *ippdrv;
 	struct drm_exynos_ipp_cmd_node *c_node;
+	u32 prop_id;
 	int ret, i;
 
 	if (!ctx) {
@@ -404,6 +366,8 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
 		return -EINVAL;
 	}
 
+	prop_id = property->prop_id;
+
 	/*
 	 * This is log print for user application property.
 	 * user application set various property.
@@ -412,14 +376,24 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
 		ipp_print_property(property, i);
 
 	/*
-	 * set property ioctl generated new prop_id.
-	 * but in this case already asigned prop_id using old set property.
-	 * e.g PAUSE state. this case supports find current prop_id and use it
-	 * instead of allocation.
+	 * In case prop_id is not zero try to set existing property.
 	 */
-	if (property->prop_id) {
-		DRM_DEBUG_KMS("prop_id[%d]\n", property->prop_id);
-		return ipp_find_and_set_property(property);
+	if (prop_id) {
+		c_node = ipp_find_obj(&ctx->prop_idr, &ctx->prop_lock, prop_id);
+
+		if (!c_node || c_node->filp != file) {
+			DRM_DEBUG_KMS("prop_id[%d] not found\n", prop_id);
+			return -EINVAL;
+		}
+
+		if (c_node->state != IPP_STATE_STOP) {
+			DRM_DEBUG_KMS("prop_id[%d] not stopped\n", prop_id);
+			return -EINVAL;
+		}
+
+		c_node->property = *property;
+
+		return 0;
 	}
 
 	/* find ipp driver using ipp id */
@@ -445,9 +419,9 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
 		property->prop_id, property->cmd, (int)ippdrv);
 
 	/* stored property information and ippdrv in private data */
-	c_node->dev = dev;
 	c_node->property = *property;
 	c_node->state = IPP_STATE_IDLE;
+	c_node->filp = file;
 
 	c_node->start_work = ipp_create_cmd_work();
 	if (IS_ERR(c_node->start_work)) {
@@ -499,105 +473,37 @@ err_clear:
 	return ret;
 }
 
-static void ipp_clean_cmd_node(struct ipp_context *ctx,
-				struct drm_exynos_ipp_cmd_node *c_node)
-{
-	/* delete list */
-	list_del(&c_node->list);
-
-	ipp_remove_id(&ctx->prop_idr, &ctx->prop_lock,
-			c_node->property.prop_id);
-
-	/* destroy mutex */
-	mutex_destroy(&c_node->lock);
-	mutex_destroy(&c_node->mem_lock);
-	mutex_destroy(&c_node->event_lock);
-
-	/* free command node */
-	kfree(c_node->start_work);
-	kfree(c_node->stop_work);
-	kfree(c_node->event_work);
-	kfree(c_node);
-}
-
-static bool ipp_check_mem_list(struct drm_exynos_ipp_cmd_node *c_node)
-{
-	switch (c_node->property.cmd) {
-	case IPP_CMD_WB:
-		return !list_empty(&c_node->mem_list[EXYNOS_DRM_OPS_DST]);
-	case IPP_CMD_OUTPUT:
-		return !list_empty(&c_node->mem_list[EXYNOS_DRM_OPS_SRC]);
-	case IPP_CMD_M2M:
-	default:
-		return !list_empty(&c_node->mem_list[EXYNOS_DRM_OPS_SRC]) &&
-		       !list_empty(&c_node->mem_list[EXYNOS_DRM_OPS_DST]);
-	}
-}
-
-static struct drm_exynos_ipp_mem_node
-		*ipp_find_mem_node(struct drm_exynos_ipp_cmd_node *c_node,
-		struct drm_exynos_ipp_queue_buf *qbuf)
-{
-	struct drm_exynos_ipp_mem_node *m_node;
-	struct list_head *head;
-	int count = 0;
-
-	DRM_DEBUG_KMS("buf_id[%d]\n", qbuf->buf_id);
-
-	/* source/destination memory list */
-	head = &c_node->mem_list[qbuf->ops_id];
-
-	/* find memory node from memory list */
-	list_for_each_entry(m_node, head, list) {
-		DRM_DEBUG_KMS("count[%d]m_node[0x%x]\n", count++, (int)m_node);
-
-		/* compare buffer id */
-		if (m_node->buf_id == qbuf->buf_id)
-			return m_node;
-	}
-
-	return NULL;
-}
-
-static int ipp_set_mem_node(struct exynos_drm_ippdrv *ippdrv,
+static int ipp_put_mem_node(struct drm_device *drm_dev,
 		struct drm_exynos_ipp_cmd_node *c_node,
 		struct drm_exynos_ipp_mem_node *m_node)
 {
-	struct exynos_drm_ipp_ops *ops = NULL;
-	int ret = 0;
+	int i;
 
 	DRM_DEBUG_KMS("node[0x%x]\n", (int)m_node);
 
 	if (!m_node) {
-		DRM_ERROR("invalid queue node.\n");
+		DRM_ERROR("invalid dequeue node.\n");
 		return -EFAULT;
 	}
 
 	DRM_DEBUG_KMS("ops_id[%d]\n", m_node->ops_id);
 
-	/* get operations callback */
-	ops = ippdrv->ops[m_node->ops_id];
-	if (!ops) {
-		DRM_ERROR("not support ops.\n");
-		return -EFAULT;
+	/* put gem buffer */
+	for_each_ipp_planar(i) {
+		unsigned long handle = m_node->buf_info.handles[i];
+		if (handle)
+			exynos_drm_gem_put_dma_addr(drm_dev, handle,
+							c_node->filp);
 	}
 
-	/* set address and enable irq */
-	if (ops->set_addr) {
-		ret = ops->set_addr(ippdrv->dev, &m_node->buf_info,
-			m_node->buf_id, IPP_BUF_ENQUEUE);
-		if (ret) {
-			DRM_ERROR("failed to set addr.\n");
-			return ret;
-		}
-	}
+	list_del(&m_node->list);
+	kfree(m_node);
 
-	return ret;
+	return 0;
 }
 
 static struct drm_exynos_ipp_mem_node
 		*ipp_get_mem_node(struct drm_device *drm_dev,
-		struct drm_file *file,
 		struct drm_exynos_ipp_cmd_node *c_node,
 		struct drm_exynos_ipp_queue_buf *qbuf)
 {
@@ -615,6 +521,7 @@ static struct drm_exynos_ipp_mem_node
 	m_node->ops_id = qbuf->ops_id;
 	m_node->prop_id = qbuf->prop_id;
 	m_node->buf_id = qbuf->buf_id;
+	INIT_LIST_HEAD(&m_node->list);
 
 	DRM_DEBUG_KMS("m_node[0x%x]ops_id[%d]\n", (int)m_node, qbuf->ops_id);
 	DRM_DEBUG_KMS("prop_id[%d]buf_id[%d]\n", qbuf->prop_id, m_node->buf_id);
@@ -627,10 +534,11 @@ static struct drm_exynos_ipp_mem_node
 			dma_addr_t *addr;
 
 			addr = exynos_drm_gem_get_dma_addr(drm_dev,
-					qbuf->handle[i], file);
+					qbuf->handle[i], c_node->filp);
 			if (IS_ERR(addr)) {
 				DRM_ERROR("failed to get addr.\n");
-				goto err_clear;
+				ipp_put_mem_node(drm_dev, c_node, m_node);
+				return ERR_PTR(-EFAULT);
 			}
 
 			buf_info->handles[i] = qbuf->handle[i];
@@ -640,46 +548,30 @@ static struct drm_exynos_ipp_mem_node
 		}
 	}
 
-	m_node->filp = file;
 	mutex_lock(&c_node->mem_lock);
 	list_add_tail(&m_node->list, &c_node->mem_list[qbuf->ops_id]);
 	mutex_unlock(&c_node->mem_lock);
 
 	return m_node;
-
-err_clear:
-	kfree(m_node);
-	return ERR_PTR(-EFAULT);
 }
 
-static int ipp_put_mem_node(struct drm_device *drm_dev,
-		struct drm_exynos_ipp_cmd_node *c_node,
-		struct drm_exynos_ipp_mem_node *m_node)
+static void ipp_clean_mem_nodes(struct drm_device *drm_dev,
+			       struct drm_exynos_ipp_cmd_node *c_node, int ops)
 {
-	int i;
-
-	DRM_DEBUG_KMS("node[0x%x]\n", (int)m_node);
+	struct drm_exynos_ipp_mem_node *m_node, *tm_node;
+	struct list_head *head = &c_node->mem_list[ops];
 
-	if (!m_node) {
-		DRM_ERROR("invalid dequeue node.\n");
-		return -EFAULT;
-	}
+	mutex_lock(&c_node->mem_lock);
 
-	DRM_DEBUG_KMS("ops_id[%d]\n", m_node->ops_id);
+	list_for_each_entry_safe(m_node, tm_node, head, list) {
+		int ret;
 
-	/* put gem buffer */
-	for_each_ipp_planar(i) {
-		unsigned long handle = m_node->buf_info.handles[i];
-		if (handle)
-			exynos_drm_gem_put_dma_addr(drm_dev, handle,
-							m_node->filp);
+		ret = ipp_put_mem_node(drm_dev, c_node, m_node);
+		if (ret)
+			DRM_ERROR("failed to put m_node.\n");
 	}
 
-	/* delete list in queue */
-	list_del(&m_node->list);
-	kfree(m_node);
-
-	return 0;
+	mutex_unlock(&c_node->mem_lock);
 }
 
 static void ipp_free_event(struct drm_pending_event *event)
@@ -688,7 +580,6 @@ static void ipp_free_event(struct drm_pending_event *event)
 }
 
 static int ipp_get_event(struct drm_device *drm_dev,
-		struct drm_file *file,
 		struct drm_exynos_ipp_cmd_node *c_node,
 		struct drm_exynos_ipp_queue_buf *qbuf)
 {
@@ -700,7 +591,7 @@ static int ipp_get_event(struct drm_device *drm_dev,
 	e = kzalloc(sizeof(*e), GFP_KERNEL);
 	if (!e) {
 		spin_lock_irqsave(&drm_dev->event_lock, flags);
-		file->event_space += sizeof(e->event);
+		c_node->filp->event_space += sizeof(e->event);
 		spin_unlock_irqrestore(&drm_dev->event_lock, flags);
 		return -ENOMEM;
 	}
@@ -712,7 +603,7 @@ static int ipp_get_event(struct drm_device *drm_dev,
 	e->event.prop_id = qbuf->prop_id;
 	e->event.buf_id[EXYNOS_DRM_OPS_DST] = qbuf->buf_id;
 	e->base.event = &e->event.base;
-	e->base.file_priv = file;
+	e->base.file_priv = c_node->filp;
 	e->base.destroy = ipp_free_event;
 	mutex_lock(&c_node->event_lock);
 	list_add_tail(&e->base.link, &c_node->event_list);
@@ -757,6 +648,115 @@ out_unlock:
 	return;
 }
 
+static void ipp_clean_cmd_node(struct ipp_context *ctx,
+				struct drm_exynos_ipp_cmd_node *c_node)
+{
+	int i;
+
+	/* cancel works */
+	cancel_work_sync(&c_node->start_work->work);
+	cancel_work_sync(&c_node->stop_work->work);
+	cancel_work_sync(&c_node->event_work->work);
+
+	/* put event */
+	ipp_put_event(c_node, NULL);
+
+	for_each_ipp_ops(i)
+		ipp_clean_mem_nodes(ctx->subdrv.drm_dev, c_node, i);
+
+	/* delete list */
+	list_del(&c_node->list);
+
+	ipp_remove_id(&ctx->prop_idr, &ctx->prop_lock,
+			c_node->property.prop_id);
+
+	/* destroy mutex */
+	mutex_destroy(&c_node->lock);
+	mutex_destroy(&c_node->mem_lock);
+	mutex_destroy(&c_node->event_lock);
+
+	/* free command node */
+	kfree(c_node->start_work);
+	kfree(c_node->stop_work);
+	kfree(c_node->event_work);
+	kfree(c_node);
+}
+
+static bool ipp_check_mem_list(struct drm_exynos_ipp_cmd_node *c_node)
+{
+	switch (c_node->property.cmd) {
+	case IPP_CMD_WB:
+		return !list_empty(&c_node->mem_list[EXYNOS_DRM_OPS_DST]);
+	case IPP_CMD_OUTPUT:
+		return !list_empty(&c_node->mem_list[EXYNOS_DRM_OPS_SRC]);
+	case IPP_CMD_M2M:
+	default:
+		return !list_empty(&c_node->mem_list[EXYNOS_DRM_OPS_SRC]) &&
+		       !list_empty(&c_node->mem_list[EXYNOS_DRM_OPS_DST]);
+	}
+}
+
+static struct drm_exynos_ipp_mem_node
+		*ipp_find_mem_node(struct drm_exynos_ipp_cmd_node *c_node,
+		struct drm_exynos_ipp_queue_buf *qbuf)
+{
+	struct drm_exynos_ipp_mem_node *m_node;
+	struct list_head *head;
+	int count = 0;
+
+	DRM_DEBUG_KMS("buf_id[%d]\n", qbuf->buf_id);
+
+	/* source/destination memory list */
+	head = &c_node->mem_list[qbuf->ops_id];
+
+	/* find memory node from memory list */
+	list_for_each_entry(m_node, head, list) {
+		DRM_DEBUG_KMS("count[%d]m_node[0x%x]\n", count++, (int)m_node);
+
+		/* compare buffer id */
+		if (m_node->buf_id == qbuf->buf_id)
+			return m_node;
+	}
+
+	return NULL;
+}
+
+static int ipp_set_mem_node(struct exynos_drm_ippdrv *ippdrv,
+		struct drm_exynos_ipp_cmd_node *c_node,
+		struct drm_exynos_ipp_mem_node *m_node)
+{
+	struct exynos_drm_ipp_ops *ops = NULL;
+	int ret = 0;
+
+	DRM_DEBUG_KMS("node[0x%x]\n", (int)m_node);
+
+	if (!m_node) {
+		DRM_ERROR("invalid queue node.\n");
+		return -EFAULT;
+	}
+
+	DRM_DEBUG_KMS("ops_id[%d]\n", m_node->ops_id);
+
+	/* get operations callback */
+	ops = ippdrv->ops[m_node->ops_id];
+	if (!ops) {
+		DRM_ERROR("not support ops.\n");
+		return -EFAULT;
+	}
+
+	/* set address and enable irq */
+	if (ops->set_addr) {
+		ret = ops->set_addr(ippdrv->dev, &m_node->buf_info,
+			m_node->buf_id, IPP_BUF_ENQUEUE);
+		if (ret) {
+			DRM_ERROR("failed to set addr.\n");
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
 static void ipp_handle_cmd_work(struct device *dev,
 		struct exynos_drm_ippdrv *ippdrv,
 		struct drm_exynos_ipp_cmd_work *cmd_work,
@@ -766,7 +766,7 @@ static void ipp_handle_cmd_work(struct device *dev,
 
 	cmd_work->ippdrv = ippdrv;
 	cmd_work->c_node = c_node;
-	queue_work(ctx->cmd_workq, (struct work_struct *)cmd_work);
+	queue_work(ctx->cmd_workq, &cmd_work->work);
 }
 
 static int ipp_queue_buf_with_run(struct device *dev,
@@ -872,7 +872,7 @@ int exynos_drm_ipp_queue_buf(struct drm_device *drm_dev, void *data,
 	/* find command node */
 	c_node = ipp_find_obj(&ctx->prop_idr, &ctx->prop_lock,
 		qbuf->prop_id);
-	if (!c_node) {
+	if (!c_node || c_node->filp != file) {
 		DRM_ERROR("failed to get command node.\n");
 		return -ENODEV;
 	}
@@ -881,7 +881,7 @@ int exynos_drm_ipp_queue_buf(struct drm_device *drm_dev, void *data,
 	switch (qbuf->buf_type) {
 	case IPP_BUF_ENQUEUE:
 		/* get memory node */
-		m_node = ipp_get_mem_node(drm_dev, file, c_node, qbuf);
+		m_node = ipp_get_mem_node(drm_dev, c_node, qbuf);
 		if (IS_ERR(m_node)) {
 			DRM_ERROR("failed to get m_node.\n");
 			return PTR_ERR(m_node);
@@ -894,7 +894,7 @@ int exynos_drm_ipp_queue_buf(struct drm_device *drm_dev, void *data,
 		 */
 		if (qbuf->ops_id == EXYNOS_DRM_OPS_DST) {
 			/* get event for destination buffer */
-			ret = ipp_get_event(drm_dev, file, c_node, qbuf);
+			ret = ipp_get_event(drm_dev, c_node, qbuf);
 			if (ret) {
 				DRM_ERROR("failed to get event.\n");
 				goto err_clean_node;
@@ -1007,7 +1007,7 @@ int exynos_drm_ipp_cmd_ctrl(struct drm_device *drm_dev, void *data,
 
 	c_node = ipp_find_obj(&ctx->prop_idr, &ctx->prop_lock,
 		cmd_ctrl->prop_id);
-	if (!c_node) {
+	if (!c_node || c_node->filp != file) {
 		DRM_ERROR("invalid command node list.\n");
 		return -ENODEV;
 	}
@@ -1257,80 +1257,39 @@ static int ipp_stop_property(struct drm_device *drm_dev,
 		struct exynos_drm_ippdrv *ippdrv,
 		struct drm_exynos_ipp_cmd_node *c_node)
 {
-	struct drm_exynos_ipp_mem_node *m_node, *tm_node;
 	struct drm_exynos_ipp_property *property = &c_node->property;
-	struct list_head *head;
-	int ret = 0, i;
+	int i;
 
 	DRM_DEBUG_KMS("prop_id[%d]\n", property->prop_id);
 
-	/* put event */
-	ipp_put_event(c_node, NULL);
-
-	mutex_lock(&c_node->mem_lock);
+	/* stop operations */
+	if (ippdrv->stop)
+		ippdrv->stop(ippdrv->dev, property->cmd);
 
 	/* check command */
 	switch (property->cmd) {
 	case IPP_CMD_M2M:
-		for_each_ipp_ops(i) {
-			/* source/destination memory list */
-			head = &c_node->mem_list[i];
-
-			list_for_each_entry_safe(m_node, tm_node,
-				head, list) {
-				ret = ipp_put_mem_node(drm_dev, c_node,
-					m_node);
-				if (ret) {
-					DRM_ERROR("failed to put m_node.\n");
-					goto err_clear;
-				}
-			}
-		}
+		for_each_ipp_ops(i)
+			ipp_clean_mem_nodes(drm_dev, c_node, i);
 		break;
 	case IPP_CMD_WB:
-		/* destination memory list */
-		head = &c_node->mem_list[EXYNOS_DRM_OPS_DST];
-
-		list_for_each_entry_safe(m_node, tm_node, head, list) {
-			ret = ipp_put_mem_node(drm_dev, c_node, m_node);
-			if (ret) {
-				DRM_ERROR("failed to put m_node.\n");
-				goto err_clear;
-			}
-		}
+		ipp_clean_mem_nodes(drm_dev, c_node, EXYNOS_DRM_OPS_DST);
 		break;
 	case IPP_CMD_OUTPUT:
-		/* source memory list */
-		head = &c_node->mem_list[EXYNOS_DRM_OPS_SRC];
-
-		list_for_each_entry_safe(m_node, tm_node, head, list) {
-			ret = ipp_put_mem_node(drm_dev, c_node, m_node);
-			if (ret) {
-				DRM_ERROR("failed to put m_node.\n");
-				goto err_clear;
-			}
-		}
+		ipp_clean_mem_nodes(drm_dev, c_node, EXYNOS_DRM_OPS_SRC);
 		break;
 	default:
 		DRM_ERROR("invalid operations.\n");
-		ret = -EINVAL;
-		goto err_clear;
+		return -EINVAL;
 	}
 
-err_clear:
-	mutex_unlock(&c_node->mem_lock);
-
-	/* stop operations */
-	if (ippdrv->stop)
-		ippdrv->stop(ippdrv->dev, property->cmd);
-
-	return ret;
+	return 0;
 }
 
 void ipp_sched_cmd(struct work_struct *work)
 {
 	struct drm_exynos_ipp_cmd_work *cmd_work =
-		(struct drm_exynos_ipp_cmd_work *)work;
+		container_of(work, struct drm_exynos_ipp_cmd_work, work);
 	struct exynos_drm_ippdrv *ippdrv;
 	struct drm_exynos_ipp_cmd_node *c_node;
 	struct drm_exynos_ipp_property *property;
@@ -1543,7 +1502,7 @@ err_event_unlock:
 void ipp_sched_event(struct work_struct *work)
 {
 	struct drm_exynos_ipp_event_work *event_work =
-		(struct drm_exynos_ipp_event_work *)work;
+		container_of(work, struct drm_exynos_ipp_event_work, work);
 	struct exynos_drm_ippdrv *ippdrv;
 	struct drm_exynos_ipp_cmd_node *c_node;
 	int ret;
@@ -1646,11 +1605,11 @@ err:
 
 static void ipp_subdrv_remove(struct drm_device *drm_dev, struct device *dev)
 {
-	struct exynos_drm_ippdrv *ippdrv;
+	struct exynos_drm_ippdrv *ippdrv, *t;
 	struct ipp_context *ctx = get_ipp_context(dev);
 
 	/* get ipp driver entry */
-	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
+	list_for_each_entry_safe(ippdrv, t, &exynos_drm_ippdrv_list, drv_list) {
 		if (is_drm_iommu_supported(drm_dev))
 			drm_iommu_detach_device(drm_dev, ippdrv->dev);
 
@@ -1677,14 +1636,11 @@ static int ipp_subdrv_open(struct drm_device *drm_dev, struct device *dev,
 static void ipp_subdrv_close(struct drm_device *drm_dev, struct device *dev,
 		struct drm_file *file)
 {
-	struct drm_exynos_file_private *file_priv = file->driver_priv;
 	struct exynos_drm_ippdrv *ippdrv = NULL;
 	struct ipp_context *ctx = get_ipp_context(dev);
 	struct drm_exynos_ipp_cmd_node *c_node, *tc_node;
 	int count = 0;
 
-	DRM_DEBUG_KMS("for priv[0x%x]\n", (int)file_priv->ipp_dev);
-
 	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
 		mutex_lock(&ippdrv->cmd_lock);
 		list_for_each_entry_safe(c_node, tc_node,
@@ -1692,7 +1648,7 @@ static void ipp_subdrv_close(struct drm_device *drm_dev, struct device *dev,
 			DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]\n",
 				count++, (int)ippdrv);
 
-			if (c_node->dev == file_priv->ipp_dev) {
+			if (c_node->filp == file) {
 				/*
 				 * userland goto unnormal state. process killed.
 				 * and close the file.
@@ -1808,63 +1764,12 @@ static int ipp_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int ipp_power_ctrl(struct ipp_context *ctx, bool enable)
-{
-	DRM_DEBUG_KMS("enable[%d]\n", enable);
-
-	return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int ipp_suspend(struct device *dev)
-{
-	struct ipp_context *ctx = get_ipp_context(dev);
-
-	if (pm_runtime_suspended(dev))
-		return 0;
-
-	return ipp_power_ctrl(ctx, false);
-}
-
-static int ipp_resume(struct device *dev)
-{
-	struct ipp_context *ctx = get_ipp_context(dev);
-
-	if (!pm_runtime_suspended(dev))
-		return ipp_power_ctrl(ctx, true);
-
-	return 0;
-}
-#endif
-
-#ifdef CONFIG_PM_RUNTIME
-static int ipp_runtime_suspend(struct device *dev)
-{
-	struct ipp_context *ctx = get_ipp_context(dev);
-
-	return ipp_power_ctrl(ctx, false);
-}
-
-static int ipp_runtime_resume(struct device *dev)
-{
-	struct ipp_context *ctx = get_ipp_context(dev);
-
-	return ipp_power_ctrl(ctx, true);
-}
-#endif
-
-static const struct dev_pm_ops ipp_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(ipp_suspend, ipp_resume)
-	SET_RUNTIME_PM_OPS(ipp_runtime_suspend, ipp_runtime_resume, NULL)
-};
-
 struct platform_driver ipp_driver = {
 	.probe		= ipp_probe,
 	.remove		= ipp_remove,
 	.driver		= {
 		.name	= "exynos-drm-ipp",
 		.owner	= THIS_MODULE,
-		.pm	= &ipp_pm_ops,
 	},
 };
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.h b/drivers/gpu/drm/exynos/exynos_drm_ipp.h
index 6f48d62aeb30..2a61547a39d0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.h
@@ -48,7 +48,6 @@ struct drm_exynos_ipp_cmd_work {
 /*
  * A structure of command node.
  *
- * @dev: IPP device.
  * @list: list head to command queue information.
  * @event_list: list head of event.
  * @mem_list: list head to source,destination memory queue information.
@@ -62,9 +61,9 @@ struct drm_exynos_ipp_cmd_work {
  * @stop_work: stop command work structure.
  * @event_work: event work structure.
  * @state: state of command node.
+ * @filp: associated file pointer.
  */
 struct drm_exynos_ipp_cmd_node {
-	struct device		*dev;
 	struct list_head	list;
 	struct list_head	event_list;
 	struct list_head	mem_list[EXYNOS_DRM_OPS_MAX];
@@ -78,6 +77,7 @@ struct drm_exynos_ipp_cmd_node {
 	struct drm_exynos_ipp_cmd_work *stop_work;
 	struct drm_exynos_ipp_event_work *event_work;
 	enum drm_exynos_ipp_state	state;
+	struct drm_file	*filp;
 };
 
 /*
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index 8371cbd7631d..c7045a663763 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -139,6 +139,8 @@ int exynos_plane_mode_set(struct drm_plane *plane, struct drm_crtc *crtc,
 			overlay->crtc_x, overlay->crtc_y,
 			overlay->crtc_width, overlay->crtc_height);
 
+	plane->crtc = crtc;
+
 	exynos_drm_crtc_plane_mode_set(crtc, overlay);
 
 	return 0;
@@ -187,8 +189,6 @@ exynos_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	if (ret < 0)
 		return ret;
 
-	plane->crtc = crtc;
-
 	exynos_plane_commit(plane);
 	exynos_plane_dpms(plane, DRM_MODE_DPMS_ON);
 
@@ -254,25 +254,26 @@ static void exynos_plane_attach_zpos_property(struct drm_plane *plane)
 }
 
 struct drm_plane *exynos_plane_init(struct drm_device *dev,
-				    unsigned long possible_crtcs, bool priv)
+				    unsigned long possible_crtcs,
+				    enum drm_plane_type type)
 {
 	struct exynos_plane *exynos_plane;
 	int err;
 
 	exynos_plane = kzalloc(sizeof(struct exynos_plane), GFP_KERNEL);
 	if (!exynos_plane)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
-	err = drm_plane_init(dev, &exynos_plane->base, possible_crtcs,
-			      &exynos_plane_funcs, formats, ARRAY_SIZE(formats),
-			      priv);
+	err = drm_universal_plane_init(dev, &exynos_plane->base, possible_crtcs,
+				       &exynos_plane_funcs, formats,
+				       ARRAY_SIZE(formats), type);
 	if (err) {
 		DRM_ERROR("failed to initialize plane\n");
 		kfree(exynos_plane);
-		return NULL;
+		return ERR_PTR(err);
 	}
 
-	if (priv)
+	if (type == DRM_PLANE_TYPE_PRIMARY)
 		exynos_plane->overlay.zpos = DEFAULT_ZPOS;
 	else
 		exynos_plane_attach_zpos_property(&exynos_plane->base);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.h b/drivers/gpu/drm/exynos/exynos_drm_plane.h
index 84d464c90d3d..0d1986b115f8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.h
@@ -17,4 +17,5 @@ int exynos_plane_mode_set(struct drm_plane *plane, struct drm_crtc *crtc,
 void exynos_plane_commit(struct drm_plane *plane);
 void exynos_plane_dpms(struct drm_plane *plane, int mode);
 struct drm_plane *exynos_plane_init(struct drm_device *dev,
-				    unsigned long possible_crtcs, bool priv);
+				    unsigned long possible_crtcs,
+				    enum drm_plane_type type);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 55af6b41c1df..b6a37d4f5b13 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -156,8 +156,7 @@ static irqreturn_t rotator_irq_handler(int irq, void *arg)
 		event_work->ippdrv = ippdrv;
 		event_work->buf_id[EXYNOS_DRM_OPS_DST] =
 			rot->cur_buf_id[EXYNOS_DRM_OPS_DST];
-		queue_work(ippdrv->event_workq,
-			(struct work_struct *)event_work);
+		queue_work(ippdrv->event_workq, &event_work->work);
 	} else {
 		DRM_ERROR("the SFR is set illegally\n");
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 9528d81d8004..d565207040a2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -303,23 +303,6 @@ static int vidi_mgr_initialize(struct exynos_drm_manager *mgr,
 	mgr->drm_dev = ctx->drm_dev = drm_dev;
 	mgr->pipe = ctx->pipe = priv->pipe++;
 
-	/*
-	 * enable drm irq mode.
-	 * - with irq_enabled = 1, we can use the vblank feature.
-	 *
-	 * P.S. note that we wouldn't use drm irq handler but
-	 *	just specific driver own one instead because
-	 *	drm framework supports only one irq handler.
-	 */
-	drm_dev->irq_enabled = 1;
-
-	/*
-	 * with vblank_disable_allowed = 1, vblank interrupt will be disabled
-	 * by drm timer once a current process gives up ownership of
-	 * vblank event.(after drm_vblank_put function is called)
-	 */
-	drm_dev->vblank_disable_allowed = 1;
-
 	return 0;
 }
 
@@ -648,7 +631,6 @@ static int vidi_remove(struct platform_device *pdev)
 	struct exynos_drm_manager *mgr = platform_get_drvdata(pdev);
 	struct vidi_context *ctx = mgr->ctx;
 	struct drm_encoder *encoder = ctx->encoder;
-	struct drm_crtc *crtc = mgr->crtc;
 
 	if (ctx->raw_edid != (struct edid *)fake_edid_info) {
 		kfree(ctx->raw_edid);
@@ -657,7 +639,6 @@ static int vidi_remove(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	crtc->funcs->destroy(crtc);
 	encoder->funcs->destroy(encoder);
 	drm_connector_cleanup(&ctx->connector);
 
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 562966db2aa1..7910fb37d9bb 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -1040,6 +1040,8 @@ static enum drm_connector_status hdmi_detect(struct drm_connector *connector,
 
 static void hdmi_connector_destroy(struct drm_connector *connector)
 {
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
 }
 
 static struct drm_connector_funcs hdmi_connector_funcs = {
@@ -2314,8 +2316,8 @@ static void hdmi_unbind(struct device *dev, struct device *master, void *data)
 	struct drm_encoder *encoder = display->encoder;
 	struct hdmi_context *hdata = display->ctx;
 
+	hdmi_connector_destroy(&hdata->connector);
 	encoder->funcs->destroy(encoder);
-	drm_connector_cleanup(&hdata->connector);
 }
 
 static const struct component_ops hdmi_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index e8b4ec84b312..a41c84ee3a2d 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -1302,15 +1302,12 @@ static int mixer_bind(struct device *dev, struct device *manager, void *data)
 static void mixer_unbind(struct device *dev, struct device *master, void *data)
 {
 	struct exynos_drm_manager *mgr = dev_get_drvdata(dev);
-	struct drm_crtc *crtc = mgr->crtc;
 
 	dev_info(dev, "remove successful\n");
 
 	mixer_mgr_remove(mgr);
 
 	pm_runtime_disable(dev);
-
-	crtc->funcs->destroy(crtc);
 }
 
 static const struct component_ops mixer_component_ops = {
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index a4cc0e60a1be..9f158eab517a 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -1089,7 +1089,7 @@ static char	*link_train_names[] = {
 };
 #endif
 
-#define CDV_DP_VOLTAGE_MAX	    DP_TRAIN_VOLTAGE_SWING_1200
+#define CDV_DP_VOLTAGE_MAX	    DP_TRAIN_VOLTAGE_SWING_LEVEL_3
 /*
 static uint8_t
 cdv_intel_dp_pre_emphasis_max(uint8_t voltage_swing)
@@ -1276,7 +1276,7 @@ cdv_intel_dp_set_vswing_premph(struct gma_encoder *encoder, uint8_t signal_level
 		cdv_sb_write(dev, ddi_reg->VSwing2, dp_vswing_premph_table[index]);
 
 	/* ;gfx_dpio_set_reg(0x814c, 0x40802040) */
-	if ((vswing + premph) == DP_TRAIN_VOLTAGE_SWING_1200)
+	if ((vswing + premph) == DP_TRAIN_VOLTAGE_SWING_LEVEL_3)
 		cdv_sb_write(dev, ddi_reg->VSwing3, 0x70802040);
 	else
 		cdv_sb_write(dev, ddi_reg->VSwing3, 0x40802040);
diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index d0dd3bea8aa5..ddd90ddbc200 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -540,7 +540,8 @@ static void psbfb_gamma_get(struct drm_crtc *crtc, u16 *red,
 static int psbfb_probe(struct drm_fb_helper *helper,
 				struct drm_fb_helper_surface_size *sizes)
 {
-	struct psb_fbdev *psb_fbdev = (struct psb_fbdev *)helper;
+	struct psb_fbdev *psb_fbdev =
+		container_of(helper, struct psb_fbdev, psb_fb_helper);
 	struct drm_device *dev = psb_fbdev->psb_fb_helper.dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	int bytespp;
diff --git a/drivers/gpu/drm/gma500/gtt.h b/drivers/gpu/drm/gma500/gtt.h
index f5860a739bd8..cdbb350c9d5d 100644
--- a/drivers/gpu/drm/gma500/gtt.h
+++ b/drivers/gpu/drm/gma500/gtt.h
@@ -21,6 +21,7 @@
 #define _PSB_GTT_H_
 
 #include <drm/drmP.h>
+#include <drm/drm_gem.h>
 
 /* This wants cleaning up with respect to the psb_dev and un-needed stuff */
 struct psb_gtt {
diff --git a/drivers/gpu/drm/gma500/intel_bios.c b/drivers/gpu/drm/gma500/intel_bios.c
index d3497348c4d5..63bde4e86c6a 100644
--- a/drivers/gpu/drm/gma500/intel_bios.c
+++ b/drivers/gpu/drm/gma500/intel_bios.c
@@ -116,30 +116,30 @@ parse_edp(struct drm_psb_private *dev_priv, struct bdb_header *bdb)
 
 	switch (edp_link_params->preemphasis) {
 	case 0:
-		dev_priv->edp.preemphasis = DP_TRAIN_PRE_EMPHASIS_0;
+		dev_priv->edp.preemphasis = DP_TRAIN_PRE_EMPH_LEVEL_0;
 		break;
 	case 1:
-		dev_priv->edp.preemphasis = DP_TRAIN_PRE_EMPHASIS_3_5;
+		dev_priv->edp.preemphasis = DP_TRAIN_PRE_EMPH_LEVEL_1;
 		break;
 	case 2:
-		dev_priv->edp.preemphasis = DP_TRAIN_PRE_EMPHASIS_6;
+		dev_priv->edp.preemphasis = DP_TRAIN_PRE_EMPH_LEVEL_2;
 		break;
 	case 3:
-		dev_priv->edp.preemphasis = DP_TRAIN_PRE_EMPHASIS_9_5;
+		dev_priv->edp.preemphasis = DP_TRAIN_PRE_EMPH_LEVEL_3;
 		break;
 	}
 	switch (edp_link_params->vswing) {
 	case 0:
-		dev_priv->edp.vswing = DP_TRAIN_VOLTAGE_SWING_400;
+		dev_priv->edp.vswing = DP_TRAIN_VOLTAGE_SWING_LEVEL_0;
 		break;
 	case 1:
-		dev_priv->edp.vswing = DP_TRAIN_VOLTAGE_SWING_600;
+		dev_priv->edp.vswing = DP_TRAIN_VOLTAGE_SWING_LEVEL_1;
 		break;
 	case 2:
-		dev_priv->edp.vswing = DP_TRAIN_VOLTAGE_SWING_800;
+		dev_priv->edp.vswing = DP_TRAIN_VOLTAGE_SWING_LEVEL_2;
 		break;
 	case 3:
-		dev_priv->edp.vswing = DP_TRAIN_VOLTAGE_SWING_1200;
+		dev_priv->edp.vswing = DP_TRAIN_VOLTAGE_SWING_LEVEL_3;
 		break;
 	}
 	DRM_DEBUG_KMS("VBT reports EDP: VSwing  %d, Preemph %d\n",
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index eec993f93b1a..6ec3a905fdd2 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -476,6 +476,7 @@ static struct drm_driver driver = {
 	.unload = psb_driver_unload,
 	.lastclose = psb_driver_lastclose,
 	.preclose = psb_driver_preclose,
+	.set_busid = drm_pci_set_busid,
 
 	.num_ioctls = ARRAY_SIZE(psb_ioctls),
 	.device_is_agp = psb_driver_device_is_agp,
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index bae897de9468..d91856779beb 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -213,7 +213,7 @@ static int i810_dma_cleanup(struct drm_device *dev)
 		    (drm_i810_private_t *) dev->dev_private;
 
 		if (dev_priv->ring.virtual_start)
-			drm_core_ioremapfree(&dev_priv->ring.map, dev);
+			drm_legacy_ioremapfree(&dev_priv->ring.map, dev);
 		if (dev_priv->hw_status_page) {
 			pci_free_consistent(dev->pdev, PAGE_SIZE,
 					    dev_priv->hw_status_page,
@@ -227,7 +227,7 @@ static int i810_dma_cleanup(struct drm_device *dev)
 			drm_i810_buf_priv_t *buf_priv = buf->dev_private;
 
 			if (buf_priv->kernel_virtual && buf->total)
-				drm_core_ioremapfree(&buf_priv->map, dev);
+				drm_legacy_ioremapfree(&buf_priv->map, dev);
 		}
 	}
 	return 0;
@@ -306,7 +306,7 @@ static int i810_freelist_init(struct drm_device *dev, drm_i810_private_t *dev_pr
 		buf_priv->map.flags = 0;
 		buf_priv->map.mtrr = 0;
 
-		drm_core_ioremap(&buf_priv->map, dev);
+		drm_legacy_ioremap(&buf_priv->map, dev);
 		buf_priv->kernel_virtual = buf_priv->map.handle;
 
 	}
@@ -334,7 +334,7 @@ static int i810_dma_initialize(struct drm_device *dev,
 		DRM_ERROR("can not find sarea!\n");
 		return -EINVAL;
 	}
-	dev_priv->mmio_map = drm_core_findmap(dev, init->mmio_offset);
+	dev_priv->mmio_map = drm_legacy_findmap(dev, init->mmio_offset);
 	if (!dev_priv->mmio_map) {
 		dev->dev_private = (void *)dev_priv;
 		i810_dma_cleanup(dev);
@@ -342,7 +342,7 @@ static int i810_dma_initialize(struct drm_device *dev,
 		return -EINVAL;
 	}
 	dev->agp_buffer_token = init->buffers_offset;
-	dev->agp_buffer_map = drm_core_findmap(dev, init->buffers_offset);
+	dev->agp_buffer_map = drm_legacy_findmap(dev, init->buffers_offset);
 	if (!dev->agp_buffer_map) {
 		dev->dev_private = (void *)dev_priv;
 		i810_dma_cleanup(dev);
@@ -363,7 +363,7 @@ static int i810_dma_initialize(struct drm_device *dev,
 	dev_priv->ring.map.flags = 0;
 	dev_priv->ring.map.mtrr = 0;
 
-	drm_core_ioremap(&dev_priv->ring.map, dev);
+	drm_legacy_ioremap(&dev_priv->ring.map, dev);
 
 	if (dev_priv->ring.map.handle == NULL) {
 		dev->dev_private = (void *)dev_priv;
@@ -1215,9 +1215,9 @@ void i810_driver_preclose(struct drm_device *dev, struct drm_file *file_priv)
 	}
 
 	if (file_priv->master && file_priv->master->lock.hw_lock) {
-		drm_idlelock_take(&file_priv->master->lock);
+		drm_legacy_idlelock_take(&file_priv->master->lock);
 		i810_driver_reclaim_buffers(dev, file_priv);
-		drm_idlelock_release(&file_priv->master->lock);
+		drm_legacy_idlelock_release(&file_priv->master->lock);
 	} else {
 		/* master disappeared, clean up stuff anyway and hope nothing
 		 * goes wrong */
diff --git a/drivers/gpu/drm/i810/i810_drv.c b/drivers/gpu/drm/i810/i810_drv.c
index 441ccf8f5bdc..44f4a131c8dd 100644
--- a/drivers/gpu/drm/i810/i810_drv.c
+++ b/drivers/gpu/drm/i810/i810_drv.c
@@ -47,7 +47,7 @@ static const struct file_operations i810_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
@@ -63,6 +63,7 @@ static struct drm_driver driver = {
 	.load = i810_driver_load,
 	.lastclose = i810_driver_lastclose,
 	.preclose = i810_driver_preclose,
+	.set_busid = drm_pci_set_busid,
 	.device_is_agp = i810_driver_device_is_agp,
 	.dma_quiescent = i810_driver_dma_quiescent,
 	.ioctls = i810_ioctls,
diff --git a/drivers/gpu/drm/i810/i810_drv.h b/drivers/gpu/drm/i810/i810_drv.h
index d4d16eddd651..93ec5dc4e7d3 100644
--- a/drivers/gpu/drm/i810/i810_drv.h
+++ b/drivers/gpu/drm/i810/i810_drv.h
@@ -32,6 +32,8 @@
 #ifndef _I810_DRV_H_
 #define _I810_DRV_H_
 
+#include <drm/drm_legacy.h>
+
 /* General customization:
  */
 
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 91bd167e1cb7..c1dd485aeb6c 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -31,6 +31,7 @@ i915-y += i915_cmd_parser.o \
 	  i915_gpu_error.o \
 	  i915_irq.o \
 	  i915_trace_points.o \
+	  intel_lrc.o \
 	  intel_ringbuffer.o \
 	  intel_uncore.o
 
diff --git a/drivers/gpu/drm/i915/dvo_ns2501.c b/drivers/gpu/drm/i915/dvo_ns2501.c
index 74f2af7c2d3e..441630434d34 100644
--- a/drivers/gpu/drm/i915/dvo_ns2501.c
+++ b/drivers/gpu/drm/i915/dvo_ns2501.c
@@ -60,16 +60,297 @@
 
 #define NS2501_REGC 0x0c
 
+enum {
+	MODE_640x480,
+	MODE_800x600,
+	MODE_1024x768,
+};
+
+struct ns2501_reg {
+	 uint8_t offset;
+	 uint8_t value;
+};
+
+/*
+ * Magic values based on what the BIOS on
+ * Fujitsu-Siemens Lifebook S6010 programs (1024x768 panel).
+ */
+static const struct ns2501_reg regs_1024x768[][86] = {
+	[MODE_640x480] = {
+		[0] = { .offset = 0x0a, .value = 0x81, },
+		[1] = { .offset = 0x18, .value = 0x07, },
+		[2] = { .offset = 0x19, .value = 0x00, },
+		[3] = { .offset = 0x1a, .value = 0x00, },
+		[4] = { .offset = 0x1b, .value = 0x11, },
+		[5] = { .offset = 0x1c, .value = 0x54, },
+		[6] = { .offset = 0x1d, .value = 0x03, },
+		[7] = { .offset = 0x1e, .value = 0x02, },
+		[8] = { .offset = 0xf3, .value = 0x90, },
+		[9] = { .offset = 0xf9, .value = 0x00, },
+		[10] = { .offset = 0xc1, .value = 0x90, },
+		[11] = { .offset = 0xc2, .value = 0x00, },
+		[12] = { .offset = 0xc3, .value = 0x0f, },
+		[13] = { .offset = 0xc4, .value = 0x03, },
+		[14] = { .offset = 0xc5, .value = 0x16, },
+		[15] = { .offset = 0xc6, .value = 0x00, },
+		[16] = { .offset = 0xc7, .value = 0x02, },
+		[17] = { .offset = 0xc8, .value = 0x02, },
+		[18] = { .offset = 0xf4, .value = 0x00, },
+		[19] = { .offset = 0x80, .value = 0xff, },
+		[20] = { .offset = 0x81, .value = 0x07, },
+		[21] = { .offset = 0x82, .value = 0x3d, },
+		[22] = { .offset = 0x83, .value = 0x05, },
+		[23] = { .offset = 0x94, .value = 0x00, },
+		[24] = { .offset = 0x95, .value = 0x00, },
+		[25] = { .offset = 0x96, .value = 0x05, },
+		[26] = { .offset = 0x97, .value = 0x00, },
+		[27] = { .offset = 0x9a, .value = 0x88, },
+		[28] = { .offset = 0x9b, .value = 0x00, },
+		[29] = { .offset = 0x98, .value = 0x00, },
+		[30] = { .offset = 0x99, .value = 0x00, },
+		[31] = { .offset = 0xf7, .value = 0x88, },
+		[32] = { .offset = 0xf8, .value = 0x0a, },
+		[33] = { .offset = 0x9c, .value = 0x24, },
+		[34] = { .offset = 0x9d, .value = 0x00, },
+		[35] = { .offset = 0x9e, .value = 0x25, },
+		[36] = { .offset = 0x9f, .value = 0x03, },
+		[37] = { .offset = 0xa0, .value = 0x28, },
+		[38] = { .offset = 0xa1, .value = 0x01, },
+		[39] = { .offset = 0xa2, .value = 0x28, },
+		[40] = { .offset = 0xa3, .value = 0x05, },
+		[41] = { .offset = 0xb6, .value = 0x09, },
+		[42] = { .offset = 0xb8, .value = 0x00, },
+		[43] = { .offset = 0xb9, .value = 0xa0, },
+		[44] = { .offset = 0xba, .value = 0x00, },
+		[45] = { .offset = 0xbb, .value = 0x20, },
+		[46] = { .offset = 0x10, .value = 0x00, },
+		[47] = { .offset = 0x11, .value = 0xa0, },
+		[48] = { .offset = 0x12, .value = 0x02, },
+		[49] = { .offset = 0x20, .value = 0x00, },
+		[50] = { .offset = 0x22, .value = 0x00, },
+		[51] = { .offset = 0x23, .value = 0x00, },
+		[52] = { .offset = 0x24, .value = 0x00, },
+		[53] = { .offset = 0x25, .value = 0x00, },
+		[54] = { .offset = 0x8c, .value = 0x10, },
+		[55] = { .offset = 0x8d, .value = 0x02, },
+		[56] = { .offset = 0x8e, .value = 0x10, },
+		[57] = { .offset = 0x8f, .value = 0x00, },
+		[58] = { .offset = 0x90, .value = 0xff, },
+		[59] = { .offset = 0x91, .value = 0x07, },
+		[60] = { .offset = 0x92, .value = 0xa0, },
+		[61] = { .offset = 0x93, .value = 0x02, },
+		[62] = { .offset = 0xa5, .value = 0x00, },
+		[63] = { .offset = 0xa6, .value = 0x00, },
+		[64] = { .offset = 0xa7, .value = 0x00, },
+		[65] = { .offset = 0xa8, .value = 0x00, },
+		[66] = { .offset = 0xa9, .value = 0x04, },
+		[67] = { .offset = 0xaa, .value = 0x70, },
+		[68] = { .offset = 0xab, .value = 0x4f, },
+		[69] = { .offset = 0xac, .value = 0x00, },
+		[70] = { .offset = 0xa4, .value = 0x84, },
+		[71] = { .offset = 0x7e, .value = 0x18, },
+		[72] = { .offset = 0x84, .value = 0x00, },
+		[73] = { .offset = 0x85, .value = 0x00, },
+		[74] = { .offset = 0x86, .value = 0x00, },
+		[75] = { .offset = 0x87, .value = 0x00, },
+		[76] = { .offset = 0x88, .value = 0x00, },
+		[77] = { .offset = 0x89, .value = 0x00, },
+		[78] = { .offset = 0x8a, .value = 0x00, },
+		[79] = { .offset = 0x8b, .value = 0x00, },
+		[80] = { .offset = 0x26, .value = 0x00, },
+		[81] = { .offset = 0x27, .value = 0x00, },
+		[82] = { .offset = 0xad, .value = 0x00, },
+		[83] = { .offset = 0x08, .value = 0x30, }, /* 0x31 */
+		[84] = { .offset = 0x41, .value = 0x00, },
+		[85] = { .offset = 0xc0, .value = 0x05, },
+	},
+	[MODE_800x600] = {
+		[0] = { .offset = 0x0a, .value = 0x81, },
+		[1] = { .offset = 0x18, .value = 0x07, },
+		[2] = { .offset = 0x19, .value = 0x00, },
+		[3] = { .offset = 0x1a, .value = 0x00, },
+		[4] = { .offset = 0x1b, .value = 0x19, },
+		[5] = { .offset = 0x1c, .value = 0x64, },
+		[6] = { .offset = 0x1d, .value = 0x02, },
+		[7] = { .offset = 0x1e, .value = 0x02, },
+		[8] = { .offset = 0xf3, .value = 0x90, },
+		[9] = { .offset = 0xf9, .value = 0x00, },
+		[10] = { .offset = 0xc1, .value = 0xd7, },
+		[11] = { .offset = 0xc2, .value = 0x00, },
+		[12] = { .offset = 0xc3, .value = 0xf8, },
+		[13] = { .offset = 0xc4, .value = 0x03, },
+		[14] = { .offset = 0xc5, .value = 0x1a, },
+		[15] = { .offset = 0xc6, .value = 0x00, },
+		[16] = { .offset = 0xc7, .value = 0x73, },
+		[17] = { .offset = 0xc8, .value = 0x02, },
+		[18] = { .offset = 0xf4, .value = 0x00, },
+		[19] = { .offset = 0x80, .value = 0x27, },
+		[20] = { .offset = 0x81, .value = 0x03, },
+		[21] = { .offset = 0x82, .value = 0x41, },
+		[22] = { .offset = 0x83, .value = 0x05, },
+		[23] = { .offset = 0x94, .value = 0x00, },
+		[24] = { .offset = 0x95, .value = 0x00, },
+		[25] = { .offset = 0x96, .value = 0x05, },
+		[26] = { .offset = 0x97, .value = 0x00, },
+		[27] = { .offset = 0x9a, .value = 0x88, },
+		[28] = { .offset = 0x9b, .value = 0x00, },
+		[29] = { .offset = 0x98, .value = 0x00, },
+		[30] = { .offset = 0x99, .value = 0x00, },
+		[31] = { .offset = 0xf7, .value = 0x88, },
+		[32] = { .offset = 0xf8, .value = 0x06, },
+		[33] = { .offset = 0x9c, .value = 0x23, },
+		[34] = { .offset = 0x9d, .value = 0x00, },
+		[35] = { .offset = 0x9e, .value = 0x25, },
+		[36] = { .offset = 0x9f, .value = 0x03, },
+		[37] = { .offset = 0xa0, .value = 0x28, },
+		[38] = { .offset = 0xa1, .value = 0x01, },
+		[39] = { .offset = 0xa2, .value = 0x28, },
+		[40] = { .offset = 0xa3, .value = 0x05, },
+		[41] = { .offset = 0xb6, .value = 0x09, },
+		[42] = { .offset = 0xb8, .value = 0x30, },
+		[43] = { .offset = 0xb9, .value = 0xc8, },
+		[44] = { .offset = 0xba, .value = 0x00, },
+		[45] = { .offset = 0xbb, .value = 0x20, },
+		[46] = { .offset = 0x10, .value = 0x20, },
+		[47] = { .offset = 0x11, .value = 0xc8, },
+		[48] = { .offset = 0x12, .value = 0x02, },
+		[49] = { .offset = 0x20, .value = 0x00, },
+		[50] = { .offset = 0x22, .value = 0x00, },
+		[51] = { .offset = 0x23, .value = 0x00, },
+		[52] = { .offset = 0x24, .value = 0x00, },
+		[53] = { .offset = 0x25, .value = 0x00, },
+		[54] = { .offset = 0x8c, .value = 0x10, },
+		[55] = { .offset = 0x8d, .value = 0x02, },
+		[56] = { .offset = 0x8e, .value = 0x04, },
+		[57] = { .offset = 0x8f, .value = 0x00, },
+		[58] = { .offset = 0x90, .value = 0xff, },
+		[59] = { .offset = 0x91, .value = 0x07, },
+		[60] = { .offset = 0x92, .value = 0xa0, },
+		[61] = { .offset = 0x93, .value = 0x02, },
+		[62] = { .offset = 0xa5, .value = 0x00, },
+		[63] = { .offset = 0xa6, .value = 0x00, },
+		[64] = { .offset = 0xa7, .value = 0x00, },
+		[65] = { .offset = 0xa8, .value = 0x00, },
+		[66] = { .offset = 0xa9, .value = 0x83, },
+		[67] = { .offset = 0xaa, .value = 0x40, },
+		[68] = { .offset = 0xab, .value = 0x32, },
+		[69] = { .offset = 0xac, .value = 0x00, },
+		[70] = { .offset = 0xa4, .value = 0x80, },
+		[71] = { .offset = 0x7e, .value = 0x18, },
+		[72] = { .offset = 0x84, .value = 0x00, },
+		[73] = { .offset = 0x85, .value = 0x00, },
+		[74] = { .offset = 0x86, .value = 0x00, },
+		[75] = { .offset = 0x87, .value = 0x00, },
+		[76] = { .offset = 0x88, .value = 0x00, },
+		[77] = { .offset = 0x89, .value = 0x00, },
+		[78] = { .offset = 0x8a, .value = 0x00, },
+		[79] = { .offset = 0x8b, .value = 0x00, },
+		[80] = { .offset = 0x26, .value = 0x00, },
+		[81] = { .offset = 0x27, .value = 0x00, },
+		[82] = { .offset = 0xad, .value = 0x00, },
+		[83] = { .offset = 0x08, .value = 0x30, }, /* 0x31 */
+		[84] = { .offset = 0x41, .value = 0x00, },
+		[85] = { .offset = 0xc0, .value = 0x07, },
+	},
+	[MODE_1024x768] = {
+		[0] = { .offset = 0x0a, .value = 0x81, },
+		[1] = { .offset = 0x18, .value = 0x07, },
+		[2] = { .offset = 0x19, .value = 0x00, },
+		[3] = { .offset = 0x1a, .value = 0x00, },
+		[4] = { .offset = 0x1b, .value = 0x11, },
+		[5] = { .offset = 0x1c, .value = 0x54, },
+		[6] = { .offset = 0x1d, .value = 0x03, },
+		[7] = { .offset = 0x1e, .value = 0x02, },
+		[8] = { .offset = 0xf3, .value = 0x90, },
+		[9] = { .offset = 0xf9, .value = 0x00, },
+		[10] = { .offset = 0xc1, .value = 0x90, },
+		[11] = { .offset = 0xc2, .value = 0x00, },
+		[12] = { .offset = 0xc3, .value = 0x0f, },
+		[13] = { .offset = 0xc4, .value = 0x03, },
+		[14] = { .offset = 0xc5, .value = 0x16, },
+		[15] = { .offset = 0xc6, .value = 0x00, },
+		[16] = { .offset = 0xc7, .value = 0x02, },
+		[17] = { .offset = 0xc8, .value = 0x02, },
+		[18] = { .offset = 0xf4, .value = 0x00, },
+		[19] = { .offset = 0x80, .value = 0xff, },
+		[20] = { .offset = 0x81, .value = 0x07, },
+		[21] = { .offset = 0x82, .value = 0x3d, },
+		[22] = { .offset = 0x83, .value = 0x05, },
+		[23] = { .offset = 0x94, .value = 0x00, },
+		[24] = { .offset = 0x95, .value = 0x00, },
+		[25] = { .offset = 0x96, .value = 0x05, },
+		[26] = { .offset = 0x97, .value = 0x00, },
+		[27] = { .offset = 0x9a, .value = 0x88, },
+		[28] = { .offset = 0x9b, .value = 0x00, },
+		[29] = { .offset = 0x98, .value = 0x00, },
+		[30] = { .offset = 0x99, .value = 0x00, },
+		[31] = { .offset = 0xf7, .value = 0x88, },
+		[32] = { .offset = 0xf8, .value = 0x0a, },
+		[33] = { .offset = 0x9c, .value = 0x24, },
+		[34] = { .offset = 0x9d, .value = 0x00, },
+		[35] = { .offset = 0x9e, .value = 0x25, },
+		[36] = { .offset = 0x9f, .value = 0x03, },
+		[37] = { .offset = 0xa0, .value = 0x28, },
+		[38] = { .offset = 0xa1, .value = 0x01, },
+		[39] = { .offset = 0xa2, .value = 0x28, },
+		[40] = { .offset = 0xa3, .value = 0x05, },
+		[41] = { .offset = 0xb6, .value = 0x09, },
+		[42] = { .offset = 0xb8, .value = 0x00, },
+		[43] = { .offset = 0xb9, .value = 0xa0, },
+		[44] = { .offset = 0xba, .value = 0x00, },
+		[45] = { .offset = 0xbb, .value = 0x20, },
+		[46] = { .offset = 0x10, .value = 0x00, },
+		[47] = { .offset = 0x11, .value = 0xa0, },
+		[48] = { .offset = 0x12, .value = 0x02, },
+		[49] = { .offset = 0x20, .value = 0x00, },
+		[50] = { .offset = 0x22, .value = 0x00, },
+		[51] = { .offset = 0x23, .value = 0x00, },
+		[52] = { .offset = 0x24, .value = 0x00, },
+		[53] = { .offset = 0x25, .value = 0x00, },
+		[54] = { .offset = 0x8c, .value = 0x10, },
+		[55] = { .offset = 0x8d, .value = 0x02, },
+		[56] = { .offset = 0x8e, .value = 0x10, },
+		[57] = { .offset = 0x8f, .value = 0x00, },
+		[58] = { .offset = 0x90, .value = 0xff, },
+		[59] = { .offset = 0x91, .value = 0x07, },
+		[60] = { .offset = 0x92, .value = 0xa0, },
+		[61] = { .offset = 0x93, .value = 0x02, },
+		[62] = { .offset = 0xa5, .value = 0x00, },
+		[63] = { .offset = 0xa6, .value = 0x00, },
+		[64] = { .offset = 0xa7, .value = 0x00, },
+		[65] = { .offset = 0xa8, .value = 0x00, },
+		[66] = { .offset = 0xa9, .value = 0x04, },
+		[67] = { .offset = 0xaa, .value = 0x70, },
+		[68] = { .offset = 0xab, .value = 0x4f, },
+		[69] = { .offset = 0xac, .value = 0x00, },
+		[70] = { .offset = 0xa4, .value = 0x84, },
+		[71] = { .offset = 0x7e, .value = 0x18, },
+		[72] = { .offset = 0x84, .value = 0x00, },
+		[73] = { .offset = 0x85, .value = 0x00, },
+		[74] = { .offset = 0x86, .value = 0x00, },
+		[75] = { .offset = 0x87, .value = 0x00, },
+		[76] = { .offset = 0x88, .value = 0x00, },
+		[77] = { .offset = 0x89, .value = 0x00, },
+		[78] = { .offset = 0x8a, .value = 0x00, },
+		[79] = { .offset = 0x8b, .value = 0x00, },
+		[80] = { .offset = 0x26, .value = 0x00, },
+		[81] = { .offset = 0x27, .value = 0x00, },
+		[82] = { .offset = 0xad, .value = 0x00, },
+		[83] = { .offset = 0x08, .value = 0x34, }, /* 0x35 */
+		[84] = { .offset = 0x41, .value = 0x00, },
+		[85] = { .offset = 0xc0, .value = 0x01, },
+	},
+};
+
+static const struct ns2501_reg regs_init[] = {
+	[0] = { .offset = 0x35, .value = 0xff, },
+	[1] = { .offset = 0x34, .value = 0x00, },
+	[2] = { .offset = 0x08, .value = 0x30, },
+};
+
 struct ns2501_priv {
-	//I2CDevRec d;
 	bool quiet;
-	int reg_8_shadow;
-	int reg_8_set;
-	// Shadow registers for i915
-	int dvoc;
-	int pll_a;
-	int srcdim;
-	int fw_blc;
+	const struct ns2501_reg *regs;
 };
 
 #define NSPTR(d) ((NS2501Ptr)(d->DriverPrivate.ptr))
@@ -205,11 +486,9 @@ static bool ns2501_init(struct intel_dvo_device *dvo,
 		goto out;
 	}
 	ns->quiet = false;
-	ns->reg_8_set = 0;
-	ns->reg_8_shadow =
-	    NS2501_8_PD | NS2501_8_BPAS | NS2501_8_VEN | NS2501_8_HEN;
 
 	DRM_DEBUG_KMS("init ns2501 dvo controller successfully!\n");
+
 	return true;
 
 out:
@@ -242,9 +521,9 @@ static enum drm_mode_status ns2501_mode_valid(struct intel_dvo_device *dvo,
 	 * of the panel in here so we could always accept it
 	 * by disabling the scaler.
 	 */
-	if ((mode->hdisplay == 800 && mode->vdisplay == 600) ||
-	    (mode->hdisplay == 640 && mode->vdisplay == 480) ||
-	    (mode->hdisplay == 1024 && mode->vdisplay == 768)) {
+	if ((mode->hdisplay == 640 && mode->vdisplay == 480 && mode->clock == 25175) ||
+	    (mode->hdisplay == 800 && mode->vdisplay == 600 && mode->clock == 40000) ||
+	    (mode->hdisplay == 1024 && mode->vdisplay == 768 && mode->clock == 65000)) {
 		return MODE_OK;
 	} else {
 		return MODE_ONE_SIZE;	/* Is this a reasonable error? */
@@ -255,180 +534,30 @@ static void ns2501_mode_set(struct intel_dvo_device *dvo,
 			    struct drm_display_mode *mode,
 			    struct drm_display_mode *adjusted_mode)
 {
-	bool ok;
-	int retries = 10;
 	struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv);
+	int mode_idx, i;
 
 	DRM_DEBUG_KMS
 	    ("set mode (hdisplay=%d,htotal=%d,vdisplay=%d,vtotal=%d).\n",
 	     mode->hdisplay, mode->htotal, mode->vdisplay, mode->vtotal);
 
-	/*
-	 * Where do I find the native resolution for which scaling is not required???
-	 *
-	 * First trigger the DVO on as otherwise the chip does not appear on the i2c
-	 * bus.
-	 */
-	do {
-		ok = true;
-
-		if (mode->hdisplay == 800 && mode->vdisplay == 600) {
-			/* mode 277 */
-			ns->reg_8_shadow &= ~NS2501_8_BPAS;
-			DRM_DEBUG_KMS("switching to 800x600\n");
-
-			/*
-			 * No, I do not know where this data comes from.
-			 * It is just what the video bios left in the DVO, so
-			 * I'm just copying it here over.
-			 * This also means that I cannot support any other modes
-			 * except the ones supported by the bios.
-			 */
-			ok &= ns2501_writeb(dvo, 0x11, 0xc8);	// 0xc7 also works.
-			ok &= ns2501_writeb(dvo, 0x1b, 0x19);
-			ok &= ns2501_writeb(dvo, 0x1c, 0x62);	// VBIOS left 0x64 here, but 0x62 works nicer
-			ok &= ns2501_writeb(dvo, 0x1d, 0x02);
-
-			ok &= ns2501_writeb(dvo, 0x34, 0x03);
-			ok &= ns2501_writeb(dvo, 0x35, 0xff);
+	if (mode->hdisplay == 640 && mode->vdisplay == 480)
+		mode_idx = MODE_640x480;
+	else if (mode->hdisplay == 800 && mode->vdisplay == 600)
+		mode_idx = MODE_800x600;
+	else if (mode->hdisplay == 1024 && mode->vdisplay == 768)
+		mode_idx = MODE_1024x768;
+	else
+		return;
 
-			ok &= ns2501_writeb(dvo, 0x80, 0x27);
-			ok &= ns2501_writeb(dvo, 0x81, 0x03);
-			ok &= ns2501_writeb(dvo, 0x82, 0x41);
-			ok &= ns2501_writeb(dvo, 0x83, 0x05);
+	/* Hopefully doing it every time won't hurt... */
+	for (i = 0; i < ARRAY_SIZE(regs_init); i++)
+		ns2501_writeb(dvo, regs_init[i].offset, regs_init[i].value);
 
-			ok &= ns2501_writeb(dvo, 0x8d, 0x02);
-			ok &= ns2501_writeb(dvo, 0x8e, 0x04);
-			ok &= ns2501_writeb(dvo, 0x8f, 0x00);
+	ns->regs = regs_1024x768[mode_idx];
 
-			ok &= ns2501_writeb(dvo, 0x90, 0xfe);	/* vertical. VBIOS left 0xff here, but 0xfe works better */
-			ok &= ns2501_writeb(dvo, 0x91, 0x07);
-			ok &= ns2501_writeb(dvo, 0x94, 0x00);
-			ok &= ns2501_writeb(dvo, 0x95, 0x00);
-
-			ok &= ns2501_writeb(dvo, 0x96, 0x00);
-
-			ok &= ns2501_writeb(dvo, 0x99, 0x00);
-			ok &= ns2501_writeb(dvo, 0x9a, 0x88);
-
-			ok &= ns2501_writeb(dvo, 0x9c, 0x23);	/* Looks like first and last line of the image. */
-			ok &= ns2501_writeb(dvo, 0x9d, 0x00);
-			ok &= ns2501_writeb(dvo, 0x9e, 0x25);
-			ok &= ns2501_writeb(dvo, 0x9f, 0x03);
-
-			ok &= ns2501_writeb(dvo, 0xa4, 0x80);
-
-			ok &= ns2501_writeb(dvo, 0xb6, 0x00);
-
-			ok &= ns2501_writeb(dvo, 0xb9, 0xc8);	/* horizontal? */
-			ok &= ns2501_writeb(dvo, 0xba, 0x00);	/* horizontal? */
-
-			ok &= ns2501_writeb(dvo, 0xc0, 0x05);	/* horizontal? */
-			ok &= ns2501_writeb(dvo, 0xc1, 0xd7);
-
-			ok &= ns2501_writeb(dvo, 0xc2, 0x00);
-			ok &= ns2501_writeb(dvo, 0xc3, 0xf8);
-
-			ok &= ns2501_writeb(dvo, 0xc4, 0x03);
-			ok &= ns2501_writeb(dvo, 0xc5, 0x1a);
-
-			ok &= ns2501_writeb(dvo, 0xc6, 0x00);
-			ok &= ns2501_writeb(dvo, 0xc7, 0x73);
-			ok &= ns2501_writeb(dvo, 0xc8, 0x02);
-
-		} else if (mode->hdisplay == 640 && mode->vdisplay == 480) {
-			/* mode 274 */
-			DRM_DEBUG_KMS("switching to 640x480\n");
-			/*
-			 * No, I do not know where this data comes from.
-			 * It is just what the video bios left in the DVO, so
-			 * I'm just copying it here over.
-			 * This also means that I cannot support any other modes
-			 * except the ones supported by the bios.
-			 */
-			ns->reg_8_shadow &= ~NS2501_8_BPAS;
-
-			ok &= ns2501_writeb(dvo, 0x11, 0xa0);
-			ok &= ns2501_writeb(dvo, 0x1b, 0x11);
-			ok &= ns2501_writeb(dvo, 0x1c, 0x54);
-			ok &= ns2501_writeb(dvo, 0x1d, 0x03);
-
-			ok &= ns2501_writeb(dvo, 0x34, 0x03);
-			ok &= ns2501_writeb(dvo, 0x35, 0xff);
-
-			ok &= ns2501_writeb(dvo, 0x80, 0xff);
-			ok &= ns2501_writeb(dvo, 0x81, 0x07);
-			ok &= ns2501_writeb(dvo, 0x82, 0x3d);
-			ok &= ns2501_writeb(dvo, 0x83, 0x05);
-
-			ok &= ns2501_writeb(dvo, 0x8d, 0x02);
-			ok &= ns2501_writeb(dvo, 0x8e, 0x10);
-			ok &= ns2501_writeb(dvo, 0x8f, 0x00);
-
-			ok &= ns2501_writeb(dvo, 0x90, 0xff);	/* vertical */
-			ok &= ns2501_writeb(dvo, 0x91, 0x07);
-			ok &= ns2501_writeb(dvo, 0x94, 0x00);
-			ok &= ns2501_writeb(dvo, 0x95, 0x00);
-
-			ok &= ns2501_writeb(dvo, 0x96, 0x05);
-
-			ok &= ns2501_writeb(dvo, 0x99, 0x00);
-			ok &= ns2501_writeb(dvo, 0x9a, 0x88);
-
-			ok &= ns2501_writeb(dvo, 0x9c, 0x24);
-			ok &= ns2501_writeb(dvo, 0x9d, 0x00);
-			ok &= ns2501_writeb(dvo, 0x9e, 0x25);
-			ok &= ns2501_writeb(dvo, 0x9f, 0x03);
-
-			ok &= ns2501_writeb(dvo, 0xa4, 0x84);
-
-			ok &= ns2501_writeb(dvo, 0xb6, 0x09);
-
-			ok &= ns2501_writeb(dvo, 0xb9, 0xa0);	/* horizontal? */
-			ok &= ns2501_writeb(dvo, 0xba, 0x00);	/* horizontal? */
-
-			ok &= ns2501_writeb(dvo, 0xc0, 0x05);	/* horizontal? */
-			ok &= ns2501_writeb(dvo, 0xc1, 0x90);
-
-			ok &= ns2501_writeb(dvo, 0xc2, 0x00);
-			ok &= ns2501_writeb(dvo, 0xc3, 0x0f);
-
-			ok &= ns2501_writeb(dvo, 0xc4, 0x03);
-			ok &= ns2501_writeb(dvo, 0xc5, 0x16);
-
-			ok &= ns2501_writeb(dvo, 0xc6, 0x00);
-			ok &= ns2501_writeb(dvo, 0xc7, 0x02);
-			ok &= ns2501_writeb(dvo, 0xc8, 0x02);
-
-		} else if (mode->hdisplay == 1024 && mode->vdisplay == 768) {
-			/* mode 280 */
-			DRM_DEBUG_KMS("switching to 1024x768\n");
-			/*
-			 * This might or might not work, actually. I'm silently
-			 * assuming here that the native panel resolution is
-			 * 1024x768. If not, then this leaves the scaler disabled
-			 * generating a picture that is likely not the expected.
-			 *
-			 * Problem is that I do not know where to take the panel
-			 * dimensions from.
-			 *
-			 * Enable the bypass, scaling not required.
-			 *
-			 * The scaler registers are irrelevant here....
-			 *
-			 */
-			ns->reg_8_shadow |= NS2501_8_BPAS;
-			ok &= ns2501_writeb(dvo, 0x37, 0x44);
-		} else {
-			/*
-			 * Data not known. Bummer!
-			 * Hopefully, the code should not go here
-			 * as mode_OK delivered no other modes.
-			 */
-			ns->reg_8_shadow |= NS2501_8_BPAS;
-		}
-		ok &= ns2501_writeb(dvo, NS2501_REG8, ns->reg_8_shadow);
-	} while (!ok && retries--);
+	for (i = 0; i < 84; i++)
+		ns2501_writeb(dvo, ns->regs[i].offset, ns->regs[i].value);
 }
 
 /* set the NS2501 power state */
@@ -439,60 +568,46 @@ static bool ns2501_get_hw_state(struct intel_dvo_device *dvo)
 	if (!ns2501_readb(dvo, NS2501_REG8, &ch))
 		return false;
 
-	if (ch & NS2501_8_PD)
-		return true;
-	else
-		return false;
+	return ch & NS2501_8_PD;
 }
 
 /* set the NS2501 power state */
 static void ns2501_dpms(struct intel_dvo_device *dvo, bool enable)
 {
-	bool ok;
-	int retries = 10;
 	struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv);
-	unsigned char ch;
 
 	DRM_DEBUG_KMS("Trying set the dpms of the DVO to %i\n", enable);
 
-	ch = ns->reg_8_shadow;
+	if (enable) {
+		if (WARN_ON(ns->regs[83].offset != 0x08 ||
+			    ns->regs[84].offset != 0x41 ||
+			    ns->regs[85].offset != 0xc0))
+			return;
 
-	if (enable)
-		ch |= NS2501_8_PD;
-	else
-		ch &= ~NS2501_8_PD;
-
-	if (ns->reg_8_set == 0 || ns->reg_8_shadow != ch) {
-		ns->reg_8_set = 1;
-		ns->reg_8_shadow = ch;
-
-		do {
-			ok = true;
-			ok &= ns2501_writeb(dvo, NS2501_REG8, ch);
-			ok &=
-			    ns2501_writeb(dvo, 0x34,
-					  enable ? 0x03 : 0x00);
-			ok &=
-			    ns2501_writeb(dvo, 0x35,
-					  enable ? 0xff : 0x00);
-		} while (!ok && retries--);
-	}
-}
+		ns2501_writeb(dvo, 0xc0, ns->regs[85].value | 0x08);
 
-static void ns2501_dump_regs(struct intel_dvo_device *dvo)
-{
-	uint8_t val;
-
-	ns2501_readb(dvo, NS2501_FREQ_LO, &val);
-	DRM_DEBUG_KMS("NS2501_FREQ_LO: 0x%02x\n", val);
-	ns2501_readb(dvo, NS2501_FREQ_HI, &val);
-	DRM_DEBUG_KMS("NS2501_FREQ_HI: 0x%02x\n", val);
-	ns2501_readb(dvo, NS2501_REG8, &val);
-	DRM_DEBUG_KMS("NS2501_REG8: 0x%02x\n", val);
-	ns2501_readb(dvo, NS2501_REG9, &val);
-	DRM_DEBUG_KMS("NS2501_REG9: 0x%02x\n", val);
-	ns2501_readb(dvo, NS2501_REGC, &val);
-	DRM_DEBUG_KMS("NS2501_REGC: 0x%02x\n", val);
+		ns2501_writeb(dvo, 0x41, ns->regs[84].value);
+
+		ns2501_writeb(dvo, 0x34, 0x01);
+		msleep(15);
+
+		ns2501_writeb(dvo, 0x08, 0x35);
+		if (!(ns->regs[83].value & NS2501_8_BPAS))
+			ns2501_writeb(dvo, 0x08, 0x31);
+		msleep(200);
+
+		ns2501_writeb(dvo, 0x34, 0x03);
+
+		ns2501_writeb(dvo, 0xc0, ns->regs[85].value);
+	} else {
+		ns2501_writeb(dvo, 0x34, 0x01);
+		msleep(200);
+
+		ns2501_writeb(dvo, 0x08, 0x34);
+		msleep(15);
+
+		ns2501_writeb(dvo, 0x34, 0x00);
+	}
 }
 
 static void ns2501_destroy(struct intel_dvo_device *dvo)
@@ -512,6 +627,5 @@ struct intel_dvo_dev_ops ns2501_ops = {
 	.mode_set = ns2501_mode_set,
 	.dpms = ns2501_dpms,
 	.get_hw_state = ns2501_get_hw_state,
-	.dump_regs = ns2501_dump_regs,
 	.destroy = ns2501_destroy,
 };
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 4b7ed5289217..593b657d3e59 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -844,8 +844,6 @@ finish:
  */
 bool i915_needs_cmd_parser(struct intel_engine_cs *ring)
 {
-	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-
 	if (!ring->needs_cmd_parser)
 		return false;
 
@@ -854,7 +852,7 @@ bool i915_needs_cmd_parser(struct intel_engine_cs *ring)
 	 * disabled. That will cause all of the parser's PPGTT checks to
 	 * fail. For now, disable parsing when PPGTT is off.
 	 */
-	if (!dev_priv->mm.aliasing_ppgtt)
+	if (USES_PPGTT(ring->dev))
 		return false;
 
 	return (i915.enable_cmd_parser == 1);
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 9e737b771c40..063b44817e08 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -136,7 +136,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		   obj->last_read_seqno,
 		   obj->last_write_seqno,
 		   obj->last_fenced_seqno,
-		   i915_cache_level_str(obj->cache_level),
+		   i915_cache_level_str(to_i915(obj->base.dev), obj->cache_level),
 		   obj->dirty ? " dirty" : "",
 		   obj->madv == I915_MADV_DONTNEED ? " purgeable" : "");
 	if (obj->base.name)
@@ -333,7 +333,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 			}
 
 			ppgtt = container_of(vma->vm, struct i915_hw_ppgtt, base);
-			if (ppgtt->ctx && ppgtt->ctx->file_priv != stats->file_priv)
+			if (ppgtt->file_priv != stats->file_priv)
 				continue;
 
 			if (obj->ring) /* XXX per-vma statistic */
@@ -515,6 +515,7 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long flags;
 	struct intel_crtc *crtc;
 	int ret;
@@ -534,6 +535,8 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 			seq_printf(m, "No flip due on pipe %c (plane %c)\n",
 				   pipe, plane);
 		} else {
+			u32 addr;
+
 			if (atomic_read(&work->pending) < INTEL_FLIP_COMPLETE) {
 				seq_printf(m, "Flip queued on pipe %c (plane %c)\n",
 					   pipe, plane);
@@ -541,23 +544,35 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 				seq_printf(m, "Flip pending (waiting for vsync) on pipe %c (plane %c)\n",
 					   pipe, plane);
 			}
+			if (work->flip_queued_ring) {
+				seq_printf(m, "Flip queued on %s at seqno %u, next seqno %u [current breadcrumb %u], completed? %d\n",
+					   work->flip_queued_ring->name,
+					   work->flip_queued_seqno,
+					   dev_priv->next_seqno,
+					   work->flip_queued_ring->get_seqno(work->flip_queued_ring, true),
+					   i915_seqno_passed(work->flip_queued_ring->get_seqno(work->flip_queued_ring, true),
+							     work->flip_queued_seqno));
+			} else
+				seq_printf(m, "Flip not associated with any ring\n");
+			seq_printf(m, "Flip queued on frame %d, (was ready on frame %d), now %d\n",
+				   work->flip_queued_vblank,
+				   work->flip_ready_vblank,
+				   drm_vblank_count(dev, crtc->pipe));
 			if (work->enable_stall_check)
 				seq_puts(m, "Stall check enabled, ");
 			else
 				seq_puts(m, "Stall check waiting for page flip ioctl, ");
 			seq_printf(m, "%d prepares\n", atomic_read(&work->pending));
 
-			if (work->old_fb_obj) {
-				struct drm_i915_gem_object *obj = work->old_fb_obj;
-				if (obj)
-					seq_printf(m, "Old framebuffer gtt_offset 0x%08lx\n",
-						   i915_gem_obj_ggtt_offset(obj));
-			}
+			if (INTEL_INFO(dev)->gen >= 4)
+				addr = I915_HI_DISPBASE(I915_READ(DSPSURF(crtc->plane)));
+			else
+				addr = I915_READ(DSPADDR(crtc->plane));
+			seq_printf(m, "Current scanout address 0x%08x\n", addr);
+
 			if (work->pending_flip_obj) {
-				struct drm_i915_gem_object *obj = work->pending_flip_obj;
-				if (obj)
-					seq_printf(m, "New framebuffer gtt_offset 0x%08lx\n",
-						   i915_gem_obj_ggtt_offset(obj));
+				seq_printf(m, "New framebuffer address 0x%08lx\n", (long)work->gtt_offset);
+				seq_printf(m, "MMIO update completed? %d\n",  addr == work->gtt_offset);
 			}
 		}
 		spin_unlock_irqrestore(&dev->event_lock, flags);
@@ -650,7 +665,6 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 	intel_runtime_pm_get(dev_priv);
 
 	if (IS_CHERRYVIEW(dev)) {
-		int i;
 		seq_printf(m, "Master Interrupt Control:\t%08x\n",
 			   I915_READ(GEN8_MASTER_IRQ));
 
@@ -662,7 +676,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 			   I915_READ(VLV_IIR_RW));
 		seq_printf(m, "Display IMR:\t%08x\n",
 			   I915_READ(VLV_IMR));
-		for_each_pipe(pipe)
+		for_each_pipe(dev_priv, pipe)
 			seq_printf(m, "Pipe %c stat:\t%08x\n",
 				   pipe_name(pipe),
 				   I915_READ(PIPESTAT(pipe)));
@@ -702,7 +716,13 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 				   i, I915_READ(GEN8_GT_IER(i)));
 		}
 
-		for_each_pipe(pipe) {
+		for_each_pipe(dev_priv, pipe) {
+			if (!intel_display_power_enabled(dev_priv,
+						POWER_DOMAIN_PIPE(pipe))) {
+				seq_printf(m, "Pipe %c power disabled\n",
+					   pipe_name(pipe));
+				continue;
+			}
 			seq_printf(m, "Pipe %c IMR:\t%08x\n",
 				   pipe_name(pipe),
 				   I915_READ(GEN8_DE_PIPE_IMR(pipe)));
@@ -743,7 +763,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 			   I915_READ(VLV_IIR_RW));
 		seq_printf(m, "Display IMR:\t%08x\n",
 			   I915_READ(VLV_IMR));
-		for_each_pipe(pipe)
+		for_each_pipe(dev_priv, pipe)
 			seq_printf(m, "Pipe %c stat:\t%08x\n",
 				   pipe_name(pipe),
 				   I915_READ(PIPESTAT(pipe)));
@@ -779,7 +799,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 			   I915_READ(IIR));
 		seq_printf(m, "Interrupt mask:      %08x\n",
 			   I915_READ(IMR));
-		for_each_pipe(pipe)
+		for_each_pipe(dev_priv, pipe)
 			seq_printf(m, "Pipe %c stat:         %08x\n",
 				   pipe_name(pipe),
 				   I915_READ(PIPESTAT(pipe)));
@@ -927,7 +947,7 @@ static ssize_t i915_error_state_read(struct file *file, char __user *userbuf,
 	ssize_t ret_count = 0;
 	int ret;
 
-	ret = i915_error_state_buf_init(&error_str, count, *pos);
+	ret = i915_error_state_buf_init(&error_str, to_i915(error_priv->dev), count, *pos);
 	if (ret)
 		return ret;
 
@@ -1024,6 +1044,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		u32 rpstat, cagf, reqf;
 		u32 rpupei, rpcurup, rpprevup;
 		u32 rpdownei, rpcurdown, rpprevdown;
+		u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask;
 		int max_freq;
 
 		/* RPSTAT1 is in the GT power well */
@@ -1061,12 +1082,21 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 		mutex_unlock(&dev->struct_mutex);
 
+		if (IS_GEN6(dev) || IS_GEN7(dev)) {
+			pm_ier = I915_READ(GEN6_PMIER);
+			pm_imr = I915_READ(GEN6_PMIMR);
+			pm_isr = I915_READ(GEN6_PMISR);
+			pm_iir = I915_READ(GEN6_PMIIR);
+			pm_mask = I915_READ(GEN6_PMINTRMSK);
+		} else {
+			pm_ier = I915_READ(GEN8_GT_IER(2));
+			pm_imr = I915_READ(GEN8_GT_IMR(2));
+			pm_isr = I915_READ(GEN8_GT_ISR(2));
+			pm_iir = I915_READ(GEN8_GT_IIR(2));
+			pm_mask = I915_READ(GEN6_PMINTRMSK);
+		}
 		seq_printf(m, "PM IER=0x%08x IMR=0x%08x ISR=0x%08x IIR=0x%08x, MASK=0x%08x\n",
-			   I915_READ(GEN6_PMIER),
-			   I915_READ(GEN6_PMIMR),
-			   I915_READ(GEN6_PMISR),
-			   I915_READ(GEN6_PMIIR),
-			   I915_READ(GEN6_PMINTRMSK));
+			   pm_ier, pm_imr, pm_isr, pm_iir, pm_mask);
 		seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
 		seq_printf(m, "Render p-state ratio: %d\n",
 			   (gt_perf_status & 0xff00) >> 8);
@@ -1365,7 +1395,7 @@ static int i915_drpc_info(struct seq_file *m, void *unused)
 
 	if (IS_VALLEYVIEW(dev))
 		return vlv_drpc_info(m);
-	else if (IS_GEN6(dev) || IS_GEN7(dev))
+	else if (INTEL_INFO(dev)->gen >= 6)
 		return gen6_drpc_info(m);
 	else
 		return ironlake_drpc_info(m);
@@ -1433,6 +1463,47 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 	return 0;
 }
 
+static int i915_fbc_fc_get(void *data, u64 *val)
+{
+	struct drm_device *dev = data;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (INTEL_INFO(dev)->gen < 7 || !HAS_FBC(dev))
+		return -ENODEV;
+
+	drm_modeset_lock_all(dev);
+	*val = dev_priv->fbc.false_color;
+	drm_modeset_unlock_all(dev);
+
+	return 0;
+}
+
+static int i915_fbc_fc_set(void *data, u64 val)
+{
+	struct drm_device *dev = data;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 reg;
+
+	if (INTEL_INFO(dev)->gen < 7 || !HAS_FBC(dev))
+		return -ENODEV;
+
+	drm_modeset_lock_all(dev);
+
+	reg = I915_READ(ILK_DPFC_CONTROL);
+	dev_priv->fbc.false_color = val;
+
+	I915_WRITE(ILK_DPFC_CONTROL, val ?
+		   (reg | FBC_CTL_FALSE_COLOR) :
+		   (reg & ~FBC_CTL_FALSE_COLOR));
+
+	drm_modeset_unlock_all(dev);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(i915_fbc_fc_fops,
+			i915_fbc_fc_get, i915_fbc_fc_set,
+			"%llu\n");
+
 static int i915_ips_status(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
@@ -1630,6 +1701,14 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 	return 0;
 }
 
+static void describe_ctx_ringbuf(struct seq_file *m,
+				 struct intel_ringbuffer *ringbuf)
+{
+	seq_printf(m, " (ringbuffer, space: %d, head: %u, tail: %u, last head: %d)",
+		   ringbuf->space, ringbuf->head, ringbuf->tail,
+		   ringbuf->last_retired_head);
+}
+
 static int i915_context_status(struct seq_file *m, void *unused)
 {
 	struct drm_info_node *node = m->private;
@@ -1656,16 +1735,168 @@ static int i915_context_status(struct seq_file *m, void *unused)
 	}
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
-		if (ctx->legacy_hw_ctx.rcs_state == NULL)
+		if (!i915.enable_execlists &&
+		    ctx->legacy_hw_ctx.rcs_state == NULL)
 			continue;
 
 		seq_puts(m, "HW context ");
 		describe_ctx(m, ctx);
-		for_each_ring(ring, dev_priv, i)
+		for_each_ring(ring, dev_priv, i) {
+			if (ring->default_context == ctx)
+				seq_printf(m, "(default context %s) ",
+					   ring->name);
+		}
+
+		if (i915.enable_execlists) {
+			seq_putc(m, '\n');
+			for_each_ring(ring, dev_priv, i) {
+				struct drm_i915_gem_object *ctx_obj =
+					ctx->engine[i].state;
+				struct intel_ringbuffer *ringbuf =
+					ctx->engine[i].ringbuf;
+
+				seq_printf(m, "%s: ", ring->name);
+				if (ctx_obj)
+					describe_obj(m, ctx_obj);
+				if (ringbuf)
+					describe_ctx_ringbuf(m, ringbuf);
+				seq_putc(m, '\n');
+			}
+		} else {
+			describe_obj(m, ctx->legacy_hw_ctx.rcs_state);
+		}
+
+		seq_putc(m, '\n');
+	}
+
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
+static int i915_dump_lrc(struct seq_file *m, void *unused)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring;
+	struct intel_context *ctx;
+	int ret, i;
+
+	if (!i915.enable_execlists) {
+		seq_printf(m, "Logical Ring Contexts are disabled\n");
+		return 0;
+	}
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	list_for_each_entry(ctx, &dev_priv->context_list, link) {
+		for_each_ring(ring, dev_priv, i) {
+			struct drm_i915_gem_object *ctx_obj = ctx->engine[i].state;
+
 			if (ring->default_context == ctx)
-				seq_printf(m, "(default context %s) ", ring->name);
+				continue;
+
+			if (ctx_obj) {
+				struct page *page = i915_gem_object_get_page(ctx_obj, 1);
+				uint32_t *reg_state = kmap_atomic(page);
+				int j;
+
+				seq_printf(m, "CONTEXT: %s %u\n", ring->name,
+						intel_execlists_ctx_id(ctx_obj));
+
+				for (j = 0; j < 0x600 / sizeof(u32) / 4; j += 4) {
+					seq_printf(m, "\t[0x%08lx] 0x%08x 0x%08x 0x%08x 0x%08x\n",
+					i915_gem_obj_ggtt_offset(ctx_obj) + 4096 + (j * 4),
+					reg_state[j], reg_state[j + 1],
+					reg_state[j + 2], reg_state[j + 3]);
+				}
+				kunmap_atomic(reg_state);
+
+				seq_putc(m, '\n');
+			}
+		}
+	}
+
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
+static int i915_execlists(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *)m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring;
+	u32 status_pointer;
+	u8 read_pointer;
+	u8 write_pointer;
+	u32 status;
+	u32 ctx_id;
+	struct list_head *cursor;
+	int ring_id, i;
+	int ret;
+
+	if (!i915.enable_execlists) {
+		seq_puts(m, "Logical Ring Contexts are disabled\n");
+		return 0;
+	}
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	for_each_ring(ring, dev_priv, ring_id) {
+		struct intel_ctx_submit_request *head_req = NULL;
+		int count = 0;
+		unsigned long flags;
+
+		seq_printf(m, "%s\n", ring->name);
+
+		status = I915_READ(RING_EXECLIST_STATUS(ring));
+		ctx_id = I915_READ(RING_EXECLIST_STATUS(ring) + 4);
+		seq_printf(m, "\tExeclist status: 0x%08X, context: %u\n",
+			   status, ctx_id);
+
+		status_pointer = I915_READ(RING_CONTEXT_STATUS_PTR(ring));
+		seq_printf(m, "\tStatus pointer: 0x%08X\n", status_pointer);
+
+		read_pointer = ring->next_context_status_buffer;
+		write_pointer = status_pointer & 0x07;
+		if (read_pointer > write_pointer)
+			write_pointer += 6;
+		seq_printf(m, "\tRead pointer: 0x%08X, write pointer 0x%08X\n",
+			   read_pointer, write_pointer);
+
+		for (i = 0; i < 6; i++) {
+			status = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + 8*i);
+			ctx_id = I915_READ(RING_CONTEXT_STATUS_BUF(ring) + 8*i + 4);
+
+			seq_printf(m, "\tStatus buffer %d: 0x%08X, context: %u\n",
+				   i, status, ctx_id);
+		}
+
+		spin_lock_irqsave(&ring->execlist_lock, flags);
+		list_for_each(cursor, &ring->execlist_queue)
+			count++;
+		head_req = list_first_entry_or_null(&ring->execlist_queue,
+				struct intel_ctx_submit_request, execlist_link);
+		spin_unlock_irqrestore(&ring->execlist_lock, flags);
+
+		seq_printf(m, "\t%d requests in queue\n", count);
+		if (head_req) {
+			struct drm_i915_gem_object *ctx_obj;
+
+			ctx_obj = head_req->ctx->engine[ring_id].state;
+			seq_printf(m, "\tHead request id: %u\n",
+				   intel_execlists_ctx_id(ctx_obj));
+			seq_printf(m, "\tHead request tail: %u\n",
+				   head_req->tail);
+		}
 
-		describe_obj(m, ctx->legacy_hw_ctx.rcs_state);
 		seq_putc(m, '\n');
 	}
 
@@ -1774,7 +2005,13 @@ static int per_file_ctx(int id, void *ptr, void *data)
 {
 	struct intel_context *ctx = ptr;
 	struct seq_file *m = data;
-	struct i915_hw_ppgtt *ppgtt = ctx_to_ppgtt(ctx);
+	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt;
+
+	if (!ppgtt) {
+		seq_printf(m, "  no ppgtt for context %d\n",
+			   ctx->user_handle);
+		return 0;
+	}
 
 	if (i915_gem_context_is_default(ctx))
 		seq_puts(m, "  default context:\n");
@@ -1834,8 +2071,7 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev)
 		seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd_offset);
 
 		ppgtt->debug_dump(ppgtt, m);
-	} else
-		return;
+	}
 
 	list_for_each_entry_reverse(file, &dev->filelist, lhead) {
 		struct drm_i915_file_private *file_priv = file->driver_priv;
@@ -2406,6 +2642,40 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 	return 0;
 }
 
+static int i915_wa_registers(struct seq_file *m, void *unused)
+{
+	int i;
+	int ret;
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	intel_runtime_pm_get(dev_priv);
+
+	seq_printf(m, "Workarounds applied: %d\n", dev_priv->num_wa_regs);
+	for (i = 0; i < dev_priv->num_wa_regs; ++i) {
+		u32 addr, mask;
+
+		addr = dev_priv->intel_wa_regs[i].addr;
+		mask = dev_priv->intel_wa_regs[i].mask;
+		dev_priv->intel_wa_regs[i].value = I915_READ(addr) | mask;
+		if (dev_priv->intel_wa_regs[i].addr)
+			seq_printf(m, "0x%X: 0x%08X, mask: 0x%08X\n",
+				   dev_priv->intel_wa_regs[i].addr,
+				   dev_priv->intel_wa_regs[i].value,
+				   dev_priv->intel_wa_regs[i].mask);
+	}
+
+	intel_runtime_pm_put(dev_priv);
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
 struct pipe_crc_info {
 	const char *name;
 	struct drm_device *dev;
@@ -2667,8 +2937,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_device *dev, enum pipe pipe,
 	*source = INTEL_PIPE_CRC_SOURCE_PIPE;
 
 	drm_modeset_lock_all(dev);
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		if (!encoder->base.crtc)
 			continue;
 
@@ -3557,9 +3826,6 @@ i915_drop_caches_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_i915_gem_object *obj, *next;
-	struct i915_address_space *vm;
-	struct i915_vma *vma, *x;
 	int ret;
 
 	DRM_DEBUG("Dropping caches: 0x%08llx\n", val);
@@ -3579,29 +3845,11 @@ i915_drop_caches_set(void *data, u64 val)
 	if (val & (DROP_RETIRE | DROP_ACTIVE))
 		i915_gem_retire_requests(dev);
 
-	if (val & DROP_BOUND) {
-		list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
-			list_for_each_entry_safe(vma, x, &vm->inactive_list,
-						 mm_list) {
-				if (vma->pin_count)
-					continue;
+	if (val & DROP_BOUND)
+		i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_BOUND);
 
-				ret = i915_vma_unbind(vma);
-				if (ret)
-					goto unlock;
-			}
-		}
-	}
-
-	if (val & DROP_UNBOUND) {
-		list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list,
-					 global_list)
-			if (obj->pages_pin_count == 0) {
-				ret = i915_gem_object_put_pages(obj);
-				if (ret)
-					goto unlock;
-			}
-	}
+	if (val & DROP_UNBOUND)
+		i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_UNBOUND);
 
 unlock:
 	mutex_unlock(&dev->struct_mutex);
@@ -3923,6 +4171,8 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_opregion", i915_opregion, 0},
 	{"i915_gem_framebuffer", i915_gem_framebuffer_info, 0},
 	{"i915_context_status", i915_context_status, 0},
+	{"i915_dump_lrc", i915_dump_lrc, 0},
+	{"i915_execlists", i915_execlists, 0},
 	{"i915_gen6_forcewake_count", i915_gen6_forcewake_count_info, 0},
 	{"i915_swizzle_info", i915_swizzle_info, 0},
 	{"i915_ppgtt_info", i915_ppgtt_info, 0},
@@ -3936,6 +4186,7 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_semaphore_status", i915_semaphore_status, 0},
 	{"i915_shared_dplls_info", i915_shared_dplls_info, 0},
 	{"i915_dp_mst_info", i915_dp_mst_info, 0},
+	{"i915_wa_registers", i915_wa_registers, 0},
 };
 #define I915_DEBUGFS_ENTRIES ARRAY_SIZE(i915_debugfs_list)
 
@@ -3957,6 +4208,7 @@ static const struct i915_debugfs_files {
 	{"i915_pri_wm_latency", &i915_pri_wm_latency_fops},
 	{"i915_spr_wm_latency", &i915_spr_wm_latency_fops},
 	{"i915_cur_wm_latency", &i915_cur_wm_latency_fops},
+	{"i915_fbc_false_color", &i915_fbc_fc_fops},
 };
 
 void intel_display_crc_init(struct drm_device *dev)
@@ -3964,7 +4216,7 @@ void intel_display_crc_init(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum pipe pipe;
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
 
 		pipe_crc->opened = false;
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 9933c26017ed..1403b01e8216 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -28,9 +28,11 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/async.h>
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_legacy.h>
 #include "intel_drv.h"
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
@@ -196,7 +198,7 @@ static int i915_initialize(struct drm_device *dev, drm_i915_init_t *init)
 	struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
 	int ret;
 
-	master_priv->sarea = drm_getsarea(dev);
+	master_priv->sarea = drm_legacy_getsarea(dev);
 	if (master_priv->sarea) {
 		master_priv->sarea_priv = (drm_i915_sarea_t *)
 			((u8 *)master_priv->sarea->handle + init->sarea_priv_offset);
@@ -999,7 +1001,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
 		value = HAS_WT(dev);
 		break;
 	case I915_PARAM_HAS_ALIASING_PPGTT:
-		value = dev_priv->mm.aliasing_ppgtt || USES_FULL_PPGTT(dev);
+		value = USES_PPGTT(dev);
 		break;
 	case I915_PARAM_HAS_WAIT_TIMEOUT:
 		value = 1;
@@ -1355,8 +1357,6 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	if (ret)
 		goto cleanup_irq;
 
-	INIT_WORK(&dev_priv->console_resume_work, intel_console_resume);
-
 	intel_modeset_gem_init(dev);
 
 	/* Always safe in the mode setting case. */
@@ -1382,7 +1382,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	 * scanning against hotplug events. Hence do this first and ignore the
 	 * tiny window where we will loose hotplug notifactions.
 	 */
-	intel_fbdev_initial_config(dev);
+	async_schedule(intel_fbdev_initial_config, dev_priv);
 
 	drm_kms_helper_poll_init(dev);
 
@@ -1393,7 +1393,6 @@ cleanup_gem:
 	i915_gem_cleanup_ringbuffer(dev);
 	i915_gem_context_fini(dev);
 	mutex_unlock(&dev->struct_mutex);
-	WARN_ON(dev_priv->mm.aliasing_ppgtt);
 cleanup_irq:
 	drm_irq_uninstall(dev);
 cleanup_gem_stolen:
@@ -1536,10 +1535,10 @@ static void intel_device_info_runtime_init(struct drm_device *dev)
 	info = (struct intel_device_info *)&dev_priv->info;
 
 	if (IS_VALLEYVIEW(dev))
-		for_each_pipe(pipe)
+		for_each_pipe(dev_priv, pipe)
 			info->num_sprites[pipe] = 2;
 	else
-		for_each_pipe(pipe)
+		for_each_pipe(dev_priv, pipe)
 			info->num_sprites[pipe] = 1;
 
 	if (i915.disable_display) {
@@ -1608,9 +1607,10 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	dev->dev_private = dev_priv;
 	dev_priv->dev = dev;
 
-	/* copy initial configuration to dev_priv->info */
+	/* Setup the write-once "constant" device info */
 	device_info = (struct intel_device_info *)&dev_priv->info;
-	*device_info = *info;
+	memcpy(device_info, info, sizeof(dev_priv->info));
+	device_info->device_id = dev->pdev->device;
 
 	spin_lock_init(&dev_priv->irq_lock);
 	spin_lock_init(&dev_priv->gpu_error.lock);
@@ -1822,7 +1822,7 @@ out_mtrrfree:
 	arch_phys_wc_del(dev_priv->gtt.mtrr);
 	io_mapping_free(dev_priv->gtt.mappable);
 out_gtt:
-	dev_priv->gtt.base.cleanup(&dev_priv->gtt.base);
+	i915_global_gtt_cleanup(dev);
 out_regs:
 	intel_uncore_fini(dev);
 	pci_iounmap(dev->pdev, dev_priv->regs);
@@ -1869,7 +1869,6 @@ int i915_driver_unload(struct drm_device *dev)
 	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
 		intel_fbdev_fini(dev);
 		intel_modeset_cleanup(dev);
-		cancel_work_sync(&dev_priv->console_resume_work);
 
 		/*
 		 * free the memory space allocated for the child device
@@ -1902,7 +1901,6 @@ int i915_driver_unload(struct drm_device *dev)
 		mutex_lock(&dev->struct_mutex);
 		i915_gem_cleanup_ringbuffer(dev);
 		i915_gem_context_fini(dev);
-		WARN_ON(dev_priv->mm.aliasing_ppgtt);
 		mutex_unlock(&dev->struct_mutex);
 		i915_gem_cleanup_stolen(dev);
 
@@ -1910,8 +1908,6 @@ int i915_driver_unload(struct drm_device *dev)
 			i915_free_hws(dev);
 	}
 
-	WARN_ON(!list_empty(&dev_priv->vm_list));
-
 	drm_vblank_cleanup(dev);
 
 	intel_teardown_gmbus(dev);
@@ -1921,7 +1917,7 @@ int i915_driver_unload(struct drm_device *dev)
 	destroy_workqueue(dev_priv->wq);
 	pm_qos_remove_request(&dev_priv->pm_qos);
 
-	dev_priv->gtt.base.cleanup(&dev_priv->gtt.base);
+	i915_global_gtt_cleanup(dev);
 
 	intel_uncore_fini(dev);
 	if (dev_priv->regs != NULL)
@@ -1986,6 +1982,9 @@ void i915_driver_preclose(struct drm_device *dev, struct drm_file *file)
 	i915_gem_context_close(dev, file);
 	i915_gem_release(dev, file);
 	mutex_unlock(&dev->struct_mutex);
+
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		intel_modeset_preclose(dev, file);
 }
 
 void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index e27cdbe9d524..055d5e7fbf12 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -481,6 +481,10 @@ bool i915_semaphore_is_enabled(struct drm_device *dev)
 	if (i915.semaphores >= 0)
 		return i915.semaphores;
 
+	/* TODO: make semaphores and Execlists play nicely together */
+	if (i915.enable_execlists)
+		return false;
+
 	/* Until we get further testing... */
 	if (IS_GEN8(dev))
 		return false;
@@ -524,6 +528,10 @@ static void intel_suspend_encoders(struct drm_i915_private *dev_priv)
 	drm_modeset_unlock_all(dev);
 }
 
+static int intel_suspend_complete(struct drm_i915_private *dev_priv);
+static int intel_resume_prepare(struct drm_i915_private *dev_priv,
+				bool rpm_resume);
+
 static int i915_drm_freeze(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -591,9 +599,7 @@ static int i915_drm_freeze(struct drm_device *dev)
 	intel_uncore_forcewake_reset(dev, false);
 	intel_opregion_fini(dev);
 
-	console_lock();
-	intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED);
-	console_unlock();
+	intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED, true);
 
 	dev_priv->suspend_count++;
 
@@ -632,30 +638,20 @@ int i915_suspend(struct drm_device *dev, pm_message_t state)
 	return 0;
 }
 
-void intel_console_resume(struct work_struct *work)
-{
-	struct drm_i915_private *dev_priv =
-		container_of(work, struct drm_i915_private,
-			     console_resume_work);
-	struct drm_device *dev = dev_priv->dev;
-
-	console_lock();
-	intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING);
-	console_unlock();
-}
-
 static int i915_drm_thaw_early(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
 
-	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
-		hsw_disable_pc8(dev_priv);
+	ret = intel_resume_prepare(dev_priv, false);
+	if (ret)
+		DRM_ERROR("Resume prepare failed: %d,Continuing resume\n", ret);
 
 	intel_uncore_early_sanitize(dev, true);
 	intel_uncore_sanitize(dev);
 	intel_power_domains_init_hw(dev_priv);
 
-	return 0;
+	return ret;
 }
 
 static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
@@ -714,17 +710,7 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 
 	intel_opregion_init(dev);
 
-	/*
-	 * The console lock can be pretty contented on resume due
-	 * to all the printk activity.  Try to keep it out of the hot
-	 * path of resume if possible.
-	 */
-	if (console_trylock()) {
-		intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING);
-		console_unlock();
-	} else {
-		schedule_work(&dev_priv->console_resume_work);
-	}
+	intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING, false);
 
 	mutex_lock(&dev_priv->modeset_restore_lock);
 	dev_priv->modeset_restore = MODESET_DONE;
@@ -858,7 +844,13 @@ int i915_reset(struct drm_device *dev)
 			!dev_priv->ums.mm_suspended) {
 		dev_priv->ums.mm_suspended = 0;
 
+		/* Used to prevent gem_check_wedged returning -EAGAIN during gpu reset */
+		dev_priv->gpu_error.reload_in_reset = true;
+
 		ret = i915_gem_init_hw(dev);
+
+		dev_priv->gpu_error.reload_in_reset = false;
+
 		mutex_unlock(&dev->struct_mutex);
 		if (ret) {
 			DRM_ERROR("Failed hw init on reset %d\n", ret);
@@ -879,8 +871,6 @@ int i915_reset(struct drm_device *dev)
 		 */
 		if (INTEL_INFO(dev)->gen > 5)
 			intel_reset_gt_powersave(dev);
-
-		intel_hpd_init(dev);
 	} else {
 		mutex_unlock(&dev->struct_mutex);
 	}
@@ -941,6 +931,7 @@ static int i915_pm_suspend_late(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
+	int ret;
 
 	/*
 	 * We have a suspedn ordering issue with the snd-hda driver also
@@ -954,13 +945,16 @@ static int i915_pm_suspend_late(struct device *dev)
 	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	if (IS_HASWELL(drm_dev) || IS_BROADWELL(drm_dev))
-		hsw_enable_pc8(dev_priv);
+	ret = intel_suspend_complete(dev_priv);
 
-	pci_disable_device(pdev);
-	pci_set_power_state(pdev, PCI_D3hot);
+	if (ret)
+		DRM_ERROR("Suspend complete failed: %d\n", ret);
+	else {
+		pci_disable_device(pdev);
+		pci_set_power_state(pdev, PCI_D3hot);
+	}
 
-	return 0;
+	return ret;
 }
 
 static int i915_pm_resume_early(struct device *dev)
@@ -1016,23 +1010,26 @@ static int i915_pm_poweroff(struct device *dev)
 	return i915_drm_freeze(drm_dev);
 }
 
-static int hsw_runtime_suspend(struct drm_i915_private *dev_priv)
+static int hsw_suspend_complete(struct drm_i915_private *dev_priv)
 {
 	hsw_enable_pc8(dev_priv);
 
 	return 0;
 }
 
-static int snb_runtime_resume(struct drm_i915_private *dev_priv)
+static int snb_resume_prepare(struct drm_i915_private *dev_priv,
+				bool rpm_resume)
 {
 	struct drm_device *dev = dev_priv->dev;
 
-	intel_init_pch_refclk(dev);
+	if (rpm_resume)
+		intel_init_pch_refclk(dev);
 
 	return 0;
 }
 
-static int hsw_runtime_resume(struct drm_i915_private *dev_priv)
+static int hsw_resume_prepare(struct drm_i915_private *dev_priv,
+				bool rpm_resume)
 {
 	hsw_disable_pc8(dev_priv);
 
@@ -1328,7 +1325,7 @@ static void vlv_check_no_gt_access(struct drm_i915_private *dev_priv)
 	I915_WRITE(VLV_GTLC_PW_STATUS, VLV_GTLC_ALLOWWAKEERR);
 }
 
-static int vlv_runtime_suspend(struct drm_i915_private *dev_priv)
+static int vlv_suspend_complete(struct drm_i915_private *dev_priv)
 {
 	u32 mask;
 	int err;
@@ -1368,7 +1365,8 @@ err1:
 	return err;
 }
 
-static int vlv_runtime_resume(struct drm_i915_private *dev_priv)
+static int vlv_resume_prepare(struct drm_i915_private *dev_priv,
+				bool rpm_resume)
 {
 	struct drm_device *dev = dev_priv->dev;
 	int err;
@@ -1393,8 +1391,10 @@ static int vlv_runtime_resume(struct drm_i915_private *dev_priv)
 
 	vlv_check_no_gt_access(dev_priv);
 
-	intel_init_clock_gating(dev);
-	i915_gem_restore_fences(dev);
+	if (rpm_resume) {
+		intel_init_clock_gating(dev);
+		i915_gem_restore_fences(dev);
+	}
 
 	return ret;
 }
@@ -1409,7 +1409,9 @@ static int intel_runtime_suspend(struct device *device)
 	if (WARN_ON_ONCE(!(dev_priv->rps.enabled && intel_enable_rc6(dev))))
 		return -ENODEV;
 
-	WARN_ON(!HAS_RUNTIME_PM(dev));
+	if (WARN_ON_ONCE(!HAS_RUNTIME_PM(dev)))
+		return -ENODEV;
+
 	assert_force_wake_inactive(dev_priv);
 
 	DRM_DEBUG_KMS("Suspending device\n");
@@ -1446,17 +1448,7 @@ static int intel_runtime_suspend(struct device *device)
 	cancel_work_sync(&dev_priv->rps.work);
 	intel_runtime_pm_disable_interrupts(dev);
 
-	if (IS_GEN6(dev)) {
-		ret = 0;
-	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
-		ret = hsw_runtime_suspend(dev_priv);
-	} else if (IS_VALLEYVIEW(dev)) {
-		ret = vlv_runtime_suspend(dev_priv);
-	} else {
-		ret = -ENODEV;
-		WARN_ON(1);
-	}
-
+	ret = intel_suspend_complete(dev_priv);
 	if (ret) {
 		DRM_ERROR("Runtime suspend failed, disabling it (%d)\n", ret);
 		intel_runtime_pm_restore_interrupts(dev);
@@ -1468,13 +1460,29 @@ static int intel_runtime_suspend(struct device *device)
 	dev_priv->pm.suspended = true;
 
 	/*
-	 * current versions of firmware which depend on this opregion
-	 * notification have repurposed the D1 definition to mean
-	 * "runtime suspended" vs. what you would normally expect (D3)
-	 * to distinguish it from notifications that might be sent
-	 * via the suspend path.
+	 * FIXME: We really should find a document that references the arguments
+	 * used below!
 	 */
-	intel_opregion_notify_adapter(dev, PCI_D1);
+	if (IS_HASWELL(dev)) {
+		/*
+		 * current versions of firmware which depend on this opregion
+		 * notification have repurposed the D1 definition to mean
+		 * "runtime suspended" vs. what you would normally expect (D3)
+		 * to distinguish it from notifications that might be sent via
+		 * the suspend path.
+		 */
+		intel_opregion_notify_adapter(dev, PCI_D1);
+	} else {
+		/*
+		 * On Broadwell, if we use PCI_D1 the PCH DDI ports will stop
+		 * being detected, and the call we do at intel_runtime_resume()
+		 * won't be able to restore them. Since PCI_D3hot matches the
+		 * actual specification and appears to be working, use it. Let's
+		 * assume the other non-Haswell platforms will stay the same as
+		 * Broadwell.
+		 */
+		intel_opregion_notify_adapter(dev, PCI_D3hot);
+	}
 
 	DRM_DEBUG_KMS("Device suspended\n");
 	return 0;
@@ -1487,24 +1495,15 @@ static int intel_runtime_resume(struct device *device)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
-	WARN_ON(!HAS_RUNTIME_PM(dev));
+	if (WARN_ON_ONCE(!HAS_RUNTIME_PM(dev)))
+		return -ENODEV;
 
 	DRM_DEBUG_KMS("Resuming device\n");
 
 	intel_opregion_notify_adapter(dev, PCI_D0);
 	dev_priv->pm.suspended = false;
 
-	if (IS_GEN6(dev)) {
-		ret = snb_runtime_resume(dev_priv);
-	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
-		ret = hsw_runtime_resume(dev_priv);
-	} else if (IS_VALLEYVIEW(dev)) {
-		ret = vlv_runtime_resume(dev_priv);
-	} else {
-		WARN_ON(1);
-		ret = -ENODEV;
-	}
-
+	ret = intel_resume_prepare(dev_priv, true);
 	/*
 	 * No point of rolling back things in case of an error, as the best
 	 * we can do is to hope that things will still work (and disable RPM).
@@ -1523,6 +1522,48 @@ static int intel_runtime_resume(struct device *device)
 	return ret;
 }
 
+/*
+ * This function implements common functionality of runtime and system
+ * suspend sequence.
+ */
+static int intel_suspend_complete(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	int ret;
+
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		ret = hsw_suspend_complete(dev_priv);
+	else if (IS_VALLEYVIEW(dev))
+		ret = vlv_suspend_complete(dev_priv);
+	else
+		ret = 0;
+
+	return ret;
+}
+
+/*
+ * This function implements common functionality of runtime and system
+ * resume sequence. Variable rpm_resume used for implementing different
+ * code paths.
+ */
+static int intel_resume_prepare(struct drm_i915_private *dev_priv,
+				bool rpm_resume)
+{
+	struct drm_device *dev = dev_priv->dev;
+	int ret;
+
+	if (IS_GEN6(dev))
+		ret = snb_resume_prepare(dev_priv, rpm_resume);
+	else if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		ret = hsw_resume_prepare(dev_priv, rpm_resume);
+	else if (IS_VALLEYVIEW(dev))
+		ret = vlv_resume_prepare(dev_priv, rpm_resume);
+	else
+		ret = 0;
+
+	return ret;
+}
+
 static const struct dev_pm_ops i915_pm_ops = {
 	.suspend = i915_pm_suspend,
 	.suspend_late = i915_pm_suspend_late,
@@ -1572,6 +1613,7 @@ static struct drm_driver driver = {
 	.lastclose = i915_driver_lastclose,
 	.preclose = i915_driver_preclose,
 	.postclose = i915_driver_postclose,
+	.set_busid = drm_pci_set_busid,
 
 	/* Used in place of i915_pm_ops for non-DRIVER_MODESET */
 	.suspend = i915_suspend,
@@ -1663,6 +1705,8 @@ static void __exit i915_exit(void)
 module_init(i915_init);
 module_exit(i915_exit);
 
-MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_AUTHOR("Tungsten Graphics, Inc.");
+MODULE_AUTHOR("Intel Corporation");
+
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 3524306d8cfb..16a6f6d187a1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -35,11 +35,15 @@
 #include "i915_reg.h"
 #include "intel_bios.h"
 #include "intel_ringbuffer.h"
+#include "intel_lrc.h"
 #include "i915_gem_gtt.h"
+#include "i915_gem_render_state.h"
 #include <linux/io-mapping.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 #include <drm/intel-gtt.h>
+#include <drm/drm_legacy.h> /* for struct drm_dma_handle */
+#include <drm/drm_gem.h>
 #include <linux/backlight.h>
 #include <linux/hashtable.h>
 #include <linux/intel-iommu.h>
@@ -49,11 +53,9 @@
 /* General customization:
  */
 
-#define DRIVER_AUTHOR		"Tungsten Graphics, Inc."
-
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20140725"
+#define DRIVER_DATE		"20140905"
 
 enum pipe {
 	INVALID_PIPE = -1,
@@ -162,7 +164,10 @@ enum hpd_pin {
 	 I915_GEM_DOMAIN_INSTRUCTION | \
 	 I915_GEM_DOMAIN_VERTEX)
 
-#define for_each_pipe(p) for ((p) = 0; (p) < INTEL_INFO(dev)->num_pipes; (p)++)
+#define for_each_pipe(__dev_priv, __p) \
+	for ((__p) = 0; (__p) < INTEL_INFO(__dev_priv)->num_pipes; (__p)++)
+#define for_each_plane(pipe, p) \
+	for ((p) = 0; (p) < INTEL_INFO(dev)->num_sprites[(pipe)] + 1; (p)++)
 #define for_each_sprite(p, s) for ((s) = 0; (s) < INTEL_INFO(dev)->num_sprites[(p)]; (s)++)
 
 #define for_each_crtc(dev, crtc) \
@@ -171,6 +176,11 @@ enum hpd_pin {
 #define for_each_intel_crtc(dev, intel_crtc) \
 	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head)
 
+#define for_each_intel_encoder(dev, intel_encoder)		\
+	list_for_each_entry(intel_encoder,			\
+			    &(dev)->mode_config.encoder_list,	\
+			    base.head)
+
 #define for_each_encoder_on_crtc(dev, __crtc, intel_encoder) \
 	list_for_each_entry((intel_encoder), &(dev)->mode_config.encoder_list, base.head) \
 		if ((intel_encoder)->base.crtc == (__crtc))
@@ -198,10 +208,13 @@ enum intel_dpll_id {
 #define I915_NUM_PLLS 2
 
 struct intel_dpll_hw_state {
+	/* i9xx, pch plls */
 	uint32_t dpll;
 	uint32_t dpll_md;
 	uint32_t fp0;
 	uint32_t fp1;
+
+	/* hsw, bdw */
 	uint32_t wrpll;
 };
 
@@ -277,8 +290,10 @@ struct intel_opregion {
 struct intel_overlay;
 struct intel_overlay_error_state;
 
+struct drm_local_map;
+
 struct drm_i915_master_private {
-	drm_local_map_t *sarea;
+	struct drm_local_map *sarea;
 	struct _drm_i915_sarea *sarea_priv;
 };
 #define I915_FENCE_REG_NONE -1
@@ -388,6 +403,7 @@ struct drm_i915_error_state {
 		pid_t pid;
 		char comm[TASK_COMM_LEN];
 	} ring[I915_NUM_RINGS];
+
 	struct drm_i915_error_buffer {
 		u32 size;
 		u32 name;
@@ -406,6 +422,7 @@ struct drm_i915_error_state {
 	} **active_bo, **pinned_bo;
 
 	u32 *active_bo_count, *pinned_bo_count;
+	u32 vm_count;
 };
 
 struct intel_connector;
@@ -551,6 +568,7 @@ struct intel_uncore {
 
 struct intel_device_info {
 	u32 display_mmio_offset;
+	u16 device_id;
 	u8 num_pipes:3;
 	u8 num_sprites[I915_MAX_PIPES];
 	u8 gen;
@@ -615,13 +633,21 @@ struct intel_context {
 	uint8_t remap_slice;
 	struct drm_i915_file_private *file_priv;
 	struct i915_ctx_hang_stats hang_stats;
-	struct i915_address_space *vm;
+	struct i915_hw_ppgtt *ppgtt;
 
+	/* Legacy ring buffer submission */
 	struct {
 		struct drm_i915_gem_object *rcs_state;
 		bool initialized;
 	} legacy_hw_ctx;
 
+	/* Execlists */
+	bool rcs_initialized;
+	struct {
+		struct drm_i915_gem_object *state;
+		struct intel_ringbuffer *ringbuf;
+	} engine[I915_NUM_RINGS];
+
 	struct list_head link;
 };
 
@@ -635,6 +661,8 @@ struct i915_fbc {
 	struct drm_mm_node compressed_fb;
 	struct drm_mm_node *compressed_llb;
 
+	bool false_color;
+
 	struct intel_fbc_work {
 		struct delayed_work work;
 		struct drm_crtc *crtc;
@@ -688,6 +716,7 @@ enum intel_sbi_destination {
 #define QUIRK_LVDS_SSC_DISABLE (1<<1)
 #define QUIRK_INVERT_BRIGHTNESS (1<<2)
 #define QUIRK_BACKLIGHT_PRESENT (1<<3)
+#define QUIRK_PIPEB_FORCE (1<<4)
 
 struct intel_fbdev;
 struct intel_fbc_work;
@@ -1147,6 +1176,7 @@ struct i915_gem_mm {
 };
 
 struct drm_i915_error_state_buf {
+	struct drm_i915_private *i915;
 	unsigned bytes;
 	unsigned size;
 	int err;
@@ -1219,6 +1249,9 @@ struct i915_gpu_error {
 
 	/* For missed irq/seqno simulation. */
 	unsigned int test_irq_rings;
+
+	/* Used to prevent gem_check_wedged returning -EAGAIN during gpu reset   */
+	bool reload_in_reset;
 };
 
 enum modeset_restore {
@@ -1228,6 +1261,12 @@ enum modeset_restore {
 };
 
 struct ddi_vbt_port_info {
+	/*
+	 * This is an index in the HDMI/DVI DDI buffer translation table.
+	 * The special value HDMI_LEVEL_SHIFT_UNKNOWN means the VBT didn't
+	 * populate this field.
+	 */
+#define HDMI_LEVEL_SHIFT_UNKNOWN	0xff
 	uint8_t hdmi_level_shift;
 
 	uint8_t supports_dvi:1;
@@ -1421,7 +1460,7 @@ struct drm_i915_private {
 	struct drm_i915_gem_object *semaphore_obj;
 	uint32_t last_seqno, next_seqno;
 
-	drm_dma_handle_t *status_page_dmah;
+	struct drm_dma_handle *status_page_dmah;
 	struct resource mch_res;
 
 	/* protects the irq masks */
@@ -1475,6 +1514,9 @@ struct drm_i915_private {
 	/* LVDS info */
 	bool no_aux_handshake;
 
+	/* protects panel power sequencer state */
+	struct mutex pps_mutex;
+
 	struct drm_i915_fence_reg fence_regs[I915_MAX_NUM_FENCES]; /* assume 965 */
 	int fence_reg_start; /* 4 if userland hasn't ioctl'd us yet */
 	int num_fence_regs; /* 8 on pre-965, 16 otherwise */
@@ -1526,6 +1568,20 @@ struct drm_i915_private {
 	struct intel_shared_dpll shared_dplls[I915_NUM_PLLS];
 	int dpio_phy_iosf_port[I915_NUM_PHYS_VLV];
 
+	/*
+	 * workarounds are currently applied at different places and
+	 * changes are being done to consolidate them so exact count is
+	 * not clear at this point, use a max value for now.
+	 */
+#define I915_MAX_WA_REGS  16
+	struct {
+		u32 addr;
+		u32 value;
+		/* bitmask representing WA bits */
+		u32 mask;
+	} intel_wa_regs[I915_MAX_WA_REGS];
+	u32 num_wa_regs;
+
 	/* Reclocking support */
 	bool render_reclock_avail;
 	bool lvds_downclock_avail;
@@ -1561,14 +1617,9 @@ struct drm_i915_private {
 #ifdef CONFIG_DRM_I915_FBDEV
 	/* list of fbdev register on this device */
 	struct intel_fbdev *fbdev;
+	struct work_struct fbdev_suspend_work;
 #endif
 
-	/*
-	 * The console may be contended at resume, but we don't
-	 * want it to block on it.
-	 */
-	struct work_struct console_resume_work;
-
 	struct drm_property *broadcast_rgb_property;
 	struct drm_property *force_audio_property;
 
@@ -1614,12 +1665,28 @@ struct drm_i915_private {
 	 */
 	struct workqueue_struct *dp_wq;
 
+	uint32_t bios_vgacntr;
+
 	/* Old dri1 support infrastructure, beware the dragons ya fools entering
 	 * here! */
 	struct i915_dri1_state dri1;
 	/* Old ums support infrastructure, same warning applies. */
 	struct i915_ums_state ums;
 
+	/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
+	struct {
+		int (*do_execbuf)(struct drm_device *dev, struct drm_file *file,
+				  struct intel_engine_cs *ring,
+				  struct intel_context *ctx,
+				  struct drm_i915_gem_execbuffer2 *args,
+				  struct list_head *vmas,
+				  struct drm_i915_gem_object *batch_obj,
+				  u64 exec_start, u32 flags);
+		int (*init_rings)(struct drm_device *dev);
+		void (*cleanup_ring)(struct intel_engine_cs *ring);
+		void (*stop_ring)(struct intel_engine_cs *ring);
+	} gt;
+
 	/*
 	 * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch
 	 * will be rejected. Instead look for a better place.
@@ -1761,13 +1828,6 @@ struct drm_i915_gem_object {
 	 * Only honoured if hardware has relevant pte bit
 	 */
 	unsigned long gt_ro:1;
-
-	/*
-	 * Is the GPU currently using a fence to access this buffer,
-	 */
-	unsigned int pending_fenced_gpu_access:1;
-	unsigned int fenced_gpu_access:1;
-
 	unsigned int cache_level:3;
 
 	unsigned int has_aliasing_ppgtt_mapping:1;
@@ -1805,7 +1865,7 @@ struct drm_i915_gem_object {
 	struct drm_file *pin_filp;
 
 	/** for phy allocated objects */
-	drm_dma_handle_t *phys_handle;
+	struct drm_dma_handle *phys_handle;
 
 	union {
 		struct i915_gem_userptr {
@@ -1971,51 +2031,63 @@ struct drm_i915_cmd_table {
 	int count;
 };
 
-#define INTEL_INFO(dev)	(&to_i915(dev)->info)
-
-#define IS_I830(dev)		((dev)->pdev->device == 0x3577)
-#define IS_845G(dev)		((dev)->pdev->device == 0x2562)
+/* Note that the (struct drm_i915_private *) cast is just to shut up gcc. */
+#define __I915__(p) ({ \
+	struct drm_i915_private *__p; \
+	if (__builtin_types_compatible_p(typeof(*p), struct drm_i915_private)) \
+		__p = (struct drm_i915_private *)p; \
+	else if (__builtin_types_compatible_p(typeof(*p), struct drm_device)) \
+		__p = to_i915((struct drm_device *)p); \
+	else \
+		BUILD_BUG(); \
+	__p; \
+})
+#define INTEL_INFO(p) 	(&__I915__(p)->info)
+#define INTEL_DEVID(p)	(INTEL_INFO(p)->device_id)
+
+#define IS_I830(dev)		(INTEL_DEVID(dev) == 0x3577)
+#define IS_845G(dev)		(INTEL_DEVID(dev) == 0x2562)
 #define IS_I85X(dev)		(INTEL_INFO(dev)->is_i85x)
-#define IS_I865G(dev)		((dev)->pdev->device == 0x2572)
+#define IS_I865G(dev)		(INTEL_DEVID(dev) == 0x2572)
 #define IS_I915G(dev)		(INTEL_INFO(dev)->is_i915g)
-#define IS_I915GM(dev)		((dev)->pdev->device == 0x2592)
-#define IS_I945G(dev)		((dev)->pdev->device == 0x2772)
+#define IS_I915GM(dev)		(INTEL_DEVID(dev) == 0x2592)
+#define IS_I945G(dev)		(INTEL_DEVID(dev) == 0x2772)
 #define IS_I945GM(dev)		(INTEL_INFO(dev)->is_i945gm)
 #define IS_BROADWATER(dev)	(INTEL_INFO(dev)->is_broadwater)
 #define IS_CRESTLINE(dev)	(INTEL_INFO(dev)->is_crestline)
-#define IS_GM45(dev)		((dev)->pdev->device == 0x2A42)
+#define IS_GM45(dev)		(INTEL_DEVID(dev) == 0x2A42)
 #define IS_G4X(dev)		(INTEL_INFO(dev)->is_g4x)
-#define IS_PINEVIEW_G(dev)	((dev)->pdev->device == 0xa001)
-#define IS_PINEVIEW_M(dev)	((dev)->pdev->device == 0xa011)
+#define IS_PINEVIEW_G(dev)	(INTEL_DEVID(dev) == 0xa001)
+#define IS_PINEVIEW_M(dev)	(INTEL_DEVID(dev) == 0xa011)
 #define IS_PINEVIEW(dev)	(INTEL_INFO(dev)->is_pineview)
 #define IS_G33(dev)		(INTEL_INFO(dev)->is_g33)
-#define IS_IRONLAKE_M(dev)	((dev)->pdev->device == 0x0046)
+#define IS_IRONLAKE_M(dev)	(INTEL_DEVID(dev) == 0x0046)
 #define IS_IVYBRIDGE(dev)	(INTEL_INFO(dev)->is_ivybridge)
-#define IS_IVB_GT1(dev)		((dev)->pdev->device == 0x0156 || \
-				 (dev)->pdev->device == 0x0152 || \
-				 (dev)->pdev->device == 0x015a)
-#define IS_SNB_GT1(dev)		((dev)->pdev->device == 0x0102 || \
-				 (dev)->pdev->device == 0x0106 || \
-				 (dev)->pdev->device == 0x010A)
+#define IS_IVB_GT1(dev)		(INTEL_DEVID(dev) == 0x0156 || \
+				 INTEL_DEVID(dev) == 0x0152 || \
+				 INTEL_DEVID(dev) == 0x015a)
+#define IS_SNB_GT1(dev)		(INTEL_DEVID(dev) == 0x0102 || \
+				 INTEL_DEVID(dev) == 0x0106 || \
+				 INTEL_DEVID(dev) == 0x010A)
 #define IS_VALLEYVIEW(dev)	(INTEL_INFO(dev)->is_valleyview)
 #define IS_CHERRYVIEW(dev)	(INTEL_INFO(dev)->is_valleyview && IS_GEN8(dev))
 #define IS_HASWELL(dev)	(INTEL_INFO(dev)->is_haswell)
 #define IS_BROADWELL(dev)	(!INTEL_INFO(dev)->is_valleyview && IS_GEN8(dev))
 #define IS_MOBILE(dev)		(INTEL_INFO(dev)->is_mobile)
 #define IS_HSW_EARLY_SDV(dev)	(IS_HASWELL(dev) && \
-				 ((dev)->pdev->device & 0xFF00) == 0x0C00)
+				 (INTEL_DEVID(dev) & 0xFF00) == 0x0C00)
 #define IS_BDW_ULT(dev)		(IS_BROADWELL(dev) && \
-				 (((dev)->pdev->device & 0xf) == 0x2  || \
-				 ((dev)->pdev->device & 0xf) == 0x6 || \
-				 ((dev)->pdev->device & 0xf) == 0xe))
+				 ((INTEL_DEVID(dev) & 0xf) == 0x2  || \
+				 (INTEL_DEVID(dev) & 0xf) == 0x6 || \
+				 (INTEL_DEVID(dev) & 0xf) == 0xe))
 #define IS_HSW_ULT(dev)		(IS_HASWELL(dev) && \
-				 ((dev)->pdev->device & 0xFF00) == 0x0A00)
+				 (INTEL_DEVID(dev) & 0xFF00) == 0x0A00)
 #define IS_ULT(dev)		(IS_HSW_ULT(dev) || IS_BDW_ULT(dev))
 #define IS_HSW_GT3(dev)		(IS_HASWELL(dev) && \
-				 ((dev)->pdev->device & 0x00F0) == 0x0020)
+				 (INTEL_DEVID(dev) & 0x00F0) == 0x0020)
 /* ULX machines are also considered ULT. */
-#define IS_HSW_ULX(dev)		((dev)->pdev->device == 0x0A0E || \
-				 (dev)->pdev->device == 0x0A1E)
+#define IS_HSW_ULX(dev)		(INTEL_DEVID(dev) == 0x0A0E || \
+				 INTEL_DEVID(dev) == 0x0A1E)
 #define IS_PRELIMINARY_HW(intel_info) ((intel_info)->is_preliminary)
 
 /*
@@ -2047,10 +2119,11 @@ struct drm_i915_cmd_table {
 #define I915_NEED_GFX_HWS(dev)	(INTEL_INFO(dev)->need_gfx_hws)
 
 #define HAS_HW_CONTEXTS(dev)	(INTEL_INFO(dev)->gen >= 6)
+#define HAS_LOGICAL_RING_CONTEXTS(dev)	(INTEL_INFO(dev)->gen >= 8)
 #define HAS_ALIASING_PPGTT(dev)	(INTEL_INFO(dev)->gen >= 6)
 #define HAS_PPGTT(dev)		(INTEL_INFO(dev)->gen >= 7 && !IS_GEN8(dev))
-#define USES_PPGTT(dev)		intel_enable_ppgtt(dev, false)
-#define USES_FULL_PPGTT(dev)	intel_enable_ppgtt(dev, true)
+#define USES_PPGTT(dev)		(i915.enable_ppgtt)
+#define USES_FULL_PPGTT(dev)	(i915.enable_ppgtt == 2)
 
 #define HAS_OVERLAY(dev)		(INTEL_INFO(dev)->has_overlay)
 #define OVERLAY_NEEDS_PHYSICAL(dev)	(INTEL_INFO(dev)->overlay_needs_physical)
@@ -2134,6 +2207,7 @@ struct i915_params {
 	int enable_rc6;
 	int enable_fbc;
 	int enable_ppgtt;
+	int enable_execlists;
 	int enable_psr;
 	unsigned int preliminary_hw_support;
 	int disable_power_well;
@@ -2180,8 +2254,6 @@ extern void i915_update_gfx_val(struct drm_i915_private *dev_priv);
 int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on);
 void intel_hpd_cancel_work(struct drm_i915_private *dev_priv);
 
-extern void intel_console_resume(struct work_struct *work);
-
 /* i915_irq.c */
 void i915_queue_hangcheck(struct drm_device *dev);
 __printf(3, 4)
@@ -2229,6 +2301,20 @@ int i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 			      struct drm_file *file_priv);
 int i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_priv);
+void i915_gem_execbuffer_move_to_active(struct list_head *vmas,
+					struct intel_engine_cs *ring);
+void i915_gem_execbuffer_retire_commands(struct drm_device *dev,
+					 struct drm_file *file,
+					 struct intel_engine_cs *ring,
+					 struct drm_i915_gem_object *obj);
+int i915_gem_ringbuffer_submission(struct drm_device *dev,
+				   struct drm_file *file,
+				   struct intel_engine_cs *ring,
+				   struct intel_context *ctx,
+				   struct drm_i915_gem_execbuffer2 *args,
+				   struct list_head *vmas,
+				   struct drm_i915_gem_object *batch_obj,
+				   u64 exec_start, u32 flags);
 int i915_gem_execbuffer(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 int i915_gem_execbuffer2(struct drm_device *dev, void *data,
@@ -2263,6 +2349,12 @@ int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 int i915_gem_wait_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 void i915_gem_load(struct drm_device *dev);
+unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
+			      long target,
+			      unsigned flags);
+#define I915_SHRINK_PURGEABLE 0x1
+#define I915_SHRINK_UNBOUND 0x2
+#define I915_SHRINK_BOUND 0x4
 void *i915_gem_object_alloc(struct drm_device *dev);
 void i915_gem_object_free(struct drm_i915_gem_object *obj);
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
@@ -2381,6 +2473,7 @@ void i915_gem_reset(struct drm_device *dev);
 bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
+int i915_gem_init_rings(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
 int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
@@ -2451,7 +2544,7 @@ static inline bool i915_gem_obj_is_pinned(struct drm_i915_gem_object *obj) {
 }
 
 /* Some GGTT VM helpers */
-#define obj_to_ggtt(obj) \
+#define i915_obj_to_ggtt(obj) \
 	(&((struct drm_i915_private *)(obj)->base.dev->dev_private)->gtt.base)
 static inline bool i915_is_ggtt(struct i915_address_space *vm)
 {
@@ -2460,21 +2553,30 @@ static inline bool i915_is_ggtt(struct i915_address_space *vm)
 	return vm == ggtt;
 }
 
+static inline struct i915_hw_ppgtt *
+i915_vm_to_ppgtt(struct i915_address_space *vm)
+{
+	WARN_ON(i915_is_ggtt(vm));
+
+	return container_of(vm, struct i915_hw_ppgtt, base);
+}
+
+
 static inline bool i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *obj)
 {
-	return i915_gem_obj_bound(obj, obj_to_ggtt(obj));
+	return i915_gem_obj_bound(obj, i915_obj_to_ggtt(obj));
 }
 
 static inline unsigned long
 i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *obj)
 {
-	return i915_gem_obj_offset(obj, obj_to_ggtt(obj));
+	return i915_gem_obj_offset(obj, i915_obj_to_ggtt(obj));
 }
 
 static inline unsigned long
 i915_gem_obj_ggtt_size(struct drm_i915_gem_object *obj)
 {
-	return i915_gem_obj_size(obj, obj_to_ggtt(obj));
+	return i915_gem_obj_size(obj, i915_obj_to_ggtt(obj));
 }
 
 static inline int __must_check
@@ -2482,7 +2584,8 @@ i915_gem_obj_ggtt_pin(struct drm_i915_gem_object *obj,
 		      uint32_t alignment,
 		      unsigned flags)
 {
-	return i915_gem_object_pin(obj, obj_to_ggtt(obj), alignment, flags | PIN_GLOBAL);
+	return i915_gem_object_pin(obj, i915_obj_to_ggtt(obj),
+				   alignment, flags | PIN_GLOBAL);
 }
 
 static inline int
@@ -2494,7 +2597,6 @@ i915_gem_object_ggtt_unbind(struct drm_i915_gem_object *obj)
 void i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj);
 
 /* i915_gem_context.c */
-#define ctx_to_ppgtt(ctx) container_of((ctx)->vm, struct i915_hw_ppgtt, base)
 int __must_check i915_gem_context_init(struct drm_device *dev);
 void i915_gem_context_fini(struct drm_device *dev);
 void i915_gem_context_reset(struct drm_device *dev);
@@ -2506,6 +2608,8 @@ int i915_switch_context(struct intel_engine_cs *ring,
 struct intel_context *
 i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id);
 void i915_gem_context_free(struct kref *ctx_ref);
+struct drm_i915_gem_object *
+i915_gem_alloc_context_obj(struct drm_device *dev, size_t size);
 static inline void i915_gem_context_reference(struct intel_context *ctx)
 {
 	kref_get(&ctx->ref);
@@ -2526,8 +2630,6 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 				   struct drm_file *file);
 
-/* i915_gem_render_state.c */
-int i915_gem_render_state_init(struct intel_engine_cs *ring);
 /* i915_gem_evict.c */
 int __must_check i915_gem_evict_something(struct drm_device *dev,
 					  struct i915_address_space *vm,
@@ -2595,6 +2697,7 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
 int i915_error_state_to_str(struct drm_i915_error_state_buf *estr,
 			    const struct i915_error_state_file_priv *error);
 int i915_error_state_buf_init(struct drm_i915_error_state_buf *eb,
+			      struct drm_i915_private *i915,
 			      size_t count, loff_t pos);
 static inline void i915_error_state_buf_release(
 	struct drm_i915_error_state_buf *eb)
@@ -2609,7 +2712,7 @@ void i915_error_state_put(struct i915_error_state_file_priv *error_priv);
 void i915_destroy_error_state(struct drm_device *dev);
 
 void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone);
-const char *i915_cache_level_str(int type);
+const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
 
 /* i915_cmd_parser.c */
 int i915_cmd_parser_get_version(void);
@@ -2701,6 +2804,7 @@ extern void intel_modeset_setup_hw_state(struct drm_device *dev,
 extern void i915_redisable_vga(struct drm_device *dev);
 extern void i915_redisable_vga_power_on(struct drm_device *dev);
 extern bool intel_fbc_enabled(struct drm_device *dev);
+extern void gen8_fbc_sw_flush(struct drm_device *dev, u32 value);
 extern void intel_disable_fbc(struct drm_device *dev);
 extern bool ironlake_set_drps(struct drm_device *dev, u8 val);
 extern void intel_init_pch_refclk(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ad55b06a3cb1..28f91df2604d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -60,7 +60,6 @@ static unsigned long i915_gem_shrinker_scan(struct shrinker *shrinker,
 static int i915_gem_shrinker_oom(struct notifier_block *nb,
 				 unsigned long event,
 				 void *ptr);
-static unsigned long i915_gem_purge(struct drm_i915_private *dev_priv, long target);
 static unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
 
 static bool cpu_cache_is_coherent(struct drm_device *dev,
@@ -1085,7 +1084,13 @@ i915_gem_check_wedge(struct i915_gpu_error *error,
 		if (i915_terminally_wedged(error))
 			return -EIO;
 
-		return -EAGAIN;
+		/*
+		 * Check if GPU Reset is in progress - we need intel_ring_begin
+		 * to work properly to reinit the hw state while the gpu is
+		 * still marked as reset-in-progress. Handle this with a flag.
+		 */
+		if (!error->reload_in_reset)
+			return -EAGAIN;
 	}
 
 	return 0;
@@ -1735,7 +1740,11 @@ static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
 	 * offsets on purgeable objects by truncating it and marking it purged,
 	 * which prevents userspace from ever using that object again.
 	 */
-	i915_gem_purge(dev_priv, obj->base.size >> PAGE_SHIFT);
+	i915_gem_shrink(dev_priv,
+			obj->base.size >> PAGE_SHIFT,
+			I915_SHRINK_BOUND |
+			I915_SHRINK_UNBOUND |
+			I915_SHRINK_PURGEABLE);
 	ret = drm_gem_create_mmap_offset(&obj->base);
 	if (ret != -ENOSPC)
 		goto out;
@@ -1932,12 +1941,11 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	return 0;
 }
 
-static unsigned long
-__i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
-		  bool purgeable_only)
+unsigned long
+i915_gem_shrink(struct drm_i915_private *dev_priv,
+		long target, unsigned flags)
 {
-	struct list_head still_in_list;
-	struct drm_i915_gem_object *obj;
+	const bool purgeable_only = flags & I915_SHRINK_PURGEABLE;
 	unsigned long count = 0;
 
 	/*
@@ -1959,62 +1967,68 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
 	 * dev->struct_mutex and so we won't ever be able to observe an
 	 * object on the bound_list with a reference count equals 0.
 	 */
-	INIT_LIST_HEAD(&still_in_list);
-	while (count < target && !list_empty(&dev_priv->mm.unbound_list)) {
-		obj = list_first_entry(&dev_priv->mm.unbound_list,
-				       typeof(*obj), global_list);
-		list_move_tail(&obj->global_list, &still_in_list);
+	if (flags & I915_SHRINK_UNBOUND) {
+		struct list_head still_in_list;
 
-		if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
-			continue;
+		INIT_LIST_HEAD(&still_in_list);
+		while (count < target && !list_empty(&dev_priv->mm.unbound_list)) {
+			struct drm_i915_gem_object *obj;
 
-		drm_gem_object_reference(&obj->base);
+			obj = list_first_entry(&dev_priv->mm.unbound_list,
+					       typeof(*obj), global_list);
+			list_move_tail(&obj->global_list, &still_in_list);
 
-		if (i915_gem_object_put_pages(obj) == 0)
-			count += obj->base.size >> PAGE_SHIFT;
+			if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
+				continue;
 
-		drm_gem_object_unreference(&obj->base);
+			drm_gem_object_reference(&obj->base);
+
+			if (i915_gem_object_put_pages(obj) == 0)
+				count += obj->base.size >> PAGE_SHIFT;
+
+			drm_gem_object_unreference(&obj->base);
+		}
+		list_splice(&still_in_list, &dev_priv->mm.unbound_list);
 	}
-	list_splice(&still_in_list, &dev_priv->mm.unbound_list);
 
-	INIT_LIST_HEAD(&still_in_list);
-	while (count < target && !list_empty(&dev_priv->mm.bound_list)) {
-		struct i915_vma *vma, *v;
+	if (flags & I915_SHRINK_BOUND) {
+		struct list_head still_in_list;
 
-		obj = list_first_entry(&dev_priv->mm.bound_list,
-				       typeof(*obj), global_list);
-		list_move_tail(&obj->global_list, &still_in_list);
+		INIT_LIST_HEAD(&still_in_list);
+		while (count < target && !list_empty(&dev_priv->mm.bound_list)) {
+			struct drm_i915_gem_object *obj;
+			struct i915_vma *vma, *v;
 
-		if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
-			continue;
+			obj = list_first_entry(&dev_priv->mm.bound_list,
+					       typeof(*obj), global_list);
+			list_move_tail(&obj->global_list, &still_in_list);
 
-		drm_gem_object_reference(&obj->base);
+			if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
+				continue;
 
-		list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link)
-			if (i915_vma_unbind(vma))
-				break;
+			drm_gem_object_reference(&obj->base);
 
-		if (i915_gem_object_put_pages(obj) == 0)
-			count += obj->base.size >> PAGE_SHIFT;
+			list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link)
+				if (i915_vma_unbind(vma))
+					break;
 
-		drm_gem_object_unreference(&obj->base);
+			if (i915_gem_object_put_pages(obj) == 0)
+				count += obj->base.size >> PAGE_SHIFT;
+
+			drm_gem_object_unreference(&obj->base);
+		}
+		list_splice(&still_in_list, &dev_priv->mm.bound_list);
 	}
-	list_splice(&still_in_list, &dev_priv->mm.bound_list);
 
 	return count;
 }
 
 static unsigned long
-i915_gem_purge(struct drm_i915_private *dev_priv, long target)
-{
-	return __i915_gem_shrink(dev_priv, target, true);
-}
-
-static unsigned long
 i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 {
 	i915_gem_evict_everything(dev_priv->dev);
-	return __i915_gem_shrink(dev_priv, LONG_MAX, false);
+	return i915_gem_shrink(dev_priv, LONG_MAX,
+			       I915_SHRINK_BOUND | I915_SHRINK_UNBOUND);
 }
 
 static int
@@ -2061,7 +2075,11 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 	for (i = 0; i < page_count; i++) {
 		page = shmem_read_mapping_page_gfp(mapping, i, gfp);
 		if (IS_ERR(page)) {
-			i915_gem_purge(dev_priv, page_count);
+			i915_gem_shrink(dev_priv,
+					page_count,
+					I915_SHRINK_BOUND |
+					I915_SHRINK_UNBOUND |
+					I915_SHRINK_PURGEABLE);
 			page = shmem_read_mapping_page_gfp(mapping, i, gfp);
 		}
 		if (IS_ERR(page)) {
@@ -2163,8 +2181,6 @@ static void
 i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
 			       struct intel_engine_cs *ring)
 {
-	struct drm_device *dev = obj->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 seqno = intel_ring_get_seqno(ring);
 
 	BUG_ON(ring == NULL);
@@ -2183,19 +2199,6 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
 	list_move_tail(&obj->ring_list, &ring->active_list);
 
 	obj->last_read_seqno = seqno;
-
-	if (obj->fenced_gpu_access) {
-		obj->last_fenced_seqno = seqno;
-
-		/* Bump MRU to take account of the delayed flush */
-		if (obj->fence_reg != I915_FENCE_REG_NONE) {
-			struct drm_i915_fence_reg *reg;
-
-			reg = &dev_priv->fence_regs[obj->fence_reg];
-			list_move_tail(&reg->lru_list,
-				       &dev_priv->mm.fence_list);
-		}
-	}
 }
 
 void i915_vma_move_to_active(struct i915_vma *vma,
@@ -2231,7 +2234,6 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj)
 	obj->base.write_domain = 0;
 
 	obj->last_fenced_seqno = 0;
-	obj->fenced_gpu_access = false;
 
 	obj->active = 0;
 	drm_gem_object_unreference(&obj->base);
@@ -2329,10 +2331,21 @@ int __i915_add_request(struct intel_engine_cs *ring,
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	struct drm_i915_gem_request *request;
+	struct intel_ringbuffer *ringbuf;
 	u32 request_ring_position, request_start;
 	int ret;
 
-	request_start = intel_ring_get_tail(ring->buffer);
+	request = ring->preallocated_lazy_request;
+	if (WARN_ON(request == NULL))
+		return -ENOMEM;
+
+	if (i915.enable_execlists) {
+		struct intel_context *ctx = request->ctx;
+		ringbuf = ctx->engine[ring->id].ringbuf;
+	} else
+		ringbuf = ring->buffer;
+
+	request_start = intel_ring_get_tail(ringbuf);
 	/*
 	 * Emit any outstanding flushes - execbuf can fail to emit the flush
 	 * after having emitted the batchbuffer command. Hence we need to fix
@@ -2340,24 +2353,32 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	 * is that the flush _must_ happen before the next request, no matter
 	 * what.
 	 */
-	ret = intel_ring_flush_all_caches(ring);
-	if (ret)
-		return ret;
-
-	request = ring->preallocated_lazy_request;
-	if (WARN_ON(request == NULL))
-		return -ENOMEM;
+	if (i915.enable_execlists) {
+		ret = logical_ring_flush_all_caches(ringbuf);
+		if (ret)
+			return ret;
+	} else {
+		ret = intel_ring_flush_all_caches(ring);
+		if (ret)
+			return ret;
+	}
 
 	/* Record the position of the start of the request so that
 	 * should we detect the updated seqno part-way through the
 	 * GPU processing the request, we never over-estimate the
 	 * position of the head.
 	 */
-	request_ring_position = intel_ring_get_tail(ring->buffer);
+	request_ring_position = intel_ring_get_tail(ringbuf);
 
-	ret = ring->add_request(ring);
-	if (ret)
-		return ret;
+	if (i915.enable_execlists) {
+		ret = ring->emit_request(ringbuf);
+		if (ret)
+			return ret;
+	} else {
+		ret = ring->add_request(ring);
+		if (ret)
+			return ret;
+	}
 
 	request->seqno = intel_ring_get_seqno(ring);
 	request->ring = ring;
@@ -2372,12 +2393,14 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	 */
 	request->batch_obj = obj;
 
-	/* Hold a reference to the current context so that we can inspect
-	 * it later in case a hangcheck error event fires.
-	 */
-	request->ctx = ring->last_context;
-	if (request->ctx)
-		i915_gem_context_reference(request->ctx);
+	if (!i915.enable_execlists) {
+		/* Hold a reference to the current context so that we can inspect
+		 * it later in case a hangcheck error event fires.
+		 */
+		request->ctx = ring->last_context;
+		if (request->ctx)
+			i915_gem_context_reference(request->ctx);
+	}
 
 	request->emitted_jiffies = jiffies;
 	list_add_tail(&request->list, &ring->request_list);
@@ -2548,6 +2571,18 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 		i915_gem_free_request(request);
 	}
 
+	while (!list_empty(&ring->execlist_queue)) {
+		struct intel_ctx_submit_request *submit_req;
+
+		submit_req = list_first_entry(&ring->execlist_queue,
+				struct intel_ctx_submit_request,
+				execlist_link);
+		list_del(&submit_req->execlist_link);
+		intel_runtime_pm_put(dev_priv);
+		i915_gem_context_unreference(submit_req->ctx);
+		kfree(submit_req);
+	}
+
 	/* These may not have been flush before the reset, do so now */
 	kfree(ring->preallocated_lazy_request);
 	ring->preallocated_lazy_request = NULL;
@@ -2632,6 +2667,7 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
 
 	while (!list_empty(&ring->request_list)) {
 		struct drm_i915_gem_request *request;
+		struct intel_ringbuffer *ringbuf;
 
 		request = list_first_entry(&ring->request_list,
 					   struct drm_i915_gem_request,
@@ -2641,12 +2677,24 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
 			break;
 
 		trace_i915_gem_request_retire(ring, request->seqno);
+
+		/* This is one of the few common intersection points
+		 * between legacy ringbuffer submission and execlists:
+		 * we need to tell them apart in order to find the correct
+		 * ringbuffer to which the request belongs to.
+		 */
+		if (i915.enable_execlists) {
+			struct intel_context *ctx = request->ctx;
+			ringbuf = ctx->engine[ring->id].ringbuf;
+		} else
+			ringbuf = ring->buffer;
+
 		/* We know the GPU must have read the request to have
 		 * sent us the seqno + interrupt, so use the position
 		 * of tail of the request to update the last known position
 		 * of the GPU head.
 		 */
-		ring->buffer->last_retired_head = request->tail;
+		ringbuf->last_retired_head = request->tail;
 
 		i915_gem_free_request(request);
 	}
@@ -2908,6 +2956,9 @@ int i915_vma_unbind(struct i915_vma *vma)
 	 * cause memory corruption through use-after-free.
 	 */
 
+	/* Throw away the active reference before moving to the unbound list */
+	i915_gem_object_retire(obj);
+
 	if (i915_is_ggtt(vma->vm)) {
 		i915_gem_object_finish_gtt(obj);
 
@@ -2922,9 +2973,8 @@ int i915_vma_unbind(struct i915_vma *vma)
 	vma->unbind_vma(vma);
 
 	list_del_init(&vma->mm_list);
-	/* Avoid an unnecessary call to unbind on rebind. */
 	if (i915_is_ggtt(vma->vm))
-		obj->map_and_fenceable = true;
+		obj->map_and_fenceable = false;
 
 	drm_mm_remove_node(&vma->node);
 	i915_gem_vma_destroy(vma);
@@ -2953,9 +3003,11 @@ int i915_gpu_idle(struct drm_device *dev)
 
 	/* Flush everything onto the inactive list. */
 	for_each_ring(ring, dev_priv, i) {
-		ret = i915_switch_context(ring, ring->default_context);
-		if (ret)
-			return ret;
+		if (!i915.enable_execlists) {
+			ret = i915_switch_context(ring, ring->default_context);
+			if (ret)
+				return ret;
+		}
 
 		ret = intel_ring_idle(ring);
 		if (ret)
@@ -3169,7 +3221,6 @@ i915_gem_object_wait_fence(struct drm_i915_gem_object *obj)
 		obj->last_fenced_seqno = 0;
 	}
 
-	obj->fenced_gpu_access = false;
 	return 0;
 }
 
@@ -3276,6 +3327,9 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj)
 			return 0;
 		}
 	} else if (enable) {
+		if (WARN_ON(!obj->map_and_fenceable))
+			return -EINVAL;
+
 		reg = i915_find_fence_reg(dev);
 		if (IS_ERR(reg))
 			return PTR_ERR(reg);
@@ -3297,17 +3351,20 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj)
 	return 0;
 }
 
-static bool i915_gem_valid_gtt_space(struct drm_device *dev,
-				     struct drm_mm_node *gtt_space,
+static bool i915_gem_valid_gtt_space(struct i915_vma *vma,
 				     unsigned long cache_level)
 {
+	struct drm_mm_node *gtt_space = &vma->node;
 	struct drm_mm_node *other;
 
-	/* On non-LLC machines we have to be careful when putting differing
-	 * types of snoopable memory together to avoid the prefetcher
-	 * crossing memory domains and dying.
+	/*
+	 * On some machines we have to be careful when putting differing types
+	 * of snoopable memory together to avoid the prefetcher crossing memory
+	 * domains and dying. During vm initialisation, we decide whether or not
+	 * these constraints apply and set the drm_mm.color_adjust
+	 * appropriately.
 	 */
-	if (HAS_LLC(dev))
+	if (vma->vm->mm.color_adjust == NULL)
 		return true;
 
 	if (!drm_mm_node_allocated(gtt_space))
@@ -3445,8 +3502,7 @@ search_free:
 
 		goto err_free_vma;
 	}
-	if (WARN_ON(!i915_gem_valid_gtt_space(dev, &vma->node,
-					      obj->cache_level))) {
+	if (WARN_ON(!i915_gem_valid_gtt_space(vma, obj->cache_level))) {
 		ret = -EINVAL;
 		goto err_remove_node;
 	}
@@ -3586,11 +3642,12 @@ int
 i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 {
 	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+	struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
 	uint32_t old_write_domain, old_read_domains;
 	int ret;
 
 	/* Not valid to be called on unbound objects. */
-	if (!i915_gem_obj_bound_any(obj))
+	if (vma == NULL)
 		return -EINVAL;
 
 	if (obj->base.write_domain == I915_GEM_DOMAIN_GTT)
@@ -3632,13 +3689,9 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 					    old_write_domain);
 
 	/* And bump the LRU for this access */
-	if (i915_gem_object_is_inactive(obj)) {
-		struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
-		if (vma)
-			list_move_tail(&vma->mm_list,
-				       &dev_priv->gtt.base.inactive_list);
-
-	}
+	if (i915_gem_object_is_inactive(obj))
+		list_move_tail(&vma->mm_list,
+			       &dev_priv->gtt.base.inactive_list);
 
 	return 0;
 }
@@ -3659,7 +3712,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 	}
 
 	list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) {
-		if (!i915_gem_valid_gtt_space(dev, &vma->node, cache_level)) {
+		if (!i915_gem_valid_gtt_space(vma, cache_level)) {
 			ret = i915_vma_unbind(vma);
 			if (ret)
 				return ret;
@@ -3802,9 +3855,6 @@ static bool is_pin_display(struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
 
-	if (list_empty(&obj->vma_list))
-		return false;
-
 	vma = i915_gem_obj_to_ggtt(obj);
 	if (!vma)
 		return false;
@@ -4331,8 +4381,6 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 
 	obj->fence_reg = I915_FENCE_REG_NONE;
 	obj->madv = I915_MADV_WILLNEED;
-	/* Avoid an unnecessary call to unbind on the first bind. */
-	obj->map_and_fenceable = true;
 
 	i915_gem_info_add_obj(obj->base.dev->dev_private, obj->base.size);
 }
@@ -4493,12 +4541,18 @@ struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
 
 void i915_gem_vma_destroy(struct i915_vma *vma)
 {
+	struct i915_address_space *vm = NULL;
 	WARN_ON(vma->node.allocated);
 
 	/* Keep the vma as a placeholder in the execbuffer reservation lists */
 	if (!list_empty(&vma->exec_list))
 		return;
 
+	vm = vma->vm;
+
+	if (!i915_is_ggtt(vm))
+		i915_ppgtt_put(i915_vm_to_ppgtt(vm));
+
 	list_del(&vma->vma_link);
 
 	kfree(vma);
@@ -4512,7 +4566,7 @@ i915_gem_stop_ringbuffers(struct drm_device *dev)
 	int i;
 
 	for_each_ring(ring, dev_priv, i)
-		intel_stop_ring_buffer(ring);
+		dev_priv->gt.stop_ring(ring);
 }
 
 int
@@ -4629,11 +4683,46 @@ intel_enable_blt(struct drm_device *dev)
 	return true;
 }
 
-static int i915_gem_init_rings(struct drm_device *dev)
+static void init_unused_ring(struct drm_device *dev, u32 base)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	I915_WRITE(RING_CTL(base), 0);
+	I915_WRITE(RING_HEAD(base), 0);
+	I915_WRITE(RING_TAIL(base), 0);
+	I915_WRITE(RING_START(base), 0);
+}
+
+static void init_unused_rings(struct drm_device *dev)
+{
+	if (IS_I830(dev)) {
+		init_unused_ring(dev, PRB1_BASE);
+		init_unused_ring(dev, SRB0_BASE);
+		init_unused_ring(dev, SRB1_BASE);
+		init_unused_ring(dev, SRB2_BASE);
+		init_unused_ring(dev, SRB3_BASE);
+	} else if (IS_GEN2(dev)) {
+		init_unused_ring(dev, SRB0_BASE);
+		init_unused_ring(dev, SRB1_BASE);
+	} else if (IS_GEN3(dev)) {
+		init_unused_ring(dev, PRB1_BASE);
+		init_unused_ring(dev, PRB2_BASE);
+	}
+}
+
+int i915_gem_init_rings(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
+	/*
+	 * At least 830 can leave some of the unused rings
+	 * "active" (ie. head != tail) after resume which
+	 * will prevent c3 entry. Makes sure all unused rings
+	 * are totally idle.
+	 */
+	init_unused_rings(dev);
+
 	ret = intel_init_render_ring_buffer(dev);
 	if (ret)
 		return ret;
@@ -4712,7 +4801,7 @@ i915_gem_init_hw(struct drm_device *dev)
 
 	i915_gem_init_swizzling(dev);
 
-	ret = i915_gem_init_rings(dev);
+	ret = dev_priv->gt.init_rings(dev);
 	if (ret)
 		return ret;
 
@@ -4730,6 +4819,14 @@ i915_gem_init_hw(struct drm_device *dev)
 	if (ret && ret != -EIO) {
 		DRM_ERROR("Context enable failed %d\n", ret);
 		i915_gem_cleanup_ringbuffer(dev);
+
+		return ret;
+	}
+
+	ret = i915_ppgtt_init_hw(dev);
+	if (ret && ret != -EIO) {
+		DRM_ERROR("PPGTT enable failed %d\n", ret);
+		i915_gem_cleanup_ringbuffer(dev);
 	}
 
 	return ret;
@@ -4740,6 +4837,9 @@ int i915_gem_init(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
+	i915.enable_execlists = intel_sanitize_enable_execlists(dev,
+			i915.enable_execlists);
+
 	mutex_lock(&dev->struct_mutex);
 
 	if (IS_VALLEYVIEW(dev)) {
@@ -4750,7 +4850,24 @@ int i915_gem_init(struct drm_device *dev)
 			DRM_DEBUG_DRIVER("allow wake ack timed out\n");
 	}
 
-	i915_gem_init_userptr(dev);
+	if (!i915.enable_execlists) {
+		dev_priv->gt.do_execbuf = i915_gem_ringbuffer_submission;
+		dev_priv->gt.init_rings = i915_gem_init_rings;
+		dev_priv->gt.cleanup_ring = intel_cleanup_ring_buffer;
+		dev_priv->gt.stop_ring = intel_stop_ring_buffer;
+	} else {
+		dev_priv->gt.do_execbuf = intel_execlists_submission;
+		dev_priv->gt.init_rings = intel_logical_rings_init;
+		dev_priv->gt.cleanup_ring = intel_logical_ring_cleanup;
+		dev_priv->gt.stop_ring = intel_logical_ring_stop;
+	}
+
+	ret = i915_gem_init_userptr(dev);
+	if (ret) {
+		mutex_unlock(&dev->struct_mutex);
+		return ret;
+	}
+
 	i915_gem_init_global_gtt(dev);
 
 	ret = i915_gem_context_init(dev);
@@ -4785,7 +4902,7 @@ i915_gem_cleanup_ringbuffer(struct drm_device *dev)
 	int i;
 
 	for_each_ring(ring, dev_priv, i)
-		intel_cleanup_ring_buffer(ring);
+		dev_priv->gt.cleanup_ring(ring);
 }
 
 int
@@ -5097,9 +5214,7 @@ unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o,
 	struct drm_i915_private *dev_priv = o->base.dev->dev_private;
 	struct i915_vma *vma;
 
-	if (!dev_priv->mm.aliasing_ppgtt ||
-	    vm == &dev_priv->mm.aliasing_ppgtt->base)
-		vm = &dev_priv->gtt.base;
+	WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base);
 
 	list_for_each_entry(vma, &o->vma_list, vma_link) {
 		if (vma->vm == vm)
@@ -5140,9 +5255,7 @@ unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
 	struct drm_i915_private *dev_priv = o->base.dev->dev_private;
 	struct i915_vma *vma;
 
-	if (!dev_priv->mm.aliasing_ppgtt ||
-	    vm == &dev_priv->mm.aliasing_ppgtt->base)
-		vm = &dev_priv->gtt.base;
+	WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base);
 
 	BUG_ON(list_empty(&o->vma_list));
 
@@ -5165,11 +5278,16 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 	if (!i915_gem_shrinker_lock(dev, &unlock))
 		return SHRINK_STOP;
 
-	freed = i915_gem_purge(dev_priv, sc->nr_to_scan);
+	freed = i915_gem_shrink(dev_priv,
+				sc->nr_to_scan,
+				I915_SHRINK_BOUND |
+				I915_SHRINK_UNBOUND |
+				I915_SHRINK_PURGEABLE);
 	if (freed < sc->nr_to_scan)
-		freed += __i915_gem_shrink(dev_priv,
-					   sc->nr_to_scan - freed,
-					   false);
+		freed += i915_gem_shrink(dev_priv,
+					 sc->nr_to_scan - freed,
+					 I915_SHRINK_BOUND |
+					 I915_SHRINK_UNBOUND);
 	if (unlock)
 		mutex_unlock(&dev->struct_mutex);
 
@@ -5247,14 +5365,8 @@ struct i915_vma *i915_gem_obj_to_ggtt(struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
 
-	/* This WARN has probably outlived its usefulness (callers already
-	 * WARN if they don't find the GGTT vma they expect). When removing,
-	 * remember to remove the pre-check in is_pin_display() as well */
-	if (WARN_ON(list_empty(&obj->vma_list)))
-		return NULL;
-
 	vma = list_first_entry(&obj->vma_list, typeof(*vma), vma_link);
-	if (vma->vm != obj_to_ggtt(obj))
+	if (vma->vm != i915_obj_to_ggtt(obj))
 		return NULL;
 
 	return vma;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 3b99390e467a..a5221d8f1580 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -96,50 +96,6 @@
 #define GEN6_CONTEXT_ALIGN (64<<10)
 #define GEN7_CONTEXT_ALIGN 4096
 
-static void do_ppgtt_cleanup(struct i915_hw_ppgtt *ppgtt)
-{
-	struct drm_device *dev = ppgtt->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_address_space *vm = &ppgtt->base;
-
-	if (ppgtt == dev_priv->mm.aliasing_ppgtt ||
-	    (list_empty(&vm->active_list) && list_empty(&vm->inactive_list))) {
-		ppgtt->base.cleanup(&ppgtt->base);
-		return;
-	}
-
-	/*
-	 * Make sure vmas are unbound before we take down the drm_mm
-	 *
-	 * FIXME: Proper refcounting should take care of this, this shouldn't be
-	 * needed at all.
-	 */
-	if (!list_empty(&vm->active_list)) {
-		struct i915_vma *vma;
-
-		list_for_each_entry(vma, &vm->active_list, mm_list)
-			if (WARN_ON(list_empty(&vma->vma_link) ||
-				    list_is_singular(&vma->vma_link)))
-				break;
-
-		i915_gem_evict_vm(&ppgtt->base, true);
-	} else {
-		i915_gem_retire_requests(dev);
-		i915_gem_evict_vm(&ppgtt->base, false);
-	}
-
-	ppgtt->base.cleanup(&ppgtt->base);
-}
-
-static void ppgtt_release(struct kref *kref)
-{
-	struct i915_hw_ppgtt *ppgtt =
-		container_of(kref, struct i915_hw_ppgtt, ref);
-
-	do_ppgtt_cleanup(ppgtt);
-	kfree(ppgtt);
-}
-
 static size_t get_context_alignment(struct drm_device *dev)
 {
 	if (IS_GEN6(dev))
@@ -179,24 +135,20 @@ static int get_context_size(struct drm_device *dev)
 void i915_gem_context_free(struct kref *ctx_ref)
 {
 	struct intel_context *ctx = container_of(ctx_ref,
-						   typeof(*ctx), ref);
-	struct i915_hw_ppgtt *ppgtt = NULL;
+						 typeof(*ctx), ref);
 
-	if (ctx->legacy_hw_ctx.rcs_state) {
-		/* We refcount even the aliasing PPGTT to keep the code symmetric */
-		if (USES_PPGTT(ctx->legacy_hw_ctx.rcs_state->base.dev))
-			ppgtt = ctx_to_ppgtt(ctx);
-	}
+	if (i915.enable_execlists)
+		intel_lr_context_free(ctx);
+
+	i915_ppgtt_put(ctx->ppgtt);
 
-	if (ppgtt)
-		kref_put(&ppgtt->ref, ppgtt_release);
 	if (ctx->legacy_hw_ctx.rcs_state)
 		drm_gem_object_unreference(&ctx->legacy_hw_ctx.rcs_state->base);
 	list_del(&ctx->link);
 	kfree(ctx);
 }
 
-static struct drm_i915_gem_object *
+struct drm_i915_gem_object *
 i915_gem_alloc_context_obj(struct drm_device *dev, size_t size)
 {
 	struct drm_i915_gem_object *obj;
@@ -226,29 +178,9 @@ i915_gem_alloc_context_obj(struct drm_device *dev, size_t size)
 	return obj;
 }
 
-static struct i915_hw_ppgtt *
-create_vm_for_ctx(struct drm_device *dev, struct intel_context *ctx)
-{
-	struct i915_hw_ppgtt *ppgtt;
-	int ret;
-
-	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
-	if (!ppgtt)
-		return ERR_PTR(-ENOMEM);
-
-	ret = i915_gem_init_ppgtt(dev, ppgtt);
-	if (ret) {
-		kfree(ppgtt);
-		return ERR_PTR(ret);
-	}
-
-	ppgtt->ctx = ctx;
-	return ppgtt;
-}
-
 static struct intel_context *
 __create_hw_context(struct drm_device *dev,
-		  struct drm_i915_file_private *file_priv)
+		    struct drm_i915_file_private *file_priv)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_context *ctx;
@@ -301,11 +233,9 @@ err_out:
  */
 static struct intel_context *
 i915_gem_create_context(struct drm_device *dev,
-			struct drm_i915_file_private *file_priv,
-			bool create_vm)
+			struct drm_i915_file_private *file_priv)
 {
 	const bool is_global_default_ctx = file_priv == NULL;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_context *ctx;
 	int ret = 0;
 
@@ -331,34 +261,18 @@ i915_gem_create_context(struct drm_device *dev,
 		}
 	}
 
-	if (create_vm) {
-		struct i915_hw_ppgtt *ppgtt = create_vm_for_ctx(dev, ctx);
+	if (USES_FULL_PPGTT(dev)) {
+		struct i915_hw_ppgtt *ppgtt = i915_ppgtt_create(dev, file_priv);
 
 		if (IS_ERR_OR_NULL(ppgtt)) {
 			DRM_DEBUG_DRIVER("PPGTT setup failed (%ld)\n",
 					 PTR_ERR(ppgtt));
 			ret = PTR_ERR(ppgtt);
 			goto err_unpin;
-		} else
-			ctx->vm = &ppgtt->base;
-
-		/* This case is reserved for the global default context and
-		 * should only happen once. */
-		if (is_global_default_ctx) {
-			if (WARN_ON(dev_priv->mm.aliasing_ppgtt)) {
-				ret = -EEXIST;
-				goto err_unpin;
-			}
-
-			dev_priv->mm.aliasing_ppgtt = ppgtt;
 		}
-	} else if (USES_PPGTT(dev)) {
-		/* For platforms which only have aliasing PPGTT, we fake the
-		 * address space and refcounting. */
-		ctx->vm = &dev_priv->mm.aliasing_ppgtt->base;
-		kref_get(&dev_priv->mm.aliasing_ppgtt->ref);
-	} else
-		ctx->vm = &dev_priv->gtt.base;
+
+		ctx->ppgtt = ppgtt;
+	}
 
 	return ctx;
 
@@ -375,34 +289,23 @@ void i915_gem_context_reset(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
 
-	/* Prevent the hardware from restoring the last context (which hung) on
-	 * the next switch */
+	/* In execlists mode we will unreference the context when the execlist
+	 * queue is cleared and the requests destroyed.
+	 */
+	if (i915.enable_execlists)
+		return;
+
 	for (i = 0; i < I915_NUM_RINGS; i++) {
 		struct intel_engine_cs *ring = &dev_priv->ring[i];
-		struct intel_context *dctx = ring->default_context;
 		struct intel_context *lctx = ring->last_context;
 
-		/* Do a fake switch to the default context */
-		if (lctx == dctx)
-			continue;
-
-		if (!lctx)
-			continue;
+		if (lctx) {
+			if (lctx->legacy_hw_ctx.rcs_state && i == RCS)
+				i915_gem_object_ggtt_unpin(lctx->legacy_hw_ctx.rcs_state);
 
-		if (dctx->legacy_hw_ctx.rcs_state && i == RCS) {
-			WARN_ON(i915_gem_obj_ggtt_pin(dctx->legacy_hw_ctx.rcs_state,
-						      get_context_alignment(dev), 0));
-			/* Fake a finish/inactive */
-			dctx->legacy_hw_ctx.rcs_state->base.write_domain = 0;
-			dctx->legacy_hw_ctx.rcs_state->active = 0;
+			i915_gem_context_unreference(lctx);
+			ring->last_context = NULL;
 		}
-
-		if (lctx->legacy_hw_ctx.rcs_state && i == RCS)
-			i915_gem_object_ggtt_unpin(lctx->legacy_hw_ctx.rcs_state);
-
-		i915_gem_context_unreference(lctx);
-		i915_gem_context_reference(dctx);
-		ring->last_context = dctx;
 	}
 }
 
@@ -417,7 +320,11 @@ int i915_gem_context_init(struct drm_device *dev)
 	if (WARN_ON(dev_priv->ring[RCS].default_context))
 		return 0;
 
-	if (HAS_HW_CONTEXTS(dev)) {
+	if (i915.enable_execlists) {
+		/* NB: intentionally left blank. We will allocate our own
+		 * backing objects as we need them, thank you very much */
+		dev_priv->hw_context_size = 0;
+	} else if (HAS_HW_CONTEXTS(dev)) {
 		dev_priv->hw_context_size = round_up(get_context_size(dev), 4096);
 		if (dev_priv->hw_context_size > (1<<20)) {
 			DRM_DEBUG_DRIVER("Disabling HW Contexts; invalid size %d\n",
@@ -426,18 +333,23 @@ int i915_gem_context_init(struct drm_device *dev)
 		}
 	}
 
-	ctx = i915_gem_create_context(dev, NULL, USES_PPGTT(dev));
+	ctx = i915_gem_create_context(dev, NULL);
 	if (IS_ERR(ctx)) {
 		DRM_ERROR("Failed to create default global context (error %ld)\n",
 			  PTR_ERR(ctx));
 		return PTR_ERR(ctx);
 	}
 
-	/* NB: RCS will hold a ref for all rings */
-	for (i = 0; i < I915_NUM_RINGS; i++)
-		dev_priv->ring[i].default_context = ctx;
+	for (i = 0; i < I915_NUM_RINGS; i++) {
+		struct intel_engine_cs *ring = &dev_priv->ring[i];
 
-	DRM_DEBUG_DRIVER("%s context support initialized\n", dev_priv->hw_context_size ? "HW" : "fake");
+		/* NB: RCS will hold a ref for all rings */
+		ring->default_context = ctx;
+	}
+
+	DRM_DEBUG_DRIVER("%s context support initialized\n",
+			i915.enable_execlists ? "LR" :
+			dev_priv->hw_context_size ? "HW" : "fake");
 	return 0;
 }
 
@@ -489,19 +401,11 @@ int i915_gem_context_enable(struct drm_i915_private *dev_priv)
 	struct intel_engine_cs *ring;
 	int ret, i;
 
-	/* This is the only place the aliasing PPGTT gets enabled, which means
-	 * it has to happen before we bail on reset */
-	if (dev_priv->mm.aliasing_ppgtt) {
-		struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
-		ppgtt->enable(ppgtt);
-	}
+	BUG_ON(!dev_priv->ring[RCS].default_context);
 
-	/* FIXME: We should make this work, even in reset */
-	if (i915_reset_in_progress(&dev_priv->gpu_error))
+	if (i915.enable_execlists)
 		return 0;
 
-	BUG_ON(!dev_priv->ring[RCS].default_context);
-
 	for_each_ring(ring, dev_priv, i) {
 		ret = i915_switch_context(ring, ring->default_context);
 		if (ret)
@@ -527,7 +431,7 @@ int i915_gem_context_open(struct drm_device *dev, struct drm_file *file)
 	idr_init(&file_priv->context_idr);
 
 	mutex_lock(&dev->struct_mutex);
-	ctx = i915_gem_create_context(dev, file_priv, USES_FULL_PPGTT(dev));
+	ctx = i915_gem_create_context(dev, file_priv);
 	mutex_unlock(&dev->struct_mutex);
 
 	if (IS_ERR(ctx)) {
@@ -563,6 +467,7 @@ mi_set_context(struct intel_engine_cs *ring,
 	       struct intel_context *new_context,
 	       u32 hw_flags)
 {
+	u32 flags = hw_flags | MI_MM_SPACE_GTT;
 	int ret;
 
 	/* w/a: If Flush TLB Invalidation Mode is enabled, driver must do a TLB
@@ -576,6 +481,10 @@ mi_set_context(struct intel_engine_cs *ring,
 			return ret;
 	}
 
+	/* These flags are for resource streamer on HSW+ */
+	if (!IS_HASWELL(ring->dev) && INTEL_INFO(ring->dev)->gen < 8)
+		flags |= (MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN);
+
 	ret = intel_ring_begin(ring, 6);
 	if (ret)
 		return ret;
@@ -589,10 +498,7 @@ mi_set_context(struct intel_engine_cs *ring,
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
 	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(new_context->legacy_hw_ctx.rcs_state) |
-			MI_MM_SPACE_GTT |
-			MI_SAVE_EXT_STATE_EN |
-			MI_RESTORE_EXT_STATE_EN |
-			hw_flags);
+			flags);
 	/*
 	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
 	 * WaMiSetContext_Hang:snb,ivb,vlv
@@ -614,7 +520,6 @@ static int do_switch(struct intel_engine_cs *ring,
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	struct intel_context *from = ring->last_context;
-	struct i915_hw_ppgtt *ppgtt = ctx_to_ppgtt(to);
 	u32 hw_flags = 0;
 	bool uninitialized = false;
 	int ret, i;
@@ -642,8 +547,8 @@ static int do_switch(struct intel_engine_cs *ring,
 	 */
 	from = ring->last_context;
 
-	if (USES_FULL_PPGTT(ring->dev)) {
-		ret = ppgtt->switch_mm(ppgtt, ring, false);
+	if (to->ppgtt) {
+		ret = to->ppgtt->switch_mm(to->ppgtt, ring);
 		if (ret)
 			goto unpin_out;
 	}
@@ -723,6 +628,12 @@ done:
 	ring->last_context = to;
 
 	if (uninitialized) {
+		if (ring->init_context) {
+			ret = ring->init_context(ring);
+			if (ret)
+				DRM_ERROR("ring init context: %d\n", ret);
+		}
+
 		ret = i915_gem_render_state_init(ring);
 		if (ret)
 			DRM_ERROR("init render state: %d\n", ret);
@@ -743,14 +654,19 @@ unpin_out:
  *
  * The context life cycle is simple. The context refcount is incremented and
  * decremented by 1 and create and destroy. If the context is in use by the GPU,
- * it will have a refoucnt > 1. This allows us to destroy the context abstract
+ * it will have a refcount > 1. This allows us to destroy the context abstract
  * object while letting the normal object tracking destroy the backing BO.
+ *
+ * This function should not be used in execlists mode.  Instead the context is
+ * switched by writing to the ELSP and requests keep a reference to their
+ * context.
  */
 int i915_switch_context(struct intel_engine_cs *ring,
 			struct intel_context *to)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 
+	WARN_ON(i915.enable_execlists);
 	WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
 
 	if (to->legacy_hw_ctx.rcs_state == NULL) { /* We have the fake context */
@@ -766,9 +682,9 @@ int i915_switch_context(struct intel_engine_cs *ring,
 	return do_switch(ring, to);
 }
 
-static bool hw_context_enabled(struct drm_device *dev)
+static bool contexts_enabled(struct drm_device *dev)
 {
-	return to_i915(dev)->hw_context_size;
+	return i915.enable_execlists || to_i915(dev)->hw_context_size;
 }
 
 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
@@ -779,14 +695,14 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	struct intel_context *ctx;
 	int ret;
 
-	if (!hw_context_enabled(dev))
+	if (!contexts_enabled(dev))
 		return -ENODEV;
 
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
 		return ret;
 
-	ctx = i915_gem_create_context(dev, file_priv, USES_FULL_PPGTT(dev));
+	ctx = i915_gem_create_context(dev, file_priv);
 	mutex_unlock(&dev->struct_mutex);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index bbf4b12d842e..886ff2ee7a28 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -243,7 +243,7 @@ int
 i915_gem_evict_everything(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_address_space *vm;
+	struct i915_address_space *vm, *v;
 	bool lists_empty = true;
 	int ret;
 
@@ -270,7 +270,7 @@ i915_gem_evict_everything(struct drm_device *dev)
 	i915_gem_retire_requests(dev);
 
 	/* Having flushed everything, unbind() should never raise an error */
-	list_for_each_entry(vm, &dev_priv->vm_list, global_link)
+	list_for_each_entry_safe(vm, v, &dev_priv->vm_list, global_link)
 		WARN_ON(i915_gem_evict_vm(vm, false));
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 60998fc4e5b2..1a0611bb576b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -35,6 +35,7 @@
 
 #define  __EXEC_OBJECT_HAS_PIN (1<<31)
 #define  __EXEC_OBJECT_HAS_FENCE (1<<30)
+#define  __EXEC_OBJECT_NEEDS_MAP (1<<29)
 #define  __EXEC_OBJECT_NEEDS_BIAS (1<<28)
 
 #define BATCH_OFFSET_BIAS (256*1024)
@@ -94,7 +95,6 @@ eb_lookup_vmas(struct eb_vmas *eb,
 	       struct i915_address_space *vm,
 	       struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	struct drm_i915_gem_object *obj;
 	struct list_head objects;
 	int i, ret;
@@ -129,20 +129,6 @@ eb_lookup_vmas(struct eb_vmas *eb,
 	i = 0;
 	while (!list_empty(&objects)) {
 		struct i915_vma *vma;
-		struct i915_address_space *bind_vm = vm;
-
-		if (exec[i].flags & EXEC_OBJECT_NEEDS_GTT &&
-		    USES_FULL_PPGTT(vm->dev)) {
-			ret = -EINVAL;
-			goto err;
-		}
-
-		/* If we have secure dispatch, or the userspace assures us that
-		 * they know what they're doing, use the GGTT VM.
-		 */
-		if (((args->flags & I915_EXEC_SECURE) &&
-		    (i == (args->buffer_count - 1))))
-			bind_vm = &dev_priv->gtt.base;
 
 		obj = list_first_entry(&objects,
 				       struct drm_i915_gem_object,
@@ -156,7 +142,7 @@ eb_lookup_vmas(struct eb_vmas *eb,
 		 * from the (obj, vm) we don't run the risk of creating
 		 * duplicated vmas for the same vm.
 		 */
-		vma = i915_gem_obj_lookup_or_create_vma(obj, bind_vm);
+		vma = i915_gem_obj_lookup_or_create_vma(obj, vm);
 		if (IS_ERR(vma)) {
 			DRM_DEBUG("Failed to lookup VMA\n");
 			ret = PTR_ERR(vma);
@@ -307,7 +293,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint64_t delta = reloc->delta + target_offset;
-	uint32_t __iomem *reloc_entry;
+	uint64_t offset;
 	void __iomem *reloc_page;
 	int ret;
 
@@ -320,25 +306,24 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 		return ret;
 
 	/* Map the page containing the relocation we're going to perform.  */
-	reloc->offset += i915_gem_obj_ggtt_offset(obj);
+	offset = i915_gem_obj_ggtt_offset(obj);
+	offset += reloc->offset;
 	reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
-			reloc->offset & PAGE_MASK);
-	reloc_entry = (uint32_t __iomem *)
-		(reloc_page + offset_in_page(reloc->offset));
-	iowrite32(lower_32_bits(delta), reloc_entry);
+					      offset & PAGE_MASK);
+	iowrite32(lower_32_bits(delta), reloc_page + offset_in_page(offset));
 
 	if (INTEL_INFO(dev)->gen >= 8) {
-		reloc_entry += 1;
+		offset += sizeof(uint32_t);
 
-		if (offset_in_page(reloc->offset + sizeof(uint32_t)) == 0) {
+		if (offset_in_page(offset) == 0) {
 			io_mapping_unmap_atomic(reloc_page);
-			reloc_page = io_mapping_map_atomic_wc(
-					dev_priv->gtt.mappable,
-					reloc->offset + sizeof(uint32_t));
-			reloc_entry = reloc_page;
+			reloc_page =
+				io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
+							 offset);
 		}
 
-		iowrite32(upper_32_bits(delta), reloc_entry);
+		iowrite32(upper_32_bits(delta),
+			  reloc_page + offset_in_page(offset));
 	}
 
 	io_mapping_unmap_atomic(reloc_page);
@@ -535,34 +520,18 @@ i915_gem_execbuffer_relocate(struct eb_vmas *eb)
 }
 
 static int
-need_reloc_mappable(struct i915_vma *vma)
-{
-	struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
-	return entry->relocation_count && !use_cpu_reloc(vma->obj) &&
-		i915_is_ggtt(vma->vm);
-}
-
-static int
 i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
 				struct intel_engine_cs *ring,
 				bool *need_reloc)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
 	struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
-	bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4;
-	bool need_fence;
 	uint64_t flags;
 	int ret;
 
 	flags = 0;
-
-	need_fence =
-		has_fenced_gpu_access &&
-		entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
-		obj->tiling_mode != I915_TILING_NONE;
-	if (need_fence || need_reloc_mappable(vma))
+	if (entry->flags & __EXEC_OBJECT_NEEDS_MAP)
 		flags |= PIN_MAPPABLE;
-
 	if (entry->flags & EXEC_OBJECT_NEEDS_GTT)
 		flags |= PIN_GLOBAL;
 	if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS)
@@ -574,17 +543,13 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
 
 	entry->flags |= __EXEC_OBJECT_HAS_PIN;
 
-	if (has_fenced_gpu_access) {
-		if (entry->flags & EXEC_OBJECT_NEEDS_FENCE) {
-			ret = i915_gem_object_get_fence(obj);
-			if (ret)
-				return ret;
-
-			if (i915_gem_object_pin_fence(obj))
-				entry->flags |= __EXEC_OBJECT_HAS_FENCE;
+	if (entry->flags & EXEC_OBJECT_NEEDS_FENCE) {
+		ret = i915_gem_object_get_fence(obj);
+		if (ret)
+			return ret;
 
-			obj->pending_fenced_gpu_access = true;
-		}
+		if (i915_gem_object_pin_fence(obj))
+			entry->flags |= __EXEC_OBJECT_HAS_FENCE;
 	}
 
 	if (entry->offset != vma->node.start) {
@@ -601,26 +566,40 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
 }
 
 static bool
-eb_vma_misplaced(struct i915_vma *vma, bool has_fenced_gpu_access)
+need_reloc_mappable(struct i915_vma *vma)
 {
 	struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
-	struct drm_i915_gem_object *obj = vma->obj;
-	bool need_fence, need_mappable;
 
-	need_fence =
-		has_fenced_gpu_access &&
-		entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
-		obj->tiling_mode != I915_TILING_NONE;
-	need_mappable = need_fence || need_reloc_mappable(vma);
+	if (entry->relocation_count == 0)
+		return false;
+
+	if (!i915_is_ggtt(vma->vm))
+		return false;
+
+	/* See also use_cpu_reloc() */
+	if (HAS_LLC(vma->obj->base.dev))
+		return false;
 
-	WARN_ON((need_mappable || need_fence) &&
+	if (vma->obj->base.write_domain == I915_GEM_DOMAIN_CPU)
+		return false;
+
+	return true;
+}
+
+static bool
+eb_vma_misplaced(struct i915_vma *vma)
+{
+	struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
+	struct drm_i915_gem_object *obj = vma->obj;
+
+	WARN_ON(entry->flags & __EXEC_OBJECT_NEEDS_MAP &&
 	       !i915_is_ggtt(vma->vm));
 
 	if (entry->alignment &&
 	    vma->node.start & (entry->alignment - 1))
 		return true;
 
-	if (need_mappable && !obj->map_and_fenceable)
+	if (entry->flags & __EXEC_OBJECT_NEEDS_MAP && !obj->map_and_fenceable)
 		return true;
 
 	if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS &&
@@ -642,9 +621,6 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
 	bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4;
 	int retry;
 
-	if (list_empty(vmas))
-		return 0;
-
 	i915_gem_retire_requests_ring(ring);
 
 	vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm;
@@ -658,20 +634,21 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
 		obj = vma->obj;
 		entry = vma->exec_entry;
 
+		if (!has_fenced_gpu_access)
+			entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE;
 		need_fence =
-			has_fenced_gpu_access &&
 			entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
 			obj->tiling_mode != I915_TILING_NONE;
 		need_mappable = need_fence || need_reloc_mappable(vma);
 
-		if (need_mappable)
+		if (need_mappable) {
+			entry->flags |= __EXEC_OBJECT_NEEDS_MAP;
 			list_move(&vma->exec_list, &ordered_vmas);
-		else
+		} else
 			list_move_tail(&vma->exec_list, &ordered_vmas);
 
 		obj->base.pending_read_domains = I915_GEM_GPU_DOMAINS & ~I915_GEM_DOMAIN_COMMAND;
 		obj->base.pending_write_domain = 0;
-		obj->pending_fenced_gpu_access = false;
 	}
 	list_splice(&ordered_vmas, vmas);
 
@@ -696,7 +673,7 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
 			if (!drm_mm_node_allocated(&vma->node))
 				continue;
 
-			if (eb_vma_misplaced(vma, has_fenced_gpu_access))
+			if (eb_vma_misplaced(vma))
 				ret = i915_vma_unbind(vma);
 			else
 				ret = i915_gem_execbuffer_reserve_vma(vma, ring, need_relocs);
@@ -744,9 +721,6 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 	int i, total, ret;
 	unsigned count = args->buffer_count;
 
-	if (WARN_ON(list_empty(&eb->vmas)))
-		return 0;
-
 	vm = list_first_entry(&eb->vmas, struct i915_vma, exec_list)->vm;
 
 	/* We may process another execbuffer during the unlock... */
@@ -890,18 +864,24 @@ i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 }
 
 static int
-validate_exec_list(struct drm_i915_gem_exec_object2 *exec,
+validate_exec_list(struct drm_device *dev,
+		   struct drm_i915_gem_exec_object2 *exec,
 		   int count)
 {
-	int i;
 	unsigned relocs_total = 0;
 	unsigned relocs_max = UINT_MAX / sizeof(struct drm_i915_gem_relocation_entry);
+	unsigned invalid_flags;
+	int i;
+
+	invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS;
+	if (USES_FULL_PPGTT(dev))
+		invalid_flags |= EXEC_OBJECT_NEEDS_GTT;
 
 	for (i = 0; i < count; i++) {
 		char __user *ptr = to_user_ptr(exec[i].relocs_ptr);
 		int length; /* limited by fault_in_pages_readable() */
 
-		if (exec[i].flags & __EXEC_OBJECT_UNKNOWN_FLAGS)
+		if (exec[i].flags & invalid_flags)
 			return -EINVAL;
 
 		/* First check for malicious input causing overflow in
@@ -951,16 +931,26 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
 		return ERR_PTR(-EIO);
 	}
 
+	if (i915.enable_execlists && !ctx->engine[ring->id].state) {
+		int ret = intel_lr_context_deferred_create(ctx, ring);
+		if (ret) {
+			DRM_DEBUG("Could not create LRC %u: %d\n", ctx_id, ret);
+			return ERR_PTR(ret);
+		}
+	}
+
 	return ctx;
 }
 
-static void
+void
 i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 				   struct intel_engine_cs *ring)
 {
+	u32 seqno = intel_ring_get_seqno(ring);
 	struct i915_vma *vma;
 
 	list_for_each_entry(vma, vmas, exec_list) {
+		struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
 		struct drm_i915_gem_object *obj = vma->obj;
 		u32 old_read = obj->base.read_domains;
 		u32 old_write = obj->base.write_domain;
@@ -969,24 +959,31 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 		if (obj->base.write_domain == 0)
 			obj->base.pending_read_domains |= obj->base.read_domains;
 		obj->base.read_domains = obj->base.pending_read_domains;
-		obj->fenced_gpu_access = obj->pending_fenced_gpu_access;
 
 		i915_vma_move_to_active(vma, ring);
 		if (obj->base.write_domain) {
 			obj->dirty = 1;
-			obj->last_write_seqno = intel_ring_get_seqno(ring);
+			obj->last_write_seqno = seqno;
 
 			intel_fb_obj_invalidate(obj, ring);
 
 			/* update for the implicit flush after a batch */
 			obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
 		}
+		if (entry->flags & EXEC_OBJECT_NEEDS_FENCE) {
+			obj->last_fenced_seqno = seqno;
+			if (entry->flags & __EXEC_OBJECT_HAS_FENCE) {
+				struct drm_i915_private *dev_priv = to_i915(ring->dev);
+				list_move_tail(&dev_priv->fence_regs[obj->fence_reg].lru_list,
+					       &dev_priv->mm.fence_list);
+			}
+		}
 
 		trace_i915_gem_object_change_domain(obj, old_read, old_write);
 	}
 }
 
-static void
+void
 i915_gem_execbuffer_retire_commands(struct drm_device *dev,
 				    struct drm_file *file,
 				    struct intel_engine_cs *ring,
@@ -1026,14 +1023,14 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
 	return 0;
 }
 
-static int
-legacy_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
-			     struct intel_engine_cs *ring,
-			     struct intel_context *ctx,
-			     struct drm_i915_gem_execbuffer2 *args,
-			     struct list_head *vmas,
-			     struct drm_i915_gem_object *batch_obj,
-			     u64 exec_start, u32 flags)
+int
+i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
+			       struct intel_engine_cs *ring,
+			       struct intel_context *ctx,
+			       struct drm_i915_gem_execbuffer2 *args,
+			       struct list_head *vmas,
+			       struct drm_i915_gem_object *batch_obj,
+			       u64 exec_start, u32 flags)
 {
 	struct drm_clip_rect *cliprects = NULL;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1254,7 +1251,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	if (!i915_gem_check_execbuffer(args))
 		return -EINVAL;
 
-	ret = validate_exec_list(exec, args->buffer_count);
+	ret = validate_exec_list(dev, exec, args->buffer_count);
 	if (ret)
 		return ret;
 
@@ -1318,8 +1315,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	i915_gem_context_reference(ctx);
 
-	vm = ctx->vm;
-	if (!USES_FULL_PPGTT(dev))
+	if (ctx->ppgtt)
+		vm = &ctx->ppgtt->base;
+	else
 		vm = &dev_priv->gtt.base;
 
 	eb = eb_create(args);
@@ -1386,25 +1384,36 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	/* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
 	 * batch" bit. Hence we need to pin secure batches into the global gtt.
 	 * hsw should have this fixed, but bdw mucks it up again. */
-	if (flags & I915_DISPATCH_SECURE &&
-	    !batch_obj->has_global_gtt_mapping) {
-		/* When we have multiple VMs, we'll need to make sure that we
-		 * allocate space first */
-		struct i915_vma *vma = i915_gem_obj_to_ggtt(batch_obj);
-		BUG_ON(!vma);
-		vma->bind_vma(vma, batch_obj->cache_level, GLOBAL_BIND);
-	}
+	if (flags & I915_DISPATCH_SECURE) {
+		/*
+		 * So on first glance it looks freaky that we pin the batch here
+		 * outside of the reservation loop. But:
+		 * - The batch is already pinned into the relevant ppgtt, so we
+		 *   already have the backing storage fully allocated.
+		 * - No other BO uses the global gtt (well contexts, but meh),
+		 *   so we don't really have issues with mutliple objects not
+		 *   fitting due to fragmentation.
+		 * So this is actually safe.
+		 */
+		ret = i915_gem_obj_ggtt_pin(batch_obj, 0, 0);
+		if (ret)
+			goto err;
 
-	if (flags & I915_DISPATCH_SECURE)
 		exec_start += i915_gem_obj_ggtt_offset(batch_obj);
-	else
+	} else
 		exec_start += i915_gem_obj_offset(batch_obj, vm);
 
-	ret = legacy_ringbuffer_submission(dev, file, ring, ctx,
-			args, &eb->vmas, batch_obj, exec_start, flags);
-	if (ret)
-		goto err;
+	ret = dev_priv->gt.do_execbuf(dev, file, ring, ctx, args,
+				      &eb->vmas, batch_obj, exec_start, flags);
 
+	/*
+	 * FIXME: We crucially rely upon the active tracking for the (ppgtt)
+	 * batch vma for correctness. For less ugly and less fragility this
+	 * needs to be adjusted to also track the ggtt batch vma properly as
+	 * active.
+	 */
+	if (flags & I915_DISPATCH_SECURE)
+		i915_gem_object_ggtt_unpin(batch_obj);
 err:
 	/* the request owns the ref now */
 	i915_gem_context_unreference(ctx);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index e42925f76b4b..b672b843fd5e 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -33,17 +33,6 @@
 static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv);
 static void chv_setup_private_ppat(struct drm_i915_private *dev_priv);
 
-bool intel_enable_ppgtt(struct drm_device *dev, bool full)
-{
-	if (i915.enable_ppgtt == 0)
-		return false;
-
-	if (i915.enable_ppgtt == 1 && full)
-		return false;
-
-	return true;
-}
-
 static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
 {
 	if (enable_ppgtt == 0 || !HAS_ALIASING_PPGTT(dev))
@@ -78,7 +67,6 @@ static void ppgtt_bind_vma(struct i915_vma *vma,
 			   enum i915_cache_level cache_level,
 			   u32 flags);
 static void ppgtt_unbind_vma(struct i915_vma *vma);
-static int gen8_ppgtt_enable(struct i915_hw_ppgtt *ppgtt);
 
 static inline gen8_gtt_pte_t gen8_pte_encode(dma_addr_t addr,
 					     enum i915_cache_level level,
@@ -216,19 +204,12 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
 
 /* Broadwell Page Directory Pointer Descriptors */
 static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
-			   uint64_t val, bool synchronous)
+			   uint64_t val)
 {
-	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	int ret;
 
 	BUG_ON(entry >= 4);
 
-	if (synchronous) {
-		I915_WRITE(GEN8_RING_PDP_UDW(ring, entry), val >> 32);
-		I915_WRITE(GEN8_RING_PDP_LDW(ring, entry), (u32)val);
-		return 0;
-	}
-
 	ret = intel_ring_begin(ring, 6);
 	if (ret)
 		return ret;
@@ -245,8 +226,7 @@ static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
 }
 
 static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct intel_engine_cs *ring,
-			  bool synchronous)
+			  struct intel_engine_cs *ring)
 {
 	int i, ret;
 
@@ -255,7 +235,7 @@ static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
 
 	for (i = used_pd - 1; i >= 0; i--) {
 		dma_addr_t addr = ppgtt->pd_dma_addr[i];
-		ret = gen8_write_pdp(ring, i, addr, synchronous);
+		ret = gen8_write_pdp(ring, i, addr);
 		if (ret)
 			return ret;
 	}
@@ -403,9 +383,6 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
 
-	list_del(&vm->global_link);
-	drm_mm_takedown(&vm->mm);
-
 	gen8_ppgtt_unmap_pages(ppgtt);
 	gen8_ppgtt_free(ppgtt);
 }
@@ -615,7 +592,6 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
 		kunmap_atomic(pd_vaddr);
 	}
 
-	ppgtt->enable = gen8_ppgtt_enable;
 	ppgtt->switch_mm = gen8_mm_switch;
 	ppgtt->base.clear_range = gen8_ppgtt_clear_range;
 	ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
@@ -724,29 +700,10 @@ static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt)
 }
 
 static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			 struct intel_engine_cs *ring,
-			 bool synchronous)
+			 struct intel_engine_cs *ring)
 {
-	struct drm_device *dev = ppgtt->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
-	/* If we're in reset, we can assume the GPU is sufficiently idle to
-	 * manually frob these bits. Ideally we could use the ring functions,
-	 * except our error handling makes it quite difficult (can't use
-	 * intel_ring_begin, ring->flush, or intel_ring_advance)
-	 *
-	 * FIXME: We should try not to special case reset
-	 */
-	if (synchronous ||
-	    i915_reset_in_progress(&dev_priv->gpu_error)) {
-		WARN_ON(ppgtt != dev_priv->mm.aliasing_ppgtt);
-		I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
-		I915_WRITE(RING_PP_DIR_BASE(ring), get_pd_offset(ppgtt));
-		POSTING_READ(RING_PP_DIR_BASE(ring));
-		return 0;
-	}
-
 	/* NB: TLBs must be flushed and invalidated before a switch */
 	ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
 	if (ret)
@@ -768,29 +725,10 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
 }
 
 static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct intel_engine_cs *ring,
-			  bool synchronous)
+			  struct intel_engine_cs *ring)
 {
-	struct drm_device *dev = ppgtt->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
-	/* If we're in reset, we can assume the GPU is sufficiently idle to
-	 * manually frob these bits. Ideally we could use the ring functions,
-	 * except our error handling makes it quite difficult (can't use
-	 * intel_ring_begin, ring->flush, or intel_ring_advance)
-	 *
-	 * FIXME: We should try not to special case reset
-	 */
-	if (synchronous ||
-	    i915_reset_in_progress(&dev_priv->gpu_error)) {
-		WARN_ON(ppgtt != dev_priv->mm.aliasing_ppgtt);
-		I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
-		I915_WRITE(RING_PP_DIR_BASE(ring), get_pd_offset(ppgtt));
-		POSTING_READ(RING_PP_DIR_BASE(ring));
-		return 0;
-	}
-
 	/* NB: TLBs must be flushed and invalidated before a switch */
 	ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, I915_GEM_GPU_DOMAINS);
 	if (ret)
@@ -819,14 +757,11 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
 }
 
 static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct intel_engine_cs *ring,
-			  bool synchronous)
+			  struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (!synchronous)
-		return 0;
 
 	I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
 	I915_WRITE(RING_PP_DIR_BASE(ring), get_pd_offset(ppgtt));
@@ -836,39 +771,20 @@ static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
 	return 0;
 }
 
-static int gen8_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
+static void gen8_ppgtt_enable(struct drm_device *dev)
 {
-	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring;
-	int j, ret;
+	int j;
 
 	for_each_ring(ring, dev_priv, j) {
 		I915_WRITE(RING_MODE_GEN7(ring),
 			   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
-
-		/* We promise to do a switch later with FULL PPGTT. If this is
-		 * aliasing, this is the one and only switch we'll do */
-		if (USES_FULL_PPGTT(dev))
-			continue;
-
-		ret = ppgtt->switch_mm(ppgtt, ring, true);
-		if (ret)
-			goto err_out;
 	}
-
-	return 0;
-
-err_out:
-	for_each_ring(ring, dev_priv, j)
-		I915_WRITE(RING_MODE_GEN7(ring),
-			   _MASKED_BIT_DISABLE(GFX_PPGTT_ENABLE));
-	return ret;
 }
 
-static int gen7_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
+static void gen7_ppgtt_enable(struct drm_device *dev)
 {
-	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring;
 	uint32_t ecochk, ecobits;
@@ -887,31 +803,16 @@ static int gen7_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
 	I915_WRITE(GAM_ECOCHK, ecochk);
 
 	for_each_ring(ring, dev_priv, i) {
-		int ret;
 		/* GFX_MODE is per-ring on gen7+ */
 		I915_WRITE(RING_MODE_GEN7(ring),
 			   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
-
-		/* We promise to do a switch later with FULL PPGTT. If this is
-		 * aliasing, this is the one and only switch we'll do */
-		if (USES_FULL_PPGTT(dev))
-			continue;
-
-		ret = ppgtt->switch_mm(ppgtt, ring, true);
-		if (ret)
-			return ret;
 	}
-
-	return 0;
 }
 
-static int gen6_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
+static void gen6_ppgtt_enable(struct drm_device *dev)
 {
-	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *ring;
 	uint32_t ecochk, gab_ctl, ecobits;
-	int i;
 
 	ecobits = I915_READ(GAC_ECO_BITS);
 	I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_SNB_BIT |
@@ -924,14 +825,6 @@ static int gen6_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
 	I915_WRITE(GAM_ECOCHK, ecochk | ECOCHK_SNB_BIT | ECOCHK_PPGTT_CACHE64B);
 
 	I915_WRITE(GFX_MODE, _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
-
-	for_each_ring(ring, dev_priv, i) {
-		int ret = ppgtt->switch_mm(ppgtt, ring, true);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
 }
 
 /* PPGTT support for Sandybdrige/Gen6 and later */
@@ -1029,8 +922,6 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
 
-	list_del(&vm->global_link);
-	drm_mm_takedown(&ppgtt->base.mm);
 	drm_mm_remove_node(&ppgtt->node);
 
 	gen6_ppgtt_unmap_pages(ppgtt);
@@ -1151,13 +1042,10 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 
 	ppgtt->base.pte_encode = dev_priv->gtt.base.pte_encode;
 	if (IS_GEN6(dev)) {
-		ppgtt->enable = gen6_ppgtt_enable;
 		ppgtt->switch_mm = gen6_mm_switch;
 	} else if (IS_HASWELL(dev)) {
-		ppgtt->enable = gen7_ppgtt_enable;
 		ppgtt->switch_mm = hsw_mm_switch;
 	} else if (IS_GEN7(dev)) {
-		ppgtt->enable = gen7_ppgtt_enable;
 		ppgtt->switch_mm = gen7_mm_switch;
 	} else
 		BUG();
@@ -1188,39 +1076,114 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 			 ppgtt->node.size >> 20,
 			 ppgtt->node.start / PAGE_SIZE);
 
+	gen6_write_pdes(ppgtt);
+	DRM_DEBUG("Adding PPGTT at offset %x\n",
+		  ppgtt->pd_offset << 10);
+
 	return 0;
 }
 
-int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
+static int __hw_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret = 0;
 
 	ppgtt->base.dev = dev;
 	ppgtt->base.scratch = dev_priv->gtt.base.scratch;
 
 	if (INTEL_INFO(dev)->gen < 8)
-		ret = gen6_ppgtt_init(ppgtt);
+		return gen6_ppgtt_init(ppgtt);
 	else if (IS_GEN8(dev))
-		ret = gen8_ppgtt_init(ppgtt, dev_priv->gtt.base.total);
+		return gen8_ppgtt_init(ppgtt, dev_priv->gtt.base.total);
 	else
 		BUG();
+}
+int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret = 0;
 
-	if (!ret) {
-		struct drm_i915_private *dev_priv = dev->dev_private;
+	ret = __hw_ppgtt_init(dev, ppgtt);
+	if (ret == 0) {
 		kref_init(&ppgtt->ref);
 		drm_mm_init(&ppgtt->base.mm, ppgtt->base.start,
 			    ppgtt->base.total);
 		i915_init_vm(dev_priv, &ppgtt->base);
-		if (INTEL_INFO(dev)->gen < 8) {
-			gen6_write_pdes(ppgtt);
-			DRM_DEBUG("Adding PPGTT at offset %x\n",
-				  ppgtt->pd_offset << 10);
+	}
+
+	return ret;
+}
+
+int i915_ppgtt_init_hw(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring;
+	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+	int i, ret = 0;
+
+	/* In the case of execlists, PPGTT is enabled by the context descriptor
+	 * and the PDPs are contained within the context itself.  We don't
+	 * need to do anything here. */
+	if (i915.enable_execlists)
+		return 0;
+
+	if (!USES_PPGTT(dev))
+		return 0;
+
+	if (IS_GEN6(dev))
+		gen6_ppgtt_enable(dev);
+	else if (IS_GEN7(dev))
+		gen7_ppgtt_enable(dev);
+	else if (INTEL_INFO(dev)->gen >= 8)
+		gen8_ppgtt_enable(dev);
+	else
+		WARN_ON(1);
+
+	if (ppgtt) {
+		for_each_ring(ring, dev_priv, i) {
+			ret = ppgtt->switch_mm(ppgtt, ring);
+			if (ret != 0)
+				return ret;
 		}
 	}
 
 	return ret;
 }
+struct i915_hw_ppgtt *
+i915_ppgtt_create(struct drm_device *dev, struct drm_i915_file_private *fpriv)
+{
+	struct i915_hw_ppgtt *ppgtt;
+	int ret;
+
+	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+	if (!ppgtt)
+		return ERR_PTR(-ENOMEM);
+
+	ret = i915_ppgtt_init(dev, ppgtt);
+	if (ret) {
+		kfree(ppgtt);
+		return ERR_PTR(ret);
+	}
+
+	ppgtt->file_priv = fpriv;
+
+	return ppgtt;
+}
+
+void  i915_ppgtt_release(struct kref *kref)
+{
+	struct i915_hw_ppgtt *ppgtt =
+		container_of(kref, struct i915_hw_ppgtt, ref);
+
+	/* vmas should already be unbound */
+	WARN_ON(!list_empty(&ppgtt->base.active_list));
+	WARN_ON(!list_empty(&ppgtt->base.inactive_list));
+
+	list_del(&ppgtt->base.global_link);
+	drm_mm_takedown(&ppgtt->base.mm);
+
+	ppgtt->base.cleanup(&ppgtt->base);
+	kfree(ppgtt);
+}
 
 static void
 ppgtt_bind_vma(struct i915_vma *vma,
@@ -1687,10 +1650,10 @@ static void i915_gtt_color_adjust(struct drm_mm_node *node,
 	}
 }
 
-void i915_gem_setup_global_gtt(struct drm_device *dev,
-			       unsigned long start,
-			       unsigned long mappable_end,
-			       unsigned long end)
+int i915_gem_setup_global_gtt(struct drm_device *dev,
+			      unsigned long start,
+			      unsigned long mappable_end,
+			      unsigned long end)
 {
 	/* Let GEM Manage all of the aperture.
 	 *
@@ -1706,6 +1669,7 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 	struct drm_mm_node *entry;
 	struct drm_i915_gem_object *obj;
 	unsigned long hole_start, hole_end;
+	int ret;
 
 	BUG_ON(mappable_end > end);
 
@@ -1717,14 +1681,16 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 	/* Mark any preallocated objects as occupied */
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		struct i915_vma *vma = i915_gem_obj_to_vma(obj, ggtt_vm);
-		int ret;
+
 		DRM_DEBUG_KMS("reserving preallocated space: %lx + %zx\n",
 			      i915_gem_obj_ggtt_offset(obj), obj->base.size);
 
 		WARN_ON(i915_gem_obj_ggtt_bound(obj));
 		ret = drm_mm_reserve_node(&ggtt_vm->mm, &vma->node);
-		if (ret)
-			DRM_DEBUG_KMS("Reservation failed\n");
+		if (ret) {
+			DRM_DEBUG_KMS("Reservation failed: %i\n", ret);
+			return ret;
+		}
 		obj->has_global_gtt_mapping = 1;
 	}
 
@@ -1741,6 +1707,22 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 
 	/* And finally clear the reserved guard page */
 	ggtt_vm->clear_range(ggtt_vm, end - PAGE_SIZE, PAGE_SIZE, true);
+
+	if (USES_PPGTT(dev) && !USES_FULL_PPGTT(dev)) {
+		struct i915_hw_ppgtt *ppgtt;
+
+		ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+		if (!ppgtt)
+			return -ENOMEM;
+
+		ret = __hw_ppgtt_init(dev, ppgtt);
+		if (ret != 0)
+			return ret;
+
+		dev_priv->mm.aliasing_ppgtt = ppgtt;
+	}
+
+	return 0;
 }
 
 void i915_gem_init_global_gtt(struct drm_device *dev)
@@ -1754,6 +1736,25 @@ void i915_gem_init_global_gtt(struct drm_device *dev)
 	i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size);
 }
 
+void i915_global_gtt_cleanup(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_address_space *vm = &dev_priv->gtt.base;
+
+	if (dev_priv->mm.aliasing_ppgtt) {
+		struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+
+		ppgtt->base.cleanup(&ppgtt->base);
+	}
+
+	if (drm_mm_initialized(&vm->mm)) {
+		drm_mm_takedown(&vm->mm);
+		list_del(&vm->global_link);
+	}
+
+	vm->cleanup(vm);
+}
+
 static int setup_scratch_page(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2022,10 +2023,6 @@ static void gen6_gmch_remove(struct i915_address_space *vm)
 
 	struct i915_gtt *gtt = container_of(vm, struct i915_gtt, base);
 
-	if (drm_mm_initialized(&vm->mm)) {
-		drm_mm_takedown(&vm->mm);
-		list_del(&vm->global_link);
-	}
 	iounmap(gtt->gsm);
 	teardown_scratch_page(vm->dev);
 }
@@ -2058,10 +2055,6 @@ static int i915_gmch_probe(struct drm_device *dev,
 
 static void i915_gmch_remove(struct i915_address_space *vm)
 {
-	if (drm_mm_initialized(&vm->mm)) {
-		drm_mm_takedown(&vm->mm);
-		list_del(&vm->global_link);
-	}
 	intel_gmch_remove();
 }
 
@@ -2160,8 +2153,10 @@ static struct i915_vma *__i915_gem_vma_create(struct drm_i915_gem_object *obj,
 	/* Keep GGTT vmas first to make debug easier */
 	if (i915_is_ggtt(vm))
 		list_add(&vma->vma_link, &obj->vma_list);
-	else
+	else {
 		list_add_tail(&vma->vma_link, &obj->vma_list);
+		i915_ppgtt_get(i915_vm_to_ppgtt(vm));
+	}
 
 	return vma;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 8d6f7c18c404..d5c14af51e99 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -34,6 +34,8 @@
 #ifndef __I915_GEM_GTT_H__
 #define __I915_GEM_GTT_H__
 
+struct drm_i915_file_private;
+
 typedef uint32_t gen6_gtt_pte_t;
 typedef uint64_t gen8_gtt_pte_t;
 typedef gen8_gtt_pte_t gen8_ppgtt_pde_t;
@@ -258,22 +260,36 @@ struct i915_hw_ppgtt {
 		dma_addr_t *gen8_pt_dma_addr[4];
 	};
 
-	struct intel_context *ctx;
+	struct drm_i915_file_private *file_priv;
 
 	int (*enable)(struct i915_hw_ppgtt *ppgtt);
 	int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
-			 struct intel_engine_cs *ring,
-			 bool synchronous);
+			 struct intel_engine_cs *ring);
 	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
 };
 
 int i915_gem_gtt_init(struct drm_device *dev);
 void i915_gem_init_global_gtt(struct drm_device *dev);
-void i915_gem_setup_global_gtt(struct drm_device *dev, unsigned long start,
-			       unsigned long mappable_end, unsigned long end);
-
-bool intel_enable_ppgtt(struct drm_device *dev, bool full);
-int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
+int i915_gem_setup_global_gtt(struct drm_device *dev, unsigned long start,
+			      unsigned long mappable_end, unsigned long end);
+void i915_global_gtt_cleanup(struct drm_device *dev);
+
+
+int i915_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
+int i915_ppgtt_init_hw(struct drm_device *dev);
+void i915_ppgtt_release(struct kref *kref);
+struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_device *dev,
+					struct drm_i915_file_private *fpriv);
+static inline void i915_ppgtt_get(struct i915_hw_ppgtt *ppgtt)
+{
+	if (ppgtt)
+		kref_get(&ppgtt->ref);
+}
+static inline void i915_ppgtt_put(struct i915_hw_ppgtt *ppgtt)
+{
+	if (ppgtt)
+		kref_put(&ppgtt->ref, i915_ppgtt_release);
+}
 
 void i915_check_and_clear_faults(struct drm_device *dev);
 void i915_gem_suspend_gtt_mappings(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index e60be3f552a6..a9a62d75aa57 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -28,13 +28,6 @@
 #include "i915_drv.h"
 #include "intel_renderstate.h"
 
-struct render_state {
-	const struct intel_renderstate_rodata *rodata;
-	struct drm_i915_gem_object *obj;
-	u64 ggtt_offset;
-	int gen;
-};
-
 static const struct intel_renderstate_rodata *
 render_state_get_rodata(struct drm_device *dev, const int gen)
 {
@@ -127,30 +120,47 @@ static int render_state_setup(struct render_state *so)
 	return 0;
 }
 
-static void render_state_fini(struct render_state *so)
+void i915_gem_render_state_fini(struct render_state *so)
 {
 	i915_gem_object_ggtt_unpin(so->obj);
 	drm_gem_object_unreference(&so->obj->base);
 }
 
-int i915_gem_render_state_init(struct intel_engine_cs *ring)
+int i915_gem_render_state_prepare(struct intel_engine_cs *ring,
+				  struct render_state *so)
 {
-	struct render_state so;
 	int ret;
 
 	if (WARN_ON(ring->id != RCS))
 		return -ENOENT;
 
-	ret = render_state_init(&so, ring->dev);
+	ret = render_state_init(so, ring->dev);
 	if (ret)
 		return ret;
 
-	if (so.rodata == NULL)
+	if (so->rodata == NULL)
 		return 0;
 
-	ret = render_state_setup(&so);
+	ret = render_state_setup(so);
+	if (ret) {
+		i915_gem_render_state_fini(so);
+		return ret;
+	}
+
+	return 0;
+}
+
+int i915_gem_render_state_init(struct intel_engine_cs *ring)
+{
+	struct render_state so;
+	int ret;
+
+	ret = i915_gem_render_state_prepare(ring, &so);
 	if (ret)
-		goto out;
+		return ret;
+
+	if (so.rodata == NULL)
+		return 0;
 
 	ret = ring->dispatch_execbuffer(ring,
 					so.ggtt_offset,
@@ -164,6 +174,6 @@ int i915_gem_render_state_init(struct intel_engine_cs *ring)
 	ret = __i915_add_request(ring, NULL, so.obj, NULL);
 	/* __i915_add_request moves object to inactive if it fails */
 out:
-	render_state_fini(&so);
+	i915_gem_render_state_fini(&so);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.h b/drivers/gpu/drm/i915/i915_gem_render_state.h
new file mode 100644
index 000000000000..c44961ed3fad
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.h
@@ -0,0 +1,47 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _I915_GEM_RENDER_STATE_H_
+#define _I915_GEM_RENDER_STATE_H_
+
+#include <linux/types.h>
+
+struct intel_renderstate_rodata {
+	const u32 *reloc;
+	const u32 *batch;
+	const u32 batch_items;
+};
+
+struct render_state {
+	const struct intel_renderstate_rodata *rodata;
+	struct drm_i915_gem_object *obj;
+	u64 ggtt_offset;
+	int gen;
+};
+
+int i915_gem_render_state_init(struct intel_engine_cs *ring);
+void i915_gem_render_state_fini(struct render_state *so);
+int i915_gem_render_state_prepare(struct intel_engine_cs *ring,
+				  struct render_state *so);
+
+#endif /* _I915_GEM_RENDER_STATE_H_ */
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 21c025a209c0..85fda6b803e4 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -289,6 +289,7 @@ void i915_gem_cleanup_stolen(struct drm_device *dev)
 int i915_gem_init_stolen(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 tmp;
 	int bios_reserved = 0;
 
 #ifdef CONFIG_INTEL_IOMMU
@@ -308,8 +309,16 @@ int i915_gem_init_stolen(struct drm_device *dev)
 	DRM_DEBUG_KMS("found %zd bytes of stolen memory at %08lx\n",
 		      dev_priv->gtt.stolen_size, dev_priv->mm.stolen_base);
 
-	if (IS_VALLEYVIEW(dev))
-		bios_reserved = 1024*1024; /* top 1M on VLV/BYT */
+	if (INTEL_INFO(dev)->gen >= 8) {
+		tmp = I915_READ(GEN7_BIOS_RESERVED);
+		tmp >>= GEN8_BIOS_RESERVED_SHIFT;
+		tmp &= GEN8_BIOS_RESERVED_MASK;
+		bios_reserved = (1024*1024) << tmp;
+	} else if (IS_GEN7(dev)) {
+		tmp = I915_READ(GEN7_BIOS_RESERVED);
+		bios_reserved = tmp & GEN7_BIOS_RESERVED_256K ?
+			256*1024 : 1024*1024;
+	}
 
 	if (WARN_ON(bios_reserved > dev_priv->gtt.stolen_size))
 		return 0;
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index cb150e8b4336..2cefb597df6d 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -91,7 +91,14 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
 	uint32_t swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
 	uint32_t swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
 
-	if (IS_VALLEYVIEW(dev)) {
+	if (INTEL_INFO(dev)->gen >= 8 || IS_VALLEYVIEW(dev)) {
+		/*
+		 * On BDW+, swizzling is not used. We leave the CPU memory
+		 * controller in charge of optimizing memory accesses without
+		 * the extra address manipulation GPU side.
+		 *
+		 * VLV and CHV don't have GPU swizzling.
+		 */
 		swizzle_x = I915_BIT_6_SWIZZLE_NONE;
 		swizzle_y = I915_BIT_6_SWIZZLE_NONE;
 	} else if (INTEL_INFO(dev)->gen >= 6) {
@@ -376,7 +383,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 
 		if (ret == 0) {
 			obj->fence_dirty =
-				obj->fenced_gpu_access ||
+				obj->last_fenced_seqno ||
 				obj->fence_reg != I915_FENCE_REG_NONE;
 
 			obj->tiling_mode = args->tiling_mode;
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index d38413997379..d182058383a9 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -293,15 +293,23 @@ i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj)
 static struct i915_mmu_notifier *
 i915_mmu_notifier_find(struct i915_mm_struct *mm)
 {
-	if (mm->mn == NULL) {
-		down_write(&mm->mm->mmap_sem);
-		mutex_lock(&to_i915(mm->dev)->mm_lock);
-		if (mm->mn == NULL)
-			mm->mn = i915_mmu_notifier_create(mm->mm);
-		mutex_unlock(&to_i915(mm->dev)->mm_lock);
-		up_write(&mm->mm->mmap_sem);
+	struct i915_mmu_notifier *mn = mm->mn;
+
+	mn = mm->mn;
+	if (mn)
+		return mn;
+
+	down_write(&mm->mm->mmap_sem);
+	mutex_lock(&to_i915(mm->dev)->mm_lock);
+	if ((mn = mm->mn) == NULL) {
+		mn = i915_mmu_notifier_create(mm->mm);
+		if (!IS_ERR(mn))
+			mm->mn = mn;
 	}
-	return mm->mn;
+	mutex_unlock(&to_i915(mm->dev)->mm_lock);
+	up_write(&mm->mm->mmap_sem);
+
+	return mn;
 }
 
 static int
@@ -681,16 +689,15 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 static void
 i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj)
 {
-	struct scatterlist *sg;
-	int i;
+	struct sg_page_iter sg_iter;
 
 	BUG_ON(obj->userptr.work != NULL);
 
 	if (obj->madv != I915_MADV_WILLNEED)
 		obj->dirty = 0;
 
-	for_each_sg(obj->pages->sgl, sg, obj->pages->nents, i) {
-		struct page *page = sg_page(sg);
+	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
+		struct page *page = sg_page_iter_page(&sg_iter);
 
 		if (obj->dirty)
 			set_page_dirty(page);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index eab41f9390f8..2c87a797213f 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -192,10 +192,10 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
 				struct drm_i915_error_buffer *err,
 				int count)
 {
-	err_printf(m, "%s [%d]:\n", name, count);
+	err_printf(m, "  %s [%d]:\n", name, count);
 
 	while (count--) {
-		err_printf(m, "  %08x %8u %02x %02x %x %x",
+		err_printf(m, "    %08x %8u %02x %02x %x %x",
 			   err->gtt_offset,
 			   err->size,
 			   err->read_domains,
@@ -208,7 +208,7 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
 		err_puts(m, err->userptr ? " userptr" : "");
 		err_puts(m, err->ring != -1 ? " " : "");
 		err_puts(m, ring_str(err->ring));
-		err_puts(m, i915_cache_level_str(err->cache_level));
+		err_puts(m, i915_cache_level_str(m->i915, err->cache_level));
 
 		if (err->name)
 			err_printf(m, " (name: %d)", err->name);
@@ -393,15 +393,17 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		i915_ring_error_state(m, dev, &error->ring[i]);
 	}
 
-	if (error->active_bo)
+	for (i = 0; i < error->vm_count; i++) {
+		err_printf(m, "vm[%d]\n", i);
+
 		print_error_buffers(m, "Active",
-				    error->active_bo[0],
-				    error->active_bo_count[0]);
+				    error->active_bo[i],
+				    error->active_bo_count[i]);
 
-	if (error->pinned_bo)
 		print_error_buffers(m, "Pinned",
-				    error->pinned_bo[0],
-				    error->pinned_bo_count[0]);
+				    error->pinned_bo[i],
+				    error->pinned_bo_count[i]);
+	}
 
 	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
 		obj = error->ring[i].batchbuffer;
@@ -492,9 +494,11 @@ out:
 }
 
 int i915_error_state_buf_init(struct drm_i915_error_state_buf *ebuf,
+			      struct drm_i915_private *i915,
 			      size_t count, loff_t pos)
 {
 	memset(ebuf, 0, sizeof(*ebuf));
+	ebuf->i915 = i915;
 
 	/* We need to have enough room to store any i915_error_state printf
 	 * so that we can move it to start position.
@@ -556,24 +560,54 @@ static void i915_error_state_free(struct kref *error_ref)
 }
 
 static struct drm_i915_error_object *
-i915_error_object_create_sized(struct drm_i915_private *dev_priv,
-			       struct drm_i915_gem_object *src,
-			       struct i915_address_space *vm,
-			       const int num_pages)
+i915_error_object_create(struct drm_i915_private *dev_priv,
+			 struct drm_i915_gem_object *src,
+			 struct i915_address_space *vm)
 {
 	struct drm_i915_error_object *dst;
-	int i;
+	int num_pages;
+	bool use_ggtt;
+	int i = 0;
 	u32 reloc_offset;
 
 	if (src == NULL || src->pages == NULL)
 		return NULL;
 
+	num_pages = src->base.size >> PAGE_SHIFT;
+
 	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), GFP_ATOMIC);
 	if (dst == NULL)
 		return NULL;
 
-	reloc_offset = dst->gtt_offset = i915_gem_obj_offset(src, vm);
-	for (i = 0; i < num_pages; i++) {
+	if (i915_gem_obj_bound(src, vm))
+		dst->gtt_offset = i915_gem_obj_offset(src, vm);
+	else
+		dst->gtt_offset = -1;
+
+	reloc_offset = dst->gtt_offset;
+	use_ggtt = (src->cache_level == I915_CACHE_NONE &&
+		    i915_is_ggtt(vm) &&
+		    src->has_global_gtt_mapping &&
+		    reloc_offset + num_pages * PAGE_SIZE <= dev_priv->gtt.mappable_end);
+
+	/* Cannot access stolen address directly, try to use the aperture */
+	if (src->stolen) {
+		use_ggtt = true;
+
+		if (!src->has_global_gtt_mapping)
+			goto unwind;
+
+		reloc_offset = i915_gem_obj_ggtt_offset(src);
+		if (reloc_offset + num_pages * PAGE_SIZE > dev_priv->gtt.mappable_end)
+			goto unwind;
+	}
+
+	/* Cannot access snooped pages through the aperture */
+	if (use_ggtt && src->cache_level != I915_CACHE_NONE && !HAS_LLC(dev_priv->dev))
+		goto unwind;
+
+	dst->page_count = num_pages;
+	while (num_pages--) {
 		unsigned long flags;
 		void *d;
 
@@ -582,10 +616,7 @@ i915_error_object_create_sized(struct drm_i915_private *dev_priv,
 			goto unwind;
 
 		local_irq_save(flags);
-		if (src->cache_level == I915_CACHE_NONE &&
-		    reloc_offset < dev_priv->gtt.mappable_end &&
-		    src->has_global_gtt_mapping &&
-		    i915_is_ggtt(vm)) {
+		if (use_ggtt) {
 			void __iomem *s;
 
 			/* Simply ignore tiling or any overlapping fence.
@@ -597,14 +628,6 @@ i915_error_object_create_sized(struct drm_i915_private *dev_priv,
 						     reloc_offset);
 			memcpy_fromio(d, s, PAGE_SIZE);
 			io_mapping_unmap_atomic(s);
-		} else if (src->stolen) {
-			unsigned long offset;
-
-			offset = dev_priv->mm.stolen_base;
-			offset += src->stolen->start;
-			offset += i << PAGE_SHIFT;
-
-			memcpy_fromio(d, (void __iomem *) offset, PAGE_SIZE);
 		} else {
 			struct page *page;
 			void *s;
@@ -621,11 +644,9 @@ i915_error_object_create_sized(struct drm_i915_private *dev_priv,
 		}
 		local_irq_restore(flags);
 
-		dst->pages[i] = d;
-
+		dst->pages[i++] = d;
 		reloc_offset += PAGE_SIZE;
 	}
-	dst->page_count = num_pages;
 
 	return dst;
 
@@ -635,22 +656,19 @@ unwind:
 	kfree(dst);
 	return NULL;
 }
-#define i915_error_object_create(dev_priv, src, vm) \
-	i915_error_object_create_sized((dev_priv), (src), (vm), \
-				       (src)->base.size>>PAGE_SHIFT)
-
 #define i915_error_ggtt_object_create(dev_priv, src) \
-	i915_error_object_create_sized((dev_priv), (src), &(dev_priv)->gtt.base, \
-				       (src)->base.size>>PAGE_SHIFT)
+	i915_error_object_create((dev_priv), (src), &(dev_priv)->gtt.base)
 
 static void capture_bo(struct drm_i915_error_buffer *err,
-		       struct drm_i915_gem_object *obj)
+		       struct i915_vma *vma)
 {
+	struct drm_i915_gem_object *obj = vma->obj;
+
 	err->size = obj->base.size;
 	err->name = obj->base.name;
 	err->rseqno = obj->last_read_seqno;
 	err->wseqno = obj->last_write_seqno;
-	err->gtt_offset = i915_gem_obj_ggtt_offset(obj);
+	err->gtt_offset = vma->node.start;
 	err->read_domains = obj->base.read_domains;
 	err->write_domain = obj->base.write_domain;
 	err->fence_reg = obj->fence_reg;
@@ -674,7 +692,7 @@ static u32 capture_active_bo(struct drm_i915_error_buffer *err,
 	int i = 0;
 
 	list_for_each_entry(vma, head, mm_list) {
-		capture_bo(err++, vma->obj);
+		capture_bo(err++, vma);
 		if (++i == count)
 			break;
 	}
@@ -683,21 +701,27 @@ static u32 capture_active_bo(struct drm_i915_error_buffer *err,
 }
 
 static u32 capture_pinned_bo(struct drm_i915_error_buffer *err,
-			     int count, struct list_head *head)
+			     int count, struct list_head *head,
+			     struct i915_address_space *vm)
 {
 	struct drm_i915_gem_object *obj;
-	int i = 0;
+	struct drm_i915_error_buffer * const first = err;
+	struct drm_i915_error_buffer * const last = err + count;
 
 	list_for_each_entry(obj, head, global_list) {
-		if (!i915_gem_obj_is_pinned(obj))
-			continue;
+		struct i915_vma *vma;
 
-		capture_bo(err++, obj);
-		if (++i == count)
+		if (err == last)
 			break;
+
+		list_for_each_entry(vma, &obj->vma_list, vma_link)
+			if (vma->vm == vm && vma->pin_count > 0) {
+				capture_bo(err++, vma);
+				break;
+			}
 	}
 
-	return i;
+	return err - first;
 }
 
 /* Generate a semi-unique error code. The code is not meant to have meaning, The
@@ -890,9 +914,6 @@ static void i915_record_ring_state(struct drm_device *dev,
 		ering->hws = I915_READ(mmio);
 	}
 
-	ering->cpu_ring_head = ring->buffer->head;
-	ering->cpu_ring_tail = ring->buffer->tail;
-
 	ering->hangcheck_score = ring->hangcheck.score;
 	ering->hangcheck_action = ring->hangcheck.action;
 
@@ -955,6 +976,7 @@ static void i915_gem_record_rings(struct drm_device *dev,
 
 	for (i = 0; i < I915_NUM_RINGS; i++) {
 		struct intel_engine_cs *ring = &dev_priv->ring[i];
+		struct intel_ringbuffer *rbuf;
 
 		error->ring[i].pid = -1;
 
@@ -967,6 +989,12 @@ static void i915_gem_record_rings(struct drm_device *dev,
 
 		request = i915_gem_find_active_request(ring);
 		if (request) {
+			struct i915_address_space *vm;
+
+			vm = request->ctx && request->ctx->ppgtt ?
+				&request->ctx->ppgtt->base :
+				&dev_priv->gtt.base;
+
 			/* We need to copy these to an anonymous buffer
 			 * as the simplest method to avoid being overwritten
 			 * by userspace.
@@ -974,12 +1002,9 @@ static void i915_gem_record_rings(struct drm_device *dev,
 			error->ring[i].batchbuffer =
 				i915_error_object_create(dev_priv,
 							 request->batch_obj,
-							 request->ctx ?
-							 request->ctx->vm :
-							 &dev_priv->gtt.base);
+							 vm);
 
-			if (HAS_BROKEN_CS_TLB(dev_priv->dev) &&
-			    ring->scratch.obj)
+			if (HAS_BROKEN_CS_TLB(dev_priv->dev))
 				error->ring[i].wa_batchbuffer =
 					i915_error_ggtt_object_create(dev_priv,
 							     ring->scratch.obj);
@@ -998,12 +1023,27 @@ static void i915_gem_record_rings(struct drm_device *dev,
 			}
 		}
 
+		if (i915.enable_execlists) {
+			/* TODO: This is only a small fix to keep basic error
+			 * capture working, but we need to add more information
+			 * for it to be useful (e.g. dump the context being
+			 * executed).
+			 */
+			if (request)
+				rbuf = request->ctx->engine[ring->id].ringbuf;
+			else
+				rbuf = ring->default_context->engine[ring->id].ringbuf;
+		} else
+			rbuf = ring->buffer;
+
+		error->ring[i].cpu_ring_head = rbuf->head;
+		error->ring[i].cpu_ring_tail = rbuf->tail;
+
 		error->ring[i].ringbuffer =
-			i915_error_ggtt_object_create(dev_priv, ring->buffer->obj);
+			i915_error_ggtt_object_create(dev_priv, rbuf->obj);
 
-		if (ring->status_page.obj)
-			error->ring[i].hws_page =
-				i915_error_ggtt_object_create(dev_priv, ring->status_page.obj);
+		error->ring[i].hws_page =
+			i915_error_ggtt_object_create(dev_priv, ring->status_page.obj);
 
 		i915_gem_record_active_context(ring, error, &error->ring[i]);
 
@@ -1049,9 +1089,14 @@ static void i915_gem_capture_vm(struct drm_i915_private *dev_priv,
 	list_for_each_entry(vma, &vm->active_list, mm_list)
 		i++;
 	error->active_bo_count[ndx] = i;
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
-		if (i915_gem_obj_is_pinned(obj))
-			i++;
+
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
+		list_for_each_entry(vma, &obj->vma_list, vma_link)
+			if (vma->vm == vm && vma->pin_count > 0) {
+				i++;
+				break;
+			}
+	}
 	error->pinned_bo_count[ndx] = i - error->active_bo_count[ndx];
 
 	if (i) {
@@ -1070,7 +1115,7 @@ static void i915_gem_capture_vm(struct drm_i915_private *dev_priv,
 		error->pinned_bo_count[ndx] =
 			capture_pinned_bo(pinned_bo,
 					  error->pinned_bo_count[ndx],
-					  &dev_priv->mm.bound_list);
+					  &dev_priv->mm.bound_list, vm);
 	error->active_bo[ndx] = active_bo;
 	error->pinned_bo[ndx] = pinned_bo;
 }
@@ -1091,8 +1136,25 @@ static void i915_gem_capture_buffers(struct drm_i915_private *dev_priv,
 	error->pinned_bo_count = kcalloc(cnt, sizeof(*error->pinned_bo_count),
 					 GFP_ATOMIC);
 
-	list_for_each_entry(vm, &dev_priv->vm_list, global_link)
-		i915_gem_capture_vm(dev_priv, error, vm, i++);
+	if (error->active_bo == NULL ||
+	    error->pinned_bo == NULL ||
+	    error->active_bo_count == NULL ||
+	    error->pinned_bo_count == NULL) {
+		kfree(error->active_bo);
+		kfree(error->active_bo_count);
+		kfree(error->pinned_bo);
+		kfree(error->pinned_bo_count);
+
+		error->active_bo = NULL;
+		error->active_bo_count = NULL;
+		error->pinned_bo = NULL;
+		error->pinned_bo_count = NULL;
+	} else {
+		list_for_each_entry(vm, &dev_priv->vm_list, global_link)
+			i915_gem_capture_vm(dev_priv, error, vm, i++);
+
+		error->vm_count = cnt;
+	}
 }
 
 /* Capture all registers which don't fit into another category. */
@@ -1295,11 +1357,11 @@ void i915_destroy_error_state(struct drm_device *dev)
 		kref_put(&error->ref, i915_error_state_free);
 }
 
-const char *i915_cache_level_str(int type)
+const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 {
 	switch (type) {
 	case I915_CACHE_NONE: return " uncached";
-	case I915_CACHE_LLC: return " snooped or LLC";
+	case I915_CACHE_LLC: return HAS_LLC(i915) ? " LLC" : " snooped";
 	case I915_CACHE_L3_LLC: return " L3+LLC";
 	case I915_CACHE_WT: return " WT";
 	default: return "";
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 0050ee9470f1..3201986bf25e 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -151,7 +151,7 @@ ironlake_disable_display_irq(struct drm_i915_private *dev_priv, u32 mask)
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (!intel_irqs_enabled(dev_priv))
+	if (WARN_ON(!intel_irqs_enabled(dev_priv)))
 		return;
 
 	if ((dev_priv->irq_mask & mask) != mask) {
@@ -238,7 +238,7 @@ static bool ivb_can_enable_err_int(struct drm_device *dev)
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
 
 		if (crtc->cpu_fifo_underrun_disabled)
@@ -296,7 +296,7 @@ static bool cpt_can_enable_serr_int(struct drm_device *dev)
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
 
 		if (crtc->pch_fifo_underrun_disabled)
@@ -497,7 +497,7 @@ static bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
 	old = !intel_crtc->cpu_fifo_underrun_disabled;
 	intel_crtc->cpu_fifo_underrun_disabled = !enable;
 
-	if (INTEL_INFO(dev)->gen < 5 || IS_VALLEYVIEW(dev))
+	if (HAS_GMCH_DISPLAY(dev))
 		i9xx_set_fifo_underrun_reporting(dev, pipe, enable, old);
 	else if (IS_GEN5(dev) || IS_GEN6(dev))
 		ironlake_set_fifo_underrun_reporting(dev, pipe, enable);
@@ -1020,7 +1020,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 
 	/* In vblank? */
 	if (in_vbl)
-		ret |= DRM_SCANOUTPOS_INVBL;
+		ret |= DRM_SCANOUTPOS_IN_VBLANK;
 
 	return ret;
 }
@@ -1322,10 +1322,10 @@ static u32 vlv_c0_residency(struct drm_i915_private *dev_priv,
  * @dev_priv: DRM device private
  *
  */
-static u32 vlv_calc_delay_from_C0_counters(struct drm_i915_private *dev_priv)
+static int vlv_calc_delay_from_C0_counters(struct drm_i915_private *dev_priv)
 {
 	u32 residency_C0_up = 0, residency_C0_down = 0;
-	u8 new_delay, adj;
+	int new_delay, adj;
 
 	dev_priv->rps.ei_interrupt_count++;
 
@@ -1627,6 +1627,7 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 				       struct drm_i915_private *dev_priv,
 				       u32 master_ctl)
 {
+	struct intel_engine_cs *ring;
 	u32 rcs, bcs, vcs;
 	uint32_t tmp = 0;
 	irqreturn_t ret = IRQ_NONE;
@@ -1636,12 +1637,20 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 		if (tmp) {
 			I915_WRITE(GEN8_GT_IIR(0), tmp);
 			ret = IRQ_HANDLED;
+
 			rcs = tmp >> GEN8_RCS_IRQ_SHIFT;
-			bcs = tmp >> GEN8_BCS_IRQ_SHIFT;
+			ring = &dev_priv->ring[RCS];
 			if (rcs & GT_RENDER_USER_INTERRUPT)
-				notify_ring(dev, &dev_priv->ring[RCS]);
+				notify_ring(dev, ring);
+			if (rcs & GT_CONTEXT_SWITCH_INTERRUPT)
+				intel_execlists_handle_ctx_events(ring);
+
+			bcs = tmp >> GEN8_BCS_IRQ_SHIFT;
+			ring = &dev_priv->ring[BCS];
 			if (bcs & GT_RENDER_USER_INTERRUPT)
-				notify_ring(dev, &dev_priv->ring[BCS]);
+				notify_ring(dev, ring);
+			if (bcs & GT_CONTEXT_SWITCH_INTERRUPT)
+				intel_execlists_handle_ctx_events(ring);
 		} else
 			DRM_ERROR("The master control interrupt lied (GT0)!\n");
 	}
@@ -1651,12 +1660,20 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 		if (tmp) {
 			I915_WRITE(GEN8_GT_IIR(1), tmp);
 			ret = IRQ_HANDLED;
+
 			vcs = tmp >> GEN8_VCS1_IRQ_SHIFT;
+			ring = &dev_priv->ring[VCS];
 			if (vcs & GT_RENDER_USER_INTERRUPT)
-				notify_ring(dev, &dev_priv->ring[VCS]);
+				notify_ring(dev, ring);
+			if (vcs & GT_CONTEXT_SWITCH_INTERRUPT)
+				intel_execlists_handle_ctx_events(ring);
+
 			vcs = tmp >> GEN8_VCS2_IRQ_SHIFT;
+			ring = &dev_priv->ring[VCS2];
 			if (vcs & GT_RENDER_USER_INTERRUPT)
-				notify_ring(dev, &dev_priv->ring[VCS2]);
+				notify_ring(dev, ring);
+			if (vcs & GT_CONTEXT_SWITCH_INTERRUPT)
+				intel_execlists_handle_ctx_events(ring);
 		} else
 			DRM_ERROR("The master control interrupt lied (GT1)!\n");
 	}
@@ -1677,9 +1694,13 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 		if (tmp) {
 			I915_WRITE(GEN8_GT_IIR(3), tmp);
 			ret = IRQ_HANDLED;
+
 			vcs = tmp >> GEN8_VECS_IRQ_SHIFT;
+			ring = &dev_priv->ring[VECS];
 			if (vcs & GT_RENDER_USER_INTERRUPT)
-				notify_ring(dev, &dev_priv->ring[VECS]);
+				notify_ring(dev, ring);
+			if (vcs & GT_CONTEXT_SWITCH_INTERRUPT)
+				intel_execlists_handle_ctx_events(ring);
 		} else
 			DRM_ERROR("The master control interrupt lied (GT3)!\n");
 	}
@@ -1772,7 +1793,9 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev,
 				long_hpd = (dig_hotplug_reg >> dig_shift) & PORTB_HOTPLUG_LONG_DETECT;
 			}
 
-			DRM_DEBUG_DRIVER("digital hpd port %d %d\n", port, long_hpd);
+			DRM_DEBUG_DRIVER("digital hpd port %c - %s\n",
+					 port_name(port),
+					 long_hpd ? "long" : "short");
 			/* for long HPD pulses we want to have the digital queue happen,
 			   but we still want HPD storm detection to function. */
 			if (long_hpd) {
@@ -1984,14 +2007,9 @@ static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
 
 static bool intel_pipe_handle_vblank(struct drm_device *dev, enum pipe pipe)
 {
-	struct intel_crtc *crtc;
-
 	if (!drm_handle_vblank(dev, pipe))
 		return false;
 
-	crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe));
-	wake_up(&crtc->vbl_wait);
-
 	return true;
 }
 
@@ -2002,7 +2020,7 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir)
 	int pipe;
 
 	spin_lock(&dev_priv->irq_lock);
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		int reg;
 		u32 mask, iir_bit = 0;
 
@@ -2047,9 +2065,10 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir)
 	}
 	spin_unlock(&dev_priv->irq_lock);
 
-	for_each_pipe(pipe) {
-		if (pipe_stats[pipe] & PIPE_START_VBLANK_INTERRUPT_STATUS)
-			intel_pipe_handle_vblank(dev, pipe);
+	for_each_pipe(dev_priv, pipe) {
+		if (pipe_stats[pipe] & PIPE_START_VBLANK_INTERRUPT_STATUS &&
+		    intel_pipe_handle_vblank(dev, pipe))
+			intel_check_page_flip(dev, pipe);
 
 		if (pipe_stats[pipe] & PLANE_FLIP_DONE_INT_STATUS_VLV) {
 			intel_prepare_page_flip(dev, pipe);
@@ -2216,7 +2235,7 @@ static void ibx_irq_handler(struct drm_device *dev, u32 pch_iir)
 		DRM_ERROR("PCH poison interrupt\n");
 
 	if (pch_iir & SDE_FDI_MASK)
-		for_each_pipe(pipe)
+		for_each_pipe(dev_priv, pipe)
 			DRM_DEBUG_DRIVER("  pipe %c FDI IIR: 0x%08x\n",
 					 pipe_name(pipe),
 					 I915_READ(FDI_RX_IIR(pipe)));
@@ -2247,7 +2266,7 @@ static void ivb_err_int_handler(struct drm_device *dev)
 	if (err_int & ERR_INT_POISON)
 		DRM_ERROR("Poison interrupt\n");
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		if (err_int & ERR_INT_FIFO_UNDERRUN(pipe)) {
 			if (intel_set_cpu_fifo_underrun_reporting(dev, pipe,
 								  false))
@@ -2324,7 +2343,7 @@ static void cpt_irq_handler(struct drm_device *dev, u32 pch_iir)
 		DRM_DEBUG_DRIVER("Audio CP change interrupt\n");
 
 	if (pch_iir & SDE_FDI_MASK_CPT)
-		for_each_pipe(pipe)
+		for_each_pipe(dev_priv, pipe)
 			DRM_DEBUG_DRIVER("  pipe %c FDI IIR: 0x%08x\n",
 					 pipe_name(pipe),
 					 I915_READ(FDI_RX_IIR(pipe)));
@@ -2347,9 +2366,10 @@ static void ilk_display_irq_handler(struct drm_device *dev, u32 de_iir)
 	if (de_iir & DE_POISON)
 		DRM_ERROR("Poison interrupt\n");
 
-	for_each_pipe(pipe) {
-		if (de_iir & DE_PIPE_VBLANK(pipe))
-			intel_pipe_handle_vblank(dev, pipe);
+	for_each_pipe(dev_priv, pipe) {
+		if (de_iir & DE_PIPE_VBLANK(pipe) &&
+		    intel_pipe_handle_vblank(dev, pipe))
+			intel_check_page_flip(dev, pipe);
 
 		if (de_iir & DE_PIPE_FIFO_UNDERRUN(pipe))
 			if (intel_set_cpu_fifo_underrun_reporting(dev, pipe, false))
@@ -2397,9 +2417,10 @@ static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir)
 	if (de_iir & DE_GSE_IVB)
 		intel_opregion_asle_intr(dev);
 
-	for_each_pipe(pipe) {
-		if (de_iir & (DE_PIPE_VBLANK_IVB(pipe)))
-			intel_pipe_handle_vblank(dev, pipe);
+	for_each_pipe(dev_priv, pipe) {
+		if (de_iir & (DE_PIPE_VBLANK_IVB(pipe)) &&
+		    intel_pipe_handle_vblank(dev, pipe))
+			intel_check_page_flip(dev, pipe);
 
 		/* plane/pipes map 1:1 on ilk+ */
 		if (de_iir & DE_PLANE_FLIP_DONE_IVB(pipe)) {
@@ -2544,7 +2565,7 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 			DRM_ERROR("The master control interrupt lied (DE PORT)!\n");
 	}
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		uint32_t pipe_iir;
 
 		if (!(master_ctl & GEN8_DE_PIPE_IRQ(pipe)))
@@ -2554,8 +2575,9 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 		if (pipe_iir) {
 			ret = IRQ_HANDLED;
 			I915_WRITE(GEN8_DE_PIPE_IIR(pipe), pipe_iir);
-			if (pipe_iir & GEN8_PIPE_VBLANK)
-				intel_pipe_handle_vblank(dev, pipe);
+			if (pipe_iir & GEN8_PIPE_VBLANK &&
+			    intel_pipe_handle_vblank(dev, pipe))
+				intel_check_page_flip(dev, pipe);
 
 			if (pipe_iir & GEN8_PIPE_PRIMARY_FLIP_DONE) {
 				intel_prepare_page_flip(dev, pipe);
@@ -2763,7 +2785,7 @@ static void i915_report_and_clear_eir(struct drm_device *dev)
 
 	if (eir & I915_ERROR_MEMORY_REFRESH) {
 		pr_err("memory refresh error:\n");
-		for_each_pipe(pipe)
+		for_each_pipe(dev_priv, pipe)
 			pr_err("pipe %c stat: 0x%08x\n",
 			       pipe_name(pipe), I915_READ(PIPESTAT(pipe)));
 		/* pipestat has already been acked */
@@ -2860,52 +2882,6 @@ void i915_handle_error(struct drm_device *dev, bool wedged,
 	schedule_work(&dev_priv->gpu_error.work);
 }
 
-static void __always_unused i915_pageflip_stall_check(struct drm_device *dev, int pipe)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_i915_gem_object *obj;
-	struct intel_unpin_work *work;
-	unsigned long flags;
-	bool stall_detected;
-
-	/* Ignore early vblank irqs */
-	if (intel_crtc == NULL)
-		return;
-
-	spin_lock_irqsave(&dev->event_lock, flags);
-	work = intel_crtc->unpin_work;
-
-	if (work == NULL ||
-	    atomic_read(&work->pending) >= INTEL_FLIP_COMPLETE ||
-	    !work->enable_stall_check) {
-		/* Either the pending flip IRQ arrived, or we're too early. Don't check */
-		spin_unlock_irqrestore(&dev->event_lock, flags);
-		return;
-	}
-
-	/* Potential stall - if we see that the flip has happened, assume a missed interrupt */
-	obj = work->pending_flip_obj;
-	if (INTEL_INFO(dev)->gen >= 4) {
-		int dspsurf = DSPSURF(intel_crtc->plane);
-		stall_detected = I915_HI_DISPBASE(I915_READ(dspsurf)) ==
-					i915_gem_obj_ggtt_offset(obj);
-	} else {
-		int dspaddr = DSPADDR(intel_crtc->plane);
-		stall_detected = I915_READ(dspaddr) == (i915_gem_obj_ggtt_offset(obj) +
-							crtc->y * crtc->primary->fb->pitches[0] +
-							crtc->x * crtc->primary->fb->bits_per_pixel/8);
-	}
-
-	spin_unlock_irqrestore(&dev->event_lock, flags);
-
-	if (stall_detected) {
-		DRM_DEBUG_DRIVER("Pageflip stall detected\n");
-		intel_prepare_page_flip(dev, intel_crtc->plane);
-	}
-}
-
 /* Called from drm generic code, passed 'crtc' which
  * we use as a pipe index
  */
@@ -3441,7 +3417,7 @@ static void valleyview_irq_preinstall(struct drm_device *dev)
 
 	I915_WRITE(PORT_HOTPLUG_EN, 0);
 	I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		I915_WRITE(PIPESTAT(pipe), 0xffff);
 	I915_WRITE(VLV_IIR, 0xffffffff);
 	I915_WRITE(VLV_IMR, 0xffffffff);
@@ -3467,7 +3443,7 @@ static void gen8_irq_reset(struct drm_device *dev)
 
 	gen8_gt_irq_reset(dev_priv);
 
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		if (intel_display_power_enabled(dev_priv,
 						POWER_DOMAIN_PIPE(pipe)))
 			GEN8_IRQ_RESET_NDX(DE_PIPE, pipe);
@@ -3510,7 +3486,7 @@ static void cherryview_irq_preinstall(struct drm_device *dev)
 	I915_WRITE(PORT_HOTPLUG_EN, 0);
 	I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
 
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		I915_WRITE(PIPESTAT(pipe), 0xffff);
 
 	I915_WRITE(VLV_IMR, 0xffffffff);
@@ -3522,18 +3498,17 @@ static void cherryview_irq_preinstall(struct drm_device *dev)
 static void ibx_hpd_irq_setup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct intel_encoder *intel_encoder;
 	u32 hotplug_irqs, hotplug, enabled_irqs = 0;
 
 	if (HAS_PCH_IBX(dev)) {
 		hotplug_irqs = SDE_HOTPLUG_MASK;
-		list_for_each_entry(intel_encoder, &mode_config->encoder_list, base.head)
+		for_each_intel_encoder(dev, intel_encoder)
 			if (dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark == HPD_ENABLED)
 				enabled_irqs |= hpd_ibx[intel_encoder->hpd_pin];
 	} else {
 		hotplug_irqs = SDE_HOTPLUG_MASK_CPT;
-		list_for_each_entry(intel_encoder, &mode_config->encoder_list, base.head)
+		for_each_intel_encoder(dev, intel_encoder)
 			if (dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark == HPD_ENABLED)
 				enabled_irqs |= hpd_cpt[intel_encoder->hpd_pin];
 	}
@@ -3782,28 +3757,31 @@ static int valleyview_irq_postinstall(struct drm_device *dev)
 
 static void gen8_gt_irq_postinstall(struct drm_i915_private *dev_priv)
 {
-	int i;
-
 	/* These are interrupts we'll toggle with the ring mask register */
 	uint32_t gt_interrupts[] = {
 		GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
+			GT_CONTEXT_SWITCH_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
 			GT_RENDER_L3_PARITY_ERROR_INTERRUPT |
-			GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT,
+			GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT |
+			GT_CONTEXT_SWITCH_INTERRUPT << GEN8_BCS_IRQ_SHIFT,
 		GT_RENDER_USER_INTERRUPT << GEN8_VCS1_IRQ_SHIFT |
-			GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT,
+			GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS1_IRQ_SHIFT |
+			GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT |
+			GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS2_IRQ_SHIFT,
 		0,
-		GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT
+		GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT |
+			GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VECS_IRQ_SHIFT
 		};
 
-	for (i = 0; i < ARRAY_SIZE(gt_interrupts); i++)
-		GEN8_IRQ_INIT_NDX(GT, i, ~gt_interrupts[i], gt_interrupts[i]);
-
 	dev_priv->pm_irq_mask = 0xffffffff;
+	GEN8_IRQ_INIT_NDX(GT, 0, ~gt_interrupts[0], gt_interrupts[0]);
+	GEN8_IRQ_INIT_NDX(GT, 1, ~gt_interrupts[1], gt_interrupts[1]);
+	GEN8_IRQ_INIT_NDX(GT, 2, dev_priv->pm_irq_mask, dev_priv->pm_rps_events);
+	GEN8_IRQ_INIT_NDX(GT, 3, ~gt_interrupts[3], gt_interrupts[3]);
 }
 
 static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 {
-	struct drm_device *dev = dev_priv->dev;
 	uint32_t de_pipe_masked = GEN8_PIPE_PRIMARY_FLIP_DONE |
 		GEN8_PIPE_CDCLK_CRC_DONE |
 		GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
@@ -3814,7 +3792,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	dev_priv->de_irq_mask[PIPE_B] = ~de_pipe_masked;
 	dev_priv->de_irq_mask[PIPE_C] = ~de_pipe_masked;
 
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		if (intel_display_power_enabled(dev_priv,
 				POWER_DOMAIN_PIPE(pipe)))
 			GEN8_IRQ_INIT_NDX(DE_PIPE, pipe,
@@ -3859,12 +3837,12 @@ static int cherryview_irq_postinstall(struct drm_device *dev)
 	 */
 	dev_priv->irq_mask = ~enable_mask;
 
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		I915_WRITE(PIPESTAT(pipe), 0xffff);
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
 	i915_enable_pipestat(dev_priv, PIPE_A, PIPE_GMBUS_INTERRUPT_STATUS);
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		i915_enable_pipestat(dev_priv, pipe, pipestat_enable);
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
@@ -3901,7 +3879,7 @@ static void valleyview_irq_uninstall(struct drm_device *dev)
 
 	I915_WRITE(VLV_MASTER_IER, 0);
 
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		I915_WRITE(PIPESTAT(pipe), 0xffff);
 
 	I915_WRITE(HWSTAM, 0xffffffff);
@@ -3963,7 +3941,7 @@ do {							\
 	I915_WRITE(PORT_HOTPLUG_EN, 0);
 	I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
 
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		I915_WRITE(PIPESTAT(pipe), 0xffff);
 
 	I915_WRITE(VLV_IMR, 0xffffffff);
@@ -3987,7 +3965,7 @@ static void i8xx_irq_preinstall(struct drm_device * dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe;
 
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		I915_WRITE(PIPESTAT(pipe), 0);
 	I915_WRITE16(IMR, 0xffff);
 	I915_WRITE16(IER, 0x0);
@@ -4041,7 +4019,7 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 		return false;
 
 	if ((iir & flip_pending) == 0)
-		return false;
+		goto check_page_flip;
 
 	intel_prepare_page_flip(dev, plane);
 
@@ -4052,11 +4030,14 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 	 * an interrupt per se, we watch for the change at vblank.
 	 */
 	if (I915_READ16(ISR) & flip_pending)
-		return false;
+		goto check_page_flip;
 
 	intel_finish_page_flip(dev, pipe);
-
 	return true;
+
+check_page_flip:
+	intel_check_page_flip(dev, pipe);
+	return false;
 }
 
 static irqreturn_t i8xx_irq_handler(int irq, void *arg)
@@ -4087,7 +4068,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 					  "Command parser error, iir 0x%08x",
 					  iir);
 
-		for_each_pipe(pipe) {
+		for_each_pipe(dev_priv, pipe) {
 			int reg = PIPESTAT(pipe);
 			pipe_stats[pipe] = I915_READ(reg);
 
@@ -4107,7 +4088,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		if (iir & I915_USER_INTERRUPT)
 			notify_ring(dev, &dev_priv->ring[RCS]);
 
-		for_each_pipe(pipe) {
+		for_each_pipe(dev_priv, pipe) {
 			int plane = pipe;
 			if (HAS_FBC(dev))
 				plane = !plane;
@@ -4135,7 +4116,7 @@ static void i8xx_irq_uninstall(struct drm_device * dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe;
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		/* Clear enable bits; then clear status bits */
 		I915_WRITE(PIPESTAT(pipe), 0);
 		I915_WRITE(PIPESTAT(pipe), I915_READ(PIPESTAT(pipe)));
@@ -4156,7 +4137,7 @@ static void i915_irq_preinstall(struct drm_device * dev)
 	}
 
 	I915_WRITE16(HWSTAM, 0xeffe);
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		I915_WRITE(PIPESTAT(pipe), 0);
 	I915_WRITE(IMR, 0xffffffff);
 	I915_WRITE(IER, 0x0);
@@ -4226,7 +4207,7 @@ static bool i915_handle_vblank(struct drm_device *dev,
 		return false;
 
 	if ((iir & flip_pending) == 0)
-		return false;
+		goto check_page_flip;
 
 	intel_prepare_page_flip(dev, plane);
 
@@ -4237,11 +4218,14 @@ static bool i915_handle_vblank(struct drm_device *dev,
 	 * an interrupt per se, we watch for the change at vblank.
 	 */
 	if (I915_READ(ISR) & flip_pending)
-		return false;
+		goto check_page_flip;
 
 	intel_finish_page_flip(dev, pipe);
-
 	return true;
+
+check_page_flip:
+	intel_check_page_flip(dev, pipe);
+	return false;
 }
 
 static irqreturn_t i915_irq_handler(int irq, void *arg)
@@ -4271,7 +4255,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 					  "Command parser error, iir 0x%08x",
 					  iir);
 
-		for_each_pipe(pipe) {
+		for_each_pipe(dev_priv, pipe) {
 			int reg = PIPESTAT(pipe);
 			pipe_stats[pipe] = I915_READ(reg);
 
@@ -4297,7 +4281,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		if (iir & I915_USER_INTERRUPT)
 			notify_ring(dev, &dev_priv->ring[RCS]);
 
-		for_each_pipe(pipe) {
+		for_each_pipe(dev_priv, pipe) {
 			int plane = pipe;
 			if (HAS_FBC(dev))
 				plane = !plane;
@@ -4355,7 +4339,7 @@ static void i915_irq_uninstall(struct drm_device * dev)
 	}
 
 	I915_WRITE16(HWSTAM, 0xffff);
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		/* Clear enable bits; then clear status bits */
 		I915_WRITE(PIPESTAT(pipe), 0);
 		I915_WRITE(PIPESTAT(pipe), I915_READ(PIPESTAT(pipe)));
@@ -4375,7 +4359,7 @@ static void i965_irq_preinstall(struct drm_device * dev)
 	I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
 
 	I915_WRITE(HWSTAM, 0xeffe);
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		I915_WRITE(PIPESTAT(pipe), 0);
 	I915_WRITE(IMR, 0xffffffff);
 	I915_WRITE(IER, 0x0);
@@ -4444,7 +4428,6 @@ static int i965_irq_postinstall(struct drm_device *dev)
 static void i915_hpd_irq_setup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct intel_encoder *intel_encoder;
 	u32 hotplug_en;
 
@@ -4455,7 +4438,7 @@ static void i915_hpd_irq_setup(struct drm_device *dev)
 		hotplug_en &= ~HOTPLUG_INT_EN_MASK;
 		/* Note HDMI and DP share hotplug bits */
 		/* enable bits are the same for all generations */
-		list_for_each_entry(intel_encoder, &mode_config->encoder_list, base.head)
+		for_each_intel_encoder(dev, intel_encoder)
 			if (dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark == HPD_ENABLED)
 				hotplug_en |= hpd_mask_i915[intel_encoder->hpd_pin];
 		/* Programming the CRT detection parameters tends
@@ -4501,7 +4484,7 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 					  "Command parser error, iir 0x%08x",
 					  iir);
 
-		for_each_pipe(pipe) {
+		for_each_pipe(dev_priv, pipe) {
 			int reg = PIPESTAT(pipe);
 			pipe_stats[pipe] = I915_READ(reg);
 
@@ -4532,7 +4515,7 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		if (iir & I915_BSD_USER_INTERRUPT)
 			notify_ring(dev, &dev_priv->ring[VCS]);
 
-		for_each_pipe(pipe) {
+		for_each_pipe(dev_priv, pipe) {
 			if (pipe_stats[pipe] & PIPE_START_VBLANK_INTERRUPT_STATUS &&
 			    i915_handle_vblank(dev, pipe, pipe, iir))
 				flip_mask &= ~DISPLAY_PLANE_FLIP_PENDING(pipe);
@@ -4589,12 +4572,12 @@ static void i965_irq_uninstall(struct drm_device * dev)
 	I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
 
 	I915_WRITE(HWSTAM, 0xffffffff);
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		I915_WRITE(PIPESTAT(pipe), 0);
 	I915_WRITE(IMR, 0xffffffff);
 	I915_WRITE(IER, 0x0);
 
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		I915_WRITE(PIPESTAT(pipe),
 			   I915_READ(PIPESTAT(pipe)) & 0x8000ffff);
 	I915_WRITE(IIR, I915_READ(IIR));
@@ -4652,8 +4635,8 @@ void intel_irq_init(struct drm_device *dev)
 	INIT_WORK(&dev_priv->l3_parity.error_work, ivybridge_parity_work);
 
 	/* Let's track the enabled rps events */
-	if (IS_VALLEYVIEW(dev))
-		/* WaGsvRC0ResidenncyMethod:VLV */
+	if (IS_VALLEYVIEW(dev) && !IS_CHERRYVIEW(dev))
+		/* WaGsvRC0ResidencyMethod:vlv */
 		dev_priv->pm_rps_events = GEN6_PM_RP_UP_EI_EXPIRED;
 	else
 		dev_priv->pm_rps_events = GEN6_PM_RPS_EVENTS;
@@ -4680,6 +4663,14 @@ void intel_irq_init(struct drm_device *dev)
 		dev->max_vblank_count = 0xffffff; /* only 24 bits of frame count */
 	}
 
+	/*
+	 * Opt out of the vblank disable timer on everything except gen2.
+	 * Gen2 doesn't have a hardware frame counter and so depends on
+	 * vblank interrupts to produce sane vblank seuquence numbers.
+	 */
+	if (!IS_GEN2(dev))
+		dev->vblank_disable_immediate = true;
+
 	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
 		dev->driver->get_vblank_timestamp = i915_get_vblank_timestamp;
 		dev->driver->get_scanout_position = i915_get_crtc_scanoutpos;
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 9842fd2e742a..c91cb2033cc5 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -35,6 +35,7 @@ struct i915_params i915 __read_mostly = {
 	.vbt_sdvo_panel_type = -1,
 	.enable_rc6 = -1,
 	.enable_fbc = -1,
+	.enable_execlists = 0,
 	.enable_hangcheck = true,
 	.enable_ppgtt = -1,
 	.enable_psr = 0,
@@ -118,6 +119,11 @@ MODULE_PARM_DESC(enable_ppgtt,
 	"Override PPGTT usage. "
 	"(-1=auto [default], 0=disabled, 1=aliasing, 2=full)");
 
+module_param_named(enable_execlists, i915.enable_execlists, int, 0400);
+MODULE_PARM_DESC(enable_execlists,
+	"Override execlists usage. "
+	"(-1=auto, 0=disabled [default], 1=enabled)");
+
 module_param_named(enable_psr, i915.enable_psr, int, 0600);
 MODULE_PARM_DESC(enable_psr, "Enable PSR (default: false)");
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f29b44c86a2f..c01e5f31430e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -143,6 +143,14 @@
 #define GAB_CTL				0x24000
 #define   GAB_CTL_CONT_AFTER_PAGEFAULT	(1<<8)
 
+#define GEN7_BIOS_RESERVED		0x1082C0
+#define GEN7_BIOS_RESERVED_1M		(0 << 5)
+#define GEN7_BIOS_RESERVED_256K		(1 << 5)
+#define GEN8_BIOS_RESERVED_SHIFT       7
+#define GEN7_BIOS_RESERVED_MASK        0x1
+#define GEN8_BIOS_RESERVED_MASK        0x3
+
+
 /* VGA stuff */
 
 #define VGA_ST01_MDA 0x3ba
@@ -272,6 +280,7 @@
 #define   MI_SEMAPHORE_POLL		(1<<15)
 #define   MI_SEMAPHORE_SAD_GTE_SDD	(1<<12)
 #define MI_STORE_DWORD_IMM	MI_INSTR(0x20, 1)
+#define MI_STORE_DWORD_IMM_GEN8	MI_INSTR(0x20, 2)
 #define   MI_MEM_VIRTUAL	(1 << 22) /* 965+ only */
 #define MI_STORE_DWORD_INDEX	MI_INSTR(0x21, 1)
 #define   MI_STORE_DWORD_INDEX_SHIFT 2
@@ -282,6 +291,7 @@
  *   address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
  */
 #define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*(x)-1)
+#define   MI_LRI_FORCE_POSTED		(1<<12)
 #define MI_STORE_REGISTER_MEM(x) MI_INSTR(0x24, 2*(x)-1)
 #define MI_STORE_REGISTER_MEM_GEN8(x) MI_INSTR(0x24, 3*(x)-1)
 #define   MI_SRM_LRM_GLOBAL_GTT		(1<<22)
@@ -501,10 +511,26 @@
 #define BUNIT_REG_BISOC				0x11
 
 #define PUNIT_REG_DSPFREQ			0x36
+#define   DSPFREQSTAT_SHIFT_CHV			24
+#define   DSPFREQSTAT_MASK_CHV			(0x1f << DSPFREQSTAT_SHIFT_CHV)
+#define   DSPFREQGUAR_SHIFT_CHV			8
+#define   DSPFREQGUAR_MASK_CHV			(0x1f << DSPFREQGUAR_SHIFT_CHV)
 #define   DSPFREQSTAT_SHIFT			30
 #define   DSPFREQSTAT_MASK			(0x3 << DSPFREQSTAT_SHIFT)
 #define   DSPFREQGUAR_SHIFT			14
 #define   DSPFREQGUAR_MASK			(0x3 << DSPFREQGUAR_SHIFT)
+#define   _DP_SSC(val, pipe)			((val) << (2 * (pipe)))
+#define   DP_SSC_MASK(pipe)			_DP_SSC(0x3, (pipe))
+#define   DP_SSC_PWR_ON(pipe)			_DP_SSC(0x0, (pipe))
+#define   DP_SSC_CLK_GATE(pipe)			_DP_SSC(0x1, (pipe))
+#define   DP_SSC_RESET(pipe)			_DP_SSC(0x2, (pipe))
+#define   DP_SSC_PWR_GATE(pipe)			_DP_SSC(0x3, (pipe))
+#define   _DP_SSS(val, pipe)			((val) << (2 * (pipe) + 16))
+#define   DP_SSS_MASK(pipe)			_DP_SSS(0x3, (pipe))
+#define   DP_SSS_PWR_ON(pipe)			_DP_SSS(0x0, (pipe))
+#define   DP_SSS_CLK_GATE(pipe)			_DP_SSS(0x1, (pipe))
+#define   DP_SSS_RESET(pipe)			_DP_SSS(0x2, (pipe))
+#define   DP_SSS_PWR_GATE(pipe)			_DP_SSS(0x3, (pipe))
 
 /* See the PUNIT HAS v0.8 for the below bits */
 enum punit_power_well {
@@ -518,6 +544,11 @@ enum punit_power_well {
 	PUNIT_POWER_WELL_DPIO_TX_C_LANES_23	= 9,
 	PUNIT_POWER_WELL_DPIO_RX0		= 10,
 	PUNIT_POWER_WELL_DPIO_RX1		= 11,
+	PUNIT_POWER_WELL_DPIO_CMN_D		= 12,
+	/* FIXME: guesswork below */
+	PUNIT_POWER_WELL_DPIO_TX_D_LANES_01	= 13,
+	PUNIT_POWER_WELL_DPIO_TX_D_LANES_23	= 14,
+	PUNIT_POWER_WELL_DPIO_RX2		= 15,
 
 	PUNIT_POWER_WELL_NUM,
 };
@@ -838,8 +869,8 @@ enum punit_power_well {
 
 #define _VLV_TX_DW2_CH0			0x8288
 #define _VLV_TX_DW2_CH1			0x8488
-#define   DPIO_SWING_MARGIN_SHIFT	16
-#define   DPIO_SWING_MARGIN_MASK	(0xff << DPIO_SWING_MARGIN_SHIFT)
+#define   DPIO_SWING_MARGIN000_SHIFT	16
+#define   DPIO_SWING_MARGIN000_MASK	(0xff << DPIO_SWING_MARGIN000_SHIFT)
 #define   DPIO_UNIQ_TRANS_SCALE_SHIFT	8
 #define VLV_TX_DW2(ch) _PORT(ch, _VLV_TX_DW2_CH0, _VLV_TX_DW2_CH1)
 
@@ -847,12 +878,16 @@ enum punit_power_well {
 #define _VLV_TX_DW3_CH1			0x848c
 /* The following bit for CHV phy */
 #define   DPIO_TX_UNIQ_TRANS_SCALE_EN	(1<<27)
+#define   DPIO_SWING_MARGIN101_SHIFT	16
+#define   DPIO_SWING_MARGIN101_MASK	(0xff << DPIO_SWING_MARGIN101_SHIFT)
 #define VLV_TX_DW3(ch) _PORT(ch, _VLV_TX_DW3_CH0, _VLV_TX_DW3_CH1)
 
 #define _VLV_TX_DW4_CH0			0x8290
 #define _VLV_TX_DW4_CH1			0x8490
 #define   DPIO_SWING_DEEMPH9P5_SHIFT	24
 #define   DPIO_SWING_DEEMPH9P5_MASK	(0xff << DPIO_SWING_DEEMPH9P5_SHIFT)
+#define   DPIO_SWING_DEEMPH6P0_SHIFT	16
+#define   DPIO_SWING_DEEMPH6P0_MASK	(0xff << DPIO_SWING_DEEMPH6P0_SHIFT)
 #define VLV_TX_DW4(ch) _PORT(ch, _VLV_TX_DW4_CH0, _VLV_TX_DW4_CH1)
 
 #define _VLV_TX3_DW4_CH0		0x690
@@ -1003,6 +1038,13 @@ enum punit_power_well {
 #define   PGTBL_ADDRESS_LO_MASK	0xfffff000 /* bits [31:12] */
 #define   PGTBL_ADDRESS_HI_MASK	0x000000f0 /* bits [35:32] (gen4) */
 #define PGTBL_ER	0x02024
+#define PRB0_BASE (0x2030-0x30)
+#define PRB1_BASE (0x2040-0x30) /* 830,gen3 */
+#define PRB2_BASE (0x2050-0x30) /* gen3 */
+#define SRB0_BASE (0x2100-0x30) /* gen2 */
+#define SRB1_BASE (0x2110-0x30) /* gen2 */
+#define SRB2_BASE (0x2120-0x30) /* 830 */
+#define SRB3_BASE (0x2130-0x30) /* 830 */
 #define RENDER_RING_BASE	0x02000
 #define BSD_RING_BASE		0x04000
 #define GEN6_BSD_RING_BASE	0x12000
@@ -1064,6 +1106,7 @@ enum punit_power_well {
 #define RING_ACTHD_UDW(base)	((base)+0x5c)
 #define RING_NOPID(base)	((base)+0x94)
 #define RING_IMR(base)		((base)+0xa8)
+#define RING_HWSTAM(base)	((base)+0x98)
 #define RING_TIMESTAMP(base)	((base)+0x358)
 #define   TAIL_ADDR		0x001FFFF8
 #define   HEAD_WRAP_COUNT	0xFFE00000
@@ -1248,6 +1291,10 @@ enum punit_power_well {
 #define   INSTPM_TLB_INVALIDATE	(1<<9)
 #define   INSTPM_SYNC_FLUSH	(1<<5)
 #define ACTHD	        0x020c8
+#define MEM_MODE	0x020cc
+#define   MEM_DISPLAY_B_TRICKLE_FEED_DISABLE (1<<3) /* 830 only */
+#define   MEM_DISPLAY_A_TRICKLE_FEED_DISABLE (1<<2) /* 830/845 only */
+#define   MEM_DISPLAY_TRICKLE_FEED_DISABLE (1<<2) /* 85x only */
 #define FW_BLC		0x020d8
 #define FW_BLC2		0x020dc
 #define FW_BLC_SELF	0x020e0 /* 915+ only */
@@ -1380,6 +1427,7 @@ enum punit_power_well {
 #define GT_BSD_CS_ERROR_INTERRUPT		(1 << 15)
 #define GT_BSD_USER_INTERRUPT			(1 << 12)
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1	(1 << 11) /* hsw+; rsvd on snb, ivb, vlv */
+#define GT_CONTEXT_SWITCH_INTERRUPT		(1 <<  8)
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT	(1 <<  5) /* !snb */
 #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT	(1 <<  4)
 #define GT_RENDER_CS_MASTER_ERROR_INTERRUPT	(1 <<  3)
@@ -1519,6 +1567,7 @@ enum punit_power_well {
 /* Framebuffer compression for Ironlake */
 #define ILK_DPFC_CB_BASE	0x43200
 #define ILK_DPFC_CONTROL	0x43208
+#define   FBC_CTL_FALSE_COLOR	(1<<10)
 /* The bit 28-8 is reserved */
 #define   DPFC_RESERVED		(0x1FFFFF00)
 #define ILK_DPFC_RECOMP_CTL	0x4320c
@@ -1675,12 +1724,9 @@ enum punit_power_well {
 #define DPIO_PHY_STATUS			(VLV_DISPLAY_BASE + 0x6240)
 #define   DPLL_PORTD_READY_MASK		(0xf)
 #define DISPLAY_PHY_CONTROL (VLV_DISPLAY_BASE + 0x60100)
-#define   PHY_COM_LANE_RESET_DEASSERT(phy, val) \
-				((phy == DPIO_PHY0) ? (val | 1) : (val | 2))
-#define   PHY_COM_LANE_RESET_ASSERT(phy, val) \
-				((phy == DPIO_PHY0) ? (val & ~1) : (val & ~2))
+#define   PHY_COM_LANE_RESET_DEASSERT(phy) (1 << (phy))
 #define DISPLAY_PHY_STATUS (VLV_DISPLAY_BASE + 0x60104)
-#define   PHY_POWERGOOD(phy)	((phy == DPIO_PHY0) ? (1<<31) : (1<<30))
+#define   PHY_POWERGOOD(phy)	(((phy) == DPIO_PHY0) ? (1<<31) : (1<<30))
 
 /*
  * The i830 generation, in LVDS mode, defines P1 as the bit number set within
@@ -2397,6 +2443,7 @@ enum punit_power_well {
 #define _PIPEASRC	0x6001c
 #define _BCLRPAT_A	0x60020
 #define _VSYNCSHIFT_A	0x60028
+#define _PIPE_MULT_A	0x6002c
 
 /* Pipe B timing regs */
 #define _HTOTAL_B	0x61000
@@ -2408,6 +2455,7 @@ enum punit_power_well {
 #define _PIPEBSRC	0x6101c
 #define _BCLRPAT_B	0x61020
 #define _VSYNCSHIFT_B	0x61028
+#define _PIPE_MULT_B	0x6102c
 
 #define TRANSCODER_A_OFFSET 0x60000
 #define TRANSCODER_B_OFFSET 0x61000
@@ -2428,6 +2476,7 @@ enum punit_power_well {
 #define BCLRPAT(trans) _TRANSCODER2(trans, _BCLRPAT_A)
 #define VSYNCSHIFT(trans) _TRANSCODER2(trans, _VSYNCSHIFT_A)
 #define PIPESRC(trans) _TRANSCODER2(trans, _PIPEASRC)
+#define PIPE_MULT(trans) _TRANSCODER2(trans, _PIPE_MULT_A)
 
 /* HSW+ eDP PSR registers */
 #define EDP_PSR_BASE(dev)                       (IS_HASWELL(dev) ? 0x64800 : 0x6f800)
@@ -3476,6 +3525,8 @@ enum punit_power_well {
 #define   DP_LINK_TRAIN_OFF		(3 << 28)
 #define   DP_LINK_TRAIN_MASK		(3 << 28)
 #define   DP_LINK_TRAIN_SHIFT		28
+#define   DP_LINK_TRAIN_PAT_3_CHV	(1 << 14)
+#define   DP_LINK_TRAIN_MASK_CHV	((3 << 28)|(1<<14))
 
 /* CPT Link training mode */
 #define   DP_LINK_TRAIN_PAT_1_CPT	(0 << 8)
@@ -3732,7 +3783,6 @@ enum punit_power_well {
 #define   PIPE_VSYNC_INTERRUPT_STATUS		(1UL<<9)
 #define   PIPE_DISPLAY_LINE_COMPARE_STATUS	(1UL<<8)
 #define   PIPE_DPST_EVENT_STATUS		(1UL<<7)
-#define   PIPE_LEGACY_BLC_EVENT_STATUS		(1UL<<6)
 #define   PIPE_A_PSR_STATUS_VLV			(1UL<<6)
 #define   PIPE_LEGACY_BLC_EVENT_STATUS		(1UL<<6)
 #define   PIPE_ODD_FIELD_INTERRUPT_STATUS	(1UL<<5)
@@ -3842,73 +3892,151 @@ enum punit_power_well {
 #define   DSPARB_BEND_SHIFT	9 /* on 855 */
 #define   DSPARB_AEND_SHIFT	0
 
+/* pnv/gen4/g4x/vlv/chv */
 #define DSPFW1			(dev_priv->info.display_mmio_offset + 0x70034)
-#define   DSPFW_SR_SHIFT	23
-#define   DSPFW_SR_MASK		(0x1ff<<23)
-#define   DSPFW_CURSORB_SHIFT	16
-#define   DSPFW_CURSORB_MASK	(0x3f<<16)
-#define   DSPFW_PLANEB_SHIFT	8
-#define   DSPFW_PLANEB_MASK	(0x7f<<8)
-#define   DSPFW_PLANEA_MASK	(0x7f)
+#define   DSPFW_SR_SHIFT		23
+#define   DSPFW_SR_MASK			(0x1ff<<23)
+#define   DSPFW_CURSORB_SHIFT		16
+#define   DSPFW_CURSORB_MASK		(0x3f<<16)
+#define   DSPFW_PLANEB_SHIFT		8
+#define   DSPFW_PLANEB_MASK		(0x7f<<8)
+#define   DSPFW_PLANEB_MASK_VLV		(0xff<<8) /* vlv/chv */
+#define   DSPFW_PLANEA_SHIFT		0
+#define   DSPFW_PLANEA_MASK		(0x7f<<0)
+#define   DSPFW_PLANEA_MASK_VLV		(0xff<<0) /* vlv/chv */
 #define DSPFW2			(dev_priv->info.display_mmio_offset + 0x70038)
-#define   DSPFW_CURSORA_MASK	0x00003f00
-#define   DSPFW_CURSORA_SHIFT	8
-#define   DSPFW_PLANEC_MASK	(0x7f)
+#define   DSPFW_FBC_SR_EN		(1<<31)	  /* g4x */
+#define   DSPFW_FBC_SR_SHIFT		28
+#define   DSPFW_FBC_SR_MASK		(0x7<<28) /* g4x */
+#define   DSPFW_FBC_HPLL_SR_SHIFT	24
+#define   DSPFW_FBC_HPLL_SR_MASK	(0xf<<24) /* g4x */
+#define   DSPFW_SPRITEB_SHIFT		(16)
+#define   DSPFW_SPRITEB_MASK		(0x7f<<16) /* g4x */
+#define   DSPFW_SPRITEB_MASK_VLV	(0xff<<16) /* vlv/chv */
+#define   DSPFW_CURSORA_SHIFT		8
+#define   DSPFW_CURSORA_MASK		(0x3f<<8)
+#define   DSPFW_PLANEC_SHIFT_OLD	0
+#define   DSPFW_PLANEC_MASK_OLD		(0x7f<<0) /* pre-gen4 sprite C */
+#define   DSPFW_SPRITEA_SHIFT		0
+#define   DSPFW_SPRITEA_MASK		(0x7f<<0) /* g4x */
+#define   DSPFW_SPRITEA_MASK_VLV	(0xff<<0) /* vlv/chv */
 #define DSPFW3			(dev_priv->info.display_mmio_offset + 0x7003c)
-#define   DSPFW_HPLL_SR_EN	(1<<31)
-#define   DSPFW_CURSOR_SR_SHIFT	24
+#define   DSPFW_HPLL_SR_EN		(1<<31)
 #define   PINEVIEW_SELF_REFRESH_EN	(1<<30)
+#define   DSPFW_CURSOR_SR_SHIFT		24
 #define   DSPFW_CURSOR_SR_MASK		(0x3f<<24)
 #define   DSPFW_HPLL_CURSOR_SHIFT	16
 #define   DSPFW_HPLL_CURSOR_MASK	(0x3f<<16)
-#define   DSPFW_HPLL_SR_MASK		(0x1ff)
-#define DSPFW4			(dev_priv->info.display_mmio_offset + 0x70070)
-#define DSPFW7			(dev_priv->info.display_mmio_offset + 0x7007c)
+#define   DSPFW_HPLL_SR_SHIFT		0
+#define   DSPFW_HPLL_SR_MASK		(0x1ff<<0)
+
+/* vlv/chv */
+#define DSPFW4			(VLV_DISPLAY_BASE + 0x70070)
+#define   DSPFW_SPRITEB_WM1_SHIFT	16
+#define   DSPFW_SPRITEB_WM1_MASK	(0xff<<16)
+#define   DSPFW_CURSORA_WM1_SHIFT	8
+#define   DSPFW_CURSORA_WM1_MASK	(0x3f<<8)
+#define   DSPFW_SPRITEA_WM1_SHIFT	0
+#define   DSPFW_SPRITEA_WM1_MASK	(0xff<<0)
+#define DSPFW5			(VLV_DISPLAY_BASE + 0x70074)
+#define   DSPFW_PLANEB_WM1_SHIFT	24
+#define   DSPFW_PLANEB_WM1_MASK		(0xff<<24)
+#define   DSPFW_PLANEA_WM1_SHIFT	16
+#define   DSPFW_PLANEA_WM1_MASK		(0xff<<16)
+#define   DSPFW_CURSORB_WM1_SHIFT	8
+#define   DSPFW_CURSORB_WM1_MASK	(0x3f<<8)
+#define   DSPFW_CURSOR_SR_WM1_SHIFT	0
+#define   DSPFW_CURSOR_SR_WM1_MASK	(0x3f<<0)
+#define DSPFW6			(VLV_DISPLAY_BASE + 0x70078)
+#define   DSPFW_SR_WM1_SHIFT		0
+#define   DSPFW_SR_WM1_MASK		(0x1ff<<0)
+#define DSPFW7			(VLV_DISPLAY_BASE + 0x7007c)
+#define DSPFW7_CHV		(VLV_DISPLAY_BASE + 0x700b4) /* wtf #1? */
+#define   DSPFW_SPRITED_WM1_SHIFT	24
+#define   DSPFW_SPRITED_WM1_MASK	(0xff<<24)
+#define   DSPFW_SPRITED_SHIFT		16
+#define   DSPFW_SPRITED_MASK		(0xff<<16)
+#define   DSPFW_SPRITEC_WM1_SHIFT	8
+#define   DSPFW_SPRITEC_WM1_MASK	(0xff<<8)
+#define   DSPFW_SPRITEC_SHIFT		0
+#define   DSPFW_SPRITEC_MASK		(0xff<<0)
+#define DSPFW8_CHV		(VLV_DISPLAY_BASE + 0x700b8)
+#define   DSPFW_SPRITEF_WM1_SHIFT	24
+#define   DSPFW_SPRITEF_WM1_MASK	(0xff<<24)
+#define   DSPFW_SPRITEF_SHIFT		16
+#define   DSPFW_SPRITEF_MASK		(0xff<<16)
+#define   DSPFW_SPRITEE_WM1_SHIFT	8
+#define   DSPFW_SPRITEE_WM1_MASK	(0xff<<8)
+#define   DSPFW_SPRITEE_SHIFT		0
+#define   DSPFW_SPRITEE_MASK		(0xff<<0)
+#define DSPFW9_CHV		(VLV_DISPLAY_BASE + 0x7007c) /* wtf #2? */
+#define   DSPFW_PLANEC_WM1_SHIFT	24
+#define   DSPFW_PLANEC_WM1_MASK		(0xff<<24)
+#define   DSPFW_PLANEC_SHIFT		16
+#define   DSPFW_PLANEC_MASK		(0xff<<16)
+#define   DSPFW_CURSORC_WM1_SHIFT	8
+#define   DSPFW_CURSORC_WM1_MASK	(0x3f<<16)
+#define   DSPFW_CURSORC_SHIFT		0
+#define   DSPFW_CURSORC_MASK		(0x3f<<0)
+
+/* vlv/chv high order bits */
+#define DSPHOWM			(VLV_DISPLAY_BASE + 0x70064)
+#define   DSPFW_SR_HI_SHIFT		24
+#define   DSPFW_SR_HI_MASK		(1<<24)
+#define   DSPFW_SPRITEF_HI_SHIFT	23
+#define   DSPFW_SPRITEF_HI_MASK		(1<<23)
+#define   DSPFW_SPRITEE_HI_SHIFT	22
+#define   DSPFW_SPRITEE_HI_MASK		(1<<22)
+#define   DSPFW_PLANEC_HI_SHIFT		21
+#define   DSPFW_PLANEC_HI_MASK		(1<<21)
+#define   DSPFW_SPRITED_HI_SHIFT	20
+#define   DSPFW_SPRITED_HI_MASK		(1<<20)
+#define   DSPFW_SPRITEC_HI_SHIFT	16
+#define   DSPFW_SPRITEC_HI_MASK		(1<<16)
+#define   DSPFW_PLANEB_HI_SHIFT		12
+#define   DSPFW_PLANEB_HI_MASK		(1<<12)
+#define   DSPFW_SPRITEB_HI_SHIFT	8
+#define   DSPFW_SPRITEB_HI_MASK		(1<<8)
+#define   DSPFW_SPRITEA_HI_SHIFT	4
+#define   DSPFW_SPRITEA_HI_MASK		(1<<4)
+#define   DSPFW_PLANEA_HI_SHIFT		0
+#define   DSPFW_PLANEA_HI_MASK		(1<<0)
+#define DSPHOWM1		(VLV_DISPLAY_BASE + 0x70068)
+#define   DSPFW_SR_WM1_HI_SHIFT		24
+#define   DSPFW_SR_WM1_HI_MASK		(1<<24)
+#define   DSPFW_SPRITEF_WM1_HI_SHIFT	23
+#define   DSPFW_SPRITEF_WM1_HI_MASK	(1<<23)
+#define   DSPFW_SPRITEE_WM1_HI_SHIFT	22
+#define   DSPFW_SPRITEE_WM1_HI_MASK	(1<<22)
+#define   DSPFW_PLANEC_WM1_HI_SHIFT	21
+#define   DSPFW_PLANEC_WM1_HI_MASK	(1<<21)
+#define   DSPFW_SPRITED_WM1_HI_SHIFT	20
+#define   DSPFW_SPRITED_WM1_HI_MASK	(1<<20)
+#define   DSPFW_SPRITEC_WM1_HI_SHIFT	16
+#define   DSPFW_SPRITEC_WM1_HI_MASK	(1<<16)
+#define   DSPFW_PLANEB_WM1_HI_SHIFT	12
+#define   DSPFW_PLANEB_WM1_HI_MASK	(1<<12)
+#define   DSPFW_SPRITEB_WM1_HI_SHIFT	8
+#define   DSPFW_SPRITEB_WM1_HI_MASK	(1<<8)
+#define   DSPFW_SPRITEA_WM1_HI_SHIFT	4
+#define   DSPFW_SPRITEA_WM1_HI_MASK	(1<<4)
+#define   DSPFW_PLANEA_WM1_HI_SHIFT	0
+#define   DSPFW_PLANEA_WM1_HI_MASK	(1<<0)
 
 /* drain latency register values*/
 #define DRAIN_LATENCY_PRECISION_32	32
 #define DRAIN_LATENCY_PRECISION_64	64
-#define VLV_DDL1			(VLV_DISPLAY_BASE + 0x70050)
-#define DDL_CURSORA_PRECISION_64	(1<<31)
-#define DDL_CURSORA_PRECISION_32	(0<<31)
-#define DDL_CURSORA_SHIFT		24
-#define DDL_SPRITEB_PRECISION_64	(1<<23)
-#define DDL_SPRITEB_PRECISION_32	(0<<23)
-#define DDL_SPRITEB_SHIFT		16
-#define DDL_SPRITEA_PRECISION_64	(1<<15)
-#define DDL_SPRITEA_PRECISION_32	(0<<15)
-#define DDL_SPRITEA_SHIFT		8
-#define DDL_PLANEA_PRECISION_64		(1<<7)
-#define DDL_PLANEA_PRECISION_32		(0<<7)
-#define DDL_PLANEA_SHIFT		0
-
-#define VLV_DDL2			(VLV_DISPLAY_BASE + 0x70054)
-#define DDL_CURSORB_PRECISION_64	(1<<31)
-#define DDL_CURSORB_PRECISION_32	(0<<31)
-#define DDL_CURSORB_SHIFT		24
-#define DDL_SPRITED_PRECISION_64	(1<<23)
-#define DDL_SPRITED_PRECISION_32	(0<<23)
-#define DDL_SPRITED_SHIFT		16
-#define DDL_SPRITEC_PRECISION_64	(1<<15)
-#define DDL_SPRITEC_PRECISION_32	(0<<15)
-#define DDL_SPRITEC_SHIFT		8
-#define DDL_PLANEB_PRECISION_64		(1<<7)
-#define DDL_PLANEB_PRECISION_32		(0<<7)
-#define DDL_PLANEB_SHIFT		0
-
-#define VLV_DDL3			(VLV_DISPLAY_BASE + 0x70058)
-#define DDL_CURSORC_PRECISION_64	(1<<31)
-#define DDL_CURSORC_PRECISION_32	(0<<31)
-#define DDL_CURSORC_SHIFT		24
-#define DDL_SPRITEF_PRECISION_64	(1<<23)
-#define DDL_SPRITEF_PRECISION_32	(0<<23)
-#define DDL_SPRITEF_SHIFT		16
-#define DDL_SPRITEE_PRECISION_64	(1<<15)
-#define DDL_SPRITEE_PRECISION_32	(0<<15)
-#define DDL_SPRITEE_SHIFT		8
-#define DDL_PLANEC_PRECISION_64		(1<<7)
-#define DDL_PLANEC_PRECISION_32		(0<<7)
-#define DDL_PLANEC_SHIFT		0
+#define VLV_DDL(pipe)			(VLV_DISPLAY_BASE + 0x70050 + 4 * (pipe))
+#define DDL_CURSOR_PRECISION_64		(1<<31)
+#define DDL_CURSOR_PRECISION_32		(0<<31)
+#define DDL_CURSOR_SHIFT		24
+#define DDL_SPRITE_PRECISION_64(sprite)	(1<<(15+8*(sprite)))
+#define DDL_SPRITE_PRECISION_32(sprite)	(0<<(15+8*(sprite)))
+#define DDL_SPRITE_SHIFT(sprite)	(8+8*(sprite))
+#define DDL_PLANE_PRECISION_64		(1<<7)
+#define DDL_PLANE_PRECISION_32		(0<<7)
+#define DDL_PLANE_SHIFT			0
+#define DRAIN_LATENCY_MASK		0x7f
 
 /* FIFO watermark sizes etc */
 #define G4X_FIFO_LINE_SIZE	64
@@ -4026,7 +4154,8 @@ enum punit_power_well {
 /* Old style CUR*CNTR flags (desktop 8xx) */
 #define   CURSOR_ENABLE		0x80000000
 #define   CURSOR_GAMMA_ENABLE	0x40000000
-#define   CURSOR_STRIDE_MASK	0x30000000
+#define   CURSOR_STRIDE_SHIFT	28
+#define   CURSOR_STRIDE(x)	((ffs(x)-9) << CURSOR_STRIDE_SHIFT) /* 256,512,1k,2k */
 #define   CURSOR_PIPE_CSC_ENABLE (1<<24)
 #define   CURSOR_FORMAT_SHIFT	24
 #define   CURSOR_FORMAT_MASK	(0x07 << CURSOR_FORMAT_SHIFT)
@@ -4111,6 +4240,7 @@ enum punit_power_well {
 #define   DISPPLANE_NO_LINE_DOUBLE		0
 #define   DISPPLANE_STEREO_POLARITY_FIRST	0
 #define   DISPPLANE_STEREO_POLARITY_SECOND	(1<<18)
+#define   DISPPLANE_ROTATE_180         (1<<15)
 #define   DISPPLANE_TRICKLE_FEED_DISABLE	(1<<14) /* Ironlake */
 #define   DISPPLANE_TILED			(1<<10)
 #define _DSPAADDR				0x70184
@@ -4195,6 +4325,7 @@ enum punit_power_well {
 #define   DVS_YUV_ORDER_UYVY	(1<<16)
 #define   DVS_YUV_ORDER_YVYU	(2<<16)
 #define   DVS_YUV_ORDER_VYUY	(3<<16)
+#define   DVS_ROTATE_180	(1<<15)
 #define   DVS_DEST_KEY		(1<<2)
 #define   DVS_TRICKLE_FEED_DISABLE (1<<14)
 #define   DVS_TILED		(1<<10)
@@ -4265,6 +4396,7 @@ enum punit_power_well {
 #define   SPRITE_YUV_ORDER_UYVY		(1<<16)
 #define   SPRITE_YUV_ORDER_YVYU		(2<<16)
 #define   SPRITE_YUV_ORDER_VYUY		(3<<16)
+#define   SPRITE_ROTATE_180		(1<<15)
 #define   SPRITE_TRICKLE_FEED_DISABLE	(1<<14)
 #define   SPRITE_INT_GAMMA_ENABLE	(1<<13)
 #define   SPRITE_TILED			(1<<10)
@@ -4338,6 +4470,7 @@ enum punit_power_well {
 #define   SP_YUV_ORDER_UYVY		(1<<16)
 #define   SP_YUV_ORDER_YVYU		(2<<16)
 #define   SP_YUV_ORDER_VYUY		(3<<16)
+#define   SP_ROTATE_180			(1<<15)
 #define   SP_TILED			(1<<10)
 #define _SPALINOFF		(VLV_DISPLAY_BASE + 0x72184)
 #define _SPASTRIDE		(VLV_DISPLAY_BASE + 0x72188)
@@ -5246,8 +5379,7 @@ enum punit_power_well {
 #define PIPEA_PP_STATUS         (VLV_DISPLAY_BASE + 0x61200)
 #define PIPEA_PP_CONTROL        (VLV_DISPLAY_BASE + 0x61204)
 #define PIPEA_PP_ON_DELAYS      (VLV_DISPLAY_BASE + 0x61208)
-#define  PANEL_PORT_SELECT_DPB_VLV	(1 << 30)
-#define  PANEL_PORT_SELECT_DPC_VLV	(2 << 30)
+#define  PANEL_PORT_SELECT_VLV(port)	((port) << 30)
 #define PIPEA_PP_OFF_DELAYS     (VLV_DISPLAY_BASE + 0x6120c)
 #define PIPEA_PP_DIVISOR        (VLV_DISPLAY_BASE + 0x61210)
 
@@ -5407,7 +5539,6 @@ enum punit_power_well {
 #define   VLV_GTLC_ALLOWWAKEERR			(1 << 1)
 #define   VLV_GTLC_PW_MEDIA_STATUS_MASK		(1 << 5)
 #define   VLV_GTLC_PW_RENDER_STATUS_MASK	(1 << 7)
-#define VLV_GTLC_SURVIVABILITY_REG              0x130098
 #define  FORCEWAKE_MT				0xa188 /* multi-threaded */
 #define   FORCEWAKE_KERNEL			0x1
 #define   FORCEWAKE_USER			0x2
@@ -5545,12 +5676,6 @@ enum punit_power_well {
 						 GEN6_PM_RP_DOWN_THRESHOLD | \
 						 GEN6_PM_RP_DOWN_TIMEOUT)
 
-#define CHV_CZ_CLOCK_FREQ_MODE_200			200
-#define CHV_CZ_CLOCK_FREQ_MODE_267			267
-#define CHV_CZ_CLOCK_FREQ_MODE_320			320
-#define CHV_CZ_CLOCK_FREQ_MODE_333			333
-#define CHV_CZ_CLOCK_FREQ_MODE_400			400
-
 #define GEN7_GT_SCRATCH_BASE			0x4F100
 #define GEN7_GT_SCRATCH_REG_NUM			8
 
@@ -5866,15 +5991,7 @@ enum punit_power_well {
 #define DDI_BUF_CTL_B				0x64100
 #define DDI_BUF_CTL(port) _PORT(port, DDI_BUF_CTL_A, DDI_BUF_CTL_B)
 #define  DDI_BUF_CTL_ENABLE			(1<<31)
-#define  DDI_BUF_EMP_400MV_0DB_HSW		(0<<24)   /* Sel0 */
-#define  DDI_BUF_EMP_400MV_3_5DB_HSW		(1<<24)   /* Sel1 */
-#define  DDI_BUF_EMP_400MV_6DB_HSW		(2<<24)   /* Sel2 */
-#define  DDI_BUF_EMP_400MV_9_5DB_HSW		(3<<24)   /* Sel3 */
-#define  DDI_BUF_EMP_600MV_0DB_HSW		(4<<24)   /* Sel4 */
-#define  DDI_BUF_EMP_600MV_3_5DB_HSW		(5<<24)   /* Sel5 */
-#define  DDI_BUF_EMP_600MV_6DB_HSW		(6<<24)   /* Sel6 */
-#define  DDI_BUF_EMP_800MV_0DB_HSW		(7<<24)   /* Sel7 */
-#define  DDI_BUF_EMP_800MV_3_5DB_HSW		(8<<24)   /* Sel8 */
+#define  DDI_BUF_TRANS_SELECT(n)	((n) << 24)
 #define  DDI_BUF_EMP_MASK			(0xf<<24)
 #define  DDI_BUF_PORT_REVERSAL			(1<<16)
 #define  DDI_BUF_IS_IDLE			(1<<7)
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index ae7fd8fc27f0..503847f18fdd 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -540,7 +540,7 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
 
 	memset(&error_priv, 0, sizeof(error_priv));
 
-	ret = i915_error_state_buf_init(&error_str, count, off);
+	ret = i915_error_state_buf_init(&error_str, to_i915(dev), count, off);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index afcc8dd40bdd..a4bd90f36a03 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -627,16 +627,16 @@ parse_edp(struct drm_i915_private *dev_priv, struct bdb_header *bdb)
 
 	switch (edp_link_params->preemphasis) {
 	case EDP_PREEMPHASIS_NONE:
-		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPHASIS_0;
+		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPH_LEVEL_0;
 		break;
 	case EDP_PREEMPHASIS_3_5dB:
-		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPHASIS_3_5;
+		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPH_LEVEL_1;
 		break;
 	case EDP_PREEMPHASIS_6dB:
-		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPHASIS_6;
+		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPH_LEVEL_2;
 		break;
 	case EDP_PREEMPHASIS_9_5dB:
-		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPHASIS_9_5;
+		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPH_LEVEL_3;
 		break;
 	default:
 		DRM_DEBUG_KMS("VBT has unknown eDP pre-emphasis value %u\n",
@@ -646,16 +646,16 @@ parse_edp(struct drm_i915_private *dev_priv, struct bdb_header *bdb)
 
 	switch (edp_link_params->vswing) {
 	case EDP_VSWING_0_4V:
-		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_400;
+		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_LEVEL_0;
 		break;
 	case EDP_VSWING_0_6V:
-		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_600;
+		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_LEVEL_1;
 		break;
 	case EDP_VSWING_0_8V:
-		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_800;
+		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_LEVEL_2;
 		break;
 	case EDP_VSWING_1_2V:
-		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_1200;
+		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_LEVEL_3;
 		break;
 	default:
 		DRM_DEBUG_KMS("VBT has unknown eDP voltage swing value %u\n",
@@ -976,12 +976,10 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
 	if (bdb->version >= 158) {
 		/* The VBT HDMI level shift values match the table we have. */
 		hdmi_level_shift = child->raw[7] & 0xF;
-		if (hdmi_level_shift < 0xC) {
-			DRM_DEBUG_KMS("VBT HDMI level shift for port %c: %d\n",
-				      port_name(port),
-				      hdmi_level_shift);
-			info->hdmi_level_shift = hdmi_level_shift;
-		}
+		DRM_DEBUG_KMS("VBT HDMI level shift for port %c: %d\n",
+			      port_name(port),
+			      hdmi_level_shift);
+		info->hdmi_level_shift = hdmi_level_shift;
 	}
 }
 
@@ -1114,8 +1112,7 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 		struct ddi_vbt_port_info *info =
 			&dev_priv->vbt.ddi_port_info[port];
 
-		/* Recommended BSpec default: 800mV 0dB. */
-		info->hdmi_level_shift = 6;
+		info->hdmi_level_shift = HDMI_LEVEL_SHIFT_UNKNOWN;
 
 		info->supports_dvi = (port != PORT_A && port != PORT_E);
 		info->supports_hdmi = info->supports_dvi;
diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h
index b98667796337..905999bee2ac 100644
--- a/drivers/gpu/drm/i915/intel_bios.h
+++ b/drivers/gpu/drm/i915/intel_bios.h
@@ -802,7 +802,8 @@ struct mipi_config {
 
 	u16 rsvd4;
 
-	u8 rsvd5[5];
+	u8 rsvd5;
+	u32 target_burst_mode_freq;
 	u32 dsi_ddr_clk;
 	u32 bridge_ref_clk;
 
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 5db0b5552e39..b63d4fa204a3 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -28,87 +28,103 @@
 #include "i915_drv.h"
 #include "intel_drv.h"
 
+struct ddi_buf_trans {
+	u32 trans1;	/* balance leg enable, de-emph level */
+	u32 trans2;	/* vref sel, vswing */
+};
+
 /* HDMI/DVI modes ignore everything but the last 2 items. So we share
  * them for both DP and FDI transports, allowing those ports to
  * automatically adapt to HDMI connections as well
  */
-static const u32 hsw_ddi_translations_dp[] = {
-	0x00FFFFFF, 0x0006000E,		/* DP parameters */
-	0x00D75FFF, 0x0005000A,
-	0x00C30FFF, 0x00040006,
-	0x80AAAFFF, 0x000B0000,
-	0x00FFFFFF, 0x0005000A,
-	0x00D75FFF, 0x000C0004,
-	0x80C30FFF, 0x000B0000,
-	0x00FFFFFF, 0x00040006,
-	0x80D75FFF, 0x000B0000,
+static const struct ddi_buf_trans hsw_ddi_translations_dp[] = {
+	{ 0x00FFFFFF, 0x0006000E },
+	{ 0x00D75FFF, 0x0005000A },
+	{ 0x00C30FFF, 0x00040006 },
+	{ 0x80AAAFFF, 0x000B0000 },
+	{ 0x00FFFFFF, 0x0005000A },
+	{ 0x00D75FFF, 0x000C0004 },
+	{ 0x80C30FFF, 0x000B0000 },
+	{ 0x00FFFFFF, 0x00040006 },
+	{ 0x80D75FFF, 0x000B0000 },
 };
 
-static const u32 hsw_ddi_translations_fdi[] = {
-	0x00FFFFFF, 0x0007000E,		/* FDI parameters */
-	0x00D75FFF, 0x000F000A,
-	0x00C30FFF, 0x00060006,
-	0x00AAAFFF, 0x001E0000,
-	0x00FFFFFF, 0x000F000A,
-	0x00D75FFF, 0x00160004,
-	0x00C30FFF, 0x001E0000,
-	0x00FFFFFF, 0x00060006,
-	0x00D75FFF, 0x001E0000,
+static const struct ddi_buf_trans hsw_ddi_translations_fdi[] = {
+	{ 0x00FFFFFF, 0x0007000E },
+	{ 0x00D75FFF, 0x000F000A },
+	{ 0x00C30FFF, 0x00060006 },
+	{ 0x00AAAFFF, 0x001E0000 },
+	{ 0x00FFFFFF, 0x000F000A },
+	{ 0x00D75FFF, 0x00160004 },
+	{ 0x00C30FFF, 0x001E0000 },
+	{ 0x00FFFFFF, 0x00060006 },
+	{ 0x00D75FFF, 0x001E0000 },
 };
 
-static const u32 hsw_ddi_translations_hdmi[] = {
-				/* Idx	NT mV diff	T mV diff	db  */
-	0x00FFFFFF, 0x0006000E, /* 0:	400		400		0   */
-	0x00E79FFF, 0x000E000C, /* 1:	400		500		2   */
-	0x00D75FFF, 0x0005000A, /* 2:	400		600		3.5 */
-	0x00FFFFFF, 0x0005000A, /* 3:	600		600		0   */
-	0x00E79FFF, 0x001D0007, /* 4:	600		750		2   */
-	0x00D75FFF, 0x000C0004, /* 5:	600		900		3.5 */
-	0x00FFFFFF, 0x00040006, /* 6:	800		800		0   */
-	0x80E79FFF, 0x00030002, /* 7:	800		1000		2   */
-	0x00FFFFFF, 0x00140005, /* 8:	850		850		0   */
-	0x00FFFFFF, 0x000C0004, /* 9:	900		900		0   */
-	0x00FFFFFF, 0x001C0003, /* 10:	950		950		0   */
-	0x80FFFFFF, 0x00030002, /* 11:	1000		1000		0   */
+static const struct ddi_buf_trans hsw_ddi_translations_hdmi[] = {
+					/* Idx	NT mV d	T mV d	db	*/
+	{ 0x00FFFFFF, 0x0006000E },	/* 0:	400	400	0	*/
+	{ 0x00E79FFF, 0x000E000C },	/* 1:	400	500	2	*/
+	{ 0x00D75FFF, 0x0005000A },	/* 2:	400	600	3.5	*/
+	{ 0x00FFFFFF, 0x0005000A },	/* 3:	600	600	0	*/
+	{ 0x00E79FFF, 0x001D0007 },	/* 4:	600	750	2	*/
+	{ 0x00D75FFF, 0x000C0004 },	/* 5:	600	900	3.5	*/
+	{ 0x00FFFFFF, 0x00040006 },	/* 6:	800	800	0	*/
+	{ 0x80E79FFF, 0x00030002 },	/* 7:	800	1000	2	*/
+	{ 0x00FFFFFF, 0x00140005 },	/* 8:	850	850	0	*/
+	{ 0x00FFFFFF, 0x000C0004 },	/* 9:	900	900	0	*/
+	{ 0x00FFFFFF, 0x001C0003 },	/* 10:	950	950	0	*/
+	{ 0x80FFFFFF, 0x00030002 },	/* 11:	1000	1000	0	*/
 };
 
-static const u32 bdw_ddi_translations_edp[] = {
-	0x00FFFFFF, 0x00000012,		/* eDP parameters */
-	0x00EBAFFF, 0x00020011,
-	0x00C71FFF, 0x0006000F,
-	0x00AAAFFF, 0x000E000A,
-	0x00FFFFFF, 0x00020011,
-	0x00DB6FFF, 0x0005000F,
-	0x00BEEFFF, 0x000A000C,
-	0x00FFFFFF, 0x0005000F,
-	0x00DB6FFF, 0x000A000C,
-	0x00FFFFFF, 0x00140006		/* HDMI parameters 800mV 0dB*/
+static const struct ddi_buf_trans bdw_ddi_translations_edp[] = {
+	{ 0x00FFFFFF, 0x00000012 },
+	{ 0x00EBAFFF, 0x00020011 },
+	{ 0x00C71FFF, 0x0006000F },
+	{ 0x00AAAFFF, 0x000E000A },
+	{ 0x00FFFFFF, 0x00020011 },
+	{ 0x00DB6FFF, 0x0005000F },
+	{ 0x00BEEFFF, 0x000A000C },
+	{ 0x00FFFFFF, 0x0005000F },
+	{ 0x00DB6FFF, 0x000A000C },
 };
 
-static const u32 bdw_ddi_translations_dp[] = {
-	0x00FFFFFF, 0x0007000E,		/* DP parameters */
-	0x00D75FFF, 0x000E000A,
-	0x00BEFFFF, 0x00140006,
-	0x80B2CFFF, 0x001B0002,
-	0x00FFFFFF, 0x000E000A,
-	0x00D75FFF, 0x00180004,
-	0x80CB2FFF, 0x001B0002,
-	0x00F7DFFF, 0x00180004,
-	0x80D75FFF, 0x001B0002,
-	0x00FFFFFF, 0x00140006		/* HDMI parameters 800mV 0dB*/
+static const struct ddi_buf_trans bdw_ddi_translations_dp[] = {
+	{ 0x00FFFFFF, 0x0007000E },
+	{ 0x00D75FFF, 0x000E000A },
+	{ 0x00BEFFFF, 0x00140006 },
+	{ 0x80B2CFFF, 0x001B0002 },
+	{ 0x00FFFFFF, 0x000E000A },
+	{ 0x00D75FFF, 0x00180004 },
+	{ 0x80CB2FFF, 0x001B0002 },
+	{ 0x00F7DFFF, 0x00180004 },
+	{ 0x80D75FFF, 0x001B0002 },
 };
 
-static const u32 bdw_ddi_translations_fdi[] = {
-	0x00FFFFFF, 0x0001000E,		/* FDI parameters */
-	0x00D75FFF, 0x0004000A,
-	0x00C30FFF, 0x00070006,
-	0x00AAAFFF, 0x000C0000,
-	0x00FFFFFF, 0x0004000A,
-	0x00D75FFF, 0x00090004,
-	0x00C30FFF, 0x000C0000,
-	0x00FFFFFF, 0x00070006,
-	0x00D75FFF, 0x000C0000,
-	0x00FFFFFF, 0x00140006		/* HDMI parameters 800mV 0dB*/
+static const struct ddi_buf_trans bdw_ddi_translations_fdi[] = {
+	{ 0x00FFFFFF, 0x0001000E },
+	{ 0x00D75FFF, 0x0004000A },
+	{ 0x00C30FFF, 0x00070006 },
+	{ 0x00AAAFFF, 0x000C0000 },
+	{ 0x00FFFFFF, 0x0004000A },
+	{ 0x00D75FFF, 0x00090004 },
+	{ 0x00C30FFF, 0x000C0000 },
+	{ 0x00FFFFFF, 0x00070006 },
+	{ 0x00D75FFF, 0x000C0000 },
+};
+
+static const struct ddi_buf_trans bdw_ddi_translations_hdmi[] = {
+					/* Idx	NT mV d	T mV df	db	*/
+	{ 0x00FFFFFF, 0x0007000E },	/* 0:	400	400	0	*/
+	{ 0x00D75FFF, 0x000E000A },	/* 1:	400	600	3.5	*/
+	{ 0x00BEFFFF, 0x00140006 },	/* 2:	400	800	6	*/
+	{ 0x00FFFFFF, 0x0009000D },	/* 3:	450	450	0	*/
+	{ 0x00FFFFFF, 0x000E000A },	/* 4:	600	600	0	*/
+	{ 0x00D7FFFF, 0x00140006 },	/* 5:	600	800	2.5	*/
+	{ 0x80CB2FFF, 0x001B0002 },	/* 6:	600	1000	4.5	*/
+	{ 0x00FFFFFF, 0x00140006 },	/* 7:	800	800	0	*/
+	{ 0x80E79FFF, 0x001B0002 },	/* 8:	800	1000	2	*/
+	{ 0x80FFFFFF, 0x001B0002 },	/* 9:	1000	1000	0	*/
 };
 
 enum port intel_ddi_get_encoder_port(struct intel_encoder *intel_encoder)
@@ -145,26 +161,36 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 reg;
-	int i;
+	int i, n_hdmi_entries, hdmi_800mV_0dB;
 	int hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
-	const u32 *ddi_translations_fdi;
-	const u32 *ddi_translations_dp;
-	const u32 *ddi_translations_edp;
-	const u32 *ddi_translations;
+	const struct ddi_buf_trans *ddi_translations_fdi;
+	const struct ddi_buf_trans *ddi_translations_dp;
+	const struct ddi_buf_trans *ddi_translations_edp;
+	const struct ddi_buf_trans *ddi_translations_hdmi;
+	const struct ddi_buf_trans *ddi_translations;
 
 	if (IS_BROADWELL(dev)) {
 		ddi_translations_fdi = bdw_ddi_translations_fdi;
 		ddi_translations_dp = bdw_ddi_translations_dp;
 		ddi_translations_edp = bdw_ddi_translations_edp;
+		ddi_translations_hdmi = bdw_ddi_translations_hdmi;
+		n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
+		hdmi_800mV_0dB = 7;
 	} else if (IS_HASWELL(dev)) {
 		ddi_translations_fdi = hsw_ddi_translations_fdi;
 		ddi_translations_dp = hsw_ddi_translations_dp;
 		ddi_translations_edp = hsw_ddi_translations_dp;
+		ddi_translations_hdmi = hsw_ddi_translations_hdmi;
+		n_hdmi_entries = ARRAY_SIZE(hsw_ddi_translations_hdmi);
+		hdmi_800mV_0dB = 6;
 	} else {
 		WARN(1, "ddi translation table missing\n");
 		ddi_translations_edp = bdw_ddi_translations_dp;
 		ddi_translations_fdi = bdw_ddi_translations_fdi;
 		ddi_translations_dp = bdw_ddi_translations_dp;
+		ddi_translations_hdmi = bdw_ddi_translations_hdmi;
+		n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
+		hdmi_800mV_0dB = 7;
 	}
 
 	switch (port) {
@@ -190,14 +216,22 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port)
 
 	for (i = 0, reg = DDI_BUF_TRANS(port);
 	     i < ARRAY_SIZE(hsw_ddi_translations_fdi); i++) {
-		I915_WRITE(reg, ddi_translations[i]);
+		I915_WRITE(reg, ddi_translations[i].trans1);
 		reg += 4;
-	}
-	/* Entry 9 is for HDMI: */
-	for (i = 0; i < 2; i++) {
-		I915_WRITE(reg, hsw_ddi_translations_hdmi[hdmi_level * 2 + i]);
+		I915_WRITE(reg, ddi_translations[i].trans2);
 		reg += 4;
 	}
+
+	/* Choose a good default if VBT is badly populated */
+	if (hdmi_level == HDMI_LEVEL_SHIFT_UNKNOWN ||
+	    hdmi_level >= n_hdmi_entries)
+		hdmi_level = hdmi_800mV_0dB;
+
+	/* Entry 9 is for HDMI: */
+	I915_WRITE(reg, ddi_translations_hdmi[hdmi_level].trans1);
+	reg += 4;
+	I915_WRITE(reg, ddi_translations_hdmi[hdmi_level].trans2);
+	reg += 4;
 }
 
 /* Program DDI buffers translations for DP. By default, program ports A-D in DP
@@ -214,18 +248,6 @@ void intel_prepare_ddi(struct drm_device *dev)
 		intel_prepare_ddi_buffers(dev, port);
 }
 
-static const long hsw_ddi_buf_ctl_values[] = {
-	DDI_BUF_EMP_400MV_0DB_HSW,
-	DDI_BUF_EMP_400MV_3_5DB_HSW,
-	DDI_BUF_EMP_400MV_6DB_HSW,
-	DDI_BUF_EMP_400MV_9_5DB_HSW,
-	DDI_BUF_EMP_600MV_0DB_HSW,
-	DDI_BUF_EMP_600MV_3_5DB_HSW,
-	DDI_BUF_EMP_600MV_6DB_HSW,
-	DDI_BUF_EMP_800MV_0DB_HSW,
-	DDI_BUF_EMP_800MV_3_5DB_HSW
-};
-
 static void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv,
 				    enum port port)
 {
@@ -285,7 +307,7 @@ void hsw_fdi_link_train(struct drm_crtc *crtc)
 
 	/* Start the training iterating through available voltages and emphasis,
 	 * testing each value twice. */
-	for (i = 0; i < ARRAY_SIZE(hsw_ddi_buf_ctl_values) * 2; i++) {
+	for (i = 0; i < ARRAY_SIZE(hsw_ddi_translations_fdi) * 2; i++) {
 		/* Configure DP_TP_CTL with auto-training */
 		I915_WRITE(DP_TP_CTL(PORT_E),
 					DP_TP_CTL_FDI_AUTOTRAIN |
@@ -300,7 +322,7 @@ void hsw_fdi_link_train(struct drm_crtc *crtc)
 		I915_WRITE(DDI_BUF_CTL(PORT_E),
 			   DDI_BUF_CTL_ENABLE |
 			   ((intel_crtc->config.fdi_lanes - 1) << 1) |
-			   hsw_ddi_buf_ctl_values[i / 2]);
+			   DDI_BUF_TRANS_SELECT(i / 2));
 		POSTING_READ(DDI_BUF_CTL(PORT_E));
 
 		udelay(600);
@@ -375,7 +397,7 @@ void intel_ddi_init_dp_buf_reg(struct intel_encoder *encoder)
 		enc_to_dig_port(&encoder->base);
 
 	intel_dp->DP = intel_dig_port->saved_port_bits |
-		DDI_BUF_CTL_ENABLE | DDI_BUF_EMP_400MV_0DB_HSW;
+		DDI_BUF_CTL_ENABLE | DDI_BUF_TRANS_SELECT(0);
 	intel_dp->DP |= DDI_PORT_WIDTH(intel_dp->lane_count);
 
 }
@@ -402,7 +424,7 @@ intel_ddi_get_crtc_encoder(struct drm_crtc *crtc)
 }
 
 #define LC_FREQ 2700
-#define LC_FREQ_2K (LC_FREQ * 2000)
+#define LC_FREQ_2K U64_C(LC_FREQ * 2000)
 
 #define P_MIN 2
 #define P_MAX 64
@@ -414,7 +436,11 @@ intel_ddi_get_crtc_encoder(struct drm_crtc *crtc)
 #define VCO_MIN 2400
 #define VCO_MAX 4800
 
-#define ABS_DIFF(a, b) ((a > b) ? (a - b) : (b - a))
+#define abs_diff(a, b) ({			\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	(void) (&__a == &__b);			\
+	__a > __b ? (__a - __b) : (__b - __a); })
 
 struct wrpll_rnp {
 	unsigned p, n2, r2;
@@ -524,9 +550,9 @@ static void wrpll_update_rnp(uint64_t freq2k, unsigned budget,
 	 */
 	a = freq2k * budget * p * r2;
 	b = freq2k * budget * best->p * best->r2;
-	diff = ABS_DIFF((freq2k * p * r2), (LC_FREQ_2K * n2));
-	diff_best = ABS_DIFF((freq2k * best->p * best->r2),
-			     (LC_FREQ_2K * best->n2));
+	diff = abs_diff(freq2k * p * r2, LC_FREQ_2K * n2);
+	diff_best = abs_diff(freq2k * best->p * best->r2,
+			     LC_FREQ_2K * best->n2);
 	c = 1000000 * diff;
 	d = 1000000 * diff_best;
 
@@ -587,8 +613,8 @@ static int intel_ddi_calc_wrpll_link(struct drm_i915_private *dev_priv,
 	return (refclk * n * 100) / (p * r);
 }
 
-void intel_ddi_clock_get(struct intel_encoder *encoder,
-			 struct intel_crtc_config *pipe_config)
+static void hsw_ddi_clock_get(struct intel_encoder *encoder,
+			      struct intel_crtc_config *pipe_config)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	int link_clock = 0;
@@ -643,9 +669,15 @@ void intel_ddi_clock_get(struct intel_encoder *encoder,
 		pipe_config->adjusted_mode.crtc_clock = pipe_config->port_clock;
 }
 
+void intel_ddi_clock_get(struct intel_encoder *encoder,
+			 struct intel_crtc_config *pipe_config)
+{
+	hsw_ddi_clock_get(encoder, pipe_config);
+}
+
 static void
-intel_ddi_calculate_wrpll(int clock /* in Hz */,
-			  unsigned *r2_out, unsigned *n2_out, unsigned *p_out)
+hsw_ddi_calculate_wrpll(int clock /* in Hz */,
+			unsigned *r2_out, unsigned *n2_out, unsigned *p_out)
 {
 	uint64_t freq2k;
 	unsigned p, n2, r2;
@@ -708,27 +740,17 @@ intel_ddi_calculate_wrpll(int clock /* in Hz */,
 	*r2_out = best.r2;
 }
 
-/*
- * Tries to find a PLL for the CRTC. If it finds, it increases the refcount and
- * stores it in intel_crtc->ddi_pll_sel, so other mode sets won't be able to
- * steal the selected PLL. You need to call intel_ddi_pll_enable to actually
- * enable the PLL.
- */
-bool intel_ddi_pll_select(struct intel_crtc *intel_crtc)
+static bool
+hsw_ddi_pll_select(struct intel_crtc *intel_crtc,
+		   struct intel_encoder *intel_encoder,
+		   int clock)
 {
-	struct drm_crtc *crtc = &intel_crtc->base;
-	struct intel_encoder *intel_encoder = intel_ddi_get_crtc_encoder(crtc);
-	int type = intel_encoder->type;
-	int clock = intel_crtc->config.port_clock;
-
-	intel_put_shared_dpll(intel_crtc);
-
-	if (type == INTEL_OUTPUT_HDMI) {
+	if (intel_encoder->type == INTEL_OUTPUT_HDMI) {
 		struct intel_shared_dpll *pll;
 		uint32_t val;
 		unsigned p, n2, r2;
 
-		intel_ddi_calculate_wrpll(clock * 1000, &r2, &n2, &p);
+		hsw_ddi_calculate_wrpll(clock * 1000, &r2, &n2, &p);
 
 		val = WRPLL_PLL_ENABLE | WRPLL_PLL_LCPLL |
 		      WRPLL_DIVIDER_REFERENCE(r2) | WRPLL_DIVIDER_FEEDBACK(n2) |
@@ -749,6 +771,25 @@ bool intel_ddi_pll_select(struct intel_crtc *intel_crtc)
 	return true;
 }
 
+
+/*
+ * Tries to find a *shared* PLL for the CRTC and store it in
+ * intel_crtc->ddi_pll_sel.
+ *
+ * For private DPLLs, compute_config() should do the selection for us. This
+ * function should be folded into compute_config() eventually.
+ */
+bool intel_ddi_pll_select(struct intel_crtc *intel_crtc)
+{
+	struct drm_crtc *crtc = &intel_crtc->base;
+	struct intel_encoder *intel_encoder = intel_ddi_get_crtc_encoder(crtc);
+	int clock = intel_crtc->config.port_clock;
+
+	intel_put_shared_dpll(intel_crtc);
+
+	return hsw_ddi_pll_select(intel_crtc, intel_encoder, clock);
+}
+
 void intel_ddi_set_pipe_settings(struct drm_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
@@ -1183,31 +1224,52 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder)
 	}
 }
 
-int intel_ddi_get_cdclk_freq(struct drm_i915_private *dev_priv)
+static int bdw_get_cdclk_freq(struct drm_i915_private *dev_priv)
+{
+	uint32_t lcpll = I915_READ(LCPLL_CTL);
+	uint32_t freq = lcpll & LCPLL_CLK_FREQ_MASK;
+
+	if (lcpll & LCPLL_CD_SOURCE_FCLK)
+		return 800000;
+	else if (I915_READ(FUSE_STRAP) & HSW_CDCLK_LIMIT)
+		return 450000;
+	else if (freq == LCPLL_CLK_FREQ_450)
+		return 450000;
+	else if (freq == LCPLL_CLK_FREQ_54O_BDW)
+		return 540000;
+	else if (freq == LCPLL_CLK_FREQ_337_5_BDW)
+		return 337500;
+	else
+		return 675000;
+}
+
+static int hsw_get_cdclk_freq(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = dev_priv->dev;
 	uint32_t lcpll = I915_READ(LCPLL_CTL);
 	uint32_t freq = lcpll & LCPLL_CLK_FREQ_MASK;
 
-	if (lcpll & LCPLL_CD_SOURCE_FCLK) {
+	if (lcpll & LCPLL_CD_SOURCE_FCLK)
 		return 800000;
-	} else if (I915_READ(FUSE_STRAP) & HSW_CDCLK_LIMIT) {
+	else if (I915_READ(FUSE_STRAP) & HSW_CDCLK_LIMIT)
 		return 450000;
-	} else if (freq == LCPLL_CLK_FREQ_450) {
+	else if (freq == LCPLL_CLK_FREQ_450)
 		return 450000;
-	} else if (IS_HASWELL(dev)) {
-		if (IS_ULT(dev))
-			return 337500;
-		else
-			return 540000;
-	} else {
-		if (freq == LCPLL_CLK_FREQ_54O_BDW)
-			return 540000;
-		else if (freq == LCPLL_CLK_FREQ_337_5_BDW)
-			return 337500;
-		else
-			return 675000;
-	}
+	else if (IS_ULT(dev))
+		return 337500;
+	else
+		return 540000;
+}
+
+int intel_ddi_get_cdclk_freq(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+
+	if (IS_BROADWELL(dev))
+		return bdw_get_cdclk_freq(dev_priv);
+
+	/* Haswell */
+	return hsw_get_cdclk_freq(dev_priv);
 }
 
 static void hsw_ddi_pll_enable(struct drm_i915_private *dev_priv,
@@ -1248,10 +1310,8 @@ static const char * const hsw_ddi_pll_names[] = {
 	"WRPLL 2",
 };
 
-void intel_ddi_pll_init(struct drm_device *dev)
+static void hsw_shared_dplls_init(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t val = I915_READ(LCPLL_CTL);
 	int i;
 
 	dev_priv->num_shared_dpll = 2;
@@ -1264,6 +1324,14 @@ void intel_ddi_pll_init(struct drm_device *dev)
 		dev_priv->shared_dplls[i].get_hw_state =
 			hsw_ddi_pll_get_hw_state;
 	}
+}
+
+void intel_ddi_pll_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t val = I915_READ(LCPLL_CTL);
+
+	hsw_shared_dplls_init(dev_priv);
 
 	/* The LCPLL register should be turned on by the BIOS. For now let's
 	 * just check its state and print errors in case something is wrong.
@@ -1444,7 +1512,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 		dev_priv->vbt.edp_bpp = pipe_config->pipe_bpp;
 	}
 
-	intel_ddi_clock_get(encoder, pipe_config);
+	hsw_ddi_clock_get(encoder, pipe_config);
 }
 
 static void intel_ddi_destroy(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index d8324c69fa86..507370513f3d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -91,15 +91,16 @@ static int intel_framebuffer_init(struct drm_device *dev,
 				  struct intel_framebuffer *ifb,
 				  struct drm_mode_fb_cmd2 *mode_cmd,
 				  struct drm_i915_gem_object *obj);
-static void intel_dp_set_m_n(struct intel_crtc *crtc);
 static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc);
 static void intel_set_pipe_timings(struct intel_crtc *intel_crtc);
 static void intel_cpu_transcoder_set_m_n(struct intel_crtc *crtc,
-					 struct intel_link_m_n *m_n);
+					 struct intel_link_m_n *m_n,
+					 struct intel_link_m_n *m2_n2);
 static void ironlake_set_pipeconf(struct drm_crtc *crtc);
 static void haswell_set_pipeconf(struct drm_crtc *crtc);
 static void intel_set_pipe_csc(struct drm_crtc *crtc);
 static void vlv_prepare_pll(struct intel_crtc *crtc);
+static void chv_prepare_pll(struct intel_crtc *crtc);
 
 static struct intel_encoder *intel_find_encoder(struct intel_connector *connector, int pipe)
 {
@@ -899,7 +900,8 @@ static void g4x_wait_for_vblank(struct drm_device *dev, int pipe)
 	frame = I915_READ(frame_reg);
 
 	if (wait_for(I915_READ_NOTRACE(frame_reg) != frame, 50))
-		WARN(1, "vblank wait timed out\n");
+		WARN(1, "vblank wait on pipe %c timed out\n",
+		     pipe_name(pipe));
 }
 
 /**
@@ -940,7 +942,8 @@ void intel_wait_for_vblank(struct drm_device *dev, int pipe)
 	if (wait_for(I915_READ(pipestat_reg) &
 		     PIPE_VBLANK_INTERRUPT_STATUS,
 		     50))
-		DRM_DEBUG_KMS("vblank wait timed out\n");
+		DRM_DEBUG_KMS("vblank wait on pipe %c timed out\n",
+			      pipe_name(pipe));
 }
 
 static bool pipe_dsl_stopped(struct drm_device *dev, enum pipe pipe)
@@ -964,8 +967,7 @@ static bool pipe_dsl_stopped(struct drm_device *dev, enum pipe pipe)
 
 /*
  * intel_wait_for_pipe_off - wait for pipe to turn off
- * @dev: drm device
- * @pipe: pipe to wait for
+ * @crtc: crtc whose pipe to wait for
  *
  * After disabling a pipe, we can't wait for vblank in the usual way,
  * spinning on the vblank interrupt status bit, since we won't actually
@@ -979,11 +981,12 @@ static bool pipe_dsl_stopped(struct drm_device *dev, enum pipe pipe)
  *   ends up stopping at the start of the next frame).
  *
  */
-void intel_wait_for_pipe_off(struct drm_device *dev, int pipe)
+static void intel_wait_for_pipe_off(struct intel_crtc *crtc)
 {
+	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
-								      pipe);
+	enum transcoder cpu_transcoder = crtc->config.cpu_transcoder;
+	enum pipe pipe = crtc->pipe;
 
 	if (INTEL_INFO(dev)->gen >= 4) {
 		int reg = PIPECONF(cpu_transcoder);
@@ -1192,27 +1195,40 @@ void assert_fdi_rx_pll(struct drm_i915_private *dev_priv,
 static void assert_panel_unlocked(struct drm_i915_private *dev_priv,
 				  enum pipe pipe)
 {
-	int pp_reg, lvds_reg;
+	struct drm_device *dev = dev_priv->dev;
+	int pp_reg;
 	u32 val;
 	enum pipe panel_pipe = PIPE_A;
 	bool locked = true;
 
-	if (HAS_PCH_SPLIT(dev_priv->dev)) {
+	if (WARN_ON(HAS_DDI(dev)))
+		return;
+
+	if (HAS_PCH_SPLIT(dev)) {
+		u32 port_sel;
+
 		pp_reg = PCH_PP_CONTROL;
-		lvds_reg = PCH_LVDS;
+		port_sel = I915_READ(PCH_PP_ON_DELAYS) & PANEL_PORT_SELECT_MASK;
+
+		if (port_sel == PANEL_PORT_SELECT_LVDS &&
+		    I915_READ(PCH_LVDS) & LVDS_PIPEB_SELECT)
+			panel_pipe = PIPE_B;
+		/* XXX: else fix for eDP */
+	} else if (IS_VALLEYVIEW(dev)) {
+		/* presumably write lock depends on pipe, not port select */
+		pp_reg = VLV_PIPE_PP_CONTROL(pipe);
+		panel_pipe = pipe;
 	} else {
 		pp_reg = PP_CONTROL;
-		lvds_reg = LVDS;
+		if (I915_READ(LVDS) & LVDS_PIPEB_SELECT)
+			panel_pipe = PIPE_B;
 	}
 
 	val = I915_READ(pp_reg);
 	if (!(val & PANEL_POWER_ON) ||
-	    ((val & PANEL_UNLOCK_REGS) == PANEL_UNLOCK_REGS))
+	    ((val & PANEL_UNLOCK_MASK) == PANEL_UNLOCK_REGS))
 		locked = false;
 
-	if (I915_READ(lvds_reg) & LVDS_PIPEB_SELECT)
-		panel_pipe = PIPE_B;
-
 	WARN(panel_pipe == pipe && locked,
 	     "panel assertion failure, pipe %c regs locked\n",
 	     pipe_name(pipe));
@@ -1245,8 +1261,9 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
 								      pipe);
 
-	/* if we need the pipe A quirk it must be always on */
-	if (pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE)
+	/* if we need the pipe quirk it must be always on */
+	if ((pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) ||
+	    (pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE))
 		state = true;
 
 	if (!intel_display_power_enabled(dev_priv,
@@ -1300,7 +1317,7 @@ static void assert_planes_disabled(struct drm_i915_private *dev_priv,
 	}
 
 	/* Need to check both planes against the pipe */
-	for_each_pipe(i) {
+	for_each_pipe(dev_priv, i) {
 		reg = DSPCNTR(i);
 		val = I915_READ(reg);
 		cur_pipe = (val & DISPPLANE_SEL_PIPE_MASK) >>
@@ -1341,6 +1358,12 @@ static void assert_sprites_disabled(struct drm_i915_private *dev_priv,
 	}
 }
 
+static void assert_vblank_disabled(struct drm_crtc *crtc)
+{
+	if (WARN_ON(drm_crtc_vblank_get(crtc) == 0))
+		drm_crtc_vblank_put(crtc);
+}
+
 static void ibx_assert_pch_refclk_enabled(struct drm_i915_private *dev_priv)
 {
 	u32 val;
@@ -1513,34 +1536,6 @@ static void intel_init_dpio(struct drm_device *dev)
 	}
 }
 
-static void intel_reset_dpio(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (IS_CHERRYVIEW(dev)) {
-		enum dpio_phy phy;
-		u32 val;
-
-		for (phy = DPIO_PHY0; phy < I915_NUM_PHYS_VLV; phy++) {
-			/* Poll for phypwrgood signal */
-			if (wait_for(I915_READ(DISPLAY_PHY_STATUS) &
-						PHY_POWERGOOD(phy), 1))
-				DRM_ERROR("Display PHY %d is not power up\n", phy);
-
-			/*
-			 * Deassert common lane reset for PHY.
-			 *
-			 * This should only be done on init and resume from S3
-			 * with both PLLs disabled, or we risk losing DPIO and
-			 * PLL synchronization.
-			 */
-			val = I915_READ(DISPLAY_PHY_CONTROL);
-			I915_WRITE(DISPLAY_PHY_CONTROL,
-				PHY_COM_LANE_RESET_DEASSERT(phy, val));
-		}
-	}
-}
-
 static void vlv_enable_pll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -1554,7 +1549,7 @@ static void vlv_enable_pll(struct intel_crtc *crtc)
 	BUG_ON(!IS_VALLEYVIEW(dev_priv->dev));
 
 	/* PLL is protected by panel, make sure we can write it */
-	if (IS_MOBILE(dev_priv->dev) && !IS_I830(dev_priv->dev))
+	if (IS_MOBILE(dev_priv->dev))
 		assert_panel_unlocked(dev_priv, crtc->pipe);
 
 	I915_WRITE(reg, dpll);
@@ -1617,6 +1612,18 @@ static void chv_enable_pll(struct intel_crtc *crtc)
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
+static int intel_num_dvo_pipes(struct drm_device *dev)
+{
+	struct intel_crtc *crtc;
+	int count = 0;
+
+	for_each_intel_crtc(dev, crtc)
+		count += crtc->active &&
+			intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DVO);
+
+	return count;
+}
+
 static void i9xx_enable_pll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -1633,7 +1640,18 @@ static void i9xx_enable_pll(struct intel_crtc *crtc)
 	if (IS_MOBILE(dev) && !IS_I830(dev))
 		assert_panel_unlocked(dev_priv, crtc->pipe);
 
-	I915_WRITE(reg, dpll);
+	/* Enable DVO 2x clock on both PLLs if necessary */
+	if (IS_I830(dev) && intel_num_dvo_pipes(dev) > 0) {
+		/*
+		 * It appears to be important that we don't enable this
+		 * for the current pipe before otherwise configuring the
+		 * PLL. No idea how this should be handled if multiple
+		 * DVO outputs are enabled simultaneosly.
+		 */
+		dpll |= DPLL_DVO_2X_MODE;
+		I915_WRITE(DPLL(!crtc->pipe),
+			   I915_READ(DPLL(!crtc->pipe)) | DPLL_DVO_2X_MODE);
+	}
 
 	/* Wait for the clocks to stabilize. */
 	POSTING_READ(reg);
@@ -1672,10 +1690,25 @@ static void i9xx_enable_pll(struct intel_crtc *crtc)
  *
  * Note!  This is for pre-ILK only.
  */
-static void i9xx_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
+static void i9xx_disable_pll(struct intel_crtc *crtc)
 {
-	/* Don't disable pipe A or pipe A PLLs if needed */
-	if (pipe == PIPE_A && (dev_priv->quirks & QUIRK_PIPEA_FORCE))
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum pipe pipe = crtc->pipe;
+
+	/* Disable DVO 2x clock on both PLLs if necessary */
+	if (IS_I830(dev) &&
+	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DVO) &&
+	    intel_num_dvo_pipes(dev) == 1) {
+		I915_WRITE(DPLL(PIPE_B),
+			   I915_READ(DPLL(PIPE_B)) & ~DPLL_DVO_2X_MODE);
+		I915_WRITE(DPLL(PIPE_A),
+			   I915_READ(DPLL(PIPE_A)) & ~DPLL_DVO_2X_MODE);
+	}
+
+	/* Don't disable pipe or pipe PLLs if needed */
+	if ((pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) ||
+	    (pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE))
 		return;
 
 	/* Make sure the pipe isn't still relying on us */
@@ -1712,7 +1745,7 @@ static void chv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
 	assert_pipe_disabled(dev_priv, pipe);
 
 	/* Set PLL en = 0 */
-	val = DPLL_SSC_REF_CLOCK_CHV;
+	val = DPLL_SSC_REF_CLOCK_CHV | DPLL_REFA_CLK_ENABLE_VLV;
 	if (pipe != PIPE_A)
 		val |= DPLL_INTEGRATED_CRI_CLK_VLV;
 	I915_WRITE(DPLL(pipe), val);
@@ -1806,7 +1839,7 @@ static void intel_enable_shared_dpll(struct intel_crtc *crtc)
 	if (WARN_ON(pll->refcount == 0))
 		return;
 
-	DRM_DEBUG_KMS("enable %s (active %d, on? %d)for crtc %d\n",
+	DRM_DEBUG_KMS("enable %s (active %d, on? %d) for crtc %d\n",
 		      pll->name, pll->active, pll->on,
 		      crtc->base.base.id);
 
@@ -1824,7 +1857,7 @@ static void intel_enable_shared_dpll(struct intel_crtc *crtc)
 	pll->on = true;
 }
 
-void intel_disable_shared_dpll(struct intel_crtc *crtc)
+static void intel_disable_shared_dpll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1868,7 +1901,7 @@ static void ironlake_enable_pch_transcoder(struct drm_i915_private *dev_priv,
 	uint32_t reg, val, pipeconf_val;
 
 	/* PCH only available on ILK+ */
-	BUG_ON(INTEL_INFO(dev)->gen < 5);
+	BUG_ON(!HAS_PCH_SPLIT(dev));
 
 	/* Make sure PCH DPLL is enabled */
 	assert_shared_dpll_enabled(dev_priv,
@@ -1921,7 +1954,7 @@ static void lpt_enable_pch_transcoder(struct drm_i915_private *dev_priv,
 	u32 val, pipeconf_val;
 
 	/* PCH only available on ILK+ */
-	BUG_ON(INTEL_INFO(dev_priv->dev)->gen < 5);
+	BUG_ON(!HAS_PCH_SPLIT(dev_priv->dev));
 
 	/* FDI must be feeding us bits for PCH ports */
 	assert_fdi_tx_enabled(dev_priv, (enum pipe) cpu_transcoder);
@@ -2043,8 +2076,8 @@ static void intel_enable_pipe(struct intel_crtc *crtc)
 	reg = PIPECONF(cpu_transcoder);
 	val = I915_READ(reg);
 	if (val & PIPECONF_ENABLE) {
-		WARN_ON(!(pipe == PIPE_A &&
-			  dev_priv->quirks & QUIRK_PIPEA_FORCE));
+		WARN_ON(!((pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) ||
+			  (pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE)));
 		return;
 	}
 
@@ -2054,21 +2087,19 @@ static void intel_enable_pipe(struct intel_crtc *crtc)
 
 /**
  * intel_disable_pipe - disable a pipe, asserting requirements
- * @dev_priv: i915 private structure
- * @pipe: pipe to disable
+ * @crtc: crtc whose pipes is to be disabled
  *
- * Disable @pipe, making sure that various hardware specific requirements
- * are met, if applicable, e.g. plane disabled, panel fitter off, etc.
- *
- * @pipe should be %PIPE_A or %PIPE_B.
+ * Disable the pipe of @crtc, making sure that various hardware
+ * specific requirements are met, if applicable, e.g. plane
+ * disabled, panel fitter off, etc.
  *
  * Will wait until the pipe has shut down before returning.
  */
-static void intel_disable_pipe(struct drm_i915_private *dev_priv,
-			       enum pipe pipe)
+static void intel_disable_pipe(struct intel_crtc *crtc)
 {
-	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
-								      pipe);
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	enum transcoder cpu_transcoder = crtc->config.cpu_transcoder;
+	enum pipe pipe = crtc->pipe;
 	int reg;
 	u32 val;
 
@@ -2080,17 +2111,26 @@ static void intel_disable_pipe(struct drm_i915_private *dev_priv,
 	assert_cursor_disabled(dev_priv, pipe);
 	assert_sprites_disabled(dev_priv, pipe);
 
-	/* Don't disable pipe A or pipe A PLLs if needed */
-	if (pipe == PIPE_A && (dev_priv->quirks & QUIRK_PIPEA_FORCE))
-		return;
-
 	reg = PIPECONF(cpu_transcoder);
 	val = I915_READ(reg);
 	if ((val & PIPECONF_ENABLE) == 0)
 		return;
 
-	I915_WRITE(reg, val & ~PIPECONF_ENABLE);
-	intel_wait_for_pipe_off(dev_priv->dev, pipe);
+	/*
+	 * Double wide has implications for planes
+	 * so best keep it disabled when not needed.
+	 */
+	if (crtc->config.double_wide)
+		val &= ~PIPECONF_DOUBLE_WIDE;
+
+	/* Don't disable pipe or pipe PLLs if needed */
+	if (!(pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) &&
+	    !(pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE))
+		val &= ~PIPECONF_ENABLE;
+
+	I915_WRITE(reg, val);
+	if ((val & PIPECONF_ENABLE) == 0)
+		intel_wait_for_pipe_off(crtc);
 }
 
 /*
@@ -2109,35 +2149,28 @@ void intel_flush_primary_plane(struct drm_i915_private *dev_priv,
 
 /**
  * intel_enable_primary_hw_plane - enable the primary plane on a given pipe
- * @dev_priv: i915 private structure
- * @plane: plane to enable
- * @pipe: pipe being fed
+ * @plane:  plane to be enabled
+ * @crtc: crtc for the plane
  *
- * Enable @plane on @pipe, making sure that @pipe is running first.
+ * Enable @plane on @crtc, making sure that the pipe is running first.
  */
-static void intel_enable_primary_hw_plane(struct drm_i915_private *dev_priv,
-					  enum plane plane, enum pipe pipe)
+static void intel_enable_primary_hw_plane(struct drm_plane *plane,
+					  struct drm_crtc *crtc)
 {
-	struct drm_device *dev = dev_priv->dev;
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
-	int reg;
-	u32 val;
+	struct drm_device *dev = plane->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
 	/* If the pipe isn't enabled, we can't pump pixels and may hang */
-	assert_pipe_enabled(dev_priv, pipe);
+	assert_pipe_enabled(dev_priv, intel_crtc->pipe);
 
 	if (intel_crtc->primary_enabled)
 		return;
 
 	intel_crtc->primary_enabled = true;
 
-	reg = DSPCNTR(plane);
-	val = I915_READ(reg);
-	WARN_ON(val & DISPLAY_PLANE_ENABLE);
-
-	I915_WRITE(reg, val | DISPLAY_PLANE_ENABLE);
-	intel_flush_primary_plane(dev_priv, plane);
+	dev_priv->display.update_primary_plane(crtc, plane->fb,
+					       crtc->x, crtc->y);
 
 	/*
 	 * BDW signals flip done immediately if the plane
@@ -2150,31 +2183,27 @@ static void intel_enable_primary_hw_plane(struct drm_i915_private *dev_priv,
 
 /**
  * intel_disable_primary_hw_plane - disable the primary hardware plane
- * @dev_priv: i915 private structure
- * @plane: plane to disable
- * @pipe: pipe consuming the data
+ * @plane: plane to be disabled
+ * @crtc: crtc for the plane
  *
- * Disable @plane; should be an independent operation.
+ * Disable @plane on @crtc, making sure that the pipe is running first.
  */
-static void intel_disable_primary_hw_plane(struct drm_i915_private *dev_priv,
-					   enum plane plane, enum pipe pipe)
+static void intel_disable_primary_hw_plane(struct drm_plane *plane,
+					   struct drm_crtc *crtc)
 {
-	struct intel_crtc *intel_crtc =
-		to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
-	int reg;
-	u32 val;
+	struct drm_device *dev = plane->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+
+	assert_pipe_enabled(dev_priv, intel_crtc->pipe);
 
 	if (!intel_crtc->primary_enabled)
 		return;
 
 	intel_crtc->primary_enabled = false;
 
-	reg = DSPCNTR(plane);
-	val = I915_READ(reg);
-	WARN_ON((val & DISPLAY_PLANE_ENABLE) == 0);
-
-	I915_WRITE(reg, val & ~DISPLAY_PLANE_ENABLE);
-	intel_flush_primary_plane(dev_priv, plane);
+	dev_priv->display.update_primary_plane(crtc, plane->fb,
+					       crtc->x, crtc->y);
 }
 
 static bool need_vtd_wa(struct drm_device *dev)
@@ -2422,16 +2451,46 @@ static void i9xx_update_primary_plane(struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	struct drm_i915_gem_object *obj;
 	int plane = intel_crtc->plane;
 	unsigned long linear_offset;
 	u32 dspcntr;
-	u32 reg;
+	u32 reg = DSPCNTR(plane);
+	int pixel_size;
+
+	if (!intel_crtc->primary_enabled) {
+		I915_WRITE(reg, 0);
+		if (INTEL_INFO(dev)->gen >= 4)
+			I915_WRITE(DSPSURF(plane), 0);
+		else
+			I915_WRITE(DSPADDR(plane), 0);
+		POSTING_READ(reg);
+		return;
+	}
+
+	obj = intel_fb_obj(fb);
+	if (WARN_ON(obj == NULL))
+		return;
+
+	pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+
+	dspcntr = DISPPLANE_GAMMA_ENABLE;
+
+	dspcntr |= DISPLAY_PLANE_ENABLE;
+
+	if (INTEL_INFO(dev)->gen < 4) {
+		if (intel_crtc->pipe == PIPE_B)
+			dspcntr |= DISPPLANE_SEL_PIPE_B;
+
+		/* pipesrc and dspsize control the size that is scaled from,
+		 * which should always be the user's requested size.
+		 */
+		I915_WRITE(DSPSIZE(plane),
+			   ((intel_crtc->config.pipe_src_h - 1) << 16) |
+			   (intel_crtc->config.pipe_src_w - 1));
+		I915_WRITE(DSPPOS(plane), 0);
+	}
 
-	reg = DSPCNTR(plane);
-	dspcntr = I915_READ(reg);
-	/* Mask out pixel format bits in case we change it */
-	dspcntr &= ~DISPPLANE_PIXFORMAT_MASK;
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_C8:
 		dspcntr |= DISPPLANE_8BPP;
@@ -2463,30 +2522,40 @@ static void i9xx_update_primary_plane(struct drm_crtc *crtc,
 		BUG();
 	}
 
-	if (INTEL_INFO(dev)->gen >= 4) {
-		if (obj->tiling_mode != I915_TILING_NONE)
-			dspcntr |= DISPPLANE_TILED;
-		else
-			dspcntr &= ~DISPPLANE_TILED;
-	}
+	if (INTEL_INFO(dev)->gen >= 4 &&
+	    obj->tiling_mode != I915_TILING_NONE)
+		dspcntr |= DISPPLANE_TILED;
 
 	if (IS_G4X(dev))
 		dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE;
 
-	I915_WRITE(reg, dspcntr);
-
-	linear_offset = y * fb->pitches[0] + x * (fb->bits_per_pixel / 8);
+	linear_offset = y * fb->pitches[0] + x * pixel_size;
 
 	if (INTEL_INFO(dev)->gen >= 4) {
 		intel_crtc->dspaddr_offset =
 			intel_gen4_compute_page_offset(&x, &y, obj->tiling_mode,
-						       fb->bits_per_pixel / 8,
+						       pixel_size,
 						       fb->pitches[0]);
 		linear_offset -= intel_crtc->dspaddr_offset;
 	} else {
 		intel_crtc->dspaddr_offset = linear_offset;
 	}
 
+	if (to_intel_plane(crtc->primary)->rotation == BIT(DRM_ROTATE_180)) {
+		dspcntr |= DISPPLANE_ROTATE_180;
+
+		x += (intel_crtc->config.pipe_src_w - 1);
+		y += (intel_crtc->config.pipe_src_h - 1);
+
+		/* Finding the last pixel of the last line of the display
+		data and adding to linear_offset*/
+		linear_offset +=
+			(intel_crtc->config.pipe_src_h - 1) * fb->pitches[0] +
+			(intel_crtc->config.pipe_src_w - 1) * pixel_size;
+	}
+
+	I915_WRITE(reg, dspcntr);
+
 	DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n",
 		      i915_gem_obj_ggtt_offset(obj), linear_offset, x, y,
 		      fb->pitches[0]);
@@ -2508,16 +2577,33 @@ static void ironlake_update_primary_plane(struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	struct drm_i915_gem_object *obj;
 	int plane = intel_crtc->plane;
 	unsigned long linear_offset;
 	u32 dspcntr;
-	u32 reg;
+	u32 reg = DSPCNTR(plane);
+	int pixel_size;
+
+	if (!intel_crtc->primary_enabled) {
+		I915_WRITE(reg, 0);
+		I915_WRITE(DSPSURF(plane), 0);
+		POSTING_READ(reg);
+		return;
+	}
+
+	obj = intel_fb_obj(fb);
+	if (WARN_ON(obj == NULL))
+		return;
+
+	pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+
+	dspcntr = DISPPLANE_GAMMA_ENABLE;
+
+	dspcntr |= DISPLAY_PLANE_ENABLE;
+
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		dspcntr |= DISPPLANE_PIPE_CSC_ENABLE;
 
-	reg = DSPCNTR(plane);
-	dspcntr = I915_READ(reg);
-	/* Mask out pixel format bits in case we change it */
-	dspcntr &= ~DISPPLANE_PIXFORMAT_MASK;
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_C8:
 		dspcntr |= DISPPLANE_8BPP;
@@ -2547,22 +2633,32 @@ static void ironlake_update_primary_plane(struct drm_crtc *crtc,
 
 	if (obj->tiling_mode != I915_TILING_NONE)
 		dspcntr |= DISPPLANE_TILED;
-	else
-		dspcntr &= ~DISPPLANE_TILED;
 
-	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
-		dspcntr &= ~DISPPLANE_TRICKLE_FEED_DISABLE;
-	else
+	if (!IS_HASWELL(dev) && !IS_BROADWELL(dev))
 		dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE;
 
-	I915_WRITE(reg, dspcntr);
-
-	linear_offset = y * fb->pitches[0] + x * (fb->bits_per_pixel / 8);
+	linear_offset = y * fb->pitches[0] + x * pixel_size;
 	intel_crtc->dspaddr_offset =
 		intel_gen4_compute_page_offset(&x, &y, obj->tiling_mode,
-					       fb->bits_per_pixel / 8,
+					       pixel_size,
 					       fb->pitches[0]);
 	linear_offset -= intel_crtc->dspaddr_offset;
+	if (to_intel_plane(crtc->primary)->rotation == BIT(DRM_ROTATE_180)) {
+		dspcntr |= DISPPLANE_ROTATE_180;
+
+		if (!IS_HASWELL(dev) && !IS_BROADWELL(dev)) {
+			x += (intel_crtc->config.pipe_src_w - 1);
+			y += (intel_crtc->config.pipe_src_h - 1);
+
+			/* Finding the last pixel of the last line of the display
+			data and adding to linear_offset*/
+			linear_offset +=
+				(intel_crtc->config.pipe_src_h - 1) * fb->pitches[0] +
+				(intel_crtc->config.pipe_src_w - 1) * pixel_size;
+		}
+	}
+
+	I915_WRITE(reg, dspcntr);
 
 	DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n",
 		      i915_gem_obj_ggtt_offset(obj), linear_offset, x, y,
@@ -3346,23 +3442,54 @@ bool intel_has_pending_fb_unpin(struct drm_device *dev)
 	return false;
 }
 
+static void page_flip_completed(struct intel_crtc *intel_crtc)
+{
+	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
+	struct intel_unpin_work *work = intel_crtc->unpin_work;
+
+	/* ensure that the unpin work is consistent wrt ->pending. */
+	smp_rmb();
+	intel_crtc->unpin_work = NULL;
+
+	if (work->event)
+		drm_send_vblank_event(intel_crtc->base.dev,
+				      intel_crtc->pipe,
+				      work->event);
+
+	drm_crtc_vblank_put(&intel_crtc->base);
+
+	wake_up_all(&dev_priv->pending_flip_queue);
+	queue_work(dev_priv->wq, &work->work);
+
+	trace_i915_flip_complete(intel_crtc->plane,
+				 work->pending_flip_obj);
+}
+
 void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (crtc->primary->fb == NULL)
-		return;
-
 	WARN_ON(waitqueue_active(&dev_priv->pending_flip_queue));
+	if (WARN_ON(wait_event_timeout(dev_priv->pending_flip_queue,
+				       !intel_crtc_has_pending_flip(crtc),
+				       60*HZ) == 0)) {
+		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+		unsigned long flags;
 
-	WARN_ON(wait_event_timeout(dev_priv->pending_flip_queue,
-				   !intel_crtc_has_pending_flip(crtc),
-				   60*HZ) == 0);
+		spin_lock_irqsave(&dev->event_lock, flags);
+		if (intel_crtc->unpin_work) {
+			WARN_ONCE(1, "Removing stuck page flip\n");
+			page_flip_completed(intel_crtc);
+		}
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
 
-	mutex_lock(&dev->struct_mutex);
-	intel_finish_fb(crtc->primary->fb);
-	mutex_unlock(&dev->struct_mutex);
+	if (crtc->primary->fb) {
+		mutex_lock(&dev->struct_mutex);
+		intel_finish_fb(crtc->primary->fb);
+		mutex_unlock(&dev->struct_mutex);
+	}
 }
 
 /* Program iCLKIP clock to the desired frequency */
@@ -3911,14 +4038,14 @@ static void intel_crtc_dpms_overlay(struct intel_crtc *intel_crtc, bool enable)
 static void intel_crtc_enable_planes(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
+
+	assert_vblank_disabled(crtc);
 
 	drm_vblank_on(dev, pipe);
 
-	intel_enable_primary_hw_plane(dev_priv, plane, pipe);
+	intel_enable_primary_hw_plane(crtc->primary, crtc);
 	intel_enable_planes(crtc);
 	intel_crtc_update_cursor(crtc, true);
 	intel_crtc_dpms_overlay(intel_crtc, true);
@@ -3955,7 +4082,7 @@ static void intel_crtc_disable_planes(struct drm_crtc *crtc)
 	intel_crtc_dpms_overlay(intel_crtc, false);
 	intel_crtc_update_cursor(crtc, false);
 	intel_disable_planes(crtc);
-	intel_disable_primary_hw_plane(dev_priv, plane, pipe);
+	intel_disable_primary_hw_plane(crtc->primary, crtc);
 
 	/*
 	 * FIXME: Once we grow proper nuclear flip support out of this we need
@@ -3965,6 +4092,8 @@ static void intel_crtc_disable_planes(struct drm_crtc *crtc)
 	intel_frontbuffer_flip(dev, INTEL_FRONTBUFFER_ALL_MASK(pipe));
 
 	drm_vblank_off(dev, pipe);
+
+	assert_vblank_disabled(crtc);
 }
 
 static void ironlake_crtc_enable(struct drm_crtc *crtc)
@@ -3974,7 +4103,6 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
-	enum plane plane = intel_crtc->plane;
 
 	WARN_ON(!crtc->enabled);
 
@@ -3991,18 +4119,11 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 
 	if (intel_crtc->config.has_pch_encoder) {
 		intel_cpu_transcoder_set_m_n(intel_crtc,
-					     &intel_crtc->config.fdi_m_n);
+				     &intel_crtc->config.fdi_m_n, NULL);
 	}
 
 	ironlake_set_pipeconf(crtc);
 
-	/* Set up the display plane register */
-	I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE);
-	POSTING_READ(DSPCNTR(plane));
-
-	dev_priv->display.update_primary_plane(crtc, crtc->primary->fb,
-					       crtc->x, crtc->y);
-
 	intel_crtc->active = true;
 
 	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
@@ -4087,7 +4208,6 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
-	enum plane plane = intel_crtc->plane;
 
 	WARN_ON(!crtc->enabled);
 
@@ -4102,22 +4222,20 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 
 	intel_set_pipe_timings(intel_crtc);
 
+	if (intel_crtc->config.cpu_transcoder != TRANSCODER_EDP) {
+		I915_WRITE(PIPE_MULT(intel_crtc->config.cpu_transcoder),
+			   intel_crtc->config.pixel_multiplier - 1);
+	}
+
 	if (intel_crtc->config.has_pch_encoder) {
 		intel_cpu_transcoder_set_m_n(intel_crtc,
-					     &intel_crtc->config.fdi_m_n);
+				     &intel_crtc->config.fdi_m_n, NULL);
 	}
 
 	haswell_set_pipeconf(crtc);
 
 	intel_set_pipe_csc(crtc);
 
-	/* Set up the display plane register */
-	I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE | DISPPLANE_PIPE_CSC_ENABLE);
-	POSTING_READ(DSPCNTR(plane));
-
-	dev_priv->display.update_primary_plane(crtc, crtc->primary->fb,
-					       crtc->x, crtc->y);
-
 	intel_crtc->active = true;
 
 	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
@@ -4198,7 +4316,8 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc)
 	if (intel_crtc->config.has_pch_encoder)
 		intel_set_pch_fifo_underrun_reporting(dev, pipe, false);
 
-	intel_disable_pipe(dev_priv, pipe);
+	intel_disable_pipe(intel_crtc);
+
 	ironlake_pfit_disable(intel_crtc);
 
 	for_each_encoder_on_crtc(dev, crtc, encoder)
@@ -4246,7 +4365,6 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
-	int pipe = intel_crtc->pipe;
 	enum transcoder cpu_transcoder = intel_crtc->config.cpu_transcoder;
 
 	if (!intel_crtc->active)
@@ -4261,7 +4379,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 
 	if (intel_crtc->config.has_pch_encoder)
 		intel_set_pch_fifo_underrun_reporting(dev, TRANSCODER_A, false);
-	intel_disable_pipe(dev_priv, pipe);
+	intel_disable_pipe(intel_crtc);
 
 	if (intel_crtc->config.dp_encoder_is_mst)
 		intel_ddi_set_vc_payload_alloc(crtc, false);
@@ -4539,12 +4657,57 @@ static void valleyview_set_cdclk(struct drm_device *dev, int cdclk)
 	vlv_update_cdclk(dev);
 }
 
+static void cherryview_set_cdclk(struct drm_device *dev, int cdclk)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 val, cmd;
+
+	WARN_ON(dev_priv->display.get_display_clock_speed(dev) != dev_priv->vlv_cdclk_freq);
+
+	switch (cdclk) {
+	case 400000:
+		cmd = 3;
+		break;
+	case 333333:
+	case 320000:
+		cmd = 2;
+		break;
+	case 266667:
+		cmd = 1;
+		break;
+	case 200000:
+		cmd = 0;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+	val = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ);
+	val &= ~DSPFREQGUAR_MASK_CHV;
+	val |= (cmd << DSPFREQGUAR_SHIFT_CHV);
+	vlv_punit_write(dev_priv, PUNIT_REG_DSPFREQ, val);
+	if (wait_for((vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ) &
+		      DSPFREQSTAT_MASK_CHV) == (cmd << DSPFREQSTAT_SHIFT_CHV),
+		     50)) {
+		DRM_ERROR("timed out waiting for CDclk change\n");
+	}
+	mutex_unlock(&dev_priv->rps.hw_lock);
+
+	vlv_update_cdclk(dev);
+}
+
 static int valleyview_calc_cdclk(struct drm_i915_private *dev_priv,
 				 int max_pixclk)
 {
 	int vco = valleyview_get_vco(dev_priv);
 	int freq_320 = (vco <<  1) % 320000 != 0 ? 333333 : 320000;
 
+	/* FIXME: Punit isn't quite ready yet */
+	if (IS_CHERRYVIEW(dev_priv->dev))
+		return 400000;
+
 	/*
 	 * Really only a few cases to deal with, as only 4 CDclks are supported:
 	 *   200MHz
@@ -4607,21 +4770,23 @@ static void valleyview_modeset_global_resources(struct drm_device *dev)
 	int max_pixclk = intel_mode_max_pixclk(dev_priv);
 	int req_cdclk = valleyview_calc_cdclk(dev_priv, max_pixclk);
 
-	if (req_cdclk != dev_priv->vlv_cdclk_freq)
-		valleyview_set_cdclk(dev, req_cdclk);
+	if (req_cdclk != dev_priv->vlv_cdclk_freq) {
+		if (IS_CHERRYVIEW(dev))
+			cherryview_set_cdclk(dev, req_cdclk);
+		else
+			valleyview_set_cdclk(dev, req_cdclk);
+	}
+
 	modeset_update_crtc_power_domains(dev);
 }
 
 static void valleyview_crtc_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
 	bool is_dsi;
-	u32 dspcntr;
 
 	WARN_ON(!crtc->enabled);
 
@@ -4630,33 +4795,20 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc)
 
 	is_dsi = intel_pipe_has_type(crtc, INTEL_OUTPUT_DSI);
 
-	if (!is_dsi && !IS_CHERRYVIEW(dev))
-		vlv_prepare_pll(intel_crtc);
-
-	/* Set up the display plane register */
-	dspcntr = DISPPLANE_GAMMA_ENABLE;
+	if (!is_dsi) {
+		if (IS_CHERRYVIEW(dev))
+			chv_prepare_pll(intel_crtc);
+		else
+			vlv_prepare_pll(intel_crtc);
+	}
 
 	if (intel_crtc->config.has_dp_encoder)
 		intel_dp_set_m_n(intel_crtc);
 
 	intel_set_pipe_timings(intel_crtc);
 
-	/* pipesrc and dspsize control the size that is scaled from,
-	 * which should always be the user's requested size.
-	 */
-	I915_WRITE(DSPSIZE(plane),
-		   ((intel_crtc->config.pipe_src_h - 1) << 16) |
-		   (intel_crtc->config.pipe_src_w - 1));
-	I915_WRITE(DSPPOS(plane), 0);
-
 	i9xx_set_pipeconf(intel_crtc);
 
-	I915_WRITE(DSPCNTR(plane), dspcntr);
-	POSTING_READ(DSPCNTR(plane));
-
-	dev_priv->display.update_primary_plane(crtc, crtc->primary->fb,
-					       crtc->x, crtc->y);
-
 	intel_crtc->active = true;
 
 	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
@@ -4704,12 +4856,9 @@ static void i9xx_set_pll_dividers(struct intel_crtc *crtc)
 static void i9xx_crtc_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
-	u32 dspcntr;
 
 	WARN_ON(!crtc->enabled);
 
@@ -4718,35 +4867,13 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc)
 
 	i9xx_set_pll_dividers(intel_crtc);
 
-	/* Set up the display plane register */
-	dspcntr = DISPPLANE_GAMMA_ENABLE;
-
-	if (pipe == 0)
-		dspcntr &= ~DISPPLANE_SEL_PIPE_MASK;
-	else
-		dspcntr |= DISPPLANE_SEL_PIPE_B;
-
 	if (intel_crtc->config.has_dp_encoder)
 		intel_dp_set_m_n(intel_crtc);
 
 	intel_set_pipe_timings(intel_crtc);
 
-	/* pipesrc and dspsize control the size that is scaled from,
-	 * which should always be the user's requested size.
-	 */
-	I915_WRITE(DSPSIZE(plane),
-		   ((intel_crtc->config.pipe_src_h - 1) << 16) |
-		   (intel_crtc->config.pipe_src_w - 1));
-	I915_WRITE(DSPPOS(plane), 0);
-
 	i9xx_set_pipeconf(intel_crtc);
 
-	I915_WRITE(DSPCNTR(plane), dspcntr);
-	POSTING_READ(DSPCNTR(plane));
-
-	dev_priv->display.update_primary_plane(crtc, crtc->primary->fb,
-					       crtc->x, crtc->y);
-
 	intel_crtc->active = true;
 
 	if (!IS_GEN2(dev))
@@ -4842,7 +4969,7 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 	 */
 	intel_wait_for_vblank(dev, pipe);
 
-	intel_disable_pipe(dev_priv, pipe);
+	intel_disable_pipe(intel_crtc);
 
 	i9xx_pfit_disable(intel_crtc);
 
@@ -4856,7 +4983,7 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 		else if (IS_VALLEYVIEW(dev))
 			vlv_disable_pll(dev_priv, pipe);
 		else
-			i9xx_disable_pll(dev_priv, pipe);
+			i9xx_disable_pll(intel_crtc);
 	}
 
 	if (!IS_GEN2(dev))
@@ -5275,6 +5402,10 @@ static int valleyview_get_display_clock_speed(struct drm_device *dev)
 	u32 val;
 	int divider;
 
+	/* FIXME: Punit isn't quite ready yet */
+	if (IS_CHERRYVIEW(dev))
+		return 400000;
+
 	mutex_lock(&dev_priv->dpio_lock);
 	val = vlv_cck_read(dev_priv, CCK_DISPLAY_CLOCK_CONTROL);
 	mutex_unlock(&dev_priv->dpio_lock);
@@ -5519,7 +5650,8 @@ static void intel_pch_transcoder_set_m_n(struct intel_crtc *crtc,
 }
 
 static void intel_cpu_transcoder_set_m_n(struct intel_crtc *crtc,
-					 struct intel_link_m_n *m_n)
+					 struct intel_link_m_n *m_n,
+					 struct intel_link_m_n *m2_n2)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -5531,6 +5663,18 @@ static void intel_cpu_transcoder_set_m_n(struct intel_crtc *crtc,
 		I915_WRITE(PIPE_DATA_N1(transcoder), m_n->gmch_n);
 		I915_WRITE(PIPE_LINK_M1(transcoder), m_n->link_m);
 		I915_WRITE(PIPE_LINK_N1(transcoder), m_n->link_n);
+		/* M2_N2 registers to be set only for gen < 8 (M2_N2 available
+		 * for gen < 8) and if DRRS is supported (to make sure the
+		 * registers are not unnecessarily accessed).
+		 */
+		if (m2_n2 && INTEL_INFO(dev)->gen < 8 &&
+			crtc->config.has_drrs) {
+			I915_WRITE(PIPE_DATA_M2(transcoder),
+					TU_SIZE(m2_n2->tu) | m2_n2->gmch_m);
+			I915_WRITE(PIPE_DATA_N2(transcoder), m2_n2->gmch_n);
+			I915_WRITE(PIPE_LINK_M2(transcoder), m2_n2->link_m);
+			I915_WRITE(PIPE_LINK_N2(transcoder), m2_n2->link_n);
+		}
 	} else {
 		I915_WRITE(PIPE_DATA_M_G4X(pipe), TU_SIZE(m_n->tu) | m_n->gmch_m);
 		I915_WRITE(PIPE_DATA_N_G4X(pipe), m_n->gmch_n);
@@ -5539,12 +5683,13 @@ static void intel_cpu_transcoder_set_m_n(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_dp_set_m_n(struct intel_crtc *crtc)
+void intel_dp_set_m_n(struct intel_crtc *crtc)
 {
 	if (crtc->config.has_pch_encoder)
 		intel_pch_transcoder_set_m_n(crtc, &crtc->config.dp_m_n);
 	else
-		intel_cpu_transcoder_set_m_n(crtc, &crtc->config.dp_m_n);
+		intel_cpu_transcoder_set_m_n(crtc, &crtc->config.dp_m_n,
+						   &crtc->config.dp_m2_n2);
 }
 
 static void vlv_update_pll(struct intel_crtc *crtc)
@@ -5662,6 +5807,18 @@ static void vlv_prepare_pll(struct intel_crtc *crtc)
 
 static void chv_update_pll(struct intel_crtc *crtc)
 {
+	crtc->config.dpll_hw_state.dpll = DPLL_SSC_REF_CLOCK_CHV |
+		DPLL_REFA_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS |
+		DPLL_VCO_ENABLE;
+	if (crtc->pipe != PIPE_A)
+		crtc->config.dpll_hw_state.dpll |= DPLL_INTEGRATED_CRI_CLK_VLV;
+
+	crtc->config.dpll_hw_state.dpll_md =
+		(crtc->config.pixel_multiplier - 1) << DPLL_MD_UDI_MULTIPLIER_SHIFT;
+}
+
+static void chv_prepare_pll(struct intel_crtc *crtc)
+{
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe = crtc->pipe;
@@ -5671,15 +5828,6 @@ static void chv_update_pll(struct intel_crtc *crtc)
 	u32 bestn, bestm1, bestm2, bestp1, bestp2, bestm2_frac;
 	int refclk;
 
-	crtc->config.dpll_hw_state.dpll = DPLL_SSC_REF_CLOCK_CHV |
-		DPLL_REFA_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS |
-		DPLL_VCO_ENABLE;
-	if (pipe != PIPE_A)
-		crtc->config.dpll_hw_state.dpll |= DPLL_INTEGRATED_CRI_CLK_VLV;
-
-	crtc->config.dpll_hw_state.dpll_md =
-		(crtc->config.pixel_multiplier - 1) << DPLL_MD_UDI_MULTIPLIER_SHIFT;
-
 	bestn = crtc->config.dpll.n;
 	bestm2_frac = crtc->config.dpll.m2 & 0x3fffff;
 	bestm1 = crtc->config.dpll.m1;
@@ -5839,7 +5987,7 @@ static void i8xx_update_pll(struct intel_crtc *crtc,
 			dpll |= PLL_P2_DIVIDE_BY_4;
 	}
 
-	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DVO))
+	if (!IS_I830(dev) && intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DVO))
 		dpll |= DPLL_DVO_2X_MODE;
 
 	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_LVDS) &&
@@ -5990,9 +6138,9 @@ static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc)
 
 	pipeconf = 0;
 
-	if (dev_priv->quirks & QUIRK_PIPEA_FORCE &&
-	    I915_READ(PIPECONF(intel_crtc->pipe)) & PIPECONF_ENABLE)
-		pipeconf |= PIPECONF_ENABLE;
+	if ((intel_crtc->pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) ||
+	    (intel_crtc->pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE))
+		pipeconf |= I915_READ(PIPECONF(intel_crtc->pipe)) & PIPECONF_ENABLE;
 
 	if (intel_crtc->config.double_wide)
 		pipeconf |= PIPECONF_DOUBLE_WIDE;
@@ -6235,7 +6383,7 @@ static void i9xx_get_plane_config(struct intel_crtc *crtc,
 	crtc->base.primary->fb->height = ((val >> 0) & 0xfff) + 1;
 
 	val = I915_READ(DSPSTRIDE(pipe));
-	crtc->base.primary->fb->pitches[0] = val & 0xffffff80;
+	crtc->base.primary->fb->pitches[0] = val & 0xffffffc0;
 
 	aligned_height = intel_align_height(dev, crtc->base.primary->fb->height,
 					    plane_config->tiled);
@@ -6345,6 +6493,14 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 	}
 	pipe_config->dpll_hw_state.dpll = I915_READ(DPLL(crtc->pipe));
 	if (!IS_VALLEYVIEW(dev)) {
+		/*
+		 * DPLL_DVO_2X_MODE must be enabled for both DPLLs
+		 * on 830. Filter it out here so that we don't
+		 * report errors due to that.
+		 */
+		if (IS_I830(dev))
+			pipe_config->dpll_hw_state.dpll &= ~DPLL_DVO_2X_MODE;
+
 		pipe_config->dpll_hw_state.fp0 = I915_READ(FP0(crtc->pipe));
 		pipe_config->dpll_hw_state.fp1 = I915_READ(FP1(crtc->pipe));
 	} else {
@@ -6367,7 +6523,6 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 static void ironlake_init_pch_refclk(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct intel_encoder *encoder;
 	u32 val, final;
 	bool has_lvds = false;
@@ -6377,8 +6532,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 	bool can_ssc = false;
 
 	/* We need to take the global config into account */
-	list_for_each_entry(encoder, &mode_config->encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		switch (encoder->type) {
 		case INTEL_OUTPUT_LVDS:
 			has_panel = true;
@@ -6685,11 +6839,10 @@ static void lpt_disable_clkout_dp(struct drm_device *dev)
 
 static void lpt_init_pch_refclk(struct drm_device *dev)
 {
-	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct intel_encoder *encoder;
 	bool has_vga = false;
 
-	list_for_each_entry(encoder, &mode_config->encoder_list, base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		switch (encoder->type) {
 		case INTEL_OUTPUT_ANALOG:
 			has_vga = true;
@@ -7145,7 +7298,8 @@ static void intel_pch_transcoder_get_m_n(struct intel_crtc *crtc,
 
 static void intel_cpu_transcoder_get_m_n(struct intel_crtc *crtc,
 					 enum transcoder transcoder,
-					 struct intel_link_m_n *m_n)
+					 struct intel_link_m_n *m_n,
+					 struct intel_link_m_n *m2_n2)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -7159,6 +7313,20 @@ static void intel_cpu_transcoder_get_m_n(struct intel_crtc *crtc,
 		m_n->gmch_n = I915_READ(PIPE_DATA_N1(transcoder));
 		m_n->tu = ((I915_READ(PIPE_DATA_M1(transcoder))
 			    & TU_SIZE_MASK) >> TU_SIZE_SHIFT) + 1;
+		/* Read M2_N2 registers only for gen < 8 (M2_N2 available for
+		 * gen < 8) and if DRRS is supported (to make sure the
+		 * registers are not unnecessarily read).
+		 */
+		if (m2_n2 && INTEL_INFO(dev)->gen < 8 &&
+			crtc->config.has_drrs) {
+			m2_n2->link_m = I915_READ(PIPE_LINK_M2(transcoder));
+			m2_n2->link_n =	I915_READ(PIPE_LINK_N2(transcoder));
+			m2_n2->gmch_m =	I915_READ(PIPE_DATA_M2(transcoder))
+					& ~TU_SIZE_MASK;
+			m2_n2->gmch_n =	I915_READ(PIPE_DATA_N2(transcoder));
+			m2_n2->tu = ((I915_READ(PIPE_DATA_M2(transcoder))
+					& TU_SIZE_MASK) >> TU_SIZE_SHIFT) + 1;
+		}
 	} else {
 		m_n->link_m = I915_READ(PIPE_LINK_M_G4X(pipe));
 		m_n->link_n = I915_READ(PIPE_LINK_N_G4X(pipe));
@@ -7177,14 +7345,15 @@ void intel_dp_get_m_n(struct intel_crtc *crtc,
 		intel_pch_transcoder_get_m_n(crtc, &pipe_config->dp_m_n);
 	else
 		intel_cpu_transcoder_get_m_n(crtc, pipe_config->cpu_transcoder,
-					     &pipe_config->dp_m_n);
+					     &pipe_config->dp_m_n,
+					     &pipe_config->dp_m2_n2);
 }
 
 static void ironlake_get_fdi_m_n_config(struct intel_crtc *crtc,
 					struct intel_crtc_config *pipe_config)
 {
 	intel_cpu_transcoder_get_m_n(crtc, pipe_config->cpu_transcoder,
-				     &pipe_config->fdi_m_n);
+				     &pipe_config->fdi_m_n, NULL);
 }
 
 static void ironlake_get_pfit_config(struct intel_crtc *crtc,
@@ -7255,7 +7424,7 @@ static void ironlake_get_plane_config(struct intel_crtc *crtc,
 	crtc->base.primary->fb->height = ((val >> 0) & 0xfff) + 1;
 
 	val = I915_READ(DSPSTRIDE(pipe));
-	crtc->base.primary->fb->pitches[0] = val & 0xffffff80;
+	crtc->base.primary->fb->pitches[0] = val & 0xffffffc0;
 
 	aligned_height = intel_align_height(dev, crtc->base.primary->fb->height,
 					    plane_config->tiled);
@@ -7615,6 +7784,22 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc,
 	return 0;
 }
 
+static void haswell_get_ddi_pll(struct drm_i915_private *dev_priv,
+				enum port port,
+				struct intel_crtc_config *pipe_config)
+{
+	pipe_config->ddi_pll_sel = I915_READ(PORT_CLK_SEL(port));
+
+	switch (pipe_config->ddi_pll_sel) {
+	case PORT_CLK_SEL_WRPLL1:
+		pipe_config->shared_dpll = DPLL_ID_WRPLL1;
+		break;
+	case PORT_CLK_SEL_WRPLL2:
+		pipe_config->shared_dpll = DPLL_ID_WRPLL2;
+		break;
+	}
+}
+
 static void haswell_get_ddi_port_state(struct intel_crtc *crtc,
 				       struct intel_crtc_config *pipe_config)
 {
@@ -7628,16 +7813,7 @@ static void haswell_get_ddi_port_state(struct intel_crtc *crtc,
 
 	port = (tmp & TRANS_DDI_PORT_MASK) >> TRANS_DDI_PORT_SHIFT;
 
-	pipe_config->ddi_pll_sel = I915_READ(PORT_CLK_SEL(port));
-
-	switch (pipe_config->ddi_pll_sel) {
-	case PORT_CLK_SEL_WRPLL1:
-		pipe_config->shared_dpll = DPLL_ID_WRPLL1;
-		break;
-	case PORT_CLK_SEL_WRPLL2:
-		pipe_config->shared_dpll = DPLL_ID_WRPLL2;
-		break;
-	}
+	haswell_get_ddi_pll(dev_priv, port, pipe_config);
 
 	if (pipe_config->shared_dpll >= 0) {
 		pll = &dev_priv->shared_dplls[pipe_config->shared_dpll];
@@ -7719,7 +7895,12 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 		pipe_config->ips_enabled = hsw_crtc_supports_ips(crtc) &&
 			(I915_READ(IPS_CTL) & IPS_ENABLE);
 
-	pipe_config->pixel_multiplier = 1;
+	if (pipe_config->cpu_transcoder != TRANSCODER_EDP) {
+		pipe_config->pixel_multiplier =
+			I915_READ(PIPE_MULT(pipe_config->cpu_transcoder)) + 1;
+	} else {
+		pipe_config->pixel_multiplier = 1;
+	}
 
 	return true;
 }
@@ -8037,74 +8218,62 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base)
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	uint32_t cntl;
+	uint32_t cntl = 0, size = 0;
 
-	if (base != intel_crtc->cursor_base) {
-		/* On these chipsets we can only modify the base whilst
-		 * the cursor is disabled.
-		 */
-		if (intel_crtc->cursor_cntl) {
-			I915_WRITE(_CURACNTR, 0);
-			POSTING_READ(_CURACNTR);
-			intel_crtc->cursor_cntl = 0;
+	if (base) {
+		unsigned int width = intel_crtc->cursor_width;
+		unsigned int height = intel_crtc->cursor_height;
+		unsigned int stride = roundup_pow_of_two(width) * 4;
+
+		switch (stride) {
+		default:
+			WARN_ONCE(1, "Invalid cursor width/stride, width=%u, stride=%u\n",
+				  width, stride);
+			stride = 256;
+			/* fallthrough */
+		case 256:
+		case 512:
+		case 1024:
+		case 2048:
+			break;
 		}
 
-		I915_WRITE(_CURABASE, base);
-		POSTING_READ(_CURABASE);
+		cntl |= CURSOR_ENABLE |
+			CURSOR_GAMMA_ENABLE |
+			CURSOR_FORMAT_ARGB |
+			CURSOR_STRIDE(stride);
+
+		size = (height << 12) | width;
 	}
 
-	/* XXX width must be 64, stride 256 => 0x00 << 28 */
-	cntl = 0;
-	if (base)
-		cntl = (CURSOR_ENABLE |
-			CURSOR_GAMMA_ENABLE |
-			CURSOR_FORMAT_ARGB);
-	if (intel_crtc->cursor_cntl != cntl) {
-		I915_WRITE(_CURACNTR, cntl);
+	if (intel_crtc->cursor_cntl != 0 &&
+	    (intel_crtc->cursor_base != base ||
+	     intel_crtc->cursor_size != size ||
+	     intel_crtc->cursor_cntl != cntl)) {
+		/* On these chipsets we can only modify the base/size/stride
+		 * whilst the cursor is disabled.
+		 */
+		I915_WRITE(_CURACNTR, 0);
 		POSTING_READ(_CURACNTR);
-		intel_crtc->cursor_cntl = cntl;
+		intel_crtc->cursor_cntl = 0;
 	}
-}
 
-static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
-	uint32_t cntl;
+	if (intel_crtc->cursor_base != base)
+		I915_WRITE(_CURABASE, base);
 
-	cntl = 0;
-	if (base) {
-		cntl = MCURSOR_GAMMA_ENABLE;
-		switch (intel_crtc->cursor_width) {
-			case 64:
-				cntl |= CURSOR_MODE_64_ARGB_AX;
-				break;
-			case 128:
-				cntl |= CURSOR_MODE_128_ARGB_AX;
-				break;
-			case 256:
-				cntl |= CURSOR_MODE_256_ARGB_AX;
-				break;
-			default:
-				WARN_ON(1);
-				return;
-		}
-		cntl |= pipe << 28; /* Connect to correct pipe */
+	if (intel_crtc->cursor_size != size) {
+		I915_WRITE(CURSIZE, size);
+		intel_crtc->cursor_size = size;
 	}
+
 	if (intel_crtc->cursor_cntl != cntl) {
-		I915_WRITE(CURCNTR(pipe), cntl);
-		POSTING_READ(CURCNTR(pipe));
+		I915_WRITE(_CURACNTR, cntl);
+		POSTING_READ(_CURACNTR);
 		intel_crtc->cursor_cntl = cntl;
 	}
-
-	/* and commit changes on next vblank */
-	I915_WRITE(CURBASE(pipe), base);
-	POSTING_READ(CURBASE(pipe));
 }
 
-static void ivb_update_cursor(struct drm_crtc *crtc, u32 base)
+static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -8129,6 +8298,7 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base)
 				WARN_ON(1);
 				return;
 		}
+		cntl |= pipe << 28; /* Connect to correct pipe */
 	}
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		cntl |= CURSOR_PIPE_CSC_ENABLE;
@@ -8188,15 +8358,50 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc,
 
 	I915_WRITE(CURPOS(pipe), pos);
 
-	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev))
-		ivb_update_cursor(crtc, base);
-	else if (IS_845G(dev) || IS_I865G(dev))
+	if (IS_845G(dev) || IS_I865G(dev))
 		i845_update_cursor(crtc, base);
 	else
 		i9xx_update_cursor(crtc, base);
 	intel_crtc->cursor_base = base;
 }
 
+static bool cursor_size_ok(struct drm_device *dev,
+			   uint32_t width, uint32_t height)
+{
+	if (width == 0 || height == 0)
+		return false;
+
+	/*
+	 * 845g/865g are special in that they are only limited by
+	 * the width of their cursors, the height is arbitrary up to
+	 * the precision of the register. Everything else requires
+	 * square cursors, limited to a few power-of-two sizes.
+	 */
+	if (IS_845G(dev) || IS_I865G(dev)) {
+		if ((width & 63) != 0)
+			return false;
+
+		if (width > (IS_845G(dev) ? 64 : 512))
+			return false;
+
+		if (height > 1023)
+			return false;
+	} else {
+		switch (width | height) {
+		case 256:
+		case 128:
+			if (IS_GEN2(dev))
+				return false;
+		case 64:
+			break;
+		default:
+			return false;
+		}
+	}
+
+	return true;
+}
+
 /*
  * intel_crtc_cursor_set_obj - Set cursor to specified GEM object
  *
@@ -8212,7 +8417,7 @@ static int intel_crtc_cursor_set_obj(struct drm_crtc *crtc,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum pipe pipe = intel_crtc->pipe;
-	unsigned old_width;
+	unsigned old_width, stride;
 	uint32_t addr;
 	int ret;
 
@@ -8220,20 +8425,18 @@ static int intel_crtc_cursor_set_obj(struct drm_crtc *crtc,
 	if (!obj) {
 		DRM_DEBUG_KMS("cursor off\n");
 		addr = 0;
-		obj = NULL;
 		mutex_lock(&dev->struct_mutex);
 		goto finish;
 	}
 
 	/* Check for which cursor types we support */
-	if (!((width == 64 && height == 64) ||
-			(width == 128 && height == 128 && !IS_GEN2(dev)) ||
-			(width == 256 && height == 256 && !IS_GEN2(dev)))) {
+	if (!cursor_size_ok(dev, width, height)) {
 		DRM_DEBUG("Cursor dimension not supported\n");
 		return -EINVAL;
 	}
 
-	if (obj->base.size < width * height * 4) {
+	stride = roundup_pow_of_two(width) * 4;
+	if (obj->base.size < stride * height) {
 		DRM_DEBUG_KMS("buffer is too small\n");
 		ret = -ENOMEM;
 		goto fail;
@@ -8295,9 +8498,6 @@ static int intel_crtc_cursor_set_obj(struct drm_crtc *crtc,
 		addr = obj->phys_handle->busaddr;
 	}
 
-	if (IS_GEN2(dev))
-		I915_WRITE(CURSIZE, (height << 12) | width);
-
  finish:
 	if (intel_crtc->cursor_bo) {
 		if (!INTEL_INFO(dev)->cursor_needs_physical)
@@ -8944,12 +9144,13 @@ static void intel_mark_fb_busy(struct drm_device *dev,
 			       unsigned frontbuffer_bits,
 			       struct intel_engine_cs *ring)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum pipe pipe;
 
 	if (!i915.powersave)
 		return;
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		if (!(frontbuffer_bits & INTEL_FRONTBUFFER_ALL_MASK(pipe)))
 			continue;
 
@@ -9019,6 +9220,14 @@ void intel_frontbuffer_flush(struct drm_device *dev,
 	intel_mark_fb_busy(dev, frontbuffer_bits, NULL);
 
 	intel_edp_psr_flush(dev, frontbuffer_bits);
+
+	/*
+	 * FIXME: Unconditional fbc flushing here is a rather gross hack and
+	 * needs to be reworked into a proper frontbuffer tracking scheme like
+	 * psr employs.
+	 */
+	if (IS_BROADWELL(dev))
+		gen8_fbc_sw_flush(dev, FBC_REND_CACHE_CLEAN);
 }
 
 /**
@@ -9151,7 +9360,6 @@ static void intel_unpin_work_fn(struct work_struct *__work)
 static void do_intel_finish_page_flip(struct drm_device *dev,
 				      struct drm_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_unpin_work *work;
 	unsigned long flags;
@@ -9171,23 +9379,9 @@ static void do_intel_finish_page_flip(struct drm_device *dev,
 		return;
 	}
 
-	/* and that the unpin work is consistent wrt ->pending. */
-	smp_rmb();
-
-	intel_crtc->unpin_work = NULL;
-
-	if (work->event)
-		drm_send_vblank_event(dev, intel_crtc->pipe, work->event);
-
-	drm_crtc_vblank_put(crtc);
+	page_flip_completed(intel_crtc);
 
 	spin_unlock_irqrestore(&dev->event_lock, flags);
-
-	wake_up_all(&dev_priv->pending_flip_queue);
-
-	queue_work(dev_priv->wq, &work->work);
-
-	trace_i915_flip_complete(intel_crtc->plane, work->pending_flip_obj);
 }
 
 void intel_finish_page_flip(struct drm_device *dev, int pipe)
@@ -9532,6 +9726,8 @@ static bool use_mmio_flip(struct intel_engine_cs *ring,
 		return false;
 	else if (i915.use_mmio_flip > 0)
 		return true;
+	else if (i915.enable_execlists)
+		return true;
 	else
 		return ring != obj->ring;
 }
@@ -9665,6 +9861,65 @@ static int intel_default_queue_flip(struct drm_device *dev,
 	return -ENODEV;
 }
 
+static bool __intel_pageflip_stall_check(struct drm_device *dev,
+					 struct drm_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct intel_unpin_work *work = intel_crtc->unpin_work;
+	u32 addr;
+
+	if (atomic_read(&work->pending) >= INTEL_FLIP_COMPLETE)
+		return true;
+
+	if (!work->enable_stall_check)
+		return false;
+
+	if (work->flip_ready_vblank == 0) {
+		if (work->flip_queued_ring &&
+		    !i915_seqno_passed(work->flip_queued_ring->get_seqno(work->flip_queued_ring, true),
+				       work->flip_queued_seqno))
+			return false;
+
+		work->flip_ready_vblank = drm_vblank_count(dev, intel_crtc->pipe);
+	}
+
+	if (drm_vblank_count(dev, intel_crtc->pipe) - work->flip_ready_vblank < 3)
+		return false;
+
+	/* Potential stall - if we see that the flip has happened,
+	 * assume a missed interrupt. */
+	if (INTEL_INFO(dev)->gen >= 4)
+		addr = I915_HI_DISPBASE(I915_READ(DSPSURF(intel_crtc->plane)));
+	else
+		addr = I915_READ(DSPADDR(intel_crtc->plane));
+
+	/* There is a potential issue here with a false positive after a flip
+	 * to the same address. We could address this by checking for a
+	 * non-incrementing frame counter.
+	 */
+	return addr == work->gtt_offset;
+}
+
+void intel_check_page_flip(struct drm_device *dev, int pipe)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	unsigned long flags;
+
+	if (crtc == NULL)
+		return;
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+	if (intel_crtc->unpin_work && __intel_pageflip_stall_check(dev, crtc)) {
+		WARN_ONCE(1, "Kicking stuck page flip: queued at %d, now %d\n",
+			 intel_crtc->unpin_work->flip_queued_vblank, drm_vblank_count(dev, pipe));
+		page_flip_completed(intel_crtc);
+	}
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
 static int intel_crtc_page_flip(struct drm_crtc *crtc,
 				struct drm_framebuffer *fb,
 				struct drm_pending_vblank_event *event,
@@ -9721,12 +9976,20 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	/* We borrow the event spin lock for protecting unpin_work */
 	spin_lock_irqsave(&dev->event_lock, flags);
 	if (intel_crtc->unpin_work) {
-		spin_unlock_irqrestore(&dev->event_lock, flags);
-		kfree(work);
-		drm_crtc_vblank_put(crtc);
+		/* Before declaring the flip queue wedged, check if
+		 * the hardware completed the operation behind our backs.
+		 */
+		if (__intel_pageflip_stall_check(dev, crtc)) {
+			DRM_DEBUG_DRIVER("flip queue: previous flip completed, continuing\n");
+			page_flip_completed(intel_crtc);
+		} else {
+			DRM_DEBUG_DRIVER("flip queue: crtc already busy\n");
+			spin_unlock_irqrestore(&dev->event_lock, flags);
 
-		DRM_DEBUG_DRIVER("flip queue: crtc already busy\n");
-		return -EBUSY;
+			drm_crtc_vblank_put(crtc);
+			kfree(work);
+			return -EBUSY;
+		}
 	}
 	intel_crtc->unpin_work = work;
 	spin_unlock_irqrestore(&dev->event_lock, flags);
@@ -9746,8 +10009,6 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 
 	work->pending_flip_obj = obj;
 
-	work->enable_stall_check = true;
-
 	atomic_inc(&intel_crtc->unpin_work_count);
 	intel_crtc->reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
 
@@ -9776,14 +10037,26 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	work->gtt_offset =
 		i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset;
 
-	if (use_mmio_flip(ring, obj))
+	if (use_mmio_flip(ring, obj)) {
 		ret = intel_queue_mmio_flip(dev, crtc, fb, obj, ring,
 					    page_flip_flags);
-	else
+		if (ret)
+			goto cleanup_unpin;
+
+		work->flip_queued_seqno = obj->last_write_seqno;
+		work->flip_queued_ring = obj->ring;
+	} else {
 		ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, ring,
-				page_flip_flags);
-	if (ret)
-		goto cleanup_unpin;
+						   page_flip_flags);
+		if (ret)
+			goto cleanup_unpin;
+
+		work->flip_queued_seqno = intel_ring_get_seqno(ring);
+		work->flip_queued_ring = ring;
+	}
+
+	work->flip_queued_vblank = drm_vblank_count(dev, intel_crtc->pipe);
+	work->enable_stall_check = true;
 
 	i915_gem_track_fb(work->old_fb_obj, obj,
 			  INTEL_FRONTBUFFER_PRIMARY(pipe));
@@ -9818,8 +10091,11 @@ free_work:
 out_hang:
 		intel_crtc_wait_for_pending_flips(crtc);
 		ret = intel_pipe_set_base(crtc, crtc->x, crtc->y, fb);
-		if (ret == 0 && event)
+		if (ret == 0 && event) {
+			spin_lock_irqsave(&dev->event_lock, flags);
 			drm_send_vblank_event(dev, pipe, event);
+			spin_unlock_irqrestore(&dev->event_lock, flags);
+		}
 	}
 	return ret;
 }
@@ -9847,8 +10123,7 @@ static void intel_modeset_update_staged_output_state(struct drm_device *dev)
 			to_intel_encoder(connector->base.encoder);
 	}
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		encoder->new_crtc =
 			to_intel_crtc(encoder->base.crtc);
 	}
@@ -9879,8 +10154,7 @@ static void intel_modeset_commit_output_state(struct drm_device *dev)
 		connector->base.encoder = &connector->new_encoder->base;
 	}
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		encoder->base.crtc = &encoder->new_crtc->base;
 	}
 
@@ -10007,6 +10281,15 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc,
 		      pipe_config->dp_m_n.gmch_m, pipe_config->dp_m_n.gmch_n,
 		      pipe_config->dp_m_n.link_m, pipe_config->dp_m_n.link_n,
 		      pipe_config->dp_m_n.tu);
+
+	DRM_DEBUG_KMS("dp: %i, gmch_m2: %u, gmch_n2: %u, link_m2: %u, link_n2: %u, tu2: %u\n",
+		      pipe_config->has_dp_encoder,
+		      pipe_config->dp_m2_n2.gmch_m,
+		      pipe_config->dp_m2_n2.gmch_n,
+		      pipe_config->dp_m2_n2.link_m,
+		      pipe_config->dp_m2_n2.link_n,
+		      pipe_config->dp_m2_n2.tu);
+
 	DRM_DEBUG_KMS("requested mode:\n");
 	drm_mode_debug_printmodeline(&pipe_config->requested_mode);
 	DRM_DEBUG_KMS("adjusted mode:\n");
@@ -10041,8 +10324,7 @@ static bool check_single_encoder_cloning(struct intel_crtc *crtc,
 	struct drm_device *dev = crtc->base.dev;
 	struct intel_encoder *source_encoder;
 
-	list_for_each_entry(source_encoder,
-			    &dev->mode_config.encoder_list, base.head) {
+	for_each_intel_encoder(dev, source_encoder) {
 		if (source_encoder->new_crtc != crtc)
 			continue;
 
@@ -10058,8 +10340,7 @@ static bool check_encoder_cloning(struct intel_crtc *crtc)
 	struct drm_device *dev = crtc->base.dev;
 	struct intel_encoder *encoder;
 
-	list_for_each_entry(encoder,
-			    &dev->mode_config.encoder_list, base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		if (encoder->new_crtc != crtc)
 			continue;
 
@@ -10143,8 +10424,7 @@ encoder_retry:
 	 * adjust it according to limitations or connector properties, and also
 	 * a chance to reject the mode entirely.
 	 */
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, encoder) {
 
 		if (&encoder->new_crtc->base != crtc)
 			continue;
@@ -10222,8 +10502,7 @@ intel_modeset_affected_pipes(struct drm_crtc *crtc, unsigned *modeset_pipes,
 				1 << connector->new_encoder->new_crtc->pipe;
 	}
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		if (encoder->base.crtc == &encoder->new_crtc->base)
 			continue;
 
@@ -10297,8 +10576,7 @@ intel_modeset_update_state(struct drm_device *dev, unsigned prepare_pipes)
 	struct intel_crtc *intel_crtc;
 	struct drm_connector *connector;
 
-	list_for_each_entry(intel_encoder, &dev->mode_config.encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, intel_encoder) {
 		if (!intel_encoder->base.crtc)
 			continue;
 
@@ -10387,6 +10665,22 @@ intel_pipe_config_compare(struct drm_device *dev,
 		return false; \
 	}
 
+/* This is required for BDW+ where there is only one set of registers for
+ * switching between high and low RR.
+ * This macro can be used whenever a comparison has to be made between one
+ * hw state and multiple sw state variables.
+ */
+#define PIPE_CONF_CHECK_I_ALT(name, alt_name) \
+	if ((current_config->name != pipe_config->name) && \
+		(current_config->alt_name != pipe_config->name)) { \
+			DRM_ERROR("mismatch in " #name " " \
+				  "(expected %i or %i, found %i)\n", \
+				  current_config->name, \
+				  current_config->alt_name, \
+				  pipe_config->name); \
+			return false; \
+	}
+
 #define PIPE_CONF_CHECK_FLAGS(name, mask)	\
 	if ((current_config->name ^ pipe_config->name) & (mask)) { \
 		DRM_ERROR("mismatch in " #name "(" #mask ") "	   \
@@ -10419,11 +10713,28 @@ intel_pipe_config_compare(struct drm_device *dev,
 	PIPE_CONF_CHECK_I(fdi_m_n.tu);
 
 	PIPE_CONF_CHECK_I(has_dp_encoder);
-	PIPE_CONF_CHECK_I(dp_m_n.gmch_m);
-	PIPE_CONF_CHECK_I(dp_m_n.gmch_n);
-	PIPE_CONF_CHECK_I(dp_m_n.link_m);
-	PIPE_CONF_CHECK_I(dp_m_n.link_n);
-	PIPE_CONF_CHECK_I(dp_m_n.tu);
+
+	if (INTEL_INFO(dev)->gen < 8) {
+		PIPE_CONF_CHECK_I(dp_m_n.gmch_m);
+		PIPE_CONF_CHECK_I(dp_m_n.gmch_n);
+		PIPE_CONF_CHECK_I(dp_m_n.link_m);
+		PIPE_CONF_CHECK_I(dp_m_n.link_n);
+		PIPE_CONF_CHECK_I(dp_m_n.tu);
+
+		if (current_config->has_drrs) {
+			PIPE_CONF_CHECK_I(dp_m2_n2.gmch_m);
+			PIPE_CONF_CHECK_I(dp_m2_n2.gmch_n);
+			PIPE_CONF_CHECK_I(dp_m2_n2.link_m);
+			PIPE_CONF_CHECK_I(dp_m2_n2.link_n);
+			PIPE_CONF_CHECK_I(dp_m2_n2.tu);
+		}
+	} else {
+		PIPE_CONF_CHECK_I_ALT(dp_m_n.gmch_m, dp_m2_n2.gmch_m);
+		PIPE_CONF_CHECK_I_ALT(dp_m_n.gmch_n, dp_m2_n2.gmch_n);
+		PIPE_CONF_CHECK_I_ALT(dp_m_n.link_m, dp_m2_n2.link_m);
+		PIPE_CONF_CHECK_I_ALT(dp_m_n.link_n, dp_m2_n2.link_n);
+		PIPE_CONF_CHECK_I_ALT(dp_m_n.tu, dp_m2_n2.tu);
+	}
 
 	PIPE_CONF_CHECK_I(adjusted_mode.crtc_hdisplay);
 	PIPE_CONF_CHECK_I(adjusted_mode.crtc_htotal);
@@ -10509,6 +10820,7 @@ intel_pipe_config_compare(struct drm_device *dev,
 
 #undef PIPE_CONF_CHECK_X
 #undef PIPE_CONF_CHECK_I
+#undef PIPE_CONF_CHECK_I_ALT
 #undef PIPE_CONF_CHECK_FLAGS
 #undef PIPE_CONF_CHECK_CLOCK_FUZZY
 #undef PIPE_CONF_QUIRK
@@ -10538,8 +10850,7 @@ check_encoder_state(struct drm_device *dev)
 	struct intel_encoder *encoder;
 	struct intel_connector *connector;
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		bool enabled = false;
 		bool active = false;
 		enum pipe pipe, tracked_pipe;
@@ -10618,8 +10929,7 @@ check_crtc_state(struct drm_device *dev)
 		WARN(crtc->active && !crtc->base.enabled,
 		     "active crtc, but not enabled in sw tracking\n");
 
-		list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-				    base.head) {
+		for_each_intel_encoder(dev, encoder) {
 			if (encoder->base.crtc != &crtc->base)
 				continue;
 			enabled = true;
@@ -10637,12 +10947,12 @@ check_crtc_state(struct drm_device *dev)
 		active = dev_priv->display.get_pipe_config(crtc,
 							   &pipe_config);
 
-		/* hw state is inconsistent with the pipe A quirk */
-		if (crtc->pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE)
+		/* hw state is inconsistent with the pipe quirk */
+		if ((crtc->pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) ||
+		    (crtc->pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE))
 			active = crtc->active;
 
-		list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-				    base.head) {
+		for_each_intel_encoder(dev, encoder) {
 			enum pipe pipe;
 			if (encoder->base.crtc != &crtc->base)
 				continue;
@@ -11010,7 +11320,7 @@ static void intel_set_config_restore_state(struct drm_device *dev,
 	}
 
 	count = 0;
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		encoder->new_crtc =
 			to_intel_crtc(config->save_encoder_crtcs[count++]);
 	}
@@ -11169,8 +11479,7 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 	}
 
 	/* Check for any encoders that needs to be disabled. */
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		int num_connectors = 0;
 		list_for_each_entry(connector,
 				    &dev->mode_config.connector_list,
@@ -11203,9 +11512,7 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 	for_each_intel_crtc(dev, crtc) {
 		crtc->new_enabled = false;
 
-		list_for_each_entry(encoder,
-				    &dev->mode_config.encoder_list,
-				    base.head) {
+		for_each_intel_encoder(dev, encoder) {
 			if (encoder->new_crtc == crtc) {
 				crtc->new_enabled = true;
 				break;
@@ -11242,7 +11549,7 @@ static void disable_crtc_nofb(struct intel_crtc *crtc)
 			connector->new_encoder = NULL;
 	}
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		if (encoder->new_crtc == crtc)
 			encoder->new_crtc = NULL;
 	}
@@ -11305,7 +11612,6 @@ static int intel_crtc_set_config(struct drm_mode_set *set)
 		ret = intel_set_mode(set->crtc, set->mode,
 				     set->x, set->y, set->fb);
 	} else if (config->fb_changed) {
-		struct drm_i915_private *dev_priv = dev->dev_private;
 		struct intel_crtc *intel_crtc = to_intel_crtc(set->crtc);
 
 		intel_crtc_wait_for_pending_flips(set->crtc);
@@ -11319,8 +11625,7 @@ static int intel_crtc_set_config(struct drm_mode_set *set)
 		 */
 		if (!intel_crtc->primary_enabled && ret == 0) {
 			WARN_ON(!intel_crtc->active);
-			intel_enable_primary_hw_plane(dev_priv, intel_crtc->plane,
-						      intel_crtc->pipe);
+			intel_enable_primary_hw_plane(set->crtc->primary, set->crtc);
 		}
 
 		/*
@@ -11473,8 +11778,6 @@ static int
 intel_primary_plane_disable(struct drm_plane *plane)
 {
 	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct intel_crtc *intel_crtc;
 
 	if (!plane->fb)
@@ -11497,8 +11800,8 @@ intel_primary_plane_disable(struct drm_plane *plane)
 		goto disable_unpin;
 
 	intel_crtc_wait_for_pending_flips(plane->crtc);
-	intel_disable_primary_hw_plane(dev_priv, intel_plane->plane,
-				       intel_plane->pipe);
+	intel_disable_primary_hw_plane(plane, plane->crtc);
+
 disable_unpin:
 	mutex_lock(&dev->struct_mutex);
 	i915_gem_track_fb(intel_fb_obj(plane->fb), NULL,
@@ -11520,7 +11823,6 @@ intel_primary_plane_setplane(struct drm_plane *plane, struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct drm_i915_gem_object *old_obj = intel_fb_obj(plane->fb);
 	struct drm_rect dest = {
@@ -11542,6 +11844,21 @@ intel_primary_plane_setplane(struct drm_plane *plane, struct drm_crtc *crtc,
 		.x2 = intel_crtc->active ? intel_crtc->config.pipe_src_w : 0,
 		.y2 = intel_crtc->active ? intel_crtc->config.pipe_src_h : 0,
 	};
+	const struct {
+		int crtc_x, crtc_y;
+		unsigned int crtc_w, crtc_h;
+		uint32_t src_x, src_y, src_w, src_h;
+	} orig = {
+		.crtc_x = crtc_x,
+		.crtc_y = crtc_y,
+		.crtc_w = crtc_w,
+		.crtc_h = crtc_h,
+		.src_x = src_x,
+		.src_y = src_y,
+		.src_w = src_w,
+		.src_h = src_h,
+	};
+	struct intel_plane *intel_plane = to_intel_plane(plane);
 	bool visible;
 	int ret;
 
@@ -11607,9 +11924,7 @@ intel_primary_plane_setplane(struct drm_plane *plane, struct drm_crtc *crtc,
 				  INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe));
 
 		if (intel_crtc->primary_enabled)
-			intel_disable_primary_hw_plane(dev_priv,
-						       intel_plane->plane,
-						       intel_plane->pipe);
+			intel_disable_primary_hw_plane(plane, crtc);
 
 
 		if (plane->fb != fb)
@@ -11618,16 +11933,42 @@ intel_primary_plane_setplane(struct drm_plane *plane, struct drm_crtc *crtc,
 
 		mutex_unlock(&dev->struct_mutex);
 
-		return 0;
-	}
+	} else {
+		if (intel_crtc && intel_crtc->active &&
+		    intel_crtc->primary_enabled) {
+			/*
+			 * FBC does not work on some platforms for rotated
+			 * planes, so disable it when rotation is not 0 and
+			 * update it when rotation is set back to 0.
+			 *
+			 * FIXME: This is redundant with the fbc update done in
+			 * the primary plane enable function except that that
+			 * one is done too late. We eventually need to unify
+			 * this.
+			 */
+			if (INTEL_INFO(dev)->gen <= 4 && !IS_G4X(dev) &&
+			    dev_priv->fbc.plane == intel_crtc->plane &&
+			    intel_plane->rotation != BIT(DRM_ROTATE_0)) {
+				intel_disable_fbc(dev);
+			}
+		}
+		ret = intel_pipe_set_base(crtc, src.x1, src.y1, fb);
+		if (ret)
+			return ret;
 
-	ret = intel_pipe_set_base(crtc, src.x1, src.y1, fb);
-	if (ret)
-		return ret;
+		if (!intel_crtc->primary_enabled)
+			intel_enable_primary_hw_plane(plane, crtc);
+	}
 
-	if (!intel_crtc->primary_enabled)
-		intel_enable_primary_hw_plane(dev_priv, intel_crtc->plane,
-					      intel_crtc->pipe);
+	intel_plane->crtc_x = orig.crtc_x;
+	intel_plane->crtc_y = orig.crtc_y;
+	intel_plane->crtc_w = orig.crtc_w;
+	intel_plane->crtc_h = orig.crtc_h;
+	intel_plane->src_x = orig.src_x;
+	intel_plane->src_y = orig.src_y;
+	intel_plane->src_w = orig.src_w;
+	intel_plane->src_h = orig.src_h;
+	intel_plane->obj = obj;
 
 	return 0;
 }
@@ -11644,6 +11985,7 @@ static const struct drm_plane_funcs intel_primary_plane_funcs = {
 	.update_plane = intel_primary_plane_setplane,
 	.disable_plane = intel_primary_plane_disable,
 	.destroy = intel_plane_destroy,
+	.set_property = intel_plane_set_property
 };
 
 static struct drm_plane *intel_primary_plane_create(struct drm_device *dev,
@@ -11661,6 +12003,7 @@ static struct drm_plane *intel_primary_plane_create(struct drm_device *dev,
 	primary->max_downscale = 1;
 	primary->pipe = pipe;
 	primary->plane = pipe;
+	primary->rotation = BIT(DRM_ROTATE_0);
 	if (HAS_FBC(dev) && INTEL_INFO(dev)->gen < 4)
 		primary->plane = !pipe;
 
@@ -11676,6 +12019,19 @@ static struct drm_plane *intel_primary_plane_create(struct drm_device *dev,
 				 &intel_primary_plane_funcs,
 				 intel_primary_formats, num_formats,
 				 DRM_PLANE_TYPE_PRIMARY);
+
+	if (INTEL_INFO(dev)->gen >= 4) {
+		if (!dev->mode_config.rotation_property)
+			dev->mode_config.rotation_property =
+				drm_mode_create_rotation_property(dev,
+							BIT(DRM_ROTATE_0) |
+							BIT(DRM_ROTATE_180));
+		if (dev->mode_config.rotation_property)
+			drm_object_attach_property(&primary->base.base,
+				dev->mode_config.rotation_property,
+				primary->rotation);
+	}
+
 	return &primary->base;
 }
 
@@ -11736,6 +12092,10 @@ intel_cursor_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 		return intel_crtc_cursor_set_obj(crtc, obj, crtc_w, crtc_h);
 	} else {
 		intel_crtc_update_cursor(crtc, visible);
+
+		intel_frontbuffer_flip(crtc->dev,
+				       INTEL_FRONTBUFFER_CURSOR(intel_crtc->pipe));
+
 		return 0;
 	}
 }
@@ -11812,8 +12172,7 @@ static void intel_crtc_init(struct drm_device *dev, int pipe)
 
 	intel_crtc->cursor_base = ~0;
 	intel_crtc->cursor_cntl = ~0;
-
-	init_waitqueue_head(&intel_crtc->vbl_wait);
+	intel_crtc->cursor_size = ~0;
 
 	BUG_ON(pipe >= ARRAY_SIZE(dev_priv->plane_to_crtc_mapping) ||
 	       dev_priv->plane_to_crtc_mapping[intel_crtc->plane] != NULL);
@@ -11876,8 +12235,7 @@ static int intel_encoder_clones(struct intel_encoder *encoder)
 	int index_mask = 0;
 	int entry = 0;
 
-	list_for_each_entry(source_encoder,
-			    &dev->mode_config.encoder_list, base.head) {
+	for_each_intel_encoder(dev, source_encoder) {
 		if (encoders_cloneable(encoder, source_encoder))
 			index_mask |= (1 << entry);
 
@@ -12066,7 +12424,7 @@ static void intel_setup_outputs(struct drm_device *dev)
 
 	intel_edp_psr_init(dev);
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		encoder->base.possible_crtcs = encoder->crtc_mask;
 		encoder->base.possible_clones =
 			intel_encoder_clones(encoder);
@@ -12332,29 +12690,27 @@ static void intel_init_display(struct drm_device *dev)
 		dev_priv->display.get_display_clock_speed =
 			i830_get_display_clock_speed;
 
-	if (HAS_PCH_SPLIT(dev)) {
-		if (IS_GEN5(dev)) {
-			dev_priv->display.fdi_link_train = ironlake_fdi_link_train;
-			dev_priv->display.write_eld = ironlake_write_eld;
-		} else if (IS_GEN6(dev)) {
-			dev_priv->display.fdi_link_train = gen6_fdi_link_train;
-			dev_priv->display.write_eld = ironlake_write_eld;
-			dev_priv->display.modeset_global_resources =
-				snb_modeset_global_resources;
-		} else if (IS_IVYBRIDGE(dev)) {
-			/* FIXME: detect B0+ stepping and use auto training */
-			dev_priv->display.fdi_link_train = ivb_manual_fdi_link_train;
-			dev_priv->display.write_eld = ironlake_write_eld;
-			dev_priv->display.modeset_global_resources =
-				ivb_modeset_global_resources;
-		} else if (IS_HASWELL(dev) || IS_GEN8(dev)) {
-			dev_priv->display.fdi_link_train = hsw_fdi_link_train;
-			dev_priv->display.write_eld = haswell_write_eld;
-			dev_priv->display.modeset_global_resources =
-				haswell_modeset_global_resources;
-		}
-	} else if (IS_G4X(dev)) {
+	if (IS_G4X(dev)) {
 		dev_priv->display.write_eld = g4x_write_eld;
+	} else if (IS_GEN5(dev)) {
+		dev_priv->display.fdi_link_train = ironlake_fdi_link_train;
+		dev_priv->display.write_eld = ironlake_write_eld;
+	} else if (IS_GEN6(dev)) {
+		dev_priv->display.fdi_link_train = gen6_fdi_link_train;
+		dev_priv->display.write_eld = ironlake_write_eld;
+		dev_priv->display.modeset_global_resources =
+			snb_modeset_global_resources;
+	} else if (IS_IVYBRIDGE(dev)) {
+		/* FIXME: detect B0+ stepping and use auto training */
+		dev_priv->display.fdi_link_train = ivb_manual_fdi_link_train;
+		dev_priv->display.write_eld = ironlake_write_eld;
+		dev_priv->display.modeset_global_resources =
+			ivb_modeset_global_resources;
+	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
+		dev_priv->display.fdi_link_train = hsw_fdi_link_train;
+		dev_priv->display.write_eld = haswell_write_eld;
+		dev_priv->display.modeset_global_resources =
+			haswell_modeset_global_resources;
 	} else if (IS_VALLEYVIEW(dev)) {
 		dev_priv->display.modeset_global_resources =
 			valleyview_modeset_global_resources;
@@ -12388,6 +12744,8 @@ static void intel_init_display(struct drm_device *dev)
 	}
 
 	intel_panel_init_backlight_funcs(dev);
+
+	mutex_init(&dev_priv->pps_mutex);
 }
 
 /*
@@ -12403,6 +12761,14 @@ static void quirk_pipea_force(struct drm_device *dev)
 	DRM_INFO("applying pipe a force quirk\n");
 }
 
+static void quirk_pipeb_force(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	dev_priv->quirks |= QUIRK_PIPEB_FORCE;
+	DRM_INFO("applying pipe b force quirk\n");
+}
+
 /*
  * Some machines (Lenovo U160) do not work with SSC on LVDS for some reason
  */
@@ -12477,6 +12843,12 @@ static struct intel_quirk intel_quirks[] = {
 	/* ThinkPad T60 needs pipe A force quirk (bug #16494) */
 	{ 0x2782, 0x17aa, 0x201a, quirk_pipea_force },
 
+	/* 830 needs to leave pipe A & dpll A up */
+	{ 0x3577, PCI_ANY_ID, PCI_ANY_ID, quirk_pipea_force },
+
+	/* 830 needs to leave pipe B & dpll B up */
+	{ 0x3577, PCI_ANY_ID, PCI_ANY_ID, quirk_pipeb_force },
+
 	/* Lenovo U160 cannot use SSC on LVDS */
 	{ 0x0046, 0x17aa, 0x3920, quirk_ssc_force_disable },
 
@@ -12550,7 +12922,11 @@ static void i915_disable_vga(struct drm_device *dev)
 	vga_put(dev->pdev, VGA_RSRC_LEGACY_IO);
 	udelay(300);
 
-	I915_WRITE(vga_reg, VGA_DISP_DISABLE);
+	/*
+	 * Fujitsu-Siemens Lifebook S6010 (830) has problems resuming
+	 * from S3 without preserving (some of?) the other bits.
+	 */
+	I915_WRITE(vga_reg, dev_priv->bios_vgacntr | VGA_DISP_DISABLE);
 	POSTING_READ(vga_reg);
 }
 
@@ -12563,8 +12939,6 @@ void intel_modeset_init_hw(struct drm_device *dev)
 
 	intel_init_clock_gating(dev);
 
-	intel_reset_dpio(dev);
-
 	intel_enable_gt_powersave(dev);
 }
 
@@ -12610,7 +12984,10 @@ void intel_modeset_init(struct drm_device *dev)
 		dev->mode_config.max_height = 8192;
 	}
 
-	if (IS_GEN2(dev)) {
+	if (IS_845G(dev) || IS_I865G(dev)) {
+		dev->mode_config.cursor_width = IS_845G(dev) ? 64 : 512;
+		dev->mode_config.cursor_height = 1023;
+	} else if (IS_GEN2(dev)) {
 		dev->mode_config.cursor_width = GEN2_CURSOR_WIDTH;
 		dev->mode_config.cursor_height = GEN2_CURSOR_HEIGHT;
 	} else {
@@ -12624,7 +13001,7 @@ void intel_modeset_init(struct drm_device *dev)
 		      INTEL_INFO(dev)->num_pipes,
 		      INTEL_INFO(dev)->num_pipes > 1 ? "s" : "");
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		intel_crtc_init(dev, pipe);
 		for_each_sprite(pipe, sprite) {
 			ret = intel_plane_init(dev, pipe, sprite);
@@ -12635,10 +13012,11 @@ void intel_modeset_init(struct drm_device *dev)
 	}
 
 	intel_init_dpio(dev);
-	intel_reset_dpio(dev);
 
 	intel_shared_dpll_init(dev);
 
+	/* save the BIOS value before clobbering it */
+	dev_priv->bios_vgacntr = I915_READ(i915_vgacntrl_reg(dev));
 	/* Just disable it once at startup */
 	i915_disable_vga(dev);
 	intel_setup_outputs(dev);
@@ -12730,9 +13108,10 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 	I915_WRITE(reg, I915_READ(reg) & ~PIPECONF_FRAME_START_DELAY_MASK);
 
 	/* restore vblank interrupts to correct state */
-	if (crtc->active)
+	if (crtc->active) {
+		update_scanline_offset(crtc);
 		drm_vblank_on(dev, crtc->pipe);
-	else
+	} else
 		drm_vblank_off(dev, crtc->pipe);
 
 	/* We need to sanitize the plane -> pipe mapping first because this will
@@ -12815,7 +13194,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 		}
 	}
 
-	if (crtc->active || IS_VALLEYVIEW(dev) || INTEL_INFO(dev)->gen < 5) {
+	if (crtc->active || HAS_GMCH_DISPLAY(dev)) {
 		/*
 		 * We start out with underrun reporting disabled to avoid races.
 		 * For correct bookkeeping mark this on active crtcs.
@@ -12831,8 +13210,6 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 		 */
 		crtc->cpu_fifo_underrun_disabled = true;
 		crtc->pch_fifo_underrun_disabled = true;
-
-		update_scanline_offset(crtc);
 	}
 }
 
@@ -12964,8 +13341,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			intel_display_power_get(dev_priv, POWER_DOMAIN_PLLS);
 	}
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		pipe = 0;
 
 		if (encoder->get_hw_state(encoder, &pipe)) {
@@ -13029,12 +13405,11 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 	}
 
 	/* HW state is read out, now we need to sanitize this mess. */
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		intel_sanitize_encoder(encoder);
 	}
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
 		intel_sanitize_crtc(crtc);
 		intel_dump_pipe_config(crtc, &crtc->config, "[setup_hw_state]");
@@ -13062,7 +13437,7 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 		 * We need to use raw interfaces for restoring state to avoid
 		 * checking (bogus) intermediate states.
 		 */
-		for_each_pipe(pipe) {
+		for_each_pipe(dev_priv, pipe) {
 			struct drm_crtc *crtc =
 				dev_priv->pipe_to_crtc_mapping[pipe];
 
@@ -13283,7 +13658,7 @@ intel_display_capture_error_state(struct drm_device *dev)
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		error->power_well_driver = I915_READ(HSW_PWR_WELL_DRIVER);
 
-	for_each_pipe(i) {
+	for_each_pipe(dev_priv, i) {
 		error->pipe[i].power_domain_on =
 			intel_display_power_enabled_unlocked(dev_priv,
 							   POWER_DOMAIN_PIPE(i));
@@ -13347,6 +13722,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 				struct drm_device *dev,
 				struct intel_display_error_state *error)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
 
 	if (!error)
@@ -13356,7 +13732,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		err_printf(m, "PWR_WELL_CTL2: %08x\n",
 			   error->power_well_driver);
-	for_each_pipe(i) {
+	for_each_pipe(dev_priv, i) {
 		err_printf(m, "Pipe [%d]:\n", i);
 		err_printf(m, "  Power: %s\n",
 			   error->pipe[i].power_domain_on ? "on" : "off");
@@ -13397,3 +13773,25 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 		err_printf(m, "  VSYNC: %08x\n", error->transcoder[i].vsync);
 	}
 }
+
+void intel_modeset_preclose(struct drm_device *dev, struct drm_file *file)
+{
+	struct intel_crtc *crtc;
+
+	for_each_intel_crtc(dev, crtc) {
+		struct intel_unpin_work *work;
+		unsigned long irqflags;
+
+		spin_lock_irqsave(&dev->event_lock, irqflags);
+
+		work = crtc->unpin_work;
+
+		if (work && work->event &&
+		    work->event->base.file_priv == file) {
+			kfree(work->event);
+			work->event = NULL;
+		}
+
+		spin_unlock_irqrestore(&dev->event_lock, irqflags);
+	}
+}
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index fdff1d420c14..f6a3fdd5589e 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -111,7 +111,7 @@ static struct intel_dp *intel_attached_dp(struct drm_connector *connector)
 }
 
 static void intel_dp_link_down(struct intel_dp *intel_dp);
-static bool _edp_panel_vdd_on(struct intel_dp *intel_dp);
+static bool edp_panel_vdd_on(struct intel_dp *intel_dp);
 static void edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync);
 
 int
@@ -290,32 +290,201 @@ intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
 					      struct intel_dp *intel_dp,
 					      struct edp_power_seq *out);
 
+static void pps_lock(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct intel_encoder *encoder = &intel_dig_port->base;
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_display_power_domain power_domain;
+
+	/*
+	 * See vlv_power_sequencer_reset() why we need
+	 * a power domain reference here.
+	 */
+	power_domain = intel_display_port_power_domain(encoder);
+	intel_display_power_get(dev_priv, power_domain);
+
+	mutex_lock(&dev_priv->pps_mutex);
+}
+
+static void pps_unlock(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct intel_encoder *encoder = &intel_dig_port->base;
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_display_power_domain power_domain;
+
+	mutex_unlock(&dev_priv->pps_mutex);
+
+	power_domain = intel_display_port_power_domain(encoder);
+	intel_display_power_put(dev_priv, power_domain);
+}
+
 static enum pipe
 vlv_power_sequencer_pipe(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_crtc *crtc = intel_dig_port->base.base.crtc;
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	enum port port = intel_dig_port->port;
-	enum pipe pipe;
+	struct intel_encoder *encoder;
+	unsigned int pipes = (1 << PIPE_A) | (1 << PIPE_B);
+	struct edp_power_seq power_seq;
+
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
+	if (intel_dp->pps_pipe != INVALID_PIPE)
+		return intel_dp->pps_pipe;
+
+	/*
+	 * We don't have power sequencer currently.
+	 * Pick one that's not used by other ports.
+	 */
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
+			    base.head) {
+		struct intel_dp *tmp;
+
+		if (encoder->type != INTEL_OUTPUT_EDP)
+			continue;
+
+		tmp = enc_to_intel_dp(&encoder->base);
+
+		if (tmp->pps_pipe != INVALID_PIPE)
+			pipes &= ~(1 << tmp->pps_pipe);
+	}
+
+	/*
+	 * Didn't find one. This should not happen since there
+	 * are two power sequencers and up to two eDP ports.
+	 */
+	if (WARN_ON(pipes == 0))
+		return PIPE_A;
+
+	intel_dp->pps_pipe = ffs(pipes) - 1;
+
+	DRM_DEBUG_KMS("picked pipe %c power sequencer for port %c\n",
+		      pipe_name(intel_dp->pps_pipe),
+		      port_name(intel_dig_port->port));
 
-	/* modeset should have pipe */
-	if (crtc)
-		return to_intel_crtc(crtc)->pipe;
+	/* init power sequencer on this pipe and port */
+	intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
+	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
+						      &power_seq);
+
+	return intel_dp->pps_pipe;
+}
+
+typedef bool (*vlv_pipe_check)(struct drm_i915_private *dev_priv,
+			       enum pipe pipe);
+
+static bool vlv_pipe_has_pp_on(struct drm_i915_private *dev_priv,
+			       enum pipe pipe)
+{
+	return I915_READ(VLV_PIPE_PP_STATUS(pipe)) & PP_ON;
+}
+
+static bool vlv_pipe_has_vdd_on(struct drm_i915_private *dev_priv,
+				enum pipe pipe)
+{
+	return I915_READ(VLV_PIPE_PP_CONTROL(pipe)) & EDP_FORCE_VDD;
+}
+
+static bool vlv_pipe_any(struct drm_i915_private *dev_priv,
+			 enum pipe pipe)
+{
+	return true;
+}
+
+static enum pipe
+vlv_initial_pps_pipe(struct drm_i915_private *dev_priv,
+		     enum port port,
+		     vlv_pipe_check pipe_check)
+{
+	enum pipe pipe;
 
-	/* init time, try to find a pipe with this port selected */
 	for (pipe = PIPE_A; pipe <= PIPE_B; pipe++) {
 		u32 port_sel = I915_READ(VLV_PIPE_PP_ON_DELAYS(pipe)) &
 			PANEL_PORT_SELECT_MASK;
-		if (port_sel == PANEL_PORT_SELECT_DPB_VLV && port == PORT_B)
-			return pipe;
-		if (port_sel == PANEL_PORT_SELECT_DPC_VLV && port == PORT_C)
-			return pipe;
+
+		if (port_sel != PANEL_PORT_SELECT_VLV(port))
+			continue;
+
+		if (!pipe_check(dev_priv, pipe))
+			continue;
+
+		return pipe;
+	}
+
+	return INVALID_PIPE;
+}
+
+static void
+vlv_initial_power_sequencer_setup(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct edp_power_seq power_seq;
+	enum port port = intel_dig_port->port;
+
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
+	/* try to find a pipe with this port selected */
+	/* first pick one where the panel is on */
+	intel_dp->pps_pipe = vlv_initial_pps_pipe(dev_priv, port,
+						  vlv_pipe_has_pp_on);
+	/* didn't find one? pick one where vdd is on */
+	if (intel_dp->pps_pipe == INVALID_PIPE)
+		intel_dp->pps_pipe = vlv_initial_pps_pipe(dev_priv, port,
+							  vlv_pipe_has_vdd_on);
+	/* didn't find one? pick one with just the correct port */
+	if (intel_dp->pps_pipe == INVALID_PIPE)
+		intel_dp->pps_pipe = vlv_initial_pps_pipe(dev_priv, port,
+							  vlv_pipe_any);
+
+	/* didn't find one? just let vlv_power_sequencer_pipe() pick one when needed */
+	if (intel_dp->pps_pipe == INVALID_PIPE) {
+		DRM_DEBUG_KMS("no initial power sequencer for port %c\n",
+			      port_name(port));
+		return;
 	}
 
-	/* shrug */
-	return PIPE_A;
+	DRM_DEBUG_KMS("initial power sequencer for port %c: pipe %c\n",
+		      port_name(port), pipe_name(intel_dp->pps_pipe));
+
+	intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
+	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
+						      &power_seq);
+}
+
+void vlv_power_sequencer_reset(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct intel_encoder *encoder;
+
+	if (WARN_ON(!IS_VALLEYVIEW(dev)))
+		return;
+
+	/*
+	 * We can't grab pps_mutex here due to deadlock with power_domain
+	 * mutex when power_domain functions are called while holding pps_mutex.
+	 * That also means that in order to use pps_pipe the code needs to
+	 * hold both a power domain reference and pps_mutex, and the power domain
+	 * reference get/put must be done while _not_ holding pps_mutex.
+	 * pps_{lock,unlock}() do these steps in the correct order, so one
+	 * should use them always.
+	 */
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.head) {
+		struct intel_dp *intel_dp;
+
+		if (encoder->type != INTEL_OUTPUT_EDP)
+			continue;
+
+		intel_dp = enc_to_intel_dp(&encoder->base);
+		intel_dp->pps_pipe = INVALID_PIPE;
+	}
 }
 
 static u32 _pp_ctrl_reg(struct intel_dp *intel_dp)
@@ -349,12 +518,15 @@ static int edp_notify_handler(struct notifier_block *this, unsigned long code,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 pp_div;
 	u32 pp_ctrl_reg, pp_div_reg;
-	enum pipe pipe = vlv_power_sequencer_pipe(intel_dp);
 
 	if (!is_edp(intel_dp) || code != SYS_RESTART)
 		return 0;
 
+	pps_lock(intel_dp);
+
 	if (IS_VALLEYVIEW(dev)) {
+		enum pipe pipe = vlv_power_sequencer_pipe(intel_dp);
+
 		pp_ctrl_reg = VLV_PIPE_PP_CONTROL(pipe);
 		pp_div_reg  = VLV_PIPE_PP_DIVISOR(pipe);
 		pp_div = I915_READ(pp_div_reg);
@@ -366,6 +538,8 @@ static int edp_notify_handler(struct notifier_block *this, unsigned long code,
 		msleep(intel_dp->panel_power_cycle_delay);
 	}
 
+	pps_unlock(intel_dp);
+
 	return 0;
 }
 
@@ -374,6 +548,8 @@ static bool edp_have_panel_power(struct intel_dp *intel_dp)
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
 	return (I915_READ(_pp_stat_reg(intel_dp)) & PP_ON) != 0;
 }
 
@@ -381,13 +557,10 @@ static bool edp_have_panel_vdd(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct intel_encoder *intel_encoder = &intel_dig_port->base;
-	enum intel_display_power_domain power_domain;
 
-	power_domain = intel_display_port_power_domain(intel_encoder);
-	return intel_display_power_enabled(dev_priv, power_domain) &&
-	       (I915_READ(_pp_ctrl_reg(intel_dp)) & EDP_FORCE_VDD) != 0;
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
+	return I915_READ(_pp_ctrl_reg(intel_dp)) & EDP_FORCE_VDD;
 }
 
 static void
@@ -535,7 +708,15 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 	bool has_aux_irq = HAS_AUX_IRQ(dev);
 	bool vdd;
 
-	vdd = _edp_panel_vdd_on(intel_dp);
+	pps_lock(intel_dp);
+
+	/*
+	 * We will be called with VDD already enabled for dpcd/edid/oui reads.
+	 * In such cases we want to leave VDD enabled and it's up to upper layers
+	 * to turn it off. But for eg. i2c-dev access we need to turn it on/off
+	 * ourselves.
+	 */
+	vdd = edp_panel_vdd_on(intel_dp);
 
 	/* dp aux is extremely sensitive to irq latency, hence request the
 	 * lowest possible wakeup latency and so prevent the cpu from going into
@@ -644,6 +825,8 @@ out:
 	if (vdd)
 		edp_panel_vdd_off(intel_dp, false);
 
+	pps_unlock(intel_dp);
+
 	return ret;
 }
 
@@ -828,20 +1011,6 @@ intel_dp_set_clock(struct intel_encoder *encoder,
 	}
 }
 
-static void
-intel_dp_set_m2_n2(struct intel_crtc *crtc, struct intel_link_m_n *m_n)
-{
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	enum transcoder transcoder = crtc->config.cpu_transcoder;
-
-	I915_WRITE(PIPE_DATA_M2(transcoder),
-		TU_SIZE(m_n->tu) | m_n->gmch_m);
-	I915_WRITE(PIPE_DATA_N2(transcoder), m_n->gmch_n);
-	I915_WRITE(PIPE_LINK_M2(transcoder), m_n->link_m);
-	I915_WRITE(PIPE_LINK_N2(transcoder), m_n->link_n);
-}
-
 bool
 intel_dp_compute_config(struct intel_encoder *encoder,
 			struct intel_crtc_config *pipe_config)
@@ -867,6 +1036,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 		pipe_config->has_pch_encoder = true;
 
 	pipe_config->has_dp_encoder = true;
+	pipe_config->has_drrs = false;
 	pipe_config->has_audio = intel_dp->has_audio;
 
 	if (is_edp(intel_dp) && intel_connector->panel.fixed_mode) {
@@ -898,23 +1068,15 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 			bpp = dev_priv->vbt.edp_bpp;
 		}
 
-		if (IS_BROADWELL(dev)) {
-			/* Yes, it's an ugly hack. */
-			min_lane_count = max_lane_count;
-			DRM_DEBUG_KMS("forcing lane count to max (%u) on BDW\n",
-				      min_lane_count);
-		} else if (dev_priv->vbt.edp_lanes) {
-			min_lane_count = min(dev_priv->vbt.edp_lanes,
-					     max_lane_count);
-			DRM_DEBUG_KMS("using min %u lanes per VBT\n",
-				      min_lane_count);
-		}
-
-		if (dev_priv->vbt.edp_rate) {
-			min_clock = min(dev_priv->vbt.edp_rate >> 3, max_clock);
-			DRM_DEBUG_KMS("using min %02x link bw per VBT\n",
-				      bws[min_clock]);
-		}
+		/*
+		 * Use the maximum clock and number of lanes the eDP panel
+		 * advertizes being capable of. The panels are generally
+		 * designed to support only a single clock and lane
+		 * configuration, and typically these values correspond to the
+		 * native resolution of the panel.
+		 */
+		min_lane_count = max_lane_count;
+		min_clock = max_clock;
 	}
 
 	for (; bpp >= 6*3; bpp -= 2*3) {
@@ -970,13 +1132,14 @@ found:
 
 	if (intel_connector->panel.downclock_mode != NULL &&
 		intel_dp->drrs_state.type == SEAMLESS_DRRS_SUPPORT) {
+			pipe_config->has_drrs = true;
 			intel_link_compute_m_n(bpp, lane_count,
 				intel_connector->panel.downclock_mode->clock,
 				pipe_config->port_clock,
 				&pipe_config->dp_m2_n2);
 	}
 
-	if (HAS_DDI(dev))
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		hsw_dp_set_ddi_pll_sel(pipe_config, intel_dp->link_bw);
 	else
 		intel_dp_set_clock(encoder, pipe_config, intel_dp->link_bw);
@@ -1110,6 +1273,8 @@ static void wait_panel_status(struct intel_dp *intel_dp,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 pp_stat_reg, pp_ctrl_reg;
 
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
 	pp_stat_reg = _pp_stat_reg(intel_dp);
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
 
@@ -1173,13 +1338,20 @@ static  u32 ironlake_get_pp_control(struct intel_dp *intel_dp)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 control;
 
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
 	control = I915_READ(_pp_ctrl_reg(intel_dp));
 	control &= ~PANEL_UNLOCK_MASK;
 	control |= PANEL_UNLOCK_REGS;
 	return control;
 }
 
-static bool _edp_panel_vdd_on(struct intel_dp *intel_dp)
+/*
+ * Must be paired with edp_panel_vdd_off().
+ * Must hold pps_mutex around the whole on/off sequence.
+ * Can be nested with intel_edp_panel_vdd_{on,off}() calls.
+ */
+static bool edp_panel_vdd_on(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
@@ -1190,6 +1362,8 @@ static bool _edp_panel_vdd_on(struct intel_dp *intel_dp)
 	u32 pp_stat_reg, pp_ctrl_reg;
 	bool need_to_disable = !intel_dp->want_panel_vdd;
 
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
 	if (!is_edp(intel_dp))
 		return false;
 
@@ -1227,62 +1401,76 @@ static bool _edp_panel_vdd_on(struct intel_dp *intel_dp)
 	return need_to_disable;
 }
 
+/*
+ * Must be paired with intel_edp_panel_vdd_off() or
+ * intel_edp_panel_off().
+ * Nested calls to these functions are not allowed since
+ * we drop the lock. Caller must use some higher level
+ * locking to prevent nested calls from other threads.
+ */
 void intel_edp_panel_vdd_on(struct intel_dp *intel_dp)
 {
-	if (is_edp(intel_dp)) {
-		bool vdd = _edp_panel_vdd_on(intel_dp);
+	bool vdd;
 
-		WARN(!vdd, "eDP VDD already requested on\n");
-	}
+	if (!is_edp(intel_dp))
+		return;
+
+	pps_lock(intel_dp);
+	vdd = edp_panel_vdd_on(intel_dp);
+	pps_unlock(intel_dp);
+
+	WARN(!vdd, "eDP VDD already requested on\n");
 }
 
 static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_digital_port *intel_dig_port =
+		dp_to_dig_port(intel_dp);
+	struct intel_encoder *intel_encoder = &intel_dig_port->base;
+	enum intel_display_power_domain power_domain;
 	u32 pp;
 	u32 pp_stat_reg, pp_ctrl_reg;
 
-	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+	lockdep_assert_held(&dev_priv->pps_mutex);
 
-	if (!intel_dp->want_panel_vdd && edp_have_panel_vdd(intel_dp)) {
-		struct intel_digital_port *intel_dig_port =
-						dp_to_dig_port(intel_dp);
-		struct intel_encoder *intel_encoder = &intel_dig_port->base;
-		enum intel_display_power_domain power_domain;
+	WARN_ON(intel_dp->want_panel_vdd);
+
+	if (!edp_have_panel_vdd(intel_dp))
+		return;
 
-		DRM_DEBUG_KMS("Turning eDP VDD off\n");
+	DRM_DEBUG_KMS("Turning eDP VDD off\n");
 
-		pp = ironlake_get_pp_control(intel_dp);
-		pp &= ~EDP_FORCE_VDD;
+	pp = ironlake_get_pp_control(intel_dp);
+	pp &= ~EDP_FORCE_VDD;
 
-		pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
-		pp_stat_reg = _pp_stat_reg(intel_dp);
+	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
+	pp_stat_reg = _pp_stat_reg(intel_dp);
 
-		I915_WRITE(pp_ctrl_reg, pp);
-		POSTING_READ(pp_ctrl_reg);
+	I915_WRITE(pp_ctrl_reg, pp);
+	POSTING_READ(pp_ctrl_reg);
 
-		/* Make sure sequencer is idle before allowing subsequent activity */
-		DRM_DEBUG_KMS("PP_STATUS: 0x%08x PP_CONTROL: 0x%08x\n",
-		I915_READ(pp_stat_reg), I915_READ(pp_ctrl_reg));
+	/* Make sure sequencer is idle before allowing subsequent activity */
+	DRM_DEBUG_KMS("PP_STATUS: 0x%08x PP_CONTROL: 0x%08x\n",
+	I915_READ(pp_stat_reg), I915_READ(pp_ctrl_reg));
 
-		if ((pp & POWER_TARGET_ON) == 0)
-			intel_dp->last_power_cycle = jiffies;
+	if ((pp & POWER_TARGET_ON) == 0)
+		intel_dp->last_power_cycle = jiffies;
 
-		power_domain = intel_display_port_power_domain(intel_encoder);
-		intel_display_power_put(dev_priv, power_domain);
-	}
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	intel_display_power_put(dev_priv, power_domain);
 }
 
 static void edp_panel_vdd_work(struct work_struct *__work)
 {
 	struct intel_dp *intel_dp = container_of(to_delayed_work(__work),
 						 struct intel_dp, panel_vdd_work);
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 
-	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
-	edp_panel_vdd_off_sync(intel_dp);
-	drm_modeset_unlock(&dev->mode_config.connection_mutex);
+	pps_lock(intel_dp);
+	if (!intel_dp->want_panel_vdd)
+		edp_panel_vdd_off_sync(intel_dp);
+	pps_unlock(intel_dp);
 }
 
 static void edp_panel_vdd_schedule_off(struct intel_dp *intel_dp)
@@ -1298,8 +1486,18 @@ static void edp_panel_vdd_schedule_off(struct intel_dp *intel_dp)
 	schedule_delayed_work(&intel_dp->panel_vdd_work, delay);
 }
 
+/*
+ * Must be paired with edp_panel_vdd_on().
+ * Must hold pps_mutex around the whole on/off sequence.
+ * Can be nested with intel_edp_panel_vdd_{on,off}() calls.
+ */
 static void edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
 {
+	struct drm_i915_private *dev_priv =
+		intel_dp_to_dev(intel_dp)->dev_private;
+
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
 	if (!is_edp(intel_dp))
 		return;
 
@@ -1313,6 +1511,22 @@ static void edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
 		edp_panel_vdd_schedule_off(intel_dp);
 }
 
+/*
+ * Must be paired with intel_edp_panel_vdd_on().
+ * Nested calls to these functions are not allowed since
+ * we drop the lock. Caller must use some higher level
+ * locking to prevent nested calls from other threads.
+ */
+static void intel_edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
+{
+	if (!is_edp(intel_dp))
+		return;
+
+	pps_lock(intel_dp);
+	edp_panel_vdd_off(intel_dp, sync);
+	pps_unlock(intel_dp);
+}
+
 void intel_edp_panel_on(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
@@ -1325,9 +1539,11 @@ void intel_edp_panel_on(struct intel_dp *intel_dp)
 
 	DRM_DEBUG_KMS("Turn eDP power on\n");
 
+	pps_lock(intel_dp);
+
 	if (edp_have_panel_power(intel_dp)) {
 		DRM_DEBUG_KMS("eDP power already on\n");
-		return;
+		goto out;
 	}
 
 	wait_panel_power_cycle(intel_dp);
@@ -1356,6 +1572,9 @@ void intel_edp_panel_on(struct intel_dp *intel_dp)
 		I915_WRITE(pp_ctrl_reg, pp);
 		POSTING_READ(pp_ctrl_reg);
 	}
+
+ out:
+	pps_unlock(intel_dp);
 }
 
 void intel_edp_panel_off(struct intel_dp *intel_dp)
@@ -1373,6 +1592,8 @@ void intel_edp_panel_off(struct intel_dp *intel_dp)
 
 	DRM_DEBUG_KMS("Turn eDP power off\n");
 
+	pps_lock(intel_dp);
+
 	WARN(!intel_dp->want_panel_vdd, "Need VDD to turn off panel\n");
 
 	pp = ironlake_get_pp_control(intel_dp);
@@ -1394,9 +1615,12 @@ void intel_edp_panel_off(struct intel_dp *intel_dp)
 	/* We got a reference when we enabled the VDD. */
 	power_domain = intel_display_port_power_domain(intel_encoder);
 	intel_display_power_put(dev_priv, power_domain);
+
+	pps_unlock(intel_dp);
 }
 
-void intel_edp_backlight_on(struct intel_dp *intel_dp)
+/* Enable backlight in the panel power control. */
+static void _intel_edp_backlight_on(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
@@ -1404,13 +1628,6 @@ void intel_edp_backlight_on(struct intel_dp *intel_dp)
 	u32 pp;
 	u32 pp_ctrl_reg;
 
-	if (!is_edp(intel_dp))
-		return;
-
-	DRM_DEBUG_KMS("\n");
-
-	intel_panel_enable_backlight(intel_dp->attached_connector);
-
 	/*
 	 * If we enable the backlight right away following a panel power
 	 * on, we may see slight flicker as the panel syncs with the eDP
@@ -1418,6 +1635,9 @@ void intel_edp_backlight_on(struct intel_dp *intel_dp)
 	 * allowing it to appear.
 	 */
 	wait_backlight_on(intel_dp);
+
+	pps_lock(intel_dp);
+
 	pp = ironlake_get_pp_control(intel_dp);
 	pp |= EDP_BLC_ENABLE;
 
@@ -1425,9 +1645,24 @@ void intel_edp_backlight_on(struct intel_dp *intel_dp)
 
 	I915_WRITE(pp_ctrl_reg, pp);
 	POSTING_READ(pp_ctrl_reg);
+
+	pps_unlock(intel_dp);
 }
 
-void intel_edp_backlight_off(struct intel_dp *intel_dp)
+/* Enable backlight PWM and backlight PP control. */
+void intel_edp_backlight_on(struct intel_dp *intel_dp)
+{
+	if (!is_edp(intel_dp))
+		return;
+
+	DRM_DEBUG_KMS("\n");
+
+	intel_panel_enable_backlight(intel_dp->attached_connector);
+	_intel_edp_backlight_on(intel_dp);
+}
+
+/* Disable backlight in the panel power control. */
+static void _intel_edp_backlight_off(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1437,7 +1672,8 @@ void intel_edp_backlight_off(struct intel_dp *intel_dp)
 	if (!is_edp(intel_dp))
 		return;
 
-	DRM_DEBUG_KMS("\n");
+	pps_lock(intel_dp);
+
 	pp = ironlake_get_pp_control(intel_dp);
 	pp &= ~EDP_BLC_ENABLE;
 
@@ -1445,13 +1681,51 @@ void intel_edp_backlight_off(struct intel_dp *intel_dp)
 
 	I915_WRITE(pp_ctrl_reg, pp);
 	POSTING_READ(pp_ctrl_reg);
-	intel_dp->last_backlight_off = jiffies;
 
+	pps_unlock(intel_dp);
+
+	intel_dp->last_backlight_off = jiffies;
 	edp_wait_backlight_off(intel_dp);
+}
+
+/* Disable backlight PP control and backlight PWM. */
+void intel_edp_backlight_off(struct intel_dp *intel_dp)
+{
+	if (!is_edp(intel_dp))
+		return;
+
+	DRM_DEBUG_KMS("\n");
 
+	_intel_edp_backlight_off(intel_dp);
 	intel_panel_disable_backlight(intel_dp->attached_connector);
 }
 
+/*
+ * Hook for controlling the panel power control backlight through the bl_power
+ * sysfs attribute. Take care to handle multiple calls.
+ */
+static void intel_edp_backlight_power(struct intel_connector *connector,
+				      bool enable)
+{
+	struct intel_dp *intel_dp = intel_attached_dp(&connector->base);
+	bool is_enabled;
+
+	pps_lock(intel_dp);
+	is_enabled = ironlake_get_pp_control(intel_dp) & EDP_BLC_ENABLE;
+	pps_unlock(intel_dp);
+
+	if (is_enabled == enable)
+		return;
+
+	DRM_DEBUG_KMS("panel power control backlight %s\n",
+		      enable ? "enable" : "disable");
+
+	if (enable)
+		_intel_edp_backlight_on(intel_dp);
+	else
+		_intel_edp_backlight_off(intel_dp);
+}
+
 static void ironlake_edp_pll_on(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
@@ -1515,8 +1789,6 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode)
 	if (mode != DRM_MODE_DPMS_ON) {
 		ret = drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER,
 					 DP_SET_POWER_D3);
-		if (ret != 1)
-			DRM_DEBUG_DRIVER("failed to write sink power state\n");
 	} else {
 		/*
 		 * When turning on, we need to retry for 1ms to give the sink
@@ -1530,6 +1802,10 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode)
 			msleep(1);
 		}
 	}
+
+	if (ret != 1)
+		DRM_DEBUG_KMS("failed to %s sink power state\n",
+			      mode == DRM_MODE_DPMS_ON ? "enable" : "disable");
 }
 
 static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
@@ -1576,7 +1852,7 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 			return true;
 		}
 
-		for_each_pipe(i) {
+		for_each_pipe(dev_priv, i) {
 			trans_dp = I915_READ(TRANS_DP_CTL(i));
 			if ((trans_dp & TRANS_DP_PORT_SEL_MASK) == trans_sel) {
 				*pipe = i;
@@ -2036,7 +2312,6 @@ void intel_edp_psr_init(struct drm_device *dev)
 static void intel_disable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	enum port port = dp_to_dig_port(intel_dp)->port;
 	struct drm_device *dev = encoder->base.dev;
 
 	/* Make sure the panel is off before trying to change the mode. But also
@@ -2046,21 +2321,19 @@ static void intel_disable_dp(struct intel_encoder *encoder)
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
 	intel_edp_panel_off(intel_dp);
 
-	/* cpu edp my only be disable _after_ the cpu pipe/plane is disabled. */
-	if (!(port == PORT_A || IS_VALLEYVIEW(dev)))
+	/* disable the port before the pipe on g4x */
+	if (INTEL_INFO(dev)->gen < 5)
 		intel_dp_link_down(intel_dp);
 }
 
-static void g4x_post_disable_dp(struct intel_encoder *encoder)
+static void ilk_post_disable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	enum port port = dp_to_dig_port(intel_dp)->port;
 
-	if (port != PORT_A)
-		return;
-
 	intel_dp_link_down(intel_dp);
-	ironlake_edp_pll_off(intel_dp);
+	if (port == PORT_A)
+		ironlake_edp_pll_off(intel_dp);
 }
 
 static void vlv_post_disable_dp(struct intel_encoder *encoder)
@@ -2106,6 +2379,104 @@ static void chv_post_disable_dp(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
+static void
+_intel_dp_set_link_train(struct intel_dp *intel_dp,
+			 uint32_t *DP,
+			 uint8_t dp_train_pat)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum port port = intel_dig_port->port;
+
+	if (HAS_DDI(dev)) {
+		uint32_t temp = I915_READ(DP_TP_CTL(port));
+
+		if (dp_train_pat & DP_LINK_SCRAMBLING_DISABLE)
+			temp |= DP_TP_CTL_SCRAMBLE_DISABLE;
+		else
+			temp &= ~DP_TP_CTL_SCRAMBLE_DISABLE;
+
+		temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
+		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
+		case DP_TRAINING_PATTERN_DISABLE:
+			temp |= DP_TP_CTL_LINK_TRAIN_NORMAL;
+
+			break;
+		case DP_TRAINING_PATTERN_1:
+			temp |= DP_TP_CTL_LINK_TRAIN_PAT1;
+			break;
+		case DP_TRAINING_PATTERN_2:
+			temp |= DP_TP_CTL_LINK_TRAIN_PAT2;
+			break;
+		case DP_TRAINING_PATTERN_3:
+			temp |= DP_TP_CTL_LINK_TRAIN_PAT3;
+			break;
+		}
+		I915_WRITE(DP_TP_CTL(port), temp);
+
+	} else if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || port != PORT_A)) {
+		*DP &= ~DP_LINK_TRAIN_MASK_CPT;
+
+		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
+		case DP_TRAINING_PATTERN_DISABLE:
+			*DP |= DP_LINK_TRAIN_OFF_CPT;
+			break;
+		case DP_TRAINING_PATTERN_1:
+			*DP |= DP_LINK_TRAIN_PAT_1_CPT;
+			break;
+		case DP_TRAINING_PATTERN_2:
+			*DP |= DP_LINK_TRAIN_PAT_2_CPT;
+			break;
+		case DP_TRAINING_PATTERN_3:
+			DRM_ERROR("DP training pattern 3 not supported\n");
+			*DP |= DP_LINK_TRAIN_PAT_2_CPT;
+			break;
+		}
+
+	} else {
+		if (IS_CHERRYVIEW(dev))
+			*DP &= ~DP_LINK_TRAIN_MASK_CHV;
+		else
+			*DP &= ~DP_LINK_TRAIN_MASK;
+
+		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
+		case DP_TRAINING_PATTERN_DISABLE:
+			*DP |= DP_LINK_TRAIN_OFF;
+			break;
+		case DP_TRAINING_PATTERN_1:
+			*DP |= DP_LINK_TRAIN_PAT_1;
+			break;
+		case DP_TRAINING_PATTERN_2:
+			*DP |= DP_LINK_TRAIN_PAT_2;
+			break;
+		case DP_TRAINING_PATTERN_3:
+			if (IS_CHERRYVIEW(dev)) {
+				*DP |= DP_LINK_TRAIN_PAT_3_CHV;
+			} else {
+				DRM_ERROR("DP training pattern 3 not supported\n");
+				*DP |= DP_LINK_TRAIN_PAT_2;
+			}
+			break;
+		}
+	}
+}
+
+static void intel_dp_enable_port(struct intel_dp *intel_dp)
+{
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	intel_dp->DP |= DP_PORT_EN;
+
+	/* enable with pattern 1 (as per spec) */
+	_intel_dp_set_link_train(intel_dp, &intel_dp->DP,
+				 DP_TRAINING_PATTERN_1);
+
+	I915_WRITE(intel_dp->output_reg, intel_dp->DP);
+	POSTING_READ(intel_dp->output_reg);
+}
+
 static void intel_enable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
@@ -2116,11 +2487,12 @@ static void intel_enable_dp(struct intel_encoder *encoder)
 	if (WARN_ON(dp_reg & DP_PORT_EN))
 		return;
 
+	intel_dp_enable_port(intel_dp);
 	intel_edp_panel_vdd_on(intel_dp);
+	intel_edp_panel_on(intel_dp);
+	intel_edp_panel_vdd_off(intel_dp, true);
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 	intel_dp_start_link_train(intel_dp);
-	intel_edp_panel_on(intel_dp);
-	edp_panel_vdd_off(intel_dp, true);
 	intel_dp_complete_link_train(intel_dp);
 	intel_dp_stop_link_train(intel_dp);
 }
@@ -2154,6 +2526,78 @@ static void g4x_pre_enable_dp(struct intel_encoder *encoder)
 	}
 }
 
+static void vlv_steal_power_sequencer(struct drm_device *dev,
+				      enum pipe pipe)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_encoder *encoder;
+
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
+			    base.head) {
+		struct intel_dp *intel_dp;
+		enum port port;
+
+		if (encoder->type != INTEL_OUTPUT_EDP)
+			continue;
+
+		intel_dp = enc_to_intel_dp(&encoder->base);
+		port = dp_to_dig_port(intel_dp)->port;
+
+		if (intel_dp->pps_pipe != pipe)
+			continue;
+
+		DRM_DEBUG_KMS("stealing pipe %c power sequencer from port %c\n",
+			      pipe_name(pipe), port_name(port));
+
+		/* make sure vdd is off before we steal it */
+		edp_panel_vdd_off_sync(intel_dp);
+
+		intel_dp->pps_pipe = INVALID_PIPE;
+	}
+}
+
+static void vlv_init_panel_power_sequencer(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct intel_encoder *encoder = &intel_dig_port->base;
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+	struct edp_power_seq power_seq;
+
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
+	if (intel_dp->pps_pipe == crtc->pipe)
+		return;
+
+	/*
+	 * If another power sequencer was being used on this
+	 * port previously make sure to turn off vdd there while
+	 * we still have control of it.
+	 */
+	if (intel_dp->pps_pipe != INVALID_PIPE)
+		edp_panel_vdd_off_sync(intel_dp);
+
+	/*
+	 * We may be stealing the power
+	 * sequencer from another port.
+	 */
+	vlv_steal_power_sequencer(dev, crtc->pipe);
+
+	/* now it's all ours */
+	intel_dp->pps_pipe = crtc->pipe;
+
+	DRM_DEBUG_KMS("initializing pipe %c power sequencer for port %c\n",
+		      pipe_name(intel_dp->pps_pipe), port_name(intel_dig_port->port));
+
+	/* init power sequencer on this pipe and port */
+	intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
+	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
+						      &power_seq);
+}
+
 static void vlv_pre_enable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
@@ -2163,7 +2607,6 @@ static void vlv_pre_enable_dp(struct intel_encoder *encoder)
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	int pipe = intel_crtc->pipe;
-	struct edp_power_seq power_seq;
 	u32 val;
 
 	mutex_lock(&dev_priv->dpio_lock);
@@ -2182,10 +2625,9 @@ static void vlv_pre_enable_dp(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->dpio_lock);
 
 	if (is_edp(intel_dp)) {
-		/* init power sequencer on this pipe and port */
-		intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
-		intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
-							      &power_seq);
+		pps_lock(intel_dp);
+		vlv_init_panel_power_sequencer(intel_dp);
+		pps_unlock(intel_dp);
 	}
 
 	intel_enable_dp(encoder);
@@ -2229,7 +2671,6 @@ static void chv_pre_enable_dp(struct intel_encoder *encoder)
 	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct edp_power_seq power_seq;
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(encoder->base.crtc);
 	enum dpio_channel ch = vlv_dport_to_channel(dport);
@@ -2275,10 +2716,9 @@ static void chv_pre_enable_dp(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->dpio_lock);
 
 	if (is_edp(intel_dp)) {
-		/* init power sequencer on this pipe and port */
-		intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
-		intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
-							      &power_seq);
+		pps_lock(intel_dp);
+		vlv_init_panel_power_sequencer(intel_dp);
+		pps_unlock(intel_dp);
 	}
 
 	intel_enable_dp(encoder);
@@ -2297,6 +2737,8 @@ static void chv_dp_pre_pll_enable(struct intel_encoder *encoder)
 	enum pipe pipe = intel_crtc->pipe;
 	u32 val;
 
+	intel_dp_prepare(encoder);
+
 	mutex_lock(&dev_priv->dpio_lock);
 
 	/* program left/right clock distribution */
@@ -2395,13 +2837,13 @@ intel_dp_voltage_max(struct intel_dp *intel_dp)
 	enum port port = dp_to_dig_port(intel_dp)->port;
 
 	if (IS_VALLEYVIEW(dev))
-		return DP_TRAIN_VOLTAGE_SWING_1200;
+		return DP_TRAIN_VOLTAGE_SWING_LEVEL_3;
 	else if (IS_GEN7(dev) && port == PORT_A)
-		return DP_TRAIN_VOLTAGE_SWING_800;
+		return DP_TRAIN_VOLTAGE_SWING_LEVEL_2;
 	else if (HAS_PCH_CPT(dev) && port != PORT_A)
-		return DP_TRAIN_VOLTAGE_SWING_1200;
+		return DP_TRAIN_VOLTAGE_SWING_LEVEL_3;
 	else
-		return DP_TRAIN_VOLTAGE_SWING_800;
+		return DP_TRAIN_VOLTAGE_SWING_LEVEL_2;
 }
 
 static uint8_t
@@ -2412,49 +2854,49 @@ intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing)
 
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
-			return DP_TRAIN_PRE_EMPHASIS_9_5;
-		case DP_TRAIN_VOLTAGE_SWING_600:
-			return DP_TRAIN_PRE_EMPHASIS_6;
-		case DP_TRAIN_VOLTAGE_SWING_800:
-			return DP_TRAIN_PRE_EMPHASIS_3_5;
-		case DP_TRAIN_VOLTAGE_SWING_1200:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
+			return DP_TRAIN_PRE_EMPH_LEVEL_3;
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
+			return DP_TRAIN_PRE_EMPH_LEVEL_2;
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
+			return DP_TRAIN_PRE_EMPH_LEVEL_1;
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
 		default:
-			return DP_TRAIN_PRE_EMPHASIS_0;
+			return DP_TRAIN_PRE_EMPH_LEVEL_0;
 		}
 	} else if (IS_VALLEYVIEW(dev)) {
 		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
-			return DP_TRAIN_PRE_EMPHASIS_9_5;
-		case DP_TRAIN_VOLTAGE_SWING_600:
-			return DP_TRAIN_PRE_EMPHASIS_6;
-		case DP_TRAIN_VOLTAGE_SWING_800:
-			return DP_TRAIN_PRE_EMPHASIS_3_5;
-		case DP_TRAIN_VOLTAGE_SWING_1200:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
+			return DP_TRAIN_PRE_EMPH_LEVEL_3;
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
+			return DP_TRAIN_PRE_EMPH_LEVEL_2;
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
+			return DP_TRAIN_PRE_EMPH_LEVEL_1;
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
 		default:
-			return DP_TRAIN_PRE_EMPHASIS_0;
+			return DP_TRAIN_PRE_EMPH_LEVEL_0;
 		}
 	} else if (IS_GEN7(dev) && port == PORT_A) {
 		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
-			return DP_TRAIN_PRE_EMPHASIS_6;
-		case DP_TRAIN_VOLTAGE_SWING_600:
-		case DP_TRAIN_VOLTAGE_SWING_800:
-			return DP_TRAIN_PRE_EMPHASIS_3_5;
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
+			return DP_TRAIN_PRE_EMPH_LEVEL_2;
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
+			return DP_TRAIN_PRE_EMPH_LEVEL_1;
 		default:
-			return DP_TRAIN_PRE_EMPHASIS_0;
+			return DP_TRAIN_PRE_EMPH_LEVEL_0;
 		}
 	} else {
 		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
-			return DP_TRAIN_PRE_EMPHASIS_6;
-		case DP_TRAIN_VOLTAGE_SWING_600:
-			return DP_TRAIN_PRE_EMPHASIS_6;
-		case DP_TRAIN_VOLTAGE_SWING_800:
-			return DP_TRAIN_PRE_EMPHASIS_3_5;
-		case DP_TRAIN_VOLTAGE_SWING_1200:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
+			return DP_TRAIN_PRE_EMPH_LEVEL_2;
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
+			return DP_TRAIN_PRE_EMPH_LEVEL_2;
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
+			return DP_TRAIN_PRE_EMPH_LEVEL_1;
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
 		default:
-			return DP_TRAIN_PRE_EMPHASIS_0;
+			return DP_TRAIN_PRE_EMPH_LEVEL_0;
 		}
 	}
 }
@@ -2473,22 +2915,22 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp)
 	int pipe = intel_crtc->pipe;
 
 	switch (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) {
-	case DP_TRAIN_PRE_EMPHASIS_0:
+	case DP_TRAIN_PRE_EMPH_LEVEL_0:
 		preemph_reg_value = 0x0004000;
 		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
 			demph_reg_value = 0x2B405555;
 			uniqtranscale_reg_value = 0x552AB83A;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_600:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
 			demph_reg_value = 0x2B404040;
 			uniqtranscale_reg_value = 0x5548B83A;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_800:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
 			demph_reg_value = 0x2B245555;
 			uniqtranscale_reg_value = 0x5560B83A;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_1200:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
 			demph_reg_value = 0x2B405555;
 			uniqtranscale_reg_value = 0x5598DA3A;
 			break;
@@ -2496,18 +2938,18 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp)
 			return 0;
 		}
 		break;
-	case DP_TRAIN_PRE_EMPHASIS_3_5:
+	case DP_TRAIN_PRE_EMPH_LEVEL_1:
 		preemph_reg_value = 0x0002000;
 		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
 			demph_reg_value = 0x2B404040;
 			uniqtranscale_reg_value = 0x5552B83A;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_600:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
 			demph_reg_value = 0x2B404848;
 			uniqtranscale_reg_value = 0x5580B83A;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_800:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
 			demph_reg_value = 0x2B404040;
 			uniqtranscale_reg_value = 0x55ADDA3A;
 			break;
@@ -2515,14 +2957,14 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp)
 			return 0;
 		}
 		break;
-	case DP_TRAIN_PRE_EMPHASIS_6:
+	case DP_TRAIN_PRE_EMPH_LEVEL_2:
 		preemph_reg_value = 0x0000000;
 		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
 			demph_reg_value = 0x2B305555;
 			uniqtranscale_reg_value = 0x5570B83A;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_600:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
 			demph_reg_value = 0x2B2B4040;
 			uniqtranscale_reg_value = 0x55ADDA3A;
 			break;
@@ -2530,10 +2972,10 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp)
 			return 0;
 		}
 		break;
-	case DP_TRAIN_PRE_EMPHASIS_9_5:
+	case DP_TRAIN_PRE_EMPH_LEVEL_3:
 		preemph_reg_value = 0x0006000;
 		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
 			demph_reg_value = 0x1B405555;
 			uniqtranscale_reg_value = 0x55ADDA3A;
 			break;
@@ -2572,21 +3014,21 @@ static uint32_t intel_chv_signal_levels(struct intel_dp *intel_dp)
 	int i;
 
 	switch (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) {
-	case DP_TRAIN_PRE_EMPHASIS_0:
+	case DP_TRAIN_PRE_EMPH_LEVEL_0:
 		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
 			deemph_reg_value = 128;
 			margin_reg_value = 52;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_600:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
 			deemph_reg_value = 128;
 			margin_reg_value = 77;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_800:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
 			deemph_reg_value = 128;
 			margin_reg_value = 102;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_1200:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
 			deemph_reg_value = 128;
 			margin_reg_value = 154;
 			/* FIXME extra to set for 1200 */
@@ -2595,17 +3037,17 @@ static uint32_t intel_chv_signal_levels(struct intel_dp *intel_dp)
 			return 0;
 		}
 		break;
-	case DP_TRAIN_PRE_EMPHASIS_3_5:
+	case DP_TRAIN_PRE_EMPH_LEVEL_1:
 		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
 			deemph_reg_value = 85;
 			margin_reg_value = 78;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_600:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
 			deemph_reg_value = 85;
 			margin_reg_value = 116;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_800:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
 			deemph_reg_value = 85;
 			margin_reg_value = 154;
 			break;
@@ -2613,13 +3055,13 @@ static uint32_t intel_chv_signal_levels(struct intel_dp *intel_dp)
 			return 0;
 		}
 		break;
-	case DP_TRAIN_PRE_EMPHASIS_6:
+	case DP_TRAIN_PRE_EMPH_LEVEL_2:
 		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
 			deemph_reg_value = 64;
 			margin_reg_value = 104;
 			break;
-		case DP_TRAIN_VOLTAGE_SWING_600:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
 			deemph_reg_value = 64;
 			margin_reg_value = 154;
 			break;
@@ -2627,9 +3069,9 @@ static uint32_t intel_chv_signal_levels(struct intel_dp *intel_dp)
 			return 0;
 		}
 		break;
-	case DP_TRAIN_PRE_EMPHASIS_9_5:
+	case DP_TRAIN_PRE_EMPH_LEVEL_3:
 		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
+		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
 			deemph_reg_value = 43;
 			margin_reg_value = 154;
 			break;
@@ -2663,8 +3105,8 @@ static uint32_t intel_chv_signal_levels(struct intel_dp *intel_dp)
 	/* Program swing margin */
 	for (i = 0; i < 4; i++) {
 		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i));
-		val &= ~DPIO_SWING_MARGIN_MASK;
-		val |= margin_reg_value << DPIO_SWING_MARGIN_SHIFT;
+		val &= ~DPIO_SWING_MARGIN000_MASK;
+		val |= margin_reg_value << DPIO_SWING_MARGIN000_SHIFT;
 		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val);
 	}
 
@@ -2676,9 +3118,9 @@ static uint32_t intel_chv_signal_levels(struct intel_dp *intel_dp)
 	}
 
 	if (((train_set & DP_TRAIN_PRE_EMPHASIS_MASK)
-			== DP_TRAIN_PRE_EMPHASIS_0) &&
+			== DP_TRAIN_PRE_EMPH_LEVEL_0) &&
 		((train_set & DP_TRAIN_VOLTAGE_SWING_MASK)
-			== DP_TRAIN_VOLTAGE_SWING_1200)) {
+			== DP_TRAIN_VOLTAGE_SWING_LEVEL_3)) {
 
 		/*
 		 * The document said it needs to set bit 27 for ch0 and bit 26
@@ -2757,32 +3199,32 @@ intel_gen4_signal_levels(uint8_t train_set)
 	uint32_t	signal_levels = 0;
 
 	switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
-	case DP_TRAIN_VOLTAGE_SWING_400:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
 	default:
 		signal_levels |= DP_VOLTAGE_0_4;
 		break;
-	case DP_TRAIN_VOLTAGE_SWING_600:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
 		signal_levels |= DP_VOLTAGE_0_6;
 		break;
-	case DP_TRAIN_VOLTAGE_SWING_800:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
 		signal_levels |= DP_VOLTAGE_0_8;
 		break;
-	case DP_TRAIN_VOLTAGE_SWING_1200:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
 		signal_levels |= DP_VOLTAGE_1_2;
 		break;
 	}
 	switch (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) {
-	case DP_TRAIN_PRE_EMPHASIS_0:
+	case DP_TRAIN_PRE_EMPH_LEVEL_0:
 	default:
 		signal_levels |= DP_PRE_EMPHASIS_0;
 		break;
-	case DP_TRAIN_PRE_EMPHASIS_3_5:
+	case DP_TRAIN_PRE_EMPH_LEVEL_1:
 		signal_levels |= DP_PRE_EMPHASIS_3_5;
 		break;
-	case DP_TRAIN_PRE_EMPHASIS_6:
+	case DP_TRAIN_PRE_EMPH_LEVEL_2:
 		signal_levels |= DP_PRE_EMPHASIS_6;
 		break;
-	case DP_TRAIN_PRE_EMPHASIS_9_5:
+	case DP_TRAIN_PRE_EMPH_LEVEL_3:
 		signal_levels |= DP_PRE_EMPHASIS_9_5;
 		break;
 	}
@@ -2796,19 +3238,19 @@ intel_gen6_edp_signal_levels(uint8_t train_set)
 	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
 					 DP_TRAIN_PRE_EMPHASIS_MASK);
 	switch (signal_levels) {
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_0:
-	case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_0:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_0:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_0:
 		return EDP_LINK_TRAIN_400_600MV_0DB_SNB_B;
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_3_5:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_1:
 		return EDP_LINK_TRAIN_400MV_3_5DB_SNB_B;
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_6:
-	case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_6:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_2:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_2:
 		return EDP_LINK_TRAIN_400_600MV_6DB_SNB_B;
-	case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_3_5:
-	case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_3_5:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_1:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_2 | DP_TRAIN_PRE_EMPH_LEVEL_1:
 		return EDP_LINK_TRAIN_600_800MV_3_5DB_SNB_B;
-	case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_0:
-	case DP_TRAIN_VOLTAGE_SWING_1200 | DP_TRAIN_PRE_EMPHASIS_0:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_2 | DP_TRAIN_PRE_EMPH_LEVEL_0:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_3 | DP_TRAIN_PRE_EMPH_LEVEL_0:
 		return EDP_LINK_TRAIN_800_1200MV_0DB_SNB_B;
 	default:
 		DRM_DEBUG_KMS("Unsupported voltage swing/pre-emphasis level:"
@@ -2824,21 +3266,21 @@ intel_gen7_edp_signal_levels(uint8_t train_set)
 	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
 					 DP_TRAIN_PRE_EMPHASIS_MASK);
 	switch (signal_levels) {
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_0:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_0:
 		return EDP_LINK_TRAIN_400MV_0DB_IVB;
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_3_5:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_1:
 		return EDP_LINK_TRAIN_400MV_3_5DB_IVB;
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_6:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_2:
 		return EDP_LINK_TRAIN_400MV_6DB_IVB;
 
-	case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_0:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_0:
 		return EDP_LINK_TRAIN_600MV_0DB_IVB;
-	case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_3_5:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_1:
 		return EDP_LINK_TRAIN_600MV_3_5DB_IVB;
 
-	case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_0:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_2 | DP_TRAIN_PRE_EMPH_LEVEL_0:
 		return EDP_LINK_TRAIN_800MV_0DB_IVB;
-	case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_3_5:
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_2 | DP_TRAIN_PRE_EMPH_LEVEL_1:
 		return EDP_LINK_TRAIN_800MV_3_5DB_IVB;
 
 	default:
@@ -2855,30 +3297,30 @@ intel_hsw_signal_levels(uint8_t train_set)
 	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
 					 DP_TRAIN_PRE_EMPHASIS_MASK);
 	switch (signal_levels) {
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_0:
-		return DDI_BUF_EMP_400MV_0DB_HSW;
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_3_5:
-		return DDI_BUF_EMP_400MV_3_5DB_HSW;
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_6:
-		return DDI_BUF_EMP_400MV_6DB_HSW;
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_9_5:
-		return DDI_BUF_EMP_400MV_9_5DB_HSW;
-
-	case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_0:
-		return DDI_BUF_EMP_600MV_0DB_HSW;
-	case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_3_5:
-		return DDI_BUF_EMP_600MV_3_5DB_HSW;
-	case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_6:
-		return DDI_BUF_EMP_600MV_6DB_HSW;
-
-	case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_0:
-		return DDI_BUF_EMP_800MV_0DB_HSW;
-	case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_3_5:
-		return DDI_BUF_EMP_800MV_3_5DB_HSW;
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_0:
+		return DDI_BUF_TRANS_SELECT(0);
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_1:
+		return DDI_BUF_TRANS_SELECT(1);
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_2:
+		return DDI_BUF_TRANS_SELECT(2);
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0 | DP_TRAIN_PRE_EMPH_LEVEL_3:
+		return DDI_BUF_TRANS_SELECT(3);
+
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_0:
+		return DDI_BUF_TRANS_SELECT(4);
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_1:
+		return DDI_BUF_TRANS_SELECT(5);
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1 | DP_TRAIN_PRE_EMPH_LEVEL_2:
+		return DDI_BUF_TRANS_SELECT(6);
+
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_2 | DP_TRAIN_PRE_EMPH_LEVEL_0:
+		return DDI_BUF_TRANS_SELECT(7);
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_2 | DP_TRAIN_PRE_EMPH_LEVEL_1:
+		return DDI_BUF_TRANS_SELECT(8);
 	default:
 		DRM_DEBUG_KMS("Unsupported voltage swing/pre-emphasis level:"
 			      "0x%x\n", signal_levels);
-		return DDI_BUF_EMP_400MV_0DB_HSW;
+		return DDI_BUF_TRANS_SELECT(0);
 	}
 }
 
@@ -2925,74 +3367,10 @@ intel_dp_set_link_train(struct intel_dp *intel_dp,
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	enum port port = intel_dig_port->port;
 	uint8_t buf[sizeof(intel_dp->train_set) + 1];
 	int ret, len;
 
-	if (HAS_DDI(dev)) {
-		uint32_t temp = I915_READ(DP_TP_CTL(port));
-
-		if (dp_train_pat & DP_LINK_SCRAMBLING_DISABLE)
-			temp |= DP_TP_CTL_SCRAMBLE_DISABLE;
-		else
-			temp &= ~DP_TP_CTL_SCRAMBLE_DISABLE;
-
-		temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
-		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
-		case DP_TRAINING_PATTERN_DISABLE:
-			temp |= DP_TP_CTL_LINK_TRAIN_NORMAL;
-
-			break;
-		case DP_TRAINING_PATTERN_1:
-			temp |= DP_TP_CTL_LINK_TRAIN_PAT1;
-			break;
-		case DP_TRAINING_PATTERN_2:
-			temp |= DP_TP_CTL_LINK_TRAIN_PAT2;
-			break;
-		case DP_TRAINING_PATTERN_3:
-			temp |= DP_TP_CTL_LINK_TRAIN_PAT3;
-			break;
-		}
-		I915_WRITE(DP_TP_CTL(port), temp);
-
-	} else if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || port != PORT_A)) {
-		*DP &= ~DP_LINK_TRAIN_MASK_CPT;
-
-		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
-		case DP_TRAINING_PATTERN_DISABLE:
-			*DP |= DP_LINK_TRAIN_OFF_CPT;
-			break;
-		case DP_TRAINING_PATTERN_1:
-			*DP |= DP_LINK_TRAIN_PAT_1_CPT;
-			break;
-		case DP_TRAINING_PATTERN_2:
-			*DP |= DP_LINK_TRAIN_PAT_2_CPT;
-			break;
-		case DP_TRAINING_PATTERN_3:
-			DRM_ERROR("DP training pattern 3 not supported\n");
-			*DP |= DP_LINK_TRAIN_PAT_2_CPT;
-			break;
-		}
-
-	} else {
-		*DP &= ~DP_LINK_TRAIN_MASK;
-
-		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
-		case DP_TRAINING_PATTERN_DISABLE:
-			*DP |= DP_LINK_TRAIN_OFF;
-			break;
-		case DP_TRAINING_PATTERN_1:
-			*DP |= DP_LINK_TRAIN_PAT_1;
-			break;
-		case DP_TRAINING_PATTERN_2:
-			*DP |= DP_LINK_TRAIN_PAT_2;
-			break;
-		case DP_TRAINING_PATTERN_3:
-			DRM_ERROR("DP training pattern 3 not supported\n");
-			*DP |= DP_LINK_TRAIN_PAT_2;
-			break;
-		}
-	}
+	_intel_dp_set_link_train(intel_dp, DP, dp_train_pat);
 
 	I915_WRITE(intel_dp->output_reg, *DP);
 	POSTING_READ(intel_dp->output_reg);
@@ -3276,7 +3654,10 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 		DP &= ~DP_LINK_TRAIN_MASK_CPT;
 		I915_WRITE(intel_dp->output_reg, DP | DP_LINK_TRAIN_PAT_IDLE_CPT);
 	} else {
-		DP &= ~DP_LINK_TRAIN_MASK;
+		if (IS_CHERRYVIEW(dev))
+			DP &= ~DP_LINK_TRAIN_MASK_CHV;
+		else
+			DP &= ~DP_LINK_TRAIN_MASK;
 		I915_WRITE(intel_dp->output_reg, DP | DP_LINK_TRAIN_PAT_IDLE);
 	}
 	POSTING_READ(intel_dp->output_reg);
@@ -3322,15 +3703,11 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 	struct drm_device *dev = dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	char dpcd_hex_dump[sizeof(intel_dp->dpcd) * 3];
-
 	if (intel_dp_dpcd_read_wake(&intel_dp->aux, 0x000, intel_dp->dpcd,
 				    sizeof(intel_dp->dpcd)) < 0)
 		return false; /* aux transfer failed */
 
-	hex_dump_to_buffer(intel_dp->dpcd, sizeof(intel_dp->dpcd),
-			   32, 1, dpcd_hex_dump, sizeof(dpcd_hex_dump), false);
-	DRM_DEBUG_KMS("DPCD: %s\n", dpcd_hex_dump);
+	DRM_DEBUG_KMS("DPCD: %*ph\n", (int) sizeof(intel_dp->dpcd), intel_dp->dpcd);
 
 	if (intel_dp->dpcd[DP_DPCD_REV] == 0)
 		return false; /* DPCD not present */
@@ -3351,7 +3728,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x12 &&
 	    intel_dp->dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED) {
 		intel_dp->use_tps3 = true;
-		DRM_DEBUG_KMS("Displayport TPS3 supported");
+		DRM_DEBUG_KMS("Displayport TPS3 supported\n");
 	} else
 		intel_dp->use_tps3 = false;
 
@@ -3388,7 +3765,7 @@ intel_dp_probe_oui(struct intel_dp *intel_dp)
 		DRM_DEBUG_KMS("Branch OUI: %02hx%02hx%02hx\n",
 			      buf[0], buf[1], buf[2]);
 
-	edp_panel_vdd_off(intel_dp, false);
+	intel_edp_panel_vdd_off(intel_dp, false);
 }
 
 static bool
@@ -3402,7 +3779,7 @@ intel_dp_probe_mst(struct intel_dp *intel_dp)
 	if (intel_dp->dpcd[DP_DPCD_REV] < 0x12)
 		return false;
 
-	_edp_panel_vdd_on(intel_dp);
+	intel_edp_panel_vdd_on(intel_dp);
 	if (intel_dp_dpcd_read_wake(&intel_dp->aux, DP_MSTM_CAP, buf, 1)) {
 		if (buf[0] & DP_MST_CAP) {
 			DRM_DEBUG_KMS("Sink is MST capable\n");
@@ -3412,7 +3789,7 @@ intel_dp_probe_mst(struct intel_dp *intel_dp)
 			intel_dp->is_mst = false;
 		}
 	}
-	edp_panel_vdd_off(intel_dp, false);
+	intel_edp_panel_vdd_off(intel_dp, false);
 
 	drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr, intel_dp->is_mst);
 	return intel_dp->is_mst;
@@ -3427,21 +3804,21 @@ int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc)
 	u8 buf[1];
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, buf) < 0)
-		return -EAGAIN;
+		return -EIO;
 
 	if (!(buf[0] & DP_TEST_CRC_SUPPORTED))
 		return -ENOTTY;
 
 	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK,
 			       DP_TEST_SINK_START) < 0)
-		return -EAGAIN;
+		return -EIO;
 
 	/* Wait 2 vblanks to be sure we will have the correct CRC value */
 	intel_wait_for_vblank(dev, intel_crtc->pipe);
 	intel_wait_for_vblank(dev, intel_crtc->pipe);
 
 	if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0)
-		return -EAGAIN;
+		return -EIO;
 
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK, 0);
 	return 0;
@@ -3644,20 +4021,24 @@ intel_dp_detect_dpcd(struct intel_dp *intel_dp)
 }
 
 static enum drm_connector_status
+edp_detect(struct intel_dp *intel_dp)
+{
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	enum drm_connector_status status;
+
+	status = intel_panel_detect(dev);
+	if (status == connector_status_unknown)
+		status = connector_status_connected;
+
+	return status;
+}
+
+static enum drm_connector_status
 ironlake_dp_detect(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	enum drm_connector_status status;
-
-	/* Can't disconnect eDP, but you can close the lid... */
-	if (is_edp(intel_dp)) {
-		status = intel_panel_detect(dev);
-		if (status == connector_status_unknown)
-			status = connector_status_connected;
-		return status;
-	}
 
 	if (!ibx_digital_port_connected(dev_priv, intel_dig_port))
 		return connector_status_disconnected;
@@ -3733,9 +4114,9 @@ g4x_dp_detect(struct intel_dp *intel_dp)
 }
 
 static struct edid *
-intel_dp_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter)
+intel_dp_get_edid(struct intel_dp *intel_dp)
 {
-	struct intel_connector *intel_connector = to_intel_connector(connector);
+	struct intel_connector *intel_connector = intel_dp->attached_connector;
 
 	/* use cached edid if we have one */
 	if (intel_connector->edid) {
@@ -3744,27 +4125,55 @@ intel_dp_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter)
 			return NULL;
 
 		return drm_edid_duplicate(intel_connector->edid);
-	}
+	} else
+		return drm_get_edid(&intel_connector->base,
+				    &intel_dp->aux.ddc);
+}
+
+static void
+intel_dp_set_edid(struct intel_dp *intel_dp)
+{
+	struct intel_connector *intel_connector = intel_dp->attached_connector;
+	struct edid *edid;
+
+	edid = intel_dp_get_edid(intel_dp);
+	intel_connector->detect_edid = edid;
 
-	return drm_get_edid(connector, adapter);
+	if (intel_dp->force_audio != HDMI_AUDIO_AUTO)
+		intel_dp->has_audio = intel_dp->force_audio == HDMI_AUDIO_ON;
+	else
+		intel_dp->has_audio = drm_detect_monitor_audio(edid);
 }
 
-static int
-intel_dp_get_edid_modes(struct drm_connector *connector, struct i2c_adapter *adapter)
+static void
+intel_dp_unset_edid(struct intel_dp *intel_dp)
 {
-	struct intel_connector *intel_connector = to_intel_connector(connector);
+	struct intel_connector *intel_connector = intel_dp->attached_connector;
 
-	/* use cached edid if we have one */
-	if (intel_connector->edid) {
-		/* invalid edid */
-		if (IS_ERR(intel_connector->edid))
-			return 0;
+	kfree(intel_connector->detect_edid);
+	intel_connector->detect_edid = NULL;
 
-		return intel_connector_update_modes(connector,
-						    intel_connector->edid);
-	}
+	intel_dp->has_audio = false;
+}
+
+static enum intel_display_power_domain
+intel_dp_power_get(struct intel_dp *dp)
+{
+	struct intel_encoder *encoder = &dp_to_dig_port(dp)->base;
+	enum intel_display_power_domain power_domain;
+
+	power_domain = intel_display_port_power_domain(encoder);
+	intel_display_power_get(to_i915(encoder->base.dev), power_domain);
+
+	return power_domain;
+}
 
-	return intel_ddc_get_modes(connector, adapter);
+static void
+intel_dp_power_put(struct intel_dp *dp,
+		   enum intel_display_power_domain power_domain)
+{
+	struct intel_encoder *encoder = &dp_to_dig_port(dp)->base;
+	intel_display_power_put(to_i915(encoder->base.dev), power_domain);
 }
 
 static enum drm_connector_status
@@ -3774,33 +4183,30 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum drm_connector_status status;
 	enum intel_display_power_domain power_domain;
-	struct edid *edid = NULL;
 	bool ret;
 
-	power_domain = intel_display_port_power_domain(intel_encoder);
-	intel_display_power_get(dev_priv, power_domain);
-
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, connector->name);
+	intel_dp_unset_edid(intel_dp);
 
 	if (intel_dp->is_mst) {
 		/* MST devices are disconnected from a monitor POV */
 		if (intel_encoder->type != INTEL_OUTPUT_EDP)
 			intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
-		status = connector_status_disconnected;
-		goto out;
+		return connector_status_disconnected;
 	}
 
-	intel_dp->has_audio = false;
+	power_domain = intel_dp_power_get(intel_dp);
 
-	if (HAS_PCH_SPLIT(dev))
+	/* Can't disconnect eDP, but you can close the lid... */
+	if (is_edp(intel_dp))
+		status = edp_detect(intel_dp);
+	else if (HAS_PCH_SPLIT(dev))
 		status = ironlake_dp_detect(intel_dp);
 	else
 		status = g4x_dp_detect(intel_dp);
-
 	if (status != connector_status_connected)
 		goto out;
 
@@ -3816,82 +4222,78 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 		goto out;
 	}
 
-	if (intel_dp->force_audio != HDMI_AUDIO_AUTO) {
-		intel_dp->has_audio = (intel_dp->force_audio == HDMI_AUDIO_ON);
-	} else {
-		edid = intel_dp_get_edid(connector, &intel_dp->aux.ddc);
-		if (edid) {
-			intel_dp->has_audio = drm_detect_monitor_audio(edid);
-			kfree(edid);
-		}
-	}
+	intel_dp_set_edid(intel_dp);
 
 	if (intel_encoder->type != INTEL_OUTPUT_EDP)
 		intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
 	status = connector_status_connected;
 
 out:
-	intel_display_power_put(dev_priv, power_domain);
+	intel_dp_power_put(intel_dp, power_domain);
 	return status;
 }
 
-static int intel_dp_get_modes(struct drm_connector *connector)
+static void
+intel_dp_force(struct drm_connector *connector)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct intel_encoder *intel_encoder = &intel_dig_port->base;
-	struct intel_connector *intel_connector = to_intel_connector(connector);
-	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_encoder *intel_encoder = &dp_to_dig_port(intel_dp)->base;
 	enum intel_display_power_domain power_domain;
-	int ret;
 
-	/* We should parse the EDID data and find out if it has an audio sink
-	 */
+	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
+		      connector->base.id, connector->name);
+	intel_dp_unset_edid(intel_dp);
 
-	power_domain = intel_display_port_power_domain(intel_encoder);
-	intel_display_power_get(dev_priv, power_domain);
+	if (connector->status != connector_status_connected)
+		return;
 
-	ret = intel_dp_get_edid_modes(connector, &intel_dp->aux.ddc);
-	intel_display_power_put(dev_priv, power_domain);
-	if (ret)
-		return ret;
+	power_domain = intel_dp_power_get(intel_dp);
+
+	intel_dp_set_edid(intel_dp);
+
+	intel_dp_power_put(intel_dp, power_domain);
+
+	if (intel_encoder->type != INTEL_OUTPUT_EDP)
+		intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
+}
+
+static int intel_dp_get_modes(struct drm_connector *connector)
+{
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+	struct edid *edid;
+
+	edid = intel_connector->detect_edid;
+	if (edid) {
+		int ret = intel_connector_update_modes(connector, edid);
+		if (ret)
+			return ret;
+	}
 
 	/* if eDP has no EDID, fall back to fixed mode */
-	if (is_edp(intel_dp) && intel_connector->panel.fixed_mode) {
+	if (is_edp(intel_attached_dp(connector)) &&
+	    intel_connector->panel.fixed_mode) {
 		struct drm_display_mode *mode;
-		mode = drm_mode_duplicate(dev,
+
+		mode = drm_mode_duplicate(connector->dev,
 					  intel_connector->panel.fixed_mode);
 		if (mode) {
 			drm_mode_probed_add(connector, mode);
 			return 1;
 		}
 	}
+
 	return 0;
 }
 
 static bool
 intel_dp_detect_audio(struct drm_connector *connector)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct intel_encoder *intel_encoder = &intel_dig_port->base;
-	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	enum intel_display_power_domain power_domain;
-	struct edid *edid;
 	bool has_audio = false;
+	struct edid *edid;
 
-	power_domain = intel_display_port_power_domain(intel_encoder);
-	intel_display_power_get(dev_priv, power_domain);
-
-	edid = intel_dp_get_edid(connector, &intel_dp->aux.ddc);
-	if (edid) {
+	edid = to_intel_connector(connector)->detect_edid;
+	if (edid)
 		has_audio = drm_detect_monitor_audio(edid);
-		kfree(edid);
-	}
-
-	intel_display_power_put(dev_priv, power_domain);
 
 	return has_audio;
 }
@@ -3989,6 +4391,8 @@ intel_dp_connector_destroy(struct drm_connector *connector)
 {
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 
+	kfree(intel_connector->detect_edid);
+
 	if (!IS_ERR_OR_NULL(intel_connector->edid))
 		kfree(intel_connector->edid);
 
@@ -4005,16 +4409,20 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder)
 {
 	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 
 	drm_dp_aux_unregister(&intel_dp->aux);
 	intel_dp_mst_encoder_cleanup(intel_dig_port);
 	drm_encoder_cleanup(encoder);
 	if (is_edp(intel_dp)) {
 		cancel_delayed_work_sync(&intel_dp->panel_vdd_work);
-		drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
+		/*
+		 * vdd might still be enabled do to the delayed vdd off.
+		 * Make sure vdd is actually turned off here.
+		 */
+		pps_lock(intel_dp);
 		edp_panel_vdd_off_sync(intel_dp);
-		drm_modeset_unlock(&dev->mode_config.connection_mutex);
+		pps_unlock(intel_dp);
+
 		if (intel_dp->edp_notifier.notifier_call) {
 			unregister_reboot_notifier(&intel_dp->edp_notifier);
 			intel_dp->edp_notifier.notifier_call = NULL;
@@ -4030,7 +4438,13 @@ static void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder)
 	if (!is_edp(intel_dp))
 		return;
 
+	/*
+	 * vdd might still be enabled do to the delayed vdd off.
+	 * Make sure vdd is actually turned off here.
+	 */
+	pps_lock(intel_dp);
 	edp_panel_vdd_off_sync(intel_dp);
+	pps_unlock(intel_dp);
 }
 
 static void intel_dp_encoder_reset(struct drm_encoder *encoder)
@@ -4041,6 +4455,7 @@ static void intel_dp_encoder_reset(struct drm_encoder *encoder)
 static const struct drm_connector_funcs intel_dp_connector_funcs = {
 	.dpms = intel_connector_dpms,
 	.detect = intel_dp_detect,
+	.force = intel_dp_force,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.set_property = intel_dp_set_property,
 	.destroy = intel_dp_connector_destroy,
@@ -4076,7 +4491,8 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 	if (intel_dig_port->base.type != INTEL_OUTPUT_EDP)
 		intel_dig_port->base.type = INTEL_OUTPUT_DISPLAYPORT;
 
-	DRM_DEBUG_KMS("got hpd irq on port %d - %s\n", intel_dig_port->port,
+	DRM_DEBUG_KMS("got hpd irq on port %c - %s\n",
+		      port_name(intel_dig_port->port),
 		      long_hpd ? "long" : "short");
 
 	power_domain = intel_display_port_power_domain(intel_encoder);
@@ -4216,6 +4632,8 @@ intel_dp_init_panel_power_sequencer(struct drm_device *dev,
 	u32 pp_on, pp_off, pp_div, pp;
 	int pp_ctrl_reg, pp_on_reg, pp_off_reg, pp_div_reg;
 
+	lockdep_assert_held(&dev_priv->pps_mutex);
+
 	if (HAS_PCH_SPLIT(dev)) {
 		pp_ctrl_reg = PCH_PP_CONTROL;
 		pp_on_reg = PCH_PP_ON_DELAYS;
@@ -4315,6 +4733,9 @@ intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
 	u32 pp_on, pp_off, pp_div, port_sel = 0;
 	int div = HAS_PCH_SPLIT(dev) ? intel_pch_rawclk(dev) : intel_hrawclk(dev);
 	int pp_on_reg, pp_off_reg, pp_div_reg;
+	enum port port = dp_to_dig_port(intel_dp)->port;
+
+	lockdep_assert_held(&dev_priv->pps_mutex);
 
 	if (HAS_PCH_SPLIT(dev)) {
 		pp_on_reg = PCH_PP_ON_DELAYS;
@@ -4349,12 +4770,9 @@ intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
 	/* Haswell doesn't have any port selection bits for the panel
 	 * power sequencer any more. */
 	if (IS_VALLEYVIEW(dev)) {
-		if (dp_to_dig_port(intel_dp)->port == PORT_B)
-			port_sel = PANEL_PORT_SELECT_DPB_VLV;
-		else
-			port_sel = PANEL_PORT_SELECT_DPC_VLV;
+		port_sel = PANEL_PORT_SELECT_VLV(port);
 	} else if (HAS_PCH_IBX(dev) || HAS_PCH_CPT(dev)) {
-		if (dp_to_dig_port(intel_dp)->port == PORT_A)
+		if (port == PORT_A)
 			port_sel = PANEL_PORT_SELECT_DPA;
 		else
 			port_sel = PANEL_PORT_SELECT_DPD;
@@ -4438,7 +4856,7 @@ void intel_dp_set_drrs_state(struct drm_device *dev, int refresh_rate)
 		val = I915_READ(reg);
 		if (index > DRRS_HIGH_RR) {
 			val |= PIPECONF_EDP_RR_MODE_SWITCH;
-			intel_dp_set_m2_n2(intel_crtc, &config->dp_m2_n2);
+			intel_dp_set_m_n(intel_crtc);
 		} else {
 			val &= ~PIPECONF_EDP_RR_MODE_SWITCH;
 		}
@@ -4478,7 +4896,7 @@ intel_dp_drrs_init(struct intel_digital_port *intel_dig_port,
 	}
 
 	if (dev_priv->vbt.drrs_type != SEAMLESS_DRRS_SUPPORT) {
-		DRM_INFO("VBT doesn't support DRRS\n");
+		DRM_DEBUG_KMS("VBT doesn't support DRRS\n");
 		return NULL;
 	}
 
@@ -4486,7 +4904,7 @@ intel_dp_drrs_init(struct intel_digital_port *intel_dig_port,
 					(dev, fixed_mode, connector);
 
 	if (!downclock_mode) {
-		DRM_INFO("DRRS not supported\n");
+		DRM_DEBUG_KMS("DRRS not supported\n");
 		return NULL;
 	}
 
@@ -4497,7 +4915,7 @@ intel_dp_drrs_init(struct intel_digital_port *intel_dig_port,
 	intel_dp->drrs_state.type = dev_priv->vbt.drrs_type;
 
 	intel_dp->drrs_state.refresh_rate_type = DRRS_HIGH_RR;
-	DRM_INFO("seamless DRRS supported for eDP panel.\n");
+	DRM_DEBUG_KMS("seamless DRRS supported for eDP panel.\n");
 	return downclock_mode;
 }
 
@@ -4512,8 +4930,11 @@ void intel_edp_panel_vdd_sanitize(struct intel_encoder *intel_encoder)
 		return;
 
 	intel_dp = enc_to_intel_dp(&intel_encoder->base);
+
+	pps_lock(intel_dp);
+
 	if (!edp_have_panel_vdd(intel_dp))
-		return;
+		goto out;
 	/*
 	 * The VDD bit needs a power domain reference, so if the bit is
 	 * already enabled when we boot or resume, grab this reference and
@@ -4525,6 +4946,8 @@ void intel_edp_panel_vdd_sanitize(struct intel_encoder *intel_encoder)
 	intel_display_power_get(dev_priv, power_domain);
 
 	edp_panel_vdd_schedule_off(intel_dp);
+ out:
+	pps_unlock(intel_dp);
 }
 
 static bool intel_edp_init_connector(struct intel_dp *intel_dp,
@@ -4552,7 +4975,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	/* Cache DPCD and EDID for edp. */
 	intel_edp_panel_vdd_on(intel_dp);
 	has_dpcd = intel_dp_get_dpcd(intel_dp);
-	edp_panel_vdd_off(intel_dp, false);
+	intel_edp_panel_vdd_off(intel_dp, false);
 
 	if (has_dpcd) {
 		if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11)
@@ -4566,7 +4989,9 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	}
 
 	/* We now know it's not a ghost, init power sequence regs. */
+	pps_lock(intel_dp);
 	intel_dp_init_panel_power_sequencer_registers(dev, intel_dp, power_seq);
+	pps_unlock(intel_dp);
 
 	mutex_lock(&dev->mode_config.mutex);
 	edid = drm_get_edid(connector, &intel_dp->aux.ddc);
@@ -4610,6 +5035,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	}
 
 	intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
+	intel_connector->panel.backlight_power = intel_edp_backlight_power;
 	intel_panel_setup_backlight(connector);
 
 	return true;
@@ -4628,6 +5054,8 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	struct edp_power_seq power_seq = { 0 };
 	int type;
 
+	intel_dp->pps_pipe = INVALID_PIPE;
+
 	/* intel_dp vfuncs */
 	if (IS_VALLEYVIEW(dev))
 		intel_dp->get_aux_clock_divider = vlv_get_aux_clock_divider;
@@ -4698,8 +5126,15 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	}
 
 	if (is_edp(intel_dp)) {
-		intel_dp_init_panel_power_timestamps(intel_dp);
-		intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
+		pps_lock(intel_dp);
+		if (IS_VALLEYVIEW(dev)) {
+			vlv_initial_power_sequencer_setup(intel_dp);
+		} else {
+			intel_dp_init_panel_power_timestamps(intel_dp);
+			intel_dp_init_panel_power_sequencer(dev, intel_dp,
+							    &power_seq);
+		}
+		pps_unlock(intel_dp);
 	}
 
 	intel_dp_aux_init(intel_dp, intel_connector);
@@ -4707,7 +5142,8 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	/* init MST on ports that can support it */
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		if (port == PORT_B || port == PORT_C || port == PORT_D) {
-			intel_dp_mst_encoder_init(intel_dig_port, intel_connector->base.base.id);
+			intel_dp_mst_encoder_init(intel_dig_port,
+						  intel_connector->base.base.id);
 		}
 	}
 
@@ -4715,9 +5151,13 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 		drm_dp_aux_unregister(&intel_dp->aux);
 		if (is_edp(intel_dp)) {
 			cancel_delayed_work_sync(&intel_dp->panel_vdd_work);
-			drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
+			/*
+			 * vdd might still be enabled do to the delayed vdd off.
+			 * Make sure vdd is actually turned off here.
+			 */
+			pps_lock(intel_dp);
 			edp_panel_vdd_off_sync(intel_dp);
-			drm_modeset_unlock(&dev->mode_config.connection_mutex);
+			pps_unlock(intel_dp);
 		}
 		drm_connector_unregister(connector);
 		drm_connector_cleanup(connector);
@@ -4781,7 +5221,8 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 	} else {
 		intel_encoder->pre_enable = g4x_pre_enable_dp;
 		intel_encoder->enable = g4x_enable_dp;
-		intel_encoder->post_disable = g4x_post_disable_dp;
+		if (INTEL_INFO(dev)->gen >= 5)
+			intel_encoder->post_disable = ilk_post_disable_dp;
 	}
 
 	intel_dig_port->port = port;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index b8c8bbd8e5f9..07ce04683c30 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -25,6 +25,7 @@
 #ifndef __INTEL_DRV_H__
 #define __INTEL_DRV_H__
 
+#include <linux/async.h>
 #include <linux/i2c.h>
 #include <linux/hdmi.h>
 #include <drm/i915_drm.h>
@@ -179,6 +180,8 @@ struct intel_panel {
 		bool active_low_pwm;
 		struct backlight_device *device;
 	} backlight;
+
+	void (*backlight_power)(struct intel_connector *, bool enable);
 };
 
 struct intel_connector {
@@ -211,6 +214,7 @@ struct intel_connector {
 
 	/* Cached EDID for eDP and LVDS. May hold ERR_PTR for invalid EDID. */
 	struct edid *edid;
+	struct edid *detect_edid;
 
 	/* since POLL and HPD connectors may use the same HPD line keep the native
 	   state of connector->polled in case hotplug storm detection changes it */
@@ -330,6 +334,7 @@ struct intel_crtc_config {
 
 	/* m2_n2 for eDP downclock */
 	struct intel_link_m_n dp_m2_n2;
+	bool has_drrs;
 
 	/*
 	 * Frequence the dpll for the port should run at. Differs from the
@@ -410,6 +415,7 @@ struct intel_crtc {
 	uint32_t cursor_addr;
 	int16_t cursor_width, cursor_height;
 	uint32_t cursor_cntl;
+	uint32_t cursor_size;
 	uint32_t cursor_base;
 
 	struct intel_plane_config plane_config;
@@ -430,8 +436,6 @@ struct intel_crtc {
 		struct intel_pipe_wm active;
 	} wm;
 
-	wait_queue_head_t vbl_wait;
-
 	int scanline_offset;
 	struct intel_mmio_flip mmio_flip;
 };
@@ -455,6 +459,7 @@ struct intel_plane {
 	unsigned int crtc_w, crtc_h;
 	uint32_t src_x, src_y;
 	uint32_t src_w, src_h;
+	unsigned int rotation;
 
 	/* Since we need to change the watermarks before/after
 	 * enabling/disabling the planes, we need to store the parameters here
@@ -565,6 +570,12 @@ struct intel_dp {
 
 	struct notifier_block edp_notifier;
 
+	/*
+	 * Pipe whose power sequencer is currently locked into
+	 * this port. Only relevant on VLV/CHV.
+	 */
+	enum pipe pps_pipe;
+
 	bool use_tps3;
 	bool can_mst; /* this port supports mst */
 	bool is_mst;
@@ -663,6 +674,10 @@ struct intel_unpin_work {
 #define INTEL_FLIP_COMPLETE	2
 	u32 flip_count;
 	u32 gtt_offset;
+	struct intel_engine_cs *flip_queued_ring;
+	u32 flip_queued_seqno;
+	int flip_queued_vblank;
+	int flip_ready_vblank;
 	bool enable_stall_check;
 };
 
@@ -827,7 +842,6 @@ int intel_get_pipe_from_crtc_id(struct drm_device *dev, void *data,
 enum transcoder intel_pipe_to_cpu_transcoder(struct drm_i915_private *dev_priv,
 					     enum pipe pipe);
 void intel_wait_for_vblank(struct drm_device *dev, int pipe);
-void intel_wait_for_pipe_off(struct drm_device *dev, int pipe);
 int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp);
 void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 			 struct intel_digital_port *dport);
@@ -848,6 +862,7 @@ __intel_framebuffer_create(struct drm_device *dev,
 void intel_prepare_page_flip(struct drm_device *dev, int plane);
 void intel_finish_page_flip(struct drm_device *dev, int pipe);
 void intel_finish_page_flip_plane(struct drm_device *dev, int plane);
+void intel_check_page_flip(struct drm_device *dev, int pipe);
 
 /* shared dpll functions */
 struct intel_shared_dpll *intel_crtc_to_shared_dpll(struct intel_crtc *crtc);
@@ -882,6 +897,7 @@ void hsw_enable_pc8(struct drm_i915_private *dev_priv);
 void hsw_disable_pc8(struct drm_i915_private *dev_priv);
 void intel_dp_get_m_n(struct intel_crtc *crtc,
 		      struct intel_crtc_config *pipe_config);
+void intel_dp_set_m_n(struct intel_crtc *crtc);
 int intel_dotclock_calculate(int link_freq, const struct intel_link_m_n *m_n);
 void
 ironlake_check_encoder_dotclock(const struct intel_crtc_config *pipe_config,
@@ -896,7 +912,7 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 				 struct intel_crtc_config *pipe_config);
 int intel_format_to_fourcc(int format);
 void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc);
-
+void intel_modeset_preclose(struct drm_device *dev, struct drm_file *file);
 
 /* intel_dp.c */
 void intel_dp_init(struct drm_device *dev, int output_reg, enum port port);
@@ -935,6 +951,7 @@ void intel_dp_mst_suspend(struct drm_device *dev);
 void intel_dp_mst_resume(struct drm_device *dev);
 int intel_dp_max_link_bw(struct intel_dp *intel_dp);
 void intel_dp_hot_plug(struct intel_encoder *intel_encoder);
+void vlv_power_sequencer_reset(struct drm_i915_private *dev_priv);
 /* intel_dp_mst.c */
 int intel_dp_mst_encoder_init(struct intel_digital_port *intel_dig_port, int conn_id);
 void intel_dp_mst_encoder_cleanup(struct intel_digital_port *intel_dig_port);
@@ -949,9 +966,9 @@ void intel_dvo_init(struct drm_device *dev);
 /* legacy fbdev emulation in intel_fbdev.c */
 #ifdef CONFIG_DRM_I915_FBDEV
 extern int intel_fbdev_init(struct drm_device *dev);
-extern void intel_fbdev_initial_config(struct drm_device *dev);
+extern void intel_fbdev_initial_config(void *data, async_cookie_t cookie);
 extern void intel_fbdev_fini(struct drm_device *dev);
-extern void intel_fbdev_set_suspend(struct drm_device *dev, int state);
+extern void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous);
 extern void intel_fbdev_output_poll_changed(struct drm_device *dev);
 extern void intel_fbdev_restore_mode(struct drm_device *dev);
 #else
@@ -960,7 +977,7 @@ static inline int intel_fbdev_init(struct drm_device *dev)
 	return 0;
 }
 
-static inline void intel_fbdev_initial_config(struct drm_device *dev)
+static inline void intel_fbdev_initial_config(void *data, async_cookie_t cookie)
 {
 }
 
@@ -968,7 +985,7 @@ static inline void intel_fbdev_fini(struct drm_device *dev)
 {
 }
 
-static inline void intel_fbdev_set_suspend(struct drm_device *dev, int state)
+static inline void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous)
 {
 }
 
@@ -1091,7 +1108,10 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob);
 int intel_plane_init(struct drm_device *dev, enum pipe pipe, int plane);
 void intel_flush_primary_plane(struct drm_i915_private *dev_priv,
 			       enum plane plane);
-void intel_plane_restore(struct drm_plane *plane);
+int intel_plane_set_property(struct drm_plane *plane,
+			     struct drm_property *prop,
+			     uint64_t val);
+int intel_plane_restore(struct drm_plane *plane);
 void intel_plane_disable(struct drm_plane *plane);
 int intel_sprite_set_colorkey(struct drm_device *dev, void *data,
 			      struct drm_file *file_priv);
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index 670c29a7b5dd..5bd9e09ad3c5 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -184,7 +184,7 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder)
 
 	/* update the hw state for DPLL */
 	intel_crtc->config.dpll_hw_state.dpll = DPLL_INTEGRATED_CLOCK_VLV |
-						DPLL_REFA_CLK_ENABLE_VLV;
+		DPLL_REFA_CLK_ENABLE_VLV;
 
 	tmp = I915_READ(DSPCLK_GATE_D);
 	tmp |= DPOUNIT_CLOCK_GATE_DISABLE;
@@ -259,8 +259,8 @@ static void intel_dsi_disable(struct intel_encoder *encoder)
 	temp = I915_READ(MIPI_CTRL(pipe));
 	temp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
 	I915_WRITE(MIPI_CTRL(pipe), temp |
-			intel_dsi->escape_clk_div <<
-			ESCAPE_CLOCK_DIVIDER_SHIFT);
+		   intel_dsi->escape_clk_div <<
+		   ESCAPE_CLOCK_DIVIDER_SHIFT);
 
 	I915_WRITE(MIPI_EOT_DISABLE(pipe), CLOCKSTOP);
 
@@ -297,7 +297,7 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 	usleep_range(2000, 2500);
 
 	if (wait_for(((I915_READ(MIPI_PORT_CTRL(pipe)) & AFE_LATCHOUT)
-					== 0x00000), 30))
+		      == 0x00000), 30))
 		DRM_ERROR("DSI LP not going Low\n");
 
 	val = I915_READ(MIPI_PORT_CTRL(pipe));
@@ -423,9 +423,11 @@ static u16 txclkesc(u32 divider, unsigned int us)
 }
 
 /* return pixels in terms of txbyteclkhs */
-static u16 txbyteclkhs(u16 pixels, int bpp, int lane_count)
+static u16 txbyteclkhs(u16 pixels, int bpp, int lane_count,
+		       u16 burst_mode_ratio)
 {
-	return DIV_ROUND_UP(DIV_ROUND_UP(pixels * bpp, 8), lane_count);
+	return DIV_ROUND_UP(DIV_ROUND_UP(pixels * bpp * burst_mode_ratio,
+					 8 * 100), lane_count);
 }
 
 static void set_dsi_timings(struct drm_encoder *encoder,
@@ -451,10 +453,12 @@ static void set_dsi_timings(struct drm_encoder *encoder,
 	vbp = mode->vtotal - mode->vsync_end;
 
 	/* horizontal values are in terms of high speed byte clock */
-	hactive = txbyteclkhs(hactive, bpp, lane_count);
-	hfp = txbyteclkhs(hfp, bpp, lane_count);
-	hsync = txbyteclkhs(hsync, bpp, lane_count);
-	hbp = txbyteclkhs(hbp, bpp, lane_count);
+	hactive = txbyteclkhs(hactive, bpp, lane_count,
+			      intel_dsi->burst_mode_ratio);
+	hfp = txbyteclkhs(hfp, bpp, lane_count, intel_dsi->burst_mode_ratio);
+	hsync = txbyteclkhs(hsync, bpp, lane_count,
+			    intel_dsi->burst_mode_ratio);
+	hbp = txbyteclkhs(hbp, bpp, lane_count, intel_dsi->burst_mode_ratio);
 
 	I915_WRITE(MIPI_HACTIVE_AREA_COUNT(pipe), hactive);
 	I915_WRITE(MIPI_HFP_COUNT(pipe), hfp);
@@ -541,12 +545,14 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 	    intel_dsi->video_mode_format == VIDEO_MODE_BURST) {
 		I915_WRITE(MIPI_HS_TX_TIMEOUT(pipe),
 			   txbyteclkhs(adjusted_mode->htotal, bpp,
-				       intel_dsi->lane_count) + 1);
+				       intel_dsi->lane_count,
+				       intel_dsi->burst_mode_ratio) + 1);
 	} else {
 		I915_WRITE(MIPI_HS_TX_TIMEOUT(pipe),
 			   txbyteclkhs(adjusted_mode->vtotal *
 				       adjusted_mode->htotal,
-				       bpp, intel_dsi->lane_count) + 1);
+				       bpp, intel_dsi->lane_count,
+				       intel_dsi->burst_mode_ratio) + 1);
 	}
 	I915_WRITE(MIPI_LP_RX_TIMEOUT(pipe), intel_dsi->lp_rx_timeout);
 	I915_WRITE(MIPI_TURN_AROUND_TIMEOUT(pipe), intel_dsi->turn_arnd_val);
@@ -576,7 +582,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 	 * XXX: write MIPI_STOP_STATE_STALL?
 	 */
 	I915_WRITE(MIPI_HIGH_LOW_SWITCH_COUNT(pipe),
-						intel_dsi->hs_to_lp_count);
+		   intel_dsi->hs_to_lp_count);
 
 	/* XXX: low power clock equivalence in terms of byte clock. the number
 	 * of byte clocks occupied in one low power clock. based on txbyteclkhs
@@ -601,10 +607,10 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 		 * 64 like 1366 x 768. Enable RANDOM resolution support for such
 		 * panels by default */
 		I915_WRITE(MIPI_VIDEO_MODE_FORMAT(pipe),
-				intel_dsi->video_frmt_cfg_bits |
-				intel_dsi->video_mode_format |
-				IP_TG_CONFIG |
-				RANDOM_DPI_DISPLAY_RESOLUTION);
+			   intel_dsi->video_frmt_cfg_bits |
+			   intel_dsi->video_mode_format |
+			   IP_TG_CONFIG |
+			   RANDOM_DPI_DISPLAY_RESOLUTION);
 }
 
 static void intel_dsi_pre_pll_enable(struct intel_encoder *encoder)
diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h
index fd51867fd0d3..657eb5c1b9d8 100644
--- a/drivers/gpu/drm/i915/intel_dsi.h
+++ b/drivers/gpu/drm/i915/intel_dsi.h
@@ -116,6 +116,8 @@ struct intel_dsi {
 	u16 clk_hs_to_lp_count;
 
 	u16 init_count;
+	u32 pclk;
+	u16 burst_mode_ratio;
 
 	/* all delays in ms */
 	u16 backlight_off_delay;
diff --git a/drivers/gpu/drm/i915/intel_dsi_cmd.c b/drivers/gpu/drm/i915/intel_dsi_cmd.c
index 7f1430ac8543..f4767fd2ebeb 100644
--- a/drivers/gpu/drm/i915/intel_dsi_cmd.c
+++ b/drivers/gpu/drm/i915/intel_dsi_cmd.c
@@ -430,7 +430,7 @@ void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi)
 	u32 mask;
 
 	mask = LP_CTRL_FIFO_EMPTY | HS_CTRL_FIFO_EMPTY |
-					LP_DATA_FIFO_EMPTY | HS_DATA_FIFO_EMPTY;
+		LP_DATA_FIFO_EMPTY | HS_DATA_FIFO_EMPTY;
 
 	if (wait_for((I915_READ(MIPI_GEN_FIFO_STAT(pipe)) & mask) == mask, 100))
 		DRM_ERROR("DPI FIFOs are not empty\n");
diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
index 47c7584a4aa0..f6bdd44069ce 100644
--- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
@@ -271,6 +271,8 @@ static bool generic_init(struct intel_dsi_device *dsi)
 	u32 ths_prepare_ns, tclk_trail_ns;
 	u32 tclk_prepare_clkzero, ths_prepare_hszero;
 	u32 lp_to_hs_switch, hs_to_lp_switch;
+	u32 pclk, computed_ddr;
+	u16 burst_mode_ratio;
 
 	DRM_DEBUG_KMS("\n");
 
@@ -284,8 +286,6 @@ static bool generic_init(struct intel_dsi_device *dsi)
 	else if (intel_dsi->pixel_format == VID_MODE_FORMAT_RGB565)
 		bits_per_pixel = 16;
 
-	bitrate = (mode->clock * bits_per_pixel) / intel_dsi->lane_count;
-
 	intel_dsi->operation_mode = mipi_config->is_cmd_mode;
 	intel_dsi->video_mode_format = mipi_config->video_transfer_mode;
 	intel_dsi->escape_clk_div = mipi_config->byte_clk_sel;
@@ -297,6 +297,40 @@ static bool generic_init(struct intel_dsi_device *dsi)
 	intel_dsi->video_frmt_cfg_bits =
 		mipi_config->bta_enabled ? DISABLE_VIDEO_BTA : 0;
 
+	pclk = mode->clock;
+
+	/* Burst Mode Ratio
+	 * Target ddr frequency from VBT / non burst ddr freq
+	 * multiply by 100 to preserve remainder
+	 */
+	if (intel_dsi->video_mode_format == VIDEO_MODE_BURST) {
+		if (mipi_config->target_burst_mode_freq) {
+			computed_ddr =
+				(pclk * bits_per_pixel) / intel_dsi->lane_count;
+
+			if (mipi_config->target_burst_mode_freq <
+								computed_ddr) {
+				DRM_ERROR("Burst mode freq is less than computed\n");
+				return false;
+			}
+
+			burst_mode_ratio = DIV_ROUND_UP(
+				mipi_config->target_burst_mode_freq * 100,
+				computed_ddr);
+
+			pclk = DIV_ROUND_UP(pclk * burst_mode_ratio, 100);
+		} else {
+			DRM_ERROR("Burst mode target is not set\n");
+			return false;
+		}
+	} else
+		burst_mode_ratio = 100;
+
+	intel_dsi->burst_mode_ratio = burst_mode_ratio;
+	intel_dsi->pclk = pclk;
+
+	bitrate = (pclk * bits_per_pixel) / intel_dsi->lane_count;
+
 	switch (intel_dsi->escape_clk_div) {
 	case 0:
 		tlpx_ns = 50;
diff --git a/drivers/gpu/drm/i915/intel_dsi_pll.c b/drivers/gpu/drm/i915/intel_dsi_pll.c
index d8bb1ea2f0da..fa7a6ca34cd6 100644
--- a/drivers/gpu/drm/i915/intel_dsi_pll.c
+++ b/drivers/gpu/drm/i915/intel_dsi_pll.c
@@ -134,8 +134,7 @@ static u32 dsi_rr_formula(const struct drm_display_mode *mode,
 #else
 
 /* Get DSI clock from pixel clock */
-static u32 dsi_clk_from_pclk(const struct drm_display_mode *mode,
-			  int pixel_format, int lane_count)
+static u32 dsi_clk_from_pclk(u32 pclk, int pixel_format, int lane_count)
 {
 	u32 dsi_clk_khz;
 	u32 bpp;
@@ -156,7 +155,7 @@ static u32 dsi_clk_from_pclk(const struct drm_display_mode *mode,
 
 	/* DSI data rate = pixel clock * bits per pixel / lane count
 	   pixel clock is converted from KHz to Hz */
-	dsi_clk_khz = DIV_ROUND_CLOSEST(mode->clock * bpp, lane_count);
+	dsi_clk_khz = DIV_ROUND_CLOSEST(pclk * bpp, lane_count);
 
 	return dsi_clk_khz;
 }
@@ -191,7 +190,7 @@ static int dsi_calc_mnp(u32 dsi_clk, struct dsi_mnp *dsi_mnp)
 	for (m = 62; m <= 92; m++) {
 		for (p = 2; p <= 6; p++) {
 			/* Find the optimal m and p divisors
-			with minimal error +/- the required clock */
+			   with minimal error +/- the required clock */
 			calc_dsi_clk = (m * ref_clk) / p;
 			if (calc_dsi_clk == target_dsi_clk) {
 				calc_m = m;
@@ -228,15 +227,13 @@ static int dsi_calc_mnp(u32 dsi_clk, struct dsi_mnp *dsi_mnp)
 static void vlv_configure_dsi_pll(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
-	const struct drm_display_mode *mode = &intel_crtc->config.adjusted_mode;
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
 	int ret;
 	struct dsi_mnp dsi_mnp;
 	u32 dsi_clk;
 
-	dsi_clk = dsi_clk_from_pclk(mode, intel_dsi->pixel_format,
-						intel_dsi->lane_count);
+	dsi_clk = dsi_clk_from_pclk(intel_dsi->pclk, intel_dsi->pixel_format,
+				    intel_dsi->lane_count);
 
 	ret = dsi_calc_mnp(dsi_clk, &dsi_mnp);
 	if (ret) {
@@ -318,8 +315,8 @@ static void assert_bpp_mismatch(int pixel_format, int pipe_bpp)
 	}
 
 	WARN(bpp != pipe_bpp,
-		"bpp match assertion failure (expected %d, current %d)\n",
-		bpp, pipe_bpp);
+	     "bpp match assertion failure (expected %d, current %d)\n",
+	     bpp, pipe_bpp);
 }
 
 u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp)
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 56b47d2ffaf7..e40e3df33517 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -85,7 +85,7 @@ static const struct intel_dvo_device intel_dvo_devices[] = {
 	{
 	        .type = INTEL_DVO_CHIP_TMDS,
 		.name = "ns2501",
-		.dvo_reg = DVOC,
+		.dvo_reg = DVOB,
 		.slave_addr = NS2501_ADDR,
 		.dev_ops = &ns2501_ops,
        }
@@ -185,12 +185,13 @@ static void intel_enable_dvo(struct intel_encoder *encoder)
 	u32 dvo_reg = intel_dvo->dev.dvo_reg;
 	u32 temp = I915_READ(dvo_reg);
 
-	I915_WRITE(dvo_reg, temp | DVO_ENABLE);
-	I915_READ(dvo_reg);
 	intel_dvo->dev.dev_ops->mode_set(&intel_dvo->dev,
 					 &crtc->config.requested_mode,
 					 &crtc->config.adjusted_mode);
 
+	I915_WRITE(dvo_reg, temp | DVO_ENABLE);
+	I915_READ(dvo_reg);
+
 	intel_dvo->dev.dev_ops->dpms(&intel_dvo->dev, true);
 }
 
@@ -226,10 +227,6 @@ static void intel_dvo_dpms(struct drm_connector *connector, int mode)
 
 		intel_crtc_update_dpms(crtc);
 
-		intel_dvo->dev.dev_ops->mode_set(&intel_dvo->dev,
-						 &config->requested_mode,
-						 &config->adjusted_mode);
-
 		intel_dvo->dev.dev_ops->dpms(&intel_dvo->dev, true);
 	} else {
 		intel_dvo->dev.dev_ops->dpms(&intel_dvo->dev, false);
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index f475414671d8..9b584f3fbb99 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -24,8 +24,10 @@
  *     David Airlie
  */
 
+#include <linux/async.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/console.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/mm.h>
@@ -331,24 +333,6 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 	int num_connectors_enabled = 0;
 	int num_connectors_detected = 0;
 
-	/*
-	 * If the user specified any force options, just bail here
-	 * and use that config.
-	 */
-	for (i = 0; i < fb_helper->connector_count; i++) {
-		struct drm_fb_helper_connector *fb_conn;
-		struct drm_connector *connector;
-
-		fb_conn = fb_helper->connector_info[i];
-		connector = fb_conn->connector;
-
-		if (!enabled[i])
-			continue;
-
-		if (connector->force != DRM_FORCE_UNSPECIFIED)
-			return false;
-	}
-
 	save_enabled = kcalloc(dev->mode_config.num_connector, sizeof(bool),
 			       GFP_KERNEL);
 	if (!save_enabled)
@@ -374,8 +358,18 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 			continue;
 		}
 
+		if (connector->force == DRM_FORCE_OFF) {
+			DRM_DEBUG_KMS("connector %s is disabled by user, skipping\n",
+				      connector->name);
+			enabled[i] = false;
+			continue;
+		}
+
 		encoder = connector->encoder;
 		if (!encoder || WARN_ON(!encoder->crtc)) {
+			if (connector->force > DRM_FORCE_OFF)
+				goto bail;
+
 			DRM_DEBUG_KMS("connector %s has no encoder or crtc, skipping\n",
 				      connector->name);
 			enabled[i] = false;
@@ -394,8 +388,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 		for (j = 0; j < fb_helper->connector_count; j++) {
 			if (crtcs[j] == new_crtc) {
 				DRM_DEBUG_KMS("fallback: cloned configuration\n");
-				fallback = true;
-				goto out;
+				goto bail;
 			}
 		}
 
@@ -466,8 +459,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 		fallback = true;
 	}
 
-out:
 	if (fallback) {
+bail:
 		DRM_DEBUG_KMS("Not using firmware configuration\n");
 		memcpy(enabled, save_enabled, dev->mode_config.num_connector);
 		kfree(save_enabled);
@@ -636,6 +629,15 @@ out:
 	return false;
 }
 
+static void intel_fbdev_suspend_worker(struct work_struct *work)
+{
+	intel_fbdev_set_suspend(container_of(work,
+					     struct drm_i915_private,
+					     fbdev_suspend_work)->dev,
+				FBINFO_STATE_RUNNING,
+				true);
+}
+
 int intel_fbdev_init(struct drm_device *dev)
 {
 	struct intel_fbdev *ifbdev;
@@ -662,14 +664,16 @@ int intel_fbdev_init(struct drm_device *dev)
 	}
 
 	dev_priv->fbdev = ifbdev;
+	INIT_WORK(&dev_priv->fbdev_suspend_work, intel_fbdev_suspend_worker);
+
 	drm_fb_helper_single_add_all_connectors(&ifbdev->helper);
 
 	return 0;
 }
 
-void intel_fbdev_initial_config(struct drm_device *dev)
+void intel_fbdev_initial_config(void *data, async_cookie_t cookie)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_private *dev_priv = data;
 	struct intel_fbdev *ifbdev = dev_priv->fbdev;
 
 	/* Due to peculiar init order wrt to hpd handling this is separate. */
@@ -682,12 +686,15 @@ void intel_fbdev_fini(struct drm_device *dev)
 	if (!dev_priv->fbdev)
 		return;
 
+	flush_work(&dev_priv->fbdev_suspend_work);
+
+	async_synchronize_full();
 	intel_fbdev_destroy(dev, dev_priv->fbdev);
 	kfree(dev_priv->fbdev);
 	dev_priv->fbdev = NULL;
 }
 
-void intel_fbdev_set_suspend(struct drm_device *dev, int state)
+void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_fbdev *ifbdev = dev_priv->fbdev;
@@ -698,6 +705,33 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state)
 
 	info = ifbdev->helper.fbdev;
 
+	if (synchronous) {
+		/* Flush any pending work to turn the console on, and then
+		 * wait to turn it off. It must be synchronous as we are
+		 * about to suspend or unload the driver.
+		 *
+		 * Note that from within the work-handler, we cannot flush
+		 * ourselves, so only flush outstanding work upon suspend!
+		 */
+		if (state != FBINFO_STATE_RUNNING)
+			flush_work(&dev_priv->fbdev_suspend_work);
+		console_lock();
+	} else {
+		/*
+		 * The console lock can be pretty contented on resume due
+		 * to all the printk activity.  Try to keep it out of the hot
+		 * path of resume if possible.
+		 */
+		WARN_ON(state != FBINFO_STATE_RUNNING);
+		if (!console_trylock()) {
+			/* Don't block our own workqueue as this can
+			 * be run in parallel with other i915.ko tasks.
+			 */
+			schedule_work(&dev_priv->fbdev_suspend_work);
+			return;
+		}
+	}
+
 	/* On resume from hibernation: If the object is shmemfs backed, it has
 	 * been restored from swap. If the object is stolen however, it will be
 	 * full of whatever garbage was left in there.
@@ -706,6 +740,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state)
 		memset_io(info->screen_base, 0, info->screen_size);
 
 	fb_set_suspend(info, state);
+	console_unlock();
 }
 
 void intel_fbdev_output_poll_changed(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 5a9de21637b7..29ec1535992d 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -869,10 +869,15 @@ static enum drm_mode_status
 intel_hdmi_mode_valid(struct drm_connector *connector,
 		      struct drm_display_mode *mode)
 {
-	if (mode->clock > hdmi_portclock_limit(intel_attached_hdmi(connector),
-					       true))
+	int clock = mode->clock;
+
+	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
+		clock *= 2;
+
+	if (clock > hdmi_portclock_limit(intel_attached_hdmi(connector),
+					 true))
 		return MODE_CLOCK_HIGH;
-	if (mode->clock < 20000)
+	if (clock < 20000)
 		return MODE_CLOCK_LOW;
 
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
@@ -890,7 +895,7 @@ static bool hdmi_12bpc_possible(struct intel_crtc *crtc)
 	if (HAS_GMCH_DISPLAY(dev))
 		return false;
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		if (encoder->new_crtc != crtc)
 			continue;
 
@@ -926,6 +931,10 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 			intel_hdmi->color_range = 0;
 	}
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) {
+		pipe_config->pixel_multiplier = 2;
+	}
+
 	if (intel_hdmi->color_range)
 		pipe_config->limited_color_range = true;
 
@@ -967,104 +976,117 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static enum drm_connector_status
-intel_hdmi_detect(struct drm_connector *connector, bool force)
+static void
+intel_hdmi_unset_edid(struct drm_connector *connector)
 {
-	struct drm_device *dev = connector->dev;
 	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
-	struct intel_digital_port *intel_dig_port =
-		hdmi_to_dig_port(intel_hdmi);
-	struct intel_encoder *intel_encoder = &intel_dig_port->base;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct edid *edid;
-	enum intel_display_power_domain power_domain;
-	enum drm_connector_status status = connector_status_disconnected;
 
-	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, connector->name);
+	intel_hdmi->has_hdmi_sink = false;
+	intel_hdmi->has_audio = false;
+	intel_hdmi->rgb_quant_range_selectable = false;
+
+	kfree(to_intel_connector(connector)->detect_edid);
+	to_intel_connector(connector)->detect_edid = NULL;
+}
+
+static bool
+intel_hdmi_set_edid(struct drm_connector *connector)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
+	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	struct intel_encoder *intel_encoder =
+		&hdmi_to_dig_port(intel_hdmi)->base;
+	enum intel_display_power_domain power_domain;
+	struct edid *edid;
+	bool connected = false;
 
 	power_domain = intel_display_port_power_domain(intel_encoder);
 	intel_display_power_get(dev_priv, power_domain);
 
-	intel_hdmi->has_hdmi_sink = false;
-	intel_hdmi->has_audio = false;
-	intel_hdmi->rgb_quant_range_selectable = false;
 	edid = drm_get_edid(connector,
 			    intel_gmbus_get_adapter(dev_priv,
 						    intel_hdmi->ddc_bus));
 
-	if (edid) {
-		if (edid->input & DRM_EDID_INPUT_DIGITAL) {
-			status = connector_status_connected;
-			if (intel_hdmi->force_audio != HDMI_AUDIO_OFF_DVI)
-				intel_hdmi->has_hdmi_sink =
-						drm_detect_hdmi_monitor(edid);
-			intel_hdmi->has_audio = drm_detect_monitor_audio(edid);
-			intel_hdmi->rgb_quant_range_selectable =
-				drm_rgb_quant_range_selectable(edid);
-		}
-		kfree(edid);
-	}
+	intel_display_power_put(dev_priv, power_domain);
+
+	to_intel_connector(connector)->detect_edid = edid;
+	if (edid && edid->input & DRM_EDID_INPUT_DIGITAL) {
+		intel_hdmi->rgb_quant_range_selectable =
+			drm_rgb_quant_range_selectable(edid);
 
-	if (status == connector_status_connected) {
+		intel_hdmi->has_audio = drm_detect_monitor_audio(edid);
 		if (intel_hdmi->force_audio != HDMI_AUDIO_AUTO)
 			intel_hdmi->has_audio =
-				(intel_hdmi->force_audio == HDMI_AUDIO_ON);
-		intel_encoder->type = INTEL_OUTPUT_HDMI;
+				intel_hdmi->force_audio == HDMI_AUDIO_ON;
+
+		if (intel_hdmi->force_audio != HDMI_AUDIO_OFF_DVI)
+			intel_hdmi->has_hdmi_sink =
+				drm_detect_hdmi_monitor(edid);
+
+		connected = true;
 	}
 
-	intel_display_power_put(dev_priv, power_domain);
+	return connected;
+}
+
+static enum drm_connector_status
+intel_hdmi_detect(struct drm_connector *connector, bool force)
+{
+	enum drm_connector_status status;
+
+	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
+		      connector->base.id, connector->name);
+
+	intel_hdmi_unset_edid(connector);
+
+	if (intel_hdmi_set_edid(connector)) {
+		struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+
+		hdmi_to_dig_port(intel_hdmi)->base.type = INTEL_OUTPUT_HDMI;
+		status = connector_status_connected;
+	} else
+		status = connector_status_disconnected;
 
 	return status;
 }
 
-static int intel_hdmi_get_modes(struct drm_connector *connector)
+static void
+intel_hdmi_force(struct drm_connector *connector)
 {
-	struct intel_encoder *intel_encoder = intel_attached_encoder(connector);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&intel_encoder->base);
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
-	enum intel_display_power_domain power_domain;
-	int ret;
+	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
 
-	/* We should parse the EDID data and find out if it's an HDMI sink so
-	 * we can send audio to it.
-	 */
+	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
+		      connector->base.id, connector->name);
 
-	power_domain = intel_display_port_power_domain(intel_encoder);
-	intel_display_power_get(dev_priv, power_domain);
+	intel_hdmi_unset_edid(connector);
 
-	ret = intel_ddc_get_modes(connector,
-				   intel_gmbus_get_adapter(dev_priv,
-							   intel_hdmi->ddc_bus));
+	if (connector->status != connector_status_connected)
+		return;
 
-	intel_display_power_put(dev_priv, power_domain);
+	intel_hdmi_set_edid(connector);
+	hdmi_to_dig_port(intel_hdmi)->base.type = INTEL_OUTPUT_HDMI;
+}
 
-	return ret;
+static int intel_hdmi_get_modes(struct drm_connector *connector)
+{
+	struct edid *edid;
+
+	edid = to_intel_connector(connector)->detect_edid;
+	if (edid == NULL)
+		return 0;
+
+	return intel_connector_update_modes(connector, edid);
 }
 
 static bool
 intel_hdmi_detect_audio(struct drm_connector *connector)
 {
-	struct intel_encoder *intel_encoder = intel_attached_encoder(connector);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&intel_encoder->base);
-	struct drm_i915_private *dev_priv = connector->dev->dev_private;
-	enum intel_display_power_domain power_domain;
-	struct edid *edid;
 	bool has_audio = false;
+	struct edid *edid;
 
-	power_domain = intel_display_port_power_domain(intel_encoder);
-	intel_display_power_get(dev_priv, power_domain);
-
-	edid = drm_get_edid(connector,
-			    intel_gmbus_get_adapter(dev_priv,
-						    intel_hdmi->ddc_bus));
-	if (edid) {
-		if (edid->input & DRM_EDID_INPUT_DIGITAL)
-			has_audio = drm_detect_monitor_audio(edid);
-		kfree(edid);
-	}
-
-	intel_display_power_put(dev_priv, power_domain);
+	edid = to_intel_connector(connector)->detect_edid;
+	if (edid && edid->input & DRM_EDID_INPUT_DIGITAL)
+		has_audio = drm_detect_monitor_audio(edid);
 
 	return has_audio;
 }
@@ -1265,6 +1287,8 @@ static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 	enum pipe pipe = intel_crtc->pipe;
 	u32 val;
 
+	intel_hdmi_prepare(encoder);
+
 	mutex_lock(&dev_priv->dpio_lock);
 
 	/* program left/right clock distribution */
@@ -1434,8 +1458,8 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder)
 
 	for (i = 0; i < 4; i++) {
 		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i));
-		val &= ~DPIO_SWING_MARGIN_MASK;
-		val |= 102 << DPIO_SWING_MARGIN_SHIFT;
+		val &= ~DPIO_SWING_MARGIN000_MASK;
+		val |= 102 << DPIO_SWING_MARGIN000_SHIFT;
 		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val);
 	}
 
@@ -1482,6 +1506,7 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder)
 
 static void intel_hdmi_destroy(struct drm_connector *connector)
 {
+	kfree(to_intel_connector(connector)->detect_edid);
 	drm_connector_cleanup(connector);
 	kfree(connector);
 }
@@ -1489,6 +1514,7 @@ static void intel_hdmi_destroy(struct drm_connector *connector)
 static const struct drm_connector_funcs intel_hdmi_connector_funcs = {
 	.dpms = intel_connector_dpms,
 	.detect = intel_hdmi_detect,
+	.force = intel_hdmi_force,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.set_property = intel_hdmi_set_property,
 	.destroy = intel_hdmi_destroy,
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
new file mode 100644
index 000000000000..bafd38b5703e
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -0,0 +1,1766 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ *    Ben Widawsky <ben@bwidawsk.net>
+ *    Michel Thierry <michel.thierry@intel.com>
+ *    Thomas Daniel <thomas.daniel@intel.com>
+ *    Oscar Mateo <oscar.mateo@intel.com>
+ *
+ */
+
+/**
+ * DOC: Logical Rings, Logical Ring Contexts and Execlists
+ *
+ * Motivation:
+ * GEN8 brings an expansion of the HW contexts: "Logical Ring Contexts".
+ * These expanded contexts enable a number of new abilities, especially
+ * "Execlists" (also implemented in this file).
+ *
+ * One of the main differences with the legacy HW contexts is that logical
+ * ring contexts incorporate many more things to the context's state, like
+ * PDPs or ringbuffer control registers:
+ *
+ * The reason why PDPs are included in the context is straightforward: as
+ * PPGTTs (per-process GTTs) are actually per-context, having the PDPs
+ * contained there mean you don't need to do a ppgtt->switch_mm yourself,
+ * instead, the GPU will do it for you on the context switch.
+ *
+ * But, what about the ringbuffer control registers (head, tail, etc..)?
+ * shouldn't we just need a set of those per engine command streamer? This is
+ * where the name "Logical Rings" starts to make sense: by virtualizing the
+ * rings, the engine cs shifts to a new "ring buffer" with every context
+ * switch. When you want to submit a workload to the GPU you: A) choose your
+ * context, B) find its appropriate virtualized ring, C) write commands to it
+ * and then, finally, D) tell the GPU to switch to that context.
+ *
+ * Instead of the legacy MI_SET_CONTEXT, the way you tell the GPU to switch
+ * to a contexts is via a context execution list, ergo "Execlists".
+ *
+ * LRC implementation:
+ * Regarding the creation of contexts, we have:
+ *
+ * - One global default context.
+ * - One local default context for each opened fd.
+ * - One local extra context for each context create ioctl call.
+ *
+ * Now that ringbuffers belong per-context (and not per-engine, like before)
+ * and that contexts are uniquely tied to a given engine (and not reusable,
+ * like before) we need:
+ *
+ * - One ringbuffer per-engine inside each context.
+ * - One backing object per-engine inside each context.
+ *
+ * The global default context starts its life with these new objects fully
+ * allocated and populated. The local default context for each opened fd is
+ * more complex, because we don't know at creation time which engine is going
+ * to use them. To handle this, we have implemented a deferred creation of LR
+ * contexts:
+ *
+ * The local context starts its life as a hollow or blank holder, that only
+ * gets populated for a given engine once we receive an execbuffer. If later
+ * on we receive another execbuffer ioctl for the same context but a different
+ * engine, we allocate/populate a new ringbuffer and context backing object and
+ * so on.
+ *
+ * Finally, regarding local contexts created using the ioctl call: as they are
+ * only allowed with the render ring, we can allocate & populate them right
+ * away (no need to defer anything, at least for now).
+ *
+ * Execlists implementation:
+ * Execlists are the new method by which, on gen8+ hardware, workloads are
+ * submitted for execution (as opposed to the legacy, ringbuffer-based, method).
+ * This method works as follows:
+ *
+ * When a request is committed, its commands (the BB start and any leading or
+ * trailing commands, like the seqno breadcrumbs) are placed in the ringbuffer
+ * for the appropriate context. The tail pointer in the hardware context is not
+ * updated at this time, but instead, kept by the driver in the ringbuffer
+ * structure. A structure representing this request is added to a request queue
+ * for the appropriate engine: this structure contains a copy of the context's
+ * tail after the request was written to the ring buffer and a pointer to the
+ * context itself.
+ *
+ * If the engine's request queue was empty before the request was added, the
+ * queue is processed immediately. Otherwise the queue will be processed during
+ * a context switch interrupt. In any case, elements on the queue will get sent
+ * (in pairs) to the GPU's ExecLists Submit Port (ELSP, for short) with a
+ * globally unique 20-bits submission ID.
+ *
+ * When execution of a request completes, the GPU updates the context status
+ * buffer with a context complete event and generates a context switch interrupt.
+ * During the interrupt handling, the driver examines the events in the buffer:
+ * for each context complete event, if the announced ID matches that on the head
+ * of the request queue, then that request is retired and removed from the queue.
+ *
+ * After processing, if any requests were retired and the queue is not empty
+ * then a new execution list can be submitted. The two requests at the front of
+ * the queue are next to be submitted but since a context may not occur twice in
+ * an execution list, if subsequent requests have the same ID as the first then
+ * the two requests must be combined. This is done simply by discarding requests
+ * at the head of the queue until either only one requests is left (in which case
+ * we use a NULL second context) or the first two requests have unique IDs.
+ *
+ * By always executing the first two requests in the queue the driver ensures
+ * that the GPU is kept as busy as possible. In the case where a single context
+ * completes but a second context is still executing, the request for this second
+ * context will be at the head of the queue when we remove the first one. This
+ * request will then be resubmitted along with a new request for a different context,
+ * which will cause the hardware to continue executing the second request and queue
+ * the new request (the GPU detects the condition of a context getting preempted
+ * with the same context and optimizes the context switch flow by not doing
+ * preemption, but just sampling the new tail pointer).
+ *
+ */
+
+#include <drm/drmP.h>
+#include <drm/i915_drm.h>
+#include "i915_drv.h"
+
+#define GEN8_LR_CONTEXT_RENDER_SIZE (20 * PAGE_SIZE)
+#define GEN8_LR_CONTEXT_OTHER_SIZE (2 * PAGE_SIZE)
+
+#define GEN8_LR_CONTEXT_ALIGN 4096
+
+#define RING_EXECLIST_QFULL		(1 << 0x2)
+#define RING_EXECLIST1_VALID		(1 << 0x3)
+#define RING_EXECLIST0_VALID		(1 << 0x4)
+#define RING_EXECLIST_ACTIVE_STATUS	(3 << 0xE)
+#define RING_EXECLIST1_ACTIVE		(1 << 0x11)
+#define RING_EXECLIST0_ACTIVE		(1 << 0x12)
+
+#define GEN8_CTX_STATUS_IDLE_ACTIVE	(1 << 0)
+#define GEN8_CTX_STATUS_PREEMPTED	(1 << 1)
+#define GEN8_CTX_STATUS_ELEMENT_SWITCH	(1 << 2)
+#define GEN8_CTX_STATUS_ACTIVE_IDLE	(1 << 3)
+#define GEN8_CTX_STATUS_COMPLETE	(1 << 4)
+#define GEN8_CTX_STATUS_LITE_RESTORE	(1 << 15)
+
+#define CTX_LRI_HEADER_0		0x01
+#define CTX_CONTEXT_CONTROL		0x02
+#define CTX_RING_HEAD			0x04
+#define CTX_RING_TAIL			0x06
+#define CTX_RING_BUFFER_START		0x08
+#define CTX_RING_BUFFER_CONTROL		0x0a
+#define CTX_BB_HEAD_U			0x0c
+#define CTX_BB_HEAD_L			0x0e
+#define CTX_BB_STATE			0x10
+#define CTX_SECOND_BB_HEAD_U		0x12
+#define CTX_SECOND_BB_HEAD_L		0x14
+#define CTX_SECOND_BB_STATE		0x16
+#define CTX_BB_PER_CTX_PTR		0x18
+#define CTX_RCS_INDIRECT_CTX		0x1a
+#define CTX_RCS_INDIRECT_CTX_OFFSET	0x1c
+#define CTX_LRI_HEADER_1		0x21
+#define CTX_CTX_TIMESTAMP		0x22
+#define CTX_PDP3_UDW			0x24
+#define CTX_PDP3_LDW			0x26
+#define CTX_PDP2_UDW			0x28
+#define CTX_PDP2_LDW			0x2a
+#define CTX_PDP1_UDW			0x2c
+#define CTX_PDP1_LDW			0x2e
+#define CTX_PDP0_UDW			0x30
+#define CTX_PDP0_LDW			0x32
+#define CTX_LRI_HEADER_2		0x41
+#define CTX_R_PWR_CLK_STATE		0x42
+#define CTX_GPGPU_CSR_BASE_ADDRESS	0x44
+
+#define GEN8_CTX_VALID (1<<0)
+#define GEN8_CTX_FORCE_PD_RESTORE (1<<1)
+#define GEN8_CTX_FORCE_RESTORE (1<<2)
+#define GEN8_CTX_L3LLC_COHERENT (1<<5)
+#define GEN8_CTX_PRIVILEGE (1<<8)
+enum {
+	ADVANCED_CONTEXT = 0,
+	LEGACY_CONTEXT,
+	ADVANCED_AD_CONTEXT,
+	LEGACY_64B_CONTEXT
+};
+#define GEN8_CTX_MODE_SHIFT 3
+enum {
+	FAULT_AND_HANG = 0,
+	FAULT_AND_HALT, /* Debug only */
+	FAULT_AND_STREAM,
+	FAULT_AND_CONTINUE /* Unsupported */
+};
+#define GEN8_CTX_ID_SHIFT 32
+
+/**
+ * intel_sanitize_enable_execlists() - sanitize i915.enable_execlists
+ * @dev: DRM device.
+ * @enable_execlists: value of i915.enable_execlists module parameter.
+ *
+ * Only certain platforms support Execlists (the prerequisites being
+ * support for Logical Ring Contexts and Aliasing PPGTT or better),
+ * and only when enabled via module parameter.
+ *
+ * Return: 1 if Execlists is supported and has to be enabled.
+ */
+int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists)
+{
+	WARN_ON(i915.enable_ppgtt == -1);
+
+	if (enable_execlists == 0)
+		return 0;
+
+	if (HAS_LOGICAL_RING_CONTEXTS(dev) && USES_PPGTT(dev) &&
+	    i915.use_mmio_flip >= 0)
+		return 1;
+
+	return 0;
+}
+
+/**
+ * intel_execlists_ctx_id() - get the Execlists Context ID
+ * @ctx_obj: Logical Ring Context backing object.
+ *
+ * Do not confuse with ctx->id! Unfortunately we have a name overload
+ * here: the old context ID we pass to userspace as a handler so that
+ * they can refer to a context, and the new context ID we pass to the
+ * ELSP so that the GPU can inform us of the context status via
+ * interrupts.
+ *
+ * Return: 20-bits globally unique context ID.
+ */
+u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj)
+{
+	u32 lrca = i915_gem_obj_ggtt_offset(ctx_obj);
+
+	/* LRCA is required to be 4K aligned so the more significant 20 bits
+	 * are globally unique */
+	return lrca >> 12;
+}
+
+static uint64_t execlists_ctx_descriptor(struct drm_i915_gem_object *ctx_obj)
+{
+	uint64_t desc;
+	uint64_t lrca = i915_gem_obj_ggtt_offset(ctx_obj);
+
+	WARN_ON(lrca & 0xFFFFFFFF00000FFFULL);
+
+	desc = GEN8_CTX_VALID;
+	desc |= LEGACY_CONTEXT << GEN8_CTX_MODE_SHIFT;
+	desc |= GEN8_CTX_L3LLC_COHERENT;
+	desc |= GEN8_CTX_PRIVILEGE;
+	desc |= lrca;
+	desc |= (u64)intel_execlists_ctx_id(ctx_obj) << GEN8_CTX_ID_SHIFT;
+
+	/* TODO: WaDisableLiteRestore when we start using semaphore
+	 * signalling between Command Streamers */
+	/* desc |= GEN8_CTX_FORCE_RESTORE; */
+
+	return desc;
+}
+
+static void execlists_elsp_write(struct intel_engine_cs *ring,
+				 struct drm_i915_gem_object *ctx_obj0,
+				 struct drm_i915_gem_object *ctx_obj1)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	uint64_t temp = 0;
+	uint32_t desc[4];
+	unsigned long flags;
+
+	/* XXX: You must always write both descriptors in the order below. */
+	if (ctx_obj1)
+		temp = execlists_ctx_descriptor(ctx_obj1);
+	else
+		temp = 0;
+	desc[1] = (u32)(temp >> 32);
+	desc[0] = (u32)temp;
+
+	temp = execlists_ctx_descriptor(ctx_obj0);
+	desc[3] = (u32)(temp >> 32);
+	desc[2] = (u32)temp;
+
+	/* Set Force Wakeup bit to prevent GT from entering C6 while ELSP writes
+	 * are in progress.
+	 *
+	 * The other problem is that we can't just call gen6_gt_force_wake_get()
+	 * because that function calls intel_runtime_pm_get(), which might sleep.
+	 * Instead, we do the runtime_pm_get/put when creating/destroying requests.
+	 */
+	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+	if (IS_CHERRYVIEW(dev_priv->dev)) {
+		if (dev_priv->uncore.fw_rendercount++ == 0)
+			dev_priv->uncore.funcs.force_wake_get(dev_priv,
+							      FORCEWAKE_RENDER);
+		if (dev_priv->uncore.fw_mediacount++ == 0)
+			dev_priv->uncore.funcs.force_wake_get(dev_priv,
+							      FORCEWAKE_MEDIA);
+	} else {
+		if (dev_priv->uncore.forcewake_count++ == 0)
+			dev_priv->uncore.funcs.force_wake_get(dev_priv,
+							      FORCEWAKE_ALL);
+	}
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
+
+	I915_WRITE(RING_ELSP(ring), desc[1]);
+	I915_WRITE(RING_ELSP(ring), desc[0]);
+	I915_WRITE(RING_ELSP(ring), desc[3]);
+	/* The context is automatically loaded after the following */
+	I915_WRITE(RING_ELSP(ring), desc[2]);
+
+	/* ELSP is a wo register, so use another nearby reg for posting instead */
+	POSTING_READ(RING_EXECLIST_STATUS(ring));
+
+	/* Release Force Wakeup (see the big comment above). */
+	spin_lock_irqsave(&dev_priv->uncore.lock, flags);
+	if (IS_CHERRYVIEW(dev_priv->dev)) {
+		if (--dev_priv->uncore.fw_rendercount == 0)
+			dev_priv->uncore.funcs.force_wake_put(dev_priv,
+							      FORCEWAKE_RENDER);
+		if (--dev_priv->uncore.fw_mediacount == 0)
+			dev_priv->uncore.funcs.force_wake_put(dev_priv,
+							      FORCEWAKE_MEDIA);
+	} else {
+		if (--dev_priv->uncore.forcewake_count == 0)
+			dev_priv->uncore.funcs.force_wake_put(dev_priv,
+							      FORCEWAKE_ALL);
+	}
+
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
+}
+
+static int execlists_ctx_write_tail(struct drm_i915_gem_object *ctx_obj, u32 tail)
+{
+	struct page *page;
+	uint32_t *reg_state;
+
+	page = i915_gem_object_get_page(ctx_obj, 1);
+	reg_state = kmap_atomic(page);
+
+	reg_state[CTX_RING_TAIL+1] = tail;
+
+	kunmap_atomic(reg_state);
+
+	return 0;
+}
+
+static int execlists_submit_context(struct intel_engine_cs *ring,
+				    struct intel_context *to0, u32 tail0,
+				    struct intel_context *to1, u32 tail1)
+{
+	struct drm_i915_gem_object *ctx_obj0;
+	struct drm_i915_gem_object *ctx_obj1 = NULL;
+
+	ctx_obj0 = to0->engine[ring->id].state;
+	BUG_ON(!ctx_obj0);
+	WARN_ON(!i915_gem_obj_is_pinned(ctx_obj0));
+
+	execlists_ctx_write_tail(ctx_obj0, tail0);
+
+	if (to1) {
+		ctx_obj1 = to1->engine[ring->id].state;
+		BUG_ON(!ctx_obj1);
+		WARN_ON(!i915_gem_obj_is_pinned(ctx_obj1));
+
+		execlists_ctx_write_tail(ctx_obj1, tail1);
+	}
+
+	execlists_elsp_write(ring, ctx_obj0, ctx_obj1);
+
+	return 0;
+}
+
+static void execlists_context_unqueue(struct intel_engine_cs *ring)
+{
+	struct intel_ctx_submit_request *req0 = NULL, *req1 = NULL;
+	struct intel_ctx_submit_request *cursor = NULL, *tmp = NULL;
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+
+	assert_spin_locked(&ring->execlist_lock);
+
+	if (list_empty(&ring->execlist_queue))
+		return;
+
+	/* Try to read in pairs */
+	list_for_each_entry_safe(cursor, tmp, &ring->execlist_queue,
+				 execlist_link) {
+		if (!req0) {
+			req0 = cursor;
+		} else if (req0->ctx == cursor->ctx) {
+			/* Same ctx: ignore first request, as second request
+			 * will update tail past first request's workload */
+			cursor->elsp_submitted = req0->elsp_submitted;
+			list_del(&req0->execlist_link);
+			queue_work(dev_priv->wq, &req0->work);
+			req0 = cursor;
+		} else {
+			req1 = cursor;
+			break;
+		}
+	}
+
+	WARN_ON(req1 && req1->elsp_submitted);
+
+	WARN_ON(execlists_submit_context(ring, req0->ctx, req0->tail,
+					 req1 ? req1->ctx : NULL,
+					 req1 ? req1->tail : 0));
+
+	req0->elsp_submitted++;
+	if (req1)
+		req1->elsp_submitted++;
+}
+
+static bool execlists_check_remove_request(struct intel_engine_cs *ring,
+					   u32 request_id)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	struct intel_ctx_submit_request *head_req;
+
+	assert_spin_locked(&ring->execlist_lock);
+
+	head_req = list_first_entry_or_null(&ring->execlist_queue,
+					    struct intel_ctx_submit_request,
+					    execlist_link);
+
+	if (head_req != NULL) {
+		struct drm_i915_gem_object *ctx_obj =
+				head_req->ctx->engine[ring->id].state;
+		if (intel_execlists_ctx_id(ctx_obj) == request_id) {
+			WARN(head_req->elsp_submitted == 0,
+			     "Never submitted head request\n");
+
+			if (--head_req->elsp_submitted <= 0) {
+				list_del(&head_req->execlist_link);
+				queue_work(dev_priv->wq, &head_req->work);
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+
+/**
+ * intel_execlists_handle_ctx_events() - handle Context Switch interrupts
+ * @ring: Engine Command Streamer to handle.
+ *
+ * Check the unread Context Status Buffers and manage the submission of new
+ * contexts to the ELSP accordingly.
+ */
+void intel_execlists_handle_ctx_events(struct intel_engine_cs *ring)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	u32 status_pointer;
+	u8 read_pointer;
+	u8 write_pointer;
+	u32 status;
+	u32 status_id;
+	u32 submit_contexts = 0;
+
+	status_pointer = I915_READ(RING_CONTEXT_STATUS_PTR(ring));
+
+	read_pointer = ring->next_context_status_buffer;
+	write_pointer = status_pointer & 0x07;
+	if (read_pointer > write_pointer)
+		write_pointer += 6;
+
+	spin_lock(&ring->execlist_lock);
+
+	while (read_pointer < write_pointer) {
+		read_pointer++;
+		status = I915_READ(RING_CONTEXT_STATUS_BUF(ring) +
+				(read_pointer % 6) * 8);
+		status_id = I915_READ(RING_CONTEXT_STATUS_BUF(ring) +
+				(read_pointer % 6) * 8 + 4);
+
+		if (status & GEN8_CTX_STATUS_PREEMPTED) {
+			if (status & GEN8_CTX_STATUS_LITE_RESTORE) {
+				if (execlists_check_remove_request(ring, status_id))
+					WARN(1, "Lite Restored request removed from queue\n");
+			} else
+				WARN(1, "Preemption without Lite Restore\n");
+		}
+
+		 if ((status & GEN8_CTX_STATUS_ACTIVE_IDLE) ||
+		     (status & GEN8_CTX_STATUS_ELEMENT_SWITCH)) {
+			if (execlists_check_remove_request(ring, status_id))
+				submit_contexts++;
+		}
+	}
+
+	if (submit_contexts != 0)
+		execlists_context_unqueue(ring);
+
+	spin_unlock(&ring->execlist_lock);
+
+	WARN(submit_contexts > 2, "More than two context complete events?\n");
+	ring->next_context_status_buffer = write_pointer % 6;
+
+	I915_WRITE(RING_CONTEXT_STATUS_PTR(ring),
+		   ((u32)ring->next_context_status_buffer & 0x07) << 8);
+}
+
+static void execlists_free_request_task(struct work_struct *work)
+{
+	struct intel_ctx_submit_request *req =
+		container_of(work, struct intel_ctx_submit_request, work);
+	struct drm_device *dev = req->ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	intel_runtime_pm_put(dev_priv);
+
+	mutex_lock(&dev->struct_mutex);
+	i915_gem_context_unreference(req->ctx);
+	mutex_unlock(&dev->struct_mutex);
+
+	kfree(req);
+}
+
+static int execlists_context_queue(struct intel_engine_cs *ring,
+				   struct intel_context *to,
+				   u32 tail)
+{
+	struct intel_ctx_submit_request *req = NULL, *cursor;
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	unsigned long flags;
+	int num_elements = 0;
+
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	if (req == NULL)
+		return -ENOMEM;
+	req->ctx = to;
+	i915_gem_context_reference(req->ctx);
+	req->ring = ring;
+	req->tail = tail;
+	INIT_WORK(&req->work, execlists_free_request_task);
+
+	intel_runtime_pm_get(dev_priv);
+
+	spin_lock_irqsave(&ring->execlist_lock, flags);
+
+	list_for_each_entry(cursor, &ring->execlist_queue, execlist_link)
+		if (++num_elements > 2)
+			break;
+
+	if (num_elements > 2) {
+		struct intel_ctx_submit_request *tail_req;
+
+		tail_req = list_last_entry(&ring->execlist_queue,
+					   struct intel_ctx_submit_request,
+					   execlist_link);
+
+		if (to == tail_req->ctx) {
+			WARN(tail_req->elsp_submitted != 0,
+			     "More than 2 already-submitted reqs queued\n");
+			list_del(&tail_req->execlist_link);
+			queue_work(dev_priv->wq, &tail_req->work);
+		}
+	}
+
+	list_add_tail(&req->execlist_link, &ring->execlist_queue);
+	if (num_elements == 0)
+		execlists_context_unqueue(ring);
+
+	spin_unlock_irqrestore(&ring->execlist_lock, flags);
+
+	return 0;
+}
+
+static int logical_ring_invalidate_all_caches(struct intel_ringbuffer *ringbuf)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	uint32_t flush_domains;
+	int ret;
+
+	flush_domains = 0;
+	if (ring->gpu_caches_dirty)
+		flush_domains = I915_GEM_GPU_DOMAINS;
+
+	ret = ring->emit_flush(ringbuf, I915_GEM_GPU_DOMAINS, flush_domains);
+	if (ret)
+		return ret;
+
+	ring->gpu_caches_dirty = false;
+	return 0;
+}
+
+static int execlists_move_to_gpu(struct intel_ringbuffer *ringbuf,
+				 struct list_head *vmas)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	struct i915_vma *vma;
+	uint32_t flush_domains = 0;
+	bool flush_chipset = false;
+	int ret;
+
+	list_for_each_entry(vma, vmas, exec_list) {
+		struct drm_i915_gem_object *obj = vma->obj;
+
+		ret = i915_gem_object_sync(obj, ring);
+		if (ret)
+			return ret;
+
+		if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
+			flush_chipset |= i915_gem_clflush_object(obj, false);
+
+		flush_domains |= obj->base.write_domain;
+	}
+
+	if (flush_domains & I915_GEM_DOMAIN_GTT)
+		wmb();
+
+	/* Unconditionally invalidate gpu caches and ensure that we do flush
+	 * any residual writes from the previous batch.
+	 */
+	return logical_ring_invalidate_all_caches(ringbuf);
+}
+
+/**
+ * execlists_submission() - submit a batchbuffer for execution, Execlists style
+ * @dev: DRM device.
+ * @file: DRM file.
+ * @ring: Engine Command Streamer to submit to.
+ * @ctx: Context to employ for this submission.
+ * @args: execbuffer call arguments.
+ * @vmas: list of vmas.
+ * @batch_obj: the batchbuffer to submit.
+ * @exec_start: batchbuffer start virtual address pointer.
+ * @flags: translated execbuffer call flags.
+ *
+ * This is the evil twin version of i915_gem_ringbuffer_submission. It abstracts
+ * away the submission details of the execbuffer ioctl call.
+ *
+ * Return: non-zero if the submission fails.
+ */
+int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
+			       struct intel_engine_cs *ring,
+			       struct intel_context *ctx,
+			       struct drm_i915_gem_execbuffer2 *args,
+			       struct list_head *vmas,
+			       struct drm_i915_gem_object *batch_obj,
+			       u64 exec_start, u32 flags)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+	int instp_mode;
+	u32 instp_mask;
+	int ret;
+
+	instp_mode = args->flags & I915_EXEC_CONSTANTS_MASK;
+	instp_mask = I915_EXEC_CONSTANTS_MASK;
+	switch (instp_mode) {
+	case I915_EXEC_CONSTANTS_REL_GENERAL:
+	case I915_EXEC_CONSTANTS_ABSOLUTE:
+	case I915_EXEC_CONSTANTS_REL_SURFACE:
+		if (instp_mode != 0 && ring != &dev_priv->ring[RCS]) {
+			DRM_DEBUG("non-0 rel constants mode on non-RCS\n");
+			return -EINVAL;
+		}
+
+		if (instp_mode != dev_priv->relative_constants_mode) {
+			if (instp_mode == I915_EXEC_CONSTANTS_REL_SURFACE) {
+				DRM_DEBUG("rel surface constants mode invalid on gen5+\n");
+				return -EINVAL;
+			}
+
+			/* The HW changed the meaning on this bit on gen6 */
+			instp_mask &= ~I915_EXEC_CONSTANTS_REL_SURFACE;
+		}
+		break;
+	default:
+		DRM_DEBUG("execbuf with unknown constants: %d\n", instp_mode);
+		return -EINVAL;
+	}
+
+	if (args->num_cliprects != 0) {
+		DRM_DEBUG("clip rectangles are only valid on pre-gen5\n");
+		return -EINVAL;
+	} else {
+		if (args->DR4 == 0xffffffff) {
+			DRM_DEBUG("UXA submitting garbage DR4, fixing up\n");
+			args->DR4 = 0;
+		}
+
+		if (args->DR1 || args->DR4 || args->cliprects_ptr) {
+			DRM_DEBUG("0 cliprects but dirt in cliprects fields\n");
+			return -EINVAL;
+		}
+	}
+
+	if (args->flags & I915_EXEC_GEN7_SOL_RESET) {
+		DRM_DEBUG("sol reset is gen7 only\n");
+		return -EINVAL;
+	}
+
+	ret = execlists_move_to_gpu(ringbuf, vmas);
+	if (ret)
+		return ret;
+
+	if (ring == &dev_priv->ring[RCS] &&
+	    instp_mode != dev_priv->relative_constants_mode) {
+		ret = intel_logical_ring_begin(ringbuf, 4);
+		if (ret)
+			return ret;
+
+		intel_logical_ring_emit(ringbuf, MI_NOOP);
+		intel_logical_ring_emit(ringbuf, MI_LOAD_REGISTER_IMM(1));
+		intel_logical_ring_emit(ringbuf, INSTPM);
+		intel_logical_ring_emit(ringbuf, instp_mask << 16 | instp_mode);
+		intel_logical_ring_advance(ringbuf);
+
+		dev_priv->relative_constants_mode = instp_mode;
+	}
+
+	ret = ring->emit_bb_start(ringbuf, exec_start, flags);
+	if (ret)
+		return ret;
+
+	i915_gem_execbuffer_move_to_active(vmas, ring);
+	i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
+
+	return 0;
+}
+
+void intel_logical_ring_stop(struct intel_engine_cs *ring)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	int ret;
+
+	if (!intel_ring_initialized(ring))
+		return;
+
+	ret = intel_ring_idle(ring);
+	if (ret && !i915_reset_in_progress(&to_i915(ring->dev)->gpu_error))
+		DRM_ERROR("failed to quiesce %s whilst cleaning up: %d\n",
+			  ring->name, ret);
+
+	/* TODO: Is this correct with Execlists enabled? */
+	I915_WRITE_MODE(ring, _MASKED_BIT_ENABLE(STOP_RING));
+	if (wait_for_atomic((I915_READ_MODE(ring) & MODE_IDLE) != 0, 1000)) {
+		DRM_ERROR("%s :timed out trying to stop ring\n", ring->name);
+		return;
+	}
+	I915_WRITE_MODE(ring, _MASKED_BIT_DISABLE(STOP_RING));
+}
+
+int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	int ret;
+
+	if (!ring->gpu_caches_dirty)
+		return 0;
+
+	ret = ring->emit_flush(ringbuf, 0, I915_GEM_GPU_DOMAINS);
+	if (ret)
+		return ret;
+
+	ring->gpu_caches_dirty = false;
+	return 0;
+}
+
+/**
+ * intel_logical_ring_advance_and_submit() - advance the tail and submit the workload
+ * @ringbuf: Logical Ringbuffer to advance.
+ *
+ * The tail is updated in our logical ringbuffer struct, not in the actual context. What
+ * really happens during submission is that the context and current tail will be placed
+ * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
+ * point, the tail *inside* the context is updated and the ELSP written to.
+ */
+void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	struct intel_context *ctx = ringbuf->FIXME_lrc_ctx;
+
+	intel_logical_ring_advance(ringbuf);
+
+	if (intel_ring_stopped(ring))
+		return;
+
+	execlists_context_queue(ring, ctx, ringbuf->tail);
+}
+
+static int logical_ring_alloc_seqno(struct intel_engine_cs *ring,
+				    struct intel_context *ctx)
+{
+	if (ring->outstanding_lazy_seqno)
+		return 0;
+
+	if (ring->preallocated_lazy_request == NULL) {
+		struct drm_i915_gem_request *request;
+
+		request = kmalloc(sizeof(*request), GFP_KERNEL);
+		if (request == NULL)
+			return -ENOMEM;
+
+		/* Hold a reference to the context this request belongs to
+		 * (we will need it when the time comes to emit/retire the
+		 * request).
+		 */
+		request->ctx = ctx;
+		i915_gem_context_reference(request->ctx);
+
+		ring->preallocated_lazy_request = request;
+	}
+
+	return i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_seqno);
+}
+
+static int logical_ring_wait_request(struct intel_ringbuffer *ringbuf,
+				     int bytes)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	struct drm_i915_gem_request *request;
+	u32 seqno = 0;
+	int ret;
+
+	if (ringbuf->last_retired_head != -1) {
+		ringbuf->head = ringbuf->last_retired_head;
+		ringbuf->last_retired_head = -1;
+
+		ringbuf->space = intel_ring_space(ringbuf);
+		if (ringbuf->space >= bytes)
+			return 0;
+	}
+
+	list_for_each_entry(request, &ring->request_list, list) {
+		if (__intel_ring_space(request->tail, ringbuf->tail,
+				       ringbuf->size) >= bytes) {
+			seqno = request->seqno;
+			break;
+		}
+	}
+
+	if (seqno == 0)
+		return -ENOSPC;
+
+	ret = i915_wait_seqno(ring, seqno);
+	if (ret)
+		return ret;
+
+	i915_gem_retire_requests_ring(ring);
+	ringbuf->head = ringbuf->last_retired_head;
+	ringbuf->last_retired_head = -1;
+
+	ringbuf->space = intel_ring_space(ringbuf);
+	return 0;
+}
+
+static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
+				       int bytes)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long end;
+	int ret;
+
+	ret = logical_ring_wait_request(ringbuf, bytes);
+	if (ret != -ENOSPC)
+		return ret;
+
+	/* Force the context submission in case we have been skipping it */
+	intel_logical_ring_advance_and_submit(ringbuf);
+
+	/* With GEM the hangcheck timer should kick us out of the loop,
+	 * leaving it early runs the risk of corrupting GEM state (due
+	 * to running on almost untested codepaths). But on resume
+	 * timers don't work yet, so prevent a complete hang in that
+	 * case by choosing an insanely large timeout. */
+	end = jiffies + 60 * HZ;
+
+	do {
+		ringbuf->head = I915_READ_HEAD(ring);
+		ringbuf->space = intel_ring_space(ringbuf);
+		if (ringbuf->space >= bytes) {
+			ret = 0;
+			break;
+		}
+
+		msleep(1);
+
+		if (dev_priv->mm.interruptible && signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+
+		ret = i915_gem_check_wedge(&dev_priv->gpu_error,
+					   dev_priv->mm.interruptible);
+		if (ret)
+			break;
+
+		if (time_after(jiffies, end)) {
+			ret = -EBUSY;
+			break;
+		}
+	} while (1);
+
+	return ret;
+}
+
+static int logical_ring_wrap_buffer(struct intel_ringbuffer *ringbuf)
+{
+	uint32_t __iomem *virt;
+	int rem = ringbuf->size - ringbuf->tail;
+
+	if (ringbuf->space < rem) {
+		int ret = logical_ring_wait_for_space(ringbuf, rem);
+
+		if (ret)
+			return ret;
+	}
+
+	virt = ringbuf->virtual_start + ringbuf->tail;
+	rem /= 4;
+	while (rem--)
+		iowrite32(MI_NOOP, virt++);
+
+	ringbuf->tail = 0;
+	ringbuf->space = intel_ring_space(ringbuf);
+
+	return 0;
+}
+
+static int logical_ring_prepare(struct intel_ringbuffer *ringbuf, int bytes)
+{
+	int ret;
+
+	if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
+		ret = logical_ring_wrap_buffer(ringbuf);
+		if (unlikely(ret))
+			return ret;
+	}
+
+	if (unlikely(ringbuf->space < bytes)) {
+		ret = logical_ring_wait_for_space(ringbuf, bytes);
+		if (unlikely(ret))
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * intel_logical_ring_begin() - prepare the logical ringbuffer to accept some commands
+ *
+ * @ringbuf: Logical ringbuffer.
+ * @num_dwords: number of DWORDs that we plan to write to the ringbuffer.
+ *
+ * The ringbuffer might not be ready to accept the commands right away (maybe it needs to
+ * be wrapped, or wait a bit for the tail to be updated). This function takes care of that
+ * and also preallocates a request (every workload submission is still mediated through
+ * requests, same as it did with legacy ringbuffer submission).
+ *
+ * Return: non-zero if the ringbuffer is not ready to be written to.
+ */
+int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf, int num_dwords)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
+
+	ret = i915_gem_check_wedge(&dev_priv->gpu_error,
+				   dev_priv->mm.interruptible);
+	if (ret)
+		return ret;
+
+	ret = logical_ring_prepare(ringbuf, num_dwords * sizeof(uint32_t));
+	if (ret)
+		return ret;
+
+	/* Preallocate the olr before touching the ring */
+	ret = logical_ring_alloc_seqno(ring, ringbuf->FIXME_lrc_ctx);
+	if (ret)
+		return ret;
+
+	ringbuf->space -= num_dwords * sizeof(uint32_t);
+	return 0;
+}
+
+static int gen8_init_common_ring(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | ring->irq_keep_mask));
+	I915_WRITE(RING_HWSTAM(ring->mmio_base), 0xffffffff);
+
+	I915_WRITE(RING_MODE_GEN7(ring),
+		   _MASKED_BIT_DISABLE(GFX_REPLAY_MODE) |
+		   _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE));
+	POSTING_READ(RING_MODE_GEN7(ring));
+	DRM_DEBUG_DRIVER("Execlists enabled for %s\n", ring->name);
+
+	memset(&ring->hangcheck, 0, sizeof(ring->hangcheck));
+
+	return 0;
+}
+
+static int gen8_init_render_ring(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
+
+	ret = gen8_init_common_ring(ring);
+	if (ret)
+		return ret;
+
+	/* We need to disable the AsyncFlip performance optimisations in order
+	 * to use MI_WAIT_FOR_EVENT within the CS. It should already be
+	 * programmed to '1' on all products.
+	 *
+	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv
+	 */
+	I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
+
+	ret = intel_init_pipe_control(ring);
+	if (ret)
+		return ret;
+
+	I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
+
+	return ret;
+}
+
+static int gen8_emit_bb_start(struct intel_ringbuffer *ringbuf,
+			      u64 offset, unsigned flags)
+{
+	bool ppgtt = !(flags & I915_DISPATCH_SECURE);
+	int ret;
+
+	ret = intel_logical_ring_begin(ringbuf, 4);
+	if (ret)
+		return ret;
+
+	/* FIXME(BDW): Address space and security selectors. */
+	intel_logical_ring_emit(ringbuf, MI_BATCH_BUFFER_START_GEN8 | (ppgtt<<8));
+	intel_logical_ring_emit(ringbuf, lower_32_bits(offset));
+	intel_logical_ring_emit(ringbuf, upper_32_bits(offset));
+	intel_logical_ring_emit(ringbuf, MI_NOOP);
+	intel_logical_ring_advance(ringbuf);
+
+	return 0;
+}
+
+static bool gen8_logical_ring_get_irq(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long flags;
+
+	if (!dev->irq_enabled)
+		return false;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	if (ring->irq_refcount++ == 0) {
+		I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | ring->irq_keep_mask));
+		POSTING_READ(RING_IMR(ring->mmio_base));
+	}
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+
+	return true;
+}
+
+static void gen8_logical_ring_put_irq(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	if (--ring->irq_refcount == 0) {
+		I915_WRITE_IMR(ring, ~ring->irq_keep_mask);
+		POSTING_READ(RING_IMR(ring->mmio_base));
+	}
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+}
+
+static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
+			   u32 invalidate_domains,
+			   u32 unused)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint32_t cmd;
+	int ret;
+
+	ret = intel_logical_ring_begin(ringbuf, 4);
+	if (ret)
+		return ret;
+
+	cmd = MI_FLUSH_DW + 1;
+
+	if (ring == &dev_priv->ring[VCS]) {
+		if (invalidate_domains & I915_GEM_GPU_DOMAINS)
+			cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD |
+				MI_FLUSH_DW_STORE_INDEX |
+				MI_FLUSH_DW_OP_STOREDW;
+	} else {
+		if (invalidate_domains & I915_GEM_DOMAIN_RENDER)
+			cmd |= MI_INVALIDATE_TLB | MI_FLUSH_DW_STORE_INDEX |
+				MI_FLUSH_DW_OP_STOREDW;
+	}
+
+	intel_logical_ring_emit(ringbuf, cmd);
+	intel_logical_ring_emit(ringbuf,
+				I915_GEM_HWS_SCRATCH_ADDR |
+				MI_FLUSH_DW_USE_GTT);
+	intel_logical_ring_emit(ringbuf, 0); /* upper addr */
+	intel_logical_ring_emit(ringbuf, 0); /* value */
+	intel_logical_ring_advance(ringbuf);
+
+	return 0;
+}
+
+static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
+				  u32 invalidate_domains,
+				  u32 flush_domains)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+	u32 flags = 0;
+	int ret;
+
+	flags |= PIPE_CONTROL_CS_STALL;
+
+	if (flush_domains) {
+		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
+		flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
+	}
+
+	if (invalidate_domains) {
+		flags |= PIPE_CONTROL_TLB_INVALIDATE;
+		flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_QW_WRITE;
+		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+	}
+
+	ret = intel_logical_ring_begin(ringbuf, 6);
+	if (ret)
+		return ret;
+
+	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
+	intel_logical_ring_emit(ringbuf, flags);
+	intel_logical_ring_emit(ringbuf, scratch_addr);
+	intel_logical_ring_emit(ringbuf, 0);
+	intel_logical_ring_emit(ringbuf, 0);
+	intel_logical_ring_emit(ringbuf, 0);
+	intel_logical_ring_advance(ringbuf);
+
+	return 0;
+}
+
+static u32 gen8_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency)
+{
+	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
+}
+
+static void gen8_set_seqno(struct intel_engine_cs *ring, u32 seqno)
+{
+	intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno);
+}
+
+static int gen8_emit_request(struct intel_ringbuffer *ringbuf)
+{
+	struct intel_engine_cs *ring = ringbuf->ring;
+	u32 cmd;
+	int ret;
+
+	ret = intel_logical_ring_begin(ringbuf, 6);
+	if (ret)
+		return ret;
+
+	cmd = MI_STORE_DWORD_IMM_GEN8;
+	cmd |= MI_GLOBAL_GTT;
+
+	intel_logical_ring_emit(ringbuf, cmd);
+	intel_logical_ring_emit(ringbuf,
+				(ring->status_page.gfx_addr +
+				(I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT)));
+	intel_logical_ring_emit(ringbuf, 0);
+	intel_logical_ring_emit(ringbuf, ring->outstanding_lazy_seqno);
+	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
+	intel_logical_ring_emit(ringbuf, MI_NOOP);
+	intel_logical_ring_advance_and_submit(ringbuf);
+
+	return 0;
+}
+
+/**
+ * intel_logical_ring_cleanup() - deallocate the Engine Command Streamer
+ *
+ * @ring: Engine Command Streamer.
+ *
+ */
+void intel_logical_ring_cleanup(struct intel_engine_cs *ring)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+
+	if (!intel_ring_initialized(ring))
+		return;
+
+	intel_logical_ring_stop(ring);
+	WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
+	ring->preallocated_lazy_request = NULL;
+	ring->outstanding_lazy_seqno = 0;
+
+	if (ring->cleanup)
+		ring->cleanup(ring);
+
+	i915_cmd_parser_fini_ring(ring);
+
+	if (ring->status_page.obj) {
+		kunmap(sg_page(ring->status_page.obj->pages->sgl));
+		ring->status_page.obj = NULL;
+	}
+}
+
+static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *ring)
+{
+	int ret;
+
+	/* Intentionally left blank. */
+	ring->buffer = NULL;
+
+	ring->dev = dev;
+	INIT_LIST_HEAD(&ring->active_list);
+	INIT_LIST_HEAD(&ring->request_list);
+	init_waitqueue_head(&ring->irq_queue);
+
+	INIT_LIST_HEAD(&ring->execlist_queue);
+	spin_lock_init(&ring->execlist_lock);
+	ring->next_context_status_buffer = 0;
+
+	ret = i915_cmd_parser_init_ring(ring);
+	if (ret)
+		return ret;
+
+	if (ring->init) {
+		ret = ring->init(ring);
+		if (ret)
+			return ret;
+	}
+
+	ret = intel_lr_context_deferred_create(ring->default_context, ring);
+
+	return ret;
+}
+
+static int logical_render_ring_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
+
+	ring->name = "render ring";
+	ring->id = RCS;
+	ring->mmio_base = RENDER_RING_BASE;
+	ring->irq_enable_mask =
+		GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT;
+	ring->irq_keep_mask =
+		GT_CONTEXT_SWITCH_INTERRUPT << GEN8_RCS_IRQ_SHIFT;
+	if (HAS_L3_DPF(dev))
+		ring->irq_keep_mask |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT;
+
+	ring->init = gen8_init_render_ring;
+	ring->cleanup = intel_fini_pipe_control;
+	ring->get_seqno = gen8_get_seqno;
+	ring->set_seqno = gen8_set_seqno;
+	ring->emit_request = gen8_emit_request;
+	ring->emit_flush = gen8_emit_flush_render;
+	ring->irq_get = gen8_logical_ring_get_irq;
+	ring->irq_put = gen8_logical_ring_put_irq;
+	ring->emit_bb_start = gen8_emit_bb_start;
+
+	return logical_ring_init(dev, ring);
+}
+
+static int logical_bsd_ring_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring = &dev_priv->ring[VCS];
+
+	ring->name = "bsd ring";
+	ring->id = VCS;
+	ring->mmio_base = GEN6_BSD_RING_BASE;
+	ring->irq_enable_mask =
+		GT_RENDER_USER_INTERRUPT << GEN8_VCS1_IRQ_SHIFT;
+	ring->irq_keep_mask =
+		GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS1_IRQ_SHIFT;
+
+	ring->init = gen8_init_common_ring;
+	ring->get_seqno = gen8_get_seqno;
+	ring->set_seqno = gen8_set_seqno;
+	ring->emit_request = gen8_emit_request;
+	ring->emit_flush = gen8_emit_flush;
+	ring->irq_get = gen8_logical_ring_get_irq;
+	ring->irq_put = gen8_logical_ring_put_irq;
+	ring->emit_bb_start = gen8_emit_bb_start;
+
+	return logical_ring_init(dev, ring);
+}
+
+static int logical_bsd2_ring_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring = &dev_priv->ring[VCS2];
+
+	ring->name = "bds2 ring";
+	ring->id = VCS2;
+	ring->mmio_base = GEN8_BSD2_RING_BASE;
+	ring->irq_enable_mask =
+		GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT;
+	ring->irq_keep_mask =
+		GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS2_IRQ_SHIFT;
+
+	ring->init = gen8_init_common_ring;
+	ring->get_seqno = gen8_get_seqno;
+	ring->set_seqno = gen8_set_seqno;
+	ring->emit_request = gen8_emit_request;
+	ring->emit_flush = gen8_emit_flush;
+	ring->irq_get = gen8_logical_ring_get_irq;
+	ring->irq_put = gen8_logical_ring_put_irq;
+	ring->emit_bb_start = gen8_emit_bb_start;
+
+	return logical_ring_init(dev, ring);
+}
+
+static int logical_blt_ring_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring = &dev_priv->ring[BCS];
+
+	ring->name = "blitter ring";
+	ring->id = BCS;
+	ring->mmio_base = BLT_RING_BASE;
+	ring->irq_enable_mask =
+		GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
+	ring->irq_keep_mask =
+		GT_CONTEXT_SWITCH_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
+
+	ring->init = gen8_init_common_ring;
+	ring->get_seqno = gen8_get_seqno;
+	ring->set_seqno = gen8_set_seqno;
+	ring->emit_request = gen8_emit_request;
+	ring->emit_flush = gen8_emit_flush;
+	ring->irq_get = gen8_logical_ring_get_irq;
+	ring->irq_put = gen8_logical_ring_put_irq;
+	ring->emit_bb_start = gen8_emit_bb_start;
+
+	return logical_ring_init(dev, ring);
+}
+
+static int logical_vebox_ring_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring = &dev_priv->ring[VECS];
+
+	ring->name = "video enhancement ring";
+	ring->id = VECS;
+	ring->mmio_base = VEBOX_RING_BASE;
+	ring->irq_enable_mask =
+		GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT;
+	ring->irq_keep_mask =
+		GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VECS_IRQ_SHIFT;
+
+	ring->init = gen8_init_common_ring;
+	ring->get_seqno = gen8_get_seqno;
+	ring->set_seqno = gen8_set_seqno;
+	ring->emit_request = gen8_emit_request;
+	ring->emit_flush = gen8_emit_flush;
+	ring->irq_get = gen8_logical_ring_get_irq;
+	ring->irq_put = gen8_logical_ring_put_irq;
+	ring->emit_bb_start = gen8_emit_bb_start;
+
+	return logical_ring_init(dev, ring);
+}
+
+/**
+ * intel_logical_rings_init() - allocate, populate and init the Engine Command Streamers
+ * @dev: DRM device.
+ *
+ * This function inits the engines for an Execlists submission style (the equivalent in the
+ * legacy ringbuffer submission world would be i915_gem_init_rings). It does it only for
+ * those engines that are present in the hardware.
+ *
+ * Return: non-zero if the initialization failed.
+ */
+int intel_logical_rings_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
+
+	ret = logical_render_ring_init(dev);
+	if (ret)
+		return ret;
+
+	if (HAS_BSD(dev)) {
+		ret = logical_bsd_ring_init(dev);
+		if (ret)
+			goto cleanup_render_ring;
+	}
+
+	if (HAS_BLT(dev)) {
+		ret = logical_blt_ring_init(dev);
+		if (ret)
+			goto cleanup_bsd_ring;
+	}
+
+	if (HAS_VEBOX(dev)) {
+		ret = logical_vebox_ring_init(dev);
+		if (ret)
+			goto cleanup_blt_ring;
+	}
+
+	if (HAS_BSD2(dev)) {
+		ret = logical_bsd2_ring_init(dev);
+		if (ret)
+			goto cleanup_vebox_ring;
+	}
+
+	ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000));
+	if (ret)
+		goto cleanup_bsd2_ring;
+
+	return 0;
+
+cleanup_bsd2_ring:
+	intel_logical_ring_cleanup(&dev_priv->ring[VCS2]);
+cleanup_vebox_ring:
+	intel_logical_ring_cleanup(&dev_priv->ring[VECS]);
+cleanup_blt_ring:
+	intel_logical_ring_cleanup(&dev_priv->ring[BCS]);
+cleanup_bsd_ring:
+	intel_logical_ring_cleanup(&dev_priv->ring[VCS]);
+cleanup_render_ring:
+	intel_logical_ring_cleanup(&dev_priv->ring[RCS]);
+
+	return ret;
+}
+
+int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
+				       struct intel_context *ctx)
+{
+	struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+	struct render_state so;
+	struct drm_i915_file_private *file_priv = ctx->file_priv;
+	struct drm_file *file = file_priv ? file_priv->file : NULL;
+	int ret;
+
+	ret = i915_gem_render_state_prepare(ring, &so);
+	if (ret)
+		return ret;
+
+	if (so.rodata == NULL)
+		return 0;
+
+	ret = ring->emit_bb_start(ringbuf,
+			so.ggtt_offset,
+			I915_DISPATCH_SECURE);
+	if (ret)
+		goto out;
+
+	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
+
+	ret = __i915_add_request(ring, file, so.obj, NULL);
+	/* intel_logical_ring_add_request moves object to inactive if it
+	 * fails */
+out:
+	i915_gem_render_state_fini(&so);
+	return ret;
+}
+
+static int
+populate_lr_context(struct intel_context *ctx, struct drm_i915_gem_object *ctx_obj,
+		    struct intel_engine_cs *ring, struct intel_ringbuffer *ringbuf)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *ring_obj = ringbuf->obj;
+	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt;
+	struct page *page;
+	uint32_t *reg_state;
+	int ret;
+
+	if (!ppgtt)
+		ppgtt = dev_priv->mm.aliasing_ppgtt;
+
+	ret = i915_gem_object_set_to_cpu_domain(ctx_obj, true);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Could not set to CPU domain\n");
+		return ret;
+	}
+
+	ret = i915_gem_object_get_pages(ctx_obj);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Could not get object pages\n");
+		return ret;
+	}
+
+	i915_gem_object_pin_pages(ctx_obj);
+
+	/* The second page of the context object contains some fields which must
+	 * be set up prior to the first execution. */
+	page = i915_gem_object_get_page(ctx_obj, 1);
+	reg_state = kmap_atomic(page);
+
+	/* A context is actually a big batch buffer with several MI_LOAD_REGISTER_IMM
+	 * commands followed by (reg, value) pairs. The values we are setting here are
+	 * only for the first context restore: on a subsequent save, the GPU will
+	 * recreate this batchbuffer with new values (including all the missing
+	 * MI_LOAD_REGISTER_IMM commands that we are not initializing here). */
+	if (ring->id == RCS)
+		reg_state[CTX_LRI_HEADER_0] = MI_LOAD_REGISTER_IMM(14);
+	else
+		reg_state[CTX_LRI_HEADER_0] = MI_LOAD_REGISTER_IMM(11);
+	reg_state[CTX_LRI_HEADER_0] |= MI_LRI_FORCE_POSTED;
+	reg_state[CTX_CONTEXT_CONTROL] = RING_CONTEXT_CONTROL(ring);
+	reg_state[CTX_CONTEXT_CONTROL+1] =
+			_MASKED_BIT_ENABLE((1<<3) | MI_RESTORE_INHIBIT);
+	reg_state[CTX_RING_HEAD] = RING_HEAD(ring->mmio_base);
+	reg_state[CTX_RING_HEAD+1] = 0;
+	reg_state[CTX_RING_TAIL] = RING_TAIL(ring->mmio_base);
+	reg_state[CTX_RING_TAIL+1] = 0;
+	reg_state[CTX_RING_BUFFER_START] = RING_START(ring->mmio_base);
+	reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(ring_obj);
+	reg_state[CTX_RING_BUFFER_CONTROL] = RING_CTL(ring->mmio_base);
+	reg_state[CTX_RING_BUFFER_CONTROL+1] =
+			((ringbuf->size - PAGE_SIZE) & RING_NR_PAGES) | RING_VALID;
+	reg_state[CTX_BB_HEAD_U] = ring->mmio_base + 0x168;
+	reg_state[CTX_BB_HEAD_U+1] = 0;
+	reg_state[CTX_BB_HEAD_L] = ring->mmio_base + 0x140;
+	reg_state[CTX_BB_HEAD_L+1] = 0;
+	reg_state[CTX_BB_STATE] = ring->mmio_base + 0x110;
+	reg_state[CTX_BB_STATE+1] = (1<<5);
+	reg_state[CTX_SECOND_BB_HEAD_U] = ring->mmio_base + 0x11c;
+	reg_state[CTX_SECOND_BB_HEAD_U+1] = 0;
+	reg_state[CTX_SECOND_BB_HEAD_L] = ring->mmio_base + 0x114;
+	reg_state[CTX_SECOND_BB_HEAD_L+1] = 0;
+	reg_state[CTX_SECOND_BB_STATE] = ring->mmio_base + 0x118;
+	reg_state[CTX_SECOND_BB_STATE+1] = 0;
+	if (ring->id == RCS) {
+		/* TODO: according to BSpec, the register state context
+		 * for CHV does not have these. OTOH, these registers do
+		 * exist in CHV. I'm waiting for a clarification */
+		reg_state[CTX_BB_PER_CTX_PTR] = ring->mmio_base + 0x1c0;
+		reg_state[CTX_BB_PER_CTX_PTR+1] = 0;
+		reg_state[CTX_RCS_INDIRECT_CTX] = ring->mmio_base + 0x1c4;
+		reg_state[CTX_RCS_INDIRECT_CTX+1] = 0;
+		reg_state[CTX_RCS_INDIRECT_CTX_OFFSET] = ring->mmio_base + 0x1c8;
+		reg_state[CTX_RCS_INDIRECT_CTX_OFFSET+1] = 0;
+	}
+	reg_state[CTX_LRI_HEADER_1] = MI_LOAD_REGISTER_IMM(9);
+	reg_state[CTX_LRI_HEADER_1] |= MI_LRI_FORCE_POSTED;
+	reg_state[CTX_CTX_TIMESTAMP] = ring->mmio_base + 0x3a8;
+	reg_state[CTX_CTX_TIMESTAMP+1] = 0;
+	reg_state[CTX_PDP3_UDW] = GEN8_RING_PDP_UDW(ring, 3);
+	reg_state[CTX_PDP3_LDW] = GEN8_RING_PDP_LDW(ring, 3);
+	reg_state[CTX_PDP2_UDW] = GEN8_RING_PDP_UDW(ring, 2);
+	reg_state[CTX_PDP2_LDW] = GEN8_RING_PDP_LDW(ring, 2);
+	reg_state[CTX_PDP1_UDW] = GEN8_RING_PDP_UDW(ring, 1);
+	reg_state[CTX_PDP1_LDW] = GEN8_RING_PDP_LDW(ring, 1);
+	reg_state[CTX_PDP0_UDW] = GEN8_RING_PDP_UDW(ring, 0);
+	reg_state[CTX_PDP0_LDW] = GEN8_RING_PDP_LDW(ring, 0);
+	reg_state[CTX_PDP3_UDW+1] = upper_32_bits(ppgtt->pd_dma_addr[3]);
+	reg_state[CTX_PDP3_LDW+1] = lower_32_bits(ppgtt->pd_dma_addr[3]);
+	reg_state[CTX_PDP2_UDW+1] = upper_32_bits(ppgtt->pd_dma_addr[2]);
+	reg_state[CTX_PDP2_LDW+1] = lower_32_bits(ppgtt->pd_dma_addr[2]);
+	reg_state[CTX_PDP1_UDW+1] = upper_32_bits(ppgtt->pd_dma_addr[1]);
+	reg_state[CTX_PDP1_LDW+1] = lower_32_bits(ppgtt->pd_dma_addr[1]);
+	reg_state[CTX_PDP0_UDW+1] = upper_32_bits(ppgtt->pd_dma_addr[0]);
+	reg_state[CTX_PDP0_LDW+1] = lower_32_bits(ppgtt->pd_dma_addr[0]);
+	if (ring->id == RCS) {
+		reg_state[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
+		reg_state[CTX_R_PWR_CLK_STATE] = 0x20c8;
+		reg_state[CTX_R_PWR_CLK_STATE+1] = 0;
+	}
+
+	kunmap_atomic(reg_state);
+
+	ctx_obj->dirty = 1;
+	set_page_dirty(page);
+	i915_gem_object_unpin_pages(ctx_obj);
+
+	return 0;
+}
+
+/**
+ * intel_lr_context_free() - free the LRC specific bits of a context
+ * @ctx: the LR context to free.
+ *
+ * The real context freeing is done in i915_gem_context_free: this only
+ * takes care of the bits that are LRC related: the per-engine backing
+ * objects and the logical ringbuffer.
+ */
+void intel_lr_context_free(struct intel_context *ctx)
+{
+	int i;
+
+	for (i = 0; i < I915_NUM_RINGS; i++) {
+		struct drm_i915_gem_object *ctx_obj = ctx->engine[i].state;
+		struct intel_ringbuffer *ringbuf = ctx->engine[i].ringbuf;
+
+		if (ctx_obj) {
+			intel_destroy_ringbuffer_obj(ringbuf);
+			kfree(ringbuf);
+			i915_gem_object_ggtt_unpin(ctx_obj);
+			drm_gem_object_unreference(&ctx_obj->base);
+		}
+	}
+}
+
+static uint32_t get_lr_context_size(struct intel_engine_cs *ring)
+{
+	int ret = 0;
+
+	WARN_ON(INTEL_INFO(ring->dev)->gen != 8);
+
+	switch (ring->id) {
+	case RCS:
+		ret = GEN8_LR_CONTEXT_RENDER_SIZE;
+		break;
+	case VCS:
+	case BCS:
+	case VECS:
+	case VCS2:
+		ret = GEN8_LR_CONTEXT_OTHER_SIZE;
+		break;
+	}
+
+	return ret;
+}
+
+/**
+ * intel_lr_context_deferred_create() - create the LRC specific bits of a context
+ * @ctx: LR context to create.
+ * @ring: engine to be used with the context.
+ *
+ * This function can be called more than once, with different engines, if we plan
+ * to use the context with them. The context backing objects and the ringbuffers
+ * (specially the ringbuffer backing objects) suck a lot of memory up, and that's why
+ * the creation is a deferred call: it's better to make sure first that we need to use
+ * a given ring with the context.
+ *
+ * Return: non-zero on eror.
+ */
+int intel_lr_context_deferred_create(struct intel_context *ctx,
+				     struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_gem_object *ctx_obj;
+	uint32_t context_size;
+	struct intel_ringbuffer *ringbuf;
+	int ret;
+
+	WARN_ON(ctx->legacy_hw_ctx.rcs_state != NULL);
+	if (ctx->engine[ring->id].state)
+		return 0;
+
+	context_size = round_up(get_lr_context_size(ring), 4096);
+
+	ctx_obj = i915_gem_alloc_context_obj(dev, context_size);
+	if (IS_ERR(ctx_obj)) {
+		ret = PTR_ERR(ctx_obj);
+		DRM_DEBUG_DRIVER("Alloc LRC backing obj failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN, 0);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Pin LRC backing obj failed: %d\n", ret);
+		drm_gem_object_unreference(&ctx_obj->base);
+		return ret;
+	}
+
+	ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL);
+	if (!ringbuf) {
+		DRM_DEBUG_DRIVER("Failed to allocate ringbuffer %s\n",
+				ring->name);
+		i915_gem_object_ggtt_unpin(ctx_obj);
+		drm_gem_object_unreference(&ctx_obj->base);
+		ret = -ENOMEM;
+		return ret;
+	}
+
+	ringbuf->ring = ring;
+	ringbuf->FIXME_lrc_ctx = ctx;
+
+	ringbuf->size = 32 * PAGE_SIZE;
+	ringbuf->effective_size = ringbuf->size;
+	ringbuf->head = 0;
+	ringbuf->tail = 0;
+	ringbuf->space = ringbuf->size;
+	ringbuf->last_retired_head = -1;
+
+	/* TODO: For now we put this in the mappable region so that we can reuse
+	 * the existing ringbuffer code which ioremaps it. When we start
+	 * creating many contexts, this will no longer work and we must switch
+	 * to a kmapish interface.
+	 */
+	ret = intel_alloc_ringbuffer_obj(dev, ringbuf);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Failed to allocate ringbuffer obj %s: %d\n",
+				ring->name, ret);
+		goto error;
+	}
+
+	ret = populate_lr_context(ctx, ctx_obj, ring, ringbuf);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Failed to populate LRC: %d\n", ret);
+		intel_destroy_ringbuffer_obj(ringbuf);
+		goto error;
+	}
+
+	ctx->engine[ring->id].ringbuf = ringbuf;
+	ctx->engine[ring->id].state = ctx_obj;
+
+	if (ctx == ring->default_context) {
+		/* The status page is offset 0 from the default context object
+		 * in LRC mode. */
+		ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(ctx_obj);
+		ring->status_page.page_addr =
+				kmap(sg_page(ctx_obj->pages->sgl));
+		if (ring->status_page.page_addr == NULL)
+			return -ENOMEM;
+		ring->status_page.obj = ctx_obj;
+	}
+
+	if (ring->id == RCS && !ctx->rcs_initialized) {
+		ret = intel_lr_context_render_state_init(ring, ctx);
+		if (ret) {
+			DRM_ERROR("Init render state failed: %d\n", ret);
+			ctx->engine[ring->id].ringbuf = NULL;
+			ctx->engine[ring->id].state = NULL;
+			intel_destroy_ringbuffer_obj(ringbuf);
+			goto error;
+		}
+		ctx->rcs_initialized = true;
+	}
+
+	return 0;
+
+error:
+	kfree(ringbuf);
+	i915_gem_object_ggtt_unpin(ctx_obj);
+	drm_gem_object_unreference(&ctx_obj->base);
+	return ret;
+}
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
new file mode 100644
index 000000000000..33c3b4bf28c5
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -0,0 +1,114 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _INTEL_LRC_H_
+#define _INTEL_LRC_H_
+
+/* Execlists regs */
+#define RING_ELSP(ring)			((ring)->mmio_base+0x230)
+#define RING_EXECLIST_STATUS(ring)	((ring)->mmio_base+0x234)
+#define RING_CONTEXT_CONTROL(ring)	((ring)->mmio_base+0x244)
+#define RING_CONTEXT_STATUS_BUF(ring)	((ring)->mmio_base+0x370)
+#define RING_CONTEXT_STATUS_PTR(ring)	((ring)->mmio_base+0x3a0)
+
+/* Logical Rings */
+void intel_logical_ring_stop(struct intel_engine_cs *ring);
+void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
+int intel_logical_rings_init(struct drm_device *dev);
+
+int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf);
+void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf);
+/**
+ * intel_logical_ring_advance() - advance the ringbuffer tail
+ * @ringbuf: Ringbuffer to advance.
+ *
+ * The tail is only updated in our logical ringbuffer struct.
+ */
+static inline void intel_logical_ring_advance(struct intel_ringbuffer *ringbuf)
+{
+	ringbuf->tail &= ringbuf->size - 1;
+}
+/**
+ * intel_logical_ring_emit() - write a DWORD to the ringbuffer.
+ * @ringbuf: Ringbuffer to write to.
+ * @data: DWORD to write.
+ */
+static inline void intel_logical_ring_emit(struct intel_ringbuffer *ringbuf,
+					   u32 data)
+{
+	iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
+	ringbuf->tail += 4;
+}
+int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf, int num_dwords);
+
+/* Logical Ring Contexts */
+int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
+				       struct intel_context *ctx);
+void intel_lr_context_free(struct intel_context *ctx);
+int intel_lr_context_deferred_create(struct intel_context *ctx,
+				     struct intel_engine_cs *ring);
+
+/* Execlists */
+int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists);
+int intel_execlists_submission(struct drm_device *dev, struct drm_file *file,
+			       struct intel_engine_cs *ring,
+			       struct intel_context *ctx,
+			       struct drm_i915_gem_execbuffer2 *args,
+			       struct list_head *vmas,
+			       struct drm_i915_gem_object *batch_obj,
+			       u64 exec_start, u32 flags);
+u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj);
+
+/**
+ * struct intel_ctx_submit_request - queued context submission request
+ * @ctx: Context to submit to the ELSP.
+ * @ring: Engine to submit it to.
+ * @tail: how far in the context's ringbuffer this request goes to.
+ * @execlist_link: link in the submission queue.
+ * @work: workqueue for processing this request in a bottom half.
+ * @elsp_submitted: no. of times this request has been sent to the ELSP.
+ *
+ * The ELSP only accepts two elements at a time, so we queue context/tail
+ * pairs on a given queue (ring->execlist_queue) until the hardware is
+ * available. The queue serves a double purpose: we also use it to keep track
+ * of the up to 2 contexts currently in the hardware (usually one in execution
+ * and the other queued up by the GPU): We only remove elements from the head
+ * of the queue when the hardware informs us that an element has been
+ * completed.
+ *
+ * All accesses to the queue are mediated by a spinlock (ring->execlist_lock).
+ */
+struct intel_ctx_submit_request {
+	struct intel_context *ctx;
+	struct intel_engine_cs *ring;
+	u32 tail;
+
+	struct list_head execlist_link;
+	struct work_struct work;
+
+	int elsp_submitted;
+};
+
+void intel_execlists_handle_ctx_events(struct intel_engine_cs *ring);
+
+#endif /* _INTEL_LRC_H_ */
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index fdf40267249c..a6bd1422e38f 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -823,8 +823,7 @@ bool intel_is_dual_link_lvds(struct drm_device *dev)
 	struct intel_encoder *encoder;
 	struct intel_lvds_encoder *lvds_encoder;
 
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
-			    base.head) {
+	for_each_intel_encoder(dev, encoder) {
 		if (encoder->type == INTEL_OUTPUT_LVDS) {
 			lvds_encoder = to_lvds_encoder(&encoder->base);
 
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 8e374449c6b5..18784470a760 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -751,6 +751,8 @@ void intel_panel_disable_backlight(struct intel_connector *connector)
 
 	spin_lock_irqsave(&dev_priv->backlight_lock, flags);
 
+	if (panel->backlight.device)
+		panel->backlight.device->props.power = FB_BLANK_POWERDOWN;
 	panel->backlight.enabled = false;
 	dev_priv->display.disable_backlight(connector);
 
@@ -957,6 +959,8 @@ void intel_panel_enable_backlight(struct intel_connector *connector)
 
 	dev_priv->display.enable_backlight(connector);
 	panel->backlight.enabled = true;
+	if (panel->backlight.device)
+		panel->backlight.device->props.power = FB_BLANK_UNBLANK;
 
 	spin_unlock_irqrestore(&dev_priv->backlight_lock, flags);
 }
@@ -965,6 +969,7 @@ void intel_panel_enable_backlight(struct intel_connector *connector)
 static int intel_backlight_device_update_status(struct backlight_device *bd)
 {
 	struct intel_connector *connector = bl_get_data(bd);
+	struct intel_panel *panel = &connector->panel;
 	struct drm_device *dev = connector->base.dev;
 
 	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
@@ -972,6 +977,23 @@ static int intel_backlight_device_update_status(struct backlight_device *bd)
 		      bd->props.brightness, bd->props.max_brightness);
 	intel_panel_set_backlight(connector, bd->props.brightness,
 				  bd->props.max_brightness);
+
+	/*
+	 * Allow flipping bl_power as a sub-state of enabled. Sadly the
+	 * backlight class device does not make it easy to to differentiate
+	 * between callbacks for brightness and bl_power, so our backlight_power
+	 * callback needs to take this into account.
+	 */
+	if (panel->backlight.enabled) {
+		if (panel->backlight_power) {
+			bool enable = bd->props.power == FB_BLANK_UNBLANK &&
+				bd->props.brightness != 0;
+			panel->backlight_power(connector, enable);
+		}
+	} else {
+		bd->props.power = FB_BLANK_POWERDOWN;
+	}
+
 	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 	return 0;
 }
@@ -1023,6 +1045,11 @@ static int intel_backlight_device_register(struct intel_connector *connector)
 					    panel->backlight.level,
 					    props.max_brightness);
 
+	if (panel->backlight.enabled)
+		props.power = FB_BLANK_UNBLANK;
+	else
+		props.power = FB_BLANK_POWERDOWN;
+
 	/*
 	 * Note: using the same name independent of the connector prevents
 	 * registration of multiple backlight devices in the driver.
@@ -1203,7 +1230,7 @@ static int vlv_setup_backlight(struct intel_connector *connector)
 	enum pipe pipe;
 	u32 ctl, ctl2, val;
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		u32 cur_val = I915_READ(VLV_BLC_PWM_CTL(pipe));
 
 		/* Skip if the modulation freq is already set */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 40c12295c0bd..c27b6140bfd1 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -309,6 +309,9 @@ static void gen7_enable_fbc(struct drm_crtc *crtc)
 
 	dpfc_ctl |= IVB_DPFC_CTL_FENCE_EN;
 
+	if (dev_priv->fbc.false_color)
+		dpfc_ctl |= FBC_CTL_FALSE_COLOR;
+
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
 	if (IS_IVYBRIDGE(dev)) {
@@ -342,6 +345,16 @@ bool intel_fbc_enabled(struct drm_device *dev)
 	return dev_priv->display.fbc_enabled(dev);
 }
 
+void gen8_fbc_sw_flush(struct drm_device *dev, u32 value)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!IS_GEN8(dev))
+		return;
+
+	I915_WRITE(MSG_FBC_REND_STATE, value);
+}
+
 static void intel_fbc_work_fn(struct work_struct *__work)
 {
 	struct intel_fbc_work *work =
@@ -578,6 +591,12 @@ void intel_update_fbc(struct drm_device *dev)
 			DRM_DEBUG_KMS("framebuffer not tiled or fenced, disabling compression\n");
 		goto out_disable;
 	}
+	if (INTEL_INFO(dev)->gen <= 4 && !IS_G4X(dev) &&
+	    to_intel_plane(crtc->primary)->rotation != BIT(DRM_ROTATE_0)) {
+		if (set_no_fbc_reason(dev_priv, FBC_UNSUPPORTED_MODE))
+			DRM_DEBUG_KMS("Rotation unsupported, disabling\n");
+		goto out_disable;
+	}
 
 	/* If the kernel debugger is active, always disable compression */
 	if (in_dbg_master())
@@ -853,7 +872,7 @@ void intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable)
  * A value of 5us seems to be a good balance; safe for very low end
  * platforms but not overly aggressive on lower latency configs.
  */
-static const int latency_ns = 5000;
+static const int pessimal_latency_ns = 5000;
 
 static int i9xx_get_fifo_size(struct drm_device *dev, int plane)
 {
@@ -982,13 +1001,20 @@ static const struct intel_watermark_params i915_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I915_FIFO_LINE_SIZE,
 };
-static const struct intel_watermark_params i830_wm_info = {
+static const struct intel_watermark_params i830_a_wm_info = {
 	.fifo_size = I855GM_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
 	.default_wm = 1,
 	.guard_size = 2,
 	.cacheline_size = I830_FIFO_LINE_SIZE,
 };
+static const struct intel_watermark_params i830_bc_wm_info = {
+	.fifo_size = I855GM_FIFO_SIZE,
+	.max_wm = I915_MAX_WM/2,
+	.default_wm = 1,
+	.guard_size = 2,
+	.cacheline_size = I830_FIFO_LINE_SIZE,
+};
 static const struct intel_watermark_params i845_wm_info = {
 	.fifo_size = I830_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
@@ -1044,6 +1070,17 @@ static unsigned long intel_calculate_wm(unsigned long clock_in_khz,
 		wm_size = wm->max_wm;
 	if (wm_size <= 0)
 		wm_size = wm->default_wm;
+
+	/*
+	 * Bspec seems to indicate that the value shouldn't be lower than
+	 * 'burst size + 1'. Certainly 830 is quite unhappy with low values.
+	 * Lets go for 8 which is the burst size since certain platforms
+	 * already use a hardcoded 8 (which is what the spec says should be
+	 * done).
+	 */
+	if (wm_size <= 8)
+		wm_size = 8;
+
 	return wm_size;
 }
 
@@ -1268,33 +1305,27 @@ static bool g4x_compute_srwm(struct drm_device *dev,
 			      display, cursor);
 }
 
-static bool vlv_compute_drain_latency(struct drm_device *dev,
-				     int plane,
-				     int *plane_prec_mult,
-				     int *plane_dl,
-				     int *cursor_prec_mult,
-				     int *cursor_dl)
+static bool vlv_compute_drain_latency(struct drm_crtc *crtc,
+				      int pixel_size,
+				      int *prec_mult,
+				      int *drain_latency)
 {
-	struct drm_crtc *crtc;
-	int clock, pixel_size;
 	int entries;
+	int clock = to_intel_crtc(crtc)->config.adjusted_mode.crtc_clock;
 
-	crtc = intel_get_crtc_for_plane(dev, plane);
-	if (!intel_crtc_active(crtc))
+	if (WARN(clock == 0, "Pixel clock is zero!\n"))
 		return false;
 
-	clock = to_intel_crtc(crtc)->config.adjusted_mode.crtc_clock;
-	pixel_size = crtc->primary->fb->bits_per_pixel / 8;	/* BPP */
+	if (WARN(pixel_size == 0, "Pixel size is zero!\n"))
+		return false;
 
-	entries = (clock / 1000) * pixel_size;
-	*plane_prec_mult = (entries > 128) ?
-		DRAIN_LATENCY_PRECISION_64 : DRAIN_LATENCY_PRECISION_32;
-	*plane_dl = (64 * (*plane_prec_mult) * 4) / entries;
+	entries = DIV_ROUND_UP(clock, 1000) * pixel_size;
+	*prec_mult = (entries > 128) ? DRAIN_LATENCY_PRECISION_64 :
+				       DRAIN_LATENCY_PRECISION_32;
+	*drain_latency = (64 * (*prec_mult) * 4) / entries;
 
-	entries = (clock / 1000) * 4;	/* BPP is always 4 for cursor */
-	*cursor_prec_mult = (entries > 128) ?
-		DRAIN_LATENCY_PRECISION_64 : DRAIN_LATENCY_PRECISION_32;
-	*cursor_dl = (64 * (*cursor_prec_mult) * 4) / entries;
+	if (*drain_latency > DRAIN_LATENCY_MASK)
+		*drain_latency = DRAIN_LATENCY_MASK;
 
 	return true;
 }
@@ -1307,39 +1338,48 @@ static bool vlv_compute_drain_latency(struct drm_device *dev,
  * latency value.
  */
 
-static void vlv_update_drain_latency(struct drm_device *dev)
+static void vlv_update_drain_latency(struct drm_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int planea_prec, planea_dl, planeb_prec, planeb_dl;
-	int cursora_prec, cursora_dl, cursorb_prec, cursorb_dl;
-	int plane_prec_mult, cursor_prec_mult; /* Precision multiplier is
-							either 16 or 32 */
+	struct drm_i915_private *dev_priv = crtc->dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	int pixel_size;
+	int drain_latency;
+	enum pipe pipe = intel_crtc->pipe;
+	int plane_prec, prec_mult, plane_dl;
+
+	plane_dl = I915_READ(VLV_DDL(pipe)) & ~(DDL_PLANE_PRECISION_64 |
+		   DRAIN_LATENCY_MASK | DDL_CURSOR_PRECISION_64 |
+		   (DRAIN_LATENCY_MASK << DDL_CURSOR_SHIFT));
 
-	/* For plane A, Cursor A */
-	if (vlv_compute_drain_latency(dev, 0, &plane_prec_mult, &planea_dl,
-				      &cursor_prec_mult, &cursora_dl)) {
-		cursora_prec = (cursor_prec_mult == DRAIN_LATENCY_PRECISION_32) ?
-			DDL_CURSORA_PRECISION_32 : DDL_CURSORA_PRECISION_64;
-		planea_prec = (plane_prec_mult == DRAIN_LATENCY_PRECISION_32) ?
-			DDL_PLANEA_PRECISION_32 : DDL_PLANEA_PRECISION_64;
+	if (!intel_crtc_active(crtc)) {
+		I915_WRITE(VLV_DDL(pipe), plane_dl);
+		return;
+	}
 
-		I915_WRITE(VLV_DDL1, cursora_prec |
-				(cursora_dl << DDL_CURSORA_SHIFT) |
-				planea_prec | planea_dl);
+	/* Primary plane Drain Latency */
+	pixel_size = crtc->primary->fb->bits_per_pixel / 8;	/* BPP */
+	if (vlv_compute_drain_latency(crtc, pixel_size, &prec_mult, &drain_latency)) {
+		plane_prec = (prec_mult == DRAIN_LATENCY_PRECISION_64) ?
+					   DDL_PLANE_PRECISION_64 :
+					   DDL_PLANE_PRECISION_32;
+		plane_dl |= plane_prec | drain_latency;
 	}
 
-	/* For plane B, Cursor B */
-	if (vlv_compute_drain_latency(dev, 1, &plane_prec_mult, &planeb_dl,
-				      &cursor_prec_mult, &cursorb_dl)) {
-		cursorb_prec = (cursor_prec_mult == DRAIN_LATENCY_PRECISION_32) ?
-			DDL_CURSORB_PRECISION_32 : DDL_CURSORB_PRECISION_64;
-		planeb_prec = (plane_prec_mult == DRAIN_LATENCY_PRECISION_32) ?
-			DDL_PLANEB_PRECISION_32 : DDL_PLANEB_PRECISION_64;
+	/* Cursor Drain Latency
+	 * BPP is always 4 for cursor
+	 */
+	pixel_size = 4;
 
-		I915_WRITE(VLV_DDL2, cursorb_prec |
-				(cursorb_dl << DDL_CURSORB_SHIFT) |
-				planeb_prec | planeb_dl);
+	/* Program cursor DL only if it is enabled */
+	if (intel_crtc->cursor_base &&
+	    vlv_compute_drain_latency(crtc, pixel_size, &prec_mult, &drain_latency)) {
+		plane_prec = (prec_mult == DRAIN_LATENCY_PRECISION_64) ?
+					   DDL_CURSOR_PRECISION_64 :
+					   DDL_CURSOR_PRECISION_32;
+		plane_dl |= plane_prec | (drain_latency << DDL_CURSOR_SHIFT);
 	}
+
+	I915_WRITE(VLV_DDL(pipe), plane_dl);
 }
 
 #define single_plane_enabled(mask) is_power_of_2(mask)
@@ -1355,20 +1395,92 @@ static void valleyview_update_wm(struct drm_crtc *crtc)
 	unsigned int enabled = 0;
 	bool cxsr_enabled;
 
-	vlv_update_drain_latency(dev);
+	vlv_update_drain_latency(crtc);
+
+	if (g4x_compute_wm0(dev, PIPE_A,
+			    &valleyview_wm_info, pessimal_latency_ns,
+			    &valleyview_cursor_wm_info, pessimal_latency_ns,
+			    &planea_wm, &cursora_wm))
+		enabled |= 1 << PIPE_A;
+
+	if (g4x_compute_wm0(dev, PIPE_B,
+			    &valleyview_wm_info, pessimal_latency_ns,
+			    &valleyview_cursor_wm_info, pessimal_latency_ns,
+			    &planeb_wm, &cursorb_wm))
+		enabled |= 1 << PIPE_B;
+
+	if (single_plane_enabled(enabled) &&
+	    g4x_compute_srwm(dev, ffs(enabled) - 1,
+			     sr_latency_ns,
+			     &valleyview_wm_info,
+			     &valleyview_cursor_wm_info,
+			     &plane_sr, &ignore_cursor_sr) &&
+	    g4x_compute_srwm(dev, ffs(enabled) - 1,
+			     2*sr_latency_ns,
+			     &valleyview_wm_info,
+			     &valleyview_cursor_wm_info,
+			     &ignore_plane_sr, &cursor_sr)) {
+		cxsr_enabled = true;
+	} else {
+		cxsr_enabled = false;
+		intel_set_memory_cxsr(dev_priv, false);
+		plane_sr = cursor_sr = 0;
+	}
+
+	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, "
+		      "B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n",
+		      planea_wm, cursora_wm,
+		      planeb_wm, cursorb_wm,
+		      plane_sr, cursor_sr);
+
+	I915_WRITE(DSPFW1,
+		   (plane_sr << DSPFW_SR_SHIFT) |
+		   (cursorb_wm << DSPFW_CURSORB_SHIFT) |
+		   (planeb_wm << DSPFW_PLANEB_SHIFT) |
+		   (planea_wm << DSPFW_PLANEA_SHIFT));
+	I915_WRITE(DSPFW2,
+		   (I915_READ(DSPFW2) & ~DSPFW_CURSORA_MASK) |
+		   (cursora_wm << DSPFW_CURSORA_SHIFT));
+	I915_WRITE(DSPFW3,
+		   (I915_READ(DSPFW3) & ~DSPFW_CURSOR_SR_MASK) |
+		   (cursor_sr << DSPFW_CURSOR_SR_SHIFT));
+
+	if (cxsr_enabled)
+		intel_set_memory_cxsr(dev_priv, true);
+}
+
+static void cherryview_update_wm(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	static const int sr_latency_ns = 12000;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int planea_wm, planeb_wm, planec_wm;
+	int cursora_wm, cursorb_wm, cursorc_wm;
+	int plane_sr, cursor_sr;
+	int ignore_plane_sr, ignore_cursor_sr;
+	unsigned int enabled = 0;
+	bool cxsr_enabled;
+
+	vlv_update_drain_latency(crtc);
 
 	if (g4x_compute_wm0(dev, PIPE_A,
-			    &valleyview_wm_info, latency_ns,
-			    &valleyview_cursor_wm_info, latency_ns,
+			    &valleyview_wm_info, pessimal_latency_ns,
+			    &valleyview_cursor_wm_info, pessimal_latency_ns,
 			    &planea_wm, &cursora_wm))
 		enabled |= 1 << PIPE_A;
 
 	if (g4x_compute_wm0(dev, PIPE_B,
-			    &valleyview_wm_info, latency_ns,
-			    &valleyview_cursor_wm_info, latency_ns,
+			    &valleyview_wm_info, pessimal_latency_ns,
+			    &valleyview_cursor_wm_info, pessimal_latency_ns,
 			    &planeb_wm, &cursorb_wm))
 		enabled |= 1 << PIPE_B;
 
+	if (g4x_compute_wm0(dev, PIPE_C,
+			    &valleyview_wm_info, pessimal_latency_ns,
+			    &valleyview_cursor_wm_info, pessimal_latency_ns,
+			    &planec_wm, &cursorc_wm))
+		enabled |= 1 << PIPE_C;
+
 	if (single_plane_enabled(enabled) &&
 	    g4x_compute_srwm(dev, ffs(enabled) - 1,
 			     sr_latency_ns,
@@ -1387,27 +1499,66 @@ static void valleyview_update_wm(struct drm_crtc *crtc)
 		plane_sr = cursor_sr = 0;
 	}
 
-	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n",
+	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, "
+		      "B: plane=%d, cursor=%d, C: plane=%d, cursor=%d, "
+		      "SR: plane=%d, cursor=%d\n",
 		      planea_wm, cursora_wm,
 		      planeb_wm, cursorb_wm,
+		      planec_wm, cursorc_wm,
 		      plane_sr, cursor_sr);
 
 	I915_WRITE(DSPFW1,
 		   (plane_sr << DSPFW_SR_SHIFT) |
 		   (cursorb_wm << DSPFW_CURSORB_SHIFT) |
 		   (planeb_wm << DSPFW_PLANEB_SHIFT) |
-		   planea_wm);
+		   (planea_wm << DSPFW_PLANEA_SHIFT));
 	I915_WRITE(DSPFW2,
 		   (I915_READ(DSPFW2) & ~DSPFW_CURSORA_MASK) |
 		   (cursora_wm << DSPFW_CURSORA_SHIFT));
 	I915_WRITE(DSPFW3,
 		   (I915_READ(DSPFW3) & ~DSPFW_CURSOR_SR_MASK) |
 		   (cursor_sr << DSPFW_CURSOR_SR_SHIFT));
+	I915_WRITE(DSPFW9_CHV,
+		   (I915_READ(DSPFW9_CHV) & ~(DSPFW_PLANEC_MASK |
+					      DSPFW_CURSORC_MASK)) |
+		   (planec_wm << DSPFW_PLANEC_SHIFT) |
+		   (cursorc_wm << DSPFW_CURSORC_SHIFT));
 
 	if (cxsr_enabled)
 		intel_set_memory_cxsr(dev_priv, true);
 }
 
+static void valleyview_update_sprite_wm(struct drm_plane *plane,
+					struct drm_crtc *crtc,
+					uint32_t sprite_width,
+					uint32_t sprite_height,
+					int pixel_size,
+					bool enabled, bool scaled)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int pipe = to_intel_plane(plane)->pipe;
+	int sprite = to_intel_plane(plane)->plane;
+	int drain_latency;
+	int plane_prec;
+	int sprite_dl;
+	int prec_mult;
+
+	sprite_dl = I915_READ(VLV_DDL(pipe)) & ~(DDL_SPRITE_PRECISION_64(sprite) |
+		    (DRAIN_LATENCY_MASK << DDL_SPRITE_SHIFT(sprite)));
+
+	if (enabled && vlv_compute_drain_latency(crtc, pixel_size, &prec_mult,
+						 &drain_latency)) {
+		plane_prec = (prec_mult == DRAIN_LATENCY_PRECISION_64) ?
+					   DDL_SPRITE_PRECISION_64(sprite) :
+					   DDL_SPRITE_PRECISION_32(sprite);
+		sprite_dl |= plane_prec |
+			     (drain_latency << DDL_SPRITE_SHIFT(sprite));
+	}
+
+	I915_WRITE(VLV_DDL(pipe), sprite_dl);
+}
+
 static void g4x_update_wm(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -1419,14 +1570,14 @@ static void g4x_update_wm(struct drm_crtc *crtc)
 	bool cxsr_enabled;
 
 	if (g4x_compute_wm0(dev, PIPE_A,
-			    &g4x_wm_info, latency_ns,
-			    &g4x_cursor_wm_info, latency_ns,
+			    &g4x_wm_info, pessimal_latency_ns,
+			    &g4x_cursor_wm_info, pessimal_latency_ns,
 			    &planea_wm, &cursora_wm))
 		enabled |= 1 << PIPE_A;
 
 	if (g4x_compute_wm0(dev, PIPE_B,
-			    &g4x_wm_info, latency_ns,
-			    &g4x_cursor_wm_info, latency_ns,
+			    &g4x_wm_info, pessimal_latency_ns,
+			    &g4x_cursor_wm_info, pessimal_latency_ns,
 			    &planeb_wm, &cursorb_wm))
 		enabled |= 1 << PIPE_B;
 
@@ -1443,7 +1594,8 @@ static void g4x_update_wm(struct drm_crtc *crtc)
 		plane_sr = cursor_sr = 0;
 	}
 
-	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n",
+	DRM_DEBUG_KMS("Setting FIFO watermarks - A: plane=%d, cursor=%d, "
+		      "B: plane=%d, cursor=%d, SR: plane=%d, cursor=%d\n",
 		      planea_wm, cursora_wm,
 		      planeb_wm, cursorb_wm,
 		      plane_sr, cursor_sr);
@@ -1452,7 +1604,7 @@ static void g4x_update_wm(struct drm_crtc *crtc)
 		   (plane_sr << DSPFW_SR_SHIFT) |
 		   (cursorb_wm << DSPFW_CURSORB_SHIFT) |
 		   (planeb_wm << DSPFW_PLANEB_SHIFT) |
-		   planea_wm);
+		   (planea_wm << DSPFW_PLANEA_SHIFT));
 	I915_WRITE(DSPFW2,
 		   (I915_READ(DSPFW2) & ~DSPFW_CURSORA_MASK) |
 		   (cursora_wm << DSPFW_CURSORA_SHIFT));
@@ -1526,8 +1678,11 @@ static void i965_update_wm(struct drm_crtc *unused_crtc)
 
 	/* 965 has limitations... */
 	I915_WRITE(DSPFW1, (srwm << DSPFW_SR_SHIFT) |
-		   (8 << 16) | (8 << 8) | (8 << 0));
-	I915_WRITE(DSPFW2, (8 << 8) | (8 << 0));
+		   (8 << DSPFW_CURSORB_SHIFT) |
+		   (8 << DSPFW_PLANEB_SHIFT) |
+		   (8 << DSPFW_PLANEA_SHIFT));
+	I915_WRITE(DSPFW2, (8 << DSPFW_CURSORA_SHIFT) |
+		   (8 << DSPFW_PLANEC_SHIFT_OLD));
 	/* update cursor SR watermark */
 	I915_WRITE(DSPFW3, (cursor_sr << DSPFW_CURSOR_SR_SHIFT));
 
@@ -1552,7 +1707,7 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 	else if (!IS_GEN2(dev))
 		wm_info = &i915_wm_info;
 	else
-		wm_info = &i830_wm_info;
+		wm_info = &i830_a_wm_info;
 
 	fifo_size = dev_priv->display.get_fifo_size(dev, 0);
 	crtc = intel_get_crtc_for_plane(dev, 0);
@@ -1565,10 +1720,16 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 		adjusted_mode = &to_intel_crtc(crtc)->config.adjusted_mode;
 		planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
 					       wm_info, fifo_size, cpp,
-					       latency_ns);
+					       pessimal_latency_ns);
 		enabled = crtc;
-	} else
+	} else {
 		planea_wm = fifo_size - wm_info->guard_size;
+		if (planea_wm > (long)wm_info->max_wm)
+			planea_wm = wm_info->max_wm;
+	}
+
+	if (IS_GEN2(dev))
+		wm_info = &i830_bc_wm_info;
 
 	fifo_size = dev_priv->display.get_fifo_size(dev, 1);
 	crtc = intel_get_crtc_for_plane(dev, 1);
@@ -1581,13 +1742,16 @@ static void i9xx_update_wm(struct drm_crtc *unused_crtc)
 		adjusted_mode = &to_intel_crtc(crtc)->config.adjusted_mode;
 		planeb_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
 					       wm_info, fifo_size, cpp,
-					       latency_ns);
+					       pessimal_latency_ns);
 		if (enabled == NULL)
 			enabled = crtc;
 		else
 			enabled = NULL;
-	} else
+	} else {
 		planeb_wm = fifo_size - wm_info->guard_size;
+		if (planeb_wm > (long)wm_info->max_wm)
+			planeb_wm = wm_info->max_wm;
+	}
 
 	DRM_DEBUG_KMS("FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm);
 
@@ -1674,7 +1838,7 @@ static void i845_update_wm(struct drm_crtc *unused_crtc)
 	planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
 				       &i845_wm_info,
 				       dev_priv->display.get_fifo_size(dev, 0),
-				       4, latency_ns);
+				       4, pessimal_latency_ns);
 	fwater_lo = I915_READ(FW_BLC) & ~0xfff;
 	fwater_lo |= (3<<8) | planea_wm;
 
@@ -2527,7 +2691,7 @@ static struct intel_pipe_wm *ilk_find_best_result(struct drm_device *dev,
 #define WM_DIRTY_FBC (1 << 24)
 #define WM_DIRTY_DDB (1 << 25)
 
-static unsigned int ilk_compute_wm_dirty(struct drm_device *dev,
+static unsigned int ilk_compute_wm_dirty(struct drm_i915_private *dev_priv,
 					 const struct ilk_wm_values *old,
 					 const struct ilk_wm_values *new)
 {
@@ -2535,7 +2699,7 @@ static unsigned int ilk_compute_wm_dirty(struct drm_device *dev,
 	enum pipe pipe;
 	int wm_lp;
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		if (old->wm_linetime[pipe] != new->wm_linetime[pipe]) {
 			dirty |= WM_DIRTY_LINETIME(pipe);
 			/* Must disable LP1+ watermarks too */
@@ -2621,7 +2785,7 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
 	unsigned int dirty;
 	uint32_t val;
 
-	dirty = ilk_compute_wm_dirty(dev, previous, results);
+	dirty = ilk_compute_wm_dirty(dev_priv, previous, results);
 	if (!dirty)
 		return;
 
@@ -3327,13 +3491,18 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 	WARN_ON(val > dev_priv->rps.max_freq_softlimit);
 	WARN_ON(val < dev_priv->rps.min_freq_softlimit);
 
-	DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
-			 dev_priv->rps.cur_freq,
-			 vlv_gpu_freq(dev_priv, val), val);
+	if (WARN_ONCE(IS_CHERRYVIEW(dev) && (val & 1),
+		      "Odd GPU freq value\n"))
+		val &= ~1;
+
+	if (val != dev_priv->rps.cur_freq) {
+		DRM_DEBUG_DRIVER("GPU freq request from %d MHz (%u) to %d MHz (%u)\n",
+				 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
+				 dev_priv->rps.cur_freq,
+				 vlv_gpu_freq(dev_priv, val), val);
 
-	if (val != dev_priv->rps.cur_freq)
 		vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
+	}
 
 	I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
 
@@ -3406,8 +3575,14 @@ static void valleyview_disable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	/* we're doing forcewake before Disabling RC6,
+	 * This what the BIOS expects when going into suspend */
+	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
+
 	I915_WRITE(GEN6_RC_CONTROL, 0);
 
+	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
+
 	gen6_disable_rps_interrupts(dev);
 }
 
@@ -3598,7 +3773,6 @@ static void gen6_enable_rps(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring;
 	u32 rp_state_cap;
-	u32 gt_perf_status;
 	u32 rc6vids, pcu_mbox = 0, rc6_mask = 0;
 	u32 gtfifodbg;
 	int rc6_mode;
@@ -3623,7 +3797,6 @@ static void gen6_enable_rps(struct drm_device *dev)
 	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
 
 	rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
-	gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
 
 	parse_rp_state_cap(dev_priv, rp_state_cap);
 
@@ -3965,11 +4138,27 @@ static void valleyview_cleanup_pctx(struct drm_device *dev)
 static void valleyview_init_gt_powersave(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 val;
 
 	valleyview_setup_pctx(dev);
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 
+	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
+	switch ((val >> 6) & 3) {
+	case 0:
+	case 1:
+		dev_priv->mem_freq = 800;
+		break;
+	case 2:
+		dev_priv->mem_freq = 1066;
+		break;
+	case 3:
+		dev_priv->mem_freq = 1333;
+		break;
+	}
+	DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
+
 	dev_priv->rps.max_freq = valleyview_rps_max_freq(dev_priv);
 	dev_priv->rps.rp0_freq = dev_priv->rps.max_freq;
 	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
@@ -4004,11 +4193,38 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
 static void cherryview_init_gt_powersave(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 val;
 
 	cherryview_setup_pctx(dev);
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 
+	val = vlv_punit_read(dev_priv, CCK_FUSE_REG);
+	switch ((val >> 2) & 0x7) {
+	case 0:
+	case 1:
+		dev_priv->rps.cz_freq = 200;
+		dev_priv->mem_freq = 1600;
+		break;
+	case 2:
+		dev_priv->rps.cz_freq = 267;
+		dev_priv->mem_freq = 1600;
+		break;
+	case 3:
+		dev_priv->rps.cz_freq = 333;
+		dev_priv->mem_freq = 2000;
+		break;
+	case 4:
+		dev_priv->rps.cz_freq = 320;
+		dev_priv->mem_freq = 1600;
+		break;
+	case 5:
+		dev_priv->rps.cz_freq = 400;
+		dev_priv->mem_freq = 1600;
+		break;
+	}
+	DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
+
 	dev_priv->rps.max_freq = cherryview_rps_max_freq(dev_priv);
 	dev_priv->rps.rp0_freq = dev_priv->rps.max_freq;
 	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
@@ -4030,6 +4246,12 @@ static void cherryview_init_gt_powersave(struct drm_device *dev)
 			 vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq),
 			 dev_priv->rps.min_freq);
 
+	WARN_ONCE((dev_priv->rps.max_freq |
+		   dev_priv->rps.efficient_freq |
+		   dev_priv->rps.rp1_freq |
+		   dev_priv->rps.min_freq) & 1,
+		  "Odd GPU freq values\n");
+
 	/* Preserve min/max settings in case of re-init */
 	if (dev_priv->rps.max_freq_softlimit == 0)
 		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
@@ -5088,7 +5310,7 @@ static void g4x_disable_trickle_feed(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe;
 
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		I915_WRITE(DSPCNTR(pipe),
 			   I915_READ(DSPCNTR(pipe)) |
 			   DISPPLANE_TRICKLE_FEED_DISABLE);
@@ -5203,7 +5425,7 @@ static void cpt_init_clock_gating(struct drm_device *dev)
 	/* The below fixes the weird display corruption, a few pixels shifted
 	 * downward, on (only) LVDS of some HP laptops with IVY.
 	 */
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		val = I915_READ(TRANS_CHICKEN2(pipe));
 		val |= TRANS_CHICKEN2_TIMING_OVERRIDE;
 		val &= ~TRANS_CHICKEN2_FDI_POLARITY_REVERSED;
@@ -5215,7 +5437,7 @@ static void cpt_init_clock_gating(struct drm_device *dev)
 		I915_WRITE(TRANS_CHICKEN2(pipe), val);
 	}
 	/* WADP0ClockGatingDisable */
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		I915_WRITE(TRANS_CHICKEN1(pipe),
 			   TRANS_CHICKEN1_DP0UNIT_GC_DISABLE);
 	}
@@ -5383,7 +5605,7 @@ static void lpt_suspend_hw(struct drm_device *dev)
 	}
 }
 
-static void gen8_init_clock_gating(struct drm_device *dev)
+static void broadwell_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum pipe pipe;
@@ -5395,37 +5617,12 @@ static void gen8_init_clock_gating(struct drm_device *dev)
 	/* FIXME(BDW): Check all the w/a, some might only apply to
 	 * pre-production hw. */
 
-	/* WaDisablePartialInstShootdown:bdw */
-	I915_WRITE(GEN8_ROW_CHICKEN,
-		   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
 
-	/* WaDisableThreadStallDopClockGating:bdw */
-	/* FIXME: Unclear whether we really need this on production bdw. */
-	I915_WRITE(GEN8_ROW_CHICKEN,
-		   _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
-
-	/*
-	 * This GEN8_CENTROID_PIXEL_OPT_DIS W/A is only needed for
-	 * pre-production hardware
-	 */
-	I915_WRITE(HALF_SLICE_CHICKEN3,
-		   _MASKED_BIT_ENABLE(GEN8_CENTROID_PIXEL_OPT_DIS));
-	I915_WRITE(HALF_SLICE_CHICKEN3,
-		   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
 	I915_WRITE(GAMTARBMODE, _MASKED_BIT_ENABLE(ARB_MODE_BWGTLB_DISABLE));
 
 	I915_WRITE(_3D_CHICKEN3,
 		   _MASKED_BIT_ENABLE(_3D_CHICKEN_SDE_LIMIT_FIFO_POLY_DEPTH(2)));
 
-	I915_WRITE(COMMON_SLICE_CHICKEN2,
-		   _MASKED_BIT_ENABLE(GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE));
-
-	I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
-		   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
-
-	/* WaDisableDopClockGating:bdw May not be needed for production */
-	I915_WRITE(GEN7_ROW_CHICKEN2,
-		   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 
 	/* WaSwitchSolVfFArbitrationPriority:bdw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
@@ -5435,37 +5632,18 @@ static void gen8_init_clock_gating(struct drm_device *dev)
 		   I915_READ(CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD);
 
 	/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
-	for_each_pipe(pipe) {
+	for_each_pipe(dev_priv, pipe) {
 		I915_WRITE(CHICKEN_PIPESL_1(pipe),
 			   I915_READ(CHICKEN_PIPESL_1(pipe)) |
 			   BDW_DPRS_MASK_VBLANK_SRD);
 	}
 
-	/* Use Force Non-Coherent whenever executing a 3D context. This is a
-	 * workaround for for a possible hang in the unlikely event a TLB
-	 * invalidation occurs during a PSD flush.
-	 */
-	I915_WRITE(HDC_CHICKEN0,
-		   I915_READ(HDC_CHICKEN0) |
-		   _MASKED_BIT_ENABLE(HDC_FORCE_NON_COHERENT));
-
 	/* WaVSRefCountFullforceMissDisable:bdw */
 	/* WaDSRefCountFullforceMissDisable:bdw */
 	I915_WRITE(GEN7_FF_THREAD_MODE,
 		   I915_READ(GEN7_FF_THREAD_MODE) &
 		   ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME));
 
-	/*
-	 * BSpec recommends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	I915_WRITE(GEN7_GT_MODE,
-		   GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
-
 	I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL,
 		   _MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE));
 
@@ -5473,9 +5651,7 @@ static void gen8_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
-	/* Wa4x4STCOptimizationDisable:bdw */
-	I915_WRITE(CACHE_MODE_1,
-		   _MASKED_BIT_ENABLE(GEN8_4x4_STC_OPTIMIZATION_DISABLE));
+	lpt_init_clock_gating(dev);
 }
 
 static void haswell_init_clock_gating(struct drm_device *dev)
@@ -5631,24 +5807,6 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 static void valleyview_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 val;
-
-	mutex_lock(&dev_priv->rps.hw_lock);
-	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-	mutex_unlock(&dev_priv->rps.hw_lock);
-	switch ((val >> 6) & 3) {
-	case 0:
-	case 1:
-		dev_priv->mem_freq = 800;
-		break;
-	case 2:
-		dev_priv->mem_freq = 1066;
-		break;
-	case 3:
-		dev_priv->mem_freq = 1333;
-		break;
-	}
-	DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
 
 	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
 
@@ -5724,48 +5882,11 @@ static void valleyview_init_clock_gating(struct drm_device *dev)
 static void cherryview_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 val;
-
-	mutex_lock(&dev_priv->rps.hw_lock);
-	val = vlv_punit_read(dev_priv, CCK_FUSE_REG);
-	mutex_unlock(&dev_priv->rps.hw_lock);
-	switch ((val >> 2) & 0x7) {
-	case 0:
-	case 1:
-			dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_200;
-			dev_priv->mem_freq = 1600;
-			break;
-	case 2:
-			dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_267;
-			dev_priv->mem_freq = 1600;
-			break;
-	case 3:
-			dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_333;
-			dev_priv->mem_freq = 2000;
-			break;
-	case 4:
-			dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_320;
-			dev_priv->mem_freq = 1600;
-			break;
-	case 5:
-			dev_priv->rps.cz_freq = CHV_CZ_CLOCK_FREQ_MODE_400;
-			dev_priv->mem_freq = 1600;
-			break;
-	}
-	DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
 
 	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
 
 	I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE);
 
-	/* WaDisablePartialInstShootdown:chv */
-	I915_WRITE(GEN8_ROW_CHICKEN,
-		   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
-
-	/* WaDisableThreadStallDopClockGating:chv */
-	I915_WRITE(GEN8_ROW_CHICKEN,
-		   _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
-
 	/* WaVSRefCountFullforceMissDisable:chv */
 	/* WaDSRefCountFullforceMissDisable:chv */
 	I915_WRITE(GEN7_FF_THREAD_MODE,
@@ -5784,10 +5905,6 @@ static void cherryview_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
-	/* WaDisableSamplerPowerBypass:chv (pre-production hw) */
-	I915_WRITE(HALF_SLICE_CHICKEN3,
-		   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
-
 	/* WaDisableGunitClockGating:chv (pre-production hw) */
 	I915_WRITE(VLV_GUNIT_CLOCK_GATE, I915_READ(VLV_GUNIT_CLOCK_GATE) |
 		   GINT_DIS);
@@ -5797,8 +5914,6 @@ static void cherryview_init_clock_gating(struct drm_device *dev)
 		   _MASKED_BIT_ENABLE(GEN8_FF_DOP_CLOCK_GATE_DISABLE));
 
 	/* WaDisableDopClockGating:chv (pre-production hw) */
-	I915_WRITE(GEN7_ROW_CHICKEN2,
-		   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 	I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
 		   GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE);
 }
@@ -5883,6 +5998,9 @@ static void gen3_init_clock_gating(struct drm_device *dev)
 
 	/* On GEN3 we really need to make sure the ARB C3 LP bit is set */
 	I915_WRITE(MI_ARB_STATE, _MASKED_BIT_ENABLE(MI_ARB_C3_LP_WRITE_ENABLE));
+
+	I915_WRITE(MI_ARB_STATE,
+		   _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
 }
 
 static void i85x_init_clock_gating(struct drm_device *dev)
@@ -5894,6 +6012,9 @@ static void i85x_init_clock_gating(struct drm_device *dev)
 	/* interrupts should cause a wake up from C3 */
 	I915_WRITE(MI_STATE, _MASKED_BIT_ENABLE(MI_AGPBUSY_INT_EN) |
 		   _MASKED_BIT_DISABLE(MI_AGPBUSY_830_MODE));
+
+	I915_WRITE(MEM_MODE,
+		   _MASKED_BIT_ENABLE(MEM_DISPLAY_TRICKLE_FEED_DISABLE));
 }
 
 static void i830_init_clock_gating(struct drm_device *dev)
@@ -5901,6 +6022,10 @@ static void i830_init_clock_gating(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	I915_WRITE(DSPCLK_GATE_D, OVRUNIT_CLOCK_GATE_DISABLE);
+
+	I915_WRITE(MEM_MODE,
+		   _MASKED_BIT_ENABLE(MEM_DISPLAY_A_TRICKLE_FEED_DISABLE) |
+		   _MASKED_BIT_ENABLE(MEM_DISPLAY_B_TRICKLE_FEED_DISABLE));
 }
 
 void intel_init_clock_gating(struct drm_device *dev)
@@ -6203,6 +6328,8 @@ static void vlv_display_power_well_disable(struct drm_i915_private *dev_priv,
 	spin_unlock_irq(&dev_priv->irq_lock);
 
 	vlv_set_power_well(dev_priv, power_well, false);
+
+	vlv_power_sequencer_reset(dev_priv);
 }
 
 static void vlv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv,
@@ -6238,12 +6365,11 @@ static void vlv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv,
 static void vlv_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv,
 					    struct i915_power_well *power_well)
 {
-	struct drm_device *dev = dev_priv->dev;
 	enum pipe pipe;
 
 	WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DPIO_CMN_BC);
 
-	for_each_pipe(pipe)
+	for_each_pipe(dev_priv, pipe)
 		assert_pll_disabled(dev_priv, pipe);
 
 	/* Assert common reset */
@@ -6252,6 +6378,153 @@ static void vlv_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv,
 	vlv_set_power_well(dev_priv, power_well, false);
 }
 
+static void chv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv,
+					   struct i915_power_well *power_well)
+{
+	enum dpio_phy phy;
+
+	WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DPIO_CMN_BC &&
+		     power_well->data != PUNIT_POWER_WELL_DPIO_CMN_D);
+
+	/*
+	 * Enable the CRI clock source so we can get at the
+	 * display and the reference clock for VGA
+	 * hotplug / manual detection.
+	 */
+	if (power_well->data == PUNIT_POWER_WELL_DPIO_CMN_BC) {
+		phy = DPIO_PHY0;
+		I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) |
+			   DPLL_REFA_CLK_ENABLE_VLV);
+		I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) |
+			   DPLL_REFA_CLK_ENABLE_VLV | DPLL_INTEGRATED_CRI_CLK_VLV);
+	} else {
+		phy = DPIO_PHY1;
+		I915_WRITE(DPLL(PIPE_C), I915_READ(DPLL(PIPE_C)) |
+			   DPLL_REFA_CLK_ENABLE_VLV | DPLL_INTEGRATED_CRI_CLK_VLV);
+	}
+	udelay(1); /* >10ns for cmnreset, >0ns for sidereset */
+	vlv_set_power_well(dev_priv, power_well, true);
+
+	/* Poll for phypwrgood signal */
+	if (wait_for(I915_READ(DISPLAY_PHY_STATUS) & PHY_POWERGOOD(phy), 1))
+		DRM_ERROR("Display PHY %d is not power up\n", phy);
+
+	I915_WRITE(DISPLAY_PHY_CONTROL, I915_READ(DISPLAY_PHY_CONTROL) |
+		   PHY_COM_LANE_RESET_DEASSERT(phy));
+}
+
+static void chv_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv,
+					    struct i915_power_well *power_well)
+{
+	enum dpio_phy phy;
+
+	WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DPIO_CMN_BC &&
+		     power_well->data != PUNIT_POWER_WELL_DPIO_CMN_D);
+
+	if (power_well->data == PUNIT_POWER_WELL_DPIO_CMN_BC) {
+		phy = DPIO_PHY0;
+		assert_pll_disabled(dev_priv, PIPE_A);
+		assert_pll_disabled(dev_priv, PIPE_B);
+	} else {
+		phy = DPIO_PHY1;
+		assert_pll_disabled(dev_priv, PIPE_C);
+	}
+
+	I915_WRITE(DISPLAY_PHY_CONTROL, I915_READ(DISPLAY_PHY_CONTROL) &
+		   ~PHY_COM_LANE_RESET_DEASSERT(phy));
+
+	vlv_set_power_well(dev_priv, power_well, false);
+}
+
+static bool chv_pipe_power_well_enabled(struct drm_i915_private *dev_priv,
+					struct i915_power_well *power_well)
+{
+	enum pipe pipe = power_well->data;
+	bool enabled;
+	u32 state, ctrl;
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+
+	state = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ) & DP_SSS_MASK(pipe);
+	/*
+	 * We only ever set the power-on and power-gate states, anything
+	 * else is unexpected.
+	 */
+	WARN_ON(state != DP_SSS_PWR_ON(pipe) && state != DP_SSS_PWR_GATE(pipe));
+	enabled = state == DP_SSS_PWR_ON(pipe);
+
+	/*
+	 * A transient state at this point would mean some unexpected party
+	 * is poking at the power controls too.
+	 */
+	ctrl = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ) & DP_SSC_MASK(pipe);
+	WARN_ON(ctrl << 16 != state);
+
+	mutex_unlock(&dev_priv->rps.hw_lock);
+
+	return enabled;
+}
+
+static void chv_set_pipe_power_well(struct drm_i915_private *dev_priv,
+				    struct i915_power_well *power_well,
+				    bool enable)
+{
+	enum pipe pipe = power_well->data;
+	u32 state;
+	u32 ctrl;
+
+	state = enable ? DP_SSS_PWR_ON(pipe) : DP_SSS_PWR_GATE(pipe);
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+
+#define COND \
+	((vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ) & DP_SSS_MASK(pipe)) == state)
+
+	if (COND)
+		goto out;
+
+	ctrl = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ);
+	ctrl &= ~DP_SSC_MASK(pipe);
+	ctrl |= enable ? DP_SSC_PWR_ON(pipe) : DP_SSC_PWR_GATE(pipe);
+	vlv_punit_write(dev_priv, PUNIT_REG_DSPFREQ, ctrl);
+
+	if (wait_for(COND, 100))
+		DRM_ERROR("timout setting power well state %08x (%08x)\n",
+			  state,
+			  vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ));
+
+#undef COND
+
+out:
+	mutex_unlock(&dev_priv->rps.hw_lock);
+}
+
+static void chv_pipe_power_well_sync_hw(struct drm_i915_private *dev_priv,
+					struct i915_power_well *power_well)
+{
+	chv_set_pipe_power_well(dev_priv, power_well, power_well->count > 0);
+}
+
+static void chv_pipe_power_well_enable(struct drm_i915_private *dev_priv,
+				       struct i915_power_well *power_well)
+{
+	WARN_ON_ONCE(power_well->data != PIPE_A &&
+		     power_well->data != PIPE_B &&
+		     power_well->data != PIPE_C);
+
+	chv_set_pipe_power_well(dev_priv, power_well, true);
+}
+
+static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv,
+					struct i915_power_well *power_well)
+{
+	WARN_ON_ONCE(power_well->data != PIPE_A &&
+		     power_well->data != PIPE_B &&
+		     power_well->data != PIPE_C);
+
+	chv_set_pipe_power_well(dev_priv, power_well, false);
+}
+
 static void check_power_well_state(struct drm_i915_private *dev_priv,
 				   struct i915_power_well *power_well)
 {
@@ -6443,6 +6716,39 @@ EXPORT_SYMBOL_GPL(i915_get_cdclk_freq);
 	BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) |	\
 	BIT(POWER_DOMAIN_INIT))
 
+#define CHV_PIPE_A_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PIPE_A) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_PIPE_B_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PIPE_B) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_PIPE_C_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PIPE_C) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_DPIO_CMN_BC_POWER_DOMAINS (		\
+	BIT(POWER_DOMAIN_PORT_DDI_B_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_B_4_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_C_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_C_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_DPIO_CMN_D_POWER_DOMAINS (		\
+	BIT(POWER_DOMAIN_PORT_DDI_D_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_D_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_DPIO_TX_D_LANES_01_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PORT_DDI_D_2_LANES) |	\
+	BIT(POWER_DOMAIN_PORT_DDI_D_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
+#define CHV_DPIO_TX_D_LANES_23_POWER_DOMAINS (	\
+	BIT(POWER_DOMAIN_PORT_DDI_D_4_LANES) |	\
+	BIT(POWER_DOMAIN_INIT))
+
 static const struct i915_power_well_ops i9xx_always_on_power_well_ops = {
 	.sync_hw = i9xx_always_on_power_well_noop,
 	.enable = i9xx_always_on_power_well_noop,
@@ -6450,6 +6756,20 @@ static const struct i915_power_well_ops i9xx_always_on_power_well_ops = {
 	.is_enabled = i9xx_always_on_power_well_enabled,
 };
 
+static const struct i915_power_well_ops chv_pipe_power_well_ops = {
+	.sync_hw = chv_pipe_power_well_sync_hw,
+	.enable = chv_pipe_power_well_enable,
+	.disable = chv_pipe_power_well_disable,
+	.is_enabled = chv_pipe_power_well_enabled,
+};
+
+static const struct i915_power_well_ops chv_dpio_cmn_power_well_ops = {
+	.sync_hw = vlv_power_well_sync_hw,
+	.enable = chv_dpio_cmn_power_well_enable,
+	.disable = chv_dpio_cmn_power_well_disable,
+	.is_enabled = vlv_power_well_enabled,
+};
+
 static struct i915_power_well i9xx_always_on_power_well[] = {
 	{
 		.name = "always-on",
@@ -6572,6 +6892,107 @@ static struct i915_power_well vlv_power_wells[] = {
 	},
 };
 
+static struct i915_power_well chv_power_wells[] = {
+	{
+		.name = "always-on",
+		.always_on = 1,
+		.domains = VLV_ALWAYS_ON_POWER_DOMAINS,
+		.ops = &i9xx_always_on_power_well_ops,
+	},
+#if 0
+	{
+		.name = "display",
+		.domains = VLV_DISPLAY_POWER_DOMAINS,
+		.data = PUNIT_POWER_WELL_DISP2D,
+		.ops = &vlv_display_power_well_ops,
+	},
+	{
+		.name = "pipe-a",
+		.domains = CHV_PIPE_A_POWER_DOMAINS,
+		.data = PIPE_A,
+		.ops = &chv_pipe_power_well_ops,
+	},
+	{
+		.name = "pipe-b",
+		.domains = CHV_PIPE_B_POWER_DOMAINS,
+		.data = PIPE_B,
+		.ops = &chv_pipe_power_well_ops,
+	},
+	{
+		.name = "pipe-c",
+		.domains = CHV_PIPE_C_POWER_DOMAINS,
+		.data = PIPE_C,
+		.ops = &chv_pipe_power_well_ops,
+	},
+#endif
+	{
+		.name = "dpio-common-bc",
+		/*
+		 * XXX: cmnreset for one PHY seems to disturb the other.
+		 * As a workaround keep both powered on at the same
+		 * time for now.
+		 */
+		.domains = CHV_DPIO_CMN_BC_POWER_DOMAINS | CHV_DPIO_CMN_D_POWER_DOMAINS,
+		.data = PUNIT_POWER_WELL_DPIO_CMN_BC,
+		.ops = &chv_dpio_cmn_power_well_ops,
+	},
+	{
+		.name = "dpio-common-d",
+		/*
+		 * XXX: cmnreset for one PHY seems to disturb the other.
+		 * As a workaround keep both powered on at the same
+		 * time for now.
+		 */
+		.domains = CHV_DPIO_CMN_BC_POWER_DOMAINS | CHV_DPIO_CMN_D_POWER_DOMAINS,
+		.data = PUNIT_POWER_WELL_DPIO_CMN_D,
+		.ops = &chv_dpio_cmn_power_well_ops,
+	},
+#if 0
+	{
+		.name = "dpio-tx-b-01",
+		.domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_B_LANES_01,
+	},
+	{
+		.name = "dpio-tx-b-23",
+		.domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_B_LANES_23,
+	},
+	{
+		.name = "dpio-tx-c-01",
+		.domains = VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_C_LANES_01,
+	},
+	{
+		.name = "dpio-tx-c-23",
+		.domains = VLV_DPIO_TX_C_LANES_01_POWER_DOMAINS |
+			   VLV_DPIO_TX_C_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_C_LANES_23,
+	},
+	{
+		.name = "dpio-tx-d-01",
+		.domains = CHV_DPIO_TX_D_LANES_01_POWER_DOMAINS |
+			   CHV_DPIO_TX_D_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_D_LANES_01,
+	},
+	{
+		.name = "dpio-tx-d-23",
+		.domains = CHV_DPIO_TX_D_LANES_01_POWER_DOMAINS |
+			   CHV_DPIO_TX_D_LANES_23_POWER_DOMAINS,
+		.ops = &vlv_dpio_power_well_ops,
+		.data = PUNIT_POWER_WELL_DPIO_TX_D_LANES_23,
+	},
+#endif
+};
+
 static struct i915_power_well *lookup_power_well(struct drm_i915_private *dev_priv,
 						 enum punit_power_well power_well_id)
 {
@@ -6608,6 +7029,8 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 	} else if (IS_BROADWELL(dev_priv->dev)) {
 		set_power_wells(power_domains, bdw_power_wells);
 		hsw_pwr = power_domains;
+	} else if (IS_CHERRYVIEW(dev_priv->dev)) {
+		set_power_wells(power_domains, chv_power_wells);
 	} else if (IS_VALLEYVIEW(dev_priv->dev)) {
 		set_power_wells(power_domains, vlv_power_wells);
 	} else {
@@ -6833,13 +7256,15 @@ void intel_init_pm(struct drm_device *dev)
 		else if (IS_HASWELL(dev))
 			dev_priv->display.init_clock_gating = haswell_init_clock_gating;
 		else if (INTEL_INFO(dev)->gen == 8)
-			dev_priv->display.init_clock_gating = gen8_init_clock_gating;
+			dev_priv->display.init_clock_gating = broadwell_init_clock_gating;
 	} else if (IS_CHERRYVIEW(dev)) {
-		dev_priv->display.update_wm = valleyview_update_wm;
+		dev_priv->display.update_wm = cherryview_update_wm;
+		dev_priv->display.update_sprite_wm = valleyview_update_sprite_wm;
 		dev_priv->display.init_clock_gating =
 			cherryview_init_clock_gating;
 	} else if (IS_VALLEYVIEW(dev)) {
 		dev_priv->display.update_wm = valleyview_update_wm;
+		dev_priv->display.update_sprite_wm = valleyview_update_sprite_wm;
 		dev_priv->display.init_clock_gating =
 			valleyview_init_clock_gating;
 	} else if (IS_PINEVIEW(dev)) {
@@ -7025,6 +7450,7 @@ static int chv_freq_opcode(struct drm_i915_private *dev_priv, int val)
 		return -1;
 	}
 
+	/* CHV needs even values */
 	opcode = (DIV_ROUND_CLOSEST((val * 2 * mul), dev_priv->rps.cz_freq) * 2);
 
 	return opcode;
diff --git a/drivers/gpu/drm/i915/intel_renderstate.h b/drivers/gpu/drm/i915/intel_renderstate.h
index fd4f66231d30..6c792d3a9c9c 100644
--- a/drivers/gpu/drm/i915/intel_renderstate.h
+++ b/drivers/gpu/drm/i915/intel_renderstate.h
@@ -24,13 +24,7 @@
 #ifndef _INTEL_RENDERSTATE_H
 #define _INTEL_RENDERSTATE_H
 
-#include <linux/types.h>
-
-struct intel_renderstate_rodata {
-	const u32 *reloc;
-	const u32 *batch;
-	const u32 batch_items;
-};
+#include "i915_drv.h"
 
 extern const struct intel_renderstate_rodata gen6_null_state;
 extern const struct intel_renderstate_rodata gen7_null_state;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 47a126a0493f..0a80e419b589 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -33,14 +33,24 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
-/* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
- * but keeps the logic simple. Indeed, the whole purpose of this macro is just
- * to give some inclination as to some of the magic values used in the various
- * workarounds!
- */
-#define CACHELINE_BYTES 64
+bool
+intel_ring_initialized(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+
+	if (!dev)
+		return false;
+
+	if (i915.enable_execlists) {
+		struct intel_context *dctx = ring->default_context;
+		struct intel_ringbuffer *ringbuf = dctx->engine[ring->id].ringbuf;
+
+		return ringbuf->obj;
+	} else
+		return ring->buffer && ring->buffer->obj;
+}
 
-static inline int __ring_space(int head, int tail, int size)
+int __intel_ring_space(int head, int tail, int size)
 {
 	int space = head - (tail + I915_RING_FREE_SPACE);
 	if (space < 0)
@@ -48,12 +58,13 @@ static inline int __ring_space(int head, int tail, int size)
 	return space;
 }
 
-static inline int ring_space(struct intel_ringbuffer *ringbuf)
+int intel_ring_space(struct intel_ringbuffer *ringbuf)
 {
-	return __ring_space(ringbuf->head & HEAD_ADDR, ringbuf->tail, ringbuf->size);
+	return __intel_ring_space(ringbuf->head & HEAD_ADDR,
+				  ringbuf->tail, ringbuf->size);
 }
 
-static bool intel_ring_stopped(struct intel_engine_cs *ring)
+bool intel_ring_stopped(struct intel_engine_cs *ring)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	return dev_priv->gpu_error.stop_rings & intel_ring_flag(ring);
@@ -433,7 +444,14 @@ gen8_render_ring_flush(struct intel_engine_cs *ring,
 			return ret;
 	}
 
-	return gen8_emit_pipe_control(ring, flags, scratch_addr);
+	ret = gen8_emit_pipe_control(ring, flags, scratch_addr);
+	if (ret)
+		return ret;
+
+	if (!invalidate_domains && flush_domains)
+		return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
+
+	return 0;
 }
 
 static void ring_write_tail(struct intel_engine_cs *ring,
@@ -476,9 +494,14 @@ static bool stop_ring(struct intel_engine_cs *ring)
 
 	if (!IS_GEN2(ring->dev)) {
 		I915_WRITE_MODE(ring, _MASKED_BIT_ENABLE(STOP_RING));
-		if (wait_for_atomic((I915_READ_MODE(ring) & MODE_IDLE) != 0, 1000)) {
-			DRM_ERROR("%s :timed out trying to stop ring\n", ring->name);
-			return false;
+		if (wait_for((I915_READ_MODE(ring) & MODE_IDLE) != 0, 1000)) {
+			DRM_ERROR("%s : timed out trying to stop ring\n", ring->name);
+			/* Sometimes we observe that the idle flag is not
+			 * set even though the ring is empty. So double
+			 * check before giving up.
+			 */
+			if (I915_READ_HEAD(ring) != I915_READ_TAIL(ring))
+				return false;
 		}
 	}
 
@@ -540,6 +563,14 @@ static int init_ring_common(struct intel_engine_cs *ring)
 	 * also enforces ordering), otherwise the hw might lose the new ring
 	 * register values. */
 	I915_WRITE_START(ring, i915_gem_obj_ggtt_offset(obj));
+
+	/* WaClearRingBufHeadRegAtInit:ctg,elk */
+	if (I915_READ_HEAD(ring))
+		DRM_DEBUG("%s initialization failed [head=%08x], fudging\n",
+			  ring->name, I915_READ_HEAD(ring));
+	I915_WRITE_HEAD(ring, 0);
+	(void)I915_READ_HEAD(ring);
+
 	I915_WRITE_CTL(ring,
 			((ringbuf->size - PAGE_SIZE) & RING_NR_PAGES)
 			| RING_VALID);
@@ -563,7 +594,7 @@ static int init_ring_common(struct intel_engine_cs *ring)
 	else {
 		ringbuf->head = I915_READ_HEAD(ring);
 		ringbuf->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
-		ringbuf->space = ring_space(ringbuf);
+		ringbuf->space = intel_ring_space(ringbuf);
 		ringbuf->last_retired_head = -1;
 	}
 
@@ -575,8 +606,25 @@ out:
 	return ret;
 }
 
-static int
-init_pipe_control(struct intel_engine_cs *ring)
+void
+intel_fini_pipe_control(struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = ring->dev;
+
+	if (ring->scratch.obj == NULL)
+		return;
+
+	if (INTEL_INFO(dev)->gen >= 5) {
+		kunmap(sg_page(ring->scratch.obj->pages->sgl));
+		i915_gem_object_ggtt_unpin(ring->scratch.obj);
+	}
+
+	drm_gem_object_unreference(&ring->scratch.obj->base);
+	ring->scratch.obj = NULL;
+}
+
+int
+intel_init_pipe_control(struct intel_engine_cs *ring)
 {
 	int ret;
 
@@ -617,6 +665,135 @@ err:
 	return ret;
 }
 
+static inline void intel_ring_emit_wa(struct intel_engine_cs *ring,
+				       u32 addr, u32 value)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (WARN_ON(dev_priv->num_wa_regs >= I915_MAX_WA_REGS))
+		return;
+
+	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
+	intel_ring_emit(ring, addr);
+	intel_ring_emit(ring, value);
+
+	dev_priv->intel_wa_regs[dev_priv->num_wa_regs].addr = addr;
+	dev_priv->intel_wa_regs[dev_priv->num_wa_regs].mask = value & 0xFFFF;
+	/* value is updated with the status of remaining bits of this
+	 * register when it is read from debugfs file
+	 */
+	dev_priv->intel_wa_regs[dev_priv->num_wa_regs].value = value;
+	dev_priv->num_wa_regs++;
+
+	return;
+}
+
+static int bdw_init_workarounds(struct intel_engine_cs *ring)
+{
+	int ret;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/*
+	 * workarounds applied in this fn are part of register state context,
+	 * they need to be re-initialized followed by gpu reset, suspend/resume,
+	 * module reload.
+	 */
+	dev_priv->num_wa_regs = 0;
+	memset(dev_priv->intel_wa_regs, 0, sizeof(dev_priv->intel_wa_regs));
+
+	/*
+	 * update the number of dwords required based on the
+	 * actual number of workarounds applied
+	 */
+	ret = intel_ring_begin(ring, 18);
+	if (ret)
+		return ret;
+
+	/* WaDisablePartialInstShootdown:bdw */
+	/* WaDisableThreadStallDopClockGating:bdw */
+	/* FIXME: Unclear whether we really need this on production bdw. */
+	intel_ring_emit_wa(ring, GEN8_ROW_CHICKEN,
+			   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE
+					     | STALL_DOP_GATING_DISABLE));
+
+	/* WaDisableDopClockGating:bdw May not be needed for production */
+	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
+			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+
+	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
+			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
+
+	/* Use Force Non-Coherent whenever executing a 3D context. This is a
+	 * workaround for for a possible hang in the unlikely event a TLB
+	 * invalidation occurs during a PSD flush.
+	 */
+	intel_ring_emit_wa(ring, HDC_CHICKEN0,
+			   _MASKED_BIT_ENABLE(HDC_FORCE_NON_COHERENT));
+
+	/* Wa4x4STCOptimizationDisable:bdw */
+	intel_ring_emit_wa(ring, CACHE_MODE_1,
+			   _MASKED_BIT_ENABLE(GEN8_4x4_STC_OPTIMIZATION_DISABLE));
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	intel_ring_emit_wa(ring, GEN7_GT_MODE,
+			   GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
+
+	intel_ring_advance(ring);
+
+	DRM_DEBUG_DRIVER("Number of Workarounds applied: %d\n",
+			 dev_priv->num_wa_regs);
+
+	return 0;
+}
+
+static int chv_init_workarounds(struct intel_engine_cs *ring)
+{
+	int ret;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/*
+	 * workarounds applied in this fn are part of register state context,
+	 * they need to be re-initialized followed by gpu reset, suspend/resume,
+	 * module reload.
+	 */
+	dev_priv->num_wa_regs = 0;
+	memset(dev_priv->intel_wa_regs, 0, sizeof(dev_priv->intel_wa_regs));
+
+	ret = intel_ring_begin(ring, 12);
+	if (ret)
+		return ret;
+
+	/* WaDisablePartialInstShootdown:chv */
+	intel_ring_emit_wa(ring, GEN8_ROW_CHICKEN,
+			   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
+
+	/* WaDisableThreadStallDopClockGating:chv */
+	intel_ring_emit_wa(ring, GEN8_ROW_CHICKEN,
+			   _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
+
+	/* WaDisableDopClockGating:chv (pre-production hw) */
+	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
+			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+
+	/* WaDisableSamplerPowerBypass:chv (pre-production hw) */
+	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
+			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
+
+	intel_ring_advance(ring);
+
+	return 0;
+}
+
 static int init_render_ring(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
@@ -651,7 +828,7 @@ static int init_render_ring(struct intel_engine_cs *ring)
 			   _MASKED_BIT_ENABLE(GFX_REPLAY_MODE));
 
 	if (INTEL_INFO(dev)->gen >= 5) {
-		ret = init_pipe_control(ring);
+		ret = intel_init_pipe_control(ring);
 		if (ret)
 			return ret;
 	}
@@ -686,16 +863,7 @@ static void render_ring_cleanup(struct intel_engine_cs *ring)
 		dev_priv->semaphore_obj = NULL;
 	}
 
-	if (ring->scratch.obj == NULL)
-		return;
-
-	if (INTEL_INFO(dev)->gen >= 5) {
-		kunmap(sg_page(ring->scratch.obj->pages->sgl));
-		i915_gem_object_ggtt_unpin(ring->scratch.obj);
-	}
-
-	drm_gem_object_unreference(&ring->scratch.obj->base);
-	ring->scratch.obj = NULL;
+	intel_fini_pipe_control(ring);
 }
 
 static int gen8_rcs_signal(struct intel_engine_cs *signaller,
@@ -1526,7 +1694,7 @@ static int init_phys_status_page(struct intel_engine_cs *ring)
 	return 0;
 }
 
-static void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
+void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
 {
 	if (!ringbuf->obj)
 		return;
@@ -1537,8 +1705,8 @@ static void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
 	ringbuf->obj = NULL;
 }
 
-static int intel_alloc_ringbuffer_obj(struct drm_device *dev,
-				      struct intel_ringbuffer *ringbuf)
+int intel_alloc_ringbuffer_obj(struct drm_device *dev,
+			       struct intel_ringbuffer *ringbuf)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
@@ -1600,7 +1768,9 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 	ring->dev = dev;
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
+	INIT_LIST_HEAD(&ring->execlist_queue);
 	ringbuf->size = 32 * PAGE_SIZE;
+	ringbuf->ring = ring;
 	memset(ring->semaphore.sync_seqno, 0, sizeof(ring->semaphore.sync_seqno));
 
 	init_waitqueue_head(&ring->irq_queue);
@@ -1683,13 +1853,14 @@ static int intel_ring_wait_request(struct intel_engine_cs *ring, int n)
 		ringbuf->head = ringbuf->last_retired_head;
 		ringbuf->last_retired_head = -1;
 
-		ringbuf->space = ring_space(ringbuf);
+		ringbuf->space = intel_ring_space(ringbuf);
 		if (ringbuf->space >= n)
 			return 0;
 	}
 
 	list_for_each_entry(request, &ring->request_list, list) {
-		if (__ring_space(request->tail, ringbuf->tail, ringbuf->size) >= n) {
+		if (__intel_ring_space(request->tail, ringbuf->tail,
+				       ringbuf->size) >= n) {
 			seqno = request->seqno;
 			break;
 		}
@@ -1706,7 +1877,7 @@ static int intel_ring_wait_request(struct intel_engine_cs *ring, int n)
 	ringbuf->head = ringbuf->last_retired_head;
 	ringbuf->last_retired_head = -1;
 
-	ringbuf->space = ring_space(ringbuf);
+	ringbuf->space = intel_ring_space(ringbuf);
 	return 0;
 }
 
@@ -1735,7 +1906,7 @@ static int ring_wait_for_space(struct intel_engine_cs *ring, int n)
 	trace_i915_ring_wait_begin(ring);
 	do {
 		ringbuf->head = I915_READ_HEAD(ring);
-		ringbuf->space = ring_space(ringbuf);
+		ringbuf->space = intel_ring_space(ringbuf);
 		if (ringbuf->space >= n) {
 			ret = 0;
 			break;
@@ -1787,7 +1958,7 @@ static int intel_wrap_ring_buffer(struct intel_engine_cs *ring)
 		iowrite32(MI_NOOP, virt++);
 
 	ringbuf->tail = 0;
-	ringbuf->space = ring_space(ringbuf);
+	ringbuf->space = intel_ring_space(ringbuf);
 
 	return 0;
 }
@@ -1992,9 +2163,7 @@ gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
 			      u64 offset, u32 len,
 			      unsigned flags)
 {
-	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-	bool ppgtt = dev_priv->mm.aliasing_ppgtt != NULL &&
-		!(flags & I915_DISPATCH_SECURE);
+	bool ppgtt = USES_PPGTT(ring->dev) && !(flags & I915_DISPATCH_SECURE);
 	int ret;
 
 	ret = intel_ring_begin(ring, 4);
@@ -2023,8 +2192,9 @@ hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
 		return ret;
 
 	intel_ring_emit(ring,
-			MI_BATCH_BUFFER_START | MI_BATCH_PPGTT_HSW |
-			(flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE_HSW));
+			MI_BATCH_BUFFER_START |
+			(flags & I915_DISPATCH_SECURE ?
+			 0 : MI_BATCH_PPGTT_HSW | MI_BATCH_NON_SECURE_HSW));
 	/* bit0-7 is the length on GEN6+ */
 	intel_ring_emit(ring, offset);
 	intel_ring_advance(ring);
@@ -2123,6 +2293,10 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 					dev_priv->semaphore_obj = obj;
 			}
 		}
+		if (IS_CHERRYVIEW(dev))
+			ring->init_context = chv_init_workarounds;
+		else
+			ring->init_context = bdw_init_workarounds;
 		ring->add_request = gen6_add_request;
 		ring->flush = gen8_render_ring_flush;
 		ring->irq_get = gen8_ring_get_irq;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 70525d0c2c74..96479c89f4bd 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -5,6 +5,13 @@
 
 #define I915_CMD_HASH_ORDER 9
 
+/* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
+ * but keeps the logic simple. Indeed, the whole purpose of this macro is just
+ * to give some inclination as to some of the magic values used in the various
+ * workarounds!
+ */
+#define CACHELINE_BYTES 64
+
 /*
  * Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use"
  * Gen3 BSpec "vol1c Memory Interface Functions" / 2.3.4.5 "Ring Buffer Use"
@@ -90,6 +97,15 @@ struct intel_ringbuffer {
 	struct drm_i915_gem_object *obj;
 	void __iomem *virtual_start;
 
+	struct intel_engine_cs *ring;
+
+	/*
+	 * FIXME: This backpointer is an artifact of the history of how the
+	 * execlist patches came into being. It will get removed once the basic
+	 * code has landed.
+	 */
+	struct intel_context *FIXME_lrc_ctx;
+
 	u32 head;
 	u32 tail;
 	int space;
@@ -132,6 +148,8 @@ struct  intel_engine_cs {
 
 	int		(*init)(struct intel_engine_cs *ring);
 
+	int		(*init_context)(struct intel_engine_cs *ring);
+
 	void		(*write_tail)(struct intel_engine_cs *ring,
 				      u32 value);
 	int __must_check (*flush)(struct intel_engine_cs *ring,
@@ -214,6 +232,18 @@ struct  intel_engine_cs {
 				  unsigned int num_dwords);
 	} semaphore;
 
+	/* Execlists */
+	spinlock_t execlist_lock;
+	struct list_head execlist_queue;
+	u8 next_context_status_buffer;
+	u32             irq_keep_mask; /* bitmask for interrupts that should not be masked */
+	int		(*emit_request)(struct intel_ringbuffer *ringbuf);
+	int		(*emit_flush)(struct intel_ringbuffer *ringbuf,
+				      u32 invalidate_domains,
+				      u32 flush_domains);
+	int		(*emit_bb_start)(struct intel_ringbuffer *ringbuf,
+					 u64 offset, unsigned flags);
+
 	/**
 	 * List of objects currently involved in rendering from the
 	 * ringbuffer.
@@ -287,11 +317,7 @@ struct  intel_engine_cs {
 	u32 (*get_cmd_length_mask)(u32 cmd_header);
 };
 
-static inline bool
-intel_ring_initialized(struct intel_engine_cs *ring)
-{
-	return ring->buffer && ring->buffer->obj;
-}
+bool intel_ring_initialized(struct intel_engine_cs *ring);
 
 static inline unsigned
 intel_ring_flag(struct intel_engine_cs *ring)
@@ -355,6 +381,10 @@ intel_write_status_page(struct intel_engine_cs *ring,
 #define I915_GEM_HWS_SCRATCH_INDEX	0x30
 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
 
+void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf);
+int intel_alloc_ringbuffer_obj(struct drm_device *dev,
+			       struct intel_ringbuffer *ringbuf);
+
 void intel_stop_ring_buffer(struct intel_engine_cs *ring);
 void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
 
@@ -372,6 +402,9 @@ static inline void intel_ring_advance(struct intel_engine_cs *ring)
 	struct intel_ringbuffer *ringbuf = ring->buffer;
 	ringbuf->tail &= ringbuf->size - 1;
 }
+int __intel_ring_space(int head, int tail, int size);
+int intel_ring_space(struct intel_ringbuffer *ringbuf);
+bool intel_ring_stopped(struct intel_engine_cs *ring);
 void __intel_ring_advance(struct intel_engine_cs *ring);
 
 int __must_check intel_ring_idle(struct intel_engine_cs *ring);
@@ -379,6 +412,9 @@ void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
 int intel_ring_flush_all_caches(struct intel_engine_cs *ring);
 int intel_ring_invalidate_all_caches(struct intel_engine_cs *ring);
 
+void intel_fini_pipe_control(struct intel_engine_cs *ring);
+int intel_init_pipe_control(struct intel_engine_cs *ring);
+
 int intel_init_render_ring_buffer(struct drm_device *dev);
 int intel_init_bsd_ring_buffer(struct drm_device *dev);
 int intel_init_bsd2_ring_buffer(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 168c6652cda1..07a74ef589bd 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -53,6 +53,7 @@ static bool intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl
 	enum pipe pipe = crtc->pipe;
 	long timeout = msecs_to_jiffies_timeout(1);
 	int scanline, min, max, vblank_start;
+	wait_queue_head_t *wq = drm_crtc_vblank_waitqueue(&crtc->base);
 	DEFINE_WAIT(wait);
 
 	WARN_ON(!drm_modeset_is_locked(&crtc->base.mutex));
@@ -81,7 +82,7 @@ static bool intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl
 		 * other CPUs can see the task state update by the time we
 		 * read the scanline.
 		 */
-		prepare_to_wait(&crtc->vbl_wait, &wait, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
 
 		scanline = intel_get_crtc_scanline(crtc);
 		if (scanline < min || scanline > max)
@@ -100,7 +101,7 @@ static bool intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl
 		local_irq_disable();
 	}
 
-	finish_wait(&crtc->vbl_wait, &wait);
+	finish_wait(wq, &wait);
 
 	drm_vblank_put(dev, pipe);
 
@@ -163,6 +164,7 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 	sprctl &= ~SP_PIXFORMAT_MASK;
 	sprctl &= ~SP_YUV_BYTE_ORDER_MASK;
 	sprctl &= ~SP_TILED;
+	sprctl &= ~SP_ROTATE_180;
 
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_YUYV:
@@ -235,6 +237,14 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 							fb->pitches[0]);
 	linear_offset -= sprsurf_offset;
 
+	if (intel_plane->rotation == BIT(DRM_ROTATE_180)) {
+		sprctl |= SP_ROTATE_180;
+
+		x += src_w;
+		y += src_h;
+		linear_offset += src_h * fb->pitches[0] + src_w * pixel_size;
+	}
+
 	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
 
 	intel_update_primary_plane(intel_crtc);
@@ -364,6 +374,7 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	sprctl &= ~SPRITE_RGB_ORDER_RGBX;
 	sprctl &= ~SPRITE_YUV_BYTE_ORDER_MASK;
 	sprctl &= ~SPRITE_TILED;
+	sprctl &= ~SPRITE_ROTATE_180;
 
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_XBGR8888:
@@ -426,6 +437,18 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 					       pixel_size, fb->pitches[0]);
 	linear_offset -= sprsurf_offset;
 
+	if (intel_plane->rotation == BIT(DRM_ROTATE_180)) {
+		sprctl |= SPRITE_ROTATE_180;
+
+		/* HSW and BDW does this automagically in hardware */
+		if (!IS_HASWELL(dev) && !IS_BROADWELL(dev)) {
+			x += src_w;
+			y += src_h;
+			linear_offset += src_h * fb->pitches[0] +
+				src_w * pixel_size;
+		}
+	}
+
 	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
 
 	intel_update_primary_plane(intel_crtc);
@@ -571,6 +594,7 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	dvscntr &= ~DVS_RGB_ORDER_XBGR;
 	dvscntr &= ~DVS_YUV_BYTE_ORDER_MASK;
 	dvscntr &= ~DVS_TILED;
+	dvscntr &= ~DVS_ROTATE_180;
 
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_XBGR8888:
@@ -628,6 +652,14 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 					       pixel_size, fb->pitches[0]);
 	linear_offset -= dvssurf_offset;
 
+	if (intel_plane->rotation == BIT(DRM_ROTATE_180)) {
+		dvscntr |= DVS_ROTATE_180;
+
+		x += src_w;
+		y += src_h;
+		linear_offset += src_h * fb->pitches[0] + src_w * pixel_size;
+	}
+
 	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
 
 	intel_update_primary_plane(intel_crtc);
@@ -895,6 +927,9 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	max_scale = intel_plane->max_downscale << 16;
 	min_scale = intel_plane->can_scale ? 1 : (1 << 16);
 
+	drm_rect_rotate(&src, fb->width << 16, fb->height << 16,
+			intel_plane->rotation);
+
 	hscale = drm_rect_calc_hscale_relaxed(&src, &dst, min_scale, max_scale);
 	BUG_ON(hscale < 0);
 
@@ -933,6 +968,9 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 				     drm_rect_width(&dst) * hscale - drm_rect_width(&src),
 				     drm_rect_height(&dst) * vscale - drm_rect_height(&src));
 
+		drm_rect_rotate_inv(&src, fb->width << 16, fb->height << 16,
+				    intel_plane->rotation);
+
 		/* sanity check to make sure the src viewport wasn't enlarged */
 		WARN_ON(src.x1 < (int) src_x ||
 			src.y1 < (int) src_y ||
@@ -1180,18 +1218,45 @@ out_unlock:
 	return ret;
 }
 
-void intel_plane_restore(struct drm_plane *plane)
+int intel_plane_set_property(struct drm_plane *plane,
+			     struct drm_property *prop,
+			     uint64_t val)
+{
+	struct drm_device *dev = plane->dev;
+	struct intel_plane *intel_plane = to_intel_plane(plane);
+	uint64_t old_val;
+	int ret = -ENOENT;
+
+	if (prop == dev->mode_config.rotation_property) {
+		/* exactly one rotation angle please */
+		if (hweight32(val & 0xf) != 1)
+			return -EINVAL;
+
+		if (intel_plane->rotation == val)
+			return 0;
+
+		old_val = intel_plane->rotation;
+		intel_plane->rotation = val;
+		ret = intel_plane_restore(plane);
+		if (ret)
+			intel_plane->rotation = old_val;
+	}
+
+	return ret;
+}
+
+int intel_plane_restore(struct drm_plane *plane)
 {
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 
 	if (!plane->crtc || !plane->fb)
-		return;
+		return 0;
 
-	intel_update_plane(plane, plane->crtc, plane->fb,
-			   intel_plane->crtc_x, intel_plane->crtc_y,
-			   intel_plane->crtc_w, intel_plane->crtc_h,
-			   intel_plane->src_x, intel_plane->src_y,
-			   intel_plane->src_w, intel_plane->src_h);
+	return plane->funcs->update_plane(plane, plane->crtc, plane->fb,
+				  intel_plane->crtc_x, intel_plane->crtc_y,
+				  intel_plane->crtc_w, intel_plane->crtc_h,
+				  intel_plane->src_x, intel_plane->src_y,
+				  intel_plane->src_w, intel_plane->src_h);
 }
 
 void intel_plane_disable(struct drm_plane *plane)
@@ -1206,6 +1271,7 @@ static const struct drm_plane_funcs intel_plane_funcs = {
 	.update_plane = intel_update_plane,
 	.disable_plane = intel_disable_plane,
 	.destroy = intel_destroy_plane,
+	.set_property = intel_plane_set_property,
 };
 
 static uint32_t ilk_plane_formats[] = {
@@ -1310,13 +1376,28 @@ intel_plane_init(struct drm_device *dev, enum pipe pipe, int plane)
 
 	intel_plane->pipe = pipe;
 	intel_plane->plane = plane;
+	intel_plane->rotation = BIT(DRM_ROTATE_0);
 	possible_crtcs = (1 << pipe);
-	ret = drm_plane_init(dev, &intel_plane->base, possible_crtcs,
-			     &intel_plane_funcs,
-			     plane_formats, num_plane_formats,
-			     false);
-	if (ret)
+	ret = drm_universal_plane_init(dev, &intel_plane->base, possible_crtcs,
+				       &intel_plane_funcs,
+				       plane_formats, num_plane_formats,
+				       DRM_PLANE_TYPE_OVERLAY);
+	if (ret) {
 		kfree(intel_plane);
+		goto out;
+	}
+
+	if (!dev->mode_config.rotation_property)
+		dev->mode_config.rotation_property =
+			drm_mode_create_rotation_property(dev,
+							  BIT(DRM_ROTATE_0) |
+							  BIT(DRM_ROTATE_180));
+
+	if (dev->mode_config.rotation_property)
+		drm_object_attach_property(&intel_plane->base.base,
+					   dev->mode_config.rotation_property,
+					   intel_plane->rotation);
 
+ out:
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index e81bc3bdc533..918b76163965 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -101,7 +101,7 @@ static void __gen7_gt_force_wake_mt_get(struct drm_i915_private *dev_priv,
 {
 	u32 forcewake_ack;
 
-	if (IS_HASWELL(dev_priv->dev) || IS_GEN8(dev_priv->dev))
+	if (IS_HASWELL(dev_priv->dev) || IS_BROADWELL(dev_priv->dev))
 		forcewake_ack = FORCEWAKE_ACK_HSW;
 	else
 		forcewake_ack = FORCEWAKE_MT_ACK;
@@ -334,7 +334,7 @@ void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore)
 	else if (IS_GEN6(dev) || IS_GEN7(dev))
 		__gen6_gt_force_wake_reset(dev_priv);
 
-	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_GEN8(dev))
+	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev))
 		__gen7_gt_force_wake_mt_reset(dev_priv);
 
 	if (restore) { /* If reset with a user forcewake, try to restore */
@@ -838,7 +838,7 @@ void intel_uncore_init(struct drm_device *dev)
 	if (IS_VALLEYVIEW(dev)) {
 		dev_priv->uncore.funcs.force_wake_get = __vlv_force_wake_get;
 		dev_priv->uncore.funcs.force_wake_put = __vlv_force_wake_put;
-	} else if (IS_HASWELL(dev) || IS_GEN8(dev)) {
+	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		dev_priv->uncore.funcs.force_wake_get = __gen7_gt_force_wake_mt_get;
 		dev_priv->uncore.funcs.force_wake_put = __gen7_gt_force_wake_mt_put;
 	} else if (IS_IVYBRIDGE(dev)) {
diff --git a/drivers/gpu/drm/mga/mga_dma.c b/drivers/gpu/drm/mga/mga_dma.c
index c3bf059ba720..8cfa9cb74c86 100644
--- a/drivers/gpu/drm/mga/mga_dma.c
+++ b/drivers/gpu/drm/mga/mga_dma.c
@@ -502,31 +502,31 @@ static int mga_do_agp_dma_bootstrap(struct drm_device *dev,
 		return err;
 	}
 
-	/* Make drm_addbufs happy by not trying to create a mapping for less
-	 * than a page.
+	/* Make drm_legacy_addbufs happy by not trying to create a mapping for
+	 * less than a page.
 	 */
 	if (warp_size < PAGE_SIZE)
 		warp_size = PAGE_SIZE;
 
 	offset = 0;
-	err = drm_addmap(dev, offset, warp_size,
-			 _DRM_AGP, _DRM_READ_ONLY, &dev_priv->warp);
+	err = drm_legacy_addmap(dev, offset, warp_size,
+				_DRM_AGP, _DRM_READ_ONLY, &dev_priv->warp);
 	if (err) {
 		DRM_ERROR("Unable to map WARP microcode: %d\n", err);
 		return err;
 	}
 
 	offset += warp_size;
-	err = drm_addmap(dev, offset, dma_bs->primary_size,
-			 _DRM_AGP, _DRM_READ_ONLY, &dev_priv->primary);
+	err = drm_legacy_addmap(dev, offset, dma_bs->primary_size,
+				_DRM_AGP, _DRM_READ_ONLY, &dev_priv->primary);
 	if (err) {
 		DRM_ERROR("Unable to map primary DMA region: %d\n", err);
 		return err;
 	}
 
 	offset += dma_bs->primary_size;
-	err = drm_addmap(dev, offset, secondary_size,
-			 _DRM_AGP, 0, &dev->agp_buffer_map);
+	err = drm_legacy_addmap(dev, offset, secondary_size,
+				_DRM_AGP, 0, &dev->agp_buffer_map);
 	if (err) {
 		DRM_ERROR("Unable to map secondary DMA region: %d\n", err);
 		return err;
@@ -538,7 +538,7 @@ static int mga_do_agp_dma_bootstrap(struct drm_device *dev,
 	req.flags = _DRM_AGP_BUFFER;
 	req.agp_start = offset;
 
-	err = drm_addbufs_agp(dev, &req);
+	err = drm_legacy_addbufs_agp(dev, &req);
 	if (err) {
 		DRM_ERROR("Unable to add secondary DMA buffers: %d\n", err);
 		return err;
@@ -559,16 +559,16 @@ static int mga_do_agp_dma_bootstrap(struct drm_device *dev,
 	}
 
 	offset += secondary_size;
-	err = drm_addmap(dev, offset, agp_size - offset,
-			 _DRM_AGP, 0, &dev_priv->agp_textures);
+	err = drm_legacy_addmap(dev, offset, agp_size - offset,
+				_DRM_AGP, 0, &dev_priv->agp_textures);
 	if (err) {
 		DRM_ERROR("Unable to map AGP texture region %d\n", err);
 		return err;
 	}
 
-	drm_core_ioremap(dev_priv->warp, dev);
-	drm_core_ioremap(dev_priv->primary, dev);
-	drm_core_ioremap(dev->agp_buffer_map, dev);
+	drm_legacy_ioremap(dev_priv->warp, dev);
+	drm_legacy_ioremap(dev_priv->primary, dev);
+	drm_legacy_ioremap(dev->agp_buffer_map, dev);
 
 	if (!dev_priv->warp->handle ||
 	    !dev_priv->primary->handle || !dev->agp_buffer_map->handle) {
@@ -602,7 +602,7 @@ static int mga_do_agp_dma_bootstrap(struct drm_device *dev,
  *
  * \todo
  * Determine whether the maximum address passed to drm_pci_alloc is correct.
- * The same goes for drm_addbufs_pci.
+ * The same goes for drm_legacy_addbufs_pci.
  *
  * \sa mga_do_dma_bootstrap, mga_do_agp_dma_bootstrap
  */
@@ -622,15 +622,15 @@ static int mga_do_pci_dma_bootstrap(struct drm_device *dev,
 		return -EFAULT;
 	}
 
-	/* Make drm_addbufs happy by not trying to create a mapping for less
-	 * than a page.
+	/* Make drm_legacy_addbufs happy by not trying to create a mapping for
+	 * less than a page.
 	 */
 	if (warp_size < PAGE_SIZE)
 		warp_size = PAGE_SIZE;
 
 	/* The proper alignment is 0x100 for this mapping */
-	err = drm_addmap(dev, 0, warp_size, _DRM_CONSISTENT,
-			 _DRM_READ_ONLY, &dev_priv->warp);
+	err = drm_legacy_addmap(dev, 0, warp_size, _DRM_CONSISTENT,
+				_DRM_READ_ONLY, &dev_priv->warp);
 	if (err != 0) {
 		DRM_ERROR("Unable to create mapping for WARP microcode: %d\n",
 			  err);
@@ -645,8 +645,8 @@ static int mga_do_pci_dma_bootstrap(struct drm_device *dev,
 	for (primary_size = dma_bs->primary_size; primary_size != 0;
 	     primary_size >>= 1) {
 		/* The proper alignment for this mapping is 0x04 */
-		err = drm_addmap(dev, 0, primary_size, _DRM_CONSISTENT,
-				 _DRM_READ_ONLY, &dev_priv->primary);
+		err = drm_legacy_addmap(dev, 0, primary_size, _DRM_CONSISTENT,
+					_DRM_READ_ONLY, &dev_priv->primary);
 		if (!err)
 			break;
 	}
@@ -669,7 +669,7 @@ static int mga_do_pci_dma_bootstrap(struct drm_device *dev,
 		req.count = bin_count;
 		req.size = dma_bs->secondary_bin_size;
 
-		err = drm_addbufs_pci(dev, &req);
+		err = drm_legacy_addbufs_pci(dev, &req);
 		if (!err)
 			break;
 	}
@@ -708,15 +708,16 @@ static int mga_do_dma_bootstrap(struct drm_device *dev,
 	/* The first steps are the same for both PCI and AGP based DMA.  Map
 	 * the cards MMIO registers and map a status page.
 	 */
-	err = drm_addmap(dev, dev_priv->mmio_base, dev_priv->mmio_size,
-			 _DRM_REGISTERS, _DRM_READ_ONLY, &dev_priv->mmio);
+	err = drm_legacy_addmap(dev, dev_priv->mmio_base, dev_priv->mmio_size,
+				_DRM_REGISTERS, _DRM_READ_ONLY,
+				&dev_priv->mmio);
 	if (err) {
 		DRM_ERROR("Unable to map MMIO region: %d\n", err);
 		return err;
 	}
 
-	err = drm_addmap(dev, 0, SAREA_MAX, _DRM_SHM,
-			 _DRM_READ_ONLY | _DRM_LOCKED | _DRM_KERNEL,
+	err = drm_legacy_addmap(dev, 0, SAREA_MAX, _DRM_SHM,
+				_DRM_READ_ONLY | _DRM_LOCKED | _DRM_KERNEL,
 			 &dev_priv->status);
 	if (err) {
 		DRM_ERROR("Unable to map status region: %d\n", err);
@@ -809,7 +810,7 @@ static int mga_do_init_dma(struct drm_device *dev, drm_mga_init_t *init)
 	dev_priv->texture_offset = init->texture_offset[0];
 	dev_priv->texture_size = init->texture_size[0];
 
-	dev_priv->sarea = drm_getsarea(dev);
+	dev_priv->sarea = drm_legacy_getsarea(dev);
 	if (!dev_priv->sarea) {
 		DRM_ERROR("failed to find sarea!\n");
 		return -EINVAL;
@@ -820,37 +821,37 @@ static int mga_do_init_dma(struct drm_device *dev, drm_mga_init_t *init)
 		dev_priv->dma_access = MGA_PAGPXFER;
 		dev_priv->wagp_enable = MGA_WAGP_ENABLE;
 
-		dev_priv->status = drm_core_findmap(dev, init->status_offset);
+		dev_priv->status = drm_legacy_findmap(dev, init->status_offset);
 		if (!dev_priv->status) {
 			DRM_ERROR("failed to find status page!\n");
 			return -EINVAL;
 		}
-		dev_priv->mmio = drm_core_findmap(dev, init->mmio_offset);
+		dev_priv->mmio = drm_legacy_findmap(dev, init->mmio_offset);
 		if (!dev_priv->mmio) {
 			DRM_ERROR("failed to find mmio region!\n");
 			return -EINVAL;
 		}
-		dev_priv->warp = drm_core_findmap(dev, init->warp_offset);
+		dev_priv->warp = drm_legacy_findmap(dev, init->warp_offset);
 		if (!dev_priv->warp) {
 			DRM_ERROR("failed to find warp microcode region!\n");
 			return -EINVAL;
 		}
-		dev_priv->primary = drm_core_findmap(dev, init->primary_offset);
+		dev_priv->primary = drm_legacy_findmap(dev, init->primary_offset);
 		if (!dev_priv->primary) {
 			DRM_ERROR("failed to find primary dma region!\n");
 			return -EINVAL;
 		}
 		dev->agp_buffer_token = init->buffers_offset;
 		dev->agp_buffer_map =
-		    drm_core_findmap(dev, init->buffers_offset);
+		    drm_legacy_findmap(dev, init->buffers_offset);
 		if (!dev->agp_buffer_map) {
 			DRM_ERROR("failed to find dma buffer region!\n");
 			return -EINVAL;
 		}
 
-		drm_core_ioremap(dev_priv->warp, dev);
-		drm_core_ioremap(dev_priv->primary, dev);
-		drm_core_ioremap(dev->agp_buffer_map, dev);
+		drm_legacy_ioremap(dev_priv->warp, dev);
+		drm_legacy_ioremap(dev_priv->primary, dev);
+		drm_legacy_ioremap(dev->agp_buffer_map, dev);
 	}
 
 	dev_priv->sarea_priv =
@@ -936,14 +937,14 @@ static int mga_do_cleanup_dma(struct drm_device *dev, int full_cleanup)
 
 		if ((dev_priv->warp != NULL)
 		    && (dev_priv->warp->type != _DRM_CONSISTENT))
-			drm_core_ioremapfree(dev_priv->warp, dev);
+			drm_legacy_ioremapfree(dev_priv->warp, dev);
 
 		if ((dev_priv->primary != NULL)
 		    && (dev_priv->primary->type != _DRM_CONSISTENT))
-			drm_core_ioremapfree(dev_priv->primary, dev);
+			drm_legacy_ioremapfree(dev_priv->primary, dev);
 
 		if (dev->agp_buffer_map != NULL)
-			drm_core_ioremapfree(dev->agp_buffer_map, dev);
+			drm_legacy_ioremapfree(dev->agp_buffer_map, dev);
 
 		if (dev_priv->used_new_dma_init) {
 #if __OS_HAS_AGP
diff --git a/drivers/gpu/drm/mga/mga_drv.c b/drivers/gpu/drm/mga/mga_drv.c
index 6b1a87c8aac5..5e2f131a6a72 100644
--- a/drivers/gpu/drm/mga/mga_drv.c
+++ b/drivers/gpu/drm/mga/mga_drv.c
@@ -48,7 +48,7 @@ static const struct file_operations mga_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = mga_compat_ioctl,
@@ -64,6 +64,7 @@ static struct drm_driver driver = {
 	.load = mga_driver_load,
 	.unload = mga_driver_unload,
 	.lastclose = mga_driver_lastclose,
+	.set_busid = drm_pci_set_busid,
 	.dma_quiescent = mga_driver_dma_quiescent,
 	.device_is_agp = mga_driver_device_is_agp,
 	.get_vblank_counter = mga_get_vblank_counter,
diff --git a/drivers/gpu/drm/mga/mga_drv.h b/drivers/gpu/drm/mga/mga_drv.h
index fe453213600a..b4a2014917e5 100644
--- a/drivers/gpu/drm/mga/mga_drv.h
+++ b/drivers/gpu/drm/mga/mga_drv.h
@@ -31,6 +31,8 @@
 #ifndef __MGA_DRV_H__
 #define __MGA_DRV_H__
 
+#include <drm/drm_legacy.h>
+
 /* General customization:
  */
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index 2d75d6df0789..97745991544d 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -91,6 +91,7 @@ static struct drm_driver driver = {
 	.driver_features = DRIVER_GEM | DRIVER_MODESET,
 	.load = mgag200_driver_load,
 	.unload = mgag200_driver_unload,
+	.set_busid = drm_pci_set_busid,
 	.fops = &mgag200_driver_fops,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index 80de23d9b9c9..e9eea1d4e7c3 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -22,6 +22,8 @@
 #include <drm/ttm/ttm_memory.h>
 #include <drm/ttm/ttm_module.h>
 
+#include <drm/drm_gem.h>
+
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 
@@ -190,8 +192,6 @@ struct mga_device {
 	resource_size_t			rmmio_size;
 	void __iomem			*rmmio;
 
-	drm_local_map_t			*framebuffer;
-
 	struct mga_mc			mc;
 	struct mga_mode_info		mode_info;
 
@@ -224,7 +224,7 @@ struct mgag200_bo {
 	struct ttm_placement placement;
 	struct ttm_bo_kmap_obj kmap;
 	struct drm_gem_object gem;
-	u32 placements[3];
+	struct ttm_place placements[3];
 	int pin_count;
 };
 #define gem_to_mga_bo(gobj) container_of((gobj), struct mgag200_bo, gem)
diff --git a/drivers/gpu/drm/mgag200/mgag200_fb.c b/drivers/gpu/drm/mgag200/mgag200_fb.c
index 5451dc58eff1..4415af3666ab 100644
--- a/drivers/gpu/drm/mgag200/mgag200_fb.c
+++ b/drivers/gpu/drm/mgag200/mgag200_fb.c
@@ -158,7 +158,8 @@ static int mgag200fb_create_object(struct mga_fbdev *afbdev,
 static int mgag200fb_create(struct drm_fb_helper *helper,
 			   struct drm_fb_helper_surface_size *sizes)
 {
-	struct mga_fbdev *mfbdev = (struct mga_fbdev *)helper;
+	struct mga_fbdev *mfbdev =
+		container_of(helper, struct mga_fbdev, helper);
 	struct drm_device *dev = mfbdev->helper.dev;
 	struct drm_mode_fb_cmd2 mode_cmd;
 	struct mga_device *mdev = dev->dev_private;
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 45f04dea0ac2..83485ab81ce8 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1483,11 +1483,7 @@ static int mga_vga_mode_valid(struct drm_connector *connector,
 {
 	struct drm_device *dev = connector->dev;
 	struct mga_device *mdev = (struct mga_device*)dev->dev_private;
-	struct mga_fbdev *mfbdev = mdev->mfbdev;
-	struct drm_fb_helper *fb_helper = &mfbdev->helper;
-	struct drm_fb_helper_connector *fb_helper_conn = NULL;
 	int bpp = 32;
-	int i = 0;
 
 	if (IS_G200_SE(mdev)) {
 		if (mdev->unique_rev_id == 0x01) {
@@ -1537,21 +1533,14 @@ static int mga_vga_mode_valid(struct drm_connector *connector,
 	}
 
 	/* Validate the mode input by the user */
-	for (i = 0; i < fb_helper->connector_count; i++) {
-		if (fb_helper->connector_info[i]->connector == connector) {
-			/* Found the helper for this connector */
-			fb_helper_conn = fb_helper->connector_info[i];
-			if (fb_helper_conn->cmdline_mode.specified) {
-				if (fb_helper_conn->cmdline_mode.bpp_specified) {
-					bpp = fb_helper_conn->cmdline_mode.bpp;
-				}
-			}
-		}
+	if (connector->cmdline_mode.specified) {
+		if (connector->cmdline_mode.bpp_specified)
+			bpp = connector->cmdline_mode.bpp;
 	}
 
 	if ((mode->hdisplay * mode->vdisplay * (bpp/8)) > mdev->mc.vram_size) {
-		if (fb_helper_conn)
-			fb_helper_conn->cmdline_mode.specified = false;
+		if (connector->cmdline_mode.specified)
+			connector->cmdline_mode.specified = false;
 		return MODE_BAD;
 	}
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 5a00e90696de..d16964ea0ed4 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -293,18 +293,22 @@ void mgag200_mm_fini(struct mga_device *mdev)
 void mgag200_ttm_placement(struct mgag200_bo *bo, int domain)
 {
 	u32 c = 0;
-	bo->placement.fpfn = 0;
-	bo->placement.lpfn = 0;
+	unsigned i;
+
 	bo->placement.placement = bo->placements;
 	bo->placement.busy_placement = bo->placements;
 	if (domain & TTM_PL_FLAG_VRAM)
-		bo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
+		bo->placements[c++].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_VRAM;
 	if (domain & TTM_PL_FLAG_SYSTEM)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	if (!c)
-		bo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		bo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	bo->placement.num_placement = c;
 	bo->placement.num_busy_placement = c;
+	for (i = 0; i < c; ++i) {
+		bo->placements[i].fpfn = 0;
+		bo->placements[i].lpfn = 0;
+	}
 }
 
 int mgag200_bo_create(struct drm_device *dev, int size, int align,
@@ -335,7 +339,7 @@ int mgag200_bo_create(struct drm_device *dev, int size, int align,
 	ret = ttm_bo_init(&mdev->ttm.bdev, &mgabo->bo, size,
 			  ttm_bo_type_device, &mgabo->placement,
 			  align >> PAGE_SHIFT, false, NULL, acc_size,
-			  NULL, mgag200_bo_ttm_destroy);
+			  NULL, NULL, mgag200_bo_ttm_destroy);
 	if (ret)
 		return ret;
 
@@ -361,7 +365,7 @@ int mgag200_bo_pin(struct mgag200_bo *bo, u32 pl_flag, u64 *gpu_addr)
 
 	mgag200_ttm_placement(bo, pl_flag);
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -384,7 +388,7 @@ int mgag200_bo_unpin(struct mgag200_bo *bo)
 		return 0;
 
 	for (i = 0; i < bo->placement.num_placement ; i++)
-		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret)
 		return ret;
@@ -408,7 +412,7 @@ int mgag200_bo_push_sysram(struct mgag200_bo *bo)
 
 	mgag200_ttm_placement(bo, TTM_PL_FLAG_SYSTEM);
 	for (i = 0; i < bo->placement.num_placement ; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 
 	ret = ttm_bo_validate(&bo->bo, &bo->placement, false, false);
 	if (ret) {
@@ -424,7 +428,7 @@ int mgag200_mmap(struct file *filp, struct vm_area_struct *vma)
 	struct mga_device *mdev;
 
 	if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET))
-		return drm_mmap(filp, vma);
+		return -EINVAL;
 
 	file_priv = filp->private_data;
 	mdev = file_priv->minor->dev->dev_private;
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index c99c50de3226..9d907c526c94 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -4,6 +4,7 @@ config DRM_MSM
 	depends on DRM
 	depends on ARCH_QCOM || (ARM && COMPILE_TEST)
 	select DRM_KMS_HELPER
+	select DRM_PANEL
 	select SHMEM
 	select TMPFS
 	default y
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 93ca49c8df44..6283dcb96af5 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -4,6 +4,7 @@ ifeq (, $(findstring -W,$(EXTRA_CFLAGS)))
 endif
 
 msm-y := \
+	adreno/adreno_device.o \
 	adreno/adreno_gpu.o \
 	adreno/a3xx_gpu.o \
 	hdmi/hdmi.o \
@@ -18,6 +19,8 @@ msm-y := \
 	mdp/mdp_kms.o \
 	mdp/mdp4/mdp4_crtc.o \
 	mdp/mdp4/mdp4_dtv_encoder.o \
+	mdp/mdp4/mdp4_lcdc_encoder.o \
+	mdp/mdp4/mdp4_lvds_connector.o \
 	mdp/mdp4/mdp4_irq.o \
 	mdp/mdp4/mdp4_kms.o \
 	mdp/mdp4/mdp4_plane.o \
@@ -39,5 +42,6 @@ msm-y := \
 	msm_ringbuffer.o
 
 msm-$(CONFIG_DRM_MSM_FBDEV) += msm_fbdev.o
+msm-$(CONFIG_COMMON_CLK) += mdp/mdp4/mdp4_lvds_pll.o
 
 obj-$(CONFIG_DRM_MSM)	+= msm.o
diff --git a/drivers/gpu/drm/msm/adreno/a2xx.xml.h b/drivers/gpu/drm/msm/adreno/a2xx.xml.h
index a8a144b38eaa..a3104598c27f 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a2xx.xml.h
@@ -12,9 +12,9 @@ The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1453 bytes, from 2013-03-31 16:51:27)
 - /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  32901 bytes, from 2014-06-02 15:21:30)
 - /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (   9859 bytes, from 2014-06-02 15:21:30)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  14477 bytes, from 2014-05-16 11:51:57)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  58020 bytes, from 2014-06-25 12:57:16)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          (  26602 bytes, from 2014-06-25 12:57:16)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  14960 bytes, from 2014-07-27 17:22:13)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  58020 bytes, from 2014-08-01 12:22:48)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          (  41068 bytes, from 2014-08-01 12:22:48)
 
 Copyright (C) 2013-2014 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
diff --git a/drivers/gpu/drm/msm/adreno/a3xx.xml.h b/drivers/gpu/drm/msm/adreno/a3xx.xml.h
index 303e8a9e91a5..82d015279b47 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a3xx.xml.h
@@ -12,9 +12,9 @@ The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1453 bytes, from 2013-03-31 16:51:27)
 - /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  32901 bytes, from 2014-06-02 15:21:30)
 - /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (   9859 bytes, from 2014-06-02 15:21:30)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  14477 bytes, from 2014-05-16 11:51:57)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  58020 bytes, from 2014-06-25 12:57:16)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          (  26602 bytes, from 2014-06-25 12:57:16)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  14960 bytes, from 2014-07-27 17:22:13)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  58020 bytes, from 2014-08-01 12:22:48)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          (  41068 bytes, from 2014-08-01 12:22:48)
 
 Copyright (C) 2013-2014 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
@@ -654,7 +654,7 @@ static inline uint32_t A3XX_GRAS_SU_POINT_SIZE(float val)
 #define A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL__SHIFT		0
 static inline uint32_t A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL(float val)
 {
-	return ((((uint32_t)(val * 40.0))) << A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL__SHIFT) & A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL__MASK;
+	return ((((uint32_t)(val * 28.0))) << A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL__SHIFT) & A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL__MASK;
 }
 
 #define REG_A3XX_GRAS_SU_POLY_OFFSET_OFFSET			0x0000206d
@@ -662,7 +662,7 @@ static inline uint32_t A3XX_GRAS_SU_POLY_OFFSET_SCALE_VAL(float val)
 #define A3XX_GRAS_SU_POLY_OFFSET_OFFSET__SHIFT			0
 static inline uint32_t A3XX_GRAS_SU_POLY_OFFSET_OFFSET(float val)
 {
-	return ((((uint32_t)(val * 44.0))) << A3XX_GRAS_SU_POLY_OFFSET_OFFSET__SHIFT) & A3XX_GRAS_SU_POLY_OFFSET_OFFSET__MASK;
+	return ((((uint32_t)(val * 28.0))) << A3XX_GRAS_SU_POLY_OFFSET_OFFSET__SHIFT) & A3XX_GRAS_SU_POLY_OFFSET_OFFSET__MASK;
 }
 
 #define REG_A3XX_GRAS_SU_MODE_CONTROL				0x00002070
@@ -1696,7 +1696,7 @@ static inline uint32_t A3XX_SP_VS_CTRL_REG1_CONSTFOOTPRINT(uint32_t val)
 {
 	return ((val) << A3XX_SP_VS_CTRL_REG1_CONSTFOOTPRINT__SHIFT) & A3XX_SP_VS_CTRL_REG1_CONSTFOOTPRINT__MASK;
 }
-#define A3XX_SP_VS_CTRL_REG1_INITIALOUTSTANDING__MASK		0x3f000000
+#define A3XX_SP_VS_CTRL_REG1_INITIALOUTSTANDING__MASK		0x7f000000
 #define A3XX_SP_VS_CTRL_REG1_INITIALOUTSTANDING__SHIFT		24
 static inline uint32_t A3XX_SP_VS_CTRL_REG1_INITIALOUTSTANDING(uint32_t val)
 {
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 2773600c9488..218c5b060398 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -35,10 +35,8 @@
 	 A3XX_INT0_CP_AHB_ERROR_HALT |     \
 	 A3XX_INT0_UCHE_OOB_ACCESS)
 
+extern bool hang_debug;
 
-static bool hang_debug = false;
-MODULE_PARM_DESC(hang_debug, "Dump registers when hang is detected (can be slow!)");
-module_param_named(hang_debug, hang_debug, bool, 0600);
 static void a3xx_dump(struct msm_gpu *gpu);
 
 static void a3xx_me_init(struct msm_gpu *gpu)
@@ -387,58 +385,26 @@ static const unsigned int a3xx_registers[] = {
 	0x2750, 0x2756, 0x2760, 0x2760, 0x300c, 0x300e, 0x301c, 0x301d,
 	0x302a, 0x302a, 0x302c, 0x302d, 0x3030, 0x3031, 0x3034, 0x3036,
 	0x303c, 0x303c, 0x305e, 0x305f,
+	~0   /* sentinel */
 };
 
 #ifdef CONFIG_DEBUG_FS
 static void a3xx_show(struct msm_gpu *gpu, struct seq_file *m)
 {
-	int i;
-
-	adreno_show(gpu, m);
-
 	gpu->funcs->pm_resume(gpu);
-
 	seq_printf(m, "status:   %08x\n",
 			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
-
-	/* dump these out in a form that can be parsed by demsm: */
-	seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
-	for (i = 0; i < ARRAY_SIZE(a3xx_registers); i += 2) {
-		uint32_t start = a3xx_registers[i];
-		uint32_t end   = a3xx_registers[i+1];
-		uint32_t addr;
-
-		for (addr = start; addr <= end; addr++) {
-			uint32_t val = gpu_read(gpu, addr);
-			seq_printf(m, "IO:R %08x %08x\n", addr<<2, val);
-		}
-	}
-
 	gpu->funcs->pm_suspend(gpu);
+	adreno_show(gpu, m);
 }
 #endif
 
 /* would be nice to not have to duplicate the _show() stuff with printk(): */
 static void a3xx_dump(struct msm_gpu *gpu)
 {
-	int i;
-
-	adreno_dump(gpu);
 	printk("status:   %08x\n",
 			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
-
-	/* dump these out in a form that can be parsed by demsm: */
-	printk("IO:region %s 00000000 00020000\n", gpu->name);
-	for (i = 0; i < ARRAY_SIZE(a3xx_registers); i += 2) {
-		uint32_t start = a3xx_registers[i];
-		uint32_t end   = a3xx_registers[i+1];
-		uint32_t addr;
-
-		for (addr = start; addr <= end; addr++) {
-			uint32_t val = gpu_read(gpu, addr);
-			printk("IO:R %08x %08x\n", addr<<2, val);
-		}
-	}
+	adreno_dump(gpu);
 }
 
 static const struct adreno_gpu_funcs funcs = {
@@ -474,7 +440,6 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 	struct msm_gpu *gpu;
 	struct msm_drm_private *priv = dev->dev_private;
 	struct platform_device *pdev = priv->gpu_pdev;
-	struct adreno_platform_config *config;
 	int ret;
 
 	if (!pdev) {
@@ -483,8 +448,6 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 		goto fail;
 	}
 
-	config = pdev->dev.platform_data;
-
 	a3xx_gpu = kzalloc(sizeof(*a3xx_gpu), GFP_KERNEL);
 	if (!a3xx_gpu) {
 		ret = -ENOMEM;
@@ -496,20 +459,12 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 
 	a3xx_gpu->pdev = pdev;
 
-	gpu->fast_rate = config->fast_rate;
-	gpu->slow_rate = config->slow_rate;
-	gpu->bus_freq  = config->bus_freq;
-#ifdef CONFIG_MSM_BUS_SCALING
-	gpu->bus_scale_table = config->bus_scale_table;
-#endif
-
-	DBG("fast_rate=%u, slow_rate=%u, bus_freq=%u",
-			gpu->fast_rate, gpu->slow_rate, gpu->bus_freq);
-
 	gpu->perfcntrs = perfcntrs;
 	gpu->num_perfcntrs = ARRAY_SIZE(perfcntrs);
 
-	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, config->rev);
+	adreno_gpu->registers = a3xx_registers;
+
+	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs);
 	if (ret)
 		goto fail;
 
@@ -549,158 +504,3 @@ fail:
 
 	return ERR_PTR(ret);
 }
-
-/*
- * The a3xx device:
- */
-
-#if defined(CONFIG_MSM_BUS_SCALING) && !defined(CONFIG_OF)
-#  include <mach/kgsl.h>
-#endif
-
-static void set_gpu_pdev(struct drm_device *dev,
-		struct platform_device *pdev)
-{
-	struct msm_drm_private *priv = dev->dev_private;
-	priv->gpu_pdev = pdev;
-}
-
-static int a3xx_bind(struct device *dev, struct device *master, void *data)
-{
-	static struct adreno_platform_config config = {};
-#ifdef CONFIG_OF
-	struct device_node *child, *node = dev->of_node;
-	u32 val;
-	int ret;
-
-	ret = of_property_read_u32(node, "qcom,chipid", &val);
-	if (ret) {
-		dev_err(dev, "could not find chipid: %d\n", ret);
-		return ret;
-	}
-
-	config.rev = ADRENO_REV((val >> 24) & 0xff,
-			(val >> 16) & 0xff, (val >> 8) & 0xff, val & 0xff);
-
-	/* find clock rates: */
-	config.fast_rate = 0;
-	config.slow_rate = ~0;
-	for_each_child_of_node(node, child) {
-		if (of_device_is_compatible(child, "qcom,gpu-pwrlevels")) {
-			struct device_node *pwrlvl;
-			for_each_child_of_node(child, pwrlvl) {
-				ret = of_property_read_u32(pwrlvl, "qcom,gpu-freq", &val);
-				if (ret) {
-					dev_err(dev, "could not find gpu-freq: %d\n", ret);
-					return ret;
-				}
-				config.fast_rate = max(config.fast_rate, val);
-				config.slow_rate = min(config.slow_rate, val);
-			}
-		}
-	}
-
-	if (!config.fast_rate) {
-		dev_err(dev, "could not find clk rates\n");
-		return -ENXIO;
-	}
-
-#else
-	struct kgsl_device_platform_data *pdata = dev->platform_data;
-	uint32_t version = socinfo_get_version();
-	if (cpu_is_apq8064ab()) {
-		config.fast_rate = 450000000;
-		config.slow_rate = 27000000;
-		config.bus_freq  = 4;
-		config.rev = ADRENO_REV(3, 2, 1, 0);
-	} else if (cpu_is_apq8064()) {
-		config.fast_rate = 400000000;
-		config.slow_rate = 27000000;
-		config.bus_freq  = 4;
-
-		if (SOCINFO_VERSION_MAJOR(version) == 2)
-			config.rev = ADRENO_REV(3, 2, 0, 2);
-		else if ((SOCINFO_VERSION_MAJOR(version) == 1) &&
-				(SOCINFO_VERSION_MINOR(version) == 1))
-			config.rev = ADRENO_REV(3, 2, 0, 1);
-		else
-			config.rev = ADRENO_REV(3, 2, 0, 0);
-
-	} else if (cpu_is_msm8960ab()) {
-		config.fast_rate = 400000000;
-		config.slow_rate = 320000000;
-		config.bus_freq  = 4;
-
-		if (SOCINFO_VERSION_MINOR(version) == 0)
-			config.rev = ADRENO_REV(3, 2, 1, 0);
-		else
-			config.rev = ADRENO_REV(3, 2, 1, 1);
-
-	} else if (cpu_is_msm8930()) {
-		config.fast_rate = 400000000;
-		config.slow_rate = 27000000;
-		config.bus_freq  = 3;
-
-		if ((SOCINFO_VERSION_MAJOR(version) == 1) &&
-			(SOCINFO_VERSION_MINOR(version) == 2))
-			config.rev = ADRENO_REV(3, 0, 5, 2);
-		else
-			config.rev = ADRENO_REV(3, 0, 5, 0);
-
-	}
-#  ifdef CONFIG_MSM_BUS_SCALING
-	config.bus_scale_table = pdata->bus_scale_table;
-#  endif
-#endif
-	dev->platform_data = &config;
-	set_gpu_pdev(dev_get_drvdata(master), to_platform_device(dev));
-	return 0;
-}
-
-static void a3xx_unbind(struct device *dev, struct device *master,
-		void *data)
-{
-	set_gpu_pdev(dev_get_drvdata(master), NULL);
-}
-
-static const struct component_ops a3xx_ops = {
-		.bind   = a3xx_bind,
-		.unbind = a3xx_unbind,
-};
-
-static int a3xx_probe(struct platform_device *pdev)
-{
-	return component_add(&pdev->dev, &a3xx_ops);
-}
-
-static int a3xx_remove(struct platform_device *pdev)
-{
-	component_del(&pdev->dev, &a3xx_ops);
-	return 0;
-}
-
-static const struct of_device_id dt_match[] = {
-	{ .compatible = "qcom,adreno-3xx" },
-	/* for backwards compat w/ downstream kgsl DT files: */
-	{ .compatible = "qcom,kgsl-3d0" },
-	{}
-};
-
-static struct platform_driver a3xx_driver = {
-	.probe = a3xx_probe,
-	.remove = a3xx_remove,
-	.driver = {
-		.name = "kgsl-3d0",
-		.of_match_table = dt_match,
-	},
-};
-
-void __init a3xx_register(void)
-{
-	platform_driver_register(&a3xx_driver);
-}
-
-void __exit a3xx_unregister(void)
-{
-	platform_driver_unregister(&a3xx_driver);
-}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_common.xml.h b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h
index 9de19ac2e86c..cc341bc62b51 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_common.xml.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_common.xml.h
@@ -12,9 +12,9 @@ The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1453 bytes, from 2013-03-31 16:51:27)
 - /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  32901 bytes, from 2014-06-02 15:21:30)
 - /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (   9859 bytes, from 2014-06-02 15:21:30)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  14477 bytes, from 2014-05-16 11:51:57)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  58020 bytes, from 2014-06-25 12:57:16)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          (  26602 bytes, from 2014-06-25 12:57:16)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  14960 bytes, from 2014-07-27 17:22:13)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  58020 bytes, from 2014-08-01 12:22:48)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          (  41068 bytes, from 2014-08-01 12:22:48)
 
 Copyright (C) 2013-2014 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
new file mode 100644
index 000000000000..7ab85af3a7db
--- /dev/null
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -0,0 +1,285 @@
+/*
+ * Copyright (C) 2013-2014 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "adreno_gpu.h"
+
+#if defined(CONFIG_MSM_BUS_SCALING) && !defined(CONFIG_OF)
+#  include <mach/kgsl.h>
+#endif
+
+#define ANY_ID 0xff
+
+bool hang_debug = false;
+MODULE_PARM_DESC(hang_debug, "Dump registers when hang is detected (can be slow!)");
+module_param_named(hang_debug, hang_debug, bool, 0600);
+
+struct msm_gpu *a3xx_gpu_init(struct drm_device *dev);
+
+static const struct adreno_info gpulist[] = {
+	{
+		.rev   = ADRENO_REV(3, 0, 5, ANY_ID),
+		.revn  = 305,
+		.name  = "A305",
+		.pm4fw = "a300_pm4.fw",
+		.pfpfw = "a300_pfp.fw",
+		.gmem  = SZ_256K,
+		.init  = a3xx_gpu_init,
+	}, {
+		.rev   = ADRENO_REV(3, 2, ANY_ID, ANY_ID),
+		.revn  = 320,
+		.name  = "A320",
+		.pm4fw = "a300_pm4.fw",
+		.pfpfw = "a300_pfp.fw",
+		.gmem  = SZ_512K,
+		.init  = a3xx_gpu_init,
+	}, {
+		.rev   = ADRENO_REV(3, 3, 0, ANY_ID),
+		.revn  = 330,
+		.name  = "A330",
+		.pm4fw = "a330_pm4.fw",
+		.pfpfw = "a330_pfp.fw",
+		.gmem  = SZ_1M,
+		.init  = a3xx_gpu_init,
+	},
+};
+
+MODULE_FIRMWARE("a300_pm4.fw");
+MODULE_FIRMWARE("a300_pfp.fw");
+MODULE_FIRMWARE("a330_pm4.fw");
+MODULE_FIRMWARE("a330_pfp.fw");
+
+static inline bool _rev_match(uint8_t entry, uint8_t id)
+{
+	return (entry == ANY_ID) || (entry == id);
+}
+
+const struct adreno_info *adreno_info(struct adreno_rev rev)
+{
+	int i;
+
+	/* identify gpu: */
+	for (i = 0; i < ARRAY_SIZE(gpulist); i++) {
+		const struct adreno_info *info = &gpulist[i];
+		if (_rev_match(info->rev.core, rev.core) &&
+				_rev_match(info->rev.major, rev.major) &&
+				_rev_match(info->rev.minor, rev.minor) &&
+				_rev_match(info->rev.patchid, rev.patchid))
+			return info;
+	}
+
+	return NULL;
+}
+
+struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct platform_device *pdev = priv->gpu_pdev;
+	struct adreno_platform_config *config;
+	struct adreno_rev rev;
+	const struct adreno_info *info;
+	struct msm_gpu *gpu = NULL;
+
+	if (!pdev) {
+		dev_err(dev->dev, "no adreno device\n");
+		return NULL;
+	}
+
+	config = pdev->dev.platform_data;
+	rev = config->rev;
+	info = adreno_info(config->rev);
+
+	if (!info) {
+		dev_warn(dev->dev, "Unknown GPU revision: %u.%u.%u.%u\n",
+				rev.core, rev.major, rev.minor, rev.patchid);
+		return NULL;
+	}
+
+	DBG("Found GPU: %u.%u.%u.%u",  rev.core, rev.major,
+			rev.minor, rev.patchid);
+
+	gpu = info->init(dev);
+	if (IS_ERR(gpu)) {
+		dev_warn(dev->dev, "failed to load adreno gpu\n");
+		gpu = NULL;
+		/* not fatal */
+	}
+
+	if (gpu) {
+		int ret;
+		mutex_lock(&dev->struct_mutex);
+		gpu->funcs->pm_resume(gpu);
+		mutex_unlock(&dev->struct_mutex);
+		ret = gpu->funcs->hw_init(gpu);
+		if (ret) {
+			dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
+			gpu->funcs->destroy(gpu);
+			gpu = NULL;
+		} else {
+			/* give inactive pm a chance to kick in: */
+			msm_gpu_retire(gpu);
+		}
+	}
+
+	return gpu;
+}
+
+static void set_gpu_pdev(struct drm_device *dev,
+		struct platform_device *pdev)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	priv->gpu_pdev = pdev;
+}
+
+static int adreno_bind(struct device *dev, struct device *master, void *data)
+{
+	static struct adreno_platform_config config = {};
+#ifdef CONFIG_OF
+	struct device_node *child, *node = dev->of_node;
+	u32 val;
+	int ret;
+
+	ret = of_property_read_u32(node, "qcom,chipid", &val);
+	if (ret) {
+		dev_err(dev, "could not find chipid: %d\n", ret);
+		return ret;
+	}
+
+	config.rev = ADRENO_REV((val >> 24) & 0xff,
+			(val >> 16) & 0xff, (val >> 8) & 0xff, val & 0xff);
+
+	/* find clock rates: */
+	config.fast_rate = 0;
+	config.slow_rate = ~0;
+	for_each_child_of_node(node, child) {
+		if (of_device_is_compatible(child, "qcom,gpu-pwrlevels")) {
+			struct device_node *pwrlvl;
+			for_each_child_of_node(child, pwrlvl) {
+				ret = of_property_read_u32(pwrlvl, "qcom,gpu-freq", &val);
+				if (ret) {
+					dev_err(dev, "could not find gpu-freq: %d\n", ret);
+					return ret;
+				}
+				config.fast_rate = max(config.fast_rate, val);
+				config.slow_rate = min(config.slow_rate, val);
+			}
+		}
+	}
+
+	if (!config.fast_rate) {
+		dev_err(dev, "could not find clk rates\n");
+		return -ENXIO;
+	}
+
+#else
+	struct kgsl_device_platform_data *pdata = dev->platform_data;
+	uint32_t version = socinfo_get_version();
+	if (cpu_is_apq8064ab()) {
+		config.fast_rate = 450000000;
+		config.slow_rate = 27000000;
+		config.bus_freq  = 4;
+		config.rev = ADRENO_REV(3, 2, 1, 0);
+	} else if (cpu_is_apq8064()) {
+		config.fast_rate = 400000000;
+		config.slow_rate = 27000000;
+		config.bus_freq  = 4;
+
+		if (SOCINFO_VERSION_MAJOR(version) == 2)
+			config.rev = ADRENO_REV(3, 2, 0, 2);
+		else if ((SOCINFO_VERSION_MAJOR(version) == 1) &&
+				(SOCINFO_VERSION_MINOR(version) == 1))
+			config.rev = ADRENO_REV(3, 2, 0, 1);
+		else
+			config.rev = ADRENO_REV(3, 2, 0, 0);
+
+	} else if (cpu_is_msm8960ab()) {
+		config.fast_rate = 400000000;
+		config.slow_rate = 320000000;
+		config.bus_freq  = 4;
+
+		if (SOCINFO_VERSION_MINOR(version) == 0)
+			config.rev = ADRENO_REV(3, 2, 1, 0);
+		else
+			config.rev = ADRENO_REV(3, 2, 1, 1);
+
+	} else if (cpu_is_msm8930()) {
+		config.fast_rate = 400000000;
+		config.slow_rate = 27000000;
+		config.bus_freq  = 3;
+
+		if ((SOCINFO_VERSION_MAJOR(version) == 1) &&
+			(SOCINFO_VERSION_MINOR(version) == 2))
+			config.rev = ADRENO_REV(3, 0, 5, 2);
+		else
+			config.rev = ADRENO_REV(3, 0, 5, 0);
+
+	}
+#  ifdef CONFIG_MSM_BUS_SCALING
+	config.bus_scale_table = pdata->bus_scale_table;
+#  endif
+#endif
+	dev->platform_data = &config;
+	set_gpu_pdev(dev_get_drvdata(master), to_platform_device(dev));
+	return 0;
+}
+
+static void adreno_unbind(struct device *dev, struct device *master,
+		void *data)
+{
+	set_gpu_pdev(dev_get_drvdata(master), NULL);
+}
+
+static const struct component_ops a3xx_ops = {
+		.bind   = adreno_bind,
+		.unbind = adreno_unbind,
+};
+
+static int adreno_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &a3xx_ops);
+}
+
+static int adreno_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &a3xx_ops);
+	return 0;
+}
+
+static const struct of_device_id dt_match[] = {
+	{ .compatible = "qcom,adreno-3xx" },
+	/* for backwards compat w/ downstream kgsl DT files: */
+	{ .compatible = "qcom,kgsl-3d0" },
+	{}
+};
+
+static struct platform_driver adreno_driver = {
+	.probe = adreno_probe,
+	.remove = adreno_remove,
+	.driver = {
+		.name = "adreno",
+		.of_match_table = dt_match,
+	},
+};
+
+void __init adreno_register(void)
+{
+	platform_driver_register(&adreno_driver);
+}
+
+void __exit adreno_unregister(void)
+{
+	platform_driver_unregister(&adreno_driver);
+}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 655ce5b14ad0..6afa29167fee 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -19,46 +19,6 @@
 #include "msm_gem.h"
 #include "msm_mmu.h"
 
-struct adreno_info {
-	struct adreno_rev rev;
-	uint32_t revn;
-	const char *name;
-	const char *pm4fw, *pfpfw;
-	uint32_t gmem;
-};
-
-#define ANY_ID 0xff
-
-static const struct adreno_info gpulist[] = {
-	{
-		.rev   = ADRENO_REV(3, 0, 5, ANY_ID),
-		.revn  = 305,
-		.name  = "A305",
-		.pm4fw = "a300_pm4.fw",
-		.pfpfw = "a300_pfp.fw",
-		.gmem  = SZ_256K,
-	}, {
-		.rev   = ADRENO_REV(3, 2, ANY_ID, ANY_ID),
-		.revn  = 320,
-		.name  = "A320",
-		.pm4fw = "a300_pm4.fw",
-		.pfpfw = "a300_pfp.fw",
-		.gmem  = SZ_512K,
-	}, {
-		.rev   = ADRENO_REV(3, 3, 0, ANY_ID),
-		.revn  = 330,
-		.name  = "A330",
-		.pm4fw = "a330_pm4.fw",
-		.pfpfw = "a330_pfp.fw",
-		.gmem  = SZ_1M,
-	},
-};
-
-MODULE_FIRMWARE("a300_pm4.fw");
-MODULE_FIRMWARE("a300_pfp.fw");
-MODULE_FIRMWARE("a330_pm4.fw");
-MODULE_FIRMWARE("a330_pfp.fw");
-
 #define RB_SIZE    SZ_32K
 #define RB_BLKSIZE 16
 
@@ -252,6 +212,7 @@ void adreno_idle(struct msm_gpu *gpu)
 void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	int i;
 
 	seq_printf(m, "revision: %d (%d.%d.%d.%d)\n",
 			adreno_gpu->info->revn, adreno_gpu->rev.core,
@@ -263,6 +224,23 @@ void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
 	seq_printf(m, "rptr:     %d\n", adreno_gpu->memptrs->rptr);
 	seq_printf(m, "wptr:     %d\n", adreno_gpu->memptrs->wptr);
 	seq_printf(m, "rb wptr:  %d\n", get_wptr(gpu->rb));
+
+	gpu->funcs->pm_resume(gpu);
+
+	/* dump these out in a form that can be parsed by demsm: */
+	seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
+	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
+		uint32_t start = adreno_gpu->registers[i];
+		uint32_t end   = adreno_gpu->registers[i+1];
+		uint32_t addr;
+
+		for (addr = start; addr <= end; addr++) {
+			uint32_t val = gpu_read(gpu, addr);
+			seq_printf(m, "IO:R %08x %08x\n", addr<<2, val);
+		}
+	}
+
+	gpu->funcs->pm_suspend(gpu);
 }
 #endif
 
@@ -270,6 +248,7 @@ void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
 void adreno_dump(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	int i;
 
 	printk("revision: %d (%d.%d.%d.%d)\n",
 			adreno_gpu->info->revn, adreno_gpu->rev.core,
@@ -282,6 +261,18 @@ void adreno_dump(struct msm_gpu *gpu)
 	printk("wptr:     %d\n", adreno_gpu->memptrs->wptr);
 	printk("rb wptr:  %d\n", get_wptr(gpu->rb));
 
+	/* dump these out in a form that can be parsed by demsm: */
+	printk("IO:region %s 00000000 00020000\n", gpu->name);
+	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
+		uint32_t start = adreno_gpu->registers[i];
+		uint32_t end   = adreno_gpu->registers[i+1];
+		uint32_t addr;
+
+		for (addr = start; addr <= end; addr++) {
+			uint32_t val = gpu_read(gpu, addr);
+			printk("IO:R %08x %08x\n", addr<<2, val);
+		}
+	}
 }
 
 static uint32_t ring_freewords(struct msm_gpu *gpu)
@@ -304,65 +295,51 @@ static const char *iommu_ports[] = {
 		"gfx3d1_user", "gfx3d1_priv",
 };
 
-static inline bool _rev_match(uint8_t entry, uint8_t id)
-{
-	return (entry == ANY_ID) || (entry == id);
-}
-
 int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
-		struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs,
-		struct adreno_rev rev)
+		struct adreno_gpu *adreno_gpu, const struct adreno_gpu_funcs *funcs)
 {
+	struct adreno_platform_config *config = pdev->dev.platform_data;
+	struct msm_gpu *gpu = &adreno_gpu->base;
 	struct msm_mmu *mmu;
-	int i, ret;
-
-	/* identify gpu: */
-	for (i = 0; i < ARRAY_SIZE(gpulist); i++) {
-		const struct adreno_info *info = &gpulist[i];
-		if (_rev_match(info->rev.core, rev.core) &&
-				_rev_match(info->rev.major, rev.major) &&
-				_rev_match(info->rev.minor, rev.minor) &&
-				_rev_match(info->rev.patchid, rev.patchid)) {
-			gpu->info = info;
-			gpu->revn = info->revn;
-			break;
-		}
-	}
-
-	if (i == ARRAY_SIZE(gpulist)) {
-		dev_err(drm->dev, "Unknown GPU revision: %u.%u.%u.%u\n",
-				rev.core, rev.major, rev.minor, rev.patchid);
-		return -ENXIO;
-	}
+	int ret;
 
-	DBG("Found GPU: %s (%u.%u.%u.%u)", gpu->info->name,
-			rev.core, rev.major, rev.minor, rev.patchid);
+	adreno_gpu->funcs = funcs;
+	adreno_gpu->info = adreno_info(config->rev);
+	adreno_gpu->gmem = adreno_gpu->info->gmem;
+	adreno_gpu->revn = adreno_gpu->info->revn;
+	adreno_gpu->rev = config->rev;
+
+	gpu->fast_rate = config->fast_rate;
+	gpu->slow_rate = config->slow_rate;
+	gpu->bus_freq  = config->bus_freq;
+#ifdef CONFIG_MSM_BUS_SCALING
+	gpu->bus_scale_table = config->bus_scale_table;
+#endif
 
-	gpu->funcs = funcs;
-	gpu->gmem = gpu->info->gmem;
-	gpu->rev = rev;
+	DBG("fast_rate=%u, slow_rate=%u, bus_freq=%u",
+			gpu->fast_rate, gpu->slow_rate, gpu->bus_freq);
 
-	ret = request_firmware(&gpu->pm4, gpu->info->pm4fw, drm->dev);
+	ret = request_firmware(&adreno_gpu->pm4, adreno_gpu->info->pm4fw, drm->dev);
 	if (ret) {
 		dev_err(drm->dev, "failed to load %s PM4 firmware: %d\n",
-				gpu->info->pm4fw, ret);
+				adreno_gpu->info->pm4fw, ret);
 		return ret;
 	}
 
-	ret = request_firmware(&gpu->pfp, gpu->info->pfpfw, drm->dev);
+	ret = request_firmware(&adreno_gpu->pfp, adreno_gpu->info->pfpfw, drm->dev);
 	if (ret) {
 		dev_err(drm->dev, "failed to load %s PFP firmware: %d\n",
-				gpu->info->pfpfw, ret);
+				adreno_gpu->info->pfpfw, ret);
 		return ret;
 	}
 
-	ret = msm_gpu_init(drm, pdev, &gpu->base, &funcs->base,
-			gpu->info->name, "kgsl_3d0_reg_memory", "kgsl_3d0_irq",
+	ret = msm_gpu_init(drm, pdev, &adreno_gpu->base, &funcs->base,
+			adreno_gpu->info->name, "kgsl_3d0_reg_memory", "kgsl_3d0_irq",
 			RB_SIZE);
 	if (ret)
 		return ret;
 
-	mmu = gpu->base.mmu;
+	mmu = gpu->mmu;
 	if (mmu) {
 		ret = mmu->funcs->attach(mmu, iommu_ports,
 				ARRAY_SIZE(iommu_ports));
@@ -371,24 +348,24 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	}
 
 	mutex_lock(&drm->struct_mutex);
-	gpu->memptrs_bo = msm_gem_new(drm, sizeof(*gpu->memptrs),
+	adreno_gpu->memptrs_bo = msm_gem_new(drm, sizeof(*adreno_gpu->memptrs),
 			MSM_BO_UNCACHED);
 	mutex_unlock(&drm->struct_mutex);
-	if (IS_ERR(gpu->memptrs_bo)) {
-		ret = PTR_ERR(gpu->memptrs_bo);
-		gpu->memptrs_bo = NULL;
+	if (IS_ERR(adreno_gpu->memptrs_bo)) {
+		ret = PTR_ERR(adreno_gpu->memptrs_bo);
+		adreno_gpu->memptrs_bo = NULL;
 		dev_err(drm->dev, "could not allocate memptrs: %d\n", ret);
 		return ret;
 	}
 
-	gpu->memptrs = msm_gem_vaddr(gpu->memptrs_bo);
-	if (!gpu->memptrs) {
+	adreno_gpu->memptrs = msm_gem_vaddr(adreno_gpu->memptrs_bo);
+	if (!adreno_gpu->memptrs) {
 		dev_err(drm->dev, "could not vmap memptrs\n");
 		return -ENOMEM;
 	}
 
-	ret = msm_gem_get_iova(gpu->memptrs_bo, gpu->base.id,
-			&gpu->memptrs_iova);
+	ret = msm_gem_get_iova(adreno_gpu->memptrs_bo, gpu->id,
+			&adreno_gpu->memptrs_iova);
 	if (ret) {
 		dev_err(drm->dev, "could not map memptrs: %d\n", ret);
 		return ret;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 63c36ce33020..52f051579753 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -39,7 +39,16 @@ struct adreno_gpu_funcs {
 	struct msm_gpu_funcs base;
 };
 
-struct adreno_info;
+struct adreno_info {
+	struct adreno_rev rev;
+	uint32_t revn;
+	const char *name;
+	const char *pm4fw, *pfpfw;
+	uint32_t gmem;
+	struct msm_gpu *(*init)(struct drm_device *dev);
+};
+
+const struct adreno_info *adreno_info(struct adreno_rev rev);
 
 struct adreno_rbmemptrs {
 	volatile uint32_t rptr;
@@ -55,6 +64,9 @@ struct adreno_gpu {
 	uint32_t revn;  /* numeric revision name */
 	const struct adreno_gpu_funcs *funcs;
 
+	/* interesting register offsets to dump: */
+	const unsigned int *registers;
+
 	/* firmware: */
 	const struct firmware *pm4, *pfp;
 
@@ -131,8 +143,7 @@ void adreno_dump(struct msm_gpu *gpu);
 void adreno_wait_ring(struct msm_gpu *gpu, uint32_t ndwords);
 
 int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
-		struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs,
-		struct adreno_rev rev);
+		struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs);
 void adreno_gpu_cleanup(struct adreno_gpu *gpu);
 
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h
index 4eee0ec8f069..6ef43f66c30a 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_pm4.xml.h
@@ -12,9 +12,9 @@ The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml  (   1453 bytes, from 2013-03-31 16:51:27)
 - /home/robclark/src/freedreno/envytools/rnndb/adreno/a2xx.xml          (  32901 bytes, from 2014-06-02 15:21:30)
 - /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_common.xml (   9859 bytes, from 2014-06-02 15:21:30)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  14477 bytes, from 2014-05-16 11:51:57)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  58020 bytes, from 2014-06-25 12:57:16)
-- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          (  26602 bytes, from 2014-06-25 12:57:16)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/adreno_pm4.xml    (  14960 bytes, from 2014-07-27 17:22:13)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a3xx.xml          (  58020 bytes, from 2014-08-01 12:22:48)
+- /home/robclark/src/freedreno/envytools/rnndb/adreno/a4xx.xml          (  41068 bytes, from 2014-08-01 12:22:48)
 
 Copyright (C) 2013-2014 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
@@ -163,12 +163,16 @@ enum adreno_pm4_type3_packets {
 	CP_INDIRECT_BUFFER_PFE = 63,
 	CP_SET_BIN = 76,
 	CP_TEST_TWO_MEMS = 113,
+	CP_REG_WR_NO_CTXT = 120,
+	CP_RECORD_PFP_TIMESTAMP = 17,
 	CP_WAIT_FOR_ME = 19,
 	CP_SET_DRAW_STATE = 67,
 	CP_DRAW_INDX_OFFSET = 56,
 	CP_DRAW_INDIRECT = 40,
 	CP_DRAW_INDX_INDIRECT = 41,
 	CP_DRAW_AUTO = 36,
+	CP_UNKNOWN_1A = 26,
+	CP_WIDE_REG_WRITE = 116,
 	IN_IB_PREFETCH_END = 23,
 	IN_SUBBLK_PREFETCH = 31,
 	IN_INSTR_PREFETCH = 32,
diff --git a/drivers/gpu/drm/msm/dsi/dsi.xml.h b/drivers/gpu/drm/msm/dsi/dsi.xml.h
index 0f1f5b9459a5..e965898dfda6 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.xml.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.xml.h
@@ -10,14 +10,14 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    647 bytes, from 2013-11-30 14:45:35)
 - /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  17996 bytes, from 2013-12-01 19:10:31)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2013-11-30 15:00:52)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-06-25 12:55:02)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20457 bytes, from 2014-08-01 12:22:48)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2014-07-17 15:34:33)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-07-17 15:34:33)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2014-08-01 12:23:53)
 - /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-06-25 12:53:44)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-07-17 15:33:30)
 
 Copyright (C) 2013 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
diff --git a/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h b/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h
index d468f86f637c..f2bdda957205 100644
--- a/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h
+++ b/drivers/gpu/drm/msm/dsi/mmss_cc.xml.h
@@ -10,16 +10,16 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    647 bytes, from 2013-11-30 14:45:35)
 - /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  17996 bytes, from 2013-12-01 19:10:31)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2013-11-30 15:00:52)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-06-25 12:55:02)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20457 bytes, from 2014-08-01 12:22:48)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2014-07-17 15:34:33)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-07-17 15:34:33)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2014-08-01 12:23:53)
 - /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-06-25 12:53:44)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-07-17 15:33:30)
 
-Copyright (C) 2013 by the following authors:
+Copyright (C) 2013-2014 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 
 Permission is hereby granted, free of charge, to any person obtaining
@@ -112,5 +112,11 @@ static inline uint32_t MMSS_CC_CLK_NS_VAL(uint32_t val)
 	return ((val) << MMSS_CC_CLK_NS_VAL__SHIFT) & MMSS_CC_CLK_NS_VAL__MASK;
 }
 
+#define REG_MMSS_CC_DSI2_PIXEL_CC				0x00000094
+
+#define REG_MMSS_CC_DSI2_PIXEL_NS				0x000000e4
+
+#define REG_MMSS_CC_DSI2_PIXEL_CC2				0x00000264
+
 
 #endif /* MMSS_CC_XML */
diff --git a/drivers/gpu/drm/msm/dsi/sfpb.xml.h b/drivers/gpu/drm/msm/dsi/sfpb.xml.h
index da8740054cdf..e5b071ffd865 100644
--- a/drivers/gpu/drm/msm/dsi/sfpb.xml.h
+++ b/drivers/gpu/drm/msm/dsi/sfpb.xml.h
@@ -10,14 +10,14 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    647 bytes, from 2013-11-30 14:45:35)
 - /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  17996 bytes, from 2013-12-01 19:10:31)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2013-11-30 15:00:52)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-06-25 12:55:02)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20457 bytes, from 2014-08-01 12:22:48)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2014-07-17 15:34:33)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-07-17 15:34:33)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2014-08-01 12:23:53)
 - /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-06-25 12:53:44)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-07-17 15:33:30)
 
 Copyright (C) 2013 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c
index c6c9b02e0ada..9d00dcba6959 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.c
@@ -123,7 +123,7 @@ struct hdmi *hdmi_init(struct drm_device *dev, struct drm_encoder *encoder)
 	for (i = 0; i < config->hpd_reg_cnt; i++) {
 		struct regulator *reg;
 
-		reg = devm_regulator_get_exclusive(&pdev->dev,
+		reg = devm_regulator_get(&pdev->dev,
 				config->hpd_reg_names[i]);
 		if (IS_ERR(reg)) {
 			ret = PTR_ERR(reg);
@@ -139,7 +139,7 @@ struct hdmi *hdmi_init(struct drm_device *dev, struct drm_encoder *encoder)
 	for (i = 0; i < config->pwr_reg_cnt; i++) {
 		struct regulator *reg;
 
-		reg = devm_regulator_get_exclusive(&pdev->dev,
+		reg = devm_regulator_get(&pdev->dev,
 				config->pwr_reg_names[i]);
 		if (IS_ERR(reg)) {
 			ret = PTR_ERR(reg);
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.xml.h b/drivers/gpu/drm/msm/hdmi/hdmi.xml.h
index e89fe053d375..76fd0cfc6558 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.xml.h
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.xml.h
@@ -10,14 +10,14 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    647 bytes, from 2013-11-30 14:45:35)
 - /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  17996 bytes, from 2013-12-01 19:10:31)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2013-11-30 15:00:52)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-06-25 12:55:02)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20457 bytes, from 2014-08-01 12:22:48)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2014-07-17 15:34:33)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-07-17 15:34:33)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2014-08-01 12:23:53)
 - /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-06-25 12:53:44)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-07-17 15:33:30)
 
 Copyright (C) 2013-2014 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
diff --git a/drivers/gpu/drm/msm/hdmi/qfprom.xml.h b/drivers/gpu/drm/msm/hdmi/qfprom.xml.h
index bd81db6a7829..d53c29327df9 100644
--- a/drivers/gpu/drm/msm/hdmi/qfprom.xml.h
+++ b/drivers/gpu/drm/msm/hdmi/qfprom.xml.h
@@ -10,14 +10,14 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    647 bytes, from 2013-11-30 14:45:35)
 - /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  17996 bytes, from 2013-12-01 19:10:31)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2013-11-30 15:00:52)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-06-25 12:55:02)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20457 bytes, from 2014-08-01 12:22:48)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2014-07-17 15:34:33)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-07-17 15:34:33)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2014-08-01 12:23:53)
 - /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-06-25 12:53:44)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-07-17 15:33:30)
 
 Copyright (C) 2013 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4.xml.h b/drivers/gpu/drm/msm/mdp/mdp4/mdp4.xml.h
index 122208e8a2ee..03c0bd9cd5b9 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4.xml.h
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4.xml.h
@@ -10,16 +10,16 @@ git clone https://github.com/freedreno/envytools.git
 The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/freedreno/envytools/rnndb/msm.xml                 (    647 bytes, from 2013-11-30 14:45:35)
 - /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml (   1453 bytes, from 2013-03-31 16:51:27)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  17996 bytes, from 2013-12-01 19:10:31)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2013-11-30 15:00:52)
-- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-06-25 12:55:02)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml            (  20457 bytes, from 2014-08-01 12:22:48)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml      (   1615 bytes, from 2014-07-17 15:34:33)
+- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml            (  22517 bytes, from 2014-07-17 15:34:33)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml             (  11712 bytes, from 2013-08-17 17:13:43)
 - /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml            (    344 bytes, from 2013-08-11 19:26:32)
-- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1544 bytes, from 2013-08-16 19:17:05)
+- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml         (   1686 bytes, from 2014-08-01 12:23:53)
 - /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml         (    600 bytes, from 2013-07-05 19:21:12)
-- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-06-25 12:53:44)
+- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml           (  23613 bytes, from 2014-07-17 15:33:30)
 
-Copyright (C) 2013 by the following authors:
+Copyright (C) 2013-2014 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 
 Permission is hereby granted, free of charge, to any person obtaining
@@ -871,6 +871,101 @@ static inline uint32_t MDP4_LCDC_UNDERFLOW_CLR_COLOR(uint32_t val)
 #define MDP4_LCDC_CTRL_POLARITY_VSYNC_LOW			0x00000002
 #define MDP4_LCDC_CTRL_POLARITY_DATA_EN_LOW			0x00000004
 
+#define REG_MDP4_LCDC_LVDS_INTF_CTL				0x000c2000
+#define MDP4_LCDC_LVDS_INTF_CTL_MODE_SEL			0x00000004
+#define MDP4_LCDC_LVDS_INTF_CTL_RGB_OUT				0x00000008
+#define MDP4_LCDC_LVDS_INTF_CTL_CH_SWAP				0x00000010
+#define MDP4_LCDC_LVDS_INTF_CTL_CH1_RES_BIT			0x00000020
+#define MDP4_LCDC_LVDS_INTF_CTL_CH2_RES_BIT			0x00000040
+#define MDP4_LCDC_LVDS_INTF_CTL_ENABLE				0x00000080
+#define MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE0_EN		0x00000100
+#define MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE1_EN		0x00000200
+#define MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE2_EN		0x00000400
+#define MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE3_EN		0x00000800
+#define MDP4_LCDC_LVDS_INTF_CTL_CH2_DATA_LANE0_EN		0x00001000
+#define MDP4_LCDC_LVDS_INTF_CTL_CH2_DATA_LANE1_EN		0x00002000
+#define MDP4_LCDC_LVDS_INTF_CTL_CH2_DATA_LANE2_EN		0x00004000
+#define MDP4_LCDC_LVDS_INTF_CTL_CH2_DATA_LANE3_EN		0x00008000
+#define MDP4_LCDC_LVDS_INTF_CTL_CH1_CLK_LANE_EN			0x00010000
+#define MDP4_LCDC_LVDS_INTF_CTL_CH2_CLK_LANE_EN			0x00020000
+
+static inline uint32_t REG_MDP4_LCDC_LVDS_MUX_CTL(uint32_t i0) { return 0x000c2014 + 0x8*i0; }
+
+static inline uint32_t REG_MDP4_LCDC_LVDS_MUX_CTL_3_TO_0(uint32_t i0) { return 0x000c2014 + 0x8*i0; }
+#define MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0__MASK		0x000000ff
+#define MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0__SHIFT		0
+static inline uint32_t MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0__SHIFT) & MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0__MASK;
+}
+#define MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1__MASK		0x0000ff00
+#define MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1__SHIFT		8
+static inline uint32_t MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1__SHIFT) & MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1__MASK;
+}
+#define MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2__MASK		0x00ff0000
+#define MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2__SHIFT		16
+static inline uint32_t MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2__SHIFT) & MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2__MASK;
+}
+#define MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3__MASK		0xff000000
+#define MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3__SHIFT		24
+static inline uint32_t MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3__SHIFT) & MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3__MASK;
+}
+
+static inline uint32_t REG_MDP4_LCDC_LVDS_MUX_CTL_6_TO_4(uint32_t i0) { return 0x000c2018 + 0x8*i0; }
+#define MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4__MASK		0x000000ff
+#define MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4__SHIFT		0
+static inline uint32_t MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4__SHIFT) & MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4__MASK;
+}
+#define MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5__MASK		0x0000ff00
+#define MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5__SHIFT		8
+static inline uint32_t MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5__SHIFT) & MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5__MASK;
+}
+#define MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6__MASK		0x00ff0000
+#define MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6__SHIFT		16
+static inline uint32_t MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6(uint32_t val)
+{
+	return ((val) << MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6__SHIFT) & MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6__MASK;
+}
+
+#define REG_MDP4_LCDC_LVDS_PHY_RESET				0x000c2034
+
+#define REG_MDP4_LVDS_PHY_PLL_CTRL_0				0x000c3000
+
+#define REG_MDP4_LVDS_PHY_PLL_CTRL_1				0x000c3004
+
+#define REG_MDP4_LVDS_PHY_PLL_CTRL_2				0x000c3008
+
+#define REG_MDP4_LVDS_PHY_PLL_CTRL_3				0x000c300c
+
+#define REG_MDP4_LVDS_PHY_PLL_CTRL_5				0x000c3014
+
+#define REG_MDP4_LVDS_PHY_PLL_CTRL_6				0x000c3018
+
+#define REG_MDP4_LVDS_PHY_PLL_CTRL_7				0x000c301c
+
+#define REG_MDP4_LVDS_PHY_PLL_CTRL_8				0x000c3020
+
+#define REG_MDP4_LVDS_PHY_PLL_CTRL_9				0x000c3024
+
+#define REG_MDP4_LVDS_PHY_PLL_LOCKED				0x000c3080
+
+#define REG_MDP4_LVDS_PHY_CFG2					0x000c3108
+
+#define REG_MDP4_LVDS_PHY_CFG0					0x000c3100
+#define MDP4_LVDS_PHY_CFG0_SERIALIZATION_ENBLE			0x00000010
+#define MDP4_LVDS_PHY_CFG0_CHANNEL0				0x00000040
+#define MDP4_LVDS_PHY_CFG0_CHANNEL1				0x00000080
+
 #define REG_MDP4_DTV						0x000d0000
 
 #define REG_MDP4_DTV_ENABLE					0x000d0000
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
index c6c80ea28c35..7d00f7fb5773 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
@@ -273,14 +273,17 @@ static void blend_setup(struct drm_crtc *crtc)
 	};
 	bool alpha[4]= { false, false, false, false };
 
+	/* Don't rely on value read back from hw, but instead use our
+	 * own shadowed value.  Possibly disable/reenable looses the
+	 * previous value and goes back to power-on default?
+	 */
+	mixer_cfg = mdp4_kms->mixer_cfg;
+
 	mdp4_write(mdp4_kms, REG_MDP4_OVLP_TRANSP_LOW0(ovlp), 0);
 	mdp4_write(mdp4_kms, REG_MDP4_OVLP_TRANSP_LOW1(ovlp), 0);
 	mdp4_write(mdp4_kms, REG_MDP4_OVLP_TRANSP_HIGH0(ovlp), 0);
 	mdp4_write(mdp4_kms, REG_MDP4_OVLP_TRANSP_HIGH1(ovlp), 0);
 
-	/* TODO single register for all CRTCs, so this won't work properly
-	 * when multiple CRTCs are active..
-	 */
 	for (i = 0; i < ARRAY_SIZE(mdp4_crtc->planes); i++) {
 		struct drm_plane *plane = mdp4_crtc->planes[i];
 		if (plane) {
@@ -291,7 +294,8 @@ static void blend_setup(struct drm_crtc *crtc)
 					to_mdp_format(msm_framebuffer_format(plane->fb));
 				alpha[idx-1] = format->alpha_enable;
 			}
-			mixer_cfg |= mixercfg(mdp4_crtc->mixer, pipe_id, stages[idx]);
+			mixer_cfg = mixercfg(mixer_cfg, mdp4_crtc->mixer,
+					pipe_id, stages[idx]);
 		}
 	}
 
@@ -320,6 +324,7 @@ static void blend_setup(struct drm_crtc *crtc)
 		mdp4_write(mdp4_kms, REG_MDP4_OVLP_STAGE_TRANSP_HIGH1(ovlp, i), 0);
 	}
 
+	mdp4_kms->mixer_cfg = mixer_cfg;
 	mdp4_write(mdp4_kms, REG_MDP4_LAYERMIXER_IN_CFG, mixer_cfg);
 }
 
@@ -672,7 +677,7 @@ void mdp4_crtc_set_config(struct drm_crtc *crtc, uint32_t config)
 }
 
 /* set interface for routing crtc->encoder: */
-void mdp4_crtc_set_intf(struct drm_crtc *crtc, enum mdp4_intf intf)
+void mdp4_crtc_set_intf(struct drm_crtc *crtc, enum mdp4_intf intf, int mixer)
 {
 	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
 	struct mdp4_kms *mdp4_kms = get_kms(crtc);
@@ -698,15 +703,13 @@ void mdp4_crtc_set_intf(struct drm_crtc *crtc, enum mdp4_intf intf)
 	if (intf == INTF_DSI_VIDEO) {
 		intf_sel &= ~MDP4_DISP_INTF_SEL_DSI_CMD;
 		intf_sel |= MDP4_DISP_INTF_SEL_DSI_VIDEO;
-		mdp4_crtc->mixer = 0;
 	} else if (intf == INTF_DSI_CMD) {
 		intf_sel &= ~MDP4_DISP_INTF_SEL_DSI_VIDEO;
 		intf_sel |= MDP4_DISP_INTF_SEL_DSI_CMD;
-		mdp4_crtc->mixer = 0;
-	} else if (intf == INTF_LCDC_DTV){
-		mdp4_crtc->mixer = 1;
 	}
 
+	mdp4_crtc->mixer = mixer;
+
 	blend_setup(crtc);
 
 	DBG("%s: intf_sel=%08x", mdp4_crtc->name, intf_sel);
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c
index 067ed03b35fe..c3878420180b 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_dtv_encoder.c
@@ -233,7 +233,7 @@ static void mdp4_dtv_encoder_commit(struct drm_encoder *encoder)
 			MDP4_DMA_CONFIG_G_BPC(BPC8) |
 			MDP4_DMA_CONFIG_B_BPC(BPC8) |
 			MDP4_DMA_CONFIG_PACK(0x21));
-	mdp4_crtc_set_intf(encoder->crtc, INTF_LCDC_DTV);
+	mdp4_crtc_set_intf(encoder->crtc, INTF_LCDC_DTV, 1);
 	mdp4_dtv_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
 }
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
index 733646c0d3f8..79d804e61cc4 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
@@ -106,6 +106,7 @@ static int mdp4_hw_init(struct msm_kms *kms)
 
 	if (mdp4_kms->rev >= 2)
 		mdp4_write(mdp4_kms, REG_MDP4_LAYERMIXER_IN_CFG_UPDATE_METHOD, 1);
+	mdp4_write(mdp4_kms, REG_MDP4_LAYERMIXER_IN_CFG, 0);
 
 	/* disable CSC matrix / YUV by default: */
 	mdp4_write(mdp4_kms, REG_MDP4_PIPE_OP_MODE(VG1), 0);
@@ -196,6 +197,28 @@ int mdp4_enable(struct mdp4_kms *mdp4_kms)
 	return 0;
 }
 
+#ifdef CONFIG_OF
+static struct drm_panel *detect_panel(struct drm_device *dev, const char *name)
+{
+	struct device_node *n;
+	struct drm_panel *panel = NULL;
+
+	n = of_parse_phandle(dev->dev->of_node, name, 0);
+	if (n) {
+		panel = of_drm_find_panel(n);
+		if (!panel)
+			panel = ERR_PTR(-EPROBE_DEFER);
+	}
+
+	return panel;
+}
+#else
+static struct drm_panel *detect_panel(struct drm_device *dev, const char *name)
+{
+	// ??? maybe use a module param to specify which panel is attached?
+}
+#endif
+
 static int modeset_init(struct mdp4_kms *mdp4_kms)
 {
 	struct drm_device *dev = mdp4_kms->dev;
@@ -203,14 +226,11 @@ static int modeset_init(struct mdp4_kms *mdp4_kms)
 	struct drm_plane *plane;
 	struct drm_crtc *crtc;
 	struct drm_encoder *encoder;
+	struct drm_connector *connector;
+	struct drm_panel *panel;
 	struct hdmi *hdmi;
 	int ret;
 
-	/*
-	 *  NOTE: this is a bit simplistic until we add support
-	 * for more than just RGB1->DMA_E->DTV->HDMI
-	 */
-
 	/* construct non-private planes: */
 	plane = mdp4_plane_init(dev, VG1, false);
 	if (IS_ERR(plane)) {
@@ -228,7 +248,57 @@ static int modeset_init(struct mdp4_kms *mdp4_kms)
 	}
 	priv->planes[priv->num_planes++] = plane;
 
-	/* the CRTCs get constructed with a private plane: */
+	/*
+	 * Setup the LCDC/LVDS path: RGB2 -> DMA_P -> LCDC -> LVDS:
+	 */
+
+	panel = detect_panel(dev, "qcom,lvds-panel");
+	if (IS_ERR(panel)) {
+		ret = PTR_ERR(panel);
+		dev_err(dev->dev, "failed to detect LVDS panel: %d\n", ret);
+		goto fail;
+	}
+
+	plane = mdp4_plane_init(dev, RGB2, true);
+	if (IS_ERR(plane)) {
+		dev_err(dev->dev, "failed to construct plane for RGB2\n");
+		ret = PTR_ERR(plane);
+		goto fail;
+	}
+
+	crtc  = mdp4_crtc_init(dev, plane, priv->num_crtcs, 0, DMA_P);
+	if (IS_ERR(crtc)) {
+		dev_err(dev->dev, "failed to construct crtc for DMA_P\n");
+		ret = PTR_ERR(crtc);
+		goto fail;
+	}
+
+	encoder = mdp4_lcdc_encoder_init(dev, panel);
+	if (IS_ERR(encoder)) {
+		dev_err(dev->dev, "failed to construct LCDC encoder\n");
+		ret = PTR_ERR(encoder);
+		goto fail;
+	}
+
+	/* LCDC can be hooked to DMA_P: */
+	encoder->possible_crtcs = 1 << priv->num_crtcs;
+
+	priv->crtcs[priv->num_crtcs++] = crtc;
+	priv->encoders[priv->num_encoders++] = encoder;
+
+	connector = mdp4_lvds_connector_init(dev, panel, encoder);
+	if (IS_ERR(connector)) {
+		ret = PTR_ERR(connector);
+		dev_err(dev->dev, "failed to initialize LVDS connector: %d\n", ret);
+		goto fail;
+	}
+
+	priv->connectors[priv->num_connectors++] = connector;
+
+	/*
+	 * Setup DTV/HDMI path: RGB1 -> DMA_E -> DTV -> HDMI:
+	 */
+
 	plane = mdp4_plane_init(dev, RGB1, true);
 	if (IS_ERR(plane)) {
 		dev_err(dev->dev, "failed to construct plane for RGB1\n");
@@ -242,7 +312,6 @@ static int modeset_init(struct mdp4_kms *mdp4_kms)
 		ret = PTR_ERR(crtc);
 		goto fail;
 	}
-	priv->crtcs[priv->num_crtcs++] = crtc;
 
 	encoder = mdp4_dtv_encoder_init(dev);
 	if (IS_ERR(encoder)) {
@@ -250,7 +319,11 @@ static int modeset_init(struct mdp4_kms *mdp4_kms)
 		ret = PTR_ERR(encoder);
 		goto fail;
 	}
-	encoder->possible_crtcs = 0x1;     /* DTV can be hooked to DMA_E */
+
+	/* DTV can be hooked to DMA_E: */
+	encoder->possible_crtcs = 1 << priv->num_crtcs;
+
+	priv->crtcs[priv->num_crtcs++] = crtc;
 	priv->encoders[priv->num_encoders++] = encoder;
 
 	hdmi = hdmi_init(dev, encoder);
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
index 3225da804c61..9ff6e7ccfe90 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
@@ -23,6 +23,8 @@
 #include "mdp/mdp_kms.h"
 #include "mdp4.xml.h"
 
+#include "drm_panel.h"
+
 struct mdp4_kms {
 	struct mdp_kms base;
 
@@ -30,6 +32,13 @@ struct mdp4_kms {
 
 	int rev;
 
+	/* Shadow value for MDP4_LAYERMIXER_IN_CFG.. since setup for all
+	 * crtcs/encoders is in one shared register, we need to update it
+	 * via read/modify/write.  But to avoid getting confused by power-
+	 * on-default values after resume, use this shadow value instead:
+	 */
+	uint32_t mixer_cfg;
+
 	/* mapper-id used to request GEM buffer mapped for scanout: */
 	int id;
 
@@ -74,7 +83,7 @@ static inline uint32_t pipe2flush(enum mdp4_pipe pipe)
 	case VG1:      return MDP4_OVERLAY_FLUSH_VG1;
 	case VG2:      return MDP4_OVERLAY_FLUSH_VG2;
 	case RGB1:     return MDP4_OVERLAY_FLUSH_RGB1;
-	case RGB2:     return MDP4_OVERLAY_FLUSH_RGB1;
+	case RGB2:     return MDP4_OVERLAY_FLUSH_RGB2;
 	default:       return 0;
 	}
 }
@@ -108,38 +117,50 @@ static inline uint32_t dma2err(enum mdp4_dma dma)
 	}
 }
 
-static inline uint32_t mixercfg(int mixer, enum mdp4_pipe pipe,
-		enum mdp_mixer_stage_id stage)
+static inline uint32_t mixercfg(uint32_t mixer_cfg, int mixer,
+		enum mdp4_pipe pipe, enum mdp_mixer_stage_id stage)
 {
-	uint32_t mixer_cfg = 0;
-
 	switch (pipe) {
 	case VG1:
-		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE0(stage) |
+		mixer_cfg &= ~(MDP4_LAYERMIXER_IN_CFG_PIPE0__MASK |
+				MDP4_LAYERMIXER_IN_CFG_PIPE0_MIXER1);
+		mixer_cfg |= MDP4_LAYERMIXER_IN_CFG_PIPE0(stage) |
 			COND(mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE0_MIXER1);
 		break;
 	case VG2:
-		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE1(stage) |
+		mixer_cfg &= ~(MDP4_LAYERMIXER_IN_CFG_PIPE1__MASK |
+				MDP4_LAYERMIXER_IN_CFG_PIPE1_MIXER1);
+		mixer_cfg |= MDP4_LAYERMIXER_IN_CFG_PIPE1(stage) |
 			COND(mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE1_MIXER1);
 		break;
 	case RGB1:
-		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE2(stage) |
+		mixer_cfg &= ~(MDP4_LAYERMIXER_IN_CFG_PIPE2__MASK |
+				MDP4_LAYERMIXER_IN_CFG_PIPE2_MIXER1);
+		mixer_cfg |= MDP4_LAYERMIXER_IN_CFG_PIPE2(stage) |
 			COND(mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE2_MIXER1);
 		break;
 	case RGB2:
-		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE3(stage) |
+		mixer_cfg &= ~(MDP4_LAYERMIXER_IN_CFG_PIPE3__MASK |
+				MDP4_LAYERMIXER_IN_CFG_PIPE3_MIXER1);
+		mixer_cfg |= MDP4_LAYERMIXER_IN_CFG_PIPE3(stage) |
 			COND(mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE3_MIXER1);
 		break;
 	case RGB3:
-		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE4(stage) |
+		mixer_cfg &= ~(MDP4_LAYERMIXER_IN_CFG_PIPE4__MASK |
+				MDP4_LAYERMIXER_IN_CFG_PIPE4_MIXER1);
+		mixer_cfg |= MDP4_LAYERMIXER_IN_CFG_PIPE4(stage) |
 			COND(mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE4_MIXER1);
 		break;
 	case VG3:
-		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE5(stage) |
+		mixer_cfg &= ~(MDP4_LAYERMIXER_IN_CFG_PIPE5__MASK |
+				MDP4_LAYERMIXER_IN_CFG_PIPE5_MIXER1);
+		mixer_cfg |= MDP4_LAYERMIXER_IN_CFG_PIPE5(stage) |
 			COND(mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE5_MIXER1);
 		break;
 	case VG4:
-		mixer_cfg = MDP4_LAYERMIXER_IN_CFG_PIPE6(stage) |
+		mixer_cfg &= ~(MDP4_LAYERMIXER_IN_CFG_PIPE6__MASK |
+				MDP4_LAYERMIXER_IN_CFG_PIPE6_MIXER1);
+		mixer_cfg |= MDP4_LAYERMIXER_IN_CFG_PIPE6(stage) |
 			COND(mixer == 1, MDP4_LAYERMIXER_IN_CFG_PIPE6_MIXER1);
 		break;
 	default:
@@ -188,7 +209,7 @@ struct drm_plane *mdp4_plane_init(struct drm_device *dev,
 uint32_t mdp4_crtc_vblank(struct drm_crtc *crtc);
 void mdp4_crtc_cancel_pending_flip(struct drm_crtc *crtc, struct drm_file *file);
 void mdp4_crtc_set_config(struct drm_crtc *crtc, uint32_t config);
-void mdp4_crtc_set_intf(struct drm_crtc *crtc, enum mdp4_intf intf);
+void mdp4_crtc_set_intf(struct drm_crtc *crtc, enum mdp4_intf intf, int mixer);
 void mdp4_crtc_attach(struct drm_crtc *crtc, struct drm_plane *plane);
 void mdp4_crtc_detach(struct drm_crtc *crtc, struct drm_plane *plane);
 struct drm_crtc *mdp4_crtc_init(struct drm_device *dev,
@@ -198,6 +219,22 @@ struct drm_crtc *mdp4_crtc_init(struct drm_device *dev,
 long mdp4_dtv_round_pixclk(struct drm_encoder *encoder, unsigned long rate);
 struct drm_encoder *mdp4_dtv_encoder_init(struct drm_device *dev);
 
+long mdp4_lcdc_round_pixclk(struct drm_encoder *encoder, unsigned long rate);
+struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev,
+		struct drm_panel *panel);
+
+struct drm_connector *mdp4_lvds_connector_init(struct drm_device *dev,
+		struct drm_panel *panel, struct drm_encoder *encoder);
+
+#ifdef CONFIG_COMMON_CLK
+struct clk *mpd4_lvds_pll_init(struct drm_device *dev);
+#else
+static inline struct clk *mpd4_lvds_pll_init(struct drm_device *dev)
+{
+	return ERR_PTR(-ENODEV);
+}
+#endif
+
 #ifdef CONFIG_MSM_BUS_SCALING
 static inline int match_dev_name(struct device *dev, void *data)
 {
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lcdc_encoder.c
new file mode 100644
index 000000000000..41f6436754fc
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lcdc_encoder.c
@@ -0,0 +1,506 @@
+/*
+ * Copyright (C) 2014 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ * Author: Vinay Simha <vinaysimha@inforcecomputing.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "mdp4_kms.h"
+
+#include "drm_crtc.h"
+#include "drm_crtc_helper.h"
+
+struct mdp4_lcdc_encoder {
+	struct drm_encoder base;
+	struct drm_panel *panel;
+	struct clk *lcdc_clk;
+	unsigned long int pixclock;
+	struct regulator *regs[3];
+	bool enabled;
+	uint32_t bsc;
+};
+#define to_mdp4_lcdc_encoder(x) container_of(x, struct mdp4_lcdc_encoder, base)
+
+static struct mdp4_kms *get_kms(struct drm_encoder *encoder)
+{
+	struct msm_drm_private *priv = encoder->dev->dev_private;
+	return to_mdp4_kms(to_mdp_kms(priv->kms));
+}
+
+#ifdef CONFIG_MSM_BUS_SCALING
+#include <mach/board.h>
+static void bs_init(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder)
+{
+	struct drm_device *dev = mdp4_lcdc_encoder->base.dev;
+	struct lcdc_platform_data *lcdc_pdata = mdp4_find_pdata("lvds.0");
+
+	if (!lcdc_pdata) {
+		dev_err(dev->dev, "could not find lvds pdata\n");
+		return;
+	}
+
+	if (lcdc_pdata->bus_scale_table) {
+		mdp4_lcdc_encoder->bsc = msm_bus_scale_register_client(
+				lcdc_pdata->bus_scale_table);
+		DBG("lvds : bus scale client: %08x", mdp4_lcdc_encoder->bsc);
+	}
+}
+
+static void bs_fini(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder)
+{
+	if (mdp4_lcdc_encoder->bsc) {
+		msm_bus_scale_unregister_client(mdp4_lcdc_encoder->bsc);
+		mdp4_lcdc_encoder->bsc = 0;
+	}
+}
+
+static void bs_set(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder, int idx)
+{
+	if (mdp4_lcdc_encoder->bsc) {
+		DBG("set bus scaling: %d", idx);
+		msm_bus_scale_client_update_request(mdp4_lcdc_encoder->bsc, idx);
+	}
+}
+#else
+static void bs_init(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder) {}
+static void bs_fini(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder) {}
+static void bs_set(struct mdp4_lcdc_encoder *mdp4_lcdc_encoder, int idx) {}
+#endif
+
+static void mdp4_lcdc_encoder_destroy(struct drm_encoder *encoder)
+{
+	struct mdp4_lcdc_encoder *mdp4_lcdc_encoder =
+			to_mdp4_lcdc_encoder(encoder);
+	bs_fini(mdp4_lcdc_encoder);
+	drm_encoder_cleanup(encoder);
+	kfree(mdp4_lcdc_encoder);
+}
+
+static const struct drm_encoder_funcs mdp4_lcdc_encoder_funcs = {
+	.destroy = mdp4_lcdc_encoder_destroy,
+};
+
+/* this should probably be a helper: */
+struct drm_connector *get_connector(struct drm_encoder *encoder)
+{
+	struct drm_device *dev = encoder->dev;
+	struct drm_connector *connector;
+
+	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
+		if (connector->encoder == encoder)
+			return connector;
+
+	return NULL;
+}
+
+static void setup_phy(struct drm_encoder *encoder)
+{
+	struct drm_device *dev = encoder->dev;
+	struct drm_connector *connector = get_connector(encoder);
+	struct mdp4_kms *mdp4_kms = get_kms(encoder);
+	uint32_t lvds_intf = 0, lvds_phy_cfg0 = 0;
+	int bpp, nchan, swap;
+
+	if (!connector)
+		return;
+
+	bpp = 3 * connector->display_info.bpc;
+
+	if (!bpp)
+		bpp = 18;
+
+	/* TODO, these should come from panel somehow: */
+	nchan = 1;
+	swap = 0;
+
+	switch (bpp) {
+	case 24:
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_3_TO_0(0),
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0(0x08) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1(0x05) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2(0x04) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3(0x03));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_6_TO_4(0),
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4(0x02) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5(0x01) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6(0x00));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_3_TO_0(1),
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0(0x11) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1(0x10) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2(0x0d) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3(0x0c));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_6_TO_4(1),
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4(0x0b) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5(0x0a) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6(0x09));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_3_TO_0(2),
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0(0x1a) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1(0x19) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2(0x18) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3(0x15));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_6_TO_4(2),
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4(0x14) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5(0x13) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6(0x12));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_3_TO_0(3),
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0(0x1b) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1(0x17) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2(0x16) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3(0x0f));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_6_TO_4(3),
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4(0x0e) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5(0x07) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6(0x06));
+		if (nchan == 2) {
+			lvds_intf |= MDP4_LCDC_LVDS_INTF_CTL_CH2_DATA_LANE3_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH2_DATA_LANE2_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH2_DATA_LANE1_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH2_DATA_LANE0_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE3_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE2_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE1_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE0_EN;
+		} else {
+			lvds_intf |= MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE3_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE2_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE1_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE0_EN;
+		}
+		break;
+
+	case 18:
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_3_TO_0(0),
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0(0x0a) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1(0x07) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2(0x06) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3(0x05));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_6_TO_4(0),
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4(0x04) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5(0x03) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6(0x02));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_3_TO_0(1),
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0(0x13) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1(0x12) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2(0x0f) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3(0x0e));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_6_TO_4(1),
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4(0x0d) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5(0x0c) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6(0x0b));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_3_TO_0(2),
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT0(0x1a) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT1(0x19) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT2(0x18) |
+				MDP4_LCDC_LVDS_MUX_CTL_3_TO_0_BIT3(0x17));
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_MUX_CTL_6_TO_4(2),
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT4(0x16) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT5(0x15) |
+				MDP4_LCDC_LVDS_MUX_CTL_6_TO_4_BIT6(0x14));
+		if (nchan == 2) {
+			lvds_intf |= MDP4_LCDC_LVDS_INTF_CTL_CH2_DATA_LANE2_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH2_DATA_LANE1_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH2_DATA_LANE0_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE2_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE1_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE0_EN;
+		} else {
+			lvds_intf |= MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE2_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE1_EN |
+					MDP4_LCDC_LVDS_INTF_CTL_CH1_DATA_LANE0_EN;
+		}
+		lvds_intf |= MDP4_LCDC_LVDS_INTF_CTL_RGB_OUT;
+		break;
+
+	default:
+		dev_err(dev->dev, "unknown bpp: %d\n", bpp);
+		return;
+	}
+
+	switch (nchan) {
+	case 1:
+		lvds_phy_cfg0 = MDP4_LVDS_PHY_CFG0_CHANNEL0;
+		lvds_intf |= MDP4_LCDC_LVDS_INTF_CTL_CH1_CLK_LANE_EN |
+				MDP4_LCDC_LVDS_INTF_CTL_MODE_SEL;
+		break;
+	case 2:
+		lvds_phy_cfg0 = MDP4_LVDS_PHY_CFG0_CHANNEL0 |
+				MDP4_LVDS_PHY_CFG0_CHANNEL1;
+		lvds_intf |= MDP4_LCDC_LVDS_INTF_CTL_CH2_CLK_LANE_EN |
+				MDP4_LCDC_LVDS_INTF_CTL_CH1_CLK_LANE_EN;
+		break;
+	default:
+		dev_err(dev->dev, "unknown # of channels: %d\n", nchan);
+		return;
+	}
+
+	if (swap)
+		lvds_intf |= MDP4_LCDC_LVDS_INTF_CTL_CH_SWAP;
+
+	lvds_intf |= MDP4_LCDC_LVDS_INTF_CTL_ENABLE;
+
+	mdp4_write(mdp4_kms, REG_MDP4_LVDS_PHY_CFG0, lvds_phy_cfg0);
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_INTF_CTL, lvds_intf);
+	mdp4_write(mdp4_kms, REG_MDP4_LVDS_PHY_CFG2, 0x30);
+
+	mb();
+	udelay(1);
+	lvds_phy_cfg0 |= MDP4_LVDS_PHY_CFG0_SERIALIZATION_ENBLE;
+	mdp4_write(mdp4_kms, REG_MDP4_LVDS_PHY_CFG0, lvds_phy_cfg0);
+}
+
+static void mdp4_lcdc_encoder_dpms(struct drm_encoder *encoder, int mode)
+{
+	struct drm_device *dev = encoder->dev;
+	struct mdp4_lcdc_encoder *mdp4_lcdc_encoder =
+			to_mdp4_lcdc_encoder(encoder);
+	struct mdp4_kms *mdp4_kms = get_kms(encoder);
+	struct drm_panel *panel = mdp4_lcdc_encoder->panel;
+	bool enabled = (mode == DRM_MODE_DPMS_ON);
+	int i, ret;
+
+	DBG("mode=%d", mode);
+
+	if (enabled == mdp4_lcdc_encoder->enabled)
+		return;
+
+	if (enabled) {
+		unsigned long pc = mdp4_lcdc_encoder->pixclock;
+		int ret;
+
+		bs_set(mdp4_lcdc_encoder, 1);
+
+		for (i = 0; i < ARRAY_SIZE(mdp4_lcdc_encoder->regs); i++) {
+			ret = regulator_enable(mdp4_lcdc_encoder->regs[i]);
+			if (ret)
+				dev_err(dev->dev, "failed to enable regulator: %d\n", ret);
+		}
+
+		DBG("setting lcdc_clk=%lu", pc);
+		ret = clk_set_rate(mdp4_lcdc_encoder->lcdc_clk, pc);
+		if (ret)
+			dev_err(dev->dev, "failed to configure lcdc_clk: %d\n", ret);
+		ret = clk_prepare_enable(mdp4_lcdc_encoder->lcdc_clk);
+		if (ret)
+			dev_err(dev->dev, "failed to enable lcdc_clk: %d\n", ret);
+
+		if (panel)
+			drm_panel_enable(panel);
+
+		setup_phy(encoder);
+
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_ENABLE, 1);
+	} else {
+		mdp4_write(mdp4_kms, REG_MDP4_LCDC_ENABLE, 0);
+
+		if (panel)
+			drm_panel_disable(panel);
+
+		/*
+		 * Wait for a vsync so we know the ENABLE=0 latched before
+		 * the (connector) source of the vsync's gets disabled,
+		 * otherwise we end up in a funny state if we re-enable
+		 * before the disable latches, which results that some of
+		 * the settings changes for the new modeset (like new
+		 * scanout buffer) don't latch properly..
+		 */
+		mdp_irq_wait(&mdp4_kms->base, MDP4_IRQ_PRIMARY_VSYNC);
+
+		clk_disable_unprepare(mdp4_lcdc_encoder->lcdc_clk);
+
+		for (i = 0; i < ARRAY_SIZE(mdp4_lcdc_encoder->regs); i++) {
+			ret = regulator_disable(mdp4_lcdc_encoder->regs[i]);
+			if (ret)
+				dev_err(dev->dev, "failed to disable regulator: %d\n", ret);
+		}
+
+		bs_set(mdp4_lcdc_encoder, 0);
+	}
+
+	mdp4_lcdc_encoder->enabled = enabled;
+}
+
+static bool mdp4_lcdc_encoder_mode_fixup(struct drm_encoder *encoder,
+		const struct drm_display_mode *mode,
+		struct drm_display_mode *adjusted_mode)
+{
+	return true;
+}
+
+static void mdp4_lcdc_encoder_mode_set(struct drm_encoder *encoder,
+		struct drm_display_mode *mode,
+		struct drm_display_mode *adjusted_mode)
+{
+	struct mdp4_lcdc_encoder *mdp4_lcdc_encoder =
+			to_mdp4_lcdc_encoder(encoder);
+	struct mdp4_kms *mdp4_kms = get_kms(encoder);
+	uint32_t lcdc_hsync_skew, vsync_period, vsync_len, ctrl_pol;
+	uint32_t display_v_start, display_v_end;
+	uint32_t hsync_start_x, hsync_end_x;
+
+	mode = adjusted_mode;
+
+	DBG("set mode: %d:\"%s\" %d %d %d %d %d %d %d %d %d %d 0x%x 0x%x",
+			mode->base.id, mode->name,
+			mode->vrefresh, mode->clock,
+			mode->hdisplay, mode->hsync_start,
+			mode->hsync_end, mode->htotal,
+			mode->vdisplay, mode->vsync_start,
+			mode->vsync_end, mode->vtotal,
+			mode->type, mode->flags);
+
+	mdp4_lcdc_encoder->pixclock = mode->clock * 1000;
+
+	DBG("pixclock=%lu", mdp4_lcdc_encoder->pixclock);
+
+	ctrl_pol = 0;
+	if (mode->flags & DRM_MODE_FLAG_NHSYNC)
+		ctrl_pol |= MDP4_LCDC_CTRL_POLARITY_HSYNC_LOW;
+	if (mode->flags & DRM_MODE_FLAG_NVSYNC)
+		ctrl_pol |= MDP4_LCDC_CTRL_POLARITY_VSYNC_LOW;
+	/* probably need to get DATA_EN polarity from panel.. */
+
+	lcdc_hsync_skew = 0;  /* get this from panel? */
+
+	hsync_start_x = (mode->htotal - mode->hsync_start);
+	hsync_end_x = mode->htotal - (mode->hsync_start - mode->hdisplay) - 1;
+
+	vsync_period = mode->vtotal * mode->htotal;
+	vsync_len = (mode->vsync_end - mode->vsync_start) * mode->htotal;
+	display_v_start = (mode->vtotal - mode->vsync_start) * mode->htotal + lcdc_hsync_skew;
+	display_v_end = vsync_period - ((mode->vsync_start - mode->vdisplay) * mode->htotal) + lcdc_hsync_skew - 1;
+
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_HSYNC_CTRL,
+			MDP4_LCDC_HSYNC_CTRL_PULSEW(mode->hsync_end - mode->hsync_start) |
+			MDP4_LCDC_HSYNC_CTRL_PERIOD(mode->htotal));
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_VSYNC_PERIOD, vsync_period);
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_VSYNC_LEN, vsync_len);
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_DISPLAY_HCTRL,
+			MDP4_LCDC_DISPLAY_HCTRL_START(hsync_start_x) |
+			MDP4_LCDC_DISPLAY_HCTRL_END(hsync_end_x));
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_DISPLAY_VSTART, display_v_start);
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_DISPLAY_VEND, display_v_end);
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_BORDER_CLR, 0);
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_UNDERFLOW_CLR,
+			MDP4_LCDC_UNDERFLOW_CLR_ENABLE_RECOVERY |
+			MDP4_LCDC_UNDERFLOW_CLR_COLOR(0xff));
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_HSYNC_SKEW, lcdc_hsync_skew);
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_CTRL_POLARITY, ctrl_pol);
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_ACTIVE_HCTL,
+			MDP4_LCDC_ACTIVE_HCTL_START(0) |
+			MDP4_LCDC_ACTIVE_HCTL_END(0));
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_ACTIVE_VSTART, 0);
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_ACTIVE_VEND, 0);
+}
+
+static void mdp4_lcdc_encoder_prepare(struct drm_encoder *encoder)
+{
+	mdp4_lcdc_encoder_dpms(encoder, DRM_MODE_DPMS_OFF);
+}
+
+static void mdp4_lcdc_encoder_commit(struct drm_encoder *encoder)
+{
+	/* TODO: hard-coded for 18bpp: */
+	mdp4_crtc_set_config(encoder->crtc,
+			MDP4_DMA_CONFIG_R_BPC(BPC6) |
+			MDP4_DMA_CONFIG_G_BPC(BPC6) |
+			MDP4_DMA_CONFIG_B_BPC(BPC6) |
+			MDP4_DMA_CONFIG_PACK_ALIGN_MSB |
+			MDP4_DMA_CONFIG_PACK(0x21) |
+			MDP4_DMA_CONFIG_DEFLKR_EN |
+			MDP4_DMA_CONFIG_DITHER_EN);
+	mdp4_crtc_set_intf(encoder->crtc, INTF_LCDC_DTV, 0);
+	mdp4_lcdc_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
+}
+
+static const struct drm_encoder_helper_funcs mdp4_lcdc_encoder_helper_funcs = {
+	.dpms = mdp4_lcdc_encoder_dpms,
+	.mode_fixup = mdp4_lcdc_encoder_mode_fixup,
+	.mode_set = mdp4_lcdc_encoder_mode_set,
+	.prepare = mdp4_lcdc_encoder_prepare,
+	.commit = mdp4_lcdc_encoder_commit,
+};
+
+long mdp4_lcdc_round_pixclk(struct drm_encoder *encoder, unsigned long rate)
+{
+	struct mdp4_lcdc_encoder *mdp4_lcdc_encoder =
+			to_mdp4_lcdc_encoder(encoder);
+	return clk_round_rate(mdp4_lcdc_encoder->lcdc_clk, rate);
+}
+
+/* initialize encoder */
+struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev,
+		struct drm_panel *panel)
+{
+	struct drm_encoder *encoder = NULL;
+	struct mdp4_lcdc_encoder *mdp4_lcdc_encoder;
+	struct regulator *reg;
+	int ret;
+
+	mdp4_lcdc_encoder = kzalloc(sizeof(*mdp4_lcdc_encoder), GFP_KERNEL);
+	if (!mdp4_lcdc_encoder) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	mdp4_lcdc_encoder->panel = panel;
+
+	encoder = &mdp4_lcdc_encoder->base;
+
+	drm_encoder_init(dev, encoder, &mdp4_lcdc_encoder_funcs,
+			 DRM_MODE_ENCODER_LVDS);
+	drm_encoder_helper_add(encoder, &mdp4_lcdc_encoder_helper_funcs);
+
+	/* TODO: do we need different pll in other cases? */
+	mdp4_lcdc_encoder->lcdc_clk = mpd4_lvds_pll_init(dev);
+	if (IS_ERR(mdp4_lcdc_encoder->lcdc_clk)) {
+		dev_err(dev->dev, "failed to get lvds_clk\n");
+		ret = PTR_ERR(mdp4_lcdc_encoder->lcdc_clk);
+		goto fail;
+	}
+
+	/* TODO: different regulators in other cases? */
+	reg = devm_regulator_get(dev->dev, "lvds-vccs-3p3v");
+	if (IS_ERR(reg)) {
+		ret = PTR_ERR(reg);
+		dev_err(dev->dev, "failed to get lvds-vccs-3p3v: %d\n", ret);
+		goto fail;
+	}
+	mdp4_lcdc_encoder->regs[0] = reg;
+
+	reg = devm_regulator_get(dev->dev, "lvds-pll-vdda");
+	if (IS_ERR(reg)) {
+		ret = PTR_ERR(reg);
+		dev_err(dev->dev, "failed to get lvds-pll-vdda: %d\n", ret);
+		goto fail;
+	}
+	mdp4_lcdc_encoder->regs[1] = reg;
+
+	reg = devm_regulator_get(dev->dev, "lvds-vdda");
+	if (IS_ERR(reg)) {
+		ret = PTR_ERR(reg);
+		dev_err(dev->dev, "failed to get lvds-vdda: %d\n", ret);
+		goto fail;
+	}
+	mdp4_lcdc_encoder->regs[2] = reg;
+
+	bs_init(mdp4_lcdc_encoder);
+
+	return encoder;
+
+fail:
+	if (encoder)
+		mdp4_lcdc_encoder_destroy(encoder);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lvds_connector.c
new file mode 100644
index 000000000000..310034688c15
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lvds_connector.c
@@ -0,0 +1,151 @@
+/*
+ * Copyright (C) 2014 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ * Author: Vinay Simha <vinaysimha@inforcecomputing.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/gpio.h>
+
+#include "mdp4_kms.h"
+
+struct mdp4_lvds_connector {
+	struct drm_connector base;
+	struct drm_encoder *encoder;
+	struct drm_panel *panel;
+};
+#define to_mdp4_lvds_connector(x) container_of(x, struct mdp4_lvds_connector, base)
+
+static enum drm_connector_status mdp4_lvds_connector_detect(
+		struct drm_connector *connector, bool force)
+{
+	struct mdp4_lvds_connector *mdp4_lvds_connector =
+			to_mdp4_lvds_connector(connector);
+
+	return mdp4_lvds_connector->panel ?
+			connector_status_connected :
+			connector_status_disconnected;
+}
+
+static void mdp4_lvds_connector_destroy(struct drm_connector *connector)
+{
+	struct mdp4_lvds_connector *mdp4_lvds_connector =
+			to_mdp4_lvds_connector(connector);
+	struct drm_panel *panel = mdp4_lvds_connector->panel;
+
+	if (panel)
+		drm_panel_detach(panel);
+
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
+
+	kfree(mdp4_lvds_connector);
+}
+
+static int mdp4_lvds_connector_get_modes(struct drm_connector *connector)
+{
+	struct mdp4_lvds_connector *mdp4_lvds_connector =
+			to_mdp4_lvds_connector(connector);
+	struct drm_panel *panel = mdp4_lvds_connector->panel;
+	int ret = 0;
+
+	if (panel)
+		ret = panel->funcs->get_modes(panel);
+
+	return ret;
+}
+
+static int mdp4_lvds_connector_mode_valid(struct drm_connector *connector,
+				 struct drm_display_mode *mode)
+{
+	struct mdp4_lvds_connector *mdp4_lvds_connector =
+			to_mdp4_lvds_connector(connector);
+	struct drm_encoder *encoder = mdp4_lvds_connector->encoder;
+	long actual, requested;
+
+	requested = 1000 * mode->clock;
+	actual = mdp4_lcdc_round_pixclk(encoder, requested);
+
+	DBG("requested=%ld, actual=%ld", requested, actual);
+
+	if (actual != requested)
+		return MODE_CLOCK_RANGE;
+
+	return MODE_OK;
+}
+
+static struct drm_encoder *
+mdp4_lvds_connector_best_encoder(struct drm_connector *connector)
+{
+	struct mdp4_lvds_connector *mdp4_lvds_connector =
+			to_mdp4_lvds_connector(connector);
+	return mdp4_lvds_connector->encoder;
+}
+
+static const struct drm_connector_funcs mdp4_lvds_connector_funcs = {
+	.dpms = drm_helper_connector_dpms,
+	.detect = mdp4_lvds_connector_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = mdp4_lvds_connector_destroy,
+};
+
+static const struct drm_connector_helper_funcs mdp4_lvds_connector_helper_funcs = {
+	.get_modes = mdp4_lvds_connector_get_modes,
+	.mode_valid = mdp4_lvds_connector_mode_valid,
+	.best_encoder = mdp4_lvds_connector_best_encoder,
+};
+
+/* initialize connector */
+struct drm_connector *mdp4_lvds_connector_init(struct drm_device *dev,
+		struct drm_panel *panel, struct drm_encoder *encoder)
+{
+	struct drm_connector *connector = NULL;
+	struct mdp4_lvds_connector *mdp4_lvds_connector;
+	int ret;
+
+	mdp4_lvds_connector = kzalloc(sizeof(*mdp4_lvds_connector), GFP_KERNEL);
+	if (!mdp4_lvds_connector) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	mdp4_lvds_connector->encoder = encoder;
+	mdp4_lvds_connector->panel = panel;
+
+	connector = &mdp4_lvds_connector->base;
+
+	drm_connector_init(dev, connector, &mdp4_lvds_connector_funcs,
+			DRM_MODE_CONNECTOR_LVDS);
+	drm_connector_helper_add(connector, &mdp4_lvds_connector_helper_funcs);
+
+	connector->polled = 0;
+
+	connector->interlace_allowed = 0;
+	connector->doublescan_allowed = 0;
+
+	drm_connector_register(connector);
+
+	drm_mode_connector_attach_encoder(connector, encoder);
+
+	if (panel)
+		drm_panel_attach(panel, connector);
+
+	return connector;
+
+fail:
+	if (connector)
+		mdp4_lvds_connector_destroy(connector);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lvds_pll.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lvds_pll.c
new file mode 100644
index 000000000000..ce4245971673
--- /dev/null
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_lvds_pll.c
@@ -0,0 +1,172 @@
+/*
+ * Copyright (C) 2014 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+
+#include "mdp4_kms.h"
+
+struct mdp4_lvds_pll {
+	struct clk_hw pll_hw;
+	struct drm_device *dev;
+	unsigned long pixclk;
+};
+#define to_mdp4_lvds_pll(x) container_of(x, struct mdp4_lvds_pll, pll_hw)
+
+static struct mdp4_kms *get_kms(struct mdp4_lvds_pll *lvds_pll)
+{
+	struct msm_drm_private *priv = lvds_pll->dev->dev_private;
+	return to_mdp4_kms(to_mdp_kms(priv->kms));
+}
+
+struct pll_rate {
+	unsigned long rate;
+	struct {
+		uint32_t val;
+		uint32_t reg;
+	} conf[32];
+};
+
+/* NOTE: keep sorted highest freq to lowest: */
+static const struct pll_rate freqtbl[] = {
+	{ 72000000, {
+		{ 0x8f, REG_MDP4_LVDS_PHY_PLL_CTRL_1 },
+		{ 0x30, REG_MDP4_LVDS_PHY_PLL_CTRL_2 },
+		{ 0xc6, REG_MDP4_LVDS_PHY_PLL_CTRL_3 },
+		{ 0x10, REG_MDP4_LVDS_PHY_PLL_CTRL_5 },
+		{ 0x07, REG_MDP4_LVDS_PHY_PLL_CTRL_6 },
+		{ 0x62, REG_MDP4_LVDS_PHY_PLL_CTRL_7 },
+		{ 0x41, REG_MDP4_LVDS_PHY_PLL_CTRL_8 },
+		{ 0x0d, REG_MDP4_LVDS_PHY_PLL_CTRL_9 },
+		{ 0, 0 } }
+	},
+};
+
+static const struct pll_rate *find_rate(unsigned long rate)
+{
+	int i;
+	for (i = 1; i < ARRAY_SIZE(freqtbl); i++)
+		if (rate > freqtbl[i].rate)
+			return &freqtbl[i-1];
+	return &freqtbl[i-1];
+}
+
+static int mpd4_lvds_pll_enable(struct clk_hw *hw)
+{
+	struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw);
+	struct mdp4_kms *mdp4_kms = get_kms(lvds_pll);
+	const struct pll_rate *pll_rate = find_rate(lvds_pll->pixclk);
+	int i;
+
+	DBG("pixclk=%lu (%lu)", lvds_pll->pixclk, pll_rate->rate);
+
+	if (WARN_ON(!pll_rate))
+		return -EINVAL;
+
+	mdp4_write(mdp4_kms, REG_MDP4_LCDC_LVDS_PHY_RESET, 0x33);
+
+	for (i = 0; pll_rate->conf[i].reg; i++)
+		mdp4_write(mdp4_kms, pll_rate->conf[i].reg, pll_rate->conf[i].val);
+
+	mdp4_write(mdp4_kms, REG_MDP4_LVDS_PHY_PLL_CTRL_0, 0x01);
+
+	/* Wait until LVDS PLL is locked and ready */
+	while (!mdp4_read(mdp4_kms, REG_MDP4_LVDS_PHY_PLL_LOCKED))
+		cpu_relax();
+
+	return 0;
+}
+
+static void mpd4_lvds_pll_disable(struct clk_hw *hw)
+{
+	struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw);
+	struct mdp4_kms *mdp4_kms = get_kms(lvds_pll);
+
+	DBG("");
+
+	mdp4_write(mdp4_kms, REG_MDP4_LVDS_PHY_CFG0, 0x0);
+	mdp4_write(mdp4_kms, REG_MDP4_LVDS_PHY_PLL_CTRL_0, 0x0);
+}
+
+static unsigned long mpd4_lvds_pll_recalc_rate(struct clk_hw *hw,
+				unsigned long parent_rate)
+{
+	struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw);
+	return lvds_pll->pixclk;
+}
+
+static long mpd4_lvds_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *parent_rate)
+{
+	const struct pll_rate *pll_rate = find_rate(rate);
+	return pll_rate->rate;
+}
+
+static int mpd4_lvds_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long parent_rate)
+{
+	struct mdp4_lvds_pll *lvds_pll = to_mdp4_lvds_pll(hw);
+	lvds_pll->pixclk = rate;
+	return 0;
+}
+
+
+static const struct clk_ops mpd4_lvds_pll_ops = {
+	.enable = mpd4_lvds_pll_enable,
+	.disable = mpd4_lvds_pll_disable,
+	.recalc_rate = mpd4_lvds_pll_recalc_rate,
+	.round_rate = mpd4_lvds_pll_round_rate,
+	.set_rate = mpd4_lvds_pll_set_rate,
+};
+
+static const char *mpd4_lvds_pll_parents[] = {
+	"pxo",
+};
+
+static struct clk_init_data pll_init = {
+	.name = "mpd4_lvds_pll",
+	.ops = &mpd4_lvds_pll_ops,
+	.parent_names = mpd4_lvds_pll_parents,
+	.num_parents = ARRAY_SIZE(mpd4_lvds_pll_parents),
+};
+
+struct clk *mpd4_lvds_pll_init(struct drm_device *dev)
+{
+	struct mdp4_lvds_pll *lvds_pll;
+	struct clk *clk;
+	int ret;
+
+	lvds_pll = devm_kzalloc(dev->dev, sizeof(*lvds_pll), GFP_KERNEL);
+	if (!lvds_pll) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	lvds_pll->dev = dev;
+
+	lvds_pll->pll_hw.init = &pll_init;
+	clk = devm_clk_register(dev->dev, &lvds_pll->pll_hw);
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		goto fail;
+	}
+
+	return clk;
+
+fail:
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index fcf95680413d..b67ef5985125 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -280,7 +280,7 @@ static int msm_load(struct drm_device *dev, unsigned long flags)
 	dev->mode_config.max_height = 2048;
 	dev->mode_config.funcs = &mode_config_funcs;
 
-	ret = drm_vblank_init(dev, 1);
+	ret = drm_vblank_init(dev, priv->num_crtcs);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to initialize vblank\n");
 		goto fail;
@@ -315,39 +315,12 @@ static void load_gpu(struct drm_device *dev)
 {
 	static DEFINE_MUTEX(init_lock);
 	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_gpu *gpu;
 
 	mutex_lock(&init_lock);
 
-	if (priv->gpu)
-		goto out;
-
-	gpu = a3xx_gpu_init(dev);
-	if (IS_ERR(gpu)) {
-		dev_warn(dev->dev, "failed to load a3xx gpu\n");
-		gpu = NULL;
-		/* not fatal */
-	}
-
-	if (gpu) {
-		int ret;
-		mutex_lock(&dev->struct_mutex);
-		gpu->funcs->pm_resume(gpu);
-		mutex_unlock(&dev->struct_mutex);
-		ret = gpu->funcs->hw_init(gpu);
-		if (ret) {
-			dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
-			gpu->funcs->destroy(gpu);
-			gpu = NULL;
-		} else {
-			/* give inactive pm a chance to kick in: */
-			msm_gpu_retire(gpu);
-		}
-	}
-
-	priv->gpu = gpu;
+	if (!priv->gpu)
+		priv->gpu = adreno_load_gpu(dev);
 
-out:
 	mutex_unlock(&init_lock);
 }
 
@@ -836,6 +809,7 @@ static struct drm_driver msm_driver = {
 	.open               = msm_open,
 	.preclose           = msm_preclose,
 	.lastclose          = msm_lastclose,
+	.set_busid          = drm_platform_set_busid,
 	.irq_handler        = msm_irq,
 	.irq_preinstall     = msm_irq_preinstall,
 	.irq_postinstall    = msm_irq_postinstall,
@@ -1025,7 +999,7 @@ static int __init msm_drm_register(void)
 {
 	DBG("init");
 	hdmi_register();
-	a3xx_register();
+	adreno_register();
 	return platform_driver_register(&msm_platform_driver);
 }
 
@@ -1034,7 +1008,7 @@ static void __exit msm_drm_unregister(void)
 	DBG("fini");
 	platform_driver_unregister(&msm_platform_driver);
 	hdmi_unregister();
-	a3xx_unregister();
+	adreno_unregister();
 }
 
 module_init(msm_drm_register);
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 8a2c5fd0893e..67f9d0a2332c 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -51,6 +51,7 @@ static inline struct device *msm_iommu_get_ctx(const char *ctx_name)
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/msm_drm.h>
+#include <drm/drm_gem.h>
 
 struct msm_kms;
 struct msm_gpu;
@@ -170,7 +171,7 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj);
 void *msm_gem_prime_vmap(struct drm_gem_object *obj);
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
-		size_t size, struct sg_table *sg);
+		struct dma_buf_attachment *attach, struct sg_table *sg);
 int msm_gem_prime_pin(struct drm_gem_object *obj);
 void msm_gem_prime_unpin(struct drm_gem_object *obj);
 void *msm_gem_vaddr_locked(struct drm_gem_object *obj);
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index d48f9fc5129b..ad772fe36115 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -18,6 +18,7 @@
 #include "msm_drv.h"
 #include "msm_gem.h"
 
+#include <linux/dma-buf.h>
 
 struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
@@ -37,9 +38,9 @@ void msm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 }
 
 struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev,
-		size_t size, struct sg_table *sg)
+		struct dma_buf_attachment *attach, struct sg_table *sg)
 {
-	return msm_gem_import(dev, size, sg);
+	return msm_gem_import(dev, attach->dmabuf->size, sg);
 }
 
 int msm_gem_prime_pin(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 9b579b792840..fd1e4b4a6d40 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -166,8 +166,8 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		const char *name, const char *ioname, const char *irqname, int ringsz);
 void msm_gpu_cleanup(struct msm_gpu *gpu);
 
-struct msm_gpu *a3xx_gpu_init(struct drm_device *dev);
-void __init a3xx_register(void);
-void __exit a3xx_unregister(void);
+struct msm_gpu *adreno_load_gpu(struct drm_device *dev);
+void __init adreno_register(void);
+void __exit adreno_unregister(void);
 
 #endif /* __MSM_GPU_H__ */
diff --git a/drivers/gpu/drm/nouveau/Makefile b/drivers/gpu/drm/nouveau/Makefile
index f5d7f7ce4bc6..12c24c8abf7f 100644
--- a/drivers/gpu/drm/nouveau/Makefile
+++ b/drivers/gpu/drm/nouveau/Makefile
@@ -38,6 +38,7 @@ nouveau-y += core/subdev/bios/dcb.o
 nouveau-y += core/subdev/bios/disp.o
 nouveau-y += core/subdev/bios/dp.o
 nouveau-y += core/subdev/bios/extdev.o
+nouveau-y += core/subdev/bios/fan.o
 nouveau-y += core/subdev/bios/gpio.o
 nouveau-y += core/subdev/bios/i2c.o
 nouveau-y += core/subdev/bios/init.o
@@ -51,6 +52,8 @@ nouveau-y += core/subdev/bios/therm.o
 nouveau-y += core/subdev/bios/vmap.o
 nouveau-y += core/subdev/bios/volt.o
 nouveau-y += core/subdev/bios/xpio.o
+nouveau-y += core/subdev/bios/M0205.o
+nouveau-y += core/subdev/bios/M0209.o
 nouveau-y += core/subdev/bios/P0260.o
 nouveau-y += core/subdev/bus/hwsq.o
 nouveau-y += core/subdev/bus/nv04.o
@@ -124,12 +127,17 @@ nouveau-y += core/subdev/fb/ramnvc0.o
 nouveau-y += core/subdev/fb/ramnve0.o
 nouveau-y += core/subdev/fb/ramgk20a.o
 nouveau-y += core/subdev/fb/ramgm107.o
+nouveau-y += core/subdev/fb/sddr2.o
 nouveau-y += core/subdev/fb/sddr3.o
 nouveau-y += core/subdev/fb/gddr5.o
+nouveau-y += core/subdev/fuse/base.o
+nouveau-y += core/subdev/fuse/g80.o
+nouveau-y += core/subdev/fuse/gf100.o
+nouveau-y += core/subdev/fuse/gm107.o
 nouveau-y += core/subdev/gpio/base.o
 nouveau-y += core/subdev/gpio/nv10.o
 nouveau-y += core/subdev/gpio/nv50.o
-nouveau-y += core/subdev/gpio/nv92.o
+nouveau-y += core/subdev/gpio/nv94.o
 nouveau-y += core/subdev/gpio/nvd0.o
 nouveau-y += core/subdev/gpio/nve0.o
 nouveau-y += core/subdev/i2c/base.o
@@ -190,6 +198,7 @@ nouveau-y += core/subdev/therm/nv50.o
 nouveau-y += core/subdev/therm/nv84.o
 nouveau-y += core/subdev/therm/nva3.o
 nouveau-y += core/subdev/therm/nvd0.o
+nouveau-y += core/subdev/therm/gm107.o
 nouveau-y += core/subdev/timer/base.o
 nouveau-y += core/subdev/timer/nv04.o
 nouveau-y += core/subdev/timer/gk20a.o
@@ -252,6 +261,7 @@ nouveau-y += core/engine/disp/hdanvd0.o
 nouveau-y += core/engine/disp/hdminv84.o
 nouveau-y += core/engine/disp/hdminva3.o
 nouveau-y += core/engine/disp/hdminvd0.o
+nouveau-y += core/engine/disp/hdminve0.o
 nouveau-y += core/engine/disp/piornv50.o
 nouveau-y += core/engine/disp/sornv50.o
 nouveau-y += core/engine/disp/sornv94.o
diff --git a/drivers/gpu/drm/nouveau/core/core/client.c b/drivers/gpu/drm/nouveau/core/core/client.c
index 68bf06768123..e962433294c3 100644
--- a/drivers/gpu/drm/nouveau/core/core/client.c
+++ b/drivers/gpu/drm/nouveau/core/core/client.c
@@ -91,9 +91,10 @@ nvkm_client_notify_del(struct nouveau_client *client, int index)
 }
 
 int
-nvkm_client_notify_new(struct nouveau_client *client,
+nvkm_client_notify_new(struct nouveau_object *object,
 		       struct nvkm_event *event, void *data, u32 size)
 {
+	struct nouveau_client *client = nouveau_client(object);
 	struct nvkm_client_notify *notify;
 	union {
 		struct nvif_notify_req_v0 v0;
@@ -127,8 +128,8 @@ nvkm_client_notify_new(struct nouveau_client *client,
 	}
 
 	if (ret == 0) {
-		ret = nvkm_notify_init(event, nvkm_client_notify, false,
-				       data, size, reply, &notify->n);
+		ret = nvkm_notify_init(object, event, nvkm_client_notify,
+				       false, data, size, reply, &notify->n);
 		if (ret == 0) {
 			client->notify[index] = notify;
 			notify->client = client;
diff --git a/drivers/gpu/drm/nouveau/core/core/event.c b/drivers/gpu/drm/nouveau/core/core/event.c
index 0540a48c5678..ff2b434b3db4 100644
--- a/drivers/gpu/drm/nouveau/core/core/event.c
+++ b/drivers/gpu/drm/nouveau/core/core/event.c
@@ -20,7 +20,7 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#include <core/os.h>
+#include <core/object.h>
 #include <core/event.h>
 
 void
diff --git a/drivers/gpu/drm/nouveau/core/core/gpuobj.c b/drivers/gpu/drm/nouveau/core/core/gpuobj.c
index 560b2214cf1c..daee87702502 100644
--- a/drivers/gpu/drm/nouveau/core/core/gpuobj.c
+++ b/drivers/gpu/drm/nouveau/core/core/gpuobj.c
@@ -115,7 +115,7 @@ nouveau_gpuobj_create_(struct nouveau_object *parent,
 	gpuobj->size = size;
 
 	if (heap) {
-		ret = nouveau_mm_head(heap, 1, size, size,
+		ret = nouveau_mm_head(heap, 0, 1, size, size,
 				      max(align, (u32)1), &gpuobj->node);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/nouveau/core/core/ioctl.c b/drivers/gpu/drm/nouveau/core/core/ioctl.c
index f7e19bfb489c..692aa92dd850 100644
--- a/drivers/gpu/drm/nouveau/core/core/ioctl.c
+++ b/drivers/gpu/drm/nouveau/core/core/ioctl.c
@@ -349,7 +349,6 @@ nvkm_ioctl_unmap(struct nouveau_handle *handle, void *data, u32 size)
 static int
 nvkm_ioctl_ntfy_new(struct nouveau_handle *handle, void *data, u32 size)
 {
-	struct nouveau_client *client = nouveau_client(handle->object);
 	struct nouveau_object *object = handle->object;
 	struct nouveau_ofuncs *ofuncs = object->oclass->ofuncs;
 	union {
@@ -365,7 +364,7 @@ nvkm_ioctl_ntfy_new(struct nouveau_handle *handle, void *data, u32 size)
 		if (ret = -ENODEV, ofuncs->ntfy)
 			ret = ofuncs->ntfy(object, args->v0.event, &event);
 		if (ret == 0) {
-			ret = nvkm_client_notify_new(client, event, data, size);
+			ret = nvkm_client_notify_new(object, event, data, size);
 			if (ret >= 0) {
 				args->v0.index = ret;
 				ret = 0;
diff --git a/drivers/gpu/drm/nouveau/core/core/mm.c b/drivers/gpu/drm/nouveau/core/core/mm.c
index 7a4e0891c5f8..b4f5db66d5b5 100644
--- a/drivers/gpu/drm/nouveau/core/core/mm.c
+++ b/drivers/gpu/drm/nouveau/core/core/mm.c
@@ -28,6 +28,24 @@
 #define node(root, dir) ((root)->nl_entry.dir == &mm->nodes) ? NULL : \
 	list_entry((root)->nl_entry.dir, struct nouveau_mm_node, nl_entry)
 
+static void
+nouveau_mm_dump(struct nouveau_mm *mm, const char *header)
+{
+	struct nouveau_mm_node *node;
+
+	printk(KERN_ERR "nouveau: %s\n", header);
+	printk(KERN_ERR "nouveau: node list:\n");
+	list_for_each_entry(node, &mm->nodes, nl_entry) {
+		printk(KERN_ERR "nouveau: \t%08x %08x %d\n",
+		       node->offset, node->length, node->type);
+	}
+	printk(KERN_ERR "nouveau: free list:\n");
+	list_for_each_entry(node, &mm->free, fl_entry) {
+		printk(KERN_ERR "nouveau: \t%08x %08x %d\n",
+		       node->offset, node->length, node->type);
+	}
+}
+
 void
 nouveau_mm_free(struct nouveau_mm *mm, struct nouveau_mm_node **pthis)
 {
@@ -37,29 +55,29 @@ nouveau_mm_free(struct nouveau_mm *mm, struct nouveau_mm_node **pthis)
 		struct nouveau_mm_node *prev = node(this, prev);
 		struct nouveau_mm_node *next = node(this, next);
 
-		if (prev && prev->type == 0) {
+		if (prev && prev->type == NVKM_MM_TYPE_NONE) {
 			prev->length += this->length;
 			list_del(&this->nl_entry);
 			kfree(this); this = prev;
 		}
 
-		if (next && next->type == 0) {
+		if (next && next->type == NVKM_MM_TYPE_NONE) {
 			next->offset  = this->offset;
 			next->length += this->length;
-			if (this->type == 0)
+			if (this->type == NVKM_MM_TYPE_NONE)
 				list_del(&this->fl_entry);
 			list_del(&this->nl_entry);
 			kfree(this); this = NULL;
 		}
 
-		if (this && this->type != 0) {
+		if (this && this->type != NVKM_MM_TYPE_NONE) {
 			list_for_each_entry(prev, &mm->free, fl_entry) {
 				if (this->offset < prev->offset)
 					break;
 			}
 
 			list_add_tail(&this->fl_entry, &prev->fl_entry);
-			this->type = 0;
+			this->type = NVKM_MM_TYPE_NONE;
 		}
 	}
 
@@ -80,27 +98,32 @@ region_head(struct nouveau_mm *mm, struct nouveau_mm_node *a, u32 size)
 
 	b->offset = a->offset;
 	b->length = size;
+	b->heap   = a->heap;
 	b->type   = a->type;
 	a->offset += size;
 	a->length -= size;
 	list_add_tail(&b->nl_entry, &a->nl_entry);
-	if (b->type == 0)
+	if (b->type == NVKM_MM_TYPE_NONE)
 		list_add_tail(&b->fl_entry, &a->fl_entry);
 	return b;
 }
 
 int
-nouveau_mm_head(struct nouveau_mm *mm, u8 type, u32 size_max, u32 size_min,
-		u32 align, struct nouveau_mm_node **pnode)
+nouveau_mm_head(struct nouveau_mm *mm, u8 heap, u8 type, u32 size_max,
+		u32 size_min, u32 align, struct nouveau_mm_node **pnode)
 {
 	struct nouveau_mm_node *prev, *this, *next;
 	u32 mask = align - 1;
 	u32 splitoff;
 	u32 s, e;
 
-	BUG_ON(!type);
+	BUG_ON(type == NVKM_MM_TYPE_NONE || type == NVKM_MM_TYPE_HOLE);
 
 	list_for_each_entry(this, &mm->free, fl_entry) {
+		if (unlikely(heap != NVKM_MM_HEAP_ANY)) {
+			if (this->heap != heap)
+				continue;
+		}
 		e = this->offset + this->length;
 		s = this->offset;
 
@@ -149,27 +172,32 @@ region_tail(struct nouveau_mm *mm, struct nouveau_mm_node *a, u32 size)
 	a->length -= size;
 	b->offset  = a->offset + a->length;
 	b->length  = size;
+	b->heap    = a->heap;
 	b->type    = a->type;
 
 	list_add(&b->nl_entry, &a->nl_entry);
-	if (b->type == 0)
+	if (b->type == NVKM_MM_TYPE_NONE)
 		list_add(&b->fl_entry, &a->fl_entry);
 	return b;
 }
 
 int
-nouveau_mm_tail(struct nouveau_mm *mm, u8 type, u32 size_max, u32 size_min,
-		u32 align, struct nouveau_mm_node **pnode)
+nouveau_mm_tail(struct nouveau_mm *mm, u8 heap, u8 type, u32 size_max,
+		u32 size_min, u32 align, struct nouveau_mm_node **pnode)
 {
 	struct nouveau_mm_node *prev, *this, *next;
 	u32 mask = align - 1;
 
-	BUG_ON(!type);
+	BUG_ON(type == NVKM_MM_TYPE_NONE || type == NVKM_MM_TYPE_HOLE);
 
 	list_for_each_entry_reverse(this, &mm->free, fl_entry) {
 		u32 e = this->offset + this->length;
 		u32 s = this->offset;
 		u32 c = 0, a;
+		if (unlikely(heap != NVKM_MM_HEAP_ANY)) {
+			if (this->heap != heap)
+				continue;
+		}
 
 		prev = node(this, prev);
 		if (prev && prev->type != type)
@@ -209,9 +237,23 @@ nouveau_mm_tail(struct nouveau_mm *mm, u8 type, u32 size_max, u32 size_min,
 int
 nouveau_mm_init(struct nouveau_mm *mm, u32 offset, u32 length, u32 block)
 {
-	struct nouveau_mm_node *node;
+	struct nouveau_mm_node *node, *prev;
+	u32 next;
 
-	if (block) {
+	if (nouveau_mm_initialised(mm)) {
+		prev = list_last_entry(&mm->nodes, typeof(*node), nl_entry);
+		next = prev->offset + prev->length;
+		if (next != offset) {
+			BUG_ON(next > offset);
+			if (!(node = kzalloc(sizeof(*node), GFP_KERNEL)))
+				return -ENOMEM;
+			node->type   = NVKM_MM_TYPE_HOLE;
+			node->offset = next;
+			node->length = offset - next;
+			list_add_tail(&node->nl_entry, &mm->nodes);
+		}
+		BUG_ON(block != mm->block_size);
+	} else {
 		INIT_LIST_HEAD(&mm->nodes);
 		INIT_LIST_HEAD(&mm->free);
 		mm->block_size = block;
@@ -230,25 +272,32 @@ nouveau_mm_init(struct nouveau_mm *mm, u32 offset, u32 length, u32 block)
 
 	list_add_tail(&node->nl_entry, &mm->nodes);
 	list_add_tail(&node->fl_entry, &mm->free);
-	mm->heap_nodes++;
+	node->heap = ++mm->heap_nodes;
 	return 0;
 }
 
 int
 nouveau_mm_fini(struct nouveau_mm *mm)
 {
-	if (nouveau_mm_initialised(mm)) {
-		struct nouveau_mm_node *node, *heap =
-			list_first_entry(&mm->nodes, typeof(*heap), nl_entry);
-		int nodes = 0;
+	struct nouveau_mm_node *node, *temp;
+	int nodes = 0;
 
-		list_for_each_entry(node, &mm->nodes, nl_entry) {
-			if (WARN_ON(nodes++ == mm->heap_nodes))
+	if (!nouveau_mm_initialised(mm))
+		return 0;
+
+	list_for_each_entry(node, &mm->nodes, nl_entry) {
+		if (node->type != NVKM_MM_TYPE_HOLE) {
+			if (++nodes > mm->heap_nodes) {
+				nouveau_mm_dump(mm, "mm not clean!");
 				return -EBUSY;
+			}
 		}
-
-		kfree(heap);
 	}
 
+	list_for_each_entry_safe(node, temp, &mm->nodes, nl_entry) {
+		list_del(&node->nl_entry);
+		kfree(node);
+	}
+	mm->heap_nodes = 0;
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/core/notify.c b/drivers/gpu/drm/nouveau/core/core/notify.c
index 76adb81bdea2..d1bcde55e9d7 100644
--- a/drivers/gpu/drm/nouveau/core/core/notify.c
+++ b/drivers/gpu/drm/nouveau/core/core/notify.c
@@ -134,14 +134,15 @@ nvkm_notify_fini(struct nvkm_notify *notify)
 }
 
 int
-nvkm_notify_init(struct nvkm_event *event, int (*func)(struct nvkm_notify *),
-		 bool work, void *data, u32 size, u32 reply,
+nvkm_notify_init(struct nouveau_object *object, struct nvkm_event *event,
+		 int (*func)(struct nvkm_notify *), bool work,
+		 void *data, u32 size, u32 reply,
 		 struct nvkm_notify *notify)
 {
 	unsigned long flags;
 	int ret = -ENODEV;
 	if ((notify->event = event), event->refs) {
-		ret = event->func->ctor(data, size, notify);
+		ret = event->func->ctor(object, data, size, notify);
 		if (ret == 0 && (ret = -EINVAL, notify->size == reply)) {
 			notify->flags = 0;
 			notify->block = 1;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/base.c b/drivers/gpu/drm/nouveau/core/engine/device/base.c
index 8928f7981d4a..0ef5a5713182 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/base.c
@@ -505,7 +505,8 @@ nouveau_device_sclass[] = {
 };
 
 static int
-nouveau_device_event_ctor(void *data, u32 size, struct nvkm_notify *notify)
+nouveau_device_event_ctor(struct nouveau_object *object, void *data, u32 size,
+			  struct nvkm_notify *notify)
 {
 	if (!WARN_ON(size != 0)) {
 		notify->size  = 0;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/gm100.c b/drivers/gpu/drm/nouveau/core/engine/device/gm100.c
index 377ec0b8851e..6295668e29a5 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/gm100.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/gm100.c
@@ -26,6 +26,7 @@
 #include <subdev/bus.h>
 #include <subdev/gpio.h>
 #include <subdev/i2c.h>
+#include <subdev/fuse.h>
 #include <subdev/clock.h>
 #include <subdev/therm.h>
 #include <subdev/mxm.h>
@@ -62,10 +63,9 @@ gm100_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gm107_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
-#if 0
-		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
-#endif
+		device->oclass[NVDEV_SUBDEV_THERM  ] = &gm107_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  gm107_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  gk20a_mc_oclass;
@@ -77,8 +77,9 @@ gm100_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_INSTMEM] =  nv50_instmem_oclass;
 		device->oclass[NVDEV_SUBDEV_VM     ] = &nvc0_vmmgr_oclass;
 		device->oclass[NVDEV_SUBDEV_BAR    ] = &nvc0_bar_oclass;
-#if 0
 		device->oclass[NVDEV_SUBDEV_PWR    ] =  nv108_pwr_oclass;
+
+#if 0
 		device->oclass[NVDEV_SUBDEV_VOLT   ] = &nv40_volt_oclass;
 #endif
 		device->oclass[NVDEV_ENGINE_DMAOBJ ] =  nvd0_dmaeng_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nv50.c b/drivers/gpu/drm/nouveau/core/engine/device/nv50.c
index 932f84fae459..96f568d1321b 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nv50.c
@@ -26,6 +26,7 @@
 #include <subdev/bus.h>
 #include <subdev/gpio.h>
 #include <subdev/i2c.h>
+#include <subdev/fuse.h>
 #include <subdev/clock.h>
 #include <subdev/therm.h>
 #include <subdev/mxm.h>
@@ -62,6 +63,7 @@ nv50_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv50_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv50_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv50_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv50_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -87,6 +89,7 @@ nv50_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv50_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv50_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -115,6 +118,7 @@ nv50_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv50_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv50_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -141,8 +145,9 @@ nv50_identify(struct nouveau_device *device)
 	case 0x92:
 		device->cname = "G92";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv50_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv50_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -169,8 +174,9 @@ nv50_identify(struct nouveau_device *device)
 	case 0x94:
 		device->cname = "G94";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -197,8 +203,9 @@ nv50_identify(struct nouveau_device *device)
 	case 0x96:
 		device->cname = "G96";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -225,8 +232,9 @@ nv50_identify(struct nouveau_device *device)
 	case 0x98:
 		device->cname = "G98";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -253,8 +261,9 @@ nv50_identify(struct nouveau_device *device)
 	case 0xa0:
 		device->cname = "G200";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv50_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -281,8 +290,9 @@ nv50_identify(struct nouveau_device *device)
 	case 0xaa:
 		device->cname = "MCP77/MCP78";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nvaa_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -309,8 +319,9 @@ nv50_identify(struct nouveau_device *device)
 	case 0xac:
 		device->cname = "MCP79/MCP7A";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nvaa_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -337,8 +348,9 @@ nv50_identify(struct nouveau_device *device)
 	case 0xa3:
 		device->cname = "GT215";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nva3_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -367,8 +379,9 @@ nv50_identify(struct nouveau_device *device)
 	case 0xa5:
 		device->cname = "GT216";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nva3_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -396,8 +409,9 @@ nv50_identify(struct nouveau_device *device)
 	case 0xa8:
 		device->cname = "GT218";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nva3_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -425,8 +439,9 @@ nv50_identify(struct nouveau_device *device)
 	case 0xaf:
 		device->cname = "MCP89";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] =  &g80_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nva3_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
index b4a2917ce555..cd05677ad4b7 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
@@ -26,6 +26,7 @@
 #include <subdev/bus.h>
 #include <subdev/gpio.h>
 #include <subdev/i2c.h>
+#include <subdev/fuse.h>
 #include <subdev/clock.h>
 #include <subdev/therm.h>
 #include <subdev/mxm.h>
@@ -60,8 +61,9 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xc0:
 		device->cname = "GF100";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -92,8 +94,9 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xc4:
 		device->cname = "GF104";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -124,8 +127,9 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xc3:
 		device->cname = "GF106";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -155,8 +159,9 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xce:
 		device->cname = "GF114";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -187,8 +192,9 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xcf:
 		device->cname = "GF116";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -219,8 +225,9 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xc1:
 		device->cname = "GF108";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -250,8 +257,9 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xc8:
 		device->cname = "GF110";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv94_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -284,6 +292,7 @@ nvc0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nvd0_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -315,6 +324,7 @@ nvc0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nvd0_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  gf117_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nve0.c b/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
index cdf9147f32a1..b1b2e484ecfa 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
@@ -26,6 +26,7 @@
 #include <subdev/bus.h>
 #include <subdev/gpio.h>
 #include <subdev/i2c.h>
+#include <subdev/fuse.h>
 #include <subdev/clock.h>
 #include <subdev/therm.h>
 #include <subdev/mxm.h>
@@ -62,6 +63,7 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -95,6 +97,7 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -128,6 +131,7 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -161,6 +165,7 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &gk20a_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  gk20a_mc_oclass;
 		device->oclass[NVDEV_SUBDEV_BUS    ] =  nvc0_bus_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_TIMER  ] = &gk20a_timer_oclass;
 		device->oclass[NVDEV_SUBDEV_FB     ] =  gk20a_fb_oclass;
 		device->oclass[NVDEV_SUBDEV_LTC    ] =  gk104_ltc_oclass;
@@ -180,6 +185,7 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -213,6 +219,7 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -246,6 +253,7 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
 		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
 		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gf100_fuse_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/base.c b/drivers/gpu/drm/nouveau/core/engine/disp/base.c
index 22d55f6cde50..64b84667f3a5 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/base.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/base.c
@@ -32,7 +32,8 @@
 #include "conn.h"
 
 int
-nouveau_disp_vblank_ctor(void *data, u32 size, struct nvkm_notify *notify)
+nouveau_disp_vblank_ctor(struct nouveau_object *object, void *data, u32 size,
+			 struct nvkm_notify *notify)
 {
 	struct nouveau_disp *disp =
 		container_of(notify->event, typeof(*disp), vblank);
@@ -61,7 +62,8 @@ nouveau_disp_vblank(struct nouveau_disp *disp, int head)
 }
 
 static int
-nouveau_disp_hpd_ctor(void *data, u32 size, struct nvkm_notify *notify)
+nouveau_disp_hpd_ctor(struct nouveau_object *object, void *data, u32 size,
+		      struct nvkm_notify *notify)
 {
 	struct nouveau_disp *disp =
 		container_of(notify->event, typeof(*disp), hpd);
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/conn.c b/drivers/gpu/drm/nouveau/core/engine/disp/conn.c
index 3d1070228977..1496b567dd4a 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/conn.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/conn.c
@@ -126,8 +126,8 @@ nvkm_connector_create_(struct nouveau_object *parent,
 			return 0;
 		}
 
-		ret = nvkm_notify_init(&gpio->event, nvkm_connector_hpd, true,
-				       &(struct nvkm_gpio_ntfy_req) {
+		ret = nvkm_notify_init(NULL, &gpio->event, nvkm_connector_hpd,
+				       true, &(struct nvkm_gpio_ntfy_req) {
 					.mask = NVKM_GPIO_TOGGLED,
 					.line = func.line,
 				       },
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/gm107.c b/drivers/gpu/drm/nouveau/core/engine/disp/gm107.c
index d54da8b5f87e..b3df3fe2dc09 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/gm107.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/gm107.c
@@ -68,6 +68,10 @@ gm107_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	ret = nvkm_event_init(&nvd0_disp_chan_uevent, 1, 17, &priv->uevent);
+	if (ret)
+		return ret;
+
 	nv_engine(priv)->sclass = gm107_disp_base_oclass;
 	nv_engine(priv)->cclass = &nv50_disp_cclass;
 	nv_subdev(priv)->intr = nvd0_disp_intr;
@@ -80,7 +84,7 @@ gm107_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->dac.sense = nv50_dac_sense;
 	priv->sor.power = nv50_sor_power;
 	priv->sor.hda_eld = nvd0_hda_eld;
-	priv->sor.hdmi = nvd0_hdmi_ctrl;
+	priv->sor.hdmi = nve0_hdmi_ctrl;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
index 8b4e06abe533..fe9ef5894dd4 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
@@ -26,6 +26,8 @@
 #include <nvif/unpack.h>
 #include <nvif/class.h>
 
+#include <subdev/timer.h>
+
 #include "nv50.h"
 
 int
@@ -46,16 +48,21 @@ nva3_hda_eld(NV50_DISP_MTHD_V1)
 		return ret;
 
 	if (size && args->v0.data[0]) {
+		if (outp->info.type == DCB_OUTPUT_DP) {
+			nv_mask(priv, 0x61c1e0 + soff, 0x8000000d, 0x80000001);
+			nv_wait(priv, 0x61c1e0 + soff, 0x80000000, 0x00000000);
+		}
 		for (i = 0; i < size; i++)
 			nv_wr32(priv, 0x61c440 + soff, (i << 8) | args->v0.data[0]);
 		for (; i < 0x60; i++)
 			nv_wr32(priv, 0x61c440 + soff, (i << 8));
 		nv_mask(priv, 0x61c448 + soff, 0x80000003, 0x80000003);
-	} else
-	if (size) {
-		nv_mask(priv, 0x61c448 + soff, 0x80000003, 0x80000001);
 	} else {
-		nv_mask(priv, 0x61c448 + soff, 0x80000003, 0x80000000);
+		if (outp->info.type == DCB_OUTPUT_DP) {
+			nv_mask(priv, 0x61c1e0 + soff, 0x80000001, 0x80000000);
+			nv_wait(priv, 0x61c1e0 + soff, 0x80000000, 0x00000000);
+		}
+		nv_mask(priv, 0x61c448 + soff, 0x80000003, 0x80000000 | !!size);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
index baf558fc12fb..1d4e8432d857 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
@@ -26,10 +26,7 @@
 #include <nvif/unpack.h>
 #include <nvif/class.h>
 
-#include <subdev/bios.h>
-#include <subdev/bios/dcb.h>
-#include <subdev/bios/dp.h>
-#include <subdev/bios/init.h>
+#include <subdev/timer.h>
 
 #include "nv50.h"
 
@@ -40,6 +37,7 @@ nvd0_hda_eld(NV50_DISP_MTHD_V1)
 		struct nv50_disp_sor_hda_eld_v0 v0;
 	} *args = data;
 	const u32 soff = outp->or * 0x030;
+	const u32 hoff = head * 0x800;
 	int ret, i;
 
 	nv_ioctl(object, "disp sor hda eld size %d\n", size);
@@ -51,16 +49,22 @@ nvd0_hda_eld(NV50_DISP_MTHD_V1)
 		return ret;
 
 	if (size && args->v0.data[0]) {
+		if (outp->info.type == DCB_OUTPUT_DP) {
+			nv_mask(priv, 0x616618 + hoff, 0x8000000c, 0x80000001);
+			nv_wait(priv, 0x616618 + hoff, 0x80000000, 0x00000000);
+		}
+		nv_mask(priv, 0x616548 + hoff, 0x00000070, 0x00000000);
 		for (i = 0; i < size; i++)
 			nv_wr32(priv, 0x10ec00 + soff, (i << 8) | args->v0.data[i]);
 		for (; i < 0x60; i++)
 			nv_wr32(priv, 0x10ec00 + soff, (i << 8));
 		nv_mask(priv, 0x10ec10 + soff, 0x80000003, 0x80000003);
-	} else
-	if (size) {
-		nv_mask(priv, 0x10ec10 + soff, 0x80000003, 0x80000001);
 	} else {
-		nv_mask(priv, 0x10ec10 + soff, 0x80000003, 0x80000000);
+		if (outp->info.type == DCB_OUTPUT_DP) {
+			nv_mask(priv, 0x616618 + hoff, 0x80000001, 0x80000000);
+			nv_wait(priv, 0x616618 + hoff, 0x80000000, 0x00000000);
+		}
+		nv_mask(priv, 0x10ec10 + soff, 0x80000003, 0x80000000 | !!size);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdminvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdminvd0.c
index 3106d295b48d..bac4fc4570f0 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/hdminvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdminvd0.c
@@ -75,8 +75,5 @@ nvd0_hdmi_ctrl(NV50_DISP_MTHD_V1)
 
 	/* HDMI_CTRL */
 	nv_mask(priv, 0x616798 + hoff, 0x401f007f, ctrl);
-
-	/* NFI, audio doesn't work without it though.. */
-	nv_mask(priv, 0x616548 + hoff, 0x00000070, 0x00000000);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdminve0.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdminve0.c
new file mode 100644
index 000000000000..528d14ec2f7f
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdminve0.c
@@ -0,0 +1,83 @@
+/*
+ * Copyright 2014 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include <core/client.h>
+#include <nvif/unpack.h>
+#include <nvif/class.h>
+
+#include "nv50.h"
+
+int
+nve0_hdmi_ctrl(NV50_DISP_MTHD_V1)
+{
+	const u32 hoff = (head * 0x800);
+	const u32 hdmi = (head * 0x400);
+	union {
+		struct nv50_disp_sor_hdmi_pwr_v0 v0;
+	} *args = data;
+	u32 ctrl;
+	int ret;
+
+	nv_ioctl(object, "disp sor hdmi ctrl size %d\n", size);
+	if (nvif_unpack(args->v0, 0, 0, false)) {
+		nv_ioctl(object, "disp sor hdmi ctrl vers %d state %d "
+				 "max_ac_packet %d rekey %d\n",
+			 args->v0.version, args->v0.state,
+			 args->v0.max_ac_packet, args->v0.rekey);
+		if (args->v0.max_ac_packet > 0x1f || args->v0.rekey > 0x7f)
+			return -EINVAL;
+		ctrl  = 0x40000000 * !!args->v0.state;
+		ctrl |= args->v0.max_ac_packet << 16;
+		ctrl |= args->v0.rekey;
+	} else
+		return ret;
+
+	if (!(ctrl & 0x40000000)) {
+		nv_mask(priv, 0x616798 + hoff, 0x40000000, 0x00000000);
+		nv_mask(priv, 0x6900c0 + hdmi, 0x00000001, 0x00000000);
+		nv_mask(priv, 0x690000 + hdmi, 0x00000001, 0x00000000);
+		return 0;
+	}
+
+	/* AVI InfoFrame */
+	nv_mask(priv, 0x690000 + hdmi, 0x00000001, 0x00000000);
+	nv_wr32(priv, 0x690008 + hdmi, 0x000d0282);
+	nv_wr32(priv, 0x69000c + hdmi, 0x0000006f);
+	nv_wr32(priv, 0x690010 + hdmi, 0x00000000);
+	nv_wr32(priv, 0x690014 + hdmi, 0x00000000);
+	nv_wr32(priv, 0x690018 + hdmi, 0x00000000);
+	nv_mask(priv, 0x690000 + hdmi, 0x00000001, 0x00000001);
+
+	/* ??? InfoFrame? */
+	nv_mask(priv, 0x6900c0 + hdmi, 0x00000001, 0x00000000);
+	nv_wr32(priv, 0x6900cc + hdmi, 0x00000010);
+	nv_mask(priv, 0x6900c0 + hdmi, 0x00000001, 0x00000001);
+
+	/* ??? */
+	nv_wr32(priv, 0x690080 + hdmi, 0x82000000);
+
+	/* HDMI_CTRL */
+	nv_mask(priv, 0x616798 + hoff, 0x401f007f, ctrl);
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
index f8cbb512132f..2df3a937037d 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
@@ -29,6 +29,7 @@
 #include <core/enum.h>
 #include <nvif/unpack.h>
 #include <nvif/class.h>
+#include <nvif/event.h>
 
 #include <subdev/bios.h>
 #include <subdev/bios/dcb.h>
@@ -82,6 +83,71 @@ nv50_disp_chan_destroy(struct nv50_disp_chan *chan)
 	nouveau_namedb_destroy(&chan->base);
 }
 
+static void
+nv50_disp_chan_uevent_fini(struct nvkm_event *event, int type, int index)
+{
+	struct nv50_disp_priv *priv = container_of(event, typeof(*priv), uevent);
+	nv_mask(priv, 0x610028, 0x00000001 << index, 0x00000000 << index);
+}
+
+static void
+nv50_disp_chan_uevent_init(struct nvkm_event *event, int types, int index)
+{
+	struct nv50_disp_priv *priv = container_of(event, typeof(*priv), uevent);
+	nv_mask(priv, 0x610028, 0x00000001 << index, 0x00000001 << index);
+}
+
+void
+nv50_disp_chan_uevent_send(struct nv50_disp_priv *priv, int chid)
+{
+	struct nvif_notify_uevent_rep {
+	} rep;
+
+	nvkm_event_send(&priv->uevent, 1, chid, &rep, sizeof(rep));
+}
+
+int
+nv50_disp_chan_uevent_ctor(struct nouveau_object *object, void *data, u32 size,
+			   struct nvkm_notify *notify)
+{
+	struct nv50_disp_dmac *dmac = (void *)object;
+	union {
+		struct nvif_notify_uevent_req none;
+	} *args = data;
+	int ret;
+
+	if (nvif_unvers(args->none)) {
+		notify->size  = sizeof(struct nvif_notify_uevent_rep);
+		notify->types = 1;
+		notify->index = dmac->base.chid;
+		return 0;
+	}
+
+	return ret;
+}
+
+const struct nvkm_event_func
+nv50_disp_chan_uevent = {
+	.ctor = nv50_disp_chan_uevent_ctor,
+	.init = nv50_disp_chan_uevent_init,
+	.fini = nv50_disp_chan_uevent_fini,
+};
+
+int
+nv50_disp_chan_ntfy(struct nouveau_object *object, u32 type,
+		    struct nvkm_event **pevent)
+{
+	struct nv50_disp_priv *priv = (void *)object->engine;
+	switch (type) {
+	case NV50_DISP_CORE_CHANNEL_DMA_V0_NTFY_UEVENT:
+		*pevent = &priv->uevent;
+		return 0;
+	default:
+		break;
+	}
+	return -EINVAL;
+}
+
 int
 nv50_disp_chan_map(struct nouveau_object *object, u64 *addr, u32 *size)
 {
@@ -195,7 +261,7 @@ nv50_disp_dmac_init(struct nouveau_object *object)
 		return ret;
 
 	/* enable error reporting */
-	nv_mask(priv, 0x610028, 0x00010001 << chid, 0x00010001 << chid);
+	nv_mask(priv, 0x610028, 0x00010000 << chid, 0x00010000 << chid);
 
 	/* initialise channel for dma command submission */
 	nv_wr32(priv, 0x610204 + (chid * 0x0010), dmac->push);
@@ -232,7 +298,7 @@ nv50_disp_dmac_fini(struct nouveau_object *object, bool suspend)
 			return -EBUSY;
 	}
 
-	/* disable error reporting */
+	/* disable error reporting and completion notifications */
 	nv_mask(priv, 0x610028, 0x00010001 << chid, 0x00000000 << chid);
 
 	return nv50_disp_chan_fini(&dmac->base, suspend);
@@ -454,7 +520,7 @@ nv50_disp_mast_init(struct nouveau_object *object)
 		return ret;
 
 	/* enable error reporting */
-	nv_mask(priv, 0x610028, 0x00010001, 0x00010001);
+	nv_mask(priv, 0x610028, 0x00010000, 0x00010000);
 
 	/* attempt to unstick channel from some unknown state */
 	if ((nv_rd32(priv, 0x610200) & 0x009f0000) == 0x00020000)
@@ -494,7 +560,7 @@ nv50_disp_mast_fini(struct nouveau_object *object, bool suspend)
 			return -EBUSY;
 	}
 
-	/* disable error reporting */
+	/* disable error reporting and completion notifications */
 	nv_mask(priv, 0x610028, 0x00010001, 0x00000000);
 
 	return nv50_disp_chan_fini(&mast->base, suspend);
@@ -507,6 +573,7 @@ nv50_disp_mast_ofuncs = {
 	.base.init = nv50_disp_mast_init,
 	.base.fini = nv50_disp_mast_fini,
 	.base.map  = nv50_disp_chan_map,
+	.base.ntfy = nv50_disp_chan_ntfy,
 	.base.rd32 = nv50_disp_chan_rd32,
 	.base.wr32 = nv50_disp_chan_wr32,
 	.chid = 0,
@@ -607,6 +674,7 @@ nv50_disp_sync_ofuncs = {
 	.base.dtor = nv50_disp_dmac_dtor,
 	.base.init = nv50_disp_dmac_init,
 	.base.fini = nv50_disp_dmac_fini,
+	.base.ntfy = nv50_disp_chan_ntfy,
 	.base.map  = nv50_disp_chan_map,
 	.base.rd32 = nv50_disp_chan_rd32,
 	.base.wr32 = nv50_disp_chan_wr32,
@@ -696,6 +764,7 @@ nv50_disp_ovly_ofuncs = {
 	.base.dtor = nv50_disp_dmac_dtor,
 	.base.init = nv50_disp_dmac_init,
 	.base.fini = nv50_disp_dmac_fini,
+	.base.ntfy = nv50_disp_chan_ntfy,
 	.base.map  = nv50_disp_chan_map,
 	.base.rd32 = nv50_disp_chan_rd32,
 	.base.wr32 = nv50_disp_chan_wr32,
@@ -813,6 +882,7 @@ nv50_disp_oimm_ofuncs = {
 	.base.dtor = nv50_disp_pioc_dtor,
 	.base.init = nv50_disp_pioc_init,
 	.base.fini = nv50_disp_pioc_fini,
+	.base.ntfy = nv50_disp_chan_ntfy,
 	.base.map  = nv50_disp_chan_map,
 	.base.rd32 = nv50_disp_chan_rd32,
 	.base.wr32 = nv50_disp_chan_wr32,
@@ -860,6 +930,7 @@ nv50_disp_curs_ofuncs = {
 	.base.dtor = nv50_disp_pioc_dtor,
 	.base.init = nv50_disp_pioc_init,
 	.base.fini = nv50_disp_pioc_fini,
+	.base.ntfy = nv50_disp_chan_ntfy,
 	.base.map  = nv50_disp_chan_map,
 	.base.rd32 = nv50_disp_chan_rd32,
 	.base.wr32 = nv50_disp_chan_wr32,
@@ -1559,7 +1630,7 @@ nv50_disp_intr_unk20_1(struct nv50_disp_priv *priv, int head)
 }
 
 static void
-nv50_disp_intr_unk20_2_dp(struct nv50_disp_priv *priv,
+nv50_disp_intr_unk20_2_dp(struct nv50_disp_priv *priv, int head,
 			  struct dcb_output *outp, u32 pclk)
 {
 	const int link = !(outp->sorconf.link & 1);
@@ -1568,24 +1639,36 @@ nv50_disp_intr_unk20_2_dp(struct nv50_disp_priv *priv,
 	const u32 loff = (link * 0x080) + soff;
 	const u32 ctrl = nv_rd32(priv, 0x610794 + (or * 8));
 	const u32 symbol = 100000;
-	u32 dpctrl = nv_rd32(priv, 0x61c10c + loff) & 0x0000f0000;
+	const s32 vactive = nv_rd32(priv, 0x610af8 + (head * 0x540)) & 0xffff;
+	const s32 vblanke = nv_rd32(priv, 0x610ae8 + (head * 0x540)) & 0xffff;
+	const s32 vblanks = nv_rd32(priv, 0x610af0 + (head * 0x540)) & 0xffff;
+	u32 dpctrl = nv_rd32(priv, 0x61c10c + loff);
 	u32 clksor = nv_rd32(priv, 0x614300 + soff);
 	int bestTU = 0, bestVTUi = 0, bestVTUf = 0, bestVTUa = 0;
 	int TU, VTUi, VTUf, VTUa;
 	u64 link_data_rate, link_ratio, unk;
 	u32 best_diff = 64 * symbol;
 	u32 link_nr, link_bw, bits;
-
-	/* calculate packed data rate for each lane */
-	if      (dpctrl > 0x00030000) link_nr = 4;
-	else if (dpctrl > 0x00010000) link_nr = 2;
-	else			      link_nr = 1;
-
-	if (clksor & 0x000c0000)
-		link_bw = 270000;
-	else
-		link_bw = 162000;
-
+	u64 value;
+
+	link_bw = (clksor & 0x000c0000) ? 270000 : 162000;
+	link_nr = hweight32(dpctrl & 0x000f0000);
+
+	/* symbols/hblank - algorithm taken from comments in tegra driver */
+	value = vblanke + vactive - vblanks - 7;
+	value = value * link_bw;
+	do_div(value, pclk);
+	value = value - (3 * !!(dpctrl & 0x00004000)) - (12 / link_nr);
+	nv_mask(priv, 0x61c1e8 + soff, 0x0000ffff, value);
+
+	/* symbols/vblank - algorithm taken from comments in tegra driver */
+	value = vblanks - vblanke - 25;
+	value = value * link_bw;
+	do_div(value, pclk);
+	value = value - ((36 / link_nr) + 3) - 1;
+	nv_mask(priv, 0x61c1ec + soff, 0x00ffffff, value);
+
+	/* watermark / activesym */
 	if      ((ctrl & 0xf0000) == 0x60000) bits = 30;
 	else if ((ctrl & 0xf0000) == 0x50000) bits = 24;
 	else                                  bits = 18;
@@ -1731,7 +1814,7 @@ nv50_disp_intr_unk20_2(struct nv50_disp_priv *priv, int head)
 	} else
 	if (!outp->info.location) {
 		if (outp->info.type == DCB_OUTPUT_DP)
-			nv50_disp_intr_unk20_2_dp(priv, &outp->info, pclk);
+			nv50_disp_intr_unk20_2_dp(priv, head, &outp->info, pclk);
 		oreg = 0x614300 + (ffs(outp->info.or) - 1) * 0x800;
 		oval = (conf & 0x0100) ? 0x00000101 : 0x00000000;
 		hval = 0x00000000;
@@ -1847,6 +1930,12 @@ nv50_disp_intr(struct nouveau_subdev *subdev)
 		intr0 &= ~(0x00010000 << chid);
 	}
 
+	while (intr0 & 0x0000001f) {
+		u32 chid = __ffs(intr0 & 0x0000001f);
+		nv50_disp_chan_uevent_send(priv, chid);
+		intr0 &= ~(0x00000001 << chid);
+	}
+
 	if (intr1 & 0x00000004) {
 		nouveau_disp_vblank(&priv->base, 0);
 		nv_wr32(priv, 0x610024, 0x00000004);
@@ -1881,6 +1970,10 @@ nv50_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	ret = nvkm_event_init(&nv50_disp_chan_uevent, 1, 9, &priv->uevent);
+	if (ret)
+		return ret;
+
 	nv_engine(priv)->sclass = nv50_disp_base_oclass;
 	nv_engine(priv)->cclass = &nv50_disp_cclass;
 	nv_subdev(priv)->intr = nv50_disp_intr;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.h b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.h
index 8ab14461f70c..5279feefec06 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.h
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.h
@@ -26,6 +26,8 @@ struct nv50_disp_priv {
 	struct work_struct supervisor;
 	u32 super;
 
+	struct nvkm_event uevent;
+
 	struct {
 		int nr;
 	} head;
@@ -75,6 +77,7 @@ int nvd0_hda_eld(NV50_DISP_MTHD_V1);
 int nv84_hdmi_ctrl(NV50_DISP_MTHD_V1);
 int nva3_hdmi_ctrl(NV50_DISP_MTHD_V1);
 int nvd0_hdmi_ctrl(NV50_DISP_MTHD_V1);
+int nve0_hdmi_ctrl(NV50_DISP_MTHD_V1);
 
 int nv50_sor_power(NV50_DISP_MTHD_V1);
 
@@ -116,9 +119,16 @@ struct nv50_disp_chan {
 	int chid;
 };
 
+int  nv50_disp_chan_ntfy(struct nouveau_object *, u32, struct nvkm_event **);
 int  nv50_disp_chan_map(struct nouveau_object *, u64 *, u32 *);
 u32  nv50_disp_chan_rd32(struct nouveau_object *, u64);
 void nv50_disp_chan_wr32(struct nouveau_object *, u64, u32);
+extern const struct nvkm_event_func nv50_disp_chan_uevent;
+int  nv50_disp_chan_uevent_ctor(struct nouveau_object *, void *, u32,
+				struct nvkm_notify *);
+void nv50_disp_chan_uevent_send(struct nv50_disp_priv *, int);
+
+extern const struct nvkm_event_func nvd0_disp_chan_uevent;
 
 #define nv50_disp_chan_init(a)                                                 \
 	nouveau_namedb_init(&(a)->base)
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv84.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv84.c
index 788ced1b6182..d36284715b2a 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv84.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv84.c
@@ -236,6 +236,10 @@ nv84_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	ret = nvkm_event_init(&nv50_disp_chan_uevent, 1, 9, &priv->uevent);
+	if (ret)
+		return ret;
+
 	nv_engine(priv)->sclass = nv84_disp_base_oclass;
 	nv_engine(priv)->cclass = &nv50_disp_cclass;
 	nv_subdev(priv)->intr = nv50_disp_intr;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv94.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv94.c
index fa79de906eae..a117064002b1 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv94.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv94.c
@@ -95,6 +95,10 @@ nv94_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	ret = nvkm_event_init(&nv50_disp_chan_uevent, 1, 9, &priv->uevent);
+	if (ret)
+		return ret;
+
 	nv_engine(priv)->sclass = nv94_disp_base_oclass;
 	nv_engine(priv)->cclass = &nv50_disp_cclass;
 	nv_subdev(priv)->intr = nv50_disp_intr;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nva0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nva0.c
index 7af15f5d48dc..c67e68aadd45 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nva0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nva0.c
@@ -112,6 +112,10 @@ nva0_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	ret = nvkm_event_init(&nv50_disp_chan_uevent, 1, 9, &priv->uevent);
+	if (ret)
+		return ret;
+
 	nv_engine(priv)->sclass = nva0_disp_base_oclass;
 	nv_engine(priv)->cclass = &nv50_disp_cclass;
 	nv_subdev(priv)->intr = nv50_disp_intr;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nva3.c b/drivers/gpu/drm/nouveau/core/engine/disp/nva3.c
index 6bd39448f8da..22969f355aae 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nva3.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nva3.c
@@ -67,6 +67,10 @@ nva3_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	ret = nvkm_event_init(&nv50_disp_chan_uevent, 1, 9, &priv->uevent);
+	if (ret)
+		return ret;
+
 	nv_engine(priv)->sclass = nva3_disp_base_oclass;
 	nv_engine(priv)->cclass = &nv50_disp_cclass;
 	nv_subdev(priv)->intr = nv50_disp_intr;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
index a4bb3c774ee1..747e64bb9c06 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
@@ -43,6 +43,31 @@
 #include "nv50.h"
 
 /*******************************************************************************
+ * EVO channel base class
+ ******************************************************************************/
+
+static void
+nvd0_disp_chan_uevent_fini(struct nvkm_event *event, int type, int index)
+{
+	struct nv50_disp_priv *priv = container_of(event, typeof(*priv), uevent);
+	nv_mask(priv, 0x610090, 0x00000001 << index, 0x00000000 << index);
+}
+
+static void
+nvd0_disp_chan_uevent_init(struct nvkm_event *event, int types, int index)
+{
+	struct nv50_disp_priv *priv = container_of(event, typeof(*priv), uevent);
+	nv_mask(priv, 0x610090, 0x00000001 << index, 0x00000001 << index);
+}
+
+const struct nvkm_event_func
+nvd0_disp_chan_uevent = {
+	.ctor = nv50_disp_chan_uevent_ctor,
+	.init = nvd0_disp_chan_uevent_init,
+	.fini = nvd0_disp_chan_uevent_fini,
+};
+
+/*******************************************************************************
  * EVO DMA channel base class
  ******************************************************************************/
 
@@ -77,7 +102,6 @@ nvd0_disp_dmac_init(struct nouveau_object *object)
 		return ret;
 
 	/* enable error reporting */
-	nv_mask(priv, 0x610090, 0x00000001 << chid, 0x00000001 << chid);
 	nv_mask(priv, 0x6100a0, 0x00000001 << chid, 0x00000001 << chid);
 
 	/* initialise channel for dma command submission */
@@ -115,7 +139,7 @@ nvd0_disp_dmac_fini(struct nouveau_object *object, bool suspend)
 			return -EBUSY;
 	}
 
-	/* disable error reporting */
+	/* disable error reporting and completion notification */
 	nv_mask(priv, 0x610090, 0x00000001 << chid, 0x00000000);
 	nv_mask(priv, 0x6100a0, 0x00000001 << chid, 0x00000000);
 
@@ -278,7 +302,6 @@ nvd0_disp_mast_init(struct nouveau_object *object)
 		return ret;
 
 	/* enable error reporting */
-	nv_mask(priv, 0x610090, 0x00000001, 0x00000001);
 	nv_mask(priv, 0x6100a0, 0x00000001, 0x00000001);
 
 	/* initialise channel for dma command submission */
@@ -313,7 +336,7 @@ nvd0_disp_mast_fini(struct nouveau_object *object, bool suspend)
 			return -EBUSY;
 	}
 
-	/* disable error reporting */
+	/* disable error reporting and completion notification */
 	nv_mask(priv, 0x610090, 0x00000001, 0x00000000);
 	nv_mask(priv, 0x6100a0, 0x00000001, 0x00000000);
 
@@ -326,6 +349,7 @@ nvd0_disp_mast_ofuncs = {
 	.base.dtor = nv50_disp_dmac_dtor,
 	.base.init = nvd0_disp_mast_init,
 	.base.fini = nvd0_disp_mast_fini,
+	.base.ntfy = nv50_disp_chan_ntfy,
 	.base.map  = nv50_disp_chan_map,
 	.base.rd32 = nv50_disp_chan_rd32,
 	.base.wr32 = nv50_disp_chan_wr32,
@@ -419,6 +443,7 @@ nvd0_disp_sync_ofuncs = {
 	.base.dtor = nv50_disp_dmac_dtor,
 	.base.init = nvd0_disp_dmac_init,
 	.base.fini = nvd0_disp_dmac_fini,
+	.base.ntfy = nv50_disp_chan_ntfy,
 	.base.map  = nv50_disp_chan_map,
 	.base.rd32 = nv50_disp_chan_rd32,
 	.base.wr32 = nv50_disp_chan_wr32,
@@ -499,6 +524,7 @@ nvd0_disp_ovly_ofuncs = {
 	.base.dtor = nv50_disp_dmac_dtor,
 	.base.init = nvd0_disp_dmac_init,
 	.base.fini = nvd0_disp_dmac_fini,
+	.base.ntfy = nv50_disp_chan_ntfy,
 	.base.map  = nv50_disp_chan_map,
 	.base.rd32 = nv50_disp_chan_rd32,
 	.base.wr32 = nv50_disp_chan_wr32,
@@ -524,7 +550,6 @@ nvd0_disp_pioc_init(struct nouveau_object *object)
 		return ret;
 
 	/* enable error reporting */
-	nv_mask(priv, 0x610090, 0x00000001 << chid, 0x00000001 << chid);
 	nv_mask(priv, 0x6100a0, 0x00000001 << chid, 0x00000001 << chid);
 
 	/* activate channel */
@@ -553,7 +578,7 @@ nvd0_disp_pioc_fini(struct nouveau_object *object, bool suspend)
 			return -EBUSY;
 	}
 
-	/* disable error reporting */
+	/* disable error reporting and completion notification */
 	nv_mask(priv, 0x610090, 0x00000001 << chid, 0x00000000);
 	nv_mask(priv, 0x6100a0, 0x00000001 << chid, 0x00000000);
 
@@ -570,6 +595,7 @@ nvd0_disp_oimm_ofuncs = {
 	.base.dtor = nv50_disp_pioc_dtor,
 	.base.init = nvd0_disp_pioc_init,
 	.base.fini = nvd0_disp_pioc_fini,
+	.base.ntfy = nv50_disp_chan_ntfy,
 	.base.map  = nv50_disp_chan_map,
 	.base.rd32 = nv50_disp_chan_rd32,
 	.base.wr32 = nv50_disp_chan_wr32,
@@ -586,6 +612,7 @@ nvd0_disp_curs_ofuncs = {
 	.base.dtor = nv50_disp_pioc_dtor,
 	.base.init = nvd0_disp_pioc_init,
 	.base.fini = nvd0_disp_pioc_fini,
+	.base.ntfy = nv50_disp_chan_ntfy,
 	.base.map  = nv50_disp_chan_map,
 	.base.rd32 = nv50_disp_chan_rd32,
 	.base.wr32 = nv50_disp_chan_wr32,
@@ -949,6 +976,9 @@ nvd0_disp_intr_unk2_2_tu(struct nv50_disp_priv *priv, int head,
 	const int or = ffs(outp->or) - 1;
 	const u32 ctrl = nv_rd32(priv, 0x660200 + (or   * 0x020));
 	const u32 conf = nv_rd32(priv, 0x660404 + (head * 0x300));
+	const s32 vactive = nv_rd32(priv, 0x660414 + (head * 0x300)) & 0xffff;
+	const s32 vblanke = nv_rd32(priv, 0x66041c + (head * 0x300)) & 0xffff;
+	const s32 vblanks = nv_rd32(priv, 0x660420 + (head * 0x300)) & 0xffff;
 	const u32 pclk = nv_rd32(priv, 0x660450 + (head * 0x300)) / 1000;
 	const u32 link = ((ctrl & 0xf00) == 0x800) ? 0 : 1;
 	const u32 hoff = (head * 0x800);
@@ -956,23 +986,35 @@ nvd0_disp_intr_unk2_2_tu(struct nv50_disp_priv *priv, int head,
 	const u32 loff = (link * 0x080) + soff;
 	const u32 symbol = 100000;
 	const u32 TU = 64;
-	u32 dpctrl = nv_rd32(priv, 0x61c10c + loff) & 0x000f0000;
+	u32 dpctrl = nv_rd32(priv, 0x61c10c + loff);
 	u32 clksor = nv_rd32(priv, 0x612300 + soff);
 	u32 datarate, link_nr, link_bw, bits;
 	u64 ratio, value;
 
+	link_nr  = hweight32(dpctrl & 0x000f0000);
+	link_bw  = (clksor & 0x007c0000) >> 18;
+	link_bw *= 27000;
+
+	/* symbols/hblank - algorithm taken from comments in tegra driver */
+	value = vblanke + vactive - vblanks - 7;
+	value = value * link_bw;
+	do_div(value, pclk);
+	value = value - (3 * !!(dpctrl & 0x00004000)) - (12 / link_nr);
+	nv_mask(priv, 0x616620 + hoff, 0x0000ffff, value);
+
+	/* symbols/vblank - algorithm taken from comments in tegra driver */
+	value = vblanks - vblanke - 25;
+	value = value * link_bw;
+	do_div(value, pclk);
+	value = value - ((36 / link_nr) + 3) - 1;
+	nv_mask(priv, 0x616624 + hoff, 0x00ffffff, value);
+
+	/* watermark */
 	if      ((conf & 0x3c0) == 0x180) bits = 30;
 	else if ((conf & 0x3c0) == 0x140) bits = 24;
 	else                              bits = 18;
 	datarate = (pclk * bits) / 8;
 
-	if      (dpctrl > 0x00030000) link_nr = 4;
-	else if (dpctrl > 0x00010000) link_nr = 2;
-	else			      link_nr = 1;
-
-	link_bw  = (clksor & 0x007c0000) >> 18;
-	link_bw *= 27000;
-
 	ratio  = datarate;
 	ratio *= symbol;
 	do_div(ratio, link_nr * link_bw);
@@ -1153,7 +1195,11 @@ nvd0_disp_intr(struct nouveau_subdev *subdev)
 
 	if (intr & 0x00000001) {
 		u32 stat = nv_rd32(priv, 0x61008c);
-		nv_wr32(priv, 0x61008c, stat);
+		while (stat) {
+			int chid = __ffs(stat); stat &= ~(1 << chid);
+			nv50_disp_chan_uevent_send(priv, chid);
+			nv_wr32(priv, 0x61008c, 1 << chid);
+		}
 		intr &= ~0x00000001;
 	}
 
@@ -1209,6 +1255,10 @@ nvd0_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	ret = nvkm_event_init(&nvd0_disp_chan_uevent, 1, 17, &priv->uevent);
+	if (ret)
+		return ret;
+
 	nv_engine(priv)->sclass = nvd0_disp_base_oclass;
 	nv_engine(priv)->cclass = &nv50_disp_cclass;
 	nv_subdev(priv)->intr = nvd0_disp_intr;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nve0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nve0.c
index 47fef1e398c4..db144b2cf06b 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nve0.c
@@ -233,6 +233,10 @@ nve0_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	ret = nvkm_event_init(&nvd0_disp_chan_uevent, 1, 17, &priv->uevent);
+	if (ret)
+		return ret;
+
 	nv_engine(priv)->sclass = nve0_disp_base_oclass;
 	nv_engine(priv)->cclass = &nv50_disp_cclass;
 	nv_subdev(priv)->intr = nvd0_disp_intr;
@@ -245,7 +249,7 @@ nve0_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->dac.sense = nv50_dac_sense;
 	priv->sor.power = nv50_sor_power;
 	priv->sor.hda_eld = nvd0_hda_eld;
-	priv->sor.hdmi = nvd0_hdmi_ctrl;
+	priv->sor.hdmi = nve0_hdmi_ctrl;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nvf0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nvf0.c
index 04bda4ac4ed3..402d7d67d806 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nvf0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nvf0.c
@@ -68,6 +68,10 @@ nvf0_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	ret = nvkm_event_init(&nvd0_disp_chan_uevent, 1, 17, &priv->uevent);
+	if (ret)
+		return ret;
+
 	nv_engine(priv)->sclass = nvf0_disp_base_oclass;
 	nv_engine(priv)->cclass = &nv50_disp_cclass;
 	nv_subdev(priv)->intr = nvd0_disp_intr;
@@ -80,7 +84,7 @@ nvf0_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->dac.sense = nv50_dac_sense;
 	priv->sor.power = nv50_sor_power;
 	priv->sor.hda_eld = nvd0_hda_eld;
-	priv->sor.hdmi = nvd0_hdmi_ctrl;
+	priv->sor.hdmi = nve0_hdmi_ctrl;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/outpdp.c b/drivers/gpu/drm/nouveau/core/engine/disp/outpdp.c
index 6f6e2a898270..667a9070e006 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/outpdp.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/outpdp.c
@@ -254,7 +254,7 @@ nvkm_output_dp_create_(struct nouveau_object *parent,
 	atomic_set(&outp->lt.done, 0);
 
 	/* link maintenance */
-	ret = nvkm_notify_init(&i2c->event, nvkm_output_dp_irq, true,
+	ret = nvkm_notify_init(NULL, &i2c->event, nvkm_output_dp_irq, true,
 			       &(struct nvkm_i2c_ntfy_req) {
 				.mask = NVKM_I2C_IRQ,
 				.port = outp->base.edid->index,
@@ -268,7 +268,7 @@ nvkm_output_dp_create_(struct nouveau_object *parent,
 	}
 
 	/* hotplug detect, replaces gpio-based mechanism with aux events */
-	ret = nvkm_notify_init(&i2c->event, nvkm_output_dp_hpd, true,
+	ret = nvkm_notify_init(NULL, &i2c->event, nvkm_output_dp_hpd, true,
 			       &(struct nvkm_i2c_ntfy_req) {
 				.mask = NVKM_I2C_PLUG | NVKM_I2C_UNPLUG,
 				.port = outp->base.edid->index,
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/priv.h b/drivers/gpu/drm/nouveau/core/engine/disp/priv.h
index dbd43ae9df81..6a0511d54ce6 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/priv.h
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/priv.h
@@ -40,7 +40,8 @@ int  _nouveau_disp_fini(struct nouveau_object *, bool);
 extern struct nouveau_oclass *nvkm_output_oclass;
 extern struct nouveau_oclass *nvkm_connector_oclass;
 
-int  nouveau_disp_vblank_ctor(void *data, u32 size, struct nvkm_notify *);
+int  nouveau_disp_vblank_ctor(struct nouveau_object *, void *data, u32 size,
+			      struct nvkm_notify *);
 void nouveau_disp_vblank(struct nouveau_disp *, int head);
 int  nouveau_disp_ntfy(struct nouveau_object *, u32, struct nvkm_event **);
 
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/base.c b/drivers/gpu/drm/nouveau/core/engine/fifo/base.c
index 0f999fc45ab9..ac8375cf4eef 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/base.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/base.c
@@ -34,7 +34,8 @@
 #include <engine/fifo.h>
 
 static int
-nouveau_fifo_event_ctor(void *data, u32 size, struct nvkm_notify *notify)
+nouveau_fifo_event_ctor(struct nouveau_object *object, void *data, u32 size,
+			struct nvkm_notify *notify)
 {
 	if (size == 0) {
 		notify->size  = 0;
@@ -170,7 +171,8 @@ _nouveau_fifo_channel_wr32(struct nouveau_object *object, u64 addr, u32 data)
 }
 
 int
-nouveau_fifo_uevent_ctor(void *data, u32 size, struct nvkm_notify *notify)
+nouveau_fifo_uevent_ctor(struct nouveau_object *object, void *data, u32 size,
+			 struct nvkm_notify *notify)
 {
 	union {
 		struct nvif_notify_uevent_req none;
diff --git a/drivers/gpu/drm/nouveau/core/engine/software/nv50.c b/drivers/gpu/drm/nouveau/core/engine/software/nv50.c
index 4d2994d8cc32..a0fec205f9db 100644
--- a/drivers/gpu/drm/nouveau/core/engine/software/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/software/nv50.c
@@ -175,7 +175,8 @@ nv50_software_context_ctor(struct nouveau_object *parent,
 		return ret;
 
 	for (i = 0; pdisp && i < pdisp->vblank.index_nr; i++) {
-		ret = nvkm_notify_init(&pdisp->vblank, pclass->vblank, false,
+		ret = nvkm_notify_init(NULL, &pdisp->vblank, pclass->vblank,
+				       false,
 				       &(struct nvif_notify_head_req_v0) {
 					.head = i,
 				       },
diff --git a/drivers/gpu/drm/nouveau/core/include/core/client.h b/drivers/gpu/drm/nouveau/core/include/core/client.h
index 1794a05205d8..b0ce9f6680b5 100644
--- a/drivers/gpu/drm/nouveau/core/include/core/client.h
+++ b/drivers/gpu/drm/nouveau/core/include/core/client.h
@@ -48,7 +48,7 @@ int  nouveau_client_init(struct nouveau_client *);
 int  nouveau_client_fini(struct nouveau_client *, bool suspend);
 const char *nouveau_client_name(void *obj);
 
-int nvkm_client_notify_new(struct nouveau_client *, struct nvkm_event *,
+int nvkm_client_notify_new(struct nouveau_object *, struct nvkm_event *,
 			   void *data, u32 size);
 int nvkm_client_notify_del(struct nouveau_client *, int index);
 int nvkm_client_notify_get(struct nouveau_client *, int index);
diff --git a/drivers/gpu/drm/nouveau/core/include/core/device.h b/drivers/gpu/drm/nouveau/core/include/core/device.h
index 8743766454a5..1d9d893929bb 100644
--- a/drivers/gpu/drm/nouveau/core/include/core/device.h
+++ b/drivers/gpu/drm/nouveau/core/include/core/device.h
@@ -24,6 +24,7 @@ enum nv_subdev_type {
 	 * been created, and are allowed to assume any subdevs in the
 	 * list above them exist and have been initialised.
 	 */
+	NVDEV_SUBDEV_FUSE,
 	NVDEV_SUBDEV_MXM,
 	NVDEV_SUBDEV_MC,
 	NVDEV_SUBDEV_BUS,
diff --git a/drivers/gpu/drm/nouveau/core/include/core/event.h b/drivers/gpu/drm/nouveau/core/include/core/event.h
index 51e55d03330a..92876528972f 100644
--- a/drivers/gpu/drm/nouveau/core/include/core/event.h
+++ b/drivers/gpu/drm/nouveau/core/include/core/event.h
@@ -4,7 +4,8 @@
 #include <core/notify.h>
 
 struct nvkm_event_func {
-	int  (*ctor)(void *data, u32 size, struct nvkm_notify *);
+	int  (*ctor)(struct nouveau_object *, void *data, u32 size,
+		     struct nvkm_notify *);
 	void (*send)(void *data, u32 size, struct nvkm_notify *);
 	void (*init)(struct nvkm_event *, int type, int index);
 	void (*fini)(struct nvkm_event *, int type, int index);
diff --git a/drivers/gpu/drm/nouveau/core/include/core/mm.h b/drivers/gpu/drm/nouveau/core/include/core/mm.h
index 2bf7d0e32261..bfe6931544fe 100644
--- a/drivers/gpu/drm/nouveau/core/include/core/mm.h
+++ b/drivers/gpu/drm/nouveau/core/include/core/mm.h
@@ -6,6 +6,10 @@ struct nouveau_mm_node {
 	struct list_head fl_entry;
 	struct list_head rl_entry;
 
+#define NVKM_MM_HEAP_ANY 0x00
+	u8  heap;
+#define NVKM_MM_TYPE_NONE 0x00
+#define NVKM_MM_TYPE_HOLE 0xff
 	u8  type;
 	u32 offset;
 	u32 length;
@@ -27,10 +31,10 @@ nouveau_mm_initialised(struct nouveau_mm *mm)
 
 int  nouveau_mm_init(struct nouveau_mm *, u32 offset, u32 length, u32 block);
 int  nouveau_mm_fini(struct nouveau_mm *);
-int  nouveau_mm_head(struct nouveau_mm *, u8 type, u32 size_max, u32 size_min,
-		     u32 align, struct nouveau_mm_node **);
-int  nouveau_mm_tail(struct nouveau_mm *, u8 type, u32 size_max, u32 size_min,
-		     u32 align, struct nouveau_mm_node **);
+int  nouveau_mm_head(struct nouveau_mm *, u8 heap, u8 type, u32 size_max,
+		     u32 size_min, u32 align, struct nouveau_mm_node **);
+int  nouveau_mm_tail(struct nouveau_mm *, u8 heap, u8 type, u32 size_max,
+		     u32 size_min, u32 align, struct nouveau_mm_node **);
 void nouveau_mm_free(struct nouveau_mm *, struct nouveau_mm_node **);
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/include/core/notify.h b/drivers/gpu/drm/nouveau/core/include/core/notify.h
index 1262d8f020f3..a7c3c5f578cc 100644
--- a/drivers/gpu/drm/nouveau/core/include/core/notify.h
+++ b/drivers/gpu/drm/nouveau/core/include/core/notify.h
@@ -25,8 +25,9 @@ struct nvkm_notify {
 	const void *data;
 };
 
-int  nvkm_notify_init(struct nvkm_event *, int (*func)(struct nvkm_notify *),
-		      bool work, void *data, u32 size, u32 reply,
+int  nvkm_notify_init(struct nouveau_object *, struct nvkm_event *,
+		      int (*func)(struct nvkm_notify *), bool work,
+		      void *data, u32 size, u32 reply,
 		      struct nvkm_notify *);
 void nvkm_notify_fini(struct nvkm_notify *);
 void nvkm_notify_get(struct nvkm_notify *);
diff --git a/drivers/gpu/drm/nouveau/core/include/engine/fifo.h b/drivers/gpu/drm/nouveau/core/include/engine/fifo.h
index e5e4d930b2c2..2007453f6fce 100644
--- a/drivers/gpu/drm/nouveau/core/include/engine/fifo.h
+++ b/drivers/gpu/drm/nouveau/core/include/engine/fifo.h
@@ -116,7 +116,8 @@ extern struct nouveau_oclass *nve0_fifo_oclass;
 extern struct nouveau_oclass *gk20a_fifo_oclass;
 extern struct nouveau_oclass *nv108_fifo_oclass;
 
-int  nouveau_fifo_uevent_ctor(void *, u32, struct nvkm_notify *);
+int  nouveau_fifo_uevent_ctor(struct nouveau_object *, void *, u32,
+			      struct nvkm_notify *);
 void nouveau_fifo_uevent(struct nouveau_fifo *);
 
 void nv04_fifo_intr(struct nouveau_subdev *);
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/bar.h b/drivers/gpu/drm/nouveau/core/include/subdev/bar.h
index be037fac534c..257ddf6d36d4 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/bar.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/bar.h
@@ -12,7 +12,6 @@ struct nouveau_bar {
 
 	int (*alloc)(struct nouveau_bar *, struct nouveau_object *,
 		     struct nouveau_mem *, struct nouveau_object **);
-	void __iomem *iomem;
 
 	int (*kmap)(struct nouveau_bar *, struct nouveau_mem *,
 		    u32 flags, struct nouveau_vma *);
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/bios/M0205.h b/drivers/gpu/drm/nouveau/core/include/subdev/bios/M0205.h
new file mode 100644
index 000000000000..e171120cec81
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/bios/M0205.h
@@ -0,0 +1,32 @@
+#ifndef __NVBIOS_M0205_H__
+#define __NVBIOS_M0205_H__
+
+struct nvbios_M0205T {
+	u16 freq;
+};
+
+u32 nvbios_M0205Te(struct nouveau_bios *,
+		   u8 *ver, u8 *hdr, u8 *cnt, u8 *len, u8 *snr, u8 *ssz);
+u32 nvbios_M0205Tp(struct nouveau_bios *,
+		   u8 *ver, u8 *hdr, u8 *cnt, u8 *len, u8 *snr, u8 *ssz,
+		   struct nvbios_M0205T *);
+
+struct nvbios_M0205E {
+	u8 type;
+};
+
+u32 nvbios_M0205Ee(struct nouveau_bios *, int idx,
+		   u8 *ver, u8 *hdr, u8 *cnt, u8 *len);
+u32 nvbios_M0205Ep(struct nouveau_bios *, int idx,
+		   u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
+		   struct nvbios_M0205E *);
+
+struct nvbios_M0205S {
+	u8 data;
+};
+
+u32 nvbios_M0205Se(struct nouveau_bios *, int ent, int idx, u8 *ver, u8 *hdr);
+u32 nvbios_M0205Sp(struct nouveau_bios *, int ent, int idx, u8 *ver, u8 *hdr,
+		   struct nvbios_M0205S *);
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/bios/M0209.h b/drivers/gpu/drm/nouveau/core/include/subdev/bios/M0209.h
new file mode 100644
index 000000000000..67dc50d837bc
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/bios/M0209.h
@@ -0,0 +1,30 @@
+#ifndef __NVBIOS_M0209_H__
+#define __NVBIOS_M0209_H__
+
+u32 nvbios_M0209Te(struct nouveau_bios *,
+		   u8 *ver, u8 *hdr, u8 *cnt, u8 *len, u8 *snr, u8 *ssz);
+
+struct nvbios_M0209E {
+	u8 v00_40;
+	u8 bits;
+	u8 modulo;
+	u8 v02_40;
+	u8 v02_07;
+	u8 v03;
+};
+
+u32 nvbios_M0209Ee(struct nouveau_bios *, int idx,
+		   u8 *ver, u8 *hdr, u8 *cnt, u8 *len);
+u32 nvbios_M0209Ep(struct nouveau_bios *, int idx,
+		   u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
+		   struct nvbios_M0209E *);
+
+struct nvbios_M0209S {
+	u32 data[0x200];
+};
+
+u32 nvbios_M0209Se(struct nouveau_bios *, int ent, int idx, u8 *ver, u8 *hdr);
+u32 nvbios_M0209Sp(struct nouveau_bios *, int ent, int idx, u8 *ver, u8 *hdr,
+		   struct nvbios_M0209S *);
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/bios/fan.h b/drivers/gpu/drm/nouveau/core/include/subdev/bios/fan.h
new file mode 100644
index 000000000000..119d0874e041
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/bios/fan.h
@@ -0,0 +1,8 @@
+#ifndef __NVBIOS_FAN_H__
+#define __NVBIOS_FAN_H__
+
+#include <subdev/bios/therm.h>
+
+u16 nvbios_fan_parse(struct nouveau_bios *bios, struct nvbios_therm_fan *fan);
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/bios/ramcfg.h b/drivers/gpu/drm/nouveau/core/include/subdev/bios/ramcfg.h
index c086ac6d677d..a685bbd04568 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/bios/ramcfg.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/bios/ramcfg.h
@@ -4,60 +4,118 @@
 struct nouveau_bios;
 
 struct nvbios_ramcfg {
-	unsigned rammap_11_08_01:1;
-	unsigned rammap_11_08_0c:2;
-	unsigned rammap_11_08_10:1;
-	unsigned rammap_11_11_0c:2;
+	unsigned rammap_ver;
+	unsigned rammap_hdr;
+	unsigned rammap_min;
+	unsigned rammap_max;
+	union {
+		struct {
+			unsigned rammap_10_04_02:1;
+			unsigned rammap_10_04_08:1;
+		};
+		struct {
+			unsigned rammap_11_08_01:1;
+			unsigned rammap_11_08_0c:2;
+			unsigned rammap_11_08_10:1;
+			unsigned rammap_11_09_01ff:9;
+			unsigned rammap_11_0a_03fe:9;
+			unsigned rammap_11_0a_0400:1;
+			unsigned rammap_11_0a_0800:1;
+			unsigned rammap_11_0b_01f0:5;
+			unsigned rammap_11_0b_0200:1;
+			unsigned rammap_11_0b_0400:1;
+			unsigned rammap_11_0b_0800:1;
+			unsigned rammap_11_0d:8;
+			unsigned rammap_11_0e:8;
+			unsigned rammap_11_0f:8;
+			unsigned rammap_11_11_0c:2;
+		};
+	};
 
-	unsigned ramcfg_11_01_01:1;
-	unsigned ramcfg_11_01_02:1;
-	unsigned ramcfg_11_01_04:1;
-	unsigned ramcfg_11_01_08:1;
-	unsigned ramcfg_11_01_10:1;
-	unsigned ramcfg_11_01_20:1;
-	unsigned ramcfg_11_01_40:1;
-	unsigned ramcfg_11_01_80:1;
-	unsigned ramcfg_11_02_03:2;
-	unsigned ramcfg_11_02_04:1;
-	unsigned ramcfg_11_02_08:1;
-	unsigned ramcfg_11_02_10:1;
-	unsigned ramcfg_11_02_40:1;
-	unsigned ramcfg_11_02_80:1;
-	unsigned ramcfg_11_03_0f:4;
-	unsigned ramcfg_11_03_30:2;
-	unsigned ramcfg_11_03_c0:2;
-	unsigned ramcfg_11_03_f0:4;
-	unsigned ramcfg_11_04:8;
-	unsigned ramcfg_11_06:8;
-	unsigned ramcfg_11_07_02:1;
-	unsigned ramcfg_11_07_04:1;
-	unsigned ramcfg_11_07_08:1;
-	unsigned ramcfg_11_07_10:1;
-	unsigned ramcfg_11_07_40:1;
-	unsigned ramcfg_11_07_80:1;
-	unsigned ramcfg_11_08_01:1;
-	unsigned ramcfg_11_08_02:1;
-	unsigned ramcfg_11_08_04:1;
-	unsigned ramcfg_11_08_08:1;
-	unsigned ramcfg_11_08_10:1;
-	unsigned ramcfg_11_08_20:1;
-	unsigned ramcfg_11_09:8;
+	unsigned ramcfg_ver;
+	unsigned ramcfg_hdr;
+	unsigned ramcfg_timing;
+	union {
+		struct {
+			unsigned ramcfg_10_02_01:1;
+			unsigned ramcfg_10_02_02:1;
+			unsigned ramcfg_10_02_04:1;
+			unsigned ramcfg_10_02_08:1;
+			unsigned ramcfg_10_02_10:1;
+			unsigned ramcfg_10_02_20:1;
+			unsigned ramcfg_10_02_40:1;
+			unsigned ramcfg_10_03_0f:4;
+			unsigned ramcfg_10_05:8;
+			unsigned ramcfg_10_06:8;
+			unsigned ramcfg_10_07:8;
+			unsigned ramcfg_10_08:8;
+			unsigned ramcfg_10_09_0f:4;
+			unsigned ramcfg_10_09_f0:4;
+		};
+		struct {
+			unsigned ramcfg_11_01_01:1;
+			unsigned ramcfg_11_01_02:1;
+			unsigned ramcfg_11_01_04:1;
+			unsigned ramcfg_11_01_08:1;
+			unsigned ramcfg_11_01_10:1;
+			unsigned ramcfg_11_01_20:1;
+			unsigned ramcfg_11_01_40:1;
+			unsigned ramcfg_11_01_80:1;
+			unsigned ramcfg_11_02_03:2;
+			unsigned ramcfg_11_02_04:1;
+			unsigned ramcfg_11_02_08:1;
+			unsigned ramcfg_11_02_10:1;
+			unsigned ramcfg_11_02_40:1;
+			unsigned ramcfg_11_02_80:1;
+			unsigned ramcfg_11_03_0f:4;
+			unsigned ramcfg_11_03_30:2;
+			unsigned ramcfg_11_03_c0:2;
+			unsigned ramcfg_11_03_f0:4;
+			unsigned ramcfg_11_04:8;
+			unsigned ramcfg_11_06:8;
+			unsigned ramcfg_11_07_02:1;
+			unsigned ramcfg_11_07_04:1;
+			unsigned ramcfg_11_07_08:1;
+			unsigned ramcfg_11_07_10:1;
+			unsigned ramcfg_11_07_40:1;
+			unsigned ramcfg_11_07_80:1;
+			unsigned ramcfg_11_08_01:1;
+			unsigned ramcfg_11_08_02:1;
+			unsigned ramcfg_11_08_04:1;
+			unsigned ramcfg_11_08_08:1;
+			unsigned ramcfg_11_08_10:1;
+			unsigned ramcfg_11_08_20:1;
+			unsigned ramcfg_11_09:8;
+		};
+	};
 
+	unsigned timing_ver;
+	unsigned timing_hdr;
 	unsigned timing[11];
-	unsigned timing_20_2e_03:2;
-	unsigned timing_20_2e_30:2;
-	unsigned timing_20_2e_c0:2;
-	unsigned timing_20_2f_03:2;
-	unsigned timing_20_2c_003f:6;
-	unsigned timing_20_2c_1fc0:7;
-	unsigned timing_20_30_f8:5;
-	unsigned timing_20_30_07:3;
-	unsigned timing_20_31_0007:3;
-	unsigned timing_20_31_0078:4;
-	unsigned timing_20_31_0780:4;
-	unsigned timing_20_31_0800:1;
-	unsigned timing_20_31_7000:3;
-	unsigned timing_20_31_8000:1;
+	union {
+		struct {
+			unsigned timing_10_WR:8;
+			unsigned timing_10_CL:8;
+			unsigned timing_10_ODT:3;
+			unsigned timing_10_CWL:8;
+		};
+		struct {
+			unsigned timing_20_2e_03:2;
+			unsigned timing_20_2e_30:2;
+			unsigned timing_20_2e_c0:2;
+			unsigned timing_20_2f_03:2;
+			unsigned timing_20_2c_003f:6;
+			unsigned timing_20_2c_1fc0:7;
+			unsigned timing_20_30_f8:5;
+			unsigned timing_20_30_07:3;
+			unsigned timing_20_31_0007:3;
+			unsigned timing_20_31_0078:4;
+			unsigned timing_20_31_0780:4;
+			unsigned timing_20_31_0800:1;
+			unsigned timing_20_31_7000:3;
+			unsigned timing_20_31_8000:1;
+		};
+	};
 };
 
 u8 nvbios_ramcfg_count(struct nouveau_bios *);
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/bios/rammap.h b/drivers/gpu/drm/nouveau/core/include/subdev/bios/rammap.h
index 5bdf8e4db40a..47e021d3e20d 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/bios/rammap.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/bios/rammap.h
@@ -8,9 +8,10 @@ u32 nvbios_rammapTe(struct nouveau_bios *, u8 *ver, u8 *hdr,
 
 u32 nvbios_rammapEe(struct nouveau_bios *, int idx,
 		    u8 *ver, u8 *hdr, u8 *cnt, u8 *len);
+u32 nvbios_rammapEp(struct nouveau_bios *, int idx,
+		    u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
+		    struct nvbios_ramcfg *);
 u32 nvbios_rammapEm(struct nouveau_bios *, u16 mhz,
-		    u8 *ver, u8 *hdr, u8 *cnt, u8 *len);
-u32 nvbios_rammapEp(struct nouveau_bios *, u16 mhz,
 		    u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
 		    struct nvbios_ramcfg *);
 
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/bios/therm.h b/drivers/gpu/drm/nouveau/core/include/subdev/bios/therm.h
index 8dc5051df55d..295d093f3b30 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/bios/therm.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/bios/therm.h
@@ -23,6 +23,12 @@ struct nvbios_therm_sensor {
 	struct nvbios_therm_threshold thrs_shutdown;
 };
 
+enum nvbios_therm_fan_type {
+	NVBIOS_THERM_FAN_UNK = 0,
+	NVBIOS_THERM_FAN_TOGGLE = 1,
+	NVBIOS_THERM_FAN_PWM = 2,
+};
+
 /* no vbios have more than 6 */
 #define NOUVEAU_TEMP_FAN_TRIP_MAX 10
 struct nouveau_therm_trip_point {
@@ -38,7 +44,9 @@ enum nvbios_therm_fan_mode {
 };
 
 struct nvbios_therm_fan {
-	u16 pwm_freq;
+	enum nvbios_therm_fan_type type;
+
+	u32 pwm_freq;
 
 	u8 min_duty;
 	u8 max_duty;
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/clock.h b/drivers/gpu/drm/nouveau/core/include/subdev/clock.h
index a5ca00dd2f61..36ed035d4d42 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/clock.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/clock.h
@@ -29,6 +29,7 @@ enum nv_clk_src {
 	nv_clk_src_mdiv,
 
 	nv_clk_src_core,
+	nv_clk_src_core_intm,
 	nv_clk_src_shader,
 
 	nv_clk_src_mem,
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/fb.h b/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
index 871e73914b24..8d0032f15205 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
@@ -111,6 +111,7 @@ extern struct nouveau_oclass *gm107_fb_oclass;
 #include <subdev/bios/ramcfg.h>
 
 struct nouveau_ram_data {
+	struct list_head head;
 	struct nvbios_ramcfg bios;
 	u32 freq;
 };
@@ -136,6 +137,7 @@ struct nouveau_ram {
 
 	int ranks;
 	int parts;
+	int part_mask;
 
 	int  (*get)(struct nouveau_fb *, u64 size, u32 align,
 		    u32 size_nc, u32 type, struct nouveau_mem **);
@@ -144,11 +146,6 @@ struct nouveau_ram {
 	int  (*calc)(struct nouveau_fb *, u32 freq);
 	int  (*prog)(struct nouveau_fb *);
 	void (*tidy)(struct nouveau_fb *);
-	struct {
-		u8  version;
-		u32 data;
-		u8  size;
-	} rammap, ramcfg, timing;
 	u32 freq;
 	u32 mr[16];
 	u32 mr1_nuts;
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/fb/regsnv04.h b/drivers/gpu/drm/nouveau/core/include/subdev/fb/regsnv04.h
new file mode 100644
index 000000000000..0f7fc0c52ab2
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/fb/regsnv04.h
@@ -0,0 +1,21 @@
+#ifndef __NOUVEAU_FB_REGS_04_H__
+#define __NOUVEAU_FB_REGS_04_H__
+
+#define NV04_PFB_BOOT_0						0x00100000
+#	define NV04_PFB_BOOT_0_RAM_AMOUNT			0x00000003
+#	define NV04_PFB_BOOT_0_RAM_AMOUNT_32MB			0x00000000
+#	define NV04_PFB_BOOT_0_RAM_AMOUNT_4MB			0x00000001
+#	define NV04_PFB_BOOT_0_RAM_AMOUNT_8MB			0x00000002
+#	define NV04_PFB_BOOT_0_RAM_AMOUNT_16MB			0x00000003
+#	define NV04_PFB_BOOT_0_RAM_WIDTH_128			0x00000004
+#	define NV04_PFB_BOOT_0_RAM_TYPE				0x00000028
+#	define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_8MBIT		0x00000000
+#	define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_16MBIT		0x00000008
+#	define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_16MBIT_4BANK	0x00000010
+#	define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_16MBIT		0x00000018
+#	define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_64MBIT		0x00000020
+#	define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_64MBITX16		0x00000028
+#	define NV04_PFB_BOOT_0_UMA_ENABLE			0x00000100
+#	define NV04_PFB_BOOT_0_UMA_SIZE				0x0000f000
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/fuse.h b/drivers/gpu/drm/nouveau/core/include/subdev/fuse.h
new file mode 100644
index 000000000000..2b1ddb2a9a7d
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/fuse.h
@@ -0,0 +1,30 @@
+#ifndef __NOUVEAU_FUSE_H__
+#define __NOUVEAU_FUSE_H__
+
+#include <core/subdev.h>
+#include <core/device.h>
+
+struct nouveau_fuse {
+	struct nouveau_subdev base;
+};
+
+static inline struct nouveau_fuse *
+nouveau_fuse(void *obj)
+{
+	return (void *)nv_device(obj)->subdev[NVDEV_SUBDEV_FUSE];
+}
+
+#define nouveau_fuse_create(p, e, o, d)                                        \
+	nouveau_fuse_create_((p), (e), (o), sizeof(**d), (void **)d)
+
+int  nouveau_fuse_create_(struct nouveau_object *, struct nouveau_object *,
+			  struct nouveau_oclass *, int, void **);
+void _nouveau_fuse_dtor(struct nouveau_object *);
+int  _nouveau_fuse_init(struct nouveau_object *);
+#define _nouveau_fuse_fini _nouveau_subdev_fini
+
+extern struct nouveau_oclass g80_fuse_oclass;
+extern struct nouveau_oclass gf100_fuse_oclass;
+extern struct nouveau_oclass gm107_fuse_oclass;
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/gpio.h b/drivers/gpu/drm/nouveau/core/include/subdev/gpio.h
index b73733d21cc7..f855140dbcb7 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/gpio.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/gpio.h
@@ -40,7 +40,7 @@ nouveau_gpio(void *obj)
 
 extern struct nouveau_oclass *nv10_gpio_oclass;
 extern struct nouveau_oclass *nv50_gpio_oclass;
-extern struct nouveau_oclass *nv92_gpio_oclass;
+extern struct nouveau_oclass *nv94_gpio_oclass;
 extern struct nouveau_oclass *nvd0_gpio_oclass;
 extern struct nouveau_oclass *nve0_gpio_oclass;
 
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/pwr.h b/drivers/gpu/drm/nouveau/core/include/subdev/pwr.h
index f73feec151db..bf3d1f611333 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/pwr.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/pwr.h
@@ -47,5 +47,8 @@ void nouveau_memx_wr32(struct nouveau_memx *, u32 addr, u32 data);
 void nouveau_memx_wait(struct nouveau_memx *,
 		       u32 addr, u32 mask, u32 data, u32 nsec);
 void nouveau_memx_nsec(struct nouveau_memx *, u32 nsec);
+void nouveau_memx_wait_vblank(struct nouveau_memx *);
+void nouveau_memx_block(struct nouveau_memx *);
+void nouveau_memx_unblock(struct nouveau_memx *);
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/therm.h b/drivers/gpu/drm/nouveau/core/include/subdev/therm.h
index d4a68179e586..a437597dcafc 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/therm.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/therm.h
@@ -78,5 +78,6 @@ extern struct nouveau_oclass nv50_therm_oclass;
 extern struct nouveau_oclass nv84_therm_oclass;
 extern struct nouveau_oclass nva3_therm_oclass;
 extern struct nouveau_oclass nvd0_therm_oclass;
+extern struct nouveau_oclass gm107_therm_oclass;
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bar/base.c b/drivers/gpu/drm/nouveau/core/subdev/bar/base.c
index 8bcbdf39cfb2..b1adc69efd88 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bar/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bar/base.c
@@ -38,10 +38,12 @@ struct nouveau_barobj {
 static int
 nouveau_barobj_ctor(struct nouveau_object *parent,
 		    struct nouveau_object *engine,
-		    struct nouveau_oclass *oclass, void *mem, u32 size,
+		    struct nouveau_oclass *oclass, void *data, u32 size,
 		    struct nouveau_object **pobject)
 {
+	struct nouveau_device *device = nv_device(parent);
 	struct nouveau_bar *bar = (void *)engine;
+	struct nouveau_mem *mem = data;
 	struct nouveau_barobj *barobj;
 	int ret;
 
@@ -54,7 +56,13 @@ nouveau_barobj_ctor(struct nouveau_object *parent,
 	if (ret)
 		return ret;
 
-	barobj->iomem = bar->iomem + (u32)barobj->vma.offset;
+	barobj->iomem = ioremap(nv_device_resource_start(device, 3) +
+				(u32)barobj->vma.offset, mem->size << 12);
+	if (!barobj->iomem) {
+		nv_warn(bar, "PRAMIN ioremap failed\n");
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
@@ -63,8 +71,11 @@ nouveau_barobj_dtor(struct nouveau_object *object)
 {
 	struct nouveau_bar *bar = (void *)object->engine;
 	struct nouveau_barobj *barobj = (void *)object;
-	if (barobj->vma.node)
+	if (barobj->vma.node) {
+		if (barobj->iomem)
+			iounmap(barobj->iomem);
 		bar->unmap(bar, &barobj->vma);
+	}
 	nouveau_object_destroy(&barobj->base);
 }
 
@@ -99,12 +110,11 @@ nouveau_bar_alloc(struct nouveau_bar *bar, struct nouveau_object *parent,
 		  struct nouveau_mem *mem, struct nouveau_object **pobject)
 {
 	struct nouveau_object *engine = nv_object(bar);
-	int ret = -ENOMEM;
-	if (bar->iomem) {
-		ret = nouveau_object_ctor(parent, engine,
-					  &nouveau_barobj_oclass,
-					  mem, 0, pobject);
-	}
+	struct nouveau_object *gpuobj;
+	int ret = nouveau_object_ctor(parent, engine, &nouveau_barobj_oclass,
+				      mem, 0, &gpuobj);
+	if (ret == 0)
+		*pobject = gpuobj;
 	return ret;
 }
 
@@ -113,7 +123,6 @@ nouveau_bar_create_(struct nouveau_object *parent,
 		    struct nouveau_object *engine,
 		    struct nouveau_oclass *oclass, int length, void **pobject)
 {
-	struct nouveau_device *device = nv_device(parent);
 	struct nouveau_bar *bar;
 	int ret;
 
@@ -123,21 +132,12 @@ nouveau_bar_create_(struct nouveau_object *parent,
 	if (ret)
 		return ret;
 
-	if (nv_device_resource_len(device, 3) != 0) {
-		bar->iomem = ioremap(nv_device_resource_start(device, 3),
-				     nv_device_resource_len(device, 3));
-		if (!bar->iomem)
-			nv_warn(bar, "PRAMIN ioremap failed\n");
-	}
-
 	return 0;
 }
 
 void
 nouveau_bar_destroy(struct nouveau_bar *bar)
 {
-	if (bar->iomem)
-		iounmap(bar->iomem);
 	nouveau_subdev_destroy(&bar->base);
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/M0205.c b/drivers/gpu/drm/nouveau/core/subdev/bios/M0205.c
new file mode 100644
index 000000000000..ac9617c5fc2a
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/M0205.c
@@ -0,0 +1,136 @@
+/*
+ * Copyright 2013 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include <subdev/bios.h>
+#include <subdev/bios/bit.h>
+#include <subdev/bios/M0205.h>
+
+u32
+nvbios_M0205Te(struct nouveau_bios *bios,
+	       u8 *ver, u8 *hdr, u8 *cnt, u8 *len, u8 *snr, u8 *ssz)
+{
+	struct bit_entry bit_M;
+	u32 data = 0x00000000;
+
+	if (!bit_entry(bios, 'M', &bit_M)) {
+		if (bit_M.version == 2 && bit_M.length > 0x08)
+			data = nv_ro32(bios, bit_M.offset + 0x05);
+		if (data) {
+			*ver = nv_ro08(bios, data + 0x00);
+			switch (*ver) {
+			case 0x10:
+				*hdr = nv_ro08(bios, data + 0x01);
+				*len = nv_ro08(bios, data + 0x02);
+				*ssz = nv_ro08(bios, data + 0x03);
+				*snr = nv_ro08(bios, data + 0x04);
+				*cnt = nv_ro08(bios, data + 0x05);
+				return data;
+			default:
+				break;
+			}
+		}
+	}
+
+	return 0x00000000;
+}
+
+u32
+nvbios_M0205Tp(struct nouveau_bios *bios,
+	       u8 *ver, u8 *hdr, u8 *cnt, u8 *len, u8 *snr, u8 *ssz,
+	       struct nvbios_M0205T *info)
+{
+	u32 data = nvbios_M0205Te(bios, ver, hdr, cnt, len, snr, ssz);
+	memset(info, 0x00, sizeof(*info));
+	switch (!!data * *ver) {
+	case 0x10:
+		info->freq = nv_ro16(bios, data + 0x06);
+		break;
+	default:
+		break;
+	}
+	return data;
+}
+
+u32
+nvbios_M0205Ee(struct nouveau_bios *bios, int idx,
+	       u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
+{
+	u8  snr, ssz;
+	u32 data = nvbios_M0205Te(bios, ver, hdr, cnt, len, &snr, &ssz);
+	if (data && idx < *cnt) {
+		data = data + *hdr + idx * (*len + (snr * ssz));
+		*hdr = *len;
+		*cnt = snr;
+		*len = ssz;
+		return data;
+	}
+	return 0x00000000;
+}
+
+u32
+nvbios_M0205Ep(struct nouveau_bios *bios, int idx,
+	       u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
+	       struct nvbios_M0205E *info)
+{
+	u32 data = nvbios_M0205Ee(bios, idx, ver, hdr, cnt, len);
+	memset(info, 0x00, sizeof(*info));
+	switch (!!data * *ver) {
+	case 0x10:
+		info->type = nv_ro08(bios, data + 0x00) & 0x0f;
+		return data;
+	default:
+		break;
+	}
+	return 0x00000000;
+}
+
+u32
+nvbios_M0205Se(struct nouveau_bios *bios, int ent, int idx, u8 *ver, u8 *hdr)
+{
+
+	u8  cnt, len;
+	u32 data = nvbios_M0205Ee(bios, ent, ver, hdr, &cnt, &len);
+	if (data && idx < cnt) {
+		data = data + *hdr + idx * len;
+		*hdr = len;
+		return data;
+	}
+	return 0x00000000;
+}
+
+u32
+nvbios_M0205Sp(struct nouveau_bios *bios, int ent, int idx, u8 *ver, u8 *hdr,
+	       struct nvbios_M0205S *info)
+{
+	u32 data = nvbios_M0205Se(bios, ent, idx, ver, hdr);
+	memset(info, 0x00, sizeof(*info));
+	switch (!!data * *ver) {
+	case 0x10:
+		info->data = nv_ro08(bios, data + 0x00);
+		return data;
+	default:
+		break;
+	}
+	return 0x00000000;
+}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/M0209.c b/drivers/gpu/drm/nouveau/core/subdev/bios/M0209.c
new file mode 100644
index 000000000000..b142a510e89f
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/M0209.c
@@ -0,0 +1,137 @@
+/*
+ * Copyright 2013 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include <subdev/bios.h>
+#include <subdev/bios/bit.h>
+#include <subdev/bios/M0209.h>
+
+u32
+nvbios_M0209Te(struct nouveau_bios *bios,
+	       u8 *ver, u8 *hdr, u8 *cnt, u8 *len, u8 *snr, u8 *ssz)
+{
+	struct bit_entry bit_M;
+	u32 data = 0x00000000;
+
+	if (!bit_entry(bios, 'M', &bit_M)) {
+		if (bit_M.version == 2 && bit_M.length > 0x0c)
+			data = nv_ro32(bios, bit_M.offset + 0x09);
+		if (data) {
+			*ver = nv_ro08(bios, data + 0x00);
+			switch (*ver) {
+			case 0x10:
+				*hdr = nv_ro08(bios, data + 0x01);
+				*len = nv_ro08(bios, data + 0x02);
+				*ssz = nv_ro08(bios, data + 0x03);
+				*snr = 1;
+				*cnt = nv_ro08(bios, data + 0x04);
+				return data;
+			default:
+				break;
+			}
+		}
+	}
+
+	return 0x00000000;
+}
+
+u32
+nvbios_M0209Ee(struct nouveau_bios *bios, int idx,
+	       u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
+{
+	u8  snr, ssz;
+	u32 data = nvbios_M0209Te(bios, ver, hdr, cnt, len, &snr, &ssz);
+	if (data && idx < *cnt) {
+		data = data + *hdr + idx * (*len + (snr * ssz));
+		*hdr = *len;
+		*cnt = snr;
+		*len = ssz;
+		return data;
+	}
+	return 0x00000000;
+}
+
+u32
+nvbios_M0209Ep(struct nouveau_bios *bios, int idx,
+	       u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
+	       struct nvbios_M0209E *info)
+{
+	u32 data = nvbios_M0209Ee(bios, idx, ver, hdr, cnt, len);
+	memset(info, 0x00, sizeof(*info));
+	switch (!!data * *ver) {
+	case 0x10:
+		info->v00_40 = (nv_ro08(bios, data + 0x00) & 0x40) >> 6;
+		info->bits   =  nv_ro08(bios, data + 0x00) & 0x3f;
+		info->modulo =  nv_ro08(bios, data + 0x01);
+		info->v02_40 = (nv_ro08(bios, data + 0x02) & 0x40) >> 6;
+		info->v02_07 =  nv_ro08(bios, data + 0x02) & 0x07;
+		info->v03    =  nv_ro08(bios, data + 0x03);
+		return data;
+	default:
+		break;
+	}
+	return 0x00000000;
+}
+
+u32
+nvbios_M0209Se(struct nouveau_bios *bios, int ent, int idx, u8 *ver, u8 *hdr)
+{
+
+	u8  cnt, len;
+	u32 data = nvbios_M0209Ee(bios, ent, ver, hdr, &cnt, &len);
+	if (data && idx < cnt) {
+		data = data + *hdr + idx * len;
+		*hdr = len;
+		return data;
+	}
+	return 0x00000000;
+}
+
+u32
+nvbios_M0209Sp(struct nouveau_bios *bios, int ent, int idx, u8 *ver, u8 *hdr,
+	       struct nvbios_M0209S *info)
+{
+	struct nvbios_M0209E M0209E;
+	u8  cnt, len;
+	u32 data = nvbios_M0209Ep(bios, ent, ver, hdr, &cnt, &len, &M0209E);
+	if (data) {
+		u32 i, data = nvbios_M0209Se(bios, ent, idx, ver, hdr);
+		memset(info, 0x00, sizeof(*info));
+		switch (!!data * *ver) {
+		case 0x10:
+			for (i = 0; i < ARRAY_SIZE(info->data); i++) {
+				u32 bits = (i % M0209E.modulo) * M0209E.bits;
+				u32 mask = (1ULL << M0209E.bits) - 1;
+				u16  off = bits / 8;
+				u8   mod = bits % 8;
+				info->data[i] = nv_ro32(bios, data + off);
+				info->data[i] = info->data[i] >> mod;
+				info->data[i] = info->data[i] & mask;
+			}
+			return data;
+		default:
+			break;
+		}
+	}
+	return 0x00000000;
+}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
index 88606bfaf847..bd8d348385b3 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
@@ -124,6 +124,7 @@ dcb_outp_parse(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *len,
 	       struct dcb_output *outp)
 {
 	u16 dcb = dcb_outp(bios, idx, ver, len);
+	memset(outp, 0x00, sizeof(*outp));
 	if (dcb) {
 		if (*ver >= 0x20) {
 			u32 conn = nv_ro32(bios, dcb + 0x00);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/fan.c b/drivers/gpu/drm/nouveau/core/subdev/bios/fan.c
new file mode 100644
index 000000000000..e419892240f5
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/fan.c
@@ -0,0 +1,93 @@
+/*
+ * Copyright 2014 Martin Peres
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Martin Peres
+ */
+
+#include <subdev/bios.h>
+#include <subdev/bios/bit.h>
+#include <subdev/bios/fan.h>
+
+u16
+nvbios_fan_table(struct nouveau_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
+{
+	struct bit_entry bit_P;
+	u16 fan = 0x0000;
+
+	if (!bit_entry(bios, 'P', &bit_P)) {
+		if (bit_P.version == 2 && bit_P.length >= 0x5a)
+			fan = nv_ro16(bios, bit_P.offset + 0x58);
+
+		if (fan) {
+			*ver = nv_ro08(bios, fan + 0);
+			switch (*ver) {
+			case 0x10:
+				*hdr = nv_ro08(bios, fan + 1);
+				*len = nv_ro08(bios, fan + 2);
+				*cnt = nv_ro08(bios, fan + 3);
+				return fan;
+			default:
+				break;
+			}
+		}
+	}
+
+	return 0x0000;
+}
+
+u16
+nvbios_fan_entry(struct nouveau_bios *bios, int idx, u8 *ver, u8 *hdr,
+		 u8 *cnt, u8 *len)
+{
+	u16 data = nvbios_fan_table(bios, ver, hdr, cnt, len);
+	if (data && idx < *cnt)
+		return data + *hdr + (idx * (*len));
+	return 0x0000;
+}
+
+u16
+nvbios_fan_parse(struct nouveau_bios *bios, struct nvbios_therm_fan *fan)
+{
+	u8 ver, hdr, cnt, len;
+
+	u16 data = nvbios_fan_entry(bios, 0, &ver, &hdr, &cnt, &len);
+	if (data) {
+		u8 type = nv_ro08(bios, data + 0x00);
+		switch (type) {
+		case 0:
+			fan->type = NVBIOS_THERM_FAN_TOGGLE;
+			break;
+		case 1:
+		case 2:
+			/* TODO: Understand the difference between the two! */
+			fan->type = NVBIOS_THERM_FAN_PWM;
+			break;
+		default:
+			fan->type = NVBIOS_THERM_FAN_UNK;
+		}
+
+		fan->min_duty = nv_ro08(bios, data + 0x02);
+		fan->max_duty = nv_ro08(bios, data + 0x03);
+
+		fan->pwm_freq = nv_ro32(bios, data + 0x0b) & 0xffffff;
+	}
+	return data;
+}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/rammap.c b/drivers/gpu/drm/nouveau/core/subdev/bios/rammap.c
index 1811b2cb0472..585e69331ccc 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/rammap.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/rammap.c
@@ -75,31 +75,39 @@ nvbios_rammapEe(struct nouveau_bios *bios, int idx,
 }
 
 u32
-nvbios_rammapEm(struct nouveau_bios *bios, u16 khz,
-		u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
-{
-	int idx = 0;
-	u32 data;
-	while ((data = nvbios_rammapEe(bios, idx++, ver, hdr, cnt, len))) {
-		if (khz >= nv_ro16(bios, data + 0x00) &&
-		    khz <= nv_ro16(bios, data + 0x02))
-			break;
-	}
-	return data;
-}
-
-u32
-nvbios_rammapEp(struct nouveau_bios *bios, u16 khz,
+nvbios_rammapEp(struct nouveau_bios *bios, int idx,
 		u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
 		struct nvbios_ramcfg *p)
 {
-	u32 data = nvbios_rammapEm(bios, khz, ver, hdr, cnt, len);
+	u32 data = nvbios_rammapEe(bios, idx, ver, hdr, cnt, len), temp;
 	memset(p, 0x00, sizeof(*p));
+	p->rammap_ver = *ver;
+	p->rammap_hdr = *hdr;
 	switch (!!data * *ver) {
+	case 0x10:
+		p->rammap_min      =  nv_ro16(bios, data + 0x00);
+		p->rammap_max      =  nv_ro16(bios, data + 0x02);
+		p->rammap_10_04_02 = (nv_ro08(bios, data + 0x04) & 0x02) >> 1;
+		p->rammap_10_04_08 = (nv_ro08(bios, data + 0x04) & 0x08) >> 3;
+		break;
 	case 0x11:
+		p->rammap_min      =  nv_ro16(bios, data + 0x00);
+		p->rammap_max      =  nv_ro16(bios, data + 0x02);
 		p->rammap_11_08_01 = (nv_ro08(bios, data + 0x08) & 0x01) >> 0;
 		p->rammap_11_08_0c = (nv_ro08(bios, data + 0x08) & 0x0c) >> 2;
 		p->rammap_11_08_10 = (nv_ro08(bios, data + 0x08) & 0x10) >> 4;
+		temp = nv_ro32(bios, data + 0x09);
+		p->rammap_11_09_01ff = (temp & 0x000001ff) >> 0;
+		p->rammap_11_0a_03fe = (temp & 0x0003fe00) >> 9;
+		p->rammap_11_0a_0400 = (temp & 0x00040000) >> 18;
+		p->rammap_11_0a_0800 = (temp & 0x00080000) >> 19;
+		p->rammap_11_0b_01f0 = (temp & 0x01f00000) >> 20;
+		p->rammap_11_0b_0200 = (temp & 0x02000000) >> 25;
+		p->rammap_11_0b_0400 = (temp & 0x04000000) >> 26;
+		p->rammap_11_0b_0800 = (temp & 0x08000000) >> 27;
+		p->rammap_11_0d    =  nv_ro08(bios, data + 0x0d);
+		p->rammap_11_0e    =  nv_ro08(bios, data + 0x0e);
+		p->rammap_11_0f    =  nv_ro08(bios, data + 0x0f);
 		p->rammap_11_11_0c = (nv_ro08(bios, data + 0x11) & 0x0c) >> 2;
 		break;
 	default:
@@ -110,6 +118,20 @@ nvbios_rammapEp(struct nouveau_bios *bios, u16 khz,
 }
 
 u32
+nvbios_rammapEm(struct nouveau_bios *bios, u16 mhz,
+		u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
+		struct nvbios_ramcfg *info)
+{
+	int idx = 0;
+	u32 data;
+	while ((data = nvbios_rammapEp(bios, idx++, ver, hdr, cnt, len, info))) {
+		if (mhz >= info->rammap_min && mhz <= info->rammap_max)
+			break;
+	}
+	return data;
+}
+
+u32
 nvbios_rammapSe(struct nouveau_bios *bios, u32 data,
 		u8 ever, u8 ehdr, u8 ecnt, u8 elen, int idx,
 		u8 *ver, u8 *hdr)
@@ -129,8 +151,28 @@ nvbios_rammapSp(struct nouveau_bios *bios, u32 data,
 		u8 *ver, u8 *hdr, struct nvbios_ramcfg *p)
 {
 	data = nvbios_rammapSe(bios, data, ever, ehdr, ecnt, elen, idx, ver, hdr);
+	p->ramcfg_ver = *ver;
+	p->ramcfg_hdr = *hdr;
 	switch (!!data * *ver) {
+	case 0x10:
+		p->ramcfg_timing   =  nv_ro08(bios, data + 0x01);
+		p->ramcfg_10_02_01 = (nv_ro08(bios, data + 0x02) & 0x01) >> 0;
+		p->ramcfg_10_02_02 = (nv_ro08(bios, data + 0x02) & 0x02) >> 1;
+		p->ramcfg_10_02_04 = (nv_ro08(bios, data + 0x02) & 0x04) >> 2;
+		p->ramcfg_10_02_08 = (nv_ro08(bios, data + 0x02) & 0x08) >> 3;
+		p->ramcfg_10_02_10 = (nv_ro08(bios, data + 0x02) & 0x10) >> 4;
+		p->ramcfg_10_02_20 = (nv_ro08(bios, data + 0x02) & 0x20) >> 5;
+		p->ramcfg_10_02_40 = (nv_ro08(bios, data + 0x02) & 0x40) >> 6;
+		p->ramcfg_10_03_0f = (nv_ro08(bios, data + 0x03) & 0x0f) >> 0;
+		p->ramcfg_10_05    = (nv_ro08(bios, data + 0x05) & 0xff) >> 0;
+		p->ramcfg_10_06    = (nv_ro08(bios, data + 0x06) & 0xff) >> 0;
+		p->ramcfg_10_07    = (nv_ro08(bios, data + 0x07) & 0xff) >> 0;
+		p->ramcfg_10_08    = (nv_ro08(bios, data + 0x08) & 0xff) >> 0;
+		p->ramcfg_10_09_0f = (nv_ro08(bios, data + 0x09) & 0x0f) >> 0;
+		p->ramcfg_10_09_f0 = (nv_ro08(bios, data + 0x09) & 0xf0) >> 4;
+		break;
 	case 0x11:
+		p->ramcfg_timing   =  nv_ro08(bios, data + 0x00);
 		p->ramcfg_11_01_01 = (nv_ro08(bios, data + 0x01) & 0x01) >> 0;
 		p->ramcfg_11_01_02 = (nv_ro08(bios, data + 0x01) & 0x02) >> 1;
 		p->ramcfg_11_01_04 = (nv_ro08(bios, data + 0x01) & 0x04) >> 2;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/timing.c b/drivers/gpu/drm/nouveau/core/subdev/bios/timing.c
index 350d44ab2ba2..46d955eb51eb 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/timing.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/timing.c
@@ -89,7 +89,15 @@ nvbios_timingEp(struct nouveau_bios *bios, int idx,
 		struct nvbios_ramcfg *p)
 {
 	u16 data = nvbios_timingEe(bios, idx, ver, hdr, cnt, len), temp;
+	p->timing_ver = *ver;
+	p->timing_hdr = *hdr;
 	switch (!!data * *ver) {
+	case 0x10:
+		p->timing_10_WR = nv_ro08(bios, data + 0x00);
+		p->timing_10_CL = nv_ro08(bios, data + 0x02);
+		p->timing_10_ODT = nv_ro08(bios, data + 0x0e) & 0x07;
+		p->timing_10_CWL = nv_ro08(bios, data + 0x13);
+		break;
 	case 0x20:
 		p->timing[0] = nv_ro32(bios, data + 0x00);
 		p->timing[1] = nv_ro32(bios, data + 0x04);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/base.c b/drivers/gpu/drm/nouveau/core/subdev/clock/base.c
index a276a711294a..e51b72d47129 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/base.c
@@ -573,7 +573,7 @@ nouveau_clock_create_(struct nouveau_object *parent,
 
 	clk->allow_reclock = allow_reclock;
 
-	ret = nvkm_notify_init(&device->event, nouveau_clock_pwrsrc, true,
+	ret = nvkm_notify_init(NULL, &device->event, nouveau_clock_pwrsrc, true,
 			       NULL, 0, 0, &clk->pwrsrc_ntfy);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.c b/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.c
index 087012b18956..094551d8ad9b 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.c
@@ -20,8 +20,10 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  * Authors: Ben Skeggs
+ *          Roy Spliet
  */
 
+#include <engine/fifo.h>
 #include <subdev/bios.h>
 #include <subdev/bios/pll.h>
 #include <subdev/timer.h>
@@ -42,9 +44,17 @@ static u32
 read_vco(struct nva3_clock_priv *priv, int clk)
 {
 	u32 sctl = nv_rd32(priv, 0x4120 + (clk * 4));
-	if ((sctl & 0x00000030) != 0x00000030)
+
+	switch (sctl & 0x00000030) {
+	case 0x00000000:
+		return nv_device(priv)->crystal;
+	case 0x00000020:
 		return read_pll(priv, 0x41, 0x00e820);
-	return read_pll(priv, 0x42, 0x00e8a0);
+	case 0x00000030:
+		return read_pll(priv, 0x42, 0x00e8a0);
+	default:
+		return 0;
+	}
 }
 
 static u32
@@ -66,14 +76,25 @@ read_clk(struct nva3_clock_priv *priv, int clk, bool ignore_en)
 	if (!ignore_en && !(sctl & 0x00000100))
 		return 0;
 
+	/* out_alt */
+	if (sctl & 0x00000400)
+		return 108000;
+
+	/* vco_out */
 	switch (sctl & 0x00003000) {
 	case 0x00000000:
-		return nv_device(priv)->crystal;
+		if (!(sctl & 0x00000200))
+			return nv_device(priv)->crystal;
+		return 0;
 	case 0x00002000:
 		if (sctl & 0x00000040)
 			return 108000;
 		return 100000;
 	case 0x00003000:
+		/* vco_enable */
+		if (!(sctl & 0x00000001))
+			return 0;
+
 		sclk = read_vco(priv, clk);
 		sdiv = ((sctl & 0x003f0000) >> 16) + 2;
 		return (sclk * 2) / sdiv;
@@ -95,7 +116,9 @@ read_pll(struct nva3_clock_priv *priv, int clk, u32 pll)
 			N = (coef & 0x0000ff00) >> 8;
 			P = (coef & 0x003f0000) >> 16;
 
-			/* no post-divider on these.. */
+			/* no post-divider on these..
+			 * XXX: it looks more like two post-"dividers" that
+			 * cross each other out in the default RPLL config */
 			if ((pll & 0x00ff00) == 0x00e800)
 				P = 1;
 
@@ -114,13 +137,13 @@ static int
 nva3_clock_read(struct nouveau_clock *clk, enum nv_clk_src src)
 {
 	struct nva3_clock_priv *priv = (void *)clk;
+	u32 hsrc;
 
 	switch (src) {
 	case nv_clk_src_crystal:
 		return nv_device(priv)->crystal;
-	case nv_clk_src_href:
-		return 100000;
 	case nv_clk_src_core:
+	case nv_clk_src_core_intm:
 		return read_pll(priv, 0x00, 0x4200);
 	case nv_clk_src_shader:
 		return read_pll(priv, 0x01, 0x4220);
@@ -132,24 +155,33 @@ nva3_clock_read(struct nouveau_clock *clk, enum nv_clk_src src)
 		return read_clk(priv, 0x21, false);
 	case nv_clk_src_daemon:
 		return read_clk(priv, 0x25, false);
+	case nv_clk_src_host:
+		hsrc = (nv_rd32(priv, 0xc040) & 0x30000000) >> 28;
+		switch (hsrc) {
+		case 0:
+			return read_clk(priv, 0x1d, false);
+		case 2:
+		case 3:
+			return 277000;
+		default:
+			nv_error(clk, "unknown HOST clock source %d\n", hsrc);
+			return -EINVAL;
+		}
 	default:
 		nv_error(clk, "invalid clock source %d\n", src);
 		return -EINVAL;
 	}
+
+	return 0;
 }
 
 int
-nva3_clock_info(struct nouveau_clock *clock, int clk, u32 pll, u32 khz,
+nva3_clk_info(struct nouveau_clock *clock, int clk, u32 khz,
 		struct nva3_clock_info *info)
 {
-	struct nouveau_bios *bios = nouveau_bios(clock);
 	struct nva3_clock_priv *priv = (void *)clock;
-	struct nvbios_pll limits;
-	u32 oclk, sclk, sdiv;
-	int P, N, M, diff;
-	int ret;
+	u32 oclk, sclk, sdiv, diff;
 
-	info->pll = 0;
 	info->clk = 0;
 
 	switch (khz) {
@@ -164,43 +196,69 @@ nva3_clock_info(struct nouveau_clock *clock, int clk, u32 pll, u32 khz,
 		return khz;
 	default:
 		sclk = read_vco(priv, clk);
-		sdiv = min((sclk * 2) / (khz - 2999), (u32)65);
-		/* if the clock has a PLL attached, and we can get a within
-		 * [-2, 3) MHz of a divider, we'll disable the PLL and use
-		 * the divider instead.
-		 *
-		 * divider can go as low as 2, limited here because NVIDIA
+		sdiv = min((sclk * 2) / khz, (u32)65);
+		oclk = (sclk * 2) / sdiv;
+		diff = ((khz + 3000) - oclk);
+
+		/* When imprecise, play it safe and aim for a clock lower than
+		 * desired rather than higher */
+		if (diff < 0) {
+			sdiv++;
+			oclk = (sclk * 2) / sdiv;
+		}
+
+		/* divider can go as low as 2, limited here because NVIDIA
 		 * and the VBIOS on my NVA8 seem to prefer using the PLL
 		 * for 810MHz - is there a good reason?
-		 */
+		 * XXX: PLLs with refclk 810MHz?  */
 		if (sdiv > 4) {
-			oclk = (sclk * 2) / sdiv;
-			diff = khz - oclk;
-			if (!pll || (diff >= -2000 && diff < 3000)) {
-				info->clk = (((sdiv - 2) << 16) | 0x00003100);
-				return oclk;
-			}
+			info->clk = (((sdiv - 2) << 16) | 0x00003100);
+			return oclk;
 		}
 
-		if (!pll)
-			return -ERANGE;
 		break;
 	}
 
+	return -ERANGE;
+}
+
+int
+nva3_pll_info(struct nouveau_clock *clock, int clk, u32 pll, u32 khz,
+		struct nva3_clock_info *info)
+{
+	struct nouveau_bios *bios = nouveau_bios(clock);
+	struct nva3_clock_priv *priv = (void *)clock;
+	struct nvbios_pll limits;
+	int P, N, M, diff;
+	int ret;
+
+	info->pll = 0;
+
+	/* If we can get a within [-2, 3) MHz of a divider, we'll disable the
+	 * PLL and use the divider instead. */
+	ret = nva3_clk_info(clock, clk, khz, info);
+	diff = khz - ret;
+	if (!pll || (diff >= -2000 && diff < 3000)) {
+		goto out;
+	}
+
+	/* Try with PLL */
 	ret = nvbios_pll_parse(bios, pll, &limits);
 	if (ret)
 		return ret;
 
-	limits.refclk = read_clk(priv, clk - 0x10, true);
-	if (!limits.refclk)
+	ret = nva3_clk_info(clock, clk - 0x10, limits.refclk, info);
+	if (ret != limits.refclk)
 		return -EINVAL;
 
 	ret = nva3_pll_calc(nv_subdev(priv), &limits, khz, &N, NULL, &M, &P);
 	if (ret >= 0) {
-		info->clk = nv_rd32(priv, 0x4120 + (clk * 4));
 		info->pll = (P << 16) | (N << 8) | M;
 	}
 
+out:
+	info->fb_delay = max(((khz + 7566) / 15133), (u32) 18);
+
 	return ret ? ret : -ERANGE;
 }
 
@@ -208,13 +266,76 @@ static int
 calc_clk(struct nva3_clock_priv *priv, struct nouveau_cstate *cstate,
 	 int clk, u32 pll, int idx)
 {
-	int ret = nva3_clock_info(&priv->base, clk, pll, cstate->domain[idx],
+	int ret = nva3_pll_info(&priv->base, clk, pll, cstate->domain[idx],
 				  &priv->eng[idx]);
 	if (ret >= 0)
 		return 0;
 	return ret;
 }
 
+static int
+calc_host(struct nva3_clock_priv *priv, struct nouveau_cstate *cstate)
+{
+	int ret = 0;
+	u32 kHz = cstate->domain[nv_clk_src_host];
+	struct nva3_clock_info *info = &priv->eng[nv_clk_src_host];
+
+	if (kHz == 277000) {
+		info->clk = 0;
+		info->host_out = NVA3_HOST_277;
+		return 0;
+	}
+
+	info->host_out = NVA3_HOST_CLK;
+
+	ret = nva3_clk_info(&priv->base, 0x1d, kHz, info);
+	if (ret >= 0)
+		return 0;
+	return ret;
+}
+
+int
+nva3_clock_pre(struct nouveau_clock *clk, unsigned long *flags)
+{
+	struct nouveau_fifo *pfifo = nouveau_fifo(clk);
+
+	/* halt and idle execution engines */
+	nv_mask(clk, 0x020060, 0x00070000, 0x00000000);
+	nv_mask(clk, 0x002504, 0x00000001, 0x00000001);
+	/* Wait until the interrupt handler is finished */
+	if (!nv_wait(clk, 0x000100, 0xffffffff, 0x00000000))
+		return -EBUSY;
+
+	if (pfifo)
+		pfifo->pause(pfifo, flags);
+
+	if (!nv_wait(clk, 0x002504, 0x00000010, 0x00000010))
+		return -EIO;
+	if (!nv_wait(clk, 0x00251c, 0x0000003f, 0x0000003f))
+		return -EIO;
+
+	return 0;
+}
+
+void
+nva3_clock_post(struct nouveau_clock *clk, unsigned long *flags)
+{
+	struct nouveau_fifo *pfifo = nouveau_fifo(clk);
+
+	if (pfifo && flags)
+		pfifo->start(pfifo, flags);
+
+	nv_mask(clk, 0x002504, 0x00000001, 0x00000000);
+	nv_mask(clk, 0x020060, 0x00070000, 0x00040000);
+}
+
+static void
+disable_clk_src(struct nva3_clock_priv *priv, u32 src)
+{
+	nv_mask(priv, src, 0x00000100, 0x00000000);
+	nv_mask(priv, src, 0x00000001, 0x00000000);
+}
+
 static void
 prog_pll(struct nva3_clock_priv *priv, int clk, u32 pll, int idx)
 {
@@ -223,24 +344,35 @@ prog_pll(struct nva3_clock_priv *priv, int clk, u32 pll, int idx)
 	const u32 src1 = 0x004160 + (clk * 4);
 	const u32 ctrl = pll + 0;
 	const u32 coef = pll + 4;
+	u32 bypass;
 
 	if (info->pll) {
-		nv_mask(priv, src0, 0x00000101, 0x00000101);
+		/* Always start from a non-PLL clock */
+		bypass = nv_rd32(priv, ctrl)  & 0x00000008;
+		if (!bypass) {
+			nv_mask(priv, src1, 0x00000101, 0x00000101);
+			nv_mask(priv, ctrl, 0x00000008, 0x00000008);
+			udelay(20);
+		}
+
+		nv_mask(priv, src0, 0x003f3141, 0x00000101 | info->clk);
 		nv_wr32(priv, coef, info->pll);
 		nv_mask(priv, ctrl, 0x00000015, 0x00000015);
 		nv_mask(priv, ctrl, 0x00000010, 0x00000000);
-		nv_wait(priv, ctrl, 0x00020000, 0x00020000);
+		if (!nv_wait(priv, ctrl, 0x00020000, 0x00020000)) {
+			nv_mask(priv, ctrl, 0x00000010, 0x00000010);
+			nv_mask(priv, src0, 0x00000101, 0x00000000);
+			return;
+		}
 		nv_mask(priv, ctrl, 0x00000010, 0x00000010);
 		nv_mask(priv, ctrl, 0x00000008, 0x00000000);
-		nv_mask(priv, src1, 0x00000100, 0x00000000);
-		nv_mask(priv, src1, 0x00000001, 0x00000000);
+		disable_clk_src(priv, src1);
 	} else {
 		nv_mask(priv, src1, 0x003f3141, 0x00000101 | info->clk);
 		nv_mask(priv, ctrl, 0x00000018, 0x00000018);
 		udelay(20);
 		nv_mask(priv, ctrl, 0x00000001, 0x00000000);
-		nv_mask(priv, src0, 0x00000100, 0x00000000);
-		nv_mask(priv, src0, 0x00000001, 0x00000000);
+		disable_clk_src(priv, src0);
 	}
 }
 
@@ -251,18 +383,72 @@ prog_clk(struct nva3_clock_priv *priv, int clk, int idx)
 	nv_mask(priv, 0x004120 + (clk * 4), 0x003f3141, 0x00000101 | info->clk);
 }
 
+static void
+prog_host(struct nva3_clock_priv *priv)
+{
+	struct nva3_clock_info *info = &priv->eng[nv_clk_src_host];
+	u32 hsrc = (nv_rd32(priv, 0xc040));
+
+	switch (info->host_out) {
+	case NVA3_HOST_277:
+		if ((hsrc & 0x30000000) == 0) {
+			nv_wr32(priv, 0xc040, hsrc | 0x20000000);
+			disable_clk_src(priv, 0x4194);
+		}
+		break;
+	case NVA3_HOST_CLK:
+		prog_clk(priv, 0x1d, nv_clk_src_host);
+		if ((hsrc & 0x30000000) >= 0x20000000) {
+			nv_wr32(priv, 0xc040, hsrc & ~0x30000000);
+		}
+		break;
+	default:
+		break;
+	}
+
+	/* This seems to be a clock gating factor on idle, always set to 64 */
+	nv_wr32(priv, 0xc044, 0x3e);
+}
+
+static void
+prog_core(struct nva3_clock_priv *priv, int idx)
+{
+	struct nva3_clock_info *info = &priv->eng[idx];
+	u32 fb_delay = nv_rd32(priv, 0x10002c);
+
+	if (fb_delay < info->fb_delay)
+		nv_wr32(priv, 0x10002c, info->fb_delay);
+
+	prog_pll(priv, 0x00, 0x004200, idx);
+
+	if (fb_delay > info->fb_delay)
+		nv_wr32(priv, 0x10002c, info->fb_delay);
+}
+
 static int
 nva3_clock_calc(struct nouveau_clock *clk, struct nouveau_cstate *cstate)
 {
 	struct nva3_clock_priv *priv = (void *)clk;
+	struct nva3_clock_info *core = &priv->eng[nv_clk_src_core];
 	int ret;
 
 	if ((ret = calc_clk(priv, cstate, 0x10, 0x4200, nv_clk_src_core)) ||
 	    (ret = calc_clk(priv, cstate, 0x11, 0x4220, nv_clk_src_shader)) ||
 	    (ret = calc_clk(priv, cstate, 0x20, 0x0000, nv_clk_src_disp)) ||
-	    (ret = calc_clk(priv, cstate, 0x21, 0x0000, nv_clk_src_vdec)))
+	    (ret = calc_clk(priv, cstate, 0x21, 0x0000, nv_clk_src_vdec)) ||
+	    (ret = calc_host(priv, cstate)))
 		return ret;
 
+	/* XXX: Should be reading the highest bit in the VBIOS clock to decide
+	 * whether to use a PLL or not... but using a PLL defeats the purpose */
+	if (core->pll) {
+		ret = nva3_clk_info(clk, 0x10,
+				cstate->domain[nv_clk_src_core_intm],
+				&priv->eng[nv_clk_src_core_intm]);
+		if (ret < 0)
+			return ret;
+	}
+
 	return 0;
 }
 
@@ -270,11 +456,31 @@ static int
 nva3_clock_prog(struct nouveau_clock *clk)
 {
 	struct nva3_clock_priv *priv = (void *)clk;
-	prog_pll(priv, 0x00, 0x004200, nv_clk_src_core);
+	struct nva3_clock_info *core = &priv->eng[nv_clk_src_core];
+	int ret = 0;
+	unsigned long flags;
+	unsigned long *f = &flags;
+
+	ret = nva3_clock_pre(clk, f);
+	if (ret)
+		goto out;
+
+	if (core->pll)
+		prog_core(priv, nv_clk_src_core_intm);
+
+	prog_core(priv,  nv_clk_src_core);
 	prog_pll(priv, 0x01, 0x004220, nv_clk_src_shader);
 	prog_clk(priv, 0x20, nv_clk_src_disp);
 	prog_clk(priv, 0x21, nv_clk_src_vdec);
-	return 0;
+	prog_host(priv);
+
+out:
+	if (ret == -EBUSY)
+		f = NULL;
+
+	nva3_clock_post(clk, f);
+
+	return ret;
 }
 
 static void
@@ -284,13 +490,14 @@ nva3_clock_tidy(struct nouveau_clock *clk)
 
 static struct nouveau_clocks
 nva3_domain[] = {
-	{ nv_clk_src_crystal, 0xff },
-	{ nv_clk_src_href   , 0xff },
-	{ nv_clk_src_core   , 0x00, 0, "core", 1000 },
-	{ nv_clk_src_shader , 0x01, 0, "shader", 1000 },
-	{ nv_clk_src_mem    , 0x02, 0, "memory", 1000 },
-	{ nv_clk_src_vdec   , 0x03 },
-	{ nv_clk_src_disp   , 0x04 },
+	{ nv_clk_src_crystal  , 0xff },
+	{ nv_clk_src_core     , 0x00, 0, "core", 1000 },
+	{ nv_clk_src_shader   , 0x01, 0, "shader", 1000 },
+	{ nv_clk_src_mem      , 0x02, 0, "memory", 1000 },
+	{ nv_clk_src_vdec     , 0x03 },
+	{ nv_clk_src_disp     , 0x04 },
+	{ nv_clk_src_host     , 0x05 },
+	{ nv_clk_src_core_intm, 0x06 },
 	{ nv_clk_src_max }
 };
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.h b/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.h
index 6229a509b42e..a45a1038b12f 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.h
@@ -6,9 +6,15 @@
 struct nva3_clock_info {
 	u32 clk;
 	u32 pll;
+	enum {
+		NVA3_HOST_277,
+		NVA3_HOST_CLK,
+	} host_out;
+	u32 fb_delay;
 };
 
-int nva3_clock_info(struct nouveau_clock *, int, u32, u32,
+int nva3_pll_info(struct nouveau_clock *, int, u32, u32,
 		    struct nva3_clock_info *);
-
+int nva3_clock_pre(struct nouveau_clock *clk, unsigned long *flags);
+void nva3_clock_post(struct nouveau_clock *clk, unsigned long *flags);
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/nvaa.c b/drivers/gpu/drm/nouveau/core/subdev/clock/nvaa.c
index 74e19731b1b7..54aeab8005a0 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/nvaa.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/nvaa.c
@@ -28,6 +28,7 @@
 #include <subdev/timer.h>
 #include <subdev/clock.h>
 
+#include "nva3.h"
 #include "pll.h"
 
 struct nvaa_clock_priv {
@@ -299,25 +300,14 @@ static int
 nvaa_clock_prog(struct nouveau_clock *clk)
 {
 	struct nvaa_clock_priv *priv = (void *)clk;
-	struct nouveau_fifo *pfifo = nouveau_fifo(clk);
+	u32 pllmask = 0, mast;
 	unsigned long flags;
-	u32 pllmask = 0, mast, ptherm_gate;
-	int ret = -EBUSY;
-
-	/* halt and idle execution engines */
-	ptherm_gate = nv_mask(clk, 0x020060, 0x00070000, 0x00000000);
-	nv_mask(clk, 0x002504, 0x00000001, 0x00000001);
-	/* Wait until the interrupt handler is finished */
-	if (!nv_wait(clk, 0x000100, 0xffffffff, 0x00000000))
-		goto resume;
-
-	if (pfifo)
-		pfifo->pause(pfifo, &flags);
+	unsigned long *f = &flags;
+	int ret = 0;
 
-	if (!nv_wait(clk, 0x002504, 0x00000010, 0x00000010))
-		goto resume;
-	if (!nv_wait(clk, 0x00251c, 0x0000003f, 0x0000003f))
-		goto resume;
+	ret = nva3_clock_pre(clk, f);
+	if (ret)
+		goto out;
 
 	/* First switch to safe clocks: href */
 	mast = nv_mask(clk, 0xc054, 0x03400e70, 0x03400640);
@@ -375,15 +365,8 @@ nvaa_clock_prog(struct nouveau_clock *clk)
 	}
 
 	nv_wr32(clk, 0xc054, mast);
-	ret = 0;
 
 resume:
-	if (pfifo)
-		pfifo->start(pfifo, &flags);
-
-	nv_mask(clk, 0x002504, 0x00000001, 0x00000000);
-	nv_wr32(clk, 0x020060, ptherm_gate);
-
 	/* Disable some PLLs and dividers when unused */
 	if (priv->csrc != nv_clk_src_core) {
 		nv_wr32(clk, 0x4040, 0x00000000);
@@ -395,6 +378,12 @@ resume:
 		nv_mask(clk, 0x4020, 0x80000000, 0x00000000);
 	}
 
+out:
+	if (ret == -EBUSY)
+		f = NULL;
+
+	nva3_clock_post(clk, f);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/devinit/fbmem.h b/drivers/gpu/drm/nouveau/core/subdev/devinit/fbmem.h
index 4fe49cf4c99a..6103484fea72 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/devinit/fbmem.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/devinit/fbmem.h
@@ -26,22 +26,8 @@
 
 #include <core/device.h>
 
-#define NV04_PFB_BOOT_0						0x00100000
-#	define NV04_PFB_BOOT_0_RAM_AMOUNT			0x00000003
-#	define NV04_PFB_BOOT_0_RAM_AMOUNT_32MB			0x00000000
-#	define NV04_PFB_BOOT_0_RAM_AMOUNT_4MB			0x00000001
-#	define NV04_PFB_BOOT_0_RAM_AMOUNT_8MB			0x00000002
-#	define NV04_PFB_BOOT_0_RAM_AMOUNT_16MB			0x00000003
-#	define NV04_PFB_BOOT_0_RAM_WIDTH_128			0x00000004
-#	define NV04_PFB_BOOT_0_RAM_TYPE				0x00000028
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_8MBIT		0x00000000
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_16MBIT		0x00000008
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_16MBIT_4BANK	0x00000010
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_16MBIT		0x00000018
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_64MBIT		0x00000020
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_64MBITX16		0x00000028
-#	define NV04_PFB_BOOT_0_UMA_ENABLE			0x00000100
-#	define NV04_PFB_BOOT_0_UMA_SIZE				0x0000f000
+#include <subdev/fb/regsnv04.h>
+
 #define NV04_PFB_DEBUG_0					0x00100080
 #	define NV04_PFB_DEBUG_0_PAGE_MODE			0x00000001
 #	define NV04_PFB_DEBUG_0_REFRESH_OFF			0x00000010
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/gddr5.c b/drivers/gpu/drm/nouveau/core/subdev/fb/gddr5.c
index 66fe959b4f74..7fbbe05d5c60 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/gddr5.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/gddr5.c
@@ -40,7 +40,7 @@ nouveau_gddr5_calc(struct nouveau_ram *ram, bool nuts)
 	int WL, CL, WR, at[2], dt, ds;
 	int rq = ram->freq < 1000000; /* XXX */
 
-	switch (ram->ramcfg.version) {
+	switch (ram->next->bios.ramcfg_ver) {
 	case 0x11:
 		pd =  ram->next->bios.ramcfg_11_01_80;
 		lf =  ram->next->bios.ramcfg_11_01_40;
@@ -54,7 +54,7 @@ nouveau_gddr5_calc(struct nouveau_ram *ram, bool nuts)
 		return -ENOSYS;
 	}
 
-	switch (ram->timing.version) {
+	switch (ram->next->bios.timing_ver) {
 	case 0x20:
 		WL = (ram->next->bios.timing[1] & 0x00000f80) >> 7;
 		CL = (ram->next->bios.timing[1] & 0x0000001f);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv20.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv20.c
index f003c1b1893f..2209ade63339 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv20.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv20.c
@@ -45,7 +45,7 @@ nv20_fb_tile_comp(struct nouveau_fb *pfb, int i, u32 size, u32 flags,
 {
 	u32 tiles = DIV_ROUND_UP(size, 0x40);
 	u32 tags  = round_up(tiles / pfb->ram->parts, 0x40);
-	if (!nouveau_mm_head(&pfb->tags, 1, tags, tags, 1, &tile->tag)) {
+	if (!nouveau_mm_head(&pfb->tags, 0, 1, tags, tags, 1, &tile->tag)) {
 		if (!(flags & 2)) tile->zcomp = 0x00000000; /* Z16 */
 		else              tile->zcomp = 0x04000000; /* Z24S8 */
 		tile->zcomp |= tile->tag->offset;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv25.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv25.c
index f34f4223210b..e2a66c355c50 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv25.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv25.c
@@ -32,7 +32,7 @@ nv25_fb_tile_comp(struct nouveau_fb *pfb, int i, u32 size, u32 flags,
 {
 	u32 tiles = DIV_ROUND_UP(size, 0x40);
 	u32 tags  = round_up(tiles / pfb->ram->parts, 0x40);
-	if (!nouveau_mm_head(&pfb->tags, 1, tags, tags, 1, &tile->tag)) {
+	if (!nouveau_mm_head(&pfb->tags, 0, 1, tags, tags, 1, &tile->tag)) {
 		if (!(flags & 2)) tile->zcomp = 0x00100000; /* Z16 */
 		else              tile->zcomp = 0x00200000; /* Z24S8 */
 		tile->zcomp |= tile->tag->offset;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv30.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv30.c
index 69093f7151f0..cbec402ba5b9 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv30.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv30.c
@@ -51,7 +51,7 @@ nv30_fb_tile_comp(struct nouveau_fb *pfb, int i, u32 size, u32 flags,
 {
 	u32 tiles = DIV_ROUND_UP(size, 0x40);
 	u32 tags  = round_up(tiles / pfb->ram->parts, 0x40);
-	if (!nouveau_mm_head(&pfb->tags, 1, tags, tags, 1, &tile->tag)) {
+	if (!nouveau_mm_head(&pfb->tags, 0, 1, tags, tags, 1, &tile->tag)) {
 		if (flags & 2) tile->zcomp |= 0x01000000; /* Z16 */
 		else           tile->zcomp |= 0x02000000; /* Z24S8 */
 		tile->zcomp |= ((tile->tag->offset           ) >> 6);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv35.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv35.c
index 161b06e8fc3f..b2cf8c69fb2e 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv35.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv35.c
@@ -32,7 +32,7 @@ nv35_fb_tile_comp(struct nouveau_fb *pfb, int i, u32 size, u32 flags,
 {
 	u32 tiles = DIV_ROUND_UP(size, 0x40);
 	u32 tags  = round_up(tiles / pfb->ram->parts, 0x40);
-	if (!nouveau_mm_head(&pfb->tags, 1, tags, tags, 1, &tile->tag)) {
+	if (!nouveau_mm_head(&pfb->tags, 0, 1, tags, tags, 1, &tile->tag)) {
 		if (flags & 2) tile->zcomp |= 0x04000000; /* Z16 */
 		else           tile->zcomp |= 0x08000000; /* Z24S8 */
 		tile->zcomp |= ((tile->tag->offset           ) >> 6);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv36.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv36.c
index 2dd3d0aab6bb..b4cdae2a3b2f 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv36.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv36.c
@@ -32,7 +32,7 @@ nv36_fb_tile_comp(struct nouveau_fb *pfb, int i, u32 size, u32 flags,
 {
 	u32 tiles = DIV_ROUND_UP(size, 0x40);
 	u32 tags  = round_up(tiles / pfb->ram->parts, 0x40);
-	if (!nouveau_mm_head(&pfb->tags, 1, tags, tags, 1, &tile->tag)) {
+	if (!nouveau_mm_head(&pfb->tags, 0, 1, tags, tags, 1, &tile->tag)) {
 		if (flags & 2) tile->zcomp |= 0x10000000; /* Z16 */
 		else           tile->zcomp |= 0x20000000; /* Z24S8 */
 		tile->zcomp |= ((tile->tag->offset           ) >> 6);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv40.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv40.c
index 95a115ab0c86..52814258c212 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv40.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv40.c
@@ -33,7 +33,7 @@ nv40_fb_tile_comp(struct nouveau_fb *pfb, int i, u32 size, u32 flags,
 	u32 tiles = DIV_ROUND_UP(size, 0x80);
 	u32 tags  = round_up(tiles / pfb->ram->parts, 0x100);
 	if ( (flags & 2) &&
-	    !nouveau_mm_head(&pfb->tags, 1, tags, tags, 1, &tile->tag)) {
+	    !nouveau_mm_head(&pfb->tags, 0, 1, tags, tags, 1, &tile->tag)) {
 		tile->zcomp  = 0x28000000; /* Z24S8_SPLIT_GRAD */
 		tile->zcomp |= ((tile->tag->offset           ) >> 8);
 		tile->zcomp |= ((tile->tag->offset + tags - 1) >> 8) << 13;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h
index 82273f832e42..60322e906dd4 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h
@@ -35,6 +35,7 @@ extern struct nouveau_oclass nve0_ram_oclass;
 extern struct nouveau_oclass gk20a_ram_oclass;
 extern struct nouveau_oclass gm107_ram_oclass;
 
+int nouveau_sddr2_calc(struct nouveau_ram *ram);
 int nouveau_sddr3_calc(struct nouveau_ram *ram);
 int nouveau_gddr5_calc(struct nouveau_ram *ram, bool nuts);
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramfuc.h b/drivers/gpu/drm/nouveau/core/subdev/fb/ramfuc.h
index 2af9cfd2c60f..d1fbbe4b00a2 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramfuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramfuc.h
@@ -12,16 +12,32 @@ struct ramfuc {
 struct ramfuc_reg {
 	int sequence;
 	bool force;
-	u32 addr[2];
+	u32 addr;
+	u32 stride; /* in bytes */
+	u32 mask;
 	u32 data;
 };
 
 static inline struct ramfuc_reg
+ramfuc_stride(u32 addr, u32 stride, u32 mask)
+{
+	return (struct ramfuc_reg) {
+		.sequence = 0,
+		.addr = addr,
+		.stride = stride,
+		.mask = mask,
+		.data = 0xdeadbeef,
+	};
+}
+
+static inline struct ramfuc_reg
 ramfuc_reg2(u32 addr1, u32 addr2)
 {
 	return (struct ramfuc_reg) {
 		.sequence = 0,
-		.addr = { addr1, addr2 },
+		.addr = addr1,
+		.stride = addr2 - addr1,
+		.mask = 0x3,
 		.data = 0xdeadbeef,
 	};
 }
@@ -29,7 +45,13 @@ ramfuc_reg2(u32 addr1, u32 addr2)
 static noinline struct ramfuc_reg
 ramfuc_reg(u32 addr)
 {
-	return ramfuc_reg2(addr, addr);
+	return (struct ramfuc_reg) {
+		.sequence = 0,
+		.addr = addr,
+		.stride = 0,
+		.mask = 0x1,
+		.data = 0xdeadbeef,
+	};
 }
 
 static inline int
@@ -62,18 +84,25 @@ static inline u32
 ramfuc_rd32(struct ramfuc *ram, struct ramfuc_reg *reg)
 {
 	if (reg->sequence != ram->sequence)
-		reg->data = nv_rd32(ram->pfb, reg->addr[0]);
+		reg->data = nv_rd32(ram->pfb, reg->addr);
 	return reg->data;
 }
 
 static inline void
 ramfuc_wr32(struct ramfuc *ram, struct ramfuc_reg *reg, u32 data)
 {
+	unsigned int mask, off = 0;
+
 	reg->sequence = ram->sequence;
 	reg->data = data;
-	if (reg->addr[0] != reg->addr[1])
-		nouveau_memx_wr32(ram->memx, reg->addr[1], reg->data);
-	nouveau_memx_wr32(ram->memx, reg->addr[0], reg->data);
+
+	for (mask = reg->mask; mask > 0; mask = (mask & ~1) >> 1) {
+		if (mask & 1) {
+			nouveau_memx_wr32(ram->memx, reg->addr+off, reg->data);
+		}
+
+		off += reg->stride;
+	}
 }
 
 static inline void
@@ -105,14 +134,35 @@ ramfuc_nsec(struct ramfuc *ram, u32 nsec)
 	nouveau_memx_nsec(ram->memx, nsec);
 }
 
-#define ram_init(s,p)       ramfuc_init(&(s)->base, (p))
-#define ram_exec(s,e)       ramfuc_exec(&(s)->base, (e))
-#define ram_have(s,r)       ((s)->r_##r.addr[0] != 0x000000)
-#define ram_rd32(s,r)       ramfuc_rd32(&(s)->base, &(s)->r_##r)
-#define ram_wr32(s,r,d)     ramfuc_wr32(&(s)->base, &(s)->r_##r, (d))
-#define ram_nuke(s,r)       ramfuc_nuke(&(s)->base, &(s)->r_##r)
-#define ram_mask(s,r,m,d)   ramfuc_mask(&(s)->base, &(s)->r_##r, (m), (d))
-#define ram_wait(s,r,m,d,n) ramfuc_wait(&(s)->base, (r), (m), (d), (n))
-#define ram_nsec(s,n)       ramfuc_nsec(&(s)->base, (n))
+static inline void
+ramfuc_wait_vblank(struct ramfuc *ram)
+{
+	nouveau_memx_wait_vblank(ram->memx);
+}
+
+static inline void
+ramfuc_block(struct ramfuc *ram)
+{
+	nouveau_memx_block(ram->memx);
+}
+
+static inline void
+ramfuc_unblock(struct ramfuc *ram)
+{
+	nouveau_memx_unblock(ram->memx);
+}
+
+#define ram_init(s,p)        ramfuc_init(&(s)->base, (p))
+#define ram_exec(s,e)        ramfuc_exec(&(s)->base, (e))
+#define ram_have(s,r)        ((s)->r_##r.addr != 0x000000)
+#define ram_rd32(s,r)        ramfuc_rd32(&(s)->base, &(s)->r_##r)
+#define ram_wr32(s,r,d)      ramfuc_wr32(&(s)->base, &(s)->r_##r, (d))
+#define ram_nuke(s,r)        ramfuc_nuke(&(s)->base, &(s)->r_##r)
+#define ram_mask(s,r,m,d)    ramfuc_mask(&(s)->base, &(s)->r_##r, (m), (d))
+#define ram_wait(s,r,m,d,n)  ramfuc_wait(&(s)->base, (r), (m), (d), (n))
+#define ram_nsec(s,n)        ramfuc_nsec(&(s)->base, (n))
+#define ram_wait_vblank(s)   ramfuc_wait_vblank(&(s)->base)
+#define ram_block(s)         ramfuc_block(&(s)->base)
+#define ram_unblock(s)       ramfuc_unblock(&(s)->base)
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv04.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv04.c
index e781080d3327..1972268d1410 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv04.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv04.c
@@ -22,22 +22,7 @@
  * Authors: Ben Skeggs
  */
 
-#define NV04_PFB_BOOT_0						0x00100000
-#	define NV04_PFB_BOOT_0_RAM_AMOUNT			0x00000003
-#	define NV04_PFB_BOOT_0_RAM_AMOUNT_32MB			0x00000000
-#	define NV04_PFB_BOOT_0_RAM_AMOUNT_4MB			0x00000001
-#	define NV04_PFB_BOOT_0_RAM_AMOUNT_8MB			0x00000002
-#	define NV04_PFB_BOOT_0_RAM_AMOUNT_16MB			0x00000003
-#	define NV04_PFB_BOOT_0_RAM_WIDTH_128			0x00000004
-#	define NV04_PFB_BOOT_0_RAM_TYPE				0x00000028
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_8MBIT		0x00000000
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_16MBIT		0x00000008
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_16MBIT_4BANK	0x00000010
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_16MBIT		0x00000018
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_64MBIT		0x00000020
-#	define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_64MBITX16		0x00000028
-#	define NV04_PFB_BOOT_0_UMA_ENABLE			0x00000100
-#	define NV04_PFB_BOOT_0_UMA_SIZE				0x0000f000
+#include <subdev/fb/regsnv04.h>
 
 #include "priv.h"
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c
index e5d12c24cc43..64a983c96625 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c
@@ -280,7 +280,7 @@ nv50_ram_get(struct nouveau_fb *pfb, u64 size, u32 align, u32 ncmin,
 		if (align == 16) {
 			int n = (max >> 4) * comp;
 
-			ret = nouveau_mm_head(tags, 1, n, n, 1, &mem->tag);
+			ret = nouveau_mm_head(tags, 0, 1, n, n, 1, &mem->tag);
 			if (ret)
 				mem->tag = NULL;
 		}
@@ -296,9 +296,9 @@ nv50_ram_get(struct nouveau_fb *pfb, u64 size, u32 align, u32 ncmin,
 	type = nv50_fb_memtype[type];
 	do {
 		if (back)
-			ret = nouveau_mm_tail(heap, type, max, min, align, &r);
+			ret = nouveau_mm_tail(heap, 0, type, max, min, align, &r);
 		else
-			ret = nouveau_mm_head(heap, type, max, min, align, &r);
+			ret = nouveau_mm_head(heap, 0, type, max, min, align, &r);
 		if (ret) {
 			mutex_unlock(&pfb->base.mutex);
 			pfb->ram->put(pfb, &mem);
@@ -319,27 +319,22 @@ nv50_ram_get(struct nouveau_fb *pfb, u64 size, u32 align, u32 ncmin,
 static u32
 nv50_fb_vram_rblock(struct nouveau_fb *pfb, struct nouveau_ram *ram)
 {
-	int i, parts, colbits, rowbitsa, rowbitsb, banks;
+	int colbits, rowbitsa, rowbitsb, banks;
 	u64 rowsize, predicted;
-	u32 r0, r4, rt, ru, rblock_size;
+	u32 r0, r4, rt, rblock_size;
 
 	r0 = nv_rd32(pfb, 0x100200);
 	r4 = nv_rd32(pfb, 0x100204);
 	rt = nv_rd32(pfb, 0x100250);
-	ru = nv_rd32(pfb, 0x001540);
-	nv_debug(pfb, "memcfg 0x%08x 0x%08x 0x%08x 0x%08x\n", r0, r4, rt, ru);
-
-	for (i = 0, parts = 0; i < 8; i++) {
-		if (ru & (0x00010000 << i))
-			parts++;
-	}
+	nv_debug(pfb, "memcfg 0x%08x 0x%08x 0x%08x 0x%08x\n", r0, r4, rt,
+			nv_rd32(pfb, 0x001540));
 
 	colbits  =  (r4 & 0x0000f000) >> 12;
 	rowbitsa = ((r4 & 0x000f0000) >> 16) + 8;
 	rowbitsb = ((r4 & 0x00f00000) >> 20) + 8;
 	banks    = 1 << (((r4 & 0x03000000) >> 24) + 2);
 
-	rowsize = parts * banks * (1 << colbits) * 8;
+	rowsize = ram->parts * banks * (1 << colbits) * 8;
 	predicted = rowsize << rowbitsa;
 	if (r0 & 0x00000004)
 		predicted += rowsize << rowbitsb;
@@ -376,6 +371,9 @@ nv50_ram_create_(struct nouveau_object *parent, struct nouveau_object *engine,
 	ram->size = nv_rd32(pfb, 0x10020c);
 	ram->size = (ram->size & 0xffffff00) | ((ram->size & 0x000000ff) << 32);
 
+	ram->part_mask = (nv_rd32(pfb, 0x001540) & 0x00ff0000) >> 16;
+	ram->parts = hweight8(ram->part_mask);
+
 	switch (nv_rd32(pfb, 0x100714) & 0x00000007) {
 	case 0: ram->type = NV_MEM_TYPE_DDR1; break;
 	case 1:
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnva3.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnva3.c
index 8076fb195dd5..3601deca0bd5 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnva3.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnva3.c
@@ -79,20 +79,27 @@ nva3_ram_calc(struct nouveau_fb *pfb, u32 freq)
 	struct nva3_ram *ram = (void *)pfb->ram;
 	struct nva3_ramfuc *fuc = &ram->fuc;
 	struct nva3_clock_info mclk;
-	u8  ver, cnt, len, strap;
+	struct nouveau_ram_data *next;
+	u8  ver, hdr, cnt, len, strap;
 	u32 data;
-	struct {
-		u32 data;
-		u8  size;
-	} rammap, ramcfg, timing;
 	u32 r004018, r100760, ctrl;
 	u32 unk714, unk718, unk71c;
-	int ret;
+	int ret, i;
+
+	next = &ram->base.target;
+	next->freq = freq;
+	ram->base.next = next;
 
 	/* lookup memory config data relevant to the target frequency */
-	rammap.data = nvbios_rammapEm(bios, freq / 1000, &ver, &rammap.size,
-				     &cnt, &ramcfg.size);
-	if (!rammap.data || ver != 0x10 || rammap.size < 0x0e) {
+	i = 0;
+	while ((data = nvbios_rammapEp(bios, i++, &ver, &hdr, &cnt, &len,
+				      &next->bios))) {
+		if (freq / 1000 >= next->bios.rammap_min &&
+		    freq / 1000 <= next->bios.rammap_max)
+			break;
+	}
+
+	if (!data || ver != 0x10 || hdr < 0x0e) {
 		nv_error(pfb, "invalid/missing rammap entry\n");
 		return -EINVAL;
 	}
@@ -104,26 +111,25 @@ nva3_ram_calc(struct nouveau_fb *pfb, u32 freq)
 		return -EINVAL;
 	}
 
-	ramcfg.data = rammap.data + rammap.size + (strap * ramcfg.size);
-	if (!ramcfg.data || ver != 0x10 || ramcfg.size < 0x0e) {
+	data = nvbios_rammapSp(bios, data, ver, hdr, cnt, len, strap,
+			       &ver, &hdr, &next->bios);
+	if (!data || ver != 0x10 || hdr < 0x0e) {
 		nv_error(pfb, "invalid/missing ramcfg entry\n");
 		return -EINVAL;
 	}
 
 	/* lookup memory timings, if bios says they're present */
-	strap = nv_ro08(bios, ramcfg.data + 0x01);
-	if (strap != 0xff) {
-		timing.data = nvbios_timingEe(bios, strap, &ver, &timing.size,
-					     &cnt, &len);
-		if (!timing.data || ver != 0x10 || timing.size < 0x19) {
+	if (next->bios.ramcfg_timing != 0xff) {
+		data = nvbios_timingEp(bios, next->bios.ramcfg_timing,
+				       &ver, &hdr, &cnt, &len,
+				       &next->bios);
+		if (!data || ver != 0x10 || hdr < 0x19) {
 			nv_error(pfb, "invalid/missing timing entry\n");
 			return -EINVAL;
 		}
-	} else {
-		timing.data = 0;
 	}
 
-	ret = nva3_clock_info(nouveau_clock(pfb), 0x12, 0x4000, freq, &mclk);
+	ret = nva3_pll_info(nouveau_clock(pfb), 0x12, 0x4000, freq, &mclk);
 	if (ret < 0) {
 		nv_error(pfb, "failed mclk calculation\n");
 		return ret;
@@ -163,17 +169,17 @@ nva3_ram_calc(struct nouveau_fb *pfb, u32 freq)
 		ram_mask(fuc, 0x004168, 0x003f3141, ctrl);
 	}
 
-	if ( (nv_ro08(bios, ramcfg.data + 0x02) & 0x10)) {
+	if (next->bios.ramcfg_10_02_10) {
 		ram_mask(fuc, 0x111104, 0x00000600, 0x00000000);
 	} else {
 		ram_mask(fuc, 0x111100, 0x40000000, 0x40000000);
 		ram_mask(fuc, 0x111104, 0x00000180, 0x00000000);
 	}
 
-	if (!(nv_ro08(bios, rammap.data + 0x04) & 0x02))
+	if (!next->bios.rammap_10_04_02)
 		ram_mask(fuc, 0x100200, 0x00000800, 0x00000000);
 	ram_wr32(fuc, 0x611200, 0x00003300);
-	if (!(nv_ro08(bios, ramcfg.data + 0x02) & 0x10))
+	if (!next->bios.ramcfg_10_02_10)
 		ram_wr32(fuc, 0x111100, 0x4c020000); /*XXX*/
 
 	ram_wr32(fuc, 0x1002d4, 0x00000001);
@@ -202,17 +208,16 @@ nva3_ram_calc(struct nouveau_fb *pfb, u32 freq)
 		ram_wr32(fuc, 0x004018, 0x0000d000 | r004018);
 	}
 
-	if ( (nv_ro08(bios, rammap.data + 0x04) & 0x08)) {
-		u32 unk5a0 = (nv_ro16(bios, ramcfg.data + 0x05) << 8) |
-			      nv_ro08(bios, ramcfg.data + 0x05);
-		u32 unk5a4 = (nv_ro16(bios, ramcfg.data + 0x07));
-		u32 unk804 = (nv_ro08(bios, ramcfg.data + 0x09) & 0xf0) << 16 |
-			     (nv_ro08(bios, ramcfg.data + 0x03) & 0x0f) << 16 |
-			     (nv_ro08(bios, ramcfg.data + 0x09) & 0x0f) |
-			     0x80000000;
-		ram_wr32(fuc, 0x1005a0, unk5a0);
-		ram_wr32(fuc, 0x1005a4, unk5a4);
-		ram_wr32(fuc, 0x10f804, unk804);
+	if (next->bios.rammap_10_04_08) {
+		ram_wr32(fuc, 0x1005a0, next->bios.ramcfg_10_06 << 16 |
+					next->bios.ramcfg_10_05 << 8 |
+					next->bios.ramcfg_10_05);
+		ram_wr32(fuc, 0x1005a4, next->bios.ramcfg_10_08 << 8 |
+					next->bios.ramcfg_10_07);
+		ram_wr32(fuc, 0x10f804, next->bios.ramcfg_10_09_f0 << 20 |
+					next->bios.ramcfg_10_03_0f << 16 |
+					next->bios.ramcfg_10_09_0f |
+					0x80000000);
 		ram_mask(fuc, 0x10053c, 0x00001000, 0x00000000);
 	} else {
 		ram_mask(fuc, 0x10053c, 0x00001000, 0x00001000);
@@ -250,27 +255,26 @@ nva3_ram_calc(struct nouveau_fb *pfb, u32 freq)
 	ram_mask(fuc, 0x100220[0], 0x00000000, 0x00000000);
 	ram_mask(fuc, 0x100220[8], 0x00000000, 0x00000000);
 
-	data = (nv_ro08(bios, ramcfg.data + 0x02) & 0x08) ? 0x00000000 : 0x00001000;
-	ram_mask(fuc, 0x100200, 0x00001000, data);
+	ram_mask(fuc, 0x100200, 0x00001000, !next->bios.ramcfg_10_02_08 << 12);
 
 	unk714 = ram_rd32(fuc, 0x100714) & ~0xf0000010;
 	unk718 = ram_rd32(fuc, 0x100718) & ~0x00000100;
 	unk71c = ram_rd32(fuc, 0x10071c) & ~0x00000100;
-	if ( (nv_ro08(bios, ramcfg.data + 0x02) & 0x20))
+	if (next->bios.ramcfg_10_02_20)
 		unk714 |= 0xf0000000;
-	if (!(nv_ro08(bios, ramcfg.data + 0x02) & 0x04))
+	if (!next->bios.ramcfg_10_02_04)
 		unk714 |= 0x00000010;
 	ram_wr32(fuc, 0x100714, unk714);
 
-	if (nv_ro08(bios, ramcfg.data + 0x02) & 0x01)
+	if (next->bios.ramcfg_10_02_01)
 		unk71c |= 0x00000100;
 	ram_wr32(fuc, 0x10071c, unk71c);
 
-	if (nv_ro08(bios, ramcfg.data + 0x02) & 0x02)
+	if (next->bios.ramcfg_10_02_02)
 		unk718 |= 0x00000100;
 	ram_wr32(fuc, 0x100718, unk718);
 
-	if (nv_ro08(bios, ramcfg.data + 0x02) & 0x10)
+	if (next->bios.ramcfg_10_02_10)
 		ram_wr32(fuc, 0x111100, 0x48000000); /*XXX*/
 
 	ram_mask(fuc, mr[0], 0x100, 0x100);
@@ -282,9 +286,9 @@ nva3_ram_calc(struct nouveau_fb *pfb, u32 freq)
 	ram_nsec(fuc, 12000);
 
 	ram_wr32(fuc, 0x611200, 0x00003330);
-	if ( (nv_ro08(bios, rammap.data + 0x04) & 0x02))
+	if (next->bios.rammap_10_04_02)
 		ram_mask(fuc, 0x100200, 0x00000800, 0x00000800);
-	if ( (nv_ro08(bios, ramcfg.data + 0x02) & 0x10)) {
+	if (next->bios.ramcfg_10_02_10) {
 		ram_mask(fuc, 0x111104, 0x00000180, 0x00000180);
 		ram_mask(fuc, 0x111100, 0x40000000, 0x00000000);
 	} else {
@@ -404,11 +408,11 @@ nva3_ram_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	ram->fuc.r_0x100714 = ramfuc_reg(0x100714);
 	ram->fuc.r_0x100718 = ramfuc_reg(0x100718);
 	ram->fuc.r_0x10071c = ramfuc_reg(0x10071c);
-	ram->fuc.r_0x100760 = ramfuc_reg(0x100760);
-	ram->fuc.r_0x1007a0 = ramfuc_reg(0x1007a0);
-	ram->fuc.r_0x1007e0 = ramfuc_reg(0x1007e0);
+	ram->fuc.r_0x100760 = ramfuc_stride(0x100760, 4, ram->base.part_mask);
+	ram->fuc.r_0x1007a0 = ramfuc_stride(0x1007a0, 4, ram->base.part_mask);
+	ram->fuc.r_0x1007e0 = ramfuc_stride(0x1007e0, 4, ram->base.part_mask);
 	ram->fuc.r_0x10f804 = ramfuc_reg(0x10f804);
-	ram->fuc.r_0x1110e0 = ramfuc_reg(0x1110e0);
+	ram->fuc.r_0x1110e0 = ramfuc_stride(0x1110e0, 4, ram->base.part_mask);
 	ram->fuc.r_0x111100 = ramfuc_reg(0x111100);
 	ram->fuc.r_0x111104 = ramfuc_reg(0x111104);
 	ram->fuc.r_0x611200 = ramfuc_reg(0x611200);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c
index 2b284b192763..735cb9580abe 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c
@@ -133,6 +133,7 @@ nvc0_ram_calc(struct nouveau_fb *pfb, u32 freq)
 	struct nouveau_bios *bios = nouveau_bios(pfb);
 	struct nvc0_ram *ram = (void *)pfb->ram;
 	struct nvc0_ramfuc *fuc = &ram->fuc;
+	struct nvbios_ramcfg cfg;
 	u8  ver, cnt, len, strap;
 	struct {
 		u32 data;
@@ -145,7 +146,7 @@ nvc0_ram_calc(struct nouveau_fb *pfb, u32 freq)
 
 	/* lookup memory config data relevant to the target frequency */
 	rammap.data = nvbios_rammapEm(bios, freq / 1000, &ver, &rammap.size,
-				     &cnt, &ramcfg.size);
+				     &cnt, &ramcfg.size, &cfg);
 	if (!rammap.data || ver != 0x10 || rammap.size < 0x0e) {
 		nv_error(pfb, "invalid/missing rammap entry\n");
 		return -EINVAL;
@@ -483,9 +484,9 @@ nvc0_ram_get(struct nouveau_fb *pfb, u64 size, u32 align, u32 ncmin,
 
 	do {
 		if (back)
-			ret = nouveau_mm_tail(mm, 1, size, ncmin, align, &r);
+			ret = nouveau_mm_tail(mm, 0, 1, size, ncmin, align, &r);
 		else
-			ret = nouveau_mm_head(mm, 1, size, ncmin, align, &r);
+			ret = nouveau_mm_head(mm, 0, 1, size, ncmin, align, &r);
 		if (ret) {
 			mutex_unlock(&pfb->base.mutex);
 			pfb->ram->put(pfb, &mem);
@@ -562,7 +563,7 @@ nvc0_ram_create_(struct nouveau_object *parent, struct nouveau_object *engine,
 		offset = (0x0200000000ULL >> 12) + (bsize << 8);
 		length = (ram->size >> 12) - ((bsize * parts) << 8) - rsvd_tail;
 
-		ret = nouveau_mm_init(&pfb->vram, offset, length, 0);
+		ret = nouveau_mm_init(&pfb->vram, offset, length, 1);
 		if (ret)
 			nouveau_mm_fini(&pfb->vram);
 	}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c
index c5b46e302319..6bae474abb44 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c
@@ -29,6 +29,8 @@
 #include <subdev/bios/init.h>
 #include <subdev/bios/rammap.h>
 #include <subdev/bios/timing.h>
+#include <subdev/bios/M0205.h>
+#include <subdev/bios/M0209.h>
 
 #include <subdev/clock.h>
 #include <subdev/clock/pll.h>
@@ -41,14 +43,6 @@
 
 #include "ramfuc.h"
 
-/* binary driver only executes this path if the condition (a) is true
- * for any configuration (combination of rammap+ramcfg+timing) that
- * can be reached on a given card.  for now, we will execute the branch
- * unconditionally in the hope that a "false everywhere" in the bios
- * tables doesn't actually mean "don't touch this".
- */
-#define NOTE00(a) 1
-
 struct nve0_ramfuc {
 	struct ramfuc base;
 
@@ -134,10 +128,12 @@ struct nve0_ram {
 	struct nouveau_ram base;
 	struct nve0_ramfuc fuc;
 
+	struct list_head cfg;
 	u32 parts;
 	u32 pmask;
 	u32 pnuts;
 
+	struct nvbios_ramcfg diff;
 	int from;
 	int mode;
 	int N1, fN1, M1, P1;
@@ -241,7 +237,7 @@ nve0_ram_nuts(struct nve0_ram *ram, struct ramfuc_reg *reg,
 {
 	struct nve0_fb_priv *priv = (void *)nouveau_fb(ram);
 	struct ramfuc *fuc = &ram->fuc.base;
-	u32 addr = 0x110000 + (reg->addr[0] & 0xfff);
+	u32 addr = 0x110000 + (reg->addr & 0xfff);
 	u32 mask = _mask | _copy;
 	u32 data = (_data & _mask) | (reg->data & _copy);
 	u32 i;
@@ -268,6 +264,7 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 	u32 mask, data;
 
 	ram_mask(fuc, 0x10f808, 0x40000000, 0x40000000);
+	ram_block(fuc);
 	ram_wr32(fuc, 0x62c000, 0x0f0f0000);
 
 	/* MR1: turn termination on early, for some reason.. */
@@ -478,7 +475,7 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 	ram_mask(fuc, 0x10f2e8, 0xffffffff, next->bios.timing[9]);
 
 	data = mask = 0x00000000;
-	if (NOTE00(ramcfg_08_20)) {
+	if (ram->diff.ramcfg_11_08_20) {
 		if (next->bios.ramcfg_11_08_20)
 			data |= 0x01000000;
 		mask |= 0x01000000;
@@ -486,11 +483,11 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 	ram_mask(fuc, 0x10f200, mask, data);
 
 	data = mask = 0x00000000;
-	if (NOTE00(ramcfg_02_03 != 0)) {
+	if (ram->diff.ramcfg_11_02_03) {
 		data |= next->bios.ramcfg_11_02_03 << 8;
 		mask |= 0x00000300;
 	}
-	if (NOTE00(ramcfg_01_10)) {
+	if (ram->diff.ramcfg_11_01_10) {
 		if (next->bios.ramcfg_11_01_10)
 			data |= 0x70000000;
 		mask |= 0x70000000;
@@ -498,11 +495,11 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 	ram_mask(fuc, 0x10f604, mask, data);
 
 	data = mask = 0x00000000;
-	if (NOTE00(timing_30_07 != 0)) {
+	if (ram->diff.timing_20_30_07) {
 		data |= next->bios.timing_20_30_07 << 28;
 		mask |= 0x70000000;
 	}
-	if (NOTE00(ramcfg_01_01)) {
+	if (ram->diff.ramcfg_11_01_01) {
 		if (next->bios.ramcfg_11_01_01)
 			data |= 0x00000100;
 		mask |= 0x00000100;
@@ -510,11 +507,11 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 	ram_mask(fuc, 0x10f614, mask, data);
 
 	data = mask = 0x00000000;
-	if (NOTE00(timing_30_07 != 0)) {
+	if (ram->diff.timing_20_30_07) {
 		data |= next->bios.timing_20_30_07 << 28;
 		mask |= 0x70000000;
 	}
-	if (NOTE00(ramcfg_01_02)) {
+	if (ram->diff.ramcfg_11_01_02) {
 		if (next->bios.ramcfg_11_01_02)
 			data |= 0x00000100;
 		mask |= 0x00000100;
@@ -548,11 +545,11 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 	ram_wr32(fuc, 0x10f870, 0x11111111 * next->bios.ramcfg_11_03_0f);
 
 	data = mask = 0x00000000;
-	if (NOTE00(ramcfg_02_03 != 0)) {
+	if (ram->diff.ramcfg_11_02_03) {
 		data |= next->bios.ramcfg_11_02_03;
 		mask |= 0x00000003;
 	}
-	if (NOTE00(ramcfg_01_10)) {
+	if (ram->diff.ramcfg_11_01_10) {
 		if (next->bios.ramcfg_11_01_10)
 			data |= 0x00000004;
 		mask |= 0x00000004;
@@ -666,6 +663,7 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 	if (next->bios.ramcfg_11_07_02)
 		nve0_ram_train(fuc, 0x80020000, 0x01000000);
 
+	ram_unblock(fuc);
 	ram_wr32(fuc, 0x62c000, 0x0f0f0f00);
 
 	if (next->bios.rammap_11_08_01)
@@ -695,6 +693,7 @@ nve0_ram_calc_sddr3(struct nouveau_fb *pfb, u32 freq)
 	u32 mask, data;
 
 	ram_mask(fuc, 0x10f808, 0x40000000, 0x40000000);
+	ram_block(fuc);
 	ram_wr32(fuc, 0x62c000, 0x0f0f0000);
 
 	if (vc == 1 && ram_have(fuc, gpio2E)) {
@@ -917,6 +916,7 @@ nve0_ram_calc_sddr3(struct nouveau_fb *pfb, u32 freq)
 	ram_mask(fuc, 0x10f200, 0x80000000, 0x00000000);
 	ram_nsec(fuc, 1000);
 
+	ram_unblock(fuc);
 	ram_wr32(fuc, 0x62c000, 0x0f0f0f00);
 
 	if (next->bios.rammap_11_08_01)
@@ -932,58 +932,24 @@ nve0_ram_calc_sddr3(struct nouveau_fb *pfb, u32 freq)
  ******************************************************************************/
 
 static int
-nve0_ram_calc_data(struct nouveau_fb *pfb, u32 freq,
+nve0_ram_calc_data(struct nouveau_fb *pfb, u32 khz,
 		   struct nouveau_ram_data *data)
 {
-	struct nouveau_bios *bios = nouveau_bios(pfb);
 	struct nve0_ram *ram = (void *)pfb->ram;
-	u8 strap, cnt, len;
-
-	/* lookup memory config data relevant to the target frequency */
-	ram->base.rammap.data = nvbios_rammapEp(bios, freq / 1000,
-					       &ram->base.rammap.version,
-					       &ram->base.rammap.size,
-					       &cnt, &len, &data->bios);
-	if (!ram->base.rammap.data || ram->base.rammap.version != 0x11 ||
-	     ram->base.rammap.size < 0x09) {
-		nv_error(pfb, "invalid/missing rammap entry\n");
-		return -EINVAL;
-	}
-
-	/* locate specific data set for the attached memory */
-	strap = nvbios_ramcfg_index(nv_subdev(pfb));
-	ram->base.ramcfg.data = nvbios_rammapSp(bios, ram->base.rammap.data,
-						ram->base.rammap.version,
-						ram->base.rammap.size,
-						cnt, len, strap,
-						&ram->base.ramcfg.version,
-						&ram->base.ramcfg.size,
-						&data->bios);
-	if (!ram->base.ramcfg.data || ram->base.ramcfg.version != 0x11 ||
-	     ram->base.ramcfg.size < 0x08) {
-		nv_error(pfb, "invalid/missing ramcfg entry\n");
-		return -EINVAL;
-	}
-
-	/* lookup memory timings, if bios says they're present */
-	strap = nv_ro08(bios, ram->base.ramcfg.data + 0x00);
-	if (strap != 0xff) {
-		ram->base.timing.data =
-			nvbios_timingEp(bios, strap, &ram->base.timing.version,
-				       &ram->base.timing.size, &cnt, &len,
-				       &data->bios);
-		if (!ram->base.timing.data ||
-		     ram->base.timing.version != 0x20 ||
-		     ram->base.timing.size < 0x33) {
-			nv_error(pfb, "invalid/missing timing entry\n");
-			return -EINVAL;
+	struct nouveau_ram_data *cfg;
+	u32 mhz = khz / 1000;
+
+	list_for_each_entry(cfg, &ram->cfg, head) {
+		if (mhz >= cfg->bios.rammap_min &&
+		    mhz <= cfg->bios.rammap_max) {
+			*data = *cfg;
+			data->freq = khz;
+			return 0;
 		}
-	} else {
-		ram->base.timing.data = 0;
 	}
 
-	data->freq = freq;
-	return 0;
+	nv_error(ram, "ramcfg data for %dMHz not found\n", mhz);
+	return -EINVAL;
 }
 
 static int
@@ -1106,13 +1072,99 @@ nve0_ram_calc(struct nouveau_fb *pfb, u32 freq)
 	return nve0_ram_calc_xits(pfb, ram->base.next);
 }
 
+static void
+nve0_ram_prog_0(struct nouveau_fb *pfb, u32 freq)
+{
+	struct nve0_ram *ram = (void *)pfb->ram;
+	struct nouveau_ram_data *cfg;
+	u32 mhz = freq / 1000;
+	u32 mask, data;
+
+	list_for_each_entry(cfg, &ram->cfg, head) {
+		if (mhz >= cfg->bios.rammap_min &&
+		    mhz <= cfg->bios.rammap_max)
+			break;
+	}
+
+	if (&cfg->head == &ram->cfg)
+		return;
+
+	if (mask = 0, data = 0, ram->diff.rammap_11_0a_03fe) {
+		data |= cfg->bios.rammap_11_0a_03fe << 12;
+		mask |= 0x001ff000;
+	}
+	if (ram->diff.rammap_11_09_01ff) {
+		data |= cfg->bios.rammap_11_09_01ff;
+		mask |= 0x000001ff;
+	}
+	nv_mask(pfb, 0x10f468, mask, data);
+
+	if (mask = 0, data = 0, ram->diff.rammap_11_0a_0400) {
+		data |= cfg->bios.rammap_11_0a_0400;
+		mask |= 0x00000001;
+	}
+	nv_mask(pfb, 0x10f420, mask, data);
+
+	if (mask = 0, data = 0, ram->diff.rammap_11_0a_0800) {
+		data |= cfg->bios.rammap_11_0a_0800;
+		mask |= 0x00000001;
+	}
+	nv_mask(pfb, 0x10f430, mask, data);
+
+	if (mask = 0, data = 0, ram->diff.rammap_11_0b_01f0) {
+		data |= cfg->bios.rammap_11_0b_01f0;
+		mask |= 0x0000001f;
+	}
+	nv_mask(pfb, 0x10f400, mask, data);
+
+	if (mask = 0, data = 0, ram->diff.rammap_11_0b_0200) {
+		data |= cfg->bios.rammap_11_0b_0200 << 9;
+		mask |= 0x00000200;
+	}
+	nv_mask(pfb, 0x10f410, mask, data);
+
+	if (mask = 0, data = 0, ram->diff.rammap_11_0d) {
+		data |= cfg->bios.rammap_11_0d << 16;
+		mask |= 0x00ff0000;
+	}
+	if (ram->diff.rammap_11_0f) {
+		data |= cfg->bios.rammap_11_0f << 8;
+		mask |= 0x0000ff00;
+	}
+	nv_mask(pfb, 0x10f440, mask, data);
+
+	if (mask = 0, data = 0, ram->diff.rammap_11_0e) {
+		data |= cfg->bios.rammap_11_0e << 8;
+		mask |= 0x0000ff00;
+	}
+	if (ram->diff.rammap_11_0b_0800) {
+		data |= cfg->bios.rammap_11_0b_0800 << 7;
+		mask |= 0x00000080;
+	}
+	if (ram->diff.rammap_11_0b_0400) {
+		data |= cfg->bios.rammap_11_0b_0400 << 5;
+		mask |= 0x00000020;
+	}
+	nv_mask(pfb, 0x10f444, mask, data);
+}
+
 static int
 nve0_ram_prog(struct nouveau_fb *pfb)
 {
 	struct nouveau_device *device = nv_device(pfb);
 	struct nve0_ram *ram = (void *)pfb->ram;
 	struct nve0_ramfuc *fuc = &ram->fuc;
-	ram_exec(fuc, nouveau_boolopt(device->cfgopt, "NvMemExec", true));
+	struct nouveau_ram_data *next = ram->base.next;
+
+	if (!nouveau_boolopt(device->cfgopt, "NvMemExec", true)) {
+		ram_exec(fuc, false);
+		return (ram->base.next == &ram->base.xition);
+	}
+
+	nve0_ram_prog_0(pfb, 1000);
+	ram_exec(fuc, true);
+	nve0_ram_prog_0(pfb, next->freq);
+
 	return (ram->base.next == &ram->base.xition);
 }
 
@@ -1125,24 +1177,147 @@ nve0_ram_tidy(struct nouveau_fb *pfb)
 	ram_exec(fuc, false);
 }
 
+struct nve0_ram_train {
+	u16 mask;
+	struct nvbios_M0209S remap;
+	struct nvbios_M0209S type00;
+	struct nvbios_M0209S type01;
+	struct nvbios_M0209S type04;
+	struct nvbios_M0209S type06;
+	struct nvbios_M0209S type07;
+	struct nvbios_M0209S type08;
+	struct nvbios_M0209S type09;
+};
+
+static int
+nve0_ram_train_type(struct nouveau_fb *pfb, int i, u8 ramcfg,
+		    struct nve0_ram_train *train)
+{
+	struct nouveau_bios *bios = nouveau_bios(pfb);
+	struct nvbios_M0205E M0205E;
+	struct nvbios_M0205S M0205S;
+	struct nvbios_M0209E M0209E;
+	struct nvbios_M0209S *remap = &train->remap;
+	struct nvbios_M0209S *value;
+	u8  ver, hdr, cnt, len;
+	u32 data;
+
+	/* determine type of data for this index */
+	if (!(data = nvbios_M0205Ep(bios, i, &ver, &hdr, &cnt, &len, &M0205E)))
+		return -ENOENT;
+
+	switch (M0205E.type) {
+	case 0x00: value = &train->type00; break;
+	case 0x01: value = &train->type01; break;
+	case 0x04: value = &train->type04; break;
+	case 0x06: value = &train->type06; break;
+	case 0x07: value = &train->type07; break;
+	case 0x08: value = &train->type08; break;
+	case 0x09: value = &train->type09; break;
+	default:
+		return 0;
+	}
+
+	/* training data index determined by ramcfg strap */
+	if (!(data = nvbios_M0205Sp(bios, i, ramcfg, &ver, &hdr, &M0205S)))
+		return -EINVAL;
+	i = M0205S.data;
+
+	/* training data format information */
+	if (!(data = nvbios_M0209Ep(bios, i, &ver, &hdr, &cnt, &len, &M0209E)))
+		return -EINVAL;
+
+	/* ... and the raw data */
+	if (!(data = nvbios_M0209Sp(bios, i, 0, &ver, &hdr, value)))
+		return -EINVAL;
+
+	if (M0209E.v02_07 == 2) {
+		/* of course! why wouldn't we have a pointer to another entry
+		 * in the same table, and use the first one as an array of
+		 * remap indices...
+		 */
+		if (!(data = nvbios_M0209Sp(bios, M0209E.v03, 0, &ver, &hdr,
+					    remap)))
+			return -EINVAL;
+
+		for (i = 0; i < ARRAY_SIZE(value->data); i++)
+			value->data[i] = remap->data[value->data[i]];
+	} else
+	if (M0209E.v02_07 != 1)
+		return -EINVAL;
+
+	train->mask |= 1 << M0205E.type;
+	return 0;
+}
+
+static int
+nve0_ram_train_init_0(struct nouveau_fb *pfb, struct nve0_ram_train *train)
+{
+	int i, j;
+
+	if ((train->mask & 0x03d3) != 0x03d3) {
+		nv_warn(pfb, "missing link training data\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < 0x30; i++) {
+		for (j = 0; j < 8; j += 4) {
+			nv_wr32(pfb, 0x10f968 + j, 0x00000000 | (i << 8));
+			nv_wr32(pfb, 0x10f920 + j, 0x00000000 |
+						   train->type08.data[i] << 4 |
+						   train->type06.data[i]);
+			nv_wr32(pfb, 0x10f918 + j, train->type00.data[i]);
+			nv_wr32(pfb, 0x10f920 + j, 0x00000100 |
+						   train->type09.data[i] << 4 |
+						   train->type07.data[i]);
+			nv_wr32(pfb, 0x10f918 + j, train->type01.data[i]);
+		}
+	}
+
+	for (j = 0; j < 8; j += 4) {
+		for (i = 0; i < 0x100; i++) {
+			nv_wr32(pfb, 0x10f968 + j, i);
+			nv_wr32(pfb, 0x10f900 + j, train->type04.data[i]);
+		}
+	}
+
+	return 0;
+}
+
+static int
+nve0_ram_train_init(struct nouveau_fb *pfb)
+{
+	u8 ramcfg = nvbios_ramcfg_index(nv_subdev(pfb));
+	struct nve0_ram_train *train;
+	int ret = -ENOMEM, i;
+
+	if ((train = kzalloc(sizeof(*train), GFP_KERNEL))) {
+		for (i = 0; i < 0x100; i++) {
+			ret = nve0_ram_train_type(pfb, i, ramcfg, train);
+			if (ret && ret != -ENOENT)
+				break;
+		}
+	}
+
+	switch (pfb->ram->type) {
+	case NV_MEM_TYPE_GDDR5:
+		ret = nve0_ram_train_init_0(pfb, train);
+		break;
+	default:
+		ret = 0;
+		break;
+	}
+
+	kfree(train);
+	return ret;
+}
+
 int
 nve0_ram_init(struct nouveau_object *object)
 {
 	struct nouveau_fb *pfb = (void *)object->parent;
 	struct nve0_ram *ram   = (void *)object;
 	struct nouveau_bios *bios = nouveau_bios(pfb);
-	static const u8  train0[] = {
-		0x00, 0xff, 0xff, 0x00, 0xff, 0x00,
-		0x00, 0xff, 0xff, 0x00, 0xff, 0x00,
-	};
-	static const u32 train1[] = {
-		0x00000000, 0xffffffff,
-		0x55555555, 0xaaaaaaaa,
-		0x33333333, 0xcccccccc,
-		0xf0f0f0f0, 0x0f0f0f0f,
-		0x00ff00ff, 0xff00ff00,
-		0x0000ffff, 0xffff0000,
-	};
 	u8  ver, hdr, cnt, len, snr, ssz;
 	u32 data, save;
 	int ret, i;
@@ -1168,51 +1343,107 @@ nve0_ram_init(struct nouveau_object *object)
 
 	cnt  = nv_ro08(bios, data + 0x14); /* guess at count */
 	data = nv_ro32(bios, data + 0x10); /* guess u32... */
-	save = nv_rd32(pfb, 0x10f65c);
-	for (i = 0; i < cnt; i++) {
-		nv_mask(pfb, 0x10f65c, 0x000000f0, i << 4);
-		nvbios_exec(&(struct nvbios_init) {
-				.subdev = nv_subdev(pfb),
-				.bios = bios,
-				.offset = nv_ro32(bios, data), /* guess u32 */
-				.execute = 1,
-			    });
-		data += 4;
-	}
-	nv_wr32(pfb, 0x10f65c, save);
+	save = nv_rd32(pfb, 0x10f65c) & 0x000000f0;
+	for (i = 0; i < cnt; i++, data += 4) {
+		if (i != save >> 4) {
+			nv_mask(pfb, 0x10f65c, 0x000000f0, i << 4);
+			nvbios_exec(&(struct nvbios_init) {
+					.subdev = nv_subdev(pfb),
+					.bios = bios,
+					.offset = nv_ro32(bios, data),
+					.execute = 1,
+				    });
+		}
+	}
+	nv_mask(pfb, 0x10f65c, 0x000000f0, save);
 	nv_mask(pfb, 0x10f584, 0x11000000, 0x00000000);
+	nv_wr32(pfb, 0x10ecc0, 0xffffffff);
+	nv_mask(pfb, 0x10f160, 0x00000010, 0x00000010);
 
-	switch (ram->base.type) {
-	case NV_MEM_TYPE_GDDR5:
-		for (i = 0; i < 0x30; i++) {
-			nv_wr32(pfb, 0x10f968, 0x00000000 | (i << 8));
-			nv_wr32(pfb, 0x10f920, 0x00000000 | train0[i % 12]);
-			nv_wr32(pfb, 0x10f918,              train1[i % 12]);
-			nv_wr32(pfb, 0x10f920, 0x00000100 | train0[i % 12]);
-			nv_wr32(pfb, 0x10f918,              train1[i % 12]);
-
-			nv_wr32(pfb, 0x10f96c, 0x00000000 | (i << 8));
-			nv_wr32(pfb, 0x10f924, 0x00000000 | train0[i % 12]);
-			nv_wr32(pfb, 0x10f91c,              train1[i % 12]);
-			nv_wr32(pfb, 0x10f924, 0x00000100 | train0[i % 12]);
-			nv_wr32(pfb, 0x10f91c,              train1[i % 12]);
-		}
+	return nve0_ram_train_init(pfb);
+}
 
-		for (i = 0; i < 0x100; i++) {
-			nv_wr32(pfb, 0x10f968, i);
-			nv_wr32(pfb, 0x10f900, train1[2 + (i & 1)]);
-		}
+static int
+nve0_ram_ctor_data(struct nve0_ram *ram, u8 ramcfg, int i)
+{
+	struct nouveau_fb *pfb = (void *)nv_object(ram)->parent;
+	struct nouveau_bios *bios = nouveau_bios(pfb);
+	struct nouveau_ram_data *cfg;
+	struct nvbios_ramcfg *d = &ram->diff;
+	struct nvbios_ramcfg *p, *n;
+	u8  ver, hdr, cnt, len;
+	u32 data;
+	int ret;
 
-		for (i = 0; i < 0x100; i++) {
-			nv_wr32(pfb, 0x10f96c, i);
-			nv_wr32(pfb, 0x10f900, train1[2 + (i & 1)]);
-		}
-		break;
-	default:
-		break;
+	if (!(cfg = kmalloc(sizeof(*cfg), GFP_KERNEL)))
+		return -ENOMEM;
+	p = &list_last_entry(&ram->cfg, typeof(*cfg), head)->bios;
+	n = &cfg->bios;
+
+	/* memory config data for a range of target frequencies */
+	data = nvbios_rammapEp(bios, i, &ver, &hdr, &cnt, &len, &cfg->bios);
+	if (ret = -ENOENT, !data)
+		goto done;
+	if (ret = -ENOSYS, ver != 0x11 || hdr < 0x12)
+		goto done;
+
+	/* ... and a portion specific to the attached memory */
+	data = nvbios_rammapSp(bios, data, ver, hdr, cnt, len, ramcfg,
+			       &ver, &hdr, &cfg->bios);
+	if (ret = -EINVAL, !data)
+		goto done;
+	if (ret = -ENOSYS, ver != 0x11 || hdr < 0x0a)
+		goto done;
+
+	/* lookup memory timings, if bios says they're present */
+	if (cfg->bios.ramcfg_timing != 0xff) {
+		data = nvbios_timingEp(bios, cfg->bios.ramcfg_timing,
+				       &ver, &hdr, &cnt, &len,
+				       &cfg->bios);
+		if (ret = -EINVAL, !data)
+			goto done;
+		if (ret = -ENOSYS, ver != 0x20 || hdr < 0x33)
+			goto done;
 	}
 
-	return 0;
+	list_add_tail(&cfg->head, &ram->cfg);
+	if (ret = 0, i == 0)
+		goto done;
+
+	d->rammap_11_0a_03fe |= p->rammap_11_0a_03fe != n->rammap_11_0a_03fe;
+	d->rammap_11_09_01ff |= p->rammap_11_09_01ff != n->rammap_11_09_01ff;
+	d->rammap_11_0a_0400 |= p->rammap_11_0a_0400 != n->rammap_11_0a_0400;
+	d->rammap_11_0a_0800 |= p->rammap_11_0a_0800 != n->rammap_11_0a_0800;
+	d->rammap_11_0b_01f0 |= p->rammap_11_0b_01f0 != n->rammap_11_0b_01f0;
+	d->rammap_11_0b_0200 |= p->rammap_11_0b_0200 != n->rammap_11_0b_0200;
+	d->rammap_11_0d |= p->rammap_11_0d != n->rammap_11_0d;
+	d->rammap_11_0f |= p->rammap_11_0f != n->rammap_11_0f;
+	d->rammap_11_0e |= p->rammap_11_0e != n->rammap_11_0e;
+	d->rammap_11_0b_0800 |= p->rammap_11_0b_0800 != n->rammap_11_0b_0800;
+	d->rammap_11_0b_0400 |= p->rammap_11_0b_0400 != n->rammap_11_0b_0400;
+	d->ramcfg_11_01_01 |= p->ramcfg_11_01_01 != n->ramcfg_11_01_01;
+	d->ramcfg_11_01_02 |= p->ramcfg_11_01_02 != n->ramcfg_11_01_02;
+	d->ramcfg_11_01_10 |= p->ramcfg_11_01_10 != n->ramcfg_11_01_10;
+	d->ramcfg_11_02_03 |= p->ramcfg_11_02_03 != n->ramcfg_11_02_03;
+	d->ramcfg_11_08_20 |= p->ramcfg_11_08_20 != n->ramcfg_11_08_20;
+	d->timing_20_30_07 |= p->timing_20_30_07 != n->timing_20_30_07;
+done:
+	if (ret)
+		kfree(cfg);
+	return ret;
+}
+
+static void
+nve0_ram_dtor(struct nouveau_object *object)
+{
+	struct nve0_ram *ram = (void *)object;
+	struct nouveau_ram_data *cfg, *tmp;
+
+	list_for_each_entry_safe(cfg, tmp, &ram->cfg, head) {
+		kfree(cfg);
+	}
+
+	nouveau_ram_destroy(&ram->base);
 }
 
 static int
@@ -1226,6 +1457,7 @@ nve0_ram_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct dcb_gpio_func func;
 	struct nve0_ram *ram;
 	int ret, i;
+	u8  ramcfg = nvbios_ramcfg_index(nv_subdev(pfb));
 	u32 tmp;
 
 	ret = nvc0_ram_create(parent, engine, oclass, 0x022554, &ram);
@@ -1233,6 +1465,8 @@ nve0_ram_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	INIT_LIST_HEAD(&ram->cfg);
+
 	switch (ram->base.type) {
 	case NV_MEM_TYPE_DDR3:
 	case NV_MEM_TYPE_GDDR5:
@@ -1264,7 +1498,26 @@ nve0_ram_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 		}
 	}
 
-	// parse bios data for both pll's
+	/* parse bios data for all rammap table entries up-front, and
+	 * build information on whether certain fields differ between
+	 * any of the entries.
+	 *
+	 * the binary driver appears to completely ignore some fields
+	 * when all entries contain the same value.  at first, it was
+	 * hoped that these were mere optimisations and the bios init
+	 * tables had configured as per the values here, but there is
+	 * evidence now to suggest that this isn't the case and we do
+	 * need to treat this condition as a "don't touch" indicator.
+	 */
+	for (i = 0; !ret; i++) {
+		ret = nve0_ram_ctor_data(ram, ramcfg, i);
+		if (ret && ret != -ENOENT) {
+			nv_error(pfb, "failed to parse ramcfg data\n");
+			return ret;
+		}
+	}
+
+	/* parse bios data for both pll's */
 	ret = nvbios_pll_parse(bios, 0x0c, &ram->fuc.refpll);
 	if (ret) {
 		nv_error(pfb, "mclk refpll data not found\n");
@@ -1277,6 +1530,7 @@ nve0_ram_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 		return ret;
 	}
 
+	/* lookup memory voltage gpios */
 	ret = gpio->find(gpio, 0, 0x18, DCB_GPIO_UNUSED, &func);
 	if (ret == 0) {
 		ram->fuc.r_gpioMV = ramfuc_reg(0x00d610 + (func.line * 0x04));
@@ -1385,7 +1639,7 @@ nve0_ram_oclass = {
 	.handle = 0,
 	.ofuncs = &(struct nouveau_ofuncs) {
 		.ctor = nve0_ram_ctor,
-		.dtor = _nouveau_ram_dtor,
+		.dtor = nve0_ram_dtor,
 		.init = nve0_ram_init,
 		.fini = _nouveau_ram_fini,
 	}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/sddr2.c b/drivers/gpu/drm/nouveau/core/subdev/fb/sddr2.c
new file mode 100644
index 000000000000..bb1eb8f3e639
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/sddr2.c
@@ -0,0 +1,94 @@
+/*
+ * Copyright 2014 Roy Spliet
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Roy Spliet <rspliet@eclipso.eu>
+ *          Ben Skeggs
+ */
+
+#include "priv.h"
+
+struct ramxlat {
+	int id;
+	u8 enc;
+};
+
+static inline int
+ramxlat(const struct ramxlat *xlat, int id)
+{
+	while (xlat->id >= 0) {
+		if (xlat->id == id)
+			return xlat->enc;
+		xlat++;
+	}
+	return -EINVAL;
+}
+
+static const struct ramxlat
+ramddr2_cl[] = {
+	{ 2, 2 }, { 3, 3 }, { 4, 4 }, { 5, 5 }, { 6, 6 },
+	/* The following are available in some, but not all DDR2 docs */
+	{ 7, 7 },
+	{ -1 }
+};
+
+static const struct ramxlat
+ramddr2_wr[] = {
+	{ 2, 1 }, { 3, 2 }, { 4, 3 }, { 5, 4 }, { 6, 5 },
+	/* The following are available in some, but not all DDR2 docs */
+	{ 7, 6 },
+	{ -1 }
+};
+
+int
+nouveau_sddr2_calc(struct nouveau_ram *ram)
+{
+	int CL, WR, DLL = 0, ODT = 0;
+
+	switch (ram->next->bios.timing_ver) {
+	case 0x10:
+		CL  = ram->next->bios.timing_10_CL;
+		WR  = ram->next->bios.timing_10_WR;
+		DLL = !ram->next->bios.ramcfg_10_02_40;
+		ODT = ram->next->bios.timing_10_ODT & 3;
+		break;
+	case 0x20:
+		CL  = (ram->next->bios.timing[1] & 0x0000001f);
+		WR  = (ram->next->bios.timing[2] & 0x007f0000) >> 16;
+		break;
+	default:
+		return -ENOSYS;
+	}
+
+	CL  = ramxlat(ramddr2_cl, CL);
+	WR  = ramxlat(ramddr2_wr, WR);
+	if (CL < 0 || WR < 0)
+		return -EINVAL;
+
+	ram->mr[0] &= ~0xf70;
+	ram->mr[0] |= (WR & 0x07) << 9;
+	ram->mr[0] |= (CL & 0x07) << 4;
+
+	ram->mr[1] &= ~0x045;
+	ram->mr[1] |= (ODT & 0x1) << 2;
+	ram->mr[1] |= (ODT & 0x2) << 5;
+	ram->mr[1] |= !DLL;
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/sddr3.c b/drivers/gpu/drm/nouveau/core/subdev/fb/sddr3.c
index ebd4cd9c35d9..83949b11833a 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/sddr3.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/sddr3.c
@@ -20,9 +20,9 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  * Authors: Ben Skeggs <bskeggs@redhat.com>
+ * 	    Roy Spliet <rspliet@eclipso.eu>
  */
 
-#include <subdev/bios.h>
 #include "priv.h"
 
 struct ramxlat {
@@ -69,31 +69,52 @@ ramddr3_cwl[] = {
 int
 nouveau_sddr3_calc(struct nouveau_ram *ram)
 {
-	struct nouveau_bios *bios = nouveau_bios(ram);
-	int WL, CL, WR;
+	int CWL, CL, WR, DLL = 0, ODT = 0;
 
-	switch (!!ram->timing.data * ram->timing.version) {
+	switch (ram->next->bios.timing_ver) {
+	case 0x10:
+		if (ram->next->bios.timing_hdr < 0x17) {
+			/* XXX: NV50: Get CWL from the timing register */
+			return -ENOSYS;
+		}
+		CWL = ram->next->bios.timing_10_CWL;
+		CL  = ram->next->bios.timing_10_CL;
+		WR  = ram->next->bios.timing_10_WR;
+		DLL = !ram->next->bios.ramcfg_10_02_40;
+		ODT = ram->next->bios.timing_10_ODT;
+		break;
 	case 0x20:
-		WL = (nv_ro16(bios, ram->timing.data + 0x04) & 0x0f80) >> 7;
-		CL =  nv_ro08(bios, ram->timing.data + 0x04) & 0x1f;
-		WR =  nv_ro08(bios, ram->timing.data + 0x0a) & 0x7f;
+		CWL = (ram->next->bios.timing[1] & 0x00000f80) >> 7;
+		CL  = (ram->next->bios.timing[1] & 0x0000001f) >> 0;
+		WR  = (ram->next->bios.timing[2] & 0x007f0000) >> 16;
+		/* XXX: Get these values from the VBIOS instead */
+		DLL = !(ram->mr[1] & 0x1);
+		ODT =   (ram->mr[1] & 0x004) >> 2 |
+			(ram->mr[1] & 0x040) >> 5 |
+		        (ram->mr[1] & 0x200) >> 7;
 		break;
 	default:
 		return -ENOSYS;
 	}
 
-	WL = ramxlat(ramddr3_cwl, WL);
-	CL = ramxlat(ramddr3_cl, CL);
-	WR = ramxlat(ramddr3_wr, WR);
-	if (WL < 0 || CL < 0 || WR < 0)
+	CWL = ramxlat(ramddr3_cwl, CWL);
+	CL  = ramxlat(ramddr3_cl, CL);
+	WR  = ramxlat(ramddr3_wr, WR);
+	if (CL < 0 || CWL < 0 || WR < 0)
 		return -EINVAL;
 
-	ram->mr[0] &= ~0xe74;
+	ram->mr[0] &= ~0xf74;
 	ram->mr[0] |= (WR & 0x07) << 9;
 	ram->mr[0] |= (CL & 0x0e) << 3;
 	ram->mr[0] |= (CL & 0x01) << 2;
 
+	ram->mr[1] &= ~0x245;
+	ram->mr[1] |= (ODT & 0x1) << 2;
+	ram->mr[1] |= (ODT & 0x2) << 5;
+	ram->mr[1] |= (ODT & 0x4) << 7;
+	ram->mr[1] |= !DLL;
+
 	ram->mr[2] &= ~0x038;
-	ram->mr[2] |= (WL & 0x07) << 3;
+	ram->mr[2] |= (CWL & 0x07) << 3;
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fuse/base.c b/drivers/gpu/drm/nouveau/core/subdev/fuse/base.c
new file mode 100644
index 000000000000..9e8e92127715
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/fuse/base.c
@@ -0,0 +1,54 @@
+/*
+ * Copyright 2014 Martin Peres
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Martin Peres
+ */
+
+#include <subdev/fuse.h>
+
+int
+_nouveau_fuse_init(struct nouveau_object *object)
+{
+	struct nouveau_fuse *fuse = (void *)object;
+	return nouveau_subdev_init(&fuse->base);
+}
+
+void
+_nouveau_fuse_dtor(struct nouveau_object *object)
+{
+	struct nouveau_fuse *fuse = (void *)object;
+	nouveau_subdev_destroy(&fuse->base);
+}
+
+int
+nouveau_fuse_create_(struct nouveau_object *parent,
+		     struct nouveau_object *engine,
+		     struct nouveau_oclass *oclass, int length, void **pobject)
+{
+	struct nouveau_fuse *fuse;
+	int ret;
+
+	ret = nouveau_subdev_create_(parent, engine, oclass, 0, "FUSE",
+				     "fuse", length, pobject);
+	fuse = *pobject;
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fuse/g80.c b/drivers/gpu/drm/nouveau/core/subdev/fuse/g80.c
new file mode 100644
index 000000000000..a374ade485be
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/fuse/g80.c
@@ -0,0 +1,81 @@
+/*
+ * Copyright 2014 Martin Peres
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Martin Peres
+ */
+
+#include "priv.h"
+
+struct g80_fuse_priv {
+	struct nouveau_fuse base;
+
+	spinlock_t fuse_enable_lock;
+};
+
+static u32
+g80_fuse_rd32(struct nouveau_object *object, u64 addr)
+{
+	struct g80_fuse_priv *priv = (void *)object;
+	unsigned long flags;
+	u32 fuse_enable, val;
+
+	spin_lock_irqsave(&priv->fuse_enable_lock, flags);
+
+	/* racy if another part of nouveau start writing to this reg */
+	fuse_enable = nv_mask(priv, 0x1084, 0x800, 0x800);
+	val = nv_rd32(priv, 0x21000 + addr);
+	nv_wr32(priv, 0x1084, fuse_enable);
+
+	spin_unlock_irqrestore(&priv->fuse_enable_lock, flags);
+
+	return val;
+}
+
+
+static int
+g80_fuse_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
+	       struct nouveau_oclass *oclass, void *data, u32 size,
+	       struct nouveau_object **pobject)
+{
+	struct g80_fuse_priv *priv;
+	int ret;
+
+	ret = nouveau_fuse_create(parent, engine, oclass, &priv);
+	*pobject = nv_object(priv);
+	if (ret)
+		return ret;
+
+	spin_lock_init(&priv->fuse_enable_lock);
+
+	return 0;
+}
+
+struct nouveau_oclass
+g80_fuse_oclass = {
+	.handle = NV_SUBDEV(FUSE, 0x50),
+	.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = g80_fuse_ctor,
+		.dtor = _nouveau_fuse_dtor,
+		.init = _nouveau_fuse_init,
+		.fini = _nouveau_fuse_fini,
+		.rd32 = g80_fuse_rd32,
+	},
+};
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fuse/gf100.c b/drivers/gpu/drm/nouveau/core/subdev/fuse/gf100.c
new file mode 100644
index 000000000000..5ed03f54b3d4
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/fuse/gf100.c
@@ -0,0 +1,83 @@
+/*
+ * Copyright 2014 Martin Peres
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Martin Peres
+ */
+
+#include "priv.h"
+
+struct gf100_fuse_priv {
+	struct nouveau_fuse base;
+
+	spinlock_t fuse_enable_lock;
+};
+
+static u32
+gf100_fuse_rd32(struct nouveau_object *object, u64 addr)
+{
+	struct gf100_fuse_priv *priv = (void *)object;
+	unsigned long flags;
+	u32 fuse_enable, unk, val;
+
+	spin_lock_irqsave(&priv->fuse_enable_lock, flags);
+
+	/* racy if another part of nouveau start writing to these regs */
+	fuse_enable = nv_mask(priv, 0x22400, 0x800, 0x800);
+	unk = nv_mask(priv, 0x21000, 0x1, 0x1);
+	val = nv_rd32(priv, 0x21100 + addr);
+	nv_wr32(priv, 0x21000, unk);
+	nv_wr32(priv, 0x22400, fuse_enable);
+
+	spin_unlock_irqrestore(&priv->fuse_enable_lock, flags);
+
+	return val;
+}
+
+
+static int
+gf100_fuse_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
+	       struct nouveau_oclass *oclass, void *data, u32 size,
+	       struct nouveau_object **pobject)
+{
+	struct gf100_fuse_priv *priv;
+	int ret;
+
+	ret = nouveau_fuse_create(parent, engine, oclass, &priv);
+	*pobject = nv_object(priv);
+	if (ret)
+		return ret;
+
+	spin_lock_init(&priv->fuse_enable_lock);
+
+	return 0;
+}
+
+struct nouveau_oclass
+gf100_fuse_oclass = {
+	.handle = NV_SUBDEV(FUSE, 0xC0),
+	.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = gf100_fuse_ctor,
+		.dtor = _nouveau_fuse_dtor,
+		.init = _nouveau_fuse_init,
+		.fini = _nouveau_fuse_fini,
+		.rd32 = gf100_fuse_rd32,
+	},
+};
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fuse/gm107.c b/drivers/gpu/drm/nouveau/core/subdev/fuse/gm107.c
new file mode 100644
index 000000000000..4f1a636c6538
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/fuse/gm107.c
@@ -0,0 +1,66 @@
+/*
+ * Copyright 2014 Martin Peres
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Martin Peres
+ */
+
+#include "priv.h"
+
+struct gm107_fuse_priv {
+	struct nouveau_fuse base;
+};
+
+static u32
+gm107_fuse_rd32(struct nouveau_object *object, u64 addr)
+{
+	struct gf100_fuse_priv *priv = (void *)object;
+
+	return nv_rd32(priv, 0x21100 + addr);
+}
+
+
+static int
+gm107_fuse_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
+	       struct nouveau_oclass *oclass, void *data, u32 size,
+	       struct nouveau_object **pobject)
+{
+	struct gm107_fuse_priv *priv;
+	int ret;
+
+	ret = nouveau_fuse_create(parent, engine, oclass, &priv);
+	*pobject = nv_object(priv);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+struct nouveau_oclass
+gm107_fuse_oclass = {
+	.handle = NV_SUBDEV(FUSE, 0x117),
+	.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = gm107_fuse_ctor,
+		.dtor = _nouveau_fuse_dtor,
+		.init = _nouveau_fuse_init,
+		.fini = _nouveau_fuse_fini,
+		.rd32 = gm107_fuse_rd32,
+	},
+};
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fuse/priv.h b/drivers/gpu/drm/nouveau/core/subdev/fuse/priv.h
new file mode 100644
index 000000000000..d2085411a5cb
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/fuse/priv.h
@@ -0,0 +1,9 @@
+#ifndef __NVKM_FUSE_PRIV_H__
+#define __NVKM_FUSE_PRIV_H__
+
+#include <subdev/fuse.h>
+
+int _nouveau_fuse_init(struct nouveau_object *object);
+void _nouveau_fuse_dtor(struct nouveau_object *object);
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/base.c b/drivers/gpu/drm/nouveau/core/subdev/gpio/base.c
index b1e3ed7c8beb..7ad99b763f4c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/gpio/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/base.c
@@ -122,7 +122,8 @@ nouveau_gpio_intr_init(struct nvkm_event *event, int type, int index)
 }
 
 static int
-nouveau_gpio_intr_ctor(void *data, u32 size, struct nvkm_notify *notify)
+nouveau_gpio_intr_ctor(struct nouveau_object *object, void *data, u32 size,
+		       struct nvkm_notify *notify)
 {
 	struct nvkm_gpio_ntfy_req *req = data;
 	if (!WARN_ON(size != sizeof(*req))) {
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/nv92.c b/drivers/gpu/drm/nouveau/core/subdev/gpio/nv94.c
index 252083d376f5..cae404ccadac 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/gpio/nv92.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/nv94.c
@@ -25,7 +25,7 @@
 #include "priv.h"
 
 void
-nv92_gpio_intr_stat(struct nouveau_gpio *gpio, u32 *hi, u32 *lo)
+nv94_gpio_intr_stat(struct nouveau_gpio *gpio, u32 *hi, u32 *lo)
 {
 	u32 intr0 = nv_rd32(gpio, 0x00e054);
 	u32 intr1 = nv_rd32(gpio, 0x00e074);
@@ -38,7 +38,7 @@ nv92_gpio_intr_stat(struct nouveau_gpio *gpio, u32 *hi, u32 *lo)
 }
 
 void
-nv92_gpio_intr_mask(struct nouveau_gpio *gpio, u32 type, u32 mask, u32 data)
+nv94_gpio_intr_mask(struct nouveau_gpio *gpio, u32 type, u32 mask, u32 data)
 {
 	u32 inte0 = nv_rd32(gpio, 0x00e050);
 	u32 inte1 = nv_rd32(gpio, 0x00e070);
@@ -57,8 +57,8 @@ nv92_gpio_intr_mask(struct nouveau_gpio *gpio, u32 type, u32 mask, u32 data)
 }
 
 struct nouveau_oclass *
-nv92_gpio_oclass = &(struct nouveau_gpio_impl) {
-	.base.handle = NV_SUBDEV(GPIO, 0x92),
+nv94_gpio_oclass = &(struct nouveau_gpio_impl) {
+	.base.handle = NV_SUBDEV(GPIO, 0x94),
 	.base.ofuncs = &(struct nouveau_ofuncs) {
 		.ctor = _nouveau_gpio_ctor,
 		.dtor = _nouveau_gpio_dtor,
@@ -66,8 +66,8 @@ nv92_gpio_oclass = &(struct nouveau_gpio_impl) {
 		.fini = _nouveau_gpio_fini,
 	},
 	.lines = 32,
-	.intr_stat = nv92_gpio_intr_stat,
-	.intr_mask = nv92_gpio_intr_mask,
+	.intr_stat = nv94_gpio_intr_stat,
+	.intr_mask = nv94_gpio_intr_mask,
 	.drive = nv50_gpio_drive,
 	.sense = nv50_gpio_sense,
 	.reset = nv50_gpio_reset,
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/nvd0.c b/drivers/gpu/drm/nouveau/core/subdev/gpio/nvd0.c
index a4682b0956ad..480d6d2af770 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/gpio/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/nvd0.c
@@ -77,8 +77,8 @@ nvd0_gpio_oclass = &(struct nouveau_gpio_impl) {
 		.fini = _nouveau_gpio_fini,
 	},
 	.lines = 32,
-	.intr_stat = nv92_gpio_intr_stat,
-	.intr_mask = nv92_gpio_intr_mask,
+	.intr_stat = nv94_gpio_intr_stat,
+	.intr_mask = nv94_gpio_intr_mask,
 	.drive = nvd0_gpio_drive,
 	.sense = nvd0_gpio_sense,
 	.reset = nvd0_gpio_reset,
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/priv.h b/drivers/gpu/drm/nouveau/core/subdev/gpio/priv.h
index e1724dfc86ae..bff98b86e2b5 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/gpio/priv.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/priv.h
@@ -56,8 +56,8 @@ void nv50_gpio_reset(struct nouveau_gpio *, u8);
 int  nv50_gpio_drive(struct nouveau_gpio *, int, int, int);
 int  nv50_gpio_sense(struct nouveau_gpio *, int);
 
-void nv92_gpio_intr_stat(struct nouveau_gpio *, u32 *, u32 *);
-void nv92_gpio_intr_mask(struct nouveau_gpio *, u32, u32, u32);
+void nv94_gpio_intr_stat(struct nouveau_gpio *, u32 *, u32 *);
+void nv94_gpio_intr_mask(struct nouveau_gpio *, u32, u32, u32);
 
 void nvd0_gpio_reset(struct nouveau_gpio *, u8);
 int  nvd0_gpio_drive(struct nouveau_gpio *, int, int, int);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
index a652cafde3d6..2b1bf545e488 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
@@ -23,6 +23,7 @@
  */
 
 #include <core/option.h>
+#include <core/object.h>
 #include <core/event.h>
 
 #include <subdev/bios.h>
@@ -346,7 +347,8 @@ nouveau_i2c_intr_init(struct nvkm_event *event, int type, int index)
 }
 
 static int
-nouveau_i2c_intr_ctor(void *data, u32 size, struct nvkm_notify *notify)
+nouveau_i2c_intr_ctor(struct nouveau_object *object, void *data, u32 size,
+		      struct nvkm_notify *notify)
 {
 	struct nvkm_i2c_ntfy_req *req = data;
 	if (!WARN_ON(size != sizeof(*req))) {
diff --git a/drivers/gpu/drm/nouveau/core/subdev/instmem/nv04.c b/drivers/gpu/drm/nouveau/core/subdev/instmem/nv04.c
index 7b64befee48f..e8b1401c59c0 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/instmem/nv04.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/instmem/nv04.c
@@ -69,7 +69,7 @@ nv04_instobj_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
-	ret = nouveau_mm_head(&priv->heap, 1, args->size, args->size,
+	ret = nouveau_mm_head(&priv->heap, 0, 1, args->size, args->size,
 			      args->align, &node->mem);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/ltc/base.c b/drivers/gpu/drm/nouveau/core/subdev/ltc/base.c
index 32ed442c5913..7fa331516f84 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/ltc/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/ltc/base.c
@@ -31,7 +31,7 @@ nvkm_ltc_tags_alloc(struct nouveau_ltc *ltc, u32 n,
 	struct nvkm_ltc_priv *priv = (void *)ltc;
 	int ret;
 
-	ret = nouveau_mm_head(&priv->tags, 1, n, n, 1, pnode);
+	ret = nouveau_mm_head(&priv->tags, 0, 1, n, n, 1, pnode);
 	if (ret)
 		*pnode = NULL;
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/ltc/gf100.c b/drivers/gpu/drm/nouveau/core/subdev/ltc/gf100.c
index d5d65285efe5..2db0977284f8 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/ltc/gf100.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/ltc/gf100.c
@@ -62,16 +62,38 @@ gf100_ltc_zbc_clear_depth(struct nvkm_ltc_priv *priv, int i, const u32 depth)
 	nv_wr32(priv, 0x17ea58, depth);
 }
 
+static const struct nouveau_bitfield
+gf100_ltc_lts_intr_name[] = {
+	{ 0x00000001, "IDLE_ERROR_IQ" },
+	{ 0x00000002, "IDLE_ERROR_CBC" },
+	{ 0x00000004, "IDLE_ERROR_TSTG" },
+	{ 0x00000008, "IDLE_ERROR_DSTG" },
+	{ 0x00000010, "EVICTED_CB" },
+	{ 0x00000020, "ILLEGAL_COMPSTAT" },
+	{ 0x00000040, "BLOCKLINEAR_CB" },
+	{ 0x00000100, "ECC_SEC_ERROR" },
+	{ 0x00000200, "ECC_DED_ERROR" },
+	{ 0x00000400, "DEBUG" },
+	{ 0x00000800, "ATOMIC_TO_Z" },
+	{ 0x00001000, "ILLEGAL_ATOMIC" },
+	{ 0x00002000, "BLKACTIVITY_ERR" },
+	{}
+};
+
 static void
-gf100_ltc_lts_isr(struct nvkm_ltc_priv *priv, int ltc, int lts)
+gf100_ltc_lts_intr(struct nvkm_ltc_priv *priv, int ltc, int lts)
 {
 	u32 base = 0x141000 + (ltc * 0x2000) + (lts * 0x400);
-	u32 stat = nv_rd32(priv, base + 0x020);
+	u32 intr = nv_rd32(priv, base + 0x020);
+	u32 stat = intr & 0x0000ffff;
 
 	if (stat) {
-		nv_info(priv, "LTC%d_LTS%d: 0x%08x\n", ltc, lts, stat);
-		nv_wr32(priv, base + 0x020, stat);
+		nv_info(priv, "LTC%d_LTS%d:", ltc, lts);
+		nouveau_bitfield_print(gf100_ltc_lts_intr_name, stat);
+		pr_cont("\n");
 	}
+
+	nv_wr32(priv, base + 0x020, intr);
 }
 
 void
@@ -84,14 +106,9 @@ gf100_ltc_intr(struct nouveau_subdev *subdev)
 	while (mask) {
 		u32 lts, ltc = __ffs(mask);
 		for (lts = 0; lts < priv->lts_nr; lts++)
-			gf100_ltc_lts_isr(priv, ltc, lts);
+			gf100_ltc_lts_intr(priv, ltc, lts);
 		mask &= ~(1 << ltc);
 	}
-
-	/* we do something horribly wrong and upset PMFB a lot, so mask off
-	 * interrupts from it after the first one until it's fixed
-	 */
-	nv_mask(priv, 0x000640, 0x02000000, 0x00000000);
 }
 
 static int
@@ -153,7 +170,7 @@ gf100_ltc_init_tag_ram(struct nouveau_fb *pfb, struct nvkm_ltc_priv *priv)
 	tag_size += tag_align;
 	tag_size  = (tag_size + 0xfff) >> 12; /* round up */
 
-	ret = nouveau_mm_tail(&pfb->vram, 1, tag_size, tag_size, 1,
+	ret = nouveau_mm_tail(&pfb->vram, 1, 1, tag_size, tag_size, 1,
 	                      &priv->tag_ram);
 	if (ret) {
 		priv->num_tags = 0;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/ltc/gm107.c b/drivers/gpu/drm/nouveau/core/subdev/ltc/gm107.c
index a4de64289762..89fc4238f50c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/ltc/gm107.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/ltc/gm107.c
@@ -87,11 +87,6 @@ gm107_ltc_intr(struct nouveau_subdev *subdev)
 			gm107_ltc_lts_isr(priv, ltc, lts);
 		mask &= ~(1 << ltc);
 	}
-
-	/* we do something horribly wrong and upset PMFB a lot, so mask off
-	 * interrupts from it after the first one until it's fixed
-	 */
-	nv_mask(priv, 0x000640, 0x02000000, 0x00000000);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/core/subdev/ltc/priv.h b/drivers/gpu/drm/nouveau/core/subdev/ltc/priv.h
index 594924f39126..41f179d93da6 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/ltc/priv.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/ltc/priv.h
@@ -4,6 +4,8 @@
 #include <subdev/ltc.h>
 #include <subdev/fb.h>
 
+#include <core/enum.h>
+
 struct nvkm_ltc_priv {
 	struct nouveau_ltc base;
 	u32 ltc_nr;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/base.c b/drivers/gpu/drm/nouveau/core/subdev/pwr/base.c
index 69f1f34f6931..0ab55f27ec45 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/base.c
@@ -203,6 +203,8 @@ _nouveau_pwr_init(struct nouveau_object *object)
 	nv_wait(ppwr, 0x10a04c, 0xffffffff, 0x00000000);
 	nv_mask(ppwr, 0x000200, 0x00002000, 0x00000000);
 	nv_mask(ppwr, 0x000200, 0x00002000, 0x00002000);
+	nv_rd32(ppwr, 0x000200);
+	nv_wait(ppwr, 0x10a10c, 0x00000006, 0x00000000);
 
 	/* upload data segment */
 	nv_wr32(ppwr, 0x10a1c0, 0x01000000);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/arith.fuc b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/arith.fuc
new file mode 100644
index 000000000000..214a6d9e088d
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/arith.fuc
@@ -0,0 +1,94 @@
+/*
+ * Copyright 2014 Martin Peres <martin.peres@free.fr>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the folloing conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Martin Peres
+ */
+
+/******************************************************************************
+ * arith data segment
+ *****************************************************************************/
+#ifdef INCLUDE_PROC
+#endif
+
+#ifdef INCLUDE_DATA
+#endif
+
+/******************************************************************************
+ * arith code segment
+ *****************************************************************************/
+#ifdef INCLUDE_CODE
+
+// does a 32x32 -> 64 multiplication
+//
+// A * B = A_lo * B_lo
+//        + ( A_hi * B_lo ) << 16
+//        + ( A_lo * B_hi ) << 16
+//        + ( A_hi * B_hi ) << 32
+//
+// $r15 - current
+// $r14 - A
+// $r13 - B
+// $r12 - mul_lo (return)
+// $r11 - mul_hi (return)
+// $r0  - zero
+mulu32_32_64:
+	push $r1 // A_hi
+	push $r2 // B_hi
+	push $r3 // tmp0
+	push $r4 // tmp1
+
+	shr b32 $r1 $r14 16
+	shr b32 $r2 $r13 16
+
+	clear b32 $r12
+	clear b32 $r11
+
+	// A_lo * B_lo
+	mulu $r12 $r14 $r13
+
+	// ( A_hi * B_lo ) << 16
+	mulu $r3 $r1 $r13 // tmp0 = A_hi * B_lo
+	mov b32 $r4 $r3
+	and $r3 0xffff // tmp0 = tmp0_lo
+	shl b32 $r3 16
+	shr b32 $r4 16 // tmp1 = tmp0_hi
+	add b32 $r12 $r3
+	adc b32 $r11 $r4
+
+	// ( A_lo * B_hi ) << 16
+	mulu $r3 $r14 $r2 // tmp0 = A_lo * B_hi
+	mov b32 $r4 $r3
+	and $r3 0xffff // tmp0 = tmp0_lo
+	shl b32 $r3 16
+	shr b32 $r4 16 // tmp1 = tmp0_hi
+	add b32 $r12 $r3
+	adc b32 $r11 $r4
+
+	// ( A_hi * B_hi ) << 32
+	mulu $r3 $r1 $r2 // tmp0 = A_hi * B_hi
+	add b32 $r11 $r3
+
+	pop $r4
+	pop $r3
+	pop $r2
+	pop $r1
+	ret
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/kernel.fuc b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/kernel.fuc
index 8f29badd785f..5cf5be63cbef 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/kernel.fuc
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/kernel.fuc
@@ -98,12 +98,16 @@ wr32:
 // $r14 - ns
 // $r0  - zero
 nsec:
+	push $r9
+	push $r8
 	nv_iord($r8, NV_PPWR_TIMER_LOW)
 	nsec_loop:
 		nv_iord($r9, NV_PPWR_TIMER_LOW)
 		sub b32 $r9 $r8
 		cmp b32 $r9 $r14
 		bra l #nsec_loop
+	pop $r8
+	pop $r9
 	ret
 
 // busy-wait for a period of time
@@ -115,6 +119,8 @@ nsec:
 // $r11 - timeout (ns)
 // $r0  - zero
 wait:
+	push $r9
+	push $r8
 	nv_iord($r8, NV_PPWR_TIMER_LOW)
 	wait_loop:
 		nv_rd32($r10, $r14)
@@ -126,6 +132,8 @@ wait:
 		cmp b32 $r9 $r11
 		bra l #wait_loop
 	wait_done:
+	pop $r8
+	pop $r9
 	ret
 
 // $r15 - current (kern)
@@ -242,12 +250,89 @@ intr:
 	bclr $flags $p0
 	iret
 
-// request the current process be sent a message after a timeout expires
+// calculate the number of ticks in the specified nanoseconds delay
+//
+// $r15 - current
+// $r14 - ns
+// $r14 - ticks (return)
+// $r0  - zero
+ticks_from_ns:
+	push $r12
+	push $r11
+
+	/* try not losing precision (multiply then divide) */
+	imm32($r13, HW_TICKS_PER_US)
+	call #mulu32_32_64
+
+	/* use an immeditate, it's ok because HW_TICKS_PER_US < 16 bits */
+	div $r12 $r12 1000
+
+	/* check if there wasn't any overflow */
+	cmpu b32 $r11 0
+	bra e #ticks_from_ns_quit
+
+	/* let's divide then multiply, too bad for the precision! */
+	div $r14 $r14 1000
+	imm32($r13, HW_TICKS_PER_US)
+	call #mulu32_32_64
+
+	/* this cannot overflow as long as HW_TICKS_PER_US < 1000 */
+
+ticks_from_ns_quit:
+	mov b32 $r14 $r12
+	pop $r11
+	pop $r12
+	ret
+
+// calculate the number of ticks in the specified microsecond delay
+//
+// $r15 - current
+// $r14 - us
+// $r14 - ticks (return)
+// $r0  - zero
+ticks_from_us:
+	push $r12
+	push $r11
+
+	/* simply multiply $us by HW_TICKS_PER_US */
+	imm32($r13, HW_TICKS_PER_US)
+	call #mulu32_32_64
+	mov b32 $r14 $r12
+
+	/* check if there wasn't any overflow */
+	cmpu b32 $r11 0
+	bra e #ticks_from_us_quit
+
+	/* Overflow! */
+	clear b32 $r14
+
+ticks_from_us_quit:
+	pop $r11
+	pop $r12
+	ret
+
+// calculate the number of ticks in the specified microsecond delay
 //
 // $r15 - current
 // $r14 - ticks
+// $r14 - us (return)
+// $r0  - zero
+ticks_to_us:
+	/* simply divide $ticks by HW_TICKS_PER_US */
+	imm32($r13, HW_TICKS_PER_US)
+	div $r14 $r14 $r13
+
+	ret
+
+// request the current process be sent a message after a timeout expires
+//
+// $r15 - current
+// $r14 - ticks (make sure it is < 2^31 to avoid any possible overflow)
 // $r0  - zero
 timer:
+	push $r9
+	push $r8
+
 	// interrupts off to prevent racing with timer isr
 	bclr $flags ie0
 
@@ -255,13 +340,22 @@ timer:
 	ld b32 $r8 D[$r15 + #proc_time]
 	cmp b32 $r8 0
 	bra g #timer_done
-	st b32 D[$r15 + #proc_time] $r14
 
-	// halt watchdog timer temporarily and check for a pending
-	// interrupt.  if there's one already pending, we can just
-	// bail since the timer isr will queue the next soonest
-	// right after it's done
+	// halt watchdog timer temporarily
+	clear b32 $r8
 	nv_iowr(NV_PPWR_WATCHDOG_ENABLE, $r8)
+
+	// find out how much time elapsed since the last update
+	// of the watchdog and add this time to the wanted ticks
+	nv_iord($r8, NV_PPWR_WATCHDOG_TIME)
+	ld b32 $r9 D[$r0 + #time_prev]
+	sub b32 $r9 $r8
+	add b32 $r14 $r9
+	st b32 D[$r15 + #proc_time] $r14
+
+	// check for a pending interrupt.  if there's one already
+	// pending, we can just bail since the timer isr will
+	// queue the next soonest right after it's done
 	nv_iord($r8, NV_PPWR_INTR)
 	and $r8 NV_PPWR_INTR_WATCHDOG
 	bra nz #timer_enable
@@ -272,10 +366,10 @@ timer:
 	cmp b32 $r14 $r0
 	bra e #timer_reset
 	cmp b32 $r14 $r8
-	bra l #timer_done
-	timer_reset:
-	nv_iowr(NV_PPWR_WATCHDOG_TIME, $r14)
-	st b32 D[$r0 + #time_prev] $r14
+	bra g #timer_enable
+		timer_reset:
+		nv_iowr(NV_PPWR_WATCHDOG_TIME, $r14)
+		st b32 D[$r0 + #time_prev] $r14
 
 	// re-enable the watchdog timer
 	timer_enable:
@@ -285,6 +379,9 @@ timer:
 	// interrupts back on
 	timer_done:
 	bset $flags ie0
+
+	pop $r8
+	pop $r9
 	ret
 
 // send message to another process
@@ -371,6 +468,9 @@ send:
 // $r14 - process
 // $r0  - zero
 recv:
+	push $r9
+	push $r8
+
 	ld b32 $r8 D[$r14 + #proc_qget]
 	ld b32 $r9 D[$r14 + #proc_qput]
 	bclr $flags $p1
@@ -403,6 +503,8 @@ recv:
 		bset $flags $p1
 		pop $r15
 	recv_done:
+	pop $r8
+	pop $r9
 	ret
 
 init:
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/macros.fuc b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/macros.fuc
index 5668e045bac1..96fc984dafdc 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/macros.fuc
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/macros.fuc
@@ -250,3 +250,23 @@
 */	st b32 D[$r0] reg /*
 */	clear b32 $r0
 #endif
+
+#define st(size, addr, reg) /*
+*/	movw $r0 addr /*
+*/	st size D[$r0] reg /*
+*/	clear b32 $r0
+
+#define ld(size, reg, addr) /*
+*/	movw $r0 addr /*
+*/	ld size reg D[$r0] /*
+*/	clear b32 $r0
+
+// does a 64+64 -> 64 unsigned addition (C = A + B)
+#define addu64(reg_a_c_hi, reg_a_c_lo, b_hi, b_lo) /*
+*/    add b32 reg_a_c_lo b_lo /*
+*/    adc b32 reg_a_c_hi b_hi
+
+// does a 64+64 -> 64 substraction (C = A - B)
+#define subu64(reg_a_c_hi, reg_a_c_lo, b_hi, b_lo) /*
+*/    sub b32 reg_a_c_lo b_lo /*
+*/    sbb b32 reg_a_c_hi b_hi
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/memx.fuc b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/memx.fuc
index d43741eccb11..e89789a53b80 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/memx.fuc
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/memx.fuc
@@ -43,17 +43,23 @@ process(PROC_MEMX, #memx_init, #memx_recv)
 */	.b32 func
 
 memx_func_head:
-handler(ENTER , 0x0001, 0x0000, #memx_func_enter)
+handler(ENTER , 0x0000, 0x0000, #memx_func_enter)
 memx_func_next:
 handler(LEAVE , 0x0000, 0x0000, #memx_func_leave)
 handler(WR32  , 0x0000, 0x0002, #memx_func_wr32)
 handler(WAIT  , 0x0004, 0x0000, #memx_func_wait)
 handler(DELAY , 0x0001, 0x0000, #memx_func_delay)
+handler(VBLANK, 0x0001, 0x0000, #memx_func_wait_vblank)
 memx_func_tail:
 
 .equ #memx_func_size #memx_func_next - #memx_func_head
 .equ #memx_func_num (#memx_func_tail - #memx_func_head) / #memx_func_size
 
+memx_ts_start:
+.b32 0
+memx_ts_end:
+.b32 0
+
 memx_data_head:
 .skip 0x0800
 memx_data_tail:
@@ -67,19 +73,44 @@ memx_data_tail:
 //
 // $r15 - current (memx)
 // $r4  - packet length
-//	+00: bitmask of heads to wait for vblank on
 // $r3  - opcode desciption
 // $r0  - zero
 memx_func_enter:
+#if NVKM_PPWR_CHIPSET == GT215
+	movw $r8 0x1610
+	nv_rd32($r7, $r8)
+	imm32($r6, 0xfffffffc)
+	and $r7 $r6
+	movw $r6 0x2
+	or $r7 $r6
+	nv_wr32($r8, $r7)
+#else
+	movw $r6 0x001620
+	imm32($r7, ~0x00000aa2);
+	nv_rd32($r8, $r6)
+	and $r8 $r7
+	nv_wr32($r6, $r8)
+
+	imm32($r7, ~0x00000001)
+	nv_rd32($r8, $r6)
+	and $r8 $r7
+	nv_wr32($r6, $r8)
+
+	movw $r6 0x0026f0
+	nv_rd32($r8, $r6)
+	and $r8 $r7
+	nv_wr32($r6, $r8)
+#endif
+
 	mov $r6 NV_PPWR_OUTPUT_SET_FB_PAUSE
 	nv_iowr(NV_PPWR_OUTPUT_SET, $r6)
 	memx_func_enter_wait:
 		nv_iord($r6, NV_PPWR_OUTPUT)
 		and $r6 NV_PPWR_OUTPUT_FB_PAUSE
 		bra z #memx_func_enter_wait
-	//XXX: TODO
-	ld b32 $r6 D[$r1 + 0x00]
-	add b32 $r1 0x04
+
+	nv_iord($r6, NV_PPWR_TIMER_LOW)
+	st b32 D[$r0 + #memx_ts_start] $r6
 	ret
 
 // description
@@ -89,14 +120,93 @@ memx_func_enter:
 // $r3  - opcode desciption
 // $r0  - zero
 memx_func_leave:
+	nv_iord($r6, NV_PPWR_TIMER_LOW)
+	st b32 D[$r0 + #memx_ts_end] $r6
+
 	mov $r6 NV_PPWR_OUTPUT_CLR_FB_PAUSE
 	nv_iowr(NV_PPWR_OUTPUT_CLR, $r6)
 	memx_func_leave_wait:
 		nv_iord($r6, NV_PPWR_OUTPUT)
 		and $r6 NV_PPWR_OUTPUT_FB_PAUSE
 		bra nz #memx_func_leave_wait
+
+#if NVKM_PPWR_CHIPSET == GT215
+	movw $r8 0x1610
+	nv_rd32($r7, $r8)
+	imm32($r6, 0xffffffcc)
+	and $r7 $r6
+	nv_wr32($r8, $r7)
+#else
+	movw $r6 0x0026f0
+	imm32($r7, 0x00000001)
+	nv_rd32($r8, $r6)
+	or $r8 $r7
+	nv_wr32($r6, $r8)
+
+	movw $r6 0x001620
+	nv_rd32($r8, $r6)
+	or $r8 $r7
+	nv_wr32($r6, $r8)
+
+	imm32($r7, 0x00000aa2);
+	nv_rd32($r8, $r6)
+	or $r8 $r7
+	nv_wr32($r6, $r8)
+#endif
+	ret
+
+#if NVKM_PPWR_CHIPSET < GF119
+// description
+//
+// $r15 - current (memx)
+// $r4  - packet length
+//	+00: head to wait for vblank on
+// $r3  - opcode desciption
+// $r0  - zero
+memx_func_wait_vblank:
+	ld b32 $r6 D[$r1 + 0x00]
+	cmp b32 $r6 0x0
+	bra z #memx_func_wait_vblank_head0
+	cmp b32 $r6 0x1
+	bra z #memx_func_wait_vblank_head1
+	bra #memx_func_wait_vblank_fini
+
+	memx_func_wait_vblank_head1:
+	movw $r7 0x20
+	bra #memx_func_wait_vblank_0
+
+	memx_func_wait_vblank_head0:
+	movw $r7 0x8
+
+	memx_func_wait_vblank_0:
+		nv_iord($r6, NV_PPWR_INPUT)
+		and $r6 $r7
+		bra nz #memx_func_wait_vblank_0
+
+	memx_func_wait_vblank_1:
+		nv_iord($r6, NV_PPWR_INPUT)
+		and $r6 $r7
+		bra z #memx_func_wait_vblank_1
+
+	memx_func_wait_vblank_fini:
+	add b32 $r1 0x4
+	ret
+
+#else
+
+// XXX: currently no-op
+//
+// $r15 - current (memx)
+// $r4  - packet length
+//	+00: head to wait for vblank on
+// $r3  - opcode desciption
+// $r0  - zero
+memx_func_wait_vblank:
+	add b32 $r1 0x4
 	ret
 
+#endif
+
 // description
 //
 // $r15 - current (memx)
@@ -160,14 +270,17 @@ memx_exec:
 	push $r13
 	mov b32 $r1 $r12
 	mov b32 $r2 $r11
+
 	memx_exec_next:
-		// fetch the packet header, and locate opcode info
+		// fetch the packet header
 		ld b32 $r3 D[$r1]
 		add b32 $r1 4
-		shr b32 $r4 $r3 16
-		mulu $r3 #memx_func_size
+		extr $r4 $r3 16:31
+		extr $r3 $r3 0:15
 
 		// execute the opcode handler
+		sub b32 $r3 1
+		mulu $r3 #memx_func_size
 		ld b32 $r5 D[$r3 + #memx_func_head + #memx_func]
 		call $r5
 
@@ -176,6 +289,10 @@ memx_exec:
 		bra l #memx_exec_next
 
 	// send completion reply
+	ld b32 $r11 D[$r0 + #memx_ts_start]
+	ld b32 $r12 D[$r0 + #memx_ts_end]
+	sub b32 $r12 $r11
+	nv_iord($r11, NV_PPWR_INPUT)
 	pop $r13
 	pop $r14
 	call(send)
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc
index 17a8a383d91a..b439519ec866 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc
@@ -23,6 +23,7 @@
  */
 
 #define NVKM_PPWR_CHIPSET GK208
+#define HW_TICKS_PER_US 324
 
 #define NVKM_FALCON_PC24
 #define NVKM_FALCON_UNSHIFTED_IO
@@ -34,6 +35,7 @@
 .section #nv108_pwr_data
 #define INCLUDE_PROC
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
@@ -44,6 +46,7 @@
 
 #define INCLUDE_DATA
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
@@ -56,6 +59,7 @@
 .section #nv108_pwr_code
 #define INCLUDE_CODE
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h
index 986495d533dd..4d278a96b2bb 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h
@@ -24,8 +24,8 @@ uint32_t nv108_pwr_data[] = {
 	0x00000000,
 /* 0x0058: proc_list_head */
 	0x54534f48,
-	0x00000379,
-	0x0000032a,
+	0x00000453,
+	0x00000404,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -46,8 +46,8 @@ uint32_t nv108_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x584d454d,
-	0x00000464,
-	0x00000456,
+	0x0000061c,
+	0x0000060e,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -68,8 +68,8 @@ uint32_t nv108_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x46524550,
-	0x00000468,
-	0x00000466,
+	0x00000620,
+	0x0000061e,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -90,8 +90,8 @@ uint32_t nv108_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x5f433249,
-	0x0000086c,
-	0x00000713,
+	0x00000a24,
+	0x000008cb,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -112,8 +112,8 @@ uint32_t nv108_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x54534554,
-	0x0000088d,
-	0x0000086e,
+	0x00000a45,
+	0x00000a26,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -134,8 +134,8 @@ uint32_t nv108_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x454c4449,
-	0x00000898,
-	0x00000896,
+	0x00000a50,
+	0x00000a4e,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -227,25 +227,31 @@ uint32_t nv108_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 /* 0x0370: memx_func_head */
-	0x00010000,
-	0x00000000,
-	0x000003a9,
-/* 0x037c: memx_func_next */
 	0x00000001,
 	0x00000000,
-	0x000003c7,
+	0x00000483,
+/* 0x037c: memx_func_next */
 	0x00000002,
+	0x00000000,
+	0x00000500,
+	0x00000003,
 	0x00000002,
-	0x000003df,
-	0x00040003,
+	0x00000580,
+	0x00040004,
+	0x00000000,
+	0x0000059d,
+	0x00010005,
+	0x00000000,
+	0x000005b7,
+	0x00010006,
 	0x00000000,
-	0x000003fc,
-	0x00010004,
+	0x0000057b,
+/* 0x03b8: memx_func_tail */
+/* 0x03b8: memx_ts_start */
 	0x00000000,
-	0x00000416,
-/* 0x03ac: memx_func_tail */
-/* 0x03ac: memx_data_head */
+/* 0x03bc: memx_ts_end */
 	0x00000000,
+/* 0x03c0: memx_data_head */
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -757,8 +763,9 @@ uint32_t nv108_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
-/* 0x0bac: memx_data_tail */
-/* 0x0bac: i2c_scl_map */
+	0x00000000,
+/* 0x0bc0: memx_data_tail */
+/* 0x0bc0: i2c_scl_map */
 	0x00000400,
 	0x00000800,
 	0x00001000,
@@ -769,7 +776,7 @@ uint32_t nv108_pwr_data[] = {
 	0x00020000,
 	0x00040000,
 	0x00080000,
-/* 0x0bd4: i2c_sda_map */
+/* 0x0be8: i2c_sda_map */
 	0x00100000,
 	0x00200000,
 	0x00400000,
@@ -781,10 +788,69 @@ uint32_t nv108_pwr_data[] = {
 	0x10000000,
 	0x20000000,
 	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 };
 
 uint32_t nv108_pwr_code[] = {
-	0x02910ef5,
+	0x031c0ef5,
 /* 0x0004: rd32 */
 	0xf607a040,
 	0x04bd000e,
@@ -812,15 +878,18 @@ uint32_t nv108_pwr_code[] = {
 	0x7000d4f1,
 	0xf8f61bf4,
 /* 0x005d: nsec */
-	0xcf2c0800,
-/* 0x0062: nsec_loop */
+	0xf990f900,
+	0xcf2c0880,
+/* 0x0066: nsec_loop */
 	0x2c090088,
 	0xbb0099cf,
 	0x9ea60298,
-	0xf8f61ef4,
-/* 0x0071: wait */
-	0xcf2c0800,
-/* 0x0076: wait_loop */
+	0xfcf61ef4,
+	0xf890fc80,
+/* 0x0079: wait */
+	0xf990f900,
+	0xcf2c0880,
+/* 0x0082: wait_loop */
 	0xeeb20088,
 	0x0000047e,
 	0xadfddab2,
@@ -828,28 +897,29 @@ uint32_t nv108_pwr_code[] = {
 	0x2c09100b,
 	0xbb0099cf,
 	0x9ba60298,
-/* 0x0093: wait_done */
-	0xf8e61ef4,
-/* 0x0095: intr_watchdog */
+/* 0x009f: wait_done */
+	0xfce61ef4,
+	0xf890fc80,
+/* 0x00a5: intr_watchdog */
 	0x03e99800,
 	0xf40096b0,
 	0x0a98280b,
 	0x029abb9a,
 	0x0d0e1cf4,
-	0x01de7e01,
+	0x02617e01,
 	0xf494bd00,
-/* 0x00b2: intr_watchdog_next_time */
+/* 0x00c2: intr_watchdog_next_time */
 	0x0a98140e,
 	0x00a6b09b,
 	0xa6080bf4,
 	0x061cf49a,
-/* 0x00c0: intr_watchdog_next_time_set */
-/* 0x00c3: intr_watchdog_next_proc */
+/* 0x00d0: intr_watchdog_next_time_set */
+/* 0x00d3: intr_watchdog_next_proc */
 	0xb59b09b5,
 	0xe0b603e9,
 	0x68e6b158,
 	0xc81bf402,
-/* 0x00d2: intr */
+/* 0x00e2: intr */
 	0x00f900f8,
 	0x80f904bd,
 	0xa0f990f9,
@@ -865,13 +935,13 @@ uint32_t nv108_pwr_code[] = {
 	0xc40088cf,
 	0x0bf40289,
 	0x9b00b51f,
-	0x957e580e,
+	0xa57e580e,
 	0x09980000,
 	0x0096b09b,
 	0x000d0bf4,
 	0x0009f634,
 	0x09b504bd,
-/* 0x0125: intr_skip_watchdog */
+/* 0x0135: intr_skip_watchdog */
 	0x0089e49a,
 	0x360bf408,
 	0xcf068849,
@@ -881,20 +951,20 @@ uint32_t nv108_pwr_code[] = {
 	0xc0f900cc,
 	0xf14f484e,
 	0x0d5453e3,
-	0x023f7e00,
+	0x02c27e00,
 	0x40c0fc00,
 	0x0cf604c0,
-/* 0x0157: intr_subintr_skip_fifo */
+/* 0x0167: intr_subintr_skip_fifo */
 	0x4004bd00,
 	0x09f60688,
-/* 0x015f: intr_skip_subintr */
+/* 0x016f: intr_skip_subintr */
 	0xc404bd00,
 	0x0bf42089,
 	0xbfa4f107,
-/* 0x0169: intr_skip_pause */
+/* 0x0179: intr_skip_pause */
 	0x4089c4ff,
 	0xf1070bf4,
-/* 0x0173: intr_skip_user0 */
+/* 0x0183: intr_skip_user0 */
 	0x00ffbfa4,
 	0x0008f604,
 	0x80fc04bd,
@@ -904,304 +974,417 @@ uint32_t nv108_pwr_code[] = {
 	0xfca0fcb0,
 	0xfc80fc90,
 	0x0032f400,
-/* 0x0196: timer */
-	0x32f401f8,
-	0x03f89810,
-	0xf40086b0,
-	0xfeb53a1c,
-	0xf6380003,
+/* 0x01a6: ticks_from_ns */
+	0xc0f901f8,
+	0xd7f1b0f9,
+	0xd3f00144,
+	0x7721f500,
+	0xe8ccec03,
+	0x00b4b003,
+	0xec120bf4,
+	0xf103e8ee,
+	0xf00144d7,
+	0x21f500d3,
+/* 0x01ce: ticks_from_ns_quit */
+	0xceb20377,
+	0xc0fcb0fc,
+/* 0x01d6: ticks_from_us */
+	0xc0f900f8,
+	0xd7f1b0f9,
+	0xd3f00144,
+	0x7721f500,
+	0xb0ceb203,
+	0x0bf400b4,
+/* 0x01ef: ticks_from_us_quit */
+	0xfce4bd05,
+	0xf8c0fcb0,
+/* 0x01f5: ticks_to_us */
+	0x44d7f100,
+	0x00d3f001,
+	0xf8ecedff,
+/* 0x0201: timer */
+	0xf990f900,
+	0x1032f480,
+	0xb003f898,
+	0x1cf40086,
+	0x0084bd4a,
+	0x0008f638,
+	0x340804bd,
+	0x980088cf,
+	0x98bb9a09,
+	0x00e9bb02,
+	0x0803feb5,
+	0x0088cf08,
+	0xf40284f0,
+	0x34081c1b,
+	0xa60088cf,
+	0x080bf4e0,
+	0x1cf4e8a6,
+/* 0x0245: timer_reset */
+	0xf634000d,
+	0x04bd000e,
+/* 0x024f: timer_enable */
+	0x089a0eb5,
+	0xf6380001,
 	0x04bd0008,
-	0x88cf0808,
-	0x0284f000,
-	0x081c1bf4,
-	0x0088cf34,
-	0x0bf4e0a6,
-	0xf4e8a608,
-/* 0x01c6: timer_reset */
-	0x3400161e,
-	0xbd000ef6,
-	0x9a0eb504,
-/* 0x01d0: timer_enable */
-	0x38000108,
-	0xbd0008f6,
-/* 0x01d9: timer_done */
-	0x1031f404,
-/* 0x01de: send_proc */
-	0x80f900f8,
-	0xe89890f9,
-	0x04e99805,
-	0xa60486f0,
-	0x2a0bf489,
-	0x940398c4,
-	0x80b60488,
-	0x008ebb18,
-	0xb500fa98,
-	0x8db5008a,
-	0x028cb501,
-	0xb6038bb5,
-	0x94f00190,
-	0x04e9b507,
-/* 0x0217: send_done */
-	0xfc0231f4,
-	0xf880fc90,
-/* 0x021d: find */
-	0x0880f900,
-	0x0131f458,
-/* 0x0224: find_loop */
-	0xa6008a98,
-	0x100bf4ae,
-	0xb15880b6,
-	0xf4026886,
-	0x32f4f11b,
-/* 0x0239: find_done */
-	0xfc8eb201,
-/* 0x023f: send */
-	0x7e00f880,
-	0xf400021d,
-	0x00f89b01,
-/* 0x0248: recv */
-	0x9805e898,
-	0x32f404e9,
-	0xf489a601,
-	0x89c43c0b,
-	0x0180b603,
-	0xb50784f0,
-	0xea9805e8,
-	0xfef0f902,
-	0xf0f9018f,
-	0x9994efb2,
-	0x00e9bb04,
-	0x9818e0b6,
-	0xec9803eb,
-	0x01ed9802,
-	0xf900ee98,
-	0xfef0fca5,
-	0x31f400f8,
-/* 0x028f: recv_done */
-	0xf8f0fc01,
-/* 0x0291: init */
-	0x01084100,
-	0xe70011cf,
-	0xb6010911,
-	0x14fe0814,
-	0x00e04100,
-	0x000013f0,
-	0x0001f61c,
-	0xff0104bd,
-	0x01f61400,
-	0x0104bd00,
-	0x0015f102,
-	0xf6100008,
-	0x04bd0001,
-	0xf000d241,
-	0x10fe0013,
-	0x1031f400,
-	0x38000101,
+/* 0x0258: timer_done */
+	0xfc1031f4,
+	0xf890fc80,
+/* 0x0261: send_proc */
+	0xf980f900,
+	0x05e89890,
+	0xf004e998,
+	0x89a60486,
+	0xc42a0bf4,
+	0x88940398,
+	0x1880b604,
+	0x98008ebb,
+	0x8ab500fa,
+	0x018db500,
+	0xb5028cb5,
+	0x90b6038b,
+	0x0794f001,
+	0xf404e9b5,
+/* 0x029a: send_done */
+	0x90fc0231,
+	0x00f880fc,
+/* 0x02a0: find */
+	0x580880f9,
+/* 0x02a7: find_loop */
+	0x980131f4,
+	0xaea6008a,
+	0xb6100bf4,
+	0x86b15880,
+	0x1bf40268,
+	0x0132f4f1,
+/* 0x02bc: find_done */
+	0x80fc8eb2,
+/* 0x02c2: send */
+	0xa07e00f8,
+	0x01f40002,
+/* 0x02cb: recv */
+	0xf900f89b,
+	0x9880f990,
+	0xe99805e8,
+	0x0132f404,
+	0x0bf489a6,
+	0x0389c43c,
+	0xf00180b6,
+	0xe8b50784,
+	0x02ea9805,
+	0x8ffef0f9,
+	0xb2f0f901,
+	0x049994ef,
+	0xb600e9bb,
+	0xeb9818e0,
+	0x02ec9803,
+	0x9801ed98,
+	0xa5f900ee,
+	0xf8fef0fc,
+	0x0131f400,
+/* 0x0316: recv_done */
+	0x80fcf0fc,
+	0x00f890fc,
+/* 0x031c: init */
+	0xcf010841,
+	0x11e70011,
+	0x14b60109,
+	0x0014fe08,
+	0xf000e041,
+	0x1c000013,
 	0xbd0001f6,
-/* 0x02db: init_proc */
-	0x98580f04,
-	0x16b001f1,
-	0xfa0bf400,
-	0xf0b615f9,
-	0xf20ef458,
-/* 0x02ec: host_send */
-	0xcf04b041,
-	0xa0420011,
-	0x0022cf04,
-	0x0bf412a6,
-	0x071ec42e,
-	0xb704ee94,
-	0x980270e0,
-	0xec9803eb,
-	0x01ed9802,
-	0x7e00ee98,
-	0xb600023f,
-	0x1ec40110,
-	0x04b0400f,
-	0xbd000ef6,
-	0xc70ef404,
-/* 0x0328: host_send_done */
-/* 0x032a: host_recv */
-	0x494100f8,
-	0x5413f14e,
-	0xf4e1a652,
-/* 0x0336: host_recv_wait */
-	0xcc41b90b,
-	0x0011cf04,
-	0xcf04c842,
-	0x16f00022,
-	0xf412a608,
-	0x23c4ef0b,
-	0x0434b607,
-	0x02f030b7,
-	0xb5033bb5,
-	0x3db5023c,
-	0x003eb501,
-	0xf00120b6,
-	0xc8400f24,
-	0x0002f604,
-	0x400204bd,
-	0x02f60000,
-	0xf804bd00,
-/* 0x0379: host_init */
-	0x00804100,
-	0xf11014b6,
-	0x40027015,
-	0x01f604d0,
+	0x00ff0104,
+	0x0001f614,
+	0x020104bd,
+	0x080015f1,
+	0x01f61000,
 	0x4104bd00,
+	0x13f000e2,
+	0x0010fe00,
+	0x011031f4,
+	0xf6380001,
+	0x04bd0001,
+/* 0x0366: init_proc */
+	0xf198580f,
+	0x0016b001,
+	0xf9fa0bf4,
+	0x58f0b615,
+/* 0x0377: mulu32_32_64 */
+	0xf9f20ef4,
+	0xf920f910,
+	0x9540f930,
+	0xd29510e1,
+	0xbdc4bd10,
+	0xc0edffb4,
+	0xb2301dff,
+	0xff34f134,
+	0x1034b6ff,
+	0xbb1045b6,
+	0xb4bb00c3,
+	0x30e2ff01,
+	0x34f134b2,
+	0x34b6ffff,
+	0x1045b610,
+	0xbb00c3bb,
+	0x12ff01b4,
+	0x00b3bb30,
+	0x30fc40fc,
+	0x10fc20fc,
+/* 0x03c6: host_send */
+	0xb04100f8,
+	0x0011cf04,
+	0xcf04a042,
+	0x12a60022,
+	0xc42e0bf4,
+	0xee94071e,
+	0x70e0b704,
+	0x03eb9802,
+	0x9802ec98,
+	0xee9801ed,
+	0x02c27e00,
+	0x0110b600,
+	0x400f1ec4,
+	0x0ef604b0,
+	0xf404bd00,
+/* 0x0402: host_send_done */
+	0x00f8c70e,
+/* 0x0404: host_recv */
+	0xf14e4941,
+	0xa6525413,
+	0xb90bf4e1,
+/* 0x0410: host_recv_wait */
+	0xcf04cc41,
+	0xc8420011,
+	0x0022cf04,
+	0xa60816f0,
+	0xef0bf412,
+	0xb60723c4,
+	0x30b70434,
+	0x3bb502f0,
+	0x023cb503,
+	0xb5013db5,
+	0x20b6003e,
+	0x0f24f001,
+	0xf604c840,
+	0x04bd0002,
+	0x00004002,
+	0xbd0002f6,
+/* 0x0453: host_init */
+	0x4100f804,
 	0x14b60080,
-	0xf015f110,
-	0x04dc4002,
+	0x7015f110,
+	0x04d04002,
+	0xbd0001f6,
+	0x00804104,
+	0xf11014b6,
+	0x4002f015,
+	0x01f604dc,
+	0x0104bd00,
+	0x04c44001,
 	0xbd0001f6,
-	0x40010104,
-	0x01f604c4,
-	0xf804bd00,
-/* 0x03a9: memx_func_enter */
-	0x40040600,
-	0x06f607e0,
-/* 0x03b3: memx_func_enter_wait */
-	0x4604bd00,
-	0x66cf07c0,
-	0x0464f000,
-	0x98f70bf4,
-	0x10b60016,
-/* 0x03c7: memx_func_leave */
-	0x0600f804,
-	0x07e44004,
-	0xbd0006f6,
-/* 0x03d1: memx_func_leave_wait */
-	0x07c04604,
-	0xf00066cf,
-	0x1bf40464,
-/* 0x03df: memx_func_wr32 */
-	0x9800f8f7,
-	0x15980016,
-	0x0810b601,
-	0x50f960f9,
+/* 0x0483: memx_func_enter */
+	0xf100f804,
+	0xf1162067,
+	0xf1f55d77,
+	0xb2ffff73,
+	0x00047e6e,
+	0xfdd8b200,
+	0x60f90487,
+	0xd0fc80f9,
+	0x2e7ee0fc,
+	0x77f10000,
+	0x73f1fffe,
+	0x6eb2ffff,
+	0x0000047e,
+	0x87fdd8b2,
+	0xf960f904,
+	0xfcd0fc80,
+	0x002e7ee0,
+	0xf067f100,
+	0x7e6eb226,
+	0xb2000004,
+	0x0487fdd8,
+	0x80f960f9,
 	0xe0fcd0fc,
 	0x00002e7e,
-	0xf40242b6,
-	0x00f8e81b,
-/* 0x03fc: memx_func_wait */
-	0x88cf2c08,
-	0x001e9800,
-	0x98011d98,
-	0x1b98021c,
-	0x1010b603,
-	0x0000717e,
-/* 0x0416: memx_func_delay */
-	0x1e9800f8,
-	0x0410b600,
-	0x00005d7e,
-/* 0x0422: memx_exec */
-	0xe0f900f8,
-	0xc1b2d0f9,
-/* 0x042a: memx_exec_next */
-	0x1398b2b2,
-	0x0410b600,
-	0xf0103495,
-	0x35980c30,
-	0xa655f9de,
-	0xed1ef412,
+	0xe0400406,
+	0x0006f607,
+/* 0x04ea: memx_func_enter_wait */
+	0xc04604bd,
+	0x0066cf07,
+	0xf40464f0,
+	0x2c06f70b,
+	0xb50066cf,
+	0x00f8ee06,
+/* 0x0500: memx_func_leave */
+	0x66cf2c06,
+	0xef06b500,
+	0xe4400406,
+	0x0006f607,
+/* 0x0512: memx_func_leave_wait */
+	0xc04604bd,
+	0x0066cf07,
+	0xf40464f0,
+	0x67f1f71b,
+	0x77f126f0,
+	0x73f00001,
+	0x7e6eb200,
+	0xb2000004,
+	0x0587fdd8,
+	0x80f960f9,
 	0xe0fcd0fc,
-	0x00023f7e,
-/* 0x044a: memx_info */
-	0xac4c00f8,
+	0x00002e7e,
+	0x162067f1,
+	0x047e6eb2,
+	0xd8b20000,
+	0xf90587fd,
+	0xfc80f960,
+	0x7ee0fcd0,
+	0xf100002e,
+	0xf00aa277,
+	0x6eb20073,
+	0x0000047e,
+	0x87fdd8b2,
+	0xf960f905,
+	0xfcd0fc80,
+	0x002e7ee0,
+/* 0x057b: memx_func_wait_vblank */
+	0xb600f800,
+	0x00f80410,
+/* 0x0580: memx_func_wr32 */
+	0x98001698,
+	0x10b60115,
+	0xf960f908,
+	0xfcd0fc50,
+	0x002e7ee0,
+	0x0242b600,
+	0xf8e81bf4,
+/* 0x059d: memx_func_wait */
+	0xcf2c0800,
+	0x1e980088,
+	0x011d9800,
+	0x98021c98,
+	0x10b6031b,
+	0x00797e10,
+/* 0x05b7: memx_func_delay */
+	0x9800f800,
+	0x10b6001e,
+	0x005d7e04,
+/* 0x05c3: memx_exec */
+	0xf900f800,
+	0xb2d0f9e0,
+/* 0x05cb: memx_exec_next */
+	0x98b2b2c1,
+	0x10b60013,
+	0xf034e704,
+	0xe033e701,
+	0x0132b601,
+	0x980c30f0,
+	0x55f9de35,
+	0x1ef412a6,
+	0xee0b98e5,
+	0xbbef0c98,
+	0xc44b02cb,
+	0x00bbcf07,
+	0xe0fcd0fc,
+	0x0002c27e,
+/* 0x0602: memx_info */
+	0xc04c00f8,
 	0x08004b03,
-	0x00023f7e,
-/* 0x0456: memx_recv */
+	0x0002c27e,
+/* 0x060e: memx_recv */
 	0xd6b000f8,
-	0xc90bf401,
+	0xb20bf401,
 	0xf400d6b0,
 	0x00f8eb0b,
-/* 0x0464: memx_init */
-/* 0x0466: perf_recv */
+/* 0x061c: memx_init */
+/* 0x061e: perf_recv */
 	0x00f800f8,
-/* 0x0468: perf_init */
-/* 0x046a: i2c_drive_scl */
+/* 0x0620: perf_init */
+/* 0x0622: i2c_drive_scl */
 	0x36b000f8,
 	0x0d0bf400,
 	0xf607e040,
 	0x04bd0001,
-/* 0x047a: i2c_drive_scl_lo */
+/* 0x0632: i2c_drive_scl_lo */
 	0xe44000f8,
 	0x0001f607,
 	0x00f804bd,
-/* 0x0484: i2c_drive_sda */
+/* 0x063c: i2c_drive_sda */
 	0xf40036b0,
 	0xe0400d0b,
 	0x0002f607,
 	0x00f804bd,
-/* 0x0494: i2c_drive_sda_lo */
+/* 0x064c: i2c_drive_sda_lo */
 	0xf607e440,
 	0x04bd0002,
-/* 0x049e: i2c_sense_scl */
+/* 0x0656: i2c_sense_scl */
 	0x32f400f8,
 	0x07c44301,
 	0xfd0033cf,
 	0x0bf40431,
 	0x0131f406,
-/* 0x04b0: i2c_sense_scl_done */
-/* 0x04b2: i2c_sense_sda */
+/* 0x0668: i2c_sense_scl_done */
+/* 0x066a: i2c_sense_sda */
 	0x32f400f8,
 	0x07c44301,
 	0xfd0033cf,
 	0x0bf40432,
 	0x0131f406,
-/* 0x04c4: i2c_sense_sda_done */
-/* 0x04c6: i2c_raise_scl */
+/* 0x067c: i2c_sense_sda_done */
+/* 0x067e: i2c_raise_scl */
 	0x40f900f8,
 	0x03089844,
-	0x046a7e01,
-/* 0x04d1: i2c_raise_scl_wait */
+	0x06227e01,
+/* 0x0689: i2c_raise_scl_wait */
 	0x03e84e00,
 	0x00005d7e,
-	0x00049e7e,
+	0x0006567e,
 	0xb60901f4,
 	0x1bf40142,
-/* 0x04e5: i2c_raise_scl_done */
+/* 0x069d: i2c_raise_scl_done */
 	0xf840fcef,
-/* 0x04e9: i2c_start */
-	0x049e7e00,
+/* 0x06a1: i2c_start */
+	0x06567e00,
 	0x0d11f400,
-	0x0004b27e,
+	0x00066a7e,
 	0xf40611f4,
-/* 0x04fa: i2c_start_rep */
+/* 0x06b2: i2c_start_rep */
 	0x00032e0e,
-	0x00046a7e,
-	0x847e0103,
-	0x76bb0004,
+	0x0006227e,
+	0x3c7e0103,
+	0x76bb0006,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0x7e50fc04,
-	0xb60004c6,
+	0xb600067e,
 	0x11f40464,
-/* 0x0525: i2c_start_send */
+/* 0x06dd: i2c_start_send */
 	0x7e00031d,
-	0x4e000484,
+	0x4e00063c,
 	0x5d7e1388,
 	0x00030000,
-	0x00046a7e,
+	0x0006227e,
 	0x7e13884e,
-/* 0x053f: i2c_start_out */
+/* 0x06f7: i2c_start_out */
 	0xf800005d,
-/* 0x0541: i2c_stop */
+/* 0x06f9: i2c_stop */
 	0x7e000300,
-	0x0300046a,
-	0x04847e00,
+	0x03000622,
+	0x063c7e00,
 	0x03e84e00,
 	0x00005d7e,
-	0x6a7e0103,
-	0x884e0004,
+	0x227e0103,
+	0x884e0006,
 	0x005d7e13,
 	0x7e010300,
-	0x4e000484,
+	0x4e00063c,
 	0x5d7e1388,
 	0x00f80000,
-/* 0x0570: i2c_bitw */
-	0x0004847e,
+/* 0x0728: i2c_bitw */
+	0x00063c7e,
 	0x7e03e84e,
 	0xbb00005d,
 	0x65b60076,
@@ -1209,44 +1392,44 @@ uint32_t nv108_pwr_code[] = {
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0004c67e,
+	0x00067e7e,
 	0xf40464b6,
 	0x884e1711,
 	0x005d7e13,
 	0x7e000300,
-	0x4e00046a,
+	0x4e000622,
 	0x5d7e1388,
-/* 0x05ae: i2c_bitw_out */
+/* 0x0766: i2c_bitw_out */
 	0x00f80000,
-/* 0x05b0: i2c_bitr */
-	0x847e0103,
-	0xe84e0004,
+/* 0x0768: i2c_bitr */
+	0x3c7e0103,
+	0xe84e0006,
 	0x005d7e03,
 	0x0076bb00,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
-	0xc67e50fc,
-	0x64b60004,
+	0x7e7e50fc,
+	0x64b60006,
 	0x1a11f404,
-	0x0004b27e,
-	0x6a7e0003,
-	0x884e0004,
+	0x00066a7e,
+	0x227e0003,
+	0x884e0006,
 	0x005d7e13,
 	0x013cf000,
-/* 0x05f3: i2c_bitr_done */
+/* 0x07ab: i2c_bitr_done */
 	0xf80131f4,
-/* 0x05f5: i2c_get_byte */
+/* 0x07ad: i2c_get_byte */
 	0x04000500,
-/* 0x05f9: i2c_get_byte_next */
+/* 0x07b1: i2c_get_byte_next */
 	0x0154b608,
 	0xb60076bb,
 	0x50f90465,
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0x05b07e50,
+	0x07687e50,
 	0x0464b600,
 	0xfd2a11f4,
 	0x42b60553,
@@ -1257,11 +1440,11 @@ uint32_t nv108_pwr_code[] = {
 	0x0256bb04,
 	0x75fd50bd,
 	0x7e50fc04,
-	0xb6000570,
-/* 0x0642: i2c_get_byte_done */
+	0xb6000728,
+/* 0x07fa: i2c_get_byte_done */
 	0x00f80464,
-/* 0x0644: i2c_put_byte */
-/* 0x0646: i2c_put_byte_next */
+/* 0x07fc: i2c_put_byte */
+/* 0x07fe: i2c_put_byte_next */
 	0x42b60804,
 	0x3854ff01,
 	0xb60076bb,
@@ -1269,7 +1452,7 @@ uint32_t nv108_pwr_code[] = {
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0x05707e50,
+	0x07287e50,
 	0x0464b600,
 	0xb03411f4,
 	0x1bf40046,
@@ -1278,21 +1461,21 @@ uint32_t nv108_pwr_code[] = {
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
-	0xb07e50fc,
-	0x64b60005,
+	0x687e50fc,
+	0x64b60007,
 	0x0f11f404,
 	0xb00076bb,
 	0x1bf40136,
 	0x0132f406,
-/* 0x069c: i2c_put_byte_done */
-/* 0x069e: i2c_addr */
+/* 0x0854: i2c_put_byte_done */
+/* 0x0856: i2c_addr */
 	0x76bb00f8,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0x7e50fc04,
-	0xb60004e9,
+	0xb60006a1,
 	0x11f40464,
 	0x2ec3e729,
 	0x0134b601,
@@ -1302,32 +1485,32 @@ uint32_t nv108_pwr_code[] = {
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0006447e,
-/* 0x06e3: i2c_addr_done */
+	0x0007fc7e,
+/* 0x089b: i2c_addr_done */
 	0xf80464b6,
-/* 0x06e5: i2c_acquire_addr */
+/* 0x089d: i2c_acquire_addr */
 	0xf8cec700,
 	0xb705e4b6,
 	0xf8d014e0,
-/* 0x06f1: i2c_acquire */
-	0x06e57e00,
+/* 0x08a9: i2c_acquire */
+	0x089d7e00,
 	0x00047e00,
 	0x03d9f000,
 	0x00002e7e,
-/* 0x0702: i2c_release */
-	0xe57e00f8,
-	0x047e0006,
+/* 0x08ba: i2c_release */
+	0x9d7e00f8,
+	0x047e0008,
 	0xdaf00000,
 	0x002e7e03,
-/* 0x0713: i2c_recv */
+/* 0x08cb: i2c_recv */
 	0xf400f800,
 	0xc1c70132,
 	0x0214b6f8,
 	0xf52816b0,
 	0xb801371f,
-	0x000bd413,
+	0x000be813,
 	0xb8003298,
-	0x000bac13,
+	0x000bc013,
 	0xf4003198,
 	0xd0f90231,
 	0xd0f9e0f9,
@@ -1339,7 +1522,7 @@ uint32_t nv108_pwr_code[] = {
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0006f17e,
+	0x0008a97e,
 	0xfc0464b6,
 	0x00d6b0d0,
 	0x00b01bf5,
@@ -1349,7 +1532,7 @@ uint32_t nv108_pwr_code[] = {
 	0x0256bb04,
 	0x75fd50bd,
 	0x7e50fc04,
-	0xb600069e,
+	0xb6000856,
 	0x11f50464,
 	0xc5c700cc,
 	0x0076bbe0,
@@ -1357,8 +1540,8 @@ uint32_t nv108_pwr_code[] = {
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
-	0x447e50fc,
-	0x64b60006,
+	0xfc7e50fc,
+	0x64b60007,
 	0xa911f504,
 	0xbb010500,
 	0x65b60076,
@@ -1366,7 +1549,7 @@ uint32_t nv108_pwr_code[] = {
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x00069e7e,
+	0x0008567e,
 	0xf50464b6,
 	0xbb008711,
 	0x65b60076,
@@ -1374,7 +1557,7 @@ uint32_t nv108_pwr_code[] = {
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0005f57e,
+	0x0007ad7e,
 	0xf40464b6,
 	0x5bcb6711,
 	0x0076bbe0,
@@ -1382,37 +1565,37 @@ uint32_t nv108_pwr_code[] = {
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
-	0x417e50fc,
-	0x64b60005,
+	0xf97e50fc,
+	0x64b60006,
 	0xbd5bb204,
 	0x410ef474,
-/* 0x0818: i2c_recv_not_rd08 */
+/* 0x09d0: i2c_recv_not_rd08 */
 	0xf401d6b0,
 	0x00053b1b,
-	0x00069e7e,
+	0x0008567e,
 	0xc73211f4,
-	0x447ee0c5,
-	0x11f40006,
+	0xfc7ee0c5,
+	0x11f40007,
 	0x7e000528,
-	0xf400069e,
+	0xf4000856,
 	0xb5c71f11,
-	0x06447ee0,
+	0x07fc7ee0,
 	0x1511f400,
-	0x0005417e,
+	0x0006f97e,
 	0xc5c774bd,
 	0x091bf408,
 	0xf40232f4,
-/* 0x0856: i2c_recv_not_wr08 */
-/* 0x0856: i2c_recv_done */
+/* 0x0a0e: i2c_recv_not_wr08 */
+/* 0x0a0e: i2c_recv_done */
 	0xcec7030e,
-	0x07027ef8,
+	0x08ba7ef8,
 	0xfce0fc00,
 	0x0912f4d0,
-	0x3f7e7cb2,
-/* 0x086a: i2c_recv_exit */
+	0xc27e7cb2,
+/* 0x0a22: i2c_recv_exit */
 	0x00f80002,
-/* 0x086c: i2c_init */
-/* 0x086e: test_recv */
+/* 0x0a24: i2c_init */
+/* 0x0a26: test_recv */
 	0x584100f8,
 	0x0011cf04,
 	0x400110b6,
@@ -1420,28 +1603,28 @@ uint32_t nv108_pwr_code[] = {
 	0xf104bd00,
 	0xf1d900e7,
 	0x7e134fe3,
-	0xf8000196,
-/* 0x088d: test_init */
+	0xf8000201,
+/* 0x0a45: test_init */
 	0x08004e00,
-	0x0001967e,
-/* 0x0896: idle_recv */
+	0x0002017e,
+/* 0x0a4e: idle_recv */
 	0x00f800f8,
-/* 0x0898: idle */
+/* 0x0a50: idle */
 	0x410031f4,
 	0x11cf0454,
 	0x0110b600,
 	0xf6045440,
 	0x04bd0001,
-/* 0x08ac: idle_loop */
+/* 0x0a64: idle_loop */
 	0x32f45801,
-/* 0x08b1: idle_proc */
-/* 0x08b1: idle_proc_exec */
+/* 0x0a69: idle_proc */
+/* 0x0a69: idle_proc_exec */
 	0xb210f902,
-	0x02487e1e,
+	0x02cb7e1e,
 	0xf410fc00,
 	0x31f40911,
 	0xf00ef402,
-/* 0x08c4: idle_proc_next */
+/* 0x0a7c: idle_proc_next */
 	0xa65810b6,
 	0xe81bf41f,
 	0xf4e002f4,
@@ -1457,4 +1640,22 @@ uint32_t nv108_pwr_code[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 };
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc
index 6744fcc06151..daa06c1c655e 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc
@@ -23,6 +23,7 @@
  */
 
 #define NVKM_PPWR_CHIPSET GT215
+#define HW_TICKS_PER_US 203 // should be 202.5
 
 //#define NVKM_FALCON_PC24
 //#define NVKM_FALCON_UNSHIFTED_IO
@@ -34,6 +35,7 @@
 .section #nva3_pwr_data
 #define INCLUDE_PROC
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
@@ -44,6 +46,7 @@
 
 #define INCLUDE_DATA
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
@@ -56,6 +59,7 @@
 .section #nva3_pwr_code
 #define INCLUDE_CODE
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h
index e087ce3041be..64e97baabc3c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h
@@ -24,8 +24,8 @@ uint32_t nva3_pwr_data[] = {
 	0x00000000,
 /* 0x0058: proc_list_head */
 	0x54534f48,
-	0x00000430,
-	0x000003cd,
+	0x00000512,
+	0x000004af,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -46,8 +46,8 @@ uint32_t nva3_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x584d454d,
-	0x00000542,
-	0x00000534,
+	0x000006e0,
+	0x000006d2,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -68,8 +68,8 @@ uint32_t nva3_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x46524550,
-	0x00000546,
-	0x00000544,
+	0x000006e4,
+	0x000006e2,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -90,8 +90,8 @@ uint32_t nva3_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x5f433249,
-	0x00000976,
-	0x00000819,
+	0x00000b14,
+	0x000009b7,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -112,8 +112,8 @@ uint32_t nva3_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x54534554,
-	0x0000099f,
-	0x00000978,
+	0x00000b3d,
+	0x00000b16,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -134,8 +134,8 @@ uint32_t nva3_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x454c4449,
-	0x000009ab,
-	0x000009a9,
+	0x00000b49,
+	0x00000b47,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -227,25 +227,31 @@ uint32_t nva3_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 /* 0x0370: memx_func_head */
-	0x00010000,
-	0x00000000,
-	0x0000046f,
-/* 0x037c: memx_func_next */
 	0x00000001,
 	0x00000000,
-	0x00000496,
+	0x00000551,
+/* 0x037c: memx_func_next */
 	0x00000002,
+	0x00000000,
+	0x000005a8,
+	0x00000003,
 	0x00000002,
-	0x000004b7,
-	0x00040003,
+	0x0000063a,
+	0x00040004,
+	0x00000000,
+	0x00000656,
+	0x00010005,
+	0x00000000,
+	0x00000673,
+	0x00010006,
 	0x00000000,
-	0x000004d3,
-	0x00010004,
+	0x000005f8,
+/* 0x03b8: memx_func_tail */
+/* 0x03b8: memx_ts_start */
 	0x00000000,
-	0x000004f0,
-/* 0x03ac: memx_func_tail */
-/* 0x03ac: memx_data_head */
+/* 0x03bc: memx_ts_end */
 	0x00000000,
+/* 0x03c0: memx_data_head */
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -757,8 +763,9 @@ uint32_t nva3_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
-/* 0x0bac: memx_data_tail */
-/* 0x0bac: i2c_scl_map */
+	0x00000000,
+/* 0x0bc0: memx_data_tail */
+/* 0x0bc0: i2c_scl_map */
 	0x00001000,
 	0x00004000,
 	0x00010000,
@@ -769,7 +776,7 @@ uint32_t nva3_pwr_data[] = {
 	0x01000000,
 	0x04000000,
 	0x10000000,
-/* 0x0bd4: i2c_sda_map */
+/* 0x0be8: i2c_sda_map */
 	0x00002000,
 	0x00008000,
 	0x00020000,
@@ -780,7 +787,7 @@ uint32_t nva3_pwr_data[] = {
 	0x02000000,
 	0x08000000,
 	0x20000000,
-/* 0x0bfc: i2c_ctrl */
+/* 0x0c10: i2c_ctrl */
 	0x0000e138,
 	0x0000e150,
 	0x0000e168,
@@ -841,15 +848,10 @@ uint32_t nva3_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
 };
 
 uint32_t nva3_pwr_code[] = {
-	0x030d0ef5,
+	0x039e0ef5,
 /* 0x0004: rd32 */
 	0x07a007f1,
 	0xd00604b6,
@@ -885,19 +887,22 @@ uint32_t nva3_pwr_code[] = {
 	0xd4f100dd,
 	0x1bf47000,
 /* 0x007f: nsec */
-	0xf000f8f2,
+	0xf900f8f2,
+	0xf080f990,
 	0x84b62c87,
 	0x0088cf06,
-/* 0x0088: nsec_loop */
+/* 0x008c: nsec_loop */
 	0xb62c97f0,
 	0x99cf0694,
 	0x0298bb00,
 	0xf4069eb8,
-	0x00f8f11e,
-/* 0x009c: wait */
+	0x80fcf11e,
+	0x00f890fc,
+/* 0x00a4: wait */
+	0x80f990f9,
 	0xb62c87f0,
 	0x88cf0684,
-/* 0x00a5: wait_loop */
+/* 0x00b1: wait_loop */
 	0x02eeb900,
 	0xb90421f4,
 	0xadfd02da,
@@ -907,28 +912,29 @@ uint32_t nva3_pwr_code[] = {
 	0x0099cf06,
 	0xb80298bb,
 	0x1ef4069b,
-/* 0x00c9: wait_done */
-/* 0x00cb: intr_watchdog */
-	0x9800f8df,
+/* 0x00d5: wait_done */
+	0xfc80fcdf,
+/* 0x00db: intr_watchdog */
+	0x9800f890,
 	0x96b003e9,
 	0x2a0bf400,
 	0xbb9a0a98,
 	0x1cf4029a,
 	0x01d7f00f,
-	0x025421f5,
+	0x02dd21f5,
 	0x0ef494bd,
-/* 0x00e9: intr_watchdog_next_time */
+/* 0x00f9: intr_watchdog_next_time */
 	0x9b0a9815,
 	0xf400a6b0,
 	0x9ab8090b,
 	0x061cf406,
-/* 0x00f8: intr_watchdog_next_time_set */
-/* 0x00fb: intr_watchdog_next_proc */
+/* 0x0108: intr_watchdog_next_time_set */
+/* 0x010b: intr_watchdog_next_proc */
 	0x809b0980,
 	0xe0b603e9,
 	0x68e6b158,
 	0xc61bf402,
-/* 0x010a: intr */
+/* 0x011a: intr */
 	0x00f900f8,
 	0x80f904bd,
 	0xa0f990f9,
@@ -948,13 +954,13 @@ uint32_t nva3_pwr_code[] = {
 	0xf40289c4,
 	0x0080230b,
 	0x58e7f09b,
-	0x98cb21f4,
+	0x98db21f4,
 	0x96b09b09,
 	0x110bf400,
 	0xb63407f0,
 	0x09d00604,
 	0x8004bd00,
-/* 0x016e: intr_skip_watchdog */
+/* 0x017e: intr_skip_watchdog */
 	0x89e49a09,
 	0x0bf40800,
 	0x8897f148,
@@ -967,22 +973,22 @@ uint32_t nva3_pwr_code[] = {
 	0x48e7f1c0,
 	0x53e3f14f,
 	0x00d7f054,
-	0x02b921f5,
+	0x034221f5,
 	0x07f1c0fc,
 	0x04b604c0,
 	0x000cd006,
-/* 0x01ae: intr_subintr_skip_fifo */
+/* 0x01be: intr_subintr_skip_fifo */
 	0x07f104bd,
 	0x04b60688,
 	0x0009d006,
-/* 0x01ba: intr_skip_subintr */
+/* 0x01ca: intr_skip_subintr */
 	0x89c404bd,
 	0x070bf420,
 	0xffbfa4f1,
-/* 0x01c4: intr_skip_pause */
+/* 0x01d4: intr_skip_pause */
 	0xf44089c4,
 	0xa4f1070b,
-/* 0x01ce: intr_skip_user0 */
+/* 0x01de: intr_skip_user0 */
 	0x07f0ffbf,
 	0x0604b604,
 	0xbd0008d0,
@@ -993,596 +999,732 @@ uint32_t nva3_pwr_code[] = {
 	0x90fca0fc,
 	0x00fc80fc,
 	0xf80032f4,
-/* 0x01f5: timer */
-	0x1032f401,
-	0xb003f898,
-	0x1cf40086,
-	0x03fe8051,
+/* 0x0205: ticks_from_ns */
+	0xf9c0f901,
+	0xcbd7f1b0,
+	0x00d3f000,
+	0x041321f5,
+	0x03e8ccec,
+	0xf400b4b0,
+	0xeeec120b,
+	0xd7f103e8,
+	0xd3f000cb,
+	0x1321f500,
+/* 0x022d: ticks_from_ns_quit */
+	0x02ceb904,
+	0xc0fcb0fc,
+/* 0x0236: ticks_from_us */
+	0xc0f900f8,
+	0xd7f1b0f9,
+	0xd3f000cb,
+	0x1321f500,
+	0x02ceb904,
+	0xf400b4b0,
+	0xe4bd050b,
+/* 0x0250: ticks_from_us_quit */
+	0xc0fcb0fc,
+/* 0x0256: ticks_to_us */
+	0xd7f100f8,
+	0xd3f000cb,
+	0xecedff00,
+/* 0x0262: timer */
+	0x90f900f8,
+	0x32f480f9,
+	0x03f89810,
+	0xf40086b0,
+	0x84bd651c,
 	0xb63807f0,
 	0x08d00604,
 	0xf004bd00,
-	0x84b60887,
+	0x84b63487,
 	0x0088cf06,
-	0xf40284f0,
-	0x87f0261b,
-	0x0684b634,
-	0xb80088cf,
-	0x0bf406e0,
-	0x06e8b809,
-/* 0x0233: timer_reset */
-	0xf01f1ef4,
-	0x04b63407,
-	0x000ed006,
-	0x0e8004bd,
-/* 0x0241: timer_enable */
-	0x0187f09a,
+	0xbb9a0998,
+	0xe9bb0298,
+	0x03fe8000,
+	0xb60887f0,
+	0x88cf0684,
+	0x0284f000,
+	0xf0261bf4,
+	0x84b63487,
+	0x0088cf06,
+	0xf406e0b8,
+	0xe8b8090b,
+	0x111cf406,
+/* 0x02b8: timer_reset */
+	0xb63407f0,
+	0x0ed00604,
+	0x8004bd00,
+/* 0x02c6: timer_enable */
+	0x87f09a0e,
+	0x3807f001,
+	0xd00604b6,
+	0x04bd0008,
+/* 0x02d4: timer_done */
+	0xfc1031f4,
+	0xf890fc80,
+/* 0x02dd: send_proc */
+	0xf980f900,
+	0x05e89890,
+	0xf004e998,
+	0x89b80486,
+	0x2a0bf406,
+	0x940398c4,
+	0x80b60488,
+	0x008ebb18,
+	0x8000fa98,
+	0x8d80008a,
+	0x028c8001,
+	0xb6038b80,
+	0x94f00190,
+	0x04e98007,
+/* 0x0317: send_done */
+	0xfc0231f4,
+	0xf880fc90,
+/* 0x031d: find */
+	0xf080f900,
+	0x31f45887,
+/* 0x0325: find_loop */
+	0x008a9801,
+	0xf406aeb8,
+	0x80b6100b,
+	0x6886b158,
+	0xf01bf402,
+/* 0x033b: find_done */
+	0xb90132f4,
+	0x80fc028e,
+/* 0x0342: send */
+	0x21f500f8,
+	0x01f4031d,
+/* 0x034b: recv */
+	0xf900f897,
+	0x9880f990,
+	0xe99805e8,
+	0x0132f404,
+	0xf40689b8,
+	0x89c43d0b,
+	0x0180b603,
+	0x800784f0,
+	0xea9805e8,
+	0xfef0f902,
+	0xf0f9018f,
+	0x9402efb9,
+	0xe9bb0499,
+	0x18e0b600,
+	0x9803eb98,
+	0xed9802ec,
+	0x00ee9801,
+	0xf0fca5f9,
+	0xf400f8fe,
+	0xf0fc0131,
+/* 0x0398: recv_done */
+	0x90fc80fc,
+/* 0x039e: init */
+	0x17f100f8,
+	0x14b60108,
+	0x0011cf06,
+	0x010911e7,
+	0xfe0814b6,
+	0x17f10014,
+	0x13f000e0,
+	0x1c07f000,
+	0xd00604b6,
+	0x04bd0001,
+	0xf0ff17f0,
+	0x04b61407,
+	0x0001d006,
+	0x17f004bd,
+	0x0015f102,
+	0x1007f008,
+	0xd00604b6,
+	0x04bd0001,
+	0x011a17f1,
+	0xfe0013f0,
+	0x31f40010,
+	0x0117f010,
 	0xb63807f0,
-	0x08d00604,
-/* 0x024f: timer_done */
-	0xf404bd00,
-	0x00f81031,
-/* 0x0254: send_proc */
-	0x90f980f9,
-	0x9805e898,
-	0x86f004e9,
-	0x0689b804,
-	0xc42a0bf4,
-	0x88940398,
-	0x1880b604,
-	0x98008ebb,
-	0x8a8000fa,
-	0x018d8000,
-	0x80028c80,
-	0x90b6038b,
-	0x0794f001,
-	0xf404e980,
-/* 0x028e: send_done */
-	0x90fc0231,
-	0x00f880fc,
-/* 0x0294: find */
-	0x87f080f9,
-	0x0131f458,
-/* 0x029c: find_loop */
-	0xb8008a98,
-	0x0bf406ae,
-	0x5880b610,
-	0x026886b1,
-	0xf4f01bf4,
-/* 0x02b2: find_done */
-	0x8eb90132,
-	0xf880fc02,
-/* 0x02b9: send */
-	0x9421f500,
-	0x9701f402,
-/* 0x02c2: recv */
-	0xe89800f8,
-	0x04e99805,
-	0xb80132f4,
-	0x0bf40689,
-	0x0389c43d,
-	0xf00180b6,
-	0xe8800784,
-	0x02ea9805,
-	0x8ffef0f9,
-	0xb9f0f901,
-	0x999402ef,
-	0x00e9bb04,
-	0x9818e0b6,
-	0xec9803eb,
-	0x01ed9802,
-	0xf900ee98,
-	0xfef0fca5,
-	0x31f400f8,
-/* 0x030b: recv_done */
-	0xf8f0fc01,
-/* 0x030d: init */
-	0x0817f100,
-	0x0614b601,
-	0xe70011cf,
-	0xb6010911,
-	0x14fe0814,
-	0xe017f100,
-	0x0013f000,
-	0xb61c07f0,
 	0x01d00604,
 	0xf004bd00,
-	0x07f0ff17,
-	0x0604b614,
-	0xbd0001d0,
-	0x0217f004,
-	0x080015f1,
-	0xb61007f0,
-	0x01d00604,
-	0xf104bd00,
-	0xf0010a17,
-	0x10fe0013,
-	0x1031f400,
-	0xf00117f0,
-	0x04b63807,
-	0x0001d006,
-	0xf7f004bd,
-/* 0x0371: init_proc */
-	0x01f19858,
-	0xf40016b0,
-	0x15f9fa0b,
-	0xf458f0b6,
-/* 0x0382: host_send */
-	0x17f1f20e,
-	0x14b604b0,
-	0x0011cf06,
-	0x04a027f1,
-	0xcf0624b6,
-	0x12b80022,
-	0x320bf406,
-	0x94071ec4,
-	0xe0b704ee,
-	0xeb980270,
-	0x02ec9803,
-	0x9801ed98,
-	0x21f500ee,
-	0x10b602b9,
-	0x0f1ec401,
-	0x04b007f1,
-	0xd00604b6,
-	0x04bd000e,
-/* 0x03cb: host_send_done */
-	0xf8ba0ef4,
-/* 0x03cd: host_recv */
-	0x4917f100,
-	0x5413f14e,
-	0x06e1b852,
-/* 0x03db: host_recv_wait */
-	0xf1aa0bf4,
-	0xb604cc17,
-	0x11cf0614,
-	0xc827f100,
-	0x0624b604,
-	0xf00022cf,
-	0x12b80816,
-	0xe60bf406,
-	0xb60723c4,
-	0x30b70434,
-	0x3b8002f0,
-	0x023c8003,
-	0x80013d80,
-	0x20b6003e,
-	0x0f24f001,
-	0x04c807f1,
+/* 0x0402: init_proc */
+	0xf19858f7,
+	0x0016b001,
+	0xf9fa0bf4,
+	0x58f0b615,
+/* 0x0413: mulu32_32_64 */
+	0xf9f20ef4,
+	0xf920f910,
+	0x9540f930,
+	0xd29510e1,
+	0xbdc4bd10,
+	0xc0edffb4,
+	0xb9301dff,
+	0x34f10234,
+	0x34b6ffff,
+	0x1045b610,
+	0xbb00c3bb,
+	0xe2ff01b4,
+	0x0234b930,
+	0xffff34f1,
+	0xb61034b6,
+	0xc3bb1045,
+	0x01b4bb00,
+	0xbb3012ff,
+	0x40fc00b3,
+	0x20fc30fc,
+	0x00f810fc,
+/* 0x0464: host_send */
+	0x04b017f1,
+	0xcf0614b6,
+	0x27f10011,
+	0x24b604a0,
+	0x0022cf06,
+	0xf40612b8,
+	0x1ec4320b,
+	0x04ee9407,
+	0x0270e0b7,
+	0x9803eb98,
+	0xed9802ec,
+	0x00ee9801,
+	0x034221f5,
+	0xc40110b6,
+	0x07f10f1e,
+	0x04b604b0,
+	0x000ed006,
+	0x0ef404bd,
+/* 0x04ad: host_send_done */
+/* 0x04af: host_recv */
+	0xf100f8ba,
+	0xf14e4917,
+	0xb8525413,
+	0x0bf406e1,
+/* 0x04bd: host_recv_wait */
+	0xcc17f1aa,
+	0x0614b604,
+	0xf10011cf,
+	0xb604c827,
+	0x22cf0624,
+	0x0816f000,
+	0xf40612b8,
+	0x23c4e60b,
+	0x0434b607,
+	0x02f030b7,
+	0x80033b80,
+	0x3d80023c,
+	0x003e8001,
+	0xf00120b6,
+	0x07f10f24,
+	0x04b604c8,
+	0x0002d006,
+	0x27f004bd,
+	0x0007f040,
 	0xd00604b6,
 	0x04bd0002,
-	0xf04027f0,
-	0x04b60007,
-	0x0002d006,
-	0x00f804bd,
-/* 0x0430: host_init */
-	0x008017f1,
-	0xf11014b6,
-	0xf1027015,
-	0xb604d007,
-	0x01d00604,
-	0xf104bd00,
-	0xb6008017,
-	0x15f11014,
-	0x07f102f0,
-	0x04b604dc,
-	0x0001d006,
-	0x17f004bd,
-	0xc407f101,
+/* 0x0512: host_init */
+	0x17f100f8,
+	0x14b60080,
+	0x7015f110,
+	0xd007f102,
 	0x0604b604,
 	0xbd0001d0,
-/* 0x046f: memx_func_enter */
-	0xf000f804,
+	0x8017f104,
+	0x1014b600,
+	0x02f015f1,
+	0x04dc07f1,
+	0xd00604b6,
+	0x04bd0001,
+	0xf10117f0,
+	0xb604c407,
+	0x01d00604,
+	0xf804bd00,
+/* 0x0551: memx_func_enter */
+	0x1087f100,
+	0x028eb916,
+	0xb90421f4,
+	0x67f102d7,
+	0x63f1fffc,
+	0x76fdffff,
+	0x0267f104,
+	0x0576fd00,
+	0x70f980f9,
+	0xe0fcd0fc,
+	0xf03f21f4,
 	0x07f10467,
 	0x04b607e0,
 	0x0006d006,
-/* 0x047e: memx_func_enter_wait */
+/* 0x058a: memx_func_enter_wait */
 	0x67f104bd,
 	0x64b607c0,
 	0x0066cf06,
 	0xf40464f0,
-	0x1698f30b,
-	0x0410b600,
-/* 0x0496: memx_func_leave */
-	0x67f000f8,
-	0xe407f104,
-	0x0604b607,
-	0xbd0006d0,
-/* 0x04a5: memx_func_leave_wait */
-	0xc067f104,
+	0x67f0f30b,
+	0x0664b62c,
+	0x800066cf,
+	0x00f8ee06,
+/* 0x05a8: memx_func_leave */
+	0xb62c67f0,
+	0x66cf0664,
+	0xef068000,
+	0xf10467f0,
+	0xb607e407,
+	0x06d00604,
+/* 0x05c3: memx_func_leave_wait */
+	0xf104bd00,
+	0xb607c067,
+	0x66cf0664,
+	0x0464f000,
+	0xf1f31bf4,
+	0xb9161087,
+	0x21f4028e,
+	0x02d7b904,
+	0xffcc67f1,
+	0xffff63f1,
+	0xf90476fd,
+	0xfc70f980,
+	0xf4e0fcd0,
+	0x00f83f21,
+/* 0x05f8: memx_func_wait_vblank */
+	0xb0001698,
+	0x0bf40066,
+	0x0166b013,
+	0xf4060bf4,
+/* 0x060a: memx_func_wait_vblank_head1 */
+	0x77f12e0e,
+	0x0ef40020,
+/* 0x0611: memx_func_wait_vblank_head0 */
+	0x0877f107,
+/* 0x0615: memx_func_wait_vblank_0 */
+	0xc467f100,
 	0x0664b607,
-	0xf00066cf,
-	0x1bf40464,
-/* 0x04b7: memx_func_wr32 */
-	0x9800f8f3,
-	0x15980016,
-	0x0810b601,
-	0x50f960f9,
-	0xe0fcd0fc,
-	0xb63f21f4,
-	0x1bf40242,
-/* 0x04d3: memx_func_wait */
-	0xf000f8e9,
-	0x84b62c87,
-	0x0088cf06,
-	0x98001e98,
-	0x1c98011d,
-	0x031b9802,
-	0xf41010b6,
-	0x00f89c21,
-/* 0x04f0: memx_func_delay */
-	0xb6001e98,
-	0x21f40410,
-/* 0x04fb: memx_exec */
-	0xf900f87f,
-	0xb9d0f9e0,
-	0xb2b902c1,
-/* 0x0505: memx_exec_next */
-	0x00139802,
-	0x950410b6,
-	0x30f01034,
-	0xde35980c,
-	0x12b855f9,
-	0xec1ef406,
-	0xe0fcd0fc,
-	0x02b921f5,
-/* 0x0526: memx_info */
-	0xc7f100f8,
-	0xb7f103ac,
-	0x21f50800,
-	0x00f802b9,
-/* 0x0534: memx_recv */
-	0xf401d6b0,
-	0xd6b0c40b,
-	0xe90bf400,
-/* 0x0542: memx_init */
-	0x00f800f8,
-/* 0x0544: perf_recv */
-/* 0x0546: perf_init */
+	0xfd0066cf,
+	0x1bf40467,
+/* 0x0625: memx_func_wait_vblank_1 */
+	0xc467f1f3,
+	0x0664b607,
+	0xfd0066cf,
+	0x0bf40467,
+/* 0x0635: memx_func_wait_vblank_fini */
+	0x0410b6f3,
+/* 0x063a: memx_func_wr32 */
+	0x169800f8,
+	0x01159800,
+	0xf90810b6,
+	0xfc50f960,
+	0xf4e0fcd0,
+	0x42b63f21,
+	0xe91bf402,
+/* 0x0656: memx_func_wait */
+	0x87f000f8,
+	0x0684b62c,
+	0x980088cf,
+	0x1d98001e,
+	0x021c9801,
+	0xb6031b98,
+	0x21f41010,
+/* 0x0673: memx_func_delay */
+	0x9800f8a4,
+	0x10b6001e,
+	0x7f21f404,
+/* 0x067e: memx_exec */
+	0xe0f900f8,
+	0xc1b9d0f9,
+	0x02b2b902,
+/* 0x0688: memx_exec_next */
+	0xb6001398,
+	0x34e70410,
+	0x33e701f0,
+	0x32b601e0,
+	0x0c30f001,
+	0xf9de3598,
+	0x0612b855,
+	0x98e41ef4,
+	0x0c98ee0b,
+	0x02cbbbef,
+	0x07c4b7f1,
+	0xcf06b4b6,
+	0xd0fc00bb,
+	0x21f5e0fc,
+	0x00f80342,
+/* 0x06c4: memx_info */
+	0x03c0c7f1,
+	0x0800b7f1,
+	0x034221f5,
+/* 0x06d2: memx_recv */
+	0xd6b000f8,
+	0xa90bf401,
+	0xf400d6b0,
+	0x00f8e90b,
+/* 0x06e0: memx_init */
+/* 0x06e2: perf_recv */
 	0x00f800f8,
-/* 0x0548: i2c_drive_scl */
-	0xf40036b0,
-	0x07f1110b,
-	0x04b607e0,
-	0x0001d006,
-	0x00f804bd,
-/* 0x055c: i2c_drive_scl_lo */
-	0x07e407f1,
-	0xd00604b6,
-	0x04bd0001,
-/* 0x056a: i2c_drive_sda */
+/* 0x06e4: perf_init */
+/* 0x06e6: i2c_drive_scl */
 	0x36b000f8,
 	0x110bf400,
 	0x07e007f1,
 	0xd00604b6,
-	0x04bd0002,
-/* 0x057e: i2c_drive_sda_lo */
+	0x04bd0001,
+/* 0x06fa: i2c_drive_scl_lo */
 	0x07f100f8,
 	0x04b607e4,
+	0x0001d006,
+	0x00f804bd,
+/* 0x0708: i2c_drive_sda */
+	0xf40036b0,
+	0x07f1110b,
+	0x04b607e0,
 	0x0002d006,
 	0x00f804bd,
-/* 0x058c: i2c_sense_scl */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0431fd00,
-	0xf4060bf4,
-/* 0x05a2: i2c_sense_scl_done */
-	0x00f80131,
-/* 0x05a4: i2c_sense_sda */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0432fd00,
-	0xf4060bf4,
-/* 0x05ba: i2c_sense_sda_done */
-	0x00f80131,
-/* 0x05bc: i2c_raise_scl */
-	0x47f140f9,
-	0x37f00898,
-	0x4821f501,
-/* 0x05c9: i2c_raise_scl_wait */
-	0xe8e7f105,
-	0x7f21f403,
-	0x058c21f5,
-	0xb60901f4,
-	0x1bf40142,
-/* 0x05dd: i2c_raise_scl_done */
-	0xf840fcef,
-/* 0x05e1: i2c_start */
-	0x8c21f500,
-	0x0d11f405,
-	0x05a421f5,
-	0xf40611f4,
-/* 0x05f2: i2c_start_rep */
-	0x37f0300e,
-	0x4821f500,
-	0x0137f005,
-	0x056a21f5,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0xbc21f550,
-	0x0464b605,
-/* 0x061f: i2c_start_send */
-	0xf01f11f4,
+/* 0x071c: i2c_drive_sda_lo */
+	0x07e407f1,
+	0xd00604b6,
+	0x04bd0002,
+/* 0x072a: i2c_sense_scl */
+	0x32f400f8,
+	0xc437f101,
+	0x0634b607,
+	0xfd0033cf,
+	0x0bf40431,
+	0x0131f406,
+/* 0x0740: i2c_sense_scl_done */
+/* 0x0742: i2c_sense_sda */
+	0x32f400f8,
+	0xc437f101,
+	0x0634b607,
+	0xfd0033cf,
+	0x0bf40432,
+	0x0131f406,
+/* 0x0758: i2c_sense_sda_done */
+/* 0x075a: i2c_raise_scl */
+	0x40f900f8,
+	0x089847f1,
+	0xf50137f0,
+/* 0x0767: i2c_raise_scl_wait */
+	0xf106e621,
+	0xf403e8e7,
+	0x21f57f21,
+	0x01f4072a,
+	0x0142b609,
+/* 0x077b: i2c_raise_scl_done */
+	0xfcef1bf4,
+/* 0x077f: i2c_start */
+	0xf500f840,
+	0xf4072a21,
+	0x21f50d11,
+	0x11f40742,
+	0x300ef406,
+/* 0x0790: i2c_start_rep */
+	0xf50037f0,
+	0xf006e621,
+	0x21f50137,
+	0x76bb0708,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb6075a21,
+	0x11f40464,
+/* 0x07bd: i2c_start_send */
+	0x0037f01f,
+	0x070821f5,
+	0x1388e7f1,
+	0xf07f21f4,
 	0x21f50037,
-	0xe7f1056a,
+	0xe7f106e6,
 	0x21f41388,
-	0x0037f07f,
-	0x054821f5,
-	0x1388e7f1,
-/* 0x063b: i2c_start_out */
-	0xf87f21f4,
-/* 0x063d: i2c_stop */
-	0x0037f000,
-	0x054821f5,
-	0xf50037f0,
-	0xf1056a21,
-	0xf403e8e7,
-	0x37f07f21,
-	0x4821f501,
-	0x88e7f105,
-	0x7f21f413,
+/* 0x07d9: i2c_start_out */
+/* 0x07db: i2c_stop */
+	0xf000f87f,
+	0x21f50037,
+	0x37f006e6,
+	0x0821f500,
+	0xe8e7f107,
+	0x7f21f403,
 	0xf50137f0,
-	0xf1056a21,
+	0xf106e621,
 	0xf41388e7,
-	0x00f87f21,
-/* 0x0670: i2c_bitw */
-	0x056a21f5,
-	0x03e8e7f1,
-	0xbb7f21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x05bc21f5,
-	0xf40464b6,
-	0xe7f11811,
-	0x21f41388,
-	0x0037f07f,
-	0x054821f5,
-	0x1388e7f1,
-/* 0x06af: i2c_bitw_out */
-	0xf87f21f4,
-/* 0x06b1: i2c_bitr */
-	0x0137f000,
-	0x056a21f5,
-	0x03e8e7f1,
-	0xbb7f21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x05bc21f5,
-	0xf40464b6,
-	0x21f51b11,
-	0x37f005a4,
-	0x4821f500,
-	0x88e7f105,
+	0x37f07f21,
+	0x0821f501,
+	0x88e7f107,
 	0x7f21f413,
-	0xf4013cf0,
-/* 0x06f6: i2c_bitr_done */
-	0x00f80131,
-/* 0x06f8: i2c_get_byte */
-	0xf00057f0,
-/* 0x06fe: i2c_get_byte_next */
-	0x54b60847,
-	0x0076bb01,
+/* 0x080e: i2c_bitw */
+	0x21f500f8,
+	0xe7f10708,
+	0x21f403e8,
+	0x0076bb7f,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b606b1,
-	0x2b11f404,
-	0xb60553fd,
-	0x1bf40142,
-	0x0137f0d8,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0x7021f550,
-	0x0464b606,
-/* 0x0748: i2c_get_byte_done */
-/* 0x074a: i2c_put_byte */
-	0x47f000f8,
-/* 0x074d: i2c_put_byte_next */
-	0x0142b608,
-	0xbb3854ff,
+	0x64b6075a,
+	0x1811f404,
+	0x1388e7f1,
+	0xf07f21f4,
+	0x21f50037,
+	0xe7f106e6,
+	0x21f41388,
+/* 0x084d: i2c_bitw_out */
+/* 0x084f: i2c_bitr */
+	0xf000f87f,
+	0x21f50137,
+	0xe7f10708,
+	0x21f403e8,
+	0x0076bb7f,
+	0xf90465b6,
+	0x04659450,
+	0xbd0256bb,
+	0x0475fd50,
+	0x21f550fc,
+	0x64b6075a,
+	0x1b11f404,
+	0x074221f5,
+	0xf50037f0,
+	0xf106e621,
+	0xf41388e7,
+	0x3cf07f21,
+	0x0131f401,
+/* 0x0894: i2c_bitr_done */
+/* 0x0896: i2c_get_byte */
+	0x57f000f8,
+	0x0847f000,
+/* 0x089c: i2c_get_byte_next */
+	0xbb0154b6,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x067021f5,
+	0x084f21f5,
 	0xf40464b6,
-	0x46b03411,
-	0xd81bf400,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0xb121f550,
-	0x0464b606,
-	0xbb0f11f4,
-	0x36b00076,
-	0x061bf401,
-/* 0x07a3: i2c_put_byte_done */
-	0xf80132f4,
-/* 0x07a5: i2c_addr */
-	0x0076bb00,
+	0x53fd2b11,
+	0x0142b605,
+	0xf0d81bf4,
+	0x76bb0137,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb6080e21,
+/* 0x08e6: i2c_get_byte_done */
+	0x00f80464,
+/* 0x08e8: i2c_put_byte */
+/* 0x08eb: i2c_put_byte_next */
+	0xb60847f0,
+	0x54ff0142,
+	0x0076bb38,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b605e1,
-	0x2911f404,
-	0x012ec3e7,
-	0xfd0134b6,
-	0x76bb0553,
+	0x64b6080e,
+	0x3411f404,
+	0xf40046b0,
+	0x76bbd81b,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb6074a21,
-/* 0x07ea: i2c_addr_done */
-	0x00f80464,
-/* 0x07ec: i2c_acquire_addr */
-	0xb6f8cec7,
-	0xe0b702e4,
-	0xee980bfc,
-/* 0x07fb: i2c_acquire */
-	0xf500f800,
-	0xf407ec21,
-	0xd9f00421,
-	0x3f21f403,
-/* 0x080a: i2c_release */
-	0x21f500f8,
-	0x21f407ec,
-	0x03daf004,
-	0xf83f21f4,
-/* 0x0819: i2c_recv */
-	0x0132f400,
-	0xb6f8c1c7,
-	0x16b00214,
-	0x3a1ff528,
-	0xd413a001,
-	0x0032980b,
-	0x0bac13a0,
-	0xf4003198,
-	0xd0f90231,
-	0xd0f9e0f9,
-	0x000067f1,
-	0x100063f1,
-	0xbb016792,
+	0xb6084f21,
+	0x11f40464,
+	0x0076bb0f,
+	0xf40136b0,
+	0x32f4061b,
+/* 0x0941: i2c_put_byte_done */
+/* 0x0943: i2c_addr */
+	0xbb00f801,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x07fb21f5,
-	0xfc0464b6,
-	0x00d6b0d0,
-	0x00b31bf5,
-	0xbb0057f0,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x07a521f5,
-	0xf50464b6,
-	0xc700d011,
-	0x76bbe0c5,
-	0x0465b600,
-	0x659450f9,
-	0x0256bb04,
-	0x75fd50bd,
-	0xf550fc04,
-	0xb6074a21,
-	0x11f50464,
-	0x57f000ad,
+	0x077f21f5,
+	0xf40464b6,
+	0xc3e72911,
+	0x34b6012e,
+	0x0553fd01,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0xe821f550,
+	0x0464b608,
+/* 0x0988: i2c_addr_done */
+/* 0x098a: i2c_acquire_addr */
+	0xcec700f8,
+	0x02e4b6f8,
+	0x0c10e0b7,
+	0xf800ee98,
+/* 0x0999: i2c_acquire */
+	0x8a21f500,
+	0x0421f409,
+	0xf403d9f0,
+	0x00f83f21,
+/* 0x09a8: i2c_release */
+	0x098a21f5,
+	0xf00421f4,
+	0x21f403da,
+/* 0x09b7: i2c_recv */
+	0xf400f83f,
+	0xc1c70132,
+	0x0214b6f8,
+	0xf52816b0,
+	0xa0013a1f,
+	0x980be813,
+	0x13a00032,
+	0x31980bc0,
+	0x0231f400,
+	0xe0f9d0f9,
+	0x67f1d0f9,
+	0x63f10000,
+	0x67921000,
 	0x0076bb01,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b607a5,
-	0x8a11f504,
+	0x64b60999,
+	0xb0d0fc04,
+	0x1bf500d6,
+	0x57f000b3,
 	0x0076bb00,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b606f8,
-	0x6a11f404,
-	0xbbe05bcb,
+	0x64b60943,
+	0xd011f504,
+	0xe0c5c700,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0xe821f550,
+	0x0464b608,
+	0x00ad11f5,
+	0xbb0157f0,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x063d21f5,
-	0xb90464b6,
-	0x74bd025b,
-/* 0x091f: i2c_recv_not_rd08 */
-	0xb0430ef4,
-	0x1bf401d6,
-	0x0057f03d,
-	0x07a521f5,
-	0xc73311f4,
-	0x21f5e0c5,
-	0x11f4074a,
-	0x0057f029,
-	0x07a521f5,
-	0xc71f11f4,
-	0x21f5e0b5,
-	0x11f4074a,
-	0x3d21f515,
-	0xc774bd06,
-	0x1bf408c5,
-	0x0232f409,
-/* 0x095f: i2c_recv_not_wr08 */
-/* 0x095f: i2c_recv_done */
-	0xc7030ef4,
-	0x21f5f8ce,
-	0xe0fc080a,
-	0x12f4d0fc,
-	0x027cb90a,
-	0x02b921f5,
-/* 0x0974: i2c_recv_exit */
-/* 0x0976: i2c_init */
-	0x00f800f8,
-/* 0x0978: test_recv */
-	0x05d817f1,
+	0x094321f5,
+	0xf50464b6,
+	0xbb008a11,
+	0x65b60076,
+	0x9450f904,
+	0x56bb0465,
+	0xfd50bd02,
+	0x50fc0475,
+	0x089621f5,
+	0xf40464b6,
+	0x5bcb6a11,
+	0x0076bbe0,
+	0xf90465b6,
+	0x04659450,
+	0xbd0256bb,
+	0x0475fd50,
+	0x21f550fc,
+	0x64b607db,
+	0x025bb904,
+	0x0ef474bd,
+/* 0x0abd: i2c_recv_not_rd08 */
+	0x01d6b043,
+	0xf03d1bf4,
+	0x21f50057,
+	0x11f40943,
+	0xe0c5c733,
+	0x08e821f5,
+	0xf02911f4,
+	0x21f50057,
+	0x11f40943,
+	0xe0b5c71f,
+	0x08e821f5,
+	0xf51511f4,
+	0xbd07db21,
+	0x08c5c774,
+	0xf4091bf4,
+	0x0ef40232,
+/* 0x0afd: i2c_recv_not_wr08 */
+/* 0x0afd: i2c_recv_done */
+	0xf8cec703,
+	0x09a821f5,
+	0xd0fce0fc,
+	0xb90a12f4,
+	0x21f5027c,
+/* 0x0b12: i2c_recv_exit */
+	0x00f80342,
+/* 0x0b14: i2c_init */
+/* 0x0b16: test_recv */
+	0x17f100f8,
+	0x14b605d8,
+	0x0011cf06,
+	0xf10110b6,
+	0xb605d807,
+	0x01d00604,
+	0xf104bd00,
+	0xf1d900e7,
+	0xf5134fe3,
+	0xf8026221,
+/* 0x0b3d: test_init */
+	0x00e7f100,
+	0x6221f508,
+/* 0x0b47: idle_recv */
+	0xf800f802,
+/* 0x0b49: idle */
+	0x0031f400,
+	0x05d417f1,
 	0xcf0614b6,
 	0x10b60011,
-	0xd807f101,
+	0xd407f101,
 	0x0604b605,
 	0xbd0001d0,
-	0x00e7f104,
-	0x4fe3f1d9,
-	0xf521f513,
-/* 0x099f: test_init */
-	0xf100f801,
-	0xf50800e7,
-	0xf801f521,
-/* 0x09a9: idle_recv */
-/* 0x09ab: idle */
-	0xf400f800,
-	0x17f10031,
-	0x14b605d4,
-	0x0011cf06,
-	0xf10110b6,
-	0xb605d407,
-	0x01d00604,
-/* 0x09c7: idle_loop */
-	0xf004bd00,
-	0x32f45817,
-/* 0x09cd: idle_proc */
-/* 0x09cd: idle_proc_exec */
-	0xb910f902,
-	0x21f5021e,
-	0x10fc02c2,
-	0xf40911f4,
-	0x0ef40231,
-/* 0x09e1: idle_proc_next */
-	0x5810b6ef,
-	0xf4061fb8,
-	0x02f4e61b,
-	0x0028f4dd,
-	0x00bb0ef4,
+/* 0x0b65: idle_loop */
+	0x5817f004,
+/* 0x0b6b: idle_proc */
+/* 0x0b6b: idle_proc_exec */
+	0xf90232f4,
+	0x021eb910,
+	0x034b21f5,
+	0x11f410fc,
+	0x0231f409,
+/* 0x0b7f: idle_proc_next */
+	0xb6ef0ef4,
+	0x1fb85810,
+	0xe61bf406,
+	0xf4dd02f4,
+	0x0ef40028,
+	0x000000bb,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc
index 48f79434a449..21bf8cc7618f 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc
@@ -23,6 +23,7 @@
  */
 
 #define NVKM_PPWR_CHIPSET GF100
+#define HW_TICKS_PER_US 203 // should be 202.5
 
 //#define NVKM_FALCON_PC24
 //#define NVKM_FALCON_UNSHIFTED_IO
@@ -34,6 +35,7 @@
 .section #nvc0_pwr_data
 #define INCLUDE_PROC
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
@@ -44,6 +46,7 @@
 
 #define INCLUDE_DATA
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
@@ -56,6 +59,7 @@
 .section #nvc0_pwr_code
 #define INCLUDE_CODE
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h
index 0773ff0e3dc3..ca30fa4011b5 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h
@@ -24,8 +24,8 @@ uint32_t nvc0_pwr_data[] = {
 	0x00000000,
 /* 0x0058: proc_list_head */
 	0x54534f48,
-	0x00000430,
-	0x000003cd,
+	0x00000512,
+	0x000004af,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -46,8 +46,8 @@ uint32_t nvc0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x584d454d,
-	0x00000542,
-	0x00000534,
+	0x0000074b,
+	0x0000073d,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -68,8 +68,8 @@ uint32_t nvc0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x46524550,
-	0x00000546,
-	0x00000544,
+	0x0000074f,
+	0x0000074d,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -90,8 +90,8 @@ uint32_t nvc0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x5f433249,
-	0x00000976,
-	0x00000819,
+	0x00000b7f,
+	0x00000a22,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -112,8 +112,8 @@ uint32_t nvc0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x54534554,
-	0x0000099f,
-	0x00000978,
+	0x00000ba8,
+	0x00000b81,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -134,8 +134,8 @@ uint32_t nvc0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x454c4449,
-	0x000009ab,
-	0x000009a9,
+	0x00000bb4,
+	0x00000bb2,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -227,25 +227,31 @@ uint32_t nvc0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 /* 0x0370: memx_func_head */
-	0x00010000,
-	0x00000000,
-	0x0000046f,
-/* 0x037c: memx_func_next */
 	0x00000001,
 	0x00000000,
-	0x00000496,
+	0x00000551,
+/* 0x037c: memx_func_next */
 	0x00000002,
+	0x00000000,
+	0x000005db,
+	0x00000003,
 	0x00000002,
-	0x000004b7,
-	0x00040003,
+	0x000006a5,
+	0x00040004,
+	0x00000000,
+	0x000006c1,
+	0x00010005,
+	0x00000000,
+	0x000006de,
+	0x00010006,
 	0x00000000,
-	0x000004d3,
-	0x00010004,
+	0x00000663,
+/* 0x03b8: memx_func_tail */
+/* 0x03b8: memx_ts_start */
 	0x00000000,
-	0x000004f0,
-/* 0x03ac: memx_func_tail */
-/* 0x03ac: memx_data_head */
+/* 0x03bc: memx_ts_end */
 	0x00000000,
+/* 0x03c0: memx_data_head */
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -757,8 +763,9 @@ uint32_t nvc0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
-/* 0x0bac: memx_data_tail */
-/* 0x0bac: i2c_scl_map */
+	0x00000000,
+/* 0x0bc0: memx_data_tail */
+/* 0x0bc0: i2c_scl_map */
 	0x00001000,
 	0x00004000,
 	0x00010000,
@@ -769,7 +776,7 @@ uint32_t nvc0_pwr_data[] = {
 	0x01000000,
 	0x04000000,
 	0x10000000,
-/* 0x0bd4: i2c_sda_map */
+/* 0x0be8: i2c_sda_map */
 	0x00002000,
 	0x00008000,
 	0x00020000,
@@ -780,7 +787,7 @@ uint32_t nvc0_pwr_data[] = {
 	0x02000000,
 	0x08000000,
 	0x20000000,
-/* 0x0bfc: i2c_ctrl */
+/* 0x0c10: i2c_ctrl */
 	0x0000e138,
 	0x0000e150,
 	0x0000e168,
@@ -841,15 +848,10 @@ uint32_t nvc0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
 };
 
 uint32_t nvc0_pwr_code[] = {
-	0x030d0ef5,
+	0x039e0ef5,
 /* 0x0004: rd32 */
 	0x07a007f1,
 	0xd00604b6,
@@ -885,19 +887,22 @@ uint32_t nvc0_pwr_code[] = {
 	0xd4f100dd,
 	0x1bf47000,
 /* 0x007f: nsec */
-	0xf000f8f2,
+	0xf900f8f2,
+	0xf080f990,
 	0x84b62c87,
 	0x0088cf06,
-/* 0x0088: nsec_loop */
+/* 0x008c: nsec_loop */
 	0xb62c97f0,
 	0x99cf0694,
 	0x0298bb00,
 	0xf4069eb8,
-	0x00f8f11e,
-/* 0x009c: wait */
+	0x80fcf11e,
+	0x00f890fc,
+/* 0x00a4: wait */
+	0x80f990f9,
 	0xb62c87f0,
 	0x88cf0684,
-/* 0x00a5: wait_loop */
+/* 0x00b1: wait_loop */
 	0x02eeb900,
 	0xb90421f4,
 	0xadfd02da,
@@ -907,28 +912,29 @@ uint32_t nvc0_pwr_code[] = {
 	0x0099cf06,
 	0xb80298bb,
 	0x1ef4069b,
-/* 0x00c9: wait_done */
-/* 0x00cb: intr_watchdog */
-	0x9800f8df,
+/* 0x00d5: wait_done */
+	0xfc80fcdf,
+/* 0x00db: intr_watchdog */
+	0x9800f890,
 	0x96b003e9,
 	0x2a0bf400,
 	0xbb9a0a98,
 	0x1cf4029a,
 	0x01d7f00f,
-	0x025421f5,
+	0x02dd21f5,
 	0x0ef494bd,
-/* 0x00e9: intr_watchdog_next_time */
+/* 0x00f9: intr_watchdog_next_time */
 	0x9b0a9815,
 	0xf400a6b0,
 	0x9ab8090b,
 	0x061cf406,
-/* 0x00f8: intr_watchdog_next_time_set */
-/* 0x00fb: intr_watchdog_next_proc */
+/* 0x0108: intr_watchdog_next_time_set */
+/* 0x010b: intr_watchdog_next_proc */
 	0x809b0980,
 	0xe0b603e9,
 	0x68e6b158,
 	0xc61bf402,
-/* 0x010a: intr */
+/* 0x011a: intr */
 	0x00f900f8,
 	0x80f904bd,
 	0xa0f990f9,
@@ -948,13 +954,13 @@ uint32_t nvc0_pwr_code[] = {
 	0xf40289c4,
 	0x0080230b,
 	0x58e7f09b,
-	0x98cb21f4,
+	0x98db21f4,
 	0x96b09b09,
 	0x110bf400,
 	0xb63407f0,
 	0x09d00604,
 	0x8004bd00,
-/* 0x016e: intr_skip_watchdog */
+/* 0x017e: intr_skip_watchdog */
 	0x89e49a09,
 	0x0bf40800,
 	0x8897f148,
@@ -967,22 +973,22 @@ uint32_t nvc0_pwr_code[] = {
 	0x48e7f1c0,
 	0x53e3f14f,
 	0x00d7f054,
-	0x02b921f5,
+	0x034221f5,
 	0x07f1c0fc,
 	0x04b604c0,
 	0x000cd006,
-/* 0x01ae: intr_subintr_skip_fifo */
+/* 0x01be: intr_subintr_skip_fifo */
 	0x07f104bd,
 	0x04b60688,
 	0x0009d006,
-/* 0x01ba: intr_skip_subintr */
+/* 0x01ca: intr_skip_subintr */
 	0x89c404bd,
 	0x070bf420,
 	0xffbfa4f1,
-/* 0x01c4: intr_skip_pause */
+/* 0x01d4: intr_skip_pause */
 	0xf44089c4,
 	0xa4f1070b,
-/* 0x01ce: intr_skip_user0 */
+/* 0x01de: intr_skip_user0 */
 	0x07f0ffbf,
 	0x0604b604,
 	0xbd0008d0,
@@ -993,597 +999,733 @@ uint32_t nvc0_pwr_code[] = {
 	0x90fca0fc,
 	0x00fc80fc,
 	0xf80032f4,
-/* 0x01f5: timer */
-	0x1032f401,
-	0xb003f898,
-	0x1cf40086,
-	0x03fe8051,
+/* 0x0205: ticks_from_ns */
+	0xf9c0f901,
+	0xcbd7f1b0,
+	0x00d3f000,
+	0x041321f5,
+	0x03e8ccec,
+	0xf400b4b0,
+	0xeeec120b,
+	0xd7f103e8,
+	0xd3f000cb,
+	0x1321f500,
+/* 0x022d: ticks_from_ns_quit */
+	0x02ceb904,
+	0xc0fcb0fc,
+/* 0x0236: ticks_from_us */
+	0xc0f900f8,
+	0xd7f1b0f9,
+	0xd3f000cb,
+	0x1321f500,
+	0x02ceb904,
+	0xf400b4b0,
+	0xe4bd050b,
+/* 0x0250: ticks_from_us_quit */
+	0xc0fcb0fc,
+/* 0x0256: ticks_to_us */
+	0xd7f100f8,
+	0xd3f000cb,
+	0xecedff00,
+/* 0x0262: timer */
+	0x90f900f8,
+	0x32f480f9,
+	0x03f89810,
+	0xf40086b0,
+	0x84bd651c,
 	0xb63807f0,
 	0x08d00604,
 	0xf004bd00,
-	0x84b60887,
+	0x84b63487,
 	0x0088cf06,
-	0xf40284f0,
-	0x87f0261b,
-	0x0684b634,
-	0xb80088cf,
-	0x0bf406e0,
-	0x06e8b809,
-/* 0x0233: timer_reset */
-	0xf01f1ef4,
-	0x04b63407,
-	0x000ed006,
-	0x0e8004bd,
-/* 0x0241: timer_enable */
-	0x0187f09a,
+	0xbb9a0998,
+	0xe9bb0298,
+	0x03fe8000,
+	0xb60887f0,
+	0x88cf0684,
+	0x0284f000,
+	0xf0261bf4,
+	0x84b63487,
+	0x0088cf06,
+	0xf406e0b8,
+	0xe8b8090b,
+	0x111cf406,
+/* 0x02b8: timer_reset */
+	0xb63407f0,
+	0x0ed00604,
+	0x8004bd00,
+/* 0x02c6: timer_enable */
+	0x87f09a0e,
+	0x3807f001,
+	0xd00604b6,
+	0x04bd0008,
+/* 0x02d4: timer_done */
+	0xfc1031f4,
+	0xf890fc80,
+/* 0x02dd: send_proc */
+	0xf980f900,
+	0x05e89890,
+	0xf004e998,
+	0x89b80486,
+	0x2a0bf406,
+	0x940398c4,
+	0x80b60488,
+	0x008ebb18,
+	0x8000fa98,
+	0x8d80008a,
+	0x028c8001,
+	0xb6038b80,
+	0x94f00190,
+	0x04e98007,
+/* 0x0317: send_done */
+	0xfc0231f4,
+	0xf880fc90,
+/* 0x031d: find */
+	0xf080f900,
+	0x31f45887,
+/* 0x0325: find_loop */
+	0x008a9801,
+	0xf406aeb8,
+	0x80b6100b,
+	0x6886b158,
+	0xf01bf402,
+/* 0x033b: find_done */
+	0xb90132f4,
+	0x80fc028e,
+/* 0x0342: send */
+	0x21f500f8,
+	0x01f4031d,
+/* 0x034b: recv */
+	0xf900f897,
+	0x9880f990,
+	0xe99805e8,
+	0x0132f404,
+	0xf40689b8,
+	0x89c43d0b,
+	0x0180b603,
+	0x800784f0,
+	0xea9805e8,
+	0xfef0f902,
+	0xf0f9018f,
+	0x9402efb9,
+	0xe9bb0499,
+	0x18e0b600,
+	0x9803eb98,
+	0xed9802ec,
+	0x00ee9801,
+	0xf0fca5f9,
+	0xf400f8fe,
+	0xf0fc0131,
+/* 0x0398: recv_done */
+	0x90fc80fc,
+/* 0x039e: init */
+	0x17f100f8,
+	0x14b60108,
+	0x0011cf06,
+	0x010911e7,
+	0xfe0814b6,
+	0x17f10014,
+	0x13f000e0,
+	0x1c07f000,
+	0xd00604b6,
+	0x04bd0001,
+	0xf0ff17f0,
+	0x04b61407,
+	0x0001d006,
+	0x17f004bd,
+	0x0015f102,
+	0x1007f008,
+	0xd00604b6,
+	0x04bd0001,
+	0x011a17f1,
+	0xfe0013f0,
+	0x31f40010,
+	0x0117f010,
 	0xb63807f0,
-	0x08d00604,
-/* 0x024f: timer_done */
-	0xf404bd00,
-	0x00f81031,
-/* 0x0254: send_proc */
-	0x90f980f9,
-	0x9805e898,
-	0x86f004e9,
-	0x0689b804,
-	0xc42a0bf4,
-	0x88940398,
-	0x1880b604,
-	0x98008ebb,
-	0x8a8000fa,
-	0x018d8000,
-	0x80028c80,
-	0x90b6038b,
-	0x0794f001,
-	0xf404e980,
-/* 0x028e: send_done */
-	0x90fc0231,
-	0x00f880fc,
-/* 0x0294: find */
-	0x87f080f9,
-	0x0131f458,
-/* 0x029c: find_loop */
-	0xb8008a98,
-	0x0bf406ae,
-	0x5880b610,
-	0x026886b1,
-	0xf4f01bf4,
-/* 0x02b2: find_done */
-	0x8eb90132,
-	0xf880fc02,
-/* 0x02b9: send */
-	0x9421f500,
-	0x9701f402,
-/* 0x02c2: recv */
-	0xe89800f8,
-	0x04e99805,
-	0xb80132f4,
-	0x0bf40689,
-	0x0389c43d,
-	0xf00180b6,
-	0xe8800784,
-	0x02ea9805,
-	0x8ffef0f9,
-	0xb9f0f901,
-	0x999402ef,
-	0x00e9bb04,
-	0x9818e0b6,
-	0xec9803eb,
-	0x01ed9802,
-	0xf900ee98,
-	0xfef0fca5,
-	0x31f400f8,
-/* 0x030b: recv_done */
-	0xf8f0fc01,
-/* 0x030d: init */
-	0x0817f100,
-	0x0614b601,
-	0xe70011cf,
-	0xb6010911,
-	0x14fe0814,
-	0xe017f100,
-	0x0013f000,
-	0xb61c07f0,
 	0x01d00604,
 	0xf004bd00,
-	0x07f0ff17,
-	0x0604b614,
-	0xbd0001d0,
-	0x0217f004,
-	0x080015f1,
-	0xb61007f0,
-	0x01d00604,
-	0xf104bd00,
-	0xf0010a17,
-	0x10fe0013,
-	0x1031f400,
-	0xf00117f0,
-	0x04b63807,
-	0x0001d006,
-	0xf7f004bd,
-/* 0x0371: init_proc */
-	0x01f19858,
-	0xf40016b0,
-	0x15f9fa0b,
-	0xf458f0b6,
-/* 0x0382: host_send */
-	0x17f1f20e,
-	0x14b604b0,
-	0x0011cf06,
-	0x04a027f1,
-	0xcf0624b6,
-	0x12b80022,
-	0x320bf406,
-	0x94071ec4,
-	0xe0b704ee,
-	0xeb980270,
-	0x02ec9803,
-	0x9801ed98,
-	0x21f500ee,
-	0x10b602b9,
-	0x0f1ec401,
-	0x04b007f1,
-	0xd00604b6,
-	0x04bd000e,
-/* 0x03cb: host_send_done */
-	0xf8ba0ef4,
-/* 0x03cd: host_recv */
-	0x4917f100,
-	0x5413f14e,
-	0x06e1b852,
-/* 0x03db: host_recv_wait */
-	0xf1aa0bf4,
-	0xb604cc17,
-	0x11cf0614,
-	0xc827f100,
-	0x0624b604,
-	0xf00022cf,
-	0x12b80816,
-	0xe60bf406,
-	0xb60723c4,
-	0x30b70434,
-	0x3b8002f0,
-	0x023c8003,
-	0x80013d80,
-	0x20b6003e,
-	0x0f24f001,
-	0x04c807f1,
+/* 0x0402: init_proc */
+	0xf19858f7,
+	0x0016b001,
+	0xf9fa0bf4,
+	0x58f0b615,
+/* 0x0413: mulu32_32_64 */
+	0xf9f20ef4,
+	0xf920f910,
+	0x9540f930,
+	0xd29510e1,
+	0xbdc4bd10,
+	0xc0edffb4,
+	0xb9301dff,
+	0x34f10234,
+	0x34b6ffff,
+	0x1045b610,
+	0xbb00c3bb,
+	0xe2ff01b4,
+	0x0234b930,
+	0xffff34f1,
+	0xb61034b6,
+	0xc3bb1045,
+	0x01b4bb00,
+	0xbb3012ff,
+	0x40fc00b3,
+	0x20fc30fc,
+	0x00f810fc,
+/* 0x0464: host_send */
+	0x04b017f1,
+	0xcf0614b6,
+	0x27f10011,
+	0x24b604a0,
+	0x0022cf06,
+	0xf40612b8,
+	0x1ec4320b,
+	0x04ee9407,
+	0x0270e0b7,
+	0x9803eb98,
+	0xed9802ec,
+	0x00ee9801,
+	0x034221f5,
+	0xc40110b6,
+	0x07f10f1e,
+	0x04b604b0,
+	0x000ed006,
+	0x0ef404bd,
+/* 0x04ad: host_send_done */
+/* 0x04af: host_recv */
+	0xf100f8ba,
+	0xf14e4917,
+	0xb8525413,
+	0x0bf406e1,
+/* 0x04bd: host_recv_wait */
+	0xcc17f1aa,
+	0x0614b604,
+	0xf10011cf,
+	0xb604c827,
+	0x22cf0624,
+	0x0816f000,
+	0xf40612b8,
+	0x23c4e60b,
+	0x0434b607,
+	0x02f030b7,
+	0x80033b80,
+	0x3d80023c,
+	0x003e8001,
+	0xf00120b6,
+	0x07f10f24,
+	0x04b604c8,
+	0x0002d006,
+	0x27f004bd,
+	0x0007f040,
 	0xd00604b6,
 	0x04bd0002,
-	0xf04027f0,
-	0x04b60007,
-	0x0002d006,
-	0x00f804bd,
-/* 0x0430: host_init */
-	0x008017f1,
-	0xf11014b6,
-	0xf1027015,
-	0xb604d007,
-	0x01d00604,
-	0xf104bd00,
-	0xb6008017,
-	0x15f11014,
-	0x07f102f0,
-	0x04b604dc,
-	0x0001d006,
-	0x17f004bd,
-	0xc407f101,
+/* 0x0512: host_init */
+	0x17f100f8,
+	0x14b60080,
+	0x7015f110,
+	0xd007f102,
 	0x0604b604,
 	0xbd0001d0,
-/* 0x046f: memx_func_enter */
-	0xf000f804,
+	0x8017f104,
+	0x1014b600,
+	0x02f015f1,
+	0x04dc07f1,
+	0xd00604b6,
+	0x04bd0001,
+	0xf10117f0,
+	0xb604c407,
+	0x01d00604,
+	0xf804bd00,
+/* 0x0551: memx_func_enter */
+	0x2067f100,
+	0x5d77f116,
+	0xff73f1f5,
+	0x026eb9ff,
+	0xb90421f4,
+	0x87fd02d8,
+	0xf960f904,
+	0xfcd0fc80,
+	0x3f21f4e0,
+	0xfffe77f1,
+	0xffff73f1,
+	0xf4026eb9,
+	0xd8b90421,
+	0x0487fd02,
+	0x80f960f9,
+	0xe0fcd0fc,
+	0xf13f21f4,
+	0xb926f067,
+	0x21f4026e,
+	0x02d8b904,
+	0xf90487fd,
+	0xfc80f960,
+	0xf4e0fcd0,
+	0x67f03f21,
+	0xe007f104,
+	0x0604b607,
+	0xbd0006d0,
+/* 0x05bd: memx_func_enter_wait */
+	0xc067f104,
+	0x0664b607,
+	0xf00066cf,
+	0x0bf40464,
+	0x2c67f0f3,
+	0xcf0664b6,
+	0x06800066,
+/* 0x05db: memx_func_leave */
+	0xf000f8ee,
+	0x64b62c67,
+	0x0066cf06,
+	0xf0ef0680,
 	0x07f10467,
-	0x04b607e0,
+	0x04b607e4,
 	0x0006d006,
-/* 0x047e: memx_func_enter_wait */
+/* 0x05f6: memx_func_leave_wait */
 	0x67f104bd,
 	0x64b607c0,
 	0x0066cf06,
 	0xf40464f0,
-	0x1698f30b,
+	0x67f1f31b,
+	0x77f126f0,
+	0x73f00001,
+	0x026eb900,
+	0xb90421f4,
+	0x87fd02d8,
+	0xf960f905,
+	0xfcd0fc80,
+	0x3f21f4e0,
+	0x162067f1,
+	0xf4026eb9,
+	0xd8b90421,
+	0x0587fd02,
+	0x80f960f9,
+	0xe0fcd0fc,
+	0xf13f21f4,
+	0xf00aa277,
+	0x6eb90073,
+	0x0421f402,
+	0xfd02d8b9,
+	0x60f90587,
+	0xd0fc80f9,
+	0x21f4e0fc,
+/* 0x0663: memx_func_wait_vblank */
+	0x9800f83f,
+	0x66b00016,
+	0x130bf400,
+	0xf40166b0,
+	0x0ef4060b,
+/* 0x0675: memx_func_wait_vblank_head1 */
+	0x2077f12e,
+	0x070ef400,
+/* 0x067c: memx_func_wait_vblank_head0 */
+	0x000877f1,
+/* 0x0680: memx_func_wait_vblank_0 */
+	0x07c467f1,
+	0xcf0664b6,
+	0x67fd0066,
+	0xf31bf404,
+/* 0x0690: memx_func_wait_vblank_1 */
+	0x07c467f1,
+	0xcf0664b6,
+	0x67fd0066,
+	0xf30bf404,
+/* 0x06a0: memx_func_wait_vblank_fini */
+	0xf80410b6,
+/* 0x06a5: memx_func_wr32 */
+	0x00169800,
+	0xb6011598,
+	0x60f90810,
+	0xd0fc50f9,
+	0x21f4e0fc,
+	0x0242b63f,
+	0xf8e91bf4,
+/* 0x06c1: memx_func_wait */
+	0x2c87f000,
+	0xcf0684b6,
+	0x1e980088,
+	0x011d9800,
+	0x98021c98,
+	0x10b6031b,
+	0xa421f410,
+/* 0x06de: memx_func_delay */
+	0x1e9800f8,
 	0x0410b600,
-/* 0x0496: memx_func_leave */
-	0x67f000f8,
-	0xe407f104,
+	0xf87f21f4,
+/* 0x06e9: memx_exec */
+	0xf9e0f900,
+	0x02c1b9d0,
+/* 0x06f3: memx_exec_next */
+	0x9802b2b9,
+	0x10b60013,
+	0xf034e704,
+	0xe033e701,
+	0x0132b601,
+	0x980c30f0,
+	0x55f9de35,
+	0xf40612b8,
+	0x0b98e41e,
+	0xef0c98ee,
+	0xf102cbbb,
+	0xb607c4b7,
+	0xbbcf06b4,
+	0xfcd0fc00,
+	0x4221f5e0,
+/* 0x072f: memx_info */
+	0xf100f803,
+	0xf103c0c7,
+	0xf50800b7,
+	0xf8034221,
+/* 0x073d: memx_recv */
+	0x01d6b000,
+	0xb0a90bf4,
+	0x0bf400d6,
+/* 0x074b: memx_init */
+	0xf800f8e9,
+/* 0x074d: perf_recv */
+/* 0x074f: perf_init */
+	0xf800f800,
+/* 0x0751: i2c_drive_scl */
+	0x0036b000,
+	0xf1110bf4,
+	0xb607e007,
+	0x01d00604,
+	0xf804bd00,
+/* 0x0765: i2c_drive_scl_lo */
+	0xe407f100,
 	0x0604b607,
-	0xbd0006d0,
-/* 0x04a5: memx_func_leave_wait */
-	0xc067f104,
-	0x0664b607,
-	0xf00066cf,
-	0x1bf40464,
-/* 0x04b7: memx_func_wr32 */
-	0x9800f8f3,
-	0x15980016,
-	0x0810b601,
-	0x50f960f9,
-	0xe0fcd0fc,
-	0xb63f21f4,
-	0x1bf40242,
-/* 0x04d3: memx_func_wait */
-	0xf000f8e9,
-	0x84b62c87,
-	0x0088cf06,
-	0x98001e98,
-	0x1c98011d,
-	0x031b9802,
-	0xf41010b6,
-	0x00f89c21,
-/* 0x04f0: memx_func_delay */
-	0xb6001e98,
-	0x21f40410,
-/* 0x04fb: memx_exec */
-	0xf900f87f,
-	0xb9d0f9e0,
-	0xb2b902c1,
-/* 0x0505: memx_exec_next */
-	0x00139802,
-	0x950410b6,
-	0x30f01034,
-	0xde35980c,
-	0x12b855f9,
-	0xec1ef406,
-	0xe0fcd0fc,
-	0x02b921f5,
-/* 0x0526: memx_info */
-	0xc7f100f8,
-	0xb7f103ac,
-	0x21f50800,
-	0x00f802b9,
-/* 0x0534: memx_recv */
-	0xf401d6b0,
-	0xd6b0c40b,
-	0xe90bf400,
-/* 0x0542: memx_init */
-	0x00f800f8,
-/* 0x0544: perf_recv */
-/* 0x0546: perf_init */
-	0x00f800f8,
-/* 0x0548: i2c_drive_scl */
-	0xf40036b0,
-	0x07f1110b,
-	0x04b607e0,
-	0x0001d006,
-	0x00f804bd,
-/* 0x055c: i2c_drive_scl_lo */
-	0x07e407f1,
-	0xd00604b6,
-	0x04bd0001,
-/* 0x056a: i2c_drive_sda */
-	0x36b000f8,
-	0x110bf400,
-	0x07e007f1,
-	0xd00604b6,
-	0x04bd0002,
-/* 0x057e: i2c_drive_sda_lo */
-	0x07f100f8,
-	0x04b607e4,
-	0x0002d006,
-	0x00f804bd,
-/* 0x058c: i2c_sense_scl */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0431fd00,
-	0xf4060bf4,
-/* 0x05a2: i2c_sense_scl_done */
-	0x00f80131,
-/* 0x05a4: i2c_sense_sda */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0432fd00,
-	0xf4060bf4,
-/* 0x05ba: i2c_sense_sda_done */
-	0x00f80131,
-/* 0x05bc: i2c_raise_scl */
-	0x47f140f9,
-	0x37f00898,
-	0x4821f501,
-/* 0x05c9: i2c_raise_scl_wait */
-	0xe8e7f105,
-	0x7f21f403,
-	0x058c21f5,
-	0xb60901f4,
-	0x1bf40142,
-/* 0x05dd: i2c_raise_scl_done */
-	0xf840fcef,
-/* 0x05e1: i2c_start */
-	0x8c21f500,
-	0x0d11f405,
-	0x05a421f5,
-	0xf40611f4,
-/* 0x05f2: i2c_start_rep */
-	0x37f0300e,
-	0x4821f500,
-	0x0137f005,
-	0x056a21f5,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0xbc21f550,
-	0x0464b605,
-/* 0x061f: i2c_start_send */
-	0xf01f11f4,
+	0xbd0001d0,
+/* 0x0773: i2c_drive_sda */
+	0xb000f804,
+	0x0bf40036,
+	0xe007f111,
+	0x0604b607,
+	0xbd0002d0,
+/* 0x0787: i2c_drive_sda_lo */
+	0xf100f804,
+	0xb607e407,
+	0x02d00604,
+	0xf804bd00,
+/* 0x0795: i2c_sense_scl */
+	0x0132f400,
+	0x07c437f1,
+	0xcf0634b6,
+	0x31fd0033,
+	0x060bf404,
+/* 0x07ab: i2c_sense_scl_done */
+	0xf80131f4,
+/* 0x07ad: i2c_sense_sda */
+	0x0132f400,
+	0x07c437f1,
+	0xcf0634b6,
+	0x32fd0033,
+	0x060bf404,
+/* 0x07c3: i2c_sense_sda_done */
+	0xf80131f4,
+/* 0x07c5: i2c_raise_scl */
+	0xf140f900,
+	0xf0089847,
+	0x21f50137,
+/* 0x07d2: i2c_raise_scl_wait */
+	0xe7f10751,
+	0x21f403e8,
+	0x9521f57f,
+	0x0901f407,
+	0xf40142b6,
+/* 0x07e6: i2c_raise_scl_done */
+	0x40fcef1b,
+/* 0x07ea: i2c_start */
+	0x21f500f8,
+	0x11f40795,
+	0xad21f50d,
+	0x0611f407,
+/* 0x07fb: i2c_start_rep */
+	0xf0300ef4,
 	0x21f50037,
-	0xe7f1056a,
-	0x21f41388,
-	0x0037f07f,
-	0x054821f5,
-	0x1388e7f1,
-/* 0x063b: i2c_start_out */
-	0xf87f21f4,
-/* 0x063d: i2c_stop */
-	0x0037f000,
-	0x054821f5,
+	0x37f00751,
+	0x7321f501,
+	0x0076bb07,
+	0xf90465b6,
+	0x04659450,
+	0xbd0256bb,
+	0x0475fd50,
+	0x21f550fc,
+	0x64b607c5,
+	0x1f11f404,
+/* 0x0828: i2c_start_send */
 	0xf50037f0,
-	0xf1056a21,
-	0xf403e8e7,
+	0xf1077321,
+	0xf41388e7,
 	0x37f07f21,
-	0x4821f501,
-	0x88e7f105,
+	0x5121f500,
+	0x88e7f107,
 	0x7f21f413,
-	0xf50137f0,
-	0xf1056a21,
-	0xf41388e7,
-	0x00f87f21,
-/* 0x0670: i2c_bitw */
-	0x056a21f5,
+/* 0x0844: i2c_start_out */
+/* 0x0846: i2c_stop */
+	0x37f000f8,
+	0x5121f500,
+	0x0037f007,
+	0x077321f5,
 	0x03e8e7f1,
-	0xbb7f21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x05bc21f5,
-	0xf40464b6,
-	0xe7f11811,
+	0xf07f21f4,
+	0x21f50137,
+	0xe7f10751,
 	0x21f41388,
-	0x0037f07f,
-	0x054821f5,
+	0x0137f07f,
+	0x077321f5,
 	0x1388e7f1,
-/* 0x06af: i2c_bitw_out */
 	0xf87f21f4,
-/* 0x06b1: i2c_bitr */
-	0x0137f000,
-	0x056a21f5,
-	0x03e8e7f1,
-	0xbb7f21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x05bc21f5,
-	0xf40464b6,
-	0x21f51b11,
-	0x37f005a4,
-	0x4821f500,
-	0x88e7f105,
+/* 0x0879: i2c_bitw */
+	0x7321f500,
+	0xe8e7f107,
+	0x7f21f403,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0xc521f550,
+	0x0464b607,
+	0xf11811f4,
+	0xf41388e7,
+	0x37f07f21,
+	0x5121f500,
+	0x88e7f107,
 	0x7f21f413,
-	0xf4013cf0,
-/* 0x06f6: i2c_bitr_done */
-	0x00f80131,
-/* 0x06f8: i2c_get_byte */
-	0xf00057f0,
-/* 0x06fe: i2c_get_byte_next */
-	0x54b60847,
+/* 0x08b8: i2c_bitw_out */
+/* 0x08ba: i2c_bitr */
+	0x37f000f8,
+	0x7321f501,
+	0xe8e7f107,
+	0x7f21f403,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0xc521f550,
+	0x0464b607,
+	0xf51b11f4,
+	0xf007ad21,
+	0x21f50037,
+	0xe7f10751,
+	0x21f41388,
+	0x013cf07f,
+/* 0x08ff: i2c_bitr_done */
+	0xf80131f4,
+/* 0x0901: i2c_get_byte */
+	0x0057f000,
+/* 0x0907: i2c_get_byte_next */
+	0xb60847f0,
+	0x76bb0154,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb608ba21,
+	0x11f40464,
+	0x0553fd2b,
+	0xf40142b6,
+	0x37f0d81b,
 	0x0076bb01,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b606b1,
-	0x2b11f404,
-	0xb60553fd,
-	0x1bf40142,
-	0x0137f0d8,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0x7021f550,
-	0x0464b606,
-/* 0x0748: i2c_get_byte_done */
-/* 0x074a: i2c_put_byte */
-	0x47f000f8,
-/* 0x074d: i2c_put_byte_next */
-	0x0142b608,
-	0xbb3854ff,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x067021f5,
-	0xf40464b6,
-	0x46b03411,
-	0xd81bf400,
+	0x64b60879,
+/* 0x0951: i2c_get_byte_done */
+/* 0x0953: i2c_put_byte */
+	0xf000f804,
+/* 0x0956: i2c_put_byte_next */
+	0x42b60847,
+	0x3854ff01,
 	0xb60076bb,
 	0x50f90465,
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0xb121f550,
-	0x0464b606,
-	0xbb0f11f4,
-	0x36b00076,
-	0x061bf401,
-/* 0x07a3: i2c_put_byte_done */
-	0xf80132f4,
-/* 0x07a5: i2c_addr */
-	0x0076bb00,
+	0x7921f550,
+	0x0464b608,
+	0xb03411f4,
+	0x1bf40046,
+	0x0076bbd8,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b605e1,
-	0x2911f404,
-	0x012ec3e7,
-	0xfd0134b6,
-	0x76bb0553,
+	0x64b608ba,
+	0x0f11f404,
+	0xb00076bb,
+	0x1bf40136,
+	0x0132f406,
+/* 0x09ac: i2c_put_byte_done */
+/* 0x09ae: i2c_addr */
+	0x76bb00f8,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb6074a21,
-/* 0x07ea: i2c_addr_done */
-	0x00f80464,
-/* 0x07ec: i2c_acquire_addr */
-	0xb6f8cec7,
-	0xe0b702e4,
-	0xee980bfc,
-/* 0x07fb: i2c_acquire */
-	0xf500f800,
-	0xf407ec21,
-	0xd9f00421,
-	0x3f21f403,
-/* 0x080a: i2c_release */
-	0x21f500f8,
-	0x21f407ec,
-	0x03daf004,
-	0xf83f21f4,
-/* 0x0819: i2c_recv */
-	0x0132f400,
-	0xb6f8c1c7,
-	0x16b00214,
-	0x3a1ff528,
-	0xd413a001,
-	0x0032980b,
-	0x0bac13a0,
-	0xf4003198,
-	0xd0f90231,
-	0xd0f9e0f9,
-	0x000067f1,
-	0x100063f1,
-	0xbb016792,
+	0xb607ea21,
+	0x11f40464,
+	0x2ec3e729,
+	0x0134b601,
+	0xbb0553fd,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x07fb21f5,
-	0xfc0464b6,
-	0x00d6b0d0,
-	0x00b31bf5,
-	0xbb0057f0,
+	0x095321f5,
+/* 0x09f3: i2c_addr_done */
+	0xf80464b6,
+/* 0x09f5: i2c_acquire_addr */
+	0xf8cec700,
+	0xb702e4b6,
+	0x980c10e0,
+	0x00f800ee,
+/* 0x0a04: i2c_acquire */
+	0x09f521f5,
+	0xf00421f4,
+	0x21f403d9,
+/* 0x0a13: i2c_release */
+	0xf500f83f,
+	0xf409f521,
+	0xdaf00421,
+	0x3f21f403,
+/* 0x0a22: i2c_recv */
+	0x32f400f8,
+	0xf8c1c701,
+	0xb00214b6,
+	0x1ff52816,
+	0x13a0013a,
+	0x32980be8,
+	0xc013a000,
+	0x0031980b,
+	0xf90231f4,
+	0xf9e0f9d0,
+	0x0067f1d0,
+	0x0063f100,
+	0x01679210,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x0421f550,
+	0x0464b60a,
+	0xd6b0d0fc,
+	0xb31bf500,
+	0x0057f000,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0xae21f550,
+	0x0464b609,
+	0x00d011f5,
+	0xbbe0c5c7,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x07a521f5,
+	0x095321f5,
 	0xf50464b6,
-	0xc700d011,
-	0x76bbe0c5,
+	0xf000ad11,
+	0x76bb0157,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb6074a21,
+	0xb609ae21,
 	0x11f50464,
-	0x57f000ad,
-	0x0076bb01,
-	0xf90465b6,
-	0x04659450,
-	0xbd0256bb,
-	0x0475fd50,
-	0x21f550fc,
-	0x64b607a5,
-	0x8a11f504,
-	0x0076bb00,
-	0xf90465b6,
-	0x04659450,
-	0xbd0256bb,
-	0x0475fd50,
-	0x21f550fc,
-	0x64b606f8,
-	0x6a11f404,
-	0xbbe05bcb,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x063d21f5,
-	0xb90464b6,
-	0x74bd025b,
-/* 0x091f: i2c_recv_not_rd08 */
-	0xb0430ef4,
-	0x1bf401d6,
-	0x0057f03d,
-	0x07a521f5,
-	0xc73311f4,
-	0x21f5e0c5,
-	0x11f4074a,
-	0x0057f029,
-	0x07a521f5,
-	0xc71f11f4,
-	0x21f5e0b5,
-	0x11f4074a,
-	0x3d21f515,
-	0xc774bd06,
-	0x1bf408c5,
-	0x0232f409,
-/* 0x095f: i2c_recv_not_wr08 */
-/* 0x095f: i2c_recv_done */
-	0xc7030ef4,
-	0x21f5f8ce,
-	0xe0fc080a,
-	0x12f4d0fc,
-	0x027cb90a,
-	0x02b921f5,
-/* 0x0974: i2c_recv_exit */
-/* 0x0976: i2c_init */
+	0x76bb008a,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb6090121,
+	0x11f40464,
+	0xe05bcb6a,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x4621f550,
+	0x0464b608,
+	0xbd025bb9,
+	0x430ef474,
+/* 0x0b28: i2c_recv_not_rd08 */
+	0xf401d6b0,
+	0x57f03d1b,
+	0xae21f500,
+	0x3311f409,
+	0xf5e0c5c7,
+	0xf4095321,
+	0x57f02911,
+	0xae21f500,
+	0x1f11f409,
+	0xf5e0b5c7,
+	0xf4095321,
+	0x21f51511,
+	0x74bd0846,
+	0xf408c5c7,
+	0x32f4091b,
+	0x030ef402,
+/* 0x0b68: i2c_recv_not_wr08 */
+/* 0x0b68: i2c_recv_done */
+	0xf5f8cec7,
+	0xfc0a1321,
+	0xf4d0fce0,
+	0x7cb90a12,
+	0x4221f502,
+/* 0x0b7d: i2c_recv_exit */
+/* 0x0b7f: i2c_init */
+	0xf800f803,
+/* 0x0b81: test_recv */
+	0xd817f100,
+	0x0614b605,
+	0xb60011cf,
+	0x07f10110,
+	0x04b605d8,
+	0x0001d006,
+	0xe7f104bd,
+	0xe3f1d900,
+	0x21f5134f,
+	0x00f80262,
+/* 0x0ba8: test_init */
+	0x0800e7f1,
+	0x026221f5,
+/* 0x0bb2: idle_recv */
 	0x00f800f8,
-/* 0x0978: test_recv */
-	0x05d817f1,
-	0xcf0614b6,
-	0x10b60011,
-	0xd807f101,
-	0x0604b605,
-	0xbd0001d0,
-	0x00e7f104,
-	0x4fe3f1d9,
-	0xf521f513,
-/* 0x099f: test_init */
-	0xf100f801,
-	0xf50800e7,
-	0xf801f521,
-/* 0x09a9: idle_recv */
-/* 0x09ab: idle */
-	0xf400f800,
-	0x17f10031,
-	0x14b605d4,
-	0x0011cf06,
-	0xf10110b6,
-	0xb605d407,
-	0x01d00604,
-/* 0x09c7: idle_loop */
-	0xf004bd00,
-	0x32f45817,
-/* 0x09cd: idle_proc */
-/* 0x09cd: idle_proc_exec */
-	0xb910f902,
-	0x21f5021e,
-	0x10fc02c2,
-	0xf40911f4,
-	0x0ef40231,
-/* 0x09e1: idle_proc_next */
-	0x5810b6ef,
-	0xf4061fb8,
-	0x02f4e61b,
-	0x0028f4dd,
-	0x00bb0ef4,
-	0x00000000,
-	0x00000000,
+/* 0x0bb4: idle */
+	0xf10031f4,
+	0xb605d417,
+	0x11cf0614,
+	0x0110b600,
+	0x05d407f1,
+	0xd00604b6,
+	0x04bd0001,
+/* 0x0bd0: idle_loop */
+	0xf45817f0,
+/* 0x0bd6: idle_proc */
+/* 0x0bd6: idle_proc_exec */
+	0x10f90232,
+	0xf5021eb9,
+	0xfc034b21,
+	0x0911f410,
+	0xf40231f4,
+/* 0x0bea: idle_proc_next */
+	0x10b6ef0e,
+	0x061fb858,
+	0xf4e61bf4,
+	0x28f4dd02,
+	0xbb0ef400,
 	0x00000000,
 };
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc
index 8a89dfe41ce1..b85443261569 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc
@@ -23,6 +23,7 @@
  */
 
 #define NVKM_PPWR_CHIPSET GF119
+#define HW_TICKS_PER_US 324
 
 //#define NVKM_FALCON_PC24
 #define NVKM_FALCON_UNSHIFTED_IO
@@ -34,6 +35,7 @@
 .section #nvd0_pwr_data
 #define INCLUDE_PROC
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
@@ -44,6 +46,7 @@
 
 #define INCLUDE_DATA
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
@@ -56,6 +59,7 @@
 .section #nvd0_pwr_code
 #define INCLUDE_CODE
 #include "kernel.fuc"
+#include "arith.fuc"
 #include "host.fuc"
 #include "memx.fuc"
 #include "perf.fuc"
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h
index 8d369b3faaba..12d86f72ad10 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h
@@ -24,8 +24,8 @@ uint32_t nvd0_pwr_data[] = {
 	0x00000000,
 /* 0x0058: proc_list_head */
 	0x54534f48,
-	0x000003be,
-	0x00000367,
+	0x0000049d,
+	0x00000446,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -46,8 +46,8 @@ uint32_t nvd0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x584d454d,
-	0x000004b8,
-	0x000004aa,
+	0x00000678,
+	0x0000066a,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -68,8 +68,8 @@ uint32_t nvd0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x46524550,
-	0x000004bc,
-	0x000004ba,
+	0x0000067c,
+	0x0000067a,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -90,8 +90,8 @@ uint32_t nvd0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x5f433249,
-	0x000008d7,
-	0x0000077a,
+	0x00000a97,
+	0x0000093a,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -112,8 +112,8 @@ uint32_t nvd0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x54534554,
-	0x000008fa,
-	0x000008d9,
+	0x00000aba,
+	0x00000a99,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -134,8 +134,8 @@ uint32_t nvd0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x454c4449,
-	0x00000906,
-	0x00000904,
+	0x00000ac6,
+	0x00000ac4,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -227,24 +227,31 @@ uint32_t nvd0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 /* 0x0370: memx_func_head */
-	0x00010000,
-	0x00000000,
-	0x000003f4,
-/* 0x037c: memx_func_next */
 	0x00000001,
 	0x00000000,
-	0x00000415,
+	0x000004d3,
+/* 0x037c: memx_func_next */
 	0x00000002,
+	0x00000000,
+	0x00000554,
+	0x00000003,
 	0x00000002,
-	0x00000430,
-	0x00040003,
+	0x000005d8,
+	0x00040004,
+	0x00000000,
+	0x000005f4,
+	0x00010005,
+	0x00000000,
+	0x0000060e,
+	0x00010006,
+	0x00000000,
+	0x000005d3,
+/* 0x03b8: memx_func_tail */
+/* 0x03b8: memx_ts_start */
 	0x00000000,
-	0x0000044c,
-	0x00010004,
+/* 0x03bc: memx_ts_end */
 	0x00000000,
-	0x00000466,
-/* 0x03ac: memx_func_tail */
-/* 0x03ac: memx_data_head */
+/* 0x03c0: memx_data_head */
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -757,8 +764,8 @@ uint32_t nvd0_pwr_data[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
-/* 0x0bac: memx_data_tail */
-/* 0x0bac: i2c_scl_map */
+/* 0x0bc0: memx_data_tail */
+/* 0x0bc0: i2c_scl_map */
 	0x00000400,
 	0x00000800,
 	0x00001000,
@@ -769,7 +776,7 @@ uint32_t nvd0_pwr_data[] = {
 	0x00020000,
 	0x00040000,
 	0x00080000,
-/* 0x0bd4: i2c_sda_map */
+/* 0x0be8: i2c_sda_map */
 	0x00100000,
 	0x00200000,
 	0x00400000,
@@ -781,10 +788,69 @@ uint32_t nvd0_pwr_data[] = {
 	0x10000000,
 	0x20000000,
 	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 };
 
 uint32_t nvd0_pwr_code[] = {
-	0x02bf0ef5,
+	0x034d0ef5,
 /* 0x0004: rd32 */
 	0x07a007f1,
 	0xbd000ed0,
@@ -814,17 +880,20 @@ uint32_t nvd0_pwr_code[] = {
 	0xd4f100dd,
 	0x1bf47000,
 /* 0x0067: nsec */
-	0xf000f8f5,
+	0xf900f8f5,
+	0xf080f990,
 	0x88cf2c87,
-/* 0x006d: nsec_loop */
+/* 0x0071: nsec_loop */
 	0x2c97f000,
 	0xbb0099cf,
 	0x9eb80298,
 	0xf41ef406,
-/* 0x007e: wait */
-	0x87f000f8,
+	0x90fc80fc,
+/* 0x0086: wait */
+	0x90f900f8,
+	0x87f080f9,
 	0x0088cf2c,
-/* 0x0084: wait_loop */
+/* 0x0090: wait_loop */
 	0xf402eeb9,
 	0xdab90421,
 	0x04adfd02,
@@ -833,28 +902,29 @@ uint32_t nvd0_pwr_code[] = {
 	0x0099cf2c,
 	0xb80298bb,
 	0x1ef4069b,
-/* 0x00a5: wait_done */
-/* 0x00a7: intr_watchdog */
-	0x9800f8e2,
+/* 0x00b1: wait_done */
+	0xfc80fce2,
+/* 0x00b7: intr_watchdog */
+	0x9800f890,
 	0x96b003e9,
 	0x2a0bf400,
 	0xbb9a0a98,
 	0x1cf4029a,
 	0x01d7f00f,
-	0x020621f5,
+	0x028c21f5,
 	0x0ef494bd,
-/* 0x00c5: intr_watchdog_next_time */
+/* 0x00d5: intr_watchdog_next_time */
 	0x9b0a9815,
 	0xf400a6b0,
 	0x9ab8090b,
 	0x061cf406,
-/* 0x00d4: intr_watchdog_next_time_set */
-/* 0x00d7: intr_watchdog_next_proc */
+/* 0x00e4: intr_watchdog_next_time_set */
+/* 0x00e7: intr_watchdog_next_proc */
 	0x809b0980,
 	0xe0b603e9,
 	0x68e6b158,
 	0xc61bf402,
-/* 0x00e6: intr */
+/* 0x00f6: intr */
 	0x00f900f8,
 	0x80f904bd,
 	0xa0f990f9,
@@ -872,12 +942,12 @@ uint32_t nvd0_pwr_code[] = {
 	0x0bf40289,
 	0x9b008020,
 	0xf458e7f0,
-	0x0998a721,
+	0x0998b721,
 	0x0096b09b,
 	0xf00e0bf4,
 	0x09d03407,
 	0x8004bd00,
-/* 0x013e: intr_skip_watchdog */
+/* 0x014e: intr_skip_watchdog */
 	0x89e49a09,
 	0x0bf40800,
 	0x8897f13c,
@@ -889,20 +959,20 @@ uint32_t nvd0_pwr_code[] = {
 	0xf14f48e7,
 	0xf05453e3,
 	0x21f500d7,
-	0xc0fc026b,
+	0xc0fc02f1,
 	0x04c007f1,
 	0xbd000cd0,
-/* 0x0175: intr_subintr_skip_fifo */
+/* 0x0185: intr_subintr_skip_fifo */
 	0x8807f104,
 	0x0009d006,
-/* 0x017e: intr_skip_subintr */
+/* 0x018e: intr_skip_subintr */
 	0x89c404bd,
 	0x070bf420,
 	0xffbfa4f1,
-/* 0x0188: intr_skip_pause */
+/* 0x0198: intr_skip_pause */
 	0xf44089c4,
 	0xa4f1070b,
-/* 0x0192: intr_skip_user0 */
+/* 0x01a2: intr_skip_user0 */
 	0x07f0ffbf,
 	0x0008d004,
 	0x80fc04bd,
@@ -912,189 +982,298 @@ uint32_t nvd0_pwr_code[] = {
 	0xfca0fcb0,
 	0xfc80fc90,
 	0x0032f400,
-/* 0x01b6: timer */
-	0x32f401f8,
-	0x03f89810,
-	0xf40086b0,
-	0xfe80421c,
-	0x3807f003,
+/* 0x01c6: ticks_from_ns */
+	0xc0f901f8,
+	0xd7f1b0f9,
+	0xd3f00144,
+	0xb321f500,
+	0xe8ccec03,
+	0x00b4b003,
+	0xec120bf4,
+	0xf103e8ee,
+	0xf00144d7,
+	0x21f500d3,
+/* 0x01ee: ticks_from_ns_quit */
+	0xceb903b3,
+	0xfcb0fc02,
+/* 0x01f7: ticks_from_us */
+	0xf900f8c0,
+	0xf1b0f9c0,
+	0xf00144d7,
+	0x21f500d3,
+	0xceb903b3,
+	0x00b4b002,
+	0xbd050bf4,
+/* 0x0211: ticks_from_us_quit */
+	0xfcb0fce4,
+/* 0x0217: ticks_to_us */
+	0xf100f8c0,
+	0xf00144d7,
+	0xedff00d3,
+/* 0x0223: timer */
+	0xf900f8ec,
+	0xf480f990,
+	0xf8981032,
+	0x0086b003,
+	0xbd531cf4,
+	0x3807f084,
 	0xbd0008d0,
-	0x0887f004,
-	0xf00088cf,
-	0x1bf40284,
-	0x3487f020,
-	0xb80088cf,
-	0x0bf406e0,
-	0x06e8b809,
-/* 0x01eb: timer_reset */
-	0xf0191ef4,
-	0x0ed03407,
-	0x8004bd00,
-/* 0x01f6: timer_enable */
-	0x87f09a0e,
-	0x3807f001,
-	0xbd0008d0,
-/* 0x0201: timer_done */
-	0x1031f404,
-/* 0x0206: send_proc */
-	0x80f900f8,
-	0xe89890f9,
+	0x3487f004,
+	0x980088cf,
+	0x98bb9a09,
+	0x00e9bb02,
+	0xf003fe80,
+	0x88cf0887,
+	0x0284f000,
+	0xf0201bf4,
+	0x88cf3487,
+	0x06e0b800,
+	0xb8090bf4,
+	0x1cf406e8,
+/* 0x026d: timer_reset */
+	0x3407f00e,
+	0xbd000ed0,
+	0x9a0e8004,
+/* 0x0278: timer_enable */
+	0xf00187f0,
+	0x08d03807,
+/* 0x0283: timer_done */
+	0xf404bd00,
+	0x80fc1031,
+	0x00f890fc,
+/* 0x028c: send_proc */
+	0x90f980f9,
+	0x9805e898,
+	0x86f004e9,
+	0x0689b804,
+	0xc42a0bf4,
+	0x88940398,
+	0x1880b604,
+	0x98008ebb,
+	0x8a8000fa,
+	0x018d8000,
+	0x80028c80,
+	0x90b6038b,
+	0x0794f001,
+	0xf404e980,
+/* 0x02c6: send_done */
+	0x90fc0231,
+	0x00f880fc,
+/* 0x02cc: find */
+	0x87f080f9,
+	0x0131f458,
+/* 0x02d4: find_loop */
+	0xb8008a98,
+	0x0bf406ae,
+	0x5880b610,
+	0x026886b1,
+	0xf4f01bf4,
+/* 0x02ea: find_done */
+	0x8eb90132,
+	0xf880fc02,
+/* 0x02f1: send */
+	0xcc21f500,
+	0x9701f402,
+/* 0x02fa: recv */
+	0x90f900f8,
+	0xe89880f9,
 	0x04e99805,
-	0xb80486f0,
+	0xb80132f4,
 	0x0bf40689,
-	0x0398c42a,
-	0xb6048894,
-	0x8ebb1880,
-	0x00fa9800,
-	0x80008a80,
-	0x8c80018d,
-	0x038b8002,
-	0xf00190b6,
-	0xe9800794,
-	0x0231f404,
-/* 0x0240: send_done */
-	0x80fc90fc,
-/* 0x0246: find */
-	0x80f900f8,
-	0xf45887f0,
-/* 0x024e: find_loop */
-	0x8a980131,
-	0x06aeb800,
-	0xb6100bf4,
-	0x86b15880,
-	0x1bf40268,
-	0x0132f4f0,
-/* 0x0264: find_done */
-	0xfc028eb9,
-/* 0x026b: send */
-	0xf500f880,
-	0xf4024621,
-	0x00f89701,
-/* 0x0274: recv */
-	0x9805e898,
-	0x32f404e9,
-	0x0689b801,
-	0xc43d0bf4,
-	0x80b60389,
-	0x0784f001,
-	0x9805e880,
-	0xf0f902ea,
-	0xf9018ffe,
-	0x02efb9f0,
-	0xbb049994,
-	0xe0b600e9,
-	0x03eb9818,
-	0x9802ec98,
-	0xee9801ed,
-	0xfca5f900,
-	0x00f8fef0,
-	0xfc0131f4,
-/* 0x02bd: recv_done */
-/* 0x02bf: init */
-	0xf100f8f0,
-	0xcf010817,
-	0x11e70011,
-	0x14b60109,
-	0x0014fe08,
-	0x00e017f1,
-	0xf00013f0,
-	0x01d01c07,
-	0xf004bd00,
-	0x07f0ff17,
-	0x0001d014,
-	0x17f004bd,
-	0x0015f102,
-	0x1007f008,
-	0xbd0001d0,
-	0xe617f104,
-	0x0013f000,
-	0xf40010fe,
-	0x17f01031,
-	0x3807f001,
-	0xbd0001d0,
-	0x58f7f004,
-/* 0x0314: init_proc */
-	0xb001f198,
-	0x0bf40016,
-	0xb615f9fa,
-	0x0ef458f0,
-/* 0x0325: host_send */
-	0xb017f1f2,
-	0x0011cf04,
-	0x04a027f1,
-	0xb80022cf,
-	0x0bf40612,
-	0x071ec42f,
-	0xb704ee94,
-	0x980270e0,
+	0x0389c43d,
+	0xf00180b6,
+	0xe8800784,
+	0x02ea9805,
+	0x8ffef0f9,
+	0xb9f0f901,
+	0x999402ef,
+	0x00e9bb04,
+	0x9818e0b6,
 	0xec9803eb,
 	0x01ed9802,
-	0xf500ee98,
-	0xb6026b21,
-	0x1ec40110,
-	0xb007f10f,
-	0x000ed004,
-	0x0ef404bd,
-/* 0x0365: host_send_done */
-/* 0x0367: host_recv */
-	0xf100f8c3,
-	0xf14e4917,
-	0xb8525413,
-	0x0bf406e1,
-/* 0x0375: host_recv_wait */
-	0xcc17f1b3,
-	0x0011cf04,
-	0x04c827f1,
-	0xf00022cf,
-	0x12b80816,
-	0xec0bf406,
-	0xb60723c4,
-	0x30b70434,
-	0x3b8002f0,
-	0x023c8003,
-	0x80013d80,
-	0x20b6003e,
-	0x0f24f001,
-	0x04c807f1,
-	0xbd0002d0,
-	0x4027f004,
-	0xd00007f0,
-	0x04bd0002,
-/* 0x03be: host_init */
+	0xf900ee98,
+	0xfef0fca5,
+	0x31f400f8,
+/* 0x0347: recv_done */
+	0xfcf0fc01,
+	0xf890fc80,
+/* 0x034d: init */
+	0x0817f100,
+	0x0011cf01,
+	0x010911e7,
+	0xfe0814b6,
+	0x17f10014,
+	0x13f000e0,
+	0x1c07f000,
+	0xbd0001d0,
+	0xff17f004,
+	0xd01407f0,
+	0x04bd0001,
+	0xf10217f0,
+	0xf0080015,
+	0x01d01007,
+	0xf104bd00,
+	0xf000f617,
+	0x10fe0013,
+	0x1031f400,
+	0xf00117f0,
+	0x01d03807,
+	0xf004bd00,
+/* 0x03a2: init_proc */
+	0xf19858f7,
+	0x0016b001,
+	0xf9fa0bf4,
+	0x58f0b615,
+/* 0x03b3: mulu32_32_64 */
+	0xf9f20ef4,
+	0xf920f910,
+	0x9540f930,
+	0xd29510e1,
+	0xbdc4bd10,
+	0xc0edffb4,
+	0xb9301dff,
+	0x34f10234,
+	0x34b6ffff,
+	0x1045b610,
+	0xbb00c3bb,
+	0xe2ff01b4,
+	0x0234b930,
+	0xffff34f1,
+	0xb61034b6,
+	0xc3bb1045,
+	0x01b4bb00,
+	0xbb3012ff,
+	0x40fc00b3,
+	0x20fc30fc,
+	0x00f810fc,
+/* 0x0404: host_send */
+	0x04b017f1,
+	0xf10011cf,
+	0xcf04a027,
+	0x12b80022,
+	0x2f0bf406,
+	0x94071ec4,
+	0xe0b704ee,
+	0xeb980270,
+	0x02ec9803,
+	0x9801ed98,
+	0x21f500ee,
+	0x10b602f1,
+	0x0f1ec401,
+	0x04b007f1,
+	0xbd000ed0,
+	0xc30ef404,
+/* 0x0444: host_send_done */
+/* 0x0446: host_recv */
 	0x17f100f8,
-	0x14b60080,
-	0x7015f110,
-	0xd007f102,
-	0x0001d004,
-	0x17f104bd,
-	0x14b60080,
-	0xf015f110,
-	0xdc07f102,
-	0x0001d004,
-	0x17f004bd,
-	0xc407f101,
-	0x0001d004,
-	0x00f804bd,
-/* 0x03f4: memx_func_enter */
+	0x13f14e49,
+	0xe1b85254,
+	0xb30bf406,
+/* 0x0454: host_recv_wait */
+	0x04cc17f1,
+	0xf10011cf,
+	0xcf04c827,
+	0x16f00022,
+	0x0612b808,
+	0xc4ec0bf4,
+	0x34b60723,
+	0xf030b704,
+	0x033b8002,
+	0x80023c80,
+	0x3e80013d,
+	0x0120b600,
+	0xf10f24f0,
+	0xd004c807,
+	0x04bd0002,
+	0xf04027f0,
+	0x02d00007,
+	0xf804bd00,
+/* 0x049d: host_init */
+	0x8017f100,
+	0x1014b600,
+	0x027015f1,
+	0x04d007f1,
+	0xbd0001d0,
+	0x8017f104,
+	0x1014b600,
+	0x02f015f1,
+	0x04dc07f1,
+	0xbd0001d0,
+	0x0117f004,
+	0x04c407f1,
+	0xbd0001d0,
+/* 0x04d3: memx_func_enter */
+	0xf100f804,
+	0xf1162067,
+	0xf1f55d77,
+	0xb9ffff73,
+	0x21f4026e,
+	0x02d8b904,
+	0xf90487fd,
+	0xfc80f960,
+	0xf4e0fcd0,
+	0x77f13321,
+	0x73f1fffe,
+	0x6eb9ffff,
+	0x0421f402,
+	0xfd02d8b9,
+	0x60f90487,
+	0xd0fc80f9,
+	0x21f4e0fc,
+	0xf067f133,
+	0x026eb926,
+	0xb90421f4,
+	0x87fd02d8,
+	0xf960f904,
+	0xfcd0fc80,
+	0x3321f4e0,
 	0xf10467f0,
 	0xd007e007,
 	0x04bd0006,
-/* 0x0400: memx_func_enter_wait */
+/* 0x053c: memx_func_enter_wait */
 	0x07c067f1,
 	0xf00066cf,
 	0x0bf40464,
-	0x001698f6,
-	0xf80410b6,
-/* 0x0415: memx_func_leave */
-	0x0467f000,
+	0x2c67f0f6,
+	0x800066cf,
+	0x00f8ee06,
+/* 0x0554: memx_func_leave */
+	0xcf2c67f0,
+	0x06800066,
+	0x0467f0ef,
 	0x07e407f1,
 	0xbd0006d0,
-/* 0x0421: memx_func_leave_wait */
+/* 0x0569: memx_func_leave_wait */
 	0xc067f104,
 	0x0066cf07,
 	0xf40464f0,
-	0x00f8f61b,
-/* 0x0430: memx_func_wr32 */
+	0x67f1f61b,
+	0x77f126f0,
+	0x73f00001,
+	0x026eb900,
+	0xb90421f4,
+	0x87fd02d8,
+	0xf960f905,
+	0xfcd0fc80,
+	0x3321f4e0,
+	0x162067f1,
+	0xf4026eb9,
+	0xd8b90421,
+	0x0587fd02,
+	0x80f960f9,
+	0xe0fcd0fc,
+	0xf13321f4,
+	0xf00aa277,
+	0x6eb90073,
+	0x0421f402,
+	0xfd02d8b9,
+	0x60f90587,
+	0xd0fc80f9,
+	0x21f4e0fc,
+/* 0x05d3: memx_func_wait_vblank */
+	0xb600f833,
+	0x00f80410,
+/* 0x05d8: memx_func_wr32 */
 	0x98001698,
 	0x10b60115,
 	0xf960f908,
@@ -1102,131 +1281,137 @@ uint32_t nvd0_pwr_code[] = {
 	0x3321f4e0,
 	0xf40242b6,
 	0x00f8e91b,
-/* 0x044c: memx_func_wait */
+/* 0x05f4: memx_func_wait */
 	0xcf2c87f0,
 	0x1e980088,
 	0x011d9800,
 	0x98021c98,
 	0x10b6031b,
-	0x7e21f410,
-/* 0x0466: memx_func_delay */
+	0x8621f410,
+/* 0x060e: memx_func_delay */
 	0x1e9800f8,
 	0x0410b600,
 	0xf86721f4,
-/* 0x0471: memx_exec */
+/* 0x0619: memx_exec */
 	0xf9e0f900,
 	0x02c1b9d0,
-/* 0x047b: memx_exec_next */
+/* 0x0623: memx_exec_next */
 	0x9802b2b9,
 	0x10b60013,
-	0x10349504,
+	0xf034e704,
+	0xe033e701,
+	0x0132b601,
 	0x980c30f0,
 	0x55f9de35,
 	0xf40612b8,
-	0xd0fcec1e,
+	0x0b98e41e,
+	0xef0c98ee,
+	0xf102cbbb,
+	0xcf07c4b7,
+	0xd0fc00bb,
 	0x21f5e0fc,
-	0x00f8026b,
-/* 0x049c: memx_info */
-	0x03acc7f1,
+	0x00f802f1,
+/* 0x065c: memx_info */
+	0x03c0c7f1,
 	0x0800b7f1,
-	0x026b21f5,
-/* 0x04aa: memx_recv */
+	0x02f121f5,
+/* 0x066a: memx_recv */
 	0xd6b000f8,
-	0xc40bf401,
+	0xac0bf401,
 	0xf400d6b0,
 	0x00f8e90b,
-/* 0x04b8: memx_init */
-/* 0x04ba: perf_recv */
+/* 0x0678: memx_init */
+/* 0x067a: perf_recv */
 	0x00f800f8,
-/* 0x04bc: perf_init */
-/* 0x04be: i2c_drive_scl */
+/* 0x067c: perf_init */
+/* 0x067e: i2c_drive_scl */
 	0x36b000f8,
 	0x0e0bf400,
 	0x07e007f1,
 	0xbd0001d0,
-/* 0x04cf: i2c_drive_scl_lo */
+/* 0x068f: i2c_drive_scl_lo */
 	0xf100f804,
 	0xd007e407,
 	0x04bd0001,
-/* 0x04da: i2c_drive_sda */
+/* 0x069a: i2c_drive_sda */
 	0x36b000f8,
 	0x0e0bf400,
 	0x07e007f1,
 	0xbd0002d0,
-/* 0x04eb: i2c_drive_sda_lo */
+/* 0x06ab: i2c_drive_sda_lo */
 	0xf100f804,
 	0xd007e407,
 	0x04bd0002,
-/* 0x04f6: i2c_sense_scl */
+/* 0x06b6: i2c_sense_scl */
 	0x32f400f8,
 	0xc437f101,
 	0x0033cf07,
 	0xf40431fd,
 	0x31f4060b,
-/* 0x0509: i2c_sense_scl_done */
-/* 0x050b: i2c_sense_sda */
+/* 0x06c9: i2c_sense_scl_done */
+/* 0x06cb: i2c_sense_sda */
 	0xf400f801,
 	0x37f10132,
 	0x33cf07c4,
 	0x0432fd00,
 	0xf4060bf4,
-/* 0x051e: i2c_sense_sda_done */
+/* 0x06de: i2c_sense_sda_done */
 	0x00f80131,
-/* 0x0520: i2c_raise_scl */
+/* 0x06e0: i2c_raise_scl */
 	0x47f140f9,
 	0x37f00898,
-	0xbe21f501,
-/* 0x052d: i2c_raise_scl_wait */
-	0xe8e7f104,
+	0x7e21f501,
+/* 0x06ed: i2c_raise_scl_wait */
+	0xe8e7f106,
 	0x6721f403,
-	0x04f621f5,
+	0x06b621f5,
 	0xb60901f4,
 	0x1bf40142,
-/* 0x0541: i2c_raise_scl_done */
+/* 0x0701: i2c_raise_scl_done */
 	0xf840fcef,
-/* 0x0545: i2c_start */
-	0xf621f500,
-	0x0d11f404,
-	0x050b21f5,
+/* 0x0705: i2c_start */
+	0xb621f500,
+	0x0d11f406,
+	0x06cb21f5,
 	0xf40611f4,
-/* 0x0556: i2c_start_rep */
+/* 0x0716: i2c_start_rep */
 	0x37f0300e,
-	0xbe21f500,
-	0x0137f004,
-	0x04da21f5,
+	0x7e21f500,
+	0x0137f006,
+	0x069a21f5,
 	0xb60076bb,
 	0x50f90465,
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0x2021f550,
-	0x0464b605,
-/* 0x0583: i2c_start_send */
+	0xe021f550,
+	0x0464b606,
+/* 0x0743: i2c_start_send */
 	0xf01f11f4,
 	0x21f50037,
-	0xe7f104da,
+	0xe7f1069a,
 	0x21f41388,
 	0x0037f067,
-	0x04be21f5,
+	0x067e21f5,
 	0x1388e7f1,
-/* 0x059f: i2c_start_out */
+/* 0x075f: i2c_start_out */
 	0xf86721f4,
-/* 0x05a1: i2c_stop */
+/* 0x0761: i2c_stop */
 	0x0037f000,
-	0x04be21f5,
+	0x067e21f5,
 	0xf50037f0,
-	0xf104da21,
+	0xf1069a21,
 	0xf403e8e7,
 	0x37f06721,
-	0xbe21f501,
-	0x88e7f104,
+	0x7e21f501,
+	0x88e7f106,
 	0x6721f413,
 	0xf50137f0,
-	0xf104da21,
+	0xf1069a21,
 	0xf41388e7,
 	0x00f86721,
-/* 0x05d4: i2c_bitw */
-	0x04da21f5,
+/* 0x0794: i2c_bitw */
+	0x069a21f5,
 	0x03e8e7f1,
 	0xbb6721f4,
 	0x65b60076,
@@ -1234,18 +1419,18 @@ uint32_t nvd0_pwr_code[] = {
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x052021f5,
+	0x06e021f5,
 	0xf40464b6,
 	0xe7f11811,
 	0x21f41388,
 	0x0037f067,
-	0x04be21f5,
+	0x067e21f5,
 	0x1388e7f1,
-/* 0x0613: i2c_bitw_out */
+/* 0x07d3: i2c_bitw_out */
 	0xf86721f4,
-/* 0x0615: i2c_bitr */
+/* 0x07d5: i2c_bitr */
 	0x0137f000,
-	0x04da21f5,
+	0x069a21f5,
 	0x03e8e7f1,
 	0xbb6721f4,
 	0x65b60076,
@@ -1253,19 +1438,19 @@ uint32_t nvd0_pwr_code[] = {
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x052021f5,
+	0x06e021f5,
 	0xf40464b6,
 	0x21f51b11,
-	0x37f0050b,
-	0xbe21f500,
-	0x88e7f104,
+	0x37f006cb,
+	0x7e21f500,
+	0x88e7f106,
 	0x6721f413,
 	0xf4013cf0,
-/* 0x065a: i2c_bitr_done */
+/* 0x081a: i2c_bitr_done */
 	0x00f80131,
-/* 0x065c: i2c_get_byte */
+/* 0x081c: i2c_get_byte */
 	0xf00057f0,
-/* 0x0662: i2c_get_byte_next */
+/* 0x0822: i2c_get_byte_next */
 	0x54b60847,
 	0x0076bb01,
 	0xf90465b6,
@@ -1273,7 +1458,7 @@ uint32_t nvd0_pwr_code[] = {
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b60615,
+	0x64b607d5,
 	0x2b11f404,
 	0xb60553fd,
 	0x1bf40142,
@@ -1283,12 +1468,12 @@ uint32_t nvd0_pwr_code[] = {
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0xd421f550,
-	0x0464b605,
-/* 0x06ac: i2c_get_byte_done */
-/* 0x06ae: i2c_put_byte */
+	0x9421f550,
+	0x0464b607,
+/* 0x086c: i2c_get_byte_done */
+/* 0x086e: i2c_put_byte */
 	0x47f000f8,
-/* 0x06b1: i2c_put_byte_next */
+/* 0x0871: i2c_put_byte_next */
 	0x0142b608,
 	0xbb3854ff,
 	0x65b60076,
@@ -1296,7 +1481,7 @@ uint32_t nvd0_pwr_code[] = {
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x05d421f5,
+	0x079421f5,
 	0xf40464b6,
 	0x46b03411,
 	0xd81bf400,
@@ -1305,21 +1490,21 @@ uint32_t nvd0_pwr_code[] = {
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0x1521f550,
-	0x0464b606,
+	0xd521f550,
+	0x0464b607,
 	0xbb0f11f4,
 	0x36b00076,
 	0x061bf401,
-/* 0x0707: i2c_put_byte_done */
+/* 0x08c7: i2c_put_byte_done */
 	0xf80132f4,
-/* 0x0709: i2c_addr */
+/* 0x08c9: i2c_addr */
 	0x0076bb00,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b60545,
+	0x64b60705,
 	0x2911f404,
 	0x012ec3e7,
 	0xfd0134b6,
@@ -1329,30 +1514,30 @@ uint32_t nvd0_pwr_code[] = {
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb606ae21,
-/* 0x074e: i2c_addr_done */
+	0xb6086e21,
+/* 0x090e: i2c_addr_done */
 	0x00f80464,
-/* 0x0750: i2c_acquire_addr */
+/* 0x0910: i2c_acquire_addr */
 	0xb6f8cec7,
 	0xe0b705e4,
 	0x00f8d014,
-/* 0x075c: i2c_acquire */
-	0x075021f5,
+/* 0x091c: i2c_acquire */
+	0x091021f5,
 	0xf00421f4,
 	0x21f403d9,
-/* 0x076b: i2c_release */
+/* 0x092b: i2c_release */
 	0xf500f833,
-	0xf4075021,
+	0xf4091021,
 	0xdaf00421,
 	0x3321f403,
-/* 0x077a: i2c_recv */
+/* 0x093a: i2c_recv */
 	0x32f400f8,
 	0xf8c1c701,
 	0xb00214b6,
 	0x1ff52816,
 	0x13a0013a,
-	0x32980bd4,
-	0xac13a000,
+	0x32980be8,
+	0xc013a000,
 	0x0031980b,
 	0xf90231f4,
 	0xf9e0f9d0,
@@ -1364,8 +1549,8 @@ uint32_t nvd0_pwr_code[] = {
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0x5c21f550,
-	0x0464b607,
+	0x1c21f550,
+	0x0464b609,
 	0xd6b0d0fc,
 	0xb31bf500,
 	0x0057f000,
@@ -1374,8 +1559,8 @@ uint32_t nvd0_pwr_code[] = {
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0x0921f550,
-	0x0464b607,
+	0xc921f550,
+	0x0464b608,
 	0x00d011f5,
 	0xbbe0c5c7,
 	0x65b60076,
@@ -1383,7 +1568,7 @@ uint32_t nvd0_pwr_code[] = {
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x06ae21f5,
+	0x086e21f5,
 	0xf50464b6,
 	0xf000ad11,
 	0x76bb0157,
@@ -1392,7 +1577,7 @@ uint32_t nvd0_pwr_code[] = {
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb6070921,
+	0xb608c921,
 	0x11f50464,
 	0x76bb008a,
 	0x0465b600,
@@ -1400,7 +1585,7 @@ uint32_t nvd0_pwr_code[] = {
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb6065c21,
+	0xb6081c21,
 	0x11f40464,
 	0xe05bcb6a,
 	0xb60076bb,
@@ -1408,38 +1593,38 @@ uint32_t nvd0_pwr_code[] = {
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0xa121f550,
-	0x0464b605,
+	0x6121f550,
+	0x0464b607,
 	0xbd025bb9,
 	0x430ef474,
-/* 0x0880: i2c_recv_not_rd08 */
+/* 0x0a40: i2c_recv_not_rd08 */
 	0xf401d6b0,
 	0x57f03d1b,
-	0x0921f500,
-	0x3311f407,
+	0xc921f500,
+	0x3311f408,
 	0xf5e0c5c7,
-	0xf406ae21,
+	0xf4086e21,
 	0x57f02911,
-	0x0921f500,
-	0x1f11f407,
+	0xc921f500,
+	0x1f11f408,
 	0xf5e0b5c7,
-	0xf406ae21,
+	0xf4086e21,
 	0x21f51511,
-	0x74bd05a1,
+	0x74bd0761,
 	0xf408c5c7,
 	0x32f4091b,
 	0x030ef402,
-/* 0x08c0: i2c_recv_not_wr08 */
-/* 0x08c0: i2c_recv_done */
+/* 0x0a80: i2c_recv_not_wr08 */
+/* 0x0a80: i2c_recv_done */
 	0xf5f8cec7,
-	0xfc076b21,
+	0xfc092b21,
 	0xf4d0fce0,
 	0x7cb90a12,
-	0x6b21f502,
-/* 0x08d5: i2c_recv_exit */
-/* 0x08d7: i2c_init */
+	0xf121f502,
+/* 0x0a95: i2c_recv_exit */
+/* 0x0a97: i2c_init */
 	0xf800f802,
-/* 0x08d9: test_recv */
+/* 0x0a99: test_recv */
 	0xd817f100,
 	0x0011cf05,
 	0xf10110b6,
@@ -1447,29 +1632,29 @@ uint32_t nvd0_pwr_code[] = {
 	0x04bd0001,
 	0xd900e7f1,
 	0x134fe3f1,
-	0x01b621f5,
-/* 0x08fa: test_init */
+	0x022321f5,
+/* 0x0aba: test_init */
 	0xe7f100f8,
 	0x21f50800,
-	0x00f801b6,
-/* 0x0904: idle_recv */
-/* 0x0906: idle */
+	0x00f80223,
+/* 0x0ac4: idle_recv */
+/* 0x0ac6: idle */
 	0x31f400f8,
 	0xd417f100,
 	0x0011cf05,
 	0xf10110b6,
 	0xd005d407,
 	0x04bd0001,
-/* 0x091c: idle_loop */
+/* 0x0adc: idle_loop */
 	0xf45817f0,
-/* 0x0922: idle_proc */
-/* 0x0922: idle_proc_exec */
+/* 0x0ae2: idle_proc */
+/* 0x0ae2: idle_proc_exec */
 	0x10f90232,
 	0xf5021eb9,
-	0xfc027421,
+	0xfc02fa21,
 	0x0911f410,
 	0xf40231f4,
-/* 0x0936: idle_proc_next */
+/* 0x0af6: idle_proc_next */
 	0x10b6ef0e,
 	0x061fb858,
 	0xf4e61bf4,
@@ -1521,4 +1706,20 @@ uint32_t nvd0_pwr_code[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 };
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/os.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/os.h
index 574acfa44c8c..522e3079f824 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/os.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/os.h
@@ -19,11 +19,12 @@
 #define MEMX_MSG_EXEC 1
 
 /* MEMX: script opcode definitions */
-#define MEMX_ENTER  0
-#define MEMX_LEAVE  1
-#define MEMX_WR32   2
-#define MEMX_WAIT   3
-#define MEMX_DELAY  4
+#define MEMX_ENTER  1
+#define MEMX_LEAVE  2
+#define MEMX_WR32   3
+#define MEMX_WAIT   4
+#define MEMX_DELAY  5
+#define MEMX_VBLANK 6
 
 /* I2C_: message identifiers */
 #define I2C__MSG_RD08 0
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/memx.c b/drivers/gpu/drm/nouveau/core/subdev/pwr/memx.c
index def6a9ac68cf..65eaa2546cad 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/memx.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/memx.c
@@ -20,10 +20,11 @@ memx_out(struct nouveau_memx *memx)
 	struct nouveau_pwr *ppwr = memx->ppwr;
 	int i;
 
-	if (memx->c.size) {
+	if (memx->c.mthd) {
 		nv_wr32(ppwr, 0x10a1c4, (memx->c.size << 16) | memx->c.mthd);
 		for (i = 0; i < memx->c.size; i++)
 			nv_wr32(ppwr, 0x10a1c4, memx->c.data[i]);
+		memx->c.mthd = 0;
 		memx->c.size = 0;
 	}
 }
@@ -32,7 +33,7 @@ static void
 memx_cmd(struct nouveau_memx *memx, u32 mthd, u32 size, u32 data[])
 {
 	if ((memx->c.size + size >= ARRAY_SIZE(memx->c.data)) ||
-	    (memx->c.size && memx->c.mthd != mthd))
+	    (memx->c.mthd && memx->c.mthd != mthd))
 		memx_out(memx);
 	memcpy(&memx->c.data[memx->c.size], data, size * sizeof(data[0]));
 	memx->c.size += size;
@@ -62,8 +63,7 @@ nouveau_memx_init(struct nouveau_pwr *ppwr, struct nouveau_memx **pmemx)
 		nv_wr32(ppwr, 0x10a580, 0x00000003);
 	} while (nv_rd32(ppwr, 0x10a580) != 0x00000003);
 	nv_wr32(ppwr, 0x10a1c0, 0x01000000 | memx->base);
-	nv_wr32(ppwr, 0x10a1c4, 0x00010000 | MEMX_ENTER);
-	nv_wr32(ppwr, 0x10a1c4, 0x00000000);
+
 	return 0;
 }
 
@@ -78,7 +78,6 @@ nouveau_memx_fini(struct nouveau_memx **pmemx, bool exec)
 	memx_out(memx);
 
 	/* release data segment access */
-	nv_wr32(ppwr, 0x10a1c4, 0x00000000 | MEMX_LEAVE);
 	finish = nv_rd32(ppwr, 0x10a1c0) & 0x00ffffff;
 	nv_wr32(ppwr, 0x10a580, 0x00000000);
 
@@ -88,6 +87,8 @@ nouveau_memx_fini(struct nouveau_memx **pmemx, bool exec)
 				 memx->base, finish);
 	}
 
+	nv_debug(memx->ppwr, "Exec took %uns, PPWR_IN %08x\n",
+		 reply[0], reply[1]);
 	kfree(memx);
 	return 0;
 }
@@ -117,4 +118,51 @@ nouveau_memx_nsec(struct nouveau_memx *memx, u32 nsec)
 	memx_out(memx); /* fuc can't handle multiple */
 }
 
+void
+nouveau_memx_wait_vblank(struct nouveau_memx *memx)
+{
+	struct nouveau_pwr *ppwr = memx->ppwr;
+	u32 heads, x, y, px = 0;
+	int i, head_sync;
+
+	if (nv_device(ppwr)->chipset < 0xd0) {
+		heads = nv_rd32(ppwr, 0x610050);
+		for (i = 0; i < 2; i++) {
+			/* Heuristic: sync to head with biggest resolution */
+			if (heads & (2 << (i << 3))) {
+				x = nv_rd32(ppwr, 0x610b40 + (0x540 * i));
+				y = (x & 0xffff0000) >> 16;
+				x &= 0x0000ffff;
+				if ((x * y) > px) {
+					px = (x * y);
+					head_sync = i;
+				}
+			}
+		}
+	}
+
+	if (px == 0) {
+		nv_debug(memx->ppwr, "WAIT VBLANK !NO ACTIVE HEAD\n");
+		return;
+	}
+
+	nv_debug(memx->ppwr, "WAIT VBLANK HEAD%d\n", head_sync);
+	memx_cmd(memx, MEMX_VBLANK, 1, (u32[]){ head_sync });
+	memx_out(memx); /* fuc can't handle multiple */
+}
+
+void
+nouveau_memx_block(struct nouveau_memx *memx)
+{
+	nv_debug(memx->ppwr, "   HOST BLOCKED\n");
+	memx_cmd(memx, MEMX_ENTER, 0, NULL);
+}
+
+void
+nouveau_memx_unblock(struct nouveau_memx *memx)
+{
+	nv_debug(memx->ppwr, "   HOST UNBLOCKED\n");
+	memx_cmd(memx, MEMX_LEAVE, 0, NULL);
+}
+
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
index 016990a8252c..3656d605168f 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
@@ -31,6 +31,8 @@
 #include <subdev/gpio.h>
 #include <subdev/timer.h>
 
+#include <subdev/bios/fan.h>
+
 static int
 nouveau_fan_update(struct nouveau_fan *fan, bool immediate, int target)
 {
@@ -275,8 +277,11 @@ nouveau_therm_fan_ctor(struct nouveau_therm *therm)
 	/* other random init... */
 	nouveau_therm_fan_set_defaults(therm);
 	nvbios_perf_fan_parse(bios, &priv->fan->perf);
-	if (nvbios_therm_fan_parse(bios, &priv->fan->bios))
-		nv_error(therm, "parsing the thermal table failed\n");
+	if (!nvbios_fan_parse(bios, &priv->fan->bios)) {
+		nv_debug(therm, "parsing the fan table failed\n");
+		if (nvbios_therm_fan_parse(bios, &priv->fan->bios))
+			nv_error(therm, "parsing both fan tables failed\n");
+	}
 	nouveau_therm_fan_safety_checks(therm);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/fanpwm.c b/drivers/gpu/drm/nouveau/core/subdev/therm/fanpwm.c
index 9a5c07340263..c629d7f2a6a4 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/fanpwm.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/fanpwm.c
@@ -25,6 +25,8 @@
 
 #include <core/option.h>
 #include <subdev/gpio.h>
+#include <subdev/bios.h>
+#include <subdev/bios/fan.h>
 
 #include "priv.h"
 
@@ -86,11 +88,15 @@ nouveau_fanpwm_create(struct nouveau_therm *therm, struct dcb_gpio_func *func)
 {
 	struct nouveau_device *device = nv_device(therm);
 	struct nouveau_therm_priv *tpriv = (void *)therm;
+	struct nouveau_bios *bios = nouveau_bios(therm);
 	struct nouveau_fanpwm_priv *priv;
+	struct nvbios_therm_fan fan;
 	u32 divs, duty;
 
+	nvbios_fan_parse(bios, &fan);
+
 	if (!nouveau_boolopt(device->cfgopt, "NvFanPWM", func->param) ||
-	    !therm->pwm_ctrl ||
+	    !therm->pwm_ctrl || fan.type == NVBIOS_THERM_FAN_TOGGLE ||
 	     therm->pwm_get(therm, func->line, &divs, &duty) == -ENODEV)
 		return -ENODEV;
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/gm107.c b/drivers/gpu/drm/nouveau/core/subdev/therm/gm107.c
new file mode 100644
index 000000000000..668cf3322285
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/gm107.c
@@ -0,0 +1,93 @@
+/*
+ * Copyright 2014 Martin Peres
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Martin Peres
+ */
+
+#include "priv.h"
+
+struct gm107_therm_priv {
+	struct nouveau_therm_priv base;
+};
+
+static int
+gm107_fan_pwm_ctrl(struct nouveau_therm *therm, int line, bool enable)
+{
+	/* nothing to do, it seems hardwired */
+	return 0;
+}
+
+static int
+gm107_fan_pwm_get(struct nouveau_therm *therm, int line, u32 *divs, u32 *duty)
+{
+	*divs = nv_rd32(therm, 0x10eb20) & 0x1fff;
+	*duty = nv_rd32(therm, 0x10eb24) & 0x1fff;
+	return 0;
+}
+
+static int
+gm107_fan_pwm_set(struct nouveau_therm *therm, int line, u32 divs, u32 duty)
+{
+	nv_mask(therm, 0x10eb10, 0x1fff, divs); /* keep the high bits */
+	nv_wr32(therm, 0x10eb14, duty | 0x80000000);
+	return 0;
+}
+
+static int
+gm107_fan_pwm_clock(struct nouveau_therm *therm, int line)
+{
+	return nv_device(therm)->crystal * 1000;
+}
+
+static int
+gm107_therm_ctor(struct nouveau_object *parent,
+		struct nouveau_object *engine,
+		struct nouveau_oclass *oclass, void *data, u32 size,
+		struct nouveau_object **pobject)
+{
+	struct gm107_therm_priv *priv;
+	int ret;
+
+	ret = nouveau_therm_create(parent, engine, oclass, &priv);
+	*pobject = nv_object(priv);
+	if (ret)
+		return ret;
+
+	priv->base.base.pwm_ctrl = gm107_fan_pwm_ctrl;
+	priv->base.base.pwm_get = gm107_fan_pwm_get;
+	priv->base.base.pwm_set = gm107_fan_pwm_set;
+	priv->base.base.pwm_clock = gm107_fan_pwm_clock;
+	priv->base.base.temp_get = nv84_temp_get;
+	priv->base.base.fan_sense = nva3_therm_fan_sense;
+	priv->base.sensor.program_alarms = nouveau_therm_program_alarms_polling;
+	return nouveau_therm_preinit(&priv->base.base);
+}
+
+struct nouveau_oclass
+gm107_therm_oclass = {
+	.handle = NV_SUBDEV(THERM, 0x117),
+	.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = gm107_therm_ctor,
+		.dtor = _nouveau_therm_dtor,
+		.init = nvd0_therm_init,
+		.fini = nv84_therm_fini,
+	},
+};
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/nv84.c b/drivers/gpu/drm/nouveau/core/subdev/therm/nv84.c
index 1d15c52fad0c..14e2e09bfc24 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/nv84.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/nv84.c
@@ -24,6 +24,7 @@
  */
 
 #include "priv.h"
+#include <subdev/fuse.h>
 
 struct nv84_therm_priv {
 	struct nouveau_therm_priv base;
@@ -32,7 +33,25 @@ struct nv84_therm_priv {
 int
 nv84_temp_get(struct nouveau_therm *therm)
 {
-	return nv_rd32(therm, 0x20400);
+	struct nouveau_fuse *fuse = nouveau_fuse(therm);
+
+	if (nv_ro32(fuse, 0x1a8) == 1)
+		return nv_rd32(therm, 0x20400);
+	else
+		return -ENODEV;
+}
+
+void
+nv84_sensor_setup(struct nouveau_therm *therm)
+{
+	struct nouveau_fuse *fuse = nouveau_fuse(therm);
+
+	/* enable temperature reading for cards with insane defaults */
+	if (nv_ro32(fuse, 0x1a8) == 1) {
+		nv_mask(therm, 0x20008, 0x80008000, 0x80000000);
+		nv_mask(therm, 0x2000c, 0x80000003, 0x00000000);
+		mdelay(20); /* wait for the temperature to stabilize */
+	}
 }
 
 static void
@@ -171,6 +190,21 @@ nv84_therm_intr(struct nouveau_subdev *subdev)
 }
 
 static int
+nv84_therm_init(struct nouveau_object *object)
+{
+	struct nv84_therm_priv *priv = (void *)object;
+	int ret;
+
+	ret = nouveau_therm_init(&priv->base.base);
+	if (ret)
+		return ret;
+
+	nv84_sensor_setup(&priv->base.base);
+
+	return 0;
+}
+
+static int
 nv84_therm_ctor(struct nouveau_object *parent,
 		struct nouveau_object *engine,
 		struct nouveau_oclass *oclass, void *data, u32 size,
@@ -228,7 +262,7 @@ nv84_therm_oclass = {
 	.ofuncs = &(struct nouveau_ofuncs) {
 		.ctor = nv84_therm_ctor,
 		.dtor = _nouveau_therm_dtor,
-		.init = _nouveau_therm_init,
+		.init = nv84_therm_init,
 		.fini = nv84_therm_fini,
 	},
 };
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/nva3.c b/drivers/gpu/drm/nouveau/core/subdev/therm/nva3.c
index 0478b2e3fb1d..7893357a7e9f 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/nva3.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/nva3.c
@@ -51,6 +51,8 @@ nva3_therm_init(struct nouveau_object *object)
 	if (ret)
 		return ret;
 
+	nv84_sensor_setup(&priv->base.base);
+
 	/* enable fan tach, count revolutions per-second */
 	nv_mask(priv, 0x00e720, 0x00000003, 0x00000002);
 	if (tach->func != DCB_GPIO_UNUSED) {
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/nvd0.c b/drivers/gpu/drm/nouveau/core/subdev/therm/nvd0.c
index bbf117be572f..b70f7cc649b8 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/nvd0.c
@@ -114,7 +114,7 @@ nvd0_fan_pwm_clock(struct nouveau_therm *therm, int line)
 		return nv_device(therm)->crystal * 1000 / 10;
 }
 
-static int
+int
 nvd0_therm_init(struct nouveau_object *object)
 {
 	struct nvd0_therm_priv *priv = (void *)object;
@@ -150,6 +150,8 @@ nvd0_therm_ctor(struct nouveau_object *parent,
 	if (ret)
 		return ret;
 
+	nv84_sensor_setup(&priv->base.base);
+
 	priv->base.base.pwm_ctrl = nvd0_fan_pwm_ctrl;
 	priv->base.base.pwm_get = nvd0_fan_pwm_get;
 	priv->base.base.pwm_set = nvd0_fan_pwm_set;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/priv.h b/drivers/gpu/drm/nouveau/core/subdev/therm/priv.h
index 916fca5c7816..7dba8c281a0b 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/priv.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/priv.h
@@ -145,10 +145,13 @@ int nv50_fan_pwm_get(struct nouveau_therm *, int, u32 *, u32 *);
 int nv50_fan_pwm_set(struct nouveau_therm *, int, u32, u32);
 int nv50_fan_pwm_clock(struct nouveau_therm *, int);
 int nv84_temp_get(struct nouveau_therm *therm);
+void nv84_sensor_setup(struct nouveau_therm *therm);
 int nv84_therm_fini(struct nouveau_object *object, bool suspend);
 
 int nva3_therm_fan_sense(struct nouveau_therm *);
 
+int nvd0_therm_init(struct nouveau_object *object);
+
 int nouveau_fanpwm_create(struct nouveau_therm *, struct dcb_gpio_func *);
 int nouveau_fantog_create(struct nouveau_therm *, struct dcb_gpio_func *);
 int nouveau_fannil_create(struct nouveau_therm *);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/vm/base.c b/drivers/gpu/drm/nouveau/core/subdev/vm/base.c
index 7dd680ff2f6f..f75a683bd47a 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/vm/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/vm/base.c
@@ -296,7 +296,7 @@ nouveau_vm_get(struct nouveau_vm *vm, u64 size, u32 page_shift,
 	int ret;
 
 	mutex_lock(&nv_subdev(vmm)->mutex);
-	ret = nouveau_mm_head(&vm->mm, page_shift, msize, msize, align,
+	ret = nouveau_mm_head(&vm->mm, 0, page_shift, msize, msize, align,
 			     &vma->node);
 	if (unlikely(ret != 0)) {
 		mutex_unlock(&nv_subdev(vmm)->mutex);
diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
index b90aa5c1f90a..fca6a1f9c20c 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
@@ -1127,7 +1127,7 @@ nv04_crtc_create(struct drm_device *dev, int crtc_num)
 	drm_mode_crtc_set_gamma_size(&nv_crtc->base, 256);
 
 	ret = nouveau_bo_new(dev, 64*64*4, 0x100, TTM_PL_FLAG_VRAM,
-			     0, 0x0000, NULL, &nv_crtc->cursor.nvbo);
+			     0, 0x0000, NULL, NULL, &nv_crtc->cursor.nvbo);
 	if (!ret) {
 		ret = nouveau_bo_pin(nv_crtc->cursor.nvbo, TTM_PL_FLAG_VRAM);
 		if (!ret) {
diff --git a/drivers/gpu/drm/nouveau/dispnv04/overlay.c b/drivers/gpu/drm/nouveau/dispnv04/overlay.c
index b36afcbbc83f..1e9056a8df94 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/overlay.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/overlay.c
@@ -97,7 +97,8 @@ nv10_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		  uint32_t src_w, uint32_t src_h)
 {
 	struct nvif_device *dev = &nouveau_drm(plane->dev)->device;
-	struct nouveau_plane *nv_plane = (struct nouveau_plane *)plane;
+	struct nouveau_plane *nv_plane =
+		container_of(plane, struct nouveau_plane, base);
 	struct nouveau_framebuffer *nv_fb = nouveau_framebuffer(fb);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
 	struct nouveau_bo *cur = nv_plane->cur;
@@ -173,7 +174,8 @@ static int
 nv10_disable_plane(struct drm_plane *plane)
 {
 	struct nvif_device *dev = &nouveau_drm(plane->dev)->device;
-	struct nouveau_plane *nv_plane = (struct nouveau_plane *)plane;
+	struct nouveau_plane *nv_plane =
+		container_of(plane, struct nouveau_plane, base);
 
 	nvif_wr32(dev, NV_PVIDEO_STOP, 1);
 	if (nv_plane->cur) {
@@ -224,7 +226,8 @@ nv_set_property(struct drm_plane *plane,
 		struct drm_property *property,
 		uint64_t value)
 {
-	struct nouveau_plane *nv_plane = (struct nouveau_plane *)plane;
+	struct nouveau_plane *nv_plane =
+		container_of(plane, struct nouveau_plane, base);
 
 	if (property == nv_plane->props.colorkey)
 		nv_plane->colorkey = value;
@@ -344,7 +347,8 @@ nv04_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		  uint32_t src_w, uint32_t src_h)
 {
 	struct nvif_device *dev = &nouveau_drm(plane->dev)->device;
-	struct nouveau_plane *nv_plane = (struct nouveau_plane *)plane;
+	struct nouveau_plane *nv_plane =
+		container_of(plane, struct nouveau_plane, base);
 	struct nouveau_framebuffer *nv_fb = nouveau_framebuffer(fb);
 	struct nouveau_bo *cur = nv_plane->cur;
 	uint32_t overlay = 1;
@@ -423,7 +427,8 @@ static int
 nv04_disable_plane(struct drm_plane *plane)
 {
 	struct nvif_device *dev = &nouveau_drm(plane->dev)->device;
-	struct nouveau_plane *nv_plane = (struct nouveau_plane *)plane;
+	struct nouveau_plane *nv_plane =
+		container_of(plane, struct nouveau_plane, base);
 
 	nvif_mask(dev, NV_PVIDEO_OVERLAY, 1, 0);
 	nvif_wr32(dev, NV_PVIDEO_OE_STATE, 0);
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index 615714c1727d..a24faa5e2a2a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -448,7 +448,7 @@ nouveau_abi16_ioctl_notifierobj_alloc(ABI16_IOCTL_ARGS)
 	list_add(&ntfy->head, &chan->notifiers);
 	ntfy->handle = info->handle;
 
-	ret = nouveau_mm_head(&chan->heap, 1, info->size, info->size, 1,
+	ret = nouveau_mm_head(&chan->heap, 0, 1, info->size, info->size, 1,
 			      &ntfy->node);
 	if (ret)
 		goto done;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 01da508625f2..3d474ac03f88 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -88,13 +88,13 @@ nv10_bo_get_tile_region(struct drm_device *dev, int i)
 
 static void
 nv10_bo_put_tile_region(struct drm_device *dev, struct nouveau_drm_tile *tile,
-			struct nouveau_fence *fence)
+			struct fence *fence)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
 
 	if (tile) {
 		spin_lock(&drm->tile.lock);
-		tile->fence = nouveau_fence_ref(fence);
+		tile->fence = (struct nouveau_fence *)fence_get(fence);
 		tile->used = false;
 		spin_unlock(&drm->tile.lock);
 	}
@@ -181,7 +181,7 @@ nouveau_bo_fixup_align(struct nouveau_bo *nvbo, u32 flags,
 int
 nouveau_bo_new(struct drm_device *dev, int size, int align,
 	       uint32_t flags, uint32_t tile_mode, uint32_t tile_flags,
-	       struct sg_table *sg,
+	       struct sg_table *sg, struct reservation_object *robj,
 	       struct nouveau_bo **pnvbo)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
@@ -230,7 +230,7 @@ nouveau_bo_new(struct drm_device *dev, int size, int align,
 	ret = ttm_bo_init(&drm->ttm.bdev, &nvbo->bo, size,
 			  type, &nvbo->placement,
 			  align >> PAGE_SHIFT, false, NULL, acc_size, sg,
-			  nouveau_bo_del_ttm);
+			  robj, nouveau_bo_del_ttm);
 	if (ret) {
 		/* ttm will call nouveau_bo_del_ttm if it fails.. */
 		return ret;
@@ -241,16 +241,16 @@ nouveau_bo_new(struct drm_device *dev, int size, int align,
 }
 
 static void
-set_placement_list(uint32_t *pl, unsigned *n, uint32_t type, uint32_t flags)
+set_placement_list(struct ttm_place *pl, unsigned *n, uint32_t type, uint32_t flags)
 {
 	*n = 0;
 
 	if (type & TTM_PL_FLAG_VRAM)
-		pl[(*n)++] = TTM_PL_FLAG_VRAM | flags;
+		pl[(*n)++].flags = TTM_PL_FLAG_VRAM | flags;
 	if (type & TTM_PL_FLAG_TT)
-		pl[(*n)++] = TTM_PL_FLAG_TT | flags;
+		pl[(*n)++].flags = TTM_PL_FLAG_TT | flags;
 	if (type & TTM_PL_FLAG_SYSTEM)
-		pl[(*n)++] = TTM_PL_FLAG_SYSTEM | flags;
+		pl[(*n)++].flags = TTM_PL_FLAG_SYSTEM | flags;
 }
 
 static void
@@ -258,6 +258,7 @@ set_placement_range(struct nouveau_bo *nvbo, uint32_t type)
 {
 	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
 	u32 vram_pages = drm->device.info.ram_size >> PAGE_SHIFT;
+	unsigned i, fpfn, lpfn;
 
 	if (drm->device.info.family == NV_DEVICE_INFO_V0_CELSIUS &&
 	    nvbo->tile_mode && (type & TTM_PL_FLAG_VRAM) &&
@@ -269,11 +270,19 @@ set_placement_range(struct nouveau_bo *nvbo, uint32_t type)
 		 * at the same time.
 		 */
 		if (nvbo->tile_flags & NOUVEAU_GEM_TILE_ZETA) {
-			nvbo->placement.fpfn = vram_pages / 2;
-			nvbo->placement.lpfn = ~0;
+			fpfn = vram_pages / 2;
+			lpfn = ~0;
 		} else {
-			nvbo->placement.fpfn = 0;
-			nvbo->placement.lpfn = vram_pages / 2;
+			fpfn = 0;
+			lpfn = vram_pages / 2;
+		}
+		for (i = 0; i < nvbo->placement.num_placement; ++i) {
+			nvbo->placements[i].fpfn = fpfn;
+			nvbo->placements[i].lpfn = lpfn;
+		}
+		for (i = 0; i < nvbo->placement.num_busy_placement; ++i) {
+			nvbo->busy_placements[i].fpfn = fpfn;
+			nvbo->busy_placements[i].lpfn = lpfn;
 		}
 	}
 }
@@ -961,13 +970,14 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
 	}
 
 	mutex_lock_nested(&cli->mutex, SINGLE_DEPTH_NESTING);
-	ret = nouveau_fence_sync(bo->sync_obj, chan);
+	ret = nouveau_fence_sync(nouveau_bo(bo), chan, true, intr);
 	if (ret == 0) {
 		ret = drm->ttm.move(chan, bo, &bo->mem, new_mem);
 		if (ret == 0) {
 			ret = nouveau_fence_new(chan, false, &fence);
 			if (ret == 0) {
-				ret = ttm_bo_move_accel_cleanup(bo, fence,
+				ret = ttm_bo_move_accel_cleanup(bo,
+								&fence->base,
 								evict,
 								no_wait_gpu,
 								new_mem);
@@ -1041,12 +1051,15 @@ static int
 nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 		      bool no_wait_gpu, struct ttm_mem_reg *new_mem)
 {
-	u32 placement_memtype = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING;
+	struct ttm_place placement_memtype = {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING
+	};
 	struct ttm_placement placement;
 	struct ttm_mem_reg tmp_mem;
 	int ret;
 
-	placement.fpfn = placement.lpfn = 0;
 	placement.num_placement = placement.num_busy_placement = 1;
 	placement.placement = placement.busy_placement = &placement_memtype;
 
@@ -1074,12 +1087,15 @@ static int
 nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr,
 		      bool no_wait_gpu, struct ttm_mem_reg *new_mem)
 {
-	u32 placement_memtype = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING;
+	struct ttm_place placement_memtype = {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING
+	};
 	struct ttm_placement placement;
 	struct ttm_mem_reg tmp_mem;
 	int ret;
 
-	placement.fpfn = placement.lpfn = 0;
 	placement.num_placement = placement.num_busy_placement = 1;
 	placement.placement = placement.busy_placement = &placement_memtype;
 
@@ -1152,8 +1168,9 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo,
 {
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
 	struct drm_device *dev = drm->dev;
+	struct fence *fence = reservation_object_get_excl(bo->resv);
 
-	nv10_bo_put_tile_region(dev, *old_tile, bo->sync_obj);
+	nv10_bo_put_tile_region(dev, *old_tile, fence);
 	*old_tile = new_tile;
 }
 
@@ -1197,9 +1214,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, bool intr,
 	}
 
 	/* Fallback to software copy. */
-	spin_lock(&bo->bdev->fence_lock);
 	ret = ttm_bo_wait(bo, true, intr, no_wait_gpu);
-	spin_unlock(&bo->bdev->fence_lock);
 	if (ret == 0)
 		ret = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
 
@@ -1294,7 +1309,7 @@ nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nvif_device *device = &drm->device;
 	u32 mappable = nv_device_resource_len(nvkm_device(device), 1) >> PAGE_SHIFT;
-	int ret;
+	int i, ret;
 
 	/* as long as the bo isn't in vram, and isn't tiled, we've got
 	 * nothing to do here.
@@ -1319,9 +1334,16 @@ nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
 	    bo->mem.start + bo->mem.num_pages < mappable)
 		return 0;
 
+	for (i = 0; i < nvbo->placement.num_placement; ++i) {
+		nvbo->placements[i].fpfn = 0;
+		nvbo->placements[i].lpfn = mappable;
+	}
+
+	for (i = 0; i < nvbo->placement.num_busy_placement; ++i) {
+		nvbo->busy_placements[i].fpfn = 0;
+		nvbo->busy_placements[i].lpfn = mappable;
+	}
 
-	nvbo->placement.fpfn = 0;
-	nvbo->placement.lpfn = mappable;
 	nouveau_bo_placement_set(nvbo, TTM_PL_FLAG_VRAM, 0);
 	return nouveau_bo_validate(nvbo, false, false);
 }
@@ -1436,47 +1458,14 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm)
 }
 
 void
-nouveau_bo_fence(struct nouveau_bo *nvbo, struct nouveau_fence *fence)
-{
-	struct nouveau_fence *new_fence = nouveau_fence_ref(fence);
-	struct nouveau_fence *old_fence = NULL;
-
-	spin_lock(&nvbo->bo.bdev->fence_lock);
-	old_fence = nvbo->bo.sync_obj;
-	nvbo->bo.sync_obj = new_fence;
-	spin_unlock(&nvbo->bo.bdev->fence_lock);
-
-	nouveau_fence_unref(&old_fence);
-}
-
-static void
-nouveau_bo_fence_unref(void **sync_obj)
-{
-	nouveau_fence_unref((struct nouveau_fence **)sync_obj);
-}
-
-static void *
-nouveau_bo_fence_ref(void *sync_obj)
+nouveau_bo_fence(struct nouveau_bo *nvbo, struct nouveau_fence *fence, bool exclusive)
 {
-	return nouveau_fence_ref(sync_obj);
-}
+	struct reservation_object *resv = nvbo->bo.resv;
 
-static bool
-nouveau_bo_fence_signalled(void *sync_obj)
-{
-	return nouveau_fence_done(sync_obj);
-}
-
-static int
-nouveau_bo_fence_wait(void *sync_obj, bool lazy, bool intr)
-{
-	return nouveau_fence_wait(sync_obj, lazy, intr);
-}
-
-static int
-nouveau_bo_fence_flush(void *sync_obj)
-{
-	return 0;
+	if (exclusive)
+		reservation_object_add_excl_fence(resv, &fence->base);
+	else if (fence)
+		reservation_object_add_shared_fence(resv, &fence->base);
 }
 
 struct ttm_bo_driver nouveau_bo_driver = {
@@ -1489,11 +1478,6 @@ struct ttm_bo_driver nouveau_bo_driver = {
 	.move_notify = nouveau_bo_move_ntfy,
 	.move = nouveau_bo_move,
 	.verify_access = nouveau_bo_verify_access,
-	.sync_obj_signaled = nouveau_bo_fence_signalled,
-	.sync_obj_wait = nouveau_bo_fence_wait,
-	.sync_obj_flush = nouveau_bo_fence_flush,
-	.sync_obj_unref = nouveau_bo_fence_unref,
-	.sync_obj_ref = nouveau_bo_fence_ref,
 	.fault_reserve_notify = &nouveau_ttm_fault_reserve_notify,
 	.io_mem_reserve = &nouveau_ttm_io_mem_reserve,
 	.io_mem_free = &nouveau_ttm_io_mem_free,
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h
index ff17c1f432fc..22d2c764d80b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.h
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.h
@@ -1,6 +1,8 @@
 #ifndef __NOUVEAU_BO_H__
 #define __NOUVEAU_BO_H__
 
+#include <drm/drm_gem.h>
+
 struct nouveau_channel;
 struct nouveau_fence;
 struct nouveau_vma;
@@ -9,8 +11,8 @@ struct nouveau_bo {
 	struct ttm_buffer_object bo;
 	struct ttm_placement placement;
 	u32 valid_domains;
-	u32 placements[3];
-	u32 busy_placements[3];
+	struct ttm_place placements[3];
+	struct ttm_place busy_placements[3];
 	struct ttm_bo_kmap_obj kmap;
 	struct list_head head;
 
@@ -68,6 +70,7 @@ extern struct ttm_bo_driver nouveau_bo_driver;
 void nouveau_bo_move_init(struct nouveau_drm *);
 int  nouveau_bo_new(struct drm_device *, int size, int align, u32 flags,
 		    u32 tile_mode, u32 tile_flags, struct sg_table *sg,
+		    struct reservation_object *robj,
 		    struct nouveau_bo **);
 int  nouveau_bo_pin(struct nouveau_bo *, u32 flags);
 int  nouveau_bo_unpin(struct nouveau_bo *);
@@ -78,7 +81,7 @@ u16  nouveau_bo_rd16(struct nouveau_bo *, unsigned index);
 void nouveau_bo_wr16(struct nouveau_bo *, unsigned index, u16 val);
 u32  nouveau_bo_rd32(struct nouveau_bo *, unsigned index);
 void nouveau_bo_wr32(struct nouveau_bo *, unsigned index, u32 val);
-void nouveau_bo_fence(struct nouveau_bo *, struct nouveau_fence *);
+void nouveau_bo_fence(struct nouveau_bo *, struct nouveau_fence *, bool exclusive);
 int  nouveau_bo_validate(struct nouveau_bo *, bool interruptible,
 			 bool no_wait_gpu);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c
index 3440fc999f2f..589dbb582da2 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.c
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.c
@@ -36,7 +36,7 @@
 #include "nouveau_abi16.h"
 
 MODULE_PARM_DESC(vram_pushbuf, "Create DMA push buffers in VRAM");
-static int nouveau_vram_pushbuf;
+int nouveau_vram_pushbuf;
 module_param_named(vram_pushbuf, nouveau_vram_pushbuf, int, 0400);
 
 int
@@ -106,7 +106,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device,
 	if (nouveau_vram_pushbuf)
 		target = TTM_PL_FLAG_VRAM;
 
-	ret = nouveau_bo_new(drm->dev, size, 0, target, 0, 0, NULL,
+	ret = nouveau_bo_new(drm->dev, size, 0, target, 0, 0, NULL, NULL,
 			    &chan->push.buffer);
 	if (ret == 0) {
 		ret = nouveau_bo_pin(chan->push.buffer, target);
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.h b/drivers/gpu/drm/nouveau/nouveau_chan.h
index 20163709d608..8309c24ee698 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.h
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.h
@@ -47,4 +47,6 @@ int  nouveau_channel_new(struct nouveau_drm *, struct nvif_device *,
 void nouveau_channel_del(struct nouveau_channel **);
 int  nouveau_channel_idle(struct nouveau_channel *);
 
+extern int nouveau_vram_pushbuf;
+
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 1ec44c83e919..c8ac9482cf2e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -45,15 +45,15 @@
 #include <nvif/event.h>
 
 MODULE_PARM_DESC(tv_disable, "Disable TV-out detection");
-static int nouveau_tv_disable = 0;
+int nouveau_tv_disable = 0;
 module_param_named(tv_disable, nouveau_tv_disable, int, 0400);
 
 MODULE_PARM_DESC(ignorelid, "Ignore ACPI lid status");
-static int nouveau_ignorelid = 0;
+int nouveau_ignorelid = 0;
 module_param_named(ignorelid, nouveau_ignorelid, int, 0400);
 
 MODULE_PARM_DESC(duallink, "Allow dual-link TMDS (default: enabled)");
-static int nouveau_duallink = 1;
+int nouveau_duallink = 1;
 module_param_named(duallink, nouveau_duallink, int, 0400);
 
 struct nouveau_encoder *
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h
index 68029d041dd2..629a380c7085 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.h
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.h
@@ -105,4 +105,8 @@ nouveau_crtc_connector_get(struct nouveau_crtc *nv_crtc)
 struct drm_connector *
 nouveau_connector_create(struct drm_device *, int index);
 
+extern int nouveau_tv_disable;
+extern int nouveau_ignorelid;
+extern int nouveau_duallink;
+
 #endif /* __NOUVEAU_CONNECTOR_H__ */
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 4a21b2b06ce2..a88e6927f571 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -126,7 +126,7 @@ nouveau_display_scanoutpos_head(struct drm_crtc *crtc, int *vpos, int *hpos,
 	if (etime) *etime = ns_to_ktime(args.scan.time[1]);
 
 	if (*vpos < 0)
-		ret |= DRM_SCANOUTPOS_INVBL;
+		ret |= DRM_SCANOUTPOS_IN_VBLANK;
 	return ret;
 }
 
@@ -657,7 +657,7 @@ nouveau_page_flip_emit(struct nouveau_channel *chan,
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 
 	/* Synchronize with the old framebuffer */
-	ret = nouveau_fence_sync(old_bo->bo.sync_obj, chan);
+	ret = nouveau_fence_sync(old_bo, chan, false, false);
 	if (ret)
 		goto fail;
 
@@ -716,19 +716,24 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	}
 
 	mutex_lock(&cli->mutex);
-
-	/* synchronise rendering channel with the kernel's channel */
-	spin_lock(&new_bo->bo.bdev->fence_lock);
-	fence = nouveau_fence_ref(new_bo->bo.sync_obj);
-	spin_unlock(&new_bo->bo.bdev->fence_lock);
-	ret = nouveau_fence_sync(fence, chan);
-	nouveau_fence_unref(&fence);
+	ret = ttm_bo_reserve(&new_bo->bo, true, false, false, NULL);
 	if (ret)
 		goto fail_unpin;
 
-	ret = ttm_bo_reserve(&old_bo->bo, true, false, false, NULL);
-	if (ret)
+	/* synchronise rendering channel with the kernel's channel */
+	ret = nouveau_fence_sync(new_bo, chan, false, true);
+	if (ret) {
+		ttm_bo_unreserve(&new_bo->bo);
 		goto fail_unpin;
+	}
+
+	if (new_bo != old_bo) {
+		ttm_bo_unreserve(&new_bo->bo);
+
+		ret = ttm_bo_reserve(&old_bo->bo, true, false, false, NULL);
+		if (ret)
+			goto fail_unpin;
+	}
 
 	/* Initialize a page flip struct */
 	*s = (struct nouveau_page_flip_state)
@@ -774,7 +779,7 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	/* Update the crtc struct and cleanup */
 	crtc->primary->fb = fb;
 
-	nouveau_bo_fence(old_bo, fence);
+	nouveau_bo_fence(old_bo, fence, false);
 	ttm_bo_unreserve(&old_bo->bo);
 	if (old_bo != new_bo)
 		nouveau_bo_unpin(old_bo);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 3ed32dd90303..57238076049f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -51,6 +51,7 @@
 #include "nouveau_fence.h"
 #include "nouveau_debugfs.h"
 #include "nouveau_usif.h"
+#include "nouveau_connector.h"
 
 MODULE_PARM_DESC(config, "option string to pass to driver core");
 static char *nouveau_config;
@@ -73,7 +74,9 @@ MODULE_PARM_DESC(runpm, "disable (0), force enable (1), optimus only default (-1
 int nouveau_runtime_pm = -1;
 module_param_named(runpm, nouveau_runtime_pm, int, 0400);
 
-static struct drm_driver driver;
+static struct drm_driver driver_stub;
+static struct drm_driver driver_pci;
+static struct drm_driver driver_platform;
 
 static u64
 nouveau_pci_name(struct pci_dev *pdev)
@@ -322,7 +325,7 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
-	ret = drm_get_pci_dev(pdev, pent, &driver);
+	ret = drm_get_pci_dev(pdev, pent, &driver_pci);
 	if (ret) {
 		nouveau_object_ref(NULL, (struct nouveau_object **)&device);
 		return ret;
@@ -831,7 +834,7 @@ nouveau_driver_fops = {
 };
 
 static struct drm_driver
-driver = {
+driver_stub = {
 	.driver_features =
 		DRIVER_USE_AGP |
 		DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_RENDER,
@@ -1002,6 +1005,23 @@ static int nouveau_pmops_runtime_idle(struct device *dev)
 	return 1;
 }
 
+static void nouveau_display_options(void)
+{
+	DRM_DEBUG_DRIVER("Loading Nouveau with parameters:\n");
+
+	DRM_DEBUG_DRIVER("... tv_disable   : %d\n", nouveau_tv_disable);
+	DRM_DEBUG_DRIVER("... ignorelid    : %d\n", nouveau_ignorelid);
+	DRM_DEBUG_DRIVER("... duallink     : %d\n", nouveau_duallink);
+	DRM_DEBUG_DRIVER("... nofbaccel    : %d\n", nouveau_nofbaccel);
+	DRM_DEBUG_DRIVER("... config       : %s\n", nouveau_config);
+	DRM_DEBUG_DRIVER("... debug        : %s\n", nouveau_debug);
+	DRM_DEBUG_DRIVER("... noaccel      : %d\n", nouveau_noaccel);
+	DRM_DEBUG_DRIVER("... modeset      : %d\n", nouveau_modeset);
+	DRM_DEBUG_DRIVER("... runpm        : %d\n", nouveau_runtime_pm);
+	DRM_DEBUG_DRIVER("... vram_pushbuf : %d\n", nouveau_vram_pushbuf);
+	DRM_DEBUG_DRIVER("... pstate       : %d\n", nouveau_pstate);
+}
+
 static const struct dev_pm_ops nouveau_pm_ops = {
 	.suspend = nouveau_pmops_suspend,
 	.resume = nouveau_pmops_resume,
@@ -1037,7 +1057,7 @@ nouveau_platform_device_create_(struct platform_device *pdev, int size,
 	if (err)
 		return ERR_PTR(err);
 
-	drm = drm_dev_alloc(&driver, &pdev->dev);
+	drm = drm_dev_alloc(&driver_platform, &pdev->dev);
 	if (!drm) {
 		err = -ENOMEM;
 		goto err_free;
@@ -1062,6 +1082,13 @@ EXPORT_SYMBOL(nouveau_platform_device_create_);
 static int __init
 nouveau_drm_init(void)
 {
+	driver_pci = driver_stub;
+	driver_pci.set_busid = drm_pci_set_busid;
+	driver_platform = driver_stub;
+	driver_platform.set_busid = drm_platform_set_busid;
+
+	nouveau_display_options();
+
 	if (nouveau_modeset == -1) {
 #ifdef CONFIG_VGA_CONSOLE
 		if (vgacon_text_force())
@@ -1073,7 +1100,7 @@ nouveau_drm_init(void)
 		return 0;
 
 	nouveau_register_dsm_handler();
-	return drm_pci_init(&driver, &nouveau_drm_pci_driver);
+	return drm_pci_init(&driver_pci, &nouveau_drm_pci_driver);
 }
 
 static void __exit
@@ -1082,7 +1109,7 @@ nouveau_drm_exit(void)
 	if (!nouveau_modeset)
 		return;
 
-	drm_pci_exit(&driver, &nouveau_drm_pci_driver);
+	drm_pci_exit(&driver_pci, &nouveau_drm_pci_driver);
 	nouveau_unregister_dsm_handler();
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.h b/drivers/gpu/drm/nouveau/nouveau_drm.h
index b02b02452c85..8ae36f265fb8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.h
@@ -10,7 +10,7 @@
 
 #define DRIVER_MAJOR		1
 #define DRIVER_MINOR		2
-#define DRIVER_PATCHLEVEL	0
+#define DRIVER_PATCHLEVEL	1
 
 /*
  * 1.1.1:
@@ -26,6 +26,8 @@
  * 1.2.0:
  * 	- object api exposed to userspace
  * 	- fermi,kepler,maxwell zbc
+ * 1.2.1:
+ *      - allow concurrent access to bo's mapped read/write.
  */
 
 #include <nvif/client.h>
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 49fe6075cc7c..593ef8a2a069 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -52,7 +52,7 @@
 #include "nouveau_crtc.h"
 
 MODULE_PARM_DESC(nofbaccel, "Disable fbcon acceleration");
-static int nouveau_nofbaccel = 0;
+int nouveau_nofbaccel = 0;
 module_param_named(nofbaccel, nouveau_nofbaccel, int, 0400);
 
 static void
@@ -308,7 +308,8 @@ static int
 nouveau_fbcon_create(struct drm_fb_helper *helper,
 		     struct drm_fb_helper_surface_size *sizes)
 {
-	struct nouveau_fbdev *fbcon = (struct nouveau_fbdev *)helper;
+	struct nouveau_fbdev *fbcon =
+		container_of(helper, struct nouveau_fbdev, helper);
 	struct drm_device *dev = fbcon->dev;
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nvif_device *device = &drm->device;
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.h b/drivers/gpu/drm/nouveau/nouveau_fbcon.h
index 0b465c7d3907..6208e70e4a1c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.h
@@ -73,5 +73,8 @@ void nouveau_fbcon_accel_save_disable(struct drm_device *dev);
 void nouveau_fbcon_accel_restore(struct drm_device *dev);
 
 void nouveau_fbcon_output_poll_changed(struct drm_device *dev);
+
+extern int nouveau_nofbaccel;
+
 #endif /* __NV50_FBCON_H__ */
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 0a93114158cd..515cd9aebb99 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -28,6 +28,7 @@
 
 #include <linux/ktime.h>
 #include <linux/hrtimer.h>
+#include <trace/events/fence.h>
 
 #include <nvif/notify.h>
 #include <nvif/event.h>
@@ -36,123 +37,234 @@
 #include "nouveau_dma.h"
 #include "nouveau_fence.h"
 
-struct fence_work {
-	struct work_struct base;
-	struct list_head head;
-	void (*func)(void *);
-	void *data;
-};
+static const struct fence_ops nouveau_fence_ops_uevent;
+static const struct fence_ops nouveau_fence_ops_legacy;
+
+static inline struct nouveau_fence *
+from_fence(struct fence *fence)
+{
+	return container_of(fence, struct nouveau_fence, base);
+}
+
+static inline struct nouveau_fence_chan *
+nouveau_fctx(struct nouveau_fence *fence)
+{
+	return container_of(fence->base.lock, struct nouveau_fence_chan, lock);
+}
 
 static void
 nouveau_fence_signal(struct nouveau_fence *fence)
 {
-	struct fence_work *work, *temp;
+	fence_signal_locked(&fence->base);
+	list_del(&fence->head);
+
+	if (test_bit(FENCE_FLAG_USER_BITS, &fence->base.flags)) {
+		struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
 
-	list_for_each_entry_safe(work, temp, &fence->work, head) {
-		schedule_work(&work->base);
-		list_del(&work->head);
+		if (!--fctx->notify_ref)
+			nvif_notify_put(&fctx->notify);
 	}
 
-	fence->channel = NULL;
-	list_del(&fence->head);
+	fence_put(&fence->base);
+}
+
+static struct nouveau_fence *
+nouveau_local_fence(struct fence *fence, struct nouveau_drm *drm) {
+	struct nouveau_fence_priv *priv = (void*)drm->fence;
+
+	if (fence->ops != &nouveau_fence_ops_legacy &&
+	    fence->ops != &nouveau_fence_ops_uevent)
+		return NULL;
+
+	if (fence->context < priv->context_base ||
+	    fence->context >= priv->context_base + priv->contexts)
+		return NULL;
+
+	return from_fence(fence);
 }
 
 void
 nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
 {
-	struct nouveau_fence *fence, *fnext;
-	spin_lock(&fctx->lock);
-	list_for_each_entry_safe(fence, fnext, &fctx->pending, head) {
+	struct nouveau_fence *fence;
+
+	nvif_notify_fini(&fctx->notify);
+
+	spin_lock_irq(&fctx->lock);
+	while (!list_empty(&fctx->pending)) {
+		fence = list_entry(fctx->pending.next, typeof(*fence), head);
+
 		nouveau_fence_signal(fence);
+		fence->channel = NULL;
 	}
-	spin_unlock(&fctx->lock);
+	spin_unlock_irq(&fctx->lock);
+}
+
+static void
+nouveau_fence_context_put(struct kref *fence_ref)
+{
+	kfree(container_of(fence_ref, struct nouveau_fence_chan, fence_ref));
 }
 
 void
-nouveau_fence_context_new(struct nouveau_fence_chan *fctx)
+nouveau_fence_context_free(struct nouveau_fence_chan *fctx)
+{
+	kref_put(&fctx->fence_ref, nouveau_fence_context_put);
+}
+
+static void
+nouveau_fence_update(struct nouveau_channel *chan, struct nouveau_fence_chan *fctx)
+{
+	struct nouveau_fence *fence;
+
+	u32 seq = fctx->read(chan);
+
+	while (!list_empty(&fctx->pending)) {
+		fence = list_entry(fctx->pending.next, typeof(*fence), head);
+
+		if ((int)(seq - fence->base.seqno) < 0)
+			return;
+
+		nouveau_fence_signal(fence);
+	}
+}
+
+static int
+nouveau_fence_wait_uevent_handler(struct nvif_notify *notify)
 {
+	struct nouveau_fence_chan *fctx =
+		container_of(notify, typeof(*fctx), notify);
+	unsigned long flags;
+
+	spin_lock_irqsave(&fctx->lock, flags);
+	if (!list_empty(&fctx->pending)) {
+		struct nouveau_fence *fence;
+
+		fence = list_entry(fctx->pending.next, typeof(*fence), head);
+		nouveau_fence_update(fence->channel, fctx);
+	}
+	spin_unlock_irqrestore(&fctx->lock, flags);
+
+	/* Always return keep here. NVIF refcount is handled with nouveau_fence_update */
+	return NVIF_NOTIFY_KEEP;
+}
+
+void
+nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_chan *fctx)
+{
+	struct nouveau_fence_priv *priv = (void*)chan->drm->fence;
+	struct nouveau_cli *cli = (void *)nvif_client(chan->object);
+	int ret;
+
 	INIT_LIST_HEAD(&fctx->flip);
 	INIT_LIST_HEAD(&fctx->pending);
 	spin_lock_init(&fctx->lock);
+	fctx->context = priv->context_base + chan->chid;
+
+	if (chan == chan->drm->cechan)
+		strcpy(fctx->name, "copy engine channel");
+	else if (chan == chan->drm->channel)
+		strcpy(fctx->name, "generic kernel channel");
+	else
+		strcpy(fctx->name, nvkm_client(&cli->base)->name);
+
+	kref_init(&fctx->fence_ref);
+	if (!priv->uevent)
+		return;
+
+	ret = nvif_notify_init(chan->object, NULL,
+			 nouveau_fence_wait_uevent_handler, false,
+			 G82_CHANNEL_DMA_V0_NTFY_UEVENT,
+			 &(struct nvif_notify_uevent_req) { },
+			 sizeof(struct nvif_notify_uevent_req),
+			 sizeof(struct nvif_notify_uevent_rep),
+			 &fctx->notify);
+
+	WARN_ON(ret);
 }
 
+struct nouveau_fence_work {
+	struct work_struct work;
+	struct fence_cb cb;
+	void (*func)(void *);
+	void *data;
+};
+
 static void
 nouveau_fence_work_handler(struct work_struct *kwork)
 {
-	struct fence_work *work = container_of(kwork, typeof(*work), base);
+	struct nouveau_fence_work *work = container_of(kwork, typeof(*work), work);
 	work->func(work->data);
 	kfree(work);
 }
 
+static void nouveau_fence_work_cb(struct fence *fence, struct fence_cb *cb)
+{
+	struct nouveau_fence_work *work = container_of(cb, typeof(*work), cb);
+
+	schedule_work(&work->work);
+}
+
 void
-nouveau_fence_work(struct nouveau_fence *fence,
+nouveau_fence_work(struct fence *fence,
 		   void (*func)(void *), void *data)
 {
-	struct nouveau_channel *chan = fence->channel;
-	struct nouveau_fence_chan *fctx;
-	struct fence_work *work = NULL;
+	struct nouveau_fence_work *work;
 
-	if (nouveau_fence_done(fence)) {
-		func(data);
-		return;
-	}
+	if (fence_is_signaled(fence))
+		goto err;
 
-	fctx = chan->fence;
 	work = kmalloc(sizeof(*work), GFP_KERNEL);
 	if (!work) {
-		WARN_ON(nouveau_fence_wait(fence, false, false));
-		func(data);
-		return;
-	}
-
-	spin_lock(&fctx->lock);
-	if (!fence->channel) {
-		spin_unlock(&fctx->lock);
-		kfree(work);
-		func(data);
-		return;
+		/*
+		 * this might not be a nouveau fence any more,
+		 * so force a lazy wait here
+		 */
+		WARN_ON(nouveau_fence_wait((struct nouveau_fence *)fence,
+					   true, false));
+		goto err;
 	}
 
-	INIT_WORK(&work->base, nouveau_fence_work_handler);
+	INIT_WORK(&work->work, nouveau_fence_work_handler);
 	work->func = func;
 	work->data = data;
-	list_add(&work->head, &fence->work);
-	spin_unlock(&fctx->lock);
-}
-
-static void
-nouveau_fence_update(struct nouveau_channel *chan)
-{
-	struct nouveau_fence_chan *fctx = chan->fence;
-	struct nouveau_fence *fence, *fnext;
 
-	spin_lock(&fctx->lock);
-	list_for_each_entry_safe(fence, fnext, &fctx->pending, head) {
-		if (fctx->read(chan) < fence->sequence)
-			break;
+	if (fence_add_callback(fence, &work->cb, nouveau_fence_work_cb) < 0)
+		goto err_free;
+	return;
 
-		nouveau_fence_signal(fence);
-		nouveau_fence_unref(&fence);
-	}
-	spin_unlock(&fctx->lock);
+err_free:
+	kfree(work);
+err:
+	func(data);
 }
 
 int
 nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan)
 {
 	struct nouveau_fence_chan *fctx = chan->fence;
+	struct nouveau_fence_priv *priv = (void*)chan->drm->fence;
 	int ret;
 
 	fence->channel  = chan;
 	fence->timeout  = jiffies + (15 * HZ);
-	fence->sequence = ++fctx->sequence;
 
+	if (priv->uevent)
+		fence_init(&fence->base, &nouveau_fence_ops_uevent,
+			   &fctx->lock, fctx->context, ++fctx->sequence);
+	else
+		fence_init(&fence->base, &nouveau_fence_ops_legacy,
+			   &fctx->lock, fctx->context, ++fctx->sequence);
+	kref_get(&fctx->fence_ref);
+
+	trace_fence_emit(&fence->base);
 	ret = fctx->emit(fence);
 	if (!ret) {
-		kref_get(&fence->kref);
-		spin_lock(&fctx->lock);
+		fence_get(&fence->base);
+		spin_lock_irq(&fctx->lock);
+		nouveau_fence_update(chan, fctx);
 		list_add_tail(&fence->head, &fctx->pending);
-		spin_unlock(&fctx->lock);
+		spin_unlock_irq(&fctx->lock);
 	}
 
 	return ret;
@@ -161,114 +273,70 @@ nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan)
 bool
 nouveau_fence_done(struct nouveau_fence *fence)
 {
-	if (fence->channel)
-		nouveau_fence_update(fence->channel);
-	return !fence->channel;
-}
+	if (fence->base.ops == &nouveau_fence_ops_legacy ||
+	    fence->base.ops == &nouveau_fence_ops_uevent) {
+		struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
+		unsigned long flags;
 
-struct nouveau_fence_wait {
-	struct nouveau_fence_priv *priv;
-	struct nvif_notify notify;
-};
+		if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->base.flags))
+			return true;
 
-static int
-nouveau_fence_wait_uevent_handler(struct nvif_notify *notify)
-{
-	struct nouveau_fence_wait *wait =
-		container_of(notify, typeof(*wait), notify);
-	wake_up_all(&wait->priv->waiting);
-	return NVIF_NOTIFY_KEEP;
+		spin_lock_irqsave(&fctx->lock, flags);
+		nouveau_fence_update(fence->channel, fctx);
+		spin_unlock_irqrestore(&fctx->lock, flags);
+	}
+	return fence_is_signaled(&fence->base);
 }
 
-static int
-nouveau_fence_wait_uevent(struct nouveau_fence *fence, bool intr)
-
+static long
+nouveau_fence_wait_legacy(struct fence *f, bool intr, long wait)
 {
-	struct nouveau_channel *chan = fence->channel;
-	struct nouveau_fence_priv *priv = chan->drm->fence;
-	struct nouveau_fence_wait wait = { .priv = priv };
-	int ret = 0;
+	struct nouveau_fence *fence = from_fence(f);
+	unsigned long sleep_time = NSEC_PER_MSEC / 1000;
+	unsigned long t = jiffies, timeout = t + wait;
 
-	ret = nvif_notify_init(chan->object, NULL,
-			       nouveau_fence_wait_uevent_handler, false,
-			       G82_CHANNEL_DMA_V0_NTFY_UEVENT,
-			       &(struct nvif_notify_uevent_req) {
-			       },
-			       sizeof(struct nvif_notify_uevent_req),
-			       sizeof(struct nvif_notify_uevent_rep),
-			       &wait.notify);
-	if (ret)
-		return ret;
+	while (!nouveau_fence_done(fence)) {
+		ktime_t kt;
 
-	nvif_notify_get(&wait.notify);
-
-	if (fence->timeout) {
-		unsigned long timeout = fence->timeout - jiffies;
-
-		if (time_before(jiffies, fence->timeout)) {
-			if (intr) {
-				ret = wait_event_interruptible_timeout(
-						priv->waiting,
-						nouveau_fence_done(fence),
-						timeout);
-			} else {
-				ret = wait_event_timeout(priv->waiting,
-						nouveau_fence_done(fence),
-						timeout);
-			}
-		}
+		t = jiffies;
 
-		if (ret >= 0) {
-			fence->timeout = jiffies + ret;
-			if (time_after_eq(jiffies, fence->timeout))
-				ret = -EBUSY;
-		}
-	} else {
-		if (intr) {
-			ret = wait_event_interruptible(priv->waiting,
-					nouveau_fence_done(fence));
-		} else {
-			wait_event(priv->waiting, nouveau_fence_done(fence));
+		if (wait != MAX_SCHEDULE_TIMEOUT && time_after_eq(t, timeout)) {
+			__set_current_state(TASK_RUNNING);
+			return 0;
 		}
+
+		__set_current_state(intr ? TASK_INTERRUPTIBLE :
+					   TASK_UNINTERRUPTIBLE);
+
+		kt = ktime_set(0, sleep_time);
+		schedule_hrtimeout(&kt, HRTIMER_MODE_REL);
+		sleep_time *= 2;
+		if (sleep_time > NSEC_PER_MSEC)
+			sleep_time = NSEC_PER_MSEC;
+
+		if (intr && signal_pending(current))
+			return -ERESTARTSYS;
 	}
 
-	nvif_notify_fini(&wait.notify);
-	if (unlikely(ret < 0))
-		return ret;
+	__set_current_state(TASK_RUNNING);
 
-	return 0;
+	return timeout - t;
 }
 
-int
-nouveau_fence_wait(struct nouveau_fence *fence, bool lazy, bool intr)
+static int
+nouveau_fence_wait_busy(struct nouveau_fence *fence, bool intr)
 {
-	struct nouveau_channel *chan = fence->channel;
-	struct nouveau_fence_priv *priv = chan ? chan->drm->fence : NULL;
-	unsigned long sleep_time = NSEC_PER_MSEC / 1000;
-	ktime_t t;
 	int ret = 0;
 
-	while (priv && priv->uevent && lazy && !nouveau_fence_done(fence)) {
-		ret = nouveau_fence_wait_uevent(fence, intr);
-		if (ret < 0)
-			return ret;
-	}
-
 	while (!nouveau_fence_done(fence)) {
-		if (fence->timeout && time_after_eq(jiffies, fence->timeout)) {
+		if (time_after_eq(jiffies, fence->timeout)) {
 			ret = -EBUSY;
 			break;
 		}
 
-		__set_current_state(intr ? TASK_INTERRUPTIBLE :
-					   TASK_UNINTERRUPTIBLE);
-		if (lazy) {
-			t = ktime_set(0, sleep_time);
-			schedule_hrtimeout(&t, HRTIMER_MODE_REL);
-			sleep_time *= 2;
-			if (sleep_time > NSEC_PER_MSEC)
-				sleep_time = NSEC_PER_MSEC;
-		}
+		__set_current_state(intr ?
+				    TASK_INTERRUPTIBLE :
+				    TASK_UNINTERRUPTIBLE);
 
 		if (intr && signal_pending(current)) {
 			ret = -ERESTARTSYS;
@@ -281,47 +349,86 @@ nouveau_fence_wait(struct nouveau_fence *fence, bool lazy, bool intr)
 }
 
 int
-nouveau_fence_sync(struct nouveau_fence *fence, struct nouveau_channel *chan)
+nouveau_fence_wait(struct nouveau_fence *fence, bool lazy, bool intr)
 {
-	struct nouveau_fence_chan *fctx = chan->fence;
-	struct nouveau_channel *prev;
-	int ret = 0;
+	long ret;
 
-	prev = fence ? fence->channel : NULL;
-	if (prev) {
-		if (unlikely(prev != chan && !nouveau_fence_done(fence))) {
-			ret = fctx->sync(fence, prev, chan);
-			if (unlikely(ret))
-				ret = nouveau_fence_wait(fence, true, false);
-		}
-	}
+	if (!lazy)
+		return nouveau_fence_wait_busy(fence, intr);
 
-	return ret;
+	ret = fence_wait_timeout(&fence->base, intr, 15 * HZ);
+	if (ret < 0)
+		return ret;
+	else if (!ret)
+		return -EBUSY;
+	else
+		return 0;
 }
 
-static void
-nouveau_fence_del(struct kref *kref)
+int
+nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool exclusive, bool intr)
 {
-	struct nouveau_fence *fence = container_of(kref, typeof(*fence), kref);
-	kfree(fence);
+	struct nouveau_fence_chan *fctx = chan->fence;
+	struct fence *fence;
+	struct reservation_object *resv = nvbo->bo.resv;
+	struct reservation_object_list *fobj;
+	struct nouveau_fence *f;
+	int ret = 0, i;
+
+	if (!exclusive) {
+		ret = reservation_object_reserve_shared(resv);
+
+		if (ret)
+			return ret;
+	}
+
+	fobj = reservation_object_get_list(resv);
+	fence = reservation_object_get_excl(resv);
+
+	if (fence && (!exclusive || !fobj || !fobj->shared_count)) {
+		struct nouveau_channel *prev = NULL;
+
+		f = nouveau_local_fence(fence, chan->drm);
+		if (f)
+			prev = f->channel;
+
+		if (!prev || (prev != chan && (ret = fctx->sync(f, prev, chan))))
+			ret = fence_wait(fence, intr);
+
+		return ret;
+	}
+
+	if (!exclusive || !fobj)
+		return ret;
+
+	for (i = 0; i < fobj->shared_count && !ret; ++i) {
+		struct nouveau_channel *prev = NULL;
+
+		fence = rcu_dereference_protected(fobj->shared[i],
+						reservation_object_held(resv));
+
+		f = nouveau_local_fence(fence, chan->drm);
+		if (f)
+			prev = f->channel;
+
+		if (!prev || (prev != chan && (ret = fctx->sync(f, prev, chan))))
+			ret = fence_wait(fence, intr);
+
+		if (ret)
+			break;
+	}
+
+	return ret;
 }
 
 void
 nouveau_fence_unref(struct nouveau_fence **pfence)
 {
 	if (*pfence)
-		kref_put(&(*pfence)->kref, nouveau_fence_del);
+		fence_put(&(*pfence)->base);
 	*pfence = NULL;
 }
 
-struct nouveau_fence *
-nouveau_fence_ref(struct nouveau_fence *fence)
-{
-	if (fence)
-		kref_get(&fence->kref);
-	return fence;
-}
-
 int
 nouveau_fence_new(struct nouveau_channel *chan, bool sysmem,
 		  struct nouveau_fence **pfence)
@@ -336,9 +443,7 @@ nouveau_fence_new(struct nouveau_channel *chan, bool sysmem,
 	if (!fence)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&fence->work);
 	fence->sysmem = sysmem;
-	kref_init(&fence->kref);
 
 	ret = nouveau_fence_emit(fence, chan);
 	if (ret)
@@ -347,3 +452,101 @@ nouveau_fence_new(struct nouveau_channel *chan, bool sysmem,
 	*pfence = fence;
 	return ret;
 }
+
+static const char *nouveau_fence_get_get_driver_name(struct fence *fence)
+{
+	return "nouveau";
+}
+
+static const char *nouveau_fence_get_timeline_name(struct fence *f)
+{
+	struct nouveau_fence *fence = from_fence(f);
+	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
+
+	return fence->channel ? fctx->name : "dead channel";
+}
+
+/*
+ * In an ideal world, read would not assume the channel context is still alive.
+ * This function may be called from another device, running into free memory as a
+ * result. The drm node should still be there, so we can derive the index from
+ * the fence context.
+ */
+static bool nouveau_fence_is_signaled(struct fence *f)
+{
+	struct nouveau_fence *fence = from_fence(f);
+	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
+	struct nouveau_channel *chan = fence->channel;
+
+	return (int)(fctx->read(chan) - fence->base.seqno) >= 0;
+}
+
+static bool nouveau_fence_no_signaling(struct fence *f)
+{
+	struct nouveau_fence *fence = from_fence(f);
+
+	/*
+	 * caller should have a reference on the fence,
+	 * else fence could get freed here
+	 */
+	WARN_ON(atomic_read(&fence->base.refcount.refcount) <= 1);
+
+	/*
+	 * This needs uevents to work correctly, but fence_add_callback relies on
+	 * being able to enable signaling. It will still get signaled eventually,
+	 * just not right away.
+	 */
+	if (nouveau_fence_is_signaled(f)) {
+		list_del(&fence->head);
+
+		fence_put(&fence->base);
+		return false;
+	}
+
+	return true;
+}
+
+static void nouveau_fence_release(struct fence *f)
+{
+	struct nouveau_fence *fence = from_fence(f);
+	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
+
+	kref_put(&fctx->fence_ref, nouveau_fence_context_put);
+	fence_free(&fence->base);
+}
+
+static const struct fence_ops nouveau_fence_ops_legacy = {
+	.get_driver_name = nouveau_fence_get_get_driver_name,
+	.get_timeline_name = nouveau_fence_get_timeline_name,
+	.enable_signaling = nouveau_fence_no_signaling,
+	.signaled = nouveau_fence_is_signaled,
+	.wait = nouveau_fence_wait_legacy,
+	.release = nouveau_fence_release
+};
+
+static bool nouveau_fence_enable_signaling(struct fence *f)
+{
+	struct nouveau_fence *fence = from_fence(f);
+	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
+	bool ret;
+
+	if (!fctx->notify_ref++)
+		nvif_notify_get(&fctx->notify);
+
+	ret = nouveau_fence_no_signaling(f);
+	if (ret)
+		set_bit(FENCE_FLAG_USER_BITS, &fence->base.flags);
+	else if (!--fctx->notify_ref)
+		nvif_notify_put(&fctx->notify);
+
+	return ret;
+}
+
+static const struct fence_ops nouveau_fence_ops_uevent = {
+	.get_driver_name = nouveau_fence_get_get_driver_name,
+	.get_timeline_name = nouveau_fence_get_timeline_name,
+	.enable_signaling = nouveau_fence_enable_signaling,
+	.signaled = nouveau_fence_is_signaled,
+	.wait = fence_default_wait,
+	.release = NULL
+};
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index c57bb61da58c..943b0b17b1fc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -1,33 +1,37 @@
 #ifndef __NOUVEAU_FENCE_H__
 #define __NOUVEAU_FENCE_H__
 
+#include <linux/fence.h>
+#include <nvif/notify.h>
+
 struct nouveau_drm;
+struct nouveau_bo;
 
 struct nouveau_fence {
+	struct fence base;
+
 	struct list_head head;
-	struct list_head work;
-	struct kref kref;
 
 	bool sysmem;
 
 	struct nouveau_channel *channel;
 	unsigned long timeout;
-	u32 sequence;
 };
 
 int  nouveau_fence_new(struct nouveau_channel *, bool sysmem,
 		       struct nouveau_fence **);
-struct nouveau_fence *
-nouveau_fence_ref(struct nouveau_fence *);
 void nouveau_fence_unref(struct nouveau_fence **);
 
 int  nouveau_fence_emit(struct nouveau_fence *, struct nouveau_channel *);
 bool nouveau_fence_done(struct nouveau_fence *);
-void nouveau_fence_work(struct nouveau_fence *, void (*)(void *), void *);
+void nouveau_fence_work(struct fence *, void (*)(void *), void *);
 int  nouveau_fence_wait(struct nouveau_fence *, bool lazy, bool intr);
-int  nouveau_fence_sync(struct nouveau_fence *, struct nouveau_channel *);
+int  nouveau_fence_sync(struct nouveau_bo *, struct nouveau_channel *, bool exclusive, bool intr);
 
 struct nouveau_fence_chan {
+	spinlock_t lock;
+	struct kref fence_ref;
+
 	struct list_head pending;
 	struct list_head flip;
 
@@ -38,8 +42,12 @@ struct nouveau_fence_chan {
 	int  (*emit32)(struct nouveau_channel *, u64, u32);
 	int  (*sync32)(struct nouveau_channel *, u64, u32);
 
-	spinlock_t lock;
 	u32 sequence;
+	u32 context;
+	char name[32];
+
+	struct nvif_notify notify;
+	int notify_ref;
 };
 
 struct nouveau_fence_priv {
@@ -49,14 +57,15 @@ struct nouveau_fence_priv {
 	int  (*context_new)(struct nouveau_channel *);
 	void (*context_del)(struct nouveau_channel *);
 
-	wait_queue_head_t waiting;
+	u32 contexts, context_base;
 	bool uevent;
 };
 
 #define nouveau_fence(drm) ((struct nouveau_fence_priv *)(drm)->fence)
 
-void nouveau_fence_context_new(struct nouveau_fence_chan *);
+void nouveau_fence_context_new(struct nouveau_channel *, struct nouveau_fence_chan *);
 void nouveau_fence_context_del(struct nouveau_fence_chan *);
+void nouveau_fence_context_free(struct nouveau_fence_chan *);
 
 int nv04_fence_create(struct nouveau_drm *);
 int nv04_fence_mthd(struct nouveau_channel *, u32, u32, u32);
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 292a677bfed4..36951ee4b157 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -98,17 +98,23 @@ static void
 nouveau_gem_object_unmap(struct nouveau_bo *nvbo, struct nouveau_vma *vma)
 {
 	const bool mapped = nvbo->bo.mem.mem_type != TTM_PL_SYSTEM;
-	struct nouveau_fence *fence = NULL;
+	struct reservation_object *resv = nvbo->bo.resv;
+	struct reservation_object_list *fobj;
+	struct fence *fence = NULL;
+
+	fobj = reservation_object_get_list(resv);
 
 	list_del(&vma->head);
 
-	if (mapped) {
-		spin_lock(&nvbo->bo.bdev->fence_lock);
-		fence = nouveau_fence_ref(nvbo->bo.sync_obj);
-		spin_unlock(&nvbo->bo.bdev->fence_lock);
-	}
+	if (fobj && fobj->shared_count > 1)
+		ttm_bo_wait(&nvbo->bo, true, false, false);
+	else if (fobj && fobj->shared_count == 1)
+		fence = rcu_dereference_protected(fobj->shared[0],
+						reservation_object_held(resv));
+	else
+		fence = reservation_object_get_excl(nvbo->bo.resv);
 
-	if (fence) {
+	if (fence && mapped) {
 		nouveau_fence_work(fence, nouveau_gem_object_delete, vma);
 	} else {
 		if (mapped)
@@ -116,7 +122,6 @@ nouveau_gem_object_unmap(struct nouveau_bo *nvbo, struct nouveau_vma *vma)
 		nouveau_vm_put(vma);
 		kfree(vma);
 	}
-	nouveau_fence_unref(&fence);
 }
 
 void
@@ -160,7 +165,7 @@ nouveau_gem_new(struct drm_device *dev, int size, int align, uint32_t domain,
 		flags |= TTM_PL_FLAG_SYSTEM;
 
 	ret = nouveau_bo_new(dev, size, align, flags, tile_mode,
-			     tile_flags, NULL, pnvbo);
+			     tile_flags, NULL, NULL, pnvbo);
 	if (ret)
 		return ret;
 	nvbo = *pnvbo;
@@ -288,24 +293,23 @@ nouveau_gem_set_domain(struct drm_gem_object *gem, uint32_t read_domains,
 }
 
 struct validate_op {
-	struct list_head vram_list;
-	struct list_head gart_list;
-	struct list_head both_list;
+	struct list_head list;
 	struct ww_acquire_ctx ticket;
 };
 
 static void
-validate_fini_list(struct list_head *list, struct nouveau_fence *fence,
-		   struct ww_acquire_ctx *ticket)
+validate_fini_no_ticket(struct validate_op *op, struct nouveau_fence *fence,
+			struct drm_nouveau_gem_pushbuf_bo *pbbo)
 {
-	struct list_head *entry, *tmp;
 	struct nouveau_bo *nvbo;
+	struct drm_nouveau_gem_pushbuf_bo *b;
 
-	list_for_each_safe(entry, tmp, list) {
-		nvbo = list_entry(entry, struct nouveau_bo, entry);
+	while (!list_empty(&op->list)) {
+		nvbo = list_entry(op->list.next, struct nouveau_bo, entry);
+		b = &pbbo[nvbo->pbbo_index];
 
 		if (likely(fence))
-			nouveau_bo_fence(nvbo, fence);
+			nouveau_bo_fence(nvbo, fence, !!b->write_domains);
 
 		if (unlikely(nvbo->validate_mapped)) {
 			ttm_bo_kunmap(&nvbo->kmap);
@@ -314,23 +318,16 @@ validate_fini_list(struct list_head *list, struct nouveau_fence *fence,
 
 		list_del(&nvbo->entry);
 		nvbo->reserved_by = NULL;
-		ttm_bo_unreserve_ticket(&nvbo->bo, ticket);
+		ttm_bo_unreserve_ticket(&nvbo->bo, &op->ticket);
 		drm_gem_object_unreference_unlocked(&nvbo->gem);
 	}
 }
 
 static void
-validate_fini_no_ticket(struct validate_op *op, struct nouveau_fence *fence)
+validate_fini(struct validate_op *op, struct nouveau_fence *fence,
+	      struct drm_nouveau_gem_pushbuf_bo *pbbo)
 {
-	validate_fini_list(&op->vram_list, fence, &op->ticket);
-	validate_fini_list(&op->gart_list, fence, &op->ticket);
-	validate_fini_list(&op->both_list, fence, &op->ticket);
-}
-
-static void
-validate_fini(struct validate_op *op, struct nouveau_fence *fence)
-{
-	validate_fini_no_ticket(op, fence);
+	validate_fini_no_ticket(op, fence, pbbo);
 	ww_acquire_fini(&op->ticket);
 }
 
@@ -344,6 +341,9 @@ validate_init(struct nouveau_channel *chan, struct drm_file *file_priv,
 	int trycnt = 0;
 	int ret, i;
 	struct nouveau_bo *res_bo = NULL;
+	LIST_HEAD(gart_list);
+	LIST_HEAD(vram_list);
+	LIST_HEAD(both_list);
 
 	ww_acquire_init(&op->ticket, &reservation_ww_class);
 retry:
@@ -360,9 +360,8 @@ retry:
 		gem = drm_gem_object_lookup(dev, file_priv, b->handle);
 		if (!gem) {
 			NV_PRINTK(error, cli, "Unknown handle 0x%08x\n", b->handle);
-			ww_acquire_done(&op->ticket);
-			validate_fini(op, NULL);
-			return -ENOENT;
+			ret = -ENOENT;
+			break;
 		}
 		nvbo = nouveau_gem_object(gem);
 		if (nvbo == res_bo) {
@@ -375,14 +374,16 @@ retry:
 			NV_PRINTK(error, cli, "multiple instances of buffer %d on "
 				      "validation list\n", b->handle);
 			drm_gem_object_unreference_unlocked(gem);
-			ww_acquire_done(&op->ticket);
-			validate_fini(op, NULL);
-			return -EINVAL;
+			ret = -EINVAL;
+			break;
 		}
 
 		ret = ttm_bo_reserve(&nvbo->bo, true, false, true, &op->ticket);
 		if (ret) {
-			validate_fini_no_ticket(op, NULL);
+			list_splice_tail_init(&vram_list, &op->list);
+			list_splice_tail_init(&gart_list, &op->list);
+			list_splice_tail_init(&both_list, &op->list);
+			validate_fini_no_ticket(op, NULL, NULL);
 			if (unlikely(ret == -EDEADLK)) {
 				ret = ttm_bo_reserve_slowpath(&nvbo->bo, true,
 							      &op->ticket);
@@ -390,12 +391,9 @@ retry:
 					res_bo = nvbo;
 			}
 			if (unlikely(ret)) {
-				ww_acquire_done(&op->ticket);
-				ww_acquire_fini(&op->ticket);
-				drm_gem_object_unreference_unlocked(gem);
 				if (ret != -ERESTARTSYS)
 					NV_PRINTK(error, cli, "fail reserve\n");
-				return ret;
+				break;
 			}
 		}
 
@@ -404,45 +402,32 @@ retry:
 		nvbo->pbbo_index = i;
 		if ((b->valid_domains & NOUVEAU_GEM_DOMAIN_VRAM) &&
 		    (b->valid_domains & NOUVEAU_GEM_DOMAIN_GART))
-			list_add_tail(&nvbo->entry, &op->both_list);
+			list_add_tail(&nvbo->entry, &both_list);
 		else
 		if (b->valid_domains & NOUVEAU_GEM_DOMAIN_VRAM)
-			list_add_tail(&nvbo->entry, &op->vram_list);
+			list_add_tail(&nvbo->entry, &vram_list);
 		else
 		if (b->valid_domains & NOUVEAU_GEM_DOMAIN_GART)
-			list_add_tail(&nvbo->entry, &op->gart_list);
+			list_add_tail(&nvbo->entry, &gart_list);
 		else {
 			NV_PRINTK(error, cli, "invalid valid domains: 0x%08x\n",
 				 b->valid_domains);
-			list_add_tail(&nvbo->entry, &op->both_list);
-			ww_acquire_done(&op->ticket);
-			validate_fini(op, NULL);
-			return -EINVAL;
+			list_add_tail(&nvbo->entry, &both_list);
+			ret = -EINVAL;
+			break;
 		}
 		if (nvbo == res_bo)
 			goto retry;
 	}
 
 	ww_acquire_done(&op->ticket);
-	return 0;
-}
-
-static int
-validate_sync(struct nouveau_channel *chan, struct nouveau_bo *nvbo)
-{
-	struct nouveau_fence *fence = NULL;
-	int ret = 0;
-
-	spin_lock(&nvbo->bo.bdev->fence_lock);
-	fence = nouveau_fence_ref(nvbo->bo.sync_obj);
-	spin_unlock(&nvbo->bo.bdev->fence_lock);
-
-	if (fence) {
-		ret = nouveau_fence_sync(fence, chan);
-		nouveau_fence_unref(&fence);
-	}
-
+	list_splice_tail(&vram_list, &op->list);
+	list_splice_tail(&gart_list, &op->list);
+	list_splice_tail(&both_list, &op->list);
+	if (ret)
+		validate_fini(op, NULL, NULL);
 	return ret;
+
 }
 
 static int
@@ -474,9 +459,10 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli,
 			return ret;
 		}
 
-		ret = validate_sync(chan, nvbo);
+		ret = nouveau_fence_sync(nvbo, chan, !!b->write_domains, true);
 		if (unlikely(ret)) {
-			NV_PRINTK(error, cli, "fail post-validate sync\n");
+			if (ret != -ERESTARTSYS)
+				NV_PRINTK(error, cli, "fail post-validate sync\n");
 			return ret;
 		}
 
@@ -513,11 +499,9 @@ nouveau_gem_pushbuf_validate(struct nouveau_channel *chan,
 			     struct validate_op *op, int *apply_relocs)
 {
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
-	int ret, relocs = 0;
+	int ret;
 
-	INIT_LIST_HEAD(&op->vram_list);
-	INIT_LIST_HEAD(&op->gart_list);
-	INIT_LIST_HEAD(&op->both_list);
+	INIT_LIST_HEAD(&op->list);
 
 	if (nr_buffers == 0)
 		return 0;
@@ -529,34 +513,14 @@ nouveau_gem_pushbuf_validate(struct nouveau_channel *chan,
 		return ret;
 	}
 
-	ret = validate_list(chan, cli, &op->vram_list, pbbo, user_buffers);
-	if (unlikely(ret < 0)) {
-		if (ret != -ERESTARTSYS)
-			NV_PRINTK(error, cli, "validate vram_list\n");
-		validate_fini(op, NULL);
-		return ret;
-	}
-	relocs += ret;
-
-	ret = validate_list(chan, cli, &op->gart_list, pbbo, user_buffers);
-	if (unlikely(ret < 0)) {
-		if (ret != -ERESTARTSYS)
-			NV_PRINTK(error, cli, "validate gart_list\n");
-		validate_fini(op, NULL);
-		return ret;
-	}
-	relocs += ret;
-
-	ret = validate_list(chan, cli, &op->both_list, pbbo, user_buffers);
+	ret = validate_list(chan, cli, &op->list, pbbo, user_buffers);
 	if (unlikely(ret < 0)) {
 		if (ret != -ERESTARTSYS)
-			NV_PRINTK(error, cli, "validate both_list\n");
-		validate_fini(op, NULL);
+			NV_PRINTK(error, cli, "validating bo list\n");
+		validate_fini(op, NULL, NULL);
 		return ret;
 	}
-	relocs += ret;
-
-	*apply_relocs = relocs;
+	*apply_relocs = ret;
 	return 0;
 }
 
@@ -659,9 +623,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 				data |= r->vor;
 		}
 
-		spin_lock(&nvbo->bo.bdev->fence_lock);
-		ret = ttm_bo_wait(&nvbo->bo, false, false, false);
-		spin_unlock(&nvbo->bo.bdev->fence_lock);
+		ret = ttm_bo_wait(&nvbo->bo, true, false, false);
 		if (ret) {
 			NV_PRINTK(error, cli, "reloc wait_idle failed: %d\n", ret);
 			break;
@@ -839,7 +801,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 	}
 
 out:
-	validate_fini(&op, fence);
+	validate_fini(&op, fence, bo);
 	nouveau_fence_unref(&fence);
 
 out_prevalid:
@@ -884,17 +846,29 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data,
 	struct drm_gem_object *gem;
 	struct nouveau_bo *nvbo;
 	bool no_wait = !!(req->flags & NOUVEAU_GEM_CPU_PREP_NOWAIT);
-	int ret = -EINVAL;
+	bool write = !!(req->flags & NOUVEAU_GEM_CPU_PREP_WRITE);
+	int ret;
 
 	gem = drm_gem_object_lookup(dev, file_priv, req->handle);
 	if (!gem)
 		return -ENOENT;
 	nvbo = nouveau_gem_object(gem);
 
-	spin_lock(&nvbo->bo.bdev->fence_lock);
-	ret = ttm_bo_wait(&nvbo->bo, true, true, no_wait);
-	spin_unlock(&nvbo->bo.bdev->fence_lock);
+	if (no_wait)
+		ret = reservation_object_test_signaled_rcu(nvbo->bo.resv, write) ? 0 : -EBUSY;
+	else {
+		long lret;
+
+		lret = reservation_object_wait_timeout_rcu(nvbo->bo.resv, write, true, 30 * HZ);
+		if (!lret)
+			ret = -EBUSY;
+		else if (lret > 0)
+			ret = 0;
+		else
+			ret = lret;
+	}
 	drm_gem_object_unreference_unlocked(gem);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.h b/drivers/gpu/drm/nouveau/nouveau_gem.h
index ddab762d81fe..e4049faca780 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.h
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.h
@@ -39,7 +39,7 @@ struct reservation_object *nouveau_gem_prime_res_obj(struct drm_gem_object *);
 extern void nouveau_gem_prime_unpin(struct drm_gem_object *);
 extern struct sg_table *nouveau_gem_prime_get_sg_table(struct drm_gem_object *);
 extern struct drm_gem_object *nouveau_gem_prime_import_sg_table(
-	struct drm_device *, size_t size, struct sg_table *);
+	struct drm_device *, struct dma_buf_attachment *, struct sg_table *);
 extern void *nouveau_gem_prime_vmap(struct drm_gem_object *);
 extern void nouveau_gem_prime_vunmap(struct drm_gem_object *, void *);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_nvif.c b/drivers/gpu/drm/nouveau/nouveau_nvif.c
index 47ca88623753..6544b84f0303 100644
--- a/drivers/gpu/drm/nouveau/nouveau_nvif.c
+++ b/drivers/gpu/drm/nouveau/nouveau_nvif.c
@@ -40,12 +40,12 @@
 #include "nouveau_usif.h"
 
 static void
-nvkm_client_unmap(void *priv, void *ptr, u32 size)
+nvkm_client_unmap(void *priv, void __iomem *ptr, u32 size)
 {
 	iounmap(ptr);
 }
 
-static void *
+static void __iomem *
 nvkm_client_map(void *priv, u64 handle, u32 size)
 {
 	return ioremap(handle, size);
diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c
index 1f51008e4d26..228226ab27fc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_prime.c
+++ b/drivers/gpu/drm/nouveau/nouveau_prime.c
@@ -23,6 +23,7 @@
  */
 
 #include <drm/drmP.h>
+#include <linux/dma-buf.h>
 
 #include "nouveau_drm.h"
 #include "nouveau_gem.h"
@@ -56,17 +57,20 @@ void nouveau_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 }
 
 struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev,
-							 size_t size,
+							 struct dma_buf_attachment *attach,
 							 struct sg_table *sg)
 {
 	struct nouveau_bo *nvbo;
+	struct reservation_object *robj = attach->dmabuf->resv;
 	u32 flags = 0;
 	int ret;
 
 	flags = TTM_PL_FLAG_TT;
 
-	ret = nouveau_bo_new(dev, size, 0, flags, 0, 0,
-			     sg, &nvbo);
+	ww_mutex_lock(&robj->lock, NULL);
+	ret = nouveau_bo_new(dev, attach->dmabuf->size, 0, flags, 0, 0,
+			     sg, robj, &nvbo);
+	ww_mutex_unlock(&robj->lock);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_sysfs.c b/drivers/gpu/drm/nouveau/nouveau_sysfs.c
index 3c6962d15b26..8fbbf3093d86 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sysfs.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sysfs.c
@@ -29,7 +29,7 @@
 #include "nouveau_sysfs.h"
 
 MODULE_PARM_DESC(pstate, "enable sysfs pstate file, which will be moved in the future");
-static int nouveau_pstate;
+int nouveau_pstate;
 module_param_named(pstate, nouveau_pstate, int, 0400);
 
 static inline struct drm_device *
diff --git a/drivers/gpu/drm/nouveau/nouveau_sysfs.h b/drivers/gpu/drm/nouveau/nouveau_sysfs.h
index f973378160f8..4e5ea9241b28 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sysfs.h
+++ b/drivers/gpu/drm/nouveau/nouveau_sysfs.h
@@ -16,4 +16,6 @@ nouveau_sysfs(struct drm_device *dev)
 int  nouveau_sysfs_init(struct drm_device *);
 void nouveau_sysfs_fini(struct drm_device *);
 
+extern int nouveau_pstate;
+
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 53874b76b031..753a6def61e7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -71,8 +71,7 @@ nouveau_vram_manager_del(struct ttm_mem_type_manager *man,
 static int
 nouveau_vram_manager_new(struct ttm_mem_type_manager *man,
 			 struct ttm_buffer_object *bo,
-			 struct ttm_placement *placement,
-			 uint32_t flags,
+			 const struct ttm_place *place,
 			 struct ttm_mem_reg *mem)
 {
 	struct nouveau_drm *drm = nouveau_bdev(man->bdev);
@@ -158,8 +157,7 @@ nouveau_gart_manager_del(struct ttm_mem_type_manager *man,
 static int
 nouveau_gart_manager_new(struct ttm_mem_type_manager *man,
 			 struct ttm_buffer_object *bo,
-			 struct ttm_placement *placement,
-			 uint32_t flags,
+			 const struct ttm_place *place,
 			 struct ttm_mem_reg *mem)
 {
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
@@ -239,8 +237,7 @@ nv04_gart_manager_del(struct ttm_mem_type_manager *man, struct ttm_mem_reg *mem)
 static int
 nv04_gart_manager_new(struct ttm_mem_type_manager *man,
 		      struct ttm_buffer_object *bo,
-		      struct ttm_placement *placement,
-		      uint32_t flags,
+		      const struct ttm_place *place,
 		      struct ttm_mem_reg *mem)
 {
 	struct nouveau_mem *node;
@@ -284,7 +281,7 @@ nouveau_ttm_mmap(struct file *filp, struct vm_area_struct *vma)
 	struct nouveau_drm *drm = nouveau_drm(file_priv->minor->dev);
 
 	if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET))
-		return drm_mmap(filp, vma);
+		return -EINVAL;
 
 	return ttm_bo_mmap(filp, vma, &drm->ttm.bdev);
 }
diff --git a/drivers/gpu/drm/nouveau/nv04_fence.c b/drivers/gpu/drm/nouveau/nv04_fence.c
index 239c2c5a9615..f9859deb108a 100644
--- a/drivers/gpu/drm/nouveau/nv04_fence.c
+++ b/drivers/gpu/drm/nouveau/nv04_fence.c
@@ -41,7 +41,7 @@ nv04_fence_emit(struct nouveau_fence *fence)
 	int ret = RING_SPACE(chan, 2);
 	if (ret == 0) {
 		BEGIN_NV04(chan, NvSubSw, 0x0150, 1);
-		OUT_RING  (chan, fence->sequence);
+		OUT_RING  (chan, fence->base.seqno);
 		FIRE_RING (chan);
 	}
 	return ret;
@@ -67,7 +67,7 @@ nv04_fence_context_del(struct nouveau_channel *chan)
 	struct nv04_fence_chan *fctx = chan->fence;
 	nouveau_fence_context_del(&fctx->base);
 	chan->fence = NULL;
-	kfree(fctx);
+	nouveau_fence_context_free(&fctx->base);
 }
 
 static int
@@ -75,7 +75,7 @@ nv04_fence_context_new(struct nouveau_channel *chan)
 {
 	struct nv04_fence_chan *fctx = kzalloc(sizeof(*fctx), GFP_KERNEL);
 	if (fctx) {
-		nouveau_fence_context_new(&fctx->base);
+		nouveau_fence_context_new(chan, &fctx->base);
 		fctx->base.emit = nv04_fence_emit;
 		fctx->base.sync = nv04_fence_sync;
 		fctx->base.read = nv04_fence_read;
@@ -105,5 +105,7 @@ nv04_fence_create(struct nouveau_drm *drm)
 	priv->base.dtor = nv04_fence_destroy;
 	priv->base.context_new = nv04_fence_context_new;
 	priv->base.context_del = nv04_fence_context_del;
+	priv->base.contexts = 15;
+	priv->base.context_base = fence_context_alloc(priv->base.contexts);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nv10_fence.c b/drivers/gpu/drm/nouveau/nv10_fence.c
index 4faaf0acf5d7..5e1ea1cdce75 100644
--- a/drivers/gpu/drm/nouveau/nv10_fence.c
+++ b/drivers/gpu/drm/nouveau/nv10_fence.c
@@ -33,7 +33,7 @@ nv10_fence_emit(struct nouveau_fence *fence)
 	int ret = RING_SPACE(chan, 2);
 	if (ret == 0) {
 		BEGIN_NV04(chan, 0, NV10_SUBCHAN_REF_CNT, 1);
-		OUT_RING  (chan, fence->sequence);
+		OUT_RING  (chan, fence->base.seqno);
 		FIRE_RING (chan);
 	}
 	return ret;
@@ -63,7 +63,7 @@ nv10_fence_context_del(struct nouveau_channel *chan)
 		nvif_object_fini(&fctx->head[i]);
 	nvif_object_fini(&fctx->sema);
 	chan->fence = NULL;
-	kfree(fctx);
+	nouveau_fence_context_free(&fctx->base);
 }
 
 int
@@ -75,7 +75,7 @@ nv10_fence_context_new(struct nouveau_channel *chan)
 	if (!fctx)
 		return -ENOMEM;
 
-	nouveau_fence_context_new(&fctx->base);
+	nouveau_fence_context_new(chan, &fctx->base);
 	fctx->base.emit = nv10_fence_emit;
 	fctx->base.read = nv10_fence_read;
 	fctx->base.sync = nv10_fence_sync;
@@ -106,6 +106,8 @@ nv10_fence_create(struct nouveau_drm *drm)
 	priv->base.dtor = nv10_fence_destroy;
 	priv->base.context_new = nv10_fence_context_new;
 	priv->base.context_del = nv10_fence_context_del;
+	priv->base.contexts = 31;
+	priv->base.context_base = fence_context_alloc(priv->base.contexts);
 	spin_lock_init(&priv->lock);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nv17_fence.c b/drivers/gpu/drm/nouveau/nv17_fence.c
index ca907479f92f..40b461c7d5c5 100644
--- a/drivers/gpu/drm/nouveau/nv17_fence.c
+++ b/drivers/gpu/drm/nouveau/nv17_fence.c
@@ -84,7 +84,7 @@ nv17_fence_context_new(struct nouveau_channel *chan)
 	if (!fctx)
 		return -ENOMEM;
 
-	nouveau_fence_context_new(&fctx->base);
+	nouveau_fence_context_new(chan, &fctx->base);
 	fctx->base.emit = nv10_fence_emit;
 	fctx->base.read = nv10_fence_read;
 	fctx->base.sync = nv17_fence_sync;
@@ -124,10 +124,12 @@ nv17_fence_create(struct nouveau_drm *drm)
 	priv->base.resume = nv17_fence_resume;
 	priv->base.context_new = nv17_fence_context_new;
 	priv->base.context_del = nv10_fence_context_del;
+	priv->base.contexts = 31;
+	priv->base.context_base = fence_context_alloc(priv->base.contexts);
 	spin_lock_init(&priv->lock);
 
 	ret = nouveau_bo_new(drm->dev, 4096, 0x1000, TTM_PL_FLAG_VRAM,
-			     0, 0x0000, NULL, &priv->bo);
+			     0, 0x0000, NULL, NULL, &priv->bo);
 	if (!ret) {
 		ret = nouveau_bo_pin(priv->bo, TTM_PL_FLAG_VRAM);
 		if (!ret) {
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 03949eaa629f..ae873d1a8d46 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -1066,7 +1066,7 @@ nv50_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *umode,
 	u32 vscan = (mode->flags & DRM_MODE_FLAG_DBLSCAN) ? 2 : 1;
 	u32 hactive, hsynce, hbackp, hfrontp, hblanke, hblanks;
 	u32 vactive, vsynce, vbackp, vfrontp, vblanke, vblanks;
-	u32 vblan2e = 0, vblan2s = 1;
+	u32 vblan2e = 0, vblan2s = 1, vblankus = 0;
 	u32 *push;
 	int ret;
 
@@ -1083,6 +1083,11 @@ nv50_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *umode,
 	vblanke = vsynce + vbackp;
 	vfrontp = (mode->vsync_start - mode->vdisplay) * vscan / ilace;
 	vblanks = vactive - vfrontp - 1;
+	/* XXX: Safe underestimate, even "0" works */
+	vblankus = (vactive - mode->vdisplay - 2) * hactive;
+	vblankus *= 1000;
+	vblankus /= mode->clock;
+
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
 		vblan2e = vactive + vsynce + vbackp;
 		vblan2s = vblan2e + (mode->vdisplay * vscan / ilace);
@@ -1099,14 +1104,14 @@ nv50_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *umode,
 			evo_mthd(push, 0x0804 + (nv_crtc->index * 0x400), 2);
 			evo_data(push, 0x00800000 | mode->clock);
 			evo_data(push, (ilace == 2) ? 2 : 0);
-			evo_mthd(push, 0x0810 + (nv_crtc->index * 0x400), 6);
+			evo_mthd(push, 0x0810 + (nv_crtc->index * 0x400), 8);
 			evo_data(push, 0x00000000);
 			evo_data(push, (vactive << 16) | hactive);
 			evo_data(push, ( vsynce << 16) | hsynce);
 			evo_data(push, (vblanke << 16) | hblanke);
 			evo_data(push, (vblanks << 16) | hblanks);
 			evo_data(push, (vblan2e << 16) | vblan2s);
-			evo_mthd(push, 0x082c + (nv_crtc->index * 0x400), 1);
+			evo_data(push, vblankus);
 			evo_data(push, 0x00000000);
 			evo_mthd(push, 0x0900 + (nv_crtc->index * 0x400), 2);
 			evo_data(push, 0x00000311);
@@ -1378,7 +1383,7 @@ nv50_crtc_create(struct drm_device *dev, int index)
 	drm_mode_crtc_set_gamma_size(crtc, 256);
 
 	ret = nouveau_bo_new(dev, 8192, 0x100, TTM_PL_FLAG_VRAM,
-			     0, 0x0000, NULL, &head->base.lut.nvbo);
+			     0, 0x0000, NULL, NULL, &head->base.lut.nvbo);
 	if (!ret) {
 		ret = nouveau_bo_pin(head->base.lut.nvbo, TTM_PL_FLAG_VRAM);
 		if (!ret) {
@@ -1401,7 +1406,7 @@ nv50_crtc_create(struct drm_device *dev, int index)
 		goto out;
 
 	ret = nouveau_bo_new(dev, 64 * 64 * 4, 0x100, TTM_PL_FLAG_VRAM,
-			     0, 0x0000, NULL, &head->base.cursor.nvbo);
+			     0, 0x0000, NULL, NULL, &head->base.cursor.nvbo);
 	if (!ret) {
 		ret = nouveau_bo_pin(head->base.cursor.nvbo, TTM_PL_FLAG_VRAM);
 		if (!ret) {
@@ -1651,17 +1656,21 @@ static void
 nv50_audio_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
 	struct nouveau_connector *nv_connector;
 	struct nv50_disp *disp = nv50_disp(encoder->dev);
-	struct {
-		struct nv50_disp_mthd_v1 base;
-		struct nv50_disp_sor_hda_eld_v0 eld;
+	struct __packed {
+		struct {
+			struct nv50_disp_mthd_v1 mthd;
+			struct nv50_disp_sor_hda_eld_v0 eld;
+		} base;
 		u8 data[sizeof(nv_connector->base.eld)];
 	} args = {
-		.base.version = 1,
-		.base.method  = NV50_DISP_MTHD_V1_SOR_HDA_ELD,
-		.base.hasht   = nv_encoder->dcb->hasht,
-		.base.hashm   = nv_encoder->dcb->hashm,
+		.base.mthd.version = 1,
+		.base.mthd.method  = NV50_DISP_MTHD_V1_SOR_HDA_ELD,
+		.base.mthd.hasht   = nv_encoder->dcb->hasht,
+		.base.mthd.hashm   = (0xf0ff & nv_encoder->dcb->hashm) |
+				     (0x0100 << nv_crtc->index),
 	};
 
 	nv_connector = nouveau_encoder_connector_get(nv_encoder);
@@ -1671,11 +1680,11 @@ nv50_audio_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode)
 	drm_edid_to_eld(&nv_connector->base, nv_connector->edid);
 	memcpy(args.data, nv_connector->base.eld, sizeof(args.data));
 
-	nvif_mthd(disp->disp, 0, &args, sizeof(args));
+	nvif_mthd(disp->disp, 0, &args, sizeof(args.base) + args.data[2] * 4);
 }
 
 static void
-nv50_audio_disconnect(struct drm_encoder *encoder)
+nv50_audio_disconnect(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nv50_disp *disp = nv50_disp(encoder->dev);
@@ -1686,7 +1695,8 @@ nv50_audio_disconnect(struct drm_encoder *encoder)
 		.base.version = 1,
 		.base.method  = NV50_DISP_MTHD_V1_SOR_HDA_ELD,
 		.base.hasht   = nv_encoder->dcb->hasht,
-		.base.hashm   = nv_encoder->dcb->hashm,
+		.base.hashm   = (0xf0ff & nv_encoder->dcb->hashm) |
+				(0x0100 << nv_crtc->index),
 	};
 
 	nvif_mthd(disp->disp, 0, &args, sizeof(args));
@@ -1745,8 +1755,6 @@ nv50_hdmi_disconnect(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
 			       (0x0100 << nv_crtc->index),
 	};
 
-	nv50_audio_disconnect(encoder);
-
 	nvif_mthd(disp->disp, 0, &args, sizeof(args));
 }
 
@@ -1855,6 +1863,7 @@ nv50_sor_disconnect(struct drm_encoder *encoder)
 	if (nv_crtc) {
 		nv50_crtc_prepare(&nv_crtc->base);
 		nv50_sor_ctrl(nv_encoder, 1 << nv_crtc->index, 0);
+		nv50_audio_disconnect(encoder, nv_crtc);
 		nv50_hdmi_disconnect(&nv_encoder->base.base, nv_crtc);
 	}
 }
@@ -1954,6 +1963,7 @@ nv50_sor_mode_set(struct drm_encoder *encoder, struct drm_display_mode *umode,
 			proto = 0x8;
 		else
 			proto = 0x9;
+		nv50_audio_mode_set(encoder, mode);
 		break;
 	default:
 		BUG_ON(1);
@@ -2458,7 +2468,7 @@ nv50_display_create(struct drm_device *dev)
 
 	/* small shared memory area we use for notifiers and semaphores */
 	ret = nouveau_bo_new(dev, 4096, 0x1000, TTM_PL_FLAG_VRAM,
-			     0, 0x0000, NULL, &disp->sync);
+			     0, 0x0000, NULL, NULL, &disp->sync);
 	if (!ret) {
 		ret = nouveau_bo_pin(disp->sync, TTM_PL_FLAG_VRAM);
 		if (!ret) {
diff --git a/drivers/gpu/drm/nouveau/nv50_fence.c b/drivers/gpu/drm/nouveau/nv50_fence.c
index 195cf51a7c31..22d242b37962 100644
--- a/drivers/gpu/drm/nouveau/nv50_fence.c
+++ b/drivers/gpu/drm/nouveau/nv50_fence.c
@@ -46,7 +46,7 @@ nv50_fence_context_new(struct nouveau_channel *chan)
 	if (!fctx)
 		return -ENOMEM;
 
-	nouveau_fence_context_new(&fctx->base);
+	nouveau_fence_context_new(chan, &fctx->base);
 	fctx->base.emit = nv10_fence_emit;
 	fctx->base.read = nv10_fence_read;
 	fctx->base.sync = nv17_fence_sync;
@@ -95,10 +95,12 @@ nv50_fence_create(struct nouveau_drm *drm)
 	priv->base.resume = nv17_fence_resume;
 	priv->base.context_new = nv50_fence_context_new;
 	priv->base.context_del = nv10_fence_context_del;
+	priv->base.contexts = 127;
+	priv->base.context_base = fence_context_alloc(priv->base.contexts);
 	spin_lock_init(&priv->lock);
 
 	ret = nouveau_bo_new(drm->dev, 4096, 0x1000, TTM_PL_FLAG_VRAM,
-			     0, 0x0000, NULL, &priv->bo);
+			     0, 0x0000, NULL, NULL, &priv->bo);
 	if (!ret) {
 		ret = nouveau_bo_pin(priv->bo, TTM_PL_FLAG_VRAM);
 		if (!ret) {
diff --git a/drivers/gpu/drm/nouveau/nv84_fence.c b/drivers/gpu/drm/nouveau/nv84_fence.c
index 933a779c93ab..d6c6c87c3f07 100644
--- a/drivers/gpu/drm/nouveau/nv84_fence.c
+++ b/drivers/gpu/drm/nouveau/nv84_fence.c
@@ -82,7 +82,7 @@ nv84_fence_emit(struct nouveau_fence *fence)
 	else
 		addr += fctx->vma.offset;
 
-	return fctx->base.emit32(chan, addr, fence->sequence);
+	return fctx->base.emit32(chan, addr, fence->base.seqno);
 }
 
 static int
@@ -97,7 +97,7 @@ nv84_fence_sync(struct nouveau_fence *fence,
 	else
 		addr += fctx->vma.offset;
 
-	return fctx->base.sync32(chan, addr, fence->sequence);
+	return fctx->base.sync32(chan, addr, fence->base.seqno);
 }
 
 static u32
@@ -120,11 +120,12 @@ nv84_fence_context_del(struct nouveau_channel *chan)
 		nouveau_bo_vma_del(bo, &fctx->dispc_vma[i]);
 	}
 
+	nouveau_bo_wr32(priv->bo, chan->chid * 16 / 4, fctx->base.sequence);
 	nouveau_bo_vma_del(priv->bo, &fctx->vma_gart);
 	nouveau_bo_vma_del(priv->bo, &fctx->vma);
 	nouveau_fence_context_del(&fctx->base);
 	chan->fence = NULL;
-	kfree(fctx);
+	nouveau_fence_context_free(&fctx->base);
 }
 
 int
@@ -139,12 +140,13 @@ nv84_fence_context_new(struct nouveau_channel *chan)
 	if (!fctx)
 		return -ENOMEM;
 
-	nouveau_fence_context_new(&fctx->base);
+	nouveau_fence_context_new(chan, &fctx->base);
 	fctx->base.emit = nv84_fence_emit;
 	fctx->base.sync = nv84_fence_sync;
 	fctx->base.read = nv84_fence_read;
 	fctx->base.emit32 = nv84_fence_emit32;
 	fctx->base.sync32 = nv84_fence_sync32;
+	fctx->base.sequence = nv84_fence_read(chan);
 
 	ret = nouveau_bo_vma_add(priv->bo, cli->vm, &fctx->vma);
 	if (ret == 0) {
@@ -158,8 +160,6 @@ nv84_fence_context_new(struct nouveau_channel *chan)
 		ret = nouveau_bo_vma_add(bo, cli->vm, &fctx->dispc_vma[i]);
 	}
 
-	nouveau_bo_wr32(priv->bo, chan->chid * 16/4, 0x00000000);
-
 	if (ret)
 		nv84_fence_context_del(chan);
 	return ret;
@@ -168,13 +168,12 @@ nv84_fence_context_new(struct nouveau_channel *chan)
 static bool
 nv84_fence_suspend(struct nouveau_drm *drm)
 {
-	struct nouveau_fifo *pfifo = nvkm_fifo(&drm->device);
 	struct nv84_fence_priv *priv = drm->fence;
 	int i;
 
-	priv->suspend = vmalloc((pfifo->max + 1) * sizeof(u32));
+	priv->suspend = vmalloc(priv->base.contexts * sizeof(u32));
 	if (priv->suspend) {
-		for (i = 0; i <= pfifo->max; i++)
+		for (i = 0; i < priv->base.contexts; i++)
 			priv->suspend[i] = nouveau_bo_rd32(priv->bo, i*4);
 	}
 
@@ -184,12 +183,11 @@ nv84_fence_suspend(struct nouveau_drm *drm)
 static void
 nv84_fence_resume(struct nouveau_drm *drm)
 {
-	struct nouveau_fifo *pfifo = nvkm_fifo(&drm->device);
 	struct nv84_fence_priv *priv = drm->fence;
 	int i;
 
 	if (priv->suspend) {
-		for (i = 0; i <= pfifo->max; i++)
+		for (i = 0; i < priv->base.contexts; i++)
 			nouveau_bo_wr32(priv->bo, i*4, priv->suspend[i]);
 		vfree(priv->suspend);
 		priv->suspend = NULL;
@@ -229,11 +227,12 @@ nv84_fence_create(struct nouveau_drm *drm)
 	priv->base.context_new = nv84_fence_context_new;
 	priv->base.context_del = nv84_fence_context_del;
 
-	init_waitqueue_head(&priv->base.waiting);
+	priv->base.contexts = pfifo->max + 1;
+	priv->base.context_base = fence_context_alloc(priv->base.contexts);
 	priv->base.uevent = true;
 
-	ret = nouveau_bo_new(drm->dev, 16 * (pfifo->max + 1), 0,
-			     TTM_PL_FLAG_VRAM, 0, 0, NULL, &priv->bo);
+	ret = nouveau_bo_new(drm->dev, 16 * priv->base.contexts, 0,
+			     TTM_PL_FLAG_VRAM, 0, 0, NULL, NULL, &priv->bo);
 	if (ret == 0) {
 		ret = nouveau_bo_pin(priv->bo, TTM_PL_FLAG_VRAM);
 		if (ret == 0) {
@@ -246,8 +245,8 @@ nv84_fence_create(struct nouveau_drm *drm)
 	}
 
 	if (ret == 0)
-		ret = nouveau_bo_new(drm->dev, 16 * (pfifo->max + 1), 0,
-				     TTM_PL_FLAG_TT, 0, 0, NULL,
+		ret = nouveau_bo_new(drm->dev, 16 * priv->base.contexts, 0,
+				     TTM_PL_FLAG_TT, 0, 0, NULL, NULL,
 				     &priv->bo_gart);
 	if (ret == 0) {
 		ret = nouveau_bo_pin(priv->bo_gart, TTM_PL_FLAG_TT);
diff --git a/drivers/gpu/drm/nouveau/nvif/class.h b/drivers/gpu/drm/nouveau/nvif/class.h
index 573491f84792..e5a27df0672b 100644
--- a/drivers/gpu/drm/nouveau/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/nvif/class.h
@@ -479,6 +479,8 @@ struct nv50_disp_core_channel_dma_v0 {
 	__u32 pushbuf;
 };
 
+#define NV50_DISP_CORE_CHANNEL_DMA_V0_NTFY_UEVENT                          0x00
+
 /* cursor immediate */
 struct nv50_disp_cursor_v0 {
 	__u8  version;
@@ -486,6 +488,8 @@ struct nv50_disp_cursor_v0 {
 	__u8  pad02[6];
 };
 
+#define NV50_DISP_CURSOR_V0_NTFY_UEVENT                                    0x00
+
 /* base */
 struct nv50_disp_base_channel_dma_v0 {
 	__u8  version;
@@ -494,6 +498,8 @@ struct nv50_disp_base_channel_dma_v0 {
 	__u32 pushbuf;
 };
 
+#define NV50_DISP_BASE_CHANNEL_DMA_V0_NTFY_UEVENT                          0x00
+
 /* overlay */
 struct nv50_disp_overlay_channel_dma_v0 {
 	__u8  version;
@@ -502,6 +508,8 @@ struct nv50_disp_overlay_channel_dma_v0 {
 	__u32 pushbuf;
 };
 
+#define NV50_DISP_OVERLAY_CHANNEL_DMA_V0_NTFY_UEVENT                       0x00
+
 /* overlay immediate */
 struct nv50_disp_overlay_v0 {
 	__u8  version;
@@ -509,6 +517,7 @@ struct nv50_disp_overlay_v0 {
 	__u8  pad02[6];
 };
 
+#define NV50_DISP_OVERLAY_V0_NTFY_UEVENT                                   0x00
 
 /*******************************************************************************
  * fermi
diff --git a/drivers/gpu/drm/nouveau/nvif/driver.h b/drivers/gpu/drm/nouveau/nvif/driver.h
index b72a8f0c2758..ac4bdb3ea506 100644
--- a/drivers/gpu/drm/nouveau/nvif/driver.h
+++ b/drivers/gpu/drm/nouveau/nvif/driver.h
@@ -9,8 +9,8 @@ struct nvif_driver {
 	int (*suspend)(void *priv);
 	int (*resume)(void *priv);
 	int (*ioctl)(void *priv, bool super, void *data, u32 size, void **hack);
-	void *(*map)(void *priv, u64 handle, u32 size);
-	void (*unmap)(void *priv, void *ptr, u32 size);
+	void __iomem *(*map)(void *priv, u64 handle, u32 size);
+	void (*unmap)(void *priv, void __iomem *ptr, u32 size);
 	bool keep;
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvif/object.h b/drivers/gpu/drm/nouveau/nvif/object.h
index fac3a3bbec44..fe519179b76c 100644
--- a/drivers/gpu/drm/nouveau/nvif/object.h
+++ b/drivers/gpu/drm/nouveau/nvif/object.h
@@ -14,7 +14,7 @@ struct nvif_object {
 	void *priv; /*XXX: hack */
 	void (*dtor)(struct nvif_object *);
 	struct {
-		void *ptr;
+		void __iomem *ptr;
 		u32 size;
 	} map;
 };
@@ -42,7 +42,7 @@ void nvif_object_unmap(struct nvif_object *);
 	struct nvif_object *_object = nvif_object(a);                          \
 	u32 _data;                                                             \
 	if (likely(_object->map.ptr))                                          \
-		_data = ioread##b##_native((u8 *)_object->map.ptr + (c));      \
+		_data = ioread##b##_native((u8 __iomem *)_object->map.ptr + (c));      \
 	else                                                                   \
 		_data = nvif_object_rd(_object, (b) / 8, (c));                 \
 	_data;                                                                 \
@@ -50,7 +50,7 @@ void nvif_object_unmap(struct nvif_object *);
 #define nvif_wr(a,b,c,d) ({                                                    \
 	struct nvif_object *_object = nvif_object(a);                          \
 	if (likely(_object->map.ptr))                                          \
-		iowrite##b##_native((d), (u8 *)_object->map.ptr + (c));        \
+		iowrite##b##_native((d), (u8 __iomem *)_object->map.ptr + (c));        \
 	else                                                                   \
 		nvif_object_wr(_object, (b) / 8, (c), (d));                    \
 })
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index 002b9721e85a..862ba03c236c 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -629,6 +629,7 @@ static struct drm_driver omap_drm_driver = {
 		.lastclose = dev_lastclose,
 		.preclose = dev_preclose,
 		.postclose = dev_postclose,
+		.set_busid = drm_platform_set_busid,
 		.get_vblank_counter = drm_vblank_count,
 		.enable_vblank = omap_irq_enable_vblank,
 		.disable_vblank = omap_irq_disable_vblank,
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h
index 84d73a61b34b..60e47b33c801 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.h
+++ b/drivers/gpu/drm/omapdrm/omap_drv.h
@@ -26,6 +26,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/omap_drm.h>
+#include <drm/drm_gem.h>
 #include <linux/platform_data/omap_drm.h>
 
 
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 4ce1db0a68ff..23de22f8c820 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -352,6 +352,30 @@ static const struct panel_desc auo_b101aw03 = {
 	},
 };
 
+static const struct drm_display_mode auo_b101xtn01_mode = {
+	.clock = 72000,
+	.hdisplay = 1366,
+	.hsync_start = 1366 + 20,
+	.hsync_end = 1366 + 20 + 70,
+	.htotal = 1366 + 20 + 70,
+	.vdisplay = 768,
+	.vsync_start = 768 + 14,
+	.vsync_end = 768 + 14 + 42,
+	.vtotal = 768 + 14 + 42,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc auo_b101xtn01 = {
+	.modes = &auo_b101xtn01_mode,
+	.num_modes = 1,
+	.bpc = 6,
+	.size = {
+		.width = 223,
+		.height = 125,
+	},
+};
+
 static const struct drm_display_mode auo_b133xtn01_mode = {
 	.clock = 69500,
 	.hdisplay = 1366,
@@ -616,6 +640,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "auo,b101aw03",
 		.data = &auo_b101aw03,
 	}, {
+		.compatible = "auo,b101xtn01",
+		.data = &auo_b101xtn01,
+	}, {
 		.compatible = "auo,b133htn01",
 		.data = &auo_b133htn01,
 	}, {
diff --git a/drivers/gpu/drm/qxl/Makefile b/drivers/gpu/drm/qxl/Makefile
index ea046ba691d2..bacc4aff1201 100644
--- a/drivers/gpu/drm/qxl/Makefile
+++ b/drivers/gpu/drm/qxl/Makefile
@@ -4,6 +4,6 @@
 
 ccflags-y := -Iinclude/drm
 
-qxl-y := qxl_drv.o qxl_kms.o qxl_display.o qxl_ttm.o qxl_fb.o qxl_object.o qxl_gem.o qxl_cmd.o qxl_image.o qxl_draw.o qxl_debugfs.o qxl_irq.o qxl_dumb.o qxl_ioctl.o qxl_fence.o qxl_release.o
+qxl-y := qxl_drv.o qxl_kms.o qxl_display.o qxl_ttm.o qxl_fb.o qxl_object.o qxl_gem.o qxl_cmd.o qxl_image.o qxl_draw.o qxl_debugfs.o qxl_irq.o qxl_dumb.o qxl_ioctl.o qxl_release.o qxl_prime.o
 
 obj-$(CONFIG_DRM_QXL)+= qxl.o
diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
index eb89653a7a17..97823644d347 100644
--- a/drivers/gpu/drm/qxl/qxl_cmd.c
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -620,17 +620,10 @@ static int qxl_reap_surf(struct qxl_device *qdev, struct qxl_bo *surf, bool stal
 	if (ret == -EBUSY)
 		return -EBUSY;
 
-	if (surf->fence.num_active_releases > 0 && stall == false) {
-		qxl_bo_unreserve(surf);
-		return -EBUSY;
-	}
-
 	if (stall)
 		mutex_unlock(&qdev->surf_evict_mutex);
 
-	spin_lock(&surf->tbo.bdev->fence_lock);
 	ret = ttm_bo_wait(&surf->tbo, true, true, !stall);
-	spin_unlock(&surf->tbo.bdev->fence_lock);
 
 	if (stall)
 		mutex_lock(&qdev->surf_evict_mutex);
diff --git a/drivers/gpu/drm/qxl/qxl_debugfs.c b/drivers/gpu/drm/qxl/qxl_debugfs.c
index c3c2bbdc6674..6911b8c44492 100644
--- a/drivers/gpu/drm/qxl/qxl_debugfs.c
+++ b/drivers/gpu/drm/qxl/qxl_debugfs.c
@@ -58,9 +58,17 @@ qxl_debugfs_buffers_info(struct seq_file *m, void *data)
 	struct qxl_bo *bo;
 
 	list_for_each_entry(bo, &qdev->gem.objects, list) {
-		seq_printf(m, "size %ld, pc %d, sync obj %p, num releases %d\n",
-			   (unsigned long)bo->gem_base.size, bo->pin_count,
-			   bo->tbo.sync_obj, bo->fence.num_active_releases);
+		struct reservation_object_list *fobj;
+		int rel;
+
+		rcu_read_lock();
+		fobj = rcu_dereference(bo->tbo.resv->fence);
+		rel = fobj ? fobj->shared_count : 0;
+		rcu_read_unlock();
+
+		seq_printf(m, "size %ld, pc %d, num releases %d\n",
+			   (unsigned long)bo->gem_base.size,
+			   bo->pin_count, rel);
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index b8ced08b6291..af9e78546688 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -187,6 +187,54 @@ static void qxl_crtc_destroy(struct drm_crtc *crtc)
 	kfree(qxl_crtc);
 }
 
+static int qxl_crtc_page_flip(struct drm_crtc *crtc,
+                              struct drm_framebuffer *fb,
+                              struct drm_pending_vblank_event *event,
+                              uint32_t page_flip_flags)
+{
+	struct drm_device *dev = crtc->dev;
+	struct qxl_device *qdev = dev->dev_private;
+	struct qxl_crtc *qcrtc = to_qxl_crtc(crtc);
+	struct qxl_framebuffer *qfb_src = to_qxl_framebuffer(fb);
+	struct qxl_framebuffer *qfb_old = to_qxl_framebuffer(crtc->primary->fb);
+	struct qxl_bo *bo_old = gem_to_qxl_bo(qfb_old->obj);
+	struct qxl_bo *bo = gem_to_qxl_bo(qfb_src->obj);
+	unsigned long flags;
+	struct drm_clip_rect norect = {
+	    .x1 = 0,
+	    .y1 = 0,
+	    .x2 = fb->width,
+	    .y2 = fb->height
+	};
+	int inc = 1;
+	int one_clip_rect = 1;
+	int ret = 0;
+
+	crtc->primary->fb = fb;
+	bo_old->is_primary = false;
+	bo->is_primary = true;
+
+	ret = qxl_bo_reserve(bo, false);
+	if (ret)
+		return ret;
+
+	qxl_draw_dirty_fb(qdev, qfb_src, bo, 0, 0,
+			  &norect, one_clip_rect, inc);
+
+	drm_vblank_get(dev, qcrtc->index);
+
+	if (event) {
+		spin_lock_irqsave(&dev->event_lock, flags);
+		drm_send_vblank_event(dev, qcrtc->index, event);
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
+	drm_vblank_put(dev, qcrtc->index);
+
+	qxl_bo_unreserve(bo);
+
+	return 0;
+}
+
 static int
 qxl_hide_cursor(struct qxl_device *qdev)
 {
@@ -374,6 +422,7 @@ static const struct drm_crtc_funcs qxl_crtc_funcs = {
 	.cursor_move = qxl_crtc_cursor_move,
 	.set_config = drm_crtc_helper_set_config,
 	.destroy = qxl_crtc_destroy,
+	.page_flip = qxl_crtc_page_flip,
 };
 
 static void qxl_user_framebuffer_destroy(struct drm_framebuffer *fb)
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index a3fd92029a14..1d9b80c91a15 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -84,6 +84,7 @@ static const struct file_operations qxl_fops = {
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
 	.poll = drm_poll,
+	.read = drm_read,
 	.mmap = qxl_mmap,
 };
 
@@ -195,6 +196,20 @@ static int qxl_pm_restore(struct device *dev)
 	return qxl_drm_resume(drm_dev, false);
 }
 
+static u32 qxl_noop_get_vblank_counter(struct drm_device *dev, int crtc)
+{
+	return dev->vblank[crtc].count.counter;
+}
+
+static int qxl_noop_enable_vblank(struct drm_device *dev, int crtc)
+{
+	return 0;
+}
+
+static void qxl_noop_disable_vblank(struct drm_device *dev, int crtc)
+{
+}
+
 static const struct dev_pm_ops qxl_pm_ops = {
 	.suspend = qxl_pm_suspend,
 	.resume = qxl_pm_resume,
@@ -212,10 +227,15 @@ static struct pci_driver qxl_pci_driver = {
 };
 
 static struct drm_driver qxl_driver = {
-	.driver_features = DRIVER_GEM | DRIVER_MODESET |
+	.driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME |
 			   DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED,
 	.load = qxl_driver_load,
 	.unload = qxl_driver_unload,
+	.get_vblank_counter = qxl_noop_get_vblank_counter,
+	.enable_vblank = qxl_noop_enable_vblank,
+	.disable_vblank = qxl_noop_disable_vblank,
+
+	.set_busid = drm_pci_set_busid,
 
 	.dumb_create = qxl_mode_dumb_create,
 	.dumb_map_offset = qxl_mode_dumb_mmap,
@@ -224,6 +244,17 @@ static struct drm_driver qxl_driver = {
 	.debugfs_init = qxl_debugfs_init,
 	.debugfs_cleanup = qxl_debugfs_takedown,
 #endif
+	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
+	.gem_prime_export = drm_gem_prime_export,
+	.gem_prime_import = drm_gem_prime_import,
+	.gem_prime_pin = qxl_gem_prime_pin,
+	.gem_prime_unpin = qxl_gem_prime_unpin,
+	.gem_prime_get_sg_table = qxl_gem_prime_get_sg_table,
+	.gem_prime_import_sg_table = qxl_gem_prime_import_sg_table,
+	.gem_prime_vmap = qxl_gem_prime_vmap,
+	.gem_prime_vunmap = qxl_gem_prime_vunmap,
+	.gem_prime_mmap = qxl_gem_prime_mmap,
 	.gem_free_object = qxl_gem_object_free,
 	.gem_open_object = qxl_gem_object_open,
 	.gem_close_object = qxl_gem_object_close,
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index 36ed40ba773f..7c6cafe21f5f 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -31,6 +31,7 @@
  * Definitions taken from spice-protocol, plus kernel driver specific bits.
  */
 
+#include <linux/fence.h>
 #include <linux/workqueue.h>
 #include <linux/firmware.h>
 #include <linux/platform_device.h>
@@ -42,6 +43,8 @@
 #include <ttm/ttm_placement.h>
 #include <ttm/ttm_module.h>
 
+#include <drm/drm_gem.h>
+
 /* just for ttm_validate_buffer */
 #include <ttm/ttm_execbuf_util.h>
 
@@ -95,31 +98,24 @@ enum {
 	QXL_INTERRUPT_IO_CMD |\
 	QXL_INTERRUPT_CLIENT_MONITORS_CONFIG)
 
-struct qxl_fence {
-	struct qxl_device *qdev;
-	uint32_t num_active_releases;
-	uint32_t *release_ids;
-	struct radix_tree_root tree;
-};
-
 struct qxl_bo {
 	/* Protected by gem.mutex */
 	struct list_head		list;
 	/* Protected by tbo.reserved */
-	u32				placements[3];
+	struct ttm_place		placements[3];
 	struct ttm_placement		placement;
 	struct ttm_buffer_object	tbo;
 	struct ttm_bo_kmap_obj		kmap;
 	unsigned			pin_count;
 	void				*kptr;
 	int                             type;
+
 	/* Constant after initialization */
 	struct drm_gem_object		gem_base;
 	bool is_primary; /* is this now a primary surface */
 	bool hw_surf_alloc;
 	struct qxl_surface surf;
 	uint32_t surface_id;
-	struct qxl_fence fence; /* per bo fence  - list of releases */
 	struct qxl_release *surf_create;
 };
 #define gem_to_qxl_bo(gobj) container_of((gobj), struct qxl_bo, gem_base)
@@ -191,6 +187,8 @@ enum {
  * spice-protocol/qxl_dev.h */
 #define QXL_MAX_RES 96
 struct qxl_release {
+	struct fence base;
+
 	int id;
 	int type;
 	uint32_t release_offset;
@@ -284,7 +282,9 @@ struct qxl_device {
 	uint8_t		slot_gen_bits;
 	uint64_t	va_slot_mask;
 
+	spinlock_t	release_lock;
 	struct idr	release_idr;
+	uint32_t	release_seqno;
 	spinlock_t release_idr_lock;
 	struct mutex	async_io_mutex;
 	unsigned int last_sent_io_cmd;
@@ -532,6 +532,18 @@ int qxl_garbage_collect(struct qxl_device *qdev);
 int qxl_debugfs_init(struct drm_minor *minor);
 void qxl_debugfs_takedown(struct drm_minor *minor);
 
+/* qxl_prime.c */
+int qxl_gem_prime_pin(struct drm_gem_object *obj);
+void qxl_gem_prime_unpin(struct drm_gem_object *obj);
+struct sg_table *qxl_gem_prime_get_sg_table(struct drm_gem_object *obj);
+struct drm_gem_object *qxl_gem_prime_import_sg_table(
+	struct drm_device *dev, struct dma_buf_attachment *attach,
+	struct sg_table *sgt);
+void *qxl_gem_prime_vmap(struct drm_gem_object *obj);
+void qxl_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
+int qxl_gem_prime_mmap(struct drm_gem_object *obj,
+				struct vm_area_struct *vma);
+
 /* qxl_irq.c */
 int qxl_irq_init(struct qxl_device *qdev);
 irqreturn_t qxl_irq_handler(int irq, void *arg);
@@ -561,10 +573,4 @@ qxl_surface_lookup(struct drm_device *dev, int surface_id);
 void qxl_surface_evict(struct qxl_device *qdev, struct qxl_bo *surf, bool freeing);
 int qxl_update_surface(struct qxl_device *qdev, struct qxl_bo *surf);
 
-/* qxl_fence.c */
-void qxl_fence_add_release_locked(struct qxl_fence *qfence, uint32_t rel_id);
-int qxl_fence_remove_release(struct qxl_fence *qfence, uint32_t rel_id);
-int qxl_fence_init(struct qxl_device *qdev, struct qxl_fence *qfence);
-void qxl_fence_fini(struct qxl_fence *qfence);
-
 #endif
diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c
index df567888bb1e..3d7c1d00a424 100644
--- a/drivers/gpu/drm/qxl/qxl_fb.c
+++ b/drivers/gpu/drm/qxl/qxl_fb.c
@@ -625,7 +625,8 @@ static int qxl_fb_find_or_create_single(
 		struct drm_fb_helper *helper,
 		struct drm_fb_helper_surface_size *sizes)
 {
-	struct qxl_fbdev *qfbdev = (struct qxl_fbdev *)helper;
+	struct qxl_fbdev *qfbdev =
+		container_of(helper, struct qxl_fbdev, helper);
 	int new_fb = 0;
 	int ret;
 
diff --git a/drivers/gpu/drm/qxl/qxl_fence.c b/drivers/gpu/drm/qxl/qxl_fence.c
deleted file mode 100644
index ae59e91cfb9a..000000000000
--- a/drivers/gpu/drm/qxl/qxl_fence.c
+++ /dev/null
@@ -1,91 +0,0 @@
-/*
- * Copyright 2013 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Dave Airlie
- *          Alon Levy
- */
-
-
-#include "qxl_drv.h"
-
-/* QXL fencing-
-
-   When we submit operations to the GPU we pass a release reference to the GPU
-   with them, the release reference is then added to the release ring when
-   the GPU is finished with that particular operation and has removed it from
-   its tree.
-
-   So we have can have multiple outstanding non linear fences per object.
-
-   From a TTM POV we only care if the object has any outstanding releases on
-   it.
-
-   we wait until all outstanding releases are processeed.
-
-   sync object is just a list of release ids that represent that fence on
-   that buffer.
-
-   we just add new releases onto the sync object attached to the object.
-
-   This currently uses a radix tree to store the list of release ids.
-
-   For some reason every so often qxl hw fails to release, things go wrong.
-*/
-/* must be called with the fence lock held */
-void qxl_fence_add_release_locked(struct qxl_fence *qfence, uint32_t rel_id)
-{
-	radix_tree_insert(&qfence->tree, rel_id, qfence);
-	qfence->num_active_releases++;
-}
-
-int qxl_fence_remove_release(struct qxl_fence *qfence, uint32_t rel_id)
-{
-	void *ret;
-	int retval = 0;
-	struct qxl_bo *bo = container_of(qfence, struct qxl_bo, fence);
-
-	spin_lock(&bo->tbo.bdev->fence_lock);
-
-	ret = radix_tree_delete(&qfence->tree, rel_id);
-	if (ret == qfence)
-		qfence->num_active_releases--;
-	else {
-		DRM_DEBUG("didn't find fence in radix tree for %d\n", rel_id);
-		retval = -ENOENT;
-	}
-	spin_unlock(&bo->tbo.bdev->fence_lock);
-	return retval;
-}
-
-
-int qxl_fence_init(struct qxl_device *qdev, struct qxl_fence *qfence)
-{
-	qfence->qdev = qdev;
-	qfence->num_active_releases = 0;
-	INIT_RADIX_TREE(&qfence->tree, GFP_ATOMIC);
-	return 0;
-}
-
-void qxl_fence_fini(struct qxl_fence *qfence)
-{
-	kfree(qfence->release_ids);
-	qfence->num_active_releases = 0;
-}
diff --git a/drivers/gpu/drm/qxl/qxl_kms.c b/drivers/gpu/drm/qxl/qxl_kms.c
index fd88eb4a3f79..b2977a181935 100644
--- a/drivers/gpu/drm/qxl/qxl_kms.c
+++ b/drivers/gpu/drm/qxl/qxl_kms.c
@@ -223,6 +223,7 @@ static int qxl_device_init(struct qxl_device *qdev,
 
 	idr_init(&qdev->release_idr);
 	spin_lock_init(&qdev->release_idr_lock);
+	spin_lock_init(&qdev->release_lock);
 
 	idr_init(&qdev->surf_id_idr);
 	spin_lock_init(&qdev->surf_id_idr_lock);
@@ -297,6 +298,9 @@ int qxl_driver_unload(struct drm_device *dev)
 
 	if (qdev == NULL)
 		return 0;
+
+	drm_vblank_cleanup(dev);
+
 	qxl_modeset_fini(qdev);
 	qxl_device_fini(qdev);
 
@@ -324,15 +328,20 @@ int qxl_driver_load(struct drm_device *dev, unsigned long flags)
 	if (r)
 		goto out;
 
+	r = drm_vblank_init(dev, 1);
+	if (r)
+		goto unload;
+
 	r = qxl_modeset_init(qdev);
-	if (r) {
-		qxl_driver_unload(dev);
-		goto out;
-	}
+	if (r)
+		goto unload;
 
 	drm_kms_helper_poll_init(qdev->ddev);
 
 	return 0;
+unload:
+	qxl_driver_unload(dev);
+
 out:
 	kfree(qdev);
 	return r;
diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c
index b95f144f0b49..cdeaf08fdc74 100644
--- a/drivers/gpu/drm/qxl/qxl_object.c
+++ b/drivers/gpu/drm/qxl/qxl_object.c
@@ -36,7 +36,6 @@ static void qxl_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 	qdev = (struct qxl_device *)bo->gem_base.dev->dev_private;
 
 	qxl_surface_evict(qdev, bo, false);
-	qxl_fence_fini(&bo->fence);
 	mutex_lock(&qdev->gem.mutex);
 	list_del_init(&bo->list);
 	mutex_unlock(&qdev->gem.mutex);
@@ -55,21 +54,24 @@ void qxl_ttm_placement_from_domain(struct qxl_bo *qbo, u32 domain, bool pinned)
 {
 	u32 c = 0;
 	u32 pflag = pinned ? TTM_PL_FLAG_NO_EVICT : 0;
+	unsigned i;
 
-	qbo->placement.fpfn = 0;
-	qbo->placement.lpfn = 0;
 	qbo->placement.placement = qbo->placements;
 	qbo->placement.busy_placement = qbo->placements;
 	if (domain == QXL_GEM_DOMAIN_VRAM)
-		qbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_VRAM | pflag;
+		qbo->placements[c++].flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_VRAM | pflag;
 	if (domain == QXL_GEM_DOMAIN_SURFACE)
-		qbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_PRIV0 | pflag;
+		qbo->placements[c++].flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_PRIV0 | pflag;
 	if (domain == QXL_GEM_DOMAIN_CPU)
-		qbo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM | pflag;
+		qbo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM | pflag;
 	if (!c)
-		qbo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		qbo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	qbo->placement.num_placement = c;
 	qbo->placement.num_busy_placement = c;
+	for (i = 0; i < c; ++i) {
+		qbo->placements[i].fpfn = 0;
+		qbo->placements[i].lpfn = 0;
+	}
 }
 
 
@@ -99,7 +101,6 @@ int qxl_bo_create(struct qxl_device *qdev,
 	bo->type = domain;
 	bo->pin_count = pinned ? 1 : 0;
 	bo->surface_id = 0;
-	qxl_fence_init(qdev, &bo->fence);
 	INIT_LIST_HEAD(&bo->list);
 
 	if (surf)
@@ -109,7 +110,7 @@ int qxl_bo_create(struct qxl_device *qdev,
 
 	r = ttm_bo_init(&qdev->mman.bdev, &bo->tbo, size, type,
 			&bo->placement, 0, !kernel, NULL, size,
-			NULL, &qxl_ttm_bo_destroy);
+			NULL, NULL, &qxl_ttm_bo_destroy);
 	if (unlikely(r != 0)) {
 		if (r != -ERESTARTSYS)
 			dev_err(qdev->dev,
@@ -259,7 +260,7 @@ int qxl_bo_unpin(struct qxl_bo *bo)
 	if (bo->pin_count)
 		return 0;
 	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
+		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
 	if (unlikely(r != 0))
 		dev_err(qdev->dev, "%p validate failed for unpin\n", bo);
diff --git a/drivers/gpu/drm/qxl/qxl_object.h b/drivers/gpu/drm/qxl/qxl_object.h
index 83a423293afd..37af1bc0dd00 100644
--- a/drivers/gpu/drm/qxl/qxl_object.h
+++ b/drivers/gpu/drm/qxl/qxl_object.h
@@ -76,12 +76,10 @@ static inline int qxl_bo_wait(struct qxl_bo *bo, u32 *mem_type,
 		}
 		return r;
 	}
-	spin_lock(&bo->tbo.bdev->fence_lock);
 	if (mem_type)
 		*mem_type = bo->tbo.mem.mem_type;
-	if (bo->tbo.sync_obj)
-		r = ttm_bo_wait(&bo->tbo, true, true, no_wait);
-	spin_unlock(&bo->tbo.bdev->fence_lock);
+
+	r = ttm_bo_wait(&bo->tbo, true, true, no_wait);
 	ttm_bo_unreserve(&bo->tbo);
 	return r;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c
new file mode 100644
index 000000000000..3d031b50a8fd
--- /dev/null
+++ b/drivers/gpu/drm/qxl/qxl_prime.c
@@ -0,0 +1,72 @@
+/*
+ * Copyright 2014 Canonical
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Andreas Pokorny
+ */
+
+#include "qxl_drv.h"
+
+/* Empty Implementations as there should not be any other driver for a virtual
+ * device that might share buffers with qxl */
+
+int qxl_gem_prime_pin(struct drm_gem_object *obj)
+{
+	WARN_ONCE(1, "not implemented");
+	return -ENOSYS;
+}
+
+void qxl_gem_prime_unpin(struct drm_gem_object *obj)
+{
+	WARN_ONCE(1, "not implemented");
+}
+
+
+struct sg_table *qxl_gem_prime_get_sg_table(struct drm_gem_object *obj)
+{
+	WARN_ONCE(1, "not implemented");
+	return ERR_PTR(-ENOSYS);
+}
+
+struct drm_gem_object *qxl_gem_prime_import_sg_table(
+	struct drm_device *dev, struct dma_buf_attachment *attach,
+	struct sg_table *table)
+{
+	WARN_ONCE(1, "not implemented");
+	return ERR_PTR(-ENOSYS);
+}
+
+void *qxl_gem_prime_vmap(struct drm_gem_object *obj)
+{
+	WARN_ONCE(1, "not implemented");
+	return ERR_PTR(-ENOSYS);
+}
+
+void qxl_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
+{
+	WARN_ONCE(1, "not implemented");
+}
+
+int qxl_gem_prime_mmap(struct drm_gem_object *obj,
+		       struct vm_area_struct *area)
+{
+	WARN_ONCE(1, "not implemented");
+	return ENOSYS;
+}
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 14e776f1d14e..446e71ca36cb 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -21,6 +21,7 @@
  */
 #include "qxl_drv.h"
 #include "qxl_object.h"
+#include <trace/events/fence.h>
 
 /*
  * drawable cmd cache - allocate a bunch of VRAM pages, suballocate
@@ -39,6 +40,88 @@
 static const int release_size_per_bo[] = { RELEASE_SIZE, SURFACE_RELEASE_SIZE, RELEASE_SIZE };
 static const int releases_per_bo[] = { RELEASES_PER_BO, SURFACE_RELEASES_PER_BO, RELEASES_PER_BO };
 
+static const char *qxl_get_driver_name(struct fence *fence)
+{
+	return "qxl";
+}
+
+static const char *qxl_get_timeline_name(struct fence *fence)
+{
+	return "release";
+}
+
+static bool qxl_nop_signaling(struct fence *fence)
+{
+	/* fences are always automatically signaled, so just pretend we did this.. */
+	return true;
+}
+
+static long qxl_fence_wait(struct fence *fence, bool intr, signed long timeout)
+{
+	struct qxl_device *qdev;
+	struct qxl_release *release;
+	int count = 0, sc = 0;
+	bool have_drawable_releases;
+	unsigned long cur, end = jiffies + timeout;
+
+	qdev = container_of(fence->lock, struct qxl_device, release_lock);
+	release = container_of(fence, struct qxl_release, base);
+	have_drawable_releases = release->type == QXL_RELEASE_DRAWABLE;
+
+retry:
+	sc++;
+
+	if (fence_is_signaled(fence))
+		goto signaled;
+
+	qxl_io_notify_oom(qdev);
+
+	for (count = 0; count < 11; count++) {
+		if (!qxl_queue_garbage_collect(qdev, true))
+			break;
+
+		if (fence_is_signaled(fence))
+			goto signaled;
+	}
+
+	if (fence_is_signaled(fence))
+		goto signaled;
+
+	if (have_drawable_releases || sc < 4) {
+		if (sc > 2)
+			/* back off */
+			usleep_range(500, 1000);
+
+		if (time_after(jiffies, end))
+			return 0;
+
+		if (have_drawable_releases && sc > 300) {
+			FENCE_WARN(fence, "failed to wait on release %d "
+					  "after spincount %d\n",
+					  fence->context & ~0xf0000000, sc);
+			goto signaled;
+		}
+		goto retry;
+	}
+	/*
+	 * yeah, original sync_obj_wait gave up after 3 spins when
+	 * have_drawable_releases is not set.
+	 */
+
+signaled:
+	cur = jiffies;
+	if (time_after(cur, end))
+		return 0;
+	return end - cur;
+}
+
+static const struct fence_ops qxl_fence_ops = {
+	.get_driver_name = qxl_get_driver_name,
+	.get_timeline_name = qxl_get_timeline_name,
+	.enable_signaling = qxl_nop_signaling,
+	.wait = qxl_fence_wait,
+};
+
 static uint64_t
 qxl_release_alloc(struct qxl_device *qdev, int type,
 		  struct qxl_release **ret)
@@ -46,13 +129,13 @@ qxl_release_alloc(struct qxl_device *qdev, int type,
 	struct qxl_release *release;
 	int handle;
 	size_t size = sizeof(*release);
-	int idr_ret;
 
 	release = kmalloc(size, GFP_KERNEL);
 	if (!release) {
 		DRM_ERROR("Out of memory\n");
 		return 0;
 	}
+	release->base.ops = NULL;
 	release->type = type;
 	release->release_offset = 0;
 	release->surface_release_id = 0;
@@ -60,44 +143,61 @@ qxl_release_alloc(struct qxl_device *qdev, int type,
 
 	idr_preload(GFP_KERNEL);
 	spin_lock(&qdev->release_idr_lock);
-	idr_ret = idr_alloc(&qdev->release_idr, release, 1, 0, GFP_NOWAIT);
+	handle = idr_alloc(&qdev->release_idr, release, 1, 0, GFP_NOWAIT);
+	release->base.seqno = ++qdev->release_seqno;
 	spin_unlock(&qdev->release_idr_lock);
 	idr_preload_end();
-	handle = idr_ret;
-	if (idr_ret < 0)
-		goto release_fail;
+	if (handle < 0) {
+		kfree(release);
+		*ret = NULL;
+		return handle;
+	}
 	*ret = release;
 	QXL_INFO(qdev, "allocated release %lld\n", handle);
 	release->id = handle;
-release_fail:
-
 	return handle;
 }
 
+static void
+qxl_release_free_list(struct qxl_release *release)
+{
+	while (!list_empty(&release->bos)) {
+		struct qxl_bo_list *entry;
+		struct qxl_bo *bo;
+
+		entry = container_of(release->bos.next,
+				     struct qxl_bo_list, tv.head);
+		bo = to_qxl_bo(entry->tv.bo);
+		qxl_bo_unref(&bo);
+		list_del(&entry->tv.head);
+		kfree(entry);
+	}
+}
+
 void
 qxl_release_free(struct qxl_device *qdev,
 		 struct qxl_release *release)
 {
-	struct qxl_bo_list *entry, *tmp;
 	QXL_INFO(qdev, "release %d, type %d\n", release->id,
 		 release->type);
 
 	if (release->surface_release_id)
 		qxl_surface_id_dealloc(qdev, release->surface_release_id);
 
-	list_for_each_entry_safe(entry, tmp, &release->bos, tv.head) {
-		struct qxl_bo *bo = to_qxl_bo(entry->tv.bo);
-		QXL_INFO(qdev, "release %llx\n",
-			drm_vma_node_offset_addr(&entry->tv.bo->vma_node)
-						- DRM_FILE_OFFSET);
-		qxl_fence_remove_release(&bo->fence, release->id);
-		qxl_bo_unref(&bo);
-		kfree(entry);
-	}
 	spin_lock(&qdev->release_idr_lock);
 	idr_remove(&qdev->release_idr, release->id);
 	spin_unlock(&qdev->release_idr_lock);
-	kfree(release);
+
+	if (release->base.ops) {
+		WARN_ON(list_empty(&release->bos));
+		qxl_release_free_list(release);
+
+		fence_signal(&release->base);
+		fence_put(&release->base);
+	} else {
+		qxl_release_free_list(release);
+		kfree(release);
+	}
 }
 
 static int qxl_release_bo_alloc(struct qxl_device *qdev,
@@ -126,6 +226,7 @@ int qxl_release_list_add(struct qxl_release *release, struct qxl_bo *bo)
 
 	qxl_bo_ref(bo);
 	entry->tv.bo = &bo->tbo;
+	entry->tv.shared = false;
 	list_add_tail(&entry->tv.head, &release->bos);
 	return 0;
 }
@@ -142,6 +243,10 @@ static int qxl_release_validate_bo(struct qxl_bo *bo)
 			return ret;
 	}
 
+	ret = reservation_object_reserve_shared(bo->tbo.resv);
+	if (ret)
+		return ret;
+
 	/* allocate a surface for reserved + validated buffers */
 	ret = qxl_bo_check_id(bo->gem_base.dev->dev_private, bo);
 	if (ret)
@@ -159,7 +264,7 @@ int qxl_release_reserve_list(struct qxl_release *release, bool no_intr)
 	if (list_is_singular(&release->bos))
 		return 0;
 
-	ret = ttm_eu_reserve_buffers(&release->ticket, &release->bos);
+	ret = ttm_eu_reserve_buffers(&release->ticket, &release->bos, !no_intr);
 	if (ret)
 		return ret;
 
@@ -199,6 +304,8 @@ int qxl_alloc_surface_release_reserved(struct qxl_device *qdev,
 
 		/* stash the release after the create command */
 		idr_ret = qxl_release_alloc(qdev, QXL_RELEASE_SURFACE_CMD, release);
+		if (idr_ret < 0)
+			return idr_ret;
 		bo = qxl_bo_ref(to_qxl_bo(entry->tv.bo));
 
 		(*release)->release_offset = create_rel->release_offset + 64;
@@ -239,6 +346,11 @@ int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size,
 	}
 
 	idr_ret = qxl_release_alloc(qdev, type, release);
+	if (idr_ret < 0) {
+		if (rbo)
+			*rbo = NULL;
+		return idr_ret;
+	}
 
 	mutex_lock(&qdev->release_mutex);
 	if (qdev->current_release_bo_offset[cur_idx] + 1 >= releases_per_bo[cur_idx]) {
@@ -319,40 +431,44 @@ void qxl_release_unmap(struct qxl_device *qdev,
 
 void qxl_release_fence_buffer_objects(struct qxl_release *release)
 {
-	struct ttm_validate_buffer *entry;
 	struct ttm_buffer_object *bo;
 	struct ttm_bo_global *glob;
 	struct ttm_bo_device *bdev;
 	struct ttm_bo_driver *driver;
 	struct qxl_bo *qbo;
+	struct ttm_validate_buffer *entry;
+	struct qxl_device *qdev;
 
 	/* if only one object on the release its the release itself
 	   since these objects are pinned no need to reserve */
-	if (list_is_singular(&release->bos))
+	if (list_is_singular(&release->bos) || list_empty(&release->bos))
 		return;
 
 	bo = list_first_entry(&release->bos, struct ttm_validate_buffer, head)->bo;
 	bdev = bo->bdev;
+	qdev = container_of(bdev, struct qxl_device, mman.bdev);
+
+	/*
+	 * Since we never really allocated a context and we don't want to conflict,
+	 * set the highest bits. This will break if we really allow exporting of dma-bufs.
+	 */
+	fence_init(&release->base, &qxl_fence_ops, &qdev->release_lock,
+		   release->id | 0xf0000000, release->base.seqno);
+	trace_fence_emit(&release->base);
+
 	driver = bdev->driver;
 	glob = bo->glob;
 
 	spin_lock(&glob->lru_lock);
-	spin_lock(&bdev->fence_lock);
 
 	list_for_each_entry(entry, &release->bos, head) {
 		bo = entry->bo;
 		qbo = to_qxl_bo(bo);
 
-		if (!entry->bo->sync_obj)
-			entry->bo->sync_obj = &qbo->fence;
-
-		qxl_fence_add_release_locked(&qbo->fence, release->id);
-
+		reservation_object_add_shared_fence(bo->resv, &release->base);
 		ttm_bo_add_to_lru(bo);
 		__ttm_bo_unreserve(bo);
-		entry->reserved = false;
 	}
-	spin_unlock(&bdev->fence_lock);
 	spin_unlock(&glob->lru_lock);
 	ww_acquire_fini(&release->ticket);
 }
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 71a1baeac14e..0cbc4c987164 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -127,7 +127,7 @@ int qxl_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET)) {
 		pr_info("%s: vma->vm_pgoff (%ld) < DRM_FILE_PAGE_OFFSET\n",
 			__func__, vma->vm_pgoff);
-		return drm_mmap(filp, vma);
+		return -EINVAL;
 	}
 
 	file_priv = filp->private_data;
@@ -188,11 +188,13 @@ static void qxl_evict_flags(struct ttm_buffer_object *bo,
 				struct ttm_placement *placement)
 {
 	struct qxl_bo *qbo;
-	static u32 placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+	static struct ttm_place placements = {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM
+	};
 
 	if (!qxl_ttm_bo_is_qxl_bo(bo)) {
-		placement->fpfn = 0;
-		placement->lpfn = 0;
 		placement->placement = &placements;
 		placement->busy_placement = &placements;
 		placement->num_placement = 1;
@@ -355,92 +357,6 @@ static int qxl_bo_move(struct ttm_buffer_object *bo,
 	return ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem);
 }
 
-
-static int qxl_sync_obj_wait(void *sync_obj,
-			     bool lazy, bool interruptible)
-{
-	struct qxl_fence *qfence = (struct qxl_fence *)sync_obj;
-	int count = 0, sc = 0;
-	struct qxl_bo *bo = container_of(qfence, struct qxl_bo, fence);
-
-	if (qfence->num_active_releases == 0)
-		return 0;
-
-retry:
-	if (sc == 0) {
-		if (bo->type == QXL_GEM_DOMAIN_SURFACE)
-			qxl_update_surface(qfence->qdev, bo);
-	} else if (sc >= 1) {
-		qxl_io_notify_oom(qfence->qdev);
-	}
-
-	sc++;
-
-	for (count = 0; count < 10; count++) {
-		bool ret;
-		ret = qxl_queue_garbage_collect(qfence->qdev, true);
-		if (ret == false)
-			break;
-
-		if (qfence->num_active_releases == 0)
-			return 0;
-	}
-
-	if (qfence->num_active_releases) {
-		bool have_drawable_releases = false;
-		void **slot;
-		struct radix_tree_iter iter;
-		int release_id;
-
-		radix_tree_for_each_slot(slot, &qfence->tree, &iter, 0) {
-			struct qxl_release *release;
-
-			release_id = iter.index;
-			release = qxl_release_from_id_locked(qfence->qdev, release_id);
-			if (release == NULL)
-				continue;
-
-			if (release->type == QXL_RELEASE_DRAWABLE)
-				have_drawable_releases = true;
-		}
-
-		qxl_queue_garbage_collect(qfence->qdev, true);
-
-		if (have_drawable_releases || sc < 4) {
-			if (sc > 2)
-				/* back off */
-				usleep_range(500, 1000);
-			if (have_drawable_releases && sc > 300) {
-				WARN(1, "sync obj %d still has outstanding releases %d %d %d %ld %d\n", sc, bo->surface_id, bo->is_primary, bo->pin_count, (unsigned long)bo->gem_base.size, qfence->num_active_releases);
-				return -EBUSY;
-			}
-			goto retry;
-		}
-	}
-	return 0;
-}
-
-static int qxl_sync_obj_flush(void *sync_obj)
-{
-	return 0;
-}
-
-static void qxl_sync_obj_unref(void **sync_obj)
-{
-	*sync_obj = NULL;
-}
-
-static void *qxl_sync_obj_ref(void *sync_obj)
-{
-	return sync_obj;
-}
-
-static bool qxl_sync_obj_signaled(void *sync_obj)
-{
-	struct qxl_fence *qfence = (struct qxl_fence *)sync_obj;
-	return (qfence->num_active_releases == 0);
-}
-
 static void qxl_bo_move_notify(struct ttm_buffer_object *bo,
 			       struct ttm_mem_reg *new_mem)
 {
@@ -467,16 +383,9 @@ static struct ttm_bo_driver qxl_bo_driver = {
 	.verify_access = &qxl_verify_access,
 	.io_mem_reserve = &qxl_ttm_io_mem_reserve,
 	.io_mem_free = &qxl_ttm_io_mem_free,
-	.sync_obj_signaled = &qxl_sync_obj_signaled,
-	.sync_obj_wait = &qxl_sync_obj_wait,
-	.sync_obj_flush = &qxl_sync_obj_flush,
-	.sync_obj_unref = &qxl_sync_obj_unref,
-	.sync_obj_ref = &qxl_sync_obj_ref,
 	.move_notify = &qxl_bo_move_notify,
 };
 
-
-
 int qxl_ttm_init(struct qxl_device *qdev)
 {
 	int r;
diff --git a/drivers/gpu/drm/r128/r128_cce.c b/drivers/gpu/drm/r128/r128_cce.c
index 59459fe4e8c5..2c45ac9c1dc3 100644
--- a/drivers/gpu/drm/r128/r128_cce.c
+++ b/drivers/gpu/drm/r128/r128_cce.c
@@ -452,7 +452,7 @@ static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init)
 	dev_priv->span_pitch_offset_c = (((dev_priv->depth_pitch / 8) << 21) |
 					 (dev_priv->span_offset >> 5));
 
-	dev_priv->sarea = drm_getsarea(dev);
+	dev_priv->sarea = drm_legacy_getsarea(dev);
 	if (!dev_priv->sarea) {
 		DRM_ERROR("could not find sarea!\n");
 		dev->dev_private = (void *)dev_priv;
@@ -460,21 +460,21 @@ static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init)
 		return -EINVAL;
 	}
 
-	dev_priv->mmio = drm_core_findmap(dev, init->mmio_offset);
+	dev_priv->mmio = drm_legacy_findmap(dev, init->mmio_offset);
 	if (!dev_priv->mmio) {
 		DRM_ERROR("could not find mmio region!\n");
 		dev->dev_private = (void *)dev_priv;
 		r128_do_cleanup_cce(dev);
 		return -EINVAL;
 	}
-	dev_priv->cce_ring = drm_core_findmap(dev, init->ring_offset);
+	dev_priv->cce_ring = drm_legacy_findmap(dev, init->ring_offset);
 	if (!dev_priv->cce_ring) {
 		DRM_ERROR("could not find cce ring region!\n");
 		dev->dev_private = (void *)dev_priv;
 		r128_do_cleanup_cce(dev);
 		return -EINVAL;
 	}
-	dev_priv->ring_rptr = drm_core_findmap(dev, init->ring_rptr_offset);
+	dev_priv->ring_rptr = drm_legacy_findmap(dev, init->ring_rptr_offset);
 	if (!dev_priv->ring_rptr) {
 		DRM_ERROR("could not find ring read pointer!\n");
 		dev->dev_private = (void *)dev_priv;
@@ -482,7 +482,7 @@ static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init)
 		return -EINVAL;
 	}
 	dev->agp_buffer_token = init->buffers_offset;
-	dev->agp_buffer_map = drm_core_findmap(dev, init->buffers_offset);
+	dev->agp_buffer_map = drm_legacy_findmap(dev, init->buffers_offset);
 	if (!dev->agp_buffer_map) {
 		DRM_ERROR("could not find dma buffer region!\n");
 		dev->dev_private = (void *)dev_priv;
@@ -492,7 +492,7 @@ static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init)
 
 	if (!dev_priv->is_pci) {
 		dev_priv->agp_textures =
-		    drm_core_findmap(dev, init->agp_textures_offset);
+		    drm_legacy_findmap(dev, init->agp_textures_offset);
 		if (!dev_priv->agp_textures) {
 			DRM_ERROR("could not find agp texture region!\n");
 			dev->dev_private = (void *)dev_priv;
@@ -507,9 +507,9 @@ static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init)
 
 #if __OS_HAS_AGP
 	if (!dev_priv->is_pci) {
-		drm_core_ioremap_wc(dev_priv->cce_ring, dev);
-		drm_core_ioremap_wc(dev_priv->ring_rptr, dev);
-		drm_core_ioremap_wc(dev->agp_buffer_map, dev);
+		drm_legacy_ioremap_wc(dev_priv->cce_ring, dev);
+		drm_legacy_ioremap_wc(dev_priv->ring_rptr, dev);
+		drm_legacy_ioremap_wc(dev->agp_buffer_map, dev);
 		if (!dev_priv->cce_ring->handle ||
 		    !dev_priv->ring_rptr->handle ||
 		    !dev->agp_buffer_map->handle) {
@@ -603,11 +603,11 @@ int r128_do_cleanup_cce(struct drm_device *dev)
 #if __OS_HAS_AGP
 		if (!dev_priv->is_pci) {
 			if (dev_priv->cce_ring != NULL)
-				drm_core_ioremapfree(dev_priv->cce_ring, dev);
+				drm_legacy_ioremapfree(dev_priv->cce_ring, dev);
 			if (dev_priv->ring_rptr != NULL)
-				drm_core_ioremapfree(dev_priv->ring_rptr, dev);
+				drm_legacy_ioremapfree(dev_priv->ring_rptr, dev);
 			if (dev->agp_buffer_map != NULL) {
-				drm_core_ioremapfree(dev->agp_buffer_map, dev);
+				drm_legacy_ioremapfree(dev->agp_buffer_map, dev);
 				dev->agp_buffer_map = NULL;
 			}
 		} else
diff --git a/drivers/gpu/drm/r128/r128_drv.c b/drivers/gpu/drm/r128/r128_drv.c
index 5bd307cd8da1..c57b4de63caf 100644
--- a/drivers/gpu/drm/r128/r128_drv.c
+++ b/drivers/gpu/drm/r128/r128_drv.c
@@ -46,7 +46,7 @@ static const struct file_operations r128_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = r128_compat_ioctl,
@@ -62,6 +62,7 @@ static struct drm_driver driver = {
 	.load = r128_driver_load,
 	.preclose = r128_driver_preclose,
 	.lastclose = r128_driver_lastclose,
+	.set_busid = drm_pci_set_busid,
 	.get_vblank_counter = r128_get_vblank_counter,
 	.enable_vblank = r128_enable_vblank,
 	.disable_vblank = r128_disable_vblank,
diff --git a/drivers/gpu/drm/r128/r128_drv.h b/drivers/gpu/drm/r128/r128_drv.h
index 5bf3f5ff805d..723e5d6f10a4 100644
--- a/drivers/gpu/drm/r128/r128_drv.h
+++ b/drivers/gpu/drm/r128/r128_drv.h
@@ -35,6 +35,9 @@
 #ifndef __R128_DRV_H__
 #define __R128_DRV_H__
 
+#include <drm/ati_pcigart.h>
+#include <drm/drm_legacy.h>
+
 /* General customization:
  */
 #define DRIVER_AUTHOR		"Gareth Hughes, VA Linux Systems Inc."
diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
index f77b7135ee4c..d01b87991422 100644
--- a/drivers/gpu/drm/radeon/Makefile
+++ b/drivers/gpu/drm/radeon/Makefile
@@ -60,7 +60,7 @@ radeon-y := radeon_drv.o
 
 # add UMS driver
 radeon-$(CONFIG_DRM_RADEON_UMS)+= radeon_cp.o radeon_state.o radeon_mem.o \
-	radeon_irq.o r300_cmdbuf.o r600_cp.o r600_blit.o
+	radeon_irq.o r300_cmdbuf.o r600_cp.o r600_blit.o drm_buffer.o
 
 # add KMS driver
 radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
@@ -72,7 +72,7 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
 	radeon_cs.o radeon_bios.o radeon_benchmark.o r100.o r300.o r420.o \
 	rs400.o rs600.o rs690.o rv515.o r520.o r600.o rv770.o radeon_test.o \
 	r200.o radeon_legacy_tv.o r600_cs.o r600_blit_shaders.o \
-	radeon_pm.o atombios_dp.o r600_audio.o r600_hdmi.o dce3_1_afmt.o \
+	radeon_pm.o atombios_dp.o r600_hdmi.o dce3_1_afmt.o \
 	evergreen.o evergreen_cs.o evergreen_blit_shaders.o \
 	evergreen_hdmi.o radeon_trace_points.o ni.o cayman_blit_shaders.o \
 	atombios_encoders.o radeon_semaphore.o radeon_sa.o atombios_i2c.o si.o \
@@ -80,7 +80,7 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
 	r600_dpm.o rs780_dpm.o rv6xx_dpm.o rv770_dpm.o rv730_dpm.o rv740_dpm.o \
 	rv770_smc.o cypress_dpm.o btc_dpm.o sumo_dpm.o sumo_smc.o trinity_dpm.o \
 	trinity_smc.o ni_dpm.o si_smc.o si_dpm.o kv_smc.o kv_dpm.o ci_smc.o \
-	ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o
+	ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o radeon_mn.o
 
 # add async DMA block
 radeon-y += \
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index ac14b67621d3..95d5d4ab3335 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -232,8 +232,8 @@ void radeon_dp_aux_init(struct radeon_connector *radeon_connector)
 
 /***** general DP utility functions *****/
 
-#define DP_VOLTAGE_MAX         DP_TRAIN_VOLTAGE_SWING_1200
-#define DP_PRE_EMPHASIS_MAX    DP_TRAIN_PRE_EMPHASIS_9_5
+#define DP_VOLTAGE_MAX         DP_TRAIN_VOLTAGE_SWING_LEVEL_3
+#define DP_PRE_EMPHASIS_MAX    DP_TRAIN_PRE_EMPH_LEVEL_3
 
 static void dp_get_adjust_train(u8 link_status[DP_LINK_STATUS_SIZE],
 				int lane_count,
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index a7f2ddf09a9d..b8cd7975f797 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -291,29 +291,6 @@ static void radeon_atom_backlight_exit(struct radeon_encoder *encoder)
 bool radeon_atom_get_tv_timings(struct radeon_device *rdev, int index,
 				struct drm_display_mode *mode);
 
-
-static inline bool radeon_encoder_is_digital(struct drm_encoder *encoder)
-{
-	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
-	switch (radeon_encoder->encoder_id) {
-	case ENCODER_OBJECT_ID_INTERNAL_LVDS:
-	case ENCODER_OBJECT_ID_INTERNAL_TMDS1:
-	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_TMDS1:
-	case ENCODER_OBJECT_ID_INTERNAL_LVTM1:
-	case ENCODER_OBJECT_ID_INTERNAL_DVO1:
-	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
-	case ENCODER_OBJECT_ID_INTERNAL_DDI:
-	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
-	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
-	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
-	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
-	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static bool radeon_atom_mode_fixup(struct drm_encoder *encoder,
 				   const struct drm_display_mode *mode,
 				   struct drm_display_mode *adjusted_mode)
diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c
index f81d7ca134db..300d971187c4 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.c
+++ b/drivers/gpu/drm/radeon/btc_dpm.c
@@ -1170,23 +1170,6 @@ static const struct radeon_blacklist_clocks btc_blacklist_clocks[] =
         { 25000, 30000, RADEON_SCLK_UP }
 };
 
-void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
-						     u32 *max_clock)
-{
-	u32 i, clock = 0;
-
-	if ((table == NULL) || (table->count == 0)) {
-		*max_clock = clock;
-		return;
-	}
-
-	for (i = 0; i < table->count; i++) {
-		if (clock < table->entries[i].clk)
-			clock = table->entries[i].clk;
-	}
-	*max_clock = clock;
-}
-
 void btc_apply_voltage_dependency_rules(struct radeon_clock_voltage_dependency_table *table,
 					u32 clock, u16 max_voltage, u16 *voltage)
 {
@@ -2099,7 +2082,6 @@ static void btc_apply_state_adjust_rules(struct radeon_device *rdev,
 	bool disable_mclk_switching;
 	u32 mclk, sclk;
 	u16 vddc, vddci;
-	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
 	    btc_dpm_vblank_too_short(rdev))
@@ -2141,39 +2123,6 @@ static void btc_apply_state_adjust_rules(struct radeon_device *rdev,
 			ps->low.vddci = max_limits->vddci;
 	}
 
-	/* limit clocks to max supported clocks based on voltage dependency tables */
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
-							&max_sclk_vddc);
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
-							&max_mclk_vddci);
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
-							&max_mclk_vddc);
-
-	if (max_sclk_vddc) {
-		if (ps->low.sclk > max_sclk_vddc)
-			ps->low.sclk = max_sclk_vddc;
-		if (ps->medium.sclk > max_sclk_vddc)
-			ps->medium.sclk = max_sclk_vddc;
-		if (ps->high.sclk > max_sclk_vddc)
-			ps->high.sclk = max_sclk_vddc;
-	}
-	if (max_mclk_vddci) {
-		if (ps->low.mclk > max_mclk_vddci)
-			ps->low.mclk = max_mclk_vddci;
-		if (ps->medium.mclk > max_mclk_vddci)
-			ps->medium.mclk = max_mclk_vddci;
-		if (ps->high.mclk > max_mclk_vddci)
-			ps->high.mclk = max_mclk_vddci;
-	}
-	if (max_mclk_vddc) {
-		if (ps->low.mclk > max_mclk_vddc)
-			ps->low.mclk = max_mclk_vddc;
-		if (ps->medium.mclk > max_mclk_vddc)
-			ps->medium.mclk = max_mclk_vddc;
-		if (ps->high.mclk > max_mclk_vddc)
-			ps->high.mclk = max_mclk_vddc;
-	}
-
 	/* XXX validate the min clocks required for display */
 
 	if (disable_mclk_switching) {
diff --git a/drivers/gpu/drm/radeon/btc_dpm.h b/drivers/gpu/drm/radeon/btc_dpm.h
index 3b6f12b7760b..1a15e0e41950 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.h
+++ b/drivers/gpu/drm/radeon/btc_dpm.h
@@ -46,8 +46,6 @@ void btc_adjust_clock_combinations(struct radeon_device *rdev,
 				   struct rv7xx_pl *pl);
 void btc_apply_voltage_dependency_rules(struct radeon_clock_voltage_dependency_table *table,
 					u32 clock, u16 max_voltage, u16 *voltage);
-void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
-						     u32 *max_clock);
 void btc_apply_voltage_delta_rules(struct radeon_device *rdev,
 				   u16 max_vddc, u16 max_vddci,
 				   u16 *vddc, u16 *vddci);
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index d416bb2ff48d..f5c8c0445a94 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -162,8 +162,6 @@ static const struct ci_pt_config_reg didt_config_ci[] =
 };
 
 extern u8 rv770_get_memory_module_index(struct radeon_device *rdev);
-extern void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table,
-							    u32 *max_clock);
 extern int ni_copy_and_switch_arb_sets(struct radeon_device *rdev,
 				       u32 arb_freq_src, u32 arb_freq_dest);
 extern u8 si_get_ddr3_mclk_frequency_ratio(u32 memory_clock);
@@ -748,7 +746,6 @@ static void ci_apply_state_adjust_rules(struct radeon_device *rdev,
 	struct radeon_clock_and_voltage_limits *max_limits;
 	bool disable_mclk_switching;
 	u32 sclk, mclk;
-	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 	int i;
 
 	if (rps->vce_active) {
@@ -784,29 +781,6 @@ static void ci_apply_state_adjust_rules(struct radeon_device *rdev,
 		}
 	}
 
-	/* limit clocks to max supported clocks based on voltage dependency tables */
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
-							&max_sclk_vddc);
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
-							&max_mclk_vddci);
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
-							&max_mclk_vddc);
-
-	for (i = 0; i < ps->performance_level_count; i++) {
-		if (max_sclk_vddc) {
-			if (ps->performance_levels[i].sclk > max_sclk_vddc)
-				ps->performance_levels[i].sclk = max_sclk_vddc;
-		}
-		if (max_mclk_vddci) {
-			if (ps->performance_levels[i].mclk > max_mclk_vddci)
-				ps->performance_levels[i].mclk = max_mclk_vddci;
-		}
-		if (max_mclk_vddc) {
-			if (ps->performance_levels[i].mclk > max_mclk_vddc)
-				ps->performance_levels[i].mclk = max_mclk_vddc;
-		}
-	}
-
 	/* XXX validate the min clocks required for display */
 
 	if (disable_mclk_switching) {
@@ -5293,9 +5267,13 @@ int ci_dpm_init(struct radeon_device *rdev)
 void ci_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
 						    struct seq_file *m)
 {
+	struct ci_power_info *pi = ci_get_pi(rdev);
+	struct radeon_ps *rps = &pi->current_rps;
 	u32 sclk = ci_get_average_sclk_freq(rdev);
 	u32 mclk = ci_get_average_mclk_freq(rdev);
 
+	seq_printf(m, "uvd    %sabled\n", pi->uvd_enabled ? "en" : "dis");
+	seq_printf(m, "vce    %sabled\n", rps->vce_active ? "en" : "dis");
 	seq_printf(m, "power level avg    sclk: %u mclk: %u\n",
 		   sclk, mclk);
 }
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 3d546c606b43..377afa504d2b 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3959,18 +3959,19 @@ bool cik_semaphore_ring_emit(struct radeon_device *rdev,
  * @src_offset: src GPU address
  * @dst_offset: dst GPU address
  * @num_gpu_pages: number of GPU pages to xfer
- * @fence: radeon fence object
+ * @resv: reservation object to sync to
  *
  * Copy GPU paging using the CP DMA engine (CIK+).
  * Used by the radeon ttm implementation to move pages if
  * registered as the asic copy callback.
  */
-int cik_copy_cpdma(struct radeon_device *rdev,
-		   uint64_t src_offset, uint64_t dst_offset,
-		   unsigned num_gpu_pages,
-		   struct radeon_fence **fence)
+struct radeon_fence *cik_copy_cpdma(struct radeon_device *rdev,
+				    uint64_t src_offset, uint64_t dst_offset,
+				    unsigned num_gpu_pages,
+				    struct reservation_object *resv)
 {
 	struct radeon_semaphore *sem = NULL;
+	struct radeon_fence *fence;
 	int ring_index = rdev->asic->copy.blit_ring_index;
 	struct radeon_ring *ring = &rdev->ring[ring_index];
 	u32 size_in_bytes, cur_size_in_bytes, control;
@@ -3980,7 +3981,7 @@ int cik_copy_cpdma(struct radeon_device *rdev,
 	r = radeon_semaphore_create(rdev, &sem);
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
@@ -3989,10 +3990,10 @@ int cik_copy_cpdma(struct radeon_device *rdev,
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
-	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_resv(rdev, sem, resv, false);
 	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	for (i = 0; i < num_loops; i++) {
@@ -4014,17 +4015,17 @@ int cik_copy_cpdma(struct radeon_device *rdev,
 		dst_offset += cur_size_in_bytes;
 	}
 
-	r = radeon_fence_emit(rdev, fence, ring->idx);
+	r = radeon_fence_emit(rdev, &fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	radeon_ring_unlock_commit(rdev, ring, false);
-	radeon_semaphore_free(rdev, &sem, *fence);
+	radeon_semaphore_free(rdev, &sem, fence);
 
-	return r;
+	return fence;
 }
 
 /*
@@ -4234,7 +4235,7 @@ static int cik_cp_gfx_load_microcode(struct radeon_device *rdev)
 		WREG32(CP_PFP_UCODE_ADDR, 0);
 		for (i = 0; i < fw_size; i++)
 			WREG32(CP_PFP_UCODE_DATA, le32_to_cpup(fw_data++));
-		WREG32(CP_PFP_UCODE_ADDR, 0);
+		WREG32(CP_PFP_UCODE_ADDR, le32_to_cpu(pfp_hdr->header.ucode_version));
 
 		/* CE */
 		fw_data = (const __le32 *)
@@ -4243,7 +4244,7 @@ static int cik_cp_gfx_load_microcode(struct radeon_device *rdev)
 		WREG32(CP_CE_UCODE_ADDR, 0);
 		for (i = 0; i < fw_size; i++)
 			WREG32(CP_CE_UCODE_DATA, le32_to_cpup(fw_data++));
-		WREG32(CP_CE_UCODE_ADDR, 0);
+		WREG32(CP_CE_UCODE_ADDR, le32_to_cpu(ce_hdr->header.ucode_version));
 
 		/* ME */
 		fw_data = (const __be32 *)
@@ -4252,7 +4253,8 @@ static int cik_cp_gfx_load_microcode(struct radeon_device *rdev)
 		WREG32(CP_ME_RAM_WADDR, 0);
 		for (i = 0; i < fw_size; i++)
 			WREG32(CP_ME_RAM_DATA, le32_to_cpup(fw_data++));
-		WREG32(CP_ME_RAM_WADDR, 0);
+		WREG32(CP_ME_RAM_WADDR, le32_to_cpu(me_hdr->header.ucode_version));
+		WREG32(CP_ME_RAM_RADDR, le32_to_cpu(me_hdr->header.ucode_version));
 	} else {
 		const __be32 *fw_data;
 
@@ -4278,10 +4280,6 @@ static int cik_cp_gfx_load_microcode(struct radeon_device *rdev)
 		WREG32(CP_ME_RAM_WADDR, 0);
 	}
 
-	WREG32(CP_PFP_UCODE_ADDR, 0);
-	WREG32(CP_CE_UCODE_ADDR, 0);
-	WREG32(CP_ME_RAM_WADDR, 0);
-	WREG32(CP_ME_RAM_RADDR, 0);
 	return 0;
 }
 
@@ -4563,7 +4561,7 @@ static int cik_cp_compute_load_microcode(struct radeon_device *rdev)
 		WREG32(CP_MEC_ME1_UCODE_ADDR, 0);
 		for (i = 0; i < fw_size; i++)
 			WREG32(CP_MEC_ME1_UCODE_DATA, le32_to_cpup(fw_data++));
-		WREG32(CP_MEC_ME1_UCODE_ADDR, 0);
+		WREG32(CP_MEC_ME1_UCODE_ADDR, le32_to_cpu(mec_hdr->header.ucode_version));
 
 		/* MEC2 */
 		if (rdev->family == CHIP_KAVERI) {
@@ -4577,7 +4575,7 @@ static int cik_cp_compute_load_microcode(struct radeon_device *rdev)
 			WREG32(CP_MEC_ME2_UCODE_ADDR, 0);
 			for (i = 0; i < fw_size; i++)
 				WREG32(CP_MEC_ME2_UCODE_DATA, le32_to_cpup(fw_data++));
-			WREG32(CP_MEC_ME2_UCODE_ADDR, 0);
+			WREG32(CP_MEC_ME2_UCODE_ADDR, le32_to_cpu(mec2_hdr->header.ucode_version));
 		}
 	} else {
 		const __be32 *fw_data;
@@ -4689,7 +4687,7 @@ static int cik_mec_init(struct radeon_device *rdev)
 		r = radeon_bo_create(rdev,
 				     rdev->mec.num_mec *rdev->mec.num_pipe * MEC_HPD_SIZE * 2,
 				     PAGE_SIZE, true,
-				     RADEON_GEM_DOMAIN_GTT, 0, NULL,
+				     RADEON_GEM_DOMAIN_GTT, 0, NULL, NULL,
 				     &rdev->mec.hpd_eop_obj);
 		if (r) {
 			dev_warn(rdev->dev, "(%d) create HDP EOP bo failed\n", r);
@@ -4860,7 +4858,7 @@ static int cik_cp_compute_resume(struct radeon_device *rdev)
 					     sizeof(struct bonaire_mqd),
 					     PAGE_SIZE, true,
 					     RADEON_GEM_DOMAIN_GTT, 0, NULL,
-					     &rdev->ring[idx].mqd_obj);
+					     NULL, &rdev->ring[idx].mqd_obj);
 			if (r) {
 				dev_warn(rdev->dev, "(%d) create MQD bo failed\n", r);
 				return r;
@@ -6226,7 +6224,7 @@ static int cik_rlc_resume(struct radeon_device *rdev)
 		WREG32(RLC_GPM_UCODE_ADDR, 0);
 		for (i = 0; i < size; i++)
 			WREG32(RLC_GPM_UCODE_DATA, le32_to_cpup(fw_data++));
-		WREG32(RLC_GPM_UCODE_ADDR, 0);
+		WREG32(RLC_GPM_UCODE_ADDR, le32_to_cpu(hdr->header.ucode_version));
 	} else {
 		const __be32 *fw_data;
 
@@ -8255,8 +8253,10 @@ restart_ih:
 	}
 	if (queue_hotplug)
 		schedule_work(&rdev->hotplug_work);
-	if (queue_reset)
-		schedule_work(&rdev->reset_work);
+	if (queue_reset) {
+		rdev->needs_reset = true;
+		wake_up_all(&rdev->fence_queue);
+	}
 	if (queue_thermal)
 		schedule_work(&rdev->pm.dpm.thermal.work);
 	rdev->ih.rptr = rptr;
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index c4ffa54b1e3d..c77dad1a4576 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -530,18 +530,19 @@ void cik_sdma_fini(struct radeon_device *rdev)
  * @src_offset: src GPU address
  * @dst_offset: dst GPU address
  * @num_gpu_pages: number of GPU pages to xfer
- * @fence: radeon fence object
+ * @resv: reservation object to sync to
  *
  * Copy GPU paging using the DMA engine (CIK).
  * Used by the radeon ttm implementation to move pages if
  * registered as the asic copy callback.
  */
-int cik_copy_dma(struct radeon_device *rdev,
-		 uint64_t src_offset, uint64_t dst_offset,
-		 unsigned num_gpu_pages,
-		 struct radeon_fence **fence)
+struct radeon_fence *cik_copy_dma(struct radeon_device *rdev,
+				  uint64_t src_offset, uint64_t dst_offset,
+				  unsigned num_gpu_pages,
+				  struct reservation_object *resv)
 {
 	struct radeon_semaphore *sem = NULL;
+	struct radeon_fence *fence;
 	int ring_index = rdev->asic->copy.dma_ring_index;
 	struct radeon_ring *ring = &rdev->ring[ring_index];
 	u32 size_in_bytes, cur_size_in_bytes;
@@ -551,7 +552,7 @@ int cik_copy_dma(struct radeon_device *rdev,
 	r = radeon_semaphore_create(rdev, &sem);
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
@@ -560,10 +561,10 @@ int cik_copy_dma(struct radeon_device *rdev,
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
-	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_resv(rdev, sem, resv, false);
 	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	for (i = 0; i < num_loops; i++) {
@@ -582,17 +583,17 @@ int cik_copy_dma(struct radeon_device *rdev,
 		dst_offset += cur_size_in_bytes;
 	}
 
-	r = radeon_fence_emit(rdev, fence, ring->idx);
+	r = radeon_fence_emit(rdev, &fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	radeon_ring_unlock_commit(rdev, ring, false);
-	radeon_semaphore_free(rdev, &sem, *fence);
+	radeon_semaphore_free(rdev, &sem, fence);
 
-	return r;
+	return fence;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/dce3_1_afmt.c b/drivers/gpu/drm/radeon/dce3_1_afmt.c
index 51800e340a57..950af153f30e 100644
--- a/drivers/gpu/drm/radeon/dce3_1_afmt.c
+++ b/drivers/gpu/drm/radeon/dce3_1_afmt.c
@@ -165,7 +165,7 @@ void dce3_1_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *m
 
 	/* disable audio prior to setting up hw */
 	dig->afmt->pin = r600_audio_get_pin(rdev);
-	r600_audio_enable(rdev, dig->afmt->pin, false);
+	r600_audio_enable(rdev, dig->afmt->pin, 0);
 
 	r600_audio_set_dto(encoder, mode->clock);
 
@@ -240,5 +240,5 @@ void dce3_1_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *m
 	r600_hdmi_audio_workaround(encoder);
 
 	/* enable audio after to setting up hw */
-	r600_audio_enable(rdev, dig->afmt->pin, true);
+	r600_audio_enable(rdev, dig->afmt->pin, 0xf);
 }
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index ab29f953a767..c0bbf68dbc27 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -284,13 +284,13 @@ static int dce6_audio_chipset_supported(struct radeon_device *rdev)
 
 void dce6_audio_enable(struct radeon_device *rdev,
 		       struct r600_audio_pin *pin,
-		       bool enable)
+		       u8 enable_mask)
 {
 	if (!pin)
 		return;
 
-	WREG32_ENDPOINT(pin->offset, AZ_F0_CODEC_PIN_CONTROL_HOTPLUG_CONTROL,
-			enable ? AUDIO_ENABLED : 0);
+	WREG32_ENDPOINT(pin->offset, AZ_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL,
+			enable_mask ? AUDIO_ENABLED : 0);
 }
 
 static const u32 pin_offsets[7] =
diff --git a/drivers/gpu/drm/drm_buffer.c b/drivers/gpu/drm/radeon/drm_buffer.c
index 86a4a4a60afc..f4e0f3a3d7b1 100644
--- a/drivers/gpu/drm/drm_buffer.c
+++ b/drivers/gpu/drm/radeon/drm_buffer.c
@@ -33,7 +33,7 @@
  */
 
 #include <linux/export.h>
-#include <drm/drm_buffer.h>
+#include "drm_buffer.h"
 
 /**
  * Allocate the drm buffer object.
@@ -86,7 +86,6 @@ error_out:
 	kfree(*buf);
 	return -ENOMEM;
 }
-EXPORT_SYMBOL(drm_buffer_alloc);
 
 /**
  * Copy the user data to the begin of the buffer and reset the processing
@@ -123,7 +122,6 @@ int drm_buffer_copy_from_user(struct drm_buffer *buf,
 	buf->iterator = 0;
 	return 0;
 }
-EXPORT_SYMBOL(drm_buffer_copy_from_user);
 
 /**
  * Free the drm buffer object
@@ -141,7 +139,6 @@ void drm_buffer_free(struct drm_buffer *buf)
 		kfree(buf);
 	}
 }
-EXPORT_SYMBOL(drm_buffer_free);
 
 /**
  * Read an object from buffer that may be split to multiple parts. If object
@@ -178,4 +175,3 @@ void *drm_buffer_read_object(struct drm_buffer *buf,
 	drm_buffer_advance(buf, objsize);
 	return obj;
 }
-EXPORT_SYMBOL(drm_buffer_read_object);
diff --git a/include/drm/drm_buffer.h b/drivers/gpu/drm/radeon/drm_buffer.h
index c80d3a340b94..c80d3a340b94 100644
--- a/include/drm/drm_buffer.h
+++ b/drivers/gpu/drm/radeon/drm_buffer.h
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index e50807c29f69..a31f1ca40c6a 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -22,7 +22,6 @@
  * Authors: Alex Deucher
  */
 #include <linux/firmware.h>
-#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <drm/drmP.h>
 #include "radeon.h"
@@ -4023,7 +4022,7 @@ int sumo_rlc_init(struct radeon_device *rdev)
 		if (rdev->rlc.save_restore_obj == NULL) {
 			r = radeon_bo_create(rdev, dws * 4, PAGE_SIZE, true,
 					     RADEON_GEM_DOMAIN_VRAM, 0, NULL,
-					     &rdev->rlc.save_restore_obj);
+					     NULL, &rdev->rlc.save_restore_obj);
 			if (r) {
 				dev_warn(rdev->dev, "(%d) create RLC sr bo failed\n", r);
 				return r;
@@ -4102,7 +4101,7 @@ int sumo_rlc_init(struct radeon_device *rdev)
 		if (rdev->rlc.clear_state_obj == NULL) {
 			r = radeon_bo_create(rdev, dws * 4, PAGE_SIZE, true,
 					     RADEON_GEM_DOMAIN_VRAM, 0, NULL,
-					     &rdev->rlc.clear_state_obj);
+					     NULL, &rdev->rlc.clear_state_obj);
 			if (r) {
 				dev_warn(rdev->dev, "(%d) create RLC c bo failed\n", r);
 				sumo_rlc_fini(rdev);
@@ -4179,7 +4178,7 @@ int sumo_rlc_init(struct radeon_device *rdev)
 			r = radeon_bo_create(rdev, rdev->rlc.cp_table_size,
 					     PAGE_SIZE, true,
 					     RADEON_GEM_DOMAIN_VRAM, 0, NULL,
-					     &rdev->rlc.cp_table_obj);
+					     NULL, &rdev->rlc.cp_table_obj);
 			if (r) {
 				dev_warn(rdev->dev, "(%d) create RLC cp table bo failed\n", r);
 				sumo_rlc_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/evergreen_dma.c b/drivers/gpu/drm/radeon/evergreen_dma.c
index afaba388c36d..66bcfadeedd1 100644
--- a/drivers/gpu/drm/radeon/evergreen_dma.c
+++ b/drivers/gpu/drm/radeon/evergreen_dma.c
@@ -104,12 +104,14 @@ void evergreen_dma_ring_ib_execute(struct radeon_device *rdev,
  * Used by the radeon ttm implementation to move pages if
  * registered as the asic copy callback.
  */
-int evergreen_copy_dma(struct radeon_device *rdev,
-		       uint64_t src_offset, uint64_t dst_offset,
-		       unsigned num_gpu_pages,
-		       struct radeon_fence **fence)
+struct radeon_fence *evergreen_copy_dma(struct radeon_device *rdev,
+					uint64_t src_offset,
+					uint64_t dst_offset,
+					unsigned num_gpu_pages,
+					struct reservation_object *resv)
 {
 	struct radeon_semaphore *sem = NULL;
+	struct radeon_fence *fence;
 	int ring_index = rdev->asic->copy.dma_ring_index;
 	struct radeon_ring *ring = &rdev->ring[ring_index];
 	u32 size_in_dw, cur_size_in_dw;
@@ -119,7 +121,7 @@ int evergreen_copy_dma(struct radeon_device *rdev,
 	r = radeon_semaphore_create(rdev, &sem);
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;
@@ -128,10 +130,10 @@ int evergreen_copy_dma(struct radeon_device *rdev,
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
-	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_resv(rdev, sem, resv, false);
 	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	for (i = 0; i < num_loops; i++) {
@@ -148,17 +150,17 @@ int evergreen_copy_dma(struct radeon_device *rdev,
 		dst_offset += cur_size_in_dw * 4;
 	}
 
-	r = radeon_fence_emit(rdev, fence, ring->idx);
+	r = radeon_fence_emit(rdev, &fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	radeon_ring_unlock_commit(rdev, ring, false);
-	radeon_semaphore_free(rdev, &sem, *fence);
+	radeon_semaphore_free(rdev, &sem, fence);
 
-	return r;
+	return fence;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index 278c7a139d74..2514d659b1ba 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -38,6 +38,37 @@ extern void dce6_afmt_select_pin(struct drm_encoder *encoder);
 extern void dce6_afmt_write_latency_fields(struct drm_encoder *encoder,
 					   struct drm_display_mode *mode);
 
+/* enable the audio stream */
+static void dce4_audio_enable(struct radeon_device *rdev,
+			      struct r600_audio_pin *pin,
+			      u8 enable_mask)
+{
+	u32 tmp = RREG32(AZ_HOT_PLUG_CONTROL);
+
+	if (!pin)
+		return;
+
+	if (enable_mask) {
+		tmp |= AUDIO_ENABLED;
+		if (enable_mask & 1)
+			tmp |= PIN0_AUDIO_ENABLED;
+		if (enable_mask & 2)
+			tmp |= PIN1_AUDIO_ENABLED;
+		if (enable_mask & 4)
+			tmp |= PIN2_AUDIO_ENABLED;
+		if (enable_mask & 8)
+			tmp |= PIN3_AUDIO_ENABLED;
+	} else {
+		tmp &= ~(AUDIO_ENABLED |
+			 PIN0_AUDIO_ENABLED |
+			 PIN1_AUDIO_ENABLED |
+			 PIN2_AUDIO_ENABLED |
+			 PIN3_AUDIO_ENABLED);
+	}
+
+	WREG32(AZ_HOT_PLUG_CONTROL, tmp);
+}
+
 /*
  * update the N and CTS parameters for a given pixel clock rate
  */
@@ -318,10 +349,10 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 	/* disable audio prior to setting up hw */
 	if (ASIC_IS_DCE6(rdev)) {
 		dig->afmt->pin = dce6_audio_get_pin(rdev);
-		dce6_audio_enable(rdev, dig->afmt->pin, false);
+		dce6_audio_enable(rdev, dig->afmt->pin, 0);
 	} else {
 		dig->afmt->pin = r600_audio_get_pin(rdev);
-		r600_audio_enable(rdev, dig->afmt->pin, false);
+		dce4_audio_enable(rdev, dig->afmt->pin, 0);
 	}
 
 	evergreen_audio_set_dto(encoder, mode->clock);
@@ -463,13 +494,15 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 
 	/* enable audio after to setting up hw */
 	if (ASIC_IS_DCE6(rdev))
-		dce6_audio_enable(rdev, dig->afmt->pin, true);
+		dce6_audio_enable(rdev, dig->afmt->pin, 1);
 	else
-		r600_audio_enable(rdev, dig->afmt->pin, true);
+		dce4_audio_enable(rdev, dig->afmt->pin, 0xf);
 }
 
 void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable)
 {
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 
@@ -482,6 +515,14 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable)
 	if (!enable && !dig->afmt->enabled)
 		return;
 
+	if (!enable && dig->afmt->pin) {
+		if (ASIC_IS_DCE6(rdev))
+			dce6_audio_enable(rdev, dig->afmt->pin, 0);
+		else
+			dce4_audio_enable(rdev, dig->afmt->pin, 0);
+		dig->afmt->pin = NULL;
+	}
+
 	dig->afmt->enabled = enable;
 
 	DRM_DEBUG("%sabling HDMI interface @ 0x%04X for encoder 0x%x\n",
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index 67cb472d188c..1dd976f447fa 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -2787,6 +2787,8 @@ void kv_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
 		tmp = (RREG32_SMC(SMU_VOLTAGE_STATUS) & SMU_VOLTAGE_CURRENT_LEVEL_MASK) >>
 			SMU_VOLTAGE_CURRENT_LEVEL_SHIFT;
 		vddc = kv_convert_8bit_index_to_voltage(rdev, (u16)tmp);
+		seq_printf(m, "uvd    %sabled\n", pi->uvd_power_gated ? "dis" : "en");
+		seq_printf(m, "vce    %sabled\n", pi->vce_power_gated ? "dis" : "en");
 		seq_printf(m, "power level %d    sclk: %u vddc: %u\n",
 			   current_index, sclk, vddc);
 	}
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index 01fc4888e6fe..715b181c6243 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -789,7 +789,6 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev,
 	bool disable_mclk_switching;
 	u32 mclk;
 	u16 vddci;
-	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 	int i;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
@@ -816,29 +815,6 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev,
 		}
 	}
 
-	/* limit clocks to max supported clocks based on voltage dependency tables */
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
-							&max_sclk_vddc);
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
-							&max_mclk_vddci);
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
-							&max_mclk_vddc);
-
-	for (i = 0; i < ps->performance_level_count; i++) {
-		if (max_sclk_vddc) {
-			if (ps->performance_levels[i].sclk > max_sclk_vddc)
-				ps->performance_levels[i].sclk = max_sclk_vddc;
-		}
-		if (max_mclk_vddci) {
-			if (ps->performance_levels[i].mclk > max_mclk_vddci)
-				ps->performance_levels[i].mclk = max_mclk_vddci;
-		}
-		if (max_mclk_vddc) {
-			if (ps->performance_levels[i].mclk > max_mclk_vddc)
-				ps->performance_levels[i].mclk = max_mclk_vddc;
-		}
-	}
-
 	/* XXX validate the min clocks required for display */
 
 	/* adjust low state */
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index b0098e792e62..10f8be0ee173 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -869,13 +869,14 @@ bool r100_semaphore_ring_emit(struct radeon_device *rdev,
 	return false;
 }
 
-int r100_copy_blit(struct radeon_device *rdev,
-		   uint64_t src_offset,
-		   uint64_t dst_offset,
-		   unsigned num_gpu_pages,
-		   struct radeon_fence **fence)
+struct radeon_fence *r100_copy_blit(struct radeon_device *rdev,
+				    uint64_t src_offset,
+				    uint64_t dst_offset,
+				    unsigned num_gpu_pages,
+				    struct reservation_object *resv)
 {
 	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
+	struct radeon_fence *fence;
 	uint32_t cur_pages;
 	uint32_t stride_bytes = RADEON_GPU_PAGE_SIZE;
 	uint32_t pitch;
@@ -896,7 +897,7 @@ int r100_copy_blit(struct radeon_device *rdev,
 	r = radeon_ring_lock(rdev, ring, ndw);
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d) asking for %u dw.\n", r, ndw);
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 	}
 	while (num_gpu_pages > 0) {
 		cur_pages = num_gpu_pages;
@@ -936,11 +937,13 @@ int r100_copy_blit(struct radeon_device *rdev,
 			  RADEON_WAIT_2D_IDLECLEAN |
 			  RADEON_WAIT_HOST_IDLECLEAN |
 			  RADEON_WAIT_DMA_GUI_IDLE);
-	if (fence) {
-		r = radeon_fence_emit(rdev, fence, RADEON_RING_TYPE_GFX_INDEX);
+	r = radeon_fence_emit(rdev, &fence, RADEON_RING_TYPE_GFX_INDEX);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return ERR_PTR(r);
 	}
 	radeon_ring_unlock_commit(rdev, ring, false);
-	return r;
+	return fence;
 }
 
 static int r100_cp_wait_for_idle(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c
index 67780374a652..732d4938aab7 100644
--- a/drivers/gpu/drm/radeon/r200.c
+++ b/drivers/gpu/drm/radeon/r200.c
@@ -80,13 +80,14 @@ static int r200_get_vtx_size_0(uint32_t vtx_fmt_0)
 	return vtx_size;
 }
 
-int r200_copy_dma(struct radeon_device *rdev,
-		  uint64_t src_offset,
-		  uint64_t dst_offset,
-		  unsigned num_gpu_pages,
-		  struct radeon_fence **fence)
+struct radeon_fence *r200_copy_dma(struct radeon_device *rdev,
+				   uint64_t src_offset,
+				   uint64_t dst_offset,
+				   unsigned num_gpu_pages,
+				   struct reservation_object *resv)
 {
 	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
+	struct radeon_fence *fence;
 	uint32_t size;
 	uint32_t cur_size;
 	int i, num_loops;
@@ -98,7 +99,7 @@ int r200_copy_dma(struct radeon_device *rdev,
 	r = radeon_ring_lock(rdev, ring, num_loops * 4 + 64);
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
+		return ERR_PTR(r);
 	}
 	/* Must wait for 2D idle & clean before DMA or hangs might happen */
 	radeon_ring_write(ring, PACKET0(RADEON_WAIT_UNTIL, 0));
@@ -118,11 +119,13 @@ int r200_copy_dma(struct radeon_device *rdev,
 	}
 	radeon_ring_write(ring, PACKET0(RADEON_WAIT_UNTIL, 0));
 	radeon_ring_write(ring, RADEON_WAIT_DMA_GUI_IDLE);
-	if (fence) {
-		r = radeon_fence_emit(rdev, fence, RADEON_RING_TYPE_GFX_INDEX);
+	r = radeon_fence_emit(rdev, &fence, RADEON_RING_TYPE_GFX_INDEX);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return ERR_PTR(r);
 	}
 	radeon_ring_unlock_commit(rdev, ring, false);
-	return r;
+	return fence;
 }
 
 
diff --git a/drivers/gpu/drm/radeon/r300_cmdbuf.c b/drivers/gpu/drm/radeon/r300_cmdbuf.c
index 84b1d5367a11..9418e388b045 100644
--- a/drivers/gpu/drm/radeon/r300_cmdbuf.c
+++ b/drivers/gpu/drm/radeon/r300_cmdbuf.c
@@ -34,10 +34,10 @@
  */
 
 #include <drm/drmP.h>
-#include <drm/drm_buffer.h>
 #include <drm/radeon_drm.h>
 #include "radeon_drv.h"
 #include "r300_reg.h"
+#include "drm_buffer.h"
 
 #include <asm/unaligned.h>
 
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index ea5c9af722ef..56b02927cd3d 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -122,6 +122,94 @@ u32 r600_get_xclk(struct radeon_device *rdev)
 
 int r600_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk)
 {
+	unsigned fb_div = 0, ref_div, vclk_div = 0, dclk_div = 0;
+	int r;
+
+	/* bypass vclk and dclk with bclk */
+	WREG32_P(CG_UPLL_FUNC_CNTL_2,
+		 VCLK_SRC_SEL(1) | DCLK_SRC_SEL(1),
+		 ~(VCLK_SRC_SEL_MASK | DCLK_SRC_SEL_MASK));
+
+	/* assert BYPASS_EN, deassert UPLL_RESET, UPLL_SLEEP and UPLL_CTLREQ */
+	WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_BYPASS_EN_MASK, ~(
+		 UPLL_RESET_MASK | UPLL_SLEEP_MASK | UPLL_CTLREQ_MASK));
+
+	if (rdev->family >= CHIP_RS780)
+		WREG32_P(GFX_MACRO_BYPASS_CNTL, UPLL_BYPASS_CNTL,
+			 ~UPLL_BYPASS_CNTL);
+
+	if (!vclk || !dclk) {
+		/* keep the Bypass mode, put PLL to sleep */
+		WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK);
+		return 0;
+	}
+
+	if (rdev->clock.spll.reference_freq == 10000)
+		ref_div = 34;
+	else
+		ref_div = 4;
+
+	r = radeon_uvd_calc_upll_dividers(rdev, vclk, dclk, 50000, 160000,
+					  ref_div + 1, 0xFFF, 2, 30, ~0,
+					  &fb_div, &vclk_div, &dclk_div);
+	if (r)
+		return r;
+
+	if (rdev->family >= CHIP_RV670 && rdev->family < CHIP_RS780)
+		fb_div >>= 1;
+	else
+		fb_div |= 1;
+
+	r = radeon_uvd_send_upll_ctlreq(rdev, CG_UPLL_FUNC_CNTL);
+        if (r)
+                return r;
+
+	/* assert PLL_RESET */
+	WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_RESET_MASK, ~UPLL_RESET_MASK);
+
+	/* For RS780 we have to choose ref clk */
+	if (rdev->family >= CHIP_RS780)
+		WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_REFCLK_SRC_SEL_MASK,
+			 ~UPLL_REFCLK_SRC_SEL_MASK);
+
+	/* set the required fb, ref and post divder values */
+	WREG32_P(CG_UPLL_FUNC_CNTL,
+		 UPLL_FB_DIV(fb_div) |
+		 UPLL_REF_DIV(ref_div),
+		 ~(UPLL_FB_DIV_MASK | UPLL_REF_DIV_MASK));
+	WREG32_P(CG_UPLL_FUNC_CNTL_2,
+		 UPLL_SW_HILEN(vclk_div >> 1) |
+		 UPLL_SW_LOLEN((vclk_div >> 1) + (vclk_div & 1)) |
+		 UPLL_SW_HILEN2(dclk_div >> 1) |
+		 UPLL_SW_LOLEN2((dclk_div >> 1) + (dclk_div & 1)) |
+		 UPLL_DIVEN_MASK | UPLL_DIVEN2_MASK,
+		 ~UPLL_SW_MASK);
+
+	/* give the PLL some time to settle */
+	mdelay(15);
+
+	/* deassert PLL_RESET */
+	WREG32_P(CG_UPLL_FUNC_CNTL, 0, ~UPLL_RESET_MASK);
+
+	mdelay(15);
+
+	/* deassert BYPASS EN */
+	WREG32_P(CG_UPLL_FUNC_CNTL, 0, ~UPLL_BYPASS_EN_MASK);
+
+	if (rdev->family >= CHIP_RS780)
+		WREG32_P(GFX_MACRO_BYPASS_CNTL, 0, ~UPLL_BYPASS_CNTL);
+
+	r = radeon_uvd_send_upll_ctlreq(rdev, CG_UPLL_FUNC_CNTL);
+	if (r)
+		return r;
+
+	/* switch VCLK and DCLK selection */
+	WREG32_P(CG_UPLL_FUNC_CNTL_2,
+		 VCLK_SRC_SEL(2) | DCLK_SRC_SEL(2),
+		 ~(VCLK_SRC_SEL_MASK | DCLK_SRC_SEL_MASK));
+
+	mdelay(100);
+
 	return 0;
 }
 
@@ -992,6 +1080,8 @@ static int r600_pcie_gart_enable(struct radeon_device *rdev)
 	WREG32(MC_VM_L1_TLB_MCB_WR_GFX_CNTL, tmp);
 	WREG32(MC_VM_L1_TLB_MCB_RD_PDMA_CNTL, tmp);
 	WREG32(MC_VM_L1_TLB_MCB_WR_PDMA_CNTL, tmp);
+	WREG32(MC_VM_L1_TLB_MCB_RD_UVD_CNTL, tmp);
+	WREG32(MC_VM_L1_TLB_MCB_WR_UVD_CNTL, tmp);
 	WREG32(MC_VM_L1_TLB_MCB_RD_SEM_CNTL, tmp | ENABLE_SEMAPHORE_MODE);
 	WREG32(MC_VM_L1_TLB_MCB_WR_SEM_CNTL, tmp | ENABLE_SEMAPHORE_MODE);
 	WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
@@ -1042,6 +1132,8 @@ static void r600_pcie_gart_disable(struct radeon_device *rdev)
 	WREG32(MC_VM_L1_TLB_MCB_WR_SYS_CNTL, tmp);
 	WREG32(MC_VM_L1_TLB_MCB_RD_HDP_CNTL, tmp);
 	WREG32(MC_VM_L1_TLB_MCB_WR_HDP_CNTL, tmp);
+	WREG32(MC_VM_L1_TLB_MCB_RD_UVD_CNTL, tmp);
+	WREG32(MC_VM_L1_TLB_MCB_WR_UVD_CNTL, tmp);
 	radeon_gart_table_vram_unpin(rdev);
 }
 
@@ -1338,7 +1430,7 @@ int r600_vram_scratch_init(struct radeon_device *rdev)
 	if (rdev->vram_scratch.robj == NULL) {
 		r = radeon_bo_create(rdev, RADEON_GPU_PAGE_SIZE,
 				     PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
-				     0, NULL, &rdev->vram_scratch.robj);
+				     0, NULL, NULL, &rdev->vram_scratch.robj);
 		if (r) {
 			return r;
 		}
@@ -2792,12 +2884,13 @@ bool r600_semaphore_ring_emit(struct radeon_device *rdev,
  * Used by the radeon ttm implementation to move pages if
  * registered as the asic copy callback.
  */
-int r600_copy_cpdma(struct radeon_device *rdev,
-		    uint64_t src_offset, uint64_t dst_offset,
-		    unsigned num_gpu_pages,
-		    struct radeon_fence **fence)
+struct radeon_fence *r600_copy_cpdma(struct radeon_device *rdev,
+				     uint64_t src_offset, uint64_t dst_offset,
+				     unsigned num_gpu_pages,
+				     struct reservation_object *resv)
 {
 	struct radeon_semaphore *sem = NULL;
+	struct radeon_fence *fence;
 	int ring_index = rdev->asic->copy.blit_ring_index;
 	struct radeon_ring *ring = &rdev->ring[ring_index];
 	u32 size_in_bytes, cur_size_in_bytes, tmp;
@@ -2807,7 +2900,7 @@ int r600_copy_cpdma(struct radeon_device *rdev,
 	r = radeon_semaphore_create(rdev, &sem);
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
@@ -2816,10 +2909,10 @@ int r600_copy_cpdma(struct radeon_device *rdev,
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
-	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_resv(rdev, sem, resv, false);
 	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
@@ -2846,17 +2939,17 @@ int r600_copy_cpdma(struct radeon_device *rdev,
 	radeon_ring_write(ring, (WAIT_UNTIL - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
 	radeon_ring_write(ring, WAIT_CP_DMA_IDLE_bit);
 
-	r = radeon_fence_emit(rdev, fence, ring->idx);
+	r = radeon_fence_emit(rdev, &fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	radeon_ring_unlock_commit(rdev, ring, false);
-	radeon_semaphore_free(rdev, &sem, *fence);
+	radeon_semaphore_free(rdev, &sem, fence);
 
-	return r;
+	return fence;
 }
 
 int r600_set_surface_reg(struct radeon_device *rdev, int reg,
@@ -2907,6 +3000,18 @@ static int r600_startup(struct radeon_device *rdev)
 		return r;
 	}
 
+	if (rdev->has_uvd) {
+		r = uvd_v1_0_resume(rdev);
+		if (!r) {
+			r = radeon_fence_driver_start_ring(rdev, R600_RING_TYPE_UVD_INDEX);
+			if (r) {
+				dev_err(rdev->dev, "failed initializing UVD fences (%d).\n", r);
+			}
+		}
+		if (r)
+			rdev->ring[R600_RING_TYPE_UVD_INDEX].ring_size = 0;
+	}
+
 	/* Enable IRQ */
 	if (!rdev->irq.installed) {
 		r = radeon_irq_kms_init(rdev);
@@ -2935,6 +3040,18 @@ static int r600_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
+	if (rdev->has_uvd) {
+		ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
+		if (ring->ring_size) {
+			r = radeon_ring_init(rdev, ring, ring->ring_size, 0,
+					     RADEON_CP_PACKET2);
+			if (!r)
+				r = uvd_v1_0_init(rdev);
+			if (r)
+				DRM_ERROR("radeon: failed initializing UVD (%d).\n", r);
+		}
+	}
+
 	r = radeon_ib_pool_init(rdev);
 	if (r) {
 		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
@@ -2994,6 +3111,10 @@ int r600_suspend(struct radeon_device *rdev)
 	radeon_pm_suspend(rdev);
 	r600_audio_fini(rdev);
 	r600_cp_stop(rdev);
+	if (rdev->has_uvd) {
+		uvd_v1_0_fini(rdev);
+		radeon_uvd_suspend(rdev);
+	}
 	r600_irq_suspend(rdev);
 	radeon_wb_disable(rdev);
 	r600_pcie_gart_disable(rdev);
@@ -3073,6 +3194,14 @@ int r600_init(struct radeon_device *rdev)
 	rdev->ring[RADEON_RING_TYPE_GFX_INDEX].ring_obj = NULL;
 	r600_ring_init(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX], 1024 * 1024);
 
+	if (rdev->has_uvd) {
+		r = radeon_uvd_init(rdev);
+		if (!r) {
+			rdev->ring[R600_RING_TYPE_UVD_INDEX].ring_obj = NULL;
+			r600_ring_init(rdev, &rdev->ring[R600_RING_TYPE_UVD_INDEX], 4096);
+		}
+	}
+
 	rdev->ih.ring_obj = NULL;
 	r600_ih_ring_init(rdev, 64 * 1024);
 
@@ -3102,6 +3231,10 @@ void r600_fini(struct radeon_device *rdev)
 	r600_audio_fini(rdev);
 	r600_cp_fini(rdev);
 	r600_irq_fini(rdev);
+	if (rdev->has_uvd) {
+		uvd_v1_0_fini(rdev);
+		radeon_uvd_fini(rdev);
+	}
 	radeon_wb_fini(rdev);
 	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
@@ -3235,7 +3368,7 @@ int r600_ih_ring_alloc(struct radeon_device *rdev)
 		r = radeon_bo_create(rdev, rdev->ih.ring_size,
 				     PAGE_SIZE, true,
 				     RADEON_GEM_DOMAIN_GTT, 0,
-				     NULL, &rdev->ih.ring_obj);
+				     NULL, NULL, &rdev->ih.ring_obj);
 		if (r) {
 			DRM_ERROR("radeon: failed to create ih ring buffer (%d).\n", r);
 			return r;
diff --git a/drivers/gpu/drm/radeon/r600_audio.c b/drivers/gpu/drm/radeon/r600_audio.c
deleted file mode 100644
index bffac10c4296..000000000000
--- a/drivers/gpu/drm/radeon/r600_audio.c
+++ /dev/null
@@ -1,207 +0,0 @@
-/*
- * Copyright 2008 Advanced Micro Devices, Inc.
- * Copyright 2008 Red Hat Inc.
- * Copyright 2009 Christian König.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: Christian König
- */
-#include <drm/drmP.h>
-#include "radeon.h"
-#include "radeon_reg.h"
-#include "radeon_asic.h"
-#include "atom.h"
-
-/*
- * check if enc_priv stores radeon_encoder_atom_dig
- */
-static bool radeon_dig_encoder(struct drm_encoder *encoder)
-{
-	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
-	switch (radeon_encoder->encoder_id) {
-	case ENCODER_OBJECT_ID_INTERNAL_LVDS:
-	case ENCODER_OBJECT_ID_INTERNAL_TMDS1:
-	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_TMDS1:
-	case ENCODER_OBJECT_ID_INTERNAL_LVTM1:
-	case ENCODER_OBJECT_ID_INTERNAL_DVO1:
-	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
-	case ENCODER_OBJECT_ID_INTERNAL_DDI:
-	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
-	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
-	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
-	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
-		return true;
-	}
-	return false;
-}
-
-/*
- * check if the chipset is supported
- */
-static int r600_audio_chipset_supported(struct radeon_device *rdev)
-{
-	return ASIC_IS_DCE2(rdev) && !ASIC_IS_NODCE(rdev);
-}
-
-struct r600_audio_pin r600_audio_status(struct radeon_device *rdev)
-{
-	struct r600_audio_pin status;
-	uint32_t value;
-
-	value = RREG32(R600_AUDIO_RATE_BPS_CHANNEL);
-
-	/* number of channels */
-	status.channels = (value & 0x7) + 1;
-
-	/* bits per sample */
-	switch ((value & 0xF0) >> 4) {
-	case 0x0:
-		status.bits_per_sample = 8;
-		break;
-	case 0x1:
-		status.bits_per_sample = 16;
-		break;
-	case 0x2:
-		status.bits_per_sample = 20;
-		break;
-	case 0x3:
-		status.bits_per_sample = 24;
-		break;
-	case 0x4:
-		status.bits_per_sample = 32;
-		break;
-	default:
-		dev_err(rdev->dev, "Unknown bits per sample 0x%x, using 16\n",
-			(int)value);
-		status.bits_per_sample = 16;
-	}
-
-	/* current sampling rate in HZ */
-	if (value & 0x4000)
-		status.rate = 44100;
-	else
-		status.rate = 48000;
-	status.rate *= ((value >> 11) & 0x7) + 1;
-	status.rate /= ((value >> 8) & 0x7) + 1;
-
-	value = RREG32(R600_AUDIO_STATUS_BITS);
-
-	/* iec 60958 status bits */
-	status.status_bits = value & 0xff;
-
-	/* iec 60958 category code */
-	status.category_code = (value >> 8) & 0xff;
-
-	return status;
-}
-
-/*
- * update all hdmi interfaces with current audio parameters
- */
-void r600_audio_update_hdmi(struct work_struct *work)
-{
-	struct radeon_device *rdev = container_of(work, struct radeon_device,
-						  audio_work);
-	struct drm_device *dev = rdev->ddev;
-	struct r600_audio_pin audio_status = r600_audio_status(rdev);
-	struct drm_encoder *encoder;
-	bool changed = false;
-
-	if (rdev->audio.pin[0].channels != audio_status.channels ||
-	    rdev->audio.pin[0].rate != audio_status.rate ||
-	    rdev->audio.pin[0].bits_per_sample != audio_status.bits_per_sample ||
-	    rdev->audio.pin[0].status_bits != audio_status.status_bits ||
-	    rdev->audio.pin[0].category_code != audio_status.category_code) {
-		rdev->audio.pin[0] = audio_status;
-		changed = true;
-	}
-
-	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		if (!radeon_dig_encoder(encoder))
-			continue;
-		if (changed || r600_hdmi_buffer_status_changed(encoder))
-			r600_hdmi_update_audio_settings(encoder);
-	}
-}
-
-/* enable the audio stream */
-void r600_audio_enable(struct radeon_device *rdev,
-		       struct r600_audio_pin *pin,
-		       bool enable)
-{
-	u32 value = 0;
-
-	if (!pin)
-		return;
-
-	if (ASIC_IS_DCE4(rdev)) {
-		if (enable) {
-			value |= 0x81000000; /* Required to enable audio */
-			value |= 0x0e1000f0; /* fglrx sets that too */
-		}
-		WREG32(EVERGREEN_AUDIO_ENABLE, value);
-	} else {
-		WREG32_P(R600_AUDIO_ENABLE,
-			 enable ? 0x81000000 : 0x0, ~0x81000000);
-	}
-}
-
-/*
- * initialize the audio vars
- */
-int r600_audio_init(struct radeon_device *rdev)
-{
-	if (!radeon_audio || !r600_audio_chipset_supported(rdev))
-		return 0;
-
-	rdev->audio.enabled = true;
-
-	rdev->audio.num_pins = 1;
-	rdev->audio.pin[0].channels = -1;
-	rdev->audio.pin[0].rate = -1;
-	rdev->audio.pin[0].bits_per_sample = -1;
-	rdev->audio.pin[0].status_bits = 0;
-	rdev->audio.pin[0].category_code = 0;
-	rdev->audio.pin[0].id = 0;
-	/* disable audio.  it will be set up later */
-	r600_audio_enable(rdev, &rdev->audio.pin[0], false);
-
-	return 0;
-}
-
-/*
- * release the audio timer
- * TODO: How to do this correctly on SMP systems?
- */
-void r600_audio_fini(struct radeon_device *rdev)
-{
-	if (!rdev->audio.enabled)
-		return;
-
-	r600_audio_enable(rdev, &rdev->audio.pin[0], false);
-
-	rdev->audio.enabled = false;
-}
-
-struct r600_audio_pin *r600_audio_get_pin(struct radeon_device *rdev)
-{
-	/* only one pin on 6xx-NI */
-	return &rdev->audio.pin[0];
-}
diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c
index 8c9b7e26533c..09e3f39925fa 100644
--- a/drivers/gpu/drm/radeon/r600_cp.c
+++ b/drivers/gpu/drm/radeon/r600_cp.c
@@ -1949,15 +1949,15 @@ int r600_do_cleanup_cp(struct drm_device *dev)
 #if __OS_HAS_AGP
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		if (dev_priv->cp_ring != NULL) {
-			drm_core_ioremapfree(dev_priv->cp_ring, dev);
+			drm_legacy_ioremapfree(dev_priv->cp_ring, dev);
 			dev_priv->cp_ring = NULL;
 		}
 		if (dev_priv->ring_rptr != NULL) {
-			drm_core_ioremapfree(dev_priv->ring_rptr, dev);
+			drm_legacy_ioremapfree(dev_priv->ring_rptr, dev);
 			dev_priv->ring_rptr = NULL;
 		}
 		if (dev->agp_buffer_map != NULL) {
-			drm_core_ioremapfree(dev->agp_buffer_map, dev);
+			drm_legacy_ioremapfree(dev->agp_buffer_map, dev);
 			dev->agp_buffer_map = NULL;
 		}
 	} else
@@ -1968,7 +1968,7 @@ int r600_do_cleanup_cp(struct drm_device *dev)
 			r600_page_table_cleanup(dev, &dev_priv->gart_info);
 
 		if (dev_priv->gart_info.gart_table_location == DRM_ATI_GART_FB) {
-			drm_core_ioremapfree(&dev_priv->gart_info.mapping, dev);
+			drm_legacy_ioremapfree(&dev_priv->gart_info.mapping, dev);
 			dev_priv->gart_info.addr = NULL;
 		}
 	}
@@ -2052,27 +2052,27 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 	dev_priv->buffers_offset = init->buffers_offset;
 	dev_priv->gart_textures_offset = init->gart_textures_offset;
 
-	master_priv->sarea = drm_getsarea(dev);
+	master_priv->sarea = drm_legacy_getsarea(dev);
 	if (!master_priv->sarea) {
 		DRM_ERROR("could not find sarea!\n");
 		r600_do_cleanup_cp(dev);
 		return -EINVAL;
 	}
 
-	dev_priv->cp_ring = drm_core_findmap(dev, init->ring_offset);
+	dev_priv->cp_ring = drm_legacy_findmap(dev, init->ring_offset);
 	if (!dev_priv->cp_ring) {
 		DRM_ERROR("could not find cp ring region!\n");
 		r600_do_cleanup_cp(dev);
 		return -EINVAL;
 	}
-	dev_priv->ring_rptr = drm_core_findmap(dev, init->ring_rptr_offset);
+	dev_priv->ring_rptr = drm_legacy_findmap(dev, init->ring_rptr_offset);
 	if (!dev_priv->ring_rptr) {
 		DRM_ERROR("could not find ring read pointer!\n");
 		r600_do_cleanup_cp(dev);
 		return -EINVAL;
 	}
 	dev->agp_buffer_token = init->buffers_offset;
-	dev->agp_buffer_map = drm_core_findmap(dev, init->buffers_offset);
+	dev->agp_buffer_map = drm_legacy_findmap(dev, init->buffers_offset);
 	if (!dev->agp_buffer_map) {
 		DRM_ERROR("could not find dma buffer region!\n");
 		r600_do_cleanup_cp(dev);
@@ -2081,7 +2081,7 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 
 	if (init->gart_textures_offset) {
 		dev_priv->gart_textures =
-		    drm_core_findmap(dev, init->gart_textures_offset);
+		    drm_legacy_findmap(dev, init->gart_textures_offset);
 		if (!dev_priv->gart_textures) {
 			DRM_ERROR("could not find GART texture region!\n");
 			r600_do_cleanup_cp(dev);
@@ -2092,9 +2092,9 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 #if __OS_HAS_AGP
 	/* XXX */
 	if (dev_priv->flags & RADEON_IS_AGP) {
-		drm_core_ioremap_wc(dev_priv->cp_ring, dev);
-		drm_core_ioremap_wc(dev_priv->ring_rptr, dev);
-		drm_core_ioremap_wc(dev->agp_buffer_map, dev);
+		drm_legacy_ioremap_wc(dev_priv->cp_ring, dev);
+		drm_legacy_ioremap_wc(dev_priv->ring_rptr, dev);
+		drm_legacy_ioremap_wc(dev->agp_buffer_map, dev);
 		if (!dev_priv->cp_ring->handle ||
 		    !dev_priv->ring_rptr->handle ||
 		    !dev->agp_buffer_map->handle) {
@@ -2235,7 +2235,7 @@ int r600_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 		dev_priv->gart_info.mapping.size =
 			dev_priv->gart_info.table_size;
 
-		drm_core_ioremap_wc(&dev_priv->gart_info.mapping, dev);
+		drm_legacy_ioremap_wc(&dev_priv->gart_info.mapping, dev);
 		if (!dev_priv->gart_info.mapping.handle) {
 			DRM_ERROR("ioremap failed.\n");
 			r600_do_cleanup_cp(dev);
diff --git a/drivers/gpu/drm/radeon/r600_dma.c b/drivers/gpu/drm/radeon/r600_dma.c
index a908daa006d2..100189ec5fa8 100644
--- a/drivers/gpu/drm/radeon/r600_dma.c
+++ b/drivers/gpu/drm/radeon/r600_dma.c
@@ -427,18 +427,19 @@ void r600_dma_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
  * @src_offset: src GPU address
  * @dst_offset: dst GPU address
  * @num_gpu_pages: number of GPU pages to xfer
- * @fence: radeon fence object
+ * @resv: reservation object to sync to
  *
  * Copy GPU paging using the DMA engine (r6xx).
  * Used by the radeon ttm implementation to move pages if
  * registered as the asic copy callback.
  */
-int r600_copy_dma(struct radeon_device *rdev,
-		  uint64_t src_offset, uint64_t dst_offset,
-		  unsigned num_gpu_pages,
-		  struct radeon_fence **fence)
+struct radeon_fence *r600_copy_dma(struct radeon_device *rdev,
+				   uint64_t src_offset, uint64_t dst_offset,
+				   unsigned num_gpu_pages,
+				   struct reservation_object *resv)
 {
 	struct radeon_semaphore *sem = NULL;
+	struct radeon_fence *fence;
 	int ring_index = rdev->asic->copy.dma_ring_index;
 	struct radeon_ring *ring = &rdev->ring[ring_index];
 	u32 size_in_dw, cur_size_in_dw;
@@ -448,7 +449,7 @@ int r600_copy_dma(struct radeon_device *rdev,
 	r = radeon_semaphore_create(rdev, &sem);
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;
@@ -457,10 +458,10 @@ int r600_copy_dma(struct radeon_device *rdev,
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
-	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_resv(rdev, sem, resv, false);
 	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	for (i = 0; i < num_loops; i++) {
@@ -477,15 +478,15 @@ int r600_copy_dma(struct radeon_device *rdev,
 		dst_offset += cur_size_in_dw * 4;
 	}
 
-	r = radeon_fence_emit(rdev, fence, ring->idx);
+	r = radeon_fence_emit(rdev, &fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	radeon_ring_unlock_commit(rdev, ring, false);
-	radeon_semaphore_free(rdev, &sem, *fence);
+	radeon_semaphore_free(rdev, &sem, fence);
 
-	return r;
+	return fence;
 }
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index 26ef8ced6f89..b90dc0eb08e6 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -72,6 +72,169 @@ static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = {
 
 
 /*
+ * check if the chipset is supported
+ */
+static int r600_audio_chipset_supported(struct radeon_device *rdev)
+{
+	return ASIC_IS_DCE2(rdev) && !ASIC_IS_NODCE(rdev);
+}
+
+static struct r600_audio_pin r600_audio_status(struct radeon_device *rdev)
+{
+	struct r600_audio_pin status;
+	uint32_t value;
+
+	value = RREG32(R600_AUDIO_RATE_BPS_CHANNEL);
+
+	/* number of channels */
+	status.channels = (value & 0x7) + 1;
+
+	/* bits per sample */
+	switch ((value & 0xF0) >> 4) {
+	case 0x0:
+		status.bits_per_sample = 8;
+		break;
+	case 0x1:
+		status.bits_per_sample = 16;
+		break;
+	case 0x2:
+		status.bits_per_sample = 20;
+		break;
+	case 0x3:
+		status.bits_per_sample = 24;
+		break;
+	case 0x4:
+		status.bits_per_sample = 32;
+		break;
+	default:
+		dev_err(rdev->dev, "Unknown bits per sample 0x%x, using 16\n",
+			(int)value);
+		status.bits_per_sample = 16;
+	}
+
+	/* current sampling rate in HZ */
+	if (value & 0x4000)
+		status.rate = 44100;
+	else
+		status.rate = 48000;
+	status.rate *= ((value >> 11) & 0x7) + 1;
+	status.rate /= ((value >> 8) & 0x7) + 1;
+
+	value = RREG32(R600_AUDIO_STATUS_BITS);
+
+	/* iec 60958 status bits */
+	status.status_bits = value & 0xff;
+
+	/* iec 60958 category code */
+	status.category_code = (value >> 8) & 0xff;
+
+	return status;
+}
+
+/*
+ * update all hdmi interfaces with current audio parameters
+ */
+void r600_audio_update_hdmi(struct work_struct *work)
+{
+	struct radeon_device *rdev = container_of(work, struct radeon_device,
+						  audio_work);
+	struct drm_device *dev = rdev->ddev;
+	struct r600_audio_pin audio_status = r600_audio_status(rdev);
+	struct drm_encoder *encoder;
+	bool changed = false;
+
+	if (rdev->audio.pin[0].channels != audio_status.channels ||
+	    rdev->audio.pin[0].rate != audio_status.rate ||
+	    rdev->audio.pin[0].bits_per_sample != audio_status.bits_per_sample ||
+	    rdev->audio.pin[0].status_bits != audio_status.status_bits ||
+	    rdev->audio.pin[0].category_code != audio_status.category_code) {
+		rdev->audio.pin[0] = audio_status;
+		changed = true;
+	}
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (!radeon_encoder_is_digital(encoder))
+			continue;
+		if (changed || r600_hdmi_buffer_status_changed(encoder))
+			r600_hdmi_update_audio_settings(encoder);
+	}
+}
+
+/* enable the audio stream */
+void r600_audio_enable(struct radeon_device *rdev,
+		       struct r600_audio_pin *pin,
+		       u8 enable_mask)
+{
+	u32 tmp = RREG32(AZ_HOT_PLUG_CONTROL);
+
+	if (!pin)
+		return;
+
+	if (enable_mask) {
+		tmp |= AUDIO_ENABLED;
+		if (enable_mask & 1)
+			tmp |= PIN0_AUDIO_ENABLED;
+		if (enable_mask & 2)
+			tmp |= PIN1_AUDIO_ENABLED;
+		if (enable_mask & 4)
+			tmp |= PIN2_AUDIO_ENABLED;
+		if (enable_mask & 8)
+			tmp |= PIN3_AUDIO_ENABLED;
+	} else {
+		tmp &= ~(AUDIO_ENABLED |
+			 PIN0_AUDIO_ENABLED |
+			 PIN1_AUDIO_ENABLED |
+			 PIN2_AUDIO_ENABLED |
+			 PIN3_AUDIO_ENABLED);
+	}
+
+	WREG32(AZ_HOT_PLUG_CONTROL, tmp);
+}
+
+/*
+ * initialize the audio vars
+ */
+int r600_audio_init(struct radeon_device *rdev)
+{
+	if (!radeon_audio || !r600_audio_chipset_supported(rdev))
+		return 0;
+
+	rdev->audio.enabled = true;
+
+	rdev->audio.num_pins = 1;
+	rdev->audio.pin[0].channels = -1;
+	rdev->audio.pin[0].rate = -1;
+	rdev->audio.pin[0].bits_per_sample = -1;
+	rdev->audio.pin[0].status_bits = 0;
+	rdev->audio.pin[0].category_code = 0;
+	rdev->audio.pin[0].id = 0;
+	/* disable audio.  it will be set up later */
+	r600_audio_enable(rdev, &rdev->audio.pin[0], 0);
+
+	return 0;
+}
+
+/*
+ * release the audio timer
+ * TODO: How to do this correctly on SMP systems?
+ */
+void r600_audio_fini(struct radeon_device *rdev)
+{
+	if (!rdev->audio.enabled)
+		return;
+
+	r600_audio_enable(rdev, &rdev->audio.pin[0], 0);
+
+	rdev->audio.enabled = false;
+}
+
+struct r600_audio_pin *r600_audio_get_pin(struct radeon_device *rdev)
+{
+	/* only one pin on 6xx-NI */
+	return &rdev->audio.pin[0];
+}
+
+/*
  * calculate CTS and N values if they are not found in the table
  */
 static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int *N, int freq)
@@ -357,7 +520,7 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod
 
 	/* disable audio prior to setting up hw */
 	dig->afmt->pin = r600_audio_get_pin(rdev);
-	r600_audio_enable(rdev, dig->afmt->pin, false);
+	r600_audio_enable(rdev, dig->afmt->pin, 0xf);
 
 	r600_audio_set_dto(encoder, mode->clock);
 
@@ -443,7 +606,7 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod
 	WREG32(HDMI0_RAMP_CONTROL3 + offset, 0x00000001);
 
 	/* enable audio after to setting up hw */
-	r600_audio_enable(rdev, dig->afmt->pin, true);
+	r600_audio_enable(rdev, dig->afmt->pin, 0xf);
 }
 
 /**
@@ -528,6 +691,11 @@ void r600_hdmi_enable(struct drm_encoder *encoder, bool enable)
 	if (!enable && !dig->afmt->enabled)
 		return;
 
+	if (!enable && dig->afmt->pin) {
+		r600_audio_enable(rdev, dig->afmt->pin, 0);
+		dig->afmt->pin = NULL;
+	}
+
 	/* Older chipsets require setting HDMI and routing manually */
 	if (!ASIC_IS_DCE3(rdev)) {
 		if (enable)
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 31e1052ad3e3..1e8495cca41e 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -323,11 +323,12 @@
 #define	HDP_TILING_CONFIG				0x2F3C
 #define HDP_DEBUG1                                      0x2F34
 
+#define MC_CONFIG					0x2000
 #define MC_VM_AGP_TOP					0x2184
 #define MC_VM_AGP_BOT					0x2188
 #define	MC_VM_AGP_BASE					0x218C
 #define MC_VM_FB_LOCATION				0x2180
-#define MC_VM_L1_TLB_MCD_RD_A_CNTL			0x219C
+#define MC_VM_L1_TLB_MCB_RD_UVD_CNTL			0x2124
 #define 	ENABLE_L1_TLB					(1 << 0)
 #define		ENABLE_L1_FRAGMENT_PROCESSING			(1 << 1)
 #define		ENABLE_L1_STRICT_ORDERING			(1 << 2)
@@ -347,12 +348,14 @@
 #define		EFFECTIVE_L1_QUEUE_SIZE(x)			(((x) & 7) << 15)
 #define		EFFECTIVE_L1_QUEUE_SIZE_MASK			0x00038000
 #define		EFFECTIVE_L1_QUEUE_SIZE_SHIFT			15
+#define MC_VM_L1_TLB_MCD_RD_A_CNTL			0x219C
 #define MC_VM_L1_TLB_MCD_RD_B_CNTL			0x21A0
 #define MC_VM_L1_TLB_MCB_RD_GFX_CNTL			0x21FC
 #define MC_VM_L1_TLB_MCB_RD_HDP_CNTL			0x2204
 #define MC_VM_L1_TLB_MCB_RD_PDMA_CNTL			0x2208
 #define MC_VM_L1_TLB_MCB_RD_SEM_CNTL			0x220C
 #define	MC_VM_L1_TLB_MCB_RD_SYS_CNTL			0x2200
+#define MC_VM_L1_TLB_MCB_WR_UVD_CNTL			0x212c
 #define MC_VM_L1_TLB_MCD_WR_A_CNTL			0x21A4
 #define MC_VM_L1_TLB_MCD_WR_B_CNTL			0x21A8
 #define MC_VM_L1_TLB_MCB_WR_GFX_CNTL			0x2210
@@ -366,6 +369,8 @@
 #define MC_VM_SYSTEM_APERTURE_HIGH_ADDR			0x2194
 #define MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR		0x2198
 
+#define RS_DQ_RD_RET_CONF				0x2348
+
 #define	PA_CL_ENHANCE					0x8A14
 #define		CLIP_VTX_REORDER_ENA				(1 << 0)
 #define		NUM_CLIP_SEQ(x)					((x) << 1)
@@ -922,6 +927,23 @@
 #       define TARGET_LINK_SPEED_MASK                     (0xf << 0)
 #       define SELECTABLE_DEEMPHASIS                      (1 << 6)
 
+/* Audio */
+#define AZ_HOT_PLUG_CONTROL               0x7300
+#       define AZ_FORCE_CODEC_WAKE        (1 << 0)
+#       define JACK_DETECTION_ENABLE      (1 << 4)
+#       define UNSOLICITED_RESPONSE_ENABLE (1 << 8)
+#       define CODEC_HOT_PLUG_ENABLE      (1 << 12)
+#       define AUDIO_ENABLED              (1 << 31)
+/* DCE3 adds */
+#       define PIN0_JACK_DETECTION_ENABLE (1 << 4)
+#       define PIN1_JACK_DETECTION_ENABLE (1 << 5)
+#       define PIN2_JACK_DETECTION_ENABLE (1 << 6)
+#       define PIN3_JACK_DETECTION_ENABLE (1 << 7)
+#       define PIN0_AUDIO_ENABLED         (1 << 24)
+#       define PIN1_AUDIO_ENABLED         (1 << 25)
+#       define PIN2_AUDIO_ENABLED         (1 << 26)
+#       define PIN3_AUDIO_ENABLED         (1 << 27)
+
 /* Audio clocks DCE 2.0/3.0 */
 #define AUDIO_DTO                         0x7340
 #       define AUDIO_DTO_PHASE(x)         (((x) & 0xffff) << 0)
@@ -1476,6 +1498,7 @@
 #define UVD_CGC_GATE					0xf4a8
 #define UVD_LMI_CTRL2					0xf4f4
 #define UVD_MASTINT_EN					0xf500
+#define UVD_FW_START					0xf51C
 #define UVD_LMI_ADDR_EXT				0xf594
 #define UVD_LMI_CTRL					0xf598
 #define UVD_LMI_SWAP_CNTL				0xf5b4
@@ -1488,6 +1511,13 @@
 #define UVD_MPC_SET_MUX					0xf5f4
 #define UVD_MPC_SET_ALU					0xf5f8
 
+#define UVD_VCPU_CACHE_OFFSET0				0xf608
+#define UVD_VCPU_CACHE_SIZE0				0xf60c
+#define UVD_VCPU_CACHE_OFFSET1				0xf610
+#define UVD_VCPU_CACHE_SIZE1				0xf614
+#define UVD_VCPU_CACHE_OFFSET2				0xf618
+#define UVD_VCPU_CACHE_SIZE2				0xf61c
+
 #define UVD_VCPU_CNTL					0xf660
 #define UVD_SOFT_RESET					0xf680
 #define		RBC_SOFT_RESET					(1<<0)
@@ -1517,9 +1547,35 @@
 
 #define UVD_CONTEXT_ID					0xf6f4
 
+/* rs780 only */
+#define	GFX_MACRO_BYPASS_CNTL				0x30c0
+#define		SPLL_BYPASS_CNTL			(1 << 0)
+#define		UPLL_BYPASS_CNTL			(1 << 1)
+
+#define CG_UPLL_FUNC_CNTL				0x7e0
+#	define UPLL_RESET_MASK				0x00000001
+#	define UPLL_SLEEP_MASK				0x00000002
+#	define UPLL_BYPASS_EN_MASK			0x00000004
 #	define UPLL_CTLREQ_MASK				0x00000008
+#	define UPLL_FB_DIV(x)				((x) << 4)
+#	define UPLL_FB_DIV_MASK				0x0000FFF0
+#	define UPLL_REF_DIV(x)				((x) << 16)
+#	define UPLL_REF_DIV_MASK			0x003F0000
+#	define UPLL_REFCLK_SRC_SEL_MASK			0x20000000
 #	define UPLL_CTLACK_MASK				0x40000000
 #	define UPLL_CTLACK2_MASK			0x80000000
+#define CG_UPLL_FUNC_CNTL_2				0x7e4
+#	define UPLL_SW_HILEN(x)				((x) << 0)
+#	define UPLL_SW_LOLEN(x)				((x) << 4)
+#	define UPLL_SW_HILEN2(x)			((x) << 8)
+#	define UPLL_SW_LOLEN2(x)			((x) << 12)
+#	define UPLL_DIVEN_MASK				0x00010000
+#	define UPLL_DIVEN2_MASK				0x00020000
+#	define UPLL_SW_MASK				0x0003FFFF
+#	define VCLK_SRC_SEL(x)				((x) << 20)
+#	define VCLK_SRC_SEL_MASK			0x01F00000
+#	define DCLK_SRC_SEL(x)				((x) << 25)
+#	define DCLK_SRC_SEL_MASK			0x3E000000
 
 /*
  * PM4
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 3247bfd14410..f7c4b226a284 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -65,6 +65,8 @@
 #include <linux/list.h>
 #include <linux/kref.h>
 #include <linux/interval_tree.h>
+#include <linux/hashtable.h>
+#include <linux/fence.h>
 
 #include <ttm/ttm_bo_api.h>
 #include <ttm/ttm_bo_driver.h>
@@ -72,6 +74,8 @@
 #include <ttm/ttm_module.h>
 #include <ttm/ttm_execbuf_util.h>
 
+#include <drm/drm_gem.h>
+
 #include "radeon_family.h"
 #include "radeon_mode.h"
 #include "radeon_reg.h"
@@ -120,9 +124,6 @@ extern int radeon_backlight;
 #define RADEONFB_CONN_LIMIT			4
 #define RADEON_BIOS_NUM_SCRATCH			8
 
-/* fence seq are set to this number when signaled */
-#define RADEON_FENCE_SIGNALED_SEQ		0LL
-
 /* internal ring indices */
 /* r1xx+ has gfx CP ring */
 #define RADEON_RING_TYPE_GFX_INDEX		0
@@ -350,28 +351,32 @@ extern void evergreen_tiling_fields(unsigned tiling_flags, unsigned *bankw,
  * Fences.
  */
 struct radeon_fence_driver {
+	struct radeon_device		*rdev;
 	uint32_t			scratch_reg;
 	uint64_t			gpu_addr;
 	volatile uint32_t		*cpu_addr;
 	/* sync_seq is protected by ring emission lock */
 	uint64_t			sync_seq[RADEON_NUM_RINGS];
 	atomic64_t			last_seq;
-	bool				initialized;
+	bool				initialized, delayed_irq;
+	struct delayed_work		lockup_work;
 };
 
 struct radeon_fence {
+	struct fence base;
+
 	struct radeon_device		*rdev;
-	struct kref			kref;
-	/* protected by radeon_fence.lock */
 	uint64_t			seq;
 	/* RB, DMA, etc. */
 	unsigned			ring;
+
+	wait_queue_t			fence_wake;
 };
 
 int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring);
 int radeon_fence_driver_init(struct radeon_device *rdev);
 void radeon_fence_driver_fini(struct radeon_device *rdev);
-void radeon_fence_driver_force_completion(struct radeon_device *rdev);
+void radeon_fence_driver_force_completion(struct radeon_device *rdev, int ring);
 int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence **fence, int ring);
 void radeon_fence_process(struct radeon_device *rdev, int ring);
 bool radeon_fence_signaled(struct radeon_fence *fence);
@@ -469,7 +474,7 @@ struct radeon_bo {
 	struct list_head		list;
 	/* Protected by tbo.reserved */
 	u32				initial_domain;
-	u32				placements[3];
+	struct ttm_place		placements[3];
 	struct ttm_placement		placement;
 	struct ttm_buffer_object	tbo;
 	struct ttm_bo_kmap_obj		kmap;
@@ -489,6 +494,9 @@ struct radeon_bo {
 
 	struct ttm_bo_kmap_obj		dma_buf_vmap;
 	pid_t				pid;
+
+	struct radeon_mn		*mn;
+	struct interval_tree_node	mn_it;
 };
 #define gem_to_radeon_bo(gobj) container_of((gobj), struct radeon_bo, gem_base)
 
@@ -580,8 +588,12 @@ bool radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
 				  struct radeon_semaphore *semaphore);
 bool radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
 				struct radeon_semaphore *semaphore);
-void radeon_semaphore_sync_to(struct radeon_semaphore *semaphore,
-			      struct radeon_fence *fence);
+void radeon_semaphore_sync_fence(struct radeon_semaphore *semaphore,
+				 struct radeon_fence *fence);
+int radeon_semaphore_sync_resv(struct radeon_device *rdev,
+			       struct radeon_semaphore *semaphore,
+			       struct reservation_object *resv,
+			       bool shared);
 int radeon_semaphore_sync_rings(struct radeon_device *rdev,
 				struct radeon_semaphore *semaphore,
 				int waiting_ring);
@@ -702,7 +714,7 @@ struct radeon_flip_work {
 	uint64_t			base;
 	struct drm_pending_vblank_event *event;
 	struct radeon_bo		*old_rbo;
-	struct radeon_fence		*fence;
+	struct fence			*fence;
 };
 
 struct r500_irq_stat_regs {
@@ -780,6 +792,7 @@ struct radeon_irq {
 int radeon_irq_kms_init(struct radeon_device *rdev);
 void radeon_irq_kms_fini(struct radeon_device *rdev);
 void radeon_irq_kms_sw_irq_get(struct radeon_device *rdev, int ring);
+bool radeon_irq_kms_sw_irq_get_delayed(struct radeon_device *rdev, int ring);
 void radeon_irq_kms_sw_irq_put(struct radeon_device *rdev, int ring);
 void radeon_irq_kms_pflip_irq_get(struct radeon_device *rdev, int crtc);
 void radeon_irq_kms_pflip_irq_put(struct radeon_device *rdev, int crtc);
@@ -1642,7 +1655,8 @@ int radeon_uvd_get_create_msg(struct radeon_device *rdev, int ring,
 			      uint32_t handle, struct radeon_fence **fence);
 int radeon_uvd_get_destroy_msg(struct radeon_device *rdev, int ring,
 			       uint32_t handle, struct radeon_fence **fence);
-void radeon_uvd_force_into_uvd_segment(struct radeon_bo *rbo);
+void radeon_uvd_force_into_uvd_segment(struct radeon_bo *rbo,
+				       uint32_t allowed_domains);
 void radeon_uvd_free_handles(struct radeon_device *rdev,
 			     struct drm_file *filp);
 int radeon_uvd_cs_parse(struct radeon_cs_parser *parser);
@@ -1731,6 +1745,11 @@ void radeon_test_ring_sync(struct radeon_device *rdev,
 			   struct radeon_ring *cpB);
 void radeon_test_syncing(struct radeon_device *rdev);
 
+/*
+ * MMU Notifier
+ */
+int radeon_mn_register(struct radeon_bo *bo, unsigned long addr);
+void radeon_mn_unregister(struct radeon_bo *bo);
 
 /*
  * Debugfs
@@ -1845,24 +1864,24 @@ struct radeon_asic {
 	} display;
 	/* copy functions for bo handling */
 	struct {
-		int (*blit)(struct radeon_device *rdev,
-			    uint64_t src_offset,
-			    uint64_t dst_offset,
-			    unsigned num_gpu_pages,
-			    struct radeon_fence **fence);
+		struct radeon_fence *(*blit)(struct radeon_device *rdev,
+					     uint64_t src_offset,
+					     uint64_t dst_offset,
+					     unsigned num_gpu_pages,
+					     struct reservation_object *resv);
 		u32 blit_ring_index;
-		int (*dma)(struct radeon_device *rdev,
-			   uint64_t src_offset,
-			   uint64_t dst_offset,
-			   unsigned num_gpu_pages,
-			   struct radeon_fence **fence);
+		struct radeon_fence *(*dma)(struct radeon_device *rdev,
+					    uint64_t src_offset,
+					    uint64_t dst_offset,
+					    unsigned num_gpu_pages,
+					    struct reservation_object *resv);
 		u32 dma_ring_index;
 		/* method used for bo copy */
-		int (*copy)(struct radeon_device *rdev,
-			    uint64_t src_offset,
-			    uint64_t dst_offset,
-			    unsigned num_gpu_pages,
-			    struct radeon_fence **fence);
+		struct radeon_fence *(*copy)(struct radeon_device *rdev,
+					     uint64_t src_offset,
+					     uint64_t dst_offset,
+					     unsigned num_gpu_pages,
+					     struct reservation_object *resv);
 		/* ring used for bo copies */
 		u32 copy_ring_index;
 	} copy;
@@ -2144,6 +2163,8 @@ int radeon_gem_info_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp);
 int radeon_gem_create_ioctl(struct drm_device *dev, void *data,
 			    struct drm_file *filp);
+int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *filp);
 int radeon_gem_pin_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
 int radeon_gem_unpin_ioctl(struct drm_device *dev, void *data,
@@ -2300,6 +2321,7 @@ struct radeon_device {
 	struct radeon_mman		mman;
 	struct radeon_fence_driver	fence_drv[RADEON_NUM_RINGS];
 	wait_queue_head_t		fence_queue;
+	unsigned			fence_context;
 	struct mutex			ring_lock;
 	struct radeon_ring		ring[RADEON_NUM_RINGS];
 	bool				ib_pool_ready;
@@ -2318,7 +2340,7 @@ struct radeon_device {
 	bool				need_dma32;
 	bool				accel_working;
 	bool				fastfb_working; /* IGP feature*/
-	bool				needs_reset;
+	bool				needs_reset, in_reset;
 	struct radeon_surface_reg surface_regs[RADEON_GEM_MAX_SURFACES];
 	const struct firmware *me_fw;	/* all family ME firmware */
 	const struct firmware *pfp_fw;	/* r6/700 PFP firmware */
@@ -2339,7 +2361,6 @@ struct radeon_device {
 	struct radeon_mec mec;
 	struct work_struct hotplug_work;
 	struct work_struct audio_work;
-	struct work_struct reset_work;
 	int num_crtc; /* number of crtcs */
 	struct mutex dc_hw_i2c_mutex; /* display controller hw i2c mutex */
 	bool has_uvd;
@@ -2376,6 +2397,9 @@ struct radeon_device {
 	/* tracking pinned memory */
 	u64 vram_pin_size;
 	u64 gart_pin_size;
+
+	struct mutex	mn_lock;
+	DECLARE_HASHTABLE(mn_hash, 7);
 };
 
 bool radeon_is_px(struct drm_device *dev);
@@ -2431,7 +2455,17 @@ void cik_mm_wdoorbell(struct radeon_device *rdev, u32 index, u32 v);
 /*
  * Cast helper
  */
-#define to_radeon_fence(p) ((struct radeon_fence *)(p))
+extern const struct fence_ops radeon_fence_ops;
+
+static inline struct radeon_fence *to_radeon_fence(struct fence *f)
+{
+	struct radeon_fence *__f = container_of(f, struct radeon_fence, base);
+
+	if (__f->base.ops == &radeon_fence_ops)
+		return __f;
+
+	return NULL;
+}
 
 /*
  * Registers read & write functions.
@@ -2751,18 +2785,25 @@ void radeon_atombios_fini(struct radeon_device *rdev);
 /*
  * RING helpers.
  */
-#if DRM_DEBUG_CODE == 0
+
+/**
+ * radeon_ring_write - write a value to the ring
+ *
+ * @ring: radeon_ring structure holding ring information
+ * @v: dword (dw) value to write
+ *
+ * Write a value to the requested ring buffer (all asics).
+ */
 static inline void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
 {
+	if (ring->count_dw <= 0)
+		DRM_ERROR("radeon: writing more dwords to the ring than expected!\n");
+
 	ring->ring[ring->wptr++] = v;
 	ring->wptr &= ring->ptr_mask;
 	ring->count_dw--;
 	ring->ring_free_dw--;
 }
-#else
-/* With debugging this is just too big to inline */
-void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
-#endif
 
 /*
  * ASICs macro.
@@ -2801,9 +2842,9 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_hdmi_setmode(rdev, e, m) (rdev)->asic->display.hdmi_setmode((e), (m))
 #define radeon_fence_ring_emit(rdev, r, fence) (rdev)->asic->ring[(r)]->emit_fence((rdev), (fence))
 #define radeon_semaphore_ring_emit(rdev, r, cp, semaphore, emit_wait) (rdev)->asic->ring[(r)]->emit_semaphore((rdev), (cp), (semaphore), (emit_wait))
-#define radeon_copy_blit(rdev, s, d, np, f) (rdev)->asic->copy.blit((rdev), (s), (d), (np), (f))
-#define radeon_copy_dma(rdev, s, d, np, f) (rdev)->asic->copy.dma((rdev), (s), (d), (np), (f))
-#define radeon_copy(rdev, s, d, np, f) (rdev)->asic->copy.copy((rdev), (s), (d), (np), (f))
+#define radeon_copy_blit(rdev, s, d, np, resv) (rdev)->asic->copy.blit((rdev), (s), (d), (np), (resv))
+#define radeon_copy_dma(rdev, s, d, np, resv) (rdev)->asic->copy.dma((rdev), (s), (d), (np), (resv))
+#define radeon_copy(rdev, s, d, np, resv) (rdev)->asic->copy.copy((rdev), (s), (d), (np), (resv))
 #define radeon_copy_blit_ring_index(rdev) (rdev)->asic->copy.blit_ring_index
 #define radeon_copy_dma_ring_index(rdev) (rdev)->asic->copy.dma_ring_index
 #define radeon_copy_ring_index(rdev) (rdev)->asic->copy.copy_ring_index
@@ -2877,6 +2918,10 @@ extern void radeon_legacy_set_clock_gating(struct radeon_device *rdev, int enabl
 extern void radeon_atom_set_clock_gating(struct radeon_device *rdev, int enable);
 extern void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain);
 extern bool radeon_ttm_bo_is_radeon_bo(struct ttm_buffer_object *bo);
+extern int radeon_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
+				     uint32_t flags);
+extern bool radeon_ttm_tt_has_userptr(struct ttm_tt *ttm);
+extern bool radeon_ttm_tt_is_readonly(struct ttm_tt *ttm);
 extern void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 base);
 extern void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
 extern int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon);
@@ -2934,10 +2979,10 @@ struct r600_audio_pin *r600_audio_get_pin(struct radeon_device *rdev);
 struct r600_audio_pin *dce6_audio_get_pin(struct radeon_device *rdev);
 void r600_audio_enable(struct radeon_device *rdev,
 		       struct r600_audio_pin *pin,
-		       bool enable);
+		       u8 enable_mask);
 void dce6_audio_enable(struct radeon_device *rdev,
 		       struct r600_audio_pin *pin,
-		       bool enable);
+		       u8 enable_mask);
 
 /*
  * R600 vram scratch functions
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 2dd5847f9b98..850de57069be 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -963,6 +963,19 @@ static struct radeon_asic r600_asic = {
 	},
 };
 
+static struct radeon_asic_ring rv6xx_uvd_ring = {
+	.ib_execute = &uvd_v1_0_ib_execute,
+	.emit_fence = &uvd_v1_0_fence_emit,
+	.emit_semaphore = &uvd_v1_0_semaphore_emit,
+	.cs_parse = &radeon_uvd_cs_parse,
+	.ring_test = &uvd_v1_0_ring_test,
+	.ib_test = &uvd_v1_0_ib_test,
+	.is_lockup = &radeon_ring_test_lockup,
+	.get_rptr = &uvd_v1_0_get_rptr,
+	.get_wptr = &uvd_v1_0_get_wptr,
+	.set_wptr = &uvd_v1_0_set_wptr,
+};
+
 static struct radeon_asic rv6xx_asic = {
 	.init = &r600_init,
 	.fini = &r600_fini,
@@ -982,6 +995,7 @@ static struct radeon_asic rv6xx_asic = {
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &r600_gfx_ring,
 		[R600_RING_TYPE_DMA_INDEX] = &r600_dma_ring,
+		[R600_RING_TYPE_UVD_INDEX] = &rv6xx_uvd_ring,
 	},
 	.irq = {
 		.set = &r600_irq_set,
@@ -1072,6 +1086,7 @@ static struct radeon_asic rs780_asic = {
 	.ring = {
 		[RADEON_RING_TYPE_GFX_INDEX] = &r600_gfx_ring,
 		[R600_RING_TYPE_DMA_INDEX] = &r600_dma_ring,
+		[R600_RING_TYPE_UVD_INDEX] = &rv6xx_uvd_ring,
 	},
 	.irq = {
 		.set = &r600_irq_set,
@@ -2296,7 +2311,15 @@ int radeon_asic_init(struct radeon_device *rdev)
 	case CHIP_RS780:
 	case CHIP_RS880:
 		rdev->asic = &rs780_asic;
-		rdev->has_uvd = true;
+		/* 760G/780V/880V don't have UVD */
+		if ((rdev->pdev->device == 0x9616)||
+		    (rdev->pdev->device == 0x9611)||
+		    (rdev->pdev->device == 0x9613)||
+		    (rdev->pdev->device == 0x9711)||
+		    (rdev->pdev->device == 0x9713))
+			rdev->has_uvd = false;
+		else
+			rdev->has_uvd = true;
 		break;
 	case CHIP_RV770:
 	case CHIP_RV730:
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 7756bc1e1cd3..d8ace5b28a5b 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -81,11 +81,11 @@ bool r100_semaphore_ring_emit(struct radeon_device *rdev,
 int r100_cs_parse(struct radeon_cs_parser *p);
 void r100_pll_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 uint32_t r100_pll_rreg(struct radeon_device *rdev, uint32_t reg);
-int r100_copy_blit(struct radeon_device *rdev,
-		   uint64_t src_offset,
-		   uint64_t dst_offset,
-		   unsigned num_gpu_pages,
-		   struct radeon_fence **fence);
+struct radeon_fence *r100_copy_blit(struct radeon_device *rdev,
+				    uint64_t src_offset,
+				    uint64_t dst_offset,
+				    unsigned num_gpu_pages,
+				    struct reservation_object *resv);
 int r100_set_surface_reg(struct radeon_device *rdev, int reg,
 			 uint32_t tiling_flags, uint32_t pitch,
 			 uint32_t offset, uint32_t obj_size);
@@ -152,11 +152,11 @@ void r100_gfx_set_wptr(struct radeon_device *rdev,
 /*
  * r200,rv250,rs300,rv280
  */
-extern int r200_copy_dma(struct radeon_device *rdev,
-			 uint64_t src_offset,
-			 uint64_t dst_offset,
-			 unsigned num_gpu_pages,
-			 struct radeon_fence **fence);
+struct radeon_fence *r200_copy_dma(struct radeon_device *rdev,
+				   uint64_t src_offset,
+				   uint64_t dst_offset,
+				   unsigned num_gpu_pages,
+				   struct reservation_object *resv);
 void r200_set_safe_registers(struct radeon_device *rdev);
 
 /*
@@ -340,12 +340,14 @@ int r600_dma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
 void r600_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
 int r600_ring_test(struct radeon_device *rdev, struct radeon_ring *cp);
 int r600_dma_ring_test(struct radeon_device *rdev, struct radeon_ring *cp);
-int r600_copy_cpdma(struct radeon_device *rdev,
-		    uint64_t src_offset, uint64_t dst_offset,
-		    unsigned num_gpu_pages, struct radeon_fence **fence);
-int r600_copy_dma(struct radeon_device *rdev,
-		  uint64_t src_offset, uint64_t dst_offset,
-		  unsigned num_gpu_pages, struct radeon_fence **fence);
+struct radeon_fence *r600_copy_cpdma(struct radeon_device *rdev,
+				     uint64_t src_offset, uint64_t dst_offset,
+				     unsigned num_gpu_pages,
+				     struct reservation_object *resv);
+struct radeon_fence *r600_copy_dma(struct radeon_device *rdev,
+				   uint64_t src_offset, uint64_t dst_offset,
+				   unsigned num_gpu_pages,
+				   struct reservation_object *resv);
 void r600_hpd_init(struct radeon_device *rdev);
 void r600_hpd_fini(struct radeon_device *rdev);
 bool r600_hpd_sense(struct radeon_device *rdev, enum radeon_hpd_id hpd);
@@ -389,7 +391,6 @@ void r600_disable_interrupts(struct radeon_device *rdev);
 void r600_rlc_stop(struct radeon_device *rdev);
 /* r600 audio */
 int r600_audio_init(struct radeon_device *rdev);
-struct r600_audio_pin r600_audio_status(struct radeon_device *rdev);
 void r600_audio_fini(struct radeon_device *rdev);
 void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock);
 void r600_hdmi_update_avi_infoframe(struct drm_encoder *encoder, void *buffer,
@@ -461,10 +462,10 @@ bool rv770_page_flip_pending(struct radeon_device *rdev, int crtc);
 void r700_vram_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
 void r700_cp_stop(struct radeon_device *rdev);
 void r700_cp_fini(struct radeon_device *rdev);
-int rv770_copy_dma(struct radeon_device *rdev,
-		  uint64_t src_offset, uint64_t dst_offset,
-		  unsigned num_gpu_pages,
-		   struct radeon_fence **fence);
+struct radeon_fence *rv770_copy_dma(struct radeon_device *rdev,
+				    uint64_t src_offset, uint64_t dst_offset,
+				    unsigned num_gpu_pages,
+				    struct reservation_object *resv);
 u32 rv770_get_xclk(struct radeon_device *rdev);
 int rv770_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk);
 int rv770_get_temp(struct radeon_device *rdev);
@@ -535,10 +536,10 @@ void evergreen_dma_fence_ring_emit(struct radeon_device *rdev,
 				   struct radeon_fence *fence);
 void evergreen_dma_ring_ib_execute(struct radeon_device *rdev,
 				   struct radeon_ib *ib);
-int evergreen_copy_dma(struct radeon_device *rdev,
-		       uint64_t src_offset, uint64_t dst_offset,
-		       unsigned num_gpu_pages,
-		       struct radeon_fence **fence);
+struct radeon_fence *evergreen_copy_dma(struct radeon_device *rdev,
+					uint64_t src_offset, uint64_t dst_offset,
+					unsigned num_gpu_pages,
+					struct reservation_object *resv);
 void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable);
 void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mode);
 int evergreen_get_temp(struct radeon_device *rdev);
@@ -700,10 +701,10 @@ int si_vm_init(struct radeon_device *rdev);
 void si_vm_fini(struct radeon_device *rdev);
 void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
 int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib);
-int si_copy_dma(struct radeon_device *rdev,
-		uint64_t src_offset, uint64_t dst_offset,
-		unsigned num_gpu_pages,
-		struct radeon_fence **fence);
+struct radeon_fence *si_copy_dma(struct radeon_device *rdev,
+				 uint64_t src_offset, uint64_t dst_offset,
+				 unsigned num_gpu_pages,
+				 struct reservation_object *resv);
 
 void si_dma_vm_copy_pages(struct radeon_device *rdev,
 			  struct radeon_ib *ib,
@@ -759,14 +760,14 @@ bool cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
 				  struct radeon_semaphore *semaphore,
 				  bool emit_wait);
 void cik_sdma_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
-int cik_copy_dma(struct radeon_device *rdev,
-		 uint64_t src_offset, uint64_t dst_offset,
-		 unsigned num_gpu_pages,
-		 struct radeon_fence **fence);
-int cik_copy_cpdma(struct radeon_device *rdev,
-		   uint64_t src_offset, uint64_t dst_offset,
-		   unsigned num_gpu_pages,
-		   struct radeon_fence **fence);
+struct radeon_fence *cik_copy_dma(struct radeon_device *rdev,
+				  uint64_t src_offset, uint64_t dst_offset,
+				  unsigned num_gpu_pages,
+				  struct reservation_object *resv);
+struct radeon_fence *cik_copy_cpdma(struct radeon_device *rdev,
+				    uint64_t src_offset, uint64_t dst_offset,
+				    unsigned num_gpu_pages,
+				    struct reservation_object *resv);
 int cik_sdma_ring_test(struct radeon_device *rdev, struct radeon_ring *ring);
 int cik_sdma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
 bool cik_sdma_is_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
@@ -882,6 +883,7 @@ uint32_t uvd_v1_0_get_wptr(struct radeon_device *rdev,
                            struct radeon_ring *ring);
 void uvd_v1_0_set_wptr(struct radeon_device *rdev,
                        struct radeon_ring *ring);
+int uvd_v1_0_resume(struct radeon_device *rdev);
 
 int uvd_v1_0_init(struct radeon_device *rdev);
 void uvd_v1_0_fini(struct radeon_device *rdev);
@@ -889,6 +891,8 @@ int uvd_v1_0_start(struct radeon_device *rdev);
 void uvd_v1_0_stop(struct radeon_device *rdev);
 
 int uvd_v1_0_ring_test(struct radeon_device *rdev, struct radeon_ring *ring);
+void uvd_v1_0_fence_emit(struct radeon_device *rdev,
+			 struct radeon_fence *fence);
 int uvd_v1_0_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
 bool uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
 			     struct radeon_ring *ring,
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index e74c7e387dde..df69b92ba164 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -458,7 +458,7 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev,
 	return true;
 }
 
-const int supported_devices_connector_convert[] = {
+static const int supported_devices_connector_convert[] = {
 	DRM_MODE_CONNECTOR_Unknown,
 	DRM_MODE_CONNECTOR_VGA,
 	DRM_MODE_CONNECTOR_DVII,
@@ -477,7 +477,7 @@ const int supported_devices_connector_convert[] = {
 	DRM_MODE_CONNECTOR_DisplayPort
 };
 
-const uint16_t supported_devices_connector_object_id_convert[] = {
+static const uint16_t supported_devices_connector_object_id_convert[] = {
 	CONNECTOR_OBJECT_ID_NONE,
 	CONNECTOR_OBJECT_ID_VGA,
 	CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_I, /* not all boards support DL */
@@ -494,7 +494,7 @@ const uint16_t supported_devices_connector_object_id_convert[] = {
 	CONNECTOR_OBJECT_ID_SVIDEO
 };
 
-const int object_connector_convert[] = {
+static const int object_connector_convert[] = {
 	DRM_MODE_CONNECTOR_Unknown,
 	DRM_MODE_CONNECTOR_DVII,
 	DRM_MODE_CONNECTOR_DVII,
diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index 69f5695bdab9..9e7f23dd14bd 100644
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -45,33 +45,29 @@ static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size,
 	for (i = 0; i < n; i++) {
 		switch (flag) {
 		case RADEON_BENCHMARK_COPY_DMA:
-			r = radeon_copy_dma(rdev, saddr, daddr,
-					    size / RADEON_GPU_PAGE_SIZE,
-					    &fence);
+			fence = radeon_copy_dma(rdev, saddr, daddr,
+						size / RADEON_GPU_PAGE_SIZE,
+						NULL);
 			break;
 		case RADEON_BENCHMARK_COPY_BLIT:
-			r = radeon_copy_blit(rdev, saddr, daddr,
-					     size / RADEON_GPU_PAGE_SIZE,
-					     &fence);
+			fence = radeon_copy_blit(rdev, saddr, daddr,
+						 size / RADEON_GPU_PAGE_SIZE,
+						 NULL);
 			break;
 		default:
 			DRM_ERROR("Unknown copy method\n");
-			r = -EINVAL;
+			return -EINVAL;
 		}
-		if (r)
-			goto exit_do_move;
+		if (IS_ERR(fence))
+			return PTR_ERR(fence);
+
 		r = radeon_fence_wait(fence, false);
-		if (r)
-			goto exit_do_move;
 		radeon_fence_unref(&fence);
+		if (r)
+			return r;
 	}
 	end_jiffies = jiffies;
-	r = jiffies_to_msecs(end_jiffies - start_jiffies);
-
-exit_do_move:
-	if (fence)
-		radeon_fence_unref(&fence);
-	return r;
+	return jiffies_to_msecs(end_jiffies - start_jiffies);
 }
 
 
@@ -97,7 +93,7 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
 	int time;
 
 	n = RADEON_BENCHMARK_ITERATIONS;
-	r = radeon_bo_create(rdev, size, PAGE_SIZE, true, sdomain, 0, NULL, &sobj);
+	r = radeon_bo_create(rdev, size, PAGE_SIZE, true, sdomain, 0, NULL, NULL, &sobj);
 	if (r) {
 		goto out_cleanup;
 	}
@@ -109,7 +105,7 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
 	if (r) {
 		goto out_cleanup;
 	}
-	r = radeon_bo_create(rdev, size, PAGE_SIZE, true, ddomain, 0, NULL, &dobj);
+	r = radeon_bo_create(rdev, size, PAGE_SIZE, true, ddomain, 0, NULL, NULL, &dobj);
 	if (r) {
 		goto out_cleanup;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 6651177110f0..3e5f6b71f3ad 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -116,7 +116,7 @@ enum radeon_combios_connector {
 	CONNECTOR_UNSUPPORTED_LEGACY
 };
 
-const int legacy_connector_convert[] = {
+static const int legacy_connector_convert[] = {
 	DRM_MODE_CONNECTOR_Unknown,
 	DRM_MODE_CONNECTOR_DVID,
 	DRM_MODE_CONNECTOR_VGA,
diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index bb0d5c3a8311..ea134a7d51a5 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -1298,27 +1298,27 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 	dev_priv->buffers_offset = init->buffers_offset;
 	dev_priv->gart_textures_offset = init->gart_textures_offset;
 
-	master_priv->sarea = drm_getsarea(dev);
+	master_priv->sarea = drm_legacy_getsarea(dev);
 	if (!master_priv->sarea) {
 		DRM_ERROR("could not find sarea!\n");
 		radeon_do_cleanup_cp(dev);
 		return -EINVAL;
 	}
 
-	dev_priv->cp_ring = drm_core_findmap(dev, init->ring_offset);
+	dev_priv->cp_ring = drm_legacy_findmap(dev, init->ring_offset);
 	if (!dev_priv->cp_ring) {
 		DRM_ERROR("could not find cp ring region!\n");
 		radeon_do_cleanup_cp(dev);
 		return -EINVAL;
 	}
-	dev_priv->ring_rptr = drm_core_findmap(dev, init->ring_rptr_offset);
+	dev_priv->ring_rptr = drm_legacy_findmap(dev, init->ring_rptr_offset);
 	if (!dev_priv->ring_rptr) {
 		DRM_ERROR("could not find ring read pointer!\n");
 		radeon_do_cleanup_cp(dev);
 		return -EINVAL;
 	}
 	dev->agp_buffer_token = init->buffers_offset;
-	dev->agp_buffer_map = drm_core_findmap(dev, init->buffers_offset);
+	dev->agp_buffer_map = drm_legacy_findmap(dev, init->buffers_offset);
 	if (!dev->agp_buffer_map) {
 		DRM_ERROR("could not find dma buffer region!\n");
 		radeon_do_cleanup_cp(dev);
@@ -1327,7 +1327,7 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 
 	if (init->gart_textures_offset) {
 		dev_priv->gart_textures =
-		    drm_core_findmap(dev, init->gart_textures_offset);
+		    drm_legacy_findmap(dev, init->gart_textures_offset);
 		if (!dev_priv->gart_textures) {
 			DRM_ERROR("could not find GART texture region!\n");
 			radeon_do_cleanup_cp(dev);
@@ -1337,9 +1337,9 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 
 #if __OS_HAS_AGP
 	if (dev_priv->flags & RADEON_IS_AGP) {
-		drm_core_ioremap_wc(dev_priv->cp_ring, dev);
-		drm_core_ioremap_wc(dev_priv->ring_rptr, dev);
-		drm_core_ioremap_wc(dev->agp_buffer_map, dev);
+		drm_legacy_ioremap_wc(dev_priv->cp_ring, dev);
+		drm_legacy_ioremap_wc(dev_priv->ring_rptr, dev);
+		drm_legacy_ioremap_wc(dev->agp_buffer_map, dev);
 		if (!dev_priv->cp_ring->handle ||
 		    !dev_priv->ring_rptr->handle ||
 		    !dev->agp_buffer_map->handle) {
@@ -1475,7 +1475,7 @@ static int radeon_do_init_cp(struct drm_device *dev, drm_radeon_init_t *init,
 			dev_priv->gart_info.mapping.size =
 			    dev_priv->gart_info.table_size;
 
-			drm_core_ioremap_wc(&dev_priv->gart_info.mapping, dev);
+			drm_legacy_ioremap_wc(&dev_priv->gart_info.mapping, dev);
 			dev_priv->gart_info.addr =
 			    dev_priv->gart_info.mapping.handle;
 
@@ -1569,15 +1569,15 @@ static int radeon_do_cleanup_cp(struct drm_device * dev)
 #if __OS_HAS_AGP
 	if (dev_priv->flags & RADEON_IS_AGP) {
 		if (dev_priv->cp_ring != NULL) {
-			drm_core_ioremapfree(dev_priv->cp_ring, dev);
+			drm_legacy_ioremapfree(dev_priv->cp_ring, dev);
 			dev_priv->cp_ring = NULL;
 		}
 		if (dev_priv->ring_rptr != NULL) {
-			drm_core_ioremapfree(dev_priv->ring_rptr, dev);
+			drm_legacy_ioremapfree(dev_priv->ring_rptr, dev);
 			dev_priv->ring_rptr = NULL;
 		}
 		if (dev->agp_buffer_map != NULL) {
-			drm_core_ioremapfree(dev->agp_buffer_map, dev);
+			drm_legacy_ioremapfree(dev->agp_buffer_map, dev);
 			dev->agp_buffer_map = NULL;
 		}
 	} else
@@ -1597,7 +1597,7 @@ static int radeon_do_cleanup_cp(struct drm_device * dev)
 
 		if (dev_priv->gart_info.gart_table_location == DRM_ATI_GART_FB)
 		{
-			drm_core_ioremapfree(&dev_priv->gart_info.mapping, dev);
+			drm_legacy_ioremapfree(&dev_priv->gart_info.mapping, dev);
 			dev_priv->gart_info.addr = NULL;
 		}
 	}
@@ -2106,9 +2106,9 @@ int radeon_driver_load(struct drm_device *dev, unsigned long flags)
 	else
 		dev_priv->flags |= RADEON_IS_PCI;
 
-	ret = drm_addmap(dev, pci_resource_start(dev->pdev, 2),
-			 pci_resource_len(dev->pdev, 2), _DRM_REGISTERS,
-			 _DRM_READ_ONLY | _DRM_DRIVER, &dev_priv->mmio);
+	ret = drm_legacy_addmap(dev, pci_resource_start(dev->pdev, 2),
+				pci_resource_len(dev->pdev, 2), _DRM_REGISTERS,
+				_DRM_READ_ONLY | _DRM_DRIVER, &dev_priv->mmio);
 	if (ret != 0)
 		return ret;
 
@@ -2135,8 +2135,8 @@ int radeon_master_create(struct drm_device *dev, struct drm_master *master)
 
 	/* prebuild the SAREA */
 	sareapage = max_t(unsigned long, SAREA_MAX, PAGE_SIZE);
-	ret = drm_addmap(dev, 0, sareapage, _DRM_SHM, _DRM_CONTAINS_LOCK,
-			 &master_priv->sarea);
+	ret = drm_legacy_addmap(dev, 0, sareapage, _DRM_SHM, _DRM_CONTAINS_LOCK,
+				&master_priv->sarea);
 	if (ret) {
 		DRM_ERROR("SAREA setup failed\n");
 		kfree(master_priv);
@@ -2162,7 +2162,7 @@ void radeon_master_destroy(struct drm_device *dev, struct drm_master *master)
 
 	master_priv->sarea_priv = NULL;
 	if (master_priv->sarea)
-		drm_rmmap_locked(dev, master_priv->sarea);
+		drm_legacy_rmmap_locked(dev, master_priv->sarea);
 
 	kfree(master_priv);
 
@@ -2181,9 +2181,9 @@ int radeon_driver_firstopen(struct drm_device *dev)
 	dev_priv->gart_info.table_size = RADEON_PCIGART_TABLE_SIZE;
 
 	dev_priv->fb_aper_offset = pci_resource_start(dev->pdev, 0);
-	ret = drm_addmap(dev, dev_priv->fb_aper_offset,
-			 pci_resource_len(dev->pdev, 0), _DRM_FRAME_BUFFER,
-			 _DRM_WRITE_COMBINING, &map);
+	ret = drm_legacy_addmap(dev, dev_priv->fb_aper_offset,
+				pci_resource_len(dev->pdev, 0),
+				_DRM_FRAME_BUFFER, _DRM_WRITE_COMBINING, &map);
 	if (ret != 0)
 		return ret;
 
@@ -2196,7 +2196,7 @@ int radeon_driver_unload(struct drm_device *dev)
 
 	DRM_DEBUG("\n");
 
-	drm_rmmap(dev, dev_priv->mmio);
+	drm_legacy_rmmap(dev, dev_priv->mmio);
 
 	kfree(dev_priv);
 
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 83f382e8e40e..1c893447d7cd 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -78,7 +78,8 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 	struct radeon_cs_chunk *chunk;
 	struct radeon_cs_buckets buckets;
 	unsigned i, j;
-	bool duplicate;
+	bool duplicate, need_mmap_lock = false;
+	int r;
 
 	if (p->chunk_relocs_idx == -1) {
 		return 0;
@@ -136,10 +137,13 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 			   + !!r->write_domain;
 
 		/* the first reloc of an UVD job is the msg and that must be in
-		   VRAM, also but everything into VRAM on AGP cards to avoid
-		   image corruptions */
+		   VRAM, also but everything into VRAM on AGP cards and older
+		   IGP chips to avoid image corruptions */
 		if (p->ring == R600_RING_TYPE_UVD_INDEX &&
-		    (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) {
+		    (i == 0 || drm_pci_device_is_agp(p->rdev->ddev) ||
+		     p->rdev->family == CHIP_RS780 ||
+		     p->rdev->family == CHIP_RS880)) {
+
 			/* TODO: is this still needed for NI+ ? */
 			p->relocs[i].prefered_domains =
 				RADEON_GEM_DOMAIN_VRAM;
@@ -165,7 +169,21 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 			p->relocs[i].allowed_domains = domain;
 		}
 
+		if (radeon_ttm_tt_has_userptr(p->relocs[i].robj->tbo.ttm)) {
+			uint32_t domain = p->relocs[i].prefered_domains;
+			if (!(domain & RADEON_GEM_DOMAIN_GTT)) {
+				DRM_ERROR("Only RADEON_GEM_DOMAIN_GTT is "
+					  "allowed for userptr BOs\n");
+				return -EINVAL;
+			}
+			need_mmap_lock = true;
+			domain = RADEON_GEM_DOMAIN_GTT;
+			p->relocs[i].prefered_domains = domain;
+			p->relocs[i].allowed_domains = domain;
+		}
+
 		p->relocs[i].tv.bo = &p->relocs[i].robj->tbo;
+		p->relocs[i].tv.shared = !r->write_domain;
 		p->relocs[i].handle = r->handle;
 
 		radeon_cs_buckets_add(&buckets, &p->relocs[i].tv.head,
@@ -177,8 +195,15 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 	if (p->cs_flags & RADEON_CS_USE_VM)
 		p->vm_bos = radeon_vm_get_bos(p->rdev, p->ib.vm,
 					      &p->validated);
+	if (need_mmap_lock)
+		down_read(&current->mm->mmap_sem);
 
-	return radeon_bo_list_validate(p->rdev, &p->ticket, &p->validated, p->ring);
+	r = radeon_bo_list_validate(p->rdev, &p->ticket, &p->validated, p->ring);
+
+	if (need_mmap_lock)
+		up_read(&current->mm->mmap_sem);
+
+	return r;
 }
 
 static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority)
@@ -224,17 +249,24 @@ static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority
 	return 0;
 }
 
-static void radeon_cs_sync_rings(struct radeon_cs_parser *p)
+static int radeon_cs_sync_rings(struct radeon_cs_parser *p)
 {
-	int i;
+	int i, r = 0;
 
 	for (i = 0; i < p->nrelocs; i++) {
+		struct reservation_object *resv;
+
 		if (!p->relocs[i].robj)
 			continue;
 
-		radeon_semaphore_sync_to(p->ib.semaphore,
-					 p->relocs[i].robj->tbo.sync_obj);
+		resv = p->relocs[i].robj->tbo.resv;
+		r = radeon_semaphore_sync_resv(p->rdev, p->ib.semaphore, resv,
+					       p->relocs[i].tv.shared);
+
+		if (r)
+			break;
 	}
+	return r;
 }
 
 /* XXX: note that this is called from the legacy UMS CS ioctl as well */
@@ -403,7 +435,7 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error, bo
 
 		ttm_eu_fence_buffer_objects(&parser->ticket,
 					    &parser->validated,
-					    parser->ib.fence);
+					    &parser->ib.fence->base);
 	} else if (backoff) {
 		ttm_eu_backoff_reservation(&parser->ticket,
 					   &parser->validated);
@@ -444,13 +476,19 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 		return r;
 	}
 
+	r = radeon_cs_sync_rings(parser);
+	if (r) {
+		if (r != -ERESTARTSYS)
+			DRM_ERROR("Failed to sync rings: %i\n", r);
+		return r;
+	}
+
 	if (parser->ring == R600_RING_TYPE_UVD_INDEX)
 		radeon_uvd_note_usage(rdev);
 	else if ((parser->ring == TN_RING_TYPE_VCE1_INDEX) ||
 		 (parser->ring == TN_RING_TYPE_VCE2_INDEX))
 		radeon_vce_note_usage(rdev);
 
-	radeon_cs_sync_rings(parser);
 	r = radeon_ib_schedule(rdev, &parser->ib, NULL, true);
 	if (r) {
 		DRM_ERROR("Failed to schedule IB !\n");
@@ -537,8 +575,14 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 	if (r) {
 		goto out;
 	}
-	radeon_cs_sync_rings(parser);
-	radeon_semaphore_sync_to(parser->ib.semaphore, vm->fence);
+
+	r = radeon_cs_sync_rings(parser);
+	if (r) {
+		if (r != -ERESTARTSYS)
+			DRM_ERROR("Failed to sync rings: %i\n", r);
+		goto out;
+	}
+	radeon_semaphore_sync_fence(parser->ib.semaphore, vm->fence);
 
 	if ((rdev->family >= CHIP_TAHITI) &&
 	    (parser->chunk_const_ib_idx != -1)) {
@@ -629,6 +673,13 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		up_read(&rdev->exclusive_lock);
 		return -EBUSY;
 	}
+	if (rdev->in_reset) {
+		up_read(&rdev->exclusive_lock);
+		r = radeon_gpu_reset(rdev);
+		if (!r)
+			r = -EAGAIN;
+		return r;
+	}
 	/* initialize parser */
 	memset(&parser, 0, sizeof(struct radeon_cs_parser));
 	parser.filp = filp;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 12c8329644c4..f41cc1538e48 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -434,7 +434,7 @@ int radeon_wb_init(struct radeon_device *rdev)
 
 	if (rdev->wb.wb_obj == NULL) {
 		r = radeon_bo_create(rdev, RADEON_GPU_PAGE_SIZE, PAGE_SIZE, true,
-				     RADEON_GEM_DOMAIN_GTT, 0, NULL,
+				     RADEON_GEM_DOMAIN_GTT, 0, NULL, NULL,
 				     &rdev->wb.wb_obj);
 		if (r) {
 			dev_warn(rdev->dev, "(%d) create WB bo failed\n", r);
@@ -1257,6 +1257,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	for (i = 0; i < RADEON_NUM_RINGS; i++) {
 		rdev->ring[i].idx = i;
 	}
+	rdev->fence_context = fence_context_alloc(RADEON_NUM_RINGS);
 
 	DRM_INFO("initializing kernel modesetting (%s 0x%04X:0x%04X 0x%04X:0x%04X).\n",
 		radeon_family_name[rdev->family], pdev->vendor, pdev->device,
@@ -1274,6 +1275,8 @@ int radeon_device_init(struct radeon_device *rdev,
 	init_rwsem(&rdev->pm.mclk_lock);
 	init_rwsem(&rdev->exclusive_lock);
 	init_waitqueue_head(&rdev->irq.vblank_queue);
+	mutex_init(&rdev->mn_lock);
+	hash_init(rdev->mn_hash);
 	r = radeon_gem_init(rdev);
 	if (r)
 		return r;
@@ -1399,10 +1402,6 @@ int radeon_device_init(struct radeon_device *rdev,
 	if (r)
 		goto failed;
 
-	r = radeon_ib_ring_tests(rdev);
-	if (r)
-		DRM_ERROR("ib ring test failed (%d).\n", r);
-
 	r = radeon_gem_debugfs_init(rdev);
 	if (r) {
 		DRM_ERROR("registering gem debugfs failed (%d).\n", r);
@@ -1420,6 +1419,10 @@ int radeon_device_init(struct radeon_device *rdev,
 			goto failed;
 	}
 
+	r = radeon_ib_ring_tests(rdev);
+	if (r)
+		DRM_ERROR("ib ring test failed (%d).\n", r);
+
 	if ((radeon_testing & 1)) {
 		if (rdev->accel_working)
 			radeon_test_moves(rdev);
@@ -1497,7 +1500,6 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon)
 	struct drm_crtc *crtc;
 	struct drm_connector *connector;
 	int i, r;
-	bool force_completion = false;
 
 	if (dev == NULL || dev->dev_private == NULL) {
 		return -ENODEV;
@@ -1541,12 +1543,9 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, bool fbcon)
 		r = radeon_fence_wait_empty(rdev, i);
 		if (r) {
 			/* delay GPU reset to resume */
-			force_completion = true;
+			radeon_fence_driver_force_completion(rdev, i);
 		}
 	}
-	if (force_completion) {
-		radeon_fence_driver_force_completion(rdev);
-	}
 
 	radeon_save_bios_scratch_regs(rdev);
 
@@ -1686,8 +1685,6 @@ int radeon_gpu_reset(struct radeon_device *rdev)
 		return 0;
 	}
 
-	rdev->needs_reset = false;
-
 	radeon_save_bios_scratch_regs(rdev);
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev);
@@ -1704,7 +1701,6 @@ int radeon_gpu_reset(struct radeon_device *rdev)
 		}
 	}
 
-retry:
 	r = radeon_asic_reset(rdev);
 	if (!r) {
 		dev_info(rdev->dev, "GPU reset succeeded, trying to resume\n");
@@ -1713,26 +1709,12 @@ retry:
 
 	radeon_restore_bios_scratch_regs(rdev);
 
-	if (!r) {
-		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		if (!r && ring_data[i]) {
 			radeon_ring_restore(rdev, &rdev->ring[i],
 					    ring_sizes[i], ring_data[i]);
-			ring_sizes[i] = 0;
-			ring_data[i] = NULL;
-		}
-
-		r = radeon_ib_ring_tests(rdev);
-		if (r) {
-			dev_err(rdev->dev, "ib ring test failed (%d).\n", r);
-			if (saved) {
-				saved = false;
-				radeon_suspend(rdev);
-				goto retry;
-			}
-		}
-	} else {
-		radeon_fence_driver_force_completion(rdev);
-		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		} else {
+			radeon_fence_driver_force_completion(rdev, i);
 			kfree(ring_data[i]);
 		}
 	}
@@ -1764,19 +1746,32 @@ retry:
 	/* reset hpd state */
 	radeon_hpd_init(rdev);
 
+	ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched);
+
+	rdev->in_reset = true;
+	rdev->needs_reset = false;
+
+	downgrade_write(&rdev->exclusive_lock);
+
 	drm_helper_resume_force_mode(rdev->ddev);
 
 	/* set the power state here in case we are a PX system or headless */
 	if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled)
 		radeon_pm_compute_clocks(rdev);
 
-	ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched);
-	if (r) {
+	if (!r) {
+		r = radeon_ib_ring_tests(rdev);
+		if (r && saved)
+			r = -EAGAIN;
+	} else {
 		/* bad news, how to tell it to userspace ? */
 		dev_info(rdev->dev, "GPU reset failed\n");
 	}
 
-	up_write(&rdev->exclusive_lock);
+	rdev->needs_reset = r == -EAGAIN;
+	rdev->in_reset = false;
+
+	up_read(&rdev->exclusive_lock);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 3fdf87318069..00ead8c2758a 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -402,12 +402,21 @@ static void radeon_flip_work_func(struct work_struct *__work)
 
         down_read(&rdev->exclusive_lock);
 	if (work->fence) {
-		r = radeon_fence_wait(work->fence, false);
-		if (r == -EDEADLK) {
-			up_read(&rdev->exclusive_lock);
-			r = radeon_gpu_reset(rdev);
-			down_read(&rdev->exclusive_lock);
-		}
+		struct radeon_fence *fence;
+
+		fence = to_radeon_fence(work->fence);
+		if (fence && fence->rdev == rdev) {
+			r = radeon_fence_wait(fence, false);
+			if (r == -EDEADLK) {
+				up_read(&rdev->exclusive_lock);
+				do {
+					r = radeon_gpu_reset(rdev);
+				} while (r == -EAGAIN);
+				down_read(&rdev->exclusive_lock);
+			}
+		} else
+			r = fence_wait(work->fence, false);
+
 		if (r)
 			DRM_ERROR("failed to wait on page flip fence (%d)!\n", r);
 
@@ -416,7 +425,8 @@ static void radeon_flip_work_func(struct work_struct *__work)
 		 * confused about which BO the CRTC is scanning out
 		 */
 
-		radeon_fence_unref(&work->fence);
+		fence_put(work->fence);
+		work->fence = NULL;
 	}
 
 	/* We borrow the event spin lock for protecting flip_status */
@@ -474,11 +484,6 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 	obj = new_radeon_fb->obj;
 	new_rbo = gem_to_radeon_bo(obj);
 
-	spin_lock(&new_rbo->tbo.bdev->fence_lock);
-	if (new_rbo->tbo.sync_obj)
-		work->fence = radeon_fence_ref(new_rbo->tbo.sync_obj);
-	spin_unlock(&new_rbo->tbo.bdev->fence_lock);
-
 	/* pin the new buffer */
 	DRM_DEBUG_DRIVER("flip-ioctl() cur_rbo = %p, new_rbo = %p\n",
 			 work->old_rbo, new_rbo);
@@ -497,6 +502,7 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 		DRM_ERROR("failed to pin new rbo buffer before flip\n");
 		goto cleanup;
 	}
+	work->fence = fence_get(reservation_object_get_excl(new_rbo->tbo.resv));
 	radeon_bo_get_tiling_flags(new_rbo, &tiling_flags, NULL);
 	radeon_bo_unreserve(new_rbo);
 
@@ -578,9 +584,8 @@ pflip_cleanup:
 
 cleanup:
 	drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
-	radeon_fence_unref(&work->fence);
+	fence_put(work->fence);
 	kfree(work);
-
 	return r;
 }
 
@@ -1917,7 +1922,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int fl
 
 	/* In vblank? */
 	if (in_vbl)
-		ret |= DRM_SCANOUTPOS_INVBL;
+		ret |= DRM_SCANOUTPOS_IN_VBLANK;
 
 	/* Is vpos outside nominal vblank area, but less than
 	 * 1/100 of a frame height away from start of vblank?
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index f9d17b29b343..dcffa30ee2db 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -38,6 +38,8 @@
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/vga_switcheroo.h>
+#include <drm/drm_gem.h>
+
 #include "drm_crtc_helper.h"
 /*
  * KMS wrapper.
@@ -114,6 +116,9 @@ int radeon_gem_object_open(struct drm_gem_object *obj,
 				struct drm_file *file_priv);
 void radeon_gem_object_close(struct drm_gem_object *obj,
 				struct drm_file *file_priv);
+struct dma_buf *radeon_gem_prime_export(struct drm_device *dev,
+					struct drm_gem_object *gobj,
+					int flags);
 extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc,
 				      unsigned int flags,
 				      int *vpos, int *hpos, ktime_t *stime,
@@ -130,7 +135,7 @@ int radeon_mode_dumb_create(struct drm_file *file_priv,
 			    struct drm_mode_create_dumb *args);
 struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev,
-							size_t size,
+							struct dma_buf_attachment *,
 							struct sg_table *sg);
 int radeon_gem_prime_pin(struct drm_gem_object *obj);
 void radeon_gem_prime_unpin(struct drm_gem_object *obj);
@@ -309,7 +314,7 @@ static const struct file_operations radeon_driver_old_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 	.read = drm_read,
 #ifdef CONFIG_COMPAT
@@ -329,6 +334,7 @@ static struct drm_driver driver_old = {
 	.preclose = radeon_driver_preclose,
 	.postclose = radeon_driver_postclose,
 	.lastclose = radeon_driver_lastclose,
+	.set_busid = drm_pci_set_busid,
 	.unload = radeon_driver_unload,
 	.suspend = radeon_suspend,
 	.resume = radeon_resume,
@@ -553,6 +559,7 @@ static struct drm_driver kms_driver = {
 	.preclose = radeon_driver_preclose_kms,
 	.postclose = radeon_driver_postclose_kms,
 	.lastclose = radeon_driver_lastclose_kms,
+	.set_busid = drm_pci_set_busid,
 	.unload = radeon_driver_unload_kms,
 	.get_vblank_counter = radeon_get_vblank_counter_kms,
 	.enable_vblank = radeon_enable_vblank_kms,
@@ -578,7 +585,7 @@ static struct drm_driver kms_driver = {
 
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
-	.gem_prime_export = drm_gem_prime_export,
+	.gem_prime_export = radeon_gem_prime_export,
 	.gem_prime_import = drm_gem_prime_import,
 	.gem_prime_pin = radeon_gem_prime_pin,
 	.gem_prime_unpin = radeon_gem_prime_unpin,
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index dafd812e4571..46bd3938282c 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -33,7 +33,9 @@
 
 #include <linux/firmware.h>
 #include <linux/platform_device.h>
+#include <drm/drm_legacy.h>
 
+#include <drm/ati_pcigart.h>
 #include "radeon_family.h"
 
 /* General customization:
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index 15edf23b465c..9a19e52cc655 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -410,3 +410,24 @@ bool radeon_dig_monitor_is_duallink(struct drm_encoder *encoder,
 	}
 }
 
+bool radeon_encoder_is_digital(struct drm_encoder *encoder)
+{
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	switch (radeon_encoder->encoder_id) {
+	case ENCODER_OBJECT_ID_INTERNAL_LVDS:
+	case ENCODER_OBJECT_ID_INTERNAL_TMDS1:
+	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_TMDS1:
+	case ENCODER_OBJECT_ID_INTERNAL_LVTM1:
+	case ENCODER_OBJECT_ID_INTERNAL_DVO1:
+	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1:
+	case ENCODER_OBJECT_ID_INTERNAL_DDI:
+	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
+	case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA:
+	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
+	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2:
+	case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3:
+		return true;
+	default:
+		return false;
+	}
+}
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 94b0f2aa3d7c..0ea1db83d573 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -189,7 +189,8 @@ out_unref:
 static int radeonfb_create(struct drm_fb_helper *helper,
 			   struct drm_fb_helper_surface_size *sizes)
 {
-	struct radeon_fbdev *rfbdev = (struct radeon_fbdev *)helper;
+	struct radeon_fbdev *rfbdev =
+		container_of(helper, struct radeon_fbdev, helper);
 	struct radeon_device *rdev = rfbdev->rdev;
 	struct fb_info *info;
 	struct drm_framebuffer *fb = NULL;
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 913787085dfa..995167025282 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -98,6 +98,25 @@ static u32 radeon_fence_read(struct radeon_device *rdev, int ring)
 }
 
 /**
+ * radeon_fence_schedule_check - schedule lockup check
+ *
+ * @rdev: radeon_device pointer
+ * @ring: ring index we should work with
+ *
+ * Queues a delayed work item to check for lockups.
+ */
+static void radeon_fence_schedule_check(struct radeon_device *rdev, int ring)
+{
+	/*
+	 * Do not reset the timer here with mod_delayed_work,
+	 * this can livelock in an interaction with TTM delayed destroy.
+	 */
+	queue_delayed_work(system_power_efficient_wq,
+			   &rdev->fence_drv[ring].lockup_work,
+			   RADEON_FENCE_JIFFIES_TIMEOUT);
+}
+
+/**
  * radeon_fence_emit - emit a fence on the requested ring
  *
  * @rdev: radeon_device pointer
@@ -111,30 +130,70 @@ int radeon_fence_emit(struct radeon_device *rdev,
 		      struct radeon_fence **fence,
 		      int ring)
 {
+	u64 seq = ++rdev->fence_drv[ring].sync_seq[ring];
+
 	/* we are protected by the ring emission mutex */
 	*fence = kmalloc(sizeof(struct radeon_fence), GFP_KERNEL);
 	if ((*fence) == NULL) {
 		return -ENOMEM;
 	}
-	kref_init(&((*fence)->kref));
 	(*fence)->rdev = rdev;
-	(*fence)->seq = ++rdev->fence_drv[ring].sync_seq[ring];
+	(*fence)->seq = seq;
 	(*fence)->ring = ring;
+	fence_init(&(*fence)->base, &radeon_fence_ops,
+		   &rdev->fence_queue.lock, rdev->fence_context + ring, seq);
 	radeon_fence_ring_emit(rdev, ring, *fence);
 	trace_radeon_fence_emit(rdev->ddev, ring, (*fence)->seq);
+	radeon_fence_schedule_check(rdev, ring);
 	return 0;
 }
 
 /**
- * radeon_fence_process - process a fence
+ * radeon_fence_check_signaled - callback from fence_queue
+ *
+ * this function is called with fence_queue lock held, which is also used
+ * for the fence locking itself, so unlocked variants are used for
+ * fence_signal, and remove_wait_queue.
+ */
+static int radeon_fence_check_signaled(wait_queue_t *wait, unsigned mode, int flags, void *key)
+{
+	struct radeon_fence *fence;
+	u64 seq;
+
+	fence = container_of(wait, struct radeon_fence, fence_wake);
+
+	/*
+	 * We cannot use radeon_fence_process here because we're already
+	 * in the waitqueue, in a call from wake_up_all.
+	 */
+	seq = atomic64_read(&fence->rdev->fence_drv[fence->ring].last_seq);
+	if (seq >= fence->seq) {
+		int ret = fence_signal_locked(&fence->base);
+
+		if (!ret)
+			FENCE_TRACE(&fence->base, "signaled from irq context\n");
+		else
+			FENCE_TRACE(&fence->base, "was already signaled\n");
+
+		radeon_irq_kms_sw_irq_put(fence->rdev, fence->ring);
+		__remove_wait_queue(&fence->rdev->fence_queue, &fence->fence_wake);
+		fence_put(&fence->base);
+	} else
+		FENCE_TRACE(&fence->base, "pending\n");
+	return 0;
+}
+
+/**
+ * radeon_fence_activity - check for fence activity
  *
  * @rdev: radeon_device pointer
  * @ring: ring index the fence is associated with
  *
- * Checks the current fence value and wakes the fence queue
- * if the sequence number has increased (all asics).
+ * Checks the current fence value and calculates the last
+ * signalled fence value. Returns true if activity occured
+ * on the ring, and the fence_queue should be waken up.
  */
-void radeon_fence_process(struct radeon_device *rdev, int ring)
+static bool radeon_fence_activity(struct radeon_device *rdev, int ring)
 {
 	uint64_t seq, last_seq, last_emitted;
 	unsigned count_loop = 0;
@@ -190,23 +249,77 @@ void radeon_fence_process(struct radeon_device *rdev, int ring)
 		}
 	} while (atomic64_xchg(&rdev->fence_drv[ring].last_seq, seq) > seq);
 
-	if (wake)
-		wake_up_all(&rdev->fence_queue);
+	if (seq < last_emitted)
+		radeon_fence_schedule_check(rdev, ring);
+
+	return wake;
 }
 
 /**
- * radeon_fence_destroy - destroy a fence
+ * radeon_fence_check_lockup - check for hardware lockup
  *
- * @kref: fence kref
+ * @work: delayed work item
  *
- * Frees the fence object (all asics).
+ * Checks for fence activity and if there is none probe
+ * the hardware if a lockup occured.
  */
-static void radeon_fence_destroy(struct kref *kref)
+static void radeon_fence_check_lockup(struct work_struct *work)
 {
-	struct radeon_fence *fence;
+	struct radeon_fence_driver *fence_drv;
+	struct radeon_device *rdev;
+	int ring;
+
+	fence_drv = container_of(work, struct radeon_fence_driver,
+				 lockup_work.work);
+	rdev = fence_drv->rdev;
+	ring = fence_drv - &rdev->fence_drv[0];
+
+	if (!down_read_trylock(&rdev->exclusive_lock)) {
+		/* just reschedule the check if a reset is going on */
+		radeon_fence_schedule_check(rdev, ring);
+		return;
+	}
+
+	if (fence_drv->delayed_irq && rdev->ddev->irq_enabled) {
+		unsigned long irqflags;
+
+		fence_drv->delayed_irq = false;
+		spin_lock_irqsave(&rdev->irq.lock, irqflags);
+		radeon_irq_set(rdev);
+		spin_unlock_irqrestore(&rdev->irq.lock, irqflags);
+	}
+
+	if (radeon_fence_activity(rdev, ring))
+		wake_up_all(&rdev->fence_queue);
 
-	fence = container_of(kref, struct radeon_fence, kref);
-	kfree(fence);
+	else if (radeon_ring_is_lockup(rdev, ring, &rdev->ring[ring])) {
+
+		/* good news we believe it's a lockup */
+		dev_warn(rdev->dev, "GPU lockup (current fence id "
+			 "0x%016llx last fence id 0x%016llx on ring %d)\n",
+			 (uint64_t)atomic64_read(&fence_drv->last_seq),
+			 fence_drv->sync_seq[ring], ring);
+
+		/* remember that we need an reset */
+		rdev->needs_reset = true;
+		wake_up_all(&rdev->fence_queue);
+	}
+	up_read(&rdev->exclusive_lock);
+}
+
+/**
+ * radeon_fence_process - process a fence
+ *
+ * @rdev: radeon_device pointer
+ * @ring: ring index the fence is associated with
+ *
+ * Checks the current fence value and wakes the fence queue
+ * if the sequence number has increased (all asics).
+ */
+void radeon_fence_process(struct radeon_device *rdev, int ring)
+{
+	if (radeon_fence_activity(rdev, ring))
+		wake_up_all(&rdev->fence_queue);
 }
 
 /**
@@ -237,6 +350,75 @@ static bool radeon_fence_seq_signaled(struct radeon_device *rdev,
 	return false;
 }
 
+static bool radeon_fence_is_signaled(struct fence *f)
+{
+	struct radeon_fence *fence = to_radeon_fence(f);
+	struct radeon_device *rdev = fence->rdev;
+	unsigned ring = fence->ring;
+	u64 seq = fence->seq;
+
+	if (atomic64_read(&rdev->fence_drv[ring].last_seq) >= seq) {
+		return true;
+	}
+
+	if (down_read_trylock(&rdev->exclusive_lock)) {
+		radeon_fence_process(rdev, ring);
+		up_read(&rdev->exclusive_lock);
+
+		if (atomic64_read(&rdev->fence_drv[ring].last_seq) >= seq) {
+			return true;
+		}
+	}
+	return false;
+}
+
+/**
+ * radeon_fence_enable_signaling - enable signalling on fence
+ * @fence: fence
+ *
+ * This function is called with fence_queue lock held, and adds a callback
+ * to fence_queue that checks if this fence is signaled, and if so it
+ * signals the fence and removes itself.
+ */
+static bool radeon_fence_enable_signaling(struct fence *f)
+{
+	struct radeon_fence *fence = to_radeon_fence(f);
+	struct radeon_device *rdev = fence->rdev;
+
+	if (atomic64_read(&rdev->fence_drv[fence->ring].last_seq) >= fence->seq)
+		return false;
+
+	if (down_read_trylock(&rdev->exclusive_lock)) {
+		radeon_irq_kms_sw_irq_get(rdev, fence->ring);
+
+		if (radeon_fence_activity(rdev, fence->ring))
+			wake_up_all_locked(&rdev->fence_queue);
+
+		/* did fence get signaled after we enabled the sw irq? */
+		if (atomic64_read(&rdev->fence_drv[fence->ring].last_seq) >= fence->seq) {
+			radeon_irq_kms_sw_irq_put(rdev, fence->ring);
+			up_read(&rdev->exclusive_lock);
+			return false;
+		}
+
+		up_read(&rdev->exclusive_lock);
+	} else {
+		/* we're probably in a lockup, lets not fiddle too much */
+		if (radeon_irq_kms_sw_irq_get_delayed(rdev, fence->ring))
+			rdev->fence_drv[fence->ring].delayed_irq = true;
+		radeon_fence_schedule_check(rdev, fence->ring);
+	}
+
+	fence->fence_wake.flags = 0;
+	fence->fence_wake.private = NULL;
+	fence->fence_wake.func = radeon_fence_check_signaled;
+	__add_wait_queue(&rdev->fence_queue, &fence->fence_wake);
+	fence_get(f);
+
+	FENCE_TRACE(&fence->base, "armed on ring %i!\n", fence->ring);
+	return true;
+}
+
 /**
  * radeon_fence_signaled - check if a fence has signaled
  *
@@ -247,14 +429,15 @@ static bool radeon_fence_seq_signaled(struct radeon_device *rdev,
  */
 bool radeon_fence_signaled(struct radeon_fence *fence)
 {
-	if (!fence) {
+	if (!fence)
 		return true;
-	}
-	if (fence->seq == RADEON_FENCE_SIGNALED_SEQ) {
-		return true;
-	}
+
 	if (radeon_fence_seq_signaled(fence->rdev, fence->seq, fence->ring)) {
-		fence->seq = RADEON_FENCE_SIGNALED_SEQ;
+		int ret;
+
+		ret = fence_signal(&fence->base);
+		if (!ret)
+			FENCE_TRACE(&fence->base, "signaled from radeon_fence_signaled\n");
 		return true;
 	}
 	return false;
@@ -283,110 +466,70 @@ static bool radeon_fence_any_seq_signaled(struct radeon_device *rdev, u64 *seq)
 }
 
 /**
- * radeon_fence_wait_seq - wait for a specific sequence numbers
+ * radeon_fence_wait_seq_timeout - wait for a specific sequence numbers
  *
  * @rdev: radeon device pointer
  * @target_seq: sequence number(s) we want to wait for
  * @intr: use interruptable sleep
+ * @timeout: maximum time to wait, or MAX_SCHEDULE_TIMEOUT for infinite wait
  *
  * Wait for the requested sequence number(s) to be written by any ring
  * (all asics).  Sequnce number array is indexed by ring id.
  * @intr selects whether to use interruptable (true) or non-interruptable
  * (false) sleep when waiting for the sequence number.  Helper function
  * for radeon_fence_wait_*().
- * Returns 0 if the sequence number has passed, error for all other cases.
+ * Returns remaining time if the sequence number has passed, 0 when
+ * the wait timeout, or an error for all other cases.
  * -EDEADLK is returned when a GPU lockup has been detected.
  */
-static int radeon_fence_wait_seq(struct radeon_device *rdev, u64 *target_seq,
-				 bool intr)
+static long radeon_fence_wait_seq_timeout(struct radeon_device *rdev,
+					  u64 *target_seq, bool intr,
+					  long timeout)
 {
-	uint64_t last_seq[RADEON_NUM_RINGS];
-	bool signaled;
-	int i, r;
-
-	while (!radeon_fence_any_seq_signaled(rdev, target_seq)) {
+	long r;
+	int i;
 
-		/* Save current sequence values, used to check for GPU lockups */
-		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-			if (!target_seq[i])
-				continue;
+	if (radeon_fence_any_seq_signaled(rdev, target_seq))
+		return timeout;
 
-			last_seq[i] = atomic64_read(&rdev->fence_drv[i].last_seq);
-			trace_radeon_fence_wait_begin(rdev->ddev, i, target_seq[i]);
-			radeon_irq_kms_sw_irq_get(rdev, i);
-		}
+	/* enable IRQs and tracing */
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		if (!target_seq[i])
+			continue;
 
-		if (intr) {
-			r = wait_event_interruptible_timeout(rdev->fence_queue, (
-				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq))
-				 || rdev->needs_reset), RADEON_FENCE_JIFFIES_TIMEOUT);
-		} else {
-			r = wait_event_timeout(rdev->fence_queue, (
-				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq))
-				 || rdev->needs_reset), RADEON_FENCE_JIFFIES_TIMEOUT);
-		}
+		trace_radeon_fence_wait_begin(rdev->ddev, i, target_seq[i]);
+		radeon_irq_kms_sw_irq_get(rdev, i);
+	}
 
-		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-			if (!target_seq[i])
-				continue;
+	if (intr) {
+		r = wait_event_interruptible_timeout(rdev->fence_queue, (
+			radeon_fence_any_seq_signaled(rdev, target_seq)
+			 || rdev->needs_reset), timeout);
+	} else {
+		r = wait_event_timeout(rdev->fence_queue, (
+			radeon_fence_any_seq_signaled(rdev, target_seq)
+			 || rdev->needs_reset), timeout);
+	}
 
-			radeon_irq_kms_sw_irq_put(rdev, i);
-			trace_radeon_fence_wait_end(rdev->ddev, i, target_seq[i]);
-		}
+	if (rdev->needs_reset)
+		r = -EDEADLK;
 
-		if (unlikely(r < 0))
-			return r;
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		if (!target_seq[i])
+			continue;
 
-		if (unlikely(!signaled)) {
-			if (rdev->needs_reset)
-				return -EDEADLK;
-
-			/* we were interrupted for some reason and fence
-			 * isn't signaled yet, resume waiting */
-			if (r)
-				continue;
-
-			for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-				if (!target_seq[i])
-					continue;
-
-				if (last_seq[i] != atomic64_read(&rdev->fence_drv[i].last_seq))
-					break;
-			}
-
-			if (i != RADEON_NUM_RINGS)
-				continue;
-
-			for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-				if (!target_seq[i])
-					continue;
-
-				if (radeon_ring_is_lockup(rdev, i, &rdev->ring[i]))
-					break;
-			}
-
-			if (i < RADEON_NUM_RINGS) {
-				/* good news we believe it's a lockup */
-				dev_warn(rdev->dev, "GPU lockup (waiting for "
-					 "0x%016llx last fence id 0x%016llx on"
-					 " ring %d)\n",
-					 target_seq[i], last_seq[i], i);
-
-				/* remember that we need an reset */
-				rdev->needs_reset = true;
-				wake_up_all(&rdev->fence_queue);
-				return -EDEADLK;
-			}
-		}
+		radeon_irq_kms_sw_irq_put(rdev, i);
+		trace_radeon_fence_wait_end(rdev->ddev, i, target_seq[i]);
 	}
-	return 0;
+
+	return r;
 }
 
 /**
  * radeon_fence_wait - wait for a fence to signal
  *
  * @fence: radeon fence object
- * @intr: use interruptable sleep
+ * @intr: use interruptible sleep
  *
  * Wait for the requested fence to signal (all asics).
  * @intr selects whether to use interruptable (true) or non-interruptable
@@ -396,22 +539,26 @@ static int radeon_fence_wait_seq(struct radeon_device *rdev, u64 *target_seq,
 int radeon_fence_wait(struct radeon_fence *fence, bool intr)
 {
 	uint64_t seq[RADEON_NUM_RINGS] = {};
-	int r;
+	long r;
 
-	if (fence == NULL) {
-		WARN(1, "Querying an invalid fence : %p !\n", fence);
-		return -EINVAL;
-	}
+	/*
+	 * This function should not be called on !radeon fences.
+	 * If this is the case, it would mean this function can
+	 * also be called on radeon fences belonging to another card.
+	 * exclusive_lock is not held in that case.
+	 */
+	if (WARN_ON_ONCE(!to_radeon_fence(&fence->base)))
+		return fence_wait(&fence->base, intr);
 
 	seq[fence->ring] = fence->seq;
-	if (seq[fence->ring] == RADEON_FENCE_SIGNALED_SEQ)
-		return 0;
-
-	r = radeon_fence_wait_seq(fence->rdev, seq, intr);
-	if (r)
+	r = radeon_fence_wait_seq_timeout(fence->rdev, seq, intr, MAX_SCHEDULE_TIMEOUT);
+	if (r < 0) {
 		return r;
+	}
 
-	fence->seq = RADEON_FENCE_SIGNALED_SEQ;
+	r = fence_signal(&fence->base);
+	if (!r)
+		FENCE_TRACE(&fence->base, "signaled from fence_wait\n");
 	return 0;
 }
 
@@ -434,7 +581,7 @@ int radeon_fence_wait_any(struct radeon_device *rdev,
 {
 	uint64_t seq[RADEON_NUM_RINGS];
 	unsigned i, num_rings = 0;
-	int r;
+	long r;
 
 	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
 		seq[i] = 0;
@@ -445,18 +592,14 @@ int radeon_fence_wait_any(struct radeon_device *rdev,
 
 		seq[i] = fences[i]->seq;
 		++num_rings;
-
-		/* test if something was allready signaled */
-		if (seq[i] == RADEON_FENCE_SIGNALED_SEQ)
-			return 0;
 	}
 
 	/* nothing to wait for ? */
 	if (num_rings == 0)
 		return -ENOENT;
 
-	r = radeon_fence_wait_seq(rdev, seq, intr);
-	if (r) {
+	r = radeon_fence_wait_seq_timeout(rdev, seq, intr, MAX_SCHEDULE_TIMEOUT);
+	if (r < 0) {
 		return r;
 	}
 	return 0;
@@ -475,6 +618,7 @@ int radeon_fence_wait_any(struct radeon_device *rdev,
 int radeon_fence_wait_next(struct radeon_device *rdev, int ring)
 {
 	uint64_t seq[RADEON_NUM_RINGS] = {};
+	long r;
 
 	seq[ring] = atomic64_read(&rdev->fence_drv[ring].last_seq) + 1ULL;
 	if (seq[ring] >= rdev->fence_drv[ring].sync_seq[ring]) {
@@ -482,7 +626,10 @@ int radeon_fence_wait_next(struct radeon_device *rdev, int ring)
 		   already the last emited fence */
 		return -ENOENT;
 	}
-	return radeon_fence_wait_seq(rdev, seq, false);
+	r = radeon_fence_wait_seq_timeout(rdev, seq, false, MAX_SCHEDULE_TIMEOUT);
+	if (r < 0)
+		return r;
+	return 0;
 }
 
 /**
@@ -498,18 +645,18 @@ int radeon_fence_wait_next(struct radeon_device *rdev, int ring)
 int radeon_fence_wait_empty(struct radeon_device *rdev, int ring)
 {
 	uint64_t seq[RADEON_NUM_RINGS] = {};
-	int r;
+	long r;
 
 	seq[ring] = rdev->fence_drv[ring].sync_seq[ring];
 	if (!seq[ring])
 		return 0;
 
-	r = radeon_fence_wait_seq(rdev, seq, false);
-	if (r) {
+	r = radeon_fence_wait_seq_timeout(rdev, seq, false, MAX_SCHEDULE_TIMEOUT);
+	if (r < 0) {
 		if (r == -EDEADLK)
 			return -EDEADLK;
 
-		dev_err(rdev->dev, "error waiting for ring[%d] to become idle (%d)\n",
+		dev_err(rdev->dev, "error waiting for ring[%d] to become idle (%ld)\n",
 			ring, r);
 	}
 	return 0;
@@ -525,7 +672,7 @@ int radeon_fence_wait_empty(struct radeon_device *rdev, int ring)
  */
 struct radeon_fence *radeon_fence_ref(struct radeon_fence *fence)
 {
-	kref_get(&fence->kref);
+	fence_get(&fence->base);
 	return fence;
 }
 
@@ -542,7 +689,7 @@ void radeon_fence_unref(struct radeon_fence **fence)
 
 	*fence = NULL;
 	if (tmp) {
-		kref_put(&tmp->kref, radeon_fence_destroy);
+		fence_put(&tmp->base);
 	}
 }
 
@@ -711,6 +858,9 @@ static void radeon_fence_driver_init_ring(struct radeon_device *rdev, int ring)
 		rdev->fence_drv[ring].sync_seq[i] = 0;
 	atomic64_set(&rdev->fence_drv[ring].last_seq, 0);
 	rdev->fence_drv[ring].initialized = false;
+	INIT_DELAYED_WORK(&rdev->fence_drv[ring].lockup_work,
+			  radeon_fence_check_lockup);
+	rdev->fence_drv[ring].rdev = rdev;
 }
 
 /**
@@ -758,8 +908,9 @@ void radeon_fence_driver_fini(struct radeon_device *rdev)
 		r = radeon_fence_wait_empty(rdev, ring);
 		if (r) {
 			/* no need to trigger GPU reset as we are unloading */
-			radeon_fence_driver_force_completion(rdev);
+			radeon_fence_driver_force_completion(rdev, ring);
 		}
+		cancel_delayed_work_sync(&rdev->fence_drv[ring].lockup_work);
 		wake_up_all(&rdev->fence_queue);
 		radeon_scratch_free(rdev, rdev->fence_drv[ring].scratch_reg);
 		rdev->fence_drv[ring].initialized = false;
@@ -771,18 +922,16 @@ void radeon_fence_driver_fini(struct radeon_device *rdev)
  * radeon_fence_driver_force_completion - force all fence waiter to complete
  *
  * @rdev: radeon device pointer
+ * @ring: the ring to complete
  *
  * In case of GPU reset failure make sure no process keep waiting on fence
  * that will never complete.
  */
-void radeon_fence_driver_force_completion(struct radeon_device *rdev)
+void radeon_fence_driver_force_completion(struct radeon_device *rdev, int ring)
 {
-	int ring;
-
-	for (ring = 0; ring < RADEON_NUM_RINGS; ring++) {
-		if (!rdev->fence_drv[ring].initialized)
-			continue;
+	if (rdev->fence_drv[ring].initialized) {
 		radeon_fence_write(rdev, rdev->fence_drv[ring].sync_seq[ring], ring);
+		cancel_delayed_work_sync(&rdev->fence_drv[ring].lockup_work);
 	}
 }
 
@@ -833,6 +982,7 @@ static int radeon_debugfs_gpu_reset(struct seq_file *m, void *data)
 	down_read(&rdev->exclusive_lock);
 	seq_printf(m, "%d\n", rdev->needs_reset);
 	rdev->needs_reset = true;
+	wake_up_all(&rdev->fence_queue);
 	up_read(&rdev->exclusive_lock);
 
 	return 0;
@@ -852,3 +1002,72 @@ int radeon_debugfs_fence_init(struct radeon_device *rdev)
 	return 0;
 #endif
 }
+
+static const char *radeon_fence_get_driver_name(struct fence *fence)
+{
+	return "radeon";
+}
+
+static const char *radeon_fence_get_timeline_name(struct fence *f)
+{
+	struct radeon_fence *fence = to_radeon_fence(f);
+	switch (fence->ring) {
+	case RADEON_RING_TYPE_GFX_INDEX: return "radeon.gfx";
+	case CAYMAN_RING_TYPE_CP1_INDEX: return "radeon.cp1";
+	case CAYMAN_RING_TYPE_CP2_INDEX: return "radeon.cp2";
+	case R600_RING_TYPE_DMA_INDEX: return "radeon.dma";
+	case CAYMAN_RING_TYPE_DMA1_INDEX: return "radeon.dma1";
+	case R600_RING_TYPE_UVD_INDEX: return "radeon.uvd";
+	case TN_RING_TYPE_VCE1_INDEX: return "radeon.vce1";
+	case TN_RING_TYPE_VCE2_INDEX: return "radeon.vce2";
+	default: WARN_ON_ONCE(1); return "radeon.unk";
+	}
+}
+
+static inline bool radeon_test_signaled(struct radeon_fence *fence)
+{
+	return test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->base.flags);
+}
+
+static signed long radeon_fence_default_wait(struct fence *f, bool intr,
+					     signed long t)
+{
+	struct radeon_fence *fence = to_radeon_fence(f);
+	struct radeon_device *rdev = fence->rdev;
+	bool signaled;
+
+	fence_enable_sw_signaling(&fence->base);
+
+	/*
+	 * This function has to return -EDEADLK, but cannot hold
+	 * exclusive_lock during the wait because some callers
+	 * may already hold it. This means checking needs_reset without
+	 * lock, and not fiddling with any gpu internals.
+	 *
+	 * The callback installed with fence_enable_sw_signaling will
+	 * run before our wait_event_*timeout call, so we will see
+	 * both the signaled fence and the changes to needs_reset.
+	 */
+
+	if (intr)
+		t = wait_event_interruptible_timeout(rdev->fence_queue,
+			((signaled = radeon_test_signaled(fence)) ||
+			 rdev->needs_reset), t);
+	else
+		t = wait_event_timeout(rdev->fence_queue,
+			((signaled = radeon_test_signaled(fence)) ||
+			 rdev->needs_reset), t);
+
+	if (t > 0 && !signaled)
+		return -EDEADLK;
+	return t;
+}
+
+const struct fence_ops radeon_fence_ops = {
+	.get_driver_name = radeon_fence_get_driver_name,
+	.get_timeline_name = radeon_fence_get_timeline_name,
+	.enable_signaling = radeon_fence_enable_signaling,
+	.signaled = radeon_fence_is_signaled,
+	.wait = radeon_fence_default_wait,
+	.release = NULL,
+};
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index a053a0779aac..84146d5901aa 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -128,7 +128,7 @@ int radeon_gart_table_vram_alloc(struct radeon_device *rdev)
 	if (rdev->gart.robj == NULL) {
 		r = radeon_bo_create(rdev, rdev->gart.table_size,
 				     PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
-				     0, NULL, &rdev->gart.robj);
+				     0, NULL, NULL, &rdev->gart.robj);
 		if (r) {
 			return r;
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index bfd7e1b0ff3f..c194497aa586 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -67,7 +67,7 @@ int radeon_gem_object_create(struct radeon_device *rdev, unsigned long size,
 
 retry:
 	r = radeon_bo_create(rdev, size, alignment, kernel, initial_domain,
-			     flags, NULL, &robj);
+			     flags, NULL, NULL, &robj);
 	if (r) {
 		if (r != -ERESTARTSYS) {
 			if (initial_domain == RADEON_GEM_DOMAIN_VRAM) {
@@ -94,7 +94,7 @@ static int radeon_gem_set_domain(struct drm_gem_object *gobj,
 {
 	struct radeon_bo *robj;
 	uint32_t domain;
-	int r;
+	long r;
 
 	/* FIXME: reeimplement */
 	robj = gem_to_radeon_bo(gobj);
@@ -110,9 +110,12 @@ static int radeon_gem_set_domain(struct drm_gem_object *gobj,
 	}
 	if (domain == RADEON_GEM_DOMAIN_CPU) {
 		/* Asking for cpu access wait for object idle */
-		r = radeon_bo_wait(robj, NULL, false);
-		if (r) {
-			printk(KERN_ERR "Failed to wait for object !\n");
+		r = reservation_object_wait_timeout_rcu(robj->tbo.resv, true, true, 30 * HZ);
+		if (!r)
+			r = -EBUSY;
+
+		if (r < 0 && r != -EINTR) {
+			printk(KERN_ERR "Failed to wait for object: %li\n", r);
 			return r;
 		}
 	}
@@ -272,6 +275,94 @@ int radeon_gem_create_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
+int radeon_gem_userptr_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *filp)
+{
+	struct radeon_device *rdev = dev->dev_private;
+	struct drm_radeon_gem_userptr *args = data;
+	struct drm_gem_object *gobj;
+	struct radeon_bo *bo;
+	uint32_t handle;
+	int r;
+
+	if (offset_in_page(args->addr | args->size))
+		return -EINVAL;
+
+	/* reject unknown flag values */
+	if (args->flags & ~(RADEON_GEM_USERPTR_READONLY |
+	    RADEON_GEM_USERPTR_ANONONLY | RADEON_GEM_USERPTR_VALIDATE |
+	    RADEON_GEM_USERPTR_REGISTER))
+		return -EINVAL;
+
+	if (args->flags & RADEON_GEM_USERPTR_READONLY) {
+		/* readonly pages not tested on older hardware */
+		if (rdev->family < CHIP_R600)
+			return -EINVAL;
+
+	} else if (!(args->flags & RADEON_GEM_USERPTR_ANONONLY) ||
+		   !(args->flags & RADEON_GEM_USERPTR_REGISTER)) {
+
+		/* if we want to write to it we must require anonymous
+		   memory and install a MMU notifier */
+		return -EACCES;
+	}
+
+	down_read(&rdev->exclusive_lock);
+
+	/* create a gem object to contain this object in */
+	r = radeon_gem_object_create(rdev, args->size, 0,
+				     RADEON_GEM_DOMAIN_CPU, 0,
+				     false, &gobj);
+	if (r)
+		goto handle_lockup;
+
+	bo = gem_to_radeon_bo(gobj);
+	r = radeon_ttm_tt_set_userptr(bo->tbo.ttm, args->addr, args->flags);
+	if (r)
+		goto release_object;
+
+	if (args->flags & RADEON_GEM_USERPTR_REGISTER) {
+		r = radeon_mn_register(bo, args->addr);
+		if (r)
+			goto release_object;
+	}
+
+	if (args->flags & RADEON_GEM_USERPTR_VALIDATE) {
+		down_read(&current->mm->mmap_sem);
+		r = radeon_bo_reserve(bo, true);
+		if (r) {
+			up_read(&current->mm->mmap_sem);
+			goto release_object;
+		}
+
+		radeon_ttm_placement_from_domain(bo, RADEON_GEM_DOMAIN_GTT);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
+		radeon_bo_unreserve(bo);
+		up_read(&current->mm->mmap_sem);
+		if (r)
+			goto release_object;
+	}
+
+	r = drm_gem_handle_create(filp, gobj, &handle);
+	/* drop reference from allocate - handle holds it now */
+	drm_gem_object_unreference_unlocked(gobj);
+	if (r)
+		goto handle_lockup;
+
+	args->handle = handle;
+	up_read(&rdev->exclusive_lock);
+	return 0;
+
+release_object:
+	drm_gem_object_unreference_unlocked(gobj);
+
+handle_lockup:
+	up_read(&rdev->exclusive_lock);
+	r = radeon_gem_handle_lockup(rdev, r);
+
+	return r;
+}
+
 int radeon_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *filp)
 {
@@ -315,6 +406,10 @@ int radeon_mode_dumb_mmap(struct drm_file *filp,
 		return -ENOENT;
 	}
 	robj = gem_to_radeon_bo(gobj);
+	if (radeon_ttm_tt_has_userptr(robj->tbo.ttm)) {
+		drm_gem_object_unreference_unlocked(gobj);
+		return -EPERM;
+	}
 	*offset_p = radeon_bo_mmap_offset(robj);
 	drm_gem_object_unreference_unlocked(gobj);
 	return 0;
@@ -357,15 +452,22 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
 	struct drm_radeon_gem_wait_idle *args = data;
 	struct drm_gem_object *gobj;
 	struct radeon_bo *robj;
-	int r;
+	int r = 0;
 	uint32_t cur_placement = 0;
+	long ret;
 
 	gobj = drm_gem_object_lookup(dev, filp, args->handle);
 	if (gobj == NULL) {
 		return -ENOENT;
 	}
 	robj = gem_to_radeon_bo(gobj);
-	r = radeon_bo_wait(robj, &cur_placement, false);
+
+	ret = reservation_object_wait_timeout_rcu(robj->tbo.resv, true, true, 30 * HZ);
+	if (ret == 0)
+		r = -EBUSY;
+	else if (ret < 0)
+		r = ret;
+
 	/* Flush HDP cache via MMIO if necessary */
 	if (rdev->asic->mmio_hdp_flush &&
 	    radeon_mem_type_to_domain(cur_placement) == RADEON_GEM_DOMAIN_VRAM)
@@ -532,6 +634,11 @@ int radeon_gem_op_ioctl(struct drm_device *dev, void *data,
 		return -ENOENT;
 	}
 	robj = gem_to_radeon_bo(gobj);
+
+	r = -EPERM;
+	if (radeon_ttm_tt_has_userptr(robj->tbo.ttm))
+		goto out;
+
 	r = radeon_bo_reserve(robj, false);
 	if (unlikely(r))
 		goto out;
diff --git a/drivers/gpu/drm/radeon/radeon_ib.c b/drivers/gpu/drm/radeon/radeon_ib.c
index 5bf2c0a05827..3f39fcca4d07 100644
--- a/drivers/gpu/drm/radeon/radeon_ib.c
+++ b/drivers/gpu/drm/radeon/radeon_ib.c
@@ -145,7 +145,7 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
 	if (ib->vm) {
 		struct radeon_fence *vm_id_fence;
 		vm_id_fence = radeon_vm_grab_id(rdev, ib->vm, ib->ring);
-        	radeon_semaphore_sync_to(ib->semaphore, vm_id_fence);
+		radeon_semaphore_sync_fence(ib->semaphore, vm_id_fence);
 	}
 
 	/* sync with other rings */
@@ -269,6 +269,7 @@ int radeon_ib_ring_tests(struct radeon_device *rdev)
 
 		r = radeon_ib_test(rdev, i, ring);
 		if (r) {
+			radeon_fence_driver_force_completion(rdev, i);
 			ring->ready = false;
 			rdev->needs_reset = false;
 
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 16807afab362..7784911d78ef 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -88,23 +88,6 @@ static void radeon_hotplug_work_func(struct work_struct *work)
 }
 
 /**
- * radeon_irq_reset_work_func - execute gpu reset
- *
- * @work: work struct
- *
- * Execute scheduled gpu reset (cayman+).
- * This function is called when the irq handler
- * thinks we need a gpu reset.
- */
-static void radeon_irq_reset_work_func(struct work_struct *work)
-{
-	struct radeon_device *rdev = container_of(work, struct radeon_device,
-						  reset_work);
-
-	radeon_gpu_reset(rdev);
-}
-
-/**
  * radeon_driver_irq_preinstall_kms - drm irq preinstall callback
  *
  * @dev: drm dev pointer
@@ -284,7 +267,6 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 
 	INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
 	INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
-	INIT_WORK(&rdev->reset_work, radeon_irq_reset_work_func);
 
 	rdev->irq.installed = true;
 	r = drm_irq_install(rdev->ddev, rdev->ddev->pdev->irq);
@@ -342,6 +324,21 @@ void radeon_irq_kms_sw_irq_get(struct radeon_device *rdev, int ring)
 }
 
 /**
+ * radeon_irq_kms_sw_irq_get_delayed - enable software interrupt
+ *
+ * @rdev: radeon device pointer
+ * @ring: ring whose interrupt you want to enable
+ *
+ * Enables the software interrupt for a specific ring (all asics).
+ * The software interrupt is generally used to signal a fence on
+ * a particular ring.
+ */
+bool radeon_irq_kms_sw_irq_get_delayed(struct radeon_device *rdev, int ring)
+{
+	return atomic_inc_return(&rdev->irq.ring_int[ring]) == 1;
+}
+
+/**
  * radeon_irq_kms_sw_irq_put - disable software interrupt
  *
  * @rdev: radeon device pointer
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index eb7164d07985..8309b11e674d 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -885,5 +885,6 @@ const struct drm_ioctl_desc radeon_ioctls_kms[] = {
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_BUSY, radeon_gem_busy_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_VA, radeon_gem_va_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_OP, radeon_gem_op_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(RADEON_GEM_USERPTR, radeon_gem_userptr_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 };
 int radeon_max_kms_ioctl = ARRAY_SIZE(radeon_ioctls_kms);
diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c
new file mode 100644
index 000000000000..a69bd441dd2d
--- /dev/null
+++ b/drivers/gpu/drm/radeon/radeon_mn.c
@@ -0,0 +1,274 @@
+/*
+ * Copyright 2014 Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ */
+/*
+ * Authors:
+ *    Christian König <christian.koenig@amd.com>
+ */
+
+#include <linux/firmware.h>
+#include <linux/module.h>
+#include <linux/mmu_notifier.h>
+#include <drm/drmP.h>
+#include <drm/drm.h>
+
+#include "radeon.h"
+
+struct radeon_mn {
+	/* constant after initialisation */
+	struct radeon_device	*rdev;
+	struct mm_struct	*mm;
+	struct mmu_notifier	mn;
+
+	/* only used on destruction */
+	struct work_struct	work;
+
+	/* protected by rdev->mn_lock */
+	struct hlist_node	node;
+
+	/* objects protected by lock */
+	struct mutex		lock;
+	struct rb_root		objects;
+};
+
+/**
+ * radeon_mn_destroy - destroy the rmn
+ *
+ * @work: previously sheduled work item
+ *
+ * Lazy destroys the notifier from a work item
+ */
+static void radeon_mn_destroy(struct work_struct *work)
+{
+	struct radeon_mn *rmn = container_of(work, struct radeon_mn, work);
+	struct radeon_device *rdev = rmn->rdev;
+	struct radeon_bo *bo, *next;
+
+	mutex_lock(&rdev->mn_lock);
+	mutex_lock(&rmn->lock);
+	hash_del(&rmn->node);
+	rbtree_postorder_for_each_entry_safe(bo, next, &rmn->objects, mn_it.rb) {
+		interval_tree_remove(&bo->mn_it, &rmn->objects);
+		bo->mn = NULL;
+	}
+	mutex_unlock(&rmn->lock);
+	mutex_unlock(&rdev->mn_lock);
+	mmu_notifier_unregister(&rmn->mn, rmn->mm);
+	kfree(rmn);
+}
+
+/**
+ * radeon_mn_release - callback to notify about mm destruction
+ *
+ * @mn: our notifier
+ * @mn: the mm this callback is about
+ *
+ * Shedule a work item to lazy destroy our notifier.
+ */
+static void radeon_mn_release(struct mmu_notifier *mn,
+			      struct mm_struct *mm)
+{
+	struct radeon_mn *rmn = container_of(mn, struct radeon_mn, mn);
+	INIT_WORK(&rmn->work, radeon_mn_destroy);
+	schedule_work(&rmn->work);
+}
+
+/**
+ * radeon_mn_invalidate_range_start - callback to notify about mm change
+ *
+ * @mn: our notifier
+ * @mn: the mm this callback is about
+ * @start: start of updated range
+ * @end: end of updated range
+ *
+ * We block for all BOs between start and end to be idle and
+ * unmap them by move them into system domain again.
+ */
+static void radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
+					     struct mm_struct *mm,
+					     unsigned long start,
+					     unsigned long end)
+{
+	struct radeon_mn *rmn = container_of(mn, struct radeon_mn, mn);
+	struct interval_tree_node *it;
+
+	/* notification is exclusive, but interval is inclusive */
+	end -= 1;
+
+	mutex_lock(&rmn->lock);
+
+	it = interval_tree_iter_first(&rmn->objects, start, end);
+	while (it) {
+		struct radeon_bo *bo;
+		struct fence *fence;
+		int r;
+
+		bo = container_of(it, struct radeon_bo, mn_it);
+		it = interval_tree_iter_next(it, start, end);
+
+		r = radeon_bo_reserve(bo, true);
+		if (r) {
+			DRM_ERROR("(%d) failed to reserve user bo\n", r);
+			continue;
+		}
+
+		fence = reservation_object_get_excl(bo->tbo.resv);
+		if (fence) {
+			r = radeon_fence_wait((struct radeon_fence *)fence, false);
+			if (r)
+				DRM_ERROR("(%d) failed to wait for user bo\n", r);
+		}
+
+		radeon_ttm_placement_from_domain(bo, RADEON_GEM_DOMAIN_CPU);
+		r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
+		if (r)
+			DRM_ERROR("(%d) failed to validate user bo\n", r);
+
+		radeon_bo_unreserve(bo);
+	}
+	
+	mutex_unlock(&rmn->lock);
+}
+
+static const struct mmu_notifier_ops radeon_mn_ops = {
+	.release = radeon_mn_release,
+	.invalidate_range_start = radeon_mn_invalidate_range_start,
+};
+
+/**
+ * radeon_mn_get - create notifier context
+ *
+ * @rdev: radeon device pointer
+ *
+ * Creates a notifier context for current->mm.
+ */
+static struct radeon_mn *radeon_mn_get(struct radeon_device *rdev)
+{
+	struct mm_struct *mm = current->mm;
+	struct radeon_mn *rmn;
+	int r;
+
+	down_write(&mm->mmap_sem);
+	mutex_lock(&rdev->mn_lock);
+
+	hash_for_each_possible(rdev->mn_hash, rmn, node, (unsigned long)mm)
+		if (rmn->mm == mm)
+			goto release_locks;
+
+	rmn = kzalloc(sizeof(*rmn), GFP_KERNEL);
+	if (!rmn) {
+		rmn = ERR_PTR(-ENOMEM);
+		goto release_locks;
+	}
+
+	rmn->rdev = rdev;
+	rmn->mm = mm;
+	rmn->mn.ops = &radeon_mn_ops;
+	mutex_init(&rmn->lock);
+	rmn->objects = RB_ROOT;
+	
+	r = __mmu_notifier_register(&rmn->mn, mm);
+	if (r)
+		goto free_rmn;
+
+	hash_add(rdev->mn_hash, &rmn->node, (unsigned long)mm);
+
+release_locks:
+	mutex_unlock(&rdev->mn_lock);
+	up_write(&mm->mmap_sem);
+
+	return rmn;
+
+free_rmn:
+	mutex_unlock(&rdev->mn_lock);
+	up_write(&mm->mmap_sem);
+	kfree(rmn);
+
+	return ERR_PTR(r);
+}
+
+/**
+ * radeon_mn_register - register a BO for notifier updates
+ *
+ * @bo: radeon buffer object
+ * @addr: userptr addr we should monitor
+ *
+ * Registers an MMU notifier for the given BO at the specified address.
+ * Returns 0 on success, -ERRNO if anything goes wrong.
+ */
+int radeon_mn_register(struct radeon_bo *bo, unsigned long addr)
+{
+	unsigned long end = addr + radeon_bo_size(bo) - 1;
+	struct radeon_device *rdev = bo->rdev;
+	struct radeon_mn *rmn;
+	struct interval_tree_node *it;
+
+	rmn = radeon_mn_get(rdev);
+	if (IS_ERR(rmn))
+		return PTR_ERR(rmn);
+
+	mutex_lock(&rmn->lock);
+
+	it = interval_tree_iter_first(&rmn->objects, addr, end);
+	if (it) {
+		mutex_unlock(&rmn->lock);
+		return -EEXIST;
+	}
+
+	bo->mn = rmn;
+	bo->mn_it.start = addr;
+	bo->mn_it.last = end;
+	interval_tree_insert(&bo->mn_it, &rmn->objects);
+
+	mutex_unlock(&rmn->lock);
+
+	return 0;
+}
+
+/**
+ * radeon_mn_unregister - unregister a BO for notifier updates
+ *
+ * @bo: radeon buffer object
+ *
+ * Remove any registration of MMU notifier updates from the buffer object.
+ */
+void radeon_mn_unregister(struct radeon_bo *bo)
+{
+	struct radeon_device *rdev = bo->rdev;
+	struct radeon_mn *rmn;
+
+	mutex_lock(&rdev->mn_lock);
+	rmn = bo->mn;
+	if (rmn == NULL) {
+		mutex_unlock(&rdev->mn_lock);
+		return;
+	}
+
+	mutex_lock(&rmn->lock);
+	interval_tree_remove(&bo->mn_it, &rmn->objects);
+	bo->mn = NULL;
+	mutex_unlock(&rmn->lock);
+	mutex_unlock(&rdev->mn_lock);
+}
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index e27608c29c11..04db2fdd8692 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -777,6 +777,7 @@ extern void atombios_digital_setup(struct drm_encoder *encoder, int action);
 extern int atombios_get_encoder_mode(struct drm_encoder *encoder);
 extern bool atombios_set_edp_panel_power(struct drm_connector *connector, int action);
 extern void radeon_encoder_set_active_device(struct drm_encoder *encoder);
+extern bool radeon_encoder_is_digital(struct drm_encoder *encoder);
 
 extern void radeon_crtc_load_lut(struct drm_crtc *crtc);
 extern int atombios_crtc_set_base(struct drm_crtc *crtc, int x, int y,
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 480c87d8edc5..99a960a4f302 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -75,6 +75,7 @@ static void radeon_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 	bo = container_of(tbo, struct radeon_bo, tbo);
 
 	radeon_update_memory_usage(bo, bo->tbo.mem.mem_type, -1);
+	radeon_mn_unregister(bo);
 
 	mutex_lock(&bo->rdev->gem.mutex);
 	list_del_init(&bo->list);
@@ -96,55 +97,80 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 {
 	u32 c = 0, i;
 
-	rbo->placement.fpfn = 0;
-	rbo->placement.lpfn = 0;
 	rbo->placement.placement = rbo->placements;
 	rbo->placement.busy_placement = rbo->placements;
 	if (domain & RADEON_GEM_DOMAIN_VRAM)
-		rbo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
-					TTM_PL_FLAG_VRAM;
+		rbo->placements[c++].flags = TTM_PL_FLAG_WC |
+					     TTM_PL_FLAG_UNCACHED |
+					     TTM_PL_FLAG_VRAM;
+
 	if (domain & RADEON_GEM_DOMAIN_GTT) {
 		if (rbo->flags & RADEON_GEM_GTT_UC) {
-			rbo->placements[c++] = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_TT;
+			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED |
+				TTM_PL_FLAG_TT;
+
 		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
 			   (rbo->rdev->flags & RADEON_IS_AGP)) {
-			rbo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
+			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
+				TTM_PL_FLAG_UNCACHED |
 				TTM_PL_FLAG_TT;
 		} else {
-			rbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_TT;
+			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED |
+						     TTM_PL_FLAG_TT;
 		}
 	}
+
 	if (domain & RADEON_GEM_DOMAIN_CPU) {
 		if (rbo->flags & RADEON_GEM_GTT_UC) {
-			rbo->placements[c++] = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_SYSTEM;
+			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED |
+				TTM_PL_FLAG_SYSTEM;
+
 		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
 		    rbo->rdev->flags & RADEON_IS_AGP) {
-			rbo->placements[c++] = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
+			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
+				TTM_PL_FLAG_UNCACHED |
 				TTM_PL_FLAG_SYSTEM;
 		} else {
-			rbo->placements[c++] = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_SYSTEM;
+			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED |
+						     TTM_PL_FLAG_SYSTEM;
 		}
 	}
 	if (!c)
-		rbo->placements[c++] = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		rbo->placements[c++].flags = TTM_PL_MASK_CACHING |
+					     TTM_PL_FLAG_SYSTEM;
+
 	rbo->placement.num_placement = c;
 	rbo->placement.num_busy_placement = c;
 
+	for (i = 0; i < c; ++i) {
+		rbo->placements[i].fpfn = 0;
+		if ((rbo->flags & RADEON_GEM_CPU_ACCESS) &&
+		    (rbo->placements[i].flags & TTM_PL_FLAG_VRAM))
+			rbo->placements[i].lpfn =
+				rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
+		else
+			rbo->placements[i].lpfn = 0;
+	}
+
 	/*
 	 * Use two-ended allocation depending on the buffer size to
 	 * improve fragmentation quality.
 	 * 512kb was measured as the most optimal number.
 	 */
-	if (rbo->tbo.mem.size > 512 * 1024) {
+	if (!((rbo->flags & RADEON_GEM_CPU_ACCESS) &&
+	      (rbo->placements[i].flags & TTM_PL_FLAG_VRAM)) &&
+	    rbo->tbo.mem.size > 512 * 1024) {
 		for (i = 0; i < c; i++) {
-			rbo->placements[i] |= TTM_PL_FLAG_TOPDOWN;
+			rbo->placements[i].flags |= TTM_PL_FLAG_TOPDOWN;
 		}
 	}
 }
 
 int radeon_bo_create(struct radeon_device *rdev,
-		     unsigned long size, int byte_align, bool kernel, u32 domain,
-		     u32 flags, struct sg_table *sg, struct radeon_bo **bo_ptr)
+		     unsigned long size, int byte_align, bool kernel,
+		     u32 domain, u32 flags, struct sg_table *sg,
+		     struct reservation_object *resv,
+		     struct radeon_bo **bo_ptr)
 {
 	struct radeon_bo *bo;
 	enum ttm_bo_type type;
@@ -192,7 +218,7 @@ int radeon_bo_create(struct radeon_device *rdev,
 	down_read(&rdev->pm.mclk_lock);
 	r = ttm_bo_init(&rdev->mman.bdev, &bo->tbo, size, type,
 			&bo->placement, page_align, !kernel, NULL,
-			acc_size, sg, &radeon_ttm_bo_destroy);
+			acc_size, sg, resv, &radeon_ttm_bo_destroy);
 	up_read(&rdev->pm.mclk_lock);
 	if (unlikely(r != 0)) {
 		return r;
@@ -264,6 +290,9 @@ int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
 {
 	int r, i;
 
+	if (radeon_ttm_tt_has_userptr(bo->tbo.ttm))
+		return -EPERM;
+
 	if (bo->pin_count) {
 		bo->pin_count++;
 		if (gpu_addr)
@@ -283,21 +312,19 @@ int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
 		return 0;
 	}
 	radeon_ttm_placement_from_domain(bo, domain);
-	if (domain == RADEON_GEM_DOMAIN_VRAM) {
+	for (i = 0; i < bo->placement.num_placement; i++) {
 		/* force to pin into visible video ram */
-		bo->placement.lpfn = bo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
-	}
-	if (max_offset) {
-		u64 lpfn = max_offset >> PAGE_SHIFT;
-
-		if (!bo->placement.lpfn)
-			bo->placement.lpfn = bo->rdev->mc.gtt_size >> PAGE_SHIFT;
+		if ((bo->placements[i].flags & TTM_PL_FLAG_VRAM) &&
+		    !(bo->flags & RADEON_GEM_NO_CPU_ACCESS) &&
+		    (!max_offset || max_offset > bo->rdev->mc.visible_vram_size))
+			bo->placements[i].lpfn =
+				bo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
+		else
+			bo->placements[i].lpfn = max_offset >> PAGE_SHIFT;
 
-		if (lpfn < bo->placement.lpfn)
-			bo->placement.lpfn = lpfn;
+		bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT;
 	}
-	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
 	if (likely(r == 0)) {
 		bo->pin_count = 1;
@@ -329,8 +356,10 @@ int radeon_bo_unpin(struct radeon_bo *bo)
 	bo->pin_count--;
 	if (bo->pin_count)
 		return 0;
-	for (i = 0; i < bo->placement.num_placement; i++)
-		bo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
+	for (i = 0; i < bo->placement.num_placement; i++) {
+		bo->placements[i].lpfn = 0;
+		bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
+	}
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, false, false);
 	if (likely(r == 0)) {
 		if (bo->tbo.mem.mem_type == TTM_PL_VRAM)
@@ -459,7 +488,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 	u64 bytes_moved = 0, initial_bytes_moved;
 	u64 bytes_moved_threshold = radeon_bo_get_threshold_for_moves(rdev);
 
-	r = ttm_eu_reserve_buffers(ticket, head);
+	r = ttm_eu_reserve_buffers(ticket, head, true);
 	if (unlikely(r != 0)) {
 		return r;
 	}
@@ -468,6 +497,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 		bo = lobj->robj;
 		if (!bo->pin_count) {
 			u32 domain = lobj->prefered_domains;
+			u32 allowed = lobj->allowed_domains;
 			u32 current_domain =
 				radeon_mem_type_to_domain(bo->tbo.mem.mem_type);
 
@@ -479,7 +509,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 			 * into account. We don't want to disallow buffer moves
 			 * completely.
 			 */
-			if ((lobj->allowed_domains & current_domain) != 0 &&
+			if ((allowed & current_domain) != 0 &&
 			    (domain & current_domain) == 0 && /* will be moved */
 			    bytes_moved > bytes_moved_threshold) {
 				/* don't move it */
@@ -489,7 +519,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 		retry:
 			radeon_ttm_placement_from_domain(bo, domain);
 			if (ring == R600_RING_TYPE_UVD_INDEX)
-				radeon_uvd_force_into_uvd_segment(bo);
+				radeon_uvd_force_into_uvd_segment(bo, allowed);
 
 			initial_bytes_moved = atomic64_read(&rdev->num_bytes_moved);
 			r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
@@ -731,7 +761,7 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 
 	/* hurrah the memory is not visible ! */
 	radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
-	rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
+	rbo->placements[0].lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
 	r = ttm_bo_validate(bo, &rbo->placement, false, false);
 	if (unlikely(r == -ENOMEM)) {
 		radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
@@ -755,12 +785,10 @@ int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type, bool no_wait)
 	r = ttm_bo_reserve(&bo->tbo, true, no_wait, false, NULL);
 	if (unlikely(r != 0))
 		return r;
-	spin_lock(&bo->tbo.bdev->fence_lock);
 	if (mem_type)
 		*mem_type = bo->tbo.mem.mem_type;
-	if (bo->tbo.sync_obj)
-		r = ttm_bo_wait(&bo->tbo, true, true, no_wait);
-	spin_unlock(&bo->tbo.bdev->fence_lock);
+
+	r = ttm_bo_wait(&bo->tbo, true, true, no_wait);
 	ttm_bo_unreserve(&bo->tbo);
 	return r;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 98a47fdf3625..1b8ec7917154 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -126,6 +126,7 @@ extern int radeon_bo_create(struct radeon_device *rdev,
 			    unsigned long size, int byte_align,
 			    bool kernel, u32 domain, u32 flags,
 			    struct sg_table *sg,
+			    struct reservation_object *resv,
 			    struct radeon_bo **bo_ptr);
 extern int radeon_bo_kmap(struct radeon_bo *bo, void **ptr);
 extern void radeon_bo_kunmap(struct radeon_bo *bo);
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 164898b0010c..32522cc940a1 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1556,7 +1556,7 @@ static bool radeon_pm_in_vbl(struct radeon_device *rdev)
 		if (rdev->pm.active_crtcs & (1 << crtc)) {
 			vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev, crtc, 0, &vpos, &hpos, NULL, NULL);
 			if ((vbl_status & DRM_SCANOUTPOS_VALID) &&
-			    !(vbl_status & DRM_SCANOUTPOS_INVBL))
+			    !(vbl_status & DRM_SCANOUTPOS_IN_VBLANK))
 				in_vbl = false;
 		}
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c
index 0b16f2cbcf17..f3609c97496b 100644
--- a/drivers/gpu/drm/radeon/radeon_prime.c
+++ b/drivers/gpu/drm/radeon/radeon_prime.c
@@ -27,6 +27,7 @@
 
 #include "radeon.h"
 #include <drm/radeon_drm.h>
+#include <linux/dma-buf.h>
 
 struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
@@ -57,15 +58,18 @@ void radeon_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 }
 
 struct drm_gem_object *radeon_gem_prime_import_sg_table(struct drm_device *dev,
-							size_t size,
+							struct dma_buf_attachment *attach,
 							struct sg_table *sg)
 {
+	struct reservation_object *resv = attach->dmabuf->resv;
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_bo *bo;
 	int ret;
 
-	ret = radeon_bo_create(rdev, size, PAGE_SIZE, false,
-			       RADEON_GEM_DOMAIN_GTT, 0, sg, &bo);
+	ww_mutex_lock(&resv->lock, NULL);
+	ret = radeon_bo_create(rdev, attach->dmabuf->size, PAGE_SIZE, false,
+			       RADEON_GEM_DOMAIN_GTT, 0, sg, resv, &bo);
+	ww_mutex_unlock(&resv->lock);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -111,3 +115,13 @@ struct reservation_object *radeon_gem_prime_res_obj(struct drm_gem_object *obj)
 
 	return bo->tbo.resv;
 }
+
+struct dma_buf *radeon_gem_prime_export(struct drm_device *dev,
+					struct drm_gem_object *gobj,
+					int flags)
+{
+	struct radeon_bo *bo = gem_to_radeon_bo(gobj);
+	if (radeon_ttm_tt_has_userptr(bo->tbo.ttm))
+		return ERR_PTR(-EPERM);
+	return drm_gem_prime_export(dev, gobj, flags);
+}
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index d65607902537..3d17af34afa7 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -45,27 +45,6 @@
 static int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring);
 
 /**
- * radeon_ring_write - write a value to the ring
- *
- * @ring: radeon_ring structure holding ring information
- * @v: dword (dw) value to write
- *
- * Write a value to the requested ring buffer (all asics).
- */
-void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
-{
-#if DRM_DEBUG_CODE
-	if (ring->count_dw <= 0) {
-		DRM_ERROR("radeon: writing more dwords to the ring than expected!\n");
-	}
-#endif
-	ring->ring[ring->wptr++] = v;
-	ring->wptr &= ring->ptr_mask;
-	ring->count_dw--;
-	ring->ring_free_dw--;
-}
-
-/**
  * radeon_ring_supports_scratch_reg - check if the ring supports
  * writing to scratch registers
  *
@@ -404,7 +383,7 @@ int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsig
 	/* Allocate ring buffer */
 	if (ring->ring_obj == NULL) {
 		r = radeon_bo_create(rdev, ring->ring_size, PAGE_SIZE, true,
-				     RADEON_GEM_DOMAIN_GTT, 0,
+				     RADEON_GEM_DOMAIN_GTT, 0, NULL,
 				     NULL, &ring->ring_obj);
 		if (r) {
 			dev_err(rdev->dev, "(%d) ring create failed\n", r);
diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index b84f97c8718c..c507896aca45 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -65,7 +65,7 @@ int radeon_sa_bo_manager_init(struct radeon_device *rdev,
 	}
 
 	r = radeon_bo_create(rdev, size, align, true,
-			     domain, flags, NULL, &sa_manager->bo);
+			     domain, flags, NULL, NULL, &sa_manager->bo);
 	if (r) {
 		dev_err(rdev->dev, "(%d) failed to allocate bo for manager\n", r);
 		return r;
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index abd6753a570a..6deb08f045b7 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -96,15 +96,15 @@ bool radeon_semaphore_emit_wait(struct radeon_device *rdev, int ridx,
 }
 
 /**
- * radeon_semaphore_sync_to - use the semaphore to sync to a fence
+ * radeon_semaphore_sync_fence - use the semaphore to sync to a fence
  *
  * @semaphore: semaphore object to add fence to
  * @fence: fence to sync to
  *
  * Sync to the fence using this semaphore object
  */
-void radeon_semaphore_sync_to(struct radeon_semaphore *semaphore,
-			      struct radeon_fence *fence)
+void radeon_semaphore_sync_fence(struct radeon_semaphore *semaphore,
+				 struct radeon_fence *fence)
 {
         struct radeon_fence *other;
 
@@ -116,6 +116,53 @@ void radeon_semaphore_sync_to(struct radeon_semaphore *semaphore,
 }
 
 /**
+ * radeon_semaphore_sync_to - use the semaphore to sync to a reservation object
+ *
+ * @sema: semaphore object to add fence from reservation object to
+ * @resv: reservation object with embedded fence
+ * @shared: true if we should onyl sync to the exclusive fence
+ *
+ * Sync to the fence using this semaphore object
+ */
+int radeon_semaphore_sync_resv(struct radeon_device *rdev,
+			       struct radeon_semaphore *sema,
+			       struct reservation_object *resv,
+			       bool shared)
+{
+	struct reservation_object_list *flist;
+	struct fence *f;
+	struct radeon_fence *fence;
+	unsigned i;
+	int r = 0;
+
+	/* always sync to the exclusive fence */
+	f = reservation_object_get_excl(resv);
+	fence = f ? to_radeon_fence(f) : NULL;
+	if (fence && fence->rdev == rdev)
+		radeon_semaphore_sync_fence(sema, fence);
+	else if (f)
+		r = fence_wait(f, true);
+
+	flist = reservation_object_get_list(resv);
+	if (shared || !flist || r)
+		return r;
+
+	for (i = 0; i < flist->shared_count; ++i) {
+		f = rcu_dereference_protected(flist->shared[i],
+					      reservation_object_held(resv));
+		fence = to_radeon_fence(f);
+		if (fence && fence->rdev == rdev)
+			radeon_semaphore_sync_fence(sema, fence);
+		else
+			r = fence_wait(f, true);
+
+		if (r)
+			break;
+	}
+	return r;
+}
+
+/**
  * radeon_semaphore_sync_rings - sync ring to all registered fences
  *
  * @rdev: radeon_device pointer
diff --git a/drivers/gpu/drm/radeon/radeon_state.c b/drivers/gpu/drm/radeon/radeon_state.c
index 23bb64fd775f..535403e0c8a2 100644
--- a/drivers/gpu/drm/radeon/radeon_state.c
+++ b/drivers/gpu/drm/radeon/radeon_state.c
@@ -30,9 +30,9 @@
  */
 
 #include <drm/drmP.h>
-#include <drm/drm_buffer.h>
 #include <drm/radeon_drm.h>
 #include "radeon_drv.h"
+#include "drm_buffer.h"
 
 /* ================================================================
  * Helper functions for client state checking and fixup
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 17bc3dced9f1..07b506b41008 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -67,7 +67,7 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 	}
 
 	r = radeon_bo_create(rdev, size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
-			     0, NULL, &vram_obj);
+			     0, NULL, NULL, &vram_obj);
 	if (r) {
 		DRM_ERROR("Failed to create VRAM object\n");
 		goto out_cleanup;
@@ -87,7 +87,8 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 		struct radeon_fence *fence = NULL;
 
 		r = radeon_bo_create(rdev, size, PAGE_SIZE, true,
-				     RADEON_GEM_DOMAIN_GTT, 0, NULL, gtt_obj + i);
+				     RADEON_GEM_DOMAIN_GTT, 0, NULL, NULL,
+				     gtt_obj + i);
 		if (r) {
 			DRM_ERROR("Failed to create GTT object %d\n", i);
 			goto out_lclean;
@@ -116,11 +117,16 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 		radeon_bo_kunmap(gtt_obj[i]);
 
 		if (ring == R600_RING_TYPE_DMA_INDEX)
-			r = radeon_copy_dma(rdev, gtt_addr, vram_addr, size / RADEON_GPU_PAGE_SIZE, &fence);
+			fence = radeon_copy_dma(rdev, gtt_addr, vram_addr,
+						size / RADEON_GPU_PAGE_SIZE,
+						NULL);
 		else
-			r = radeon_copy_blit(rdev, gtt_addr, vram_addr, size / RADEON_GPU_PAGE_SIZE, &fence);
-		if (r) {
+			fence = radeon_copy_blit(rdev, gtt_addr, vram_addr,
+						 size / RADEON_GPU_PAGE_SIZE,
+						 NULL);
+		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed GTT->VRAM copy %d\n", i);
+			r = PTR_ERR(fence);
 			goto out_lclean_unpin;
 		}
 
@@ -162,11 +168,16 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 		radeon_bo_kunmap(vram_obj);
 
 		if (ring == R600_RING_TYPE_DMA_INDEX)
-			r = radeon_copy_dma(rdev, vram_addr, gtt_addr, size / RADEON_GPU_PAGE_SIZE, &fence);
+			fence = radeon_copy_dma(rdev, vram_addr, gtt_addr,
+						size / RADEON_GPU_PAGE_SIZE,
+						NULL);
 		else
-			r = radeon_copy_blit(rdev, vram_addr, gtt_addr, size / RADEON_GPU_PAGE_SIZE, &fence);
-		if (r) {
+			fence = radeon_copy_blit(rdev, vram_addr, gtt_addr,
+						 size / RADEON_GPU_PAGE_SIZE,
+						 NULL);
+		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed VRAM->GTT copy %d\n", i);
+			r = PTR_ERR(fence);
 			goto out_lclean_unpin;
 		}
 
@@ -222,7 +233,7 @@ out_lclean:
 			radeon_bo_unreserve(gtt_obj[i]);
 			radeon_bo_unref(&gtt_obj[i]);
 		}
-		if (fence)
+		if (fence && !IS_ERR(fence))
 			radeon_fence_unref(&fence);
 		break;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 72afe82a95c9..8624979afb65 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -39,6 +39,8 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/swiotlb.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
 #include <linux/debugfs.h>
 #include "radeon_reg.h"
 #include "radeon.h"
@@ -176,12 +178,15 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 static void radeon_evict_flags(struct ttm_buffer_object *bo,
 				struct ttm_placement *placement)
 {
+	static struct ttm_place placements = {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM
+	};
+
 	struct radeon_bo *rbo;
-	static u32 placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 
 	if (!radeon_ttm_bo_is_radeon_bo(bo)) {
-		placement->fpfn = 0;
-		placement->lpfn = 0;
 		placement->placement = &placements;
 		placement->busy_placement = &placements;
 		placement->num_placement = 1;
@@ -228,6 +233,7 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 	struct radeon_device *rdev;
 	uint64_t old_start, new_start;
 	struct radeon_fence *fence;
+	unsigned num_pages;
 	int r, ridx;
 
 	rdev = radeon_get_rdev(bo->bdev);
@@ -264,13 +270,12 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 
 	BUILD_BUG_ON((PAGE_SIZE % RADEON_GPU_PAGE_SIZE) != 0);
 
-	/* sync other rings */
-	fence = bo->sync_obj;
-	r = radeon_copy(rdev, old_start, new_start,
-			new_mem->num_pages * (PAGE_SIZE / RADEON_GPU_PAGE_SIZE), /* GPU pages */
-			&fence);
-	/* FIXME: handle copy error */
-	r = ttm_bo_move_accel_cleanup(bo, (void *)fence,
+	num_pages = new_mem->num_pages * (PAGE_SIZE / RADEON_GPU_PAGE_SIZE);
+	fence = radeon_copy(rdev, old_start, new_start, num_pages, bo->resv);
+	if (IS_ERR(fence))
+		return PTR_ERR(fence);
+
+	r = ttm_bo_move_accel_cleanup(bo, &fence->base,
 				      evict, no_wait_gpu, new_mem);
 	radeon_fence_unref(&fence);
 	return r;
@@ -284,20 +289,20 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 	struct radeon_device *rdev;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	struct ttm_mem_reg tmp_mem;
-	u32 placements;
+	struct ttm_place placements;
 	struct ttm_placement placement;
 	int r;
 
 	rdev = radeon_get_rdev(bo->bdev);
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
-	placement.fpfn = 0;
-	placement.lpfn = 0;
 	placement.num_placement = 1;
 	placement.placement = &placements;
 	placement.num_busy_placement = 1;
 	placement.busy_placement = &placements;
-	placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
+	placements.fpfn = 0;
+	placements.lpfn = 0;
+	placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
 	r = ttm_bo_mem_space(bo, &placement, &tmp_mem,
 			     interruptible, no_wait_gpu);
 	if (unlikely(r)) {
@@ -332,19 +337,19 @@ static int radeon_move_ram_vram(struct ttm_buffer_object *bo,
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	struct ttm_mem_reg tmp_mem;
 	struct ttm_placement placement;
-	u32 placements;
+	struct ttm_place placements;
 	int r;
 
 	rdev = radeon_get_rdev(bo->bdev);
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
-	placement.fpfn = 0;
-	placement.lpfn = 0;
 	placement.num_placement = 1;
 	placement.placement = &placements;
 	placement.num_busy_placement = 1;
 	placement.busy_placement = &placements;
-	placements = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
+	placements.fpfn = 0;
+	placements.lpfn = 0;
+	placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
 	r = ttm_bo_mem_space(bo, &placement, &tmp_mem,
 			     interruptible, no_wait_gpu);
 	if (unlikely(r)) {
@@ -483,39 +488,108 @@ static void radeon_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_re
 {
 }
 
-static int radeon_sync_obj_wait(void *sync_obj, bool lazy, bool interruptible)
-{
-	return radeon_fence_wait((struct radeon_fence *)sync_obj, interruptible);
-}
+/*
+ * TTM backend functions.
+ */
+struct radeon_ttm_tt {
+	struct ttm_dma_tt		ttm;
+	struct radeon_device		*rdev;
+	u64				offset;
 
-static int radeon_sync_obj_flush(void *sync_obj)
+	uint64_t			userptr;
+	struct mm_struct		*usermm;
+	uint32_t			userflags;
+};
+
+/* prepare the sg table with the user pages */
+static int radeon_ttm_tt_pin_userptr(struct ttm_tt *ttm)
 {
+	struct radeon_device *rdev = radeon_get_rdev(ttm->bdev);
+	struct radeon_ttm_tt *gtt = (void *)ttm;
+	unsigned pinned = 0, nents;
+	int r;
+
+	int write = !(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
+	enum dma_data_direction direction = write ?
+		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
+
+	if (current->mm != gtt->usermm)
+		return -EPERM;
+
+	if (gtt->userflags & RADEON_GEM_USERPTR_ANONONLY) {
+		/* check that we only pin down anonymous memory
+		   to prevent problems with writeback */
+		unsigned long end = gtt->userptr + ttm->num_pages * PAGE_SIZE;
+		struct vm_area_struct *vma;
+		vma = find_vma(gtt->usermm, gtt->userptr);
+		if (!vma || vma->vm_file || vma->vm_end < end)
+			return -EPERM;
+	}
+
+	do {
+		unsigned num_pages = ttm->num_pages - pinned;
+		uint64_t userptr = gtt->userptr + pinned * PAGE_SIZE;
+		struct page **pages = ttm->pages + pinned;
+
+		r = get_user_pages(current, current->mm, userptr, num_pages,
+				   write, 0, pages, NULL);
+		if (r < 0)
+			goto release_pages;
+
+		pinned += r;
+
+	} while (pinned < ttm->num_pages);
+
+	r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0,
+				      ttm->num_pages << PAGE_SHIFT,
+				      GFP_KERNEL);
+	if (r)
+		goto release_sg;
+
+	r = -ENOMEM;
+	nents = dma_map_sg(rdev->dev, ttm->sg->sgl, ttm->sg->nents, direction);
+	if (nents != ttm->sg->nents)
+		goto release_sg;
+
+	drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
+					 gtt->ttm.dma_address, ttm->num_pages);
+
 	return 0;
-}
 
-static void radeon_sync_obj_unref(void **sync_obj)
-{
-	radeon_fence_unref((struct radeon_fence **)sync_obj);
-}
+release_sg:
+	kfree(ttm->sg);
 
-static void *radeon_sync_obj_ref(void *sync_obj)
-{
-	return radeon_fence_ref((struct radeon_fence *)sync_obj);
+release_pages:
+	release_pages(ttm->pages, pinned, 0);
+	return r;
 }
 
-static bool radeon_sync_obj_signaled(void *sync_obj)
+static void radeon_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
 {
-	return radeon_fence_signaled((struct radeon_fence *)sync_obj);
-}
+	struct radeon_device *rdev = radeon_get_rdev(ttm->bdev);
+	struct radeon_ttm_tt *gtt = (void *)ttm;
+	struct scatterlist *sg;
+	int i;
 
-/*
- * TTM backend functions.
- */
-struct radeon_ttm_tt {
-	struct ttm_dma_tt		ttm;
-	struct radeon_device		*rdev;
-	u64				offset;
-};
+	int write = !(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
+	enum dma_data_direction direction = write ?
+		DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
+
+	/* free the sg table and pages again */
+	dma_unmap_sg(rdev->dev, ttm->sg->sgl, ttm->sg->nents, direction);
+
+	for_each_sg(ttm->sg->sgl, sg, ttm->sg->nents, i) {
+		struct page *page = sg_page(sg);
+
+		if (!(gtt->userflags & RADEON_GEM_USERPTR_READONLY))
+			set_page_dirty(page);
+
+		mark_page_accessed(page);
+		page_cache_release(page);
+	}
+
+	sg_free_table(ttm->sg);
+}
 
 static int radeon_ttm_backend_bind(struct ttm_tt *ttm,
 				   struct ttm_mem_reg *bo_mem)
@@ -525,6 +599,11 @@ static int radeon_ttm_backend_bind(struct ttm_tt *ttm,
 		RADEON_GART_PAGE_WRITE;
 	int r;
 
+	if (gtt->userptr) {
+		radeon_ttm_tt_pin_userptr(ttm);
+		flags &= ~RADEON_GART_PAGE_WRITE;
+	}
+
 	gtt->offset = (unsigned long)(bo_mem->start << PAGE_SHIFT);
 	if (!ttm->num_pages) {
 		WARN(1, "nothing to bind %lu pages for mreg %p back %p!\n",
@@ -547,6 +626,10 @@ static int radeon_ttm_backend_unbind(struct ttm_tt *ttm)
 	struct radeon_ttm_tt *gtt = (void *)ttm;
 
 	radeon_gart_unbind(gtt->rdev, gtt->offset, ttm->num_pages);
+
+	if (gtt->userptr)
+		radeon_ttm_tt_unpin_userptr(ttm);
+
 	return 0;
 }
 
@@ -592,10 +675,17 @@ static struct ttm_tt *radeon_ttm_tt_create(struct ttm_bo_device *bdev,
 	return &gtt->ttm.ttm;
 }
 
+static struct radeon_ttm_tt *radeon_ttm_tt_to_gtt(struct ttm_tt *ttm)
+{
+	if (!ttm || ttm->func != &radeon_backend_func)
+		return NULL;
+	return (struct radeon_ttm_tt *)ttm;
+}
+
 static int radeon_ttm_tt_populate(struct ttm_tt *ttm)
 {
+	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(ttm);
 	struct radeon_device *rdev;
-	struct radeon_ttm_tt *gtt = (void *)ttm;
 	unsigned i;
 	int r;
 	bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
@@ -603,6 +693,16 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm)
 	if (ttm->state != tt_unpopulated)
 		return 0;
 
+	if (gtt && gtt->userptr) {
+		ttm->sg = kcalloc(1, sizeof(struct sg_table), GFP_KERNEL);
+		if (!ttm->sg)
+			return -ENOMEM;
+
+		ttm->page_flags |= TTM_PAGE_FLAG_SG;
+		ttm->state = tt_unbound;
+		return 0;
+	}
+
 	if (slave && ttm->sg) {
 		drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
 						 gtt->ttm.dma_address, ttm->num_pages);
@@ -648,10 +748,16 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm)
 static void radeon_ttm_tt_unpopulate(struct ttm_tt *ttm)
 {
 	struct radeon_device *rdev;
-	struct radeon_ttm_tt *gtt = (void *)ttm;
+	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(ttm);
 	unsigned i;
 	bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
 
+	if (gtt && gtt->userptr) {
+		kfree(ttm->sg);
+		ttm->page_flags &= ~TTM_PAGE_FLAG_SG;
+		return;
+	}
+
 	if (slave)
 		return;
 
@@ -680,6 +786,40 @@ static void radeon_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	ttm_pool_unpopulate(ttm);
 }
 
+int radeon_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr,
+			      uint32_t flags)
+{
+	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(ttm);
+
+	if (gtt == NULL)
+		return -EINVAL;
+
+	gtt->userptr = addr;
+	gtt->usermm = current->mm;
+	gtt->userflags = flags;
+	return 0;
+}
+
+bool radeon_ttm_tt_has_userptr(struct ttm_tt *ttm)
+{
+	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(ttm);
+
+	if (gtt == NULL)
+		return false;
+
+	return !!gtt->userptr;
+}
+
+bool radeon_ttm_tt_is_readonly(struct ttm_tt *ttm)
+{
+	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(ttm);
+
+	if (gtt == NULL)
+		return false;
+
+	return !!(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
+}
+
 static struct ttm_bo_driver radeon_bo_driver = {
 	.ttm_tt_create = &radeon_ttm_tt_create,
 	.ttm_tt_populate = &radeon_ttm_tt_populate,
@@ -689,11 +829,6 @@ static struct ttm_bo_driver radeon_bo_driver = {
 	.evict_flags = &radeon_evict_flags,
 	.move = &radeon_bo_move,
 	.verify_access = &radeon_verify_access,
-	.sync_obj_signaled = &radeon_sync_obj_signaled,
-	.sync_obj_wait = &radeon_sync_obj_wait,
-	.sync_obj_flush = &radeon_sync_obj_flush,
-	.sync_obj_unref = &radeon_sync_obj_unref,
-	.sync_obj_ref = &radeon_sync_obj_ref,
 	.move_notify = &radeon_bo_move_notify,
 	.fault_reserve_notify = &radeon_bo_fault_reserve_notify,
 	.io_mem_reserve = &radeon_ttm_io_mem_reserve,
@@ -730,7 +865,7 @@ int radeon_ttm_init(struct radeon_device *rdev)
 	radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size);
 
 	r = radeon_bo_create(rdev, 256 * 1024, PAGE_SIZE, true,
-			     RADEON_GEM_DOMAIN_VRAM, 0,
+			     RADEON_GEM_DOMAIN_VRAM, 0, NULL,
 			     NULL, &rdev->stollen_vga_memory);
 	if (r) {
 		return r;
@@ -828,7 +963,7 @@ int radeon_mmap(struct file *filp, struct vm_area_struct *vma)
 	int r;
 
 	if (unlikely(vma->vm_pgoff < DRM_FILE_PAGE_OFFSET)) {
-		return drm_mmap(filp, vma);
+		return -EINVAL;
 	}
 
 	file_priv = filp->private_data;
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 341848a14376..11b662469253 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -40,12 +40,18 @@
 #define UVD_IDLE_TIMEOUT_MS	1000
 
 /* Firmware Names */
+#define FIRMWARE_R600		"radeon/R600_uvd.bin"
+#define FIRMWARE_RS780		"radeon/RS780_uvd.bin"
+#define FIRMWARE_RV770		"radeon/RV770_uvd.bin"
 #define FIRMWARE_RV710		"radeon/RV710_uvd.bin"
 #define FIRMWARE_CYPRESS	"radeon/CYPRESS_uvd.bin"
 #define FIRMWARE_SUMO		"radeon/SUMO_uvd.bin"
 #define FIRMWARE_TAHITI		"radeon/TAHITI_uvd.bin"
 #define FIRMWARE_BONAIRE	"radeon/BONAIRE_uvd.bin"
 
+MODULE_FIRMWARE(FIRMWARE_R600);
+MODULE_FIRMWARE(FIRMWARE_RS780);
+MODULE_FIRMWARE(FIRMWARE_RV770);
 MODULE_FIRMWARE(FIRMWARE_RV710);
 MODULE_FIRMWARE(FIRMWARE_CYPRESS);
 MODULE_FIRMWARE(FIRMWARE_SUMO);
@@ -63,6 +69,23 @@ int radeon_uvd_init(struct radeon_device *rdev)
 	INIT_DELAYED_WORK(&rdev->uvd.idle_work, radeon_uvd_idle_work_handler);
 
 	switch (rdev->family) {
+	case CHIP_RV610:
+	case CHIP_RV630:
+	case CHIP_RV670:
+	case CHIP_RV620:
+	case CHIP_RV635:
+		fw_name = FIRMWARE_R600;
+		break;
+
+	case CHIP_RS780:
+	case CHIP_RS880:
+		fw_name = FIRMWARE_RS780;
+		break;
+
+	case CHIP_RV770:
+		fw_name = FIRMWARE_RV770;
+		break;
+
 	case CHIP_RV710:
 	case CHIP_RV730:
 	case CHIP_RV740:
@@ -115,9 +138,11 @@ int radeon_uvd_init(struct radeon_device *rdev)
 	}
 
 	bo_size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 8) +
-		  RADEON_UVD_STACK_SIZE + RADEON_UVD_HEAP_SIZE;
+		  RADEON_UVD_STACK_SIZE + RADEON_UVD_HEAP_SIZE +
+		  RADEON_GPU_PAGE_SIZE;
 	r = radeon_bo_create(rdev, bo_size, PAGE_SIZE, true,
-			     RADEON_GEM_DOMAIN_VRAM, 0, NULL, &rdev->uvd.vcpu_bo);
+			     RADEON_GEM_DOMAIN_VRAM, 0, NULL,
+			     NULL, &rdev->uvd.vcpu_bo);
 	if (r) {
 		dev_err(rdev->dev, "(%d) failed to allocate UVD bo\n", r);
 		return r;
@@ -231,10 +256,30 @@ int radeon_uvd_resume(struct radeon_device *rdev)
 	return 0;
 }
 
-void radeon_uvd_force_into_uvd_segment(struct radeon_bo *rbo)
+void radeon_uvd_force_into_uvd_segment(struct radeon_bo *rbo,
+				       uint32_t allowed_domains)
 {
-	rbo->placement.fpfn = 0 >> PAGE_SHIFT;
-	rbo->placement.lpfn = (256 * 1024 * 1024) >> PAGE_SHIFT;
+	int i;
+
+	for (i = 0; i < rbo->placement.num_placement; ++i) {
+		rbo->placements[i].fpfn = 0 >> PAGE_SHIFT;
+		rbo->placements[i].lpfn = (256 * 1024 * 1024) >> PAGE_SHIFT;
+	}
+
+	/* If it must be in VRAM it must be in the first segment as well */
+	if (allowed_domains == RADEON_GEM_DOMAIN_VRAM)
+		return;
+
+	/* abort if we already have more than one placement */
+	if (rbo->placement.num_placement > 1)
+		return;
+
+	/* add another 256MB segment */
+	rbo->placements[1] = rbo->placements[0];
+	rbo->placements[1].fpfn += (256 * 1024 * 1024) >> PAGE_SHIFT;
+	rbo->placements[1].lpfn += (256 * 1024 * 1024) >> PAGE_SHIFT;
+	rbo->placement.num_placement++;
+	rbo->placement.num_busy_placement++;
 }
 
 void radeon_uvd_free_handles(struct radeon_device *rdev, struct drm_file *filp)
@@ -356,6 +401,7 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 {
 	int32_t *msg, msg_type, handle;
 	unsigned img_size = 0;
+	struct fence *f;
 	void *ptr;
 
 	int i, r;
@@ -365,8 +411,9 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 		return -EINVAL;
 	}
 
-	if (bo->tbo.sync_obj) {
-		r = radeon_fence_wait(bo->tbo.sync_obj, false);
+	f = reservation_object_get_excl(bo->tbo.resv);
+	if (f) {
+		r = radeon_fence_wait((struct radeon_fence *)f, false);
 		if (r) {
 			DRM_ERROR("Failed waiting for UVD message (%d)!\n", r);
 			return r;
@@ -604,38 +651,16 @@ int radeon_uvd_cs_parse(struct radeon_cs_parser *p)
 }
 
 static int radeon_uvd_send_msg(struct radeon_device *rdev,
-			       int ring, struct radeon_bo *bo,
+			       int ring, uint64_t addr,
 			       struct radeon_fence **fence)
 {
-	struct ttm_validate_buffer tv;
-	struct ww_acquire_ctx ticket;
-	struct list_head head;
 	struct radeon_ib ib;
-	uint64_t addr;
 	int i, r;
 
-	memset(&tv, 0, sizeof(tv));
-	tv.bo = &bo->tbo;
-
-	INIT_LIST_HEAD(&head);
-	list_add(&tv.head, &head);
-
-	r = ttm_eu_reserve_buffers(&ticket, &head);
-	if (r)
-		return r;
-
-	radeon_ttm_placement_from_domain(bo, RADEON_GEM_DOMAIN_VRAM);
-	radeon_uvd_force_into_uvd_segment(bo);
-
-	r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
-	if (r) 
-		goto err;
-
 	r = radeon_ib_get(rdev, ring, &ib, NULL, 64);
 	if (r)
-		goto err;
+		return r;
 
-	addr = radeon_bo_gpu_offset(bo);
 	ib.ptr[0] = PACKET0(UVD_GPCOM_VCPU_DATA0, 0);
 	ib.ptr[1] = addr;
 	ib.ptr[2] = PACKET0(UVD_GPCOM_VCPU_DATA1, 0);
@@ -647,19 +672,11 @@ static int radeon_uvd_send_msg(struct radeon_device *rdev,
 	ib.length_dw = 16;
 
 	r = radeon_ib_schedule(rdev, &ib, NULL, false);
-	if (r)
-		goto err;
-	ttm_eu_fence_buffer_objects(&ticket, &head, ib.fence);
 
 	if (fence)
 		*fence = radeon_fence_ref(ib.fence);
 
 	radeon_ib_free(rdev, &ib);
-	radeon_bo_unref(&bo);
-	return 0;
-
-err:
-	ttm_eu_backoff_reservation(&ticket, &head);
 	return r;
 }
 
@@ -669,27 +686,18 @@ err:
 int radeon_uvd_get_create_msg(struct radeon_device *rdev, int ring,
 			      uint32_t handle, struct radeon_fence **fence)
 {
-	struct radeon_bo *bo;
-	uint32_t *msg;
-	int r, i;
+	/* we use the last page of the vcpu bo for the UVD message */
+	uint64_t offs = radeon_bo_size(rdev->uvd.vcpu_bo) -
+		RADEON_GPU_PAGE_SIZE;
 
-	r = radeon_bo_create(rdev, 1024, PAGE_SIZE, true,
-			     RADEON_GEM_DOMAIN_VRAM, 0, NULL, &bo);
-	if (r)
-		return r;
+	uint32_t *msg = rdev->uvd.cpu_addr + offs;
+	uint64_t addr = rdev->uvd.gpu_addr + offs;
 
-	r = radeon_bo_reserve(bo, false);
-	if (r) {
-		radeon_bo_unref(&bo);
-		return r;
-	}
+	int r, i;
 
-	r = radeon_bo_kmap(bo, (void **)&msg);
-	if (r) {
-		radeon_bo_unreserve(bo);
-		radeon_bo_unref(&bo);
+	r = radeon_bo_reserve(rdev->uvd.vcpu_bo, true);
+	if (r)
 		return r;
-	}
 
 	/* stitch together an UVD create msg */
 	msg[0] = cpu_to_le32(0x00000de4);
@@ -706,36 +714,26 @@ int radeon_uvd_get_create_msg(struct radeon_device *rdev, int ring,
 	for (i = 11; i < 1024; ++i)
 		msg[i] = cpu_to_le32(0x0);
 
-	radeon_bo_kunmap(bo);
-	radeon_bo_unreserve(bo);
-
-	return radeon_uvd_send_msg(rdev, ring, bo, fence);
+	r = radeon_uvd_send_msg(rdev, ring, addr, fence);
+	radeon_bo_unreserve(rdev->uvd.vcpu_bo);
+	return r;
 }
 
 int radeon_uvd_get_destroy_msg(struct radeon_device *rdev, int ring,
 			       uint32_t handle, struct radeon_fence **fence)
 {
-	struct radeon_bo *bo;
-	uint32_t *msg;
-	int r, i;
+	/* we use the last page of the vcpu bo for the UVD message */
+	uint64_t offs = radeon_bo_size(rdev->uvd.vcpu_bo) -
+		RADEON_GPU_PAGE_SIZE;
 
-	r = radeon_bo_create(rdev, 1024, PAGE_SIZE, true,
-			     RADEON_GEM_DOMAIN_VRAM, 0, NULL, &bo);
-	if (r)
-		return r;
+	uint32_t *msg = rdev->uvd.cpu_addr + offs;
+	uint64_t addr = rdev->uvd.gpu_addr + offs;
 
-	r = radeon_bo_reserve(bo, false);
-	if (r) {
-		radeon_bo_unref(&bo);
-		return r;
-	}
+	int r, i;
 
-	r = radeon_bo_kmap(bo, (void **)&msg);
-	if (r) {
-		radeon_bo_unreserve(bo);
-		radeon_bo_unref(&bo);
+	r = radeon_bo_reserve(rdev->uvd.vcpu_bo, true);
+	if (r)
 		return r;
-	}
 
 	/* stitch together an UVD destroy msg */
 	msg[0] = cpu_to_le32(0x00000de4);
@@ -745,10 +743,9 @@ int radeon_uvd_get_destroy_msg(struct radeon_device *rdev, int ring,
 	for (i = 4; i < 1024; ++i)
 		msg[i] = cpu_to_le32(0x0);
 
-	radeon_bo_kunmap(bo);
-	radeon_bo_unreserve(bo);
-
-	return radeon_uvd_send_msg(rdev, ring, bo, fence);
+	r = radeon_uvd_send_msg(rdev, ring, addr, fence);
+	radeon_bo_unreserve(rdev->uvd.vcpu_bo);
+	return r;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c
index c7190aadbd89..9e85757d5599 100644
--- a/drivers/gpu/drm/radeon/radeon_vce.c
+++ b/drivers/gpu/drm/radeon/radeon_vce.c
@@ -126,7 +126,8 @@ int radeon_vce_init(struct radeon_device *rdev)
 	size = RADEON_GPU_PAGE_ALIGN(rdev->vce_fw->size) +
 	       RADEON_VCE_STACK_SIZE + RADEON_VCE_HEAP_SIZE;
 	r = radeon_bo_create(rdev, size, PAGE_SIZE, true,
-			     RADEON_GEM_DOMAIN_VRAM, 0, NULL, &rdev->vce.vcpu_bo);
+			     RADEON_GEM_DOMAIN_VRAM, 0, NULL, NULL,
+			     &rdev->vce.vcpu_bo);
 	if (r) {
 		dev_err(rdev->dev, "(%d) failed to allocate VCE bo\n", r);
 		return r;
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 088ffdc2f577..4532cc76a0a6 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -143,6 +143,7 @@ struct radeon_cs_reloc *radeon_vm_get_bos(struct radeon_device *rdev,
 	list[0].prefered_domains = RADEON_GEM_DOMAIN_VRAM;
 	list[0].allowed_domains = RADEON_GEM_DOMAIN_VRAM;
 	list[0].tv.bo = &vm->page_directory->tbo;
+	list[0].tv.shared = false;
 	list[0].tiling_flags = 0;
 	list[0].handle = 0;
 	list_add(&list[0].tv.head, head);
@@ -156,6 +157,7 @@ struct radeon_cs_reloc *radeon_vm_get_bos(struct radeon_device *rdev,
 		list[idx].prefered_domains = RADEON_GEM_DOMAIN_VRAM;
 		list[idx].allowed_domains = RADEON_GEM_DOMAIN_VRAM;
 		list[idx].tv.bo = &list[idx].robj->tbo;
+		list[idx].tv.shared = false;
 		list[idx].tiling_flags = 0;
 		list[idx].handle = 0;
 		list_add(&list[idx++].tv.head, head);
@@ -395,11 +397,12 @@ static int radeon_vm_clear_bo(struct radeon_device *rdev,
 
         memset(&tv, 0, sizeof(tv));
         tv.bo = &bo->tbo;
+	tv.shared = false;
 
         INIT_LIST_HEAD(&head);
         list_add(&tv.head, &head);
 
-        r = ttm_eu_reserve_buffers(&ticket, &head);
+        r = ttm_eu_reserve_buffers(&ticket, &head, true);
         if (r)
 		return r;
 
@@ -424,7 +427,7 @@ static int radeon_vm_clear_bo(struct radeon_device *rdev,
 	if (r)
                 goto error;
 
-	ttm_eu_fence_buffer_objects(&ticket, &head, ib.fence);
+	ttm_eu_fence_buffer_objects(&ticket, &head, &ib.fence->base);
 	radeon_ib_free(rdev, &ib);
 
 	return 0;
@@ -545,7 +548,8 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 
 		r = radeon_bo_create(rdev, RADEON_VM_PTE_COUNT * 8,
 				     RADEON_GPU_PAGE_SIZE, true,
-				     RADEON_GEM_DOMAIN_VRAM, 0, NULL, &pt);
+				     RADEON_GEM_DOMAIN_VRAM, 0,
+				     NULL, NULL, &pt);
 		if (r)
 			return r;
 
@@ -694,8 +698,9 @@ int radeon_vm_update_page_directory(struct radeon_device *rdev,
 
 	if (ib.length_dw != 0) {
 		radeon_asic_vm_pad_ib(rdev, &ib);
-		radeon_semaphore_sync_to(ib.semaphore, pd->tbo.sync_obj);
-		radeon_semaphore_sync_to(ib.semaphore, vm->last_id_use);
+
+		radeon_semaphore_sync_resv(rdev, ib.semaphore, pd->tbo.resv, false);
+		radeon_semaphore_sync_fence(ib.semaphore, vm->last_id_use);
 		WARN_ON(ib.length_dw > ndw);
 		r = radeon_ib_schedule(rdev, &ib, NULL, false);
 		if (r) {
@@ -821,7 +826,7 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
 		unsigned nptes;
 		uint64_t pte;
 
-		radeon_semaphore_sync_to(ib->semaphore, pt->tbo.sync_obj);
+		radeon_semaphore_sync_resv(rdev, ib->semaphore, pt->tbo.resv, false);
 
 		if ((addr & ~mask) == (end & ~mask))
 			nptes = end - addr;
@@ -892,6 +897,9 @@ int radeon_vm_bo_update(struct radeon_device *rdev,
 	bo_va->flags &= ~RADEON_VM_PAGE_VALID;
 	bo_va->flags &= ~RADEON_VM_PAGE_SYSTEM;
 	bo_va->flags &= ~RADEON_VM_PAGE_SNOOPED;
+	if (bo_va->bo && radeon_ttm_tt_is_readonly(bo_va->bo->tbo.ttm))
+		bo_va->flags &= ~RADEON_VM_PAGE_WRITEABLE;
+
 	if (mem) {
 		addr = mem->start << PAGE_SHIFT;
 		if (mem->mem_type != TTM_PL_SYSTEM) {
@@ -960,7 +968,7 @@ int radeon_vm_bo_update(struct radeon_device *rdev,
 	radeon_asic_vm_pad_ib(rdev, &ib);
 	WARN_ON(ib.length_dw > ndw);
 
-	radeon_semaphore_sync_to(ib.semaphore, vm->fence);
+	radeon_semaphore_sync_fence(ib.semaphore, vm->fence);
 	r = radeon_ib_schedule(rdev, &ib, NULL, false);
 	if (r) {
 		radeon_ib_free(rdev, &ib);
@@ -1120,7 +1128,7 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
 
 	r = radeon_bo_create(rdev, pd_size, align, true,
 			     RADEON_GEM_DOMAIN_VRAM, 0, NULL,
-			     &vm->page_directory);
+			     NULL, &vm->page_directory);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index d9f5ce715c9b..372016e266d0 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -26,7 +26,6 @@
  *          Jerome Glisse
  */
 #include <linux/firmware.h>
-#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <drm/drmP.h>
 #include "radeon.h"
diff --git a/drivers/gpu/drm/radeon/rv770_dma.c b/drivers/gpu/drm/radeon/rv770_dma.c
index 74426ac2bb5c..7f34bad2e724 100644
--- a/drivers/gpu/drm/radeon/rv770_dma.c
+++ b/drivers/gpu/drm/radeon/rv770_dma.c
@@ -33,18 +33,19 @@
  * @src_offset: src GPU address
  * @dst_offset: dst GPU address
  * @num_gpu_pages: number of GPU pages to xfer
- * @fence: radeon fence object
+ * @resv: reservation object to sync to
  *
  * Copy GPU paging using the DMA engine (r7xx).
  * Used by the radeon ttm implementation to move pages if
  * registered as the asic copy callback.
  */
-int rv770_copy_dma(struct radeon_device *rdev,
-		  uint64_t src_offset, uint64_t dst_offset,
-		  unsigned num_gpu_pages,
-		  struct radeon_fence **fence)
+struct radeon_fence *rv770_copy_dma(struct radeon_device *rdev,
+				    uint64_t src_offset, uint64_t dst_offset,
+				    unsigned num_gpu_pages,
+				    struct reservation_object *resv)
 {
 	struct radeon_semaphore *sem = NULL;
+	struct radeon_fence *fence;
 	int ring_index = rdev->asic->copy.dma_ring_index;
 	struct radeon_ring *ring = &rdev->ring[ring_index];
 	u32 size_in_dw, cur_size_in_dw;
@@ -54,7 +55,7 @@ int rv770_copy_dma(struct radeon_device *rdev,
 	r = radeon_semaphore_create(rdev, &sem);
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;
@@ -63,10 +64,10 @@ int rv770_copy_dma(struct radeon_device *rdev,
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
-	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_resv(rdev, sem, resv, false);
 	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	for (i = 0; i < num_loops; i++) {
@@ -83,15 +84,15 @@ int rv770_copy_dma(struct radeon_device *rdev,
 		dst_offset += cur_size_in_dw * 4;
 	}
 
-	r = radeon_fence_emit(rdev, fence, ring->idx);
+	r = radeon_fence_emit(rdev, &fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	radeon_ring_unlock_commit(rdev, ring, false);
-	radeon_semaphore_free(rdev, &sem, *fence);
+	radeon_semaphore_free(rdev, &sem, fence);
 
-	return r;
+	return fence;
 }
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 3a0b973e8a96..eeea5b6a1775 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -4684,7 +4684,7 @@ static int si_vm_packet3_compute_check(struct radeon_device *rdev,
 int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib)
 {
 	int ret = 0;
-	u32 idx = 0;
+	u32 idx = 0, i;
 	struct radeon_cs_packet pkt;
 
 	do {
@@ -4695,6 +4695,12 @@ int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib)
 		switch (pkt.type) {
 		case RADEON_PACKET_TYPE0:
 			dev_err(rdev->dev, "Packet0 not allowed!\n");
+			for (i = 0; i < ib->length_dw; i++) {
+				if (i == idx)
+					printk("\t0x%08x <---\n", ib->ptr[i]);
+				else
+					printk("\t0x%08x\n", ib->ptr[i]);
+			}
 			ret = -EINVAL;
 			break;
 		case RADEON_PACKET_TYPE2:
diff --git a/drivers/gpu/drm/radeon/si_dma.c b/drivers/gpu/drm/radeon/si_dma.c
index 7c22baaf94db..b58f12b762d7 100644
--- a/drivers/gpu/drm/radeon/si_dma.c
+++ b/drivers/gpu/drm/radeon/si_dma.c
@@ -218,18 +218,19 @@ void si_dma_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
  * @src_offset: src GPU address
  * @dst_offset: dst GPU address
  * @num_gpu_pages: number of GPU pages to xfer
- * @fence: radeon fence object
+ * @resv: reservation object to sync to
  *
  * Copy GPU paging using the DMA engine (SI).
  * Used by the radeon ttm implementation to move pages if
  * registered as the asic copy callback.
  */
-int si_copy_dma(struct radeon_device *rdev,
-		uint64_t src_offset, uint64_t dst_offset,
-		unsigned num_gpu_pages,
-		struct radeon_fence **fence)
+struct radeon_fence *si_copy_dma(struct radeon_device *rdev,
+				 uint64_t src_offset, uint64_t dst_offset,
+				 unsigned num_gpu_pages,
+				 struct reservation_object *resv)
 {
 	struct radeon_semaphore *sem = NULL;
+	struct radeon_fence *fence;
 	int ring_index = rdev->asic->copy.dma_ring_index;
 	struct radeon_ring *ring = &rdev->ring[ring_index];
 	u32 size_in_bytes, cur_size_in_bytes;
@@ -239,7 +240,7 @@ int si_copy_dma(struct radeon_device *rdev,
 	r = radeon_semaphore_create(rdev, &sem);
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
@@ -248,10 +249,10 @@ int si_copy_dma(struct radeon_device *rdev,
 	if (r) {
 		DRM_ERROR("radeon: moving bo (%d).\n", r);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
-	radeon_semaphore_sync_to(sem, *fence);
+	radeon_semaphore_sync_resv(rdev, sem, resv, false);
 	radeon_semaphore_sync_rings(rdev, sem, ring->idx);
 
 	for (i = 0; i < num_loops; i++) {
@@ -268,16 +269,16 @@ int si_copy_dma(struct radeon_device *rdev,
 		dst_offset += cur_size_in_bytes;
 	}
 
-	r = radeon_fence_emit(rdev, fence, ring->idx);
+	r = radeon_fence_emit(rdev, &fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
 		radeon_semaphore_free(rdev, &sem, NULL);
-		return r;
+		return ERR_PTR(r);
 	}
 
 	radeon_ring_unlock_commit(rdev, ring, false);
-	radeon_semaphore_free(rdev, &sem, *fence);
+	radeon_semaphore_free(rdev, &sem, fence);
 
-	return r;
+	return fence;
 }
 
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 70e61ffeace2..9e4d5d7d348f 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2916,7 +2916,6 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 	bool disable_sclk_switching = false;
 	u32 mclk, sclk;
 	u16 vddc, vddci;
-	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 	int i;
 
 	if ((rdev->pm.dpm.new_active_crtc_count > 1) ||
@@ -2950,29 +2949,6 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 		}
 	}
 
-	/* limit clocks to max supported clocks based on voltage dependency tables */
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk,
-							&max_sclk_vddc);
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk,
-							&max_mclk_vddci);
-	btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk,
-							&max_mclk_vddc);
-
-	for (i = 0; i < ps->performance_level_count; i++) {
-		if (max_sclk_vddc) {
-			if (ps->performance_levels[i].sclk > max_sclk_vddc)
-				ps->performance_levels[i].sclk = max_sclk_vddc;
-		}
-		if (max_mclk_vddci) {
-			if (ps->performance_levels[i].mclk > max_mclk_vddci)
-				ps->performance_levels[i].mclk = max_mclk_vddci;
-		}
-		if (max_mclk_vddc) {
-			if (ps->performance_levels[i].mclk > max_mclk_vddc)
-				ps->performance_levels[i].mclk = max_mclk_vddc;
-		}
-	}
-
 	/* XXX validate the min clocks required for display */
 
 	if (disable_mclk_switching) {
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index fd414d34d885..6635da9ec986 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -736,7 +736,7 @@
 #       define DESCRIPTION16(x)                          (((x) & 0xff) << 0)
 #       define DESCRIPTION17(x)                          (((x) & 0xff) << 8)
 
-#define AZ_F0_CODEC_PIN_CONTROL_HOTPLUG_CONTROL          0x54
+#define AZ_F0_CODEC_PIN_CONTROL_HOT_PLUG_CONTROL         0x54
 #       define AUDIO_ENABLED                             (1 << 31)
 
 #define AZ_F0_CODEC_PIN_CONTROL_RESPONSE_CONFIGURATION_DEFAULT  0x56
diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c
index cda391347286..e72b3cb59358 100644
--- a/drivers/gpu/drm/radeon/uvd_v1_0.c
+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c
@@ -22,6 +22,7 @@
  * Authors: Christian König <christian.koenig@amd.com>
  */
 
+#include <linux/firmware.h>
 #include <drm/drmP.h>
 #include "radeon.h"
 #include "radeon_asic.h"
@@ -70,6 +71,82 @@ void uvd_v1_0_set_wptr(struct radeon_device *rdev,
 }
 
 /**
+ * uvd_v1_0_fence_emit - emit an fence & trap command
+ *
+ * @rdev: radeon_device pointer
+ * @fence: fence to emit
+ *
+ * Write a fence and a trap command to the ring.
+ */
+void uvd_v1_0_fence_emit(struct radeon_device *rdev,
+			 struct radeon_fence *fence)
+{
+	struct radeon_ring *ring = &rdev->ring[fence->ring];
+	uint64_t addr = rdev->fence_drv[fence->ring].gpu_addr;
+
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA0, 0));
+	radeon_ring_write(ring, addr & 0xffffffff);
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA1, 0));
+	radeon_ring_write(ring, fence->seq);
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_CMD, 0));
+	radeon_ring_write(ring, 0);
+
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA0, 0));
+	radeon_ring_write(ring, 0);
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA1, 0));
+	radeon_ring_write(ring, 0);
+	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_CMD, 0));
+	radeon_ring_write(ring, 2);
+	return;
+}
+
+/**
+ * uvd_v1_0_resume - memory controller programming
+ *
+ * @rdev: radeon_device pointer
+ *
+ * Let the UVD memory controller know it's offsets
+ */
+int uvd_v1_0_resume(struct radeon_device *rdev)
+{
+	uint64_t addr;
+	uint32_t size;
+	int r;
+
+	r = radeon_uvd_resume(rdev);
+	if (r)
+		return r;
+
+	/* programm the VCPU memory controller bits 0-27 */
+	addr = (rdev->uvd.gpu_addr >> 3) + 16;
+	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size) >> 3;
+	WREG32(UVD_VCPU_CACHE_OFFSET0, addr);
+	WREG32(UVD_VCPU_CACHE_SIZE0, size);
+
+	addr += size;
+	size = RADEON_UVD_STACK_SIZE >> 3;
+	WREG32(UVD_VCPU_CACHE_OFFSET1, addr);
+	WREG32(UVD_VCPU_CACHE_SIZE1, size);
+
+	addr += size;
+	size = RADEON_UVD_HEAP_SIZE >> 3;
+	WREG32(UVD_VCPU_CACHE_OFFSET2, addr);
+	WREG32(UVD_VCPU_CACHE_SIZE2, size);
+
+	/* bits 28-31 */
+	addr = (rdev->uvd.gpu_addr >> 28) & 0xF;
+	WREG32(UVD_LMI_ADDR_EXT, (addr << 12) | (addr << 0));
+
+	/* bits 32-39 */
+	addr = (rdev->uvd.gpu_addr >> 32) & 0xFF;
+	WREG32(UVD_LMI_EXT40_ADDR, addr | (0x9 << 16) | (0x1 << 31));
+
+	WREG32(UVD_FW_START, *((uint32_t*)rdev->uvd.cpu_addr));
+
+	return 0;
+}
+
+/**
  * uvd_v1_0_init - start and test UVD block
  *
  * @rdev: radeon_device pointer
@@ -130,8 +207,32 @@ done:
 	/* lower clocks again */
 	radeon_set_uvd_clocks(rdev, 0, 0);
 
-	if (!r)
+	if (!r) {
+		switch (rdev->family) {
+		case CHIP_RV610:
+		case CHIP_RV630:
+		case CHIP_RV620:
+			/* 64byte granularity workaround */
+			WREG32(MC_CONFIG, 0);
+			WREG32(MC_CONFIG, 1 << 4);
+			WREG32(RS_DQ_RD_RET_CONF, 0x3f);
+			WREG32(MC_CONFIG, 0x1f);
+
+			/* fall through */
+		case CHIP_RV670:
+		case CHIP_RV635:
+
+			/* write clean workaround */
+			WREG32_P(UVD_VCPU_CNTL, 0x10, ~0x10);
+			break;
+
+		default:
+			/* TODO: Do we need more? */
+			break;
+		}
+
 		DRM_INFO("UVD initialized successfully.\n");
+	}
 
 	return r;
 }
@@ -218,12 +319,12 @@ int uvd_v1_0_start(struct radeon_device *rdev)
 	/* enable UMC */
 	WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8));
 
+	WREG32_P(UVD_RB_ARB_CTRL, 0, ~(1 << 3));
+
 	/* boot up the VCPU */
 	WREG32(UVD_SOFT_RESET, 0);
 	mdelay(10);
 
-	WREG32_P(UVD_RB_ARB_CTRL, 0, ~(1 << 3));
-
 	for (i = 0; i < 10; ++i) {
 		uint32_t status;
 		for (j = 0; j < 100; ++j) {
diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c
index 8bfdadd56598..89193519f8a1 100644
--- a/drivers/gpu/drm/radeon/uvd_v2_2.c
+++ b/drivers/gpu/drm/radeon/uvd_v2_2.c
@@ -72,6 +72,10 @@ int uvd_v2_2_resume(struct radeon_device *rdev)
 	uint32_t chip_id, size;
 	int r;
 
+	/* RV770 uses V1.0 MC */
+	if (rdev->family == CHIP_RV770)
+		return uvd_v1_0_resume(rdev);
+
 	r = radeon_uvd_resume(rdev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index 2e3d7b5b0ad7..c96f6089f8bf 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -6,6 +6,7 @@ config DRM_RCAR_DU
 	select DRM_KMS_CMA_HELPER
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_FB_HELPER
+	select VIDEOMODE_HELPERS
 	help
 	  Choose this option if you have an R-Car chipset.
 	  If M is selected the module will be called rcar-du-drm.
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
index 299267db2898..148b50589181 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
@@ -1,7 +1,7 @@
 /*
  * rcar_du_crtc.c  --  R-Car Display Unit CRTCs
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
index 43e7575c700c..e97ae502dec5 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
@@ -1,7 +1,7 @@
 /*
  * rcar_du_crtc.h  --  R-Car Display Unit CRTCs
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index fda64b7b73e8..d212efa6a495 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -1,7 +1,7 @@
 /*
  * rcar_du_drv.c  --  R-Car Display Unit DRM driver
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
@@ -15,6 +15,7 @@
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm.h>
 #include <linux/slab.h>
@@ -30,6 +31,97 @@
 #include "rcar_du_regs.h"
 
 /* -----------------------------------------------------------------------------
+ * Device Information
+ */
+
+static const struct rcar_du_device_info rcar_du_r8a7779_info = {
+	.features = 0,
+	.num_crtcs = 2,
+	.routes = {
+		/* R8A7779 has two RGB outputs and one (currently unsupported)
+		 * TCON output.
+		 */
+		[RCAR_DU_OUTPUT_DPAD0] = {
+			.possible_crtcs = BIT(0),
+			.encoder_type = DRM_MODE_ENCODER_NONE,
+			.port = 0,
+		},
+		[RCAR_DU_OUTPUT_DPAD1] = {
+			.possible_crtcs = BIT(1) | BIT(0),
+			.encoder_type = DRM_MODE_ENCODER_NONE,
+			.port = 1,
+		},
+	},
+	.num_lvds = 0,
+};
+
+static const struct rcar_du_device_info rcar_du_r8a7790_info = {
+	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK | RCAR_DU_FEATURE_DEFR8,
+	.quirks = RCAR_DU_QUIRK_ALIGN_128B | RCAR_DU_QUIRK_LVDS_LANES,
+	.num_crtcs = 3,
+	.routes = {
+		/* R8A7790 has one RGB output, two LVDS outputs and one
+		 * (currently unsupported) TCON output.
+		 */
+		[RCAR_DU_OUTPUT_DPAD0] = {
+			.possible_crtcs = BIT(2) | BIT(1) | BIT(0),
+			.encoder_type = DRM_MODE_ENCODER_NONE,
+			.port = 0,
+		},
+		[RCAR_DU_OUTPUT_LVDS0] = {
+			.possible_crtcs = BIT(0),
+			.encoder_type = DRM_MODE_ENCODER_LVDS,
+			.port = 1,
+		},
+		[RCAR_DU_OUTPUT_LVDS1] = {
+			.possible_crtcs = BIT(2) | BIT(1),
+			.encoder_type = DRM_MODE_ENCODER_LVDS,
+			.port = 2,
+		},
+	},
+	.num_lvds = 2,
+};
+
+static const struct rcar_du_device_info rcar_du_r8a7791_info = {
+	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK | RCAR_DU_FEATURE_DEFR8,
+	.num_crtcs = 2,
+	.routes = {
+		/* R8A7791 has one RGB output, one LVDS output and one
+		 * (currently unsupported) TCON output.
+		 */
+		[RCAR_DU_OUTPUT_DPAD0] = {
+			.possible_crtcs = BIT(1),
+			.encoder_type = DRM_MODE_ENCODER_NONE,
+			.port = 0,
+		},
+		[RCAR_DU_OUTPUT_LVDS0] = {
+			.possible_crtcs = BIT(0),
+			.encoder_type = DRM_MODE_ENCODER_LVDS,
+			.port = 1,
+		},
+	},
+	.num_lvds = 1,
+};
+
+static const struct platform_device_id rcar_du_id_table[] = {
+	{ "rcar-du-r8a7779", (kernel_ulong_t)&rcar_du_r8a7779_info },
+	{ "rcar-du-r8a7790", (kernel_ulong_t)&rcar_du_r8a7790_info },
+	{ "rcar-du-r8a7791", (kernel_ulong_t)&rcar_du_r8a7791_info },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(platform, rcar_du_id_table);
+
+static const struct of_device_id rcar_du_of_table[] = {
+	{ .compatible = "renesas,du-r8a7779", .data = &rcar_du_r8a7779_info },
+	{ .compatible = "renesas,du-r8a7790", .data = &rcar_du_r8a7790_info },
+	{ .compatible = "renesas,du-r8a7791", .data = &rcar_du_r8a7791_info },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, rcar_du_of_table);
+
+/* -----------------------------------------------------------------------------
  * DRM operations
  */
 
@@ -53,12 +145,13 @@ static int rcar_du_unload(struct drm_device *dev)
 static int rcar_du_load(struct drm_device *dev, unsigned long flags)
 {
 	struct platform_device *pdev = dev->platformdev;
+	struct device_node *np = pdev->dev.of_node;
 	struct rcar_du_platform_data *pdata = pdev->dev.platform_data;
 	struct rcar_du_device *rcdu;
 	struct resource *mem;
 	int ret;
 
-	if (pdata == NULL) {
+	if (pdata == NULL && np == NULL) {
 		dev_err(dev->dev, "no platform data\n");
 		return -ENODEV;
 	}
@@ -71,7 +164,8 @@ static int rcar_du_load(struct drm_device *dev, unsigned long flags)
 
 	rcdu->dev = &pdev->dev;
 	rcdu->pdata = pdata;
-	rcdu->info = (struct rcar_du_device_info *)pdev->id_entry->driver_data;
+	rcdu->info = np ? of_match_device(rcar_du_of_table, rcdu->dev)->data
+		   : (void *)platform_get_device_id(pdev)->driver_data;
 	rcdu->ddev = dev;
 	dev->dev_private = rcdu;
 
@@ -158,6 +252,7 @@ static struct drm_driver rcar_du_driver = {
 	.unload			= rcar_du_unload,
 	.preclose		= rcar_du_preclose,
 	.lastclose		= rcar_du_lastclose,
+	.set_busid		= drm_platform_set_busid,
 	.get_vblank_counter	= drm_vblank_count,
 	.enable_vblank		= rcar_du_enable_vblank,
 	.disable_vblank		= rcar_du_disable_vblank,
@@ -231,77 +326,6 @@ static int rcar_du_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct rcar_du_device_info rcar_du_r8a7779_info = {
-	.features = 0,
-	.num_crtcs = 2,
-	.routes = {
-		/* R8A7779 has two RGB outputs and one (currently unsupported)
-		 * TCON output.
-		 */
-		[RCAR_DU_OUTPUT_DPAD0] = {
-			.possible_crtcs = BIT(0),
-			.encoder_type = DRM_MODE_ENCODER_NONE,
-		},
-		[RCAR_DU_OUTPUT_DPAD1] = {
-			.possible_crtcs = BIT(1) | BIT(0),
-			.encoder_type = DRM_MODE_ENCODER_NONE,
-		},
-	},
-	.num_lvds = 0,
-};
-
-static const struct rcar_du_device_info rcar_du_r8a7790_info = {
-	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK | RCAR_DU_FEATURE_DEFR8,
-	.quirks = RCAR_DU_QUIRK_ALIGN_128B | RCAR_DU_QUIRK_LVDS_LANES,
-	.num_crtcs = 3,
-	.routes = {
-		/* R8A7790 has one RGB output, two LVDS outputs and one
-		 * (currently unsupported) TCON output.
-		 */
-		[RCAR_DU_OUTPUT_DPAD0] = {
-			.possible_crtcs = BIT(2) | BIT(1) | BIT(0),
-			.encoder_type = DRM_MODE_ENCODER_NONE,
-		},
-		[RCAR_DU_OUTPUT_LVDS0] = {
-			.possible_crtcs = BIT(0),
-			.encoder_type = DRM_MODE_ENCODER_LVDS,
-		},
-		[RCAR_DU_OUTPUT_LVDS1] = {
-			.possible_crtcs = BIT(2) | BIT(1),
-			.encoder_type = DRM_MODE_ENCODER_LVDS,
-		},
-	},
-	.num_lvds = 2,
-};
-
-static const struct rcar_du_device_info rcar_du_r8a7791_info = {
-	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK | RCAR_DU_FEATURE_DEFR8,
-	.num_crtcs = 2,
-	.routes = {
-		/* R8A7791 has one RGB output, one LVDS output and one
-		 * (currently unsupported) TCON output.
-		 */
-		[RCAR_DU_OUTPUT_DPAD0] = {
-			.possible_crtcs = BIT(1),
-			.encoder_type = DRM_MODE_ENCODER_NONE,
-		},
-		[RCAR_DU_OUTPUT_LVDS0] = {
-			.possible_crtcs = BIT(0),
-			.encoder_type = DRM_MODE_ENCODER_LVDS,
-		},
-	},
-	.num_lvds = 1,
-};
-
-static const struct platform_device_id rcar_du_id_table[] = {
-	{ "rcar-du-r8a7779", (kernel_ulong_t)&rcar_du_r8a7779_info },
-	{ "rcar-du-r8a7790", (kernel_ulong_t)&rcar_du_r8a7790_info },
-	{ "rcar-du-r8a7791", (kernel_ulong_t)&rcar_du_r8a7791_info },
-	{ }
-};
-
-MODULE_DEVICE_TABLE(platform, rcar_du_id_table);
-
 static struct platform_driver rcar_du_platform_driver = {
 	.probe		= rcar_du_probe,
 	.remove		= rcar_du_remove,
@@ -309,6 +333,7 @@ static struct platform_driver rcar_du_platform_driver = {
 		.owner	= THIS_MODULE,
 		.name	= "rcar-du",
 		.pm	= &rcar_du_pm_ops,
+		.of_match_table = rcar_du_of_table,
 	},
 	.id_table	= rcar_du_id_table,
 };
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.h b/drivers/gpu/drm/rcar-du/rcar_du_drv.h
index e31b735d3f25..8e494633c3b3 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.h
@@ -1,7 +1,7 @@
 /*
  * rcar_du_drv.h  --  R-Car Display Unit DRM driver
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
@@ -37,6 +37,7 @@ struct rcar_du_lvdsenc;
  * struct rcar_du_output_routing - Output routing specification
  * @possible_crtcs: bitmask of possible CRTCs for the output
  * @encoder_type: DRM type of the internal encoder associated with the output
+ * @port: device tree port number corresponding to this output route
  *
  * The DU has 5 possible outputs (DPAD0/1, LVDS0/1, TCON). Output routing data
  * specify the valid SoC outputs, which CRTCs can drive the output, and the type
@@ -45,6 +46,7 @@ struct rcar_du_lvdsenc;
 struct rcar_du_output_routing {
 	unsigned int possible_crtcs;
 	unsigned int encoder_type;
+	unsigned int port;
 };
 
 /*
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
index 3daa7a168dc6..7c0ec95915ef 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c
@@ -1,7 +1,7 @@
 /*
  * rcar_du_encoder.c  --  R-Car Display Unit Encoder
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
@@ -142,7 +142,8 @@ static const struct drm_encoder_funcs encoder_funcs = {
 int rcar_du_encoder_init(struct rcar_du_device *rcdu,
 			 enum rcar_du_encoder_type type,
 			 enum rcar_du_output output,
-			 const struct rcar_du_encoder_data *data)
+			 const struct rcar_du_encoder_data *data,
+			 struct device_node *np)
 {
 	struct rcar_du_encoder *renc;
 	unsigned int encoder_type;
@@ -189,9 +190,11 @@ int rcar_du_encoder_init(struct rcar_du_device *rcdu,
 	drm_encoder_helper_add(&renc->encoder, &encoder_helper_funcs);
 
 	switch (encoder_type) {
-	case DRM_MODE_ENCODER_LVDS:
-		return rcar_du_lvds_connector_init(rcdu, renc,
-						   &data->connector.lvds.panel);
+	case DRM_MODE_ENCODER_LVDS: {
+		const struct rcar_du_panel_data *pdata =
+			data ? &data->connector.lvds.panel : NULL;
+		return rcar_du_lvds_connector_init(rcdu, renc, pdata, np);
+	}
 
 	case DRM_MODE_ENCODER_DAC:
 		return rcar_du_vga_connector_init(rcdu, renc);
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.h b/drivers/gpu/drm/rcar-du/rcar_du_encoder.h
index 0e5a65e45d0e..bd624135ef1f 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.h
@@ -1,7 +1,7 @@
 /*
  * rcar_du_encoder.h  --  R-Car Display Unit Encoder
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
@@ -44,6 +44,7 @@ rcar_du_connector_best_encoder(struct drm_connector *connector);
 int rcar_du_encoder_init(struct rcar_du_device *rcdu,
 			 enum rcar_du_encoder_type type,
 			 enum rcar_du_output output,
-			 const struct rcar_du_encoder_data *data);
+			 const struct rcar_du_encoder_data *data,
+			 struct device_node *np);
 
 #endif /* __RCAR_DU_ENCODER_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_group.c b/drivers/gpu/drm/rcar-du/rcar_du_group.c
index eb53cd97e8c6..4e7614b145db 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_group.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_group.c
@@ -1,7 +1,7 @@
 /*
  * rcar_du_group.c  --  R-Car Display Unit Channels Pair
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_group.h b/drivers/gpu/drm/rcar-du/rcar_du_group.h
index 5025930972ec..0c38cdcda4ca 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_group.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_group.h
@@ -1,7 +1,7 @@
 /*
  * rcar_du_group.c  --  R-Car Display Unit Planes and CRTCs Group
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index 76026104d000..6c24ad7d03ef 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -1,7 +1,7 @@
 /*
  * rcar_du_kms.c  --  R-Car Display Unit Mode Setting
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
@@ -17,6 +17,8 @@
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 
+#include <linux/of_graph.h>
+
 #include "rcar_du_crtc.h"
 #include "rcar_du_drv.h"
 #include "rcar_du_encoder.h"
@@ -188,6 +190,205 @@ static const struct drm_mode_config_funcs rcar_du_mode_config_funcs = {
 	.output_poll_changed = rcar_du_output_poll_changed,
 };
 
+static int rcar_du_encoders_init_pdata(struct rcar_du_device *rcdu)
+{
+	unsigned int num_encoders = 0;
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < rcdu->pdata->num_encoders; ++i) {
+		const struct rcar_du_encoder_data *pdata =
+			&rcdu->pdata->encoders[i];
+		const struct rcar_du_output_routing *route =
+			&rcdu->info->routes[pdata->output];
+
+		if (pdata->type == RCAR_DU_ENCODER_UNUSED)
+			continue;
+
+		if (pdata->output >= RCAR_DU_OUTPUT_MAX ||
+		    route->possible_crtcs == 0) {
+			dev_warn(rcdu->dev,
+				 "encoder %u references unexisting output %u, skipping\n",
+				 i, pdata->output);
+			continue;
+		}
+
+		ret = rcar_du_encoder_init(rcdu, pdata->type, pdata->output,
+					   pdata, NULL);
+		if (ret < 0)
+			return ret;
+
+		num_encoders++;
+	}
+
+	return num_encoders;
+}
+
+static int rcar_du_encoders_init_dt_one(struct rcar_du_device *rcdu,
+					enum rcar_du_output output,
+					struct of_endpoint *ep)
+{
+	static const struct {
+		const char *compatible;
+		enum rcar_du_encoder_type type;
+	} encoders[] = {
+		{ "adi,adv7123", RCAR_DU_ENCODER_VGA },
+		{ "thine,thc63lvdm83d", RCAR_DU_ENCODER_LVDS },
+	};
+
+	enum rcar_du_encoder_type enc_type = RCAR_DU_ENCODER_NONE;
+	struct device_node *connector = NULL;
+	struct device_node *encoder = NULL;
+	struct device_node *prev = NULL;
+	struct device_node *entity_ep_node;
+	struct device_node *entity;
+	int ret;
+
+	/*
+	 * Locate the connected entity and infer its type from the number of
+	 * endpoints.
+	 */
+	entity = of_graph_get_remote_port_parent(ep->local_node);
+	if (!entity) {
+		dev_dbg(rcdu->dev, "unconnected endpoint %s, skipping\n",
+			ep->local_node->full_name);
+		return 0;
+	}
+
+	entity_ep_node = of_parse_phandle(ep->local_node, "remote-endpoint", 0);
+
+	while (1) {
+		struct device_node *ep_node;
+
+		ep_node = of_graph_get_next_endpoint(entity, prev);
+		of_node_put(prev);
+		prev = ep_node;
+
+		if (!ep_node)
+			break;
+
+		if (ep_node == entity_ep_node)
+			continue;
+
+		/*
+		 * We've found one endpoint other than the input, this must
+		 * be an encoder. Locate the connector.
+		 */
+		encoder = entity;
+		connector = of_graph_get_remote_port_parent(ep_node);
+		of_node_put(ep_node);
+
+		if (!connector) {
+			dev_warn(rcdu->dev,
+				 "no connector for encoder %s, skipping\n",
+				 encoder->full_name);
+			of_node_put(entity_ep_node);
+			of_node_put(encoder);
+			return 0;
+		}
+
+		break;
+	}
+
+	of_node_put(entity_ep_node);
+
+	if (encoder) {
+		/*
+		 * If an encoder has been found, get its type based on its
+		 * compatible string.
+		 */
+		unsigned int i;
+
+		for (i = 0; i < ARRAY_SIZE(encoders); ++i) {
+			if (of_device_is_compatible(encoder,
+						    encoders[i].compatible)) {
+				enc_type = encoders[i].type;
+				break;
+			}
+		}
+
+		if (i == ARRAY_SIZE(encoders)) {
+			dev_warn(rcdu->dev,
+				 "unknown encoder type for %s, skipping\n",
+				 encoder->full_name);
+			of_node_put(encoder);
+			of_node_put(connector);
+			return 0;
+		}
+	} else {
+		/*
+		 * If no encoder has been found the entity must be the
+		 * connector.
+		 */
+		connector = entity;
+	}
+
+	ret = rcar_du_encoder_init(rcdu, enc_type, output, NULL, connector);
+	of_node_put(encoder);
+	of_node_put(connector);
+
+	return ret < 0 ? ret : 1;
+}
+
+static int rcar_du_encoders_init_dt(struct rcar_du_device *rcdu)
+{
+	struct device_node *np = rcdu->dev->of_node;
+	struct device_node *prev = NULL;
+	unsigned int num_encoders = 0;
+
+	/*
+	 * Iterate over the endpoints and create one encoder for each output
+	 * pipeline.
+	 */
+	while (1) {
+		struct device_node *ep_node;
+		enum rcar_du_output output;
+		struct of_endpoint ep;
+		unsigned int i;
+		int ret;
+
+		ep_node = of_graph_get_next_endpoint(np, prev);
+		of_node_put(prev);
+		prev = ep_node;
+
+		if (ep_node == NULL)
+			break;
+
+		ret = of_graph_parse_endpoint(ep_node, &ep);
+		if (ret < 0) {
+			of_node_put(ep_node);
+			return ret;
+		}
+
+		/* Find the output route corresponding to the port number. */
+		for (i = 0; i < RCAR_DU_OUTPUT_MAX; ++i) {
+			if (rcdu->info->routes[i].possible_crtcs &&
+			    rcdu->info->routes[i].port == ep.port) {
+				output = i;
+				break;
+			}
+		}
+
+		if (i == RCAR_DU_OUTPUT_MAX) {
+			dev_warn(rcdu->dev,
+				 "port %u references unexisting output, skipping\n",
+				 ep.port);
+			continue;
+		}
+
+		/* Process the output pipeline. */
+		ret = rcar_du_encoders_init_dt_one(rcdu, output, &ep);
+		if (ret < 0) {
+			of_node_put(ep_node);
+			return ret;
+		}
+
+		num_encoders += ret;
+	}
+
+	return num_encoders;
+}
+
 int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 {
 	static const unsigned int mmio_offsets[] = {
@@ -197,6 +398,7 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 	struct drm_device *dev = rcdu->ddev;
 	struct drm_encoder *encoder;
 	struct drm_fbdev_cma *fbdev;
+	unsigned int num_encoders;
 	unsigned int num_groups;
 	unsigned int i;
 	int ret;
@@ -240,28 +442,15 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 	if (ret < 0)
 		return ret;
 
-	for (i = 0; i < rcdu->pdata->num_encoders; ++i) {
-		const struct rcar_du_encoder_data *pdata =
-			&rcdu->pdata->encoders[i];
-		const struct rcar_du_output_routing *route =
-			&rcdu->info->routes[pdata->output];
-
-		if (pdata->type == RCAR_DU_ENCODER_UNUSED)
-			continue;
+	if (rcdu->pdata)
+		ret = rcar_du_encoders_init_pdata(rcdu);
+	else
+		ret = rcar_du_encoders_init_dt(rcdu);
 
-		if (pdata->output >= RCAR_DU_OUTPUT_MAX ||
-		    route->possible_crtcs == 0) {
-			dev_warn(rcdu->dev,
-				 "encoder %u references unexisting output %u, skipping\n",
-				 i, pdata->output);
-			continue;
-		}
+	if (ret < 0)
+		return ret;
 
-		ret = rcar_du_encoder_init(rcdu, pdata->type, pdata->output,
-					   pdata);
-		if (ret < 0)
-			return ret;
-	}
+	num_encoders = ret;
 
 	/* Set the possible CRTCs and possible clones. There's always at least
 	 * one way for all encoders to clone each other, set all bits in the
@@ -273,7 +462,7 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 			&rcdu->info->routes[renc->output];
 
 		encoder->possible_crtcs = route->possible_crtcs;
-		encoder->possible_clones = (1 << rcdu->pdata->num_encoders) - 1;
+		encoder->possible_clones = (1 << num_encoders) - 1;
 	}
 
 	/* Now that the CRTCs have been initialized register the planes. */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.h b/drivers/gpu/drm/rcar-du/rcar_du_kms.h
index 5750e6af5655..07951d5fe38b 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.h
@@ -1,7 +1,7 @@
 /*
  * rcar_du_kms.h  --  R-Car Display Unit Mode Setting
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
index 21426bd234eb..115eed20db12 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
@@ -1,7 +1,7 @@
 /*
  * rcar_du_lvdscon.c  --  R-Car Display Unit LVDS Connector
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
@@ -15,6 +15,10 @@
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
 
+#include <video/display_timing.h>
+#include <video/of_display_timing.h>
+#include <video/videomode.h>
+
 #include "rcar_du_drv.h"
 #include "rcar_du_encoder.h"
 #include "rcar_du_kms.h"
@@ -23,7 +27,7 @@
 struct rcar_du_lvds_connector {
 	struct rcar_du_connector connector;
 
-	const struct rcar_du_panel_data *panel;
+	struct rcar_du_panel_data panel;
 };
 
 #define to_rcar_lvds_connector(c) \
@@ -40,18 +44,9 @@ static int rcar_du_lvds_connector_get_modes(struct drm_connector *connector)
 		return 0;
 
 	mode->type = DRM_MODE_TYPE_PREFERRED | DRM_MODE_TYPE_DRIVER;
-	mode->clock = lvdscon->panel->mode.clock;
-	mode->hdisplay = lvdscon->panel->mode.hdisplay;
-	mode->hsync_start = lvdscon->panel->mode.hsync_start;
-	mode->hsync_end = lvdscon->panel->mode.hsync_end;
-	mode->htotal = lvdscon->panel->mode.htotal;
-	mode->vdisplay = lvdscon->panel->mode.vdisplay;
-	mode->vsync_start = lvdscon->panel->mode.vsync_start;
-	mode->vsync_end = lvdscon->panel->mode.vsync_end;
-	mode->vtotal = lvdscon->panel->mode.vtotal;
-	mode->flags = lvdscon->panel->mode.flags;
-
-	drm_mode_set_name(mode);
+
+	drm_display_mode_from_videomode(&lvdscon->panel.mode, mode);
+
 	drm_mode_probed_add(connector, mode);
 
 	return 1;
@@ -83,7 +78,8 @@ static const struct drm_connector_funcs connector_funcs = {
 
 int rcar_du_lvds_connector_init(struct rcar_du_device *rcdu,
 				struct rcar_du_encoder *renc,
-				const struct rcar_du_panel_data *panel)
+				const struct rcar_du_panel_data *panel,
+				/* TODO const */ struct device_node *np)
 {
 	struct rcar_du_lvds_connector *lvdscon;
 	struct drm_connector *connector;
@@ -93,11 +89,24 @@ int rcar_du_lvds_connector_init(struct rcar_du_device *rcdu,
 	if (lvdscon == NULL)
 		return -ENOMEM;
 
-	lvdscon->panel = panel;
+	if (panel) {
+		lvdscon->panel = *panel;
+	} else {
+		struct display_timing timing;
+
+		ret = of_get_display_timing(np, "panel-timing", &timing);
+		if (ret < 0)
+			return ret;
+
+		videomode_from_timing(&timing, &lvdscon->panel.mode);
+
+		of_property_read_u32(np, "width-mm", &lvdscon->panel.width_mm);
+		of_property_read_u32(np, "height-mm", &lvdscon->panel.height_mm);
+	}
 
 	connector = &lvdscon->connector.connector;
-	connector->display_info.width_mm = panel->width_mm;
-	connector->display_info.height_mm = panel->height_mm;
+	connector->display_info.width_mm = lvdscon->panel.width_mm;
+	connector->display_info.height_mm = lvdscon->panel.height_mm;
 
 	ret = drm_connector_init(rcdu->ddev, connector, &connector_funcs,
 				 DRM_MODE_CONNECTOR_LVDS);
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.h b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.h
index bff8683699ca..d11424d537f9 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.h
@@ -1,7 +1,7 @@
 /*
  * rcar_du_lvdscon.h  --  R-Car Display Unit LVDS Connector
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
@@ -20,6 +20,7 @@ struct rcar_du_panel_data;
 
 int rcar_du_lvds_connector_init(struct rcar_du_device *rcdu,
 				struct rcar_du_encoder *renc,
-				const struct rcar_du_panel_data *panel);
+				const struct rcar_du_panel_data *panel,
+				struct device_node *np);
 
 #endif /* __RCAR_DU_LVDSCON_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.c b/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.c
index df30a075d793..7cfb48ce1791 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.c
@@ -1,7 +1,7 @@
 /*
  * rcar_du_lvdsenc.c  --  R-Car Display Unit LVDS Encoder
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.h b/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.h
index 7051c6de19ae..3303a55cec79 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdsenc.h
@@ -1,7 +1,7 @@
 /*
  * rcar_du_lvdsenc.h  --  R-Car Display Unit LVDS Encoder
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
index 3fb69d9ae61b..72a7cb47bd9f 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
@@ -1,7 +1,7 @@
 /*
  * rcar_du_plane.c  --  R-Car Display Unit Planes
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.h b/drivers/gpu/drm/rcar-du/rcar_du_plane.h
index f94f9ce84998..3021288b1a89 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_plane.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.h
@@ -1,7 +1,7 @@
 /*
  * rcar_du_plane.h  --  R-Car Display Unit Planes
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
index 8af3944d31b9..564a723ede03 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
@@ -1,7 +1,7 @@
 /*
  * rcar_du_vgacon.c  --  R-Car Display Unit VGA Connector
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.h b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.h
index b12b0cf7f117..112f50316e01 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.h
@@ -1,7 +1,7 @@
 /*
  * rcar_du_vgacon.h  --  R-Car Display Unit VGA Connector
  *
- * Copyright (C) 2013 Renesas Corporation
+ * Copyright (C) 2013-2014 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/savage/savage_bci.c b/drivers/gpu/drm/savage/savage_bci.c
index c97cdc9ab239..d47dff95fe52 100644
--- a/drivers/gpu/drm/savage/savage_bci.c
+++ b/drivers/gpu/drm/savage/savage_bci.c
@@ -556,7 +556,7 @@ int savage_driver_load(struct drm_device *dev, unsigned long chipset)
 /*
  * Initialize mappings. On Savage4 and SavageIX the alignment
  * and size of the aperture is not suitable for automatic MTRR setup
- * in drm_addmap. Therefore we add them manually before the maps are
+ * in drm_legacy_addmap. Therefore we add them manually before the maps are
  * initialized, and tear them down on last close.
  */
 int savage_driver_firstopen(struct drm_device *dev)
@@ -624,19 +624,20 @@ int savage_driver_firstopen(struct drm_device *dev)
 		/* Automatic MTRR setup will do the right thing. */
 	}
 
-	ret = drm_addmap(dev, mmio_base, SAVAGE_MMIO_SIZE, _DRM_REGISTERS,
-			 _DRM_READ_ONLY, &dev_priv->mmio);
+	ret = drm_legacy_addmap(dev, mmio_base, SAVAGE_MMIO_SIZE,
+				_DRM_REGISTERS, _DRM_READ_ONLY,
+				&dev_priv->mmio);
 	if (ret)
 		return ret;
 
-	ret = drm_addmap(dev, fb_base, fb_size, _DRM_FRAME_BUFFER,
-			 _DRM_WRITE_COMBINING, &dev_priv->fb);
+	ret = drm_legacy_addmap(dev, fb_base, fb_size, _DRM_FRAME_BUFFER,
+				_DRM_WRITE_COMBINING, &dev_priv->fb);
 	if (ret)
 		return ret;
 
-	ret = drm_addmap(dev, aperture_base, SAVAGE_APERTURE_SIZE,
-			 _DRM_FRAME_BUFFER, _DRM_WRITE_COMBINING,
-			 &dev_priv->aperture);
+	ret = drm_legacy_addmap(dev, aperture_base, SAVAGE_APERTURE_SIZE,
+				_DRM_FRAME_BUFFER, _DRM_WRITE_COMBINING,
+				&dev_priv->aperture);
 	return ret;
 }
 
@@ -698,14 +699,14 @@ static int savage_do_init_bci(struct drm_device * dev, drm_savage_init_t * init)
 	dev_priv->texture_offset = init->texture_offset;
 	dev_priv->texture_size = init->texture_size;
 
-	dev_priv->sarea = drm_getsarea(dev);
+	dev_priv->sarea = drm_legacy_getsarea(dev);
 	if (!dev_priv->sarea) {
 		DRM_ERROR("could not find sarea!\n");
 		savage_do_cleanup_bci(dev);
 		return -EINVAL;
 	}
 	if (init->status_offset != 0) {
-		dev_priv->status = drm_core_findmap(dev, init->status_offset);
+		dev_priv->status = drm_legacy_findmap(dev, init->status_offset);
 		if (!dev_priv->status) {
 			DRM_ERROR("could not find shadow status region!\n");
 			savage_do_cleanup_bci(dev);
@@ -716,14 +717,14 @@ static int savage_do_init_bci(struct drm_device * dev, drm_savage_init_t * init)
 	}
 	if (dev_priv->dma_type == SAVAGE_DMA_AGP && init->buffers_offset) {
 		dev->agp_buffer_token = init->buffers_offset;
-		dev->agp_buffer_map = drm_core_findmap(dev,
+		dev->agp_buffer_map = drm_legacy_findmap(dev,
 						       init->buffers_offset);
 		if (!dev->agp_buffer_map) {
 			DRM_ERROR("could not find DMA buffer region!\n");
 			savage_do_cleanup_bci(dev);
 			return -EINVAL;
 		}
-		drm_core_ioremap(dev->agp_buffer_map, dev);
+		drm_legacy_ioremap(dev->agp_buffer_map, dev);
 		if (!dev->agp_buffer_map->handle) {
 			DRM_ERROR("failed to ioremap DMA buffer region!\n");
 			savage_do_cleanup_bci(dev);
@@ -732,7 +733,7 @@ static int savage_do_init_bci(struct drm_device * dev, drm_savage_init_t * init)
 	}
 	if (init->agp_textures_offset) {
 		dev_priv->agp_textures =
-		    drm_core_findmap(dev, init->agp_textures_offset);
+		    drm_legacy_findmap(dev, init->agp_textures_offset);
 		if (!dev_priv->agp_textures) {
 			DRM_ERROR("could not find agp texture region!\n");
 			savage_do_cleanup_bci(dev);
@@ -755,7 +756,7 @@ static int savage_do_init_bci(struct drm_device * dev, drm_savage_init_t * init)
 			savage_do_cleanup_bci(dev);
 			return -EINVAL;
 		}
-		dev_priv->cmd_dma = drm_core_findmap(dev, init->cmd_dma_offset);
+		dev_priv->cmd_dma = drm_legacy_findmap(dev, init->cmd_dma_offset);
 		if (!dev_priv->cmd_dma) {
 			DRM_ERROR("could not find command DMA region!\n");
 			savage_do_cleanup_bci(dev);
@@ -768,7 +769,7 @@ static int savage_do_init_bci(struct drm_device * dev, drm_savage_init_t * init)
 				savage_do_cleanup_bci(dev);
 				return -EINVAL;
 			}
-			drm_core_ioremap(dev_priv->cmd_dma, dev);
+			drm_legacy_ioremap(dev_priv->cmd_dma, dev);
 			if (!dev_priv->cmd_dma->handle) {
 				DRM_ERROR("failed to ioremap command "
 					  "DMA region!\n");
@@ -894,11 +895,11 @@ static int savage_do_cleanup_bci(struct drm_device * dev)
 	} else if (dev_priv->cmd_dma && dev_priv->cmd_dma->handle &&
 		   dev_priv->cmd_dma->type == _DRM_AGP &&
 		   dev_priv->dma_type == SAVAGE_DMA_AGP)
-		drm_core_ioremapfree(dev_priv->cmd_dma, dev);
+		drm_legacy_ioremapfree(dev_priv->cmd_dma, dev);
 
 	if (dev_priv->dma_type == SAVAGE_DMA_AGP &&
 	    dev->agp_buffer_map && dev->agp_buffer_map->handle) {
-		drm_core_ioremapfree(dev->agp_buffer_map, dev);
+		drm_legacy_ioremapfree(dev->agp_buffer_map, dev);
 		/* make sure the next instance (which may be running
 		 * in PCI mode) doesn't try to use an old
 		 * agp_buffer_map. */
@@ -1050,7 +1051,7 @@ void savage_reclaim_buffers(struct drm_device *dev, struct drm_file *file_priv)
 		return;
 
 	if (file_priv->master && file_priv->master->lock.hw_lock) {
-		drm_idlelock_take(&file_priv->master->lock);
+		drm_legacy_idlelock_take(&file_priv->master->lock);
 		release_idlelock = 1;
 	}
 
@@ -1069,7 +1070,7 @@ void savage_reclaim_buffers(struct drm_device *dev, struct drm_file *file_priv)
 	}
 
 	if (release_idlelock)
-		drm_idlelock_release(&file_priv->master->lock);
+		drm_legacy_idlelock_release(&file_priv->master->lock);
 }
 
 const struct drm_ioctl_desc savage_ioctls[] = {
diff --git a/drivers/gpu/drm/savage/savage_drv.c b/drivers/gpu/drm/savage/savage_drv.c
index 3c030216e888..21aed1febeb4 100644
--- a/drivers/gpu/drm/savage/savage_drv.c
+++ b/drivers/gpu/drm/savage/savage_drv.c
@@ -40,7 +40,7 @@ static const struct file_operations savage_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
@@ -57,6 +57,7 @@ static struct drm_driver driver = {
 	.preclose = savage_reclaim_buffers,
 	.lastclose = savage_driver_lastclose,
 	.unload = savage_driver_unload,
+	.set_busid = drm_pci_set_busid,
 	.ioctls = savage_ioctls,
 	.dma_ioctl = savage_bci_buffers,
 	.fops = &savage_driver_fops,
diff --git a/drivers/gpu/drm/savage/savage_drv.h b/drivers/gpu/drm/savage/savage_drv.h
index 335f8fcf1041..37b699571ad0 100644
--- a/drivers/gpu/drm/savage/savage_drv.h
+++ b/drivers/gpu/drm/savage/savage_drv.h
@@ -26,6 +26,8 @@
 #ifndef __SAVAGE_DRV_H__
 #define __SAVAGE_DRV_H__
 
+#include <drm/drm_legacy.h>
+
 #define DRIVER_AUTHOR	"Felix Kuehling"
 
 #define DRIVER_NAME	"savage"
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_backlight.c b/drivers/gpu/drm/shmobile/shmob_drm_backlight.c
index 463aee18f774..33dd41afea0e 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_backlight.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_backlight.c
@@ -1,7 +1,7 @@
 /*
  * shmob_drm_backlight.c  --  SH Mobile DRM Backlight
  *
- * Copyright (C) 2012 Renesas Corporation
+ * Copyright (C) 2012 Renesas Electronics Corporation
  *
  * Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_backlight.h b/drivers/gpu/drm/shmobile/shmob_drm_backlight.h
index 9477595d2ff3..bac719ecc301 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_backlight.h
+++ b/drivers/gpu/drm/shmobile/shmob_drm_backlight.h
@@ -1,7 +1,7 @@
 /*
  * shmob_drm_backlight.h  --  SH Mobile DRM Backlight
  *
- * Copyright (C) 2012 Renesas Corporation
+ * Copyright (C) 2012 Renesas Electronics Corporation
  *
  * Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
index 47875de89010..0ddce4d046d9 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
@@ -1,7 +1,7 @@
 /*
  * shmob_drm_crtc.c  --  SH Mobile DRM CRTCs
  *
- * Copyright (C) 2012 Renesas Corporation
+ * Copyright (C) 2012 Renesas Electronics Corporation
  *
  * Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_crtc.h b/drivers/gpu/drm/shmobile/shmob_drm_crtc.h
index e5bd109c4c38..eddad6dcc88a 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_crtc.h
+++ b/drivers/gpu/drm/shmobile/shmob_drm_crtc.h
@@ -1,7 +1,7 @@
 /*
  * shmob_drm_crtc.h  --  SH Mobile DRM CRTCs
  *
- * Copyright (C) 2012 Renesas Corporation
+ * Copyright (C) 2012 Renesas Electronics Corporation
  *
  * Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
index ff4ba483b602..e62cbde81e50 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_drv.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
@@ -1,7 +1,7 @@
 /*
  * shmob_drm_drv.c  --  SH Mobile DRM driver
  *
- * Copyright (C) 2012 Renesas Corporation
+ * Copyright (C) 2012 Renesas Electronics Corporation
  *
  * Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
@@ -267,6 +267,7 @@ static struct drm_driver shmob_drm_driver = {
 	.load			= shmob_drm_load,
 	.unload			= shmob_drm_unload,
 	.preclose		= shmob_drm_preclose,
+	.set_busid		= drm_platform_set_busid,
 	.irq_handler		= shmob_drm_irq,
 	.get_vblank_counter	= drm_vblank_count,
 	.enable_vblank		= shmob_drm_enable_vblank,
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_drv.h b/drivers/gpu/drm/shmobile/shmob_drm_drv.h
index 4d46b811b5a7..02ea315ba69a 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_drv.h
+++ b/drivers/gpu/drm/shmobile/shmob_drm_drv.h
@@ -1,7 +1,7 @@
 /*
  * shmob_drm.h  --  SH Mobile DRM driver
  *
- * Copyright (C) 2012 Renesas Corporation
+ * Copyright (C) 2012 Renesas Electronics Corporation
  *
  * Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_kms.c b/drivers/gpu/drm/shmobile/shmob_drm_kms.c
index fc0ef0ca7d04..aaf98ace4a90 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_kms.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_kms.c
@@ -1,7 +1,7 @@
 /*
  * shmob_drm_kms.c  --  SH Mobile DRM Mode Setting
  *
- * Copyright (C) 2012 Renesas Corporation
+ * Copyright (C) 2012 Renesas Electronics Corporation
  *
  * Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_kms.h b/drivers/gpu/drm/shmobile/shmob_drm_kms.h
index 9495c9111308..06d5b7caa026 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_kms.h
+++ b/drivers/gpu/drm/shmobile/shmob_drm_kms.h
@@ -1,7 +1,7 @@
 /*
  * shmob_drm_kms.h  --  SH Mobile DRM Mode Setting
  *
- * Copyright (C) 2012 Renesas Corporation
+ * Copyright (C) 2012 Renesas Electronics Corporation
  *
  * Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_plane.c b/drivers/gpu/drm/shmobile/shmob_drm_plane.c
index 060ae03e5f9b..1805bb23b113 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_plane.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_plane.c
@@ -1,7 +1,7 @@
 /*
  * shmob_drm_plane.c  --  SH Mobile DRM Planes
  *
- * Copyright (C) 2012 Renesas Corporation
+ * Copyright (C) 2012 Renesas Electronics Corporation
  *
  * Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_plane.h b/drivers/gpu/drm/shmobile/shmob_drm_plane.h
index 99623d05e3b0..a58cc1fc3240 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_plane.h
+++ b/drivers/gpu/drm/shmobile/shmob_drm_plane.h
@@ -1,7 +1,7 @@
 /*
  * shmob_drm_plane.h  --  SH Mobile DRM Planes
  *
- * Copyright (C) 2012 Renesas Corporation
+ * Copyright (C) 2012 Renesas Electronics Corporation
  *
  * Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_regs.h b/drivers/gpu/drm/shmobile/shmob_drm_regs.h
index 7923cdd6368e..ea17d4415b9e 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_regs.h
+++ b/drivers/gpu/drm/shmobile/shmob_drm_regs.h
@@ -1,7 +1,7 @@
 /*
  * shmob_drm_regs.h  --  SH Mobile DRM registers
  *
- * Copyright (C) 2012 Renesas Corporation
+ * Copyright (C) 2012 Renesas Electronics Corporation
  *
  * Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  *
diff --git a/drivers/gpu/drm/sis/sis_drv.c b/drivers/gpu/drm/sis/sis_drv.c
index 756f787b7143..79bce76cb8f7 100644
--- a/drivers/gpu/drm/sis/sis_drv.c
+++ b/drivers/gpu/drm/sis/sis_drv.c
@@ -70,7 +70,7 @@ static const struct file_operations sis_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
@@ -108,6 +108,7 @@ static struct drm_driver driver = {
 	.open = sis_driver_open,
 	.preclose = sis_reclaim_buffers_locked,
 	.postclose = sis_driver_postclose,
+	.set_busid = drm_pci_set_busid,
 	.dma_quiescent = sis_idle,
 	.lastclose = sis_lastclose,
 	.ioctls = sis_ioctls,
diff --git a/drivers/gpu/drm/sis/sis_drv.h b/drivers/gpu/drm/sis/sis_drv.h
index c31c0253054d..16f972b2a76a 100644
--- a/drivers/gpu/drm/sis/sis_drv.h
+++ b/drivers/gpu/drm/sis/sis_drv.h
@@ -28,6 +28,8 @@
 #ifndef _SIS_DRV_H_
 #define _SIS_DRV_H_
 
+#include <drm/drm_legacy.h>
+
 /* General customization:
  */
 
diff --git a/drivers/gpu/drm/sis/sis_mm.c b/drivers/gpu/drm/sis/sis_mm.c
index 77f288e4a0a6..93ad8a5704d1 100644
--- a/drivers/gpu/drm/sis/sis_mm.c
+++ b/drivers/gpu/drm/sis/sis_mm.c
@@ -319,12 +319,12 @@ void sis_reclaim_buffers_locked(struct drm_device *dev,
 	if (!(file->minor->master && file->master->lock.hw_lock))
 		return;
 
-	drm_idlelock_take(&file->master->lock);
+	drm_legacy_idlelock_take(&file->master->lock);
 
 	mutex_lock(&dev->struct_mutex);
 	if (list_empty(&file_priv->obj_list)) {
 		mutex_unlock(&dev->struct_mutex);
-		drm_idlelock_release(&file->master->lock);
+		drm_legacy_idlelock_release(&file->master->lock);
 
 		return;
 	}
@@ -345,7 +345,7 @@ void sis_reclaim_buffers_locked(struct drm_device *dev,
 	}
 	mutex_unlock(&dev->struct_mutex);
 
-	drm_idlelock_release(&file->master->lock);
+	drm_legacy_idlelock_release(&file->master->lock);
 
 	return;
 }
diff --git a/drivers/gpu/drm/sti/sti_vtac.c b/drivers/gpu/drm/sti/sti_vtac.c
index 82a51d488434..97bcdac23ae1 100644
--- a/drivers/gpu/drm/sti/sti_vtac.c
+++ b/drivers/gpu/drm/sti/sti_vtac.c
@@ -56,8 +56,16 @@ struct sti_vtac_mode {
 	u32 phyts_per_pixel;
 };
 
-static const struct sti_vtac_mode vtac_mode_main = {0x2, 0x2, VTAC_5_PPP};
-static const struct sti_vtac_mode vtac_mode_aux = {0x1, 0x0, VTAC_17_PPP};
+static const struct sti_vtac_mode vtac_mode_main = {
+	.vid_in_width = 0x2,
+	.phyts_width = 0x2,
+	.phyts_per_pixel = VTAC_5_PPP,
+};
+static const struct sti_vtac_mode vtac_mode_aux = {
+	.vid_in_width = 0x1,
+	.phyts_width = 0x0,
+	.phyts_per_pixel = VTAC_17_PPP,
+};
 
 /**
  * VTAC structure
diff --git a/drivers/gpu/drm/tdfx/tdfx_drv.c b/drivers/gpu/drm/tdfx/tdfx_drv.c
index 3492ca5c46d3..fab5ebcb0fef 100644
--- a/drivers/gpu/drm/tdfx/tdfx_drv.c
+++ b/drivers/gpu/drm/tdfx/tdfx_drv.c
@@ -36,6 +36,7 @@
 #include "tdfx_drv.h"
 
 #include <drm/drm_pciids.h>
+#include <drm/drm_legacy.h>
 
 static struct pci_device_id pciidlist[] = {
 	tdfx_PCI_IDS
@@ -46,7 +47,7 @@ static const struct file_operations tdfx_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
@@ -55,6 +56,7 @@ static const struct file_operations tdfx_driver_fops = {
 };
 
 static struct drm_driver driver = {
+	.set_busid = drm_pci_set_busid,
 	.fops = &tdfx_driver_fops,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c
index 708f783ead47..d6b55e3e3716 100644
--- a/drivers/gpu/drm/tegra/dpaux.c
+++ b/drivers/gpu/drm/tegra/dpaux.c
@@ -533,9 +533,9 @@ int tegra_dpaux_train(struct tegra_dpaux *dpaux, struct drm_dp_link *link,
 
 	for (i = 0; i < link->num_lanes; i++)
 		values[i] = DP_TRAIN_MAX_PRE_EMPHASIS_REACHED |
-			    DP_TRAIN_PRE_EMPHASIS_0 |
+			    DP_TRAIN_PRE_EMPH_LEVEL_0 |
 			    DP_TRAIN_MAX_SWING_REACHED |
-			    DP_TRAIN_VOLTAGE_SWING_400;
+			    DP_TRAIN_VOLTAGE_SWING_LEVEL_0;
 
 	err = drm_dp_dpcd_write(&dpaux->aux, DP_TRAINING_LANE0_SET, values,
 				link->num_lanes);
diff --git a/drivers/gpu/drm/tegra/gem.h b/drivers/gpu/drm/tegra/gem.h
index 43a25c853357..6538b56780c2 100644
--- a/drivers/gpu/drm/tegra/gem.h
+++ b/drivers/gpu/drm/tegra/gem.h
@@ -15,6 +15,7 @@
 
 #include <drm/drm.h>
 #include <drm/drmP.h>
+#include <drm/drm_gem.h>
 
 #define TEGRA_BO_BOTTOM_UP (1 << 0)
 
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index 6be623b4a86f..79a34cbd29f5 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -84,6 +84,7 @@ static int modeset_init(struct drm_device *dev)
 	if ((priv->num_encoders == 0) || (priv->num_connectors == 0)) {
 		/* oh nos! */
 		dev_err(dev->dev, "no encoders/connectors found\n");
+		drm_mode_config_cleanup(dev);
 		return -ENXIO;
 	}
 
@@ -172,33 +173,37 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	dev->dev_private = priv;
 
 	priv->wq = alloc_ordered_workqueue("tilcdc", 0);
+	if (!priv->wq) {
+		ret = -ENOMEM;
+		goto fail_free_priv;
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		dev_err(dev->dev, "failed to get memory resource\n");
 		ret = -EINVAL;
-		goto fail;
+		goto fail_free_wq;
 	}
 
 	priv->mmio = ioremap_nocache(res->start, resource_size(res));
 	if (!priv->mmio) {
 		dev_err(dev->dev, "failed to ioremap\n");
 		ret = -ENOMEM;
-		goto fail;
+		goto fail_free_wq;
 	}
 
 	priv->clk = clk_get(dev->dev, "fck");
 	if (IS_ERR(priv->clk)) {
 		dev_err(dev->dev, "failed to get functional clock\n");
 		ret = -ENODEV;
-		goto fail;
+		goto fail_iounmap;
 	}
 
 	priv->disp_clk = clk_get(dev->dev, "dpll_disp_ck");
 	if (IS_ERR(priv->clk)) {
 		dev_err(dev->dev, "failed to get display clock\n");
 		ret = -ENODEV;
-		goto fail;
+		goto fail_put_clk;
 	}
 
 #ifdef CONFIG_CPU_FREQ
@@ -208,7 +213,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 			CPUFREQ_TRANSITION_NOTIFIER);
 	if (ret) {
 		dev_err(dev->dev, "failed to register cpufreq notifier\n");
-		goto fail;
+		goto fail_put_disp_clk;
 	}
 #endif
 
@@ -253,13 +258,13 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	ret = modeset_init(dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to initialize mode setting\n");
-		goto fail;
+		goto fail_cpufreq_unregister;
 	}
 
 	ret = drm_vblank_init(dev, 1);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to initialize vblank\n");
-		goto fail;
+		goto fail_mode_config_cleanup;
 	}
 
 	pm_runtime_get_sync(dev->dev);
@@ -267,7 +272,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	pm_runtime_put_sync(dev->dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to install IRQ handler\n");
-		goto fail;
+		goto fail_vblank_cleanup;
 	}
 
 	platform_set_drvdata(pdev, dev);
@@ -283,13 +288,48 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	priv->fbdev = drm_fbdev_cma_init(dev, bpp,
 			dev->mode_config.num_crtc,
 			dev->mode_config.num_connector);
+	if (IS_ERR(priv->fbdev)) {
+		ret = PTR_ERR(priv->fbdev);
+		goto fail_irq_uninstall;
+	}
 
 	drm_kms_helper_poll_init(dev);
 
 	return 0;
 
-fail:
-	tilcdc_unload(dev);
+fail_irq_uninstall:
+	pm_runtime_get_sync(dev->dev);
+	drm_irq_uninstall(dev);
+	pm_runtime_put_sync(dev->dev);
+
+fail_vblank_cleanup:
+	drm_vblank_cleanup(dev);
+
+fail_mode_config_cleanup:
+	drm_mode_config_cleanup(dev);
+
+fail_cpufreq_unregister:
+	pm_runtime_disable(dev->dev);
+#ifdef CONFIG_CPU_FREQ
+	cpufreq_unregister_notifier(&priv->freq_transition,
+			CPUFREQ_TRANSITION_NOTIFIER);
+fail_put_disp_clk:
+	clk_put(priv->disp_clk);
+#endif
+
+fail_put_clk:
+	clk_put(priv->clk);
+
+fail_iounmap:
+	iounmap(priv->mmio);
+
+fail_free_wq:
+	flush_workqueue(priv->wq);
+	destroy_workqueue(priv->wq);
+
+fail_free_priv:
+	dev->dev_private = NULL;
+	kfree(priv);
 	return ret;
 }
 
@@ -502,6 +542,7 @@ static struct drm_driver tilcdc_driver = {
 	.unload             = tilcdc_unload,
 	.preclose           = tilcdc_preclose,
 	.lastclose          = tilcdc_lastclose,
+	.set_busid          = drm_platform_set_busid,
 	.irq_handler        = tilcdc_irq,
 	.irq_preinstall     = tilcdc_irq_preinstall,
 	.irq_postinstall    = tilcdc_irq_postinstall,
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
index 4c7aa1d8134f..7a0315855e90 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
@@ -18,6 +18,7 @@
 #include <linux/pinctrl/pinmux.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/backlight.h>
+#include <linux/gpio/consumer.h>
 #include <video/display_timing.h>
 #include <video/of_display_timing.h>
 #include <video/videomode.h>
@@ -29,6 +30,7 @@ struct panel_module {
 	struct tilcdc_panel_info *info;
 	struct display_timings *timings;
 	struct backlight_device *backlight;
+	struct gpio_desc *enable_gpio;
 };
 #define to_panel_module(x) container_of(x, struct panel_module, base)
 
@@ -55,13 +57,17 @@ static void panel_encoder_dpms(struct drm_encoder *encoder, int mode)
 {
 	struct panel_encoder *panel_encoder = to_panel_encoder(encoder);
 	struct backlight_device *backlight = panel_encoder->mod->backlight;
+	struct gpio_desc *gpio = panel_encoder->mod->enable_gpio;
 
-	if (!backlight)
-		return;
+	if (backlight) {
+		backlight->props.power = mode == DRM_MODE_DPMS_ON ?
+					 FB_BLANK_UNBLANK : FB_BLANK_POWERDOWN;
+		backlight_update_status(backlight);
+	}
 
-	backlight->props.power = mode == DRM_MODE_DPMS_ON
-				     ? FB_BLANK_UNBLANK : FB_BLANK_POWERDOWN;
-	backlight_update_status(backlight);
+	if (gpio)
+		gpiod_set_value_cansleep(gpio,
+					 mode == DRM_MODE_DPMS_ON ? 1 : 0);
 }
 
 static bool panel_encoder_mode_fixup(struct drm_encoder *encoder,
@@ -311,6 +317,7 @@ static struct tilcdc_panel_info *of_get_panel_info(struct device_node *np)
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info) {
 		pr_err("%s: allocation failed\n", __func__);
+		of_node_put(info_np);
 		return NULL;
 	}
 
@@ -331,22 +338,21 @@ static struct tilcdc_panel_info *of_get_panel_info(struct device_node *np)
 	if (ret) {
 		pr_err("%s: error reading panel-info properties\n", __func__);
 		kfree(info);
+		of_node_put(info_np);
 		return NULL;
 	}
+	of_node_put(info_np);
 
 	return info;
 }
 
-static struct of_device_id panel_of_match[];
-
 static int panel_probe(struct platform_device *pdev)
 {
-	struct device_node *node = pdev->dev.of_node;
+	struct device_node *bl_node, *node = pdev->dev.of_node;
 	struct panel_module *panel_mod;
 	struct tilcdc_module *mod;
 	struct pinctrl *pinctrl;
-	int ret = -EINVAL;
-
+	int ret;
 
 	/* bail out early if no DT data: */
 	if (!node) {
@@ -354,10 +360,40 @@ static int panel_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	panel_mod = kzalloc(sizeof(*panel_mod), GFP_KERNEL);
+	panel_mod = devm_kzalloc(&pdev->dev, sizeof(*panel_mod), GFP_KERNEL);
 	if (!panel_mod)
 		return -ENOMEM;
 
+	bl_node = of_parse_phandle(node, "backlight", 0);
+	if (bl_node) {
+		panel_mod->backlight = of_find_backlight_by_node(bl_node);
+		of_node_put(bl_node);
+
+		if (!panel_mod->backlight)
+			return -EPROBE_DEFER;
+
+		dev_info(&pdev->dev, "found backlight\n");
+	}
+
+	panel_mod->enable_gpio = devm_gpiod_get(&pdev->dev, "enable");
+	if (IS_ERR(panel_mod->enable_gpio)) {
+		ret = PTR_ERR(panel_mod->enable_gpio);
+		if (ret != -ENOENT) {
+			dev_err(&pdev->dev, "failed to request enable GPIO\n");
+			goto fail_backlight;
+		}
+
+		/* Optional GPIO is not here, continue silently. */
+		panel_mod->enable_gpio = NULL;
+	} else {
+		ret = gpiod_direction_output(panel_mod->enable_gpio, 0);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "failed to setup GPIO\n");
+			goto fail_backlight;
+		}
+		dev_info(&pdev->dev, "found enable GPIO\n");
+	}
+
 	mod = &panel_mod->base;
 	pdev->dev.platform_data = mod;
 
@@ -370,29 +406,30 @@ static int panel_probe(struct platform_device *pdev)
 	panel_mod->timings = of_get_display_timings(node);
 	if (!panel_mod->timings) {
 		dev_err(&pdev->dev, "could not get panel timings\n");
+		ret = -EINVAL;
 		goto fail_free;
 	}
 
 	panel_mod->info = of_get_panel_info(node);
 	if (!panel_mod->info) {
 		dev_err(&pdev->dev, "could not get panel info\n");
+		ret = -EINVAL;
 		goto fail_timings;
 	}
 
 	mod->preferred_bpp = panel_mod->info->bpp;
 
-	panel_mod->backlight = of_find_backlight_by_node(node);
-	if (panel_mod->backlight)
-		dev_info(&pdev->dev, "found backlight\n");
-
 	return 0;
 
 fail_timings:
 	display_timings_release(panel_mod->timings);
 
 fail_free:
-	kfree(panel_mod);
 	tilcdc_module_cleanup(mod);
+
+fail_backlight:
+	if (panel_mod->backlight)
+		put_device(&panel_mod->backlight->dev);
 	return ret;
 }
 
@@ -400,12 +437,15 @@ static int panel_remove(struct platform_device *pdev)
 {
 	struct tilcdc_module *mod = dev_get_platdata(&pdev->dev);
 	struct panel_module *panel_mod = to_panel_module(mod);
+	struct backlight_device *backlight = panel_mod->backlight;
+
+	if (backlight)
+		put_device(&backlight->dev);
 
 	display_timings_release(panel_mod->timings);
 
 	tilcdc_module_cleanup(mod);
 	kfree(panel_mod->info);
-	kfree(panel_mod);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 3da89d5dab60..8f5cec67c47d 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -40,6 +40,7 @@
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/atomic.h>
+#include <linux/reservation.h>
 
 #define TTM_ASSERT_LOCKED(param)
 #define TTM_DEBUG(fmt, arg...)
@@ -53,12 +54,13 @@ static struct attribute ttm_bo_count = {
 	.mode = S_IRUGO
 };
 
-static inline int ttm_mem_type_from_flags(uint32_t flags, uint32_t *mem_type)
+static inline int ttm_mem_type_from_place(const struct ttm_place *place,
+					  uint32_t *mem_type)
 {
 	int i;
 
 	for (i = 0; i <= TTM_PL_PRIV5; i++)
-		if (flags & (1 << i)) {
+		if (place->flags & (1 << i)) {
 			*mem_type = i;
 			return 0;
 		}
@@ -89,12 +91,12 @@ static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo,
 	       bo, bo->mem.num_pages, bo->mem.size >> 10,
 	       bo->mem.size >> 20);
 	for (i = 0; i < placement->num_placement; i++) {
-		ret = ttm_mem_type_from_flags(placement->placement[i],
+		ret = ttm_mem_type_from_place(&placement->placement[i],
 						&mem_type);
 		if (ret)
 			return;
 		pr_err("  placement[%d]=0x%08X (%d)\n",
-		       i, placement->placement[i], mem_type);
+		       i, placement->placement[i].flags, mem_type);
 		ttm_mem_type_debug(bo->bdev, mem_type);
 	}
 }
@@ -141,7 +143,6 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	BUG_ON(atomic_read(&bo->list_kref.refcount));
 	BUG_ON(atomic_read(&bo->kref.refcount));
 	BUG_ON(atomic_read(&bo->cpu_writers));
-	BUG_ON(bo->sync_obj != NULL);
 	BUG_ON(bo->mem.mm_node != NULL);
 	BUG_ON(!list_empty(&bo->lru));
 	BUG_ON(!list_empty(&bo->ddestroy));
@@ -402,36 +403,48 @@ static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo)
 	ww_mutex_unlock (&bo->resv->lock);
 }
 
+static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo)
+{
+	struct reservation_object_list *fobj;
+	struct fence *fence;
+	int i;
+
+	fobj = reservation_object_get_list(bo->resv);
+	fence = reservation_object_get_excl(bo->resv);
+	if (fence && !fence->ops->signaled)
+		fence_enable_sw_signaling(fence);
+
+	for (i = 0; fobj && i < fobj->shared_count; ++i) {
+		fence = rcu_dereference_protected(fobj->shared[i],
+					reservation_object_held(bo->resv));
+
+		if (!fence->ops->signaled)
+			fence_enable_sw_signaling(fence);
+	}
+}
+
 static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_bo_global *glob = bo->glob;
-	struct ttm_bo_driver *driver = bdev->driver;
-	void *sync_obj = NULL;
 	int put_count;
 	int ret;
 
 	spin_lock(&glob->lru_lock);
 	ret = __ttm_bo_reserve(bo, false, true, false, NULL);
 
-	spin_lock(&bdev->fence_lock);
-	(void) ttm_bo_wait(bo, false, false, true);
-	if (!ret && !bo->sync_obj) {
-		spin_unlock(&bdev->fence_lock);
-		put_count = ttm_bo_del_from_lru(bo);
-
-		spin_unlock(&glob->lru_lock);
-		ttm_bo_cleanup_memtype_use(bo);
+	if (!ret) {
+		if (!ttm_bo_wait(bo, false, false, true)) {
+			put_count = ttm_bo_del_from_lru(bo);
 
-		ttm_bo_list_ref_sub(bo, put_count, true);
+			spin_unlock(&glob->lru_lock);
+			ttm_bo_cleanup_memtype_use(bo);
 
-		return;
-	}
-	if (bo->sync_obj)
-		sync_obj = driver->sync_obj_ref(bo->sync_obj);
-	spin_unlock(&bdev->fence_lock);
+			ttm_bo_list_ref_sub(bo, put_count, true);
 
-	if (!ret) {
+			return;
+		} else
+			ttm_bo_flush_all_fences(bo);
 
 		/*
 		 * Make NO_EVICT bos immediately available to
@@ -450,10 +463,6 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 	list_add_tail(&bo->ddestroy, &bdev->ddestroy);
 	spin_unlock(&glob->lru_lock);
 
-	if (sync_obj) {
-		driver->sync_obj_flush(sync_obj);
-		driver->sync_obj_unref(&sync_obj);
-	}
 	schedule_delayed_work(&bdev->wq,
 			      ((HZ / 100) < 1) ? 1 : HZ / 100);
 }
@@ -474,44 +483,26 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 					  bool interruptible,
 					  bool no_wait_gpu)
 {
-	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_bo_driver *driver = bdev->driver;
 	struct ttm_bo_global *glob = bo->glob;
 	int put_count;
 	int ret;
 
-	spin_lock(&bdev->fence_lock);
 	ret = ttm_bo_wait(bo, false, false, true);
 
 	if (ret && !no_wait_gpu) {
-		void *sync_obj;
-
-		/*
-		 * Take a reference to the fence and unreserve,
-		 * at this point the buffer should be dead, so
-		 * no new sync objects can be attached.
-		 */
-		sync_obj = driver->sync_obj_ref(bo->sync_obj);
-		spin_unlock(&bdev->fence_lock);
-
-		__ttm_bo_unreserve(bo);
+		long lret;
+		ww_mutex_unlock(&bo->resv->lock);
 		spin_unlock(&glob->lru_lock);
 
-		ret = driver->sync_obj_wait(sync_obj, false, interruptible);
-		driver->sync_obj_unref(&sync_obj);
-		if (ret)
-			return ret;
+		lret = reservation_object_wait_timeout_rcu(bo->resv,
+							   true,
+							   interruptible,
+							   30 * HZ);
 
-		/*
-		 * remove sync_obj with ttm_bo_wait, the wait should be
-		 * finished, and no new wait object should have been added.
-		 */
-		spin_lock(&bdev->fence_lock);
-		ret = ttm_bo_wait(bo, false, false, true);
-		WARN_ON(ret);
-		spin_unlock(&bdev->fence_lock);
-		if (ret)
-			return ret;
+		if (lret < 0)
+			return lret;
+		else if (lret == 0)
+			return -EBUSY;
 
 		spin_lock(&glob->lru_lock);
 		ret = __ttm_bo_reserve(bo, false, true, false, NULL);
@@ -528,8 +519,14 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 			spin_unlock(&glob->lru_lock);
 			return 0;
 		}
-	} else
-		spin_unlock(&bdev->fence_lock);
+
+		/*
+		 * remove sync_obj with ttm_bo_wait, the wait should be
+		 * finished, and no new wait object should have been added.
+		 */
+		ret = ttm_bo_wait(bo, false, false, true);
+		WARN_ON(ret);
+	}
 
 	if (ret || unlikely(list_empty(&bo->ddestroy))) {
 		__ttm_bo_unreserve(bo);
@@ -667,9 +664,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	struct ttm_placement placement;
 	int ret = 0;
 
-	spin_lock(&bdev->fence_lock);
 	ret = ttm_bo_wait(bo, false, interruptible, no_wait_gpu);
-	spin_unlock(&bdev->fence_lock);
 
 	if (unlikely(ret != 0)) {
 		if (ret != -ERESTARTSYS) {
@@ -685,8 +680,6 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible,
 	evict_mem.bus.io_reserved_vm = false;
 	evict_mem.bus.io_reserved_count = 0;
 
-	placement.fpfn = 0;
-	placement.lpfn = 0;
 	placement.num_placement = 0;
 	placement.num_busy_placement = 0;
 	bdev->driver->evict_flags(bo, &placement);
@@ -774,7 +767,7 @@ EXPORT_SYMBOL(ttm_bo_mem_put);
  */
 static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 					uint32_t mem_type,
-					struct ttm_placement *placement,
+					const struct ttm_place *place,
 					struct ttm_mem_reg *mem,
 					bool interruptible,
 					bool no_wait_gpu)
@@ -784,7 +777,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 	int ret;
 
 	do {
-		ret = (*man->func->get_node)(man, bo, placement, 0, mem);
+		ret = (*man->func->get_node)(man, bo, place, mem);
 		if (unlikely(ret != 0))
 			return ret;
 		if (mem->mm_node)
@@ -827,18 +820,18 @@ static uint32_t ttm_bo_select_caching(struct ttm_mem_type_manager *man,
 
 static bool ttm_bo_mt_compatible(struct ttm_mem_type_manager *man,
 				 uint32_t mem_type,
-				 uint32_t proposed_placement,
+				 const struct ttm_place *place,
 				 uint32_t *masked_placement)
 {
 	uint32_t cur_flags = ttm_bo_type_flags(mem_type);
 
-	if ((cur_flags & proposed_placement & TTM_PL_MASK_MEM) == 0)
+	if ((cur_flags & place->flags & TTM_PL_MASK_MEM) == 0)
 		return false;
 
-	if ((proposed_placement & man->available_caching) == 0)
+	if ((place->flags & man->available_caching) == 0)
 		return false;
 
-	cur_flags |= (proposed_placement & man->available_caching);
+	cur_flags |= (place->flags & man->available_caching);
 
 	*masked_placement = cur_flags;
 	return true;
@@ -869,15 +862,14 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 
 	mem->mm_node = NULL;
 	for (i = 0; i < placement->num_placement; ++i) {
-		ret = ttm_mem_type_from_flags(placement->placement[i],
-						&mem_type);
+		const struct ttm_place *place = &placement->placement[i];
+
+		ret = ttm_mem_type_from_place(place, &mem_type);
 		if (ret)
 			return ret;
 		man = &bdev->man[mem_type];
 
-		type_ok = ttm_bo_mt_compatible(man,
-						mem_type,
-						placement->placement[i],
+		type_ok = ttm_bo_mt_compatible(man, mem_type, place,
 						&cur_flags);
 
 		if (!type_ok)
@@ -889,7 +881,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		 * Use the access and other non-mapping-related flag bits from
 		 * the memory placement flags to the current flags
 		 */
-		ttm_flag_masked(&cur_flags, placement->placement[i],
+		ttm_flag_masked(&cur_flags, place->flags,
 				~TTM_PL_MASK_MEMTYPE);
 
 		if (mem_type == TTM_PL_SYSTEM)
@@ -897,8 +889,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 
 		if (man->has_type && man->use_type) {
 			type_found = true;
-			ret = (*man->func->get_node)(man, bo, placement,
-						     cur_flags, mem);
+			ret = (*man->func->get_node)(man, bo, place, mem);
 			if (unlikely(ret))
 				return ret;
 		}
@@ -916,17 +907,15 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		return -EINVAL;
 
 	for (i = 0; i < placement->num_busy_placement; ++i) {
-		ret = ttm_mem_type_from_flags(placement->busy_placement[i],
-						&mem_type);
+		const struct ttm_place *place = &placement->busy_placement[i];
+
+		ret = ttm_mem_type_from_place(place, &mem_type);
 		if (ret)
 			return ret;
 		man = &bdev->man[mem_type];
 		if (!man->has_type)
 			continue;
-		if (!ttm_bo_mt_compatible(man,
-						mem_type,
-						placement->busy_placement[i],
-						&cur_flags))
+		if (!ttm_bo_mt_compatible(man, mem_type, place, &cur_flags))
 			continue;
 
 		cur_flags = ttm_bo_select_caching(man, bo->mem.placement,
@@ -935,7 +924,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		 * Use the access and other non-mapping-related flag bits from
 		 * the memory placement flags to the current flags
 		 */
-		ttm_flag_masked(&cur_flags, placement->busy_placement[i],
+		ttm_flag_masked(&cur_flags, place->flags,
 				~TTM_PL_MASK_MEMTYPE);
 
 		if (mem_type == TTM_PL_SYSTEM) {
@@ -945,7 +934,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 			return 0;
 		}
 
-		ret = ttm_bo_mem_force_space(bo, mem_type, placement, mem,
+		ret = ttm_bo_mem_force_space(bo, mem_type, place, mem,
 						interruptible, no_wait_gpu);
 		if (ret == 0 && mem->mm_node) {
 			mem->placement = cur_flags;
@@ -966,7 +955,6 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 {
 	int ret = 0;
 	struct ttm_mem_reg mem;
-	struct ttm_bo_device *bdev = bo->bdev;
 
 	lockdep_assert_held(&bo->resv->lock.base);
 
@@ -975,9 +963,7 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 	 * Have the driver move function wait for idle when necessary,
 	 * instead of doing it here.
 	 */
-	spin_lock(&bdev->fence_lock);
 	ret = ttm_bo_wait(bo, false, interruptible, no_wait_gpu);
-	spin_unlock(&bdev->fence_lock);
 	if (ret)
 		return ret;
 	mem.num_pages = bo->num_pages;
@@ -1006,20 +992,27 @@ static bool ttm_bo_mem_compat(struct ttm_placement *placement,
 {
 	int i;
 
-	if (mem->mm_node && placement->lpfn != 0 &&
-	    (mem->start < placement->fpfn ||
-	     mem->start + mem->num_pages > placement->lpfn))
-		return false;
-
 	for (i = 0; i < placement->num_placement; i++) {
-		*new_flags = placement->placement[i];
+		const struct ttm_place *heap = &placement->placement[i];
+		if (mem->mm_node && heap->lpfn != 0 &&
+		    (mem->start < heap->fpfn ||
+		     mem->start + mem->num_pages > heap->lpfn))
+			continue;
+
+		*new_flags = heap->flags;
 		if ((*new_flags & mem->placement & TTM_PL_MASK_CACHING) &&
 		    (*new_flags & mem->placement & TTM_PL_MASK_MEM))
 			return true;
 	}
 
 	for (i = 0; i < placement->num_busy_placement; i++) {
-		*new_flags = placement->busy_placement[i];
+		const struct ttm_place *heap = &placement->busy_placement[i];
+		if (mem->mm_node && heap->lpfn != 0 &&
+		    (mem->start < heap->fpfn ||
+		     mem->start + mem->num_pages > heap->lpfn))
+			continue;
+
+		*new_flags = heap->flags;
 		if ((*new_flags & mem->placement & TTM_PL_MASK_CACHING) &&
 		    (*new_flags & mem->placement & TTM_PL_MASK_MEM))
 			return true;
@@ -1037,11 +1030,6 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 	uint32_t new_flags;
 
 	lockdep_assert_held(&bo->resv->lock.base);
-	/* Check that range is valid */
-	if (placement->lpfn || placement->fpfn)
-		if (placement->fpfn > placement->lpfn ||
-			(placement->lpfn - placement->fpfn) < bo->num_pages)
-			return -EINVAL;
 	/*
 	 * Check whether we need to move buffer.
 	 */
@@ -1070,15 +1058,6 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_bo_validate);
 
-int ttm_bo_check_placement(struct ttm_buffer_object *bo,
-				struct ttm_placement *placement)
-{
-	BUG_ON((placement->fpfn || placement->lpfn) &&
-	       (bo->mem.num_pages > (placement->lpfn - placement->fpfn)));
-
-	return 0;
-}
-
 int ttm_bo_init(struct ttm_bo_device *bdev,
 		struct ttm_buffer_object *bo,
 		unsigned long size,
@@ -1089,6 +1068,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 		struct file *persistent_swap_storage,
 		size_t acc_size,
 		struct sg_table *sg,
+		struct reservation_object *resv,
 		void (*destroy) (struct ttm_buffer_object *))
 {
 	int ret = 0;
@@ -1142,30 +1122,38 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 	bo->persistent_swap_storage = persistent_swap_storage;
 	bo->acc_size = acc_size;
 	bo->sg = sg;
-	bo->resv = &bo->ttm_resv;
-	reservation_object_init(bo->resv);
+	if (resv) {
+		bo->resv = resv;
+		lockdep_assert_held(&bo->resv->lock.base);
+	} else {
+		bo->resv = &bo->ttm_resv;
+		reservation_object_init(&bo->ttm_resv);
+	}
 	atomic_inc(&bo->glob->bo_count);
 	drm_vma_node_reset(&bo->vma_node);
 
-	ret = ttm_bo_check_placement(bo, placement);
-
 	/*
 	 * For ttm_bo_type_device buffers, allocate
 	 * address space from the device.
 	 */
-	if (likely(!ret) &&
-	    (bo->type == ttm_bo_type_device ||
-	     bo->type == ttm_bo_type_sg))
+	if (bo->type == ttm_bo_type_device ||
+	    bo->type == ttm_bo_type_sg)
 		ret = drm_vma_offset_add(&bdev->vma_manager, &bo->vma_node,
 					 bo->mem.num_pages);
 
-	locked = ww_mutex_trylock(&bo->resv->lock);
-	WARN_ON(!locked);
+	/* passed reservation objects should already be locked,
+	 * since otherwise lockdep will be angered in radeon.
+	 */
+	if (!resv) {
+		locked = ww_mutex_trylock(&bo->resv->lock);
+		WARN_ON(!locked);
+	}
 
 	if (likely(!ret))
 		ret = ttm_bo_validate(bo, placement, interruptible, false);
 
-	ttm_bo_unreserve(bo);
+	if (!resv)
+		ttm_bo_unreserve(bo);
 
 	if (unlikely(ret))
 		ttm_bo_unref(&bo);
@@ -1223,7 +1211,7 @@ int ttm_bo_create(struct ttm_bo_device *bdev,
 	acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct ttm_buffer_object));
 	ret = ttm_bo_init(bdev, bo, size, type, placement, page_alignment,
 			  interruptible, persistent_swap_storage, acc_size,
-			  NULL, NULL);
+			  NULL, NULL, NULL);
 	if (likely(ret == 0))
 		*p_bo = bo;
 
@@ -1477,7 +1465,6 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 	bdev->glob = glob;
 	bdev->need_dma32 = need_dma32;
 	bdev->val_seq = 0;
-	spin_lock_init(&bdev->fence_lock);
 	mutex_lock(&glob->device_list_mutex);
 	list_add_tail(&bdev->device_list, &glob->device_list);
 	mutex_unlock(&glob->device_list_mutex);
@@ -1530,65 +1517,56 @@ void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo)
 
 EXPORT_SYMBOL(ttm_bo_unmap_virtual);
 
-
 int ttm_bo_wait(struct ttm_buffer_object *bo,
 		bool lazy, bool interruptible, bool no_wait)
 {
-	struct ttm_bo_driver *driver = bo->bdev->driver;
-	struct ttm_bo_device *bdev = bo->bdev;
-	void *sync_obj;
-	int ret = 0;
-
-	if (likely(bo->sync_obj == NULL))
-		return 0;
+	struct reservation_object_list *fobj;
+	struct reservation_object *resv;
+	struct fence *excl;
+	long timeout = 15 * HZ;
+	int i;
 
-	while (bo->sync_obj) {
+	resv = bo->resv;
+	fobj = reservation_object_get_list(resv);
+	excl = reservation_object_get_excl(resv);
+	if (excl) {
+		if (!fence_is_signaled(excl)) {
+			if (no_wait)
+				return -EBUSY;
 
-		if (driver->sync_obj_signaled(bo->sync_obj)) {
-			void *tmp_obj = bo->sync_obj;
-			bo->sync_obj = NULL;
-			clear_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
-			spin_unlock(&bdev->fence_lock);
-			driver->sync_obj_unref(&tmp_obj);
-			spin_lock(&bdev->fence_lock);
-			continue;
+			timeout = fence_wait_timeout(excl,
+						     interruptible, timeout);
 		}
+	}
 
-		if (no_wait)
-			return -EBUSY;
+	for (i = 0; fobj && timeout > 0 && i < fobj->shared_count; ++i) {
+		struct fence *fence;
+		fence = rcu_dereference_protected(fobj->shared[i],
+						reservation_object_held(resv));
 
-		sync_obj = driver->sync_obj_ref(bo->sync_obj);
-		spin_unlock(&bdev->fence_lock);
-		ret = driver->sync_obj_wait(sync_obj,
-					    lazy, interruptible);
-		if (unlikely(ret != 0)) {
-			driver->sync_obj_unref(&sync_obj);
-			spin_lock(&bdev->fence_lock);
-			return ret;
-		}
-		spin_lock(&bdev->fence_lock);
-		if (likely(bo->sync_obj == sync_obj)) {
-			void *tmp_obj = bo->sync_obj;
-			bo->sync_obj = NULL;
-			clear_bit(TTM_BO_PRIV_FLAG_MOVING,
-				  &bo->priv_flags);
-			spin_unlock(&bdev->fence_lock);
-			driver->sync_obj_unref(&sync_obj);
-			driver->sync_obj_unref(&tmp_obj);
-			spin_lock(&bdev->fence_lock);
-		} else {
-			spin_unlock(&bdev->fence_lock);
-			driver->sync_obj_unref(&sync_obj);
-			spin_lock(&bdev->fence_lock);
+		if (!fence_is_signaled(fence)) {
+			if (no_wait)
+				return -EBUSY;
+
+			timeout = fence_wait_timeout(fence,
+						     interruptible, timeout);
 		}
 	}
+
+	if (timeout < 0)
+		return timeout;
+
+	if (timeout == 0)
+		return -EBUSY;
+
+	reservation_object_add_excl_fence(resv, NULL);
+	clear_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
 	return 0;
 }
 EXPORT_SYMBOL(ttm_bo_wait);
 
 int ttm_bo_synccpu_write_grab(struct ttm_buffer_object *bo, bool no_wait)
 {
-	struct ttm_bo_device *bdev = bo->bdev;
 	int ret = 0;
 
 	/*
@@ -1598,9 +1576,7 @@ int ttm_bo_synccpu_write_grab(struct ttm_buffer_object *bo, bool no_wait)
 	ret = ttm_bo_reserve(bo, true, no_wait, false, NULL);
 	if (unlikely(ret != 0))
 		return ret;
-	spin_lock(&bdev->fence_lock);
 	ret = ttm_bo_wait(bo, false, true, no_wait);
-	spin_unlock(&bdev->fence_lock);
 	if (likely(ret == 0))
 		atomic_inc(&bo->cpu_writers);
 	ttm_bo_unreserve(bo);
@@ -1657,9 +1633,7 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 	 * Wait for GPU, then move to system cached.
 	 */
 
-	spin_lock(&bo->bdev->fence_lock);
 	ret = ttm_bo_wait(bo, false, false, false);
-	spin_unlock(&bo->bdev->fence_lock);
 
 	if (unlikely(ret != 0))
 		goto out;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_manager.c b/drivers/gpu/drm/ttm/ttm_bo_manager.c
index 9e103a4875c8..964387fc5c8f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_manager.c
@@ -49,8 +49,7 @@ struct ttm_range_manager {
 
 static int ttm_bo_man_get_node(struct ttm_mem_type_manager *man,
 			       struct ttm_buffer_object *bo,
-			       struct ttm_placement *placement,
-			       uint32_t flags,
+			       const struct ttm_place *place,
 			       struct ttm_mem_reg *mem)
 {
 	struct ttm_range_manager *rman = (struct ttm_range_manager *) man->priv;
@@ -60,7 +59,7 @@ static int ttm_bo_man_get_node(struct ttm_mem_type_manager *man,
 	unsigned long lpfn;
 	int ret;
 
-	lpfn = placement->lpfn;
+	lpfn = place->lpfn;
 	if (!lpfn)
 		lpfn = man->size;
 
@@ -68,13 +67,13 @@ static int ttm_bo_man_get_node(struct ttm_mem_type_manager *man,
 	if (!node)
 		return -ENOMEM;
 
-	if (flags & TTM_PL_FLAG_TOPDOWN)
+	if (place->flags & TTM_PL_FLAG_TOPDOWN)
 		aflags = DRM_MM_CREATE_TOP;
 
 	spin_lock(&rman->lock);
 	ret = drm_mm_insert_node_in_range_generic(mm, node, mem->num_pages,
 					  mem->page_alignment, 0,
-					  placement->fpfn, lpfn,
+					  place->fpfn, lpfn,
 					  DRM_MM_SEARCH_BEST,
 					  aflags);
 	spin_unlock(&rman->lock);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 30e5d90cb7bc..882cccdad272 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -37,6 +37,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/module.h>
+#include <linux/reservation.h>
 
 void ttm_bo_free_old_node(struct ttm_buffer_object *bo)
 {
@@ -444,8 +445,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 				      struct ttm_buffer_object **new_obj)
 {
 	struct ttm_buffer_object *fbo;
-	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_bo_driver *driver = bdev->driver;
 	int ret;
 
 	fbo = kmalloc(sizeof(*fbo), GFP_KERNEL);
@@ -466,12 +465,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	drm_vma_node_reset(&fbo->vma_node);
 	atomic_set(&fbo->cpu_writers, 0);
 
-	spin_lock(&bdev->fence_lock);
-	if (bo->sync_obj)
-		fbo->sync_obj = driver->sync_obj_ref(bo->sync_obj);
-	else
-		fbo->sync_obj = NULL;
-	spin_unlock(&bdev->fence_lock);
 	kref_init(&fbo->list_kref);
 	kref_init(&fbo->kref);
 	fbo->destroy = &ttm_transfered_destroy;
@@ -487,28 +480,24 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 
 pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp)
 {
+	/* Cached mappings need no adjustment */
+	if (caching_flags & TTM_PL_FLAG_CACHED)
+		return tmp;
+
 #if defined(__i386__) || defined(__x86_64__)
 	if (caching_flags & TTM_PL_FLAG_WC)
 		tmp = pgprot_writecombine(tmp);
 	else if (boot_cpu_data.x86 > 3)
 		tmp = pgprot_noncached(tmp);
-
-#elif defined(__powerpc__)
-	if (!(caching_flags & TTM_PL_FLAG_CACHED)) {
-		pgprot_val(tmp) |= _PAGE_NO_CACHE;
-		if (caching_flags & TTM_PL_FLAG_UNCACHED)
-			pgprot_val(tmp) |= _PAGE_GUARDED;
-	}
 #endif
-#if defined(__ia64__) || defined(__arm__)
+#if defined(__ia64__) || defined(__arm__) || defined(__powerpc__)
 	if (caching_flags & TTM_PL_FLAG_WC)
 		tmp = pgprot_writecombine(tmp);
 	else
 		tmp = pgprot_noncached(tmp);
 #endif
 #if defined(__sparc__) || defined(__mips__)
-	if (!(caching_flags & TTM_PL_FLAG_CACHED))
-		tmp = pgprot_noncached(tmp);
+	tmp = pgprot_noncached(tmp);
 #endif
 	return tmp;
 }
@@ -567,9 +556,7 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo,
 		 * We need to use vmap to get the desired page protection
 		 * or to make the buffer object look contiguous.
 		 */
-		prot = (mem->placement & TTM_PL_FLAG_CACHED) ?
-			PAGE_KERNEL :
-			ttm_io_prot(mem->placement, PAGE_KERNEL);
+		prot = ttm_io_prot(mem->placement, PAGE_KERNEL);
 		map->bo_kmap_type = ttm_bo_map_vmap;
 		map->virtual = vmap(ttm->pages + start_page, num_pages,
 				    0, prot);
@@ -644,30 +631,20 @@ void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map)
 EXPORT_SYMBOL(ttm_bo_kunmap);
 
 int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
-			      void *sync_obj,
+			      struct fence *fence,
 			      bool evict,
 			      bool no_wait_gpu,
 			      struct ttm_mem_reg *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_bo_driver *driver = bdev->driver;
 	struct ttm_mem_type_manager *man = &bdev->man[new_mem->mem_type];
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	int ret;
 	struct ttm_buffer_object *ghost_obj;
-	void *tmp_obj = NULL;
 
-	spin_lock(&bdev->fence_lock);
-	if (bo->sync_obj) {
-		tmp_obj = bo->sync_obj;
-		bo->sync_obj = NULL;
-	}
-	bo->sync_obj = driver->sync_obj_ref(sync_obj);
+	reservation_object_add_excl_fence(bo->resv, fence);
 	if (evict) {
 		ret = ttm_bo_wait(bo, false, false, false);
-		spin_unlock(&bdev->fence_lock);
-		if (tmp_obj)
-			driver->sync_obj_unref(&tmp_obj);
 		if (ret)
 			return ret;
 
@@ -688,14 +665,13 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		 */
 
 		set_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
-		spin_unlock(&bdev->fence_lock);
-		if (tmp_obj)
-			driver->sync_obj_unref(&tmp_obj);
 
 		ret = ttm_buffer_object_transfer(bo, &ghost_obj);
 		if (ret)
 			return ret;
 
+		reservation_object_add_excl_fence(ghost_obj->resv, fence);
+
 		/**
 		 * If we're not moving to fixed memory, the TTM object
 		 * needs to stay alive. Otherwhise hang it on the ghost
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 0ce48e5a9cb4..8fb7213277cc 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -45,10 +45,8 @@ static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 				struct vm_area_struct *vma,
 				struct vm_fault *vmf)
 {
-	struct ttm_bo_device *bdev = bo->bdev;
 	int ret = 0;
 
-	spin_lock(&bdev->fence_lock);
 	if (likely(!test_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags)))
 		goto out_unlock;
 
@@ -82,7 +80,6 @@ static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 			VM_FAULT_NOPAGE;
 
 out_unlock:
-	spin_unlock(&bdev->fence_lock);
 	return ret;
 }
 
@@ -200,9 +197,8 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 						cvma.vm_page_prot);
 	} else {
 		ttm = bo->ttm;
-		if (!(bo->mem.placement & TTM_PL_FLAG_CACHED))
-			cvma.vm_page_prot = ttm_io_prot(bo->mem.placement,
-							cvma.vm_page_prot);
+		cvma.vm_page_prot = ttm_io_prot(bo->mem.placement,
+						cvma.vm_page_prot);
 
 		/* Allocate all page at once, most common usage */
 		if (ttm->bdev->driver->ttm_tt_populate(ttm)) {
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index e8dac8758528..8ce508e76208 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -32,20 +32,12 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 
-static void ttm_eu_backoff_reservation_locked(struct list_head *list)
+static void ttm_eu_backoff_reservation_reverse(struct list_head *list,
+					      struct ttm_validate_buffer *entry)
 {
-	struct ttm_validate_buffer *entry;
-
-	list_for_each_entry(entry, list, head) {
+	list_for_each_entry_continue_reverse(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
-		if (!entry->reserved)
-			continue;
 
-		entry->reserved = false;
-		if (entry->removed) {
-			ttm_bo_add_to_lru(bo);
-			entry->removed = false;
-		}
 		__ttm_bo_unreserve(bo);
 	}
 }
@@ -56,27 +48,9 @@ static void ttm_eu_del_from_lru_locked(struct list_head *list)
 
 	list_for_each_entry(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
-		if (!entry->reserved)
-			continue;
-
-		if (!entry->removed) {
-			entry->put_count = ttm_bo_del_from_lru(bo);
-			entry->removed = true;
-		}
-	}
-}
-
-static void ttm_eu_list_ref_sub(struct list_head *list)
-{
-	struct ttm_validate_buffer *entry;
-
-	list_for_each_entry(entry, list, head) {
-		struct ttm_buffer_object *bo = entry->bo;
+		unsigned put_count = ttm_bo_del_from_lru(bo);
 
-		if (entry->put_count) {
-			ttm_bo_list_ref_sub(bo, entry->put_count, true);
-			entry->put_count = 0;
-		}
+		ttm_bo_list_ref_sub(bo, put_count, true);
 	}
 }
 
@@ -91,11 +65,18 @@ void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
 
 	entry = list_first_entry(list, struct ttm_validate_buffer, head);
 	glob = entry->bo->glob;
+
 	spin_lock(&glob->lru_lock);
-	ttm_eu_backoff_reservation_locked(list);
+	list_for_each_entry(entry, list, head) {
+		struct ttm_buffer_object *bo = entry->bo;
+
+		ttm_bo_add_to_lru(bo);
+		__ttm_bo_unreserve(bo);
+	}
+	spin_unlock(&glob->lru_lock);
+
 	if (ticket)
 		ww_acquire_fini(ticket);
-	spin_unlock(&glob->lru_lock);
 }
 EXPORT_SYMBOL(ttm_eu_backoff_reservation);
 
@@ -112,7 +93,7 @@ EXPORT_SYMBOL(ttm_eu_backoff_reservation);
  */
 
 int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
-			   struct list_head *list)
+			   struct list_head *list, bool intr)
 {
 	struct ttm_bo_global *glob;
 	struct ttm_validate_buffer *entry;
@@ -121,60 +102,64 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 	if (list_empty(list))
 		return 0;
 
-	list_for_each_entry(entry, list, head) {
-		entry->reserved = false;
-		entry->put_count = 0;
-		entry->removed = false;
-	}
-
 	entry = list_first_entry(list, struct ttm_validate_buffer, head);
 	glob = entry->bo->glob;
 
 	if (ticket)
 		ww_acquire_init(ticket, &reservation_ww_class);
-retry:
+
 	list_for_each_entry(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
 
-		/* already slowpath reserved? */
-		if (entry->reserved)
-			continue;
-
-		ret = __ttm_bo_reserve(bo, true, (ticket == NULL), true,
+		ret = __ttm_bo_reserve(bo, intr, (ticket == NULL), true,
 				       ticket);
+		if (!ret && unlikely(atomic_read(&bo->cpu_writers) > 0)) {
+			__ttm_bo_unreserve(bo);
+
+			ret = -EBUSY;
+		}
 
-		if (ret == -EDEADLK) {
-			/* uh oh, we lost out, drop every reservation and try
-			 * to only reserve this buffer, then start over if
-			 * this succeeds.
-			 */
-			BUG_ON(ticket == NULL);
-			spin_lock(&glob->lru_lock);
-			ttm_eu_backoff_reservation_locked(list);
-			spin_unlock(&glob->lru_lock);
-			ttm_eu_list_ref_sub(list);
+		if (!ret) {
+			if (!entry->shared)
+				continue;
+
+			ret = reservation_object_reserve_shared(bo->resv);
+			if (!ret)
+				continue;
+		}
+
+		/* uh oh, we lost out, drop every reservation and try
+		 * to only reserve this buffer, then start over if
+		 * this succeeds.
+		 */
+		ttm_eu_backoff_reservation_reverse(list, entry);
+
+		if (ret == -EDEADLK && intr) {
 			ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
 							       ticket);
-			if (unlikely(ret != 0)) {
-				if (ret == -EINTR)
-					ret = -ERESTARTSYS;
-				goto err_fini;
-			}
+		} else if (ret == -EDEADLK) {
+			ww_mutex_lock_slow(&bo->resv->lock, ticket);
+			ret = 0;
+		}
 
-			entry->reserved = true;
-			if (unlikely(atomic_read(&bo->cpu_writers) > 0)) {
-				ret = -EBUSY;
-				goto err;
-			}
-			goto retry;
-		} else if (ret)
-			goto err;
+		if (!ret && entry->shared)
+			ret = reservation_object_reserve_shared(bo->resv);
 
-		entry->reserved = true;
-		if (unlikely(atomic_read(&bo->cpu_writers) > 0)) {
-			ret = -EBUSY;
-			goto err;
+		if (unlikely(ret != 0)) {
+			if (ret == -EINTR)
+				ret = -ERESTARTSYS;
+			if (ticket) {
+				ww_acquire_done(ticket);
+				ww_acquire_fini(ticket);
+			}
+			return ret;
 		}
+
+		/* move this item to the front of the list,
+		 * forces correct iteration of the loop without keeping track
+		 */
+		list_del(&entry->head);
+		list_add(&entry->head, list);
 	}
 
 	if (ticket)
@@ -182,25 +167,12 @@ retry:
 	spin_lock(&glob->lru_lock);
 	ttm_eu_del_from_lru_locked(list);
 	spin_unlock(&glob->lru_lock);
-	ttm_eu_list_ref_sub(list);
 	return 0;
-
-err:
-	spin_lock(&glob->lru_lock);
-	ttm_eu_backoff_reservation_locked(list);
-	spin_unlock(&glob->lru_lock);
-	ttm_eu_list_ref_sub(list);
-err_fini:
-	if (ticket) {
-		ww_acquire_done(ticket);
-		ww_acquire_fini(ticket);
-	}
-	return ret;
 }
 EXPORT_SYMBOL(ttm_eu_reserve_buffers);
 
 void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
-				 struct list_head *list, void *sync_obj)
+				 struct list_head *list, struct fence *fence)
 {
 	struct ttm_validate_buffer *entry;
 	struct ttm_buffer_object *bo;
@@ -217,24 +189,18 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
 	glob = bo->glob;
 
 	spin_lock(&glob->lru_lock);
-	spin_lock(&bdev->fence_lock);
 
 	list_for_each_entry(entry, list, head) {
 		bo = entry->bo;
-		entry->old_sync_obj = bo->sync_obj;
-		bo->sync_obj = driver->sync_obj_ref(sync_obj);
+		if (entry->shared)
+			reservation_object_add_shared_fence(bo->resv, fence);
+		else
+			reservation_object_add_excl_fence(bo->resv, fence);
 		ttm_bo_add_to_lru(bo);
 		__ttm_bo_unreserve(bo);
-		entry->reserved = false;
 	}
-	spin_unlock(&bdev->fence_lock);
 	spin_unlock(&glob->lru_lock);
 	if (ticket)
 		ww_acquire_fini(ticket);
-
-	list_for_each_entry(entry, list, head) {
-		if (entry->old_sync_obj)
-			driver->sync_obj_unref(&entry->old_sync_obj);
-	}
 }
 EXPORT_SYMBOL(ttm_eu_fence_buffer_objects);
diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c
index dbc2def887cd..a1803fbcc898 100644
--- a/drivers/gpu/drm/ttm/ttm_memory.c
+++ b/drivers/gpu/drm/ttm/ttm_memory.c
@@ -300,7 +300,8 @@ static int ttm_mem_init_highmem_zone(struct ttm_mem_global *glob,
 	zone->glob = glob;
 	glob->zone_highmem = zone;
 	ret = kobject_init_and_add(
-		&zone->kobj, &ttm_mem_zone_kobj_type, &glob->kobj, zone->name);
+		&zone->kobj, &ttm_mem_zone_kobj_type, &glob->kobj, "%s",
+		zone->name);
 	if (unlikely(ret != 0)) {
 		kobject_put(&zone->kobj);
 		return ret;
diff --git a/drivers/gpu/drm/udl/Kconfig b/drivers/gpu/drm/udl/Kconfig
index f02528686cd5..613ab0622d6e 100644
--- a/drivers/gpu/drm/udl/Kconfig
+++ b/drivers/gpu/drm/udl/Kconfig
@@ -1,8 +1,9 @@
 config DRM_UDL
 	tristate "DisplayLink"
 	depends on DRM
+	depends on USB_SUPPORT
 	depends on USB_ARCH_HAS_HCD
-	select DRM_USB
+	select USB
 	select FB_SYS_FILLRECT
 	select FB_SYS_COPYAREA
 	select FB_SYS_IMAGEBLIT
diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c
index e026a9e2942a..0110d95522f3 100644
--- a/drivers/gpu/drm/udl/udl_connector.c
+++ b/drivers/gpu/drm/udl/udl_connector.c
@@ -34,8 +34,8 @@ static u8 *udl_get_edid(struct udl_device *udl)
 		goto error;
 
 	for (i = 0; i < EDID_LENGTH; i++) {
-		ret = usb_control_msg(udl->ddev->usbdev,
-				      usb_rcvctrlpipe(udl->ddev->usbdev, 0), (0x02),
+		ret = usb_control_msg(udl->udev,
+				      usb_rcvctrlpipe(udl->udev, 0), (0x02),
 				      (0x80 | (0x02 << 5)), i << 8, 0xA1, rbuf, 2,
 				      HZ);
 		if (ret < 1) {
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 3ddd6cd98ac1..8607e9e513db 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -7,48 +7,13 @@
  */
 
 #include <linux/module.h>
-#include <drm/drm_usb.h>
+#include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
 #include "udl_drv.h"
 
-static struct drm_driver driver;
-
-/*
- * There are many DisplayLink-based graphics products, all with unique PIDs.
- * So we match on DisplayLink's VID + Vendor-Defined Interface Class (0xff)
- * We also require a match on SubClass (0x00) and Protocol (0x00),
- * which is compatible with all known USB 2.0 era graphics chips and firmware,
- * but allows DisplayLink to increment those for any future incompatible chips
- */
-static struct usb_device_id id_table[] = {
-	{.idVendor = 0x17e9, .bInterfaceClass = 0xff,
-	 .bInterfaceSubClass = 0x00,
-	 .bInterfaceProtocol = 0x00,
-	 .match_flags = USB_DEVICE_ID_MATCH_VENDOR |
-			USB_DEVICE_ID_MATCH_INT_CLASS |
-			USB_DEVICE_ID_MATCH_INT_SUBCLASS |
-			USB_DEVICE_ID_MATCH_INT_PROTOCOL,},
-	{},
-};
-MODULE_DEVICE_TABLE(usb, id_table);
-
-MODULE_LICENSE("GPL");
-
-static int udl_usb_probe(struct usb_interface *interface,
-			 const struct usb_device_id *id)
+static int udl_driver_set_busid(struct drm_device *d, struct drm_master *m)
 {
-	return drm_get_usb_dev(interface, id, &driver);
-}
-
-static void udl_usb_disconnect(struct usb_interface *interface)
-{
-	struct drm_device *dev = usb_get_intfdata(interface);
-
-	drm_kms_helper_poll_disable(dev);
-	drm_connector_unplug_all(dev);
-	udl_fbdev_unplug(dev);
-	udl_drop_usb(dev);
-	drm_unplug_dev(dev);
+	return 0;
 }
 
 static const struct vm_operations_struct udl_gem_vm_ops = {
@@ -75,6 +40,7 @@ static struct drm_driver driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME,
 	.load = udl_driver_load,
 	.unload = udl_driver_unload,
+	.set_busid = udl_driver_set_busid,
 
 	/* gem hooks */
 	.gem_free_object = udl_gem_free_object,
@@ -96,6 +62,61 @@ static struct drm_driver driver = {
 	.patchlevel = DRIVER_PATCHLEVEL,
 };
 
+static int udl_usb_probe(struct usb_interface *interface,
+			 const struct usb_device_id *id)
+{
+	struct usb_device *udev = interface_to_usbdev(interface);
+	struct drm_device *dev;
+	int r;
+
+	dev = drm_dev_alloc(&driver, &interface->dev);
+	if (!dev)
+		return -ENOMEM;
+
+	r = drm_dev_register(dev, (unsigned long)udev);
+	if (r)
+		goto err_free;
+
+	usb_set_intfdata(interface, dev);
+	DRM_INFO("Initialized udl on minor %d\n", dev->primary->index);
+
+	return 0;
+
+err_free:
+	drm_dev_unref(dev);
+	return r;
+}
+
+static void udl_usb_disconnect(struct usb_interface *interface)
+{
+	struct drm_device *dev = usb_get_intfdata(interface);
+
+	drm_kms_helper_poll_disable(dev);
+	drm_connector_unplug_all(dev);
+	udl_fbdev_unplug(dev);
+	udl_drop_usb(dev);
+	drm_unplug_dev(dev);
+}
+
+/*
+ * There are many DisplayLink-based graphics products, all with unique PIDs.
+ * So we match on DisplayLink's VID + Vendor-Defined Interface Class (0xff)
+ * We also require a match on SubClass (0x00) and Protocol (0x00),
+ * which is compatible with all known USB 2.0 era graphics chips and firmware,
+ * but allows DisplayLink to increment those for any future incompatible chips
+ */
+static struct usb_device_id id_table[] = {
+	{.idVendor = 0x17e9, .bInterfaceClass = 0xff,
+	 .bInterfaceSubClass = 0x00,
+	 .bInterfaceProtocol = 0x00,
+	 .match_flags = USB_DEVICE_ID_MATCH_VENDOR |
+			USB_DEVICE_ID_MATCH_INT_CLASS |
+			USB_DEVICE_ID_MATCH_INT_SUBCLASS |
+			USB_DEVICE_ID_MATCH_INT_PROTOCOL,},
+	{},
+};
+MODULE_DEVICE_TABLE(usb, id_table);
+
 static struct usb_driver udl_driver = {
 	.name = "udl",
 	.probe = udl_usb_probe,
@@ -105,13 +126,14 @@ static struct usb_driver udl_driver = {
 
 static int __init udl_init(void)
 {
-	return drm_usb_init(&driver, &udl_driver);
+	return usb_register(&udl_driver);
 }
 
 static void __exit udl_exit(void)
 {
-	drm_usb_exit(&driver, &udl_driver);
+	usb_deregister(&udl_driver);
 }
 
 module_init(udl_init);
 module_exit(udl_exit);
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 1fbf7b357f16..c7490a2489a7 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -15,6 +15,7 @@
 #define UDL_DRV_H
 
 #include <linux/usb.h>
+#include <drm/drm_gem.h>
 
 #define DRIVER_NAME		"udl"
 #define DRIVER_DESC		"DisplayLink"
@@ -47,6 +48,7 @@ struct udl_fbdev;
 struct udl_device {
 	struct device *dev;
 	struct drm_device *ddev;
+	struct usb_device *udev;
 
 	int sku_pixel_limit;
 
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index d1da339843ca..8cbcb4589bd3 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -472,7 +472,8 @@ udl_framebuffer_init(struct drm_device *dev,
 static int udlfb_create(struct drm_fb_helper *helper,
 			struct drm_fb_helper_surface_size *sizes)
 {
-	struct udl_fbdev *ufbdev = (struct udl_fbdev *)helper;
+	struct udl_fbdev *ufbdev =
+		container_of(helper, struct udl_fbdev, helper);
 	struct drm_device *dev = ufbdev->helper.dev;
 	struct fb_info *info;
 	struct device *device = dev->dev;
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index 42795674bc07..33dbfb2c4748 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -202,7 +202,7 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 		}
 		unode->urb = urb;
 
-		buf = usb_alloc_coherent(udl->ddev->usbdev, MAX_TRANSFER, GFP_KERNEL,
+		buf = usb_alloc_coherent(udl->udev, MAX_TRANSFER, GFP_KERNEL,
 					 &urb->transfer_dma);
 		if (!buf) {
 			kfree(unode);
@@ -211,7 +211,7 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 		}
 
 		/* urb->transfer_buffer_length set to actual before submit */
-		usb_fill_bulk_urb(urb, udl->ddev->usbdev, usb_sndbulkpipe(udl->ddev->usbdev, 1),
+		usb_fill_bulk_urb(urb, udl->udev, usb_sndbulkpipe(udl->udev, 1),
 			buf, size, udl_urb_completion, unode);
 		urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
 
@@ -282,6 +282,7 @@ int udl_submit_urb(struct drm_device *dev, struct urb *urb, size_t len)
 
 int udl_driver_load(struct drm_device *dev, unsigned long flags)
 {
+	struct usb_device *udev = (void*)flags;
 	struct udl_device *udl;
 	int ret = -ENOMEM;
 
@@ -290,10 +291,11 @@ int udl_driver_load(struct drm_device *dev, unsigned long flags)
 	if (!udl)
 		return -ENOMEM;
 
+	udl->udev = udev;
 	udl->ddev = dev;
 	dev->dev_private = udl;
 
-	if (!udl_parse_vendor_descriptor(dev, dev->usbdev)) {
+	if (!udl_parse_vendor_descriptor(dev, udl->udev)) {
 		ret = -ENODEV;
 		DRM_ERROR("firmware not recognized. Assume incompatible device\n");
 		goto err;
diff --git a/drivers/gpu/drm/via/via_dma.c b/drivers/gpu/drm/via/via_dma.c
index 6fc0648dd37f..d17d8f245c1a 100644
--- a/drivers/gpu/drm/via/via_dma.c
+++ b/drivers/gpu/drm/via/via_dma.c
@@ -161,7 +161,7 @@ int via_dma_cleanup(struct drm_device *dev)
 		if (dev_priv->ring.virtual_start) {
 			via_cmdbuf_reset(dev_priv);
 
-			drm_core_ioremapfree(&dev_priv->ring.map, dev);
+			drm_legacy_ioremapfree(&dev_priv->ring.map, dev);
 			dev_priv->ring.virtual_start = NULL;
 		}
 
@@ -200,7 +200,7 @@ static int via_initialize(struct drm_device *dev,
 	dev_priv->ring.map.flags = 0;
 	dev_priv->ring.map.mtrr = 0;
 
-	drm_core_ioremap(&dev_priv->ring.map, dev);
+	drm_legacy_ioremap(&dev_priv->ring.map, dev);
 
 	if (dev_priv->ring.map.handle == NULL) {
 		via_dma_cleanup(dev);
diff --git a/drivers/gpu/drm/via/via_drv.c b/drivers/gpu/drm/via/via_drv.c
index 50abc2adfaee..ed8aa8ff861a 100644
--- a/drivers/gpu/drm/via/via_drv.c
+++ b/drivers/gpu/drm/via/via_drv.c
@@ -62,7 +62,7 @@ static const struct file_operations via_driver_fops = {
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_mmap,
+	.mmap = drm_legacy_mmap,
 	.poll = drm_poll,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = drm_compat_ioctl,
@@ -79,6 +79,7 @@ static struct drm_driver driver = {
 	.open = via_driver_open,
 	.preclose = via_reclaim_buffers_locked,
 	.postclose = via_driver_postclose,
+	.set_busid = drm_pci_set_busid,
 	.context_dtor = via_final_context,
 	.get_vblank_counter = via_get_vblank_counter,
 	.enable_vblank = via_enable_vblank,
diff --git a/drivers/gpu/drm/via/via_drv.h b/drivers/gpu/drm/via/via_drv.h
index ad0273256beb..ef8c500b4a00 100644
--- a/drivers/gpu/drm/via/via_drv.h
+++ b/drivers/gpu/drm/via/via_drv.h
@@ -25,6 +25,8 @@
 #define _VIA_DRV_H_
 
 #include <drm/drm_mm.h>
+#include <drm/drm_legacy.h>
+
 #define DRIVER_AUTHOR	"Various"
 
 #define DRIVER_NAME		"via"
diff --git a/drivers/gpu/drm/via/via_map.c b/drivers/gpu/drm/via/via_map.c
index d0ab3fb32acd..0b3522dba6e8 100644
--- a/drivers/gpu/drm/via/via_map.c
+++ b/drivers/gpu/drm/via/via_map.c
@@ -31,7 +31,7 @@ static int via_do_init_map(struct drm_device *dev, drm_via_init_t *init)
 
 	DRM_DEBUG("\n");
 
-	dev_priv->sarea = drm_getsarea(dev);
+	dev_priv->sarea = drm_legacy_getsarea(dev);
 	if (!dev_priv->sarea) {
 		DRM_ERROR("could not find sarea!\n");
 		dev->dev_private = (void *)dev_priv;
@@ -39,14 +39,14 @@ static int via_do_init_map(struct drm_device *dev, drm_via_init_t *init)
 		return -EINVAL;
 	}
 
-	dev_priv->fb = drm_core_findmap(dev, init->fb_offset);
+	dev_priv->fb = drm_legacy_findmap(dev, init->fb_offset);
 	if (!dev_priv->fb) {
 		DRM_ERROR("could not find framebuffer!\n");
 		dev->dev_private = (void *)dev_priv;
 		via_do_cleanup_map(dev);
 		return -EINVAL;
 	}
-	dev_priv->mmio = drm_core_findmap(dev, init->mmio_offset);
+	dev_priv->mmio = drm_legacy_findmap(dev, init->mmio_offset);
 	if (!dev_priv->mmio) {
 		DRM_ERROR("could not find mmio region!\n");
 		dev->dev_private = (void *)dev_priv;
diff --git a/drivers/gpu/drm/via/via_mm.c b/drivers/gpu/drm/via/via_mm.c
index d70b1e1544bf..4f20742e7788 100644
--- a/drivers/gpu/drm/via/via_mm.c
+++ b/drivers/gpu/drm/via/via_mm.c
@@ -211,12 +211,12 @@ void via_reclaim_buffers_locked(struct drm_device *dev,
 	if (!(file->minor->master && file->master->lock.hw_lock))
 		return;
 
-	drm_idlelock_take(&file->master->lock);
+	drm_legacy_idlelock_take(&file->master->lock);
 
 	mutex_lock(&dev->struct_mutex);
 	if (list_empty(&file_priv->obj_list)) {
 		mutex_unlock(&dev->struct_mutex);
-		drm_idlelock_release(&file->master->lock);
+		drm_legacy_idlelock_release(&file->master->lock);
 
 		return;
 	}
@@ -231,7 +231,7 @@ void via_reclaim_buffers_locked(struct drm_device *dev,
 	}
 	mutex_unlock(&dev->struct_mutex);
 
-	drm_idlelock_release(&file->master->lock);
+	drm_legacy_idlelock_release(&file->master->lock);
 
 	return;
 }
diff --git a/drivers/gpu/drm/via/via_verifier.c b/drivers/gpu/drm/via/via_verifier.c
index 9dbc92bd1512..0677bbf4ec7e 100644
--- a/drivers/gpu/drm/via/via_verifier.c
+++ b/drivers/gpu/drm/via/via_verifier.c
@@ -31,6 +31,7 @@
 #include "via_3d_reg.h"
 #include <drm/drmP.h>
 #include <drm/via_drm.h>
+#include <drm/drm_legacy.h>
 #include "via_verifier.h"
 #include "via_drv.h"
 
diff --git a/drivers/gpu/drm/vmwgfx/svga_reg.h b/drivers/gpu/drm/vmwgfx/svga_reg.h
index 11323dd5196f..e4259c2c1acc 100644
--- a/drivers/gpu/drm/vmwgfx/svga_reg.h
+++ b/drivers/gpu/drm/vmwgfx/svga_reg.h
@@ -35,7 +35,6 @@
 /*
  * PCI device IDs.
  */
-#define PCI_VENDOR_ID_VMWARE            0x15AD
 #define PCI_DEVICE_ID_VMWARE_SVGA2      0x0405
 
 /*
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
index 6327cfc36805..cff2bf9db9d2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
@@ -30,66 +30,101 @@
 #include <drm/ttm/ttm_placement.h>
 #include <drm/ttm/ttm_page_alloc.h>
 
-static uint32_t vram_placement_flags = TTM_PL_FLAG_VRAM |
-	TTM_PL_FLAG_CACHED;
-
-static uint32_t vram_ne_placement_flags = TTM_PL_FLAG_VRAM |
-	TTM_PL_FLAG_CACHED |
-	TTM_PL_FLAG_NO_EVICT;
+static struct ttm_place vram_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+};
 
-static uint32_t sys_placement_flags = TTM_PL_FLAG_SYSTEM |
-	TTM_PL_FLAG_CACHED;
+static struct ttm_place vram_ne_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+};
 
-static uint32_t sys_ne_placement_flags = TTM_PL_FLAG_SYSTEM |
-	TTM_PL_FLAG_CACHED |
-	TTM_PL_FLAG_NO_EVICT;
+static struct ttm_place sys_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
+};
 
-static uint32_t gmr_placement_flags = VMW_PL_FLAG_GMR |
-	TTM_PL_FLAG_CACHED;
+static struct ttm_place sys_ne_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+};
 
-static uint32_t gmr_ne_placement_flags = VMW_PL_FLAG_GMR |
-	TTM_PL_FLAG_CACHED |
-	TTM_PL_FLAG_NO_EVICT;
+static struct ttm_place gmr_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+};
 
-static uint32_t mob_placement_flags = VMW_PL_FLAG_MOB |
-	TTM_PL_FLAG_CACHED;
+static struct ttm_place gmr_ne_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+};
 
-struct ttm_placement vmw_vram_placement = {
+static struct ttm_place mob_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
+	.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+};
+
+struct ttm_placement vmw_vram_placement = {
 	.num_placement = 1,
 	.placement = &vram_placement_flags,
 	.num_busy_placement = 1,
 	.busy_placement = &vram_placement_flags
 };
 
-static uint32_t vram_gmr_placement_flags[] = {
-	TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED,
-	VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+static struct ttm_place vram_gmr_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+	}
 };
 
-static uint32_t gmr_vram_placement_flags[] = {
-	VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED,
-	TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+static struct ttm_place gmr_vram_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+	}
 };
 
 struct ttm_placement vmw_vram_gmr_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 2,
 	.placement = vram_gmr_placement_flags,
 	.num_busy_placement = 1,
 	.busy_placement = &gmr_placement_flags
 };
 
-static uint32_t vram_gmr_ne_placement_flags[] = {
-	TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT,
-	VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+static struct ttm_place vram_gmr_ne_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED |
+			 TTM_PL_FLAG_NO_EVICT
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED |
+			 TTM_PL_FLAG_NO_EVICT
+	}
 };
 
 struct ttm_placement vmw_vram_gmr_ne_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 2,
 	.placement = vram_gmr_ne_placement_flags,
 	.num_busy_placement = 1,
@@ -97,8 +132,6 @@ struct ttm_placement vmw_vram_gmr_ne_placement = {
 };
 
 struct ttm_placement vmw_vram_sys_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.placement = &vram_placement_flags,
 	.num_busy_placement = 1,
@@ -106,8 +139,6 @@ struct ttm_placement vmw_vram_sys_placement = {
 };
 
 struct ttm_placement vmw_vram_ne_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.placement = &vram_ne_placement_flags,
 	.num_busy_placement = 1,
@@ -115,8 +146,6 @@ struct ttm_placement vmw_vram_ne_placement = {
 };
 
 struct ttm_placement vmw_sys_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.placement = &sys_placement_flags,
 	.num_busy_placement = 1,
@@ -124,24 +153,33 @@ struct ttm_placement vmw_sys_placement = {
 };
 
 struct ttm_placement vmw_sys_ne_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.placement = &sys_ne_placement_flags,
 	.num_busy_placement = 1,
 	.busy_placement = &sys_ne_placement_flags
 };
 
-static uint32_t evictable_placement_flags[] = {
-	TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED,
-	TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED,
-	VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED,
-	VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+static struct ttm_place evictable_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+	}
 };
 
 struct ttm_placement vmw_evictable_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 4,
 	.placement = evictable_placement_flags,
 	.num_busy_placement = 1,
@@ -149,8 +187,6 @@ struct ttm_placement vmw_evictable_placement = {
 };
 
 struct ttm_placement vmw_srf_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.num_busy_placement = 2,
 	.placement = &gmr_placement_flags,
@@ -158,8 +194,6 @@ struct ttm_placement vmw_srf_placement = {
 };
 
 struct ttm_placement vmw_mob_placement = {
-	.fpfn = 0,
-	.lpfn = 0,
 	.num_placement = 1,
 	.num_busy_placement = 1,
 	.placement = &mob_placement_flags,
@@ -768,44 +802,6 @@ static int vmw_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
 }
 
 /**
- * FIXME: We're using the old vmware polling method to sync.
- * Do this with fences instead.
- */
-
-static void *vmw_sync_obj_ref(void *sync_obj)
-{
-
-	return (void *)
-		vmw_fence_obj_reference((struct vmw_fence_obj *) sync_obj);
-}
-
-static void vmw_sync_obj_unref(void **sync_obj)
-{
-	vmw_fence_obj_unreference((struct vmw_fence_obj **) sync_obj);
-}
-
-static int vmw_sync_obj_flush(void *sync_obj)
-{
-	vmw_fence_obj_flush((struct vmw_fence_obj *) sync_obj);
-	return 0;
-}
-
-static bool vmw_sync_obj_signaled(void *sync_obj)
-{
-	return	vmw_fence_obj_signaled((struct vmw_fence_obj *) sync_obj,
-				       DRM_VMW_FENCE_FLAG_EXEC);
-
-}
-
-static int vmw_sync_obj_wait(void *sync_obj, bool lazy, bool interruptible)
-{
-	return vmw_fence_obj_wait((struct vmw_fence_obj *) sync_obj,
-				  DRM_VMW_FENCE_FLAG_EXEC,
-				  lazy, interruptible,
-				  VMW_FENCE_WAIT_TIMEOUT);
-}
-
-/**
  * vmw_move_notify - TTM move_notify_callback
  *
  * @bo:             The TTM buffer object about to move.
@@ -829,11 +825,7 @@ static void vmw_move_notify(struct ttm_buffer_object *bo,
  */
 static void vmw_swap_notify(struct ttm_buffer_object *bo)
 {
-	struct ttm_bo_device *bdev = bo->bdev;
-
-	spin_lock(&bdev->fence_lock);
 	ttm_bo_wait(bo, false, false, false);
-	spin_unlock(&bdev->fence_lock);
 }
 
 
@@ -846,11 +838,6 @@ struct ttm_bo_driver vmw_bo_driver = {
 	.evict_flags = vmw_evict_flags,
 	.move = NULL,
 	.verify_access = vmw_verify_access,
-	.sync_obj_signaled = vmw_sync_obj_signaled,
-	.sync_obj_wait = vmw_sync_obj_wait,
-	.sync_obj_flush = vmw_sync_obj_flush,
-	.sync_obj_unref = vmw_sync_obj_unref,
-	.sync_obj_ref = vmw_sync_obj_ref,
 	.move_notify = vmw_move_notify,
 	.swap_notify = vmw_swap_notify,
 	.fault_reserve_notify = &vmw_ttm_fault_reserve_notify,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
index ed1d51006ab1..914b375763dc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
@@ -198,13 +198,19 @@ int vmw_dmabuf_to_start_of_vram(struct vmw_private *dev_priv,
 {
 	struct ttm_buffer_object *bo = &buf->base;
 	struct ttm_placement placement;
+	struct ttm_place place;
 	int ret = 0;
 
 	if (pin)
-		placement = vmw_vram_ne_placement;
+		place = vmw_vram_ne_placement.placement[0];
 	else
-		placement = vmw_vram_placement;
-	placement.lpfn = bo->num_pages;
+		place = vmw_vram_placement.placement[0];
+	place.lpfn = bo->num_pages;
+
+	placement.num_placement = 1;
+	placement.placement = &place;
+	placement.num_busy_placement = 1;
+	placement.busy_placement = &place;
 
 	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
 	if (unlikely(ret != 0))
@@ -293,21 +299,23 @@ void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo,
  */
 void vmw_bo_pin(struct ttm_buffer_object *bo, bool pin)
 {
-	uint32_t pl_flags;
+	struct ttm_place pl;
 	struct ttm_placement placement;
 	uint32_t old_mem_type = bo->mem.mem_type;
 	int ret;
 
 	lockdep_assert_held(&bo->resv->lock.base);
 
-	pl_flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB
+	pl.fpfn = 0;
+	pl.lpfn = 0;
+	pl.flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB
 		| TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED;
 	if (pin)
-		pl_flags |= TTM_PL_FLAG_NO_EVICT;
+		pl.flags |= TTM_PL_FLAG_NO_EVICT;
 
 	memset(&placement, 0, sizeof(placement));
 	placement.num_placement = 1;
-	placement.placement = &pl_flags;
+	placement.placement = &pl;
 
 	ret = ttm_bo_validate(bo, &placement, false, true);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 18b54acacfbb..7197af157313 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -1418,6 +1418,7 @@ static struct drm_driver driver = {
 	.open = vmw_driver_open,
 	.preclose = vmw_preclose,
 	.postclose = vmw_postclose,
+	.set_busid = drm_pci_set_busid,
 
 	.dumb_create = vmw_dumb_create,
 	.dumb_map_offset = vmw_dumb_map_offset,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 99f731757c4b..4ee799b43d5d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -342,7 +342,6 @@ struct vmw_sw_context{
 	uint32_t *cmd_bounce;
 	uint32_t cmd_bounce_size;
 	struct list_head resource_list;
-	uint32_t fence_flags;
 	struct ttm_buffer_object *cur_query_bo;
 	struct list_head res_relocations;
 	uint32_t *buf_start;
@@ -704,6 +703,7 @@ extern void *vmw_fifo_reserve(struct vmw_private *dev_priv, uint32_t bytes);
 extern void vmw_fifo_commit(struct vmw_private *dev_priv, uint32_t bytes);
 extern int vmw_fifo_send_fence(struct vmw_private *dev_priv,
 			       uint32_t *seqno);
+extern void vmw_fifo_ping_host_locked(struct vmw_private *, uint32_t reason);
 extern void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason);
 extern bool vmw_fifo_have_3d(struct vmw_private *dev_priv);
 extern bool vmw_fifo_have_pitchlock(struct vmw_private *dev_priv);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 36b871686d3c..596cd6dafd33 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -346,13 +346,11 @@ static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context,
 		++sw_context->cur_val_buf;
 		val_buf = &vval_buf->base;
 		val_buf->bo = ttm_bo_reference(bo);
-		val_buf->reserved = false;
+		val_buf->shared = false;
 		list_add_tail(&val_buf->head, &sw_context->validate_nodes);
 		vval_buf->validate_as_mob = validate_as_mob;
 	}
 
-	sw_context->fence_flags |= DRM_VMW_FENCE_FLAG_EXEC;
-
 	if (p_val_node)
 		*p_val_node = val_node;
 
@@ -2337,13 +2335,9 @@ int vmw_execbuf_fence_commands(struct drm_file *file_priv,
 
 	if (p_handle != NULL)
 		ret = vmw_user_fence_create(file_priv, dev_priv->fman,
-					    sequence,
-					    DRM_VMW_FENCE_FLAG_EXEC,
-					    p_fence, p_handle);
+					    sequence, p_fence, p_handle);
 	else
-		ret = vmw_fence_create(dev_priv->fman, sequence,
-				       DRM_VMW_FENCE_FLAG_EXEC,
-				       p_fence);
+		ret = vmw_fence_create(dev_priv->fman, sequence, p_fence);
 
 	if (unlikely(ret != 0 && !synced)) {
 		(void) vmw_fallback_wait(dev_priv, false, false,
@@ -2395,7 +2389,7 @@ vmw_execbuf_copy_fence_user(struct vmw_private *dev_priv,
 		BUG_ON(fence == NULL);
 
 		fence_rep.handle = fence_handle;
-		fence_rep.seqno = fence->seqno;
+		fence_rep.seqno = fence->base.seqno;
 		vmw_update_seqno(dev_priv, &dev_priv->fifo);
 		fence_rep.passed_seqno = dev_priv->last_read_seqno;
 	}
@@ -2416,8 +2410,7 @@ vmw_execbuf_copy_fence_user(struct vmw_private *dev_priv,
 		ttm_ref_object_base_unref(vmw_fp->tfile,
 					  fence_handle, TTM_REF_USAGE);
 		DRM_ERROR("Fence copy error. Syncing.\n");
-		(void) vmw_fence_obj_wait(fence, fence->signal_mask,
-					  false, false,
+		(void) vmw_fence_obj_wait(fence, false, false,
 					  VMW_FENCE_WAIT_TIMEOUT);
 	}
 }
@@ -2469,7 +2462,6 @@ int vmw_execbuf_process(struct drm_file *file_priv,
 	sw_context->fp = vmw_fpriv(file_priv);
 	sw_context->cur_reloc = 0;
 	sw_context->cur_val_buf = 0;
-	sw_context->fence_flags = 0;
 	INIT_LIST_HEAD(&sw_context->resource_list);
 	sw_context->cur_query_bo = dev_priv->pinned_bo;
 	sw_context->last_query_ctx = NULL;
@@ -2495,7 +2487,7 @@ int vmw_execbuf_process(struct drm_file *file_priv,
 	if (unlikely(ret != 0))
 		goto out_err_nores;
 
-	ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes);
+	ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes, true);
 	if (unlikely(ret != 0))
 		goto out_err;
 
@@ -2678,15 +2670,14 @@ void __vmw_execbuf_release_pinned_bo(struct vmw_private *dev_priv,
 	INIT_LIST_HEAD(&validate_list);
 
 	pinned_val.bo = ttm_bo_reference(dev_priv->pinned_bo);
+	pinned_val.shared = false;
 	list_add_tail(&pinned_val.head, &validate_list);
 
 	query_val.bo = ttm_bo_reference(dev_priv->dummy_query_bo);
+	query_val.shared = false;
 	list_add_tail(&query_val.head, &validate_list);
 
-	do {
-		ret = ttm_eu_reserve_buffers(&ticket, &validate_list);
-	} while (ret == -ERESTARTSYS);
-
+	ret = ttm_eu_reserve_buffers(&ticket, &validate_list, false);
 	if (unlikely(ret != 0)) {
 		vmw_execbuf_unpin_panic(dev_priv);
 		goto out_no_reserve;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index b031b48dbb3c..0a474f391fad 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -374,10 +374,16 @@ static int vmw_fb_create_bo(struct vmw_private *vmw_priv,
 			    size_t size, struct vmw_dma_buffer **out)
 {
 	struct vmw_dma_buffer *vmw_bo;
-	struct ttm_placement ne_placement = vmw_vram_ne_placement;
+	struct ttm_place ne_place = vmw_vram_ne_placement.placement[0];
+	struct ttm_placement ne_placement;
 	int ret;
 
-	ne_placement.lpfn = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	ne_placement.num_placement = 1;
+	ne_placement.placement = &ne_place;
+	ne_placement.num_busy_placement = 1;
+	ne_placement.busy_placement = &ne_place;
+
+	ne_place.lpfn = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	(void) ttm_write_lock(&vmw_priv->reservation_sem, false);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 436b013b4231..197164fd7803 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -35,7 +35,7 @@ struct vmw_fence_manager {
 	struct vmw_private *dev_priv;
 	spinlock_t lock;
 	struct list_head fence_list;
-	struct work_struct work;
+	struct work_struct work, ping_work;
 	u32 user_fence_size;
 	u32 fence_size;
 	u32 event_fence_action_size;
@@ -46,6 +46,7 @@ struct vmw_fence_manager {
 	bool goal_irq_on; /* Protected by @goal_irq_mutex */
 	bool seqno_valid; /* Protected by @lock, and may not be set to true
 			     without the @goal_irq_mutex held. */
+	unsigned ctx;
 };
 
 struct vmw_user_fence {
@@ -80,6 +81,12 @@ struct vmw_event_fence_action {
 	uint32_t *tv_usec;
 };
 
+static struct vmw_fence_manager *
+fman_from_fence(struct vmw_fence_obj *fence)
+{
+	return container_of(fence->base.lock, struct vmw_fence_manager, lock);
+}
+
 /**
  * Note on fencing subsystem usage of irqs:
  * Typically the vmw_fences_update function is called
@@ -102,25 +109,143 @@ struct vmw_event_fence_action {
  * objects with actions attached to them.
  */
 
-static void vmw_fence_obj_destroy_locked(struct kref *kref)
+static void vmw_fence_obj_destroy(struct fence *f)
 {
 	struct vmw_fence_obj *fence =
-		container_of(kref, struct vmw_fence_obj, kref);
+		container_of(f, struct vmw_fence_obj, base);
 
-	struct vmw_fence_manager *fman = fence->fman;
-	unsigned int num_fences;
+	struct vmw_fence_manager *fman = fman_from_fence(fence);
+	unsigned long irq_flags;
 
+	spin_lock_irqsave(&fman->lock, irq_flags);
 	list_del_init(&fence->head);
-	num_fences = --fman->num_fence_objects;
-	spin_unlock_irq(&fman->lock);
-	if (fence->destroy)
-		fence->destroy(fence);
-	else
-		kfree(fence);
+	--fman->num_fence_objects;
+	spin_unlock_irqrestore(&fman->lock, irq_flags);
+	fence->destroy(fence);
+}
 
-	spin_lock_irq(&fman->lock);
+static const char *vmw_fence_get_driver_name(struct fence *f)
+{
+	return "vmwgfx";
+}
+
+static const char *vmw_fence_get_timeline_name(struct fence *f)
+{
+	return "svga";
+}
+
+static void vmw_fence_ping_func(struct work_struct *work)
+{
+	struct vmw_fence_manager *fman =
+		container_of(work, struct vmw_fence_manager, ping_work);
+
+	vmw_fifo_ping_host(fman->dev_priv, SVGA_SYNC_GENERIC);
+}
+
+static bool vmw_fence_enable_signaling(struct fence *f)
+{
+	struct vmw_fence_obj *fence =
+		container_of(f, struct vmw_fence_obj, base);
+
+	struct vmw_fence_manager *fman = fman_from_fence(fence);
+	struct vmw_private *dev_priv = fman->dev_priv;
+
+	__le32 __iomem *fifo_mem = dev_priv->mmio_virt;
+	u32 seqno = ioread32(fifo_mem + SVGA_FIFO_FENCE);
+	if (seqno - fence->base.seqno < VMW_FENCE_WRAP)
+		return false;
+
+	if (mutex_trylock(&dev_priv->hw_mutex)) {
+		vmw_fifo_ping_host_locked(dev_priv, SVGA_SYNC_GENERIC);
+		mutex_unlock(&dev_priv->hw_mutex);
+	} else
+		schedule_work(&fman->ping_work);
+
+	return true;
+}
+
+struct vmwgfx_wait_cb {
+	struct fence_cb base;
+	struct task_struct *task;
+};
+
+static void
+vmwgfx_wait_cb(struct fence *fence, struct fence_cb *cb)
+{
+	struct vmwgfx_wait_cb *wait =
+		container_of(cb, struct vmwgfx_wait_cb, base);
+
+	wake_up_process(wait->task);
+}
+
+static void __vmw_fences_update(struct vmw_fence_manager *fman);
+
+static long vmw_fence_wait(struct fence *f, bool intr, signed long timeout)
+{
+	struct vmw_fence_obj *fence =
+		container_of(f, struct vmw_fence_obj, base);
+
+	struct vmw_fence_manager *fman = fman_from_fence(fence);
+	struct vmw_private *dev_priv = fman->dev_priv;
+	struct vmwgfx_wait_cb cb;
+	long ret = timeout;
+	unsigned long irq_flags;
+
+	if (likely(vmw_fence_obj_signaled(fence)))
+		return timeout;
+
+	vmw_fifo_ping_host(dev_priv, SVGA_SYNC_GENERIC);
+	vmw_seqno_waiter_add(dev_priv);
+
+	spin_lock_irqsave(f->lock, irq_flags);
+
+	if (intr && signal_pending(current)) {
+		ret = -ERESTARTSYS;
+		goto out;
+	}
+
+	cb.base.func = vmwgfx_wait_cb;
+	cb.task = current;
+	list_add(&cb.base.node, &f->cb_list);
+
+	while (ret > 0) {
+		__vmw_fences_update(fman);
+		if (test_bit(FENCE_FLAG_SIGNALED_BIT, &f->flags))
+			break;
+
+		if (intr)
+			__set_current_state(TASK_INTERRUPTIBLE);
+		else
+			__set_current_state(TASK_UNINTERRUPTIBLE);
+		spin_unlock_irqrestore(f->lock, irq_flags);
+
+		ret = schedule_timeout(ret);
+
+		spin_lock_irqsave(f->lock, irq_flags);
+		if (ret > 0 && intr && signal_pending(current))
+			ret = -ERESTARTSYS;
+	}
+
+	if (!list_empty(&cb.base.node))
+		list_del(&cb.base.node);
+	__set_current_state(TASK_RUNNING);
+
+out:
+	spin_unlock_irqrestore(f->lock, irq_flags);
+
+	vmw_seqno_waiter_remove(dev_priv);
+
+	return ret;
 }
 
+static struct fence_ops vmw_fence_ops = {
+	.get_driver_name = vmw_fence_get_driver_name,
+	.get_timeline_name = vmw_fence_get_timeline_name,
+	.enable_signaling = vmw_fence_enable_signaling,
+	.wait = vmw_fence_wait,
+	.release = vmw_fence_obj_destroy,
+};
+
 
 /**
  * Execute signal actions on fences recently signaled.
@@ -180,12 +305,14 @@ struct vmw_fence_manager *vmw_fence_manager_init(struct vmw_private *dev_priv)
 	INIT_LIST_HEAD(&fman->fence_list);
 	INIT_LIST_HEAD(&fman->cleanup_list);
 	INIT_WORK(&fman->work, &vmw_fence_work_func);
+	INIT_WORK(&fman->ping_work, &vmw_fence_ping_func);
 	fman->fifo_down = true;
 	fman->user_fence_size = ttm_round_pot(sizeof(struct vmw_user_fence));
 	fman->fence_size = ttm_round_pot(sizeof(struct vmw_fence_obj));
 	fman->event_fence_action_size =
 		ttm_round_pot(sizeof(struct vmw_event_fence_action));
 	mutex_init(&fman->goal_irq_mutex);
+	fman->ctx = fence_context_alloc(1);
 
 	return fman;
 }
@@ -196,6 +323,7 @@ void vmw_fence_manager_takedown(struct vmw_fence_manager *fman)
 	bool lists_empty;
 
 	(void) cancel_work_sync(&fman->work);
+	(void) cancel_work_sync(&fman->ping_work);
 
 	spin_lock_irqsave(&fman->lock, irq_flags);
 	lists_empty = list_empty(&fman->fence_list) &&
@@ -207,23 +335,16 @@ void vmw_fence_manager_takedown(struct vmw_fence_manager *fman)
 }
 
 static int vmw_fence_obj_init(struct vmw_fence_manager *fman,
-			      struct vmw_fence_obj *fence,
-			      u32 seqno,
-			      uint32_t mask,
+			      struct vmw_fence_obj *fence, u32 seqno,
 			      void (*destroy) (struct vmw_fence_obj *fence))
 {
 	unsigned long irq_flags;
-	unsigned int num_fences;
 	int ret = 0;
 
-	fence->seqno = seqno;
+	fence_init(&fence->base, &vmw_fence_ops, &fman->lock,
+		   fman->ctx, seqno);
 	INIT_LIST_HEAD(&fence->seq_passed_actions);
-	fence->fman = fman;
-	fence->signaled = 0;
-	fence->signal_mask = mask;
-	kref_init(&fence->kref);
 	fence->destroy = destroy;
-	init_waitqueue_head(&fence->queue);
 
 	spin_lock_irqsave(&fman->lock, irq_flags);
 	if (unlikely(fman->fifo_down)) {
@@ -231,7 +352,7 @@ static int vmw_fence_obj_init(struct vmw_fence_manager *fman,
 		goto out_unlock;
 	}
 	list_add_tail(&fence->head, &fman->fence_list);
-	num_fences = ++fman->num_fence_objects;
+	++fman->num_fence_objects;
 
 out_unlock:
 	spin_unlock_irqrestore(&fman->lock, irq_flags);
@@ -239,38 +360,6 @@ out_unlock:
 
 }
 
-struct vmw_fence_obj *vmw_fence_obj_reference(struct vmw_fence_obj *fence)
-{
-	if (unlikely(fence == NULL))
-		return NULL;
-
-	kref_get(&fence->kref);
-	return fence;
-}
-
-/**
- * vmw_fence_obj_unreference
- *
- * Note that this function may not be entered with disabled irqs since
- * it may re-enable them in the destroy function.
- *
- */
-void vmw_fence_obj_unreference(struct vmw_fence_obj **fence_p)
-{
-	struct vmw_fence_obj *fence = *fence_p;
-	struct vmw_fence_manager *fman;
-
-	if (unlikely(fence == NULL))
-		return;
-
-	fman = fence->fman;
-	*fence_p = NULL;
-	spin_lock_irq(&fman->lock);
-	BUG_ON(atomic_read(&fence->kref.refcount) == 0);
-	kref_put(&fence->kref, vmw_fence_obj_destroy_locked);
-	spin_unlock_irq(&fman->lock);
-}
-
 static void vmw_fences_perform_actions(struct vmw_fence_manager *fman,
 				struct list_head *list)
 {
@@ -326,7 +415,7 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman,
 	list_for_each_entry(fence, &fman->fence_list, head) {
 		if (!list_empty(&fence->seq_passed_actions)) {
 			fman->seqno_valid = true;
-			iowrite32(fence->seqno,
+			iowrite32(fence->base.seqno,
 				  fifo_mem + SVGA_FIFO_FENCE_GOAL);
 			break;
 		}
@@ -353,27 +442,27 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman,
  */
 static bool vmw_fence_goal_check_locked(struct vmw_fence_obj *fence)
 {
+	struct vmw_fence_manager *fman = fman_from_fence(fence);
 	u32 goal_seqno;
 	__le32 __iomem *fifo_mem;
 
-	if (fence->signaled & DRM_VMW_FENCE_FLAG_EXEC)
+	if (fence_is_signaled_locked(&fence->base))
 		return false;
 
-	fifo_mem = fence->fman->dev_priv->mmio_virt;
+	fifo_mem = fman->dev_priv->mmio_virt;
 	goal_seqno = ioread32(fifo_mem + SVGA_FIFO_FENCE_GOAL);
-	if (likely(fence->fman->seqno_valid &&
-		   goal_seqno - fence->seqno < VMW_FENCE_WRAP))
+	if (likely(fman->seqno_valid &&
+		   goal_seqno - fence->base.seqno < VMW_FENCE_WRAP))
 		return false;
 
-	iowrite32(fence->seqno, fifo_mem + SVGA_FIFO_FENCE_GOAL);
-	fence->fman->seqno_valid = true;
+	iowrite32(fence->base.seqno, fifo_mem + SVGA_FIFO_FENCE_GOAL);
+	fman->seqno_valid = true;
 
 	return true;
 }
 
-void vmw_fences_update(struct vmw_fence_manager *fman)
+static void __vmw_fences_update(struct vmw_fence_manager *fman)
 {
-	unsigned long flags;
 	struct vmw_fence_obj *fence, *next_fence;
 	struct list_head action_list;
 	bool needs_rerun;
@@ -382,32 +471,25 @@ void vmw_fences_update(struct vmw_fence_manager *fman)
 
 	seqno = ioread32(fifo_mem + SVGA_FIFO_FENCE);
 rerun:
-	spin_lock_irqsave(&fman->lock, flags);
 	list_for_each_entry_safe(fence, next_fence, &fman->fence_list, head) {
-		if (seqno - fence->seqno < VMW_FENCE_WRAP) {
+		if (seqno - fence->base.seqno < VMW_FENCE_WRAP) {
 			list_del_init(&fence->head);
-			fence->signaled |= DRM_VMW_FENCE_FLAG_EXEC;
+			fence_signal_locked(&fence->base);
 			INIT_LIST_HEAD(&action_list);
 			list_splice_init(&fence->seq_passed_actions,
 					 &action_list);
 			vmw_fences_perform_actions(fman, &action_list);
-			wake_up_all(&fence->queue);
 		} else
 			break;
 	}
 
-	needs_rerun = vmw_fence_goal_new_locked(fman, seqno);
-
-	if (!list_empty(&fman->cleanup_list))
-		(void) schedule_work(&fman->work);
-	spin_unlock_irqrestore(&fman->lock, flags);
-
 	/*
 	 * Rerun if the fence goal seqno was updated, and the
 	 * hardware might have raced with that update, so that
 	 * we missed a fence_goal irq.
 	 */
 
+	needs_rerun = vmw_fence_goal_new_locked(fman, seqno);
 	if (unlikely(needs_rerun)) {
 		new_seqno = ioread32(fifo_mem + SVGA_FIFO_FENCE);
 		if (new_seqno != seqno) {
@@ -415,79 +497,58 @@ rerun:
 			goto rerun;
 		}
 	}
+
+	if (!list_empty(&fman->cleanup_list))
+		(void) schedule_work(&fman->work);
 }
 
-bool vmw_fence_obj_signaled(struct vmw_fence_obj *fence,
-			    uint32_t flags)
+void vmw_fences_update(struct vmw_fence_manager *fman)
 {
-	struct vmw_fence_manager *fman = fence->fman;
 	unsigned long irq_flags;
-	uint32_t signaled;
 
 	spin_lock_irqsave(&fman->lock, irq_flags);
-	signaled = fence->signaled;
+	__vmw_fences_update(fman);
 	spin_unlock_irqrestore(&fman->lock, irq_flags);
+}
 
-	flags &= fence->signal_mask;
-	if ((signaled & flags) == flags)
-		return 1;
+bool vmw_fence_obj_signaled(struct vmw_fence_obj *fence)
+{
+	struct vmw_fence_manager *fman = fman_from_fence(fence);
 
-	if ((signaled & DRM_VMW_FENCE_FLAG_EXEC) == 0)
-		vmw_fences_update(fman);
+	if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->base.flags))
+		return 1;
 
-	spin_lock_irqsave(&fman->lock, irq_flags);
-	signaled = fence->signaled;
-	spin_unlock_irqrestore(&fman->lock, irq_flags);
+	vmw_fences_update(fman);
 
-	return ((signaled & flags) == flags);
+	return fence_is_signaled(&fence->base);
 }
 
-int vmw_fence_obj_wait(struct vmw_fence_obj *fence,
-		       uint32_t flags, bool lazy,
+int vmw_fence_obj_wait(struct vmw_fence_obj *fence, bool lazy,
 		       bool interruptible, unsigned long timeout)
 {
-	struct vmw_private *dev_priv = fence->fman->dev_priv;
-	long ret;
+	long ret = fence_wait_timeout(&fence->base, interruptible, timeout);
 
-	if (likely(vmw_fence_obj_signaled(fence, flags)))
+	if (likely(ret > 0))
 		return 0;
-
-	vmw_fifo_ping_host(dev_priv, SVGA_SYNC_GENERIC);
-	vmw_seqno_waiter_add(dev_priv);
-
-	if (interruptible)
-		ret = wait_event_interruptible_timeout
-			(fence->queue,
-			 vmw_fence_obj_signaled(fence, flags),
-			 timeout);
+	else if (ret == 0)
+		return -EBUSY;
 	else
-		ret = wait_event_timeout
-			(fence->queue,
-			 vmw_fence_obj_signaled(fence, flags),
-			 timeout);
-
-	vmw_seqno_waiter_remove(dev_priv);
-
-	if (unlikely(ret == 0))
-		ret = -EBUSY;
-	else if (likely(ret > 0))
-		ret = 0;
-
-	return ret;
+		return ret;
 }
 
 void vmw_fence_obj_flush(struct vmw_fence_obj *fence)
 {
-	struct vmw_private *dev_priv = fence->fman->dev_priv;
+	struct vmw_private *dev_priv = fman_from_fence(fence)->dev_priv;
 
 	vmw_fifo_ping_host(dev_priv, SVGA_SYNC_GENERIC);
 }
 
 static void vmw_fence_destroy(struct vmw_fence_obj *fence)
 {
-	struct vmw_fence_manager *fman = fence->fman;
+	struct vmw_fence_manager *fman = fman_from_fence(fence);
+
+	fence_free(&fence->base);
 
-	kfree(fence);
 	/*
 	 * Free kernel space accounting.
 	 */
@@ -497,7 +558,6 @@ static void vmw_fence_destroy(struct vmw_fence_obj *fence)
 
 int vmw_fence_create(struct vmw_fence_manager *fman,
 		     uint32_t seqno,
-		     uint32_t mask,
 		     struct vmw_fence_obj **p_fence)
 {
 	struct ttm_mem_global *mem_glob = vmw_mem_glob(fman->dev_priv);
@@ -515,7 +575,7 @@ int vmw_fence_create(struct vmw_fence_manager *fman,
 		goto out_no_object;
 	}
 
-	ret = vmw_fence_obj_init(fman, fence, seqno, mask,
+	ret = vmw_fence_obj_init(fman, fence, seqno,
 				 vmw_fence_destroy);
 	if (unlikely(ret != 0))
 		goto out_err_init;
@@ -535,7 +595,7 @@ static void vmw_user_fence_destroy(struct vmw_fence_obj *fence)
 {
 	struct vmw_user_fence *ufence =
 		container_of(fence, struct vmw_user_fence, fence);
-	struct vmw_fence_manager *fman = fence->fman;
+	struct vmw_fence_manager *fman = fman_from_fence(fence);
 
 	ttm_base_object_kfree(ufence, base);
 	/*
@@ -559,7 +619,6 @@ static void vmw_user_fence_base_release(struct ttm_base_object **p_base)
 int vmw_user_fence_create(struct drm_file *file_priv,
 			  struct vmw_fence_manager *fman,
 			  uint32_t seqno,
-			  uint32_t mask,
 			  struct vmw_fence_obj **p_fence,
 			  uint32_t *p_handle)
 {
@@ -586,7 +645,7 @@ int vmw_user_fence_create(struct drm_file *file_priv,
 	}
 
 	ret = vmw_fence_obj_init(fman, &ufence->fence, seqno,
-				 mask, vmw_user_fence_destroy);
+				 vmw_user_fence_destroy);
 	if (unlikely(ret != 0)) {
 		kfree(ufence);
 		goto out_no_object;
@@ -629,7 +688,6 @@ out_no_object:
 
 void vmw_fence_fifo_down(struct vmw_fence_manager *fman)
 {
-	unsigned long irq_flags;
 	struct list_head action_list;
 	int ret;
 
@@ -638,35 +696,32 @@ void vmw_fence_fifo_down(struct vmw_fence_manager *fman)
 	 * restart when we've released the fman->lock.
 	 */
 
-	spin_lock_irqsave(&fman->lock, irq_flags);
+	spin_lock_irq(&fman->lock);
 	fman->fifo_down = true;
 	while (!list_empty(&fman->fence_list)) {
 		struct vmw_fence_obj *fence =
 			list_entry(fman->fence_list.prev, struct vmw_fence_obj,
 				   head);
-		kref_get(&fence->kref);
+		fence_get(&fence->base);
 		spin_unlock_irq(&fman->lock);
 
-		ret = vmw_fence_obj_wait(fence, fence->signal_mask,
-					 false, false,
+		ret = vmw_fence_obj_wait(fence, false, false,
 					 VMW_FENCE_WAIT_TIMEOUT);
 
 		if (unlikely(ret != 0)) {
 			list_del_init(&fence->head);
-			fence->signaled |= DRM_VMW_FENCE_FLAG_EXEC;
+			fence_signal(&fence->base);
 			INIT_LIST_HEAD(&action_list);
 			list_splice_init(&fence->seq_passed_actions,
 					 &action_list);
 			vmw_fences_perform_actions(fman, &action_list);
-			wake_up_all(&fence->queue);
 		}
 
-		spin_lock_irq(&fman->lock);
-
 		BUG_ON(!list_empty(&fence->head));
-		kref_put(&fence->kref, vmw_fence_obj_destroy_locked);
+		fence_put(&fence->base);
+		spin_lock_irq(&fman->lock);
 	}
-	spin_unlock_irqrestore(&fman->lock, irq_flags);
+	spin_unlock_irq(&fman->lock);
 }
 
 void vmw_fence_fifo_up(struct vmw_fence_manager *fman)
@@ -716,14 +771,14 @@ int vmw_fence_obj_wait_ioctl(struct drm_device *dev, void *data,
 
 	timeout = jiffies;
 	if (time_after_eq(timeout, (unsigned long)arg->kernel_cookie)) {
-		ret = ((vmw_fence_obj_signaled(fence, arg->flags)) ?
+		ret = ((vmw_fence_obj_signaled(fence)) ?
 		       0 : -EBUSY);
 		goto out;
 	}
 
 	timeout = (unsigned long)arg->kernel_cookie - timeout;
 
-	ret = vmw_fence_obj_wait(fence, arg->flags, arg->lazy, true, timeout);
+	ret = vmw_fence_obj_wait(fence, arg->lazy, true, timeout);
 
 out:
 	ttm_base_object_unref(&base);
@@ -758,12 +813,12 @@ int vmw_fence_obj_signaled_ioctl(struct drm_device *dev, void *data,
 	}
 
 	fence = &(container_of(base, struct vmw_user_fence, base)->fence);
-	fman = fence->fman;
+	fman = fman_from_fence(fence);
 
-	arg->signaled = vmw_fence_obj_signaled(fence, arg->flags);
-	spin_lock_irq(&fman->lock);
+	arg->signaled = vmw_fence_obj_signaled(fence);
 
-	arg->signaled_flags = fence->signaled;
+	arg->signaled_flags = arg->flags;
+	spin_lock_irq(&fman->lock);
 	arg->passed_seqno = dev_priv->last_read_seqno;
 	spin_unlock_irq(&fman->lock);
 
@@ -876,7 +931,7 @@ static void vmw_event_fence_action_cleanup(struct vmw_fence_action *action)
 {
 	struct vmw_event_fence_action *eaction =
 		container_of(action, struct vmw_event_fence_action, action);
-	struct vmw_fence_manager *fman = eaction->fence->fman;
+	struct vmw_fence_manager *fman = fman_from_fence(eaction->fence);
 	unsigned long irq_flags;
 
 	spin_lock_irqsave(&fman->lock, irq_flags);
@@ -900,7 +955,7 @@ static void vmw_event_fence_action_cleanup(struct vmw_fence_action *action)
 static void vmw_fence_obj_add_action(struct vmw_fence_obj *fence,
 			      struct vmw_fence_action *action)
 {
-	struct vmw_fence_manager *fman = fence->fman;
+	struct vmw_fence_manager *fman = fman_from_fence(fence);
 	unsigned long irq_flags;
 	bool run_update = false;
 
@@ -908,7 +963,7 @@ static void vmw_fence_obj_add_action(struct vmw_fence_obj *fence,
 	spin_lock_irqsave(&fman->lock, irq_flags);
 
 	fman->pending_actions[action->type]++;
-	if (fence->signaled & DRM_VMW_FENCE_FLAG_EXEC) {
+	if (fence_is_signaled_locked(&fence->base)) {
 		struct list_head action_list;
 
 		INIT_LIST_HEAD(&action_list);
@@ -960,7 +1015,7 @@ int vmw_event_fence_action_queue(struct drm_file *file_priv,
 				 bool interruptible)
 {
 	struct vmw_event_fence_action *eaction;
-	struct vmw_fence_manager *fman = fence->fman;
+	struct vmw_fence_manager *fman = fman_from_fence(fence);
 	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
 	unsigned long irq_flags;
 
@@ -1000,7 +1055,8 @@ static int vmw_event_fence_action_create(struct drm_file *file_priv,
 				  bool interruptible)
 {
 	struct vmw_event_fence_pending *event;
-	struct drm_device *dev = fence->fman->dev_priv->dev;
+	struct vmw_fence_manager *fman = fman_from_fence(fence);
+	struct drm_device *dev = fman->dev_priv->dev;
 	unsigned long irq_flags;
 	int ret;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h
index faf2e7873860..26a4add39208 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h
@@ -27,6 +27,8 @@
 
 #ifndef _VMWGFX_FENCE_H_
 
+#include <linux/fence.h>
+
 #define VMW_FENCE_WAIT_TIMEOUT (5*HZ)
 
 struct vmw_private;
@@ -50,16 +52,11 @@ struct vmw_fence_action {
 };
 
 struct vmw_fence_obj {
-	struct kref kref;
-	u32 seqno;
+	struct fence base;
 
-	struct vmw_fence_manager *fman;
 	struct list_head head;
-	uint32_t signaled;
-	uint32_t signal_mask;
 	struct list_head seq_passed_actions;
 	void (*destroy)(struct vmw_fence_obj *fence);
-	wait_queue_head_t queue;
 };
 
 extern struct vmw_fence_manager *
@@ -67,17 +64,29 @@ vmw_fence_manager_init(struct vmw_private *dev_priv);
 
 extern void vmw_fence_manager_takedown(struct vmw_fence_manager *fman);
 
-extern void vmw_fence_obj_unreference(struct vmw_fence_obj **fence_p);
+static inline void
+vmw_fence_obj_unreference(struct vmw_fence_obj **fence_p)
+{
+	struct vmw_fence_obj *fence = *fence_p;
+
+	*fence_p = NULL;
+	if (fence)
+		fence_put(&fence->base);
+}
 
-extern struct vmw_fence_obj *
-vmw_fence_obj_reference(struct vmw_fence_obj *fence);
+static inline struct vmw_fence_obj *
+vmw_fence_obj_reference(struct vmw_fence_obj *fence)
+{
+	if (fence)
+		fence_get(&fence->base);
+	return fence;
+}
 
 extern void vmw_fences_update(struct vmw_fence_manager *fman);
 
-extern bool vmw_fence_obj_signaled(struct vmw_fence_obj *fence,
-				   uint32_t flags);
+extern bool vmw_fence_obj_signaled(struct vmw_fence_obj *fence);
 
-extern int vmw_fence_obj_wait(struct vmw_fence_obj *fence, uint32_t flags,
+extern int vmw_fence_obj_wait(struct vmw_fence_obj *fence,
 			      bool lazy,
 			      bool interruptible, unsigned long timeout);
 
@@ -85,13 +94,11 @@ extern void vmw_fence_obj_flush(struct vmw_fence_obj *fence);
 
 extern int vmw_fence_create(struct vmw_fence_manager *fman,
 			    uint32_t seqno,
-			    uint32_t mask,
 			    struct vmw_fence_obj **p_fence);
 
 extern int vmw_user_fence_create(struct drm_file *file_priv,
 				 struct vmw_fence_manager *fman,
 				 uint32_t sequence,
-				 uint32_t mask,
 				 struct vmw_fence_obj **p_fence,
 				 uint32_t *p_handle);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index 6eae14d2a3f7..09e10aefcd8e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -160,16 +160,21 @@ int vmw_fifo_init(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo)
 	return vmw_fifo_send_fence(dev_priv, &dummy);
 }
 
-void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason)
+void vmw_fifo_ping_host_locked(struct vmw_private *dev_priv, uint32_t reason)
 {
 	__le32 __iomem *fifo_mem = dev_priv->mmio_virt;
 
-	mutex_lock(&dev_priv->hw_mutex);
-
 	if (unlikely(ioread32(fifo_mem + SVGA_FIFO_BUSY) == 0)) {
 		iowrite32(1, fifo_mem + SVGA_FIFO_BUSY);
 		vmw_write(dev_priv, SVGA_REG_SYNC, reason);
 	}
+}
+
+void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason)
+{
+	mutex_lock(&dev_priv->hw_mutex);
+
+	vmw_fifo_ping_host_locked(dev_priv, reason);
 
 	mutex_unlock(&dev_priv->hw_mutex);
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index 26f8bdde3529..170b61be1e4e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -46,8 +46,7 @@ struct vmwgfx_gmrid_man {
 
 static int vmw_gmrid_man_get_node(struct ttm_mem_type_manager *man,
 				  struct ttm_buffer_object *bo,
-				  struct ttm_placement *placement,
-				  uint32_t flags,
+				  const struct ttm_place *place,
 				  struct ttm_mem_reg *mem)
 {
 	struct vmwgfx_gmrid_man *gman =
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index a432c0db257c..026de7cea0f6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -133,6 +133,7 @@ static void vmw_resource_release(struct kref *kref)
 			struct ttm_validate_buffer val_buf;
 
 			val_buf.bo = bo;
+			val_buf.shared = false;
 			res->func->unbind(res, false, &val_buf);
 		}
 		res->backup_dirty = false;
@@ -429,7 +430,7 @@ int vmw_dmabuf_init(struct vmw_private *dev_priv,
 	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
 			  ttm_bo_type_device, placement,
 			  0, interruptible,
-			  NULL, acc_size, NULL, bo_free);
+			  NULL, acc_size, NULL, NULL, bo_free);
 	return ret;
 }
 
@@ -567,13 +568,18 @@ static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo,
 	int ret;
 
 	if (flags & drm_vmw_synccpu_allow_cs) {
-		struct ttm_bo_device *bdev = bo->bdev;
+		bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
+		long lret;
 
-		spin_lock(&bdev->fence_lock);
-		ret = ttm_bo_wait(bo, false, true,
-				  !!(flags & drm_vmw_synccpu_dontblock));
-		spin_unlock(&bdev->fence_lock);
-		return ret;
+		if (nonblock)
+			return reservation_object_test_signaled_rcu(bo->resv, true) ? 0 : -EBUSY;
+
+		lret = reservation_object_wait_timeout_rcu(bo->resv, true, true, MAX_SCHEDULE_TIMEOUT);
+		if (!lret)
+			return -EBUSY;
+		else if (lret < 0)
+			return lret;
+		return 0;
 	}
 
 	ret = ttm_bo_synccpu_write_grab
@@ -1214,8 +1220,9 @@ vmw_resource_check_buffer(struct vmw_resource *res,
 
 	INIT_LIST_HEAD(&val_list);
 	val_buf->bo = ttm_bo_reference(&res->backup->base);
+	val_buf->shared = false;
 	list_add_tail(&val_buf->head, &val_list);
-	ret = ttm_eu_reserve_buffers(NULL, &val_list);
+	ret = ttm_eu_reserve_buffers(NULL, &val_list, interruptible);
 	if (unlikely(ret != 0))
 		goto out_no_reserve;
 
@@ -1307,6 +1314,7 @@ int vmw_resource_do_evict(struct vmw_resource *res, bool interruptible)
 	BUG_ON(!func->may_evict);
 
 	val_buf.bo = NULL;
+	val_buf.shared = false;
 	ret = vmw_resource_check_buffer(res, interruptible, &val_buf);
 	if (unlikely(ret != 0))
 		return ret;
@@ -1352,6 +1360,7 @@ int vmw_resource_validate(struct vmw_resource *res)
 		return 0;
 
 	val_buf.bo = NULL;
+	val_buf.shared = false;
 	if (res->backup)
 		val_buf.bo = &res->backup->base;
 	do {
@@ -1419,25 +1428,16 @@ void vmw_fence_single_bo(struct ttm_buffer_object *bo,
 			 struct vmw_fence_obj *fence)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_bo_driver *driver = bdev->driver;
-	struct vmw_fence_obj *old_fence_obj;
+
 	struct vmw_private *dev_priv =
 		container_of(bdev, struct vmw_private, bdev);
 
-	if (fence == NULL)
+	if (fence == NULL) {
 		vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-	else
-		driver->sync_obj_ref(fence);
-
-	spin_lock(&bdev->fence_lock);
-
-	old_fence_obj = bo->sync_obj;
-	bo->sync_obj = fence;
-
-	spin_unlock(&bdev->fence_lock);
-
-	if (old_fence_obj)
-		vmw_fence_obj_unreference(&old_fence_obj);
+		reservation_object_add_excl_fence(bo->resv, &fence->base);
+		fence_put(&fence->base);
+	} else
+		reservation_object_add_excl_fence(bo->resv, &fence->base);
 }
 
 /**
@@ -1475,10 +1475,10 @@ void vmw_resource_move_notify(struct ttm_buffer_object *bo,
 
 	if (mem->mem_type != VMW_PL_MOB) {
 		struct vmw_resource *res, *n;
-		struct ttm_bo_device *bdev = bo->bdev;
 		struct ttm_validate_buffer val_buf;
 
 		val_buf.bo = bo;
+		val_buf.shared = false;
 
 		list_for_each_entry_safe(res, n, &dma_buf->res_list, mob_head) {
 
@@ -1491,9 +1491,7 @@ void vmw_resource_move_notify(struct ttm_buffer_object *bo,
 			list_del_init(&res->mob_head);
 		}
 
-		spin_lock(&bdev->fence_lock);
 		(void) ttm_bo_wait(bo, false, false, false);
-		spin_unlock(&bdev->fence_lock);
 	}
 }
 
diff --git a/drivers/gpu/ipu-v3/Kconfig b/drivers/gpu/ipu-v3/Kconfig
index 2f228a2f2a48..aefdff95356d 100644
--- a/drivers/gpu/ipu-v3/Kconfig
+++ b/drivers/gpu/ipu-v3/Kconfig
@@ -1,7 +1,8 @@
 config IMX_IPUV3_CORE
 	tristate "IPUv3 core support"
-	depends on SOC_IMX5 || SOC_IMX6Q || SOC_IMX6SL || ARCH_MULTIPLATFORM
+	depends on SOC_IMX5 || SOC_IMX6Q || ARCH_MULTIPLATFORM
 	depends on RESET_CONTROLLER
+	select GENERIC_IRQ_CHIP
 	help
 	  Choose this if you have a i.MX5/6 system and want to use the Image
 	  Processing Unit. This option only enables IPU base support.
diff --git a/drivers/gpu/ipu-v3/Makefile b/drivers/gpu/ipu-v3/Makefile
index 0b42836caae1..107ec236a4a6 100644
--- a/drivers/gpu/ipu-v3/Makefile
+++ b/drivers/gpu/ipu-v3/Makefile
@@ -1,4 +1,4 @@
 obj-$(CONFIG_IMX_IPUV3_CORE) += imx-ipu-v3.o
 
-imx-ipu-v3-objs := ipu-common.o ipu-cpmem.o ipu-dc.o ipu-di.o \
-		ipu-dp.o ipu-dmfc.o ipu-smfc.o
+imx-ipu-v3-objs := ipu-common.o ipu-cpmem.o ipu-csi.o ipu-dc.o ipu-di.o \
+		ipu-dp.o ipu-dmfc.o ipu-ic.o ipu-smfc.o
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 5978e7aab8ed..f707d25ae78f 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -74,6 +74,12 @@ enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc)
 	case DRM_FORMAT_UYVY:
 	case DRM_FORMAT_YUV420:
 	case DRM_FORMAT_YVU420:
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YVU422:
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV61:
 		return IPUV3_COLORSPACE_YUV;
 	default:
 		return IPUV3_COLORSPACE_UNKNOWN;
@@ -86,8 +92,13 @@ enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat)
 	switch (pixelformat) {
 	case V4L2_PIX_FMT_YUV420:
 	case V4L2_PIX_FMT_YVU420:
+	case V4L2_PIX_FMT_YUV422P:
 	case V4L2_PIX_FMT_UYVY:
 	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
 		return IPUV3_COLORSPACE_YUV;
 	case V4L2_PIX_FMT_RGB32:
 	case V4L2_PIX_FMT_BGR32:
@@ -101,6 +112,135 @@ enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat)
 }
 EXPORT_SYMBOL_GPL(ipu_pixelformat_to_colorspace);
 
+bool ipu_pixelformat_is_planar(u32 pixelformat)
+{
+	switch (pixelformat) {
+	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_YVU420:
+	case V4L2_PIX_FMT_YUV422P:
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(ipu_pixelformat_is_planar);
+
+enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code)
+{
+	switch (mbus_code & 0xf000) {
+	case 0x1000:
+		return IPUV3_COLORSPACE_RGB;
+	case 0x2000:
+		return IPUV3_COLORSPACE_YUV;
+	default:
+		return IPUV3_COLORSPACE_UNKNOWN;
+	}
+}
+EXPORT_SYMBOL_GPL(ipu_mbus_code_to_colorspace);
+
+int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat)
+{
+	switch (pixelformat) {
+	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_YVU420:
+	case V4L2_PIX_FMT_YUV422P:
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		/*
+		 * for the planar YUV formats, the stride passed to
+		 * cpmem must be the stride in bytes of the Y plane.
+		 * And all the planar YUV formats have an 8-bit
+		 * Y component.
+		 */
+		return (8 * pixel_stride) >> 3;
+	case V4L2_PIX_FMT_RGB565:
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_UYVY:
+		return (16 * pixel_stride) >> 3;
+	case V4L2_PIX_FMT_BGR24:
+	case V4L2_PIX_FMT_RGB24:
+		return (24 * pixel_stride) >> 3;
+	case V4L2_PIX_FMT_BGR32:
+	case V4L2_PIX_FMT_RGB32:
+		return (32 * pixel_stride) >> 3;
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(ipu_stride_to_bytes);
+
+int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
+			    bool hflip, bool vflip)
+{
+	u32 r90, vf, hf;
+
+	switch (degrees) {
+	case 0:
+		vf = hf = r90 = 0;
+		break;
+	case 90:
+		vf = hf = 0;
+		r90 = 1;
+		break;
+	case 180:
+		vf = hf = 1;
+		r90 = 0;
+		break;
+	case 270:
+		vf = hf = r90 = 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	hf ^= (u32)hflip;
+	vf ^= (u32)vflip;
+
+	*mode = (enum ipu_rotate_mode)((r90 << 2) | (hf << 1) | vf);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_degrees_to_rot_mode);
+
+int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode,
+			    bool hflip, bool vflip)
+{
+	u32 r90, vf, hf;
+
+	r90 = ((u32)mode >> 2) & 0x1;
+	hf = ((u32)mode >> 1) & 0x1;
+	vf = ((u32)mode >> 0) & 0x1;
+	hf ^= (u32)hflip;
+	vf ^= (u32)vflip;
+
+	switch ((enum ipu_rotate_mode)((r90 << 2) | (hf << 1) | vf)) {
+	case IPU_ROTATE_NONE:
+		*degrees = 0;
+		break;
+	case IPU_ROTATE_90_RIGHT:
+		*degrees = 90;
+		break;
+	case IPU_ROTATE_180:
+		*degrees = 180;
+		break;
+	case IPU_ROTATE_90_LEFT:
+		*degrees = 270;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_rot_mode_to_degrees);
+
 struct ipuv3_channel *ipu_idmac_get(struct ipu_soc *ipu, unsigned num)
 {
 	struct ipuv3_channel *channel;
@@ -143,7 +283,26 @@ void ipu_idmac_put(struct ipuv3_channel *channel)
 }
 EXPORT_SYMBOL_GPL(ipu_idmac_put);
 
-#define idma_mask(ch)			(1 << (ch & 0x1f))
+#define idma_mask(ch)			(1 << ((ch) & 0x1f))
+
+/*
+ * This is an undocumented feature, a write one to a channel bit in
+ * IPU_CHA_CUR_BUF and IPU_CHA_TRIPLE_CUR_BUF will reset the channel's
+ * internal current buffer pointer so that transfers start from buffer
+ * 0 on the next channel enable (that's the theory anyway, the imx6 TRM
+ * only says these are read-only registers). This operation is required
+ * for channel linking to work correctly, for instance video capture
+ * pipelines that carry out image rotations will fail after the first
+ * streaming unless this function is called for each channel before
+ * re-enabling the channels.
+ */
+static void __ipu_idmac_reset_current_buffer(struct ipuv3_channel *channel)
+{
+	struct ipu_soc *ipu = channel->ipu;
+	unsigned int chno = channel->num;
+
+	ipu_cm_write(ipu, idma_mask(chno), IPU_CHA_CUR_BUF(chno));
+}
 
 void ipu_idmac_set_double_buffer(struct ipuv3_channel *channel,
 		bool doublebuffer)
@@ -161,10 +320,81 @@ void ipu_idmac_set_double_buffer(struct ipuv3_channel *channel,
 		reg &= ~idma_mask(channel->num);
 	ipu_cm_write(ipu, reg, IPU_CHA_DB_MODE_SEL(channel->num));
 
+	__ipu_idmac_reset_current_buffer(channel);
+
 	spin_unlock_irqrestore(&ipu->lock, flags);
 }
 EXPORT_SYMBOL_GPL(ipu_idmac_set_double_buffer);
 
+static const struct {
+	int chnum;
+	u32 reg;
+	int shift;
+} idmac_lock_en_info[] = {
+	{ .chnum =  5, .reg = IDMAC_CH_LOCK_EN_1, .shift =  0, },
+	{ .chnum = 11, .reg = IDMAC_CH_LOCK_EN_1, .shift =  2, },
+	{ .chnum = 12, .reg = IDMAC_CH_LOCK_EN_1, .shift =  4, },
+	{ .chnum = 14, .reg = IDMAC_CH_LOCK_EN_1, .shift =  6, },
+	{ .chnum = 15, .reg = IDMAC_CH_LOCK_EN_1, .shift =  8, },
+	{ .chnum = 20, .reg = IDMAC_CH_LOCK_EN_1, .shift = 10, },
+	{ .chnum = 21, .reg = IDMAC_CH_LOCK_EN_1, .shift = 12, },
+	{ .chnum = 22, .reg = IDMAC_CH_LOCK_EN_1, .shift = 14, },
+	{ .chnum = 23, .reg = IDMAC_CH_LOCK_EN_1, .shift = 16, },
+	{ .chnum = 27, .reg = IDMAC_CH_LOCK_EN_1, .shift = 18, },
+	{ .chnum = 28, .reg = IDMAC_CH_LOCK_EN_1, .shift = 20, },
+	{ .chnum = 45, .reg = IDMAC_CH_LOCK_EN_2, .shift =  0, },
+	{ .chnum = 46, .reg = IDMAC_CH_LOCK_EN_2, .shift =  2, },
+	{ .chnum = 47, .reg = IDMAC_CH_LOCK_EN_2, .shift =  4, },
+	{ .chnum = 48, .reg = IDMAC_CH_LOCK_EN_2, .shift =  6, },
+	{ .chnum = 49, .reg = IDMAC_CH_LOCK_EN_2, .shift =  8, },
+	{ .chnum = 50, .reg = IDMAC_CH_LOCK_EN_2, .shift = 10, },
+};
+
+int ipu_idmac_lock_enable(struct ipuv3_channel *channel, int num_bursts)
+{
+	struct ipu_soc *ipu = channel->ipu;
+	unsigned long flags;
+	u32 bursts, regval;
+	int i;
+
+	switch (num_bursts) {
+	case 0:
+	case 1:
+		bursts = 0x00; /* locking disabled */
+		break;
+	case 2:
+		bursts = 0x01;
+		break;
+	case 4:
+		bursts = 0x02;
+		break;
+	case 8:
+		bursts = 0x03;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(idmac_lock_en_info); i++) {
+		if (channel->num == idmac_lock_en_info[i].chnum)
+			break;
+	}
+	if (i >= ARRAY_SIZE(idmac_lock_en_info))
+		return -EINVAL;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+
+	regval = ipu_idmac_read(ipu, idmac_lock_en_info[i].reg);
+	regval &= ~(0x03 << idmac_lock_en_info[i].shift);
+	regval |= (bursts << idmac_lock_en_info[i].shift);
+	ipu_idmac_write(ipu, regval, idmac_lock_en_info[i].reg);
+
+	spin_unlock_irqrestore(&ipu->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_idmac_lock_enable);
+
 int ipu_module_enable(struct ipu_soc *ipu, u32 mask)
 {
 	unsigned long lock_flags;
@@ -217,30 +447,6 @@ int ipu_module_disable(struct ipu_soc *ipu, u32 mask)
 }
 EXPORT_SYMBOL_GPL(ipu_module_disable);
 
-int ipu_csi_enable(struct ipu_soc *ipu, int csi)
-{
-	return ipu_module_enable(ipu, csi ? IPU_CONF_CSI1_EN : IPU_CONF_CSI0_EN);
-}
-EXPORT_SYMBOL_GPL(ipu_csi_enable);
-
-int ipu_csi_disable(struct ipu_soc *ipu, int csi)
-{
-	return ipu_module_disable(ipu, csi ? IPU_CONF_CSI1_EN : IPU_CONF_CSI0_EN);
-}
-EXPORT_SYMBOL_GPL(ipu_csi_disable);
-
-int ipu_smfc_enable(struct ipu_soc *ipu)
-{
-	return ipu_module_enable(ipu, IPU_CONF_SMFC_EN);
-}
-EXPORT_SYMBOL_GPL(ipu_smfc_enable);
-
-int ipu_smfc_disable(struct ipu_soc *ipu)
-{
-	return ipu_module_disable(ipu, IPU_CONF_SMFC_EN);
-}
-EXPORT_SYMBOL_GPL(ipu_smfc_disable);
-
 int ipu_idmac_get_current_buffer(struct ipuv3_channel *channel)
 {
 	struct ipu_soc *ipu = channel->ipu;
@@ -250,6 +456,30 @@ int ipu_idmac_get_current_buffer(struct ipuv3_channel *channel)
 }
 EXPORT_SYMBOL_GPL(ipu_idmac_get_current_buffer);
 
+bool ipu_idmac_buffer_is_ready(struct ipuv3_channel *channel, u32 buf_num)
+{
+	struct ipu_soc *ipu = channel->ipu;
+	unsigned long flags;
+	u32 reg = 0;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+	switch (buf_num) {
+	case 0:
+		reg = ipu_cm_read(ipu, IPU_CHA_BUF0_RDY(channel->num));
+		break;
+	case 1:
+		reg = ipu_cm_read(ipu, IPU_CHA_BUF1_RDY(channel->num));
+		break;
+	case 2:
+		reg = ipu_cm_read(ipu, IPU_CHA_BUF2_RDY(channel->num));
+		break;
+	}
+	spin_unlock_irqrestore(&ipu->lock, flags);
+
+	return ((reg & idma_mask(channel->num)) != 0);
+}
+EXPORT_SYMBOL_GPL(ipu_idmac_buffer_is_ready);
+
 void ipu_idmac_select_buffer(struct ipuv3_channel *channel, u32 buf_num)
 {
 	struct ipu_soc *ipu = channel->ipu;
@@ -268,6 +498,34 @@ void ipu_idmac_select_buffer(struct ipuv3_channel *channel, u32 buf_num)
 }
 EXPORT_SYMBOL_GPL(ipu_idmac_select_buffer);
 
+void ipu_idmac_clear_buffer(struct ipuv3_channel *channel, u32 buf_num)
+{
+	struct ipu_soc *ipu = channel->ipu;
+	unsigned int chno = channel->num;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+
+	ipu_cm_write(ipu, 0xF0300000, IPU_GPR); /* write one to clear */
+	switch (buf_num) {
+	case 0:
+		ipu_cm_write(ipu, idma_mask(chno), IPU_CHA_BUF0_RDY(chno));
+		break;
+	case 1:
+		ipu_cm_write(ipu, idma_mask(chno), IPU_CHA_BUF1_RDY(chno));
+		break;
+	case 2:
+		ipu_cm_write(ipu, idma_mask(chno), IPU_CHA_BUF2_RDY(chno));
+		break;
+	default:
+		break;
+	}
+	ipu_cm_write(ipu, 0x0, IPU_GPR); /* write one to set */
+
+	spin_unlock_irqrestore(&ipu->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_idmac_clear_buffer);
+
 int ipu_idmac_enable_channel(struct ipuv3_channel *channel)
 {
 	struct ipu_soc *ipu = channel->ipu;
@@ -338,6 +596,8 @@ int ipu_idmac_disable_channel(struct ipuv3_channel *channel)
 	val &= ~idma_mask(channel->num);
 	ipu_idmac_write(ipu, val, IDMAC_CHA_EN(channel->num));
 
+	__ipu_idmac_reset_current_buffer(channel);
+
 	/* Set channel buffers NOT to be ready */
 	ipu_cm_write(ipu, 0xf0000000, IPU_GPR); /* write one to clear */
 
@@ -366,6 +626,31 @@ int ipu_idmac_disable_channel(struct ipuv3_channel *channel)
 }
 EXPORT_SYMBOL_GPL(ipu_idmac_disable_channel);
 
+/*
+ * The imx6 rev. D TRM says that enabling the WM feature will increase
+ * a channel's priority. Refer to Table 36-8 Calculated priority value.
+ * The sub-module that is the sink or source for the channel must enable
+ * watermark signal for this to take effect (SMFC_WM for instance).
+ */
+void ipu_idmac_enable_watermark(struct ipuv3_channel *channel, bool enable)
+{
+	struct ipu_soc *ipu = channel->ipu;
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+
+	val = ipu_idmac_read(ipu, IDMAC_WM_EN(channel->num));
+	if (enable)
+		val |= 1 << (channel->num % 32);
+	else
+		val &= ~(1 << (channel->num % 32));
+	ipu_idmac_write(ipu, val, IDMAC_WM_EN(channel->num));
+
+	spin_unlock_irqrestore(&ipu->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_idmac_enable_watermark);
+
 static int ipu_memory_reset(struct ipu_soc *ipu)
 {
 	unsigned long timeout;
@@ -382,12 +667,66 @@ static int ipu_memory_reset(struct ipu_soc *ipu)
 	return 0;
 }
 
+/*
+ * Set the source mux for the given CSI. Selects either parallel or
+ * MIPI CSI2 sources.
+ */
+void ipu_set_csi_src_mux(struct ipu_soc *ipu, int csi_id, bool mipi_csi2)
+{
+	unsigned long flags;
+	u32 val, mask;
+
+	mask = (csi_id == 1) ? IPU_CONF_CSI1_DATA_SOURCE :
+		IPU_CONF_CSI0_DATA_SOURCE;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+
+	val = ipu_cm_read(ipu, IPU_CONF);
+	if (mipi_csi2)
+		val |= mask;
+	else
+		val &= ~mask;
+	ipu_cm_write(ipu, val, IPU_CONF);
+
+	spin_unlock_irqrestore(&ipu->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_set_csi_src_mux);
+
+/*
+ * Set the source mux for the IC. Selects either CSI[01] or the VDI.
+ */
+void ipu_set_ic_src_mux(struct ipu_soc *ipu, int csi_id, bool vdi)
+{
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&ipu->lock, flags);
+
+	val = ipu_cm_read(ipu, IPU_CONF);
+	if (vdi) {
+		val |= IPU_CONF_IC_INPUT;
+	} else {
+		val &= ~IPU_CONF_IC_INPUT;
+		if (csi_id == 1)
+			val |= IPU_CONF_CSI_SEL;
+		else
+			val &= ~IPU_CONF_CSI_SEL;
+	}
+	ipu_cm_write(ipu, val, IPU_CONF);
+
+	spin_unlock_irqrestore(&ipu->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_set_ic_src_mux);
+
 struct ipu_devtype {
 	const char *name;
 	unsigned long cm_ofs;
 	unsigned long cpmem_ofs;
 	unsigned long srm_ofs;
 	unsigned long tpm_ofs;
+	unsigned long csi0_ofs;
+	unsigned long csi1_ofs;
+	unsigned long ic_ofs;
 	unsigned long disp0_ofs;
 	unsigned long disp1_ofs;
 	unsigned long dc_tmpl_ofs;
@@ -401,6 +740,9 @@ static struct ipu_devtype ipu_type_imx51 = {
 	.cpmem_ofs = 0x1f000000,
 	.srm_ofs = 0x1f040000,
 	.tpm_ofs = 0x1f060000,
+	.csi0_ofs = 0x1f030000,
+	.csi1_ofs = 0x1f038000,
+	.ic_ofs = 0x1f020000,
 	.disp0_ofs = 0x1e040000,
 	.disp1_ofs = 0x1e048000,
 	.dc_tmpl_ofs = 0x1f080000,
@@ -414,6 +756,9 @@ static struct ipu_devtype ipu_type_imx53 = {
 	.cpmem_ofs = 0x07000000,
 	.srm_ofs = 0x07040000,
 	.tpm_ofs = 0x07060000,
+	.csi0_ofs = 0x07030000,
+	.csi1_ofs = 0x07038000,
+	.ic_ofs = 0x07020000,
 	.disp0_ofs = 0x06040000,
 	.disp1_ofs = 0x06048000,
 	.dc_tmpl_ofs = 0x07080000,
@@ -427,6 +772,9 @@ static struct ipu_devtype ipu_type_imx6q = {
 	.cpmem_ofs = 0x00300000,
 	.srm_ofs = 0x00340000,
 	.tpm_ofs = 0x00360000,
+	.csi0_ofs = 0x00230000,
+	.csi1_ofs = 0x00238000,
+	.ic_ofs = 0x00220000,
 	.disp0_ofs = 0x00240000,
 	.disp1_ofs = 0x00248000,
 	.dc_tmpl_ofs = 0x00380000,
@@ -457,8 +805,30 @@ static int ipu_submodules_init(struct ipu_soc *ipu,
 		goto err_cpmem;
 	}
 
+	ret = ipu_csi_init(ipu, dev, 0, ipu_base + devtype->csi0_ofs,
+			   IPU_CONF_CSI0_EN, ipu_clk);
+	if (ret) {
+		unit = "csi0";
+		goto err_csi_0;
+	}
+
+	ret = ipu_csi_init(ipu, dev, 1, ipu_base + devtype->csi1_ofs,
+			   IPU_CONF_CSI1_EN, ipu_clk);
+	if (ret) {
+		unit = "csi1";
+		goto err_csi_1;
+	}
+
+	ret = ipu_ic_init(ipu, dev,
+			  ipu_base + devtype->ic_ofs,
+			  ipu_base + devtype->tpm_ofs);
+	if (ret) {
+		unit = "ic";
+		goto err_ic;
+	}
+
 	ret = ipu_di_init(ipu, dev, 0, ipu_base + devtype->disp0_ofs,
-			IPU_CONF_DI0_EN, ipu_clk);
+			  IPU_CONF_DI0_EN, ipu_clk);
 	if (ret) {
 		unit = "di0";
 		goto err_di_0;
@@ -511,6 +881,12 @@ err_dc:
 err_di_1:
 	ipu_di_exit(ipu, 0);
 err_di_0:
+	ipu_ic_exit(ipu);
+err_ic:
+	ipu_csi_exit(ipu, 1);
+err_csi_1:
+	ipu_csi_exit(ipu, 0);
+err_csi_0:
 	ipu_cpmem_exit(ipu);
 err_cpmem:
 	dev_err(&pdev->dev, "init %s failed with %d\n", unit, ret);
@@ -589,6 +965,9 @@ static void ipu_submodules_exit(struct ipu_soc *ipu)
 	ipu_dc_exit(ipu);
 	ipu_di_exit(ipu, 1);
 	ipu_di_exit(ipu, 0);
+	ipu_ic_exit(ipu);
+	ipu_csi_exit(ipu, 1);
+	ipu_csi_exit(ipu, 0);
 	ipu_cpmem_exit(ipu);
 }
 
@@ -681,8 +1060,10 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base)
 				id++, &reg->pdata, sizeof(reg->pdata));
 		}
 
-		if (IS_ERR(pdev))
+		if (IS_ERR(pdev)) {
+			ret = PTR_ERR(pdev);
 			goto err_register;
+		}
 	}
 
 	return 0;
@@ -766,6 +1147,44 @@ static void ipu_irq_exit(struct ipu_soc *ipu)
 	irq_domain_remove(ipu->domain);
 }
 
+void ipu_dump(struct ipu_soc *ipu)
+{
+	int i;
+
+	dev_dbg(ipu->dev, "IPU_CONF = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_CONF));
+	dev_dbg(ipu->dev, "IDMAC_CONF = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_CONF));
+	dev_dbg(ipu->dev, "IDMAC_CHA_EN1 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_CHA_EN(0)));
+	dev_dbg(ipu->dev, "IDMAC_CHA_EN2 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_CHA_EN(32)));
+	dev_dbg(ipu->dev, "IDMAC_CHA_PRI1 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_CHA_PRI(0)));
+	dev_dbg(ipu->dev, "IDMAC_CHA_PRI2 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_CHA_PRI(32)));
+	dev_dbg(ipu->dev, "IDMAC_BAND_EN1 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_BAND_EN(0)));
+	dev_dbg(ipu->dev, "IDMAC_BAND_EN2 = \t0x%08X\n",
+		ipu_idmac_read(ipu, IDMAC_BAND_EN(32)));
+	dev_dbg(ipu->dev, "IPU_CHA_DB_MODE_SEL0 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_CHA_DB_MODE_SEL(0)));
+	dev_dbg(ipu->dev, "IPU_CHA_DB_MODE_SEL1 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_CHA_DB_MODE_SEL(32)));
+	dev_dbg(ipu->dev, "IPU_FS_PROC_FLOW1 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_FS_PROC_FLOW1));
+	dev_dbg(ipu->dev, "IPU_FS_PROC_FLOW2 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_FS_PROC_FLOW2));
+	dev_dbg(ipu->dev, "IPU_FS_PROC_FLOW3 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_FS_PROC_FLOW3));
+	dev_dbg(ipu->dev, "IPU_FS_DISP_FLOW1 = \t0x%08X\n",
+		ipu_cm_read(ipu, IPU_FS_DISP_FLOW1));
+	for (i = 0; i < 15; i++)
+		dev_dbg(ipu->dev, "IPU_INT_CTRL(%d) = \t%08X\n", i,
+			ipu_cm_read(ipu, IPU_INT_CTRL(i)));
+}
+EXPORT_SYMBOL_GPL(ipu_dump);
+
 static int ipu_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id =
@@ -808,6 +1227,12 @@ static int ipu_probe(struct platform_device *pdev)
 			ipu_base + devtype->cm_ofs + IPU_CM_IDMAC_REG_OFS);
 	dev_dbg(&pdev->dev, "cpmem:    0x%08lx\n",
 			ipu_base + devtype->cpmem_ofs);
+	dev_dbg(&pdev->dev, "csi0:    0x%08lx\n",
+			ipu_base + devtype->csi0_ofs);
+	dev_dbg(&pdev->dev, "csi1:    0x%08lx\n",
+			ipu_base + devtype->csi1_ofs);
+	dev_dbg(&pdev->dev, "ic:      0x%08lx\n",
+			ipu_base + devtype->ic_ofs);
 	dev_dbg(&pdev->dev, "disp0:    0x%08lx\n",
 			ipu_base + devtype->disp0_ofs);
 	dev_dbg(&pdev->dev, "disp1:    0x%08lx\n",
diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index 7adfa78a48bc..3bf05bc4ab67 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -64,6 +64,7 @@ struct ipu_cpmem {
 #define IPU_FIELD_BNDM		IPU_CPMEM_WORD(0, 114, 3)
 #define IPU_FIELD_BM		IPU_CPMEM_WORD(0, 117, 2)
 #define IPU_FIELD_ROT		IPU_CPMEM_WORD(0, 119, 1)
+#define IPU_FIELD_ROT_HF_VF	IPU_CPMEM_WORD(0, 119, 3)
 #define IPU_FIELD_HF		IPU_CPMEM_WORD(0, 120, 1)
 #define IPU_FIELD_VF		IPU_CPMEM_WORD(0, 121, 1)
 #define IPU_FIELD_THE		IPU_CPMEM_WORD(0, 122, 1)
@@ -192,8 +193,14 @@ static int v4l2_pix_fmt_to_drm_fourcc(u32 pixelformat)
 		return DRM_FORMAT_YUYV;
 	case V4L2_PIX_FMT_YUV420:
 		return DRM_FORMAT_YUV420;
+	case V4L2_PIX_FMT_YUV422P:
+		return DRM_FORMAT_YUV422;
 	case V4L2_PIX_FMT_YVU420:
 		return DRM_FORMAT_YVU420;
+	case V4L2_PIX_FMT_NV12:
+		return DRM_FORMAT_NV12;
+	case V4L2_PIX_FMT_NV16:
+		return DRM_FORMAT_NV16;
 	}
 
 	return -EINVAL;
@@ -254,12 +261,34 @@ void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride)
 };
 EXPORT_SYMBOL_GPL(ipu_cpmem_interlaced_scan);
 
+void ipu_cpmem_set_axi_id(struct ipuv3_channel *ch, u32 id)
+{
+	id &= 0x3;
+	ipu_ch_param_write_field(ch, IPU_FIELD_ID, id);
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_axi_id);
+
 void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize)
 {
 	ipu_ch_param_write_field(ch, IPU_FIELD_NPB, burstsize - 1);
 };
 EXPORT_SYMBOL_GPL(ipu_cpmem_set_burstsize);
 
+void ipu_cpmem_set_block_mode(struct ipuv3_channel *ch)
+{
+	ipu_ch_param_write_field(ch, IPU_FIELD_BM, 1);
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_block_mode);
+
+void ipu_cpmem_set_rotation(struct ipuv3_channel *ch,
+			    enum ipu_rotate_mode rot)
+{
+	u32 temp_rot = bitrev8(rot) >> 5;
+
+	ipu_ch_param_write_field(ch, IPU_FIELD_ROT_HF_VF, temp_rot);
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_set_rotation);
+
 int ipu_cpmem_set_format_rgb(struct ipuv3_channel *ch,
 			     const struct ipu_rgb *rgb)
 {
@@ -371,6 +400,7 @@ void ipu_cpmem_set_yuv_planar_full(struct ipuv3_channel *ch,
 {
 	switch (pixel_format) {
 	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_YUV422P:
 		ipu_ch_param_write_field(ch, IPU_FIELD_SLUV, (stride / 2) - 1);
 		ipu_ch_param_write_field(ch, IPU_FIELD_UBO, u_offset / 8);
 		ipu_ch_param_write_field(ch, IPU_FIELD_VBO, v_offset / 8);
@@ -380,6 +410,12 @@ void ipu_cpmem_set_yuv_planar_full(struct ipuv3_channel *ch,
 		ipu_ch_param_write_field(ch, IPU_FIELD_UBO, v_offset / 8);
 		ipu_ch_param_write_field(ch, IPU_FIELD_VBO, u_offset / 8);
 		break;
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV16:
+		ipu_ch_param_write_field(ch, IPU_FIELD_SLUV, stride - 1);
+		ipu_ch_param_write_field(ch, IPU_FIELD_UBO, u_offset / 8);
+		ipu_ch_param_write_field(ch, IPU_FIELD_VBO, u_offset / 8);
+		break;
 	}
 }
 EXPORT_SYMBOL_GPL(ipu_cpmem_set_yuv_planar_full);
@@ -399,6 +435,19 @@ void ipu_cpmem_set_yuv_planar(struct ipuv3_channel *ch,
 		ipu_cpmem_set_yuv_planar_full(ch, pixel_format, stride,
 					      u_offset, v_offset);
 		break;
+	case V4L2_PIX_FMT_YUV422P:
+		uv_stride = stride / 2;
+		u_offset = stride * height;
+		v_offset = u_offset + (uv_stride * height);
+		ipu_cpmem_set_yuv_planar_full(ch, pixel_format, stride,
+					      u_offset, v_offset);
+		break;
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV16:
+		u_offset = stride * height;
+		ipu_cpmem_set_yuv_planar_full(ch, pixel_format, stride,
+					      u_offset, 0);
+		break;
 	}
 }
 EXPORT_SYMBOL_GPL(ipu_cpmem_set_yuv_planar);
@@ -452,11 +501,20 @@ static const struct ipu_rgb def_bgr_16 = {
 };
 
 #define Y_OFFSET(pix, x, y)	((x) + pix->width * (y))
-#define U_OFFSET(pix, x, y)	((pix->width * pix->height) + \
-					(pix->width * (y) / 4) + (x) / 2)
-#define V_OFFSET(pix, x, y)	((pix->width * pix->height) + \
-					(pix->width * pix->height / 4) + \
-					(pix->width * (y) / 4) + (x) / 2)
+#define U_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
+				 (pix->width * (y) / 4) + (x) / 2)
+#define V_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
+				 (pix->width * pix->height / 4) +	\
+				 (pix->width * (y) / 4) + (x) / 2)
+#define U2_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
+				 (pix->width * (y) / 2) + (x) / 2)
+#define V2_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
+				 (pix->width * pix->height / 2) +	\
+				 (pix->width * (y) / 2) + (x) / 2)
+#define UV_OFFSET(pix, x, y)	((pix->width * pix->height) +	\
+				 (pix->width * (y) / 2) + (x))
+#define UV2_OFFSET(pix, x, y)	((pix->width * pix->height) +	\
+				 (pix->width * y) + (x))
 
 int ipu_cpmem_set_fmt(struct ipuv3_channel *ch, u32 drm_fourcc)
 {
@@ -468,6 +526,25 @@ int ipu_cpmem_set_fmt(struct ipuv3_channel *ch, u32 drm_fourcc)
 		/* burst size */
 		ipu_ch_param_write_field(ch, IPU_FIELD_NPB, 31);
 		break;
+	case DRM_FORMAT_YUV422:
+	case DRM_FORMAT_YVU422:
+		/* pix format */
+		ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 1);
+		/* burst size */
+		ipu_ch_param_write_field(ch, IPU_FIELD_NPB, 31);
+		break;
+	case DRM_FORMAT_NV12:
+		/* pix format */
+		ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 4);
+		/* burst size */
+		ipu_ch_param_write_field(ch, IPU_FIELD_NPB, 31);
+		break;
+	case DRM_FORMAT_NV16:
+		/* pix format */
+		ipu_ch_param_write_field(ch, IPU_FIELD_PFS, 3);
+		/* burst size */
+		ipu_ch_param_write_field(ch, IPU_FIELD_NPB, 31);
+		break;
 	case DRM_FORMAT_UYVY:
 		/* bits/pixel */
 		ipu_ch_param_write_field(ch, IPU_FIELD_BPP, 3);
@@ -515,7 +592,7 @@ EXPORT_SYMBOL_GPL(ipu_cpmem_set_fmt);
 int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image)
 {
 	struct v4l2_pix_format *pix = &image->pix;
-	int y_offset, u_offset, v_offset;
+	int offset, u_offset, v_offset;
 
 	pr_debug("%s: resolution: %dx%d stride: %d\n",
 		 __func__, pix->width, pix->height,
@@ -529,47 +606,137 @@ int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image)
 	switch (pix->pixelformat) {
 	case V4L2_PIX_FMT_YUV420:
 	case V4L2_PIX_FMT_YVU420:
-		y_offset = Y_OFFSET(pix, image->rect.left, image->rect.top);
+		offset = Y_OFFSET(pix, image->rect.left, image->rect.top);
 		u_offset = U_OFFSET(pix, image->rect.left,
-				    image->rect.top) - y_offset;
+				    image->rect.top) - offset;
 		v_offset = V_OFFSET(pix, image->rect.left,
-				    image->rect.top) - y_offset;
+				    image->rect.top) - offset;
+
+		ipu_cpmem_set_yuv_planar_full(ch, pix->pixelformat,
+					      pix->bytesperline,
+					      u_offset, v_offset);
+		break;
+	case V4L2_PIX_FMT_YUV422P:
+		offset = Y_OFFSET(pix, image->rect.left, image->rect.top);
+		u_offset = U2_OFFSET(pix, image->rect.left,
+				     image->rect.top) - offset;
+		v_offset = V2_OFFSET(pix, image->rect.left,
+				     image->rect.top) - offset;
 
 		ipu_cpmem_set_yuv_planar_full(ch, pix->pixelformat,
-				pix->bytesperline, u_offset, v_offset);
-		ipu_cpmem_set_buffer(ch, 0, image->phys + y_offset);
+					      pix->bytesperline,
+					      u_offset, v_offset);
+		break;
+	case V4L2_PIX_FMT_NV12:
+		offset = Y_OFFSET(pix, image->rect.left, image->rect.top);
+		u_offset = UV_OFFSET(pix, image->rect.left,
+				     image->rect.top) - offset;
+		v_offset = 0;
+
+		ipu_cpmem_set_yuv_planar_full(ch, pix->pixelformat,
+					      pix->bytesperline,
+					      u_offset, v_offset);
+		break;
+	case V4L2_PIX_FMT_NV16:
+		offset = Y_OFFSET(pix, image->rect.left, image->rect.top);
+		u_offset = UV2_OFFSET(pix, image->rect.left,
+				      image->rect.top) - offset;
+		v_offset = 0;
+
+		ipu_cpmem_set_yuv_planar_full(ch, pix->pixelformat,
+					      pix->bytesperline,
+					      u_offset, v_offset);
 		break;
 	case V4L2_PIX_FMT_UYVY:
 	case V4L2_PIX_FMT_YUYV:
-		ipu_cpmem_set_buffer(ch, 0, image->phys +
-				     image->rect.left * 2 +
-				     image->rect.top * image->pix.bytesperline);
+	case V4L2_PIX_FMT_RGB565:
+		offset = image->rect.left * 2 +
+			image->rect.top * pix->bytesperline;
 		break;
 	case V4L2_PIX_FMT_RGB32:
 	case V4L2_PIX_FMT_BGR32:
-		ipu_cpmem_set_buffer(ch, 0, image->phys +
-				     image->rect.left * 4 +
-				     image->rect.top * image->pix.bytesperline);
-		break;
-	case V4L2_PIX_FMT_RGB565:
-		ipu_cpmem_set_buffer(ch, 0, image->phys +
-				     image->rect.left * 2 +
-				     image->rect.top * image->pix.bytesperline);
+		offset = image->rect.left * 4 +
+			image->rect.top * pix->bytesperline;
 		break;
 	case V4L2_PIX_FMT_RGB24:
 	case V4L2_PIX_FMT_BGR24:
-		ipu_cpmem_set_buffer(ch, 0, image->phys +
-				     image->rect.left * 3 +
-				     image->rect.top * image->pix.bytesperline);
+		offset = image->rect.left * 3 +
+			image->rect.top * pix->bytesperline;
 		break;
 	default:
 		return -EINVAL;
 	}
 
+	ipu_cpmem_set_buffer(ch, 0, image->phys0 + offset);
+	ipu_cpmem_set_buffer(ch, 1, image->phys1 + offset);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ipu_cpmem_set_image);
 
+void ipu_cpmem_dump(struct ipuv3_channel *ch)
+{
+	struct ipu_ch_param __iomem *p = ipu_get_cpmem(ch);
+	struct ipu_soc *ipu = ch->ipu;
+	int chno = ch->num;
+
+	dev_dbg(ipu->dev, "ch %d word 0 - %08X %08X %08X %08X %08X\n", chno,
+		readl(&p->word[0].data[0]),
+		readl(&p->word[0].data[1]),
+		readl(&p->word[0].data[2]),
+		readl(&p->word[0].data[3]),
+		readl(&p->word[0].data[4]));
+	dev_dbg(ipu->dev, "ch %d word 1 - %08X %08X %08X %08X %08X\n", chno,
+		readl(&p->word[1].data[0]),
+		readl(&p->word[1].data[1]),
+		readl(&p->word[1].data[2]),
+		readl(&p->word[1].data[3]),
+		readl(&p->word[1].data[4]));
+	dev_dbg(ipu->dev, "PFS 0x%x, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_PFS));
+	dev_dbg(ipu->dev, "BPP 0x%x, ",
+		ipu_ch_param_read_field(ch, IPU_FIELD_BPP));
+	dev_dbg(ipu->dev, "NPB 0x%x\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_NPB));
+
+	dev_dbg(ipu->dev, "FW %d, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_FW));
+	dev_dbg(ipu->dev, "FH %d, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_FH));
+	dev_dbg(ipu->dev, "EBA0 0x%x\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_EBA0) << 3);
+	dev_dbg(ipu->dev, "EBA1 0x%x\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_EBA1) << 3);
+	dev_dbg(ipu->dev, "Stride %d\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_SL));
+	dev_dbg(ipu->dev, "scan_order %d\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_SO));
+	dev_dbg(ipu->dev, "uv_stride %d\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_SLUV));
+	dev_dbg(ipu->dev, "u_offset 0x%x\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_UBO) << 3);
+	dev_dbg(ipu->dev, "v_offset 0x%x\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_VBO) << 3);
+
+	dev_dbg(ipu->dev, "Width0 %d+1, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_WID0));
+	dev_dbg(ipu->dev, "Width1 %d+1, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_WID1));
+	dev_dbg(ipu->dev, "Width2 %d+1, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_WID2));
+	dev_dbg(ipu->dev, "Width3 %d+1, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_WID3));
+	dev_dbg(ipu->dev, "Offset0 %d, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_OFS0));
+	dev_dbg(ipu->dev, "Offset1 %d, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_OFS1));
+	dev_dbg(ipu->dev, "Offset2 %d, ",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_OFS2));
+	dev_dbg(ipu->dev, "Offset3 %d\n",
+		 ipu_ch_param_read_field(ch, IPU_FIELD_OFS3));
+}
+EXPORT_SYMBOL_GPL(ipu_cpmem_dump);
+
 int ipu_cpmem_init(struct ipu_soc *ipu, struct device *dev, unsigned long base)
 {
 	struct ipu_cpmem *cpmem;
diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c
new file mode 100644
index 000000000000..d6f56471bd2a
--- /dev/null
+++ b/drivers/gpu/ipu-v3/ipu-csi.c
@@ -0,0 +1,741 @@
+/*
+ * Copyright (C) 2012-2014 Mentor Graphics Inc.
+ * Copyright (C) 2005-2009 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ */
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/videodev2.h>
+#include <uapi/linux/v4l2-mediabus.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+
+#include "ipu-prv.h"
+
+struct ipu_csi {
+	void __iomem *base;
+	int id;
+	u32 module;
+	struct clk *clk_ipu;	/* IPU bus clock */
+	spinlock_t lock;
+	bool inuse;
+	struct ipu_soc *ipu;
+};
+
+/* CSI Register Offsets */
+#define CSI_SENS_CONF		0x0000
+#define CSI_SENS_FRM_SIZE	0x0004
+#define CSI_ACT_FRM_SIZE	0x0008
+#define CSI_OUT_FRM_CTRL	0x000c
+#define CSI_TST_CTRL		0x0010
+#define CSI_CCIR_CODE_1		0x0014
+#define CSI_CCIR_CODE_2		0x0018
+#define CSI_CCIR_CODE_3		0x001c
+#define CSI_MIPI_DI		0x0020
+#define CSI_SKIP		0x0024
+#define CSI_CPD_CTRL		0x0028
+#define CSI_CPD_RC(n)		(0x002c + ((n)*4))
+#define CSI_CPD_RS(n)		(0x004c + ((n)*4))
+#define CSI_CPD_GRC(n)		(0x005c + ((n)*4))
+#define CSI_CPD_GRS(n)		(0x007c + ((n)*4))
+#define CSI_CPD_GBC(n)		(0x008c + ((n)*4))
+#define CSI_CPD_GBS(n)		(0x00Ac + ((n)*4))
+#define CSI_CPD_BC(n)		(0x00Bc + ((n)*4))
+#define CSI_CPD_BS(n)		(0x00Dc + ((n)*4))
+#define CSI_CPD_OFFSET1		0x00ec
+#define CSI_CPD_OFFSET2		0x00f0
+
+/* CSI Register Fields */
+#define CSI_SENS_CONF_DATA_FMT_SHIFT		8
+#define CSI_SENS_CONF_DATA_FMT_MASK		0x00000700
+#define CSI_SENS_CONF_DATA_FMT_RGB_YUV444	0L
+#define CSI_SENS_CONF_DATA_FMT_YUV422_YUYV	1L
+#define CSI_SENS_CONF_DATA_FMT_YUV422_UYVY	2L
+#define CSI_SENS_CONF_DATA_FMT_BAYER		3L
+#define CSI_SENS_CONF_DATA_FMT_RGB565		4L
+#define CSI_SENS_CONF_DATA_FMT_RGB555		5L
+#define CSI_SENS_CONF_DATA_FMT_RGB444		6L
+#define CSI_SENS_CONF_DATA_FMT_JPEG		7L
+
+#define CSI_SENS_CONF_VSYNC_POL_SHIFT		0
+#define CSI_SENS_CONF_HSYNC_POL_SHIFT		1
+#define CSI_SENS_CONF_DATA_POL_SHIFT		2
+#define CSI_SENS_CONF_PIX_CLK_POL_SHIFT		3
+#define CSI_SENS_CONF_SENS_PRTCL_MASK		0x00000070
+#define CSI_SENS_CONF_SENS_PRTCL_SHIFT		4
+#define CSI_SENS_CONF_PACK_TIGHT_SHIFT		7
+#define CSI_SENS_CONF_DATA_WIDTH_SHIFT		11
+#define CSI_SENS_CONF_EXT_VSYNC_SHIFT		15
+#define CSI_SENS_CONF_DIVRATIO_SHIFT		16
+
+#define CSI_SENS_CONF_DIVRATIO_MASK		0x00ff0000
+#define CSI_SENS_CONF_DATA_DEST_SHIFT		24
+#define CSI_SENS_CONF_DATA_DEST_MASK		0x07000000
+#define CSI_SENS_CONF_JPEG8_EN_SHIFT		27
+#define CSI_SENS_CONF_JPEG_EN_SHIFT		28
+#define CSI_SENS_CONF_FORCE_EOF_SHIFT		29
+#define CSI_SENS_CONF_DATA_EN_POL_SHIFT		31
+
+#define CSI_DATA_DEST_IC			2
+#define CSI_DATA_DEST_IDMAC			4
+
+#define CSI_CCIR_ERR_DET_EN			0x01000000
+#define CSI_HORI_DOWNSIZE_EN			0x80000000
+#define CSI_VERT_DOWNSIZE_EN			0x40000000
+#define CSI_TEST_GEN_MODE_EN			0x01000000
+
+#define CSI_HSC_MASK				0x1fff0000
+#define CSI_HSC_SHIFT				16
+#define CSI_VSC_MASK				0x00000fff
+#define CSI_VSC_SHIFT				0
+
+#define CSI_TEST_GEN_R_MASK			0x000000ff
+#define CSI_TEST_GEN_R_SHIFT			0
+#define CSI_TEST_GEN_G_MASK			0x0000ff00
+#define CSI_TEST_GEN_G_SHIFT			8
+#define CSI_TEST_GEN_B_MASK			0x00ff0000
+#define CSI_TEST_GEN_B_SHIFT			16
+
+#define CSI_MAX_RATIO_SKIP_SMFC_MASK		0x00000007
+#define CSI_MAX_RATIO_SKIP_SMFC_SHIFT		0
+#define CSI_SKIP_SMFC_MASK			0x000000f8
+#define CSI_SKIP_SMFC_SHIFT			3
+#define CSI_ID_2_SKIP_MASK			0x00000300
+#define CSI_ID_2_SKIP_SHIFT			8
+
+#define CSI_COLOR_FIRST_ROW_MASK		0x00000002
+#define CSI_COLOR_FIRST_COMP_MASK		0x00000001
+
+/* MIPI CSI-2 data types */
+#define MIPI_DT_YUV420		0x18 /* YYY.../UYVY.... */
+#define MIPI_DT_YUV420_LEGACY	0x1a /* UYY.../VYY...   */
+#define MIPI_DT_YUV422		0x1e /* UYVY...         */
+#define MIPI_DT_RGB444		0x20
+#define MIPI_DT_RGB555		0x21
+#define MIPI_DT_RGB565		0x22
+#define MIPI_DT_RGB666		0x23
+#define MIPI_DT_RGB888		0x24
+#define MIPI_DT_RAW6		0x28
+#define MIPI_DT_RAW7		0x29
+#define MIPI_DT_RAW8		0x2a
+#define MIPI_DT_RAW10		0x2b
+#define MIPI_DT_RAW12		0x2c
+#define MIPI_DT_RAW14		0x2d
+
+/*
+ * Bitfield of CSI bus signal polarities and modes.
+ */
+struct ipu_csi_bus_config {
+	unsigned data_width:4;
+	unsigned clk_mode:3;
+	unsigned ext_vsync:1;
+	unsigned vsync_pol:1;
+	unsigned hsync_pol:1;
+	unsigned pixclk_pol:1;
+	unsigned data_pol:1;
+	unsigned sens_clksrc:1;
+	unsigned pack_tight:1;
+	unsigned force_eof:1;
+	unsigned data_en_pol:1;
+
+	unsigned data_fmt;
+	unsigned mipi_dt;
+};
+
+/*
+ * Enumeration of CSI data bus widths.
+ */
+enum ipu_csi_data_width {
+	IPU_CSI_DATA_WIDTH_4   = 0,
+	IPU_CSI_DATA_WIDTH_8   = 1,
+	IPU_CSI_DATA_WIDTH_10  = 3,
+	IPU_CSI_DATA_WIDTH_12  = 5,
+	IPU_CSI_DATA_WIDTH_16  = 9,
+};
+
+/*
+ * Enumeration of CSI clock modes.
+ */
+enum ipu_csi_clk_mode {
+	IPU_CSI_CLK_MODE_GATED_CLK,
+	IPU_CSI_CLK_MODE_NONGATED_CLK,
+	IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE,
+	IPU_CSI_CLK_MODE_CCIR656_INTERLACED,
+	IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_DDR,
+	IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_SDR,
+	IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_DDR,
+	IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_SDR,
+};
+
+static inline u32 ipu_csi_read(struct ipu_csi *csi, unsigned offset)
+{
+	return readl(csi->base + offset);
+}
+
+static inline void ipu_csi_write(struct ipu_csi *csi, u32 value,
+				 unsigned offset)
+{
+	writel(value, csi->base + offset);
+}
+
+/*
+ * Set mclk division ratio for generating test mode mclk. Only used
+ * for test generator.
+ */
+static int ipu_csi_set_testgen_mclk(struct ipu_csi *csi, u32 pixel_clk,
+					u32 ipu_clk)
+{
+	u32 temp;
+	u32 div_ratio;
+
+	div_ratio = (ipu_clk / pixel_clk) - 1;
+
+	if (div_ratio > 0xFF || div_ratio < 0) {
+		dev_err(csi->ipu->dev,
+			"value of pixel_clk extends normal range\n");
+		return -EINVAL;
+	}
+
+	temp = ipu_csi_read(csi, CSI_SENS_CONF);
+	temp &= ~CSI_SENS_CONF_DIVRATIO_MASK;
+	ipu_csi_write(csi, temp | (div_ratio << CSI_SENS_CONF_DIVRATIO_SHIFT),
+			  CSI_SENS_CONF);
+
+	return 0;
+}
+
+/*
+ * Find the CSI data format and data width for the given V4L2 media
+ * bus pixel format code.
+ */
+static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code)
+{
+	switch (mbus_code) {
+	case V4L2_MBUS_FMT_BGR565_2X8_BE:
+	case V4L2_MBUS_FMT_BGR565_2X8_LE:
+	case V4L2_MBUS_FMT_RGB565_2X8_BE:
+	case V4L2_MBUS_FMT_RGB565_2X8_LE:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB565;
+		cfg->mipi_dt = MIPI_DT_RGB565;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_RGB444_2X8_PADHI_BE:
+	case V4L2_MBUS_FMT_RGB444_2X8_PADHI_LE:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB444;
+		cfg->mipi_dt = MIPI_DT_RGB444;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_RGB555_2X8_PADHI_BE:
+	case V4L2_MBUS_FMT_RGB555_2X8_PADHI_LE:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB555;
+		cfg->mipi_dt = MIPI_DT_RGB555;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_UYVY8_2X8:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_YUV422_UYVY;
+		cfg->mipi_dt = MIPI_DT_YUV422;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_YUYV8_2X8:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_YUV422_YUYV;
+		cfg->mipi_dt = MIPI_DT_YUV422;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_UYVY8_1X16:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_YUV422_UYVY;
+		cfg->mipi_dt = MIPI_DT_YUV422;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_16;
+		break;
+	case V4L2_MBUS_FMT_YUYV8_1X16:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_YUV422_YUYV;
+		cfg->mipi_dt = MIPI_DT_YUV422;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_16;
+		break;
+	case V4L2_MBUS_FMT_SBGGR8_1X8:
+	case V4L2_MBUS_FMT_SGBRG8_1X8:
+	case V4L2_MBUS_FMT_SGRBG8_1X8:
+	case V4L2_MBUS_FMT_SRGGB8_1X8:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER;
+		cfg->mipi_dt = MIPI_DT_RAW8;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_SBGGR10_DPCM8_1X8:
+	case V4L2_MBUS_FMT_SGBRG10_DPCM8_1X8:
+	case V4L2_MBUS_FMT_SGRBG10_DPCM8_1X8:
+	case V4L2_MBUS_FMT_SRGGB10_DPCM8_1X8:
+	case V4L2_MBUS_FMT_SBGGR10_2X8_PADHI_BE:
+	case V4L2_MBUS_FMT_SBGGR10_2X8_PADHI_LE:
+	case V4L2_MBUS_FMT_SBGGR10_2X8_PADLO_BE:
+	case V4L2_MBUS_FMT_SBGGR10_2X8_PADLO_LE:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER;
+		cfg->mipi_dt = MIPI_DT_RAW10;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	case V4L2_MBUS_FMT_SBGGR10_1X10:
+	case V4L2_MBUS_FMT_SGBRG10_1X10:
+	case V4L2_MBUS_FMT_SGRBG10_1X10:
+	case V4L2_MBUS_FMT_SRGGB10_1X10:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER;
+		cfg->mipi_dt = MIPI_DT_RAW10;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_10;
+		break;
+	case V4L2_MBUS_FMT_SBGGR12_1X12:
+	case V4L2_MBUS_FMT_SGBRG12_1X12:
+	case V4L2_MBUS_FMT_SGRBG12_1X12:
+	case V4L2_MBUS_FMT_SRGGB12_1X12:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER;
+		cfg->mipi_dt = MIPI_DT_RAW12;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_12;
+		break;
+	case V4L2_MBUS_FMT_JPEG_1X8:
+		/* TODO */
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_JPEG;
+		cfg->mipi_dt = MIPI_DT_RAW8;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Fill a CSI bus config struct from mbus_config and mbus_framefmt.
+ */
+static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
+				 struct v4l2_mbus_config *mbus_cfg,
+				 struct v4l2_mbus_framefmt *mbus_fmt)
+{
+	memset(csicfg, 0, sizeof(*csicfg));
+
+	mbus_code_to_bus_cfg(csicfg, mbus_fmt->code);
+
+	switch (mbus_cfg->type) {
+	case V4L2_MBUS_PARALLEL:
+		csicfg->ext_vsync = 1;
+		csicfg->vsync_pol = (mbus_cfg->flags &
+				     V4L2_MBUS_VSYNC_ACTIVE_LOW) ? 1 : 0;
+		csicfg->hsync_pol = (mbus_cfg->flags &
+				     V4L2_MBUS_HSYNC_ACTIVE_LOW) ? 1 : 0;
+		csicfg->pixclk_pol = (mbus_cfg->flags &
+				      V4L2_MBUS_PCLK_SAMPLE_FALLING) ? 1 : 0;
+		csicfg->clk_mode = IPU_CSI_CLK_MODE_GATED_CLK;
+		break;
+	case V4L2_MBUS_BT656:
+		csicfg->ext_vsync = 0;
+		if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field))
+			csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_INTERLACED;
+		else
+			csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE;
+		break;
+	case V4L2_MBUS_CSI2:
+		/*
+		 * MIPI CSI-2 requires non gated clock mode, all other
+		 * parameters are not applicable for MIPI CSI-2 bus.
+		 */
+		csicfg->clk_mode = IPU_CSI_CLK_MODE_NONGATED_CLK;
+		break;
+	default:
+		/* will never get here, keep compiler quiet */
+		break;
+	}
+}
+
+int ipu_csi_init_interface(struct ipu_csi *csi,
+			   struct v4l2_mbus_config *mbus_cfg,
+			   struct v4l2_mbus_framefmt *mbus_fmt)
+{
+	struct ipu_csi_bus_config cfg;
+	unsigned long flags;
+	u32 data = 0;
+
+	fill_csi_bus_cfg(&cfg, mbus_cfg, mbus_fmt);
+
+	/* Set the CSI_SENS_CONF register remaining fields */
+	data |= cfg.data_width << CSI_SENS_CONF_DATA_WIDTH_SHIFT |
+		cfg.data_fmt << CSI_SENS_CONF_DATA_FMT_SHIFT |
+		cfg.data_pol << CSI_SENS_CONF_DATA_POL_SHIFT |
+		cfg.vsync_pol << CSI_SENS_CONF_VSYNC_POL_SHIFT |
+		cfg.hsync_pol << CSI_SENS_CONF_HSYNC_POL_SHIFT |
+		cfg.pixclk_pol << CSI_SENS_CONF_PIX_CLK_POL_SHIFT |
+		cfg.ext_vsync << CSI_SENS_CONF_EXT_VSYNC_SHIFT |
+		cfg.clk_mode << CSI_SENS_CONF_SENS_PRTCL_SHIFT |
+		cfg.pack_tight << CSI_SENS_CONF_PACK_TIGHT_SHIFT |
+		cfg.force_eof << CSI_SENS_CONF_FORCE_EOF_SHIFT |
+		cfg.data_en_pol << CSI_SENS_CONF_DATA_EN_POL_SHIFT;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	ipu_csi_write(csi, data, CSI_SENS_CONF);
+
+	/* Setup sensor frame size */
+	ipu_csi_write(csi,
+		      (mbus_fmt->width - 1) | ((mbus_fmt->height - 1) << 16),
+		      CSI_SENS_FRM_SIZE);
+
+	/* Set CCIR registers */
+
+	switch (cfg.clk_mode) {
+	case IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE:
+		ipu_csi_write(csi, 0x40030, CSI_CCIR_CODE_1);
+		ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3);
+		break;
+	case IPU_CSI_CLK_MODE_CCIR656_INTERLACED:
+		if (mbus_fmt->width == 720 && mbus_fmt->height == 576) {
+			/*
+			 * PAL case
+			 *
+			 * Field0BlankEnd = 0x6, Field0BlankStart = 0x2,
+			 * Field0ActiveEnd = 0x4, Field0ActiveStart = 0
+			 * Field1BlankEnd = 0x7, Field1BlankStart = 0x3,
+			 * Field1ActiveEnd = 0x5, Field1ActiveStart = 0x1
+			 */
+			ipu_csi_write(csi, 0x40596 | CSI_CCIR_ERR_DET_EN,
+					  CSI_CCIR_CODE_1);
+			ipu_csi_write(csi, 0xD07DF, CSI_CCIR_CODE_2);
+			ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3);
+
+		} else if (mbus_fmt->width == 720 && mbus_fmt->height == 480) {
+			/*
+			 * NTSC case
+			 *
+			 * Field0BlankEnd = 0x7, Field0BlankStart = 0x3,
+			 * Field0ActiveEnd = 0x5, Field0ActiveStart = 0x1
+			 * Field1BlankEnd = 0x6, Field1BlankStart = 0x2,
+			 * Field1ActiveEnd = 0x4, Field1ActiveStart = 0
+			 */
+			ipu_csi_write(csi, 0xD07DF | CSI_CCIR_ERR_DET_EN,
+					  CSI_CCIR_CODE_1);
+			ipu_csi_write(csi, 0x40596, CSI_CCIR_CODE_2);
+			ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3);
+		} else {
+			dev_err(csi->ipu->dev,
+				"Unsupported CCIR656 interlaced video mode\n");
+			spin_unlock_irqrestore(&csi->lock, flags);
+			return -EINVAL;
+		}
+		break;
+	case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_DDR:
+	case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_SDR:
+	case IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_DDR:
+	case IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_SDR:
+		ipu_csi_write(csi, 0x40030 | CSI_CCIR_ERR_DET_EN,
+				   CSI_CCIR_CODE_1);
+		ipu_csi_write(csi, 0xFF0000, CSI_CCIR_CODE_3);
+		break;
+	case IPU_CSI_CLK_MODE_GATED_CLK:
+	case IPU_CSI_CLK_MODE_NONGATED_CLK:
+		ipu_csi_write(csi, 0, CSI_CCIR_CODE_1);
+		break;
+	}
+
+	dev_dbg(csi->ipu->dev, "CSI_SENS_CONF = 0x%08X\n",
+		ipu_csi_read(csi, CSI_SENS_CONF));
+	dev_dbg(csi->ipu->dev, "CSI_ACT_FRM_SIZE = 0x%08X\n",
+		ipu_csi_read(csi, CSI_ACT_FRM_SIZE));
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_init_interface);
+
+bool ipu_csi_is_interlaced(struct ipu_csi *csi)
+{
+	unsigned long flags;
+	u32 sensor_protocol;
+
+	spin_lock_irqsave(&csi->lock, flags);
+	sensor_protocol =
+		(ipu_csi_read(csi, CSI_SENS_CONF) &
+		 CSI_SENS_CONF_SENS_PRTCL_MASK) >>
+		CSI_SENS_CONF_SENS_PRTCL_SHIFT;
+	spin_unlock_irqrestore(&csi->lock, flags);
+
+	switch (sensor_protocol) {
+	case IPU_CSI_CLK_MODE_GATED_CLK:
+	case IPU_CSI_CLK_MODE_NONGATED_CLK:
+	case IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE:
+	case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_DDR:
+	case IPU_CSI_CLK_MODE_CCIR1120_PROGRESSIVE_SDR:
+		return false;
+	case IPU_CSI_CLK_MODE_CCIR656_INTERLACED:
+	case IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_DDR:
+	case IPU_CSI_CLK_MODE_CCIR1120_INTERLACED_SDR:
+		return true;
+	default:
+		dev_err(csi->ipu->dev,
+			"CSI %d sensor protocol unsupported\n", csi->id);
+		return false;
+	}
+}
+EXPORT_SYMBOL_GPL(ipu_csi_is_interlaced);
+
+void ipu_csi_get_window(struct ipu_csi *csi, struct v4l2_rect *w)
+{
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	reg = ipu_csi_read(csi, CSI_ACT_FRM_SIZE);
+	w->width = (reg & 0xFFFF) + 1;
+	w->height = (reg >> 16 & 0xFFFF) + 1;
+
+	reg = ipu_csi_read(csi, CSI_OUT_FRM_CTRL);
+	w->left = (reg & CSI_HSC_MASK) >> CSI_HSC_SHIFT;
+	w->top = (reg & CSI_VSC_MASK) >> CSI_VSC_SHIFT;
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_csi_get_window);
+
+void ipu_csi_set_window(struct ipu_csi *csi, struct v4l2_rect *w)
+{
+	unsigned long flags;
+	u32 reg;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	ipu_csi_write(csi, (w->width - 1) | ((w->height - 1) << 16),
+			  CSI_ACT_FRM_SIZE);
+
+	reg = ipu_csi_read(csi, CSI_OUT_FRM_CTRL);
+	reg &= ~(CSI_HSC_MASK | CSI_VSC_MASK);
+	reg |= ((w->top << CSI_VSC_SHIFT) | (w->left << CSI_HSC_SHIFT));
+	ipu_csi_write(csi, reg, CSI_OUT_FRM_CTRL);
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_csi_set_window);
+
+void ipu_csi_set_test_generator(struct ipu_csi *csi, bool active,
+				u32 r_value, u32 g_value, u32 b_value,
+				u32 pix_clk)
+{
+	unsigned long flags;
+	u32 ipu_clk = clk_get_rate(csi->clk_ipu);
+	u32 temp;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	temp = ipu_csi_read(csi, CSI_TST_CTRL);
+
+	if (active == false) {
+		temp &= ~CSI_TEST_GEN_MODE_EN;
+		ipu_csi_write(csi, temp, CSI_TST_CTRL);
+	} else {
+		/* Set sensb_mclk div_ratio */
+		ipu_csi_set_testgen_mclk(csi, pix_clk, ipu_clk);
+
+		temp &= ~(CSI_TEST_GEN_R_MASK | CSI_TEST_GEN_G_MASK |
+			  CSI_TEST_GEN_B_MASK);
+		temp |= CSI_TEST_GEN_MODE_EN;
+		temp |= (r_value << CSI_TEST_GEN_R_SHIFT) |
+			(g_value << CSI_TEST_GEN_G_SHIFT) |
+			(b_value << CSI_TEST_GEN_B_SHIFT);
+		ipu_csi_write(csi, temp, CSI_TST_CTRL);
+	}
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_csi_set_test_generator);
+
+int ipu_csi_set_mipi_datatype(struct ipu_csi *csi, u32 vc,
+			      struct v4l2_mbus_framefmt *mbus_fmt)
+{
+	struct ipu_csi_bus_config cfg;
+	unsigned long flags;
+	u32 temp;
+
+	if (vc > 3)
+		return -EINVAL;
+
+	mbus_code_to_bus_cfg(&cfg, mbus_fmt->code);
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	temp = ipu_csi_read(csi, CSI_MIPI_DI);
+	temp &= ~(0xff << (vc * 8));
+	temp |= (cfg.mipi_dt << (vc * 8));
+	ipu_csi_write(csi, temp, CSI_MIPI_DI);
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_set_mipi_datatype);
+
+int ipu_csi_set_skip_smfc(struct ipu_csi *csi, u32 skip,
+			  u32 max_ratio, u32 id)
+{
+	unsigned long flags;
+	u32 temp;
+
+	if (max_ratio > 5 || id > 3)
+		return -EINVAL;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	temp = ipu_csi_read(csi, CSI_SKIP);
+	temp &= ~(CSI_MAX_RATIO_SKIP_SMFC_MASK | CSI_ID_2_SKIP_MASK |
+		  CSI_SKIP_SMFC_MASK);
+	temp |= (max_ratio << CSI_MAX_RATIO_SKIP_SMFC_SHIFT) |
+		(id << CSI_ID_2_SKIP_SHIFT) |
+		(skip << CSI_SKIP_SMFC_SHIFT);
+	ipu_csi_write(csi, temp, CSI_SKIP);
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_set_skip_smfc);
+
+int ipu_csi_set_dest(struct ipu_csi *csi, enum ipu_csi_dest csi_dest)
+{
+	unsigned long flags;
+	u32 csi_sens_conf, dest;
+
+	if (csi_dest == IPU_CSI_DEST_IDMAC)
+		dest = CSI_DATA_DEST_IDMAC;
+	else
+		dest = CSI_DATA_DEST_IC; /* IC or VDIC */
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	csi_sens_conf = ipu_csi_read(csi, CSI_SENS_CONF);
+	csi_sens_conf &= ~CSI_SENS_CONF_DATA_DEST_MASK;
+	csi_sens_conf |= (dest << CSI_SENS_CONF_DATA_DEST_SHIFT);
+	ipu_csi_write(csi, csi_sens_conf, CSI_SENS_CONF);
+
+	spin_unlock_irqrestore(&csi->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_set_dest);
+
+int ipu_csi_enable(struct ipu_csi *csi)
+{
+	ipu_module_enable(csi->ipu, csi->module);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_enable);
+
+int ipu_csi_disable(struct ipu_csi *csi)
+{
+	ipu_module_disable(csi->ipu, csi->module);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_disable);
+
+struct ipu_csi *ipu_csi_get(struct ipu_soc *ipu, int id)
+{
+	unsigned long flags;
+	struct ipu_csi *csi, *ret;
+
+	if (id > 1)
+		return ERR_PTR(-EINVAL);
+
+	csi = ipu->csi_priv[id];
+	ret = csi;
+
+	spin_lock_irqsave(&csi->lock, flags);
+
+	if (csi->inuse) {
+		ret = ERR_PTR(-EBUSY);
+		goto unlock;
+	}
+
+	csi->inuse = true;
+unlock:
+	spin_unlock_irqrestore(&csi->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_csi_get);
+
+void ipu_csi_put(struct ipu_csi *csi)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&csi->lock, flags);
+	csi->inuse = false;
+	spin_unlock_irqrestore(&csi->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_csi_put);
+
+int ipu_csi_init(struct ipu_soc *ipu, struct device *dev, int id,
+		 unsigned long base, u32 module, struct clk *clk_ipu)
+{
+	struct ipu_csi *csi;
+
+	if (id > 1)
+		return -ENODEV;
+
+	csi = devm_kzalloc(dev, sizeof(*csi), GFP_KERNEL);
+	if (!csi)
+		return -ENOMEM;
+
+	ipu->csi_priv[id] = csi;
+
+	spin_lock_init(&csi->lock);
+	csi->module = module;
+	csi->id = id;
+	csi->clk_ipu = clk_ipu;
+	csi->base = devm_ioremap(dev, base, PAGE_SIZE);
+	if (!csi->base)
+		return -ENOMEM;
+
+	dev_dbg(dev, "CSI%d base: 0x%08lx remapped to %p\n",
+		id, base, csi->base);
+	csi->ipu = ipu;
+
+	return 0;
+}
+
+void ipu_csi_exit(struct ipu_soc *ipu, int id)
+{
+}
+
+void ipu_csi_dump(struct ipu_csi *csi)
+{
+	dev_dbg(csi->ipu->dev, "CSI_SENS_CONF:     %08x\n",
+		ipu_csi_read(csi, CSI_SENS_CONF));
+	dev_dbg(csi->ipu->dev, "CSI_SENS_FRM_SIZE: %08x\n",
+		ipu_csi_read(csi, CSI_SENS_FRM_SIZE));
+	dev_dbg(csi->ipu->dev, "CSI_ACT_FRM_SIZE:  %08x\n",
+		ipu_csi_read(csi, CSI_ACT_FRM_SIZE));
+	dev_dbg(csi->ipu->dev, "CSI_OUT_FRM_CTRL:  %08x\n",
+		ipu_csi_read(csi, CSI_OUT_FRM_CTRL));
+	dev_dbg(csi->ipu->dev, "CSI_TST_CTRL:      %08x\n",
+		ipu_csi_read(csi, CSI_TST_CTRL));
+	dev_dbg(csi->ipu->dev, "CSI_CCIR_CODE_1:   %08x\n",
+		ipu_csi_read(csi, CSI_CCIR_CODE_1));
+	dev_dbg(csi->ipu->dev, "CSI_CCIR_CODE_2:   %08x\n",
+		ipu_csi_read(csi, CSI_CCIR_CODE_2));
+	dev_dbg(csi->ipu->dev, "CSI_CCIR_CODE_3:   %08x\n",
+		ipu_csi_read(csi, CSI_CCIR_CODE_3));
+	dev_dbg(csi->ipu->dev, "CSI_MIPI_DI:       %08x\n",
+		ipu_csi_read(csi, CSI_MIPI_DI));
+	dev_dbg(csi->ipu->dev, "CSI_SKIP:          %08x\n",
+		ipu_csi_read(csi, CSI_SKIP));
+}
+EXPORT_SYMBOL_GPL(ipu_csi_dump);
diff --git a/drivers/gpu/ipu-v3/ipu-ic.c b/drivers/gpu/ipu-v3/ipu-ic.c
new file mode 100644
index 000000000000..ad75588e1629
--- /dev/null
+++ b/drivers/gpu/ipu-v3/ipu-ic.c
@@ -0,0 +1,778 @@
+/*
+ * Copyright (C) 2012-2014 Mentor Graphics Inc.
+ * Copyright 2005-2012 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/bitrev.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include "ipu-prv.h"
+
+/* IC Register Offsets */
+#define IC_CONF                 0x0000
+#define IC_PRP_ENC_RSC          0x0004
+#define IC_PRP_VF_RSC           0x0008
+#define IC_PP_RSC               0x000C
+#define IC_CMBP_1               0x0010
+#define IC_CMBP_2               0x0014
+#define IC_IDMAC_1              0x0018
+#define IC_IDMAC_2              0x001C
+#define IC_IDMAC_3              0x0020
+#define IC_IDMAC_4              0x0024
+
+/* IC Register Fields */
+#define IC_CONF_PRPENC_EN       (1 << 0)
+#define IC_CONF_PRPENC_CSC1     (1 << 1)
+#define IC_CONF_PRPENC_ROT_EN   (1 << 2)
+#define IC_CONF_PRPVF_EN        (1 << 8)
+#define IC_CONF_PRPVF_CSC1      (1 << 9)
+#define IC_CONF_PRPVF_CSC2      (1 << 10)
+#define IC_CONF_PRPVF_CMB       (1 << 11)
+#define IC_CONF_PRPVF_ROT_EN    (1 << 12)
+#define IC_CONF_PP_EN           (1 << 16)
+#define IC_CONF_PP_CSC1         (1 << 17)
+#define IC_CONF_PP_CSC2         (1 << 18)
+#define IC_CONF_PP_CMB          (1 << 19)
+#define IC_CONF_PP_ROT_EN       (1 << 20)
+#define IC_CONF_IC_GLB_LOC_A    (1 << 28)
+#define IC_CONF_KEY_COLOR_EN    (1 << 29)
+#define IC_CONF_RWS_EN          (1 << 30)
+#define IC_CONF_CSI_MEM_WR_EN   (1 << 31)
+
+#define IC_IDMAC_1_CB0_BURST_16         (1 << 0)
+#define IC_IDMAC_1_CB1_BURST_16         (1 << 1)
+#define IC_IDMAC_1_CB2_BURST_16         (1 << 2)
+#define IC_IDMAC_1_CB3_BURST_16         (1 << 3)
+#define IC_IDMAC_1_CB4_BURST_16         (1 << 4)
+#define IC_IDMAC_1_CB5_BURST_16         (1 << 5)
+#define IC_IDMAC_1_CB6_BURST_16         (1 << 6)
+#define IC_IDMAC_1_CB7_BURST_16         (1 << 7)
+#define IC_IDMAC_1_PRPENC_ROT_MASK      (0x7 << 11)
+#define IC_IDMAC_1_PRPENC_ROT_OFFSET    11
+#define IC_IDMAC_1_PRPVF_ROT_MASK       (0x7 << 14)
+#define IC_IDMAC_1_PRPVF_ROT_OFFSET     14
+#define IC_IDMAC_1_PP_ROT_MASK          (0x7 << 17)
+#define IC_IDMAC_1_PP_ROT_OFFSET        17
+#define IC_IDMAC_1_PP_FLIP_RS           (1 << 22)
+#define IC_IDMAC_1_PRPVF_FLIP_RS        (1 << 21)
+#define IC_IDMAC_1_PRPENC_FLIP_RS       (1 << 20)
+
+#define IC_IDMAC_2_PRPENC_HEIGHT_MASK   (0x3ff << 0)
+#define IC_IDMAC_2_PRPENC_HEIGHT_OFFSET 0
+#define IC_IDMAC_2_PRPVF_HEIGHT_MASK    (0x3ff << 10)
+#define IC_IDMAC_2_PRPVF_HEIGHT_OFFSET  10
+#define IC_IDMAC_2_PP_HEIGHT_MASK       (0x3ff << 20)
+#define IC_IDMAC_2_PP_HEIGHT_OFFSET     20
+
+#define IC_IDMAC_3_PRPENC_WIDTH_MASK    (0x3ff << 0)
+#define IC_IDMAC_3_PRPENC_WIDTH_OFFSET  0
+#define IC_IDMAC_3_PRPVF_WIDTH_MASK     (0x3ff << 10)
+#define IC_IDMAC_3_PRPVF_WIDTH_OFFSET   10
+#define IC_IDMAC_3_PP_WIDTH_MASK        (0x3ff << 20)
+#define IC_IDMAC_3_PP_WIDTH_OFFSET      20
+
+struct ic_task_regoffs {
+	u32 rsc;
+	u32 tpmem_csc[2];
+};
+
+struct ic_task_bitfields {
+	u32 ic_conf_en;
+	u32 ic_conf_rot_en;
+	u32 ic_conf_cmb_en;
+	u32 ic_conf_csc1_en;
+	u32 ic_conf_csc2_en;
+	u32 ic_cmb_galpha_bit;
+};
+
+static const struct ic_task_regoffs ic_task_reg[IC_NUM_TASKS] = {
+	[IC_TASK_ENCODER] = {
+		.rsc = IC_PRP_ENC_RSC,
+		.tpmem_csc = {0x2008, 0},
+	},
+	[IC_TASK_VIEWFINDER] = {
+		.rsc = IC_PRP_VF_RSC,
+		.tpmem_csc = {0x4028, 0x4040},
+	},
+	[IC_TASK_POST_PROCESSOR] = {
+		.rsc = IC_PP_RSC,
+		.tpmem_csc = {0x6060, 0x6078},
+	},
+};
+
+static const struct ic_task_bitfields ic_task_bit[IC_NUM_TASKS] = {
+	[IC_TASK_ENCODER] = {
+		.ic_conf_en = IC_CONF_PRPENC_EN,
+		.ic_conf_rot_en = IC_CONF_PRPENC_ROT_EN,
+		.ic_conf_cmb_en = 0,    /* NA */
+		.ic_conf_csc1_en = IC_CONF_PRPENC_CSC1,
+		.ic_conf_csc2_en = 0,   /* NA */
+		.ic_cmb_galpha_bit = 0, /* NA */
+	},
+	[IC_TASK_VIEWFINDER] = {
+		.ic_conf_en = IC_CONF_PRPVF_EN,
+		.ic_conf_rot_en = IC_CONF_PRPVF_ROT_EN,
+		.ic_conf_cmb_en = IC_CONF_PRPVF_CMB,
+		.ic_conf_csc1_en = IC_CONF_PRPVF_CSC1,
+		.ic_conf_csc2_en = IC_CONF_PRPVF_CSC2,
+		.ic_cmb_galpha_bit = 0,
+	},
+	[IC_TASK_POST_PROCESSOR] = {
+		.ic_conf_en = IC_CONF_PP_EN,
+		.ic_conf_rot_en = IC_CONF_PP_ROT_EN,
+		.ic_conf_cmb_en = IC_CONF_PP_CMB,
+		.ic_conf_csc1_en = IC_CONF_PP_CSC1,
+		.ic_conf_csc2_en = IC_CONF_PP_CSC2,
+		.ic_cmb_galpha_bit = 8,
+	},
+};
+
+struct ipu_ic_priv;
+
+struct ipu_ic {
+	enum ipu_ic_task task;
+	const struct ic_task_regoffs *reg;
+	const struct ic_task_bitfields *bit;
+
+	enum ipu_color_space in_cs, g_in_cs;
+	enum ipu_color_space out_cs;
+	bool graphics;
+	bool rotation;
+	bool in_use;
+
+	struct ipu_ic_priv *priv;
+};
+
+struct ipu_ic_priv {
+	void __iomem *base;
+	void __iomem *tpmem_base;
+	spinlock_t lock;
+	struct ipu_soc *ipu;
+	int use_count;
+	struct ipu_ic task[IC_NUM_TASKS];
+};
+
+static inline u32 ipu_ic_read(struct ipu_ic *ic, unsigned offset)
+{
+	return readl(ic->priv->base + offset);
+}
+
+static inline void ipu_ic_write(struct ipu_ic *ic, u32 value, unsigned offset)
+{
+	writel(value, ic->priv->base + offset);
+}
+
+struct ic_csc_params {
+	s16 coeff[3][3];	/* signed 9-bit integer coefficients */
+	s16 offset[3];		/* signed 11+2-bit fixed point offset */
+	u8 scale:2;		/* scale coefficients * 2^(scale-1) */
+	bool sat:1;		/* saturate to (16, 235(Y) / 240(U, V)) */
+};
+
+/*
+ * Y = R *  .299 + G *  .587 + B *  .114;
+ * U = R * -.169 + G * -.332 + B *  .500 + 128.;
+ * V = R *  .500 + G * -.419 + B * -.0813 + 128.;
+ */
+static const struct ic_csc_params ic_csc_rgb2ycbcr = {
+	.coeff = {
+		{ 77, 150, 29 },
+		{ 469, 427, 128 },
+		{ 128, 405, 491 },
+	},
+	.offset = { 0, 512, 512 },
+	.scale = 1,
+};
+
+/* transparent RGB->RGB matrix for graphics combining */
+static const struct ic_csc_params ic_csc_rgb2rgb = {
+	.coeff = {
+		{ 128, 0, 0 },
+		{ 0, 128, 0 },
+		{ 0, 0, 128 },
+	},
+	.scale = 2,
+};
+
+/*
+ * R = (1.164 * (Y - 16)) + (1.596 * (Cr - 128));
+ * G = (1.164 * (Y - 16)) - (0.392 * (Cb - 128)) - (0.813 * (Cr - 128));
+ * B = (1.164 * (Y - 16)) + (2.017 * (Cb - 128);
+ */
+static const struct ic_csc_params ic_csc_ycbcr2rgb = {
+	.coeff = {
+		{ 149, 0, 204 },
+		{ 149, 462, 408 },
+		{ 149, 255, 0 },
+	},
+	.offset = { -446, 266, -554 },
+	.scale = 2,
+};
+
+static int init_csc(struct ipu_ic *ic,
+		    enum ipu_color_space inf,
+		    enum ipu_color_space outf,
+		    int csc_index)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	const struct ic_csc_params *params;
+	u32 __iomem *base;
+	const u16 (*c)[3];
+	const u16 *a;
+	u32 param;
+
+	base = (u32 __iomem *)
+		(priv->tpmem_base + ic->reg->tpmem_csc[csc_index]);
+
+	if (inf == IPUV3_COLORSPACE_YUV && outf == IPUV3_COLORSPACE_RGB)
+		params = &ic_csc_ycbcr2rgb;
+	else if (inf == IPUV3_COLORSPACE_RGB && outf == IPUV3_COLORSPACE_YUV)
+		params = &ic_csc_rgb2ycbcr;
+	else if (inf == IPUV3_COLORSPACE_RGB && outf == IPUV3_COLORSPACE_RGB)
+		params = &ic_csc_rgb2rgb;
+	else {
+		dev_err(priv->ipu->dev, "Unsupported color space conversion\n");
+		return -EINVAL;
+	}
+
+	/* Cast to unsigned */
+	c = (const u16 (*)[3])params->coeff;
+	a = (const u16 *)params->offset;
+
+	param = ((a[0] & 0x1f) << 27) | ((c[0][0] & 0x1ff) << 18) |
+		((c[1][1] & 0x1ff) << 9) | (c[2][2] & 0x1ff);
+	writel(param, base++);
+
+	param = ((a[0] & 0x1fe0) >> 5) | (params->scale << 8) |
+		(params->sat << 9);
+	writel(param, base++);
+
+	param = ((a[1] & 0x1f) << 27) | ((c[0][1] & 0x1ff) << 18) |
+		((c[1][0] & 0x1ff) << 9) | (c[2][0] & 0x1ff);
+	writel(param, base++);
+
+	param = ((a[1] & 0x1fe0) >> 5);
+	writel(param, base++);
+
+	param = ((a[2] & 0x1f) << 27) | ((c[0][2] & 0x1ff) << 18) |
+		((c[1][2] & 0x1ff) << 9) | (c[2][1] & 0x1ff);
+	writel(param, base++);
+
+	param = ((a[2] & 0x1fe0) >> 5);
+	writel(param, base++);
+
+	return 0;
+}
+
+static int calc_resize_coeffs(struct ipu_ic *ic,
+			      u32 in_size, u32 out_size,
+			      u32 *resize_coeff,
+			      u32 *downsize_coeff)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	struct ipu_soc *ipu = priv->ipu;
+	u32 temp_size, temp_downsize;
+
+	/*
+	 * Input size cannot be more than 4096, and output size cannot
+	 * be more than 1024
+	 */
+	if (in_size > 4096) {
+		dev_err(ipu->dev, "Unsupported resize (in_size > 4096)\n");
+		return -EINVAL;
+	}
+	if (out_size > 1024) {
+		dev_err(ipu->dev, "Unsupported resize (out_size > 1024)\n");
+		return -EINVAL;
+	}
+
+	/* Cannot downsize more than 8:1 */
+	if ((out_size << 3) < in_size) {
+		dev_err(ipu->dev, "Unsupported downsize\n");
+		return -EINVAL;
+	}
+
+	/* Compute downsizing coefficient */
+	temp_downsize = 0;
+	temp_size = in_size;
+	while (((temp_size > 1024) || (temp_size >= out_size * 2)) &&
+	       (temp_downsize < 2)) {
+		temp_size >>= 1;
+		temp_downsize++;
+	}
+	*downsize_coeff = temp_downsize;
+
+	/*
+	 * compute resizing coefficient using the following equation:
+	 * resize_coeff = M * (SI - 1) / (SO - 1)
+	 * where M = 2^13, SI = input size, SO = output size
+	 */
+	*resize_coeff = (8192L * (temp_size - 1)) / (out_size - 1);
+	if (*resize_coeff >= 16384L) {
+		dev_err(ipu->dev, "Warning! Overflow on resize coeff.\n");
+		*resize_coeff = 0x3FFF;
+	}
+
+	return 0;
+}
+
+void ipu_ic_task_enable(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+	u32 ic_conf;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	ic_conf = ipu_ic_read(ic, IC_CONF);
+
+	ic_conf |= ic->bit->ic_conf_en;
+
+	if (ic->rotation)
+		ic_conf |= ic->bit->ic_conf_rot_en;
+
+	if (ic->in_cs != ic->out_cs)
+		ic_conf |= ic->bit->ic_conf_csc1_en;
+
+	if (ic->graphics) {
+		ic_conf |= ic->bit->ic_conf_cmb_en;
+		ic_conf |= ic->bit->ic_conf_csc1_en;
+
+		if (ic->g_in_cs != ic->out_cs)
+			ic_conf |= ic->bit->ic_conf_csc2_en;
+	}
+
+	ipu_ic_write(ic, ic_conf, IC_CONF);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_ic_task_enable);
+
+void ipu_ic_task_disable(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+	u32 ic_conf;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	ic_conf = ipu_ic_read(ic, IC_CONF);
+
+	ic_conf &= ~(ic->bit->ic_conf_en |
+		     ic->bit->ic_conf_csc1_en |
+		     ic->bit->ic_conf_rot_en);
+	if (ic->bit->ic_conf_csc2_en)
+		ic_conf &= ~ic->bit->ic_conf_csc2_en;
+	if (ic->bit->ic_conf_cmb_en)
+		ic_conf &= ~ic->bit->ic_conf_cmb_en;
+
+	ipu_ic_write(ic, ic_conf, IC_CONF);
+
+	ic->rotation = ic->graphics = false;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_ic_task_disable);
+
+int ipu_ic_task_graphics_init(struct ipu_ic *ic,
+			      enum ipu_color_space in_g_cs,
+			      bool galpha_en, u32 galpha,
+			      bool colorkey_en, u32 colorkey)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+	u32 reg, ic_conf;
+	int ret = 0;
+
+	if (ic->task == IC_TASK_ENCODER)
+		return -EINVAL;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	ic_conf = ipu_ic_read(ic, IC_CONF);
+
+	if (!(ic_conf & ic->bit->ic_conf_csc1_en)) {
+		/* need transparent CSC1 conversion */
+		ret = init_csc(ic, IPUV3_COLORSPACE_RGB,
+			       IPUV3_COLORSPACE_RGB, 0);
+		if (ret)
+			goto unlock;
+	}
+
+	ic->g_in_cs = in_g_cs;
+
+	if (ic->g_in_cs != ic->out_cs) {
+		ret = init_csc(ic, ic->g_in_cs, ic->out_cs, 1);
+		if (ret)
+			goto unlock;
+	}
+
+	if (galpha_en) {
+		ic_conf |= IC_CONF_IC_GLB_LOC_A;
+		reg = ipu_ic_read(ic, IC_CMBP_1);
+		reg &= ~(0xff << ic->bit->ic_cmb_galpha_bit);
+		reg |= (galpha << ic->bit->ic_cmb_galpha_bit);
+		ipu_ic_write(ic, reg, IC_CMBP_1);
+	} else
+		ic_conf &= ~IC_CONF_IC_GLB_LOC_A;
+
+	if (colorkey_en) {
+		ic_conf |= IC_CONF_KEY_COLOR_EN;
+		ipu_ic_write(ic, colorkey, IC_CMBP_2);
+	} else
+		ic_conf &= ~IC_CONF_KEY_COLOR_EN;
+
+	ipu_ic_write(ic, ic_conf, IC_CONF);
+
+	ic->graphics = true;
+unlock:
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_task_graphics_init);
+
+int ipu_ic_task_init(struct ipu_ic *ic,
+		     int in_width, int in_height,
+		     int out_width, int out_height,
+		     enum ipu_color_space in_cs,
+		     enum ipu_color_space out_cs)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	u32 reg, downsize_coeff, resize_coeff;
+	unsigned long flags;
+	int ret = 0;
+
+	/* Setup vertical resizing */
+	ret = calc_resize_coeffs(ic, in_height, out_height,
+				 &resize_coeff, &downsize_coeff);
+	if (ret)
+		return ret;
+
+	reg = (downsize_coeff << 30) | (resize_coeff << 16);
+
+	/* Setup horizontal resizing */
+	ret = calc_resize_coeffs(ic, in_width, out_width,
+				 &resize_coeff, &downsize_coeff);
+	if (ret)
+		return ret;
+
+	reg |= (downsize_coeff << 14) | resize_coeff;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	ipu_ic_write(ic, reg, ic->reg->rsc);
+
+	/* Setup color space conversion */
+	ic->in_cs = in_cs;
+	ic->out_cs = out_cs;
+
+	if (ic->in_cs != ic->out_cs) {
+		ret = init_csc(ic, ic->in_cs, ic->out_cs, 0);
+		if (ret)
+			goto unlock;
+	}
+
+unlock:
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_task_init);
+
+int ipu_ic_task_idma_init(struct ipu_ic *ic, struct ipuv3_channel *channel,
+			  u32 width, u32 height, int burst_size,
+			  enum ipu_rotate_mode rot)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	struct ipu_soc *ipu = priv->ipu;
+	u32 ic_idmac_1, ic_idmac_2, ic_idmac_3;
+	u32 temp_rot = bitrev8(rot) >> 5;
+	bool need_hor_flip = false;
+	unsigned long flags;
+	int ret = 0;
+
+	if ((burst_size != 8) && (burst_size != 16)) {
+		dev_err(ipu->dev, "Illegal burst length for IC\n");
+		return -EINVAL;
+	}
+
+	width--;
+	height--;
+
+	if (temp_rot & 0x2)	/* Need horizontal flip */
+		need_hor_flip = true;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	ic_idmac_1 = ipu_ic_read(ic, IC_IDMAC_1);
+	ic_idmac_2 = ipu_ic_read(ic, IC_IDMAC_2);
+	ic_idmac_3 = ipu_ic_read(ic, IC_IDMAC_3);
+
+	switch (channel->num) {
+	case IPUV3_CHANNEL_IC_PP_MEM:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB2_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB2_BURST_16;
+
+		if (need_hor_flip)
+			ic_idmac_1 |= IC_IDMAC_1_PP_FLIP_RS;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_PP_FLIP_RS;
+
+		ic_idmac_2 &= ~IC_IDMAC_2_PP_HEIGHT_MASK;
+		ic_idmac_2 |= height << IC_IDMAC_2_PP_HEIGHT_OFFSET;
+
+		ic_idmac_3 &= ~IC_IDMAC_3_PP_WIDTH_MASK;
+		ic_idmac_3 |= width << IC_IDMAC_3_PP_WIDTH_OFFSET;
+		break;
+	case IPUV3_CHANNEL_MEM_IC_PP:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB5_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB5_BURST_16;
+		break;
+	case IPUV3_CHANNEL_MEM_ROT_PP:
+		ic_idmac_1 &= ~IC_IDMAC_1_PP_ROT_MASK;
+		ic_idmac_1 |= temp_rot << IC_IDMAC_1_PP_ROT_OFFSET;
+		break;
+	case IPUV3_CHANNEL_MEM_IC_PRP_VF:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB6_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB6_BURST_16;
+		break;
+	case IPUV3_CHANNEL_IC_PRP_ENC_MEM:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB0_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB0_BURST_16;
+
+		if (need_hor_flip)
+			ic_idmac_1 |= IC_IDMAC_1_PRPENC_FLIP_RS;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_PRPENC_FLIP_RS;
+
+		ic_idmac_2 &= ~IC_IDMAC_2_PRPENC_HEIGHT_MASK;
+		ic_idmac_2 |= height << IC_IDMAC_2_PRPENC_HEIGHT_OFFSET;
+
+		ic_idmac_3 &= ~IC_IDMAC_3_PRPENC_WIDTH_MASK;
+		ic_idmac_3 |= width << IC_IDMAC_3_PRPENC_WIDTH_OFFSET;
+		break;
+	case IPUV3_CHANNEL_MEM_ROT_ENC:
+		ic_idmac_1 &= ~IC_IDMAC_1_PRPENC_ROT_MASK;
+		ic_idmac_1 |= temp_rot << IC_IDMAC_1_PRPENC_ROT_OFFSET;
+		break;
+	case IPUV3_CHANNEL_IC_PRP_VF_MEM:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB1_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB1_BURST_16;
+
+		if (need_hor_flip)
+			ic_idmac_1 |= IC_IDMAC_1_PRPVF_FLIP_RS;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_PRPVF_FLIP_RS;
+
+		ic_idmac_2 &= ~IC_IDMAC_2_PRPVF_HEIGHT_MASK;
+		ic_idmac_2 |= height << IC_IDMAC_2_PRPVF_HEIGHT_OFFSET;
+
+		ic_idmac_3 &= ~IC_IDMAC_3_PRPVF_WIDTH_MASK;
+		ic_idmac_3 |= width << IC_IDMAC_3_PRPVF_WIDTH_OFFSET;
+		break;
+	case IPUV3_CHANNEL_MEM_ROT_VF:
+		ic_idmac_1 &= ~IC_IDMAC_1_PRPVF_ROT_MASK;
+		ic_idmac_1 |= temp_rot << IC_IDMAC_1_PRPVF_ROT_OFFSET;
+		break;
+	case IPUV3_CHANNEL_G_MEM_IC_PRP_VF:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB3_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB3_BURST_16;
+		break;
+	case IPUV3_CHANNEL_G_MEM_IC_PP:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB4_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB4_BURST_16;
+		break;
+	case IPUV3_CHANNEL_VDI_MEM_IC_VF:
+		if (burst_size == 16)
+			ic_idmac_1 |= IC_IDMAC_1_CB7_BURST_16;
+		else
+			ic_idmac_1 &= ~IC_IDMAC_1_CB7_BURST_16;
+		break;
+	default:
+		goto unlock;
+	}
+
+	ipu_ic_write(ic, ic_idmac_1, IC_IDMAC_1);
+	ipu_ic_write(ic, ic_idmac_2, IC_IDMAC_2);
+	ipu_ic_write(ic, ic_idmac_3, IC_IDMAC_3);
+
+	if (rot >= IPU_ROTATE_90_RIGHT)
+		ic->rotation = true;
+
+unlock:
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_task_idma_init);
+
+int ipu_ic_enable(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+	u32 module = IPU_CONF_IC_EN;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	if (ic->rotation)
+		module |= IPU_CONF_ROT_EN;
+
+	if (!priv->use_count)
+		ipu_module_enable(priv->ipu, module);
+
+	priv->use_count++;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_enable);
+
+int ipu_ic_disable(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+	u32 module = IPU_CONF_IC_EN | IPU_CONF_ROT_EN;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	priv->use_count--;
+
+	if (!priv->use_count)
+		ipu_module_disable(priv->ipu, module);
+
+	if (priv->use_count < 0)
+		priv->use_count = 0;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_disable);
+
+struct ipu_ic *ipu_ic_get(struct ipu_soc *ipu, enum ipu_ic_task task)
+{
+	struct ipu_ic_priv *priv = ipu->ic_priv;
+	unsigned long flags;
+	struct ipu_ic *ic, *ret;
+
+	if (task >= IC_NUM_TASKS)
+		return ERR_PTR(-EINVAL);
+
+	ic = &priv->task[task];
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	if (ic->in_use) {
+		ret = ERR_PTR(-EBUSY);
+		goto unlock;
+	}
+
+	ic->in_use = true;
+	ret = ic;
+
+unlock:
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_ic_get);
+
+void ipu_ic_put(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	ic->in_use = false;
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_ic_put);
+
+int ipu_ic_init(struct ipu_soc *ipu, struct device *dev,
+		unsigned long base, unsigned long tpmem_base)
+{
+	struct ipu_ic_priv *priv;
+	int i;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	ipu->ic_priv = priv;
+
+	spin_lock_init(&priv->lock);
+	priv->base = devm_ioremap(dev, base, PAGE_SIZE);
+	if (!priv->base)
+		return -ENOMEM;
+	priv->tpmem_base = devm_ioremap(dev, tpmem_base, SZ_64K);
+	if (!priv->tpmem_base)
+		return -ENOMEM;
+
+	dev_dbg(dev, "IC base: 0x%08lx remapped to %p\n", base, priv->base);
+
+	priv->ipu = ipu;
+
+	for (i = 0; i < IC_NUM_TASKS; i++) {
+		priv->task[i].task = i;
+		priv->task[i].priv = priv;
+		priv->task[i].reg = &ic_task_reg[i];
+		priv->task[i].bit = &ic_task_bit[i];
+	}
+
+	return 0;
+}
+
+void ipu_ic_exit(struct ipu_soc *ipu)
+{
+}
+
+void ipu_ic_dump(struct ipu_ic *ic)
+{
+	struct ipu_ic_priv *priv = ic->priv;
+	struct ipu_soc *ipu = priv->ipu;
+
+	dev_dbg(ipu->dev, "IC_CONF = \t0x%08X\n",
+		ipu_ic_read(ic, IC_CONF));
+	dev_dbg(ipu->dev, "IC_PRP_ENC_RSC = \t0x%08X\n",
+		ipu_ic_read(ic, IC_PRP_ENC_RSC));
+	dev_dbg(ipu->dev, "IC_PRP_VF_RSC = \t0x%08X\n",
+		ipu_ic_read(ic, IC_PRP_VF_RSC));
+	dev_dbg(ipu->dev, "IC_PP_RSC = \t0x%08X\n",
+		ipu_ic_read(ic, IC_PP_RSC));
+	dev_dbg(ipu->dev, "IC_CMBP_1 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_CMBP_1));
+	dev_dbg(ipu->dev, "IC_CMBP_2 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_CMBP_2));
+	dev_dbg(ipu->dev, "IC_IDMAC_1 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_IDMAC_1));
+	dev_dbg(ipu->dev, "IC_IDMAC_2 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_IDMAC_2));
+	dev_dbg(ipu->dev, "IC_IDMAC_3 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_IDMAC_3));
+	dev_dbg(ipu->dev, "IC_IDMAC_4 = \t0x%08X\n",
+		ipu_ic_read(ic, IC_IDMAC_4));
+}
+EXPORT_SYMBOL_GPL(ipu_ic_dump);
diff --git a/drivers/gpu/ipu-v3/ipu-prv.h b/drivers/gpu/ipu-v3/ipu-prv.h
index 0a7b2adaba39..bfb1e8a4483f 100644
--- a/drivers/gpu/ipu-v3/ipu-prv.h
+++ b/drivers/gpu/ipu-v3/ipu-prv.h
@@ -24,23 +24,6 @@ struct ipu_soc;
 
 #include <video/imx-ipu-v3.h>
 
-#define IPUV3_CHANNEL_CSI0			 0
-#define IPUV3_CHANNEL_CSI1			 1
-#define IPUV3_CHANNEL_CSI2			 2
-#define IPUV3_CHANNEL_CSI3			 3
-#define IPUV3_CHANNEL_MEM_BG_SYNC		23
-#define IPUV3_CHANNEL_MEM_FG_SYNC		27
-#define IPUV3_CHANNEL_MEM_DC_SYNC		28
-#define IPUV3_CHANNEL_MEM_FG_SYNC_ALPHA		31
-#define IPUV3_CHANNEL_MEM_DC_ASYNC		41
-#define IPUV3_CHANNEL_ROT_ENC_MEM		45
-#define IPUV3_CHANNEL_ROT_VF_MEM		46
-#define IPUV3_CHANNEL_ROT_PP_MEM		47
-#define IPUV3_CHANNEL_ROT_ENC_MEM_OUT		48
-#define IPUV3_CHANNEL_ROT_VF_MEM_OUT		49
-#define IPUV3_CHANNEL_ROT_PP_MEM_OUT		50
-#define IPUV3_CHANNEL_MEM_BG_SYNC_ALPHA		51
-
 #define IPU_MCU_T_DEFAULT	8
 #define IPU_CM_IDMAC_REG_OFS	0x00008000
 #define IPU_CM_IC_REG_OFS	0x00020000
@@ -85,6 +68,7 @@ struct ipu_soc;
 #define IPU_DISP_TASK_STAT		IPU_CM_REG(0x0254)
 #define IPU_CHA_BUF0_RDY(ch)		IPU_CM_REG(0x0268 + 4 * ((ch) / 32))
 #define IPU_CHA_BUF1_RDY(ch)		IPU_CM_REG(0x0270 + 4 * ((ch) / 32))
+#define IPU_CHA_BUF2_RDY(ch)		IPU_CM_REG(0x0288 + 4 * ((ch) / 32))
 #define IPU_ALT_CHA_BUF0_RDY(ch)	IPU_CM_REG(0x0278 + 4 * ((ch) / 32))
 #define IPU_ALT_CHA_BUF1_RDY(ch)	IPU_CM_REG(0x0280 + 4 * ((ch) / 32))
 
@@ -149,9 +133,11 @@ struct ipuv3_channel {
 };
 
 struct ipu_cpmem;
+struct ipu_csi;
 struct ipu_dc_priv;
 struct ipu_dmfc_priv;
 struct ipu_di;
+struct ipu_ic_priv;
 struct ipu_smfc_priv;
 
 struct ipu_devtype;
@@ -181,6 +167,8 @@ struct ipu_soc {
 	struct ipu_dp_priv	*dp_priv;
 	struct ipu_dmfc_priv	*dmfc_priv;
 	struct ipu_di		*di_priv[2];
+	struct ipu_csi		*csi_priv[2];
+	struct ipu_ic_priv	*ic_priv;
 	struct ipu_smfc_priv	*smfc_priv;
 };
 
@@ -203,6 +191,14 @@ int ipu_module_disable(struct ipu_soc *ipu, u32 mask);
 bool ipu_idmac_channel_busy(struct ipu_soc *ipu, unsigned int chno);
 int ipu_wait_interrupt(struct ipu_soc *ipu, int irq, int ms);
 
+int ipu_csi_init(struct ipu_soc *ipu, struct device *dev, int id,
+		 unsigned long base, u32 module, struct clk *clk_ipu);
+void ipu_csi_exit(struct ipu_soc *ipu, int id);
+
+int ipu_ic_init(struct ipu_soc *ipu, struct device *dev,
+		unsigned long base, unsigned long tpmem_base);
+void ipu_ic_exit(struct ipu_soc *ipu);
+
 int ipu_di_init(struct ipu_soc *ipu, struct device *dev, int id,
 		unsigned long base, u32 module, struct clk *ipu_clk);
 void ipu_di_exit(struct ipu_soc *ipu, int id);
diff --git a/drivers/gpu/ipu-v3/ipu-smfc.c b/drivers/gpu/ipu-v3/ipu-smfc.c
index e4f85ad286fc..4ef910991413 100644
--- a/drivers/gpu/ipu-v3/ipu-smfc.c
+++ b/drivers/gpu/ipu-v3/ipu-smfc.c
@@ -8,7 +8,6 @@
  * http://www.opensource.org/licenses/gpl-license.html
  * http://www.gnu.org/copyleft/gpl.html
  */
-#define DEBUG
 #include <linux/export.h>
 #include <linux/types.h>
 #include <linux/init.h>
@@ -21,9 +20,18 @@
 
 #include "ipu-prv.h"
 
+struct ipu_smfc {
+	struct ipu_smfc_priv *priv;
+	int chno;
+	bool inuse;
+};
+
 struct ipu_smfc_priv {
 	void __iomem *base;
 	spinlock_t lock;
+	struct ipu_soc *ipu;
+	struct ipu_smfc channel[4];
+	int use_count;
 };
 
 /*SMFC Registers */
@@ -31,63 +39,166 @@ struct ipu_smfc_priv {
 #define SMFC_WMC	0x0004
 #define SMFC_BS		0x0008
 
-int ipu_smfc_set_burstsize(struct ipu_soc *ipu, int channel, int burstsize)
+int ipu_smfc_set_burstsize(struct ipu_smfc *smfc, int burstsize)
 {
-	struct ipu_smfc_priv *smfc = ipu->smfc_priv;
+	struct ipu_smfc_priv *priv = smfc->priv;
 	unsigned long flags;
 	u32 val, shift;
 
-	spin_lock_irqsave(&smfc->lock, flags);
+	spin_lock_irqsave(&priv->lock, flags);
 
-	shift = channel * 4;
-	val = readl(smfc->base + SMFC_BS);
+	shift = smfc->chno * 4;
+	val = readl(priv->base + SMFC_BS);
 	val &= ~(0xf << shift);
 	val |= burstsize << shift;
-	writel(val, smfc->base + SMFC_BS);
+	writel(val, priv->base + SMFC_BS);
 
-	spin_unlock_irqrestore(&smfc->lock, flags);
+	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ipu_smfc_set_burstsize);
 
-int ipu_smfc_map_channel(struct ipu_soc *ipu, int channel, int csi_id, int mipi_id)
+int ipu_smfc_map_channel(struct ipu_smfc *smfc, int csi_id, int mipi_id)
 {
-	struct ipu_smfc_priv *smfc = ipu->smfc_priv;
+	struct ipu_smfc_priv *priv = smfc->priv;
 	unsigned long flags;
 	u32 val, shift;
 
-	spin_lock_irqsave(&smfc->lock, flags);
+	spin_lock_irqsave(&priv->lock, flags);
 
-	shift = channel * 3;
-	val = readl(smfc->base + SMFC_MAP);
+	shift = smfc->chno * 3;
+	val = readl(priv->base + SMFC_MAP);
 	val &= ~(0x7 << shift);
 	val |= ((csi_id << 2) | mipi_id) << shift;
-	writel(val, smfc->base + SMFC_MAP);
+	writel(val, priv->base + SMFC_MAP);
 
-	spin_unlock_irqrestore(&smfc->lock, flags);
+	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ipu_smfc_map_channel);
 
+int ipu_smfc_set_watermark(struct ipu_smfc *smfc, u32 set_level, u32 clr_level)
+{
+	struct ipu_smfc_priv *priv = smfc->priv;
+	unsigned long flags;
+	u32 val, shift;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	shift = smfc->chno * 6 + (smfc->chno > 1 ? 4 : 0);
+	val = readl(priv->base + SMFC_WMC);
+	val &= ~(0x3f << shift);
+	val |= ((clr_level << 3) | set_level) << shift;
+	writel(val, priv->base + SMFC_WMC);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_set_watermark);
+
+int ipu_smfc_enable(struct ipu_smfc *smfc)
+{
+	struct ipu_smfc_priv *priv = smfc->priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	if (!priv->use_count)
+		ipu_module_enable(priv->ipu, IPU_CONF_SMFC_EN);
+
+	priv->use_count++;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_enable);
+
+int ipu_smfc_disable(struct ipu_smfc *smfc)
+{
+	struct ipu_smfc_priv *priv = smfc->priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	priv->use_count--;
+
+	if (!priv->use_count)
+		ipu_module_disable(priv->ipu, IPU_CONF_SMFC_EN);
+
+	if (priv->use_count < 0)
+		priv->use_count = 0;
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_disable);
+
+struct ipu_smfc *ipu_smfc_get(struct ipu_soc *ipu, unsigned int chno)
+{
+	struct ipu_smfc_priv *priv = ipu->smfc_priv;
+	struct ipu_smfc *smfc, *ret;
+	unsigned long flags;
+
+	if (chno >= 4)
+		return ERR_PTR(-EINVAL);
+
+	smfc = &priv->channel[chno];
+	ret = smfc;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	if (smfc->inuse) {
+		ret = ERR_PTR(-EBUSY);
+		goto unlock;
+	}
+
+	smfc->inuse = true;
+unlock:
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_get);
+
+void ipu_smfc_put(struct ipu_smfc *smfc)
+{
+	struct ipu_smfc_priv *priv = smfc->priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	smfc->inuse = false;
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_put);
+
 int ipu_smfc_init(struct ipu_soc *ipu, struct device *dev,
 		  unsigned long base)
 {
-	struct ipu_smfc_priv *smfc;
+	struct ipu_smfc_priv *priv;
+	int i;
 
-	smfc = devm_kzalloc(dev, sizeof(*smfc), GFP_KERNEL);
-	if (!smfc)
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
 		return -ENOMEM;
 
-	ipu->smfc_priv = smfc;
-	spin_lock_init(&smfc->lock);
+	ipu->smfc_priv = priv;
+	spin_lock_init(&priv->lock);
+	priv->ipu = ipu;
 
-	smfc->base = devm_ioremap(dev, base, PAGE_SIZE);
-	if (!smfc->base)
+	priv->base = devm_ioremap(dev, base, PAGE_SIZE);
+	if (!priv->base)
 		return -ENOMEM;
 
-	pr_debug("%s: ioremap 0x%08lx -> %p\n", __func__, base, smfc->base);
+	for (i = 0; i < 4; i++) {
+		priv->channel[i].priv = priv;
+		priv->channel[i].chno = i;
+	}
+
+	pr_debug("%s: ioremap 0x%08lx -> %p\n", __func__, base, priv->base);
 
 	return 0;
 }
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index 77711623b973..7bcbf863656e 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -400,7 +400,6 @@ int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible)
 		}
 		schedule();
 		remove_wait_queue(&vga_wait_queue, &wait);
-		set_current_state(TASK_RUNNING);
 	}
 	return rc;
 }
diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c
index a822db5a8338..3318de690e00 100644
--- a/drivers/hid/hid-cp2112.c
+++ b/drivers/hid/hid-cp2112.c
@@ -1069,8 +1069,7 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	return ret;
 
 err_gpiochip_remove:
-	if (gpiochip_remove(&dev->gc) < 0)
-		hid_err(hdev, "error removing gpio chip\n");
+	gpiochip_remove(&dev->gc);
 err_free_i2c:
 	i2c_del_adapter(&dev->adap);
 err_free_dev:
@@ -1089,8 +1088,7 @@ static void cp2112_remove(struct hid_device *hdev)
 	struct cp2112_device *dev = hid_get_drvdata(hdev);
 
 	sysfs_remove_group(&hdev->dev.kobj, &cp2112_attr_group);
-	if (gpiochip_remove(&dev->gc))
-		hid_err(hdev, "unable to remove gpio chip\n");
+	gpiochip_remove(&dev->gc);
 	i2c_del_adapter(&dev->adap);
 	/* i2c_del_adapter has finished removing all i2c devices from our
 	 * adapter. Well behaved devices should no longer call our cp2112_xfer
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index f00d048aa583..5286d7ce1f9e 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -280,8 +280,8 @@ config SENSORS_K10TEMP
 	  If you say yes here you get support for the temperature
 	  sensor(s) inside your CPU. Supported are later revisions of
 	  the AMD Family 10h and all revisions of the AMD Family 11h,
-	  12h (Llano), 14h (Brazos), 15h (Bulldozer/Trinity/Kaveri) and
-	  16h (Kabini/Mullins) microarchitectures.
+	  12h (Llano), 14h (Brazos), 15h (Bulldozer/Trinity/Kaveri/Carrizo)
+	  and 16h (Kabini/Mullins) microarchitectures.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called k10temp.
@@ -839,6 +839,16 @@ config SENSORS_MCP3021
 	  This driver can also be built as a module.  If so, the module
 	  will be called mcp3021.
 
+config SENSORS_MENF21BMC_HWMON
+	tristate "MEN 14F021P00 BMC Hardware Monitoring"
+	depends on MFD_MENF21BMC
+	help
+	  Say Y here to include support for the MEN 14F021P00 BMC
+	  hardware monitoring.
+
+	  This driver can also be built as a module. If so the module
+	  will be called menf21bmc_hwmon.
+
 config SENSORS_ADCXX
 	tristate "National Semiconductor ADCxxxSxxx"
 	depends on SPI_MASTER
@@ -1077,6 +1087,7 @@ config SENSORS_PC87427
 config SENSORS_NTC_THERMISTOR
 	tristate "NTC thermistor support from Murata"
 	depends on !OF || IIO=n || IIO
+	depends on THERMAL || !THERMAL_OF
 	help
 	  This driver supports NTC thermistors sensor reading and its
 	  interpretation. The driver can also monitor the temperature and
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index be28152c9848..c90a7611efaa 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -115,6 +115,7 @@ obj-$(CONFIG_SENSORS_MAX6650)	+= max6650.o
 obj-$(CONFIG_SENSORS_MAX6697)	+= max6697.o
 obj-$(CONFIG_SENSORS_MC13783_ADC)+= mc13783-adc.o
 obj-$(CONFIG_SENSORS_MCP3021)	+= mcp3021.o
+obj-$(CONFIG_SENSORS_MENF21BMC_HWMON) += menf21bmc_hwmon.o
 obj-$(CONFIG_SENSORS_NCT6683)	+= nct6683.o
 obj-$(CONFIG_SENSORS_NCT6775)	+= nct6775.o
 obj-$(CONFIG_SENSORS_NTC_THERMISTOR)	+= ntc_thermistor.o
diff --git a/drivers/hwmon/ab8500.c b/drivers/hwmon/ab8500.c
index d844dc806853..8b6a4f4c8774 100644
--- a/drivers/hwmon/ab8500.c
+++ b/drivers/hwmon/ab8500.c
@@ -6,7 +6,7 @@
  *
  * When the AB8500 thermal warning temperature is reached (threshold cannot
  * be changed by SW), an interrupt is set, and if no further action is taken
- * within a certain time frame, pm_power off will be called.
+ * within a certain time frame, kernel_power_off will be called.
  *
  * When AB8500 thermal shutdown temperature is reached a hardware shutdown of
  * the AB8500 will occur.
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/power/ab8500.h>
+#include <linux/reboot.h>
 #include <linux/slab.h>
 #include <linux/sysfs.h>
 #include "abx500.h"
@@ -106,7 +107,7 @@ static void ab8500_thermal_power_off(struct work_struct *work)
 
 	dev_warn(&abx500_data->pdev->dev, "Power off due to critical temp\n");
 
-	pm_power_off();
+	kernel_power_off();
 }
 
 static ssize_t ab8500_show_name(struct device *dev,
diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index 126516414c11..f155b8380481 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -184,20 +184,18 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
 		return -EINVAL;
 
 	for_each_child_of_node(client->dev.of_node, node) {
-		const __be32 *property;
-		int len;
+		u32 pval;
 		unsigned int channel;
 		unsigned int pga = ADS1015_DEFAULT_PGA;
 		unsigned int data_rate = ADS1015_DEFAULT_DATA_RATE;
 
-		property = of_get_property(node, "reg", &len);
-		if (!property || len != sizeof(int)) {
+		if (of_property_read_u32(node, "reg", &pval)) {
 			dev_err(&client->dev, "invalid reg on %s\n",
 				node->full_name);
 			continue;
 		}
 
-		channel = be32_to_cpup(property);
+		channel = pval;
 		if (channel >= ADS1015_CHANNELS) {
 			dev_err(&client->dev,
 				"invalid channel index %d on %s\n",
@@ -205,20 +203,17 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
 			continue;
 		}
 
-		property = of_get_property(node, "ti,gain", &len);
-		if (property && len == sizeof(int)) {
-			pga = be32_to_cpup(property);
+		if (!of_property_read_u32(node, "ti,gain", &pval)) {
+			pga = pval;
 			if (pga > 6) {
-				dev_err(&client->dev,
-					"invalid gain on %s\n",
+				dev_err(&client->dev, "invalid gain on %s\n",
 					node->full_name);
 				return -EINVAL;
 			}
 		}
 
-		property = of_get_property(node, "ti,datarate", &len);
-		if (property && len == sizeof(int)) {
-			data_rate = be32_to_cpup(property);
+		if (!of_property_read_u32(node, "ti,datarate", &pval)) {
+			data_rate = pval;
 			if (data_rate > 7) {
 				dev_err(&client->dev,
 					"invalid data_rate on %s\n",
diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c
index d14ab3c45daa..692b3f34d88c 100644
--- a/drivers/hwmon/da9052-hwmon.c
+++ b/drivers/hwmon/da9052-hwmon.c
@@ -26,7 +26,6 @@
 
 struct da9052_hwmon {
 	struct da9052	*da9052;
-	struct device	*class_device;
 	struct mutex	hwmon_lock;
 };
 
@@ -190,13 +189,6 @@ static ssize_t da9052_read_vbbat(struct device *dev,
 	return sprintf(buf, "%d\n", vbbat_reg_to_mv(ret));
 }
 
-static ssize_t da9052_hwmon_show_name(struct device *dev,
-				      struct device_attribute *devattr,
-				      char *buf)
-{
-	return sprintf(buf, "da9052\n");
-}
-
 static ssize_t show_label(struct device *dev,
 			  struct device_attribute *devattr, char *buf)
 {
@@ -243,10 +235,7 @@ static SENSOR_DEVICE_ATTR(temp8_input, S_IRUGO, da9052_read_tjunc, NULL,
 static SENSOR_DEVICE_ATTR(temp8_label, S_IRUGO, show_label, NULL,
 			  DA9052_ADC_TJUNC);
 
-static DEVICE_ATTR(name, S_IRUGO, da9052_hwmon_show_name, NULL);
-
-static struct attribute *da9052_attr[] = {
-	&dev_attr_name.attr,
+static struct attribute *da9052_attrs[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
 	&sensor_dev_attr_in0_label.dev_attr.attr,
 	&sensor_dev_attr_in3_input.dev_attr.attr,
@@ -268,54 +257,29 @@ static struct attribute *da9052_attr[] = {
 	NULL
 };
 
-static const struct attribute_group da9052_attr_group = {.attrs = da9052_attr};
+ATTRIBUTE_GROUPS(da9052);
 
 static int da9052_hwmon_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct da9052_hwmon *hwmon;
-	int ret;
+	struct device *hwmon_dev;
 
-	hwmon = devm_kzalloc(&pdev->dev, sizeof(struct da9052_hwmon),
-			     GFP_KERNEL);
+	hwmon = devm_kzalloc(dev, sizeof(struct da9052_hwmon), GFP_KERNEL);
 	if (!hwmon)
 		return -ENOMEM;
 
 	mutex_init(&hwmon->hwmon_lock);
 	hwmon->da9052 = dev_get_drvdata(pdev->dev.parent);
 
-	platform_set_drvdata(pdev, hwmon);
-
-	ret = sysfs_create_group(&pdev->dev.kobj, &da9052_attr_group);
-	if (ret)
-		goto err_mem;
-
-	hwmon->class_device = hwmon_device_register(&pdev->dev);
-	if (IS_ERR(hwmon->class_device)) {
-		ret = PTR_ERR(hwmon->class_device);
-		goto err_sysfs;
-	}
-
-	return 0;
-
-err_sysfs:
-	sysfs_remove_group(&pdev->dev.kobj, &da9052_attr_group);
-err_mem:
-	return ret;
-}
-
-static int da9052_hwmon_remove(struct platform_device *pdev)
-{
-	struct da9052_hwmon *hwmon = platform_get_drvdata(pdev);
-
-	hwmon_device_unregister(hwmon->class_device);
-	sysfs_remove_group(&pdev->dev.kobj, &da9052_attr_group);
-
-	return 0;
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, "da9052",
+							   hwmon,
+							   da9052_groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
 static struct platform_driver da9052_hwmon_driver = {
 	.probe = da9052_hwmon_probe,
-	.remove = da9052_hwmon_remove,
 	.driver = {
 		.name = "da9052-hwmon",
 		.owner = THIS_MODULE,
diff --git a/drivers/hwmon/da9055-hwmon.c b/drivers/hwmon/da9055-hwmon.c
index 35eb7738d711..9916a3fb4bb9 100644
--- a/drivers/hwmon/da9055-hwmon.c
+++ b/drivers/hwmon/da9055-hwmon.c
@@ -36,7 +36,6 @@
 
 struct da9055_hwmon {
 	struct da9055	*da9055;
-	struct device	*class_device;
 	struct mutex	hwmon_lock;
 	struct mutex	irq_lock;
 	struct completion done;
@@ -200,13 +199,6 @@ static ssize_t da9055_read_tjunc(struct device *dev,
 							+ 3076332, 10000));
 }
 
-static ssize_t da9055_hwmon_show_name(struct device *dev,
-				      struct device_attribute *devattr,
-				      char *buf)
-{
-	return sprintf(buf, "da9055\n");
-}
-
 static ssize_t show_label(struct device *dev,
 			  struct device_attribute *devattr, char *buf)
 {
@@ -236,10 +228,7 @@ static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, da9055_read_tjunc, NULL,
 static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, show_label, NULL,
 			  DA9055_ADC_TJUNC);
 
-static DEVICE_ATTR(name, S_IRUGO, da9055_hwmon_show_name, NULL);
-
-static struct attribute *da9055_attr[] = {
-	&dev_attr_name.attr,
+static struct attribute *da9055_attrs[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
 	&sensor_dev_attr_in0_label.dev_attr.attr,
 	&sensor_dev_attr_in1_input.dev_attr.attr,
@@ -254,15 +243,16 @@ static struct attribute *da9055_attr[] = {
 	NULL
 };
 
-static const struct attribute_group da9055_attr_group = {.attrs = da9055_attr};
+ATTRIBUTE_GROUPS(da9055);
 
 static int da9055_hwmon_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct da9055_hwmon *hwmon;
+	struct device *hwmon_dev;
 	int hwmon_irq, ret;
 
-	hwmon = devm_kzalloc(&pdev->dev, sizeof(struct da9055_hwmon),
-			     GFP_KERNEL);
+	hwmon = devm_kzalloc(dev, sizeof(struct da9055_hwmon), GFP_KERNEL);
 	if (!hwmon)
 		return -ENOMEM;
 
@@ -272,8 +262,6 @@ static int da9055_hwmon_probe(struct platform_device *pdev)
 	init_completion(&hwmon->done);
 	hwmon->da9055 = dev_get_drvdata(pdev->dev.parent);
 
-	platform_set_drvdata(pdev, hwmon);
-
 	hwmon_irq = platform_get_irq_byname(pdev, "HWMON");
 	if (hwmon_irq < 0)
 		return hwmon_irq;
@@ -288,36 +276,14 @@ static int da9055_hwmon_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = sysfs_create_group(&pdev->dev.kobj, &da9055_attr_group);
-	if (ret)
-		return ret;
-
-	hwmon->class_device = hwmon_device_register(&pdev->dev);
-	if (IS_ERR(hwmon->class_device)) {
-		ret = PTR_ERR(hwmon->class_device);
-		goto err;
-	}
-
-	return 0;
-
-err:
-	sysfs_remove_group(&pdev->dev.kobj, &da9055_attr_group);
-	return ret;
-}
-
-static int da9055_hwmon_remove(struct platform_device *pdev)
-{
-	struct da9055_hwmon *hwmon = platform_get_drvdata(pdev);
-
-	sysfs_remove_group(&pdev->dev.kobj, &da9055_attr_group);
-	hwmon_device_unregister(hwmon->class_device);
-
-	return 0;
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, "da9055",
+							   hwmon,
+							   da9055_groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
 static struct platform_driver da9055_hwmon_driver = {
 	.probe = da9055_hwmon_probe,
-	.remove = da9055_hwmon_remove,
 	.driver = {
 		.name = "da9055-hwmon",
 		.owner = THIS_MODULE,
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index f7b46f68ef43..1e7bdcdcb295 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -33,6 +33,9 @@ static bool force;
 module_param(force, bool, 0444);
 MODULE_PARM_DESC(force, "force loading on processors with erratum 319");
 
+/* Provide lock for writing to NB_SMU_IND_ADDR */
+static DEFINE_MUTEX(nb_smu_ind_mutex);
+
 /* CPUID function 0x80000001, ebx */
 #define CPUID_PKGTYPE_MASK	0xf0000000
 #define CPUID_PKGTYPE_F		0x00000000
@@ -51,13 +54,38 @@ MODULE_PARM_DESC(force, "force loading on processors with erratum 319");
 #define REG_NORTHBRIDGE_CAPABILITIES	0xe8
 #define  NB_CAP_HTC			0x00000400
 
+/*
+ * For F15h M60h, functionality of REG_REPORTED_TEMPERATURE
+ * has been moved to D0F0xBC_xD820_0CA4 [Reported Temperature
+ * Control]
+ */
+#define F15H_M60H_REPORTED_TEMP_CTRL_OFFSET	0xd8200ca4
+#define PCI_DEVICE_ID_AMD_15H_M60H_NB_F3	0x1573
+
+static void amd_nb_smu_index_read(struct pci_dev *pdev, unsigned int devfn,
+				  int offset, u32 *val)
+{
+	mutex_lock(&nb_smu_ind_mutex);
+	pci_bus_write_config_dword(pdev->bus, devfn,
+				   0xb8, offset);
+	pci_bus_read_config_dword(pdev->bus, devfn,
+				  0xbc, val);
+	mutex_unlock(&nb_smu_ind_mutex);
+}
+
 static ssize_t show_temp(struct device *dev,
 			 struct device_attribute *attr, char *buf)
 {
 	u32 regval;
-
-	pci_read_config_dword(to_pci_dev(dev),
-			      REG_REPORTED_TEMPERATURE, &regval);
+	struct pci_dev *pdev = dev_get_drvdata(dev);
+
+	if (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model == 0x60) {
+		amd_nb_smu_index_read(pdev, PCI_DEVFN(0, 0),
+				      F15H_M60H_REPORTED_TEMP_CTRL_OFFSET,
+				      &regval);
+	} else {
+		pci_read_config_dword(pdev, REG_REPORTED_TEMPERATURE, &regval);
+	}
 	return sprintf(buf, "%u\n", (regval >> 21) * 125);
 }
 
@@ -75,7 +103,7 @@ static ssize_t show_temp_crit(struct device *dev,
 	u32 regval;
 	int value;
 
-	pci_read_config_dword(to_pci_dev(dev),
+	pci_read_config_dword(dev_get_drvdata(dev),
 			      REG_HARDWARE_THERMAL_CONTROL, &regval);
 	value = ((regval >> 16) & 0x7f) * 500 + 52000;
 	if (show_hyst)
@@ -83,17 +111,43 @@ static ssize_t show_temp_crit(struct device *dev,
 	return sprintf(buf, "%d\n", value);
 }
 
-static ssize_t show_name(struct device *dev,
-			 struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "k10temp\n");
-}
-
 static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
 static DEVICE_ATTR(temp1_max, S_IRUGO, show_temp_max, NULL);
 static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp_crit, NULL, 0);
 static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IRUGO, show_temp_crit, NULL, 1);
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+
+static umode_t k10temp_is_visible(struct kobject *kobj,
+				  struct attribute *attr, int index)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct pci_dev *pdev = dev_get_drvdata(dev);
+
+	if (index >= 2) {
+		u32 reg_caps, reg_htc;
+
+		pci_read_config_dword(pdev, REG_NORTHBRIDGE_CAPABILITIES,
+				      &reg_caps);
+		pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL,
+				      &reg_htc);
+		if (!(reg_caps & NB_CAP_HTC) || !(reg_htc & HTC_ENABLE))
+			return 0;
+	}
+	return attr->mode;
+}
+
+static struct attribute *k10temp_attrs[] = {
+	&dev_attr_temp1_input.attr,
+	&dev_attr_temp1_max.attr,
+	&sensor_dev_attr_temp1_crit.dev_attr.attr,
+	&sensor_dev_attr_temp1_crit_hyst.dev_attr.attr,
+	NULL
+};
+
+static const struct attribute_group k10temp_group = {
+	.attrs = k10temp_attrs,
+	.is_visible = k10temp_is_visible,
+};
+__ATTRIBUTE_GROUPS(k10temp);
 
 static bool has_erratum_319(struct pci_dev *pdev)
 {
@@ -132,76 +186,23 @@ static bool has_erratum_319(struct pci_dev *pdev)
 static int k10temp_probe(struct pci_dev *pdev,
 				   const struct pci_device_id *id)
 {
-	struct device *hwmon_dev;
-	u32 reg_caps, reg_htc;
 	int unreliable = has_erratum_319(pdev);
-	int err;
-
-	if (unreliable && !force) {
-		dev_err(&pdev->dev,
-			"unreliable CPU thermal sensor; monitoring disabled\n");
-		err = -ENODEV;
-		goto exit;
-	}
-
-	err = device_create_file(&pdev->dev, &dev_attr_temp1_input);
-	if (err)
-		goto exit;
-	err = device_create_file(&pdev->dev, &dev_attr_temp1_max);
-	if (err)
-		goto exit_remove;
-
-	pci_read_config_dword(pdev, REG_NORTHBRIDGE_CAPABILITIES, &reg_caps);
-	pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL, &reg_htc);
-	if ((reg_caps & NB_CAP_HTC) && (reg_htc & HTC_ENABLE)) {
-		err = device_create_file(&pdev->dev,
-				&sensor_dev_attr_temp1_crit.dev_attr);
-		if (err)
-			goto exit_remove;
-		err = device_create_file(&pdev->dev,
-				&sensor_dev_attr_temp1_crit_hyst.dev_attr);
-		if (err)
-			goto exit_remove;
-	}
-
-	err = device_create_file(&pdev->dev, &dev_attr_name);
-	if (err)
-		goto exit_remove;
-
-	hwmon_dev = hwmon_device_register(&pdev->dev);
-	if (IS_ERR(hwmon_dev)) {
-		err = PTR_ERR(hwmon_dev);
-		goto exit_remove;
-	}
-	pci_set_drvdata(pdev, hwmon_dev);
+	struct device *dev = &pdev->dev;
+	struct device *hwmon_dev;
 
-	if (unreliable && force)
-		dev_warn(&pdev->dev,
+	if (unreliable) {
+		if (!force) {
+			dev_err(dev,
+				"unreliable CPU thermal sensor; monitoring disabled\n");
+			return -ENODEV;
+		}
+		dev_warn(dev,
 			 "unreliable CPU thermal sensor; check erratum 319\n");
-	return 0;
-
-exit_remove:
-	device_remove_file(&pdev->dev, &dev_attr_name);
-	device_remove_file(&pdev->dev, &dev_attr_temp1_input);
-	device_remove_file(&pdev->dev, &dev_attr_temp1_max);
-	device_remove_file(&pdev->dev,
-			   &sensor_dev_attr_temp1_crit.dev_attr);
-	device_remove_file(&pdev->dev,
-			   &sensor_dev_attr_temp1_crit_hyst.dev_attr);
-exit:
-	return err;
-}
+	}
 
-static void k10temp_remove(struct pci_dev *pdev)
-{
-	hwmon_device_unregister(pci_get_drvdata(pdev));
-	device_remove_file(&pdev->dev, &dev_attr_name);
-	device_remove_file(&pdev->dev, &dev_attr_temp1_input);
-	device_remove_file(&pdev->dev, &dev_attr_temp1_max);
-	device_remove_file(&pdev->dev,
-			   &sensor_dev_attr_temp1_crit.dev_attr);
-	device_remove_file(&pdev->dev,
-			   &sensor_dev_attr_temp1_crit_hyst.dev_attr);
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, "k10temp", pdev,
+							   k10temp_groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
 static const struct pci_device_id k10temp_id_table[] = {
@@ -211,6 +212,7 @@ static const struct pci_device_id k10temp_id_table[] = {
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
+	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
 	{}
@@ -221,7 +223,6 @@ static struct pci_driver k10temp_driver = {
 	.name = "k10temp",
 	.id_table = k10temp_id_table,
 	.probe = k10temp_probe,
-	.remove = k10temp_remove,
 };
 
 module_pci_driver(k10temp_driver);
diff --git a/drivers/hwmon/menf21bmc_hwmon.c b/drivers/hwmon/menf21bmc_hwmon.c
new file mode 100644
index 000000000000..c92229d321c9
--- /dev/null
+++ b/drivers/hwmon/menf21bmc_hwmon.c
@@ -0,0 +1,230 @@
+/*
+ *  MEN 14F021P00 Board Management Controller (BMC) hwmon driver.
+ *
+ *  This is the core hwmon driver of the MEN 14F021P00 BMC.
+ *  The BMC monitors the board voltages which can be access with this
+ *  driver through sysfs.
+ *
+ *  Copyright (C) 2014 MEN Mikro Elektronik Nuernberg GmbH
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/jiffies.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+
+#define DRV_NAME  "menf21bmc_hwmon"
+
+#define BMC_VOLT_COUNT	5
+#define MENF21BMC_V33	0
+#define MENF21BMC_V5	1
+#define MENF21BMC_V12	2
+#define MENF21BMC_V5_SB	3
+#define MENF21BMC_VBAT	4
+
+#define IDX_TO_VOLT_MIN_CMD(idx) (0x40 + idx)
+#define IDX_TO_VOLT_MAX_CMD(idx) (0x50 + idx)
+#define IDX_TO_VOLT_INP_CMD(idx) (0x60 + idx)
+
+struct menf21bmc_hwmon {
+	bool valid;
+	struct i2c_client *i2c_client;
+	unsigned long last_update;
+	int in_val[BMC_VOLT_COUNT];
+	int in_min[BMC_VOLT_COUNT];
+	int in_max[BMC_VOLT_COUNT];
+};
+
+static const char *const input_names[] = {
+	[MENF21BMC_V33]		= "MON_3_3V",
+	[MENF21BMC_V5]		= "MON_5V",
+	[MENF21BMC_V12]		= "MON_12V",
+	[MENF21BMC_V5_SB]	= "5V_STANDBY",
+	[MENF21BMC_VBAT]	= "VBAT"
+};
+
+static struct menf21bmc_hwmon *menf21bmc_hwmon_update(struct device *dev)
+{
+	int i;
+	int val;
+	struct menf21bmc_hwmon *drv_data = dev_get_drvdata(dev);
+	struct menf21bmc_hwmon *data_ret = drv_data;
+
+	if (time_after(jiffies, drv_data->last_update + HZ)
+	    || !drv_data->valid) {
+		for (i = 0; i < BMC_VOLT_COUNT; i++) {
+			val = i2c_smbus_read_word_data(drv_data->i2c_client,
+						       IDX_TO_VOLT_INP_CMD(i));
+			if (val < 0) {
+				data_ret = ERR_PTR(val);
+				goto abort;
+			}
+			drv_data->in_val[i] = val;
+		}
+		drv_data->last_update = jiffies;
+		drv_data->valid = true;
+	}
+abort:
+	return data_ret;
+}
+
+static int menf21bmc_hwmon_get_volt_limits(struct menf21bmc_hwmon *drv_data)
+{
+	int i, val;
+
+	for (i = 0; i < BMC_VOLT_COUNT; i++) {
+		val = i2c_smbus_read_word_data(drv_data->i2c_client,
+					       IDX_TO_VOLT_MIN_CMD(i));
+		if (val < 0)
+			return val;
+
+		drv_data->in_min[i] = val;
+
+		val = i2c_smbus_read_word_data(drv_data->i2c_client,
+					       IDX_TO_VOLT_MAX_CMD(i));
+		if (val < 0)
+			return val;
+
+		drv_data->in_max[i] = val;
+	}
+	return 0;
+}
+
+static ssize_t
+show_label(struct device *dev, struct device_attribute *devattr, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+
+	return sprintf(buf, "%s\n", input_names[attr->index]);
+}
+
+static ssize_t
+show_in(struct device *dev, struct device_attribute *devattr, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct menf21bmc_hwmon *drv_data = menf21bmc_hwmon_update(dev);
+
+	if (IS_ERR(drv_data))
+		return PTR_ERR(drv_data);
+
+	return sprintf(buf, "%d\n", drv_data->in_val[attr->index]);
+}
+
+static ssize_t
+show_min(struct device *dev, struct device_attribute *devattr, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct menf21bmc_hwmon *drv_data = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", drv_data->in_min[attr->index]);
+}
+
+static ssize_t
+show_max(struct device *dev, struct device_attribute *devattr, char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+	struct menf21bmc_hwmon *drv_data = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", drv_data->in_max[attr->index]);
+}
+
+#define create_voltage_sysfs(idx)			\
+static SENSOR_DEVICE_ATTR(in##idx##_input, S_IRUGO,	\
+			show_in, NULL, idx);		\
+static SENSOR_DEVICE_ATTR(in##idx##_min, S_IRUGO,	\
+			show_min, NULL, idx);		\
+static SENSOR_DEVICE_ATTR(in##idx##_max, S_IRUGO,	\
+			show_max, NULL, idx);		\
+static SENSOR_DEVICE_ATTR(in##idx##_label, S_IRUGO,	\
+			show_label, NULL, idx);
+
+create_voltage_sysfs(0);
+create_voltage_sysfs(1);
+create_voltage_sysfs(2);
+create_voltage_sysfs(3);
+create_voltage_sysfs(4);
+
+static struct attribute *menf21bmc_hwmon_attrs[] = {
+	&sensor_dev_attr_in0_input.dev_attr.attr,
+	&sensor_dev_attr_in0_min.dev_attr.attr,
+	&sensor_dev_attr_in0_max.dev_attr.attr,
+	&sensor_dev_attr_in0_label.dev_attr.attr,
+
+	&sensor_dev_attr_in1_input.dev_attr.attr,
+	&sensor_dev_attr_in1_min.dev_attr.attr,
+	&sensor_dev_attr_in1_max.dev_attr.attr,
+	&sensor_dev_attr_in1_label.dev_attr.attr,
+
+	&sensor_dev_attr_in2_input.dev_attr.attr,
+	&sensor_dev_attr_in2_min.dev_attr.attr,
+	&sensor_dev_attr_in2_max.dev_attr.attr,
+	&sensor_dev_attr_in2_label.dev_attr.attr,
+
+	&sensor_dev_attr_in3_input.dev_attr.attr,
+	&sensor_dev_attr_in3_min.dev_attr.attr,
+	&sensor_dev_attr_in3_max.dev_attr.attr,
+	&sensor_dev_attr_in3_label.dev_attr.attr,
+
+	&sensor_dev_attr_in4_input.dev_attr.attr,
+	&sensor_dev_attr_in4_min.dev_attr.attr,
+	&sensor_dev_attr_in4_max.dev_attr.attr,
+	&sensor_dev_attr_in4_label.dev_attr.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(menf21bmc_hwmon);
+
+static int menf21bmc_hwmon_probe(struct platform_device *pdev)
+{
+	int ret;
+	struct menf21bmc_hwmon *drv_data;
+	struct i2c_client *i2c_client = to_i2c_client(pdev->dev.parent);
+	struct device *hwmon_dev;
+
+	drv_data = devm_kzalloc(&pdev->dev, sizeof(struct menf21bmc_hwmon),
+				GFP_KERNEL);
+	if (!drv_data)
+		return -ENOMEM;
+
+	drv_data->i2c_client = i2c_client;
+
+	ret = menf21bmc_hwmon_get_volt_limits(drv_data);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to read sensor limits");
+		return ret;
+	}
+
+	hwmon_dev = devm_hwmon_device_register_with_groups(&pdev->dev,
+						   "menf21bmc", drv_data,
+						   menf21bmc_hwmon_groups);
+	if (IS_ERR(hwmon_dev))
+		return PTR_ERR(hwmon_dev);
+
+	dev_info(&pdev->dev, "MEN 14F021P00 BMC hwmon device enabled");
+
+	return 0;
+}
+
+static struct platform_driver menf21bmc_hwmon = {
+	.probe		= menf21bmc_hwmon_probe,
+	.driver		= {
+		.name		= DRV_NAME,
+		.owner		= THIS_MODULE,
+	},
+};
+
+module_platform_driver(menf21bmc_hwmon);
+
+MODULE_AUTHOR("Andreas Werner <andreas.werner@men.de>");
+MODULE_DESCRIPTION("MEN 14F021P00 BMC hwmon");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:menf21bmc_hwmon");
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index bd410722cd4b..4ff89b2482e4 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -38,6 +38,7 @@
 
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
+#include <linux/thermal.h>
 
 struct ntc_compensation {
 	int		temp_c;
@@ -182,6 +183,7 @@ struct ntc_data {
 	struct device *dev;
 	int n_comp;
 	char name[PLATFORM_NAME_SIZE];
+	struct thermal_zone_device *tz;
 };
 
 #if defined(CONFIG_OF) && IS_ENABLED(CONFIG_IIO)
@@ -428,6 +430,20 @@ static int ntc_thermistor_get_ohm(struct ntc_data *data)
 	return -EINVAL;
 }
 
+static int ntc_read_temp(void *dev, long *temp)
+{
+	struct ntc_data *data = dev_get_drvdata(dev);
+	int ohm;
+
+	ohm = ntc_thermistor_get_ohm(data);
+	if (ohm < 0)
+		return ohm;
+
+	*temp = get_temp_mc(data, ohm);
+
+	return 0;
+}
+
 static ssize_t ntc_show_name(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -562,6 +578,13 @@ static int ntc_thermistor_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "Thermistor type: %s successfully probed.\n",
 								pdev_id->name);
 
+	data->tz = thermal_zone_of_sensor_register(data->dev, 0, data->dev,
+						ntc_read_temp, NULL);
+	if (IS_ERR(data->tz)) {
+		dev_dbg(&pdev->dev, "Failed to register to thermal fw.\n");
+		data->tz = NULL;
+	}
+
 	return 0;
 err_after_sysfs:
 	sysfs_remove_group(&data->dev->kobj, &ntc_attr_group);
@@ -578,6 +601,8 @@ static int ntc_thermistor_remove(struct platform_device *pdev)
 	sysfs_remove_group(&data->dev->kobj, &ntc_attr_group);
 	ntc_iio_channel_release(pdata);
 
+	thermal_zone_of_sensor_unregister(data->dev, data->tz);
+
 	return 0;
 }
 
diff --git a/drivers/hwmon/smsc47b397.c b/drivers/hwmon/smsc47b397.c
index bd89e87bd6ae..221f0931bf1c 100644
--- a/drivers/hwmon/smsc47b397.c
+++ b/drivers/hwmon/smsc47b397.c
@@ -100,8 +100,6 @@ static u8 smsc47b397_reg_temp[] = {0x25, 0x26, 0x27, 0x80};
 
 struct smsc47b397_data {
 	unsigned short addr;
-	const char *name;
-	struct device *hwmon_dev;
 	struct mutex lock;
 
 	struct mutex update_lock;
@@ -202,15 +200,7 @@ static SENSOR_DEVICE_ATTR(fan2_input, S_IRUGO, show_fan, NULL, 1);
 static SENSOR_DEVICE_ATTR(fan3_input, S_IRUGO, show_fan, NULL, 2);
 static SENSOR_DEVICE_ATTR(fan4_input, S_IRUGO, show_fan, NULL, 3);
 
-static ssize_t show_name(struct device *dev, struct device_attribute
-			 *devattr, char *buf)
-{
-	struct smsc47b397_data *data = dev_get_drvdata(dev);
-	return sprintf(buf, "%s\n", data->name);
-}
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
-
-static struct attribute *smsc47b397_attributes[] = {
+static struct attribute *smsc47b397_attrs[] = {
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
 	&sensor_dev_attr_temp2_input.dev_attr.attr,
 	&sensor_dev_attr_temp3_input.dev_attr.attr,
@@ -220,23 +210,10 @@ static struct attribute *smsc47b397_attributes[] = {
 	&sensor_dev_attr_fan3_input.dev_attr.attr,
 	&sensor_dev_attr_fan4_input.dev_attr.attr,
 
-	&dev_attr_name.attr,
 	NULL
 };
 
-static const struct attribute_group smsc47b397_group = {
-	.attrs = smsc47b397_attributes,
-};
-
-static int smsc47b397_remove(struct platform_device *pdev)
-{
-	struct smsc47b397_data *data = platform_get_drvdata(pdev);
-
-	hwmon_device_unregister(data->hwmon_dev);
-	sysfs_remove_group(&pdev->dev.kobj, &smsc47b397_group);
-
-	return 0;
-}
+ATTRIBUTE_GROUPS(smsc47b397);
 
 static int smsc47b397_probe(struct platform_device *pdev);
 
@@ -246,15 +223,14 @@ static struct platform_driver smsc47b397_driver = {
 		.name	= DRVNAME,
 	},
 	.probe		= smsc47b397_probe,
-	.remove		= smsc47b397_remove,
 };
 
 static int smsc47b397_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct smsc47b397_data *data;
+	struct device *hwmon_dev;
 	struct resource *res;
-	int err = 0;
 
 	res = platform_get_resource(pdev, IORESOURCE_IO, 0);
 	if (!devm_request_region(dev, res->start, SMSC_EXTENT,
@@ -270,26 +246,13 @@ static int smsc47b397_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	data->addr = res->start;
-	data->name = "smsc47b397";
 	mutex_init(&data->lock);
 	mutex_init(&data->update_lock);
-	platform_set_drvdata(pdev, data);
-
-	err = sysfs_create_group(&dev->kobj, &smsc47b397_group);
-	if (err)
-		return err;
 
-	data->hwmon_dev = hwmon_device_register(dev);
-	if (IS_ERR(data->hwmon_dev)) {
-		err = PTR_ERR(data->hwmon_dev);
-		goto error_remove;
-	}
-
-	return 0;
-
-error_remove:
-	sysfs_remove_group(&dev->kobj, &smsc47b397_group);
-	return err;
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, "smsc47b397",
+							   data,
+							   smsc47b397_groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
 static int __init smsc47b397_device_add(unsigned short address)
diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
index 05e033c98115..8ca5cbbcec91 100644
--- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c
+++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
@@ -16,6 +16,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
+#define I2C_MAX_RETRIES 3
+
 /**
  * struct ec_i2c_device - Driver data for I2C tunnel
  *
@@ -227,7 +229,7 @@ static int ec_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg i2c_msgs[],
 	msg.indata = response;
 	msg.insize = response_len;
 
-	result = bus->ec->cmd_xfer(bus->ec, &msg);
+	result = cros_ec_cmd_xfer(bus->ec, &msg);
 	if (result < 0)
 		goto exit;
 
@@ -290,6 +292,7 @@ static int ec_i2c_probe(struct platform_device *pdev)
 	bus->adap.algo_data = bus;
 	bus->adap.dev.parent = &pdev->dev;
 	bus->adap.dev.of_node = np;
+	bus->adap.retries = I2C_MAX_RETRIES;
 
 	err = i2c_add_adapter(&bus->adap);
 	if (err) {
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index ccfbbab82a15..2f90ac6a7f79 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -50,6 +50,7 @@
 #include <linux/irqflags.h>
 #include <linux/rwsem.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/acpi.h>
 #include <linux/jump_label.h>
 #include <asm/uaccess.h>
@@ -643,10 +644,13 @@ static int i2c_device_probe(struct device *dev)
 	if (status < 0)
 		return status;
 
-	acpi_dev_pm_attach(&client->dev, true);
-	status = driver->probe(client, i2c_match_id(driver->id_table, client));
-	if (status)
-		acpi_dev_pm_detach(&client->dev, true);
+	status = dev_pm_domain_attach(&client->dev, true);
+	if (status != -EPROBE_DEFER) {
+		status = driver->probe(client, i2c_match_id(driver->id_table,
+					client));
+		if (status)
+			dev_pm_domain_detach(&client->dev, true);
+	}
 
 	return status;
 }
@@ -666,7 +670,7 @@ static int i2c_device_remove(struct device *dev)
 		status = driver->remove(client);
 	}
 
-	acpi_dev_pm_detach(&client->dev, true);
+	dev_pm_domain_detach(&client->dev, true);
 	return status;
 }
 
diff --git a/drivers/ide/atiixp.c b/drivers/ide/atiixp.c
index dbd0f242ec18..76650e92db41 100644
--- a/drivers/ide/atiixp.c
+++ b/drivers/ide/atiixp.c
@@ -19,12 +19,12 @@
 #define ATIIXP_IDE_UDMA_CONTROL		0x54
 #define ATIIXP_IDE_UDMA_MODE		0x56
 
-typedef struct {
+struct atiixp_ide_timing {
 	u8 command_width;
 	u8 recover_width;
-} atiixp_ide_timing;
+};
 
-static atiixp_ide_timing pio_timing[] = {
+static struct atiixp_ide_timing pio_timing[] = {
 	{ 0x05, 0x0d },
 	{ 0x04, 0x07 },
 	{ 0x03, 0x04 },
@@ -32,7 +32,7 @@ static atiixp_ide_timing pio_timing[] = {
 	{ 0x02, 0x00 },
 };
 
-static atiixp_ide_timing mdma_timing[] = {
+static struct atiixp_ide_timing mdma_timing[] = {
 	{ 0x07, 0x07 },
 	{ 0x02, 0x01 },
 	{ 0x02, 0x00 },
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index ee880382e3bc..56b9708894a5 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -685,8 +685,10 @@ static void ide_disk_setup(ide_drive_t *drive)
 	printk(KERN_INFO "%s: max request size: %dKiB\n", drive->name,
 	       queue_max_sectors(q) / 2);
 
-	if (ata_id_is_ssd(id))
+	if (ata_id_is_ssd(id)) {
 		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
+		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q);
+	}
 
 	/* calculate drive capacity, and select LBA if possible */
 	ide_disk_get_capacity(drive);
diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c
index f41558a0bcd1..ca958604cda2 100644
--- a/drivers/ide/ide-park.c
+++ b/drivers/ide/ide-park.c
@@ -46,7 +46,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	 * timeout has expired, so power management will be reenabled.
 	 */
 	rq = blk_get_request(q, READ, GFP_NOWAIT);
-	if (unlikely(!rq))
+	if (IS_ERR(rq))
 		goto out;
 
 	rq->cmd[0] = REQ_UNPARK_HEADS;
diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c
index e0c404bdc4a8..4977082e081f 100644
--- a/drivers/infiniband/hw/ipath/ipath_fs.c
+++ b/drivers/infiniband/hw/ipath/ipath_fs.c
@@ -82,7 +82,6 @@ static int create_file(const char *name, umode_t mode,
 {
 	int error;
 
-	*dentry = NULL;
 	mutex_lock(&parent->d_inode->i_mutex);
 	*dentry = lookup_one_len(name, parent, strlen(name));
 	if (!IS_ERR(*dentry))
diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c
index cab610ccd50e..81854586c081 100644
--- a/drivers/infiniband/hw/qib/qib_fs.c
+++ b/drivers/infiniband/hw/qib/qib_fs.c
@@ -89,7 +89,6 @@ static int create_file(const char *name, umode_t mode,
 {
 	int error;
 
-	*dentry = NULL;
 	mutex_lock(&parent->d_inode->i_mutex);
 	*dentry = lookup_one_len(name, parent, strlen(name));
 	if (!IS_ERR(*dentry))
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 801a1d6937e4..417de1f32960 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -507,7 +507,7 @@ int usnic_uiom_attach_dev_to_pd(struct usnic_uiom_pd *pd, struct device *dev)
 	if (err)
 		goto out_free_dev;
 
-	if (!iommu_domain_has_cap(pd->domain, IOMMU_CAP_CACHE_COHERENCY)) {
+	if (!iommu_capable(dev->bus, IOMMU_CAP_CACHE_COHERENCY)) {
 		usnic_err("IOMMU of %s does not support cache coherency\n",
 				dev_name(dev));
 		err = -EINVAL;
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index d28a8c284da9..7206547c13ce 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -3574,7 +3574,7 @@ static int srpt_parse_i_port_id(u8 i_port_id[16], const char *name)
 	int ret, rc;
 
 	p = name;
-	if (strnicmp(p, "0x", 2) == 0)
+	if (strncasecmp(p, "0x", 2) == 0)
 		p += 2;
 	ret = -EINVAL;
 	len = strlen(p);
diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c
index 5ef7fcf0e250..b97ed443e0a4 100644
--- a/drivers/input/keyboard/adp5588-keys.c
+++ b/drivers/input/keyboard/adp5588-keys.c
@@ -251,9 +251,7 @@ static void adp5588_gpio_remove(struct adp5588_kpad *kpad)
 			dev_warn(dev, "teardown failed %d\n", error);
 	}
 
-	error = gpiochip_remove(&kpad->gc);
-	if (error)
-		dev_warn(dev, "gpiochip_remove failed %d\n", error);
+	gpiochip_remove(&kpad->gc);
 }
 #else
 static inline int adp5588_gpio_add(struct adp5588_kpad *kpad)
diff --git a/drivers/input/keyboard/adp5589-keys.c b/drivers/input/keyboard/adp5589-keys.c
index 6329549bf6ad..a45267729dfc 100644
--- a/drivers/input/keyboard/adp5589-keys.c
+++ b/drivers/input/keyboard/adp5589-keys.c
@@ -567,9 +567,7 @@ static void adp5589_gpio_remove(struct adp5589_kpad *kpad)
 			dev_warn(dev, "teardown failed %d\n", error);
 	}
 
-	error = gpiochip_remove(&kpad->gc);
-	if (error)
-		dev_warn(dev, "gpiochip_remove failed %d\n", error);
+	gpiochip_remove(&kpad->gc);
 }
 #else
 static inline int adp5589_gpio_add(struct adp5589_kpad *kpad)
diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c
index 72d3499bb029..5d773d20230a 100644
--- a/drivers/input/keyboard/cros_ec_keyb.c
+++ b/drivers/input/keyboard/cros_ec_keyb.c
@@ -157,7 +157,7 @@ static int cros_ec_keyb_get_state(struct cros_ec_keyb *ckdev, uint8_t *kb_state)
 		.insize = ckdev->cols,
 	};
 
-	return ckdev->ec->cmd_xfer(ckdev->ec, &msg);
+	return cros_ec_cmd_xfer(ckdev->ec, &msg);
 }
 
 static irqreturn_t cros_ec_keyb_irq(int irq, void *data)
diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c
index fbfdc10573be..1af28b06c713 100644
--- a/drivers/input/misc/xen-kbdfront.c
+++ b/drivers/input/misc/xen-kbdfront.c
@@ -365,12 +365,13 @@ static const struct xenbus_device_id xenkbd_ids[] = {
 	{ "" }
 };
 
-static DEFINE_XENBUS_DRIVER(xenkbd, ,
+static struct xenbus_driver xenkbd_driver = {
+	.ids = xenkbd_ids,
 	.probe = xenkbd_probe,
 	.remove = xenkbd_remove,
 	.resume = xenkbd_resume,
 	.otherend_changed = xenkbd_backend_changed,
-);
+};
 
 static int __init xenkbd_init(void)
 {
diff --git a/drivers/input/touchscreen/ad7879.c b/drivers/input/touchscreen/ad7879.c
index fce590677b7b..1eb9d3c20886 100644
--- a/drivers/input/touchscreen/ad7879.c
+++ b/drivers/input/touchscreen/ad7879.c
@@ -470,14 +470,10 @@ static int ad7879_gpio_add(struct ad7879 *ts,
 static void ad7879_gpio_remove(struct ad7879 *ts)
 {
 	const struct ad7879_platform_data *pdata = dev_get_platdata(ts->dev);
-	int ret;
 
-	if (pdata->gpio_export) {
-		ret = gpiochip_remove(&ts->gc);
-		if (ret)
-			dev_err(ts->dev, "failed to remove gpio %d\n",
-				ts->gc.base);
-	}
+	if (pdata->gpio_export)
+		gpiochip_remove(&ts->gc);
+
 }
 #else
 static inline int ad7879_gpio_add(struct ad7879 *ts,
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index 8857d5b9be71..ee3434f1e949 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -812,7 +812,7 @@ static int edt_ft5x06_ts_identify(struct i2c_client *client,
 	/* if we find something consistent, stay with that assumption
 	 * at least M09 won't send 3 bytes here
 	 */
-	if (!(strnicmp(rdbuf + 1, "EP0", 3))) {
+	if (!(strncasecmp(rdbuf + 1, "EP0", 3))) {
 		tsdata->version = M06;
 
 		/* remove last '$' end marker */
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index ecb0109a5360..505a9adac2d5 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -88,6 +88,27 @@ int amd_iommu_max_glx_val = -1;
 static struct dma_map_ops amd_iommu_dma_ops;
 
 /*
+ * This struct contains device specific data for the IOMMU
+ */
+struct iommu_dev_data {
+	struct list_head list;		  /* For domain->dev_list */
+	struct list_head dev_data_list;	  /* For global dev_data_list */
+	struct list_head alias_list;      /* Link alias-groups together */
+	struct iommu_dev_data *alias_data;/* The alias dev_data */
+	struct protection_domain *domain; /* Domain the device is bound to */
+	u16 devid;			  /* PCI Device ID */
+	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
+	bool passthrough;		  /* Default for device is pt_domain */
+	struct {
+		bool enabled;
+		int qdep;
+	} ats;				  /* ATS state */
+	bool pri_tlp;			  /* PASID TLB required for
+					     PPR completions */
+	u32 errata;			  /* Bitmap for errata to apply */
+};
+
+/*
  * general struct to manage commands send to an IOMMU
  */
 struct iommu_cmd {
@@ -114,8 +135,9 @@ static struct iommu_dev_data *alloc_dev_data(u16 devid)
 	if (!dev_data)
 		return NULL;
 
+	INIT_LIST_HEAD(&dev_data->alias_list);
+
 	dev_data->devid = devid;
-	atomic_set(&dev_data->bind, 0);
 
 	spin_lock_irqsave(&dev_data_list_lock, flags);
 	list_add_tail(&dev_data->dev_data_list, &dev_data_list);
@@ -260,17 +282,13 @@ static bool check_device(struct device *dev)
 	return true;
 }
 
-static int init_iommu_group(struct device *dev)
+static void init_iommu_group(struct device *dev)
 {
 	struct iommu_group *group;
 
 	group = iommu_group_get_for_dev(dev);
-
-	if (IS_ERR(group))
-		return PTR_ERR(group);
-
-	iommu_group_put(group);
-	return 0;
+	if (!IS_ERR(group))
+		iommu_group_put(group);
 }
 
 static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
@@ -340,7 +358,6 @@ static int iommu_init_device(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct iommu_dev_data *dev_data;
 	u16 alias;
-	int ret;
 
 	if (dev->archdata.iommu)
 		return 0;
@@ -362,12 +379,9 @@ static int iommu_init_device(struct device *dev)
 			return -ENOTSUPP;
 		}
 		dev_data->alias_data = alias_data;
-	}
 
-	ret = init_iommu_group(dev);
-	if (ret) {
-		free_dev_data(dev_data);
-		return ret;
+		/* Add device to the alias_list */
+		list_add(&dev_data->alias_list, &alias_data->alias_list);
 	}
 
 	if (pci_iommuv2_capable(pdev)) {
@@ -455,6 +469,15 @@ int __init amd_iommu_init_devices(void)
 			goto out_free;
 	}
 
+	/*
+	 * Initialize IOMMU groups only after iommu_init_device() has
+	 * had a chance to populate any IVRS defined aliases.
+	 */
+	for_each_pci_dev(pdev) {
+		if (check_device(&pdev->dev))
+			init_iommu_group(&pdev->dev);
+	}
+
 	return 0;
 
 out_free:
@@ -1368,6 +1391,9 @@ static int iommu_map_page(struct protection_domain *dom,
 	count     = PAGE_SIZE_PTE_COUNT(page_size);
 	pte       = alloc_pte(dom, bus_addr, page_size, NULL, GFP_KERNEL);
 
+	if (!pte)
+		return -ENOMEM;
+
 	for (i = 0; i < count; ++i)
 		if (IOMMU_PTE_PRESENT(pte[i]))
 			return -EBUSY;
@@ -2122,35 +2148,29 @@ static void do_detach(struct iommu_dev_data *dev_data)
 static int __attach_device(struct iommu_dev_data *dev_data,
 			   struct protection_domain *domain)
 {
+	struct iommu_dev_data *head, *entry;
 	int ret;
 
 	/* lock domain */
 	spin_lock(&domain->lock);
 
-	if (dev_data->alias_data != NULL) {
-		struct iommu_dev_data *alias_data = dev_data->alias_data;
+	head = dev_data;
 
-		/* Some sanity checks */
-		ret = -EBUSY;
-		if (alias_data->domain != NULL &&
-				alias_data->domain != domain)
-			goto out_unlock;
+	if (head->alias_data != NULL)
+		head = head->alias_data;
 
-		if (dev_data->domain != NULL &&
-				dev_data->domain != domain)
-			goto out_unlock;
+	/* Now we have the root of the alias group, if any */
 
-		/* Do real assignment */
-		if (alias_data->domain == NULL)
-			do_attach(alias_data, domain);
-
-		atomic_inc(&alias_data->bind);
-	}
+	ret = -EBUSY;
+	if (head->domain != NULL)
+		goto out_unlock;
 
-	if (dev_data->domain == NULL)
-		do_attach(dev_data, domain);
+	/* Attach alias group root */
+	do_attach(head, domain);
 
-	atomic_inc(&dev_data->bind);
+	/* Attach other devices in the alias group */
+	list_for_each_entry(entry, &head->alias_list, alias_list)
+		do_attach(entry, domain);
 
 	ret = 0;
 
@@ -2298,6 +2318,7 @@ static int attach_device(struct device *dev,
  */
 static void __detach_device(struct iommu_dev_data *dev_data)
 {
+	struct iommu_dev_data *head, *entry;
 	struct protection_domain *domain;
 	unsigned long flags;
 
@@ -2307,15 +2328,14 @@ static void __detach_device(struct iommu_dev_data *dev_data)
 
 	spin_lock_irqsave(&domain->lock, flags);
 
-	if (dev_data->alias_data != NULL) {
-		struct iommu_dev_data *alias_data = dev_data->alias_data;
+	head = dev_data;
+	if (head->alias_data != NULL)
+		head = head->alias_data;
 
-		if (atomic_dec_and_test(&alias_data->bind))
-			do_detach(alias_data);
-	}
+	list_for_each_entry(entry, &head->alias_list, alias_list)
+		do_detach(entry);
 
-	if (atomic_dec_and_test(&dev_data->bind))
-		do_detach(dev_data);
+	do_detach(head);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
 
@@ -2415,6 +2435,7 @@ static int device_change_notifier(struct notifier_block *nb,
 	case BUS_NOTIFY_ADD_DEVICE:
 
 		iommu_init_device(dev);
+		init_iommu_group(dev);
 
 		/*
 		 * dev_data is still NULL and
@@ -3158,7 +3179,6 @@ static void cleanup_domain(struct protection_domain *domain)
 		entry = list_first_entry(&domain->dev_list,
 					 struct iommu_dev_data, list);
 		__detach_device(entry);
-		atomic_set(&entry->bind, 0);
 	}
 
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
@@ -3384,20 +3404,20 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
 	return paddr;
 }
 
-static int amd_iommu_domain_has_cap(struct iommu_domain *domain,
-				    unsigned long cap)
+static bool amd_iommu_capable(enum iommu_cap cap)
 {
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
-		return 1;
+		return true;
 	case IOMMU_CAP_INTR_REMAP:
-		return irq_remapping_enabled;
+		return (irq_remapping_enabled == 1);
 	}
 
-	return 0;
+	return false;
 }
 
 static const struct iommu_ops amd_iommu_ops = {
+	.capable = amd_iommu_capable,
 	.domain_init = amd_iommu_domain_init,
 	.domain_destroy = amd_iommu_domain_destroy,
 	.attach_dev = amd_iommu_attach_device,
@@ -3405,7 +3425,6 @@ static const struct iommu_ops amd_iommu_ops = {
 	.map = amd_iommu_map,
 	.unmap = amd_iommu_unmap,
 	.iova_to_phys = amd_iommu_iova_to_phys,
-	.domain_has_cap = amd_iommu_domain_has_cap,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 };
 
@@ -4235,7 +4254,7 @@ static int msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
 	return 0;
 }
 
-static int setup_hpet_msi(unsigned int irq, unsigned int id)
+static int alloc_hpet_msi(unsigned int irq, unsigned int id)
 {
 	struct irq_2_irte *irte_info;
 	struct irq_cfg *cfg;
@@ -4274,6 +4293,6 @@ struct irq_remap_ops amd_iommu_irq_ops = {
 	.compose_msi_msg	= compose_msi_msg,
 	.msi_alloc_irq		= msi_alloc_irq,
 	.msi_setup_irq		= msi_setup_irq,
-	.setup_hpet_msi		= setup_hpet_msi,
+	.alloc_hpet_msi		= alloc_hpet_msi,
 };
 #endif
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 3783e0b44df6..b0522f15730f 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -712,7 +712,7 @@ static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
 	set_iommu_for_device(iommu, devid);
 }
 
-static int __init add_special_device(u8 type, u8 id, u16 devid, bool cmd_line)
+static int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
 {
 	struct devid_map *entry;
 	struct list_head *list;
@@ -731,6 +731,8 @@ static int __init add_special_device(u8 type, u8 id, u16 devid, bool cmd_line)
 		pr_info("AMD-Vi: Command-line override present for %s id %d - ignoring\n",
 			type == IVHD_SPECIAL_IOAPIC ? "IOAPIC" : "HPET", id);
 
+		*devid = entry->devid;
+
 		return 0;
 	}
 
@@ -739,7 +741,7 @@ static int __init add_special_device(u8 type, u8 id, u16 devid, bool cmd_line)
 		return -ENOMEM;
 
 	entry->id	= id;
-	entry->devid	= devid;
+	entry->devid	= *devid;
 	entry->cmd_line	= cmd_line;
 
 	list_add_tail(&entry->list, list);
@@ -754,7 +756,7 @@ static int __init add_early_maps(void)
 	for (i = 0; i < early_ioapic_map_size; ++i) {
 		ret = add_special_device(IVHD_SPECIAL_IOAPIC,
 					 early_ioapic_map[i].id,
-					 early_ioapic_map[i].devid,
+					 &early_ioapic_map[i].devid,
 					 early_ioapic_map[i].cmd_line);
 		if (ret)
 			return ret;
@@ -763,7 +765,7 @@ static int __init add_early_maps(void)
 	for (i = 0; i < early_hpet_map_size; ++i) {
 		ret = add_special_device(IVHD_SPECIAL_HPET,
 					 early_hpet_map[i].id,
-					 early_hpet_map[i].devid,
+					 &early_hpet_map[i].devid,
 					 early_hpet_map[i].cmd_line);
 		if (ret)
 			return ret;
@@ -978,10 +980,17 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 				    PCI_SLOT(devid),
 				    PCI_FUNC(devid));
 
-			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
-			ret = add_special_device(type, handle, devid, false);
+			ret = add_special_device(type, handle, &devid, false);
 			if (ret)
 				return ret;
+
+			/*
+			 * add_special_device might update the devid in case a
+			 * command-line override is present. So call
+			 * set_dev_entry_from_acpi after add_special_device.
+			 */
+			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
+
 			break;
 		}
 		default:
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 8e43b7cba133..cec51a8ba844 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -418,27 +418,6 @@ struct protection_domain {
 };
 
 /*
- * This struct contains device specific data for the IOMMU
- */
-struct iommu_dev_data {
-	struct list_head list;		  /* For domain->dev_list */
-	struct list_head dev_data_list;	  /* For global dev_data_list */
-	struct iommu_dev_data *alias_data;/* The alias dev_data */
-	struct protection_domain *domain; /* Domain the device is bound to */
-	atomic_t bind;			  /* Domain attach reference count */
-	u16 devid;			  /* PCI Device ID */
-	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
-	bool passthrough;		  /* Default for device is pt_domain */
-	struct {
-		bool enabled;
-		int qdep;
-	} ats;				  /* ATS state */
-	bool pri_tlp;			  /* PASID TLB required for
-					     PPR completions */
-	u32 errata;			  /* Bitmap for errata to apply */
-};
-
-/*
  * For dynamic growth the aperture size is split into ranges of 128MB of
  * DMA address space each. This struct represents one such range.
  */
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index a83cc2a2a2ca..60558f794922 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -24,7 +24,7 @@
  *	- v7/v8 long-descriptor format
  *	- Non-secure access to the SMMU
  *	- 4k and 64k pages, with contiguous pte hints.
- *	- Up to 42-bit addressing (dependent on VA_BITS)
+ *	- Up to 48-bit addressing (dependent on VA_BITS)
  *	- Context fault reporting
  */
 
@@ -59,7 +59,7 @@
 
 /* SMMU global address space */
 #define ARM_SMMU_GR0(smmu)		((smmu)->base)
-#define ARM_SMMU_GR1(smmu)		((smmu)->base + (smmu)->pagesize)
+#define ARM_SMMU_GR1(smmu)		((smmu)->base + (1 << (smmu)->pgshift))
 
 /*
  * SMMU global address space with conditional offset to access secure
@@ -224,7 +224,7 @@
 
 /* Translation context bank */
 #define ARM_SMMU_CB_BASE(smmu)		((smmu)->base + ((smmu)->size >> 1))
-#define ARM_SMMU_CB(smmu, n)		((n) * (smmu)->pagesize)
+#define ARM_SMMU_CB(smmu, n)		((n) * (1 << (smmu)->pgshift))
 
 #define ARM_SMMU_CB_SCTLR		0x0
 #define ARM_SMMU_CB_RESUME		0x8
@@ -326,6 +326,16 @@
 
 #define FSYNR0_WNR			(1 << 4)
 
+static int force_stage;
+module_param_named(force_stage, force_stage, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(force_stage,
+	"Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation.");
+
+enum arm_smmu_arch_version {
+	ARM_SMMU_V1 = 1,
+	ARM_SMMU_V2,
+};
+
 struct arm_smmu_smr {
 	u8				idx;
 	u16				mask;
@@ -349,7 +359,7 @@ struct arm_smmu_device {
 
 	void __iomem			*base;
 	unsigned long			size;
-	unsigned long			pagesize;
+	unsigned long			pgshift;
 
 #define ARM_SMMU_FEAT_COHERENT_WALK	(1 << 0)
 #define ARM_SMMU_FEAT_STREAM_MATCH	(1 << 1)
@@ -360,7 +370,7 @@ struct arm_smmu_device {
 
 #define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0)
 	u32				options;
-	int				version;
+	enum arm_smmu_arch_version	version;
 
 	u32				num_context_banks;
 	u32				num_s2_context_banks;
@@ -370,8 +380,9 @@ struct arm_smmu_device {
 	u32				num_mapping_groups;
 	DECLARE_BITMAP(smr_map, ARM_SMMU_MAX_SMRS);
 
-	unsigned long			input_size;
+	unsigned long			s1_input_size;
 	unsigned long			s1_output_size;
+	unsigned long			s2_input_size;
 	unsigned long			s2_output_size;
 
 	u32				num_global_irqs;
@@ -426,17 +437,17 @@ static void parse_driver_options(struct arm_smmu_device *smmu)
 	} while (arm_smmu_options[++i].opt);
 }
 
-static struct device *dev_get_master_dev(struct device *dev)
+static struct device_node *dev_get_dev_node(struct device *dev)
 {
 	if (dev_is_pci(dev)) {
 		struct pci_bus *bus = to_pci_dev(dev)->bus;
 
 		while (!pci_is_root_bus(bus))
 			bus = bus->parent;
-		return bus->bridge->parent;
+		return bus->bridge->parent->of_node;
 	}
 
-	return dev;
+	return dev->of_node;
 }
 
 static struct arm_smmu_master *find_smmu_master(struct arm_smmu_device *smmu,
@@ -461,15 +472,17 @@ static struct arm_smmu_master *find_smmu_master(struct arm_smmu_device *smmu,
 }
 
 static struct arm_smmu_master_cfg *
-find_smmu_master_cfg(struct arm_smmu_device *smmu, struct device *dev)
+find_smmu_master_cfg(struct device *dev)
 {
-	struct arm_smmu_master *master;
+	struct arm_smmu_master_cfg *cfg = NULL;
+	struct iommu_group *group = iommu_group_get(dev);
 
-	if (dev_is_pci(dev))
-		return dev->archdata.iommu;
+	if (group) {
+		cfg = iommu_group_get_iommudata(group);
+		iommu_group_put(group);
+	}
 
-	master = find_smmu_master(smmu, dev->of_node);
-	return master ? &master->cfg : NULL;
+	return cfg;
 }
 
 static int insert_smmu_master(struct arm_smmu_device *smmu,
@@ -545,7 +558,7 @@ static struct arm_smmu_device *find_smmu_for_device(struct device *dev)
 {
 	struct arm_smmu_device *smmu;
 	struct arm_smmu_master *master = NULL;
-	struct device_node *dev_node = dev_get_master_dev(dev)->of_node;
+	struct device_node *dev_node = dev_get_dev_node(dev);
 
 	spin_lock(&arm_smmu_devices_lock);
 	list_for_each_entry(smmu, &arm_smmu_devices, list) {
@@ -729,7 +742,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 
 	/* CBAR */
 	reg = cfg->cbar;
-	if (smmu->version == 1)
+	if (smmu->version == ARM_SMMU_V1)
 		reg |= cfg->irptndx << CBAR_IRPTNDX_SHIFT;
 
 	/*
@@ -744,7 +757,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 	}
 	writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(cfg->cbndx));
 
-	if (smmu->version > 1) {
+	if (smmu->version > ARM_SMMU_V1) {
 		/* CBA2R */
 #ifdef CONFIG_64BIT
 		reg = CBA2R_RW64_64BIT;
@@ -755,7 +768,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 			       gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx));
 
 		/* TTBCR2 */
-		switch (smmu->input_size) {
+		switch (smmu->s1_input_size) {
 		case 32:
 			reg = (TTBCR2_ADDR_32 << TTBCR2_SEP_SHIFT);
 			break;
@@ -817,14 +830,14 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 	 * TTBCR
 	 * We use long descriptor, with inner-shareable WBWA tables in TTBR0.
 	 */
-	if (smmu->version > 1) {
+	if (smmu->version > ARM_SMMU_V1) {
 		if (PAGE_SIZE == SZ_4K)
 			reg = TTBCR_TG0_4K;
 		else
 			reg = TTBCR_TG0_64K;
 
 		if (!stage1) {
-			reg |= (64 - smmu->s1_output_size) << TTBCR_T0SZ_SHIFT;
+			reg |= (64 - smmu->s2_input_size) << TTBCR_T0SZ_SHIFT;
 
 			switch (smmu->s2_output_size) {
 			case 32:
@@ -847,7 +860,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain)
 				break;
 			}
 		} else {
-			reg |= (64 - smmu->input_size) << TTBCR_T0SZ_SHIFT;
+			reg |= (64 - smmu->s1_input_size) << TTBCR_T0SZ_SHIFT;
 		}
 	} else {
 		reg = 0;
@@ -914,7 +927,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		goto out_unlock;
 
 	cfg->cbndx = ret;
-	if (smmu->version == 1) {
+	if (smmu->version == ARM_SMMU_V1) {
 		cfg->irptndx = atomic_inc_return(&smmu->irptndx);
 		cfg->irptndx %= smmu->num_context_irqs;
 	} else {
@@ -1151,9 +1164,10 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
 
+	/* Devices in an IOMMU group may already be configured */
 	ret = arm_smmu_master_configure_smrs(smmu, cfg);
 	if (ret)
-		return ret;
+		return ret == -EEXIST ? 0 : ret;
 
 	for (i = 0; i < cfg->num_streamids; ++i) {
 		u32 idx, s2cr;
@@ -1174,6 +1188,10 @@ static void arm_smmu_domain_remove_master(struct arm_smmu_domain *smmu_domain,
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
 
+	/* An IOMMU group is torn down by the first device to be removed */
+	if ((smmu->features & ARM_SMMU_FEAT_STREAM_MATCH) && !cfg->smrs)
+		return;
+
 	/*
 	 * We *must* clear the S2CR first, because freeing the SMR means
 	 * that it can be re-allocated immediately.
@@ -1195,12 +1213,17 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	struct arm_smmu_device *smmu, *dom_smmu;
 	struct arm_smmu_master_cfg *cfg;
 
-	smmu = dev_get_master_dev(dev)->archdata.iommu;
+	smmu = find_smmu_for_device(dev);
 	if (!smmu) {
 		dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
 		return -ENXIO;
 	}
 
+	if (dev->archdata.iommu) {
+		dev_err(dev, "already attached to IOMMU domain\n");
+		return -EEXIST;
+	}
+
 	/*
 	 * Sanity check the domain. We don't support domains across
 	 * different SMMUs.
@@ -1223,11 +1246,14 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	}
 
 	/* Looks ok, so add the device to the domain */
-	cfg = find_smmu_master_cfg(smmu_domain->smmu, dev);
+	cfg = find_smmu_master_cfg(dev);
 	if (!cfg)
 		return -ENODEV;
 
-	return arm_smmu_domain_add_master(smmu_domain, cfg);
+	ret = arm_smmu_domain_add_master(smmu_domain, cfg);
+	if (!ret)
+		dev->archdata.iommu = domain;
+	return ret;
 }
 
 static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
@@ -1235,9 +1261,12 @@ static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
 	struct arm_smmu_domain *smmu_domain = domain->priv;
 	struct arm_smmu_master_cfg *cfg;
 
-	cfg = find_smmu_master_cfg(smmu_domain->smmu, dev);
-	if (cfg)
-		arm_smmu_domain_remove_master(smmu_domain, cfg);
+	cfg = find_smmu_master_cfg(dev);
+	if (!cfg)
+		return;
+
+	dev->archdata.iommu = NULL;
+	arm_smmu_domain_remove_master(smmu_domain, cfg);
 }
 
 static bool arm_smmu_pte_is_contiguous_range(unsigned long addr,
@@ -1379,6 +1408,7 @@ static int arm_smmu_alloc_init_pmd(struct arm_smmu_device *smmu, pud_t *pud,
 		ret = arm_smmu_alloc_init_pte(smmu, pmd, addr, next, pfn,
 					      prot, stage);
 		phys += next - addr;
+		pfn = __phys_to_pfn(phys);
 	} while (pmd++, addr = next, addr < end);
 
 	return ret;
@@ -1431,9 +1461,11 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
 
 	if (cfg->cbar == CBAR_TYPE_S2_TRANS) {
 		stage = 2;
+		input_mask = (1ULL << smmu->s2_input_size) - 1;
 		output_mask = (1ULL << smmu->s2_output_size) - 1;
 	} else {
 		stage = 1;
+		input_mask = (1ULL << smmu->s1_input_size) - 1;
 		output_mask = (1ULL << smmu->s1_output_size) - 1;
 	}
 
@@ -1443,7 +1475,6 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain,
 	if (size & ~PAGE_MASK)
 		return -EINVAL;
 
-	input_mask = (1ULL << smmu->input_size) - 1;
 	if ((phys_addr_t)iova & ~input_mask)
 		return -ERANGE;
 
@@ -1526,20 +1557,19 @@ static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
 	return __pfn_to_phys(pte_pfn(pte)) | (iova & ~PAGE_MASK);
 }
 
-static int arm_smmu_domain_has_cap(struct iommu_domain *domain,
-				   unsigned long cap)
+static bool arm_smmu_capable(enum iommu_cap cap)
 {
-	struct arm_smmu_domain *smmu_domain = domain->priv;
-	struct arm_smmu_device *smmu = smmu_domain->smmu;
-	u32 features = smmu ? smmu->features : 0;
-
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
-		return features & ARM_SMMU_FEAT_COHERENT_WALK;
+		/*
+		 * Return true here as the SMMU can always send out coherent
+		 * requests.
+		 */
+		return true;
 	case IOMMU_CAP_INTR_REMAP:
-		return 1; /* MSIs are just memory writes */
+		return true; /* MSIs are just memory writes */
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -1549,17 +1579,19 @@ static int __arm_smmu_get_pci_sid(struct pci_dev *pdev, u16 alias, void *data)
 	return 0; /* Continue walking */
 }
 
+static void __arm_smmu_release_pci_iommudata(void *data)
+{
+	kfree(data);
+}
+
 static int arm_smmu_add_device(struct device *dev)
 {
 	struct arm_smmu_device *smmu;
+	struct arm_smmu_master_cfg *cfg;
 	struct iommu_group *group;
+	void (*releasefn)(void *) = NULL;
 	int ret;
 
-	if (dev->archdata.iommu) {
-		dev_warn(dev, "IOMMU driver already assigned to device\n");
-		return -EINVAL;
-	}
-
 	smmu = find_smmu_for_device(dev);
 	if (!smmu)
 		return -ENODEV;
@@ -1571,7 +1603,6 @@ static int arm_smmu_add_device(struct device *dev)
 	}
 
 	if (dev_is_pci(dev)) {
-		struct arm_smmu_master_cfg *cfg;
 		struct pci_dev *pdev = to_pci_dev(dev);
 
 		cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
@@ -1587,11 +1618,20 @@ static int arm_smmu_add_device(struct device *dev)
 		 */
 		pci_for_each_dma_alias(pdev, __arm_smmu_get_pci_sid,
 				       &cfg->streamids[0]);
-		dev->archdata.iommu = cfg;
+		releasefn = __arm_smmu_release_pci_iommudata;
 	} else {
-		dev->archdata.iommu = smmu;
+		struct arm_smmu_master *master;
+
+		master = find_smmu_master(smmu, dev->of_node);
+		if (!master) {
+			ret = -ENODEV;
+			goto out_put_group;
+		}
+
+		cfg = &master->cfg;
 	}
 
+	iommu_group_set_iommudata(group, cfg, releasefn);
 	ret = iommu_group_add_device(group, dev);
 
 out_put_group:
@@ -1601,14 +1641,11 @@ out_put_group:
 
 static void arm_smmu_remove_device(struct device *dev)
 {
-	if (dev_is_pci(dev))
-		kfree(dev->archdata.iommu);
-
-	dev->archdata.iommu = NULL;
 	iommu_group_remove_device(dev);
 }
 
 static const struct iommu_ops arm_smmu_ops = {
+	.capable	= arm_smmu_capable,
 	.domain_init	= arm_smmu_domain_init,
 	.domain_destroy	= arm_smmu_domain_destroy,
 	.attach_dev	= arm_smmu_attach_dev,
@@ -1616,7 +1653,6 @@ static const struct iommu_ops arm_smmu_ops = {
 	.map		= arm_smmu_map,
 	.unmap		= arm_smmu_unmap,
 	.iova_to_phys	= arm_smmu_iova_to_phys,
-	.domain_has_cap	= arm_smmu_domain_has_cap,
 	.add_device	= arm_smmu_add_device,
 	.remove_device	= arm_smmu_remove_device,
 	.pgsize_bitmap	= (SECTION_SIZE |
@@ -1702,10 +1738,6 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	u32 id;
 
 	dev_notice(smmu->dev, "probing hardware configuration...\n");
-
-	/* Primecell ID */
-	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_PIDR2);
-	smmu->version = ((id >> PIDR2_ARCH_SHIFT) & PIDR2_ARCH_MASK) + 1;
 	dev_notice(smmu->dev, "SMMUv%d with:\n", smmu->version);
 
 	/* ID0 */
@@ -1716,6 +1748,13 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 		return -ENODEV;
 	}
 #endif
+
+	/* Restrict available stages based on module parameter */
+	if (force_stage == 1)
+		id &= ~(ID0_S2TS | ID0_NTS);
+	else if (force_stage == 2)
+		id &= ~(ID0_S1TS | ID0_NTS);
+
 	if (id & ID0_S1TS) {
 		smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
 		dev_notice(smmu->dev, "\tstage 1 translation\n");
@@ -1732,8 +1771,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	}
 
 	if (!(smmu->features &
-		(ARM_SMMU_FEAT_TRANS_S1 | ARM_SMMU_FEAT_TRANS_S2 |
-		 ARM_SMMU_FEAT_TRANS_NESTED))) {
+		(ARM_SMMU_FEAT_TRANS_S1 | ARM_SMMU_FEAT_TRANS_S2))) {
 		dev_err(smmu->dev, "\tno translation support!\n");
 		return -ENODEV;
 	}
@@ -1779,12 +1817,12 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 
 	/* ID1 */
 	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID1);
-	smmu->pagesize = (id & ID1_PAGESIZE) ? SZ_64K : SZ_4K;
+	smmu->pgshift = (id & ID1_PAGESIZE) ? 16 : 12;
 
 	/* Check for size mismatch of SMMU address space from mapped region */
 	size = 1 <<
 		(((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
-	size *= (smmu->pagesize << 1);
+	size *= 2 << smmu->pgshift;
 	if (smmu->size != size)
 		dev_warn(smmu->dev,
 			"SMMU address space size (0x%lx) differs from mapped region size (0x%lx)!\n",
@@ -1803,28 +1841,21 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	/* ID2 */
 	id = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID2);
 	size = arm_smmu_id_size_to_bits((id >> ID2_IAS_SHIFT) & ID2_IAS_MASK);
+	smmu->s1_output_size = min_t(unsigned long, PHYS_MASK_SHIFT, size);
 
-	/*
-	 * Stage-1 output limited by stage-2 input size due to pgd
-	 * allocation (PTRS_PER_PGD).
-	 */
-	if (smmu->features & ARM_SMMU_FEAT_TRANS_NESTED) {
+	/* Stage-2 input size limited due to pgd allocation (PTRS_PER_PGD) */
 #ifdef CONFIG_64BIT
-		smmu->s1_output_size = min_t(unsigned long, VA_BITS, size);
+	smmu->s2_input_size = min_t(unsigned long, VA_BITS, size);
 #else
-		smmu->s1_output_size = min(32UL, size);
+	smmu->s2_input_size = min(32UL, size);
 #endif
-	} else {
-		smmu->s1_output_size = min_t(unsigned long, PHYS_MASK_SHIFT,
-					     size);
-	}
 
 	/* The stage-2 output mask is also applied for bypass */
 	size = arm_smmu_id_size_to_bits((id >> ID2_OAS_SHIFT) & ID2_OAS_MASK);
 	smmu->s2_output_size = min_t(unsigned long, PHYS_MASK_SHIFT, size);
 
-	if (smmu->version == 1) {
-		smmu->input_size = 32;
+	if (smmu->version == ARM_SMMU_V1) {
+		smmu->s1_input_size = 32;
 	} else {
 #ifdef CONFIG_64BIT
 		size = (id >> ID2_UBS_SHIFT) & ID2_UBS_MASK;
@@ -1832,7 +1863,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 #else
 		size = 32;
 #endif
-		smmu->input_size = size;
+		smmu->s1_input_size = size;
 
 		if ((PAGE_SIZE == SZ_4K && !(id & ID2_PTFS_4K)) ||
 		    (PAGE_SIZE == SZ_64K && !(id & ID2_PTFS_64K)) ||
@@ -1843,15 +1874,30 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 		}
 	}
 
-	dev_notice(smmu->dev,
-		   "\t%lu-bit VA, %lu-bit IPA, %lu-bit PA\n",
-		   smmu->input_size, smmu->s1_output_size,
-		   smmu->s2_output_size);
+	if (smmu->features & ARM_SMMU_FEAT_TRANS_S1)
+		dev_notice(smmu->dev, "\tStage-1: %lu-bit VA -> %lu-bit IPA\n",
+			   smmu->s1_input_size, smmu->s1_output_size);
+
+	if (smmu->features & ARM_SMMU_FEAT_TRANS_S2)
+		dev_notice(smmu->dev, "\tStage-2: %lu-bit IPA -> %lu-bit PA\n",
+			   smmu->s2_input_size, smmu->s2_output_size);
+
 	return 0;
 }
 
+static const struct of_device_id arm_smmu_of_match[] = {
+	{ .compatible = "arm,smmu-v1", .data = (void *)ARM_SMMU_V1 },
+	{ .compatible = "arm,smmu-v2", .data = (void *)ARM_SMMU_V2 },
+	{ .compatible = "arm,mmu-400", .data = (void *)ARM_SMMU_V1 },
+	{ .compatible = "arm,mmu-401", .data = (void *)ARM_SMMU_V1 },
+	{ .compatible = "arm,mmu-500", .data = (void *)ARM_SMMU_V2 },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
+
 static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 {
+	const struct of_device_id *of_id;
 	struct resource *res;
 	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
@@ -1866,6 +1912,9 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 	}
 	smmu->dev = dev;
 
+	of_id = of_match_node(arm_smmu_of_match, dev->of_node);
+	smmu->version = (enum arm_smmu_arch_version)of_id->data;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	smmu->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(smmu->base))
@@ -1930,7 +1979,7 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 
 	parse_driver_options(smmu);
 
-	if (smmu->version > 1 &&
+	if (smmu->version > ARM_SMMU_V1 &&
 	    smmu->num_context_banks != smmu->num_context_irqs) {
 		dev_err(dev,
 			"found only %d context interrupt(s) but %d required\n",
@@ -2011,17 +2060,6 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_OF
-static struct of_device_id arm_smmu_of_match[] = {
-	{ .compatible = "arm,smmu-v1", },
-	{ .compatible = "arm,smmu-v2", },
-	{ .compatible = "arm,mmu-400", },
-	{ .compatible = "arm,mmu-500", },
-	{ },
-};
-MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
-#endif
-
 static struct platform_driver arm_smmu_driver = {
 	.driver	= {
 		.owner		= THIS_MODULE,
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 06d268abe951..c5c61cabd6e3 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -155,6 +155,7 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
 	if (event == BUS_NOTIFY_ADD_DEVICE) {
 		for (tmp = dev; tmp; tmp = tmp->bus->self) {
 			level--;
+			info->path[level].bus = tmp->bus->number;
 			info->path[level].device = PCI_SLOT(tmp->devfn);
 			info->path[level].function = PCI_FUNC(tmp->devfn);
 			if (pci_is_root_bus(tmp->bus))
@@ -177,17 +178,33 @@ static bool dmar_match_pci_path(struct dmar_pci_notify_info *info, int bus,
 	int i;
 
 	if (info->bus != bus)
-		return false;
+		goto fallback;
 	if (info->level != count)
-		return false;
+		goto fallback;
 
 	for (i = 0; i < count; i++) {
 		if (path[i].device != info->path[i].device ||
 		    path[i].function != info->path[i].function)
-			return false;
+			goto fallback;
 	}
 
 	return true;
+
+fallback:
+
+	if (count != 1)
+		return false;
+
+	i = info->level - 1;
+	if (bus              == info->path[i].bus &&
+	    path[0].device   == info->path[i].device &&
+	    path[0].function == info->path[i].function) {
+		pr_info(FW_BUG "RMRR entry for device %02x:%02x.%x is broken - applying workaround\n",
+			bus, path[0].device, path[0].function);
+		return true;
+	}
+
+	return false;
 }
 
 /* Return: > 0 if match found, 0 if no match found, < 0 if error happens */
@@ -247,7 +264,7 @@ int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment,
 
 	for_each_active_dev_scope(devices, count, index, tmp)
 		if (tmp == &info->dev->dev) {
-			rcu_assign_pointer(devices[index].dev, NULL);
+			RCU_INIT_POINTER(devices[index].dev, NULL);
 			synchronize_rcu();
 			put_device(tmp);
 			return 1;
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index d037e87a1fe5..74233186f6f7 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -32,7 +32,7 @@
 typedef u32 sysmmu_iova_t;
 typedef u32 sysmmu_pte_t;
 
-/* We does not consider super section mapping (16MB) */
+/* We do not consider super section mapping (16MB) */
 #define SECT_ORDER 20
 #define LPAGE_ORDER 16
 #define SPAGE_ORDER 12
@@ -307,7 +307,7 @@ static void show_fault_information(const char *name,
 
 static irqreturn_t exynos_sysmmu_irq(int irq, void *dev_id)
 {
-	/* SYSMMU is in blocked when interrupt occurred. */
+	/* SYSMMU is in blocked state when interrupt occurred. */
 	struct sysmmu_drvdata *data = dev_id;
 	enum exynos_sysmmu_inttype itype;
 	sysmmu_iova_t addr = -1;
@@ -567,8 +567,8 @@ static void sysmmu_tlb_invalidate_entry(struct device *dev, sysmmu_iova_t iova,
 		/*
 		 * L2TLB invalidation required
 		 * 4KB page: 1 invalidation
-		 * 64KB page: 16 invalidation
-		 * 1MB page: 64 invalidation
+		 * 64KB page: 16 invalidations
+		 * 1MB page: 64 invalidations
 		 * because it is set-associative TLB
 		 * with 8-way and 64 sets.
 		 * 1MB page can be cached in one of all sets.
@@ -714,7 +714,7 @@ static int exynos_iommu_domain_init(struct iommu_domain *domain)
 	if (!priv->lv2entcnt)
 		goto err_counter;
 
-	/* w/a of System MMU v3.3 to prevent caching 1MiB mapping */
+	/* Workaround for System MMU v3.3 to prevent caching 1MiB mapping */
 	for (i = 0; i < NUM_LV1ENTRIES; i += 8) {
 		priv->pgtable[i + 0] = ZERO_LV2LINK;
 		priv->pgtable[i + 1] = ZERO_LV2LINK;
@@ -861,14 +861,14 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *priv,
 		pgtable_flush(sent, sent + 1);
 
 		/*
-		 * If pretched SLPD is a fault SLPD in zero_l2_table, FLPD cache
-		 * may caches the address of zero_l2_table. This function
-		 * replaces the zero_l2_table with new L2 page table to write
-		 * valid mappings.
+		 * If pre-fetched SLPD is a faulty SLPD in zero_l2_table,
+		 * FLPD cache may cache the address of zero_l2_table. This
+		 * function replaces the zero_l2_table with new L2 page table
+		 * to write valid mappings.
 		 * Accessing the valid area may cause page fault since FLPD
-		 * cache may still caches zero_l2_table for the valid area
-		 * instead of new L2 page table that have the mapping
-		 * information of the valid area
+		 * cache may still cache zero_l2_table for the valid area
+		 * instead of new L2 page table that has the mapping
+		 * information of the valid area.
 		 * Thus any replacement of zero_l2_table with other valid L2
 		 * page table must involve FLPD cache invalidation for System
 		 * MMU v3.3.
@@ -963,27 +963,27 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
 /*
  * *CAUTION* to the I/O virtual memory managers that support exynos-iommu:
  *
- * System MMU v3.x have an advanced logic to improve address translation
+ * System MMU v3.x has advanced logic to improve address translation
  * performance with caching more page table entries by a page table walk.
- * However, the logic has a bug that caching fault page table entries and System
- * MMU reports page fault if the cached fault entry is hit even though the fault
- * entry is updated to a valid entry after the entry is cached.
- * To prevent caching fault page table entries which may be updated to valid
- * entries later, the virtual memory manager should care about the w/a about the
- * problem. The followings describe w/a.
+ * However, the logic has a bug that while caching faulty page table entries,
+ * System MMU reports page fault if the cached fault entry is hit even though
+ * the fault entry is updated to a valid entry after the entry is cached.
+ * To prevent caching faulty page table entries which may be updated to valid
+ * entries later, the virtual memory manager should care about the workaround
+ * for the problem. The following describes the workaround.
  *
  * Any two consecutive I/O virtual address regions must have a hole of 128KiB
- * in maximum to prevent misbehavior of System MMU 3.x. (w/a of h/w bug)
+ * at maximum to prevent misbehavior of System MMU 3.x (workaround for h/w bug).
  *
- * Precisely, any start address of I/O virtual region must be aligned by
+ * Precisely, any start address of I/O virtual region must be aligned with
  * the following sizes for System MMU v3.1 and v3.2.
  * System MMU v3.1: 128KiB
  * System MMU v3.2: 256KiB
  *
  * Because System MMU v3.3 caches page table entries more aggressively, it needs
- * more w/a.
- * - Any two consecutive I/O virtual regions must be have a hole of larger size
- *   than or equal size to 128KiB.
+ * more workarounds.
+ * - Any two consecutive I/O virtual regions must have a hole of size larger
+ *   than or equal to 128KiB.
  * - Start address of an I/O virtual region must be aligned by 128KiB.
  */
 static int exynos_iommu_map(struct iommu_domain *domain, unsigned long l_iova,
@@ -1061,7 +1061,8 @@ static size_t exynos_iommu_unmap(struct iommu_domain *domain,
 			goto err;
 		}
 
-		*ent = ZERO_LV2LINK; /* w/a for h/w bug in Sysmem MMU v3.3 */
+		/* workaround for h/w bug in System MMU v3.3 */
+		*ent = ZERO_LV2LINK;
 		pgtable_flush(ent, ent + 1);
 		size = SECT_SIZE;
 		goto done;
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index 56feed7cec15..c828f80d48b0 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -411,8 +411,7 @@ static phys_addr_t fsl_pamu_iova_to_phys(struct iommu_domain *domain,
 	return get_phys_addr(dma_domain, iova);
 }
 
-static int fsl_pamu_domain_has_cap(struct iommu_domain *domain,
-				      unsigned long cap)
+static bool fsl_pamu_capable(enum iommu_cap cap)
 {
 	return cap == IOMMU_CAP_CACHE_COHERENCY;
 }
@@ -1080,6 +1079,7 @@ static u32 fsl_pamu_get_windows(struct iommu_domain *domain)
 }
 
 static const struct iommu_ops fsl_pamu_ops = {
+	.capable	= fsl_pamu_capable,
 	.domain_init	= fsl_pamu_domain_init,
 	.domain_destroy = fsl_pamu_domain_destroy,
 	.attach_dev	= fsl_pamu_attach_device,
@@ -1089,7 +1089,6 @@ static const struct iommu_ops fsl_pamu_ops = {
 	.domain_get_windows = fsl_pamu_get_windows,
 	.domain_set_windows = fsl_pamu_set_windows,
 	.iova_to_phys	= fsl_pamu_iova_to_phys,
-	.domain_has_cap = fsl_pamu_domain_has_cap,
 	.domain_set_attr = fsl_pamu_set_domain_attr,
 	.domain_get_attr = fsl_pamu_get_domain_attr,
 	.add_device	= fsl_pamu_add_device,
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 5619f264862d..a27d6cb1a793 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3865,8 +3865,7 @@ static int device_notifier(struct notifier_block *nb,
 	if (iommu_dummy(dev))
 		return 0;
 
-	if (action != BUS_NOTIFY_UNBOUND_DRIVER &&
-	    action != BUS_NOTIFY_DEL_DEVICE)
+	if (action != BUS_NOTIFY_REMOVED_DEVICE)
 		return 0;
 
 	/*
@@ -4415,17 +4414,14 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	return phys;
 }
 
-static int intel_iommu_domain_has_cap(struct iommu_domain *domain,
-				      unsigned long cap)
+static bool intel_iommu_capable(enum iommu_cap cap)
 {
-	struct dmar_domain *dmar_domain = domain->priv;
-
 	if (cap == IOMMU_CAP_CACHE_COHERENCY)
-		return dmar_domain->iommu_snooping;
+		return domain_update_iommu_snooping(NULL) == 1;
 	if (cap == IOMMU_CAP_INTR_REMAP)
-		return irq_remapping_enabled;
+		return irq_remapping_enabled == 1;
 
-	return 0;
+	return false;
 }
 
 static int intel_iommu_add_device(struct device *dev)
@@ -4464,6 +4460,7 @@ static void intel_iommu_remove_device(struct device *dev)
 }
 
 static const struct iommu_ops intel_iommu_ops = {
+	.capable	= intel_iommu_capable,
 	.domain_init	= intel_iommu_domain_init,
 	.domain_destroy = intel_iommu_domain_destroy,
 	.attach_dev	= intel_iommu_attach_device,
@@ -4471,7 +4468,6 @@ static const struct iommu_ops intel_iommu_ops = {
 	.map		= intel_iommu_map,
 	.unmap		= intel_iommu_unmap,
 	.iova_to_phys	= intel_iommu_iova_to_phys,
-	.domain_has_cap = intel_iommu_domain_has_cap,
 	.add_device	= intel_iommu_add_device,
 	.remove_device	= intel_iommu_remove_device,
 	.pgsize_bitmap	= INTEL_IOMMU_PGSIZES,
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 0df41f6264f5..7c80661b35c1 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -438,8 +438,7 @@ static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode)
 		    (addr) | IR_X2APIC_MODE(mode) | INTR_REMAP_TABLE_REG_SIZE);
 
 	/* Set interrupt-remapping table pointer */
-	iommu->gcmd |= DMA_GCMD_SIRTP;
-	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);
+	writel(iommu->gcmd | DMA_GCMD_SIRTP, iommu->reg + DMAR_GCMD_REG);
 
 	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
 		      readl, (sts & DMA_GSTS_IRTPS), sts);
@@ -1139,7 +1138,7 @@ static int intel_msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
 	return ret;
 }
 
-static int intel_setup_hpet_msi(unsigned int irq, unsigned int id)
+static int intel_alloc_hpet_msi(unsigned int irq, unsigned int id)
 {
 	int ret = -1;
 	struct intel_iommu *iommu;
@@ -1170,5 +1169,5 @@ struct irq_remap_ops intel_irq_remap_ops = {
 	.compose_msi_msg	= intel_compose_msi_msg,
 	.msi_alloc_irq		= intel_msi_alloc_irq,
 	.msi_setup_irq		= intel_msi_setup_irq,
-	.setup_hpet_msi		= intel_setup_hpet_msi,
+	.alloc_hpet_msi		= intel_alloc_hpet_msi,
 };
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 0639b9274b11..ed8b04867b1f 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -30,6 +30,7 @@
 #include <linux/notifier.h>
 #include <linux/err.h>
 #include <linux/pci.h>
+#include <linux/bitops.h>
 #include <trace/events/iommu.h>
 
 static struct kset *iommu_group_kset;
@@ -519,6 +520,9 @@ int iommu_group_id(struct iommu_group *group)
 }
 EXPORT_SYMBOL_GPL(iommu_group_id);
 
+static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
+					       unsigned long *devfns);
+
 /*
  * To consider a PCI device isolated, we require ACS to support Source
  * Validation, Request Redirection, Completer Redirection, and Upstream
@@ -529,6 +533,86 @@ EXPORT_SYMBOL_GPL(iommu_group_id);
  */
 #define REQ_ACS_FLAGS   (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF)
 
+/*
+ * For multifunction devices which are not isolated from each other, find
+ * all the other non-isolated functions and look for existing groups.  For
+ * each function, we also need to look for aliases to or from other devices
+ * that may already have a group.
+ */
+static struct iommu_group *get_pci_function_alias_group(struct pci_dev *pdev,
+							unsigned long *devfns)
+{
+	struct pci_dev *tmp = NULL;
+	struct iommu_group *group;
+
+	if (!pdev->multifunction || pci_acs_enabled(pdev, REQ_ACS_FLAGS))
+		return NULL;
+
+	for_each_pci_dev(tmp) {
+		if (tmp == pdev || tmp->bus != pdev->bus ||
+		    PCI_SLOT(tmp->devfn) != PCI_SLOT(pdev->devfn) ||
+		    pci_acs_enabled(tmp, REQ_ACS_FLAGS))
+			continue;
+
+		group = get_pci_alias_group(tmp, devfns);
+		if (group) {
+			pci_dev_put(tmp);
+			return group;
+		}
+	}
+
+	return NULL;
+}
+
+/*
+ * Look for aliases to or from the given device for exisiting groups.  The
+ * dma_alias_devfn only supports aliases on the same bus, therefore the search
+ * space is quite small (especially since we're really only looking at pcie
+ * device, and therefore only expect multiple slots on the root complex or
+ * downstream switch ports).  It's conceivable though that a pair of
+ * multifunction devices could have aliases between them that would cause a
+ * loop.  To prevent this, we use a bitmap to track where we've been.
+ */
+static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev,
+					       unsigned long *devfns)
+{
+	struct pci_dev *tmp = NULL;
+	struct iommu_group *group;
+
+	if (test_and_set_bit(pdev->devfn & 0xff, devfns))
+		return NULL;
+
+	group = iommu_group_get(&pdev->dev);
+	if (group)
+		return group;
+
+	for_each_pci_dev(tmp) {
+		if (tmp == pdev || tmp->bus != pdev->bus)
+			continue;
+
+		/* We alias them or they alias us */
+		if (((pdev->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN) &&
+		     pdev->dma_alias_devfn == tmp->devfn) ||
+		    ((tmp->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN) &&
+		     tmp->dma_alias_devfn == pdev->devfn)) {
+
+			group = get_pci_alias_group(tmp, devfns);
+			if (group) {
+				pci_dev_put(tmp);
+				return group;
+			}
+
+			group = get_pci_function_alias_group(tmp, devfns);
+			if (group) {
+				pci_dev_put(tmp);
+				return group;
+			}
+		}
+	}
+
+	return NULL;
+}
+
 struct group_for_pci_data {
 	struct pci_dev *pdev;
 	struct iommu_group *group;
@@ -557,7 +641,7 @@ static struct iommu_group *iommu_group_get_for_pci_dev(struct pci_dev *pdev)
 	struct group_for_pci_data data;
 	struct pci_bus *bus;
 	struct iommu_group *group = NULL;
-	struct pci_dev *tmp;
+	u64 devfns[4] = { 0 };
 
 	/*
 	 * Find the upstream DMA alias for the device.  A device must not
@@ -591,76 +675,21 @@ static struct iommu_group *iommu_group_get_for_pci_dev(struct pci_dev *pdev)
 	}
 
 	/*
-	 * Next we need to consider DMA alias quirks.  If one device aliases
-	 * to another, they should be grouped together.  It's theoretically
-	 * possible that aliases could create chains of devices where each
-	 * device aliases another device.  If we then factor in multifunction
-	 * ACS grouping requirements, each alias could incorporate a new slot
-	 * with multiple functions, each with aliases.  This is all extremely
-	 * unlikely as DMA alias quirks are typically only used for PCIe
-	 * devices where we usually have a single slot per bus.  Furthermore,
-	 * the alias quirk is usually to another function within the slot
-	 * (and ACS multifunction is not supported) or to a different slot
-	 * that doesn't physically exist.  The likely scenario is therefore
-	 * that everything on the bus gets grouped together.  To reduce the
-	 * problem space, share the IOMMU group for all devices on the bus
-	 * if a DMA alias quirk is present on the bus.
+	 * Look for existing groups on device aliases.  If we alias another
+	 * device or another device aliases us, use the same group.
 	 */
-	tmp = NULL;
-	for_each_pci_dev(tmp) {
-		if (tmp->bus != pdev->bus ||
-		    !(tmp->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN))
-			continue;
-
-		pci_dev_put(tmp);
-		tmp = NULL;
-
-		/* We have an alias quirk, search for an existing group */
-		for_each_pci_dev(tmp) {
-			struct iommu_group *group_tmp;
-
-			if (tmp->bus != pdev->bus)
-				continue;
-
-			group_tmp = iommu_group_get(&tmp->dev);
-			if (!group) {
-				group = group_tmp;
-				continue;
-			}
-
-			if (group_tmp) {
-				WARN_ON(group != group_tmp);
-				iommu_group_put(group_tmp);
-			}
-		}
-
-		return group ? group : iommu_group_alloc();
-	}
-
-	/*
-	 * Non-multifunction devices or multifunction devices supporting
-	 * ACS get their own group.
-	 */
-	if (!pdev->multifunction || pci_acs_enabled(pdev, REQ_ACS_FLAGS))
-		return iommu_group_alloc();
+	group = get_pci_alias_group(pdev, (unsigned long *)devfns);
+	if (group)
+		return group;
 
 	/*
-	 * Multifunction devices not supporting ACS share a group with other
-	 * similar devices in the same slot.
+	 * Look for existing groups on non-isolated functions on the same
+	 * slot and aliases of those funcions, if any.  No need to clear
+	 * the search bitmap, the tested devfns are still valid.
 	 */
-	tmp = NULL;
-	for_each_pci_dev(tmp) {
-		if (tmp == pdev || tmp->bus != pdev->bus ||
-		    PCI_SLOT(tmp->devfn) !=  PCI_SLOT(pdev->devfn) ||
-		    pci_acs_enabled(tmp, REQ_ACS_FLAGS))
-			continue;
-
-		group = iommu_group_get(&tmp->dev);
-		if (group) {
-			pci_dev_put(tmp);
-			return group;
-		}
-	}
+	group = get_pci_function_alias_group(pdev, (unsigned long *)devfns);
+	if (group)
+		return group;
 
 	/* No shared group found, allocate new */
 	return iommu_group_alloc();
@@ -770,18 +799,26 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 	return 0;
 }
 
-static struct notifier_block iommu_bus_nb = {
-	.notifier_call = iommu_bus_notifier,
-};
-
-static void iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
+static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
 {
+	int err;
+	struct notifier_block *nb;
 	struct iommu_callback_data cb = {
 		.ops = ops,
 	};
 
-	bus_register_notifier(bus, &iommu_bus_nb);
-	bus_for_each_dev(bus, NULL, &cb, add_iommu_group);
+	nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
+	if (!nb)
+		return -ENOMEM;
+
+	nb->notifier_call = iommu_bus_notifier;
+
+	err = bus_register_notifier(bus, nb);
+	if (err) {
+		kfree(nb);
+		return err;
+	}
+	return bus_for_each_dev(bus, NULL, &cb, add_iommu_group);
 }
 
 /**
@@ -805,9 +842,7 @@ int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops)
 	bus->iommu_ops = ops;
 
 	/* Do IOMMU specific setup for this bus-type */
-	iommu_bus_init(bus, ops);
-
-	return 0;
+	return iommu_bus_init(bus, ops);
 }
 EXPORT_SYMBOL_GPL(bus_set_iommu);
 
@@ -817,6 +852,15 @@ bool iommu_present(struct bus_type *bus)
 }
 EXPORT_SYMBOL_GPL(iommu_present);
 
+bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
+{
+	if (!bus->iommu_ops || !bus->iommu_ops->capable)
+		return false;
+
+	return bus->iommu_ops->capable(cap);
+}
+EXPORT_SYMBOL_GPL(iommu_capable);
+
 /**
  * iommu_set_fault_handler() - set a fault handler for an iommu domain
  * @domain: iommu domain
@@ -947,16 +991,6 @@ phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 }
 EXPORT_SYMBOL_GPL(iommu_iova_to_phys);
 
-int iommu_domain_has_cap(struct iommu_domain *domain,
-			 unsigned long cap)
-{
-	if (unlikely(domain->ops->domain_has_cap == NULL))
-		return 0;
-
-	return domain->ops->domain_has_cap(domain, cap);
-}
-EXPORT_SYMBOL_GPL(iommu_domain_has_cap);
-
 static size_t iommu_pgsize(struct iommu_domain *domain,
 			   unsigned long addr_merge, size_t size)
 {
diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
index 33c439524080..74a1767c89b5 100644
--- a/drivers/iommu/irq_remapping.c
+++ b/drivers/iommu/irq_remapping.c
@@ -12,6 +12,7 @@
 #include <asm/processor.h>
 #include <asm/x86_init.h>
 #include <asm/apic.h>
+#include <asm/hpet.h>
 
 #include "irq_remapping.h"
 
@@ -345,10 +346,16 @@ static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
 
 int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
 {
-	if (!remap_ops || !remap_ops->setup_hpet_msi)
+	int ret;
+
+	if (!remap_ops || !remap_ops->alloc_hpet_msi)
 		return -ENODEV;
 
-	return remap_ops->setup_hpet_msi(irq, id);
+	ret = remap_ops->alloc_hpet_msi(irq, id);
+	if (ret)
+		return -EINVAL;
+
+	return default_setup_hpet_msi(irq, id);
 }
 
 void panic_if_irq_remap(const char *msg)
diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h
index 90c4dae5a46b..fde250f86e60 100644
--- a/drivers/iommu/irq_remapping.h
+++ b/drivers/iommu/irq_remapping.h
@@ -80,7 +80,7 @@ struct irq_remap_ops {
 	int (*msi_setup_irq)(struct pci_dev *, unsigned int, int, int);
 
 	/* Setup interrupt remapping for an HPET MSI */
-	int (*setup_hpet_msi)(unsigned int, unsigned int);
+	int (*alloc_hpet_msi)(unsigned int, unsigned int);
 };
 
 extern struct irq_remap_ops intel_irq_remap_ops;
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 49f41d6e02f1..6e3dcc289d59 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -603,10 +603,9 @@ fail:
 	return ret;
 }
 
-static int msm_iommu_domain_has_cap(struct iommu_domain *domain,
-				    unsigned long cap)
+static bool msm_iommu_capable(enum iommu_cap cap)
 {
-	return 0;
+	return false;
 }
 
 static void print_ctx_regs(void __iomem *base, int ctx)
@@ -675,6 +674,7 @@ fail:
 }
 
 static const struct iommu_ops msm_iommu_ops = {
+	.capable = msm_iommu_capable,
 	.domain_init = msm_iommu_domain_init,
 	.domain_destroy = msm_iommu_domain_destroy,
 	.attach_dev = msm_iommu_attach_dev,
@@ -682,7 +682,6 @@ static const struct iommu_ops msm_iommu_ops = {
 	.map = msm_iommu_map,
 	.unmap = msm_iommu_unmap,
 	.iova_to_phys = msm_iommu_iova_to_phys,
-	.domain_has_cap = msm_iommu_domain_has_cap,
 	.pgsize_bitmap = MSM_IOMMU_PGSIZES,
 };
 
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index e202b0c24120..36278870e84a 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -26,6 +26,7 @@
 #include <linux/of.h>
 #include <linux/of_iommu.h>
 #include <linux/of_irq.h>
+#include <linux/of_platform.h>
 
 #include <asm/cacheflush.h>
 
@@ -892,19 +893,11 @@ static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd)
 		goto err_enable;
 	flush_iotlb_all(obj);
 
-	if (!try_module_get(obj->owner)) {
-		err = -ENODEV;
-		goto err_module;
-	}
-
 	spin_unlock(&obj->iommu_lock);
 
 	dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
 	return obj;
 
-err_module:
-	if (obj->refcount == 1)
-		iommu_disable(obj);
 err_enable:
 	obj->refcount--;
 	spin_unlock(&obj->iommu_lock);
@@ -925,8 +918,6 @@ static void omap_iommu_detach(struct omap_iommu *obj)
 	if (--obj->refcount == 0)
 		iommu_disable(obj);
 
-	module_put(obj->owner);
-
 	obj->iopgd = NULL;
 
 	spin_unlock(&obj->iommu_lock);
@@ -1006,7 +997,7 @@ static int omap_iommu_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct of_device_id omap_iommu_of_match[] = {
+static const struct of_device_id omap_iommu_of_match[] = {
 	{ .compatible = "ti,omap2-iommu" },
 	{ .compatible = "ti,omap4-iommu" },
 	{ .compatible = "ti,dra7-iommu"	},
@@ -1091,6 +1082,11 @@ omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
 	int ret = 0;
 
+	if (!arch_data || !arch_data->name) {
+		dev_err(dev, "device doesn't have an associated iommu\n");
+		return -EINVAL;
+	}
+
 	spin_lock(&omap_domain->lock);
 
 	/* only a single device is supported per domain for now */
@@ -1239,6 +1235,7 @@ static int omap_iommu_add_device(struct device *dev)
 {
 	struct omap_iommu_arch_data *arch_data;
 	struct device_node *np;
+	struct platform_device *pdev;
 
 	/*
 	 * Allocate the archdata iommu structure for DT-based devices.
@@ -1253,13 +1250,19 @@ static int omap_iommu_add_device(struct device *dev)
 	if (!np)
 		return 0;
 
+	pdev = of_find_device_by_node(np);
+	if (WARN_ON(!pdev)) {
+		of_node_put(np);
+		return -EINVAL;
+	}
+
 	arch_data = kzalloc(sizeof(*arch_data), GFP_KERNEL);
 	if (!arch_data) {
 		of_node_put(np);
 		return -ENOMEM;
 	}
 
-	arch_data->name = kstrdup(dev_name(dev), GFP_KERNEL);
+	arch_data->name = kstrdup(dev_name(&pdev->dev), GFP_KERNEL);
 	dev->archdata.iommu = arch_data;
 
 	of_node_put(np);
diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h
index 1275a822934b..4f1b68c08c15 100644
--- a/drivers/iommu/omap-iommu.h
+++ b/drivers/iommu/omap-iommu.h
@@ -28,7 +28,6 @@ struct iotlb_entry {
 
 struct omap_iommu {
 	const char	*name;
-	struct module	*owner;
 	void __iomem	*regbase;
 	struct device	*dev;
 	void		*isr_priv;
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index b10a8ecede8e..a6d76abf2c06 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -303,13 +303,13 @@ static phys_addr_t gart_iommu_iova_to_phys(struct iommu_domain *domain,
 	return pa;
 }
 
-static int gart_iommu_domain_has_cap(struct iommu_domain *domain,
-				     unsigned long cap)
+static bool gart_iommu_capable(enum iommu_cap cap)
 {
-	return 0;
+	return false;
 }
 
 static const struct iommu_ops gart_iommu_ops = {
+	.capable	= gart_iommu_capable,
 	.domain_init	= gart_iommu_domain_init,
 	.domain_destroy	= gart_iommu_domain_destroy,
 	.attach_dev	= gart_iommu_attach_dev,
@@ -317,7 +317,6 @@ static const struct iommu_ops gart_iommu_ops = {
 	.map		= gart_iommu_map,
 	.unmap		= gart_iommu_unmap,
 	.iova_to_phys	= gart_iommu_iova_to_phys,
-	.domain_has_cap	= gart_iommu_domain_has_cap,
 	.pgsize_bitmap	= GART_IOMMU_PGSIZES,
 };
 
@@ -416,7 +415,7 @@ static const struct dev_pm_ops tegra_gart_pm_ops = {
 	.resume		= tegra_gart_resume,
 };
 
-static struct of_device_id tegra_gart_of_match[] = {
+static const struct of_device_id tegra_gart_of_match[] = {
 	{ .compatible = "nvidia,tegra20-gart", },
 	{ },
 };
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 3ded3894623c..3afdf43f732a 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -780,10 +780,9 @@ static phys_addr_t smmu_iommu_iova_to_phys(struct iommu_domain *domain,
 	return PFN_PHYS(pfn);
 }
 
-static int smmu_iommu_domain_has_cap(struct iommu_domain *domain,
-				     unsigned long cap)
+static bool smmu_iommu_capable(enum iommu_cap cap)
 {
-	return 0;
+	return false;
 }
 
 static int smmu_iommu_attach_dev(struct iommu_domain *domain,
@@ -949,6 +948,7 @@ static void smmu_iommu_domain_destroy(struct iommu_domain *domain)
 }
 
 static const struct iommu_ops smmu_iommu_ops = {
+	.capable	= smmu_iommu_capable,
 	.domain_init	= smmu_iommu_domain_init,
 	.domain_destroy	= smmu_iommu_domain_destroy,
 	.attach_dev	= smmu_iommu_attach_dev,
@@ -956,7 +956,6 @@ static const struct iommu_ops smmu_iommu_ops = {
 	.map		= smmu_iommu_map,
 	.unmap		= smmu_iommu_unmap,
 	.iova_to_phys	= smmu_iommu_iova_to_phys,
-	.domain_has_cap	= smmu_iommu_domain_has_cap,
 	.pgsize_bitmap	= SMMU_IOMMU_PGSIZES,
 };
 
@@ -1260,7 +1259,7 @@ static const struct dev_pm_ops tegra_smmu_pm_ops = {
 	.resume		= tegra_smmu_resume,
 };
 
-static struct of_device_id tegra_smmu_of_match[] = {
+static const struct of_device_id tegra_smmu_of_match[] = {
 	{ .compatible = "nvidia,tegra30-smmu", },
 	{ },
 };
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 78d4ff551590..b21f12f1766d 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -118,3 +118,10 @@ config IRQ_CROSSBAR
 	  The primary irqchip invokes the crossbar's callback which inturn allocates
 	  a free irq and configures the IP. Thus the peripheral interrupts are
 	  routed to one of the free irqchip interrupt lines.
+
+config KEYSTONE_IRQ
+	tristate "Keystone 2 IRQ controller IP"
+	depends on ARCH_KEYSTONE
+	help
+		Support for Texas Instruments Keystone 2 IRQ controller IP which
+		is part of the Keystone 2 IPC mechanism
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index d0a2613c73bc..173bb5fa2cc9 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -2,6 +2,7 @@ obj-$(CONFIG_IRQCHIP)			+= irqchip.o
 
 obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2835.o
 obj-$(CONFIG_ARCH_EXYNOS)		+= exynos-combiner.o
+obj-$(CONFIG_ARCH_HIP04)		+= irq-hip04.o
 obj-$(CONFIG_ARCH_MMP)			+= irq-mmp.o
 obj-$(CONFIG_ARCH_MVEBU)		+= irq-armada-370-xp.o
 obj-$(CONFIG_ARCH_MXS)			+= irq-mxs.o
@@ -34,4 +35,6 @@ obj-$(CONFIG_TB10X_IRQC)		+= irq-tb10x.o
 obj-$(CONFIG_XTENSA)			+= irq-xtensa-pic.o
 obj-$(CONFIG_XTENSA_MX)			+= irq-xtensa-mx.o
 obj-$(CONFIG_IRQ_CROSSBAR)		+= irq-crossbar.o
-obj-$(CONFIG_BRCMSTB_L2_IRQ)		+= irq-brcmstb-l2.o
+obj-$(CONFIG_BRCMSTB_L2_IRQ)		+= irq-brcmstb-l2.o \
+					   irq-bcm7120-l2.o
+obj-$(CONFIG_KEYSTONE_IRQ)		+= irq-keystone.o
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 574aba0eba4e..3e238cd049e6 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -136,6 +136,10 @@ static int armada_370_xp_setup_msi_irq(struct msi_chip *chip,
 	struct msi_msg msg;
 	int virq, hwirq;
 
+	/* We support MSI, but not MSI-X */
+	if (desc->msi_attrib.is_msix)
+		return -EINVAL;
+
 	hwirq = armada_370_xp_alloc_msi();
 	if (hwirq < 0)
 		return hwirq;
@@ -166,15 +170,6 @@ static void armada_370_xp_teardown_msi_irq(struct msi_chip *chip,
 	armada_370_xp_free_msi(hwirq);
 }
 
-static int armada_370_xp_check_msi_device(struct msi_chip *chip, struct pci_dev *dev,
-					  int nvec, int type)
-{
-	/* We support MSI, but not MSI-X */
-	if (type == PCI_CAP_ID_MSI)
-		return 0;
-	return -EINVAL;
-}
-
 static struct irq_chip armada_370_xp_msi_irq_chip = {
 	.name = "armada_370_xp_msi_irq",
 	.irq_enable = unmask_msi_irq,
@@ -213,7 +208,6 @@ static int armada_370_xp_msi_init(struct device_node *node,
 
 	msi_chip->setup_irq = armada_370_xp_setup_msi_irq;
 	msi_chip->teardown_irq = armada_370_xp_teardown_msi_irq;
-	msi_chip->check_device = armada_370_xp_check_msi_device;
 	msi_chip->of_node = node;
 
 	armada_370_xp_msi_domain =
@@ -393,13 +387,15 @@ static void armada_370_xp_handle_msi_irq(struct pt_regs *regs, bool is_chained)
 		if (!(msimask & BIT(msinr)))
 			continue;
 
-		irq = irq_find_mapping(armada_370_xp_msi_domain,
-				       msinr - 16);
-
-		if (is_chained)
+		if (is_chained) {
+			irq = irq_find_mapping(armada_370_xp_msi_domain,
+					       msinr - 16);
 			generic_handle_irq(irq);
-		else
-			handle_IRQ(irq, regs);
+		} else {
+			irq = msinr - 16;
+			handle_domain_irq(armada_370_xp_msi_domain,
+					  irq, regs);
+		}
 	}
 }
 #else
@@ -444,9 +440,8 @@ armada_370_xp_handle_irq(struct pt_regs *regs)
 			break;
 
 		if (irqnr > 1) {
-			irqnr =	irq_find_mapping(armada_370_xp_mpic_domain,
-					irqnr);
-			handle_IRQ(irqnr, regs);
+			handle_domain_irq(armada_370_xp_mpic_domain,
+					  irqnr, regs);
 			continue;
 		}
 
diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c
index a82869e9fb26..9a2cf3c1a3a5 100644
--- a/drivers/irqchip/irq-atmel-aic.c
+++ b/drivers/irqchip/irq-atmel-aic.c
@@ -68,12 +68,10 @@ aic_handle(struct pt_regs *regs)
 	irqnr = irq_reg_readl(gc->reg_base + AT91_AIC_IVR);
 	irqstat = irq_reg_readl(gc->reg_base + AT91_AIC_ISR);
 
-	irqnr = irq_find_mapping(aic_domain, irqnr);
-
 	if (!irqstat)
 		irq_reg_writel(0, gc->reg_base + AT91_AIC_EOICR);
 	else
-		handle_IRQ(irqnr, regs);
+		handle_domain_irq(aic_domain, irqnr, regs);
 }
 
 static int aic_retrigger(struct irq_data *d)
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index edb227081524..a11aae8fb006 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -78,12 +78,10 @@ aic5_handle(struct pt_regs *regs)
 	irqnr = irq_reg_readl(gc->reg_base + AT91_AIC5_IVR);
 	irqstat = irq_reg_readl(gc->reg_base + AT91_AIC5_ISR);
 
-	irqnr = irq_find_mapping(aic5_domain, irqnr);
-
 	if (!irqstat)
 		irq_reg_writel(0, gc->reg_base + AT91_AIC5_EOICR);
 	else
-		handle_IRQ(irqnr, regs);
+		handle_domain_irq(aic5_domain, irqnr, regs);
 }
 
 static void aic5_mask(struct irq_data *d)
@@ -297,6 +295,7 @@ static void __init sama5d3_aic_irq_fixup(struct device_node *root)
 
 static const struct of_device_id __initdata aic5_irq_fixups[] = {
 	{ .compatible = "atmel,sama5d3", .data = sama5d3_aic_irq_fixup },
+	{ .compatible = "atmel,sama5d4", .data = sama5d3_aic_irq_fixup },
 	{ /* sentinel */ },
 };
 
@@ -343,7 +342,7 @@ static int __init aic5_of_init(struct device_node *node,
 	return 0;
 }
 
-#define NR_SAMA5D3_IRQS		50
+#define NR_SAMA5D3_IRQS		48
 
 static int __init sama5d3_aic5_of_init(struct device_node *node,
 				       struct device_node *parent)
@@ -351,3 +350,12 @@ static int __init sama5d3_aic5_of_init(struct device_node *node,
 	return aic5_of_init(node, parent, NR_SAMA5D3_IRQS);
 }
 IRQCHIP_DECLARE(sama5d3_aic5, "atmel,sama5d3-aic", sama5d3_aic5_of_init);
+
+#define NR_SAMA5D4_IRQS		68
+
+static int __init sama5d4_aic5_of_init(struct device_node *node,
+				       struct device_node *parent)
+{
+	return aic5_of_init(node, parent, NR_SAMA5D4_IRQS);
+}
+IRQCHIP_DECLARE(sama5d4_aic5, "atmel,sama5d4-aic", sama5d4_aic5_of_init);
diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c
new file mode 100644
index 000000000000..b9f4fb808e49
--- /dev/null
+++ b/drivers/irqchip/irq-bcm7120-l2.c
@@ -0,0 +1,219 @@
+/*
+ * Broadcom BCM7120 style Level 2 interrupt controller driver
+ *
+ * Copyright (C) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME	": " fmt
+
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/irqdomain.h>
+#include <linux/reboot.h>
+#include <linux/irqchip/chained_irq.h>
+
+#include "irqchip.h"
+
+#include <asm/mach/irq.h>
+
+/* Register offset in the L2 interrupt controller */
+#define IRQEN		0x00
+#define IRQSTAT		0x04
+
+struct bcm7120_l2_intc_data {
+	void __iomem *base;
+	struct irq_domain *domain;
+	bool can_wake;
+	u32 irq_fwd_mask;
+	u32 irq_map_mask;
+	u32 saved_mask;
+};
+
+static void bcm7120_l2_intc_irq_handle(unsigned int irq, struct irq_desc *desc)
+{
+	struct bcm7120_l2_intc_data *b = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	u32 status;
+
+	chained_irq_enter(chip, desc);
+
+	status = __raw_readl(b->base + IRQSTAT);
+
+	if (status == 0) {
+		do_bad_IRQ(irq, desc);
+		goto out;
+	}
+
+	do {
+		irq = ffs(status) - 1;
+		status &= ~(1 << irq);
+		generic_handle_irq(irq_find_mapping(b->domain, irq));
+	} while (status);
+
+out:
+	chained_irq_exit(chip, desc);
+}
+
+static void bcm7120_l2_intc_suspend(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct bcm7120_l2_intc_data *b = gc->private;
+	u32 reg;
+
+	irq_gc_lock(gc);
+	/* Save the current mask and the interrupt forward mask */
+	b->saved_mask = __raw_readl(b->base) | b->irq_fwd_mask;
+	if (b->can_wake) {
+		reg = b->saved_mask | gc->wake_active;
+		__raw_writel(reg, b->base);
+	}
+	irq_gc_unlock(gc);
+}
+
+static void bcm7120_l2_intc_resume(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct bcm7120_l2_intc_data *b = gc->private;
+
+	/* Restore the saved mask */
+	irq_gc_lock(gc);
+	__raw_writel(b->saved_mask, b->base);
+	irq_gc_unlock(gc);
+}
+
+static int bcm7120_l2_intc_init_one(struct device_node *dn,
+					struct bcm7120_l2_intc_data *data,
+					int irq, const __be32 *map_mask)
+{
+	int parent_irq;
+
+	parent_irq = irq_of_parse_and_map(dn, irq);
+	if (parent_irq < 0) {
+		pr_err("failed to map interrupt %d\n", irq);
+		return parent_irq;
+	}
+
+	data->irq_map_mask |= be32_to_cpup(map_mask + irq);
+
+	irq_set_handler_data(parent_irq, data);
+	irq_set_chained_handler(parent_irq, bcm7120_l2_intc_irq_handle);
+
+	return 0;
+}
+
+int __init bcm7120_l2_intc_of_init(struct device_node *dn,
+					struct device_node *parent)
+{
+	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
+	struct bcm7120_l2_intc_data *data;
+	struct irq_chip_generic *gc;
+	struct irq_chip_type *ct;
+	const __be32 *map_mask;
+	int num_parent_irqs;
+	int ret = 0, len, irq;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->base = of_iomap(dn, 0);
+	if (!data->base) {
+		pr_err("failed to remap intc L2 registers\n");
+		ret = -ENOMEM;
+		goto out_free;
+	}
+
+	if (of_property_read_u32(dn, "brcm,int-fwd-mask", &data->irq_fwd_mask))
+		data->irq_fwd_mask = 0;
+
+	/* Enable all interrupt specified in the interrupt forward mask and have
+	 * the other disabled
+	 */
+	__raw_writel(data->irq_fwd_mask, data->base + IRQEN);
+
+	num_parent_irqs = of_irq_count(dn);
+	if (num_parent_irqs <= 0) {
+		pr_err("invalid number of parent interrupts\n");
+		ret = -ENOMEM;
+		goto out_unmap;
+	}
+
+	map_mask = of_get_property(dn, "brcm,int-map-mask", &len);
+	if (!map_mask || (len != (sizeof(*map_mask) * num_parent_irqs))) {
+		pr_err("invalid brcm,int-map-mask property\n");
+		ret = -EINVAL;
+		goto out_unmap;
+	}
+
+	for (irq = 0; irq < num_parent_irqs; irq++) {
+		ret = bcm7120_l2_intc_init_one(dn, data, irq, map_mask);
+		if (ret)
+			goto out_unmap;
+	}
+
+	data->domain = irq_domain_add_linear(dn, 32,
+					&irq_generic_chip_ops, NULL);
+	if (!data->domain) {
+		ret = -ENOMEM;
+		goto out_unmap;
+	}
+
+	ret = irq_alloc_domain_generic_chips(data->domain, 32, 1,
+				dn->full_name, handle_level_irq, clr, 0,
+				IRQ_GC_INIT_MASK_CACHE);
+	if (ret) {
+		pr_err("failed to allocate generic irq chip\n");
+		goto out_free_domain;
+	}
+
+	gc = irq_get_domain_generic_chip(data->domain, 0);
+	gc->unused = 0xfffffff & ~data->irq_map_mask;
+	gc->reg_base = data->base;
+	gc->private = data;
+	ct = gc->chip_types;
+
+	ct->regs.mask = IRQEN;
+	ct->chip.irq_mask = irq_gc_mask_clr_bit;
+	ct->chip.irq_unmask = irq_gc_mask_set_bit;
+	ct->chip.irq_ack = irq_gc_noop;
+	ct->chip.irq_suspend = bcm7120_l2_intc_suspend;
+	ct->chip.irq_resume = bcm7120_l2_intc_resume;
+
+	if (of_property_read_bool(dn, "brcm,irq-can-wake")) {
+		data->can_wake = true;
+		/* This IRQ chip can wake the system, set all relevant child
+		 * interupts in wake_enabled mask
+		 */
+		gc->wake_enabled = 0xffffffff;
+		gc->wake_enabled &= ~gc->unused;
+		ct->chip.irq_set_wake = irq_gc_set_wake;
+	}
+
+	pr_info("registered BCM7120 L2 intc (mem: 0x%p, parent IRQ(s): %d)\n",
+			data->base, num_parent_irqs);
+
+	return 0;
+
+out_free_domain:
+	irq_domain_remove(data->domain);
+out_unmap:
+	iounmap(data->base);
+out_free:
+	kfree(data);
+	return ret;
+}
+IRQCHIP_DECLARE(brcmstb_l2_intc, "brcm,bcm7120-l2-intc",
+		bcm7120_l2_intc_of_init);
diff --git a/drivers/irqchip/irq-clps711x.c b/drivers/irqchip/irq-clps711x.c
index 33340dc97d1d..33127f131d78 100644
--- a/drivers/irqchip/irq-clps711x.c
+++ b/drivers/irqchip/irq-clps711x.c
@@ -76,24 +76,20 @@ static struct {
 
 static asmlinkage void __exception_irq_entry clps711x_irqh(struct pt_regs *regs)
 {
-	u32 irqnr, irqstat;
+	u32 irqstat;
 
 	do {
 		irqstat = readw_relaxed(clps711x_intc->intmr[0]) &
 			  readw_relaxed(clps711x_intc->intsr[0]);
-		if (irqstat) {
-			irqnr =	irq_find_mapping(clps711x_intc->domain,
-						 fls(irqstat) - 1);
-			handle_IRQ(irqnr, regs);
-		}
+		if (irqstat)
+			handle_domain_irq(clps711x_intc->domain,
+					  fls(irqstat) - 1, regs);
 
 		irqstat = readw_relaxed(clps711x_intc->intmr[1]) &
 			  readw_relaxed(clps711x_intc->intsr[1]);
-		if (irqstat) {
-			irqnr =	irq_find_mapping(clps711x_intc->domain,
-						 fls(irqstat) - 1 + 16);
-			handle_IRQ(irqnr, regs);
-		}
+		if (irqstat)
+			handle_domain_irq(clps711x_intc->domain,
+					  fls(irqstat) - 1 + 16, regs);
 	} while (irqstat);
 }
 
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
index 60ac704d2090..61541ff24397 100644
--- a/drivers/irqchip/irq-gic-common.c
+++ b/drivers/irqchip/irq-gic-common.c
@@ -74,20 +74,22 @@ void __init gic_dist_config(void __iomem *base, int gic_irqs,
 	 * Set all global interrupts to be level triggered, active low.
 	 */
 	for (i = 32; i < gic_irqs; i += 16)
-		writel_relaxed(0, base + GIC_DIST_CONFIG + i / 4);
+		writel_relaxed(GICD_INT_ACTLOW_LVLTRIG,
+					base + GIC_DIST_CONFIG + i / 4);
 
 	/*
 	 * Set priority on all global interrupts.
 	 */
 	for (i = 32; i < gic_irqs; i += 4)
-		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i);
+		writel_relaxed(GICD_INT_DEF_PRI_X4, base + GIC_DIST_PRI + i);
 
 	/*
 	 * Disable all interrupts.  Leave the PPI and SGIs alone
 	 * as they are enabled by redistributor registers.
 	 */
 	for (i = 32; i < gic_irqs; i += 32)
-		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i / 8);
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+					base + GIC_DIST_ENABLE_CLEAR + i / 8);
 
 	if (sync_access)
 		sync_access();
@@ -101,14 +103,15 @@ void gic_cpu_config(void __iomem *base, void (*sync_access)(void))
 	 * Deal with the banked PPI and SGI interrupts - disable all
 	 * PPI interrupts, ensure all SGI interrupts are enabled.
 	 */
-	writel_relaxed(0xffff0000, base + GIC_DIST_ENABLE_CLEAR);
-	writel_relaxed(0x0000ffff, base + GIC_DIST_ENABLE_SET);
+	writel_relaxed(GICD_INT_EN_CLR_PPI, base + GIC_DIST_ENABLE_CLEAR);
+	writel_relaxed(GICD_INT_EN_SET_SGI, base + GIC_DIST_ENABLE_SET);
 
 	/*
 	 * Set priority on PPI and SGI interrupts
 	 */
 	for (i = 0; i < 32; i += 4)
-		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
+		writel_relaxed(GICD_INT_DEF_PRI_X4,
+					base + GIC_DIST_PRI + i * 4 / 4);
 
 	if (sync_access)
 		sync_access();
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index a0698b4f0303..aa17ae805a70 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -16,6 +16,7 @@
  */
 
 #include <linux/cpu.h>
+#include <linux/cpu_pm.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
@@ -155,7 +156,7 @@ static void gic_enable_sre(void)
 		pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n");
 }
 
-static void gic_enable_redist(void)
+static void gic_enable_redist(bool enable)
 {
 	void __iomem *rbase;
 	u32 count = 1000000;	/* 1s! */
@@ -163,20 +164,30 @@ static void gic_enable_redist(void)
 
 	rbase = gic_data_rdist_rd_base();
 
-	/* Wake up this CPU redistributor */
 	val = readl_relaxed(rbase + GICR_WAKER);
-	val &= ~GICR_WAKER_ProcessorSleep;
+	if (enable)
+		/* Wake up this CPU redistributor */
+		val &= ~GICR_WAKER_ProcessorSleep;
+	else
+		val |= GICR_WAKER_ProcessorSleep;
 	writel_relaxed(val, rbase + GICR_WAKER);
 
-	while (readl_relaxed(rbase + GICR_WAKER) & GICR_WAKER_ChildrenAsleep) {
-		count--;
-		if (!count) {
-			pr_err_ratelimited("redist didn't wake up...\n");
-			return;
-		}
+	if (!enable) {		/* Check that GICR_WAKER is writeable */
+		val = readl_relaxed(rbase + GICR_WAKER);
+		if (!(val & GICR_WAKER_ProcessorSleep))
+			return;	/* No PM support in this redistributor */
+	}
+
+	while (count--) {
+		val = readl_relaxed(rbase + GICR_WAKER);
+		if (enable ^ (val & GICR_WAKER_ChildrenAsleep))
+			break;
 		cpu_relax();
 		udelay(1);
 	};
+	if (!count)
+		pr_err_ratelimited("redistributor failed to %s...\n",
+				   enable ? "wakeup" : "sleep");
 }
 
 /*
@@ -261,14 +272,13 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs
 		irqnr = gic_read_iar();
 
 		if (likely(irqnr > 15 && irqnr < 1020)) {
-			u64 irq = irq_find_mapping(gic_data.domain, irqnr);
-			if (likely(irq)) {
-				handle_IRQ(irq, regs);
-				continue;
+			int err;
+			err = handle_domain_irq(gic_data.domain, irqnr, regs);
+			if (err) {
+				WARN_ONCE(true, "Unexpected SPI received!\n");
+				gic_write_eoir(irqnr);
 			}
-
-			WARN_ONCE(true, "Unexpected SPI received!\n");
-			gic_write_eoir(irqnr);
+			continue;
 		}
 		if (irqnr < 16) {
 			gic_write_eoir(irqnr);
@@ -360,6 +370,21 @@ static int gic_populate_rdist(void)
 	return -ENODEV;
 }
 
+static void gic_cpu_sys_reg_init(void)
+{
+	/* Enable system registers */
+	gic_enable_sre();
+
+	/* Set priority mask register */
+	gic_write_pmr(DEFAULT_PMR_VALUE);
+
+	/* EOI deactivates interrupt too (mode 0) */
+	gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir);
+
+	/* ... and let's hit the road... */
+	gic_write_grpen1(1);
+}
+
 static void gic_cpu_init(void)
 {
 	void __iomem *rbase;
@@ -368,23 +393,14 @@ static void gic_cpu_init(void)
 	if (gic_populate_rdist())
 		return;
 
-	gic_enable_redist();
+	gic_enable_redist(true);
 
 	rbase = gic_data_rdist_sgi_base();
 
 	gic_cpu_config(rbase, gic_redist_wait_for_rwp);
 
-	/* Enable system registers */
-	gic_enable_sre();
-
-	/* Set priority mask register */
-	gic_write_pmr(DEFAULT_PMR_VALUE);
-
-	/* EOI deactivates interrupt too (mode 0) */
-	gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir);
-
-	/* ... and let's hit the road... */
-	gic_write_grpen1(1);
+	/* initialise system registers */
+	gic_cpu_sys_reg_init();
 }
 
 #ifdef CONFIG_SMP
@@ -533,6 +549,33 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 #define gic_smp_init()		do { } while(0)
 #endif
 
+#ifdef CONFIG_CPU_PM
+static int gic_cpu_pm_notifier(struct notifier_block *self,
+			       unsigned long cmd, void *v)
+{
+	if (cmd == CPU_PM_EXIT) {
+		gic_enable_redist(true);
+		gic_cpu_sys_reg_init();
+	} else if (cmd == CPU_PM_ENTER) {
+		gic_write_grpen1(0);
+		gic_enable_redist(false);
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block gic_cpu_pm_notifier_block = {
+	.notifier_call = gic_cpu_pm_notifier,
+};
+
+static void gic_cpu_pm_init(void)
+{
+	cpu_pm_register_notifier(&gic_cpu_pm_notifier_block);
+}
+
+#else
+static inline void gic_cpu_pm_init(void) { }
+#endif /* CONFIG_CPU_PM */
+
 static struct irq_chip gic_chip = {
 	.name			= "GICv3",
 	.irq_mask		= gic_mask_irq,
@@ -672,6 +715,7 @@ static int __init gic_of_init(struct device_node *node, struct device_node *pare
 	gic_smp_init();
 	gic_dist_init();
 	gic_cpu_init();
+	gic_cpu_pm_init();
 
 	return 0;
 
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index dda6dbc23565..38493ff28fa5 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -102,7 +102,7 @@ static struct gic_chip_data gic_data[MAX_GIC_NR] __read_mostly;
 #ifdef CONFIG_GIC_NON_BANKED
 static void __iomem *gic_get_percpu_base(union gic_base *base)
 {
-	return *__this_cpu_ptr(base->percpu_base);
+	return raw_cpu_read(*base->percpu_base);
 }
 
 static void __iomem *gic_get_common_base(union gic_base *base)
@@ -270,8 +270,7 @@ static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 		irqnr = irqstat & GICC_IAR_INT_ID_MASK;
 
 		if (likely(irqnr > 15 && irqnr < 1021)) {
-			irqnr = irq_find_mapping(gic->domain, irqnr);
-			handle_IRQ(irqnr, regs);
+			handle_domain_irq(gic->domain, irqnr, regs);
 			continue;
 		}
 		if (irqnr < 16) {
@@ -298,8 +297,8 @@ static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
 	status = readl_relaxed(gic_data_cpu_base(chip_data) + GIC_CPU_INTACK);
 	raw_spin_unlock(&irq_controller_lock);
 
-	gic_irq = (status & 0x3ff);
-	if (gic_irq == 1023)
+	gic_irq = (status & GICC_IAR_INT_ID_MASK);
+	if (gic_irq == GICC_INT_SPURIOUS)
 		goto out;
 
 	cascade_irq = irq_find_mapping(chip_data->domain, gic_irq);
@@ -353,6 +352,21 @@ static u8 gic_get_cpumask(struct gic_chip_data *gic)
 	return mask;
 }
 
+static void gic_cpu_if_up(void)
+{
+	void __iomem *cpu_base = gic_data_cpu_base(&gic_data[0]);
+	u32 bypass = 0;
+
+	/*
+	* Preserve bypass disable bits to be written back later
+	*/
+	bypass = readl(cpu_base + GIC_CPU_CTRL);
+	bypass &= GICC_DIS_BYPASS_MASK;
+
+	writel_relaxed(bypass | GICC_ENABLE, cpu_base + GIC_CPU_CTRL);
+}
+
+
 static void __init gic_dist_init(struct gic_chip_data *gic)
 {
 	unsigned int i;
@@ -360,7 +374,7 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	unsigned int gic_irqs = gic->gic_irqs;
 	void __iomem *base = gic_data_dist_base(gic);
 
-	writel_relaxed(0, base + GIC_DIST_CTRL);
+	writel_relaxed(GICD_DISABLE, base + GIC_DIST_CTRL);
 
 	/*
 	 * Set all global interrupts to this CPU only.
@@ -373,7 +387,7 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 
 	gic_dist_config(base, gic_irqs, NULL);
 
-	writel_relaxed(1, base + GIC_DIST_CTRL);
+	writel_relaxed(GICD_ENABLE, base + GIC_DIST_CTRL);
 }
 
 static void gic_cpu_init(struct gic_chip_data *gic)
@@ -400,14 +414,18 @@ static void gic_cpu_init(struct gic_chip_data *gic)
 
 	gic_cpu_config(dist_base, NULL);
 
-	writel_relaxed(0xf0, base + GIC_CPU_PRIMASK);
-	writel_relaxed(1, base + GIC_CPU_CTRL);
+	writel_relaxed(GICC_INT_PRI_THRESHOLD, base + GIC_CPU_PRIMASK);
+	gic_cpu_if_up();
 }
 
 void gic_cpu_if_down(void)
 {
 	void __iomem *cpu_base = gic_data_cpu_base(&gic_data[0]);
-	writel_relaxed(0, cpu_base + GIC_CPU_CTRL);
+	u32 val = 0;
+
+	val = readl(cpu_base + GIC_CPU_CTRL);
+	val &= ~GICC_ENABLE;
+	writel_relaxed(val, cpu_base + GIC_CPU_CTRL);
 }
 
 #ifdef CONFIG_CPU_PM
@@ -467,14 +485,14 @@ static void gic_dist_restore(unsigned int gic_nr)
 	if (!dist_base)
 		return;
 
-	writel_relaxed(0, dist_base + GIC_DIST_CTRL);
+	writel_relaxed(GICD_DISABLE, dist_base + GIC_DIST_CTRL);
 
 	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++)
 		writel_relaxed(gic_data[gic_nr].saved_spi_conf[i],
 			dist_base + GIC_DIST_CONFIG + i * 4);
 
 	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
-		writel_relaxed(0xa0a0a0a0,
+		writel_relaxed(GICD_INT_DEF_PRI_X4,
 			dist_base + GIC_DIST_PRI + i * 4);
 
 	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++)
@@ -485,7 +503,7 @@ static void gic_dist_restore(unsigned int gic_nr)
 		writel_relaxed(gic_data[gic_nr].saved_spi_enable[i],
 			dist_base + GIC_DIST_ENABLE_SET + i * 4);
 
-	writel_relaxed(1, dist_base + GIC_DIST_CTRL);
+	writel_relaxed(GICD_ENABLE, dist_base + GIC_DIST_CTRL);
 }
 
 static void gic_cpu_save(unsigned int gic_nr)
@@ -504,11 +522,11 @@ static void gic_cpu_save(unsigned int gic_nr)
 	if (!dist_base || !cpu_base)
 		return;
 
-	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
 	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
 		ptr[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
 
-	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
 	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
 		ptr[i] = readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
 
@@ -530,19 +548,20 @@ static void gic_cpu_restore(unsigned int gic_nr)
 	if (!dist_base || !cpu_base)
 		return;
 
-	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
+	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
 	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
 		writel_relaxed(ptr[i], dist_base + GIC_DIST_ENABLE_SET + i * 4);
 
-	ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
+	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
 	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
 		writel_relaxed(ptr[i], dist_base + GIC_DIST_CONFIG + i * 4);
 
 	for (i = 0; i < DIV_ROUND_UP(32, 4); i++)
-		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4);
+		writel_relaxed(GICD_INT_DEF_PRI_X4,
+					dist_base + GIC_DIST_PRI + i * 4);
 
-	writel_relaxed(0xf0, cpu_base + GIC_CPU_PRIMASK);
-	writel_relaxed(1, cpu_base + GIC_CPU_CTRL);
+	writel_relaxed(GICC_INT_PRI_THRESHOLD, cpu_base + GIC_CPU_PRIMASK);
+	gic_cpu_if_up();
 }
 
 static int gic_notifier(struct notifier_block *self, unsigned long cmd,	void *v)
diff --git a/drivers/irqchip/irq-hip04.c b/drivers/irqchip/irq-hip04.c
new file mode 100644
index 000000000000..9c8f833522e6
--- /dev/null
+++ b/drivers/irqchip/irq-hip04.c
@@ -0,0 +1,424 @@
+/*
+ * Hisilicon HiP04 INTC
+ *
+ * Copyright (C) 2002-2014 ARM Limited.
+ * Copyright (c) 2013-2014 Hisilicon Ltd.
+ * Copyright (c) 2013-2014 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Interrupt architecture for the HIP04 INTC:
+ *
+ * o There is one Interrupt Distributor, which receives interrupts
+ *   from system devices and sends them to the Interrupt Controllers.
+ *
+ * o There is one CPU Interface per CPU, which sends interrupts sent
+ *   by the Distributor, and interrupts generated locally, to the
+ *   associated CPU. The base address of the CPU interface is usually
+ *   aliased so that the same address points to different chips depending
+ *   on the CPU it is accessed from.
+ *
+ * Note that IRQs 0-31 are special - they are local to each CPU.
+ * As such, the enable set/clear, pending set/clear and active bit
+ * registers are banked per-cpu for these sources.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/smp.h>
+#include <linux/cpu.h>
+#include <linux/cpu_pm.h>
+#include <linux/cpumask.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/irq.h>
+#include <asm/exception.h>
+#include <asm/smp_plat.h>
+
+#include "irq-gic-common.h"
+#include "irqchip.h"
+
+#define HIP04_MAX_IRQS		510
+
+struct hip04_irq_data {
+	void __iomem *dist_base;
+	void __iomem *cpu_base;
+	struct irq_domain *domain;
+	unsigned int nr_irqs;
+};
+
+static DEFINE_RAW_SPINLOCK(irq_controller_lock);
+
+/*
+ * The GIC mapping of CPU interfaces does not necessarily match
+ * the logical CPU numbering.  Let's use a mapping as returned
+ * by the GIC itself.
+ */
+#define NR_HIP04_CPU_IF 16
+static u16 hip04_cpu_map[NR_HIP04_CPU_IF] __read_mostly;
+
+static struct hip04_irq_data hip04_data __read_mostly;
+
+static inline void __iomem *hip04_dist_base(struct irq_data *d)
+{
+	struct hip04_irq_data *hip04_data = irq_data_get_irq_chip_data(d);
+	return hip04_data->dist_base;
+}
+
+static inline void __iomem *hip04_cpu_base(struct irq_data *d)
+{
+	struct hip04_irq_data *hip04_data = irq_data_get_irq_chip_data(d);
+	return hip04_data->cpu_base;
+}
+
+static inline unsigned int hip04_irq(struct irq_data *d)
+{
+	return d->hwirq;
+}
+
+/*
+ * Routines to acknowledge, disable and enable interrupts
+ */
+static void hip04_mask_irq(struct irq_data *d)
+{
+	u32 mask = 1 << (hip04_irq(d) % 32);
+
+	raw_spin_lock(&irq_controller_lock);
+	writel_relaxed(mask, hip04_dist_base(d) + GIC_DIST_ENABLE_CLEAR +
+		       (hip04_irq(d) / 32) * 4);
+	raw_spin_unlock(&irq_controller_lock);
+}
+
+static void hip04_unmask_irq(struct irq_data *d)
+{
+	u32 mask = 1 << (hip04_irq(d) % 32);
+
+	raw_spin_lock(&irq_controller_lock);
+	writel_relaxed(mask, hip04_dist_base(d) + GIC_DIST_ENABLE_SET +
+		       (hip04_irq(d) / 32) * 4);
+	raw_spin_unlock(&irq_controller_lock);
+}
+
+static void hip04_eoi_irq(struct irq_data *d)
+{
+	writel_relaxed(hip04_irq(d), hip04_cpu_base(d) + GIC_CPU_EOI);
+}
+
+static int hip04_irq_set_type(struct irq_data *d, unsigned int type)
+{
+	void __iomem *base = hip04_dist_base(d);
+	unsigned int irq = hip04_irq(d);
+
+	/* Interrupt configuration for SGIs can't be changed */
+	if (irq < 16)
+		return -EINVAL;
+
+	if (type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
+		return -EINVAL;
+
+	raw_spin_lock(&irq_controller_lock);
+
+	gic_configure_irq(irq, type, base, NULL);
+
+	raw_spin_unlock(&irq_controller_lock);
+
+	return 0;
+}
+
+#ifdef CONFIG_SMP
+static int hip04_irq_set_affinity(struct irq_data *d,
+				  const struct cpumask *mask_val,
+				  bool force)
+{
+	void __iomem *reg;
+	unsigned int cpu, shift = (hip04_irq(d) % 2) * 16;
+	u32 val, mask, bit;
+
+	if (!force)
+		cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	else
+		cpu = cpumask_first(mask_val);
+
+	if (cpu >= NR_HIP04_CPU_IF || cpu >= nr_cpu_ids)
+		return -EINVAL;
+
+	raw_spin_lock(&irq_controller_lock);
+	reg = hip04_dist_base(d) + GIC_DIST_TARGET + ((hip04_irq(d) * 2) & ~3);
+	mask = 0xffff << shift;
+	bit = hip04_cpu_map[cpu] << shift;
+	val = readl_relaxed(reg) & ~mask;
+	writel_relaxed(val | bit, reg);
+	raw_spin_unlock(&irq_controller_lock);
+
+	return IRQ_SET_MASK_OK;
+}
+#endif
+
+static void __exception_irq_entry hip04_handle_irq(struct pt_regs *regs)
+{
+	u32 irqstat, irqnr;
+	void __iomem *cpu_base = hip04_data.cpu_base;
+
+	do {
+		irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
+		irqnr = irqstat & GICC_IAR_INT_ID_MASK;
+
+		if (likely(irqnr > 15 && irqnr <= HIP04_MAX_IRQS)) {
+			irqnr = irq_find_mapping(hip04_data.domain, irqnr);
+			handle_IRQ(irqnr, regs);
+			continue;
+		}
+		if (irqnr < 16) {
+			writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
+#ifdef CONFIG_SMP
+			handle_IPI(irqnr, regs);
+#endif
+			continue;
+		}
+		break;
+	} while (1);
+}
+
+static struct irq_chip hip04_irq_chip = {
+	.name			= "HIP04 INTC",
+	.irq_mask		= hip04_mask_irq,
+	.irq_unmask		= hip04_unmask_irq,
+	.irq_eoi		= hip04_eoi_irq,
+	.irq_set_type		= hip04_irq_set_type,
+#ifdef CONFIG_SMP
+	.irq_set_affinity	= hip04_irq_set_affinity,
+#endif
+};
+
+static u16 hip04_get_cpumask(struct hip04_irq_data *intc)
+{
+	void __iomem *base = intc->dist_base;
+	u32 mask, i;
+
+	for (i = mask = 0; i < 32; i += 2) {
+		mask = readl_relaxed(base + GIC_DIST_TARGET + i * 2);
+		mask |= mask >> 16;
+		if (mask)
+			break;
+	}
+
+	if (!mask)
+		pr_crit("GIC CPU mask not found - kernel will fail to boot.\n");
+
+	return mask;
+}
+
+static void __init hip04_irq_dist_init(struct hip04_irq_data *intc)
+{
+	unsigned int i;
+	u32 cpumask;
+	unsigned int nr_irqs = intc->nr_irqs;
+	void __iomem *base = intc->dist_base;
+
+	writel_relaxed(0, base + GIC_DIST_CTRL);
+
+	/*
+	 * Set all global interrupts to this CPU only.
+	 */
+	cpumask = hip04_get_cpumask(intc);
+	cpumask |= cpumask << 16;
+	for (i = 32; i < nr_irqs; i += 2)
+		writel_relaxed(cpumask, base + GIC_DIST_TARGET + ((i * 2) & ~3));
+
+	gic_dist_config(base, nr_irqs, NULL);
+
+	writel_relaxed(1, base + GIC_DIST_CTRL);
+}
+
+static void hip04_irq_cpu_init(struct hip04_irq_data *intc)
+{
+	void __iomem *dist_base = intc->dist_base;
+	void __iomem *base = intc->cpu_base;
+	unsigned int cpu_mask, cpu = smp_processor_id();
+	int i;
+
+	/*
+	 * Get what the GIC says our CPU mask is.
+	 */
+	BUG_ON(cpu >= NR_HIP04_CPU_IF);
+	cpu_mask = hip04_get_cpumask(intc);
+	hip04_cpu_map[cpu] = cpu_mask;
+
+	/*
+	 * Clear our mask from the other map entries in case they're
+	 * still undefined.
+	 */
+	for (i = 0; i < NR_HIP04_CPU_IF; i++)
+		if (i != cpu)
+			hip04_cpu_map[i] &= ~cpu_mask;
+
+	gic_cpu_config(dist_base, NULL);
+
+	writel_relaxed(0xf0, base + GIC_CPU_PRIMASK);
+	writel_relaxed(1, base + GIC_CPU_CTRL);
+}
+
+#ifdef CONFIG_SMP
+static void hip04_raise_softirq(const struct cpumask *mask, unsigned int irq)
+{
+	int cpu;
+	unsigned long flags, map = 0;
+
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= hip04_cpu_map[cpu];
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before they observe us issuing the IPI.
+	 */
+	dmb(ishst);
+
+	/* this always happens on GIC0 */
+	writel_relaxed(map << 8 | irq, hip04_data.dist_base + GIC_DIST_SOFTINT);
+
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
+}
+#endif
+
+static int hip04_irq_domain_map(struct irq_domain *d, unsigned int irq,
+				irq_hw_number_t hw)
+{
+	if (hw < 32) {
+		irq_set_percpu_devid(irq);
+		irq_set_chip_and_handler(irq, &hip04_irq_chip,
+					 handle_percpu_devid_irq);
+		set_irq_flags(irq, IRQF_VALID | IRQF_NOAUTOEN);
+	} else {
+		irq_set_chip_and_handler(irq, &hip04_irq_chip,
+					 handle_fasteoi_irq);
+		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+	}
+	irq_set_chip_data(irq, d->host_data);
+	return 0;
+}
+
+static int hip04_irq_domain_xlate(struct irq_domain *d,
+				  struct device_node *controller,
+				  const u32 *intspec, unsigned int intsize,
+				  unsigned long *out_hwirq,
+				  unsigned int *out_type)
+{
+	unsigned long ret = 0;
+
+	if (d->of_node != controller)
+		return -EINVAL;
+	if (intsize < 3)
+		return -EINVAL;
+
+	/* Get the interrupt number and add 16 to skip over SGIs */
+	*out_hwirq = intspec[1] + 16;
+
+	/* For SPIs, we need to add 16 more to get the irq ID number */
+	if (!intspec[0])
+		*out_hwirq += 16;
+
+	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
+
+	return ret;
+}
+
+#ifdef CONFIG_SMP
+static int hip04_irq_secondary_init(struct notifier_block *nfb,
+				    unsigned long action,
+				    void *hcpu)
+{
+	if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
+		hip04_irq_cpu_init(&hip04_data);
+	return NOTIFY_OK;
+}
+
+/*
+ * Notifier for enabling the INTC CPU interface. Set an arbitrarily high
+ * priority because the GIC needs to be up before the ARM generic timers.
+ */
+static struct notifier_block hip04_irq_cpu_notifier = {
+	.notifier_call	= hip04_irq_secondary_init,
+	.priority	= 100,
+};
+#endif
+
+static const struct irq_domain_ops hip04_irq_domain_ops = {
+	.map	= hip04_irq_domain_map,
+	.xlate	= hip04_irq_domain_xlate,
+};
+
+static int __init
+hip04_of_init(struct device_node *node, struct device_node *parent)
+{
+	irq_hw_number_t hwirq_base = 16;
+	int nr_irqs, irq_base, i;
+
+	if (WARN_ON(!node))
+		return -ENODEV;
+
+	hip04_data.dist_base = of_iomap(node, 0);
+	WARN(!hip04_data.dist_base, "fail to map hip04 intc dist registers\n");
+
+	hip04_data.cpu_base = of_iomap(node, 1);
+	WARN(!hip04_data.cpu_base, "unable to map hip04 intc cpu registers\n");
+
+	/*
+	 * Initialize the CPU interface map to all CPUs.
+	 * It will be refined as each CPU probes its ID.
+	 */
+	for (i = 0; i < NR_HIP04_CPU_IF; i++)
+		hip04_cpu_map[i] = 0xff;
+
+	/*
+	 * Find out how many interrupts are supported.
+	 * The HIP04 INTC only supports up to 510 interrupt sources.
+	 */
+	nr_irqs = readl_relaxed(hip04_data.dist_base + GIC_DIST_CTR) & 0x1f;
+	nr_irqs = (nr_irqs + 1) * 32;
+	if (nr_irqs > HIP04_MAX_IRQS)
+		nr_irqs = HIP04_MAX_IRQS;
+	hip04_data.nr_irqs = nr_irqs;
+
+	nr_irqs -= hwirq_base; /* calculate # of irqs to allocate */
+
+	irq_base = irq_alloc_descs(-1, hwirq_base, nr_irqs, numa_node_id());
+	if (IS_ERR_VALUE(irq_base)) {
+		pr_err("failed to allocate IRQ numbers\n");
+		return -EINVAL;
+	}
+
+	hip04_data.domain = irq_domain_add_legacy(node, nr_irqs, irq_base,
+						  hwirq_base,
+						  &hip04_irq_domain_ops,
+						  &hip04_data);
+
+	if (WARN_ON(!hip04_data.domain))
+		return -EINVAL;
+
+#ifdef CONFIG_SMP
+	set_smp_cross_call(hip04_raise_softirq);
+	register_cpu_notifier(&hip04_irq_cpu_notifier);
+#endif
+	set_handle_irq(hip04_handle_irq);
+
+	hip04_irq_dist_init(&hip04_data);
+	hip04_irq_cpu_init(&hip04_data);
+
+	return 0;
+}
+IRQCHIP_DECLARE(hip04_intc, "hisilicon,hip04-intc", hip04_of_init);
diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c
new file mode 100644
index 000000000000..608abf9c9283
--- /dev/null
+++ b/drivers/irqchip/irq-keystone.c
@@ -0,0 +1,232 @@
+/*
+ * Texas Instruments Keystone IRQ controller IP driver
+ *
+ * Copyright (C) 2014 Texas Instruments, Inc.
+ * Author: Sajesh Kumar Saran <sajesh@ti.com>
+ *	   Grygorii Strashko <grygorii.strashko@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/irq.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include "irqchip.h"
+
+
+/* The source ID bits start from 4 to 31 (total 28 bits)*/
+#define BIT_OFS			4
+#define KEYSTONE_N_IRQ		(32 - BIT_OFS)
+
+struct keystone_irq_device {
+	struct device		*dev;
+	struct irq_chip		 chip;
+	u32			 mask;
+	int			 irq;
+	struct irq_domain	*irqd;
+	struct regmap		*devctrl_regs;
+	u32			devctrl_offset;
+};
+
+static inline u32 keystone_irq_readl(struct keystone_irq_device *kirq)
+{
+	int ret;
+	u32 val = 0;
+
+	ret = regmap_read(kirq->devctrl_regs, kirq->devctrl_offset, &val);
+	if (ret < 0)
+		dev_dbg(kirq->dev, "irq read failed ret(%d)\n", ret);
+	return val;
+}
+
+static inline void
+keystone_irq_writel(struct keystone_irq_device *kirq, u32 value)
+{
+	int ret;
+
+	ret = regmap_write(kirq->devctrl_regs, kirq->devctrl_offset, value);
+	if (ret < 0)
+		dev_dbg(kirq->dev, "irq write failed ret(%d)\n", ret);
+}
+
+static void keystone_irq_setmask(struct irq_data *d)
+{
+	struct keystone_irq_device *kirq = irq_data_get_irq_chip_data(d);
+
+	kirq->mask |= BIT(d->hwirq);
+	dev_dbg(kirq->dev, "mask %lu [%x]\n", d->hwirq, kirq->mask);
+}
+
+static void keystone_irq_unmask(struct irq_data *d)
+{
+	struct keystone_irq_device *kirq = irq_data_get_irq_chip_data(d);
+
+	kirq->mask &= ~BIT(d->hwirq);
+	dev_dbg(kirq->dev, "unmask %lu [%x]\n", d->hwirq, kirq->mask);
+}
+
+static void keystone_irq_ack(struct irq_data *d)
+{
+	/* nothing to do here */
+}
+
+static void keystone_irq_handler(unsigned irq, struct irq_desc *desc)
+{
+	struct keystone_irq_device *kirq = irq_desc_get_handler_data(desc);
+	unsigned long pending;
+	int src, virq;
+
+	dev_dbg(kirq->dev, "start irq %d\n", irq);
+
+	chained_irq_enter(irq_desc_get_chip(desc), desc);
+
+	pending = keystone_irq_readl(kirq);
+	keystone_irq_writel(kirq, pending);
+
+	dev_dbg(kirq->dev, "pending 0x%lx, mask 0x%x\n", pending, kirq->mask);
+
+	pending = (pending >> BIT_OFS) & ~kirq->mask;
+
+	dev_dbg(kirq->dev, "pending after mask 0x%lx\n", pending);
+
+	for (src = 0; src < KEYSTONE_N_IRQ; src++) {
+		if (BIT(src) & pending) {
+			virq = irq_find_mapping(kirq->irqd, src);
+			dev_dbg(kirq->dev, "dispatch bit %d, virq %d\n",
+				src, virq);
+			if (!virq)
+				dev_warn(kirq->dev, "sporious irq detected hwirq %d, virq %d\n",
+					 src, virq);
+			generic_handle_irq(virq);
+		}
+	}
+
+	chained_irq_exit(irq_desc_get_chip(desc), desc);
+
+	dev_dbg(kirq->dev, "end irq %d\n", irq);
+}
+
+static int keystone_irq_map(struct irq_domain *h, unsigned int virq,
+				irq_hw_number_t hw)
+{
+	struct keystone_irq_device *kirq = h->host_data;
+
+	irq_set_chip_data(virq, kirq);
+	irq_set_chip_and_handler(virq, &kirq->chip, handle_level_irq);
+	set_irq_flags(virq, IRQF_VALID | IRQF_PROBE);
+	return 0;
+}
+
+static struct irq_domain_ops keystone_irq_ops = {
+	.map	= keystone_irq_map,
+	.xlate	= irq_domain_xlate_onecell,
+};
+
+static int keystone_irq_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct keystone_irq_device *kirq;
+	int ret;
+
+	if (np == NULL)
+		return -EINVAL;
+
+	kirq = devm_kzalloc(dev, sizeof(*kirq), GFP_KERNEL);
+	if (!kirq)
+		return -ENOMEM;
+
+	kirq->devctrl_regs =
+		syscon_regmap_lookup_by_phandle(np, "ti,syscon-dev");
+	if (IS_ERR(kirq->devctrl_regs))
+		return PTR_ERR(kirq->devctrl_regs);
+
+	ret = of_property_read_u32_index(np, "ti,syscon-dev", 1,
+					 &kirq->devctrl_offset);
+	if (ret) {
+		dev_err(dev, "couldn't read the devctrl_offset offset!\n");
+		return ret;
+	}
+
+	kirq->irq = platform_get_irq(pdev, 0);
+	if (kirq->irq < 0) {
+		dev_err(dev, "no irq resource %d\n", kirq->irq);
+		return kirq->irq;
+	}
+
+	kirq->dev = dev;
+	kirq->mask = ~0x0;
+	kirq->chip.name		= "keystone-irq";
+	kirq->chip.irq_ack	= keystone_irq_ack;
+	kirq->chip.irq_mask	= keystone_irq_setmask;
+	kirq->chip.irq_unmask	= keystone_irq_unmask;
+
+	kirq->irqd = irq_domain_add_linear(np, KEYSTONE_N_IRQ,
+					   &keystone_irq_ops, kirq);
+	if (!kirq->irqd) {
+		dev_err(dev, "IRQ domain registration failed\n");
+		return -ENODEV;
+	}
+
+	platform_set_drvdata(pdev, kirq);
+
+	irq_set_chained_handler(kirq->irq, keystone_irq_handler);
+	irq_set_handler_data(kirq->irq, kirq);
+
+	/* clear all source bits */
+	keystone_irq_writel(kirq, ~0x0);
+
+	dev_info(dev, "irqchip registered, nr_irqs %u\n", KEYSTONE_N_IRQ);
+
+	return 0;
+}
+
+static int keystone_irq_remove(struct platform_device *pdev)
+{
+	struct keystone_irq_device *kirq = platform_get_drvdata(pdev);
+	int hwirq;
+
+	for (hwirq = 0; hwirq < KEYSTONE_N_IRQ; hwirq++)
+		irq_dispose_mapping(irq_find_mapping(kirq->irqd, hwirq));
+
+	irq_domain_remove(kirq->irqd);
+	return 0;
+}
+
+static const struct of_device_id keystone_irq_dt_ids[] = {
+	{ .compatible = "ti,keystone-irq", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, keystone_irq_dt_ids);
+
+static struct platform_driver keystone_irq_device_driver = {
+	.probe		= keystone_irq_probe,
+	.remove		= keystone_irq_remove,
+	.driver		= {
+		.name	= "keystone_irq",
+		.owner	= THIS_MODULE,
+		.of_match_table	= of_match_ptr(keystone_irq_dt_ids),
+	}
+};
+
+module_platform_driver(keystone_irq_device_driver);
+
+MODULE_AUTHOR("Texas Instruments");
+MODULE_AUTHOR("Sajesh Kumar Saran");
+MODULE_AUTHOR("Grygorii Strashko");
+MODULE_DESCRIPTION("Keystone IRQ chip");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c
index 1c3e2c9b46ba..c0da57bdb89d 100644
--- a/drivers/irqchip/irq-mmp.c
+++ b/drivers/irqchip/irq-mmp.c
@@ -196,26 +196,24 @@ static struct mmp_intc_conf mmp2_conf = {
 
 static void __exception_irq_entry mmp_handle_irq(struct pt_regs *regs)
 {
-	int irq, hwirq;
+	int hwirq;
 
 	hwirq = readl_relaxed(mmp_icu_base + PJ1_INT_SEL);
 	if (!(hwirq & SEL_INT_PENDING))
 		return;
 	hwirq &= SEL_INT_NUM_MASK;
-	irq = irq_find_mapping(icu_data[0].domain, hwirq);
-	handle_IRQ(irq, regs);
+	handle_domain_irq(icu_data[0].domain, hwirq, regs);
 }
 
 static void __exception_irq_entry mmp2_handle_irq(struct pt_regs *regs)
 {
-	int irq, hwirq;
+	int hwirq;
 
 	hwirq = readl_relaxed(mmp_icu_base + PJ4_INT_SEL);
 	if (!(hwirq & SEL_INT_PENDING))
 		return;
 	hwirq &= SEL_INT_NUM_MASK;
-	irq = irq_find_mapping(icu_data[0].domain, hwirq);
-	handle_IRQ(irq, regs);
+	handle_domain_irq(icu_data[0].domain, hwirq, regs);
 }
 
 /* MMP (ARMv5) */
diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c
index 4044ff287663..e4acf1e3f8e3 100644
--- a/drivers/irqchip/irq-mxs.c
+++ b/drivers/irqchip/irq-mxs.c
@@ -78,8 +78,7 @@ asmlinkage void __exception_irq_entry icoll_handle_irq(struct pt_regs *regs)
 
 	irqnr = __raw_readl(icoll_base + HW_ICOLL_STAT_OFFSET);
 	__raw_writel(irqnr, icoll_base + HW_ICOLL_VECTOR);
-	irqnr = irq_find_mapping(icoll_domain, irqnr);
-	handle_IRQ(irqnr, regs);
+	handle_domain_irq(icoll_domain, irqnr, regs);
 }
 
 static int icoll_irq_domain_map(struct irq_domain *d, unsigned int virq,
diff --git a/drivers/irqchip/irq-omap-intc.c b/drivers/irqchip/irq-omap-intc.c
index f3814e79192d..28718d3e8281 100644
--- a/drivers/irqchip/irq-omap-intc.c
+++ b/drivers/irqchip/irq-omap-intc.c
@@ -334,8 +334,7 @@ out:
 		irqnr &= ACTIVEIRQ_MASK;
 
 		if (irqnr) {
-			irqnr = irq_find_mapping(domain, irqnr);
-			handle_IRQ(irqnr, regs);
+			handle_domain_irq(domain, irqnr, regs);
 			handled_irq = 1;
 		}
 	} while (irqnr);
diff --git a/drivers/irqchip/irq-or1k-pic.c b/drivers/irqchip/irq-or1k-pic.c
index 17ff033d9925..e93d079fe069 100644
--- a/drivers/irqchip/irq-or1k-pic.c
+++ b/drivers/irqchip/irq-or1k-pic.c
@@ -113,7 +113,7 @@ static inline int pic_get_irq(int first)
 	else
 		hwirq = hwirq + first - 1;
 
-	return irq_find_mapping(root_domain, hwirq);
+	return hwirq;
 }
 
 static void or1k_pic_handle_irq(struct pt_regs *regs)
@@ -121,7 +121,7 @@ static void or1k_pic_handle_irq(struct pt_regs *regs)
 	int irq = -1;
 
 	while ((irq = pic_get_irq(irq + 1)) != NO_IRQ)
-		handle_IRQ(irq, regs);
+		handle_domain_irq(root_domain, irq, regs);
 }
 
 static int or1k_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
diff --git a/drivers/irqchip/irq-orion.c b/drivers/irqchip/irq-orion.c
index 34d18b48bb78..ad0c0f6f1d65 100644
--- a/drivers/irqchip/irq-orion.c
+++ b/drivers/irqchip/irq-orion.c
@@ -43,9 +43,8 @@ __exception_irq_entry orion_handle_irq(struct pt_regs *regs)
 			gc->mask_cache;
 		while (stat) {
 			u32 hwirq = __fls(stat);
-			u32 irq = irq_find_mapping(orion_irq_domain,
-						   gc->irq_base + hwirq);
-			handle_IRQ(irq, regs);
+			handle_domain_irq(orion_irq_domain,
+					  gc->irq_base + hwirq, regs);
 			stat &= ~(1 << hwirq);
 		}
 	}
diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c
index 3ee78f02e5d7..542e850f4946 100644
--- a/drivers/irqchip/irq-renesas-intc-irqpin.c
+++ b/drivers/irqchip/irq-renesas-intc-irqpin.c
@@ -17,6 +17,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/clk.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
@@ -30,6 +31,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/platform_data/irq-renesas-intc-irqpin.h>
+#include <linux/pm_runtime.h>
 
 #define INTC_IRQPIN_MAX 8 /* maximum 8 interrupts per driver instance */
 
@@ -75,6 +77,7 @@ struct intc_irqpin_priv {
 	struct platform_device *pdev;
 	struct irq_chip irq_chip;
 	struct irq_domain *irq_domain;
+	struct clk *clk;
 	bool shared_irqs;
 	u8 shared_irq_mask;
 };
@@ -270,6 +273,21 @@ static int intc_irqpin_irq_set_type(struct irq_data *d, unsigned int type)
 				     value ^ INTC_IRQ_SENSE_VALID);
 }
 
+static int intc_irqpin_irq_set_wake(struct irq_data *d, unsigned int on)
+{
+	struct intc_irqpin_priv *p = irq_data_get_irq_chip_data(d);
+
+	if (!p->clk)
+		return 0;
+
+	if (on)
+		clk_enable(p->clk);
+	else
+		clk_disable(p->clk);
+
+	return 0;
+}
+
 static irqreturn_t intc_irqpin_irq_handler(int irq, void *dev_id)
 {
 	struct intc_irqpin_irq *i = dev_id;
@@ -329,7 +347,8 @@ static struct irq_domain_ops intc_irqpin_irq_domain_ops = {
 
 static int intc_irqpin_probe(struct platform_device *pdev)
 {
-	struct renesas_intc_irqpin_config *pdata = pdev->dev.platform_data;
+	struct device *dev = &pdev->dev;
+	struct renesas_intc_irqpin_config *pdata = dev->platform_data;
 	struct intc_irqpin_priv *p;
 	struct intc_irqpin_iomem *i;
 	struct resource *io[INTC_IRQPIN_REG_NR];
@@ -337,25 +356,24 @@ static int intc_irqpin_probe(struct platform_device *pdev)
 	struct irq_chip *irq_chip;
 	void (*enable_fn)(struct irq_data *d);
 	void (*disable_fn)(struct irq_data *d);
-	const char *name = dev_name(&pdev->dev);
+	const char *name = dev_name(dev);
 	int ref_irq;
 	int ret;
 	int k;
 
-	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
+	p = devm_kzalloc(dev, sizeof(*p), GFP_KERNEL);
 	if (!p) {
-		dev_err(&pdev->dev, "failed to allocate driver data\n");
-		ret = -ENOMEM;
-		goto err0;
+		dev_err(dev, "failed to allocate driver data\n");
+		return -ENOMEM;
 	}
 
 	/* deal with driver instance configuration */
 	if (pdata) {
 		memcpy(&p->config, pdata, sizeof(*pdata));
 	} else {
-		of_property_read_u32(pdev->dev.of_node, "sense-bitfield-width",
+		of_property_read_u32(dev->of_node, "sense-bitfield-width",
 				     &p->config.sense_bitfield_width);
-		p->config.control_parent = of_property_read_bool(pdev->dev.of_node,
+		p->config.control_parent = of_property_read_bool(dev->of_node,
 								 "control-parent");
 	}
 	if (!p->config.sense_bitfield_width)
@@ -364,11 +382,20 @@ static int intc_irqpin_probe(struct platform_device *pdev)
 	p->pdev = pdev;
 	platform_set_drvdata(pdev, p);
 
+	p->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(p->clk)) {
+		dev_warn(dev, "unable to get clock\n");
+		p->clk = NULL;
+	}
+
+	pm_runtime_enable(dev);
+	pm_runtime_get_sync(dev);
+
 	/* get hold of manadatory IOMEM */
 	for (k = 0; k < INTC_IRQPIN_REG_NR; k++) {
 		io[k] = platform_get_resource(pdev, IORESOURCE_MEM, k);
 		if (!io[k]) {
-			dev_err(&pdev->dev, "not enough IOMEM resources\n");
+			dev_err(dev, "not enough IOMEM resources\n");
 			ret = -EINVAL;
 			goto err0;
 		}
@@ -386,7 +413,7 @@ static int intc_irqpin_probe(struct platform_device *pdev)
 
 	p->number_of_irqs = k;
 	if (p->number_of_irqs < 1) {
-		dev_err(&pdev->dev, "not enough IRQ resources\n");
+		dev_err(dev, "not enough IRQ resources\n");
 		ret = -EINVAL;
 		goto err0;
 	}
@@ -407,15 +434,15 @@ static int intc_irqpin_probe(struct platform_device *pdev)
 			i->write = intc_irqpin_write32;
 			break;
 		default:
-			dev_err(&pdev->dev, "IOMEM size mismatch\n");
+			dev_err(dev, "IOMEM size mismatch\n");
 			ret = -EINVAL;
 			goto err0;
 		}
 
-		i->iomem = devm_ioremap_nocache(&pdev->dev, io[k]->start,
+		i->iomem = devm_ioremap_nocache(dev, io[k]->start,
 						resource_size(io[k]));
 		if (!i->iomem) {
-			dev_err(&pdev->dev, "failed to remap IOMEM\n");
+			dev_err(dev, "failed to remap IOMEM\n");
 			ret = -ENXIO;
 			goto err0;
 		}
@@ -454,39 +481,36 @@ static int intc_irqpin_probe(struct platform_device *pdev)
 	irq_chip->name = name;
 	irq_chip->irq_mask = disable_fn;
 	irq_chip->irq_unmask = enable_fn;
-	irq_chip->irq_enable = enable_fn;
-	irq_chip->irq_disable = disable_fn;
 	irq_chip->irq_set_type = intc_irqpin_irq_set_type;
-	irq_chip->flags	= IRQCHIP_SKIP_SET_WAKE;
+	irq_chip->irq_set_wake = intc_irqpin_irq_set_wake;
+	irq_chip->flags	= IRQCHIP_MASK_ON_SUSPEND;
 
-	p->irq_domain = irq_domain_add_simple(pdev->dev.of_node,
+	p->irq_domain = irq_domain_add_simple(dev->of_node,
 					      p->number_of_irqs,
 					      p->config.irq_base,
 					      &intc_irqpin_irq_domain_ops, p);
 	if (!p->irq_domain) {
 		ret = -ENXIO;
-		dev_err(&pdev->dev, "cannot initialize irq domain\n");
+		dev_err(dev, "cannot initialize irq domain\n");
 		goto err0;
 	}
 
 	if (p->shared_irqs) {
 		/* request one shared interrupt */
-		if (devm_request_irq(&pdev->dev, p->irq[0].requested_irq,
+		if (devm_request_irq(dev, p->irq[0].requested_irq,
 				intc_irqpin_shared_irq_handler,
 				IRQF_SHARED, name, p)) {
-			dev_err(&pdev->dev, "failed to request low IRQ\n");
+			dev_err(dev, "failed to request low IRQ\n");
 			ret = -ENOENT;
 			goto err1;
 		}
 	} else {
 		/* request interrupts one by one */
 		for (k = 0; k < p->number_of_irqs; k++) {
-			if (devm_request_irq(&pdev->dev,
-					p->irq[k].requested_irq,
-					intc_irqpin_irq_handler,
-					0, name, &p->irq[k])) {
-				dev_err(&pdev->dev,
-					"failed to request low IRQ\n");
+			if (devm_request_irq(dev, p->irq[k].requested_irq,
+					     intc_irqpin_irq_handler, 0, name,
+					     &p->irq[k])) {
+				dev_err(dev, "failed to request low IRQ\n");
 				ret = -ENOENT;
 				goto err1;
 			}
@@ -497,12 +521,12 @@ static int intc_irqpin_probe(struct platform_device *pdev)
 	for (k = 0; k < p->number_of_irqs; k++)
 		intc_irqpin_mask_unmask_prio(p, k, 0);
 
-	dev_info(&pdev->dev, "driving %d irqs\n", p->number_of_irqs);
+	dev_info(dev, "driving %d irqs\n", p->number_of_irqs);
 
 	/* warn in case of mismatch if irq base is specified */
 	if (p->config.irq_base) {
 		if (p->config.irq_base != p->irq[0].domain_irq)
-			dev_warn(&pdev->dev, "irq base mismatch (%d/%d)\n",
+			dev_warn(dev, "irq base mismatch (%d/%d)\n",
 				 p->config.irq_base, p->irq[0].domain_irq);
 	}
 
@@ -511,6 +535,8 @@ static int intc_irqpin_probe(struct platform_device *pdev)
 err1:
 	irq_domain_remove(p->irq_domain);
 err0:
+	pm_runtime_put(dev);
+	pm_runtime_disable(dev);
 	return ret;
 }
 
@@ -519,7 +545,8 @@ static int intc_irqpin_remove(struct platform_device *pdev)
 	struct intc_irqpin_priv *p = platform_get_drvdata(pdev);
 
 	irq_domain_remove(p->irq_domain);
-
+	pm_runtime_put(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-s3c24xx.c b/drivers/irqchip/irq-s3c24xx.c
index 78a6accd205f..c8d373fcd823 100644
--- a/drivers/irqchip/irq-s3c24xx.c
+++ b/drivers/irqchip/irq-s3c24xx.c
@@ -339,7 +339,6 @@ static inline int s3c24xx_handle_intc(struct s3c_irq_intc *intc,
 {
 	int pnd;
 	int offset;
-	int irq;
 
 	pnd = __raw_readl(intc->reg_intpnd);
 	if (!pnd)
@@ -365,8 +364,7 @@ static inline int s3c24xx_handle_intc(struct s3c_irq_intc *intc,
 	if (!(pnd & (1 << offset)))
 		offset =  __ffs(pnd);
 
-	irq = irq_find_mapping(intc->domain, intc_offset + offset);
-	handle_IRQ(irq, regs);
+	handle_domain_irq(intc->domain, intc_offset + offset, regs);
 	return true;
 }
 
diff --git a/drivers/irqchip/irq-sirfsoc.c b/drivers/irqchip/irq-sirfsoc.c
index 5e54f6d71e77..a469355df352 100644
--- a/drivers/irqchip/irq-sirfsoc.c
+++ b/drivers/irqchip/irq-sirfsoc.c
@@ -50,12 +50,10 @@ sirfsoc_alloc_gc(void __iomem *base, unsigned int irq_start, unsigned int num)
 static void __exception_irq_entry sirfsoc_handle_irq(struct pt_regs *regs)
 {
 	void __iomem *base = sirfsoc_irqdomain->host_data;
-	u32 irqstat, irqnr;
+	u32 irqstat;
 
 	irqstat = readl_relaxed(base + SIRFSOC_INIT_IRQ_ID);
-	irqnr = irq_find_mapping(sirfsoc_irqdomain, irqstat & 0xff);
-
-	handle_IRQ(irqnr, regs);
+	handle_domain_irq(sirfsoc_irqdomain, irqstat & 0xff, regs);
 }
 
 static int __init sirfsoc_irq_init(struct device_node *np,
diff --git a/drivers/irqchip/irq-sun4i.c b/drivers/irqchip/irq-sun4i.c
index 6fcef4a95a18..64155b686081 100644
--- a/drivers/irqchip/irq-sun4i.c
+++ b/drivers/irqchip/irq-sun4i.c
@@ -136,7 +136,7 @@ IRQCHIP_DECLARE(allwinner_sun4i_ic, "allwinner,sun4i-a10-ic", sun4i_of_init);
 
 static void __exception_irq_entry sun4i_handle_irq(struct pt_regs *regs)
 {
-	u32 irq, hwirq;
+	u32 hwirq;
 
 	/*
 	 * hwirq == 0 can mean one of 3 things:
@@ -154,8 +154,7 @@ static void __exception_irq_entry sun4i_handle_irq(struct pt_regs *regs)
 		return;
 
 	do {
-		irq = irq_find_mapping(sun4i_irq_domain, hwirq);
-		handle_IRQ(irq, regs);
+		handle_domain_irq(sun4i_irq_domain, hwirq, regs);
 		hwirq = readl(sun4i_irq_base + SUN4I_IRQ_VECTOR_REG) >> 2;
 	} while (hwirq != 0);
 }
diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c
index ccf58548b161..1ab451729a5c 100644
--- a/drivers/irqchip/irq-versatile-fpga.c
+++ b/drivers/irqchip/irq-versatile-fpga.c
@@ -96,7 +96,7 @@ static int handle_one_fpga(struct fpga_irq_data *f, struct pt_regs *regs)
 
 	while ((status  = readl(f->base + IRQ_STATUS))) {
 		irq = ffs(status) - 1;
-		handle_IRQ(irq_find_mapping(f->domain, irq), regs);
+		handle_domain_irq(f->domain, irq, regs);
 		handled = 1;
 	}
 
diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c
index 7d35287f9e90..54089debf2dc 100644
--- a/drivers/irqchip/irq-vic.c
+++ b/drivers/irqchip/irq-vic.c
@@ -219,7 +219,7 @@ static int handle_one_vic(struct vic_device *vic, struct pt_regs *regs)
 
 	while ((stat = readl_relaxed(vic->base + VIC_IRQ_STATUS))) {
 		irq = ffs(stat) - 1;
-		handle_IRQ(irq_find_mapping(vic->domain, irq), regs);
+		handle_domain_irq(vic->domain, irq, regs);
 		handled = 1;
 	}
 
diff --git a/drivers/irqchip/irq-vt8500.c b/drivers/irqchip/irq-vt8500.c
index eb6e91efdec8..b7af816f2769 100644
--- a/drivers/irqchip/irq-vt8500.c
+++ b/drivers/irqchip/irq-vt8500.c
@@ -181,7 +181,7 @@ static struct irq_domain_ops vt8500_irq_domain_ops = {
 static void __exception_irq_entry vt8500_handle_irq(struct pt_regs *regs)
 {
 	u32 stat, i;
-	int irqnr, virq;
+	int irqnr;
 	void __iomem *base;
 
 	/* Loop through each active controller */
@@ -198,8 +198,7 @@ static void __exception_irq_entry vt8500_handle_irq(struct pt_regs *regs)
 				continue;
 		}
 
-		virq = irq_find_mapping(intc[i].domain, irqnr);
-		handle_IRQ(virq, regs);
+		handle_domain_irq(intc[i].domain, irqnr, regs);
 	}
 }
 
diff --git a/drivers/irqchip/irq-zevio.c b/drivers/irqchip/irq-zevio.c
index ceb3a4318f73..e4ef74ed454a 100644
--- a/drivers/irqchip/irq-zevio.c
+++ b/drivers/irqchip/irq-zevio.c
@@ -56,8 +56,7 @@ static void __exception_irq_entry zevio_handle_irq(struct pt_regs *regs)
 
 	while (readl(zevio_irq_io + IO_STATUS)) {
 		irqnr = readl(zevio_irq_io + IO_CURRENT);
-		irqnr = irq_find_mapping(zevio_irq_domain, irqnr);
-		handle_IRQ(irqnr, regs);
+		handle_domain_irq(zevio_irq_domain, irqnr, regs);
 	};
 }
 
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 90e108f9e22e..a210338cfeb1 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -468,6 +468,15 @@ config LEDS_OT200
 	  This option enables support for the LEDs on the Bachmann OT200.
 	  Say Y to enable LEDs on the Bachmann OT200.
 
+config LEDS_MENF21BMC
+	tristate "LED support for the MEN 14F021P00 BMC"
+	depends on LEDS_CLASS && MFD_MENF21BMC
+	help
+	  Say Y here to include support for the MEN 14F021P00 BMC LEDs.
+
+	  This driver can also be built as a module. If so the module
+	  will be called leds-menf21bmc.
+
 comment "LED driver for blink(1) USB RGB LED is under Special HID drivers (HID_THINGM)"
 
 config LEDS_BLINKM
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index 822dd83ef97a..a2b164741465 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -55,6 +55,7 @@ obj-$(CONFIG_LEDS_LM355x)		+= leds-lm355x.o
 obj-$(CONFIG_LEDS_BLINKM)		+= leds-blinkm.o
 obj-$(CONFIG_LEDS_SYSCON)		+= leds-syscon.o
 obj-$(CONFIG_LEDS_VERSATILE)		+= leds-versatile.o
+obj-$(CONFIG_LEDS_MENF21BMC)		+= leds-menf21bmc.o
 
 # LED SPI Drivers
 obj-$(CONFIG_LEDS_DAC124S085)		+= leds-dac124s085.o
diff --git a/drivers/leds/leds-menf21bmc.c b/drivers/leds/leds-menf21bmc.c
new file mode 100644
index 000000000000..89dd57769e3b
--- /dev/null
+++ b/drivers/leds/leds-menf21bmc.c
@@ -0,0 +1,131 @@
+/*
+ *  MEN 14F021P00 Board Management Controller (BMC) LEDs Driver.
+ *
+ *  This is the core LED driver of the MEN 14F021P00 BMC.
+ *  There are four LEDs available which can be switched on and off.
+ *  STATUS LED, HOT SWAP LED, USER LED 1, USER LED 2
+ *
+ *  Copyright (C) 2014 MEN Mikro Elektronik Nuernberg GmbH
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/leds.h>
+#include <linux/i2c.h>
+
+#define BMC_CMD_LED_GET_SET	0xA0
+#define BMC_BIT_LED_STATUS	BIT(0)
+#define BMC_BIT_LED_HOTSWAP	BIT(1)
+#define BMC_BIT_LED_USER1	BIT(2)
+#define BMC_BIT_LED_USER2	BIT(3)
+
+struct menf21bmc_led {
+	struct led_classdev cdev;
+	u8 led_bit;
+	const char *name;
+	struct i2c_client *i2c_client;
+};
+
+static struct menf21bmc_led leds[] = {
+	{
+		.name = "menf21bmc:led_status",
+		.led_bit = BMC_BIT_LED_STATUS,
+	},
+	{
+		.name = "menf21bmc:led_hotswap",
+		.led_bit = BMC_BIT_LED_HOTSWAP,
+	},
+	{
+		.name = "menf21bmc:led_user1",
+		.led_bit = BMC_BIT_LED_USER1,
+	},
+	{
+		.name = "menf21bmc:led_user2",
+		.led_bit = BMC_BIT_LED_USER2,
+	}
+};
+
+static DEFINE_MUTEX(led_lock);
+
+static void
+menf21bmc_led_set(struct led_classdev *led_cdev, enum led_brightness value)
+{
+	int led_val;
+	struct menf21bmc_led *led = container_of(led_cdev,
+					struct menf21bmc_led, cdev);
+
+	mutex_lock(&led_lock);
+	led_val = i2c_smbus_read_byte_data(led->i2c_client,
+					   BMC_CMD_LED_GET_SET);
+	if (led_val < 0)
+		goto err_out;
+
+	if (value == LED_OFF)
+		led_val &= ~led->led_bit;
+	else
+		led_val |= led->led_bit;
+
+	i2c_smbus_write_byte_data(led->i2c_client,
+				  BMC_CMD_LED_GET_SET, led_val);
+err_out:
+	mutex_unlock(&led_lock);
+}
+
+static int menf21bmc_led_probe(struct platform_device *pdev)
+{
+	int i;
+	int ret;
+	struct i2c_client *i2c_client = to_i2c_client(pdev->dev.parent);
+
+	for (i = 0; i < ARRAY_SIZE(leds); i++) {
+		leds[i].cdev.name = leds[i].name;
+		leds[i].cdev.brightness_set = menf21bmc_led_set;
+		leds[i].i2c_client = i2c_client;
+		ret = led_classdev_register(&pdev->dev, &leds[i].cdev);
+		if (ret < 0)
+			goto err_free_leds;
+	}
+	dev_info(&pdev->dev, "MEN 140F21P00 BMC LED device enabled\n");
+
+	return 0;
+
+err_free_leds:
+	dev_err(&pdev->dev, "failed to register LED device\n");
+
+	for (i = i - 1; i >= 0; i--)
+		led_classdev_unregister(&leds[i].cdev);
+
+	return ret;
+}
+
+static int menf21bmc_led_remove(struct platform_device *pdev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(leds); i++)
+		led_classdev_unregister(&leds[i].cdev);
+
+	return 0;
+}
+
+static struct platform_driver menf21bmc_led = {
+	.probe		= menf21bmc_led_probe,
+	.remove		= menf21bmc_led_remove,
+	.driver		= {
+		.name		= "menf21bmc_led",
+		.owner		= THIS_MODULE,
+	},
+};
+
+module_platform_driver(menf21bmc_led);
+
+MODULE_AUTHOR("Andreas Werner <andreas.werner@men.de>");
+MODULE_DESCRIPTION("MEN 14F021P00 BMC led driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:menf21bmc_led");
diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c
index 4a0e786b7832..5a6363d161a2 100644
--- a/drivers/leds/leds-pca9532.c
+++ b/drivers/leds/leds-pca9532.c
@@ -319,14 +319,8 @@ static int pca9532_destroy_devices(struct pca9532_data *data, int n_devs)
 	}
 
 #ifdef CONFIG_LEDS_PCA9532_GPIO
-	if (data->gpio.dev) {
-		int err = gpiochip_remove(&data->gpio);
-		if (err) {
-			dev_err(&data->client->dev, "%s failed, %d\n",
-						"gpiochip_remove()", err);
-			return err;
-		}
-	}
+	if (data->gpio.dev)
+		gpiochip_remove(&data->gpio);
 #endif
 
 	return 0;
diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c
index 3d9e267a56c4..20fa8e77f186 100644
--- a/drivers/leds/leds-tca6507.c
+++ b/drivers/leds/leds-tca6507.c
@@ -667,11 +667,8 @@ static int tca6507_probe_gpios(struct i2c_client *client,
 
 static void tca6507_remove_gpio(struct tca6507_chip *tca)
 {
-	if (tca->gpio.ngpio) {
-		int err = gpiochip_remove(&tca->gpio);
-		dev_err(&tca->client->dev, "%s failed, %d\n",
-			"gpiochip_remove()", err);
-	}
+	if (tca->gpio.ngpio)
+		gpiochip_remove(&tca->gpio);
 }
 #else /* CONFIG_GPIOLIB */
 static int tca6507_probe_gpios(struct i2c_client *client,
diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c
index 9e9c56758a08..226179b975a0 100644
--- a/drivers/macintosh/adb.c
+++ b/drivers/macintosh/adb.c
@@ -411,6 +411,7 @@ adb_poll(void)
 		return;
 	adb_controller->poll();
 }
+EXPORT_SYMBOL(adb_poll);
 
 static void adb_sync_req_done(struct adb_request *req)
 {
@@ -460,6 +461,7 @@ adb_request(struct adb_request *req, void (*done)(struct adb_request *),
 
 	return rc;
 }
+EXPORT_SYMBOL(adb_request);
 
  /* Ultimately this should return the number of devices with
     the given default id.
@@ -495,6 +497,7 @@ adb_register(int default_id, int handler_id, struct adb_ids *ids,
 	mutex_unlock(&adb_handler_mutex);
 	return ids->nids;
 }
+EXPORT_SYMBOL(adb_register);
 
 int
 adb_unregister(int index)
@@ -516,6 +519,7 @@ adb_unregister(int index)
 	mutex_unlock(&adb_handler_mutex);
 	return ret;
 }
+EXPORT_SYMBOL(adb_unregister);
 
 void
 adb_input(unsigned char *buf, int nb, int autopoll)
@@ -582,6 +586,7 @@ adb_try_handler_change(int address, int new_id)
 	mutex_unlock(&adb_handler_mutex);
 	return ret;
 }
+EXPORT_SYMBOL(adb_try_handler_change);
 
 int
 adb_get_infos(int address, int *original_address, int *handler_id)
diff --git a/drivers/macintosh/via-cuda.c b/drivers/macintosh/via-cuda.c
index d61f271d2207..bad18130f125 100644
--- a/drivers/macintosh/via-cuda.c
+++ b/drivers/macintosh/via-cuda.c
@@ -379,6 +379,7 @@ cuda_request(struct adb_request *req, void (*done)(struct adb_request *),
     req->reply_expected = 1;
     return cuda_write(req);
 }
+EXPORT_SYMBOL(cuda_request);
 
 static int
 cuda_write(struct adb_request *req)
@@ -441,6 +442,7 @@ cuda_poll(void)
     if (cuda_irq)
 	enable_irq(cuda_irq);
 }
+EXPORT_SYMBOL(cuda_poll);
 
 static irqreturn_t
 cuda_interrupt(int irq, void *arg)
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index d4713d098a39..4dd2bb7167f0 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -842,6 +842,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	q->limits.logical_block_size	= block_size;
 	q->limits.physical_block_size	= block_size;
 	set_bit(QUEUE_FLAG_NONROT,	&d->disk->queue->queue_flags);
+	clear_bit(QUEUE_FLAG_ADD_RANDOM, &d->disk->queue->queue_flags);
 	set_bit(QUEUE_FLAG_DISCARD,	&d->disk->queue->queue_flags);
 
 	blk_queue_flush(q, REQ_FLUSH|REQ_FUA);
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 67f8b31e2054..da3604e73e8a 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -879,7 +879,6 @@ void bitmap_unplug(struct bitmap *bitmap)
 {
 	unsigned long i;
 	int dirty, need_write;
-	int wait = 0;
 
 	if (!bitmap || !bitmap->storage.filemap ||
 	    test_bit(BITMAP_STALE, &bitmap->flags))
@@ -897,16 +896,13 @@ void bitmap_unplug(struct bitmap *bitmap)
 			clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
 			write_page(bitmap, bitmap->storage.filemap[i], 0);
 		}
-		if (dirty)
-			wait = 1;
-	}
-	if (wait) { /* if any writes were performed, we need to wait on them */
-		if (bitmap->storage.file)
-			wait_event(bitmap->write_wait,
-				   atomic_read(&bitmap->pending_writes)==0);
-		else
-			md_super_wait(bitmap->mddev);
 	}
+	if (bitmap->storage.file)
+		wait_event(bitmap->write_wait,
+			   atomic_read(&bitmap->pending_writes)==0);
+	else
+		md_super_wait(bitmap->mddev);
+
 	if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
 		bitmap_file_kick(bitmap);
 }
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index ab472c557d18..825ca1f87639 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -465,6 +465,7 @@ static void __relink_lru(struct dm_buffer *b, int dirty)
 	c->n_buffers[dirty]++;
 	b->list_mode = dirty;
 	list_move(&b->lru_list, &c->lru[dirty]);
+	b->last_accessed = jiffies;
 }
 
 /*----------------------------------------------------------------
@@ -720,7 +721,6 @@ static void __wait_for_free_buffer(struct dm_bufio_client *c)
 
 	io_schedule();
 
-	set_task_state(current, TASK_RUNNING);
 	remove_wait_queue(&c->free_buffer_wait, &wait);
 
 	dm_bufio_lock(c);
@@ -1472,9 +1472,9 @@ static long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
 		list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) {
 			freed += __cleanup_old_buffer(b, gfp_mask, 0);
 			if (!--nr_to_scan)
-				break;
+				return freed;
+			dm_bufio_cond_resched();
 		}
-		dm_bufio_cond_resched();
 	}
 	return freed;
 }
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index cd15e0801228..fc93b9330af4 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -526,29 +526,26 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv,
 			    u8 *data)
 {
 	struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;
-	struct {
-		struct shash_desc desc;
-		char ctx[crypto_shash_descsize(lmk->hash_tfm)];
-	} sdesc;
+	SHASH_DESC_ON_STACK(desc, lmk->hash_tfm);
 	struct md5_state md5state;
 	__le32 buf[4];
 	int i, r;
 
-	sdesc.desc.tfm = lmk->hash_tfm;
-	sdesc.desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	desc->tfm = lmk->hash_tfm;
+	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
-	r = crypto_shash_init(&sdesc.desc);
+	r = crypto_shash_init(desc);
 	if (r)
 		return r;
 
 	if (lmk->seed) {
-		r = crypto_shash_update(&sdesc.desc, lmk->seed, LMK_SEED_SIZE);
+		r = crypto_shash_update(desc, lmk->seed, LMK_SEED_SIZE);
 		if (r)
 			return r;
 	}
 
 	/* Sector is always 512B, block size 16, add data of blocks 1-31 */
-	r = crypto_shash_update(&sdesc.desc, data + 16, 16 * 31);
+	r = crypto_shash_update(desc, data + 16, 16 * 31);
 	if (r)
 		return r;
 
@@ -557,12 +554,12 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv,
 	buf[1] = cpu_to_le32((((u64)dmreq->iv_sector >> 32) & 0x00FFFFFF) | 0x80000000);
 	buf[2] = cpu_to_le32(4024);
 	buf[3] = 0;
-	r = crypto_shash_update(&sdesc.desc, (u8 *)buf, sizeof(buf));
+	r = crypto_shash_update(desc, (u8 *)buf, sizeof(buf));
 	if (r)
 		return r;
 
 	/* No MD5 padding here */
-	r = crypto_shash_export(&sdesc.desc, &md5state);
+	r = crypto_shash_export(desc, &md5state);
 	if (r)
 		return r;
 
@@ -679,10 +676,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
 	struct iv_tcw_private *tcw = &cc->iv_gen_private.tcw;
 	u64 sector = cpu_to_le64((u64)dmreq->iv_sector);
 	u8 buf[TCW_WHITENING_SIZE];
-	struct {
-		struct shash_desc desc;
-		char ctx[crypto_shash_descsize(tcw->crc32_tfm)];
-	} sdesc;
+	SHASH_DESC_ON_STACK(desc, tcw->crc32_tfm);
 	int i, r;
 
 	/* xor whitening with sector number */
@@ -691,16 +685,16 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
 	crypto_xor(&buf[8], (u8 *)&sector, 8);
 
 	/* calculate crc32 for every 32bit part and xor it */
-	sdesc.desc.tfm = tcw->crc32_tfm;
-	sdesc.desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	desc->tfm = tcw->crc32_tfm;
+	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	for (i = 0; i < 4; i++) {
-		r = crypto_shash_init(&sdesc.desc);
+		r = crypto_shash_init(desc);
 		if (r)
 			goto out;
-		r = crypto_shash_update(&sdesc.desc, &buf[i * 4], 4);
+		r = crypto_shash_update(desc, &buf[i * 4], 4);
 		if (r)
 			goto out;
-		r = crypto_shash_final(&sdesc.desc, &buf[i * 4]);
+		r = crypto_shash_final(desc, &buf[i * 4]);
 		if (r)
 			goto out;
 	}
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 51521429fb59..0be9381365d7 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1418,7 +1418,7 @@ static void retrieve_deps(struct dm_table *table,
 	deps->count = count;
 	count = 0;
 	list_for_each_entry (dd, dm_table_get_devices(table), list)
-		deps->dev[count++] = huge_encode_dev(dd->dm_dev.bdev->bd_dev);
+		deps->dev[count++] = huge_encode_dev(dd->dm_dev->bdev->bd_dev);
 
 	param->data_size = param->data_start + needed;
 }
diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c
index b428c0ae63d5..39ad9664d397 100644
--- a/drivers/md/dm-log-userspace-transfer.c
+++ b/drivers/md/dm-log-userspace-transfer.c
@@ -272,7 +272,7 @@ int dm_ulog_tfr_init(void)
 
 	r = cn_add_callback(&ulog_cn_id, "dmlogusr", cn_ulog_callback);
 	if (r) {
-		cn_del_callback(&ulog_cn_id);
+		kfree(prealloced_cn_msg);
 		return r;
 	}
 
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 833d7e752f06..7b6b0f0f831a 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -317,8 +317,10 @@ static void __choose_pgpath(struct multipath *m, size_t nr_bytes)
 	struct priority_group *pg;
 	unsigned bypassed = 1;
 
-	if (!m->nr_valid_paths)
+	if (!m->nr_valid_paths) {
+		m->queue_io = 0;
 		goto failed;
+	}
 
 	/* Were we instructed to switch PG? */
 	if (m->next_pg) {
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 4880b69e2e9e..4857fa4a5484 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010-2011 Neil Brown
- * Copyright (C) 2010-2011 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2010-2014 Red Hat, Inc. All rights reserved.
  *
  * This file is released under the GPL.
  */
@@ -18,6 +18,8 @@
 
 #define DM_MSG_PREFIX "raid"
 
+static bool devices_handle_discard_safely = false;
+
 /*
  * The following flags are used by dm-raid.c to set up the array state.
  * They must be cleared before md_run is called.
@@ -475,6 +477,8 @@ too_many:
  *                                      will form the "stripe"
  *    [[no]sync]			Force or prevent recovery of the
  *                                      entire array
+ *    [devices_handle_discard_safely]	Allow discards on RAID4/5/6; useful if RAID
+ *					member device(s) properly support TRIM/UNMAP
  *    [rebuild <idx>]			Rebuild the drive indicated by the index
  *    [daemon_sleep <ms>]		Time between bitmap daemon work to
  *                                      clear bits
@@ -1150,6 +1154,49 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs)
 }
 
 /*
+ * Enable/disable discard support on RAID set depending on
+ * RAID level and discard properties of underlying RAID members.
+ */
+static void configure_discard_support(struct dm_target *ti, struct raid_set *rs)
+{
+	int i;
+	bool raid456;
+
+	/* Assume discards not supported until after checks below. */
+	ti->discards_supported = false;
+
+	/* RAID level 4,5,6 require discard_zeroes_data for data integrity! */
+	raid456 = (rs->md.level == 4 || rs->md.level == 5 || rs->md.level == 6);
+
+	for (i = 0; i < rs->md.raid_disks; i++) {
+		struct request_queue *q = bdev_get_queue(rs->dev[i].rdev.bdev);
+
+		if (!q || !blk_queue_discard(q))
+			return;
+
+		if (raid456) {
+			if (!q->limits.discard_zeroes_data)
+				return;
+			if (!devices_handle_discard_safely) {
+				DMERR("raid456 discard support disabled due to discard_zeroes_data uncertainty.");
+				DMERR("Set dm-raid.devices_handle_discard_safely=Y to override.");
+				return;
+			}
+		}
+	}
+
+	/* All RAID members properly support discards */
+	ti->discards_supported = true;
+
+	/*
+	 * RAID1 and RAID10 personalities require bio splitting,
+	 * RAID0/4/5/6 don't and process large discard bios properly.
+	 */
+	ti->split_discard_bios = !!(rs->md.level == 1 || rs->md.level == 10);
+	ti->num_discard_bios = 1;
+}
+
+/*
  * Construct a RAID4/5/6 mapping:
  * Args:
  *	<raid_type> <#raid_params> <raid_params>		\
@@ -1231,6 +1278,11 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->private = rs;
 	ti->num_flush_bios = 1;
 
+	/*
+	 * Disable/enable discard support on RAID set.
+	 */
+	configure_discard_support(ti, rs);
+
 	mutex_lock(&rs->md.reconfig_mutex);
 	ret = md_run(&rs->md);
 	rs->md.in_sync = 0; /* Assume already marked dirty */
@@ -1652,7 +1704,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 5, 2},
+	.version = {1, 6, 0},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
@@ -1683,6 +1735,10 @@ static void __exit dm_raid_exit(void)
 module_init(dm_raid_init);
 module_exit(dm_raid_exit);
 
+module_param(devices_handle_discard_safely, bool, 0644);
+MODULE_PARM_DESC(devices_handle_discard_safely,
+		 "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
+
 MODULE_DESCRIPTION(DM_NAME " raid4/5/6 target");
 MODULE_ALIAS("dm-raid1");
 MODULE_ALIAS("dm-raid10");
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 28a90122a5a8..87f86c77b094 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -548,7 +548,7 @@ void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw,
 		 * A race condition can at worst result in the merged flag being
 		 * misrepresented, so we don't have to disable preemption here.
 		 */
-		last = __this_cpu_ptr(stats->last);
+		last = raw_cpu_ptr(stats->last);
 		stats_aux->merged =
 			(bi_sector == (ACCESS_ONCE(last->last_sector) &&
 				       ((bi_rw & (REQ_WRITE | REQ_DISCARD)) ==
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index f9c6cb8dbcf8..b2bd1ebf4562 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -210,15 +210,16 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 	return 0;
 }
 
-static void free_devices(struct list_head *devices)
+static void free_devices(struct list_head *devices, struct mapped_device *md)
 {
 	struct list_head *tmp, *next;
 
 	list_for_each_safe(tmp, next, devices) {
 		struct dm_dev_internal *dd =
 		    list_entry(tmp, struct dm_dev_internal, list);
-		DMWARN("dm_table_destroy: dm_put_device call missing for %s",
-		       dd->dm_dev.name);
+		DMWARN("%s: dm_table_destroy: dm_put_device call missing for %s",
+		       dm_device_name(md), dd->dm_dev->name);
+		dm_put_table_device(md, dd->dm_dev);
 		kfree(dd);
 	}
 }
@@ -247,7 +248,7 @@ void dm_table_destroy(struct dm_table *t)
 	vfree(t->highs);
 
 	/* free the device list */
-	free_devices(&t->devices);
+	free_devices(&t->devices, t->md);
 
 	dm_free_md_mempools(t->mempools);
 
@@ -262,53 +263,13 @@ static struct dm_dev_internal *find_device(struct list_head *l, dev_t dev)
 	struct dm_dev_internal *dd;
 
 	list_for_each_entry (dd, l, list)
-		if (dd->dm_dev.bdev->bd_dev == dev)
+		if (dd->dm_dev->bdev->bd_dev == dev)
 			return dd;
 
 	return NULL;
 }
 
 /*
- * Open a device so we can use it as a map destination.
- */
-static int open_dev(struct dm_dev_internal *d, dev_t dev,
-		    struct mapped_device *md)
-{
-	static char *_claim_ptr = "I belong to device-mapper";
-	struct block_device *bdev;
-
-	int r;
-
-	BUG_ON(d->dm_dev.bdev);
-
-	bdev = blkdev_get_by_dev(dev, d->dm_dev.mode | FMODE_EXCL, _claim_ptr);
-	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
-
-	r = bd_link_disk_holder(bdev, dm_disk(md));
-	if (r) {
-		blkdev_put(bdev, d->dm_dev.mode | FMODE_EXCL);
-		return r;
-	}
-
-	d->dm_dev.bdev = bdev;
-	return 0;
-}
-
-/*
- * Close a device that we've been using.
- */
-static void close_dev(struct dm_dev_internal *d, struct mapped_device *md)
-{
-	if (!d->dm_dev.bdev)
-		return;
-
-	bd_unlink_disk_holder(d->dm_dev.bdev, dm_disk(md));
-	blkdev_put(d->dm_dev.bdev, d->dm_dev.mode | FMODE_EXCL);
-	d->dm_dev.bdev = NULL;
-}
-
-/*
  * If possible, this checks an area of a destination device is invalid.
  */
 static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
@@ -386,19 +347,17 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 			struct mapped_device *md)
 {
 	int r;
-	struct dm_dev_internal dd_new, dd_old;
+	struct dm_dev *old_dev, *new_dev;
 
-	dd_new = dd_old = *dd;
+	old_dev = dd->dm_dev;
 
-	dd_new.dm_dev.mode |= new_mode;
-	dd_new.dm_dev.bdev = NULL;
-
-	r = open_dev(&dd_new, dd->dm_dev.bdev->bd_dev, md);
+	r = dm_get_table_device(md, dd->dm_dev->bdev->bd_dev,
+				dd->dm_dev->mode | new_mode, &new_dev);
 	if (r)
 		return r;
 
-	dd->dm_dev.mode |= new_mode;
-	close_dev(&dd_old, md);
+	dd->dm_dev = new_dev;
+	dm_put_table_device(md, old_dev);
 
 	return 0;
 }
@@ -440,27 +399,22 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
 		if (!dd)
 			return -ENOMEM;
 
-		dd->dm_dev.mode = mode;
-		dd->dm_dev.bdev = NULL;
-
-		if ((r = open_dev(dd, dev, t->md))) {
+		if ((r = dm_get_table_device(t->md, dev, mode, &dd->dm_dev))) {
 			kfree(dd);
 			return r;
 		}
 
-		format_dev_t(dd->dm_dev.name, dev);
-
 		atomic_set(&dd->count, 0);
 		list_add(&dd->list, &t->devices);
 
-	} else if (dd->dm_dev.mode != (mode | dd->dm_dev.mode)) {
+	} else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) {
 		r = upgrade_mode(dd, mode, t->md);
 		if (r)
 			return r;
 	}
 	atomic_inc(&dd->count);
 
-	*result = &dd->dm_dev;
+	*result = dd->dm_dev;
 	return 0;
 }
 EXPORT_SYMBOL(dm_get_device);
@@ -505,11 +459,23 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
  */
 void dm_put_device(struct dm_target *ti, struct dm_dev *d)
 {
-	struct dm_dev_internal *dd = container_of(d, struct dm_dev_internal,
-						  dm_dev);
+	int found = 0;
+	struct list_head *devices = &ti->table->devices;
+	struct dm_dev_internal *dd;
 
+	list_for_each_entry(dd, devices, list) {
+		if (dd->dm_dev == d) {
+			found = 1;
+			break;
+		}
+	}
+	if (!found) {
+		DMWARN("%s: device %s not in table devices list",
+		       dm_device_name(ti->table->md), d->name);
+		return;
+	}
 	if (atomic_dec_and_test(&dd->count)) {
-		close_dev(dd, ti->table->md);
+		dm_put_table_device(ti->table->md, d);
 		list_del(&dd->list);
 		kfree(dd);
 	}
@@ -906,7 +872,7 @@ static int dm_table_set_type(struct dm_table *t)
 	/* Non-request-stackable devices can't be used for request-based dm */
 	devices = dm_table_get_devices(t);
 	list_for_each_entry(dd, devices, list) {
-		if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev.bdev))) {
+		if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev->bdev))) {
 			DMWARN("table load rejected: including"
 			       " non-request-stackable devices");
 			return -EINVAL;
@@ -1043,7 +1009,7 @@ static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t,
 	struct gendisk *prev_disk = NULL, *template_disk = NULL;
 
 	list_for_each_entry(dd, devices, list) {
-		template_disk = dd->dm_dev.bdev->bd_disk;
+		template_disk = dd->dm_dev->bdev->bd_disk;
 		if (!blk_get_integrity(template_disk))
 			goto no_integrity;
 		if (!match_all && !blk_integrity_is_initialized(template_disk))
@@ -1629,7 +1595,7 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 	int r = 0;
 
 	list_for_each_entry(dd, devices, list) {
-		struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev);
+		struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev);
 		char b[BDEVNAME_SIZE];
 
 		if (likely(q))
@@ -1637,7 +1603,7 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 		else
 			DMWARN_LIMIT("%s: any_congested: nonexistent device %s",
 				     dm_device_name(t->md),
-				     bdevname(dd->dm_dev.bdev, b));
+				     bdevname(dd->dm_dev->bdev, b));
 	}
 
 	list_for_each_entry(cb, &t->target_callbacks, list)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 32b958dbc499..58f3927fd7cc 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -142,6 +142,9 @@ struct mapped_device {
 	 */
 	struct dm_table *map;
 
+	struct list_head table_devices;
+	struct mutex table_devices_lock;
+
 	unsigned long flags;
 
 	struct request_queue *queue;
@@ -212,6 +215,12 @@ struct dm_md_mempools {
 	struct bio_set *bs;
 };
 
+struct table_device {
+	struct list_head list;
+	atomic_t count;
+	struct dm_dev dm_dev;
+};
+
 #define RESERVED_BIO_BASED_IOS		16
 #define RESERVED_REQUEST_BASED_IOS	256
 #define RESERVED_MAX_IOS		1024
@@ -670,6 +679,120 @@ static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU)
 }
 
 /*
+ * Open a table device so we can use it as a map destination.
+ */
+static int open_table_device(struct table_device *td, dev_t dev,
+			     struct mapped_device *md)
+{
+	static char *_claim_ptr = "I belong to device-mapper";
+	struct block_device *bdev;
+
+	int r;
+
+	BUG_ON(td->dm_dev.bdev);
+
+	bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _claim_ptr);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
+
+	r = bd_link_disk_holder(bdev, dm_disk(md));
+	if (r) {
+		blkdev_put(bdev, td->dm_dev.mode | FMODE_EXCL);
+		return r;
+	}
+
+	td->dm_dev.bdev = bdev;
+	return 0;
+}
+
+/*
+ * Close a table device that we've been using.
+ */
+static void close_table_device(struct table_device *td, struct mapped_device *md)
+{
+	if (!td->dm_dev.bdev)
+		return;
+
+	bd_unlink_disk_holder(td->dm_dev.bdev, dm_disk(md));
+	blkdev_put(td->dm_dev.bdev, td->dm_dev.mode | FMODE_EXCL);
+	td->dm_dev.bdev = NULL;
+}
+
+static struct table_device *find_table_device(struct list_head *l, dev_t dev,
+					      fmode_t mode) {
+	struct table_device *td;
+
+	list_for_each_entry(td, l, list)
+		if (td->dm_dev.bdev->bd_dev == dev && td->dm_dev.mode == mode)
+			return td;
+
+	return NULL;
+}
+
+int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode,
+			struct dm_dev **result) {
+	int r;
+	struct table_device *td;
+
+	mutex_lock(&md->table_devices_lock);
+	td = find_table_device(&md->table_devices, dev, mode);
+	if (!td) {
+		td = kmalloc(sizeof(*td), GFP_KERNEL);
+		if (!td) {
+			mutex_unlock(&md->table_devices_lock);
+			return -ENOMEM;
+		}
+
+		td->dm_dev.mode = mode;
+		td->dm_dev.bdev = NULL;
+
+		if ((r = open_table_device(td, dev, md))) {
+			mutex_unlock(&md->table_devices_lock);
+			kfree(td);
+			return r;
+		}
+
+		format_dev_t(td->dm_dev.name, dev);
+
+		atomic_set(&td->count, 0);
+		list_add(&td->list, &md->table_devices);
+	}
+	atomic_inc(&td->count);
+	mutex_unlock(&md->table_devices_lock);
+
+	*result = &td->dm_dev;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dm_get_table_device);
+
+void dm_put_table_device(struct mapped_device *md, struct dm_dev *d)
+{
+	struct table_device *td = container_of(d, struct table_device, dm_dev);
+
+	mutex_lock(&md->table_devices_lock);
+	if (atomic_dec_and_test(&td->count)) {
+		close_table_device(td, md);
+		list_del(&td->list);
+		kfree(td);
+	}
+	mutex_unlock(&md->table_devices_lock);
+}
+EXPORT_SYMBOL(dm_put_table_device);
+
+static void free_table_devices(struct list_head *devices)
+{
+	struct list_head *tmp, *next;
+
+	list_for_each_safe(tmp, next, devices) {
+		struct table_device *td = list_entry(tmp, struct table_device, list);
+
+		DMWARN("dm_destroy: %s still exists with %d references",
+		       td->dm_dev.name, atomic_read(&td->count));
+		kfree(td);
+	}
+}
+
+/*
  * Get the geometry associated with a dm device
  */
 int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo)
@@ -1249,13 +1372,13 @@ static void clone_bio(struct dm_target_io *tio, struct bio *bio,
 }
 
 static struct dm_target_io *alloc_tio(struct clone_info *ci,
-				      struct dm_target *ti, int nr_iovecs,
+				      struct dm_target *ti,
 				      unsigned target_bio_nr)
 {
 	struct dm_target_io *tio;
 	struct bio *clone;
 
-	clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, ci->md->bs);
+	clone = bio_alloc_bioset(GFP_NOIO, 0, ci->md->bs);
 	tio = container_of(clone, struct dm_target_io, clone);
 
 	tio->io = ci->io;
@@ -1269,17 +1392,12 @@ static void __clone_and_map_simple_bio(struct clone_info *ci,
 				       struct dm_target *ti,
 				       unsigned target_bio_nr, unsigned *len)
 {
-	struct dm_target_io *tio = alloc_tio(ci, ti, ci->bio->bi_max_vecs, target_bio_nr);
+	struct dm_target_io *tio = alloc_tio(ci, ti, target_bio_nr);
 	struct bio *clone = &tio->clone;
 
 	tio->len_ptr = len;
 
-	/*
-	 * Discard requests require the bio's inline iovecs be initialized.
-	 * ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush
-	 * and discard, so no need for concern about wasted bvec allocations.
-	 */
-	 __bio_clone_fast(clone, ci->bio);
+	__bio_clone_fast(clone, ci->bio);
 	if (len)
 		bio_setup_sector(clone, ci->sector, *len);
 
@@ -1322,7 +1440,7 @@ static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti
 		num_target_bios = ti->num_write_bios(ti, bio);
 
 	for (target_bio_nr = 0; target_bio_nr < num_target_bios; target_bio_nr++) {
-		tio = alloc_tio(ci, ti, 0, target_bio_nr);
+		tio = alloc_tio(ci, ti, target_bio_nr);
 		tio->len_ptr = len;
 		clone_bio(tio, bio, sector, *len);
 		__map_bio(tio);
@@ -1949,12 +2067,14 @@ static struct mapped_device *alloc_dev(int minor)
 	md->type = DM_TYPE_NONE;
 	mutex_init(&md->suspend_lock);
 	mutex_init(&md->type_lock);
+	mutex_init(&md->table_devices_lock);
 	spin_lock_init(&md->deferred_lock);
 	atomic_set(&md->holders, 1);
 	atomic_set(&md->open_count, 0);
 	atomic_set(&md->event_nr, 0);
 	atomic_set(&md->uevent_seq, 0);
 	INIT_LIST_HEAD(&md->uevent_list);
+	INIT_LIST_HEAD(&md->table_devices);
 	spin_lock_init(&md->uevent_lock);
 
 	md->queue = blk_alloc_queue(GFP_KERNEL);
@@ -2040,6 +2160,7 @@ static void free_dev(struct mapped_device *md)
 	blk_integrity_unregister(md->disk);
 	del_gendisk(md->disk);
 	cleanup_srcu_struct(&md->io_barrier);
+	free_table_devices(&md->table_devices);
 	free_minor(minor);
 
 	spin_lock(&_minor_lock);
@@ -2900,7 +3021,7 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, u
 	if (!pools->io_pool)
 		goto out;
 
-	pools->bs = bioset_create(pool_size, front_pad);
+	pools->bs = bioset_create_nobvec(pool_size, front_pad);
 	if (!pools->bs)
 		goto out;
 
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index e81d2152fa68..988c7fb7b145 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -44,7 +44,7 @@
 struct dm_dev_internal {
 	struct list_head list;
 	atomic_t count;
-	struct dm_dev dm_dev;
+	struct dm_dev *dm_dev;
 };
 
 struct dm_table;
@@ -188,6 +188,9 @@ int dm_cancel_deferred_remove(struct mapped_device *md);
 int dm_request_based(struct mapped_device *md);
 sector_t dm_get_size(struct mapped_device *md);
 struct request_queue *dm_get_md_queue(struct mapped_device *md);
+int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode,
+			struct dm_dev **result);
+void dm_put_table_device(struct mapped_device *md, struct dm_dev *d);
 struct dm_stats *dm_get_stats(struct mapped_device *md);
 
 int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 56f534b4a2d2..64713b77df1c 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -10,10 +10,10 @@
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2, or (at your option)
    any later version.
-   
+
    You should have received a copy of the GNU General Public License
    (for example /usr/src/linux/COPYING); if not, write to the Free
-   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
+   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
 
 #include <linux/blkdev.h>
@@ -25,7 +25,7 @@
 #include "linear.h"
 
 /*
- * find which device holds a particular offset 
+ * find which device holds a particular offset
  */
 static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 {
@@ -355,7 +355,6 @@ static void linear_status (struct seq_file *seq, struct mddev *mddev)
 	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
 }
 
-
 static struct md_personality linear_personality =
 {
 	.name		= "linear",
@@ -379,7 +378,6 @@ static void linear_exit (void)
 	unregister_md_personality (&linear_personality);
 }
 
-
 module_init(linear_init);
 module_exit(linear_exit);
 MODULE_LICENSE("GPL");
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1294238610df..4dfa15da9cb8 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1,6 +1,6 @@
 /*
    md.c : Multiple Devices driver for Linux
-	  Copyright (C) 1998, 1999, 2000 Ingo Molnar
+     Copyright (C) 1998, 1999, 2000 Ingo Molnar
 
      completely rewritten, based on the MD driver code from Marc Zyngier
 
@@ -66,8 +66,6 @@ static void autostart_arrays(int part);
 static LIST_HEAD(pers_list);
 static DEFINE_SPINLOCK(pers_lock);
 
-static void md_print_devices(void);
-
 static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
 static struct workqueue_struct *md_wq;
 static struct workqueue_struct *md_misc_wq;
@@ -75,8 +73,6 @@ static struct workqueue_struct *md_misc_wq;
 static int remove_and_add_spares(struct mddev *mddev,
 				 struct md_rdev *this);
 
-#define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
-
 /*
  * Default number of read corrections we'll attempt on an rdev
  * before ejecting it from the array. We divide the read error
@@ -218,7 +214,6 @@ static void md_new_event_inintr(struct mddev *mddev)
 static LIST_HEAD(all_mddevs);
 static DEFINE_SPINLOCK(all_mddevs_lock);
 
-
 /*
  * iterates through all used mddevs in the system.
  * We take care to grab the all_mddevs_lock whenever navigating
@@ -228,7 +223,7 @@ static DEFINE_SPINLOCK(all_mddevs_lock);
  */
 #define for_each_mddev(_mddev,_tmp)					\
 									\
-	for (({ spin_lock(&all_mddevs_lock); 				\
+	for (({ spin_lock(&all_mddevs_lock);				\
 		_tmp = all_mddevs.next;					\
 		_mddev = NULL;});					\
 	     ({ if (_tmp != &all_mddevs)				\
@@ -241,7 +236,6 @@ static DEFINE_SPINLOCK(all_mddevs_lock);
 		_tmp = _tmp->next;})					\
 		)
 
-
 /* Rather than calling directly into the personality make_request function,
  * IO requests come here first so that we can check if the device is
  * being suspended pending a reconfiguration.
@@ -488,7 +482,7 @@ void mddev_init(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(mddev_init);
 
-static struct mddev * mddev_find(dev_t unit)
+static struct mddev *mddev_find(dev_t unit)
 {
 	struct mddev *mddev, *new = NULL;
 
@@ -530,7 +524,7 @@ static struct mddev * mddev_find(dev_t unit)
 				kfree(new);
 				return NULL;
 			}
-				
+
 			is_free = 1;
 			list_for_each_entry(mddev, &all_mddevs, all_mddevs)
 				if (mddev->unit == dev) {
@@ -562,7 +556,7 @@ static struct mddev * mddev_find(dev_t unit)
 	goto retry;
 }
 
-static inline int __must_check mddev_lock(struct mddev * mddev)
+static inline int __must_check mddev_lock(struct mddev *mddev)
 {
 	return mutex_lock_interruptible(&mddev->reconfig_mutex);
 }
@@ -570,7 +564,7 @@ static inline int __must_check mddev_lock(struct mddev * mddev)
 /* Sometimes we need to take the lock in a situation where
  * failure due to interrupts is not acceptable.
  */
-static inline void mddev_lock_nointr(struct mddev * mddev)
+static inline void mddev_lock_nointr(struct mddev *mddev)
 {
 	mutex_lock(&mddev->reconfig_mutex);
 }
@@ -580,14 +574,14 @@ static inline int mddev_is_locked(struct mddev *mddev)
 	return mutex_is_locked(&mddev->reconfig_mutex);
 }
 
-static inline int mddev_trylock(struct mddev * mddev)
+static inline int mddev_trylock(struct mddev *mddev)
 {
 	return mutex_trylock(&mddev->reconfig_mutex);
 }
 
 static struct attribute_group md_redundancy_group;
 
-static void mddev_unlock(struct mddev * mddev)
+static void mddev_unlock(struct mddev *mddev)
 {
 	if (mddev->to_remove) {
 		/* These cannot be removed under reconfig_mutex as
@@ -630,17 +624,6 @@ static void mddev_unlock(struct mddev * mddev)
 	spin_unlock(&pers_lock);
 }
 
-static struct md_rdev * find_rdev_nr(struct mddev *mddev, int nr)
-{
-	struct md_rdev *rdev;
-
-	rdev_for_each(rdev, mddev)
-		if (rdev->desc_nr == nr)
-			return rdev;
-
-	return NULL;
-}
-
 static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr)
 {
 	struct md_rdev *rdev;
@@ -693,11 +676,8 @@ static inline sector_t calc_dev_sboffset(struct md_rdev *rdev)
 	return MD_NEW_SIZE_SECTORS(num_sectors);
 }
 
-static int alloc_disk_sb(struct md_rdev * rdev)
+static int alloc_disk_sb(struct md_rdev *rdev)
 {
-	if (rdev->sb_page)
-		MD_BUG();
-
 	rdev->sb_page = alloc_page(GFP_KERNEL);
 	if (!rdev->sb_page) {
 		printk(KERN_ALERT "md: out of memory.\n");
@@ -766,14 +746,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 void md_super_wait(struct mddev *mddev)
 {
 	/* wait for all superblock writes that were scheduled to complete */
-	DEFINE_WAIT(wq);
-	for(;;) {
-		prepare_to_wait(&mddev->sb_wait, &wq, TASK_UNINTERRUPTIBLE);
-		if (atomic_read(&mddev->pending_writes)==0)
-			break;
-		schedule();
-	}
-	finish_wait(&mddev->sb_wait, &wq);
+	wait_event(mddev->sb_wait, atomic_read(&mddev->pending_writes)==0);
 }
 
 int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
@@ -801,17 +774,13 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
 }
 EXPORT_SYMBOL_GPL(sync_page_io);
 
-static int read_disk_sb(struct md_rdev * rdev, int size)
+static int read_disk_sb(struct md_rdev *rdev, int size)
 {
 	char b[BDEVNAME_SIZE];
-	if (!rdev->sb_page) {
-		MD_BUG();
-		return -EINVAL;
-	}
+
 	if (rdev->sb_loaded)
 		return 0;
 
-
 	if (!sync_page_io(rdev, 0, size, rdev->sb_page, READ, true))
 		goto fail;
 	rdev->sb_loaded = 1;
@@ -825,7 +794,7 @@ fail:
 
 static int uuid_equal(mdp_super_t *sb1, mdp_super_t *sb2)
 {
-	return 	sb1->set_uuid0 == sb2->set_uuid0 &&
+	return	sb1->set_uuid0 == sb2->set_uuid0 &&
 		sb1->set_uuid1 == sb2->set_uuid1 &&
 		sb1->set_uuid2 == sb2->set_uuid2 &&
 		sb1->set_uuid3 == sb2->set_uuid3;
@@ -861,14 +830,13 @@ abort:
 	return ret;
 }
 
-
 static u32 md_csum_fold(u32 csum)
 {
 	csum = (csum & 0xffff) + (csum >> 16);
 	return (csum & 0xffff) + (csum >> 16);
 }
 
-static unsigned int calc_sb_csum(mdp_super_t * sb)
+static unsigned int calc_sb_csum(mdp_super_t *sb)
 {
 	u64 newcsum = 0;
 	u32 *sb32 = (u32*)sb;
@@ -882,7 +850,6 @@ static unsigned int calc_sb_csum(mdp_super_t * sb)
 		newcsum += sb32[i];
 	csum = (newcsum & 0xffffffff) + (newcsum>>32);
 
-
 #ifdef CONFIG_ALPHA
 	/* This used to use csum_partial, which was wrong for several
 	 * reasons including that different results are returned on
@@ -899,7 +866,6 @@ static unsigned int calc_sb_csum(mdp_super_t * sb)
 	return csum;
 }
 
-
 /*
  * Handle superblock details.
  * We want to be able to handle multiple superblock formats
@@ -965,7 +931,7 @@ int md_check_no_bitmap(struct mddev *mddev)
 EXPORT_SYMBOL(md_check_no_bitmap);
 
 /*
- * load_super for 0.90.0 
+ * load_super for 0.90.0
  */
 static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version)
 {
@@ -1044,7 +1010,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 		ev2 = md_event(refsb);
 		if (ev1 > ev2)
 			ret = 1;
-		else 
+		else
 			ret = 0;
 	}
 	rdev->sectors = rdev->sb_start;
@@ -1118,7 +1084,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 		if (sb->state & (1<<MD_SB_CLEAN))
 			mddev->recovery_cp = MaxSector;
 		else {
-			if (sb->events_hi == sb->cp_events_hi && 
+			if (sb->events_hi == sb->cp_events_hi &&
 				sb->events_lo == sb->cp_events_lo) {
 				mddev->recovery_cp = sb->recovery_cp;
 			} else
@@ -1146,7 +1112,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 		++ev1;
 		if (sb->disks[rdev->desc_nr].state & (
 			    (1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)))
-			if (ev1 < mddev->events) 
+			if (ev1 < mddev->events)
 				return -EINVAL;
 	} else if (mddev->bitmap) {
 		/* if adding to array with a bitmap, then we can accept an
@@ -1197,7 +1163,6 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev)
 	struct md_rdev *rdev2;
 	int next_spare = mddev->raid_disks;
 
-
 	/* make rdev->sb match mddev data..
 	 *
 	 * 1/ zero out disks
@@ -1366,7 +1331,7 @@ super_90_allow_new_offset(struct md_rdev *rdev, unsigned long long new_offset)
  * version 1 superblock
  */
 
-static __le32 calc_sb_1_csum(struct mdp_superblock_1 * sb)
+static __le32 calc_sb_1_csum(struct mdp_superblock_1 *sb)
 {
 	__le32 disk_csum;
 	u32 csum;
@@ -1430,7 +1395,6 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	ret = read_disk_sb(rdev, 4096);
 	if (ret) return ret;
 
-
 	sb = page_address(rdev->sb_page);
 
 	if (sb->magic != cpu_to_le32(MD_SB_MAGIC) ||
@@ -1817,7 +1781,7 @@ retry:
 
 	for (i=0; i<max_dev;i++)
 		sb->dev_roles[i] = cpu_to_le16(0xfffe);
-	
+
 	rdev_for_each(rdev2, mddev) {
 		i = rdev2->desc_nr;
 		if (test_bit(Faulty, &rdev2->flags))
@@ -2033,18 +1997,13 @@ void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
 }
 EXPORT_SYMBOL(md_integrity_add_rdev);
 
-static int bind_rdev_to_array(struct md_rdev * rdev, struct mddev * mddev)
+static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 {
 	char b[BDEVNAME_SIZE];
 	struct kobject *ko;
 	char *s;
 	int err;
 
-	if (rdev->mddev) {
-		MD_BUG();
-		return -EINVAL;
-	}
-
 	/* prevent duplicates */
 	if (find_rdev(mddev, rdev->bdev->bd_dev))
 		return -EEXIST;
@@ -2067,16 +2026,21 @@ static int bind_rdev_to_array(struct md_rdev * rdev, struct mddev * mddev)
 	 * If it is -1, assign a free number, else
 	 * check number is not in use
 	 */
+	rcu_read_lock();
 	if (rdev->desc_nr < 0) {
 		int choice = 0;
-		if (mddev->pers) choice = mddev->raid_disks;
-		while (find_rdev_nr(mddev, choice))
+		if (mddev->pers)
+			choice = mddev->raid_disks;
+		while (find_rdev_nr_rcu(mddev, choice))
 			choice++;
 		rdev->desc_nr = choice;
 	} else {
-		if (find_rdev_nr(mddev, rdev->desc_nr))
+		if (find_rdev_nr_rcu(mddev, rdev->desc_nr)) {
+			rcu_read_unlock();
 			return -EBUSY;
+		}
 	}
+	rcu_read_unlock();
 	if (mddev->max_disks && rdev->desc_nr >= mddev->max_disks) {
 		printk(KERN_WARNING "md: %s: array is limited to %d devices\n",
 		       mdname(mddev), mddev->max_disks);
@@ -2118,13 +2082,10 @@ static void md_delayed_delete(struct work_struct *ws)
 	kobject_put(&rdev->kobj);
 }
 
-static void unbind_rdev_from_array(struct md_rdev * rdev)
+static void unbind_rdev_from_array(struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
-	if (!rdev->mddev) {
-		MD_BUG();
-		return;
-	}
+
 	bd_unlink_disk_holder(rdev->bdev, rdev->mddev->gendisk);
 	list_del_rcu(&rdev->same_set);
 	printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
@@ -2169,20 +2130,17 @@ static void unlock_rdev(struct md_rdev *rdev)
 {
 	struct block_device *bdev = rdev->bdev;
 	rdev->bdev = NULL;
-	if (!bdev)
-		MD_BUG();
 	blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 }
 
 void md_autodetect_dev(dev_t dev);
 
-static void export_rdev(struct md_rdev * rdev)
+static void export_rdev(struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
+
 	printk(KERN_INFO "md: export_rdev(%s)\n",
 		bdevname(rdev->bdev,b));
-	if (rdev->mddev)
-		MD_BUG();
 	md_rdev_clear(rdev);
 #ifndef MODULE
 	if (test_bit(AutoDetected, &rdev->flags))
@@ -2192,7 +2150,7 @@ static void export_rdev(struct md_rdev * rdev)
 	kobject_put(&rdev->kobj);
 }
 
-static void kick_rdev_from_array(struct md_rdev * rdev)
+static void kick_rdev_from_array(struct md_rdev *rdev)
 {
 	unbind_rdev_from_array(rdev);
 	export_rdev(rdev);
@@ -2200,153 +2158,18 @@ static void kick_rdev_from_array(struct md_rdev * rdev)
 
 static void export_array(struct mddev *mddev)
 {
-	struct md_rdev *rdev, *tmp;
+	struct md_rdev *rdev;
 
-	rdev_for_each_safe(rdev, tmp, mddev) {
-		if (!rdev->mddev) {
-			MD_BUG();
-			continue;
-		}
+	while (!list_empty(&mddev->disks)) {
+		rdev = list_first_entry(&mddev->disks, struct md_rdev,
+					same_set);
 		kick_rdev_from_array(rdev);
 	}
-	if (!list_empty(&mddev->disks))
-		MD_BUG();
 	mddev->raid_disks = 0;
 	mddev->major_version = 0;
 }
 
-static void print_desc(mdp_disk_t *desc)
-{
-	printk(" DISK<N:%d,(%d,%d),R:%d,S:%d>\n", desc->number,
-		desc->major,desc->minor,desc->raid_disk,desc->state);
-}
-
-static void print_sb_90(mdp_super_t *sb)
-{
-	int i;
-
-	printk(KERN_INFO 
-		"md:  SB: (V:%d.%d.%d) ID:<%08x.%08x.%08x.%08x> CT:%08x\n",
-		sb->major_version, sb->minor_version, sb->patch_version,
-		sb->set_uuid0, sb->set_uuid1, sb->set_uuid2, sb->set_uuid3,
-		sb->ctime);
-	printk(KERN_INFO "md:     L%d S%08d ND:%d RD:%d md%d LO:%d CS:%d\n",
-		sb->level, sb->size, sb->nr_disks, sb->raid_disks,
-		sb->md_minor, sb->layout, sb->chunk_size);
-	printk(KERN_INFO "md:     UT:%08x ST:%d AD:%d WD:%d"
-		" FD:%d SD:%d CSUM:%08x E:%08lx\n",
-		sb->utime, sb->state, sb->active_disks, sb->working_disks,
-		sb->failed_disks, sb->spare_disks,
-		sb->sb_csum, (unsigned long)sb->events_lo);
-
-	printk(KERN_INFO);
-	for (i = 0; i < MD_SB_DISKS; i++) {
-		mdp_disk_t *desc;
-
-		desc = sb->disks + i;
-		if (desc->number || desc->major || desc->minor ||
-		    desc->raid_disk || (desc->state && (desc->state != 4))) {
-			printk("     D %2d: ", i);
-			print_desc(desc);
-		}
-	}
-	printk(KERN_INFO "md:     THIS: ");
-	print_desc(&sb->this_disk);
-}
-
-static void print_sb_1(struct mdp_superblock_1 *sb)
-{
-	__u8 *uuid;
-
-	uuid = sb->set_uuid;
-	printk(KERN_INFO
-	       "md:  SB: (V:%u) (F:0x%08x) Array-ID:<%pU>\n"
-	       "md:    Name: \"%s\" CT:%llu\n",
-		le32_to_cpu(sb->major_version),
-		le32_to_cpu(sb->feature_map),
-		uuid,
-		sb->set_name,
-		(unsigned long long)le64_to_cpu(sb->ctime)
-		       & MD_SUPERBLOCK_1_TIME_SEC_MASK);
-
-	uuid = sb->device_uuid;
-	printk(KERN_INFO
-	       "md:       L%u SZ%llu RD:%u LO:%u CS:%u DO:%llu DS:%llu SO:%llu"
-			" RO:%llu\n"
-	       "md:     Dev:%08x UUID: %pU\n"
-	       "md:       (F:0x%08x) UT:%llu Events:%llu ResyncOffset:%llu CSUM:0x%08x\n"
-	       "md:         (MaxDev:%u) \n",
-		le32_to_cpu(sb->level),
-		(unsigned long long)le64_to_cpu(sb->size),
-		le32_to_cpu(sb->raid_disks),
-		le32_to_cpu(sb->layout),
-		le32_to_cpu(sb->chunksize),
-		(unsigned long long)le64_to_cpu(sb->data_offset),
-		(unsigned long long)le64_to_cpu(sb->data_size),
-		(unsigned long long)le64_to_cpu(sb->super_offset),
-		(unsigned long long)le64_to_cpu(sb->recovery_offset),
-		le32_to_cpu(sb->dev_number),
-		uuid,
-		sb->devflags,
-		(unsigned long long)le64_to_cpu(sb->utime) & MD_SUPERBLOCK_1_TIME_SEC_MASK,
-		(unsigned long long)le64_to_cpu(sb->events),
-		(unsigned long long)le64_to_cpu(sb->resync_offset),
-		le32_to_cpu(sb->sb_csum),
-		le32_to_cpu(sb->max_dev)
-		);
-}
-
-static void print_rdev(struct md_rdev *rdev, int major_version)
-{
-	char b[BDEVNAME_SIZE];
-	printk(KERN_INFO "md: rdev %s, Sect:%08llu F:%d S:%d DN:%u\n",
-		bdevname(rdev->bdev, b), (unsigned long long)rdev->sectors,
-	        test_bit(Faulty, &rdev->flags), test_bit(In_sync, &rdev->flags),
-	        rdev->desc_nr);
-	if (rdev->sb_loaded) {
-		printk(KERN_INFO "md: rdev superblock (MJ:%d):\n", major_version);
-		switch (major_version) {
-		case 0:
-			print_sb_90(page_address(rdev->sb_page));
-			break;
-		case 1:
-			print_sb_1(page_address(rdev->sb_page));
-			break;
-		}
-	} else
-		printk(KERN_INFO "md: no rdev superblock!\n");
-}
-
-static void md_print_devices(void)
-{
-	struct list_head *tmp;
-	struct md_rdev *rdev;
-	struct mddev *mddev;
-	char b[BDEVNAME_SIZE];
-
-	printk("\n");
-	printk("md:	**********************************\n");
-	printk("md:	* <COMPLETE RAID STATE PRINTOUT> *\n");
-	printk("md:	**********************************\n");
-	for_each_mddev(mddev, tmp) {
-
-		if (mddev->bitmap)
-			bitmap_print_sb(mddev->bitmap);
-		else
-			printk("%s: ", mdname(mddev));
-		rdev_for_each(rdev, mddev)
-			printk("<%s>", bdevname(rdev->bdev,b));
-		printk("\n");
-
-		rdev_for_each(rdev, mddev)
-			print_rdev(rdev, mddev->major_version);
-	}
-	printk("md:	**********************************\n");
-	printk("\n");
-}
-
-
-static void sync_sbs(struct mddev * mddev, int nospares)
+static void sync_sbs(struct mddev *mddev, int nospares)
 {
 	/* Update each superblock (in-memory image), but
 	 * if we are allowed to, skip spares which already
@@ -2369,7 +2192,7 @@ static void sync_sbs(struct mddev * mddev, int nospares)
 	}
 }
 
-static void md_update_sb(struct mddev * mddev, int force_change)
+static void md_update_sb(struct mddev *mddev, int force_change)
 {
 	struct md_rdev *rdev;
 	int sync_req;
@@ -2390,7 +2213,7 @@ repeat:
 		    mddev->curr_resync_completed > rdev->recovery_offset)
 				rdev->recovery_offset = mddev->curr_resync_completed;
 
-	}	
+	}
 	if (!mddev->persistent) {
 		clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
 		clear_bit(MD_CHANGE_DEVS, &mddev->flags);
@@ -2453,15 +2276,12 @@ repeat:
 		mddev->can_decrease_events = nospares;
 	}
 
-	if (!mddev->events) {
-		/*
-		 * oops, this 64-bit counter should never wrap.
-		 * Either we are in around ~1 trillion A.C., assuming
-		 * 1 reboot per second, or we have a bug:
-		 */
-		MD_BUG();
-		mddev->events --;
-	}
+	/*
+	 * This 64-bit counter should never wrap.
+	 * Either we are in around ~1 trillion A.C., assuming
+	 * 1 reboot per second, or we have a bug...
+	 */
+	WARN_ON(mddev->events == 0);
 
 	rdev_for_each(rdev, mddev) {
 		if (rdev->badblocks.changed)
@@ -2668,10 +2488,12 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 		set_bit(In_sync, &rdev->flags);
 		err = 0;
 	} else if (cmd_match(buf, "-insync") && rdev->raid_disk >= 0) {
-		clear_bit(In_sync, &rdev->flags);
-		rdev->saved_raid_disk = rdev->raid_disk;
-		rdev->raid_disk = -1;
-		err = 0;
+		if (rdev->mddev->pers == NULL) {
+			clear_bit(In_sync, &rdev->flags);
+			rdev->saved_raid_disk = rdev->raid_disk;
+			rdev->raid_disk = -1;
+			err = 0;
+		}
 	} else if (cmd_match(buf, "write_error")) {
 		set_bit(WriteErrorSeen, &rdev->flags);
 		err = 0;
@@ -2829,7 +2651,6 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 	return len;
 }
 
-
 static struct rdev_sysfs_entry rdev_slot =
 __ATTR(slot, S_IRUGO|S_IWUSR, slot_show, slot_store);
 
@@ -2980,20 +2801,20 @@ rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len)
 
 	rdev->sectors = sectors;
 	if (sectors > oldsectors && my_mddev->external) {
-		/* need to check that all other rdevs with the same ->bdev
-		 * do not overlap.  We need to unlock the mddev to avoid
-		 * a deadlock.  We have already changed rdev->sectors, and if
-		 * we have to change it back, we will have the lock again.
+		/* Need to check that all other rdevs with the same
+		 * ->bdev do not overlap.  'rcu' is sufficient to walk
+		 * the rdev lists safely.
+		 * This check does not provide a hard guarantee, it
+		 * just helps avoid dangerous mistakes.
 		 */
 		struct mddev *mddev;
 		int overlap = 0;
 		struct list_head *tmp;
 
-		mddev_unlock(my_mddev);
+		rcu_read_lock();
 		for_each_mddev(mddev, tmp) {
 			struct md_rdev *rdev2;
 
-			mddev_lock_nointr(mddev);
 			rdev_for_each(rdev2, mddev)
 				if (rdev->bdev == rdev2->bdev &&
 				    rdev != rdev2 &&
@@ -3003,13 +2824,12 @@ rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len)
 					overlap = 1;
 					break;
 				}
-			mddev_unlock(mddev);
 			if (overlap) {
 				mddev_put(mddev);
 				break;
 			}
 		}
-		mddev_lock_nointr(my_mddev);
+		rcu_read_unlock();
 		if (overlap) {
 			/* Someone else could have slipped in a size
 			 * change here, but doing so is just silly.
@@ -3027,7 +2847,6 @@ rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len)
 static struct rdev_sysfs_entry rdev_size =
 __ATTR(size, S_IRUGO|S_IWUSR, rdev_size_show, rdev_size_store);
 
-
 static ssize_t recovery_start_show(struct md_rdev *rdev, char *page)
 {
 	unsigned long long recovery_start = rdev->recovery_offset;
@@ -3063,7 +2882,6 @@ static ssize_t recovery_start_store(struct md_rdev *rdev, const char *buf, size_
 static struct rdev_sysfs_entry rdev_recovery_start =
 __ATTR(recovery_start, S_IRUGO|S_IWUSR, recovery_start_show, recovery_start_store);
 
-
 static ssize_t
 badblocks_show(struct badblocks *bb, char *page, int unack);
 static ssize_t
@@ -3084,7 +2902,6 @@ static ssize_t bb_store(struct md_rdev *rdev, const char *page, size_t len)
 static struct rdev_sysfs_entry rdev_bad_blocks =
 __ATTR(bad_blocks, S_IRUGO|S_IWUSR, bb_show, bb_store);
 
-
 static ssize_t ubb_show(struct md_rdev *rdev, char *page)
 {
 	return badblocks_show(&rdev->badblocks, page, 1);
@@ -3241,7 +3058,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 
 	size = i_size_read(rdev->bdev->bd_inode) >> BLOCK_SIZE_BITS;
 	if (!size) {
-		printk(KERN_WARNING 
+		printk(KERN_WARNING
 			"md: %s has zero or unknown size, marking faulty!\n",
 			bdevname(rdev->bdev,b));
 		err = -EINVAL;
@@ -3260,7 +3077,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 			goto abort_free;
 		}
 		if (err < 0) {
-			printk(KERN_WARNING 
+			printk(KERN_WARNING
 				"md: could not read %s's sb, not importing!\n",
 				bdevname(rdev->bdev,b));
 			goto abort_free;
@@ -3281,8 +3098,7 @@ abort_free:
  * Check a full RAID array for plausibility
  */
 
-
-static void analyze_sbs(struct mddev * mddev)
+static void analyze_sbs(struct mddev *mddev)
 {
 	int i;
 	struct md_rdev *rdev, *freshest, *tmp;
@@ -3300,12 +3116,11 @@ static void analyze_sbs(struct mddev * mddev)
 		default:
 			printk( KERN_ERR \
 				"md: fatal superblock inconsistency in %s"
-				" -- removing from array\n", 
+				" -- removing from array\n",
 				bdevname(rdev->bdev,b));
 			kick_rdev_from_array(rdev);
 		}
 
-
 	super_types[mddev->major_version].
 		validate_super(mddev, freshest);
 
@@ -3344,7 +3159,7 @@ static void analyze_sbs(struct mddev * mddev)
 /* Read a fixed-point number.
  * Numbers in sysfs attributes should be in "standard" units where
  * possible, so time should be in seconds.
- * However we internally use a a much smaller unit such as 
+ * However we internally use a a much smaller unit such as
  * milliseconds or jiffies.
  * This function takes a decimal number with a possible fractional
  * component, and produces an integer which is the result of
@@ -3381,7 +3196,6 @@ int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale)
 	return 0;
 }
 
-
 static void md_safemode_timeout(unsigned long data);
 
 static ssize_t
@@ -3524,7 +3338,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	/* Looks like we have a winner */
 	mddev_suspend(mddev);
 	mddev->pers->stop(mddev);
-	
+
 	if (mddev->pers->sync_request == NULL &&
 	    pers->sync_request != NULL) {
 		/* need to add the md_redundancy_group */
@@ -3533,7 +3347,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 			       "md: cannot register extra attributes for %s\n",
 			       mdname(mddev));
 		mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action");
-	}		
+	}
 	if (mddev->pers->sync_request != NULL &&
 	    pers->sync_request == NULL) {
 		/* need to remove the md_redundancy_group */
@@ -3611,7 +3425,6 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 static struct md_sysfs_entry md_level =
 __ATTR(level, S_IRUGO|S_IWUSR, level_show, level_store);
 
-
 static ssize_t
 layout_show(struct mddev *mddev, char *page)
 {
@@ -3654,7 +3467,6 @@ layout_store(struct mddev *mddev, const char *buf, size_t len)
 static struct md_sysfs_entry md_layout =
 __ATTR(layout, S_IRUGO|S_IWUSR, layout_show, layout_store);
 
-
 static ssize_t
 raid_disks_show(struct mddev *mddev, char *page)
 {
@@ -3859,9 +3671,9 @@ array_state_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", array_states[st]);
 }
 
-static int do_md_stop(struct mddev * mddev, int ro, struct block_device *bdev);
-static int md_set_readonly(struct mddev * mddev, struct block_device *bdev);
-static int do_md_run(struct mddev * mddev);
+static int do_md_stop(struct mddev *mddev, int ro, struct block_device *bdev);
+static int md_set_readonly(struct mddev *mddev, struct block_device *bdev);
+static int do_md_run(struct mddev *mddev);
 static int restart_array(struct mddev *mddev);
 
 static ssize_t
@@ -4012,7 +3824,6 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
 	    minor != MINOR(dev))
 		return -EOVERFLOW;
 
-
 	if (mddev->persistent) {
 		rdev = md_import_device(dev, mddev->major_version,
 					mddev->minor_version);
@@ -4108,7 +3919,6 @@ size_store(struct mddev *mddev, const char *buf, size_t len)
 static struct md_sysfs_entry md_size =
 __ATTR(component_size, S_IRUGO|S_IWUSR, size_show, size_store);
 
-
 /* Metadata version.
  * This is one of
  *   'none' for arrays with no metadata (good luck...)
@@ -4490,7 +4300,7 @@ suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
 	unsigned long long new = simple_strtoull(buf, &e, 10);
 	unsigned long long old = mddev->suspend_lo;
 
-	if (mddev->pers == NULL || 
+	if (mddev->pers == NULL ||
 	    mddev->pers->quiesce == NULL)
 		return -EINVAL;
 	if (buf == e || (*e && *e != '\n'))
@@ -4510,7 +4320,6 @@ suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
 static struct md_sysfs_entry md_suspend_lo =
 __ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store);
 
-
 static ssize_t
 suspend_hi_show(struct mddev *mddev, char *page)
 {
@@ -4698,7 +4507,6 @@ static struct attribute_group md_redundancy_group = {
 	.attrs = md_redundancy_attrs,
 };
 
-
 static ssize_t
 md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 {
@@ -5111,7 +4919,7 @@ int md_run(struct mddev *mddev)
 	} else if (mddev->ro == 2) /* auto-readonly not meaningful */
 		mddev->ro = 0;
 
- 	atomic_set(&mddev->writes_pending,0);
+	atomic_set(&mddev->writes_pending,0);
 	atomic_set(&mddev->max_corr_read_errors,
 		   MD_DEFAULT_MAX_CORRECTED_READ_ERRORS);
 	mddev->safemode = 0;
@@ -5125,9 +4933,9 @@ int md_run(struct mddev *mddev)
 		if (rdev->raid_disk >= 0)
 			if (sysfs_link_rdev(mddev, rdev))
 				/* failure here is OK */;
-	
+
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	
+
 	if (mddev->flags & MD_UPDATE_SB_FLAGS)
 		md_update_sb(mddev, 0);
 
@@ -5307,7 +5115,7 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 	mddev_lock_nointr(mddev);
 
 	mutex_lock(&mddev->open_mutex);
-	if (atomic_read(&mddev->openers) > !!bdev ||
+	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
 	    mddev->sync_thread ||
 	    (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags))) {
 		printk("md: %s still in use.\n",mdname(mddev));
@@ -5339,7 +5147,7 @@ out:
  *   0 - completely stop and dis-assemble array
  *   2 - stop but do not disassemble array
  */
-static int do_md_stop(struct mddev * mddev, int mode,
+static int do_md_stop(struct mddev *mddev, int mode,
 		      struct block_device *bdev)
 {
 	struct gendisk *disk = mddev->gendisk;
@@ -5362,7 +5170,7 @@ static int do_md_stop(struct mddev * mddev, int mode,
 	mddev_lock_nointr(mddev);
 
 	mutex_lock(&mddev->open_mutex);
-	if (atomic_read(&mddev->openers) > !!bdev ||
+	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
 	    mddev->sysfs_active ||
 	    mddev->sync_thread ||
 	    (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags))) {
@@ -5512,12 +5320,12 @@ static void autorun_devices(int part)
 				"md: cannot allocate memory for md drive.\n");
 			break;
 		}
-		if (mddev_lock(mddev)) 
+		if (mddev_lock(mddev))
 			printk(KERN_WARNING "md: %s locked, cannot run\n",
 			       mdname(mddev));
 		else if (mddev->raid_disks || mddev->major_version
 			 || !list_empty(&mddev->disks)) {
-			printk(KERN_WARNING 
+			printk(KERN_WARNING
 				"md: %s already running, cannot run %s\n",
 				mdname(mddev), bdevname(rdev0->bdev,b));
 			mddev_unlock(mddev);
@@ -5545,7 +5353,7 @@ static void autorun_devices(int part)
 }
 #endif /* !MODULE */
 
-static int get_version(void __user * arg)
+static int get_version(void __user *arg)
 {
 	mdu_version_t ver;
 
@@ -5559,7 +5367,7 @@ static int get_version(void __user * arg)
 	return 0;
 }
 
-static int get_array_info(struct mddev * mddev, void __user * arg)
+static int get_array_info(struct mddev *mddev, void __user *arg)
 {
 	mdu_array_info_t info;
 	int nr,working,insync,failed,spare;
@@ -5574,7 +5382,7 @@ static int get_array_info(struct mddev * mddev, void __user * arg)
 		else {
 			working++;
 			if (test_bit(In_sync, &rdev->flags))
-				insync++;	
+				insync++;
 			else
 				spare++;
 		}
@@ -5614,7 +5422,7 @@ static int get_array_info(struct mddev * mddev, void __user * arg)
 	return 0;
 }
 
-static int get_bitmap_file(struct mddev * mddev, void __user * arg)
+static int get_bitmap_file(struct mddev *mddev, void __user * arg)
 {
 	mdu_bitmap_file_t *file = NULL; /* too big for stack allocation */
 	char *ptr, *buf = NULL;
@@ -5652,7 +5460,7 @@ out:
 	return err;
 }
 
-static int get_disk_info(struct mddev * mddev, void __user * arg)
+static int get_disk_info(struct mddev *mddev, void __user * arg)
 {
 	mdu_disk_info_t info;
 	struct md_rdev *rdev;
@@ -5688,7 +5496,7 @@ static int get_disk_info(struct mddev * mddev, void __user * arg)
 	return 0;
 }
 
-static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
+static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info)
 {
 	char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
 	struct md_rdev *rdev;
@@ -5702,7 +5510,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
 		/* expecting a device which has a superblock */
 		rdev = md_import_device(dev, mddev->major_version, mddev->minor_version);
 		if (IS_ERR(rdev)) {
-			printk(KERN_WARNING 
+			printk(KERN_WARNING
 				"md: md_import_device returned %ld\n",
 				PTR_ERR(rdev));
 			return PTR_ERR(rdev);
@@ -5714,9 +5522,9 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
 			err = super_types[mddev->major_version]
 				.load_super(rdev, rdev0, mddev->minor_version);
 			if (err < 0) {
-				printk(KERN_WARNING 
+				printk(KERN_WARNING
 					"md: %s has different UUID to %s\n",
-					bdevname(rdev->bdev,b), 
+					bdevname(rdev->bdev,b),
 					bdevname(rdev0->bdev,b2));
 				export_rdev(rdev);
 				return -EINVAL;
@@ -5736,7 +5544,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
 	if (mddev->pers) {
 		int err;
 		if (!mddev->pers->hot_add_disk) {
-			printk(KERN_WARNING 
+			printk(KERN_WARNING
 				"%s: personality does not support diskops!\n",
 			       mdname(mddev));
 			return -EINVAL;
@@ -5747,7 +5555,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
 		else
 			rdev = md_import_device(dev, -1, -1);
 		if (IS_ERR(rdev)) {
-			printk(KERN_WARNING 
+			printk(KERN_WARNING
 				"md: md_import_device returned %ld\n",
 				PTR_ERR(rdev));
 			return PTR_ERR(rdev);
@@ -5821,7 +5629,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
 		int err;
 		rdev = md_import_device(dev, -1, 0);
 		if (IS_ERR(rdev)) {
-			printk(KERN_WARNING 
+			printk(KERN_WARNING
 				"md: error, md_import_device() returned %ld\n",
 				PTR_ERR(rdev));
 			return PTR_ERR(rdev);
@@ -5856,7 +5664,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
 	return 0;
 }
 
-static int hot_remove_disk(struct mddev * mddev, dev_t dev)
+static int hot_remove_disk(struct mddev *mddev, dev_t dev)
 {
 	char b[BDEVNAME_SIZE];
 	struct md_rdev *rdev;
@@ -5882,7 +5690,7 @@ busy:
 	return -EBUSY;
 }
 
-static int hot_add_disk(struct mddev * mddev, dev_t dev)
+static int hot_add_disk(struct mddev *mddev, dev_t dev)
 {
 	char b[BDEVNAME_SIZE];
 	int err;
@@ -5898,7 +5706,7 @@ static int hot_add_disk(struct mddev * mddev, dev_t dev)
 		return -EINVAL;
 	}
 	if (!mddev->pers->hot_add_disk) {
-		printk(KERN_WARNING 
+		printk(KERN_WARNING
 			"%s: personality does not support diskops!\n",
 			mdname(mddev));
 		return -EINVAL;
@@ -5906,7 +5714,7 @@ static int hot_add_disk(struct mddev * mddev, dev_t dev)
 
 	rdev = md_import_device(dev, -1, 0);
 	if (IS_ERR(rdev)) {
-		printk(KERN_WARNING 
+		printk(KERN_WARNING
 			"md: error, md_import_device() returned %ld\n",
 			PTR_ERR(rdev));
 		return -EINVAL;
@@ -5920,7 +5728,7 @@ static int hot_add_disk(struct mddev * mddev, dev_t dev)
 	rdev->sectors = rdev->sb_start;
 
 	if (test_bit(Faulty, &rdev->flags)) {
-		printk(KERN_WARNING 
+		printk(KERN_WARNING
 			"md: can not hot-add faulty %s disk to %s!\n",
 			bdevname(rdev->bdev,b), mdname(mddev));
 		err = -EINVAL;
@@ -5968,7 +5776,6 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
 		/* we should be able to change the bitmap.. */
 	}
 
-
 	if (fd >= 0) {
 		struct inode *inode;
 		if (mddev->bitmap)
@@ -6039,7 +5846,7 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
  *  The minor and patch _version numbers are also kept incase the
  *  super_block handler wishes to interpret them.
  */
-static int set_array_info(struct mddev * mddev, mdu_array_info_t *info)
+static int set_array_info(struct mddev *mddev, mdu_array_info_t *info)
 {
 
 	if (info->raid_disks == 0) {
@@ -6048,7 +5855,7 @@ static int set_array_info(struct mddev * mddev, mdu_array_info_t *info)
 		    info->major_version >= ARRAY_SIZE(super_types) ||
 		    super_types[info->major_version].name == NULL) {
 			/* maybe try to auto-load a module? */
-			printk(KERN_INFO 
+			printk(KERN_INFO
 				"md: superblock version %d not known\n",
 				info->major_version);
 			return -EINVAL;
@@ -6196,7 +6003,6 @@ static int update_raid_disks(struct mddev *mddev, int raid_disks)
 	return rv;
 }
 
-
 /*
  * update_array_info is used to change the configuration of an
  * on-line array.
@@ -6347,7 +6153,6 @@ static inline bool md_ioctl_valid(unsigned int cmd)
 	case GET_DISK_INFO:
 	case HOT_ADD_DISK:
 	case HOT_REMOVE_DISK:
-	case PRINT_RAID_DEBUG:
 	case RAID_AUTORUN:
 	case RAID_VERSION:
 	case RESTART_ARRAY_RW:
@@ -6391,18 +6196,13 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	switch (cmd) {
 	case RAID_VERSION:
 		err = get_version(argp);
-		goto done;
-
-	case PRINT_RAID_DEBUG:
-		err = 0;
-		md_print_devices();
-		goto done;
+		goto out;
 
 #ifndef MODULE
 	case RAID_AUTORUN:
 		err = 0;
 		autostart_arrays(arg);
-		goto done;
+		goto out;
 #endif
 	default:;
 	}
@@ -6415,7 +6215,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 
 	if (!mddev) {
 		BUG();
-		goto abort;
+		goto out;
 	}
 
 	/* Some actions do not requires the mutex */
@@ -6425,18 +6225,18 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			err = -ENODEV;
 		else
 			err = get_array_info(mddev, argp);
-		goto abort;
+		goto out;
 
 	case GET_DISK_INFO:
 		if (!mddev->raid_disks && !mddev->external)
 			err = -ENODEV;
 		else
 			err = get_disk_info(mddev, argp);
-		goto abort;
+		goto out;
 
 	case SET_DISK_FAULTY:
 		err = set_disk_faulty(mddev, new_decode_dev(arg));
-		goto abort;
+		goto out;
 	}
 
 	if (cmd == ADD_NEW_DISK)
@@ -6454,10 +6254,10 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 		 * and writes
 		 */
 		mutex_lock(&mddev->open_mutex);
-		if (atomic_read(&mddev->openers) > 1) {
+		if (mddev->pers && atomic_read(&mddev->openers) > 1) {
 			mutex_unlock(&mddev->open_mutex);
 			err = -EBUSY;
-			goto abort;
+			goto out;
 		}
 		set_bit(MD_STILL_CLOSED, &mddev->flags);
 		mutex_unlock(&mddev->open_mutex);
@@ -6465,10 +6265,10 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	}
 	err = mddev_lock(mddev);
 	if (err) {
-		printk(KERN_INFO 
+		printk(KERN_INFO
 			"md: ioctl lock interrupted, reason %d, cmd %d\n",
 			err, cmd);
-		goto abort;
+		goto out;
 	}
 
 	if (cmd == SET_ARRAY_INFO) {
@@ -6477,38 +6277,38 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			memset(&info, 0, sizeof(info));
 		else if (copy_from_user(&info, argp, sizeof(info))) {
 			err = -EFAULT;
-			goto abort_unlock;
+			goto unlock;
 		}
 		if (mddev->pers) {
 			err = update_array_info(mddev, &info);
 			if (err) {
 				printk(KERN_WARNING "md: couldn't update"
 				       " array info. %d\n", err);
-				goto abort_unlock;
+				goto unlock;
 			}
-			goto done_unlock;
+			goto unlock;
 		}
 		if (!list_empty(&mddev->disks)) {
 			printk(KERN_WARNING
 			       "md: array %s already has disks!\n",
 			       mdname(mddev));
 			err = -EBUSY;
-			goto abort_unlock;
+			goto unlock;
 		}
 		if (mddev->raid_disks) {
 			printk(KERN_WARNING
 			       "md: array %s already initialised!\n",
 			       mdname(mddev));
 			err = -EBUSY;
-			goto abort_unlock;
+			goto unlock;
 		}
 		err = set_array_info(mddev, &info);
 		if (err) {
 			printk(KERN_WARNING "md: couldn't set"
 			       " array info. %d\n", err);
-			goto abort_unlock;
+			goto unlock;
 		}
-		goto done_unlock;
+		goto unlock;
 	}
 
 	/*
@@ -6521,7 +6321,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	    && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE
 	    && cmd != GET_BITMAP_FILE) {
 		err = -ENODEV;
-		goto abort_unlock;
+		goto unlock;
 	}
 
 	/*
@@ -6530,23 +6330,23 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 	switch (cmd) {
 	case GET_BITMAP_FILE:
 		err = get_bitmap_file(mddev, argp);
-		goto done_unlock;
+		goto unlock;
 
 	case RESTART_ARRAY_RW:
 		err = restart_array(mddev);
-		goto done_unlock;
+		goto unlock;
 
 	case STOP_ARRAY:
 		err = do_md_stop(mddev, 0, bdev);
-		goto done_unlock;
+		goto unlock;
 
 	case STOP_ARRAY_RO:
 		err = md_set_readonly(mddev, bdev);
-		goto done_unlock;
+		goto unlock;
 
 	case HOT_REMOVE_DISK:
 		err = hot_remove_disk(mddev, new_decode_dev(arg));
-		goto done_unlock;
+		goto unlock;
 
 	case ADD_NEW_DISK:
 		/* We can support ADD_NEW_DISK on read-only arrays
@@ -6562,14 +6362,14 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 				break;
 			else
 				err = add_new_disk(mddev, &info);
-			goto done_unlock;
+			goto unlock;
 		}
 		break;
 
 	case BLKROSET:
 		if (get_user(ro, (int __user *)(arg))) {
 			err = -EFAULT;
-			goto done_unlock;
+			goto unlock;
 		}
 		err = -EINVAL;
 
@@ -6577,11 +6377,11 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 		 * does not matter, no writes are coming
 		 */
 		if (ro)
-			goto done_unlock;
+			goto unlock;
 
 		/* are we are already prepared for writes? */
 		if (mddev->ro != 1)
-			goto done_unlock;
+			goto unlock;
 
 		/* transitioning to readauto need only happen for
 		 * arrays that call md_write_start
@@ -6593,17 +6393,14 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 				set_disk_ro(mddev->gendisk, 0);
 			}
 		}
-		goto done_unlock;
+		goto unlock;
 	}
 
 	/*
 	 * The remaining ioctls are changing the state of the
 	 * superblock, so we do not allow them on read-only arrays.
-	 * However non-MD ioctls (e.g. get-size) will still come through
-	 * here and hit the 'default' below, so only disallow
-	 * 'md' ioctls, and switch to rw mode if started auto-readonly.
 	 */
-	if (_IOC_TYPE(cmd) == MD_MAJOR && mddev->ro && mddev->pers) {
+	if (mddev->ro && mddev->pers) {
 		if (mddev->ro == 2) {
 			mddev->ro = 0;
 			sysfs_notify_dirent_safe(mddev->sysfs_state);
@@ -6621,7 +6418,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			}
 		} else {
 			err = -EROFS;
-			goto abort_unlock;
+			goto unlock;
 		}
 	}
 
@@ -6633,38 +6430,32 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			err = -EFAULT;
 		else
 			err = add_new_disk(mddev, &info);
-		goto done_unlock;
+		goto unlock;
 	}
 
 	case HOT_ADD_DISK:
 		err = hot_add_disk(mddev, new_decode_dev(arg));
-		goto done_unlock;
+		goto unlock;
 
 	case RUN_ARRAY:
 		err = do_md_run(mddev);
-		goto done_unlock;
+		goto unlock;
 
 	case SET_BITMAP_FILE:
 		err = set_bitmap_file(mddev, (int)arg);
-		goto done_unlock;
+		goto unlock;
 
 	default:
 		err = -EINVAL;
-		goto abort_unlock;
+		goto unlock;
 	}
 
-done_unlock:
-abort_unlock:
+unlock:
 	if (mddev->hold_active == UNTIL_IOCTL &&
 	    err != -EINVAL)
 		mddev->hold_active = 0;
 	mddev_unlock(mddev);
-
-	return err;
-done:
-	if (err)
-		MD_BUG();
-abort:
+out:
 	return err;
 }
 #ifdef CONFIG_COMPAT
@@ -6726,7 +6517,7 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 
 static void md_release(struct gendisk *disk, fmode_t mode)
 {
- 	struct mddev *mddev = disk->private_data;
+	struct mddev *mddev = disk->private_data;
 
 	BUG_ON(!mddev);
 	atomic_dec(&mddev->openers);
@@ -6761,7 +6552,7 @@ static const struct block_device_operations md_fops =
 	.revalidate_disk= md_revalidate,
 };
 
-static int md_thread(void * arg)
+static int md_thread(void *arg)
 {
 	struct md_thread *thread = arg;
 
@@ -6810,6 +6601,7 @@ void md_wakeup_thread(struct md_thread *thread)
 		wake_up(&thread->wqueue);
 	}
 }
+EXPORT_SYMBOL(md_wakeup_thread);
 
 struct md_thread *md_register_thread(void (*run) (struct md_thread *),
 		struct mddev *mddev, const char *name)
@@ -6835,6 +6627,7 @@ struct md_thread *md_register_thread(void (*run) (struct md_thread *),
 	}
 	return thread;
 }
+EXPORT_SYMBOL(md_register_thread);
 
 void md_unregister_thread(struct md_thread **threadp)
 {
@@ -6852,14 +6645,10 @@ void md_unregister_thread(struct md_thread **threadp)
 	kthread_stop(thread->tsk);
 	kfree(thread);
 }
+EXPORT_SYMBOL(md_unregister_thread);
 
 void md_error(struct mddev *mddev, struct md_rdev *rdev)
 {
-	if (!mddev) {
-		MD_BUG();
-		return;
-	}
-
 	if (!rdev || test_bit(Faulty, &rdev->flags))
 		return;
 
@@ -6876,6 +6665,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
 		queue_work(md_misc_wq, &mddev->event_work);
 	md_new_event_inintr(mddev);
 }
+EXPORT_SYMBOL(md_error);
 
 /* seq_file implementation /proc/mdstat */
 
@@ -6898,8 +6688,7 @@ static void status_unused(struct seq_file *seq)
 	seq_printf(seq, "\n");
 }
 
-
-static void status_resync(struct seq_file *seq, struct mddev * mddev)
+static void status_resync(struct seq_file *seq, struct mddev *mddev)
 {
 	sector_t max_sectors, resync, res;
 	unsigned long dt, db;
@@ -6919,13 +6708,7 @@ static void status_resync(struct seq_file *seq, struct mddev * mddev)
 	else
 		max_sectors = mddev->dev_sectors;
 
-	/*
-	 * Should not happen.
-	 */
-	if (!max_sectors) {
-		MD_BUG();
-		return;
-	}
+	WARN_ON(max_sectors == 0);
 	/* Pick 'scale' such that (resync>>scale)*1000 will fit
 	 * in a sector_t, and (max_sectors>>scale) will fit in a
 	 * u32, as those are the requirements for sector_div.
@@ -7021,7 +6804,7 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct list_head *tmp;
 	struct mddev *next_mddev, *mddev = v;
-	
+
 	++*pos;
 	if (v == (void*)2)
 		return NULL;
@@ -7036,7 +6819,7 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	else {
 		next_mddev = (void*)2;
 		*pos = 0x10000;
-	}		
+	}
 	spin_unlock(&all_mddevs_lock);
 
 	if (v != (void*)1)
@@ -7132,7 +6915,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 
 		if (mddev->pers) {
 			mddev->pers->status(seq, mddev);
-	 		seq_printf(seq, "\n      ");
+			seq_printf(seq, "\n      ");
 			if (mddev->pers->sync_request) {
 				if (mddev->curr_resync > 2) {
 					status_resync(seq, mddev);
@@ -7150,7 +6933,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq, "\n");
 	}
 	mddev_unlock(mddev);
-	
+
 	return 0;
 }
 
@@ -7204,12 +6987,14 @@ static const struct file_operations md_seq_fops = {
 
 int register_md_personality(struct md_personality *p)
 {
+	printk(KERN_INFO "md: %s personality registered for level %d\n",
+						p->name, p->level);
 	spin_lock(&pers_lock);
 	list_add_tail(&p->list, &pers_list);
-	printk(KERN_INFO "md: %s personality registered for level %d\n", p->name, p->level);
 	spin_unlock(&pers_lock);
 	return 0;
 }
+EXPORT_SYMBOL(register_md_personality);
 
 int unregister_md_personality(struct md_personality *p)
 {
@@ -7219,10 +7004,11 @@ int unregister_md_personality(struct md_personality *p)
 	spin_unlock(&pers_lock);
 	return 0;
 }
+EXPORT_SYMBOL(unregister_md_personality);
 
 static int is_mddev_idle(struct mddev *mddev, int init)
 {
-	struct md_rdev * rdev;
+	struct md_rdev *rdev;
 	int idle;
 	int curr_events;
 
@@ -7276,7 +7062,7 @@ void md_done_sync(struct mddev *mddev, int blocks, int ok)
 		// stop recovery, signal do_sync ....
 	}
 }
-
+EXPORT_SYMBOL(md_done_sync);
 
 /* md_write_start(mddev, bi)
  * If we need to update some array metadata (e.g. 'active' flag
@@ -7317,6 +7103,7 @@ void md_write_start(struct mddev *mddev, struct bio *bi)
 	wait_event(mddev->sb_wait,
 		   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
 }
+EXPORT_SYMBOL(md_write_start);
 
 void md_write_end(struct mddev *mddev)
 {
@@ -7327,6 +7114,7 @@ void md_write_end(struct mddev *mddev)
 			mod_timer(&mddev->safemode_timer, jiffies + mddev->safemode_delay);
 	}
 }
+EXPORT_SYMBOL(md_write_end);
 
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes
@@ -7784,6 +7572,33 @@ no_add:
 	return spares;
 }
 
+static void md_start_sync(struct work_struct *ws)
+{
+	struct mddev *mddev = container_of(ws, struct mddev, del_work);
+
+	mddev->sync_thread = md_register_thread(md_do_sync,
+						mddev,
+						"resync");
+	if (!mddev->sync_thread) {
+		printk(KERN_ERR "%s: could not start resync"
+		       " thread...\n",
+		       mdname(mddev));
+		/* leave the spares where they are, it shouldn't hurt */
+		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+		clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+		clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+		clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+		if (test_and_clear_bit(MD_RECOVERY_RECOVER,
+				       &mddev->recovery))
+			if (mddev->sysfs_action)
+				sysfs_notify_dirent_safe(mddev->sysfs_action);
+	} else
+		md_wakeup_thread(mddev->sync_thread);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
+	md_new_event(mddev);
+}
+
 /*
  * This routine is regularly called by all per-raid-array threads to
  * deal with generic issues like resync and super-block update.
@@ -7900,7 +7715,7 @@ void md_check_recovery(struct mddev *mddev)
 
 		if (!test_and_clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
 		    test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
-			goto unlock;
+			goto not_running;
 		/* no recovery is running.
 		 * remove any failed drives, then
 		 * add spares if possible.
@@ -7912,7 +7727,7 @@ void md_check_recovery(struct mddev *mddev)
 			if (mddev->pers->check_reshape == NULL ||
 			    mddev->pers->check_reshape(mddev) != 0)
 				/* Cannot proceed */
-				goto unlock;
+				goto not_running;
 			set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		} else if ((spares = remove_and_add_spares(mddev, NULL))) {
@@ -7925,7 +7740,7 @@ void md_check_recovery(struct mddev *mddev)
 			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		} else if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
 			/* nothing to be done ... */
-			goto unlock;
+			goto not_running;
 
 		if (mddev->pers->sync_request) {
 			if (spares) {
@@ -7935,27 +7750,11 @@ void md_check_recovery(struct mddev *mddev)
 				 */
 				bitmap_write_all(mddev->bitmap);
 			}
-			mddev->sync_thread = md_register_thread(md_do_sync,
-								mddev,
-								"resync");
-			if (!mddev->sync_thread) {
-				printk(KERN_ERR "%s: could not start resync"
-					" thread...\n", 
-					mdname(mddev));
-				/* leave the spares where they are, it shouldn't hurt */
-				clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-				clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
-				clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-				clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
-				clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-			} else
-				md_wakeup_thread(mddev->sync_thread);
-			sysfs_notify_dirent_safe(mddev->sysfs_action);
-			md_new_event(mddev);
+			INIT_WORK(&mddev->del_work, md_start_sync);
+			queue_work(md_misc_wq, &mddev->del_work);
+			goto unlock;
 		}
-	unlock:
-		wake_up(&mddev->sb_wait);
-
+	not_running:
 		if (!mddev->sync_thread) {
 			clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 			if (test_and_clear_bit(MD_RECOVERY_RECOVER,
@@ -7963,9 +7762,12 @@ void md_check_recovery(struct mddev *mddev)
 				if (mddev->sysfs_action)
 					sysfs_notify_dirent_safe(mddev->sysfs_action);
 		}
+	unlock:
+		wake_up(&mddev->sb_wait);
 		mddev_unlock(mddev);
 	}
 }
+EXPORT_SYMBOL(md_check_recovery);
 
 void md_reap_sync_thread(struct mddev *mddev)
 {
@@ -8008,6 +7810,7 @@ void md_reap_sync_thread(struct mddev *mddev)
 	if (mddev->event_work.func)
 		queue_work(md_misc_wq, &mddev->event_work);
 }
+EXPORT_SYMBOL(md_reap_sync_thread);
 
 void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev)
 {
@@ -8641,7 +8444,6 @@ void md_autodetect_dev(dev_t dev)
 	}
 }
 
-
 static void autostart_arrays(int part)
 {
 	struct md_rdev *rdev;
@@ -8665,10 +8467,9 @@ static void autostart_arrays(int part)
 		if (IS_ERR(rdev))
 			continue;
 
-		if (test_bit(Faulty, &rdev->flags)) {
-			MD_BUG();
+		if (test_bit(Faulty, &rdev->flags))
 			continue;
-		}
+
 		set_bit(AutoDetected, &rdev->flags);
 		list_add(&rdev->same_set, &pending_raid_disks);
 		i_passed++;
@@ -8736,20 +8537,8 @@ static int set_ro(const char *val, struct kernel_param *kp)
 
 module_param_call(start_ro, set_ro, get_ro, NULL, S_IRUSR|S_IWUSR);
 module_param(start_dirty_degraded, int, S_IRUGO|S_IWUSR);
-
 module_param_call(new_array, add_named_array, NULL, NULL, S_IWUSR);
 
-EXPORT_SYMBOL(register_md_personality);
-EXPORT_SYMBOL(unregister_md_personality);
-EXPORT_SYMBOL(md_error);
-EXPORT_SYMBOL(md_done_sync);
-EXPORT_SYMBOL(md_write_start);
-EXPORT_SYMBOL(md_write_end);
-EXPORT_SYMBOL(md_register_thread);
-EXPORT_SYMBOL(md_unregister_thread);
-EXPORT_SYMBOL(md_wakeup_thread);
-EXPORT_SYMBOL(md_check_recovery);
-EXPORT_SYMBOL(md_reap_sync_thread);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD RAID framework");
 MODULE_ALIAS("md");
diff --git a/drivers/md/md.h b/drivers/md/md.h
index a49d991f3fe1..03cec5bdcaae 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -1,15 +1,15 @@
 /*
    md.h : kernel internal structure of the Linux MD driver
           Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman
-	  
+
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2, or (at your option)
    any later version.
-   
+
    You should have received a copy of the GNU General Public License
    (for example /usr/src/linux/COPYING); if not, write to the Free
-   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
+   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
 
 #ifndef _MD_MD_H
@@ -56,7 +56,7 @@ struct md_rdev {
 	__u64		sb_events;
 	sector_t	data_offset;	/* start of data in array */
 	sector_t	new_data_offset;/* only relevant while reshaping */
-	sector_t 	sb_start;	/* offset of the super block (in 512byte sectors) */
+	sector_t	sb_start;	/* offset of the super block (in 512byte sectors) */
 	int		sb_size;	/* bytes in the superblock */
 	int		preferred_minor;	/* autorun support */
 
@@ -239,7 +239,7 @@ struct mddev {
 					minor_version,
 					patch_version;
 	int				persistent;
-	int 				external;	/* metadata is
+	int				external;	/* metadata is
 							 * managed externally */
 	char				metadata_type[17]; /* externally set*/
 	int				chunk_sectors;
@@ -248,7 +248,7 @@ struct mddev {
 	char				clevel[16];
 	int				raid_disks;
 	int				max_disks;
-	sector_t			dev_sectors; 	/* used size of
+	sector_t			dev_sectors;	/* used size of
 							 * component devices */
 	sector_t			array_sectors; /* exported array size */
 	int				external_size; /* size managed
@@ -312,7 +312,7 @@ struct mddev {
 	int				parallel_resync;
 
 	int				ok_start_degraded;
-	/* recovery/resync flags 
+	/* recovery/resync flags
 	 * NEEDED:   we might need to start a resync/recover
 	 * RUNNING:  a thread is running, or about to be started
 	 * SYNC:     actually doing a resync, not a recovery
@@ -392,20 +392,20 @@ struct mddev {
 
 	unsigned int			safemode;	/* if set, update "clean" superblock
 							 * when no writes pending.
-							 */ 
+							 */
 	unsigned int			safemode_delay;
 	struct timer_list		safemode_timer;
-	atomic_t			writes_pending; 
+	atomic_t			writes_pending;
 	struct request_queue		*queue;	/* for plugging ... */
 
-	struct bitmap                   *bitmap; /* the bitmap for the device */
+	struct bitmap			*bitmap; /* the bitmap for the device */
 	struct {
 		struct file		*file; /* the bitmap file */
 		loff_t			offset; /* offset from superblock of
 						 * start of bitmap. May be
 						 * negative, but not '0'
 						 * For external metadata, offset
-						 * from start of device. 
+						 * from start of device.
 						 */
 		unsigned long		space; /* space available at this offset */
 		loff_t			default_offset; /* this is the offset to use when
@@ -421,7 +421,7 @@ struct mddev {
 		int			external;
 	} bitmap_info;
 
-	atomic_t 			max_corr_read_errors; /* max read retries */
+	atomic_t			max_corr_read_errors; /* max read retries */
 	struct list_head		all_mddevs;
 
 	struct attribute_group		*to_remove;
@@ -439,7 +439,6 @@ struct mddev {
 	void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev);
 };
 
-
 static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
 {
 	int faulty = test_bit(Faulty, &rdev->flags);
@@ -449,7 +448,7 @@ static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
 
 static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors)
 {
-        atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io);
+	atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io);
 }
 
 struct md_personality
@@ -463,7 +462,7 @@ struct md_personality
 	int (*stop)(struct mddev *mddev);
 	void (*status)(struct seq_file *seq, struct mddev *mddev);
 	/* error_handler must set ->faulty and clear ->in_sync
-	 * if appropriate, and should abort recovery if needed 
+	 * if appropriate, and should abort recovery if needed
 	 */
 	void (*error_handler)(struct mddev *mddev, struct md_rdev *rdev);
 	int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev);
@@ -493,7 +492,6 @@ struct md_personality
 	void *(*takeover) (struct mddev *mddev);
 };
 
-
 struct md_sysfs_entry {
 	struct attribute attr;
 	ssize_t (*show)(struct mddev *, char *);
@@ -560,7 +558,7 @@ struct md_thread {
 	void			(*run) (struct md_thread *thread);
 	struct mddev		*mddev;
 	wait_queue_head_t	wqueue;
-	unsigned long           flags;
+	unsigned long		flags;
 	struct task_struct	*tsk;
 	unsigned long		timeout;
 	void			*private;
@@ -594,7 +592,7 @@ extern void md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 			   sector_t sector, int size, struct page *page);
 extern void md_super_wait(struct mddev *mddev);
-extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, 
+extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
 			struct page *page, int rw, bool metadata_op);
 extern void md_do_sync(struct md_thread *thread);
 extern void md_new_event(struct mddev *mddev);
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 849ad39f547b..399272f9c042 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -31,13 +31,12 @@
 
 #define	NR_RESERVED_BUFS	32
 
-
 static int multipath_map (struct mpconf *conf)
 {
 	int i, disks = conf->raid_disks;
 
 	/*
-	 * Later we do read balancing on the read side 
+	 * Later we do read balancing on the read side
 	 * now we use the first available disk.
 	 */
 
@@ -68,7 +67,6 @@ static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
 	md_wakeup_thread(mddev->thread);
 }
 
-
 /*
  * multipath_end_bh_io() is called when we have finished servicing a multipathed
  * operation and are ready to return a success/failure code to the buffer
@@ -98,8 +96,8 @@ static void multipath_end_request(struct bio *bio, int error)
 		 */
 		char b[BDEVNAME_SIZE];
 		md_error (mp_bh->mddev, rdev);
-		printk(KERN_ERR "multipath: %s: rescheduling sector %llu\n", 
-		       bdevname(rdev->bdev,b), 
+		printk(KERN_ERR "multipath: %s: rescheduling sector %llu\n",
+		       bdevname(rdev->bdev,b),
 		       (unsigned long long)bio->bi_iter.bi_sector);
 		multipath_reschedule_retry(mp_bh);
 	} else
@@ -145,12 +143,12 @@ static void multipath_status (struct seq_file *seq, struct mddev *mddev)
 {
 	struct mpconf *conf = mddev->private;
 	int i;
-	
+
 	seq_printf (seq, " [%d/%d] [", conf->raid_disks,
 		    conf->raid_disks - mddev->degraded);
 	for (i = 0; i < conf->raid_disks; i++)
 		seq_printf (seq, "%s",
-			       conf->multipaths[i].rdev && 
+			       conf->multipaths[i].rdev &&
 			       test_bit(In_sync, &conf->multipaths[i].rdev->flags) ? "U" : "_");
 	seq_printf (seq, "]");
 }
@@ -195,7 +193,7 @@ static void multipath_error (struct mddev *mddev, struct md_rdev *rdev)
 		 * first check if this is a queued request for a device
 		 * which has just failed.
 		 */
-		printk(KERN_ALERT 
+		printk(KERN_ALERT
 		       "multipath: only one IO path left and IO error.\n");
 		/* leave it active... it's all we have */
 		return;
@@ -242,7 +240,6 @@ static void print_multipath_conf (struct mpconf *conf)
 	}
 }
 
-
 static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct mpconf *conf = mddev->private;
@@ -325,8 +322,6 @@ abort:
 	return err;
 }
 
-
-
 /*
  * This is a kernel thread which:
  *
@@ -356,7 +351,7 @@ static void multipathd(struct md_thread *thread)
 
 		bio = &mp_bh->bio;
 		bio->bi_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector;
-		
+
 		if ((mp_bh->path = multipath_map (conf))<0) {
 			printk(KERN_ALERT "multipath: %s: unrecoverable IO read"
 				" error for block %llu\n",
@@ -414,7 +409,7 @@ static int multipath_run (struct mddev *mddev)
 	conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL);
 	mddev->private = conf;
 	if (!conf) {
-		printk(KERN_ERR 
+		printk(KERN_ERR
 			"multipath: couldn't allocate memory for %s\n",
 			mdname(mddev));
 		goto out;
@@ -423,7 +418,7 @@ static int multipath_run (struct mddev *mddev)
 	conf->multipaths = kzalloc(sizeof(struct multipath_info)*mddev->raid_disks,
 				   GFP_KERNEL);
 	if (!conf->multipaths) {
-		printk(KERN_ERR 
+		printk(KERN_ERR
 			"multipath: couldn't allocate memory for %s\n",
 			mdname(mddev));
 		goto out_free_conf;
@@ -469,7 +464,7 @@ static int multipath_run (struct mddev *mddev)
 	conf->pool = mempool_create_kmalloc_pool(NR_RESERVED_BUFS,
 						 sizeof(struct multipath_bh));
 	if (conf->pool == NULL) {
-		printk(KERN_ERR 
+		printk(KERN_ERR
 			"multipath: couldn't allocate memory for %s\n",
 			mdname(mddev));
 		goto out_free_conf;
@@ -485,7 +480,7 @@ static int multipath_run (struct mddev *mddev)
 		}
 	}
 
-	printk(KERN_INFO 
+	printk(KERN_INFO
 		"multipath: array %s active with %d out of %d IO paths\n",
 		mdname(mddev), conf->raid_disks - mddev->degraded,
 	       mddev->raid_disks);
@@ -512,7 +507,6 @@ out:
 	return -EIO;
 }
 
-
 static int multipath_stop (struct mddev *mddev)
 {
 	struct mpconf *conf = mddev->private;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index cf91f5910c7c..ba6b85de96d2 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -1,10 +1,9 @@
 /*
    raid0.c : Multiple Devices driver for Linux
-             Copyright (C) 1994-96 Marc ZYNGIER
+	     Copyright (C) 1994-96 Marc ZYNGIER
 	     <zyngier@ufr-info-p7.ibp.fr> or
 	     <maz@gloups.fdn.fr>
-             Copyright (C) 1999, 2000 Ingo Molnar, Red Hat
-
+	     Copyright (C) 1999, 2000 Ingo Molnar, Red Hat
 
    RAID-0 management functions.
 
@@ -12,10 +11,10 @@
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2, or (at your option)
    any later version.
-   
+
    You should have received a copy of the GNU General Public License
    (for example /usr/src/linux/COPYING); if not, write to the Free
-   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
+   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
 
 #include <linux/blkdev.h>
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 55de4f6f7eaf..40b35be34f8d 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -494,7 +494,6 @@ static void raid1_end_write_request(struct bio *bio, int error)
 		bio_put(to_put);
 }
 
-
 /*
  * This routine returns the disk from which the requested read should
  * be done. There is a per-array 'next expected sequential IO' sector
@@ -901,18 +900,18 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
 		 * However if there are already pending
 		 * requests (preventing the barrier from
 		 * rising completely), and the
-		 * pre-process bio queue isn't empty,
+		 * per-process bio queue isn't empty,
 		 * then don't wait, as we need to empty
-		 * that queue to get the nr_pending
-		 * count down.
+		 * that queue to allow conf->start_next_window
+		 * to increase.
 		 */
 		wait_event_lock_irq(conf->wait_barrier,
 				    !conf->array_frozen &&
 				    (!conf->barrier ||
-				    ((conf->start_next_window <
-				      conf->next_resync + RESYNC_SECTORS) &&
-				     current->bio_list &&
-				     !bio_list_empty(current->bio_list))),
+				     ((conf->start_next_window <
+				       conf->next_resync + RESYNC_SECTORS) &&
+				      current->bio_list &&
+				      !bio_list_empty(current->bio_list))),
 				    conf->resync_lock);
 		conf->nr_waiting--;
 	}
@@ -1001,8 +1000,7 @@ static void unfreeze_array(struct r1conf *conf)
 	spin_unlock_irq(&conf->resync_lock);
 }
 
-
-/* duplicate the data pages for behind I/O 
+/* duplicate the data pages for behind I/O
  */
 static void alloc_behind_pages(struct bio *bio, struct r1bio *r1_bio)
 {
@@ -1471,7 +1469,6 @@ static void status(struct seq_file *seq, struct mddev *mddev)
 	seq_printf(seq, "]");
 }
 
-
 static void error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
@@ -1565,7 +1562,7 @@ static int raid1_spare_active(struct mddev *mddev)
 	unsigned long flags;
 
 	/*
-	 * Find all failed disks within the RAID1 configuration 
+	 * Find all failed disks within the RAID1 configuration
 	 * and mark them readable.
 	 * Called under mddev lock, so rcu protection not needed.
 	 */
@@ -1606,7 +1603,6 @@ static int raid1_spare_active(struct mddev *mddev)
 	return count;
 }
 
-
 static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r1conf *conf = mddev->private;
@@ -1735,7 +1731,6 @@ abort:
 	return err;
 }
 
-
 static void end_sync_read(struct bio *bio, int error)
 {
 	struct r1bio *r1_bio = bio->bi_private;
@@ -1947,7 +1942,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 	return 1;
 }
 
-static int process_checks(struct r1bio *r1_bio)
+static void process_checks(struct r1bio *r1_bio)
 {
 	/* We have read all readable devices.  If we haven't
 	 * got the block, then there is no hope left.
@@ -2039,7 +2034,6 @@ static int process_checks(struct r1bio *r1_bio)
 
 		bio_copy_data(sbio, pbio);
 	}
-	return 0;
 }
 
 static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
@@ -2057,8 +2051,8 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 			return;
 
 	if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
-		if (process_checks(r1_bio) < 0)
-			return;
+		process_checks(r1_bio);
+
 	/*
 	 * schedule writes
 	 */
@@ -2458,7 +2452,6 @@ static void raid1d(struct md_thread *thread)
 	blk_finish_plug(&plug);
 }
 
-
 static int init_resync(struct r1conf *conf)
 {
 	int buffs;
@@ -2722,7 +2715,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 						/* remove last page from this bio */
 						bio->bi_vcnt--;
 						bio->bi_iter.bi_size -= len;
-						bio->bi_flags &= ~(1<< BIO_SEG_VALID);
+						__clear_bit(BIO_SEG_VALID, &bio->bi_flags);
 					}
 					goto bio_full;
 				}
@@ -2947,9 +2940,9 @@ static int run(struct mddev *mddev)
 		printk(KERN_NOTICE "md/raid1:%s: not clean"
 		       " -- starting background reconstruction\n",
 		       mdname(mddev));
-	printk(KERN_INFO 
+	printk(KERN_INFO
 		"md/raid1:%s: active with %d out of %d mirrors\n",
-		mdname(mddev), mddev->raid_disks - mddev->degraded, 
+		mdname(mddev), mddev->raid_disks - mddev->degraded,
 		mddev->raid_disks);
 
 	/*
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 9bebca7bff2f..33bda55ef9f7 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -90,7 +90,6 @@ struct r1conf {
 	 */
 	int			recovery_disabled;
 
-
 	/* poolinfo contains information about the content of the
 	 * mempools - it changes when the array grows or shrinks
 	 */
@@ -103,7 +102,6 @@ struct r1conf {
 	 */
 	struct page		*tmppage;
 
-
 	/* When taking over an array from a different personality, we store
 	 * the new thread here until we fully activate the array.
 	 */
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 6703751d87d7..32e282f4c83c 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -366,7 +366,6 @@ static void raid10_end_read_request(struct bio *bio, int error)
 	struct md_rdev *rdev;
 	struct r10conf *conf = r10_bio->mddev->private;
 
-
 	slot = r10_bio->read_slot;
 	dev = r10_bio->devs[slot].devnum;
 	rdev = r10_bio->devs[slot].rdev;
@@ -1559,7 +1558,6 @@ static void make_request(struct mddev *mddev, struct bio *bio)
 
 	md_write_start(mddev, bio);
 
-
 	do {
 
 		/*
@@ -1782,7 +1780,6 @@ static int raid10_spare_active(struct mddev *mddev)
 	return count;
 }
 
-
 static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r10conf *conf = mddev->private;
@@ -1929,7 +1926,6 @@ abort:
 	return err;
 }
 
-
 static void end_sync_read(struct bio *bio, int error)
 {
 	struct r10bio *r10_bio = bio->bi_private;
@@ -2295,7 +2291,6 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	}
 }
 
-
 /*
  * Used by fix_read_error() to decay the per rdev read_errors.
  * We halve the read error count for every hour that has elapsed
@@ -2852,7 +2847,6 @@ static void raid10d(struct md_thread *thread)
 	blk_finish_plug(&plug);
 }
 
-
 static int init_resync(struct r10conf *conf)
 {
 	int buffs;
@@ -3388,7 +3382,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 				/* remove last page from this bio */
 				bio2->bi_vcnt--;
 				bio2->bi_iter.bi_size -= len;
-				bio2->bi_flags &= ~(1<< BIO_SEG_VALID);
+				__clear_bit(BIO_SEG_VALID, &bio2->bi_flags);
 			}
 			goto bio_full;
 		}
@@ -3776,7 +3770,6 @@ static int run(struct mddev *mddev)
 		blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
 	}
 
-
 	if (md_integrity_register(mddev))
 		goto out_free_conf;
 
@@ -3834,6 +3827,8 @@ static int stop(struct mddev *mddev)
 		mempool_destroy(conf->r10bio_pool);
 	safe_put_page(conf->tmppage);
 	kfree(conf->mirrors);
+	kfree(conf->mirrors_old);
+	kfree(conf->mirrors_new);
 	kfree(conf);
 	mddev->private = NULL;
 	return 0;
@@ -4121,7 +4116,7 @@ static int raid10_start_reshape(struct mddev *mddev)
 		memcpy(conf->mirrors_new, conf->mirrors,
 		       sizeof(struct raid10_info)*conf->prev.raid_disks);
 		smp_mb();
-		kfree(conf->mirrors_old); /* FIXME and elsewhere */
+		kfree(conf->mirrors_old);
 		conf->mirrors_old = conf->mirrors;
 		conf->mirrors = conf->mirrors_new;
 		conf->mirrors_new = NULL;
@@ -4416,7 +4411,7 @@ read_more:
 	read_bio->bi_end_io = end_sync_read;
 	read_bio->bi_rw = READ;
 	read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
-	read_bio->bi_flags |= 1 << BIO_UPTODATE;
+	__set_bit(BIO_UPTODATE, &read_bio->bi_flags);
 	read_bio->bi_vcnt = 0;
 	read_bio->bi_iter.bi_size = 0;
 	r10_bio->master_bio = read_bio;
@@ -4473,7 +4468,7 @@ read_more:
 				/* Remove last page from this bio */
 				bio2->bi_vcnt--;
 				bio2->bi_iter.bi_size -= len;
-				bio2->bi_flags &= ~(1<<BIO_SEG_VALID);
+				__clear_bit(BIO_SEG_VALID, &bio2->bi_flags);
 			}
 			goto bio_full;
 		}
@@ -4575,7 +4570,6 @@ static void end_reshape(struct r10conf *conf)
 	conf->fullsync = 0;
 }
 
-
 static int handle_reshape_read_error(struct mddev *mddev,
 				     struct r10bio *r10_bio)
 {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 9f0fbecd1eb5..9c66e5997fc8 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -463,7 +463,6 @@ static inline void insert_hash(struct r5conf *conf, struct stripe_head *sh)
 	hlist_add_head(&sh->hash, hp);
 }
 
-
 /* find an idle stripe, make sure it is unhashed, and return it. */
 static struct stripe_head *get_free_stripe(struct r5conf *conf, int hash)
 {
@@ -531,9 +530,7 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int previous)
 	BUG_ON(stripe_operations_active(sh));
 
 	pr_debug("init_stripe called, stripe %llu\n",
-		(unsigned long long)sh->sector);
-
-	remove_hash(sh);
+		(unsigned long long)sector);
 retry:
 	seq = read_seqcount_begin(&conf->gen_lock);
 	sh->generation = conf->generation - previous;
@@ -542,7 +539,6 @@ retry:
 	stripe_set_idx(sector, conf, previous, sh);
 	sh->state = 0;
 
-
 	for (i = sh->disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 
@@ -1350,7 +1346,6 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 	}
 }
 
-
 static void ops_complete_prexor(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
@@ -2419,7 +2414,6 @@ static sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
 	return new_sector;
 }
 
-
 static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
 {
 	struct r5conf *conf = sh->raid_conf;
@@ -2437,7 +2431,6 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
 	sector_t r_sector;
 	struct stripe_head sh2;
 
-
 	chunk_offset = sector_div(new_sector, sectors_per_chunk);
 	stripe = new_sector;
 
@@ -2541,7 +2534,6 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
 	return r_sector;
 }
 
-
 static void
 schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
 			 int rcw, int expand)
@@ -3013,7 +3005,6 @@ static void handle_stripe_fill(struct stripe_head *sh,
 	set_bit(STRIPE_HANDLE, &sh->state);
 }
 
-
 /* handle_stripe_clean_event
  * any written block on an uptodate or failed drive can be returned.
  * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but
@@ -3304,7 +3295,6 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh,
 	}
 }
 
-
 static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh,
 				  struct stripe_head_state *s,
 				  int disks)
@@ -3939,7 +3929,6 @@ static void handle_stripe(struct stripe_head *sh)
 			}
 		}
 
-
 	/* Finish reconstruct operations initiated by the expansion process */
 	if (sh->reconstruct_state == reconstruct_state_result) {
 		struct stripe_head *sh_src
@@ -4137,7 +4126,6 @@ static int raid5_mergeable_bvec(struct request_queue *q,
 		return max;
 }
 
-
 static int in_chunk_boundary(struct mddev *mddev, struct bio *bio)
 {
 	sector_t sector = bio->bi_iter.bi_sector + get_start_sect(bio->bi_bdev);
@@ -4167,7 +4155,6 @@ static void add_bio_to_retry(struct bio *bi,struct r5conf *conf)
 	md_wakeup_thread(conf->mddev->thread);
 }
 
-
 static struct bio *remove_bio_from_retry(struct r5conf *conf)
 {
 	struct bio *bi;
@@ -4191,7 +4178,6 @@ static struct bio *remove_bio_from_retry(struct r5conf *conf)
 	return bi;
 }
 
-
 /*
  *  The "raid5_align_endio" should check if the read succeeded and if it
  *  did, call bio_endio on the original bio (having bio_put the new bio
@@ -4224,7 +4210,6 @@ static void raid5_align_endio(struct bio *bi, int error)
 		return;
 	}
 
-
 	pr_debug("raid5_align_endio : io error...handing IO for a retry\n");
 
 	add_bio_to_retry(raid_bi, conf);
@@ -4249,7 +4234,6 @@ static int bio_fits_rdev(struct bio *bi)
 	return 1;
 }
 
-
 static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 {
 	struct r5conf *conf = mddev->private;
@@ -4301,7 +4285,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		rcu_read_unlock();
 		raid_bio->bi_next = (void*)rdev;
 		align_bi->bi_bdev =  rdev->bdev;
-		align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
+		__clear_bit(BIO_SEG_VALID, &align_bi->bi_flags);
 
 		if (!bio_fits_rdev(align_bi) ||
 		    is_badblock(rdev, align_bi->bi_iter.bi_sector,
@@ -5446,7 +5430,6 @@ raid5_skip_copy = __ATTR(skip_copy, S_IRUGO | S_IWUSR,
 					raid5_show_skip_copy,
 					raid5_store_skip_copy);
 
-
 static ssize_t
 stripe_cache_active_show(struct mddev *mddev, char *page)
 {
@@ -5898,7 +5881,6 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 		return ERR_PTR(-ENOMEM);
 }
 
-
 static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded)
 {
 	switch (algo) {
@@ -5911,7 +5893,7 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
 			return 1;
 		break;
 	case ALGORITHM_PARITY_0_6:
-		if (raid_disk == 0 || 
+		if (raid_disk == 0 ||
 		    raid_disk == raid_disks - 1)
 			return 1;
 		break;
@@ -6165,7 +6147,6 @@ static int run(struct mddev *mddev)
 							"reshape");
 	}
 
-
 	/* Ok, everything is just fine now */
 	if (mddev->to_remove == &raid5_attrs_group)
 		mddev->to_remove = NULL;
@@ -6814,7 +6795,6 @@ static void raid5_quiesce(struct mddev *mddev, int state)
 	}
 }
 
-
 static void *raid45_takeover_raid0(struct mddev *mddev, int level)
 {
 	struct r0conf *raid0_conf = mddev->private;
@@ -6841,7 +6821,6 @@ static void *raid45_takeover_raid0(struct mddev *mddev, int level)
 	return setup_conf(mddev);
 }
 
-
 static void *raid5_takeover_raid1(struct mddev *mddev)
 {
 	int chunksect;
@@ -6902,7 +6881,6 @@ static void *raid5_takeover_raid6(struct mddev *mddev)
 	return setup_conf(mddev);
 }
 
-
 static int raid5_check_reshape(struct mddev *mddev)
 {
 	/* For a 2-drive array, the layout and chunk size can be changed
@@ -7051,7 +7029,6 @@ static void *raid6_takeover(struct mddev *mddev)
 	return setup_conf(mddev);
 }
 
-
 static struct md_personality raid6_personality =
 {
 	.name		= "raid6",
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index bc72cd4be5f8..d59f5ca743cd 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -155,7 +155,7 @@
  */
 
 /*
- * Operations state - intermediate states that are visible outside of 
+ * Operations state - intermediate states that are visible outside of
  *   STRIPE_ACTIVE.
  * In general _idle indicates nothing is running, _run indicates a data
  * processing operation is active, and _result means the data processing result
@@ -364,7 +364,6 @@ enum {
  * HANDLE gets cleared if stripe_handle leaves nothing locked.
  */
 
-
 struct disk_info {
 	struct md_rdev	*rdev, *replacement;
 };
@@ -528,7 +527,6 @@ struct r5conf {
 #define ALGORITHM_ROTATING_N_RESTART	9 /* DDF PRL=6 RLQ=2 */
 #define ALGORITHM_ROTATING_N_CONTINUE	10 /*DDF PRL=6 RLQ=3 */
 
-
 /* For every RAID5 algorithm we define a RAID6 algorithm
  * with exactly the same layout for data and parity, and
  * with the Q block always on the last device (N-1).
diff --git a/drivers/media/common/b2c2/flexcop.h b/drivers/media/common/b2c2/flexcop.h
index 897b10c85ad9..8942bdacbf61 100644
--- a/drivers/media/common/b2c2/flexcop.h
+++ b/drivers/media/common/b2c2/flexcop.h
@@ -4,7 +4,7 @@
  * see flexcop.c for copyright information
  */
 #ifndef __FLEXCOP_H__
-#define __FLEXCOP_H___
+#define __FLEXCOP_H__
 
 #define FC_LOG_PREFIX "b2c2-flexcop"
 #include "flexcop-common.h"
diff --git a/drivers/media/common/saa7146/saa7146_fops.c b/drivers/media/common/saa7146/saa7146_fops.c
index 6c47f3fe9b0f..b7d63933dae6 100644
--- a/drivers/media/common/saa7146/saa7146_fops.c
+++ b/drivers/media/common/saa7146/saa7146_fops.c
@@ -311,7 +311,6 @@ static int fops_mmap(struct file *file, struct vm_area_struct * vma)
 		}
 	default:
 		BUG();
-		return 0;
 	}
 
 	if (mutex_lock_interruptible(vdev->lock))
@@ -399,7 +398,6 @@ static ssize_t fops_read(struct file *file, char __user *data, size_t count, lof
 		return -EINVAL;
 	default:
 		BUG();
-		return 0;
 	}
 }
 
@@ -423,7 +421,6 @@ static ssize_t fops_write(struct file *file, const char __user *data, size_t cou
 		return -EINVAL;
 	default:
 		BUG();
-		return -EINVAL;
 	}
 }
 
diff --git a/drivers/media/common/siano/sms-cards.c b/drivers/media/common/siano/sms-cards.c
index 82769993eeb7..82c7a1289f05 100644
--- a/drivers/media/common/siano/sms-cards.c
+++ b/drivers/media/common/siano/sms-cards.c
@@ -157,6 +157,12 @@ static struct sms_board sms_boards[] = {
 		.type = SMS_DENVER_2160,
 		.default_mode = DEVICE_MODE_DAB_TDMB,
 	},
+	[SMS1XXX_BOARD_PCTV_77E] = {
+		.name	= "Hauppauge microStick 77e",
+		.type	= SMS_NOVA_B0,
+		.fw[DEVICE_MODE_DVBT_BDA] = SMS_FW_DVB_NOVA_12MHZ_B0,
+		.default_mode = DEVICE_MODE_DVBT_BDA,
+	},
 };
 
 struct sms_board *sms_get_board(unsigned id)
diff --git a/drivers/media/common/siano/sms-cards.h b/drivers/media/common/siano/sms-cards.h
index c63b544c49c5..4c4caddf9869 100644
--- a/drivers/media/common/siano/sms-cards.h
+++ b/drivers/media/common/siano/sms-cards.h
@@ -45,6 +45,7 @@
 #define SMS1XXX_BOARD_SIANO_RIO		18
 #define SMS1XXX_BOARD_SIANO_DENVER_1530	19
 #define SMS1XXX_BOARD_SIANO_DENVER_2160 20
+#define SMS1XXX_BOARD_PCTV_77E		21
 
 struct sms_board_gpio_cfg {
 	int lna_vhf_exist;
diff --git a/drivers/media/common/siano/smscoreapi.c b/drivers/media/common/siano/smscoreapi.c
index 050984c5b1e3..a3677438205e 100644
--- a/drivers/media/common/siano/smscoreapi.c
+++ b/drivers/media/common/siano/smscoreapi.c
@@ -2129,8 +2129,6 @@ int smscore_gpio_get_level(struct smscore_device_t *coredev, u8 pin_num,
 
 static int __init smscore_module_init(void)
 {
-	int rc = 0;
-
 	INIT_LIST_HEAD(&g_smscore_notifyees);
 	INIT_LIST_HEAD(&g_smscore_devices);
 	kmutex_init(&g_smscore_deviceslock);
@@ -2138,7 +2136,7 @@ static int __init smscore_module_init(void)
 	INIT_LIST_HEAD(&g_smscore_registry);
 	kmutex_init(&g_smscore_registrylock);
 
-	return rc;
+	return 0;
 }
 
 static void __exit smscore_module_exit(void)
diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c
index c0363f1b6c90..abff803ad69a 100644
--- a/drivers/media/dvb-core/dmxdev.c
+++ b/drivers/media/dvb-core/dmxdev.c
@@ -1087,8 +1087,8 @@ static unsigned int dvb_demux_poll(struct file *file, poll_table *wait)
 	struct dmxdev_filter *dmxdevfilter = file->private_data;
 	unsigned int mask = 0;
 
-	if (!dmxdevfilter)
-		return -EINVAL;
+	if ((!dmxdevfilter) || dmxdevfilter->dev->exit)
+		return POLLERR;
 
 	poll_wait(file, &dmxdevfilter->buffer.queue, wait);
 
@@ -1181,6 +1181,9 @@ static unsigned int dvb_dvr_poll(struct file *file, poll_table *wait)
 
 	dprintk("function : %s\n", __func__);
 
+	if (dmxdev->exit)
+		return POLLERR;
+
 	poll_wait(file, &dmxdev->dvr_buffer.queue, wait);
 
 	if ((file->f_flags & O_ACCMODE) == O_RDONLY) {
diff --git a/drivers/media/dvb-core/dvb-usb-ids.h b/drivers/media/dvb-core/dvb-usb-ids.h
index 12ce19c98ded..e07a84e7bc56 100644
--- a/drivers/media/dvb-core/dvb-usb-ids.h
+++ b/drivers/media/dvb-core/dvb-usb-ids.h
@@ -144,6 +144,7 @@
 #define USB_PID_ITETECH_IT9135				0x9135
 #define USB_PID_ITETECH_IT9135_9005			0x9005
 #define USB_PID_ITETECH_IT9135_9006			0x9006
+#define USB_PID_ITETECH_IT9303				0x9306
 #define USB_PID_KWORLD_399U				0xe399
 #define USB_PID_KWORLD_399U_2				0xe400
 #define USB_PID_KWORLD_395U				0xe396
@@ -244,6 +245,7 @@
 #define USB_PID_TECHNOTREND_CONNECT_S2400               0x3006
 #define USB_PID_TECHNOTREND_CONNECT_S2400_8KEEPROM	0x3009
 #define USB_PID_TECHNOTREND_CONNECT_CT3650		0x300d
+#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI		0x3012
 #define USB_PID_TECHNOTREND_TVSTICK_CT2_4400		0x3014
 #define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY	0x005a
 #define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY_2	0x0081
diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c
index c2a6a0a85813..b8579ee68bd6 100644
--- a/drivers/media/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb-core/dvb_frontend.c
@@ -1934,15 +1934,13 @@ static int dvb_frontend_ioctl_properties(struct file *file,
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int err = 0;
 
-	struct dtv_properties *tvps = NULL;
+	struct dtv_properties *tvps = parg;
 	struct dtv_property *tvp = NULL;
 	int i;
 
 	dev_dbg(fe->dvb->device, "%s:\n", __func__);
 
-	if(cmd == FE_SET_PROPERTY) {
-		tvps = (struct dtv_properties __user *)parg;
-
+	if (cmd == FE_SET_PROPERTY) {
 		dev_dbg(fe->dvb->device, "%s: properties.num = %d\n", __func__, tvps->num);
 		dev_dbg(fe->dvb->device, "%s: properties.props = %p\n", __func__, tvps->props);
 
@@ -1957,7 +1955,8 @@ static int dvb_frontend_ioctl_properties(struct file *file,
 			goto out;
 		}
 
-		if (copy_from_user(tvp, tvps->props, tvps->num * sizeof(struct dtv_property))) {
+		if (copy_from_user(tvp, (void __user *)tvps->props,
+				   tvps->num * sizeof(struct dtv_property))) {
 			err = -EFAULT;
 			goto out;
 		}
@@ -1972,10 +1971,7 @@ static int dvb_frontend_ioctl_properties(struct file *file,
 		if (c->state == DTV_TUNE)
 			dev_dbg(fe->dvb->device, "%s: Property cache is full, tuning\n", __func__);
 
-	} else
-	if(cmd == FE_GET_PROPERTY) {
-		tvps = (struct dtv_properties __user *)parg;
-
+	} else if (cmd == FE_GET_PROPERTY) {
 		dev_dbg(fe->dvb->device, "%s: properties.num = %d\n", __func__, tvps->num);
 		dev_dbg(fe->dvb->device, "%s: properties.props = %p\n", __func__, tvps->props);
 
@@ -1990,7 +1986,8 @@ static int dvb_frontend_ioctl_properties(struct file *file,
 			goto out;
 		}
 
-		if (copy_from_user(tvp, tvps->props, tvps->num * sizeof(struct dtv_property))) {
+		if (copy_from_user(tvp, (void __user *)tvps->props,
+				   tvps->num * sizeof(struct dtv_property))) {
 			err = -EFAULT;
 			goto out;
 		}
@@ -2012,7 +2009,8 @@ static int dvb_frontend_ioctl_properties(struct file *file,
 			(tvp + i)->result = err;
 		}
 
-		if (copy_to_user(tvps->props, tvp, tvps->num * sizeof(struct dtv_property))) {
+		if (copy_to_user((void __user *)tvps->props, tvp,
+				 tvps->num * sizeof(struct dtv_property))) {
 			err = -EFAULT;
 			goto out;
 		}
@@ -2072,6 +2070,23 @@ static int dtv_set_frontend(struct dvb_frontend *fe)
 	case SYS_DVBC_ANNEX_C:
 		rolloff = 113;
 		break;
+	case SYS_DVBS:
+	case SYS_TURBO:
+		rolloff = 135;
+		break;
+	case SYS_DVBS2:
+		switch (c->rolloff) {
+		case ROLLOFF_20:
+			rolloff = 120;
+			break;
+		case ROLLOFF_25:
+			rolloff = 125;
+			break;
+		default:
+		case ROLLOFF_35:
+			rolloff = 135;
+		}
+		break;
 	default:
 		break;
 	}
@@ -2550,7 +2565,9 @@ int dvb_frontend_suspend(struct dvb_frontend *fe)
 	dev_dbg(fe->dvb->device, "%s: adap=%d fe=%d\n", __func__, fe->dvb->num,
 			fe->id);
 
-	if (fe->ops.tuner_ops.sleep)
+	if (fe->ops.tuner_ops.suspend)
+		ret = fe->ops.tuner_ops.suspend(fe);
+	else if (fe->ops.tuner_ops.sleep)
 		ret = fe->ops.tuner_ops.sleep(fe);
 
 	if (fe->ops.sleep)
@@ -2572,7 +2589,9 @@ int dvb_frontend_resume(struct dvb_frontend *fe)
 	if (fe->ops.init)
 		ret = fe->ops.init(fe);
 
-	if (fe->ops.tuner_ops.init)
+	if (fe->ops.tuner_ops.resume)
+		ret = fe->ops.tuner_ops.resume(fe);
+	else if (fe->ops.tuner_ops.init)
 		ret = fe->ops.tuner_ops.init(fe);
 
 	fe->exit = DVB_FE_NO_EXIT;
diff --git a/drivers/media/dvb-core/dvb_frontend.h b/drivers/media/dvb-core/dvb_frontend.h
index d398de4b6ef4..816269e5f706 100644
--- a/drivers/media/dvb-core/dvb_frontend.h
+++ b/drivers/media/dvb-core/dvb_frontend.h
@@ -201,6 +201,8 @@ struct dvb_tuner_ops {
 	int (*release)(struct dvb_frontend *fe);
 	int (*init)(struct dvb_frontend *fe);
 	int (*sleep)(struct dvb_frontend *fe);
+	int (*suspend)(struct dvb_frontend *fe);
+	int (*resume)(struct dvb_frontend *fe);
 
 	/** This is for simple PLLs - set all parameters in one go. */
 	int (*set_params)(struct dvb_frontend *fe);
diff --git a/drivers/media/dvb-core/dvb_ringbuffer.c b/drivers/media/dvb-core/dvb_ringbuffer.c
index a5712cd7c65f..1100e98a7b1d 100644
--- a/drivers/media/dvb-core/dvb_ringbuffer.c
+++ b/drivers/media/dvb-core/dvb_ringbuffer.c
@@ -166,6 +166,31 @@ ssize_t dvb_ringbuffer_write(struct dvb_ringbuffer *rbuf, const u8 *buf, size_t
 	return len;
 }
 
+ssize_t dvb_ringbuffer_write_user(struct dvb_ringbuffer *rbuf,
+				  const u8 __user *buf, size_t len)
+{
+	int status;
+	size_t todo = len;
+	size_t split;
+
+	split = (rbuf->pwrite + len > rbuf->size) ? rbuf->size - rbuf->pwrite : 0;
+
+	if (split > 0) {
+		status = copy_from_user(rbuf->data+rbuf->pwrite, buf, split);
+		if (status)
+			return len - todo;
+		buf += split;
+		todo -= split;
+		rbuf->pwrite = 0;
+	}
+	status = copy_from_user(rbuf->data+rbuf->pwrite, buf, todo);
+	if (status)
+		return len - todo;
+	rbuf->pwrite = (rbuf->pwrite + todo) % rbuf->size;
+
+	return len;
+}
+
 ssize_t dvb_ringbuffer_pkt_write(struct dvb_ringbuffer *rbuf, u8* buf, size_t len)
 {
 	int status;
@@ -297,3 +322,4 @@ EXPORT_SYMBOL(dvb_ringbuffer_flush_spinlock_wakeup);
 EXPORT_SYMBOL(dvb_ringbuffer_read_user);
 EXPORT_SYMBOL(dvb_ringbuffer_read);
 EXPORT_SYMBOL(dvb_ringbuffer_write);
+EXPORT_SYMBOL(dvb_ringbuffer_write_user);
diff --git a/drivers/media/dvb-core/dvb_ringbuffer.h b/drivers/media/dvb-core/dvb_ringbuffer.h
index 41f04dae69b6..9e1e11b7c39c 100644
--- a/drivers/media/dvb-core/dvb_ringbuffer.h
+++ b/drivers/media/dvb-core/dvb_ringbuffer.h
@@ -133,6 +133,8 @@ extern void dvb_ringbuffer_read(struct dvb_ringbuffer *rbuf,
 */
 extern ssize_t dvb_ringbuffer_write(struct dvb_ringbuffer *rbuf, const u8 *buf,
 				    size_t len);
+extern ssize_t dvb_ringbuffer_write_user(struct dvb_ringbuffer *rbuf,
+				         const u8 __user *buf, size_t len);
 
 
 /**
diff --git a/drivers/media/dvb-frontends/Kconfig b/drivers/media/dvb-frontends/Kconfig
index fe0ddcca192c..5a134547e325 100644
--- a/drivers/media/dvb-frontends/Kconfig
+++ b/drivers/media/dvb-frontends/Kconfig
@@ -471,6 +471,11 @@ config DVB_SI2168
 	help
 	  Say Y when you want to support this frontend.
 
+config DVB_AS102_FE
+	tristate
+	depends on DVB_CORE
+	default DVB_AS102
+
 comment "DVB-C (cable) frontends"
 	depends on DVB_CORE
 
@@ -643,6 +648,14 @@ config DVB_MB86A20S
 	  A driver for Fujitsu mb86a20s ISDB-T/ISDB-Tsb demodulator.
 	  Say Y when you want to support this frontend.
 
+config DVB_TC90522
+	tristate "Toshiba TC90522"
+	depends on DVB_CORE && I2C
+	default m if !MEDIA_SUBDRV_AUTOSELECT
+	help
+	  A Toshiba TC90522 2xISDB-T + 2xISDB-S demodulator.
+	  Say Y when you want to support this frontend.
+
 comment "Digital terrestrial only tuners/PLL"
 	depends on DVB_CORE
 
@@ -720,6 +733,13 @@ config DVB_A8293
 	depends on DVB_CORE && I2C
 	default m if !MEDIA_SUBDRV_AUTOSELECT
 
+config DVB_SP2
+	tristate "CIMaX SP2"
+	depends on DVB_CORE && I2C
+	default m if !MEDIA_SUBDRV_AUTOSELECT
+	help
+	  CIMaX SP2/SP2HF Common Interface module.
+
 config DVB_LGS8GL5
 	tristate "Silicon Legend LGS-8GL5 demodulator (OFDM)"
 	depends on DVB_CORE && I2C
diff --git a/drivers/media/dvb-frontends/Makefile b/drivers/media/dvb-frontends/Makefile
index edf103d45920..ba59df63d050 100644
--- a/drivers/media/dvb-frontends/Makefile
+++ b/drivers/media/dvb-frontends/Makefile
@@ -107,10 +107,12 @@ obj-$(CONFIG_DVB_DRXK) += drxk.o
 obj-$(CONFIG_DVB_TDA18271C2DD) += tda18271c2dd.o
 obj-$(CONFIG_DVB_SI2165) += si2165.o
 obj-$(CONFIG_DVB_A8293) += a8293.o
+obj-$(CONFIG_DVB_SP2) += sp2.o
 obj-$(CONFIG_DVB_TDA10071) += tda10071.o
 obj-$(CONFIG_DVB_RTL2830) += rtl2830.o
 obj-$(CONFIG_DVB_RTL2832) += rtl2832.o
 obj-$(CONFIG_DVB_RTL2832_SDR) += rtl2832_sdr.o
 obj-$(CONFIG_DVB_M88RS2000) += m88rs2000.o
 obj-$(CONFIG_DVB_AF9033) += af9033.o
-
+obj-$(CONFIG_DVB_AS102_FE) += as102_fe.o
+obj-$(CONFIG_DVB_TC90522) += tc90522.o
diff --git a/drivers/media/dvb-frontends/af9013.c b/drivers/media/dvb-frontends/af9013.c
index ecf6388d2200..8001690d7576 100644
--- a/drivers/media/dvb-frontends/af9013.c
+++ b/drivers/media/dvb-frontends/af9013.c
@@ -683,7 +683,7 @@ static int af9013_set_frontend(struct dvb_frontend *fe)
 
 	switch (c->transmission_mode) {
 	case TRANSMISSION_MODE_AUTO:
-		auto_mode = 1;
+		auto_mode = true;
 		break;
 	case TRANSMISSION_MODE_2K:
 		break;
@@ -693,12 +693,12 @@ static int af9013_set_frontend(struct dvb_frontend *fe)
 	default:
 		dev_dbg(&state->i2c->dev, "%s: invalid transmission_mode\n",
 				__func__);
-		auto_mode = 1;
+		auto_mode = true;
 	}
 
 	switch (c->guard_interval) {
 	case GUARD_INTERVAL_AUTO:
-		auto_mode = 1;
+		auto_mode = true;
 		break;
 	case GUARD_INTERVAL_1_32:
 		break;
@@ -714,12 +714,12 @@ static int af9013_set_frontend(struct dvb_frontend *fe)
 	default:
 		dev_dbg(&state->i2c->dev, "%s: invalid guard_interval\n",
 				__func__);
-		auto_mode = 1;
+		auto_mode = true;
 	}
 
 	switch (c->hierarchy) {
 	case HIERARCHY_AUTO:
-		auto_mode = 1;
+		auto_mode = true;
 		break;
 	case HIERARCHY_NONE:
 		break;
@@ -734,12 +734,12 @@ static int af9013_set_frontend(struct dvb_frontend *fe)
 		break;
 	default:
 		dev_dbg(&state->i2c->dev, "%s: invalid hierarchy\n", __func__);
-		auto_mode = 1;
+		auto_mode = true;
 	}
 
 	switch (c->modulation) {
 	case QAM_AUTO:
-		auto_mode = 1;
+		auto_mode = true;
 		break;
 	case QPSK:
 		break;
@@ -751,7 +751,7 @@ static int af9013_set_frontend(struct dvb_frontend *fe)
 		break;
 	default:
 		dev_dbg(&state->i2c->dev, "%s: invalid modulation\n", __func__);
-		auto_mode = 1;
+		auto_mode = true;
 	}
 
 	/* Use HP. How and which case we can switch to LP? */
@@ -759,7 +759,7 @@ static int af9013_set_frontend(struct dvb_frontend *fe)
 
 	switch (c->code_rate_HP) {
 	case FEC_AUTO:
-		auto_mode = 1;
+		auto_mode = true;
 		break;
 	case FEC_1_2:
 		break;
@@ -778,12 +778,12 @@ static int af9013_set_frontend(struct dvb_frontend *fe)
 	default:
 		dev_dbg(&state->i2c->dev, "%s: invalid code_rate_HP\n",
 				__func__);
-		auto_mode = 1;
+		auto_mode = true;
 	}
 
 	switch (c->code_rate_LP) {
 	case FEC_AUTO:
-		auto_mode = 1;
+		auto_mode = true;
 		break;
 	case FEC_1_2:
 		break;
@@ -804,7 +804,7 @@ static int af9013_set_frontend(struct dvb_frontend *fe)
 	default:
 		dev_dbg(&state->i2c->dev, "%s: invalid code_rate_LP\n",
 				__func__);
-		auto_mode = 1;
+		auto_mode = true;
 	}
 
 	switch (c->bandwidth_hz) {
diff --git a/drivers/media/dvb-frontends/af9033.c b/drivers/media/dvb-frontends/af9033.c
index 5c90ea683a7e..63a89c1c59ff 100644
--- a/drivers/media/dvb-frontends/af9033.c
+++ b/drivers/media/dvb-frontends/af9033.c
@@ -24,29 +24,35 @@
 /* Max transfer size done by I2C transfer functions */
 #define MAX_XFER_SIZE  64
 
-struct af9033_state {
-	struct i2c_adapter *i2c;
+struct af9033_dev {
+	struct i2c_client *client;
 	struct dvb_frontend fe;
 	struct af9033_config cfg;
+	bool is_af9035;
+	bool is_it9135;
 
 	u32 bandwidth_hz;
 	bool ts_mode_parallel;
 	bool ts_mode_serial;
 
-	u32 ber;
-	u32 ucb;
-	unsigned long last_stat_check;
+	fe_status_t fe_status;
+	u64 post_bit_error_prev; /* for old read_ber we return (curr - prev) */
+	u64 post_bit_error;
+	u64 post_bit_count;
+	u64 error_block_count;
+	u64 total_block_count;
+	struct delayed_work stat_work;
 };
 
 /* write multiple registers */
-static int af9033_wr_regs(struct af9033_state *state, u32 reg, const u8 *val,
+static int af9033_wr_regs(struct af9033_dev *dev, u32 reg, const u8 *val,
 		int len)
 {
 	int ret;
 	u8 buf[MAX_XFER_SIZE];
 	struct i2c_msg msg[1] = {
 		{
-			.addr = state->cfg.i2c_addr,
+			.addr = dev->client->addr,
 			.flags = 0,
 			.len = 3 + len,
 			.buf = buf,
@@ -54,9 +60,9 @@ static int af9033_wr_regs(struct af9033_state *state, u32 reg, const u8 *val,
 	};
 
 	if (3 + len > sizeof(buf)) {
-		dev_warn(&state->i2c->dev,
-			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
-			 KBUILD_MODNAME, reg, len);
+		dev_warn(&dev->client->dev,
+				"i2c wr reg=%04x: len=%d is too big!\n",
+				reg, len);
 		return -EINVAL;
 	}
 
@@ -65,12 +71,12 @@ static int af9033_wr_regs(struct af9033_state *state, u32 reg, const u8 *val,
 	buf[2] = (reg >>  0) & 0xff;
 	memcpy(&buf[3], val, len);
 
-	ret = i2c_transfer(state->i2c, msg, 1);
+	ret = i2c_transfer(dev->client->adapter, msg, 1);
 	if (ret == 1) {
 		ret = 0;
 	} else {
-		dev_warn(&state->i2c->dev, "%s: i2c wr failed=%d reg=%06x " \
-				"len=%d\n", KBUILD_MODNAME, ret, reg, len);
+		dev_warn(&dev->client->dev, "i2c wr failed=%d reg=%06x len=%d\n",
+				ret, reg, len);
 		ret = -EREMOTEIO;
 	}
 
@@ -78,31 +84,31 @@ static int af9033_wr_regs(struct af9033_state *state, u32 reg, const u8 *val,
 }
 
 /* read multiple registers */
-static int af9033_rd_regs(struct af9033_state *state, u32 reg, u8 *val, int len)
+static int af9033_rd_regs(struct af9033_dev *dev, u32 reg, u8 *val, int len)
 {
 	int ret;
 	u8 buf[3] = { (reg >> 16) & 0xff, (reg >> 8) & 0xff,
 			(reg >> 0) & 0xff };
 	struct i2c_msg msg[2] = {
 		{
-			.addr = state->cfg.i2c_addr,
+			.addr = dev->client->addr,
 			.flags = 0,
 			.len = sizeof(buf),
 			.buf = buf
 		}, {
-			.addr = state->cfg.i2c_addr,
+			.addr = dev->client->addr,
 			.flags = I2C_M_RD,
 			.len = len,
 			.buf = val
 		}
 	};
 
-	ret = i2c_transfer(state->i2c, msg, 2);
+	ret = i2c_transfer(dev->client->adapter, msg, 2);
 	if (ret == 2) {
 		ret = 0;
 	} else {
-		dev_warn(&state->i2c->dev, "%s: i2c rd failed=%d reg=%06x " \
-				"len=%d\n", KBUILD_MODNAME, ret, reg, len);
+		dev_warn(&dev->client->dev, "i2c rd failed=%d reg=%06x len=%d\n",
+				ret, reg, len);
 		ret = -EREMOTEIO;
 	}
 
@@ -111,19 +117,19 @@ static int af9033_rd_regs(struct af9033_state *state, u32 reg, u8 *val, int len)
 
 
 /* write single register */
-static int af9033_wr_reg(struct af9033_state *state, u32 reg, u8 val)
+static int af9033_wr_reg(struct af9033_dev *dev, u32 reg, u8 val)
 {
-	return af9033_wr_regs(state, reg, &val, 1);
+	return af9033_wr_regs(dev, reg, &val, 1);
 }
 
 /* read single register */
-static int af9033_rd_reg(struct af9033_state *state, u32 reg, u8 *val)
+static int af9033_rd_reg(struct af9033_dev *dev, u32 reg, u8 *val)
 {
-	return af9033_rd_regs(state, reg, val, 1);
+	return af9033_rd_regs(dev, reg, val, 1);
 }
 
 /* write single register with mask */
-static int af9033_wr_reg_mask(struct af9033_state *state, u32 reg, u8 val,
+static int af9033_wr_reg_mask(struct af9033_dev *dev, u32 reg, u8 val,
 		u8 mask)
 {
 	int ret;
@@ -131,7 +137,7 @@ static int af9033_wr_reg_mask(struct af9033_state *state, u32 reg, u8 val,
 
 	/* no need for read if whole reg is written */
 	if (mask != 0xff) {
-		ret = af9033_rd_regs(state, reg, &tmp, 1);
+		ret = af9033_rd_regs(dev, reg, &tmp, 1);
 		if (ret)
 			return ret;
 
@@ -140,17 +146,17 @@ static int af9033_wr_reg_mask(struct af9033_state *state, u32 reg, u8 val,
 		val |= tmp;
 	}
 
-	return af9033_wr_regs(state, reg, &val, 1);
+	return af9033_wr_regs(dev, reg, &val, 1);
 }
 
 /* read single register with mask */
-static int af9033_rd_reg_mask(struct af9033_state *state, u32 reg, u8 *val,
+static int af9033_rd_reg_mask(struct af9033_dev *dev, u32 reg, u8 *val,
 		u8 mask)
 {
 	int ret, i;
 	u8 tmp;
 
-	ret = af9033_rd_regs(state, reg, &tmp, 1);
+	ret = af9033_rd_regs(dev, reg, &tmp, 1);
 	if (ret)
 		return ret;
 
@@ -167,18 +173,17 @@ static int af9033_rd_reg_mask(struct af9033_state *state, u32 reg, u8 *val,
 }
 
 /* write reg val table using reg addr auto increment */
-static int af9033_wr_reg_val_tab(struct af9033_state *state,
+static int af9033_wr_reg_val_tab(struct af9033_dev *dev,
 		const struct reg_val *tab, int tab_len)
 {
 #define MAX_TAB_LEN 212
 	int ret, i, j;
 	u8 buf[1 + MAX_TAB_LEN];
 
-	dev_dbg(&state->i2c->dev, "%s: tab_len=%d\n", __func__, tab_len);
+	dev_dbg(&dev->client->dev, "tab_len=%d\n", tab_len);
 
 	if (tab_len > sizeof(buf)) {
-		dev_warn(&state->i2c->dev, "%s: tab len %d is too big\n",
-				KBUILD_MODNAME, tab_len);
+		dev_warn(&dev->client->dev, "tab len %d is too big\n", tab_len);
 		return -EINVAL;
 	}
 
@@ -186,7 +191,7 @@ static int af9033_wr_reg_val_tab(struct af9033_state *state,
 		buf[j] = tab[i].val;
 
 		if (i == tab_len - 1 || tab[i].reg != tab[i + 1].reg - 1) {
-			ret = af9033_wr_regs(state, tab[i].reg - j, buf, j + 1);
+			ret = af9033_wr_regs(dev, tab[i].reg - j, buf, j + 1);
 			if (ret < 0)
 				goto err;
 
@@ -199,16 +204,16 @@ static int af9033_wr_reg_val_tab(struct af9033_state *state,
 	return 0;
 
 err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
 
-static u32 af9033_div(struct af9033_state *state, u32 a, u32 b, u32 x)
+static u32 af9033_div(struct af9033_dev *dev, u32 a, u32 b, u32 x)
 {
 	u32 r = 0, c = 0, i;
 
-	dev_dbg(&state->i2c->dev, "%s: a=%d b=%d x=%d\n", __func__, a, b, x);
+	dev_dbg(&dev->client->dev, "a=%d b=%d x=%d\n", a, b, x);
 
 	if (a > b) {
 		c = a / b;
@@ -225,22 +230,15 @@ static u32 af9033_div(struct af9033_state *state, u32 a, u32 b, u32 x)
 	}
 	r = (c << (u32)x) + r;
 
-	dev_dbg(&state->i2c->dev, "%s: a=%d b=%d x=%d r=%d r=%x\n",
-			__func__, a, b, x, r, r);
+	dev_dbg(&dev->client->dev, "a=%d b=%d x=%d r=%d r=%x\n", a, b, x, r, r);
 
 	return r;
 }
 
-static void af9033_release(struct dvb_frontend *fe)
-{
-	struct af9033_state *state = fe->demodulator_priv;
-
-	kfree(state);
-}
-
 static int af9033_init(struct dvb_frontend *fe)
 {
-	struct af9033_state *state = fe->demodulator_priv;
+	struct af9033_dev *dev = fe->demodulator_priv;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret, i, len;
 	const struct reg_val *init;
 	u8 buf[4];
@@ -248,7 +246,7 @@ static int af9033_init(struct dvb_frontend *fe)
 	struct reg_val_mask tab[] = {
 		{ 0x80fb24, 0x00, 0x08 },
 		{ 0x80004c, 0x00, 0xff },
-		{ 0x00f641, state->cfg.tuner, 0xff },
+		{ 0x00f641, dev->cfg.tuner, 0xff },
 		{ 0x80f5ca, 0x01, 0x01 },
 		{ 0x80f715, 0x01, 0x01 },
 		{ 0x00f41f, 0x04, 0x04 },
@@ -267,88 +265,82 @@ static int af9033_init(struct dvb_frontend *fe)
 		{ 0x00d830, 0x01, 0xff },
 		{ 0x00d831, 0x00, 0xff },
 		{ 0x00d832, 0x00, 0xff },
-		{ 0x80f985, state->ts_mode_serial, 0x01 },
-		{ 0x80f986, state->ts_mode_parallel, 0x01 },
+		{ 0x80f985, dev->ts_mode_serial, 0x01 },
+		{ 0x80f986, dev->ts_mode_parallel, 0x01 },
 		{ 0x00d827, 0x00, 0xff },
 		{ 0x00d829, 0x00, 0xff },
-		{ 0x800045, state->cfg.adc_multiplier, 0xff },
+		{ 0x800045, dev->cfg.adc_multiplier, 0xff },
 	};
 
 	/* program clock control */
-	clock_cw = af9033_div(state, state->cfg.clock, 1000000ul, 19ul);
+	clock_cw = af9033_div(dev, dev->cfg.clock, 1000000ul, 19ul);
 	buf[0] = (clock_cw >>  0) & 0xff;
 	buf[1] = (clock_cw >>  8) & 0xff;
 	buf[2] = (clock_cw >> 16) & 0xff;
 	buf[3] = (clock_cw >> 24) & 0xff;
 
-	dev_dbg(&state->i2c->dev, "%s: clock=%d clock_cw=%08x\n",
-			__func__, state->cfg.clock, clock_cw);
+	dev_dbg(&dev->client->dev, "clock=%d clock_cw=%08x\n",
+			dev->cfg.clock, clock_cw);
 
-	ret = af9033_wr_regs(state, 0x800025, buf, 4);
+	ret = af9033_wr_regs(dev, 0x800025, buf, 4);
 	if (ret < 0)
 		goto err;
 
 	/* program ADC control */
 	for (i = 0; i < ARRAY_SIZE(clock_adc_lut); i++) {
-		if (clock_adc_lut[i].clock == state->cfg.clock)
+		if (clock_adc_lut[i].clock == dev->cfg.clock)
 			break;
 	}
 
-	adc_cw = af9033_div(state, clock_adc_lut[i].adc, 1000000ul, 19ul);
+	adc_cw = af9033_div(dev, clock_adc_lut[i].adc, 1000000ul, 19ul);
 	buf[0] = (adc_cw >>  0) & 0xff;
 	buf[1] = (adc_cw >>  8) & 0xff;
 	buf[2] = (adc_cw >> 16) & 0xff;
 
-	dev_dbg(&state->i2c->dev, "%s: adc=%d adc_cw=%06x\n",
-			__func__, clock_adc_lut[i].adc, adc_cw);
+	dev_dbg(&dev->client->dev, "adc=%d adc_cw=%06x\n",
+			clock_adc_lut[i].adc, adc_cw);
 
-	ret = af9033_wr_regs(state, 0x80f1cd, buf, 3);
+	ret = af9033_wr_regs(dev, 0x80f1cd, buf, 3);
 	if (ret < 0)
 		goto err;
 
 	/* program register table */
 	for (i = 0; i < ARRAY_SIZE(tab); i++) {
-		ret = af9033_wr_reg_mask(state, tab[i].reg, tab[i].val,
+		ret = af9033_wr_reg_mask(dev, tab[i].reg, tab[i].val,
 				tab[i].mask);
 		if (ret < 0)
 			goto err;
 	}
 
-	/* feed clock to RF tuner */
-	switch (state->cfg.tuner) {
-	case AF9033_TUNER_IT9135_38:
-	case AF9033_TUNER_IT9135_51:
-	case AF9033_TUNER_IT9135_52:
-	case AF9033_TUNER_IT9135_60:
-	case AF9033_TUNER_IT9135_61:
-	case AF9033_TUNER_IT9135_62:
-		ret = af9033_wr_reg(state, 0x80fba8, 0x00);
+	/* clock output */
+	if (dev->cfg.dyn0_clk) {
+		ret = af9033_wr_reg(dev, 0x80fba8, 0x00);
 		if (ret < 0)
 			goto err;
 	}
 
 	/* settings for TS interface */
-	if (state->cfg.ts_mode == AF9033_TS_MODE_USB) {
-		ret = af9033_wr_reg_mask(state, 0x80f9a5, 0x00, 0x01);
+	if (dev->cfg.ts_mode == AF9033_TS_MODE_USB) {
+		ret = af9033_wr_reg_mask(dev, 0x80f9a5, 0x00, 0x01);
 		if (ret < 0)
 			goto err;
 
-		ret = af9033_wr_reg_mask(state, 0x80f9b5, 0x01, 0x01);
+		ret = af9033_wr_reg_mask(dev, 0x80f9b5, 0x01, 0x01);
 		if (ret < 0)
 			goto err;
 	} else {
-		ret = af9033_wr_reg_mask(state, 0x80f990, 0x00, 0x01);
+		ret = af9033_wr_reg_mask(dev, 0x80f990, 0x00, 0x01);
 		if (ret < 0)
 			goto err;
 
-		ret = af9033_wr_reg_mask(state, 0x80f9b5, 0x00, 0x01);
+		ret = af9033_wr_reg_mask(dev, 0x80f9b5, 0x00, 0x01);
 		if (ret < 0)
 			goto err;
 	}
 
 	/* load OFSM settings */
-	dev_dbg(&state->i2c->dev, "%s: load ofsm settings\n", __func__);
-	switch (state->cfg.tuner) {
+	dev_dbg(&dev->client->dev, "load ofsm settings\n");
+	switch (dev->cfg.tuner) {
 	case AF9033_TUNER_IT9135_38:
 	case AF9033_TUNER_IT9135_51:
 	case AF9033_TUNER_IT9135_52:
@@ -367,14 +359,13 @@ static int af9033_init(struct dvb_frontend *fe)
 		break;
 	}
 
-	ret = af9033_wr_reg_val_tab(state, init, len);
+	ret = af9033_wr_reg_val_tab(dev, init, len);
 	if (ret < 0)
 		goto err;
 
 	/* load tuner specific settings */
-	dev_dbg(&state->i2c->dev, "%s: load tuner specific settings\n",
-			__func__);
-	switch (state->cfg.tuner) {
+	dev_dbg(&dev->client->dev, "load tuner specific settings\n");
+	switch (dev->cfg.tuner) {
 	case AF9033_TUNER_TUA9001:
 		len = ARRAY_SIZE(tuner_init_tua9001);
 		init = tuner_init_tua9001;
@@ -424,90 +415,108 @@ static int af9033_init(struct dvb_frontend *fe)
 		init = tuner_init_it9135_62;
 		break;
 	default:
-		dev_dbg(&state->i2c->dev, "%s: unsupported tuner ID=%d\n",
-				__func__, state->cfg.tuner);
+		dev_dbg(&dev->client->dev, "unsupported tuner ID=%d\n",
+				dev->cfg.tuner);
 		ret = -ENODEV;
 		goto err;
 	}
 
-	ret = af9033_wr_reg_val_tab(state, init, len);
+	ret = af9033_wr_reg_val_tab(dev, init, len);
 	if (ret < 0)
 		goto err;
 
-	if (state->cfg.ts_mode == AF9033_TS_MODE_SERIAL) {
-		ret = af9033_wr_reg_mask(state, 0x00d91c, 0x01, 0x01);
+	if (dev->cfg.ts_mode == AF9033_TS_MODE_SERIAL) {
+		ret = af9033_wr_reg_mask(dev, 0x00d91c, 0x01, 0x01);
 		if (ret < 0)
 			goto err;
 
-		ret = af9033_wr_reg_mask(state, 0x00d917, 0x00, 0x01);
+		ret = af9033_wr_reg_mask(dev, 0x00d917, 0x00, 0x01);
 		if (ret < 0)
 			goto err;
 
-		ret = af9033_wr_reg_mask(state, 0x00d916, 0x00, 0x01);
+		ret = af9033_wr_reg_mask(dev, 0x00d916, 0x00, 0x01);
 		if (ret < 0)
 			goto err;
 	}
 
-	switch (state->cfg.tuner) {
+	switch (dev->cfg.tuner) {
 	case AF9033_TUNER_IT9135_60:
 	case AF9033_TUNER_IT9135_61:
 	case AF9033_TUNER_IT9135_62:
-		ret = af9033_wr_reg(state, 0x800000, 0x01);
+		ret = af9033_wr_reg(dev, 0x800000, 0x01);
 		if (ret < 0)
 			goto err;
 	}
 
-	state->bandwidth_hz = 0; /* force to program all parameters */
+	dev->bandwidth_hz = 0; /* force to program all parameters */
+	/* init stats here in order signal app which stats are supported */
+	c->strength.len = 1;
+	c->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	c->cnr.len = 1;
+	c->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	c->block_count.len = 1;
+	c->block_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	c->block_error.len = 1;
+	c->block_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	c->post_bit_count.len = 1;
+	c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	c->post_bit_error.len = 1;
+	c->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	/* start statistics polling */
+	schedule_delayed_work(&dev->stat_work, msecs_to_jiffies(2000));
 
 	return 0;
 
 err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
 
 static int af9033_sleep(struct dvb_frontend *fe)
 {
-	struct af9033_state *state = fe->demodulator_priv;
+	struct af9033_dev *dev = fe->demodulator_priv;
 	int ret, i;
 	u8 tmp;
 
-	ret = af9033_wr_reg(state, 0x80004c, 1);
+	/* stop statistics polling */
+	cancel_delayed_work_sync(&dev->stat_work);
+
+	ret = af9033_wr_reg(dev, 0x80004c, 1);
 	if (ret < 0)
 		goto err;
 
-	ret = af9033_wr_reg(state, 0x800000, 0);
+	ret = af9033_wr_reg(dev, 0x800000, 0);
 	if (ret < 0)
 		goto err;
 
 	for (i = 100, tmp = 1; i && tmp; i--) {
-		ret = af9033_rd_reg(state, 0x80004c, &tmp);
+		ret = af9033_rd_reg(dev, 0x80004c, &tmp);
 		if (ret < 0)
 			goto err;
 
 		usleep_range(200, 10000);
 	}
 
-	dev_dbg(&state->i2c->dev, "%s: loop=%d\n", __func__, i);
+	dev_dbg(&dev->client->dev, "loop=%d\n", i);
 
 	if (i == 0) {
 		ret = -ETIMEDOUT;
 		goto err;
 	}
 
-	ret = af9033_wr_reg_mask(state, 0x80fb24, 0x08, 0x08);
+	ret = af9033_wr_reg_mask(dev, 0x80fb24, 0x08, 0x08);
 	if (ret < 0)
 		goto err;
 
 	/* prevent current leak (?) */
-	if (state->cfg.ts_mode == AF9033_TS_MODE_SERIAL) {
+	if (dev->cfg.ts_mode == AF9033_TS_MODE_SERIAL) {
 		/* enable parallel TS */
-		ret = af9033_wr_reg_mask(state, 0x00d917, 0x00, 0x01);
+		ret = af9033_wr_reg_mask(dev, 0x00d917, 0x00, 0x01);
 		if (ret < 0)
 			goto err;
 
-		ret = af9033_wr_reg_mask(state, 0x00d916, 0x01, 0x01);
+		ret = af9033_wr_reg_mask(dev, 0x00d916, 0x01, 0x01);
 		if (ret < 0)
 			goto err;
 	}
@@ -515,7 +524,7 @@ static int af9033_sleep(struct dvb_frontend *fe)
 	return 0;
 
 err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -533,14 +542,14 @@ static int af9033_get_tune_settings(struct dvb_frontend *fe,
 
 static int af9033_set_frontend(struct dvb_frontend *fe)
 {
-	struct af9033_state *state = fe->demodulator_priv;
+	struct af9033_dev *dev = fe->demodulator_priv;
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret, i, spec_inv, sampling_freq;
 	u8 tmp, buf[3], bandwidth_reg_val;
 	u32 if_frequency, freq_cw, adc_freq;
 
-	dev_dbg(&state->i2c->dev, "%s: frequency=%d bandwidth_hz=%d\n",
-			__func__, c->frequency, c->bandwidth_hz);
+	dev_dbg(&dev->client->dev, "frequency=%d bandwidth_hz=%d\n",
+			c->frequency, c->bandwidth_hz);
 
 	/* check bandwidth */
 	switch (c->bandwidth_hz) {
@@ -554,8 +563,7 @@ static int af9033_set_frontend(struct dvb_frontend *fe)
 		bandwidth_reg_val = 0x02;
 		break;
 	default:
-		dev_dbg(&state->i2c->dev, "%s: invalid bandwidth_hz\n",
-				__func__);
+		dev_dbg(&dev->client->dev, "invalid bandwidth_hz\n");
 		ret = -EINVAL;
 		goto err;
 	}
@@ -565,23 +573,23 @@ static int af9033_set_frontend(struct dvb_frontend *fe)
 		fe->ops.tuner_ops.set_params(fe);
 
 	/* program CFOE coefficients */
-	if (c->bandwidth_hz != state->bandwidth_hz) {
+	if (c->bandwidth_hz != dev->bandwidth_hz) {
 		for (i = 0; i < ARRAY_SIZE(coeff_lut); i++) {
-			if (coeff_lut[i].clock == state->cfg.clock &&
+			if (coeff_lut[i].clock == dev->cfg.clock &&
 				coeff_lut[i].bandwidth_hz == c->bandwidth_hz) {
 				break;
 			}
 		}
-		ret =  af9033_wr_regs(state, 0x800001,
+		ret =  af9033_wr_regs(dev, 0x800001,
 				coeff_lut[i].val, sizeof(coeff_lut[i].val));
 	}
 
 	/* program frequency control */
-	if (c->bandwidth_hz != state->bandwidth_hz) {
-		spec_inv = state->cfg.spec_inv ? -1 : 1;
+	if (c->bandwidth_hz != dev->bandwidth_hz) {
+		spec_inv = dev->cfg.spec_inv ? -1 : 1;
 
 		for (i = 0; i < ARRAY_SIZE(clock_adc_lut); i++) {
-			if (clock_adc_lut[i].clock == state->cfg.clock)
+			if (clock_adc_lut[i].clock == dev->cfg.clock)
 				break;
 		}
 		adc_freq = clock_adc_lut[i].adc;
@@ -602,12 +610,12 @@ static int af9033_set_frontend(struct dvb_frontend *fe)
 		else
 			sampling_freq *= -1;
 
-		freq_cw = af9033_div(state, sampling_freq, adc_freq, 23ul);
+		freq_cw = af9033_div(dev, sampling_freq, adc_freq, 23ul);
 
 		if (spec_inv == -1)
 			freq_cw = 0x800000 - freq_cw;
 
-		if (state->cfg.adc_multiplier == AF9033_ADC_MULTIPLIER_2X)
+		if (dev->cfg.adc_multiplier == AF9033_ADC_MULTIPLIER_2X)
 			freq_cw /= 2;
 
 		buf[0] = (freq_cw >>  0) & 0xff;
@@ -618,26 +626,26 @@ static int af9033_set_frontend(struct dvb_frontend *fe)
 		if (if_frequency == 0)
 			buf[2] = 0;
 
-		ret = af9033_wr_regs(state, 0x800029, buf, 3);
+		ret = af9033_wr_regs(dev, 0x800029, buf, 3);
 		if (ret < 0)
 			goto err;
 
-		state->bandwidth_hz = c->bandwidth_hz;
+		dev->bandwidth_hz = c->bandwidth_hz;
 	}
 
-	ret = af9033_wr_reg_mask(state, 0x80f904, bandwidth_reg_val, 0x03);
+	ret = af9033_wr_reg_mask(dev, 0x80f904, bandwidth_reg_val, 0x03);
 	if (ret < 0)
 		goto err;
 
-	ret = af9033_wr_reg(state, 0x800040, 0x00);
+	ret = af9033_wr_reg(dev, 0x800040, 0x00);
 	if (ret < 0)
 		goto err;
 
-	ret = af9033_wr_reg(state, 0x800047, 0x00);
+	ret = af9033_wr_reg(dev, 0x800047, 0x00);
 	if (ret < 0)
 		goto err;
 
-	ret = af9033_wr_reg_mask(state, 0x80f999, 0x00, 0x01);
+	ret = af9033_wr_reg_mask(dev, 0x80f999, 0x00, 0x01);
 	if (ret < 0)
 		goto err;
 
@@ -646,33 +654,33 @@ static int af9033_set_frontend(struct dvb_frontend *fe)
 	else
 		tmp = 0x01; /* UHF */
 
-	ret = af9033_wr_reg(state, 0x80004b, tmp);
+	ret = af9033_wr_reg(dev, 0x80004b, tmp);
 	if (ret < 0)
 		goto err;
 
-	ret = af9033_wr_reg(state, 0x800000, 0x00);
+	ret = af9033_wr_reg(dev, 0x800000, 0x00);
 	if (ret < 0)
 		goto err;
 
 	return 0;
 
 err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
 
 static int af9033_get_frontend(struct dvb_frontend *fe)
 {
-	struct af9033_state *state = fe->demodulator_priv;
+	struct af9033_dev *dev = fe->demodulator_priv;
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 	u8 buf[8];
 
-	dev_dbg(&state->i2c->dev, "%s:\n", __func__);
+	dev_dbg(&dev->client->dev, "\n");
 
 	/* read all needed registers */
-	ret = af9033_rd_regs(state, 0x80f900, buf, sizeof(buf));
+	ret = af9033_rd_regs(dev, 0x80f900, buf, sizeof(buf));
 	if (ret < 0)
 		goto err;
 
@@ -784,21 +792,21 @@ static int af9033_get_frontend(struct dvb_frontend *fe)
 	return 0;
 
 err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
 
 static int af9033_read_status(struct dvb_frontend *fe, fe_status_t *status)
 {
-	struct af9033_state *state = fe->demodulator_priv;
+	struct af9033_dev *dev = fe->demodulator_priv;
 	int ret;
 	u8 tmp;
 
 	*status = 0;
 
 	/* radio channel status, 0=no result, 1=has signal, 2=no signal */
-	ret = af9033_rd_reg(state, 0x800047, &tmp);
+	ret = af9033_rd_reg(dev, 0x800047, &tmp);
 	if (ret < 0)
 		goto err;
 
@@ -808,7 +816,7 @@ static int af9033_read_status(struct dvb_frontend *fe, fe_status_t *status)
 
 	if (tmp != 0x02) {
 		/* TPS lock */
-		ret = af9033_rd_reg_mask(state, 0x80f5a9, &tmp, 0x01);
+		ret = af9033_rd_reg_mask(dev, 0x80f5a9, &tmp, 0x01);
 		if (ret < 0)
 			goto err;
 
@@ -817,7 +825,7 @@ static int af9033_read_status(struct dvb_frontend *fe, fe_status_t *status)
 					FE_HAS_VITERBI;
 
 		/* full lock */
-		ret = af9033_rd_reg_mask(state, 0x80f999, &tmp, 0x01);
+		ret = af9033_rd_reg_mask(dev, 0x80f999, &tmp, 0x01);
 		if (ret < 0)
 			goto err;
 
@@ -827,76 +835,38 @@ static int af9033_read_status(struct dvb_frontend *fe, fe_status_t *status)
 					FE_HAS_LOCK;
 	}
 
+	dev->fe_status = *status;
+
 	return 0;
 
 err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
 
 static int af9033_read_snr(struct dvb_frontend *fe, u16 *snr)
 {
-	struct af9033_state *state = fe->demodulator_priv;
-	int ret, i, len;
-	u8 buf[3], tmp;
-	u32 snr_val;
-	const struct val_snr *uninitialized_var(snr_lut);
-
-	/* read value */
-	ret = af9033_rd_regs(state, 0x80002c, buf, 3);
-	if (ret < 0)
-		goto err;
+	struct af9033_dev *dev = fe->demodulator_priv;
+	struct dtv_frontend_properties *c = &dev->fe.dtv_property_cache;
 
-	snr_val = (buf[2] << 16) | (buf[1] << 8) | buf[0];
-
-	/* read current modulation */
-	ret = af9033_rd_reg(state, 0x80f903, &tmp);
-	if (ret < 0)
-		goto err;
-
-	switch ((tmp >> 0) & 3) {
-	case 0:
-		len = ARRAY_SIZE(qpsk_snr_lut);
-		snr_lut = qpsk_snr_lut;
-		break;
-	case 1:
-		len = ARRAY_SIZE(qam16_snr_lut);
-		snr_lut = qam16_snr_lut;
-		break;
-	case 2:
-		len = ARRAY_SIZE(qam64_snr_lut);
-		snr_lut = qam64_snr_lut;
-		break;
-	default:
-		goto err;
-	}
-
-	for (i = 0; i < len; i++) {
-		tmp = snr_lut[i].snr;
-
-		if (snr_val < snr_lut[i].val)
-			break;
-	}
-
-	*snr = tmp * 10; /* dB/10 */
+	/* use DVBv5 CNR */
+	if (c->cnr.stat[0].scale == FE_SCALE_DECIBEL)
+		*snr = div_s64(c->cnr.stat[0].svalue, 100); /* 1000x => 10x */
+	else
+		*snr = 0;
 
 	return 0;
-
-err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
-
-	return ret;
 }
 
 static int af9033_read_signal_strength(struct dvb_frontend *fe, u16 *strength)
 {
-	struct af9033_state *state = fe->demodulator_priv;
+	struct af9033_dev *dev = fe->demodulator_priv;
 	int ret;
 	u8 strength2;
 
 	/* read signal strength of 0-100 scale */
-	ret = af9033_rd_reg(state, 0x800048, &strength2);
+	ret = af9033_rd_reg(dev, 0x800048, &strength2);
 	if (ret < 0)
 		goto err;
 
@@ -906,244 +876,225 @@ static int af9033_read_signal_strength(struct dvb_frontend *fe, u16 *strength)
 	return 0;
 
 err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
-
-	return ret;
-}
-
-static int af9033_update_ch_stat(struct af9033_state *state)
-{
-	int ret = 0;
-	u32 err_cnt, bit_cnt;
-	u16 abort_cnt;
-	u8 buf[7];
-
-	/* only update data every half second */
-	if (time_after(jiffies, state->last_stat_check + msecs_to_jiffies(500))) {
-		ret = af9033_rd_regs(state, 0x800032, buf, sizeof(buf));
-		if (ret < 0)
-			goto err;
-		/* in 8 byte packets? */
-		abort_cnt = (buf[1] << 8) + buf[0];
-		/* in bits */
-		err_cnt = (buf[4] << 16) + (buf[3] << 8) + buf[2];
-		/* in 8 byte packets? always(?) 0x2710 = 10000 */
-		bit_cnt = (buf[6] << 8) + buf[5];
-
-		if (bit_cnt < abort_cnt) {
-			abort_cnt = 1000;
-			state->ber = 0xffffffff;
-		} else {
-			/* 8 byte packets, that have not been rejected already */
-			bit_cnt -= (u32)abort_cnt;
-			if (bit_cnt == 0) {
-				state->ber = 0xffffffff;
-			} else {
-				err_cnt -= (u32)abort_cnt * 8 * 8;
-				bit_cnt *= 8 * 8;
-				state->ber = err_cnt * (0xffffffff / bit_cnt);
-			}
-		}
-		state->ucb += abort_cnt;
-		state->last_stat_check = jiffies;
-	}
-
-	return 0;
-err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
 
 static int af9033_read_ber(struct dvb_frontend *fe, u32 *ber)
 {
-	struct af9033_state *state = fe->demodulator_priv;
-	int ret;
-
-	ret = af9033_update_ch_stat(state);
-	if (ret < 0)
-		return ret;
+	struct af9033_dev *dev = fe->demodulator_priv;
 
-	*ber = state->ber;
+	*ber = (dev->post_bit_error - dev->post_bit_error_prev);
+	dev->post_bit_error_prev = dev->post_bit_error;
 
 	return 0;
 }
 
 static int af9033_read_ucblocks(struct dvb_frontend *fe, u32 *ucblocks)
 {
-	struct af9033_state *state = fe->demodulator_priv;
-	int ret;
-
-	ret = af9033_update_ch_stat(state);
-	if (ret < 0)
-		return ret;
-
-	*ucblocks = state->ucb;
+	struct af9033_dev *dev = fe->demodulator_priv;
 
+	*ucblocks = dev->error_block_count;
 	return 0;
 }
 
 static int af9033_i2c_gate_ctrl(struct dvb_frontend *fe, int enable)
 {
-	struct af9033_state *state = fe->demodulator_priv;
+	struct af9033_dev *dev = fe->demodulator_priv;
 	int ret;
 
-	dev_dbg(&state->i2c->dev, "%s: enable=%d\n", __func__, enable);
+	dev_dbg(&dev->client->dev, "enable=%d\n", enable);
 
-	ret = af9033_wr_reg_mask(state, 0x00fa04, enable, 0x01);
+	ret = af9033_wr_reg_mask(dev, 0x00fa04, enable, 0x01);
 	if (ret < 0)
 		goto err;
 
 	return 0;
 
 err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
 
 static int af9033_pid_filter_ctrl(struct dvb_frontend *fe, int onoff)
 {
-	struct af9033_state *state = fe->demodulator_priv;
+	struct af9033_dev *dev = fe->demodulator_priv;
 	int ret;
 
-	dev_dbg(&state->i2c->dev, "%s: onoff=%d\n", __func__, onoff);
+	dev_dbg(&dev->client->dev, "onoff=%d\n", onoff);
 
-	ret = af9033_wr_reg_mask(state, 0x80f993, onoff, 0x01);
+	ret = af9033_wr_reg_mask(dev, 0x80f993, onoff, 0x01);
 	if (ret < 0)
 		goto err;
 
 	return 0;
 
 err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
 
-static int af9033_pid_filter(struct dvb_frontend *fe, int index, u16 pid, int onoff)
+static int af9033_pid_filter(struct dvb_frontend *fe, int index, u16 pid,
+		int onoff)
 {
-	struct af9033_state *state = fe->demodulator_priv;
+	struct af9033_dev *dev = fe->demodulator_priv;
 	int ret;
 	u8 wbuf[2] = {(pid >> 0) & 0xff, (pid >> 8) & 0xff};
 
-	dev_dbg(&state->i2c->dev, "%s: index=%d pid=%04x onoff=%d\n",
-			__func__, index, pid, onoff);
+	dev_dbg(&dev->client->dev, "index=%d pid=%04x onoff=%d\n",
+			index, pid, onoff);
 
 	if (pid > 0x1fff)
 		return 0;
 
-	ret = af9033_wr_regs(state, 0x80f996, wbuf, 2);
+	ret = af9033_wr_regs(dev, 0x80f996, wbuf, 2);
 	if (ret < 0)
 		goto err;
 
-	ret = af9033_wr_reg(state, 0x80f994, onoff);
+	ret = af9033_wr_reg(dev, 0x80f994, onoff);
 	if (ret < 0)
 		goto err;
 
-	ret = af9033_wr_reg(state, 0x80f995, index);
+	ret = af9033_wr_reg(dev, 0x80f995, index);
 	if (ret < 0)
 		goto err;
 
 	return 0;
 
 err:
-	dev_dbg(&state->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
 
-static struct dvb_frontend_ops af9033_ops;
-
-struct dvb_frontend *af9033_attach(const struct af9033_config *config,
-				   struct i2c_adapter *i2c,
-				   struct af9033_ops *ops)
+static void af9033_stat_work(struct work_struct *work)
 {
-	int ret;
-	struct af9033_state *state;
-	u8 buf[8];
+	struct af9033_dev *dev = container_of(work, struct af9033_dev, stat_work.work);
+	struct dtv_frontend_properties *c = &dev->fe.dtv_property_cache;
+	int ret, tmp, i, len;
+	u8 u8tmp, buf[7];
+
+	dev_dbg(&dev->client->dev, "\n");
+
+	/* signal strength */
+	if (dev->fe_status & FE_HAS_SIGNAL) {
+		if (dev->is_af9035) {
+			ret = af9033_rd_reg(dev, 0x80004a, &u8tmp);
+			tmp = -u8tmp * 1000;
+		} else {
+			ret = af9033_rd_reg(dev, 0x8000f7, &u8tmp);
+			tmp = (u8tmp - 100) * 1000;
+		}
+		if (ret)
+			goto err;
 
-	dev_dbg(&i2c->dev, "%s:\n", __func__);
+		c->strength.len = 1;
+		c->strength.stat[0].scale = FE_SCALE_DECIBEL;
+		c->strength.stat[0].svalue = tmp;
+	} else {
+		c->strength.len = 1;
+		c->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	}
 
-	/* allocate memory for the internal state */
-	state = kzalloc(sizeof(struct af9033_state), GFP_KERNEL);
-	if (state == NULL)
-		goto err;
+	/* CNR */
+	if (dev->fe_status & FE_HAS_VITERBI) {
+		u32 snr_val;
+		const struct val_snr *snr_lut;
 
-	/* setup the state */
-	state->i2c = i2c;
-	memcpy(&state->cfg, config, sizeof(struct af9033_config));
+		/* read value */
+		ret = af9033_rd_regs(dev, 0x80002c, buf, 3);
+		if (ret)
+			goto err;
 
-	if (state->cfg.clock != 12000000) {
-		dev_err(&state->i2c->dev, "%s: af9033: unsupported clock=%d, " \
-				"only 12000000 Hz is supported currently\n",
-				KBUILD_MODNAME, state->cfg.clock);
-		goto err;
-	}
+		snr_val = (buf[2] << 16) | (buf[1] << 8) | (buf[0] << 0);
 
-	/* firmware version */
-	ret = af9033_rd_regs(state, 0x0083e9, &buf[0], 4);
-	if (ret < 0)
-		goto err;
+		/* read current modulation */
+		ret = af9033_rd_reg(dev, 0x80f903, &u8tmp);
+		if (ret)
+			goto err;
 
-	ret = af9033_rd_regs(state, 0x804191, &buf[4], 4);
-	if (ret < 0)
-		goto err;
+		switch ((u8tmp >> 0) & 3) {
+		case 0:
+			len = ARRAY_SIZE(qpsk_snr_lut);
+			snr_lut = qpsk_snr_lut;
+			break;
+		case 1:
+			len = ARRAY_SIZE(qam16_snr_lut);
+			snr_lut = qam16_snr_lut;
+			break;
+		case 2:
+			len = ARRAY_SIZE(qam64_snr_lut);
+			snr_lut = qam64_snr_lut;
+			break;
+		default:
+			goto err_schedule_delayed_work;
+		}
 
-	dev_info(&state->i2c->dev, "%s: firmware version: LINK=%d.%d.%d.%d " \
-			"OFDM=%d.%d.%d.%d\n", KBUILD_MODNAME, buf[0], buf[1],
-			buf[2], buf[3], buf[4], buf[5], buf[6], buf[7]);
+		for (i = 0; i < len; i++) {
+			tmp = snr_lut[i].snr * 1000;
+			if (snr_val < snr_lut[i].val)
+				break;
+		}
 
-	/* sleep */
-	switch (state->cfg.tuner) {
-	case AF9033_TUNER_IT9135_38:
-	case AF9033_TUNER_IT9135_51:
-	case AF9033_TUNER_IT9135_52:
-	case AF9033_TUNER_IT9135_60:
-	case AF9033_TUNER_IT9135_61:
-	case AF9033_TUNER_IT9135_62:
-		/* IT9135 did not like to sleep at that early */
-		break;
-	default:
-		ret = af9033_wr_reg(state, 0x80004c, 1);
-		if (ret < 0)
-			goto err;
+		c->cnr.len = 1;
+		c->cnr.stat[0].scale = FE_SCALE_DECIBEL;
+		c->cnr.stat[0].svalue = tmp;
+	} else {
+		c->cnr.len = 1;
+		c->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	}
 
-		ret = af9033_wr_reg(state, 0x800000, 0);
-		if (ret < 0)
+	/* UCB/PER/BER */
+	if (dev->fe_status & FE_HAS_LOCK) {
+		/* outer FEC, 204 byte packets */
+		u16 abort_packet_count, rsd_packet_count;
+		/* inner FEC, bits */
+		u32 rsd_bit_err_count;
+
+		/*
+		 * Packet count used for measurement is 10000
+		 * (rsd_packet_count). Maybe it should be increased?
+		 */
+
+		ret = af9033_rd_regs(dev, 0x800032, buf, 7);
+		if (ret)
 			goto err;
-	}
 
-	/* configure internal TS mode */
-	switch (state->cfg.ts_mode) {
-	case AF9033_TS_MODE_PARALLEL:
-		state->ts_mode_parallel = true;
-		break;
-	case AF9033_TS_MODE_SERIAL:
-		state->ts_mode_serial = true;
-		break;
-	case AF9033_TS_MODE_USB:
-		/* usb mode for AF9035 */
-	default:
-		break;
-	}
+		abort_packet_count = (buf[1] << 8) | (buf[0] << 0);
+		rsd_bit_err_count = (buf[4] << 16) | (buf[3] << 8) | buf[2];
+		rsd_packet_count = (buf[6] << 8) | (buf[5] << 0);
 
-	/* create dvb_frontend */
-	memcpy(&state->fe.ops, &af9033_ops, sizeof(struct dvb_frontend_ops));
-	state->fe.demodulator_priv = state;
+		dev->error_block_count += abort_packet_count;
+		dev->total_block_count += rsd_packet_count;
+		dev->post_bit_error += rsd_bit_err_count;
+		dev->post_bit_count += rsd_packet_count * 204 * 8;
 
-	if (ops) {
-		ops->pid_filter = af9033_pid_filter;
-		ops->pid_filter_ctrl = af9033_pid_filter_ctrl;
-	}
+		c->block_count.len = 1;
+		c->block_count.stat[0].scale = FE_SCALE_COUNTER;
+		c->block_count.stat[0].uvalue = dev->total_block_count;
+
+		c->block_error.len = 1;
+		c->block_error.stat[0].scale = FE_SCALE_COUNTER;
+		c->block_error.stat[0].uvalue = dev->error_block_count;
+
+		c->post_bit_count.len = 1;
+		c->post_bit_count.stat[0].scale = FE_SCALE_COUNTER;
+		c->post_bit_count.stat[0].uvalue = dev->post_bit_count;
 
-	return &state->fe;
+		c->post_bit_error.len = 1;
+		c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
+		c->post_bit_error.stat[0].uvalue = dev->post_bit_error;
+	}
 
+err_schedule_delayed_work:
+	schedule_delayed_work(&dev->stat_work, msecs_to_jiffies(2000));
+	return;
 err:
-	kfree(state);
-	return NULL;
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 }
-EXPORT_SYMBOL(af9033_attach);
 
 static struct dvb_frontend_ops af9033_ops = {
 	.delsys = { SYS_DVBT },
@@ -1170,8 +1121,6 @@ static struct dvb_frontend_ops af9033_ops = {
 			FE_CAN_MUTE_TS
 	},
 
-	.release = af9033_release,
-
 	.init = af9033_init,
 	.sleep = af9033_sleep,
 
@@ -1188,6 +1137,150 @@ static struct dvb_frontend_ops af9033_ops = {
 	.i2c_gate_ctrl = af9033_i2c_gate_ctrl,
 };
 
+static int af9033_probe(struct i2c_client *client,
+		const struct i2c_device_id *id)
+{
+	struct af9033_config *cfg = client->dev.platform_data;
+	struct af9033_dev *dev;
+	int ret;
+	u8 buf[8];
+	u32 reg;
+
+	/* allocate memory for the internal state */
+	dev = kzalloc(sizeof(struct af9033_dev), GFP_KERNEL);
+	if (dev == NULL) {
+		ret = -ENOMEM;
+		dev_err(&client->dev, "Could not allocate memory for state\n");
+		goto err;
+	}
+
+	/* setup the state */
+	dev->client = client;
+	INIT_DELAYED_WORK(&dev->stat_work, af9033_stat_work);
+	memcpy(&dev->cfg, cfg, sizeof(struct af9033_config));
+
+	if (dev->cfg.clock != 12000000) {
+		ret = -ENODEV;
+		dev_err(&dev->client->dev,
+				"unsupported clock %d Hz, only 12000000 Hz is supported currently\n",
+				dev->cfg.clock);
+		goto err_kfree;
+	}
+
+	/* firmware version */
+	switch (dev->cfg.tuner) {
+	case AF9033_TUNER_IT9135_38:
+	case AF9033_TUNER_IT9135_51:
+	case AF9033_TUNER_IT9135_52:
+	case AF9033_TUNER_IT9135_60:
+	case AF9033_TUNER_IT9135_61:
+	case AF9033_TUNER_IT9135_62:
+		dev->is_it9135 = true;
+		reg = 0x004bfc;
+		break;
+	default:
+		dev->is_af9035 = true;
+		reg = 0x0083e9;
+		break;
+	}
+
+	ret = af9033_rd_regs(dev, reg, &buf[0], 4);
+	if (ret < 0)
+		goto err_kfree;
+
+	ret = af9033_rd_regs(dev, 0x804191, &buf[4], 4);
+	if (ret < 0)
+		goto err_kfree;
+
+	dev_info(&dev->client->dev,
+			"firmware version: LINK %d.%d.%d.%d - OFDM %d.%d.%d.%d\n",
+			buf[0], buf[1], buf[2], buf[3], buf[4], buf[5], buf[6],
+			buf[7]);
+
+	/* sleep */
+	switch (dev->cfg.tuner) {
+	case AF9033_TUNER_IT9135_38:
+	case AF9033_TUNER_IT9135_51:
+	case AF9033_TUNER_IT9135_52:
+	case AF9033_TUNER_IT9135_60:
+	case AF9033_TUNER_IT9135_61:
+	case AF9033_TUNER_IT9135_62:
+		/* IT9135 did not like to sleep at that early */
+		break;
+	default:
+		ret = af9033_wr_reg(dev, 0x80004c, 1);
+		if (ret < 0)
+			goto err_kfree;
+
+		ret = af9033_wr_reg(dev, 0x800000, 0);
+		if (ret < 0)
+			goto err_kfree;
+	}
+
+	/* configure internal TS mode */
+	switch (dev->cfg.ts_mode) {
+	case AF9033_TS_MODE_PARALLEL:
+		dev->ts_mode_parallel = true;
+		break;
+	case AF9033_TS_MODE_SERIAL:
+		dev->ts_mode_serial = true;
+		break;
+	case AF9033_TS_MODE_USB:
+		/* usb mode for AF9035 */
+	default:
+		break;
+	}
+
+	/* create dvb_frontend */
+	memcpy(&dev->fe.ops, &af9033_ops, sizeof(struct dvb_frontend_ops));
+	dev->fe.demodulator_priv = dev;
+	*cfg->fe = &dev->fe;
+	if (cfg->ops) {
+		cfg->ops->pid_filter = af9033_pid_filter;
+		cfg->ops->pid_filter_ctrl = af9033_pid_filter_ctrl;
+	}
+	i2c_set_clientdata(client, dev);
+
+	dev_info(&dev->client->dev, "Afatech AF9033 successfully attached\n");
+	return 0;
+err_kfree:
+	kfree(dev);
+err:
+	dev_dbg(&client->dev, "failed=%d\n", ret);
+	return ret;
+}
+
+static int af9033_remove(struct i2c_client *client)
+{
+	struct af9033_dev *dev = i2c_get_clientdata(client);
+
+	dev_dbg(&dev->client->dev, "\n");
+
+	dev->fe.ops.release = NULL;
+	dev->fe.demodulator_priv = NULL;
+	kfree(dev);
+
+	return 0;
+}
+
+static const struct i2c_device_id af9033_id_table[] = {
+	{"af9033", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, af9033_id_table);
+
+static struct i2c_driver af9033_driver = {
+	.driver = {
+		.owner	= THIS_MODULE,
+		.name	= "af9033",
+	},
+	.probe		= af9033_probe,
+	.remove		= af9033_remove,
+	.id_table	= af9033_id_table,
+};
+
+module_i2c_driver(af9033_driver);
+
 MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>");
 MODULE_DESCRIPTION("Afatech AF9033 DVB-T demodulator driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/af9033.h b/drivers/media/dvb-frontends/af9033.h
index 539f4db678b8..6ad22b69a636 100644
--- a/drivers/media/dvb-frontends/af9033.h
+++ b/drivers/media/dvb-frontends/af9033.h
@@ -24,13 +24,12 @@
 
 #include <linux/kconfig.h>
 
+/*
+ * I2C address (TODO: are these in 8-bit format?)
+ * 0x38, 0x3a, 0x3c, 0x3e
+ */
 struct af9033_config {
 	/*
-	 * I2C address
-	 */
-	u8 i2c_addr;
-
-	/*
 	 * clock Hz
 	 * 12000000, 22000000, 24000000, 34000000, 32000000, 28000000, 26000000,
 	 * 30000000, 36000000, 20480000, 16384000
@@ -75,8 +74,23 @@ struct af9033_config {
 	 * input spectrum inversion
 	 */
 	bool spec_inv;
-};
 
+	/*
+	 *
+	 */
+	bool dyn0_clk;
+
+	/*
+	 * PID filter ops
+	 */
+	struct af9033_ops *ops;
+
+	/*
+	 * frontend
+	 * returned by that driver
+	 */
+	struct dvb_frontend **fe;
+};
 
 struct af9033_ops {
 	int (*pid_filter_ctrl)(struct dvb_frontend *fe, int onoff);
@@ -84,36 +98,4 @@ struct af9033_ops {
 			  int onoff);
 };
 
-
-#if IS_ENABLED(CONFIG_DVB_AF9033)
-extern
-struct dvb_frontend *af9033_attach(const struct af9033_config *config,
-				   struct i2c_adapter *i2c,
-				   struct af9033_ops *ops);
-
-#else
-static inline
-struct dvb_frontend *af9033_attach(const struct af9033_config *config,
-				   struct i2c_adapter *i2c,
-				   struct af9033_ops *ops)
-{
-	pr_warn("%s: driver disabled by Kconfig\n", __func__);
-	return NULL;
-}
-
-static inline int af9033_pid_filter_ctrl(struct dvb_frontend *fe, int onoff)
-{
-	pr_warn("%s: driver disabled by Kconfig\n", __func__);
-	return -ENODEV;
-}
-
-static inline int af9033_pid_filter(struct dvb_frontend *fe, int index, u16 pid,
-	int onoff)
-{
-	pr_warn("%s: driver disabled by Kconfig\n", __func__);
-	return -ENODEV;
-}
-
-#endif
-
 #endif /* AF9033_H */
diff --git a/drivers/media/dvb-frontends/af9033_priv.h b/drivers/media/dvb-frontends/af9033_priv.h
index ded7b67d7526..c12c92cb5855 100644
--- a/drivers/media/dvb-frontends/af9033_priv.h
+++ b/drivers/media/dvb-frontends/af9033_priv.h
@@ -24,6 +24,7 @@
 
 #include "dvb_frontend.h"
 #include "af9033.h"
+#include <linux/math64.h>
 
 struct reg_val {
 	u32 reg;
diff --git a/drivers/media/dvb-frontends/as102_fe.c b/drivers/media/dvb-frontends/as102_fe.c
new file mode 100644
index 000000000000..493665899565
--- /dev/null
+++ b/drivers/media/dvb-frontends/as102_fe.c
@@ -0,0 +1,480 @@
+/*
+ * Abilis Systems Single DVB-T Receiver
+ * Copyright (C) 2008 Pierrick Hascoet <pierrick.hascoet@abilis.com>
+ * Copyright (C) 2010 Devin Heitmueller <dheitmueller@kernellabs.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <dvb_frontend.h>
+
+#include "as102_fe.h"
+
+struct as102_state {
+	struct dvb_frontend frontend;
+	struct as10x_demod_stats demod_stats;
+
+	const struct as102_fe_ops *ops;
+	void *priv;
+	uint8_t elna_cfg;
+
+	/* signal strength */
+	uint16_t signal_strength;
+	/* bit error rate */
+	uint32_t ber;
+};
+
+static uint8_t as102_fe_get_code_rate(fe_code_rate_t arg)
+{
+	uint8_t c;
+
+	switch (arg) {
+	case FEC_1_2:
+		c = CODE_RATE_1_2;
+		break;
+	case FEC_2_3:
+		c = CODE_RATE_2_3;
+		break;
+	case FEC_3_4:
+		c = CODE_RATE_3_4;
+		break;
+	case FEC_5_6:
+		c = CODE_RATE_5_6;
+		break;
+	case FEC_7_8:
+		c = CODE_RATE_7_8;
+		break;
+	default:
+		c = CODE_RATE_UNKNOWN;
+		break;
+	}
+
+	return c;
+}
+
+static int as102_fe_set_frontend(struct dvb_frontend *fe)
+{
+	struct as102_state *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	struct as10x_tune_args tune_args = { 0 };
+
+	/* set frequency */
+	tune_args.freq = c->frequency / 1000;
+
+	/* fix interleaving_mode */
+	tune_args.interleaving_mode = INTLV_NATIVE;
+
+	switch (c->bandwidth_hz) {
+	case 8000000:
+		tune_args.bandwidth = BW_8_MHZ;
+		break;
+	case 7000000:
+		tune_args.bandwidth = BW_7_MHZ;
+		break;
+	case 6000000:
+		tune_args.bandwidth = BW_6_MHZ;
+		break;
+	default:
+		tune_args.bandwidth = BW_8_MHZ;
+	}
+
+	switch (c->guard_interval) {
+	case GUARD_INTERVAL_1_32:
+		tune_args.guard_interval = GUARD_INT_1_32;
+		break;
+	case GUARD_INTERVAL_1_16:
+		tune_args.guard_interval = GUARD_INT_1_16;
+		break;
+	case GUARD_INTERVAL_1_8:
+		tune_args.guard_interval = GUARD_INT_1_8;
+		break;
+	case GUARD_INTERVAL_1_4:
+		tune_args.guard_interval = GUARD_INT_1_4;
+		break;
+	case GUARD_INTERVAL_AUTO:
+	default:
+		tune_args.guard_interval = GUARD_UNKNOWN;
+		break;
+	}
+
+	switch (c->modulation) {
+	case QPSK:
+		tune_args.modulation = CONST_QPSK;
+		break;
+	case QAM_16:
+		tune_args.modulation = CONST_QAM16;
+		break;
+	case QAM_64:
+		tune_args.modulation = CONST_QAM64;
+		break;
+	default:
+		tune_args.modulation = CONST_UNKNOWN;
+		break;
+	}
+
+	switch (c->transmission_mode) {
+	case TRANSMISSION_MODE_2K:
+		tune_args.transmission_mode = TRANS_MODE_2K;
+		break;
+	case TRANSMISSION_MODE_8K:
+		tune_args.transmission_mode = TRANS_MODE_8K;
+		break;
+	default:
+		tune_args.transmission_mode = TRANS_MODE_UNKNOWN;
+	}
+
+	switch (c->hierarchy) {
+	case HIERARCHY_NONE:
+		tune_args.hierarchy = HIER_NONE;
+		break;
+	case HIERARCHY_1:
+		tune_args.hierarchy = HIER_ALPHA_1;
+		break;
+	case HIERARCHY_2:
+		tune_args.hierarchy = HIER_ALPHA_2;
+		break;
+	case HIERARCHY_4:
+		tune_args.hierarchy = HIER_ALPHA_4;
+		break;
+	case HIERARCHY_AUTO:
+		tune_args.hierarchy = HIER_UNKNOWN;
+		break;
+	}
+
+	pr_debug("as102: tuner parameters: freq: %d  bw: 0x%02x  gi: 0x%02x\n",
+			c->frequency,
+			tune_args.bandwidth,
+			tune_args.guard_interval);
+
+	/*
+	 * Detect a hierarchy selection
+	 * if HP/LP are both set to FEC_NONE, HP will be selected.
+	 */
+	if ((tune_args.hierarchy != HIER_NONE) &&
+		       ((c->code_rate_LP == FEC_NONE) ||
+			(c->code_rate_HP == FEC_NONE))) {
+
+		if (c->code_rate_LP == FEC_NONE) {
+			tune_args.hier_select = HIER_HIGH_PRIORITY;
+			tune_args.code_rate =
+			   as102_fe_get_code_rate(c->code_rate_HP);
+		}
+
+		if (c->code_rate_HP == FEC_NONE) {
+			tune_args.hier_select = HIER_LOW_PRIORITY;
+			tune_args.code_rate =
+			   as102_fe_get_code_rate(c->code_rate_LP);
+		}
+
+		pr_debug("as102: \thierarchy: 0x%02x  selected: %s  code_rate_%s: 0x%02x\n",
+			tune_args.hierarchy,
+			tune_args.hier_select == HIER_HIGH_PRIORITY ?
+			"HP" : "LP",
+			tune_args.hier_select == HIER_HIGH_PRIORITY ?
+			"HP" : "LP",
+			tune_args.code_rate);
+	} else {
+		tune_args.code_rate =
+			as102_fe_get_code_rate(c->code_rate_HP);
+	}
+
+	/* Set frontend arguments */
+	return state->ops->set_tune(state->priv, &tune_args);
+}
+
+static int as102_fe_get_frontend(struct dvb_frontend *fe)
+{
+	struct as102_state *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	int ret = 0;
+	struct as10x_tps tps = { 0 };
+
+	/* send abilis command: GET_TPS */
+	ret = state->ops->get_tps(state->priv, &tps);
+	if (ret < 0)
+		return ret;
+
+	/* extract constellation */
+	switch (tps.modulation) {
+	case CONST_QPSK:
+		c->modulation = QPSK;
+		break;
+	case CONST_QAM16:
+		c->modulation = QAM_16;
+		break;
+	case CONST_QAM64:
+		c->modulation = QAM_64;
+		break;
+	}
+
+	/* extract hierarchy */
+	switch (tps.hierarchy) {
+	case HIER_NONE:
+		c->hierarchy = HIERARCHY_NONE;
+		break;
+	case HIER_ALPHA_1:
+		c->hierarchy = HIERARCHY_1;
+		break;
+	case HIER_ALPHA_2:
+		c->hierarchy = HIERARCHY_2;
+		break;
+	case HIER_ALPHA_4:
+		c->hierarchy = HIERARCHY_4;
+		break;
+	}
+
+	/* extract code rate HP */
+	switch (tps.code_rate_HP) {
+	case CODE_RATE_1_2:
+		c->code_rate_HP = FEC_1_2;
+		break;
+	case CODE_RATE_2_3:
+		c->code_rate_HP = FEC_2_3;
+		break;
+	case CODE_RATE_3_4:
+		c->code_rate_HP = FEC_3_4;
+		break;
+	case CODE_RATE_5_6:
+		c->code_rate_HP = FEC_5_6;
+		break;
+	case CODE_RATE_7_8:
+		c->code_rate_HP = FEC_7_8;
+		break;
+	}
+
+	/* extract code rate LP */
+	switch (tps.code_rate_LP) {
+	case CODE_RATE_1_2:
+		c->code_rate_LP = FEC_1_2;
+		break;
+	case CODE_RATE_2_3:
+		c->code_rate_LP = FEC_2_3;
+		break;
+	case CODE_RATE_3_4:
+		c->code_rate_LP = FEC_3_4;
+		break;
+	case CODE_RATE_5_6:
+		c->code_rate_LP = FEC_5_6;
+		break;
+	case CODE_RATE_7_8:
+		c->code_rate_LP = FEC_7_8;
+		break;
+	}
+
+	/* extract guard interval */
+	switch (tps.guard_interval) {
+	case GUARD_INT_1_32:
+		c->guard_interval = GUARD_INTERVAL_1_32;
+		break;
+	case GUARD_INT_1_16:
+		c->guard_interval = GUARD_INTERVAL_1_16;
+		break;
+	case GUARD_INT_1_8:
+		c->guard_interval = GUARD_INTERVAL_1_8;
+		break;
+	case GUARD_INT_1_4:
+		c->guard_interval = GUARD_INTERVAL_1_4;
+		break;
+	}
+
+	/* extract transmission mode */
+	switch (tps.transmission_mode) {
+	case TRANS_MODE_2K:
+		c->transmission_mode = TRANSMISSION_MODE_2K;
+		break;
+	case TRANS_MODE_8K:
+		c->transmission_mode = TRANSMISSION_MODE_8K;
+		break;
+	}
+
+	return 0;
+}
+
+static int as102_fe_get_tune_settings(struct dvb_frontend *fe,
+			struct dvb_frontend_tune_settings *settings) {
+
+	settings->min_delay_ms = 1000;
+
+	return 0;
+}
+
+static int as102_fe_read_status(struct dvb_frontend *fe, fe_status_t *status)
+{
+	int ret = 0;
+	struct as102_state *state = fe->demodulator_priv;
+	struct as10x_tune_status tstate = { 0 };
+
+	/* send abilis command: GET_TUNE_STATUS */
+	ret = state->ops->get_status(state->priv, &tstate);
+	if (ret < 0)
+		return ret;
+
+	state->signal_strength  = tstate.signal_strength;
+	state->ber  = tstate.BER;
+
+	switch (tstate.tune_state) {
+	case TUNE_STATUS_SIGNAL_DVB_OK:
+		*status = FE_HAS_SIGNAL | FE_HAS_CARRIER;
+		break;
+	case TUNE_STATUS_STREAM_DETECTED:
+		*status = FE_HAS_SIGNAL | FE_HAS_CARRIER | FE_HAS_SYNC |
+			  FE_HAS_VITERBI;
+		break;
+	case TUNE_STATUS_STREAM_TUNED:
+		*status = FE_HAS_SIGNAL | FE_HAS_CARRIER | FE_HAS_SYNC |
+			  FE_HAS_LOCK | FE_HAS_VITERBI;
+		break;
+	default:
+		*status = TUNE_STATUS_NOT_TUNED;
+	}
+
+	pr_debug("as102: tuner status: 0x%02x, strength %d, per: %d, ber: %d\n",
+		 tstate.tune_state, tstate.signal_strength,
+		 tstate.PER, tstate.BER);
+
+	if (!(*status & FE_HAS_LOCK)) {
+		memset(&state->demod_stats, 0, sizeof(state->demod_stats));
+		return 0;
+	}
+
+	ret = state->ops->get_stats(state->priv, &state->demod_stats);
+	if (ret < 0)
+		memset(&state->demod_stats, 0, sizeof(state->demod_stats));
+
+	return ret;
+}
+
+/*
+ * Note:
+ * - in AS102 SNR=MER
+ *   - the SNR will be returned in linear terms, i.e. not in dB
+ *   - the accuracy equals ±2dB for a SNR range from 4dB to 30dB
+ *   - the accuracy is >2dB for SNR values outside this range
+ */
+static int as102_fe_read_snr(struct dvb_frontend *fe, u16 *snr)
+{
+	struct as102_state *state = fe->demodulator_priv;
+
+	*snr = state->demod_stats.mer;
+
+	return 0;
+}
+
+static int as102_fe_read_ber(struct dvb_frontend *fe, u32 *ber)
+{
+	struct as102_state *state = fe->demodulator_priv;
+
+	*ber = state->ber;
+
+	return 0;
+}
+
+static int as102_fe_read_signal_strength(struct dvb_frontend *fe,
+					 u16 *strength)
+{
+	struct as102_state *state = fe->demodulator_priv;
+
+	*strength = (((0xffff * 400) * state->signal_strength + 41000) * 2);
+
+	return 0;
+}
+
+static int as102_fe_read_ucblocks(struct dvb_frontend *fe, u32 *ucblocks)
+{
+	struct as102_state *state = fe->demodulator_priv;
+
+	if (state->demod_stats.has_started)
+		*ucblocks = state->demod_stats.bad_frame_count;
+	else
+		*ucblocks = 0;
+
+	return 0;
+}
+
+static int as102_fe_ts_bus_ctrl(struct dvb_frontend *fe, int acquire)
+{
+	struct as102_state *state = fe->demodulator_priv;
+
+	return state->ops->stream_ctrl(state->priv, acquire,
+				      state->elna_cfg);
+}
+
+static void as102_fe_release(struct dvb_frontend *fe)
+{
+	struct as102_state *state = fe->demodulator_priv;
+
+	kfree(state);
+}
+
+
+static struct dvb_frontend_ops as102_fe_ops = {
+	.delsys = { SYS_DVBT },
+	.info = {
+		.name			= "Abilis AS102 DVB-T",
+		.frequency_min		= 174000000,
+		.frequency_max		= 862000000,
+		.frequency_stepsize	= 166667,
+		.caps = FE_CAN_INVERSION_AUTO
+			| FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4
+			| FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO
+			| FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QPSK
+			| FE_CAN_QAM_AUTO
+			| FE_CAN_TRANSMISSION_MODE_AUTO
+			| FE_CAN_GUARD_INTERVAL_AUTO
+			| FE_CAN_HIERARCHY_AUTO
+			| FE_CAN_RECOVER
+			| FE_CAN_MUTE_TS
+	},
+
+	.set_frontend		= as102_fe_set_frontend,
+	.get_frontend		= as102_fe_get_frontend,
+	.get_tune_settings	= as102_fe_get_tune_settings,
+
+	.read_status		= as102_fe_read_status,
+	.read_snr		= as102_fe_read_snr,
+	.read_ber		= as102_fe_read_ber,
+	.read_signal_strength	= as102_fe_read_signal_strength,
+	.read_ucblocks		= as102_fe_read_ucblocks,
+	.ts_bus_ctrl		= as102_fe_ts_bus_ctrl,
+	.release		= as102_fe_release,
+};
+
+struct dvb_frontend *as102_attach(const char *name,
+				  const struct as102_fe_ops *ops,
+				  void *priv,
+				  uint8_t elna_cfg)
+{
+	struct as102_state *state;
+	struct dvb_frontend *fe;
+
+	state = kzalloc(sizeof(struct as102_state), GFP_KERNEL);
+	if (state == NULL) {
+		pr_err("%s: unable to allocate memory for state\n", __func__);
+		return NULL;
+	}
+	fe = &state->frontend;
+	fe->demodulator_priv = state;
+	state->ops = ops;
+	state->priv = priv;
+	state->elna_cfg = elna_cfg;
+
+	/* init frontend callback ops */
+	memcpy(&fe->ops, &as102_fe_ops, sizeof(struct dvb_frontend_ops));
+	strncpy(fe->ops.info.name, name, sizeof(fe->ops.info.name));
+
+	return fe;
+
+}
+EXPORT_SYMBOL_GPL(as102_attach);
+
+MODULE_DESCRIPTION("as102-fe");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pierrick Hascoet <pierrick.hascoet@abilis.com>");
diff --git a/drivers/media/dvb-frontends/as102_fe.h b/drivers/media/dvb-frontends/as102_fe.h
new file mode 100644
index 000000000000..a7c91430ca3d
--- /dev/null
+++ b/drivers/media/dvb-frontends/as102_fe.h
@@ -0,0 +1,29 @@
+/*
+ * Abilis Systems Single DVB-T Receiver
+ * Copyright (C) 2014 Mauro Carvalho Chehab <m.chehab@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "as102_fe_types.h"
+
+struct as102_fe_ops {
+	int (*set_tune)(void *priv, struct as10x_tune_args *tune_args);
+	int (*get_tps)(void *priv, struct as10x_tps *tps);
+	int (*get_status)(void *priv, struct as10x_tune_status *tstate);
+	int (*get_stats)(void *priv, struct as10x_demod_stats *demod_stats);
+	int (*stream_ctrl)(void *priv, int acquire, uint32_t elna_cfg);
+};
+
+struct dvb_frontend *as102_attach(const char *name,
+				  const struct as102_fe_ops *ops,
+				  void *priv,
+				  uint8_t elna_cfg);
diff --git a/drivers/staging/media/as102/as10x_types.h b/drivers/media/dvb-frontends/as102_fe_types.h
index af26e057d9a2..80a5398b580f 100644
--- a/drivers/staging/media/as102/as10x_types.h
+++ b/drivers/media/dvb-frontends/as102_fe_types.h
@@ -11,16 +11,10 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #ifndef _AS10X_TYPES_H_
 #define _AS10X_TYPES_H_
 
-#include "as10x_handle.h"
-
 /*********************************/
 /*       MACRO DEFINITIONS       */
 /*********************************/
diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c
index 39a29dd29519..638c7aa0fb7e 100644
--- a/drivers/media/dvb-frontends/bcm3510.c
+++ b/drivers/media/dvb-frontends/bcm3510.c
@@ -639,12 +639,12 @@ static int bcm3510_download_firmware(struct dvb_frontend* fe)
 		err("could not load firmware (%s): %d",BCM3510_DEFAULT_FIRMWARE,ret);
 		return ret;
 	}
-	deb_info("got firmware: %zd\n",fw->size);
+	deb_info("got firmware: %zu\n", fw->size);
 
 	b = fw->data;
 	for (i = 0; i < fw->size;) {
-		addr = le16_to_cpu( *( (u16 *)&b[i] ) );
-		len  = le16_to_cpu( *( (u16 *)&b[i+2] ) );
+		addr = le16_to_cpu(*((__le16 *)&b[i]));
+		len  = le16_to_cpu(*((__le16 *)&b[i+2]));
 		deb_info("firmware chunk, addr: 0x%04x, len: 0x%04x, total length: 0x%04zx\n",addr,len,fw->size);
 		if ((ret = bcm3510_write_ram(st,addr,&b[i+4],len)) < 0) {
 			err("firmware download failed: %d\n",ret);
diff --git a/drivers/media/dvb-frontends/cxd2820r_c.c b/drivers/media/dvb-frontends/cxd2820r_c.c
index 0f4657e01cde..149fdca3fb44 100644
--- a/drivers/media/dvb-frontends/cxd2820r_c.c
+++ b/drivers/media/dvb-frontends/cxd2820r_c.c
@@ -65,7 +65,7 @@ int cxd2820r_set_frontend_c(struct dvb_frontend *fe)
 	}
 
 	priv->delivery_system = SYS_DVBC_ANNEX_A;
-	priv->ber_running = 0; /* tune stops BER counter */
+	priv->ber_running = false; /* tune stops BER counter */
 
 	/* program IF frequency */
 	if (fe->ops.tuner_ops.get_if_frequency) {
@@ -168,7 +168,7 @@ int cxd2820r_read_ber_c(struct dvb_frontend *fe, u32 *ber)
 			start_ber = 1;
 		}
 	} else {
-		priv->ber_running = 1;
+		priv->ber_running = true;
 		start_ber = 1;
 	}
 
diff --git a/drivers/media/dvb-frontends/cxd2820r_core.c b/drivers/media/dvb-frontends/cxd2820r_core.c
index 03930d5e9fea..422e84bbb008 100644
--- a/drivers/media/dvb-frontends/cxd2820r_core.c
+++ b/drivers/media/dvb-frontends/cxd2820r_core.c
@@ -564,10 +564,10 @@ static enum dvbfe_search cxd2820r_search(struct dvb_frontend *fe)
 
 	/* check if we have a valid signal */
 	if (status & FE_HAS_LOCK) {
-		priv->last_tune_failed = 0;
+		priv->last_tune_failed = false;
 		return DVBFE_ALGO_SEARCH_SUCCESS;
 	} else {
-		priv->last_tune_failed = 1;
+		priv->last_tune_failed = true;
 		return DVBFE_ALGO_SEARCH_AGAIN;
 	}
 
@@ -584,18 +584,14 @@ static int cxd2820r_get_frontend_algo(struct dvb_frontend *fe)
 static void cxd2820r_release(struct dvb_frontend *fe)
 {
 	struct cxd2820r_priv *priv = fe->demodulator_priv;
-	int uninitialized_var(ret); /* silence compiler warning */
 
 	dev_dbg(&priv->i2c->dev, "%s\n", __func__);
 
 #ifdef CONFIG_GPIOLIB
 	/* remove GPIOs */
-	if (priv->gpio_chip.label) {
-		ret = gpiochip_remove(&priv->gpio_chip);
-		if (ret)
-			dev_err(&priv->i2c->dev, "%s: gpiochip_remove() " \
-					"failed=%d\n", KBUILD_MODNAME, ret);
-	}
+	if (priv->gpio_chip.label)
+		gpiochip_remove(&priv->gpio_chip);
+
 #endif
 	kfree(priv);
 	return;
diff --git a/drivers/media/dvb-frontends/cxd2820r_t.c b/drivers/media/dvb-frontends/cxd2820r_t.c
index 9b5a45b907bc..51401d036530 100644
--- a/drivers/media/dvb-frontends/cxd2820r_t.c
+++ b/drivers/media/dvb-frontends/cxd2820r_t.c
@@ -89,7 +89,7 @@ int cxd2820r_set_frontend_t(struct dvb_frontend *fe)
 	}
 
 	priv->delivery_system = SYS_DVBT;
-	priv->ber_running = 0; /* tune stops BER counter */
+	priv->ber_running = false; /* tune stops BER counter */
 
 	/* program IF frequency */
 	if (fe->ops.tuner_ops.get_if_frequency) {
@@ -272,7 +272,7 @@ int cxd2820r_read_ber_t(struct dvb_frontend *fe, u32 *ber)
 			start_ber = 1;
 		}
 	} else {
-		priv->ber_running = 1;
+		priv->ber_running = true;
 		start_ber = 1;
 	}
 
diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c
index 661760d60232..589134e95175 100644
--- a/drivers/media/dvb-frontends/dib7000p.c
+++ b/drivers/media/dvb-frontends/dib7000p.c
@@ -2559,7 +2559,7 @@ static void dib7090_setHostBusMux(struct dib7000p_state *state, int mode)
 	dib7000p_write_word(state, 1288, reg_1288);
 }
 
-int dib7090_set_diversity_in(struct dvb_frontend *fe, int onoff)
+static int dib7090_set_diversity_in(struct dvb_frontend *fe, int onoff)
 {
 	struct dib7000p_state *state = fe->demodulator_priv;
 	u16 reg_1287;
diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c
index 7ca7a21df183..5ec221ffdfca 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drxj.c
+++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c
@@ -2174,7 +2174,7 @@ int drxj_dap_atomic_read_reg32(struct i2c_device_addr *dev_addr,
 				     u32 addr,
 				     u32 *data, u32 flags)
 {
-	u8 buf[sizeof(*data)];
+	u8 buf[sizeof(*data)] = { 0 };
 	int rc = -EIO;
 	u32 word = 0;
 
@@ -4193,7 +4193,7 @@ int drxj_dap_scu_atomic_read_reg16(struct i2c_device_addr *dev_addr,
 					 u32 addr,
 					 u16 *data, u32 flags)
 {
-	u8 buf[2];
+	u8 buf[2] = { 0 };
 	int rc = -EIO;
 	u16 word = 0;
 
@@ -10667,7 +10667,7 @@ ctrl_sig_quality(struct drx_demod_instance *demod,
 	enum drx_standard standard = ext_attr->standard;
 	int rc;
 	u32 ber, cnt, err, pkt;
-	u16 mer, strength;
+	u16 mer, strength = 0;
 
 	rc = get_sig_strength(demod, &strength);
 	if (rc < 0) {
@@ -11602,7 +11602,7 @@ static u16 drx_u_code_compute_crc(u8 *block_data, u16 nr_words)
 	u32 carry = 0;
 
 	while (i < nr_words) {
-		crc_word |= (u32)be16_to_cpu(*(u32 *)(block_data));
+		crc_word |= (u32)be16_to_cpu(*(__be16 *)(block_data));
 		for (j = 0; j < 16; j++) {
 			crc_word <<= 1;
 			if (carry != 0)
@@ -11629,7 +11629,7 @@ static int drx_check_firmware(struct drx_demod_instance *demod, u8 *mc_data,
 	int i;
 	unsigned count = 2 * sizeof(u16);
 	u32 mc_dev_type, mc_version, mc_base_version;
-	u16 mc_nr_of_blks = be16_to_cpu(*(u32 *)(mc_data + sizeof(u16)));
+	u16 mc_nr_of_blks = be16_to_cpu(*(__be16 *)(mc_data + sizeof(u16)));
 
 	/*
 	 * Scan microcode blocks first for version info
@@ -11647,13 +11647,13 @@ static int drx_check_firmware(struct drx_demod_instance *demod, u8 *mc_data,
 			goto eof;
 
 		/* Process block header */
-		block_hdr.addr = be32_to_cpu(*(u32 *)(mc_data + count));
+		block_hdr.addr = be32_to_cpu(*(__be32 *)(mc_data + count));
 		count += sizeof(u32);
-		block_hdr.size = be16_to_cpu(*(u32 *)(mc_data + count));
+		block_hdr.size = be16_to_cpu(*(__be16 *)(mc_data + count));
 		count += sizeof(u16);
-		block_hdr.flags = be16_to_cpu(*(u32 *)(mc_data + count));
+		block_hdr.flags = be16_to_cpu(*(__be16 *)(mc_data + count));
 		count += sizeof(u16);
-		block_hdr.CRC = be16_to_cpu(*(u32 *)(mc_data + count));
+		block_hdr.CRC = be16_to_cpu(*(__be16 *)(mc_data + count));
 		count += sizeof(u16);
 
 		pr_debug("%u: addr %u, size %u, flags 0x%04x, CRC 0x%04x\n",
@@ -11667,7 +11667,7 @@ static int drx_check_firmware(struct drx_demod_instance *demod, u8 *mc_data,
 			if (block_hdr.addr + sizeof(u16) > size)
 				goto eof;
 
-			auxtype = be16_to_cpu(*(u32 *)(auxblk));
+			auxtype = be16_to_cpu(*(__be16 *)(auxblk));
 
 			/* Aux block. Check type */
 			if (DRX_ISMCVERTYPE(auxtype)) {
@@ -11675,11 +11675,11 @@ static int drx_check_firmware(struct drx_demod_instance *demod, u8 *mc_data,
 					goto eof;
 
 				auxblk += sizeof(u16);
-				mc_dev_type = be32_to_cpu(*(u32 *)(auxblk));
+				mc_dev_type = be32_to_cpu(*(__be32 *)(auxblk));
 				auxblk += sizeof(u32);
-				mc_version = be32_to_cpu(*(u32 *)(auxblk));
+				mc_version = be32_to_cpu(*(__be32 *)(auxblk));
 				auxblk += sizeof(u32);
-				mc_base_version = be32_to_cpu(*(u32 *)(auxblk));
+				mc_base_version = be32_to_cpu(*(__be32 *)(auxblk));
 
 				DRX_ATTR_MCRECORD(demod).aux_type = auxtype;
 				DRX_ATTR_MCRECORD(demod).mc_dev_type = mc_dev_type;
@@ -11765,9 +11765,9 @@ static int drx_ctrl_u_code(struct drx_demod_instance *demod,
 
 	mc_data = (void *)mc_data_init;
 	/* Check data */
-	mc_magic_word = be16_to_cpu(*(u32 *)(mc_data));
+	mc_magic_word = be16_to_cpu(*(__be16 *)(mc_data));
 	mc_data += sizeof(u16);
-	mc_nr_of_blks = be16_to_cpu(*(u32 *)(mc_data));
+	mc_nr_of_blks = be16_to_cpu(*(__be16 *)(mc_data));
 	mc_data += sizeof(u16);
 
 	if ((mc_magic_word != DRX_UCODE_MAGIC_WORD) || (mc_nr_of_blks == 0)) {
@@ -11791,13 +11791,13 @@ static int drx_ctrl_u_code(struct drx_demod_instance *demod,
 		u16 mc_block_nr_bytes = 0;
 
 		/* Process block header */
-		block_hdr.addr = be32_to_cpu(*(u32 *)(mc_data));
+		block_hdr.addr = be32_to_cpu(*(__be32 *)(mc_data));
 		mc_data += sizeof(u32);
-		block_hdr.size = be16_to_cpu(*(u32 *)(mc_data));
+		block_hdr.size = be16_to_cpu(*(__be16 *)(mc_data));
 		mc_data += sizeof(u16);
-		block_hdr.flags = be16_to_cpu(*(u32 *)(mc_data));
+		block_hdr.flags = be16_to_cpu(*(__be16 *)(mc_data));
 		mc_data += sizeof(u16);
-		block_hdr.CRC = be16_to_cpu(*(u32 *)(mc_data));
+		block_hdr.CRC = be16_to_cpu(*(__be16 *)(mc_data));
 		mc_data += sizeof(u16);
 
 		pr_debug("%u: addr %u, size %u, flags 0x%04x, CRC 0x%04x\n",
diff --git a/drivers/media/dvb-frontends/drxd_hard.c b/drivers/media/dvb-frontends/drxd_hard.c
index ae2276db77bc..687e893d29fe 100644
--- a/drivers/media/dvb-frontends/drxd_hard.c
+++ b/drivers/media/dvb-frontends/drxd_hard.c
@@ -2628,10 +2628,11 @@ static int DRXD_init(struct drxd_state *state, const u8 *fw, u32 fw_size)
 			break;
 
 		/* Apply I2c address patch to B1 */
-		if (!state->type_A && state->m_HiI2cPatch != NULL)
+		if (!state->type_A && state->m_HiI2cPatch != NULL) {
 			status = WriteTable(state, state->m_HiI2cPatch);
 			if (status < 0)
 				break;
+		}
 
 		if (state->type_A) {
 			/* HI firmware patch for UIO readout,
@@ -2830,14 +2831,8 @@ static int drxd_read_status(struct dvb_frontend *fe, fe_status_t * status)
 static int drxd_init(struct dvb_frontend *fe)
 {
 	struct drxd_state *state = fe->demodulator_priv;
-	int err = 0;
 
-/*	if (request_firmware(&state->fw, "drxd.fw", state->dev)<0) */
 	return DRXD_init(state, NULL, 0);
-
-	err = DRXD_init(state, state->fw->data, state->fw->size);
-	release_firmware(state->fw);
-	return err;
 }
 
 static int drxd_config_i2c(struct dvb_frontend *fe, int onoff)
diff --git a/drivers/media/dvb-frontends/drxk_hard.c b/drivers/media/dvb-frontends/drxk_hard.c
index cce94a75b2e1..672195147d01 100644
--- a/drivers/media/dvb-frontends/drxk_hard.c
+++ b/drivers/media/dvb-frontends/drxk_hard.c
@@ -1028,7 +1028,7 @@ static int hi_command(struct drxk_state *state, u16 cmd, u16 *p_result)
 		    ((state->m_hi_cfg_ctrl) &
 		     SIO_HI_RA_RAM_PAR_5_CFG_SLEEP__M) ==
 		    SIO_HI_RA_RAM_PAR_5_CFG_SLEEP_ZZZ);
-	if (powerdown_cmd == false) {
+	if (!powerdown_cmd) {
 		/* Wait until command rdy */
 		u32 retry_count = 0;
 		u16 wait_cmd;
@@ -1129,7 +1129,7 @@ static int mpegts_configure_pins(struct drxk_state *state, bool mpeg_enable)
 	if (status < 0)
 		goto error;
 
-	if (mpeg_enable == false) {
+	if (!mpeg_enable) {
 		/*  Set MPEG TS pads to inputmode */
 		status = write16(state, SIO_PDR_MSTRT_CFG__A, 0x0000);
 		if (status < 0)
@@ -1190,7 +1190,7 @@ static int mpegts_configure_pins(struct drxk_state *state, bool mpeg_enable)
 		if (status < 0)
 			goto error;
 
-		if (state->m_enable_parallel == true) {
+		if (state->m_enable_parallel) {
 			/* parallel -> enable MD1 to MD7 */
 			status = write16(state, SIO_PDR_MD1_CFG__A,
 					 sio_pdr_mdx_cfg);
@@ -1392,7 +1392,7 @@ static int dvbt_enable_ofdm_token_ring(struct drxk_state *state, bool enable)
 
 	dprintk(1, "\n");
 
-	if (enable == false) {
+	if (!enable) {
 		desired_ctrl = SIO_OFDM_SH_OFDM_RING_ENABLE_OFF;
 		desired_status = SIO_OFDM_SH_OFDM_RING_STATUS_DOWN;
 	}
@@ -2012,7 +2012,7 @@ static int mpegts_dto_setup(struct drxk_state *state,
 		goto error;
 	fec_oc_reg_mode &= (~FEC_OC_MODE_PARITY__M);
 	fec_oc_reg_ipr_mode &= (~FEC_OC_IPR_MODE_MVAL_DIS_PAR__M);
-	if (state->m_insert_rs_byte == true) {
+	if (state->m_insert_rs_byte) {
 		/* enable parity symbol forward */
 		fec_oc_reg_mode |= FEC_OC_MODE_PARITY__M;
 		/* MVAL disable during parity bytes */
@@ -2023,7 +2023,7 @@ static int mpegts_dto_setup(struct drxk_state *state,
 
 	/* Check serial or parallel output */
 	fec_oc_reg_ipr_mode &= (~(FEC_OC_IPR_MODE_SERIAL__M));
-	if (state->m_enable_parallel == false) {
+	if (!state->m_enable_parallel) {
 		/* MPEG data output is serial -> set ipr_mode[0] */
 		fec_oc_reg_ipr_mode |= FEC_OC_IPR_MODE_SERIAL__M;
 	}
@@ -2136,19 +2136,19 @@ static int mpegts_configure_polarity(struct drxk_state *state)
 
 	/* Control selective inversion of output bits */
 	fec_oc_reg_ipr_invert &= (~(invert_data_mask));
-	if (state->m_invert_data == true)
+	if (state->m_invert_data)
 		fec_oc_reg_ipr_invert |= invert_data_mask;
 	fec_oc_reg_ipr_invert &= (~(FEC_OC_IPR_INVERT_MERR__M));
-	if (state->m_invert_err == true)
+	if (state->m_invert_err)
 		fec_oc_reg_ipr_invert |= FEC_OC_IPR_INVERT_MERR__M;
 	fec_oc_reg_ipr_invert &= (~(FEC_OC_IPR_INVERT_MSTRT__M));
-	if (state->m_invert_str == true)
+	if (state->m_invert_str)
 		fec_oc_reg_ipr_invert |= FEC_OC_IPR_INVERT_MSTRT__M;
 	fec_oc_reg_ipr_invert &= (~(FEC_OC_IPR_INVERT_MVAL__M));
-	if (state->m_invert_val == true)
+	if (state->m_invert_val)
 		fec_oc_reg_ipr_invert |= FEC_OC_IPR_INVERT_MVAL__M;
 	fec_oc_reg_ipr_invert &= (~(FEC_OC_IPR_INVERT_MCLK__M));
-	if (state->m_invert_clk == true)
+	if (state->m_invert_clk)
 		fec_oc_reg_ipr_invert |= FEC_OC_IPR_INVERT_MCLK__M;
 
 	return write16(state, FEC_OC_IPR_INVERT__A, fec_oc_reg_ipr_invert);
@@ -2220,12 +2220,13 @@ static int set_agc_rf(struct drxk_state *state,
 		}
 
 		/* Set TOP, only if IF-AGC is in AUTO mode */
-		if (p_if_agc_settings->ctrl_mode == DRXK_AGC_CTRL_AUTO)
+		if (p_if_agc_settings->ctrl_mode == DRXK_AGC_CTRL_AUTO) {
 			status = write16(state,
 					 SCU_RAM_AGC_IF_IACCU_HI_TGT_MAX__A,
 					 p_agc_cfg->top);
 			if (status < 0)
 				goto error;
+		}
 
 		/* Cut-Off current */
 		status = write16(state, SCU_RAM_AGC_RF_IACCU_HI_CO__A,
@@ -3352,7 +3353,7 @@ static int dvbt_ctrl_set_inc_enable(struct drxk_state *state, bool *enabled)
 	int status;
 
 	dprintk(1, "\n");
-	if (*enabled == true)
+	if (*enabled)
 		status = write16(state, IQM_CF_BYPASSDET__A, 0);
 	else
 		status = write16(state, IQM_CF_BYPASSDET__A, 1);
@@ -3368,7 +3369,7 @@ static int dvbt_ctrl_set_fr_enable(struct drxk_state *state, bool *enabled)
 	int status;
 
 	dprintk(1, "\n");
-	if (*enabled == true) {
+	if (*enabled) {
 		/* write mask to 1 */
 		status = write16(state, OFDM_SC_RA_RAM_FR_THRES_8K__A,
 				   DEFAULT_FR_THRES_8K);
@@ -6794,11 +6795,11 @@ struct dvb_frontend *drxk_attach(const struct drxk_config *config,
 	state->enable_merr_cfg = config->enable_merr_cfg;
 
 	if (config->dynamic_clk) {
-		state->m_dvbt_static_clk = 0;
-		state->m_dvbc_static_clk = 0;
+		state->m_dvbt_static_clk = false;
+		state->m_dvbc_static_clk = false;
 	} else {
-		state->m_dvbt_static_clk = 1;
-		state->m_dvbc_static_clk = 1;
+		state->m_dvbt_static_clk = true;
+		state->m_dvbc_static_clk = true;
 	}
 
 
diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c
index dfe0c2f7f1ef..81657e94c5a4 100644
--- a/drivers/media/dvb-frontends/m88ds3103.c
+++ b/drivers/media/dvb-frontends/m88ds3103.c
@@ -159,6 +159,7 @@ static int m88ds3103_wr_reg_val_tab(struct m88ds3103_priv *priv,
 {
 	int ret, i, j;
 	u8 buf[83];
+
 	dev_dbg(&priv->i2c->dev, "%s: tab_len=%d\n", __func__, tab_len);
 
 	if (tab_len > 83) {
@@ -247,8 +248,9 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 	u8 u8tmp, u8tmp1, u8tmp2;
 	u8 buf[2];
 	u16 u16tmp, divide_ratio;
-	u32 tuner_frequency, target_mclk, ts_clk;
+	u32 tuner_frequency, target_mclk;
 	s32 s32tmp;
+
 	dev_dbg(&priv->i2c->dev,
 			"%s: delivery_system=%d modulation=%d frequency=%d symbol_rate=%d inversion=%d pilot=%d rolloff=%d\n",
 			__func__, c->delivery_system,
@@ -316,9 +318,6 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 				target_mclk = 144000;
 			break;
 		case M88DS3103_TS_PARALLEL:
-		case M88DS3103_TS_PARALLEL_12:
-		case M88DS3103_TS_PARALLEL_16:
-		case M88DS3103_TS_PARALLEL_19_2:
 		case M88DS3103_TS_CI:
 			if (c->symbol_rate < 18000000)
 				target_mclk = 96000;
@@ -352,33 +351,17 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 	switch (priv->cfg->ts_mode) {
 	case M88DS3103_TS_SERIAL:
 		u8tmp1 = 0x00;
-		ts_clk = 0;
-		u8tmp = 0x46;
+		u8tmp = 0x06;
 		break;
 	case M88DS3103_TS_SERIAL_D7:
 		u8tmp1 = 0x20;
-		ts_clk = 0;
-		u8tmp = 0x46;
+		u8tmp = 0x06;
 		break;
 	case M88DS3103_TS_PARALLEL:
-		ts_clk = 24000;
-		u8tmp = 0x42;
-		break;
-	case M88DS3103_TS_PARALLEL_12:
-		ts_clk = 12000;
-		u8tmp = 0x42;
-		break;
-	case M88DS3103_TS_PARALLEL_16:
-		ts_clk = 16000;
-		u8tmp = 0x42;
-		break;
-	case M88DS3103_TS_PARALLEL_19_2:
-		ts_clk = 19200;
-		u8tmp = 0x42;
+		u8tmp = 0x02;
 		break;
 	case M88DS3103_TS_CI:
-		ts_clk = 6000;
-		u8tmp = 0x43;
+		u8tmp = 0x03;
 		break;
 	default:
 		dev_dbg(&priv->i2c->dev, "%s: invalid ts_mode\n", __func__);
@@ -386,6 +369,9 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 		goto err;
 	}
 
+	if (priv->cfg->ts_clk_pol)
+		u8tmp |= 0x40;
+
 	/* TS mode */
 	ret = m88ds3103_wr_reg(priv, 0xfd, u8tmp);
 	if (ret)
@@ -399,8 +385,8 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 			goto err;
 	}
 
-	if (ts_clk) {
-		divide_ratio = DIV_ROUND_UP(target_mclk, ts_clk);
+	if (priv->cfg->ts_clk) {
+		divide_ratio = DIV_ROUND_UP(target_mclk, priv->cfg->ts_clk);
 		u8tmp1 = divide_ratio / 2;
 		u8tmp2 = DIV_ROUND_UP(divide_ratio, 2);
 	} else {
@@ -411,7 +397,7 @@ static int m88ds3103_set_frontend(struct dvb_frontend *fe)
 
 	dev_dbg(&priv->i2c->dev,
 			"%s: target_mclk=%d ts_clk=%d divide_ratio=%d\n",
-			__func__, target_mclk, ts_clk, divide_ratio);
+			__func__, target_mclk, priv->cfg->ts_clk, divide_ratio);
 
 	u8tmp1--;
 	u8tmp2--;
@@ -536,6 +522,7 @@ static int m88ds3103_init(struct dvb_frontend *fe)
 	const struct firmware *fw = NULL;
 	u8 *fw_file = M88DS3103_FIRMWARE;
 	u8 u8tmp;
+
 	dev_dbg(&priv->i2c->dev, "%s:\n", __func__);
 
 	/* set cold state by default */
@@ -648,6 +635,7 @@ static int m88ds3103_sleep(struct dvb_frontend *fe)
 {
 	struct m88ds3103_priv *priv = fe->demodulator_priv;
 	int ret;
+
 	dev_dbg(&priv->i2c->dev, "%s:\n", __func__);
 
 	priv->delivery_system = SYS_UNDEFINED;
@@ -682,6 +670,7 @@ static int m88ds3103_get_frontend(struct dvb_frontend *fe)
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 	u8 buf[3];
+
 	dev_dbg(&priv->i2c->dev, "%s:\n", __func__);
 
 	if (!priv->warm || !(priv->fe_status & FE_HAS_LOCK)) {
@@ -857,6 +846,7 @@ static int m88ds3103_read_snr(struct dvb_frontend *fe, u16 *snr)
 	u8 buf[3];
 	u16 noise, signal;
 	u32 noise_tot, signal_tot;
+
 	dev_dbg(&priv->i2c->dev, "%s:\n", __func__);
 	/* reports SNR in resolution of 0.1 dB */
 
@@ -933,6 +923,7 @@ static int m88ds3103_read_ber(struct dvb_frontend *fe, u32 *ber)
 	int ret;
 	unsigned int utmp;
 	u8 buf[3], u8tmp;
+
 	dev_dbg(&priv->i2c->dev, "%s:\n", __func__);
 
 	switch (c->delivery_system) {
@@ -1013,6 +1004,7 @@ static int m88ds3103_set_tone(struct dvb_frontend *fe,
 	struct m88ds3103_priv *priv = fe->demodulator_priv;
 	int ret;
 	u8 u8tmp, tone, reg_a1_mask;
+
 	dev_dbg(&priv->i2c->dev, "%s: fe_sec_tone_mode=%d\n", __func__,
 			fe_sec_tone_mode);
 
@@ -1053,12 +1045,64 @@ err:
 	return ret;
 }
 
+static int m88ds3103_set_voltage(struct dvb_frontend *fe,
+	fe_sec_voltage_t fe_sec_voltage)
+{
+	struct m88ds3103_priv *priv = fe->demodulator_priv;
+	int ret;
+	u8 u8tmp;
+	bool voltage_sel, voltage_dis;
+
+	dev_dbg(&priv->i2c->dev, "%s: fe_sec_voltage=%d\n", __func__,
+			fe_sec_voltage);
+
+	if (!priv->warm) {
+		ret = -EAGAIN;
+		goto err;
+	}
+
+	switch (fe_sec_voltage) {
+	case SEC_VOLTAGE_18:
+		voltage_sel = true;
+		voltage_dis = false;
+		break;
+	case SEC_VOLTAGE_13:
+		voltage_sel = false;
+		voltage_dis = false;
+		break;
+	case SEC_VOLTAGE_OFF:
+		voltage_sel = false;
+		voltage_dis = true;
+		break;
+	default:
+		dev_dbg(&priv->i2c->dev, "%s: invalid fe_sec_voltage\n",
+				__func__);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	/* output pin polarity */
+	voltage_sel ^= priv->cfg->lnb_hv_pol;
+	voltage_dis ^= priv->cfg->lnb_en_pol;
+
+	u8tmp = voltage_dis << 1 | voltage_sel << 0;
+	ret = m88ds3103_wr_reg_mask(priv, 0xa2, u8tmp, 0x03);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	dev_dbg(&priv->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	return ret;
+}
+
 static int m88ds3103_diseqc_send_master_cmd(struct dvb_frontend *fe,
 		struct dvb_diseqc_master_cmd *diseqc_cmd)
 {
 	struct m88ds3103_priv *priv = fe->demodulator_priv;
 	int ret, i;
 	u8 u8tmp;
+
 	dev_dbg(&priv->i2c->dev, "%s: msg=%*ph\n", __func__,
 			diseqc_cmd->msg_len, diseqc_cmd->msg);
 
@@ -1130,6 +1174,7 @@ static int m88ds3103_diseqc_send_burst(struct dvb_frontend *fe,
 	struct m88ds3103_priv *priv = fe->demodulator_priv;
 	int ret, i;
 	u8 u8tmp, burst;
+
 	dev_dbg(&priv->i2c->dev, "%s: fe_sec_mini_cmd=%d\n", __func__,
 			fe_sec_mini_cmd);
 
@@ -1202,6 +1247,7 @@ static int m88ds3103_get_tune_settings(struct dvb_frontend *fe,
 static void m88ds3103_release(struct dvb_frontend *fe)
 {
 	struct m88ds3103_priv *priv = fe->demodulator_priv;
+
 	i2c_del_mux_adapter(priv->i2c_adapter);
 	kfree(priv);
 }
@@ -1370,6 +1416,7 @@ static struct dvb_frontend_ops m88ds3103_ops = {
 	.diseqc_send_burst = m88ds3103_diseqc_send_burst,
 
 	.set_tone = m88ds3103_set_tone,
+	.set_voltage = m88ds3103_set_voltage,
 };
 
 MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>");
diff --git a/drivers/media/dvb-frontends/m88ds3103.h b/drivers/media/dvb-frontends/m88ds3103.h
index bbb7e3aa5675..9b3b4962da7c 100644
--- a/drivers/media/dvb-frontends/m88ds3103.h
+++ b/drivers/media/dvb-frontends/m88ds3103.h
@@ -47,14 +47,23 @@ struct m88ds3103_config {
 	 */
 #define M88DS3103_TS_SERIAL             0 /* TS output pin D0, normal */
 #define M88DS3103_TS_SERIAL_D7          1 /* TS output pin D7 */
-#define M88DS3103_TS_PARALLEL           2 /* 24 MHz, normal */
-#define M88DS3103_TS_PARALLEL_12        3 /* 12 MHz */
-#define M88DS3103_TS_PARALLEL_16        4 /* 16 MHz */
-#define M88DS3103_TS_PARALLEL_19_2      5 /* 19.2 MHz */
-#define M88DS3103_TS_CI                 6 /* 6 MHz */
+#define M88DS3103_TS_PARALLEL           2 /* TS Parallel mode */
+#define M88DS3103_TS_CI                 3 /* TS CI Mode */
 	u8 ts_mode;
 
 	/*
+	 * TS clk in KHz
+	 * Default: 0.
+	 */
+	u32 ts_clk;
+
+	/*
+	 * TS clk polarity.
+	 * Default: 0. 1-active at falling edge; 0-active at rising edge.
+	 */
+	u8 ts_clk_pol:1;
+
+	/*
 	 * spectrum inversion
 	 * Default: 0
 	 */
@@ -86,6 +95,22 @@ struct m88ds3103_config {
 	 * Default: none, must set
 	 */
 	u8 agc;
+
+	/*
+	 * LNB H/V pin polarity
+	 * Default: 0.
+	 * 1: pin high set to VOLTAGE_13, pin low to set VOLTAGE_18.
+	 * 0: pin high set to VOLTAGE_18, pin low to set VOLTAGE_13.
+	 */
+	u8 lnb_hv_pol:1;
+
+	/*
+	 * LNB enable pin polarity
+	 * Default: 0.
+	 * 1: pin high to enable, pin low to disable.
+	 * 0: pin high to disable, pin low to enable.
+	 */
+	u8 lnb_en_pol:1;
 };
 
 /*
diff --git a/drivers/media/dvb-frontends/mb86a16.c b/drivers/media/dvb-frontends/mb86a16.c
index 9ae40abfd71a..3ddea4471d2b 100644
--- a/drivers/media/dvb-frontends/mb86a16.c
+++ b/drivers/media/dvb-frontends/mb86a16.c
@@ -28,7 +28,7 @@
 #include "mb86a16.h"
 #include "mb86a16_priv.h"
 
-unsigned int verbose = 5;
+static unsigned int verbose = 5;
 module_param(verbose, int, 0644);
 
 #define ABS(x)		((x) < 0 ? (-x) : (x))
@@ -115,9 +115,11 @@ static int mb86a16_read(struct mb86a16_state *state, u8 reg, u8 *val)
 	};
 	ret = i2c_transfer(state->i2c_adap, msg, 2);
 	if (ret != 2) {
-		dprintk(verbose, MB86A16_ERROR, 1, "read error(reg=0x%02x, ret=0x%i)",
+		dprintk(verbose, MB86A16_ERROR, 1, "read error(reg=0x%02x, ret=%i)",
 			reg, ret);
 
+		if (ret < 0)
+			return ret;
 		return -EREMOTEIO;
 	}
 	*val = b1[0];
diff --git a/drivers/media/dvb-frontends/mb86a20s.c b/drivers/media/dvb-frontends/mb86a20s.c
index b931179c70a4..e6f165a5b90d 100644
--- a/drivers/media/dvb-frontends/mb86a20s.c
+++ b/drivers/media/dvb-frontends/mb86a20s.c
@@ -33,7 +33,7 @@ enum mb86a20s_bandwidth {
 	MB86A20S_3SEG = 3,
 };
 
-u8 mb86a20s_subchannel[] = {
+static u8 mb86a20s_subchannel[] = {
 	0xb0, 0xc0, 0xd0, 0xe0,
 	0xf0, 0x00, 0x10, 0x20,
 };
@@ -1228,7 +1228,7 @@ struct linear_segments {
  * All tables below return a dB/1000 measurement
  */
 
-static struct linear_segments cnr_to_db_table[] = {
+static const struct linear_segments cnr_to_db_table[] = {
 	{ 19648,     0},
 	{ 18187,  1000},
 	{ 16534,  2000},
@@ -1262,7 +1262,7 @@ static struct linear_segments cnr_to_db_table[] = {
 	{   788, 30000},
 };
 
-static struct linear_segments cnr_64qam_table[] = {
+static const struct linear_segments cnr_64qam_table[] = {
 	{ 3922688,     0},
 	{ 3920384,  1000},
 	{ 3902720,  2000},
@@ -1296,7 +1296,7 @@ static struct linear_segments cnr_64qam_table[] = {
 	{  388864, 30000},
 };
 
-static struct linear_segments cnr_16qam_table[] = {
+static const struct linear_segments cnr_16qam_table[] = {
 	{ 5314816,     0},
 	{ 5219072,  1000},
 	{ 5118720,  2000},
@@ -1330,7 +1330,7 @@ static struct linear_segments cnr_16qam_table[] = {
 	{   95744, 30000},
 };
 
-struct linear_segments cnr_qpsk_table[] = {
+static const struct linear_segments cnr_qpsk_table[] = {
 	{ 2834176,     0},
 	{ 2683648,  1000},
 	{ 2536960,  2000},
@@ -1364,7 +1364,7 @@ struct linear_segments cnr_qpsk_table[] = {
 	{   11520, 30000},
 };
 
-static u32 interpolate_value(u32 value, struct linear_segments *segments,
+static u32 interpolate_value(u32 value, const struct linear_segments *segments,
 			     unsigned len)
 {
 	u64 tmp64;
@@ -1448,7 +1448,7 @@ static int mb86a20s_get_blk_error_layer_CNR(struct dvb_frontend *fe)
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	u32 mer, cnr;
 	int rc, val, layer;
-	struct linear_segments *segs;
+	const struct linear_segments *segs;
 	unsigned segs_len;
 
 	dev_dbg(&state->i2c->dev, "%s called.\n", __func__);
diff --git a/drivers/media/dvb-frontends/mt312.c b/drivers/media/dvb-frontends/mt312.c
index a74ac0ddb833..2163490c1e6b 100644
--- a/drivers/media/dvb-frontends/mt312.c
+++ b/drivers/media/dvb-frontends/mt312.c
@@ -103,7 +103,7 @@ static int mt312_write(struct mt312_state *state, const enum mt312_reg_addr reg,
 
 	if (1 + count > sizeof(buf)) {
 		printk(KERN_WARNING
-		       "mt312: write: len=%zd is too big!\n", count);
+		       "mt312: write: len=%zu is too big!\n", count);
 		return -EINVAL;
 	}
 
diff --git a/drivers/media/dvb-frontends/or51211.c b/drivers/media/dvb-frontends/or51211.c
index 10cfc0579168..873ea1da844b 100644
--- a/drivers/media/dvb-frontends/or51211.c
+++ b/drivers/media/dvb-frontends/or51211.c
@@ -111,7 +111,7 @@ static int or51211_load_firmware (struct dvb_frontend* fe,
 	u8 tudata[585];
 	int i;
 
-	dprintk("Firmware is %zd bytes\n",fw->size);
+	dprintk("Firmware is %zu bytes\n", fw->size);
 
 	/* Get eprom data */
 	tudata[0] = 17;
diff --git a/drivers/media/dvb-frontends/rtl2832.c b/drivers/media/dvb-frontends/rtl2832.c
index fdbed35c87fa..eb737cf29a36 100644
--- a/drivers/media/dvb-frontends/rtl2832.c
+++ b/drivers/media/dvb-frontends/rtl2832.c
@@ -936,7 +936,7 @@ static void rtl2832_i2c_gate_work(struct work_struct *work)
 	if (ret != 1)
 		goto err;
 
-	priv->i2c_gate_state = 0;
+	priv->i2c_gate_state = false;
 
 	return;
 err:
diff --git a/drivers/media/dvb-frontends/rtl2832_sdr.c b/drivers/media/dvb-frontends/rtl2832_sdr.c
index 023e0f49c786..7bf98cf6bbe1 100644
--- a/drivers/media/dvb-frontends/rtl2832_sdr.c
+++ b/drivers/media/dvb-frontends/rtl2832_sdr.c
@@ -329,7 +329,7 @@ static int rtl2832_sdr_rd_reg_mask(struct rtl2832_sdr_state *s, u16 reg,
 static struct rtl2832_sdr_frame_buf *rtl2832_sdr_get_next_fill_buf(
 		struct rtl2832_sdr_state *s)
 {
-	unsigned long flags = 0;
+	unsigned long flags;
 	struct rtl2832_sdr_frame_buf *buf = NULL;
 
 	spin_lock_irqsave(&s->queued_bufs_lock, flags);
@@ -365,17 +365,19 @@ static unsigned int rtl2832_sdr_convert_stream(struct rtl2832_sdr_state *s,
 		dst_len = 0;
 	}
 
-	/* calculate samping rate and output it in 10 seconds intervals */
+	/* calculate sample rate and output it in 10 seconds intervals */
 	if (unlikely(time_is_before_jiffies(s->jiffies_next))) {
-#define MSECS 10000UL
+		#define MSECS 10000UL
+		unsigned int msecs = jiffies_to_msecs(jiffies -
+				s->jiffies_next + msecs_to_jiffies(MSECS));
 		unsigned int samples = s->sample - s->sample_measured;
 
 		s->jiffies_next = jiffies + msecs_to_jiffies(MSECS);
 		s->sample_measured = s->sample;
 		dev_dbg(&s->udev->dev,
-				"slen=%d samples=%u msecs=%lu sampling rate=%lu\n",
-				src_len, samples, MSECS,
-				samples * 1000UL / MSECS);
+				"slen=%u samples=%u msecs=%u sample rate=%lu\n",
+				src_len, samples, msecs,
+				samples * 1000UL / msecs);
 	}
 
 	/* total number of I+Q pairs */
@@ -394,8 +396,8 @@ static void rtl2832_sdr_urb_complete(struct urb *urb)
 	struct rtl2832_sdr_frame_buf *fbuf;
 
 	dev_dbg_ratelimited(&s->udev->dev,
-			"%s: status=%d length=%d/%d errors=%d\n",
-			__func__, urb->status, urb->actual_length,
+			"status=%d length=%d/%d errors=%d\n",
+			urb->status, urb->actual_length,
 			urb->transfer_buffer_length, urb->error_count);
 
 	switch (urb->status) {
@@ -443,7 +445,7 @@ static int rtl2832_sdr_kill_urbs(struct rtl2832_sdr_state *s)
 	int i;
 
 	for (i = s->urbs_submitted - 1; i >= 0; i--) {
-		dev_dbg(&s->udev->dev, "%s: kill urb=%d\n", __func__, i);
+		dev_dbg(&s->udev->dev, "kill urb=%d\n", i);
 		/* stop the URB */
 		usb_kill_urb(s->urb_list[i]);
 	}
@@ -457,7 +459,7 @@ static int rtl2832_sdr_submit_urbs(struct rtl2832_sdr_state *s)
 	int i, ret;
 
 	for (i = 0; i < s->urbs_initialized; i++) {
-		dev_dbg(&s->udev->dev, "%s: submit urb=%d\n", __func__, i);
+		dev_dbg(&s->udev->dev, "submit urb=%d\n", i);
 		ret = usb_submit_urb(s->urb_list[i], GFP_ATOMIC);
 		if (ret) {
 			dev_err(&s->udev->dev,
@@ -477,8 +479,7 @@ static int rtl2832_sdr_free_stream_bufs(struct rtl2832_sdr_state *s)
 	if (s->flags & USB_STATE_URB_BUF) {
 		while (s->buf_num) {
 			s->buf_num--;
-			dev_dbg(&s->udev->dev, "%s: free buf=%d\n",
-					__func__, s->buf_num);
+			dev_dbg(&s->udev->dev, "free buf=%d\n", s->buf_num);
 			usb_free_coherent(s->udev, s->buf_size,
 					  s->buf_list[s->buf_num],
 					  s->dma_addr[s->buf_num]);
@@ -494,24 +495,22 @@ static int rtl2832_sdr_alloc_stream_bufs(struct rtl2832_sdr_state *s)
 	s->buf_num = 0;
 	s->buf_size = BULK_BUFFER_SIZE;
 
-	dev_dbg(&s->udev->dev,
-			"%s: all in all I will use %u bytes for streaming\n",
-			__func__,  MAX_BULK_BUFS * BULK_BUFFER_SIZE);
+	dev_dbg(&s->udev->dev, "all in all I will use %u bytes for streaming\n",
+			MAX_BULK_BUFS * BULK_BUFFER_SIZE);
 
 	for (s->buf_num = 0; s->buf_num < MAX_BULK_BUFS; s->buf_num++) {
 		s->buf_list[s->buf_num] = usb_alloc_coherent(s->udev,
 				BULK_BUFFER_SIZE, GFP_ATOMIC,
 				&s->dma_addr[s->buf_num]);
 		if (!s->buf_list[s->buf_num]) {
-			dev_dbg(&s->udev->dev, "%s: alloc buf=%d failed\n",
-					__func__, s->buf_num);
+			dev_dbg(&s->udev->dev, "alloc buf=%d failed\n",
+					s->buf_num);
 			rtl2832_sdr_free_stream_bufs(s);
 			return -ENOMEM;
 		}
 
-		dev_dbg(&s->udev->dev, "%s: alloc buf=%d %p (dma %llu)\n",
-				__func__, s->buf_num,
-				s->buf_list[s->buf_num],
+		dev_dbg(&s->udev->dev, "alloc buf=%d %p (dma %llu)\n",
+				s->buf_num, s->buf_list[s->buf_num],
 				(long long)s->dma_addr[s->buf_num]);
 		s->flags |= USB_STATE_URB_BUF;
 	}
@@ -527,8 +526,7 @@ static int rtl2832_sdr_free_urbs(struct rtl2832_sdr_state *s)
 
 	for (i = s->urbs_initialized - 1; i >= 0; i--) {
 		if (s->urb_list[i]) {
-			dev_dbg(&s->udev->dev, "%s: free urb=%d\n",
-					__func__, i);
+			dev_dbg(&s->udev->dev, "free urb=%d\n", i);
 			/* free the URBs */
 			usb_free_urb(s->urb_list[i]);
 		}
@@ -544,10 +542,10 @@ static int rtl2832_sdr_alloc_urbs(struct rtl2832_sdr_state *s)
 
 	/* allocate the URBs */
 	for (i = 0; i < MAX_BULK_BUFS; i++) {
-		dev_dbg(&s->udev->dev, "%s: alloc urb=%d\n", __func__, i);
+		dev_dbg(&s->udev->dev, "alloc urb=%d\n", i);
 		s->urb_list[i] = usb_alloc_urb(0, GFP_ATOMIC);
 		if (!s->urb_list[i]) {
-			dev_dbg(&s->udev->dev, "%s: failed\n", __func__);
+			dev_dbg(&s->udev->dev, "failed\n");
 			for (j = 0; j < i; j++)
 				usb_free_urb(s->urb_list[j]);
 			return -ENOMEM;
@@ -570,9 +568,9 @@ static int rtl2832_sdr_alloc_urbs(struct rtl2832_sdr_state *s)
 /* Must be called with vb_queue_lock hold */
 static void rtl2832_sdr_cleanup_queued_bufs(struct rtl2832_sdr_state *s)
 {
-	unsigned long flags = 0;
+	unsigned long flags;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(&s->udev->dev, "\n");
 
 	spin_lock_irqsave(&s->queued_bufs_lock, flags);
 	while (!list_empty(&s->queued_bufs)) {
@@ -591,7 +589,7 @@ static void rtl2832_sdr_release_sec(struct dvb_frontend *fe)
 {
 	struct rtl2832_sdr_state *s = fe->sec_priv;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(&s->udev->dev, "\n");
 
 	mutex_lock(&s->vb_queue_lock);
 	mutex_lock(&s->v4l2_lock);
@@ -613,7 +611,7 @@ static int rtl2832_sdr_querycap(struct file *file, void *fh,
 {
 	struct rtl2832_sdr_state *s = video_drvdata(file);
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(&s->udev->dev, "\n");
 
 	strlcpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver));
 	strlcpy(cap->card, s->vdev.name, sizeof(cap->card));
@@ -631,15 +629,15 @@ static int rtl2832_sdr_queue_setup(struct vb2_queue *vq,
 {
 	struct rtl2832_sdr_state *s = vb2_get_drv_priv(vq);
 
-	dev_dbg(&s->udev->dev, "%s: *nbuffers=%d\n", __func__, *nbuffers);
+	dev_dbg(&s->udev->dev, "nbuffers=%d\n", *nbuffers);
 
 	/* Need at least 8 buffers */
 	if (vq->num_buffers + *nbuffers < 8)
 		*nbuffers = 8 - vq->num_buffers;
 	*nplanes = 1;
 	sizes[0] = PAGE_ALIGN(s->buffersize);
-	dev_dbg(&s->udev->dev, "%s: nbuffers=%d sizes[0]=%d\n",
-			__func__, *nbuffers, sizes[0]);
+	dev_dbg(&s->udev->dev, "nbuffers=%d sizes[0]=%d\n",
+			*nbuffers, sizes[0]);
 	return 0;
 }
 
@@ -659,7 +657,7 @@ static void rtl2832_sdr_buf_queue(struct vb2_buffer *vb)
 	struct rtl2832_sdr_state *s = vb2_get_drv_priv(vb->vb2_queue);
 	struct rtl2832_sdr_frame_buf *buf =
 			container_of(vb, struct rtl2832_sdr_frame_buf, vb);
-	unsigned long flags = 0;
+	unsigned long flags;
 
 	/* Check the device has not disconnected between prep and queuing */
 	if (!s->udev) {
@@ -681,7 +679,7 @@ static int rtl2832_sdr_set_adc(struct rtl2832_sdr_state *s)
 	u64 u64tmp;
 	u32 u32tmp;
 
-	dev_dbg(&s->udev->dev, "%s: f_adc=%u\n", __func__, s->f_adc);
+	dev_dbg(&s->udev->dev, "f_adc=%u\n", s->f_adc);
 
 	if (!test_bit(POWER_ON, &s->flags))
 		return 0;
@@ -715,8 +713,7 @@ static int rtl2832_sdr_set_adc(struct rtl2832_sdr_state *s)
 	u64tmp = -u64tmp;
 	u32tmp = u64tmp & 0x3fffff;
 
-	dev_dbg(&s->udev->dev, "%s: f_if=%u if_ctl=%08x\n",
-			__func__, f_if, u32tmp);
+	dev_dbg(&s->udev->dev, "f_if=%u if_ctl=%08x\n", f_if, u32tmp);
 
 	buf[0] = (u32tmp >> 16) & 0xff;
 	buf[1] = (u32tmp >>  8) & 0xff;
@@ -903,7 +900,7 @@ static void rtl2832_sdr_unset_adc(struct rtl2832_sdr_state *s)
 {
 	int ret;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(&s->udev->dev, "\n");
 
 	/* PID filter */
 	ret = rtl2832_sdr_wr_regs(s, 0x061, "\xe0", 1);
@@ -964,8 +961,8 @@ static int rtl2832_sdr_set_tuner_freq(struct rtl2832_sdr_state *s)
 	c->frequency = s->f_tuner;
 	c->delivery_system = SYS_DVBT;
 
-	dev_dbg(&s->udev->dev, "%s: frequency=%u bandwidth=%d\n",
-			__func__, c->frequency, c->bandwidth_hz);
+	dev_dbg(&s->udev->dev, "frequency=%u bandwidth=%d\n",
+			c->frequency, c->bandwidth_hz);
 
 	if (!test_bit(POWER_ON, &s->flags))
 		return 0;
@@ -980,7 +977,7 @@ static int rtl2832_sdr_set_tuner(struct rtl2832_sdr_state *s)
 {
 	struct dvb_frontend *fe = s->fe;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(&s->udev->dev, "\n");
 
 	if (fe->ops.tuner_ops.init)
 		fe->ops.tuner_ops.init(fe);
@@ -992,7 +989,7 @@ static void rtl2832_sdr_unset_tuner(struct rtl2832_sdr_state *s)
 {
 	struct dvb_frontend *fe = s->fe;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(&s->udev->dev, "\n");
 
 	if (fe->ops.tuner_ops.sleep)
 		fe->ops.tuner_ops.sleep(fe);
@@ -1005,7 +1002,7 @@ static int rtl2832_sdr_start_streaming(struct vb2_queue *vq, unsigned int count)
 	struct rtl2832_sdr_state *s = vb2_get_drv_priv(vq);
 	int ret;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(&s->udev->dev, "\n");
 
 	if (!s->udev)
 		return -ENODEV;
@@ -1054,7 +1051,7 @@ static void rtl2832_sdr_stop_streaming(struct vb2_queue *vq)
 {
 	struct rtl2832_sdr_state *s = vb2_get_drv_priv(vq);
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(&s->udev->dev, "\n");
 
 	mutex_lock(&s->v4l2_lock);
 
@@ -1088,8 +1085,7 @@ static int rtl2832_sdr_g_tuner(struct file *file, void *priv,
 {
 	struct rtl2832_sdr_state *s = video_drvdata(file);
 
-	dev_dbg(&s->udev->dev, "%s: index=%d type=%d\n",
-			__func__, v->index, v->type);
+	dev_dbg(&s->udev->dev, "index=%d type=%d\n", v->index, v->type);
 
 	if (v->index == 0) {
 		strlcpy(v->name, "ADC: Realtek RTL2832", sizeof(v->name));
@@ -1115,7 +1111,7 @@ static int rtl2832_sdr_s_tuner(struct file *file, void *priv,
 {
 	struct rtl2832_sdr_state *s = video_drvdata(file);
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(&s->udev->dev, "\n");
 
 	if (v->index > 1)
 		return -EINVAL;
@@ -1127,8 +1123,8 @@ static int rtl2832_sdr_enum_freq_bands(struct file *file, void *priv,
 {
 	struct rtl2832_sdr_state *s = video_drvdata(file);
 
-	dev_dbg(&s->udev->dev, "%s: tuner=%d type=%d index=%d\n",
-			__func__, band->tuner, band->type, band->index);
+	dev_dbg(&s->udev->dev, "tuner=%d type=%d index=%d\n",
+			band->tuner, band->type, band->index);
 
 	if (band->tuner == 0) {
 		if (band->index >= ARRAY_SIZE(bands_adc))
@@ -1153,8 +1149,8 @@ static int rtl2832_sdr_g_frequency(struct file *file, void *priv,
 	struct rtl2832_sdr_state *s = video_drvdata(file);
 	int ret  = 0;
 
-	dev_dbg(&s->udev->dev, "%s: tuner=%d type=%d\n",
-			__func__, f->tuner, f->type);
+	dev_dbg(&s->udev->dev, "tuner=%d type=%d\n",
+			f->tuner, f->type);
 
 	if (f->tuner == 0) {
 		f->frequency = s->f_adc;
@@ -1175,8 +1171,8 @@ static int rtl2832_sdr_s_frequency(struct file *file, void *priv,
 	struct rtl2832_sdr_state *s = video_drvdata(file);
 	int ret, band;
 
-	dev_dbg(&s->udev->dev, "%s: tuner=%d type=%d frequency=%u\n",
-			__func__, f->tuner, f->type, f->frequency);
+	dev_dbg(&s->udev->dev, "tuner=%d type=%d frequency=%u\n",
+			f->tuner, f->type, f->frequency);
 
 	/* ADC band midpoints */
 	#define BAND_ADC_0 ((bands_adc[0].rangehigh + bands_adc[1].rangelow) / 2)
@@ -1194,15 +1190,13 @@ static int rtl2832_sdr_s_frequency(struct file *file, void *priv,
 				bands_adc[band].rangelow,
 				bands_adc[band].rangehigh);
 
-		dev_dbg(&s->udev->dev, "%s: ADC frequency=%u Hz\n",
-				__func__, s->f_adc);
+		dev_dbg(&s->udev->dev, "ADC frequency=%u Hz\n", s->f_adc);
 		ret = rtl2832_sdr_set_adc(s);
 	} else if (f->tuner == 1) {
 		s->f_tuner = clamp_t(unsigned int, f->frequency,
 				bands_fm[0].rangelow,
 				bands_fm[0].rangehigh);
-		dev_dbg(&s->udev->dev, "%s: RF frequency=%u Hz\n",
-				__func__, f->frequency);
+		dev_dbg(&s->udev->dev, "RF frequency=%u Hz\n", f->frequency);
 
 		ret = rtl2832_sdr_set_tuner_freq(s);
 	} else {
@@ -1217,7 +1211,7 @@ static int rtl2832_sdr_enum_fmt_sdr_cap(struct file *file, void *priv,
 {
 	struct rtl2832_sdr_state *s = video_drvdata(file);
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(&s->udev->dev, "\n");
 
 	if (f->index >= s->num_formats)
 		return -EINVAL;
@@ -1233,7 +1227,7 @@ static int rtl2832_sdr_g_fmt_sdr_cap(struct file *file, void *priv,
 {
 	struct rtl2832_sdr_state *s = video_drvdata(file);
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(&s->udev->dev, "\n");
 
 	f->fmt.sdr.pixelformat = s->pixelformat;
 	f->fmt.sdr.buffersize = s->buffersize;
@@ -1250,7 +1244,7 @@ static int rtl2832_sdr_s_fmt_sdr_cap(struct file *file, void *priv,
 	struct vb2_queue *q = &s->vb_queue;
 	int i;
 
-	dev_dbg(&s->udev->dev, "%s: pixelformat fourcc %4.4s\n", __func__,
+	dev_dbg(&s->udev->dev, "pixelformat fourcc %4.4s\n",
 			(char *)&f->fmt.sdr.pixelformat);
 
 	if (vb2_is_busy(q))
@@ -1280,7 +1274,7 @@ static int rtl2832_sdr_try_fmt_sdr_cap(struct file *file, void *priv,
 	struct rtl2832_sdr_state *s = video_drvdata(file);
 	int i;
 
-	dev_dbg(&s->udev->dev, "%s: pixelformat fourcc %4.4s\n", __func__,
+	dev_dbg(&s->udev->dev, "pixelformat fourcc %4.4s\n",
 			(char *)&f->fmt.sdr.pixelformat);
 
 	memset(f->fmt.sdr.reserved, 0, sizeof(f->fmt.sdr.reserved));
@@ -1354,8 +1348,8 @@ static int rtl2832_sdr_s_ctrl(struct v4l2_ctrl *ctrl)
 	int ret;
 
 	dev_dbg(&s->udev->dev,
-			"%s: id=%d name=%s val=%d min=%lld max=%lld step=%lld\n",
-			__func__, ctrl->id, ctrl->name, ctrl->val,
+			"id=%d name=%s val=%d min=%lld max=%lld step=%lld\n",
+			ctrl->id, ctrl->name, ctrl->val,
 			ctrl->minimum, ctrl->maximum, ctrl->step);
 
 	switch (ctrl->id) {
@@ -1432,7 +1426,7 @@ struct dvb_frontend *rtl2832_sdr_attach(struct dvb_frontend *fe,
 	s->pixelformat = formats[0].pixelformat;
 	s->buffersize = formats[0].buffersize;
 	s->num_formats = NUM_FORMATS;
-	if (rtl2832_sdr_emulated_fmt == false)
+	if (!rtl2832_sdr_emulated_fmt)
 		s->num_formats -= 1;
 
 	mutex_init(&s->v4l2_lock);
diff --git a/drivers/media/dvb-frontends/si2165.c b/drivers/media/dvb-frontends/si2165.c
index 3a2d6c5aded6..98ddb49ad52b 100644
--- a/drivers/media/dvb-frontends/si2165.c
+++ b/drivers/media/dvb-frontends/si2165.c
@@ -1,5 +1,5 @@
 /*
-    Driver for Silicon Labs SI2165 DVB-C/-T Demodulator
+    Driver for Silicon Labs Si2161 DVB-T and Si2165 DVB-C/-T Demodulator
 
     Copyright (C) 2013-2014 Matthias Schwarzott <zzam@gentoo.org>
 
@@ -44,9 +44,7 @@ struct si2165_state {
 
 	struct si2165_config config;
 
-	/* chip revision */
-	u8 revcode;
-	/* chip type */
+	u8 chip_revcode;
 	u8 chip_type;
 
 	/* calculated by xtal and div settings */
@@ -312,7 +310,7 @@ static u32 si2165_get_fe_clk(struct si2165_state *state)
 	return state->adc_clk;
 }
 
-static bool si2165_wait_init_done(struct si2165_state *state)
+static int si2165_wait_init_done(struct si2165_state *state)
 {
 	int ret = -EINVAL;
 	u8 val = 0;
@@ -407,7 +405,7 @@ static int si2165_upload_firmware(struct si2165_state *state)
 	int ret;
 
 	const struct firmware *fw = NULL;
-	u8 *fw_file = SI2165_FIRMWARE;
+	u8 *fw_file;
 	const u8 *data;
 	u32 len;
 	u32 offset;
@@ -415,10 +413,20 @@ static int si2165_upload_firmware(struct si2165_state *state)
 	u8 block_count;
 	u16 crc_expected;
 
+	switch (state->chip_revcode) {
+	case 0x03: /* revision D */
+		fw_file = SI2165_FIRMWARE_REV_D;
+		break;
+	default:
+		dev_info(&state->i2c->dev, "%s: no firmware file for revision=%d\n",
+			KBUILD_MODNAME, state->chip_revcode);
+		return 0;
+	}
+
 	/* request the firmware, this will block and timeout */
 	ret = request_firmware(&fw, fw_file, state->i2c->dev.parent);
 	if (ret) {
-		dev_warn(&state->i2c->dev, "%s: firmare file '%s' not found\n",
+		dev_warn(&state->i2c->dev, "%s: firmware file '%s' not found\n",
 				KBUILD_MODNAME, fw_file);
 		goto error;
 	}
@@ -908,7 +916,7 @@ static void si2165_release(struct dvb_frontend *fe)
 
 static struct dvb_frontend_ops si2165_ops = {
 	.info = {
-		.name = "Silicon Labs Si2165",
+		.name = "Silicon Labs ",
 		.caps =	FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
@@ -948,6 +956,8 @@ struct dvb_frontend *si2165_attach(const struct si2165_config *config,
 	int n;
 	int io_ret;
 	u8 val;
+	char rev_char;
+	const char *chip_name;
 
 	if (config == NULL || i2c == NULL)
 		goto error;
@@ -984,7 +994,7 @@ struct dvb_frontend *si2165_attach(const struct si2165_config *config,
 	if (val != state->config.chip_mode)
 		goto error;
 
-	io_ret = si2165_readreg8(state, 0x0023 , &state->revcode);
+	io_ret = si2165_readreg8(state, 0x0023, &state->chip_revcode);
 	if (io_ret < 0)
 		goto error;
 
@@ -997,22 +1007,35 @@ struct dvb_frontend *si2165_attach(const struct si2165_config *config,
 	if (io_ret < 0)
 		goto error;
 
-	dev_info(&state->i2c->dev, "%s: hardware revision 0x%02x, chip type 0x%02x\n",
-		 KBUILD_MODNAME, state->revcode, state->chip_type);
+	if (state->chip_revcode < 26)
+		rev_char = 'A' + state->chip_revcode;
+	else
+		rev_char = '?';
 
-	/* It is a guess that register 0x0118 (chip type?) can be used to
-	 * differ between si2161, si2163 and si2165
-	 * Only si2165 has been tested.
-	 */
-	if (state->revcode == 0x03 && state->chip_type == 0x07) {
+	switch (state->chip_type) {
+	case 0x06:
+		chip_name = "Si2161";
+		state->has_dvbt = true;
+		break;
+	case 0x07:
+		chip_name = "Si2165";
 		state->has_dvbt = true;
 		state->has_dvbc = true;
-	} else {
-		dev_err(&state->i2c->dev, "%s: Unsupported chip.\n",
-			KBUILD_MODNAME);
+		break;
+	default:
+		dev_err(&state->i2c->dev, "%s: Unsupported Silicon Labs chip (type %d, rev %d)\n",
+			KBUILD_MODNAME, state->chip_type, state->chip_revcode);
 		goto error;
 	}
 
+	dev_info(&state->i2c->dev,
+		"%s: Detected Silicon Labs %s-%c (type %d, rev %d)\n",
+		KBUILD_MODNAME, chip_name, rev_char, state->chip_type,
+		state->chip_revcode);
+
+	strlcat(state->frontend.ops.info.name, chip_name,
+			sizeof(state->frontend.ops.info.name));
+
 	n = 0;
 	if (state->has_dvbt) {
 		state->frontend.ops.delsys[n++] = SYS_DVBT;
@@ -1037,4 +1060,4 @@ MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
 MODULE_DESCRIPTION("Silicon Labs Si2165 DVB-C/-T Demodulator driver");
 MODULE_AUTHOR("Matthias Schwarzott <zzam@gentoo.org>");
 MODULE_LICENSE("GPL");
-MODULE_FIRMWARE(SI2165_FIRMWARE);
+MODULE_FIRMWARE(SI2165_FIRMWARE_REV_D);
diff --git a/drivers/media/dvb-frontends/si2165_priv.h b/drivers/media/dvb-frontends/si2165_priv.h
index d4cc93fe1096..2b70cf12cd79 100644
--- a/drivers/media/dvb-frontends/si2165_priv.h
+++ b/drivers/media/dvb-frontends/si2165_priv.h
@@ -18,6 +18,6 @@
 #ifndef _DVB_SI2165_PRIV
 #define _DVB_SI2165_PRIV
 
-#define SI2165_FIRMWARE "dvb-demod-si2165.fw"
+#define SI2165_FIRMWARE_REV_D "dvb-demod-si2165.fw"
 
 #endif /* _DVB_SI2165_PRIV */
diff --git a/drivers/media/dvb-frontends/si2168.c b/drivers/media/dvb-frontends/si2168.c
index 8f81d979de30..1cd93be281ed 100644
--- a/drivers/media/dvb-frontends/si2168.c
+++ b/drivers/media/dvb-frontends/si2168.c
@@ -55,8 +55,7 @@ static int si2168_cmd_execute(struct si2168 *s, struct si2168_cmd *cmd)
 				break;
 		}
 
-		dev_dbg(&s->client->dev, "%s: cmd execution took %d ms\n",
-				__func__,
+		dev_dbg(&s->client->dev, "cmd execution took %d ms\n",
 				jiffies_to_msecs(jiffies) -
 				(jiffies_to_msecs(timeout) - TIMEOUT));
 
@@ -75,7 +74,7 @@ err_mutex_unlock:
 
 	return 0;
 err:
-	dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&s->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -150,12 +149,12 @@ static int si2168_read_status(struct dvb_frontend *fe, fe_status_t *status)
 		c->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
 	}
 
-	dev_dbg(&s->client->dev, "%s: status=%02x args=%*ph\n",
-			__func__, *status, cmd.rlen, cmd.args);
+	dev_dbg(&s->client->dev, "status=%02x args=%*ph\n",
+			*status, cmd.rlen, cmd.args);
 
 	return 0;
 err:
-	dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&s->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -168,10 +167,10 @@ static int si2168_set_frontend(struct dvb_frontend *fe)
 	u8 bandwidth, delivery_system;
 
 	dev_dbg(&s->client->dev,
-			"%s: delivery_system=%u modulation=%u frequency=%u bandwidth_hz=%u symbol_rate=%u inversion=%u\n",
-			__func__, c->delivery_system, c->modulation,
+			"delivery_system=%u modulation=%u frequency=%u bandwidth_hz=%u symbol_rate=%u inversion=%u, stream_id=%d\n",
+			c->delivery_system, c->modulation,
 			c->frequency, c->bandwidth_hz, c->symbol_rate,
-			c->inversion);
+			c->inversion, c->stream_id);
 
 	if (!s->active) {
 		ret = -EAGAIN;
@@ -235,6 +234,18 @@ static int si2168_set_frontend(struct dvb_frontend *fe)
 	if (ret)
 		goto err;
 
+	if (c->delivery_system == SYS_DVBT2) {
+		/* select PLP */
+		cmd.args[0] = 0x52;
+		cmd.args[1] = c->stream_id & 0xff;
+		cmd.args[2] = c->stream_id == NO_STREAM_ID_FILTER ? 0 : 1;
+		cmd.wlen = 3;
+		cmd.rlen = 1;
+		ret = si2168_cmd_execute(s, &cmd);
+		if (ret)
+			goto err;
+	}
+
 	memcpy(cmd.args, "\x51\x03", 2);
 	cmd.wlen = 2;
 	cmd.rlen = 12;
@@ -297,13 +308,6 @@ static int si2168_set_frontend(struct dvb_frontend *fe)
 	if (ret)
 		goto err;
 
-	memcpy(cmd.args, "\x14\x00\x01\x10\x16\x00", 6);
-	cmd.wlen = 6;
-	cmd.rlen = 4;
-	ret = si2168_cmd_execute(s, &cmd);
-	if (ret)
-		goto err;
-
 	memcpy(cmd.args, "\x14\x00\x09\x10\xe3\x18", 6);
 	cmd.wlen = 6;
 	cmd.rlen = 4;
@@ -343,7 +347,7 @@ static int si2168_set_frontend(struct dvb_frontend *fe)
 
 	return 0;
 err:
-	dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&s->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -357,8 +361,9 @@ static int si2168_init(struct dvb_frontend *fe)
 	struct si2168_cmd cmd;
 	unsigned int chip_id;
 
-	dev_dbg(&s->client->dev, "%s:\n", __func__);
+	dev_dbg(&s->client->dev, "\n");
 
+	/* initialize */
 	memcpy(cmd.args, "\xc0\x12\x00\x0c\x00\x0d\x16\x00\x00\x00\x00\x00\x00", 13);
 	cmd.wlen = 13;
 	cmd.rlen = 0;
@@ -366,6 +371,26 @@ static int si2168_init(struct dvb_frontend *fe)
 	if (ret)
 		goto err;
 
+	if (s->fw_loaded) {
+		/* resume */
+		memcpy(cmd.args, "\xc0\x06\x08\x0f\x00\x20\x21\x01", 8);
+		cmd.wlen = 8;
+		cmd.rlen = 1;
+		ret = si2168_cmd_execute(s, &cmd);
+		if (ret)
+			goto err;
+
+		memcpy(cmd.args, "\x85", 1);
+		cmd.wlen = 1;
+		cmd.rlen = 1;
+		ret = si2168_cmd_execute(s, &cmd);
+		if (ret)
+			goto err;
+
+		goto warm;
+	}
+
+	/* power up */
 	memcpy(cmd.args, "\xc0\x06\x01\x0f\x00\x20\x20\x01", 8);
 	cmd.wlen = 8;
 	cmd.rlen = 1;
@@ -400,16 +425,16 @@ static int si2168_init(struct dvb_frontend *fe)
 		break;
 	default:
 		dev_err(&s->client->dev,
-				"%s: unkown chip version Si21%d-%c%c%c\n",
-				KBUILD_MODNAME, cmd.args[2], cmd.args[1],
+				"unknown chip version Si21%d-%c%c%c\n",
+				cmd.args[2], cmd.args[1],
 				cmd.args[3], cmd.args[4]);
 		ret = -EINVAL;
 		goto err;
 	}
 
 	/* cold state - try to download firmware */
-	dev_info(&s->client->dev, "%s: found a '%s' in cold state\n",
-			KBUILD_MODNAME, si2168_ops.info.name);
+	dev_info(&s->client->dev, "found a '%s' in cold state\n",
+			si2168_ops.info.name);
 
 	/* request the firmware, this will block and timeout */
 	ret = request_firmware(&fw, fw_file, &s->client->dev);
@@ -422,18 +447,18 @@ static int si2168_init(struct dvb_frontend *fe)
 
 		if (ret == 0) {
 			dev_notice(&s->client->dev,
-					"%s: please install firmware file '%s'\n",
-					KBUILD_MODNAME, SI2168_B40_FIRMWARE);
+					"please install firmware file '%s'\n",
+					SI2168_B40_FIRMWARE);
 		} else {
 			dev_err(&s->client->dev,
-					"%s: firmware file '%s' not found\n",
-					KBUILD_MODNAME, fw_file);
+					"firmware file '%s' not found\n",
+					fw_file);
 			goto err;
 		}
 	}
 
-	dev_info(&s->client->dev, "%s: downloading firmware from file '%s'\n",
-			KBUILD_MODNAME, fw_file);
+	dev_info(&s->client->dev, "downloading firmware from file '%s'\n",
+			fw_file);
 
 	for (remaining = fw->size; remaining > 0; remaining -= i2c_wr_max) {
 		len = remaining;
@@ -446,8 +471,8 @@ static int si2168_init(struct dvb_frontend *fe)
 		ret = si2168_cmd_execute(s, &cmd);
 		if (ret) {
 			dev_err(&s->client->dev,
-					"%s: firmware download failed=%d\n",
-					KBUILD_MODNAME, ret);
+					"firmware download failed=%d\n",
+					ret);
 			goto err;
 		}
 	}
@@ -462,8 +487,20 @@ static int si2168_init(struct dvb_frontend *fe)
 	if (ret)
 		goto err;
 
-	dev_info(&s->client->dev, "%s: found a '%s' in warm state\n",
-			KBUILD_MODNAME, si2168_ops.info.name);
+	/* set ts mode */
+	memcpy(cmd.args, "\x14\x00\x01\x10\x10\x00", 6);
+	cmd.args[4] |= s->ts_mode;
+	cmd.wlen = 6;
+	cmd.rlen = 4;
+	ret = si2168_cmd_execute(s, &cmd);
+	if (ret)
+		goto err;
+
+	s->fw_loaded = true;
+
+warm:
+	dev_info(&s->client->dev, "found a '%s' in warm state\n",
+			si2168_ops.info.name);
 
 	s->active = true;
 
@@ -472,7 +509,7 @@ err:
 	if (fw)
 		release_firmware(fw);
 
-	dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&s->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -482,7 +519,7 @@ static int si2168_sleep(struct dvb_frontend *fe)
 	int ret;
 	struct si2168_cmd cmd;
 
-	dev_dbg(&s->client->dev, "%s:\n", __func__);
+	dev_dbg(&s->client->dev, "\n");
 
 	s->active = false;
 
@@ -495,7 +532,7 @@ static int si2168_sleep(struct dvb_frontend *fe)
 
 	return 0;
 err:
-	dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&s->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -528,8 +565,7 @@ static int si2168_select(struct i2c_adapter *adap, void *mux_priv, u32 chan)
 	/* open tuner I2C gate */
 	ret = __i2c_transfer(s->client->adapter, &gate_open_msg, 1);
 	if (ret != 1) {
-		dev_warn(&s->client->dev, "%s: i2c write failed=%d\n",
-				KBUILD_MODNAME, ret);
+		dev_warn(&s->client->dev, "i2c write failed=%d\n", ret);
 		if (ret >= 0)
 			ret = -EREMOTEIO;
 	} else {
@@ -553,8 +589,7 @@ static int si2168_deselect(struct i2c_adapter *adap, void *mux_priv, u32 chan)
 	/* close tuner I2C gate */
 	ret = __i2c_transfer(s->client->adapter, &gate_close_msg, 1);
 	if (ret != 1) {
-		dev_warn(&s->client->dev, "%s: i2c write failed=%d\n",
-				KBUILD_MODNAME, ret);
+		dev_warn(&s->client->dev, "i2c write failed=%d\n", ret);
 		if (ret >= 0)
 			ret = -EREMOTEIO;
 	} else {
@@ -587,7 +622,8 @@ static const struct dvb_frontend_ops si2168_ops = {
 			FE_CAN_GUARD_INTERVAL_AUTO |
 			FE_CAN_HIERARCHY_AUTO |
 			FE_CAN_MUTE_TS |
-			FE_CAN_2G_MODULATION
+			FE_CAN_2G_MODULATION |
+			FE_CAN_MULTISTREAM
 	},
 
 	.get_tune_settings = si2168_get_tune_settings,
@@ -607,12 +643,12 @@ static int si2168_probe(struct i2c_client *client,
 	struct si2168 *s;
 	int ret;
 
-	dev_dbg(&client->dev, "%s:\n", __func__);
+	dev_dbg(&client->dev, "\n");
 
 	s = kzalloc(sizeof(struct si2168), GFP_KERNEL);
 	if (!s) {
 		ret = -ENOMEM;
-		dev_err(&client->dev, "%s: kzalloc() failed\n", KBUILD_MODNAME);
+		dev_err(&client->dev, "kzalloc() failed\n");
 		goto err;
 	}
 
@@ -633,16 +669,17 @@ static int si2168_probe(struct i2c_client *client,
 
 	*config->i2c_adapter = s->adapter;
 	*config->fe = &s->fe;
+	s->ts_mode = config->ts_mode;
+	s->fw_loaded = false;
 
 	i2c_set_clientdata(client, s);
 
 	dev_info(&s->client->dev,
-			"%s: Silicon Labs Si2168 successfully attached\n",
-			KBUILD_MODNAME);
+			"Silicon Labs Si2168 successfully attached\n");
 	return 0;
 err:
 	kfree(s);
-	dev_dbg(&client->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -650,7 +687,7 @@ static int si2168_remove(struct i2c_client *client)
 {
 	struct si2168 *s = i2c_get_clientdata(client);
 
-	dev_dbg(&client->dev, "%s:\n", __func__);
+	dev_dbg(&client->dev, "\n");
 
 	i2c_del_mux_adapter(s->adapter);
 
diff --git a/drivers/media/dvb-frontends/si2168.h b/drivers/media/dvb-frontends/si2168.h
index 3c5b5ab01796..e086d6719451 100644
--- a/drivers/media/dvb-frontends/si2168.h
+++ b/drivers/media/dvb-frontends/si2168.h
@@ -34,6 +34,12 @@ struct si2168_config {
 	 * returned by driver
 	 */
 	struct i2c_adapter **i2c_adapter;
+
+	/* TS mode */
+	u8 ts_mode;
 };
 
+#define SI2168_TS_PARALLEL	0x06
+#define SI2168_TS_SERIAL	0x03
+
 #endif
diff --git a/drivers/media/dvb-frontends/si2168_priv.h b/drivers/media/dvb-frontends/si2168_priv.h
index ebbf502ec313..e13983ed4be1 100644
--- a/drivers/media/dvb-frontends/si2168_priv.h
+++ b/drivers/media/dvb-frontends/si2168_priv.h
@@ -36,6 +36,8 @@ struct si2168 {
 	fe_delivery_system_t delivery_system;
 	fe_status_t fe_status;
 	bool active;
+	bool fw_loaded;
+	u8 ts_mode;
 };
 
 /* firmare command struct */
diff --git a/drivers/media/dvb-frontends/si21xx.c b/drivers/media/dvb-frontends/si21xx.c
index 73b47cc6a13b..16850e2bf02f 100644
--- a/drivers/media/dvb-frontends/si21xx.c
+++ b/drivers/media/dvb-frontends/si21xx.c
@@ -236,6 +236,9 @@ static int si21_writeregs(struct si21xx_state *state, u8 reg1,
 				.len = len + 1
 	};
 
+	if (len > sizeof(buf) - 1)
+		return -EINVAL;
+
 	msg.buf[0] =  reg1;
 	memcpy(msg.buf + 1, data, len);
 
diff --git a/drivers/media/dvb-frontends/sp2.c b/drivers/media/dvb-frontends/sp2.c
new file mode 100644
index 000000000000..9b684d5c8f91
--- /dev/null
+++ b/drivers/media/dvb-frontends/sp2.c
@@ -0,0 +1,441 @@
+/*
+ * CIMaX SP2/SP2HF (Atmel T90FJR) CI driver
+ *
+ * Copyright (C) 2014 Olli Salonen <olli.salonen@iki.fi>
+ *
+ * Heavily based on CIMax2(R) SP2 driver in conjunction with NetUp Dual
+ * DVB-S2 CI card (cimax2) with following copyrights:
+ *
+ *  Copyright (C) 2009 NetUP Inc.
+ *  Copyright (C) 2009 Igor M. Liplianin <liplianin@netup.ru>
+ *  Copyright (C) 2009 Abylay Ospan <aospan@netup.ru>
+ *
+ *    This program is free software; you can redistribute it and/or modify
+ *    it under the terms of the GNU General Public License as published by
+ *    the Free Software Foundation; either version 2 of the License, or
+ *    (at your option) any later version.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU General Public License for more details.
+ */
+
+#include "sp2_priv.h"
+
+static int sp2_read_i2c(struct sp2 *s, u8 reg, u8 *buf, int len)
+{
+	int ret;
+	struct i2c_client *client = s->client;
+	struct i2c_adapter *adap = client->adapter;
+	struct i2c_msg msg[] = {
+		{
+			.addr = client->addr,
+			.flags = 0,
+			.buf = &reg,
+			.len = 1
+		}, {
+			.addr = client->addr,
+			.flags	= I2C_M_RD,
+			.buf = buf,
+			.len = len
+		}
+	};
+
+	ret = i2c_transfer(adap, msg, 2);
+
+	if (ret != 2) {
+		dev_err(&client->dev, "i2c read error, reg = 0x%02x, status = %d\n",
+				reg, ret);
+		if (ret < 0)
+			return ret;
+		else
+			return -EIO;
+	}
+
+	dev_dbg(&s->client->dev, "addr=0x%04x, reg = 0x%02x, data = %02x\n",
+				client->addr, reg, buf[0]);
+
+	return 0;
+}
+
+static int sp2_write_i2c(struct sp2 *s, u8 reg, u8 *buf, int len)
+{
+	int ret;
+	u8 buffer[35];
+	struct i2c_client *client = s->client;
+	struct i2c_adapter *adap = client->adapter;
+	struct i2c_msg msg = {
+		.addr = client->addr,
+		.flags = 0,
+		.buf = &buffer[0],
+		.len = len + 1
+	};
+
+	if ((len + 1) > sizeof(buffer)) {
+		dev_err(&client->dev, "i2c wr reg=%02x: len=%d is too big!\n",
+				reg, len);
+		return -EINVAL;
+	}
+
+	buffer[0] = reg;
+	memcpy(&buffer[1], buf, len);
+
+	ret = i2c_transfer(adap, &msg, 1);
+
+	if (ret != 1) {
+		dev_err(&client->dev, "i2c write error, reg = 0x%02x, status = %d\n",
+				reg, ret);
+		if (ret < 0)
+			return ret;
+		else
+			return -EIO;
+	}
+
+	return 0;
+}
+
+static int sp2_ci_op_cam(struct dvb_ca_en50221 *en50221, int slot, u8 acs,
+			u8 read, int addr, u8 data)
+{
+	struct sp2 *s = en50221->data;
+	u8 store;
+	int mem, ret;
+	int (*ci_op_cam)(void*, u8, int, u8, int*) = s->ci_control;
+
+	dev_dbg(&s->client->dev, "slot=%d, acs=0x%02x, addr=0x%04x, data = 0x%02x",
+			slot, acs, addr, data);
+
+	if (slot != 0)
+		return -EINVAL;
+
+	/*
+	 * change module access type between IO space and attribute memory
+	 * when needed
+	 */
+	if (s->module_access_type != acs) {
+		ret = sp2_read_i2c(s, 0x00, &store, 1);
+
+		if (ret)
+			return ret;
+
+		store &= ~(SP2_MOD_CTL_ACS1 | SP2_MOD_CTL_ACS0);
+		store |= acs;
+
+		ret = sp2_write_i2c(s, 0x00, &store, 1);
+		if (ret)
+			return ret;
+	}
+
+	s->module_access_type = acs;
+
+	/* implementation of ci_op_cam is device specific */
+	if (ci_op_cam) {
+		ret = ci_op_cam(s->priv, read, addr, data, &mem);
+	} else {
+		dev_err(&s->client->dev, "callback not defined");
+		return -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	if (read) {
+		dev_dbg(&s->client->dev, "cam read, addr=0x%04x, data = 0x%04x",
+				addr, mem);
+		return mem;
+	} else {
+		return 0;
+	}
+}
+
+int sp2_ci_read_attribute_mem(struct dvb_ca_en50221 *en50221,
+				int slot, int addr)
+{
+	return sp2_ci_op_cam(en50221, slot, SP2_CI_ATTR_ACS,
+			SP2_CI_RD, addr, 0);
+}
+
+int sp2_ci_write_attribute_mem(struct dvb_ca_en50221 *en50221,
+				int slot, int addr, u8 data)
+{
+	return sp2_ci_op_cam(en50221, slot, SP2_CI_ATTR_ACS,
+			SP2_CI_WR, addr, data);
+}
+
+int sp2_ci_read_cam_control(struct dvb_ca_en50221 *en50221,
+				int slot, u8 addr)
+{
+	return sp2_ci_op_cam(en50221, slot, SP2_CI_IO_ACS,
+			SP2_CI_RD, addr, 0);
+}
+
+int sp2_ci_write_cam_control(struct dvb_ca_en50221 *en50221,
+				int slot, u8 addr, u8 data)
+{
+	return sp2_ci_op_cam(en50221, slot, SP2_CI_IO_ACS,
+			SP2_CI_WR, addr, data);
+}
+
+int sp2_ci_slot_reset(struct dvb_ca_en50221 *en50221, int slot)
+{
+	struct sp2 *s = en50221->data;
+	u8 buf;
+	int ret;
+
+	dev_dbg(&s->client->dev, "slot: %d\n", slot);
+
+	if (slot != 0)
+		return -EINVAL;
+
+	/* RST on */
+	buf = SP2_MOD_CTL_RST;
+	ret = sp2_write_i2c(s, 0x00, &buf, 1);
+
+	if (ret)
+		return ret;
+
+	usleep_range(500, 600);
+
+	/* RST off */
+	buf = 0x00;
+	ret = sp2_write_i2c(s, 0x00, &buf, 1);
+
+	if (ret)
+		return ret;
+
+	msleep(1000);
+
+	return 0;
+}
+
+int sp2_ci_slot_shutdown(struct dvb_ca_en50221 *en50221, int slot)
+{
+	struct sp2 *s = en50221->data;
+
+	dev_dbg(&s->client->dev, "slot:%d\n", slot);
+
+	/* not implemented */
+	return 0;
+}
+
+int sp2_ci_slot_ts_enable(struct dvb_ca_en50221 *en50221, int slot)
+{
+	struct sp2 *s = en50221->data;
+	u8 buf;
+
+	dev_dbg(&s->client->dev, "slot:%d\n", slot);
+
+	if (slot != 0)
+		return -EINVAL;
+
+	sp2_read_i2c(s, 0x00, &buf, 1);
+
+	/* disable bypass and enable TS */
+	buf |= (SP2_MOD_CTL_TSOEN | SP2_MOD_CTL_TSIEN);
+	return sp2_write_i2c(s, 0, &buf, 1);
+}
+
+int sp2_ci_poll_slot_status(struct dvb_ca_en50221 *en50221,
+				int slot, int open)
+{
+	struct sp2 *s = en50221->data;
+	u8 buf[2];
+	int ret;
+
+	dev_dbg(&s->client->dev, "slot:%d open:%d\n", slot, open);
+
+	/*
+	 * CAM module INSERT/REMOVE processing. Slow operation because of i2c
+	 * transfers. Throttle read to one per sec.
+	 */
+	if (time_after(jiffies, s->next_status_checked_time)) {
+		ret = sp2_read_i2c(s, 0x00, buf, 1);
+		s->next_status_checked_time = jiffies +	msecs_to_jiffies(1000);
+
+		if (ret)
+			return 0;
+
+		if (buf[0] & SP2_MOD_CTL_DET)
+			s->status = DVB_CA_EN50221_POLL_CAM_PRESENT |
+					DVB_CA_EN50221_POLL_CAM_READY;
+		else
+			s->status = 0;
+	}
+
+	return s->status;
+}
+
+int sp2_init(struct sp2 *s)
+{
+	int ret = 0;
+	u8 buf;
+	u8 cimax_init[34] = {
+		0x00, /* module A control*/
+		0x00, /* auto select mask high A */
+		0x00, /* auto select mask low A */
+		0x00, /* auto select pattern high A */
+		0x00, /* auto select pattern low A */
+		0x44, /* memory access time A, 600 ns */
+		0x00, /* invert input A */
+		0x00, /* RFU */
+		0x00, /* RFU */
+		0x00, /* module B control*/
+		0x00, /* auto select mask high B */
+		0x00, /* auto select mask low B */
+		0x00, /* auto select pattern high B */
+		0x00, /* auto select pattern low B */
+		0x44, /* memory access time B, 600 ns */
+		0x00, /* invert input B */
+		0x00, /* RFU */
+		0x00, /* RFU */
+		0x00, /* auto select mask high Ext */
+		0x00, /* auto select mask low Ext */
+		0x00, /* auto select pattern high Ext */
+		0x00, /* auto select pattern low Ext */
+		0x00, /* RFU */
+		0x02, /* destination - module A */
+		0x01, /* power control reg, VCC power on */
+		0x00, /* RFU */
+		0x00, /* int status read only */
+		0x00, /* Interrupt Mask Register */
+		0x05, /* EXTINT=active-high, INT=push-pull */
+		0x00, /* USCG1 */
+		0x04, /* ack active low */
+		0x00, /* LOCK = 0 */
+		0x22, /* unknown */
+		0x00, /* synchronization? */
+	};
+
+	dev_dbg(&s->client->dev, "\n");
+
+	s->ca.owner = THIS_MODULE;
+	s->ca.read_attribute_mem = sp2_ci_read_attribute_mem;
+	s->ca.write_attribute_mem = sp2_ci_write_attribute_mem;
+	s->ca.read_cam_control = sp2_ci_read_cam_control;
+	s->ca.write_cam_control = sp2_ci_write_cam_control;
+	s->ca.slot_reset = sp2_ci_slot_reset;
+	s->ca.slot_shutdown = sp2_ci_slot_shutdown;
+	s->ca.slot_ts_enable = sp2_ci_slot_ts_enable;
+	s->ca.poll_slot_status = sp2_ci_poll_slot_status;
+	s->ca.data = s;
+	s->module_access_type = 0;
+
+	/* initialize all regs */
+	ret = sp2_write_i2c(s, 0x00, &cimax_init[0], 34);
+	if (ret)
+		goto err;
+
+	/* lock registers */
+	buf = 1;
+	ret = sp2_write_i2c(s, 0x1f, &buf, 1);
+	if (ret)
+		goto err;
+
+	/* power on slots */
+	ret = sp2_write_i2c(s, 0x18, &buf, 1);
+	if (ret)
+		goto err;
+
+	ret = dvb_ca_en50221_init(s->dvb_adap, &s->ca, 0, 1);
+	if (ret)
+		goto err;
+
+	return 0;
+
+err:
+	dev_dbg(&s->client->dev, "init failed=%d\n", ret);
+	return ret;
+}
+
+int sp2_exit(struct i2c_client *client)
+{
+	struct sp2 *s;
+
+	dev_dbg(&client->dev, "\n");
+
+	if (client == NULL)
+		return 0;
+
+	s = i2c_get_clientdata(client);
+	if (s == NULL)
+		return 0;
+
+	if (s->ca.data == NULL)
+		return 0;
+
+	dvb_ca_en50221_release(&s->ca);
+
+	return 0;
+}
+
+static int sp2_probe(struct i2c_client *client,
+		const struct i2c_device_id *id)
+{
+	struct sp2_config *cfg = client->dev.platform_data;
+	struct sp2 *s;
+	int ret;
+
+	dev_dbg(&client->dev, "\n");
+
+	s = kzalloc(sizeof(struct sp2), GFP_KERNEL);
+	if (!s) {
+		ret = -ENOMEM;
+		dev_err(&client->dev, "kzalloc() failed\n");
+		goto err;
+	}
+
+	s->client = client;
+	s->dvb_adap = cfg->dvb_adap;
+	s->priv = cfg->priv;
+	s->ci_control = cfg->ci_control;
+
+	i2c_set_clientdata(client, s);
+
+	ret = sp2_init(s);
+	if (ret)
+		goto err;
+
+	dev_info(&s->client->dev, "CIMaX SP2 successfully attached\n");
+	return 0;
+err:
+	dev_dbg(&client->dev, "init failed=%d\n", ret);
+	kfree(s);
+
+	return ret;
+}
+
+static int sp2_remove(struct i2c_client *client)
+{
+	struct si2157 *s = i2c_get_clientdata(client);
+
+	dev_dbg(&client->dev, "\n");
+
+	sp2_exit(client);
+	if (s != NULL)
+		kfree(s);
+
+	return 0;
+}
+
+static const struct i2c_device_id sp2_id[] = {
+	{"sp2", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, sp2_id);
+
+static struct i2c_driver sp2_driver = {
+	.driver = {
+		.owner	= THIS_MODULE,
+		.name	= "sp2",
+	},
+	.probe		= sp2_probe,
+	.remove		= sp2_remove,
+	.id_table	= sp2_id,
+};
+
+module_i2c_driver(sp2_driver);
+
+MODULE_DESCRIPTION("CIMaX SP2/HF CI driver");
+MODULE_AUTHOR("Olli Salonen <olli.salonen@iki.fi>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/sp2.h b/drivers/media/dvb-frontends/sp2.h
new file mode 100644
index 000000000000..6cceea022d49
--- /dev/null
+++ b/drivers/media/dvb-frontends/sp2.h
@@ -0,0 +1,53 @@
+/*
+ * CIMaX SP2/HF CI driver
+ *
+ * Copyright (C) 2014 Olli Salonen <olli.salonen@iki.fi>
+ *
+ *    This program is free software; you can redistribute it and/or modify
+ *    it under the terms of the GNU General Public License as published by
+ *    the Free Software Foundation; either version 2 of the License, or
+ *    (at your option) any later version.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU General Public License for more details.
+ */
+
+#ifndef SP2_H
+#define SP2_H
+
+#include <linux/kconfig.h>
+#include "dvb_ca_en50221.h"
+
+/*
+ * I2C address
+ * 0x40 (port 0)
+ * 0x41 (port 1)
+ */
+struct sp2_config {
+	/* dvb_adapter to attach the ci to */
+	struct dvb_adapter *dvb_adap;
+
+	/* function ci_control handles the device specific ci ops */
+	void *ci_control;
+
+	/* priv is passed back to function ci_control */
+	void *priv;
+};
+
+extern int sp2_ci_read_attribute_mem(struct dvb_ca_en50221 *en50221,
+					int slot, int addr);
+extern int sp2_ci_write_attribute_mem(struct dvb_ca_en50221 *en50221,
+					int slot, int addr, u8 data);
+extern int sp2_ci_read_cam_control(struct dvb_ca_en50221 *en50221,
+					int slot, u8 addr);
+extern int sp2_ci_write_cam_control(struct dvb_ca_en50221 *en50221,
+					int slot, u8 addr, u8 data);
+extern int sp2_ci_slot_reset(struct dvb_ca_en50221 *en50221, int slot);
+extern int sp2_ci_slot_shutdown(struct dvb_ca_en50221 *en50221, int slot);
+extern int sp2_ci_slot_ts_enable(struct dvb_ca_en50221 *en50221, int slot);
+extern int sp2_ci_poll_slot_status(struct dvb_ca_en50221 *en50221,
+					int slot, int open);
+
+#endif
diff --git a/drivers/media/dvb-frontends/sp2_priv.h b/drivers/media/dvb-frontends/sp2_priv.h
new file mode 100644
index 000000000000..37fef7bcd63f
--- /dev/null
+++ b/drivers/media/dvb-frontends/sp2_priv.h
@@ -0,0 +1,50 @@
+/*
+ * CIMaX SP2/HF CI driver
+ *
+ * Copyright (C) 2014 Olli Salonen <olli.salonen@iki.fi>
+ *
+ *    This program is free software; you can redistribute it and/or modify
+ *    it under the terms of the GNU General Public License as published by
+ *    the Free Software Foundation; either version 2 of the License, or
+ *    (at your option) any later version.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU General Public License for more details.
+ */
+
+#ifndef SP2_PRIV_H
+#define SP2_PRIV_H
+
+#include "sp2.h"
+#include "dvb_frontend.h"
+
+/* state struct */
+struct sp2 {
+	int status;
+	struct i2c_client *client;
+	struct dvb_adapter *dvb_adap;
+	struct dvb_ca_en50221 ca;
+	int module_access_type;
+	unsigned long next_status_checked_time;
+	void *priv;
+	void *ci_control;
+};
+
+#define SP2_CI_ATTR_ACS		0x00
+#define SP2_CI_IO_ACS		0x04
+#define SP2_CI_WR		0
+#define SP2_CI_RD		1
+
+/* Module control register (0x00 module A, 0x09 module B) bits */
+#define SP2_MOD_CTL_DET		0x01
+#define SP2_MOD_CTL_AUTO	0x02
+#define SP2_MOD_CTL_ACS0	0x04
+#define SP2_MOD_CTL_ACS1	0x08
+#define SP2_MOD_CTL_HAD		0x10
+#define SP2_MOD_CTL_TSIEN	0x20
+#define SP2_MOD_CTL_TSOEN	0x40
+#define SP2_MOD_CTL_RST		0x80
+
+#endif
diff --git a/drivers/media/dvb-frontends/sp8870.c b/drivers/media/dvb-frontends/sp8870.c
index 2aa8ef76eba2..57dc2abaa87b 100644
--- a/drivers/media/dvb-frontends/sp8870.c
+++ b/drivers/media/dvb-frontends/sp8870.c
@@ -394,8 +394,7 @@ static int sp8870_read_ber (struct dvb_frontend* fe, u32 * ber)
 	if (ret < 0)
 		return -EIO;
 
-	 tmp = ret << 6;
-
+	tmp = ret << 6;
 	if (tmp >= 0x3FFF0)
 		tmp = ~0;
 
diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c
index 59b6e661acc0..b31ff265ff24 100644
--- a/drivers/media/dvb-frontends/stv0367.c
+++ b/drivers/media/dvb-frontends/stv0367.c
@@ -59,7 +59,6 @@ struct stv0367cab_state {
 	int locked;			/* channel found		*/
 	u32 freq_khz;			/* found frequency (in kHz)	*/
 	u32 symbol_rate;		/* found symbol rate (in Bds)	*/
-	enum stv0367cab_mod modulation;	/* modulation			*/
 	fe_spectral_inversion_t	spect_inv; /* Spectrum Inversion	*/
 };
 
@@ -554,7 +553,7 @@ static struct st_register def0367ter[STV0367TER_NBREGS] = {
 #define RF_LOOKUP_TABLE_SIZE  31
 #define RF_LOOKUP_TABLE2_SIZE 16
 /* RF Level (for RF AGC->AGC1) Lookup Table, depends on the board and tuner.*/
-s32 stv0367cab_RF_LookUp1[RF_LOOKUP_TABLE_SIZE][RF_LOOKUP_TABLE_SIZE] = {
+static const s32 stv0367cab_RF_LookUp1[RF_LOOKUP_TABLE_SIZE][RF_LOOKUP_TABLE_SIZE] = {
 	{/*AGC1*/
 		48, 50, 51, 53, 54, 56, 57, 58, 60, 61, 62, 63,
 		64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75,
@@ -566,7 +565,7 @@ s32 stv0367cab_RF_LookUp1[RF_LOOKUP_TABLE_SIZE][RF_LOOKUP_TABLE_SIZE] = {
 	}
 };
 /* RF Level (for IF AGC->AGC2) Lookup Table, depends on the board and tuner.*/
-s32 stv0367cab_RF_LookUp2[RF_LOOKUP_TABLE2_SIZE][RF_LOOKUP_TABLE2_SIZE] = {
+static const s32 stv0367cab_RF_LookUp2[RF_LOOKUP_TABLE2_SIZE][RF_LOOKUP_TABLE2_SIZE] = {
 	{/*AGC2*/
 		28, 29, 31, 32, 34, 35, 36, 37,
 		38, 39, 40, 41, 42, 43, 44, 45,
@@ -1935,8 +1934,6 @@ static int stv0367ter_get_frontend(struct dvb_frontend *fe)
 	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
 	struct stv0367_state *state = fe->demodulator_priv;
 	struct stv0367ter_state *ter_state = state->ter_state;
-
-	int error = 0;
 	enum stv0367_ter_mode mode;
 	int constell = 0,/* snr = 0,*/ Data = 0;
 
@@ -2020,7 +2017,7 @@ static int stv0367ter_get_frontend(struct dvb_frontend *fe)
 
 	p->guard_interval = stv0367_readbits(state, F367TER_SYR_GUARD);
 
-	return error;
+	return 0;
 }
 
 static int stv0367ter_read_snr(struct dvb_frontend *fe, u16 *snr)
@@ -2999,7 +2996,6 @@ enum stv0367_cab_signal_type stv0367cab_algo(struct stv0367_state *state,
 
 	if (QAMFEC_Lock) {
 		signalType = FE_CAB_DATAOK;
-		cab_state->modulation = p->modulation;
 		cab_state->spect_inv = stv0367_readbits(state,
 							F367CAB_QUAD_INV);
 #if 0
@@ -3165,7 +3161,7 @@ static int stv0367cab_get_frontend(struct dvb_frontend *fe)
 	case FE_CAB_MOD_QAM128:
 		p->modulation = QAM_128;
 		break;
-	case QAM_256:
+	case FE_CAB_MOD_QAM256:
 		p->modulation = QAM_256;
 		break;
 	default:
diff --git a/drivers/media/dvb-frontends/stv0900_core.c b/drivers/media/dvb-frontends/stv0900_core.c
index e5a87b57d855..2c88abfab531 100644
--- a/drivers/media/dvb-frontends/stv0900_core.c
+++ b/drivers/media/dvb-frontends/stv0900_core.c
@@ -1270,7 +1270,6 @@ enum fe_stv0900_error stv0900_st_dvbs2_single(struct stv0900_internal *intp,
 					enum fe_stv0900_demod_mode LDPC_Mode,
 					enum fe_stv0900_demod_num demod)
 {
-	enum fe_stv0900_error error = STV0900_NO_ERROR;
 	s32 reg_ind;
 
 	dprintk("%s\n", __func__);
@@ -1337,7 +1336,7 @@ enum fe_stv0900_error stv0900_st_dvbs2_single(struct stv0900_internal *intp,
 		break;
 	}
 
-	return error;
+	return STV0900_NO_ERROR;
 }
 
 static enum fe_stv0900_error stv0900_init_internal(struct dvb_frontend *fe,
@@ -1555,8 +1554,6 @@ static int stv0900_status(struct stv0900_internal *intp,
 static int stv0900_set_mis(struct stv0900_internal *intp,
 				enum fe_stv0900_demod_num demod, int mis)
 {
-	enum fe_stv0900_error error = STV0900_NO_ERROR;
-
 	dprintk("%s\n", __func__);
 
 	if (mis < 0 || mis > 255) {
@@ -1569,7 +1566,7 @@ static int stv0900_set_mis(struct stv0900_internal *intp,
 		stv0900_write_reg(intp, ISIBITENA, 0xff);
 	}
 
-	return error;
+	return STV0900_NO_ERROR;
 }
 
 
diff --git a/drivers/media/dvb-frontends/stv0900_sw.c b/drivers/media/dvb-frontends/stv0900_sw.c
index 4ce1d260b3eb..a0a7b1664c53 100644
--- a/drivers/media/dvb-frontends/stv0900_sw.c
+++ b/drivers/media/dvb-frontends/stv0900_sw.c
@@ -1733,9 +1733,10 @@ static void stv0900_set_search_standard(struct stv0900_internal *intp,
 		break;
 	case STV0900_SEARCH_DSS:
 		dprintk("Search Standard = DSS\n");
-	case STV0900_SEARCH_DVBS2:
 		break;
+	case STV0900_SEARCH_DVBS2:
 		dprintk("Search Standard = DVBS2\n");
+		break;
 	case STV0900_AUTO_SEARCH:
 	default:
 		dprintk("Search Standard = AUTO\n");
diff --git a/drivers/media/dvb-frontends/tc90522.c b/drivers/media/dvb-frontends/tc90522.c
new file mode 100644
index 000000000000..d9905fb52f84
--- /dev/null
+++ b/drivers/media/dvb-frontends/tc90522.c
@@ -0,0 +1,840 @@
+/*
+ * Toshiba TC90522 Demodulator
+ *
+ * Copyright (C) 2014 Akihiro Tsukada <tskd08@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * NOTICE:
+ * This driver is incomplete and lacks init/config of the chips,
+ * as the necessary info is not disclosed.
+ * It assumes that users of this driver (such as a PCI bridge of
+ * DTV receiver cards) properly init and configure the chip
+ * via I2C *before* calling this driver's init() function.
+ *
+ * Currently, PT3 driver is the only one that uses this driver,
+ * and contains init/config code in its firmware.
+ * Thus some part of the code might be dependent on PT3 specific config.
+ */
+
+#include <linux/kernel.h>
+#include <linux/math64.h>
+#include <linux/dvb/frontend.h>
+#include "dvb_math.h"
+#include "tc90522.h"
+
+#define TC90522_I2C_THRU_REG 0xfe
+
+#define TC90522_MODULE_IDX(addr) (((u8)(addr) & 0x02U) >> 1)
+
+struct tc90522_state {
+	struct tc90522_config cfg;
+	struct dvb_frontend fe;
+	struct i2c_client *i2c_client;
+	struct i2c_adapter tuner_i2c;
+
+	bool lna;
+};
+
+struct reg_val {
+	u8 reg;
+	u8 val;
+};
+
+static int
+reg_write(struct tc90522_state *state, const struct reg_val *regs, int num)
+{
+	int i, ret;
+	struct i2c_msg msg;
+
+	ret = 0;
+	msg.addr = state->i2c_client->addr;
+	msg.flags = 0;
+	msg.len = 2;
+	for (i = 0; i < num; i++) {
+		msg.buf = (u8 *)&regs[i];
+		ret = i2c_transfer(state->i2c_client->adapter, &msg, 1);
+		if (ret == 0)
+			ret = -EIO;
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+static int reg_read(struct tc90522_state *state, u8 reg, u8 *val, u8 len)
+{
+	struct i2c_msg msgs[2] = {
+		{
+			.addr = state->i2c_client->addr,
+			.flags = 0,
+			.buf = &reg,
+			.len = 1,
+		},
+		{
+			.addr = state->i2c_client->addr,
+			.flags = I2C_M_RD,
+			.buf = val,
+			.len = len,
+		},
+	};
+	int ret;
+
+	ret = i2c_transfer(state->i2c_client->adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret == ARRAY_SIZE(msgs))
+		ret = 0;
+	else if (ret >= 0)
+		ret = -EIO;
+	return ret;
+}
+
+static struct tc90522_state *cfg_to_state(struct tc90522_config *c)
+{
+	return container_of(c, struct tc90522_state, cfg);
+}
+
+
+static int tc90522s_set_tsid(struct dvb_frontend *fe)
+{
+	struct reg_val set_tsid[] = {
+		{ 0x8f, 00 },
+		{ 0x90, 00 }
+	};
+
+	set_tsid[0].val = (fe->dtv_property_cache.stream_id & 0xff00) >> 8;
+	set_tsid[1].val = fe->dtv_property_cache.stream_id & 0xff;
+	return reg_write(fe->demodulator_priv, set_tsid, ARRAY_SIZE(set_tsid));
+}
+
+static int tc90522t_set_layers(struct dvb_frontend *fe)
+{
+	struct reg_val rv;
+	u8 laysel;
+
+	laysel = ~fe->dtv_property_cache.isdbt_layer_enabled & 0x07;
+	laysel = (laysel & 0x01) << 2 | (laysel & 0x02) | (laysel & 0x04) >> 2;
+	rv.reg = 0x71;
+	rv.val = laysel;
+	return reg_write(fe->demodulator_priv, &rv, 1);
+}
+
+/* frontend ops */
+
+static int tc90522s_read_status(struct dvb_frontend *fe, fe_status_t *status)
+{
+	struct tc90522_state *state;
+	int ret;
+	u8 reg;
+
+	state = fe->demodulator_priv;
+	ret = reg_read(state, 0xc3, &reg, 1);
+	if (ret < 0)
+		return ret;
+
+	*status = 0;
+	if (reg & 0x80) /* input level under min ? */
+		return 0;
+	*status |= FE_HAS_SIGNAL;
+
+	if (reg & 0x60) /* carrier? */
+		return 0;
+	*status |= FE_HAS_CARRIER | FE_HAS_VITERBI | FE_HAS_SYNC;
+
+	if (reg & 0x10)
+		return 0;
+	if (reg_read(state, 0xc5, &reg, 1) < 0 || !(reg & 0x03))
+		return 0;
+	*status |= FE_HAS_LOCK;
+	return 0;
+}
+
+static int tc90522t_read_status(struct dvb_frontend *fe, fe_status_t *status)
+{
+	struct tc90522_state *state;
+	int ret;
+	u8 reg;
+
+	state = fe->demodulator_priv;
+	ret = reg_read(state, 0x96, &reg, 1);
+	if (ret < 0)
+		return ret;
+
+	*status = 0;
+	if (reg & 0xe0) {
+		*status = FE_HAS_SIGNAL | FE_HAS_CARRIER | FE_HAS_VITERBI
+				| FE_HAS_SYNC | FE_HAS_LOCK;
+		return 0;
+	}
+
+	ret = reg_read(state, 0x80, &reg, 1);
+	if (ret < 0)
+		return ret;
+
+	if (reg & 0xf0)
+		return 0;
+	*status |= FE_HAS_SIGNAL | FE_HAS_CARRIER;
+
+	if (reg & 0x0c)
+		return 0;
+	*status |= FE_HAS_SYNC | FE_HAS_VITERBI;
+
+	if (reg & 0x02)
+		return 0;
+	*status |= FE_HAS_LOCK;
+	return 0;
+}
+
+static const fe_code_rate_t fec_conv_sat[] = {
+	FEC_NONE, /* unused */
+	FEC_1_2, /* for BPSK */
+	FEC_1_2, FEC_2_3, FEC_3_4, FEC_5_6, FEC_7_8, /* for QPSK */
+	FEC_2_3, /* for 8PSK. (trellis code) */
+};
+
+static int tc90522s_get_frontend(struct dvb_frontend *fe)
+{
+	struct tc90522_state *state;
+	struct dtv_frontend_properties *c;
+	struct dtv_fe_stats *stats;
+	int ret, i;
+	int layers;
+	u8 val[10];
+	u32 cndat;
+
+	state = fe->demodulator_priv;
+	c = &fe->dtv_property_cache;
+	c->delivery_system = SYS_ISDBS;
+
+	layers = 0;
+	ret = reg_read(state, 0xe8, val, 3);
+	if (ret == 0) {
+		int slots;
+		u8 v;
+
+		/* high/single layer */
+		v = (val[0] & 0x70) >> 4;
+		c->modulation = (v == 7) ? PSK_8 : QPSK;
+		c->fec_inner = fec_conv_sat[v];
+		c->layer[0].fec = c->fec_inner;
+		c->layer[0].modulation = c->modulation;
+		c->layer[0].segment_count = val[1] & 0x3f; /* slots */
+
+		/* low layer */
+		v = (val[0] & 0x07);
+		c->layer[1].fec = fec_conv_sat[v];
+		if (v == 0)  /* no low layer */
+			c->layer[1].segment_count = 0;
+		else
+			c->layer[1].segment_count = val[2] & 0x3f; /* slots */
+		/* actually, BPSK if v==1, but not defined in fe_modulation_t */
+		c->layer[1].modulation = QPSK;
+		layers = (v > 0) ? 2 : 1;
+
+		slots =  c->layer[0].segment_count +  c->layer[1].segment_count;
+		c->symbol_rate = 28860000 * slots / 48;
+	}
+
+	/* statistics */
+
+	stats = &c->strength;
+	stats->len = 0;
+	/* let the connected tuner set RSSI property cache */
+	if (fe->ops.tuner_ops.get_rf_strength) {
+		u16 dummy;
+
+		fe->ops.tuner_ops.get_rf_strength(fe, &dummy);
+	}
+
+	stats = &c->cnr;
+	stats->len = 1;
+	stats->stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	cndat = 0;
+	ret = reg_read(state, 0xbc, val, 2);
+	if (ret == 0)
+		cndat = val[0] << 8 | val[1];
+	if (cndat >= 3000) {
+		u32 p, p4;
+		s64 cn;
+
+		cndat -= 3000;  /* cndat: 4.12 fixed point float */
+		/*
+		 * cnr[mdB] = -1634.6 * P^5 + 14341 * P^4 - 50259 * P^3
+		 *                 + 88977 * P^2 - 89565 * P + 58857
+		 *  (P = sqrt(cndat) / 64)
+		 */
+		/* p := sqrt(cndat) << 8 = P << 14, 2.14 fixed  point float */
+		/* cn = cnr << 3 */
+		p = int_sqrt(cndat << 16);
+		p4 = cndat * cndat;
+		cn = div64_s64(-16346LL * p4 * p, 10) >> 35;
+		cn += (14341LL * p4) >> 21;
+		cn -= (50259LL * cndat * p) >> 23;
+		cn += (88977LL * cndat) >> 9;
+		cn -= (89565LL * p) >> 11;
+		cn += 58857  << 3;
+		stats->stat[0].svalue = cn >> 3;
+		stats->stat[0].scale = FE_SCALE_DECIBEL;
+	}
+
+	/* per-layer post viterbi BER (or PER? config dependent?) */
+	stats = &c->post_bit_error;
+	memset(stats, 0, sizeof(*stats));
+	stats->len = layers;
+	ret = reg_read(state, 0xeb, val, 10);
+	if (ret < 0)
+		for (i = 0; i < layers; i++)
+			stats->stat[i].scale = FE_SCALE_NOT_AVAILABLE;
+	else {
+		for (i = 0; i < layers; i++) {
+			stats->stat[i].scale = FE_SCALE_COUNTER;
+			stats->stat[i].uvalue = val[i * 5] << 16
+				| val[i * 5 + 1] << 8 | val[i * 5 + 2];
+		}
+	}
+	stats = &c->post_bit_count;
+	memset(stats, 0, sizeof(*stats));
+	stats->len = layers;
+	if (ret < 0)
+		for (i = 0; i < layers; i++)
+			stats->stat[i].scale = FE_SCALE_NOT_AVAILABLE;
+	else {
+		for (i = 0; i < layers; i++) {
+			stats->stat[i].scale = FE_SCALE_COUNTER;
+			stats->stat[i].uvalue =
+				val[i * 5 + 3] << 8 | val[i * 5 + 4];
+			stats->stat[i].uvalue *= 204 * 8;
+		}
+	}
+
+	return 0;
+}
+
+
+static const fe_transmit_mode_t tm_conv[] = {
+	TRANSMISSION_MODE_2K,
+	TRANSMISSION_MODE_4K,
+	TRANSMISSION_MODE_8K,
+	0
+};
+
+static const fe_code_rate_t fec_conv_ter[] = {
+	FEC_1_2, FEC_2_3, FEC_3_4, FEC_5_6, FEC_7_8, 0, 0, 0
+};
+
+static const fe_modulation_t mod_conv[] = {
+	DQPSK, QPSK, QAM_16, QAM_64, 0, 0, 0, 0
+};
+
+static int tc90522t_get_frontend(struct dvb_frontend *fe)
+{
+	struct tc90522_state *state;
+	struct dtv_frontend_properties *c;
+	struct dtv_fe_stats *stats;
+	int ret, i;
+	int layers;
+	u8 val[15], mode;
+	u32 cndat;
+
+	state = fe->demodulator_priv;
+	c = &fe->dtv_property_cache;
+	c->delivery_system = SYS_ISDBT;
+	c->bandwidth_hz = 6000000;
+	mode = 1;
+	ret = reg_read(state, 0xb0, val, 1);
+	if (ret == 0) {
+		mode = (val[0] & 0xc0) >> 2;
+		c->transmission_mode = tm_conv[mode];
+		c->guard_interval = (val[0] & 0x30) >> 4;
+	}
+
+	ret = reg_read(state, 0xb2, val, 6);
+	layers = 0;
+	if (ret == 0) {
+		u8 v;
+
+		c->isdbt_partial_reception = val[0] & 0x01;
+		c->isdbt_sb_mode = (val[0] & 0xc0) == 0x01;
+
+		/* layer A */
+		v = (val[2] & 0x78) >> 3;
+		if (v == 0x0f)
+			c->layer[0].segment_count = 0;
+		else {
+			layers++;
+			c->layer[0].segment_count = v;
+			c->layer[0].fec = fec_conv_ter[(val[1] & 0x1c) >> 2];
+			c->layer[0].modulation = mod_conv[(val[1] & 0xe0) >> 5];
+			v = (val[1] & 0x03) << 1 | (val[2] & 0x80) >> 7;
+			c->layer[0].interleaving = v;
+		}
+
+		/* layer B */
+		v = (val[3] & 0x03) << 1 | (val[4] & 0xc0) >> 6;
+		if (v == 0x0f)
+			c->layer[1].segment_count = 0;
+		else {
+			layers++;
+			c->layer[1].segment_count = v;
+			c->layer[1].fec = fec_conv_ter[(val[3] & 0xe0) >> 5];
+			c->layer[1].modulation = mod_conv[(val[2] & 0x07)];
+			c->layer[1].interleaving = (val[3] & 0x1c) >> 2;
+		}
+
+		/* layer C */
+		v = (val[5] & 0x1e) >> 1;
+		if (v == 0x0f)
+			c->layer[2].segment_count = 0;
+		else {
+			layers++;
+			c->layer[2].segment_count = v;
+			c->layer[2].fec = fec_conv_ter[(val[4] & 0x07)];
+			c->layer[2].modulation = mod_conv[(val[4] & 0x38) >> 3];
+			c->layer[2].interleaving = (val[5] & 0xe0) >> 5;
+		}
+	}
+
+	/* statistics */
+
+	stats = &c->strength;
+	stats->len = 0;
+	/* let the connected tuner set RSSI property cache */
+	if (fe->ops.tuner_ops.get_rf_strength) {
+		u16 dummy;
+
+		fe->ops.tuner_ops.get_rf_strength(fe, &dummy);
+	}
+
+	stats = &c->cnr;
+	stats->len = 1;
+	stats->stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	cndat = 0;
+	ret = reg_read(state, 0x8b, val, 3);
+	if (ret == 0)
+		cndat = val[0] << 16 | val[1] << 8 | val[2];
+	if (cndat != 0) {
+		u32 p, tmp;
+		s64 cn;
+
+		/*
+		 * cnr[mdB] = 0.024 P^4 - 1.6 P^3 + 39.8 P^2 + 549.1 P + 3096.5
+		 * (P = 10log10(5505024/cndat))
+		 */
+		/* cn = cnr << 3 (61.3 fixed point float */
+		/* p = 10log10(5505024/cndat) << 24  (8.24 fixed point float)*/
+		p = intlog10(5505024) - intlog10(cndat);
+		p *= 10;
+
+		cn = 24772;
+		cn += div64_s64(43827LL * p, 10) >> 24;
+		tmp = p >> 8;
+		cn += div64_s64(3184LL * tmp * tmp, 10) >> 32;
+		tmp = p >> 13;
+		cn -= div64_s64(128LL * tmp * tmp * tmp, 10) >> 33;
+		tmp = p >> 18;
+		cn += div64_s64(192LL * tmp * tmp * tmp * tmp, 1000) >> 24;
+
+		stats->stat[0].svalue = cn >> 3;
+		stats->stat[0].scale = FE_SCALE_DECIBEL;
+	}
+
+	/* per-layer post viterbi BER (or PER? config dependent?) */
+	stats = &c->post_bit_error;
+	memset(stats, 0, sizeof(*stats));
+	stats->len = layers;
+	ret = reg_read(state, 0x9d, val, 15);
+	if (ret < 0)
+		for (i = 0; i < layers; i++)
+			stats->stat[i].scale = FE_SCALE_NOT_AVAILABLE;
+	else {
+		for (i = 0; i < layers; i++) {
+			stats->stat[i].scale = FE_SCALE_COUNTER;
+			stats->stat[i].uvalue = val[i * 3] << 16
+				| val[i * 3 + 1] << 8 | val[i * 3 + 2];
+		}
+	}
+	stats = &c->post_bit_count;
+	memset(stats, 0, sizeof(*stats));
+	stats->len = layers;
+	if (ret < 0)
+		for (i = 0; i < layers; i++)
+			stats->stat[i].scale = FE_SCALE_NOT_AVAILABLE;
+	else {
+		for (i = 0; i < layers; i++) {
+			stats->stat[i].scale = FE_SCALE_COUNTER;
+			stats->stat[i].uvalue =
+				val[9 + i * 2] << 8 | val[9 + i * 2 + 1];
+			stats->stat[i].uvalue *= 204 * 8;
+		}
+	}
+
+	return 0;
+}
+
+static const struct reg_val reset_sat = { 0x03, 0x01 };
+static const struct reg_val reset_ter = { 0x01, 0x40 };
+
+static int tc90522_set_frontend(struct dvb_frontend *fe)
+{
+	struct tc90522_state *state;
+	int ret;
+
+	state = fe->demodulator_priv;
+
+	if (fe->ops.tuner_ops.set_params)
+		ret = fe->ops.tuner_ops.set_params(fe);
+	else
+		ret = -ENODEV;
+	if (ret < 0)
+		goto failed;
+
+	if (fe->ops.delsys[0] == SYS_ISDBS) {
+		ret = tc90522s_set_tsid(fe);
+		if (ret < 0)
+			goto failed;
+		ret = reg_write(state, &reset_sat, 1);
+	} else {
+		ret = tc90522t_set_layers(fe);
+		if (ret < 0)
+			goto failed;
+		ret = reg_write(state, &reset_ter, 1);
+	}
+	if (ret < 0)
+		goto failed;
+
+	return 0;
+
+failed:
+	dev_warn(&state->tuner_i2c.dev, "(%s) failed. [adap%d-fe%d]\n",
+			__func__, fe->dvb->num, fe->id);
+	return ret;
+}
+
+static int tc90522_get_tune_settings(struct dvb_frontend *fe,
+	struct dvb_frontend_tune_settings *settings)
+{
+	if (fe->ops.delsys[0] == SYS_ISDBS) {
+		settings->min_delay_ms = 250;
+		settings->step_size = 1000;
+		settings->max_drift = settings->step_size * 2;
+	} else {
+		settings->min_delay_ms = 400;
+		settings->step_size = 142857;
+		settings->max_drift = settings->step_size;
+	}
+	return 0;
+}
+
+static int tc90522_set_if_agc(struct dvb_frontend *fe, bool on)
+{
+	struct reg_val agc_sat[] = {
+		{ 0x0a, 0x00 },
+		{ 0x10, 0x30 },
+		{ 0x11, 0x00 },
+		{ 0x03, 0x01 },
+	};
+	struct reg_val agc_ter[] = {
+		{ 0x25, 0x00 },
+		{ 0x23, 0x4c },
+		{ 0x01, 0x40 },
+	};
+	struct tc90522_state *state;
+	struct reg_val *rv;
+	int num;
+
+	state = fe->demodulator_priv;
+	if (fe->ops.delsys[0] == SYS_ISDBS) {
+		agc_sat[0].val = on ? 0xff : 0x00;
+		agc_sat[1].val |= 0x80;
+		agc_sat[1].val |= on ? 0x01 : 0x00;
+		agc_sat[2].val |= on ? 0x40 : 0x00;
+		rv = agc_sat;
+		num = ARRAY_SIZE(agc_sat);
+	} else {
+		agc_ter[0].val = on ? 0x40 : 0x00;
+		agc_ter[1].val |= on ? 0x00 : 0x01;
+		rv = agc_ter;
+		num = ARRAY_SIZE(agc_ter);
+	}
+	return reg_write(state, rv, num);
+}
+
+static const struct reg_val sleep_sat = { 0x17, 0x01 };
+static const struct reg_val sleep_ter = { 0x03, 0x90 };
+
+static int tc90522_sleep(struct dvb_frontend *fe)
+{
+	struct tc90522_state *state;
+	int ret;
+
+	state = fe->demodulator_priv;
+	if (fe->ops.delsys[0] == SYS_ISDBS)
+		ret = reg_write(state, &sleep_sat, 1);
+	else {
+		ret = reg_write(state, &sleep_ter, 1);
+		if (ret == 0 && fe->ops.set_lna &&
+		    fe->dtv_property_cache.lna == LNA_AUTO) {
+			fe->dtv_property_cache.lna = 0;
+			ret = fe->ops.set_lna(fe);
+			fe->dtv_property_cache.lna = LNA_AUTO;
+		}
+	}
+	if (ret < 0)
+		dev_warn(&state->tuner_i2c.dev,
+			"(%s) failed. [adap%d-fe%d]\n",
+			__func__, fe->dvb->num, fe->id);
+	return ret;
+}
+
+static const struct reg_val wakeup_sat = { 0x17, 0x00 };
+static const struct reg_val wakeup_ter = { 0x03, 0x80 };
+
+static int tc90522_init(struct dvb_frontend *fe)
+{
+	struct tc90522_state *state;
+	int ret;
+
+	/*
+	 * Because the init sequence is not public,
+	 * the parent device/driver should have init'ed the device before.
+	 * just wake up the device here.
+	 */
+
+	state = fe->demodulator_priv;
+	if (fe->ops.delsys[0] == SYS_ISDBS)
+		ret = reg_write(state, &wakeup_sat, 1);
+	else {
+		ret = reg_write(state, &wakeup_ter, 1);
+		if (ret == 0 && fe->ops.set_lna &&
+		    fe->dtv_property_cache.lna == LNA_AUTO) {
+			fe->dtv_property_cache.lna = 1;
+			ret = fe->ops.set_lna(fe);
+			fe->dtv_property_cache.lna = LNA_AUTO;
+		}
+	}
+	if (ret < 0) {
+		dev_warn(&state->tuner_i2c.dev,
+			"(%s) failed. [adap%d-fe%d]\n",
+			__func__, fe->dvb->num, fe->id);
+		return ret;
+	}
+
+	/* prefer 'all-layers' to 'none' as a default */
+	if (fe->dtv_property_cache.isdbt_layer_enabled == 0)
+		fe->dtv_property_cache.isdbt_layer_enabled = 7;
+	return tc90522_set_if_agc(fe, true);
+}
+
+
+/*
+ * tuner I2C adapter functions
+ */
+
+static int
+tc90522_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
+{
+	struct tc90522_state *state;
+	struct i2c_msg *new_msgs;
+	int i, j;
+	int ret, rd_num;
+	u8 wbuf[256];
+	u8 *p, *bufend;
+
+	if (num <= 0)
+		return -EINVAL;
+
+	rd_num = 0;
+	for (i = 0; i < num; i++)
+		if (msgs[i].flags & I2C_M_RD)
+			rd_num++;
+	new_msgs = kmalloc(sizeof(*new_msgs) * (num + rd_num), GFP_KERNEL);
+	if (!new_msgs)
+		return -ENOMEM;
+
+	state = i2c_get_adapdata(adap);
+	p = wbuf;
+	bufend = wbuf + sizeof(wbuf);
+	for (i = 0, j = 0; i < num; i++, j++) {
+		new_msgs[j].addr = state->i2c_client->addr;
+		new_msgs[j].flags = msgs[i].flags;
+
+		if (msgs[i].flags & I2C_M_RD) {
+			new_msgs[j].flags &= ~I2C_M_RD;
+			if (p + 2 > bufend)
+				break;
+			p[0] = TC90522_I2C_THRU_REG;
+			p[1] = msgs[i].addr << 1 | 0x01;
+			new_msgs[j].buf = p;
+			new_msgs[j].len = 2;
+			p += 2;
+			j++;
+			new_msgs[j].addr = state->i2c_client->addr;
+			new_msgs[j].flags = msgs[i].flags;
+			new_msgs[j].buf = msgs[i].buf;
+			new_msgs[j].len = msgs[i].len;
+			continue;
+		}
+
+		if (p + msgs[i].len + 2 > bufend)
+			break;
+		p[0] = TC90522_I2C_THRU_REG;
+		p[1] = msgs[i].addr << 1;
+		memcpy(p + 2, msgs[i].buf, msgs[i].len);
+		new_msgs[j].buf = p;
+		new_msgs[j].len = msgs[i].len + 2;
+		p += new_msgs[j].len;
+	}
+
+	if (i < num)
+		ret = -ENOMEM;
+	else
+		ret = i2c_transfer(state->i2c_client->adapter, new_msgs, j);
+	if (ret >= 0 && ret < j)
+		ret = -EIO;
+	kfree(new_msgs);
+	return (ret == j) ? num : ret;
+}
+
+static u32 tc90522_functionality(struct i2c_adapter *adap)
+{
+	return I2C_FUNC_I2C;
+}
+
+static const struct i2c_algorithm tc90522_tuner_i2c_algo = {
+	.master_xfer   = &tc90522_master_xfer,
+	.functionality = &tc90522_functionality,
+};
+
+
+/*
+ * I2C driver functions
+ */
+
+static const struct dvb_frontend_ops tc90522_ops_sat = {
+	.delsys = { SYS_ISDBS },
+	.info = {
+		.name = "Toshiba TC90522 ISDB-S module",
+		.frequency_min =  950000,
+		.frequency_max = 2150000,
+		.caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_AUTO |
+			FE_CAN_QAM_AUTO | FE_CAN_TRANSMISSION_MODE_AUTO |
+			FE_CAN_GUARD_INTERVAL_AUTO | FE_CAN_HIERARCHY_AUTO,
+	},
+
+	.init = tc90522_init,
+	.sleep = tc90522_sleep,
+	.set_frontend = tc90522_set_frontend,
+	.get_tune_settings = tc90522_get_tune_settings,
+
+	.get_frontend = tc90522s_get_frontend,
+	.read_status = tc90522s_read_status,
+};
+
+static const struct dvb_frontend_ops tc90522_ops_ter = {
+	.delsys = { SYS_ISDBT },
+	.info = {
+		.name = "Toshiba TC90522 ISDB-T module",
+		.frequency_min = 470000000,
+		.frequency_max = 770000000,
+		.frequency_stepsize = 142857,
+		.caps = FE_CAN_INVERSION_AUTO |
+			FE_CAN_FEC_1_2  | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
+			FE_CAN_FEC_5_6  | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
+			FE_CAN_QPSK     | FE_CAN_QAM_16 | FE_CAN_QAM_64 |
+			FE_CAN_QAM_AUTO | FE_CAN_TRANSMISSION_MODE_AUTO |
+			FE_CAN_GUARD_INTERVAL_AUTO | FE_CAN_RECOVER |
+			FE_CAN_HIERARCHY_AUTO,
+	},
+
+	.init = tc90522_init,
+	.sleep = tc90522_sleep,
+	.set_frontend = tc90522_set_frontend,
+	.get_tune_settings = tc90522_get_tune_settings,
+
+	.get_frontend = tc90522t_get_frontend,
+	.read_status = tc90522t_read_status,
+};
+
+
+static int tc90522_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	struct tc90522_state *state;
+	struct tc90522_config *cfg;
+	const struct dvb_frontend_ops *ops;
+	struct i2c_adapter *adap;
+	int ret;
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+	state->i2c_client = client;
+
+	cfg = client->dev.platform_data;
+	memcpy(&state->cfg, cfg, sizeof(state->cfg));
+	cfg->fe = state->cfg.fe = &state->fe;
+	ops =  id->driver_data == 0 ? &tc90522_ops_sat : &tc90522_ops_ter;
+	memcpy(&state->fe.ops, ops, sizeof(*ops));
+	state->fe.demodulator_priv = state;
+
+	adap = &state->tuner_i2c;
+	adap->owner = THIS_MODULE;
+	adap->algo = &tc90522_tuner_i2c_algo;
+	adap->dev.parent = &client->dev;
+	strlcpy(adap->name, "tc90522_sub", sizeof(adap->name));
+	i2c_set_adapdata(adap, state);
+	ret = i2c_add_adapter(adap);
+	if (ret < 0)
+		goto err;
+	cfg->tuner_i2c = state->cfg.tuner_i2c = adap;
+
+	i2c_set_clientdata(client, &state->cfg);
+	dev_info(&client->dev, "Toshiba TC90522 attached.\n");
+	return 0;
+
+err:
+	kfree(state);
+	return ret;
+}
+
+static int tc90522_remove(struct i2c_client *client)
+{
+	struct tc90522_state *state;
+
+	state = cfg_to_state(i2c_get_clientdata(client));
+	i2c_del_adapter(&state->tuner_i2c);
+	kfree(state);
+	return 0;
+}
+
+
+static const struct i2c_device_id tc90522_id[] = {
+	{ TC90522_I2C_DEV_SAT, 0 },
+	{ TC90522_I2C_DEV_TER, 1 },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, tc90522_id);
+
+static struct i2c_driver tc90522_driver = {
+	.driver = {
+		.name	= "tc90522",
+	},
+	.probe		= tc90522_probe,
+	.remove		= tc90522_remove,
+	.id_table	= tc90522_id,
+};
+
+module_i2c_driver(tc90522_driver);
+
+MODULE_DESCRIPTION("Toshiba TC90522 frontend");
+MODULE_AUTHOR("Akihiro TSUKADA");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/tc90522.h b/drivers/media/dvb-frontends/tc90522.h
new file mode 100644
index 000000000000..b1cbddfa6ee6
--- /dev/null
+++ b/drivers/media/dvb-frontends/tc90522.h
@@ -0,0 +1,42 @@
+/*
+ * Toshiba TC90522 Demodulator
+ *
+ * Copyright (C) 2014 Akihiro Tsukada <tskd08@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * The demod has 4 input (2xISDB-T and 2xISDB-S),
+ * and provides independent sub modules for each input.
+ * As the sub modules work in parallel and have the separate i2c addr's,
+ * this driver treats each sub module as one demod device.
+ */
+
+#ifndef TC90522_H
+#define TC90522_H
+
+#include <linux/i2c.h>
+#include "dvb_frontend.h"
+
+/* I2C device types */
+#define TC90522_I2C_DEV_SAT "tc90522sat"
+#define TC90522_I2C_DEV_TER "tc90522ter"
+
+struct tc90522_config {
+	/* [OUT] frontend returned by driver */
+	struct dvb_frontend *fe;
+
+	/* [OUT] tuner I2C adapter returned by driver */
+	struct i2c_adapter *tuner_i2c;
+};
+
+#endif /* TC90522_H */
diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c
index 9619be5d4827..4a19b85995f1 100644
--- a/drivers/media/dvb-frontends/tda10071.c
+++ b/drivers/media/dvb-frontends/tda10071.c
@@ -1037,7 +1037,7 @@ static int tda10071_init(struct dvb_frontend *fe)
 			ret = -EFAULT;
 			goto error;
 		} else {
-			priv->warm = 1;
+			priv->warm = true;
 		}
 
 		cmd.args[0] = CMD_GET_FW_VERSION;
diff --git a/drivers/media/dvb-frontends/zl10039.c b/drivers/media/dvb-frontends/zl10039.c
index 91b6b2e9b792..ee09ec26c553 100644
--- a/drivers/media/dvb-frontends/zl10039.c
+++ b/drivers/media/dvb-frontends/zl10039.c
@@ -111,7 +111,7 @@ static int zl10039_write(struct zl10039_state *state,
 
 	if (1 + count > sizeof(buf)) {
 		printk(KERN_WARNING
-		       "%s: i2c wr reg=%04x: len=%zd is too big!\n",
+		       "%s: i2c wr reg=%04x: len=%zu is too big!\n",
 		       KBUILD_MODNAME, reg, count);
 		return -EINVAL;
 	}
diff --git a/drivers/media/firewire/firedtv-avc.c b/drivers/media/firewire/firedtv-avc.c
index d1a1a1324ef8..251a556112a9 100644
--- a/drivers/media/firewire/firedtv-avc.c
+++ b/drivers/media/firewire/firedtv-avc.c
@@ -1157,6 +1157,10 @@ int avc_ca_pmt(struct firedtv *fdtv, char *msg, int length)
 		if (pmt_cmd_id != 1 && pmt_cmd_id != 4)
 			dev_err(fdtv->device,
 				"invalid pmt_cmd_id %d\n", pmt_cmd_id);
+		if (program_info_length > sizeof(c->operand) - 4 - write_pos) {
+			ret = -EINVAL;
+			goto out;
+		}
 
 		memcpy(&c->operand[write_pos], &msg[read_pos],
 		       program_info_length);
@@ -1180,6 +1184,12 @@ int avc_ca_pmt(struct firedtv *fdtv, char *msg, int length)
 				dev_err(fdtv->device, "invalid pmt_cmd_id %d "
 					"at stream level\n", pmt_cmd_id);
 
+			if (es_info_length > sizeof(c->operand) - 4 -
+					     write_pos) {
+				ret = -EINVAL;
+				goto out;
+			}
+
 			memcpy(&c->operand[write_pos], &msg[read_pos],
 			       es_info_length);
 			read_pos += es_info_length;
diff --git a/drivers/media/i2c/adv7343_regs.h b/drivers/media/i2c/adv7343_regs.h
index 446606764346..2f04ce4b9118 100644
--- a/drivers/media/i2c/adv7343_regs.h
+++ b/drivers/media/i2c/adv7343_regs.h
@@ -13,7 +13,7 @@
  * GNU General Public License for more details.
  */
 
-#ifndef ADV7343_REG_H
+#ifndef ADV7343_REGS_H
 #define ADV7343_REGS_H
 
 struct adv7343_std_info {
diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c
index de88b980a837..47795ff71688 100644
--- a/drivers/media/i2c/adv7604.c
+++ b/drivers/media/i2c/adv7604.c
@@ -1593,7 +1593,7 @@ static int adv7604_query_dv_timings(struct v4l2_subdev *sd,
 			bt->height += hdmi_read16(sd, 0x0b, 0xfff);
 			bt->il_vfrontporch = hdmi_read16(sd, 0x2c, 0x1fff) / 2;
 			bt->il_vsync = hdmi_read16(sd, 0x30, 0x1fff) / 2;
-			bt->vbackporch = hdmi_read16(sd, 0x34, 0x1fff) / 2;
+			bt->il_vbackporch = hdmi_read16(sd, 0x34, 0x1fff) / 2;
 		}
 		adv7604_fill_optional_dv_timings_fields(sd, timings);
 	} else {
diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c
index 0d554919cdd5..48b628bc6714 100644
--- a/drivers/media/i2c/adv7842.c
+++ b/drivers/media/i2c/adv7842.c
@@ -1435,6 +1435,8 @@ static int adv7842_query_dv_timings(struct v4l2_subdev *sd,
 
 	v4l2_dbg(1, debug, sd, "%s:\n", __func__);
 
+	memset(timings, 0, sizeof(struct v4l2_dv_timings));
+
 	/* SDP block */
 	if (state->mode == ADV7842_MODE_SDP)
 		return -ENODATA;
@@ -1483,7 +1485,7 @@ static int adv7842_query_dv_timings(struct v4l2_subdev *sd,
 					hdmi_read(sd, 0x2d)) / 2;
 			bt->il_vsync = ((hdmi_read(sd, 0x30) & 0x1f) * 256 +
 					hdmi_read(sd, 0x31)) / 2;
-			bt->vbackporch = ((hdmi_read(sd, 0x34) & 0x1f) * 256 +
+			bt->il_vbackporch = ((hdmi_read(sd, 0x34) & 0x1f) * 256 +
 					hdmi_read(sd, 0x35)) / 2;
 		}
 		adv7842_fill_optional_dv_timings_fields(sd, timings);
diff --git a/drivers/media/i2c/lm3560.c b/drivers/media/i2c/lm3560.c
index c23de593c17d..d9ece4b2d047 100644
--- a/drivers/media/i2c/lm3560.c
+++ b/drivers/media/i2c/lm3560.c
@@ -100,14 +100,14 @@ static int lm3560_enable_ctrl(struct lm3560_flash *flash,
 	int rval;
 
 	if (led_no == LM3560_LED0) {
-		if (on == true)
+		if (on)
 			rval = regmap_update_bits(flash->regmap,
 						  REG_ENABLE, 0x08, 0x08);
 		else
 			rval = regmap_update_bits(flash->regmap,
 						  REG_ENABLE, 0x08, 0x00);
 	} else {
-		if (on == true)
+		if (on)
 			rval = regmap_update_bits(flash->regmap,
 						  REG_ENABLE, 0x10, 0x10);
 		else
diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c
index cdd7c1b7259b..dd3db2458a4f 100644
--- a/drivers/media/i2c/ov7670.c
+++ b/drivers/media/i2c/ov7670.c
@@ -19,6 +19,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-mediabus.h>
+#include <media/v4l2-image-sizes.h>
 #include <media/ov7670.h>
 
 MODULE_AUTHOR("Jonathan Corbet <corbet@lwn.net>");
@@ -30,19 +31,6 @@ module_param(debug, bool, 0644);
 MODULE_PARM_DESC(debug, "Debug level (0-1)");
 
 /*
- * Basic window sizes.  These probably belong somewhere more globally
- * useful.
- */
-#define VGA_WIDTH	640
-#define VGA_HEIGHT	480
-#define QVGA_WIDTH	320
-#define QVGA_HEIGHT	240
-#define CIF_WIDTH	352
-#define CIF_HEIGHT	288
-#define QCIF_WIDTH	176
-#define	QCIF_HEIGHT	144
-
-/*
  * The 7670 sits on i2c with ID 0x42
  */
 #define OV7670_I2C_ADDR 0x42
diff --git a/drivers/media/i2c/s5k5baf.c b/drivers/media/i2c/s5k5baf.c
index 564f05f2c9ef..0e461a6fd065 100644
--- a/drivers/media/i2c/s5k5baf.c
+++ b/drivers/media/i2c/s5k5baf.c
@@ -816,7 +816,7 @@ static void s5k5baf_hw_find_min_fiv(struct s5k5baf *state)
 				 "error setting frame interval: %d\n", err);
 			state->error = -EINVAL;
 		}
-	};
+	}
 	v4l2_err(&state->sd, "cannot find correct frame interval\n");
 	state->error = -ERANGE;
 }
diff --git a/drivers/media/i2c/saa6752hs.c b/drivers/media/i2c/saa6752hs.c
index 04e9e55018a5..4024ea6f1371 100644
--- a/drivers/media/i2c/saa6752hs.c
+++ b/drivers/media/i2c/saa6752hs.c
@@ -660,7 +660,7 @@ static const struct v4l2_subdev_ops saa6752hs_ops = {
 static int saa6752hs_probe(struct i2c_client *client,
 		const struct i2c_device_id *id)
 {
-	struct saa6752hs_state *h = kzalloc(sizeof(*h), GFP_KERNEL);
+	struct saa6752hs_state *h;
 	struct v4l2_subdev *sd;
 	struct v4l2_ctrl_handler *hdl;
 	u8 addr = 0x13;
@@ -668,6 +668,8 @@ static int saa6752hs_probe(struct i2c_client *client,
 
 	v4l_info(client, "chip found @ 0x%x (%s)\n",
 			client->addr << 1, client->adapter->name);
+
+	h = devm_kzalloc(&client->dev, sizeof(*h), GFP_KERNEL);
 	if (h == NULL)
 		return -ENOMEM;
 	sd = &h->sd;
@@ -752,7 +754,6 @@ static int saa6752hs_probe(struct i2c_client *client,
 		int err = hdl->error;
 
 		v4l2_ctrl_handler_free(hdl);
-		kfree(h);
 		return err;
 	}
 	v4l2_ctrl_cluster(3, &h->video_bitrate_mode);
@@ -767,7 +768,6 @@ static int saa6752hs_remove(struct i2c_client *client)
 
 	v4l2_device_unregister_subdev(sd);
 	v4l2_ctrl_handler_free(&to_state(sd)->hdl);
-	kfree(to_state(sd));
 	return 0;
 }
 
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index 62acb10630f9..932ed9be9ff3 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -31,8 +31,9 @@
 #include <linux/device.h>
 #include <linux/gpio.h>
 #include <linux/module.h>
-#include <linux/slab.h>
 #include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+#include <linux/smiapp.h>
 #include <linux/v4l2-mediabus.h>
 #include <media/v4l2-device.h>
 
@@ -297,8 +298,9 @@ static int smiapp_pll_update(struct smiapp_sensor *sensor)
 	if (rval < 0)
 		return rval;
 
-	*sensor->pixel_rate_parray->p_cur.p_s64 = pll->vt_pix_clk_freq_hz;
-	*sensor->pixel_rate_csi->p_cur.p_s64 = pll->pixel_rate_csi;
+	__v4l2_ctrl_s_ctrl_int64(sensor->pixel_rate_parray,
+				 pll->vt_pix_clk_freq_hz);
+	__v4l2_ctrl_s_ctrl_int64(sensor->pixel_rate_csi, pll->pixel_rate_csi);
 
 	return 0;
 }
@@ -319,13 +321,7 @@ static void __smiapp_update_exposure_limits(struct smiapp_sensor *sensor)
 		+ sensor->vblank->val
 		- sensor->limits[SMIAPP_LIMIT_COARSE_INTEGRATION_TIME_MAX_MARGIN];
 
-	ctrl->maximum = max;
-	if (ctrl->default_value > max)
-		ctrl->default_value = max;
-	if (ctrl->val > max)
-		ctrl->val = max;
-	if (ctrl->cur.val > max)
-		ctrl->cur.val = max;
+	__v4l2_ctrl_modify_range(ctrl, ctrl->minimum, max, ctrl->step, max);
 }
 
 /*
@@ -404,6 +400,14 @@ static void smiapp_update_mbus_formats(struct smiapp_sensor *sensor)
 		pixel_order_str[pixel_order]);
 }
 
+static const char * const smiapp_test_patterns[] = {
+	"Disabled",
+	"Solid Colour",
+	"Eight Vertical Colour Bars",
+	"Colour Bars With Fade to Grey",
+	"Pseudorandom Sequence (PN9)",
+};
+
 static int smiapp_set_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct smiapp_sensor *sensor =
@@ -477,6 +481,39 @@ static int smiapp_set_ctrl(struct v4l2_ctrl *ctrl)
 
 		return smiapp_pll_update(sensor);
 
+	case V4L2_CID_TEST_PATTERN: {
+		unsigned int i;
+
+		for (i = 0; i < ARRAY_SIZE(sensor->test_data); i++)
+			v4l2_ctrl_activate(
+				sensor->test_data[i],
+				ctrl->val ==
+				V4L2_SMIAPP_TEST_PATTERN_MODE_SOLID_COLOUR);
+
+		return smiapp_write(
+			sensor, SMIAPP_REG_U16_TEST_PATTERN_MODE, ctrl->val);
+	}
+
+	case V4L2_CID_TEST_PATTERN_RED:
+		return smiapp_write(
+			sensor, SMIAPP_REG_U16_TEST_DATA_RED, ctrl->val);
+
+	case V4L2_CID_TEST_PATTERN_GREENR:
+		return smiapp_write(
+			sensor, SMIAPP_REG_U16_TEST_DATA_GREENR, ctrl->val);
+
+	case V4L2_CID_TEST_PATTERN_BLUE:
+		return smiapp_write(
+			sensor, SMIAPP_REG_U16_TEST_DATA_BLUE, ctrl->val);
+
+	case V4L2_CID_TEST_PATTERN_GREENB:
+		return smiapp_write(
+			sensor, SMIAPP_REG_U16_TEST_DATA_GREENB, ctrl->val);
+
+	case V4L2_CID_PIXEL_RATE:
+		/* For v4l2_ctrl_s_ctrl_int64() used internally. */
+		return 0;
+
 	default:
 		return -EINVAL;
 	}
@@ -489,10 +526,10 @@ static const struct v4l2_ctrl_ops smiapp_ctrl_ops = {
 static int smiapp_init_controls(struct smiapp_sensor *sensor)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(&sensor->src->sd);
-	unsigned int max;
+	unsigned int max, i;
 	int rval;
 
-	rval = v4l2_ctrl_handler_init(&sensor->pixel_array->ctrl_handler, 7);
+	rval = v4l2_ctrl_handler_init(&sensor->pixel_array->ctrl_handler, 12);
 	if (rval)
 		return rval;
 	sensor->pixel_array->ctrl_handler.lock = &sensor->mutex;
@@ -535,6 +572,20 @@ static int smiapp_init_controls(struct smiapp_sensor *sensor)
 		&sensor->pixel_array->ctrl_handler, &smiapp_ctrl_ops,
 		V4L2_CID_PIXEL_RATE, 1, INT_MAX, 1, 1);
 
+	v4l2_ctrl_new_std_menu_items(&sensor->pixel_array->ctrl_handler,
+				     &smiapp_ctrl_ops, V4L2_CID_TEST_PATTERN,
+				     ARRAY_SIZE(smiapp_test_patterns) - 1,
+				     0, 0, smiapp_test_patterns);
+
+	for (i = 0; i < ARRAY_SIZE(sensor->test_data); i++) {
+		int max_value = (1 << sensor->csi_format->width) - 1;
+		sensor->test_data[i] =
+			v4l2_ctrl_new_std(
+				&sensor->pixel_array->ctrl_handler,
+				&smiapp_ctrl_ops, V4L2_CID_TEST_PATTERN_RED + i,
+				0, max_value, 1, max_value);
+	}
+
 	if (sensor->pixel_array->ctrl_handler.error) {
 		dev_err(&client->dev,
 			"pixel array controls initialization failed (%d)\n",
@@ -782,36 +833,25 @@ static void smiapp_update_blanking(struct smiapp_sensor *sensor)
 {
 	struct v4l2_ctrl *vblank = sensor->vblank;
 	struct v4l2_ctrl *hblank = sensor->hblank;
+	int min, max;
 
-	vblank->minimum =
-		max_t(int,
-		      sensor->limits[SMIAPP_LIMIT_MIN_FRAME_BLANKING_LINES],
-		      sensor->limits[SMIAPP_LIMIT_MIN_FRAME_LENGTH_LINES_BIN] -
-		      sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].height);
-	vblank->maximum =
-		sensor->limits[SMIAPP_LIMIT_MAX_FRAME_LENGTH_LINES_BIN] -
+	min = max_t(int,
+		    sensor->limits[SMIAPP_LIMIT_MIN_FRAME_BLANKING_LINES],
+		    sensor->limits[SMIAPP_LIMIT_MIN_FRAME_LENGTH_LINES_BIN] -
+		    sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].height);
+	max = sensor->limits[SMIAPP_LIMIT_MAX_FRAME_LENGTH_LINES_BIN] -
 		sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].height;
 
-	vblank->val = clamp_t(int, vblank->val,
-			      vblank->minimum, vblank->maximum);
-	vblank->default_value = vblank->minimum;
-	vblank->val = vblank->val;
-	vblank->cur.val = vblank->val;
-
-	hblank->minimum =
-		max_t(int,
-		      sensor->limits[SMIAPP_LIMIT_MIN_LINE_LENGTH_PCK_BIN] -
-		      sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].width,
-		      sensor->limits[SMIAPP_LIMIT_MIN_LINE_BLANKING_PCK_BIN]);
-	hblank->maximum =
-		sensor->limits[SMIAPP_LIMIT_MAX_LINE_LENGTH_PCK_BIN] -
+	__v4l2_ctrl_modify_range(vblank, min, max, vblank->step, min);
+
+	min = max_t(int,
+		    sensor->limits[SMIAPP_LIMIT_MIN_LINE_LENGTH_PCK_BIN] -
+		    sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].width,
+		    sensor->limits[SMIAPP_LIMIT_MIN_LINE_BLANKING_PCK_BIN]);
+	max = sensor->limits[SMIAPP_LIMIT_MAX_LINE_LENGTH_PCK_BIN] -
 		sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].width;
 
-	hblank->val = clamp_t(int, hblank->val,
-			      hblank->minimum, hblank->maximum);
-	hblank->default_value = hblank->minimum;
-	hblank->val = hblank->val;
-	hblank->cur.val = hblank->val;
+	__v4l2_ctrl_modify_range(hblank, min, max, hblank->step, min);
 
 	__smiapp_update_exposure_limits(sensor);
 }
@@ -1272,7 +1312,7 @@ static void smiapp_power_off(struct smiapp_sensor *sensor)
 		clk_disable_unprepare(sensor->ext_clk);
 	usleep_range(5000, 5000);
 	regulator_disable(sensor->vana);
-	sensor->streaming = 0;
+	sensor->streaming = false;
 }
 
 static int smiapp_set_power(struct v4l2_subdev *subdev, int on)
@@ -1462,13 +1502,13 @@ static int smiapp_set_stream(struct v4l2_subdev *subdev, int enable)
 		return 0;
 
 	if (enable) {
-		sensor->streaming = 1;
+		sensor->streaming = true;
 		rval = smiapp_start_streaming(sensor);
 		if (rval < 0)
-			sensor->streaming = 0;
+			sensor->streaming = false;
 	} else {
 		rval = smiapp_stop_streaming(sensor);
-		sensor->streaming = 0;
+		sensor->streaming = false;
 	}
 
 	return rval;
@@ -1664,17 +1704,34 @@ static int smiapp_set_format(struct v4l2_subdev *subdev,
 	if (fmt->pad == ssd->source_pad) {
 		u32 code = fmt->format.code;
 		int rval = __smiapp_get_format(subdev, fh, fmt);
+		bool range_changed = false;
+		unsigned int i;
 
 		if (!rval && subdev == &sensor->src->sd) {
 			const struct smiapp_csi_data_format *csi_format =
 				smiapp_validate_csi_data_format(sensor, code);
-			if (fmt->which == V4L2_SUBDEV_FORMAT_ACTIVE)
+
+			if (fmt->which == V4L2_SUBDEV_FORMAT_ACTIVE) {
+				if (csi_format->width !=
+				    sensor->csi_format->width)
+					range_changed = true;
+
 				sensor->csi_format = csi_format;
+			}
+
 			fmt->format.code = csi_format->code;
 		}
 
 		mutex_unlock(&sensor->mutex);
-		return rval;
+		if (rval || !range_changed)
+			return rval;
+
+		for (i = 0; i < ARRAY_SIZE(sensor->test_data); i++)
+			v4l2_ctrl_modify_range(
+				sensor->test_data[i],
+				0, (1 << sensor->csi_format->width) - 1, 1, 0);
+
+		return 0;
 	}
 
 	/* Sink pad. Width and height are changeable here. */
diff --git a/drivers/media/i2c/smiapp/smiapp.h b/drivers/media/i2c/smiapp/smiapp.h
index 7cc5aae662fd..874b49ffd88f 100644
--- a/drivers/media/i2c/smiapp/smiapp.h
+++ b/drivers/media/i2c/smiapp/smiapp.h
@@ -54,6 +54,8 @@
 	(1000 +	(SMIAPP_RESET_DELAY_CLOCKS * 1000	\
 		 + (clk) / 1000 - 1) / ((clk) / 1000))
 
+#define SMIAPP_COLOUR_COMPONENTS	4
+
 #include "smiapp-limits.h"
 
 struct smiapp_quirk;
@@ -241,6 +243,8 @@ struct smiapp_sensor {
 	/* src controls */
 	struct v4l2_ctrl *link_freq;
 	struct v4l2_ctrl *pixel_rate_csi;
+	/* test pattern colour components */
+	struct v4l2_ctrl *test_data[SMIAPP_COLOUR_COMPONENTS];
 };
 
 #define to_smiapp_subdev(_sd)				\
diff --git a/drivers/media/i2c/soc_camera/mt9t112.c b/drivers/media/i2c/soc_camera/mt9t112.c
index 46f431a13782..996d7b4007a5 100644
--- a/drivers/media/i2c/soc_camera/mt9t112.c
+++ b/drivers/media/i2c/soc_camera/mt9t112.c
@@ -29,6 +29,7 @@
 #include <media/soc_camera.h>
 #include <media/v4l2-clk.h>
 #include <media/v4l2-common.h>
+#include <media/v4l2-image-sizes.h>
 
 /* you can check PLL/clock info */
 /* #define EXT_CLOCK 24000000 */
@@ -42,9 +43,6 @@
 #define MAX_WIDTH   2048
 #define MAX_HEIGHT  1536
 
-#define VGA_WIDTH   640
-#define VGA_HEIGHT  480
-
 /*
  * macro of read/write
  */
diff --git a/drivers/media/i2c/soc_camera/ov772x.c b/drivers/media/i2c/soc_camera/ov772x.c
index 7f2b3c8926af..970a04e1e56e 100644
--- a/drivers/media/i2c/soc_camera/ov772x.c
+++ b/drivers/media/i2c/soc_camera/ov772x.c
@@ -29,6 +29,7 @@
 #include <media/v4l2-clk.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-subdev.h>
+#include <media/v4l2-image-sizes.h>
 
 /*
  * register offset
@@ -360,10 +361,6 @@
 #define SCAL0_ACTRL     0x08 /* Auto scaling factor control */
 #define SCAL1_2_ACTRL   0x04 /* Auto scaling factor control */
 
-#define VGA_WIDTH		640
-#define VGA_HEIGHT		480
-#define QVGA_WIDTH		320
-#define QVGA_HEIGHT		240
 #define OV772X_MAX_WIDTH	VGA_WIDTH
 #define OV772X_MAX_HEIGHT	VGA_HEIGHT
 
diff --git a/drivers/media/i2c/soc_camera/ov9740.c b/drivers/media/i2c/soc_camera/ov9740.c
index ea76863dfdb4..ee9eb635d540 100644
--- a/drivers/media/i2c/soc_camera/ov9740.c
+++ b/drivers/media/i2c/soc_camera/ov9740.c
@@ -564,13 +564,13 @@ static int ov9740_set_res(struct i2c_client *client, u32 width, u32 height)
 	u32 y_start;
 	u32 x_end;
 	u32 y_end;
-	bool scaling = 0;
+	bool scaling = false;
 	u32 scale_input_x;
 	u32 scale_input_y;
 	int ret;
 
 	if ((width != OV9740_MAX_WIDTH) || (height != OV9740_MAX_HEIGHT))
-		scaling = 1;
+		scaling = true;
 
 	/*
 	 * Try to use as much of the sensor area as possible when supporting
diff --git a/drivers/media/i2c/tda7432.c b/drivers/media/i2c/tda7432.c
index 72af644fa051..cf93021a6500 100644
--- a/drivers/media/i2c/tda7432.c
+++ b/drivers/media/i2c/tda7432.c
@@ -293,7 +293,7 @@ static int tda7432_s_ctrl(struct v4l2_ctrl *ctrl)
 		if (t->mute->val) {
 			lf |= TDA7432_MUTE;
 			lr |= TDA7432_MUTE;
-			lf |= TDA7432_MUTE;
+			rf |= TDA7432_MUTE;
 			rr |= TDA7432_MUTE;
 		}
 		/* Mute & update balance*/
diff --git a/drivers/media/i2c/tvp7002.c b/drivers/media/i2c/tvp7002.c
index 11f2387e1dab..51bac762638b 100644
--- a/drivers/media/i2c/tvp7002.c
+++ b/drivers/media/i2c/tvp7002.c
@@ -775,25 +775,20 @@ static int tvp7002_enum_mbus_fmt(struct v4l2_subdev *sd, unsigned index,
 static int tvp7002_s_stream(struct v4l2_subdev *sd, int enable)
 {
 	struct tvp7002 *device = to_tvp7002(sd);
-	int error = 0;
+	int error;
 
 	if (device->streaming == enable)
 		return 0;
 
-	if (enable) {
-		/* Set output state on (low impedance means stream on) */
-		error = tvp7002_write(sd, TVP7002_MISC_CTL_2, 0x00);
-		device->streaming = enable;
-	} else {
-		/* Set output state off (high impedance means stream off) */
-		error = tvp7002_write(sd, TVP7002_MISC_CTL_2, 0x03);
-		if (error)
-			v4l2_dbg(1, debug, sd, "Unable to stop streaming\n");
-
-		device->streaming = enable;
+	/* low impedance: on, high impedance: off */
+	error = tvp7002_write(sd, TVP7002_MISC_CTL_2, enable ? 0x00 : 0x03);
+	if (error) {
+		v4l2_dbg(1, debug, sd, "Fail to set streaming\n");
+		return error;
 	}
 
-	return error;
+	device->streaming = enable;
+	return 0;
 }
 
 /*
diff --git a/drivers/media/i2c/vs6624.c b/drivers/media/i2c/vs6624.c
index 23f4f65fccd7..373f2df52492 100644
--- a/drivers/media/i2c/vs6624.c
+++ b/drivers/media/i2c/vs6624.c
@@ -30,22 +30,10 @@
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-mediabus.h>
+#include <media/v4l2-image-sizes.h>
 
 #include "vs6624_regs.h"
 
-#define VGA_WIDTH       640
-#define VGA_HEIGHT      480
-#define QVGA_WIDTH      320
-#define QVGA_HEIGHT     240
-#define QQVGA_WIDTH     160
-#define QQVGA_HEIGHT    120
-#define CIF_WIDTH       352
-#define CIF_HEIGHT      288
-#define QCIF_WIDTH      176
-#define QCIF_HEIGHT     144
-#define QQCIF_WIDTH     88
-#define QQCIF_HEIGHT    72
-
 #define MAX_FRAME_RATE  30
 
 struct vs6624 {
diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index 73a432934bd8..7b39440192d6 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -103,10 +103,8 @@ static long media_device_enum_entities(struct media_device *mdev,
 		return -EINVAL;
 
 	u_ent.id = ent->id;
-	if (ent->name) {
-		strncpy(u_ent.name, ent->name, sizeof(u_ent.name));
-		u_ent.name[sizeof(u_ent.name) - 1] = '\0';
-	}
+	if (ent->name)
+		strlcpy(u_ent.name, ent->name, sizeof(u_ent.name));
 	u_ent.type = ent->type;
 	u_ent.revision = ent->revision;
 	u_ent.flags = ent->flags;
diff --git a/drivers/media/media-devnode.c b/drivers/media/media-devnode.c
index 7acd19c881de..ebf9626e5ae5 100644
--- a/drivers/media/media-devnode.c
+++ b/drivers/media/media-devnode.c
@@ -192,7 +192,6 @@ static int media_open(struct inode *inode, struct file *filp)
 static int media_release(struct inode *inode, struct file *filp)
 {
 	struct media_devnode *mdev = media_devnode_data(filp);
-	int ret = 0;
 
 	if (mdev->fops->release)
 		mdev->fops->release(filp);
@@ -201,7 +200,7 @@ static int media_release(struct inode *inode, struct file *filp)
 	   return value is ignored. */
 	put_device(&mdev->dev);
 	filp->private_data = NULL;
-	return ret;
+	return 0;
 }
 
 static const struct file_operations media_devnode_fops = {
diff --git a/drivers/media/parport/pms.c b/drivers/media/parport/pms.c
index 9bc105b3db1b..e6b497528cea 100644
--- a/drivers/media/parport/pms.c
+++ b/drivers/media/parport/pms.c
@@ -629,11 +629,15 @@ static int pms_capture(struct pms *dev, char __user *buf, int rgb555, int count)
 {
 	int y;
 	int dw = 2 * dev->width;
-	char tmp[dw + 32]; /* using a temp buffer is faster than direct  */
+	char *tmp; /* using a temp buffer is faster than direct  */
 	int cnt = 0;
 	int len = 0;
 	unsigned char r8 = 0x5;  /* value for reg8  */
 
+	tmp = kmalloc(dw + 32, GFP_KERNEL);
+	if (!tmp)
+		return 0;
+
 	if (rgb555)
 		r8 |= 0x20; /* else use untranslated rgb = 565 */
 	mvv_write(dev, 0x08, r8); /* capture rgb555/565, init DRAM, PC enable */
@@ -664,6 +668,7 @@ static int pms_capture(struct pms *dev, char __user *buf, int rgb555, int count)
 			len += dt;
 		}
 	}
+	kfree(tmp);
 	return len;
 }
 
diff --git a/drivers/media/pci/Kconfig b/drivers/media/pci/Kconfig
index 5c16c9c2203e..f8cec8e8cf82 100644
--- a/drivers/media/pci/Kconfig
+++ b/drivers/media/pci/Kconfig
@@ -20,6 +20,7 @@ source "drivers/media/pci/ivtv/Kconfig"
 source "drivers/media/pci/zoran/Kconfig"
 source "drivers/media/pci/saa7146/Kconfig"
 source "drivers/media/pci/solo6x10/Kconfig"
+source "drivers/media/pci/tw68/Kconfig"
 endif
 
 if MEDIA_ANALOG_TV_SUPPORT || MEDIA_DIGITAL_TV_SUPPORT
@@ -41,6 +42,7 @@ source "drivers/media/pci/b2c2/Kconfig"
 source "drivers/media/pci/pluto2/Kconfig"
 source "drivers/media/pci/dm1105/Kconfig"
 source "drivers/media/pci/pt1/Kconfig"
+source "drivers/media/pci/pt3/Kconfig"
 source "drivers/media/pci/mantis/Kconfig"
 source "drivers/media/pci/ngene/Kconfig"
 source "drivers/media/pci/ddbridge/Kconfig"
diff --git a/drivers/media/pci/Makefile b/drivers/media/pci/Makefile
index e5b53fb569ef..a12926e4b51f 100644
--- a/drivers/media/pci/Makefile
+++ b/drivers/media/pci/Makefile
@@ -7,10 +7,10 @@ obj-y        +=	ttpci/		\
 		pluto2/		\
 		dm1105/		\
 		pt1/		\
+		pt3/		\
 		mantis/		\
 		ngene/		\
 		ddbridge/	\
-		b2c2/		\
 		saa7146/
 
 obj-$(CONFIG_VIDEO_IVTV) += ivtv/
@@ -22,6 +22,7 @@ obj-$(CONFIG_VIDEO_CX88) += cx88/
 obj-$(CONFIG_VIDEO_BT848) += bt8xx/
 obj-$(CONFIG_VIDEO_SAA7134) += saa7134/
 obj-$(CONFIG_VIDEO_SAA7164) += saa7164/
+obj-$(CONFIG_VIDEO_TW68) += tw68/
 obj-$(CONFIG_VIDEO_MEYE) += meye/
 obj-$(CONFIG_STA2X11_VIP) += sta2x11/
 obj-$(CONFIG_VIDEO_SOLO6X10) += solo6x10/
diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index 970e542d3a51..4a8176c09fc9 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -1531,7 +1531,6 @@ bttv_switch_overlay(struct bttv *btv, struct bttv_fh *fh,
 {
 	struct bttv_buffer *old;
 	unsigned long flags;
-	int retval = 0;
 
 	dprintk("switch_overlay: enter [new=%p]\n", new);
 	if (new)
@@ -1551,7 +1550,7 @@ bttv_switch_overlay(struct bttv *btv, struct bttv_fh *fh,
 	if (NULL == new)
 		free_btres_lock(btv,fh,RESOURCE_OVERLAY);
 	dprintk("switch_overlay: done\n");
-	return retval;
+	return 0;
 }
 
 /* ----------------------------------------------------------------------- */
@@ -3856,7 +3855,7 @@ static irqreturn_t bttv_irq(int irq, void *dev_id)
 
 				btwrite(btread(BT848_INT_MASK) & (-1 ^ BT848_INT_GPINT),
 						BT848_INT_MASK);
-			};
+			}
 
 			bttv_print_irqbits(stat,astat);
 
diff --git a/drivers/media/pci/bt8xx/dst_ca.c b/drivers/media/pci/bt8xx/dst_ca.c
index 0e788fca992c..c22c4ae06844 100644
--- a/drivers/media/pci/bt8xx/dst_ca.c
+++ b/drivers/media/pci/bt8xx/dst_ca.c
@@ -674,11 +674,9 @@ static int dst_ca_release(struct inode *inode, struct file *file)
 
 static ssize_t dst_ca_read(struct file *file, char __user *buffer, size_t length, loff_t *offset)
 {
-	ssize_t bytes_read = 0;
-
 	dprintk(verbose, DST_CA_DEBUG, 1, " Device read.");
 
-	return bytes_read;
+	return 0;
 }
 
 static ssize_t dst_ca_write(struct file *file, const char __user *buffer, size_t length, loff_t *offset)
diff --git a/drivers/media/pci/cx18/cx18-alsa-pcm.c b/drivers/media/pci/cx18/cx18-alsa-pcm.c
index 180077c49123..ffb6acdc575f 100644
--- a/drivers/media/pci/cx18/cx18-alsa-pcm.c
+++ b/drivers/media/pci/cx18/cx18-alsa-pcm.c
@@ -80,7 +80,7 @@ void cx18_alsa_announce_pcm_data(struct snd_cx18_card *cxsc, u8 *pcm_data,
 	int period_elapsed = 0;
 	int length;
 
-	dprintk("cx18 alsa announce ptr=%p data=%p num_bytes=%zd\n", cxsc,
+	dprintk("cx18 alsa announce ptr=%p data=%p num_bytes=%zu\n", cxsc,
 		pcm_data, num_bytes);
 
 	substream = cxsc->capture_pcm_substream;
diff --git a/drivers/media/pci/cx18/cx18-firmware.c b/drivers/media/pci/cx18/cx18-firmware.c
index a1c1cec05f98..c6c83445f8bf 100644
--- a/drivers/media/pci/cx18/cx18-firmware.c
+++ b/drivers/media/pci/cx18/cx18-firmware.c
@@ -130,7 +130,7 @@ static int load_cpu_fw_direct(const char *fn, u8 __iomem *mem, struct cx18 *cx)
 		}
 	}
 	if (!test_bit(CX18_F_I_LOADED_FW, &cx->i_flags))
-		CX18_INFO("loaded %s firmware (%zd bytes)\n", fn, fw->size);
+		CX18_INFO("loaded %s firmware (%zu bytes)\n", fn, fw->size);
 	size = fw->size;
 	release_firmware(fw);
 	cx18_setup_page(cx, SCB_OFFSET);
@@ -164,7 +164,7 @@ static int load_apu_fw_direct(const char *fn, u8 __iomem *dst, struct cx18 *cx,
 
 	apu_version = (vers[0] << 24) | (vers[4] << 16) | vers[32];
 	while (offset + sizeof(seghdr) < fw->size) {
-		const u32 *shptr = src + offset / 4;
+		const __le32 *shptr = (__force __le32 *)src + offset / 4;
 
 		seghdr.sync1 = le32_to_cpu(shptr[0]);
 		seghdr.sync2 = le32_to_cpu(shptr[1]);
@@ -202,7 +202,7 @@ static int load_apu_fw_direct(const char *fn, u8 __iomem *dst, struct cx18 *cx,
 		offset += seghdr.size;
 	}
 	if (!test_bit(CX18_F_I_LOADED_FW, &cx->i_flags))
-		CX18_INFO("loaded %s firmware V%08x (%zd bytes)\n",
+		CX18_INFO("loaded %s firmware V%08x (%zu bytes)\n",
 				fn, apu_version, fw->size);
 	size = fw->size;
 	release_firmware(fw);
diff --git a/drivers/media/pci/cx18/cx18-queue.c b/drivers/media/pci/cx18/cx18-queue.c
index 8884537bd62f..2a247d264b87 100644
--- a/drivers/media/pci/cx18/cx18-queue.c
+++ b/drivers/media/pci/cx18/cx18-queue.c
@@ -364,7 +364,7 @@ int cx18_stream_alloc(struct cx18_stream *s)
 					((char __iomem *)cx->scb->cpu_mdl));
 
 		CX18_ERR("Too many buffers, cannot fit in SCB area\n");
-		CX18_ERR("Max buffers = %zd\n",
+		CX18_ERR("Max buffers = %zu\n",
 			bufsz / sizeof(struct cx18_mdl_ent));
 		return -ENOMEM;
 	}
diff --git a/drivers/media/pci/cx23885/Kconfig b/drivers/media/pci/cx23885/Kconfig
index e12c006e6e2d..f613314b360b 100644
--- a/drivers/media/pci/cx23885/Kconfig
+++ b/drivers/media/pci/cx23885/Kconfig
@@ -3,12 +3,11 @@ config VIDEO_CX23885
 	depends on DVB_CORE && VIDEO_DEV && PCI && I2C && INPUT && SND
 	select SND_PCM
 	select I2C_ALGOBIT
-	select VIDEO_BTCX
 	select VIDEO_TUNER
 	select VIDEO_TVEEPROM
 	depends on RC_CORE
-	select VIDEOBUF_DVB
-	select VIDEOBUF_DMA_SG
+	select VIDEOBUF2_DVB
+	select VIDEOBUF2_DMA_SG
 	select VIDEO_CX25840
 	select VIDEO_CX2341X
 	select DVB_DIB7000P if MEDIA_SUBDRV_AUTOSELECT
@@ -32,12 +31,16 @@ config VIDEO_CX23885
 	select DVB_A8293 if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_MB86A20S if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_SI2165 if MEDIA_SUBDRV_AUTOSELECT
+	select DVB_SI2168 if MEDIA_SUBDRV_AUTOSELECT
+	select DVB_M88DS3103 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_MT2063 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_MT2131 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_XC2028 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_TDA8290 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_TDA18271 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_XC5000 if MEDIA_SUBDRV_AUTOSELECT
+	select MEDIA_TUNER_SI2157 if MEDIA_SUBDRV_AUTOSELECT
+	select MEDIA_TUNER_M88TS2022 if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_TUNER_DIB0070 if MEDIA_SUBDRV_AUTOSELECT
 	---help---
 	  This is a video4linux driver for Conexant 23885 based
diff --git a/drivers/media/pci/cx23885/Makefile b/drivers/media/pci/cx23885/Makefile
index 2a2cafb8cf5b..a2cbdcf15a8c 100644
--- a/drivers/media/pci/cx23885/Makefile
+++ b/drivers/media/pci/cx23885/Makefile
@@ -8,7 +8,6 @@ obj-$(CONFIG_VIDEO_CX23885) += cx23885.o
 obj-$(CONFIG_MEDIA_ALTERA_CI) += altera-ci.o
 
 ccflags-y += -Idrivers/media/i2c
-ccflags-y += -Idrivers/media/common
 ccflags-y += -Idrivers/media/tuners
 ccflags-y += -Idrivers/media/dvb-core
 ccflags-y += -Idrivers/media/dvb-frontends
diff --git a/drivers/media/pci/cx23885/altera-ci.c b/drivers/media/pci/cx23885/altera-ci.c
index 2926f7fadccd..2bbbf545b042 100644
--- a/drivers/media/pci/cx23885/altera-ci.c
+++ b/drivers/media/pci/cx23885/altera-ci.c
@@ -16,10 +16,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 /*
@@ -52,8 +48,8 @@
  * |  DATA7|  DATA6|  DATA5|  DATA4|  DATA3|  DATA2|  DATA1|  DATA0|
  * +-------+-------+-------+-------+-------+-------+-------+-------+
  */
-#include <media/videobuf-dma-sg.h>
-#include <media/videobuf-dvb.h>
+#include <dvb_demux.h>
+#include <dvb_frontend.h>
 #include "altera-ci.h"
 #include "dvb_ca_en50221.h"
 
diff --git a/drivers/media/pci/cx23885/altera-ci.h b/drivers/media/pci/cx23885/altera-ci.h
index 4998c96caebe..5028f0cf83f4 100644
--- a/drivers/media/pci/cx23885/altera-ci.h
+++ b/drivers/media/pci/cx23885/altera-ci.h
@@ -16,10 +16,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #ifndef __ALTERA_CI_H
 #define __ALTERA_CI_H
diff --git a/drivers/media/pci/cx23885/cimax2.c b/drivers/media/pci/cx23885/cimax2.c
index 16fa7ea4d4aa..631e4f24aea6 100644
--- a/drivers/media/pci/cx23885/cimax2.c
+++ b/drivers/media/pci/cx23885/cimax2.c
@@ -17,10 +17,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include "cx23885.h"
diff --git a/drivers/media/pci/cx23885/cimax2.h b/drivers/media/pci/cx23885/cimax2.h
index 518744a4c8a5..565e958f6f8d 100644
--- a/drivers/media/pci/cx23885/cimax2.h
+++ b/drivers/media/pci/cx23885/cimax2.h
@@ -17,10 +17,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef CIMAX2_H
diff --git a/drivers/media/pci/cx23885/cx23885-417.c b/drivers/media/pci/cx23885/cx23885-417.c
index bf89fc88692e..3948db386fb5 100644
--- a/drivers/media/pci/cx23885/cx23885-417.c
+++ b/drivers/media/pci/cx23885/cx23885-417.c
@@ -18,10 +18,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/module.h>
@@ -865,6 +861,11 @@ static int cx23885_api_cmd(struct cx23885_dev *dev,
 	return err;
 }
 
+static int cx23885_api_func(void *priv, u32 cmd, int in, int out, u32 data[CX2341X_MBOX_MAX_DATA])
+{
+	return cx23885_mbox_func(priv, cmd, in, out, data);
+}
+
 static int cx23885_find_mailbox(struct cx23885_dev *dev)
 {
 	u32 signature[4] = {
@@ -941,7 +942,7 @@ static int cx23885_load_firmware(struct cx23885_dev *dev)
 
 	if (firmware->size != CX23885_FIRM_IMAGE_SIZE) {
 		printk(KERN_ERR "ERROR: Firmware size mismatch "
-			"(have %zd, expected %d)\n",
+			"(have %zu, expected %d)\n",
 			firmware->size, CX23885_FIRM_IMAGE_SIZE);
 		release_firmware(firmware);
 		return -1;
@@ -1033,12 +1034,12 @@ static void cx23885_codec_settings(struct cx23885_dev *dev)
 	cx23885_api_cmd(dev, CX2341X_ENC_SET_FRAME_SIZE, 2, 0,
 				dev->ts1.height, dev->ts1.width);
 
-	dev->mpeg_params.width = dev->ts1.width;
-	dev->mpeg_params.height = dev->ts1.height;
-	dev->mpeg_params.is_50hz =
+	dev->cxhdl.width = dev->ts1.width;
+	dev->cxhdl.height = dev->ts1.height;
+	dev->cxhdl.is_50hz =
 		(dev->encodernorm.id & V4L2_STD_625_50) != 0;
 
-	cx2341x_update(dev, cx23885_mbox_func, NULL, &dev->mpeg_params);
+	cx2341x_handler_setup(&dev->cxhdl);
 
 	cx23885_api_cmd(dev, CX2341X_ENC_MISC, 2, 0, 3, 1);
 	cx23885_api_cmd(dev, CX2341X_ENC_MISC, 2, 0, 4, 1);
@@ -1137,85 +1138,107 @@ static int cx23885_initialize_codec(struct cx23885_dev *dev, int startencoder)
 
 /* ------------------------------------------------------------------ */
 
-static int bb_buf_setup(struct videobuf_queue *q,
-	unsigned int *count, unsigned int *size)
+static int queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
+			   unsigned int *num_buffers, unsigned int *num_planes,
+			   unsigned int sizes[], void *alloc_ctxs[])
 {
-	struct cx23885_fh *fh = q->priv_data;
-
-	fh->dev->ts1.ts_packet_size  = mpeglinesize;
-	fh->dev->ts1.ts_packet_count = mpeglines;
-
-	*size = fh->dev->ts1.ts_packet_size * fh->dev->ts1.ts_packet_count;
-	*count = mpegbufs;
+	struct cx23885_dev *dev = q->drv_priv;
 
+	dev->ts1.ts_packet_size  = mpeglinesize;
+	dev->ts1.ts_packet_count = mpeglines;
+	*num_planes = 1;
+	sizes[0] = mpeglinesize * mpeglines;
+	*num_buffers = mpegbufs;
 	return 0;
 }
 
-static int bb_buf_prepare(struct videobuf_queue *q,
-	struct videobuf_buffer *vb, enum v4l2_field field)
+static int buffer_prepare(struct vb2_buffer *vb)
 {
-	struct cx23885_fh *fh = q->priv_data;
-	return cx23885_buf_prepare(q, &fh->dev->ts1,
-		(struct cx23885_buffer *)vb,
-		field);
+	struct cx23885_dev *dev = vb->vb2_queue->drv_priv;
+	struct cx23885_buffer *buf =
+		container_of(vb, struct cx23885_buffer, vb);
+
+	return cx23885_buf_prepare(buf, &dev->ts1);
 }
 
-static void bb_buf_queue(struct videobuf_queue *q,
-	struct videobuf_buffer *vb)
+static void buffer_finish(struct vb2_buffer *vb)
 {
-	struct cx23885_fh *fh = q->priv_data;
-	cx23885_buf_queue(&fh->dev->ts1, (struct cx23885_buffer *)vb);
+	struct cx23885_dev *dev = vb->vb2_queue->drv_priv;
+	struct cx23885_buffer *buf = container_of(vb,
+		struct cx23885_buffer, vb);
+	struct sg_table *sgt = vb2_dma_sg_plane_desc(vb, 0);
+
+	cx23885_free_buffer(dev, buf);
+
+	dma_unmap_sg(&dev->pci->dev, sgt->sgl, sgt->nents, DMA_FROM_DEVICE);
 }
 
-static void bb_buf_release(struct videobuf_queue *q,
-	struct videobuf_buffer *vb)
+static void buffer_queue(struct vb2_buffer *vb)
 {
-	cx23885_free_buffer(q, (struct cx23885_buffer *)vb);
-}
+	struct cx23885_dev *dev = vb->vb2_queue->drv_priv;
+	struct cx23885_buffer   *buf = container_of(vb,
+		struct cx23885_buffer, vb);
 
-static struct videobuf_queue_ops cx23885_qops = {
-	.buf_setup    = bb_buf_setup,
-	.buf_prepare  = bb_buf_prepare,
-	.buf_queue    = bb_buf_queue,
-	.buf_release  = bb_buf_release,
-};
+	cx23885_buf_queue(&dev->ts1, buf);
+}
 
-/* ------------------------------------------------------------------ */
+static int cx23885_start_streaming(struct vb2_queue *q, unsigned int count)
+{
+	struct cx23885_dev *dev = q->drv_priv;
+	struct cx23885_dmaqueue *dmaq = &dev->ts1.mpegq;
+	unsigned long flags;
+	int ret;
+
+	ret = cx23885_initialize_codec(dev, 1);
+	if (ret == 0) {
+		struct cx23885_buffer *buf = list_entry(dmaq->active.next,
+			struct cx23885_buffer, queue);
+
+		cx23885_start_dma(&dev->ts1, dmaq, buf);
+		return 0;
+	}
+	spin_lock_irqsave(&dev->slock, flags);
+	while (!list_empty(&dmaq->active)) {
+		struct cx23885_buffer *buf = list_entry(dmaq->active.next,
+			struct cx23885_buffer, queue);
 
-static const u32 *ctrl_classes[] = {
-	cx2341x_mpeg_ctrls,
-	NULL
-};
+		list_del(&buf->queue);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
+	}
+	spin_unlock_irqrestore(&dev->slock, flags);
+	return ret;
+}
 
-static int cx23885_queryctrl(struct cx23885_dev *dev,
-	struct v4l2_queryctrl *qctrl)
+static void cx23885_stop_streaming(struct vb2_queue *q)
 {
-	qctrl->id = v4l2_ctrl_next(ctrl_classes, qctrl->id);
-	if (qctrl->id == 0)
-		return -EINVAL;
+	struct cx23885_dev *dev = q->drv_priv;
 
-	/* MPEG V4L2 controls */
-	if (cx2341x_ctrl_query(&dev->mpeg_params, qctrl))
-		qctrl->flags |= V4L2_CTRL_FLAG_DISABLED;
+	/* stop mpeg capture */
+	cx23885_api_cmd(dev, CX2341X_ENC_STOP_CAPTURE, 3, 0,
+			CX23885_END_NOW, CX23885_MPEG_CAPTURE,
+			CX23885_RAW_BITS_NONE);
 
-	return 0;
+	msleep(500);
+	cx23885_417_check_encoder(dev);
+	cx23885_cancel_buffers(&dev->ts1);
 }
 
-static int cx23885_querymenu(struct cx23885_dev *dev,
-	struct v4l2_querymenu *qmenu)
-{
-	struct v4l2_queryctrl qctrl;
+static struct vb2_ops cx23885_qops = {
+	.queue_setup    = queue_setup,
+	.buf_prepare  = buffer_prepare,
+	.buf_finish = buffer_finish,
+	.buf_queue    = buffer_queue,
+	.wait_prepare = vb2_ops_wait_prepare,
+	.wait_finish = vb2_ops_wait_finish,
+	.start_streaming = cx23885_start_streaming,
+	.stop_streaming = cx23885_stop_streaming,
+};
 
-	qctrl.id = qmenu->id;
-	cx23885_queryctrl(dev, &qctrl);
-	return v4l2_ctrl_query_menu(qmenu, &qctrl,
-		cx2341x_ctrl_get_menu(&dev->mpeg_params, qmenu->id));
-}
+/* ------------------------------------------------------------------ */
 
 static int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *id)
 {
-	struct cx23885_fh  *fh  = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	*id = dev->tvnorm;
 	return 0;
@@ -1223,29 +1246,26 @@ static int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *id)
 
 static int vidioc_s_std(struct file *file, void *priv, v4l2_std_id id)
 {
-	struct cx23885_fh  *fh  = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 	unsigned int i;
+	int ret;
 
 	for (i = 0; i < ARRAY_SIZE(cx23885_tvnorms); i++)
 		if (id & cx23885_tvnorms[i].id)
 			break;
 	if (i == ARRAY_SIZE(cx23885_tvnorms))
 		return -EINVAL;
-	dev->encodernorm = cx23885_tvnorms[i];
 
-	/* Have the drier core notify the subdevices */
-	mutex_lock(&dev->lock);
-	cx23885_set_tvnorm(dev, id);
-	mutex_unlock(&dev->lock);
-
-	return 0;
+	ret = cx23885_set_tvnorm(dev, id);
+	if (!ret)
+		dev->encodernorm = cx23885_tvnorms[i];
+	return ret;
 }
 
 static int vidioc_enum_input(struct file *file, void *priv,
 	struct v4l2_input *i)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 	dprintk(1, "%s()\n", __func__);
 	return cx23885_enum_input(dev, i);
 }
@@ -1263,8 +1283,7 @@ static int vidioc_s_input(struct file *file, void *priv, unsigned int i)
 static int vidioc_g_tuner(struct file *file, void *priv,
 				struct v4l2_tuner *t)
 {
-	struct cx23885_fh  *fh  = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	if (dev->tuner_type == TUNER_ABSENT)
 		return -EINVAL;
@@ -1281,8 +1300,7 @@ static int vidioc_g_tuner(struct file *file, void *priv,
 static int vidioc_s_tuner(struct file *file, void *priv,
 				const struct v4l2_tuner *t)
 {
-	struct cx23885_fh  *fh  = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	if (dev->tuner_type == TUNER_ABSENT)
 		return -EINVAL;
@@ -1296,8 +1314,7 @@ static int vidioc_s_tuner(struct file *file, void *priv,
 static int vidioc_g_frequency(struct file *file, void *priv,
 				struct v4l2_frequency *f)
 {
-	struct cx23885_fh  *fh  = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	if (dev->tuner_type == TUNER_ABSENT)
 		return -EINVAL;
@@ -1315,27 +1332,10 @@ static int vidioc_s_frequency(struct file *file, void *priv,
 	return cx23885_set_frequency(file, priv, f);
 }
 
-static int vidioc_g_ctrl(struct file *file, void *priv,
-	struct v4l2_control *ctl)
-{
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
-
-	return cx23885_get_control(dev, ctl);
-}
-
-static int vidioc_s_ctrl(struct file *file, void *priv,
-	struct v4l2_control *ctl)
-{
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
-
-	return cx23885_set_control(dev, ctl);
-}
-
 static int vidioc_querycap(struct file *file, void  *priv,
 				struct v4l2_capability *cap)
 {
-	struct cx23885_fh  *fh  = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 	struct cx23885_tsport  *tsport = &dev->ts1;
 
 	strlcpy(cap->driver, dev->name, sizeof(cap->driver));
@@ -1368,8 +1368,7 @@ static int vidioc_enum_fmt_vid_cap(struct file *file, void  *priv,
 static int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
 				struct v4l2_format *f)
 {
-	struct cx23885_fh  *fh  = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	f->fmt.pix.pixelformat  = V4L2_PIX_FMT_MPEG;
 	f->fmt.pix.bytesperline = 0;
@@ -1378,285 +1377,63 @@ static int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
 	f->fmt.pix.colorspace   = 0;
 	f->fmt.pix.width        = dev->ts1.width;
 	f->fmt.pix.height       = dev->ts1.height;
-	f->fmt.pix.field        = fh->mpegq.field;
-	dprintk(1, "VIDIOC_G_FMT: w: %d, h: %d, f: %d\n",
-		dev->ts1.width, dev->ts1.height, fh->mpegq.field);
+	f->fmt.pix.field        = V4L2_FIELD_INTERLACED;
+	dprintk(1, "VIDIOC_G_FMT: w: %d, h: %d\n",
+		dev->ts1.width, dev->ts1.height);
 	return 0;
 }
 
 static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
 				struct v4l2_format *f)
 {
-	struct cx23885_fh  *fh  = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	f->fmt.pix.pixelformat  = V4L2_PIX_FMT_MPEG;
 	f->fmt.pix.bytesperline = 0;
 	f->fmt.pix.sizeimage    =
 		dev->ts1.ts_packet_size * dev->ts1.ts_packet_count;
 	f->fmt.pix.colorspace   = 0;
-	dprintk(1, "VIDIOC_TRY_FMT: w: %d, h: %d, f: %d\n",
-		dev->ts1.width, dev->ts1.height, fh->mpegq.field);
+	f->fmt.pix.field        = V4L2_FIELD_INTERLACED;
+	dprintk(1, "VIDIOC_TRY_FMT: w: %d, h: %d\n",
+		dev->ts1.width, dev->ts1.height);
 	return 0;
 }
 
 static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
 				struct v4l2_format *f)
 {
-	struct cx23885_fh  *fh  = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	f->fmt.pix.pixelformat  = V4L2_PIX_FMT_MPEG;
 	f->fmt.pix.bytesperline = 0;
 	f->fmt.pix.sizeimage    =
 		dev->ts1.ts_packet_size * dev->ts1.ts_packet_count;
 	f->fmt.pix.colorspace   = 0;
+	f->fmt.pix.field        = V4L2_FIELD_INTERLACED;
 	dprintk(1, "VIDIOC_S_FMT: w: %d, h: %d, f: %d\n",
 		f->fmt.pix.width, f->fmt.pix.height, f->fmt.pix.field);
 	return 0;
 }
 
-static int vidioc_reqbufs(struct file *file, void *priv,
-				struct v4l2_requestbuffers *p)
-{
-	struct cx23885_fh  *fh  = file->private_data;
-
-	return videobuf_reqbufs(&fh->mpegq, p);
-}
-
-static int vidioc_querybuf(struct file *file, void *priv,
-				struct v4l2_buffer *p)
-{
-	struct cx23885_fh  *fh  = file->private_data;
-
-	return videobuf_querybuf(&fh->mpegq, p);
-}
-
-static int vidioc_qbuf(struct file *file, void *priv,
-				struct v4l2_buffer *p)
-{
-	struct cx23885_fh  *fh  = file->private_data;
-
-	return videobuf_qbuf(&fh->mpegq, p);
-}
-
-static int vidioc_dqbuf(struct file *file, void *priv, struct v4l2_buffer *b)
-{
-	struct cx23885_fh  *fh  = priv;
-
-	return videobuf_dqbuf(&fh->mpegq, b, file->f_flags & O_NONBLOCK);
-}
-
-
-static int vidioc_streamon(struct file *file, void *priv,
-				enum v4l2_buf_type i)
-{
-	struct cx23885_fh  *fh  = file->private_data;
-
-	return videobuf_streamon(&fh->mpegq);
-}
-
-static int vidioc_streamoff(struct file *file, void *priv, enum v4l2_buf_type i)
-{
-	struct cx23885_fh  *fh  = file->private_data;
-
-	return videobuf_streamoff(&fh->mpegq);
-}
-
-static int vidioc_g_ext_ctrls(struct file *file, void *priv,
-				struct v4l2_ext_controls *f)
-{
-	struct cx23885_fh  *fh  = priv;
-	struct cx23885_dev *dev = fh->dev;
-
-	if (f->ctrl_class != V4L2_CTRL_CLASS_MPEG)
-		return -EINVAL;
-	return cx2341x_ext_ctrls(&dev->mpeg_params, 0, f, VIDIOC_G_EXT_CTRLS);
-}
-
-static int vidioc_s_ext_ctrls(struct file *file, void *priv,
-				struct v4l2_ext_controls *f)
-{
-	struct cx23885_fh  *fh  = priv;
-	struct cx23885_dev *dev = fh->dev;
-	struct cx2341x_mpeg_params p;
-	int err;
-
-	if (f->ctrl_class != V4L2_CTRL_CLASS_MPEG)
-		return -EINVAL;
-
-	p = dev->mpeg_params;
-	err = cx2341x_ext_ctrls(&p, 0, f, VIDIOC_S_EXT_CTRLS);
-
-	if (err == 0) {
-		err = cx2341x_update(dev, cx23885_mbox_func,
-			&dev->mpeg_params, &p);
-		dev->mpeg_params = p;
-	}
-	return err;
-}
-
-static int vidioc_try_ext_ctrls(struct file *file, void *priv,
-				struct v4l2_ext_controls *f)
-{
-	struct cx23885_fh  *fh  = priv;
-	struct cx23885_dev *dev = fh->dev;
-	struct cx2341x_mpeg_params p;
-	int err;
-
-	if (f->ctrl_class != V4L2_CTRL_CLASS_MPEG)
-		return -EINVAL;
-
-	p = dev->mpeg_params;
-	err = cx2341x_ext_ctrls(&p, 0, f, VIDIOC_TRY_EXT_CTRLS);
-	return err;
-}
-
 static int vidioc_log_status(struct file *file, void *priv)
 {
-	struct cx23885_fh  *fh  = priv;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 	char name[32 + 2];
 
 	snprintf(name, sizeof(name), "%s/2", dev->name);
-	printk(KERN_INFO
-		"%s/2: ============  START LOG STATUS  ============\n",
-	       dev->name);
 	call_all(dev, core, log_status);
-	cx2341x_log_status(&dev->mpeg_params, name);
-	printk(KERN_INFO
-		"%s/2: =============  END LOG STATUS  =============\n",
-	       dev->name);
+	v4l2_ctrl_handler_log_status(&dev->cxhdl.hdl, name);
 	return 0;
 }
 
-static int vidioc_querymenu(struct file *file, void *priv,
-				struct v4l2_querymenu *a)
-{
-	struct cx23885_fh  *fh  = priv;
-	struct cx23885_dev *dev = fh->dev;
-
-	return cx23885_querymenu(dev, a);
-}
-
-static int vidioc_queryctrl(struct file *file, void *priv,
-				struct v4l2_queryctrl *c)
-{
-	struct cx23885_fh  *fh  = priv;
-	struct cx23885_dev *dev = fh->dev;
-
-	return cx23885_queryctrl(dev, c);
-}
-
-static int mpeg_open(struct file *file)
-{
-	struct cx23885_dev *dev = video_drvdata(file);
-	struct cx23885_fh *fh;
-
-	dprintk(2, "%s()\n", __func__);
-
-	/* allocate + initialize per filehandle data */
-	fh = kzalloc(sizeof(*fh), GFP_KERNEL);
-	if (!fh)
-		return -ENOMEM;
-
-	file->private_data = fh;
-	fh->dev      = dev;
-
-	videobuf_queue_sg_init(&fh->mpegq, &cx23885_qops,
-			    &dev->pci->dev, &dev->ts1.slock,
-			    V4L2_BUF_TYPE_VIDEO_CAPTURE,
-			    V4L2_FIELD_INTERLACED,
-			    sizeof(struct cx23885_buffer),
-			    fh, NULL);
-	return 0;
-}
-
-static int mpeg_release(struct file *file)
-{
-	struct cx23885_fh  *fh  = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
-
-	dprintk(2, "%s()\n", __func__);
-
-	/* FIXME: Review this crap */
-	/* Shut device down on last close */
-	if (atomic_cmpxchg(&fh->v4l_reading, 1, 0) == 1) {
-		if (atomic_dec_return(&dev->v4l_reader_count) == 0) {
-			/* stop mpeg capture */
-			cx23885_api_cmd(fh->dev, CX2341X_ENC_STOP_CAPTURE, 3, 0,
-				CX23885_END_NOW, CX23885_MPEG_CAPTURE,
-				CX23885_RAW_BITS_NONE);
-
-			msleep(500);
-			cx23885_417_check_encoder(dev);
-
-			cx23885_cancel_buffers(&fh->dev->ts1);
-		}
-	}
-
-	if (fh->mpegq.streaming)
-		videobuf_streamoff(&fh->mpegq);
-	if (fh->mpegq.reading)
-		videobuf_read_stop(&fh->mpegq);
-
-	videobuf_mmap_free(&fh->mpegq);
-	file->private_data = NULL;
-	kfree(fh);
-
-	return 0;
-}
-
-static ssize_t mpeg_read(struct file *file, char __user *data,
-	size_t count, loff_t *ppos)
-{
-	struct cx23885_fh *fh = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
-
-	dprintk(2, "%s()\n", __func__);
-
-	/* Deal w/ A/V decoder * and mpeg encoder sync issues. */
-	/* Start mpeg encoder on first read. */
-	if (atomic_cmpxchg(&fh->v4l_reading, 0, 1) == 0) {
-		if (atomic_inc_return(&dev->v4l_reader_count) == 1) {
-			if (cx23885_initialize_codec(dev, 1) < 0)
-				return -EINVAL;
-		}
-	}
-
-	return videobuf_read_stream(&fh->mpegq, data, count, ppos, 0,
-				    file->f_flags & O_NONBLOCK);
-}
-
-static unsigned int mpeg_poll(struct file *file,
-	struct poll_table_struct *wait)
-{
-	struct cx23885_fh *fh = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
-
-	dprintk(2, "%s\n", __func__);
-
-	return videobuf_poll_stream(file, &fh->mpegq, wait);
-}
-
-static int mpeg_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	struct cx23885_fh *fh = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
-
-	dprintk(2, "%s()\n", __func__);
-
-	return videobuf_mmap_mapper(&fh->mpegq, vma);
-}
-
 static struct v4l2_file_operations mpeg_fops = {
 	.owner	       = THIS_MODULE,
-	.open	       = mpeg_open,
-	.release       = mpeg_release,
-	.read	       = mpeg_read,
-	.poll          = mpeg_poll,
-	.mmap	       = mpeg_mmap,
-	.ioctl	       = video_ioctl2,
+	.open           = v4l2_fh_open,
+	.release        = vb2_fop_release,
+	.read           = vb2_fop_read,
+	.poll		= vb2_fop_poll,
+	.unlocked_ioctl = video_ioctl2,
+	.mmap           = vb2_fop_mmap,
 };
 
 static const struct v4l2_ioctl_ops mpeg_ioctl_ops = {
@@ -1669,25 +1446,19 @@ static const struct v4l2_ioctl_ops mpeg_ioctl_ops = {
 	.vidioc_s_tuner		 = vidioc_s_tuner,
 	.vidioc_g_frequency	 = vidioc_g_frequency,
 	.vidioc_s_frequency	 = vidioc_s_frequency,
-	.vidioc_s_ctrl		 = vidioc_s_ctrl,
-	.vidioc_g_ctrl		 = vidioc_g_ctrl,
 	.vidioc_querycap	 = vidioc_querycap,
 	.vidioc_enum_fmt_vid_cap = vidioc_enum_fmt_vid_cap,
 	.vidioc_g_fmt_vid_cap	 = vidioc_g_fmt_vid_cap,
 	.vidioc_try_fmt_vid_cap	 = vidioc_try_fmt_vid_cap,
 	.vidioc_s_fmt_vid_cap	 = vidioc_s_fmt_vid_cap,
-	.vidioc_reqbufs		 = vidioc_reqbufs,
-	.vidioc_querybuf	 = vidioc_querybuf,
-	.vidioc_qbuf		 = vidioc_qbuf,
-	.vidioc_dqbuf		 = vidioc_dqbuf,
-	.vidioc_streamon	 = vidioc_streamon,
-	.vidioc_streamoff	 = vidioc_streamoff,
-	.vidioc_g_ext_ctrls	 = vidioc_g_ext_ctrls,
-	.vidioc_s_ext_ctrls	 = vidioc_s_ext_ctrls,
-	.vidioc_try_ext_ctrls	 = vidioc_try_ext_ctrls,
+	.vidioc_reqbufs       = vb2_ioctl_reqbufs,
+	.vidioc_prepare_buf   = vb2_ioctl_prepare_buf,
+	.vidioc_querybuf      = vb2_ioctl_querybuf,
+	.vidioc_qbuf          = vb2_ioctl_qbuf,
+	.vidioc_dqbuf         = vb2_ioctl_dqbuf,
+	.vidioc_streamon      = vb2_ioctl_streamon,
+	.vidioc_streamoff     = vb2_ioctl_streamoff,
 	.vidioc_log_status	 = vidioc_log_status,
-	.vidioc_querymenu	 = vidioc_querymenu,
-	.vidioc_queryctrl	 = vidioc_queryctrl,
 #ifdef CONFIG_VIDEO_ADV_DEBUG
 	.vidioc_g_chip_info	 = cx23885_g_chip_info,
 	.vidioc_g_register	 = cx23885_g_register,
@@ -1711,6 +1482,7 @@ void cx23885_417_unregister(struct cx23885_dev *dev)
 			video_unregister_device(dev->v4l_device);
 		else
 			video_device_release(dev->v4l_device);
+		v4l2_ctrl_handler_free(&dev->cxhdl.hdl);
 		dev->v4l_device = NULL;
 	}
 }
@@ -1742,6 +1514,7 @@ int cx23885_417_register(struct cx23885_dev *dev)
 	/* FIXME: Port1 hardcoded here */
 	int err = -ENODEV;
 	struct cx23885_tsport *tsport = &dev->ts1;
+	struct vb2_queue *q;
 
 	dprintk(1, "%s()\n", __func__);
 
@@ -1757,14 +1530,36 @@ int cx23885_417_register(struct cx23885_dev *dev)
 		tsport->height = 576;
 
 	tsport->width = 720;
-	cx2341x_fill_defaults(&dev->mpeg_params);
-
-	dev->mpeg_params.port = CX2341X_PORT_SERIAL;
+	dev->cxhdl.port = CX2341X_PORT_SERIAL;
+	err = cx2341x_handler_init(&dev->cxhdl, 50);
+	if (err)
+		return err;
+	dev->cxhdl.priv = dev;
+	dev->cxhdl.func = cx23885_api_func;
+	cx2341x_handler_set_50hz(&dev->cxhdl, tsport->height == 576);
+	v4l2_ctrl_add_handler(&dev->ctrl_handler, &dev->cxhdl.hdl, NULL);
 
 	/* Allocate and initialize V4L video device */
 	dev->v4l_device = cx23885_video_dev_alloc(tsport,
 		dev->pci, &cx23885_mpeg_template, "mpeg");
+	q = &dev->vb2_mpegq;
+	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
+	q->gfp_flags = GFP_DMA32;
+	q->min_buffers_needed = 2;
+	q->drv_priv = dev;
+	q->buf_struct_size = sizeof(struct cx23885_buffer);
+	q->ops = &cx23885_qops;
+	q->mem_ops = &vb2_dma_sg_memops;
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->lock = &dev->lock;
+
+	err = vb2_queue_init(q);
+	if (err < 0)
+		return err;
 	video_set_drvdata(dev->v4l_device, dev);
+	dev->v4l_device->lock = &dev->lock;
+	dev->v4l_device->queue = q;
 	err = video_register_device(dev->v4l_device,
 		VFL_TYPE_GRABBER, -1);
 	if (err < 0) {
diff --git a/drivers/media/pci/cx23885/cx23885-alsa.c b/drivers/media/pci/cx23885/cx23885-alsa.c
index 554798dcedd0..ae7c2e89ad1c 100644
--- a/drivers/media/pci/cx23885/cx23885-alsa.c
+++ b/drivers/media/pci/cx23885/cx23885-alsa.c
@@ -15,10 +15,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/module.h>
@@ -84,6 +80,82 @@ MODULE_PARM_DESC(audio_debug, "enable debug messages [analog audio]");
 #define AUD_INT_MCHG_IRQ        (1 << 21)
 #define GP_COUNT_CONTROL_RESET	0x3
 
+static int cx23885_alsa_dma_init(struct cx23885_audio_dev *chip, int nr_pages)
+{
+	struct cx23885_audio_buffer *buf = chip->buf;
+	struct page *pg;
+	int i;
+
+	buf->vaddr = vmalloc_32(nr_pages << PAGE_SHIFT);
+	if (NULL == buf->vaddr) {
+		dprintk(1, "vmalloc_32(%d pages) failed\n", nr_pages);
+		return -ENOMEM;
+	}
+
+	dprintk(1, "vmalloc is at addr 0x%08lx, size=%d\n",
+				(unsigned long)buf->vaddr,
+				nr_pages << PAGE_SHIFT);
+
+	memset(buf->vaddr, 0, nr_pages << PAGE_SHIFT);
+	buf->nr_pages = nr_pages;
+
+	buf->sglist = vzalloc(buf->nr_pages * sizeof(*buf->sglist));
+	if (NULL == buf->sglist)
+		goto vzalloc_err;
+
+	sg_init_table(buf->sglist, buf->nr_pages);
+	for (i = 0; i < buf->nr_pages; i++) {
+		pg = vmalloc_to_page(buf->vaddr + i * PAGE_SIZE);
+		if (NULL == pg)
+			goto vmalloc_to_page_err;
+		sg_set_page(&buf->sglist[i], pg, PAGE_SIZE, 0);
+	}
+	return 0;
+
+vmalloc_to_page_err:
+	vfree(buf->sglist);
+	buf->sglist = NULL;
+vzalloc_err:
+	vfree(buf->vaddr);
+	buf->vaddr = NULL;
+	return -ENOMEM;
+}
+
+static int cx23885_alsa_dma_map(struct cx23885_audio_dev *dev)
+{
+	struct cx23885_audio_buffer *buf = dev->buf;
+
+	buf->sglen = dma_map_sg(&dev->pci->dev, buf->sglist,
+			buf->nr_pages, PCI_DMA_FROMDEVICE);
+
+	if (0 == buf->sglen) {
+		pr_warn("%s: cx23885_alsa_map_sg failed\n", __func__);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static int cx23885_alsa_dma_unmap(struct cx23885_audio_dev *dev)
+{
+	struct cx23885_audio_buffer *buf = dev->buf;
+
+	if (!buf->sglen)
+		return 0;
+
+	dma_unmap_sg(&dev->pci->dev, buf->sglist, buf->sglen, PCI_DMA_FROMDEVICE);
+	buf->sglen = 0;
+	return 0;
+}
+
+static int cx23885_alsa_dma_free(struct cx23885_audio_buffer *buf)
+{
+	vfree(buf->sglist);
+	buf->sglist = NULL;
+	vfree(buf->vaddr);
+	buf->vaddr = NULL;
+	return 0;
+}
+
 /*
  * BOARD Specific: Sets audio DMA
  */
@@ -198,15 +270,18 @@ int cx23885_audio_irq(struct cx23885_dev *dev, u32 status, u32 mask)
 
 static int dsp_buffer_free(struct cx23885_audio_dev *chip)
 {
+	struct cx23885_riscmem *risc;
+
 	BUG_ON(!chip->dma_size);
 
 	dprintk(2, "Freeing buffer\n");
-	videobuf_dma_unmap(&chip->pci->dev, chip->dma_risc);
-	videobuf_dma_free(chip->dma_risc);
-	btcx_riscmem_free(chip->pci, &chip->buf->risc);
+	cx23885_alsa_dma_unmap(chip);
+	cx23885_alsa_dma_free(chip->buf);
+	risc = &chip->buf->risc;
+	pci_free_consistent(chip->pci, risc->size, risc->cpu, risc->dma);
 	kfree(chip->buf);
 
-	chip->dma_risc = NULL;
+	chip->buf = NULL;
 	chip->dma_size = 0;
 
 	return 0;
@@ -289,6 +364,7 @@ static int snd_cx23885_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
+
 /*
  * hw_params callback
  */
@@ -296,8 +372,6 @@ static int snd_cx23885_hw_params(struct snd_pcm_substream *substream,
 			      struct snd_pcm_hw_params *hw_params)
 {
 	struct cx23885_audio_dev *chip = snd_pcm_substream_chip(substream);
-	struct videobuf_dmabuf *dma;
-
 	struct cx23885_audio_buffer *buf;
 	int ret;
 
@@ -318,19 +392,18 @@ static int snd_cx23885_hw_params(struct snd_pcm_substream *substream,
 		return -ENOMEM;
 
 	buf->bpl = chip->period_size;
+	chip->buf = buf;
 
-	dma = &buf->dma;
-	videobuf_dma_init(dma);
-	ret = videobuf_dma_init_kernel(dma, PCI_DMA_FROMDEVICE,
+	ret = cx23885_alsa_dma_init(chip,
 			(PAGE_ALIGN(chip->dma_size) >> PAGE_SHIFT));
 	if (ret < 0)
 		goto error;
 
-	ret = videobuf_dma_map(&chip->pci->dev, dma);
+	ret = cx23885_alsa_dma_map(chip);
 	if (ret < 0)
 		goto error;
 
-	ret = cx23885_risc_databuffer(chip->pci, &buf->risc, dma->sglist,
+	ret = cx23885_risc_databuffer(chip->pci, &buf->risc, buf->sglist,
 				   chip->period_size, chip->num_periods, 1);
 	if (ret < 0)
 		goto error;
@@ -340,10 +413,7 @@ static int snd_cx23885_hw_params(struct snd_pcm_substream *substream,
 	buf->risc.jmp[1] = cpu_to_le32(buf->risc.dma);
 	buf->risc.jmp[2] = cpu_to_le32(0); /* bits 63-32 */
 
-	chip->buf = buf;
-	chip->dma_risc = dma;
-
-	substream->runtime->dma_area = chip->dma_risc->vaddr;
+	substream->runtime->dma_area = chip->buf->vaddr;
 	substream->runtime->dma_bytes = chip->dma_size;
 	substream->runtime->dma_addr = 0;
 
@@ -351,6 +421,7 @@ static int snd_cx23885_hw_params(struct snd_pcm_substream *substream,
 
 error:
 	kfree(buf);
+	chip->buf = NULL;
 	return ret;
 }
 
diff --git a/drivers/media/pci/cx23885/cx23885-av.c b/drivers/media/pci/cx23885/cx23885-av.c
index c443b7ac5adf..877dad89107e 100644
--- a/drivers/media/pci/cx23885/cx23885-av.c
+++ b/drivers/media/pci/cx23885/cx23885-av.c
@@ -14,11 +14,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- *  02110-1301, USA.
  */
 
 #include "cx23885.h"
diff --git a/drivers/media/pci/cx23885/cx23885-av.h b/drivers/media/pci/cx23885/cx23885-av.h
index d2915c3e53a2..97f232f8efb9 100644
--- a/drivers/media/pci/cx23885/cx23885-av.h
+++ b/drivers/media/pci/cx23885/cx23885-av.h
@@ -14,11 +14,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- *  02110-1301, USA.
  */
 
 #ifndef _CX23885_AV_H_
diff --git a/drivers/media/pci/cx23885/cx23885-cards.c b/drivers/media/pci/cx23885/cx23885-cards.c
index c2b608007190..88c257d1161b 100644
--- a/drivers/media/pci/cx23885/cx23885-cards.c
+++ b/drivers/media/pci/cx23885/cx23885-cards.c
@@ -13,10 +13,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/init.h>
@@ -679,6 +675,11 @@ struct cx23885_board cx23885_boards[] = {
 			.amux   = CX25840_AUDIO7,
 		} },
 	},
+	[CX23885_BOARD_DVBSKY_T9580] = {
+		.name		= "DVBSky T9580",
+		.portb		= CX23885_MPEG_DVB,
+		.portc		= CX23885_MPEG_DVB,
+	},
 };
 const unsigned int cx23885_bcount = ARRAY_SIZE(cx23885_boards);
 
@@ -934,6 +935,10 @@ struct cx23885_subid cx23885_subids[] = {
 		.subvendor = 0x18ac,
 		.subdevice = 0xdb98,
 		.card      = CX23885_BOARD_DVICO_FUSIONHDTV_DVB_T_DUAL_EXP2,
+	}, {
+		.subvendor = 0x4254,
+		.subdevice = 0x9580,
+		.card      = CX23885_BOARD_DVBSKY_T9580,
 	},
 };
 const unsigned int cx23885_idcount = ARRAY_SIZE(cx23885_subids);
@@ -1528,6 +1533,14 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx_set(GP0_IO, 0x00040004);
 		mdelay(60);
 		break;
+	case CX23885_BOARD_DVBSKY_T9580:
+		/* enable GPIO3-18 pins */
+		cx_write(MC417_CTL, 0x00000037);
+		cx23885_gpio_enable(dev, GPIO_2 | GPIO_11, 1);
+		cx23885_gpio_clear(dev, GPIO_2 | GPIO_11);
+		mdelay(100);
+		cx23885_gpio_set(dev, GPIO_2 | GPIO_11);
+		break;
 	}
 }
 
@@ -1851,6 +1864,14 @@ void cx23885_card_setup(struct cx23885_dev *dev)
 		ts2->ts_clk_en_val = 0x1; /* Enable TS_CLK */
 		ts2->src_sel_val   = CX23885_SRC_SEL_PARALLEL_MPEG_VIDEO;
 		break;
+	case CX23885_BOARD_DVBSKY_T9580:
+		ts1->gen_ctrl_val  = 0x5; /* Parallel */
+		ts1->ts_clk_en_val = 0x1; /* Enable TS_CLK */
+		ts1->src_sel_val   = CX23885_SRC_SEL_PARALLEL_MPEG_VIDEO;
+		ts2->gen_ctrl_val  = 0x8; /* Serial bus */
+		ts2->ts_clk_en_val = 0x1; /* Enable TS_CLK */
+		ts2->src_sel_val   = CX23885_SRC_SEL_PARALLEL_MPEG_VIDEO;
+		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1250:
 	case CX23885_BOARD_HAUPPAUGE_HVR1500:
 	case CX23885_BOARD_HAUPPAUGE_HVR1500Q:
@@ -1913,6 +1934,7 @@ void cx23885_card_setup(struct cx23885_dev *dev)
 	case CX23885_BOARD_AVERMEDIA_HC81R:
 	case CX23885_BOARD_TBS_6980:
 	case CX23885_BOARD_TBS_6981:
+	case CX23885_BOARD_DVBSKY_T9580:
 		dev->sd_cx25840 = v4l2_i2c_new_subdev(&dev->v4l2_dev,
 				&dev->i2c_bus[2].i2c_adap,
 				"cx25840", 0x88 >> 1, NULL);
@@ -1970,5 +1992,3 @@ void cx23885_card_setup(struct cx23885_dev *dev)
 	}
 	}
 }
-
-/* ------------------------------------------------------------------ */
diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c
index edcd79db1e4e..331eddac7222 100644
--- a/drivers/media/pci/cx23885/cx23885-core.c
+++ b/drivers/media/pci/cx23885/cx23885-core.c
@@ -13,10 +13,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/init.h>
@@ -420,39 +416,23 @@ static int cx23885_risc_decode(u32 risc)
 	return incr[risc >> 28] ? incr[risc >> 28] : 1;
 }
 
-void cx23885_wakeup(struct cx23885_tsport *port,
+static void cx23885_wakeup(struct cx23885_tsport *port,
 			   struct cx23885_dmaqueue *q, u32 count)
 {
 	struct cx23885_dev *dev = port->dev;
 	struct cx23885_buffer *buf;
-	int bc;
-
-	for (bc = 0;; bc++) {
-		if (list_empty(&q->active))
-			break;
-		buf = list_entry(q->active.next,
-				 struct cx23885_buffer, vb.queue);
-
-		/* count comes from the hw and is is 16bit wide --
-		 * this trick handles wrap-arounds correctly for
-		 * up to 32767 buffers in flight... */
-		if ((s16) (count - buf->count) < 0)
-			break;
 
-		v4l2_get_timestamp(&buf->vb.ts);
-		dprintk(2, "[%p/%d] wakeup reg=%d buf=%d\n", buf, buf->vb.i,
-			count, buf->count);
-		buf->vb.state = VIDEOBUF_DONE;
-		list_del(&buf->vb.queue);
-		wake_up(&buf->vb.done);
-	}
 	if (list_empty(&q->active))
-		del_timer(&q->timeout);
-	else
-		mod_timer(&q->timeout, jiffies + BUFFER_TIMEOUT);
-	if (bc != 1)
-		printk(KERN_WARNING "%s: %d buffers handled (should be 1)\n",
-		       __func__, bc);
+		return;
+	buf = list_entry(q->active.next,
+			 struct cx23885_buffer, queue);
+
+	v4l2_get_timestamp(&buf->vb.v4l2_buf.timestamp);
+	buf->vb.v4l2_buf.sequence = q->count++;
+	dprintk(1, "[%p/%d] wakeup reg=%d buf=%d\n", buf, buf->vb.v4l2_buf.index,
+		count, q->count);
+	list_del(&buf->queue);
+	vb2_buffer_done(&buf->vb, VB2_BUF_STATE_DONE);
 }
 
 int cx23885_sram_channel_setup(struct cx23885_dev *dev,
@@ -482,8 +462,8 @@ int cx23885_sram_channel_setup(struct cx23885_dev *dev,
 		lines = 6;
 	BUG_ON(lines < 2);
 
-	cx_write(8 + 0, RISC_JUMP | RISC_IRQ1 | RISC_CNT_INC);
-	cx_write(8 + 4, 8);
+	cx_write(8 + 0, RISC_JUMP | RISC_CNT_RESET);
+	cx_write(8 + 4, 12);
 	cx_write(8 + 8, 0);
 
 	/* write CDT */
@@ -590,7 +570,7 @@ void cx23885_sram_channel_dump(struct cx23885_dev *dev,
 }
 
 static void cx23885_risc_disasm(struct cx23885_tsport *port,
-				struct btcx_riscmem *risc)
+				struct cx23885_riscmem *risc)
 {
 	struct cx23885_dev *dev = port->dev;
 	unsigned int i, j, n;
@@ -699,10 +679,6 @@ static int get_resources(struct cx23885_dev *dev)
 	return -EBUSY;
 }
 
-static void cx23885_timeout(unsigned long data);
-int cx23885_risc_stopper(struct pci_dev *pci, struct btcx_riscmem *risc,
-				u32 reg, u32 mask, u32 value);
-
 static int cx23885_init_tsport(struct cx23885_dev *dev,
 	struct cx23885_tsport *port, int portno)
 {
@@ -719,11 +695,6 @@ static int cx23885_init_tsport(struct cx23885_dev *dev,
 	port->nr = portno;
 
 	INIT_LIST_HEAD(&port->mpegq.active);
-	INIT_LIST_HEAD(&port->mpegq.queued);
-	port->mpegq.timeout.function = cx23885_timeout;
-	port->mpegq.timeout.data = (unsigned long)port;
-	init_timer(&port->mpegq.timeout);
-
 	mutex_init(&port->frontends.lock);
 	INIT_LIST_HEAD(&port->frontends.felist);
 	port->frontends.active_fe_id = 0;
@@ -776,9 +747,6 @@ static int cx23885_init_tsport(struct cx23885_dev *dev,
 		BUG();
 	}
 
-	cx23885_risc_stopper(dev->pci, &port->mpegq.stopper,
-		     port->reg_dma_ctl, port->dma_ctl_val, 0x00);
-
 	return 0;
 }
 
@@ -1089,11 +1057,18 @@ static void cx23885_dev_unregister(struct cx23885_dev *dev)
 static __le32 *cx23885_risc_field(__le32 *rp, struct scatterlist *sglist,
 			       unsigned int offset, u32 sync_line,
 			       unsigned int bpl, unsigned int padding,
-			       unsigned int lines,  unsigned int lpi)
+			       unsigned int lines,  unsigned int lpi, bool jump)
 {
 	struct scatterlist *sg;
 	unsigned int line, todo, sol;
 
+
+	if (jump) {
+		*(rp++) = cpu_to_le32(RISC_JUMP);
+		*(rp++) = cpu_to_le32(0);
+		*(rp++) = cpu_to_le32(0); /* bits 63-32 */
+	}
+
 	/* sync instruction */
 	if (sync_line != NO_SYNC_LINE)
 		*(rp++) = cpu_to_le32(RISC_RESYNC | sync_line);
@@ -1146,14 +1121,13 @@ static __le32 *cx23885_risc_field(__le32 *rp, struct scatterlist *sglist,
 	return rp;
 }
 
-int cx23885_risc_buffer(struct pci_dev *pci, struct btcx_riscmem *risc,
+int cx23885_risc_buffer(struct pci_dev *pci, struct cx23885_riscmem *risc,
 			struct scatterlist *sglist, unsigned int top_offset,
 			unsigned int bottom_offset, unsigned int bpl,
 			unsigned int padding, unsigned int lines)
 {
 	u32 instructions, fields;
 	__le32 *rp;
-	int rc;
 
 	fields = 0;
 	if (UNSET != top_offset)
@@ -1168,19 +1142,20 @@ int cx23885_risc_buffer(struct pci_dev *pci, struct btcx_riscmem *risc,
 	/* write and jump need and extra dword */
 	instructions  = fields * (1 + ((bpl + padding) * lines)
 		/ PAGE_SIZE + lines);
-	instructions += 2;
-	rc = btcx_riscmem_alloc(pci, risc, instructions*12);
-	if (rc < 0)
-		return rc;
+	instructions += 5;
+	risc->size = instructions * 12;
+	risc->cpu = pci_alloc_consistent(pci, risc->size, &risc->dma);
+	if (risc->cpu == NULL)
+		return -ENOMEM;
 
 	/* write risc instructions */
 	rp = risc->cpu;
 	if (UNSET != top_offset)
 		rp = cx23885_risc_field(rp, sglist, top_offset, 0,
-					bpl, padding, lines, 0);
+					bpl, padding, lines, 0, true);
 	if (UNSET != bottom_offset)
 		rp = cx23885_risc_field(rp, sglist, bottom_offset, 0x200,
-					bpl, padding, lines, 0);
+					bpl, padding, lines, 0, UNSET == top_offset);
 
 	/* save pointer to jmp instruction address */
 	risc->jmp = rp;
@@ -1189,14 +1164,13 @@ int cx23885_risc_buffer(struct pci_dev *pci, struct btcx_riscmem *risc,
 }
 
 int cx23885_risc_databuffer(struct pci_dev *pci,
-				   struct btcx_riscmem *risc,
+				   struct cx23885_riscmem *risc,
 				   struct scatterlist *sglist,
 				   unsigned int bpl,
 				   unsigned int lines, unsigned int lpi)
 {
 	u32 instructions;
 	__le32 *rp;
-	int rc;
 
 	/* estimate risc mem: worst case is one write per page border +
 	   one write per scan line + syncs + jump (all 2 dwords).  Here
@@ -1204,16 +1178,17 @@ int cx23885_risc_databuffer(struct pci_dev *pci,
 	   than PAGE_SIZE */
 	/* Jump and write need an extra dword */
 	instructions  = 1 + (bpl * lines) / PAGE_SIZE + lines;
-	instructions += 1;
+	instructions += 4;
 
-	rc = btcx_riscmem_alloc(pci, risc, instructions*12);
-	if (rc < 0)
-		return rc;
+	risc->size = instructions * 12;
+	risc->cpu = pci_alloc_consistent(pci, risc->size, &risc->dma);
+	if (risc->cpu == NULL)
+		return -ENOMEM;
 
 	/* write risc instructions */
 	rp = risc->cpu;
 	rp = cx23885_risc_field(rp, sglist, 0, NO_SYNC_LINE,
-				bpl, 0, lines, lpi);
+				bpl, 0, lines, lpi, lpi == 0);
 
 	/* save pointer to jmp instruction address */
 	risc->jmp = rp;
@@ -1221,14 +1196,13 @@ int cx23885_risc_databuffer(struct pci_dev *pci,
 	return 0;
 }
 
-int cx23885_risc_vbibuffer(struct pci_dev *pci, struct btcx_riscmem *risc,
+int cx23885_risc_vbibuffer(struct pci_dev *pci, struct cx23885_riscmem *risc,
 			struct scatterlist *sglist, unsigned int top_offset,
 			unsigned int bottom_offset, unsigned int bpl,
 			unsigned int padding, unsigned int lines)
 {
 	u32 instructions, fields;
 	__le32 *rp;
-	int rc;
 
 	fields = 0;
 	if (UNSET != top_offset)
@@ -1243,22 +1217,23 @@ int cx23885_risc_vbibuffer(struct pci_dev *pci, struct btcx_riscmem *risc,
 	/* write and jump need and extra dword */
 	instructions  = fields * (1 + ((bpl + padding) * lines)
 		/ PAGE_SIZE + lines);
-	instructions += 2;
-	rc = btcx_riscmem_alloc(pci, risc, instructions*12);
-	if (rc < 0)
-		return rc;
+	instructions += 5;
+	risc->size = instructions * 12;
+	risc->cpu = pci_alloc_consistent(pci, risc->size, &risc->dma);
+	if (risc->cpu == NULL)
+		return -ENOMEM;
 	/* write risc instructions */
 	rp = risc->cpu;
 
 	/* Sync to line 6, so US CC line 21 will appear in line '12'
 	 * in the userland vbi payload */
 	if (UNSET != top_offset)
-		rp = cx23885_risc_field(rp, sglist, top_offset, 6,
-					bpl, padding, lines, 0);
+		rp = cx23885_risc_field(rp, sglist, top_offset, 0,
+					bpl, padding, lines, 0, true);
 
 	if (UNSET != bottom_offset)
-		rp = cx23885_risc_field(rp, sglist, bottom_offset, 0x207,
-					bpl, padding, lines, 0);
+		rp = cx23885_risc_field(rp, sglist, bottom_offset, 0x200,
+					bpl, padding, lines, 0, UNSET == top_offset);
 
 
 
@@ -1269,38 +1244,12 @@ int cx23885_risc_vbibuffer(struct pci_dev *pci, struct btcx_riscmem *risc,
 }
 
 
-int cx23885_risc_stopper(struct pci_dev *pci, struct btcx_riscmem *risc,
-				u32 reg, u32 mask, u32 value)
+void cx23885_free_buffer(struct cx23885_dev *dev, struct cx23885_buffer *buf)
 {
-	__le32 *rp;
-	int rc;
-
-	rc = btcx_riscmem_alloc(pci, risc, 4*16);
-	if (rc < 0)
-		return rc;
-
-	/* write risc instructions */
-	rp = risc->cpu;
-	*(rp++) = cpu_to_le32(RISC_WRITECR  | RISC_IRQ2);
-	*(rp++) = cpu_to_le32(reg);
-	*(rp++) = cpu_to_le32(value);
-	*(rp++) = cpu_to_le32(mask);
-	*(rp++) = cpu_to_le32(RISC_JUMP);
-	*(rp++) = cpu_to_le32(risc->dma);
-	*(rp++) = cpu_to_le32(0); /* bits 63-32 */
-	return 0;
-}
-
-void cx23885_free_buffer(struct videobuf_queue *q, struct cx23885_buffer *buf)
-{
-	struct videobuf_dmabuf *dma = videobuf_to_dma(&buf->vb);
+	struct cx23885_riscmem *risc = &buf->risc;
 
 	BUG_ON(in_interrupt());
-	videobuf_waiton(q, &buf->vb, 0, 0);
-	videobuf_dma_unmap(q->dev, dma);
-	videobuf_dma_free(dma);
-	btcx_riscmem_free(to_pci_dev(q->dev), &buf->risc);
-	buf->vb.state = VIDEOBUF_NEEDS_INIT;
+	pci_free_consistent(dev->pci, risc->size, risc->cpu, risc->dma);
 }
 
 static void cx23885_tsport_reg_dump(struct cx23885_tsport *port)
@@ -1355,7 +1304,7 @@ static void cx23885_tsport_reg_dump(struct cx23885_tsport *port)
 		port->reg_ts_int_msk, cx_read(port->reg_ts_int_msk));
 }
 
-static int cx23885_start_dma(struct cx23885_tsport *port,
+int cx23885_start_dma(struct cx23885_tsport *port,
 			     struct cx23885_dmaqueue *q,
 			     struct cx23885_buffer   *buf)
 {
@@ -1363,7 +1312,7 @@ static int cx23885_start_dma(struct cx23885_tsport *port,
 	u32 reg;
 
 	dprintk(1, "%s() w: %d, h: %d, f: %d\n", __func__,
-		buf->vb.width, buf->vb.height, buf->vb.field);
+		dev->width, dev->height, dev->field);
 
 	/* Stop the fifo and risc engine for this port */
 	cx_clear(port->reg_dma_ctl, port->dma_ctl_val);
@@ -1379,7 +1328,7 @@ static int cx23885_start_dma(struct cx23885_tsport *port,
 	}
 
 	/* write TS length to chip */
-	cx_write(port->reg_lngth, buf->vb.width);
+	cx_write(port->reg_lngth, port->ts_packet_size);
 
 	if ((!(cx23885_boards[dev->board].portb & CX23885_MPEG_DVB)) &&
 		(!(cx23885_boards[dev->board].portc & CX23885_MPEG_DVB))) {
@@ -1408,7 +1357,7 @@ static int cx23885_start_dma(struct cx23885_tsport *port,
 	/* NOTE: this is 2 (reserved) for portb, does it matter? */
 	/* reset counter to zero */
 	cx_write(port->reg_gpcnt_ctl, 3);
-	q->count = 1;
+	q->count = 0;
 
 	/* Set VIDB pins to input */
 	if (cx23885_boards[dev->board].portb == CX23885_MPEG_DVB) {
@@ -1497,134 +1446,83 @@ static int cx23885_stop_dma(struct cx23885_tsport *port)
 	return 0;
 }
 
-int cx23885_restart_queue(struct cx23885_tsport *port,
-				struct cx23885_dmaqueue *q)
-{
-	struct cx23885_dev *dev = port->dev;
-	struct cx23885_buffer *buf;
-
-	dprintk(5, "%s()\n", __func__);
-	if (list_empty(&q->active)) {
-		struct cx23885_buffer *prev;
-		prev = NULL;
-
-		dprintk(5, "%s() queue is empty\n", __func__);
-
-		for (;;) {
-			if (list_empty(&q->queued))
-				return 0;
-			buf = list_entry(q->queued.next, struct cx23885_buffer,
-					 vb.queue);
-			if (NULL == prev) {
-				list_move_tail(&buf->vb.queue, &q->active);
-				cx23885_start_dma(port, q, buf);
-				buf->vb.state = VIDEOBUF_ACTIVE;
-				buf->count    = q->count++;
-				mod_timer(&q->timeout, jiffies+BUFFER_TIMEOUT);
-				dprintk(5, "[%p/%d] restart_queue - f/active\n",
-					buf, buf->vb.i);
-
-			} else if (prev->vb.width  == buf->vb.width  &&
-				   prev->vb.height == buf->vb.height &&
-				   prev->fmt       == buf->fmt) {
-				list_move_tail(&buf->vb.queue, &q->active);
-				buf->vb.state = VIDEOBUF_ACTIVE;
-				buf->count    = q->count++;
-				prev->risc.jmp[1] = cpu_to_le32(buf->risc.dma);
-				/* 64 bit bits 63-32 */
-				prev->risc.jmp[2] = cpu_to_le32(0);
-				dprintk(5, "[%p/%d] restart_queue - m/active\n",
-					buf, buf->vb.i);
-			} else {
-				return 0;
-			}
-			prev = buf;
-		}
-		return 0;
-	}
-
-	buf = list_entry(q->active.next, struct cx23885_buffer, vb.queue);
-	dprintk(2, "restart_queue [%p/%d]: restart dma\n",
-		buf, buf->vb.i);
-	cx23885_start_dma(port, q, buf);
-	list_for_each_entry(buf, &q->active, vb.queue)
-		buf->count = q->count++;
-	mod_timer(&q->timeout, jiffies + BUFFER_TIMEOUT);
-	return 0;
-}
-
 /* ------------------------------------------------------------------ */
 
-int cx23885_buf_prepare(struct videobuf_queue *q, struct cx23885_tsport *port,
-			struct cx23885_buffer *buf, enum v4l2_field field)
+int cx23885_buf_prepare(struct cx23885_buffer *buf, struct cx23885_tsport *port)
 {
 	struct cx23885_dev *dev = port->dev;
 	int size = port->ts_packet_size * port->ts_packet_count;
+	struct sg_table *sgt = vb2_dma_sg_plane_desc(&buf->vb, 0);
 	int rc;
 
 	dprintk(1, "%s: %p\n", __func__, buf);
-	if (0 != buf->vb.baddr  &&  buf->vb.bsize < size)
+	if (vb2_plane_size(&buf->vb, 0) < size)
 		return -EINVAL;
+	vb2_set_plane_payload(&buf->vb, 0, size);
 
-	if (VIDEOBUF_NEEDS_INIT == buf->vb.state) {
-		buf->vb.width  = port->ts_packet_size;
-		buf->vb.height = port->ts_packet_count;
-		buf->vb.size   = size;
-		buf->vb.field  = field /*V4L2_FIELD_TOP*/;
-
-		rc = videobuf_iolock(q, &buf->vb, NULL);
-		if (0 != rc)
-			goto fail;
-		cx23885_risc_databuffer(dev->pci, &buf->risc,
-					videobuf_to_dma(&buf->vb)->sglist,
-					buf->vb.width, buf->vb.height, 0);
-	}
-	buf->vb.state = VIDEOBUF_PREPARED;
-	return 0;
+	rc = dma_map_sg(&dev->pci->dev, sgt->sgl, sgt->nents, DMA_FROM_DEVICE);
+	if (!rc)
+		return -EIO;
 
- fail:
-	cx23885_free_buffer(q, buf);
-	return rc;
+	cx23885_risc_databuffer(dev->pci, &buf->risc,
+				sgt->sgl,
+				port->ts_packet_size, port->ts_packet_count, 0);
+	return 0;
 }
 
+/*
+ * The risc program for each buffer works as follows: it starts with a simple
+ * 'JUMP to addr + 12', which is effectively a NOP. Then the code to DMA the
+ * buffer follows and at the end we have a JUMP back to the start + 12 (skipping
+ * the initial JUMP).
+ *
+ * This is the risc program of the first buffer to be queued if the active list
+ * is empty and it just keeps DMAing this buffer without generating any
+ * interrupts.
+ *
+ * If a new buffer is added then the initial JUMP in the code for that buffer
+ * will generate an interrupt which signals that the previous buffer has been
+ * DMAed successfully and that it can be returned to userspace.
+ *
+ * It also sets the final jump of the previous buffer to the start of the new
+ * buffer, thus chaining the new buffer into the DMA chain. This is a single
+ * atomic u32 write, so there is no race condition.
+ *
+ * The end-result of all this that you only get an interrupt when a buffer
+ * is ready, so the control flow is very easy.
+ */
 void cx23885_buf_queue(struct cx23885_tsport *port, struct cx23885_buffer *buf)
 {
 	struct cx23885_buffer    *prev;
 	struct cx23885_dev *dev = port->dev;
 	struct cx23885_dmaqueue  *cx88q = &port->mpegq;
+	unsigned long flags;
 
-	/* add jump to stopper */
-	buf->risc.jmp[0] = cpu_to_le32(RISC_JUMP | RISC_IRQ1 | RISC_CNT_INC);
-	buf->risc.jmp[1] = cpu_to_le32(cx88q->stopper.dma);
+	buf->risc.cpu[1] = cpu_to_le32(buf->risc.dma + 12);
+	buf->risc.jmp[0] = cpu_to_le32(RISC_JUMP | RISC_CNT_INC);
+	buf->risc.jmp[1] = cpu_to_le32(buf->risc.dma + 12);
 	buf->risc.jmp[2] = cpu_to_le32(0); /* bits 63-32 */
 
+	spin_lock_irqsave(&dev->slock, flags);
 	if (list_empty(&cx88q->active)) {
-		dprintk(1, "queue is empty - first active\n");
-		list_add_tail(&buf->vb.queue, &cx88q->active);
-		cx23885_start_dma(port, cx88q, buf);
-		buf->vb.state = VIDEOBUF_ACTIVE;
-		buf->count    = cx88q->count++;
-		mod_timer(&cx88q->timeout, jiffies + BUFFER_TIMEOUT);
+		list_add_tail(&buf->queue, &cx88q->active);
 		dprintk(1, "[%p/%d] %s - first active\n",
-			buf, buf->vb.i, __func__);
+			buf, buf->vb.v4l2_buf.index, __func__);
 	} else {
-		dprintk(1, "queue is not empty - append to active\n");
+		buf->risc.cpu[0] |= cpu_to_le32(RISC_IRQ1);
 		prev = list_entry(cx88q->active.prev, struct cx23885_buffer,
-				  vb.queue);
-		list_add_tail(&buf->vb.queue, &cx88q->active);
-		buf->vb.state = VIDEOBUF_ACTIVE;
-		buf->count    = cx88q->count++;
+				  queue);
+		list_add_tail(&buf->queue, &cx88q->active);
 		prev->risc.jmp[1] = cpu_to_le32(buf->risc.dma);
-		prev->risc.jmp[2] = cpu_to_le32(0); /* 64 bit bits 63-32 */
 		dprintk(1, "[%p/%d] %s - append to active\n",
-			 buf, buf->vb.i, __func__);
+			 buf, buf->vb.v4l2_buf.index, __func__);
 	}
+	spin_unlock_irqrestore(&dev->slock, flags);
 }
 
 /* ----------------------------------------------------------- */
 
-static void do_cancel_buffers(struct cx23885_tsport *port, char *reason,
-			      int restart)
+static void do_cancel_buffers(struct cx23885_tsport *port, char *reason)
 {
 	struct cx23885_dev *dev = port->dev;
 	struct cx23885_dmaqueue *q = &port->mpegq;
@@ -1634,16 +1532,11 @@ static void do_cancel_buffers(struct cx23885_tsport *port, char *reason,
 	spin_lock_irqsave(&port->slock, flags);
 	while (!list_empty(&q->active)) {
 		buf = list_entry(q->active.next, struct cx23885_buffer,
-				 vb.queue);
-		list_del(&buf->vb.queue);
-		buf->vb.state = VIDEOBUF_ERROR;
-		wake_up(&buf->vb.done);
+				 queue);
+		list_del(&buf->queue);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
 		dprintk(1, "[%p/%d] %s - dma=0x%08lx\n",
-			buf, buf->vb.i, reason, (unsigned long)buf->risc.dma);
-	}
-	if (restart) {
-		dprintk(1, "restarting queue\n");
-		cx23885_restart_queue(port, q);
+			buf, buf->vb.v4l2_buf.index, reason, (unsigned long)buf->risc.dma);
 	}
 	spin_unlock_irqrestore(&port->slock, flags);
 }
@@ -1651,27 +1544,10 @@ static void do_cancel_buffers(struct cx23885_tsport *port, char *reason,
 void cx23885_cancel_buffers(struct cx23885_tsport *port)
 {
 	struct cx23885_dev *dev = port->dev;
-	struct cx23885_dmaqueue *q = &port->mpegq;
-
-	dprintk(1, "%s()\n", __func__);
-	del_timer_sync(&q->timeout);
-	cx23885_stop_dma(port);
-	do_cancel_buffers(port, "cancel", 0);
-}
-
-static void cx23885_timeout(unsigned long data)
-{
-	struct cx23885_tsport *port = (struct cx23885_tsport *)data;
-	struct cx23885_dev *dev = port->dev;
 
 	dprintk(1, "%s()\n", __func__);
-
-	if (debug > 5)
-		cx23885_sram_channel_dump(dev,
-			&dev->sram_channels[port->sram_chno]);
-
 	cx23885_stop_dma(port);
-	do_cancel_buffers(port, "timeout", 1);
+	do_cancel_buffers(port, "cancel");
 }
 
 int cx23885_irq_417(struct cx23885_dev *dev, u32 status)
@@ -1721,11 +1597,6 @@ int cx23885_irq_417(struct cx23885_dev *dev, u32 status)
 		spin_lock(&port->slock);
 		cx23885_wakeup(port, &port->mpegq, count);
 		spin_unlock(&port->slock);
-	} else if (status & VID_B_MSK_RISCI2) {
-		dprintk(7, "        VID_B_MSK_RISCI2\n");
-		spin_lock(&port->slock);
-		cx23885_restart_queue(port, &port->mpegq);
-		spin_unlock(&port->slock);
 	}
 	if (status) {
 		cx_write(port->reg_ts_int_stat, status);
@@ -1777,14 +1648,6 @@ static int cx23885_irq_ts(struct cx23885_tsport *port, u32 status)
 		cx23885_wakeup(port, &port->mpegq, count);
 		spin_unlock(&port->slock);
 
-	} else if (status & VID_BC_MSK_RISCI2) {
-
-		dprintk(7, " (RISCI2            0x%08x)\n", VID_BC_MSK_RISCI2);
-
-		spin_lock(&port->slock);
-		cx23885_restart_queue(port, &port->mpegq);
-		spin_unlock(&port->slock);
-
 	}
 	if (status) {
 		cx_write(port->reg_ts_int_stat, status);
@@ -2087,6 +1950,7 @@ static int cx23885_initdev(struct pci_dev *pci_dev,
 			   const struct pci_device_id *pci_id)
 {
 	struct cx23885_dev *dev;
+	struct v4l2_ctrl_handler *hdl;
 	int err;
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
@@ -2097,6 +1961,14 @@ static int cx23885_initdev(struct pci_dev *pci_dev,
 	if (err < 0)
 		goto fail_free;
 
+	hdl = &dev->ctrl_handler;
+	v4l2_ctrl_handler_init(hdl, 6);
+	if (hdl->error) {
+		err = hdl->error;
+		goto fail_ctrl;
+	}
+	dev->v4l2_dev.ctrl_handler = hdl;
+
 	/* Prepare to handle notifications from subdevices */
 	cx23885_v4l2_dev_notify_init(dev);
 
@@ -2104,12 +1976,12 @@ static int cx23885_initdev(struct pci_dev *pci_dev,
 	dev->pci = pci_dev;
 	if (pci_enable_device(pci_dev)) {
 		err = -EIO;
-		goto fail_unreg;
+		goto fail_ctrl;
 	}
 
 	if (cx23885_dev_setup(dev) < 0) {
 		err = -EINVAL;
-		goto fail_unreg;
+		goto fail_ctrl;
 	}
 
 	/* print pci info */
@@ -2157,7 +2029,8 @@ static int cx23885_initdev(struct pci_dev *pci_dev,
 
 fail_irq:
 	cx23885_dev_unregister(dev);
-fail_unreg:
+fail_ctrl:
+	v4l2_ctrl_handler_free(hdl);
 	v4l2_device_unregister(&dev->v4l2_dev);
 fail_free:
 	kfree(dev);
@@ -2180,6 +2053,7 @@ static void cx23885_finidev(struct pci_dev *pci_dev)
 	free_irq(pci_dev->irq, dev);
 
 	cx23885_dev_unregister(dev);
+	v4l2_ctrl_handler_free(&dev->ctrl_handler);
 	v4l2_device_unregister(v4l2_dev);
 	kfree(dev);
 }
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index 968fecc32f9c..13734b8c7917 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -13,10 +13,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/module.h>
@@ -73,6 +69,10 @@
 #include "a8293.h"
 #include "mb86a20s.h"
 #include "si2165.h"
+#include "si2168.h"
+#include "si2157.h"
+#include "m88ds3103.h"
+#include "m88ts2022.h"
 
 static unsigned int debug;
 
@@ -91,59 +91,95 @@ DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
 /* ------------------------------------------------------------------ */
 
-static int dvb_buf_setup(struct videobuf_queue *q,
-			 unsigned int *count, unsigned int *size)
+static int queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
+			   unsigned int *num_buffers, unsigned int *num_planes,
+			   unsigned int sizes[], void *alloc_ctxs[])
 {
-	struct cx23885_tsport *port = q->priv_data;
+	struct cx23885_tsport *port = q->drv_priv;
 
 	port->ts_packet_size  = 188 * 4;
 	port->ts_packet_count = 32;
-
-	*size  = port->ts_packet_size * port->ts_packet_count;
-	*count = 32;
+	*num_planes = 1;
+	sizes[0] = port->ts_packet_size * port->ts_packet_count;
+	*num_buffers = 32;
 	return 0;
 }
 
-static int dvb_buf_prepare(struct videobuf_queue *q,
-			   struct videobuf_buffer *vb, enum v4l2_field field)
+
+static int buffer_prepare(struct vb2_buffer *vb)
 {
-	struct cx23885_tsport *port = q->priv_data;
-	return cx23885_buf_prepare(q, port, (struct cx23885_buffer *)vb, field);
+	struct cx23885_tsport *port = vb->vb2_queue->drv_priv;
+	struct cx23885_buffer *buf =
+		container_of(vb, struct cx23885_buffer, vb);
+
+	return cx23885_buf_prepare(buf, port);
 }
 
-static void dvb_buf_queue(struct videobuf_queue *q, struct videobuf_buffer *vb)
+static void buffer_finish(struct vb2_buffer *vb)
 {
-	struct cx23885_tsport *port = q->priv_data;
-	cx23885_buf_queue(port, (struct cx23885_buffer *)vb);
+	struct cx23885_tsport *port = vb->vb2_queue->drv_priv;
+	struct cx23885_dev *dev = port->dev;
+	struct cx23885_buffer *buf = container_of(vb,
+		struct cx23885_buffer, vb);
+	struct sg_table *sgt = vb2_dma_sg_plane_desc(vb, 0);
+
+	cx23885_free_buffer(dev, buf);
+
+	dma_unmap_sg(&dev->pci->dev, sgt->sgl, sgt->nents, DMA_FROM_DEVICE);
 }
 
-static void dvb_buf_release(struct videobuf_queue *q,
-			    struct videobuf_buffer *vb)
+static void buffer_queue(struct vb2_buffer *vb)
 {
-	cx23885_free_buffer(q, (struct cx23885_buffer *)vb);
+	struct cx23885_tsport *port = vb->vb2_queue->drv_priv;
+	struct cx23885_buffer   *buf = container_of(vb,
+		struct cx23885_buffer, vb);
+
+	cx23885_buf_queue(port, buf);
 }
 
 static void cx23885_dvb_gate_ctrl(struct cx23885_tsport  *port, int open)
 {
-	struct videobuf_dvb_frontends *f;
-	struct videobuf_dvb_frontend *fe;
+	struct vb2_dvb_frontends *f;
+	struct vb2_dvb_frontend *fe;
 
 	f = &port->frontends;
 
 	if (f->gate <= 1) /* undefined or fe0 */
-		fe = videobuf_dvb_get_frontend(f, 1);
+		fe = vb2_dvb_get_frontend(f, 1);
 	else
-		fe = videobuf_dvb_get_frontend(f, f->gate);
+		fe = vb2_dvb_get_frontend(f, f->gate);
 
 	if (fe && fe->dvb.frontend && fe->dvb.frontend->ops.i2c_gate_ctrl)
 		fe->dvb.frontend->ops.i2c_gate_ctrl(fe->dvb.frontend, open);
 }
 
-static struct videobuf_queue_ops dvb_qops = {
-	.buf_setup    = dvb_buf_setup,
-	.buf_prepare  = dvb_buf_prepare,
-	.buf_queue    = dvb_buf_queue,
-	.buf_release  = dvb_buf_release,
+static int cx23885_start_streaming(struct vb2_queue *q, unsigned int count)
+{
+	struct cx23885_tsport *port = q->drv_priv;
+	struct cx23885_dmaqueue *dmaq = &port->mpegq;
+	struct cx23885_buffer *buf = list_entry(dmaq->active.next,
+			struct cx23885_buffer, queue);
+
+	cx23885_start_dma(port, dmaq, buf);
+	return 0;
+}
+
+static void cx23885_stop_streaming(struct vb2_queue *q)
+{
+	struct cx23885_tsport *port = q->drv_priv;
+
+	cx23885_cancel_buffers(port);
+}
+
+static struct vb2_ops dvb_qops = {
+	.queue_setup    = queue_setup,
+	.buf_prepare  = buffer_prepare,
+	.buf_finish = buffer_finish,
+	.buf_queue    = buffer_queue,
+	.wait_prepare = vb2_ops_wait_prepare,
+	.wait_finish = vb2_ops_wait_finish,
+	.start_streaming = cx23885_start_streaming,
+	.stop_streaming = cx23885_stop_streaming,
 };
 
 static struct s5h1409_config hauppauge_generic_config = {
@@ -551,6 +587,35 @@ static int p8000_set_voltage(struct dvb_frontend *fe, fe_sec_voltage_t voltage)
 	return 0;
 }
 
+static int dvbsky_t9580_set_voltage(struct dvb_frontend *fe,
+					fe_sec_voltage_t voltage)
+{
+	struct cx23885_tsport *port = fe->dvb->priv;
+	struct cx23885_dev *dev = port->dev;
+
+	cx23885_gpio_enable(dev, GPIO_0 | GPIO_1, 1);
+
+	switch (voltage) {
+	case SEC_VOLTAGE_13:
+		cx23885_gpio_set(dev, GPIO_1);
+		cx23885_gpio_clear(dev, GPIO_0);
+		break;
+	case SEC_VOLTAGE_18:
+		cx23885_gpio_set(dev, GPIO_1);
+		cx23885_gpio_set(dev, GPIO_0);
+		break;
+	case SEC_VOLTAGE_OFF:
+		cx23885_gpio_clear(dev, GPIO_1);
+		cx23885_gpio_clear(dev, GPIO_0);
+		break;
+	}
+
+	/* call the frontend set_voltage function */
+	port->fe_set_voltage(fe, voltage);
+
+	return 0;
+}
+
 static int cx23885_dvb_set_frontend(struct dvb_frontend *fe)
 {
 	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
@@ -715,6 +780,19 @@ static const struct si2165_config hauppauge_hvr4400_si2165_config = {
 	.ref_freq_Hz	= 16000000,
 };
 
+static const struct m88ds3103_config dvbsky_t9580_m88ds3103_config = {
+	.i2c_addr = 0x68,
+	.clock = 27000000,
+	.i2c_wr_max = 33,
+	.clock_out = 0,
+	.ts_mode = M88DS3103_TS_PARALLEL,
+	.ts_clk = 16000,
+	.ts_clk_pol = 1,
+	.lnb_en_pol = 1,
+	.lnb_hv_pol = 0,
+	.agc = 0x99,
+};
+
 static int netup_altera_fpga_rw(void *device, int flag, int data, int read)
 {
 	struct cx23885_dev *dev = (struct cx23885_dev *)device;
@@ -863,16 +941,23 @@ static int dvb_register(struct cx23885_tsport *port)
 	struct dib7000p_ops dib7000p_ops;
 	struct cx23885_dev *dev = port->dev;
 	struct cx23885_i2c *i2c_bus = NULL, *i2c_bus2 = NULL;
-	struct videobuf_dvb_frontend *fe0, *fe1 = NULL;
+	struct vb2_dvb_frontend *fe0, *fe1 = NULL;
+	struct si2168_config si2168_config;
+	struct si2157_config si2157_config;
+	struct m88ts2022_config m88ts2022_config;
+	struct i2c_board_info info;
+	struct i2c_adapter *adapter;
+	struct i2c_client *client_demod;
+	struct i2c_client *client_tuner;
 	int mfe_shared = 0; /* bus not shared by default */
 	int ret;
 
 	/* Get the first frontend */
-	fe0 = videobuf_dvb_get_frontend(&port->frontends, 1);
+	fe0 = vb2_dvb_get_frontend(&port->frontends, 1);
 	if (!fe0)
 		return -EINVAL;
 
-	/* init struct videobuf_dvb */
+	/* init struct vb2_dvb */
 	fe0->dvb.name = dev->name;
 
 	/* multi-frontend gate control is undefined or defaults to fe0 */
@@ -1392,7 +1477,7 @@ static int dvb_register(struct cx23885_tsport *port)
 			fe0->dvb.frontend->ops.tuner_ops.init(fe0->dvb.frontend);
 		}
 		/* MFE frontend 2 */
-		fe1 = videobuf_dvb_get_frontend(&port->frontends, 2);
+		fe1 = vb2_dvb_get_frontend(&port->frontends, 2);
 		if (fe1 == NULL)
 			goto frontend_detach;
 		/* DVB-C init */
@@ -1491,7 +1576,7 @@ static int dvb_register(struct cx23885_tsport *port)
 					&hauppauge_hvr4400_si2165_config,
 					&i2c_bus->i2c_adap);
 			if (fe0->dvb.frontend != NULL) {
-				fe0->dvb.frontend->ops.i2c_gate_ctrl = 0;
+				fe0->dvb.frontend->ops.i2c_gate_ctrl = NULL;
 				if (!dvb_attach(tda18271_attach,
 						fe0->dvb.frontend,
 						0x60, &i2c_bus2->i2c_adap,
@@ -1501,6 +1586,97 @@ static int dvb_register(struct cx23885_tsport *port)
 			break;
 		}
 		break;
+	case CX23885_BOARD_DVBSKY_T9580:
+		i2c_bus = &dev->i2c_bus[0];
+		i2c_bus2 = &dev->i2c_bus[1];
+		switch (port->nr) {
+		/* port b - satellite */
+		case 1:
+			/* attach frontend */
+			fe0->dvb.frontend = dvb_attach(m88ds3103_attach,
+					&dvbsky_t9580_m88ds3103_config,
+					&i2c_bus2->i2c_adap, &adapter);
+			if (fe0->dvb.frontend == NULL)
+				break;
+
+			/* attach tuner */
+			m88ts2022_config.fe = fe0->dvb.frontend;
+			m88ts2022_config.clock = 27000000;
+			memset(&info, 0, sizeof(struct i2c_board_info));
+			strlcpy(info.type, "m88ts2022", I2C_NAME_SIZE);
+			info.addr = 0x60;
+			info.platform_data = &m88ts2022_config;
+			request_module(info.type);
+			client_tuner = i2c_new_device(adapter, &info);
+			if (client_tuner == NULL ||
+					client_tuner->dev.driver == NULL)
+				goto frontend_detach;
+			if (!try_module_get(client_tuner->dev.driver->owner)) {
+				i2c_unregister_device(client_tuner);
+				goto frontend_detach;
+			}
+
+			/* delegate signal strength measurement to tuner */
+			fe0->dvb.frontend->ops.read_signal_strength =
+				fe0->dvb.frontend->ops.tuner_ops.get_rf_strength;
+
+			/*
+			 * for setting the voltage we need to set GPIOs on
+			 * the card.
+			 */
+			port->fe_set_voltage =
+				fe0->dvb.frontend->ops.set_voltage;
+			fe0->dvb.frontend->ops.set_voltage =
+				dvbsky_t9580_set_voltage;
+
+			port->i2c_client_tuner = client_tuner;
+
+			break;
+		/* port c - terrestrial/cable */
+		case 2:
+			/* attach frontend */
+			si2168_config.i2c_adapter = &adapter;
+			si2168_config.fe = &fe0->dvb.frontend;
+			si2168_config.ts_mode = SI2168_TS_SERIAL;
+			memset(&info, 0, sizeof(struct i2c_board_info));
+			strlcpy(info.type, "si2168", I2C_NAME_SIZE);
+			info.addr = 0x64;
+			info.platform_data = &si2168_config;
+			request_module(info.type);
+			client_demod = i2c_new_device(&i2c_bus->i2c_adap, &info);
+			if (client_demod == NULL ||
+					client_demod->dev.driver == NULL)
+				goto frontend_detach;
+			if (!try_module_get(client_demod->dev.driver->owner)) {
+				i2c_unregister_device(client_demod);
+				goto frontend_detach;
+			}
+			port->i2c_client_demod = client_demod;
+
+			/* attach tuner */
+			si2157_config.fe = fe0->dvb.frontend;
+			memset(&info, 0, sizeof(struct i2c_board_info));
+			strlcpy(info.type, "si2157", I2C_NAME_SIZE);
+			info.addr = 0x60;
+			info.platform_data = &si2157_config;
+			request_module(info.type);
+			client_tuner = i2c_new_device(adapter, &info);
+			if (client_tuner == NULL ||
+					client_tuner->dev.driver == NULL) {
+				module_put(client_demod->dev.driver->owner);
+				i2c_unregister_device(client_demod);
+				goto frontend_detach;
+			}
+			if (!try_module_get(client_tuner->dev.driver->owner)) {
+				i2c_unregister_device(client_tuner);
+				module_put(client_demod->dev.driver->owner);
+				i2c_unregister_device(client_demod);
+				goto frontend_detach;
+			}
+			port->i2c_client_tuner = client_tuner;
+			break;
+		}
+		break;
 	default:
 		printk(KERN_INFO "%s: The frontend of your DVB/ATSC card "
 			" isn't supported yet\n",
@@ -1532,7 +1708,7 @@ static int dvb_register(struct cx23885_tsport *port)
 		fe0->dvb.frontend->ops.analog_ops.standby(fe0->dvb.frontend);
 
 	/* register everything */
-	ret = videobuf_dvb_register_bus(&port->frontends, THIS_MODULE, port,
+	ret = vb2_dvb_register_bus(&port->frontends, THIS_MODULE, port,
 					&dev->pci->dev, adapter_nr, mfe_shared);
 	if (ret)
 		goto frontend_detach;
@@ -1575,20 +1751,36 @@ static int dvb_register(struct cx23885_tsport *port)
 		memcpy(port->frontends.adapter.proposed_mac, eeprom + 0xa0, 6);
 		break;
 		}
+	case CX23885_BOARD_DVBSKY_T9580: {
+		u8 eeprom[256]; /* 24C02 i2c eeprom */
+
+		if (port->nr > 2)
+			break;
+
+		/* Read entire EEPROM */
+		dev->i2c_bus[0].i2c_client.addr = 0xa0 >> 1;
+		tveeprom_read(&dev->i2c_bus[0].i2c_client, eeprom,
+				sizeof(eeprom));
+		printk(KERN_INFO "DVBSky T9580 port %d MAC address: %pM\n",
+			port->nr, eeprom + 0xc0 + (port->nr-1) * 8);
+		memcpy(port->frontends.adapter.proposed_mac, eeprom + 0xc0 +
+			(port->nr-1) * 8, 6);
+		break;
+		}
 	}
 
 	return ret;
 
 frontend_detach:
 	port->gate_ctrl = NULL;
-	videobuf_dvb_dealloc_frontends(&port->frontends);
+	vb2_dvb_dealloc_frontends(&port->frontends);
 	return -EINVAL;
 }
 
 int cx23885_dvb_register(struct cx23885_tsport *port)
 {
 
-	struct videobuf_dvb_frontend *fe0;
+	struct vb2_dvb_frontend *fe0;
 	struct cx23885_dev *dev = port->dev;
 	int err, i;
 
@@ -1605,13 +1797,15 @@ int cx23885_dvb_register(struct cx23885_tsport *port)
 		port->num_frontends);
 
 	for (i = 1; i <= port->num_frontends; i++) {
-		if (videobuf_dvb_alloc_frontend(
+		struct vb2_queue *q;
+
+		if (vb2_dvb_alloc_frontend(
 			&port->frontends, i) == NULL) {
 			printk(KERN_ERR "%s() failed to alloc\n", __func__);
 			return -ENOMEM;
 		}
 
-		fe0 = videobuf_dvb_get_frontend(&port->frontends, i);
+		fe0 = vb2_dvb_get_frontend(&port->frontends, i);
 		if (!fe0)
 			err = -EINVAL;
 
@@ -1627,10 +1821,21 @@ int cx23885_dvb_register(struct cx23885_tsport *port)
 		/* dvb stuff */
 		/* We have to init the queue for each frontend on a port. */
 		printk(KERN_INFO "%s: cx23885 based dvb card\n", dev->name);
-		videobuf_queue_sg_init(&fe0->dvb.dvbq, &dvb_qops,
-			    &dev->pci->dev, &port->slock,
-			    V4L2_BUF_TYPE_VIDEO_CAPTURE, V4L2_FIELD_TOP,
-			    sizeof(struct cx23885_buffer), port, NULL);
+		q = &fe0->dvb.dvbq;
+		q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+		q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
+		q->gfp_flags = GFP_DMA32;
+		q->min_buffers_needed = 2;
+		q->drv_priv = port;
+		q->buf_struct_size = sizeof(struct cx23885_buffer);
+		q->ops = &dvb_qops;
+		q->mem_ops = &vb2_dma_sg_memops;
+		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+		q->lock = &dev->lock;
+
+		err = vb2_queue_init(q);
+		if (err < 0)
+			return err;
 	}
 	err = dvb_register(port);
 	if (err != 0)
@@ -1642,18 +1847,27 @@ int cx23885_dvb_register(struct cx23885_tsport *port)
 
 int cx23885_dvb_unregister(struct cx23885_tsport *port)
 {
-	struct videobuf_dvb_frontend *fe0;
-
-	/* FIXME: in an error condition where the we have
-	 * an expected number of frontends (attach problem)
-	 * then this might not clean up correctly, if 1
-	 * is invalid.
-	 * This comment only applies to future boards IF they
-	 * implement MFE support.
-	 */
-	fe0 = videobuf_dvb_get_frontend(&port->frontends, 1);
+	struct vb2_dvb_frontend *fe0;
+	struct i2c_client *client;
+
+	/* remove I2C client for tuner */
+	client = port->i2c_client_tuner;
+	if (client) {
+		module_put(client->dev.driver->owner);
+		i2c_unregister_device(client);
+	}
+
+	/* remove I2C client for demodulator */
+	client = port->i2c_client_demod;
+	if (client) {
+		module_put(client->dev.driver->owner);
+		i2c_unregister_device(client);
+	}
+
+	fe0 = vb2_dvb_get_frontend(&port->frontends, 1);
+
 	if (fe0 && fe0->dvb.frontend)
-		videobuf_dvb_unregister_bus(&port->frontends);
+		vb2_dvb_unregister_bus(&port->frontends);
 
 	switch (port->dev->board) {
 	case CX23885_BOARD_NETUP_DUAL_DVBS2_CI:
@@ -1668,4 +1882,3 @@ int cx23885_dvb_unregister(struct cx23885_tsport *port)
 
 	return 0;
 }
-
diff --git a/drivers/media/pci/cx23885/cx23885-f300.c b/drivers/media/pci/cx23885/cx23885-f300.c
index 5444cc526008..6f817d8732da 100644
--- a/drivers/media/pci/cx23885/cx23885-f300.c
+++ b/drivers/media/pci/cx23885/cx23885-f300.c
@@ -22,10 +22,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include "cx23885.h"
diff --git a/drivers/media/pci/cx23885/cx23885-i2c.c b/drivers/media/pci/cx23885/cx23885-i2c.c
index 4887314339cb..fd71306af6e2 100644
--- a/drivers/media/pci/cx23885/cx23885-i2c.c
+++ b/drivers/media/pci/cx23885/cx23885-i2c.c
@@ -13,10 +13,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/module.h>
@@ -386,11 +382,3 @@ void cx23885_av_clk(struct cx23885_dev *dev, int enable)
 
 	i2c_xfer(&dev->i2c_bus[2].i2c_adap, &msg, 1);
 }
-
-/* ----------------------------------------------------------------------- */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/pci/cx23885/cx23885-input.c b/drivers/media/pci/cx23885/cx23885-input.c
index 1940c18e186c..9d37fe661691 100644
--- a/drivers/media/pci/cx23885/cx23885-input.c
+++ b/drivers/media/pci/cx23885/cx23885-input.c
@@ -28,11 +28,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- *  02110-1301, USA.
  */
 
 #include <linux/slab.h>
diff --git a/drivers/media/pci/cx23885/cx23885-input.h b/drivers/media/pci/cx23885/cx23885-input.h
index 87dc44e69977..6199c7e86e83 100644
--- a/drivers/media/pci/cx23885/cx23885-input.h
+++ b/drivers/media/pci/cx23885/cx23885-input.h
@@ -14,11 +14,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- *  02110-1301, USA.
  */
 
 #ifndef _CX23885_INPUT_H_
diff --git a/drivers/media/pci/cx23885/cx23885-ioctl.c b/drivers/media/pci/cx23885/cx23885-ioctl.c
index 271d69d1ca8c..d2cdd40f79f5 100644
--- a/drivers/media/pci/cx23885/cx23885-ioctl.c
+++ b/drivers/media/pci/cx23885/cx23885-ioctl.c
@@ -15,10 +15,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include "cx23885.h"
@@ -28,7 +24,7 @@
 int cx23885_g_chip_info(struct file *file, void *fh,
 			 struct v4l2_dbg_chip_info *chip)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)fh)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	if (chip->match.addr > 1)
 		return -EINVAL;
@@ -64,7 +60,7 @@ static int cx23417_g_register(struct cx23885_dev *dev,
 int cx23885_g_register(struct file *file, void *fh,
 		       struct v4l2_dbg_register *reg)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)fh)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	if (reg->match.addr > 1)
 		return -EINVAL;
@@ -96,7 +92,7 @@ static int cx23417_s_register(struct cx23885_dev *dev,
 int cx23885_s_register(struct file *file, void *fh,
 		       const struct v4l2_dbg_register *reg)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)fh)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	if (reg->match.addr > 1)
 		return -EINVAL;
diff --git a/drivers/media/pci/cx23885/cx23885-ioctl.h b/drivers/media/pci/cx23885/cx23885-ioctl.h
index 92d9f0774366..cc5dbb6c1afc 100644
--- a/drivers/media/pci/cx23885/cx23885-ioctl.h
+++ b/drivers/media/pci/cx23885/cx23885-ioctl.h
@@ -15,10 +15,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef _CX23885_IOCTL_H_
diff --git a/drivers/media/pci/cx23885/cx23885-ir.c b/drivers/media/pci/cx23885/cx23885-ir.c
index bfef19359291..89dc4cc3e1ce 100644
--- a/drivers/media/pci/cx23885/cx23885-ir.c
+++ b/drivers/media/pci/cx23885/cx23885-ir.c
@@ -14,11 +14,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- *  02110-1301, USA.
  */
 
 #include <media/v4l2-device.h>
diff --git a/drivers/media/pci/cx23885/cx23885-ir.h b/drivers/media/pci/cx23885/cx23885-ir.h
index 0c9d8bda9e28..8e93d1f10ae0 100644
--- a/drivers/media/pci/cx23885/cx23885-ir.h
+++ b/drivers/media/pci/cx23885/cx23885-ir.h
@@ -14,11 +14,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- *  02110-1301, USA.
  */
 
 #ifndef _CX23885_IR_H_
diff --git a/drivers/media/pci/cx23885/cx23885-reg.h b/drivers/media/pci/cx23885/cx23885-reg.h
index a99936e0cbc2..2d3cbafe2402 100644
--- a/drivers/media/pci/cx23885/cx23885-reg.h
+++ b/drivers/media/pci/cx23885/cx23885-reg.h
@@ -13,10 +13,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef _CX23885_REG_H_
diff --git a/drivers/media/pci/cx23885/cx23885-vbi.c b/drivers/media/pci/cx23885/cx23885-vbi.c
index a1154f035bc1..a7c6ef8f3ea3 100644
--- a/drivers/media/pci/cx23885/cx23885-vbi.c
+++ b/drivers/media/pci/cx23885/cx23885-vbi.c
@@ -13,10 +13,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/kernel.h>
@@ -42,33 +38,32 @@ MODULE_PARM_DESC(vbi_debug, "enable debug messages [vbi]");
 /* ------------------------------------------------------------------ */
 
 #define VBI_LINE_LENGTH 1440
-#define NTSC_VBI_START_LINE 10        /* line 10 - 21 */
-#define NTSC_VBI_END_LINE   21
-#define NTSC_VBI_LINES      (NTSC_VBI_END_LINE - NTSC_VBI_START_LINE + 1)
+#define VBI_NTSC_LINE_COUNT 12
+#define VBI_PAL_LINE_COUNT 18
 
 
 int cx23885_vbi_fmt(struct file *file, void *priv,
 	struct v4l2_format *f)
 {
-	struct cx23885_fh *fh = priv;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
+	f->fmt.vbi.sampling_rate = 27000000;
+	f->fmt.vbi.samples_per_line = VBI_LINE_LENGTH;
+	f->fmt.vbi.sample_format = V4L2_PIX_FMT_GREY;
+	f->fmt.vbi.offset = 0;
+	f->fmt.vbi.flags = 0;
 	if (dev->tvnorm & V4L2_STD_525_60) {
 		/* ntsc */
-		f->fmt.vbi.samples_per_line = VBI_LINE_LENGTH;
-		f->fmt.vbi.sampling_rate = 27000000;
-		f->fmt.vbi.sample_format = V4L2_PIX_FMT_GREY;
-		f->fmt.vbi.offset = 0;
-		f->fmt.vbi.flags = 0;
-		f->fmt.vbi.start[0] = 10;
-		f->fmt.vbi.count[0] = 17;
-		f->fmt.vbi.start[1] = 263 + 10 + 1;
-		f->fmt.vbi.count[1] = 17;
+		f->fmt.vbi.start[0] = V4L2_VBI_ITU_525_F1_START + 9;
+		f->fmt.vbi.start[1] = V4L2_VBI_ITU_525_F2_START + 9;
+		f->fmt.vbi.count[0] = VBI_NTSC_LINE_COUNT;
+		f->fmt.vbi.count[1] = VBI_NTSC_LINE_COUNT;
 	} else if (dev->tvnorm & V4L2_STD_625_50) {
 		/* pal */
-		f->fmt.vbi.sampling_rate = 35468950;
-		f->fmt.vbi.start[0] = 7 - 1;
-		f->fmt.vbi.start[1] = 319 - 1;
+		f->fmt.vbi.start[0] = V4L2_VBI_ITU_625_F1_START + 5;
+		f->fmt.vbi.start[1] = V4L2_VBI_ITU_625_F2_START + 5;
+		f->fmt.vbi.count[0] = VBI_PAL_LINE_COUNT;
+		f->fmt.vbi.count[1] = VBI_PAL_LINE_COUNT;
 	}
 
 	return 0;
@@ -94,15 +89,6 @@ int cx23885_vbi_irq(struct cx23885_dev *dev, u32 status)
 		handled++;
 	}
 
-	if (status & VID_BC_MSK_VBI_RISCI2) {
-		dprintk(1, "%s() VID_BC_MSK_VBI_RISCI2\n", __func__);
-		dprintk(2, "stopper vbi\n");
-		spin_lock(&dev->slock);
-		cx23885_restart_vbi_queue(dev, &dev->vbiq);
-		spin_unlock(&dev->slock);
-		handled++;
-	}
-
 	return handled;
 }
 
@@ -114,13 +100,13 @@ static int cx23885_start_vbi_dma(struct cx23885_dev    *dev,
 
 	/* setup fifo + format */
 	cx23885_sram_channel_setup(dev, &dev->sram_channels[SRAM_CH02],
-				buf->vb.width, buf->risc.dma);
+				VBI_LINE_LENGTH, buf->risc.dma);
 
 	/* reset counter */
 	cx_write(VID_A_GPCNT_CTL, 3);
 	cx_write(VID_A_VBI_CTRL, 3);
 	cx_write(VBI_A_GPCNT_CTL, 3);
-	q->count = 1;
+	q->count = 0;
 
 	/* enable irq */
 	cx23885_irq_add_enable(dev, 0x01);
@@ -133,163 +119,153 @@ static int cx23885_start_vbi_dma(struct cx23885_dev    *dev,
 	return 0;
 }
 
+/* ------------------------------------------------------------------ */
 
-int cx23885_restart_vbi_queue(struct cx23885_dev    *dev,
-			     struct cx23885_dmaqueue *q)
+static int queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
+			   unsigned int *num_buffers, unsigned int *num_planes,
+			   unsigned int sizes[], void *alloc_ctxs[])
 {
-	struct cx23885_buffer *buf;
-	struct list_head *item;
-
-	if (list_empty(&q->active))
-		return 0;
-
-	buf = list_entry(q->active.next, struct cx23885_buffer, vb.queue);
-	dprintk(2, "restart_queue [%p/%d]: restart dma\n",
-		buf, buf->vb.i);
-	cx23885_start_vbi_dma(dev, q, buf);
-	list_for_each(item, &q->active) {
-		buf = list_entry(item, struct cx23885_buffer, vb.queue);
-		buf->count = q->count++;
-	}
-	mod_timer(&q->timeout, jiffies + (BUFFER_TIMEOUT / 30));
+	struct cx23885_dev *dev = q->drv_priv;
+	unsigned lines = VBI_PAL_LINE_COUNT;
+
+	if (dev->tvnorm & V4L2_STD_525_60)
+		lines = VBI_NTSC_LINE_COUNT;
+	*num_planes = 1;
+	sizes[0] = lines * VBI_LINE_LENGTH * 2;
 	return 0;
 }
 
-void cx23885_vbi_timeout(unsigned long data)
+static int buffer_prepare(struct vb2_buffer *vb)
 {
-	struct cx23885_dev *dev = (struct cx23885_dev *)data;
-	struct cx23885_dmaqueue *q = &dev->vbiq;
-	struct cx23885_buffer *buf;
-	unsigned long flags;
+	struct cx23885_dev *dev = vb->vb2_queue->drv_priv;
+	struct cx23885_buffer *buf = container_of(vb,
+		struct cx23885_buffer, vb);
+	struct sg_table *sgt = vb2_dma_sg_plane_desc(vb, 0);
+	unsigned lines = VBI_PAL_LINE_COUNT;
+	int ret;
 
-	/* Stop the VBI engine */
-	cx_clear(VID_A_DMA_CTL, 0x22);
+	if (dev->tvnorm & V4L2_STD_525_60)
+		lines = VBI_NTSC_LINE_COUNT;
 
-	spin_lock_irqsave(&dev->slock, flags);
-	while (!list_empty(&q->active)) {
-		buf = list_entry(q->active.next, struct cx23885_buffer,
-			vb.queue);
-		list_del(&buf->vb.queue);
-		buf->vb.state = VIDEOBUF_ERROR;
-		wake_up(&buf->vb.done);
-		printk("%s/0: [%p/%d] timeout - dma=0x%08lx\n", dev->name,
-		       buf, buf->vb.i, (unsigned long)buf->risc.dma);
-	}
-	cx23885_restart_vbi_queue(dev, q);
-	spin_unlock_irqrestore(&dev->slock, flags);
-}
+	if (vb2_plane_size(vb, 0) < lines * VBI_LINE_LENGTH * 2)
+		return -EINVAL;
+	vb2_set_plane_payload(vb, 0, lines * VBI_LINE_LENGTH * 2);
 
-/* ------------------------------------------------------------------ */
-#define VBI_LINE_LENGTH 1440
-#define VBI_LINE_COUNT 17
+	ret = dma_map_sg(&dev->pci->dev, sgt->sgl, sgt->nents, DMA_FROM_DEVICE);
+	if (!ret)
+		return -EIO;
 
-static int
-vbi_setup(struct videobuf_queue *q, unsigned int *count, unsigned int *size)
-{
-	*size = VBI_LINE_COUNT * VBI_LINE_LENGTH * 2;
-	if (0 == *count)
-		*count = vbibufs;
-	if (*count < 2)
-		*count = 2;
-	if (*count > 32)
-		*count = 32;
+	cx23885_risc_vbibuffer(dev->pci, &buf->risc,
+			 sgt->sgl,
+			 0, VBI_LINE_LENGTH * lines,
+			 VBI_LINE_LENGTH, 0,
+			 lines);
 	return 0;
 }
 
-static int
-vbi_prepare(struct videobuf_queue *q, struct videobuf_buffer *vb,
-	    enum v4l2_field field)
+static void buffer_finish(struct vb2_buffer *vb)
 {
-	struct cx23885_fh *fh  = q->priv_data;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = vb->vb2_queue->drv_priv;
 	struct cx23885_buffer *buf = container_of(vb,
 		struct cx23885_buffer, vb);
-	struct videobuf_dmabuf *dma = videobuf_to_dma(&buf->vb);
-	unsigned int size;
-	int rc;
-
-	size = VBI_LINE_COUNT * VBI_LINE_LENGTH * 2;
-	if (0 != buf->vb.baddr  &&  buf->vb.bsize < size)
-		return -EINVAL;
+	struct sg_table *sgt = vb2_dma_sg_plane_desc(vb, 0);
 
-	if (VIDEOBUF_NEEDS_INIT == buf->vb.state) {
-		buf->vb.width  = VBI_LINE_LENGTH;
-		buf->vb.height = VBI_LINE_COUNT;
-		buf->vb.size   = size;
-		buf->vb.field  = V4L2_FIELD_SEQ_TB;
-
-		rc = videobuf_iolock(q, &buf->vb, NULL);
-		if (0 != rc)
-			goto fail;
-		cx23885_risc_vbibuffer(dev->pci, &buf->risc,
-				 dma->sglist,
-				 0, buf->vb.width * buf->vb.height,
-				 buf->vb.width, 0,
-				 buf->vb.height);
-	}
-	buf->vb.state = VIDEOBUF_PREPARED;
-	return 0;
+	cx23885_free_buffer(vb->vb2_queue->drv_priv, buf);
 
- fail:
-	cx23885_free_buffer(q, buf);
-	return rc;
+	dma_unmap_sg(&dev->pci->dev, sgt->sgl, sgt->nents, DMA_FROM_DEVICE);
 }
 
-static void
-vbi_queue(struct videobuf_queue *vq, struct videobuf_buffer *vb)
+/*
+ * The risc program for each buffer works as follows: it starts with a simple
+ * 'JUMP to addr + 12', which is effectively a NOP. Then the code to DMA the
+ * buffer follows and at the end we have a JUMP back to the start + 12 (skipping
+ * the initial JUMP).
+ *
+ * This is the risc program of the first buffer to be queued if the active list
+ * is empty and it just keeps DMAing this buffer without generating any
+ * interrupts.
+ *
+ * If a new buffer is added then the initial JUMP in the code for that buffer
+ * will generate an interrupt which signals that the previous buffer has been
+ * DMAed successfully and that it can be returned to userspace.
+ *
+ * It also sets the final jump of the previous buffer to the start of the new
+ * buffer, thus chaining the new buffer into the DMA chain. This is a single
+ * atomic u32 write, so there is no race condition.
+ *
+ * The end-result of all this that you only get an interrupt when a buffer
+ * is ready, so the control flow is very easy.
+ */
+static void buffer_queue(struct vb2_buffer *vb)
 {
-	struct cx23885_buffer   *buf =
-		container_of(vb, struct cx23885_buffer, vb);
-	struct cx23885_buffer   *prev;
-	struct cx23885_fh       *fh   = vq->priv_data;
-	struct cx23885_dev      *dev  = fh->dev;
-	struct cx23885_dmaqueue *q    = &dev->vbiq;
-
-	/* add jump to stopper */
-	buf->risc.jmp[0] = cpu_to_le32(RISC_JUMP | RISC_IRQ1 | RISC_CNT_INC);
-	buf->risc.jmp[1] = cpu_to_le32(q->stopper.dma);
+	struct cx23885_dev *dev = vb->vb2_queue->drv_priv;
+	struct cx23885_buffer *buf = container_of(vb, struct cx23885_buffer, vb);
+	struct cx23885_buffer *prev;
+	struct cx23885_dmaqueue *q = &dev->vbiq;
+	unsigned long flags;
+
+	buf->risc.cpu[1] = cpu_to_le32(buf->risc.dma + 12);
+	buf->risc.jmp[0] = cpu_to_le32(RISC_JUMP | RISC_CNT_INC);
+	buf->risc.jmp[1] = cpu_to_le32(buf->risc.dma + 12);
 	buf->risc.jmp[2] = cpu_to_le32(0); /* bits 63-32 */
 
 	if (list_empty(&q->active)) {
-		list_add_tail(&buf->vb.queue, &q->active);
-		cx23885_start_vbi_dma(dev, q, buf);
-		buf->vb.state = VIDEOBUF_ACTIVE;
-		buf->count    = q->count++;
-		mod_timer(&q->timeout, jiffies + (BUFFER_TIMEOUT / 30));
+		spin_lock_irqsave(&dev->slock, flags);
+		list_add_tail(&buf->queue, &q->active);
+		spin_unlock_irqrestore(&dev->slock, flags);
 		dprintk(2, "[%p/%d] vbi_queue - first active\n",
-			buf, buf->vb.i);
+			buf, buf->vb.v4l2_buf.index);
 
 	} else {
+		buf->risc.cpu[0] |= cpu_to_le32(RISC_IRQ1);
 		prev = list_entry(q->active.prev, struct cx23885_buffer,
-			vb.queue);
-		list_add_tail(&buf->vb.queue, &q->active);
-		buf->vb.state = VIDEOBUF_ACTIVE;
-		buf->count    = q->count++;
+			queue);
+		spin_lock_irqsave(&dev->slock, flags);
+		list_add_tail(&buf->queue, &q->active);
+		spin_unlock_irqrestore(&dev->slock, flags);
 		prev->risc.jmp[1] = cpu_to_le32(buf->risc.dma);
-		prev->risc.jmp[2] = cpu_to_le32(0); /* Bits 63-32 */
 		dprintk(2, "[%p/%d] buffer_queue - append to active\n",
-			buf, buf->vb.i);
+			buf, buf->vb.v4l2_buf.index);
 	}
 }
 
-static void vbi_release(struct videobuf_queue *q, struct videobuf_buffer *vb)
+static int cx23885_start_streaming(struct vb2_queue *q, unsigned int count)
 {
-	struct cx23885_buffer *buf =
-		container_of(vb, struct cx23885_buffer, vb);
+	struct cx23885_dev *dev = q->drv_priv;
+	struct cx23885_dmaqueue *dmaq = &dev->vbiq;
+	struct cx23885_buffer *buf = list_entry(dmaq->active.next,
+			struct cx23885_buffer, queue);
 
-	cx23885_free_buffer(q, buf);
+	cx23885_start_vbi_dma(dev, dmaq, buf);
+	return 0;
 }
 
-struct videobuf_queue_ops cx23885_vbi_qops = {
-	.buf_setup    = vbi_setup,
-	.buf_prepare  = vbi_prepare,
-	.buf_queue    = vbi_queue,
-	.buf_release  = vbi_release,
-};
+static void cx23885_stop_streaming(struct vb2_queue *q)
+{
+	struct cx23885_dev *dev = q->drv_priv;
+	struct cx23885_dmaqueue *dmaq = &dev->vbiq;
+	unsigned long flags;
 
-/* ------------------------------------------------------------------ */
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
+	cx_clear(VID_A_DMA_CTL, 0x22); /* FIFO and RISC enable */
+	spin_lock_irqsave(&dev->slock, flags);
+	while (!list_empty(&dmaq->active)) {
+		struct cx23885_buffer *buf = list_entry(dmaq->active.next,
+			struct cx23885_buffer, queue);
+
+		list_del(&buf->queue);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+	}
+	spin_unlock_irqrestore(&dev->slock, flags);
+}
+
+
+struct vb2_ops cx23885_vbi_qops = {
+	.queue_setup    = queue_setup,
+	.buf_prepare  = buffer_prepare,
+	.buf_finish = buffer_finish,
+	.buf_queue    = buffer_queue,
+	.wait_prepare = vb2_ops_wait_prepare,
+	.wait_finish = vb2_ops_wait_finish,
+	.start_streaming = cx23885_start_streaming,
+	.stop_streaming = cx23885_stop_streaming,
+};
diff --git a/drivers/media/pci/cx23885/cx23885-video.c b/drivers/media/pci/cx23885/cx23885-video.c
index 91e4cb457296..682a4f95df6b 100644
--- a/drivers/media/pci/cx23885/cx23885-video.c
+++ b/drivers/media/pci/cx23885/cx23885-video.c
@@ -13,10 +13,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/init.h>
@@ -35,6 +31,7 @@
 #include "cx23885-video.h"
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
+#include <media/v4l2-event.h>
 #include "cx23885-ioctl.h"
 #include "tuner-xc2028.h"
 
@@ -48,15 +45,12 @@ MODULE_LICENSE("GPL");
 
 static unsigned int video_nr[] = {[0 ... (CX23885_MAXBOARDS - 1)] = UNSET };
 static unsigned int vbi_nr[]   = {[0 ... (CX23885_MAXBOARDS - 1)] = UNSET };
-static unsigned int radio_nr[] = {[0 ... (CX23885_MAXBOARDS - 1)] = UNSET };
 
 module_param_array(video_nr, int, NULL, 0444);
 module_param_array(vbi_nr,   int, NULL, 0444);
-module_param_array(radio_nr, int, NULL, 0444);
 
 MODULE_PARM_DESC(video_nr, "video device numbers");
 MODULE_PARM_DESC(vbi_nr, "vbi device numbers");
-MODULE_PARM_DESC(radio_nr, "radio device numbers");
 
 static unsigned int video_debug;
 module_param(video_debug, int, 0644);
@@ -79,77 +73,14 @@ MODULE_PARM_DESC(vid_limit, "capture memory limit in megabytes");
 /* static data                                                         */
 
 #define FORMAT_FLAGS_PACKED       0x01
-#if 0
-static struct cx23885_fmt formats[] = {
-	{
-		.name     = "8 bpp, gray",
-		.fourcc   = V4L2_PIX_FMT_GREY,
-		.depth    = 8,
-		.flags    = FORMAT_FLAGS_PACKED,
-	}, {
-		.name     = "15 bpp RGB, le",
-		.fourcc   = V4L2_PIX_FMT_RGB555,
-		.depth    = 16,
-		.flags    = FORMAT_FLAGS_PACKED,
-	}, {
-		.name     = "15 bpp RGB, be",
-		.fourcc   = V4L2_PIX_FMT_RGB555X,
-		.depth    = 16,
-		.flags    = FORMAT_FLAGS_PACKED,
-	}, {
-		.name     = "16 bpp RGB, le",
-		.fourcc   = V4L2_PIX_FMT_RGB565,
-		.depth    = 16,
-		.flags    = FORMAT_FLAGS_PACKED,
-	}, {
-		.name     = "16 bpp RGB, be",
-		.fourcc   = V4L2_PIX_FMT_RGB565X,
-		.depth    = 16,
-		.flags    = FORMAT_FLAGS_PACKED,
-	}, {
-		.name     = "24 bpp RGB, le",
-		.fourcc   = V4L2_PIX_FMT_BGR24,
-		.depth    = 24,
-		.flags    = FORMAT_FLAGS_PACKED,
-	}, {
-		.name     = "32 bpp RGB, le",
-		.fourcc   = V4L2_PIX_FMT_BGR32,
-		.depth    = 32,
-		.flags    = FORMAT_FLAGS_PACKED,
-	}, {
-		.name     = "32 bpp RGB, be",
-		.fourcc   = V4L2_PIX_FMT_RGB32,
-		.depth    = 32,
-		.flags    = FORMAT_FLAGS_PACKED,
-	}, {
-		.name     = "4:2:2, packed, YUYV",
-		.fourcc   = V4L2_PIX_FMT_YUYV,
-		.depth    = 16,
-		.flags    = FORMAT_FLAGS_PACKED,
-	}, {
-		.name     = "4:2:2, packed, UYVY",
-		.fourcc   = V4L2_PIX_FMT_UYVY,
-		.depth    = 16,
-		.flags    = FORMAT_FLAGS_PACKED,
-	},
-};
-#else
 static struct cx23885_fmt formats[] = {
 	{
-#if 0
-		.name     = "4:2:2, packed, UYVY",
-		.fourcc   = V4L2_PIX_FMT_UYVY,
-		.depth    = 16,
-		.flags    = FORMAT_FLAGS_PACKED,
-	}, {
-#endif
 		.name     = "4:2:2, packed, YUYV",
 		.fourcc   = V4L2_PIX_FMT_YUYV,
 		.depth    = 16,
 		.flags    = FORMAT_FLAGS_PACKED,
 	}
 };
-#endif
 
 static struct cx23885_fmt *format_by_fourcc(unsigned int fourcc)
 {
@@ -158,163 +89,27 @@ static struct cx23885_fmt *format_by_fourcc(unsigned int fourcc)
 	for (i = 0; i < ARRAY_SIZE(formats); i++)
 		if (formats[i].fourcc == fourcc)
 			return formats+i;
-
-	printk(KERN_ERR "%s(%c%c%c%c) NOT FOUND\n", __func__,
-		(fourcc & 0xff),
-		((fourcc >> 8) & 0xff),
-		((fourcc >> 16) & 0xff),
-		((fourcc >> 24) & 0xff)
-		);
 	return NULL;
 }
 
 /* ------------------------------------------------------------------- */
 
-static const struct v4l2_queryctrl no_ctl = {
-	.name  = "42",
-	.flags = V4L2_CTRL_FLAG_DISABLED,
-};
-
-static struct cx23885_ctrl cx23885_ctls[] = {
-	/* --- video --- */
-	{
-		.v = {
-			.id            = V4L2_CID_BRIGHTNESS,
-			.name          = "Brightness",
-			.minimum       = 0x00,
-			.maximum       = 0xff,
-			.step          = 1,
-			.default_value = 0x7f,
-			.type          = V4L2_CTRL_TYPE_INTEGER,
-		},
-		.off                   = 128,
-		.reg                   = LUMA_CTRL,
-		.mask                  = 0x00ff,
-		.shift                 = 0,
-	}, {
-		.v = {
-			.id            = V4L2_CID_CONTRAST,
-			.name          = "Contrast",
-			.minimum       = 0,
-			.maximum       = 0x7f,
-			.step          = 1,
-			.default_value = 0x3f,
-			.type          = V4L2_CTRL_TYPE_INTEGER,
-		},
-		.off                   = 0,
-		.reg                   = LUMA_CTRL,
-		.mask                  = 0xff00,
-		.shift                 = 8,
-	}, {
-		.v = {
-			.id            = V4L2_CID_HUE,
-			.name          = "Hue",
-			.minimum       = -127,
-			.maximum       = 128,
-			.step          = 1,
-			.default_value = 0x0,
-			.type          = V4L2_CTRL_TYPE_INTEGER,
-		},
-		.off                   = 128,
-		.reg                   = CHROMA_CTRL,
-		.mask                  = 0xff0000,
-		.shift                 = 16,
-	}, {
-		/* strictly, this only describes only U saturation.
-		 * V saturation is handled specially through code.
-		 */
-		.v = {
-			.id            = V4L2_CID_SATURATION,
-			.name          = "Saturation",
-			.minimum       = 0,
-			.maximum       = 0x7f,
-			.step          = 1,
-			.default_value = 0x3f,
-			.type          = V4L2_CTRL_TYPE_INTEGER,
-		},
-		.off                   = 0,
-		.reg                   = CHROMA_CTRL,
-		.mask                  = 0x00ff,
-		.shift                 = 0,
-	}, {
-	/* --- audio --- */
-		.v = {
-			.id            = V4L2_CID_AUDIO_MUTE,
-			.name          = "Mute",
-			.minimum       = 0,
-			.maximum       = 1,
-			.default_value = 1,
-			.type          = V4L2_CTRL_TYPE_BOOLEAN,
-		},
-		.reg                   = PATH1_CTL1,
-		.mask                  = (0x1f << 24),
-		.shift                 = 24,
-	}, {
-		.v = {
-			.id            = V4L2_CID_AUDIO_VOLUME,
-			.name          = "Volume",
-			.minimum       = 0,
-			.maximum       = 65535,
-			.step          = 65535 / 100,
-			.default_value = 65535,
-			.type          = V4L2_CTRL_TYPE_INTEGER,
-		},
-		.reg                   = PATH1_VOL_CTL,
-		.mask                  = 0xff,
-		.shift                 = 0,
-	}
-};
-static const int CX23885_CTLS = ARRAY_SIZE(cx23885_ctls);
-
-/* Must be sorted from low to high control ID! */
-static const u32 cx23885_user_ctrls[] = {
-	V4L2_CID_USER_CLASS,
-	V4L2_CID_BRIGHTNESS,
-	V4L2_CID_CONTRAST,
-	V4L2_CID_SATURATION,
-	V4L2_CID_HUE,
-	V4L2_CID_AUDIO_VOLUME,
-	V4L2_CID_AUDIO_MUTE,
-	0
-};
-
-static const u32 *ctrl_classes[] = {
-	cx23885_user_ctrls,
-	NULL
-};
-
 void cx23885_video_wakeup(struct cx23885_dev *dev,
 	struct cx23885_dmaqueue *q, u32 count)
 {
 	struct cx23885_buffer *buf;
-	int bc;
-
-	for (bc = 0;; bc++) {
-		if (list_empty(&q->active))
-			break;
-		buf = list_entry(q->active.next,
-				 struct cx23885_buffer, vb.queue);
-
-		/* count comes from the hw and is is 16bit wide --
-		 * this trick handles wrap-arounds correctly for
-		 * up to 32767 buffers in flight... */
-		if ((s16) (count - buf->count) < 0)
-			break;
-
-		v4l2_get_timestamp(&buf->vb.ts);
-		dprintk(2, "[%p/%d] wakeup reg=%d buf=%d\n", buf, buf->vb.i,
-			count, buf->count);
-		buf->vb.state = VIDEOBUF_DONE;
-		list_del(&buf->vb.queue);
-		wake_up(&buf->vb.done);
-	}
+
 	if (list_empty(&q->active))
-		del_timer(&q->timeout);
-	else
-		mod_timer(&q->timeout, jiffies+BUFFER_TIMEOUT);
-	if (bc != 1)
-		printk(KERN_ERR "%s: %d buffers handled (should be 1)\n",
-			__func__, bc);
+		return;
+	buf = list_entry(q->active.next,
+			struct cx23885_buffer, queue);
+
+	buf->vb.v4l2_buf.sequence = q->count++;
+	v4l2_get_timestamp(&buf->vb.v4l2_buf.timestamp);
+	dprintk(2, "[%p/%d] wakeup reg=%d buf=%d\n", buf, buf->vb.v4l2_buf.index,
+			count, q->count);
+	list_del(&buf->queue);
+	vb2_buffer_done(&buf->vb, VB2_BUF_STATE_DONE);
 }
 
 int cx23885_set_tvnorm(struct cx23885_dev *dev, v4l2_std_id norm)
@@ -324,6 +119,12 @@ int cx23885_set_tvnorm(struct cx23885_dev *dev, v4l2_std_id norm)
 		(unsigned int)norm,
 		v4l2_norm_to_name(norm));
 
+	if (dev->tvnorm != norm) {
+		if (vb2_is_busy(&dev->vb2_vidq) || vb2_is_busy(&dev->vb2_vbiq) ||
+		    vb2_is_busy(&dev->vb2_mpegq))
+			return -EBUSY;
+	}
+
 	dev->tvnorm = norm;
 
 	call_all(dev, video, s_std, norm);
@@ -345,79 +146,13 @@ static struct video_device *cx23885_vdev_init(struct cx23885_dev *dev,
 	*vfd = *template;
 	vfd->v4l2_dev = &dev->v4l2_dev;
 	vfd->release = video_device_release;
+	vfd->lock = &dev->lock;
 	snprintf(vfd->name, sizeof(vfd->name), "%s (%s)",
 		 cx23885_boards[dev->board].name, type);
 	video_set_drvdata(vfd, dev);
 	return vfd;
 }
 
-static int cx23885_ctrl_query(struct v4l2_queryctrl *qctrl)
-{
-	int i;
-
-	if (qctrl->id < V4L2_CID_BASE ||
-	    qctrl->id >= V4L2_CID_LASTP1)
-		return -EINVAL;
-	for (i = 0; i < CX23885_CTLS; i++)
-		if (cx23885_ctls[i].v.id == qctrl->id)
-			break;
-	if (i == CX23885_CTLS) {
-		*qctrl = no_ctl;
-		return 0;
-	}
-	*qctrl = cx23885_ctls[i].v;
-	return 0;
-}
-
-/* ------------------------------------------------------------------- */
-/* resource management                                                 */
-
-static int res_get(struct cx23885_dev *dev, struct cx23885_fh *fh,
-	unsigned int bit)
-{
-	dprintk(1, "%s()\n", __func__);
-	if (fh->resources & bit)
-		/* have it already allocated */
-		return 1;
-
-	/* is it free? */
-	mutex_lock(&dev->lock);
-	if (dev->resources & bit) {
-		/* no, someone else uses it */
-		mutex_unlock(&dev->lock);
-		return 0;
-	}
-	/* it's free, grab it */
-	fh->resources  |= bit;
-	dev->resources |= bit;
-	dprintk(1, "res: get %d\n", bit);
-	mutex_unlock(&dev->lock);
-	return 1;
-}
-
-static int res_check(struct cx23885_fh *fh, unsigned int bit)
-{
-	return fh->resources & bit;
-}
-
-static int res_locked(struct cx23885_dev *dev, unsigned int bit)
-{
-	return dev->resources & bit;
-}
-
-static void res_free(struct cx23885_dev *dev, struct cx23885_fh *fh,
-	unsigned int bits)
-{
-	BUG_ON((fh->resources & bits) != bits);
-	dprintk(1, "%s()\n", __func__);
-
-	mutex_lock(&dev->lock);
-	fh->resources  &= ~bits;
-	dev->resources &= ~bits;
-	dprintk(1, "res: put %d\n", bits);
-	mutex_unlock(&dev->lock);
-}
-
 int cx23885_flatiron_write(struct cx23885_dev *dev, u8 reg, u8 data)
 {
 	/* 8 bit registers, 8 bit values */
@@ -567,7 +302,7 @@ static int cx23885_start_video_dma(struct cx23885_dev *dev,
 
 	/* reset counter */
 	cx_write(VID_A_GPCNT_CTL, 3);
-	q->count = 1;
+	q->count = 0;
 
 	/* enable irq */
 	cx23885_irq_add_enable(dev, 0x01);
@@ -580,479 +315,206 @@ static int cx23885_start_video_dma(struct cx23885_dev *dev,
 	return 0;
 }
 
-
-static int cx23885_restart_video_queue(struct cx23885_dev *dev,
-			       struct cx23885_dmaqueue *q)
-{
-	struct cx23885_buffer *buf, *prev;
-	struct list_head *item;
-	dprintk(1, "%s()\n", __func__);
-
-	if (!list_empty(&q->active)) {
-		buf = list_entry(q->active.next, struct cx23885_buffer,
-			vb.queue);
-		dprintk(2, "restart_queue [%p/%d]: restart dma\n",
-			buf, buf->vb.i);
-		cx23885_start_video_dma(dev, q, buf);
-		list_for_each(item, &q->active) {
-			buf = list_entry(item, struct cx23885_buffer,
-				vb.queue);
-			buf->count    = q->count++;
-		}
-		mod_timer(&q->timeout, jiffies+BUFFER_TIMEOUT);
-		return 0;
-	}
-
-	prev = NULL;
-	for (;;) {
-		if (list_empty(&q->queued))
-			return 0;
-		buf = list_entry(q->queued.next, struct cx23885_buffer,
-			vb.queue);
-		if (NULL == prev) {
-			list_move_tail(&buf->vb.queue, &q->active);
-			cx23885_start_video_dma(dev, q, buf);
-			buf->vb.state = VIDEOBUF_ACTIVE;
-			buf->count    = q->count++;
-			mod_timer(&q->timeout, jiffies+BUFFER_TIMEOUT);
-			dprintk(2, "[%p/%d] restart_queue - first active\n",
-				buf, buf->vb.i);
-
-		} else if (prev->vb.width  == buf->vb.width  &&
-			   prev->vb.height == buf->vb.height &&
-			   prev->fmt       == buf->fmt) {
-			list_move_tail(&buf->vb.queue, &q->active);
-			buf->vb.state = VIDEOBUF_ACTIVE;
-			buf->count    = q->count++;
-			prev->risc.jmp[1] = cpu_to_le32(buf->risc.dma);
-			prev->risc.jmp[2] = cpu_to_le32(0); /* Bits 63 - 32 */
-			dprintk(2, "[%p/%d] restart_queue - move to active\n",
-				buf, buf->vb.i);
-		} else {
-			return 0;
-		}
-		prev = buf;
-	}
-}
-
-static int buffer_setup(struct videobuf_queue *q, unsigned int *count,
-	unsigned int *size)
+static int queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
+			   unsigned int *num_buffers, unsigned int *num_planes,
+			   unsigned int sizes[], void *alloc_ctxs[])
 {
-	struct cx23885_fh *fh = q->priv_data;
+	struct cx23885_dev *dev = q->drv_priv;
 
-	*size = fh->fmt->depth*fh->width*fh->height >> 3;
-	if (0 == *count)
-		*count = 32;
-	if (*size * *count > vid_limit * 1024 * 1024)
-		*count = (vid_limit * 1024 * 1024) / *size;
+	*num_planes = 1;
+	sizes[0] = (dev->fmt->depth * dev->width * dev->height) >> 3;
 	return 0;
 }
 
-static int buffer_prepare(struct videobuf_queue *q, struct videobuf_buffer *vb,
-	       enum v4l2_field field)
+static int buffer_prepare(struct vb2_buffer *vb)
 {
-	struct cx23885_fh *fh  = q->priv_data;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = vb->vb2_queue->drv_priv;
 	struct cx23885_buffer *buf =
 		container_of(vb, struct cx23885_buffer, vb);
-	int rc, init_buffer = 0;
 	u32 line0_offset, line1_offset;
-	struct videobuf_dmabuf *dma = videobuf_to_dma(&buf->vb);
+	struct sg_table *sgt = vb2_dma_sg_plane_desc(vb, 0);
 	int field_tff;
+	int ret;
 
-	BUG_ON(NULL == fh->fmt);
-	if (fh->width  < 48 || fh->width  > norm_maxw(dev->tvnorm) ||
-	    fh->height < 32 || fh->height > norm_maxh(dev->tvnorm))
-		return -EINVAL;
-	buf->vb.size = (fh->width * fh->height * fh->fmt->depth) >> 3;
-	if (0 != buf->vb.baddr  &&  buf->vb.bsize < buf->vb.size)
+	buf->bpl = (dev->width * dev->fmt->depth) >> 3;
+
+	if (vb2_plane_size(vb, 0) < dev->height * buf->bpl)
 		return -EINVAL;
+	vb2_set_plane_payload(vb, 0, dev->height * buf->bpl);
 
-	if (buf->fmt       != fh->fmt    ||
-	    buf->vb.width  != fh->width  ||
-	    buf->vb.height != fh->height ||
-	    buf->vb.field  != field) {
-		buf->fmt       = fh->fmt;
-		buf->vb.width  = fh->width;
-		buf->vb.height = fh->height;
-		buf->vb.field  = field;
-		init_buffer = 1;
-	}
+	ret = dma_map_sg(&dev->pci->dev, sgt->sgl, sgt->nents, DMA_FROM_DEVICE);
+	if (!ret)
+		return -EIO;
 
-	if (VIDEOBUF_NEEDS_INIT == buf->vb.state) {
-		init_buffer = 1;
-		rc = videobuf_iolock(q, &buf->vb, NULL);
-		if (0 != rc)
-			goto fail;
-	}
+	switch (dev->field) {
+	case V4L2_FIELD_TOP:
+		cx23885_risc_buffer(dev->pci, &buf->risc,
+				sgt->sgl, 0, UNSET,
+				buf->bpl, 0, dev->height);
+		break;
+	case V4L2_FIELD_BOTTOM:
+		cx23885_risc_buffer(dev->pci, &buf->risc,
+				sgt->sgl, UNSET, 0,
+				buf->bpl, 0, dev->height);
+		break;
+	case V4L2_FIELD_INTERLACED:
+		if (dev->tvnorm & V4L2_STD_525_60)
+			/* NTSC or  */
+			field_tff = 1;
+		else
+			field_tff = 0;
+
+		if (cx23885_boards[dev->board].force_bff)
+			/* PAL / SECAM OR 888 in NTSC MODE */
+			field_tff = 0;
 
-	if (init_buffer) {
-		buf->bpl = buf->vb.width * buf->fmt->depth >> 3;
-		switch (buf->vb.field) {
-		case V4L2_FIELD_TOP:
-			cx23885_risc_buffer(dev->pci, &buf->risc,
-					 dma->sglist, 0, UNSET,
-					 buf->bpl, 0, buf->vb.height);
-			break;
-		case V4L2_FIELD_BOTTOM:
-			cx23885_risc_buffer(dev->pci, &buf->risc,
-					 dma->sglist, UNSET, 0,
-					 buf->bpl, 0, buf->vb.height);
-			break;
-		case V4L2_FIELD_INTERLACED:
-			if (dev->tvnorm & V4L2_STD_NTSC)
-				/* NTSC or  */
-				field_tff = 1;
-			else
-				field_tff = 0;
-
-			if (cx23885_boards[dev->board].force_bff)
-				/* PAL / SECAM OR 888 in NTSC MODE */
-				field_tff = 0;
-
-			if (field_tff) {
-				/* cx25840 transmits NTSC bottom field first */
-				dprintk(1, "%s() Creating TFF/NTSC risc\n",
+		if (field_tff) {
+			/* cx25840 transmits NTSC bottom field first */
+			dprintk(1, "%s() Creating TFF/NTSC risc\n",
 					__func__);
-				line0_offset = buf->bpl;
-				line1_offset = 0;
-			} else {
-				/* All other formats are top field first */
-				dprintk(1, "%s() Creating BFF/PAL/SECAM risc\n",
+			line0_offset = buf->bpl;
+			line1_offset = 0;
+		} else {
+			/* All other formats are top field first */
+			dprintk(1, "%s() Creating BFF/PAL/SECAM risc\n",
 					__func__);
-				line0_offset = 0;
-				line1_offset = buf->bpl;
-			}
-			cx23885_risc_buffer(dev->pci, &buf->risc,
-					dma->sglist, line0_offset,
-					line1_offset,
-					buf->bpl, buf->bpl,
-					buf->vb.height >> 1);
-			break;
-		case V4L2_FIELD_SEQ_TB:
-			cx23885_risc_buffer(dev->pci, &buf->risc,
-					 dma->sglist,
-					 0, buf->bpl * (buf->vb.height >> 1),
-					 buf->bpl, 0,
-					 buf->vb.height >> 1);
-			break;
-		case V4L2_FIELD_SEQ_BT:
-			cx23885_risc_buffer(dev->pci, &buf->risc,
-					 dma->sglist,
-					 buf->bpl * (buf->vb.height >> 1), 0,
-					 buf->bpl, 0,
-					 buf->vb.height >> 1);
-			break;
-		default:
-			BUG();
+			line0_offset = 0;
+			line1_offset = buf->bpl;
 		}
+		cx23885_risc_buffer(dev->pci, &buf->risc,
+				sgt->sgl, line0_offset,
+				line1_offset,
+				buf->bpl, buf->bpl,
+				dev->height >> 1);
+		break;
+	case V4L2_FIELD_SEQ_TB:
+		cx23885_risc_buffer(dev->pci, &buf->risc,
+				sgt->sgl,
+				0, buf->bpl * (dev->height >> 1),
+				buf->bpl, 0,
+				dev->height >> 1);
+		break;
+	case V4L2_FIELD_SEQ_BT:
+		cx23885_risc_buffer(dev->pci, &buf->risc,
+				sgt->sgl,
+				buf->bpl * (dev->height >> 1), 0,
+				buf->bpl, 0,
+				dev->height >> 1);
+		break;
+	default:
+		BUG();
 	}
-	dprintk(2, "[%p/%d] buffer_prep - %dx%d %dbpp \"%s\" - dma=0x%08lx\n",
-		buf, buf->vb.i,
-		fh->width, fh->height, fh->fmt->depth, fh->fmt->name,
+	dprintk(2, "[%p/%d] buffer_init - %dx%d %dbpp \"%s\" - dma=0x%08lx\n",
+		buf, buf->vb.v4l2_buf.index,
+		dev->width, dev->height, dev->fmt->depth, dev->fmt->name,
 		(unsigned long)buf->risc.dma);
-
-	buf->vb.state = VIDEOBUF_PREPARED;
 	return 0;
+}
+
+static void buffer_finish(struct vb2_buffer *vb)
+{
+	struct cx23885_dev *dev = vb->vb2_queue->drv_priv;
+	struct cx23885_buffer *buf = container_of(vb,
+		struct cx23885_buffer, vb);
+	struct sg_table *sgt = vb2_dma_sg_plane_desc(vb, 0);
+
+	cx23885_free_buffer(vb->vb2_queue->drv_priv, buf);
 
- fail:
-	cx23885_free_buffer(q, buf);
-	return rc;
+	dma_unmap_sg(&dev->pci->dev, sgt->sgl, sgt->nents, DMA_FROM_DEVICE);
 }
 
-static void buffer_queue(struct videobuf_queue *vq, struct videobuf_buffer *vb)
+/*
+ * The risc program for each buffer works as follows: it starts with a simple
+ * 'JUMP to addr + 12', which is effectively a NOP. Then the code to DMA the
+ * buffer follows and at the end we have a JUMP back to the start + 12 (skipping
+ * the initial JUMP).
+ *
+ * This is the risc program of the first buffer to be queued if the active list
+ * is empty and it just keeps DMAing this buffer without generating any
+ * interrupts.
+ *
+ * If a new buffer is added then the initial JUMP in the code for that buffer
+ * will generate an interrupt which signals that the previous buffer has been
+ * DMAed successfully and that it can be returned to userspace.
+ *
+ * It also sets the final jump of the previous buffer to the start of the new
+ * buffer, thus chaining the new buffer into the DMA chain. This is a single
+ * atomic u32 write, so there is no race condition.
+ *
+ * The end-result of all this that you only get an interrupt when a buffer
+ * is ready, so the control flow is very easy.
+ */
+static void buffer_queue(struct vb2_buffer *vb)
 {
+	struct cx23885_dev *dev = vb->vb2_queue->drv_priv;
 	struct cx23885_buffer   *buf = container_of(vb,
 		struct cx23885_buffer, vb);
 	struct cx23885_buffer   *prev;
-	struct cx23885_fh       *fh   = vq->priv_data;
-	struct cx23885_dev      *dev  = fh->dev;
 	struct cx23885_dmaqueue *q    = &dev->vidq;
+	unsigned long flags;
 
-	/* add jump to stopper */
-	buf->risc.jmp[0] = cpu_to_le32(RISC_JUMP | RISC_IRQ1 | RISC_CNT_INC);
-	buf->risc.jmp[1] = cpu_to_le32(q->stopper.dma);
+	/* add jump to start */
+	buf->risc.cpu[1] = cpu_to_le32(buf->risc.dma + 12);
+	buf->risc.jmp[0] = cpu_to_le32(RISC_JUMP | RISC_CNT_INC);
+	buf->risc.jmp[1] = cpu_to_le32(buf->risc.dma + 12);
 	buf->risc.jmp[2] = cpu_to_le32(0); /* bits 63-32 */
 
-	if (!list_empty(&q->queued)) {
-		list_add_tail(&buf->vb.queue, &q->queued);
-		buf->vb.state = VIDEOBUF_QUEUED;
-		dprintk(2, "[%p/%d] buffer_queue - append to queued\n",
-			buf, buf->vb.i);
-
-	} else if (list_empty(&q->active)) {
-		list_add_tail(&buf->vb.queue, &q->active);
-		cx23885_start_video_dma(dev, q, buf);
-		buf->vb.state = VIDEOBUF_ACTIVE;
-		buf->count    = q->count++;
-		mod_timer(&q->timeout, jiffies+BUFFER_TIMEOUT);
+	spin_lock_irqsave(&dev->slock, flags);
+	if (list_empty(&q->active)) {
+		list_add_tail(&buf->queue, &q->active);
 		dprintk(2, "[%p/%d] buffer_queue - first active\n",
-			buf, buf->vb.i);
-
+			buf, buf->vb.v4l2_buf.index);
 	} else {
+		buf->risc.cpu[0] |= cpu_to_le32(RISC_IRQ1);
 		prev = list_entry(q->active.prev, struct cx23885_buffer,
-			vb.queue);
-		if (prev->vb.width  == buf->vb.width  &&
-		    prev->vb.height == buf->vb.height &&
-		    prev->fmt       == buf->fmt) {
-			list_add_tail(&buf->vb.queue, &q->active);
-			buf->vb.state = VIDEOBUF_ACTIVE;
-			buf->count    = q->count++;
-			prev->risc.jmp[1] = cpu_to_le32(buf->risc.dma);
-			/* 64 bit bits 63-32 */
-			prev->risc.jmp[2] = cpu_to_le32(0);
-			dprintk(2, "[%p/%d] buffer_queue - append to active\n",
-				buf, buf->vb.i);
-
-		} else {
-			list_add_tail(&buf->vb.queue, &q->queued);
-			buf->vb.state = VIDEOBUF_QUEUED;
-			dprintk(2, "[%p/%d] buffer_queue - first queued\n",
-				buf, buf->vb.i);
-		}
-	}
-}
-
-static void buffer_release(struct videobuf_queue *q,
-	struct videobuf_buffer *vb)
-{
-	struct cx23885_buffer *buf = container_of(vb,
-		struct cx23885_buffer, vb);
-
-	cx23885_free_buffer(q, buf);
-}
-
-static struct videobuf_queue_ops cx23885_video_qops = {
-	.buf_setup    = buffer_setup,
-	.buf_prepare  = buffer_prepare,
-	.buf_queue    = buffer_queue,
-	.buf_release  = buffer_release,
-};
-
-static struct videobuf_queue *get_queue(struct cx23885_fh *fh)
-{
-	switch (fh->type) {
-	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
-		return &fh->vidq;
-	case V4L2_BUF_TYPE_VBI_CAPTURE:
-		return &fh->vbiq;
-	default:
-		BUG();
-		return NULL;
-	}
-}
-
-static int get_resource(struct cx23885_fh *fh)
-{
-	switch (fh->type) {
-	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
-		return RESOURCE_VIDEO;
-	case V4L2_BUF_TYPE_VBI_CAPTURE:
-		return RESOURCE_VBI;
-	default:
-		BUG();
-		return 0;
+			queue);
+		list_add_tail(&buf->queue, &q->active);
+		prev->risc.jmp[1] = cpu_to_le32(buf->risc.dma);
+		dprintk(2, "[%p/%d] buffer_queue - append to active\n",
+				buf, buf->vb.v4l2_buf.index);
 	}
+	spin_unlock_irqrestore(&dev->slock, flags);
 }
 
-static int video_open(struct file *file)
+static int cx23885_start_streaming(struct vb2_queue *q, unsigned int count)
 {
-	struct video_device *vdev = video_devdata(file);
-	struct cx23885_dev *dev = video_drvdata(file);
-	struct cx23885_fh *fh;
-	enum v4l2_buf_type type = 0;
-	int radio = 0;
-
-	switch (vdev->vfl_type) {
-	case VFL_TYPE_GRABBER:
-		type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-		break;
-	case VFL_TYPE_VBI:
-		type = V4L2_BUF_TYPE_VBI_CAPTURE;
-		break;
-	case VFL_TYPE_RADIO:
-		radio = 1;
-		break;
-	}
-
-	dprintk(1, "open dev=%s radio=%d type=%s\n",
-		video_device_node_name(vdev), radio, v4l2_type_names[type]);
-
-	/* allocate + initialize per filehandle data */
-	fh = kzalloc(sizeof(*fh), GFP_KERNEL);
-	if (NULL == fh)
-		return -ENOMEM;
-
-	file->private_data = fh;
-	fh->dev      = dev;
-	fh->radio    = radio;
-	fh->type     = type;
-	fh->width    = 320;
-	fh->height   = 240;
-	fh->fmt      = format_by_fourcc(V4L2_PIX_FMT_YUYV);
-
-	videobuf_queue_sg_init(&fh->vidq, &cx23885_video_qops,
-			    &dev->pci->dev, &dev->slock,
-			    V4L2_BUF_TYPE_VIDEO_CAPTURE,
-			    V4L2_FIELD_INTERLACED,
-			    sizeof(struct cx23885_buffer),
-			    fh, NULL);
-
-	videobuf_queue_sg_init(&fh->vbiq, &cx23885_vbi_qops,
-		&dev->pci->dev, &dev->slock,
-		V4L2_BUF_TYPE_VBI_CAPTURE,
-		V4L2_FIELD_SEQ_TB,
-		sizeof(struct cx23885_buffer),
-		fh, NULL);
-
-
-	dprintk(1, "post videobuf_queue_init()\n");
+	struct cx23885_dev *dev = q->drv_priv;
+	struct cx23885_dmaqueue *dmaq = &dev->vidq;
+	struct cx23885_buffer *buf = list_entry(dmaq->active.next,
+			struct cx23885_buffer, queue);
 
+	cx23885_start_video_dma(dev, dmaq, buf);
 	return 0;
 }
 
-static ssize_t video_read(struct file *file, char __user *data,
-	size_t count, loff_t *ppos)
+static void cx23885_stop_streaming(struct vb2_queue *q)
 {
-	struct cx23885_fh *fh = file->private_data;
-
-	switch (fh->type) {
-	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
-		if (res_locked(fh->dev, RESOURCE_VIDEO))
-			return -EBUSY;
-		return videobuf_read_one(&fh->vidq, data, count, ppos,
-					 file->f_flags & O_NONBLOCK);
-	case V4L2_BUF_TYPE_VBI_CAPTURE:
-		if (!res_get(fh->dev, fh, RESOURCE_VBI))
-			return -EBUSY;
-		return videobuf_read_stream(&fh->vbiq, data, count, ppos, 1,
-					    file->f_flags & O_NONBLOCK);
-	default:
-		BUG();
-		return 0;
-	}
-}
-
-static unsigned int video_poll(struct file *file,
-	struct poll_table_struct *wait)
-{
-	struct cx23885_fh *fh = file->private_data;
-	struct cx23885_buffer *buf;
-	unsigned int rc = POLLERR;
-
-	if (V4L2_BUF_TYPE_VBI_CAPTURE == fh->type) {
-		if (!res_get(fh->dev, fh, RESOURCE_VBI))
-			return POLLERR;
-		return videobuf_poll_stream(file, &fh->vbiq, wait);
-	}
-
-	mutex_lock(&fh->vidq.vb_lock);
-	if (res_check(fh, RESOURCE_VIDEO)) {
-		/* streaming capture */
-		if (list_empty(&fh->vidq.stream))
-			goto done;
-		buf = list_entry(fh->vidq.stream.next,
-			struct cx23885_buffer, vb.stream);
-	} else {
-		/* read() capture */
-		buf = (struct cx23885_buffer *)fh->vidq.read_buf;
-		if (NULL == buf)
-			goto done;
-	}
-	poll_wait(file, &buf->vb.done, wait);
-	if (buf->vb.state == VIDEOBUF_DONE ||
-	    buf->vb.state == VIDEOBUF_ERROR)
-		rc =  POLLIN|POLLRDNORM;
-	else
-		rc = 0;
-done:
-	mutex_unlock(&fh->vidq.vb_lock);
-	return rc;
-}
-
-static int video_release(struct file *file)
-{
-	struct cx23885_fh *fh = file->private_data;
-	struct cx23885_dev *dev = fh->dev;
-
-	/* turn off overlay */
-	if (res_check(fh, RESOURCE_OVERLAY)) {
-		/* FIXME */
-		res_free(dev, fh, RESOURCE_OVERLAY);
-	}
+	struct cx23885_dev *dev = q->drv_priv;
+	struct cx23885_dmaqueue *dmaq = &dev->vidq;
+	unsigned long flags;
 
-	/* stop video capture */
-	if (res_check(fh, RESOURCE_VIDEO)) {
-		videobuf_queue_cancel(&fh->vidq);
-		res_free(dev, fh, RESOURCE_VIDEO);
-	}
-	if (fh->vidq.read_buf) {
-		buffer_release(&fh->vidq, fh->vidq.read_buf);
-		kfree(fh->vidq.read_buf);
-	}
+	cx_clear(VID_A_DMA_CTL, 0x11);
+	spin_lock_irqsave(&dev->slock, flags);
+	while (!list_empty(&dmaq->active)) {
+		struct cx23885_buffer *buf = list_entry(dmaq->active.next,
+			struct cx23885_buffer, queue);
 
-	/* stop vbi capture */
-	if (res_check(fh, RESOURCE_VBI)) {
-		if (fh->vbiq.streaming)
-			videobuf_streamoff(&fh->vbiq);
-		if (fh->vbiq.reading)
-			videobuf_read_stop(&fh->vbiq);
-		res_free(dev, fh, RESOURCE_VBI);
+		list_del(&buf->queue);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
 	}
-
-	videobuf_mmap_free(&fh->vidq);
-	videobuf_mmap_free(&fh->vbiq);
-
-	file->private_data = NULL;
-	kfree(fh);
-
-	/* We are not putting the tuner to sleep here on exit, because
-	 * we want to use the mpeg encoder in another session to capture
-	 * tuner video. Closing this will result in no video to the encoder.
-	 */
-
-	return 0;
-}
-
-static int video_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	struct cx23885_fh *fh = file->private_data;
-
-	return videobuf_mmap_mapper(get_queue(fh), vma);
-}
-
-/* ------------------------------------------------------------------ */
-/* VIDEO CTRL IOCTLS                                                  */
-
-int cx23885_get_control(struct cx23885_dev *dev,
-	struct v4l2_control *ctl)
-{
-	dprintk(1, "%s() calling cx25840(VIDIOC_G_CTRL)\n", __func__);
-	call_all(dev, core, g_ctrl, ctl);
-	return 0;
-}
-
-int cx23885_set_control(struct cx23885_dev *dev,
-	struct v4l2_control *ctl)
-{
-	dprintk(1, "%s() calling cx25840(VIDIOC_S_CTRL)\n", __func__);
-	call_all(dev, core, s_ctrl, ctl);
-
-	return 0;
+	spin_unlock_irqrestore(&dev->slock, flags);
 }
 
-static void init_controls(struct cx23885_dev *dev)
-{
-	struct v4l2_control ctrl;
-	int i;
-
-	for (i = 0; i < CX23885_CTLS; i++) {
-		ctrl.id = cx23885_ctls[i].v.id;
-		ctrl.value = cx23885_ctls[i].v.default_value;
-
-		cx23885_set_control(dev, &ctrl);
-	}
-}
+static struct vb2_ops cx23885_video_qops = {
+	.queue_setup    = queue_setup,
+	.buf_prepare  = buffer_prepare,
+	.buf_finish = buffer_finish,
+	.buf_queue    = buffer_queue,
+	.wait_prepare = vb2_ops_wait_prepare,
+	.wait_finish = vb2_ops_wait_finish,
+	.start_streaming = cx23885_start_streaming,
+	.stop_streaming = cx23885_stop_streaming,
+};
 
 /* ------------------------------------------------------------------ */
 /* VIDEO IOCTLS                                                       */
@@ -1060,16 +522,17 @@ static void init_controls(struct cx23885_dev *dev)
 static int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
 	struct v4l2_format *f)
 {
-	struct cx23885_fh *fh   = priv;
+	struct cx23885_dev *dev = video_drvdata(file);
 
-	f->fmt.pix.width        = fh->width;
-	f->fmt.pix.height       = fh->height;
-	f->fmt.pix.field        = fh->vidq.field;
-	f->fmt.pix.pixelformat  = fh->fmt->fourcc;
+	f->fmt.pix.width        = dev->width;
+	f->fmt.pix.height       = dev->height;
+	f->fmt.pix.field        = dev->field;
+	f->fmt.pix.pixelformat  = dev->fmt->fourcc;
 	f->fmt.pix.bytesperline =
-		(f->fmt.pix.width * fh->fmt->depth) >> 3;
+		(f->fmt.pix.width * dev->fmt->depth) >> 3;
 	f->fmt.pix.sizeimage =
 		f->fmt.pix.height * f->fmt.pix.bytesperline;
+	f->fmt.pix.colorspace   = V4L2_COLORSPACE_SMPTE170M;
 
 	return 0;
 }
@@ -1077,7 +540,7 @@ static int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
 static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
 	struct v4l2_format *f)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 	struct cx23885_fmt *fmt;
 	enum v4l2_field   field;
 	unsigned int      maxw, maxh;
@@ -1102,9 +565,12 @@ static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
 		maxh = maxh / 2;
 		break;
 	case V4L2_FIELD_INTERLACED:
+	case V4L2_FIELD_SEQ_TB:
+	case V4L2_FIELD_SEQ_BT:
 		break;
 	default:
-		return -EINVAL;
+		field = V4L2_FIELD_INTERLACED;
+		break;
 	}
 
 	f->fmt.pix.field = field;
@@ -1114,6 +580,7 @@ static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
 		(f->fmt.pix.width * fmt->depth) >> 3;
 	f->fmt.pix.sizeimage =
 		f->fmt.pix.height * f->fmt.pix.bytesperline;
+	f->fmt.pix.colorspace = V4L2_COLORSPACE_SMPTE170M;
 
 	return 0;
 }
@@ -1121,8 +588,7 @@ static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
 static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
 	struct v4l2_format *f)
 {
-	struct cx23885_fh *fh = priv;
-	struct cx23885_dev *dev  = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 	struct v4l2_mbus_framefmt mbus_fmt;
 	int err;
 
@@ -1131,34 +597,44 @@ static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
 
 	if (0 != err)
 		return err;
-	fh->fmt        = format_by_fourcc(f->fmt.pix.pixelformat);
-	fh->width      = f->fmt.pix.width;
-	fh->height     = f->fmt.pix.height;
-	fh->vidq.field = f->fmt.pix.field;
+
+	if (vb2_is_busy(&dev->vb2_vidq) || vb2_is_busy(&dev->vb2_vbiq) ||
+	    vb2_is_busy(&dev->vb2_mpegq))
+		return -EBUSY;
+
+	dev->fmt        = format_by_fourcc(f->fmt.pix.pixelformat);
+	dev->width      = f->fmt.pix.width;
+	dev->height     = f->fmt.pix.height;
+	dev->field	= f->fmt.pix.field;
 	dprintk(2, "%s() width=%d height=%d field=%d\n", __func__,
-		fh->width, fh->height, fh->vidq.field);
+		dev->width, dev->height, dev->field);
 	v4l2_fill_mbus_format(&mbus_fmt, &f->fmt.pix, V4L2_MBUS_FMT_FIXED);
 	call_all(dev, video, s_mbus_fmt, &mbus_fmt);
 	v4l2_fill_pix_format(&f->fmt.pix, &mbus_fmt);
+	/* s_mbus_fmt overwrites f->fmt.pix.field, restore it */
+	f->fmt.pix.field = dev->field;
 	return 0;
 }
 
 static int vidioc_querycap(struct file *file, void  *priv,
 	struct v4l2_capability *cap)
 {
-	struct cx23885_dev *dev  = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
+	struct video_device *vdev = video_devdata(file);
 
 	strcpy(cap->driver, "cx23885");
 	strlcpy(cap->card, cx23885_boards[dev->board].name,
 		sizeof(cap->card));
 	sprintf(cap->bus_info, "PCIe:%s", pci_name(dev->pci));
-	cap->capabilities =
-		V4L2_CAP_VIDEO_CAPTURE |
-		V4L2_CAP_READWRITE     |
-		V4L2_CAP_STREAMING     |
-		V4L2_CAP_VBI_CAPTURE;
+	cap->device_caps = V4L2_CAP_READWRITE | V4L2_CAP_STREAMING | V4L2_CAP_AUDIO;
 	if (dev->tuner_type != TUNER_ABSENT)
-		cap->capabilities |= V4L2_CAP_TUNER;
+		cap->device_caps |= V4L2_CAP_TUNER;
+	if (vdev->vfl_type == VFL_TYPE_VBI)
+		cap->device_caps |= V4L2_CAP_VBI_CAPTURE;
+	else
+		cap->device_caps |= V4L2_CAP_VIDEO_CAPTURE;
+	cap->capabilities = cap->device_caps | V4L2_CAP_VBI_CAPTURE |
+		V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_DEVICE_CAPS;
 	return 0;
 }
 
@@ -1175,85 +651,9 @@ static int vidioc_enum_fmt_vid_cap(struct file *file, void  *priv,
 	return 0;
 }
 
-static int vidioc_reqbufs(struct file *file, void *priv,
-	struct v4l2_requestbuffers *p)
-{
-	struct cx23885_fh *fh = priv;
-	return videobuf_reqbufs(get_queue(fh), p);
-}
-
-static int vidioc_querybuf(struct file *file, void *priv,
-	struct v4l2_buffer *p)
-{
-	struct cx23885_fh *fh = priv;
-	return videobuf_querybuf(get_queue(fh), p);
-}
-
-static int vidioc_qbuf(struct file *file, void *priv,
-	struct v4l2_buffer *p)
-{
-	struct cx23885_fh *fh = priv;
-	return videobuf_qbuf(get_queue(fh), p);
-}
-
-static int vidioc_dqbuf(struct file *file, void *priv,
-	struct v4l2_buffer *p)
-{
-	struct cx23885_fh *fh = priv;
-	return videobuf_dqbuf(get_queue(fh), p,
-				file->f_flags & O_NONBLOCK);
-}
-
-static int vidioc_streamon(struct file *file, void *priv,
-	enum v4l2_buf_type i)
-{
-	struct cx23885_fh *fh = priv;
-	struct cx23885_dev *dev = fh->dev;
-	dprintk(1, "%s()\n", __func__);
-
-	if ((fh->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) &&
-		(fh->type != V4L2_BUF_TYPE_VBI_CAPTURE))
-		return -EINVAL;
-	if (unlikely(i != fh->type))
-		return -EINVAL;
-
-	if (unlikely(!res_get(dev, fh, get_resource(fh))))
-		return -EBUSY;
-
-	/* Don't start VBI streaming unless vida streaming
-	 * has already started.
-	 */
-	if ((fh->type == V4L2_BUF_TYPE_VBI_CAPTURE) &&
-		((cx_read(VID_A_DMA_CTL) & 0x11) == 0))
-		return -EINVAL;
-
-	return videobuf_streamon(get_queue(fh));
-}
-
-static int vidioc_streamoff(struct file *file, void *priv, enum v4l2_buf_type i)
-{
-	struct cx23885_fh *fh = priv;
-	struct cx23885_dev *dev = fh->dev;
-	int err, res;
-	dprintk(1, "%s()\n", __func__);
-
-	if ((fh->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) &&
-		(fh->type != V4L2_BUF_TYPE_VBI_CAPTURE))
-		return -EINVAL;
-	if (i != fh->type)
-		return -EINVAL;
-
-	res = get_resource(fh);
-	err = videobuf_streamoff(get_queue(fh));
-	if (err < 0)
-		return err;
-	res_free(dev, fh, res);
-	return 0;
-}
-
 static int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *id)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 	dprintk(1, "%s()\n", __func__);
 
 	*id = dev->tvnorm;
@@ -1262,14 +662,10 @@ static int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *id)
 
 static int vidioc_s_std(struct file *file, void *priv, v4l2_std_id tvnorms)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 	dprintk(1, "%s()\n", __func__);
 
-	mutex_lock(&dev->lock);
-	cx23885_set_tvnorm(dev, tvnorms);
-	mutex_unlock(&dev->lock);
-
-	return 0;
+	return cx23885_set_tvnorm(dev, tvnorms);
 }
 
 int cx23885_enum_input(struct cx23885_dev *dev, struct v4l2_input *i)
@@ -1299,16 +695,16 @@ int cx23885_enum_input(struct cx23885_dev *dev, struct v4l2_input *i)
 	i->index = n;
 	i->type  = V4L2_INPUT_TYPE_CAMERA;
 	strcpy(i->name, iname[INPUT(n)->type]);
+	i->std = CX23885_NORMS;
 	if ((CX23885_VMUX_TELEVISION == INPUT(n)->type) ||
 		(CX23885_VMUX_CABLE == INPUT(n)->type)) {
 		i->type = V4L2_INPUT_TYPE_TUNER;
-		i->std = CX23885_NORMS;
+		i->audioset = 4;
+	} else {
+		/* Two selectable audio inputs for non-tv inputs */
+		i->audioset = 3;
 	}
 
-	/* Two selectable audio inputs for non-tv inputs */
-	if (INPUT(n)->type != CX23885_VMUX_TELEVISION)
-		i->audioset = 0x3;
-
 	if (dev->input == n) {
 		/* enum'd input matches our configured input.
 		 * Ask the video decoder to process the call
@@ -1324,14 +720,14 @@ int cx23885_enum_input(struct cx23885_dev *dev, struct v4l2_input *i)
 static int vidioc_enum_input(struct file *file, void *priv,
 				struct v4l2_input *i)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 	dprintk(1, "%s()\n", __func__);
 	return cx23885_enum_input(dev, i);
 }
 
 int cx23885_get_input(struct file *file, void *priv, unsigned int *i)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	*i = dev->input;
 	dprintk(1, "%s() returns %d\n", __func__, *i);
@@ -1345,7 +741,7 @@ static int vidioc_g_input(struct file *file, void *priv, unsigned int *i)
 
 int cx23885_set_input(struct file *file, void *priv, unsigned int i)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	dprintk(1, "%s(%d)\n", __func__, i);
 
@@ -1357,13 +753,11 @@ int cx23885_set_input(struct file *file, void *priv, unsigned int i)
 	if (INPUT(i)->type == 0)
 		return -EINVAL;
 
-	mutex_lock(&dev->lock);
 	cx23885_video_mux(dev, i);
 
 	/* By default establish the default audio input for the card also */
 	/* Caller is free to use VIDIOC_S_AUDIO to override afterwards */
 	cx23885_audio_mux(dev, i);
-	mutex_unlock(&dev->lock);
 	return 0;
 }
 
@@ -1374,39 +768,32 @@ static int vidioc_s_input(struct file *file, void *priv, unsigned int i)
 
 static int vidioc_log_status(struct file *file, void *priv)
 {
-	struct cx23885_fh  *fh  = priv;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
-	printk(KERN_INFO
-		"%s/0: ============  START LOG STATUS  ============\n",
-		dev->name);
 	call_all(dev, core, log_status);
-	printk(KERN_INFO
-		"%s/0: =============  END LOG STATUS  =============\n",
-		dev->name);
 	return 0;
 }
 
 static int cx23885_query_audinput(struct file *file, void *priv,
 	struct v4l2_audio *i)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 	static const char *iname[] = {
 		[0] = "Baseband L/R 1",
 		[1] = "Baseband L/R 2",
+		[2] = "TV",
 	};
 	unsigned int n;
 	dprintk(1, "%s()\n", __func__);
 
 	n = i->index;
-	if (n >= 2)
+	if (n >= 3)
 		return -EINVAL;
 
 	memset(i, 0, sizeof(*i));
 	i->index = n;
 	strcpy(i->name, iname[n]);
-	i->capability  = V4L2_AUDCAP_STEREO;
-	i->mode  = V4L2_AUDMODE_AVL;
+	i->capability = V4L2_AUDCAP_STEREO;
 	return 0;
 
 }
@@ -1420,9 +807,13 @@ static int vidioc_enum_audinput(struct file *file, void *priv,
 static int vidioc_g_audinput(struct file *file, void *priv,
 	struct v4l2_audio *i)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
-	i->index = dev->audinput;
+	if ((CX23885_VMUX_TELEVISION == INPUT(dev->input)->type) ||
+		(CX23885_VMUX_CABLE == INPUT(dev->input)->type))
+		i->index = 2;
+	else
+		i->index = dev->audinput;
 	dprintk(1, "%s(input=%d)\n", __func__, i->index);
 
 	return cx23885_query_audinput(file, priv, i);
@@ -1431,8 +822,13 @@ static int vidioc_g_audinput(struct file *file, void *priv,
 static int vidioc_s_audinput(struct file *file, void *priv,
 	const struct v4l2_audio *i)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
-	if (i->index >= 2)
+	struct cx23885_dev *dev = video_drvdata(file);
+
+	if ((CX23885_VMUX_TELEVISION == INPUT(dev->input)->type) ||
+		(CX23885_VMUX_CABLE == INPUT(dev->input)->type)) {
+		return i->index != 2 ? -EINVAL : 0;
+	}
+	if (i->index > 1)
 		return -EINVAL;
 
 	dprintk(1, "%s(%d)\n", __func__, i->index);
@@ -1445,35 +841,10 @@ static int vidioc_s_audinput(struct file *file, void *priv,
 	return 0;
 }
 
-static int vidioc_queryctrl(struct file *file, void *priv,
-				struct v4l2_queryctrl *qctrl)
-{
-	qctrl->id = v4l2_ctrl_next(ctrl_classes, qctrl->id);
-	if (unlikely(qctrl->id == 0))
-		return -EINVAL;
-	return cx23885_ctrl_query(qctrl);
-}
-
-static int vidioc_g_ctrl(struct file *file, void *priv,
-				struct v4l2_control *ctl)
-{
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
-
-	return cx23885_get_control(dev, ctl);
-}
-
-static int vidioc_s_ctrl(struct file *file, void *priv,
-				struct v4l2_control *ctl)
-{
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
-
-	return cx23885_set_control(dev, ctl);
-}
-
 static int vidioc_g_tuner(struct file *file, void *priv,
 				struct v4l2_tuner *t)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	if (dev->tuner_type == TUNER_ABSENT)
 		return -EINVAL;
@@ -1489,7 +860,7 @@ static int vidioc_g_tuner(struct file *file, void *priv,
 static int vidioc_s_tuner(struct file *file, void *priv,
 				const struct v4l2_tuner *t)
 {
-	struct cx23885_dev *dev = ((struct cx23885_fh *)priv)->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	if (dev->tuner_type == TUNER_ABSENT)
 		return -EINVAL;
@@ -1504,14 +875,12 @@ static int vidioc_s_tuner(struct file *file, void *priv,
 static int vidioc_g_frequency(struct file *file, void *priv,
 				struct v4l2_frequency *f)
 {
-	struct cx23885_fh *fh = priv;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 
 	if (dev->tuner_type == TUNER_ABSENT)
 		return -EINVAL;
 
-	/* f->type = fh->radio ? V4L2_TUNER_RADIO : V4L2_TUNER_ANALOG_TV; */
-	f->type = fh->radio ? V4L2_TUNER_RADIO : V4L2_TUNER_ANALOG_TV;
+	f->type = V4L2_TUNER_ANALOG_TV;
 	f->frequency = dev->freq;
 
 	call_all(dev, tuner, g_frequency, f);
@@ -1521,20 +890,23 @@ static int vidioc_g_frequency(struct file *file, void *priv,
 
 static int cx23885_set_freq(struct cx23885_dev *dev, const struct v4l2_frequency *f)
 {
-	struct v4l2_control ctrl;
+	struct v4l2_ctrl *mute;
+	int old_mute_val = 1;
 
 	if (dev->tuner_type == TUNER_ABSENT)
 		return -EINVAL;
 	if (unlikely(f->tuner != 0))
 		return -EINVAL;
 
-	mutex_lock(&dev->lock);
 	dev->freq = f->frequency;
 
 	/* I need to mute audio here */
-	ctrl.id = V4L2_CID_AUDIO_MUTE;
-	ctrl.value = 1;
-	cx23885_set_control(dev, &ctrl);
+	mute = v4l2_ctrl_find(&dev->ctrl_handler, V4L2_CID_AUDIO_MUTE);
+	if (mute) {
+		old_mute_val = v4l2_ctrl_g_ctrl(mute);
+		if (!old_mute_val)
+			v4l2_ctrl_s_ctrl(mute, 1);
+	}
 
 	call_all(dev, tuner, s_frequency, f);
 
@@ -1542,10 +914,8 @@ static int cx23885_set_freq(struct cx23885_dev *dev, const struct v4l2_frequency
 	msleep(100);
 
 	/* I need to unmute audio here */
-	ctrl.value = 0;
-	cx23885_set_control(dev, &ctrl);
-
-	mutex_unlock(&dev->lock);
+	if (old_mute_val == 0)
+		v4l2_ctrl_s_ctrl(mute, old_mute_val);
 
 	return 0;
 }
@@ -1553,8 +923,9 @@ static int cx23885_set_freq(struct cx23885_dev *dev, const struct v4l2_frequency
 static int cx23885_set_freq_via_ops(struct cx23885_dev *dev,
 	const struct v4l2_frequency *f)
 {
-	struct v4l2_control ctrl;
-	struct videobuf_dvb_frontend *vfe;
+	struct v4l2_ctrl *mute;
+	int old_mute_val = 1;
+	struct vb2_dvb_frontend *vfe;
 	struct dvb_frontend *fe;
 
 	struct analog_parameters params = {
@@ -1564,21 +935,22 @@ static int cx23885_set_freq_via_ops(struct cx23885_dev *dev,
 		.frequency = f->frequency
 	};
 
-	mutex_lock(&dev->lock);
 	dev->freq = f->frequency;
 
 	/* I need to mute audio here */
-	ctrl.id = V4L2_CID_AUDIO_MUTE;
-	ctrl.value = 1;
-	cx23885_set_control(dev, &ctrl);
+	mute = v4l2_ctrl_find(&dev->ctrl_handler, V4L2_CID_AUDIO_MUTE);
+	if (mute) {
+		old_mute_val = v4l2_ctrl_g_ctrl(mute);
+		if (!old_mute_val)
+			v4l2_ctrl_s_ctrl(mute, 1);
+	}
 
 	/* If HVR1850 */
 	dprintk(1, "%s() frequency=%d tuner=%d std=0x%llx\n", __func__,
 		params.frequency, f->tuner, params.std);
 
-	vfe = videobuf_dvb_get_frontend(&dev->ts2.frontends, 1);
+	vfe = vb2_dvb_get_frontend(&dev->ts2.frontends, 1);
 	if (!vfe) {
-		mutex_unlock(&dev->lock);
 		return -EINVAL;
 	}
 
@@ -1600,10 +972,8 @@ static int cx23885_set_freq_via_ops(struct cx23885_dev *dev,
 	msleep(100);
 
 	/* I need to unmute audio here */
-	ctrl.value = 0;
-	cx23885_set_control(dev, &ctrl);
-
-	mutex_unlock(&dev->lock);
+	if (old_mute_val == 0)
+		v4l2_ctrl_s_ctrl(mute, old_mute_val);
 
 	return 0;
 }
@@ -1611,8 +981,7 @@ static int cx23885_set_freq_via_ops(struct cx23885_dev *dev,
 int cx23885_set_frequency(struct file *file, void *priv,
 	const struct v4l2_frequency *f)
 {
-	struct cx23885_fh *fh = priv;
-	struct cx23885_dev *dev = fh->dev;
+	struct cx23885_dev *dev = video_drvdata(file);
 	int ret;
 
 	switch (dev->board) {
@@ -1636,28 +1005,6 @@ static int vidioc_s_frequency(struct file *file, void *priv,
 
 /* ----------------------------------------------------------- */
 
-static void cx23885_vid_timeout(unsigned long data)
-{
-	struct cx23885_dev *dev = (struct cx23885_dev *)data;
-	struct cx23885_dmaqueue *q = &dev->vidq;
-	struct cx23885_buffer *buf;
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev->slock, flags);
-	while (!list_empty(&q->active)) {
-		buf = list_entry(q->active.next,
-			struct cx23885_buffer, vb.queue);
-		list_del(&buf->vb.queue);
-		buf->vb.state = VIDEOBUF_ERROR;
-		wake_up(&buf->vb.done);
-		printk(KERN_ERR "%s: [%p/%d] timeout - dma=0x%08lx\n",
-			dev->name, buf, buf->vb.i,
-			(unsigned long)buf->risc.dma);
-	}
-	cx23885_restart_video_queue(dev, q);
-	spin_unlock_irqrestore(&dev->slock, flags);
-}
-
 int cx23885_video_irq(struct cx23885_dev *dev, u32 status)
 {
 	u32 mask, count;
@@ -1702,13 +1049,6 @@ int cx23885_video_irq(struct cx23885_dev *dev, u32 status)
 		spin_unlock(&dev->slock);
 		handled++;
 	}
-	if (status & VID_BC_MSK_RISCI2) {
-		dprintk(2, "stopper video\n");
-		spin_lock(&dev->slock);
-		cx23885_restart_video_queue(dev, &dev->vidq);
-		spin_unlock(&dev->slock);
-		handled++;
-	}
 
 	/* Allow the VBI framework to process it's payload */
 	handled += cx23885_vbi_irq(dev, status);
@@ -1721,12 +1061,12 @@ int cx23885_video_irq(struct cx23885_dev *dev, u32 status)
 
 static const struct v4l2_file_operations video_fops = {
 	.owner	       = THIS_MODULE,
-	.open	       = video_open,
-	.release       = video_release,
-	.read	       = video_read,
-	.poll          = video_poll,
-	.mmap	       = video_mmap,
-	.ioctl	       = video_ioctl2,
+	.open           = v4l2_fh_open,
+	.release        = vb2_fop_release,
+	.read           = vb2_fop_read,
+	.poll		= vb2_fop_poll,
+	.unlocked_ioctl = video_ioctl2,
+	.mmap           = vb2_fop_mmap,
 };
 
 static const struct v4l2_ioctl_ops video_ioctl_ops = {
@@ -1738,21 +1078,19 @@ static const struct v4l2_ioctl_ops video_ioctl_ops = {
 	.vidioc_g_fmt_vbi_cap     = cx23885_vbi_fmt,
 	.vidioc_try_fmt_vbi_cap   = cx23885_vbi_fmt,
 	.vidioc_s_fmt_vbi_cap     = cx23885_vbi_fmt,
-	.vidioc_reqbufs       = vidioc_reqbufs,
-	.vidioc_querybuf      = vidioc_querybuf,
-	.vidioc_qbuf          = vidioc_qbuf,
-	.vidioc_dqbuf         = vidioc_dqbuf,
+	.vidioc_reqbufs       = vb2_ioctl_reqbufs,
+	.vidioc_prepare_buf   = vb2_ioctl_prepare_buf,
+	.vidioc_querybuf      = vb2_ioctl_querybuf,
+	.vidioc_qbuf          = vb2_ioctl_qbuf,
+	.vidioc_dqbuf         = vb2_ioctl_dqbuf,
+	.vidioc_streamon      = vb2_ioctl_streamon,
+	.vidioc_streamoff     = vb2_ioctl_streamoff,
 	.vidioc_s_std         = vidioc_s_std,
 	.vidioc_g_std         = vidioc_g_std,
 	.vidioc_enum_input    = vidioc_enum_input,
 	.vidioc_g_input       = vidioc_g_input,
 	.vidioc_s_input       = vidioc_s_input,
 	.vidioc_log_status    = vidioc_log_status,
-	.vidioc_queryctrl     = vidioc_queryctrl,
-	.vidioc_g_ctrl        = vidioc_g_ctrl,
-	.vidioc_s_ctrl        = vidioc_s_ctrl,
-	.vidioc_streamon      = vidioc_streamon,
-	.vidioc_streamoff     = vidioc_streamoff,
 	.vidioc_g_tuner       = vidioc_g_tuner,
 	.vidioc_s_tuner       = vidioc_s_tuner,
 	.vidioc_g_frequency   = vidioc_g_frequency,
@@ -1765,6 +1103,8 @@ static const struct v4l2_ioctl_ops video_ioctl_ops = {
 	.vidioc_enumaudio     = vidioc_enum_audinput,
 	.vidioc_g_audio       = vidioc_g_audinput,
 	.vidioc_s_audio       = vidioc_s_audinput,
+	.vidioc_subscribe_event = v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
 };
 
 static struct video_device cx23885_vbi_template;
@@ -1775,14 +1115,6 @@ static struct video_device cx23885_video_template = {
 	.tvnorms              = CX23885_NORMS,
 };
 
-static const struct v4l2_file_operations radio_fops = {
-	.owner         = THIS_MODULE,
-	.open          = video_open,
-	.release       = video_release,
-	.ioctl         = video_ioctl2,
-};
-
-
 void cx23885_video_unregister(struct cx23885_dev *dev)
 {
 	dprintk(1, "%s()\n", __func__);
@@ -1794,7 +1126,6 @@ void cx23885_video_unregister(struct cx23885_dev *dev)
 		else
 			video_device_release(dev->vbi_dev);
 		dev->vbi_dev = NULL;
-		btcx_riscmem_free(dev->pci, &dev->vbiq.stopper);
 	}
 	if (dev->video_dev) {
 		if (video_is_registered(dev->video_dev))
@@ -1802,8 +1133,6 @@ void cx23885_video_unregister(struct cx23885_dev *dev)
 		else
 			video_device_release(dev->video_dev);
 		dev->video_dev = NULL;
-
-		btcx_riscmem_free(dev->pci, &dev->vidq.stopper);
 	}
 
 	if (dev->audio_dev)
@@ -1812,6 +1141,7 @@ void cx23885_video_unregister(struct cx23885_dev *dev)
 
 int cx23885_video_register(struct cx23885_dev *dev)
 {
+	struct vb2_queue *q;
 	int err;
 
 	dprintk(1, "%s()\n", __func__);
@@ -1822,24 +1152,16 @@ int cx23885_video_register(struct cx23885_dev *dev)
 	strcpy(cx23885_vbi_template.name, "cx23885-vbi");
 
 	dev->tvnorm = V4L2_STD_NTSC_M;
+	dev->fmt = format_by_fourcc(V4L2_PIX_FMT_YUYV);
+	dev->field = V4L2_FIELD_INTERLACED;
+	dev->width = 720;
+	dev->height = norm_maxh(dev->tvnorm);
 
 	/* init video dma queues */
 	INIT_LIST_HEAD(&dev->vidq.active);
-	INIT_LIST_HEAD(&dev->vidq.queued);
-	dev->vidq.timeout.function = cx23885_vid_timeout;
-	dev->vidq.timeout.data = (unsigned long)dev;
-	init_timer(&dev->vidq.timeout);
-	cx23885_risc_stopper(dev->pci, &dev->vidq.stopper,
-		VID_A_DMA_CTL, 0x11, 0x00);
 
 	/* init vbi dma queues */
 	INIT_LIST_HEAD(&dev->vbiq.active);
-	INIT_LIST_HEAD(&dev->vbiq.queued);
-	dev->vbiq.timeout.function = cx23885_vbi_timeout;
-	dev->vbiq.timeout.data = (unsigned long)dev;
-	init_timer(&dev->vbiq.timeout);
-	cx23885_risc_stopper(dev->pci, &dev->vbiq.stopper,
-		VID_A_DMA_CTL, 0x22, 0x00);
 
 	cx23885_irq_add_enable(dev, 0x01);
 
@@ -1893,9 +1215,49 @@ int cx23885_video_register(struct cx23885_dev *dev)
 		}
 	}
 
+	/* initial device configuration */
+	mutex_lock(&dev->lock);
+	cx23885_set_tvnorm(dev, dev->tvnorm);
+	cx23885_video_mux(dev, 0);
+	cx23885_audio_mux(dev, 0);
+	mutex_unlock(&dev->lock);
+
+	q = &dev->vb2_vidq;
+	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
+	q->gfp_flags = GFP_DMA32;
+	q->min_buffers_needed = 2;
+	q->drv_priv = dev;
+	q->buf_struct_size = sizeof(struct cx23885_buffer);
+	q->ops = &cx23885_video_qops;
+	q->mem_ops = &vb2_dma_sg_memops;
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->lock = &dev->lock;
+
+	err = vb2_queue_init(q);
+	if (err < 0)
+		goto fail_unreg;
+
+	q = &dev->vb2_vbiq;
+	q->type = V4L2_BUF_TYPE_VBI_CAPTURE;
+	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
+	q->gfp_flags = GFP_DMA32;
+	q->min_buffers_needed = 2;
+	q->drv_priv = dev;
+	q->buf_struct_size = sizeof(struct cx23885_buffer);
+	q->ops = &cx23885_vbi_qops;
+	q->mem_ops = &vb2_dma_sg_memops;
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->lock = &dev->lock;
+
+	err = vb2_queue_init(q);
+	if (err < 0)
+		goto fail_unreg;
+
 	/* register Video device */
 	dev->video_dev = cx23885_vdev_init(dev, dev->pci,
 		&cx23885_video_template, "video");
+	dev->video_dev->queue = &dev->vb2_vidq;
 	err = video_register_device(dev->video_dev, VFL_TYPE_GRABBER,
 				    video_nr[dev->nr]);
 	if (err < 0) {
@@ -1909,6 +1271,7 @@ int cx23885_video_register(struct cx23885_dev *dev)
 	/* register VBI device */
 	dev->vbi_dev = cx23885_vdev_init(dev, dev->pci,
 		&cx23885_vbi_template, "vbi");
+	dev->vbi_dev->queue = &dev->vb2_vbiq;
 	err = video_register_device(dev->vbi_dev, VFL_TYPE_VBI,
 				    vbi_nr[dev->nr]);
 	if (err < 0) {
@@ -1922,18 +1285,9 @@ int cx23885_video_register(struct cx23885_dev *dev)
 	/* Register ALSA audio device */
 	dev->audio_dev = cx23885_audio_register(dev);
 
-	/* initial device configuration */
-	mutex_lock(&dev->lock);
-	cx23885_set_tvnorm(dev, dev->tvnorm);
-	init_controls(dev);
-	cx23885_video_mux(dev, 0);
-	cx23885_audio_mux(dev, 0);
-	mutex_unlock(&dev->lock);
-
 	return 0;
 
 fail_unreg:
 	cx23885_video_unregister(dev);
 	return err;
 }
-
diff --git a/drivers/media/pci/cx23885/cx23885-video.h b/drivers/media/pci/cx23885/cx23885-video.h
index c961a2b0de0f..291e8f3189f0 100644
--- a/drivers/media/pci/cx23885/cx23885-video.h
+++ b/drivers/media/pci/cx23885/cx23885-video.h
@@ -12,11 +12,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- *  02110-1301, USA.
  */
 
 #ifndef _CX23885_VIDEO_H_
diff --git a/drivers/media/pci/cx23885/cx23885.h b/drivers/media/pci/cx23885/cx23885.h
index 0e086c03da67..6c35e6115969 100644
--- a/drivers/media/pci/cx23885/cx23885.h
+++ b/drivers/media/pci/cx23885/cx23885.h
@@ -13,10 +13,6 @@
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/pci.h>
@@ -25,19 +21,20 @@
 #include <linux/slab.h>
 
 #include <media/v4l2-device.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-ctrls.h>
 #include <media/tuner.h>
 #include <media/tveeprom.h>
-#include <media/videobuf-dma-sg.h>
-#include <media/videobuf-dvb.h>
+#include <media/videobuf2-dma-sg.h>
+#include <media/videobuf2-dvb.h>
 #include <media/rc-core.h>
 
-#include "btcx-risc.h"
 #include "cx23885-reg.h"
 #include "media/cx2341x.h"
 
 #include <linux/mutex.h>
 
-#define CX23885_VERSION "0.0.3"
+#define CX23885_VERSION "0.0.4"
 
 #define UNSET (-1U)
 
@@ -46,9 +43,6 @@
 /* Max number of inputs by card */
 #define MAX_CX23885_INPUT 8
 #define INPUT(nr) (&cx23885_boards[dev->board].input[nr])
-#define RESOURCE_OVERLAY       1
-#define RESOURCE_VIDEO         2
-#define RESOURCE_VBI           4
 
 #define BUFFER_TIMEOUT     (HZ)  /* 0.5 seconds */
 
@@ -98,6 +92,7 @@
 #define CX23885_BOARD_LEADTEK_WINFAST_PXPVR2200 42
 #define CX23885_BOARD_HAUPPAUGE_IMPACTVCBE     43
 #define CX23885_BOARD_DVICO_FUSIONHDTV_DVB_T_DUAL_EXP2 44
+#define CX23885_BOARD_DVBSKY_T9580             45
 
 #define GPIO_0 0x00000001
 #define GPIO_1 0x00000002
@@ -131,14 +126,6 @@ struct cx23885_fmt {
 	u32   cxformat;
 };
 
-struct cx23885_ctrl {
-	struct v4l2_queryctrl v;
-	u32                   off;
-	u32                   reg;
-	u32                   mask;
-	u32                   shift;
-};
-
 struct cx23885_tvnorm {
 	char		*name;
 	v4l2_std_id	id;
@@ -146,30 +133,6 @@ struct cx23885_tvnorm {
 	u32		cxoformat;
 };
 
-struct cx23885_fh {
-	struct cx23885_dev         *dev;
-	enum v4l2_buf_type         type;
-	int                        radio;
-	u32                        resources;
-
-	/* video overlay */
-	struct v4l2_window         win;
-	struct v4l2_clip           *clips;
-	unsigned int               nclips;
-
-	/* video capture */
-	struct cx23885_fmt         *fmt;
-	unsigned int               width, height;
-
-	/* vbi capture */
-	struct videobuf_queue      vidq;
-	struct videobuf_queue      vbiq;
-
-	/* MPEG Encoder specifics ONLY */
-	struct videobuf_queue      mpegq;
-	atomic_t                   v4l_reading;
-};
-
 enum cx23885_itype {
 	CX23885_VMUX_COMPOSITE1 = 1,
 	CX23885_VMUX_COMPOSITE2,
@@ -189,14 +152,22 @@ enum cx23885_src_sel_type {
 	CX23885_SRC_SEL_PARALLEL_MPEG_VIDEO
 };
 
+struct cx23885_riscmem {
+	unsigned int   size;
+	__le32         *cpu;
+	__le32         *jmp;
+	dma_addr_t     dma;
+};
+
 /* buffer for one video frame */
 struct cx23885_buffer {
 	/* common v4l buffer stuff -- must be first */
-	struct videobuf_buffer vb;
+	struct vb2_buffer vb;
+	struct list_head queue;
 
 	/* cx23885 specific */
 	unsigned int           bpl;
-	struct btcx_riscmem    risc;
+	struct cx23885_riscmem risc;
 	struct cx23885_fmt     *fmt;
 	u32                    count;
 };
@@ -268,9 +239,6 @@ struct cx23885_i2c {
 
 struct cx23885_dmaqueue {
 	struct list_head       active;
-	struct list_head       queued;
-	struct timer_list      timeout;
-	struct btcx_riscmem    stopper;
 	u32                    count;
 };
 
@@ -280,7 +248,7 @@ struct cx23885_tsport {
 	int                        nr;
 	int                        sram_chno;
 
-	struct videobuf_dvb_frontends frontends;
+	struct vb2_dvb_frontends   frontends;
 
 	/* dma queues */
 	struct cx23885_dmaqueue    mpegq;
@@ -326,7 +294,12 @@ struct cx23885_tsport {
 	/* Workaround for a temp dvb_frontend that the tuner can attached to */
 	struct dvb_frontend analog_fe;
 
+	struct i2c_client *i2c_client_demod;
+	struct i2c_client *i2c_client_tuner;
+
 	int (*set_frontend)(struct dvb_frontend *fe);
+	int (*fe_set_voltage)(struct dvb_frontend *fe,
+				fe_sec_voltage_t voltage);
 };
 
 struct cx23885_kernel_ir {
@@ -339,8 +312,11 @@ struct cx23885_kernel_ir {
 
 struct cx23885_audio_buffer {
 	unsigned int		bpl;
-	struct btcx_riscmem	risc;
-	struct videobuf_dmabuf	dma;
+	struct cx23885_riscmem	risc;
+	void			*vaddr;
+	struct scatterlist	*sglist;
+	int                     sglen;
+	int                     nr_pages;
 };
 
 struct cx23885_audio_dev {
@@ -358,8 +334,6 @@ struct cx23885_audio_dev {
 	unsigned int		period_size;
 	unsigned int		num_periods;
 
-	struct videobuf_dmabuf	*dma_risc;
-
 	struct cx23885_audio_buffer   *buf;
 
 	struct snd_pcm_substream *substream;
@@ -368,6 +342,7 @@ struct cx23885_audio_dev {
 struct cx23885_dev {
 	atomic_t                   refcount;
 	struct v4l2_device 	   v4l2_dev;
+	struct v4l2_ctrl_handler   ctrl_handler;
 
 	/* pci stuff */
 	struct pci_dev             *pci;
@@ -407,7 +382,6 @@ struct cx23885_dev {
 	} bridge;
 
 	/* Analog video */
-	u32                        resources;
 	unsigned int               input;
 	unsigned int               audinput; /* Selectable audio input */
 	u32                        tvaudio;
@@ -417,7 +391,6 @@ struct cx23885_dev {
 	unsigned int               tuner_bus;
 	unsigned int               radio_type;
 	unsigned char              radio_addr;
-	unsigned int               has_radio;
 	struct v4l2_subdev 	   *sd_cx25840;
 	struct work_struct	   cx25840_work;
 
@@ -435,17 +408,24 @@ struct cx23885_dev {
 	u32                        freq;
 	struct video_device        *video_dev;
 	struct video_device        *vbi_dev;
-	struct video_device        *radio_dev;
+
+	/* video capture */
+	struct cx23885_fmt         *fmt;
+	unsigned int               width, height;
+	unsigned		   field;
 
 	struct cx23885_dmaqueue    vidq;
+	struct vb2_queue           vb2_vidq;
 	struct cx23885_dmaqueue    vbiq;
+	struct vb2_queue           vb2_vbiq;
+
 	spinlock_t                 slock;
 
 	/* MPEG Encoder ONLY settings */
 	u32                        cx23417_mailbox;
-	struct cx2341x_mpeg_params mpeg_params;
+	struct cx2341x_handler     cxhdl;
 	struct video_device        *v4l_device;
-	atomic_t                   v4l_reader_count;
+	struct vb2_queue           vb2_mpegq;
 	struct cx23885_tvnorm      encodernorm;
 
 	/* Analog raw audio */
@@ -521,26 +501,21 @@ extern int cx23885_sram_channel_setup(struct cx23885_dev *dev,
 extern void cx23885_sram_channel_dump(struct cx23885_dev *dev,
 	struct sram_channel *ch);
 
-extern int cx23885_risc_stopper(struct pci_dev *pci, struct btcx_riscmem *risc,
-	u32 reg, u32 mask, u32 value);
-
-extern int cx23885_risc_buffer(struct pci_dev *pci, struct btcx_riscmem *risc,
+extern int cx23885_risc_buffer(struct pci_dev *pci, struct cx23885_riscmem *risc,
 	struct scatterlist *sglist,
 	unsigned int top_offset, unsigned int bottom_offset,
 	unsigned int bpl, unsigned int padding, unsigned int lines);
 
 extern int cx23885_risc_vbibuffer(struct pci_dev *pci,
-	struct btcx_riscmem *risc, struct scatterlist *sglist,
+	struct cx23885_riscmem *risc, struct scatterlist *sglist,
 	unsigned int top_offset, unsigned int bottom_offset,
 	unsigned int bpl, unsigned int padding, unsigned int lines);
 
+int cx23885_start_dma(struct cx23885_tsport *port,
+			     struct cx23885_dmaqueue *q,
+			     struct cx23885_buffer   *buf);
 void cx23885_cancel_buffers(struct cx23885_tsport *port);
 
-extern int cx23885_restart_queue(struct cx23885_tsport *port,
-				struct cx23885_dmaqueue *q);
-
-extern void cx23885_wakeup(struct cx23885_tsport *port,
-			   struct cx23885_dmaqueue *q, u32 count);
 
 extern void cx23885_gpio_set(struct cx23885_dev *dev, u32 mask);
 extern void cx23885_gpio_clear(struct cx23885_dev *dev, u32 mask);
@@ -574,13 +549,11 @@ extern void cx23885_card_setup_pre_i2c(struct cx23885_dev *dev);
 extern int cx23885_dvb_register(struct cx23885_tsport *port);
 extern int cx23885_dvb_unregister(struct cx23885_tsport *port);
 
-extern int cx23885_buf_prepare(struct videobuf_queue *q,
-			       struct cx23885_tsport *port,
-			       struct cx23885_buffer *buf,
-			       enum v4l2_field field);
+extern int cx23885_buf_prepare(struct cx23885_buffer *buf,
+			       struct cx23885_tsport *port);
 extern void cx23885_buf_queue(struct cx23885_tsport *port,
 			      struct cx23885_buffer *buf);
-extern void cx23885_free_buffer(struct videobuf_queue *q,
+extern void cx23885_free_buffer(struct cx23885_dev *dev,
 				struct cx23885_buffer *buf);
 
 /* ----------------------------------------------------------- */
@@ -595,8 +568,6 @@ int cx23885_enum_input(struct cx23885_dev *dev, struct v4l2_input *i);
 int cx23885_set_input(struct file *file, void *priv, unsigned int i);
 int cx23885_get_input(struct file *file, void *priv, unsigned int *i);
 int cx23885_set_frequency(struct file *file, void *priv, const struct v4l2_frequency *f);
-int cx23885_set_control(struct cx23885_dev *dev, struct v4l2_control *ctl);
-int cx23885_get_control(struct cx23885_dev *dev, struct v4l2_control *ctl);
 int cx23885_set_tvnorm(struct cx23885_dev *dev, v4l2_std_id norm);
 
 /* ----------------------------------------------------------- */
@@ -604,9 +575,7 @@ int cx23885_set_tvnorm(struct cx23885_dev *dev, v4l2_std_id norm);
 extern int cx23885_vbi_fmt(struct file *file, void *priv,
 	struct v4l2_format *f);
 extern void cx23885_vbi_timeout(unsigned long data);
-extern struct videobuf_queue_ops cx23885_vbi_qops;
-extern int cx23885_restart_vbi_queue(struct cx23885_dev *dev,
-	struct cx23885_dmaqueue *q);
+extern struct vb2_ops cx23885_vbi_qops;
 extern int cx23885_vbi_irq(struct cx23885_dev *dev, u32 status);
 
 /* cx23885-i2c.c                                                */
@@ -638,7 +607,7 @@ extern struct cx23885_audio_dev *cx23885_audio_register(
 extern void cx23885_audio_unregister(struct cx23885_dev *dev);
 extern int cx23885_audio_irq(struct cx23885_dev *dev, u32 status, u32 mask);
 extern int cx23885_risc_databuffer(struct pci_dev *pci,
-				   struct btcx_riscmem *risc,
+				   struct cx23885_riscmem *risc,
 				   struct scatterlist *sglist,
 				   unsigned int bpl,
 				   unsigned int lines,
@@ -649,15 +618,10 @@ extern int cx23885_risc_databuffer(struct pci_dev *pci,
 
 static inline unsigned int norm_maxw(v4l2_std_id norm)
 {
-	return (norm & (V4L2_STD_MN & ~V4L2_STD_PAL_Nc)) ? 720 : 768;
+	return (norm & V4L2_STD_525_60) ? 720 : 768;
 }
 
 static inline unsigned int norm_maxh(v4l2_std_id norm)
 {
-	return (norm & V4L2_STD_625_50) ? 576 : 480;
-}
-
-static inline unsigned int norm_swidth(v4l2_std_id norm)
-{
-	return (norm & (V4L2_STD_MN & ~V4L2_STD_PAL_Nc)) ? 754 : 922;
+	return (norm & V4L2_STD_525_60) ? 480 : 576;
 }
diff --git a/drivers/media/pci/cx23885/cx23888-ir.c b/drivers/media/pci/cx23885/cx23888-ir.c
index c2ff5fc01157..c1aa888af705 100644
--- a/drivers/media/pci/cx23885/cx23888-ir.c
+++ b/drivers/media/pci/cx23885/cx23888-ir.c
@@ -14,11 +14,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- *  02110-1301, USA.
  */
 
 #include <linux/kfifo.h>
diff --git a/drivers/media/pci/cx23885/cx23888-ir.h b/drivers/media/pci/cx23885/cx23888-ir.h
index d2de41caaf1d..ff74a93575d6 100644
--- a/drivers/media/pci/cx23885/cx23888-ir.h
+++ b/drivers/media/pci/cx23885/cx23888-ir.h
@@ -14,11 +14,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- *  02110-1301, USA.
  */
 
 #ifndef _CX23888_IR_H_
diff --git a/drivers/media/pci/cx23885/netup-eeprom.c b/drivers/media/pci/cx23885/netup-eeprom.c
index 98a48f500684..b6542ee4385b 100644
--- a/drivers/media/pci/cx23885/netup-eeprom.c
+++ b/drivers/media/pci/cx23885/netup-eeprom.c
@@ -17,10 +17,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #
diff --git a/drivers/media/pci/cx23885/netup-eeprom.h b/drivers/media/pci/cx23885/netup-eeprom.h
index 13926e18feba..90cac5b655d5 100644
--- a/drivers/media/pci/cx23885/netup-eeprom.h
+++ b/drivers/media/pci/cx23885/netup-eeprom.h
@@ -16,10 +16,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef NETUP_EEPROM_H
diff --git a/drivers/media/pci/cx23885/netup-init.c b/drivers/media/pci/cx23885/netup-init.c
index 0044fef7ca24..76d9487aafc8 100644
--- a/drivers/media/pci/cx23885/netup-init.c
+++ b/drivers/media/pci/cx23885/netup-init.c
@@ -17,10 +17,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include "cx23885.h"
diff --git a/drivers/media/pci/cx23885/netup-init.h b/drivers/media/pci/cx23885/netup-init.h
index d26ae4b1590e..daaa212adfba 100644
--- a/drivers/media/pci/cx23885/netup-init.h
+++ b/drivers/media/pci/cx23885/netup-init.h
@@ -17,9 +17,5 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 extern void netup_initialize(struct cx23885_dev *dev);
diff --git a/drivers/media/pci/cx25821/cx25821-video-upstream.c b/drivers/media/pci/cx25821/cx25821-video-upstream.c
index 1f43be0b04c8..a664997e1958 100644
--- a/drivers/media/pci/cx25821/cx25821-video-upstream.c
+++ b/drivers/media/pci/cx25821/cx25821-video-upstream.c
@@ -330,8 +330,9 @@ int cx25821_write_frame(struct cx25821_channel *chan,
 
 	if (frame_size - curpos < count)
 		count = frame_size - curpos;
-	memcpy((char *)out->_data_buf_virt_addr + frame_offset + curpos,
-			data, count);
+	if (copy_from_user((__force char *)out->_data_buf_virt_addr + frame_offset + curpos,
+				data, count))
+		return -EFAULT;
 	curpos += count;
 	if (curpos == frame_size) {
 		out->_frame_count++;
diff --git a/drivers/media/pci/cx88/cx88-cards.c b/drivers/media/pci/cx88/cx88-cards.c
index e18a7ace08b1..851754bf1291 100644
--- a/drivers/media/pci/cx88/cx88-cards.c
+++ b/drivers/media/pci/cx88/cx88-cards.c
@@ -78,19 +78,19 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 0,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE2,
 			.vmux   = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE3,
 			.vmux   = 2,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE4,
 			.vmux   = 3,
-		}},
+		} },
 	},
 	[CX88_BOARD_HAUPPAUGE] = {
 		.name		= "Hauppauge WinTV 34xxx models",
@@ -99,23 +99,23 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0xff00,  // internal decoder
-		},{
+		}, {
 			.type   = CX88_VMUX_DEBUG,
 			.vmux   = 0,
 			.gpio0  = 0xff01,  // mono from tuner chip
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0xff02,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0xff02,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.gpio0  = 0xff01,
@@ -127,13 +127,13 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
-		}},
+		} },
 	},
 	[CX88_BOARD_PIXELVIEW] = {
 		.name           = "PixelView",
@@ -141,17 +141,17 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0xff00,  // internal decoder
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
-		}},
+		} },
 		.radio = {
 			 .type  = CX88_RADIO,
 			 .gpio0 = 0xff10,
@@ -164,19 +164,19 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT | TDA9887_INTERCARRIER,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x03ff,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x03fe,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x03fe,
-		}},
+		} },
 	},
 	[CX88_BOARD_WINFAST2000XP_EXPERT] = {
 		.name           = "Leadtek Winfast 2000XP Expert",
@@ -185,28 +185,28 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0	= 0x00F5e700,
 			.gpio1  = 0x00003004,
 			.gpio2  = 0x00F5e700,
 			.gpio3  = 0x02000000,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0	= 0x00F5c700,
 			.gpio1  = 0x00003004,
 			.gpio2  = 0x00F5c700,
 			.gpio3  = 0x02000000,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0	= 0x00F5c700,
 			.gpio1  = 0x00003004,
 			.gpio2  = 0x00F5c700,
 			.gpio3  = 0x02000000,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.gpio0	= 0x00F5d700,
@@ -222,19 +222,19 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio1  = 0xe09f,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio1  = 0xe05f,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio1  = 0xe05f,
-		}},
+		} },
 		.radio = {
 			.gpio1  = 0xe0df,
 			.type   = CX88_RADIO,
@@ -249,25 +249,25 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf	= TDA9887_PRESENT | TDA9887_INTERCARRIER_NTSC,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x000040bf,
 			.gpio1  = 0x000080c0,
 			.gpio2  = 0x0000ff40,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x000040bf,
 			.gpio1  = 0x000080c0,
 			.gpio2  = 0x0000ff40,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x000040bf,
 			.gpio1  = 0x000080c0,
 			.gpio2  = 0x0000ff40,
-		}},
+		} },
 		.radio = {
 			 .type   = CX88_RADIO,
 			 .vmux   = 3,
@@ -283,14 +283,14 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x0035e700,
 			.gpio1  = 0x00003004,
 			.gpio2  = 0x0035e700,
 			.gpio3  = 0x02000000,
-		},{
+		}, {
 
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
@@ -298,14 +298,14 @@ static const struct cx88_board cx88_boards[] = {
 			.gpio1  = 0x00003004,
 			.gpio2  = 0x0035c700,
 			.gpio3  = 0x02000000,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x0035c700,
 			.gpio1  = 0x0035c700,
 			.gpio2  = 0x02000000,
 			.gpio3  = 0x02000000,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.gpio0  = 0x0035d700,
@@ -322,22 +322,22 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x0000bde2,
 			.audioroute = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x0000bde6,
 			.audioroute = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x0000bde6,
 			.audioroute = 1,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.gpio0  = 0x0000bd62,
@@ -351,16 +351,16 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 0,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE2,
 			.vmux   = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
-		}},
+		} },
 	},
 	[CX88_BOARD_PROLINK_PLAYTVPVR] = {
 		.name           = "Prolink PlayTV PVR",
@@ -369,19 +369,19 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf	= TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0xbff0,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0xbff3,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0xbff3,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.gpio0  = 0xbff0,
@@ -394,16 +394,16 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x0000fde6,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x0000fde6, // 0x0000fda6 L,R RCA audio in?
 			.audioroute = 1,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.gpio0  = 0x0000fde2,
@@ -417,22 +417,22 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x00000fbf,
 			.gpio2  = 0x0000fc08,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x00000fbf,
 			.gpio2  = 0x0000fc68,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x00000fbf,
 			.gpio2  = 0x0000fc68,
-		}},
+		} },
 	},
 	[CX88_BOARD_KWORLD_DVB_T] = {
 		.name           = "KWorld/VStream XPert DVB-T",
@@ -440,17 +440,17 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x0700,
 			.gpio2  = 0x0101,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x0700,
 			.gpio2  = 0x0101,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_DVICO_FUSIONHDTV_DVB_T1] = {
@@ -459,15 +459,15 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x000027df,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x000027df,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_KWORLD_LTV883] = {
@@ -476,23 +476,23 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x07f8,
-		},{
+		}, {
 			.type   = CX88_VMUX_DEBUG,
 			.vmux   = 0,
 			.gpio0  = 0x07f9,  // mono from tuner chip
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x000007fa,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x000007fa,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.gpio0  = 0x000007f8,
@@ -521,23 +521,23 @@ static const struct cx88_board cx88_boards[] = {
 		    0 - normal RF
 		    1 - high RF
 		*/
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0	= 0x0f0d,
-		},{
+		}, {
 			.type   = CX88_VMUX_CABLE,
 			.vmux   = 0,
 			.gpio0	= 0x0f05,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0	= 0x0f00,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0	= 0x0f00,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_HAUPPAUGE_DVB_T1] = {
@@ -546,10 +546,10 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_CONEXANT_DVB_T1] = {
@@ -558,10 +558,10 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_PROVIDEO_PV259] = {
@@ -570,11 +570,11 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.audioroute = 1,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_BLACKBIRD,
 	},
 	[CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_PLUS] = {
@@ -583,15 +583,15 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x000027df,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x000027df,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_DNTV_LIVE_DVB_T] = {
@@ -600,17 +600,17 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input		= {{
+		.input		= { {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x00000700,
 			.gpio2  = 0x00000101,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x00000700,
 			.gpio2  = 0x00000101,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_PCHDTV_HD3000] = {
@@ -632,19 +632,19 @@ static const struct cx88_board cx88_boards[] = {
 		 *
 		 * GPIO[16] = Remote control input
 		 */
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x00008484,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x00008400,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x00008400,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.gpio0  = 0x00008404,
@@ -659,25 +659,25 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0xed1a,
 			.gpio2  = 0x00ff,
-		},{
+		}, {
 			.type   = CX88_VMUX_DEBUG,
 			.vmux   = 0,
 			.gpio0  = 0xff01,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0xff02,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0xed92,
 			.gpio2  = 0x00ff,
-		}},
+		} },
 		.radio = {
 			 .type   = CX88_RADIO,
 			 .gpio0  = 0xed96,
@@ -692,22 +692,22 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x00009d80,
 			.audioroute = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x00009d76,
 			.audioroute = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x00009d76,
 			.audioroute = 1,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.gpio0  = 0x00009d00,
@@ -722,19 +722,19 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 1,
 			.gpio1  = 0x0000e03f,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 2,
 			.gpio1  = 0x0000e07f,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 3,
 			.gpio1  = 0x0000e07f,
-		}}
+		} }
 	},
 	[CX88_BOARD_PIXELVIEW_PLAYTV_ULTRA_PRO] = {
 		.name           = "PixelView PlayTV Ultra Pro (Stereo)",
@@ -745,19 +745,19 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		/* Some variants use a tda9874 and so need the tvaudio module. */
 		.audio_chip     = CX88_AUDIO_TVAUDIO,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0xbf61,  /* internal decoder */
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0	= 0xbf63,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0	= 0xbf63,
-		}},
+		} },
 		.radio = {
 			 .type  = CX88_RADIO,
 			 .gpio0 = 0xbf60,
@@ -770,19 +770,19 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x97ed,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x97e9,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x97e9,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_ADSTECH_DVB_T_PCI] = {
@@ -791,32 +791,32 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x0700,
 			.gpio2  = 0x0101,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x0700,
 			.gpio2  = 0x0101,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_TERRATEC_CINERGY_1400_DVB_T1] = {
 		.name           = "TerraTec Cinergy 1400 DVB-T",
 		.tuner_type     = TUNER_ABSENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 2,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_DVICO_FUSIONHDTV_5_GOLD] = {
@@ -826,19 +826,19 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x87fd,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x87f9,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x87f9,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_AVERMEDIA_ULTRATV_MC_550] = {
@@ -848,22 +848,22 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 0,
 			.gpio0  = 0x0000cd73,
 			.audioroute = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 1,
 			.gpio0  = 0x0000cd73,
 			.audioroute = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 3,
 			.gpio0  = 0x0000cdb3,
 			.audioroute = 1,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.vmux   = 2,
@@ -876,21 +876,21 @@ static const struct cx88_board cx88_boards[] = {
 		 /* Alexander Wold <awold@bigfoot.com> */
 		 .name           = "Kworld V-Stream Xpert DVD",
 		 .tuner_type     = UNSET,
-		 .input          = {{
+		 .input          = { {
 			 .type   = CX88_VMUX_COMPOSITE1,
 			 .vmux   = 1,
 			 .gpio0  = 0x03000000,
 			 .gpio1  = 0x01000000,
 			 .gpio2  = 0x02000000,
 			 .gpio3  = 0x00100000,
-		 },{
+		 }, {
 			 .type   = CX88_VMUX_SVIDEO,
 			 .vmux   = 2,
 			 .gpio0  = 0x03000000,
 			 .gpio1  = 0x01000000,
 			 .gpio2  = 0x02000000,
 			 .gpio3  = 0x00100000,
-		 }},
+		 } },
 	},
 	[CX88_BOARD_ATI_HDTVWONDER] = {
 		.name           = "ATI HDTV Wonder",
@@ -898,28 +898,28 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x00000ff7,
 			.gpio1  = 0x000000ff,
 			.gpio2  = 0x00000001,
 			.gpio3  = 0x00000000,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x00000ffe,
 			.gpio1  = 0x000000ff,
 			.gpio2  = 0x00000001,
 			.gpio3  = 0x00000000,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x00000ffe,
 			.gpio1  = 0x000000ff,
 			.gpio2  = 0x00000001,
 			.gpio3  = 0x00000000,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_WINFAST_DTV1000] = {
@@ -928,16 +928,16 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_AVERTV_303] = {
@@ -947,28 +947,28 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x00ff,
 			.gpio1  = 0xe09f,
 			.gpio2  = 0x0010,
 			.gpio3  = 0x0000,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x00ff,
 			.gpio1  = 0xe05f,
 			.gpio2  = 0x0010,
 			.gpio3  = 0x0000,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x00ff,
 			.gpio1  = 0xe05f,
 			.gpio2  = 0x0010,
 			.gpio3  = 0x0000,
-		}},
+		} },
 	},
 	[CX88_BOARD_HAUPPAUGE_NOVASPLUS_S1] = {
 		.name		= "Hauppauge Nova-S-Plus DVB-S",
@@ -978,22 +978,22 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.audio_chip	= CX88_AUDIO_WM8775,
 		.i2sinputcntl   = 2,
-		.input		= {{
+		.input		= { {
 			.type	= CX88_VMUX_DVB,
 			.vmux	= 0,
 			/* 2: Line-In */
 			.audioroute = 2,
-		},{
+		}, {
 			.type	= CX88_VMUX_COMPOSITE1,
 			.vmux	= 1,
 			/* 2: Line-In */
 			.audioroute = 2,
-		},{
+		}, {
 			.type	= CX88_VMUX_SVIDEO,
 			.vmux	= 2,
 			/* 2: Line-In */
 			.audioroute = 2,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_HAUPPAUGE_NOVASE2_S1] = {
@@ -1002,10 +1002,10 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type	= UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input		= {{
+		.input		= { {
 			.type	= CX88_VMUX_DVB,
 			.vmux	= 0,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_KWORLD_DVBS_100] = {
@@ -1015,22 +1015,22 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.audio_chip = CX88_AUDIO_WM8775,
-		.input		= {{
+		.input		= { {
 			.type	= CX88_VMUX_DVB,
 			.vmux	= 0,
 			/* 2: Line-In */
 			.audioroute = 2,
-		},{
+		}, {
 			.type	= CX88_VMUX_COMPOSITE1,
 			.vmux	= 1,
 			/* 2: Line-In */
 			.audioroute = 2,
-		},{
+		}, {
 			.type	= CX88_VMUX_SVIDEO,
 			.vmux	= 2,
 			/* 2: Line-In */
 			.audioroute = 2,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_HAUPPAUGE_HVR1100] = {
@@ -1040,16 +1040,16 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input		= {{
+		.input		= { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
-		},{
+		}, {
 			.type	= CX88_VMUX_COMPOSITE1,
 			.vmux	= 1,
-		},{
+		}, {
 			.type	= CX88_VMUX_SVIDEO,
 			.vmux	= 2,
-		}},
+		} },
 		/* fixme: Add radio support */
 		.mpeg           = CX88_MPEG_DVB,
 	},
@@ -1060,13 +1060,13 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input		= {{
+		.input		= { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
-		},{
+		}, {
 			.type	= CX88_VMUX_COMPOSITE1,
 			.vmux	= 1,
-		}},
+		} },
 		/* fixme: Add radio support */
 		.mpeg           = CX88_MPEG_DVB,
 	},
@@ -1078,19 +1078,19 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT | TDA9887_PORT1_ACTIVE |
 				  TDA9887_PORT2_ACTIVE,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0xf80808,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0	= 0xf80808,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0	= 0xf80808,
-		}},
+		} },
 		.radio = {
 			 .type  = CX88_RADIO,
 			 .gpio0 = 0xf80808,
@@ -1106,17 +1106,17 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x0700,
 			.gpio2  = 0x0101,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x0700,
 			.gpio2  = 0x0101,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_DUAL] = {
@@ -1125,15 +1125,15 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x000067df,
-		 },{
+		 }, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x000067df,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_KWORLD_HARDWARE_MPEG_TV_XPERT] = {
@@ -1142,22 +1142,22 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x3de2,
 			.gpio2  = 0x00ff,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x3de6,
 			.audioroute = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x3de6,
 			.audioroute = 1,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.gpio0  = 0x3de6,
@@ -1171,19 +1171,19 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x0000a75f,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x0000a75b,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x0000a75b,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_PCHDTV_HD5500] = {
@@ -1193,19 +1193,19 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x87fd,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x87f9,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x87f9,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_KWORLD_MCE200_DELUXE] = {
@@ -1217,11 +1217,11 @@ static const struct cx88_board cx88_boards[] = {
 		.tda9887_conf   = TDA9887_PRESENT,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x0000BDE6
-		}},
+		} },
 		.mpeg           = CX88_MPEG_BLACKBIRD,
 	},
 	[CX88_BOARD_PIXELVIEW_PLAYTV_P7000] = {
@@ -1233,11 +1233,11 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_addr	= ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT | TDA9887_PORT1_ACTIVE |
 				  TDA9887_PORT2_ACTIVE,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x5da6,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_BLACKBIRD,
 	},
 	[CX88_BOARD_NPGTECH_REALTV_TOP10FM] = {
@@ -1246,19 +1246,19 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0	= 0x0788,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0	= 0x078b,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0	= 0x078b,
-		}},
+		} },
 		.radio = {
 			 .type  = CX88_RADIO,
 			 .gpio0 = 0x074a,
@@ -1271,7 +1271,7 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x00017304,
@@ -1299,7 +1299,7 @@ static const struct cx88_board cx88_boards[] = {
 			.gpio1  = 0x0000b207,
 			.gpio2  = 0x0001d701,
 			.gpio3  = 0x02000000,
-		}},
+		} },
 		.radio = {
 			 .type  = CX88_RADIO,
 			 .gpio0 = 0x00015702,
@@ -1316,35 +1316,35 @@ static const struct cx88_board cx88_boards[] = {
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x00017300,
 			.gpio1  = 0x00008207,
 			.gpio2	= 0x00000000,
 			.gpio3  = 0x02000000,
-		},{
+		}, {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x00018300,
 			.gpio1  = 0x0000f207,
 			.gpio2	= 0x00017304,
 			.gpio3  = 0x02000000,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x00018301,
 			.gpio1  = 0x0000f207,
 			.gpio2	= 0x00017304,
 			.gpio3  = 0x02000000,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x00018301,
 			.gpio1  = 0x0000f207,
 			.gpio2	= 0x00017304,
 			.gpio3  = 0x02000000,
-		}},
+		} },
 		.radio = {
 			 .type  = CX88_RADIO,
 			 .gpio0 = 0x00015702,
@@ -1360,13 +1360,13 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type    = UNSET,
 		.tuner_addr    = ADDR_UNSET,
 		.radio_addr    = ADDR_UNSET,
-		.input  = {{
+		.input  = { {
 			.type  = CX88_VMUX_DVB,
 			.vmux  = 0,
-		},{
+		}, {
 			.type  = CX88_VMUX_COMPOSITE1,
 			.vmux  = 1,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_HAUPPAUGE_HVR3000] = {
@@ -1377,25 +1377,25 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_addr     = ADDR_UNSET,
 		.tda9887_conf   = TDA9887_PRESENT,
 		.audio_chip     = CX88_AUDIO_WM8775,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x84bf,
 			/* 1: TV Audio / FM Mono */
 			.audioroute = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x84bf,
 			/* 2: Line-In */
 			.audioroute = 2,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x84bf,
 			/* 2: Line-In */
 			.audioroute = 2,
-		}},
+		} },
 		.radio = {
 			.type   = CX88_RADIO,
 			.gpio0	= 0x84bf,
@@ -1411,19 +1411,19 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x0709,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x070b,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x070b,
-		}},
+		} },
 	},
 	[CX88_BOARD_TE_DTV_250_OEM_SWANN] = {
 		.name           = "Shenzhen Tungsten Ages Tech TE-DTV-250 / Swann OEM",
@@ -1431,28 +1431,28 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x003fffff,
 			.gpio1  = 0x00e00000,
 			.gpio2  = 0x003fffff,
 			.gpio3  = 0x02000000,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x003fffff,
 			.gpio1  = 0x00e00000,
 			.gpio2  = 0x003fffff,
 			.gpio3  = 0x02000000,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x003fffff,
 			.gpio1  = 0x00e00000,
 			.gpio2  = 0x003fffff,
 			.gpio3  = 0x02000000,
-		}},
+		} },
 	},
 	[CX88_BOARD_HAUPPAUGE_HVR1300] = {
 		.name		= "Hauppauge WinTV-HVR1300 DVB-T/Hybrid MPEG Encoder",
@@ -1465,25 +1465,25 @@ static const struct cx88_board cx88_boards[] = {
 		/*
 		 * gpio0 as reported by Mike Crash <mike AT mikecrash.com>
 		 */
-		.input		= {{
+		.input		= { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0	= 0xef88,
 			/* 1: TV Audio / FM Mono */
 			.audioroute = 1,
-		},{
+		}, {
 			.type	= CX88_VMUX_COMPOSITE1,
 			.vmux	= 1,
 			.gpio0	= 0xef88,
 			/* 2: Line-In */
 			.audioroute = 2,
-		},{
+		}, {
 			.type	= CX88_VMUX_SVIDEO,
 			.vmux	= 2,
 			.gpio0	= 0xef88,
 			/* 2: Line-In */
 			.audioroute = 2,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB | CX88_MPEG_BLACKBIRD,
 		.radio = {
 			.type   = CX88_RADIO,
@@ -1510,19 +1510,19 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DEBUG,
 			.vmux   = 3,
 			.gpio0  = 0x04ff,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x07fa,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x07fa,
-		}},
+		} },
 	},
 	[CX88_BOARD_PINNACLE_PCTV_HD_800i] = {
 		.name           = "Pinnacle PCTV HD 800i",
@@ -1530,24 +1530,24 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x04fb,
 			.gpio1  = 0x10ff,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x04fb,
 			.gpio1  = 0x10ef,
 			.audioroute = 1,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x04fb,
 			.gpio1  = 0x10ef,
 			.audioroute = 1,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_DVICO_FUSIONHDTV_5_PCI_NANO] = {
@@ -1557,7 +1557,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x000027df, /* Unconfirmed */
@@ -1815,19 +1815,19 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr	= ADDR_UNSET,
 		.radio_addr	= ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x10df,
-		},{
+		}, {
 			.type   = CX88_VMUX_COMPOSITE1,
 			.vmux   = 1,
 			.gpio0  = 0x16d9,
-		},{
+		}, {
 			.type   = CX88_VMUX_SVIDEO,
 			.vmux   = 2,
 			.gpio0  = 0x16d9,
-		}},
+		} },
 		.mpeg           = CX88_MPEG_DVB,
 	},
 	[CX88_BOARD_PROLINK_PV_8000GT] = {
@@ -1967,7 +1967,7 @@ static const struct cx88_board cx88_boards[] = {
 		 * 3: Line-In Expansion
 		 * 4: FM Stereo
 		 */
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0xc4bf,
@@ -2001,7 +2001,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
 		} },
@@ -2013,7 +2013,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
 		} },
@@ -2025,7 +2025,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
 		} },
@@ -2037,7 +2037,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
 		} },
@@ -2049,7 +2049,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
 		} },
@@ -2061,7 +2061,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
 		} },
@@ -2073,7 +2073,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
 			.gpio0  = 0x8080,
@@ -2086,7 +2086,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
 		} },
@@ -2098,7 +2098,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
 		} },
@@ -2110,7 +2110,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_DVB,
 			.vmux   = 0,
 		} },
@@ -2170,7 +2170,7 @@ static const struct cx88_board cx88_boards[] = {
 		 * 13: audio source (0=tuner audio,1=line in)
 		 * 14: FM (0=on,1=off ???)
 		 */
-		.input          = {{
+		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,
 			.gpio0  = 0x0400,       /* pin 2 = 0 */
@@ -2211,7 +2211,7 @@ static const struct cx88_board cx88_boards[] = {
 		 * 13: audio source (0=tuner audio,1=line in)
 		 * 14: FM (0=on,1=off ???)
 		 */
-		.input		= {{
+		.input		= { {
 			.type	= CX88_VMUX_TELEVISION,
 			.vmux	= 0,
 			.gpio0	= 0x0400,	/* pin 2 = 0 */
@@ -2229,7 +2229,7 @@ static const struct cx88_board cx88_boards[] = {
 			.gpio0	= 0x0400,	/* pin 2 = 0 */
 			.gpio1	= 0x6060,	/* pin 13 = 1, pin 14 = 1 */
 			.gpio2	= 0x0000,
-		}},
+		} },
 		.radio = {
 			.type	= CX88_RADIO,
 			.gpio0	= 0x0400,	/* pin 2 = 0 */
@@ -2252,7 +2252,7 @@ static const struct cx88_board cx88_boards[] = {
 		 *  14: 0: FM radio
 		 *  16: 0: RF input is cable
 		 */
-		.input		= {{
+		.input		= { {
 			.type	= CX88_VMUX_TELEVISION,
 			.vmux	= 0,
 			.gpio0	= 0x0403,
@@ -2280,7 +2280,7 @@ static const struct cx88_board cx88_boards[] = {
 			.gpio1	= 0xF0F7,
 			.gpio2	= 0x0101,
 			.gpio3	= 0x0000,
-		}},
+		} },
 		.radio = {
 			.type	= CX88_RADIO,
 			.gpio0	= 0x0403,
@@ -2308,7 +2308,7 @@ static const struct cx88_board cx88_boards[] = {
 		.radio_type     = UNSET,
 		.tuner_addr     = ADDR_UNSET,
 		.radio_addr     = ADDR_UNSET,
-		.input          = {{
+		.input          = { {
 		       .type   = CX88_VMUX_DVB,
 		       .vmux   = 0,
 		} },
@@ -2324,19 +2324,19 @@ static const struct cx88_subid cx88_subids[] = {
 		.subvendor = 0x0070,
 		.subdevice = 0x3400,
 		.card      = CX88_BOARD_HAUPPAUGE,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x3401,
 		.card      = CX88_BOARD_HAUPPAUGE,
-	},{
+	}, {
 		.subvendor = 0x14c7,
 		.subdevice = 0x0106,
 		.card      = CX88_BOARD_GDI,
-	},{
+	}, {
 		.subvendor = 0x14c7,
 		.subdevice = 0x0107, /* with mpeg encoder */
 		.card      = CX88_BOARD_GDI,
-	},{
+	}, {
 		.subvendor = PCI_VENDOR_ID_ATI,
 		.subdevice = 0x00f8,
 		.card      = CX88_BOARD_ATI_WONDER_PRO,
@@ -2348,176 +2348,176 @@ static const struct cx88_subid cx88_subids[] = {
 		.subvendor = 0x107d,
 		.subdevice = 0x6611,
 		.card      = CX88_BOARD_WINFAST2000XP_EXPERT,
-	},{
+	}, {
 		.subvendor = 0x107d,
 		.subdevice = 0x6613,	/* NTSC */
 		.card      = CX88_BOARD_WINFAST2000XP_EXPERT,
-	},{
+	}, {
 		.subvendor = 0x107d,
 		.subdevice = 0x6620,
 		.card      = CX88_BOARD_WINFAST_DV2000,
-	},{
+	}, {
 		.subvendor = 0x107d,
 		.subdevice = 0x663b,
 		.card      = CX88_BOARD_LEADTEK_PVR2000,
-	},{
+	}, {
 		.subvendor = 0x107d,
 		.subdevice = 0x663c,
 		.card      = CX88_BOARD_LEADTEK_PVR2000,
-	},{
+	}, {
 		.subvendor = 0x1461,
 		.subdevice = 0x000b,
 		.card      = CX88_BOARD_AVERTV_STUDIO_303,
-	},{
+	}, {
 		.subvendor = 0x1462,
 		.subdevice = 0x8606,
 		.card      = CX88_BOARD_MSI_TVANYWHERE_MASTER,
-	},{
+	}, {
 		.subvendor = 0x10fc,
 		.subdevice = 0xd003,
 		.card      = CX88_BOARD_IODATA_GVVCP3PCI,
-	},{
+	}, {
 		.subvendor = 0x1043,
 		.subdevice = 0x4823,  /* with mpeg encoder */
 		.card      = CX88_BOARD_ASUS_PVR_416,
-	},{
+	}, {
 		.subvendor = 0x17de,
 		.subdevice = 0x08a6,
 		.card      = CX88_BOARD_KWORLD_DVB_T,
-	},{
+	}, {
 		.subvendor = 0x18ac,
 		.subdevice = 0xd810,
 		.card      = CX88_BOARD_DVICO_FUSIONHDTV_3_GOLD_Q,
-	},{
+	}, {
 		.subvendor = 0x18ac,
 		.subdevice = 0xd820,
 		.card      = CX88_BOARD_DVICO_FUSIONHDTV_3_GOLD_T,
-	},{
+	}, {
 		.subvendor = 0x18ac,
 		.subdevice = 0xdb00,
 		.card      = CX88_BOARD_DVICO_FUSIONHDTV_DVB_T1,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9002,
 		.card      = CX88_BOARD_HAUPPAUGE_DVB_T1,
-	},{
+	}, {
 		.subvendor = 0x14f1,
 		.subdevice = 0x0187,
 		.card      = CX88_BOARD_CONEXANT_DVB_T1,
-	},{
+	}, {
 		.subvendor = 0x1540,
 		.subdevice = 0x2580,
 		.card      = CX88_BOARD_PROVIDEO_PV259,
-	},{
+	}, {
 		.subvendor = 0x18ac,
 		.subdevice = 0xdb10,
 		.card      = CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_PLUS,
-	},{
+	}, {
 		.subvendor = 0x1554,
 		.subdevice = 0x4811,
 		.card      = CX88_BOARD_PIXELVIEW,
-	},{
+	}, {
 		.subvendor = 0x7063,
 		.subdevice = 0x3000, /* HD-3000 card */
 		.card      = CX88_BOARD_PCHDTV_HD3000,
-	},{
+	}, {
 		.subvendor = 0x17de,
 		.subdevice = 0xa8a6,
 		.card      = CX88_BOARD_DNTV_LIVE_DVB_T,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x2801,
 		.card      = CX88_BOARD_HAUPPAUGE_ROSLYN,
-	},{
+	}, {
 		.subvendor = 0x14f1,
 		.subdevice = 0x0342,
 		.card      = CX88_BOARD_DIGITALLOGIC_MEC,
-	},{
+	}, {
 		.subvendor = 0x10fc,
 		.subdevice = 0xd035,
 		.card      = CX88_BOARD_IODATA_GVBCTV7E,
-	},{
+	}, {
 		.subvendor = 0x1421,
 		.subdevice = 0x0334,
 		.card      = CX88_BOARD_ADSTECH_DVB_T_PCI,
-	},{
+	}, {
 		.subvendor = 0x153b,
 		.subdevice = 0x1166,
 		.card      = CX88_BOARD_TERRATEC_CINERGY_1400_DVB_T1,
-	},{
+	}, {
 		.subvendor = 0x18ac,
 		.subdevice = 0xd500,
 		.card      = CX88_BOARD_DVICO_FUSIONHDTV_5_GOLD,
-	},{
+	}, {
 		.subvendor = 0x1461,
 		.subdevice = 0x8011,
 		.card      = CX88_BOARD_AVERMEDIA_ULTRATV_MC_550,
-	},{
+	}, {
 		.subvendor = PCI_VENDOR_ID_ATI,
 		.subdevice = 0xa101,
 		.card      = CX88_BOARD_ATI_HDTVWONDER,
-	},{
+	}, {
 		.subvendor = 0x107d,
 		.subdevice = 0x665f,
 		.card      = CX88_BOARD_WINFAST_DTV1000,
-	},{
+	}, {
 		.subvendor = 0x1461,
 		.subdevice = 0x000a,
 		.card      = CX88_BOARD_AVERTV_303,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9200,
 		.card      = CX88_BOARD_HAUPPAUGE_NOVASE2_S1,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9201,
 		.card      = CX88_BOARD_HAUPPAUGE_NOVASPLUS_S1,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9202,
 		.card      = CX88_BOARD_HAUPPAUGE_NOVASPLUS_S1,
-	},{
+	}, {
 		.subvendor = 0x17de,
 		.subdevice = 0x08b2,
 		.card      = CX88_BOARD_KWORLD_DVBS_100,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9400,
 		.card      = CX88_BOARD_HAUPPAUGE_HVR1100,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9402,
 		.card      = CX88_BOARD_HAUPPAUGE_HVR1100,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9800,
 		.card      = CX88_BOARD_HAUPPAUGE_HVR1100LP,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9802,
 		.card      = CX88_BOARD_HAUPPAUGE_HVR1100LP,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9001,
 		.card      = CX88_BOARD_HAUPPAUGE_DVB_T1,
-	},{
+	}, {
 		.subvendor = 0x1822,
 		.subdevice = 0x0025,
 		.card      = CX88_BOARD_DNTV_LIVE_DVB_T_PRO,
-	},{
+	}, {
 		.subvendor = 0x17de,
 		.subdevice = 0x08a1,
 		.card      = CX88_BOARD_KWORLD_DVB_T_CX22702,
-	},{
+	}, {
 		.subvendor = 0x18ac,
 		.subdevice = 0xdb50,
 		.card      = CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_DUAL,
-	},{
+	}, {
 		.subvendor = 0x18ac,
 		.subdevice = 0xdb54,
 		.card      = CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_DUAL,
 		/* Re-branded DViCO: DigitalNow DVB-T Dual */
-	},{
+	}, {
 		.subvendor = 0x18ac,
 		.subdevice = 0xdb11,
 		.card      = CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_PLUS,
@@ -2530,55 +2530,55 @@ static const struct cx88_subid cx88_subids[] = {
 		.subvendor = 0x17de,
 		.subdevice = 0x0840,
 		.card      = CX88_BOARD_KWORLD_HARDWARE_MPEG_TV_XPERT,
-	},{
+	}, {
 		.subvendor = 0x1421,
 		.subdevice = 0x0305,
 		.card      = CX88_BOARD_KWORLD_HARDWARE_MPEG_TV_XPERT,
-	},{
+	}, {
 		.subvendor = 0x18ac,
 		.subdevice = 0xdb40,
 		.card      = CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_HYBRID,
-	},{
+	}, {
 		.subvendor = 0x18ac,
 		.subdevice = 0xdb44,
 		.card      = CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_HYBRID,
-	},{
+	}, {
 		.subvendor = 0x7063,
 		.subdevice = 0x5500,
 		.card      = CX88_BOARD_PCHDTV_HD5500,
-	},{
+	}, {
 		.subvendor = 0x17de,
 		.subdevice = 0x0841,
 		.card      = CX88_BOARD_KWORLD_MCE200_DELUXE,
-	},{
+	}, {
 		.subvendor = 0x1822,
 		.subdevice = 0x0019,
 		.card      = CX88_BOARD_DNTV_LIVE_DVB_T_PRO,
-	},{
+	}, {
 		.subvendor = 0x1554,
 		.subdevice = 0x4813,
 		.card      = CX88_BOARD_PIXELVIEW_PLAYTV_P7000,
-	},{
+	}, {
 		.subvendor = 0x14f1,
 		.subdevice = 0x0842,
 		.card      = CX88_BOARD_NPGTECH_REALTV_TOP10FM,
-	},{
+	}, {
 		.subvendor = 0x107d,
 		.subdevice = 0x665e,
 		.card      = CX88_BOARD_WINFAST_DTV2000H,
-	},{
+	}, {
 		.subvendor = 0x107d,
 		.subdevice = 0x6f2b,
 		.card      = CX88_BOARD_WINFAST_DTV2000H_J,
-	},{
+	}, {
 		.subvendor = 0x18ac,
 		.subdevice = 0xd800, /* FusionHDTV 3 Gold (original revision) */
 		.card      = CX88_BOARD_DVICO_FUSIONHDTV_3_GOLD_Q,
-	},{
+	}, {
 		.subvendor = 0x14f1,
 		.subdevice = 0x0084,
 		.card      = CX88_BOARD_GENIATECH_DVBS,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x1404,
 		.card      = CX88_BOARD_HAUPPAUGE_HVR3000,
@@ -2590,60 +2590,60 @@ static const struct cx88_subid cx88_subids[] = {
 		.subvendor = 0x18ac,
 		.subdevice = 0xdccd,
 		.card      = CX88_BOARD_SAMSUNG_SMT_7020,
-	},{
+	}, {
 		.subvendor = 0x1461,
 		.subdevice = 0xc111, /* AverMedia M150-D */
 		/* This board is known to work with the ASUS PVR416 config */
 		.card      = CX88_BOARD_ASUS_PVR_416,
-	},{
+	}, {
 		.subvendor = 0xc180,
 		.subdevice = 0xc980,
 		.card      = CX88_BOARD_TE_DTV_250_OEM_SWANN,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9600,
 		.card      = CX88_BOARD_HAUPPAUGE_HVR1300,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9601,
 		.card      = CX88_BOARD_HAUPPAUGE_HVR1300,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9602,
 		.card      = CX88_BOARD_HAUPPAUGE_HVR1300,
-	},{
+	}, {
 		.subvendor = 0x107d,
 		.subdevice = 0x6632,
 		.card      = CX88_BOARD_LEADTEK_PVR2000,
-	},{
+	}, {
 		.subvendor = 0x12ab,
 		.subdevice = 0x2300, /* Club3D Zap TV2100 */
 		.card      = CX88_BOARD_KWORLD_DVB_T_CX22702,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x9000,
 		.card      = CX88_BOARD_HAUPPAUGE_DVB_T1,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x1400,
 		.card      = CX88_BOARD_HAUPPAUGE_HVR3000,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x1401,
 		.card      = CX88_BOARD_HAUPPAUGE_HVR3000,
-	},{
+	}, {
 		.subvendor = 0x0070,
 		.subdevice = 0x1402,
 		.card      = CX88_BOARD_HAUPPAUGE_HVR3000,
-	},{
+	}, {
 		.subvendor = 0x1421,
 		.subdevice = 0x0341, /* ADS Tech InstantTV DVB-S */
 		.card      = CX88_BOARD_KWORLD_DVBS_100,
-	},{
+	}, {
 		.subvendor = 0x1421,
 		.subdevice = 0x0390,
 		.card      = CX88_BOARD_ADSTECH_PTV_390,
-	},{
+	}, {
 		.subvendor = 0x11bd,
 		.subdevice = 0x0051,
 		.card      = CX88_BOARD_PINNACLE_PCTV_HD_800i,
diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c
index ed8cb9037b6f..ce27e6d4f16e 100644
--- a/drivers/media/pci/cx88/cx88-video.c
+++ b/drivers/media/pci/cx88/cx88-video.c
@@ -696,7 +696,6 @@ static struct videobuf_queue *get_queue(struct file *file)
 		return &fh->vbiq;
 	default:
 		BUG();
-		return NULL;
 	}
 }
 
@@ -711,7 +710,6 @@ static int get_resource(struct file *file)
 		return RESOURCE_VBI;
 	default:
 		BUG();
-		return 0;
 	}
 }
 
@@ -812,7 +810,6 @@ video_read(struct file *file, char __user *data, size_t count, loff_t *ppos)
 					    file->f_flags & O_NONBLOCK);
 	default:
 		BUG();
-		return 0;
 	}
 }
 
diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index da8f848be3b8..c82e855a0814 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -149,7 +149,7 @@ static u32 ddb_i2c_functionality(struct i2c_adapter *adap)
 	return I2C_FUNC_SMBUS_EMUL;
 }
 
-struct i2c_algorithm ddb_i2c_algo = {
+static struct i2c_algorithm ddb_i2c_algo = {
 	.master_xfer   = ddb_i2c_master_xfer,
 	.functionality = ddb_i2c_functionality,
 };
@@ -266,7 +266,7 @@ static void io_free(struct pci_dev *pdev, u8 **vbuf,
 	for (i = 0; i < num; i++) {
 		if (vbuf[i]) {
 			pci_free_consistent(pdev, size, vbuf[i], pbuf[i]);
-			vbuf[i] = 0;
+			vbuf[i] = NULL;
 		}
 	}
 }
@@ -440,7 +440,7 @@ static u32 ddb_output_free(struct ddb_output *output)
 }
 
 static ssize_t ddb_output_write(struct ddb_output *output,
-				const u8 *buf, size_t count)
+				const __user u8 *buf, size_t count)
 {
 	struct ddb *dev = output->port->dev;
 	u32 idx, off, stat = output->stat;
@@ -506,7 +506,7 @@ static u32 ddb_input_avail(struct ddb_input *input)
 	return 0;
 }
 
-static ssize_t ddb_input_read(struct ddb_input *input, u8 *buf, size_t count)
+static ssize_t ddb_input_read(struct ddb_input *input, __user u8 *buf, size_t count)
 {
 	struct ddb *dev = input->port->dev;
 	u32 left = count;
@@ -849,7 +849,7 @@ static int dvb_input_attach(struct ddb_input *input)
 		return ret;
 	input->attached = 4;
 
-	input->fe = 0;
+	input->fe = NULL;
 	switch (port->type) {
 	case DDB_TUNER_DVBS_ST:
 		if (demod_attach_stv0900(input, 0) < 0)
@@ -895,7 +895,7 @@ static int dvb_input_attach(struct ddb_input *input)
 /****************************************************************************/
 /****************************************************************************/
 
-static ssize_t ts_write(struct file *file, const char *buf,
+static ssize_t ts_write(struct file *file, const __user char *buf,
 			size_t count, loff_t *ppos)
 {
 	struct dvb_device *dvbdev = file->private_data;
@@ -920,7 +920,7 @@ static ssize_t ts_write(struct file *file, const char *buf,
 	return (left == count) ? -EAGAIN : (count - left);
 }
 
-static ssize_t ts_read(struct file *file, char *buf,
+static ssize_t ts_read(struct file *file, __user char *buf,
 		       size_t count, loff_t *ppos)
 {
 	struct dvb_device *dvbdev = file->private_data;
@@ -975,11 +975,9 @@ static const struct file_operations ci_fops = {
 	.open    = dvb_generic_open,
 	.release = dvb_generic_release,
 	.poll    = ts_poll,
-	.mmap    = 0,
 };
 
 static struct dvb_device dvbdev_ci = {
-	.priv    = 0,
 	.readers = -1,
 	.writers = -1,
 	.users   = -1,
@@ -1038,7 +1036,7 @@ static void output_tasklet(unsigned long data)
 }
 
 
-struct cxd2099_cfg cxd_cfg = {
+static struct cxd2099_cfg cxd_cfg = {
 	.bitrate =  62000,
 	.adr     =  0x40,
 	.polarity = 1,
@@ -1127,7 +1125,7 @@ static void ddb_ports_detach(struct ddb *dev)
 				ddb_output_stop(port->output);
 				dvb_ca_en50221_release(port->en);
 				kfree(port->en);
-				port->en = 0;
+				port->en = NULL;
 				dvb_unregister_adapter(&port->output->adap);
 			}
 			break;
@@ -1413,9 +1411,9 @@ static int flashio(struct ddb *dev, u8 *wbuf, u32 wlen, u8 *rbuf, u32 rlen)
 #define DDB_MAGIC 'd'
 
 struct ddb_flashio {
-	__u8 *write_buf;
+	__user __u8 *write_buf;
 	__u32 write_len;
-	__u8 *read_buf;
+	__user __u8 *read_buf;
 	__u32 read_len;
 };
 
@@ -1439,7 +1437,7 @@ static int ddb_open(struct inode *inode, struct file *file)
 static long ddb_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct ddb *dev = file->private_data;
-	void *parg = (void *)arg;
+	__user void *parg = (__user void *)arg;
 	int res;
 
 	switch (cmd) {
@@ -1558,7 +1556,7 @@ static void ddb_remove(struct pci_dev *pdev)
 	ddb_device_destroy(dev);
 
 	ddb_unmap(dev);
-	pci_set_drvdata(pdev, 0);
+	pci_set_drvdata(pdev, NULL);
 	pci_disable_device(pdev);
 }
 
@@ -1637,7 +1635,7 @@ fail1:
 fail:
 	printk(KERN_ERR "fail\n");
 	ddb_unmap(dev);
-	pci_set_drvdata(pdev, 0);
+	pci_set_drvdata(pdev, NULL);
 	pci_disable_device(pdev);
 	return -1;
 }
diff --git a/drivers/media/pci/ddbridge/ddbridge.h b/drivers/media/pci/ddbridge/ddbridge.h
index 8b1b41d2a52d..be87fbd90456 100644
--- a/drivers/media/pci/ddbridge/ddbridge.h
+++ b/drivers/media/pci/ddbridge/ddbridge.h
@@ -156,7 +156,7 @@ struct ddb_port {
 
 struct ddb {
 	struct pci_dev        *pdev;
-	unsigned char         *regs;
+	unsigned char __iomem *regs;
 	struct ddb_port        port[DDB_MAX_PORT];
 	struct ddb_i2c         i2c[DDB_MAX_I2C];
 	struct ddb_input       input[DDB_MAX_INPUT];
@@ -173,12 +173,10 @@ struct ddb {
 /****************************************************************************/
 
 #define ddbwritel(_val, _adr)        writel((_val), \
-				     (char *) (dev->regs+(_adr)))
-#define ddbreadl(_adr)               readl((char *) (dev->regs+(_adr)))
-#define ddbcpyto(_adr, _src, _count) memcpy_toio((char *)	\
-				     (dev->regs+(_adr)), (_src), (_count))
-#define ddbcpyfrom(_dst, _adr, _count) memcpy_fromio((_dst), (char *) \
-				       (dev->regs+(_adr)), (_count))
+				     dev->regs+(_adr))
+#define ddbreadl(_adr)               readl(dev->regs+(_adr))
+#define ddbcpyto(_adr, _src, _count) memcpy_toio(dev->regs+(_adr), (_src), (_count))
+#define ddbcpyfrom(_dst, _adr, _count) memcpy_fromio((_dst), dev->regs+(_adr), (_count))
 
 /****************************************************************************/
 
diff --git a/drivers/media/pci/dm1105/dm1105.c b/drivers/media/pci/dm1105/dm1105.c
index e8826c535ccd..ed11716731e9 100644
--- a/drivers/media/pci/dm1105/dm1105.c
+++ b/drivers/media/pci/dm1105/dm1105.c
@@ -614,7 +614,7 @@ static int dm1105_set_voltage(struct dvb_frontend *fe, fe_sec_voltage_t voltage)
 
 static void dm1105_set_dma_addr(struct dm1105_dev *dev)
 {
-	dm_writel(DM1105_STADR, cpu_to_le32(dev->dma_addr));
+	dm_writel(DM1105_STADR, (__force u32)cpu_to_le32(dev->dma_addr));
 }
 
 static int dm1105_dma_map(struct dm1105_dev *dev)
diff --git a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
index 7a9b98bc208b..7bf9cbca4fa6 100644
--- a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
+++ b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
@@ -81,7 +81,7 @@ static void ivtv_alsa_announce_pcm_data(struct snd_ivtv_card *itvsc,
 	int period_elapsed = 0;
 	int length;
 
-	dprintk("ivtv alsa announce ptr=%p data=%p num_bytes=%zd\n", itvsc,
+	dprintk("ivtv alsa announce ptr=%p data=%p num_bytes=%zu\n", itvsc,
 		pcm_data, num_bytes);
 
 	substream = itvsc->capture_pcm_substream;
diff --git a/drivers/media/pci/ivtv/ivtv-firmware.c b/drivers/media/pci/ivtv/ivtv-firmware.c
index ed73edd2bcd3..4b0e758a7bce 100644
--- a/drivers/media/pci/ivtv/ivtv-firmware.c
+++ b/drivers/media/pci/ivtv/ivtv-firmware.c
@@ -65,7 +65,7 @@ retry:
 			   the wrong file was sometimes loaded. So we check filesizes to
 			   see if at least the right-sized file was loaded. If not, then we
 			   retry. */
-			IVTV_INFO("Retry: file loaded was not %s (expected size %ld, got %zd)\n", fn, size, fw->size);
+			IVTV_INFO("Retry: file loaded was not %s (expected size %ld, got %zu)\n", fn, size, fw->size);
 			release_firmware(fw);
 			retries--;
 			goto retry;
@@ -76,7 +76,7 @@ retry:
 			dst++;
 			src++;
 		}
-		IVTV_INFO("Loaded %s firmware (%zd bytes)\n", fn, fw->size);
+		IVTV_INFO("Loaded %s firmware (%zu bytes)\n", fn, fw->size);
 		release_firmware(fw);
 		return size;
 	}
diff --git a/drivers/media/pci/ivtv/ivtv-irq.c b/drivers/media/pci/ivtv/ivtv-irq.c
index 19a7c9b990a3..ab6d5d25aa6f 100644
--- a/drivers/media/pci/ivtv/ivtv-irq.c
+++ b/drivers/media/pci/ivtv/ivtv-irq.c
@@ -192,11 +192,11 @@ static int stream_enc_dma_append(struct ivtv_stream *s, u32 data[CX2341X_MBOX_MA
 		if (itv->has_cx23415 && (s->type == IVTV_ENC_STREAM_TYPE_PCM ||
 		    s->type == IVTV_DEC_STREAM_TYPE_VBI)) {
 			s->pending_backup = read_dec(offset - IVTV_DECODER_OFFSET);
-			write_dec_sync(cpu_to_le32(DMA_MAGIC_COOKIE), offset - IVTV_DECODER_OFFSET);
+			write_dec_sync(DMA_MAGIC_COOKIE, offset - IVTV_DECODER_OFFSET);
 		}
 		else {
 			s->pending_backup = read_enc(offset);
-			write_enc_sync(cpu_to_le32(DMA_MAGIC_COOKIE), offset);
+			write_enc_sync(DMA_MAGIC_COOKIE, offset);
 		}
 		s->pending_offset = offset;
 	}
@@ -275,13 +275,11 @@ static void dma_post(struct ivtv_stream *s)
 
 		if (x == 0 && ivtv_use_dma(s)) {
 			offset = s->dma_last_offset;
-			if (u32buf[offset / 4] != DMA_MAGIC_COOKIE)
+			if (le32_to_cpu(u32buf[offset / 4]) != DMA_MAGIC_COOKIE)
 			{
-				for (offset = 0; offset < 64; offset++) {
-					if (u32buf[offset] == DMA_MAGIC_COOKIE) {
+				for (offset = 0; offset < 64; offset++)
+					if (le32_to_cpu(u32buf[offset]) == DMA_MAGIC_COOKIE)
 						break;
-					}
-				}
 				offset *= 4;
 				if (offset == 256) {
 					IVTV_DEBUG_WARN("%s: Couldn't find start of buffer within the first 256 bytes\n", s->name);
diff --git a/drivers/media/pci/mantis/hopper_vp3028.c b/drivers/media/pci/mantis/hopper_vp3028.c
index 68a29f8bdf73..1032db6bb789 100644
--- a/drivers/media/pci/mantis/hopper_vp3028.c
+++ b/drivers/media/pci/mantis/hopper_vp3028.c
@@ -34,7 +34,7 @@
 #include "mantis_dvb.h"
 #include "hopper_vp3028.h"
 
-struct zl10353_config hopper_vp3028_config = {
+static struct zl10353_config hopper_vp3028_config = {
 	.demod_address	= 0x0f,
 };
 
diff --git a/drivers/media/pci/mantis/mantis_common.h b/drivers/media/pci/mantis/mantis_common.h
index f2410cf0a6bf..8ff448bb792d 100644
--- a/drivers/media/pci/mantis/mantis_common.h
+++ b/drivers/media/pci/mantis/mantis_common.h
@@ -127,7 +127,7 @@ struct mantis_pci {
 	u32			last_block;
 	u8			*buf_cpu;
 	dma_addr_t		buf_dma;
-	u32			*risc_cpu;
+	__le32			*risc_cpu;
 	dma_addr_t		risc_dma;
 
 	struct tasklet_struct	tasklet;
diff --git a/drivers/media/pci/mantis/mantis_vp1033.c b/drivers/media/pci/mantis/mantis_vp1033.c
index 115003e8d19d..12a6adb2bd7e 100644
--- a/drivers/media/pci/mantis/mantis_vp1033.c
+++ b/drivers/media/pci/mantis/mantis_vp1033.c
@@ -35,7 +35,7 @@
 #include "mantis_vp1033.h"
 #include "mantis_reg.h"
 
-u8 lgtdqcs001f_inittab[] = {
+static u8 lgtdqcs001f_inittab[] = {
 	0x01, 0x15,
 	0x02, 0x30,
 	0x03, 0x00,
@@ -150,7 +150,7 @@ static int lgtdqcs001f_set_symbol_rate(struct dvb_frontend *fe,
 	return 0;
 }
 
-struct stv0299_config lgtdqcs001f_config = {
+static struct stv0299_config lgtdqcs001f_config = {
 	.demod_address		= 0x68,
 	.inittab		= lgtdqcs001f_inittab,
 	.mclk			= 88000000UL,
diff --git a/drivers/media/pci/mantis/mantis_vp1034.c b/drivers/media/pci/mantis/mantis_vp1034.c
index 430ae84ce528..7c1bd167225c 100644
--- a/drivers/media/pci/mantis/mantis_vp1034.c
+++ b/drivers/media/pci/mantis/mantis_vp1034.c
@@ -36,7 +36,7 @@
 #include "mantis_vp1034.h"
 #include "mantis_reg.h"
 
-struct mb86a16_config vp1034_mb86a16_config = {
+static struct mb86a16_config vp1034_mb86a16_config = {
 	.demod_address	= 0x08,
 	.set_voltage	= vp1034_set_voltage,
 };
diff --git a/drivers/media/pci/mantis/mantis_vp1041.c b/drivers/media/pci/mantis/mantis_vp1041.c
index 07a20748b707..7082fcbc94a1 100644
--- a/drivers/media/pci/mantis/mantis_vp1041.c
+++ b/drivers/media/pci/mantis/mantis_vp1041.c
@@ -263,7 +263,7 @@ static const struct stb0899_s1_reg vp1041_stb0899_s1_init_3[] = {
 	{ 0xffff			, 0xff },
 };
 
-struct stb0899_config vp1041_stb0899_config = {
+static struct stb0899_config vp1041_stb0899_config = {
 	.init_dev		= vp1041_stb0899_s1_init_1,
 	.init_s2_demod		= stb0899_s2_init_2,
 	.init_s1_demod		= vp1041_stb0899_s1_init_3,
@@ -300,7 +300,7 @@ struct stb0899_config vp1041_stb0899_config = {
 	.tuner_set_rfsiggain	= NULL,
 };
 
-struct stb6100_config vp1041_stb6100_config = {
+static struct stb6100_config vp1041_stb6100_config = {
 	.tuner_address	= 0x60,
 	.refclock	= 27000000,
 };
diff --git a/drivers/media/pci/mantis/mantis_vp2033.c b/drivers/media/pci/mantis/mantis_vp2033.c
index 1ca6837fbe46..8d48b5abe04a 100644
--- a/drivers/media/pci/mantis/mantis_vp2033.c
+++ b/drivers/media/pci/mantis/mantis_vp2033.c
@@ -37,12 +37,12 @@
 #define MANTIS_MODEL_NAME	"VP-2033"
 #define MANTIS_DEV_TYPE		"DVB-C"
 
-struct tda1002x_config vp2033_tda1002x_cu1216_config = {
+static struct tda1002x_config vp2033_tda1002x_cu1216_config = {
 	.demod_address = 0x18 >> 1,
 	.invert = 1,
 };
 
-struct tda10023_config vp2033_tda10023_cu1216_config = {
+static struct tda10023_config vp2033_tda10023_cu1216_config = {
 	.demod_address = 0x18 >> 1,
 	.invert = 1,
 };
diff --git a/drivers/media/pci/mantis/mantis_vp2040.c b/drivers/media/pci/mantis/mantis_vp2040.c
index d480741afd78..8dd17d7c0881 100644
--- a/drivers/media/pci/mantis/mantis_vp2040.c
+++ b/drivers/media/pci/mantis/mantis_vp2040.c
@@ -37,12 +37,12 @@
 #define MANTIS_MODEL_NAME	"VP-2040"
 #define MANTIS_DEV_TYPE		"DVB-C"
 
-struct tda1002x_config vp2040_tda1002x_cu1216_config = {
+static struct tda1002x_config vp2040_tda1002x_cu1216_config = {
 	.demod_address	= 0x18 >> 1,
 	.invert		= 1,
 };
 
-struct tda10023_config vp2040_tda10023_cu1216_config = {
+static struct tda10023_config vp2040_tda10023_cu1216_config = {
 	.demod_address	= 0x18 >> 1,
 	.invert		= 1,
 };
diff --git a/drivers/media/pci/mantis/mantis_vp3030.c b/drivers/media/pci/mantis/mantis_vp3030.c
index c09308cd3ac6..5c1dd925bdd5 100644
--- a/drivers/media/pci/mantis/mantis_vp3030.c
+++ b/drivers/media/pci/mantis/mantis_vp3030.c
@@ -35,11 +35,11 @@
 #include "mantis_dvb.h"
 #include "mantis_vp3030.h"
 
-struct zl10353_config mantis_vp3030_config = {
+static struct zl10353_config mantis_vp3030_config = {
 	.demod_address		= 0x0f,
 };
 
-struct tda665x_config env57h12d5_config = {
+static struct tda665x_config env57h12d5_config = {
 	.name			= "ENV57H12D5 (ET-50DT)",
 	.addr			= 0x60,
 	.frequency_min		=  47000000,
diff --git a/drivers/media/pci/ngene/ngene-cards.c b/drivers/media/pci/ngene/ngene-cards.c
index 9e82d2105d53..039bed3cc919 100644
--- a/drivers/media/pci/ngene/ngene-cards.c
+++ b/drivers/media/pci/ngene/ngene-cards.c
@@ -696,7 +696,7 @@ static struct ngene_info ngene_info_m780 = {
 	.demod_attach   = { NULL, demod_attach_lg330x },
 
 	/* Ensure these are NULL else the frame will call them (as funcs) */
-	.tuner_attach   = { 0, 0, 0, 0 },
+	.tuner_attach   = { NULL, NULL, NULL, NULL },
 	.fe_config      = { NULL, &aver_m780 },
 	.avf            = { 0 },
 
diff --git a/drivers/media/pci/ngene/ngene-core.c b/drivers/media/pci/ngene/ngene-core.c
index 4930b55fd5f4..e29bc3af4baf 100644
--- a/drivers/media/pci/ngene/ngene-core.c
+++ b/drivers/media/pci/ngene/ngene-core.c
@@ -57,15 +57,13 @@ DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
 #define dprintk	if (debug) printk
 
-#define ngwriteb(dat, adr)         writeb((dat), (char *)(dev->iomem + (adr)))
-#define ngwritel(dat, adr)         writel((dat), (char *)(dev->iomem + (adr)))
-#define ngwriteb(dat, adr)         writeb((dat), (char *)(dev->iomem + (adr)))
+#define ngwriteb(dat, adr)         writeb((dat), dev->iomem + (adr))
+#define ngwritel(dat, adr)         writel((dat), dev->iomem + (adr))
+#define ngwriteb(dat, adr)         writeb((dat), dev->iomem + (adr))
 #define ngreadl(adr)               readl(dev->iomem + (adr))
 #define ngreadb(adr)               readb(dev->iomem + (adr))
-#define ngcpyto(adr, src, count)   memcpy_toio((char *) \
-				   (dev->iomem + (adr)), (src), (count))
-#define ngcpyfrom(dst, adr, count) memcpy_fromio((dst), (char *) \
-				   (dev->iomem + (adr)), (count))
+#define ngcpyto(adr, src, count)   memcpy_toio(dev->iomem + (adr), (src), (count))
+#define ngcpyfrom(dst, adr, count) memcpy_fromio((dst), dev->iomem + (adr), (count))
 
 /****************************************************************************/
 /* nGene interrupt handler **************************************************/
@@ -1592,7 +1590,7 @@ static void cxd_detach(struct ngene *dev)
 
 	dvb_ca_en50221_release(ci->en);
 	kfree(ci->en);
-	ci->en = 0;
+	ci->en = NULL;
 }
 
 /***********************************/
diff --git a/drivers/media/pci/ngene/ngene-dvb.c b/drivers/media/pci/ngene/ngene-dvb.c
index fcb16a615aab..59bb2858c8d0 100644
--- a/drivers/media/pci/ngene/ngene-dvb.c
+++ b/drivers/media/pci/ngene/ngene-dvb.c
@@ -47,7 +47,7 @@
 /* COMMAND API interface ****************************************************/
 /****************************************************************************/
 
-static ssize_t ts_write(struct file *file, const char *buf,
+static ssize_t ts_write(struct file *file, const char __user *buf,
 			size_t count, loff_t *ppos)
 {
 	struct dvb_device *dvbdev = file->private_data;
@@ -59,12 +59,12 @@ static ssize_t ts_write(struct file *file, const char *buf,
 				     (&dev->tsout_rbuf) >= count) < 0)
 		return 0;
 
-	dvb_ringbuffer_write(&dev->tsout_rbuf, buf, count);
+	dvb_ringbuffer_write_user(&dev->tsout_rbuf, buf, count);
 
 	return count;
 }
 
-static ssize_t ts_read(struct file *file, char *buf,
+static ssize_t ts_read(struct file *file, char __user *buf,
 		       size_t count, loff_t *ppos)
 {
 	struct dvb_device *dvbdev = file->private_data;
@@ -97,7 +97,6 @@ static const struct file_operations ci_fops = {
 };
 
 struct dvb_device ngene_dvbdev_ci = {
-	.priv    = 0,
 	.readers = -1,
 	.writers = -1,
 	.users   = -1,
diff --git a/drivers/media/pci/ngene/ngene.h b/drivers/media/pci/ngene/ngene.h
index 22c39ff6bfa0..51e2fbd18b1b 100644
--- a/drivers/media/pci/ngene/ngene.h
+++ b/drivers/media/pci/ngene/ngene.h
@@ -737,7 +737,7 @@ typedef void (tx_cb_t)(struct ngene *, u32);
 struct ngene {
 	int                   nr;
 	struct pci_dev       *pci_dev;
-	unsigned char        *iomem;
+	unsigned char __iomem *iomem;
 
 	/*struct i2c_adapter  i2c_adapter;*/
 
diff --git a/drivers/media/pci/pt3/Kconfig b/drivers/media/pci/pt3/Kconfig
new file mode 100644
index 000000000000..16c208ae0079
--- /dev/null
+++ b/drivers/media/pci/pt3/Kconfig
@@ -0,0 +1,10 @@
+config DVB_PT3
+	tristate "Earthsoft PT3 cards"
+	depends on DVB_CORE && PCI && I2C
+	select DVB_TC90522 if MEDIA_SUBDRV_AUTOSELECT
+	select MEDIA_TUNER_QM1D1C0042 if MEDIA_SUBDRV_AUTOSELECT
+	select MEDIA_TUNER_MXL301RF if MEDIA_SUBDRV_AUTOSELECT
+	help
+	  Support for Earthsoft PT3 PCIe cards.
+
+	  Say Y or M if you own such a device and want to use it.
diff --git a/drivers/media/pci/pt3/Makefile b/drivers/media/pci/pt3/Makefile
new file mode 100644
index 000000000000..396f146b1c18
--- /dev/null
+++ b/drivers/media/pci/pt3/Makefile
@@ -0,0 +1,8 @@
+
+earth-pt3-objs += pt3.o pt3_i2c.o pt3_dma.o
+
+obj-$(CONFIG_DVB_PT3) += earth-pt3.o
+
+ccflags-y += -Idrivers/media/dvb-core
+ccflags-y += -Idrivers/media/dvb-frontends
+ccflags-y += -Idrivers/media/tuners
diff --git a/drivers/media/pci/pt3/pt3.c b/drivers/media/pci/pt3/pt3.c
new file mode 100644
index 000000000000..1fdeac11501a
--- /dev/null
+++ b/drivers/media/pci/pt3/pt3.c
@@ -0,0 +1,876 @@
+/*
+ * Earthsoft PT3 driver
+ *
+ * Copyright (C) 2014 Akihiro Tsukada <tskd08@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/freezer.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/mutex.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+
+#include "dmxdev.h"
+#include "dvbdev.h"
+#include "dvb_demux.h"
+#include "dvb_frontend.h"
+
+#include "pt3.h"
+
+DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
+
+static bool one_adapter;
+module_param(one_adapter, bool, 0444);
+MODULE_PARM_DESC(one_adapter, "Place FE's together under one adapter.");
+
+static int num_bufs = 4;
+module_param(num_bufs, int, 0444);
+MODULE_PARM_DESC(num_bufs, "Number of DMA buffer (188KiB) per FE.");
+
+
+static const struct i2c_algorithm pt3_i2c_algo = {
+	.master_xfer   = &pt3_i2c_master_xfer,
+	.functionality = &pt3_i2c_functionality,
+};
+
+static const struct pt3_adap_config adap_conf[PT3_NUM_FE] = {
+	{
+		.demod_info = {
+			I2C_BOARD_INFO(TC90522_I2C_DEV_SAT, 0x11),
+		},
+		.tuner_info = {
+			I2C_BOARD_INFO("qm1d1c0042", 0x63),
+		},
+		.tuner_cfg.qm1d1c0042 = {
+			.lpf = 1,
+		},
+		.init_freq = 1049480 - 300,
+	},
+	{
+		.demod_info = {
+			I2C_BOARD_INFO(TC90522_I2C_DEV_TER, 0x10),
+		},
+		.tuner_info = {
+			I2C_BOARD_INFO("mxl301rf", 0x62),
+		},
+		.init_freq = 515142857,
+	},
+	{
+		.demod_info = {
+			I2C_BOARD_INFO(TC90522_I2C_DEV_SAT, 0x13),
+		},
+		.tuner_info = {
+			I2C_BOARD_INFO("qm1d1c0042", 0x60),
+		},
+		.tuner_cfg.qm1d1c0042 = {
+			.lpf = 1,
+		},
+		.init_freq = 1049480 + 300,
+	},
+	{
+		.demod_info = {
+			I2C_BOARD_INFO(TC90522_I2C_DEV_TER, 0x12),
+		},
+		.tuner_info = {
+			I2C_BOARD_INFO("mxl301rf", 0x61),
+		},
+		.init_freq = 521142857,
+	},
+};
+
+
+struct reg_val {
+	u8 reg;
+	u8 val;
+};
+
+static int
+pt3_demod_write(struct pt3_adapter *adap, const struct reg_val *data, int num)
+{
+	struct i2c_msg msg;
+	int i, ret;
+
+	ret = 0;
+	msg.addr = adap->i2c_demod->addr;
+	msg.flags = 0;
+	msg.len = 2;
+	for (i = 0; i < num; i++) {
+		msg.buf = (u8 *)&data[i];
+		ret = i2c_transfer(adap->i2c_demod->adapter, &msg, 1);
+		if (ret == 0)
+			ret = -EREMOTE;
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+static inline void pt3_lnb_ctrl(struct pt3_board *pt3, bool on)
+{
+	iowrite32((on ? 0x0f : 0x0c), pt3->regs[0] + REG_SYSTEM_W);
+}
+
+static inline struct pt3_adapter *pt3_find_adapter(struct dvb_frontend *fe)
+{
+	struct pt3_board *pt3;
+	int i;
+
+	if (one_adapter) {
+		pt3 = fe->dvb->priv;
+		for (i = 0; i < PT3_NUM_FE; i++)
+			if (pt3->adaps[i]->fe == fe)
+				return pt3->adaps[i];
+	}
+	return container_of(fe->dvb, struct pt3_adapter, dvb_adap);
+}
+
+/*
+ * all 4 tuners in PT3 are packaged in a can module (Sharp VA4M6JC2103).
+ * it seems that they share the power lines and Amp power line and
+ * adaps[3] controls those powers.
+ */
+static int
+pt3_set_tuner_power(struct pt3_board *pt3, bool tuner_on, bool amp_on)
+{
+	struct reg_val rv = { 0x1e, 0x99 };
+
+	if (tuner_on)
+		rv.val |= 0x40;
+	if (amp_on)
+		rv.val |= 0x04;
+	return pt3_demod_write(pt3->adaps[PT3_NUM_FE - 1], &rv, 1);
+}
+
+static int pt3_set_lna(struct dvb_frontend *fe)
+{
+	struct pt3_adapter *adap;
+	struct pt3_board *pt3;
+	u32 val;
+	int ret;
+
+	/* LNA is shared btw. 2 TERR-tuners */
+
+	adap = pt3_find_adapter(fe);
+	val = fe->dtv_property_cache.lna;
+	if (val == LNA_AUTO || val == adap->cur_lna)
+		return 0;
+
+	pt3 = adap->dvb_adap.priv;
+	if (mutex_lock_interruptible(&pt3->lock))
+		return -ERESTARTSYS;
+	if (val)
+		pt3->lna_on_cnt++;
+	else
+		pt3->lna_on_cnt--;
+
+	if (val && pt3->lna_on_cnt <= 1) {
+		pt3->lna_on_cnt = 1;
+		ret = pt3_set_tuner_power(pt3, true, true);
+	} else if (!val && pt3->lna_on_cnt <= 0) {
+		pt3->lna_on_cnt = 0;
+		ret = pt3_set_tuner_power(pt3, true, false);
+	} else
+		ret = 0;
+	mutex_unlock(&pt3->lock);
+	adap->cur_lna = (val != 0);
+	return ret;
+}
+
+static int pt3_set_voltage(struct dvb_frontend *fe, fe_sec_voltage_t volt)
+{
+	struct pt3_adapter *adap;
+	struct pt3_board *pt3;
+	bool on;
+
+	/* LNB power is shared btw. 2 SAT-tuners */
+
+	adap = pt3_find_adapter(fe);
+	on = (volt != SEC_VOLTAGE_OFF);
+	if (on == adap->cur_lnb)
+		return 0;
+	adap->cur_lnb = on;
+	pt3 = adap->dvb_adap.priv;
+	if (mutex_lock_interruptible(&pt3->lock))
+		return -ERESTARTSYS;
+	if (on)
+		pt3->lnb_on_cnt++;
+	else
+		pt3->lnb_on_cnt--;
+
+	if (on && pt3->lnb_on_cnt <= 1) {
+		pt3->lnb_on_cnt = 1;
+		pt3_lnb_ctrl(pt3, true);
+	} else if (!on && pt3->lnb_on_cnt <= 0) {
+		pt3->lnb_on_cnt = 0;
+		pt3_lnb_ctrl(pt3, false);
+	}
+	mutex_unlock(&pt3->lock);
+	return 0;
+}
+
+/* register values used in pt3_fe_init() */
+
+static const struct reg_val init0_sat[] = {
+	{ 0x03, 0x01 },
+	{ 0x1e, 0x10 },
+};
+static const struct reg_val init0_ter[] = {
+	{ 0x01, 0x40 },
+	{ 0x1c, 0x10 },
+};
+static const struct reg_val cfg_sat[] = {
+	{ 0x1c, 0x15 },
+	{ 0x1f, 0x04 },
+};
+static const struct reg_val cfg_ter[] = {
+	{ 0x1d, 0x01 },
+};
+
+/*
+ * pt3_fe_init: initialize demod sub modules and ISDB-T tuners all at once.
+ *
+ * As for demod IC (TC90522) and ISDB-T tuners (MxL301RF),
+ * the i2c sequences for init'ing them are not public and hidden in a ROM,
+ * and include the board specific configurations as well.
+ * They are stored in a lump and cannot be taken out / accessed separately,
+ * thus cannot be moved to the FE/tuner driver.
+ */
+static int pt3_fe_init(struct pt3_board *pt3)
+{
+	int i, ret;
+	struct dvb_frontend *fe;
+
+	pt3_i2c_reset(pt3);
+	ret = pt3_init_all_demods(pt3);
+	if (ret < 0) {
+		dev_warn(&pt3->pdev->dev, "Failed to init demod chips.");
+		return ret;
+	}
+
+	/* additional config? */
+	for (i = 0; i < PT3_NUM_FE; i++) {
+		fe = pt3->adaps[i]->fe;
+
+		if (fe->ops.delsys[0] == SYS_ISDBS)
+			ret = pt3_demod_write(pt3->adaps[i],
+					      init0_sat, ARRAY_SIZE(init0_sat));
+		else
+			ret = pt3_demod_write(pt3->adaps[i],
+					      init0_ter, ARRAY_SIZE(init0_ter));
+		if (ret < 0) {
+			dev_warn(&pt3->pdev->dev,
+				 "demod[%d] faild in init sequence0.", i);
+			return ret;
+		}
+		ret = fe->ops.init(fe);
+		if (ret < 0)
+			return ret;
+	}
+
+	usleep_range(2000, 4000);
+	ret = pt3_set_tuner_power(pt3, true, false);
+	if (ret < 0) {
+		dev_warn(&pt3->pdev->dev, "Failed to control tuner module.");
+		return ret;
+	}
+
+	/* output pin configuration */
+	for (i = 0; i < PT3_NUM_FE; i++) {
+		fe = pt3->adaps[i]->fe;
+		if (fe->ops.delsys[0] == SYS_ISDBS)
+			ret = pt3_demod_write(pt3->adaps[i],
+						cfg_sat, ARRAY_SIZE(cfg_sat));
+		else
+			ret = pt3_demod_write(pt3->adaps[i],
+						cfg_ter, ARRAY_SIZE(cfg_ter));
+		if (ret < 0) {
+			dev_warn(&pt3->pdev->dev,
+				 "demod[%d] faild in init sequence1.", i);
+			return ret;
+		}
+	}
+	usleep_range(4000, 6000);
+
+	for (i = 0; i < PT3_NUM_FE; i++) {
+		fe = pt3->adaps[i]->fe;
+		if (fe->ops.delsys[0] != SYS_ISDBS)
+			continue;
+		/* init and wake-up ISDB-S tuners */
+		ret = fe->ops.tuner_ops.init(fe);
+		if (ret < 0) {
+			dev_warn(&pt3->pdev->dev,
+				 "Failed to init SAT-tuner[%d].", i);
+			return ret;
+		}
+	}
+	ret = pt3_init_all_mxl301rf(pt3);
+	if (ret < 0) {
+		dev_warn(&pt3->pdev->dev, "Failed to init TERR-tuners.");
+		return ret;
+	}
+
+	ret = pt3_set_tuner_power(pt3, true, true);
+	if (ret < 0) {
+		dev_warn(&pt3->pdev->dev, "Failed to control tuner module.");
+		return ret;
+	}
+
+	/* Wake up all tuners and make an initial tuning,
+	 * in order to avoid interference among the tuners in the module,
+	 * according to the doc from the manufacturer.
+	 */
+	for (i = 0; i < PT3_NUM_FE; i++) {
+		fe = pt3->adaps[i]->fe;
+		ret = 0;
+		if (fe->ops.delsys[0] == SYS_ISDBT)
+			ret = fe->ops.tuner_ops.init(fe);
+		/* set only when called from pt3_probe(), not resume() */
+		if (ret == 0 && fe->dtv_property_cache.frequency == 0) {
+			fe->dtv_property_cache.frequency =
+						adap_conf[i].init_freq;
+			ret = fe->ops.tuner_ops.set_params(fe);
+		}
+		if (ret < 0) {
+			dev_warn(&pt3->pdev->dev,
+				 "Failed in initial tuning of tuner[%d].", i);
+			return ret;
+		}
+	}
+
+	/* and sleep again, waiting to be opened by users. */
+	for (i = 0; i < PT3_NUM_FE; i++) {
+		fe = pt3->adaps[i]->fe;
+		if (fe->ops.tuner_ops.sleep)
+			ret = fe->ops.tuner_ops.sleep(fe);
+		if (ret < 0)
+			break;
+		if (fe->ops.sleep)
+			ret = fe->ops.sleep(fe);
+		if (ret < 0)
+			break;
+		if (fe->ops.delsys[0] == SYS_ISDBS)
+			fe->ops.set_voltage = &pt3_set_voltage;
+		else
+			fe->ops.set_lna = &pt3_set_lna;
+	}
+	if (i < PT3_NUM_FE) {
+		dev_warn(&pt3->pdev->dev, "FE[%d] failed to standby.", i);
+		return ret;
+	}
+	return 0;
+}
+
+
+static int pt3_attach_fe(struct pt3_board *pt3, int i)
+{
+	struct i2c_board_info info;
+	struct tc90522_config cfg;
+	struct i2c_client *cl;
+	struct dvb_adapter *dvb_adap;
+	int ret;
+
+	info = adap_conf[i].demod_info;
+	cfg = adap_conf[i].demod_cfg;
+	cfg.tuner_i2c = NULL;
+	info.platform_data = &cfg;
+
+	ret = -ENODEV;
+	request_module("tc90522");
+	cl = i2c_new_device(&pt3->i2c_adap, &info);
+	if (!cl || !cl->dev.driver)
+		return -ENODEV;
+	pt3->adaps[i]->i2c_demod = cl;
+	if (!try_module_get(cl->dev.driver->owner))
+		goto err_demod_i2c_unregister_device;
+
+	if (!strncmp(cl->name, TC90522_I2C_DEV_SAT, sizeof(cl->name))) {
+		struct qm1d1c0042_config tcfg;
+
+		tcfg = adap_conf[i].tuner_cfg.qm1d1c0042;
+		tcfg.fe = cfg.fe;
+		info = adap_conf[i].tuner_info;
+		info.platform_data = &tcfg;
+		request_module("qm1d1c0042");
+		cl = i2c_new_device(cfg.tuner_i2c, &info);
+	} else {
+		struct mxl301rf_config tcfg;
+
+		tcfg = adap_conf[i].tuner_cfg.mxl301rf;
+		tcfg.fe = cfg.fe;
+		info = adap_conf[i].tuner_info;
+		info.platform_data = &tcfg;
+		request_module("mxl301rf");
+		cl = i2c_new_device(cfg.tuner_i2c, &info);
+	}
+	if (!cl || !cl->dev.driver)
+		goto err_demod_module_put;
+	pt3->adaps[i]->i2c_tuner = cl;
+	if (!try_module_get(cl->dev.driver->owner))
+		goto err_tuner_i2c_unregister_device;
+
+	dvb_adap = &pt3->adaps[one_adapter ? 0 : i]->dvb_adap;
+	ret = dvb_register_frontend(dvb_adap, cfg.fe);
+	if (ret < 0)
+		goto err_tuner_module_put;
+	pt3->adaps[i]->fe = cfg.fe;
+	return 0;
+
+err_tuner_module_put:
+	module_put(pt3->adaps[i]->i2c_tuner->dev.driver->owner);
+err_tuner_i2c_unregister_device:
+	i2c_unregister_device(pt3->adaps[i]->i2c_tuner);
+err_demod_module_put:
+	module_put(pt3->adaps[i]->i2c_demod->dev.driver->owner);
+err_demod_i2c_unregister_device:
+	i2c_unregister_device(pt3->adaps[i]->i2c_demod);
+
+	return ret;
+}
+
+
+static int pt3_fetch_thread(void *data)
+{
+	struct pt3_adapter *adap = data;
+	ktime_t delay;
+	bool was_frozen;
+
+#define PT3_INITIAL_BUF_DROPS 4
+#define PT3_FETCH_DELAY 10
+#define PT3_FETCH_DELAY_DELTA 2
+
+	pt3_init_dmabuf(adap);
+	adap->num_discard = PT3_INITIAL_BUF_DROPS;
+
+	dev_dbg(adap->dvb_adap.device,
+		"PT3: [%s] started.\n", adap->thread->comm);
+	set_freezable();
+	while (!kthread_freezable_should_stop(&was_frozen)) {
+		if (was_frozen)
+			adap->num_discard = PT3_INITIAL_BUF_DROPS;
+
+		pt3_proc_dma(adap);
+
+		delay = ktime_set(0, PT3_FETCH_DELAY * NSEC_PER_MSEC);
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		freezable_schedule_hrtimeout_range(&delay,
+					PT3_FETCH_DELAY_DELTA * NSEC_PER_MSEC,
+					HRTIMER_MODE_REL);
+	}
+	dev_dbg(adap->dvb_adap.device,
+		"PT3: [%s] exited.\n", adap->thread->comm);
+	adap->thread = NULL;
+	return 0;
+}
+
+static int pt3_start_streaming(struct pt3_adapter *adap)
+{
+	struct task_struct *thread;
+
+	/* start fetching thread */
+	thread = kthread_run(pt3_fetch_thread, adap, "pt3-ad%i-dmx%i",
+				adap->dvb_adap.num, adap->dmxdev.dvbdev->id);
+	if (IS_ERR(thread)) {
+		int ret = PTR_ERR(thread);
+
+		dev_warn(adap->dvb_adap.device,
+			"PT3 (adap:%d, dmx:%d): failed to start kthread.\n",
+			adap->dvb_adap.num, adap->dmxdev.dvbdev->id);
+		return ret;
+	}
+	adap->thread = thread;
+
+	return pt3_start_dma(adap);
+}
+
+static int pt3_stop_streaming(struct pt3_adapter *adap)
+{
+	int ret;
+
+	ret = pt3_stop_dma(adap);
+	if (ret)
+		dev_warn(adap->dvb_adap.device,
+			"PT3: failed to stop streaming of adap:%d/FE:%d\n",
+			adap->dvb_adap.num, adap->fe->id);
+
+	/* kill the fetching thread */
+	ret = kthread_stop(adap->thread);
+	return ret;
+}
+
+static int pt3_start_feed(struct dvb_demux_feed *feed)
+{
+	struct pt3_adapter *adap;
+
+	if (signal_pending(current))
+		return -EINTR;
+
+	adap = container_of(feed->demux, struct pt3_adapter, demux);
+	adap->num_feeds++;
+	if (adap->thread)
+		return 0;
+	if (adap->num_feeds != 1) {
+		dev_warn(adap->dvb_adap.device,
+			"%s: unmatched start/stop_feed in adap:%i/dmx:%i.\n",
+			__func__, adap->dvb_adap.num, adap->dmxdev.dvbdev->id);
+		adap->num_feeds = 1;
+	}
+
+	return pt3_start_streaming(adap);
+
+}
+
+static int pt3_stop_feed(struct dvb_demux_feed *feed)
+{
+	struct pt3_adapter *adap;
+
+	adap = container_of(feed->demux, struct pt3_adapter, demux);
+
+	adap->num_feeds--;
+	if (adap->num_feeds > 0 || !adap->thread)
+		return 0;
+	adap->num_feeds = 0;
+
+	return pt3_stop_streaming(adap);
+}
+
+
+static int pt3_alloc_adapter(struct pt3_board *pt3, int index)
+{
+	int ret;
+	struct pt3_adapter *adap;
+	struct dvb_adapter *da;
+
+	adap = kzalloc(sizeof(*adap), GFP_KERNEL);
+	if (!adap) {
+		dev_err(&pt3->pdev->dev, "failed to alloc mem for adapter.\n");
+		return -ENOMEM;
+	}
+	pt3->adaps[index] = adap;
+	adap->adap_idx = index;
+
+	if (index == 0 || !one_adapter) {
+		ret = dvb_register_adapter(&adap->dvb_adap, "PT3 DVB",
+				THIS_MODULE, &pt3->pdev->dev, adapter_nr);
+		if (ret < 0) {
+			dev_err(&pt3->pdev->dev,
+				"failed to register adapter dev.\n");
+			goto err_mem;
+		}
+		da = &adap->dvb_adap;
+	} else
+		da = &pt3->adaps[0]->dvb_adap;
+
+	adap->dvb_adap.priv = pt3;
+	adap->demux.dmx.capabilities = DMX_TS_FILTERING | DMX_SECTION_FILTERING;
+	adap->demux.priv = adap;
+	adap->demux.feednum = 256;
+	adap->demux.filternum = 256;
+	adap->demux.start_feed = pt3_start_feed;
+	adap->demux.stop_feed = pt3_stop_feed;
+	ret = dvb_dmx_init(&adap->demux);
+	if (ret < 0) {
+		dev_err(&pt3->pdev->dev, "failed to init dmx dev.\n");
+		goto err_adap;
+	}
+
+	adap->dmxdev.filternum = 256;
+	adap->dmxdev.demux = &adap->demux.dmx;
+	ret = dvb_dmxdev_init(&adap->dmxdev, da);
+	if (ret < 0) {
+		dev_err(&pt3->pdev->dev, "failed to init dmxdev.\n");
+		goto err_demux;
+	}
+
+	ret = pt3_alloc_dmabuf(adap);
+	if (ret) {
+		dev_err(&pt3->pdev->dev, "failed to alloc DMA buffers.\n");
+		goto err_dmabuf;
+	}
+
+	return 0;
+
+err_dmabuf:
+	pt3_free_dmabuf(adap);
+	dvb_dmxdev_release(&adap->dmxdev);
+err_demux:
+	dvb_dmx_release(&adap->demux);
+err_adap:
+	if (index == 0 || !one_adapter)
+		dvb_unregister_adapter(da);
+err_mem:
+	kfree(adap);
+	pt3->adaps[index] = NULL;
+	return ret;
+}
+
+static void pt3_cleanup_adapter(struct pt3_board *pt3, int index)
+{
+	struct pt3_adapter *adap;
+	struct dmx_demux *dmx;
+
+	adap = pt3->adaps[index];
+	if (adap == NULL)
+		return;
+
+	/* stop demux kthread */
+	if (adap->thread)
+		pt3_stop_streaming(adap);
+
+	dmx = &adap->demux.dmx;
+	dmx->close(dmx);
+	if (adap->fe) {
+		adap->fe->callback = NULL;
+		if (adap->fe->frontend_priv)
+			dvb_unregister_frontend(adap->fe);
+		if (adap->i2c_tuner) {
+			module_put(adap->i2c_tuner->dev.driver->owner);
+			i2c_unregister_device(adap->i2c_tuner);
+		}
+		if (adap->i2c_demod) {
+			module_put(adap->i2c_demod->dev.driver->owner);
+			i2c_unregister_device(adap->i2c_demod);
+		}
+	}
+	pt3_free_dmabuf(adap);
+	dvb_dmxdev_release(&adap->dmxdev);
+	dvb_dmx_release(&adap->demux);
+	if (index == 0 || !one_adapter)
+		dvb_unregister_adapter(&adap->dvb_adap);
+	kfree(adap);
+	pt3->adaps[index] = NULL;
+}
+
+#ifdef CONFIG_PM_SLEEP
+
+static int pt3_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pt3_board *pt3 = pci_get_drvdata(pdev);
+	int i;
+	struct pt3_adapter *adap;
+
+	for (i = 0; i < PT3_NUM_FE; i++) {
+		adap = pt3->adaps[i];
+		if (adap->num_feeds > 0)
+			pt3_stop_dma(adap);
+		dvb_frontend_suspend(adap->fe);
+		pt3_free_dmabuf(adap);
+	}
+
+	pt3_lnb_ctrl(pt3, false);
+	pt3_set_tuner_power(pt3, false, false);
+	return 0;
+}
+
+static int pt3_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pt3_board *pt3 = pci_get_drvdata(pdev);
+	int i, ret;
+	struct pt3_adapter *adap;
+
+	ret = pt3_fe_init(pt3);
+	if (ret)
+		return ret;
+
+	if (pt3->lna_on_cnt > 0)
+		pt3_set_tuner_power(pt3, true, true);
+	if (pt3->lnb_on_cnt > 0)
+		pt3_lnb_ctrl(pt3, true);
+
+	for (i = 0; i < PT3_NUM_FE; i++) {
+		adap = pt3->adaps[i];
+		dvb_frontend_resume(adap->fe);
+		ret = pt3_alloc_dmabuf(adap);
+		if (ret) {
+			dev_err(&pt3->pdev->dev, "failed to alloc DMA bufs.\n");
+			continue;
+		}
+		if (adap->num_feeds > 0)
+			pt3_start_dma(adap);
+	}
+
+	return 0;
+}
+
+#endif /* CONFIG_PM_SLEEP */
+
+
+static void pt3_remove(struct pci_dev *pdev)
+{
+	struct pt3_board *pt3;
+	int i;
+
+	pt3 = pci_get_drvdata(pdev);
+	for (i = PT3_NUM_FE - 1; i >= 0; i--)
+		pt3_cleanup_adapter(pt3, i);
+	i2c_del_adapter(&pt3->i2c_adap);
+	kfree(pt3->i2c_buf);
+	pci_iounmap(pt3->pdev, pt3->regs[0]);
+	pci_iounmap(pt3->pdev, pt3->regs[1]);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	kfree(pt3);
+}
+
+static int pt3_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	u8 rev;
+	u32 ver;
+	int i, ret;
+	struct pt3_board *pt3;
+	struct i2c_adapter *i2c;
+
+	if (pci_read_config_byte(pdev, PCI_REVISION_ID, &rev) || rev != 1)
+		return -ENODEV;
+
+	ret = pci_enable_device(pdev);
+	if (ret < 0)
+		return -ENODEV;
+	pci_set_master(pdev);
+
+	ret = pci_request_regions(pdev, DRV_NAME);
+	if (ret < 0)
+		goto err_disable_device;
+
+	ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
+	if (ret == 0)
+		dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
+	else {
+		ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+		if (ret == 0)
+			dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+		else {
+			dev_err(&pdev->dev, "Failed to set DMA mask.\n");
+			goto err_release_regions;
+		}
+		dev_info(&pdev->dev, "Use 32bit DMA.\n");
+	}
+
+	pt3 = kzalloc(sizeof(*pt3), GFP_KERNEL);
+	if (!pt3) {
+		dev_err(&pdev->dev, "Failed to alloc mem for this dev.\n");
+		ret = -ENOMEM;
+		goto err_release_regions;
+	}
+	pci_set_drvdata(pdev, pt3);
+	pt3->pdev = pdev;
+	mutex_init(&pt3->lock);
+	pt3->regs[0] = pci_ioremap_bar(pdev, 0);
+	pt3->regs[1] = pci_ioremap_bar(pdev, 2);
+	if (pt3->regs[0] == NULL || pt3->regs[1] == NULL) {
+		dev_err(&pdev->dev, "Failed to ioremap.\n");
+		ret = -ENOMEM;
+		goto err_kfree;
+	}
+
+	ver = ioread32(pt3->regs[0] + REG_VERSION);
+	if ((ver >> 16) != 0x0301) {
+		dev_warn(&pdev->dev, "PT%d, I/F-ver.:%d not supported",
+			ver >> 24, (ver & 0x00ff0000) >> 16);
+		ret = -ENODEV;
+		goto err_iounmap;
+	}
+
+	pt3->num_bufs = clamp_val(num_bufs, MIN_DATA_BUFS, MAX_DATA_BUFS);
+
+	pt3->i2c_buf = kmalloc(sizeof(*pt3->i2c_buf), GFP_KERNEL);
+	if (pt3->i2c_buf == NULL) {
+		dev_err(&pdev->dev, "Failed to alloc mem for i2c.\n");
+		ret = -ENOMEM;
+		goto err_iounmap;
+	}
+	i2c = &pt3->i2c_adap;
+	i2c->owner = THIS_MODULE;
+	i2c->algo = &pt3_i2c_algo;
+	i2c->algo_data = NULL;
+	i2c->dev.parent = &pdev->dev;
+	strlcpy(i2c->name, DRV_NAME, sizeof(i2c->name));
+	i2c_set_adapdata(i2c, pt3);
+	ret = i2c_add_adapter(i2c);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to add i2c adapter.\n");
+		goto err_i2cbuf;
+	}
+
+	for (i = 0; i < PT3_NUM_FE; i++) {
+		ret = pt3_alloc_adapter(pt3, i);
+		if (ret < 0)
+			break;
+
+		ret = pt3_attach_fe(pt3, i);
+		if (ret < 0)
+			break;
+	}
+	if (i < PT3_NUM_FE) {
+		dev_err(&pdev->dev, "Failed to create FE%d.\n", i);
+		goto err_cleanup_adapters;
+	}
+
+	ret = pt3_fe_init(pt3);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to init frontends.\n");
+		i = PT3_NUM_FE - 1;
+		goto err_cleanup_adapters;
+	}
+
+	dev_info(&pdev->dev,
+		"successfully init'ed PT%d (fw:0x%02x, I/F:0x%02x).\n",
+		ver >> 24, (ver >> 8) & 0xff, (ver >> 16) & 0xff);
+	return 0;
+
+err_cleanup_adapters:
+	while (i >= 0)
+		pt3_cleanup_adapter(pt3, i--);
+	i2c_del_adapter(i2c);
+err_i2cbuf:
+	kfree(pt3->i2c_buf);
+err_iounmap:
+	if (pt3->regs[0])
+		pci_iounmap(pdev, pt3->regs[0]);
+	if (pt3->regs[1])
+		pci_iounmap(pdev, pt3->regs[1]);
+err_kfree:
+	kfree(pt3);
+err_release_regions:
+	pci_release_regions(pdev);
+err_disable_device:
+	pci_disable_device(pdev);
+	return ret;
+
+}
+
+static const struct pci_device_id pt3_id_table[] = {
+	{ PCI_DEVICE_SUB(0x1172, 0x4c15, 0xee8d, 0x0368) },
+	{ },
+};
+MODULE_DEVICE_TABLE(pci, pt3_id_table);
+
+static SIMPLE_DEV_PM_OPS(pt3_pm_ops, pt3_suspend, pt3_resume);
+
+static struct pci_driver pt3_driver = {
+	.name		= DRV_NAME,
+	.probe		= pt3_probe,
+	.remove		= pt3_remove,
+	.id_table	= pt3_id_table,
+
+	.driver.pm	= &pt3_pm_ops,
+};
+
+module_pci_driver(pt3_driver);
+
+MODULE_DESCRIPTION("Earthsoft PT3 Driver");
+MODULE_AUTHOR("Akihiro TSUKADA");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/pci/pt3/pt3.h b/drivers/media/pci/pt3/pt3.h
new file mode 100644
index 000000000000..1b3f2ad25db3
--- /dev/null
+++ b/drivers/media/pci/pt3/pt3.h
@@ -0,0 +1,186 @@
+/*
+ * Earthsoft PT3 driver
+ *
+ * Copyright (C) 2014 Akihiro Tsukada <tskd08@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef PT3_H
+#define PT3_H
+
+#include <linux/atomic.h>
+#include <linux/types.h>
+
+#include "dvb_demux.h"
+#include "dvb_frontend.h"
+#include "dmxdev.h"
+
+#include "tc90522.h"
+#include "mxl301rf.h"
+#include "qm1d1c0042.h"
+
+#define DRV_NAME KBUILD_MODNAME
+
+#define PT3_NUM_FE 4
+
+/*
+ * register index of the FPGA chip
+ */
+#define REG_VERSION	0x00
+#define REG_BUS		0x04
+#define REG_SYSTEM_W	0x08
+#define REG_SYSTEM_R	0x0c
+#define REG_I2C_W	0x10
+#define REG_I2C_R	0x14
+#define REG_RAM_W	0x18
+#define REG_RAM_R	0x1c
+#define REG_DMA_BASE	0x40	/* regs for FE[i] = REG_DMA_BASE + 0x18 * i */
+#define OFST_DMA_DESC_L	0x00
+#define OFST_DMA_DESC_H	0x04
+#define OFST_DMA_CTL	0x08
+#define OFST_TS_CTL	0x0c
+#define OFST_STATUS	0x10
+#define OFST_TS_ERR	0x14
+
+/*
+ * internal buffer for I2C
+ */
+#define PT3_I2C_MAX 4091
+struct pt3_i2cbuf {
+	u8  data[PT3_I2C_MAX];
+	u8  tmp;
+	u32 num_cmds;
+};
+
+/*
+ * DMA things
+ */
+#define TS_PACKET_SZ  188
+/* DMA transfers must not cross 4GiB, so use one page / transfer */
+#define DATA_XFER_SZ   4096
+#define DATA_BUF_XFERS 47
+/* (num_bufs * DATA_BUF_SZ) % TS_PACKET_SZ must be 0 */
+#define DATA_BUF_SZ    (DATA_BUF_XFERS * DATA_XFER_SZ)
+#define MAX_DATA_BUFS  16
+#define MIN_DATA_BUFS   2
+
+#define DESCS_IN_PAGE (PAGE_SIZE / sizeof(struct xfer_desc))
+#define MAX_NUM_XFERS (MAX_DATA_BUFS * DATA_BUF_XFERS)
+#define MAX_DESC_BUFS DIV_ROUND_UP(MAX_NUM_XFERS, DESCS_IN_PAGE)
+
+/* DMA transfer description.
+ * device is passed a pointer to this struct, dma-reads it,
+ * and gets the DMA buffer ring for storing TS data.
+ */
+struct xfer_desc {
+	u32 addr_l; /* bus address of target data buffer */
+	u32 addr_h;
+	u32 size;
+	u32 next_l; /* bus adddress of the next xfer_desc */
+	u32 next_h;
+};
+
+/* A DMA mapping of a page containing xfer_desc's */
+struct xfer_desc_buffer {
+	dma_addr_t b_addr;
+	struct xfer_desc *descs; /* PAGE_SIZE (xfer_desc[DESCS_IN_PAGE]) */
+};
+
+/* A DMA mapping of a data buffer */
+struct dma_data_buffer {
+	dma_addr_t b_addr;
+	u8 *data; /* size: u8[PAGE_SIZE] */
+};
+
+/*
+ * device things
+ */
+struct pt3_adap_config {
+	struct i2c_board_info demod_info;
+	struct tc90522_config demod_cfg;
+
+	struct i2c_board_info tuner_info;
+	union tuner_config {
+		struct qm1d1c0042_config qm1d1c0042;
+		struct mxl301rf_config   mxl301rf;
+	} tuner_cfg;
+	u32 init_freq;
+};
+
+struct pt3_adapter {
+	struct dvb_adapter  dvb_adap;  /* dvb_adap.priv => struct pt3_board */
+	int adap_idx;
+
+	struct dvb_demux    demux;
+	struct dmxdev       dmxdev;
+	struct dvb_frontend *fe;
+	struct i2c_client   *i2c_demod;
+	struct i2c_client   *i2c_tuner;
+
+	/* data fetch thread */
+	struct task_struct *thread;
+	int num_feeds;
+
+	bool cur_lna;
+	bool cur_lnb; /* current LNB power status (on/off) */
+
+	/* items below are for DMA */
+	struct dma_data_buffer buffer[MAX_DATA_BUFS];
+	int buf_idx;
+	int buf_ofs;
+	int num_bufs;  /* == pt3_board->num_bufs */
+	int num_discard; /* how many access units to discard initially */
+
+	struct xfer_desc_buffer desc_buf[MAX_DESC_BUFS];
+	int num_desc_bufs;  /* == num_bufs * DATA_BUF_XFERS / DESCS_IN_PAGE */
+};
+
+
+struct pt3_board {
+	struct pci_dev *pdev;
+	void __iomem *regs[2];
+	/* regs[0]: registers, regs[1]: internal memory, used for I2C */
+
+	struct mutex lock;
+
+	/* LNB power shared among sat-FEs */
+	int lnb_on_cnt; /* LNB power on count */
+
+	/* LNA shared among terr-FEs */
+	int lna_on_cnt; /* booster enabled count */
+
+	int num_bufs;  /* number of DMA buffers allocated/mapped per FE */
+
+	struct i2c_adapter i2c_adap;
+	struct pt3_i2cbuf *i2c_buf;
+
+	struct pt3_adapter *adaps[PT3_NUM_FE];
+};
+
+
+/*
+ * prototypes
+ */
+extern int  pt3_alloc_dmabuf(struct pt3_adapter *adap);
+extern void pt3_init_dmabuf(struct pt3_adapter *adap);
+extern void pt3_free_dmabuf(struct pt3_adapter *adap);
+extern int  pt3_start_dma(struct pt3_adapter *adap);
+extern int  pt3_stop_dma(struct pt3_adapter *adap);
+extern int  pt3_proc_dma(struct pt3_adapter *adap);
+
+extern int  pt3_i2c_master_xfer(struct i2c_adapter *adap,
+				struct i2c_msg *msgs, int num);
+extern u32  pt3_i2c_functionality(struct i2c_adapter *adap);
+extern void pt3_i2c_reset(struct pt3_board *pt3);
+extern int  pt3_init_all_demods(struct pt3_board *pt3);
+extern int  pt3_init_all_mxl301rf(struct pt3_board *pt3);
+#endif /* PT3_H */
diff --git a/drivers/media/pci/pt3/pt3_dma.c b/drivers/media/pci/pt3/pt3_dma.c
new file mode 100644
index 000000000000..f0ce90437fac
--- /dev/null
+++ b/drivers/media/pci/pt3/pt3_dma.c
@@ -0,0 +1,225 @@
+/*
+ * Earthsoft PT3 driver
+ *
+ * Copyright (C) 2014 Akihiro Tsukada <tskd08@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/dma-mapping.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+
+#include "pt3.h"
+
+#define PT3_ACCESS_UNIT (TS_PACKET_SZ * 128)
+#define PT3_BUF_CANARY  (0x74)
+
+static u32 get_dma_base(int idx)
+{
+	int i;
+
+	i = (idx == 1 || idx == 2) ? 3 - idx : idx;
+	return REG_DMA_BASE + 0x18 * i;
+}
+
+int pt3_stop_dma(struct pt3_adapter *adap)
+{
+	struct pt3_board *pt3 = adap->dvb_adap.priv;
+	u32 base;
+	u32 stat;
+	int retry;
+
+	base = get_dma_base(adap->adap_idx);
+	stat = ioread32(pt3->regs[0] + base + OFST_STATUS);
+	if (!(stat & 0x01))
+		return 0;
+
+	iowrite32(0x02, pt3->regs[0] + base + OFST_DMA_CTL);
+	for (retry = 0; retry < 5; retry++) {
+		stat = ioread32(pt3->regs[0] + base + OFST_STATUS);
+		if (!(stat & 0x01))
+			return 0;
+		msleep(50);
+	}
+	return -EIO;
+}
+
+int pt3_start_dma(struct pt3_adapter *adap)
+{
+	struct pt3_board *pt3 = adap->dvb_adap.priv;
+	u32 base = get_dma_base(adap->adap_idx);
+
+	iowrite32(0x02, pt3->regs[0] + base + OFST_DMA_CTL);
+	iowrite32(lower_32_bits(adap->desc_buf[0].b_addr),
+			pt3->regs[0] + base + OFST_DMA_DESC_L);
+	iowrite32(upper_32_bits(adap->desc_buf[0].b_addr),
+			pt3->regs[0] + base + OFST_DMA_DESC_H);
+	iowrite32(0x01, pt3->regs[0] + base + OFST_DMA_CTL);
+	return 0;
+}
+
+
+static u8 *next_unit(struct pt3_adapter *adap, int *idx, int *ofs)
+{
+	*ofs += PT3_ACCESS_UNIT;
+	if (*ofs >= DATA_BUF_SZ) {
+		*ofs -= DATA_BUF_SZ;
+		(*idx)++;
+		if (*idx == adap->num_bufs)
+			*idx = 0;
+	}
+	return &adap->buffer[*idx].data[*ofs];
+}
+
+int pt3_proc_dma(struct pt3_adapter *adap)
+{
+	int idx, ofs;
+
+	idx = adap->buf_idx;
+	ofs = adap->buf_ofs;
+
+	if (adap->buffer[idx].data[ofs] == PT3_BUF_CANARY)
+		return 0;
+
+	while (*next_unit(adap, &idx, &ofs) != PT3_BUF_CANARY) {
+		u8 *p;
+
+		p = &adap->buffer[adap->buf_idx].data[adap->buf_ofs];
+		if (adap->num_discard > 0)
+			adap->num_discard--;
+		else if (adap->buf_ofs + PT3_ACCESS_UNIT > DATA_BUF_SZ) {
+			dvb_dmx_swfilter_packets(&adap->demux, p,
+				(DATA_BUF_SZ - adap->buf_ofs) / TS_PACKET_SZ);
+			dvb_dmx_swfilter_packets(&adap->demux,
+				adap->buffer[idx].data, ofs / TS_PACKET_SZ);
+		} else
+			dvb_dmx_swfilter_packets(&adap->demux, p,
+				PT3_ACCESS_UNIT / TS_PACKET_SZ);
+
+		*p = PT3_BUF_CANARY;
+		adap->buf_idx = idx;
+		adap->buf_ofs = ofs;
+	}
+	return 0;
+}
+
+void pt3_init_dmabuf(struct pt3_adapter *adap)
+{
+	int idx, ofs;
+	u8 *p;
+
+	idx = 0;
+	ofs = 0;
+	p = adap->buffer[0].data;
+	/* mark the whole buffers as "not written yet" */
+	while (idx < adap->num_bufs) {
+		p[ofs] = PT3_BUF_CANARY;
+		ofs += PT3_ACCESS_UNIT;
+		if (ofs >= DATA_BUF_SZ) {
+			ofs -= DATA_BUF_SZ;
+			idx++;
+			p = adap->buffer[idx].data;
+		}
+	}
+	adap->buf_idx = 0;
+	adap->buf_ofs = 0;
+}
+
+void pt3_free_dmabuf(struct pt3_adapter *adap)
+{
+	struct pt3_board *pt3;
+	int i;
+
+	pt3 = adap->dvb_adap.priv;
+	for (i = 0; i < adap->num_bufs; i++)
+		dma_free_coherent(&pt3->pdev->dev, DATA_BUF_SZ,
+			adap->buffer[i].data, adap->buffer[i].b_addr);
+	adap->num_bufs = 0;
+
+	for (i = 0; i < adap->num_desc_bufs; i++)
+		dma_free_coherent(&pt3->pdev->dev, PAGE_SIZE,
+			adap->desc_buf[i].descs, adap->desc_buf[i].b_addr);
+	adap->num_desc_bufs = 0;
+}
+
+
+int pt3_alloc_dmabuf(struct pt3_adapter *adap)
+{
+	struct pt3_board *pt3;
+	void *p;
+	int i, j;
+	int idx, ofs;
+	int num_desc_bufs;
+	dma_addr_t data_addr, desc_addr;
+	struct xfer_desc *d;
+
+	pt3 = adap->dvb_adap.priv;
+	adap->num_bufs = 0;
+	adap->num_desc_bufs = 0;
+	for (i = 0; i < pt3->num_bufs; i++) {
+		p = dma_alloc_coherent(&pt3->pdev->dev, DATA_BUF_SZ,
+					&adap->buffer[i].b_addr, GFP_KERNEL);
+		if (p == NULL)
+			goto failed;
+		adap->buffer[i].data = p;
+		adap->num_bufs++;
+	}
+	pt3_init_dmabuf(adap);
+
+	/* build circular-linked pointers (xfer_desc) to the data buffers*/
+	idx = 0;
+	ofs = 0;
+	num_desc_bufs =
+		DIV_ROUND_UP(adap->num_bufs * DATA_BUF_XFERS, DESCS_IN_PAGE);
+	for (i = 0; i < num_desc_bufs; i++) {
+		p = dma_alloc_coherent(&pt3->pdev->dev, PAGE_SIZE,
+					&desc_addr, GFP_KERNEL);
+		if (p == NULL)
+			goto failed;
+		adap->num_desc_bufs++;
+		adap->desc_buf[i].descs = p;
+		adap->desc_buf[i].b_addr = desc_addr;
+
+		if (i > 0) {
+			d = &adap->desc_buf[i - 1].descs[DESCS_IN_PAGE - 1];
+			d->next_l = lower_32_bits(desc_addr);
+			d->next_h = upper_32_bits(desc_addr);
+		}
+		for (j = 0; j < DESCS_IN_PAGE; j++) {
+			data_addr = adap->buffer[idx].b_addr + ofs;
+			d = &adap->desc_buf[i].descs[j];
+			d->addr_l = lower_32_bits(data_addr);
+			d->addr_h = upper_32_bits(data_addr);
+			d->size = DATA_XFER_SZ;
+
+			desc_addr += sizeof(struct xfer_desc);
+			d->next_l = lower_32_bits(desc_addr);
+			d->next_h = upper_32_bits(desc_addr);
+
+			ofs += DATA_XFER_SZ;
+			if (ofs >= DATA_BUF_SZ) {
+				ofs -= DATA_BUF_SZ;
+				idx++;
+				if (idx >= adap->num_bufs) {
+					desc_addr = adap->desc_buf[0].b_addr;
+					d->next_l = lower_32_bits(desc_addr);
+					d->next_h = upper_32_bits(desc_addr);
+					return 0;
+				}
+			}
+		}
+	}
+	return 0;
+
+failed:
+	pt3_free_dmabuf(adap);
+	return -ENOMEM;
+}
diff --git a/drivers/media/pci/pt3/pt3_i2c.c b/drivers/media/pci/pt3/pt3_i2c.c
new file mode 100644
index 000000000000..ec6a8a2e4744
--- /dev/null
+++ b/drivers/media/pci/pt3/pt3_i2c.c
@@ -0,0 +1,240 @@
+/*
+ * Earthsoft PT3 driver
+ *
+ * Copyright (C) 2014 Akihiro Tsukada <tskd08@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/i2c.h>
+#include <linux/io.h>
+#include <linux/pci.h>
+
+#include "pt3.h"
+
+#define PT3_I2C_BASE  2048
+#define PT3_CMD_ADDR_NORMAL 0
+#define PT3_CMD_ADDR_INIT_DEMOD  4096
+#define PT3_CMD_ADDR_INIT_TUNER  (4096 + 2042)
+
+/* masks for I2C status register */
+#define STAT_SEQ_RUNNING 0x1
+#define STAT_SEQ_ERROR   0x6
+#define STAT_NO_SEQ      0x8
+
+#define PT3_I2C_RUN   (1 << 16)
+#define PT3_I2C_RESET (1 << 17)
+
+enum ctl_cmd {
+	I_END,
+	I_ADDRESS,
+	I_CLOCK_L,
+	I_CLOCK_H,
+	I_DATA_L,
+	I_DATA_H,
+	I_RESET,
+	I_SLEEP,
+	I_DATA_L_NOP  = 0x08,
+	I_DATA_H_NOP  = 0x0c,
+	I_DATA_H_READ = 0x0d,
+	I_DATA_H_ACK0 = 0x0e,
+	I_DATA_H_ACK1 = 0x0f,
+};
+
+
+static void cmdbuf_add(struct pt3_i2cbuf *cbuf, enum ctl_cmd cmd)
+{
+	int buf_idx;
+
+	if ((cbuf->num_cmds % 2) == 0)
+		cbuf->tmp = cmd;
+	else {
+		cbuf->tmp |= cmd << 4;
+		buf_idx = cbuf->num_cmds / 2;
+		if (buf_idx < ARRAY_SIZE(cbuf->data))
+			cbuf->data[buf_idx] = cbuf->tmp;
+	}
+	cbuf->num_cmds++;
+}
+
+static void put_end(struct pt3_i2cbuf *cbuf)
+{
+	cmdbuf_add(cbuf, I_END);
+	if (cbuf->num_cmds % 2)
+		cmdbuf_add(cbuf, I_END);
+}
+
+static void put_start(struct pt3_i2cbuf *cbuf)
+{
+	cmdbuf_add(cbuf, I_DATA_H);
+	cmdbuf_add(cbuf, I_CLOCK_H);
+	cmdbuf_add(cbuf, I_DATA_L);
+	cmdbuf_add(cbuf, I_CLOCK_L);
+}
+
+static void put_byte_write(struct pt3_i2cbuf *cbuf, u8 val)
+{
+	u8 mask;
+
+	mask = 0x80;
+	for (mask = 0x80; mask > 0; mask >>= 1)
+		cmdbuf_add(cbuf, (val & mask) ? I_DATA_H_NOP : I_DATA_L_NOP);
+	cmdbuf_add(cbuf, I_DATA_H_ACK0);
+}
+
+static void put_byte_read(struct pt3_i2cbuf *cbuf, u32 size)
+{
+	int i, j;
+
+	for (i = 0; i < size; i++) {
+		for (j = 0; j < 8; j++)
+			cmdbuf_add(cbuf, I_DATA_H_READ);
+		cmdbuf_add(cbuf, (i == size - 1) ? I_DATA_H_NOP : I_DATA_L_NOP);
+	}
+}
+
+static void put_stop(struct pt3_i2cbuf *cbuf)
+{
+	cmdbuf_add(cbuf, I_DATA_L);
+	cmdbuf_add(cbuf, I_CLOCK_H);
+	cmdbuf_add(cbuf, I_DATA_H);
+}
+
+
+/* translates msgs to internal commands for bit-banging */
+static void translate(struct pt3_i2cbuf *cbuf, struct i2c_msg *msgs, int num)
+{
+	int i, j;
+	bool rd;
+
+	cbuf->num_cmds = 0;
+	for (i = 0; i < num; i++) {
+		rd = !!(msgs[i].flags & I2C_M_RD);
+		put_start(cbuf);
+		put_byte_write(cbuf, msgs[i].addr << 1 | rd);
+		if (rd)
+			put_byte_read(cbuf, msgs[i].len);
+		else
+			for (j = 0; j < msgs[i].len; j++)
+				put_byte_write(cbuf, msgs[i].buf[j]);
+	}
+	if (num > 0) {
+		put_stop(cbuf);
+		put_end(cbuf);
+	}
+}
+
+static int wait_i2c_result(struct pt3_board *pt3, u32 *result, int max_wait)
+{
+	int i;
+	u32 v;
+
+	for (i = 0; i < max_wait; i++) {
+		v = ioread32(pt3->regs[0] + REG_I2C_R);
+		if (!(v & STAT_SEQ_RUNNING))
+			break;
+		usleep_range(500, 750);
+	}
+	if (i >= max_wait)
+		return -EIO;
+	if (result)
+		*result = v;
+	return 0;
+}
+
+/* send [pre-]translated i2c msgs stored at addr */
+static int send_i2c_cmd(struct pt3_board *pt3, u32 addr)
+{
+	u32 ret;
+
+	/* make sure that previous transactions had finished */
+	if (wait_i2c_result(pt3, NULL, 50)) {
+		dev_warn(&pt3->pdev->dev, "(%s) prev. transaction stalled\n",
+				__func__);
+		return -EIO;
+	}
+
+	iowrite32(PT3_I2C_RUN | addr, pt3->regs[0] + REG_I2C_W);
+	usleep_range(200, 300);
+	/* wait for the current transaction to finish */
+	if (wait_i2c_result(pt3, &ret, 500) || (ret & STAT_SEQ_ERROR)) {
+		dev_warn(&pt3->pdev->dev, "(%s) failed.\n", __func__);
+		return -EIO;
+	}
+	return 0;
+}
+
+
+/* init commands for each demod are combined into one transaction
+ *  and hidden in ROM with the address PT3_CMD_ADDR_INIT_DEMOD.
+ */
+int  pt3_init_all_demods(struct pt3_board *pt3)
+{
+	ioread32(pt3->regs[0] + REG_I2C_R);
+	return send_i2c_cmd(pt3, PT3_CMD_ADDR_INIT_DEMOD);
+}
+
+/* init commands for two ISDB-T tuners are hidden in ROM. */
+int  pt3_init_all_mxl301rf(struct pt3_board *pt3)
+{
+	usleep_range(1000, 2000);
+	return send_i2c_cmd(pt3, PT3_CMD_ADDR_INIT_TUNER);
+}
+
+void pt3_i2c_reset(struct pt3_board *pt3)
+{
+	iowrite32(PT3_I2C_RESET, pt3->regs[0] + REG_I2C_W);
+}
+
+/*
+ * I2C algorithm
+ */
+int
+pt3_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
+{
+	struct pt3_board *pt3;
+	struct pt3_i2cbuf *cbuf;
+	int i;
+	void __iomem *p;
+
+	pt3 = i2c_get_adapdata(adap);
+	cbuf = pt3->i2c_buf;
+
+	for (i = 0; i < num; i++)
+		if (msgs[i].flags & I2C_M_RECV_LEN) {
+			dev_warn(&pt3->pdev->dev,
+				"(%s) I2C_M_RECV_LEN not supported.\n",
+				__func__);
+			return -EINVAL;
+		}
+
+	translate(cbuf, msgs, num);
+	memcpy_toio(pt3->regs[1] + PT3_I2C_BASE + PT3_CMD_ADDR_NORMAL / 2,
+			cbuf->data, cbuf->num_cmds);
+
+	if (send_i2c_cmd(pt3, PT3_CMD_ADDR_NORMAL) < 0)
+		return -EIO;
+
+	p = pt3->regs[1] + PT3_I2C_BASE;
+	for (i = 0; i < num; i++)
+		if ((msgs[i].flags & I2C_M_RD) && msgs[i].len > 0) {
+			memcpy_fromio(msgs[i].buf, p, msgs[i].len);
+			p += msgs[i].len;
+		}
+
+	return num;
+}
+
+u32 pt3_i2c_functionality(struct i2c_adapter *adap)
+{
+	return I2C_FUNC_I2C;
+}
diff --git a/drivers/media/pci/saa7134/Kconfig b/drivers/media/pci/saa7134/Kconfig
index 18ae75546302..b44e0d70907e 100644
--- a/drivers/media/pci/saa7134/Kconfig
+++ b/drivers/media/pci/saa7134/Kconfig
@@ -63,3 +63,11 @@ config VIDEO_SAA7134_DVB
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called saa7134-dvb.
+
+config VIDEO_SAA7134_GO7007
+	tristate "go7007 support for saa7134 based TV cards"
+	depends on VIDEO_SAA7134
+	depends on VIDEO_GO7007
+	---help---
+	  Enables saa7134 driver support for boards with go7007
+	  MPEG encoder (WIS Voyager or compatible).
diff --git a/drivers/media/pci/saa7134/Makefile b/drivers/media/pci/saa7134/Makefile
index 58de9b085689..09c43da67588 100644
--- a/drivers/media/pci/saa7134/Makefile
+++ b/drivers/media/pci/saa7134/Makefile
@@ -5,6 +5,7 @@ saa7134-y +=	saa7134-video.o
 saa7134-$(CONFIG_VIDEO_SAA7134_RC) += saa7134-input.o
 
 obj-$(CONFIG_VIDEO_SAA7134) +=  saa7134.o saa7134-empress.o
+obj-$(CONFIG_VIDEO_SAA7134_GO7007) += saa7134-go7007.o
 
 obj-$(CONFIG_VIDEO_SAA7134_ALSA) += saa7134-alsa.o
 
@@ -14,3 +15,4 @@ ccflags-y += -I$(srctree)/drivers/media/i2c
 ccflags-y += -I$(srctree)/drivers/media/tuners
 ccflags-y += -I$(srctree)/drivers/media/dvb-core
 ccflags-y += -I$(srctree)/drivers/media/dvb-frontends
+ccflags-y += -I$(srctree)/drivers/media/usb/go7007
diff --git a/drivers/media/pci/saa7134/saa7134-cards.c b/drivers/media/pci/saa7134/saa7134-cards.c
index 6e4bdb90aa92..3ca078057755 100644
--- a/drivers/media/pci/saa7134/saa7134-cards.c
+++ b/drivers/media/pci/saa7134/saa7134-cards.c
@@ -5827,6 +5827,29 @@ struct saa7134_board saa7134_boards[] = {
 			.gpio = 0x0000800,
 		},
 	},
+	[SAA7134_BOARD_WIS_VOYAGER] = {
+		.name           = "WIS Voyager or compatible",
+		.audio_clock    = 0x00200000,
+		.tuner_type	= TUNER_PHILIPS_TDA8290,
+		.radio_type     = UNSET,
+		.tuner_addr     = ADDR_UNSET,
+		.radio_addr     = ADDR_UNSET,
+		.mpeg		= SAA7134_MPEG_GO7007,
+		.inputs		= { {
+			.name = name_comp1,
+			.vmux = 0,
+			.amux = LINE2,
+		}, {
+			.name = name_tv,
+			.vmux = 3,
+			.amux = TV,
+			.tv   = 1,
+		}, {
+			.name = name_svideo,
+			.vmux = 6,
+		.amux = LINE1,
+		} },
+	},
 
 };
 
@@ -7080,6 +7103,12 @@ struct pci_device_id saa7134_pci_tbl[] = {
 		.subdevice    = 0x2055, /* AverTV Satellite Hybrid+FM A706 */
 		.driver_data  = SAA7134_BOARD_AVERMEDIA_A706,
 	}, {
+		.vendor       = PCI_VENDOR_ID_PHILIPS,
+		.device       = PCI_DEVICE_ID_PHILIPS_SAA7133,
+		.subvendor    = 0x1905, /* WIS */
+		.subdevice    = 0x7007,
+		.driver_data  = SAA7134_BOARD_WIS_VOYAGER,
+	}, {
 		/* --- boards without eeprom + subsystem ID --- */
 		.vendor       = PCI_VENDOR_ID_PHILIPS,
 		.device       = PCI_DEVICE_ID_PHILIPS_SAA7134,
diff --git a/drivers/media/pci/saa7134/saa7134-core.c b/drivers/media/pci/saa7134/saa7134-core.c
index 9ff03a69ced4..236ed725f933 100644
--- a/drivers/media/pci/saa7134/saa7134-core.c
+++ b/drivers/media/pci/saa7134/saa7134-core.c
@@ -160,6 +160,8 @@ static void request_module_async(struct work_struct *work){
 		request_module("saa7134-empress");
 	if (card_is_dvb(dev))
 		request_module("saa7134-dvb");
+	if (card_is_go7007(dev))
+		request_module("saa7134-go7007");
 	if (alsa) {
 		if (dev->pci->device != PCI_DEVICE_ID_PHILIPS_SAA7130)
 			request_module("saa7134-alsa");
@@ -563,8 +565,12 @@ static irqreturn_t saa7134_irq(int irq, void *dev_id)
 			saa7134_irq_vbi_done(dev,status);
 
 		if ((report & SAA7134_IRQ_REPORT_DONE_RA2) &&
-		    card_has_mpeg(dev))
-			saa7134_irq_ts_done(dev,status);
+		    card_has_mpeg(dev)) {
+			if (dev->mops->irq_ts_done != NULL)
+				dev->mops->irq_ts_done(dev, status);
+			else
+				saa7134_irq_ts_done(dev, status);
+		}
 
 		if (report & SAA7134_IRQ_REPORT_GPIO16) {
 			switch (dev->has_remote) {
diff --git a/drivers/media/pci/saa7134/saa7134-go7007.c b/drivers/media/pci/saa7134/saa7134-go7007.c
new file mode 100644
index 000000000000..54e650b4dff1
--- /dev/null
+++ b/drivers/media/pci/saa7134/saa7134-go7007.c
@@ -0,0 +1,531 @@
+/*
+ * Copyright (C) 2005-2006 Micronas USA Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (Version 2) as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/mm.h>
+#include <linux/usb.h>
+#include <linux/i2c.h>
+#include <asm/byteorder.h>
+#include <media/v4l2-common.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-subdev.h>
+
+#include "saa7134.h"
+#include "saa7134-reg.h"
+#include "go7007-priv.h"
+
+/*#define GO7007_HPI_DEBUG*/
+
+enum hpi_address {
+	HPI_ADDR_VIDEO_BUFFER = 0xe4,
+	HPI_ADDR_INIT_BUFFER = 0xea,
+	HPI_ADDR_INTR_RET_VALUE = 0xee,
+	HPI_ADDR_INTR_RET_DATA = 0xec,
+	HPI_ADDR_INTR_STATUS = 0xf4,
+	HPI_ADDR_INTR_WR_PARAM = 0xf6,
+	HPI_ADDR_INTR_WR_INDEX = 0xf8,
+};
+
+enum gpio_command {
+	GPIO_COMMAND_RESET = 0x00, /* 000b */
+	GPIO_COMMAND_REQ1  = 0x04, /* 001b */
+	GPIO_COMMAND_WRITE = 0x20, /* 010b */
+	GPIO_COMMAND_REQ2  = 0x24, /* 011b */
+	GPIO_COMMAND_READ  = 0x80, /* 100b */
+	GPIO_COMMAND_VIDEO = 0x84, /* 101b */
+	GPIO_COMMAND_IDLE  = 0xA0, /* 110b */
+	GPIO_COMMAND_ADDR  = 0xA4, /* 111b */
+};
+
+struct saa7134_go7007 {
+	struct v4l2_subdev sd;
+	struct saa7134_dev *dev;
+	u8 *top;
+	u8 *bottom;
+	dma_addr_t top_dma;
+	dma_addr_t bottom_dma;
+};
+
+static inline struct saa7134_go7007 *to_state(struct v4l2_subdev *sd)
+{
+	return container_of(sd, struct saa7134_go7007, sd);
+}
+
+static const struct go7007_board_info board_voyager = {
+	.flags		 = 0,
+	.sensor_flags	 = GO7007_SENSOR_656 |
+				GO7007_SENSOR_VALID_ENABLE |
+				GO7007_SENSOR_TV |
+				GO7007_SENSOR_VBI,
+	.audio_flags	= GO7007_AUDIO_I2S_MODE_1 |
+				GO7007_AUDIO_WORD_16,
+	.audio_rate	 = 48000,
+	.audio_bclk_div	 = 8,
+	.audio_main_div	 = 2,
+	.hpi_buffer_cap  = 7,
+	.num_inputs	 = 1,
+	.inputs		 = {
+		{
+			.name		= "SAA7134",
+		},
+	},
+};
+
+/********************* Driver for GPIO HPI interface *********************/
+
+static int gpio_write(struct saa7134_dev *dev, u8 addr, u16 data)
+{
+	saa_writeb(SAA7134_GPIO_GPMODE0, 0xff);
+
+	/* Write HPI address */
+	saa_writeb(SAA7134_GPIO_GPSTATUS0, addr);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_ADDR);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_IDLE);
+
+	/* Write low byte */
+	saa_writeb(SAA7134_GPIO_GPSTATUS0, data & 0xff);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_WRITE);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_IDLE);
+
+	/* Write high byte */
+	saa_writeb(SAA7134_GPIO_GPSTATUS0, data >> 8);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_WRITE);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_IDLE);
+
+	return 0;
+}
+
+static int gpio_read(struct saa7134_dev *dev, u8 addr, u16 *data)
+{
+	saa_writeb(SAA7134_GPIO_GPMODE0, 0xff);
+
+	/* Write HPI address */
+	saa_writeb(SAA7134_GPIO_GPSTATUS0, addr);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_ADDR);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_IDLE);
+
+	saa_writeb(SAA7134_GPIO_GPMODE0, 0x00);
+
+	/* Read low byte */
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_READ);
+	saa_clearb(SAA7134_GPIO_GPMODE3, SAA7134_GPIO_GPRESCAN);
+	saa_setb(SAA7134_GPIO_GPMODE3, SAA7134_GPIO_GPRESCAN);
+	*data = saa_readb(SAA7134_GPIO_GPSTATUS0);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_IDLE);
+
+	/* Read high byte */
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_READ);
+	saa_clearb(SAA7134_GPIO_GPMODE3, SAA7134_GPIO_GPRESCAN);
+	saa_setb(SAA7134_GPIO_GPMODE3, SAA7134_GPIO_GPRESCAN);
+	*data |= saa_readb(SAA7134_GPIO_GPSTATUS0) << 8;
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_IDLE);
+
+	return 0;
+}
+
+static int saa7134_go7007_interface_reset(struct go7007 *go)
+{
+	struct saa7134_go7007 *saa = go->hpi_context;
+	struct saa7134_dev *dev = saa->dev;
+	u16 intr_val, intr_data;
+	int count = 20;
+
+	saa_clearb(SAA7134_TS_PARALLEL, 0x80); /* Disable TS interface */
+	saa_writeb(SAA7134_GPIO_GPMODE2, 0xa4);
+	saa_writeb(SAA7134_GPIO_GPMODE0, 0xff);
+
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_REQ1);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_RESET);
+	msleep(1);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_REQ1);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_REQ2);
+	msleep(10);
+
+	saa_clearb(SAA7134_GPIO_GPMODE3, SAA7134_GPIO_GPRESCAN);
+	saa_setb(SAA7134_GPIO_GPMODE3, SAA7134_GPIO_GPRESCAN);
+
+	saa_readb(SAA7134_GPIO_GPSTATUS2);
+	/*pr_debug("status is %s\n", saa_readb(SAA7134_GPIO_GPSTATUS2) & 0x40 ? "OK" : "not OK"); */
+
+	/* enter command mode...(?) */
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_REQ1);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_REQ2);
+
+	do {
+		saa_clearb(SAA7134_GPIO_GPMODE3, SAA7134_GPIO_GPRESCAN);
+		saa_setb(SAA7134_GPIO_GPMODE3, SAA7134_GPIO_GPRESCAN);
+		saa_readb(SAA7134_GPIO_GPSTATUS2);
+		/*pr_info("gpio is %08x\n", saa_readl(SAA7134_GPIO_GPSTATUS0 >> 2)); */
+	} while (--count > 0);
+
+	/* Wait for an interrupt to indicate successful hardware reset */
+	if (go7007_read_interrupt(go, &intr_val, &intr_data) < 0 ||
+			(intr_val & ~0x1) != 0x55aa) {
+		pr_err("saa7134-go7007: unable to reset the GO7007\n");
+		return -1;
+	}
+	return 0;
+}
+
+static int saa7134_go7007_write_interrupt(struct go7007 *go, int addr, int data)
+{
+	struct saa7134_go7007 *saa = go->hpi_context;
+	struct saa7134_dev *dev = saa->dev;
+	int i;
+	u16 status_reg;
+
+#ifdef GO7007_HPI_DEBUG
+	pr_debug("saa7134-go7007: WriteInterrupt: %04x %04x\n", addr, data);
+#endif
+
+	for (i = 0; i < 100; ++i) {
+		gpio_read(dev, HPI_ADDR_INTR_STATUS, &status_reg);
+		if (!(status_reg & 0x0010))
+			break;
+		msleep(10);
+	}
+	if (i == 100) {
+		pr_err("saa7134-go7007: device is hung, status reg = 0x%04x\n",
+			status_reg);
+		return -1;
+	}
+	gpio_write(dev, HPI_ADDR_INTR_WR_PARAM, data);
+	gpio_write(dev, HPI_ADDR_INTR_WR_INDEX, addr);
+
+	return 0;
+}
+
+static int saa7134_go7007_read_interrupt(struct go7007 *go)
+{
+	struct saa7134_go7007 *saa = go->hpi_context;
+	struct saa7134_dev *dev = saa->dev;
+
+	/* XXX we need to wait if there is no interrupt available */
+	go->interrupt_available = 1;
+	gpio_read(dev, HPI_ADDR_INTR_RET_VALUE, &go->interrupt_value);
+	gpio_read(dev, HPI_ADDR_INTR_RET_DATA, &go->interrupt_data);
+#ifdef GO7007_HPI_DEBUG
+	pr_debug("saa7134-go7007: ReadInterrupt: %04x %04x\n",
+			go->interrupt_value, go->interrupt_data);
+#endif
+	return 0;
+}
+
+static void saa7134_go7007_irq_ts_done(struct saa7134_dev *dev,
+						unsigned long status)
+{
+	struct go7007 *go = video_get_drvdata(dev->empress_dev);
+	struct saa7134_go7007 *saa = go->hpi_context;
+
+	if (!vb2_is_streaming(&go->vidq))
+		return;
+	if (0 != (status & 0x000f0000))
+		pr_debug("saa7134-go7007: irq: lost %ld\n",
+				(status >> 16) & 0x0f);
+	if (status & 0x100000) {
+		dma_sync_single_for_cpu(&dev->pci->dev,
+					saa->bottom_dma, PAGE_SIZE, DMA_FROM_DEVICE);
+		go7007_parse_video_stream(go, saa->bottom, PAGE_SIZE);
+		saa_writel(SAA7134_RS_BA2(5), saa->bottom_dma);
+	} else {
+		dma_sync_single_for_cpu(&dev->pci->dev,
+					saa->top_dma, PAGE_SIZE, DMA_FROM_DEVICE);
+		go7007_parse_video_stream(go, saa->top, PAGE_SIZE);
+		saa_writel(SAA7134_RS_BA1(5), saa->top_dma);
+	}
+}
+
+static int saa7134_go7007_stream_start(struct go7007 *go)
+{
+	struct saa7134_go7007 *saa = go->hpi_context;
+	struct saa7134_dev *dev = saa->dev;
+
+	saa->top_dma = dma_map_page(&dev->pci->dev, virt_to_page(saa->top),
+			0, PAGE_SIZE, DMA_FROM_DEVICE);
+	if (dma_mapping_error(&dev->pci->dev, saa->top_dma))
+		return -ENOMEM;
+	saa->bottom_dma = dma_map_page(&dev->pci->dev,
+			virt_to_page(saa->bottom),
+			0, PAGE_SIZE, DMA_FROM_DEVICE);
+	if (dma_mapping_error(&dev->pci->dev, saa->bottom_dma)) {
+		dma_unmap_page(&dev->pci->dev, saa->top_dma, PAGE_SIZE,
+				DMA_FROM_DEVICE);
+		return -ENOMEM;
+	}
+
+	saa_writel(SAA7134_VIDEO_PORT_CTRL0 >> 2, 0xA300B000);
+	saa_writel(SAA7134_VIDEO_PORT_CTRL4 >> 2, 0x40000200);
+
+	/* Set HPI interface for video */
+	saa_writeb(SAA7134_GPIO_GPMODE0, 0xff);
+	saa_writeb(SAA7134_GPIO_GPSTATUS0, HPI_ADDR_VIDEO_BUFFER);
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_ADDR);
+	saa_writeb(SAA7134_GPIO_GPMODE0, 0x00);
+
+	/* Enable TS interface */
+	saa_writeb(SAA7134_TS_PARALLEL, 0xe6);
+
+	/* Reset TS interface */
+	saa_setb(SAA7134_TS_SERIAL1, 0x01);
+	saa_clearb(SAA7134_TS_SERIAL1, 0x01);
+
+	/* Set up transfer block size */
+	saa_writeb(SAA7134_TS_PARALLEL_SERIAL, 128 - 1);
+	saa_writeb(SAA7134_TS_DMA0, (PAGE_SIZE >> 7) - 1);
+	saa_writeb(SAA7134_TS_DMA1, 0);
+	saa_writeb(SAA7134_TS_DMA2, 0);
+
+	/* Enable video streaming mode */
+	saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_VIDEO);
+
+	saa_writel(SAA7134_RS_BA1(5), saa->top_dma);
+	saa_writel(SAA7134_RS_BA2(5), saa->bottom_dma);
+	saa_writel(SAA7134_RS_PITCH(5), 128);
+	saa_writel(SAA7134_RS_CONTROL(5), SAA7134_RS_CONTROL_BURST_MAX);
+
+	/* Enable TS FIFO */
+	saa_setl(SAA7134_MAIN_CTRL, SAA7134_MAIN_CTRL_TE5);
+
+	/* Enable DMA IRQ */
+	saa_setl(SAA7134_IRQ1,
+			SAA7134_IRQ1_INTE_RA2_1 | SAA7134_IRQ1_INTE_RA2_0);
+
+	return 0;
+}
+
+static int saa7134_go7007_stream_stop(struct go7007 *go)
+{
+	struct saa7134_go7007 *saa = go->hpi_context;
+	struct saa7134_dev *dev;
+
+	if (!saa)
+		return -EINVAL;
+	dev = saa->dev;
+	if (!dev)
+		return -EINVAL;
+
+	/* Shut down TS FIFO */
+	saa_clearl(SAA7134_MAIN_CTRL, SAA7134_MAIN_CTRL_TE5);
+
+	/* Disable DMA IRQ */
+	saa_clearl(SAA7134_IRQ1,
+			SAA7134_IRQ1_INTE_RA2_1 | SAA7134_IRQ1_INTE_RA2_0);
+
+	/* Disable TS interface */
+	saa_clearb(SAA7134_TS_PARALLEL, 0x80);
+
+	dma_unmap_page(&dev->pci->dev, saa->top_dma, PAGE_SIZE,
+			DMA_FROM_DEVICE);
+	dma_unmap_page(&dev->pci->dev, saa->bottom_dma, PAGE_SIZE,
+			DMA_FROM_DEVICE);
+
+	return 0;
+}
+
+static int saa7134_go7007_send_firmware(struct go7007 *go, u8 *data, int len)
+{
+	struct saa7134_go7007 *saa = go->hpi_context;
+	struct saa7134_dev *dev = saa->dev;
+	u16 status_reg;
+	int i;
+
+#ifdef GO7007_HPI_DEBUG
+	pr_debug("saa7134-go7007: DownloadBuffer sending %d bytes\n", len);
+#endif
+
+	while (len > 0) {
+		i = len > 64 ? 64 : len;
+		saa_writeb(SAA7134_GPIO_GPMODE0, 0xff);
+		saa_writeb(SAA7134_GPIO_GPSTATUS0, HPI_ADDR_INIT_BUFFER);
+		saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_ADDR);
+		saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_IDLE);
+		while (i-- > 0) {
+			saa_writeb(SAA7134_GPIO_GPSTATUS0, *data);
+			saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_WRITE);
+			saa_writeb(SAA7134_GPIO_GPSTATUS2, GPIO_COMMAND_IDLE);
+			++data;
+			--len;
+		}
+		for (i = 0; i < 100; ++i) {
+			gpio_read(dev, HPI_ADDR_INTR_STATUS, &status_reg);
+			if (!(status_reg & 0x0002))
+				break;
+		}
+		if (i == 100) {
+			pr_err("saa7134-go7007: device is hung, status reg = 0x%04x\n",
+			       status_reg);
+			return -1;
+		}
+	}
+	return 0;
+}
+
+static struct go7007_hpi_ops saa7134_go7007_hpi_ops = {
+	.interface_reset	= saa7134_go7007_interface_reset,
+	.write_interrupt	= saa7134_go7007_write_interrupt,
+	.read_interrupt		= saa7134_go7007_read_interrupt,
+	.stream_start		= saa7134_go7007_stream_start,
+	.stream_stop		= saa7134_go7007_stream_stop,
+	.send_firmware		= saa7134_go7007_send_firmware,
+};
+MODULE_FIRMWARE("go7007/go7007tv.bin");
+
+/* --------------------------------------------------------------------------*/
+
+static int saa7134_go7007_s_std(struct v4l2_subdev *sd, v4l2_std_id norm)
+{
+#if 0
+	struct saa7134_go7007 *saa = to_state(sd);
+	struct saa7134_dev *dev = saa->dev;
+
+	return saa7134_s_std_internal(dev, NULL, norm);
+#else
+	return 0;
+#endif
+}
+
+static const struct v4l2_subdev_video_ops saa7134_go7007_video_ops = {
+	.s_std = saa7134_go7007_s_std,
+};
+
+static const struct v4l2_subdev_ops saa7134_go7007_sd_ops = {
+	.video = &saa7134_go7007_video_ops,
+};
+
+/* --------------------------------------------------------------------------*/
+
+
+/********************* Add/remove functions *********************/
+
+static int saa7134_go7007_init(struct saa7134_dev *dev)
+{
+	struct go7007 *go;
+	struct saa7134_go7007 *saa;
+	struct v4l2_subdev *sd;
+
+	pr_debug("saa7134-go7007: probing new SAA713X board\n");
+
+	go = go7007_alloc(&board_voyager, &dev->pci->dev);
+	if (go == NULL)
+		return -ENOMEM;
+
+	saa = kzalloc(sizeof(struct saa7134_go7007), GFP_KERNEL);
+	if (saa == NULL) {
+		kfree(go);
+		return -ENOMEM;
+	}
+
+	go->board_id = GO7007_BOARDID_PCI_VOYAGER;
+	snprintf(go->bus_info, sizeof(go->bus_info), "PCI:%s", pci_name(dev->pci));
+	strlcpy(go->name, saa7134_boards[dev->board].name, sizeof(go->name));
+	go->hpi_ops = &saa7134_go7007_hpi_ops;
+	go->hpi_context = saa;
+	saa->dev = dev;
+
+	/* Init the subdevice interface */
+	sd = &saa->sd;
+	v4l2_subdev_init(sd, &saa7134_go7007_sd_ops);
+	v4l2_set_subdevdata(sd, saa);
+	strncpy(sd->name, "saa7134-go7007", sizeof(sd->name));
+
+	/* Allocate a couple pages for receiving the compressed stream */
+	saa->top = (u8 *)get_zeroed_page(GFP_KERNEL);
+	if (!saa->top)
+		goto allocfail;
+	saa->bottom = (u8 *)get_zeroed_page(GFP_KERNEL);
+	if (!saa->bottom)
+		goto allocfail;
+
+	/* Boot the GO7007 */
+	if (go7007_boot_encoder(go, go->board_info->flags &
+					GO7007_BOARD_USE_ONBOARD_I2C) < 0)
+		goto allocfail;
+
+	/* Do any final GO7007 initialization, then register the
+	 * V4L2 and ALSA interfaces */
+	if (go7007_register_encoder(go, go->board_info->num_i2c_devs) < 0)
+		goto allocfail;
+
+	/* Register the subdevice interface with the go7007 device */
+	if (v4l2_device_register_subdev(&go->v4l2_dev, sd) < 0)
+		pr_info("saa7134-go7007: register subdev failed\n");
+
+	dev->empress_dev = &go->vdev;
+
+	go->status = STATUS_ONLINE;
+	return 0;
+
+allocfail:
+	if (saa->top)
+		free_page((unsigned long)saa->top);
+	if (saa->bottom)
+		free_page((unsigned long)saa->bottom);
+	kfree(saa);
+	kfree(go);
+	return -ENOMEM;
+}
+
+static int saa7134_go7007_fini(struct saa7134_dev *dev)
+{
+	struct go7007 *go;
+	struct saa7134_go7007 *saa;
+
+	if (NULL == dev->empress_dev)
+		return 0;
+
+	go = video_get_drvdata(dev->empress_dev);
+	if (go->audio_enabled)
+		go7007_snd_remove(go);
+
+	saa = go->hpi_context;
+	go->status = STATUS_SHUTDOWN;
+	free_page((unsigned long)saa->top);
+	free_page((unsigned long)saa->bottom);
+	v4l2_device_unregister_subdev(&saa->sd);
+	kfree(saa);
+	video_unregister_device(&go->vdev);
+
+	v4l2_device_put(&go->v4l2_dev);
+	dev->empress_dev = NULL;
+
+	return 0;
+}
+
+static struct saa7134_mpeg_ops saa7134_go7007_ops = {
+	.type          = SAA7134_MPEG_GO7007,
+	.init          = saa7134_go7007_init,
+	.fini          = saa7134_go7007_fini,
+	.irq_ts_done   = saa7134_go7007_irq_ts_done,
+};
+
+static int __init saa7134_go7007_mod_init(void)
+{
+	return saa7134_ts_register(&saa7134_go7007_ops);
+}
+
+static void __exit saa7134_go7007_mod_cleanup(void)
+{
+	saa7134_ts_unregister(&saa7134_go7007_ops);
+}
+
+module_init(saa7134_go7007_mod_init);
+module_exit(saa7134_go7007_mod_cleanup);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/pci/saa7134/saa7134-vbi.c b/drivers/media/pci/saa7134/saa7134-vbi.c
index c06dbe17a87f..4f0b1012e4f3 100644
--- a/drivers/media/pci/saa7134/saa7134-vbi.c
+++ b/drivers/media/pci/saa7134/saa7134-vbi.c
@@ -43,7 +43,7 @@ MODULE_PARM_DESC(vbibufs,"number of vbi buffers, range 2-32");
 
 /* ------------------------------------------------------------------ */
 
-#define VBI_LINE_COUNT     16
+#define VBI_LINE_COUNT     17
 #define VBI_LINE_LENGTH  2048
 #define VBI_SCALE       0x200
 
diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c
index 0cfa2ca6a32a..fc4a427cb51f 100644
--- a/drivers/media/pci/saa7134/saa7134-video.c
+++ b/drivers/media/pci/saa7134/saa7134-video.c
@@ -201,7 +201,7 @@ static struct saa7134_format formats[] = {
 		.video_v_start = 24,	\
 		.video_v_stop  = 311,	\
 		.vbi_v_start_0 = 7,	\
-		.vbi_v_stop_0  = 22,	\
+		.vbi_v_stop_0  = 23,	\
 		.vbi_v_start_1 = 319,   \
 		.src_timing    = 4
 
diff --git a/drivers/media/pci/saa7134/saa7134.h b/drivers/media/pci/saa7134/saa7134.h
index e47edd4b57ce..1a82dd07205b 100644
--- a/drivers/media/pci/saa7134/saa7134.h
+++ b/drivers/media/pci/saa7134/saa7134.h
@@ -338,6 +338,7 @@ struct saa7134_card_ir {
 #define SAA7134_BOARD_ASUSTeK_PS3_100      190
 #define SAA7134_BOARD_HAWELL_HW_9004V1      191
 #define SAA7134_BOARD_AVERMEDIA_A706		192
+#define SAA7134_BOARD_WIS_VOYAGER           193
 
 #define SAA7134_MAXBOARDS 32
 #define SAA7134_INPUT_MAX 8
@@ -368,6 +369,7 @@ enum saa7134_mpeg_type {
 	SAA7134_MPEG_UNUSED,
 	SAA7134_MPEG_EMPRESS,
 	SAA7134_MPEG_DVB,
+	SAA7134_MPEG_GO7007,
 };
 
 enum saa7134_mpeg_ts_type {
@@ -407,6 +409,7 @@ struct saa7134_board {
 #define card_has_radio(dev)   (NULL != saa7134_boards[dev->board].radio.name)
 #define card_is_empress(dev)  (SAA7134_MPEG_EMPRESS == saa7134_boards[dev->board].mpeg)
 #define card_is_dvb(dev)      (SAA7134_MPEG_DVB     == saa7134_boards[dev->board].mpeg)
+#define card_is_go7007(dev)   (SAA7134_MPEG_GO7007  == saa7134_boards[dev->board].mpeg)
 #define card_has_mpeg(dev)    (SAA7134_MPEG_UNUSED  != saa7134_boards[dev->board].mpeg)
 #define card(dev)             (saa7134_boards[dev->board])
 #define card_in(dev,n)        (saa7134_boards[dev->board].inputs[n])
@@ -522,6 +525,8 @@ struct saa7134_mpeg_ops {
 	int                        (*init)(struct saa7134_dev *dev);
 	int                        (*fini)(struct saa7134_dev *dev);
 	void                       (*signal_change)(struct saa7134_dev *dev);
+	void                       (*irq_ts_done)(struct saa7134_dev *dev,
+						  unsigned long status);
 };
 
 /* global device status */
diff --git a/drivers/media/pci/saa7164/saa7164-api.c b/drivers/media/pci/saa7164/saa7164-api.c
index e042963d377d..4f3b1dd18ba4 100644
--- a/drivers/media/pci/saa7164/saa7164-api.c
+++ b/drivers/media/pci/saa7164/saa7164-api.c
@@ -680,7 +680,6 @@ static int saa7164_api_set_dif(struct saa7164_port *port, u8 reg, u8 val)
 int saa7164_api_configure_dif(struct saa7164_port *port, u32 std)
 {
 	struct saa7164_dev *dev = port->dev;
-	int ret = 0;
 	u8 agc_disable;
 
 	dprintk(DBGLVL_API, "%s(nr=%d, 0x%x)\n", __func__, port->nr, std);
@@ -733,7 +732,7 @@ int saa7164_api_configure_dif(struct saa7164_port *port, u32 std)
 	saa7164_api_set_dif(port, 0x04, 0x00); /* Active (again) */
 	msleep(100);
 
-	return ret;
+	return 0;
 }
 
 /* Ensure the dif is in the correct state for the operating mode
diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c
index 1bf06970ca3e..cc1be8a7a451 100644
--- a/drivers/media/pci/saa7164/saa7164-core.c
+++ b/drivers/media/pci/saa7164/saa7164-core.c
@@ -52,7 +52,7 @@ unsigned int saa_debug;
 module_param_named(debug, saa_debug, int, 0644);
 MODULE_PARM_DESC(debug, "enable debug messages");
 
-unsigned int fw_debug;
+static unsigned int fw_debug;
 module_param(fw_debug, int, 0644);
 MODULE_PARM_DESC(fw_debug, "Firmware debug level def:2");
 
@@ -72,7 +72,7 @@ static unsigned int card[]  = {[0 ... (SAA7164_MAXBOARDS - 1)] = UNSET };
 module_param_array(card,  int, NULL, 0444);
 MODULE_PARM_DESC(card, "card type");
 
-unsigned int print_histogram = 64;
+static unsigned int print_histogram = 64;
 module_param(print_histogram, int, 0644);
 MODULE_PARM_DESC(print_histogram, "print histogram values once");
 
@@ -80,7 +80,7 @@ unsigned int crc_checking = 1;
 module_param(crc_checking, int, 0644);
 MODULE_PARM_DESC(crc_checking, "enable crc sanity checking on buffers");
 
-unsigned int guard_checking = 1;
+static unsigned int guard_checking = 1;
 module_param(guard_checking, int, 0644);
 MODULE_PARM_DESC(guard_checking,
 	"enable dma sanity checking for buffer overruns");
diff --git a/drivers/media/pci/solo6x10/Kconfig b/drivers/media/pci/solo6x10/Kconfig
index d9e06a6bf1eb..0fb91dc7ca73 100644
--- a/drivers/media/pci/solo6x10/Kconfig
+++ b/drivers/media/pci/solo6x10/Kconfig
@@ -1,6 +1,7 @@
 config VIDEO_SOLO6X10
 	tristate "Bluecherry / Softlogic 6x10 capture cards (MPEG-4/H.264)"
 	depends on PCI && VIDEO_DEV && SND && I2C
+	depends on HAS_DMA
 	select BITREVERSE
 	select FONT_SUPPORT
 	select FONT_8x16
diff --git a/drivers/media/pci/solo6x10/solo6x10-disp.c b/drivers/media/pci/solo6x10/solo6x10-disp.c
index 5ea9cac03968..11c98f0625e4 100644
--- a/drivers/media/pci/solo6x10/solo6x10-disp.c
+++ b/drivers/media/pci/solo6x10/solo6x10-disp.c
@@ -172,7 +172,7 @@ static void solo_vout_config(struct solo_dev *solo_dev)
 static int solo_dma_vin_region(struct solo_dev *solo_dev, u32 off,
 			       u16 val, int reg_size)
 {
-	u16 *buf;
+	__le16 *buf;
 	const int n = 64, size = n * sizeof(*buf);
 	int i, ret = 0;
 
@@ -211,7 +211,7 @@ int solo_set_motion_block(struct solo_dev *solo_dev, u8 ch,
 {
 	const unsigned size = sizeof(u16) * 64;
 	u32 off = SOLO_MOT_FLAG_AREA + ch * SOLO_MOT_THRESH_SIZE * 2;
-	u16 *buf;
+	__le16 *buf;
 	int x, y;
 	int ret = 0;
 
diff --git a/drivers/media/pci/solo6x10/solo6x10-eeprom.c b/drivers/media/pci/solo6x10/solo6x10-eeprom.c
index af40b3aba410..da25ce4a6952 100644
--- a/drivers/media/pci/solo6x10/solo6x10-eeprom.c
+++ b/drivers/media/pci/solo6x10/solo6x10-eeprom.c
@@ -100,7 +100,7 @@ unsigned int solo_eeprom_ewen(struct solo_dev *solo_dev, int w_en)
 	return retval;
 }
 
-unsigned short solo_eeprom_read(struct solo_dev *solo_dev, int loc)
+__be16 solo_eeprom_read(struct solo_dev *solo_dev, int loc)
 {
 	int read_cmd = loc | (EE_READ_CMD << ADDR_LEN);
 	unsigned short retval = 0;
@@ -117,11 +117,11 @@ unsigned short solo_eeprom_read(struct solo_dev *solo_dev, int loc)
 
 	solo_eeprom_reg_write(solo_dev, ~EE_CS);
 
-	return retval;
+	return (__force __be16)retval;
 }
 
 int solo_eeprom_write(struct solo_dev *solo_dev, int loc,
-		      unsigned short data)
+		      __be16 data)
 {
 	int write_cmd = loc | (EE_WRITE_CMD << ADDR_LEN);
 	unsigned int retval;
@@ -130,7 +130,7 @@ int solo_eeprom_write(struct solo_dev *solo_dev, int loc,
 	solo_eeprom_cmd(solo_dev, write_cmd);
 
 	for (i = 15; i >= 0; i--) {
-		unsigned int dataval = (data >> i) & 1;
+		unsigned int dataval = ((__force unsigned)data >> i) & 1;
 
 		solo_eeprom_reg_write(solo_dev, EE_ENB);
 		solo_eeprom_reg_write(solo_dev,
diff --git a/drivers/media/pci/solo6x10/solo6x10.h b/drivers/media/pci/solo6x10/solo6x10.h
index c6154b00fcbd..72017b7f0a75 100644
--- a/drivers/media/pci/solo6x10/solo6x10.h
+++ b/drivers/media/pci/solo6x10/solo6x10.h
@@ -394,9 +394,9 @@ int solo_osd_print(struct solo_enc_dev *solo_enc);
 
 /* EEPROM commands */
 unsigned int solo_eeprom_ewen(struct solo_dev *solo_dev, int w_en);
-unsigned short solo_eeprom_read(struct solo_dev *solo_dev, int loc);
+__be16 solo_eeprom_read(struct solo_dev *solo_dev, int loc);
 int solo_eeprom_write(struct solo_dev *solo_dev, int loc,
-		      unsigned short data);
+		      __be16 data);
 
 /* JPEG Qp functions */
 void solo_s_jpeg_qp(struct solo_dev *solo_dev, unsigned int ch,
diff --git a/drivers/media/pci/sta2x11/Kconfig b/drivers/media/pci/sta2x11/Kconfig
index 03130157db83..f6f30abc088b 100644
--- a/drivers/media/pci/sta2x11/Kconfig
+++ b/drivers/media/pci/sta2x11/Kconfig
@@ -1,6 +1,7 @@
 config STA2X11_VIP
 	tristate "STA2X11 VIP Video For Linux"
 	depends on STA2X11
+	depends on HAS_DMA
 	select VIDEO_ADV7180 if MEDIA_SUBDRV_AUTOSELECT
 	select VIDEOBUF2_DMA_CONTIG
 	depends on PCI && VIDEO_V4L2 && VIRT_TO_BUS
diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c
index 365bd21301ba..22450f583da1 100644
--- a/drivers/media/pci/sta2x11/sta2x11_vip.c
+++ b/drivers/media/pci/sta2x11/sta2x11_vip.c
@@ -152,7 +152,7 @@ struct sta2x11_vip {
 	int tcount, bcount;
 	int overflow;
 
-	void *iomem;	/* I/O Memory */
+	void __iomem *iomem;	/* I/O Memory */
 	struct vip_config *config;
 };
 
diff --git a/drivers/media/pci/ttpci/Kconfig b/drivers/media/pci/ttpci/Kconfig
index 0dcb8cd77676..7b83151ed6c4 100644
--- a/drivers/media/pci/ttpci/Kconfig
+++ b/drivers/media/pci/ttpci/Kconfig
@@ -1,8 +1,12 @@
+config DVB_AV7110_IR
+	bool
+
 config DVB_AV7110
 	tristate "AV7110 cards"
 	depends on DVB_CORE && PCI && I2C
 	select TTPCI_EEPROM
 	select VIDEO_SAA7146_VV
+	select DVB_AV7110_IR if INPUT_EVDEV=y || INPUT_EVDEV=DVB_AV7110
 	depends on VIDEO_DEV	# dependencies of VIDEO_SAA7146_VV
 	select DVB_VES1820 if MEDIA_SUBDRV_AUTOSELECT
 	select DVB_VES1X93 if MEDIA_SUBDRV_AUTOSELECT
diff --git a/drivers/media/pci/ttpci/Makefile b/drivers/media/pci/ttpci/Makefile
index 98905963ff08..49f71b1eaf14 100644
--- a/drivers/media/pci/ttpci/Makefile
+++ b/drivers/media/pci/ttpci/Makefile
@@ -5,7 +5,7 @@
 
 dvb-ttpci-objs := av7110_hw.o av7110_v4l.o av7110_av.o av7110_ca.o av7110.o av7110_ipack.o
 
-ifdef CONFIG_INPUT_EVDEV
+ifdef CONFIG_DVB_AV7110_IR
 dvb-ttpci-objs += av7110_ir.o
 endif
 
diff --git a/drivers/media/pci/ttpci/av7110.c b/drivers/media/pci/ttpci/av7110.c
index f38329d29daa..c1f0617a6973 100644
--- a/drivers/media/pci/ttpci/av7110.c
+++ b/drivers/media/pci/ttpci/av7110.c
@@ -235,7 +235,7 @@ static void recover_arm(struct av7110 *av7110)
 
 	restart_feeds(av7110);
 
-#if IS_ENABLED(CONFIG_INPUT_EVDEV)
+#if IS_ENABLED(CONFIG_DVB_AV7110_IR)
 	av7110_check_ir_config(av7110, true);
 #endif
 }
@@ -268,7 +268,7 @@ static int arm_thread(void *data)
 		if (!av7110->arm_ready)
 			continue;
 
-#if IS_ENABLED(CONFIG_INPUT_EVDEV)
+#if IS_ENABLED(CONFIG_DVB_AV7110_IR)
 		av7110_check_ir_config(av7110, false);
 #endif
 
@@ -2725,7 +2725,7 @@ static int av7110_attach(struct saa7146_dev* dev,
 
 	mutex_init(&av7110->ioctl_mutex);
 
-#if IS_ENABLED(CONFIG_INPUT_EVDEV)
+#if IS_ENABLED(CONFIG_DVB_AV7110_IR)
 	av7110_ir_init(av7110);
 #endif
 	printk(KERN_INFO "dvb-ttpci: found av7110-%d.\n", av7110_num);
@@ -2768,7 +2768,7 @@ static int av7110_detach(struct saa7146_dev* saa)
 	struct av7110 *av7110 = saa->ext_priv;
 	dprintk(4, "%p\n", av7110);
 
-#if IS_ENABLED(CONFIG_INPUT_EVDEV)
+#if IS_ENABLED(CONFIG_DVB_AV7110_IR)
 	av7110_ir_exit(av7110);
 #endif
 	if (budgetpatch || av7110->full_ts) {
diff --git a/drivers/media/pci/tw68/Kconfig b/drivers/media/pci/tw68/Kconfig
new file mode 100644
index 000000000000..5425ba1e320d
--- /dev/null
+++ b/drivers/media/pci/tw68/Kconfig
@@ -0,0 +1,10 @@
+config VIDEO_TW68
+	tristate "Techwell tw68x Video For Linux"
+	depends on VIDEO_DEV && PCI && VIDEO_V4L2
+	select I2C_ALGOBIT
+	select VIDEOBUF2_DMA_SG
+	---help---
+	  Support for Techwell tw68xx based frame grabber boards.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called tw68.
diff --git a/drivers/media/pci/tw68/Makefile b/drivers/media/pci/tw68/Makefile
new file mode 100644
index 000000000000..3d02f28b14fb
--- /dev/null
+++ b/drivers/media/pci/tw68/Makefile
@@ -0,0 +1,3 @@
+tw68-objs := tw68-core.o tw68-video.o tw68-risc.o
+
+obj-$(CONFIG_VIDEO_TW68) += tw68.o
diff --git a/drivers/media/pci/tw68/tw68-core.c b/drivers/media/pci/tw68/tw68-core.c
new file mode 100644
index 000000000000..a6fb48cf7aae
--- /dev/null
+++ b/drivers/media/pci/tw68/tw68-core.c
@@ -0,0 +1,434 @@
+/*
+ *  tw68-core.c
+ *  Core functions for the Techwell 68xx driver
+ *
+ *  Much of this code is derived from the cx88 and sa7134 drivers, which
+ *  were in turn derived from the bt87x driver.  The original work was by
+ *  Gerd Knorr; more recently the code was enhanced by Mauro Carvalho Chehab,
+ *  Hans Verkuil, Andy Walls and many others.  Their work is gratefully
+ *  acknowledged.  Full credit goes to them - any problems within this code
+ *  are mine.
+ *
+ *  Copyright (C) 2009  William M. Brack
+ *
+ *  Refactored and updated to the latest v4l core frameworks:
+ *
+ *  Copyright (C) 2014 Hans Verkuil <hverkuil@xs4all.nl>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/sound.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/mutex.h>
+#include <linux/dma-mapping.h>
+#include <linux/pm.h>
+
+#include <media/v4l2-dev.h>
+#include "tw68.h"
+#include "tw68-reg.h"
+
+MODULE_DESCRIPTION("v4l2 driver module for tw6800 based video capture cards");
+MODULE_AUTHOR("William M. Brack");
+MODULE_AUTHOR("Hans Verkuil <hverkuil@xs4all.nl>");
+MODULE_LICENSE("GPL");
+
+static unsigned int latency = UNSET;
+module_param(latency, int, 0444);
+MODULE_PARM_DESC(latency, "pci latency timer");
+
+static unsigned int video_nr[] = {[0 ... (TW68_MAXBOARDS - 1)] = UNSET };
+module_param_array(video_nr, int, NULL, 0444);
+MODULE_PARM_DESC(video_nr, "video device number");
+
+static unsigned int card[] = {[0 ... (TW68_MAXBOARDS - 1)] = UNSET };
+module_param_array(card, int, NULL, 0444);
+MODULE_PARM_DESC(card, "card type");
+
+static atomic_t tw68_instance = ATOMIC_INIT(0);
+
+/* ------------------------------------------------------------------ */
+
+/*
+ * Please add any new PCI IDs to: http://pci-ids.ucw.cz.  This keeps
+ * the PCI ID database up to date.  Note that the entries must be
+ * added under vendor 0x1797 (Techwell Inc.) as subsystem IDs.
+ */
+static const struct pci_device_id tw68_pci_tbl[] = {
+	{PCI_DEVICE(PCI_VENDOR_ID_TECHWELL, PCI_DEVICE_ID_6800)},
+	{PCI_DEVICE(PCI_VENDOR_ID_TECHWELL, PCI_DEVICE_ID_6801)},
+	{PCI_DEVICE(PCI_VENDOR_ID_TECHWELL, PCI_DEVICE_ID_6804)},
+	{PCI_DEVICE(PCI_VENDOR_ID_TECHWELL, PCI_DEVICE_ID_6816_1)},
+	{PCI_DEVICE(PCI_VENDOR_ID_TECHWELL, PCI_DEVICE_ID_6816_2)},
+	{PCI_DEVICE(PCI_VENDOR_ID_TECHWELL, PCI_DEVICE_ID_6816_3)},
+	{PCI_DEVICE(PCI_VENDOR_ID_TECHWELL, PCI_DEVICE_ID_6816_4)},
+	{0,}
+};
+
+/* ------------------------------------------------------------------ */
+
+
+/*
+ * The device is given a "soft reset". According to the specifications,
+ * after this "all register content remain unchanged", so we also write
+ * to all specified registers manually as well (mostly to manufacturer's
+ * specified reset values)
+ */
+static int tw68_hw_init1(struct tw68_dev *dev)
+{
+	/* Assure all interrupts are disabled */
+	tw_writel(TW68_INTMASK, 0);		/* 020 */
+	/* Clear any pending interrupts */
+	tw_writel(TW68_INTSTAT, 0xffffffff);	/* 01C */
+	/* Stop risc processor, set default buffer level */
+	tw_writel(TW68_DMAC, 0x1600);
+
+	tw_writeb(TW68_ACNTL, 0x80);	/* 218	soft reset */
+	msleep(100);
+
+	tw_writeb(TW68_INFORM, 0x40);	/* 208	mux0, 27mhz xtal */
+	tw_writeb(TW68_OPFORM, 0x04);	/* 20C	analog line-lock */
+	tw_writeb(TW68_HSYNC, 0);	/* 210	color-killer high sens */
+	tw_writeb(TW68_ACNTL, 0x42);	/* 218	int vref #2, chroma adc off */
+
+	tw_writeb(TW68_CROP_HI, 0x02);	/* 21C	Hactive m.s. bits */
+	tw_writeb(TW68_VDELAY_LO, 0x12);/* 220	Mfg specified reset value */
+	tw_writeb(TW68_VACTIVE_LO, 0xf0);
+	tw_writeb(TW68_HDELAY_LO, 0x0f);
+	tw_writeb(TW68_HACTIVE_LO, 0xd0);
+
+	tw_writeb(TW68_CNTRL1, 0xcd);	/* 230	Wide Chroma BPF B/W
+					 *	Secam reduction, Adap comb for
+					 *	NTSC, Op Mode 1 */
+
+	tw_writeb(TW68_VSCALE_LO, 0);	/* 234 */
+	tw_writeb(TW68_SCALE_HI, 0x11);	/* 238 */
+	tw_writeb(TW68_HSCALE_LO, 0);	/* 23c */
+	tw_writeb(TW68_BRIGHT, 0);	/* 240 */
+	tw_writeb(TW68_CONTRAST, 0x5c);	/* 244 */
+	tw_writeb(TW68_SHARPNESS, 0x51);/* 248 */
+	tw_writeb(TW68_SAT_U, 0x80);	/* 24C */
+	tw_writeb(TW68_SAT_V, 0x80);	/* 250 */
+	tw_writeb(TW68_HUE, 0x00);	/* 254 */
+
+	/* TODO - Check that none of these are set by control defaults */
+	tw_writeb(TW68_SHARP2, 0x53);	/* 258	Mfg specified reset val */
+	tw_writeb(TW68_VSHARP, 0x80);	/* 25C	Sharpness Coring val 8 */
+	tw_writeb(TW68_CORING, 0x44);	/* 260	CTI and Vert Peak coring */
+	tw_writeb(TW68_CNTRL2, 0x00);	/* 268	No power saving enabled */
+	tw_writeb(TW68_SDT, 0x07);	/* 270	Enable shadow reg, auto-det */
+	tw_writeb(TW68_SDTR, 0x7f);	/* 274	All stds recog, don't start */
+	tw_writeb(TW68_CLMPG, 0x50);	/* 280	Clamp end at 40 sys clocks */
+	tw_writeb(TW68_IAGC, 0x22);	/* 284	Mfg specified reset val */
+	tw_writeb(TW68_AGCGAIN, 0xf0);	/* 288	AGC gain when loop disabled */
+	tw_writeb(TW68_PEAKWT, 0xd8);	/* 28C	White peak threshold */
+	tw_writeb(TW68_CLMPL, 0x3c);	/* 290	Y channel clamp level */
+/*	tw_writeb(TW68_SYNCT, 0x38);*/	/* 294	Sync amplitude */
+	tw_writeb(TW68_SYNCT, 0x30);	/* 294	Sync amplitude */
+	tw_writeb(TW68_MISSCNT, 0x44);	/* 298	Horiz sync, VCR detect sens */
+	tw_writeb(TW68_PCLAMP, 0x28);	/* 29C	Clamp pos from PLL sync */
+	/* Bit DETV of VCNTL1 helps sync multi cams/chip board */
+	tw_writeb(TW68_VCNTL1, 0x04);	/* 2A0 */
+	tw_writeb(TW68_VCNTL2, 0);	/* 2A4 */
+	tw_writeb(TW68_CKILL, 0x68);	/* 2A8	Mfg specified reset val */
+	tw_writeb(TW68_COMB, 0x44);	/* 2AC	Mfg specified reset val */
+	tw_writeb(TW68_LDLY, 0x30);	/* 2B0	Max positive luma delay */
+	tw_writeb(TW68_MISC1, 0x14);	/* 2B4	Mfg specified reset val */
+	tw_writeb(TW68_LOOP, 0xa5);	/* 2B8	Mfg specified reset val */
+	tw_writeb(TW68_MISC2, 0xe0);	/* 2BC	Enable colour killer */
+	tw_writeb(TW68_MVSN, 0);	/* 2C0 */
+	tw_writeb(TW68_CLMD, 0x05);	/* 2CC	slice level auto, clamp med. */
+	tw_writeb(TW68_IDCNTL, 0);	/* 2D0	Writing zero to this register
+					 *	selects NTSC ID detection,
+					 *	but doesn't change the
+					 *	sensitivity (which has a reset
+					 *	value of 1E).  Since we are
+					 *	not doing auto-detection, it
+					 *	has no real effect */
+	tw_writeb(TW68_CLCNTL1, 0);	/* 2D4 */
+	tw_writel(TW68_VBIC, 0x03);	/* 010 */
+	tw_writel(TW68_CAP_CTL, 0x03);	/* 040	Enable both even & odd flds */
+	tw_writel(TW68_DMAC, 0x2000);	/* patch set had 0x2080 */
+	tw_writel(TW68_TESTREG, 0);	/* 02C */
+
+	/*
+	 * Some common boards, especially inexpensive single-chip models,
+	 * use the GPIO bits 0-3 to control an on-board video-output mux.
+	 * For these boards, we need to set up the GPIO register into
+	 * "normal" mode, set bits 0-3 as output, and then set those bits
+	 * zero.
+	 *
+	 * Eventually, it would be nice if we could identify these boards
+	 * uniquely, and only do this initialisation if the board has been
+	 * identify.  For the moment, however, it shouldn't hurt anything
+	 * to do these steps.
+	 */
+	tw_writel(TW68_GPIOC, 0);	/* Set the GPIO to "normal", no ints */
+	tw_writel(TW68_GPOE, 0x0f);	/* Set bits 0-3 to "output" */
+	tw_writel(TW68_GPDATA, 0);	/* Set all bits to low state */
+
+	/* Initialize the device control structures */
+	mutex_init(&dev->lock);
+	spin_lock_init(&dev->slock);
+
+	/* Initialize any subsystems */
+	tw68_video_init1(dev);
+	return 0;
+}
+
+static irqreturn_t tw68_irq(int irq, void *dev_id)
+{
+	struct tw68_dev *dev = dev_id;
+	u32 status, orig;
+	int loop;
+
+	status = orig = tw_readl(TW68_INTSTAT) & dev->pci_irqmask;
+	/* Check if anything to do */
+	if (0 == status)
+		return IRQ_NONE;	/* Nope - return */
+	for (loop = 0; loop < 10; loop++) {
+		if (status & dev->board_virqmask)	/* video interrupt */
+			tw68_irq_video_done(dev, status);
+		status = tw_readl(TW68_INTSTAT) & dev->pci_irqmask;
+		if (0 == status)
+			return IRQ_HANDLED;
+	}
+	dev_dbg(&dev->pci->dev, "%s: **** INTERRUPT NOT HANDLED - clearing mask (orig 0x%08x, cur 0x%08x)",
+			dev->name, orig, tw_readl(TW68_INTSTAT));
+	dev_dbg(&dev->pci->dev, "%s: pci_irqmask 0x%08x; board_virqmask 0x%08x ****\n",
+			dev->name, dev->pci_irqmask, dev->board_virqmask);
+	tw_clearl(TW68_INTMASK, dev->pci_irqmask);
+	return IRQ_HANDLED;
+}
+
+static int tw68_initdev(struct pci_dev *pci_dev,
+				     const struct pci_device_id *pci_id)
+{
+	struct tw68_dev *dev;
+	int vidnr = -1;
+	int err;
+
+	dev = devm_kzalloc(&pci_dev->dev, sizeof(*dev), GFP_KERNEL);
+	if (NULL == dev)
+		return -ENOMEM;
+
+	dev->instance = v4l2_device_set_name(&dev->v4l2_dev, "tw68",
+						&tw68_instance);
+
+	err = v4l2_device_register(&pci_dev->dev, &dev->v4l2_dev);
+	if (err)
+		return err;
+
+	/* pci init */
+	dev->pci = pci_dev;
+	if (pci_enable_device(pci_dev)) {
+		err = -EIO;
+		goto fail1;
+	}
+
+	dev->name = dev->v4l2_dev.name;
+
+	if (UNSET != latency) {
+		pr_info("%s: setting pci latency timer to %d\n",
+		       dev->name, latency);
+		pci_write_config_byte(pci_dev, PCI_LATENCY_TIMER, latency);
+	}
+
+	/* print pci info */
+	pci_read_config_byte(pci_dev, PCI_CLASS_REVISION, &dev->pci_rev);
+	pci_read_config_byte(pci_dev, PCI_LATENCY_TIMER,  &dev->pci_lat);
+	pr_info("%s: found at %s, rev: %d, irq: %d, latency: %d, mmio: 0x%llx\n",
+		dev->name, pci_name(pci_dev), dev->pci_rev, pci_dev->irq,
+		dev->pci_lat, (u64)pci_resource_start(pci_dev, 0));
+	pci_set_master(pci_dev);
+	if (!pci_dma_supported(pci_dev, DMA_BIT_MASK(32))) {
+		pr_info("%s: Oops: no 32bit PCI DMA ???\n", dev->name);
+		err = -EIO;
+		goto fail1;
+	}
+
+	switch (pci_id->device) {
+	case PCI_DEVICE_ID_6800:	/* TW6800 */
+		dev->vdecoder = TW6800;
+		dev->board_virqmask = TW68_VID_INTS;
+		break;
+	case PCI_DEVICE_ID_6801:	/* Video decoder for TW6802 */
+		dev->vdecoder = TW6801;
+		dev->board_virqmask = TW68_VID_INTS | TW68_VID_INTSX;
+		break;
+	case PCI_DEVICE_ID_6804:	/* Video decoder for TW6804 */
+		dev->vdecoder = TW6804;
+		dev->board_virqmask = TW68_VID_INTS | TW68_VID_INTSX;
+		break;
+	default:
+		dev->vdecoder = TWXXXX;	/* To be announced */
+		dev->board_virqmask = TW68_VID_INTS | TW68_VID_INTSX;
+		break;
+	}
+
+	/* get mmio */
+	if (!request_mem_region(pci_resource_start(pci_dev, 0),
+				pci_resource_len(pci_dev, 0),
+				dev->name)) {
+		err = -EBUSY;
+		pr_err("%s: can't get MMIO memory @ 0x%llx\n",
+			dev->name,
+			(unsigned long long)pci_resource_start(pci_dev, 0));
+		goto fail1;
+	}
+	dev->lmmio = ioremap(pci_resource_start(pci_dev, 0),
+			     pci_resource_len(pci_dev, 0));
+	dev->bmmio = (__u8 __iomem *)dev->lmmio;
+	if (NULL == dev->lmmio) {
+		err = -EIO;
+		pr_err("%s: can't ioremap() MMIO memory\n",
+		       dev->name);
+		goto fail2;
+	}
+	/* initialize hardware #1 */
+	/* Then do any initialisation wanted before interrupts are on */
+	tw68_hw_init1(dev);
+
+	/* get irq */
+	err = devm_request_irq(&pci_dev->dev, pci_dev->irq, tw68_irq,
+			  IRQF_SHARED | IRQF_DISABLED, dev->name, dev);
+	if (err < 0) {
+		pr_err("%s: can't get IRQ %d\n",
+		       dev->name, pci_dev->irq);
+		goto fail3;
+	}
+
+	/*
+	 *  Now do remainder of initialisation, first for
+	 *  things unique for this card, then for general board
+	 */
+	if (dev->instance < TW68_MAXBOARDS)
+		vidnr = video_nr[dev->instance];
+	/* initialise video function first */
+	err = tw68_video_init2(dev, vidnr);
+	if (err < 0) {
+		pr_err("%s: can't register video device\n",
+		       dev->name);
+		goto fail4;
+	}
+	tw_setl(TW68_INTMASK, dev->pci_irqmask);
+
+	pr_info("%s: registered device %s\n",
+	       dev->name, video_device_node_name(&dev->vdev));
+
+	return 0;
+
+fail4:
+	video_unregister_device(&dev->vdev);
+fail3:
+	iounmap(dev->lmmio);
+fail2:
+	release_mem_region(pci_resource_start(pci_dev, 0),
+			   pci_resource_len(pci_dev, 0));
+fail1:
+	v4l2_device_unregister(&dev->v4l2_dev);
+	return err;
+}
+
+static void tw68_finidev(struct pci_dev *pci_dev)
+{
+	struct v4l2_device *v4l2_dev = pci_get_drvdata(pci_dev);
+	struct tw68_dev *dev =
+		container_of(v4l2_dev, struct tw68_dev, v4l2_dev);
+
+	/* shutdown subsystems */
+	tw_clearl(TW68_DMAC, TW68_DMAP_EN | TW68_FIFO_EN);
+	tw_writel(TW68_INTMASK, 0);
+
+	/* unregister */
+	video_unregister_device(&dev->vdev);
+	v4l2_ctrl_handler_free(&dev->hdl);
+
+	/* release resources */
+	iounmap(dev->lmmio);
+	release_mem_region(pci_resource_start(pci_dev, 0),
+			   pci_resource_len(pci_dev, 0));
+
+	v4l2_device_unregister(&dev->v4l2_dev);
+}
+
+#ifdef CONFIG_PM
+
+static int tw68_suspend(struct pci_dev *pci_dev , pm_message_t state)
+{
+	struct v4l2_device *v4l2_dev = pci_get_drvdata(pci_dev);
+	struct tw68_dev *dev = container_of(v4l2_dev,
+				struct tw68_dev, v4l2_dev);
+
+	tw_clearl(TW68_DMAC, TW68_DMAP_EN | TW68_FIFO_EN);
+	dev->pci_irqmask &= ~TW68_VID_INTS;
+	tw_writel(TW68_INTMASK, 0);
+
+	synchronize_irq(pci_dev->irq);
+
+	pci_save_state(pci_dev);
+	pci_set_power_state(pci_dev, pci_choose_state(pci_dev, state));
+	vb2_discard_done(&dev->vidq);
+
+	return 0;
+}
+
+static int tw68_resume(struct pci_dev *pci_dev)
+{
+	struct v4l2_device *v4l2_dev = pci_get_drvdata(pci_dev);
+	struct tw68_dev *dev = container_of(v4l2_dev,
+					    struct tw68_dev, v4l2_dev);
+	struct tw68_buf *buf;
+	unsigned long flags;
+
+	pci_set_power_state(pci_dev, PCI_D0);
+	pci_restore_state(pci_dev);
+
+	/* Do things that are done in tw68_initdev ,
+		except of initializing memory structures.*/
+
+	msleep(100);
+
+	tw68_set_tvnorm_hw(dev);
+
+	/*resume unfinished buffer(s)*/
+	spin_lock_irqsave(&dev->slock, flags);
+	buf = container_of(dev->active.next, struct tw68_buf, list);
+
+	tw68_video_start_dma(dev, buf);
+
+	spin_unlock_irqrestore(&dev->slock, flags);
+
+	return 0;
+}
+#endif
+
+/* ----------------------------------------------------------- */
+
+static struct pci_driver tw68_pci_driver = {
+	.name	  = "tw68",
+	.id_table = tw68_pci_tbl,
+	.probe	  = tw68_initdev,
+	.remove	  = tw68_finidev,
+#ifdef CONFIG_PM
+	.suspend  = tw68_suspend,
+	.resume   = tw68_resume
+#endif
+};
+
+module_pci_driver(tw68_pci_driver);
diff --git a/drivers/media/pci/tw68/tw68-reg.h b/drivers/media/pci/tw68/tw68-reg.h
new file mode 100644
index 000000000000..f60b3a896fa7
--- /dev/null
+++ b/drivers/media/pci/tw68/tw68-reg.h
@@ -0,0 +1,195 @@
+/*
+ *  tw68-reg.h - TW68xx register offsets
+ *
+ *  Much of this code is derived from the cx88 and sa7134 drivers, which
+ *  were in turn derived from the bt87x driver.  The original work was by
+ *  Gerd Knorr; more recently the code was enhanced by Mauro Carvalho Chehab,
+ *  Hans Verkuil, Andy Walls and many others.  Their work is gratefully
+ *  acknowledged.  Full credit goes to them - any problems within this code
+ *  are mine.
+ *
+ *  Copyright (C) William M. Brack
+ *
+ *  Refactored and updated to the latest v4l core frameworks:
+ *
+ *  Copyright (C) 2014 Hans Verkuil <hverkuil@xs4all.nl>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+*/
+
+#ifndef _TW68_REG_H_
+#define _TW68_REG_H_
+
+/* ---------------------------------------------------------------------- */
+#define	TW68_DMAC		0x000
+#define	TW68_DMAP_SA		0x004
+#define	TW68_DMAP_EXE		0x008
+#define	TW68_DMAP_PP		0x00c
+#define	TW68_VBIC		0x010
+#define	TW68_SBUSC		0x014
+#define	TW68_SBUSSD		0x018
+#define	TW68_INTSTAT		0x01C
+#define	TW68_INTMASK		0x020
+#define	TW68_GPIOC		0x024
+#define	TW68_GPOE		0x028
+#define	TW68_TESTREG		0x02C
+#define	TW68_SBUSRD		0x030
+#define	TW68_SBUS_TRIG		0x034
+#define	TW68_CAP_CTL		0x040
+#define	TW68_SUBSYS		0x054
+#define	TW68_I2C_RST		0x064
+#define	TW68_VBIINST		0x06C
+/* define bits in FIFO and DMAP Control reg */
+#define	TW68_DMAP_EN		(1 << 0)
+#define	TW68_FIFO_EN		(1 << 1)
+/* define the Interrupt Status Register bits */
+#define	TW68_SBDONE		(1 << 0)
+#define	TW68_DMAPI		(1 << 1)
+#define	TW68_GPINT		(1 << 2)
+#define	TW68_FFOF		(1 << 3)
+#define	TW68_FDMIS		(1 << 4)
+#define	TW68_DMAPERR		(1 << 5)
+#define	TW68_PABORT		(1 << 6)
+#define	TW68_SBDONE2		(1 << 12)
+#define	TW68_SBERR2		(1 << 13)
+#define	TW68_PPERR		(1 << 14)
+#define	TW68_FFERR		(1 << 15)
+#define	TW68_DET50		(1 << 16)
+#define	TW68_FLOCK		(1 << 17)
+#define	TW68_CCVALID		(1 << 18)
+#define	TW68_VLOCK		(1 << 19)
+#define	TW68_FIELD		(1 << 20)
+#define	TW68_SLOCK		(1 << 21)
+#define	TW68_HLOCK		(1 << 22)
+#define	TW68_VDLOSS		(1 << 23)
+#define	TW68_SBERR		(1 << 24)
+/* define the i2c control register bits */
+#define	TW68_SBMODE		(0)
+#define	TW68_WREN		(1)
+#define	TW68_SSCLK		(6)
+#define	TW68_SSDAT		(7)
+#define	TW68_SBCLK		(8)
+#define	TW68_WDLEN		(16)
+#define	TW68_RDLEN		(20)
+#define	TW68_SBRW		(24)
+#define	TW68_SBDEV		(25)
+
+#define	TW68_SBMODE_B		(1 << TW68_SBMODE)
+#define	TW68_WREN_B		(1 << TW68_WREN)
+#define	TW68_SSCLK_B		(1 << TW68_SSCLK)
+#define	TW68_SSDAT_B		(1 << TW68_SSDAT)
+#define	TW68_SBRW_B		(1 << TW68_SBRW)
+
+#define	TW68_GPDATA		0x100
+#define	TW68_STATUS1		0x204
+#define	TW68_INFORM		0x208
+#define	TW68_OPFORM		0x20C
+#define	TW68_HSYNC		0x210
+#define	TW68_ACNTL		0x218
+#define	TW68_CROP_HI		0x21C
+#define	TW68_VDELAY_LO		0x220
+#define	TW68_VACTIVE_LO		0x224
+#define	TW68_HDELAY_LO		0x228
+#define	TW68_HACTIVE_LO		0x22C
+#define	TW68_CNTRL1		0x230
+#define	TW68_VSCALE_LO		0x234
+#define	TW68_SCALE_HI		0x238
+#define	TW68_HSCALE_LO		0x23C
+#define	TW68_BRIGHT		0x240
+#define	TW68_CONTRAST		0x244
+#define	TW68_SHARPNESS		0x248
+#define	TW68_SAT_U		0x24C
+#define	TW68_SAT_V		0x250
+#define	TW68_HUE		0x254
+#define	TW68_SHARP2		0x258
+#define	TW68_VSHARP		0x25C
+#define	TW68_CORING		0x260
+#define	TW68_VBICNTL		0x264
+#define	TW68_CNTRL2		0x268
+#define	TW68_CC_DATA		0x26C
+#define	TW68_SDT		0x270
+#define	TW68_SDTR		0x274
+#define	TW68_RESERV2		0x278
+#define	TW68_RESERV3		0x27C
+#define	TW68_CLMPG		0x280
+#define	TW68_IAGC		0x284
+#define	TW68_AGCGAIN		0x288
+#define	TW68_PEAKWT		0x28C
+#define	TW68_CLMPL		0x290
+#define	TW68_SYNCT		0x294
+#define	TW68_MISSCNT		0x298
+#define	TW68_PCLAMP		0x29C
+#define	TW68_VCNTL1		0x2A0
+#define	TW68_VCNTL2		0x2A4
+#define	TW68_CKILL		0x2A8
+#define	TW68_COMB		0x2AC
+#define	TW68_LDLY		0x2B0
+#define	TW68_MISC1		0x2B4
+#define	TW68_LOOP		0x2B8
+#define	TW68_MISC2		0x2BC
+#define	TW68_MVSN		0x2C0
+#define	TW68_STATUS2		0x2C4
+#define	TW68_HFREF		0x2C8
+#define	TW68_CLMD		0x2CC
+#define	TW68_IDCNTL		0x2D0
+#define	TW68_CLCNTL1		0x2D4
+
+/* Audio */
+#define	TW68_ACKI1		0x300
+#define	TW68_ACKI2		0x304
+#define	TW68_ACKI3		0x308
+#define	TW68_ACKN1		0x30C
+#define	TW68_ACKN2		0x310
+#define	TW68_ACKN3		0x314
+#define	TW68_SDIV		0x318
+#define	TW68_LRDIV		0x31C
+#define	TW68_ACCNTL		0x320
+
+#define	TW68_VSCTL		0x3B8
+#define	TW68_CHROMAGVAL		0x3BC
+
+#define	TW68_F2CROP_HI		0x3DC
+#define	TW68_F2VDELAY_LO	0x3E0
+#define	TW68_F2VACTIVE_LO	0x3E4
+#define	TW68_F2HDELAY_LO	0x3E8
+#define	TW68_F2HACTIVE_LO	0x3EC
+#define	TW68_F2CNT		0x3F0
+#define	TW68_F2VSCALE_LO	0x3F4
+#define	TW68_F2SCALE_HI		0x3F8
+#define	TW68_F2HSCALE_LO	0x3FC
+
+#define	RISC_INT_BIT		0x08000000
+#define	RISC_SYNCO		0xC0000000
+#define	RISC_SYNCE		0xD0000000
+#define	RISC_JUMP		0xB0000000
+#define	RISC_LINESTART		0x90000000
+#define	RISC_INLINE		0xA0000000
+
+#define VideoFormatNTSC		 0
+#define VideoFormatNTSCJapan	 0
+#define VideoFormatPALBDGHI	 1
+#define VideoFormatSECAM	 2
+#define VideoFormatNTSC443	 3
+#define VideoFormatPALM		 4
+#define VideoFormatPALN		 5
+#define VideoFormatPALNC	 5
+#define VideoFormatPAL60	 6
+#define VideoFormatAuto		 7
+
+#define ColorFormatRGB32	 0x00
+#define ColorFormatRGB24	 0x10
+#define ColorFormatRGB16	 0x20
+#define ColorFormatRGB15	 0x30
+#define ColorFormatYUY2		 0x40
+#define ColorFormatBSWAP         0x04
+#define ColorFormatWSWAP         0x08
+#define ColorFormatGamma         0x80
+#endif
diff --git a/drivers/media/pci/tw68/tw68-risc.c b/drivers/media/pci/tw68/tw68-risc.c
new file mode 100644
index 000000000000..7439db212a69
--- /dev/null
+++ b/drivers/media/pci/tw68/tw68-risc.c
@@ -0,0 +1,230 @@
+/*
+ *  tw68_risc.c
+ *  Part of the device driver for Techwell 68xx based cards
+ *
+ *  Much of this code is derived from the cx88 and sa7134 drivers, which
+ *  were in turn derived from the bt87x driver.  The original work was by
+ *  Gerd Knorr; more recently the code was enhanced by Mauro Carvalho Chehab,
+ *  Hans Verkuil, Andy Walls and many others.  Their work is gratefully
+ *  acknowledged.  Full credit goes to them - any problems within this code
+ *  are mine.
+ *
+ *  Copyright (C) 2009  William M. Brack
+ *
+ *  Refactored and updated to the latest v4l core frameworks:
+ *
+ *  Copyright (C) 2014 Hans Verkuil <hverkuil@xs4all.nl>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ */
+
+#include "tw68.h"
+
+/**
+ *  @rp		pointer to current risc program position
+ *  @sglist	pointer to "scatter-gather list" of buffer pointers
+ *  @offset	offset to target memory buffer
+ *  @sync_line	0 -> no sync, 1 -> odd sync, 2 -> even sync
+ *  @bpl	number of bytes per scan line
+ *  @padding	number of bytes of padding to add
+ *  @lines	number of lines in field
+ *  @jump	insert a jump at the start
+ */
+static __le32 *tw68_risc_field(__le32 *rp, struct scatterlist *sglist,
+			    unsigned int offset, u32 sync_line,
+			    unsigned int bpl, unsigned int padding,
+			    unsigned int lines, bool jump)
+{
+	struct scatterlist *sg;
+	unsigned int line, todo, done;
+
+	if (jump) {
+		*(rp++) = cpu_to_le32(RISC_JUMP);
+		*(rp++) = 0;
+	}
+
+	/* sync instruction */
+	if (sync_line == 1)
+		*(rp++) = cpu_to_le32(RISC_SYNCO);
+	else
+		*(rp++) = cpu_to_le32(RISC_SYNCE);
+	*(rp++) = 0;
+
+	/* scan lines */
+	sg = sglist;
+	for (line = 0; line < lines; line++) {
+		/* calculate next starting position */
+		while (offset && offset >= sg_dma_len(sg)) {
+			offset -= sg_dma_len(sg);
+			sg = sg_next(sg);
+		}
+		if (bpl <= sg_dma_len(sg) - offset) {
+			/* fits into current chunk */
+			*(rp++) = cpu_to_le32(RISC_LINESTART |
+					      /* (offset<<12) |*/  bpl);
+			*(rp++) = cpu_to_le32(sg_dma_address(sg) + offset);
+			offset += bpl;
+		} else {
+			/*
+			 * scanline needs to be split.  Put the start in
+			 * whatever memory remains using RISC_LINESTART,
+			 * then the remainder into following addresses
+			 * given by the scatter-gather list.
+			 */
+			todo = bpl;	/* one full line to be done */
+			/* first fragment */
+			done = (sg_dma_len(sg) - offset);
+			*(rp++) = cpu_to_le32(RISC_LINESTART |
+						(7 << 24) |
+						done);
+			*(rp++) = cpu_to_le32(sg_dma_address(sg) + offset);
+			todo -= done;
+			sg = sg_next(sg);
+			/* succeeding fragments have no offset */
+			while (todo > sg_dma_len(sg)) {
+				*(rp++) = cpu_to_le32(RISC_INLINE |
+						(done << 12) |
+						sg_dma_len(sg));
+				*(rp++) = cpu_to_le32(sg_dma_address(sg));
+				todo -= sg_dma_len(sg);
+				sg = sg_next(sg);
+				done += sg_dma_len(sg);
+			}
+			if (todo) {
+				/* final chunk - offset 0, count 'todo' */
+				*(rp++) = cpu_to_le32(RISC_INLINE |
+							(done << 12) |
+							todo);
+				*(rp++) = cpu_to_le32(sg_dma_address(sg));
+			}
+			offset = todo;
+		}
+		offset += padding;
+	}
+
+	return rp;
+}
+
+/**
+ * tw68_risc_buffer
+ *
+ *	This routine is called by tw68-video.  It allocates
+ *	memory for the dma controller "program" and then fills in that
+ *	memory with the appropriate "instructions".
+ *
+ *	@pci_dev	structure with info about the pci
+ *			slot which our device is in.
+ *	@risc		structure with info about the memory
+ *			used for our controller program.
+ *	@sglist		scatter-gather list entry
+ *	@top_offset	offset within the risc program area for the
+ *			first odd frame line
+ *	@bottom_offset	offset within the risc program area for the
+ *			first even frame line
+ *	@bpl		number of data bytes per scan line
+ *	@padding	number of extra bytes to add at end of line
+ *	@lines		number of scan lines
+ */
+int tw68_risc_buffer(struct pci_dev *pci,
+			struct tw68_buf *buf,
+			struct scatterlist *sglist,
+			unsigned int top_offset,
+			unsigned int bottom_offset,
+			unsigned int bpl,
+			unsigned int padding,
+			unsigned int lines)
+{
+	u32 instructions, fields;
+	__le32 *rp;
+
+	fields = 0;
+	if (UNSET != top_offset)
+		fields++;
+	if (UNSET != bottom_offset)
+		fields++;
+	/*
+	 * estimate risc mem: worst case is one write per page border +
+	 * one write per scan line + syncs + 2 jumps (all 2 dwords).
+	 * Padding can cause next bpl to start close to a page border.
+	 * First DMA region may be smaller than PAGE_SIZE
+	 */
+	instructions  = fields * (1 + (((bpl + padding) * lines) /
+			 PAGE_SIZE) + lines) + 4;
+	buf->size = instructions * 8;
+	buf->cpu = pci_alloc_consistent(pci, buf->size, &buf->dma);
+	if (buf->cpu == NULL)
+		return -ENOMEM;
+
+	/* write risc instructions */
+	rp = buf->cpu;
+	if (UNSET != top_offset)	/* generates SYNCO */
+		rp = tw68_risc_field(rp, sglist, top_offset, 1,
+				     bpl, padding, lines, true);
+	if (UNSET != bottom_offset)	/* generates SYNCE */
+		rp = tw68_risc_field(rp, sglist, bottom_offset, 2,
+				     bpl, padding, lines, top_offset == UNSET);
+
+	/* save pointer to jmp instruction address */
+	buf->jmp = rp;
+	buf->cpu[1] = cpu_to_le32(buf->dma + 8);
+	/* assure risc buffer hasn't overflowed */
+	BUG_ON((buf->jmp - buf->cpu + 2) * sizeof(buf->cpu[0]) > buf->size);
+	return 0;
+}
+
+#if 0
+/* ------------------------------------------------------------------ */
+/* debug helper code                                                  */
+
+static void tw68_risc_decode(u32 risc, u32 addr)
+{
+#define	RISC_OP(reg)	(((reg) >> 28) & 7)
+	static struct instr_details {
+		char *name;
+		u8 has_data_type;
+		u8 has_byte_info;
+		u8 has_addr;
+	} instr[8] = {
+		[RISC_OP(RISC_SYNCO)]	  = {"syncOdd", 0, 0, 0},
+		[RISC_OP(RISC_SYNCE)]	  = {"syncEven", 0, 0, 0},
+		[RISC_OP(RISC_JUMP)]	  = {"jump", 0, 0, 1},
+		[RISC_OP(RISC_LINESTART)] = {"lineStart", 1, 1, 1},
+		[RISC_OP(RISC_INLINE)]	  = {"inline", 1, 1, 1},
+	};
+	u32 p;
+
+	p = RISC_OP(risc);
+	if (!(risc & 0x80000000) || !instr[p].name) {
+		pr_debug("0x%08x [ INVALID ]\n", risc);
+		return;
+	}
+	pr_debug("0x%08x %-9s IRQ=%d",
+		risc, instr[p].name, (risc >> 27) & 1);
+	if (instr[p].has_data_type)
+		pr_debug(" Type=%d", (risc >> 24) & 7);
+	if (instr[p].has_byte_info)
+		pr_debug(" Start=0x%03x Count=%03u",
+			(risc >> 12) & 0xfff, risc & 0xfff);
+	if (instr[p].has_addr)
+		pr_debug(" StartAddr=0x%08x", addr);
+	pr_debug("\n");
+}
+
+void tw68_risc_program_dump(struct tw68_core *core, struct tw68_buf *buf)
+{
+	const __le32 *addr;
+
+	pr_debug("%s: risc_program_dump: risc=%p, buf->cpu=0x%p, buf->jmp=0x%p\n",
+		  core->name, buf, buf->cpu, buf->jmp);
+	for (addr = buf->cpu; addr <= buf->jmp; addr += 2)
+		tw68_risc_decode(*addr, *(addr+1));
+}
+#endif
diff --git a/drivers/media/pci/tw68/tw68-video.c b/drivers/media/pci/tw68/tw68-video.c
new file mode 100644
index 000000000000..5c94ac7c88d9
--- /dev/null
+++ b/drivers/media/pci/tw68/tw68-video.c
@@ -0,0 +1,1051 @@
+/*
+ *  tw68 functions to handle video data
+ *
+ *  Much of this code is derived from the cx88 and sa7134 drivers, which
+ *  were in turn derived from the bt87x driver.  The original work was by
+ *  Gerd Knorr; more recently the code was enhanced by Mauro Carvalho Chehab,
+ *  Hans Verkuil, Andy Walls and many others.  Their work is gratefully
+ *  acknowledged.  Full credit goes to them - any problems within this code
+ *  are mine.
+ *
+ *  Copyright (C) 2009  William M. Brack
+ *
+ *  Refactored and updated to the latest v4l core frameworks:
+ *
+ *  Copyright (C) 2014 Hans Verkuil <hverkuil@xs4all.nl>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <media/v4l2-common.h>
+#include <media/v4l2-event.h>
+#include <media/videobuf2-dma-sg.h>
+
+#include "tw68.h"
+#include "tw68-reg.h"
+
+/* ------------------------------------------------------------------ */
+/* data structs for video                                             */
+/*
+ * FIXME -
+ * Note that the saa7134 has formats, e.g. YUV420, which are classified
+ * as "planar".  These affect overlay mode, and are flagged with a field
+ * ".planar" in the format.  Do we need to implement this in this driver?
+ */
+static const struct tw68_format formats[] = {
+	{
+		.name		= "15 bpp RGB, le",
+		.fourcc		= V4L2_PIX_FMT_RGB555,
+		.depth		= 16,
+		.twformat	= ColorFormatRGB15,
+	}, {
+		.name		= "15 bpp RGB, be",
+		.fourcc		= V4L2_PIX_FMT_RGB555X,
+		.depth		= 16,
+		.twformat	= ColorFormatRGB15 | ColorFormatBSWAP,
+	}, {
+		.name		= "16 bpp RGB, le",
+		.fourcc		= V4L2_PIX_FMT_RGB565,
+		.depth		= 16,
+		.twformat	= ColorFormatRGB16,
+	}, {
+		.name		= "16 bpp RGB, be",
+		.fourcc		= V4L2_PIX_FMT_RGB565X,
+		.depth		= 16,
+		.twformat	= ColorFormatRGB16 | ColorFormatBSWAP,
+	}, {
+		.name		= "24 bpp RGB, le",
+		.fourcc		= V4L2_PIX_FMT_BGR24,
+		.depth		= 24,
+		.twformat	= ColorFormatRGB24,
+	}, {
+		.name		= "24 bpp RGB, be",
+		.fourcc		= V4L2_PIX_FMT_RGB24,
+		.depth		= 24,
+		.twformat	= ColorFormatRGB24 | ColorFormatBSWAP,
+	}, {
+		.name		= "32 bpp RGB, le",
+		.fourcc		= V4L2_PIX_FMT_BGR32,
+		.depth		= 32,
+		.twformat	= ColorFormatRGB32,
+	}, {
+		.name		= "32 bpp RGB, be",
+		.fourcc		= V4L2_PIX_FMT_RGB32,
+		.depth		= 32,
+		.twformat	= ColorFormatRGB32 | ColorFormatBSWAP |
+				  ColorFormatWSWAP,
+	}, {
+		.name		= "4:2:2 packed, YUYV",
+		.fourcc		= V4L2_PIX_FMT_YUYV,
+		.depth		= 16,
+		.twformat	= ColorFormatYUY2,
+	}, {
+		.name		= "4:2:2 packed, UYVY",
+		.fourcc		= V4L2_PIX_FMT_UYVY,
+		.depth		= 16,
+		.twformat	= ColorFormatYUY2 | ColorFormatBSWAP,
+	}
+};
+#define FORMATS ARRAY_SIZE(formats)
+
+#define NORM_625_50			\
+		.h_delay	= 3,	\
+		.h_delay0	= 133,	\
+		.h_start	= 0,	\
+		.h_stop		= 719,	\
+		.v_delay	= 24,	\
+		.vbi_v_start_0	= 7,	\
+		.vbi_v_stop_0	= 22,	\
+		.video_v_start	= 24,	\
+		.video_v_stop	= 311,	\
+		.vbi_v_start_1	= 319
+
+#define NORM_525_60			\
+		.h_delay	= 8,	\
+		.h_delay0	= 138,	\
+		.h_start	= 0,	\
+		.h_stop		= 719,	\
+		.v_delay	= 22,	\
+		.vbi_v_start_0	= 10,	\
+		.vbi_v_stop_0	= 21,	\
+		.video_v_start	= 22,	\
+		.video_v_stop	= 262,	\
+		.vbi_v_start_1	= 273
+
+/*
+ * The following table is searched by tw68_s_std, first for a specific
+ * match, then for an entry which contains the desired id.  The table
+ * entries should therefore be ordered in ascending order of specificity.
+ */
+static const struct tw68_tvnorm tvnorms[] = {
+	{
+		.name		= "PAL", /* autodetect */
+		.id		= V4L2_STD_PAL,
+		NORM_625_50,
+
+		.sync_control	= 0x18,
+		.luma_control	= 0x40,
+		.chroma_ctrl1	= 0x81,
+		.chroma_gain	= 0x2a,
+		.chroma_ctrl2	= 0x06,
+		.vgate_misc	= 0x1c,
+		.format		= VideoFormatPALBDGHI,
+	}, {
+		.name		= "NTSC",
+		.id		= V4L2_STD_NTSC,
+		NORM_525_60,
+
+		.sync_control	= 0x59,
+		.luma_control	= 0x40,
+		.chroma_ctrl1	= 0x89,
+		.chroma_gain	= 0x2a,
+		.chroma_ctrl2	= 0x0e,
+		.vgate_misc	= 0x18,
+		.format		= VideoFormatNTSC,
+	}, {
+		.name		= "SECAM",
+		.id		= V4L2_STD_SECAM,
+		NORM_625_50,
+
+		.sync_control	= 0x18,
+		.luma_control	= 0x1b,
+		.chroma_ctrl1	= 0xd1,
+		.chroma_gain	= 0x80,
+		.chroma_ctrl2	= 0x00,
+		.vgate_misc	= 0x1c,
+		.format		= VideoFormatSECAM,
+	}, {
+		.name		= "PAL-M",
+		.id		= V4L2_STD_PAL_M,
+		NORM_525_60,
+
+		.sync_control	= 0x59,
+		.luma_control	= 0x40,
+		.chroma_ctrl1	= 0xb9,
+		.chroma_gain	= 0x2a,
+		.chroma_ctrl2	= 0x0e,
+		.vgate_misc	= 0x18,
+		.format		= VideoFormatPALM,
+	}, {
+		.name		= "PAL-Nc",
+		.id		= V4L2_STD_PAL_Nc,
+		NORM_625_50,
+
+		.sync_control	= 0x18,
+		.luma_control	= 0x40,
+		.chroma_ctrl1	= 0xa1,
+		.chroma_gain	= 0x2a,
+		.chroma_ctrl2	= 0x06,
+		.vgate_misc	= 0x1c,
+		.format		= VideoFormatPALNC,
+	}, {
+		.name		= "PAL-60",
+		.id		= V4L2_STD_PAL_60,
+		.h_delay	= 186,
+		.h_start	= 0,
+		.h_stop		= 719,
+		.v_delay	= 26,
+		.video_v_start	= 23,
+		.video_v_stop	= 262,
+		.vbi_v_start_0	= 10,
+		.vbi_v_stop_0	= 21,
+		.vbi_v_start_1	= 273,
+
+		.sync_control	= 0x18,
+		.luma_control	= 0x40,
+		.chroma_ctrl1	= 0x81,
+		.chroma_gain	= 0x2a,
+		.chroma_ctrl2	= 0x06,
+		.vgate_misc	= 0x1c,
+		.format		= VideoFormatPAL60,
+	}
+};
+#define TVNORMS ARRAY_SIZE(tvnorms)
+
+static const struct tw68_format *format_by_fourcc(unsigned int fourcc)
+{
+	unsigned int i;
+
+	for (i = 0; i < FORMATS; i++)
+		if (formats[i].fourcc == fourcc)
+			return formats+i;
+	return NULL;
+}
+
+
+/* ------------------------------------------------------------------ */
+/*
+ * Note that the cropping rectangles are described in terms of a single
+ * frame, i.e. line positions are only 1/2 the interlaced equivalent
+ */
+static void set_tvnorm(struct tw68_dev *dev, const struct tw68_tvnorm *norm)
+{
+	if (norm != dev->tvnorm) {
+		dev->width = 720;
+		dev->height = (norm->id & V4L2_STD_525_60) ? 480 : 576;
+		dev->tvnorm = norm;
+		tw68_set_tvnorm_hw(dev);
+	}
+}
+
+/*
+ * tw68_set_scale
+ *
+ * Scaling and Cropping for video decoding
+ *
+ * We are working with 3 values for horizontal and vertical - scale,
+ * delay and active.
+ *
+ * HACTIVE represent the actual number of pixels in the "usable" image,
+ * before scaling.  HDELAY represents the number of pixels skipped
+ * between the start of the horizontal sync and the start of the image.
+ * HSCALE is calculated using the formula
+ *	HSCALE = (HACTIVE / (#pixels desired)) * 256
+ *
+ * The vertical registers are similar, except based upon the total number
+ * of lines in the image, and the first line of the image (i.e. ignoring
+ * vertical sync and VBI).
+ *
+ * Note that the number of bytes reaching the FIFO (and hence needing
+ * to be processed by the DMAP program) is completely dependent upon
+ * these values, especially HSCALE.
+ *
+ * Parameters:
+ *	@dev		pointer to the device structure, needed for
+ *			getting current norm (as well as debug print)
+ *	@width		actual image width (from user buffer)
+ *	@height		actual image height
+ *	@field		indicates Top, Bottom or Interlaced
+ */
+static int tw68_set_scale(struct tw68_dev *dev, unsigned int width,
+			  unsigned int height, enum v4l2_field field)
+{
+	const struct tw68_tvnorm *norm = dev->tvnorm;
+	/* set individually for debugging clarity */
+	int hactive, hdelay, hscale;
+	int vactive, vdelay, vscale;
+	int comb;
+
+	if (V4L2_FIELD_HAS_BOTH(field))	/* if field is interlaced */
+		height /= 2;		/* we must set for 1-frame */
+
+	pr_debug("%s: width=%d, height=%d, both=%d\n"
+		 "  tvnorm h_delay=%d, h_start=%d, h_stop=%d, "
+		 "v_delay=%d, v_start=%d, v_stop=%d\n" , __func__,
+		width, height, V4L2_FIELD_HAS_BOTH(field),
+		norm->h_delay, norm->h_start, norm->h_stop,
+		norm->v_delay, norm->video_v_start,
+		norm->video_v_stop);
+
+	switch (dev->vdecoder) {
+	case TW6800:
+		hdelay = norm->h_delay0;
+		break;
+	default:
+		hdelay = norm->h_delay;
+		break;
+	}
+
+	hdelay += norm->h_start;
+	hactive = norm->h_stop - norm->h_start + 1;
+
+	hscale = (hactive * 256) / (width);
+
+	vdelay = norm->v_delay;
+	vactive = ((norm->id & V4L2_STD_525_60) ? 524 : 624) / 2 - norm->video_v_start;
+	vscale = (vactive * 256) / height;
+
+	pr_debug("%s: %dx%d [%s%s,%s]\n", __func__,
+		width, height,
+		V4L2_FIELD_HAS_TOP(field)    ? "T" : "",
+		V4L2_FIELD_HAS_BOTTOM(field) ? "B" : "",
+		v4l2_norm_to_name(dev->tvnorm->id));
+	pr_debug("%s: hactive=%d, hdelay=%d, hscale=%d; "
+		"vactive=%d, vdelay=%d, vscale=%d\n", __func__,
+		hactive, hdelay, hscale, vactive, vdelay, vscale);
+
+	comb =	((vdelay & 0x300)  >> 2) |
+		((vactive & 0x300) >> 4) |
+		((hdelay & 0x300)  >> 6) |
+		((hactive & 0x300) >> 8);
+	pr_debug("%s: setting CROP_HI=%02x, VDELAY_LO=%02x, "
+		"VACTIVE_LO=%02x, HDELAY_LO=%02x, HACTIVE_LO=%02x\n",
+		__func__, comb, vdelay, vactive, hdelay, hactive);
+	tw_writeb(TW68_CROP_HI, comb);
+	tw_writeb(TW68_VDELAY_LO, vdelay & 0xff);
+	tw_writeb(TW68_VACTIVE_LO, vactive & 0xff);
+	tw_writeb(TW68_HDELAY_LO, hdelay & 0xff);
+	tw_writeb(TW68_HACTIVE_LO, hactive & 0xff);
+
+	comb = ((vscale & 0xf00) >> 4) | ((hscale & 0xf00) >> 8);
+	pr_debug("%s: setting SCALE_HI=%02x, VSCALE_LO=%02x, "
+		"HSCALE_LO=%02x\n", __func__, comb, vscale, hscale);
+	tw_writeb(TW68_SCALE_HI, comb);
+	tw_writeb(TW68_VSCALE_LO, vscale);
+	tw_writeb(TW68_HSCALE_LO, hscale);
+
+	return 0;
+}
+
+/* ------------------------------------------------------------------ */
+
+int tw68_video_start_dma(struct tw68_dev *dev, struct tw68_buf *buf)
+{
+	/* Set cropping and scaling */
+	tw68_set_scale(dev, dev->width, dev->height, dev->field);
+	/*
+	 *  Set start address for RISC program.  Note that if the DMAP
+	 *  processor is currently running, it must be stopped before
+	 *  a new address can be set.
+	 */
+	tw_clearl(TW68_DMAC, TW68_DMAP_EN);
+	tw_writel(TW68_DMAP_SA, buf->dma);
+	/* Clear any pending interrupts */
+	tw_writel(TW68_INTSTAT, dev->board_virqmask);
+	/* Enable the risc engine and the fifo */
+	tw_andorl(TW68_DMAC, 0xff, dev->fmt->twformat |
+		ColorFormatGamma | TW68_DMAP_EN | TW68_FIFO_EN);
+	dev->pci_irqmask |= dev->board_virqmask;
+	tw_setl(TW68_INTMASK, dev->pci_irqmask);
+	return 0;
+}
+
+/* ------------------------------------------------------------------ */
+
+/* calc max # of buffers from size (must not exceed the 4MB virtual
+ * address space per DMA channel) */
+static int tw68_buffer_count(unsigned int size, unsigned int count)
+{
+	unsigned int maxcount;
+
+	maxcount = (4 * 1024 * 1024) / roundup(size, PAGE_SIZE);
+	if (count > maxcount)
+		count = maxcount;
+	return count;
+}
+
+/* ------------------------------------------------------------- */
+/* vb2 queue operations                                          */
+
+static int tw68_queue_setup(struct vb2_queue *q, const struct v4l2_format *fmt,
+			   unsigned int *num_buffers, unsigned int *num_planes,
+			   unsigned int sizes[], void *alloc_ctxs[])
+{
+	struct tw68_dev *dev = vb2_get_drv_priv(q);
+	unsigned tot_bufs = q->num_buffers + *num_buffers;
+
+	sizes[0] = (dev->fmt->depth * dev->width * dev->height) >> 3;
+	/*
+	 * We allow create_bufs, but only if the sizeimage is the same as the
+	 * current sizeimage. The tw68_buffer_count calculation becomes quite
+	 * difficult otherwise.
+	 */
+	if (fmt && fmt->fmt.pix.sizeimage < sizes[0])
+		return -EINVAL;
+	*num_planes = 1;
+	if (tot_bufs < 2)
+		tot_bufs = 2;
+	tot_bufs = tw68_buffer_count(sizes[0], tot_bufs);
+	*num_buffers = tot_bufs - q->num_buffers;
+
+	return 0;
+}
+
+/*
+ * The risc program for each buffers works as follows: it starts with a simple
+ * 'JUMP to addr + 8', which is effectively a NOP. Then the program to DMA the
+ * buffer follows and at the end we have a JUMP back to the start + 8 (skipping
+ * the initial JUMP).
+ *
+ * This is the program of the first buffer to be queued if the active list is
+ * empty and it just keeps DMAing this buffer without generating any interrupts.
+ *
+ * If a new buffer is added then the initial JUMP in the program generates an
+ * interrupt as well which signals that the previous buffer has been DMAed
+ * successfully and that it can be returned to userspace.
+ *
+ * It also sets the final jump of the previous buffer to the start of the new
+ * buffer, thus chaining the new buffer into the DMA chain. This is a single
+ * atomic u32 write, so there is no race condition.
+ *
+ * The end-result of all this that you only get an interrupt when a buffer
+ * is ready, so the control flow is very easy.
+ */
+static void tw68_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_queue *vq = vb->vb2_queue;
+	struct tw68_dev *dev = vb2_get_drv_priv(vq);
+	struct tw68_buf *buf = container_of(vb, struct tw68_buf, vb);
+	struct tw68_buf *prev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->slock, flags);
+
+	/* append a 'JUMP to start of buffer' to the buffer risc program */
+	buf->jmp[0] = cpu_to_le32(RISC_JUMP);
+	buf->jmp[1] = cpu_to_le32(buf->dma + 8);
+
+	if (!list_empty(&dev->active)) {
+		prev = list_entry(dev->active.prev, struct tw68_buf, list);
+		buf->cpu[0] |= cpu_to_le32(RISC_INT_BIT);
+		prev->jmp[1] = cpu_to_le32(buf->dma);
+	}
+	list_add_tail(&buf->list, &dev->active);
+	spin_unlock_irqrestore(&dev->slock, flags);
+}
+
+/*
+ * buffer_prepare
+ *
+ * Set the ancilliary information into the buffer structure.  This
+ * includes generating the necessary risc program if it hasn't already
+ * been done for the current buffer format.
+ * The structure fh contains the details of the format requested by the
+ * user - type, width, height and #fields.  This is compared with the
+ * last format set for the current buffer.  If they differ, the risc
+ * code (which controls the filling of the buffer) is (re-)generated.
+ */
+static int tw68_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vb2_queue *vq = vb->vb2_queue;
+	struct tw68_dev *dev = vb2_get_drv_priv(vq);
+	struct tw68_buf *buf = container_of(vb, struct tw68_buf, vb);
+	struct sg_table *dma = vb2_dma_sg_plane_desc(vb, 0);
+	unsigned size, bpl;
+	int rc;
+
+	size = (dev->width * dev->height * dev->fmt->depth) >> 3;
+	if (vb2_plane_size(vb, 0) < size)
+		return -EINVAL;
+	vb2_set_plane_payload(vb, 0, size);
+
+	rc = dma_map_sg(&dev->pci->dev, dma->sgl, dma->nents, DMA_FROM_DEVICE);
+	if (!rc)
+		return -EIO;
+
+	bpl = (dev->width * dev->fmt->depth) >> 3;
+	switch (dev->field) {
+	case V4L2_FIELD_TOP:
+		tw68_risc_buffer(dev->pci, buf, dma->sgl,
+				 0, UNSET, bpl, 0, dev->height);
+		break;
+	case V4L2_FIELD_BOTTOM:
+		tw68_risc_buffer(dev->pci, buf, dma->sgl,
+				 UNSET, 0, bpl, 0, dev->height);
+		break;
+	case V4L2_FIELD_SEQ_TB:
+		tw68_risc_buffer(dev->pci, buf, dma->sgl,
+				 0, bpl * (dev->height >> 1),
+				 bpl, 0, dev->height >> 1);
+		break;
+	case V4L2_FIELD_SEQ_BT:
+		tw68_risc_buffer(dev->pci, buf, dma->sgl,
+				 bpl * (dev->height >> 1), 0,
+				 bpl, 0, dev->height >> 1);
+		break;
+	case V4L2_FIELD_INTERLACED:
+	default:
+		tw68_risc_buffer(dev->pci, buf, dma->sgl,
+				 0, bpl, bpl, bpl, dev->height >> 1);
+		break;
+	}
+	return 0;
+}
+
+static void tw68_buf_finish(struct vb2_buffer *vb)
+{
+	struct vb2_queue *vq = vb->vb2_queue;
+	struct tw68_dev *dev = vb2_get_drv_priv(vq);
+	struct sg_table *dma = vb2_dma_sg_plane_desc(vb, 0);
+	struct tw68_buf *buf = container_of(vb, struct tw68_buf, vb);
+
+	dma_unmap_sg(&dev->pci->dev, dma->sgl, dma->nents, DMA_FROM_DEVICE);
+
+	pci_free_consistent(dev->pci, buf->size, buf->cpu, buf->dma);
+}
+
+static int tw68_start_streaming(struct vb2_queue *q, unsigned int count)
+{
+	struct tw68_dev *dev = vb2_get_drv_priv(q);
+	struct tw68_buf *buf =
+		container_of(dev->active.next, struct tw68_buf, list);
+
+	dev->seqnr = 0;
+	tw68_video_start_dma(dev, buf);
+	return 0;
+}
+
+static void tw68_stop_streaming(struct vb2_queue *q)
+{
+	struct tw68_dev *dev = vb2_get_drv_priv(q);
+
+	/* Stop risc & fifo */
+	tw_clearl(TW68_DMAC, TW68_DMAP_EN | TW68_FIFO_EN);
+	while (!list_empty(&dev->active)) {
+		struct tw68_buf *buf =
+			container_of(dev->active.next, struct tw68_buf, list);
+
+		list_del(&buf->list);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+	}
+}
+
+static struct vb2_ops tw68_video_qops = {
+	.queue_setup	= tw68_queue_setup,
+	.buf_queue	= tw68_buf_queue,
+	.buf_prepare	= tw68_buf_prepare,
+	.buf_finish	= tw68_buf_finish,
+	.start_streaming = tw68_start_streaming,
+	.stop_streaming = tw68_stop_streaming,
+	.wait_prepare	= vb2_ops_wait_prepare,
+	.wait_finish	= vb2_ops_wait_finish,
+};
+
+/* ------------------------------------------------------------------ */
+
+static int tw68_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct tw68_dev *dev =
+		container_of(ctrl->handler, struct tw68_dev, hdl);
+
+	switch (ctrl->id) {
+	case V4L2_CID_BRIGHTNESS:
+		tw_writeb(TW68_BRIGHT, ctrl->val);
+		break;
+	case V4L2_CID_HUE:
+		tw_writeb(TW68_HUE, ctrl->val);
+		break;
+	case V4L2_CID_CONTRAST:
+		tw_writeb(TW68_CONTRAST, ctrl->val);
+		break;
+	case V4L2_CID_SATURATION:
+		tw_writeb(TW68_SAT_U, ctrl->val);
+		tw_writeb(TW68_SAT_V, ctrl->val);
+		break;
+	case V4L2_CID_COLOR_KILLER:
+		if (ctrl->val)
+			tw_andorb(TW68_MISC2, 0xe0, 0xe0);
+		else
+			tw_andorb(TW68_MISC2, 0xe0, 0x00);
+		break;
+	case V4L2_CID_CHROMA_AGC:
+		if (ctrl->val)
+			tw_andorb(TW68_LOOP, 0x30, 0x20);
+		else
+			tw_andorb(TW68_LOOP, 0x30, 0x00);
+		break;
+	}
+	return 0;
+}
+
+/* ------------------------------------------------------------------ */
+
+/*
+ * Note that this routine returns what is stored in the fh structure, and
+ * does not interrogate any of the device registers.
+ */
+static int tw68_g_fmt_vid_cap(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+
+	f->fmt.pix.width        = dev->width;
+	f->fmt.pix.height       = dev->height;
+	f->fmt.pix.field        = dev->field;
+	f->fmt.pix.pixelformat  = dev->fmt->fourcc;
+	f->fmt.pix.bytesperline =
+		(f->fmt.pix.width * (dev->fmt->depth)) >> 3;
+	f->fmt.pix.sizeimage =
+		f->fmt.pix.height * f->fmt.pix.bytesperline;
+	f->fmt.pix.colorspace	= V4L2_COLORSPACE_SMPTE170M;
+	f->fmt.pix.priv = 0;
+	return 0;
+}
+
+static int tw68_try_fmt_vid_cap(struct file *file, void *priv,
+						struct v4l2_format *f)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+	const struct tw68_format *fmt;
+	enum v4l2_field field;
+	unsigned int maxh;
+
+	fmt = format_by_fourcc(f->fmt.pix.pixelformat);
+	if (NULL == fmt)
+		return -EINVAL;
+
+	field = f->fmt.pix.field;
+	maxh  = (dev->tvnorm->id & V4L2_STD_525_60) ? 480 : 576;
+
+	switch (field) {
+	case V4L2_FIELD_TOP:
+	case V4L2_FIELD_BOTTOM:
+		break;
+	case V4L2_FIELD_INTERLACED:
+	case V4L2_FIELD_SEQ_BT:
+	case V4L2_FIELD_SEQ_TB:
+		maxh = maxh * 2;
+		break;
+	default:
+		field = (f->fmt.pix.height > maxh / 2)
+			? V4L2_FIELD_INTERLACED
+			: V4L2_FIELD_BOTTOM;
+		break;
+	}
+
+	f->fmt.pix.field = field;
+	if (f->fmt.pix.width  < 48)
+		f->fmt.pix.width  = 48;
+	if (f->fmt.pix.height < 32)
+		f->fmt.pix.height = 32;
+	if (f->fmt.pix.width > 720)
+		f->fmt.pix.width = 720;
+	if (f->fmt.pix.height > maxh)
+		f->fmt.pix.height = maxh;
+	f->fmt.pix.width &= ~0x03;
+	f->fmt.pix.bytesperline =
+		(f->fmt.pix.width * (fmt->depth)) >> 3;
+	f->fmt.pix.sizeimage =
+		f->fmt.pix.height * f->fmt.pix.bytesperline;
+	f->fmt.pix.colorspace = V4L2_COLORSPACE_SMPTE170M;
+	return 0;
+}
+
+/*
+ * Note that tw68_s_fmt_vid_cap sets the information into the fh structure,
+ * and it will be used for all future new buffers.  However, there could be
+ * some number of buffers on the "active" chain which will be filled before
+ * the change takes place.
+ */
+static int tw68_s_fmt_vid_cap(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+	int err;
+
+	err = tw68_try_fmt_vid_cap(file, priv, f);
+	if (0 != err)
+		return err;
+
+	dev->fmt = format_by_fourcc(f->fmt.pix.pixelformat);
+	dev->width = f->fmt.pix.width;
+	dev->height = f->fmt.pix.height;
+	dev->field = f->fmt.pix.field;
+	return 0;
+}
+
+static int tw68_enum_input(struct file *file, void *priv,
+					struct v4l2_input *i)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+	unsigned int n;
+
+	n = i->index;
+	if (n >= TW68_INPUT_MAX)
+		return -EINVAL;
+	i->index = n;
+	i->type = V4L2_INPUT_TYPE_CAMERA;
+	snprintf(i->name, sizeof(i->name), "Composite %d", n);
+
+	/* If the query is for the current input, get live data */
+	if (n == dev->input) {
+		int v1 = tw_readb(TW68_STATUS1);
+		int v2 = tw_readb(TW68_MVSN);
+
+		if (0 != (v1 & (1 << 7)))
+			i->status |= V4L2_IN_ST_NO_SYNC;
+		if (0 != (v1 & (1 << 6)))
+			i->status |= V4L2_IN_ST_NO_H_LOCK;
+		if (0 != (v1 & (1 << 2)))
+			i->status |= V4L2_IN_ST_NO_SIGNAL;
+		if (0 != (v1 & 1 << 1))
+			i->status |= V4L2_IN_ST_NO_COLOR;
+		if (0 != (v2 & (1 << 2)))
+			i->status |= V4L2_IN_ST_MACROVISION;
+	}
+	i->std = video_devdata(file)->tvnorms;
+	return 0;
+}
+
+static int tw68_g_input(struct file *file, void *priv, unsigned int *i)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+
+	*i = dev->input;
+	return 0;
+}
+
+static int tw68_s_input(struct file *file, void *priv, unsigned int i)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+
+	if (i >= TW68_INPUT_MAX)
+		return -EINVAL;
+	dev->input = i;
+	tw_andorb(TW68_INFORM, 0x03 << 2, dev->input << 2);
+	return 0;
+}
+
+static int tw68_querycap(struct file *file, void  *priv,
+					struct v4l2_capability *cap)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+
+	strcpy(cap->driver, "tw68");
+	strlcpy(cap->card, "Techwell Capture Card",
+		sizeof(cap->card));
+	sprintf(cap->bus_info, "PCI:%s", pci_name(dev->pci));
+	cap->device_caps =
+		V4L2_CAP_VIDEO_CAPTURE |
+		V4L2_CAP_READWRITE |
+		V4L2_CAP_STREAMING;
+
+	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
+	return 0;
+}
+
+static int tw68_s_std(struct file *file, void *priv, v4l2_std_id id)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+	unsigned int i;
+
+	if (vb2_is_busy(&dev->vidq))
+		return -EBUSY;
+
+	/* Look for match on complete norm id (may have mult bits) */
+	for (i = 0; i < TVNORMS; i++) {
+		if (id == tvnorms[i].id)
+			break;
+	}
+
+	/* If no exact match, look for norm which contains this one */
+	if (i == TVNORMS) {
+		for (i = 0; i < TVNORMS; i++)
+			if (id & tvnorms[i].id)
+				break;
+	}
+	/* If still not matched, give up */
+	if (i == TVNORMS)
+		return -EINVAL;
+
+	set_tvnorm(dev, &tvnorms[i]);	/* do the actual setting */
+	return 0;
+}
+
+static int tw68_g_std(struct file *file, void *priv, v4l2_std_id *id)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+
+	*id = dev->tvnorm->id;
+	return 0;
+}
+
+static int tw68_enum_fmt_vid_cap(struct file *file, void  *priv,
+					struct v4l2_fmtdesc *f)
+{
+	if (f->index >= FORMATS)
+		return -EINVAL;
+
+	strlcpy(f->description, formats[f->index].name,
+		sizeof(f->description));
+
+	f->pixelformat = formats[f->index].fourcc;
+
+	return 0;
+}
+
+/*
+ * Used strictly for internal development and debugging, this routine
+ * prints out the current register contents for the tw68xx device.
+ */
+static void tw68_dump_regs(struct tw68_dev *dev)
+{
+	unsigned char line[80];
+	int i, j, k;
+	unsigned char *cptr;
+
+	pr_info("Full dump of TW68 registers:\n");
+	/* First we do the PCI regs, 8 4-byte regs per line */
+	for (i = 0; i < 0x100; i += 32) {
+		cptr = line;
+		cptr += sprintf(cptr, "%03x  ", i);
+		/* j steps through the next 4 words */
+		for (j = i; j < i + 16; j += 4)
+			cptr += sprintf(cptr, "%08x ", tw_readl(j));
+		*cptr++ = ' ';
+		for (; j < i + 32; j += 4)
+			cptr += sprintf(cptr, "%08x ", tw_readl(j));
+		*cptr++ = '\n';
+		*cptr = 0;
+		pr_info("%s", line);
+	}
+	/* Next the control regs, which are single-byte, address mod 4 */
+	while (i < 0x400) {
+		cptr = line;
+		cptr += sprintf(cptr, "%03x ", i);
+		/* Print out 4 groups of 4 bytes */
+		for (j = 0; j < 4; j++) {
+			for (k = 0; k < 4; k++) {
+				cptr += sprintf(cptr, "%02x ",
+					tw_readb(i));
+				i += 4;
+			}
+			*cptr++ = ' ';
+		}
+		*cptr++ = '\n';
+		*cptr = 0;
+		pr_info("%s", line);
+	}
+}
+
+static int vidioc_log_status(struct file *file, void *priv)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+
+	tw68_dump_regs(dev);
+	return v4l2_ctrl_log_status(file, priv);
+}
+
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+static int vidioc_g_register(struct file *file, void *priv,
+			      struct v4l2_dbg_register *reg)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+
+	if (reg->size == 1)
+		reg->val = tw_readb(reg->reg);
+	else
+		reg->val = tw_readl(reg->reg);
+	return 0;
+}
+
+static int vidioc_s_register(struct file *file, void *priv,
+				const struct v4l2_dbg_register *reg)
+{
+	struct tw68_dev *dev = video_drvdata(file);
+
+	if (reg->size == 1)
+		tw_writeb(reg->reg, reg->val);
+	else
+		tw_writel(reg->reg & 0xffff, reg->val);
+	return 0;
+}
+#endif
+
+static const struct v4l2_ctrl_ops tw68_ctrl_ops = {
+	.s_ctrl = tw68_s_ctrl,
+};
+
+static const struct v4l2_file_operations video_fops = {
+	.owner			= THIS_MODULE,
+	.open			= v4l2_fh_open,
+	.release		= vb2_fop_release,
+	.read			= vb2_fop_read,
+	.poll			= vb2_fop_poll,
+	.mmap			= vb2_fop_mmap,
+	.unlocked_ioctl		= video_ioctl2,
+};
+
+static const struct v4l2_ioctl_ops video_ioctl_ops = {
+	.vidioc_querycap		= tw68_querycap,
+	.vidioc_enum_fmt_vid_cap	= tw68_enum_fmt_vid_cap,
+	.vidioc_reqbufs			= vb2_ioctl_reqbufs,
+	.vidioc_create_bufs		= vb2_ioctl_create_bufs,
+	.vidioc_querybuf		= vb2_ioctl_querybuf,
+	.vidioc_qbuf			= vb2_ioctl_qbuf,
+	.vidioc_dqbuf			= vb2_ioctl_dqbuf,
+	.vidioc_s_std			= tw68_s_std,
+	.vidioc_g_std			= tw68_g_std,
+	.vidioc_enum_input		= tw68_enum_input,
+	.vidioc_g_input			= tw68_g_input,
+	.vidioc_s_input			= tw68_s_input,
+	.vidioc_streamon		= vb2_ioctl_streamon,
+	.vidioc_streamoff		= vb2_ioctl_streamoff,
+	.vidioc_g_fmt_vid_cap		= tw68_g_fmt_vid_cap,
+	.vidioc_try_fmt_vid_cap		= tw68_try_fmt_vid_cap,
+	.vidioc_s_fmt_vid_cap		= tw68_s_fmt_vid_cap,
+	.vidioc_log_status		= vidioc_log_status,
+	.vidioc_subscribe_event		= v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event	= v4l2_event_unsubscribe,
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+	.vidioc_g_register              = vidioc_g_register,
+	.vidioc_s_register              = vidioc_s_register,
+#endif
+};
+
+static struct video_device tw68_video_template = {
+	.name			= "tw68_video",
+	.fops			= &video_fops,
+	.ioctl_ops		= &video_ioctl_ops,
+	.release		= video_device_release_empty,
+	.tvnorms		= TW68_NORMS,
+};
+
+/* ------------------------------------------------------------------ */
+/* exported stuff                                                     */
+void tw68_set_tvnorm_hw(struct tw68_dev *dev)
+{
+	tw_andorb(TW68_SDT, 0x07, dev->tvnorm->format);
+}
+
+int tw68_video_init1(struct tw68_dev *dev)
+{
+	struct v4l2_ctrl_handler *hdl = &dev->hdl;
+
+	v4l2_ctrl_handler_init(hdl, 6);
+	v4l2_ctrl_new_std(hdl, &tw68_ctrl_ops,
+			V4L2_CID_BRIGHTNESS, -128, 127, 1, 20);
+	v4l2_ctrl_new_std(hdl, &tw68_ctrl_ops,
+			V4L2_CID_CONTRAST, 0, 255, 1, 100);
+	v4l2_ctrl_new_std(hdl, &tw68_ctrl_ops,
+			V4L2_CID_SATURATION, 0, 255, 1, 128);
+	/* NTSC only */
+	v4l2_ctrl_new_std(hdl, &tw68_ctrl_ops,
+			V4L2_CID_HUE, -128, 127, 1, 0);
+	v4l2_ctrl_new_std(hdl, &tw68_ctrl_ops,
+			V4L2_CID_COLOR_KILLER, 0, 1, 1, 0);
+	v4l2_ctrl_new_std(hdl, &tw68_ctrl_ops,
+			V4L2_CID_CHROMA_AGC, 0, 1, 1, 1);
+	if (hdl->error) {
+		v4l2_ctrl_handler_free(hdl);
+		return hdl->error;
+	}
+	dev->v4l2_dev.ctrl_handler = hdl;
+	v4l2_ctrl_handler_setup(hdl);
+	return 0;
+}
+
+int tw68_video_init2(struct tw68_dev *dev, int video_nr)
+{
+	int ret;
+
+	set_tvnorm(dev, &tvnorms[0]);
+
+	dev->fmt      = format_by_fourcc(V4L2_PIX_FMT_BGR24);
+	dev->width    = 720;
+	dev->height   = 576;
+	dev->field    = V4L2_FIELD_INTERLACED;
+
+	INIT_LIST_HEAD(&dev->active);
+	dev->vidq.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	dev->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	dev->vidq.io_modes = VB2_MMAP | VB2_USERPTR | VB2_READ | VB2_DMABUF;
+	dev->vidq.ops = &tw68_video_qops;
+	dev->vidq.mem_ops = &vb2_dma_sg_memops;
+	dev->vidq.drv_priv = dev;
+	dev->vidq.gfp_flags = __GFP_DMA32;
+	dev->vidq.buf_struct_size = sizeof(struct tw68_buf);
+	dev->vidq.lock = &dev->lock;
+	dev->vidq.min_buffers_needed = 2;
+	ret = vb2_queue_init(&dev->vidq);
+	if (ret)
+		return ret;
+	dev->vdev = tw68_video_template;
+	dev->vdev.v4l2_dev = &dev->v4l2_dev;
+	dev->vdev.lock = &dev->lock;
+	dev->vdev.queue = &dev->vidq;
+	video_set_drvdata(&dev->vdev, dev);
+	return video_register_device(&dev->vdev, VFL_TYPE_GRABBER, video_nr);
+}
+
+/*
+ * tw68_irq_video_done
+ */
+void tw68_irq_video_done(struct tw68_dev *dev, unsigned long status)
+{
+	__u32 reg;
+
+	/* reset interrupts handled by this routine */
+	tw_writel(TW68_INTSTAT, status);
+	/*
+	 * Check most likely first
+	 *
+	 * DMAPI shows we have reached the end of the risc code
+	 * for the current buffer.
+	 */
+	if (status & TW68_DMAPI) {
+		struct tw68_buf *buf;
+
+		spin_lock(&dev->slock);
+		buf = list_entry(dev->active.next, struct tw68_buf, list);
+		list_del(&buf->list);
+		spin_unlock(&dev->slock);
+		v4l2_get_timestamp(&buf->vb.v4l2_buf.timestamp);
+		buf->vb.v4l2_buf.field = dev->field;
+		buf->vb.v4l2_buf.sequence = dev->seqnr++;
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_DONE);
+		status &= ~(TW68_DMAPI);
+		if (0 == status)
+			return;
+	}
+	if (status & (TW68_VLOCK | TW68_HLOCK))
+		dev_dbg(&dev->pci->dev, "Lost sync\n");
+	if (status & TW68_PABORT)
+		dev_err(&dev->pci->dev, "PABORT interrupt\n");
+	if (status & TW68_DMAPERR)
+		dev_err(&dev->pci->dev, "DMAPERR interrupt\n");
+	/*
+	 * On TW6800, FDMIS is apparently generated if video input is switched
+	 * during operation.  Therefore, it is not enabled for that chip.
+	 */
+	if (status & TW68_FDMIS)
+		dev_dbg(&dev->pci->dev, "FDMIS interrupt\n");
+	if (status & TW68_FFOF) {
+		/* probably a logic error */
+		reg = tw_readl(TW68_DMAC) & TW68_FIFO_EN;
+		tw_clearl(TW68_DMAC, TW68_FIFO_EN);
+		dev_dbg(&dev->pci->dev, "FFOF interrupt\n");
+		tw_setl(TW68_DMAC, reg);
+	}
+	if (status & TW68_FFERR)
+		dev_dbg(&dev->pci->dev, "FFERR interrupt\n");
+}
diff --git a/drivers/media/pci/tw68/tw68.h b/drivers/media/pci/tw68/tw68.h
new file mode 100644
index 000000000000..2c8abe26b13b
--- /dev/null
+++ b/drivers/media/pci/tw68/tw68.h
@@ -0,0 +1,231 @@
+/*
+ *  tw68 driver common header file
+ *
+ *  Much of this code is derived from the cx88 and sa7134 drivers, which
+ *  were in turn derived from the bt87x driver.  The original work was by
+ *  Gerd Knorr; more recently the code was enhanced by Mauro Carvalho Chehab,
+ *  Hans Verkuil, Andy Walls and many others.  Their work is gratefully
+ *  acknowledged.  Full credit goes to them - any problems within this code
+ *  are mine.
+ *
+ *  Copyright (C) 2009  William M. Brack
+ *
+ *  Refactored and updated to the latest v4l core frameworks:
+ *
+ *  Copyright (C) 2014 Hans Verkuil <hverkuil@xs4all.nl>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ */
+
+#include <linux/version.h>
+#include <linux/pci.h>
+#include <linux/videodev2.h>
+#include <linux/notifier.h>
+#include <linux/delay.h>
+#include <linux/mutex.h>
+#include <linux/io.h>
+
+#include <media/v4l2-common.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/videobuf2-dma-sg.h>
+
+#include "tw68-reg.h"
+
+#define	UNSET	(-1U)
+
+/* system vendor and device ID's */
+#define	PCI_VENDOR_ID_TECHWELL	0x1797
+#define	PCI_DEVICE_ID_6800	0x6800
+#define	PCI_DEVICE_ID_6801	0x6801
+#define	PCI_DEVICE_ID_AUDIO2	0x6802
+#define	PCI_DEVICE_ID_TS3	0x6803
+#define	PCI_DEVICE_ID_6804	0x6804
+#define	PCI_DEVICE_ID_AUDIO5	0x6805
+#define	PCI_DEVICE_ID_TS6	0x6806
+
+/* tw6816 based cards */
+#define	PCI_DEVICE_ID_6816_1   0x6810
+#define	PCI_DEVICE_ID_6816_2   0x6811
+#define	PCI_DEVICE_ID_6816_3   0x6812
+#define	PCI_DEVICE_ID_6816_4   0x6813
+
+#define TW68_NORMS ( \
+	V4L2_STD_NTSC    | V4L2_STD_PAL       | V4L2_STD_SECAM    | \
+	V4L2_STD_PAL_M   | V4L2_STD_PAL_Nc    | V4L2_STD_PAL_60)
+
+#define	TW68_VID_INTS	(TW68_FFERR | TW68_PABORT | TW68_DMAPERR | \
+			 TW68_FFOF   | TW68_DMAPI)
+/* TW6800 chips have trouble with these, so we don't set them for that chip */
+#define	TW68_VID_INTSX	(TW68_FDMIS | TW68_HLOCK | TW68_VLOCK)
+
+#define	TW68_I2C_INTS	(TW68_SBERR | TW68_SBDONE | TW68_SBERR2  | \
+			 TW68_SBDONE2)
+
+enum tw68_decoder_type {
+	TW6800,
+	TW6801,
+	TW6804,
+	TWXXXX,
+};
+
+/* ----------------------------------------------------------- */
+/* static data                                                 */
+
+struct tw68_tvnorm {
+	char		*name;
+	v4l2_std_id	id;
+
+	/* video decoder */
+	u32	sync_control;
+	u32	luma_control;
+	u32	chroma_ctrl1;
+	u32	chroma_gain;
+	u32	chroma_ctrl2;
+	u32	vgate_misc;
+
+	/* video scaler */
+	u32	h_delay;
+	u32	h_delay0;	/* for TW6800 */
+	u32	h_start;
+	u32	h_stop;
+	u32	v_delay;
+	u32	video_v_start;
+	u32	video_v_stop;
+	u32	vbi_v_start_0;
+	u32	vbi_v_stop_0;
+	u32	vbi_v_start_1;
+
+	/* Techwell specific */
+	u32	format;
+};
+
+struct tw68_format {
+	char	*name;
+	u32	fourcc;
+	u32	depth;
+	u32	twformat;
+};
+
+/* ----------------------------------------------------------- */
+/* card configuration					  */
+
+#define TW68_BOARD_NOAUTO		UNSET
+#define TW68_BOARD_UNKNOWN		0
+#define	TW68_BOARD_GENERIC_6802		1
+
+#define	TW68_MAXBOARDS			16
+#define	TW68_INPUT_MAX			4
+
+/* ----------------------------------------------------------- */
+/* device / file handle status                                 */
+
+#define	BUFFER_TIMEOUT	msecs_to_jiffies(500)	/* 0.5 seconds */
+
+struct tw68_dev;	/* forward delclaration */
+
+/* buffer for one video/vbi/ts frame */
+struct tw68_buf {
+	struct vb2_buffer vb;
+	struct list_head list;
+
+	unsigned int   size;
+	__le32         *cpu;
+	__le32         *jmp;
+	dma_addr_t     dma;
+};
+
+struct tw68_fmt {
+	char			*name;
+	u32			fourcc;	/* v4l2 format id */
+	int			depth;
+	int			flags;
+	u32			twformat;
+};
+
+/* global device status */
+struct tw68_dev {
+	struct mutex		lock;
+	spinlock_t		slock;
+	u16			instance;
+	struct v4l2_device	v4l2_dev;
+
+	/* various device info */
+	enum tw68_decoder_type	vdecoder;
+	struct video_device	vdev;
+	struct v4l2_ctrl_handler hdl;
+
+	/* pci i/o */
+	char			*name;
+	struct pci_dev		*pci;
+	unsigned char		pci_rev, pci_lat;
+	u32			__iomem *lmmio;
+	u8			__iomem *bmmio;
+	u32			pci_irqmask;
+	/* The irq mask to be used will depend upon the chip type */
+	u32			board_virqmask;
+
+	/* video capture */
+	const struct tw68_format *fmt;
+	unsigned		width, height;
+	unsigned		seqnr;
+	unsigned		field;
+	struct vb2_queue	vidq;
+	struct list_head	active;
+
+	/* various v4l controls */
+	const struct tw68_tvnorm *tvnorm;	/* video */
+
+	int			input;
+};
+
+/* ----------------------------------------------------------- */
+
+#define tw_readl(reg)		readl(dev->lmmio + ((reg) >> 2))
+#define	tw_readb(reg)		readb(dev->bmmio + (reg))
+#define tw_writel(reg, value)	writel((value), dev->lmmio + ((reg) >> 2))
+#define	tw_writeb(reg, value)	writeb((value), dev->bmmio + (reg))
+
+#define tw_andorl(reg, mask, value) \
+		writel((readl(dev->lmmio+((reg)>>2)) & ~(mask)) |\
+		((value) & (mask)), dev->lmmio+((reg)>>2))
+#define	tw_andorb(reg, mask, value) \
+		writeb((readb(dev->bmmio + (reg)) & ~(mask)) |\
+		((value) & (mask)), dev->bmmio+(reg))
+#define tw_setl(reg, bit)	tw_andorl((reg), (bit), (bit))
+#define	tw_setb(reg, bit)	tw_andorb((reg), (bit), (bit))
+#define	tw_clearl(reg, bit)	\
+		writel((readl(dev->lmmio + ((reg) >> 2)) & ~(bit)), \
+		dev->lmmio + ((reg) >> 2))
+#define	tw_clearb(reg, bit)	\
+		writeb((readb(dev->bmmio+(reg)) & ~(bit)), \
+		dev->bmmio + (reg))
+
+#define tw_wait(us) { udelay(us); }
+
+/* ----------------------------------------------------------- */
+/* tw68-video.c                                                */
+
+void tw68_set_tvnorm_hw(struct tw68_dev *dev);
+
+int tw68_video_init1(struct tw68_dev *dev);
+int tw68_video_init2(struct tw68_dev *dev, int video_nr);
+void tw68_irq_video_done(struct tw68_dev *dev, unsigned long status);
+int tw68_video_start_dma(struct tw68_dev *dev, struct tw68_buf *buf);
+
+/* ----------------------------------------------------------- */
+/* tw68-risc.c                                                 */
+
+int tw68_risc_buffer(struct pci_dev *pci, struct tw68_buf *buf,
+	struct scatterlist *sglist, unsigned int top_offset,
+	unsigned int bottom_offset, unsigned int bpl,
+	unsigned int padding, unsigned int lines);
diff --git a/drivers/media/pci/zoran/zoran_device.c b/drivers/media/pci/zoran/zoran_device.c
index bf34b93f23ee..b6801e035ea4 100644
--- a/drivers/media/pci/zoran/zoran_device.c
+++ b/drivers/media/pci/zoran/zoran_device.c
@@ -682,7 +682,7 @@ set_videobus_dir (struct zoran *zr,
 	switch (zr->card.type) {
 	case LML33:
 	case LML33R10:
-		if (lml33dpath == 0)
+		if (!lml33dpath)
 			GPIO(zr, 5, val);
 		else
 			GPIO(zr, 5, 1);
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 6d86646d9743..bee9074ebc13 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -56,7 +56,8 @@ config VIDEO_VIU
 
 config VIDEO_TIMBERDALE
 	tristate "Support for timberdale Video In/LogiWIN"
-	depends on MFD_TIMBERDALE && VIDEO_V4L2 && I2C && DMADEVICES
+	depends on VIDEO_V4L2 && I2C && DMADEVICES
+	depends on MFD_TIMBERDALE || COMPILE_TEST
 	select DMA_ENGINE
 	select TIMB_DMA
 	select VIDEO_ADV7180
@@ -74,7 +75,8 @@ config VIDEO_VINO
 
 config VIDEO_M32R_AR
 	tristate "AR devices"
-	depends on M32R && VIDEO_V4L2
+	depends on VIDEO_V4L2
+	depends on M32R || COMPILE_TEST
 	---help---
 	  This is a video4linux driver for the Renesas AR (Artificial Retina)
 	  camera module.
@@ -94,6 +96,7 @@ config VIDEO_M32R_AR_M64278
 config VIDEO_OMAP3
 	tristate "OMAP 3 Camera support"
 	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API && ARCH_OMAP3
+	depends on HAS_DMA
 	select ARM_DMA_USE_IOMMU
 	select OMAP_IOMMU
 	select VIDEOBUF2_DMA_CONTIG
@@ -109,7 +112,9 @@ config VIDEO_OMAP3_DEBUG
 config VIDEO_S3C_CAMIF
 	tristate "Samsung S3C24XX/S3C64XX SoC Camera Interface driver"
 	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API
-	depends on (ARCH_S3C64XX || PLAT_S3C24XX) && PM_RUNTIME
+	depends on PM_RUNTIME
+	depends on ARCH_S3C64XX || PLAT_S3C24XX || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	---help---
 	  This is a v4l2 driver for s3c24xx and s3c64xx SoC series camera
@@ -140,6 +145,7 @@ if V4L_MEM2MEM_DRIVERS
 config VIDEO_CODA
 	tristate "Chips&Media Coda multi-standard codec IP"
 	depends on VIDEO_DEV && VIDEO_V4L2 && ARCH_MXC
+	depends on HAS_DMA
 	select SRAM
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
@@ -151,6 +157,7 @@ config VIDEO_CODA
 config VIDEO_MEM2MEM_DEINTERLACE
 	tristate "Deinterlace support"
 	depends on VIDEO_DEV && VIDEO_V4L2 && DMA_ENGINE
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
 	help
@@ -158,7 +165,9 @@ config VIDEO_MEM2MEM_DEINTERLACE
 
 config VIDEO_SAMSUNG_S5P_G2D
 	tristate "Samsung S5P and EXYNOS4 G2D 2d graphics accelerator driver"
-	depends on VIDEO_DEV && VIDEO_V4L2 && (PLAT_S5P || ARCH_EXYNOS)
+	depends on VIDEO_DEV && VIDEO_V4L2
+	depends on PLAT_S5P || ARCH_EXYNOS || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
 	default n
@@ -168,7 +177,9 @@ config VIDEO_SAMSUNG_S5P_G2D
 
 config VIDEO_SAMSUNG_S5P_JPEG
 	tristate "Samsung S5P/Exynos3250/Exynos4 JPEG codec driver"
-	depends on VIDEO_DEV && VIDEO_V4L2 && (PLAT_S5P || ARCH_EXYNOS)
+	depends on VIDEO_DEV && VIDEO_V4L2
+	depends on PLAT_S5P || ARCH_EXYNOS || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
 	---help---
@@ -177,7 +188,9 @@ config VIDEO_SAMSUNG_S5P_JPEG
 
 config VIDEO_SAMSUNG_S5P_MFC
 	tristate "Samsung S5P MFC Video Codec"
-	depends on VIDEO_DEV && VIDEO_V4L2 && (PLAT_S5P || ARCH_EXYNOS)
+	depends on VIDEO_DEV && VIDEO_V4L2
+	depends on PLAT_S5P || ARCH_EXYNOS || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	default n
 	help
@@ -185,7 +198,9 @@ config VIDEO_SAMSUNG_S5P_MFC
 
 config VIDEO_MX2_EMMAPRP
 	tristate "MX2 eMMa-PrP support"
-	depends on VIDEO_DEV && VIDEO_V4L2 && SOC_IMX27
+	depends on VIDEO_DEV && VIDEO_V4L2
+	depends on SOC_IMX27 || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
 	help
@@ -195,7 +210,9 @@ config VIDEO_MX2_EMMAPRP
 
 config VIDEO_SAMSUNG_EXYNOS_GSC
 	tristate "Samsung Exynos G-Scaler driver"
-	depends on VIDEO_DEV && VIDEO_V4L2 && ARCH_EXYNOS5
+	depends on VIDEO_DEV && VIDEO_V4L2
+	depends on ARCH_EXYNOS5 || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
 	help
@@ -204,6 +221,7 @@ config VIDEO_SAMSUNG_EXYNOS_GSC
 config VIDEO_SH_VEU
 	tristate "SuperH VEU mem2mem video processing driver"
 	depends on VIDEO_DEV && VIDEO_V4L2 && HAS_DMA
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
 	help
@@ -213,6 +231,7 @@ config VIDEO_SH_VEU
 config VIDEO_RENESAS_VSP1
 	tristate "Renesas VSP1 Video Processing Engine"
 	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && HAS_DMA
+	depends on ARCH_SHMOBILE || COMPILE_TEST
 	select VIDEOBUF2_DMA_CONTIG
 	---help---
 	  This is a V4L2 driver for the Renesas VSP1 video processing engine.
@@ -222,7 +241,9 @@ config VIDEO_RENESAS_VSP1
 
 config VIDEO_TI_VPE
 	tristate "TI VPE (Video Processing Engine) driver"
-	depends on VIDEO_DEV && VIDEO_V4L2 && SOC_DRA7XX
+	depends on VIDEO_DEV && VIDEO_V4L2
+	depends on SOC_DRA7XX || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
 	default n
@@ -243,19 +264,8 @@ menuconfig V4L_TEST_DRIVERS
 	depends on MEDIA_CAMERA_SUPPORT
 
 if V4L_TEST_DRIVERS
-config VIDEO_VIVI
-	tristate "Virtual Video Driver"
-	depends on VIDEO_DEV && VIDEO_V4L2 && !SPARC32 && !SPARC64
-	select FONT_SUPPORT
-	select FONT_8x16
-	select VIDEOBUF2_VMALLOC
-	default n
-	---help---
-	  Enables a virtual video driver. This device shows a color bar
-	  and a timestamp, as a real device would generate by using V4L2
-	  api.
-	  Say Y here if you want to test video apps or debug V4L devices.
-	  In doubt, say N.
+
+source "drivers/media/platform/vivid/Kconfig"
 
 config VIDEO_MEM2MEM_TESTDEV
 	tristate "Virtual test device for mem2mem framework"
diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile
index e5269da91906..579046bc276f 100644
--- a/drivers/media/platform/Makefile
+++ b/drivers/media/platform/Makefile
@@ -15,14 +15,14 @@ obj-$(CONFIG_VIDEO_MMP_CAMERA) += marvell-ccic/
 obj-$(CONFIG_VIDEO_OMAP3)	+= omap3isp/
 
 obj-$(CONFIG_VIDEO_VIU) += fsl-viu.o
-obj-$(CONFIG_VIDEO_VIVI) += vivi.o
 
+obj-$(CONFIG_VIDEO_VIVID)		+= vivid/
 obj-$(CONFIG_VIDEO_MEM2MEM_TESTDEV) += mem2mem_testdev.o
 
 obj-$(CONFIG_VIDEO_TI_VPE)		+= ti-vpe/
 
 obj-$(CONFIG_VIDEO_MX2_EMMAPRP)		+= mx2_emmaprp.o
-obj-$(CONFIG_VIDEO_CODA) 		+= coda.o
+obj-$(CONFIG_VIDEO_CODA) 		+= coda/
 
 obj-$(CONFIG_VIDEO_SH_VEU)		+= sh_veu.o
 
@@ -47,8 +47,6 @@ obj-$(CONFIG_SOC_CAMERA)		+= soc_camera/
 
 obj-$(CONFIG_VIDEO_RENESAS_VSP1)	+= vsp1/
 
-obj-y	+= davinci/
-
-obj-$(CONFIG_ARCH_OMAP)	+= omap/
+obj-y	+= omap/
 
 ccflags-y += -I$(srctree)/drivers/media/i2c
diff --git a/drivers/media/platform/blackfin/Kconfig b/drivers/media/platform/blackfin/Kconfig
index cc239972fa2c..68fa90151b8f 100644
--- a/drivers/media/platform/blackfin/Kconfig
+++ b/drivers/media/platform/blackfin/Kconfig
@@ -1,6 +1,7 @@
 config VIDEO_BLACKFIN_CAPTURE
 	tristate "Blackfin Video Capture Driver"
 	depends on VIDEO_V4L2 && BLACKFIN && I2C
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	help
 	  V4L2 bridge driver for Blackfin video capture device.
diff --git a/drivers/media/platform/coda.c b/drivers/media/platform/coda.c
deleted file mode 100644
index 3a6d1d2b429e..000000000000
--- a/drivers/media/platform/coda.c
+++ /dev/null
@@ -1,3933 +0,0 @@
-/*
- * Coda multi-standard codec IP
- *
- * Copyright (C) 2012 Vista Silicon S.L.
- *    Javier Martin, <javier.martin@vista-silicon.com>
- *    Xavier Duret
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <linux/clk.h>
-#include <linux/debugfs.h>
-#include <linux/delay.h>
-#include <linux/firmware.h>
-#include <linux/genalloc.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/kfifo.h>
-#include <linux/module.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
-#include <linux/pm_runtime.h>
-#include <linux/slab.h>
-#include <linux/videodev2.h>
-#include <linux/of.h>
-#include <linux/platform_data/coda.h>
-#include <linux/reset.h>
-
-#include <media/v4l2-ctrls.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-event.h>
-#include <media/v4l2-ioctl.h>
-#include <media/v4l2-mem2mem.h>
-#include <media/videobuf2-core.h>
-#include <media/videobuf2-dma-contig.h>
-
-#include "coda.h"
-
-#define CODA_NAME		"coda"
-
-#define CODADX6_MAX_INSTANCES	4
-
-#define CODA_PARA_BUF_SIZE	(10 * 1024)
-#define CODA_ISRAM_SIZE	(2048 * 2)
-
-#define CODA7_PS_BUF_SIZE	0x28000
-#define CODA9_PS_SAVE_SIZE	(512 * 1024)
-
-#define CODA_MAX_FRAMEBUFFERS	8
-
-#define CODA_MAX_FRAME_SIZE	0x100000
-#define FMO_SLICE_SAVE_BUF_SIZE         (32)
-#define CODA_DEFAULT_GAMMA		4096
-#define CODA9_DEFAULT_GAMMA		24576	/* 0.75 * 32768 */
-
-#define MIN_W 176
-#define MIN_H 144
-
-#define S_ALIGN		1 /* multiple of 2 */
-#define W_ALIGN		1 /* multiple of 2 */
-#define H_ALIGN		1 /* multiple of 2 */
-
-#define fh_to_ctx(__fh)	container_of(__fh, struct coda_ctx, fh)
-
-static int coda_debug;
-module_param(coda_debug, int, 0644);
-MODULE_PARM_DESC(coda_debug, "Debug level (0-1)");
-
-enum {
-	V4L2_M2M_SRC = 0,
-	V4L2_M2M_DST = 1,
-};
-
-enum coda_inst_type {
-	CODA_INST_ENCODER,
-	CODA_INST_DECODER,
-};
-
-enum coda_product {
-	CODA_DX6 = 0xf001,
-	CODA_7541 = 0xf012,
-	CODA_960 = 0xf020,
-};
-
-struct coda_fmt {
-	char *name;
-	u32 fourcc;
-};
-
-struct coda_codec {
-	u32 mode;
-	u32 src_fourcc;
-	u32 dst_fourcc;
-	u32 max_w;
-	u32 max_h;
-};
-
-struct coda_devtype {
-	char			*firmware;
-	enum coda_product	product;
-	struct coda_codec	*codecs;
-	unsigned int		num_codecs;
-	size_t			workbuf_size;
-	size_t			tempbuf_size;
-	size_t			iram_size;
-};
-
-/* Per-queue, driver-specific private data */
-struct coda_q_data {
-	unsigned int		width;
-	unsigned int		height;
-	unsigned int		bytesperline;
-	unsigned int		sizeimage;
-	unsigned int		fourcc;
-	struct v4l2_rect	rect;
-};
-
-struct coda_aux_buf {
-	void			*vaddr;
-	dma_addr_t		paddr;
-	u32			size;
-	struct debugfs_blob_wrapper blob;
-	struct dentry		*dentry;
-};
-
-struct coda_dev {
-	struct v4l2_device	v4l2_dev;
-	struct video_device	vfd;
-	struct platform_device	*plat_dev;
-	const struct coda_devtype *devtype;
-
-	void __iomem		*regs_base;
-	struct clk		*clk_per;
-	struct clk		*clk_ahb;
-	struct reset_control	*rstc;
-
-	struct coda_aux_buf	codebuf;
-	struct coda_aux_buf	tempbuf;
-	struct coda_aux_buf	workbuf;
-	struct gen_pool		*iram_pool;
-	struct coda_aux_buf	iram;
-
-	spinlock_t		irqlock;
-	struct mutex		dev_mutex;
-	struct mutex		coda_mutex;
-	struct workqueue_struct	*workqueue;
-	struct v4l2_m2m_dev	*m2m_dev;
-	struct vb2_alloc_ctx	*alloc_ctx;
-	struct list_head	instances;
-	unsigned long		instance_mask;
-	struct dentry		*debugfs_root;
-};
-
-struct coda_params {
-	u8			rot_mode;
-	u8			h264_intra_qp;
-	u8			h264_inter_qp;
-	u8			h264_min_qp;
-	u8			h264_max_qp;
-	u8			h264_deblk_enabled;
-	u8			h264_deblk_alpha;
-	u8			h264_deblk_beta;
-	u8			mpeg4_intra_qp;
-	u8			mpeg4_inter_qp;
-	u8			gop_size;
-	int			intra_refresh;
-	int			codec_mode;
-	int			codec_mode_aux;
-	enum v4l2_mpeg_video_multi_slice_mode slice_mode;
-	u32			framerate;
-	u16			bitrate;
-	u32			slice_max_bits;
-	u32			slice_max_mb;
-};
-
-struct coda_iram_info {
-	u32		axi_sram_use;
-	phys_addr_t	buf_bit_use;
-	phys_addr_t	buf_ip_ac_dc_use;
-	phys_addr_t	buf_dbk_y_use;
-	phys_addr_t	buf_dbk_c_use;
-	phys_addr_t	buf_ovl_use;
-	phys_addr_t	buf_btp_use;
-	phys_addr_t	search_ram_paddr;
-	int		search_ram_size;
-	int		remaining;
-	phys_addr_t	next_paddr;
-};
-
-struct gdi_tiled_map {
-	int xy2ca_map[16];
-	int xy2ba_map[16];
-	int xy2ra_map[16];
-	int rbc2axi_map[32];
-	int xy2rbc_config;
-	int map_type;
-#define GDI_LINEAR_FRAME_MAP 0
-};
-
-struct coda_timestamp {
-	struct list_head	list;
-	u32			sequence;
-	struct v4l2_timecode	timecode;
-	struct timeval		timestamp;
-};
-
-struct coda_ctx {
-	struct coda_dev			*dev;
-	struct mutex			buffer_mutex;
-	struct list_head		list;
-	struct work_struct		pic_run_work;
-	struct work_struct		seq_end_work;
-	struct completion		completion;
-	int				aborting;
-	int				initialized;
-	int				streamon_out;
-	int				streamon_cap;
-	u32				isequence;
-	u32				qsequence;
-	u32				osequence;
-	u32				sequence_offset;
-	struct coda_q_data		q_data[2];
-	enum coda_inst_type		inst_type;
-	struct coda_codec		*codec;
-	enum v4l2_colorspace		colorspace;
-	struct coda_params		params;
-	struct v4l2_ctrl_handler	ctrls;
-	struct v4l2_fh			fh;
-	int				gopcounter;
-	int				runcounter;
-	char				vpu_header[3][64];
-	int				vpu_header_size[3];
-	struct kfifo			bitstream_fifo;
-	struct mutex			bitstream_mutex;
-	struct coda_aux_buf		bitstream;
-	bool				hold;
-	struct coda_aux_buf		parabuf;
-	struct coda_aux_buf		psbuf;
-	struct coda_aux_buf		slicebuf;
-	struct coda_aux_buf		internal_frames[CODA_MAX_FRAMEBUFFERS];
-	u32				frame_types[CODA_MAX_FRAMEBUFFERS];
-	struct coda_timestamp		frame_timestamps[CODA_MAX_FRAMEBUFFERS];
-	u32				frame_errors[CODA_MAX_FRAMEBUFFERS];
-	struct list_head		timestamp_list;
-	struct coda_aux_buf		workbuf;
-	int				num_internal_frames;
-	int				idx;
-	int				reg_idx;
-	struct coda_iram_info		iram_info;
-	struct gdi_tiled_map		tiled_map;
-	u32				bit_stream_param;
-	u32				frm_dis_flg;
-	u32				frame_mem_ctrl;
-	int				display_idx;
-	struct dentry			*debugfs_entry;
-};
-
-static const u8 coda_filler_nal[14] = { 0x00, 0x00, 0x00, 0x01, 0x0c, 0xff,
-			0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x80 };
-static const u8 coda_filler_size[8] = { 0, 7, 14, 13, 12, 11, 10, 9 };
-
-static inline void coda_write(struct coda_dev *dev, u32 data, u32 reg)
-{
-	v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
-		 "%s: data=0x%x, reg=0x%x\n", __func__, data, reg);
-	writel(data, dev->regs_base + reg);
-}
-
-static inline unsigned int coda_read(struct coda_dev *dev, u32 reg)
-{
-	u32 data;
-	data = readl(dev->regs_base + reg);
-	v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
-		 "%s: data=0x%x, reg=0x%x\n", __func__, data, reg);
-	return data;
-}
-
-static inline unsigned long coda_isbusy(struct coda_dev *dev)
-{
-	return coda_read(dev, CODA_REG_BIT_BUSY);
-}
-
-static inline int coda_is_initialized(struct coda_dev *dev)
-{
-	return (coda_read(dev, CODA_REG_BIT_CUR_PC) != 0);
-}
-
-static int coda_wait_timeout(struct coda_dev *dev)
-{
-	unsigned long timeout = jiffies + msecs_to_jiffies(1000);
-
-	while (coda_isbusy(dev)) {
-		if (time_after(jiffies, timeout))
-			return -ETIMEDOUT;
-	}
-	return 0;
-}
-
-static void coda_command_async(struct coda_ctx *ctx, int cmd)
-{
-	struct coda_dev *dev = ctx->dev;
-
-	if (dev->devtype->product == CODA_960 ||
-	    dev->devtype->product == CODA_7541) {
-		/* Restore context related registers to CODA */
-		coda_write(dev, ctx->bit_stream_param,
-				CODA_REG_BIT_BIT_STREAM_PARAM);
-		coda_write(dev, ctx->frm_dis_flg,
-				CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));
-		coda_write(dev, ctx->frame_mem_ctrl,
-				CODA_REG_BIT_FRAME_MEM_CTRL);
-		coda_write(dev, ctx->workbuf.paddr, CODA_REG_BIT_WORK_BUF_ADDR);
-	}
-
-	if (dev->devtype->product == CODA_960) {
-		coda_write(dev, 1, CODA9_GDI_WPROT_ERR_CLR);
-		coda_write(dev, 0, CODA9_GDI_WPROT_RGN_EN);
-	}
-
-	coda_write(dev, CODA_REG_BIT_BUSY_FLAG, CODA_REG_BIT_BUSY);
-
-	coda_write(dev, ctx->idx, CODA_REG_BIT_RUN_INDEX);
-	coda_write(dev, ctx->params.codec_mode, CODA_REG_BIT_RUN_COD_STD);
-	coda_write(dev, ctx->params.codec_mode_aux, CODA7_REG_BIT_RUN_AUX_STD);
-
-	coda_write(dev, cmd, CODA_REG_BIT_RUN_COMMAND);
-}
-
-static int coda_command_sync(struct coda_ctx *ctx, int cmd)
-{
-	struct coda_dev *dev = ctx->dev;
-
-	coda_command_async(ctx, cmd);
-	return coda_wait_timeout(dev);
-}
-
-static int coda_hw_reset(struct coda_ctx *ctx)
-{
-	struct coda_dev *dev = ctx->dev;
-	unsigned long timeout;
-	unsigned int idx;
-	int ret;
-
-	if (!dev->rstc)
-		return -ENOENT;
-
-	idx = coda_read(dev, CODA_REG_BIT_RUN_INDEX);
-
-	timeout = jiffies + msecs_to_jiffies(100);
-	coda_write(dev, 0x11, CODA9_GDI_BUS_CTRL);
-	while (coda_read(dev, CODA9_GDI_BUS_STATUS) != 0x77) {
-		if (time_after(jiffies, timeout))
-			return -ETIME;
-		cpu_relax();
-	}
-
-	ret = reset_control_reset(dev->rstc);
-	if (ret < 0)
-		return ret;
-
-	coda_write(dev, 0x00, CODA9_GDI_BUS_CTRL);
-	coda_write(dev, CODA_REG_BIT_BUSY_FLAG, CODA_REG_BIT_BUSY);
-	coda_write(dev, CODA_REG_RUN_ENABLE, CODA_REG_BIT_CODE_RUN);
-	ret = coda_wait_timeout(dev);
-	coda_write(dev, idx, CODA_REG_BIT_RUN_INDEX);
-
-	return ret;
-}
-
-static struct coda_q_data *get_q_data(struct coda_ctx *ctx,
-					 enum v4l2_buf_type type)
-{
-	switch (type) {
-	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
-		return &(ctx->q_data[V4L2_M2M_SRC]);
-	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
-		return &(ctx->q_data[V4L2_M2M_DST]);
-	default:
-		return NULL;
-	}
-}
-
-/*
- * Array of all formats supported by any version of Coda:
- */
-static struct coda_fmt coda_formats[] = {
-	{
-		.name = "YUV 4:2:0 Planar, YCbCr",
-		.fourcc = V4L2_PIX_FMT_YUV420,
-	},
-	{
-		.name = "YUV 4:2:0 Planar, YCrCb",
-		.fourcc = V4L2_PIX_FMT_YVU420,
-	},
-	{
-		.name = "H264 Encoded Stream",
-		.fourcc = V4L2_PIX_FMT_H264,
-	},
-	{
-		.name = "MPEG4 Encoded Stream",
-		.fourcc = V4L2_PIX_FMT_MPEG4,
-	},
-};
-
-#define CODA_CODEC(mode, src_fourcc, dst_fourcc, max_w, max_h) \
-	{ mode, src_fourcc, dst_fourcc, max_w, max_h }
-
-/*
- * Arrays of codecs supported by each given version of Coda:
- *  i.MX27 -> codadx6
- *  i.MX5x -> coda7
- *  i.MX6  -> coda960
- * Use V4L2_PIX_FMT_YUV420 as placeholder for all supported YUV 4:2:0 variants
- */
-static struct coda_codec codadx6_codecs[] = {
-	CODA_CODEC(CODADX6_MODE_ENCODE_H264, V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_H264,  720, 576),
-	CODA_CODEC(CODADX6_MODE_ENCODE_MP4,  V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_MPEG4, 720, 576),
-};
-
-static struct coda_codec coda7_codecs[] = {
-	CODA_CODEC(CODA7_MODE_ENCODE_H264, V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_H264,   1280, 720),
-	CODA_CODEC(CODA7_MODE_ENCODE_MP4,  V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_MPEG4,  1280, 720),
-	CODA_CODEC(CODA7_MODE_DECODE_H264, V4L2_PIX_FMT_H264,   V4L2_PIX_FMT_YUV420, 1920, 1080),
-	CODA_CODEC(CODA7_MODE_DECODE_MP4,  V4L2_PIX_FMT_MPEG4,  V4L2_PIX_FMT_YUV420, 1920, 1080),
-};
-
-static struct coda_codec coda9_codecs[] = {
-	CODA_CODEC(CODA9_MODE_ENCODE_H264, V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_H264,   1920, 1080),
-	CODA_CODEC(CODA9_MODE_ENCODE_MP4,  V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_MPEG4,  1920, 1080),
-	CODA_CODEC(CODA9_MODE_DECODE_H264, V4L2_PIX_FMT_H264,   V4L2_PIX_FMT_YUV420, 1920, 1080),
-	CODA_CODEC(CODA9_MODE_DECODE_MP4,  V4L2_PIX_FMT_MPEG4,  V4L2_PIX_FMT_YUV420, 1920, 1080),
-};
-
-static bool coda_format_is_yuv(u32 fourcc)
-{
-	switch (fourcc) {
-	case V4L2_PIX_FMT_YUV420:
-	case V4L2_PIX_FMT_YVU420:
-		return true;
-	default:
-		return false;
-	}
-}
-
-/*
- * Normalize all supported YUV 4:2:0 formats to the value used in the codec
- * tables.
- */
-static u32 coda_format_normalize_yuv(u32 fourcc)
-{
-	return coda_format_is_yuv(fourcc) ? V4L2_PIX_FMT_YUV420 : fourcc;
-}
-
-static struct coda_codec *coda_find_codec(struct coda_dev *dev, int src_fourcc,
-					  int dst_fourcc)
-{
-	struct coda_codec *codecs = dev->devtype->codecs;
-	int num_codecs = dev->devtype->num_codecs;
-	int k;
-
-	src_fourcc = coda_format_normalize_yuv(src_fourcc);
-	dst_fourcc = coda_format_normalize_yuv(dst_fourcc);
-	if (src_fourcc == dst_fourcc)
-		return NULL;
-
-	for (k = 0; k < num_codecs; k++) {
-		if (codecs[k].src_fourcc == src_fourcc &&
-		    codecs[k].dst_fourcc == dst_fourcc)
-			break;
-	}
-
-	if (k == num_codecs)
-		return NULL;
-
-	return &codecs[k];
-}
-
-static void coda_get_max_dimensions(struct coda_dev *dev,
-				    struct coda_codec *codec,
-				    int *max_w, int *max_h)
-{
-	struct coda_codec *codecs = dev->devtype->codecs;
-	int num_codecs = dev->devtype->num_codecs;
-	unsigned int w, h;
-	int k;
-
-	if (codec) {
-		w = codec->max_w;
-		h = codec->max_h;
-	} else {
-		for (k = 0, w = 0, h = 0; k < num_codecs; k++) {
-			w = max(w, codecs[k].max_w);
-			h = max(h, codecs[k].max_h);
-		}
-	}
-
-	if (max_w)
-		*max_w = w;
-	if (max_h)
-		*max_h = h;
-}
-
-static char *coda_product_name(int product)
-{
-	static char buf[9];
-
-	switch (product) {
-	case CODA_DX6:
-		return "CodaDx6";
-	case CODA_7541:
-		return "CODA7541";
-	case CODA_960:
-		return "CODA960";
-	default:
-		snprintf(buf, sizeof(buf), "(0x%04x)", product);
-		return buf;
-	}
-}
-
-/*
- * V4L2 ioctl() operations.
- */
-static int coda_querycap(struct file *file, void *priv,
-			 struct v4l2_capability *cap)
-{
-	struct coda_ctx *ctx = fh_to_ctx(priv);
-
-	strlcpy(cap->driver, CODA_NAME, sizeof(cap->driver));
-	strlcpy(cap->card, coda_product_name(ctx->dev->devtype->product),
-		sizeof(cap->card));
-	strlcpy(cap->bus_info, "platform:" CODA_NAME, sizeof(cap->bus_info));
-	/*
-	 * This is only a mem-to-mem video device. The capture and output
-	 * device capability flags are left only for backward compatibility
-	 * and are scheduled for removal.
-	 */
-	cap->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_VIDEO_OUTPUT |
-			   V4L2_CAP_VIDEO_M2M | V4L2_CAP_STREAMING;
-	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
-
-	return 0;
-}
-
-static int enum_fmt(void *priv, struct v4l2_fmtdesc *f,
-			enum v4l2_buf_type type, int src_fourcc)
-{
-	struct coda_ctx *ctx = fh_to_ctx(priv);
-	struct coda_codec *codecs = ctx->dev->devtype->codecs;
-	struct coda_fmt *formats = coda_formats;
-	struct coda_fmt *fmt;
-	int num_codecs = ctx->dev->devtype->num_codecs;
-	int num_formats = ARRAY_SIZE(coda_formats);
-	int i, k, num = 0;
-
-	for (i = 0; i < num_formats; i++) {
-		/* Both uncompressed formats are always supported */
-		if (coda_format_is_yuv(formats[i].fourcc) &&
-		    !coda_format_is_yuv(src_fourcc)) {
-			if (num == f->index)
-				break;
-			++num;
-			continue;
-		}
-		/* Compressed formats may be supported, check the codec list */
-		for (k = 0; k < num_codecs; k++) {
-			/* if src_fourcc is set, only consider matching codecs */
-			if (type == V4L2_BUF_TYPE_VIDEO_CAPTURE &&
-			    formats[i].fourcc == codecs[k].dst_fourcc &&
-			    (!src_fourcc || src_fourcc == codecs[k].src_fourcc))
-				break;
-			if (type == V4L2_BUF_TYPE_VIDEO_OUTPUT &&
-			    formats[i].fourcc == codecs[k].src_fourcc)
-				break;
-		}
-		if (k < num_codecs) {
-			if (num == f->index)
-				break;
-			++num;
-		}
-	}
-
-	if (i < num_formats) {
-		fmt = &formats[i];
-		strlcpy(f->description, fmt->name, sizeof(f->description));
-		f->pixelformat = fmt->fourcc;
-		if (!coda_format_is_yuv(fmt->fourcc))
-			f->flags |= V4L2_FMT_FLAG_COMPRESSED;
-		return 0;
-	}
-
-	/* Format not found */
-	return -EINVAL;
-}
-
-static int coda_enum_fmt_vid_cap(struct file *file, void *priv,
-				 struct v4l2_fmtdesc *f)
-{
-	struct coda_ctx *ctx = fh_to_ctx(priv);
-	struct vb2_queue *src_vq;
-	struct coda_q_data *q_data_src;
-
-	/* If the source format is already fixed, only list matching formats */
-	src_vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-	if (vb2_is_streaming(src_vq)) {
-		q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-
-		return enum_fmt(priv, f, V4L2_BUF_TYPE_VIDEO_CAPTURE,
-				q_data_src->fourcc);
-	}
-
-	return enum_fmt(priv, f, V4L2_BUF_TYPE_VIDEO_CAPTURE, 0);
-}
-
-static int coda_enum_fmt_vid_out(struct file *file, void *priv,
-				 struct v4l2_fmtdesc *f)
-{
-	return enum_fmt(priv, f, V4L2_BUF_TYPE_VIDEO_OUTPUT, 0);
-}
-
-static int coda_g_fmt(struct file *file, void *priv,
-		      struct v4l2_format *f)
-{
-	struct coda_q_data *q_data;
-	struct coda_ctx *ctx = fh_to_ctx(priv);
-
-	q_data = get_q_data(ctx, f->type);
-	if (!q_data)
-		return -EINVAL;
-
-	f->fmt.pix.field	= V4L2_FIELD_NONE;
-	f->fmt.pix.pixelformat	= q_data->fourcc;
-	f->fmt.pix.width	= q_data->width;
-	f->fmt.pix.height	= q_data->height;
-	f->fmt.pix.bytesperline = q_data->bytesperline;
-
-	f->fmt.pix.sizeimage	= q_data->sizeimage;
-	f->fmt.pix.colorspace	= ctx->colorspace;
-
-	return 0;
-}
-
-static int coda_try_fmt(struct coda_ctx *ctx, struct coda_codec *codec,
-			struct v4l2_format *f)
-{
-	struct coda_dev *dev = ctx->dev;
-	struct coda_q_data *q_data;
-	unsigned int max_w, max_h;
-	enum v4l2_field field;
-
-	field = f->fmt.pix.field;
-	if (field == V4L2_FIELD_ANY)
-		field = V4L2_FIELD_NONE;
-	else if (V4L2_FIELD_NONE != field)
-		return -EINVAL;
-
-	/* V4L2 specification suggests the driver corrects the format struct
-	 * if any of the dimensions is unsupported */
-	f->fmt.pix.field = field;
-
-	coda_get_max_dimensions(dev, codec, &max_w, &max_h);
-	v4l_bound_align_image(&f->fmt.pix.width, MIN_W, max_w, W_ALIGN,
-			      &f->fmt.pix.height, MIN_H, max_h, H_ALIGN,
-			      S_ALIGN);
-
-	switch (f->fmt.pix.pixelformat) {
-	case V4L2_PIX_FMT_YUV420:
-	case V4L2_PIX_FMT_YVU420:
-	case V4L2_PIX_FMT_H264:
-	case V4L2_PIX_FMT_MPEG4:
-	case V4L2_PIX_FMT_JPEG:
-		break;
-	default:
-		q_data = get_q_data(ctx, f->type);
-		if (!q_data)
-			return -EINVAL;
-		f->fmt.pix.pixelformat = q_data->fourcc;
-	}
-
-	switch (f->fmt.pix.pixelformat) {
-	case V4L2_PIX_FMT_YUV420:
-	case V4L2_PIX_FMT_YVU420:
-		/* Frame stride must be multiple of 8, but 16 for h.264 */
-		f->fmt.pix.bytesperline = round_up(f->fmt.pix.width, 16);
-		f->fmt.pix.sizeimage = f->fmt.pix.bytesperline *
-					f->fmt.pix.height * 3 / 2;
-		break;
-	case V4L2_PIX_FMT_H264:
-	case V4L2_PIX_FMT_MPEG4:
-	case V4L2_PIX_FMT_JPEG:
-		f->fmt.pix.bytesperline = 0;
-		f->fmt.pix.sizeimage = CODA_MAX_FRAME_SIZE;
-		break;
-	default:
-		BUG();
-	}
-
-	return 0;
-}
-
-static int coda_try_fmt_vid_cap(struct file *file, void *priv,
-				struct v4l2_format *f)
-{
-	struct coda_ctx *ctx = fh_to_ctx(priv);
-	struct coda_codec *codec;
-	struct vb2_queue *src_vq;
-	int ret;
-
-	/*
-	 * If the source format is already fixed, try to find a codec that
-	 * converts to the given destination format
-	 */
-	src_vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-	if (vb2_is_streaming(src_vq)) {
-		struct coda_q_data *q_data_src;
-
-		q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-		codec = coda_find_codec(ctx->dev, q_data_src->fourcc,
-					f->fmt.pix.pixelformat);
-		if (!codec)
-			return -EINVAL;
-	} else {
-		/* Otherwise determine codec by encoded format, if possible */
-		codec = coda_find_codec(ctx->dev, V4L2_PIX_FMT_YUV420,
-					f->fmt.pix.pixelformat);
-	}
-
-	f->fmt.pix.colorspace = ctx->colorspace;
-
-	ret = coda_try_fmt(ctx, codec, f);
-	if (ret < 0)
-		return ret;
-
-	/* The h.264 decoder only returns complete 16x16 macroblocks */
-	if (codec && codec->src_fourcc == V4L2_PIX_FMT_H264) {
-		f->fmt.pix.width = f->fmt.pix.width;
-		f->fmt.pix.height = round_up(f->fmt.pix.height, 16);
-		f->fmt.pix.bytesperline = round_up(f->fmt.pix.width, 16);
-		f->fmt.pix.sizeimage = f->fmt.pix.bytesperline *
-				       f->fmt.pix.height * 3 / 2;
-	}
-
-	return 0;
-}
-
-static int coda_try_fmt_vid_out(struct file *file, void *priv,
-				struct v4l2_format *f)
-{
-	struct coda_ctx *ctx = fh_to_ctx(priv);
-	struct coda_codec *codec;
-
-	/* Determine codec by encoded format, returns NULL if raw or invalid */
-	codec = coda_find_codec(ctx->dev, f->fmt.pix.pixelformat,
-				V4L2_PIX_FMT_YUV420);
-
-	if (!f->fmt.pix.colorspace)
-		f->fmt.pix.colorspace = V4L2_COLORSPACE_REC709;
-
-	return coda_try_fmt(ctx, codec, f);
-}
-
-static int coda_s_fmt(struct coda_ctx *ctx, struct v4l2_format *f)
-{
-	struct coda_q_data *q_data;
-	struct vb2_queue *vq;
-
-	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
-	if (!vq)
-		return -EINVAL;
-
-	q_data = get_q_data(ctx, f->type);
-	if (!q_data)
-		return -EINVAL;
-
-	if (vb2_is_busy(vq)) {
-		v4l2_err(&ctx->dev->v4l2_dev, "%s queue busy\n", __func__);
-		return -EBUSY;
-	}
-
-	q_data->fourcc = f->fmt.pix.pixelformat;
-	q_data->width = f->fmt.pix.width;
-	q_data->height = f->fmt.pix.height;
-	q_data->bytesperline = f->fmt.pix.bytesperline;
-	q_data->sizeimage = f->fmt.pix.sizeimage;
-	q_data->rect.left = 0;
-	q_data->rect.top = 0;
-	q_data->rect.width = f->fmt.pix.width;
-	q_data->rect.height = f->fmt.pix.height;
-
-	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-		"Setting format for type %d, wxh: %dx%d, fmt: %d\n",
-		f->type, q_data->width, q_data->height, q_data->fourcc);
-
-	return 0;
-}
-
-static int coda_s_fmt_vid_cap(struct file *file, void *priv,
-			      struct v4l2_format *f)
-{
-	struct coda_ctx *ctx = fh_to_ctx(priv);
-	int ret;
-
-	ret = coda_try_fmt_vid_cap(file, priv, f);
-	if (ret)
-		return ret;
-
-	return coda_s_fmt(ctx, f);
-}
-
-static int coda_s_fmt_vid_out(struct file *file, void *priv,
-			      struct v4l2_format *f)
-{
-	struct coda_ctx *ctx = fh_to_ctx(priv);
-	int ret;
-
-	ret = coda_try_fmt_vid_out(file, priv, f);
-	if (ret)
-		return ret;
-
-	ret = coda_s_fmt(ctx, f);
-	if (ret)
-		ctx->colorspace = f->fmt.pix.colorspace;
-
-	return ret;
-}
-
-static int coda_qbuf(struct file *file, void *priv,
-		     struct v4l2_buffer *buf)
-{
-	struct coda_ctx *ctx = fh_to_ctx(priv);
-
-	return v4l2_m2m_qbuf(file, ctx->fh.m2m_ctx, buf);
-}
-
-static bool coda_buf_is_end_of_stream(struct coda_ctx *ctx,
-				      struct v4l2_buffer *buf)
-{
-	struct vb2_queue *src_vq;
-
-	src_vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-
-	return ((ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG) &&
-		(buf->sequence == (ctx->qsequence - 1)));
-}
-
-static int coda_dqbuf(struct file *file, void *priv,
-		      struct v4l2_buffer *buf)
-{
-	struct coda_ctx *ctx = fh_to_ctx(priv);
-	int ret;
-
-	ret = v4l2_m2m_dqbuf(file, ctx->fh.m2m_ctx, buf);
-
-	/* If this is the last capture buffer, emit an end-of-stream event */
-	if (buf->type == V4L2_BUF_TYPE_VIDEO_CAPTURE &&
-	    coda_buf_is_end_of_stream(ctx, buf)) {
-		const struct v4l2_event eos_event = {
-			.type = V4L2_EVENT_EOS
-		};
-
-		v4l2_event_queue_fh(&ctx->fh, &eos_event);
-	}
-
-	return ret;
-}
-
-static int coda_g_selection(struct file *file, void *fh,
-			    struct v4l2_selection *s)
-{
-	struct coda_ctx *ctx = fh_to_ctx(fh);
-	struct coda_q_data *q_data;
-	struct v4l2_rect r, *rsel;
-
-	q_data = get_q_data(ctx, s->type);
-	if (!q_data)
-		return -EINVAL;
-
-	r.left = 0;
-	r.top = 0;
-	r.width = q_data->width;
-	r.height = q_data->height;
-	rsel = &q_data->rect;
-
-	switch (s->target) {
-	case V4L2_SEL_TGT_CROP_DEFAULT:
-	case V4L2_SEL_TGT_CROP_BOUNDS:
-		rsel = &r;
-		/* fallthrough */
-	case V4L2_SEL_TGT_CROP:
-		if (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT)
-			return -EINVAL;
-		break;
-	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
-	case V4L2_SEL_TGT_COMPOSE_PADDED:
-		rsel = &r;
-		/* fallthrough */
-	case V4L2_SEL_TGT_COMPOSE:
-	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
-		if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
-			return -EINVAL;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	s->r = *rsel;
-
-	return 0;
-}
-
-static int coda_try_decoder_cmd(struct file *file, void *fh,
-				struct v4l2_decoder_cmd *dc)
-{
-	if (dc->cmd != V4L2_DEC_CMD_STOP)
-		return -EINVAL;
-
-	if (dc->flags & V4L2_DEC_CMD_STOP_TO_BLACK)
-		return -EINVAL;
-
-	if (!(dc->flags & V4L2_DEC_CMD_STOP_IMMEDIATELY) && (dc->stop.pts != 0))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int coda_decoder_cmd(struct file *file, void *fh,
-			    struct v4l2_decoder_cmd *dc)
-{
-	struct coda_ctx *ctx = fh_to_ctx(fh);
-	struct coda_dev *dev = ctx->dev;
-	int ret;
-
-	ret = coda_try_decoder_cmd(file, fh, dc);
-	if (ret < 0)
-		return ret;
-
-	/* Ignore decoder stop command silently in encoder context */
-	if (ctx->inst_type != CODA_INST_DECODER)
-		return 0;
-
-	/* Set the strem-end flag on this context */
-	ctx->bit_stream_param |= CODA_BIT_STREAM_END_FLAG;
-
-	if ((dev->devtype->product == CODA_960) &&
-	    coda_isbusy(dev) &&
-	    (ctx->idx == coda_read(dev, CODA_REG_BIT_RUN_INDEX))) {
-		/* If this context is currently running, update the hardware flag */
-		coda_write(dev, ctx->bit_stream_param, CODA_REG_BIT_BIT_STREAM_PARAM);
-	}
-	ctx->hold = false;
-	v4l2_m2m_try_schedule(ctx->fh.m2m_ctx);
-
-	return 0;
-}
-
-static int coda_subscribe_event(struct v4l2_fh *fh,
-				const struct v4l2_event_subscription *sub)
-{
-	switch (sub->type) {
-	case V4L2_EVENT_EOS:
-		return v4l2_event_subscribe(fh, sub, 0, NULL);
-	default:
-		return v4l2_ctrl_subscribe_event(fh, sub);
-	}
-}
-
-static const struct v4l2_ioctl_ops coda_ioctl_ops = {
-	.vidioc_querycap	= coda_querycap,
-
-	.vidioc_enum_fmt_vid_cap = coda_enum_fmt_vid_cap,
-	.vidioc_g_fmt_vid_cap	= coda_g_fmt,
-	.vidioc_try_fmt_vid_cap	= coda_try_fmt_vid_cap,
-	.vidioc_s_fmt_vid_cap	= coda_s_fmt_vid_cap,
-
-	.vidioc_enum_fmt_vid_out = coda_enum_fmt_vid_out,
-	.vidioc_g_fmt_vid_out	= coda_g_fmt,
-	.vidioc_try_fmt_vid_out	= coda_try_fmt_vid_out,
-	.vidioc_s_fmt_vid_out	= coda_s_fmt_vid_out,
-
-	.vidioc_reqbufs		= v4l2_m2m_ioctl_reqbufs,
-	.vidioc_querybuf	= v4l2_m2m_ioctl_querybuf,
-
-	.vidioc_qbuf		= coda_qbuf,
-	.vidioc_expbuf		= v4l2_m2m_ioctl_expbuf,
-	.vidioc_dqbuf		= coda_dqbuf,
-	.vidioc_create_bufs	= v4l2_m2m_ioctl_create_bufs,
-
-	.vidioc_streamon	= v4l2_m2m_ioctl_streamon,
-	.vidioc_streamoff	= v4l2_m2m_ioctl_streamoff,
-
-	.vidioc_g_selection	= coda_g_selection,
-
-	.vidioc_try_decoder_cmd	= coda_try_decoder_cmd,
-	.vidioc_decoder_cmd	= coda_decoder_cmd,
-
-	.vidioc_subscribe_event = coda_subscribe_event,
-	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
-};
-
-static int coda_start_decoding(struct coda_ctx *ctx);
-
-static inline int coda_get_bitstream_payload(struct coda_ctx *ctx)
-{
-	return kfifo_len(&ctx->bitstream_fifo);
-}
-
-static void coda_kfifo_sync_from_device(struct coda_ctx *ctx)
-{
-	struct __kfifo *kfifo = &ctx->bitstream_fifo.kfifo;
-	struct coda_dev *dev = ctx->dev;
-	u32 rd_ptr;
-
-	rd_ptr = coda_read(dev, CODA_REG_BIT_RD_PTR(ctx->reg_idx));
-	kfifo->out = (kfifo->in & ~kfifo->mask) |
-		      (rd_ptr - ctx->bitstream.paddr);
-	if (kfifo->out > kfifo->in)
-		kfifo->out -= kfifo->mask + 1;
-}
-
-static void coda_kfifo_sync_to_device_full(struct coda_ctx *ctx)
-{
-	struct __kfifo *kfifo = &ctx->bitstream_fifo.kfifo;
-	struct coda_dev *dev = ctx->dev;
-	u32 rd_ptr, wr_ptr;
-
-	rd_ptr = ctx->bitstream.paddr + (kfifo->out & kfifo->mask);
-	coda_write(dev, rd_ptr, CODA_REG_BIT_RD_PTR(ctx->reg_idx));
-	wr_ptr = ctx->bitstream.paddr + (kfifo->in & kfifo->mask);
-	coda_write(dev, wr_ptr, CODA_REG_BIT_WR_PTR(ctx->reg_idx));
-}
-
-static void coda_kfifo_sync_to_device_write(struct coda_ctx *ctx)
-{
-	struct __kfifo *kfifo = &ctx->bitstream_fifo.kfifo;
-	struct coda_dev *dev = ctx->dev;
-	u32 wr_ptr;
-
-	wr_ptr = ctx->bitstream.paddr + (kfifo->in & kfifo->mask);
-	coda_write(dev, wr_ptr, CODA_REG_BIT_WR_PTR(ctx->reg_idx));
-}
-
-static int coda_bitstream_queue(struct coda_ctx *ctx, struct vb2_buffer *src_buf)
-{
-	u32 src_size = vb2_get_plane_payload(src_buf, 0);
-	u32 n;
-
-	n = kfifo_in(&ctx->bitstream_fifo, vb2_plane_vaddr(src_buf, 0), src_size);
-	if (n < src_size)
-		return -ENOSPC;
-
-	dma_sync_single_for_device(&ctx->dev->plat_dev->dev, ctx->bitstream.paddr,
-				   ctx->bitstream.size, DMA_TO_DEVICE);
-
-	src_buf->v4l2_buf.sequence = ctx->qsequence++;
-
-	return 0;
-}
-
-static bool coda_bitstream_try_queue(struct coda_ctx *ctx,
-				     struct vb2_buffer *src_buf)
-{
-	int ret;
-
-	if (coda_get_bitstream_payload(ctx) +
-	    vb2_get_plane_payload(src_buf, 0) + 512 >= ctx->bitstream.size)
-		return false;
-
-	if (vb2_plane_vaddr(src_buf, 0) == NULL) {
-		v4l2_err(&ctx->dev->v4l2_dev, "trying to queue empty buffer\n");
-		return true;
-	}
-
-	ret = coda_bitstream_queue(ctx, src_buf);
-	if (ret < 0) {
-		v4l2_err(&ctx->dev->v4l2_dev, "bitstream buffer overflow\n");
-		return false;
-	}
-	/* Sync read pointer to device */
-	if (ctx == v4l2_m2m_get_curr_priv(ctx->dev->m2m_dev))
-		coda_kfifo_sync_to_device_write(ctx);
-
-	ctx->hold = false;
-
-	return true;
-}
-
-static void coda_fill_bitstream(struct coda_ctx *ctx)
-{
-	struct vb2_buffer *src_buf;
-	struct coda_timestamp *ts;
-
-	while (v4l2_m2m_num_src_bufs_ready(ctx->fh.m2m_ctx) > 0) {
-		src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
-
-		if (coda_bitstream_try_queue(ctx, src_buf)) {
-			/*
-			 * Source buffer is queued in the bitstream ringbuffer;
-			 * queue the timestamp and mark source buffer as done
-			 */
-			src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
-
-			ts = kmalloc(sizeof(*ts), GFP_KERNEL);
-			if (ts) {
-				ts->sequence = src_buf->v4l2_buf.sequence;
-				ts->timecode = src_buf->v4l2_buf.timecode;
-				ts->timestamp = src_buf->v4l2_buf.timestamp;
-				list_add_tail(&ts->list, &ctx->timestamp_list);
-			}
-
-			v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE);
-		} else {
-			break;
-		}
-	}
-}
-
-static void coda_set_gdi_regs(struct coda_ctx *ctx)
-{
-	struct gdi_tiled_map *tiled_map = &ctx->tiled_map;
-	struct coda_dev *dev = ctx->dev;
-	int i;
-
-	for (i = 0; i < 16; i++)
-		coda_write(dev, tiled_map->xy2ca_map[i],
-				CODA9_GDI_XY2_CAS_0 + 4 * i);
-	for (i = 0; i < 4; i++)
-		coda_write(dev, tiled_map->xy2ba_map[i],
-				CODA9_GDI_XY2_BA_0 + 4 * i);
-	for (i = 0; i < 16; i++)
-		coda_write(dev, tiled_map->xy2ra_map[i],
-				CODA9_GDI_XY2_RAS_0 + 4 * i);
-	coda_write(dev, tiled_map->xy2rbc_config, CODA9_GDI_XY2_RBC_CONFIG);
-	for (i = 0; i < 32; i++)
-		coda_write(dev, tiled_map->rbc2axi_map[i],
-				CODA9_GDI_RBC2_AXI_0 + 4 * i);
-}
-
-/*
- * Mem-to-mem operations.
- */
-static int coda_prepare_decode(struct coda_ctx *ctx)
-{
-	struct vb2_buffer *dst_buf;
-	struct coda_dev *dev = ctx->dev;
-	struct coda_q_data *q_data_dst;
-	u32 stridey, height;
-	u32 picture_y, picture_cb, picture_cr;
-
-	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
-	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
-
-	if (ctx->params.rot_mode & CODA_ROT_90) {
-		stridey = q_data_dst->height;
-		height = q_data_dst->width;
-	} else {
-		stridey = q_data_dst->width;
-		height = q_data_dst->height;
-	}
-
-	/* Try to copy source buffer contents into the bitstream ringbuffer */
-	mutex_lock(&ctx->bitstream_mutex);
-	coda_fill_bitstream(ctx);
-	mutex_unlock(&ctx->bitstream_mutex);
-
-	if (coda_get_bitstream_payload(ctx) < 512 &&
-	    (!(ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG))) {
-		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
-			 "bitstream payload: %d, skipping\n",
-			 coda_get_bitstream_payload(ctx));
-		v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx);
-		return -EAGAIN;
-	}
-
-	/* Run coda_start_decoding (again) if not yet initialized */
-	if (!ctx->initialized) {
-		int ret = coda_start_decoding(ctx);
-		if (ret < 0) {
-			v4l2_err(&dev->v4l2_dev, "failed to start decoding\n");
-			v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx);
-			return -EAGAIN;
-		} else {
-			ctx->initialized = 1;
-		}
-	}
-
-	if (dev->devtype->product == CODA_960)
-		coda_set_gdi_regs(ctx);
-
-	/* Set rotator output */
-	picture_y = vb2_dma_contig_plane_dma_addr(dst_buf, 0);
-	if (q_data_dst->fourcc == V4L2_PIX_FMT_YVU420) {
-		/* Switch Cr and Cb for YVU420 format */
-		picture_cr = picture_y + stridey * height;
-		picture_cb = picture_cr + stridey / 2 * height / 2;
-	} else {
-		picture_cb = picture_y + stridey * height;
-		picture_cr = picture_cb + stridey / 2 * height / 2;
-	}
-
-	if (dev->devtype->product == CODA_960) {
-		/*
-		 * The CODA960 seems to have an internal list of buffers with
-		 * 64 entries that includes the registered frame buffers as
-		 * well as the rotator buffer output.
-		 * ROT_INDEX needs to be < 0x40, but > ctx->num_internal_frames.
-		 */
-		coda_write(dev, CODA_MAX_FRAMEBUFFERS + dst_buf->v4l2_buf.index,
-				CODA9_CMD_DEC_PIC_ROT_INDEX);
-		coda_write(dev, picture_y, CODA9_CMD_DEC_PIC_ROT_ADDR_Y);
-		coda_write(dev, picture_cb, CODA9_CMD_DEC_PIC_ROT_ADDR_CB);
-		coda_write(dev, picture_cr, CODA9_CMD_DEC_PIC_ROT_ADDR_CR);
-		coda_write(dev, stridey, CODA9_CMD_DEC_PIC_ROT_STRIDE);
-	} else {
-		coda_write(dev, picture_y, CODA_CMD_DEC_PIC_ROT_ADDR_Y);
-		coda_write(dev, picture_cb, CODA_CMD_DEC_PIC_ROT_ADDR_CB);
-		coda_write(dev, picture_cr, CODA_CMD_DEC_PIC_ROT_ADDR_CR);
-		coda_write(dev, stridey, CODA_CMD_DEC_PIC_ROT_STRIDE);
-	}
-	coda_write(dev, CODA_ROT_MIR_ENABLE | ctx->params.rot_mode,
-			CODA_CMD_DEC_PIC_ROT_MODE);
-
-	switch (dev->devtype->product) {
-	case CODA_DX6:
-		/* TBD */
-	case CODA_7541:
-		coda_write(dev, CODA_PRE_SCAN_EN, CODA_CMD_DEC_PIC_OPTION);
-		break;
-	case CODA_960:
-		coda_write(dev, (1 << 10), CODA_CMD_DEC_PIC_OPTION); /* 'hardcode to use interrupt disable mode'? */
-		break;
-	}
-
-	coda_write(dev, 0, CODA_CMD_DEC_PIC_SKIP_NUM);
-
-	coda_write(dev, 0, CODA_CMD_DEC_PIC_BB_START);
-	coda_write(dev, 0, CODA_CMD_DEC_PIC_START_BYTE);
-
-	return 0;
-}
-
-static void coda_prepare_encode(struct coda_ctx *ctx)
-{
-	struct coda_q_data *q_data_src, *q_data_dst;
-	struct vb2_buffer *src_buf, *dst_buf;
-	struct coda_dev *dev = ctx->dev;
-	int force_ipicture;
-	int quant_param = 0;
-	u32 picture_y, picture_cb, picture_cr;
-	u32 pic_stream_buffer_addr, pic_stream_buffer_size;
-	u32 dst_fourcc;
-
-	src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
-	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
-	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
-	dst_fourcc = q_data_dst->fourcc;
-
-	src_buf->v4l2_buf.sequence = ctx->osequence;
-	dst_buf->v4l2_buf.sequence = ctx->osequence;
-	ctx->osequence++;
-
-	/*
-	 * Workaround coda firmware BUG that only marks the first
-	 * frame as IDR. This is a problem for some decoders that can't
-	 * recover when a frame is lost.
-	 */
-	if (src_buf->v4l2_buf.sequence % ctx->params.gop_size) {
-		src_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_PFRAME;
-		src_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_KEYFRAME;
-	} else {
-		src_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_KEYFRAME;
-		src_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_PFRAME;
-	}
-
-	if (dev->devtype->product == CODA_960)
-		coda_set_gdi_regs(ctx);
-
-	/*
-	 * Copy headers at the beginning of the first frame for H.264 only.
-	 * In MPEG4 they are already copied by the coda.
-	 */
-	if (src_buf->v4l2_buf.sequence == 0) {
-		pic_stream_buffer_addr =
-			vb2_dma_contig_plane_dma_addr(dst_buf, 0) +
-			ctx->vpu_header_size[0] +
-			ctx->vpu_header_size[1] +
-			ctx->vpu_header_size[2];
-		pic_stream_buffer_size = CODA_MAX_FRAME_SIZE -
-			ctx->vpu_header_size[0] -
-			ctx->vpu_header_size[1] -
-			ctx->vpu_header_size[2];
-		memcpy(vb2_plane_vaddr(dst_buf, 0),
-		       &ctx->vpu_header[0][0], ctx->vpu_header_size[0]);
-		memcpy(vb2_plane_vaddr(dst_buf, 0) + ctx->vpu_header_size[0],
-		       &ctx->vpu_header[1][0], ctx->vpu_header_size[1]);
-		memcpy(vb2_plane_vaddr(dst_buf, 0) + ctx->vpu_header_size[0] +
-			ctx->vpu_header_size[1], &ctx->vpu_header[2][0],
-			ctx->vpu_header_size[2]);
-	} else {
-		pic_stream_buffer_addr =
-			vb2_dma_contig_plane_dma_addr(dst_buf, 0);
-		pic_stream_buffer_size = CODA_MAX_FRAME_SIZE;
-	}
-
-	if (src_buf->v4l2_buf.flags & V4L2_BUF_FLAG_KEYFRAME) {
-		force_ipicture = 1;
-		switch (dst_fourcc) {
-		case V4L2_PIX_FMT_H264:
-			quant_param = ctx->params.h264_intra_qp;
-			break;
-		case V4L2_PIX_FMT_MPEG4:
-			quant_param = ctx->params.mpeg4_intra_qp;
-			break;
-		default:
-			v4l2_warn(&ctx->dev->v4l2_dev,
-				"cannot set intra qp, fmt not supported\n");
-			break;
-		}
-	} else {
-		force_ipicture = 0;
-		switch (dst_fourcc) {
-		case V4L2_PIX_FMT_H264:
-			quant_param = ctx->params.h264_inter_qp;
-			break;
-		case V4L2_PIX_FMT_MPEG4:
-			quant_param = ctx->params.mpeg4_inter_qp;
-			break;
-		default:
-			v4l2_warn(&ctx->dev->v4l2_dev,
-				"cannot set inter qp, fmt not supported\n");
-			break;
-		}
-	}
-
-	/* submit */
-	coda_write(dev, CODA_ROT_MIR_ENABLE | ctx->params.rot_mode, CODA_CMD_ENC_PIC_ROT_MODE);
-	coda_write(dev, quant_param, CODA_CMD_ENC_PIC_QS);
-
-
-	picture_y = vb2_dma_contig_plane_dma_addr(src_buf, 0);
-	switch (q_data_src->fourcc) {
-	case V4L2_PIX_FMT_YVU420:
-		/* Switch Cb and Cr for YVU420 format */
-		picture_cr = picture_y + q_data_src->bytesperline *
-				q_data_src->height;
-		picture_cb = picture_cr + q_data_src->bytesperline / 2 *
-				q_data_src->height / 2;
-		break;
-	case V4L2_PIX_FMT_YUV420:
-	default:
-		picture_cb = picture_y + q_data_src->bytesperline *
-				q_data_src->height;
-		picture_cr = picture_cb + q_data_src->bytesperline / 2 *
-				q_data_src->height / 2;
-		break;
-	}
-
-	if (dev->devtype->product == CODA_960) {
-		coda_write(dev, 4/*FIXME: 0*/, CODA9_CMD_ENC_PIC_SRC_INDEX);
-		coda_write(dev, q_data_src->width, CODA9_CMD_ENC_PIC_SRC_STRIDE);
-		coda_write(dev, 0, CODA9_CMD_ENC_PIC_SUB_FRAME_SYNC);
-
-		coda_write(dev, picture_y, CODA9_CMD_ENC_PIC_SRC_ADDR_Y);
-		coda_write(dev, picture_cb, CODA9_CMD_ENC_PIC_SRC_ADDR_CB);
-		coda_write(dev, picture_cr, CODA9_CMD_ENC_PIC_SRC_ADDR_CR);
-	} else {
-		coda_write(dev, picture_y, CODA_CMD_ENC_PIC_SRC_ADDR_Y);
-		coda_write(dev, picture_cb, CODA_CMD_ENC_PIC_SRC_ADDR_CB);
-		coda_write(dev, picture_cr, CODA_CMD_ENC_PIC_SRC_ADDR_CR);
-	}
-	coda_write(dev, force_ipicture << 1 & 0x2,
-		   CODA_CMD_ENC_PIC_OPTION);
-
-	coda_write(dev, pic_stream_buffer_addr, CODA_CMD_ENC_PIC_BB_START);
-	coda_write(dev, pic_stream_buffer_size / 1024,
-		   CODA_CMD_ENC_PIC_BB_SIZE);
-
-	if (!ctx->streamon_out) {
-		/* After streamoff on the output side, set the stream end flag */
-		ctx->bit_stream_param |= CODA_BIT_STREAM_END_FLAG;
-		coda_write(dev, ctx->bit_stream_param, CODA_REG_BIT_BIT_STREAM_PARAM);
-	}
-}
-
-static void coda_device_run(void *m2m_priv)
-{
-	struct coda_ctx *ctx = m2m_priv;
-	struct coda_dev *dev = ctx->dev;
-
-	queue_work(dev->workqueue, &ctx->pic_run_work);
-}
-
-static void coda_free_framebuffers(struct coda_ctx *ctx);
-static void coda_free_context_buffers(struct coda_ctx *ctx);
-
-static void coda_seq_end_work(struct work_struct *work)
-{
-	struct coda_ctx *ctx = container_of(work, struct coda_ctx, seq_end_work);
-	struct coda_dev *dev = ctx->dev;
-
-	mutex_lock(&ctx->buffer_mutex);
-	mutex_lock(&dev->coda_mutex);
-
-	v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
-		 "%d: %s: sent command 'SEQ_END' to coda\n", ctx->idx, __func__);
-	if (coda_command_sync(ctx, CODA_COMMAND_SEQ_END)) {
-		v4l2_err(&dev->v4l2_dev,
-			 "CODA_COMMAND_SEQ_END failed\n");
-	}
-
-	kfifo_init(&ctx->bitstream_fifo,
-		ctx->bitstream.vaddr, ctx->bitstream.size);
-
-	coda_free_framebuffers(ctx);
-	coda_free_context_buffers(ctx);
-
-	mutex_unlock(&dev->coda_mutex);
-	mutex_unlock(&ctx->buffer_mutex);
-}
-
-static void coda_finish_decode(struct coda_ctx *ctx);
-static void coda_finish_encode(struct coda_ctx *ctx);
-
-static void coda_pic_run_work(struct work_struct *work)
-{
-	struct coda_ctx *ctx = container_of(work, struct coda_ctx, pic_run_work);
-	struct coda_dev *dev = ctx->dev;
-	int ret;
-
-	mutex_lock(&ctx->buffer_mutex);
-	mutex_lock(&dev->coda_mutex);
-
-	if (ctx->inst_type == CODA_INST_DECODER) {
-		ret = coda_prepare_decode(ctx);
-		if (ret < 0) {
-			mutex_unlock(&dev->coda_mutex);
-			mutex_unlock(&ctx->buffer_mutex);
-			/* job_finish scheduled by prepare_decode */
-			return;
-		}
-	} else {
-		coda_prepare_encode(ctx);
-	}
-
-	if (dev->devtype->product != CODA_DX6)
-		coda_write(dev, ctx->iram_info.axi_sram_use,
-				CODA7_REG_BIT_AXI_SRAM_USE);
-
-	if (ctx->inst_type == CODA_INST_DECODER)
-		coda_kfifo_sync_to_device_full(ctx);
-	coda_command_async(ctx, CODA_COMMAND_PIC_RUN);
-
-	if (!wait_for_completion_timeout(&ctx->completion, msecs_to_jiffies(1000))) {
-		dev_err(&dev->plat_dev->dev, "CODA PIC_RUN timeout\n");
-
-		ctx->hold = true;
-
-		coda_hw_reset(ctx);
-	} else if (!ctx->aborting) {
-		if (ctx->inst_type == CODA_INST_DECODER)
-			coda_finish_decode(ctx);
-		else
-			coda_finish_encode(ctx);
-	}
-
-	if (ctx->aborting || (!ctx->streamon_cap && !ctx->streamon_out))
-		queue_work(dev->workqueue, &ctx->seq_end_work);
-
-	mutex_unlock(&dev->coda_mutex);
-	mutex_unlock(&ctx->buffer_mutex);
-
-	v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx);
-}
-
-static int coda_job_ready(void *m2m_priv)
-{
-	struct coda_ctx *ctx = m2m_priv;
-
-	/*
-	 * For both 'P' and 'key' frame cases 1 picture
-	 * and 1 frame are needed. In the decoder case,
-	 * the compressed frame can be in the bitstream.
-	 */
-	if (!v4l2_m2m_num_src_bufs_ready(ctx->fh.m2m_ctx) &&
-	    ctx->inst_type != CODA_INST_DECODER) {
-		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-			 "not ready: not enough video buffers.\n");
-		return 0;
-	}
-
-	if (!v4l2_m2m_num_dst_bufs_ready(ctx->fh.m2m_ctx)) {
-		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-			 "not ready: not enough video capture buffers.\n");
-		return 0;
-	}
-
-	if (ctx->hold ||
-	    ((ctx->inst_type == CODA_INST_DECODER) &&
-	     (coda_get_bitstream_payload(ctx) < 512) &&
-	     !(ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG))) {
-		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-			 "%d: not ready: not enough bitstream data.\n",
-			 ctx->idx);
-		return 0;
-	}
-
-	if (ctx->aborting) {
-		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-			 "not ready: aborting\n");
-		return 0;
-	}
-
-	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-			"job ready\n");
-	return 1;
-}
-
-static void coda_job_abort(void *priv)
-{
-	struct coda_ctx *ctx = priv;
-
-	ctx->aborting = 1;
-
-	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-		 "Aborting task\n");
-}
-
-static void coda_lock(void *m2m_priv)
-{
-	struct coda_ctx *ctx = m2m_priv;
-	struct coda_dev *pcdev = ctx->dev;
-	mutex_lock(&pcdev->dev_mutex);
-}
-
-static void coda_unlock(void *m2m_priv)
-{
-	struct coda_ctx *ctx = m2m_priv;
-	struct coda_dev *pcdev = ctx->dev;
-	mutex_unlock(&pcdev->dev_mutex);
-}
-
-static struct v4l2_m2m_ops coda_m2m_ops = {
-	.device_run	= coda_device_run,
-	.job_ready	= coda_job_ready,
-	.job_abort	= coda_job_abort,
-	.lock		= coda_lock,
-	.unlock		= coda_unlock,
-};
-
-static void coda_set_tiled_map_type(struct coda_ctx *ctx, int tiled_map_type)
-{
-	struct gdi_tiled_map *tiled_map = &ctx->tiled_map;
-	int luma_map, chro_map, i;
-
-	memset(tiled_map, 0, sizeof(*tiled_map));
-
-	luma_map = 64;
-	chro_map = 64;
-	tiled_map->map_type = tiled_map_type;
-	for (i = 0; i < 16; i++)
-		tiled_map->xy2ca_map[i] = luma_map << 8 | chro_map;
-	for (i = 0; i < 4; i++)
-		tiled_map->xy2ba_map[i] = luma_map << 8 | chro_map;
-	for (i = 0; i < 16; i++)
-		tiled_map->xy2ra_map[i] = luma_map << 8 | chro_map;
-
-	if (tiled_map_type == GDI_LINEAR_FRAME_MAP) {
-		tiled_map->xy2rbc_config = 0;
-	} else {
-		dev_err(&ctx->dev->plat_dev->dev, "invalid map type: %d\n",
-			tiled_map_type);
-		return;
-	}
-}
-
-static void set_default_params(struct coda_ctx *ctx)
-{
-	int max_w;
-	int max_h;
-
-	ctx->codec = &ctx->dev->devtype->codecs[0];
-	max_w = ctx->codec->max_w;
-	max_h = ctx->codec->max_h;
-
-	ctx->params.codec_mode = CODA_MODE_INVALID;
-	ctx->colorspace = V4L2_COLORSPACE_REC709;
-	ctx->params.framerate = 30;
-	ctx->aborting = 0;
-
-	/* Default formats for output and input queues */
-	ctx->q_data[V4L2_M2M_SRC].fourcc = ctx->codec->src_fourcc;
-	ctx->q_data[V4L2_M2M_DST].fourcc = ctx->codec->dst_fourcc;
-	ctx->q_data[V4L2_M2M_SRC].width = max_w;
-	ctx->q_data[V4L2_M2M_SRC].height = max_h;
-	ctx->q_data[V4L2_M2M_SRC].bytesperline = max_w;
-	ctx->q_data[V4L2_M2M_SRC].sizeimage = (max_w * max_h * 3) / 2;
-	ctx->q_data[V4L2_M2M_DST].width = max_w;
-	ctx->q_data[V4L2_M2M_DST].height = max_h;
-	ctx->q_data[V4L2_M2M_DST].bytesperline = 0;
-	ctx->q_data[V4L2_M2M_DST].sizeimage = CODA_MAX_FRAME_SIZE;
-	ctx->q_data[V4L2_M2M_SRC].rect.width = max_w;
-	ctx->q_data[V4L2_M2M_SRC].rect.height = max_h;
-	ctx->q_data[V4L2_M2M_DST].rect.width = max_w;
-	ctx->q_data[V4L2_M2M_DST].rect.height = max_h;
-
-	if (ctx->dev->devtype->product == CODA_960)
-		coda_set_tiled_map_type(ctx, GDI_LINEAR_FRAME_MAP);
-}
-
-/*
- * Queue operations
- */
-static int coda_queue_setup(struct vb2_queue *vq,
-				const struct v4l2_format *fmt,
-				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
-{
-	struct coda_ctx *ctx = vb2_get_drv_priv(vq);
-	struct coda_q_data *q_data;
-	unsigned int size;
-
-	q_data = get_q_data(ctx, vq->type);
-	size = q_data->sizeimage;
-
-	*nplanes = 1;
-	sizes[0] = size;
-
-	alloc_ctxs[0] = ctx->dev->alloc_ctx;
-
-	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-		 "get %d buffer(s) of size %d each.\n", *nbuffers, size);
-
-	return 0;
-}
-
-static int coda_buf_prepare(struct vb2_buffer *vb)
-{
-	struct coda_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
-	struct coda_q_data *q_data;
-
-	q_data = get_q_data(ctx, vb->vb2_queue->type);
-
-	if (vb2_plane_size(vb, 0) < q_data->sizeimage) {
-		v4l2_warn(&ctx->dev->v4l2_dev,
-			  "%s data will not fit into plane (%lu < %lu)\n",
-			  __func__, vb2_plane_size(vb, 0),
-			  (long)q_data->sizeimage);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static void coda_buf_queue(struct vb2_buffer *vb)
-{
-	struct coda_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
-	struct coda_dev *dev = ctx->dev;
-	struct coda_q_data *q_data;
-
-	q_data = get_q_data(ctx, vb->vb2_queue->type);
-
-	/*
-	 * In the decoder case, immediately try to copy the buffer into the
-	 * bitstream ringbuffer and mark it as ready to be dequeued.
-	 */
-	if (q_data->fourcc == V4L2_PIX_FMT_H264 &&
-	    vb->vb2_queue->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) {
-		/*
-		 * For backwards compatibility, queuing an empty buffer marks
-		 * the stream end
-		 */
-		if (vb2_get_plane_payload(vb, 0) == 0) {
-			ctx->bit_stream_param |= CODA_BIT_STREAM_END_FLAG;
-			if ((dev->devtype->product == CODA_960) &&
-			    coda_isbusy(dev) &&
-			    (ctx->idx == coda_read(dev, CODA_REG_BIT_RUN_INDEX))) {
-				/* if this decoder instance is running, set the stream end flag */
-				coda_write(dev, ctx->bit_stream_param, CODA_REG_BIT_BIT_STREAM_PARAM);
-			}
-		}
-		mutex_lock(&ctx->bitstream_mutex);
-		v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vb);
-		coda_fill_bitstream(ctx);
-		mutex_unlock(&ctx->bitstream_mutex);
-	} else {
-		v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vb);
-	}
-}
-
-static void coda_parabuf_write(struct coda_ctx *ctx, int index, u32 value)
-{
-	struct coda_dev *dev = ctx->dev;
-	u32 *p = ctx->parabuf.vaddr;
-
-	if (dev->devtype->product == CODA_DX6)
-		p[index] = value;
-	else
-		p[index ^ 1] = value;
-}
-
-static int coda_alloc_aux_buf(struct coda_dev *dev,
-			      struct coda_aux_buf *buf, size_t size,
-			      const char *name, struct dentry *parent)
-{
-	buf->vaddr = dma_alloc_coherent(&dev->plat_dev->dev, size, &buf->paddr,
-					GFP_KERNEL);
-	if (!buf->vaddr)
-		return -ENOMEM;
-
-	buf->size = size;
-
-	if (name && parent) {
-		buf->blob.data = buf->vaddr;
-		buf->blob.size = size;
-		buf->dentry = debugfs_create_blob(name, 0644, parent, &buf->blob);
-		if (!buf->dentry)
-			dev_warn(&dev->plat_dev->dev,
-				 "failed to create debugfs entry %s\n", name);
-	}
-
-	return 0;
-}
-
-static inline int coda_alloc_context_buf(struct coda_ctx *ctx,
-					 struct coda_aux_buf *buf, size_t size,
-					 const char *name)
-{
-	return coda_alloc_aux_buf(ctx->dev, buf, size, name, ctx->debugfs_entry);
-}
-
-static void coda_free_aux_buf(struct coda_dev *dev,
-			      struct coda_aux_buf *buf)
-{
-	if (buf->vaddr) {
-		dma_free_coherent(&dev->plat_dev->dev, buf->size,
-				  buf->vaddr, buf->paddr);
-		buf->vaddr = NULL;
-		buf->size = 0;
-	}
-	debugfs_remove(buf->dentry);
-}
-
-static void coda_free_framebuffers(struct coda_ctx *ctx)
-{
-	int i;
-
-	for (i = 0; i < CODA_MAX_FRAMEBUFFERS; i++)
-		coda_free_aux_buf(ctx->dev, &ctx->internal_frames[i]);
-}
-
-static int coda_alloc_framebuffers(struct coda_ctx *ctx, struct coda_q_data *q_data, u32 fourcc)
-{
-	struct coda_dev *dev = ctx->dev;
-	int width, height;
-	dma_addr_t paddr;
-	int ysize;
-	int ret;
-	int i;
-
-	if (ctx->codec && (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 ||
-	     ctx->codec->dst_fourcc == V4L2_PIX_FMT_H264)) {
-		width = round_up(q_data->width, 16);
-		height = round_up(q_data->height, 16);
-	} else {
-		width = round_up(q_data->width, 8);
-		height = q_data->height;
-	}
-	ysize = width * height;
-
-	/* Allocate frame buffers */
-	for (i = 0; i < ctx->num_internal_frames; i++) {
-		size_t size;
-		char *name;
-
-		size = ysize + ysize / 2;
-		if (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 &&
-		    dev->devtype->product != CODA_DX6)
-			size += ysize / 4;
-		name = kasprintf(GFP_KERNEL, "fb%d", i);
-		ret = coda_alloc_context_buf(ctx, &ctx->internal_frames[i],
-					     size, name);
-		kfree(name);
-		if (ret < 0) {
-			coda_free_framebuffers(ctx);
-			return ret;
-		}
-	}
-
-	/* Register frame buffers in the parameter buffer */
-	for (i = 0; i < ctx->num_internal_frames; i++) {
-		paddr = ctx->internal_frames[i].paddr;
-		coda_parabuf_write(ctx, i * 3 + 0, paddr); /* Y */
-		coda_parabuf_write(ctx, i * 3 + 1, paddr + ysize); /* Cb */
-		coda_parabuf_write(ctx, i * 3 + 2, paddr + ysize + ysize/4); /* Cr */
-
-		/* mvcol buffer for h.264 */
-		if (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 &&
-		    dev->devtype->product != CODA_DX6)
-			coda_parabuf_write(ctx, 96 + i,
-					   ctx->internal_frames[i].paddr +
-					   ysize + ysize/4 + ysize/4);
-	}
-
-	/* mvcol buffer for mpeg4 */
-	if ((dev->devtype->product != CODA_DX6) &&
-	    (ctx->codec->src_fourcc == V4L2_PIX_FMT_MPEG4))
-		coda_parabuf_write(ctx, 97, ctx->internal_frames[i].paddr +
-					    ysize + ysize/4 + ysize/4);
-
-	return 0;
-}
-
-static int coda_h264_padding(int size, char *p)
-{
-	int nal_size;
-	int diff;
-
-	diff = size - (size & ~0x7);
-	if (diff == 0)
-		return 0;
-
-	nal_size = coda_filler_size[diff];
-	memcpy(p, coda_filler_nal, nal_size);
-
-	/* Add rbsp stop bit and trailing at the end */
-	*(p + nal_size - 1) = 0x80;
-
-	return nal_size;
-}
-
-static phys_addr_t coda_iram_alloc(struct coda_iram_info *iram, size_t size)
-{
-	phys_addr_t ret;
-
-	size = round_up(size, 1024);
-	if (size > iram->remaining)
-		return 0;
-	iram->remaining -= size;
-
-	ret = iram->next_paddr;
-	iram->next_paddr += size;
-
-	return ret;
-}
-
-static void coda_setup_iram(struct coda_ctx *ctx)
-{
-	struct coda_iram_info *iram_info = &ctx->iram_info;
-	struct coda_dev *dev = ctx->dev;
-	int mb_width;
-	int dbk_bits;
-	int bit_bits;
-	int ip_bits;
-
-	memset(iram_info, 0, sizeof(*iram_info));
-	iram_info->next_paddr = dev->iram.paddr;
-	iram_info->remaining = dev->iram.size;
-
-	switch (dev->devtype->product) {
-	case CODA_7541:
-		dbk_bits = CODA7_USE_HOST_DBK_ENABLE | CODA7_USE_DBK_ENABLE;
-		bit_bits = CODA7_USE_HOST_BIT_ENABLE | CODA7_USE_BIT_ENABLE;
-		ip_bits = CODA7_USE_HOST_IP_ENABLE | CODA7_USE_IP_ENABLE;
-		break;
-	case CODA_960:
-		dbk_bits = CODA9_USE_HOST_DBK_ENABLE | CODA9_USE_DBK_ENABLE;
-		bit_bits = CODA9_USE_HOST_BIT_ENABLE | CODA7_USE_BIT_ENABLE;
-		ip_bits = CODA9_USE_HOST_IP_ENABLE | CODA7_USE_IP_ENABLE;
-		break;
-	default: /* CODA_DX6 */
-		return;
-	}
-
-	if (ctx->inst_type == CODA_INST_ENCODER) {
-		struct coda_q_data *q_data_src;
-
-		q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-		mb_width = DIV_ROUND_UP(q_data_src->width, 16);
-
-		/* Prioritize in case IRAM is too small for everything */
-		if (dev->devtype->product == CODA_7541) {
-			iram_info->search_ram_size = round_up(mb_width * 16 *
-							      36 + 2048, 1024);
-			iram_info->search_ram_paddr = coda_iram_alloc(iram_info,
-							iram_info->search_ram_size);
-			if (!iram_info->search_ram_paddr) {
-				pr_err("IRAM is smaller than the search ram size\n");
-				goto out;
-			}
-			iram_info->axi_sram_use |= CODA7_USE_HOST_ME_ENABLE |
-						   CODA7_USE_ME_ENABLE;
-		}
-
-		/* Only H.264BP and H.263P3 are considered */
-		iram_info->buf_dbk_y_use = coda_iram_alloc(iram_info, 64 * mb_width);
-		iram_info->buf_dbk_c_use = coda_iram_alloc(iram_info, 64 * mb_width);
-		if (!iram_info->buf_dbk_c_use)
-			goto out;
-		iram_info->axi_sram_use |= dbk_bits;
-
-		iram_info->buf_bit_use = coda_iram_alloc(iram_info, 128 * mb_width);
-		if (!iram_info->buf_bit_use)
-			goto out;
-		iram_info->axi_sram_use |= bit_bits;
-
-		iram_info->buf_ip_ac_dc_use = coda_iram_alloc(iram_info, 128 * mb_width);
-		if (!iram_info->buf_ip_ac_dc_use)
-			goto out;
-		iram_info->axi_sram_use |= ip_bits;
-
-		/* OVL and BTP disabled for encoder */
-	} else if (ctx->inst_type == CODA_INST_DECODER) {
-		struct coda_q_data *q_data_dst;
-
-		q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
-		mb_width = DIV_ROUND_UP(q_data_dst->width, 16);
-
-		iram_info->buf_dbk_y_use = coda_iram_alloc(iram_info, 128 * mb_width);
-		iram_info->buf_dbk_c_use = coda_iram_alloc(iram_info, 128 * mb_width);
-		if (!iram_info->buf_dbk_c_use)
-			goto out;
-		iram_info->axi_sram_use |= dbk_bits;
-
-		iram_info->buf_bit_use = coda_iram_alloc(iram_info, 128 * mb_width);
-		if (!iram_info->buf_bit_use)
-			goto out;
-		iram_info->axi_sram_use |= bit_bits;
-
-		iram_info->buf_ip_ac_dc_use = coda_iram_alloc(iram_info, 128 * mb_width);
-		if (!iram_info->buf_ip_ac_dc_use)
-			goto out;
-		iram_info->axi_sram_use |= ip_bits;
-
-		/* OVL and BTP unused as there is no VC1 support yet */
-	}
-
-out:
-	if (!(iram_info->axi_sram_use & CODA7_USE_HOST_IP_ENABLE))
-		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-			 "IRAM smaller than needed\n");
-
-	if (dev->devtype->product == CODA_7541) {
-		/* TODO - Enabling these causes picture errors on CODA7541 */
-		if (ctx->inst_type == CODA_INST_DECODER) {
-			/* fw 1.4.50 */
-			iram_info->axi_sram_use &= ~(CODA7_USE_HOST_IP_ENABLE |
-						     CODA7_USE_IP_ENABLE);
-		} else {
-			/* fw 13.4.29 */
-			iram_info->axi_sram_use &= ~(CODA7_USE_HOST_IP_ENABLE |
-						     CODA7_USE_HOST_DBK_ENABLE |
-						     CODA7_USE_IP_ENABLE |
-						     CODA7_USE_DBK_ENABLE);
-		}
-	}
-}
-
-static void coda_free_context_buffers(struct coda_ctx *ctx)
-{
-	struct coda_dev *dev = ctx->dev;
-
-	coda_free_aux_buf(dev, &ctx->slicebuf);
-	coda_free_aux_buf(dev, &ctx->psbuf);
-	if (dev->devtype->product != CODA_DX6)
-		coda_free_aux_buf(dev, &ctx->workbuf);
-}
-
-static int coda_alloc_context_buffers(struct coda_ctx *ctx,
-				      struct coda_q_data *q_data)
-{
-	struct coda_dev *dev = ctx->dev;
-	size_t size;
-	int ret;
-
-	if (dev->devtype->product == CODA_DX6)
-		return 0;
-
-	if (ctx->psbuf.vaddr) {
-		v4l2_err(&dev->v4l2_dev, "psmembuf still allocated\n");
-		return -EBUSY;
-	}
-	if (ctx->slicebuf.vaddr) {
-		v4l2_err(&dev->v4l2_dev, "slicebuf still allocated\n");
-		return -EBUSY;
-	}
-	if (ctx->workbuf.vaddr) {
-		v4l2_err(&dev->v4l2_dev, "context buffer still allocated\n");
-		ret = -EBUSY;
-		return -ENOMEM;
-	}
-
-	if (q_data->fourcc == V4L2_PIX_FMT_H264) {
-		/* worst case slice size */
-		size = (DIV_ROUND_UP(q_data->width, 16) *
-			DIV_ROUND_UP(q_data->height, 16)) * 3200 / 8 + 512;
-		ret = coda_alloc_context_buf(ctx, &ctx->slicebuf, size, "slicebuf");
-		if (ret < 0) {
-			v4l2_err(&dev->v4l2_dev, "failed to allocate %d byte slice buffer",
-				 ctx->slicebuf.size);
-			return ret;
-		}
-	}
-
-	if (dev->devtype->product == CODA_7541) {
-		ret = coda_alloc_context_buf(ctx, &ctx->psbuf, CODA7_PS_BUF_SIZE, "psbuf");
-		if (ret < 0) {
-			v4l2_err(&dev->v4l2_dev, "failed to allocate psmem buffer");
-			goto err;
-		}
-	}
-
-	size = dev->devtype->workbuf_size;
-	if (dev->devtype->product == CODA_960 &&
-	    q_data->fourcc == V4L2_PIX_FMT_H264)
-		size += CODA9_PS_SAVE_SIZE;
-	ret = coda_alloc_context_buf(ctx, &ctx->workbuf, size, "workbuf");
-	if (ret < 0) {
-		v4l2_err(&dev->v4l2_dev, "failed to allocate %d byte context buffer",
-			 ctx->workbuf.size);
-		goto err;
-	}
-
-	return 0;
-
-err:
-	coda_free_context_buffers(ctx);
-	return ret;
-}
-
-static int coda_start_decoding(struct coda_ctx *ctx)
-{
-	struct coda_q_data *q_data_src, *q_data_dst;
-	u32 bitstream_buf, bitstream_size;
-	struct coda_dev *dev = ctx->dev;
-	int width, height;
-	u32 src_fourcc;
-	u32 val;
-	int ret;
-
-	/* Start decoding */
-	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
-	bitstream_buf = ctx->bitstream.paddr;
-	bitstream_size = ctx->bitstream.size;
-	src_fourcc = q_data_src->fourcc;
-
-	coda_write(dev, ctx->parabuf.paddr, CODA_REG_BIT_PARA_BUF_ADDR);
-
-	/* Update coda bitstream read and write pointers from kfifo */
-	coda_kfifo_sync_to_device_full(ctx);
-
-	ctx->display_idx = -1;
-	ctx->frm_dis_flg = 0;
-	coda_write(dev, 0, CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));
-
-	coda_write(dev, CODA_BIT_DEC_SEQ_INIT_ESCAPE,
-			CODA_REG_BIT_BIT_STREAM_PARAM);
-
-	coda_write(dev, bitstream_buf, CODA_CMD_DEC_SEQ_BB_START);
-	coda_write(dev, bitstream_size / 1024, CODA_CMD_DEC_SEQ_BB_SIZE);
-	val = 0;
-	if ((dev->devtype->product == CODA_7541) ||
-	    (dev->devtype->product == CODA_960))
-		val |= CODA_REORDER_ENABLE;
-	coda_write(dev, val, CODA_CMD_DEC_SEQ_OPTION);
-
-	ctx->params.codec_mode = ctx->codec->mode;
-	if (dev->devtype->product == CODA_960 &&
-	    src_fourcc == V4L2_PIX_FMT_MPEG4)
-		ctx->params.codec_mode_aux = CODA_MP4_AUX_MPEG4;
-	else
-		ctx->params.codec_mode_aux = 0;
-	if (src_fourcc == V4L2_PIX_FMT_H264) {
-		if (dev->devtype->product == CODA_7541) {
-			coda_write(dev, ctx->psbuf.paddr,
-					CODA_CMD_DEC_SEQ_PS_BB_START);
-			coda_write(dev, (CODA7_PS_BUF_SIZE / 1024),
-					CODA_CMD_DEC_SEQ_PS_BB_SIZE);
-		}
-		if (dev->devtype->product == CODA_960) {
-			coda_write(dev, 0, CODA_CMD_DEC_SEQ_X264_MV_EN);
-			coda_write(dev, 512, CODA_CMD_DEC_SEQ_SPP_CHUNK_SIZE);
-		}
-	}
-	if (dev->devtype->product != CODA_960) {
-		coda_write(dev, 0, CODA_CMD_DEC_SEQ_SRC_SIZE);
-	}
-
-	if (coda_command_sync(ctx, CODA_COMMAND_SEQ_INIT)) {
-		v4l2_err(&dev->v4l2_dev, "CODA_COMMAND_SEQ_INIT timeout\n");
-		coda_write(dev, 0, CODA_REG_BIT_BIT_STREAM_PARAM);
-		return -ETIMEDOUT;
-	}
-
-	/* Update kfifo out pointer from coda bitstream read pointer */
-	coda_kfifo_sync_from_device(ctx);
-
-	coda_write(dev, 0, CODA_REG_BIT_BIT_STREAM_PARAM);
-
-	if (coda_read(dev, CODA_RET_DEC_SEQ_SUCCESS) == 0) {
-		v4l2_err(&dev->v4l2_dev,
-			"CODA_COMMAND_SEQ_INIT failed, error code = %d\n",
-			coda_read(dev, CODA_RET_DEC_SEQ_ERR_REASON));
-		return -EAGAIN;
-	}
-
-	val = coda_read(dev, CODA_RET_DEC_SEQ_SRC_SIZE);
-	if (dev->devtype->product == CODA_DX6) {
-		width = (val >> CODADX6_PICWIDTH_OFFSET) & CODADX6_PICWIDTH_MASK;
-		height = val & CODADX6_PICHEIGHT_MASK;
-	} else {
-		width = (val >> CODA7_PICWIDTH_OFFSET) & CODA7_PICWIDTH_MASK;
-		height = val & CODA7_PICHEIGHT_MASK;
-	}
-
-	if (width > q_data_dst->width || height > q_data_dst->height) {
-		v4l2_err(&dev->v4l2_dev, "stream is %dx%d, not %dx%d\n",
-			 width, height, q_data_dst->width, q_data_dst->height);
-		return -EINVAL;
-	}
-
-	width = round_up(width, 16);
-	height = round_up(height, 16);
-
-	v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "%s instance %d now: %dx%d\n",
-		 __func__, ctx->idx, width, height);
-
-	ctx->num_internal_frames = coda_read(dev, CODA_RET_DEC_SEQ_FRAME_NEED);
-	if (ctx->num_internal_frames > CODA_MAX_FRAMEBUFFERS) {
-		v4l2_err(&dev->v4l2_dev,
-			 "not enough framebuffers to decode (%d < %d)\n",
-			 CODA_MAX_FRAMEBUFFERS, ctx->num_internal_frames);
-		return -EINVAL;
-	}
-
-	if (src_fourcc == V4L2_PIX_FMT_H264) {
-		u32 left_right;
-		u32 top_bottom;
-
-		left_right = coda_read(dev, CODA_RET_DEC_SEQ_CROP_LEFT_RIGHT);
-		top_bottom = coda_read(dev, CODA_RET_DEC_SEQ_CROP_TOP_BOTTOM);
-
-		q_data_dst->rect.left = (left_right >> 10) & 0x3ff;
-		q_data_dst->rect.top = (top_bottom >> 10) & 0x3ff;
-		q_data_dst->rect.width = width - q_data_dst->rect.left -
-					 (left_right & 0x3ff);
-		q_data_dst->rect.height = height - q_data_dst->rect.top -
-					  (top_bottom & 0x3ff);
-	}
-
-	ret = coda_alloc_framebuffers(ctx, q_data_dst, src_fourcc);
-	if (ret < 0)
-		return ret;
-
-	/* Tell the decoder how many frame buffers we allocated. */
-	coda_write(dev, ctx->num_internal_frames, CODA_CMD_SET_FRAME_BUF_NUM);
-	coda_write(dev, width, CODA_CMD_SET_FRAME_BUF_STRIDE);
-
-	if (dev->devtype->product != CODA_DX6) {
-		/* Set secondary AXI IRAM */
-		coda_setup_iram(ctx);
-
-		coda_write(dev, ctx->iram_info.buf_bit_use,
-				CODA7_CMD_SET_FRAME_AXI_BIT_ADDR);
-		coda_write(dev, ctx->iram_info.buf_ip_ac_dc_use,
-				CODA7_CMD_SET_FRAME_AXI_IPACDC_ADDR);
-		coda_write(dev, ctx->iram_info.buf_dbk_y_use,
-				CODA7_CMD_SET_FRAME_AXI_DBKY_ADDR);
-		coda_write(dev, ctx->iram_info.buf_dbk_c_use,
-				CODA7_CMD_SET_FRAME_AXI_DBKC_ADDR);
-		coda_write(dev, ctx->iram_info.buf_ovl_use,
-				CODA7_CMD_SET_FRAME_AXI_OVL_ADDR);
-		if (dev->devtype->product == CODA_960)
-			coda_write(dev, ctx->iram_info.buf_btp_use,
-					CODA9_CMD_SET_FRAME_AXI_BTP_ADDR);
-	}
-
-	if (dev->devtype->product == CODA_960) {
-		coda_write(dev, -1, CODA9_CMD_SET_FRAME_DELAY);
-
-		coda_write(dev, 0x20262024, CODA9_CMD_SET_FRAME_CACHE_SIZE);
-		coda_write(dev, 2 << CODA9_CACHE_PAGEMERGE_OFFSET |
-				32 << CODA9_CACHE_LUMA_BUFFER_SIZE_OFFSET |
-				8 << CODA9_CACHE_CB_BUFFER_SIZE_OFFSET |
-				8 << CODA9_CACHE_CR_BUFFER_SIZE_OFFSET,
-				CODA9_CMD_SET_FRAME_CACHE_CONFIG);
-	}
-
-	if (src_fourcc == V4L2_PIX_FMT_H264) {
-		coda_write(dev, ctx->slicebuf.paddr,
-				CODA_CMD_SET_FRAME_SLICE_BB_START);
-		coda_write(dev, ctx->slicebuf.size / 1024,
-				CODA_CMD_SET_FRAME_SLICE_BB_SIZE);
-	}
-
-	if (dev->devtype->product == CODA_7541) {
-		int max_mb_x = 1920 / 16;
-		int max_mb_y = 1088 / 16;
-		int max_mb_num = max_mb_x * max_mb_y;
-
-		coda_write(dev, max_mb_num << 16 | max_mb_x << 8 | max_mb_y,
-				CODA7_CMD_SET_FRAME_MAX_DEC_SIZE);
-	} else if (dev->devtype->product == CODA_960) {
-		int max_mb_x = 1920 / 16;
-		int max_mb_y = 1088 / 16;
-		int max_mb_num = max_mb_x * max_mb_y;
-
-		coda_write(dev, max_mb_num << 16 | max_mb_x << 8 | max_mb_y,
-				CODA9_CMD_SET_FRAME_MAX_DEC_SIZE);
-	}
-
-	if (coda_command_sync(ctx, CODA_COMMAND_SET_FRAME_BUF)) {
-		v4l2_err(&ctx->dev->v4l2_dev,
-			 "CODA_COMMAND_SET_FRAME_BUF timeout\n");
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-static int coda_encode_header(struct coda_ctx *ctx, struct vb2_buffer *buf,
-			      int header_code, u8 *header, int *size)
-{
-	struct coda_dev *dev = ctx->dev;
-	size_t bufsize;
-	int ret;
-	int i;
-
-	if (dev->devtype->product == CODA_960)
-		memset(vb2_plane_vaddr(buf, 0), 0, 64);
-
-	coda_write(dev, vb2_dma_contig_plane_dma_addr(buf, 0),
-		   CODA_CMD_ENC_HEADER_BB_START);
-	bufsize = vb2_plane_size(buf, 0);
-	if (dev->devtype->product == CODA_960)
-		bufsize /= 1024;
-	coda_write(dev, bufsize, CODA_CMD_ENC_HEADER_BB_SIZE);
-	coda_write(dev, header_code, CODA_CMD_ENC_HEADER_CODE);
-	ret = coda_command_sync(ctx, CODA_COMMAND_ENCODE_HEADER);
-	if (ret < 0) {
-		v4l2_err(&dev->v4l2_dev, "CODA_COMMAND_ENCODE_HEADER timeout\n");
-		return ret;
-	}
-
-	if (dev->devtype->product == CODA_960) {
-		for (i = 63; i > 0; i--)
-			if (((char *)vb2_plane_vaddr(buf, 0))[i] != 0)
-				break;
-		*size = i + 1;
-	} else {
-		*size = coda_read(dev, CODA_REG_BIT_WR_PTR(ctx->reg_idx)) -
-			coda_read(dev, CODA_CMD_ENC_HEADER_BB_START);
-	}
-	memcpy(header, vb2_plane_vaddr(buf, 0), *size);
-
-	return 0;
-}
-
-static int coda_start_encoding(struct coda_ctx *ctx);
-
-static int coda_start_streaming(struct vb2_queue *q, unsigned int count)
-{
-	struct coda_ctx *ctx = vb2_get_drv_priv(q);
-	struct v4l2_device *v4l2_dev = &ctx->dev->v4l2_dev;
-	struct coda_dev *dev = ctx->dev;
-	struct coda_q_data *q_data_src, *q_data_dst;
-	u32 dst_fourcc;
-	int ret = 0;
-
-	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) {
-		if (q_data_src->fourcc == V4L2_PIX_FMT_H264) {
-			if (coda_get_bitstream_payload(ctx) < 512)
-				return -EINVAL;
-		} else {
-			if (count < 1)
-				return -EINVAL;
-		}
-
-		ctx->streamon_out = 1;
-
-		if (coda_format_is_yuv(q_data_src->fourcc))
-			ctx->inst_type = CODA_INST_ENCODER;
-		else
-			ctx->inst_type = CODA_INST_DECODER;
-	} else {
-		if (count < 1)
-			return -EINVAL;
-
-		ctx->streamon_cap = 1;
-	}
-
-	/* Don't start the coda unless both queues are on */
-	if (!(ctx->streamon_out & ctx->streamon_cap))
-		return 0;
-
-	/* Allow decoder device_run with no new buffers queued */
-	if (ctx->inst_type == CODA_INST_DECODER)
-		v4l2_m2m_set_src_buffered(ctx->fh.m2m_ctx, true);
-
-	ctx->gopcounter = ctx->params.gop_size - 1;
-	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
-	dst_fourcc = q_data_dst->fourcc;
-
-	ctx->codec = coda_find_codec(ctx->dev, q_data_src->fourcc,
-				     q_data_dst->fourcc);
-	if (!ctx->codec) {
-		v4l2_err(v4l2_dev, "couldn't tell instance type.\n");
-		return -EINVAL;
-	}
-
-	/* Allocate per-instance buffers */
-	ret = coda_alloc_context_buffers(ctx, q_data_src);
-	if (ret < 0)
-		return ret;
-
-	if (ctx->inst_type == CODA_INST_DECODER) {
-		mutex_lock(&dev->coda_mutex);
-		ret = coda_start_decoding(ctx);
-		mutex_unlock(&dev->coda_mutex);
-		if (ret == -EAGAIN)
-			return 0;
-		else if (ret < 0)
-			return ret;
-	} else {
-		ret = coda_start_encoding(ctx);
-	}
-
-	ctx->initialized = 1;
-	return ret;
-}
-
-static int coda_start_encoding(struct coda_ctx *ctx)
-{
-	struct coda_dev *dev = ctx->dev;
-	struct v4l2_device *v4l2_dev = &dev->v4l2_dev;
-	struct coda_q_data *q_data_src, *q_data_dst;
-	u32 bitstream_buf, bitstream_size;
-	struct vb2_buffer *buf;
-	int gamma, ret, value;
-	u32 dst_fourcc;
-
-	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
-	dst_fourcc = q_data_dst->fourcc;
-
-	buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
-	bitstream_buf = vb2_dma_contig_plane_dma_addr(buf, 0);
-	bitstream_size = q_data_dst->sizeimage;
-
-	if (!coda_is_initialized(dev)) {
-		v4l2_err(v4l2_dev, "coda is not initialized.\n");
-		return -EFAULT;
-	}
-
-	mutex_lock(&dev->coda_mutex);
-
-	coda_write(dev, ctx->parabuf.paddr, CODA_REG_BIT_PARA_BUF_ADDR);
-	coda_write(dev, bitstream_buf, CODA_REG_BIT_RD_PTR(ctx->reg_idx));
-	coda_write(dev, bitstream_buf, CODA_REG_BIT_WR_PTR(ctx->reg_idx));
-	switch (dev->devtype->product) {
-	case CODA_DX6:
-		coda_write(dev, CODADX6_STREAM_BUF_DYNALLOC_EN |
-			CODADX6_STREAM_BUF_PIC_RESET, CODA_REG_BIT_STREAM_CTRL);
-		break;
-	case CODA_960:
-		coda_write(dev, 0, CODA9_GDI_WPROT_RGN_EN);
-		/* fallthrough */
-	case CODA_7541:
-		coda_write(dev, CODA7_STREAM_BUF_DYNALLOC_EN |
-			CODA7_STREAM_BUF_PIC_RESET, CODA_REG_BIT_STREAM_CTRL);
-		break;
-	}
-
-	value = coda_read(dev, CODA_REG_BIT_FRAME_MEM_CTRL);
-	value &= ~(1 << 2 | 0x7 << 9);
-	ctx->frame_mem_ctrl = value;
-	coda_write(dev, value, CODA_REG_BIT_FRAME_MEM_CTRL);
-
-	if (dev->devtype->product == CODA_DX6) {
-		/* Configure the coda */
-		coda_write(dev, dev->iram.paddr, CODADX6_REG_BIT_SEARCH_RAM_BASE_ADDR);
-	}
-
-	/* Could set rotation here if needed */
-	switch (dev->devtype->product) {
-	case CODA_DX6:
-		value = (q_data_src->width & CODADX6_PICWIDTH_MASK) << CODADX6_PICWIDTH_OFFSET;
-		value |= (q_data_src->height & CODADX6_PICHEIGHT_MASK) << CODA_PICHEIGHT_OFFSET;
-		break;
-	case CODA_7541:
-		if (dst_fourcc == V4L2_PIX_FMT_H264) {
-			value = (round_up(q_data_src->width, 16) &
-				 CODA7_PICWIDTH_MASK) << CODA7_PICWIDTH_OFFSET;
-			value |= (round_up(q_data_src->height, 16) &
-				  CODA7_PICHEIGHT_MASK) << CODA_PICHEIGHT_OFFSET;
-			break;
-		}
-		/* fallthrough */
-	case CODA_960:
-		value = (q_data_src->width & CODA7_PICWIDTH_MASK) << CODA7_PICWIDTH_OFFSET;
-		value |= (q_data_src->height & CODA7_PICHEIGHT_MASK) << CODA_PICHEIGHT_OFFSET;
-	}
-	coda_write(dev, value, CODA_CMD_ENC_SEQ_SRC_SIZE);
-	coda_write(dev, ctx->params.framerate,
-		   CODA_CMD_ENC_SEQ_SRC_F_RATE);
-
-	ctx->params.codec_mode = ctx->codec->mode;
-	switch (dst_fourcc) {
-	case V4L2_PIX_FMT_MPEG4:
-		if (dev->devtype->product == CODA_960)
-			coda_write(dev, CODA9_STD_MPEG4, CODA_CMD_ENC_SEQ_COD_STD);
-		else
-			coda_write(dev, CODA_STD_MPEG4, CODA_CMD_ENC_SEQ_COD_STD);
-		coda_write(dev, 0, CODA_CMD_ENC_SEQ_MP4_PARA);
-		break;
-	case V4L2_PIX_FMT_H264:
-		if (dev->devtype->product == CODA_960)
-			coda_write(dev, CODA9_STD_H264, CODA_CMD_ENC_SEQ_COD_STD);
-		else
-			coda_write(dev, CODA_STD_H264, CODA_CMD_ENC_SEQ_COD_STD);
-		if (ctx->params.h264_deblk_enabled) {
-			value = ((ctx->params.h264_deblk_alpha &
-				  CODA_264PARAM_DEBLKFILTEROFFSETALPHA_MASK) <<
-				 CODA_264PARAM_DEBLKFILTEROFFSETALPHA_OFFSET) |
-				((ctx->params.h264_deblk_beta &
-				  CODA_264PARAM_DEBLKFILTEROFFSETBETA_MASK) <<
-				 CODA_264PARAM_DEBLKFILTEROFFSETBETA_OFFSET);
-		} else {
-			value = 1 << CODA_264PARAM_DISABLEDEBLK_OFFSET;
-		}
-		coda_write(dev, value, CODA_CMD_ENC_SEQ_264_PARA);
-		break;
-	default:
-		v4l2_err(v4l2_dev,
-			 "dst format (0x%08x) invalid.\n", dst_fourcc);
-		ret = -EINVAL;
-		goto out;
-	}
-
-	switch (ctx->params.slice_mode) {
-	case V4L2_MPEG_VIDEO_MULTI_SLICE_MODE_SINGLE:
-		value = 0;
-		break;
-	case V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_MB:
-		value  = (ctx->params.slice_max_mb & CODA_SLICING_SIZE_MASK) << CODA_SLICING_SIZE_OFFSET;
-		value |= (1 & CODA_SLICING_UNIT_MASK) << CODA_SLICING_UNIT_OFFSET;
-		value |=  1 & CODA_SLICING_MODE_MASK;
-		break;
-	case V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_BYTES:
-		value  = (ctx->params.slice_max_bits & CODA_SLICING_SIZE_MASK) << CODA_SLICING_SIZE_OFFSET;
-		value |= (0 & CODA_SLICING_UNIT_MASK) << CODA_SLICING_UNIT_OFFSET;
-		value |=  1 & CODA_SLICING_MODE_MASK;
-		break;
-	}
-	coda_write(dev, value, CODA_CMD_ENC_SEQ_SLICE_MODE);
-	value = ctx->params.gop_size & CODA_GOP_SIZE_MASK;
-	coda_write(dev, value, CODA_CMD_ENC_SEQ_GOP_SIZE);
-
-	if (ctx->params.bitrate) {
-		/* Rate control enabled */
-		value = (ctx->params.bitrate & CODA_RATECONTROL_BITRATE_MASK) << CODA_RATECONTROL_BITRATE_OFFSET;
-		value |=  1 & CODA_RATECONTROL_ENABLE_MASK;
-		if (dev->devtype->product == CODA_960)
-			value |= BIT(31); /* disable autoskip */
-	} else {
-		value = 0;
-	}
-	coda_write(dev, value, CODA_CMD_ENC_SEQ_RC_PARA);
-
-	coda_write(dev, 0, CODA_CMD_ENC_SEQ_RC_BUF_SIZE);
-	coda_write(dev, ctx->params.intra_refresh,
-		   CODA_CMD_ENC_SEQ_INTRA_REFRESH);
-
-	coda_write(dev, bitstream_buf, CODA_CMD_ENC_SEQ_BB_START);
-	coda_write(dev, bitstream_size / 1024, CODA_CMD_ENC_SEQ_BB_SIZE);
-
-
-	value = 0;
-	if (dev->devtype->product == CODA_960)
-		gamma = CODA9_DEFAULT_GAMMA;
-	else
-		gamma = CODA_DEFAULT_GAMMA;
-	if (gamma > 0) {
-		coda_write(dev, (gamma & CODA_GAMMA_MASK) << CODA_GAMMA_OFFSET,
-			   CODA_CMD_ENC_SEQ_RC_GAMMA);
-	}
-
-	if (ctx->params.h264_min_qp || ctx->params.h264_max_qp) {
-		coda_write(dev,
-			   ctx->params.h264_min_qp << CODA_QPMIN_OFFSET |
-			   ctx->params.h264_max_qp << CODA_QPMAX_OFFSET,
-			   CODA_CMD_ENC_SEQ_RC_QP_MIN_MAX);
-	}
-	if (dev->devtype->product == CODA_960) {
-		if (ctx->params.h264_max_qp)
-			value |= 1 << CODA9_OPTION_RCQPMAX_OFFSET;
-		if (CODA_DEFAULT_GAMMA > 0)
-			value |= 1 << CODA9_OPTION_GAMMA_OFFSET;
-	} else {
-		if (CODA_DEFAULT_GAMMA > 0) {
-			if (dev->devtype->product == CODA_DX6)
-				value |= 1 << CODADX6_OPTION_GAMMA_OFFSET;
-			else
-				value |= 1 << CODA7_OPTION_GAMMA_OFFSET;
-		}
-		if (ctx->params.h264_min_qp)
-			value |= 1 << CODA7_OPTION_RCQPMIN_OFFSET;
-		if (ctx->params.h264_max_qp)
-			value |= 1 << CODA7_OPTION_RCQPMAX_OFFSET;
-	}
-	coda_write(dev, value, CODA_CMD_ENC_SEQ_OPTION);
-
-	coda_write(dev, 0, CODA_CMD_ENC_SEQ_RC_INTERVAL_MODE);
-
-	coda_setup_iram(ctx);
-
-	if (dst_fourcc == V4L2_PIX_FMT_H264) {
-		switch (dev->devtype->product) {
-		case CODA_DX6:
-			value = FMO_SLICE_SAVE_BUF_SIZE << 7;
-			coda_write(dev, value, CODADX6_CMD_ENC_SEQ_FMO);
-			break;
-		case CODA_7541:
-			coda_write(dev, ctx->iram_info.search_ram_paddr,
-					CODA7_CMD_ENC_SEQ_SEARCH_BASE);
-			coda_write(dev, ctx->iram_info.search_ram_size,
-					CODA7_CMD_ENC_SEQ_SEARCH_SIZE);
-			break;
-		case CODA_960:
-			coda_write(dev, 0, CODA9_CMD_ENC_SEQ_ME_OPTION);
-			coda_write(dev, 0, CODA9_CMD_ENC_SEQ_INTRA_WEIGHT);
-		}
-	}
-
-	ret = coda_command_sync(ctx, CODA_COMMAND_SEQ_INIT);
-	if (ret < 0) {
-		v4l2_err(v4l2_dev, "CODA_COMMAND_SEQ_INIT timeout\n");
-		goto out;
-	}
-
-	if (coda_read(dev, CODA_RET_ENC_SEQ_SUCCESS) == 0) {
-		v4l2_err(v4l2_dev, "CODA_COMMAND_SEQ_INIT failed\n");
-		ret = -EFAULT;
-		goto out;
-	}
-
-	if (dev->devtype->product == CODA_960)
-		ctx->num_internal_frames = 4;
-	else
-		ctx->num_internal_frames = 2;
-	ret = coda_alloc_framebuffers(ctx, q_data_src, dst_fourcc);
-	if (ret < 0) {
-		v4l2_err(v4l2_dev, "failed to allocate framebuffers\n");
-		goto out;
-	}
-
-	coda_write(dev, ctx->num_internal_frames, CODA_CMD_SET_FRAME_BUF_NUM);
-	coda_write(dev, q_data_src->bytesperline,
-			CODA_CMD_SET_FRAME_BUF_STRIDE);
-	if (dev->devtype->product == CODA_7541) {
-		coda_write(dev, q_data_src->bytesperline,
-				CODA7_CMD_SET_FRAME_SOURCE_BUF_STRIDE);
-	}
-	if (dev->devtype->product != CODA_DX6) {
-		coda_write(dev, ctx->iram_info.buf_bit_use,
-				CODA7_CMD_SET_FRAME_AXI_BIT_ADDR);
-		coda_write(dev, ctx->iram_info.buf_ip_ac_dc_use,
-				CODA7_CMD_SET_FRAME_AXI_IPACDC_ADDR);
-		coda_write(dev, ctx->iram_info.buf_dbk_y_use,
-				CODA7_CMD_SET_FRAME_AXI_DBKY_ADDR);
-		coda_write(dev, ctx->iram_info.buf_dbk_c_use,
-				CODA7_CMD_SET_FRAME_AXI_DBKC_ADDR);
-		coda_write(dev, ctx->iram_info.buf_ovl_use,
-				CODA7_CMD_SET_FRAME_AXI_OVL_ADDR);
-		if (dev->devtype->product == CODA_960) {
-			coda_write(dev, ctx->iram_info.buf_btp_use,
-					CODA9_CMD_SET_FRAME_AXI_BTP_ADDR);
-
-			/* FIXME */
-			coda_write(dev, ctx->internal_frames[2].paddr, CODA9_CMD_SET_FRAME_SUBSAMP_A);
-			coda_write(dev, ctx->internal_frames[3].paddr, CODA9_CMD_SET_FRAME_SUBSAMP_B);
-		}
-	}
-
-	ret = coda_command_sync(ctx, CODA_COMMAND_SET_FRAME_BUF);
-	if (ret < 0) {
-		v4l2_err(v4l2_dev, "CODA_COMMAND_SET_FRAME_BUF timeout\n");
-		goto out;
-	}
-
-	/* Save stream headers */
-	buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
-	switch (dst_fourcc) {
-	case V4L2_PIX_FMT_H264:
-		/*
-		 * Get SPS in the first frame and copy it to an
-		 * intermediate buffer.
-		 */
-		ret = coda_encode_header(ctx, buf, CODA_HEADER_H264_SPS,
-					 &ctx->vpu_header[0][0],
-					 &ctx->vpu_header_size[0]);
-		if (ret < 0)
-			goto out;
-
-		/*
-		 * Get PPS in the first frame and copy it to an
-		 * intermediate buffer.
-		 */
-		ret = coda_encode_header(ctx, buf, CODA_HEADER_H264_PPS,
-					 &ctx->vpu_header[1][0],
-					 &ctx->vpu_header_size[1]);
-		if (ret < 0)
-			goto out;
-
-		/*
-		 * Length of H.264 headers is variable and thus it might not be
-		 * aligned for the coda to append the encoded frame. In that is
-		 * the case a filler NAL must be added to header 2.
-		 */
-		ctx->vpu_header_size[2] = coda_h264_padding(
-					(ctx->vpu_header_size[0] +
-					 ctx->vpu_header_size[1]),
-					 ctx->vpu_header[2]);
-		break;
-	case V4L2_PIX_FMT_MPEG4:
-		/*
-		 * Get VOS in the first frame and copy it to an
-		 * intermediate buffer
-		 */
-		ret = coda_encode_header(ctx, buf, CODA_HEADER_MP4V_VOS,
-					 &ctx->vpu_header[0][0],
-					 &ctx->vpu_header_size[0]);
-		if (ret < 0)
-			goto out;
-
-		ret = coda_encode_header(ctx, buf, CODA_HEADER_MP4V_VIS,
-					 &ctx->vpu_header[1][0],
-					 &ctx->vpu_header_size[1]);
-		if (ret < 0)
-			goto out;
-
-		ret = coda_encode_header(ctx, buf, CODA_HEADER_MP4V_VOL,
-					 &ctx->vpu_header[2][0],
-					 &ctx->vpu_header_size[2]);
-		if (ret < 0)
-			goto out;
-		break;
-	default:
-		/* No more formats need to save headers at the moment */
-		break;
-	}
-
-out:
-	mutex_unlock(&dev->coda_mutex);
-	return ret;
-}
-
-static void coda_stop_streaming(struct vb2_queue *q)
-{
-	struct coda_ctx *ctx = vb2_get_drv_priv(q);
-	struct coda_dev *dev = ctx->dev;
-
-	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) {
-		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
-			 "%s: output\n", __func__);
-		ctx->streamon_out = 0;
-
-		if (ctx->inst_type == CODA_INST_DECODER &&
-		    coda_isbusy(dev) && ctx->idx == coda_read(dev, CODA_REG_BIT_RUN_INDEX)) {
-			/* if this decoder instance is running, set the stream end flag */
-			if (dev->devtype->product == CODA_960) {
-				u32 val = coda_read(dev, CODA_REG_BIT_BIT_STREAM_PARAM);
-
-				val |= CODA_BIT_STREAM_END_FLAG;
-				coda_write(dev, val, CODA_REG_BIT_BIT_STREAM_PARAM);
-				ctx->bit_stream_param = val;
-			}
-		}
-		ctx->bit_stream_param |= CODA_BIT_STREAM_END_FLAG;
-
-		ctx->isequence = 0;
-	} else {
-		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
-			 "%s: capture\n", __func__);
-		ctx->streamon_cap = 0;
-
-		ctx->osequence = 0;
-		ctx->sequence_offset = 0;
-	}
-
-	if (!ctx->streamon_out && !ctx->streamon_cap) {
-		struct coda_timestamp *ts;
-
-		while (!list_empty(&ctx->timestamp_list)) {
-			ts = list_first_entry(&ctx->timestamp_list,
-					      struct coda_timestamp, list);
-			list_del(&ts->list);
-			kfree(ts);
-		}
-		kfifo_init(&ctx->bitstream_fifo,
-			ctx->bitstream.vaddr, ctx->bitstream.size);
-		ctx->runcounter = 0;
-	}
-}
-
-static struct vb2_ops coda_qops = {
-	.queue_setup		= coda_queue_setup,
-	.buf_prepare		= coda_buf_prepare,
-	.buf_queue		= coda_buf_queue,
-	.start_streaming	= coda_start_streaming,
-	.stop_streaming		= coda_stop_streaming,
-	.wait_prepare		= vb2_ops_wait_prepare,
-	.wait_finish		= vb2_ops_wait_finish,
-};
-
-static int coda_s_ctrl(struct v4l2_ctrl *ctrl)
-{
-	struct coda_ctx *ctx =
-			container_of(ctrl->handler, struct coda_ctx, ctrls);
-
-	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-		 "s_ctrl: id = %d, val = %d\n", ctrl->id, ctrl->val);
-
-	switch (ctrl->id) {
-	case V4L2_CID_HFLIP:
-		if (ctrl->val)
-			ctx->params.rot_mode |= CODA_MIR_HOR;
-		else
-			ctx->params.rot_mode &= ~CODA_MIR_HOR;
-		break;
-	case V4L2_CID_VFLIP:
-		if (ctrl->val)
-			ctx->params.rot_mode |= CODA_MIR_VER;
-		else
-			ctx->params.rot_mode &= ~CODA_MIR_VER;
-		break;
-	case V4L2_CID_MPEG_VIDEO_BITRATE:
-		ctx->params.bitrate = ctrl->val / 1000;
-		break;
-	case V4L2_CID_MPEG_VIDEO_GOP_SIZE:
-		ctx->params.gop_size = ctrl->val;
-		break;
-	case V4L2_CID_MPEG_VIDEO_H264_I_FRAME_QP:
-		ctx->params.h264_intra_qp = ctrl->val;
-		break;
-	case V4L2_CID_MPEG_VIDEO_H264_P_FRAME_QP:
-		ctx->params.h264_inter_qp = ctrl->val;
-		break;
-	case V4L2_CID_MPEG_VIDEO_H264_MIN_QP:
-		ctx->params.h264_min_qp = ctrl->val;
-		break;
-	case V4L2_CID_MPEG_VIDEO_H264_MAX_QP:
-		ctx->params.h264_max_qp = ctrl->val;
-		break;
-	case V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_ALPHA:
-		ctx->params.h264_deblk_alpha = ctrl->val;
-		break;
-	case V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_BETA:
-		ctx->params.h264_deblk_beta = ctrl->val;
-		break;
-	case V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_MODE:
-		ctx->params.h264_deblk_enabled = (ctrl->val ==
-				V4L2_MPEG_VIDEO_H264_LOOP_FILTER_MODE_ENABLED);
-		break;
-	case V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP:
-		ctx->params.mpeg4_intra_qp = ctrl->val;
-		break;
-	case V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP:
-		ctx->params.mpeg4_inter_qp = ctrl->val;
-		break;
-	case V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MODE:
-		ctx->params.slice_mode = ctrl->val;
-		break;
-	case V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MAX_MB:
-		ctx->params.slice_max_mb = ctrl->val;
-		break;
-	case V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MAX_BYTES:
-		ctx->params.slice_max_bits = ctrl->val * 8;
-		break;
-	case V4L2_CID_MPEG_VIDEO_HEADER_MODE:
-		break;
-	case V4L2_CID_MPEG_VIDEO_CYCLIC_INTRA_REFRESH_MB:
-		ctx->params.intra_refresh = ctrl->val;
-		break;
-	default:
-		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-			"Invalid control, id=%d, val=%d\n",
-			ctrl->id, ctrl->val);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static struct v4l2_ctrl_ops coda_ctrl_ops = {
-	.s_ctrl = coda_s_ctrl,
-};
-
-static int coda_ctrls_setup(struct coda_ctx *ctx)
-{
-	v4l2_ctrl_handler_init(&ctx->ctrls, 9);
-
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_HFLIP, 0, 1, 1, 0);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_VFLIP, 0, 1, 1, 0);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_BITRATE, 0, 32767000, 1, 0);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_GOP_SIZE, 1, 60, 1, 16);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_H264_I_FRAME_QP, 0, 51, 1, 25);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_H264_P_FRAME_QP, 0, 51, 1, 25);
-	if (ctx->dev->devtype->product != CODA_960) {
-		v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-			V4L2_CID_MPEG_VIDEO_H264_MIN_QP, 0, 51, 1, 12);
-	}
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_H264_MAX_QP, 0, 51, 1, 51);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_ALPHA, 0, 15, 1, 0);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_BETA, 0, 15, 1, 0);
-	v4l2_ctrl_new_std_menu(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_MODE,
-		V4L2_MPEG_VIDEO_H264_LOOP_FILTER_MODE_DISABLED, 0x0,
-		V4L2_MPEG_VIDEO_H264_LOOP_FILTER_MODE_ENABLED);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP, 1, 31, 1, 2);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP, 1, 31, 1, 2);
-	v4l2_ctrl_new_std_menu(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MODE,
-		V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_BYTES, 0x0,
-		V4L2_MPEG_VIDEO_MULTI_SLICE_MODE_SINGLE);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MAX_MB, 1, 0x3fffffff, 1, 1);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MAX_BYTES, 1, 0x3fffffff, 1, 500);
-	v4l2_ctrl_new_std_menu(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_HEADER_MODE,
-		V4L2_MPEG_VIDEO_HEADER_MODE_JOINED_WITH_1ST_FRAME,
-		(1 << V4L2_MPEG_VIDEO_HEADER_MODE_SEPARATE),
-		V4L2_MPEG_VIDEO_HEADER_MODE_JOINED_WITH_1ST_FRAME);
-	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_CYCLIC_INTRA_REFRESH_MB, 0, 1920 * 1088 / 256, 1, 0);
-
-	if (ctx->ctrls.error) {
-		v4l2_err(&ctx->dev->v4l2_dev, "control initialization error (%d)",
-			ctx->ctrls.error);
-		return -EINVAL;
-	}
-
-	return v4l2_ctrl_handler_setup(&ctx->ctrls);
-}
-
-static int coda_queue_init(void *priv, struct vb2_queue *src_vq,
-		      struct vb2_queue *dst_vq)
-{
-	struct coda_ctx *ctx = priv;
-	int ret;
-
-	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT;
-	src_vq->io_modes = VB2_DMABUF | VB2_MMAP | VB2_USERPTR;
-	src_vq->drv_priv = ctx;
-	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
-	src_vq->ops = &coda_qops;
-	src_vq->mem_ops = &vb2_dma_contig_memops;
-	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
-	src_vq->lock = &ctx->dev->dev_mutex;
-
-	ret = vb2_queue_init(src_vq);
-	if (ret)
-		return ret;
-
-	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	dst_vq->io_modes = VB2_DMABUF | VB2_MMAP | VB2_USERPTR;
-	dst_vq->drv_priv = ctx;
-	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
-	dst_vq->ops = &coda_qops;
-	dst_vq->mem_ops = &vb2_dma_contig_memops;
-	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
-	dst_vq->lock = &ctx->dev->dev_mutex;
-
-	return vb2_queue_init(dst_vq);
-}
-
-static int coda_next_free_instance(struct coda_dev *dev)
-{
-	int idx = ffz(dev->instance_mask);
-
-	if ((idx < 0) ||
-	    (dev->devtype->product == CODA_DX6 && idx > CODADX6_MAX_INSTANCES))
-		return -EBUSY;
-
-	return idx;
-}
-
-static int coda_open(struct file *file)
-{
-	struct coda_dev *dev = video_drvdata(file);
-	struct coda_ctx *ctx = NULL;
-	char *name;
-	int ret;
-	int idx;
-
-	ctx = kzalloc(sizeof *ctx, GFP_KERNEL);
-	if (!ctx)
-		return -ENOMEM;
-
-	idx = coda_next_free_instance(dev);
-	if (idx < 0) {
-		ret = idx;
-		goto err_coda_max;
-	}
-	set_bit(idx, &dev->instance_mask);
-
-	name = kasprintf(GFP_KERNEL, "context%d", idx);
-	ctx->debugfs_entry = debugfs_create_dir(name, dev->debugfs_root);
-	kfree(name);
-
-	init_completion(&ctx->completion);
-	INIT_WORK(&ctx->pic_run_work, coda_pic_run_work);
-	INIT_WORK(&ctx->seq_end_work, coda_seq_end_work);
-	v4l2_fh_init(&ctx->fh, video_devdata(file));
-	file->private_data = &ctx->fh;
-	v4l2_fh_add(&ctx->fh);
-	ctx->dev = dev;
-	ctx->idx = idx;
-	switch (dev->devtype->product) {
-	case CODA_7541:
-	case CODA_960:
-		ctx->reg_idx = 0;
-		break;
-	default:
-		ctx->reg_idx = idx;
-	}
-
-	/* Power up and upload firmware if necessary */
-	ret = pm_runtime_get_sync(&dev->plat_dev->dev);
-	if (ret < 0) {
-		v4l2_err(&dev->v4l2_dev, "failed to power up: %d\n", ret);
-		goto err_pm_get;
-	}
-
-	ret = clk_prepare_enable(dev->clk_per);
-	if (ret)
-		goto err_clk_per;
-
-	ret = clk_prepare_enable(dev->clk_ahb);
-	if (ret)
-		goto err_clk_ahb;
-
-	set_default_params(ctx);
-	ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->m2m_dev, ctx,
-					 &coda_queue_init);
-	if (IS_ERR(ctx->fh.m2m_ctx)) {
-		ret = PTR_ERR(ctx->fh.m2m_ctx);
-
-		v4l2_err(&dev->v4l2_dev, "%s return error (%d)\n",
-			 __func__, ret);
-		goto err_ctx_init;
-	}
-
-	ret = coda_ctrls_setup(ctx);
-	if (ret) {
-		v4l2_err(&dev->v4l2_dev, "failed to setup coda controls\n");
-		goto err_ctrls_setup;
-	}
-
-	ctx->fh.ctrl_handler = &ctx->ctrls;
-
-	ret = coda_alloc_context_buf(ctx, &ctx->parabuf, CODA_PARA_BUF_SIZE,
-				     "parabuf");
-	if (ret < 0) {
-		v4l2_err(&dev->v4l2_dev, "failed to allocate parabuf");
-		goto err_dma_alloc;
-	}
-
-	ctx->bitstream.size = CODA_MAX_FRAME_SIZE;
-	ctx->bitstream.vaddr = dma_alloc_writecombine(&dev->plat_dev->dev,
-			ctx->bitstream.size, &ctx->bitstream.paddr, GFP_KERNEL);
-	if (!ctx->bitstream.vaddr) {
-		v4l2_err(&dev->v4l2_dev, "failed to allocate bitstream ringbuffer");
-		ret = -ENOMEM;
-		goto err_dma_writecombine;
-	}
-	kfifo_init(&ctx->bitstream_fifo,
-		ctx->bitstream.vaddr, ctx->bitstream.size);
-	mutex_init(&ctx->bitstream_mutex);
-	mutex_init(&ctx->buffer_mutex);
-	INIT_LIST_HEAD(&ctx->timestamp_list);
-
-	coda_lock(ctx);
-	list_add(&ctx->list, &dev->instances);
-	coda_unlock(ctx);
-
-	v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "Created instance %d (%p)\n",
-		 ctx->idx, ctx);
-
-	return 0;
-
-err_dma_writecombine:
-	coda_free_context_buffers(ctx);
-	if (ctx->dev->devtype->product == CODA_DX6)
-		coda_free_aux_buf(dev, &ctx->workbuf);
-	coda_free_aux_buf(dev, &ctx->parabuf);
-err_dma_alloc:
-	v4l2_ctrl_handler_free(&ctx->ctrls);
-err_ctrls_setup:
-	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);
-err_ctx_init:
-	clk_disable_unprepare(dev->clk_ahb);
-err_clk_ahb:
-	clk_disable_unprepare(dev->clk_per);
-err_clk_per:
-	pm_runtime_put_sync(&dev->plat_dev->dev);
-err_pm_get:
-	v4l2_fh_del(&ctx->fh);
-	v4l2_fh_exit(&ctx->fh);
-	clear_bit(ctx->idx, &dev->instance_mask);
-err_coda_max:
-	kfree(ctx);
-	return ret;
-}
-
-static int coda_release(struct file *file)
-{
-	struct coda_dev *dev = video_drvdata(file);
-	struct coda_ctx *ctx = fh_to_ctx(file->private_data);
-
-	v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "Releasing instance %p\n",
-		 ctx);
-
-	debugfs_remove_recursive(ctx->debugfs_entry);
-
-	/* If this instance is running, call .job_abort and wait for it to end */
-	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);
-
-	/* In case the instance was not running, we still need to call SEQ_END */
-	if (ctx->initialized) {
-		queue_work(dev->workqueue, &ctx->seq_end_work);
-		flush_work(&ctx->seq_end_work);
-	}
-
-	coda_free_framebuffers(ctx);
-
-	coda_lock(ctx);
-	list_del(&ctx->list);
-	coda_unlock(ctx);
-
-	dma_free_writecombine(&dev->plat_dev->dev, ctx->bitstream.size,
-		ctx->bitstream.vaddr, ctx->bitstream.paddr);
-	coda_free_context_buffers(ctx);
-	if (ctx->dev->devtype->product == CODA_DX6)
-		coda_free_aux_buf(dev, &ctx->workbuf);
-
-	coda_free_aux_buf(dev, &ctx->parabuf);
-	v4l2_ctrl_handler_free(&ctx->ctrls);
-	clk_disable_unprepare(dev->clk_ahb);
-	clk_disable_unprepare(dev->clk_per);
-	pm_runtime_put_sync(&dev->plat_dev->dev);
-	v4l2_fh_del(&ctx->fh);
-	v4l2_fh_exit(&ctx->fh);
-	clear_bit(ctx->idx, &dev->instance_mask);
-	kfree(ctx);
-
-	return 0;
-}
-
-static const struct v4l2_file_operations coda_fops = {
-	.owner		= THIS_MODULE,
-	.open		= coda_open,
-	.release	= coda_release,
-	.poll		= v4l2_m2m_fop_poll,
-	.unlocked_ioctl	= video_ioctl2,
-	.mmap		= v4l2_m2m_fop_mmap,
-};
-
-static void coda_finish_decode(struct coda_ctx *ctx)
-{
-	struct coda_dev *dev = ctx->dev;
-	struct coda_q_data *q_data_src;
-	struct coda_q_data *q_data_dst;
-	struct vb2_buffer *dst_buf;
-	struct coda_timestamp *ts;
-	int width, height;
-	int decoded_idx;
-	int display_idx;
-	u32 src_fourcc;
-	int success;
-	u32 err_mb;
-	u32 val;
-
-	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
-
-	/* Update kfifo out pointer from coda bitstream read pointer */
-	coda_kfifo_sync_from_device(ctx);
-
-	/*
-	 * in stream-end mode, the read pointer can overshoot the write pointer
-	 * by up to 512 bytes
-	 */
-	if (ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG) {
-		if (coda_get_bitstream_payload(ctx) >= 0x100000 - 512)
-			kfifo_init(&ctx->bitstream_fifo,
-				ctx->bitstream.vaddr, ctx->bitstream.size);
-	}
-
-	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-	src_fourcc = q_data_src->fourcc;
-
-	val = coda_read(dev, CODA_RET_DEC_PIC_SUCCESS);
-	if (val != 1)
-		pr_err("DEC_PIC_SUCCESS = %d\n", val);
-
-	success = val & 0x1;
-	if (!success)
-		v4l2_err(&dev->v4l2_dev, "decode failed\n");
-
-	if (src_fourcc == V4L2_PIX_FMT_H264) {
-		if (val & (1 << 3))
-			v4l2_err(&dev->v4l2_dev,
-				 "insufficient PS buffer space (%d bytes)\n",
-				 ctx->psbuf.size);
-		if (val & (1 << 2))
-			v4l2_err(&dev->v4l2_dev,
-				 "insufficient slice buffer space (%d bytes)\n",
-				 ctx->slicebuf.size);
-	}
-
-	val = coda_read(dev, CODA_RET_DEC_PIC_SIZE);
-	width = (val >> 16) & 0xffff;
-	height = val & 0xffff;
-
-	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
-
-	/* frame crop information */
-	if (src_fourcc == V4L2_PIX_FMT_H264) {
-		u32 left_right;
-		u32 top_bottom;
-
-		left_right = coda_read(dev, CODA_RET_DEC_PIC_CROP_LEFT_RIGHT);
-		top_bottom = coda_read(dev, CODA_RET_DEC_PIC_CROP_TOP_BOTTOM);
-
-		if (left_right == 0xffffffff && top_bottom == 0xffffffff) {
-			/* Keep current crop information */
-		} else {
-			struct v4l2_rect *rect = &q_data_dst->rect;
-
-			rect->left = left_right >> 16 & 0xffff;
-			rect->top = top_bottom >> 16 & 0xffff;
-			rect->width = width - rect->left -
-				      (left_right & 0xffff);
-			rect->height = height - rect->top -
-				       (top_bottom & 0xffff);
-		}
-	} else {
-		/* no cropping */
-	}
-
-	err_mb = coda_read(dev, CODA_RET_DEC_PIC_ERR_MB);
-	if (err_mb > 0)
-		v4l2_err(&dev->v4l2_dev,
-			 "errors in %d macroblocks\n", err_mb);
-
-	if (dev->devtype->product == CODA_7541) {
-		val = coda_read(dev, CODA_RET_DEC_PIC_OPTION);
-		if (val == 0) {
-			/* not enough bitstream data */
-			v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
-				 "prescan failed: %d\n", val);
-			ctx->hold = true;
-			return;
-		}
-	}
-
-	ctx->frm_dis_flg = coda_read(dev, CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));
-
-	/*
-	 * The previous display frame was copied out by the rotator,
-	 * now it can be overwritten again
-	 */
-	if (ctx->display_idx >= 0 &&
-	    ctx->display_idx < ctx->num_internal_frames) {
-		ctx->frm_dis_flg &= ~(1 << ctx->display_idx);
-		coda_write(dev, ctx->frm_dis_flg,
-				CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));
-	}
-
-	/*
-	 * The index of the last decoded frame, not necessarily in
-	 * display order, and the index of the next display frame.
-	 * The latter could have been decoded in a previous run.
-	 */
-	decoded_idx = coda_read(dev, CODA_RET_DEC_PIC_CUR_IDX);
-	display_idx = coda_read(dev, CODA_RET_DEC_PIC_FRAME_IDX);
-
-	if (decoded_idx == -1) {
-		/* no frame was decoded, but we might have a display frame */
-		if (display_idx >= 0 && display_idx < ctx->num_internal_frames)
-			ctx->sequence_offset++;
-		else if (ctx->display_idx < 0)
-			ctx->hold = true;
-	} else if (decoded_idx == -2) {
-		/* no frame was decoded, we still return the remaining buffers */
-	} else if (decoded_idx < 0 || decoded_idx >= ctx->num_internal_frames) {
-		v4l2_err(&dev->v4l2_dev,
-			 "decoded frame index out of range: %d\n", decoded_idx);
-	} else {
-		ts = list_first_entry(&ctx->timestamp_list,
-				      struct coda_timestamp, list);
-		list_del(&ts->list);
-		val = coda_read(dev, CODA_RET_DEC_PIC_FRAME_NUM) - 1;
-		val -= ctx->sequence_offset;
-		if (val != (ts->sequence & 0xffff)) {
-			v4l2_err(&dev->v4l2_dev,
-				 "sequence number mismatch (%d(%d) != %d)\n",
-				 val, ctx->sequence_offset, ts->sequence);
-		}
-		ctx->frame_timestamps[decoded_idx] = *ts;
-		kfree(ts);
-
-		val = coda_read(dev, CODA_RET_DEC_PIC_TYPE) & 0x7;
-		if (val == 0)
-			ctx->frame_types[decoded_idx] = V4L2_BUF_FLAG_KEYFRAME;
-		else if (val == 1)
-			ctx->frame_types[decoded_idx] = V4L2_BUF_FLAG_PFRAME;
-		else
-			ctx->frame_types[decoded_idx] = V4L2_BUF_FLAG_BFRAME;
-
-		ctx->frame_errors[decoded_idx] = err_mb;
-	}
-
-	if (display_idx == -1) {
-		/*
-		 * no more frames to be decoded, but there could still
-		 * be rotator output to dequeue
-		 */
-		ctx->hold = true;
-	} else if (display_idx == -3) {
-		/* possibly prescan failure */
-	} else if (display_idx < 0 || display_idx >= ctx->num_internal_frames) {
-		v4l2_err(&dev->v4l2_dev,
-			 "presentation frame index out of range: %d\n",
-			 display_idx);
-	}
-
-	/* If a frame was copied out, return it */
-	if (ctx->display_idx >= 0 &&
-	    ctx->display_idx < ctx->num_internal_frames) {
-		dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
-		dst_buf->v4l2_buf.sequence = ctx->osequence++;
-
-		dst_buf->v4l2_buf.flags &= ~(V4L2_BUF_FLAG_KEYFRAME |
-					     V4L2_BUF_FLAG_PFRAME |
-					     V4L2_BUF_FLAG_BFRAME);
-		dst_buf->v4l2_buf.flags |= ctx->frame_types[ctx->display_idx];
-		ts = &ctx->frame_timestamps[ctx->display_idx];
-		dst_buf->v4l2_buf.timecode = ts->timecode;
-		dst_buf->v4l2_buf.timestamp = ts->timestamp;
-
-		vb2_set_plane_payload(dst_buf, 0, width * height * 3 / 2);
-
-		v4l2_m2m_buf_done(dst_buf, ctx->frame_errors[display_idx] ?
-				  VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
-
-		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
-			"job finished: decoding frame (%d) (%s)\n",
-			dst_buf->v4l2_buf.sequence,
-			(dst_buf->v4l2_buf.flags & V4L2_BUF_FLAG_KEYFRAME) ?
-			"KEYFRAME" : "PFRAME");
-	} else {
-		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
-			"job finished: no frame decoded\n");
-	}
-
-	/* The rotator will copy the current display frame next time */
-	ctx->display_idx = display_idx;
-}
-
-static void coda_finish_encode(struct coda_ctx *ctx)
-{
-	struct vb2_buffer *src_buf, *dst_buf;
-	struct coda_dev *dev = ctx->dev;
-	u32 wr_ptr, start_ptr;
-
-	src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
-	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
-
-	/* Get results from the coda */
-	start_ptr = coda_read(dev, CODA_CMD_ENC_PIC_BB_START);
-	wr_ptr = coda_read(dev, CODA_REG_BIT_WR_PTR(ctx->reg_idx));
-
-	/* Calculate bytesused field */
-	if (dst_buf->v4l2_buf.sequence == 0) {
-		vb2_set_plane_payload(dst_buf, 0, wr_ptr - start_ptr +
-					ctx->vpu_header_size[0] +
-					ctx->vpu_header_size[1] +
-					ctx->vpu_header_size[2]);
-	} else {
-		vb2_set_plane_payload(dst_buf, 0, wr_ptr - start_ptr);
-	}
-
-	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev, "frame size = %u\n",
-		 wr_ptr - start_ptr);
-
-	coda_read(dev, CODA_RET_ENC_PIC_SLICE_NUM);
-	coda_read(dev, CODA_RET_ENC_PIC_FLAG);
-
-	if (coda_read(dev, CODA_RET_ENC_PIC_TYPE) == 0) {
-		dst_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_KEYFRAME;
-		dst_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_PFRAME;
-	} else {
-		dst_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_PFRAME;
-		dst_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_KEYFRAME;
-	}
-
-	dst_buf->v4l2_buf.timestamp = src_buf->v4l2_buf.timestamp;
-	dst_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
-	dst_buf->v4l2_buf.flags |=
-		src_buf->v4l2_buf.flags & V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
-	dst_buf->v4l2_buf.timecode = src_buf->v4l2_buf.timecode;
-
-	v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE);
-
-	dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
-	v4l2_m2m_buf_done(dst_buf, VB2_BUF_STATE_DONE);
-
-	ctx->gopcounter--;
-	if (ctx->gopcounter < 0)
-		ctx->gopcounter = ctx->params.gop_size - 1;
-
-	v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
-		"job finished: encoding frame (%d) (%s)\n",
-		dst_buf->v4l2_buf.sequence,
-		(dst_buf->v4l2_buf.flags & V4L2_BUF_FLAG_KEYFRAME) ?
-		"KEYFRAME" : "PFRAME");
-}
-
-static irqreturn_t coda_irq_handler(int irq, void *data)
-{
-	struct coda_dev *dev = data;
-	struct coda_ctx *ctx;
-
-	/* read status register to attend the IRQ */
-	coda_read(dev, CODA_REG_BIT_INT_STATUS);
-	coda_write(dev, CODA_REG_BIT_INT_CLEAR_SET,
-		      CODA_REG_BIT_INT_CLEAR);
-
-	ctx = v4l2_m2m_get_curr_priv(dev->m2m_dev);
-	if (ctx == NULL) {
-		v4l2_err(&dev->v4l2_dev, "Instance released before the end of transaction\n");
-		mutex_unlock(&dev->coda_mutex);
-		return IRQ_HANDLED;
-	}
-
-	if (ctx->aborting) {
-		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-			 "task has been aborted\n");
-	}
-
-	if (coda_isbusy(ctx->dev)) {
-		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
-			 "coda is still busy!!!!\n");
-		return IRQ_NONE;
-	}
-
-	complete(&ctx->completion);
-
-	return IRQ_HANDLED;
-}
-
-static u32 coda_supported_firmwares[] = {
-	CODA_FIRMWARE_VERNUM(CODA_DX6, 2, 2, 5),
-	CODA_FIRMWARE_VERNUM(CODA_7541, 1, 4, 50),
-	CODA_FIRMWARE_VERNUM(CODA_960, 2, 1, 5),
-};
-
-static bool coda_firmware_supported(u32 vernum)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(coda_supported_firmwares); i++)
-		if (vernum == coda_supported_firmwares[i])
-			return true;
-	return false;
-}
-
-static int coda_hw_init(struct coda_dev *dev)
-{
-	u32 data;
-	u16 *p;
-	int i, ret;
-
-	ret = clk_prepare_enable(dev->clk_per);
-	if (ret)
-		goto err_clk_per;
-
-	ret = clk_prepare_enable(dev->clk_ahb);
-	if (ret)
-		goto err_clk_ahb;
-
-	if (dev->rstc)
-		reset_control_reset(dev->rstc);
-
-	/*
-	 * Copy the first CODA_ISRAM_SIZE in the internal SRAM.
-	 * The 16-bit chars in the code buffer are in memory access
-	 * order, re-sort them to CODA order for register download.
-	 * Data in this SRAM survives a reboot.
-	 */
-	p = (u16 *)dev->codebuf.vaddr;
-	if (dev->devtype->product == CODA_DX6) {
-		for (i = 0; i < (CODA_ISRAM_SIZE / 2); i++)  {
-			data = CODA_DOWN_ADDRESS_SET(i) |
-				CODA_DOWN_DATA_SET(p[i ^ 1]);
-			coda_write(dev, data, CODA_REG_BIT_CODE_DOWN);
-		}
-	} else {
-		for (i = 0; i < (CODA_ISRAM_SIZE / 2); i++) {
-			data = CODA_DOWN_ADDRESS_SET(i) |
-				CODA_DOWN_DATA_SET(p[round_down(i, 4) +
-							3 - (i % 4)]);
-			coda_write(dev, data, CODA_REG_BIT_CODE_DOWN);
-		}
-	}
-
-	/* Clear registers */
-	for (i = 0; i < 64; i++)
-		coda_write(dev, 0, CODA_REG_BIT_CODE_BUF_ADDR + i * 4);
-
-	/* Tell the BIT where to find everything it needs */
-	if (dev->devtype->product == CODA_960 ||
-	    dev->devtype->product == CODA_7541) {
-		coda_write(dev, dev->tempbuf.paddr,
-				CODA_REG_BIT_TEMP_BUF_ADDR);
-		coda_write(dev, 0, CODA_REG_BIT_BIT_STREAM_PARAM);
-	} else {
-		coda_write(dev, dev->workbuf.paddr,
-			      CODA_REG_BIT_WORK_BUF_ADDR);
-	}
-	coda_write(dev, dev->codebuf.paddr,
-		      CODA_REG_BIT_CODE_BUF_ADDR);
-	coda_write(dev, 0, CODA_REG_BIT_CODE_RUN);
-
-	/* Set default values */
-	switch (dev->devtype->product) {
-	case CODA_DX6:
-		coda_write(dev, CODADX6_STREAM_BUF_PIC_FLUSH, CODA_REG_BIT_STREAM_CTRL);
-		break;
-	default:
-		coda_write(dev, CODA7_STREAM_BUF_PIC_FLUSH, CODA_REG_BIT_STREAM_CTRL);
-	}
-	if (dev->devtype->product == CODA_960)
-		coda_write(dev, 1 << 12, CODA_REG_BIT_FRAME_MEM_CTRL);
-	else
-		coda_write(dev, 0, CODA_REG_BIT_FRAME_MEM_CTRL);
-
-	if (dev->devtype->product != CODA_DX6)
-		coda_write(dev, 0, CODA7_REG_BIT_AXI_SRAM_USE);
-
-	coda_write(dev, CODA_INT_INTERRUPT_ENABLE,
-		      CODA_REG_BIT_INT_ENABLE);
-
-	/* Reset VPU and start processor */
-	data = coda_read(dev, CODA_REG_BIT_CODE_RESET);
-	data |= CODA_REG_RESET_ENABLE;
-	coda_write(dev, data, CODA_REG_BIT_CODE_RESET);
-	udelay(10);
-	data &= ~CODA_REG_RESET_ENABLE;
-	coda_write(dev, data, CODA_REG_BIT_CODE_RESET);
-	coda_write(dev, CODA_REG_RUN_ENABLE, CODA_REG_BIT_CODE_RUN);
-
-	clk_disable_unprepare(dev->clk_ahb);
-	clk_disable_unprepare(dev->clk_per);
-
-	return 0;
-
-err_clk_ahb:
-	clk_disable_unprepare(dev->clk_per);
-err_clk_per:
-	return ret;
-}
-
-static int coda_check_firmware(struct coda_dev *dev)
-{
-	u16 product, major, minor, release;
-	u32 data;
-	int ret;
-
-	ret = clk_prepare_enable(dev->clk_per);
-	if (ret)
-		goto err_clk_per;
-
-	ret = clk_prepare_enable(dev->clk_ahb);
-	if (ret)
-		goto err_clk_ahb;
-
-	coda_write(dev, 0, CODA_CMD_FIRMWARE_VERNUM);
-	coda_write(dev, CODA_REG_BIT_BUSY_FLAG, CODA_REG_BIT_BUSY);
-	coda_write(dev, 0, CODA_REG_BIT_RUN_INDEX);
-	coda_write(dev, 0, CODA_REG_BIT_RUN_COD_STD);
-	coda_write(dev, CODA_COMMAND_FIRMWARE_GET, CODA_REG_BIT_RUN_COMMAND);
-	if (coda_wait_timeout(dev)) {
-		v4l2_err(&dev->v4l2_dev, "firmware get command error\n");
-		ret = -EIO;
-		goto err_run_cmd;
-	}
-
-	if (dev->devtype->product == CODA_960) {
-		data = coda_read(dev, CODA9_CMD_FIRMWARE_CODE_REV);
-		v4l2_info(&dev->v4l2_dev, "Firmware code revision: %d\n",
-			  data);
-	}
-
-	/* Check we are compatible with the loaded firmware */
-	data = coda_read(dev, CODA_CMD_FIRMWARE_VERNUM);
-	product = CODA_FIRMWARE_PRODUCT(data);
-	major = CODA_FIRMWARE_MAJOR(data);
-	minor = CODA_FIRMWARE_MINOR(data);
-	release = CODA_FIRMWARE_RELEASE(data);
-
-	clk_disable_unprepare(dev->clk_per);
-	clk_disable_unprepare(dev->clk_ahb);
-
-	if (product != dev->devtype->product) {
-		v4l2_err(&dev->v4l2_dev, "Wrong firmware. Hw: %s, Fw: %s,"
-			 " Version: %u.%u.%u\n",
-			 coda_product_name(dev->devtype->product),
-			 coda_product_name(product), major, minor, release);
-		return -EINVAL;
-	}
-
-	v4l2_info(&dev->v4l2_dev, "Initialized %s.\n",
-		  coda_product_name(product));
-
-	if (coda_firmware_supported(data)) {
-		v4l2_info(&dev->v4l2_dev, "Firmware version: %u.%u.%u\n",
-			  major, minor, release);
-	} else {
-		v4l2_warn(&dev->v4l2_dev, "Unsupported firmware version: "
-			  "%u.%u.%u\n", major, minor, release);
-	}
-
-	return 0;
-
-err_run_cmd:
-	clk_disable_unprepare(dev->clk_ahb);
-err_clk_ahb:
-	clk_disable_unprepare(dev->clk_per);
-err_clk_per:
-	return ret;
-}
-
-static void coda_fw_callback(const struct firmware *fw, void *context)
-{
-	struct coda_dev *dev = context;
-	struct platform_device *pdev = dev->plat_dev;
-	int ret;
-
-	if (!fw) {
-		v4l2_err(&dev->v4l2_dev, "firmware request failed\n");
-		return;
-	}
-
-	/* allocate auxiliary per-device code buffer for the BIT processor */
-	ret = coda_alloc_aux_buf(dev, &dev->codebuf, fw->size, "codebuf",
-				 dev->debugfs_root);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to allocate code buffer\n");
-		return;
-	}
-
-	/* Copy the whole firmware image to the code buffer */
-	memcpy(dev->codebuf.vaddr, fw->data, fw->size);
-	release_firmware(fw);
-
-	if (pm_runtime_enabled(&pdev->dev) && pdev->dev.pm_domain) {
-		/*
-		 * Enabling power temporarily will cause coda_hw_init to be
-		 * called via coda_runtime_resume by the pm domain.
-		 */
-		ret = pm_runtime_get_sync(&dev->plat_dev->dev);
-		if (ret < 0) {
-			v4l2_err(&dev->v4l2_dev, "failed to power on: %d\n",
-				 ret);
-			return;
-		}
-
-		ret = coda_check_firmware(dev);
-		if (ret < 0)
-			return;
-
-		pm_runtime_put_sync(&dev->plat_dev->dev);
-	} else {
-		/*
-		 * If runtime pm is disabled or pm_domain is not set,
-		 * initialize once manually.
-		 */
-		ret = coda_hw_init(dev);
-		if (ret < 0) {
-			v4l2_err(&dev->v4l2_dev, "HW initialization failed\n");
-			return;
-		}
-
-		ret = coda_check_firmware(dev);
-		if (ret < 0)
-			return;
-	}
-
-	dev->vfd.fops	= &coda_fops,
-	dev->vfd.ioctl_ops	= &coda_ioctl_ops;
-	dev->vfd.release	= video_device_release_empty,
-	dev->vfd.lock	= &dev->dev_mutex;
-	dev->vfd.v4l2_dev	= &dev->v4l2_dev;
-	dev->vfd.vfl_dir	= VFL_DIR_M2M;
-	snprintf(dev->vfd.name, sizeof(dev->vfd.name), "%s", CODA_NAME);
-	video_set_drvdata(&dev->vfd, dev);
-
-	dev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
-	if (IS_ERR(dev->alloc_ctx)) {
-		v4l2_err(&dev->v4l2_dev, "Failed to alloc vb2 context\n");
-		return;
-	}
-
-	dev->m2m_dev = v4l2_m2m_init(&coda_m2m_ops);
-	if (IS_ERR(dev->m2m_dev)) {
-		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem device\n");
-		goto rel_ctx;
-	}
-
-	ret = video_register_device(&dev->vfd, VFL_TYPE_GRABBER, 0);
-	if (ret) {
-		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
-		goto rel_m2m;
-	}
-	v4l2_info(&dev->v4l2_dev, "codec registered as /dev/video%d\n",
-		  dev->vfd.num);
-
-	return;
-
-rel_m2m:
-	v4l2_m2m_release(dev->m2m_dev);
-rel_ctx:
-	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
-}
-
-static int coda_firmware_request(struct coda_dev *dev)
-{
-	char *fw = dev->devtype->firmware;
-
-	dev_dbg(&dev->plat_dev->dev, "requesting firmware '%s' for %s\n", fw,
-		coda_product_name(dev->devtype->product));
-
-	return request_firmware_nowait(THIS_MODULE, true,
-		fw, &dev->plat_dev->dev, GFP_KERNEL, dev, coda_fw_callback);
-}
-
-enum coda_platform {
-	CODA_IMX27,
-	CODA_IMX53,
-	CODA_IMX6Q,
-	CODA_IMX6DL,
-};
-
-static const struct coda_devtype coda_devdata[] = {
-	[CODA_IMX27] = {
-		.firmware     = "v4l-codadx6-imx27.bin",
-		.product      = CODA_DX6,
-		.codecs       = codadx6_codecs,
-		.num_codecs   = ARRAY_SIZE(codadx6_codecs),
-		.workbuf_size = 288 * 1024 + FMO_SLICE_SAVE_BUF_SIZE * 8 * 1024,
-		.iram_size    = 0xb000,
-	},
-	[CODA_IMX53] = {
-		.firmware     = "v4l-coda7541-imx53.bin",
-		.product      = CODA_7541,
-		.codecs       = coda7_codecs,
-		.num_codecs   = ARRAY_SIZE(coda7_codecs),
-		.workbuf_size = 128 * 1024,
-		.tempbuf_size = 304 * 1024,
-		.iram_size    = 0x14000,
-	},
-	[CODA_IMX6Q] = {
-		.firmware     = "v4l-coda960-imx6q.bin",
-		.product      = CODA_960,
-		.codecs       = coda9_codecs,
-		.num_codecs   = ARRAY_SIZE(coda9_codecs),
-		.workbuf_size = 80 * 1024,
-		.tempbuf_size = 204 * 1024,
-		.iram_size    = 0x21000,
-	},
-	[CODA_IMX6DL] = {
-		.firmware     = "v4l-coda960-imx6dl.bin",
-		.product      = CODA_960,
-		.codecs       = coda9_codecs,
-		.num_codecs   = ARRAY_SIZE(coda9_codecs),
-		.workbuf_size = 80 * 1024,
-		.tempbuf_size = 204 * 1024,
-		.iram_size    = 0x20000,
-	},
-};
-
-static struct platform_device_id coda_platform_ids[] = {
-	{ .name = "coda-imx27", .driver_data = CODA_IMX27 },
-	{ .name = "coda-imx53", .driver_data = CODA_IMX53 },
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(platform, coda_platform_ids);
-
-#ifdef CONFIG_OF
-static const struct of_device_id coda_dt_ids[] = {
-	{ .compatible = "fsl,imx27-vpu", .data = &coda_devdata[CODA_IMX27] },
-	{ .compatible = "fsl,imx53-vpu", .data = &coda_devdata[CODA_IMX53] },
-	{ .compatible = "fsl,imx6q-vpu", .data = &coda_devdata[CODA_IMX6Q] },
-	{ .compatible = "fsl,imx6dl-vpu", .data = &coda_devdata[CODA_IMX6DL] },
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(of, coda_dt_ids);
-#endif
-
-static int coda_probe(struct platform_device *pdev)
-{
-	const struct of_device_id *of_id =
-			of_match_device(of_match_ptr(coda_dt_ids), &pdev->dev);
-	const struct platform_device_id *pdev_id;
-	struct coda_platform_data *pdata = pdev->dev.platform_data;
-	struct device_node *np = pdev->dev.of_node;
-	struct gen_pool *pool;
-	struct coda_dev *dev;
-	struct resource *res;
-	int ret, irq;
-
-	dev = devm_kzalloc(&pdev->dev, sizeof *dev, GFP_KERNEL);
-	if (!dev) {
-		dev_err(&pdev->dev, "Not enough memory for %s\n",
-			CODA_NAME);
-		return -ENOMEM;
-	}
-
-	spin_lock_init(&dev->irqlock);
-	INIT_LIST_HEAD(&dev->instances);
-
-	dev->plat_dev = pdev;
-	dev->clk_per = devm_clk_get(&pdev->dev, "per");
-	if (IS_ERR(dev->clk_per)) {
-		dev_err(&pdev->dev, "Could not get per clock\n");
-		return PTR_ERR(dev->clk_per);
-	}
-
-	dev->clk_ahb = devm_clk_get(&pdev->dev, "ahb");
-	if (IS_ERR(dev->clk_ahb)) {
-		dev_err(&pdev->dev, "Could not get ahb clock\n");
-		return PTR_ERR(dev->clk_ahb);
-	}
-
-	/* Get  memory for physical registers */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	dev->regs_base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(dev->regs_base))
-		return PTR_ERR(dev->regs_base);
-
-	/* IRQ */
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "failed to get irq resource\n");
-		return irq;
-	}
-
-	ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, coda_irq_handler,
-			IRQF_ONESHOT, dev_name(&pdev->dev), dev);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to request irq: %d\n", ret);
-		return ret;
-	}
-
-	dev->rstc = devm_reset_control_get_optional(&pdev->dev, NULL);
-	if (IS_ERR(dev->rstc)) {
-		ret = PTR_ERR(dev->rstc);
-		if (ret == -ENOENT || ret == -ENOSYS) {
-			dev->rstc = NULL;
-		} else {
-			dev_err(&pdev->dev, "failed get reset control: %d\n", ret);
-			return ret;
-		}
-	}
-
-	/* Get IRAM pool from device tree or platform data */
-	pool = of_get_named_gen_pool(np, "iram", 0);
-	if (!pool && pdata)
-		pool = dev_get_gen_pool(pdata->iram_dev);
-	if (!pool) {
-		dev_err(&pdev->dev, "iram pool not available\n");
-		return -ENOMEM;
-	}
-	dev->iram_pool = pool;
-
-	ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev);
-	if (ret)
-		return ret;
-
-	mutex_init(&dev->dev_mutex);
-	mutex_init(&dev->coda_mutex);
-
-	pdev_id = of_id ? of_id->data : platform_get_device_id(pdev);
-
-	if (of_id) {
-		dev->devtype = of_id->data;
-	} else if (pdev_id) {
-		dev->devtype = &coda_devdata[pdev_id->driver_data];
-	} else {
-		v4l2_device_unregister(&dev->v4l2_dev);
-		return -EINVAL;
-	}
-
-	dev->debugfs_root = debugfs_create_dir("coda", NULL);
-	if (!dev->debugfs_root)
-		dev_warn(&pdev->dev, "failed to create debugfs root\n");
-
-	/* allocate auxiliary per-device buffers for the BIT processor */
-	if (dev->devtype->product == CODA_DX6) {
-		ret = coda_alloc_aux_buf(dev, &dev->workbuf,
-					 dev->devtype->workbuf_size, "workbuf",
-					 dev->debugfs_root);
-		if (ret < 0) {
-			dev_err(&pdev->dev, "failed to allocate work buffer\n");
-			v4l2_device_unregister(&dev->v4l2_dev);
-			return ret;
-		}
-	}
-
-	if (dev->devtype->tempbuf_size) {
-		ret = coda_alloc_aux_buf(dev, &dev->tempbuf,
-					 dev->devtype->tempbuf_size, "tempbuf",
-					 dev->debugfs_root);
-		if (ret < 0) {
-			dev_err(&pdev->dev, "failed to allocate temp buffer\n");
-			v4l2_device_unregister(&dev->v4l2_dev);
-			return ret;
-		}
-	}
-
-	dev->iram.size = dev->devtype->iram_size;
-	dev->iram.vaddr = gen_pool_dma_alloc(dev->iram_pool, dev->iram.size,
-					     &dev->iram.paddr);
-	if (!dev->iram.vaddr) {
-		dev_err(&pdev->dev, "unable to alloc iram\n");
-		return -ENOMEM;
-	}
-
-	dev->iram.blob.data = dev->iram.vaddr;
-	dev->iram.blob.size = dev->iram.size;
-	dev->iram.dentry = debugfs_create_blob("iram", 0644, dev->debugfs_root,
-					       &dev->iram.blob);
-
-	dev->workqueue = alloc_workqueue("coda", WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
-	if (!dev->workqueue) {
-		dev_err(&pdev->dev, "unable to alloc workqueue\n");
-		return -ENOMEM;
-	}
-
-	platform_set_drvdata(pdev, dev);
-
-	pm_runtime_enable(&pdev->dev);
-
-	return coda_firmware_request(dev);
-}
-
-static int coda_remove(struct platform_device *pdev)
-{
-	struct coda_dev *dev = platform_get_drvdata(pdev);
-
-	video_unregister_device(&dev->vfd);
-	if (dev->m2m_dev)
-		v4l2_m2m_release(dev->m2m_dev);
-	pm_runtime_disable(&pdev->dev);
-	if (dev->alloc_ctx)
-		vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
-	v4l2_device_unregister(&dev->v4l2_dev);
-	destroy_workqueue(dev->workqueue);
-	if (dev->iram.vaddr)
-		gen_pool_free(dev->iram_pool, (unsigned long)dev->iram.vaddr,
-			      dev->iram.size);
-	coda_free_aux_buf(dev, &dev->codebuf);
-	coda_free_aux_buf(dev, &dev->tempbuf);
-	coda_free_aux_buf(dev, &dev->workbuf);
-	debugfs_remove_recursive(dev->debugfs_root);
-	return 0;
-}
-
-#ifdef CONFIG_PM_RUNTIME
-static int coda_runtime_resume(struct device *dev)
-{
-	struct coda_dev *cdev = dev_get_drvdata(dev);
-	int ret = 0;
-
-	if (dev->pm_domain) {
-		ret = coda_hw_init(cdev);
-		if (ret)
-			v4l2_err(&cdev->v4l2_dev, "HW initialization failed\n");
-	}
-
-	return ret;
-}
-#endif
-
-static const struct dev_pm_ops coda_pm_ops = {
-	SET_RUNTIME_PM_OPS(NULL, coda_runtime_resume, NULL)
-};
-
-static struct platform_driver coda_driver = {
-	.probe	= coda_probe,
-	.remove	= coda_remove,
-	.driver	= {
-		.name	= CODA_NAME,
-		.owner	= THIS_MODULE,
-		.of_match_table = of_match_ptr(coda_dt_ids),
-		.pm	= &coda_pm_ops,
-	},
-	.id_table = coda_platform_ids,
-};
-
-module_platform_driver(coda_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Javier Martin <javier.martin@vista-silicon.com>");
-MODULE_DESCRIPTION("Coda multi-standard codec V4L2 driver");
diff --git a/drivers/media/platform/coda/Makefile b/drivers/media/platform/coda/Makefile
new file mode 100644
index 000000000000..3543291e6273
--- /dev/null
+++ b/drivers/media/platform/coda/Makefile
@@ -0,0 +1,3 @@
+coda-objs := coda-common.o coda-bit.o coda-h264.o
+
+obj-$(CONFIG_VIDEO_CODA) += coda.o
diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
new file mode 100644
index 000000000000..9b8ea8bbeb4e
--- /dev/null
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -0,0 +1,1861 @@
+/*
+ * Coda multi-standard codec IP - BIT processor functions
+ *
+ * Copyright (C) 2012 Vista Silicon S.L.
+ *    Javier Martin, <javier.martin@vista-silicon.com>
+ *    Xavier Duret
+ * Copyright (C) 2012-2014 Philipp Zabel, Pengutronix
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/irqreturn.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/slab.h>
+#include <linux/videodev2.h>
+
+#include <media/v4l2-common.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-dma-contig.h>
+#include <media/videobuf2-vmalloc.h>
+
+#include "coda.h"
+
+#define CODA7_PS_BUF_SIZE	0x28000
+#define CODA9_PS_SAVE_SIZE	(512 * 1024)
+
+#define CODA_DEFAULT_GAMMA	4096
+#define CODA9_DEFAULT_GAMMA	24576	/* 0.75 * 32768 */
+
+static inline int coda_is_initialized(struct coda_dev *dev)
+{
+	return coda_read(dev, CODA_REG_BIT_CUR_PC) != 0;
+}
+
+static inline unsigned long coda_isbusy(struct coda_dev *dev)
+{
+	return coda_read(dev, CODA_REG_BIT_BUSY);
+}
+
+static int coda_wait_timeout(struct coda_dev *dev)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(1000);
+
+	while (coda_isbusy(dev)) {
+		if (time_after(jiffies, timeout))
+			return -ETIMEDOUT;
+	}
+	return 0;
+}
+
+static void coda_command_async(struct coda_ctx *ctx, int cmd)
+{
+	struct coda_dev *dev = ctx->dev;
+
+	if (dev->devtype->product == CODA_960 ||
+	    dev->devtype->product == CODA_7541) {
+		/* Restore context related registers to CODA */
+		coda_write(dev, ctx->bit_stream_param,
+				CODA_REG_BIT_BIT_STREAM_PARAM);
+		coda_write(dev, ctx->frm_dis_flg,
+				CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));
+		coda_write(dev, ctx->frame_mem_ctrl,
+				CODA_REG_BIT_FRAME_MEM_CTRL);
+		coda_write(dev, ctx->workbuf.paddr, CODA_REG_BIT_WORK_BUF_ADDR);
+	}
+
+	if (dev->devtype->product == CODA_960) {
+		coda_write(dev, 1, CODA9_GDI_WPROT_ERR_CLR);
+		coda_write(dev, 0, CODA9_GDI_WPROT_RGN_EN);
+	}
+
+	coda_write(dev, CODA_REG_BIT_BUSY_FLAG, CODA_REG_BIT_BUSY);
+
+	coda_write(dev, ctx->idx, CODA_REG_BIT_RUN_INDEX);
+	coda_write(dev, ctx->params.codec_mode, CODA_REG_BIT_RUN_COD_STD);
+	coda_write(dev, ctx->params.codec_mode_aux, CODA7_REG_BIT_RUN_AUX_STD);
+
+	coda_write(dev, cmd, CODA_REG_BIT_RUN_COMMAND);
+}
+
+static int coda_command_sync(struct coda_ctx *ctx, int cmd)
+{
+	struct coda_dev *dev = ctx->dev;
+
+	coda_command_async(ctx, cmd);
+	return coda_wait_timeout(dev);
+}
+
+int coda_hw_reset(struct coda_ctx *ctx)
+{
+	struct coda_dev *dev = ctx->dev;
+	unsigned long timeout;
+	unsigned int idx;
+	int ret;
+
+	if (!dev->rstc)
+		return -ENOENT;
+
+	idx = coda_read(dev, CODA_REG_BIT_RUN_INDEX);
+
+	if (dev->devtype->product == CODA_960) {
+		timeout = jiffies + msecs_to_jiffies(100);
+		coda_write(dev, 0x11, CODA9_GDI_BUS_CTRL);
+		while (coda_read(dev, CODA9_GDI_BUS_STATUS) != 0x77) {
+			if (time_after(jiffies, timeout))
+				return -ETIME;
+			cpu_relax();
+		}
+	}
+
+	ret = reset_control_reset(dev->rstc);
+	if (ret < 0)
+		return ret;
+
+	if (dev->devtype->product == CODA_960)
+		coda_write(dev, 0x00, CODA9_GDI_BUS_CTRL);
+	coda_write(dev, CODA_REG_BIT_BUSY_FLAG, CODA_REG_BIT_BUSY);
+	coda_write(dev, CODA_REG_RUN_ENABLE, CODA_REG_BIT_CODE_RUN);
+	ret = coda_wait_timeout(dev);
+	coda_write(dev, idx, CODA_REG_BIT_RUN_INDEX);
+
+	return ret;
+}
+
+static void coda_kfifo_sync_from_device(struct coda_ctx *ctx)
+{
+	struct __kfifo *kfifo = &ctx->bitstream_fifo.kfifo;
+	struct coda_dev *dev = ctx->dev;
+	u32 rd_ptr;
+
+	rd_ptr = coda_read(dev, CODA_REG_BIT_RD_PTR(ctx->reg_idx));
+	kfifo->out = (kfifo->in & ~kfifo->mask) |
+		      (rd_ptr - ctx->bitstream.paddr);
+	if (kfifo->out > kfifo->in)
+		kfifo->out -= kfifo->mask + 1;
+}
+
+static void coda_kfifo_sync_to_device_full(struct coda_ctx *ctx)
+{
+	struct __kfifo *kfifo = &ctx->bitstream_fifo.kfifo;
+	struct coda_dev *dev = ctx->dev;
+	u32 rd_ptr, wr_ptr;
+
+	rd_ptr = ctx->bitstream.paddr + (kfifo->out & kfifo->mask);
+	coda_write(dev, rd_ptr, CODA_REG_BIT_RD_PTR(ctx->reg_idx));
+	wr_ptr = ctx->bitstream.paddr + (kfifo->in & kfifo->mask);
+	coda_write(dev, wr_ptr, CODA_REG_BIT_WR_PTR(ctx->reg_idx));
+}
+
+static void coda_kfifo_sync_to_device_write(struct coda_ctx *ctx)
+{
+	struct __kfifo *kfifo = &ctx->bitstream_fifo.kfifo;
+	struct coda_dev *dev = ctx->dev;
+	u32 wr_ptr;
+
+	wr_ptr = ctx->bitstream.paddr + (kfifo->in & kfifo->mask);
+	coda_write(dev, wr_ptr, CODA_REG_BIT_WR_PTR(ctx->reg_idx));
+}
+
+static int coda_bitstream_queue(struct coda_ctx *ctx,
+				struct vb2_buffer *src_buf)
+{
+	u32 src_size = vb2_get_plane_payload(src_buf, 0);
+	u32 n;
+
+	n = kfifo_in(&ctx->bitstream_fifo, vb2_plane_vaddr(src_buf, 0),
+		     src_size);
+	if (n < src_size)
+		return -ENOSPC;
+
+	dma_sync_single_for_device(&ctx->dev->plat_dev->dev,
+				   ctx->bitstream.paddr, ctx->bitstream.size,
+				   DMA_TO_DEVICE);
+
+	src_buf->v4l2_buf.sequence = ctx->qsequence++;
+
+	return 0;
+}
+
+static bool coda_bitstream_try_queue(struct coda_ctx *ctx,
+				     struct vb2_buffer *src_buf)
+{
+	int ret;
+
+	if (coda_get_bitstream_payload(ctx) +
+	    vb2_get_plane_payload(src_buf, 0) + 512 >= ctx->bitstream.size)
+		return false;
+
+	if (vb2_plane_vaddr(src_buf, 0) == NULL) {
+		v4l2_err(&ctx->dev->v4l2_dev, "trying to queue empty buffer\n");
+		return true;
+	}
+
+	ret = coda_bitstream_queue(ctx, src_buf);
+	if (ret < 0) {
+		v4l2_err(&ctx->dev->v4l2_dev, "bitstream buffer overflow\n");
+		return false;
+	}
+	/* Sync read pointer to device */
+	if (ctx == v4l2_m2m_get_curr_priv(ctx->dev->m2m_dev))
+		coda_kfifo_sync_to_device_write(ctx);
+
+	ctx->hold = false;
+
+	return true;
+}
+
+void coda_fill_bitstream(struct coda_ctx *ctx)
+{
+	struct vb2_buffer *src_buf;
+	struct coda_timestamp *ts;
+
+	while (v4l2_m2m_num_src_bufs_ready(ctx->fh.m2m_ctx) > 0) {
+		src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+
+		if (coda_bitstream_try_queue(ctx, src_buf)) {
+			/*
+			 * Source buffer is queued in the bitstream ringbuffer;
+			 * queue the timestamp and mark source buffer as done
+			 */
+			src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+
+			ts = kmalloc(sizeof(*ts), GFP_KERNEL);
+			if (ts) {
+				ts->sequence = src_buf->v4l2_buf.sequence;
+				ts->timecode = src_buf->v4l2_buf.timecode;
+				ts->timestamp = src_buf->v4l2_buf.timestamp;
+				list_add_tail(&ts->list, &ctx->timestamp_list);
+			}
+
+			v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE);
+		} else {
+			break;
+		}
+	}
+}
+
+void coda_bit_stream_end_flag(struct coda_ctx *ctx)
+{
+	struct coda_dev *dev = ctx->dev;
+
+	ctx->bit_stream_param |= CODA_BIT_STREAM_END_FLAG;
+
+	/* If this context is currently running, update the hardware flag */
+	if ((dev->devtype->product == CODA_960) &&
+	    coda_isbusy(dev) &&
+	    (ctx->idx == coda_read(dev, CODA_REG_BIT_RUN_INDEX))) {
+		coda_write(dev, ctx->bit_stream_param,
+			   CODA_REG_BIT_BIT_STREAM_PARAM);
+	}
+}
+
+static void coda_parabuf_write(struct coda_ctx *ctx, int index, u32 value)
+{
+	struct coda_dev *dev = ctx->dev;
+	u32 *p = ctx->parabuf.vaddr;
+
+	if (dev->devtype->product == CODA_DX6)
+		p[index] = value;
+	else
+		p[index ^ 1] = value;
+}
+
+static void coda_free_framebuffers(struct coda_ctx *ctx)
+{
+	int i;
+
+	for (i = 0; i < CODA_MAX_FRAMEBUFFERS; i++)
+		coda_free_aux_buf(ctx->dev, &ctx->internal_frames[i]);
+}
+
+static int coda_alloc_framebuffers(struct coda_ctx *ctx,
+				   struct coda_q_data *q_data, u32 fourcc)
+{
+	struct coda_dev *dev = ctx->dev;
+	int width, height;
+	dma_addr_t paddr;
+	int ysize;
+	int ret;
+	int i;
+
+	if (ctx->codec && (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 ||
+	     ctx->codec->dst_fourcc == V4L2_PIX_FMT_H264)) {
+		width = round_up(q_data->width, 16);
+		height = round_up(q_data->height, 16);
+	} else {
+		width = round_up(q_data->width, 8);
+		height = q_data->height;
+	}
+	ysize = width * height;
+
+	/* Allocate frame buffers */
+	for (i = 0; i < ctx->num_internal_frames; i++) {
+		size_t size;
+		char *name;
+
+		size = ysize + ysize / 2;
+		if (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 &&
+		    dev->devtype->product != CODA_DX6)
+			size += ysize / 4;
+		name = kasprintf(GFP_KERNEL, "fb%d", i);
+		ret = coda_alloc_context_buf(ctx, &ctx->internal_frames[i],
+					     size, name);
+		kfree(name);
+		if (ret < 0) {
+			coda_free_framebuffers(ctx);
+			return ret;
+		}
+	}
+
+	/* Register frame buffers in the parameter buffer */
+	for (i = 0; i < ctx->num_internal_frames; i++) {
+		paddr = ctx->internal_frames[i].paddr;
+		/* Start addresses of Y, Cb, Cr planes */
+		coda_parabuf_write(ctx, i * 3 + 0, paddr);
+		coda_parabuf_write(ctx, i * 3 + 1, paddr + ysize);
+		coda_parabuf_write(ctx, i * 3 + 2, paddr + ysize + ysize / 4);
+
+		/* mvcol buffer for h.264 */
+		if (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 &&
+		    dev->devtype->product != CODA_DX6)
+			coda_parabuf_write(ctx, 96 + i,
+					   ctx->internal_frames[i].paddr +
+					   ysize + ysize/4 + ysize/4);
+	}
+
+	/* mvcol buffer for mpeg4 */
+	if ((dev->devtype->product != CODA_DX6) &&
+	    (ctx->codec->src_fourcc == V4L2_PIX_FMT_MPEG4))
+		coda_parabuf_write(ctx, 97, ctx->internal_frames[i].paddr +
+					    ysize + ysize/4 + ysize/4);
+
+	return 0;
+}
+
+static void coda_free_context_buffers(struct coda_ctx *ctx)
+{
+	struct coda_dev *dev = ctx->dev;
+
+	coda_free_aux_buf(dev, &ctx->slicebuf);
+	coda_free_aux_buf(dev, &ctx->psbuf);
+	if (dev->devtype->product != CODA_DX6)
+		coda_free_aux_buf(dev, &ctx->workbuf);
+}
+
+static int coda_alloc_context_buffers(struct coda_ctx *ctx,
+				      struct coda_q_data *q_data)
+{
+	struct coda_dev *dev = ctx->dev;
+	size_t size;
+	int ret;
+
+	if (dev->devtype->product == CODA_DX6)
+		return 0;
+
+	if (ctx->psbuf.vaddr) {
+		v4l2_err(&dev->v4l2_dev, "psmembuf still allocated\n");
+		return -EBUSY;
+	}
+	if (ctx->slicebuf.vaddr) {
+		v4l2_err(&dev->v4l2_dev, "slicebuf still allocated\n");
+		return -EBUSY;
+	}
+	if (ctx->workbuf.vaddr) {
+		v4l2_err(&dev->v4l2_dev, "context buffer still allocated\n");
+		ret = -EBUSY;
+		return -ENOMEM;
+	}
+
+	if (q_data->fourcc == V4L2_PIX_FMT_H264) {
+		/* worst case slice size */
+		size = (DIV_ROUND_UP(q_data->width, 16) *
+			DIV_ROUND_UP(q_data->height, 16)) * 3200 / 8 + 512;
+		ret = coda_alloc_context_buf(ctx, &ctx->slicebuf, size,
+					     "slicebuf");
+		if (ret < 0) {
+			v4l2_err(&dev->v4l2_dev,
+				 "failed to allocate %d byte slice buffer",
+				 ctx->slicebuf.size);
+			return ret;
+		}
+	}
+
+	if (dev->devtype->product == CODA_7541) {
+		ret = coda_alloc_context_buf(ctx, &ctx->psbuf,
+					     CODA7_PS_BUF_SIZE, "psbuf");
+		if (ret < 0) {
+			v4l2_err(&dev->v4l2_dev,
+				 "failed to allocate psmem buffer");
+			goto err;
+		}
+	}
+
+	size = dev->devtype->workbuf_size;
+	if (dev->devtype->product == CODA_960 &&
+	    q_data->fourcc == V4L2_PIX_FMT_H264)
+		size += CODA9_PS_SAVE_SIZE;
+	ret = coda_alloc_context_buf(ctx, &ctx->workbuf, size, "workbuf");
+	if (ret < 0) {
+		v4l2_err(&dev->v4l2_dev,
+			 "failed to allocate %d byte context buffer",
+			 ctx->workbuf.size);
+		goto err;
+	}
+
+	return 0;
+
+err:
+	coda_free_context_buffers(ctx);
+	return ret;
+}
+
+static int coda_encode_header(struct coda_ctx *ctx, struct vb2_buffer *buf,
+			      int header_code, u8 *header, int *size)
+{
+	struct coda_dev *dev = ctx->dev;
+	size_t bufsize;
+	int ret;
+	int i;
+
+	if (dev->devtype->product == CODA_960)
+		memset(vb2_plane_vaddr(buf, 0), 0, 64);
+
+	coda_write(dev, vb2_dma_contig_plane_dma_addr(buf, 0),
+		   CODA_CMD_ENC_HEADER_BB_START);
+	bufsize = vb2_plane_size(buf, 0);
+	if (dev->devtype->product == CODA_960)
+		bufsize /= 1024;
+	coda_write(dev, bufsize, CODA_CMD_ENC_HEADER_BB_SIZE);
+	coda_write(dev, header_code, CODA_CMD_ENC_HEADER_CODE);
+	ret = coda_command_sync(ctx, CODA_COMMAND_ENCODE_HEADER);
+	if (ret < 0) {
+		v4l2_err(&dev->v4l2_dev, "CODA_COMMAND_ENCODE_HEADER timeout\n");
+		return ret;
+	}
+
+	if (dev->devtype->product == CODA_960) {
+		for (i = 63; i > 0; i--)
+			if (((char *)vb2_plane_vaddr(buf, 0))[i] != 0)
+				break;
+		*size = i + 1;
+	} else {
+		*size = coda_read(dev, CODA_REG_BIT_WR_PTR(ctx->reg_idx)) -
+			coda_read(dev, CODA_CMD_ENC_HEADER_BB_START);
+	}
+	memcpy(header, vb2_plane_vaddr(buf, 0), *size);
+
+	return 0;
+}
+
+static phys_addr_t coda_iram_alloc(struct coda_iram_info *iram, size_t size)
+{
+	phys_addr_t ret;
+
+	size = round_up(size, 1024);
+	if (size > iram->remaining)
+		return 0;
+	iram->remaining -= size;
+
+	ret = iram->next_paddr;
+	iram->next_paddr += size;
+
+	return ret;
+}
+
+static void coda_setup_iram(struct coda_ctx *ctx)
+{
+	struct coda_iram_info *iram_info = &ctx->iram_info;
+	struct coda_dev *dev = ctx->dev;
+	int w64, w128;
+	int mb_width;
+	int dbk_bits;
+	int bit_bits;
+	int ip_bits;
+
+	memset(iram_info, 0, sizeof(*iram_info));
+	iram_info->next_paddr = dev->iram.paddr;
+	iram_info->remaining = dev->iram.size;
+
+	if (!dev->iram.vaddr)
+		return;
+
+	switch (dev->devtype->product) {
+	case CODA_7541:
+		dbk_bits = CODA7_USE_HOST_DBK_ENABLE | CODA7_USE_DBK_ENABLE;
+		bit_bits = CODA7_USE_HOST_BIT_ENABLE | CODA7_USE_BIT_ENABLE;
+		ip_bits = CODA7_USE_HOST_IP_ENABLE | CODA7_USE_IP_ENABLE;
+		break;
+	case CODA_960:
+		dbk_bits = CODA9_USE_HOST_DBK_ENABLE | CODA9_USE_DBK_ENABLE;
+		bit_bits = CODA9_USE_HOST_BIT_ENABLE | CODA7_USE_BIT_ENABLE;
+		ip_bits = CODA9_USE_HOST_IP_ENABLE | CODA7_USE_IP_ENABLE;
+		break;
+	default: /* CODA_DX6 */
+		return;
+	}
+
+	if (ctx->inst_type == CODA_INST_ENCODER) {
+		struct coda_q_data *q_data_src;
+
+		q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+		mb_width = DIV_ROUND_UP(q_data_src->width, 16);
+		w128 = mb_width * 128;
+		w64 = mb_width * 64;
+
+		/* Prioritize in case IRAM is too small for everything */
+		if (dev->devtype->product == CODA_7541) {
+			iram_info->search_ram_size = round_up(mb_width * 16 *
+							      36 + 2048, 1024);
+			iram_info->search_ram_paddr = coda_iram_alloc(iram_info,
+						iram_info->search_ram_size);
+			if (!iram_info->search_ram_paddr) {
+				pr_err("IRAM is smaller than the search ram size\n");
+				goto out;
+			}
+			iram_info->axi_sram_use |= CODA7_USE_HOST_ME_ENABLE |
+						   CODA7_USE_ME_ENABLE;
+		}
+
+		/* Only H.264BP and H.263P3 are considered */
+		iram_info->buf_dbk_y_use = coda_iram_alloc(iram_info, w64);
+		iram_info->buf_dbk_c_use = coda_iram_alloc(iram_info, w64);
+		if (!iram_info->buf_dbk_c_use)
+			goto out;
+		iram_info->axi_sram_use |= dbk_bits;
+
+		iram_info->buf_bit_use = coda_iram_alloc(iram_info, w128);
+		if (!iram_info->buf_bit_use)
+			goto out;
+		iram_info->axi_sram_use |= bit_bits;
+
+		iram_info->buf_ip_ac_dc_use = coda_iram_alloc(iram_info, w128);
+		if (!iram_info->buf_ip_ac_dc_use)
+			goto out;
+		iram_info->axi_sram_use |= ip_bits;
+
+		/* OVL and BTP disabled for encoder */
+	} else if (ctx->inst_type == CODA_INST_DECODER) {
+		struct coda_q_data *q_data_dst;
+
+		q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+		mb_width = DIV_ROUND_UP(q_data_dst->width, 16);
+		w128 = mb_width * 128;
+
+		iram_info->buf_dbk_y_use = coda_iram_alloc(iram_info, w128);
+		iram_info->buf_dbk_c_use = coda_iram_alloc(iram_info, w128);
+		if (!iram_info->buf_dbk_c_use)
+			goto out;
+		iram_info->axi_sram_use |= dbk_bits;
+
+		iram_info->buf_bit_use = coda_iram_alloc(iram_info, w128);
+		if (!iram_info->buf_bit_use)
+			goto out;
+		iram_info->axi_sram_use |= bit_bits;
+
+		iram_info->buf_ip_ac_dc_use = coda_iram_alloc(iram_info, w128);
+		if (!iram_info->buf_ip_ac_dc_use)
+			goto out;
+		iram_info->axi_sram_use |= ip_bits;
+
+		/* OVL and BTP unused as there is no VC1 support yet */
+	}
+
+out:
+	if (!(iram_info->axi_sram_use & CODA7_USE_HOST_IP_ENABLE))
+		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+			 "IRAM smaller than needed\n");
+
+	if (dev->devtype->product == CODA_7541) {
+		/* TODO - Enabling these causes picture errors on CODA7541 */
+		if (ctx->inst_type == CODA_INST_DECODER) {
+			/* fw 1.4.50 */
+			iram_info->axi_sram_use &= ~(CODA7_USE_HOST_IP_ENABLE |
+						     CODA7_USE_IP_ENABLE);
+		} else {
+			/* fw 13.4.29 */
+			iram_info->axi_sram_use &= ~(CODA7_USE_HOST_IP_ENABLE |
+						     CODA7_USE_HOST_DBK_ENABLE |
+						     CODA7_USE_IP_ENABLE |
+						     CODA7_USE_DBK_ENABLE);
+		}
+	}
+}
+
+static u32 coda_supported_firmwares[] = {
+	CODA_FIRMWARE_VERNUM(CODA_DX6, 2, 2, 5),
+	CODA_FIRMWARE_VERNUM(CODA_7541, 1, 4, 50),
+	CODA_FIRMWARE_VERNUM(CODA_960, 2, 1, 5),
+};
+
+static bool coda_firmware_supported(u32 vernum)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(coda_supported_firmwares); i++)
+		if (vernum == coda_supported_firmwares[i])
+			return true;
+	return false;
+}
+
+int coda_check_firmware(struct coda_dev *dev)
+{
+	u16 product, major, minor, release;
+	u32 data;
+	int ret;
+
+	ret = clk_prepare_enable(dev->clk_per);
+	if (ret)
+		goto err_clk_per;
+
+	ret = clk_prepare_enable(dev->clk_ahb);
+	if (ret)
+		goto err_clk_ahb;
+
+	coda_write(dev, 0, CODA_CMD_FIRMWARE_VERNUM);
+	coda_write(dev, CODA_REG_BIT_BUSY_FLAG, CODA_REG_BIT_BUSY);
+	coda_write(dev, 0, CODA_REG_BIT_RUN_INDEX);
+	coda_write(dev, 0, CODA_REG_BIT_RUN_COD_STD);
+	coda_write(dev, CODA_COMMAND_FIRMWARE_GET, CODA_REG_BIT_RUN_COMMAND);
+	if (coda_wait_timeout(dev)) {
+		v4l2_err(&dev->v4l2_dev, "firmware get command error\n");
+		ret = -EIO;
+		goto err_run_cmd;
+	}
+
+	if (dev->devtype->product == CODA_960) {
+		data = coda_read(dev, CODA9_CMD_FIRMWARE_CODE_REV);
+		v4l2_info(&dev->v4l2_dev, "Firmware code revision: %d\n",
+			  data);
+	}
+
+	/* Check we are compatible with the loaded firmware */
+	data = coda_read(dev, CODA_CMD_FIRMWARE_VERNUM);
+	product = CODA_FIRMWARE_PRODUCT(data);
+	major = CODA_FIRMWARE_MAJOR(data);
+	minor = CODA_FIRMWARE_MINOR(data);
+	release = CODA_FIRMWARE_RELEASE(data);
+
+	clk_disable_unprepare(dev->clk_per);
+	clk_disable_unprepare(dev->clk_ahb);
+
+	if (product != dev->devtype->product) {
+		v4l2_err(&dev->v4l2_dev,
+			 "Wrong firmware. Hw: %s, Fw: %s, Version: %u.%u.%u\n",
+			 coda_product_name(dev->devtype->product),
+			 coda_product_name(product), major, minor, release);
+		return -EINVAL;
+	}
+
+	v4l2_info(&dev->v4l2_dev, "Initialized %s.\n",
+		  coda_product_name(product));
+
+	if (coda_firmware_supported(data)) {
+		v4l2_info(&dev->v4l2_dev, "Firmware version: %u.%u.%u\n",
+			  major, minor, release);
+	} else {
+		v4l2_warn(&dev->v4l2_dev,
+			  "Unsupported firmware version: %u.%u.%u\n",
+			  major, minor, release);
+	}
+
+	return 0;
+
+err_run_cmd:
+	clk_disable_unprepare(dev->clk_ahb);
+err_clk_ahb:
+	clk_disable_unprepare(dev->clk_per);
+err_clk_per:
+	return ret;
+}
+
+/*
+ * Encoder context operations
+ */
+
+static int coda_start_encoding(struct coda_ctx *ctx)
+{
+	struct coda_dev *dev = ctx->dev;
+	struct v4l2_device *v4l2_dev = &dev->v4l2_dev;
+	struct coda_q_data *q_data_src, *q_data_dst;
+	u32 bitstream_buf, bitstream_size;
+	struct vb2_buffer *buf;
+	int gamma, ret, value;
+	u32 dst_fourcc;
+
+	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+	dst_fourcc = q_data_dst->fourcc;
+
+	/* Allocate per-instance buffers */
+	ret = coda_alloc_context_buffers(ctx, q_data_src);
+	if (ret < 0)
+		return ret;
+
+	buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+	bitstream_buf = vb2_dma_contig_plane_dma_addr(buf, 0);
+	bitstream_size = q_data_dst->sizeimage;
+
+	if (!coda_is_initialized(dev)) {
+		v4l2_err(v4l2_dev, "coda is not initialized.\n");
+		return -EFAULT;
+	}
+
+	mutex_lock(&dev->coda_mutex);
+
+	coda_write(dev, ctx->parabuf.paddr, CODA_REG_BIT_PARA_BUF_ADDR);
+	coda_write(dev, bitstream_buf, CODA_REG_BIT_RD_PTR(ctx->reg_idx));
+	coda_write(dev, bitstream_buf, CODA_REG_BIT_WR_PTR(ctx->reg_idx));
+	switch (dev->devtype->product) {
+	case CODA_DX6:
+		coda_write(dev, CODADX6_STREAM_BUF_DYNALLOC_EN |
+			CODADX6_STREAM_BUF_PIC_RESET, CODA_REG_BIT_STREAM_CTRL);
+		break;
+	case CODA_960:
+		coda_write(dev, 0, CODA9_GDI_WPROT_RGN_EN);
+		/* fallthrough */
+	case CODA_7541:
+		coda_write(dev, CODA7_STREAM_BUF_DYNALLOC_EN |
+			CODA7_STREAM_BUF_PIC_RESET, CODA_REG_BIT_STREAM_CTRL);
+		break;
+	}
+
+	value = coda_read(dev, CODA_REG_BIT_FRAME_MEM_CTRL);
+	value &= ~(1 << 2 | 0x7 << 9);
+	ctx->frame_mem_ctrl = value;
+	coda_write(dev, value, CODA_REG_BIT_FRAME_MEM_CTRL);
+
+	if (dev->devtype->product == CODA_DX6) {
+		/* Configure the coda */
+		coda_write(dev, dev->iram.paddr,
+			   CODADX6_REG_BIT_SEARCH_RAM_BASE_ADDR);
+	}
+
+	/* Could set rotation here if needed */
+	switch (dev->devtype->product) {
+	case CODA_DX6:
+		value = (q_data_src->width & CODADX6_PICWIDTH_MASK)
+			<< CODADX6_PICWIDTH_OFFSET;
+		value |= (q_data_src->height & CODADX6_PICHEIGHT_MASK)
+			 << CODA_PICHEIGHT_OFFSET;
+		break;
+	case CODA_7541:
+		if (dst_fourcc == V4L2_PIX_FMT_H264) {
+			value = (round_up(q_data_src->width, 16) &
+				 CODA7_PICWIDTH_MASK) << CODA7_PICWIDTH_OFFSET;
+			value |= (round_up(q_data_src->height, 16) &
+				 CODA7_PICHEIGHT_MASK) << CODA_PICHEIGHT_OFFSET;
+			break;
+		}
+		/* fallthrough */
+	case CODA_960:
+		value = (q_data_src->width & CODA7_PICWIDTH_MASK)
+			<< CODA7_PICWIDTH_OFFSET;
+		value |= (q_data_src->height & CODA7_PICHEIGHT_MASK)
+			 << CODA_PICHEIGHT_OFFSET;
+	}
+	coda_write(dev, value, CODA_CMD_ENC_SEQ_SRC_SIZE);
+	coda_write(dev, ctx->params.framerate,
+		   CODA_CMD_ENC_SEQ_SRC_F_RATE);
+
+	ctx->params.codec_mode = ctx->codec->mode;
+	switch (dst_fourcc) {
+	case V4L2_PIX_FMT_MPEG4:
+		if (dev->devtype->product == CODA_960)
+			coda_write(dev, CODA9_STD_MPEG4,
+				   CODA_CMD_ENC_SEQ_COD_STD);
+		else
+			coda_write(dev, CODA_STD_MPEG4,
+				   CODA_CMD_ENC_SEQ_COD_STD);
+		coda_write(dev, 0, CODA_CMD_ENC_SEQ_MP4_PARA);
+		break;
+	case V4L2_PIX_FMT_H264:
+		if (dev->devtype->product == CODA_960)
+			coda_write(dev, CODA9_STD_H264,
+				   CODA_CMD_ENC_SEQ_COD_STD);
+		else
+			coda_write(dev, CODA_STD_H264,
+				   CODA_CMD_ENC_SEQ_COD_STD);
+		if (ctx->params.h264_deblk_enabled) {
+			value = ((ctx->params.h264_deblk_alpha &
+				  CODA_264PARAM_DEBLKFILTEROFFSETALPHA_MASK) <<
+				 CODA_264PARAM_DEBLKFILTEROFFSETALPHA_OFFSET) |
+				((ctx->params.h264_deblk_beta &
+				  CODA_264PARAM_DEBLKFILTEROFFSETBETA_MASK) <<
+				 CODA_264PARAM_DEBLKFILTEROFFSETBETA_OFFSET);
+		} else {
+			value = 1 << CODA_264PARAM_DISABLEDEBLK_OFFSET;
+		}
+		coda_write(dev, value, CODA_CMD_ENC_SEQ_264_PARA);
+		break;
+	default:
+		v4l2_err(v4l2_dev,
+			 "dst format (0x%08x) invalid.\n", dst_fourcc);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	switch (ctx->params.slice_mode) {
+	case V4L2_MPEG_VIDEO_MULTI_SLICE_MODE_SINGLE:
+		value = 0;
+		break;
+	case V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_MB:
+		value  = (ctx->params.slice_max_mb & CODA_SLICING_SIZE_MASK)
+			 << CODA_SLICING_SIZE_OFFSET;
+		value |= (1 & CODA_SLICING_UNIT_MASK)
+			 << CODA_SLICING_UNIT_OFFSET;
+		value |=  1 & CODA_SLICING_MODE_MASK;
+		break;
+	case V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_BYTES:
+		value  = (ctx->params.slice_max_bits & CODA_SLICING_SIZE_MASK)
+			 << CODA_SLICING_SIZE_OFFSET;
+		value |= (0 & CODA_SLICING_UNIT_MASK)
+			 << CODA_SLICING_UNIT_OFFSET;
+		value |=  1 & CODA_SLICING_MODE_MASK;
+		break;
+	}
+	coda_write(dev, value, CODA_CMD_ENC_SEQ_SLICE_MODE);
+	value = ctx->params.gop_size & CODA_GOP_SIZE_MASK;
+	coda_write(dev, value, CODA_CMD_ENC_SEQ_GOP_SIZE);
+
+	if (ctx->params.bitrate) {
+		/* Rate control enabled */
+		value = (ctx->params.bitrate & CODA_RATECONTROL_BITRATE_MASK)
+			<< CODA_RATECONTROL_BITRATE_OFFSET;
+		value |=  1 & CODA_RATECONTROL_ENABLE_MASK;
+		if (dev->devtype->product == CODA_960)
+			value |= BIT(31); /* disable autoskip */
+	} else {
+		value = 0;
+	}
+	coda_write(dev, value, CODA_CMD_ENC_SEQ_RC_PARA);
+
+	coda_write(dev, 0, CODA_CMD_ENC_SEQ_RC_BUF_SIZE);
+	coda_write(dev, ctx->params.intra_refresh,
+		   CODA_CMD_ENC_SEQ_INTRA_REFRESH);
+
+	coda_write(dev, bitstream_buf, CODA_CMD_ENC_SEQ_BB_START);
+	coda_write(dev, bitstream_size / 1024, CODA_CMD_ENC_SEQ_BB_SIZE);
+
+
+	value = 0;
+	if (dev->devtype->product == CODA_960)
+		gamma = CODA9_DEFAULT_GAMMA;
+	else
+		gamma = CODA_DEFAULT_GAMMA;
+	if (gamma > 0) {
+		coda_write(dev, (gamma & CODA_GAMMA_MASK) << CODA_GAMMA_OFFSET,
+			   CODA_CMD_ENC_SEQ_RC_GAMMA);
+	}
+
+	if (ctx->params.h264_min_qp || ctx->params.h264_max_qp) {
+		coda_write(dev,
+			   ctx->params.h264_min_qp << CODA_QPMIN_OFFSET |
+			   ctx->params.h264_max_qp << CODA_QPMAX_OFFSET,
+			   CODA_CMD_ENC_SEQ_RC_QP_MIN_MAX);
+	}
+	if (dev->devtype->product == CODA_960) {
+		if (ctx->params.h264_max_qp)
+			value |= 1 << CODA9_OPTION_RCQPMAX_OFFSET;
+		if (CODA_DEFAULT_GAMMA > 0)
+			value |= 1 << CODA9_OPTION_GAMMA_OFFSET;
+	} else {
+		if (CODA_DEFAULT_GAMMA > 0) {
+			if (dev->devtype->product == CODA_DX6)
+				value |= 1 << CODADX6_OPTION_GAMMA_OFFSET;
+			else
+				value |= 1 << CODA7_OPTION_GAMMA_OFFSET;
+		}
+		if (ctx->params.h264_min_qp)
+			value |= 1 << CODA7_OPTION_RCQPMIN_OFFSET;
+		if (ctx->params.h264_max_qp)
+			value |= 1 << CODA7_OPTION_RCQPMAX_OFFSET;
+	}
+	coda_write(dev, value, CODA_CMD_ENC_SEQ_OPTION);
+
+	coda_write(dev, 0, CODA_CMD_ENC_SEQ_RC_INTERVAL_MODE);
+
+	coda_setup_iram(ctx);
+
+	if (dst_fourcc == V4L2_PIX_FMT_H264) {
+		switch (dev->devtype->product) {
+		case CODA_DX6:
+			value = FMO_SLICE_SAVE_BUF_SIZE << 7;
+			coda_write(dev, value, CODADX6_CMD_ENC_SEQ_FMO);
+			break;
+		case CODA_7541:
+			coda_write(dev, ctx->iram_info.search_ram_paddr,
+					CODA7_CMD_ENC_SEQ_SEARCH_BASE);
+			coda_write(dev, ctx->iram_info.search_ram_size,
+					CODA7_CMD_ENC_SEQ_SEARCH_SIZE);
+			break;
+		case CODA_960:
+			coda_write(dev, 0, CODA9_CMD_ENC_SEQ_ME_OPTION);
+			coda_write(dev, 0, CODA9_CMD_ENC_SEQ_INTRA_WEIGHT);
+		}
+	}
+
+	ret = coda_command_sync(ctx, CODA_COMMAND_SEQ_INIT);
+	if (ret < 0) {
+		v4l2_err(v4l2_dev, "CODA_COMMAND_SEQ_INIT timeout\n");
+		goto out;
+	}
+
+	if (coda_read(dev, CODA_RET_ENC_SEQ_SUCCESS) == 0) {
+		v4l2_err(v4l2_dev, "CODA_COMMAND_SEQ_INIT failed\n");
+		ret = -EFAULT;
+		goto out;
+	}
+
+	if (dev->devtype->product == CODA_960)
+		ctx->num_internal_frames = 4;
+	else
+		ctx->num_internal_frames = 2;
+	ret = coda_alloc_framebuffers(ctx, q_data_src, dst_fourcc);
+	if (ret < 0) {
+		v4l2_err(v4l2_dev, "failed to allocate framebuffers\n");
+		goto out;
+	}
+
+	coda_write(dev, ctx->num_internal_frames, CODA_CMD_SET_FRAME_BUF_NUM);
+	coda_write(dev, q_data_src->bytesperline,
+			CODA_CMD_SET_FRAME_BUF_STRIDE);
+	if (dev->devtype->product == CODA_7541) {
+		coda_write(dev, q_data_src->bytesperline,
+				CODA7_CMD_SET_FRAME_SOURCE_BUF_STRIDE);
+	}
+	if (dev->devtype->product != CODA_DX6) {
+		coda_write(dev, ctx->iram_info.buf_bit_use,
+				CODA7_CMD_SET_FRAME_AXI_BIT_ADDR);
+		coda_write(dev, ctx->iram_info.buf_ip_ac_dc_use,
+				CODA7_CMD_SET_FRAME_AXI_IPACDC_ADDR);
+		coda_write(dev, ctx->iram_info.buf_dbk_y_use,
+				CODA7_CMD_SET_FRAME_AXI_DBKY_ADDR);
+		coda_write(dev, ctx->iram_info.buf_dbk_c_use,
+				CODA7_CMD_SET_FRAME_AXI_DBKC_ADDR);
+		coda_write(dev, ctx->iram_info.buf_ovl_use,
+				CODA7_CMD_SET_FRAME_AXI_OVL_ADDR);
+		if (dev->devtype->product == CODA_960) {
+			coda_write(dev, ctx->iram_info.buf_btp_use,
+					CODA9_CMD_SET_FRAME_AXI_BTP_ADDR);
+
+			/* FIXME */
+			coda_write(dev, ctx->internal_frames[2].paddr,
+				   CODA9_CMD_SET_FRAME_SUBSAMP_A);
+			coda_write(dev, ctx->internal_frames[3].paddr,
+				   CODA9_CMD_SET_FRAME_SUBSAMP_B);
+		}
+	}
+
+	ret = coda_command_sync(ctx, CODA_COMMAND_SET_FRAME_BUF);
+	if (ret < 0) {
+		v4l2_err(v4l2_dev, "CODA_COMMAND_SET_FRAME_BUF timeout\n");
+		goto out;
+	}
+
+	/* Save stream headers */
+	buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+	switch (dst_fourcc) {
+	case V4L2_PIX_FMT_H264:
+		/*
+		 * Get SPS in the first frame and copy it to an
+		 * intermediate buffer.
+		 */
+		ret = coda_encode_header(ctx, buf, CODA_HEADER_H264_SPS,
+					 &ctx->vpu_header[0][0],
+					 &ctx->vpu_header_size[0]);
+		if (ret < 0)
+			goto out;
+
+		/*
+		 * Get PPS in the first frame and copy it to an
+		 * intermediate buffer.
+		 */
+		ret = coda_encode_header(ctx, buf, CODA_HEADER_H264_PPS,
+					 &ctx->vpu_header[1][0],
+					 &ctx->vpu_header_size[1]);
+		if (ret < 0)
+			goto out;
+
+		/*
+		 * Length of H.264 headers is variable and thus it might not be
+		 * aligned for the coda to append the encoded frame. In that is
+		 * the case a filler NAL must be added to header 2.
+		 */
+		ctx->vpu_header_size[2] = coda_h264_padding(
+					(ctx->vpu_header_size[0] +
+					 ctx->vpu_header_size[1]),
+					 ctx->vpu_header[2]);
+		break;
+	case V4L2_PIX_FMT_MPEG4:
+		/*
+		 * Get VOS in the first frame and copy it to an
+		 * intermediate buffer
+		 */
+		ret = coda_encode_header(ctx, buf, CODA_HEADER_MP4V_VOS,
+					 &ctx->vpu_header[0][0],
+					 &ctx->vpu_header_size[0]);
+		if (ret < 0)
+			goto out;
+
+		ret = coda_encode_header(ctx, buf, CODA_HEADER_MP4V_VIS,
+					 &ctx->vpu_header[1][0],
+					 &ctx->vpu_header_size[1]);
+		if (ret < 0)
+			goto out;
+
+		ret = coda_encode_header(ctx, buf, CODA_HEADER_MP4V_VOL,
+					 &ctx->vpu_header[2][0],
+					 &ctx->vpu_header_size[2]);
+		if (ret < 0)
+			goto out;
+		break;
+	default:
+		/* No more formats need to save headers at the moment */
+		break;
+	}
+
+out:
+	mutex_unlock(&dev->coda_mutex);
+	return ret;
+}
+
+static int coda_prepare_encode(struct coda_ctx *ctx)
+{
+	struct coda_q_data *q_data_src, *q_data_dst;
+	struct vb2_buffer *src_buf, *dst_buf;
+	struct coda_dev *dev = ctx->dev;
+	int force_ipicture;
+	int quant_param = 0;
+	u32 picture_y, picture_cb, picture_cr;
+	u32 pic_stream_buffer_addr, pic_stream_buffer_size;
+	u32 dst_fourcc;
+
+	src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+	dst_fourcc = q_data_dst->fourcc;
+
+	src_buf->v4l2_buf.sequence = ctx->osequence;
+	dst_buf->v4l2_buf.sequence = ctx->osequence;
+	ctx->osequence++;
+
+	/*
+	 * Workaround coda firmware BUG that only marks the first
+	 * frame as IDR. This is a problem for some decoders that can't
+	 * recover when a frame is lost.
+	 */
+	if (src_buf->v4l2_buf.sequence % ctx->params.gop_size) {
+		src_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_PFRAME;
+		src_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_KEYFRAME;
+	} else {
+		src_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_KEYFRAME;
+		src_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_PFRAME;
+	}
+
+	if (dev->devtype->product == CODA_960)
+		coda_set_gdi_regs(ctx);
+
+	/*
+	 * Copy headers at the beginning of the first frame for H.264 only.
+	 * In MPEG4 they are already copied by the coda.
+	 */
+	if (src_buf->v4l2_buf.sequence == 0) {
+		pic_stream_buffer_addr =
+			vb2_dma_contig_plane_dma_addr(dst_buf, 0) +
+			ctx->vpu_header_size[0] +
+			ctx->vpu_header_size[1] +
+			ctx->vpu_header_size[2];
+		pic_stream_buffer_size = CODA_MAX_FRAME_SIZE -
+			ctx->vpu_header_size[0] -
+			ctx->vpu_header_size[1] -
+			ctx->vpu_header_size[2];
+		memcpy(vb2_plane_vaddr(dst_buf, 0),
+		       &ctx->vpu_header[0][0], ctx->vpu_header_size[0]);
+		memcpy(vb2_plane_vaddr(dst_buf, 0) + ctx->vpu_header_size[0],
+		       &ctx->vpu_header[1][0], ctx->vpu_header_size[1]);
+		memcpy(vb2_plane_vaddr(dst_buf, 0) + ctx->vpu_header_size[0] +
+			ctx->vpu_header_size[1], &ctx->vpu_header[2][0],
+			ctx->vpu_header_size[2]);
+	} else {
+		pic_stream_buffer_addr =
+			vb2_dma_contig_plane_dma_addr(dst_buf, 0);
+		pic_stream_buffer_size = CODA_MAX_FRAME_SIZE;
+	}
+
+	if (src_buf->v4l2_buf.flags & V4L2_BUF_FLAG_KEYFRAME) {
+		force_ipicture = 1;
+		switch (dst_fourcc) {
+		case V4L2_PIX_FMT_H264:
+			quant_param = ctx->params.h264_intra_qp;
+			break;
+		case V4L2_PIX_FMT_MPEG4:
+			quant_param = ctx->params.mpeg4_intra_qp;
+			break;
+		default:
+			v4l2_warn(&ctx->dev->v4l2_dev,
+				"cannot set intra qp, fmt not supported\n");
+			break;
+		}
+	} else {
+		force_ipicture = 0;
+		switch (dst_fourcc) {
+		case V4L2_PIX_FMT_H264:
+			quant_param = ctx->params.h264_inter_qp;
+			break;
+		case V4L2_PIX_FMT_MPEG4:
+			quant_param = ctx->params.mpeg4_inter_qp;
+			break;
+		default:
+			v4l2_warn(&ctx->dev->v4l2_dev,
+				"cannot set inter qp, fmt not supported\n");
+			break;
+		}
+	}
+
+	/* submit */
+	coda_write(dev, CODA_ROT_MIR_ENABLE | ctx->params.rot_mode,
+		   CODA_CMD_ENC_PIC_ROT_MODE);
+	coda_write(dev, quant_param, CODA_CMD_ENC_PIC_QS);
+
+
+	picture_y = vb2_dma_contig_plane_dma_addr(src_buf, 0);
+	switch (q_data_src->fourcc) {
+	case V4L2_PIX_FMT_YVU420:
+		/* Switch Cb and Cr for YVU420 format */
+		picture_cr = picture_y + q_data_src->bytesperline *
+				q_data_src->height;
+		picture_cb = picture_cr + q_data_src->bytesperline / 2 *
+				q_data_src->height / 2;
+		break;
+	case V4L2_PIX_FMT_YUV420:
+	default:
+		picture_cb = picture_y + q_data_src->bytesperline *
+				q_data_src->height;
+		picture_cr = picture_cb + q_data_src->bytesperline / 2 *
+				q_data_src->height / 2;
+		break;
+	}
+
+	if (dev->devtype->product == CODA_960) {
+		coda_write(dev, 4/*FIXME: 0*/, CODA9_CMD_ENC_PIC_SRC_INDEX);
+		coda_write(dev, q_data_src->width, CODA9_CMD_ENC_PIC_SRC_STRIDE);
+		coda_write(dev, 0, CODA9_CMD_ENC_PIC_SUB_FRAME_SYNC);
+
+		coda_write(dev, picture_y, CODA9_CMD_ENC_PIC_SRC_ADDR_Y);
+		coda_write(dev, picture_cb, CODA9_CMD_ENC_PIC_SRC_ADDR_CB);
+		coda_write(dev, picture_cr, CODA9_CMD_ENC_PIC_SRC_ADDR_CR);
+	} else {
+		coda_write(dev, picture_y, CODA_CMD_ENC_PIC_SRC_ADDR_Y);
+		coda_write(dev, picture_cb, CODA_CMD_ENC_PIC_SRC_ADDR_CB);
+		coda_write(dev, picture_cr, CODA_CMD_ENC_PIC_SRC_ADDR_CR);
+	}
+	coda_write(dev, force_ipicture << 1 & 0x2,
+		   CODA_CMD_ENC_PIC_OPTION);
+
+	coda_write(dev, pic_stream_buffer_addr, CODA_CMD_ENC_PIC_BB_START);
+	coda_write(dev, pic_stream_buffer_size / 1024,
+		   CODA_CMD_ENC_PIC_BB_SIZE);
+
+	if (!ctx->streamon_out) {
+		/* After streamoff on the output side, set stream end flag */
+		ctx->bit_stream_param |= CODA_BIT_STREAM_END_FLAG;
+		coda_write(dev, ctx->bit_stream_param,
+			   CODA_REG_BIT_BIT_STREAM_PARAM);
+	}
+
+	if (dev->devtype->product != CODA_DX6)
+		coda_write(dev, ctx->iram_info.axi_sram_use,
+				CODA7_REG_BIT_AXI_SRAM_USE);
+
+	coda_command_async(ctx, CODA_COMMAND_PIC_RUN);
+
+	return 0;
+}
+
+static void coda_finish_encode(struct coda_ctx *ctx)
+{
+	struct vb2_buffer *src_buf, *dst_buf;
+	struct coda_dev *dev = ctx->dev;
+	u32 wr_ptr, start_ptr;
+
+	src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+
+	/* Get results from the coda */
+	start_ptr = coda_read(dev, CODA_CMD_ENC_PIC_BB_START);
+	wr_ptr = coda_read(dev, CODA_REG_BIT_WR_PTR(ctx->reg_idx));
+
+	/* Calculate bytesused field */
+	if (dst_buf->v4l2_buf.sequence == 0) {
+		vb2_set_plane_payload(dst_buf, 0, wr_ptr - start_ptr +
+					ctx->vpu_header_size[0] +
+					ctx->vpu_header_size[1] +
+					ctx->vpu_header_size[2]);
+	} else {
+		vb2_set_plane_payload(dst_buf, 0, wr_ptr - start_ptr);
+	}
+
+	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev, "frame size = %u\n",
+		 wr_ptr - start_ptr);
+
+	coda_read(dev, CODA_RET_ENC_PIC_SLICE_NUM);
+	coda_read(dev, CODA_RET_ENC_PIC_FLAG);
+
+	if (coda_read(dev, CODA_RET_ENC_PIC_TYPE) == 0) {
+		dst_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_KEYFRAME;
+		dst_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_PFRAME;
+	} else {
+		dst_buf->v4l2_buf.flags |= V4L2_BUF_FLAG_PFRAME;
+		dst_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_KEYFRAME;
+	}
+
+	dst_buf->v4l2_buf.timestamp = src_buf->v4l2_buf.timestamp;
+	dst_buf->v4l2_buf.flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
+	dst_buf->v4l2_buf.flags |=
+		src_buf->v4l2_buf.flags & V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
+	dst_buf->v4l2_buf.timecode = src_buf->v4l2_buf.timecode;
+
+	v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE);
+
+	dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+	v4l2_m2m_buf_done(dst_buf, VB2_BUF_STATE_DONE);
+
+	ctx->gopcounter--;
+	if (ctx->gopcounter < 0)
+		ctx->gopcounter = ctx->params.gop_size - 1;
+
+	v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
+		"job finished: encoding frame (%d) (%s)\n",
+		dst_buf->v4l2_buf.sequence,
+		(dst_buf->v4l2_buf.flags & V4L2_BUF_FLAG_KEYFRAME) ?
+		"KEYFRAME" : "PFRAME");
+}
+
+static void coda_seq_end_work(struct work_struct *work)
+{
+	struct coda_ctx *ctx = container_of(work, struct coda_ctx, seq_end_work);
+	struct coda_dev *dev = ctx->dev;
+
+	mutex_lock(&ctx->buffer_mutex);
+	mutex_lock(&dev->coda_mutex);
+
+	v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
+		 "%d: %s: sent command 'SEQ_END' to coda\n", ctx->idx,
+		 __func__);
+	if (coda_command_sync(ctx, CODA_COMMAND_SEQ_END)) {
+		v4l2_err(&dev->v4l2_dev,
+			 "CODA_COMMAND_SEQ_END failed\n");
+	}
+
+	kfifo_init(&ctx->bitstream_fifo,
+		ctx->bitstream.vaddr, ctx->bitstream.size);
+
+	coda_free_framebuffers(ctx);
+	coda_free_context_buffers(ctx);
+
+	mutex_unlock(&dev->coda_mutex);
+	mutex_unlock(&ctx->buffer_mutex);
+}
+
+static void coda_bit_release(struct coda_ctx *ctx)
+{
+	coda_free_framebuffers(ctx);
+	coda_free_context_buffers(ctx);
+}
+
+const struct coda_context_ops coda_bit_encode_ops = {
+	.queue_init = coda_encoder_queue_init,
+	.start_streaming = coda_start_encoding,
+	.prepare_run = coda_prepare_encode,
+	.finish_run = coda_finish_encode,
+	.seq_end_work = coda_seq_end_work,
+	.release = coda_bit_release,
+};
+
+/*
+ * Decoder context operations
+ */
+
+static int __coda_start_decoding(struct coda_ctx *ctx)
+{
+	struct coda_q_data *q_data_src, *q_data_dst;
+	u32 bitstream_buf, bitstream_size;
+	struct coda_dev *dev = ctx->dev;
+	int width, height;
+	u32 src_fourcc;
+	u32 val;
+	int ret;
+
+	/* Start decoding */
+	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+	bitstream_buf = ctx->bitstream.paddr;
+	bitstream_size = ctx->bitstream.size;
+	src_fourcc = q_data_src->fourcc;
+
+	/* Allocate per-instance buffers */
+	ret = coda_alloc_context_buffers(ctx, q_data_src);
+	if (ret < 0)
+		return ret;
+
+	coda_write(dev, ctx->parabuf.paddr, CODA_REG_BIT_PARA_BUF_ADDR);
+
+	/* Update coda bitstream read and write pointers from kfifo */
+	coda_kfifo_sync_to_device_full(ctx);
+
+	ctx->display_idx = -1;
+	ctx->frm_dis_flg = 0;
+	coda_write(dev, 0, CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));
+
+	coda_write(dev, CODA_BIT_DEC_SEQ_INIT_ESCAPE,
+			CODA_REG_BIT_BIT_STREAM_PARAM);
+
+	coda_write(dev, bitstream_buf, CODA_CMD_DEC_SEQ_BB_START);
+	coda_write(dev, bitstream_size / 1024, CODA_CMD_DEC_SEQ_BB_SIZE);
+	val = 0;
+	if ((dev->devtype->product == CODA_7541) ||
+	    (dev->devtype->product == CODA_960))
+		val |= CODA_REORDER_ENABLE;
+	coda_write(dev, val, CODA_CMD_DEC_SEQ_OPTION);
+
+	ctx->params.codec_mode = ctx->codec->mode;
+	if (dev->devtype->product == CODA_960 &&
+	    src_fourcc == V4L2_PIX_FMT_MPEG4)
+		ctx->params.codec_mode_aux = CODA_MP4_AUX_MPEG4;
+	else
+		ctx->params.codec_mode_aux = 0;
+	if (src_fourcc == V4L2_PIX_FMT_H264) {
+		if (dev->devtype->product == CODA_7541) {
+			coda_write(dev, ctx->psbuf.paddr,
+					CODA_CMD_DEC_SEQ_PS_BB_START);
+			coda_write(dev, (CODA7_PS_BUF_SIZE / 1024),
+					CODA_CMD_DEC_SEQ_PS_BB_SIZE);
+		}
+		if (dev->devtype->product == CODA_960) {
+			coda_write(dev, 0, CODA_CMD_DEC_SEQ_X264_MV_EN);
+			coda_write(dev, 512, CODA_CMD_DEC_SEQ_SPP_CHUNK_SIZE);
+		}
+	}
+	if (dev->devtype->product != CODA_960)
+		coda_write(dev, 0, CODA_CMD_DEC_SEQ_SRC_SIZE);
+
+	if (coda_command_sync(ctx, CODA_COMMAND_SEQ_INIT)) {
+		v4l2_err(&dev->v4l2_dev, "CODA_COMMAND_SEQ_INIT timeout\n");
+		coda_write(dev, 0, CODA_REG_BIT_BIT_STREAM_PARAM);
+		return -ETIMEDOUT;
+	}
+
+	/* Update kfifo out pointer from coda bitstream read pointer */
+	coda_kfifo_sync_from_device(ctx);
+
+	coda_write(dev, 0, CODA_REG_BIT_BIT_STREAM_PARAM);
+
+	if (coda_read(dev, CODA_RET_DEC_SEQ_SUCCESS) == 0) {
+		v4l2_err(&dev->v4l2_dev,
+			"CODA_COMMAND_SEQ_INIT failed, error code = %d\n",
+			coda_read(dev, CODA_RET_DEC_SEQ_ERR_REASON));
+		return -EAGAIN;
+	}
+
+	val = coda_read(dev, CODA_RET_DEC_SEQ_SRC_SIZE);
+	if (dev->devtype->product == CODA_DX6) {
+		width = (val >> CODADX6_PICWIDTH_OFFSET) & CODADX6_PICWIDTH_MASK;
+		height = val & CODADX6_PICHEIGHT_MASK;
+	} else {
+		width = (val >> CODA7_PICWIDTH_OFFSET) & CODA7_PICWIDTH_MASK;
+		height = val & CODA7_PICHEIGHT_MASK;
+	}
+
+	if (width > q_data_dst->width || height > q_data_dst->height) {
+		v4l2_err(&dev->v4l2_dev, "stream is %dx%d, not %dx%d\n",
+			 width, height, q_data_dst->width, q_data_dst->height);
+		return -EINVAL;
+	}
+
+	width = round_up(width, 16);
+	height = round_up(height, 16);
+
+	v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "%s instance %d now: %dx%d\n",
+		 __func__, ctx->idx, width, height);
+
+	ctx->num_internal_frames = coda_read(dev, CODA_RET_DEC_SEQ_FRAME_NEED);
+	if (ctx->num_internal_frames > CODA_MAX_FRAMEBUFFERS) {
+		v4l2_err(&dev->v4l2_dev,
+			 "not enough framebuffers to decode (%d < %d)\n",
+			 CODA_MAX_FRAMEBUFFERS, ctx->num_internal_frames);
+		return -EINVAL;
+	}
+
+	if (src_fourcc == V4L2_PIX_FMT_H264) {
+		u32 left_right;
+		u32 top_bottom;
+
+		left_right = coda_read(dev, CODA_RET_DEC_SEQ_CROP_LEFT_RIGHT);
+		top_bottom = coda_read(dev, CODA_RET_DEC_SEQ_CROP_TOP_BOTTOM);
+
+		q_data_dst->rect.left = (left_right >> 10) & 0x3ff;
+		q_data_dst->rect.top = (top_bottom >> 10) & 0x3ff;
+		q_data_dst->rect.width = width - q_data_dst->rect.left -
+					 (left_right & 0x3ff);
+		q_data_dst->rect.height = height - q_data_dst->rect.top -
+					  (top_bottom & 0x3ff);
+	}
+
+	ret = coda_alloc_framebuffers(ctx, q_data_dst, src_fourcc);
+	if (ret < 0) {
+		v4l2_err(&dev->v4l2_dev, "failed to allocate framebuffers\n");
+		return ret;
+	}
+
+	/* Tell the decoder how many frame buffers we allocated. */
+	coda_write(dev, ctx->num_internal_frames, CODA_CMD_SET_FRAME_BUF_NUM);
+	coda_write(dev, width, CODA_CMD_SET_FRAME_BUF_STRIDE);
+
+	if (dev->devtype->product != CODA_DX6) {
+		/* Set secondary AXI IRAM */
+		coda_setup_iram(ctx);
+
+		coda_write(dev, ctx->iram_info.buf_bit_use,
+				CODA7_CMD_SET_FRAME_AXI_BIT_ADDR);
+		coda_write(dev, ctx->iram_info.buf_ip_ac_dc_use,
+				CODA7_CMD_SET_FRAME_AXI_IPACDC_ADDR);
+		coda_write(dev, ctx->iram_info.buf_dbk_y_use,
+				CODA7_CMD_SET_FRAME_AXI_DBKY_ADDR);
+		coda_write(dev, ctx->iram_info.buf_dbk_c_use,
+				CODA7_CMD_SET_FRAME_AXI_DBKC_ADDR);
+		coda_write(dev, ctx->iram_info.buf_ovl_use,
+				CODA7_CMD_SET_FRAME_AXI_OVL_ADDR);
+		if (dev->devtype->product == CODA_960)
+			coda_write(dev, ctx->iram_info.buf_btp_use,
+					CODA9_CMD_SET_FRAME_AXI_BTP_ADDR);
+	}
+
+	if (dev->devtype->product == CODA_960) {
+		coda_write(dev, -1, CODA9_CMD_SET_FRAME_DELAY);
+
+		coda_write(dev, 0x20262024, CODA9_CMD_SET_FRAME_CACHE_SIZE);
+		coda_write(dev, 2 << CODA9_CACHE_PAGEMERGE_OFFSET |
+				32 << CODA9_CACHE_LUMA_BUFFER_SIZE_OFFSET |
+				8 << CODA9_CACHE_CB_BUFFER_SIZE_OFFSET |
+				8 << CODA9_CACHE_CR_BUFFER_SIZE_OFFSET,
+				CODA9_CMD_SET_FRAME_CACHE_CONFIG);
+	}
+
+	if (src_fourcc == V4L2_PIX_FMT_H264) {
+		coda_write(dev, ctx->slicebuf.paddr,
+				CODA_CMD_SET_FRAME_SLICE_BB_START);
+		coda_write(dev, ctx->slicebuf.size / 1024,
+				CODA_CMD_SET_FRAME_SLICE_BB_SIZE);
+	}
+
+	if (dev->devtype->product == CODA_7541) {
+		int max_mb_x = 1920 / 16;
+		int max_mb_y = 1088 / 16;
+		int max_mb_num = max_mb_x * max_mb_y;
+
+		coda_write(dev, max_mb_num << 16 | max_mb_x << 8 | max_mb_y,
+				CODA7_CMD_SET_FRAME_MAX_DEC_SIZE);
+	} else if (dev->devtype->product == CODA_960) {
+		int max_mb_x = 1920 / 16;
+		int max_mb_y = 1088 / 16;
+		int max_mb_num = max_mb_x * max_mb_y;
+
+		coda_write(dev, max_mb_num << 16 | max_mb_x << 8 | max_mb_y,
+				CODA9_CMD_SET_FRAME_MAX_DEC_SIZE);
+	}
+
+	if (coda_command_sync(ctx, CODA_COMMAND_SET_FRAME_BUF)) {
+		v4l2_err(&ctx->dev->v4l2_dev,
+			 "CODA_COMMAND_SET_FRAME_BUF timeout\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static int coda_start_decoding(struct coda_ctx *ctx)
+{
+	struct coda_dev *dev = ctx->dev;
+	int ret;
+
+	mutex_lock(&dev->coda_mutex);
+	ret = __coda_start_decoding(ctx);
+	mutex_unlock(&dev->coda_mutex);
+
+	return ret;
+}
+
+static int coda_prepare_decode(struct coda_ctx *ctx)
+{
+	struct vb2_buffer *dst_buf;
+	struct coda_dev *dev = ctx->dev;
+	struct coda_q_data *q_data_dst;
+	u32 stridey, height;
+	u32 picture_y, picture_cb, picture_cr;
+
+	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+
+	if (ctx->params.rot_mode & CODA_ROT_90) {
+		stridey = q_data_dst->height;
+		height = q_data_dst->width;
+	} else {
+		stridey = q_data_dst->width;
+		height = q_data_dst->height;
+	}
+
+	/* Try to copy source buffer contents into the bitstream ringbuffer */
+	mutex_lock(&ctx->bitstream_mutex);
+	coda_fill_bitstream(ctx);
+	mutex_unlock(&ctx->bitstream_mutex);
+
+	if (coda_get_bitstream_payload(ctx) < 512 &&
+	    (!(ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG))) {
+		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
+			 "bitstream payload: %d, skipping\n",
+			 coda_get_bitstream_payload(ctx));
+		v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx);
+		return -EAGAIN;
+	}
+
+	/* Run coda_start_decoding (again) if not yet initialized */
+	if (!ctx->initialized) {
+		int ret = __coda_start_decoding(ctx);
+
+		if (ret < 0) {
+			v4l2_err(&dev->v4l2_dev, "failed to start decoding\n");
+			v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx);
+			return -EAGAIN;
+		} else {
+			ctx->initialized = 1;
+		}
+	}
+
+	if (dev->devtype->product == CODA_960)
+		coda_set_gdi_regs(ctx);
+
+	/* Set rotator output */
+	picture_y = vb2_dma_contig_plane_dma_addr(dst_buf, 0);
+	if (q_data_dst->fourcc == V4L2_PIX_FMT_YVU420) {
+		/* Switch Cr and Cb for YVU420 format */
+		picture_cr = picture_y + stridey * height;
+		picture_cb = picture_cr + stridey / 2 * height / 2;
+	} else {
+		picture_cb = picture_y + stridey * height;
+		picture_cr = picture_cb + stridey / 2 * height / 2;
+	}
+
+	if (dev->devtype->product == CODA_960) {
+		/*
+		 * The CODA960 seems to have an internal list of buffers with
+		 * 64 entries that includes the registered frame buffers as
+		 * well as the rotator buffer output.
+		 * ROT_INDEX needs to be < 0x40, but > ctx->num_internal_frames.
+		 */
+		coda_write(dev, CODA_MAX_FRAMEBUFFERS + dst_buf->v4l2_buf.index,
+				CODA9_CMD_DEC_PIC_ROT_INDEX);
+		coda_write(dev, picture_y, CODA9_CMD_DEC_PIC_ROT_ADDR_Y);
+		coda_write(dev, picture_cb, CODA9_CMD_DEC_PIC_ROT_ADDR_CB);
+		coda_write(dev, picture_cr, CODA9_CMD_DEC_PIC_ROT_ADDR_CR);
+		coda_write(dev, stridey, CODA9_CMD_DEC_PIC_ROT_STRIDE);
+	} else {
+		coda_write(dev, picture_y, CODA_CMD_DEC_PIC_ROT_ADDR_Y);
+		coda_write(dev, picture_cb, CODA_CMD_DEC_PIC_ROT_ADDR_CB);
+		coda_write(dev, picture_cr, CODA_CMD_DEC_PIC_ROT_ADDR_CR);
+		coda_write(dev, stridey, CODA_CMD_DEC_PIC_ROT_STRIDE);
+	}
+	coda_write(dev, CODA_ROT_MIR_ENABLE | ctx->params.rot_mode,
+			CODA_CMD_DEC_PIC_ROT_MODE);
+
+	switch (dev->devtype->product) {
+	case CODA_DX6:
+		/* TBD */
+	case CODA_7541:
+		coda_write(dev, CODA_PRE_SCAN_EN, CODA_CMD_DEC_PIC_OPTION);
+		break;
+	case CODA_960:
+		/* 'hardcode to use interrupt disable mode'? */
+		coda_write(dev, (1 << 10), CODA_CMD_DEC_PIC_OPTION);
+		break;
+	}
+
+	coda_write(dev, 0, CODA_CMD_DEC_PIC_SKIP_NUM);
+
+	coda_write(dev, 0, CODA_CMD_DEC_PIC_BB_START);
+	coda_write(dev, 0, CODA_CMD_DEC_PIC_START_BYTE);
+
+	if (dev->devtype->product != CODA_DX6)
+		coda_write(dev, ctx->iram_info.axi_sram_use,
+				CODA7_REG_BIT_AXI_SRAM_USE);
+
+	coda_kfifo_sync_to_device_full(ctx);
+
+	coda_command_async(ctx, CODA_COMMAND_PIC_RUN);
+
+	return 0;
+}
+
+static void coda_finish_decode(struct coda_ctx *ctx)
+{
+	struct coda_dev *dev = ctx->dev;
+	struct coda_q_data *q_data_src;
+	struct coda_q_data *q_data_dst;
+	struct vb2_buffer *dst_buf;
+	struct coda_timestamp *ts;
+	int width, height;
+	int decoded_idx;
+	int display_idx;
+	u32 src_fourcc;
+	int success;
+	u32 err_mb;
+	u32 val;
+
+	/* Update kfifo out pointer from coda bitstream read pointer */
+	coda_kfifo_sync_from_device(ctx);
+
+	/*
+	 * in stream-end mode, the read pointer can overshoot the write pointer
+	 * by up to 512 bytes
+	 */
+	if (ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG) {
+		if (coda_get_bitstream_payload(ctx) >= CODA_MAX_FRAME_SIZE - 512)
+			kfifo_init(&ctx->bitstream_fifo,
+				ctx->bitstream.vaddr, ctx->bitstream.size);
+	}
+
+	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	src_fourcc = q_data_src->fourcc;
+
+	val = coda_read(dev, CODA_RET_DEC_PIC_SUCCESS);
+	if (val != 1)
+		pr_err("DEC_PIC_SUCCESS = %d\n", val);
+
+	success = val & 0x1;
+	if (!success)
+		v4l2_err(&dev->v4l2_dev, "decode failed\n");
+
+	if (src_fourcc == V4L2_PIX_FMT_H264) {
+		if (val & (1 << 3))
+			v4l2_err(&dev->v4l2_dev,
+				 "insufficient PS buffer space (%d bytes)\n",
+				 ctx->psbuf.size);
+		if (val & (1 << 2))
+			v4l2_err(&dev->v4l2_dev,
+				 "insufficient slice buffer space (%d bytes)\n",
+				 ctx->slicebuf.size);
+	}
+
+	val = coda_read(dev, CODA_RET_DEC_PIC_SIZE);
+	width = (val >> 16) & 0xffff;
+	height = val & 0xffff;
+
+	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+
+	/* frame crop information */
+	if (src_fourcc == V4L2_PIX_FMT_H264) {
+		u32 left_right;
+		u32 top_bottom;
+
+		left_right = coda_read(dev, CODA_RET_DEC_PIC_CROP_LEFT_RIGHT);
+		top_bottom = coda_read(dev, CODA_RET_DEC_PIC_CROP_TOP_BOTTOM);
+
+		if (left_right == 0xffffffff && top_bottom == 0xffffffff) {
+			/* Keep current crop information */
+		} else {
+			struct v4l2_rect *rect = &q_data_dst->rect;
+
+			rect->left = left_right >> 16 & 0xffff;
+			rect->top = top_bottom >> 16 & 0xffff;
+			rect->width = width - rect->left -
+				      (left_right & 0xffff);
+			rect->height = height - rect->top -
+				       (top_bottom & 0xffff);
+		}
+	} else {
+		/* no cropping */
+	}
+
+	err_mb = coda_read(dev, CODA_RET_DEC_PIC_ERR_MB);
+	if (err_mb > 0)
+		v4l2_err(&dev->v4l2_dev,
+			 "errors in %d macroblocks\n", err_mb);
+
+	if (dev->devtype->product == CODA_7541) {
+		val = coda_read(dev, CODA_RET_DEC_PIC_OPTION);
+		if (val == 0) {
+			/* not enough bitstream data */
+			v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
+				 "prescan failed: %d\n", val);
+			ctx->hold = true;
+			return;
+		}
+	}
+
+	ctx->frm_dis_flg = coda_read(dev,
+				     CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));
+
+	/*
+	 * The previous display frame was copied out by the rotator,
+	 * now it can be overwritten again
+	 */
+	if (ctx->display_idx >= 0 &&
+	    ctx->display_idx < ctx->num_internal_frames) {
+		ctx->frm_dis_flg &= ~(1 << ctx->display_idx);
+		coda_write(dev, ctx->frm_dis_flg,
+				CODA_REG_BIT_FRM_DIS_FLG(ctx->reg_idx));
+	}
+
+	/*
+	 * The index of the last decoded frame, not necessarily in
+	 * display order, and the index of the next display frame.
+	 * The latter could have been decoded in a previous run.
+	 */
+	decoded_idx = coda_read(dev, CODA_RET_DEC_PIC_CUR_IDX);
+	display_idx = coda_read(dev, CODA_RET_DEC_PIC_FRAME_IDX);
+
+	if (decoded_idx == -1) {
+		/* no frame was decoded, but we might have a display frame */
+		if (display_idx >= 0 && display_idx < ctx->num_internal_frames)
+			ctx->sequence_offset++;
+		else if (ctx->display_idx < 0)
+			ctx->hold = true;
+	} else if (decoded_idx == -2) {
+		/* no frame was decoded, we still return remaining buffers */
+	} else if (decoded_idx < 0 || decoded_idx >= ctx->num_internal_frames) {
+		v4l2_err(&dev->v4l2_dev,
+			 "decoded frame index out of range: %d\n", decoded_idx);
+	} else {
+		val = coda_read(dev, CODA_RET_DEC_PIC_FRAME_NUM) - 1;
+		val -= ctx->sequence_offset;
+		mutex_lock(&ctx->bitstream_mutex);
+		if (!list_empty(&ctx->timestamp_list)) {
+			ts = list_first_entry(&ctx->timestamp_list,
+					      struct coda_timestamp, list);
+			list_del(&ts->list);
+			if (val != (ts->sequence & 0xffff)) {
+				v4l2_err(&dev->v4l2_dev,
+					 "sequence number mismatch (%d(%d) != %d)\n",
+					 val, ctx->sequence_offset,
+					 ts->sequence);
+			}
+			ctx->frame_timestamps[decoded_idx] = *ts;
+			kfree(ts);
+		} else {
+			v4l2_err(&dev->v4l2_dev, "empty timestamp list!\n");
+			memset(&ctx->frame_timestamps[decoded_idx], 0,
+			       sizeof(struct coda_timestamp));
+			ctx->frame_timestamps[decoded_idx].sequence = val;
+		}
+		mutex_unlock(&ctx->bitstream_mutex);
+
+		val = coda_read(dev, CODA_RET_DEC_PIC_TYPE) & 0x7;
+		if (val == 0)
+			ctx->frame_types[decoded_idx] = V4L2_BUF_FLAG_KEYFRAME;
+		else if (val == 1)
+			ctx->frame_types[decoded_idx] = V4L2_BUF_FLAG_PFRAME;
+		else
+			ctx->frame_types[decoded_idx] = V4L2_BUF_FLAG_BFRAME;
+
+		ctx->frame_errors[decoded_idx] = err_mb;
+	}
+
+	if (display_idx == -1) {
+		/*
+		 * no more frames to be decoded, but there could still
+		 * be rotator output to dequeue
+		 */
+		ctx->hold = true;
+	} else if (display_idx == -3) {
+		/* possibly prescan failure */
+	} else if (display_idx < 0 || display_idx >= ctx->num_internal_frames) {
+		v4l2_err(&dev->v4l2_dev,
+			 "presentation frame index out of range: %d\n",
+			 display_idx);
+	}
+
+	/* If a frame was copied out, return it */
+	if (ctx->display_idx >= 0 &&
+	    ctx->display_idx < ctx->num_internal_frames) {
+		dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+		dst_buf->v4l2_buf.sequence = ctx->osequence++;
+
+		dst_buf->v4l2_buf.flags &= ~(V4L2_BUF_FLAG_KEYFRAME |
+					     V4L2_BUF_FLAG_PFRAME |
+					     V4L2_BUF_FLAG_BFRAME);
+		dst_buf->v4l2_buf.flags |= ctx->frame_types[ctx->display_idx];
+		ts = &ctx->frame_timestamps[ctx->display_idx];
+		dst_buf->v4l2_buf.timecode = ts->timecode;
+		dst_buf->v4l2_buf.timestamp = ts->timestamp;
+
+		vb2_set_plane_payload(dst_buf, 0, width * height * 3 / 2);
+
+		v4l2_m2m_buf_done(dst_buf, ctx->frame_errors[display_idx] ?
+				  VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
+
+		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
+			"job finished: decoding frame (%d) (%s)\n",
+			dst_buf->v4l2_buf.sequence,
+			(dst_buf->v4l2_buf.flags & V4L2_BUF_FLAG_KEYFRAME) ?
+			"KEYFRAME" : "PFRAME");
+	} else {
+		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
+			"job finished: no frame decoded\n");
+	}
+
+	/* The rotator will copy the current display frame next time */
+	ctx->display_idx = display_idx;
+}
+
+const struct coda_context_ops coda_bit_decode_ops = {
+	.queue_init = coda_decoder_queue_init,
+	.start_streaming = coda_start_decoding,
+	.prepare_run = coda_prepare_decode,
+	.finish_run = coda_finish_decode,
+	.seq_end_work = coda_seq_end_work,
+	.release = coda_bit_release,
+};
+
+irqreturn_t coda_irq_handler(int irq, void *data)
+{
+	struct coda_dev *dev = data;
+	struct coda_ctx *ctx;
+
+	/* read status register to attend the IRQ */
+	coda_read(dev, CODA_REG_BIT_INT_STATUS);
+	coda_write(dev, CODA_REG_BIT_INT_CLEAR_SET,
+		      CODA_REG_BIT_INT_CLEAR);
+
+	ctx = v4l2_m2m_get_curr_priv(dev->m2m_dev);
+	if (ctx == NULL) {
+		v4l2_err(&dev->v4l2_dev,
+			 "Instance released before the end of transaction\n");
+		mutex_unlock(&dev->coda_mutex);
+		return IRQ_HANDLED;
+	}
+
+	if (ctx->aborting) {
+		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+			 "task has been aborted\n");
+	}
+
+	if (coda_isbusy(ctx->dev)) {
+		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+			 "coda is still busy!!!!\n");
+		return IRQ_NONE;
+	}
+
+	complete(&ctx->completion);
+
+	return IRQ_HANDLED;
+}
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
new file mode 100644
index 000000000000..ced47609f5ef
--- /dev/null
+++ b/drivers/media/platform/coda/coda-common.c
@@ -0,0 +1,2052 @@
+/*
+ * Coda multi-standard codec IP
+ *
+ * Copyright (C) 2012 Vista Silicon S.L.
+ *    Javier Martin, <javier.martin@vista-silicon.com>
+ *    Xavier Duret
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/firmware.h>
+#include <linux/genalloc.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kfifo.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/videodev2.h>
+#include <linux/of.h>
+#include <linux/platform_data/coda.h>
+#include <linux/reset.h>
+
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "coda.h"
+
+#define CODA_NAME		"coda"
+
+#define CODADX6_MAX_INSTANCES	4
+
+#define CODA_PARA_BUF_SIZE	(10 * 1024)
+#define CODA_ISRAM_SIZE	(2048 * 2)
+
+#define MIN_W 176
+#define MIN_H 144
+
+#define S_ALIGN		1 /* multiple of 2 */
+#define W_ALIGN		1 /* multiple of 2 */
+#define H_ALIGN		1 /* multiple of 2 */
+
+#define fh_to_ctx(__fh)	container_of(__fh, struct coda_ctx, fh)
+
+int coda_debug;
+module_param(coda_debug, int, 0644);
+MODULE_PARM_DESC(coda_debug, "Debug level (0-2)");
+
+struct coda_fmt {
+	char *name;
+	u32 fourcc;
+};
+
+void coda_write(struct coda_dev *dev, u32 data, u32 reg)
+{
+	v4l2_dbg(2, coda_debug, &dev->v4l2_dev,
+		 "%s: data=0x%x, reg=0x%x\n", __func__, data, reg);
+	writel(data, dev->regs_base + reg);
+}
+
+unsigned int coda_read(struct coda_dev *dev, u32 reg)
+{
+	u32 data;
+
+	data = readl(dev->regs_base + reg);
+	v4l2_dbg(2, coda_debug, &dev->v4l2_dev,
+		 "%s: data=0x%x, reg=0x%x\n", __func__, data, reg);
+	return data;
+}
+
+/*
+ * Array of all formats supported by any version of Coda:
+ */
+static const struct coda_fmt coda_formats[] = {
+	{
+		.name = "YUV 4:2:0 Planar, YCbCr",
+		.fourcc = V4L2_PIX_FMT_YUV420,
+	},
+	{
+		.name = "YUV 4:2:0 Planar, YCrCb",
+		.fourcc = V4L2_PIX_FMT_YVU420,
+	},
+	{
+		.name = "H264 Encoded Stream",
+		.fourcc = V4L2_PIX_FMT_H264,
+	},
+	{
+		.name = "MPEG4 Encoded Stream",
+		.fourcc = V4L2_PIX_FMT_MPEG4,
+	},
+};
+
+#define CODA_CODEC(mode, src_fourcc, dst_fourcc, max_w, max_h) \
+	{ mode, src_fourcc, dst_fourcc, max_w, max_h }
+
+/*
+ * Arrays of codecs supported by each given version of Coda:
+ *  i.MX27 -> codadx6
+ *  i.MX5x -> coda7
+ *  i.MX6  -> coda960
+ * Use V4L2_PIX_FMT_YUV420 as placeholder for all supported YUV 4:2:0 variants
+ */
+static const struct coda_codec codadx6_codecs[] = {
+	CODA_CODEC(CODADX6_MODE_ENCODE_H264, V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_H264,  720, 576),
+	CODA_CODEC(CODADX6_MODE_ENCODE_MP4,  V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_MPEG4, 720, 576),
+};
+
+static const struct coda_codec coda7_codecs[] = {
+	CODA_CODEC(CODA7_MODE_ENCODE_H264, V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_H264,   1280, 720),
+	CODA_CODEC(CODA7_MODE_ENCODE_MP4,  V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_MPEG4,  1280, 720),
+	CODA_CODEC(CODA7_MODE_DECODE_H264, V4L2_PIX_FMT_H264,   V4L2_PIX_FMT_YUV420, 1920, 1088),
+	CODA_CODEC(CODA7_MODE_DECODE_MP4,  V4L2_PIX_FMT_MPEG4,  V4L2_PIX_FMT_YUV420, 1920, 1088),
+};
+
+static const struct coda_codec coda9_codecs[] = {
+	CODA_CODEC(CODA9_MODE_ENCODE_H264, V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_H264,   1920, 1088),
+	CODA_CODEC(CODA9_MODE_ENCODE_MP4,  V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_MPEG4,  1920, 1088),
+	CODA_CODEC(CODA9_MODE_DECODE_H264, V4L2_PIX_FMT_H264,   V4L2_PIX_FMT_YUV420, 1920, 1088),
+	CODA_CODEC(CODA9_MODE_DECODE_MP4,  V4L2_PIX_FMT_MPEG4,  V4L2_PIX_FMT_YUV420, 1920, 1088),
+};
+
+static bool coda_format_is_yuv(u32 fourcc)
+{
+	switch (fourcc) {
+	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_YVU420:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/*
+ * Normalize all supported YUV 4:2:0 formats to the value used in the codec
+ * tables.
+ */
+static u32 coda_format_normalize_yuv(u32 fourcc)
+{
+	return coda_format_is_yuv(fourcc) ? V4L2_PIX_FMT_YUV420 : fourcc;
+}
+
+static const struct coda_codec *coda_find_codec(struct coda_dev *dev,
+						int src_fourcc, int dst_fourcc)
+{
+	const struct coda_codec *codecs = dev->devtype->codecs;
+	int num_codecs = dev->devtype->num_codecs;
+	int k;
+
+	src_fourcc = coda_format_normalize_yuv(src_fourcc);
+	dst_fourcc = coda_format_normalize_yuv(dst_fourcc);
+	if (src_fourcc == dst_fourcc)
+		return NULL;
+
+	for (k = 0; k < num_codecs; k++) {
+		if (codecs[k].src_fourcc == src_fourcc &&
+		    codecs[k].dst_fourcc == dst_fourcc)
+			break;
+	}
+
+	if (k == num_codecs)
+		return NULL;
+
+	return &codecs[k];
+}
+
+static void coda_get_max_dimensions(struct coda_dev *dev,
+				    const struct coda_codec *codec,
+				    int *max_w, int *max_h)
+{
+	const struct coda_codec *codecs = dev->devtype->codecs;
+	int num_codecs = dev->devtype->num_codecs;
+	unsigned int w, h;
+	int k;
+
+	if (codec) {
+		w = codec->max_w;
+		h = codec->max_h;
+	} else {
+		for (k = 0, w = 0, h = 0; k < num_codecs; k++) {
+			w = max(w, codecs[k].max_w);
+			h = max(h, codecs[k].max_h);
+		}
+	}
+
+	if (max_w)
+		*max_w = w;
+	if (max_h)
+		*max_h = h;
+}
+
+const char *coda_product_name(int product)
+{
+	static char buf[9];
+
+	switch (product) {
+	case CODA_DX6:
+		return "CodaDx6";
+	case CODA_7541:
+		return "CODA7541";
+	case CODA_960:
+		return "CODA960";
+	default:
+		snprintf(buf, sizeof(buf), "(0x%04x)", product);
+		return buf;
+	}
+}
+
+/*
+ * V4L2 ioctl() operations.
+ */
+static int coda_querycap(struct file *file, void *priv,
+			 struct v4l2_capability *cap)
+{
+	struct coda_ctx *ctx = fh_to_ctx(priv);
+
+	strlcpy(cap->driver, CODA_NAME, sizeof(cap->driver));
+	strlcpy(cap->card, coda_product_name(ctx->dev->devtype->product),
+		sizeof(cap->card));
+	strlcpy(cap->bus_info, "platform:" CODA_NAME, sizeof(cap->bus_info));
+	cap->device_caps = V4L2_CAP_VIDEO_M2M | V4L2_CAP_STREAMING;
+	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
+
+	return 0;
+}
+
+static int coda_enum_fmt(struct file *file, void *priv,
+			 struct v4l2_fmtdesc *f)
+{
+	struct coda_ctx *ctx = fh_to_ctx(priv);
+	const struct coda_codec *codecs = ctx->dev->devtype->codecs;
+	const struct coda_fmt *formats = coda_formats;
+	const struct coda_fmt *fmt;
+	int num_codecs = ctx->dev->devtype->num_codecs;
+	int num_formats = ARRAY_SIZE(coda_formats);
+	int i, k, num = 0;
+	bool yuv;
+
+	if (ctx->inst_type == CODA_INST_ENCODER)
+		yuv = (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	else
+		yuv = (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE);
+
+	for (i = 0; i < num_formats; i++) {
+		/* Skip either raw or compressed formats */
+		if (yuv != coda_format_is_yuv(formats[i].fourcc))
+			continue;
+		/* All uncompressed formats are always supported */
+		if (yuv) {
+			if (num == f->index)
+				break;
+			++num;
+			continue;
+		}
+		/* Compressed formats may be supported, check the codec list */
+		for (k = 0; k < num_codecs; k++) {
+			if (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE &&
+			    formats[i].fourcc == codecs[k].dst_fourcc)
+				break;
+			if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT &&
+			    formats[i].fourcc == codecs[k].src_fourcc)
+				break;
+		}
+		if (k < num_codecs) {
+			if (num == f->index)
+				break;
+			++num;
+		}
+	}
+
+	if (i < num_formats) {
+		fmt = &formats[i];
+		strlcpy(f->description, fmt->name, sizeof(f->description));
+		f->pixelformat = fmt->fourcc;
+		if (!yuv)
+			f->flags |= V4L2_FMT_FLAG_COMPRESSED;
+		return 0;
+	}
+
+	/* Format not found */
+	return -EINVAL;
+}
+
+static int coda_g_fmt(struct file *file, void *priv,
+		      struct v4l2_format *f)
+{
+	struct coda_q_data *q_data;
+	struct coda_ctx *ctx = fh_to_ctx(priv);
+
+	q_data = get_q_data(ctx, f->type);
+	if (!q_data)
+		return -EINVAL;
+
+	f->fmt.pix.field	= V4L2_FIELD_NONE;
+	f->fmt.pix.pixelformat	= q_data->fourcc;
+	f->fmt.pix.width	= q_data->width;
+	f->fmt.pix.height	= q_data->height;
+	f->fmt.pix.bytesperline = q_data->bytesperline;
+
+	f->fmt.pix.sizeimage	= q_data->sizeimage;
+	f->fmt.pix.colorspace	= ctx->colorspace;
+
+	return 0;
+}
+
+static int coda_try_fmt(struct coda_ctx *ctx, const struct coda_codec *codec,
+			struct v4l2_format *f)
+{
+	struct coda_dev *dev = ctx->dev;
+	struct coda_q_data *q_data;
+	unsigned int max_w, max_h;
+	enum v4l2_field field;
+
+	field = f->fmt.pix.field;
+	if (field == V4L2_FIELD_ANY)
+		field = V4L2_FIELD_NONE;
+	else if (V4L2_FIELD_NONE != field)
+		return -EINVAL;
+
+	/* V4L2 specification suggests the driver corrects the format struct
+	 * if any of the dimensions is unsupported */
+	f->fmt.pix.field = field;
+
+	coda_get_max_dimensions(dev, codec, &max_w, &max_h);
+	v4l_bound_align_image(&f->fmt.pix.width, MIN_W, max_w, W_ALIGN,
+			      &f->fmt.pix.height, MIN_H, max_h, H_ALIGN,
+			      S_ALIGN);
+
+	switch (f->fmt.pix.pixelformat) {
+	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_YVU420:
+	case V4L2_PIX_FMT_H264:
+	case V4L2_PIX_FMT_MPEG4:
+	case V4L2_PIX_FMT_JPEG:
+		break;
+	default:
+		q_data = get_q_data(ctx, f->type);
+		if (!q_data)
+			return -EINVAL;
+		f->fmt.pix.pixelformat = q_data->fourcc;
+	}
+
+	switch (f->fmt.pix.pixelformat) {
+	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_YVU420:
+		/* Frame stride must be multiple of 8, but 16 for h.264 */
+		f->fmt.pix.bytesperline = round_up(f->fmt.pix.width, 16);
+		f->fmt.pix.sizeimage = f->fmt.pix.bytesperline *
+					f->fmt.pix.height * 3 / 2;
+		break;
+	case V4L2_PIX_FMT_H264:
+	case V4L2_PIX_FMT_MPEG4:
+	case V4L2_PIX_FMT_JPEG:
+		f->fmt.pix.bytesperline = 0;
+		f->fmt.pix.sizeimage = CODA_MAX_FRAME_SIZE;
+		break;
+	default:
+		BUG();
+	}
+
+	return 0;
+}
+
+static int coda_try_fmt_vid_cap(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	struct coda_ctx *ctx = fh_to_ctx(priv);
+	const struct coda_codec *codec = NULL;
+	struct vb2_queue *src_vq;
+	int ret;
+
+	/*
+	 * If the source format is already fixed, try to find a codec that
+	 * converts to the given destination format
+	 */
+	src_vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	if (vb2_is_streaming(src_vq)) {
+		struct coda_q_data *q_data_src;
+
+		q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+		codec = coda_find_codec(ctx->dev, q_data_src->fourcc,
+					f->fmt.pix.pixelformat);
+		if (!codec)
+			return -EINVAL;
+
+		f->fmt.pix.width = q_data_src->width;
+		f->fmt.pix.height = q_data_src->height;
+	} else {
+		/* Otherwise determine codec by encoded format, if possible */
+		codec = coda_find_codec(ctx->dev, V4L2_PIX_FMT_YUV420,
+					f->fmt.pix.pixelformat);
+	}
+
+	f->fmt.pix.colorspace = ctx->colorspace;
+
+	ret = coda_try_fmt(ctx, codec, f);
+	if (ret < 0)
+		return ret;
+
+	/* The h.264 decoder only returns complete 16x16 macroblocks */
+	if (codec && codec->src_fourcc == V4L2_PIX_FMT_H264) {
+		f->fmt.pix.width = f->fmt.pix.width;
+		f->fmt.pix.height = round_up(f->fmt.pix.height, 16);
+		f->fmt.pix.bytesperline = round_up(f->fmt.pix.width, 16);
+		f->fmt.pix.sizeimage = f->fmt.pix.bytesperline *
+				       f->fmt.pix.height * 3 / 2;
+	}
+
+	return 0;
+}
+
+static int coda_try_fmt_vid_out(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	struct coda_ctx *ctx = fh_to_ctx(priv);
+	const struct coda_codec *codec = NULL;
+
+	/* Determine codec by encoded format, returns NULL if raw or invalid */
+	if (ctx->inst_type == CODA_INST_DECODER) {
+		codec = coda_find_codec(ctx->dev, f->fmt.pix.pixelformat,
+					V4L2_PIX_FMT_YUV420);
+		if (!codec)
+			codec = coda_find_codec(ctx->dev, V4L2_PIX_FMT_H264,
+						V4L2_PIX_FMT_YUV420);
+		if (!codec)
+			return -EINVAL;
+	}
+
+	if (!f->fmt.pix.colorspace)
+		f->fmt.pix.colorspace = V4L2_COLORSPACE_REC709;
+
+	return coda_try_fmt(ctx, codec, f);
+}
+
+static int coda_s_fmt(struct coda_ctx *ctx, struct v4l2_format *f)
+{
+	struct coda_q_data *q_data;
+	struct vb2_queue *vq;
+
+	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
+	if (!vq)
+		return -EINVAL;
+
+	q_data = get_q_data(ctx, f->type);
+	if (!q_data)
+		return -EINVAL;
+
+	if (vb2_is_busy(vq)) {
+		v4l2_err(&ctx->dev->v4l2_dev, "%s queue busy\n", __func__);
+		return -EBUSY;
+	}
+
+	q_data->fourcc = f->fmt.pix.pixelformat;
+	q_data->width = f->fmt.pix.width;
+	q_data->height = f->fmt.pix.height;
+	q_data->bytesperline = f->fmt.pix.bytesperline;
+	q_data->sizeimage = f->fmt.pix.sizeimage;
+	q_data->rect.left = 0;
+	q_data->rect.top = 0;
+	q_data->rect.width = f->fmt.pix.width;
+	q_data->rect.height = f->fmt.pix.height;
+
+	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+		"Setting format for type %d, wxh: %dx%d, fmt: %d\n",
+		f->type, q_data->width, q_data->height, q_data->fourcc);
+
+	return 0;
+}
+
+static int coda_s_fmt_vid_cap(struct file *file, void *priv,
+			      struct v4l2_format *f)
+{
+	struct coda_ctx *ctx = fh_to_ctx(priv);
+	int ret;
+
+	ret = coda_try_fmt_vid_cap(file, priv, f);
+	if (ret)
+		return ret;
+
+	return coda_s_fmt(ctx, f);
+}
+
+static int coda_s_fmt_vid_out(struct file *file, void *priv,
+			      struct v4l2_format *f)
+{
+	struct coda_ctx *ctx = fh_to_ctx(priv);
+	struct v4l2_format f_cap;
+	int ret;
+
+	ret = coda_try_fmt_vid_out(file, priv, f);
+	if (ret)
+		return ret;
+
+	ret = coda_s_fmt(ctx, f);
+	if (ret)
+		return ret;
+
+	ctx->colorspace = f->fmt.pix.colorspace;
+
+	f_cap.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	coda_g_fmt(file, priv, &f_cap);
+	f_cap.fmt.pix.width = f->fmt.pix.width;
+	f_cap.fmt.pix.height = f->fmt.pix.height;
+
+	ret = coda_try_fmt_vid_cap(file, priv, &f_cap);
+	if (ret)
+		return ret;
+
+	return coda_s_fmt(ctx, &f_cap);
+}
+
+static int coda_qbuf(struct file *file, void *priv,
+		     struct v4l2_buffer *buf)
+{
+	struct coda_ctx *ctx = fh_to_ctx(priv);
+
+	return v4l2_m2m_qbuf(file, ctx->fh.m2m_ctx, buf);
+}
+
+static bool coda_buf_is_end_of_stream(struct coda_ctx *ctx,
+				      struct v4l2_buffer *buf)
+{
+	struct vb2_queue *src_vq;
+
+	src_vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+
+	return ((ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG) &&
+		(buf->sequence == (ctx->qsequence - 1)));
+}
+
+static int coda_dqbuf(struct file *file, void *priv,
+		      struct v4l2_buffer *buf)
+{
+	struct coda_ctx *ctx = fh_to_ctx(priv);
+	int ret;
+
+	ret = v4l2_m2m_dqbuf(file, ctx->fh.m2m_ctx, buf);
+
+	/* If this is the last capture buffer, emit an end-of-stream event */
+	if (buf->type == V4L2_BUF_TYPE_VIDEO_CAPTURE &&
+	    coda_buf_is_end_of_stream(ctx, buf)) {
+		const struct v4l2_event eos_event = {
+			.type = V4L2_EVENT_EOS
+		};
+
+		v4l2_event_queue_fh(&ctx->fh, &eos_event);
+	}
+
+	return ret;
+}
+
+static int coda_g_selection(struct file *file, void *fh,
+			    struct v4l2_selection *s)
+{
+	struct coda_ctx *ctx = fh_to_ctx(fh);
+	struct coda_q_data *q_data;
+	struct v4l2_rect r, *rsel;
+
+	q_data = get_q_data(ctx, s->type);
+	if (!q_data)
+		return -EINVAL;
+
+	r.left = 0;
+	r.top = 0;
+	r.width = q_data->width;
+	r.height = q_data->height;
+	rsel = &q_data->rect;
+
+	switch (s->target) {
+	case V4L2_SEL_TGT_CROP_DEFAULT:
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+		rsel = &r;
+		/* fallthrough */
+	case V4L2_SEL_TGT_CROP:
+		if (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT)
+			return -EINVAL;
+		break;
+	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
+	case V4L2_SEL_TGT_COMPOSE_PADDED:
+		rsel = &r;
+		/* fallthrough */
+	case V4L2_SEL_TGT_COMPOSE:
+	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
+		if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	s->r = *rsel;
+
+	return 0;
+}
+
+static int coda_try_decoder_cmd(struct file *file, void *fh,
+				struct v4l2_decoder_cmd *dc)
+{
+	if (dc->cmd != V4L2_DEC_CMD_STOP)
+		return -EINVAL;
+
+	if (dc->flags & V4L2_DEC_CMD_STOP_TO_BLACK)
+		return -EINVAL;
+
+	if (!(dc->flags & V4L2_DEC_CMD_STOP_IMMEDIATELY) && (dc->stop.pts != 0))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int coda_decoder_cmd(struct file *file, void *fh,
+			    struct v4l2_decoder_cmd *dc)
+{
+	struct coda_ctx *ctx = fh_to_ctx(fh);
+	int ret;
+
+	ret = coda_try_decoder_cmd(file, fh, dc);
+	if (ret < 0)
+		return ret;
+
+	/* Ignore decoder stop command silently in encoder context */
+	if (ctx->inst_type != CODA_INST_DECODER)
+		return 0;
+
+	/* Set the stream-end flag on this context */
+	coda_bit_stream_end_flag(ctx);
+	ctx->hold = false;
+	v4l2_m2m_try_schedule(ctx->fh.m2m_ctx);
+
+	return 0;
+}
+
+static int coda_subscribe_event(struct v4l2_fh *fh,
+				const struct v4l2_event_subscription *sub)
+{
+	switch (sub->type) {
+	case V4L2_EVENT_EOS:
+		return v4l2_event_subscribe(fh, sub, 0, NULL);
+	default:
+		return v4l2_ctrl_subscribe_event(fh, sub);
+	}
+}
+
+static const struct v4l2_ioctl_ops coda_ioctl_ops = {
+	.vidioc_querycap	= coda_querycap,
+
+	.vidioc_enum_fmt_vid_cap = coda_enum_fmt,
+	.vidioc_g_fmt_vid_cap	= coda_g_fmt,
+	.vidioc_try_fmt_vid_cap	= coda_try_fmt_vid_cap,
+	.vidioc_s_fmt_vid_cap	= coda_s_fmt_vid_cap,
+
+	.vidioc_enum_fmt_vid_out = coda_enum_fmt,
+	.vidioc_g_fmt_vid_out	= coda_g_fmt,
+	.vidioc_try_fmt_vid_out	= coda_try_fmt_vid_out,
+	.vidioc_s_fmt_vid_out	= coda_s_fmt_vid_out,
+
+	.vidioc_reqbufs		= v4l2_m2m_ioctl_reqbufs,
+	.vidioc_querybuf	= v4l2_m2m_ioctl_querybuf,
+
+	.vidioc_qbuf		= coda_qbuf,
+	.vidioc_expbuf		= v4l2_m2m_ioctl_expbuf,
+	.vidioc_dqbuf		= coda_dqbuf,
+	.vidioc_create_bufs	= v4l2_m2m_ioctl_create_bufs,
+
+	.vidioc_streamon	= v4l2_m2m_ioctl_streamon,
+	.vidioc_streamoff	= v4l2_m2m_ioctl_streamoff,
+
+	.vidioc_g_selection	= coda_g_selection,
+
+	.vidioc_try_decoder_cmd	= coda_try_decoder_cmd,
+	.vidioc_decoder_cmd	= coda_decoder_cmd,
+
+	.vidioc_subscribe_event = coda_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
+};
+
+void coda_set_gdi_regs(struct coda_ctx *ctx)
+{
+	struct gdi_tiled_map *tiled_map = &ctx->tiled_map;
+	struct coda_dev *dev = ctx->dev;
+	int i;
+
+	for (i = 0; i < 16; i++)
+		coda_write(dev, tiled_map->xy2ca_map[i],
+				CODA9_GDI_XY2_CAS_0 + 4 * i);
+	for (i = 0; i < 4; i++)
+		coda_write(dev, tiled_map->xy2ba_map[i],
+				CODA9_GDI_XY2_BA_0 + 4 * i);
+	for (i = 0; i < 16; i++)
+		coda_write(dev, tiled_map->xy2ra_map[i],
+				CODA9_GDI_XY2_RAS_0 + 4 * i);
+	coda_write(dev, tiled_map->xy2rbc_config, CODA9_GDI_XY2_RBC_CONFIG);
+	for (i = 0; i < 32; i++)
+		coda_write(dev, tiled_map->rbc2axi_map[i],
+				CODA9_GDI_RBC2_AXI_0 + 4 * i);
+}
+
+/*
+ * Mem-to-mem operations.
+ */
+
+static void coda_device_run(void *m2m_priv)
+{
+	struct coda_ctx *ctx = m2m_priv;
+	struct coda_dev *dev = ctx->dev;
+
+	queue_work(dev->workqueue, &ctx->pic_run_work);
+}
+
+static void coda_pic_run_work(struct work_struct *work)
+{
+	struct coda_ctx *ctx = container_of(work, struct coda_ctx, pic_run_work);
+	struct coda_dev *dev = ctx->dev;
+	int ret;
+
+	mutex_lock(&ctx->buffer_mutex);
+	mutex_lock(&dev->coda_mutex);
+
+	ret = ctx->ops->prepare_run(ctx);
+	if (ret < 0 && ctx->inst_type == CODA_INST_DECODER) {
+		mutex_unlock(&dev->coda_mutex);
+		mutex_unlock(&ctx->buffer_mutex);
+		/* job_finish scheduled by prepare_decode */
+		return;
+	}
+
+	if (!wait_for_completion_timeout(&ctx->completion,
+					 msecs_to_jiffies(1000))) {
+		dev_err(&dev->plat_dev->dev, "CODA PIC_RUN timeout\n");
+
+		ctx->hold = true;
+
+		coda_hw_reset(ctx);
+	} else if (!ctx->aborting) {
+		ctx->ops->finish_run(ctx);
+	}
+
+	if (ctx->aborting || (!ctx->streamon_cap && !ctx->streamon_out))
+		queue_work(dev->workqueue, &ctx->seq_end_work);
+
+	mutex_unlock(&dev->coda_mutex);
+	mutex_unlock(&ctx->buffer_mutex);
+
+	v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx);
+}
+
+static int coda_job_ready(void *m2m_priv)
+{
+	struct coda_ctx *ctx = m2m_priv;
+
+	/*
+	 * For both 'P' and 'key' frame cases 1 picture
+	 * and 1 frame are needed. In the decoder case,
+	 * the compressed frame can be in the bitstream.
+	 */
+	if (!v4l2_m2m_num_src_bufs_ready(ctx->fh.m2m_ctx) &&
+	    ctx->inst_type != CODA_INST_DECODER) {
+		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+			 "not ready: not enough video buffers.\n");
+		return 0;
+	}
+
+	if (!v4l2_m2m_num_dst_bufs_ready(ctx->fh.m2m_ctx)) {
+		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+			 "not ready: not enough video capture buffers.\n");
+		return 0;
+	}
+
+	if (ctx->hold ||
+	    ((ctx->inst_type == CODA_INST_DECODER) &&
+	     (coda_get_bitstream_payload(ctx) < 512) &&
+	     !(ctx->bit_stream_param & CODA_BIT_STREAM_END_FLAG))) {
+		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+			 "%d: not ready: not enough bitstream data.\n",
+			 ctx->idx);
+		return 0;
+	}
+
+	if (ctx->aborting) {
+		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+			 "not ready: aborting\n");
+		return 0;
+	}
+
+	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+			"job ready\n");
+	return 1;
+}
+
+static void coda_job_abort(void *priv)
+{
+	struct coda_ctx *ctx = priv;
+
+	ctx->aborting = 1;
+
+	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+		 "Aborting task\n");
+}
+
+static void coda_lock(void *m2m_priv)
+{
+	struct coda_ctx *ctx = m2m_priv;
+	struct coda_dev *pcdev = ctx->dev;
+
+	mutex_lock(&pcdev->dev_mutex);
+}
+
+static void coda_unlock(void *m2m_priv)
+{
+	struct coda_ctx *ctx = m2m_priv;
+	struct coda_dev *pcdev = ctx->dev;
+
+	mutex_unlock(&pcdev->dev_mutex);
+}
+
+static const struct v4l2_m2m_ops coda_m2m_ops = {
+	.device_run	= coda_device_run,
+	.job_ready	= coda_job_ready,
+	.job_abort	= coda_job_abort,
+	.lock		= coda_lock,
+	.unlock		= coda_unlock,
+};
+
+static void coda_set_tiled_map_type(struct coda_ctx *ctx, int tiled_map_type)
+{
+	struct gdi_tiled_map *tiled_map = &ctx->tiled_map;
+	int luma_map, chro_map, i;
+
+	memset(tiled_map, 0, sizeof(*tiled_map));
+
+	luma_map = 64;
+	chro_map = 64;
+	tiled_map->map_type = tiled_map_type;
+	for (i = 0; i < 16; i++)
+		tiled_map->xy2ca_map[i] = luma_map << 8 | chro_map;
+	for (i = 0; i < 4; i++)
+		tiled_map->xy2ba_map[i] = luma_map << 8 | chro_map;
+	for (i = 0; i < 16; i++)
+		tiled_map->xy2ra_map[i] = luma_map << 8 | chro_map;
+
+	if (tiled_map_type == GDI_LINEAR_FRAME_MAP) {
+		tiled_map->xy2rbc_config = 0;
+	} else {
+		dev_err(&ctx->dev->plat_dev->dev, "invalid map type: %d\n",
+			tiled_map_type);
+		return;
+	}
+}
+
+static void set_default_params(struct coda_ctx *ctx)
+{
+	u32 src_fourcc, dst_fourcc;
+	int max_w;
+	int max_h;
+
+	if (ctx->inst_type == CODA_INST_ENCODER) {
+		src_fourcc = V4L2_PIX_FMT_YUV420;
+		dst_fourcc = V4L2_PIX_FMT_H264;
+	} else {
+		src_fourcc = V4L2_PIX_FMT_H264;
+		dst_fourcc = V4L2_PIX_FMT_YUV420;
+	}
+	ctx->codec = coda_find_codec(ctx->dev, src_fourcc, dst_fourcc);
+	max_w = ctx->codec->max_w;
+	max_h = ctx->codec->max_h;
+
+	ctx->params.codec_mode = ctx->codec->mode;
+	ctx->colorspace = V4L2_COLORSPACE_REC709;
+	ctx->params.framerate = 30;
+	ctx->aborting = 0;
+
+	/* Default formats for output and input queues */
+	ctx->q_data[V4L2_M2M_SRC].fourcc = ctx->codec->src_fourcc;
+	ctx->q_data[V4L2_M2M_DST].fourcc = ctx->codec->dst_fourcc;
+	ctx->q_data[V4L2_M2M_SRC].width = max_w;
+	ctx->q_data[V4L2_M2M_SRC].height = max_h;
+	ctx->q_data[V4L2_M2M_DST].width = max_w;
+	ctx->q_data[V4L2_M2M_DST].height = max_h;
+	if (ctx->codec->src_fourcc == V4L2_PIX_FMT_YUV420) {
+		ctx->q_data[V4L2_M2M_SRC].bytesperline = max_w;
+		ctx->q_data[V4L2_M2M_SRC].sizeimage = (max_w * max_h * 3) / 2;
+		ctx->q_data[V4L2_M2M_DST].bytesperline = 0;
+		ctx->q_data[V4L2_M2M_DST].sizeimage = CODA_MAX_FRAME_SIZE;
+	} else {
+		ctx->q_data[V4L2_M2M_SRC].bytesperline = 0;
+		ctx->q_data[V4L2_M2M_SRC].sizeimage = CODA_MAX_FRAME_SIZE;
+		ctx->q_data[V4L2_M2M_DST].bytesperline = max_w;
+		ctx->q_data[V4L2_M2M_DST].sizeimage = (max_w * max_h * 3) / 2;
+	}
+	ctx->q_data[V4L2_M2M_SRC].rect.width = max_w;
+	ctx->q_data[V4L2_M2M_SRC].rect.height = max_h;
+	ctx->q_data[V4L2_M2M_DST].rect.width = max_w;
+	ctx->q_data[V4L2_M2M_DST].rect.height = max_h;
+
+	if (ctx->dev->devtype->product == CODA_960)
+		coda_set_tiled_map_type(ctx, GDI_LINEAR_FRAME_MAP);
+}
+
+/*
+ * Queue operations
+ */
+static int coda_queue_setup(struct vb2_queue *vq,
+				const struct v4l2_format *fmt,
+				unsigned int *nbuffers, unsigned int *nplanes,
+				unsigned int sizes[], void *alloc_ctxs[])
+{
+	struct coda_ctx *ctx = vb2_get_drv_priv(vq);
+	struct coda_q_data *q_data;
+	unsigned int size;
+
+	q_data = get_q_data(ctx, vq->type);
+	size = q_data->sizeimage;
+
+	*nplanes = 1;
+	sizes[0] = size;
+
+	alloc_ctxs[0] = ctx->dev->alloc_ctx;
+
+	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+		 "get %d buffer(s) of size %d each.\n", *nbuffers, size);
+
+	return 0;
+}
+
+static int coda_buf_prepare(struct vb2_buffer *vb)
+{
+	struct coda_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct coda_q_data *q_data;
+
+	q_data = get_q_data(ctx, vb->vb2_queue->type);
+
+	if (vb2_plane_size(vb, 0) < q_data->sizeimage) {
+		v4l2_warn(&ctx->dev->v4l2_dev,
+			  "%s data will not fit into plane (%lu < %lu)\n",
+			  __func__, vb2_plane_size(vb, 0),
+			  (long)q_data->sizeimage);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void coda_buf_queue(struct vb2_buffer *vb)
+{
+	struct coda_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct coda_q_data *q_data;
+
+	q_data = get_q_data(ctx, vb->vb2_queue->type);
+
+	/*
+	 * In the decoder case, immediately try to copy the buffer into the
+	 * bitstream ringbuffer and mark it as ready to be dequeued.
+	 */
+	if (q_data->fourcc == V4L2_PIX_FMT_H264 &&
+	    vb->vb2_queue->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) {
+		/*
+		 * For backwards compatibility, queuing an empty buffer marks
+		 * the stream end
+		 */
+		if (vb2_get_plane_payload(vb, 0) == 0)
+			coda_bit_stream_end_flag(ctx);
+		mutex_lock(&ctx->bitstream_mutex);
+		v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vb);
+		if (vb2_is_streaming(vb->vb2_queue))
+			coda_fill_bitstream(ctx);
+		mutex_unlock(&ctx->bitstream_mutex);
+	} else {
+		v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vb);
+	}
+}
+
+int coda_alloc_aux_buf(struct coda_dev *dev, struct coda_aux_buf *buf,
+		       size_t size, const char *name, struct dentry *parent)
+{
+	buf->vaddr = dma_alloc_coherent(&dev->plat_dev->dev, size, &buf->paddr,
+					GFP_KERNEL);
+	if (!buf->vaddr) {
+		v4l2_err(&dev->v4l2_dev,
+			 "Failed to allocate %s buffer of size %u\n",
+			 name, size);
+		return -ENOMEM;
+	}
+
+	buf->size = size;
+
+	if (name && parent) {
+		buf->blob.data = buf->vaddr;
+		buf->blob.size = size;
+		buf->dentry = debugfs_create_blob(name, 0644, parent,
+						  &buf->blob);
+		if (!buf->dentry)
+			dev_warn(&dev->plat_dev->dev,
+				 "failed to create debugfs entry %s\n", name);
+	}
+
+	return 0;
+}
+
+void coda_free_aux_buf(struct coda_dev *dev,
+		       struct coda_aux_buf *buf)
+{
+	if (buf->vaddr) {
+		dma_free_coherent(&dev->plat_dev->dev, buf->size,
+				  buf->vaddr, buf->paddr);
+		buf->vaddr = NULL;
+		buf->size = 0;
+	}
+	debugfs_remove(buf->dentry);
+}
+
+static int coda_start_streaming(struct vb2_queue *q, unsigned int count)
+{
+	struct coda_ctx *ctx = vb2_get_drv_priv(q);
+	struct v4l2_device *v4l2_dev = &ctx->dev->v4l2_dev;
+	struct coda_q_data *q_data_src, *q_data_dst;
+	struct vb2_buffer *buf;
+	u32 dst_fourcc;
+	int ret = 0;
+
+	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) {
+		if (q_data_src->fourcc == V4L2_PIX_FMT_H264) {
+			/* copy the buffers that where queued before streamon */
+			mutex_lock(&ctx->bitstream_mutex);
+			coda_fill_bitstream(ctx);
+			mutex_unlock(&ctx->bitstream_mutex);
+
+			if (coda_get_bitstream_payload(ctx) < 512) {
+				ret = -EINVAL;
+				goto err;
+			}
+		} else {
+			if (count < 1) {
+				ret = -EINVAL;
+				goto err;
+			}
+		}
+
+		ctx->streamon_out = 1;
+	} else {
+		if (count < 1) {
+			ret = -EINVAL;
+			goto err;
+		}
+
+		ctx->streamon_cap = 1;
+	}
+
+	/* Don't start the coda unless both queues are on */
+	if (!(ctx->streamon_out & ctx->streamon_cap))
+		return 0;
+
+	/* Allow decoder device_run with no new buffers queued */
+	if (ctx->inst_type == CODA_INST_DECODER)
+		v4l2_m2m_set_src_buffered(ctx->fh.m2m_ctx, true);
+
+	ctx->gopcounter = ctx->params.gop_size - 1;
+	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+	dst_fourcc = q_data_dst->fourcc;
+
+	ctx->codec = coda_find_codec(ctx->dev, q_data_src->fourcc,
+				     q_data_dst->fourcc);
+	if (!ctx->codec) {
+		v4l2_err(v4l2_dev, "couldn't tell instance type.\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	ret = ctx->ops->start_streaming(ctx);
+	if (ctx->inst_type == CODA_INST_DECODER) {
+		if (ret == -EAGAIN)
+			return 0;
+		else if (ret < 0)
+			goto err;
+	}
+
+	ctx->initialized = 1;
+	return ret;
+
+err:
+	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) {
+		while ((buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx)))
+			v4l2_m2m_buf_done(buf, VB2_BUF_STATE_DEQUEUED);
+	} else {
+		while ((buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx)))
+			v4l2_m2m_buf_done(buf, VB2_BUF_STATE_DEQUEUED);
+	}
+	return ret;
+}
+
+static void coda_stop_streaming(struct vb2_queue *q)
+{
+	struct coda_ctx *ctx = vb2_get_drv_priv(q);
+	struct coda_dev *dev = ctx->dev;
+	struct vb2_buffer *buf;
+
+	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) {
+		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
+			 "%s: output\n", __func__);
+		ctx->streamon_out = 0;
+
+		coda_bit_stream_end_flag(ctx);
+
+		ctx->isequence = 0;
+
+		while ((buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx)))
+			v4l2_m2m_buf_done(buf, VB2_BUF_STATE_ERROR);
+	} else {
+		v4l2_dbg(1, coda_debug, &dev->v4l2_dev,
+			 "%s: capture\n", __func__);
+		ctx->streamon_cap = 0;
+
+		ctx->osequence = 0;
+		ctx->sequence_offset = 0;
+
+		while ((buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx)))
+			v4l2_m2m_buf_done(buf, VB2_BUF_STATE_ERROR);
+	}
+
+	if (!ctx->streamon_out && !ctx->streamon_cap) {
+		struct coda_timestamp *ts;
+
+		mutex_lock(&ctx->bitstream_mutex);
+		while (!list_empty(&ctx->timestamp_list)) {
+			ts = list_first_entry(&ctx->timestamp_list,
+					      struct coda_timestamp, list);
+			list_del(&ts->list);
+			kfree(ts);
+		}
+		mutex_unlock(&ctx->bitstream_mutex);
+		kfifo_init(&ctx->bitstream_fifo,
+			ctx->bitstream.vaddr, ctx->bitstream.size);
+		ctx->runcounter = 0;
+	}
+}
+
+static const struct vb2_ops coda_qops = {
+	.queue_setup		= coda_queue_setup,
+	.buf_prepare		= coda_buf_prepare,
+	.buf_queue		= coda_buf_queue,
+	.start_streaming	= coda_start_streaming,
+	.stop_streaming		= coda_stop_streaming,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
+};
+
+static int coda_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct coda_ctx *ctx =
+			container_of(ctrl->handler, struct coda_ctx, ctrls);
+
+	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+		 "s_ctrl: id = %d, val = %d\n", ctrl->id, ctrl->val);
+
+	switch (ctrl->id) {
+	case V4L2_CID_HFLIP:
+		if (ctrl->val)
+			ctx->params.rot_mode |= CODA_MIR_HOR;
+		else
+			ctx->params.rot_mode &= ~CODA_MIR_HOR;
+		break;
+	case V4L2_CID_VFLIP:
+		if (ctrl->val)
+			ctx->params.rot_mode |= CODA_MIR_VER;
+		else
+			ctx->params.rot_mode &= ~CODA_MIR_VER;
+		break;
+	case V4L2_CID_MPEG_VIDEO_BITRATE:
+		ctx->params.bitrate = ctrl->val / 1000;
+		break;
+	case V4L2_CID_MPEG_VIDEO_GOP_SIZE:
+		ctx->params.gop_size = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_H264_I_FRAME_QP:
+		ctx->params.h264_intra_qp = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_H264_P_FRAME_QP:
+		ctx->params.h264_inter_qp = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_H264_MIN_QP:
+		ctx->params.h264_min_qp = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_H264_MAX_QP:
+		ctx->params.h264_max_qp = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_ALPHA:
+		ctx->params.h264_deblk_alpha = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_BETA:
+		ctx->params.h264_deblk_beta = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_MODE:
+		ctx->params.h264_deblk_enabled = (ctrl->val ==
+				V4L2_MPEG_VIDEO_H264_LOOP_FILTER_MODE_ENABLED);
+		break;
+	case V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP:
+		ctx->params.mpeg4_intra_qp = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP:
+		ctx->params.mpeg4_inter_qp = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MODE:
+		ctx->params.slice_mode = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MAX_MB:
+		ctx->params.slice_max_mb = ctrl->val;
+		break;
+	case V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MAX_BYTES:
+		ctx->params.slice_max_bits = ctrl->val * 8;
+		break;
+	case V4L2_CID_MPEG_VIDEO_HEADER_MODE:
+		break;
+	case V4L2_CID_MPEG_VIDEO_CYCLIC_INTRA_REFRESH_MB:
+		ctx->params.intra_refresh = ctrl->val;
+		break;
+	default:
+		v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev,
+			"Invalid control, id=%d, val=%d\n",
+			ctrl->id, ctrl->val);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops coda_ctrl_ops = {
+	.s_ctrl = coda_s_ctrl,
+};
+
+static int coda_ctrls_setup(struct coda_ctx *ctx)
+{
+	v4l2_ctrl_handler_init(&ctx->ctrls, 9);
+
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_HFLIP, 0, 1, 1, 0);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_VFLIP, 0, 1, 1, 0);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_BITRATE, 0, 32767000, 1, 0);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_GOP_SIZE, 1, 60, 1, 16);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_H264_I_FRAME_QP, 0, 51, 1, 25);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_H264_P_FRAME_QP, 0, 51, 1, 25);
+	if (ctx->dev->devtype->product != CODA_960) {
+		v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+			V4L2_CID_MPEG_VIDEO_H264_MIN_QP, 0, 51, 1, 12);
+	}
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_H264_MAX_QP, 0, 51, 1, 51);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_ALPHA, 0, 15, 1, 0);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_BETA, 0, 15, 1, 0);
+	v4l2_ctrl_new_std_menu(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_H264_LOOP_FILTER_MODE,
+		V4L2_MPEG_VIDEO_H264_LOOP_FILTER_MODE_DISABLED, 0x0,
+		V4L2_MPEG_VIDEO_H264_LOOP_FILTER_MODE_ENABLED);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP, 1, 31, 1, 2);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_MPEG4_P_FRAME_QP, 1, 31, 1, 2);
+	v4l2_ctrl_new_std_menu(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MODE,
+		V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_BYTES, 0x0,
+		V4L2_MPEG_VIDEO_MULTI_SLICE_MODE_SINGLE);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MAX_MB, 1, 0x3fffffff, 1, 1);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MAX_BYTES, 1, 0x3fffffff, 1,
+		500);
+	v4l2_ctrl_new_std_menu(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_HEADER_MODE,
+		V4L2_MPEG_VIDEO_HEADER_MODE_JOINED_WITH_1ST_FRAME,
+		(1 << V4L2_MPEG_VIDEO_HEADER_MODE_SEPARATE),
+		V4L2_MPEG_VIDEO_HEADER_MODE_JOINED_WITH_1ST_FRAME);
+	v4l2_ctrl_new_std(&ctx->ctrls, &coda_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_CYCLIC_INTRA_REFRESH_MB, 0,
+		1920 * 1088 / 256, 1, 0);
+
+	if (ctx->ctrls.error) {
+		v4l2_err(&ctx->dev->v4l2_dev,
+			"control initialization error (%d)",
+			ctx->ctrls.error);
+		return -EINVAL;
+	}
+
+	return v4l2_ctrl_handler_setup(&ctx->ctrls);
+}
+
+static int coda_queue_init(struct coda_ctx *ctx, struct vb2_queue *vq)
+{
+	vq->drv_priv = ctx;
+	vq->ops = &coda_qops;
+	vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	vq->lock = &ctx->dev->dev_mutex;
+
+	return vb2_queue_init(vq);
+}
+
+int coda_encoder_queue_init(void *priv, struct vb2_queue *src_vq,
+			    struct vb2_queue *dst_vq)
+{
+	int ret;
+
+	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT;
+	src_vq->io_modes = VB2_DMABUF | VB2_MMAP;
+	src_vq->mem_ops = &vb2_dma_contig_memops;
+
+	ret = coda_queue_init(priv, src_vq);
+	if (ret)
+		return ret;
+
+	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	dst_vq->io_modes = VB2_DMABUF | VB2_MMAP;
+	dst_vq->mem_ops = &vb2_dma_contig_memops;
+
+	return coda_queue_init(priv, dst_vq);
+}
+
+int coda_decoder_queue_init(void *priv, struct vb2_queue *src_vq,
+			    struct vb2_queue *dst_vq)
+{
+	int ret;
+
+	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT;
+	src_vq->io_modes = VB2_DMABUF | VB2_MMAP;
+	src_vq->mem_ops = &vb2_dma_contig_memops;
+
+	ret = coda_queue_init(priv, src_vq);
+	if (ret)
+		return ret;
+
+	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	dst_vq->io_modes = VB2_DMABUF | VB2_MMAP;
+	dst_vq->mem_ops = &vb2_dma_contig_memops;
+
+	return coda_queue_init(priv, dst_vq);
+}
+
+static int coda_next_free_instance(struct coda_dev *dev)
+{
+	int idx = ffz(dev->instance_mask);
+
+	if ((idx < 0) ||
+	    (dev->devtype->product == CODA_DX6 && idx > CODADX6_MAX_INSTANCES))
+		return -EBUSY;
+
+	return idx;
+}
+
+static int coda_open(struct file *file, enum coda_inst_type inst_type,
+		     const struct coda_context_ops *ctx_ops)
+{
+	struct coda_dev *dev = video_drvdata(file);
+	struct coda_ctx *ctx = NULL;
+	char *name;
+	int ret;
+	int idx;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	idx = coda_next_free_instance(dev);
+	if (idx < 0) {
+		ret = idx;
+		goto err_coda_max;
+	}
+	set_bit(idx, &dev->instance_mask);
+
+	name = kasprintf(GFP_KERNEL, "context%d", idx);
+	ctx->debugfs_entry = debugfs_create_dir(name, dev->debugfs_root);
+	kfree(name);
+
+	ctx->inst_type = inst_type;
+	ctx->ops = ctx_ops;
+	init_completion(&ctx->completion);
+	INIT_WORK(&ctx->pic_run_work, coda_pic_run_work);
+	INIT_WORK(&ctx->seq_end_work, ctx->ops->seq_end_work);
+	v4l2_fh_init(&ctx->fh, video_devdata(file));
+	file->private_data = &ctx->fh;
+	v4l2_fh_add(&ctx->fh);
+	ctx->dev = dev;
+	ctx->idx = idx;
+	switch (dev->devtype->product) {
+	case CODA_7541:
+	case CODA_960:
+		ctx->reg_idx = 0;
+		break;
+	default:
+		ctx->reg_idx = idx;
+	}
+
+	/* Power up and upload firmware if necessary */
+	ret = pm_runtime_get_sync(&dev->plat_dev->dev);
+	if (ret < 0) {
+		v4l2_err(&dev->v4l2_dev, "failed to power up: %d\n", ret);
+		goto err_pm_get;
+	}
+
+	ret = clk_prepare_enable(dev->clk_per);
+	if (ret)
+		goto err_clk_per;
+
+	ret = clk_prepare_enable(dev->clk_ahb);
+	if (ret)
+		goto err_clk_ahb;
+
+	set_default_params(ctx);
+	ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->m2m_dev, ctx,
+					    ctx->ops->queue_init);
+	if (IS_ERR(ctx->fh.m2m_ctx)) {
+		ret = PTR_ERR(ctx->fh.m2m_ctx);
+
+		v4l2_err(&dev->v4l2_dev, "%s return error (%d)\n",
+			 __func__, ret);
+		goto err_ctx_init;
+	}
+
+	ret = coda_ctrls_setup(ctx);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "failed to setup coda controls\n");
+		goto err_ctrls_setup;
+	}
+
+	ctx->fh.ctrl_handler = &ctx->ctrls;
+
+	ret = coda_alloc_context_buf(ctx, &ctx->parabuf, CODA_PARA_BUF_SIZE,
+				     "parabuf");
+	if (ret < 0) {
+		v4l2_err(&dev->v4l2_dev, "failed to allocate parabuf");
+		goto err_dma_alloc;
+	}
+
+	ctx->bitstream.size = CODA_MAX_FRAME_SIZE;
+	ctx->bitstream.vaddr = dma_alloc_writecombine(&dev->plat_dev->dev,
+			ctx->bitstream.size, &ctx->bitstream.paddr, GFP_KERNEL);
+	if (!ctx->bitstream.vaddr) {
+		v4l2_err(&dev->v4l2_dev,
+			 "failed to allocate bitstream ringbuffer");
+		ret = -ENOMEM;
+		goto err_dma_writecombine;
+	}
+	kfifo_init(&ctx->bitstream_fifo,
+		ctx->bitstream.vaddr, ctx->bitstream.size);
+	mutex_init(&ctx->bitstream_mutex);
+	mutex_init(&ctx->buffer_mutex);
+	INIT_LIST_HEAD(&ctx->timestamp_list);
+
+	coda_lock(ctx);
+	list_add(&ctx->list, &dev->instances);
+	coda_unlock(ctx);
+
+	v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "Created instance %d (%p)\n",
+		 ctx->idx, ctx);
+
+	return 0;
+
+err_dma_writecombine:
+	if (ctx->dev->devtype->product == CODA_DX6)
+		coda_free_aux_buf(dev, &ctx->workbuf);
+	coda_free_aux_buf(dev, &ctx->parabuf);
+err_dma_alloc:
+	v4l2_ctrl_handler_free(&ctx->ctrls);
+err_ctrls_setup:
+	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);
+err_ctx_init:
+	clk_disable_unprepare(dev->clk_ahb);
+err_clk_ahb:
+	clk_disable_unprepare(dev->clk_per);
+err_clk_per:
+	pm_runtime_put_sync(&dev->plat_dev->dev);
+err_pm_get:
+	v4l2_fh_del(&ctx->fh);
+	v4l2_fh_exit(&ctx->fh);
+	clear_bit(ctx->idx, &dev->instance_mask);
+err_coda_max:
+	kfree(ctx);
+	return ret;
+}
+
+static int coda_encoder_open(struct file *file)
+{
+	return coda_open(file, CODA_INST_ENCODER, &coda_bit_encode_ops);
+}
+
+static int coda_decoder_open(struct file *file)
+{
+	return coda_open(file, CODA_INST_DECODER, &coda_bit_decode_ops);
+}
+
+static int coda_release(struct file *file)
+{
+	struct coda_dev *dev = video_drvdata(file);
+	struct coda_ctx *ctx = fh_to_ctx(file->private_data);
+
+	v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "Releasing instance %p\n",
+		 ctx);
+
+	debugfs_remove_recursive(ctx->debugfs_entry);
+
+	/* If this instance is running, call .job_abort and wait for it to end */
+	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);
+
+	/* In case the instance was not running, we still need to call SEQ_END */
+	if (ctx->initialized) {
+		queue_work(dev->workqueue, &ctx->seq_end_work);
+		flush_work(&ctx->seq_end_work);
+	}
+
+	coda_lock(ctx);
+	list_del(&ctx->list);
+	coda_unlock(ctx);
+
+	dma_free_writecombine(&dev->plat_dev->dev, ctx->bitstream.size,
+		ctx->bitstream.vaddr, ctx->bitstream.paddr);
+	if (ctx->dev->devtype->product == CODA_DX6)
+		coda_free_aux_buf(dev, &ctx->workbuf);
+
+	coda_free_aux_buf(dev, &ctx->parabuf);
+	v4l2_ctrl_handler_free(&ctx->ctrls);
+	clk_disable_unprepare(dev->clk_ahb);
+	clk_disable_unprepare(dev->clk_per);
+	pm_runtime_put_sync(&dev->plat_dev->dev);
+	v4l2_fh_del(&ctx->fh);
+	v4l2_fh_exit(&ctx->fh);
+	clear_bit(ctx->idx, &dev->instance_mask);
+	if (ctx->ops->release)
+		ctx->ops->release(ctx);
+	kfree(ctx);
+
+	return 0;
+}
+
+static const struct v4l2_file_operations coda_encoder_fops = {
+	.owner		= THIS_MODULE,
+	.open		= coda_encoder_open,
+	.release	= coda_release,
+	.poll		= v4l2_m2m_fop_poll,
+	.unlocked_ioctl	= video_ioctl2,
+	.mmap		= v4l2_m2m_fop_mmap,
+};
+
+static const struct v4l2_file_operations coda_decoder_fops = {
+	.owner		= THIS_MODULE,
+	.open		= coda_decoder_open,
+	.release	= coda_release,
+	.poll		= v4l2_m2m_fop_poll,
+	.unlocked_ioctl	= video_ioctl2,
+	.mmap		= v4l2_m2m_fop_mmap,
+};
+
+static int coda_hw_init(struct coda_dev *dev)
+{
+	u32 data;
+	u16 *p;
+	int i, ret;
+
+	ret = clk_prepare_enable(dev->clk_per);
+	if (ret)
+		goto err_clk_per;
+
+	ret = clk_prepare_enable(dev->clk_ahb);
+	if (ret)
+		goto err_clk_ahb;
+
+	if (dev->rstc)
+		reset_control_reset(dev->rstc);
+
+	/*
+	 * Copy the first CODA_ISRAM_SIZE in the internal SRAM.
+	 * The 16-bit chars in the code buffer are in memory access
+	 * order, re-sort them to CODA order for register download.
+	 * Data in this SRAM survives a reboot.
+	 */
+	p = (u16 *)dev->codebuf.vaddr;
+	if (dev->devtype->product == CODA_DX6) {
+		for (i = 0; i < (CODA_ISRAM_SIZE / 2); i++)  {
+			data = CODA_DOWN_ADDRESS_SET(i) |
+				CODA_DOWN_DATA_SET(p[i ^ 1]);
+			coda_write(dev, data, CODA_REG_BIT_CODE_DOWN);
+		}
+	} else {
+		for (i = 0; i < (CODA_ISRAM_SIZE / 2); i++) {
+			data = CODA_DOWN_ADDRESS_SET(i) |
+				CODA_DOWN_DATA_SET(p[round_down(i, 4) +
+							3 - (i % 4)]);
+			coda_write(dev, data, CODA_REG_BIT_CODE_DOWN);
+		}
+	}
+
+	/* Clear registers */
+	for (i = 0; i < 64; i++)
+		coda_write(dev, 0, CODA_REG_BIT_CODE_BUF_ADDR + i * 4);
+
+	/* Tell the BIT where to find everything it needs */
+	if (dev->devtype->product == CODA_960 ||
+	    dev->devtype->product == CODA_7541) {
+		coda_write(dev, dev->tempbuf.paddr,
+				CODA_REG_BIT_TEMP_BUF_ADDR);
+		coda_write(dev, 0, CODA_REG_BIT_BIT_STREAM_PARAM);
+	} else {
+		coda_write(dev, dev->workbuf.paddr,
+			      CODA_REG_BIT_WORK_BUF_ADDR);
+	}
+	coda_write(dev, dev->codebuf.paddr,
+		      CODA_REG_BIT_CODE_BUF_ADDR);
+	coda_write(dev, 0, CODA_REG_BIT_CODE_RUN);
+
+	/* Set default values */
+	switch (dev->devtype->product) {
+	case CODA_DX6:
+		coda_write(dev, CODADX6_STREAM_BUF_PIC_FLUSH,
+			   CODA_REG_BIT_STREAM_CTRL);
+		break;
+	default:
+		coda_write(dev, CODA7_STREAM_BUF_PIC_FLUSH,
+			   CODA_REG_BIT_STREAM_CTRL);
+	}
+	if (dev->devtype->product == CODA_960)
+		coda_write(dev, 1 << 12, CODA_REG_BIT_FRAME_MEM_CTRL);
+	else
+		coda_write(dev, 0, CODA_REG_BIT_FRAME_MEM_CTRL);
+
+	if (dev->devtype->product != CODA_DX6)
+		coda_write(dev, 0, CODA7_REG_BIT_AXI_SRAM_USE);
+
+	coda_write(dev, CODA_INT_INTERRUPT_ENABLE,
+		      CODA_REG_BIT_INT_ENABLE);
+
+	/* Reset VPU and start processor */
+	data = coda_read(dev, CODA_REG_BIT_CODE_RESET);
+	data |= CODA_REG_RESET_ENABLE;
+	coda_write(dev, data, CODA_REG_BIT_CODE_RESET);
+	udelay(10);
+	data &= ~CODA_REG_RESET_ENABLE;
+	coda_write(dev, data, CODA_REG_BIT_CODE_RESET);
+	coda_write(dev, CODA_REG_RUN_ENABLE, CODA_REG_BIT_CODE_RUN);
+
+	clk_disable_unprepare(dev->clk_ahb);
+	clk_disable_unprepare(dev->clk_per);
+
+	return 0;
+
+err_clk_ahb:
+	clk_disable_unprepare(dev->clk_per);
+err_clk_per:
+	return ret;
+}
+
+static int coda_register_device(struct coda_dev *dev, struct video_device *vfd)
+{
+	vfd->release	= video_device_release_empty,
+	vfd->lock	= &dev->dev_mutex;
+	vfd->v4l2_dev	= &dev->v4l2_dev;
+	vfd->vfl_dir	= VFL_DIR_M2M;
+	video_set_drvdata(vfd, dev);
+
+	/* Not applicable, use the selection API instead */
+	v4l2_disable_ioctl(vfd, VIDIOC_CROPCAP);
+	v4l2_disable_ioctl(vfd, VIDIOC_G_CROP);
+	v4l2_disable_ioctl(vfd, VIDIOC_S_CROP);
+
+	return video_register_device(vfd, VFL_TYPE_GRABBER, 0);
+}
+
+static void coda_fw_callback(const struct firmware *fw, void *context)
+{
+	struct coda_dev *dev = context;
+	struct platform_device *pdev = dev->plat_dev;
+	int ret;
+
+	if (!fw) {
+		v4l2_err(&dev->v4l2_dev, "firmware request failed\n");
+		goto put_pm;
+	}
+
+	/* allocate auxiliary per-device code buffer for the BIT processor */
+	ret = coda_alloc_aux_buf(dev, &dev->codebuf, fw->size, "codebuf",
+				 dev->debugfs_root);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to allocate code buffer\n");
+		goto put_pm;
+	}
+
+	/* Copy the whole firmware image to the code buffer */
+	memcpy(dev->codebuf.vaddr, fw->data, fw->size);
+	release_firmware(fw);
+
+	ret = coda_hw_init(dev);
+	if (ret < 0) {
+		v4l2_err(&dev->v4l2_dev, "HW initialization failed\n");
+		goto put_pm;
+	}
+
+	ret = coda_check_firmware(dev);
+	if (ret < 0)
+		goto put_pm;
+
+	dev->alloc_ctx = vb2_dma_contig_init_ctx(&pdev->dev);
+	if (IS_ERR(dev->alloc_ctx)) {
+		v4l2_err(&dev->v4l2_dev, "Failed to alloc vb2 context\n");
+		goto put_pm;
+	}
+
+	dev->m2m_dev = v4l2_m2m_init(&coda_m2m_ops);
+	if (IS_ERR(dev->m2m_dev)) {
+		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem device\n");
+		goto rel_ctx;
+	}
+
+	dev->vfd[0].fops      = &coda_encoder_fops,
+	dev->vfd[0].ioctl_ops = &coda_ioctl_ops;
+	snprintf(dev->vfd[0].name, sizeof(dev->vfd[0].name), "coda-encoder");
+	ret = coda_register_device(dev, &dev->vfd[0]);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev,
+			 "Failed to register encoder video device\n");
+		goto rel_m2m;
+	}
+
+	dev->vfd[1].fops      = &coda_decoder_fops,
+	dev->vfd[1].ioctl_ops = &coda_ioctl_ops;
+	snprintf(dev->vfd[1].name, sizeof(dev->vfd[1].name), "coda-decoder");
+	ret = coda_register_device(dev, &dev->vfd[1]);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev,
+			 "Failed to register decoder video device\n");
+		goto rel_m2m;
+	}
+
+	v4l2_info(&dev->v4l2_dev, "codec registered as /dev/video[%d-%d]\n",
+		  dev->vfd[0].num, dev->vfd[1].num);
+
+	pm_runtime_put_sync(&pdev->dev);
+	return;
+
+rel_m2m:
+	v4l2_m2m_release(dev->m2m_dev);
+rel_ctx:
+	vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
+put_pm:
+	pm_runtime_put_sync(&pdev->dev);
+}
+
+static int coda_firmware_request(struct coda_dev *dev)
+{
+	char *fw = dev->devtype->firmware;
+
+	dev_dbg(&dev->plat_dev->dev, "requesting firmware '%s' for %s\n", fw,
+		coda_product_name(dev->devtype->product));
+
+	return request_firmware_nowait(THIS_MODULE, true,
+		fw, &dev->plat_dev->dev, GFP_KERNEL, dev, coda_fw_callback);
+}
+
+enum coda_platform {
+	CODA_IMX27,
+	CODA_IMX53,
+	CODA_IMX6Q,
+	CODA_IMX6DL,
+};
+
+static const struct coda_devtype coda_devdata[] = {
+	[CODA_IMX27] = {
+		.firmware     = "v4l-codadx6-imx27.bin",
+		.product      = CODA_DX6,
+		.codecs       = codadx6_codecs,
+		.num_codecs   = ARRAY_SIZE(codadx6_codecs),
+		.workbuf_size = 288 * 1024 + FMO_SLICE_SAVE_BUF_SIZE * 8 * 1024,
+		.iram_size    = 0xb000,
+	},
+	[CODA_IMX53] = {
+		.firmware     = "v4l-coda7541-imx53.bin",
+		.product      = CODA_7541,
+		.codecs       = coda7_codecs,
+		.num_codecs   = ARRAY_SIZE(coda7_codecs),
+		.workbuf_size = 128 * 1024,
+		.tempbuf_size = 304 * 1024,
+		.iram_size    = 0x14000,
+	},
+	[CODA_IMX6Q] = {
+		.firmware     = "v4l-coda960-imx6q.bin",
+		.product      = CODA_960,
+		.codecs       = coda9_codecs,
+		.num_codecs   = ARRAY_SIZE(coda9_codecs),
+		.workbuf_size = 80 * 1024,
+		.tempbuf_size = 204 * 1024,
+		.iram_size    = 0x21000,
+	},
+	[CODA_IMX6DL] = {
+		.firmware     = "v4l-coda960-imx6dl.bin",
+		.product      = CODA_960,
+		.codecs       = coda9_codecs,
+		.num_codecs   = ARRAY_SIZE(coda9_codecs),
+		.workbuf_size = 80 * 1024,
+		.tempbuf_size = 204 * 1024,
+		.iram_size    = 0x20000,
+	},
+};
+
+static struct platform_device_id coda_platform_ids[] = {
+	{ .name = "coda-imx27", .driver_data = CODA_IMX27 },
+	{ .name = "coda-imx53", .driver_data = CODA_IMX53 },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(platform, coda_platform_ids);
+
+#ifdef CONFIG_OF
+static const struct of_device_id coda_dt_ids[] = {
+	{ .compatible = "fsl,imx27-vpu", .data = &coda_devdata[CODA_IMX27] },
+	{ .compatible = "fsl,imx53-vpu", .data = &coda_devdata[CODA_IMX53] },
+	{ .compatible = "fsl,imx6q-vpu", .data = &coda_devdata[CODA_IMX6Q] },
+	{ .compatible = "fsl,imx6dl-vpu", .data = &coda_devdata[CODA_IMX6DL] },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, coda_dt_ids);
+#endif
+
+static int coda_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *of_id =
+			of_match_device(of_match_ptr(coda_dt_ids), &pdev->dev);
+	const struct platform_device_id *pdev_id;
+	struct coda_platform_data *pdata = pdev->dev.platform_data;
+	struct device_node *np = pdev->dev.of_node;
+	struct gen_pool *pool;
+	struct coda_dev *dev;
+	struct resource *res;
+	int ret, irq;
+
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev) {
+		dev_err(&pdev->dev, "Not enough memory for %s\n",
+			CODA_NAME);
+		return -ENOMEM;
+	}
+
+	spin_lock_init(&dev->irqlock);
+	INIT_LIST_HEAD(&dev->instances);
+
+	dev->plat_dev = pdev;
+	dev->clk_per = devm_clk_get(&pdev->dev, "per");
+	if (IS_ERR(dev->clk_per)) {
+		dev_err(&pdev->dev, "Could not get per clock\n");
+		return PTR_ERR(dev->clk_per);
+	}
+
+	dev->clk_ahb = devm_clk_get(&pdev->dev, "ahb");
+	if (IS_ERR(dev->clk_ahb)) {
+		dev_err(&pdev->dev, "Could not get ahb clock\n");
+		return PTR_ERR(dev->clk_ahb);
+	}
+
+	/* Get  memory for physical registers */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	dev->regs_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(dev->regs_base))
+		return PTR_ERR(dev->regs_base);
+
+	/* IRQ */
+	irq = platform_get_irq_byname(pdev, "bit");
+	if (irq < 0)
+		irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "failed to get irq resource\n");
+		return irq;
+	}
+
+	ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, coda_irq_handler,
+			IRQF_ONESHOT, dev_name(&pdev->dev), dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to request irq: %d\n", ret);
+		return ret;
+	}
+
+	dev->rstc = devm_reset_control_get_optional(&pdev->dev, NULL);
+	if (IS_ERR(dev->rstc)) {
+		ret = PTR_ERR(dev->rstc);
+		if (ret == -ENOENT || ret == -ENOSYS) {
+			dev->rstc = NULL;
+		} else {
+			dev_err(&pdev->dev, "failed get reset control: %d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	/* Get IRAM pool from device tree or platform data */
+	pool = of_get_named_gen_pool(np, "iram", 0);
+	if (!pool && pdata)
+		pool = dev_get_gen_pool(pdata->iram_dev);
+	if (!pool) {
+		dev_err(&pdev->dev, "iram pool not available\n");
+		return -ENOMEM;
+	}
+	dev->iram_pool = pool;
+
+	ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev);
+	if (ret)
+		return ret;
+
+	mutex_init(&dev->dev_mutex);
+	mutex_init(&dev->coda_mutex);
+
+	pdev_id = of_id ? of_id->data : platform_get_device_id(pdev);
+
+	if (of_id) {
+		dev->devtype = of_id->data;
+	} else if (pdev_id) {
+		dev->devtype = &coda_devdata[pdev_id->driver_data];
+	} else {
+		v4l2_device_unregister(&dev->v4l2_dev);
+		return -EINVAL;
+	}
+
+	dev->debugfs_root = debugfs_create_dir("coda", NULL);
+	if (!dev->debugfs_root)
+		dev_warn(&pdev->dev, "failed to create debugfs root\n");
+
+	/* allocate auxiliary per-device buffers for the BIT processor */
+	if (dev->devtype->product == CODA_DX6) {
+		ret = coda_alloc_aux_buf(dev, &dev->workbuf,
+					 dev->devtype->workbuf_size, "workbuf",
+					 dev->debugfs_root);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "failed to allocate work buffer\n");
+			v4l2_device_unregister(&dev->v4l2_dev);
+			return ret;
+		}
+	}
+
+	if (dev->devtype->tempbuf_size) {
+		ret = coda_alloc_aux_buf(dev, &dev->tempbuf,
+					 dev->devtype->tempbuf_size, "tempbuf",
+					 dev->debugfs_root);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "failed to allocate temp buffer\n");
+			v4l2_device_unregister(&dev->v4l2_dev);
+			return ret;
+		}
+	}
+
+	dev->iram.size = dev->devtype->iram_size;
+	dev->iram.vaddr = gen_pool_dma_alloc(dev->iram_pool, dev->iram.size,
+					     &dev->iram.paddr);
+	if (!dev->iram.vaddr) {
+		dev_warn(&pdev->dev, "unable to alloc iram\n");
+	} else {
+		dev->iram.blob.data = dev->iram.vaddr;
+		dev->iram.blob.size = dev->iram.size;
+		dev->iram.dentry = debugfs_create_blob("iram", 0644,
+						       dev->debugfs_root,
+						       &dev->iram.blob);
+	}
+
+	dev->workqueue = alloc_workqueue("coda", WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
+	if (!dev->workqueue) {
+		dev_err(&pdev->dev, "unable to alloc workqueue\n");
+		return -ENOMEM;
+	}
+
+	platform_set_drvdata(pdev, dev);
+
+	/*
+	 * Start activated so we can directly call coda_hw_init in
+	 * coda_fw_callback regardless of whether CONFIG_PM_RUNTIME is
+	 * enabled or whether the device is associated with a PM domain.
+	 */
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+	return coda_firmware_request(dev);
+}
+
+static int coda_remove(struct platform_device *pdev)
+{
+	struct coda_dev *dev = platform_get_drvdata(pdev);
+
+	video_unregister_device(&dev->vfd[0]);
+	video_unregister_device(&dev->vfd[1]);
+	if (dev->m2m_dev)
+		v4l2_m2m_release(dev->m2m_dev);
+	pm_runtime_disable(&pdev->dev);
+	if (dev->alloc_ctx)
+		vb2_dma_contig_cleanup_ctx(dev->alloc_ctx);
+	v4l2_device_unregister(&dev->v4l2_dev);
+	destroy_workqueue(dev->workqueue);
+	if (dev->iram.vaddr)
+		gen_pool_free(dev->iram_pool, (unsigned long)dev->iram.vaddr,
+			      dev->iram.size);
+	coda_free_aux_buf(dev, &dev->codebuf);
+	coda_free_aux_buf(dev, &dev->tempbuf);
+	coda_free_aux_buf(dev, &dev->workbuf);
+	debugfs_remove_recursive(dev->debugfs_root);
+	return 0;
+}
+
+#ifdef CONFIG_PM_RUNTIME
+static int coda_runtime_resume(struct device *dev)
+{
+	struct coda_dev *cdev = dev_get_drvdata(dev);
+	int ret = 0;
+
+	if (dev->pm_domain && cdev->codebuf.vaddr) {
+		ret = coda_hw_init(cdev);
+		if (ret)
+			v4l2_err(&cdev->v4l2_dev, "HW initialization failed\n");
+	}
+
+	return ret;
+}
+#endif
+
+static const struct dev_pm_ops coda_pm_ops = {
+	SET_RUNTIME_PM_OPS(NULL, coda_runtime_resume, NULL)
+};
+
+static struct platform_driver coda_driver = {
+	.probe	= coda_probe,
+	.remove	= coda_remove,
+	.driver	= {
+		.name	= CODA_NAME,
+		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(coda_dt_ids),
+		.pm	= &coda_pm_ops,
+	},
+	.id_table = coda_platform_ids,
+};
+
+module_platform_driver(coda_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Javier Martin <javier.martin@vista-silicon.com>");
+MODULE_DESCRIPTION("Coda multi-standard codec V4L2 driver");
diff --git a/drivers/media/platform/coda/coda-h264.c b/drivers/media/platform/coda/coda-h264.c
new file mode 100644
index 000000000000..456773af1f1d
--- /dev/null
+++ b/drivers/media/platform/coda/coda-h264.c
@@ -0,0 +1,37 @@
+/*
+ * Coda multi-standard codec IP - H.264 helper functions
+ *
+ * Copyright (C) 2012 Vista Silicon S.L.
+ *    Javier Martin, <javier.martin@vista-silicon.com>
+ *    Xavier Duret
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+
+static const u8 coda_filler_nal[14] = { 0x00, 0x00, 0x00, 0x01, 0x0c, 0xff,
+			0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x80 };
+static const u8 coda_filler_size[8] = { 0, 7, 14, 13, 12, 11, 10, 9 };
+
+int coda_h264_padding(int size, char *p)
+{
+	int nal_size;
+	int diff;
+
+	diff = size - (size & ~0x7);
+	if (diff == 0)
+		return 0;
+
+	nal_size = coda_filler_size[diff];
+	memcpy(p, coda_filler_nal, nal_size);
+
+	/* Add rbsp stop bit and trailing at the end */
+	*(p + nal_size - 1) = 0x80;
+
+	return nal_size;
+}
diff --git a/drivers/media/platform/coda/coda.h b/drivers/media/platform/coda/coda.h
new file mode 100644
index 000000000000..bbc18c0dacd9
--- /dev/null
+++ b/drivers/media/platform/coda/coda.h
@@ -0,0 +1,287 @@
+/*
+ * Coda multi-standard codec IP
+ *
+ * Copyright (C) 2012 Vista Silicon S.L.
+ *    Javier Martin, <javier.martin@vista-silicon.com>
+ *    Xavier Duret
+ * Copyright (C) 2012-2014 Philipp Zabel, Pengutronix
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/irqreturn.h>
+#include <linux/mutex.h>
+#include <linux/kfifo.h>
+#include <linux/videodev2.h>
+
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-fh.h>
+#include <media/videobuf2-core.h>
+
+#include "coda_regs.h"
+
+#define CODA_MAX_FRAMEBUFFERS	8
+#define CODA_MAX_FRAME_SIZE	0x100000
+#define FMO_SLICE_SAVE_BUF_SIZE	(32)
+
+enum {
+	V4L2_M2M_SRC = 0,
+	V4L2_M2M_DST = 1,
+};
+
+enum coda_inst_type {
+	CODA_INST_ENCODER,
+	CODA_INST_DECODER,
+};
+
+enum coda_product {
+	CODA_DX6 = 0xf001,
+	CODA_7541 = 0xf012,
+	CODA_960 = 0xf020,
+};
+
+struct coda_devtype {
+	char			*firmware;
+	enum coda_product	product;
+	const struct coda_codec	*codecs;
+	unsigned int		num_codecs;
+	size_t			workbuf_size;
+	size_t			tempbuf_size;
+	size_t			iram_size;
+};
+
+struct coda_aux_buf {
+	void			*vaddr;
+	dma_addr_t		paddr;
+	u32			size;
+	struct debugfs_blob_wrapper blob;
+	struct dentry		*dentry;
+};
+
+struct coda_dev {
+	struct v4l2_device	v4l2_dev;
+	struct video_device	vfd[2];
+	struct platform_device	*plat_dev;
+	const struct coda_devtype *devtype;
+
+	void __iomem		*regs_base;
+	struct clk		*clk_per;
+	struct clk		*clk_ahb;
+	struct reset_control	*rstc;
+
+	struct coda_aux_buf	codebuf;
+	struct coda_aux_buf	tempbuf;
+	struct coda_aux_buf	workbuf;
+	struct gen_pool		*iram_pool;
+	struct coda_aux_buf	iram;
+
+	spinlock_t		irqlock;
+	struct mutex		dev_mutex;
+	struct mutex		coda_mutex;
+	struct workqueue_struct	*workqueue;
+	struct v4l2_m2m_dev	*m2m_dev;
+	struct vb2_alloc_ctx	*alloc_ctx;
+	struct list_head	instances;
+	unsigned long		instance_mask;
+	struct dentry		*debugfs_root;
+};
+
+struct coda_codec {
+	u32 mode;
+	u32 src_fourcc;
+	u32 dst_fourcc;
+	u32 max_w;
+	u32 max_h;
+};
+
+struct coda_huff_tab;
+
+struct coda_params {
+	u8			rot_mode;
+	u8			h264_intra_qp;
+	u8			h264_inter_qp;
+	u8			h264_min_qp;
+	u8			h264_max_qp;
+	u8			h264_deblk_enabled;
+	u8			h264_deblk_alpha;
+	u8			h264_deblk_beta;
+	u8			mpeg4_intra_qp;
+	u8			mpeg4_inter_qp;
+	u8			gop_size;
+	int			intra_refresh;
+	int			codec_mode;
+	int			codec_mode_aux;
+	enum v4l2_mpeg_video_multi_slice_mode slice_mode;
+	u32			framerate;
+	u16			bitrate;
+	u32			slice_max_bits;
+	u32			slice_max_mb;
+};
+
+struct coda_timestamp {
+	struct list_head	list;
+	u32			sequence;
+	struct v4l2_timecode	timecode;
+	struct timeval		timestamp;
+};
+
+/* Per-queue, driver-specific private data */
+struct coda_q_data {
+	unsigned int		width;
+	unsigned int		height;
+	unsigned int		bytesperline;
+	unsigned int		sizeimage;
+	unsigned int		fourcc;
+	struct v4l2_rect	rect;
+};
+
+struct coda_iram_info {
+	u32		axi_sram_use;
+	phys_addr_t	buf_bit_use;
+	phys_addr_t	buf_ip_ac_dc_use;
+	phys_addr_t	buf_dbk_y_use;
+	phys_addr_t	buf_dbk_c_use;
+	phys_addr_t	buf_ovl_use;
+	phys_addr_t	buf_btp_use;
+	phys_addr_t	search_ram_paddr;
+	int		search_ram_size;
+	int		remaining;
+	phys_addr_t	next_paddr;
+};
+
+struct gdi_tiled_map {
+	int xy2ca_map[16];
+	int xy2ba_map[16];
+	int xy2ra_map[16];
+	int rbc2axi_map[32];
+	int xy2rbc_config;
+	int map_type;
+#define GDI_LINEAR_FRAME_MAP 0
+};
+
+struct coda_ctx;
+
+struct coda_context_ops {
+	int (*queue_init)(void *priv, struct vb2_queue *src_vq,
+			  struct vb2_queue *dst_vq);
+	int (*start_streaming)(struct coda_ctx *ctx);
+	int (*prepare_run)(struct coda_ctx *ctx);
+	void (*finish_run)(struct coda_ctx *ctx);
+	void (*seq_end_work)(struct work_struct *work);
+	void (*release)(struct coda_ctx *ctx);
+};
+
+struct coda_ctx {
+	struct coda_dev			*dev;
+	struct mutex			buffer_mutex;
+	struct list_head		list;
+	struct work_struct		pic_run_work;
+	struct work_struct		seq_end_work;
+	struct completion		completion;
+	const struct coda_context_ops	*ops;
+	int				aborting;
+	int				initialized;
+	int				streamon_out;
+	int				streamon_cap;
+	u32				isequence;
+	u32				qsequence;
+	u32				osequence;
+	u32				sequence_offset;
+	struct coda_q_data		q_data[2];
+	enum coda_inst_type		inst_type;
+	const struct coda_codec		*codec;
+	enum v4l2_colorspace		colorspace;
+	struct coda_params		params;
+	struct v4l2_ctrl_handler	ctrls;
+	struct v4l2_fh			fh;
+	int				gopcounter;
+	int				runcounter;
+	char				vpu_header[3][64];
+	int				vpu_header_size[3];
+	struct kfifo			bitstream_fifo;
+	struct mutex			bitstream_mutex;
+	struct coda_aux_buf		bitstream;
+	bool				hold;
+	struct coda_aux_buf		parabuf;
+	struct coda_aux_buf		psbuf;
+	struct coda_aux_buf		slicebuf;
+	struct coda_aux_buf		internal_frames[CODA_MAX_FRAMEBUFFERS];
+	u32				frame_types[CODA_MAX_FRAMEBUFFERS];
+	struct coda_timestamp		frame_timestamps[CODA_MAX_FRAMEBUFFERS];
+	u32				frame_errors[CODA_MAX_FRAMEBUFFERS];
+	struct list_head		timestamp_list;
+	struct coda_aux_buf		workbuf;
+	int				num_internal_frames;
+	int				idx;
+	int				reg_idx;
+	struct coda_iram_info		iram_info;
+	struct gdi_tiled_map		tiled_map;
+	u32				bit_stream_param;
+	u32				frm_dis_flg;
+	u32				frame_mem_ctrl;
+	int				display_idx;
+	struct dentry			*debugfs_entry;
+};
+
+extern int coda_debug;
+
+void coda_write(struct coda_dev *dev, u32 data, u32 reg);
+unsigned int coda_read(struct coda_dev *dev, u32 reg);
+
+int coda_alloc_aux_buf(struct coda_dev *dev, struct coda_aux_buf *buf,
+		       size_t size, const char *name, struct dentry *parent);
+void coda_free_aux_buf(struct coda_dev *dev, struct coda_aux_buf *buf);
+
+static inline int coda_alloc_context_buf(struct coda_ctx *ctx,
+					 struct coda_aux_buf *buf, size_t size,
+					 const char *name)
+{
+	return coda_alloc_aux_buf(ctx->dev, buf, size, name, ctx->debugfs_entry);
+}
+
+int coda_encoder_queue_init(void *priv, struct vb2_queue *src_vq,
+			    struct vb2_queue *dst_vq);
+int coda_decoder_queue_init(void *priv, struct vb2_queue *src_vq,
+			    struct vb2_queue *dst_vq);
+
+int coda_hw_reset(struct coda_ctx *ctx);
+
+void coda_fill_bitstream(struct coda_ctx *ctx);
+
+void coda_set_gdi_regs(struct coda_ctx *ctx);
+
+static inline struct coda_q_data *get_q_data(struct coda_ctx *ctx,
+					     enum v4l2_buf_type type)
+{
+	switch (type) {
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		return &(ctx->q_data[V4L2_M2M_SRC]);
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+		return &(ctx->q_data[V4L2_M2M_DST]);
+	default:
+		return NULL;
+	}
+}
+
+const char *coda_product_name(int product);
+
+int coda_check_firmware(struct coda_dev *dev);
+
+static inline int coda_get_bitstream_payload(struct coda_ctx *ctx)
+{
+	return kfifo_len(&ctx->bitstream_fifo);
+}
+
+void coda_bit_stream_end_flag(struct coda_ctx *ctx);
+
+int coda_h264_padding(int size, char *p);
+
+extern const struct coda_context_ops coda_bit_encode_ops;
+extern const struct coda_context_ops coda_bit_decode_ops;
+
+irqreturn_t coda_irq_handler(int irq, void *data);
diff --git a/drivers/media/platform/coda.h b/drivers/media/platform/coda/coda_regs.h
index c791275e307b..c791275e307b 100644
--- a/drivers/media/platform/coda.h
+++ b/drivers/media/platform/coda/coda_regs.h
diff --git a/drivers/media/platform/davinci/Kconfig b/drivers/media/platform/davinci/Kconfig
index afb3aec1320e..d9e1ddb586b1 100644
--- a/drivers/media/platform/davinci/Kconfig
+++ b/drivers/media/platform/davinci/Kconfig
@@ -1,6 +1,8 @@
 config VIDEO_DAVINCI_VPIF_DISPLAY
 	tristate "TI DaVinci VPIF V4L2-Display driver"
-	depends on VIDEO_DEV && ARCH_DAVINCI
+	depends on VIDEO_DEV
+	depends on ARCH_DAVINCI || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select VIDEO_ADV7343 if MEDIA_SUBDRV_AUTOSELECT
 	select VIDEO_THS7303 if MEDIA_SUBDRV_AUTOSELECT
@@ -14,7 +16,9 @@ config VIDEO_DAVINCI_VPIF_DISPLAY
 
 config VIDEO_DAVINCI_VPIF_CAPTURE
 	tristate "TI DaVinci VPIF video capture driver"
-	depends on VIDEO_DEV && ARCH_DAVINCI
+	depends on VIDEO_DEV
+	depends on ARCH_DAVINCI || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	help
 	  Enables Davinci VPIF module used for capture devices.
@@ -26,7 +30,9 @@ config VIDEO_DAVINCI_VPIF_CAPTURE
 
 config VIDEO_DM6446_CCDC
 	tristate "TI DM6446 CCDC video capture driver"
-	depends on VIDEO_V4L2 && (ARCH_DAVINCI || ARCH_OMAP3)
+	depends on VIDEO_V4L2
+	depends on ARCH_DAVINCI || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF_DMA_CONTIG
 	help
 	   Enables DaVinci CCD hw module. DaVinci CCDC hw interfaces
@@ -40,7 +46,9 @@ config VIDEO_DM6446_CCDC
 
 config VIDEO_DM355_CCDC
 	tristate "TI DM355 CCDC video capture driver"
-	depends on VIDEO_V4L2 && ARCH_DAVINCI
+	depends on VIDEO_V4L2
+	depends on ARCH_DAVINCI || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF_DMA_CONTIG
 	help
 	   Enables DM355 CCD hw module. DM355 CCDC hw interfaces
@@ -55,6 +63,7 @@ config VIDEO_DM355_CCDC
 config VIDEO_DM365_ISIF
 	tristate "TI DM365 ISIF video capture driver"
 	depends on VIDEO_V4L2 && ARCH_DAVINCI
+	depends on HAS_DMA
 	select VIDEOBUF_DMA_CONTIG
 	help
 	   Enables ISIF hw module. This is the hardware module for
@@ -67,6 +76,7 @@ config VIDEO_DM365_ISIF
 config VIDEO_DAVINCI_VPBE_DISPLAY
 	tristate "TI DaVinci VPBE V4L2-Display driver"
 	depends on ARCH_DAVINCI
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	help
 	    Enables Davinci VPBE module used for display devices.
diff --git a/drivers/media/platform/davinci/dm355_ccdc.c b/drivers/media/platform/davinci/dm355_ccdc.c
index 05f8fb7f7b70..3f44deb5b7a7 100644
--- a/drivers/media/platform/davinci/dm355_ccdc.c
+++ b/drivers/media/platform/davinci/dm355_ccdc.c
@@ -460,7 +460,7 @@ static void ccdc_config_black_compense(struct ccdc_black_compensation *bcomp)
  * ccdc_write_dfc_entry()
  * write an entry in the dfc table.
  */
-int ccdc_write_dfc_entry(int index, struct ccdc_vertical_dft *dfc)
+static int ccdc_write_dfc_entry(int index, struct ccdc_vertical_dft *dfc)
 {
 /* TODO This is to be re-visited and adjusted */
 #define DFC_WRITE_WAIT_COUNT	1000
diff --git a/drivers/media/platform/davinci/dm644x_ccdc.c b/drivers/media/platform/davinci/dm644x_ccdc.c
index 07e98df3d867..62a0ebb01056 100644
--- a/drivers/media/platform/davinci/dm644x_ccdc.c
+++ b/drivers/media/platform/davinci/dm644x_ccdc.c
@@ -130,9 +130,9 @@ static void ccdc_enable_vport(int flag)
  * This function will configure the window size
  * to be capture in CCDC reg
  */
-void ccdc_setwin(struct v4l2_rect *image_win,
-		enum ccdc_frmfmt frm_fmt,
-		int ppc)
+static void ccdc_setwin(struct v4l2_rect *image_win,
+			enum ccdc_frmfmt frm_fmt,
+			int ppc)
 {
 	int horz_start, horz_nr_pixels;
 	int vert_start, vert_nr_lines;
@@ -291,7 +291,7 @@ static int ccdc_update_raw_params(struct ccdc_config_params_raw *raw_params)
 		dev_dbg(ccdc_cfg.dev, "\n copy_from_user failed");
 		return -EFAULT;
 	}
-	config_params->fault_pxl.fpc_table_addr = (unsigned int)fpc_physaddr;
+	config_params->fault_pxl.fpc_table_addr = (unsigned long)fpc_physaddr;
 	return 0;
 }
 
@@ -370,7 +370,7 @@ static int ccdc_set_params(void __user *params)
  * ccdc_config_ycbcr()
  * This function will configure CCDC for YCbCr video capture
  */
-void ccdc_config_ycbcr(void)
+static void ccdc_config_ycbcr(void)
 {
 	struct ccdc_params_ycbcr *params = &ccdc_cfg.ycbcr;
 	u32 syn_mode;
@@ -506,7 +506,7 @@ static void ccdc_config_fpc(struct ccdc_fault_pixel *fpc)
 
 	/* Configure Fault pixel if needed */
 	regw(fpc->fpc_table_addr, CCDC_FPC_ADDR);
-	dev_dbg(ccdc_cfg.dev, "\nWriting 0x%x to FPC_ADDR...\n",
+	dev_dbg(ccdc_cfg.dev, "\nWriting 0x%lx to FPC_ADDR...\n",
 		       (fpc->fpc_table_addr));
 	/* Write the FPC params with FPC disable */
 	val = fpc->fp_num & CCDC_FPC_FPC_NUM_MASK;
@@ -523,7 +523,7 @@ static void ccdc_config_fpc(struct ccdc_fault_pixel *fpc)
  * ccdc_config_raw()
  * This function will configure CCDC for Raw capture mode
  */
-void ccdc_config_raw(void)
+static void ccdc_config_raw(void)
 {
 	struct ccdc_params_raw *params = &ccdc_cfg.bayer;
 	struct ccdc_config_params_raw *config_params =
diff --git a/drivers/media/platform/davinci/vpfe_capture.c b/drivers/media/platform/davinci/vpfe_capture.c
index ea7661a27479..de55f47a77db 100644
--- a/drivers/media/platform/davinci/vpfe_capture.c
+++ b/drivers/media/platform/davinci/vpfe_capture.c
@@ -125,7 +125,7 @@ static DEFINE_MUTEX(ccdc_lock);
 /* ccdc configuration */
 static struct ccdc_config *ccdc_cfg;
 
-const struct vpfe_standard vpfe_standards[] = {
+static const struct vpfe_standard vpfe_standards[] = {
 	{V4L2_STD_525_60, 720, 480, {11, 10}, 1},
 	{V4L2_STD_625_50, 720, 576, {54, 59}, 1},
 };
@@ -442,11 +442,10 @@ static int vpfe_config_image_format(struct vpfe_device *vpfe_dev,
 		return ret;
 
 	/* Update the values of sizeimage and bytesperline */
-	if (!ret) {
-		pix->bytesperline = ccdc_dev->hw_ops.get_line_length();
-		pix->sizeimage = pix->bytesperline * pix->height;
-	}
-	return ret;
+	pix->bytesperline = ccdc_dev->hw_ops.get_line_length();
+	pix->sizeimage = pix->bytesperline * pix->height;
+
+	return 0;
 }
 
 static int vpfe_initialize_device(struct vpfe_device *vpfe_dev)
@@ -943,12 +942,11 @@ static int vpfe_g_fmt_vid_cap(struct file *file, void *priv,
 				struct v4l2_format *fmt)
 {
 	struct vpfe_device *vpfe_dev = video_drvdata(file);
-	int ret = 0;
 
 	v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_g_fmt_vid_cap\n");
 	/* Fill in the information about format */
 	*fmt = vpfe_dev->fmt;
-	return ret;
+	return 0;
 }
 
 static int vpfe_enum_fmt_vid_cap(struct file *file, void  *priv,
@@ -1914,7 +1912,7 @@ static int vpfe_probe(struct platform_device *pdev)
 	v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
 		"trying to register vpfe device.\n");
 	v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev,
-		"video_dev=%x\n", (int)&vpfe_dev->video_dev);
+		"video_dev=%p\n", &vpfe_dev->video_dev);
 	vpfe_dev->fmt.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 	ret = video_register_device(vpfe_dev->video_dev,
 				    VFL_TYPE_GRABBER, -1);
diff --git a/drivers/media/platform/davinci/vpif.c b/drivers/media/platform/davinci/vpif.c
index cd08e5248387..3dad5bd7fe0a 100644
--- a/drivers/media/platform/davinci/vpif.c
+++ b/drivers/media/platform/davinci/vpif.c
@@ -38,6 +38,7 @@ MODULE_LICENSE("GPL");
 #define VPIF_CH3_MAX_MODES	2
 
 spinlock_t vpif_lock;
+EXPORT_SYMBOL_GPL(vpif_lock);
 
 void __iomem *vpif_base;
 EXPORT_SYMBOL_GPL(vpif_base);
diff --git a/drivers/media/platform/davinci/vpif_capture.c b/drivers/media/platform/davinci/vpif_capture.c
index b054b7eec53d..3ccb26ff43c8 100644
--- a/drivers/media/platform/davinci/vpif_capture.c
+++ b/drivers/media/platform/davinci/vpif_capture.c
@@ -213,8 +213,6 @@ static int vpif_start_streaming(struct vb2_queue *vq, unsigned int count)
 	/* Remove buffer from the buffer queue */
 	list_del(&common->cur_frm->list);
 	spin_unlock_irqrestore(&common->irqlock, flags);
-	/* Mark state of the current frame to active */
-	common->cur_frm->vb.state = VB2_BUF_STATE_ACTIVE;
 
 	addr = vb2_dma_contig_plane_dma_addr(&common->cur_frm->vb, 0);
 
@@ -350,7 +348,6 @@ static void vpif_schedule_next_buffer(struct common_obj *common)
 	/* Remove that buffer from the buffer queue */
 	list_del(&common->next_frm->list);
 	spin_unlock(&common->irqlock);
-	common->next_frm->vb.state = VB2_BUF_STATE_ACTIVE;
 	addr = vb2_dma_contig_plane_dma_addr(&common->next_frm->vb, 0);
 
 	/* Set top and bottom field addresses in VPIF registers */
@@ -373,7 +370,6 @@ static irqreturn_t vpif_channel_isr(int irq, void *dev_id)
 	struct vpif_device *dev = &vpif_obj;
 	struct common_obj *common;
 	struct channel_obj *ch;
-	enum v4l2_field field;
 	int channel_id = 0;
 	int fid = -1, i;
 
@@ -383,8 +379,6 @@ static irqreturn_t vpif_channel_isr(int irq, void *dev_id)
 
 	ch = dev->dev[channel_id];
 
-	field = ch->common[VPIF_VIDEO_INDEX].fmt.fmt.pix.field;
-
 	for (i = 0; i < VPIF_NUMBER_OF_OBJECTS; i++) {
 		common = &ch->common[i];
 		/* skip If streaming is not started in this channel */
@@ -533,7 +527,7 @@ static int vpif_update_std_info(struct channel_obj *ch)
  */
 static void vpif_calculate_offsets(struct channel_obj *ch)
 {
-	unsigned int hpitch, vpitch, sizeimage;
+	unsigned int hpitch, sizeimage;
 	struct video_obj *vid_ch = &(ch->video);
 	struct vpif_params *vpifparams = &ch->vpifparams;
 	struct common_obj *common = &ch->common[VPIF_VIDEO_INDEX];
@@ -552,7 +546,6 @@ static void vpif_calculate_offsets(struct channel_obj *ch)
 	sizeimage = common->fmt.fmt.pix.sizeimage;
 
 	hpitch = common->fmt.fmt.pix.bytesperline;
-	vpitch = sizeimage / (hpitch * 2);
 
 	if ((V4L2_FIELD_NONE == vid_ch->buf_field) ||
 	    (V4L2_FIELD_INTERLACED == vid_ch->buf_field)) {
@@ -1603,7 +1596,7 @@ static int vpif_suspend(struct device *dev)
 		ch = vpif_obj.dev[i];
 		common = &ch->common[VPIF_VIDEO_INDEX];
 
-		if (!vb2_is_streaming(&common->buffer_queue))
+		if (!vb2_start_streaming_called(&common->buffer_queue))
 			continue;
 
 		mutex_lock(&common->lock);
@@ -1637,7 +1630,7 @@ static int vpif_resume(struct device *dev)
 		ch = vpif_obj.dev[i];
 		common = &ch->common[VPIF_VIDEO_INDEX];
 
-		if (!vb2_is_streaming(&common->buffer_queue))
+		if (!vb2_start_streaming_called(&common->buffer_queue))
 			continue;
 
 		mutex_lock(&common->lock);
diff --git a/drivers/media/platform/davinci/vpif_display.c b/drivers/media/platform/davinci/vpif_display.c
index a03ec7381cfe..8d6ced56253c 100644
--- a/drivers/media/platform/davinci/vpif_display.c
+++ b/drivers/media/platform/davinci/vpif_display.c
@@ -196,8 +196,6 @@ static int vpif_start_streaming(struct vb2_queue *vq, unsigned int count)
 
 	list_del(&common->cur_frm->list);
 	spin_unlock_irqrestore(&common->irqlock, flags);
-	/* Mark state of the current frame to active */
-	common->cur_frm->vb.state = VB2_BUF_STATE_ACTIVE;
 
 	addr = vb2_dma_contig_plane_dma_addr(&common->cur_frm->vb, 0);
 	common->set_addr((addr + common->ytop_off),
@@ -306,8 +304,6 @@ static void process_progressive_mode(struct common_obj *common)
 	/* Remove that buffer from the buffer queue */
 	list_del(&common->next_frm->list);
 	spin_unlock(&common->irqlock);
-	/* Mark status of the buffer as active */
-	common->next_frm->vb.state = VB2_BUF_STATE_ACTIVE;
 
 	/* Set top and bottom field addrs in VPIF registers */
 	addr = vb2_dma_contig_plane_dma_addr(&common->next_frm->vb, 0);
@@ -360,7 +356,6 @@ static irqreturn_t vpif_channel_isr(int irq, void *dev_id)
 	struct vpif_device *dev = &vpif_obj;
 	struct channel_obj *ch;
 	struct common_obj *common;
-	enum v4l2_field field;
 	int fid = -1, i;
 	int channel_id = 0;
 
@@ -369,7 +364,6 @@ static irqreturn_t vpif_channel_isr(int irq, void *dev_id)
 		return IRQ_NONE;
 
 	ch = dev->dev[channel_id];
-	field = ch->common[VPIF_VIDEO_INDEX].fmt.fmt.pix.field;
 	for (i = 0; i < VPIF_NUMOBJECTS; i++) {
 		common = &ch->common[i];
 		/* If streaming is started in this channel */
@@ -502,7 +496,7 @@ static void vpif_calculate_offsets(struct channel_obj *ch)
 	struct vpif_params *vpifparams = &ch->vpifparams;
 	enum v4l2_field field = common->fmt.fmt.pix.field;
 	struct video_obj *vid_ch = &ch->video;
-	unsigned int hpitch, vpitch, sizeimage;
+	unsigned int hpitch, sizeimage;
 
 	if (V4L2_FIELD_ANY == common->fmt.fmt.pix.field) {
 		if (ch->vpifparams.std_info.frm_fmt)
@@ -516,7 +510,6 @@ static void vpif_calculate_offsets(struct channel_obj *ch)
 	sizeimage = common->fmt.fmt.pix.sizeimage;
 
 	hpitch = common->fmt.fmt.pix.bytesperline;
-	vpitch = sizeimage / (hpitch * 2);
 	if ((V4L2_FIELD_NONE == vid_ch->buf_field) ||
 	    (V4L2_FIELD_INTERLACED == vid_ch->buf_field)) {
 		common->ytop_off = 0;
@@ -813,17 +806,14 @@ static int vpif_set_output(struct vpif_display_config *vpif_cfg,
 {
 	struct vpif_display_chan_config *chan_cfg =
 		&vpif_cfg->chan_config[ch->channel_id];
-	struct vpif_subdev_info *subdev_info = NULL;
 	struct v4l2_subdev *sd = NULL;
 	u32 input = 0, output = 0;
 	int sd_index;
 	int ret;
 
 	sd_index = vpif_output_to_subdev(vpif_cfg, chan_cfg, index);
-	if (sd_index >= 0) {
+	if (sd_index >= 0)
 		sd = vpif_obj.sd[sd_index];
-		subdev_info = &vpif_cfg->subdevinfo[sd_index];
-	}
 
 	if (sd) {
 		input = chan_cfg->outputs[index].input_route;
@@ -1210,8 +1200,8 @@ static int vpif_probe_complete(void)
 		INIT_LIST_HEAD(&common->dma_queue);
 
 		/* register video device */
-		vpif_dbg(1, debug, "channel=%x,channel->video_dev=%x\n",
-			 (int)ch, (int)&ch->video_dev);
+		vpif_dbg(1, debug, "channel=%p,channel->video_dev=%p\n",
+			 ch, &ch->video_dev);
 
 		/* Initialize the video_device structure */
 		vdev = ch->video_dev;
@@ -1410,7 +1400,7 @@ static int vpif_suspend(struct device *dev)
 		ch = vpif_obj.dev[i];
 		common = &ch->common[VPIF_VIDEO_INDEX];
 
-		if (!vb2_is_streaming(&common->buffer_queue))
+		if (!vb2_start_streaming_called(&common->buffer_queue))
 			continue;
 
 		mutex_lock(&common->lock);
@@ -1442,7 +1432,7 @@ static int vpif_resume(struct device *dev)
 		ch = vpif_obj.dev[i];
 		common = &ch->common[VPIF_VIDEO_INDEX];
 
-		if (!vb2_is_streaming(&common->buffer_queue))
+		if (!vb2_start_streaming_called(&common->buffer_queue))
 			continue;
 
 		mutex_lock(&common->lock);
diff --git a/drivers/media/platform/exynos-gsc/gsc-core.c b/drivers/media/platform/exynos-gsc/gsc-core.c
index 9d0cc04d7ab7..b4c9f1d08968 100644
--- a/drivers/media/platform/exynos-gsc/gsc-core.c
+++ b/drivers/media/platform/exynos-gsc/gsc-core.c
@@ -852,8 +852,8 @@ int gsc_prepare_addr(struct gsc_ctx *ctx, struct vb2_buffer *vb,
 		(frame->fmt->pixelformat == V4L2_PIX_FMT_YVU420M))
 		swap(addr->cb, addr->cr);
 
-	pr_debug("ADDR: y= 0x%X  cb= 0x%X cr= 0x%X ret= %d",
-		addr->y, addr->cb, addr->cr, ret);
+	pr_debug("ADDR: y= %pad  cb= %pad cr= %pad ret= %d",
+		&addr->y, &addr->cb, &addr->cr, ret);
 
 	return ret;
 }
@@ -1086,7 +1086,7 @@ static int gsc_probe(struct platform_device *pdev)
 	else
 		gsc->id = pdev->id;
 
-	if (gsc->id < 0 || gsc->id >= drv_data->num_entities) {
+	if (gsc->id >= drv_data->num_entities) {
 		dev_err(dev, "Invalid platform device id: %d\n", gsc->id);
 		return -EINVAL;
 	}
diff --git a/drivers/media/platform/exynos-gsc/gsc-m2m.c b/drivers/media/platform/exynos-gsc/gsc-m2m.c
index e434f1f03d7b..74e1de637e8f 100644
--- a/drivers/media/platform/exynos-gsc/gsc-m2m.c
+++ b/drivers/media/platform/exynos-gsc/gsc-m2m.c
@@ -362,7 +362,6 @@ static int gsc_m2m_reqbufs(struct file *file, void *fh,
 {
 	struct gsc_ctx *ctx = fh_to_ctx(fh);
 	struct gsc_dev *gsc = ctx->gsc_dev;
-	struct gsc_frame *frame;
 	u32 max_cnt;
 
 	max_cnt = (reqbufs->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) ?
@@ -376,8 +375,6 @@ static int gsc_m2m_reqbufs(struct file *file, void *fh,
 			gsc_ctx_state_lock_clear(GSC_DST_FMT, ctx);
 	}
 
-	frame = ctx_get_frame(ctx, reqbufs->type);
-
 	return v4l2_m2m_reqbufs(file, ctx->m2m_ctx, reqbufs);
 }
 
diff --git a/drivers/media/platform/exynos-gsc/gsc-regs.c b/drivers/media/platform/exynos-gsc/gsc-regs.c
index e22d147a6940..ce12a1100511 100644
--- a/drivers/media/platform/exynos-gsc/gsc-regs.c
+++ b/drivers/media/platform/exynos-gsc/gsc-regs.c
@@ -90,8 +90,8 @@ void gsc_hw_set_output_buf_masking(struct gsc_dev *dev, u32 shift,
 void gsc_hw_set_input_addr(struct gsc_dev *dev, struct gsc_addr *addr,
 				int index)
 {
-	pr_debug("src_buf[%d]: 0x%X, cb: 0x%X, cr: 0x%X", index,
-			addr->y, addr->cb, addr->cr);
+	pr_debug("src_buf[%d]: %pad, cb: %pad, cr: %pad", index,
+			&addr->y, &addr->cb, &addr->cr);
 	writel(addr->y, dev->regs + GSC_IN_BASE_ADDR_Y(index));
 	writel(addr->cb, dev->regs + GSC_IN_BASE_ADDR_CB(index));
 	writel(addr->cr, dev->regs + GSC_IN_BASE_ADDR_CR(index));
@@ -101,8 +101,8 @@ void gsc_hw_set_input_addr(struct gsc_dev *dev, struct gsc_addr *addr,
 void gsc_hw_set_output_addr(struct gsc_dev *dev,
 			     struct gsc_addr *addr, int index)
 {
-	pr_debug("dst_buf[%d]: 0x%X, cb: 0x%X, cr: 0x%X",
-			index, addr->y, addr->cb, addr->cr);
+	pr_debug("dst_buf[%d]: %pad, cb: %pad, cr: %pad",
+			index, &addr->y, &addr->cb, &addr->cr);
 	writel(addr->y, dev->regs + GSC_OUT_BASE_ADDR_Y(index));
 	writel(addr->cb, dev->regs + GSC_OUT_BASE_ADDR_CB(index));
 	writel(addr->cr, dev->regs + GSC_OUT_BASE_ADDR_CR(index));
diff --git a/drivers/media/platform/exynos4-is/Kconfig b/drivers/media/platform/exynos4-is/Kconfig
index 5dcaa0a80540..77c951237744 100644
--- a/drivers/media/platform/exynos4-is/Kconfig
+++ b/drivers/media/platform/exynos4-is/Kconfig
@@ -2,7 +2,7 @@
 config VIDEO_SAMSUNG_EXYNOS4_IS
 	bool "Samsung S5P/EXYNOS4 SoC series Camera Subsystem driver"
 	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on (PLAT_S5P || ARCH_EXYNOS)
+	depends on (PLAT_S5P || ARCH_EXYNOS || COMPILE_TEST)
 	depends on OF && COMMON_CLK
 	help
 	  Say Y here to enable camera host interface devices for
@@ -16,6 +16,7 @@ config VIDEO_EXYNOS4_IS_COMMON
 config VIDEO_S5P_FIMC
 	tristate "S5P/EXYNOS4 FIMC/CAMIF camera interface driver"
 	depends on I2C
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
 	select MFD_SYSCON
@@ -43,6 +44,7 @@ if SOC_EXYNOS4212 || SOC_EXYNOS4412 || SOC_EXYNOS5250
 config VIDEO_EXYNOS_FIMC_LITE
 	tristate "EXYNOS FIMC-LITE camera interface driver"
 	depends on I2C
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select VIDEO_EXYNOS4_IS_COMMON
 	help
@@ -55,6 +57,7 @@ endif
 
 config VIDEO_EXYNOS4_FIMC_IS
 	tristate "EXYNOS4x12 FIMC-IS (Imaging Subsystem) driver"
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	depends on OF
 	select FW_LOADER
diff --git a/drivers/media/platform/exynos4-is/fimc-is-errno.c b/drivers/media/platform/exynos4-is/fimc-is-errno.c
index e8519e151c1a..e050e63fe358 100644
--- a/drivers/media/platform/exynos4-is/fimc-is-errno.c
+++ b/drivers/media/platform/exynos4-is/fimc-is-errno.c
@@ -15,7 +15,7 @@
 
 #include "fimc-is-errno.h"
 
-const char * const fimc_is_param_strerr(unsigned int error)
+const char *fimc_is_param_strerr(unsigned int error)
 {
 	switch (error) {
 	case ERROR_COMMON_CMD:
@@ -146,7 +146,7 @@ const char * const fimc_is_param_strerr(unsigned int error)
 	}
 }
 
-const char * const fimc_is_strerr(unsigned int error)
+const char *fimc_is_strerr(unsigned int error)
 {
 	error &= ~IS_ERROR_TIME_OUT_FLAG;
 
diff --git a/drivers/media/platform/exynos4-is/fimc-is-errno.h b/drivers/media/platform/exynos4-is/fimc-is-errno.h
index 3de6f6da6f87..ef981e74513a 100644
--- a/drivers/media/platform/exynos4-is/fimc-is-errno.h
+++ b/drivers/media/platform/exynos4-is/fimc-is-errno.h
@@ -242,7 +242,7 @@ enum fimc_is_error {
 	ERROR_SCALER_FLIP				= 521,
 };
 
-const char * const fimc_is_strerr(unsigned int error);
-const char * const fimc_is_param_strerr(unsigned int error);
+const char *fimc_is_strerr(unsigned int error);
+const char *fimc_is_param_strerr(unsigned int error);
 
 #endif /* FIMC_IS_ERR_H_ */
diff --git a/drivers/media/platform/exynos4-is/fimc-is-param.c b/drivers/media/platform/exynos4-is/fimc-is-param.c
index bf1465d1bf6d..72b9b436c5c0 100644
--- a/drivers/media/platform/exynos4-is/fimc-is-param.c
+++ b/drivers/media/platform/exynos4-is/fimc-is-param.c
@@ -667,7 +667,6 @@ void __is_set_fd_config_orientation_val(struct fimc_is *is, u32 val)
 void fimc_is_set_initial_params(struct fimc_is *is)
 {
 	struct global_param *global;
-	struct sensor_param *sensor;
 	struct isp_param *isp;
 	struct drc_param *drc;
 	struct fd_param *fd;
@@ -676,7 +675,6 @@ void fimc_is_set_initial_params(struct fimc_is *is)
 
 	index = is->config_index;
 	global = &is->config[index].global;
-	sensor = &is->config[index].sensor;
 	isp = &is->config[index].isp;
 	drc = &is->config[index].drc;
 	fd = &is->config[index].fd;
diff --git a/drivers/media/platform/exynos4-is/fimc-is.c b/drivers/media/platform/exynos4-is/fimc-is.c
index 5476dce3ad29..22162b2567da 100644
--- a/drivers/media/platform/exynos4-is/fimc-is.c
+++ b/drivers/media/platform/exynos4-is/fimc-is.c
@@ -388,7 +388,7 @@ static void fimc_is_load_firmware(const struct firmware *fw, void *context)
 	mutex_lock(&is->lock);
 
 	if (fw->size < FIMC_IS_FW_SIZE_MIN || fw->size > FIMC_IS_FW_SIZE_MAX) {
-		dev_err(dev, "wrong firmware size: %d\n", fw->size);
+		dev_err(dev, "wrong firmware size: %zu\n", fw->size);
 		goto done;
 	}
 
@@ -416,7 +416,7 @@ static void fimc_is_load_firmware(const struct firmware *fw, void *context)
 
 	dev_info(dev, "loaded firmware: %s, rev. %s\n",
 		 is->fw.info, is->fw.version);
-	dev_dbg(dev, "FW size: %d, paddr: %#x\n", fw->size, is->memory.paddr);
+	dev_dbg(dev, "FW size: %zu, paddr: %pad\n", fw->size, &is->memory.paddr);
 
 	is->is_shared_region->chip_id = 0xe4412;
 	is->is_shared_region->chip_rev_no = 1;
@@ -693,9 +693,9 @@ int fimc_is_hw_initialize(struct fimc_is *is)
 		return -EIO;
 	}
 
-	pr_debug("shared region: %#x, parameter region: %#x\n",
-		 is->memory.paddr + FIMC_IS_SHARED_REGION_OFFSET,
-		 is->is_dma_p_region);
+	pr_debug("shared region: %pad, parameter region: %pad\n",
+		 &is->memory.paddr + FIMC_IS_SHARED_REGION_OFFSET,
+		 &is->is_dma_p_region);
 
 	is->setfile.sub_index = 0;
 
diff --git a/drivers/media/platform/exynos4-is/fimc-isp-video.c b/drivers/media/platform/exynos4-is/fimc-isp-video.c
index 93f9cf2ebcd6..76b6b4d14616 100644
--- a/drivers/media/platform/exynos4-is/fimc-isp-video.c
+++ b/drivers/media/platform/exynos4-is/fimc-isp-video.c
@@ -219,9 +219,9 @@ static void isp_video_capture_buffer_queue(struct vb2_buffer *vb)
 							ivb->dma_addr[i];
 
 			isp_dbg(2, &video->ve.vdev,
-				"dma_buf %d (%d/%d/%d) addr: %#x\n",
-				buf_index, ivb->index, i, vb->v4l2_buf.index,
-				ivb->dma_addr[i]);
+				"dma_buf %pad (%d/%d/%d) addr: %pad\n",
+				&buf_index, ivb->index, i, vb->v4l2_buf.index,
+				&ivb->dma_addr[i]);
 		}
 
 		if (++video->buf_count < video->reqbufs_count)
@@ -313,7 +313,6 @@ static int isp_video_release(struct file *file)
 	struct fimc_is_video *ivc = &isp->video_capture;
 	struct media_entity *entity = &ivc->ve.vdev.entity;
 	struct media_device *mdev = entity->parent;
-	int ret = 0;
 
 	mutex_lock(&isp->video_lock);
 
@@ -335,7 +334,7 @@ static int isp_video_release(struct file *file)
 	pm_runtime_put(&isp->pdev->dev);
 	mutex_unlock(&isp->video_lock);
 
-	return ret;
+	return 0;
 }
 
 static const struct v4l2_file_operations isp_video_fops = {
diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c
index 344718df5c62..54c49d5e7690 100644
--- a/drivers/media/platform/exynos4-is/media-dev.c
+++ b/drivers/media/platform/exynos4-is/media-dev.c
@@ -1098,8 +1098,10 @@ static int fimc_md_link_notify(struct media_link *link, unsigned int flags,
 	if (notification == MEDIA_DEV_NOTIFY_PRE_LINK_CH) {
 		if (!(flags & MEDIA_LNK_FL_ENABLED))
 			ret = __fimc_md_modify_pipelines(sink, false);
+#if 0
 		else
-			; /* TODO: Link state change validation */
+			/* TODO: Link state change validation */
+#endif
 	/* After link activation */
 	} else if (notification == MEDIA_DEV_NOTIFY_POST_LINK_CH &&
 		   (link->flags & MEDIA_LNK_FL_ENABLED)) {
diff --git a/drivers/media/platform/exynos4-is/mipi-csis.c b/drivers/media/platform/exynos4-is/mipi-csis.c
index ae54ef5f535d..db6fd14d1936 100644
--- a/drivers/media/platform/exynos4-is/mipi-csis.c
+++ b/drivers/media/platform/exynos4-is/mipi-csis.c
@@ -25,6 +25,7 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
+#include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/videodev2.h>
@@ -752,7 +753,7 @@ static int s5pcsis_parse_dt(struct platform_device *pdev,
 	v4l2_of_parse_endpoint(node, &endpoint);
 
 	state->index = endpoint.base.port - FIMC_INPUT_MIPI_CSI2_0;
-	if (state->index < 0 || state->index >= CSIS_MAX_ENTITIES)
+	if (state->index >= CSIS_MAX_ENTITIES)
 		return -ENXIO;
 
 	/* Get MIPI CSI-2 bus configration from the endpoint node. */
diff --git a/drivers/media/platform/marvell-ccic/Kconfig b/drivers/media/platform/marvell-ccic/Kconfig
index bf739e3b3398..6265d36adceb 100644
--- a/drivers/media/platform/marvell-ccic/Kconfig
+++ b/drivers/media/platform/marvell-ccic/Kconfig
@@ -1,6 +1,7 @@
 config VIDEO_CAFE_CCIC
 	tristate "Marvell 88ALP01 (Cafe) CMOS Camera Controller support"
 	depends on PCI && I2C && VIDEO_V4L2
+	depends on HAS_DMA
 	select VIDEO_OV7670
 	select VIDEOBUF2_VMALLOC
 	select VIDEOBUF2_DMA_CONTIG
@@ -12,6 +13,7 @@ config VIDEO_CAFE_CCIC
 config VIDEO_MMP_CAMERA
 	tristate "Marvell Armada 610 integrated camera controller support"
 	depends on ARCH_MMP && I2C && VIDEO_V4L2
+	depends on HAS_DMA
 	select VIDEO_OV7670
 	select I2C_GPIO
 	select VIDEOBUF2_DMA_SG
diff --git a/drivers/media/platform/marvell-ccic/mcam-core.c b/drivers/media/platform/marvell-ccic/mcam-core.c
index be4b51212106..7a86c77bffa0 100644
--- a/drivers/media/platform/marvell-ccic/mcam-core.c
+++ b/drivers/media/platform/marvell-ccic/mcam-core.c
@@ -67,7 +67,7 @@ MODULE_PARM_DESC(dma_buf_size,
 		"parameters require larger buffers, an attempt to reallocate "
 		"will be made.");
 #else /* MCAM_MODE_VMALLOC */
-static const bool alloc_bufs_at_read = 0;
+static const bool alloc_bufs_at_read;
 static const int n_dma_bufs = 3;  /* Used by S/G_PARM */
 #endif /* MCAM_MODE_VMALLOC */
 
diff --git a/drivers/media/platform/mx2_emmaprp.c b/drivers/media/platform/mx2_emmaprp.c
index fa8f7cabe364..4971ff21f82b 100644
--- a/drivers/media/platform/mx2_emmaprp.c
+++ b/drivers/media/platform/mx2_emmaprp.c
@@ -27,7 +27,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-ioctl.h>
 #include <media/videobuf2-dma-contig.h>
-#include <asm/sizes.h>
+#include <linux/sizes.h>
 
 #define EMMAPRP_MODULE_NAME "mem2mem-emmaprp"
 
diff --git a/drivers/media/platform/omap/Kconfig b/drivers/media/platform/omap/Kconfig
index 37ad446b35b3..05de442d24e4 100644
--- a/drivers/media/platform/omap/Kconfig
+++ b/drivers/media/platform/omap/Kconfig
@@ -3,7 +3,7 @@ config VIDEO_OMAP2_VOUT_VRFB
 
 config VIDEO_OMAP2_VOUT
 	tristate "OMAP2/OMAP3 V4L2-Display driver"
-	depends on ARCH_OMAP2 || ARCH_OMAP3
+	depends on ARCH_OMAP2 || ARCH_OMAP3 || (COMPILE_TEST && HAS_MMU)
 	select VIDEOBUF_GEN
 	select VIDEOBUF_DMA_CONTIG
 	select OMAP2_DSS if HAS_IOMEM && ARCH_OMAP2PLUS
diff --git a/drivers/media/platform/omap/omap_vout.c b/drivers/media/platform/omap/omap_vout.c
index 2d177fa58471..64ab6fb06b9c 100644
--- a/drivers/media/platform/omap/omap_vout.c
+++ b/drivers/media/platform/omap/omap_vout.c
@@ -369,7 +369,7 @@ static int omapvid_setup_overlay(struct omap_vout_device *vout,
 {
 	int ret = 0;
 	struct omap_overlay_info info;
-	int cropheight, cropwidth, pixheight, pixwidth;
+	int cropheight, cropwidth, pixwidth;
 
 	if ((ovl->caps & OMAP_DSS_OVL_CAP_SCALE) == 0 &&
 			(outw != vout->pix.width || outh != vout->pix.height)) {
@@ -389,12 +389,10 @@ static int omapvid_setup_overlay(struct omap_vout_device *vout,
 	if (is_rotation_90_or_270(vout)) {
 		cropheight = vout->crop.width;
 		cropwidth = vout->crop.height;
-		pixheight = vout->pix.width;
 		pixwidth = vout->pix.height;
 	} else {
 		cropheight = vout->crop.height;
 		cropwidth = vout->crop.width;
-		pixheight = vout->pix.height;
 		pixwidth = vout->pix.width;
 	}
 
@@ -991,7 +989,7 @@ static int omap_vout_release(struct file *file)
 		mask = DISPC_IRQ_VSYNC | DISPC_IRQ_EVSYNC_EVEN |
 			DISPC_IRQ_EVSYNC_ODD | DISPC_IRQ_VSYNC2;
 		omap_dispc_unregister_isr(omap_vout_isr, vout, mask);
-		vout->streaming = 0;
+		vout->streaming = false;
 
 		videobuf_streamoff(q);
 		videobuf_queue_cancel(q);
@@ -1451,12 +1449,10 @@ static int vidioc_s_ctrl(struct file *file, void *fh, struct v4l2_control *a)
 	}
 	case V4L2_CID_VFLIP:
 	{
-		struct omap_overlay *ovl;
 		struct omapvideo_info *ovid;
 		unsigned int  mirror = a->value;
 
 		ovid = &vout->vid_info;
-		ovl = ovid->overlays[0];
 
 		mutex_lock(&vout->lock);
 		if (mirror && ovid->rotation_type == VOUT_ROT_NONE) {
@@ -1489,7 +1485,7 @@ static int vidioc_reqbufs(struct file *file, void *fh,
 	struct omap_vout_device *vout = fh;
 	struct videobuf_queue *q = &vout->vbq;
 
-	if ((req->type != V4L2_BUF_TYPE_VIDEO_OUTPUT) || (req->count < 0))
+	if (req->type != V4L2_BUF_TYPE_VIDEO_OUTPUT)
 		return -EINVAL;
 	/* if memory is not mmp or userptr
 	   return error */
@@ -1648,7 +1644,7 @@ static int vidioc_streamon(struct file *file, void *fh, enum v4l2_buf_type i)
 	vout->field_id = 0;
 
 	/* set flag here. Next QBUF will start DMA */
-	vout->streaming = 1;
+	vout->streaming = true;
 
 	vout->first_int = 1;
 
@@ -1708,7 +1704,7 @@ static int vidioc_streamoff(struct file *file, void *fh, enum v4l2_buf_type i)
 	if (!vout->streaming)
 		return -EINVAL;
 
-	vout->streaming = 0;
+	vout->streaming = false;
 	mask = DISPC_IRQ_VSYNC | DISPC_IRQ_EVSYNC_EVEN | DISPC_IRQ_EVSYNC_ODD
 		| DISPC_IRQ_VSYNC2;
 
@@ -1916,7 +1912,7 @@ static int __init omap_vout_setup_video_data(struct omap_vout_device *vout)
 	control[0].id = V4L2_CID_ROTATE;
 	control[0].value = 0;
 	vout->rotation = 0;
-	vout->mirror = 0;
+	vout->mirror = false;
 	vout->control[2].id = V4L2_CID_HFLIP;
 	vout->control[2].value = 0;
 	if (vout->vid_info.rotation_type == VOUT_ROT_VRFB)
diff --git a/drivers/media/platform/omap/omap_vout_vrfb.c b/drivers/media/platform/omap/omap_vout_vrfb.c
index 62e7e5783ce8..aa39306afc73 100644
--- a/drivers/media/platform/omap/omap_vout_vrfb.c
+++ b/drivers/media/platform/omap/omap_vout_vrfb.c
@@ -148,7 +148,7 @@ int omap_vout_setup_vrfb_bufs(struct platform_device *pdev, int vid_num,
 			ret =  -ENOMEM;
 			goto release_vrfb_ctx;
 		}
-		vout->vrfb_static_allocation = 1;
+		vout->vrfb_static_allocation = true;
 	}
 	return 0;
 
@@ -336,7 +336,7 @@ void omap_vout_calculate_vrfb_offset(struct omap_vout_device *vout)
 		offset = vout->vrfb_context[0].yoffset *
 			vout->vrfb_context[0].bytespp;
 		temp_ps = ps / vr_ps;
-		if (mirroring == 0) {
+		if (!mirroring) {
 			*cropped_offset = offset + line_length *
 				temp_ps * cleft + crop->top * temp_ps;
 		} else {
@@ -350,7 +350,7 @@ void omap_vout_calculate_vrfb_offset(struct omap_vout_device *vout)
 			vout->vrfb_context[0].bytespp) +
 			(vout->vrfb_context[0].xoffset *
 			vout->vrfb_context[0].bytespp));
-		if (mirroring == 0) {
+		if (!mirroring) {
 			*cropped_offset = offset + (line_length * ps * ctop) +
 				(cleft / vr_ps) * ps;
 
@@ -364,7 +364,7 @@ void omap_vout_calculate_vrfb_offset(struct omap_vout_device *vout)
 		offset = MAX_PIXELS_PER_LINE * vout->vrfb_context[0].xoffset *
 			vout->vrfb_context[0].bytespp;
 		temp_ps = ps / vr_ps;
-		if (mirroring == 0) {
+		if (!mirroring) {
 			*cropped_offset = offset + line_length *
 			    temp_ps * crop->left + ctop * ps;
 		} else {
@@ -375,7 +375,7 @@ void omap_vout_calculate_vrfb_offset(struct omap_vout_device *vout)
 		}
 		break;
 	case dss_rotation_0_degree:
-		if (mirroring == 0) {
+		if (!mirroring) {
 			*cropped_offset = (line_length * ps) *
 				crop->top + (crop->left / vr_ps) * ps;
 		} else {
diff --git a/drivers/media/platform/omap/omap_vout_vrfb.h b/drivers/media/platform/omap/omap_vout_vrfb.h
index ffde741e0590..4c2314839b48 100644
--- a/drivers/media/platform/omap/omap_vout_vrfb.h
+++ b/drivers/media/platform/omap/omap_vout_vrfb.h
@@ -23,18 +23,18 @@ int omap_vout_prepare_vrfb(struct omap_vout_device *vout,
 			struct videobuf_buffer *vb);
 void omap_vout_calculate_vrfb_offset(struct omap_vout_device *vout);
 #else
-void omap_vout_free_vrfb_buffers(struct omap_vout_device *vout) { }
-int omap_vout_setup_vrfb_bufs(struct platform_device *pdev, int vid_num,
+static inline void omap_vout_free_vrfb_buffers(struct omap_vout_device *vout) { };
+static inline int omap_vout_setup_vrfb_bufs(struct platform_device *pdev, int vid_num,
 			u32 static_vrfb_allocation)
-		{ return 0; }
-void omap_vout_release_vrfb(struct omap_vout_device *vout) { }
-int omap_vout_vrfb_buffer_setup(struct omap_vout_device *vout,
+		{ return 0; };
+static inline void omap_vout_release_vrfb(struct omap_vout_device *vout) { };
+static inline int omap_vout_vrfb_buffer_setup(struct omap_vout_device *vout,
 			unsigned int *count, unsigned int startindex)
-		{ return 0; }
-int omap_vout_prepare_vrfb(struct omap_vout_device *vout,
+		{ return 0; };
+static inline int omap_vout_prepare_vrfb(struct omap_vout_device *vout,
 			struct videobuf_buffer *vb)
-		{ return 0; }
-void omap_vout_calculate_vrfb_offset(struct omap_vout_device *vout) { }
+		{ return 0; };
+static inline void omap_vout_calculate_vrfb_offset(struct omap_vout_device *vout) { };
 #endif
 
 #endif
diff --git a/drivers/media/platform/omap3isp/cfa_coef_table.h b/drivers/media/platform/omap3isp/cfa_coef_table.h
index c84df0706f3e..e75b0eb2519b 100644
--- a/drivers/media/platform/omap3isp/cfa_coef_table.h
+++ b/drivers/media/platform/omap3isp/cfa_coef_table.h
@@ -11,16 +11,6 @@
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
  * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 { 244, 0, 247,   0,  12,  27,  36, 247, 250,   0,  27,   0,   4, 250,  12, 244,
diff --git a/drivers/media/platform/omap3isp/gamma_table.h b/drivers/media/platform/omap3isp/gamma_table.h
index 78deebf7d965..3b507078016d 100644
--- a/drivers/media/platform/omap3isp/gamma_table.h
+++ b/drivers/media/platform/omap3isp/gamma_table.h
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
   0,   0,   1,   2,   3,   3,   4,   5,   6,   8,  10,  12,  14,  16,  18,  20,
diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index 2c7aa6720569..72265e58ca60 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -40,16 +40,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #include <asm/cacheflush.h>
@@ -999,16 +989,14 @@ static int isp_pipeline_disable(struct isp_pipeline *pipe)
 					 video, s_stream, 0);
 		}
 
-		v4l2_subdev_call(subdev, video, s_stream, 0);
+		ret = v4l2_subdev_call(subdev, video, s_stream, 0);
 
 		if (subdev == &isp->isp_res.subdev)
-			ret = isp_pipeline_wait(isp, isp_pipeline_wait_resizer);
+			ret |= isp_pipeline_wait(isp, isp_pipeline_wait_resizer);
 		else if (subdev == &isp->isp_prev.subdev)
-			ret = isp_pipeline_wait(isp, isp_pipeline_wait_preview);
+			ret |= isp_pipeline_wait(isp, isp_pipeline_wait_preview);
 		else if (subdev == &isp->isp_ccdc.subdev)
-			ret = isp_pipeline_wait(isp, isp_pipeline_wait_ccdc);
-		else
-			ret = 0;
+			ret |= isp_pipeline_wait(isp, isp_pipeline_wait_ccdc);
 
 		/* Handle stop failures. An entity that fails to stop can
 		 * usually just be restarted. Flag the stop failure nonetheless
diff --git a/drivers/media/platform/omap3isp/isp.h b/drivers/media/platform/omap3isp/isp.h
index 2c314eea1252..cfdfc8714b6b 100644
--- a/drivers/media/platform/omap3isp/isp.h
+++ b/drivers/media/platform/omap3isp/isp.h
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_CORE_H
diff --git a/drivers/media/platform/omap3isp/ispccdc.c b/drivers/media/platform/omap3isp/ispccdc.c
index 9f727d20f06d..81a9dc053d58 100644
--- a/drivers/media/platform/omap3isp/ispccdc.c
+++ b/drivers/media/platform/omap3isp/ispccdc.c
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #include <linux/module.h>
@@ -491,14 +481,13 @@ done:
 static inline int ccdc_lsc_is_configured(struct isp_ccdc_device *ccdc)
 {
 	unsigned long flags;
+	int ret;
 
 	spin_lock_irqsave(&ccdc->lsc.req_lock, flags);
-	if (ccdc->lsc.active) {
-		spin_unlock_irqrestore(&ccdc->lsc.req_lock, flags);
-		return 1;
-	}
+	ret = ccdc->lsc.active != NULL;
 	spin_unlock_irqrestore(&ccdc->lsc.req_lock, flags);
-	return 0;
+
+	return ret;
 }
 
 static int ccdc_lsc_enable(struct isp_ccdc_device *ccdc)
@@ -818,29 +807,48 @@ static void ccdc_config_vp(struct isp_ccdc_device *ccdc)
 	struct isp_pipeline *pipe = to_isp_pipeline(&ccdc->subdev.entity);
 	struct isp_device *isp = to_isp_device(ccdc);
 	const struct isp_format_info *info;
+	struct v4l2_mbus_framefmt *format;
 	unsigned long l3_ick = pipe->l3_ick;
 	unsigned int max_div = isp->revision == ISP_REVISION_15_0 ? 64 : 8;
 	unsigned int div = 0;
-	u32 fmtcfg_vp;
+	u32 fmtcfg = ISPCCDC_FMTCFG_VPEN;
+
+	format = &ccdc->formats[CCDC_PAD_SOURCE_VP];
+
+	if (!format->code) {
+		/* Disable the video port when the input format isn't supported.
+		 * This is indicated by a pixel code set to 0.
+		 */
+		isp_reg_writel(isp, 0, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_FMTCFG);
+		return;
+	}
+
+	isp_reg_writel(isp, (0 << ISPCCDC_FMT_HORZ_FMTSPH_SHIFT) |
+		       (format->width << ISPCCDC_FMT_HORZ_FMTLNH_SHIFT),
+		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_FMT_HORZ);
+	isp_reg_writel(isp, (0 << ISPCCDC_FMT_VERT_FMTSLV_SHIFT) |
+		       ((format->height + 1) << ISPCCDC_FMT_VERT_FMTLNV_SHIFT),
+		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_FMT_VERT);
 
-	fmtcfg_vp = isp_reg_readl(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_FMTCFG)
-		  & ~(ISPCCDC_FMTCFG_VPIN_MASK | ISPCCDC_FMTCFG_VPIF_FRQ_MASK);
+	isp_reg_writel(isp, (format->width << ISPCCDC_VP_OUT_HORZ_NUM_SHIFT) |
+		       (format->height << ISPCCDC_VP_OUT_VERT_NUM_SHIFT),
+		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_VP_OUT);
 
 	info = omap3isp_video_format_info(ccdc->formats[CCDC_PAD_SINK].code);
 
 	switch (info->width) {
 	case 8:
 	case 10:
-		fmtcfg_vp |= ISPCCDC_FMTCFG_VPIN_9_0;
+		fmtcfg |= ISPCCDC_FMTCFG_VPIN_9_0;
 		break;
 	case 11:
-		fmtcfg_vp |= ISPCCDC_FMTCFG_VPIN_10_1;
+		fmtcfg |= ISPCCDC_FMTCFG_VPIN_10_1;
 		break;
 	case 12:
-		fmtcfg_vp |= ISPCCDC_FMTCFG_VPIN_11_2;
+		fmtcfg |= ISPCCDC_FMTCFG_VPIN_11_2;
 		break;
 	case 13:
-		fmtcfg_vp |= ISPCCDC_FMTCFG_VPIN_12_3;
+		fmtcfg |= ISPCCDC_FMTCFG_VPIN_12_3;
 		break;
 	}
 
@@ -850,75 +858,59 @@ static void ccdc_config_vp(struct isp_ccdc_device *ccdc)
 		div = l3_ick / pipe->external_rate;
 
 	div = clamp(div, 2U, max_div);
-	fmtcfg_vp |= (div - 2) << ISPCCDC_FMTCFG_VPIF_FRQ_SHIFT;
+	fmtcfg |= (div - 2) << ISPCCDC_FMTCFG_VPIF_FRQ_SHIFT;
 
-	isp_reg_writel(isp, fmtcfg_vp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_FMTCFG);
-}
-
-/*
- * ccdc_enable_vp - Enable Video Port.
- * @ccdc: Pointer to ISP CCDC device.
- * @enable: 0 Disables VP, 1 Enables VP
- *
- * This is needed for outputting image to Preview, H3A and HIST ISP submodules.
- */
-static void ccdc_enable_vp(struct isp_ccdc_device *ccdc, u8 enable)
-{
-	struct isp_device *isp = to_isp_device(ccdc);
-
-	isp_reg_clr_set(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_FMTCFG,
-			ISPCCDC_FMTCFG_VPEN, enable ? ISPCCDC_FMTCFG_VPEN : 0);
+	isp_reg_writel(isp, fmtcfg, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_FMTCFG);
 }
 
 /*
  * ccdc_config_outlineoffset - Configure memory saving output line offset
  * @ccdc: Pointer to ISP CCDC device.
- * @offset: Address offset to start a new line. Must be twice the
- *          Output width and aligned on 32 byte boundary
- * @oddeven: Specifies the odd/even line pattern to be chosen to store the
- *           output.
- * @numlines: Set the value 0-3 for +1-4lines, 4-7 for -1-4lines.
+ * @bpl: Number of bytes per line when stored in memory.
+ * @field: Field order when storing interlaced formats in memory.
+ *
+ * Configure the offsets for the line output control:
+ *
+ * - The horizontal line offset is defined as the number of bytes between the
+ *   start of two consecutive lines in memory. Set it to the given bytes per
+ *   line value.
+ *
+ * - The field offset value is defined as the number of lines to offset the
+ *   start of the field identified by FID = 1. Set it to one.
  *
- * - Configures the output line offset when stored in memory
- * - Sets the odd/even line pattern to store the output
- *    (EVENEVEN (1), ODDEVEN (2), EVENODD (3), ODDODD (4))
- * - Configures the number of even and odd line fields in case of rearranging
- * the lines.
+ * - The line offset values are defined as the number of lines (as defined by
+ *   the horizontal line offset) between the start of two consecutive lines for
+ *   all combinations of odd/even lines in odd/even fields. When interleaving
+ *   fields set them all to two lines, and to one line otherwise.
  */
 static void ccdc_config_outlineoffset(struct isp_ccdc_device *ccdc,
-					u32 offset, u8 oddeven, u8 numlines)
+				      unsigned int bpl,
+				      enum v4l2_field field)
 {
 	struct isp_device *isp = to_isp_device(ccdc);
+	u32 sdofst = 0;
 
-	isp_reg_writel(isp, offset & 0xffff,
-		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_HSIZE_OFF);
+	isp_reg_writel(isp, bpl & 0xffff, OMAP3_ISP_IOMEM_CCDC,
+		       ISPCCDC_HSIZE_OFF);
 
-	isp_reg_clr(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SDOFST,
-		    ISPCCDC_SDOFST_FINV);
-
-	isp_reg_clr(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SDOFST,
-		    ISPCCDC_SDOFST_FOFST_4L);
-
-	switch (oddeven) {
-	case EVENEVEN:
-		isp_reg_set(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SDOFST,
-			    (numlines & 0x7) << ISPCCDC_SDOFST_LOFST0_SHIFT);
-		break;
-	case ODDEVEN:
-		isp_reg_set(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SDOFST,
-			    (numlines & 0x7) << ISPCCDC_SDOFST_LOFST1_SHIFT);
-		break;
-	case EVENODD:
-		isp_reg_set(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SDOFST,
-			    (numlines & 0x7) << ISPCCDC_SDOFST_LOFST2_SHIFT);
-		break;
-	case ODDODD:
-		isp_reg_set(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SDOFST,
-			    (numlines & 0x7) << ISPCCDC_SDOFST_LOFST3_SHIFT);
+	switch (field) {
+	case V4L2_FIELD_INTERLACED_TB:
+	case V4L2_FIELD_INTERLACED_BT:
+		/* When interleaving fields in memory offset field one by one
+		 * line and set the line offset to two lines.
+		 */
+		sdofst |= (1 << ISPCCDC_SDOFST_LOFST0_SHIFT)
+		       |  (1 << ISPCCDC_SDOFST_LOFST1_SHIFT)
+		       |  (1 << ISPCCDC_SDOFST_LOFST2_SHIFT)
+		       |  (1 << ISPCCDC_SDOFST_LOFST3_SHIFT);
 		break;
+
 	default:
+		/* In all other cases set the line offsets to one line. */
 		break;
 	}
+
+	isp_reg_writel(isp, sdofst, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SDOFST);
 }
 
 /*
@@ -981,10 +973,16 @@ static void ccdc_config_sync_if(struct isp_ccdc_device *ccdc,
 
 	if (format->code == V4L2_MBUS_FMT_YUYV8_2X8 ||
 	    format->code == V4L2_MBUS_FMT_UYVY8_2X8) {
-		/* The bridge is enabled for YUV8 formats. Configure the input
-		 * mode accordingly.
+		/* According to the OMAP3 TRM the input mode only affects SYNC
+		 * mode, enabling BT.656 mode should take precedence. However,
+		 * in practice setting the input mode to YCbCr data on 8 bits
+		 * seems to be required in BT.656 mode. In SYNC mode set it to
+		 * YCbCr on 16 bits as the bridge is enabled in that case.
 		 */
-		syn_mode |= ISPCCDC_SYN_MODE_INPMOD_YCBCR16;
+		if (ccdc->bt656)
+			syn_mode |= ISPCCDC_SYN_MODE_INPMOD_YCBCR8;
+		else
+			syn_mode |= ISPCCDC_SYN_MODE_INPMOD_YCBCR16;
 	}
 
 	switch (data_size) {
@@ -1008,9 +1006,15 @@ static void ccdc_config_sync_if(struct isp_ccdc_device *ccdc,
 	if (pdata && pdata->hs_pol)
 		syn_mode |= ISPCCDC_SYN_MODE_HDPOL;
 
-	if (pdata && pdata->vs_pol)
+	/* The polarity of the vertical sync signal output by the BT.656
+	 * decoder is not documented and seems to be active low.
+	 */
+	if ((pdata && pdata->vs_pol) || ccdc->bt656)
 		syn_mode |= ISPCCDC_SYN_MODE_VDPOL;
 
+	if (pdata && pdata->fld_pol)
+		syn_mode |= ISPCCDC_SYN_MODE_FLDPOL;
+
 	isp_reg_writel(isp, syn_mode, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SYN_MODE);
 
 	/* The CCDC_CFG.Y8POS bit is used in YCbCr8 input mode only. The
@@ -1023,8 +1027,16 @@ static void ccdc_config_sync_if(struct isp_ccdc_device *ccdc,
 		isp_reg_clr(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_CFG,
 			    ISPCCDC_CFG_Y8POS);
 
-	isp_reg_clr(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_REC656IF,
-		    ISPCCDC_REC656IF_R656ON);
+	/* Enable or disable BT.656 mode, including error correction for the
+	 * synchronization codes.
+	 */
+	if (ccdc->bt656)
+		isp_reg_set(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_REC656IF,
+			    ISPCCDC_REC656IF_R656ON | ISPCCDC_REC656IF_ECCFVH);
+	else
+		isp_reg_clr(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_REC656IF,
+			    ISPCCDC_REC656IF_R656ON | ISPCCDC_REC656IF_ECCFVH);
+
 }
 
 /* CCDC formats descriptions */
@@ -1115,17 +1127,33 @@ static void ccdc_configure(struct isp_ccdc_device *ccdc)
 	unsigned long flags;
 	unsigned int bridge;
 	unsigned int shift;
+	unsigned int nph;
+	unsigned int sph;
 	u32 syn_mode;
 	u32 ccdc_pattern;
 
+	ccdc->bt656 = false;
+	ccdc->fields = 0;
+
 	pad = media_entity_remote_pad(&ccdc->pads[CCDC_PAD_SINK]);
 	sensor = media_entity_to_v4l2_subdev(pad->entity);
-	if (ccdc->input == CCDC_INPUT_PARALLEL)
+	if (ccdc->input == CCDC_INPUT_PARALLEL) {
+		struct v4l2_mbus_config cfg;
+		int ret;
+
+		ret = v4l2_subdev_call(sensor, video, g_mbus_config, &cfg);
+		if (!ret)
+			ccdc->bt656 = cfg.type == V4L2_MBUS_BT656;
+
 		pdata = &((struct isp_v4l2_subdevs_group *)sensor->host_priv)
 			->bus.parallel;
+	}
+
+	/* CCDC_PAD_SINK */
+	format = &ccdc->formats[CCDC_PAD_SINK];
 
 	/* Compute the lane shifter shift value and enable the bridge when the
-	 * input format is YUV.
+	 * input format is a non-BT.656 YUV variant.
 	 */
 	fmt_src.pad = pad->index;
 	fmt_src.which = V4L2_SUBDEV_FORMAT_ACTIVE;
@@ -1134,12 +1162,13 @@ static void ccdc_configure(struct isp_ccdc_device *ccdc)
 		depth_in = fmt_info->width;
 	}
 
-	fmt_info = omap3isp_video_format_info
-		(isp->isp_ccdc.formats[CCDC_PAD_SINK].code);
+	fmt_info = omap3isp_video_format_info(format->code);
 	depth_out = fmt_info->width;
 	shift = depth_in - depth_out;
 
-	if (fmt_info->code == V4L2_MBUS_FMT_YUYV8_2X8)
+	if (ccdc->bt656)
+		bridge = ISPCTRL_PAR_BRIDGE_DISABLE;
+	else if (fmt_info->code == V4L2_MBUS_FMT_YUYV8_2X8)
 		bridge = ISPCTRL_PAR_BRIDGE_LENDIAN;
 	else if (fmt_info->code == V4L2_MBUS_FMT_UYVY8_2X8)
 		bridge = ISPCTRL_PAR_BRIDGE_BENDIAN;
@@ -1148,6 +1177,7 @@ static void ccdc_configure(struct isp_ccdc_device *ccdc)
 
 	omap3isp_configure_bridge(isp, ccdc->input, pdata, shift, bridge);
 
+	/* Configure the sync interface. */
 	ccdc_config_sync_if(ccdc, pdata, depth_out);
 
 	syn_mode = isp_reg_readl(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SYN_MODE);
@@ -1167,9 +1197,6 @@ static void ccdc_configure(struct isp_ccdc_device *ccdc)
 	else
 		syn_mode &= ~ISPCCDC_SYN_MODE_SDR2RSZ;
 
-	/* CCDC_PAD_SINK */
-	format = &ccdc->formats[CCDC_PAD_SINK];
-
 	/* Mosaic filter */
 	switch (format->code) {
 	case V4L2_MBUS_FMT_SRGGB10_1X10:
@@ -1202,16 +1229,40 @@ static void ccdc_configure(struct isp_ccdc_device *ccdc)
 	format = &ccdc->formats[CCDC_PAD_SOURCE_OF];
 	crop = &ccdc->crop;
 
-	isp_reg_writel(isp, (crop->left << ISPCCDC_HORZ_INFO_SPH_SHIFT) |
-		       ((crop->width - 1) << ISPCCDC_HORZ_INFO_NPH_SHIFT),
+	/* The horizontal coordinates are expressed in pixel clock cycles. We
+	 * need two cycles per pixel in BT.656 mode, and one cycle per pixel in
+	 * SYNC mode regardless of the format as the bridge is enabled for YUV
+	 * formats in that case.
+	 */
+	if (ccdc->bt656) {
+		sph = crop->left * 2;
+		nph = crop->width * 2 - 1;
+	} else {
+		sph = crop->left;
+		nph = crop->width - 1;
+	}
+
+	isp_reg_writel(isp, (sph << ISPCCDC_HORZ_INFO_SPH_SHIFT) |
+		       (nph << ISPCCDC_HORZ_INFO_NPH_SHIFT),
 		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_HORZ_INFO);
-	isp_reg_writel(isp, crop->top << ISPCCDC_VERT_START_SLV0_SHIFT,
+	isp_reg_writel(isp, (crop->top << ISPCCDC_VERT_START_SLV0_SHIFT) |
+		       (crop->top << ISPCCDC_VERT_START_SLV1_SHIFT),
 		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_VERT_START);
 	isp_reg_writel(isp, (crop->height - 1)
 			<< ISPCCDC_VERT_LINES_NLV_SHIFT,
 		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_VERT_LINES);
 
-	ccdc_config_outlineoffset(ccdc, ccdc->video_out.bpl_value, 0, 0);
+	ccdc_config_outlineoffset(ccdc, ccdc->video_out.bpl_value,
+				  format->field);
+
+	/* When interleaving fields enable processing of the field input signal.
+	 * This will cause the line output control module to apply the field
+	 * offset to field 1.
+	 */
+	if (ccdc->formats[CCDC_PAD_SINK].field == V4L2_FIELD_ALTERNATE &&
+	    (format->field == V4L2_FIELD_INTERLACED_TB ||
+	     format->field == V4L2_FIELD_INTERLACED_BT))
+		syn_mode |= ISPCCDC_SYN_MODE_FLDMODE;
 
 	/* The CCDC outputs data in UYVY order by default. Swap bytes to get
 	 * YUYV.
@@ -1223,8 +1274,11 @@ static void ccdc_configure(struct isp_ccdc_device *ccdc)
 		isp_reg_clr(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_CFG,
 			    ISPCCDC_CFG_BSWD);
 
-	/* Use PACK8 mode for 1byte per pixel formats. */
-	if (omap3isp_video_format_info(format->code)->width <= 8)
+	/* Use PACK8 mode for 1byte per pixel formats. Check for BT.656 mode
+	 * explicitly as the driver reports 1X16 instead of 2X8 at the OF pad
+	 * for simplicity.
+	 */
+	if (omap3isp_video_format_info(format->code)->width <= 8 || ccdc->bt656)
 		syn_mode |= ISPCCDC_SYN_MODE_PACK8;
 	else
 		syn_mode &= ~ISPCCDC_SYN_MODE_PACK8;
@@ -1232,18 +1286,7 @@ static void ccdc_configure(struct isp_ccdc_device *ccdc)
 	isp_reg_writel(isp, syn_mode, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SYN_MODE);
 
 	/* CCDC_PAD_SOURCE_VP */
-	format = &ccdc->formats[CCDC_PAD_SOURCE_VP];
-
-	isp_reg_writel(isp, (0 << ISPCCDC_FMT_HORZ_FMTSPH_SHIFT) |
-		       (format->width << ISPCCDC_FMT_HORZ_FMTLNH_SHIFT),
-		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_FMT_HORZ);
-	isp_reg_writel(isp, (0 << ISPCCDC_FMT_VERT_FMTSLV_SHIFT) |
-		       ((format->height + 1) << ISPCCDC_FMT_VERT_FMTLNV_SHIFT),
-		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_FMT_VERT);
-
-	isp_reg_writel(isp, (format->width << ISPCCDC_VP_OUT_HORZ_NUM_SHIFT) |
-		       (format->height << ISPCCDC_VP_OUT_VERT_NUM_SHIFT),
-		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_VP_OUT);
+	ccdc_config_vp(ccdc);
 
 	/* Lens shading correction. */
 	spin_lock_irqsave(&ccdc->lsc.req_lock, flags);
@@ -1277,6 +1320,8 @@ static void __ccdc_enable(struct isp_ccdc_device *ccdc, int enable)
 
 	isp_reg_clr_set(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_PCR,
 			ISPCCDC_PCR_EN, enable ? ISPCCDC_PCR_EN : 0);
+
+	ccdc->running = enable;
 }
 
 static int ccdc_disable(struct isp_ccdc_device *ccdc)
@@ -1287,6 +1332,8 @@ static int ccdc_disable(struct isp_ccdc_device *ccdc)
 	spin_lock_irqsave(&ccdc->lock, flags);
 	if (ccdc->state == ISP_PIPELINE_STREAM_CONTINUOUS)
 		ccdc->stopping = CCDC_STOP_REQUEST;
+	if (!ccdc->running)
+		ccdc->stopping = CCDC_STOP_FINISHED;
 	spin_unlock_irqrestore(&ccdc->lock, flags);
 
 	ret = wait_event_timeout(ccdc->wait,
@@ -1369,14 +1416,14 @@ static int ccdc_sbl_wait_idle(struct isp_ccdc_device *ccdc,
 	return -EBUSY;
 }
 
-/* __ccdc_handle_stopping - Handle CCDC and/or LSC stopping sequence
+/* ccdc_handle_stopping - Handle CCDC and/or LSC stopping sequence
  * @ccdc: Pointer to ISP CCDC device.
  * @event: Pointing which event trigger handler
  *
  * Return 1 when the event and stopping request combination is satisfied,
  * zero otherwise.
  */
-static int __ccdc_handle_stopping(struct isp_ccdc_device *ccdc, u32 event)
+static int ccdc_handle_stopping(struct isp_ccdc_device *ccdc, u32 event)
 {
 	int rval = 0;
 
@@ -1458,7 +1505,7 @@ static void ccdc_lsc_isr(struct isp_ccdc_device *ccdc, u32 events)
 	if (ccdc->lsc.state == LSC_STATE_STOPPING)
 		ccdc->lsc.state = LSC_STATE_STOPPED;
 
-	if (__ccdc_handle_stopping(ccdc, CCDC_EVENT_LSC_DONE))
+	if (ccdc_handle_stopping(ccdc, CCDC_EVENT_LSC_DONE))
 		goto done;
 
 	if (ccdc->lsc.state != LSC_STATE_RECONFIG)
@@ -1486,12 +1533,59 @@ done:
 	spin_unlock_irqrestore(&ccdc->lsc.req_lock, flags);
 }
 
+/*
+ * Check whether the CCDC has captured all fields necessary to complete the
+ * buffer.
+ */
+static bool ccdc_has_all_fields(struct isp_ccdc_device *ccdc)
+{
+	struct isp_pipeline *pipe = to_isp_pipeline(&ccdc->subdev.entity);
+	struct isp_device *isp = to_isp_device(ccdc);
+	enum v4l2_field of_field = ccdc->formats[CCDC_PAD_SOURCE_OF].field;
+	enum v4l2_field field;
+
+	/* When the input is progressive fields don't matter. */
+	if (of_field == V4L2_FIELD_NONE)
+		return true;
+
+	/* Read the current field identifier. */
+	field = isp_reg_readl(isp, OMAP3_ISP_IOMEM_CCDC, ISPCCDC_SYN_MODE)
+	      & ISPCCDC_SYN_MODE_FLDSTAT
+	      ? V4L2_FIELD_BOTTOM : V4L2_FIELD_TOP;
+
+	/* When capturing fields in alternate order just store the current field
+	 * identifier in the pipeline.
+	 */
+	if (of_field == V4L2_FIELD_ALTERNATE) {
+		pipe->field = field;
+		return true;
+	}
+
+	/* The format is interlaced. Make sure we've captured both fields. */
+	ccdc->fields |= field == V4L2_FIELD_BOTTOM
+		      ? CCDC_FIELD_BOTTOM : CCDC_FIELD_TOP;
+
+	if (ccdc->fields != CCDC_FIELD_BOTH)
+		return false;
+
+	/* Verify that the field just captured corresponds to the last field
+	 * needed based on the desired field order.
+	 */
+	if ((of_field == V4L2_FIELD_INTERLACED_TB && field == V4L2_FIELD_TOP) ||
+	    (of_field == V4L2_FIELD_INTERLACED_BT && field == V4L2_FIELD_BOTTOM))
+		return false;
+
+	/* The buffer can be completed, reset the fields for the next buffer. */
+	ccdc->fields = 0;
+
+	return true;
+}
+
 static int ccdc_isr_buffer(struct isp_ccdc_device *ccdc)
 {
 	struct isp_pipeline *pipe = to_isp_pipeline(&ccdc->subdev.entity);
 	struct isp_device *isp = to_isp_device(ccdc);
 	struct isp_buffer *buffer;
-	int restart = 0;
 
 	/* The CCDC generates VD0 interrupts even when disabled (the datasheet
 	 * doesn't explicitly state if that's supposed to happen or not, so it
@@ -1500,30 +1594,31 @@ static int ccdc_isr_buffer(struct isp_ccdc_device *ccdc)
 	 * would thus not be enough, we need to handle the situation explicitly.
 	 */
 	if (list_empty(&ccdc->video_out.dmaqueue))
-		goto done;
+		return 0;
 
 	/* We're in continuous mode, and memory writes were disabled due to a
 	 * buffer underrun. Reenable them now that we have a buffer. The buffer
 	 * address has been set in ccdc_video_queue.
 	 */
 	if (ccdc->state == ISP_PIPELINE_STREAM_CONTINUOUS && ccdc->underrun) {
-		restart = 1;
 		ccdc->underrun = 0;
-		goto done;
+		return 1;
 	}
 
+	/* Wait for the CCDC to become idle. */
 	if (ccdc_sbl_wait_idle(ccdc, 1000)) {
 		dev_info(isp->dev, "CCDC won't become idle!\n");
 		isp->crashed |= 1U << ccdc->subdev.entity.id;
 		omap3isp_pipeline_cancel_stream(pipe);
-		goto done;
+		return 0;
 	}
 
+	if (!ccdc_has_all_fields(ccdc))
+		return 1;
+
 	buffer = omap3isp_video_buffer_next(&ccdc->video_out);
-	if (buffer != NULL) {
+	if (buffer != NULL)
 		ccdc_set_outaddr(ccdc, buffer->dma);
-		restart = 1;
-	}
 
 	pipe->state |= ISP_PIPELINE_IDLE_OUTPUT;
 
@@ -1532,8 +1627,7 @@ static int ccdc_isr_buffer(struct isp_ccdc_device *ccdc)
 		omap3isp_pipeline_set_stream(pipe,
 					ISP_PIPELINE_STREAM_SINGLESHOT);
 
-done:
-	return restart;
+	return buffer != NULL;
 }
 
 /*
@@ -1547,11 +1641,38 @@ static void ccdc_vd0_isr(struct isp_ccdc_device *ccdc)
 	unsigned long flags;
 	int restart = 0;
 
+	/* In BT.656 mode the CCDC doesn't generate an HS/VS interrupt. We thus
+	 * need to increment the frame counter here.
+	 */
+	if (ccdc->bt656) {
+		struct isp_pipeline *pipe =
+			to_isp_pipeline(&ccdc->subdev.entity);
+
+		atomic_inc(&pipe->frame_number);
+	}
+
+	/* Emulate a VD1 interrupt for BT.656 mode, as we can't stop the CCDC in
+	 * the VD1 interrupt handler in that mode without risking a CCDC stall
+	 * if a short frame is received.
+	 */
+	if (ccdc->bt656) {
+		spin_lock_irqsave(&ccdc->lock, flags);
+		if (ccdc->state == ISP_PIPELINE_STREAM_CONTINUOUS &&
+		    ccdc->output & CCDC_OUTPUT_MEMORY) {
+			if (ccdc->lsc.state != LSC_STATE_STOPPED)
+				__ccdc_lsc_enable(ccdc, 0);
+			__ccdc_enable(ccdc, 0);
+		}
+		ccdc_handle_stopping(ccdc, CCDC_EVENT_VD1);
+		spin_unlock_irqrestore(&ccdc->lock, flags);
+	}
+
 	if (ccdc->output & CCDC_OUTPUT_MEMORY)
 		restart = ccdc_isr_buffer(ccdc);
 
 	spin_lock_irqsave(&ccdc->lock, flags);
-	if (__ccdc_handle_stopping(ccdc, CCDC_EVENT_VD0)) {
+
+	if (ccdc_handle_stopping(ccdc, CCDC_EVENT_VD0)) {
 		spin_unlock_irqrestore(&ccdc->lock, flags);
 		return;
 	}
@@ -1572,6 +1693,18 @@ static void ccdc_vd1_isr(struct isp_ccdc_device *ccdc)
 {
 	unsigned long flags;
 
+	/* In BT.656 mode the synchronization signals are generated by the CCDC
+	 * from the embedded sync codes. The VD0 and VD1 interrupts are thus
+	 * only triggered when the CCDC is enabled, unlike external sync mode
+	 * where the line counter runs even when the CCDC is stopped. We can't
+	 * disable the CCDC at VD1 time, as no VD0 interrupt would be generated
+	 * for a short frame, which would result in the CCDC being stopped and
+	 * no VD interrupt generated anymore. The CCDC is stopped from the VD0
+	 * interrupt handler instead for BT.656.
+	 */
+	if (ccdc->bt656)
+		return;
+
 	spin_lock_irqsave(&ccdc->lsc.req_lock, flags);
 
 	/*
@@ -1601,7 +1734,7 @@ static void ccdc_vd1_isr(struct isp_ccdc_device *ccdc)
 		break;
 	}
 
-	if (__ccdc_handle_stopping(ccdc, CCDC_EVENT_VD1))
+	if (ccdc_handle_stopping(ccdc, CCDC_EVENT_VD1))
 		goto done;
 
 	if (ccdc->lsc.request == NULL)
@@ -1656,6 +1789,8 @@ int omap3isp_ccdc_isr(struct isp_ccdc_device *ccdc, u32 events)
 static int ccdc_video_queue(struct isp_video *video, struct isp_buffer *buffer)
 {
 	struct isp_ccdc_device *ccdc = &video->isp->isp_ccdc;
+	unsigned long flags;
+	bool restart = false;
 
 	if (!(ccdc->output & CCDC_OUTPUT_MEMORY))
 		return -ENODEV;
@@ -1664,9 +1799,20 @@ static int ccdc_video_queue(struct isp_video *video, struct isp_buffer *buffer)
 
 	/* We now have a buffer queued on the output, restart the pipeline
 	 * on the next CCDC interrupt if running in continuous mode (or when
-	 * starting the stream).
+	 * starting the stream) in external sync mode, or immediately in BT.656
+	 * sync mode as no CCDC interrupt is generated when the CCDC is stopped
+	 * in that case.
 	 */
-	ccdc->underrun = 1;
+	spin_lock_irqsave(&ccdc->lock, flags);
+	if (ccdc->state == ISP_PIPELINE_STREAM_CONTINUOUS && !ccdc->running &&
+	    ccdc->bt656)
+		restart = true;
+	else
+		ccdc->underrun = 1;
+	spin_unlock_irqrestore(&ccdc->lock, flags);
+
+	if (restart)
+		ccdc_enable(ccdc);
 
 	return 0;
 }
@@ -1753,11 +1899,6 @@ static int ccdc_set_stream(struct v4l2_subdev *sd, int enable)
 
 		ccdc_configure(ccdc);
 
-		/* TODO: Don't configure the video port if all of its output
-		 * links are inactive.
-		 */
-		ccdc_config_vp(ccdc);
-		ccdc_enable_vp(ccdc, 1);
 		ccdc_print_status(ccdc);
 	}
 
@@ -1830,6 +1971,7 @@ ccdc_try_format(struct isp_ccdc_device *ccdc, struct v4l2_subdev_fh *fh,
 	unsigned int width = fmt->width;
 	unsigned int height = fmt->height;
 	struct v4l2_rect *crop;
+	enum v4l2_field field;
 	unsigned int i;
 
 	switch (pad) {
@@ -1846,14 +1988,24 @@ ccdc_try_format(struct isp_ccdc_device *ccdc, struct v4l2_subdev_fh *fh,
 		/* Clamp the input size. */
 		fmt->width = clamp_t(u32, width, 32, 4096);
 		fmt->height = clamp_t(u32, height, 32, 4096);
+
+		/* Default to progressive field order. */
+		if (fmt->field == V4L2_FIELD_ANY)
+			fmt->field = V4L2_FIELD_NONE;
+
 		break;
 
 	case CCDC_PAD_SOURCE_OF:
 		pixelcode = fmt->code;
+		field = fmt->field;
 		*fmt = *__ccdc_get_format(ccdc, fh, CCDC_PAD_SINK, which);
 
-		/* YUV formats are converted from 2X8 to 1X16 by the bridge and
-		 * can be byte-swapped.
+		/* In SYNC mode the bridge converts YUV formats from 2X8 to
+		 * 1X16. In BT.656 no such conversion occurs. As we don't know
+		 * at this point whether the source will use SYNC or BT.656 mode
+		 * let's pretend the conversion always occurs. The CCDC will be
+		 * configured to pack bytes in BT.656, hiding the inaccuracy.
+		 * In all cases bytes can be swapped.
 		 */
 		if (fmt->code == V4L2_MBUS_FMT_YUYV8_2X8 ||
 		    fmt->code == V4L2_MBUS_FMT_UYVY8_2X8) {
@@ -1874,6 +2026,17 @@ ccdc_try_format(struct isp_ccdc_device *ccdc, struct v4l2_subdev_fh *fh,
 		crop = __ccdc_get_crop(ccdc, fh, which);
 		fmt->width = crop->width;
 		fmt->height = crop->height;
+
+		/* When input format is interlaced with alternating fields the
+		 * CCDC can interleave the fields.
+		 */
+		if (fmt->field == V4L2_FIELD_ALTERNATE &&
+		    (field == V4L2_FIELD_INTERLACED_TB ||
+		     field == V4L2_FIELD_INTERLACED_BT)) {
+			fmt->field = field;
+			fmt->height *= 2;
+		}
+
 		break;
 
 	case CCDC_PAD_SOURCE_VP:
@@ -1901,7 +2064,6 @@ ccdc_try_format(struct isp_ccdc_device *ccdc, struct v4l2_subdev_fh *fh,
 	 * stored on 2 bytes.
 	 */
 	fmt->colorspace = V4L2_COLORSPACE_SRGB;
-	fmt->field = V4L2_FIELD_NONE;
 }
 
 /*
diff --git a/drivers/media/platform/omap3isp/ispccdc.h b/drivers/media/platform/omap3isp/ispccdc.h
index f65061602c71..3440a7097940 100644
--- a/drivers/media/platform/omap3isp/ispccdc.h
+++ b/drivers/media/platform/omap3isp/ispccdc.h
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_CCDC_H
@@ -103,6 +93,10 @@ struct ispccdc_lsc {
 #define CCDC_PAD_SOURCE_VP		2
 #define CCDC_PADS_NUM			3
 
+#define CCDC_FIELD_TOP			1
+#define CCDC_FIELD_BOTTOM		2
+#define CCDC_FIELD_BOTH			3
+
 /*
  * struct isp_ccdc_device - Structure for the CCDC module to store its own
  *			    information
@@ -123,11 +117,14 @@ struct ispccdc_lsc {
  * @lsc: Lens shading compensation configuration
  * @update: Bitmask of controls to update during the next interrupt
  * @shadow_update: Controls update in progress by userspace
+ * @bt656: Whether the input interface uses BT.656 synchronization
+ * @fields: The fields (CCDC_FIELD_*) stored in the current buffer
  * @underrun: A buffer underrun occurred and a new buffer has been queued
  * @state: Streaming state
  * @lock: Serializes shadow_update with interrupt handler
  * @wait: Wait queue used to stop the module
  * @stopping: Stopping state
+ * @running: Is the CCDC hardware running
  * @ioctl_lock: Serializes ioctl calls and LSC requests freeing
  */
 struct isp_ccdc_device {
@@ -151,11 +148,15 @@ struct isp_ccdc_device {
 	unsigned int update;
 	unsigned int shadow_update;
 
+	bool bt656;
+	unsigned int fields;
+
 	unsigned int underrun:1;
 	enum isp_pipeline_stream_state state;
 	spinlock_t lock;
 	wait_queue_head_t wait;
 	unsigned int stopping;
+	bool running;
 	struct mutex ioctl_lock;
 };
 
diff --git a/drivers/media/platform/omap3isp/ispccp2.c b/drivers/media/platform/omap3isp/ispccp2.c
index f3801db9095c..9cb49b3c04bd 100644
--- a/drivers/media/platform/omap3isp/ispccp2.c
+++ b/drivers/media/platform/omap3isp/ispccp2.c
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #include <linux/delay.h>
diff --git a/drivers/media/platform/omap3isp/ispccp2.h b/drivers/media/platform/omap3isp/ispccp2.h
index 76d65f4576ef..4662bffa79e3 100644
--- a/drivers/media/platform/omap3isp/ispccp2.h
+++ b/drivers/media/platform/omap3isp/ispccp2.h
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_CCP2_H
diff --git a/drivers/media/platform/omap3isp/ispcsi2.c b/drivers/media/platform/omap3isp/ispcsi2.c
index 5a2e47e58b84..6530b255f103 100644
--- a/drivers/media/platform/omap3isp/ispcsi2.c
+++ b/drivers/media/platform/omap3isp/ispcsi2.c
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 #include <linux/delay.h>
 #include <media/v4l2-common.h>
diff --git a/drivers/media/platform/omap3isp/ispcsi2.h b/drivers/media/platform/omap3isp/ispcsi2.h
index c57729b7e86e..453ed62fe394 100644
--- a/drivers/media/platform/omap3isp/ispcsi2.h
+++ b/drivers/media/platform/omap3isp/ispcsi2.h
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_CSI2_H
diff --git a/drivers/media/platform/omap3isp/ispcsiphy.c b/drivers/media/platform/omap3isp/ispcsiphy.c
index c09de32f986a..e033f2237a72 100644
--- a/drivers/media/platform/omap3isp/ispcsiphy.c
+++ b/drivers/media/platform/omap3isp/ispcsiphy.c
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #include <linux/delay.h>
diff --git a/drivers/media/platform/omap3isp/ispcsiphy.h b/drivers/media/platform/omap3isp/ispcsiphy.h
index 14551fd77697..e17c88beab92 100644
--- a/drivers/media/platform/omap3isp/ispcsiphy.h
+++ b/drivers/media/platform/omap3isp/ispcsiphy.h
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_CSI_PHY_H
diff --git a/drivers/media/platform/omap3isp/isph3a.h b/drivers/media/platform/omap3isp/isph3a.h
index fb09fd4ca755..e5b28d0f3b0f 100644
--- a/drivers/media/platform/omap3isp/isph3a.h
+++ b/drivers/media/platform/omap3isp/isph3a.h
@@ -13,16 +13,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_H3A_H
diff --git a/drivers/media/platform/omap3isp/isph3a_aewb.c b/drivers/media/platform/omap3isp/isph3a_aewb.c
index d6811ce263eb..b208c5417146 100644
--- a/drivers/media/platform/omap3isp/isph3a_aewb.c
+++ b/drivers/media/platform/omap3isp/isph3a_aewb.c
@@ -13,16 +13,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #include <linux/slab.h>
diff --git a/drivers/media/platform/omap3isp/isph3a_af.c b/drivers/media/platform/omap3isp/isph3a_af.c
index 6fc960cd30f5..8a83e195f3e3 100644
--- a/drivers/media/platform/omap3isp/isph3a_af.c
+++ b/drivers/media/platform/omap3isp/isph3a_af.c
@@ -13,16 +13,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 /* Linux specific include files */
diff --git a/drivers/media/platform/omap3isp/isphist.c b/drivers/media/platform/omap3isp/isphist.c
index 06a5f8164eaa..ce822c34c843 100644
--- a/drivers/media/platform/omap3isp/isphist.c
+++ b/drivers/media/platform/omap3isp/isphist.c
@@ -13,16 +13,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #include <linux/delay.h>
diff --git a/drivers/media/platform/omap3isp/isphist.h b/drivers/media/platform/omap3isp/isphist.h
index 0b2a38ec94c4..3b5415517dcd 100644
--- a/drivers/media/platform/omap3isp/isphist.h
+++ b/drivers/media/platform/omap3isp/isphist.h
@@ -13,16 +13,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_HIST_H
diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c
index 720809b07e75..605f57ef0a49 100644
--- a/drivers/media/platform/omap3isp/isppreview.c
+++ b/drivers/media/platform/omap3isp/isppreview.c
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #include <linux/device.h>
diff --git a/drivers/media/platform/omap3isp/isppreview.h b/drivers/media/platform/omap3isp/isppreview.h
index f66923407f8c..16fdc03a3d43 100644
--- a/drivers/media/platform/omap3isp/isppreview.h
+++ b/drivers/media/platform/omap3isp/isppreview.h
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_PREVIEW_H
diff --git a/drivers/media/platform/omap3isp/ispreg.h b/drivers/media/platform/omap3isp/ispreg.h
index b7d90e6fb01d..b5ea8da0b904 100644
--- a/drivers/media/platform/omap3isp/ispreg.h
+++ b/drivers/media/platform/omap3isp/ispreg.h
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_REG_H
@@ -740,17 +730,13 @@
 
 #define ISPCCDC_HSIZE_OFF_SHIFT			0
 
-#define ISPCCDC_SDOFST_FINV			(1 << 14)
-#define ISPCCDC_SDOFST_FOFST_1L			0
-#define ISPCCDC_SDOFST_FOFST_4L			(3 << 12)
+#define ISPCCDC_SDOFST_FIINV			(1 << 14)
+#define ISPCCDC_SDOFST_FOFST_SHIFT		12
+#define ISPCCDC_SDOFST_FOFST_MASK		(3 << 12)
 #define ISPCCDC_SDOFST_LOFST3_SHIFT		0
 #define ISPCCDC_SDOFST_LOFST2_SHIFT		3
 #define ISPCCDC_SDOFST_LOFST1_SHIFT		6
 #define ISPCCDC_SDOFST_LOFST0_SHIFT		9
-#define EVENEVEN				1
-#define ODDEVEN					2
-#define EVENODD					3
-#define ODDODD					4
 
 #define ISPCCDC_CLAMP_OBGAIN_SHIFT		0
 #define ISPCCDC_CLAMP_OBST_SHIFT		10
diff --git a/drivers/media/platform/omap3isp/ispresizer.c b/drivers/media/platform/omap3isp/ispresizer.c
index 6f077c2377db..05d1ace57451 100644
--- a/drivers/media/platform/omap3isp/ispresizer.c
+++ b/drivers/media/platform/omap3isp/ispresizer.c
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #include <linux/device.h>
@@ -239,7 +229,7 @@ static void resizer_set_phase(struct isp_res_device *res, u32 h_phase,
 			      u32 v_phase)
 {
 	struct isp_device *isp = to_isp_device(res);
-	u32 rgval = 0;
+	u32 rgval;
 
 	rgval = isp_reg_readl(isp, OMAP3_ISP_IOMEM_RESZ, ISPRSZ_CNT) &
 	      ~(ISPRSZ_CNT_HSTPH_MASK | ISPRSZ_CNT_VSTPH_MASK);
@@ -275,7 +265,7 @@ static void resizer_set_luma(struct isp_res_device *res,
 			     struct resizer_luma_yenh *luma)
 {
 	struct isp_device *isp = to_isp_device(res);
-	u32 rgval = 0;
+	u32 rgval;
 
 	rgval  = (luma->algo << ISPRSZ_YENH_ALGO_SHIFT)
 		  & ISPRSZ_YENH_ALGO_MASK;
@@ -322,7 +312,7 @@ static void resizer_set_ratio(struct isp_res_device *res,
 {
 	struct isp_device *isp = to_isp_device(res);
 	const u16 *h_filter, *v_filter;
-	u32 rgval = 0;
+	u32 rgval;
 
 	rgval = isp_reg_readl(isp, OMAP3_ISP_IOMEM_RESZ, ISPRSZ_CNT) &
 			      ~(ISPRSZ_CNT_HRSZ_MASK | ISPRSZ_CNT_VRSZ_MASK);
@@ -365,9 +355,8 @@ static void resizer_set_output_size(struct isp_res_device *res,
 				    u32 width, u32 height)
 {
 	struct isp_device *isp = to_isp_device(res);
-	u32 rgval = 0;
+	u32 rgval;
 
-	dev_dbg(isp->dev, "Output size[w/h]: %dx%d\n", width, height);
 	rgval  = (width << ISPRSZ_OUT_SIZE_HORZ_SHIFT)
 		 & ISPRSZ_OUT_SIZE_HORZ_MASK;
 	rgval |= (height << ISPRSZ_OUT_SIZE_VERT_SHIFT)
@@ -409,7 +398,7 @@ static void resizer_set_output_offset(struct isp_res_device *res, u32 offset)
 static void resizer_set_start(struct isp_res_device *res, u32 left, u32 top)
 {
 	struct isp_device *isp = to_isp_device(res);
-	u32 rgval = 0;
+	u32 rgval;
 
 	rgval = (left << ISPRSZ_IN_START_HORZ_ST_SHIFT)
 		& ISPRSZ_IN_START_HORZ_ST_MASK;
@@ -429,9 +418,7 @@ static void resizer_set_input_size(struct isp_res_device *res,
 				   u32 width, u32 height)
 {
 	struct isp_device *isp = to_isp_device(res);
-	u32 rgval = 0;
-
-	dev_dbg(isp->dev, "Input size[w/h]: %dx%d\n", width, height);
+	u32 rgval;
 
 	rgval = (width << ISPRSZ_IN_SIZE_HORZ_SHIFT)
 		& ISPRSZ_IN_SIZE_HORZ_MASK;
@@ -1075,10 +1062,13 @@ static void resizer_isr_buffer(struct isp_res_device *res)
 void omap3isp_resizer_isr(struct isp_res_device *res)
 {
 	struct v4l2_mbus_framefmt *informat, *outformat;
+	unsigned long flags;
 
 	if (omap3isp_module_sync_is_stopping(&res->wait, &res->stopping))
 		return;
 
+	spin_lock_irqsave(&res->lock, flags);
+
 	if (res->applycrop) {
 		outformat = __resizer_get_format(res, NULL, RESZ_PAD_SOURCE,
 					      V4L2_SUBDEV_FORMAT_ACTIVE);
@@ -1088,6 +1078,8 @@ void omap3isp_resizer_isr(struct isp_res_device *res)
 		res->applycrop = 0;
 	}
 
+	spin_unlock_irqrestore(&res->lock, flags);
+
 	resizer_isr_buffer(res);
 }
 
@@ -1290,8 +1282,10 @@ static int resizer_set_selection(struct v4l2_subdev *sd,
 {
 	struct isp_res_device *res = v4l2_get_subdevdata(sd);
 	struct isp_device *isp = to_isp_device(res);
-	struct v4l2_mbus_framefmt *format_sink, *format_source;
+	const struct v4l2_mbus_framefmt *format_sink;
+	struct v4l2_mbus_framefmt format_source;
 	struct resizer_ratio ratio;
+	unsigned long flags;
 
 	if (sel->target != V4L2_SEL_TGT_CROP ||
 	    sel->pad != RESZ_PAD_SINK)
@@ -1299,16 +1293,14 @@ static int resizer_set_selection(struct v4l2_subdev *sd,
 
 	format_sink = __resizer_get_format(res, fh, RESZ_PAD_SINK,
 					   sel->which);
-	format_source = __resizer_get_format(res, fh, RESZ_PAD_SOURCE,
-					     sel->which);
-
-	dev_dbg(isp->dev, "%s: L=%d,T=%d,W=%d,H=%d,which=%d\n", __func__,
-		sel->r.left, sel->r.top, sel->r.width, sel->r.height,
-		sel->which);
+	format_source = *__resizer_get_format(res, fh, RESZ_PAD_SOURCE,
+					      sel->which);
 
-	dev_dbg(isp->dev, "%s: input=%dx%d, output=%dx%d\n", __func__,
+	dev_dbg(isp->dev, "%s(%s): req %ux%u -> (%d,%d)/%ux%u -> %ux%u\n",
+		__func__, sel->which == V4L2_SUBDEV_FORMAT_TRY ? "try" : "act",
 		format_sink->width, format_sink->height,
-		format_source->width, format_source->height);
+		sel->r.left, sel->r.top, sel->r.width, sel->r.height,
+		format_source.width, format_source.height);
 
 	/* Clamp the crop rectangle to the bounds, and then mangle it further to
 	 * fulfill the TRM equations. Store the clamped but otherwise unmangled
@@ -1318,23 +1310,39 @@ static int resizer_set_selection(struct v4l2_subdev *sd,
 	 * smaller input crop rectangle every time the output size is set if we
 	 * stored the mangled rectangle.
 	 */
-	resizer_try_crop(format_sink, format_source, &sel->r);
+	resizer_try_crop(format_sink, &format_source, &sel->r);
 	*__resizer_get_crop(res, fh, sel->which) = sel->r;
-	resizer_calc_ratios(res, &sel->r, format_source, &ratio);
+	resizer_calc_ratios(res, &sel->r, &format_source, &ratio);
 
-	if (sel->which == V4L2_SUBDEV_FORMAT_TRY)
+	dev_dbg(isp->dev, "%s(%s): got %ux%u -> (%d,%d)/%ux%u -> %ux%u\n",
+		__func__, sel->which == V4L2_SUBDEV_FORMAT_TRY ? "try" : "act",
+		format_sink->width, format_sink->height,
+		sel->r.left, sel->r.top, sel->r.width, sel->r.height,
+		format_source.width, format_source.height);
+
+	if (sel->which == V4L2_SUBDEV_FORMAT_TRY) {
+		*__resizer_get_format(res, fh, RESZ_PAD_SOURCE, sel->which) =
+			format_source;
 		return 0;
+	}
+
+	/* Update the source format, resizing ratios and crop rectangle. If
+	 * streaming is on the IRQ handler will reprogram the resizer after the
+	 * current frame. We thus we need to protect against race conditions.
+	 */
+	spin_lock_irqsave(&res->lock, flags);
+
+	*__resizer_get_format(res, fh, RESZ_PAD_SOURCE, sel->which) =
+		format_source;
 
 	res->ratio = ratio;
 	res->crop.active = sel->r;
 
-	/*
-	 * set_selection can be called while streaming is on. In this case the
-	 * crop values will be set in the next IRQ.
-	 */
 	if (res->state != ISP_PIPELINE_STREAM_STOPPED)
 		res->applycrop = 1;
 
+	spin_unlock_irqrestore(&res->lock, flags);
+
 	return 0;
 }
 
@@ -1781,6 +1789,8 @@ int omap3isp_resizer_init(struct isp_device *isp)
 
 	init_waitqueue_head(&res->wait);
 	atomic_set(&res->stopping, 0);
+	spin_lock_init(&res->lock);
+
 	return resizer_init_entities(res);
 }
 
diff --git a/drivers/media/platform/omap3isp/ispresizer.h b/drivers/media/platform/omap3isp/ispresizer.h
index 9b01e9047c15..5414542912e2 100644
--- a/drivers/media/platform/omap3isp/ispresizer.h
+++ b/drivers/media/platform/omap3isp/ispresizer.h
@@ -12,21 +12,12 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_RESIZER_H
 #define OMAP3_ISP_RESIZER_H
 
+#include <linux/spinlock.h>
 #include <linux/types.h>
 
 /*
@@ -96,6 +87,7 @@ enum resizer_input_entity {
 
 /*
  * struct isp_res_device - OMAP3 ISP resizer module
+ * @lock: Protects formats and crop rectangles between set_selection and IRQ
  * @crop.request: Crop rectangle requested by the user
  * @crop.active: Active crop rectangle (based on hardware requirements)
  */
@@ -116,6 +108,7 @@ struct isp_res_device {
 	enum isp_pipeline_stream_state state;
 	wait_queue_head_t wait;
 	atomic_t stopping;
+	spinlock_t lock;
 
 	struct {
 		struct v4l2_rect request;
diff --git a/drivers/media/platform/omap3isp/ispstat.c b/drivers/media/platform/omap3isp/ispstat.c
index e6cbc1eaf4ca..a94e8340508f 100644
--- a/drivers/media/platform/omap3isp/ispstat.c
+++ b/drivers/media/platform/omap3isp/ispstat.c
@@ -13,16 +13,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #include <linux/dma-mapping.h>
diff --git a/drivers/media/platform/omap3isp/ispstat.h b/drivers/media/platform/omap3isp/ispstat.h
index 58d6ac7cb664..b32b29677e2c 100644
--- a/drivers/media/platform/omap3isp/ispstat.h
+++ b/drivers/media/platform/omap3isp/ispstat.h
@@ -13,16 +13,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_STAT_H
diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c
index e36bac26476c..bc38c88c7bd9 100644
--- a/drivers/media/platform/omap3isp/ispvideo.c
+++ b/drivers/media/platform/omap3isp/ispvideo.c
@@ -11,16 +11,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #include <asm/cacheflush.h>
@@ -319,10 +309,11 @@ isp_video_check_format(struct isp_video *video, struct isp_video_fh *vfh)
 	    vfh->format.fmt.pix.height != format.fmt.pix.height ||
 	    vfh->format.fmt.pix.width != format.fmt.pix.width ||
 	    vfh->format.fmt.pix.bytesperline != format.fmt.pix.bytesperline ||
-	    vfh->format.fmt.pix.sizeimage != format.fmt.pix.sizeimage)
+	    vfh->format.fmt.pix.sizeimage != format.fmt.pix.sizeimage ||
+	    vfh->format.fmt.pix.field != format.fmt.pix.field)
 		return -EINVAL;
 
-	return ret;
+	return 0;
 }
 
 /* -----------------------------------------------------------------------------
@@ -491,6 +482,11 @@ struct isp_buffer *omap3isp_video_buffer_next(struct isp_video *video)
 	else
 		buf->vb.v4l2_buf.sequence = atomic_read(&pipe->frame_number);
 
+	if (pipe->field != V4L2_FIELD_NONE)
+		buf->vb.v4l2_buf.sequence /= 2;
+
+	buf->vb.v4l2_buf.field = pipe->field;
+
 	/* Report pipeline errors to userspace on the capture device side. */
 	if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && pipe->error) {
 		state = VB2_BUF_STATE_ERROR;
@@ -641,7 +637,40 @@ isp_video_set_format(struct file *file, void *fh, struct v4l2_format *format)
 	if (format->type != video->type)
 		return -EINVAL;
 
-	mutex_lock(&video->mutex);
+	/* Replace unsupported field orders with sane defaults. */
+	switch (format->fmt.pix.field) {
+	case V4L2_FIELD_NONE:
+		/* Progressive is supported everywhere. */
+		break;
+	case V4L2_FIELD_ALTERNATE:
+		/* ALTERNATE is not supported on output nodes. */
+		if (video->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
+			format->fmt.pix.field = V4L2_FIELD_NONE;
+		break;
+	case V4L2_FIELD_INTERLACED:
+		/* The ISP has no concept of video standard, select the
+		 * top-bottom order when the unqualified interlaced order is
+		 * requested.
+		 */
+		format->fmt.pix.field = V4L2_FIELD_INTERLACED_TB;
+		/* Fall-through */
+	case V4L2_FIELD_INTERLACED_TB:
+	case V4L2_FIELD_INTERLACED_BT:
+		/* Interlaced orders are only supported at the CCDC output. */
+		if (video != &video->isp->isp_ccdc.video_out)
+			format->fmt.pix.field = V4L2_FIELD_NONE;
+		break;
+	case V4L2_FIELD_TOP:
+	case V4L2_FIELD_BOTTOM:
+	case V4L2_FIELD_SEQ_TB:
+	case V4L2_FIELD_SEQ_BT:
+	default:
+		/* All other field orders are currently unsupported, default to
+		 * progressive.
+		 */
+		format->fmt.pix.field = V4L2_FIELD_NONE;
+		break;
+	}
 
 	/* Fill the bytesperline and sizeimage fields by converting to media bus
 	 * format and back to pixel format.
@@ -649,9 +678,10 @@ isp_video_set_format(struct file *file, void *fh, struct v4l2_format *format)
 	isp_video_pix_to_mbus(&format->fmt.pix, &fmt);
 	isp_video_mbus_to_pix(video, &fmt, &format->fmt.pix);
 
+	mutex_lock(&video->mutex);
 	vfh->format = *format;
-
 	mutex_unlock(&video->mutex);
+
 	return 0;
 }
 
@@ -1039,6 +1069,7 @@ isp_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 	video->queue = &vfh->queue;
 	INIT_LIST_HEAD(&video->dmaqueue);
 	atomic_set(&pipe->frame_number, -1);
+	pipe->field = vfh->format.fmt.pix.field;
 
 	mutex_lock(&video->queue_lock);
 	ret = vb2_streamon(&vfh->queue, type);
diff --git a/drivers/media/platform/omap3isp/ispvideo.h b/drivers/media/platform/omap3isp/ispvideo.h
index 7d2e82122ecd..0b7efedc3da9 100644
--- a/drivers/media/platform/omap3isp/ispvideo.h
+++ b/drivers/media/platform/omap3isp/ispvideo.h
@@ -11,16 +11,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 #ifndef OMAP3_ISP_VIDEO_H
@@ -88,6 +78,7 @@ enum isp_pipeline_state {
 
 /*
  * struct isp_pipeline - An ISP hardware pipeline
+ * @field: The field being processed by the pipeline
  * @error: A hardware error occurred during capture
  * @entities: Bitmask of entities in the pipeline (indexed by entity ID)
  */
@@ -101,6 +92,7 @@ struct isp_pipeline {
 	u32 entities;
 	unsigned long l3_ick;
 	unsigned int max_rate;
+	enum v4l2_field field;
 	atomic_t frame_number;
 	bool do_propagation; /* of frame number */
 	bool error;
diff --git a/drivers/media/platform/omap3isp/luma_enhance_table.h b/drivers/media/platform/omap3isp/luma_enhance_table.h
index 098b45e2280f..81c5b1566469 100644
--- a/drivers/media/platform/omap3isp/luma_enhance_table.h
+++ b/drivers/media/platform/omap3isp/luma_enhance_table.h
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 1047552, 1047552, 1047552, 1047552, 1047552, 1047552, 1047552, 1047552,
diff --git a/drivers/media/platform/omap3isp/noise_filter_table.h b/drivers/media/platform/omap3isp/noise_filter_table.h
index d50451a4a242..5073f9847937 100644
--- a/drivers/media/platform/omap3isp/noise_filter_table.h
+++ b/drivers/media/platform/omap3isp/noise_filter_table.h
@@ -12,16 +12,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
  */
 
 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
diff --git a/drivers/media/platform/s3c-camif/camif-capture.c b/drivers/media/platform/s3c-camif/camif-capture.c
index f33641384e15..4f81b4c9d113 100644
--- a/drivers/media/platform/s3c-camif/camif-capture.c
+++ b/drivers/media/platform/s3c-camif/camif-capture.c
@@ -280,8 +280,8 @@ static int camif_prepare_addr(struct camif_vp *vp, struct vb2_buffer *vb,
 		return -EINVAL;
 	}
 
-	pr_debug("DMA address: y: %#x  cb: %#x cr: %#x\n",
-		 paddr->y, paddr->cb, paddr->cr);
+	pr_debug("DMA address: y: %pad  cb: %pad cr: %pad\n",
+		 &paddr->y, &paddr->cb, &paddr->cr);
 
 	return 0;
 }
diff --git a/drivers/media/platform/s3c-camif/camif-regs.c b/drivers/media/platform/s3c-camif/camif-regs.c
index ebf5b184cce4..6e0c9988a191 100644
--- a/drivers/media/platform/s3c-camif/camif-regs.c
+++ b/drivers/media/platform/s3c-camif/camif-regs.c
@@ -214,8 +214,8 @@ void camif_hw_set_output_addr(struct camif_vp *vp,
 								paddr->cr);
 	}
 
-	pr_debug("dst_buf[%d]: %#X, cb: %#X, cr: %#X\n",
-		 i, paddr->y, paddr->cb, paddr->cr);
+	pr_debug("dst_buf[%d]: %pad, cb: %pad, cr: %pad\n",
+		 i, &paddr->y, &paddr->cb, &paddr->cr);
 }
 
 static void camif_hw_set_out_dma_size(struct camif_vp *vp)
diff --git a/drivers/media/platform/s5p-g2d/g2d.c b/drivers/media/platform/s5p-g2d/g2d.c
index 357af1ebaeda..d79e214ce8ce 100644
--- a/drivers/media/platform/s5p-g2d/g2d.c
+++ b/drivers/media/platform/s5p-g2d/g2d.c
@@ -490,14 +490,13 @@ static void job_abort(void *prv)
 {
 	struct g2d_ctx *ctx = prv;
 	struct g2d_dev *dev = ctx->dev;
-	int ret;
 
 	if (dev->curr == NULL) /* No job currently running */
 		return;
 
-	ret = wait_event_timeout(dev->irq_queue,
-		dev->curr == NULL,
-		msecs_to_jiffies(G2D_TIMEOUT));
+	wait_event_timeout(dev->irq_queue,
+			   dev->curr == NULL,
+			   msecs_to_jiffies(G2D_TIMEOUT));
 }
 
 static void device_run(void *prv)
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c
index e66acbc2a82d..e525a7c8d885 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-core.c
+++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c
@@ -729,7 +729,7 @@ static inline void exynos4_jpeg_set_qtbl_chr(void __iomem *regs, int quality)
 			     ARRAY_SIZE(qtbl_chrominance[quality]));
 }
 
-void exynos4_jpeg_set_huff_tbl(void __iomem *base)
+static void exynos4_jpeg_set_huff_tbl(void __iomem *base)
 {
 	exynos4_jpeg_set_tbl(base, hdctbl0, EXYNOS4_HUFF_TBL_HDCLL,
 							ARRAY_SIZE(hdctbl0));
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos3250.c b/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos3250.c
index d26e1f846553..e8c2cad93962 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos3250.c
+++ b/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos3250.c
@@ -233,6 +233,7 @@ void exynos3250_jpeg_set_x(void __iomem *regs, unsigned int x)
 	writel(reg, regs + EXYNOS3250_JPGX);
 }
 
+#if 0	/* Currently unused */
 unsigned int exynos3250_jpeg_get_y(void __iomem *regs)
 {
 	return readl(regs + EXYNOS3250_JPGY);
@@ -242,6 +243,7 @@ unsigned int exynos3250_jpeg_get_x(void __iomem *regs)
 {
 	return readl(regs + EXYNOS3250_JPGX);
 }
+#endif
 
 void exynos3250_jpeg_interrupts_enable(void __iomem *regs)
 {
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos4.c b/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos4.c
index da8d6a1a984f..ab6d6f43c96f 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos4.c
+++ b/drivers/media/platform/s5p-jpeg/jpeg-hw-exynos4.c
@@ -23,7 +23,7 @@ void exynos4_jpeg_sw_reset(void __iomem *base)
 	reg = readl(base + EXYNOS4_JPEG_CNTL_REG);
 	writel(reg & ~EXYNOS4_SOFT_RESET_HI, base + EXYNOS4_JPEG_CNTL_REG);
 
-	ndelay(100000);
+	udelay(100);
 
 	writel(reg | EXYNOS4_SOFT_RESET_HI, base + EXYNOS4_JPEG_CNTL_REG);
 }
@@ -151,9 +151,6 @@ void exynos4_jpeg_set_enc_out_fmt(void __iomem *base, unsigned int out_fmt)
 
 void exynos4_jpeg_set_interrupt(void __iomem *base)
 {
-	unsigned int reg;
-
-	reg = readl(base + EXYNOS4_INT_EN_REG) & ~EXYNOS4_INT_EN_MASK;
 	writel(EXYNOS4_INT_EN_ALL, base + EXYNOS4_INT_EN_REG);
 }
 
@@ -185,7 +182,7 @@ void exynos4_jpeg_set_huf_table_enable(void __iomem *base, int value)
 		writel(reg | EXYNOS4_HUF_TBL_EN,
 					base + EXYNOS4_JPEG_CNTL_REG);
 	else
-		writel(reg | ~EXYNOS4_HUF_TBL_EN,
+		writel(reg & ~EXYNOS4_HUF_TBL_EN,
 					base + EXYNOS4_JPEG_CNTL_REG);
 }
 
@@ -196,9 +193,9 @@ void exynos4_jpeg_set_sys_int_enable(void __iomem *base, int value)
 	reg = readl(base + EXYNOS4_JPEG_CNTL_REG) & ~(EXYNOS4_SYS_INT_EN);
 
 	if (value == 1)
-		writel(EXYNOS4_SYS_INT_EN, base + EXYNOS4_JPEG_CNTL_REG);
+		writel(reg | EXYNOS4_SYS_INT_EN, base + EXYNOS4_JPEG_CNTL_REG);
 	else
-		writel(~EXYNOS4_SYS_INT_EN, base + EXYNOS4_JPEG_CNTL_REG);
+		writel(reg & ~EXYNOS4_SYS_INT_EN, base + EXYNOS4_JPEG_CNTL_REG);
 }
 
 void exynos4_jpeg_set_stream_buf_address(void __iomem *base,
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.c b/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.c
index 52407d790726..e3b8e67e005f 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.c
+++ b/drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.c
@@ -324,11 +324,9 @@ int s5p_jpeg_stream_stat_ok(void __iomem *regs)
 
 void s5p_jpeg_clear_int(void __iomem *regs)
 {
-	unsigned long reg;
-
-	reg = readl(regs + S5P_JPGINTST);
+	readl(regs + S5P_JPGINTST);
 	writel(S5P_INT_RELEASE, regs + S5P_JPGCOM);
-	reg = readl(regs + S5P_JPGOPR);
+	readl(regs + S5P_JPGOPR);
 }
 
 unsigned int s5p_jpeg_compressed_size(void __iomem *regs)
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index d35b0418ab37..165bc86c5962 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -37,8 +37,8 @@
 #define S5P_MFC_DEC_NAME	"s5p-mfc-dec"
 #define S5P_MFC_ENC_NAME	"s5p-mfc-enc"
 
-int debug;
-module_param(debug, int, S_IRUGO | S_IWUSR);
+int mfc_debug_level;
+module_param_named(debug, mfc_debug_level, int, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(debug, "Debug level - higher value produces more verbose messages");
 
 /* Helper functions for interrupt processing */
@@ -150,10 +150,10 @@ static void s5p_mfc_watchdog_worker(struct work_struct *work)
 		if (!ctx)
 			continue;
 		ctx->state = MFCINST_ERROR;
-		s5p_mfc_hw_call(dev->mfc_ops, cleanup_queue, &ctx->dst_queue,
-				&ctx->vq_dst);
-		s5p_mfc_hw_call(dev->mfc_ops, cleanup_queue, &ctx->src_queue,
-				&ctx->vq_src);
+		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
+						&ctx->dst_queue, &ctx->vq_dst);
+		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
+						&ctx->src_queue, &ctx->vq_src);
 		clear_work_bit(ctx);
 		wake_up_ctx(ctx, S5P_MFC_R2H_CMD_ERR_RET, 0);
 	}
@@ -264,7 +264,12 @@ static void s5p_mfc_handle_frame_new(struct s5p_mfc_ctx *ctx, unsigned int err)
 	unsigned int frame_type;
 
 	dspl_y_addr = s5p_mfc_hw_call(dev->mfc_ops, get_dspl_y_adr, dev);
-	frame_type = s5p_mfc_hw_call(dev->mfc_ops, get_disp_frame_type, ctx);
+	if (IS_MFCV6_PLUS(dev))
+		frame_type = s5p_mfc_hw_call(dev->mfc_ops,
+			get_disp_frame_type, ctx);
+	else
+		frame_type = s5p_mfc_hw_call(dev->mfc_ops,
+			get_dec_frame_type, dev);
 
 	/* If frame is same as previous then skip and do not dequeue */
 	if (frame_type == S5P_FIMV_DECODE_FRAME_SKIPPED) {
@@ -327,12 +332,12 @@ static void s5p_mfc_handle_frame(struct s5p_mfc_ctx *ctx,
 	if (res_change == S5P_FIMV_RES_INCREASE ||
 		res_change == S5P_FIMV_RES_DECREASE) {
 		ctx->state = MFCINST_RES_CHANGE_INIT;
-		s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
+		s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
 		wake_up_ctx(ctx, reason, err);
 		if (test_and_clear_bit(0, &dev->hw_lock) == 0)
 			BUG();
 		s5p_mfc_clock_off();
-		s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+		s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 		return;
 	}
 	if (ctx->dpb_flush_flag)
@@ -400,7 +405,7 @@ leave_handle_frame:
 	if ((ctx->src_queue_cnt == 0 && ctx->state != MFCINST_FINISHING)
 				    || ctx->dst_queue_cnt < ctx->pb_count)
 		clear_work_bit(ctx);
-	s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
 	wake_up_ctx(ctx, reason, err);
 	if (test_and_clear_bit(0, &dev->hw_lock) == 0)
 		BUG();
@@ -409,7 +414,7 @@ leave_handle_frame:
 	if (test_bit(0, &dev->enter_suspend))
 		wake_up_dev(dev, reason, err);
 	else
-		s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+		s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 }
 
 /* Error handling for interrupt */
@@ -435,10 +440,10 @@ static void s5p_mfc_handle_error(struct s5p_mfc_dev *dev,
 			ctx->state = MFCINST_ERROR;
 			/* Mark all dst buffers as having an error */
 			spin_lock_irqsave(&dev->irqlock, flags);
-			s5p_mfc_hw_call(dev->mfc_ops, cleanup_queue,
+			s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
 						&ctx->dst_queue, &ctx->vq_dst);
 			/* Mark all src buffers as having an error */
-			s5p_mfc_hw_call(dev->mfc_ops, cleanup_queue,
+			s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
 						&ctx->src_queue, &ctx->vq_src);
 			spin_unlock_irqrestore(&dev->irqlock, flags);
 			wake_up_ctx(ctx, reason, err);
@@ -452,7 +457,7 @@ static void s5p_mfc_handle_error(struct s5p_mfc_dev *dev,
 	}
 	if (test_and_clear_bit(0, &dev->hw_lock) == 0)
 		BUG();
-	s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
 	s5p_mfc_clock_off();
 	wake_up_dev(dev, reason, err);
 	return;
@@ -476,7 +481,7 @@ static void s5p_mfc_handle_seq_done(struct s5p_mfc_ctx *ctx,
 		ctx->img_height = s5p_mfc_hw_call(dev->mfc_ops, get_img_height,
 				dev);
 
-		s5p_mfc_hw_call(dev->mfc_ops, dec_calc_dpb_size, ctx);
+		s5p_mfc_hw_call_void(dev->mfc_ops, dec_calc_dpb_size, ctx);
 
 		ctx->pb_count = s5p_mfc_hw_call(dev->mfc_ops, get_dpb_count,
 				dev);
@@ -503,12 +508,12 @@ static void s5p_mfc_handle_seq_done(struct s5p_mfc_ctx *ctx,
 			ctx->head_processed = 1;
 		}
 	}
-	s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
 	clear_work_bit(ctx);
 	if (test_and_clear_bit(0, &dev->hw_lock) == 0)
 		BUG();
 	s5p_mfc_clock_off();
-	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 	wake_up_ctx(ctx, reason, err);
 }
 
@@ -523,7 +528,7 @@ static void s5p_mfc_handle_init_buffers(struct s5p_mfc_ctx *ctx,
 	if (ctx == NULL)
 		return;
 	dev = ctx->dev;
-	s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
 	ctx->int_type = reason;
 	ctx->int_err = err;
 	ctx->int_cond = 1;
@@ -550,7 +555,7 @@ static void s5p_mfc_handle_init_buffers(struct s5p_mfc_ctx *ctx,
 		s5p_mfc_clock_off();
 
 		wake_up(&ctx->queue);
-		s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+		s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 	} else {
 		if (test_and_clear_bit(0, &dev->hw_lock) == 0)
 			BUG();
@@ -591,7 +596,7 @@ static void s5p_mfc_handle_stream_complete(struct s5p_mfc_ctx *ctx,
 
 	s5p_mfc_clock_off();
 	wake_up(&ctx->queue);
-	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 }
 
 /* Interrupt processing */
@@ -628,12 +633,12 @@ static irqreturn_t s5p_mfc_irq(int irq, void *priv)
 		if (ctx->c_ops->post_frame_start) {
 			if (ctx->c_ops->post_frame_start(ctx))
 				mfc_err("post_frame_start() failed\n");
-			s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
+			s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
 			wake_up_ctx(ctx, reason, err);
 			if (test_and_clear_bit(0, &dev->hw_lock) == 0)
 				BUG();
 			s5p_mfc_clock_off();
-			s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+			s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 		} else {
 			s5p_mfc_handle_frame(ctx, reason, err);
 		}
@@ -663,7 +668,7 @@ static irqreturn_t s5p_mfc_irq(int irq, void *priv)
 	case S5P_MFC_R2H_CMD_WAKEUP_RET:
 		if (ctx)
 			clear_work_bit(ctx);
-		s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
+		s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
 		wake_up_dev(dev, reason, err);
 		clear_bit(0, &dev->hw_lock);
 		clear_bit(0, &dev->enter_suspend);
@@ -685,12 +690,12 @@ static irqreturn_t s5p_mfc_irq(int irq, void *priv)
 
 	default:
 		mfc_debug(2, "Unknown int reason\n");
-		s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
+		s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
 	}
 	mfc_debug_leave();
 	return IRQ_HANDLED;
 irq_cleanup_hw:
-	s5p_mfc_hw_call(dev->mfc_ops, clear_int_flags, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, clear_int_flags, dev);
 	ctx->int_type = reason;
 	ctx->int_err = err;
 	ctx->int_cond = 1;
@@ -699,7 +704,7 @@ irq_cleanup_hw:
 
 	s5p_mfc_clock_off();
 
-	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 	mfc_debug(2, "Exit via irq_cleanup_hw\n");
 	return IRQ_HANDLED;
 }
@@ -1311,11 +1316,9 @@ static int s5p_mfc_runtime_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct s5p_mfc_dev *m_dev = platform_get_drvdata(pdev);
-	int pre_power;
 
 	if (!m_dev->alloc_ctx)
 		return 0;
-	pre_power = atomic_read(&m_dev->pm.power);
 	atomic_set(&m_dev->pm.power, 1);
 	return 0;
 }
@@ -1328,20 +1331,20 @@ static const struct dev_pm_ops s5p_mfc_pm_ops = {
 			   NULL)
 };
 
-struct s5p_mfc_buf_size_v5 mfc_buf_size_v5 = {
+static struct s5p_mfc_buf_size_v5 mfc_buf_size_v5 = {
 	.h264_ctx	= MFC_H264_CTX_BUF_SIZE,
 	.non_h264_ctx	= MFC_CTX_BUF_SIZE,
 	.dsc		= DESC_BUF_SIZE,
 	.shm		= SHARED_BUF_SIZE,
 };
 
-struct s5p_mfc_buf_size buf_size_v5 = {
+static struct s5p_mfc_buf_size buf_size_v5 = {
 	.fw	= MAX_FW_SIZE,
 	.cpb	= MAX_CPB_SIZE,
 	.priv	= &mfc_buf_size_v5,
 };
 
-struct s5p_mfc_buf_align mfc_buf_align_v5 = {
+static struct s5p_mfc_buf_align mfc_buf_align_v5 = {
 	.base = MFC_BASE_ALIGN_ORDER,
 };
 
@@ -1354,7 +1357,7 @@ static struct s5p_mfc_variant mfc_drvdata_v5 = {
 	.fw_name[0]	= "s5p-mfc.fw",
 };
 
-struct s5p_mfc_buf_size_v6 mfc_buf_size_v6 = {
+static struct s5p_mfc_buf_size_v6 mfc_buf_size_v6 = {
 	.dev_ctx	= MFC_CTX_BUF_SIZE_V6,
 	.h264_dec_ctx	= MFC_H264_DEC_CTX_BUF_SIZE_V6,
 	.other_dec_ctx	= MFC_OTHER_DEC_CTX_BUF_SIZE_V6,
@@ -1362,13 +1365,13 @@ struct s5p_mfc_buf_size_v6 mfc_buf_size_v6 = {
 	.other_enc_ctx	= MFC_OTHER_ENC_CTX_BUF_SIZE_V6,
 };
 
-struct s5p_mfc_buf_size buf_size_v6 = {
+static struct s5p_mfc_buf_size buf_size_v6 = {
 	.fw	= MAX_FW_SIZE_V6,
 	.cpb	= MAX_CPB_SIZE_V6,
 	.priv	= &mfc_buf_size_v6,
 };
 
-struct s5p_mfc_buf_align mfc_buf_align_v6 = {
+static struct s5p_mfc_buf_align mfc_buf_align_v6 = {
 	.base = 0,
 };
 
@@ -1386,7 +1389,7 @@ static struct s5p_mfc_variant mfc_drvdata_v6 = {
 	.fw_name[1]     = "s5p-mfc-v6-v2.fw",
 };
 
-struct s5p_mfc_buf_size_v6 mfc_buf_size_v7 = {
+static struct s5p_mfc_buf_size_v6 mfc_buf_size_v7 = {
 	.dev_ctx	= MFC_CTX_BUF_SIZE_V7,
 	.h264_dec_ctx	= MFC_H264_DEC_CTX_BUF_SIZE_V7,
 	.other_dec_ctx	= MFC_OTHER_DEC_CTX_BUF_SIZE_V7,
@@ -1394,13 +1397,13 @@ struct s5p_mfc_buf_size_v6 mfc_buf_size_v7 = {
 	.other_enc_ctx	= MFC_OTHER_ENC_CTX_BUF_SIZE_V7,
 };
 
-struct s5p_mfc_buf_size buf_size_v7 = {
+static struct s5p_mfc_buf_size buf_size_v7 = {
 	.fw	= MAX_FW_SIZE_V7,
 	.cpb	= MAX_CPB_SIZE_V7,
 	.priv	= &mfc_buf_size_v7,
 };
 
-struct s5p_mfc_buf_align mfc_buf_align_v7 = {
+static struct s5p_mfc_buf_align mfc_buf_align_v7 = {
 	.base = 0,
 };
 
@@ -1413,7 +1416,7 @@ static struct s5p_mfc_variant mfc_drvdata_v7 = {
 	.fw_name[0]     = "s5p-mfc-v7.fw",
 };
 
-struct s5p_mfc_buf_size_v6 mfc_buf_size_v8 = {
+static struct s5p_mfc_buf_size_v6 mfc_buf_size_v8 = {
 	.dev_ctx	= MFC_CTX_BUF_SIZE_V8,
 	.h264_dec_ctx	= MFC_H264_DEC_CTX_BUF_SIZE_V8,
 	.other_dec_ctx	= MFC_OTHER_DEC_CTX_BUF_SIZE_V8,
@@ -1421,13 +1424,13 @@ struct s5p_mfc_buf_size_v6 mfc_buf_size_v8 = {
 	.other_enc_ctx	= MFC_OTHER_ENC_CTX_BUF_SIZE_V8,
 };
 
-struct s5p_mfc_buf_size buf_size_v8 = {
+static struct s5p_mfc_buf_size buf_size_v8 = {
 	.fw	= MAX_FW_SIZE_V8,
 	.cpb	= MAX_CPB_SIZE_V8,
 	.priv	= &mfc_buf_size_v8,
 };
 
-struct s5p_mfc_buf_align mfc_buf_align_v8 = {
+static struct s5p_mfc_buf_align mfc_buf_align_v8 = {
 	.base = 0,
 };
 
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_cmd_v5.c b/drivers/media/platform/s5p-mfc/s5p_mfc_cmd_v5.c
index 9a6efd6c1329..8c4739ca16d6 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_cmd_v5.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_cmd_v5.c
@@ -14,6 +14,7 @@
 #include "s5p_mfc_cmd.h"
 #include "s5p_mfc_common.h"
 #include "s5p_mfc_debug.h"
+#include "s5p_mfc_cmd_v5.h"
 
 /* This function is used to send a command to the MFC */
 static int s5p_mfc_cmd_host2risc_v5(struct s5p_mfc_dev *dev, int cmd,
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_cmd_v6.c b/drivers/media/platform/s5p-mfc/s5p_mfc_cmd_v6.c
index ec1a5947ed7d..f17609669b96 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_cmd_v6.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_cmd_v6.c
@@ -16,6 +16,7 @@
 #include "s5p_mfc_debug.h"
 #include "s5p_mfc_intr.h"
 #include "s5p_mfc_opr.h"
+#include "s5p_mfc_cmd_v6.h"
 
 static int s5p_mfc_cmd_host2risc_v6(struct s5p_mfc_dev *dev, int cmd,
 				struct s5p_mfc_cmd_args *args)
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
index 01816ffb384b..3e41ca1293ed 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
@@ -698,6 +698,12 @@ struct mfc_control {
 #define s5p_mfc_hw_call(f, op, args...) \
 	((f && f->op) ? f->op(args) : -ENODEV)
 
+#define s5p_mfc_hw_call_void(f, op, args...) \
+do { \
+	if (f && f->op) \
+		f->op(args); \
+} while (0)
+
 #define fh_to_ctx(__fh) container_of(__fh, struct s5p_mfc_ctx, fh)
 #define ctrl_to_ctx(__ctrl) \
 	container_of((__ctrl)->handler, struct s5p_mfc_ctx, ctrl_handler)
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c b/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c
index ca9f78922832..0c885a8a0e9f 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_ctrl.c
@@ -21,6 +21,7 @@
 #include "s5p_mfc_intr.h"
 #include "s5p_mfc_opr.h"
 #include "s5p_mfc_pm.h"
+#include "s5p_mfc_ctrl.h"
 
 /* Allocate memory for firmware */
 int s5p_mfc_alloc_firmware(struct s5p_mfc_dev *dev)
@@ -188,12 +189,12 @@ static inline void s5p_mfc_init_memctrl(struct s5p_mfc_dev *dev)
 {
 	if (IS_MFCV6_PLUS(dev)) {
 		mfc_write(dev, dev->bank1, S5P_FIMV_RISC_BASE_ADDRESS_V6);
-		mfc_debug(2, "Base Address : %08x\n", dev->bank1);
+		mfc_debug(2, "Base Address : %pad\n", &dev->bank1);
 	} else {
 		mfc_write(dev, dev->bank1, S5P_FIMV_MC_DRAMBASE_ADR_A);
 		mfc_write(dev, dev->bank2, S5P_FIMV_MC_DRAMBASE_ADR_B);
-		mfc_debug(2, "Bank1: %08x, Bank2: %08x\n",
-				dev->bank1, dev->bank2);
+		mfc_debug(2, "Bank1: %pad, Bank2: %pad\n",
+				&dev->bank1, &dev->bank2);
 	}
 }
 
@@ -257,9 +258,9 @@ int s5p_mfc_init_hw(struct s5p_mfc_dev *dev)
 		s5p_mfc_clock_off();
 		return ret;
 	}
-	mfc_debug(2, "Ok, now will write a command to init the system\n");
+	mfc_debug(2, "Ok, now will wait for completion of hardware init\n");
 	if (s5p_mfc_wait_for_done_dev(dev, S5P_MFC_R2H_CMD_SYS_INIT_RET)) {
-		mfc_err("Failed to load firmware\n");
+		mfc_err("Failed to init hardware\n");
 		s5p_mfc_reset(dev);
 		s5p_mfc_clock_off();
 		return -EIO;
@@ -293,7 +294,7 @@ void s5p_mfc_deinit_hw(struct s5p_mfc_dev *dev)
 	s5p_mfc_clock_on();
 
 	s5p_mfc_reset(dev);
-	s5p_mfc_hw_call(dev->mfc_ops, release_dev_context_buffer, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, release_dev_context_buffer, dev);
 
 	s5p_mfc_clock_off();
 }
@@ -396,7 +397,7 @@ int s5p_mfc_open_mfc_inst(struct s5p_mfc_dev *dev, struct s5p_mfc_ctx *ctx)
 
 	set_work_bit_irqsave(ctx);
 	s5p_mfc_clean_ctx_int_flags(ctx);
-	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 	if (s5p_mfc_wait_for_done_ctx(ctx,
 		S5P_MFC_R2H_CMD_OPEN_INSTANCE_RET, 0)) {
 		/* Error or timeout */
@@ -410,9 +411,9 @@ int s5p_mfc_open_mfc_inst(struct s5p_mfc_dev *dev, struct s5p_mfc_ctx *ctx)
 
 err_free_desc_buf:
 	if (ctx->type == MFCINST_DECODER)
-		s5p_mfc_hw_call(dev->mfc_ops, release_dec_desc_buffer, ctx);
+		s5p_mfc_hw_call_void(dev->mfc_ops, release_dec_desc_buffer, ctx);
 err_free_inst_buf:
-	s5p_mfc_hw_call(dev->mfc_ops, release_instance_buffer, ctx);
+	s5p_mfc_hw_call_void(dev->mfc_ops, release_instance_buffer, ctx);
 err:
 	return ret;
 }
@@ -422,17 +423,17 @@ void s5p_mfc_close_mfc_inst(struct s5p_mfc_dev *dev, struct s5p_mfc_ctx *ctx)
 	ctx->state = MFCINST_RETURN_INST;
 	set_work_bit_irqsave(ctx);
 	s5p_mfc_clean_ctx_int_flags(ctx);
-	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 	/* Wait until instance is returned or timeout occurred */
 	if (s5p_mfc_wait_for_done_ctx(ctx,
 				S5P_MFC_R2H_CMD_CLOSE_INSTANCE_RET, 0))
 		mfc_err("Err returning instance\n");
 
 	/* Free resources */
-	s5p_mfc_hw_call(dev->mfc_ops, release_codec_buffers, ctx);
-	s5p_mfc_hw_call(dev->mfc_ops, release_instance_buffer, ctx);
+	s5p_mfc_hw_call_void(dev->mfc_ops, release_codec_buffers, ctx);
+	s5p_mfc_hw_call_void(dev->mfc_ops, release_instance_buffer, ctx);
 	if (ctx->type == MFCINST_DECODER)
-		s5p_mfc_hw_call(dev->mfc_ops, release_dec_desc_buffer, ctx);
+		s5p_mfc_hw_call_void(dev->mfc_ops, release_dec_desc_buffer, ctx);
 
 	ctx->inst_no = MFC_NO_INSTANCE_SET;
 	ctx->state = MFCINST_FREE;
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_debug.h b/drivers/media/platform/s5p-mfc/s5p_mfc_debug.h
index 8e608f5aa0d7..5936923c631c 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_debug.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_debug.h
@@ -1,5 +1,5 @@
 /*
- * drivers/media/platform/samsung/mfc5/s5p_mfc_debug.h
+ * drivers/media/platform/s5p-mfc/s5p_mfc_debug.h
  *
  * Header file for Samsung MFC (Multi Function Codec - FIMV) driver
  * This file contains debug macros
@@ -18,11 +18,11 @@
 #define DEBUG
 
 #ifdef DEBUG
-extern int debug;
+extern int mfc_debug_level;
 
 #define mfc_debug(level, fmt, args...)				\
 	do {							\
-		if (debug >= level)				\
+		if (mfc_debug_level >= level)			\
 			printk(KERN_DEBUG "%s:%d: " fmt,	\
 				__func__, __LINE__, ##args);	\
 	} while (0)
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c b/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
index 9103258b7df3..a98fe023deaf 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_dec.c
@@ -283,17 +283,13 @@ static int vidioc_querycap(struct file *file, void *priv,
 
 /* Enumerate format */
 static int vidioc_enum_fmt(struct file *file, struct v4l2_fmtdesc *f,
-							bool mplane, bool out)
+							bool out)
 {
 	struct s5p_mfc_dev *dev = video_drvdata(file);
 	struct s5p_mfc_fmt *fmt;
 	int i, j = 0;
 
 	for (i = 0; i < ARRAY_SIZE(formats); ++i) {
-		if (mplane && formats[i].num_planes == 1)
-			continue;
-		else if (!mplane && formats[i].num_planes > 1)
-			continue;
 		if (out && formats[i].type != MFC_FMT_DEC)
 			continue;
 		else if (!out && formats[i].type != MFC_FMT_RAW)
@@ -313,28 +309,16 @@ static int vidioc_enum_fmt(struct file *file, struct v4l2_fmtdesc *f,
 	return 0;
 }
 
-static int vidioc_enum_fmt_vid_cap(struct file *file, void *pirv,
-							struct v4l2_fmtdesc *f)
-{
-	return vidioc_enum_fmt(file, f, false, false);
-}
-
 static int vidioc_enum_fmt_vid_cap_mplane(struct file *file, void *pirv,
 							struct v4l2_fmtdesc *f)
 {
-	return vidioc_enum_fmt(file, f, true, false);
-}
-
-static int vidioc_enum_fmt_vid_out(struct file *file, void *priv,
-							struct v4l2_fmtdesc *f)
-{
-	return vidioc_enum_fmt(file, f, false, true);
+	return vidioc_enum_fmt(file, f, false);
 }
 
 static int vidioc_enum_fmt_vid_out_mplane(struct file *file, void *priv,
 							struct v4l2_fmtdesc *f)
 {
-	return vidioc_enum_fmt(file, f, true, true);
+	return vidioc_enum_fmt(file, f, true);
 }
 
 /* Get format */
@@ -543,7 +527,7 @@ static int reqbufs_capture(struct s5p_mfc_dev *dev, struct s5p_mfc_ctx *ctx,
 		ret = vb2_reqbufs(&ctx->vq_dst, reqbufs);
 		if (ret)
 			goto out;
-		s5p_mfc_hw_call(dev->mfc_ops, release_codec_buffers, ctx);
+		s5p_mfc_hw_call_void(dev->mfc_ops, release_codec_buffers, ctx);
 		ctx->dst_bufs_cnt = 0;
 	} else if (ctx->capture_state == QUEUE_FREE) {
 		WARN_ON(ctx->dst_bufs_cnt != 0);
@@ -571,7 +555,7 @@ static int reqbufs_capture(struct s5p_mfc_dev *dev, struct s5p_mfc_ctx *ctx,
 
 		if (s5p_mfc_ctx_ready(ctx))
 			set_work_bit_irqsave(ctx);
-		s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+		s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 		s5p_mfc_wait_for_done_ctx(ctx, S5P_MFC_R2H_CMD_INIT_BUFFERS_RET,
 					  0);
 	} else {
@@ -823,8 +807,8 @@ static int vidioc_g_crop(struct file *file, void *priv,
 	return 0;
 }
 
-int vidioc_decoder_cmd(struct file *file, void *priv,
-						struct v4l2_decoder_cmd *cmd)
+static int vidioc_decoder_cmd(struct file *file, void *priv,
+			      struct v4l2_decoder_cmd *cmd)
 {
 	struct s5p_mfc_ctx *ctx = fh_to_ctx(priv);
 	struct s5p_mfc_dev *dev = ctx->dev;
@@ -846,7 +830,7 @@ int vidioc_decoder_cmd(struct file *file, void *priv,
 			if (s5p_mfc_ctx_ready(ctx))
 				set_work_bit_irqsave(ctx);
 			spin_unlock_irqrestore(&dev->irqlock, flags);
-			s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+			s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 		} else {
 			mfc_err("EOS: marking last buffer of stream");
 			buf = list_entry(ctx->src_queue.prev,
@@ -881,9 +865,7 @@ static int vidioc_subscribe_event(struct v4l2_fh *fh,
 /* v4l2_ioctl_ops */
 static const struct v4l2_ioctl_ops s5p_mfc_dec_ioctl_ops = {
 	.vidioc_querycap = vidioc_querycap,
-	.vidioc_enum_fmt_vid_cap = vidioc_enum_fmt_vid_cap,
 	.vidioc_enum_fmt_vid_cap_mplane = vidioc_enum_fmt_vid_cap_mplane,
-	.vidioc_enum_fmt_vid_out = vidioc_enum_fmt_vid_out,
 	.vidioc_enum_fmt_vid_out_mplane = vidioc_enum_fmt_vid_out_mplane,
 	.vidioc_g_fmt_vid_cap_mplane = vidioc_g_fmt,
 	.vidioc_g_fmt_vid_out_mplane = vidioc_g_fmt,
@@ -990,7 +972,7 @@ static int s5p_mfc_buf_init(struct vb2_buffer *vb)
 	if (vq->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
 		if (ctx->capture_state == QUEUE_BUFS_MMAPED)
 			return 0;
-		for (i = 0; i <= ctx->src_fmt->num_planes ; i++) {
+		for (i = 0; i < ctx->dst_fmt->num_planes; i++) {
 			if (IS_ERR_OR_NULL(ERR_PTR(
 					vb2_dma_contig_plane_dma_addr(vb, i)))) {
 				mfc_err("Plane mem not allocated\n");
@@ -1044,7 +1026,7 @@ static int s5p_mfc_start_streaming(struct vb2_queue *q, unsigned int count)
 	/* If context is ready then dev = work->data;schedule it to run */
 	if (s5p_mfc_ctx_ready(ctx))
 		set_work_bit_irqsave(ctx);
-	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 	return 0;
 }
 
@@ -1065,8 +1047,8 @@ static void s5p_mfc_stop_streaming(struct vb2_queue *q)
 	}
 	if (q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
 		spin_lock_irqsave(&dev->irqlock, flags);
-		s5p_mfc_hw_call(dev->mfc_ops, cleanup_queue, &ctx->dst_queue,
-				&ctx->vq_dst);
+		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
+						&ctx->dst_queue, &ctx->vq_dst);
 		INIT_LIST_HEAD(&ctx->dst_queue);
 		ctx->dst_queue_cnt = 0;
 		ctx->dpb_flush_flag = 1;
@@ -1076,7 +1058,7 @@ static void s5p_mfc_stop_streaming(struct vb2_queue *q)
 			ctx->state = MFCINST_FLUSH;
 			set_work_bit_irqsave(ctx);
 			s5p_mfc_clean_ctx_int_flags(ctx);
-			s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+			s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 			if (s5p_mfc_wait_for_done_ctx(ctx,
 				S5P_MFC_R2H_CMD_DPB_FLUSH_RET, 0))
 				mfc_err("Err flushing buffers\n");
@@ -1084,8 +1066,8 @@ static void s5p_mfc_stop_streaming(struct vb2_queue *q)
 	}
 	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
 		spin_lock_irqsave(&dev->irqlock, flags);
-		s5p_mfc_hw_call(dev->mfc_ops, cleanup_queue, &ctx->src_queue,
-				&ctx->vq_src);
+		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
+						&ctx->src_queue, &ctx->vq_src);
 		INIT_LIST_HEAD(&ctx->src_queue);
 		ctx->src_queue_cnt = 0;
 		spin_unlock_irqrestore(&dev->irqlock, flags);
@@ -1124,7 +1106,7 @@ static void s5p_mfc_buf_queue(struct vb2_buffer *vb)
 	}
 	if (s5p_mfc_ctx_ready(ctx))
 		set_work_bit_irqsave(ctx);
-	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 }
 
 static struct vb2_ops s5p_mfc_dec_qops = {
@@ -1220,7 +1202,7 @@ void s5p_mfc_dec_init(struct s5p_mfc_ctx *ctx)
 	else
 		f.fmt.pix_mp.pixelformat = V4L2_PIX_FMT_NV12MT;
 	ctx->dst_fmt = find_format(&f, MFC_FMT_RAW);
-	mfc_debug(2, "Default src_fmt is %x, dest_fmt is %x\n",
-			(unsigned int)ctx->src_fmt, (unsigned int)ctx->dst_fmt);
+	mfc_debug(2, "Default src_fmt is %p, dest_fmt is %p\n",
+			ctx->src_fmt, ctx->dst_fmt);
 }
 
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
index d26b2484ca10..a904a1c7bb21 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
@@ -739,14 +739,11 @@ static int s5p_mfc_ctx_ready(struct s5p_mfc_ctx *ctx)
 static void cleanup_ref_queue(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_buf *mb_entry;
-	unsigned long mb_y_addr, mb_c_addr;
 
 	/* move buffers in ref queue to src queue */
 	while (!list_empty(&ctx->ref_queue)) {
 		mb_entry = list_entry((&ctx->ref_queue)->next,
 						struct s5p_mfc_buf, list);
-		mb_y_addr = vb2_dma_contig_plane_dma_addr(mb_entry->b, 0);
-		mb_c_addr = vb2_dma_contig_plane_dma_addr(mb_entry->b, 1);
 		list_del(&mb_entry->list);
 		ctx->ref_queue_cnt--;
 		list_add_tail(&mb_entry->list, &ctx->src_queue);
@@ -770,7 +767,7 @@ static int enc_pre_seq_start(struct s5p_mfc_ctx *ctx)
 	dst_mb = list_entry(ctx->dst_queue.next, struct s5p_mfc_buf, list);
 	dst_addr = vb2_dma_contig_plane_dma_addr(dst_mb->b, 0);
 	dst_size = vb2_plane_size(dst_mb->b, 0);
-	s5p_mfc_hw_call(dev->mfc_ops, set_enc_stream_buffer, ctx, dst_addr,
+	s5p_mfc_hw_call_void(dev->mfc_ops, set_enc_stream_buffer, ctx, dst_addr,
 			dst_size);
 	spin_unlock_irqrestore(&dev->irqlock, flags);
 	return 0;
@@ -803,7 +800,7 @@ static int enc_post_seq_start(struct s5p_mfc_ctx *ctx)
 		ctx->state = MFCINST_RUNNING;
 		if (s5p_mfc_ctx_ready(ctx))
 			set_work_bit_irqsave(ctx);
-		s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+		s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 	} else {
 		enc_pb_count = s5p_mfc_hw_call(dev->mfc_ops,
 				get_enc_dpb_count, dev);
@@ -828,15 +825,15 @@ static int enc_pre_frame_start(struct s5p_mfc_ctx *ctx)
 	src_mb = list_entry(ctx->src_queue.next, struct s5p_mfc_buf, list);
 	src_y_addr = vb2_dma_contig_plane_dma_addr(src_mb->b, 0);
 	src_c_addr = vb2_dma_contig_plane_dma_addr(src_mb->b, 1);
-	s5p_mfc_hw_call(dev->mfc_ops, set_enc_frame_buffer, ctx, src_y_addr,
-			src_c_addr);
+	s5p_mfc_hw_call_void(dev->mfc_ops, set_enc_frame_buffer, ctx,
+							src_y_addr, src_c_addr);
 	spin_unlock_irqrestore(&dev->irqlock, flags);
 
 	spin_lock_irqsave(&dev->irqlock, flags);
 	dst_mb = list_entry(ctx->dst_queue.next, struct s5p_mfc_buf, list);
 	dst_addr = vb2_dma_contig_plane_dma_addr(dst_mb->b, 0);
 	dst_size = vb2_plane_size(dst_mb->b, 0);
-	s5p_mfc_hw_call(dev->mfc_ops, set_enc_stream_buffer, ctx, dst_addr,
+	s5p_mfc_hw_call_void(dev->mfc_ops, set_enc_stream_buffer, ctx, dst_addr,
 			dst_size);
 	spin_unlock_irqrestore(&dev->irqlock, flags);
 
@@ -861,7 +858,7 @@ static int enc_post_frame_start(struct s5p_mfc_ctx *ctx)
 		  mfc_read(dev, S5P_FIMV_ENC_SI_PIC_CNT));
 	spin_lock_irqsave(&dev->irqlock, flags);
 	if (slice_type >= 0) {
-		s5p_mfc_hw_call(dev->mfc_ops, get_enc_frame_buffer, ctx,
+		s5p_mfc_hw_call_void(dev->mfc_ops, get_enc_frame_buffer, ctx,
 				&enc_y_addr, &enc_c_addr);
 		list_for_each_entry(mb_entry, &ctx->src_queue, list) {
 			mb_y_addr = vb2_dma_contig_plane_dma_addr(mb_entry->b, 0);
@@ -954,17 +951,13 @@ static int vidioc_querycap(struct file *file, void *priv,
 }
 
 static int vidioc_enum_fmt(struct file *file, struct v4l2_fmtdesc *f,
-							bool mplane, bool out)
+							bool out)
 {
 	struct s5p_mfc_dev *dev = video_drvdata(file);
 	struct s5p_mfc_fmt *fmt;
 	int i, j = 0;
 
 	for (i = 0; i < ARRAY_SIZE(formats); ++i) {
-		if (mplane && formats[i].num_planes == 1)
-			continue;
-		else if (!mplane && formats[i].num_planes > 1)
-			continue;
 		if (out && formats[i].type != MFC_FMT_RAW)
 			continue;
 		else if (!out && formats[i].type != MFC_FMT_ENC)
@@ -984,28 +977,16 @@ static int vidioc_enum_fmt(struct file *file, struct v4l2_fmtdesc *f,
 	return -EINVAL;
 }
 
-static int vidioc_enum_fmt_vid_cap(struct file *file, void *pirv,
-				   struct v4l2_fmtdesc *f)
-{
-	return vidioc_enum_fmt(file, f, false, false);
-}
-
 static int vidioc_enum_fmt_vid_cap_mplane(struct file *file, void *pirv,
 					  struct v4l2_fmtdesc *f)
 {
-	return vidioc_enum_fmt(file, f, true, false);
-}
-
-static int vidioc_enum_fmt_vid_out(struct file *file, void *prov,
-				   struct v4l2_fmtdesc *f)
-{
-	return vidioc_enum_fmt(file, f, false, true);
+	return vidioc_enum_fmt(file, f, false);
 }
 
 static int vidioc_enum_fmt_vid_out_mplane(struct file *file, void *prov,
 					  struct v4l2_fmtdesc *f)
 {
-	return vidioc_enum_fmt(file, f, true, true);
+	return vidioc_enum_fmt(file, f, true);
 }
 
 static int vidioc_g_fmt(struct file *file, void *priv, struct v4l2_format *f)
@@ -1127,7 +1108,7 @@ static int vidioc_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
 			pix_fmt_mp->width, pix_fmt_mp->height,
 			ctx->img_width, ctx->img_height);
 
-		s5p_mfc_hw_call(dev->mfc_ops, enc_calc_src_size, ctx);
+		s5p_mfc_hw_call_void(dev->mfc_ops, enc_calc_src_size, ctx);
 		pix_fmt_mp->plane_fmt[0].sizeimage = ctx->luma_size;
 		pix_fmt_mp->plane_fmt[0].bytesperline = ctx->buf_width;
 		pix_fmt_mp->plane_fmt[1].sizeimage = ctx->chroma_size;
@@ -1681,8 +1662,8 @@ static int vidioc_g_parm(struct file *file, void *priv,
 	return 0;
 }
 
-int vidioc_encoder_cmd(struct file *file, void *priv,
-						struct v4l2_encoder_cmd *cmd)
+static int vidioc_encoder_cmd(struct file *file, void *priv,
+			      struct v4l2_encoder_cmd *cmd)
 {
 	struct s5p_mfc_ctx *ctx = fh_to_ctx(priv);
 	struct s5p_mfc_dev *dev = ctx->dev;
@@ -1704,7 +1685,7 @@ int vidioc_encoder_cmd(struct file *file, void *priv,
 			if (s5p_mfc_ctx_ready(ctx))
 				set_work_bit_irqsave(ctx);
 			spin_unlock_irqrestore(&dev->irqlock, flags);
-			s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+			s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 		} else {
 			mfc_debug(2, "EOS: marking last buffer of stream\n");
 			buf = list_entry(ctx->src_queue.prev,
@@ -1736,9 +1717,7 @@ static int vidioc_subscribe_event(struct v4l2_fh *fh,
 
 static const struct v4l2_ioctl_ops s5p_mfc_enc_ioctl_ops = {
 	.vidioc_querycap = vidioc_querycap,
-	.vidioc_enum_fmt_vid_cap = vidioc_enum_fmt_vid_cap,
 	.vidioc_enum_fmt_vid_cap_mplane = vidioc_enum_fmt_vid_cap_mplane,
-	.vidioc_enum_fmt_vid_out = vidioc_enum_fmt_vid_out,
 	.vidioc_enum_fmt_vid_out_mplane = vidioc_enum_fmt_vid_out_mplane,
 	.vidioc_g_fmt_vid_cap_mplane = vidioc_g_fmt,
 	.vidioc_g_fmt_vid_out_mplane = vidioc_g_fmt,
@@ -1771,13 +1750,13 @@ static int check_vb_with_fmt(struct s5p_mfc_fmt *fmt, struct vb2_buffer *vb)
 		return -EINVAL;
 	}
 	for (i = 0; i < fmt->num_planes; i++) {
-		if (!vb2_dma_contig_plane_dma_addr(vb, i)) {
+		dma_addr_t dma = vb2_dma_contig_plane_dma_addr(vb, i);
+		if (!dma) {
 			mfc_err("failed to get plane cookie\n");
 			return -EINVAL;
 		}
-		mfc_debug(2, "index: %d, plane[%d] cookie: 0x%08zx\n",
-			  vb->v4l2_buf.index, i,
-			  vb2_dma_contig_plane_dma_addr(vb, i));
+		mfc_debug(2, "index: %d, plane[%d] cookie: %pad\n",
+			  vb->v4l2_buf.index, i, &dma);
 	}
 	return 0;
 }
@@ -1897,7 +1876,7 @@ static int s5p_mfc_buf_prepare(struct vb2_buffer *vb)
 		ret = check_vb_with_fmt(ctx->dst_fmt, vb);
 		if (ret < 0)
 			return ret;
-		mfc_debug(2, "plane size: %ld, dst size: %d\n",
+		mfc_debug(2, "plane size: %ld, dst size: %zu\n",
 			vb2_plane_size(vb, 0), ctx->enc_dst_buf_size);
 		if (vb2_plane_size(vb, 0) < ctx->enc_dst_buf_size) {
 			mfc_err("plane size is too small for capture\n");
@@ -1948,7 +1927,7 @@ static int s5p_mfc_start_streaming(struct vb2_queue *q, unsigned int count)
 	/* If context is ready then dev = work->data;schedule it to run */
 	if (s5p_mfc_ctx_ready(ctx))
 		set_work_bit_irqsave(ctx);
-	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 
 	return 0;
 }
@@ -1969,14 +1948,14 @@ static void s5p_mfc_stop_streaming(struct vb2_queue *q)
 	ctx->state = MFCINST_FINISHED;
 	spin_lock_irqsave(&dev->irqlock, flags);
 	if (q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
-		s5p_mfc_hw_call(dev->mfc_ops, cleanup_queue, &ctx->dst_queue,
-				&ctx->vq_dst);
+		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue,
+						&ctx->dst_queue, &ctx->vq_dst);
 		INIT_LIST_HEAD(&ctx->dst_queue);
 		ctx->dst_queue_cnt = 0;
 	}
 	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
 		cleanup_ref_queue(ctx);
-		s5p_mfc_hw_call(dev->mfc_ops, cleanup_queue, &ctx->src_queue,
+		s5p_mfc_hw_call_void(dev->mfc_ops, cleanup_queue, &ctx->src_queue,
 				&ctx->vq_src);
 		INIT_LIST_HEAD(&ctx->src_queue);
 		ctx->src_queue_cnt = 0;
@@ -2017,7 +1996,7 @@ static void s5p_mfc_buf_queue(struct vb2_buffer *vb)
 	}
 	if (s5p_mfc_ctx_ready(ctx))
 		set_work_bit_irqsave(ctx);
-	s5p_mfc_hw_call(dev->mfc_ops, try_run, dev);
+	s5p_mfc_hw_call_void(dev->mfc_ops, try_run, dev);
 }
 
 static struct vb2_ops s5p_mfc_enc_qops = {
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_opr.c b/drivers/media/platform/s5p-mfc/s5p_mfc_opr.c
index c9a227428e6a..00a1d8b2a8c2 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_opr.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_opr.c
@@ -41,7 +41,7 @@ int s5p_mfc_alloc_priv_buf(struct device *dev,
 					struct s5p_mfc_priv_buf *b)
 {
 
-	mfc_debug(3, "Allocating priv: %d\n", b->size);
+	mfc_debug(3, "Allocating priv: %zu\n", b->size);
 
 	b->virt = dma_alloc_coherent(dev, b->size, &b->dma, GFP_KERNEL);
 
@@ -50,7 +50,7 @@ int s5p_mfc_alloc_priv_buf(struct device *dev,
 		return -ENOMEM;
 	}
 
-	mfc_debug(3, "Allocated addr %p %08x\n", b->virt, b->dma);
+	mfc_debug(3, "Allocated addr %p %pad\n", b->virt, &b->dma);
 	return 0;
 }
 
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h b/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h
index 7a7ad32ee608..de2b8c69daa5 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_opr.h
@@ -20,254 +20,254 @@
 struct s5p_mfc_regs {
 
 	/* codec common registers */
-	void *risc_on;
-	void *risc2host_int;
-	void *host2risc_int;
-	void *risc_base_address;
-	void *mfc_reset;
-	void *host2risc_command;
-	void *risc2host_command;
-	void *mfc_bus_reset_ctrl;
-	void *firmware_version;
-	void *instance_id;
-	void *codec_type;
-	void *context_mem_addr;
-	void *context_mem_size;
-	void *pixel_format;
-	void *metadata_enable;
-	void *mfc_version;
-	void *dbg_info_enable;
-	void *dbg_buffer_addr;
-	void *dbg_buffer_size;
-	void *hed_control;
-	void *mfc_timeout_value;
-	void *hed_shared_mem_addr;
-	void *dis_shared_mem_addr;/* only v7 */
-	void *ret_instance_id;
-	void *error_code;
-	void *dbg_buffer_output_size;
-	void *metadata_status;
-	void *metadata_addr_mb_info;
-	void *metadata_size_mb_info;
-	void *dbg_info_stage_counter;
+	volatile void __iomem *risc_on;
+	volatile void __iomem *risc2host_int;
+	volatile void __iomem *host2risc_int;
+	volatile void __iomem *risc_base_address;
+	volatile void __iomem *mfc_reset;
+	volatile void __iomem *host2risc_command;
+	volatile void __iomem *risc2host_command;
+	volatile void __iomem *mfc_bus_reset_ctrl;
+	volatile void __iomem *firmware_version;
+	volatile void __iomem *instance_id;
+	volatile void __iomem *codec_type;
+	volatile void __iomem *context_mem_addr;
+	volatile void __iomem *context_mem_size;
+	volatile void __iomem *pixel_format;
+	volatile void __iomem *metadata_enable;
+	volatile void __iomem *mfc_version;
+	volatile void __iomem *dbg_info_enable;
+	volatile void __iomem *dbg_buffer_addr;
+	volatile void __iomem *dbg_buffer_size;
+	volatile void __iomem *hed_control;
+	volatile void __iomem *mfc_timeout_value;
+	volatile void __iomem *hed_shared_mem_addr;
+	volatile void __iomem *dis_shared_mem_addr;/* only v7 */
+	volatile void __iomem *ret_instance_id;
+	volatile void __iomem *error_code;
+	volatile void __iomem *dbg_buffer_output_size;
+	volatile void __iomem *metadata_status;
+	volatile void __iomem *metadata_addr_mb_info;
+	volatile void __iomem *metadata_size_mb_info;
+	volatile void __iomem *dbg_info_stage_counter;
 
 	/* decoder registers */
-	void *d_crc_ctrl;
-	void *d_dec_options;
-	void *d_display_delay;
-	void *d_set_frame_width;
-	void *d_set_frame_height;
-	void *d_sei_enable;
-	void *d_min_num_dpb;
-	void *d_min_first_plane_dpb_size;
-	void *d_min_second_plane_dpb_size;
-	void *d_min_third_plane_dpb_size;/* only v8 */
-	void *d_min_num_mv;
-	void *d_mvc_num_views;
-	void *d_min_num_dis;/* only v7 */
-	void *d_min_first_dis_size;/* only v7 */
-	void *d_min_second_dis_size;/* only v7 */
-	void *d_min_third_dis_size;/* only v7 */
-	void *d_post_filter_luma_dpb0;/*  v7 and v8 */
-	void *d_post_filter_luma_dpb1;/* v7 and v8 */
-	void *d_post_filter_luma_dpb2;/* only v7 */
-	void *d_post_filter_chroma_dpb0;/* v7 and v8 */
-	void *d_post_filter_chroma_dpb1;/* v7 and v8 */
-	void *d_post_filter_chroma_dpb2;/* only v7 */
-	void *d_num_dpb;
-	void *d_num_mv;
-	void *d_init_buffer_options;
-	void *d_first_plane_dpb_stride_size;/* only v8 */
-	void *d_second_plane_dpb_stride_size;/* only v8 */
-	void *d_third_plane_dpb_stride_size;/* only v8 */
-	void *d_first_plane_dpb_size;
-	void *d_second_plane_dpb_size;
-	void *d_third_plane_dpb_size;/* only v8 */
-	void *d_mv_buffer_size;
-	void *d_first_plane_dpb;
-	void *d_second_plane_dpb;
-	void *d_third_plane_dpb;
-	void *d_mv_buffer;
-	void *d_scratch_buffer_addr;
-	void *d_scratch_buffer_size;
-	void *d_metadata_buffer_addr;
-	void *d_metadata_buffer_size;
-	void *d_nal_start_options;/* v7 and v8 */
-	void *d_cpb_buffer_addr;
-	void *d_cpb_buffer_size;
-	void *d_available_dpb_flag_upper;
-	void *d_available_dpb_flag_lower;
-	void *d_cpb_buffer_offset;
-	void *d_slice_if_enable;
-	void *d_picture_tag;
-	void *d_stream_data_size;
-	void *d_dynamic_dpb_flag_upper;/* v7 and v8 */
-	void *d_dynamic_dpb_flag_lower;/* v7 and v8 */
-	void *d_display_frame_width;
-	void *d_display_frame_height;
-	void *d_display_status;
-	void *d_display_first_plane_addr;
-	void *d_display_second_plane_addr;
-	void *d_display_third_plane_addr;/* only v8 */
-	void *d_display_frame_type;
-	void *d_display_crop_info1;
-	void *d_display_crop_info2;
-	void *d_display_picture_profile;
-	void *d_display_luma_crc;/* v7 and v8 */
-	void *d_display_chroma0_crc;/* v7 and v8 */
-	void *d_display_chroma1_crc;/* only v8 */
-	void *d_display_luma_crc_top;/* only v6 */
-	void *d_display_chroma_crc_top;/* only v6 */
-	void *d_display_luma_crc_bot;/* only v6 */
-	void *d_display_chroma_crc_bot;/* only v6 */
-	void *d_display_aspect_ratio;
-	void *d_display_extended_ar;
-	void *d_decoded_frame_width;
-	void *d_decoded_frame_height;
-	void *d_decoded_status;
-	void *d_decoded_first_plane_addr;
-	void *d_decoded_second_plane_addr;
-	void *d_decoded_third_plane_addr;/* only v8 */
-	void *d_decoded_frame_type;
-	void *d_decoded_crop_info1;
-	void *d_decoded_crop_info2;
-	void *d_decoded_picture_profile;
-	void *d_decoded_nal_size;
-	void *d_decoded_luma_crc;
-	void *d_decoded_chroma0_crc;
-	void *d_decoded_chroma1_crc;/* only v8 */
-	void *d_ret_picture_tag_top;
-	void *d_ret_picture_tag_bot;
-	void *d_ret_picture_time_top;
-	void *d_ret_picture_time_bot;
-	void *d_chroma_format;
-	void *d_vc1_info;/* v7 and v8 */
-	void *d_mpeg4_info;
-	void *d_h264_info;
-	void *d_metadata_addr_concealed_mb;
-	void *d_metadata_size_concealed_mb;
-	void *d_metadata_addr_vc1_param;
-	void *d_metadata_size_vc1_param;
-	void *d_metadata_addr_sei_nal;
-	void *d_metadata_size_sei_nal;
-	void *d_metadata_addr_vui;
-	void *d_metadata_size_vui;
-	void *d_metadata_addr_mvcvui;/* v7 and v8 */
-	void *d_metadata_size_mvcvui;/* v7 and v8 */
-	void *d_mvc_view_id;
-	void *d_frame_pack_sei_avail;
-	void *d_frame_pack_arrgment_id;
-	void *d_frame_pack_sei_info;
-	void *d_frame_pack_grid_pos;
-	void *d_display_recovery_sei_info;/* v7 and v8 */
-	void *d_decoded_recovery_sei_info;/* v7 and v8 */
-	void *d_display_first_addr;/* only v7 */
-	void *d_display_second_addr;/* only v7 */
-	void *d_display_third_addr;/* only v7 */
-	void *d_decoded_first_addr;/* only v7 */
-	void *d_decoded_second_addr;/* only v7 */
-	void *d_decoded_third_addr;/* only v7 */
-	void *d_used_dpb_flag_upper;/* v7 and v8 */
-	void *d_used_dpb_flag_lower;/* v7 and v8 */
+	volatile void __iomem *d_crc_ctrl;
+	volatile void __iomem *d_dec_options;
+	volatile void __iomem *d_display_delay;
+	volatile void __iomem *d_set_frame_width;
+	volatile void __iomem *d_set_frame_height;
+	volatile void __iomem *d_sei_enable;
+	volatile void __iomem *d_min_num_dpb;
+	volatile void __iomem *d_min_first_plane_dpb_size;
+	volatile void __iomem *d_min_second_plane_dpb_size;
+	volatile void __iomem *d_min_third_plane_dpb_size;/* only v8 */
+	volatile void __iomem *d_min_num_mv;
+	volatile void __iomem *d_mvc_num_views;
+	volatile void __iomem *d_min_num_dis;/* only v7 */
+	volatile void __iomem *d_min_first_dis_size;/* only v7 */
+	volatile void __iomem *d_min_second_dis_size;/* only v7 */
+	volatile void __iomem *d_min_third_dis_size;/* only v7 */
+	volatile void __iomem *d_post_filter_luma_dpb0;/*  v7 and v8 */
+	volatile void __iomem *d_post_filter_luma_dpb1;/* v7 and v8 */
+	volatile void __iomem *d_post_filter_luma_dpb2;/* only v7 */
+	volatile void __iomem *d_post_filter_chroma_dpb0;/* v7 and v8 */
+	volatile void __iomem *d_post_filter_chroma_dpb1;/* v7 and v8 */
+	volatile void __iomem *d_post_filter_chroma_dpb2;/* only v7 */
+	volatile void __iomem *d_num_dpb;
+	volatile void __iomem *d_num_mv;
+	volatile void __iomem *d_init_buffer_options;
+	volatile void __iomem *d_first_plane_dpb_stride_size;/* only v8 */
+	volatile void __iomem *d_second_plane_dpb_stride_size;/* only v8 */
+	volatile void __iomem *d_third_plane_dpb_stride_size;/* only v8 */
+	volatile void __iomem *d_first_plane_dpb_size;
+	volatile void __iomem *d_second_plane_dpb_size;
+	volatile void __iomem *d_third_plane_dpb_size;/* only v8 */
+	volatile void __iomem *d_mv_buffer_size;
+	volatile void __iomem *d_first_plane_dpb;
+	volatile void __iomem *d_second_plane_dpb;
+	volatile void __iomem *d_third_plane_dpb;
+	volatile void __iomem *d_mv_buffer;
+	volatile void __iomem *d_scratch_buffer_addr;
+	volatile void __iomem *d_scratch_buffer_size;
+	volatile void __iomem *d_metadata_buffer_addr;
+	volatile void __iomem *d_metadata_buffer_size;
+	volatile void __iomem *d_nal_start_options;/* v7 and v8 */
+	volatile void __iomem *d_cpb_buffer_addr;
+	volatile void __iomem *d_cpb_buffer_size;
+	volatile void __iomem *d_available_dpb_flag_upper;
+	volatile void __iomem *d_available_dpb_flag_lower;
+	volatile void __iomem *d_cpb_buffer_offset;
+	volatile void __iomem *d_slice_if_enable;
+	volatile void __iomem *d_picture_tag;
+	volatile void __iomem *d_stream_data_size;
+	volatile void __iomem *d_dynamic_dpb_flag_upper;/* v7 and v8 */
+	volatile void __iomem *d_dynamic_dpb_flag_lower;/* v7 and v8 */
+	volatile void __iomem *d_display_frame_width;
+	volatile void __iomem *d_display_frame_height;
+	volatile void __iomem *d_display_status;
+	volatile void __iomem *d_display_first_plane_addr;
+	volatile void __iomem *d_display_second_plane_addr;
+	volatile void __iomem *d_display_third_plane_addr;/* only v8 */
+	volatile void __iomem *d_display_frame_type;
+	volatile void __iomem *d_display_crop_info1;
+	volatile void __iomem *d_display_crop_info2;
+	volatile void __iomem *d_display_picture_profile;
+	volatile void __iomem *d_display_luma_crc;/* v7 and v8 */
+	volatile void __iomem *d_display_chroma0_crc;/* v7 and v8 */
+	volatile void __iomem *d_display_chroma1_crc;/* only v8 */
+	volatile void __iomem *d_display_luma_crc_top;/* only v6 */
+	volatile void __iomem *d_display_chroma_crc_top;/* only v6 */
+	volatile void __iomem *d_display_luma_crc_bot;/* only v6 */
+	volatile void __iomem *d_display_chroma_crc_bot;/* only v6 */
+	volatile void __iomem *d_display_aspect_ratio;
+	volatile void __iomem *d_display_extended_ar;
+	volatile void __iomem *d_decoded_frame_width;
+	volatile void __iomem *d_decoded_frame_height;
+	volatile void __iomem *d_decoded_status;
+	volatile void __iomem *d_decoded_first_plane_addr;
+	volatile void __iomem *d_decoded_second_plane_addr;
+	volatile void __iomem *d_decoded_third_plane_addr;/* only v8 */
+	volatile void __iomem *d_decoded_frame_type;
+	volatile void __iomem *d_decoded_crop_info1;
+	volatile void __iomem *d_decoded_crop_info2;
+	volatile void __iomem *d_decoded_picture_profile;
+	volatile void __iomem *d_decoded_nal_size;
+	volatile void __iomem *d_decoded_luma_crc;
+	volatile void __iomem *d_decoded_chroma0_crc;
+	volatile void __iomem *d_decoded_chroma1_crc;/* only v8 */
+	volatile void __iomem *d_ret_picture_tag_top;
+	volatile void __iomem *d_ret_picture_tag_bot;
+	volatile void __iomem *d_ret_picture_time_top;
+	volatile void __iomem *d_ret_picture_time_bot;
+	volatile void __iomem *d_chroma_format;
+	volatile void __iomem *d_vc1_info;/* v7 and v8 */
+	volatile void __iomem *d_mpeg4_info;
+	volatile void __iomem *d_h264_info;
+	volatile void __iomem *d_metadata_addr_concealed_mb;
+	volatile void __iomem *d_metadata_size_concealed_mb;
+	volatile void __iomem *d_metadata_addr_vc1_param;
+	volatile void __iomem *d_metadata_size_vc1_param;
+	volatile void __iomem *d_metadata_addr_sei_nal;
+	volatile void __iomem *d_metadata_size_sei_nal;
+	volatile void __iomem *d_metadata_addr_vui;
+	volatile void __iomem *d_metadata_size_vui;
+	volatile void __iomem *d_metadata_addr_mvcvui;/* v7 and v8 */
+	volatile void __iomem *d_metadata_size_mvcvui;/* v7 and v8 */
+	volatile void __iomem *d_mvc_view_id;
+	volatile void __iomem *d_frame_pack_sei_avail;
+	volatile void __iomem *d_frame_pack_arrgment_id;
+	volatile void __iomem *d_frame_pack_sei_info;
+	volatile void __iomem *d_frame_pack_grid_pos;
+	volatile void __iomem *d_display_recovery_sei_info;/* v7 and v8 */
+	volatile void __iomem *d_decoded_recovery_sei_info;/* v7 and v8 */
+	volatile void __iomem *d_display_first_addr;/* only v7 */
+	volatile void __iomem *d_display_second_addr;/* only v7 */
+	volatile void __iomem *d_display_third_addr;/* only v7 */
+	volatile void __iomem *d_decoded_first_addr;/* only v7 */
+	volatile void __iomem *d_decoded_second_addr;/* only v7 */
+	volatile void __iomem *d_decoded_third_addr;/* only v7 */
+	volatile void __iomem *d_used_dpb_flag_upper;/* v7 and v8 */
+	volatile void __iomem *d_used_dpb_flag_lower;/* v7 and v8 */
 
 	/* encoder registers */
-	void *e_frame_width;
-	void *e_frame_height;
-	void *e_cropped_frame_width;
-	void *e_cropped_frame_height;
-	void *e_frame_crop_offset;
-	void *e_enc_options;
-	void *e_picture_profile;
-	void *e_vbv_buffer_size;
-	void *e_vbv_init_delay;
-	void *e_fixed_picture_qp;
-	void *e_rc_config;
-	void *e_rc_qp_bound;
-	void *e_rc_qp_bound_pb;/* v7 and v8 */
-	void *e_rc_mode;
-	void *e_mb_rc_config;
-	void *e_padding_ctrl;
-	void *e_air_threshold;
-	void *e_mv_hor_range;
-	void *e_mv_ver_range;
-	void *e_num_dpb;
-	void *e_luma_dpb;
-	void *e_chroma_dpb;
-	void *e_me_buffer;
-	void *e_scratch_buffer_addr;
-	void *e_scratch_buffer_size;
-	void *e_tmv_buffer0;
-	void *e_tmv_buffer1;
-	void *e_ir_buffer_addr;/* v7 and v8 */
-	void *e_source_first_plane_addr;
-	void *e_source_second_plane_addr;
-	void *e_source_third_plane_addr;/* v7 and v8 */
-	void *e_source_first_plane_stride;/* v7 and v8 */
-	void *e_source_second_plane_stride;/* v7 and v8 */
-	void *e_source_third_plane_stride;/* v7 and v8 */
-	void *e_stream_buffer_addr;
-	void *e_stream_buffer_size;
-	void *e_roi_buffer_addr;
-	void *e_param_change;
-	void *e_ir_size;
-	void *e_gop_config;
-	void *e_mslice_mode;
-	void *e_mslice_size_mb;
-	void *e_mslice_size_bits;
-	void *e_frame_insertion;
-	void *e_rc_frame_rate;
-	void *e_rc_bit_rate;
-	void *e_rc_roi_ctrl;
-	void *e_picture_tag;
-	void *e_bit_count_enable;
-	void *e_max_bit_count;
-	void *e_min_bit_count;
-	void *e_metadata_buffer_addr;
-	void *e_metadata_buffer_size;
-	void *e_encoded_source_first_plane_addr;
-	void *e_encoded_source_second_plane_addr;
-	void *e_encoded_source_third_plane_addr;/* v7 and v8 */
-	void *e_stream_size;
-	void *e_slice_type;
-	void *e_picture_count;
-	void *e_ret_picture_tag;
-	void *e_stream_buffer_write_pointer; /*  only v6 */
-	void *e_recon_luma_dpb_addr;
-	void *e_recon_chroma_dpb_addr;
-	void *e_metadata_addr_enc_slice;
-	void *e_metadata_size_enc_slice;
-	void *e_mpeg4_options;
-	void *e_mpeg4_hec_period;
-	void *e_aspect_ratio;
-	void *e_extended_sar;
-	void *e_h264_options;
-	void *e_h264_options_2;/* v7 and v8 */
-	void *e_h264_lf_alpha_offset;
-	void *e_h264_lf_beta_offset;
-	void *e_h264_i_period;
-	void *e_h264_fmo_slice_grp_map_type;
-	void *e_h264_fmo_num_slice_grp_minus1;
-	void *e_h264_fmo_slice_grp_change_dir;
-	void *e_h264_fmo_slice_grp_change_rate_minus1;
-	void *e_h264_fmo_run_length_minus1_0;
-	void *e_h264_aso_slice_order_0;
-	void *e_h264_chroma_qp_offset;
-	void *e_h264_num_t_layer;
-	void *e_h264_hierarchical_qp_layer0;
-	void *e_h264_frame_packing_sei_info;
-	void *e_h264_nal_control;/* v7 and v8 */
-	void *e_mvc_frame_qp_view1;
-	void *e_mvc_rc_bit_rate_view1;
-	void *e_mvc_rc_qbound_view1;
-	void *e_mvc_rc_mode_view1;
-	void *e_mvc_inter_view_prediction_on;
-	void *e_vp8_options;/* v7 and v8 */
-	void *e_vp8_filter_options;/* v7 and v8 */
-	void *e_vp8_golden_frame_option;/* v7 and v8 */
-	void *e_vp8_num_t_layer;/* v7 and v8 */
-	void *e_vp8_hierarchical_qp_layer0;/* v7 and v8 */
-	void *e_vp8_hierarchical_qp_layer1;/* v7 and v8 */
-	void *e_vp8_hierarchical_qp_layer2;/* v7 and v8 */
+	volatile void __iomem *e_frame_width;
+	volatile void __iomem *e_frame_height;
+	volatile void __iomem *e_cropped_frame_width;
+	volatile void __iomem *e_cropped_frame_height;
+	volatile void __iomem *e_frame_crop_offset;
+	volatile void __iomem *e_enc_options;
+	volatile void __iomem *e_picture_profile;
+	volatile void __iomem *e_vbv_buffer_size;
+	volatile void __iomem *e_vbv_init_delay;
+	volatile void __iomem *e_fixed_picture_qp;
+	volatile void __iomem *e_rc_config;
+	volatile void __iomem *e_rc_qp_bound;
+	volatile void __iomem *e_rc_qp_bound_pb;/* v7 and v8 */
+	volatile void __iomem *e_rc_mode;
+	volatile void __iomem *e_mb_rc_config;
+	volatile void __iomem *e_padding_ctrl;
+	volatile void __iomem *e_air_threshold;
+	volatile void __iomem *e_mv_hor_range;
+	volatile void __iomem *e_mv_ver_range;
+	volatile void __iomem *e_num_dpb;
+	volatile void __iomem *e_luma_dpb;
+	volatile void __iomem *e_chroma_dpb;
+	volatile void __iomem *e_me_buffer;
+	volatile void __iomem *e_scratch_buffer_addr;
+	volatile void __iomem *e_scratch_buffer_size;
+	volatile void __iomem *e_tmv_buffer0;
+	volatile void __iomem *e_tmv_buffer1;
+	volatile void __iomem *e_ir_buffer_addr;/* v7 and v8 */
+	volatile void __iomem *e_source_first_plane_addr;
+	volatile void __iomem *e_source_second_plane_addr;
+	volatile void __iomem *e_source_third_plane_addr;/* v7 and v8 */
+	volatile void __iomem *e_source_first_plane_stride;/* v7 and v8 */
+	volatile void __iomem *e_source_second_plane_stride;/* v7 and v8 */
+	volatile void __iomem *e_source_third_plane_stride;/* v7 and v8 */
+	volatile void __iomem *e_stream_buffer_addr;
+	volatile void __iomem *e_stream_buffer_size;
+	volatile void __iomem *e_roi_buffer_addr;
+	volatile void __iomem *e_param_change;
+	volatile void __iomem *e_ir_size;
+	volatile void __iomem *e_gop_config;
+	volatile void __iomem *e_mslice_mode;
+	volatile void __iomem *e_mslice_size_mb;
+	volatile void __iomem *e_mslice_size_bits;
+	volatile void __iomem *e_frame_insertion;
+	volatile void __iomem *e_rc_frame_rate;
+	volatile void __iomem *e_rc_bit_rate;
+	volatile void __iomem *e_rc_roi_ctrl;
+	volatile void __iomem *e_picture_tag;
+	volatile void __iomem *e_bit_count_enable;
+	volatile void __iomem *e_max_bit_count;
+	volatile void __iomem *e_min_bit_count;
+	volatile void __iomem *e_metadata_buffer_addr;
+	volatile void __iomem *e_metadata_buffer_size;
+	volatile void __iomem *e_encoded_source_first_plane_addr;
+	volatile void __iomem *e_encoded_source_second_plane_addr;
+	volatile void __iomem *e_encoded_source_third_plane_addr;/* v7 and v8 */
+	volatile void __iomem *e_stream_size;
+	volatile void __iomem *e_slice_type;
+	volatile void __iomem *e_picture_count;
+	volatile void __iomem *e_ret_picture_tag;
+	volatile void __iomem *e_stream_buffer_write_pointer; /*  only v6 */
+	volatile void __iomem *e_recon_luma_dpb_addr;
+	volatile void __iomem *e_recon_chroma_dpb_addr;
+	volatile void __iomem *e_metadata_addr_enc_slice;
+	volatile void __iomem *e_metadata_size_enc_slice;
+	volatile void __iomem *e_mpeg4_options;
+	volatile void __iomem *e_mpeg4_hec_period;
+	volatile void __iomem *e_aspect_ratio;
+	volatile void __iomem *e_extended_sar;
+	volatile void __iomem *e_h264_options;
+	volatile void __iomem *e_h264_options_2;/* v7 and v8 */
+	volatile void __iomem *e_h264_lf_alpha_offset;
+	volatile void __iomem *e_h264_lf_beta_offset;
+	volatile void __iomem *e_h264_i_period;
+	volatile void __iomem *e_h264_fmo_slice_grp_map_type;
+	volatile void __iomem *e_h264_fmo_num_slice_grp_minus1;
+	volatile void __iomem *e_h264_fmo_slice_grp_change_dir;
+	volatile void __iomem *e_h264_fmo_slice_grp_change_rate_minus1;
+	volatile void __iomem *e_h264_fmo_run_length_minus1_0;
+	volatile void __iomem *e_h264_aso_slice_order_0;
+	volatile void __iomem *e_h264_chroma_qp_offset;
+	volatile void __iomem *e_h264_num_t_layer;
+	volatile void __iomem *e_h264_hierarchical_qp_layer0;
+	volatile void __iomem *e_h264_frame_packing_sei_info;
+	volatile void __iomem *e_h264_nal_control;/* v7 and v8 */
+	volatile void __iomem *e_mvc_frame_qp_view1;
+	volatile void __iomem *e_mvc_rc_bit_rate_view1;
+	volatile void __iomem *e_mvc_rc_qbound_view1;
+	volatile void __iomem *e_mvc_rc_mode_view1;
+	volatile void __iomem *e_mvc_inter_view_prediction_on;
+	volatile void __iomem *e_vp8_options;/* v7 and v8 */
+	volatile void __iomem *e_vp8_filter_options;/* v7 and v8 */
+	volatile void __iomem *e_vp8_golden_frame_option;/* v7 and v8 */
+	volatile void __iomem *e_vp8_num_t_layer;/* v7 and v8 */
+	volatile void __iomem *e_vp8_hierarchical_qp_layer0;/* v7 and v8 */
+	volatile void __iomem *e_vp8_hierarchical_qp_layer1;/* v7 and v8 */
+	volatile void __iomem *e_vp8_hierarchical_qp_layer2;/* v7 and v8 */
 };
 
 struct s5p_mfc_hw_ops {
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c
index 58ec7bb26ebc..7cf07963187d 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v5.c
@@ -228,6 +228,7 @@ static int s5p_mfc_alloc_instance_buffer_v5(struct s5p_mfc_ctx *ctx)
 	ret = s5p_mfc_alloc_priv_buf(dev->mem_dev_l, &ctx->shm);
 	if (ret) {
 		mfc_err("Failed to allocate shared memory buffer\n");
+		s5p_mfc_release_priv_buf(dev->mem_dev_l, &ctx->ctx);
 		return ret;
 	}
 
@@ -262,7 +263,7 @@ static void s5p_mfc_release_dev_context_buffer_v5(struct s5p_mfc_dev *dev)
 static void s5p_mfc_write_info_v5(struct s5p_mfc_ctx *ctx, unsigned int data,
 			unsigned int ofs)
 {
-	writel(data, (ctx->shm.virt + ofs));
+	writel(data, (volatile void __iomem *)(ctx->shm.virt + ofs));
 	wmb();
 }
 
@@ -270,7 +271,7 @@ static unsigned int s5p_mfc_read_info_v5(struct s5p_mfc_ctx *ctx,
 				unsigned int ofs)
 {
 	rmb();
-	return readl(ctx->shm.virt + ofs);
+	return readl((volatile void __iomem *)(ctx->shm.virt + ofs));
 }
 
 static void s5p_mfc_dec_calc_dpb_size_v5(struct s5p_mfc_ctx *ctx)
@@ -377,7 +378,7 @@ static int s5p_mfc_set_dec_stream_buffer_v5(struct s5p_mfc_ctx *ctx,
 /* Set decoding frame buffer */
 static int s5p_mfc_set_dec_frame_buffer_v5(struct s5p_mfc_ctx *ctx)
 {
-	unsigned int frame_size, i;
+	unsigned int frame_size_lu, i;
 	unsigned int frame_size_ch, frame_size_mv;
 	struct s5p_mfc_dev *dev = ctx->dev;
 	unsigned int dpb;
@@ -465,23 +466,23 @@ static int s5p_mfc_set_dec_frame_buffer_v5(struct s5p_mfc_ctx *ctx)
 			ctx->codec_mode);
 		return -EINVAL;
 	}
-	frame_size = ctx->luma_size;
+	frame_size_lu = ctx->luma_size;
 	frame_size_ch = ctx->chroma_size;
 	frame_size_mv = ctx->mv_size;
-	mfc_debug(2, "Frm size: %d ch: %d mv: %d\n", frame_size, frame_size_ch,
+	mfc_debug(2, "Frm size: %d ch: %d mv: %d\n", frame_size_lu, frame_size_ch,
 								frame_size_mv);
 	for (i = 0; i < ctx->total_dpb_count; i++) {
 		/* Bank2 */
-		mfc_debug(2, "Luma %d: %x\n", i,
+		mfc_debug(2, "Luma %d: %zx\n", i,
 					ctx->dst_bufs[i].cookie.raw.luma);
 		mfc_write(dev, OFFSETB(ctx->dst_bufs[i].cookie.raw.luma),
 						S5P_FIMV_DEC_LUMA_ADR + i * 4);
-		mfc_debug(2, "\tChroma %d: %x\n", i,
+		mfc_debug(2, "\tChroma %d: %zx\n", i,
 					ctx->dst_bufs[i].cookie.raw.chroma);
 		mfc_write(dev, OFFSETA(ctx->dst_bufs[i].cookie.raw.chroma),
 					       S5P_FIMV_DEC_CHROMA_ADR + i * 4);
 		if (ctx->codec_mode == S5P_MFC_CODEC_H264_DEC) {
-			mfc_debug(2, "\tBuf2: %x, size: %d\n",
+			mfc_debug(2, "\tBuf2: %zx, size: %d\n",
 							buf_addr2, buf_size2);
 			mfc_write(dev, OFFSETB(buf_addr2),
 						S5P_FIMV_H264_MV_ADR + i * 4);
@@ -489,14 +490,14 @@ static int s5p_mfc_set_dec_frame_buffer_v5(struct s5p_mfc_ctx *ctx)
 			buf_size2 -= frame_size_mv;
 		}
 	}
-	mfc_debug(2, "Buf1: %u, buf_size1: %d\n", buf_addr1, buf_size1);
+	mfc_debug(2, "Buf1: %zu, buf_size1: %d\n", buf_addr1, buf_size1);
 	mfc_debug(2, "Buf 1/2 size after: %d/%d (frames %d)\n",
 			buf_size1,  buf_size2, ctx->total_dpb_count);
 	if (buf_size1 < 0 || buf_size2 < 0) {
 		mfc_debug(2, "Not enough memory has been allocated\n");
 		return -ENOMEM;
 	}
-	s5p_mfc_write_info_v5(ctx, frame_size, ALLOC_LUMA_DPB_SIZE);
+	s5p_mfc_write_info_v5(ctx, frame_size_lu, ALLOC_LUMA_DPB_SIZE);
 	s5p_mfc_write_info_v5(ctx, frame_size_ch, ALLOC_CHROMA_DPB_SIZE);
 	if (ctx->codec_mode == S5P_MFC_CODEC_H264_DEC)
 		s5p_mfc_write_info_v5(ctx, frame_size_mv, ALLOC_MV_SIZE);
@@ -566,7 +567,7 @@ static int s5p_mfc_set_enc_ref_buffer_v5(struct s5p_mfc_ctx *ctx)
 		enc_ref_c_size = ALIGN(guard_width * guard_height,
 				       S5P_FIMV_NV12MT_SALIGN);
 	}
-	mfc_debug(2, "buf_size1: %d, buf_size2: %d\n", buf_size1, buf_size2);
+	mfc_debug(2, "buf_size1: %zu, buf_size2: %zu\n", buf_size1, buf_size2);
 	switch (ctx->codec_mode) {
 	case S5P_MFC_CODEC_H264_ENC:
 		for (i = 0; i < 2; i++) {
@@ -605,7 +606,7 @@ static int s5p_mfc_set_enc_ref_buffer_v5(struct s5p_mfc_ctx *ctx)
 					S5P_FIMV_H264_NBOR_INFO_ADR);
 		buf_addr1 += S5P_FIMV_ENC_NBORINFO_SIZE;
 		buf_size1 -= S5P_FIMV_ENC_NBORINFO_SIZE;
-		mfc_debug(2, "buf_size1: %d, buf_size2: %d\n",
+		mfc_debug(2, "buf_size1: %zu, buf_size2: %zu\n",
 			buf_size1, buf_size2);
 		break;
 	case S5P_MFC_CODEC_MPEG4_ENC:
@@ -636,7 +637,7 @@ static int s5p_mfc_set_enc_ref_buffer_v5(struct s5p_mfc_ctx *ctx)
 						S5P_FIMV_MPEG4_ACDC_COEF_ADR);
 		buf_addr1 += S5P_FIMV_ENC_ACDCCOEF_SIZE;
 		buf_size1 -= S5P_FIMV_ENC_ACDCCOEF_SIZE;
-		mfc_debug(2, "buf_size1: %d, buf_size2: %d\n",
+		mfc_debug(2, "buf_size1: %zu, buf_size2: %zu\n",
 			buf_size1, buf_size2);
 		break;
 	case S5P_MFC_CODEC_H263_ENC:
@@ -662,7 +663,7 @@ static int s5p_mfc_set_enc_ref_buffer_v5(struct s5p_mfc_ctx *ctx)
 		mfc_write(dev, OFFSETA(buf_addr1), S5P_FIMV_H263_ACDC_COEF_ADR);
 		buf_addr1 += S5P_FIMV_ENC_ACDCCOEF_SIZE;
 		buf_size1 -= S5P_FIMV_ENC_ACDCCOEF_SIZE;
-		mfc_debug(2, "buf_size1: %d, buf_size2: %d\n",
+		mfc_debug(2, "buf_size1: %zu, buf_size2: %zu\n",
 			buf_size1, buf_size2);
 		break;
 	default:
@@ -1186,7 +1187,6 @@ static int s5p_mfc_run_dec_frame(struct s5p_mfc_ctx *ctx, int last_frame)
 	struct s5p_mfc_dev *dev = ctx->dev;
 	struct s5p_mfc_buf *temp_vb;
 	unsigned long flags;
-	unsigned int index;
 
 	if (ctx->state == MFCINST_FINISHING) {
 		last_frame = MFC_DEC_LAST_FRAME;
@@ -1211,7 +1211,6 @@ static int s5p_mfc_run_dec_frame(struct s5p_mfc_ctx *ctx, int last_frame)
 		vb2_dma_contig_plane_dma_addr(temp_vb->b, 0),
 		ctx->consumed_stream, temp_vb->b->v4l2_planes[0].bytesused);
 	spin_unlock_irqrestore(&dev->irqlock, flags);
-	index = temp_vb->b->v4l2_buf.index;
 	dev->curr_ctx = ctx->num;
 	s5p_mfc_clean_ctx_int_flags(ctx);
 	if (temp_vb->b->v4l2_planes[0].bytesused == 0) {
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c
index c1c12f8d8f68..8798b14bacce 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_opr_v6.c
@@ -43,11 +43,6 @@
 	} while (0)
 #endif /* S5P_MFC_DEBUG_REGWRITE */
 
-#define READL(reg) \
-	(WARN_ON_ONCE(!(reg)) ? 0 : readl(reg))
-#define WRITEL(data, reg) \
-	(WARN_ON_ONCE(!(reg)) ? 0 : writel((data), (reg)))
-
 #define IS_MFCV6_V2(dev) (!IS_MFCV7_PLUS(dev) && dev->fw_ver == MFC_FW_V2)
 
 /* Allocate temporary buffers for decoding */
@@ -105,7 +100,7 @@ static int s5p_mfc_alloc_codec_buffers_v6(struct s5p_mfc_ctx *ctx)
 						mb_width, mb_height),
 						S5P_FIMV_ME_BUFFER_ALIGN_V6);
 
-		mfc_debug(2, "recon luma size: %d chroma size: %d\n",
+		mfc_debug(2, "recon luma size: %zu chroma size: %zu\n",
 			  ctx->luma_dpb_size, ctx->chroma_dpb_size);
 	} else {
 		return -EINVAL;
@@ -416,10 +411,10 @@ static int s5p_mfc_set_dec_stream_buffer_v6(struct s5p_mfc_ctx *ctx,
 	mfc_debug(2, "inst_no: %d, buf_addr: 0x%08x,\n"
 		"buf_size: 0x%08x (%d)\n",
 		ctx->inst_no, buf_addr, strm_size, strm_size);
-	WRITEL(strm_size, mfc_regs->d_stream_data_size);
-	WRITEL(buf_addr, mfc_regs->d_cpb_buffer_addr);
-	WRITEL(buf_size->cpb, mfc_regs->d_cpb_buffer_size);
-	WRITEL(start_num_byte, mfc_regs->d_cpb_buffer_offset);
+	writel(strm_size, mfc_regs->d_stream_data_size);
+	writel(buf_addr, mfc_regs->d_cpb_buffer_addr);
+	writel(buf_size->cpb, mfc_regs->d_cpb_buffer_size);
+	writel(start_num_byte, mfc_regs->d_cpb_buffer_offset);
 
 	mfc_debug_leave();
 	return 0;
@@ -443,17 +438,17 @@ static int s5p_mfc_set_dec_frame_buffer_v6(struct s5p_mfc_ctx *ctx)
 	mfc_debug(2, "Total DPB COUNT: %d\n", ctx->total_dpb_count);
 	mfc_debug(2, "Setting display delay to %d\n", ctx->display_delay);
 
-	WRITEL(ctx->total_dpb_count, mfc_regs->d_num_dpb);
-	WRITEL(ctx->luma_size, mfc_regs->d_first_plane_dpb_size);
-	WRITEL(ctx->chroma_size, mfc_regs->d_second_plane_dpb_size);
+	writel(ctx->total_dpb_count, mfc_regs->d_num_dpb);
+	writel(ctx->luma_size, mfc_regs->d_first_plane_dpb_size);
+	writel(ctx->chroma_size, mfc_regs->d_second_plane_dpb_size);
 
-	WRITEL(buf_addr1, mfc_regs->d_scratch_buffer_addr);
-	WRITEL(ctx->scratch_buf_size, mfc_regs->d_scratch_buffer_size);
+	writel(buf_addr1, mfc_regs->d_scratch_buffer_addr);
+	writel(ctx->scratch_buf_size, mfc_regs->d_scratch_buffer_size);
 
 	if (IS_MFCV8(dev)) {
-		WRITEL(ctx->img_width,
+		writel(ctx->img_width,
 			mfc_regs->d_first_plane_dpb_stride_size);
-		WRITEL(ctx->img_width,
+		writel(ctx->img_width,
 			mfc_regs->d_second_plane_dpb_stride_size);
 	}
 
@@ -462,8 +457,8 @@ static int s5p_mfc_set_dec_frame_buffer_v6(struct s5p_mfc_ctx *ctx)
 
 	if (ctx->codec_mode == S5P_FIMV_CODEC_H264_DEC ||
 			ctx->codec_mode == S5P_FIMV_CODEC_H264_MVC_DEC){
-		WRITEL(ctx->mv_size, mfc_regs->d_mv_buffer_size);
-		WRITEL(ctx->mv_count, mfc_regs->d_num_mv);
+		writel(ctx->mv_size, mfc_regs->d_mv_buffer_size);
+		writel(ctx->mv_count, mfc_regs->d_num_mv);
 	}
 
 	frame_size = ctx->luma_size;
@@ -474,13 +469,13 @@ static int s5p_mfc_set_dec_frame_buffer_v6(struct s5p_mfc_ctx *ctx)
 
 	for (i = 0; i < ctx->total_dpb_count; i++) {
 		/* Bank2 */
-		mfc_debug(2, "Luma %d: %x\n", i,
+		mfc_debug(2, "Luma %d: %zx\n", i,
 					ctx->dst_bufs[i].cookie.raw.luma);
-		WRITEL(ctx->dst_bufs[i].cookie.raw.luma,
+		writel(ctx->dst_bufs[i].cookie.raw.luma,
 				mfc_regs->d_first_plane_dpb + i * 4);
-		mfc_debug(2, "\tChroma %d: %x\n", i,
+		mfc_debug(2, "\tChroma %d: %zx\n", i,
 					ctx->dst_bufs[i].cookie.raw.chroma);
-		WRITEL(ctx->dst_bufs[i].cookie.raw.chroma,
+		writel(ctx->dst_bufs[i].cookie.raw.chroma,
 				mfc_regs->d_second_plane_dpb + i * 4);
 	}
 	if (ctx->codec_mode == S5P_MFC_CODEC_H264_DEC ||
@@ -492,23 +487,23 @@ static int s5p_mfc_set_dec_frame_buffer_v6(struct s5p_mfc_ctx *ctx)
 			align_gap = buf_addr1 - align_gap;
 			buf_size1 -= align_gap;
 
-			mfc_debug(2, "\tBuf1: %x, size: %d\n",
+			mfc_debug(2, "\tBuf1: %zx, size: %d\n",
 					buf_addr1, buf_size1);
-			WRITEL(buf_addr1, mfc_regs->d_mv_buffer + i * 4);
+			writel(buf_addr1, mfc_regs->d_mv_buffer + i * 4);
 			buf_addr1 += frame_size_mv;
 			buf_size1 -= frame_size_mv;
 		}
 	}
 
-	mfc_debug(2, "Buf1: %u, buf_size1: %d (frames %d)\n",
+	mfc_debug(2, "Buf1: %zu, buf_size1: %d (frames %d)\n",
 			buf_addr1, buf_size1, ctx->total_dpb_count);
 	if (buf_size1 < 0) {
 		mfc_debug(2, "Not enough memory has been allocated.\n");
 		return -ENOMEM;
 	}
 
-	WRITEL(ctx->inst_no, mfc_regs->instance_id);
-	s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
+	writel(ctx->inst_no, mfc_regs->instance_id);
+	s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
 			S5P_FIMV_CH_INIT_BUFS_V6, NULL);
 
 	mfc_debug(2, "After setting buffers.\n");
@@ -522,8 +517,8 @@ static int s5p_mfc_set_enc_stream_buffer_v6(struct s5p_mfc_ctx *ctx,
 	struct s5p_mfc_dev *dev = ctx->dev;
 	const struct s5p_mfc_regs *mfc_regs = dev->mfc_regs;
 
-	WRITEL(addr, mfc_regs->e_stream_buffer_addr); /* 16B align */
-	WRITEL(size, mfc_regs->e_stream_buffer_size);
+	writel(addr, mfc_regs->e_stream_buffer_addr); /* 16B align */
+	writel(size, mfc_regs->e_stream_buffer_size);
 
 	mfc_debug(2, "stream buf addr: 0x%08lx, size: 0x%d\n",
 		  addr, size);
@@ -537,8 +532,8 @@ static void s5p_mfc_set_enc_frame_buffer_v6(struct s5p_mfc_ctx *ctx,
 	struct s5p_mfc_dev *dev = ctx->dev;
 	const struct s5p_mfc_regs *mfc_regs = dev->mfc_regs;
 
-	WRITEL(y_addr, mfc_regs->e_source_first_plane_addr);
-	WRITEL(c_addr, mfc_regs->e_source_second_plane_addr);
+	writel(y_addr, mfc_regs->e_source_first_plane_addr);
+	writel(c_addr, mfc_regs->e_source_second_plane_addr);
 
 	mfc_debug(2, "enc src y buf addr: 0x%08lx\n", y_addr);
 	mfc_debug(2, "enc src c buf addr: 0x%08lx\n", c_addr);
@@ -551,11 +546,11 @@ static void s5p_mfc_get_enc_frame_buffer_v6(struct s5p_mfc_ctx *ctx,
 	const struct s5p_mfc_regs *mfc_regs = dev->mfc_regs;
 	unsigned long enc_recon_y_addr, enc_recon_c_addr;
 
-	*y_addr = READL(mfc_regs->e_encoded_source_first_plane_addr);
-	*c_addr = READL(mfc_regs->e_encoded_source_second_plane_addr);
+	*y_addr = readl(mfc_regs->e_encoded_source_first_plane_addr);
+	*c_addr = readl(mfc_regs->e_encoded_source_second_plane_addr);
 
-	enc_recon_y_addr = READL(mfc_regs->e_recon_luma_dpb_addr);
-	enc_recon_c_addr = READL(mfc_regs->e_recon_chroma_dpb_addr);
+	enc_recon_y_addr = readl(mfc_regs->e_recon_luma_dpb_addr);
+	enc_recon_c_addr = readl(mfc_regs->e_recon_chroma_dpb_addr);
 
 	mfc_debug(2, "recon y addr: 0x%08lx\n", enc_recon_y_addr);
 	mfc_debug(2, "recon c addr: 0x%08lx\n", enc_recon_c_addr);
@@ -577,36 +572,36 @@ static int s5p_mfc_set_enc_ref_buffer_v6(struct s5p_mfc_ctx *ctx)
 	mfc_debug(2, "Buf1: %p (%d)\n", (void *)buf_addr1, buf_size1);
 
 	for (i = 0; i < ctx->pb_count; i++) {
-		WRITEL(buf_addr1, mfc_regs->e_luma_dpb + (4 * i));
+		writel(buf_addr1, mfc_regs->e_luma_dpb + (4 * i));
 		buf_addr1 += ctx->luma_dpb_size;
-		WRITEL(buf_addr1, mfc_regs->e_chroma_dpb + (4 * i));
+		writel(buf_addr1, mfc_regs->e_chroma_dpb + (4 * i));
 		buf_addr1 += ctx->chroma_dpb_size;
-		WRITEL(buf_addr1, mfc_regs->e_me_buffer + (4 * i));
+		writel(buf_addr1, mfc_regs->e_me_buffer + (4 * i));
 		buf_addr1 += ctx->me_buffer_size;
 		buf_size1 -= (ctx->luma_dpb_size + ctx->chroma_dpb_size +
 			ctx->me_buffer_size);
 	}
 
-	WRITEL(buf_addr1, mfc_regs->e_scratch_buffer_addr);
-	WRITEL(ctx->scratch_buf_size, mfc_regs->e_scratch_buffer_size);
+	writel(buf_addr1, mfc_regs->e_scratch_buffer_addr);
+	writel(ctx->scratch_buf_size, mfc_regs->e_scratch_buffer_size);
 	buf_addr1 += ctx->scratch_buf_size;
 	buf_size1 -= ctx->scratch_buf_size;
 
-	WRITEL(buf_addr1, mfc_regs->e_tmv_buffer0);
+	writel(buf_addr1, mfc_regs->e_tmv_buffer0);
 	buf_addr1 += ctx->tmv_buffer_size >> 1;
-	WRITEL(buf_addr1, mfc_regs->e_tmv_buffer1);
+	writel(buf_addr1, mfc_regs->e_tmv_buffer1);
 	buf_addr1 += ctx->tmv_buffer_size >> 1;
 	buf_size1 -= ctx->tmv_buffer_size;
 
-	mfc_debug(2, "Buf1: %u, buf_size1: %d (ref frames %d)\n",
+	mfc_debug(2, "Buf1: %zu, buf_size1: %d (ref frames %d)\n",
 			buf_addr1, buf_size1, ctx->pb_count);
 	if (buf_size1 < 0) {
 		mfc_debug(2, "Not enough memory has been allocated.\n");
 		return -ENOMEM;
 	}
 
-	WRITEL(ctx->inst_no, mfc_regs->instance_id);
-	s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
+	writel(ctx->inst_no, mfc_regs->instance_id);
+	s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
 			S5P_FIMV_CH_INIT_BUFS_V6, NULL);
 
 	mfc_debug_leave();
@@ -621,15 +616,15 @@ static int s5p_mfc_set_slice_mode(struct s5p_mfc_ctx *ctx)
 
 	/* multi-slice control */
 	/* multi-slice MB number or bit size */
-	WRITEL(ctx->slice_mode, mfc_regs->e_mslice_mode);
+	writel(ctx->slice_mode, mfc_regs->e_mslice_mode);
 	if (ctx->slice_mode == V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_MB) {
-		WRITEL(ctx->slice_size.mb, mfc_regs->e_mslice_size_mb);
+		writel(ctx->slice_size.mb, mfc_regs->e_mslice_size_mb);
 	} else if (ctx->slice_mode ==
 			V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_BYTES) {
-		WRITEL(ctx->slice_size.bits, mfc_regs->e_mslice_size_bits);
+		writel(ctx->slice_size.bits, mfc_regs->e_mslice_size_bits);
 	} else {
-		WRITEL(0x0, mfc_regs->e_mslice_size_mb);
-		WRITEL(0x0, mfc_regs->e_mslice_size_bits);
+		writel(0x0, mfc_regs->e_mslice_size_mb);
+		writel(0x0, mfc_regs->e_mslice_size_bits);
 	}
 
 	return 0;
@@ -645,21 +640,21 @@ static int s5p_mfc_set_enc_params(struct s5p_mfc_ctx *ctx)
 	mfc_debug_enter();
 
 	/* width */
-	WRITEL(ctx->img_width, mfc_regs->e_frame_width); /* 16 align */
+	writel(ctx->img_width, mfc_regs->e_frame_width); /* 16 align */
 	/* height */
-	WRITEL(ctx->img_height, mfc_regs->e_frame_height); /* 16 align */
+	writel(ctx->img_height, mfc_regs->e_frame_height); /* 16 align */
 
 	/* cropped width */
-	WRITEL(ctx->img_width, mfc_regs->e_cropped_frame_width);
+	writel(ctx->img_width, mfc_regs->e_cropped_frame_width);
 	/* cropped height */
-	WRITEL(ctx->img_height, mfc_regs->e_cropped_frame_height);
+	writel(ctx->img_height, mfc_regs->e_cropped_frame_height);
 	/* cropped offset */
-	WRITEL(0x0, mfc_regs->e_frame_crop_offset);
+	writel(0x0, mfc_regs->e_frame_crop_offset);
 
 	/* pictype : IDR period */
 	reg = 0;
 	reg |= p->gop_size & 0xFFFF;
-	WRITEL(reg, mfc_regs->e_gop_config);
+	writel(reg, mfc_regs->e_gop_config);
 
 	/* multi-slice control */
 	/* multi-slice MB number or bit size */
@@ -667,65 +662,65 @@ static int s5p_mfc_set_enc_params(struct s5p_mfc_ctx *ctx)
 	reg = 0;
 	if (p->slice_mode == V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_MB) {
 		reg |= (0x1 << 3);
-		WRITEL(reg, mfc_regs->e_enc_options);
+		writel(reg, mfc_regs->e_enc_options);
 		ctx->slice_size.mb = p->slice_mb;
 	} else if (p->slice_mode == V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_BYTES) {
 		reg |= (0x1 << 3);
-		WRITEL(reg, mfc_regs->e_enc_options);
+		writel(reg, mfc_regs->e_enc_options);
 		ctx->slice_size.bits = p->slice_bit;
 	} else {
 		reg &= ~(0x1 << 3);
-		WRITEL(reg, mfc_regs->e_enc_options);
+		writel(reg, mfc_regs->e_enc_options);
 	}
 
 	s5p_mfc_set_slice_mode(ctx);
 
 	/* cyclic intra refresh */
-	WRITEL(p->intra_refresh_mb, mfc_regs->e_ir_size);
-	reg = READL(mfc_regs->e_enc_options);
+	writel(p->intra_refresh_mb, mfc_regs->e_ir_size);
+	reg = readl(mfc_regs->e_enc_options);
 	if (p->intra_refresh_mb == 0)
 		reg &= ~(0x1 << 4);
 	else
 		reg |= (0x1 << 4);
-	WRITEL(reg, mfc_regs->e_enc_options);
+	writel(reg, mfc_regs->e_enc_options);
 
 	/* 'NON_REFERENCE_STORE_ENABLE' for debugging */
-	reg = READL(mfc_regs->e_enc_options);
+	reg = readl(mfc_regs->e_enc_options);
 	reg &= ~(0x1 << 9);
-	WRITEL(reg, mfc_regs->e_enc_options);
+	writel(reg, mfc_regs->e_enc_options);
 
 	/* memory structure cur. frame */
 	if (ctx->src_fmt->fourcc == V4L2_PIX_FMT_NV12M) {
 		/* 0: Linear, 1: 2D tiled*/
-		reg = READL(mfc_regs->e_enc_options);
+		reg = readl(mfc_regs->e_enc_options);
 		reg &= ~(0x1 << 7);
-		WRITEL(reg, mfc_regs->e_enc_options);
+		writel(reg, mfc_regs->e_enc_options);
 		/* 0: NV12(CbCr), 1: NV21(CrCb) */
-		WRITEL(0x0, mfc_regs->pixel_format);
+		writel(0x0, mfc_regs->pixel_format);
 	} else if (ctx->src_fmt->fourcc == V4L2_PIX_FMT_NV21M) {
 		/* 0: Linear, 1: 2D tiled*/
-		reg = READL(mfc_regs->e_enc_options);
+		reg = readl(mfc_regs->e_enc_options);
 		reg &= ~(0x1 << 7);
-		WRITEL(reg, mfc_regs->e_enc_options);
+		writel(reg, mfc_regs->e_enc_options);
 		/* 0: NV12(CbCr), 1: NV21(CrCb) */
-		WRITEL(0x1, mfc_regs->pixel_format);
+		writel(0x1, mfc_regs->pixel_format);
 	} else if (ctx->src_fmt->fourcc == V4L2_PIX_FMT_NV12MT_16X16) {
 		/* 0: Linear, 1: 2D tiled*/
-		reg = READL(mfc_regs->e_enc_options);
+		reg = readl(mfc_regs->e_enc_options);
 		reg |= (0x1 << 7);
-		WRITEL(reg, mfc_regs->e_enc_options);
+		writel(reg, mfc_regs->e_enc_options);
 		/* 0: NV12(CbCr), 1: NV21(CrCb) */
-		WRITEL(0x0, mfc_regs->pixel_format);
+		writel(0x0, mfc_regs->pixel_format);
 	}
 
 	/* memory structure recon. frame */
 	/* 0: Linear, 1: 2D tiled */
-	reg = READL(mfc_regs->e_enc_options);
+	reg = readl(mfc_regs->e_enc_options);
 	reg |= (0x1 << 8);
-	WRITEL(reg, mfc_regs->e_enc_options);
+	writel(reg, mfc_regs->e_enc_options);
 
 	/* padding control & value */
-	WRITEL(0x0, mfc_regs->e_padding_ctrl);
+	writel(0x0, mfc_regs->e_padding_ctrl);
 	if (p->pad) {
 		reg = 0;
 		/** enable */
@@ -736,64 +731,64 @@ static int s5p_mfc_set_enc_params(struct s5p_mfc_ctx *ctx)
 		reg |= ((p->pad_cb & 0xFF) << 8);
 		/** y value */
 		reg |= p->pad_luma & 0xFF;
-		WRITEL(reg, mfc_regs->e_padding_ctrl);
+		writel(reg, mfc_regs->e_padding_ctrl);
 	}
 
 	/* rate control config. */
 	reg = 0;
 	/* frame-level rate control */
 	reg |= ((p->rc_frame & 0x1) << 9);
-	WRITEL(reg, mfc_regs->e_rc_config);
+	writel(reg, mfc_regs->e_rc_config);
 
 	/* bit rate */
 	if (p->rc_frame)
-		WRITEL(p->rc_bitrate,
+		writel(p->rc_bitrate,
 			mfc_regs->e_rc_bit_rate);
 	else
-		WRITEL(1, mfc_regs->e_rc_bit_rate);
+		writel(1, mfc_regs->e_rc_bit_rate);
 
 	/* reaction coefficient */
 	if (p->rc_frame) {
 		if (p->rc_reaction_coeff < TIGHT_CBR_MAX) /* tight CBR */
-			WRITEL(1, mfc_regs->e_rc_mode);
+			writel(1, mfc_regs->e_rc_mode);
 		else					  /* loose CBR */
-			WRITEL(2, mfc_regs->e_rc_mode);
+			writel(2, mfc_regs->e_rc_mode);
 	}
 
 	/* seq header ctrl */
-	reg = READL(mfc_regs->e_enc_options);
+	reg = readl(mfc_regs->e_enc_options);
 	reg &= ~(0x1 << 2);
 	reg |= ((p->seq_hdr_mode & 0x1) << 2);
 
 	/* frame skip mode */
 	reg &= ~(0x3);
 	reg |= (p->frame_skip_mode & 0x3);
-	WRITEL(reg, mfc_regs->e_enc_options);
+	writel(reg, mfc_regs->e_enc_options);
 
 	/* 'DROP_CONTROL_ENABLE', disable */
-	reg = READL(mfc_regs->e_rc_config);
+	reg = readl(mfc_regs->e_rc_config);
 	reg &= ~(0x1 << 10);
-	WRITEL(reg, mfc_regs->e_rc_config);
+	writel(reg, mfc_regs->e_rc_config);
 
 	/* setting for MV range [16, 256] */
 	reg = (p->mv_h_range & S5P_FIMV_E_MV_RANGE_V6_MASK);
-	WRITEL(reg, mfc_regs->e_mv_hor_range);
+	writel(reg, mfc_regs->e_mv_hor_range);
 
 	reg = (p->mv_v_range & S5P_FIMV_E_MV_RANGE_V6_MASK);
-	WRITEL(reg, mfc_regs->e_mv_ver_range);
+	writel(reg, mfc_regs->e_mv_ver_range);
 
-	WRITEL(0x0, mfc_regs->e_frame_insertion);
-	WRITEL(0x0, mfc_regs->e_roi_buffer_addr);
-	WRITEL(0x0, mfc_regs->e_param_change);
-	WRITEL(0x0, mfc_regs->e_rc_roi_ctrl);
-	WRITEL(0x0, mfc_regs->e_picture_tag);
+	writel(0x0, mfc_regs->e_frame_insertion);
+	writel(0x0, mfc_regs->e_roi_buffer_addr);
+	writel(0x0, mfc_regs->e_param_change);
+	writel(0x0, mfc_regs->e_rc_roi_ctrl);
+	writel(0x0, mfc_regs->e_picture_tag);
 
-	WRITEL(0x0, mfc_regs->e_bit_count_enable);
-	WRITEL(0x0, mfc_regs->e_max_bit_count);
-	WRITEL(0x0, mfc_regs->e_min_bit_count);
+	writel(0x0, mfc_regs->e_bit_count_enable);
+	writel(0x0, mfc_regs->e_max_bit_count);
+	writel(0x0, mfc_regs->e_min_bit_count);
 
-	WRITEL(0x0, mfc_regs->e_metadata_buffer_addr);
-	WRITEL(0x0, mfc_regs->e_metadata_buffer_size);
+	writel(0x0, mfc_regs->e_metadata_buffer_addr);
+	writel(0x0, mfc_regs->e_metadata_buffer_size);
 
 	mfc_debug_leave();
 
@@ -814,10 +809,10 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx)
 	s5p_mfc_set_enc_params(ctx);
 
 	/* pictype : number of B */
-	reg = READL(mfc_regs->e_gop_config);
+	reg = readl(mfc_regs->e_gop_config);
 	reg &= ~(0x3 << 16);
 	reg |= ((p->num_b_frame & 0x3) << 16);
-	WRITEL(reg, mfc_regs->e_gop_config);
+	writel(reg, mfc_regs->e_gop_config);
 
 	/* profile & level */
 	reg = 0;
@@ -825,19 +820,19 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx)
 	reg |= ((p_h264->level & 0xFF) << 8);
 	/** profile - 0 ~ 3 */
 	reg |= p_h264->profile & 0x3F;
-	WRITEL(reg, mfc_regs->e_picture_profile);
+	writel(reg, mfc_regs->e_picture_profile);
 
 	/* rate control config. */
-	reg = READL(mfc_regs->e_rc_config);
+	reg = readl(mfc_regs->e_rc_config);
 	/** macroblock level rate control */
 	reg &= ~(0x1 << 8);
 	reg |= ((p->rc_mb & 0x1) << 8);
-	WRITEL(reg, mfc_regs->e_rc_config);
+	writel(reg, mfc_regs->e_rc_config);
 
 	/** frame QP */
 	reg &= ~(0x3F);
 	reg |= p_h264->rc_frame_qp & 0x3F;
-	WRITEL(reg, mfc_regs->e_rc_config);
+	writel(reg, mfc_regs->e_rc_config);
 
 	/* max & min value of QP */
 	reg = 0;
@@ -845,16 +840,16 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx)
 	reg |= ((p_h264->rc_max_qp & 0x3F) << 8);
 	/** min QP */
 	reg |= p_h264->rc_min_qp & 0x3F;
-	WRITEL(reg, mfc_regs->e_rc_qp_bound);
+	writel(reg, mfc_regs->e_rc_qp_bound);
 
 	/* other QPs */
-	WRITEL(0x0, mfc_regs->e_fixed_picture_qp);
+	writel(0x0, mfc_regs->e_fixed_picture_qp);
 	if (!p->rc_frame && !p->rc_mb) {
 		reg = 0;
 		reg |= ((p_h264->rc_b_frame_qp & 0x3F) << 16);
 		reg |= ((p_h264->rc_p_frame_qp & 0x3F) << 8);
 		reg |= p_h264->rc_frame_qp & 0x3F;
-		WRITEL(reg, mfc_regs->e_fixed_picture_qp);
+		writel(reg, mfc_regs->e_fixed_picture_qp);
 	}
 
 	/* frame rate */
@@ -862,38 +857,38 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx)
 		reg = 0;
 		reg |= ((p->rc_framerate_num & 0xFFFF) << 16);
 		reg |= p->rc_framerate_denom & 0xFFFF;
-		WRITEL(reg, mfc_regs->e_rc_frame_rate);
+		writel(reg, mfc_regs->e_rc_frame_rate);
 	}
 
 	/* vbv buffer size */
 	if (p->frame_skip_mode ==
 			V4L2_MPEG_MFC51_VIDEO_FRAME_SKIP_MODE_BUF_LIMIT) {
-		WRITEL(p_h264->cpb_size & 0xFFFF,
+		writel(p_h264->cpb_size & 0xFFFF,
 				mfc_regs->e_vbv_buffer_size);
 
 		if (p->rc_frame)
-			WRITEL(p->vbv_delay, mfc_regs->e_vbv_init_delay);
+			writel(p->vbv_delay, mfc_regs->e_vbv_init_delay);
 	}
 
 	/* interlace */
 	reg = 0;
 	reg |= ((p_h264->interlace & 0x1) << 3);
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 
 	/* height */
 	if (p_h264->interlace) {
-		WRITEL(ctx->img_height >> 1,
+		writel(ctx->img_height >> 1,
 				mfc_regs->e_frame_height); /* 32 align */
 		/* cropped height */
-		WRITEL(ctx->img_height >> 1,
+		writel(ctx->img_height >> 1,
 				mfc_regs->e_cropped_frame_height);
 	}
 
 	/* loop filter ctrl */
-	reg = READL(mfc_regs->e_h264_options);
+	reg = readl(mfc_regs->e_h264_options);
 	reg &= ~(0x3 << 1);
 	reg |= ((p_h264->loop_filter_mode & 0x3) << 1);
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 
 	/* loopfilter alpha offset */
 	if (p_h264->loop_filter_alpha < 0) {
@@ -903,7 +898,7 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx)
 		reg = 0x00;
 		reg |= (p_h264->loop_filter_alpha & 0xF);
 	}
-	WRITEL(reg, mfc_regs->e_h264_lf_alpha_offset);
+	writel(reg, mfc_regs->e_h264_lf_alpha_offset);
 
 	/* loopfilter beta offset */
 	if (p_h264->loop_filter_beta < 0) {
@@ -913,28 +908,28 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx)
 		reg = 0x00;
 		reg |= (p_h264->loop_filter_beta & 0xF);
 	}
-	WRITEL(reg, mfc_regs->e_h264_lf_beta_offset);
+	writel(reg, mfc_regs->e_h264_lf_beta_offset);
 
 	/* entropy coding mode */
-	reg = READL(mfc_regs->e_h264_options);
+	reg = readl(mfc_regs->e_h264_options);
 	reg &= ~(0x1);
 	reg |= p_h264->entropy_mode & 0x1;
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 
 	/* number of ref. picture */
-	reg = READL(mfc_regs->e_h264_options);
+	reg = readl(mfc_regs->e_h264_options);
 	reg &= ~(0x1 << 7);
 	reg |= (((p_h264->num_ref_pic_4p - 1) & 0x1) << 7);
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 
 	/* 8x8 transform enable */
-	reg = READL(mfc_regs->e_h264_options);
+	reg = readl(mfc_regs->e_h264_options);
 	reg &= ~(0x3 << 12);
 	reg |= ((p_h264->_8x8_transform & 0x3) << 12);
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 
 	/* macroblock adaptive scaling features */
-	WRITEL(0x0, mfc_regs->e_mb_rc_config);
+	writel(0x0, mfc_regs->e_mb_rc_config);
 	if (p->rc_mb) {
 		reg = 0;
 		/** dark region */
@@ -945,95 +940,95 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx)
 		reg |= ((p_h264->rc_mb_static & 0x1) << 1);
 		/** high activity region */
 		reg |= p_h264->rc_mb_activity & 0x1;
-		WRITEL(reg, mfc_regs->e_mb_rc_config);
+		writel(reg, mfc_regs->e_mb_rc_config);
 	}
 
 	/* aspect ratio VUI */
-	READL(mfc_regs->e_h264_options);
+	readl(mfc_regs->e_h264_options);
 	reg &= ~(0x1 << 5);
 	reg |= ((p_h264->vui_sar & 0x1) << 5);
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 
-	WRITEL(0x0, mfc_regs->e_aspect_ratio);
-	WRITEL(0x0, mfc_regs->e_extended_sar);
+	writel(0x0, mfc_regs->e_aspect_ratio);
+	writel(0x0, mfc_regs->e_extended_sar);
 	if (p_h264->vui_sar) {
 		/* aspect ration IDC */
 		reg = 0;
 		reg |= p_h264->vui_sar_idc & 0xFF;
-		WRITEL(reg, mfc_regs->e_aspect_ratio);
+		writel(reg, mfc_regs->e_aspect_ratio);
 		if (p_h264->vui_sar_idc == 0xFF) {
 			/* extended SAR */
 			reg = 0;
 			reg |= (p_h264->vui_ext_sar_width & 0xFFFF) << 16;
 			reg |= p_h264->vui_ext_sar_height & 0xFFFF;
-			WRITEL(reg, mfc_regs->e_extended_sar);
+			writel(reg, mfc_regs->e_extended_sar);
 		}
 	}
 
 	/* intra picture period for H.264 open GOP */
 	/* control */
-	READL(mfc_regs->e_h264_options);
+	readl(mfc_regs->e_h264_options);
 	reg &= ~(0x1 << 4);
 	reg |= ((p_h264->open_gop & 0x1) << 4);
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 
 	/* value */
-	WRITEL(0x0, mfc_regs->e_h264_i_period);
+	writel(0x0, mfc_regs->e_h264_i_period);
 	if (p_h264->open_gop) {
 		reg = 0;
 		reg |= p_h264->open_gop_size & 0xFFFF;
-		WRITEL(reg, mfc_regs->e_h264_i_period);
+		writel(reg, mfc_regs->e_h264_i_period);
 	}
 
 	/* 'WEIGHTED_BI_PREDICTION' for B is disable */
-	READL(mfc_regs->e_h264_options);
+	readl(mfc_regs->e_h264_options);
 	reg &= ~(0x3 << 9);
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 
 	/* 'CONSTRAINED_INTRA_PRED_ENABLE' is disable */
-	READL(mfc_regs->e_h264_options);
+	readl(mfc_regs->e_h264_options);
 	reg &= ~(0x1 << 14);
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 
 	/* ASO */
-	READL(mfc_regs->e_h264_options);
+	readl(mfc_regs->e_h264_options);
 	reg &= ~(0x1 << 6);
 	reg |= ((p_h264->aso & 0x1) << 6);
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 
 	/* hier qp enable */
-	READL(mfc_regs->e_h264_options);
+	readl(mfc_regs->e_h264_options);
 	reg &= ~(0x1 << 8);
 	reg |= ((p_h264->open_gop & 0x1) << 8);
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 	reg = 0;
 	if (p_h264->hier_qp && p_h264->hier_qp_layer) {
 		reg |= (p_h264->hier_qp_type & 0x1) << 0x3;
 		reg |= p_h264->hier_qp_layer & 0x7;
-		WRITEL(reg, mfc_regs->e_h264_num_t_layer);
+		writel(reg, mfc_regs->e_h264_num_t_layer);
 		/* QP value for each layer */
 		for (i = 0; i < p_h264->hier_qp_layer &&
 				i < ARRAY_SIZE(p_h264->hier_qp_layer_qp); i++) {
-			WRITEL(p_h264->hier_qp_layer_qp[i],
+			writel(p_h264->hier_qp_layer_qp[i],
 				mfc_regs->e_h264_hierarchical_qp_layer0
 				+ i * 4);
 		}
 	}
 	/* number of coding layer should be zero when hierarchical is disable */
-	WRITEL(reg, mfc_regs->e_h264_num_t_layer);
+	writel(reg, mfc_regs->e_h264_num_t_layer);
 
 	/* frame packing SEI generation */
-	READL(mfc_regs->e_h264_options);
+	readl(mfc_regs->e_h264_options);
 	reg &= ~(0x1 << 25);
 	reg |= ((p_h264->sei_frame_packing & 0x1) << 25);
-	WRITEL(reg, mfc_regs->e_h264_options);
+	writel(reg, mfc_regs->e_h264_options);
 	if (p_h264->sei_frame_packing) {
 		reg = 0;
 		/** current frame0 flag */
 		reg |= ((p_h264->sei_fp_curr_frame_0 & 0x1) << 2);
 		/** arrangement type */
 		reg |= p_h264->sei_fp_arrangement_type & 0x3;
-		WRITEL(reg, mfc_regs->e_h264_frame_packing_sei_info);
+		writel(reg, mfc_regs->e_h264_frame_packing_sei_info);
 	}
 
 	if (p_h264->fmo) {
@@ -1042,7 +1037,7 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx)
 			if (p_h264->fmo_slice_grp > 4)
 				p_h264->fmo_slice_grp = 4;
 			for (i = 0; i < (p_h264->fmo_slice_grp & 0xF); i++)
-				WRITEL(p_h264->fmo_run_len[i] - 1,
+				writel(p_h264->fmo_run_len[i] - 1,
 					mfc_regs->e_h264_fmo_run_length_minus1_0
 					+ i * 4);
 			break;
@@ -1054,10 +1049,10 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx)
 		case V4L2_MPEG_VIDEO_H264_FMO_MAP_TYPE_WIPE_SCAN:
 			if (p_h264->fmo_slice_grp > 2)
 				p_h264->fmo_slice_grp = 2;
-			WRITEL(p_h264->fmo_chg_dir & 0x1,
+			writel(p_h264->fmo_chg_dir & 0x1,
 				mfc_regs->e_h264_fmo_slice_grp_change_dir);
 			/* the valid range is 0 ~ number of macroblocks -1 */
-			WRITEL(p_h264->fmo_chg_rate,
+			writel(p_h264->fmo_chg_rate,
 			mfc_regs->e_h264_fmo_slice_grp_change_rate_minus1);
 			break;
 		default:
@@ -1068,12 +1063,12 @@ static int s5p_mfc_set_enc_params_h264(struct s5p_mfc_ctx *ctx)
 			break;
 		}
 
-		WRITEL(p_h264->fmo_map_type,
+		writel(p_h264->fmo_map_type,
 				mfc_regs->e_h264_fmo_slice_grp_map_type);
-		WRITEL(p_h264->fmo_slice_grp - 1,
+		writel(p_h264->fmo_slice_grp - 1,
 				mfc_regs->e_h264_fmo_num_slice_grp_minus1);
 	} else {
-		WRITEL(0, mfc_regs->e_h264_fmo_num_slice_grp_minus1);
+		writel(0, mfc_regs->e_h264_fmo_num_slice_grp_minus1);
 	}
 
 	mfc_debug_leave();
@@ -1094,10 +1089,10 @@ static int s5p_mfc_set_enc_params_mpeg4(struct s5p_mfc_ctx *ctx)
 	s5p_mfc_set_enc_params(ctx);
 
 	/* pictype : number of B */
-	reg = READL(mfc_regs->e_gop_config);
+	reg = readl(mfc_regs->e_gop_config);
 	reg &= ~(0x3 << 16);
 	reg |= ((p->num_b_frame & 0x3) << 16);
-	WRITEL(reg, mfc_regs->e_gop_config);
+	writel(reg, mfc_regs->e_gop_config);
 
 	/* profile & level */
 	reg = 0;
@@ -1105,19 +1100,19 @@ static int s5p_mfc_set_enc_params_mpeg4(struct s5p_mfc_ctx *ctx)
 	reg |= ((p_mpeg4->level & 0xFF) << 8);
 	/** profile - 0 ~ 1 */
 	reg |= p_mpeg4->profile & 0x3F;
-	WRITEL(reg, mfc_regs->e_picture_profile);
+	writel(reg, mfc_regs->e_picture_profile);
 
 	/* rate control config. */
-	reg = READL(mfc_regs->e_rc_config);
+	reg = readl(mfc_regs->e_rc_config);
 	/** macroblock level rate control */
 	reg &= ~(0x1 << 8);
 	reg |= ((p->rc_mb & 0x1) << 8);
-	WRITEL(reg, mfc_regs->e_rc_config);
+	writel(reg, mfc_regs->e_rc_config);
 
 	/** frame QP */
 	reg &= ~(0x3F);
 	reg |= p_mpeg4->rc_frame_qp & 0x3F;
-	WRITEL(reg, mfc_regs->e_rc_config);
+	writel(reg, mfc_regs->e_rc_config);
 
 	/* max & min value of QP */
 	reg = 0;
@@ -1125,16 +1120,16 @@ static int s5p_mfc_set_enc_params_mpeg4(struct s5p_mfc_ctx *ctx)
 	reg |= ((p_mpeg4->rc_max_qp & 0x3F) << 8);
 	/** min QP */
 	reg |= p_mpeg4->rc_min_qp & 0x3F;
-	WRITEL(reg, mfc_regs->e_rc_qp_bound);
+	writel(reg, mfc_regs->e_rc_qp_bound);
 
 	/* other QPs */
-	WRITEL(0x0, mfc_regs->e_fixed_picture_qp);
+	writel(0x0, mfc_regs->e_fixed_picture_qp);
 	if (!p->rc_frame && !p->rc_mb) {
 		reg = 0;
 		reg |= ((p_mpeg4->rc_b_frame_qp & 0x3F) << 16);
 		reg |= ((p_mpeg4->rc_p_frame_qp & 0x3F) << 8);
 		reg |= p_mpeg4->rc_frame_qp & 0x3F;
-		WRITEL(reg, mfc_regs->e_fixed_picture_qp);
+		writel(reg, mfc_regs->e_fixed_picture_qp);
 	}
 
 	/* frame rate */
@@ -1142,21 +1137,21 @@ static int s5p_mfc_set_enc_params_mpeg4(struct s5p_mfc_ctx *ctx)
 		reg = 0;
 		reg |= ((p->rc_framerate_num & 0xFFFF) << 16);
 		reg |= p->rc_framerate_denom & 0xFFFF;
-		WRITEL(reg, mfc_regs->e_rc_frame_rate);
+		writel(reg, mfc_regs->e_rc_frame_rate);
 	}
 
 	/* vbv buffer size */
 	if (p->frame_skip_mode ==
 			V4L2_MPEG_MFC51_VIDEO_FRAME_SKIP_MODE_BUF_LIMIT) {
-		WRITEL(p->vbv_size & 0xFFFF, mfc_regs->e_vbv_buffer_size);
+		writel(p->vbv_size & 0xFFFF, mfc_regs->e_vbv_buffer_size);
 
 		if (p->rc_frame)
-			WRITEL(p->vbv_delay, mfc_regs->e_vbv_init_delay);
+			writel(p->vbv_delay, mfc_regs->e_vbv_init_delay);
 	}
 
 	/* Disable HEC */
-	WRITEL(0x0, mfc_regs->e_mpeg4_options);
-	WRITEL(0x0, mfc_regs->e_mpeg4_hec_period);
+	writel(0x0, mfc_regs->e_mpeg4_options);
+	writel(0x0, mfc_regs->e_mpeg4_hec_period);
 
 	mfc_debug_leave();
 
@@ -1179,19 +1174,19 @@ static int s5p_mfc_set_enc_params_h263(struct s5p_mfc_ctx *ctx)
 	reg = 0;
 	/** profile */
 	reg |= (0x1 << 4);
-	WRITEL(reg, mfc_regs->e_picture_profile);
+	writel(reg, mfc_regs->e_picture_profile);
 
 	/* rate control config. */
-	reg = READL(mfc_regs->e_rc_config);
+	reg = readl(mfc_regs->e_rc_config);
 	/** macroblock level rate control */
 	reg &= ~(0x1 << 8);
 	reg |= ((p->rc_mb & 0x1) << 8);
-	WRITEL(reg, mfc_regs->e_rc_config);
+	writel(reg, mfc_regs->e_rc_config);
 
 	/** frame QP */
 	reg &= ~(0x3F);
 	reg |= p_h263->rc_frame_qp & 0x3F;
-	WRITEL(reg, mfc_regs->e_rc_config);
+	writel(reg, mfc_regs->e_rc_config);
 
 	/* max & min value of QP */
 	reg = 0;
@@ -1199,16 +1194,16 @@ static int s5p_mfc_set_enc_params_h263(struct s5p_mfc_ctx *ctx)
 	reg |= ((p_h263->rc_max_qp & 0x3F) << 8);
 	/** min QP */
 	reg |= p_h263->rc_min_qp & 0x3F;
-	WRITEL(reg, mfc_regs->e_rc_qp_bound);
+	writel(reg, mfc_regs->e_rc_qp_bound);
 
 	/* other QPs */
-	WRITEL(0x0, mfc_regs->e_fixed_picture_qp);
+	writel(0x0, mfc_regs->e_fixed_picture_qp);
 	if (!p->rc_frame && !p->rc_mb) {
 		reg = 0;
 		reg |= ((p_h263->rc_b_frame_qp & 0x3F) << 16);
 		reg |= ((p_h263->rc_p_frame_qp & 0x3F) << 8);
 		reg |= p_h263->rc_frame_qp & 0x3F;
-		WRITEL(reg, mfc_regs->e_fixed_picture_qp);
+		writel(reg, mfc_regs->e_fixed_picture_qp);
 	}
 
 	/* frame rate */
@@ -1216,16 +1211,16 @@ static int s5p_mfc_set_enc_params_h263(struct s5p_mfc_ctx *ctx)
 		reg = 0;
 		reg |= ((p->rc_framerate_num & 0xFFFF) << 16);
 		reg |= p->rc_framerate_denom & 0xFFFF;
-		WRITEL(reg, mfc_regs->e_rc_frame_rate);
+		writel(reg, mfc_regs->e_rc_frame_rate);
 	}
 
 	/* vbv buffer size */
 	if (p->frame_skip_mode ==
 			V4L2_MPEG_MFC51_VIDEO_FRAME_SKIP_MODE_BUF_LIMIT) {
-		WRITEL(p->vbv_size & 0xFFFF, mfc_regs->e_vbv_buffer_size);
+		writel(p->vbv_size & 0xFFFF, mfc_regs->e_vbv_buffer_size);
 
 		if (p->rc_frame)
-			WRITEL(p->vbv_delay, mfc_regs->e_vbv_init_delay);
+			writel(p->vbv_delay, mfc_regs->e_vbv_init_delay);
 	}
 
 	mfc_debug_leave();
@@ -1247,57 +1242,57 @@ static int s5p_mfc_set_enc_params_vp8(struct s5p_mfc_ctx *ctx)
 	s5p_mfc_set_enc_params(ctx);
 
 	/* pictype : number of B */
-	reg = READL(mfc_regs->e_gop_config);
+	reg = readl(mfc_regs->e_gop_config);
 	reg &= ~(0x3 << 16);
 	reg |= ((p->num_b_frame & 0x3) << 16);
-	WRITEL(reg, mfc_regs->e_gop_config);
+	writel(reg, mfc_regs->e_gop_config);
 
 	/* profile - 0 ~ 3 */
 	reg = p_vp8->profile & 0x3;
-	WRITEL(reg, mfc_regs->e_picture_profile);
+	writel(reg, mfc_regs->e_picture_profile);
 
 	/* rate control config. */
-	reg = READL(mfc_regs->e_rc_config);
+	reg = readl(mfc_regs->e_rc_config);
 	/** macroblock level rate control */
 	reg &= ~(0x1 << 8);
 	reg |= ((p->rc_mb & 0x1) << 8);
-	WRITEL(reg, mfc_regs->e_rc_config);
+	writel(reg, mfc_regs->e_rc_config);
 
 	/* frame rate */
 	if (p->rc_frame && p->rc_framerate_num && p->rc_framerate_denom) {
 		reg = 0;
 		reg |= ((p->rc_framerate_num & 0xFFFF) << 16);
 		reg |= p->rc_framerate_denom & 0xFFFF;
-		WRITEL(reg, mfc_regs->e_rc_frame_rate);
+		writel(reg, mfc_regs->e_rc_frame_rate);
 	}
 
 	/* frame QP */
 	reg &= ~(0x7F);
 	reg |= p_vp8->rc_frame_qp & 0x7F;
-	WRITEL(reg, mfc_regs->e_rc_config);
+	writel(reg, mfc_regs->e_rc_config);
 
 	/* other QPs */
-	WRITEL(0x0, mfc_regs->e_fixed_picture_qp);
+	writel(0x0, mfc_regs->e_fixed_picture_qp);
 	if (!p->rc_frame && !p->rc_mb) {
 		reg = 0;
 		reg |= ((p_vp8->rc_p_frame_qp & 0x7F) << 8);
 		reg |= p_vp8->rc_frame_qp & 0x7F;
-		WRITEL(reg, mfc_regs->e_fixed_picture_qp);
+		writel(reg, mfc_regs->e_fixed_picture_qp);
 	}
 
 	/* max QP */
 	reg = ((p_vp8->rc_max_qp & 0x7F) << 8);
 	/* min QP */
 	reg |= p_vp8->rc_min_qp & 0x7F;
-	WRITEL(reg, mfc_regs->e_rc_qp_bound);
+	writel(reg, mfc_regs->e_rc_qp_bound);
 
 	/* vbv buffer size */
 	if (p->frame_skip_mode ==
 			V4L2_MPEG_MFC51_VIDEO_FRAME_SKIP_MODE_BUF_LIMIT) {
-		WRITEL(p->vbv_size & 0xFFFF, mfc_regs->e_vbv_buffer_size);
+		writel(p->vbv_size & 0xFFFF, mfc_regs->e_vbv_buffer_size);
 
 		if (p->rc_frame)
-			WRITEL(p->vbv_delay, mfc_regs->e_vbv_init_delay);
+			writel(p->vbv_delay, mfc_regs->e_vbv_init_delay);
 	}
 
 	/* VP8 specific params */
@@ -1319,7 +1314,7 @@ static int s5p_mfc_set_enc_params_vp8(struct s5p_mfc_ctx *ctx)
 	}
 	reg |= (val & 0xF) << 3;
 	reg |= (p_vp8->num_ref & 0x2);
-	WRITEL(reg, mfc_regs->e_vp8_options);
+	writel(reg, mfc_regs->e_vp8_options);
 
 	mfc_debug_leave();
 
@@ -1338,9 +1333,9 @@ static int s5p_mfc_init_decode_v6(struct s5p_mfc_ctx *ctx)
 	mfc_debug(2, "InstNo: %d/%d\n", ctx->inst_no,
 			S5P_FIMV_CH_SEQ_HEADER_V6);
 	mfc_debug(2, "BUFs: %08x %08x %08x\n",
-		  READL(mfc_regs->d_cpb_buffer_addr),
-		  READL(mfc_regs->d_cpb_buffer_addr),
-		  READL(mfc_regs->d_cpb_buffer_addr));
+		  readl(mfc_regs->d_cpb_buffer_addr),
+		  readl(mfc_regs->d_cpb_buffer_addr),
+		  readl(mfc_regs->d_cpb_buffer_addr));
 
 	/* FMO_ASO_CTRL - 0: Enable, 1: Disable */
 	reg |= (fmo_aso_ctrl << S5P_FIMV_D_OPT_FMO_ASO_CTRL_MASK_V6);
@@ -1351,11 +1346,11 @@ static int s5p_mfc_init_decode_v6(struct s5p_mfc_ctx *ctx)
 	 * set to negative value. */
 	if (ctx->display_delay >= 0) {
 		reg |= (0x1 << S5P_FIMV_D_OPT_DDELAY_EN_SHIFT_V6);
-		WRITEL(ctx->display_delay, mfc_regs->d_display_delay);
+		writel(ctx->display_delay, mfc_regs->d_display_delay);
 	}
 
 	if (IS_MFCV7_PLUS(dev) || IS_MFCV6_V2(dev)) {
-		WRITEL(reg, mfc_regs->d_dec_options);
+		writel(reg, mfc_regs->d_dec_options);
 		reg = 0;
 	}
 
@@ -1370,22 +1365,22 @@ static int s5p_mfc_init_decode_v6(struct s5p_mfc_ctx *ctx)
 		reg |= (0x1 << S5P_FIMV_D_OPT_TILE_MODE_SHIFT_V6);
 
 	if (IS_MFCV7_PLUS(dev) || IS_MFCV6_V2(dev))
-		WRITEL(reg, mfc_regs->d_init_buffer_options);
+		writel(reg, mfc_regs->d_init_buffer_options);
 	else
-		WRITEL(reg, mfc_regs->d_dec_options);
+		writel(reg, mfc_regs->d_dec_options);
 
 	/* 0: NV12(CbCr), 1: NV21(CrCb) */
 	if (ctx->dst_fmt->fourcc == V4L2_PIX_FMT_NV21M)
-		WRITEL(0x1, mfc_regs->pixel_format);
+		writel(0x1, mfc_regs->pixel_format);
 	else
-		WRITEL(0x0, mfc_regs->pixel_format);
+		writel(0x0, mfc_regs->pixel_format);
 
 
 	/* sei parse */
-	WRITEL(ctx->sei_fp_parse & 0x1, mfc_regs->d_sei_enable);
+	writel(ctx->sei_fp_parse & 0x1, mfc_regs->d_sei_enable);
 
-	WRITEL(ctx->inst_no, mfc_regs->instance_id);
-	s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
+	writel(ctx->inst_no, mfc_regs->instance_id);
+	s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
 			S5P_FIMV_CH_SEQ_HEADER_V6, NULL);
 
 	mfc_debug_leave();
@@ -1400,8 +1395,8 @@ static inline void s5p_mfc_set_flush(struct s5p_mfc_ctx *ctx, int flush)
 	if (flush) {
 		dev->curr_ctx = ctx->num;
 		s5p_mfc_clean_ctx_int_flags(ctx);
-		WRITEL(ctx->inst_no, mfc_regs->instance_id);
-		s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
+		writel(ctx->inst_no, mfc_regs->instance_id);
+		s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
 				S5P_FIMV_H2R_CMD_FLUSH_V6, NULL);
 	}
 }
@@ -1413,19 +1408,19 @@ static int s5p_mfc_decode_one_frame_v6(struct s5p_mfc_ctx *ctx,
 	struct s5p_mfc_dev *dev = ctx->dev;
 	const struct s5p_mfc_regs *mfc_regs = dev->mfc_regs;
 
-	WRITEL(ctx->dec_dst_flag, mfc_regs->d_available_dpb_flag_lower);
-	WRITEL(ctx->slice_interface & 0x1, mfc_regs->d_slice_if_enable);
+	writel(ctx->dec_dst_flag, mfc_regs->d_available_dpb_flag_lower);
+	writel(ctx->slice_interface & 0x1, mfc_regs->d_slice_if_enable);
 
-	WRITEL(ctx->inst_no, mfc_regs->instance_id);
+	writel(ctx->inst_no, mfc_regs->instance_id);
 	/* Issue different commands to instance basing on whether it
 	 * is the last frame or not. */
 	switch (last_frame) {
 	case 0:
-		s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
+		s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
 				S5P_FIMV_CH_FRAME_START_V6, NULL);
 		break;
 	case 1:
-		s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
+		s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
 				S5P_FIMV_CH_LAST_FRAME_V6, NULL);
 		break;
 	default:
@@ -1458,12 +1453,12 @@ static int s5p_mfc_init_encode_v6(struct s5p_mfc_ctx *ctx)
 
 	/* Set stride lengths for v7 & above */
 	if (IS_MFCV7_PLUS(dev)) {
-		WRITEL(ctx->img_width, mfc_regs->e_source_first_plane_stride);
-		WRITEL(ctx->img_width, mfc_regs->e_source_second_plane_stride);
+		writel(ctx->img_width, mfc_regs->e_source_first_plane_stride);
+		writel(ctx->img_width, mfc_regs->e_source_second_plane_stride);
 	}
 
-	WRITEL(ctx->inst_no, mfc_regs->instance_id);
-	s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
+	writel(ctx->inst_no, mfc_regs->instance_id);
+	s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
 			S5P_FIMV_CH_SEQ_HEADER_V6, NULL);
 
 	return 0;
@@ -1479,7 +1474,7 @@ static int s5p_mfc_h264_set_aso_slice_order_v6(struct s5p_mfc_ctx *ctx)
 
 	if (p_h264->aso) {
 		for (i = 0; i < ARRAY_SIZE(p_h264->aso_slice_order); i++) {
-			WRITEL(p_h264->aso_slice_order[i],
+			writel(p_h264->aso_slice_order[i],
 				mfc_regs->e_h264_aso_slice_order_0 + i * 4);
 		}
 	}
@@ -1501,8 +1496,8 @@ static int s5p_mfc_encode_one_frame_v6(struct s5p_mfc_ctx *ctx)
 
 	s5p_mfc_set_slice_mode(ctx);
 
-	WRITEL(ctx->inst_no, mfc_regs->instance_id);
-	s5p_mfc_hw_call(dev->mfc_cmds, cmd_host2risc, dev,
+	writel(ctx->inst_no, mfc_regs->instance_id);
+	s5p_mfc_hw_call_void(dev->mfc_cmds, cmd_host2risc, dev,
 			S5P_FIMV_CH_FRAME_START_V6, NULL);
 
 	mfc_debug(2, "--\n");
@@ -1877,15 +1872,15 @@ static void s5p_mfc_cleanup_queue_v6(struct list_head *lh, struct vb2_queue *vq)
 static void s5p_mfc_clear_int_flags_v6(struct s5p_mfc_dev *dev)
 {
 	const struct s5p_mfc_regs *mfc_regs = dev->mfc_regs;
-	WRITEL(0, mfc_regs->risc2host_command);
-	WRITEL(0, mfc_regs->risc2host_int);
+	writel(0, mfc_regs->risc2host_command);
+	writel(0, mfc_regs->risc2host_int);
 }
 
 static void s5p_mfc_write_info_v6(struct s5p_mfc_ctx *ctx, unsigned int data,
 		unsigned int ofs)
 {
 	s5p_mfc_clock_on();
-	WRITEL(data, (void *)ofs);
+	writel(data, (volatile void __iomem *)((unsigned long)ofs));
 	s5p_mfc_clock_off();
 }
 
@@ -1895,7 +1890,7 @@ s5p_mfc_read_info_v6(struct s5p_mfc_ctx *ctx, unsigned int ofs)
 	int ret;
 
 	s5p_mfc_clock_on();
-	ret = READL((void *)ofs);
+	ret = readl((volatile void __iomem *)((unsigned long)ofs));
 	s5p_mfc_clock_off();
 
 	return ret;
@@ -1903,51 +1898,51 @@ s5p_mfc_read_info_v6(struct s5p_mfc_ctx *ctx, unsigned int ofs)
 
 static int s5p_mfc_get_dspl_y_adr_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_display_first_plane_addr);
+	return readl(dev->mfc_regs->d_display_first_plane_addr);
 }
 
 static int s5p_mfc_get_dec_y_adr_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_decoded_first_plane_addr);
+	return readl(dev->mfc_regs->d_decoded_first_plane_addr);
 }
 
 static int s5p_mfc_get_dspl_status_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_display_status);
+	return readl(dev->mfc_regs->d_display_status);
 }
 
 static int s5p_mfc_get_dec_status_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_decoded_status);
+	return readl(dev->mfc_regs->d_decoded_status);
 }
 
 static int s5p_mfc_get_dec_frame_type_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_decoded_frame_type) &
+	return readl(dev->mfc_regs->d_decoded_frame_type) &
 		S5P_FIMV_DECODE_FRAME_MASK_V6;
 }
 
 static int s5p_mfc_get_disp_frame_type_v6(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
-	return READL(dev->mfc_regs->d_display_frame_type) &
+	return readl(dev->mfc_regs->d_display_frame_type) &
 		S5P_FIMV_DECODE_FRAME_MASK_V6;
 }
 
 static int s5p_mfc_get_consumed_stream_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_decoded_nal_size);
+	return readl(dev->mfc_regs->d_decoded_nal_size);
 }
 
 static int s5p_mfc_get_int_reason_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->risc2host_command) &
+	return readl(dev->mfc_regs->risc2host_command) &
 		S5P_FIMV_RISC2HOST_CMD_MASK;
 }
 
 static int s5p_mfc_get_int_err_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->error_code);
+	return readl(dev->mfc_regs->error_code);
 }
 
 static int s5p_mfc_err_dec_v6(unsigned int err)
@@ -1962,87 +1957,87 @@ static int s5p_mfc_err_dspl_v6(unsigned int err)
 
 static int s5p_mfc_get_img_width_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_display_frame_width);
+	return readl(dev->mfc_regs->d_display_frame_width);
 }
 
 static int s5p_mfc_get_img_height_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_display_frame_height);
+	return readl(dev->mfc_regs->d_display_frame_height);
 }
 
 static int s5p_mfc_get_dpb_count_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_min_num_dpb);
+	return readl(dev->mfc_regs->d_min_num_dpb);
 }
 
 static int s5p_mfc_get_mv_count_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_min_num_mv);
+	return readl(dev->mfc_regs->d_min_num_mv);
 }
 
 static int s5p_mfc_get_inst_no_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->ret_instance_id);
+	return readl(dev->mfc_regs->ret_instance_id);
 }
 
 static int s5p_mfc_get_enc_dpb_count_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->e_num_dpb);
+	return readl(dev->mfc_regs->e_num_dpb);
 }
 
 static int s5p_mfc_get_enc_strm_size_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->e_stream_size);
+	return readl(dev->mfc_regs->e_stream_size);
 }
 
 static int s5p_mfc_get_enc_slice_type_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->e_slice_type);
+	return readl(dev->mfc_regs->e_slice_type);
 }
 
 static int s5p_mfc_get_enc_pic_count_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->e_picture_count);
+	return readl(dev->mfc_regs->e_picture_count);
 }
 
 static int s5p_mfc_get_sei_avail_status_v6(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
-	return READL(dev->mfc_regs->d_frame_pack_sei_avail);
+	return readl(dev->mfc_regs->d_frame_pack_sei_avail);
 }
 
 static int s5p_mfc_get_mvc_num_views_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_mvc_num_views);
+	return readl(dev->mfc_regs->d_mvc_num_views);
 }
 
 static int s5p_mfc_get_mvc_view_id_v6(struct s5p_mfc_dev *dev)
 {
-	return READL(dev->mfc_regs->d_mvc_view_id);
+	return readl(dev->mfc_regs->d_mvc_view_id);
 }
 
 static unsigned int s5p_mfc_get_pic_type_top_v6(struct s5p_mfc_ctx *ctx)
 {
 	return s5p_mfc_read_info_v6(ctx,
-		(unsigned int) ctx->dev->mfc_regs->d_ret_picture_tag_top);
+		(__force unsigned long) ctx->dev->mfc_regs->d_ret_picture_tag_top);
 }
 
 static unsigned int s5p_mfc_get_pic_type_bot_v6(struct s5p_mfc_ctx *ctx)
 {
 	return s5p_mfc_read_info_v6(ctx,
-		(unsigned int) ctx->dev->mfc_regs->d_ret_picture_tag_bot);
+		(__force unsigned long) ctx->dev->mfc_regs->d_ret_picture_tag_bot);
 }
 
 static unsigned int s5p_mfc_get_crop_info_h_v6(struct s5p_mfc_ctx *ctx)
 {
 	return s5p_mfc_read_info_v6(ctx,
-		(unsigned int) ctx->dev->mfc_regs->d_display_crop_info1);
+		(__force unsigned long) ctx->dev->mfc_regs->d_display_crop_info1);
 }
 
 static unsigned int s5p_mfc_get_crop_info_v_v6(struct s5p_mfc_ctx *ctx)
 {
 	return s5p_mfc_read_info_v6(ctx,
-		(unsigned int) ctx->dev->mfc_regs->d_display_crop_info2);
+		(__force unsigned long) ctx->dev->mfc_regs->d_display_crop_info2);
 }
 
 static struct s5p_mfc_regs mfc_regs;
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c b/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
index b6a8be97a96c..826c48945bf5 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
@@ -21,7 +21,7 @@
 #include "s5p_mfc_pm.h"
 
 #define MFC_GATE_CLK_NAME	"mfc"
-#define MFC_SCLK_NAME		"sclk-mfc"
+#define MFC_SCLK_NAME		"sclk_mfc"
 #define MFC_SCLK_RATE		(200 * 1000000)
 
 #define CLK_DEBUG
diff --git a/drivers/media/platform/s5p-tv/Kconfig b/drivers/media/platform/s5p-tv/Kconfig
index 369a4c191e18..a9d56f8936b4 100644
--- a/drivers/media/platform/s5p-tv/Kconfig
+++ b/drivers/media/platform/s5p-tv/Kconfig
@@ -8,7 +8,8 @@
 
 config VIDEO_SAMSUNG_S5P_TV
 	bool "Samsung TV driver for S5P platform"
-	depends on (PLAT_S5P || ARCH_EXYNOS) && PM_RUNTIME
+	depends on PM_RUNTIME
+	depends on PLAT_S5P || ARCH_EXYNOS || COMPILE_TEST
 	default n
 	---help---
 	  Say Y here to enable selecting the TV output devices for
@@ -70,6 +71,7 @@ config VIDEO_SAMSUNG_S5P_MIXER
 	tristate "Samsung Mixer and Video Processor Driver"
 	depends on VIDEO_DEV && VIDEO_V4L2
 	depends on VIDEO_SAMSUNG_S5P_TV
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	help
 	  Say Y here if you want support for the Mixer in Samsung S5P SoCs.
diff --git a/drivers/media/platform/s5p-tv/hdmi_drv.c b/drivers/media/platform/s5p-tv/hdmi_drv.c
index 754740f4b671..37c8bd694c5f 100644
--- a/drivers/media/platform/s5p-tv/hdmi_drv.c
+++ b/drivers/media/platform/s5p-tv/hdmi_drv.c
@@ -615,7 +615,7 @@ static int hdmi_s_power(struct v4l2_subdev *sd, int on)
 	else
 		ret = pm_runtime_put_sync(hdev->dev);
 	/* only values < 0 indicate errors */
-	return IS_ERR_VALUE(ret) ? ret : 0;
+	return ret < 0 ? ret : 0;
 }
 
 static int hdmi_s_dv_timings(struct v4l2_subdev *sd,
diff --git a/drivers/media/platform/s5p-tv/sdo_drv.c b/drivers/media/platform/s5p-tv/sdo_drv.c
index 5a7c3796f22e..72cf892dd008 100644
--- a/drivers/media/platform/s5p-tv/sdo_drv.c
+++ b/drivers/media/platform/s5p-tv/sdo_drv.c
@@ -190,7 +190,7 @@ static int sdo_s_power(struct v4l2_subdev *sd, int on)
 		ret = pm_runtime_put_sync(dev);
 
 	/* only values < 0 indicate errors */
-	return IS_ERR_VALUE(ret) ? ret : 0;
+	return ret < 0 ? ret : 0;
 }
 
 static int sdo_streamon(struct sdo_device *sdev)
diff --git a/drivers/media/platform/s5p-tv/sii9234_drv.c b/drivers/media/platform/s5p-tv/sii9234_drv.c
index 3dd762e5b67e..db8c17bb4aaa 100644
--- a/drivers/media/platform/s5p-tv/sii9234_drv.c
+++ b/drivers/media/platform/s5p-tv/sii9234_drv.c
@@ -289,7 +289,7 @@ static int sii9234_s_power(struct v4l2_subdev *sd, int on)
 	else
 		ret = pm_runtime_put(&ctx->client->dev);
 	/* only values < 0 indicate errors */
-	return IS_ERR_VALUE(ret) ? ret : 0;
+	return ret < 0 ? ret : 0;
 }
 
 static int sii9234_s_stream(struct v4l2_subdev *sd, int enable)
diff --git a/drivers/media/platform/sh_veu.c b/drivers/media/platform/sh_veu.c
index 8dc279d4d561..be3b3bc71a0f 100644
--- a/drivers/media/platform/sh_veu.c
+++ b/drivers/media/platform/sh_veu.c
@@ -26,6 +26,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-mem2mem.h>
+#include <media/v4l2-image-sizes.h>
 #include <media/videobuf2-dma-contig.h>
 
 #define VEU_STR 0x00 /* start register */
@@ -135,9 +136,6 @@ enum sh_veu_fmt_idx {
 	SH_VEU_FMT_RGB24,
 };
 
-#define VGA_WIDTH	640
-#define VGA_HEIGHT	480
-
 #define DEFAULT_IN_WIDTH	VGA_WIDTH
 #define DEFAULT_IN_HEIGHT	VGA_HEIGHT
 #define DEFAULT_IN_FMTIDX	SH_VEU_FMT_NV12
diff --git a/drivers/media/platform/soc_camera/Kconfig b/drivers/media/platform/soc_camera/Kconfig
index 6540847f4e1d..f2776cd415ca 100644
--- a/drivers/media/platform/soc_camera/Kconfig
+++ b/drivers/media/platform/soc_camera/Kconfig
@@ -20,6 +20,8 @@ config SOC_CAMERA_PLATFORM
 config VIDEO_MX3
 	tristate "i.MX3x Camera Sensor Interface driver"
 	depends on VIDEO_DEV && MX3_IPU && SOC_CAMERA
+	depends on MX3_IPU || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	---help---
 	  This is a v4l2 driver for the i.MX3x Camera Sensor Interface
@@ -35,6 +37,7 @@ config VIDEO_RCAR_VIN
 	tristate "R-Car Video Input (VIN) support"
 	depends on VIDEO_DEV && SOC_CAMERA
 	depends on ARCH_SHMOBILE || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select SOC_CAMERA_SCALE_CROP
 	---help---
@@ -51,6 +54,7 @@ config VIDEO_SH_MOBILE_CEU
 	tristate "SuperH Mobile CEU Interface driver"
 	depends on VIDEO_DEV && SOC_CAMERA && HAS_DMA && HAVE_CLK
 	depends on ARCH_SHMOBILE || SUPERH || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	select SOC_CAMERA_SCALE_CROP
 	---help---
@@ -58,7 +62,9 @@ config VIDEO_SH_MOBILE_CEU
 
 config VIDEO_OMAP1
 	tristate "OMAP1 Camera Interface driver"
-	depends on VIDEO_DEV && ARCH_OMAP1 && SOC_CAMERA
+	depends on VIDEO_DEV && SOC_CAMERA
+	depends on ARCH_OMAP1
+	depends on HAS_DMA
 	select VIDEOBUF_DMA_CONTIG
 	select VIDEOBUF_DMA_SG
 	---help---
@@ -66,14 +72,18 @@ config VIDEO_OMAP1
 
 config VIDEO_MX2
 	tristate "i.MX27 Camera Sensor Interface driver"
-	depends on VIDEO_DEV && SOC_CAMERA && SOC_IMX27
+	depends on VIDEO_DEV && SOC_CAMERA
+	depends on SOC_IMX27 || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	---help---
 	  This is a v4l2 driver for the i.MX27 Camera Sensor Interface
 
 config VIDEO_ATMEL_ISI
 	tristate "ATMEL Image Sensor Interface (ISI) support"
-	depends on VIDEO_DEV && SOC_CAMERA && ARCH_AT91
+	depends on VIDEO_DEV && SOC_CAMERA
+	depends on ARCH_AT91 || COMPILE_TEST
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	---help---
 	  This module makes the ATMEL Image Sensor Interface available
diff --git a/drivers/media/platform/soc_camera/atmel-isi.c b/drivers/media/platform/soc_camera/atmel-isi.c
index 3408b045b3f1..c5291b001057 100644
--- a/drivers/media/platform/soc_camera/atmel-isi.c
+++ b/drivers/media/platform/soc_camera/atmel-isi.c
@@ -54,7 +54,7 @@ static void set_dma_ctrl(struct fbd *fb_desc, u32 ctrl)
 struct isi_dma_desc {
 	struct list_head list;
 	struct fbd *p_fbd;
-	u32 fbd_phys;
+	dma_addr_t fbd_phys;
 };
 
 /* Frame buffer data */
@@ -75,7 +75,7 @@ struct atmel_isi {
 
 	/* Allocate descriptors for dma buffer use */
 	struct fbd			*p_fb_descriptors;
-	u32				fb_descriptors_phys;
+	dma_addr_t			fb_descriptors_phys;
 	struct				list_head dma_desc_head;
 	struct isi_dma_desc		dma_desc[MAX_BUFFER_NUM];
 
@@ -169,7 +169,7 @@ static irqreturn_t atmel_isi_handle_streaming(struct atmel_isi *isi)
 		isi->active = list_entry(isi->video_buffer_list.next,
 					struct frame_buffer, list);
 		isi_writel(isi, ISI_DMA_C_DSCR,
-			isi->active->p_dma_desc->fbd_phys);
+			(u32)isi->active->p_dma_desc->fbd_phys);
 		isi_writel(isi, ISI_DMA_C_CTRL,
 			ISI_DMA_CTRL_FETCH | ISI_DMA_CTRL_DONE);
 		isi_writel(isi, ISI_DMA_CHER, ISI_DMA_CHSR_C_CH);
@@ -346,7 +346,7 @@ static void start_dma(struct atmel_isi *isi, struct frame_buffer *buffer)
 		return;
 	}
 
-	isi_writel(isi, ISI_DMA_C_DSCR, buffer->p_dma_desc->fbd_phys);
+	isi_writel(isi, ISI_DMA_C_DSCR, (u32)buffer->p_dma_desc->fbd_phys);
 	isi_writel(isi, ISI_DMA_C_CTRL, ISI_DMA_CTRL_FETCH | ISI_DMA_CTRL_DONE);
 	isi_writel(isi, ISI_DMA_CHER, ISI_DMA_CHSR_C_CH);
 
@@ -384,7 +384,6 @@ static int start_streaming(struct vb2_queue *vq, unsigned int count)
 	struct soc_camera_device *icd = soc_camera_from_vb2q(vq);
 	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
 	struct atmel_isi *isi = ici->priv;
-	u32 sr = 0;
 	int ret;
 
 	/* Reset ISI */
@@ -394,11 +393,11 @@ static int start_streaming(struct vb2_queue *vq, unsigned int count)
 		return ret;
 	}
 	/* Disable all interrupts */
-	isi_writel(isi, ISI_INTDIS, ~0UL);
+	isi_writel(isi, ISI_INTDIS, (u32)~0UL);
 
 	spin_lock_irq(&isi->lock);
 	/* Clear any pending interrupt */
-	sr = isi_readl(isi, ISI_STATUS);
+	isi_readl(isi, ISI_STATUS);
 
 	if (count)
 		start_dma(isi, isi->active);
diff --git a/drivers/media/platform/soc_camera/mx2_camera.c b/drivers/media/platform/soc_camera/mx2_camera.c
index b40bc2e5ba47..2347612a4cc1 100644
--- a/drivers/media/platform/soc_camera/mx2_camera.c
+++ b/drivers/media/platform/soc_camera/mx2_camera.c
@@ -809,10 +809,9 @@ static int mx2_camera_init_videobuf(struct vb2_queue *q,
 
 static int mx27_camera_emma_prp_reset(struct mx2_camera_dev *pcdev)
 {
-	u32 cntl;
 	int count = 0;
 
-	cntl = readl(pcdev->base_emma + PRP_CNTL);
+	readl(pcdev->base_emma + PRP_CNTL);
 	writel(PRP_CNTL_SWRST, pcdev->base_emma + PRP_CNTL);
 	while (count++ < 100) {
 		if (!(readl(pcdev->base_emma + PRP_CNTL) & PRP_CNTL_SWRST))
@@ -1003,7 +1002,7 @@ static int mx2_emmaprp_resize(struct mx2_camera_dev *pcdev,
 			      struct v4l2_mbus_framefmt *mf_in,
 			      struct v4l2_pix_format *pix_out, bool apply)
 {
-	int num, den;
+	unsigned int num, den;
 	unsigned long m;
 	int i, dir;
 
diff --git a/drivers/media/platform/soc_camera/mx3_camera.c b/drivers/media/platform/soc_camera/mx3_camera.c
index 83315dfeef62..7696a873510d 100644
--- a/drivers/media/platform/soc_camera/mx3_camera.c
+++ b/drivers/media/platform/soc_camera/mx3_camera.c
@@ -415,10 +415,8 @@ static void mx3_stop_streaming(struct vb2_queue *q)
 	struct mx3_camera_buffer *buf, *tmp;
 	unsigned long flags;
 
-	if (ichan) {
-		struct dma_chan *chan = &ichan->dma_chan;
-		chan->device->device_control(chan, DMA_PAUSE, 0);
-	}
+	if (ichan)
+		dmaengine_pause(&ichan->dma_chan);
 
 	spin_lock_irqsave(&mx3_cam->lock, flags);
 
diff --git a/drivers/media/platform/soc_camera/pxa_camera.c b/drivers/media/platform/soc_camera/pxa_camera.c
index 64dc80ccd6f9..66178fc9f9eb 100644
--- a/drivers/media/platform/soc_camera/pxa_camera.c
+++ b/drivers/media/platform/soc_camera/pxa_camera.c
@@ -1694,7 +1694,7 @@ static int pxa_camera_pdata_from_dt(struct device *dev,
 		break;
 	default:
 		break;
-	};
+	}
 
 	if (ep.bus.parallel.flags & V4L2_MBUS_MASTER)
 		pcdev->platform_flags |= PXA_CAMERA_MASTER;
diff --git a/drivers/media/platform/soc_camera/rcar_vin.c b/drivers/media/platform/soc_camera/rcar_vin.c
index 85d579f65f52..20defcb8b31b 100644
--- a/drivers/media/platform/soc_camera/rcar_vin.c
+++ b/drivers/media/platform/soc_camera/rcar_vin.c
@@ -981,7 +981,7 @@ static int rcar_vin_get_formats(struct soc_camera_device *icd, unsigned int idx,
 
 		if (shift == 3) {
 			dev_err(dev,
-				"Failed to configure the client below %ux%x\n",
+				"Failed to configure the client below %ux%u\n",
 				mf.width, mf.height);
 			return -EIO;
 		}
@@ -1502,7 +1502,7 @@ static int rcar_vin_probe(struct platform_device *pdev)
 	} else {
 		priv->ici.nr = of_alias_get_id(pdev->dev.of_node, "vin");
 		priv->chip = (enum chip_id)match->data;
-	};
+	}
 
 	spin_lock_init(&priv->lock);
 	INIT_LIST_HEAD(&priv->capture);
diff --git a/drivers/media/platform/soc_camera/soc_camera.c b/drivers/media/platform/soc_camera/soc_camera.c
index f4308fed5431..8e61b976da19 100644
--- a/drivers/media/platform/soc_camera/soc_camera.c
+++ b/drivers/media/platform/soc_camera/soc_camera.c
@@ -437,6 +437,22 @@ static int soc_camera_prepare_buf(struct file *file, void *priv,
 		return vb2_prepare_buf(&icd->vb2_vidq, b);
 }
 
+static int soc_camera_expbuf(struct file *file, void *priv,
+			     struct v4l2_exportbuffer *p)
+{
+	struct soc_camera_device *icd = file->private_data;
+	struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
+
+	if (icd->streamer != file)
+		return -EBUSY;
+
+	/* videobuf2 only */
+	if (ici->ops->init_videobuf)
+		return -EINVAL;
+	else
+		return vb2_expbuf(&icd->vb2_vidq, p);
+}
+
 /* Always entered with .host_lock held */
 static int soc_camera_init_user_formats(struct soc_camera_device *icd)
 {
@@ -1347,13 +1363,11 @@ static int soc_camera_i2c_init(struct soc_camera_device *icd,
 		return -ENODEV;
 	}
 
-	ssdd = kzalloc(sizeof(*ssdd), GFP_KERNEL);
+	ssdd = kmemdup(&sdesc->subdev_desc, sizeof(*ssdd), GFP_KERNEL);
 	if (!ssdd) {
 		ret = -ENOMEM;
 		goto ealloc;
 	}
-
-	memcpy(ssdd, &sdesc->subdev_desc, sizeof(*ssdd));
 	/*
 	 * In synchronous case we request regulators ourselves in
 	 * soc_camera_pdrv_probe(), make sure the subdevice driver doesn't try
@@ -2085,6 +2099,7 @@ static const struct v4l2_ioctl_ops soc_camera_ioctl_ops = {
 	.vidioc_dqbuf		 = soc_camera_dqbuf,
 	.vidioc_create_bufs	 = soc_camera_create_bufs,
 	.vidioc_prepare_buf	 = soc_camera_prepare_buf,
+	.vidioc_expbuf		 = soc_camera_expbuf,
 	.vidioc_streamon	 = soc_camera_streamon,
 	.vidioc_streamoff	 = soc_camera_streamoff,
 	.vidioc_cropcap		 = soc_camera_cropcap,
diff --git a/drivers/media/platform/ti-vpe/vpdma.c b/drivers/media/platform/ti-vpe/vpdma.c
index a51a01359805..3e2e3a33e6ed 100644
--- a/drivers/media/platform/ti-vpe/vpdma.c
+++ b/drivers/media/platform/ti-vpe/vpdma.c
@@ -329,7 +329,7 @@ int vpdma_alloc_desc_buf(struct vpdma_buf *buf, size_t size)
 	if (!buf->addr)
 		return -ENOMEM;
 
-	WARN_ON((u32) buf->addr & VPDMA_DESC_ALIGN);
+	WARN_ON(((unsigned long)buf->addr & VPDMA_DESC_ALIGN) != 0);
 
 	return 0;
 }
@@ -584,7 +584,7 @@ static void dump_dtd(struct vpdma_dtd *dtd)
 		pr_debug("word1: line_length = %d, xfer_height = %d\n",
 			dtd_get_line_length(dtd), dtd_get_xfer_height(dtd));
 
-	pr_debug("word2: start_addr = 0x%08x\n", dtd->start_addr);
+	pr_debug("word2: start_addr = %pad\n", &dtd->start_addr);
 
 	pr_debug("word3: pkt_type = %d, mode = %d, dir = %d, chan = %d, "
 		"pri = %d, next_chan = %d\n", dtd_get_pkt_type(dtd),
diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c
index 972f43f69206..9a081c291159 100644
--- a/drivers/media/platform/ti-vpe/vpe.c
+++ b/drivers/media/platform/ti-vpe/vpe.c
@@ -31,6 +31,7 @@
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 #include <linux/log2.h>
+#include <linux/sizes.h>
 
 #include <media/v4l2-common.h>
 #include <media/v4l2-ctrls.h>
@@ -138,12 +139,12 @@ struct vpe_dei_regs {
  * default expert DEI register values, unlikely to be modified.
  */
 static const struct vpe_dei_regs dei_regs = {
-	0x020C0804u,
-	0x0118100Fu,
-	0x08040200u,
-	0x1010100Cu,
-	0x10101010u,
-	0x10101010u,
+	.mdt_spacial_freq_thr_reg = 0x020C0804u,
+	.edi_config_reg = 0x0118100Fu,
+	.edi_lut_reg0 = 0x08040200u,
+	.edi_lut_reg1 = 0x1010100Cu,
+	.edi_lut_reg2 = 0x10101010u,
+	.edi_lut_reg3 = 0x10101010u,
 };
 
 /*
@@ -834,10 +835,10 @@ static int set_srcdst_params(struct vpe_ctx *ctx)
 					VPDMA_STRIDE_ALIGN);
 		mv_buf_size = bytes_per_line * s_q_data->height;
 
-		ctx->deinterlacing = 1;
+		ctx->deinterlacing = true;
 		src_h <<= 1;
 	} else {
-		ctx->deinterlacing = 0;
+		ctx->deinterlacing = false;
 		mv_buf_size = 0;
 	}
 
@@ -2343,8 +2344,7 @@ v4l2_dev_unreg:
 
 static int vpe_remove(struct platform_device *pdev)
 {
-	struct vpe_dev *dev =
-		(struct vpe_dev *) platform_get_drvdata(pdev);
+	struct vpe_dev *dev = platform_get_drvdata(pdev);
 
 	v4l2_info(&dev->v4l2_dev, "Removing " VPE_MODULE_NAME);
 
diff --git a/drivers/media/platform/via-camera.c b/drivers/media/platform/via-camera.c
index b4f9d03636e3..ae6870cb8339 100644
--- a/drivers/media/platform/via-camera.c
+++ b/drivers/media/platform/via-camera.c
@@ -18,6 +18,7 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-ctrls.h>
+#include <media/v4l2-image-sizes.h>
 #include <media/ov7670.h>
 #include <media/videobuf-dma-sg.h>
 #include <linux/delay.h>
@@ -49,14 +50,6 @@ MODULE_PARM_DESC(override_serial,
 		"to force-enable the camera.");
 
 /*
- * Basic window sizes.
- */
-#define VGA_WIDTH	640
-#define VGA_HEIGHT	480
-#define QCIF_WIDTH	176
-#define	QCIF_HEIGHT	144
-
-/*
  * The structure describing our camera.
  */
 enum viacam_opstate { S_IDLE = 0, S_RUNNING = 1 };
@@ -89,7 +82,7 @@ struct via_camera {
 	 * live in frame buffer memory, so we don't call them "DMA".
 	 */
 	unsigned int cb_offsets[3];	/* offsets into fb mem */
-	u8 *cb_addrs[3];		/* Kernel-space addresses */
+	u8 __iomem *cb_addrs[3];		/* Kernel-space addresses */
 	int n_cap_bufs;			/* How many are we using? */
 	int next_buf;
 	struct videobuf_queue vb_queue;
@@ -1283,7 +1276,7 @@ static bool viacam_serial_is_enabled(void)
 			VIACAM_SERIAL_CREG, &cbyte);
 	if ((cbyte & VIACAM_SERIAL_BIT) == 0)
 		return false; /* Not enabled */
-	if (override_serial == 0) {
+	if (!override_serial) {
 		printk(KERN_NOTICE "Via camera: serial port is enabled, " \
 				"refusing to load.\n");
 		printk(KERN_NOTICE "Specify override_serial=1 to force " \
diff --git a/drivers/media/platform/vivi.c b/drivers/media/platform/vivi.c
deleted file mode 100644
index 80333714ffa7..000000000000
--- a/drivers/media/platform/vivi.c
+++ /dev/null
@@ -1,1542 +0,0 @@
-/*
- * Virtual Video driver - This code emulates a real video device with v4l2 api
- *
- * Copyright (c) 2006 by:
- *      Mauro Carvalho Chehab <mchehab--a.t--infradead.org>
- *      Ted Walther <ted--a.t--enumera.com>
- *      John Sokol <sokol--a.t--videotechnology.com>
- *      http://v4l.videotechnology.com/
- *
- *      Conversion to videobuf2 by Pawel Osciak & Marek Szyprowski
- *      Copyright (c) 2010 Samsung Electronics
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the BSD Licence, GNU General Public License
- * as published by the Free Software Foundation; either version 2 of the
- * License, or (at your option) any later version
- */
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/font.h>
-#include <linux/mutex.h>
-#include <linux/videodev2.h>
-#include <linux/kthread.h>
-#include <linux/freezer.h>
-#include <media/videobuf2-vmalloc.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-ioctl.h>
-#include <media/v4l2-ctrls.h>
-#include <media/v4l2-fh.h>
-#include <media/v4l2-event.h>
-#include <media/v4l2-common.h>
-
-#define VIVI_MODULE_NAME "vivi"
-
-/* Maximum allowed frame rate
- *
- * Vivi will allow setting timeperframe in [1/FPS_MAX - FPS_MAX/1] range.
- *
- * Ideally FPS_MAX should be infinity, i.e. practically UINT_MAX, but that
- * might hit application errors when they manipulate these values.
- *
- * Besides, for tpf < 1ms image-generation logic should be changed, to avoid
- * producing frames with equal content.
- */
-#define FPS_MAX 1000
-
-#define MAX_WIDTH 1920
-#define MAX_HEIGHT 1200
-
-#define VIVI_VERSION "0.8.1"
-
-MODULE_DESCRIPTION("Video Technology Magazine Virtual Video Capture Board");
-MODULE_AUTHOR("Mauro Carvalho Chehab, Ted Walther and John Sokol");
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(VIVI_VERSION);
-
-static unsigned video_nr = -1;
-module_param(video_nr, uint, 0644);
-MODULE_PARM_DESC(video_nr, "videoX start number, -1 is autodetect");
-
-static unsigned n_devs = 1;
-module_param(n_devs, uint, 0644);
-MODULE_PARM_DESC(n_devs, "number of video devices to create");
-
-static unsigned debug;
-module_param(debug, uint, 0644);
-MODULE_PARM_DESC(debug, "activates debug info");
-
-/* Global font descriptor */
-static const u8 *font8x16;
-
-/* timeperframe: min/max and default */
-static const struct v4l2_fract
-	tpf_min     = {.numerator = 1,		.denominator = FPS_MAX},
-	tpf_max     = {.numerator = FPS_MAX,	.denominator = 1},
-	tpf_default = {.numerator = 1001,	.denominator = 30000};	/* NTSC */
-
-#define dprintk(dev, level, fmt, arg...) \
-	v4l2_dbg(level, debug, &dev->v4l2_dev, fmt, ## arg)
-
-/* ------------------------------------------------------------------
-	Basic structures
-   ------------------------------------------------------------------*/
-
-struct vivi_fmt {
-	const char *name;
-	u32   fourcc;          /* v4l2 format id */
-	u8    depth;
-	bool  is_yuv;
-};
-
-static const struct vivi_fmt formats[] = {
-	{
-		.name     = "4:2:2, packed, YUYV",
-		.fourcc   = V4L2_PIX_FMT_YUYV,
-		.depth    = 16,
-		.is_yuv   = true,
-	},
-	{
-		.name     = "4:2:2, packed, UYVY",
-		.fourcc   = V4L2_PIX_FMT_UYVY,
-		.depth    = 16,
-		.is_yuv   = true,
-	},
-	{
-		.name     = "4:2:2, packed, YVYU",
-		.fourcc   = V4L2_PIX_FMT_YVYU,
-		.depth    = 16,
-		.is_yuv   = true,
-	},
-	{
-		.name     = "4:2:2, packed, VYUY",
-		.fourcc   = V4L2_PIX_FMT_VYUY,
-		.depth    = 16,
-		.is_yuv   = true,
-	},
-	{
-		.name     = "RGB565 (LE)",
-		.fourcc   = V4L2_PIX_FMT_RGB565, /* gggbbbbb rrrrrggg */
-		.depth    = 16,
-	},
-	{
-		.name     = "RGB565 (BE)",
-		.fourcc   = V4L2_PIX_FMT_RGB565X, /* rrrrrggg gggbbbbb */
-		.depth    = 16,
-	},
-	{
-		.name     = "RGB555 (LE)",
-		.fourcc   = V4L2_PIX_FMT_RGB555, /* gggbbbbb arrrrrgg */
-		.depth    = 16,
-	},
-	{
-		.name     = "RGB555 (BE)",
-		.fourcc   = V4L2_PIX_FMT_RGB555X, /* arrrrrgg gggbbbbb */
-		.depth    = 16,
-	},
-	{
-		.name     = "RGB24 (LE)",
-		.fourcc   = V4L2_PIX_FMT_RGB24, /* rgb */
-		.depth    = 24,
-	},
-	{
-		.name     = "RGB24 (BE)",
-		.fourcc   = V4L2_PIX_FMT_BGR24, /* bgr */
-		.depth    = 24,
-	},
-	{
-		.name     = "RGB32 (LE)",
-		.fourcc   = V4L2_PIX_FMT_RGB32, /* argb */
-		.depth    = 32,
-	},
-	{
-		.name     = "RGB32 (BE)",
-		.fourcc   = V4L2_PIX_FMT_BGR32, /* bgra */
-		.depth    = 32,
-	},
-};
-
-static const struct vivi_fmt *__get_format(u32 pixelformat)
-{
-	const struct vivi_fmt *fmt;
-	unsigned int k;
-
-	for (k = 0; k < ARRAY_SIZE(formats); k++) {
-		fmt = &formats[k];
-		if (fmt->fourcc == pixelformat)
-			break;
-	}
-
-	if (k == ARRAY_SIZE(formats))
-		return NULL;
-
-	return &formats[k];
-}
-
-static const struct vivi_fmt *get_format(struct v4l2_format *f)
-{
-	return __get_format(f->fmt.pix.pixelformat);
-}
-
-/* buffer for one video frame */
-struct vivi_buffer {
-	/* common v4l buffer stuff -- must be first */
-	struct vb2_buffer	vb;
-	struct list_head	list;
-};
-
-struct vivi_dmaqueue {
-	struct list_head       active;
-
-	/* thread for generating video stream*/
-	struct task_struct         *kthread;
-	wait_queue_head_t          wq;
-	/* Counters to control fps rate */
-	int                        frame;
-	int                        ini_jiffies;
-};
-
-static LIST_HEAD(vivi_devlist);
-
-struct vivi_dev {
-	struct list_head           vivi_devlist;
-	struct v4l2_device 	   v4l2_dev;
-	struct v4l2_ctrl_handler   ctrl_handler;
-	struct video_device	   vdev;
-
-	/* controls */
-	struct v4l2_ctrl	   *brightness;
-	struct v4l2_ctrl	   *contrast;
-	struct v4l2_ctrl	   *saturation;
-	struct v4l2_ctrl	   *hue;
-	struct {
-		/* autogain/gain cluster */
-		struct v4l2_ctrl	   *autogain;
-		struct v4l2_ctrl	   *gain;
-	};
-	struct v4l2_ctrl	   *volume;
-	struct v4l2_ctrl	   *alpha;
-	struct v4l2_ctrl	   *button;
-	struct v4l2_ctrl	   *boolean;
-	struct v4l2_ctrl	   *int32;
-	struct v4l2_ctrl	   *int64;
-	struct v4l2_ctrl	   *menu;
-	struct v4l2_ctrl	   *string;
-	struct v4l2_ctrl	   *bitmask;
-	struct v4l2_ctrl	   *int_menu;
-
-	spinlock_t                 slock;
-	struct mutex		   mutex;
-
-	struct vivi_dmaqueue       vidq;
-
-	/* Several counters */
-	unsigned 		   ms;
-	unsigned long              jiffies;
-	unsigned		   button_pressed;
-
-	int			   mv_count;	/* Controls bars movement */
-
-	/* Input Number */
-	int			   input;
-
-	/* video capture */
-	const struct vivi_fmt      *fmt;
-	struct v4l2_fract          timeperframe;
-	unsigned int               width, height;
-	struct vb2_queue	   vb_vidq;
-	unsigned int		   seq_count;
-
-	u8			   bars[9][3];
-	u8			   line[MAX_WIDTH * 8] __attribute__((__aligned__(4)));
-	unsigned int		   pixelsize;
-	u8			   alpha_component;
-	u32			   textfg, textbg;
-};
-
-/* ------------------------------------------------------------------
-	DMA and thread functions
-   ------------------------------------------------------------------*/
-
-/* Bars and Colors should match positions */
-
-enum colors {
-	WHITE,
-	AMBER,
-	CYAN,
-	GREEN,
-	MAGENTA,
-	RED,
-	BLUE,
-	BLACK,
-	TEXT_BLACK,
-};
-
-/* R   G   B */
-#define COLOR_WHITE	{204, 204, 204}
-#define COLOR_AMBER	{208, 208,   0}
-#define COLOR_CYAN	{  0, 206, 206}
-#define	COLOR_GREEN	{  0, 239,   0}
-#define COLOR_MAGENTA	{239,   0, 239}
-#define COLOR_RED	{205,   0,   0}
-#define COLOR_BLUE	{  0,   0, 255}
-#define COLOR_BLACK	{  0,   0,   0}
-
-struct bar_std {
-	u8 bar[9][3];
-};
-
-/* Maximum number of bars are 10 - otherwise, the input print code
-   should be modified */
-static const struct bar_std bars[] = {
-	{	/* Standard ITU-R color bar sequence */
-		{ COLOR_WHITE, COLOR_AMBER, COLOR_CYAN, COLOR_GREEN,
-		  COLOR_MAGENTA, COLOR_RED, COLOR_BLUE, COLOR_BLACK, COLOR_BLACK }
-	}, {
-		{ COLOR_WHITE, COLOR_AMBER, COLOR_BLACK, COLOR_WHITE,
-		  COLOR_AMBER, COLOR_BLACK, COLOR_WHITE, COLOR_AMBER, COLOR_BLACK }
-	}, {
-		{ COLOR_WHITE, COLOR_CYAN, COLOR_BLACK, COLOR_WHITE,
-		  COLOR_CYAN, COLOR_BLACK, COLOR_WHITE, COLOR_CYAN, COLOR_BLACK }
-	}, {
-		{ COLOR_WHITE, COLOR_GREEN, COLOR_BLACK, COLOR_WHITE,
-		  COLOR_GREEN, COLOR_BLACK, COLOR_WHITE, COLOR_GREEN, COLOR_BLACK }
-	},
-};
-
-#define NUM_INPUTS ARRAY_SIZE(bars)
-
-#define TO_Y(r, g, b) \
-	(((16829 * r + 33039 * g + 6416 * b  + 32768) >> 16) + 16)
-/* RGB to  V(Cr) Color transform */
-#define TO_V(r, g, b) \
-	(((28784 * r - 24103 * g - 4681 * b  + 32768) >> 16) + 128)
-/* RGB to  U(Cb) Color transform */
-#define TO_U(r, g, b) \
-	(((-9714 * r - 19070 * g + 28784 * b + 32768) >> 16) + 128)
-
-/* precalculate color bar values to speed up rendering */
-static void precalculate_bars(struct vivi_dev *dev)
-{
-	u8 r, g, b;
-	int k, is_yuv;
-
-	for (k = 0; k < 9; k++) {
-		r = bars[dev->input].bar[k][0];
-		g = bars[dev->input].bar[k][1];
-		b = bars[dev->input].bar[k][2];
-		is_yuv = dev->fmt->is_yuv;
-
-		switch (dev->fmt->fourcc) {
-		case V4L2_PIX_FMT_RGB565:
-		case V4L2_PIX_FMT_RGB565X:
-			r >>= 3;
-			g >>= 2;
-			b >>= 3;
-			break;
-		case V4L2_PIX_FMT_RGB555:
-		case V4L2_PIX_FMT_RGB555X:
-			r >>= 3;
-			g >>= 3;
-			b >>= 3;
-			break;
-		case V4L2_PIX_FMT_YUYV:
-		case V4L2_PIX_FMT_UYVY:
-		case V4L2_PIX_FMT_YVYU:
-		case V4L2_PIX_FMT_VYUY:
-		case V4L2_PIX_FMT_RGB24:
-		case V4L2_PIX_FMT_BGR24:
-		case V4L2_PIX_FMT_RGB32:
-		case V4L2_PIX_FMT_BGR32:
-			break;
-		}
-
-		if (is_yuv) {
-			dev->bars[k][0] = TO_Y(r, g, b);	/* Luma */
-			dev->bars[k][1] = TO_U(r, g, b);	/* Cb */
-			dev->bars[k][2] = TO_V(r, g, b);	/* Cr */
-		} else {
-			dev->bars[k][0] = r;
-			dev->bars[k][1] = g;
-			dev->bars[k][2] = b;
-		}
-	}
-}
-
-/* 'odd' is true for pixels 1, 3, 5, etc. and false for pixels 0, 2, 4, etc. */
-static void gen_twopix(struct vivi_dev *dev, u8 *buf, int colorpos, bool odd)
-{
-	u8 r_y, g_u, b_v;
-	u8 alpha = dev->alpha_component;
-	int color;
-	u8 *p;
-
-	r_y = dev->bars[colorpos][0]; /* R or precalculated Y */
-	g_u = dev->bars[colorpos][1]; /* G or precalculated U */
-	b_v = dev->bars[colorpos][2]; /* B or precalculated V */
-
-	for (color = 0; color < dev->pixelsize; color++) {
-		p = buf + color;
-
-		switch (dev->fmt->fourcc) {
-		case V4L2_PIX_FMT_YUYV:
-			switch (color) {
-			case 0:
-				*p = r_y;
-				break;
-			case 1:
-				*p = odd ? b_v : g_u;
-				break;
-			}
-			break;
-		case V4L2_PIX_FMT_UYVY:
-			switch (color) {
-			case 0:
-				*p = odd ? b_v : g_u;
-				break;
-			case 1:
-				*p = r_y;
-				break;
-			}
-			break;
-		case V4L2_PIX_FMT_YVYU:
-			switch (color) {
-			case 0:
-				*p = r_y;
-				break;
-			case 1:
-				*p = odd ? g_u : b_v;
-				break;
-			}
-			break;
-		case V4L2_PIX_FMT_VYUY:
-			switch (color) {
-			case 0:
-				*p = odd ? g_u : b_v;
-				break;
-			case 1:
-				*p = r_y;
-				break;
-			}
-			break;
-		case V4L2_PIX_FMT_RGB565:
-			switch (color) {
-			case 0:
-				*p = (g_u << 5) | b_v;
-				break;
-			case 1:
-				*p = (r_y << 3) | (g_u >> 3);
-				break;
-			}
-			break;
-		case V4L2_PIX_FMT_RGB565X:
-			switch (color) {
-			case 0:
-				*p = (r_y << 3) | (g_u >> 3);
-				break;
-			case 1:
-				*p = (g_u << 5) | b_v;
-				break;
-			}
-			break;
-		case V4L2_PIX_FMT_RGB555:
-			switch (color) {
-			case 0:
-				*p = (g_u << 5) | b_v;
-				break;
-			case 1:
-				*p = (alpha & 0x80) | (r_y << 2) | (g_u >> 3);
-				break;
-			}
-			break;
-		case V4L2_PIX_FMT_RGB555X:
-			switch (color) {
-			case 0:
-				*p = (alpha & 0x80) | (r_y << 2) | (g_u >> 3);
-				break;
-			case 1:
-				*p = (g_u << 5) | b_v;
-				break;
-			}
-			break;
-		case V4L2_PIX_FMT_RGB24:
-			switch (color) {
-			case 0:
-				*p = r_y;
-				break;
-			case 1:
-				*p = g_u;
-				break;
-			case 2:
-				*p = b_v;
-				break;
-			}
-			break;
-		case V4L2_PIX_FMT_BGR24:
-			switch (color) {
-			case 0:
-				*p = b_v;
-				break;
-			case 1:
-				*p = g_u;
-				break;
-			case 2:
-				*p = r_y;
-				break;
-			}
-			break;
-		case V4L2_PIX_FMT_RGB32:
-			switch (color) {
-			case 0:
-				*p = alpha;
-				break;
-			case 1:
-				*p = r_y;
-				break;
-			case 2:
-				*p = g_u;
-				break;
-			case 3:
-				*p = b_v;
-				break;
-			}
-			break;
-		case V4L2_PIX_FMT_BGR32:
-			switch (color) {
-			case 0:
-				*p = b_v;
-				break;
-			case 1:
-				*p = g_u;
-				break;
-			case 2:
-				*p = r_y;
-				break;
-			case 3:
-				*p = alpha;
-				break;
-			}
-			break;
-		}
-	}
-}
-
-static void precalculate_line(struct vivi_dev *dev)
-{
-	unsigned pixsize  = dev->pixelsize;
-	unsigned pixsize2 = 2*pixsize;
-	int colorpos;
-	u8 *pos;
-
-	for (colorpos = 0; colorpos < 16; ++colorpos) {
-		u8 pix[8];
-		int wstart =  colorpos    * dev->width / 8;
-		int wend   = (colorpos+1) * dev->width / 8;
-		int w;
-
-		gen_twopix(dev, &pix[0],        colorpos % 8, 0);
-		gen_twopix(dev, &pix[pixsize],  colorpos % 8, 1);
-
-		for (w = wstart/2*2, pos = dev->line + w*pixsize; w < wend; w += 2, pos += pixsize2)
-			memcpy(pos, pix, pixsize2);
-	}
-}
-
-/* need this to do rgb24 rendering */
-typedef struct { u16 __; u8 _; } __attribute__((packed)) x24;
-
-static void gen_text(struct vivi_dev *dev, char *basep,
-					int y, int x, char *text)
-{
-	int line;
-	unsigned int width = dev->width;
-
-	/* Checks if it is possible to show string */
-	if (y + 16 >= dev->height || x + strlen(text) * 8 >= width)
-		return;
-
-	/* Print stream time */
-#define PRINTSTR(PIXTYPE) do {	\
-	PIXTYPE fg;	\
-	PIXTYPE bg;	\
-	memcpy(&fg, &dev->textfg, sizeof(PIXTYPE));	\
-	memcpy(&bg, &dev->textbg, sizeof(PIXTYPE));	\
-	\
-	for (line = 0; line < 16; line++) {	\
-		PIXTYPE *pos = (PIXTYPE *)( basep + ((y + line) * width + x) * sizeof(PIXTYPE) );	\
-		u8 *s;	\
-	\
-		for (s = text; *s; s++) {	\
-			u8 chr = font8x16[*s * 16 + line];	\
-	\
-			pos[0] = (chr & (0x01 << 7) ? fg : bg);	\
-			pos[1] = (chr & (0x01 << 6) ? fg : bg);	\
-			pos[2] = (chr & (0x01 << 5) ? fg : bg);	\
-			pos[3] = (chr & (0x01 << 4) ? fg : bg);	\
-			pos[4] = (chr & (0x01 << 3) ? fg : bg);	\
-			pos[5] = (chr & (0x01 << 2) ? fg : bg);	\
-			pos[6] = (chr & (0x01 << 1) ? fg : bg);	\
-			pos[7] = (chr & (0x01 << 0) ? fg : bg);	\
-	\
-			pos += 8;	\
-		}	\
-	}	\
-} while (0)
-
-	switch (dev->pixelsize) {
-	case 2:
-		PRINTSTR(u16); break;
-	case 4:
-		PRINTSTR(u32); break;
-	case 3:
-		PRINTSTR(x24); break;
-	}
-}
-
-static void vivi_fillbuff(struct vivi_dev *dev, struct vivi_buffer *buf)
-{
-	int stride = dev->width * dev->pixelsize;
-	int hmax = dev->height;
-	void *vbuf = vb2_plane_vaddr(&buf->vb, 0);
-	unsigned ms;
-	char str[100];
-	int h, line = 1;
-	u8 *linestart;
-	s32 gain;
-
-	if (!vbuf)
-		return;
-
-	linestart = dev->line + (dev->mv_count % dev->width) * dev->pixelsize;
-
-	for (h = 0; h < hmax; h++)
-		memcpy(vbuf + h * stride, linestart, stride);
-
-	/* Updates stream time */
-
-	gen_twopix(dev, (u8 *)&dev->textbg, TEXT_BLACK, /*odd=*/ 0);
-	gen_twopix(dev, (u8 *)&dev->textfg, WHITE, /*odd=*/ 0);
-
-	dev->ms += jiffies_to_msecs(jiffies - dev->jiffies);
-	dev->jiffies = jiffies;
-	ms = dev->ms;
-	snprintf(str, sizeof(str), " %02d:%02d:%02d:%03d ",
-			(ms / (60 * 60 * 1000)) % 24,
-			(ms / (60 * 1000)) % 60,
-			(ms / 1000) % 60,
-			ms % 1000);
-	gen_text(dev, vbuf, line++ * 16, 16, str);
-	snprintf(str, sizeof(str), " %dx%d, input %d ",
-			dev->width, dev->height, dev->input);
-	gen_text(dev, vbuf, line++ * 16, 16, str);
-
-	gain = v4l2_ctrl_g_ctrl(dev->gain);
-	mutex_lock(dev->ctrl_handler.lock);
-	snprintf(str, sizeof(str), " brightness %3d, contrast %3d, saturation %3d, hue %d ",
-			dev->brightness->cur.val,
-			dev->contrast->cur.val,
-			dev->saturation->cur.val,
-			dev->hue->cur.val);
-	gen_text(dev, vbuf, line++ * 16, 16, str);
-	snprintf(str, sizeof(str), " autogain %d, gain %3d, volume %3d, alpha 0x%02x ",
-			dev->autogain->cur.val, gain, dev->volume->cur.val,
-			dev->alpha->cur.val);
-	gen_text(dev, vbuf, line++ * 16, 16, str);
-	snprintf(str, sizeof(str), " int32 %d, int64 %lld, bitmask %08x ",
-			dev->int32->cur.val,
-			*dev->int64->p_cur.p_s64,
-			dev->bitmask->cur.val);
-	gen_text(dev, vbuf, line++ * 16, 16, str);
-	snprintf(str, sizeof(str), " boolean %d, menu %s, string \"%s\" ",
-			dev->boolean->cur.val,
-			dev->menu->qmenu[dev->menu->cur.val],
-			dev->string->p_cur.p_char);
-	gen_text(dev, vbuf, line++ * 16, 16, str);
-	snprintf(str, sizeof(str), " integer_menu %lld, value %d ",
-			dev->int_menu->qmenu_int[dev->int_menu->cur.val],
-			dev->int_menu->cur.val);
-	gen_text(dev, vbuf, line++ * 16, 16, str);
-	mutex_unlock(dev->ctrl_handler.lock);
-	if (dev->button_pressed) {
-		dev->button_pressed--;
-		snprintf(str, sizeof(str), " button pressed!");
-		gen_text(dev, vbuf, line++ * 16, 16, str);
-	}
-
-	dev->mv_count += 2;
-
-	buf->vb.v4l2_buf.field = V4L2_FIELD_INTERLACED;
-	buf->vb.v4l2_buf.sequence = dev->seq_count++;
-	v4l2_get_timestamp(&buf->vb.v4l2_buf.timestamp);
-}
-
-static void vivi_thread_tick(struct vivi_dev *dev)
-{
-	struct vivi_dmaqueue *dma_q = &dev->vidq;
-	struct vivi_buffer *buf;
-	unsigned long flags = 0;
-
-	dprintk(dev, 1, "Thread tick\n");
-
-	spin_lock_irqsave(&dev->slock, flags);
-	if (list_empty(&dma_q->active)) {
-		dprintk(dev, 1, "No active queue to serve\n");
-		spin_unlock_irqrestore(&dev->slock, flags);
-		return;
-	}
-
-	buf = list_entry(dma_q->active.next, struct vivi_buffer, list);
-	list_del(&buf->list);
-	spin_unlock_irqrestore(&dev->slock, flags);
-
-	v4l2_get_timestamp(&buf->vb.v4l2_buf.timestamp);
-
-	/* Fill buffer */
-	vivi_fillbuff(dev, buf);
-	dprintk(dev, 1, "filled buffer %p\n", buf);
-
-	vb2_buffer_done(&buf->vb, VB2_BUF_STATE_DONE);
-	dprintk(dev, 2, "[%p/%d] done\n", buf, buf->vb.v4l2_buf.index);
-}
-
-#define frames_to_ms(dev, frames)				\
-	((frames * dev->timeperframe.numerator * 1000) / dev->timeperframe.denominator)
-
-static void vivi_sleep(struct vivi_dev *dev)
-{
-	struct vivi_dmaqueue *dma_q = &dev->vidq;
-	int timeout;
-	DECLARE_WAITQUEUE(wait, current);
-
-	dprintk(dev, 1, "%s dma_q=0x%08lx\n", __func__,
-		(unsigned long)dma_q);
-
-	add_wait_queue(&dma_q->wq, &wait);
-	if (kthread_should_stop())
-		goto stop_task;
-
-	/* Calculate time to wake up */
-	timeout = msecs_to_jiffies(frames_to_ms(dev, 1));
-
-	vivi_thread_tick(dev);
-
-	schedule_timeout_interruptible(timeout);
-
-stop_task:
-	remove_wait_queue(&dma_q->wq, &wait);
-	try_to_freeze();
-}
-
-static int vivi_thread(void *data)
-{
-	struct vivi_dev *dev = data;
-
-	dprintk(dev, 1, "thread started\n");
-
-	set_freezable();
-
-	for (;;) {
-		vivi_sleep(dev);
-
-		if (kthread_should_stop())
-			break;
-	}
-	dprintk(dev, 1, "thread: exit\n");
-	return 0;
-}
-
-static int vivi_start_generating(struct vivi_dev *dev)
-{
-	struct vivi_dmaqueue *dma_q = &dev->vidq;
-
-	dprintk(dev, 1, "%s\n", __func__);
-
-	/* Resets frame counters */
-	dev->ms = 0;
-	dev->mv_count = 0;
-	dev->jiffies = jiffies;
-
-	dma_q->frame = 0;
-	dma_q->ini_jiffies = jiffies;
-	dma_q->kthread = kthread_run(vivi_thread, dev, "%s",
-				     dev->v4l2_dev.name);
-
-	if (IS_ERR(dma_q->kthread)) {
-		v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n");
-		return PTR_ERR(dma_q->kthread);
-	}
-	/* Wakes thread */
-	wake_up_interruptible(&dma_q->wq);
-
-	dprintk(dev, 1, "returning from %s\n", __func__);
-	return 0;
-}
-
-static void vivi_stop_generating(struct vivi_dev *dev)
-{
-	struct vivi_dmaqueue *dma_q = &dev->vidq;
-
-	dprintk(dev, 1, "%s\n", __func__);
-
-	/* shutdown control thread */
-	if (dma_q->kthread) {
-		kthread_stop(dma_q->kthread);
-		dma_q->kthread = NULL;
-	}
-
-	/*
-	 * Typical driver might need to wait here until dma engine stops.
-	 * In this case we can abort imiedetly, so it's just a noop.
-	 */
-
-	/* Release all active buffers */
-	while (!list_empty(&dma_q->active)) {
-		struct vivi_buffer *buf;
-		buf = list_entry(dma_q->active.next, struct vivi_buffer, list);
-		list_del(&buf->list);
-		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
-		dprintk(dev, 2, "[%p/%d] done\n", buf, buf->vb.v4l2_buf.index);
-	}
-}
-/* ------------------------------------------------------------------
-	Videobuf operations
-   ------------------------------------------------------------------*/
-static int queue_setup(struct vb2_queue *vq, const struct v4l2_format *fmt,
-				unsigned int *nbuffers, unsigned int *nplanes,
-				unsigned int sizes[], void *alloc_ctxs[])
-{
-	struct vivi_dev *dev = vb2_get_drv_priv(vq);
-	unsigned long size;
-
-	size = dev->width * dev->height * dev->pixelsize;
-	if (fmt) {
-		if (fmt->fmt.pix.sizeimage < size)
-			return -EINVAL;
-		size = fmt->fmt.pix.sizeimage;
-		/* check against insane over 8K resolution buffers */
-		if (size > 7680 * 4320 * dev->pixelsize)
-			return -EINVAL;
-	}
-
-	*nplanes = 1;
-
-	sizes[0] = size;
-
-	/*
-	 * videobuf2-vmalloc allocator is context-less so no need to set
-	 * alloc_ctxs array.
-	 */
-
-	dprintk(dev, 1, "%s, count=%d, size=%ld\n", __func__,
-		*nbuffers, size);
-
-	return 0;
-}
-
-static int buffer_prepare(struct vb2_buffer *vb)
-{
-	struct vivi_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
-	struct vivi_buffer *buf = container_of(vb, struct vivi_buffer, vb);
-	unsigned long size;
-
-	dprintk(dev, 1, "%s, field=%d\n", __func__, vb->v4l2_buf.field);
-
-	BUG_ON(NULL == dev->fmt);
-
-	/*
-	 * Theses properties only change when queue is idle, see s_fmt.
-	 * The below checks should not be performed here, on each
-	 * buffer_prepare (i.e. on each qbuf). Most of the code in this function
-	 * should thus be moved to buffer_init and s_fmt.
-	 */
-	if (dev->width  < 48 || dev->width  > MAX_WIDTH ||
-	    dev->height < 32 || dev->height > MAX_HEIGHT)
-		return -EINVAL;
-
-	size = dev->width * dev->height * dev->pixelsize;
-	if (vb2_plane_size(vb, 0) < size) {
-		dprintk(dev, 1, "%s data will not fit into plane (%lu < %lu)\n",
-				__func__, vb2_plane_size(vb, 0), size);
-		return -EINVAL;
-	}
-
-	vb2_set_plane_payload(&buf->vb, 0, size);
-
-	precalculate_bars(dev);
-	precalculate_line(dev);
-
-	return 0;
-}
-
-static void buffer_queue(struct vb2_buffer *vb)
-{
-	struct vivi_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
-	struct vivi_buffer *buf = container_of(vb, struct vivi_buffer, vb);
-	struct vivi_dmaqueue *vidq = &dev->vidq;
-	unsigned long flags = 0;
-
-	dprintk(dev, 1, "%s\n", __func__);
-
-	spin_lock_irqsave(&dev->slock, flags);
-	list_add_tail(&buf->list, &vidq->active);
-	spin_unlock_irqrestore(&dev->slock, flags);
-}
-
-static int start_streaming(struct vb2_queue *vq, unsigned int count)
-{
-	struct vivi_dev *dev = vb2_get_drv_priv(vq);
-	int err;
-
-	dprintk(dev, 1, "%s\n", __func__);
-	dev->seq_count = 0;
-	err = vivi_start_generating(dev);
-	if (err) {
-		struct vivi_buffer *buf, *tmp;
-
-		list_for_each_entry_safe(buf, tmp, &dev->vidq.active, list) {
-			list_del(&buf->list);
-			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
-		}
-	}
-	return err;
-}
-
-/* abort streaming and wait for last buffer */
-static void stop_streaming(struct vb2_queue *vq)
-{
-	struct vivi_dev *dev = vb2_get_drv_priv(vq);
-	dprintk(dev, 1, "%s\n", __func__);
-	vivi_stop_generating(dev);
-}
-
-static void vivi_lock(struct vb2_queue *vq)
-{
-	struct vivi_dev *dev = vb2_get_drv_priv(vq);
-	mutex_lock(&dev->mutex);
-}
-
-static void vivi_unlock(struct vb2_queue *vq)
-{
-	struct vivi_dev *dev = vb2_get_drv_priv(vq);
-	mutex_unlock(&dev->mutex);
-}
-
-
-static const struct vb2_ops vivi_video_qops = {
-	.queue_setup		= queue_setup,
-	.buf_prepare		= buffer_prepare,
-	.buf_queue		= buffer_queue,
-	.start_streaming	= start_streaming,
-	.stop_streaming		= stop_streaming,
-	.wait_prepare		= vivi_unlock,
-	.wait_finish		= vivi_lock,
-};
-
-/* ------------------------------------------------------------------
-	IOCTL vidioc handling
-   ------------------------------------------------------------------*/
-static int vidioc_querycap(struct file *file, void  *priv,
-					struct v4l2_capability *cap)
-{
-	struct vivi_dev *dev = video_drvdata(file);
-
-	strcpy(cap->driver, "vivi");
-	strcpy(cap->card, "vivi");
-	snprintf(cap->bus_info, sizeof(cap->bus_info),
-			"platform:%s", dev->v4l2_dev.name);
-	cap->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING |
-			    V4L2_CAP_READWRITE;
-	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
-	return 0;
-}
-
-static int vidioc_enum_fmt_vid_cap(struct file *file, void  *priv,
-					struct v4l2_fmtdesc *f)
-{
-	const struct vivi_fmt *fmt;
-
-	if (f->index >= ARRAY_SIZE(formats))
-		return -EINVAL;
-
-	fmt = &formats[f->index];
-
-	strlcpy(f->description, fmt->name, sizeof(f->description));
-	f->pixelformat = fmt->fourcc;
-	return 0;
-}
-
-static int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
-					struct v4l2_format *f)
-{
-	struct vivi_dev *dev = video_drvdata(file);
-
-	f->fmt.pix.width        = dev->width;
-	f->fmt.pix.height       = dev->height;
-	f->fmt.pix.field        = V4L2_FIELD_INTERLACED;
-	f->fmt.pix.pixelformat  = dev->fmt->fourcc;
-	f->fmt.pix.bytesperline =
-		(f->fmt.pix.width * dev->fmt->depth) >> 3;
-	f->fmt.pix.sizeimage =
-		f->fmt.pix.height * f->fmt.pix.bytesperline;
-	if (dev->fmt->is_yuv)
-		f->fmt.pix.colorspace = V4L2_COLORSPACE_SMPTE170M;
-	else
-		f->fmt.pix.colorspace = V4L2_COLORSPACE_SRGB;
-	return 0;
-}
-
-static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
-			struct v4l2_format *f)
-{
-	struct vivi_dev *dev = video_drvdata(file);
-	const struct vivi_fmt *fmt;
-
-	fmt = get_format(f);
-	if (!fmt) {
-		dprintk(dev, 1, "Fourcc format (0x%08x) unknown.\n",
-			f->fmt.pix.pixelformat);
-		f->fmt.pix.pixelformat = V4L2_PIX_FMT_YUYV;
-		fmt = get_format(f);
-	}
-
-	f->fmt.pix.field = V4L2_FIELD_INTERLACED;
-	v4l_bound_align_image(&f->fmt.pix.width, 48, MAX_WIDTH, 2,
-			      &f->fmt.pix.height, 32, MAX_HEIGHT, 0, 0);
-	f->fmt.pix.bytesperline =
-		(f->fmt.pix.width * fmt->depth) >> 3;
-	f->fmt.pix.sizeimage =
-		f->fmt.pix.height * f->fmt.pix.bytesperline;
-	if (fmt->is_yuv)
-		f->fmt.pix.colorspace = V4L2_COLORSPACE_SMPTE170M;
-	else
-		f->fmt.pix.colorspace = V4L2_COLORSPACE_SRGB;
-	return 0;
-}
-
-static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
-					struct v4l2_format *f)
-{
-	struct vivi_dev *dev = video_drvdata(file);
-	struct vb2_queue *q = &dev->vb_vidq;
-
-	int ret = vidioc_try_fmt_vid_cap(file, priv, f);
-	if (ret < 0)
-		return ret;
-
-	if (vb2_is_busy(q)) {
-		dprintk(dev, 1, "%s device busy\n", __func__);
-		return -EBUSY;
-	}
-
-	dev->fmt = get_format(f);
-	dev->pixelsize = dev->fmt->depth / 8;
-	dev->width = f->fmt.pix.width;
-	dev->height = f->fmt.pix.height;
-
-	return 0;
-}
-
-static int vidioc_enum_framesizes(struct file *file, void *fh,
-					 struct v4l2_frmsizeenum *fsize)
-{
-	static const struct v4l2_frmsize_stepwise sizes = {
-		48, MAX_WIDTH, 4,
-		32, MAX_HEIGHT, 1
-	};
-	int i;
-
-	if (fsize->index)
-		return -EINVAL;
-	for (i = 0; i < ARRAY_SIZE(formats); i++)
-		if (formats[i].fourcc == fsize->pixel_format)
-			break;
-	if (i == ARRAY_SIZE(formats))
-		return -EINVAL;
-	fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE;
-	fsize->stepwise = sizes;
-	return 0;
-}
-
-/* only one input in this sample driver */
-static int vidioc_enum_input(struct file *file, void *priv,
-				struct v4l2_input *inp)
-{
-	if (inp->index >= NUM_INPUTS)
-		return -EINVAL;
-
-	inp->type = V4L2_INPUT_TYPE_CAMERA;
-	sprintf(inp->name, "Camera %u", inp->index);
-	return 0;
-}
-
-static int vidioc_g_input(struct file *file, void *priv, unsigned int *i)
-{
-	struct vivi_dev *dev = video_drvdata(file);
-
-	*i = dev->input;
-	return 0;
-}
-
-static int vidioc_s_input(struct file *file, void *priv, unsigned int i)
-{
-	struct vivi_dev *dev = video_drvdata(file);
-
-	if (i >= NUM_INPUTS)
-		return -EINVAL;
-
-	if (i == dev->input)
-		return 0;
-
-	dev->input = i;
-	/*
-	 * Modify the brightness range depending on the input.
-	 * This makes it easy to use vivi to test if applications can
-	 * handle control range modifications and is also how this is
-	 * typically used in practice as different inputs may be hooked
-	 * up to different receivers with different control ranges.
-	 */
-	v4l2_ctrl_modify_range(dev->brightness,
-			128 * i, 255 + 128 * i, 1, 127 + 128 * i);
-	precalculate_bars(dev);
-	precalculate_line(dev);
-	return 0;
-}
-
-/* timeperframe is arbitrary and continuous */
-static int vidioc_enum_frameintervals(struct file *file, void *priv,
-					     struct v4l2_frmivalenum *fival)
-{
-	const struct vivi_fmt *fmt;
-
-	if (fival->index)
-		return -EINVAL;
-
-	fmt = __get_format(fival->pixel_format);
-	if (!fmt)
-		return -EINVAL;
-
-	/* check for valid width/height */
-	if (fival->width < 48 || fival->width > MAX_WIDTH || (fival->width & 3))
-		return -EINVAL;
-	if (fival->height < 32 || fival->height > MAX_HEIGHT)
-		return -EINVAL;
-
-	fival->type = V4L2_FRMIVAL_TYPE_CONTINUOUS;
-
-	/* fill in stepwise (step=1.0 is required by V4L2 spec) */
-	fival->stepwise.min  = tpf_min;
-	fival->stepwise.max  = tpf_max;
-	fival->stepwise.step = (struct v4l2_fract) {1, 1};
-
-	return 0;
-}
-
-static int vidioc_g_parm(struct file *file, void *priv,
-			  struct v4l2_streamparm *parm)
-{
-	struct vivi_dev *dev = video_drvdata(file);
-
-	if (parm->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		return -EINVAL;
-
-	parm->parm.capture.capability   = V4L2_CAP_TIMEPERFRAME;
-	parm->parm.capture.timeperframe = dev->timeperframe;
-	parm->parm.capture.readbuffers  = 1;
-	return 0;
-}
-
-#define FRACT_CMP(a, OP, b)	\
-	((u64)(a).numerator * (b).denominator  OP  (u64)(b).numerator * (a).denominator)
-
-static int vidioc_s_parm(struct file *file, void *priv,
-			  struct v4l2_streamparm *parm)
-{
-	struct vivi_dev *dev = video_drvdata(file);
-	struct v4l2_fract tpf;
-
-	if (parm->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		return -EINVAL;
-
-	tpf = parm->parm.capture.timeperframe;
-
-	/* tpf: {*, 0} resets timing; clip to [min, max]*/
-	tpf = tpf.denominator ? tpf : tpf_default;
-	tpf = FRACT_CMP(tpf, <, tpf_min) ? tpf_min : tpf;
-	tpf = FRACT_CMP(tpf, >, tpf_max) ? tpf_max : tpf;
-
-	dev->timeperframe = tpf;
-	parm->parm.capture.timeperframe = tpf;
-	parm->parm.capture.readbuffers  = 1;
-	return 0;
-}
-
-/* --- controls ---------------------------------------------- */
-
-static int vivi_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
-{
-	struct vivi_dev *dev = container_of(ctrl->handler, struct vivi_dev, ctrl_handler);
-
-	if (ctrl == dev->autogain)
-		dev->gain->val = jiffies & 0xff;
-	return 0;
-}
-
-static int vivi_s_ctrl(struct v4l2_ctrl *ctrl)
-{
-	struct vivi_dev *dev = container_of(ctrl->handler, struct vivi_dev, ctrl_handler);
-
-	switch (ctrl->id) {
-	case V4L2_CID_ALPHA_COMPONENT:
-		dev->alpha_component = ctrl->val;
-		break;
-	default:
-		if (ctrl == dev->button)
-			dev->button_pressed = 30;
-		break;
-	}
-	return 0;
-}
-
-/* ------------------------------------------------------------------
-	File operations for the device
-   ------------------------------------------------------------------*/
-
-static const struct v4l2_ctrl_ops vivi_ctrl_ops = {
-	.g_volatile_ctrl = vivi_g_volatile_ctrl,
-	.s_ctrl = vivi_s_ctrl,
-};
-
-#define VIVI_CID_CUSTOM_BASE	(V4L2_CID_USER_BASE | 0xf000)
-
-static const struct v4l2_ctrl_config vivi_ctrl_button = {
-	.ops = &vivi_ctrl_ops,
-	.id = VIVI_CID_CUSTOM_BASE + 0,
-	.name = "Button",
-	.type = V4L2_CTRL_TYPE_BUTTON,
-};
-
-static const struct v4l2_ctrl_config vivi_ctrl_boolean = {
-	.ops = &vivi_ctrl_ops,
-	.id = VIVI_CID_CUSTOM_BASE + 1,
-	.name = "Boolean",
-	.type = V4L2_CTRL_TYPE_BOOLEAN,
-	.min = 0,
-	.max = 1,
-	.step = 1,
-	.def = 1,
-};
-
-static const struct v4l2_ctrl_config vivi_ctrl_int32 = {
-	.ops = &vivi_ctrl_ops,
-	.id = VIVI_CID_CUSTOM_BASE + 2,
-	.name = "Integer 32 Bits",
-	.type = V4L2_CTRL_TYPE_INTEGER,
-	.min = -0x80000000LL,
-	.max = 0x7fffffff,
-	.step = 1,
-};
-
-static const struct v4l2_ctrl_config vivi_ctrl_int64 = {
-	.ops = &vivi_ctrl_ops,
-	.id = VIVI_CID_CUSTOM_BASE + 3,
-	.name = "Integer 64 Bits",
-	.type = V4L2_CTRL_TYPE_INTEGER64,
-	.min = LLONG_MIN,
-	.max = LLONG_MAX,
-	.step = 1,
-};
-
-static const char * const vivi_ctrl_menu_strings[] = {
-	"Menu Item 0 (Skipped)",
-	"Menu Item 1",
-	"Menu Item 2 (Skipped)",
-	"Menu Item 3",
-	"Menu Item 4",
-	"Menu Item 5 (Skipped)",
-	NULL,
-};
-
-static const struct v4l2_ctrl_config vivi_ctrl_menu = {
-	.ops = &vivi_ctrl_ops,
-	.id = VIVI_CID_CUSTOM_BASE + 4,
-	.name = "Menu",
-	.type = V4L2_CTRL_TYPE_MENU,
-	.min = 1,
-	.max = 4,
-	.def = 3,
-	.menu_skip_mask = 0x04,
-	.qmenu = vivi_ctrl_menu_strings,
-};
-
-static const struct v4l2_ctrl_config vivi_ctrl_string = {
-	.ops = &vivi_ctrl_ops,
-	.id = VIVI_CID_CUSTOM_BASE + 5,
-	.name = "String",
-	.type = V4L2_CTRL_TYPE_STRING,
-	.min = 2,
-	.max = 4,
-	.step = 1,
-};
-
-static const struct v4l2_ctrl_config vivi_ctrl_bitmask = {
-	.ops = &vivi_ctrl_ops,
-	.id = VIVI_CID_CUSTOM_BASE + 6,
-	.name = "Bitmask",
-	.type = V4L2_CTRL_TYPE_BITMASK,
-	.def = 0x80002000,
-	.min = 0,
-	.max = 0x80402010,
-	.step = 0,
-};
-
-static const s64 vivi_ctrl_int_menu_values[] = {
-	1, 1, 2, 3, 5, 8, 13, 21, 42,
-};
-
-static const struct v4l2_ctrl_config vivi_ctrl_int_menu = {
-	.ops = &vivi_ctrl_ops,
-	.id = VIVI_CID_CUSTOM_BASE + 7,
-	.name = "Integer menu",
-	.type = V4L2_CTRL_TYPE_INTEGER_MENU,
-	.min = 1,
-	.max = 8,
-	.def = 4,
-	.menu_skip_mask = 0x02,
-	.qmenu_int = vivi_ctrl_int_menu_values,
-};
-
-static const struct v4l2_file_operations vivi_fops = {
-	.owner		= THIS_MODULE,
-	.open           = v4l2_fh_open,
-	.release        = vb2_fop_release,
-	.read           = vb2_fop_read,
-	.poll		= vb2_fop_poll,
-	.unlocked_ioctl = video_ioctl2, /* V4L2 ioctl handler */
-	.mmap           = vb2_fop_mmap,
-};
-
-static const struct v4l2_ioctl_ops vivi_ioctl_ops = {
-	.vidioc_querycap      = vidioc_querycap,
-	.vidioc_enum_fmt_vid_cap  = vidioc_enum_fmt_vid_cap,
-	.vidioc_g_fmt_vid_cap     = vidioc_g_fmt_vid_cap,
-	.vidioc_try_fmt_vid_cap   = vidioc_try_fmt_vid_cap,
-	.vidioc_s_fmt_vid_cap     = vidioc_s_fmt_vid_cap,
-	.vidioc_enum_framesizes   = vidioc_enum_framesizes,
-	.vidioc_reqbufs       = vb2_ioctl_reqbufs,
-	.vidioc_create_bufs   = vb2_ioctl_create_bufs,
-	.vidioc_prepare_buf   = vb2_ioctl_prepare_buf,
-	.vidioc_querybuf      = vb2_ioctl_querybuf,
-	.vidioc_qbuf          = vb2_ioctl_qbuf,
-	.vidioc_dqbuf         = vb2_ioctl_dqbuf,
-	.vidioc_enum_input    = vidioc_enum_input,
-	.vidioc_g_input       = vidioc_g_input,
-	.vidioc_s_input       = vidioc_s_input,
-	.vidioc_enum_frameintervals = vidioc_enum_frameintervals,
-	.vidioc_g_parm        = vidioc_g_parm,
-	.vidioc_s_parm        = vidioc_s_parm,
-	.vidioc_streamon      = vb2_ioctl_streamon,
-	.vidioc_streamoff     = vb2_ioctl_streamoff,
-	.vidioc_log_status    = v4l2_ctrl_log_status,
-	.vidioc_subscribe_event = v4l2_ctrl_subscribe_event,
-	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
-};
-
-static const struct video_device vivi_template = {
-	.name		= "vivi",
-	.fops           = &vivi_fops,
-	.ioctl_ops 	= &vivi_ioctl_ops,
-	.release	= video_device_release_empty,
-};
-
-/* -----------------------------------------------------------------
-	Initialization and module stuff
-   ------------------------------------------------------------------*/
-
-static int vivi_release(void)
-{
-	struct vivi_dev *dev;
-	struct list_head *list;
-
-	while (!list_empty(&vivi_devlist)) {
-		list = vivi_devlist.next;
-		list_del(list);
-		dev = list_entry(list, struct vivi_dev, vivi_devlist);
-
-		v4l2_info(&dev->v4l2_dev, "unregistering %s\n",
-			video_device_node_name(&dev->vdev));
-		video_unregister_device(&dev->vdev);
-		v4l2_device_unregister(&dev->v4l2_dev);
-		v4l2_ctrl_handler_free(&dev->ctrl_handler);
-		kfree(dev);
-	}
-
-	return 0;
-}
-
-static int __init vivi_create_instance(int inst)
-{
-	struct vivi_dev *dev;
-	struct video_device *vfd;
-	struct v4l2_ctrl_handler *hdl;
-	struct vb2_queue *q;
-	int ret;
-
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev)
-		return -ENOMEM;
-
-	snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name),
-			"%s-%03d", VIVI_MODULE_NAME, inst);
-	ret = v4l2_device_register(NULL, &dev->v4l2_dev);
-	if (ret)
-		goto free_dev;
-
-	dev->fmt = &formats[0];
-	dev->timeperframe = tpf_default;
-	dev->width = 640;
-	dev->height = 480;
-	dev->pixelsize = dev->fmt->depth / 8;
-	hdl = &dev->ctrl_handler;
-	v4l2_ctrl_handler_init(hdl, 11);
-	dev->volume = v4l2_ctrl_new_std(hdl, &vivi_ctrl_ops,
-			V4L2_CID_AUDIO_VOLUME, 0, 255, 1, 200);
-	dev->brightness = v4l2_ctrl_new_std(hdl, &vivi_ctrl_ops,
-			V4L2_CID_BRIGHTNESS, 0, 255, 1, 127);
-	dev->contrast = v4l2_ctrl_new_std(hdl, &vivi_ctrl_ops,
-			V4L2_CID_CONTRAST, 0, 255, 1, 16);
-	dev->saturation = v4l2_ctrl_new_std(hdl, &vivi_ctrl_ops,
-			V4L2_CID_SATURATION, 0, 255, 1, 127);
-	dev->hue = v4l2_ctrl_new_std(hdl, &vivi_ctrl_ops,
-			V4L2_CID_HUE, -128, 127, 1, 0);
-	dev->autogain = v4l2_ctrl_new_std(hdl, &vivi_ctrl_ops,
-			V4L2_CID_AUTOGAIN, 0, 1, 1, 1);
-	dev->gain = v4l2_ctrl_new_std(hdl, &vivi_ctrl_ops,
-			V4L2_CID_GAIN, 0, 255, 1, 100);
-	dev->alpha = v4l2_ctrl_new_std(hdl, &vivi_ctrl_ops,
-			V4L2_CID_ALPHA_COMPONENT, 0, 255, 1, 0);
-	dev->button = v4l2_ctrl_new_custom(hdl, &vivi_ctrl_button, NULL);
-	dev->int32 = v4l2_ctrl_new_custom(hdl, &vivi_ctrl_int32, NULL);
-	dev->int64 = v4l2_ctrl_new_custom(hdl, &vivi_ctrl_int64, NULL);
-	dev->boolean = v4l2_ctrl_new_custom(hdl, &vivi_ctrl_boolean, NULL);
-	dev->menu = v4l2_ctrl_new_custom(hdl, &vivi_ctrl_menu, NULL);
-	dev->string = v4l2_ctrl_new_custom(hdl, &vivi_ctrl_string, NULL);
-	dev->bitmask = v4l2_ctrl_new_custom(hdl, &vivi_ctrl_bitmask, NULL);
-	dev->int_menu = v4l2_ctrl_new_custom(hdl, &vivi_ctrl_int_menu, NULL);
-	if (hdl->error) {
-		ret = hdl->error;
-		goto unreg_dev;
-	}
-	v4l2_ctrl_auto_cluster(2, &dev->autogain, 0, true);
-	dev->v4l2_dev.ctrl_handler = hdl;
-
-	/* initialize locks */
-	spin_lock_init(&dev->slock);
-
-	/* initialize queue */
-	q = &dev->vb_vidq;
-	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
-	q->drv_priv = dev;
-	q->buf_struct_size = sizeof(struct vivi_buffer);
-	q->ops = &vivi_video_qops;
-	q->mem_ops = &vb2_vmalloc_memops;
-	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-
-	ret = vb2_queue_init(q);
-	if (ret)
-		goto unreg_dev;
-
-	mutex_init(&dev->mutex);
-
-	/* init video dma queues */
-	INIT_LIST_HEAD(&dev->vidq.active);
-	init_waitqueue_head(&dev->vidq.wq);
-
-	vfd = &dev->vdev;
-	*vfd = vivi_template;
-	vfd->debug = debug;
-	vfd->v4l2_dev = &dev->v4l2_dev;
-	vfd->queue = q;
-
-	/*
-	 * Provide a mutex to v4l2 core. It will be used to protect
-	 * all fops and v4l2 ioctls.
-	 */
-	vfd->lock = &dev->mutex;
-	video_set_drvdata(vfd, dev);
-
-	ret = video_register_device(vfd, VFL_TYPE_GRABBER, video_nr);
-	if (ret < 0)
-		goto unreg_dev;
-
-	/* Now that everything is fine, let's add it to device list */
-	list_add_tail(&dev->vivi_devlist, &vivi_devlist);
-
-	v4l2_info(&dev->v4l2_dev, "V4L2 device registered as %s\n",
-		  video_device_node_name(vfd));
-	return 0;
-
-unreg_dev:
-	v4l2_ctrl_handler_free(hdl);
-	v4l2_device_unregister(&dev->v4l2_dev);
-free_dev:
-	kfree(dev);
-	return ret;
-}
-
-/* This routine allocates from 1 to n_devs virtual drivers.
-
-   The real maximum number of virtual drivers will depend on how many drivers
-   will succeed. This is limited to the maximum number of devices that
-   videodev supports, which is equal to VIDEO_NUM_DEVICES.
- */
-static int __init vivi_init(void)
-{
-	const struct font_desc *font = find_font("VGA8x16");
-	int ret = 0, i;
-
-	if (font == NULL) {
-		printk(KERN_ERR "vivi: could not find font\n");
-		return -ENODEV;
-	}
-	font8x16 = font->data;
-
-	if (n_devs <= 0)
-		n_devs = 1;
-
-	for (i = 0; i < n_devs; i++) {
-		ret = vivi_create_instance(i);
-		if (ret) {
-			/* If some instantiations succeeded, keep driver */
-			if (i)
-				ret = 0;
-			break;
-		}
-	}
-
-	if (ret < 0) {
-		printk(KERN_ERR "vivi: error %d while loading driver\n", ret);
-		return ret;
-	}
-
-	printk(KERN_INFO "Video Technology Magazine Virtual Video "
-			"Capture Board ver %s successfully loaded.\n",
-			VIVI_VERSION);
-
-	/* n_devs will reflect the actual number of allocated devices */
-	n_devs = i;
-
-	return ret;
-}
-
-static void __exit vivi_exit(void)
-{
-	vivi_release();
-}
-
-module_init(vivi_init);
-module_exit(vivi_exit);
diff --git a/drivers/media/platform/vivid/Kconfig b/drivers/media/platform/vivid/Kconfig
new file mode 100644
index 000000000000..d71139a2ae00
--- /dev/null
+++ b/drivers/media/platform/vivid/Kconfig
@@ -0,0 +1,19 @@
+config VIDEO_VIVID
+	tristate "Virtual Video Test Driver"
+	depends on VIDEO_DEV && VIDEO_V4L2 && !SPARC32 && !SPARC64
+	select FONT_SUPPORT
+	select FONT_8x16
+	select VIDEOBUF2_VMALLOC
+	default n
+	---help---
+	  Enables a virtual video driver. This driver emulates a webcam,
+	  TV, S-Video and HDMI capture hardware, including VBI support for
+	  the SDTV inputs. Also video output, VBI output, radio receivers,
+	  transmitters and software defined radio capture is emulated.
+
+	  It is highly configurable and is ideal for testing applications.
+	  Error injection is supported to test rare errors that are hard
+	  to reproduce in real hardware.
+
+	  Say Y here if you want to test video apps or debug V4L devices.
+	  When in doubt, say N.
diff --git a/drivers/media/platform/vivid/Makefile b/drivers/media/platform/vivid/Makefile
new file mode 100644
index 000000000000..756fc12851df
--- /dev/null
+++ b/drivers/media/platform/vivid/Makefile
@@ -0,0 +1,6 @@
+vivid-objs := vivid-core.o vivid-ctrls.o vivid-vid-common.o vivid-vbi-gen.o \
+		vivid-vid-cap.o vivid-vid-out.o vivid-kthread-cap.o vivid-kthread-out.o \
+		vivid-radio-rx.o vivid-radio-tx.o vivid-radio-common.o \
+		vivid-rds-gen.o vivid-sdr-cap.o vivid-vbi-cap.o vivid-vbi-out.o \
+		vivid-osd.o vivid-tpg.o vivid-tpg-colors.o
+obj-$(CONFIG_VIDEO_VIVID) += vivid.o
diff --git a/drivers/media/platform/vivid/vivid-core.c b/drivers/media/platform/vivid/vivid-core.c
new file mode 100644
index 000000000000..2c61a62ab48b
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-core.c
@@ -0,0 +1,1390 @@
+/*
+ * vivid-core.c - A Virtual Video Test Driver, core initialization
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/font.h>
+#include <linux/mutex.h>
+#include <linux/videodev2.h>
+#include <linux/v4l2-dv-timings.h>
+#include <media/videobuf2-vmalloc.h>
+#include <media/v4l2-dv-timings.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-event.h>
+
+#include "vivid-core.h"
+#include "vivid-vid-common.h"
+#include "vivid-vid-cap.h"
+#include "vivid-vid-out.h"
+#include "vivid-radio-common.h"
+#include "vivid-radio-rx.h"
+#include "vivid-radio-tx.h"
+#include "vivid-sdr-cap.h"
+#include "vivid-vbi-cap.h"
+#include "vivid-vbi-out.h"
+#include "vivid-osd.h"
+#include "vivid-ctrls.h"
+
+#define VIVID_MODULE_NAME "vivid"
+
+/* The maximum number of vivid devices */
+#define VIVID_MAX_DEVS 64
+
+MODULE_DESCRIPTION("Virtual Video Test Driver");
+MODULE_AUTHOR("Hans Verkuil");
+MODULE_LICENSE("GPL");
+
+static unsigned n_devs = 1;
+module_param(n_devs, uint, 0444);
+MODULE_PARM_DESC(n_devs, " number of driver instances to create");
+
+static int vid_cap_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(vid_cap_nr, int, NULL, 0444);
+MODULE_PARM_DESC(vid_cap_nr, " videoX start number, -1 is autodetect");
+
+static int vid_out_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(vid_out_nr, int, NULL, 0444);
+MODULE_PARM_DESC(vid_out_nr, " videoX start number, -1 is autodetect");
+
+static int vbi_cap_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(vbi_cap_nr, int, NULL, 0444);
+MODULE_PARM_DESC(vbi_cap_nr, " vbiX start number, -1 is autodetect");
+
+static int vbi_out_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(vbi_out_nr, int, NULL, 0444);
+MODULE_PARM_DESC(vbi_out_nr, " vbiX start number, -1 is autodetect");
+
+static int sdr_cap_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(sdr_cap_nr, int, NULL, 0444);
+MODULE_PARM_DESC(sdr_cap_nr, " swradioX start number, -1 is autodetect");
+
+static int radio_rx_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(radio_rx_nr, int, NULL, 0444);
+MODULE_PARM_DESC(radio_rx_nr, " radioX start number, -1 is autodetect");
+
+static int radio_tx_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(radio_tx_nr, int, NULL, 0444);
+MODULE_PARM_DESC(radio_tx_nr, " radioX start number, -1 is autodetect");
+
+static int ccs_cap_mode[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(ccs_cap_mode, int, NULL, 0444);
+MODULE_PARM_DESC(ccs_cap_mode, " capture crop/compose/scale mode:\n"
+			   "\t\t    bit 0=crop, 1=compose, 2=scale,\n"
+			   "\t\t    -1=user-controlled (default)");
+
+static int ccs_out_mode[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(ccs_out_mode, int, NULL, 0444);
+MODULE_PARM_DESC(ccs_out_mode, " output crop/compose/scale mode:\n"
+			   "\t\t    bit 0=crop, 1=compose, 2=scale,\n"
+			   "\t\t    -1=user-controlled (default)");
+
+static unsigned multiplanar[VIVID_MAX_DEVS];
+module_param_array(multiplanar, uint, NULL, 0444);
+MODULE_PARM_DESC(multiplanar, " 0 (default) is alternating single and multiplanar devices,\n"
+			      "\t\t    1 is single planar devices,\n"
+			      "\t\t    2 is multiplanar devices");
+
+/* Default: video + vbi-cap (raw and sliced) + radio rx + radio tx + sdr + vbi-out + vid-out */
+static unsigned node_types[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = 0x1d3d };
+module_param_array(node_types, uint, NULL, 0444);
+MODULE_PARM_DESC(node_types, " node types, default is 0x1d3d. Bitmask with the following meaning:\n"
+			     "\t\t    bit 0: Video Capture node\n"
+			     "\t\t    bit 2-3: VBI Capture node: 0 = none, 1 = raw vbi, 2 = sliced vbi, 3 = both\n"
+			     "\t\t    bit 4: Radio Receiver node\n"
+			     "\t\t    bit 5: Software Defined Radio Receiver node\n"
+			     "\t\t    bit 8: Video Output node\n"
+			     "\t\t    bit 10-11: VBI Output node: 0 = none, 1 = raw vbi, 2 = sliced vbi, 3 = both\n"
+			     "\t\t    bit 12: Radio Transmitter node\n"
+			     "\t\t    bit 16: Framebuffer for testing overlays");
+
+/* Default: 4 inputs */
+static unsigned num_inputs[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = 4 };
+module_param_array(num_inputs, uint, NULL, 0444);
+MODULE_PARM_DESC(num_inputs, " number of inputs, default is 4");
+
+/* Default: input 0 = WEBCAM, 1 = TV, 2 = SVID, 3 = HDMI */
+static unsigned input_types[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = 0xe4 };
+module_param_array(input_types, uint, NULL, 0444);
+MODULE_PARM_DESC(input_types, " input types, default is 0xe4. Two bits per input,\n"
+			      "\t\t    bits 0-1 == input 0, bits 31-30 == input 15.\n"
+			      "\t\t    Type 0 == webcam, 1 == TV, 2 == S-Video, 3 == HDMI");
+
+/* Default: 2 outputs */
+static unsigned num_outputs[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = 2 };
+module_param_array(num_outputs, uint, NULL, 0444);
+MODULE_PARM_DESC(num_outputs, " number of outputs, default is 2");
+
+/* Default: output 0 = SVID, 1 = HDMI */
+static unsigned output_types[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = 2 };
+module_param_array(output_types, uint, NULL, 0444);
+MODULE_PARM_DESC(output_types, " output types, default is 0x02. One bit per output,\n"
+			      "\t\t    bit 0 == output 0, bit 15 == output 15.\n"
+			      "\t\t    Type 0 == S-Video, 1 == HDMI");
+
+unsigned vivid_debug;
+module_param(vivid_debug, uint, 0644);
+MODULE_PARM_DESC(vivid_debug, " activates debug info");
+
+static bool no_error_inj;
+module_param(no_error_inj, bool, 0444);
+MODULE_PARM_DESC(no_error_inj, " if set disable the error injecting controls");
+
+static struct vivid_dev *vivid_devs[VIVID_MAX_DEVS];
+
+const struct v4l2_rect vivid_min_rect = {
+	0, 0, MIN_WIDTH, MIN_HEIGHT
+};
+
+const struct v4l2_rect vivid_max_rect = {
+	0, 0, MAX_WIDTH * MAX_ZOOM, MAX_HEIGHT * MAX_ZOOM
+};
+
+static const u8 vivid_hdmi_edid[256] = {
+	0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
+	0x63, 0x3a, 0xaa, 0x55, 0x00, 0x00, 0x00, 0x00,
+	0x0a, 0x18, 0x01, 0x03, 0x80, 0x10, 0x09, 0x78,
+	0x0e, 0x00, 0xb2, 0xa0, 0x57, 0x49, 0x9b, 0x26,
+	0x10, 0x48, 0x4f, 0x2f, 0xcf, 0x00, 0x31, 0x59,
+	0x45, 0x59, 0x81, 0x80, 0x81, 0x40, 0x90, 0x40,
+	0x95, 0x00, 0xa9, 0x40, 0xb3, 0x00, 0x02, 0x3a,
+	0x80, 0x18, 0x71, 0x38, 0x2d, 0x40, 0x58, 0x2c,
+	0x46, 0x00, 0x10, 0x09, 0x00, 0x00, 0x00, 0x1e,
+	0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x55, 0x18,
+	0x5e, 0x11, 0x00, 0x0a, 0x20, 0x20, 0x20, 0x20,
+	0x20, 0x20, 0x00, 0x00, 0x00, 0xfc, 0x00,  'v',
+	'4',   'l',  '2',  '-',  'h',  'd',  'm',  'i',
+	0x0a, 0x0a, 0x0a, 0x0a, 0x00, 0x00, 0x00, 0x10,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0xf0,
+
+	0x02, 0x03, 0x1a, 0xc0, 0x48, 0xa2, 0x10, 0x04,
+	0x02, 0x01, 0x21, 0x14, 0x13, 0x23, 0x09, 0x07,
+	0x07, 0x65, 0x03, 0x0c, 0x00, 0x10, 0x00, 0xe2,
+	0x00, 0x2a, 0x01, 0x1d, 0x00, 0x80, 0x51, 0xd0,
+	0x1c, 0x20, 0x40, 0x80, 0x35, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x1e, 0x8c, 0x0a, 0xd0, 0x8a,
+	0x20, 0xe0, 0x2d, 0x10, 0x10, 0x3e, 0x96, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x18, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd7
+};
+
+void vivid_lock(struct vb2_queue *vq)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+
+	mutex_lock(&dev->mutex);
+}
+
+void vivid_unlock(struct vb2_queue *vq)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+
+	mutex_unlock(&dev->mutex);
+}
+
+static int vidioc_querycap(struct file *file, void  *priv,
+					struct v4l2_capability *cap)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct video_device *vdev = video_devdata(file);
+
+	strcpy(cap->driver, "vivid");
+	strcpy(cap->card, "vivid");
+	snprintf(cap->bus_info, sizeof(cap->bus_info),
+			"platform:%s", dev->v4l2_dev.name);
+
+	if (vdev->vfl_type == VFL_TYPE_GRABBER && vdev->vfl_dir == VFL_DIR_RX)
+		cap->device_caps = dev->vid_cap_caps;
+	if (vdev->vfl_type == VFL_TYPE_GRABBER && vdev->vfl_dir == VFL_DIR_TX)
+		cap->device_caps = dev->vid_out_caps;
+	else if (vdev->vfl_type == VFL_TYPE_VBI && vdev->vfl_dir == VFL_DIR_RX)
+		cap->device_caps = dev->vbi_cap_caps;
+	else if (vdev->vfl_type == VFL_TYPE_VBI && vdev->vfl_dir == VFL_DIR_TX)
+		cap->device_caps = dev->vbi_out_caps;
+	else if (vdev->vfl_type == VFL_TYPE_SDR)
+		cap->device_caps = dev->sdr_cap_caps;
+	else if (vdev->vfl_type == VFL_TYPE_RADIO && vdev->vfl_dir == VFL_DIR_RX)
+		cap->device_caps = dev->radio_rx_caps;
+	else if (vdev->vfl_type == VFL_TYPE_RADIO && vdev->vfl_dir == VFL_DIR_TX)
+		cap->device_caps = dev->radio_tx_caps;
+	cap->capabilities = dev->vid_cap_caps | dev->vid_out_caps |
+		dev->vbi_cap_caps | dev->vbi_out_caps |
+		dev->radio_rx_caps | dev->radio_tx_caps |
+		dev->sdr_cap_caps | V4L2_CAP_DEVICE_CAPS;
+	return 0;
+}
+
+static int vidioc_s_hw_freq_seek(struct file *file, void *fh, const struct v4l2_hw_freq_seek *a)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_RADIO)
+		return vivid_radio_rx_s_hw_freq_seek(file, fh, a);
+	return -ENOTTY;
+}
+
+static int vidioc_enum_freq_bands(struct file *file, void *fh, struct v4l2_frequency_band *band)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_RADIO)
+		return vivid_radio_rx_enum_freq_bands(file, fh, band);
+	if (vdev->vfl_type == VFL_TYPE_SDR)
+		return vivid_sdr_enum_freq_bands(file, fh, band);
+	return -ENOTTY;
+}
+
+static int vidioc_g_tuner(struct file *file, void *fh, struct v4l2_tuner *vt)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_RADIO)
+		return vivid_radio_rx_g_tuner(file, fh, vt);
+	if (vdev->vfl_type == VFL_TYPE_SDR)
+		return vivid_sdr_g_tuner(file, fh, vt);
+	return vivid_video_g_tuner(file, fh, vt);
+}
+
+static int vidioc_s_tuner(struct file *file, void *fh, const struct v4l2_tuner *vt)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_RADIO)
+		return vivid_radio_rx_s_tuner(file, fh, vt);
+	if (vdev->vfl_type == VFL_TYPE_SDR)
+		return vivid_sdr_s_tuner(file, fh, vt);
+	return vivid_video_s_tuner(file, fh, vt);
+}
+
+static int vidioc_g_frequency(struct file *file, void *fh, struct v4l2_frequency *vf)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_RADIO)
+		return vivid_radio_g_frequency(file,
+			vdev->vfl_dir == VFL_DIR_RX ?
+			&dev->radio_rx_freq : &dev->radio_tx_freq, vf);
+	if (vdev->vfl_type == VFL_TYPE_SDR)
+		return vivid_sdr_g_frequency(file, fh, vf);
+	return vivid_video_g_frequency(file, fh, vf);
+}
+
+static int vidioc_s_frequency(struct file *file, void *fh, const struct v4l2_frequency *vf)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_RADIO)
+		return vivid_radio_s_frequency(file,
+			vdev->vfl_dir == VFL_DIR_RX ?
+			&dev->radio_rx_freq : &dev->radio_tx_freq, vf);
+	if (vdev->vfl_type == VFL_TYPE_SDR)
+		return vivid_sdr_s_frequency(file, fh, vf);
+	return vivid_video_s_frequency(file, fh, vf);
+}
+
+static int vidioc_overlay(struct file *file, void *fh, unsigned i)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return vivid_vid_cap_overlay(file, fh, i);
+	return vivid_vid_out_overlay(file, fh, i);
+}
+
+static int vidioc_g_fbuf(struct file *file, void *fh, struct v4l2_framebuffer *a)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return vivid_vid_cap_g_fbuf(file, fh, a);
+	return vivid_vid_out_g_fbuf(file, fh, a);
+}
+
+static int vidioc_s_fbuf(struct file *file, void *fh, const struct v4l2_framebuffer *a)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return vivid_vid_cap_s_fbuf(file, fh, a);
+	return vivid_vid_out_s_fbuf(file, fh, a);
+}
+
+static int vidioc_s_std(struct file *file, void *fh, v4l2_std_id id)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return vivid_vid_cap_s_std(file, fh, id);
+	return vivid_vid_out_s_std(file, fh, id);
+}
+
+static int vidioc_s_dv_timings(struct file *file, void *fh, struct v4l2_dv_timings *timings)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return vivid_vid_cap_s_dv_timings(file, fh, timings);
+	return vivid_vid_out_s_dv_timings(file, fh, timings);
+}
+
+static int vidioc_cropcap(struct file *file, void *fh, struct v4l2_cropcap *cc)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return vivid_vid_cap_cropcap(file, fh, cc);
+	return vivid_vid_out_cropcap(file, fh, cc);
+}
+
+static int vidioc_g_selection(struct file *file, void *fh,
+			      struct v4l2_selection *sel)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return vivid_vid_cap_g_selection(file, fh, sel);
+	return vivid_vid_out_g_selection(file, fh, sel);
+}
+
+static int vidioc_s_selection(struct file *file, void *fh,
+			      struct v4l2_selection *sel)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return vivid_vid_cap_s_selection(file, fh, sel);
+	return vivid_vid_out_s_selection(file, fh, sel);
+}
+
+static int vidioc_g_parm(struct file *file, void *fh,
+			  struct v4l2_streamparm *parm)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return vivid_vid_cap_g_parm(file, fh, parm);
+	return vivid_vid_out_g_parm(file, fh, parm);
+}
+
+static int vidioc_s_parm(struct file *file, void *fh,
+			  struct v4l2_streamparm *parm)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return vivid_vid_cap_s_parm(file, fh, parm);
+	return vivid_vid_out_g_parm(file, fh, parm);
+}
+
+static ssize_t vivid_radio_read(struct file *file, char __user *buf,
+			 size_t size, loff_t *offset)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_TX)
+		return -EINVAL;
+	return vivid_radio_rx_read(file, buf, size, offset);
+}
+
+static ssize_t vivid_radio_write(struct file *file, const char __user *buf,
+			  size_t size, loff_t *offset)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return -EINVAL;
+	return vivid_radio_tx_write(file, buf, size, offset);
+}
+
+static unsigned int vivid_radio_poll(struct file *file, struct poll_table_struct *wait)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX)
+		return vivid_radio_rx_poll(file, wait);
+	return vivid_radio_tx_poll(file, wait);
+}
+
+static bool vivid_is_in_use(struct video_device *vdev)
+{
+	unsigned long flags;
+	bool res;
+
+	spin_lock_irqsave(&vdev->fh_lock, flags);
+	res = !list_empty(&vdev->fh_list);
+	spin_unlock_irqrestore(&vdev->fh_lock, flags);
+	return res;
+}
+
+static bool vivid_is_last_user(struct vivid_dev *dev)
+{
+	unsigned uses = vivid_is_in_use(&dev->vid_cap_dev) +
+			vivid_is_in_use(&dev->vid_out_dev) +
+			vivid_is_in_use(&dev->vbi_cap_dev) +
+			vivid_is_in_use(&dev->vbi_out_dev) +
+			vivid_is_in_use(&dev->sdr_cap_dev) +
+			vivid_is_in_use(&dev->radio_rx_dev) +
+			vivid_is_in_use(&dev->radio_tx_dev);
+
+	return uses == 1;
+}
+
+static int vivid_fop_release(struct file *file)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct video_device *vdev = video_devdata(file);
+
+	mutex_lock(&dev->mutex);
+	if (!no_error_inj && v4l2_fh_is_singular_file(file) &&
+	    !video_is_registered(vdev) && vivid_is_last_user(dev)) {
+		/*
+		 * I am the last user of this driver, and a disconnect
+		 * was forced (since this video_device is unregistered),
+		 * so re-register all video_device's again.
+		 */
+		v4l2_info(&dev->v4l2_dev, "reconnect\n");
+		set_bit(V4L2_FL_REGISTERED, &dev->vid_cap_dev.flags);
+		set_bit(V4L2_FL_REGISTERED, &dev->vid_out_dev.flags);
+		set_bit(V4L2_FL_REGISTERED, &dev->vbi_cap_dev.flags);
+		set_bit(V4L2_FL_REGISTERED, &dev->vbi_out_dev.flags);
+		set_bit(V4L2_FL_REGISTERED, &dev->sdr_cap_dev.flags);
+		set_bit(V4L2_FL_REGISTERED, &dev->radio_rx_dev.flags);
+		set_bit(V4L2_FL_REGISTERED, &dev->radio_tx_dev.flags);
+	}
+	mutex_unlock(&dev->mutex);
+	if (file->private_data == dev->overlay_cap_owner)
+		dev->overlay_cap_owner = NULL;
+	if (file->private_data == dev->radio_rx_rds_owner) {
+		dev->radio_rx_rds_last_block = 0;
+		dev->radio_rx_rds_owner = NULL;
+	}
+	if (file->private_data == dev->radio_tx_rds_owner) {
+		dev->radio_tx_rds_last_block = 0;
+		dev->radio_tx_rds_owner = NULL;
+	}
+	if (vdev->queue)
+		return vb2_fop_release(file);
+	return v4l2_fh_release(file);
+}
+
+static const struct v4l2_file_operations vivid_fops = {
+	.owner		= THIS_MODULE,
+	.open           = v4l2_fh_open,
+	.release        = vivid_fop_release,
+	.read           = vb2_fop_read,
+	.write          = vb2_fop_write,
+	.poll		= vb2_fop_poll,
+	.unlocked_ioctl = video_ioctl2,
+	.mmap           = vb2_fop_mmap,
+};
+
+static const struct v4l2_file_operations vivid_radio_fops = {
+	.owner		= THIS_MODULE,
+	.open           = v4l2_fh_open,
+	.release        = vivid_fop_release,
+	.read           = vivid_radio_read,
+	.write          = vivid_radio_write,
+	.poll		= vivid_radio_poll,
+	.unlocked_ioctl = video_ioctl2,
+};
+
+static const struct v4l2_ioctl_ops vivid_ioctl_ops = {
+	.vidioc_querycap		= vidioc_querycap,
+
+	.vidioc_enum_fmt_vid_cap	= vidioc_enum_fmt_vid,
+	.vidioc_g_fmt_vid_cap		= vidioc_g_fmt_vid_cap,
+	.vidioc_try_fmt_vid_cap		= vidioc_try_fmt_vid_cap,
+	.vidioc_s_fmt_vid_cap		= vidioc_s_fmt_vid_cap,
+	.vidioc_enum_fmt_vid_cap_mplane = vidioc_enum_fmt_vid_mplane,
+	.vidioc_g_fmt_vid_cap_mplane	= vidioc_g_fmt_vid_cap_mplane,
+	.vidioc_try_fmt_vid_cap_mplane	= vidioc_try_fmt_vid_cap_mplane,
+	.vidioc_s_fmt_vid_cap_mplane	= vidioc_s_fmt_vid_cap_mplane,
+
+	.vidioc_enum_fmt_vid_out	= vidioc_enum_fmt_vid,
+	.vidioc_g_fmt_vid_out		= vidioc_g_fmt_vid_out,
+	.vidioc_try_fmt_vid_out		= vidioc_try_fmt_vid_out,
+	.vidioc_s_fmt_vid_out		= vidioc_s_fmt_vid_out,
+	.vidioc_enum_fmt_vid_out_mplane = vidioc_enum_fmt_vid_mplane,
+	.vidioc_g_fmt_vid_out_mplane	= vidioc_g_fmt_vid_out_mplane,
+	.vidioc_try_fmt_vid_out_mplane	= vidioc_try_fmt_vid_out_mplane,
+	.vidioc_s_fmt_vid_out_mplane	= vidioc_s_fmt_vid_out_mplane,
+
+	.vidioc_g_selection		= vidioc_g_selection,
+	.vidioc_s_selection		= vidioc_s_selection,
+	.vidioc_cropcap			= vidioc_cropcap,
+
+	.vidioc_g_fmt_vbi_cap		= vidioc_g_fmt_vbi_cap,
+	.vidioc_try_fmt_vbi_cap		= vidioc_g_fmt_vbi_cap,
+	.vidioc_s_fmt_vbi_cap		= vidioc_s_fmt_vbi_cap,
+
+	.vidioc_g_fmt_sliced_vbi_cap    = vidioc_g_fmt_sliced_vbi_cap,
+	.vidioc_try_fmt_sliced_vbi_cap  = vidioc_try_fmt_sliced_vbi_cap,
+	.vidioc_s_fmt_sliced_vbi_cap    = vidioc_s_fmt_sliced_vbi_cap,
+	.vidioc_g_sliced_vbi_cap	= vidioc_g_sliced_vbi_cap,
+
+	.vidioc_g_fmt_vbi_out		= vidioc_g_fmt_vbi_out,
+	.vidioc_try_fmt_vbi_out		= vidioc_g_fmt_vbi_out,
+	.vidioc_s_fmt_vbi_out		= vidioc_s_fmt_vbi_out,
+
+	.vidioc_g_fmt_sliced_vbi_out    = vidioc_g_fmt_sliced_vbi_out,
+	.vidioc_try_fmt_sliced_vbi_out  = vidioc_try_fmt_sliced_vbi_out,
+	.vidioc_s_fmt_sliced_vbi_out    = vidioc_s_fmt_sliced_vbi_out,
+
+	.vidioc_enum_fmt_sdr_cap	= vidioc_enum_fmt_sdr_cap,
+	.vidioc_g_fmt_sdr_cap		= vidioc_g_fmt_sdr_cap,
+	.vidioc_try_fmt_sdr_cap		= vidioc_g_fmt_sdr_cap,
+	.vidioc_s_fmt_sdr_cap		= vidioc_g_fmt_sdr_cap,
+
+	.vidioc_overlay			= vidioc_overlay,
+	.vidioc_enum_framesizes		= vidioc_enum_framesizes,
+	.vidioc_enum_frameintervals	= vidioc_enum_frameintervals,
+	.vidioc_g_parm			= vidioc_g_parm,
+	.vidioc_s_parm			= vidioc_s_parm,
+
+	.vidioc_enum_fmt_vid_overlay	= vidioc_enum_fmt_vid_overlay,
+	.vidioc_g_fmt_vid_overlay	= vidioc_g_fmt_vid_overlay,
+	.vidioc_try_fmt_vid_overlay	= vidioc_try_fmt_vid_overlay,
+	.vidioc_s_fmt_vid_overlay	= vidioc_s_fmt_vid_overlay,
+	.vidioc_g_fmt_vid_out_overlay	= vidioc_g_fmt_vid_out_overlay,
+	.vidioc_try_fmt_vid_out_overlay	= vidioc_try_fmt_vid_out_overlay,
+	.vidioc_s_fmt_vid_out_overlay	= vidioc_s_fmt_vid_out_overlay,
+	.vidioc_g_fbuf			= vidioc_g_fbuf,
+	.vidioc_s_fbuf			= vidioc_s_fbuf,
+
+	.vidioc_reqbufs			= vb2_ioctl_reqbufs,
+	.vidioc_create_bufs		= vb2_ioctl_create_bufs,
+	.vidioc_prepare_buf		= vb2_ioctl_prepare_buf,
+	.vidioc_querybuf		= vb2_ioctl_querybuf,
+	.vidioc_qbuf			= vb2_ioctl_qbuf,
+	.vidioc_dqbuf			= vb2_ioctl_dqbuf,
+/* Not yet	.vidioc_expbuf		= vb2_ioctl_expbuf,*/
+	.vidioc_streamon		= vb2_ioctl_streamon,
+	.vidioc_streamoff		= vb2_ioctl_streamoff,
+
+	.vidioc_enum_input		= vidioc_enum_input,
+	.vidioc_g_input			= vidioc_g_input,
+	.vidioc_s_input			= vidioc_s_input,
+	.vidioc_s_audio			= vidioc_s_audio,
+	.vidioc_g_audio			= vidioc_g_audio,
+	.vidioc_enumaudio		= vidioc_enumaudio,
+	.vidioc_s_frequency		= vidioc_s_frequency,
+	.vidioc_g_frequency		= vidioc_g_frequency,
+	.vidioc_s_tuner			= vidioc_s_tuner,
+	.vidioc_g_tuner			= vidioc_g_tuner,
+	.vidioc_s_modulator		= vidioc_s_modulator,
+	.vidioc_g_modulator		= vidioc_g_modulator,
+	.vidioc_s_hw_freq_seek		= vidioc_s_hw_freq_seek,
+	.vidioc_enum_freq_bands		= vidioc_enum_freq_bands,
+
+	.vidioc_enum_output		= vidioc_enum_output,
+	.vidioc_g_output		= vidioc_g_output,
+	.vidioc_s_output		= vidioc_s_output,
+	.vidioc_s_audout		= vidioc_s_audout,
+	.vidioc_g_audout		= vidioc_g_audout,
+	.vidioc_enumaudout		= vidioc_enumaudout,
+
+	.vidioc_querystd		= vidioc_querystd,
+	.vidioc_g_std			= vidioc_g_std,
+	.vidioc_s_std			= vidioc_s_std,
+	.vidioc_s_dv_timings		= vidioc_s_dv_timings,
+	.vidioc_g_dv_timings		= vidioc_g_dv_timings,
+	.vidioc_query_dv_timings	= vidioc_query_dv_timings,
+	.vidioc_enum_dv_timings		= vidioc_enum_dv_timings,
+	.vidioc_dv_timings_cap		= vidioc_dv_timings_cap,
+	.vidioc_g_edid			= vidioc_g_edid,
+	.vidioc_s_edid			= vidioc_s_edid,
+
+	.vidioc_log_status		= v4l2_ctrl_log_status,
+	.vidioc_subscribe_event		= vidioc_subscribe_event,
+	.vidioc_unsubscribe_event	= v4l2_event_unsubscribe,
+};
+
+/* -----------------------------------------------------------------
+	Initialization and module stuff
+   ------------------------------------------------------------------*/
+
+static int __init vivid_create_instance(int inst)
+{
+	static const struct v4l2_dv_timings def_dv_timings =
+					V4L2_DV_BT_CEA_1280X720P60;
+	unsigned in_type_counter[4] = { 0, 0, 0, 0 };
+	unsigned out_type_counter[4] = { 0, 0, 0, 0 };
+	int ccs_cap = ccs_cap_mode[inst];
+	int ccs_out = ccs_out_mode[inst];
+	bool has_tuner;
+	bool has_modulator;
+	struct vivid_dev *dev;
+	struct video_device *vfd;
+	struct vb2_queue *q;
+	unsigned node_type = node_types[inst];
+	v4l2_std_id tvnorms_cap = 0, tvnorms_out = 0;
+	int ret;
+	int i;
+
+	/* allocate main vivid state structure */
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	dev->inst = inst;
+
+	/* register v4l2_device */
+	snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name),
+			"%s-%03d", VIVID_MODULE_NAME, inst);
+	ret = v4l2_device_register(NULL, &dev->v4l2_dev);
+	if (ret)
+		goto free_dev;
+
+	/* start detecting feature set */
+
+	/* do we use single- or multi-planar? */
+	if (multiplanar[inst] == 0)
+		dev->multiplanar = inst & 1;
+	else
+		dev->multiplanar = multiplanar[inst] > 1;
+	v4l2_info(&dev->v4l2_dev, "using %splanar format API\n",
+			dev->multiplanar ? "multi" : "single ");
+
+	/* how many inputs do we have and of what type? */
+	dev->num_inputs = num_inputs[inst];
+	if (dev->num_inputs < 1)
+		dev->num_inputs = 1;
+	if (dev->num_inputs >= MAX_INPUTS)
+		dev->num_inputs = MAX_INPUTS;
+	for (i = 0; i < dev->num_inputs; i++) {
+		dev->input_type[i] = (input_types[inst] >> (i * 2)) & 0x3;
+		dev->input_name_counter[i] = in_type_counter[dev->input_type[i]]++;
+	}
+	dev->has_audio_inputs = in_type_counter[TV] && in_type_counter[SVID];
+
+	/* how many outputs do we have and of what type? */
+	dev->num_outputs = num_outputs[inst];
+	if (dev->num_outputs < 1)
+		dev->num_outputs = 1;
+	if (dev->num_outputs >= MAX_OUTPUTS)
+		dev->num_outputs = MAX_OUTPUTS;
+	for (i = 0; i < dev->num_outputs; i++) {
+		dev->output_type[i] = ((output_types[inst] >> i) & 1) ? HDMI : SVID;
+		dev->output_name_counter[i] = out_type_counter[dev->output_type[i]]++;
+	}
+	dev->has_audio_outputs = out_type_counter[SVID];
+
+	/* do we create a video capture device? */
+	dev->has_vid_cap = node_type & 0x0001;
+
+	/* do we create a vbi capture device? */
+	if (in_type_counter[TV] || in_type_counter[SVID]) {
+		dev->has_raw_vbi_cap = node_type & 0x0004;
+		dev->has_sliced_vbi_cap = node_type & 0x0008;
+		dev->has_vbi_cap = dev->has_raw_vbi_cap | dev->has_sliced_vbi_cap;
+	}
+
+	/* do we create a video output device? */
+	dev->has_vid_out = node_type & 0x0100;
+
+	/* do we create a vbi output device? */
+	if (out_type_counter[SVID]) {
+		dev->has_raw_vbi_out = node_type & 0x0400;
+		dev->has_sliced_vbi_out = node_type & 0x0800;
+		dev->has_vbi_out = dev->has_raw_vbi_out | dev->has_sliced_vbi_out;
+	}
+
+	/* do we create a radio receiver device? */
+	dev->has_radio_rx = node_type & 0x0010;
+
+	/* do we create a radio transmitter device? */
+	dev->has_radio_tx = node_type & 0x1000;
+
+	/* do we create a software defined radio capture device? */
+	dev->has_sdr_cap = node_type & 0x0020;
+
+	/* do we have a tuner? */
+	has_tuner = ((dev->has_vid_cap || dev->has_vbi_cap) && in_type_counter[TV]) ||
+		    dev->has_radio_rx || dev->has_sdr_cap;
+
+	/* do we have a modulator? */
+	has_modulator = dev->has_radio_tx;
+
+	if (dev->has_vid_cap)
+		/* do we have a framebuffer for overlay testing? */
+		dev->has_fb = node_type & 0x10000;
+
+	/* can we do crop/compose/scaling while capturing? */
+	if (no_error_inj && ccs_cap == -1)
+		ccs_cap = 7;
+
+	/* if ccs_cap == -1, then the use can select it using controls */
+	if (ccs_cap != -1) {
+		dev->has_crop_cap = ccs_cap & 1;
+		dev->has_compose_cap = ccs_cap & 2;
+		dev->has_scaler_cap = ccs_cap & 4;
+		v4l2_info(&dev->v4l2_dev, "Capture Crop: %c Compose: %c Scaler: %c\n",
+			dev->has_crop_cap ? 'Y' : 'N',
+			dev->has_compose_cap ? 'Y' : 'N',
+			dev->has_scaler_cap ? 'Y' : 'N');
+	}
+
+	/* can we do crop/compose/scaling with video output? */
+	if (no_error_inj && ccs_out == -1)
+		ccs_out = 7;
+
+	/* if ccs_out == -1, then the use can select it using controls */
+	if (ccs_out != -1) {
+		dev->has_crop_out = ccs_out & 1;
+		dev->has_compose_out = ccs_out & 2;
+		dev->has_scaler_out = ccs_out & 4;
+		v4l2_info(&dev->v4l2_dev, "Output Crop: %c Compose: %c Scaler: %c\n",
+			dev->has_crop_out ? 'Y' : 'N',
+			dev->has_compose_out ? 'Y' : 'N',
+			dev->has_scaler_out ? 'Y' : 'N');
+	}
+
+	/* end detecting feature set */
+
+	if (dev->has_vid_cap) {
+		/* set up the capabilities of the video capture device */
+		dev->vid_cap_caps = dev->multiplanar ?
+			V4L2_CAP_VIDEO_CAPTURE_MPLANE :
+			V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_VIDEO_OVERLAY;
+		dev->vid_cap_caps |= V4L2_CAP_STREAMING | V4L2_CAP_READWRITE;
+		if (dev->has_audio_inputs)
+			dev->vid_cap_caps |= V4L2_CAP_AUDIO;
+		if (in_type_counter[TV])
+			dev->vid_cap_caps |= V4L2_CAP_TUNER;
+	}
+	if (dev->has_vid_out) {
+		/* set up the capabilities of the video output device */
+		dev->vid_out_caps = dev->multiplanar ?
+			V4L2_CAP_VIDEO_OUTPUT_MPLANE :
+			V4L2_CAP_VIDEO_OUTPUT;
+		if (dev->has_fb)
+			dev->vid_out_caps |= V4L2_CAP_VIDEO_OUTPUT_OVERLAY;
+		dev->vid_out_caps |= V4L2_CAP_STREAMING | V4L2_CAP_READWRITE;
+		if (dev->has_audio_outputs)
+			dev->vid_out_caps |= V4L2_CAP_AUDIO;
+	}
+	if (dev->has_vbi_cap) {
+		/* set up the capabilities of the vbi capture device */
+		dev->vbi_cap_caps = (dev->has_raw_vbi_cap ? V4L2_CAP_VBI_CAPTURE : 0) |
+				    (dev->has_sliced_vbi_cap ? V4L2_CAP_SLICED_VBI_CAPTURE : 0);
+		dev->vbi_cap_caps |= V4L2_CAP_STREAMING | V4L2_CAP_READWRITE;
+		if (dev->has_audio_inputs)
+			dev->vbi_cap_caps |= V4L2_CAP_AUDIO;
+		if (in_type_counter[TV])
+			dev->vbi_cap_caps |= V4L2_CAP_TUNER;
+	}
+	if (dev->has_vbi_out) {
+		/* set up the capabilities of the vbi output device */
+		dev->vbi_out_caps = (dev->has_raw_vbi_out ? V4L2_CAP_VBI_OUTPUT : 0) |
+				    (dev->has_sliced_vbi_out ? V4L2_CAP_SLICED_VBI_OUTPUT : 0);
+		dev->vbi_out_caps |= V4L2_CAP_STREAMING | V4L2_CAP_READWRITE;
+		if (dev->has_audio_outputs)
+			dev->vbi_out_caps |= V4L2_CAP_AUDIO;
+	}
+	if (dev->has_sdr_cap) {
+		/* set up the capabilities of the sdr capture device */
+		dev->sdr_cap_caps = V4L2_CAP_SDR_CAPTURE | V4L2_CAP_TUNER;
+		dev->sdr_cap_caps |= V4L2_CAP_STREAMING | V4L2_CAP_READWRITE;
+	}
+	/* set up the capabilities of the radio receiver device */
+	if (dev->has_radio_rx)
+		dev->radio_rx_caps = V4L2_CAP_RADIO | V4L2_CAP_RDS_CAPTURE |
+				     V4L2_CAP_HW_FREQ_SEEK | V4L2_CAP_TUNER |
+				     V4L2_CAP_READWRITE;
+	/* set up the capabilities of the radio transmitter device */
+	if (dev->has_radio_tx)
+		dev->radio_tx_caps = V4L2_CAP_RDS_OUTPUT | V4L2_CAP_MODULATOR |
+				     V4L2_CAP_READWRITE;
+
+	/* initialize the test pattern generator */
+	tpg_init(&dev->tpg, 640, 360);
+	if (tpg_alloc(&dev->tpg, MAX_ZOOM * MAX_WIDTH))
+		goto free_dev;
+	dev->scaled_line = vzalloc(MAX_ZOOM * MAX_WIDTH);
+	if (!dev->scaled_line)
+		goto free_dev;
+	dev->blended_line = vzalloc(MAX_ZOOM * MAX_WIDTH);
+	if (!dev->blended_line)
+		goto free_dev;
+
+	/* load the edid */
+	dev->edid = vmalloc(256 * 128);
+	if (!dev->edid)
+		goto free_dev;
+
+	/* create a string array containing the names of all the preset timings */
+	while (v4l2_dv_timings_presets[dev->query_dv_timings_size].bt.width)
+		dev->query_dv_timings_size++;
+	dev->query_dv_timings_qmenu = kmalloc(dev->query_dv_timings_size *
+					   (sizeof(void *) + 32), GFP_KERNEL);
+	if (dev->query_dv_timings_qmenu == NULL)
+		goto free_dev;
+	for (i = 0; i < dev->query_dv_timings_size; i++) {
+		const struct v4l2_bt_timings *bt = &v4l2_dv_timings_presets[i].bt;
+		char *p = (char *)&dev->query_dv_timings_qmenu[dev->query_dv_timings_size];
+		u32 htot, vtot;
+
+		p += i * 32;
+		dev->query_dv_timings_qmenu[i] = p;
+
+		htot = V4L2_DV_BT_FRAME_WIDTH(bt);
+		vtot = V4L2_DV_BT_FRAME_HEIGHT(bt);
+		snprintf(p, 32, "%ux%u%s%u",
+			bt->width, bt->height, bt->interlaced ? "i" : "p",
+			(u32)bt->pixelclock / (htot * vtot));
+	}
+
+	/* disable invalid ioctls based on the feature set */
+	if (!dev->has_audio_inputs) {
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_S_AUDIO);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_G_AUDIO);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_ENUMAUDIO);
+		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_S_AUDIO);
+		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_G_AUDIO);
+		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_ENUMAUDIO);
+	}
+	if (!dev->has_audio_outputs) {
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_S_AUDOUT);
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_G_AUDOUT);
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_ENUMAUDOUT);
+		v4l2_disable_ioctl(&dev->vbi_out_dev, VIDIOC_S_AUDOUT);
+		v4l2_disable_ioctl(&dev->vbi_out_dev, VIDIOC_G_AUDOUT);
+		v4l2_disable_ioctl(&dev->vbi_out_dev, VIDIOC_ENUMAUDOUT);
+	}
+	if (!in_type_counter[TV] && !in_type_counter[SVID]) {
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_S_STD);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_G_STD);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_ENUMSTD);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_QUERYSTD);
+	}
+	if (!out_type_counter[SVID]) {
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_S_STD);
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_G_STD);
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_ENUMSTD);
+	}
+	if (!has_tuner && !has_modulator) {
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_S_FREQUENCY);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_G_FREQUENCY);
+		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_S_FREQUENCY);
+		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_G_FREQUENCY);
+	}
+	if (!has_tuner) {
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_S_TUNER);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_G_TUNER);
+		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_S_TUNER);
+		v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_G_TUNER);
+	}
+	if (in_type_counter[HDMI] == 0) {
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_S_EDID);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_G_EDID);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_DV_TIMINGS_CAP);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_G_DV_TIMINGS);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_S_DV_TIMINGS);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_ENUM_DV_TIMINGS);
+		v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_QUERY_DV_TIMINGS);
+	}
+	if (out_type_counter[HDMI] == 0) {
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_G_EDID);
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_DV_TIMINGS_CAP);
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_G_DV_TIMINGS);
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_S_DV_TIMINGS);
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_ENUM_DV_TIMINGS);
+	}
+	if (!dev->has_fb) {
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_G_FBUF);
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_S_FBUF);
+		v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_OVERLAY);
+	}
+	v4l2_disable_ioctl(&dev->vid_cap_dev, VIDIOC_S_HW_FREQ_SEEK);
+	v4l2_disable_ioctl(&dev->vbi_cap_dev, VIDIOC_S_HW_FREQ_SEEK);
+	v4l2_disable_ioctl(&dev->sdr_cap_dev, VIDIOC_S_HW_FREQ_SEEK);
+	v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_S_FREQUENCY);
+	v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_G_FREQUENCY);
+	v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_ENUM_FRAMESIZES);
+	v4l2_disable_ioctl(&dev->vid_out_dev, VIDIOC_ENUM_FRAMEINTERVALS);
+	v4l2_disable_ioctl(&dev->vbi_out_dev, VIDIOC_S_FREQUENCY);
+	v4l2_disable_ioctl(&dev->vbi_out_dev, VIDIOC_G_FREQUENCY);
+
+	/* configure internal data */
+	dev->fmt_cap = &vivid_formats[0];
+	dev->fmt_out = &vivid_formats[0];
+	if (!dev->multiplanar)
+		vivid_formats[0].data_offset[0] = 0;
+	dev->webcam_size_idx = 1;
+	dev->webcam_ival_idx = 3;
+	tpg_s_fourcc(&dev->tpg, dev->fmt_cap->fourcc);
+	dev->std_cap = V4L2_STD_PAL;
+	dev->std_out = V4L2_STD_PAL;
+	if (dev->input_type[0] == TV || dev->input_type[0] == SVID)
+		tvnorms_cap = V4L2_STD_ALL;
+	if (dev->output_type[0] == SVID)
+		tvnorms_out = V4L2_STD_ALL;
+	dev->dv_timings_cap = def_dv_timings;
+	dev->dv_timings_out = def_dv_timings;
+	dev->tv_freq = 2804 /* 175.25 * 16 */;
+	dev->tv_audmode = V4L2_TUNER_MODE_STEREO;
+	dev->tv_field_cap = V4L2_FIELD_INTERLACED;
+	dev->tv_field_out = V4L2_FIELD_INTERLACED;
+	dev->radio_rx_freq = 95000 * 16;
+	dev->radio_rx_audmode = V4L2_TUNER_MODE_STEREO;
+	if (dev->has_radio_tx) {
+		dev->radio_tx_freq = 95500 * 16;
+		dev->radio_rds_loop = false;
+	}
+	dev->radio_tx_subchans = V4L2_TUNER_SUB_STEREO | V4L2_TUNER_SUB_RDS;
+	dev->sdr_adc_freq = 300000;
+	dev->sdr_fm_freq = 50000000;
+	dev->edid_max_blocks = dev->edid_blocks = 2;
+	memcpy(dev->edid, vivid_hdmi_edid, sizeof(vivid_hdmi_edid));
+	ktime_get_ts(&dev->radio_rds_init_ts);
+
+	/* create all controls */
+	ret = vivid_create_controls(dev, ccs_cap == -1, ccs_out == -1, no_error_inj,
+			in_type_counter[TV] || in_type_counter[SVID] ||
+			out_type_counter[SVID],
+			in_type_counter[HDMI] || out_type_counter[HDMI]);
+	if (ret)
+		goto unreg_dev;
+
+	/*
+	 * update the capture and output formats to do a proper initial
+	 * configuration.
+	 */
+	vivid_update_format_cap(dev, false);
+	vivid_update_format_out(dev);
+
+	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_vid_cap);
+	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_vid_out);
+	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_vbi_cap);
+	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_vbi_out);
+	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_radio_rx);
+	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_radio_tx);
+	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_sdr_cap);
+
+	/* initialize overlay */
+	dev->fb_cap.fmt.width = dev->src_rect.width;
+	dev->fb_cap.fmt.height = dev->src_rect.height;
+	dev->fb_cap.fmt.pixelformat = dev->fmt_cap->fourcc;
+	dev->fb_cap.fmt.bytesperline = dev->src_rect.width * tpg_g_twopixelsize(&dev->tpg, 0) / 2;
+	dev->fb_cap.fmt.sizeimage = dev->src_rect.height * dev->fb_cap.fmt.bytesperline;
+
+	/* initialize locks */
+	spin_lock_init(&dev->slock);
+	mutex_init(&dev->mutex);
+
+	/* init dma queues */
+	INIT_LIST_HEAD(&dev->vid_cap_active);
+	INIT_LIST_HEAD(&dev->vid_out_active);
+	INIT_LIST_HEAD(&dev->vbi_cap_active);
+	INIT_LIST_HEAD(&dev->vbi_out_active);
+	INIT_LIST_HEAD(&dev->sdr_cap_active);
+
+	/* start creating the vb2 queues */
+	if (dev->has_vid_cap) {
+		/* initialize vid_cap queue */
+		q = &dev->vb_vid_cap_q;
+		q->type = dev->multiplanar ? V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE :
+			V4L2_BUF_TYPE_VIDEO_CAPTURE;
+		q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
+		q->drv_priv = dev;
+		q->buf_struct_size = sizeof(struct vivid_buffer);
+		q->ops = &vivid_vid_cap_qops;
+		q->mem_ops = &vb2_vmalloc_memops;
+		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+		q->min_buffers_needed = 2;
+
+		ret = vb2_queue_init(q);
+		if (ret)
+			goto unreg_dev;
+	}
+
+	if (dev->has_vid_out) {
+		/* initialize vid_out queue */
+		q = &dev->vb_vid_out_q;
+		q->type = dev->multiplanar ? V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE :
+			V4L2_BUF_TYPE_VIDEO_OUTPUT;
+		q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_WRITE;
+		q->drv_priv = dev;
+		q->buf_struct_size = sizeof(struct vivid_buffer);
+		q->ops = &vivid_vid_out_qops;
+		q->mem_ops = &vb2_vmalloc_memops;
+		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+		q->min_buffers_needed = 2;
+
+		ret = vb2_queue_init(q);
+		if (ret)
+			goto unreg_dev;
+	}
+
+	if (dev->has_vbi_cap) {
+		/* initialize vbi_cap queue */
+		q = &dev->vb_vbi_cap_q;
+		q->type = dev->has_raw_vbi_cap ? V4L2_BUF_TYPE_VBI_CAPTURE :
+					      V4L2_BUF_TYPE_SLICED_VBI_CAPTURE;
+		q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
+		q->drv_priv = dev;
+		q->buf_struct_size = sizeof(struct vivid_buffer);
+		q->ops = &vivid_vbi_cap_qops;
+		q->mem_ops = &vb2_vmalloc_memops;
+		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+		q->min_buffers_needed = 2;
+
+		ret = vb2_queue_init(q);
+		if (ret)
+			goto unreg_dev;
+	}
+
+	if (dev->has_vbi_out) {
+		/* initialize vbi_out queue */
+		q = &dev->vb_vbi_out_q;
+		q->type = dev->has_raw_vbi_out ? V4L2_BUF_TYPE_VBI_OUTPUT :
+					      V4L2_BUF_TYPE_SLICED_VBI_OUTPUT;
+		q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_WRITE;
+		q->drv_priv = dev;
+		q->buf_struct_size = sizeof(struct vivid_buffer);
+		q->ops = &vivid_vbi_out_qops;
+		q->mem_ops = &vb2_vmalloc_memops;
+		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+		q->min_buffers_needed = 2;
+
+		ret = vb2_queue_init(q);
+		if (ret)
+			goto unreg_dev;
+	}
+
+	if (dev->has_sdr_cap) {
+		/* initialize sdr_cap queue */
+		q = &dev->vb_sdr_cap_q;
+		q->type = V4L2_BUF_TYPE_SDR_CAPTURE;
+		q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
+		q->drv_priv = dev;
+		q->buf_struct_size = sizeof(struct vivid_buffer);
+		q->ops = &vivid_sdr_cap_qops;
+		q->mem_ops = &vb2_vmalloc_memops;
+		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+		q->min_buffers_needed = 8;
+
+		ret = vb2_queue_init(q);
+		if (ret)
+			goto unreg_dev;
+	}
+
+	if (dev->has_fb) {
+		/* Create framebuffer for testing capture/output overlay */
+		ret = vivid_fb_init(dev);
+		if (ret)
+			goto unreg_dev;
+		v4l2_info(&dev->v4l2_dev, "Framebuffer device registered as fb%d\n",
+				dev->fb_info.node);
+	}
+
+	/* finally start creating the device nodes */
+	if (dev->has_vid_cap) {
+		vfd = &dev->vid_cap_dev;
+		strlcpy(vfd->name, "vivid-vid-cap", sizeof(vfd->name));
+		vfd->fops = &vivid_fops;
+		vfd->ioctl_ops = &vivid_ioctl_ops;
+		vfd->release = video_device_release_empty;
+		vfd->v4l2_dev = &dev->v4l2_dev;
+		vfd->queue = &dev->vb_vid_cap_q;
+		vfd->tvnorms = tvnorms_cap;
+
+		/*
+		 * Provide a mutex to v4l2 core. It will be used to protect
+		 * all fops and v4l2 ioctls.
+		 */
+		vfd->lock = &dev->mutex;
+		video_set_drvdata(vfd, dev);
+
+		ret = video_register_device(vfd, VFL_TYPE_GRABBER, vid_cap_nr[inst]);
+		if (ret < 0)
+			goto unreg_dev;
+		v4l2_info(&dev->v4l2_dev, "V4L2 capture device registered as %s\n",
+					  video_device_node_name(vfd));
+	}
+
+	if (dev->has_vid_out) {
+		vfd = &dev->vid_out_dev;
+		strlcpy(vfd->name, "vivid-vid-out", sizeof(vfd->name));
+		vfd->vfl_dir = VFL_DIR_TX;
+		vfd->fops = &vivid_fops;
+		vfd->ioctl_ops = &vivid_ioctl_ops;
+		vfd->release = video_device_release_empty;
+		vfd->v4l2_dev = &dev->v4l2_dev;
+		vfd->queue = &dev->vb_vid_out_q;
+		vfd->tvnorms = tvnorms_out;
+
+		/*
+		 * Provide a mutex to v4l2 core. It will be used to protect
+		 * all fops and v4l2 ioctls.
+		 */
+		vfd->lock = &dev->mutex;
+		video_set_drvdata(vfd, dev);
+
+		ret = video_register_device(vfd, VFL_TYPE_GRABBER, vid_out_nr[inst]);
+		if (ret < 0)
+			goto unreg_dev;
+		v4l2_info(&dev->v4l2_dev, "V4L2 output device registered as %s\n",
+					  video_device_node_name(vfd));
+	}
+
+	if (dev->has_vbi_cap) {
+		vfd = &dev->vbi_cap_dev;
+		strlcpy(vfd->name, "vivid-vbi-cap", sizeof(vfd->name));
+		vfd->fops = &vivid_fops;
+		vfd->ioctl_ops = &vivid_ioctl_ops;
+		vfd->release = video_device_release_empty;
+		vfd->v4l2_dev = &dev->v4l2_dev;
+		vfd->queue = &dev->vb_vbi_cap_q;
+		vfd->lock = &dev->mutex;
+		vfd->tvnorms = tvnorms_cap;
+		video_set_drvdata(vfd, dev);
+
+		ret = video_register_device(vfd, VFL_TYPE_VBI, vbi_cap_nr[inst]);
+		if (ret < 0)
+			goto unreg_dev;
+		v4l2_info(&dev->v4l2_dev, "V4L2 capture device registered as %s, supports %s VBI\n",
+					  video_device_node_name(vfd),
+					  (dev->has_raw_vbi_cap && dev->has_sliced_vbi_cap) ?
+					  "raw and sliced" :
+					  (dev->has_raw_vbi_cap ? "raw" : "sliced"));
+	}
+
+	if (dev->has_vbi_out) {
+		vfd = &dev->vbi_out_dev;
+		strlcpy(vfd->name, "vivid-vbi-out", sizeof(vfd->name));
+		vfd->vfl_dir = VFL_DIR_TX;
+		vfd->fops = &vivid_fops;
+		vfd->ioctl_ops = &vivid_ioctl_ops;
+		vfd->release = video_device_release_empty;
+		vfd->v4l2_dev = &dev->v4l2_dev;
+		vfd->queue = &dev->vb_vbi_out_q;
+		vfd->lock = &dev->mutex;
+		vfd->tvnorms = tvnorms_out;
+		video_set_drvdata(vfd, dev);
+
+		ret = video_register_device(vfd, VFL_TYPE_VBI, vbi_out_nr[inst]);
+		if (ret < 0)
+			goto unreg_dev;
+		v4l2_info(&dev->v4l2_dev, "V4L2 output device registered as %s, supports %s VBI\n",
+					  video_device_node_name(vfd),
+					  (dev->has_raw_vbi_out && dev->has_sliced_vbi_out) ?
+					  "raw and sliced" :
+					  (dev->has_raw_vbi_out ? "raw" : "sliced"));
+	}
+
+	if (dev->has_sdr_cap) {
+		vfd = &dev->sdr_cap_dev;
+		strlcpy(vfd->name, "vivid-sdr-cap", sizeof(vfd->name));
+		vfd->fops = &vivid_fops;
+		vfd->ioctl_ops = &vivid_ioctl_ops;
+		vfd->release = video_device_release_empty;
+		vfd->v4l2_dev = &dev->v4l2_dev;
+		vfd->queue = &dev->vb_sdr_cap_q;
+		vfd->lock = &dev->mutex;
+		video_set_drvdata(vfd, dev);
+
+		ret = video_register_device(vfd, VFL_TYPE_SDR, sdr_cap_nr[inst]);
+		if (ret < 0)
+			goto unreg_dev;
+		v4l2_info(&dev->v4l2_dev, "V4L2 capture device registered as %s\n",
+					  video_device_node_name(vfd));
+	}
+
+	if (dev->has_radio_rx) {
+		vfd = &dev->radio_rx_dev;
+		strlcpy(vfd->name, "vivid-rad-rx", sizeof(vfd->name));
+		vfd->fops = &vivid_radio_fops;
+		vfd->ioctl_ops = &vivid_ioctl_ops;
+		vfd->release = video_device_release_empty;
+		vfd->v4l2_dev = &dev->v4l2_dev;
+		vfd->lock = &dev->mutex;
+		video_set_drvdata(vfd, dev);
+
+		ret = video_register_device(vfd, VFL_TYPE_RADIO, radio_rx_nr[inst]);
+		if (ret < 0)
+			goto unreg_dev;
+		v4l2_info(&dev->v4l2_dev, "V4L2 receiver device registered as %s\n",
+					  video_device_node_name(vfd));
+	}
+
+	if (dev->has_radio_tx) {
+		vfd = &dev->radio_tx_dev;
+		strlcpy(vfd->name, "vivid-rad-tx", sizeof(vfd->name));
+		vfd->vfl_dir = VFL_DIR_TX;
+		vfd->fops = &vivid_radio_fops;
+		vfd->ioctl_ops = &vivid_ioctl_ops;
+		vfd->release = video_device_release_empty;
+		vfd->v4l2_dev = &dev->v4l2_dev;
+		vfd->lock = &dev->mutex;
+		video_set_drvdata(vfd, dev);
+
+		ret = video_register_device(vfd, VFL_TYPE_RADIO, radio_tx_nr[inst]);
+		if (ret < 0)
+			goto unreg_dev;
+		v4l2_info(&dev->v4l2_dev, "V4L2 transmitter device registered as %s\n",
+					  video_device_node_name(vfd));
+	}
+
+	/* Now that everything is fine, let's add it to device list */
+	vivid_devs[inst] = dev;
+
+	return 0;
+
+unreg_dev:
+	video_unregister_device(&dev->radio_tx_dev);
+	video_unregister_device(&dev->radio_rx_dev);
+	video_unregister_device(&dev->sdr_cap_dev);
+	video_unregister_device(&dev->vbi_out_dev);
+	video_unregister_device(&dev->vbi_cap_dev);
+	video_unregister_device(&dev->vid_out_dev);
+	video_unregister_device(&dev->vid_cap_dev);
+	vivid_free_controls(dev);
+	v4l2_device_unregister(&dev->v4l2_dev);
+free_dev:
+	vfree(dev->scaled_line);
+	vfree(dev->blended_line);
+	vfree(dev->edid);
+	tpg_free(&dev->tpg);
+	kfree(dev->query_dv_timings_qmenu);
+	kfree(dev);
+	return ret;
+}
+
+/* This routine allocates from 1 to n_devs virtual drivers.
+
+   The real maximum number of virtual drivers will depend on how many drivers
+   will succeed. This is limited to the maximum number of devices that
+   videodev supports, which is equal to VIDEO_NUM_DEVICES.
+ */
+static int __init vivid_init(void)
+{
+	const struct font_desc *font = find_font("VGA8x16");
+	int ret = 0, i;
+
+	if (font == NULL) {
+		pr_err("vivid: could not find font\n");
+		return -ENODEV;
+	}
+
+	tpg_set_font(font->data);
+
+	n_devs = clamp_t(unsigned, n_devs, 1, VIVID_MAX_DEVS);
+
+	for (i = 0; i < n_devs; i++) {
+		ret = vivid_create_instance(i);
+		if (ret) {
+			/* If some instantiations succeeded, keep driver */
+			if (i)
+				ret = 0;
+			break;
+		}
+	}
+
+	if (ret < 0) {
+		pr_err("vivid: error %d while loading driver\n", ret);
+		return ret;
+	}
+
+	/* n_devs will reflect the actual number of allocated devices */
+	n_devs = i;
+
+	return ret;
+}
+
+static void __exit vivid_exit(void)
+{
+	struct vivid_dev *dev;
+	unsigned i;
+
+	for (i = 0; vivid_devs[i]; i++) {
+		dev = vivid_devs[i];
+
+		if (dev->has_vid_cap) {
+			v4l2_info(&dev->v4l2_dev, "unregistering %s\n",
+				video_device_node_name(&dev->vid_cap_dev));
+			video_unregister_device(&dev->vid_cap_dev);
+		}
+		if (dev->has_vid_out) {
+			v4l2_info(&dev->v4l2_dev, "unregistering %s\n",
+				video_device_node_name(&dev->vid_out_dev));
+			video_unregister_device(&dev->vid_out_dev);
+		}
+		if (dev->has_vbi_cap) {
+			v4l2_info(&dev->v4l2_dev, "unregistering %s\n",
+				video_device_node_name(&dev->vbi_cap_dev));
+			video_unregister_device(&dev->vbi_cap_dev);
+		}
+		if (dev->has_vbi_out) {
+			v4l2_info(&dev->v4l2_dev, "unregistering %s\n",
+				video_device_node_name(&dev->vbi_out_dev));
+			video_unregister_device(&dev->vbi_out_dev);
+		}
+		if (dev->has_sdr_cap) {
+			v4l2_info(&dev->v4l2_dev, "unregistering %s\n",
+				video_device_node_name(&dev->sdr_cap_dev));
+			video_unregister_device(&dev->sdr_cap_dev);
+		}
+		if (dev->has_radio_rx) {
+			v4l2_info(&dev->v4l2_dev, "unregistering %s\n",
+				video_device_node_name(&dev->radio_rx_dev));
+			video_unregister_device(&dev->radio_rx_dev);
+		}
+		if (dev->has_radio_tx) {
+			v4l2_info(&dev->v4l2_dev, "unregistering %s\n",
+				video_device_node_name(&dev->radio_tx_dev));
+			video_unregister_device(&dev->radio_tx_dev);
+		}
+		if (dev->has_fb) {
+			v4l2_info(&dev->v4l2_dev, "unregistering fb%d\n",
+				dev->fb_info.node);
+			unregister_framebuffer(&dev->fb_info);
+			vivid_fb_release_buffers(dev);
+		}
+		v4l2_device_unregister(&dev->v4l2_dev);
+		vivid_free_controls(dev);
+		vfree(dev->scaled_line);
+		vfree(dev->blended_line);
+		vfree(dev->edid);
+		vfree(dev->bitmap_cap);
+		vfree(dev->bitmap_out);
+		tpg_free(&dev->tpg);
+		kfree(dev->query_dv_timings_qmenu);
+		kfree(dev);
+		vivid_devs[i] = NULL;
+	}
+}
+
+module_init(vivid_init);
+module_exit(vivid_exit);
diff --git a/drivers/media/platform/vivid/vivid-core.h b/drivers/media/platform/vivid/vivid-core.h
new file mode 100644
index 000000000000..811c286491a5
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-core.h
@@ -0,0 +1,520 @@
+/*
+ * vivid-core.h - core datastructures
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_CORE_H_
+#define _VIVID_CORE_H_
+
+#include <linux/fb.h>
+#include <media/videobuf2-core.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-dev.h>
+#include <media/v4l2-ctrls.h>
+#include "vivid-tpg.h"
+#include "vivid-rds-gen.h"
+#include "vivid-vbi-gen.h"
+
+#define dprintk(dev, level, fmt, arg...) \
+	v4l2_dbg(level, vivid_debug, &dev->v4l2_dev, fmt, ## arg)
+
+/* Maximum allowed frame rate
+ *
+ * vivid will allow setting timeperframe in [1/FPS_MAX - FPS_MAX/1] range.
+ *
+ * Ideally FPS_MAX should be infinity, i.e. practically UINT_MAX, but that
+ * might hit application errors when they manipulate these values.
+ *
+ * Besides, for tpf < 10ms image-generation logic should be changed, to avoid
+ * producing frames with equal content.
+ */
+#define FPS_MAX 100
+
+/* The maximum number of clip rectangles */
+#define MAX_CLIPS  16
+/* The maximum number of inputs */
+#define MAX_INPUTS 16
+/* The maximum number of outputs */
+#define MAX_OUTPUTS 16
+/* The maximum up or down scaling factor is 4 */
+#define MAX_ZOOM  4
+/* The maximum image width/height are set to 4K DMT */
+#define MAX_WIDTH  4096
+#define MAX_HEIGHT 2160
+/* The minimum image width/height */
+#define MIN_WIDTH  16
+#define MIN_HEIGHT 16
+/* The data_offset of plane 0 for the multiplanar formats */
+#define PLANE0_DATA_OFFSET 128
+
+/* The supported TV frequency range in MHz */
+#define MIN_TV_FREQ (44U * 16U)
+#define MAX_TV_FREQ (958U * 16U)
+
+/* The number of samples returned in every SDR buffer */
+#define SDR_CAP_SAMPLES_PER_BUF 0x4000
+
+/* used by the threads to know when to resync internal counters */
+#define JIFFIES_PER_DAY (3600U * 24U * HZ)
+#define JIFFIES_RESYNC (JIFFIES_PER_DAY * (0xf0000000U / JIFFIES_PER_DAY))
+
+extern const struct v4l2_rect vivid_min_rect;
+extern const struct v4l2_rect vivid_max_rect;
+extern unsigned vivid_debug;
+
+struct vivid_fmt {
+	const char *name;
+	u32	fourcc;          /* v4l2 format id */
+	u8	depth;
+	bool	is_yuv;
+	bool	can_do_overlay;
+	u32	alpha_mask;
+	u8	planes;
+	u32	data_offset[2];
+};
+
+extern struct vivid_fmt vivid_formats[];
+
+/* buffer for one video frame */
+struct vivid_buffer {
+	/* common v4l buffer stuff -- must be first */
+	struct vb2_buffer	vb;
+	struct list_head	list;
+};
+
+enum vivid_input {
+	WEBCAM,
+	TV,
+	SVID,
+	HDMI,
+};
+
+enum vivid_signal_mode {
+	CURRENT_DV_TIMINGS,
+	CURRENT_STD = CURRENT_DV_TIMINGS,
+	NO_SIGNAL,
+	NO_LOCK,
+	OUT_OF_RANGE,
+	SELECTED_DV_TIMINGS,
+	SELECTED_STD = SELECTED_DV_TIMINGS,
+	CYCLE_DV_TIMINGS,
+	CYCLE_STD = CYCLE_DV_TIMINGS,
+	CUSTOM_DV_TIMINGS,
+};
+
+#define VIVID_INVALID_SIGNAL(mode) \
+	((mode) == NO_SIGNAL || (mode) == NO_LOCK || (mode) == OUT_OF_RANGE)
+
+struct vivid_dev {
+	unsigned			inst;
+	struct v4l2_device		v4l2_dev;
+	struct v4l2_ctrl_handler	ctrl_hdl_user_gen;
+	struct v4l2_ctrl_handler	ctrl_hdl_user_vid;
+	struct v4l2_ctrl_handler	ctrl_hdl_user_aud;
+	struct v4l2_ctrl_handler	ctrl_hdl_streaming;
+	struct v4l2_ctrl_handler	ctrl_hdl_sdtv_cap;
+	struct v4l2_ctrl_handler	ctrl_hdl_loop_out;
+	struct video_device		vid_cap_dev;
+	struct v4l2_ctrl_handler	ctrl_hdl_vid_cap;
+	struct video_device		vid_out_dev;
+	struct v4l2_ctrl_handler	ctrl_hdl_vid_out;
+	struct video_device		vbi_cap_dev;
+	struct v4l2_ctrl_handler	ctrl_hdl_vbi_cap;
+	struct video_device		vbi_out_dev;
+	struct v4l2_ctrl_handler	ctrl_hdl_vbi_out;
+	struct video_device		radio_rx_dev;
+	struct v4l2_ctrl_handler	ctrl_hdl_radio_rx;
+	struct video_device		radio_tx_dev;
+	struct v4l2_ctrl_handler	ctrl_hdl_radio_tx;
+	struct video_device		sdr_cap_dev;
+	struct v4l2_ctrl_handler	ctrl_hdl_sdr_cap;
+	spinlock_t			slock;
+	struct mutex			mutex;
+
+	/* capabilities */
+	u32				vid_cap_caps;
+	u32				vid_out_caps;
+	u32				vbi_cap_caps;
+	u32				vbi_out_caps;
+	u32				sdr_cap_caps;
+	u32				radio_rx_caps;
+	u32				radio_tx_caps;
+
+	/* supported features */
+	bool				multiplanar;
+	unsigned			num_inputs;
+	u8				input_type[MAX_INPUTS];
+	u8				input_name_counter[MAX_INPUTS];
+	unsigned			num_outputs;
+	u8				output_type[MAX_OUTPUTS];
+	u8				output_name_counter[MAX_OUTPUTS];
+	bool				has_audio_inputs;
+	bool				has_audio_outputs;
+	bool				has_vid_cap;
+	bool				has_vid_out;
+	bool				has_vbi_cap;
+	bool				has_raw_vbi_cap;
+	bool				has_sliced_vbi_cap;
+	bool				has_vbi_out;
+	bool				has_raw_vbi_out;
+	bool				has_sliced_vbi_out;
+	bool				has_radio_rx;
+	bool				has_radio_tx;
+	bool				has_sdr_cap;
+	bool				has_fb;
+
+	bool				can_loop_video;
+
+	/* controls */
+	struct v4l2_ctrl		*brightness;
+	struct v4l2_ctrl		*contrast;
+	struct v4l2_ctrl		*saturation;
+	struct v4l2_ctrl		*hue;
+	struct {
+		/* autogain/gain cluster */
+		struct v4l2_ctrl	*autogain;
+		struct v4l2_ctrl	*gain;
+	};
+	struct v4l2_ctrl		*volume;
+	struct v4l2_ctrl		*mute;
+	struct v4l2_ctrl		*alpha;
+	struct v4l2_ctrl		*button;
+	struct v4l2_ctrl		*boolean;
+	struct v4l2_ctrl		*int32;
+	struct v4l2_ctrl		*int64;
+	struct v4l2_ctrl		*menu;
+	struct v4l2_ctrl		*string;
+	struct v4l2_ctrl		*bitmask;
+	struct v4l2_ctrl		*int_menu;
+	struct v4l2_ctrl		*test_pattern;
+	struct v4l2_ctrl		*colorspace;
+	struct v4l2_ctrl		*rgb_range_cap;
+	struct v4l2_ctrl		*real_rgb_range_cap;
+	struct {
+		/* std_signal_mode/standard cluster */
+		struct v4l2_ctrl	*ctrl_std_signal_mode;
+		struct v4l2_ctrl	*ctrl_standard;
+	};
+	struct {
+		/* dv_timings_signal_mode/timings cluster */
+		struct v4l2_ctrl	*ctrl_dv_timings_signal_mode;
+		struct v4l2_ctrl	*ctrl_dv_timings;
+	};
+	struct v4l2_ctrl		*ctrl_has_crop_cap;
+	struct v4l2_ctrl		*ctrl_has_compose_cap;
+	struct v4l2_ctrl		*ctrl_has_scaler_cap;
+	struct v4l2_ctrl		*ctrl_has_crop_out;
+	struct v4l2_ctrl		*ctrl_has_compose_out;
+	struct v4l2_ctrl		*ctrl_has_scaler_out;
+	struct v4l2_ctrl		*ctrl_tx_mode;
+	struct v4l2_ctrl		*ctrl_tx_rgb_range;
+
+	struct v4l2_ctrl		*radio_tx_rds_pi;
+	struct v4l2_ctrl		*radio_tx_rds_pty;
+	struct v4l2_ctrl		*radio_tx_rds_mono_stereo;
+	struct v4l2_ctrl		*radio_tx_rds_art_head;
+	struct v4l2_ctrl		*radio_tx_rds_compressed;
+	struct v4l2_ctrl		*radio_tx_rds_dyn_pty;
+	struct v4l2_ctrl		*radio_tx_rds_ta;
+	struct v4l2_ctrl		*radio_tx_rds_tp;
+	struct v4l2_ctrl		*radio_tx_rds_ms;
+	struct v4l2_ctrl		*radio_tx_rds_psname;
+	struct v4l2_ctrl		*radio_tx_rds_radiotext;
+
+	struct v4l2_ctrl		*radio_rx_rds_pty;
+	struct v4l2_ctrl		*radio_rx_rds_ta;
+	struct v4l2_ctrl		*radio_rx_rds_tp;
+	struct v4l2_ctrl		*radio_rx_rds_ms;
+	struct v4l2_ctrl		*radio_rx_rds_psname;
+	struct v4l2_ctrl		*radio_rx_rds_radiotext;
+
+	unsigned			input_brightness[MAX_INPUTS];
+	unsigned			osd_mode;
+	unsigned			button_pressed;
+	bool				sensor_hflip;
+	bool				sensor_vflip;
+	bool				hflip;
+	bool				vflip;
+	bool				vbi_cap_interlaced;
+	bool				loop_video;
+
+	/* Framebuffer */
+	unsigned long			video_pbase;
+	void				*video_vbase;
+	u32				video_buffer_size;
+	int				display_width;
+	int				display_height;
+	int				display_byte_stride;
+	int				bits_per_pixel;
+	int				bytes_per_pixel;
+	struct fb_info			fb_info;
+	struct fb_var_screeninfo	fb_defined;
+	struct fb_fix_screeninfo	fb_fix;
+
+	/* Error injection */
+	bool				queue_setup_error;
+	bool				buf_prepare_error;
+	bool				start_streaming_error;
+	bool				dqbuf_error;
+	bool				seq_wrap;
+	bool				time_wrap;
+	__kernel_time_t			time_wrap_offset;
+	unsigned			perc_dropped_buffers;
+	enum vivid_signal_mode		std_signal_mode;
+	unsigned			query_std_last;
+	v4l2_std_id			query_std;
+	enum tpg_video_aspect		std_aspect_ratio;
+
+	enum vivid_signal_mode		dv_timings_signal_mode;
+	char				**query_dv_timings_qmenu;
+	unsigned			query_dv_timings_size;
+	unsigned			query_dv_timings_last;
+	unsigned			query_dv_timings;
+	enum tpg_video_aspect		dv_timings_aspect_ratio;
+
+	/* Input */
+	unsigned			input;
+	v4l2_std_id			std_cap;
+	struct v4l2_dv_timings		dv_timings_cap;
+	u32				service_set_cap;
+	struct vivid_vbi_gen_data	vbi_gen;
+	u8				*edid;
+	unsigned			edid_blocks;
+	unsigned			edid_max_blocks;
+	unsigned			webcam_size_idx;
+	unsigned			webcam_ival_idx;
+	unsigned			tv_freq;
+	unsigned			tv_audmode;
+	unsigned			tv_field_cap;
+	unsigned			tv_audio_input;
+
+	/* Capture Overlay */
+	struct v4l2_framebuffer		fb_cap;
+	struct v4l2_fh			*overlay_cap_owner;
+	void				*fb_vbase_cap;
+	int				overlay_cap_top, overlay_cap_left;
+	enum v4l2_field			overlay_cap_field;
+	void				*bitmap_cap;
+	struct v4l2_clip		clips_cap[MAX_CLIPS];
+	struct v4l2_clip		try_clips_cap[MAX_CLIPS];
+	unsigned			clipcount_cap;
+
+	/* Output */
+	unsigned			output;
+	v4l2_std_id			std_out;
+	struct v4l2_dv_timings		dv_timings_out;
+	u32				colorspace_out;
+	u32				service_set_out;
+	u32				bytesperline_out[2];
+	unsigned			tv_field_out;
+	unsigned			tv_audio_output;
+	bool				vbi_out_have_wss;
+	u8				vbi_out_wss[2];
+	bool				vbi_out_have_cc[2];
+	u8				vbi_out_cc[2][2];
+	bool				dvi_d_out;
+	u8				*scaled_line;
+	u8				*blended_line;
+	unsigned			cur_scaled_line;
+
+	/* Output Overlay */
+	void				*fb_vbase_out;
+	bool				overlay_out_enabled;
+	int				overlay_out_top, overlay_out_left;
+	void				*bitmap_out;
+	struct v4l2_clip		clips_out[MAX_CLIPS];
+	struct v4l2_clip		try_clips_out[MAX_CLIPS];
+	unsigned			clipcount_out;
+	unsigned			fbuf_out_flags;
+	u32				chromakey_out;
+	u8				global_alpha_out;
+
+	/* video capture */
+	struct tpg_data			tpg;
+	unsigned			ms_vid_cap;
+	bool				must_blank[VIDEO_MAX_FRAME];
+
+	const struct vivid_fmt		*fmt_cap;
+	struct v4l2_fract		timeperframe_vid_cap;
+	enum v4l2_field			field_cap;
+	struct v4l2_rect		src_rect;
+	struct v4l2_rect		fmt_cap_rect;
+	struct v4l2_rect		crop_cap;
+	struct v4l2_rect		compose_cap;
+	struct v4l2_rect		crop_bounds_cap;
+	struct vb2_queue		vb_vid_cap_q;
+	struct list_head		vid_cap_active;
+	struct vb2_queue		vb_vbi_cap_q;
+	struct list_head		vbi_cap_active;
+
+	/* thread for generating video capture stream */
+	struct task_struct		*kthread_vid_cap;
+	unsigned long			jiffies_vid_cap;
+	u32				cap_seq_offset;
+	u32				cap_seq_count;
+	bool				cap_seq_resync;
+	u32				vid_cap_seq_start;
+	u32				vid_cap_seq_count;
+	bool				vid_cap_streaming;
+	u32				vbi_cap_seq_start;
+	u32				vbi_cap_seq_count;
+	bool				vbi_cap_streaming;
+	bool				stream_sliced_vbi_cap;
+
+	/* video output */
+	const struct vivid_fmt		*fmt_out;
+	struct v4l2_fract		timeperframe_vid_out;
+	enum v4l2_field			field_out;
+	struct v4l2_rect		sink_rect;
+	struct v4l2_rect		fmt_out_rect;
+	struct v4l2_rect		crop_out;
+	struct v4l2_rect		compose_out;
+	struct v4l2_rect		compose_bounds_out;
+	struct vb2_queue		vb_vid_out_q;
+	struct list_head		vid_out_active;
+	struct vb2_queue		vb_vbi_out_q;
+	struct list_head		vbi_out_active;
+
+	/* video loop precalculated rectangles */
+
+	/*
+	 * Intersection between what the output side composes and the capture side
+	 * crops. I.e., what actually needs to be copied from the output buffer to
+	 * the capture buffer.
+	 */
+	struct v4l2_rect		loop_vid_copy;
+	/* The part of the output buffer that (after scaling) corresponds to loop_vid_copy. */
+	struct v4l2_rect		loop_vid_out;
+	/* The part of the capture buffer that (after scaling) corresponds to loop_vid_copy. */
+	struct v4l2_rect		loop_vid_cap;
+	/*
+	 * The intersection of the framebuffer, the overlay output window and
+	 * loop_vid_copy. I.e., the part of the framebuffer that actually should be
+	 * blended with the compose_out rectangle. This uses the framebuffer origin.
+	 */
+	struct v4l2_rect		loop_fb_copy;
+	/* The same as loop_fb_copy but with compose_out origin. */
+	struct v4l2_rect		loop_vid_overlay;
+	/*
+	 * The part of the capture buffer that (after scaling) corresponds
+	 * to loop_vid_overlay.
+	 */
+	struct v4l2_rect		loop_vid_overlay_cap;
+
+	/* thread for generating video output stream */
+	struct task_struct		*kthread_vid_out;
+	unsigned long			jiffies_vid_out;
+	u32				out_seq_offset;
+	u32				out_seq_count;
+	bool				out_seq_resync;
+	u32				vid_out_seq_start;
+	u32				vid_out_seq_count;
+	bool				vid_out_streaming;
+	u32				vbi_out_seq_start;
+	u32				vbi_out_seq_count;
+	bool				vbi_out_streaming;
+	bool				stream_sliced_vbi_out;
+
+	/* SDR capture */
+	struct vb2_queue		vb_sdr_cap_q;
+	struct list_head		sdr_cap_active;
+	unsigned			sdr_adc_freq;
+	unsigned			sdr_fm_freq;
+	int				sdr_fixp_src_phase;
+	int				sdr_fixp_mod_phase;
+
+	bool				tstamp_src_is_soe;
+	bool				has_crop_cap;
+	bool				has_compose_cap;
+	bool				has_scaler_cap;
+	bool				has_crop_out;
+	bool				has_compose_out;
+	bool				has_scaler_out;
+
+	/* thread for generating SDR stream */
+	struct task_struct		*kthread_sdr_cap;
+	unsigned long			jiffies_sdr_cap;
+	u32				sdr_cap_seq_offset;
+	u32				sdr_cap_seq_count;
+	bool				sdr_cap_seq_resync;
+
+	/* RDS generator */
+	struct vivid_rds_gen		rds_gen;
+
+	/* Radio receiver */
+	unsigned			radio_rx_freq;
+	unsigned			radio_rx_audmode;
+	int				radio_rx_sig_qual;
+	unsigned			radio_rx_hw_seek_mode;
+	bool				radio_rx_hw_seek_prog_lim;
+	bool				radio_rx_rds_controls;
+	bool				radio_rx_rds_enabled;
+	unsigned			radio_rx_rds_use_alternates;
+	unsigned			radio_rx_rds_last_block;
+	struct v4l2_fh			*radio_rx_rds_owner;
+
+	/* Radio transmitter */
+	unsigned			radio_tx_freq;
+	unsigned			radio_tx_subchans;
+	bool				radio_tx_rds_controls;
+	unsigned			radio_tx_rds_last_block;
+	struct v4l2_fh			*radio_tx_rds_owner;
+
+	/* Shared between radio receiver and transmitter */
+	bool				radio_rds_loop;
+	struct timespec			radio_rds_init_ts;
+};
+
+static inline bool vivid_is_webcam(const struct vivid_dev *dev)
+{
+	return dev->input_type[dev->input] == WEBCAM;
+}
+
+static inline bool vivid_is_tv_cap(const struct vivid_dev *dev)
+{
+	return dev->input_type[dev->input] == TV;
+}
+
+static inline bool vivid_is_svid_cap(const struct vivid_dev *dev)
+{
+	return dev->input_type[dev->input] == SVID;
+}
+
+static inline bool vivid_is_hdmi_cap(const struct vivid_dev *dev)
+{
+	return dev->input_type[dev->input] == HDMI;
+}
+
+static inline bool vivid_is_sdtv_cap(const struct vivid_dev *dev)
+{
+	return vivid_is_tv_cap(dev) || vivid_is_svid_cap(dev);
+}
+
+static inline bool vivid_is_svid_out(const struct vivid_dev *dev)
+{
+	return dev->output_type[dev->output] == SVID;
+}
+
+static inline bool vivid_is_hdmi_out(const struct vivid_dev *dev)
+{
+	return dev->output_type[dev->output] == HDMI;
+}
+
+void vivid_lock(struct vb2_queue *vq);
+void vivid_unlock(struct vb2_queue *vq);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-ctrls.c b/drivers/media/platform/vivid/vivid-ctrls.c
new file mode 100644
index 000000000000..d5cbf0038f24
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-ctrls.c
@@ -0,0 +1,1502 @@
+/*
+ * vivid-ctrls.c - control support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/videodev2.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-common.h>
+
+#include "vivid-core.h"
+#include "vivid-vid-cap.h"
+#include "vivid-vid-out.h"
+#include "vivid-vid-common.h"
+#include "vivid-radio-common.h"
+#include "vivid-osd.h"
+#include "vivid-ctrls.h"
+
+#define VIVID_CID_CUSTOM_BASE		(V4L2_CID_USER_BASE | 0xf000)
+#define VIVID_CID_BUTTON		(VIVID_CID_CUSTOM_BASE + 0)
+#define VIVID_CID_BOOLEAN		(VIVID_CID_CUSTOM_BASE + 1)
+#define VIVID_CID_INTEGER		(VIVID_CID_CUSTOM_BASE + 2)
+#define VIVID_CID_INTEGER64		(VIVID_CID_CUSTOM_BASE + 3)
+#define VIVID_CID_MENU			(VIVID_CID_CUSTOM_BASE + 4)
+#define VIVID_CID_STRING		(VIVID_CID_CUSTOM_BASE + 5)
+#define VIVID_CID_BITMASK		(VIVID_CID_CUSTOM_BASE + 6)
+#define VIVID_CID_INTMENU		(VIVID_CID_CUSTOM_BASE + 7)
+
+#define VIVID_CID_VIVID_BASE		(0x00f00000 | 0xf000)
+#define VIVID_CID_VIVID_CLASS		(0x00f00000 | 1)
+#define VIVID_CID_TEST_PATTERN		(VIVID_CID_VIVID_BASE + 0)
+#define VIVID_CID_OSD_TEXT_MODE		(VIVID_CID_VIVID_BASE + 1)
+#define VIVID_CID_HOR_MOVEMENT		(VIVID_CID_VIVID_BASE + 2)
+#define VIVID_CID_VERT_MOVEMENT		(VIVID_CID_VIVID_BASE + 3)
+#define VIVID_CID_SHOW_BORDER		(VIVID_CID_VIVID_BASE + 4)
+#define VIVID_CID_SHOW_SQUARE		(VIVID_CID_VIVID_BASE + 5)
+#define VIVID_CID_INSERT_SAV		(VIVID_CID_VIVID_BASE + 6)
+#define VIVID_CID_INSERT_EAV		(VIVID_CID_VIVID_BASE + 7)
+#define VIVID_CID_VBI_CAP_INTERLACED	(VIVID_CID_VIVID_BASE + 8)
+
+#define VIVID_CID_HFLIP			(VIVID_CID_VIVID_BASE + 20)
+#define VIVID_CID_VFLIP			(VIVID_CID_VIVID_BASE + 21)
+#define VIVID_CID_STD_ASPECT_RATIO	(VIVID_CID_VIVID_BASE + 22)
+#define VIVID_CID_DV_TIMINGS_ASPECT_RATIO	(VIVID_CID_VIVID_BASE + 23)
+#define VIVID_CID_TSTAMP_SRC		(VIVID_CID_VIVID_BASE + 24)
+#define VIVID_CID_COLORSPACE		(VIVID_CID_VIVID_BASE + 25)
+#define VIVID_CID_LIMITED_RGB_RANGE	(VIVID_CID_VIVID_BASE + 26)
+#define VIVID_CID_ALPHA_MODE		(VIVID_CID_VIVID_BASE + 27)
+#define VIVID_CID_HAS_CROP_CAP		(VIVID_CID_VIVID_BASE + 28)
+#define VIVID_CID_HAS_COMPOSE_CAP	(VIVID_CID_VIVID_BASE + 29)
+#define VIVID_CID_HAS_SCALER_CAP	(VIVID_CID_VIVID_BASE + 30)
+#define VIVID_CID_HAS_CROP_OUT		(VIVID_CID_VIVID_BASE + 31)
+#define VIVID_CID_HAS_COMPOSE_OUT	(VIVID_CID_VIVID_BASE + 32)
+#define VIVID_CID_HAS_SCALER_OUT	(VIVID_CID_VIVID_BASE + 33)
+#define VIVID_CID_LOOP_VIDEO		(VIVID_CID_VIVID_BASE + 34)
+#define VIVID_CID_SEQ_WRAP		(VIVID_CID_VIVID_BASE + 35)
+#define VIVID_CID_TIME_WRAP		(VIVID_CID_VIVID_BASE + 36)
+#define VIVID_CID_MAX_EDID_BLOCKS	(VIVID_CID_VIVID_BASE + 37)
+#define VIVID_CID_PERCENTAGE_FILL	(VIVID_CID_VIVID_BASE + 38)
+
+#define VIVID_CID_STD_SIGNAL_MODE	(VIVID_CID_VIVID_BASE + 60)
+#define VIVID_CID_STANDARD		(VIVID_CID_VIVID_BASE + 61)
+#define VIVID_CID_DV_TIMINGS_SIGNAL_MODE	(VIVID_CID_VIVID_BASE + 62)
+#define VIVID_CID_DV_TIMINGS		(VIVID_CID_VIVID_BASE + 63)
+#define VIVID_CID_PERC_DROPPED		(VIVID_CID_VIVID_BASE + 64)
+#define VIVID_CID_DISCONNECT		(VIVID_CID_VIVID_BASE + 65)
+#define VIVID_CID_DQBUF_ERROR		(VIVID_CID_VIVID_BASE + 66)
+#define VIVID_CID_QUEUE_SETUP_ERROR	(VIVID_CID_VIVID_BASE + 67)
+#define VIVID_CID_BUF_PREPARE_ERROR	(VIVID_CID_VIVID_BASE + 68)
+#define VIVID_CID_START_STR_ERROR	(VIVID_CID_VIVID_BASE + 69)
+#define VIVID_CID_QUEUE_ERROR		(VIVID_CID_VIVID_BASE + 70)
+#define VIVID_CID_CLEAR_FB		(VIVID_CID_VIVID_BASE + 71)
+
+#define VIVID_CID_RADIO_SEEK_MODE	(VIVID_CID_VIVID_BASE + 90)
+#define VIVID_CID_RADIO_SEEK_PROG_LIM	(VIVID_CID_VIVID_BASE + 91)
+#define VIVID_CID_RADIO_RX_RDS_RBDS	(VIVID_CID_VIVID_BASE + 92)
+#define VIVID_CID_RADIO_RX_RDS_BLOCKIO	(VIVID_CID_VIVID_BASE + 93)
+
+#define VIVID_CID_RADIO_TX_RDS_BLOCKIO	(VIVID_CID_VIVID_BASE + 94)
+
+
+/* General User Controls */
+
+static int vivid_user_gen_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_user_gen);
+
+	switch (ctrl->id) {
+	case VIVID_CID_DISCONNECT:
+		v4l2_info(&dev->v4l2_dev, "disconnect\n");
+		clear_bit(V4L2_FL_REGISTERED, &dev->vid_cap_dev.flags);
+		clear_bit(V4L2_FL_REGISTERED, &dev->vid_out_dev.flags);
+		clear_bit(V4L2_FL_REGISTERED, &dev->vbi_cap_dev.flags);
+		clear_bit(V4L2_FL_REGISTERED, &dev->vbi_out_dev.flags);
+		clear_bit(V4L2_FL_REGISTERED, &dev->sdr_cap_dev.flags);
+		clear_bit(V4L2_FL_REGISTERED, &dev->radio_rx_dev.flags);
+		clear_bit(V4L2_FL_REGISTERED, &dev->radio_tx_dev.flags);
+		break;
+	case VIVID_CID_CLEAR_FB:
+		vivid_clear_fb(dev);
+		break;
+	case VIVID_CID_BUTTON:
+		dev->button_pressed = 30;
+		break;
+	}
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vivid_user_gen_ctrl_ops = {
+	.s_ctrl = vivid_user_gen_s_ctrl,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_button = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.id = VIVID_CID_BUTTON,
+	.name = "Button",
+	.type = V4L2_CTRL_TYPE_BUTTON,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_boolean = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.id = VIVID_CID_BOOLEAN,
+	.name = "Boolean",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.min = 0,
+	.max = 1,
+	.step = 1,
+	.def = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_int32 = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.id = VIVID_CID_INTEGER,
+	.name = "Integer 32 Bits",
+	.type = V4L2_CTRL_TYPE_INTEGER,
+	.min = 0xffffffff80000000ULL,
+	.max = 0x7fffffff,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_int64 = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.id = VIVID_CID_INTEGER64,
+	.name = "Integer 64 Bits",
+	.type = V4L2_CTRL_TYPE_INTEGER64,
+	.min = 0x8000000000000000ULL,
+	.max = 0x7fffffffffffffffLL,
+	.step = 1,
+};
+
+static const char * const vivid_ctrl_menu_strings[] = {
+	"Menu Item 0 (Skipped)",
+	"Menu Item 1",
+	"Menu Item 2 (Skipped)",
+	"Menu Item 3",
+	"Menu Item 4",
+	"Menu Item 5 (Skipped)",
+	NULL,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_menu = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.id = VIVID_CID_MENU,
+	.name = "Menu",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.min = 1,
+	.max = 4,
+	.def = 3,
+	.menu_skip_mask = 0x04,
+	.qmenu = vivid_ctrl_menu_strings,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_string = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.id = VIVID_CID_STRING,
+	.name = "String",
+	.type = V4L2_CTRL_TYPE_STRING,
+	.min = 2,
+	.max = 4,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_bitmask = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.id = VIVID_CID_BITMASK,
+	.name = "Bitmask",
+	.type = V4L2_CTRL_TYPE_BITMASK,
+	.def = 0x80002000,
+	.min = 0,
+	.max = 0x80402010,
+	.step = 0,
+};
+
+static const s64 vivid_ctrl_int_menu_values[] = {
+	1, 1, 2, 3, 5, 8, 13, 21, 42,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_int_menu = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.id = VIVID_CID_INTMENU,
+	.name = "Integer Menu",
+	.type = V4L2_CTRL_TYPE_INTEGER_MENU,
+	.min = 1,
+	.max = 8,
+	.def = 4,
+	.menu_skip_mask = 0x02,
+	.qmenu_int = vivid_ctrl_int_menu_values,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_disconnect = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.id = VIVID_CID_DISCONNECT,
+	.name = "Disconnect",
+	.type = V4L2_CTRL_TYPE_BUTTON,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_clear_fb = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.id = VIVID_CID_CLEAR_FB,
+	.name = "Clear Framebuffer",
+	.type = V4L2_CTRL_TYPE_BUTTON,
+};
+
+
+/* Video User Controls */
+
+static int vivid_user_vid_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_user_vid);
+
+	switch (ctrl->id) {
+	case V4L2_CID_AUTOGAIN:
+		dev->gain->val = dev->jiffies_vid_cap & 0xff;
+		break;
+	}
+	return 0;
+}
+
+static int vivid_user_vid_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_user_vid);
+
+	switch (ctrl->id) {
+	case V4L2_CID_BRIGHTNESS:
+		dev->input_brightness[dev->input] = ctrl->val - dev->input * 128;
+		tpg_s_brightness(&dev->tpg, dev->input_brightness[dev->input]);
+		break;
+	case V4L2_CID_CONTRAST:
+		tpg_s_contrast(&dev->tpg, ctrl->val);
+		break;
+	case V4L2_CID_SATURATION:
+		tpg_s_saturation(&dev->tpg, ctrl->val);
+		break;
+	case V4L2_CID_HUE:
+		tpg_s_hue(&dev->tpg, ctrl->val);
+		break;
+	case V4L2_CID_HFLIP:
+		dev->hflip = ctrl->val;
+		tpg_s_hflip(&dev->tpg, dev->sensor_hflip ^ dev->hflip);
+		break;
+	case V4L2_CID_VFLIP:
+		dev->vflip = ctrl->val;
+		tpg_s_vflip(&dev->tpg, dev->sensor_vflip ^ dev->vflip);
+		break;
+	case V4L2_CID_ALPHA_COMPONENT:
+		tpg_s_alpha_component(&dev->tpg, ctrl->val);
+		break;
+	}
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vivid_user_vid_ctrl_ops = {
+	.g_volatile_ctrl = vivid_user_vid_g_volatile_ctrl,
+	.s_ctrl = vivid_user_vid_s_ctrl,
+};
+
+
+/* Video Capture Controls */
+
+static int vivid_vid_cap_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_vid_cap);
+	unsigned i;
+
+	switch (ctrl->id) {
+	case VIVID_CID_TEST_PATTERN:
+		vivid_update_quality(dev);
+		tpg_s_pattern(&dev->tpg, ctrl->val);
+		break;
+	case VIVID_CID_COLORSPACE:
+		tpg_s_colorspace(&dev->tpg, ctrl->val);
+		vivid_send_source_change(dev, TV);
+		vivid_send_source_change(dev, SVID);
+		vivid_send_source_change(dev, HDMI);
+		vivid_send_source_change(dev, WEBCAM);
+		break;
+	case V4L2_CID_DV_RX_RGB_RANGE:
+		if (!vivid_is_hdmi_cap(dev))
+			break;
+		tpg_s_rgb_range(&dev->tpg, ctrl->val);
+		break;
+	case VIVID_CID_LIMITED_RGB_RANGE:
+		tpg_s_real_rgb_range(&dev->tpg, ctrl->val ?
+				V4L2_DV_RGB_RANGE_LIMITED : V4L2_DV_RGB_RANGE_FULL);
+		break;
+	case VIVID_CID_ALPHA_MODE:
+		tpg_s_alpha_mode(&dev->tpg, ctrl->val);
+		break;
+	case VIVID_CID_HOR_MOVEMENT:
+		tpg_s_mv_hor_mode(&dev->tpg, ctrl->val);
+		break;
+	case VIVID_CID_VERT_MOVEMENT:
+		tpg_s_mv_vert_mode(&dev->tpg, ctrl->val);
+		break;
+	case VIVID_CID_OSD_TEXT_MODE:
+		dev->osd_mode = ctrl->val;
+		break;
+	case VIVID_CID_PERCENTAGE_FILL:
+		tpg_s_perc_fill(&dev->tpg, ctrl->val);
+		for (i = 0; i < VIDEO_MAX_FRAME; i++)
+			dev->must_blank[i] = ctrl->val < 100;
+		break;
+	case VIVID_CID_INSERT_SAV:
+		tpg_s_insert_sav(&dev->tpg, ctrl->val);
+		break;
+	case VIVID_CID_INSERT_EAV:
+		tpg_s_insert_eav(&dev->tpg, ctrl->val);
+		break;
+	case VIVID_CID_HFLIP:
+		dev->sensor_hflip = ctrl->val;
+		tpg_s_hflip(&dev->tpg, dev->sensor_hflip ^ dev->hflip);
+		break;
+	case VIVID_CID_VFLIP:
+		dev->sensor_vflip = ctrl->val;
+		tpg_s_vflip(&dev->tpg, dev->sensor_vflip ^ dev->vflip);
+		break;
+	case VIVID_CID_HAS_CROP_CAP:
+		dev->has_crop_cap = ctrl->val;
+		vivid_update_format_cap(dev, true);
+		break;
+	case VIVID_CID_HAS_COMPOSE_CAP:
+		dev->has_compose_cap = ctrl->val;
+		vivid_update_format_cap(dev, true);
+		break;
+	case VIVID_CID_HAS_SCALER_CAP:
+		dev->has_scaler_cap = ctrl->val;
+		vivid_update_format_cap(dev, true);
+		break;
+	case VIVID_CID_SHOW_BORDER:
+		tpg_s_show_border(&dev->tpg, ctrl->val);
+		break;
+	case VIVID_CID_SHOW_SQUARE:
+		tpg_s_show_square(&dev->tpg, ctrl->val);
+		break;
+	case VIVID_CID_STD_ASPECT_RATIO:
+		dev->std_aspect_ratio = ctrl->val;
+		tpg_s_video_aspect(&dev->tpg, vivid_get_video_aspect(dev));
+		break;
+	case VIVID_CID_DV_TIMINGS_SIGNAL_MODE:
+		dev->dv_timings_signal_mode = dev->ctrl_dv_timings_signal_mode->val;
+		if (dev->dv_timings_signal_mode == SELECTED_DV_TIMINGS)
+			dev->query_dv_timings = dev->ctrl_dv_timings->val;
+		v4l2_ctrl_activate(dev->ctrl_dv_timings,
+				dev->dv_timings_signal_mode == SELECTED_DV_TIMINGS);
+		vivid_update_quality(dev);
+		vivid_send_source_change(dev, HDMI);
+		break;
+	case VIVID_CID_DV_TIMINGS_ASPECT_RATIO:
+		dev->dv_timings_aspect_ratio = ctrl->val;
+		tpg_s_video_aspect(&dev->tpg, vivid_get_video_aspect(dev));
+		break;
+	case VIVID_CID_TSTAMP_SRC:
+		dev->tstamp_src_is_soe = ctrl->val;
+		dev->vb_vid_cap_q.timestamp_flags &= ~V4L2_BUF_FLAG_TSTAMP_SRC_MASK;
+		if (dev->tstamp_src_is_soe)
+			dev->vb_vid_cap_q.timestamp_flags |= V4L2_BUF_FLAG_TSTAMP_SRC_SOE;
+		break;
+	case VIVID_CID_MAX_EDID_BLOCKS:
+		dev->edid_max_blocks = ctrl->val;
+		if (dev->edid_blocks > dev->edid_max_blocks)
+			dev->edid_blocks = dev->edid_max_blocks;
+		break;
+	}
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vivid_vid_cap_ctrl_ops = {
+	.s_ctrl = vivid_vid_cap_s_ctrl,
+};
+
+static const char * const vivid_ctrl_hor_movement_strings[] = {
+	"Move Left Fast",
+	"Move Left",
+	"Move Left Slow",
+	"No Movement",
+	"Move Right Slow",
+	"Move Right",
+	"Move Right Fast",
+	NULL,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_hor_movement = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_HOR_MOVEMENT,
+	.name = "Horizontal Movement",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.max = TPG_MOVE_POS_FAST,
+	.def = TPG_MOVE_NONE,
+	.qmenu = vivid_ctrl_hor_movement_strings,
+};
+
+static const char * const vivid_ctrl_vert_movement_strings[] = {
+	"Move Up Fast",
+	"Move Up",
+	"Move Up Slow",
+	"No Movement",
+	"Move Down Slow",
+	"Move Down",
+	"Move Down Fast",
+	NULL,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_vert_movement = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_VERT_MOVEMENT,
+	.name = "Vertical Movement",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.max = TPG_MOVE_POS_FAST,
+	.def = TPG_MOVE_NONE,
+	.qmenu = vivid_ctrl_vert_movement_strings,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_show_border = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_SHOW_BORDER,
+	.name = "Show Border",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_show_square = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_SHOW_SQUARE,
+	.name = "Show Square",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+static const char * const vivid_ctrl_osd_mode_strings[] = {
+	"All",
+	"Counters Only",
+	"None",
+	NULL,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_osd_mode = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_OSD_TEXT_MODE,
+	.name = "OSD Text Mode",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.max = 2,
+	.qmenu = vivid_ctrl_osd_mode_strings,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_perc_fill = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_PERCENTAGE_FILL,
+	.name = "Fill Percentage of Frame",
+	.type = V4L2_CTRL_TYPE_INTEGER,
+	.min = 0,
+	.max = 100,
+	.def = 100,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_insert_sav = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_INSERT_SAV,
+	.name = "Insert SAV Code in Image",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_insert_eav = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_INSERT_EAV,
+	.name = "Insert EAV Code in Image",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_hflip = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_HFLIP,
+	.name = "Sensor Flipped Horizontally",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_vflip = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_VFLIP,
+	.name = "Sensor Flipped Vertically",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_has_crop_cap = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_HAS_CROP_CAP,
+	.name = "Enable Capture Cropping",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.def = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_has_compose_cap = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_HAS_COMPOSE_CAP,
+	.name = "Enable Capture Composing",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.def = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_has_scaler_cap = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_HAS_SCALER_CAP,
+	.name = "Enable Capture Scaler",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.def = 1,
+	.step = 1,
+};
+
+static const char * const vivid_ctrl_tstamp_src_strings[] = {
+	"End of Frame",
+	"Start of Exposure",
+	NULL,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_tstamp_src = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_TSTAMP_SRC,
+	.name = "Timestamp Source",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.max = 1,
+	.qmenu = vivid_ctrl_tstamp_src_strings,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_std_aspect_ratio = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_STD_ASPECT_RATIO,
+	.name = "Standard Aspect Ratio",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.min = 1,
+	.max = 4,
+	.def = 1,
+	.qmenu = tpg_aspect_strings,
+};
+
+static const char * const vivid_ctrl_dv_timings_signal_mode_strings[] = {
+	"Current DV Timings",
+	"No Signal",
+	"No Lock",
+	"Out of Range",
+	"Selected DV Timings",
+	"Cycle Through All DV Timings",
+	"Custom DV Timings",
+	NULL,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_dv_timings_signal_mode = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_DV_TIMINGS_SIGNAL_MODE,
+	.name = "DV Timings Signal Mode",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.max = 5,
+	.qmenu = vivid_ctrl_dv_timings_signal_mode_strings,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_dv_timings_aspect_ratio = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_DV_TIMINGS_ASPECT_RATIO,
+	.name = "DV Timings Aspect Ratio",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.max = 3,
+	.qmenu = tpg_aspect_strings,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_max_edid_blocks = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_MAX_EDID_BLOCKS,
+	.name = "Maximum EDID Blocks",
+	.type = V4L2_CTRL_TYPE_INTEGER,
+	.min = 1,
+	.max = 256,
+	.def = 2,
+	.step = 1,
+};
+
+static const char * const vivid_ctrl_colorspace_strings[] = {
+	"",
+	"SMPTE 170M",
+	"SMPTE 240M",
+	"REC 709",
+	"", /* Skip Bt878 entry */
+	"470 System M",
+	"470 System BG",
+	"", /* Skip JPEG entry */
+	"sRGB",
+	NULL,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_colorspace = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_COLORSPACE,
+	.name = "Colorspace",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.min = 1,
+	.max = 8,
+	.menu_skip_mask = (1 << 4) | (1 << 7),
+	.def = 8,
+	.qmenu = vivid_ctrl_colorspace_strings,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_alpha_mode = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_ALPHA_MODE,
+	.name = "Apply Alpha To Red Only",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_limited_rgb_range = {
+	.ops = &vivid_vid_cap_ctrl_ops,
+	.id = VIVID_CID_LIMITED_RGB_RANGE,
+	.name = "Limited RGB Range (16-235)",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+
+/* VBI Capture Control */
+
+static int vivid_vbi_cap_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_vbi_cap);
+
+	switch (ctrl->id) {
+	case VIVID_CID_VBI_CAP_INTERLACED:
+		dev->vbi_cap_interlaced = ctrl->val;
+		break;
+	}
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vivid_vbi_cap_ctrl_ops = {
+	.s_ctrl = vivid_vbi_cap_s_ctrl,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_vbi_cap_interlaced = {
+	.ops = &vivid_vbi_cap_ctrl_ops,
+	.id = VIVID_CID_VBI_CAP_INTERLACED,
+	.name = "Interlaced VBI Format",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+
+/* Video Output Controls */
+
+static int vivid_vid_out_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_vid_out);
+	struct v4l2_bt_timings *bt = &dev->dv_timings_out.bt;
+
+	switch (ctrl->id) {
+	case VIVID_CID_HAS_CROP_OUT:
+		dev->has_crop_out = ctrl->val;
+		vivid_update_format_out(dev);
+		break;
+	case VIVID_CID_HAS_COMPOSE_OUT:
+		dev->has_compose_out = ctrl->val;
+		vivid_update_format_out(dev);
+		break;
+	case VIVID_CID_HAS_SCALER_OUT:
+		dev->has_scaler_out = ctrl->val;
+		vivid_update_format_out(dev);
+		break;
+	case V4L2_CID_DV_TX_MODE:
+		dev->dvi_d_out = ctrl->val == V4L2_DV_TX_MODE_DVI_D;
+		if (!vivid_is_hdmi_out(dev))
+			break;
+		if (!dev->dvi_d_out && (bt->standards & V4L2_DV_BT_STD_CEA861)) {
+			if (bt->width == 720 && bt->height <= 576)
+				dev->colorspace_out = V4L2_COLORSPACE_SMPTE170M;
+			else
+				dev->colorspace_out = V4L2_COLORSPACE_REC709;
+		} else {
+			dev->colorspace_out = V4L2_COLORSPACE_SRGB;
+		}
+		if (dev->loop_video)
+			vivid_send_source_change(dev, HDMI);
+		break;
+	}
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vivid_vid_out_ctrl_ops = {
+	.s_ctrl = vivid_vid_out_s_ctrl,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_has_crop_out = {
+	.ops = &vivid_vid_out_ctrl_ops,
+	.id = VIVID_CID_HAS_CROP_OUT,
+	.name = "Enable Output Cropping",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.def = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_has_compose_out = {
+	.ops = &vivid_vid_out_ctrl_ops,
+	.id = VIVID_CID_HAS_COMPOSE_OUT,
+	.name = "Enable Output Composing",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.def = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_has_scaler_out = {
+	.ops = &vivid_vid_out_ctrl_ops,
+	.id = VIVID_CID_HAS_SCALER_OUT,
+	.name = "Enable Output Scaler",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.def = 1,
+	.step = 1,
+};
+
+
+/* Streaming Controls */
+
+static int vivid_streaming_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_streaming);
+	struct timeval tv;
+
+	switch (ctrl->id) {
+	case VIVID_CID_DQBUF_ERROR:
+		dev->dqbuf_error = true;
+		break;
+	case VIVID_CID_PERC_DROPPED:
+		dev->perc_dropped_buffers = ctrl->val;
+		break;
+	case VIVID_CID_QUEUE_SETUP_ERROR:
+		dev->queue_setup_error = true;
+		break;
+	case VIVID_CID_BUF_PREPARE_ERROR:
+		dev->buf_prepare_error = true;
+		break;
+	case VIVID_CID_START_STR_ERROR:
+		dev->start_streaming_error = true;
+		break;
+	case VIVID_CID_QUEUE_ERROR:
+		if (dev->vb_vid_cap_q.start_streaming_called)
+			vb2_queue_error(&dev->vb_vid_cap_q);
+		if (dev->vb_vbi_cap_q.start_streaming_called)
+			vb2_queue_error(&dev->vb_vbi_cap_q);
+		if (dev->vb_vid_out_q.start_streaming_called)
+			vb2_queue_error(&dev->vb_vid_out_q);
+		if (dev->vb_vbi_out_q.start_streaming_called)
+			vb2_queue_error(&dev->vb_vbi_out_q);
+		if (dev->vb_sdr_cap_q.start_streaming_called)
+			vb2_queue_error(&dev->vb_sdr_cap_q);
+		break;
+	case VIVID_CID_SEQ_WRAP:
+		dev->seq_wrap = ctrl->val;
+		break;
+	case VIVID_CID_TIME_WRAP:
+		dev->time_wrap = ctrl->val;
+		if (ctrl->val == 0) {
+			dev->time_wrap_offset = 0;
+			break;
+		}
+		v4l2_get_timestamp(&tv);
+		dev->time_wrap_offset = -tv.tv_sec - 16;
+		break;
+	}
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vivid_streaming_ctrl_ops = {
+	.s_ctrl = vivid_streaming_s_ctrl,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_dqbuf_error = {
+	.ops = &vivid_streaming_ctrl_ops,
+	.id = VIVID_CID_DQBUF_ERROR,
+	.name = "Inject V4L2_BUF_FLAG_ERROR",
+	.type = V4L2_CTRL_TYPE_BUTTON,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_perc_dropped = {
+	.ops = &vivid_streaming_ctrl_ops,
+	.id = VIVID_CID_PERC_DROPPED,
+	.name = "Percentage of Dropped Buffers",
+	.type = V4L2_CTRL_TYPE_INTEGER,
+	.min = 0,
+	.max = 100,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_queue_setup_error = {
+	.ops = &vivid_streaming_ctrl_ops,
+	.id = VIVID_CID_QUEUE_SETUP_ERROR,
+	.name = "Inject VIDIOC_REQBUFS Error",
+	.type = V4L2_CTRL_TYPE_BUTTON,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_buf_prepare_error = {
+	.ops = &vivid_streaming_ctrl_ops,
+	.id = VIVID_CID_BUF_PREPARE_ERROR,
+	.name = "Inject VIDIOC_QBUF Error",
+	.type = V4L2_CTRL_TYPE_BUTTON,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_start_streaming_error = {
+	.ops = &vivid_streaming_ctrl_ops,
+	.id = VIVID_CID_START_STR_ERROR,
+	.name = "Inject VIDIOC_STREAMON Error",
+	.type = V4L2_CTRL_TYPE_BUTTON,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_queue_error = {
+	.ops = &vivid_streaming_ctrl_ops,
+	.id = VIVID_CID_QUEUE_ERROR,
+	.name = "Inject Fatal Streaming Error",
+	.type = V4L2_CTRL_TYPE_BUTTON,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_seq_wrap = {
+	.ops = &vivid_streaming_ctrl_ops,
+	.id = VIVID_CID_SEQ_WRAP,
+	.name = "Wrap Sequence Number",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_time_wrap = {
+	.ops = &vivid_streaming_ctrl_ops,
+	.id = VIVID_CID_TIME_WRAP,
+	.name = "Wrap Timestamp",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+
+/* SDTV Capture Controls */
+
+static int vivid_sdtv_cap_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_sdtv_cap);
+
+	switch (ctrl->id) {
+	case VIVID_CID_STD_SIGNAL_MODE:
+		dev->std_signal_mode = dev->ctrl_std_signal_mode->val;
+		if (dev->std_signal_mode == SELECTED_STD)
+			dev->query_std = vivid_standard[dev->ctrl_standard->val];
+		v4l2_ctrl_activate(dev->ctrl_standard, dev->std_signal_mode == SELECTED_STD);
+		vivid_update_quality(dev);
+		vivid_send_source_change(dev, TV);
+		vivid_send_source_change(dev, SVID);
+		break;
+	}
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vivid_sdtv_cap_ctrl_ops = {
+	.s_ctrl = vivid_sdtv_cap_s_ctrl,
+};
+
+static const char * const vivid_ctrl_std_signal_mode_strings[] = {
+	"Current Standard",
+	"No Signal",
+	"No Lock",
+	"",
+	"Selected Standard",
+	"Cycle Through All Standards",
+	NULL,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_std_signal_mode = {
+	.ops = &vivid_sdtv_cap_ctrl_ops,
+	.id = VIVID_CID_STD_SIGNAL_MODE,
+	.name = "Standard Signal Mode",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.max = 5,
+	.menu_skip_mask = 1 << 3,
+	.qmenu = vivid_ctrl_std_signal_mode_strings,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_standard = {
+	.ops = &vivid_sdtv_cap_ctrl_ops,
+	.id = VIVID_CID_STANDARD,
+	.name = "Standard",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.max = 14,
+	.qmenu = vivid_ctrl_standard_strings,
+};
+
+
+
+/* Radio Receiver Controls */
+
+static int vivid_radio_rx_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_radio_rx);
+
+	switch (ctrl->id) {
+	case VIVID_CID_RADIO_SEEK_MODE:
+		dev->radio_rx_hw_seek_mode = ctrl->val;
+		break;
+	case VIVID_CID_RADIO_SEEK_PROG_LIM:
+		dev->radio_rx_hw_seek_prog_lim = ctrl->val;
+		break;
+	case VIVID_CID_RADIO_RX_RDS_RBDS:
+		dev->rds_gen.use_rbds = ctrl->val;
+		break;
+	case VIVID_CID_RADIO_RX_RDS_BLOCKIO:
+		dev->radio_rx_rds_controls = ctrl->val;
+		dev->radio_rx_caps &= ~V4L2_CAP_READWRITE;
+		dev->radio_rx_rds_use_alternates = false;
+		if (!dev->radio_rx_rds_controls) {
+			dev->radio_rx_caps |= V4L2_CAP_READWRITE;
+			__v4l2_ctrl_s_ctrl(dev->radio_rx_rds_pty, 0);
+			__v4l2_ctrl_s_ctrl(dev->radio_rx_rds_ta, 0);
+			__v4l2_ctrl_s_ctrl(dev->radio_rx_rds_tp, 0);
+			__v4l2_ctrl_s_ctrl(dev->radio_rx_rds_ms, 0);
+			__v4l2_ctrl_s_ctrl_string(dev->radio_rx_rds_psname, "");
+			__v4l2_ctrl_s_ctrl_string(dev->radio_rx_rds_radiotext, "");
+		}
+		v4l2_ctrl_activate(dev->radio_rx_rds_pty, dev->radio_rx_rds_controls);
+		v4l2_ctrl_activate(dev->radio_rx_rds_psname, dev->radio_rx_rds_controls);
+		v4l2_ctrl_activate(dev->radio_rx_rds_radiotext, dev->radio_rx_rds_controls);
+		v4l2_ctrl_activate(dev->radio_rx_rds_ta, dev->radio_rx_rds_controls);
+		v4l2_ctrl_activate(dev->radio_rx_rds_tp, dev->radio_rx_rds_controls);
+		v4l2_ctrl_activate(dev->radio_rx_rds_ms, dev->radio_rx_rds_controls);
+		break;
+	case V4L2_CID_RDS_RECEPTION:
+		dev->radio_rx_rds_enabled = ctrl->val;
+		break;
+	}
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vivid_radio_rx_ctrl_ops = {
+	.s_ctrl = vivid_radio_rx_s_ctrl,
+};
+
+static const char * const vivid_ctrl_radio_rds_mode_strings[] = {
+	"Block I/O",
+	"Controls",
+	NULL,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_radio_rx_rds_blockio = {
+	.ops = &vivid_radio_rx_ctrl_ops,
+	.id = VIVID_CID_RADIO_RX_RDS_BLOCKIO,
+	.name = "RDS Rx I/O Mode",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.qmenu = vivid_ctrl_radio_rds_mode_strings,
+	.max = 1,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_radio_rx_rds_rbds = {
+	.ops = &vivid_radio_rx_ctrl_ops,
+	.id = VIVID_CID_RADIO_RX_RDS_RBDS,
+	.name = "Generate RBDS Instead of RDS",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+static const char * const vivid_ctrl_radio_hw_seek_mode_strings[] = {
+	"Bounded",
+	"Wrap Around",
+	"Both",
+	NULL,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_radio_hw_seek_mode = {
+	.ops = &vivid_radio_rx_ctrl_ops,
+	.id = VIVID_CID_RADIO_SEEK_MODE,
+	.name = "Radio HW Seek Mode",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.max = 2,
+	.qmenu = vivid_ctrl_radio_hw_seek_mode_strings,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_radio_hw_seek_prog_lim = {
+	.ops = &vivid_radio_rx_ctrl_ops,
+	.id = VIVID_CID_RADIO_SEEK_PROG_LIM,
+	.name = "Radio Programmable HW Seek",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+
+/* Radio Transmitter Controls */
+
+static int vivid_radio_tx_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_radio_tx);
+
+	switch (ctrl->id) {
+	case VIVID_CID_RADIO_TX_RDS_BLOCKIO:
+		dev->radio_tx_rds_controls = ctrl->val;
+		dev->radio_tx_caps &= ~V4L2_CAP_READWRITE;
+		if (!dev->radio_tx_rds_controls)
+			dev->radio_tx_caps |= V4L2_CAP_READWRITE;
+		break;
+	case V4L2_CID_RDS_TX_PTY:
+		if (dev->radio_rx_rds_controls)
+			v4l2_ctrl_s_ctrl(dev->radio_rx_rds_pty, ctrl->val);
+		break;
+	case V4L2_CID_RDS_TX_PS_NAME:
+		if (dev->radio_rx_rds_controls)
+			v4l2_ctrl_s_ctrl_string(dev->radio_rx_rds_psname, ctrl->p_new.p_char);
+		break;
+	case V4L2_CID_RDS_TX_RADIO_TEXT:
+		if (dev->radio_rx_rds_controls)
+			v4l2_ctrl_s_ctrl_string(dev->radio_rx_rds_radiotext, ctrl->p_new.p_char);
+		break;
+	case V4L2_CID_RDS_TX_TRAFFIC_ANNOUNCEMENT:
+		if (dev->radio_rx_rds_controls)
+			v4l2_ctrl_s_ctrl(dev->radio_rx_rds_ta, ctrl->val);
+		break;
+	case V4L2_CID_RDS_TX_TRAFFIC_PROGRAM:
+		if (dev->radio_rx_rds_controls)
+			v4l2_ctrl_s_ctrl(dev->radio_rx_rds_tp, ctrl->val);
+		break;
+	case V4L2_CID_RDS_TX_MUSIC_SPEECH:
+		if (dev->radio_rx_rds_controls)
+			v4l2_ctrl_s_ctrl(dev->radio_rx_rds_ms, ctrl->val);
+		break;
+	}
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vivid_radio_tx_ctrl_ops = {
+	.s_ctrl = vivid_radio_tx_s_ctrl,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_radio_tx_rds_blockio = {
+	.ops = &vivid_radio_tx_ctrl_ops,
+	.id = VIVID_CID_RADIO_TX_RDS_BLOCKIO,
+	.name = "RDS Tx I/O Mode",
+	.type = V4L2_CTRL_TYPE_MENU,
+	.qmenu = vivid_ctrl_radio_rds_mode_strings,
+	.max = 1,
+	.def = 1,
+};
+
+
+
+/* Video Loop Control */
+
+static int vivid_loop_out_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct vivid_dev *dev = container_of(ctrl->handler, struct vivid_dev, ctrl_hdl_loop_out);
+
+	switch (ctrl->id) {
+	case VIVID_CID_LOOP_VIDEO:
+		dev->loop_video = ctrl->val;
+		vivid_update_quality(dev);
+		vivid_send_source_change(dev, SVID);
+		vivid_send_source_change(dev, HDMI);
+		break;
+	}
+	return 0;
+}
+
+static const struct v4l2_ctrl_ops vivid_loop_out_ctrl_ops = {
+	.s_ctrl = vivid_loop_out_s_ctrl,
+};
+
+static const struct v4l2_ctrl_config vivid_ctrl_loop_video = {
+	.ops = &vivid_loop_out_ctrl_ops,
+	.id = VIVID_CID_LOOP_VIDEO,
+	.name = "Loop Video",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.max = 1,
+	.step = 1,
+};
+
+
+static const struct v4l2_ctrl_config vivid_ctrl_class = {
+	.ops = &vivid_user_gen_ctrl_ops,
+	.flags = V4L2_CTRL_FLAG_READ_ONLY | V4L2_CTRL_FLAG_WRITE_ONLY,
+	.id = VIVID_CID_VIVID_CLASS,
+	.name = "Vivid Controls",
+	.type = V4L2_CTRL_TYPE_CTRL_CLASS,
+};
+
+int vivid_create_controls(struct vivid_dev *dev, bool show_ccs_cap,
+		bool show_ccs_out, bool no_error_inj,
+		bool has_sdtv, bool has_hdmi)
+{
+	struct v4l2_ctrl_handler *hdl_user_gen = &dev->ctrl_hdl_user_gen;
+	struct v4l2_ctrl_handler *hdl_user_vid = &dev->ctrl_hdl_user_vid;
+	struct v4l2_ctrl_handler *hdl_user_aud = &dev->ctrl_hdl_user_aud;
+	struct v4l2_ctrl_handler *hdl_streaming = &dev->ctrl_hdl_streaming;
+	struct v4l2_ctrl_handler *hdl_sdtv_cap = &dev->ctrl_hdl_sdtv_cap;
+	struct v4l2_ctrl_handler *hdl_loop_out = &dev->ctrl_hdl_loop_out;
+	struct v4l2_ctrl_handler *hdl_vid_cap = &dev->ctrl_hdl_vid_cap;
+	struct v4l2_ctrl_handler *hdl_vid_out = &dev->ctrl_hdl_vid_out;
+	struct v4l2_ctrl_handler *hdl_vbi_cap = &dev->ctrl_hdl_vbi_cap;
+	struct v4l2_ctrl_handler *hdl_vbi_out = &dev->ctrl_hdl_vbi_out;
+	struct v4l2_ctrl_handler *hdl_radio_rx = &dev->ctrl_hdl_radio_rx;
+	struct v4l2_ctrl_handler *hdl_radio_tx = &dev->ctrl_hdl_radio_tx;
+	struct v4l2_ctrl_handler *hdl_sdr_cap = &dev->ctrl_hdl_sdr_cap;
+	struct v4l2_ctrl_config vivid_ctrl_dv_timings = {
+		.ops = &vivid_vid_cap_ctrl_ops,
+		.id = VIVID_CID_DV_TIMINGS,
+		.name = "DV Timings",
+		.type = V4L2_CTRL_TYPE_MENU,
+	};
+	int i;
+
+	v4l2_ctrl_handler_init(hdl_user_gen, 10);
+	v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_user_vid, 9);
+	v4l2_ctrl_new_custom(hdl_user_vid, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_user_aud, 2);
+	v4l2_ctrl_new_custom(hdl_user_aud, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_streaming, 8);
+	v4l2_ctrl_new_custom(hdl_streaming, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_sdtv_cap, 2);
+	v4l2_ctrl_new_custom(hdl_sdtv_cap, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_loop_out, 1);
+	v4l2_ctrl_new_custom(hdl_loop_out, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_vid_cap, 55);
+	v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_vid_out, 26);
+	v4l2_ctrl_new_custom(hdl_vid_out, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_vbi_cap, 21);
+	v4l2_ctrl_new_custom(hdl_vbi_cap, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_vbi_out, 19);
+	v4l2_ctrl_new_custom(hdl_vbi_out, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_radio_rx, 17);
+	v4l2_ctrl_new_custom(hdl_radio_rx, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_radio_tx, 17);
+	v4l2_ctrl_new_custom(hdl_radio_tx, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_sdr_cap, 18);
+	v4l2_ctrl_new_custom(hdl_sdr_cap, &vivid_ctrl_class, NULL);
+
+	/* User Controls */
+	dev->volume = v4l2_ctrl_new_std(hdl_user_aud, NULL,
+		V4L2_CID_AUDIO_VOLUME, 0, 255, 1, 200);
+	dev->mute = v4l2_ctrl_new_std(hdl_user_aud, NULL,
+		V4L2_CID_AUDIO_MUTE, 0, 1, 1, 0);
+	if (dev->has_vid_cap) {
+		dev->brightness = v4l2_ctrl_new_std(hdl_user_vid, &vivid_user_vid_ctrl_ops,
+			V4L2_CID_BRIGHTNESS, 0, 255, 1, 128);
+		for (i = 0; i < MAX_INPUTS; i++)
+			dev->input_brightness[i] = 128;
+		dev->contrast = v4l2_ctrl_new_std(hdl_user_vid, &vivid_user_vid_ctrl_ops,
+			V4L2_CID_CONTRAST, 0, 255, 1, 128);
+		dev->saturation = v4l2_ctrl_new_std(hdl_user_vid, &vivid_user_vid_ctrl_ops,
+			V4L2_CID_SATURATION, 0, 255, 1, 128);
+		dev->hue = v4l2_ctrl_new_std(hdl_user_vid, &vivid_user_vid_ctrl_ops,
+			V4L2_CID_HUE, -128, 128, 1, 0);
+		v4l2_ctrl_new_std(hdl_user_vid, &vivid_user_vid_ctrl_ops,
+			V4L2_CID_HFLIP, 0, 1, 1, 0);
+		v4l2_ctrl_new_std(hdl_user_vid, &vivid_user_vid_ctrl_ops,
+			V4L2_CID_VFLIP, 0, 1, 1, 0);
+		dev->autogain = v4l2_ctrl_new_std(hdl_user_vid, &vivid_user_vid_ctrl_ops,
+			V4L2_CID_AUTOGAIN, 0, 1, 1, 1);
+		dev->gain = v4l2_ctrl_new_std(hdl_user_vid, &vivid_user_vid_ctrl_ops,
+			V4L2_CID_GAIN, 0, 255, 1, 100);
+		dev->alpha = v4l2_ctrl_new_std(hdl_user_vid, &vivid_user_vid_ctrl_ops,
+			V4L2_CID_ALPHA_COMPONENT, 0, 255, 1, 0);
+	}
+	dev->button = v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_button, NULL);
+	dev->int32 = v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_int32, NULL);
+	dev->int64 = v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_int64, NULL);
+	dev->boolean = v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_boolean, NULL);
+	dev->menu = v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_menu, NULL);
+	dev->string = v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_string, NULL);
+	dev->bitmask = v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_bitmask, NULL);
+	dev->int_menu = v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_int_menu, NULL);
+
+	if (dev->has_vid_cap) {
+		/* Image Processing Controls */
+		struct v4l2_ctrl_config vivid_ctrl_test_pattern = {
+			.ops = &vivid_vid_cap_ctrl_ops,
+			.id = VIVID_CID_TEST_PATTERN,
+			.name = "Test Pattern",
+			.type = V4L2_CTRL_TYPE_MENU,
+			.max = TPG_PAT_NOISE,
+			.qmenu = tpg_pattern_strings,
+		};
+
+		dev->test_pattern = v4l2_ctrl_new_custom(hdl_vid_cap,
+				&vivid_ctrl_test_pattern, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_perc_fill, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_hor_movement, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_vert_movement, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_osd_mode, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_show_border, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_show_square, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_hflip, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_vflip, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_insert_sav, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_insert_eav, NULL);
+		if (show_ccs_cap) {
+			dev->ctrl_has_crop_cap = v4l2_ctrl_new_custom(hdl_vid_cap,
+				&vivid_ctrl_has_crop_cap, NULL);
+			dev->ctrl_has_compose_cap = v4l2_ctrl_new_custom(hdl_vid_cap,
+				&vivid_ctrl_has_compose_cap, NULL);
+			dev->ctrl_has_scaler_cap = v4l2_ctrl_new_custom(hdl_vid_cap,
+				&vivid_ctrl_has_scaler_cap, NULL);
+		}
+
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_tstamp_src, NULL);
+		dev->colorspace = v4l2_ctrl_new_custom(hdl_vid_cap,
+			&vivid_ctrl_colorspace, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_alpha_mode, NULL);
+	}
+
+	if (dev->has_vid_out && show_ccs_out) {
+		dev->ctrl_has_crop_out = v4l2_ctrl_new_custom(hdl_vid_out,
+			&vivid_ctrl_has_crop_out, NULL);
+		dev->ctrl_has_compose_out = v4l2_ctrl_new_custom(hdl_vid_out,
+			&vivid_ctrl_has_compose_out, NULL);
+		dev->ctrl_has_scaler_out = v4l2_ctrl_new_custom(hdl_vid_out,
+			&vivid_ctrl_has_scaler_out, NULL);
+	}
+
+	/*
+	 * Testing this driver with v4l2-compliance will trigger the error
+	 * injection controls, and after that nothing will work as expected.
+	 * So we have a module option to drop these error injecting controls
+	 * allowing us to run v4l2_compliance again.
+	 */
+	if (!no_error_inj) {
+		v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_disconnect, NULL);
+		v4l2_ctrl_new_custom(hdl_streaming, &vivid_ctrl_dqbuf_error, NULL);
+		v4l2_ctrl_new_custom(hdl_streaming, &vivid_ctrl_perc_dropped, NULL);
+		v4l2_ctrl_new_custom(hdl_streaming, &vivid_ctrl_queue_setup_error, NULL);
+		v4l2_ctrl_new_custom(hdl_streaming, &vivid_ctrl_buf_prepare_error, NULL);
+		v4l2_ctrl_new_custom(hdl_streaming, &vivid_ctrl_start_streaming_error, NULL);
+		v4l2_ctrl_new_custom(hdl_streaming, &vivid_ctrl_queue_error, NULL);
+		v4l2_ctrl_new_custom(hdl_streaming, &vivid_ctrl_seq_wrap, NULL);
+		v4l2_ctrl_new_custom(hdl_streaming, &vivid_ctrl_time_wrap, NULL);
+	}
+
+	if (has_sdtv && (dev->has_vid_cap || dev->has_vbi_cap)) {
+		if (dev->has_vid_cap)
+			v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_std_aspect_ratio, NULL);
+		dev->ctrl_std_signal_mode = v4l2_ctrl_new_custom(hdl_sdtv_cap,
+			&vivid_ctrl_std_signal_mode, NULL);
+		dev->ctrl_standard = v4l2_ctrl_new_custom(hdl_sdtv_cap,
+			&vivid_ctrl_standard, NULL);
+		if (dev->ctrl_std_signal_mode)
+			v4l2_ctrl_cluster(2, &dev->ctrl_std_signal_mode);
+		if (dev->has_raw_vbi_cap)
+			v4l2_ctrl_new_custom(hdl_vbi_cap, &vivid_ctrl_vbi_cap_interlaced, NULL);
+	}
+
+	if (has_hdmi && dev->has_vid_cap) {
+		dev->ctrl_dv_timings_signal_mode = v4l2_ctrl_new_custom(hdl_vid_cap,
+					&vivid_ctrl_dv_timings_signal_mode, NULL);
+
+		vivid_ctrl_dv_timings.max = dev->query_dv_timings_size - 1;
+		vivid_ctrl_dv_timings.qmenu =
+			(const char * const *)dev->query_dv_timings_qmenu;
+		dev->ctrl_dv_timings = v4l2_ctrl_new_custom(hdl_vid_cap,
+			&vivid_ctrl_dv_timings, NULL);
+		if (dev->ctrl_dv_timings_signal_mode)
+			v4l2_ctrl_cluster(2, &dev->ctrl_dv_timings_signal_mode);
+
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_dv_timings_aspect_ratio, NULL);
+		v4l2_ctrl_new_custom(hdl_vid_cap, &vivid_ctrl_max_edid_blocks, NULL);
+		dev->real_rgb_range_cap = v4l2_ctrl_new_custom(hdl_vid_cap,
+			&vivid_ctrl_limited_rgb_range, NULL);
+		dev->rgb_range_cap = v4l2_ctrl_new_std_menu(hdl_vid_cap,
+			&vivid_vid_cap_ctrl_ops,
+			V4L2_CID_DV_RX_RGB_RANGE, V4L2_DV_RGB_RANGE_FULL,
+			0, V4L2_DV_RGB_RANGE_AUTO);
+	}
+	if (has_hdmi && dev->has_vid_out) {
+		/*
+		 * We aren't doing anything with this at the moment, but
+		 * HDMI outputs typically have this controls.
+		 */
+		dev->ctrl_tx_rgb_range = v4l2_ctrl_new_std_menu(hdl_vid_out, NULL,
+			V4L2_CID_DV_TX_RGB_RANGE, V4L2_DV_RGB_RANGE_FULL,
+			0, V4L2_DV_RGB_RANGE_AUTO);
+		dev->ctrl_tx_mode = v4l2_ctrl_new_std_menu(hdl_vid_out, NULL,
+			V4L2_CID_DV_TX_MODE, V4L2_DV_TX_MODE_HDMI,
+			0, V4L2_DV_TX_MODE_HDMI);
+	}
+	if ((dev->has_vid_cap && dev->has_vid_out) ||
+	    (dev->has_vbi_cap && dev->has_vbi_out))
+		v4l2_ctrl_new_custom(hdl_loop_out, &vivid_ctrl_loop_video, NULL);
+
+	if (dev->has_fb)
+		v4l2_ctrl_new_custom(hdl_user_gen, &vivid_ctrl_clear_fb, NULL);
+
+	if (dev->has_radio_rx) {
+		v4l2_ctrl_new_custom(hdl_radio_rx, &vivid_ctrl_radio_hw_seek_mode, NULL);
+		v4l2_ctrl_new_custom(hdl_radio_rx, &vivid_ctrl_radio_hw_seek_prog_lim, NULL);
+		v4l2_ctrl_new_custom(hdl_radio_rx, &vivid_ctrl_radio_rx_rds_blockio, NULL);
+		v4l2_ctrl_new_custom(hdl_radio_rx, &vivid_ctrl_radio_rx_rds_rbds, NULL);
+		v4l2_ctrl_new_std(hdl_radio_rx, &vivid_radio_rx_ctrl_ops,
+			V4L2_CID_RDS_RECEPTION, 0, 1, 1, 1);
+		dev->radio_rx_rds_pty = v4l2_ctrl_new_std(hdl_radio_rx,
+			&vivid_radio_rx_ctrl_ops,
+			V4L2_CID_RDS_RX_PTY, 0, 31, 1, 0);
+		dev->radio_rx_rds_psname = v4l2_ctrl_new_std(hdl_radio_rx,
+			&vivid_radio_rx_ctrl_ops,
+			V4L2_CID_RDS_RX_PS_NAME, 0, 8, 8, 0);
+		dev->radio_rx_rds_radiotext = v4l2_ctrl_new_std(hdl_radio_rx,
+			&vivid_radio_rx_ctrl_ops,
+			V4L2_CID_RDS_RX_RADIO_TEXT, 0, 64, 64, 0);
+		dev->radio_rx_rds_ta = v4l2_ctrl_new_std(hdl_radio_rx,
+			&vivid_radio_rx_ctrl_ops,
+			V4L2_CID_RDS_RX_TRAFFIC_ANNOUNCEMENT, 0, 1, 1, 0);
+		dev->radio_rx_rds_tp = v4l2_ctrl_new_std(hdl_radio_rx,
+			&vivid_radio_rx_ctrl_ops,
+			V4L2_CID_RDS_RX_TRAFFIC_PROGRAM, 0, 1, 1, 0);
+		dev->radio_rx_rds_ms = v4l2_ctrl_new_std(hdl_radio_rx,
+			&vivid_radio_rx_ctrl_ops,
+			V4L2_CID_RDS_RX_MUSIC_SPEECH, 0, 1, 1, 1);
+	}
+	if (dev->has_radio_tx) {
+		v4l2_ctrl_new_custom(hdl_radio_tx,
+			&vivid_ctrl_radio_tx_rds_blockio, NULL);
+		dev->radio_tx_rds_pi = v4l2_ctrl_new_std(hdl_radio_tx,
+			&vivid_radio_tx_ctrl_ops,
+			V4L2_CID_RDS_TX_PI, 0, 0xffff, 1, 0x8088);
+		dev->radio_tx_rds_pty = v4l2_ctrl_new_std(hdl_radio_tx,
+			&vivid_radio_tx_ctrl_ops,
+			V4L2_CID_RDS_TX_PTY, 0, 31, 1, 3);
+		dev->radio_tx_rds_psname = v4l2_ctrl_new_std(hdl_radio_tx,
+			&vivid_radio_tx_ctrl_ops,
+			V4L2_CID_RDS_TX_PS_NAME, 0, 8, 8, 0);
+		if (dev->radio_tx_rds_psname)
+			v4l2_ctrl_s_ctrl_string(dev->radio_tx_rds_psname, "VIVID-TX");
+		dev->radio_tx_rds_radiotext = v4l2_ctrl_new_std(hdl_radio_tx,
+			&vivid_radio_tx_ctrl_ops,
+			V4L2_CID_RDS_TX_RADIO_TEXT, 0, 64 * 2, 64, 0);
+		if (dev->radio_tx_rds_radiotext)
+			v4l2_ctrl_s_ctrl_string(dev->radio_tx_rds_radiotext,
+			       "This is a VIVID default Radio Text template text, change at will");
+		dev->radio_tx_rds_mono_stereo = v4l2_ctrl_new_std(hdl_radio_tx,
+			&vivid_radio_tx_ctrl_ops,
+			V4L2_CID_RDS_TX_MONO_STEREO, 0, 1, 1, 1);
+		dev->radio_tx_rds_art_head = v4l2_ctrl_new_std(hdl_radio_tx,
+			&vivid_radio_tx_ctrl_ops,
+			V4L2_CID_RDS_TX_ARTIFICIAL_HEAD, 0, 1, 1, 0);
+		dev->radio_tx_rds_compressed = v4l2_ctrl_new_std(hdl_radio_tx,
+			&vivid_radio_tx_ctrl_ops,
+			V4L2_CID_RDS_TX_COMPRESSED, 0, 1, 1, 0);
+		dev->radio_tx_rds_dyn_pty = v4l2_ctrl_new_std(hdl_radio_tx,
+			&vivid_radio_tx_ctrl_ops,
+			V4L2_CID_RDS_TX_DYNAMIC_PTY, 0, 1, 1, 0);
+		dev->radio_tx_rds_ta = v4l2_ctrl_new_std(hdl_radio_tx,
+			&vivid_radio_tx_ctrl_ops,
+			V4L2_CID_RDS_TX_TRAFFIC_ANNOUNCEMENT, 0, 1, 1, 0);
+		dev->radio_tx_rds_tp = v4l2_ctrl_new_std(hdl_radio_tx,
+			&vivid_radio_tx_ctrl_ops,
+			V4L2_CID_RDS_TX_TRAFFIC_PROGRAM, 0, 1, 1, 1);
+		dev->radio_tx_rds_ms = v4l2_ctrl_new_std(hdl_radio_tx,
+			&vivid_radio_tx_ctrl_ops,
+			V4L2_CID_RDS_TX_MUSIC_SPEECH, 0, 1, 1, 1);
+	}
+	if (hdl_user_gen->error)
+		return hdl_user_gen->error;
+	if (hdl_user_vid->error)
+		return hdl_user_vid->error;
+	if (hdl_user_aud->error)
+		return hdl_user_aud->error;
+	if (hdl_streaming->error)
+		return hdl_streaming->error;
+	if (hdl_sdr_cap->error)
+		return hdl_sdr_cap->error;
+	if (hdl_loop_out->error)
+		return hdl_loop_out->error;
+
+	if (dev->autogain)
+		v4l2_ctrl_auto_cluster(2, &dev->autogain, 0, true);
+
+	if (dev->has_vid_cap) {
+		v4l2_ctrl_add_handler(hdl_vid_cap, hdl_user_gen, NULL);
+		v4l2_ctrl_add_handler(hdl_vid_cap, hdl_user_vid, NULL);
+		v4l2_ctrl_add_handler(hdl_vid_cap, hdl_user_aud, NULL);
+		v4l2_ctrl_add_handler(hdl_vid_cap, hdl_streaming, NULL);
+		v4l2_ctrl_add_handler(hdl_vid_cap, hdl_sdtv_cap, NULL);
+		if (hdl_vid_cap->error)
+			return hdl_vid_cap->error;
+		dev->vid_cap_dev.ctrl_handler = hdl_vid_cap;
+	}
+	if (dev->has_vid_out) {
+		v4l2_ctrl_add_handler(hdl_vid_out, hdl_user_gen, NULL);
+		v4l2_ctrl_add_handler(hdl_vid_out, hdl_user_aud, NULL);
+		v4l2_ctrl_add_handler(hdl_vid_out, hdl_streaming, NULL);
+		v4l2_ctrl_add_handler(hdl_vid_out, hdl_loop_out, NULL);
+		if (hdl_vid_out->error)
+			return hdl_vid_out->error;
+		dev->vid_out_dev.ctrl_handler = hdl_vid_out;
+	}
+	if (dev->has_vbi_cap) {
+		v4l2_ctrl_add_handler(hdl_vbi_cap, hdl_user_gen, NULL);
+		v4l2_ctrl_add_handler(hdl_vbi_cap, hdl_streaming, NULL);
+		v4l2_ctrl_add_handler(hdl_vbi_cap, hdl_sdtv_cap, NULL);
+		if (hdl_vbi_cap->error)
+			return hdl_vbi_cap->error;
+		dev->vbi_cap_dev.ctrl_handler = hdl_vbi_cap;
+	}
+	if (dev->has_vbi_out) {
+		v4l2_ctrl_add_handler(hdl_vbi_out, hdl_user_gen, NULL);
+		v4l2_ctrl_add_handler(hdl_vbi_out, hdl_streaming, NULL);
+		v4l2_ctrl_add_handler(hdl_vbi_out, hdl_loop_out, NULL);
+		if (hdl_vbi_out->error)
+			return hdl_vbi_out->error;
+		dev->vbi_out_dev.ctrl_handler = hdl_vbi_out;
+	}
+	if (dev->has_radio_rx) {
+		v4l2_ctrl_add_handler(hdl_radio_rx, hdl_user_gen, NULL);
+		v4l2_ctrl_add_handler(hdl_radio_rx, hdl_user_aud, NULL);
+		if (hdl_radio_rx->error)
+			return hdl_radio_rx->error;
+		dev->radio_rx_dev.ctrl_handler = hdl_radio_rx;
+	}
+	if (dev->has_radio_tx) {
+		v4l2_ctrl_add_handler(hdl_radio_tx, hdl_user_gen, NULL);
+		v4l2_ctrl_add_handler(hdl_radio_tx, hdl_user_aud, NULL);
+		if (hdl_radio_tx->error)
+			return hdl_radio_tx->error;
+		dev->radio_tx_dev.ctrl_handler = hdl_radio_tx;
+	}
+	if (dev->has_sdr_cap) {
+		v4l2_ctrl_add_handler(hdl_sdr_cap, hdl_user_gen, NULL);
+		v4l2_ctrl_add_handler(hdl_sdr_cap, hdl_streaming, NULL);
+		if (hdl_sdr_cap->error)
+			return hdl_sdr_cap->error;
+		dev->sdr_cap_dev.ctrl_handler = hdl_sdr_cap;
+	}
+	return 0;
+}
+
+void vivid_free_controls(struct vivid_dev *dev)
+{
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_vid_cap);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_vid_out);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_vbi_cap);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_vbi_out);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_radio_rx);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_radio_tx);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_sdr_cap);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_user_gen);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_user_vid);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_user_aud);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_streaming);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_sdtv_cap);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_loop_out);
+}
diff --git a/drivers/media/platform/vivid/vivid-ctrls.h b/drivers/media/platform/vivid/vivid-ctrls.h
new file mode 100644
index 000000000000..9bcca9d56359
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-ctrls.h
@@ -0,0 +1,34 @@
+/*
+ * vivid-ctrls.h - control support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_CTRLS_H_
+#define _VIVID_CTRLS_H_
+
+enum vivid_hw_seek_modes {
+	VIVID_HW_SEEK_BOUNDED,
+	VIVID_HW_SEEK_WRAP,
+	VIVID_HW_SEEK_BOTH,
+};
+
+int vivid_create_controls(struct vivid_dev *dev, bool show_ccs_cap,
+		bool show_ccs_out, bool no_error_inj,
+		bool has_sdtv, bool has_hdmi);
+void vivid_free_controls(struct vivid_dev *dev);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.c b/drivers/media/platform/vivid/vivid-kthread-cap.c
new file mode 100644
index 000000000000..39a67cfae120
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-kthread-cap.c
@@ -0,0 +1,886 @@
+/*
+ * vivid-kthread-cap.h - video/vbi capture thread support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/font.h>
+#include <linux/mutex.h>
+#include <linux/videodev2.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/random.h>
+#include <linux/v4l2-dv-timings.h>
+#include <asm/div64.h>
+#include <media/videobuf2-vmalloc.h>
+#include <media/v4l2-dv-timings.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-event.h>
+
+#include "vivid-core.h"
+#include "vivid-vid-common.h"
+#include "vivid-vid-cap.h"
+#include "vivid-vid-out.h"
+#include "vivid-radio-common.h"
+#include "vivid-radio-rx.h"
+#include "vivid-radio-tx.h"
+#include "vivid-sdr-cap.h"
+#include "vivid-vbi-cap.h"
+#include "vivid-vbi-out.h"
+#include "vivid-osd.h"
+#include "vivid-ctrls.h"
+#include "vivid-kthread-cap.h"
+
+static inline v4l2_std_id vivid_get_std_cap(const struct vivid_dev *dev)
+{
+	if (vivid_is_sdtv_cap(dev))
+		return dev->std_cap;
+	return 0;
+}
+
+static void copy_pix(struct vivid_dev *dev, int win_y, int win_x,
+			u16 *cap, const u16 *osd)
+{
+	u16 out;
+	int left = dev->overlay_out_left;
+	int top = dev->overlay_out_top;
+	int fb_x = win_x + left;
+	int fb_y = win_y + top;
+	int i;
+
+	out = *cap;
+	*cap = *osd;
+	if (dev->bitmap_out) {
+		const u8 *p = dev->bitmap_out;
+		unsigned stride = (dev->compose_out.width + 7) / 8;
+
+		win_x -= dev->compose_out.left;
+		win_y -= dev->compose_out.top;
+		if (!(p[stride * win_y + win_x / 8] & (1 << (win_x & 7))))
+			return;
+	}
+
+	for (i = 0; i < dev->clipcount_out; i++) {
+		struct v4l2_rect *r = &dev->clips_out[i].c;
+
+		if (fb_y >= r->top && fb_y < r->top + r->height &&
+		    fb_x >= r->left && fb_x < r->left + r->width)
+			return;
+	}
+	if ((dev->fbuf_out_flags & V4L2_FBUF_FLAG_CHROMAKEY) &&
+	    *osd != dev->chromakey_out)
+		return;
+	if ((dev->fbuf_out_flags & V4L2_FBUF_FLAG_SRC_CHROMAKEY) &&
+	    out == dev->chromakey_out)
+		return;
+	if (dev->fmt_cap->alpha_mask) {
+		if ((dev->fbuf_out_flags & V4L2_FBUF_FLAG_GLOBAL_ALPHA) &&
+		    dev->global_alpha_out)
+			return;
+		if ((dev->fbuf_out_flags & V4L2_FBUF_FLAG_LOCAL_ALPHA) &&
+		    *cap & dev->fmt_cap->alpha_mask)
+			return;
+		if ((dev->fbuf_out_flags & V4L2_FBUF_FLAG_LOCAL_INV_ALPHA) &&
+		    !(*cap & dev->fmt_cap->alpha_mask))
+			return;
+	}
+	*cap = out;
+}
+
+static void blend_line(struct vivid_dev *dev, unsigned y_offset, unsigned x_offset,
+		u8 *vcapbuf, const u8 *vosdbuf,
+		unsigned width, unsigned pixsize)
+{
+	unsigned x;
+
+	for (x = 0; x < width; x++, vcapbuf += pixsize, vosdbuf += pixsize) {
+		copy_pix(dev, y_offset, x_offset + x,
+			 (u16 *)vcapbuf, (const u16 *)vosdbuf);
+	}
+}
+
+static void scale_line(const u8 *src, u8 *dst, unsigned srcw, unsigned dstw, unsigned twopixsize)
+{
+	/* Coarse scaling with Bresenham */
+	unsigned int_part;
+	unsigned fract_part;
+	unsigned src_x = 0;
+	unsigned error = 0;
+	unsigned x;
+
+	/*
+	 * We always combine two pixels to prevent color bleed in the packed
+	 * yuv case.
+	 */
+	srcw /= 2;
+	dstw /= 2;
+	int_part = srcw / dstw;
+	fract_part = srcw % dstw;
+	for (x = 0; x < dstw; x++, dst += twopixsize) {
+		memcpy(dst, src + src_x * twopixsize, twopixsize);
+		src_x += int_part;
+		error += fract_part;
+		if (error >= dstw) {
+			error -= dstw;
+			src_x++;
+		}
+	}
+}
+
+/*
+ * Precalculate the rectangles needed to perform video looping:
+ *
+ * The nominal pipeline is that the video output buffer is cropped by
+ * crop_out, scaled to compose_out, overlaid with the output overlay,
+ * cropped on the capture side by crop_cap and scaled again to the video
+ * capture buffer using compose_cap.
+ *
+ * To keep things efficient we calculate the intersection of compose_out
+ * and crop_cap (since that's the only part of the video that will
+ * actually end up in the capture buffer), determine which part of the
+ * video output buffer that is and which part of the video capture buffer
+ * so we can scale the video straight from the output buffer to the capture
+ * buffer without any intermediate steps.
+ *
+ * If we need to deal with an output overlay, then there is no choice and
+ * that intermediate step still has to be taken. For the output overlay
+ * support we calculate the intersection of the framebuffer and the overlay
+ * window (which may be partially or wholly outside of the framebuffer
+ * itself) and the intersection of that with loop_vid_copy (i.e. the part of
+ * the actual looped video that will be overlaid). The result is calculated
+ * both in framebuffer coordinates (loop_fb_copy) and compose_out coordinates
+ * (loop_vid_overlay). Finally calculate the part of the capture buffer that
+ * will receive that overlaid video.
+ */
+static void vivid_precalc_copy_rects(struct vivid_dev *dev)
+{
+	/* Framebuffer rectangle */
+	struct v4l2_rect r_fb = {
+		0, 0, dev->display_width, dev->display_height
+	};
+	/* Overlay window rectangle in framebuffer coordinates */
+	struct v4l2_rect r_overlay = {
+		dev->overlay_out_left, dev->overlay_out_top,
+		dev->compose_out.width, dev->compose_out.height
+	};
+
+	dev->loop_vid_copy = rect_intersect(&dev->crop_cap, &dev->compose_out);
+
+	dev->loop_vid_out = dev->loop_vid_copy;
+	rect_scale(&dev->loop_vid_out, &dev->compose_out, &dev->crop_out);
+	dev->loop_vid_out.left += dev->crop_out.left;
+	dev->loop_vid_out.top += dev->crop_out.top;
+
+	dev->loop_vid_cap = dev->loop_vid_copy;
+	rect_scale(&dev->loop_vid_cap, &dev->crop_cap, &dev->compose_cap);
+
+	dprintk(dev, 1,
+		"loop_vid_copy: %dx%d@%dx%d loop_vid_out: %dx%d@%dx%d loop_vid_cap: %dx%d@%dx%d\n",
+		dev->loop_vid_copy.width, dev->loop_vid_copy.height,
+		dev->loop_vid_copy.left, dev->loop_vid_copy.top,
+		dev->loop_vid_out.width, dev->loop_vid_out.height,
+		dev->loop_vid_out.left, dev->loop_vid_out.top,
+		dev->loop_vid_cap.width, dev->loop_vid_cap.height,
+		dev->loop_vid_cap.left, dev->loop_vid_cap.top);
+
+	r_overlay = rect_intersect(&r_fb, &r_overlay);
+
+	/* shift r_overlay to the same origin as compose_out */
+	r_overlay.left += dev->compose_out.left - dev->overlay_out_left;
+	r_overlay.top += dev->compose_out.top - dev->overlay_out_top;
+
+	dev->loop_vid_overlay = rect_intersect(&r_overlay, &dev->loop_vid_copy);
+	dev->loop_fb_copy = dev->loop_vid_overlay;
+
+	/* shift dev->loop_fb_copy back again to the fb origin */
+	dev->loop_fb_copy.left -= dev->compose_out.left - dev->overlay_out_left;
+	dev->loop_fb_copy.top -= dev->compose_out.top - dev->overlay_out_top;
+
+	dev->loop_vid_overlay_cap = dev->loop_vid_overlay;
+	rect_scale(&dev->loop_vid_overlay_cap, &dev->crop_cap, &dev->compose_cap);
+
+	dprintk(dev, 1,
+		"loop_fb_copy: %dx%d@%dx%d loop_vid_overlay: %dx%d@%dx%d loop_vid_overlay_cap: %dx%d@%dx%d\n",
+		dev->loop_fb_copy.width, dev->loop_fb_copy.height,
+		dev->loop_fb_copy.left, dev->loop_fb_copy.top,
+		dev->loop_vid_overlay.width, dev->loop_vid_overlay.height,
+		dev->loop_vid_overlay.left, dev->loop_vid_overlay.top,
+		dev->loop_vid_overlay_cap.width, dev->loop_vid_overlay_cap.height,
+		dev->loop_vid_overlay_cap.left, dev->loop_vid_overlay_cap.top);
+}
+
+static int vivid_copy_buffer(struct vivid_dev *dev, unsigned p, u8 *vcapbuf,
+		struct vivid_buffer *vid_cap_buf)
+{
+	bool blank = dev->must_blank[vid_cap_buf->vb.v4l2_buf.index];
+	struct tpg_data *tpg = &dev->tpg;
+	struct vivid_buffer *vid_out_buf = NULL;
+	unsigned pixsize = tpg_g_twopixelsize(tpg, p) / 2;
+	unsigned img_width = dev->compose_cap.width;
+	unsigned img_height = dev->compose_cap.height;
+	unsigned stride_cap = tpg->bytesperline[p];
+	unsigned stride_out = dev->bytesperline_out[p];
+	unsigned stride_osd = dev->display_byte_stride;
+	unsigned hmax = (img_height * tpg->perc_fill) / 100;
+	u8 *voutbuf;
+	u8 *vosdbuf = NULL;
+	unsigned y;
+	bool blend = dev->bitmap_out || dev->clipcount_out || dev->fbuf_out_flags;
+	/* Coarse scaling with Bresenham */
+	unsigned vid_out_int_part;
+	unsigned vid_out_fract_part;
+	unsigned vid_out_y = 0;
+	unsigned vid_out_error = 0;
+	unsigned vid_overlay_int_part = 0;
+	unsigned vid_overlay_fract_part = 0;
+	unsigned vid_overlay_y = 0;
+	unsigned vid_overlay_error = 0;
+	unsigned vid_cap_right;
+	bool quick;
+
+	vid_out_int_part = dev->loop_vid_out.height / dev->loop_vid_cap.height;
+	vid_out_fract_part = dev->loop_vid_out.height % dev->loop_vid_cap.height;
+
+	if (!list_empty(&dev->vid_out_active))
+		vid_out_buf = list_entry(dev->vid_out_active.next,
+					 struct vivid_buffer, list);
+	if (vid_out_buf == NULL)
+		return -ENODATA;
+
+	vid_cap_buf->vb.v4l2_buf.field = vid_out_buf->vb.v4l2_buf.field;
+
+	voutbuf = vb2_plane_vaddr(&vid_out_buf->vb, p) +
+				  vid_out_buf->vb.v4l2_planes[p].data_offset;
+	voutbuf += dev->loop_vid_out.left * pixsize + dev->loop_vid_out.top * stride_out;
+	vcapbuf += dev->compose_cap.left * pixsize + dev->compose_cap.top * stride_cap;
+
+	if (dev->loop_vid_copy.width == 0 || dev->loop_vid_copy.height == 0) {
+		/*
+		 * If there is nothing to copy, then just fill the capture window
+		 * with black.
+		 */
+		for (y = 0; y < hmax; y++, vcapbuf += stride_cap)
+			memcpy(vcapbuf, tpg->black_line[p], img_width * pixsize);
+		return 0;
+	}
+
+	if (dev->overlay_out_enabled &&
+	    dev->loop_vid_overlay.width && dev->loop_vid_overlay.height) {
+		vosdbuf = dev->video_vbase;
+		vosdbuf += dev->loop_fb_copy.left * pixsize +
+			   dev->loop_fb_copy.top * stride_osd;
+		vid_overlay_int_part = dev->loop_vid_overlay.height /
+				       dev->loop_vid_overlay_cap.height;
+		vid_overlay_fract_part = dev->loop_vid_overlay.height %
+					 dev->loop_vid_overlay_cap.height;
+	}
+
+	vid_cap_right = dev->loop_vid_cap.left + dev->loop_vid_cap.width;
+	/* quick is true if no video scaling is needed */
+	quick = dev->loop_vid_out.width == dev->loop_vid_cap.width;
+
+	dev->cur_scaled_line = dev->loop_vid_out.height;
+	for (y = 0; y < hmax; y++, vcapbuf += stride_cap) {
+		/* osdline is true if this line requires overlay blending */
+		bool osdline = vosdbuf && y >= dev->loop_vid_overlay_cap.top &&
+			  y < dev->loop_vid_overlay_cap.top + dev->loop_vid_overlay_cap.height;
+
+		/*
+		 * If this line of the capture buffer doesn't get any video, then
+		 * just fill with black.
+		 */
+		if (y < dev->loop_vid_cap.top ||
+		    y >= dev->loop_vid_cap.top + dev->loop_vid_cap.height) {
+			memcpy(vcapbuf, tpg->black_line[p], img_width * pixsize);
+			continue;
+		}
+
+		/* fill the left border with black */
+		if (dev->loop_vid_cap.left)
+			memcpy(vcapbuf, tpg->black_line[p], dev->loop_vid_cap.left * pixsize);
+
+		/* fill the right border with black */
+		if (vid_cap_right < img_width)
+			memcpy(vcapbuf + vid_cap_right * pixsize,
+				tpg->black_line[p], (img_width - vid_cap_right) * pixsize);
+
+		if (quick && !osdline) {
+			memcpy(vcapbuf + dev->loop_vid_cap.left * pixsize,
+			       voutbuf + vid_out_y * stride_out,
+			       dev->loop_vid_cap.width * pixsize);
+			goto update_vid_out_y;
+		}
+		if (dev->cur_scaled_line == vid_out_y) {
+			memcpy(vcapbuf + dev->loop_vid_cap.left * pixsize,
+			       dev->scaled_line,
+			       dev->loop_vid_cap.width * pixsize);
+			goto update_vid_out_y;
+		}
+		if (!osdline) {
+			scale_line(voutbuf + vid_out_y * stride_out, dev->scaled_line,
+				dev->loop_vid_out.width, dev->loop_vid_cap.width,
+				tpg_g_twopixelsize(tpg, p));
+		} else {
+			/*
+			 * Offset in bytes within loop_vid_copy to the start of the
+			 * loop_vid_overlay rectangle.
+			 */
+			unsigned offset =
+				(dev->loop_vid_overlay.left - dev->loop_vid_copy.left) * pixsize;
+			u8 *osd = vosdbuf + vid_overlay_y * stride_osd;
+
+			scale_line(voutbuf + vid_out_y * stride_out, dev->blended_line,
+				dev->loop_vid_out.width, dev->loop_vid_copy.width,
+				tpg_g_twopixelsize(tpg, p));
+			if (blend)
+				blend_line(dev, vid_overlay_y + dev->loop_vid_overlay.top,
+					   dev->loop_vid_overlay.left,
+					   dev->blended_line + offset, osd,
+					   dev->loop_vid_overlay.width, pixsize);
+			else
+				memcpy(dev->blended_line + offset,
+				       osd, dev->loop_vid_overlay.width * pixsize);
+			scale_line(dev->blended_line, dev->scaled_line,
+					dev->loop_vid_copy.width, dev->loop_vid_cap.width,
+					tpg_g_twopixelsize(tpg, p));
+		}
+		dev->cur_scaled_line = vid_out_y;
+		memcpy(vcapbuf + dev->loop_vid_cap.left * pixsize,
+		       dev->scaled_line,
+		       dev->loop_vid_cap.width * pixsize);
+
+update_vid_out_y:
+		if (osdline) {
+			vid_overlay_y += vid_overlay_int_part;
+			vid_overlay_error += vid_overlay_fract_part;
+			if (vid_overlay_error >= dev->loop_vid_overlay_cap.height) {
+				vid_overlay_error -= dev->loop_vid_overlay_cap.height;
+				vid_overlay_y++;
+			}
+		}
+		vid_out_y += vid_out_int_part;
+		vid_out_error += vid_out_fract_part;
+		if (vid_out_error >= dev->loop_vid_cap.height) {
+			vid_out_error -= dev->loop_vid_cap.height;
+			vid_out_y++;
+		}
+	}
+
+	if (!blank)
+		return 0;
+	for (; y < img_height; y++, vcapbuf += stride_cap)
+		memcpy(vcapbuf, tpg->contrast_line[p], img_width * pixsize);
+	return 0;
+}
+
+static void vivid_fillbuff(struct vivid_dev *dev, struct vivid_buffer *buf)
+{
+	unsigned factor = V4L2_FIELD_HAS_T_OR_B(dev->field_cap) ? 2 : 1;
+	unsigned line_height = 16 / factor;
+	bool is_tv = vivid_is_sdtv_cap(dev);
+	bool is_60hz = is_tv && (dev->std_cap & V4L2_STD_525_60);
+	unsigned p;
+	int line = 1;
+	u8 *basep[TPG_MAX_PLANES][2];
+	unsigned ms;
+	char str[100];
+	s32 gain;
+	bool is_loop = false;
+
+	if (dev->loop_video && dev->can_loop_video &&
+	    ((vivid_is_svid_cap(dev) && !VIVID_INVALID_SIGNAL(dev->std_signal_mode)) ||
+	     (vivid_is_hdmi_cap(dev) && !VIVID_INVALID_SIGNAL(dev->dv_timings_signal_mode))))
+		is_loop = true;
+
+	buf->vb.v4l2_buf.sequence = dev->vid_cap_seq_count;
+	/*
+	 * Take the timestamp now if the timestamp source is set to
+	 * "Start of Exposure".
+	 */
+	if (dev->tstamp_src_is_soe)
+		v4l2_get_timestamp(&buf->vb.v4l2_buf.timestamp);
+	if (dev->field_cap == V4L2_FIELD_ALTERNATE) {
+		/*
+		 * 60 Hz standards start with the bottom field, 50 Hz standards
+		 * with the top field. So if the 0-based seq_count is even,
+		 * then the field is TOP for 50 Hz and BOTTOM for 60 Hz
+		 * standards.
+		 */
+		buf->vb.v4l2_buf.field = ((dev->vid_cap_seq_count & 1) ^ is_60hz) ?
+			V4L2_FIELD_TOP : V4L2_FIELD_BOTTOM;
+		/*
+		 * The sequence counter counts frames, not fields. So divide
+		 * by two.
+		 */
+		buf->vb.v4l2_buf.sequence /= 2;
+	} else {
+		buf->vb.v4l2_buf.field = dev->field_cap;
+	}
+	tpg_s_field(&dev->tpg, buf->vb.v4l2_buf.field);
+	tpg_s_perc_fill_blank(&dev->tpg, dev->must_blank[buf->vb.v4l2_buf.index]);
+
+	vivid_precalc_copy_rects(dev);
+
+	for (p = 0; p < tpg_g_planes(&dev->tpg); p++) {
+		void *vbuf = vb2_plane_vaddr(&buf->vb, p);
+
+		/*
+		 * The first plane of a multiplanar format has a non-zero
+		 * data_offset. This helps testing whether the application
+		 * correctly supports non-zero data offsets.
+		 */
+		if (dev->fmt_cap->data_offset[p]) {
+			memset(vbuf, dev->fmt_cap->data_offset[p] & 0xff,
+			       dev->fmt_cap->data_offset[p]);
+			vbuf += dev->fmt_cap->data_offset[p];
+		}
+		tpg_calc_text_basep(&dev->tpg, basep, p, vbuf);
+		if (!is_loop || vivid_copy_buffer(dev, p, vbuf, buf))
+			tpg_fillbuffer(&dev->tpg, vivid_get_std_cap(dev), p, vbuf);
+	}
+	dev->must_blank[buf->vb.v4l2_buf.index] = false;
+
+	/* Updates stream time, only update at the start of a new frame. */
+	if (dev->field_cap != V4L2_FIELD_ALTERNATE || (buf->vb.v4l2_buf.sequence & 1) == 0)
+		dev->ms_vid_cap = jiffies_to_msecs(jiffies - dev->jiffies_vid_cap);
+
+	ms = dev->ms_vid_cap;
+	if (dev->osd_mode <= 1) {
+		snprintf(str, sizeof(str), " %02d:%02d:%02d:%03d %u%s",
+				(ms / (60 * 60 * 1000)) % 24,
+				(ms / (60 * 1000)) % 60,
+				(ms / 1000) % 60,
+				ms % 1000,
+				buf->vb.v4l2_buf.sequence,
+				(dev->field_cap == V4L2_FIELD_ALTERNATE) ?
+					(buf->vb.v4l2_buf.field == V4L2_FIELD_TOP ?
+					 " top" : " bottom") : "");
+		tpg_gen_text(&dev->tpg, basep, line++ * line_height, 16, str);
+	}
+	if (dev->osd_mode == 0) {
+		snprintf(str, sizeof(str), " %dx%d, input %d ",
+				dev->src_rect.width, dev->src_rect.height, dev->input);
+		tpg_gen_text(&dev->tpg, basep, line++ * line_height, 16, str);
+
+		gain = v4l2_ctrl_g_ctrl(dev->gain);
+		mutex_lock(dev->ctrl_hdl_user_vid.lock);
+		snprintf(str, sizeof(str),
+			" brightness %3d, contrast %3d, saturation %3d, hue %d ",
+			dev->brightness->cur.val,
+			dev->contrast->cur.val,
+			dev->saturation->cur.val,
+			dev->hue->cur.val);
+		tpg_gen_text(&dev->tpg, basep, line++ * line_height, 16, str);
+		snprintf(str, sizeof(str),
+			" autogain %d, gain %3d, alpha 0x%02x ",
+			dev->autogain->cur.val, gain, dev->alpha->cur.val);
+		mutex_unlock(dev->ctrl_hdl_user_vid.lock);
+		tpg_gen_text(&dev->tpg, basep, line++ * line_height, 16, str);
+		mutex_lock(dev->ctrl_hdl_user_aud.lock);
+		snprintf(str, sizeof(str),
+			" volume %3d, mute %d ",
+			dev->volume->cur.val, dev->mute->cur.val);
+		mutex_unlock(dev->ctrl_hdl_user_aud.lock);
+		tpg_gen_text(&dev->tpg, basep, line++ * line_height, 16, str);
+		mutex_lock(dev->ctrl_hdl_user_gen.lock);
+		snprintf(str, sizeof(str), " int32 %d, int64 %lld, bitmask %08x ",
+			dev->int32->cur.val,
+			*dev->int64->p_cur.p_s64,
+			dev->bitmask->cur.val);
+		tpg_gen_text(&dev->tpg, basep, line++ * line_height, 16, str);
+		snprintf(str, sizeof(str), " boolean %d, menu %s, string \"%s\" ",
+			dev->boolean->cur.val,
+			dev->menu->qmenu[dev->menu->cur.val],
+			dev->string->p_cur.p_char);
+		tpg_gen_text(&dev->tpg, basep, line++ * line_height, 16, str);
+		snprintf(str, sizeof(str), " integer_menu %lld, value %d ",
+			dev->int_menu->qmenu_int[dev->int_menu->cur.val],
+			dev->int_menu->cur.val);
+		mutex_unlock(dev->ctrl_hdl_user_gen.lock);
+		tpg_gen_text(&dev->tpg, basep, line++ * line_height, 16, str);
+		if (dev->button_pressed) {
+			dev->button_pressed--;
+			snprintf(str, sizeof(str), " button pressed!");
+			tpg_gen_text(&dev->tpg, basep, line++ * line_height, 16, str);
+		}
+	}
+
+	/*
+	 * If "End of Frame" is specified at the timestamp source, then take
+	 * the timestamp now.
+	 */
+	if (!dev->tstamp_src_is_soe)
+		v4l2_get_timestamp(&buf->vb.v4l2_buf.timestamp);
+	buf->vb.v4l2_buf.timestamp.tv_sec += dev->time_wrap_offset;
+}
+
+/*
+ * Return true if this pixel coordinate is a valid video pixel.
+ */
+static bool valid_pix(struct vivid_dev *dev, int win_y, int win_x, int fb_y, int fb_x)
+{
+	int i;
+
+	if (dev->bitmap_cap) {
+		/*
+		 * Only if the corresponding bit in the bitmap is set can
+		 * the video pixel be shown. Coordinates are relative to
+		 * the overlay window set by VIDIOC_S_FMT.
+		 */
+		const u8 *p = dev->bitmap_cap;
+		unsigned stride = (dev->compose_cap.width + 7) / 8;
+
+		if (!(p[stride * win_y + win_x / 8] & (1 << (win_x & 7))))
+			return false;
+	}
+
+	for (i = 0; i < dev->clipcount_cap; i++) {
+		/*
+		 * Only if the framebuffer coordinate is not in any of the
+		 * clip rectangles will be video pixel be shown.
+		 */
+		struct v4l2_rect *r = &dev->clips_cap[i].c;
+
+		if (fb_y >= r->top && fb_y < r->top + r->height &&
+		    fb_x >= r->left && fb_x < r->left + r->width)
+			return false;
+	}
+	return true;
+}
+
+/*
+ * Draw the image into the overlay buffer.
+ * Note that the combination of overlay and multiplanar is not supported.
+ */
+static void vivid_overlay(struct vivid_dev *dev, struct vivid_buffer *buf)
+{
+	struct tpg_data *tpg = &dev->tpg;
+	unsigned pixsize = tpg_g_twopixelsize(tpg, 0) / 2;
+	void *vbase = dev->fb_vbase_cap;
+	void *vbuf = vb2_plane_vaddr(&buf->vb, 0);
+	unsigned img_width = dev->compose_cap.width;
+	unsigned img_height = dev->compose_cap.height;
+	unsigned stride = tpg->bytesperline[0];
+	/* if quick is true, then valid_pix() doesn't have to be called */
+	bool quick = dev->bitmap_cap == NULL && dev->clipcount_cap == 0;
+	int x, y, w, out_x = 0;
+
+	if ((dev->overlay_cap_field == V4L2_FIELD_TOP ||
+	     dev->overlay_cap_field == V4L2_FIELD_BOTTOM) &&
+	    dev->overlay_cap_field != buf->vb.v4l2_buf.field)
+		return;
+
+	vbuf += dev->compose_cap.left * pixsize + dev->compose_cap.top * stride;
+	x = dev->overlay_cap_left;
+	w = img_width;
+	if (x < 0) {
+		out_x = -x;
+		w = w - out_x;
+		x = 0;
+	} else {
+		w = dev->fb_cap.fmt.width - x;
+		if (w > img_width)
+			w = img_width;
+	}
+	if (w <= 0)
+		return;
+	if (dev->overlay_cap_top >= 0)
+		vbase += dev->overlay_cap_top * dev->fb_cap.fmt.bytesperline;
+	for (y = dev->overlay_cap_top;
+	     y < dev->overlay_cap_top + (int)img_height;
+	     y++, vbuf += stride) {
+		int px;
+
+		if (y < 0 || y > dev->fb_cap.fmt.height)
+			continue;
+		if (quick) {
+			memcpy(vbase + x * pixsize,
+			       vbuf + out_x * pixsize, w * pixsize);
+			vbase += dev->fb_cap.fmt.bytesperline;
+			continue;
+		}
+		for (px = 0; px < w; px++) {
+			if (!valid_pix(dev, y - dev->overlay_cap_top,
+				       px + out_x, y, px + x))
+				continue;
+			memcpy(vbase + (px + x) * pixsize,
+			       vbuf + (px + out_x) * pixsize,
+			       pixsize);
+		}
+		vbase += dev->fb_cap.fmt.bytesperline;
+	}
+}
+
+static void vivid_thread_vid_cap_tick(struct vivid_dev *dev, int dropped_bufs)
+{
+	struct vivid_buffer *vid_cap_buf = NULL;
+	struct vivid_buffer *vbi_cap_buf = NULL;
+
+	dprintk(dev, 1, "Video Capture Thread Tick\n");
+
+	while (dropped_bufs-- > 1)
+		tpg_update_mv_count(&dev->tpg,
+				dev->field_cap == V4L2_FIELD_NONE ||
+				dev->field_cap == V4L2_FIELD_ALTERNATE);
+
+	/* Drop a certain percentage of buffers. */
+	if (dev->perc_dropped_buffers &&
+	    prandom_u32_max(100) < dev->perc_dropped_buffers)
+		goto update_mv;
+
+	spin_lock(&dev->slock);
+	if (!list_empty(&dev->vid_cap_active)) {
+		vid_cap_buf = list_entry(dev->vid_cap_active.next, struct vivid_buffer, list);
+		list_del(&vid_cap_buf->list);
+	}
+	if (!list_empty(&dev->vbi_cap_active)) {
+		if (dev->field_cap != V4L2_FIELD_ALTERNATE ||
+		    (dev->vbi_cap_seq_count & 1)) {
+			vbi_cap_buf = list_entry(dev->vbi_cap_active.next,
+						 struct vivid_buffer, list);
+			list_del(&vbi_cap_buf->list);
+		}
+	}
+	spin_unlock(&dev->slock);
+
+	if (!vid_cap_buf && !vbi_cap_buf)
+		goto update_mv;
+
+	if (vid_cap_buf) {
+		/* Fill buffer */
+		vivid_fillbuff(dev, vid_cap_buf);
+		dprintk(dev, 1, "filled buffer %d\n",
+			vid_cap_buf->vb.v4l2_buf.index);
+
+		/* Handle overlay */
+		if (dev->overlay_cap_owner && dev->fb_cap.base &&
+				dev->fb_cap.fmt.pixelformat == dev->fmt_cap->fourcc)
+			vivid_overlay(dev, vid_cap_buf);
+
+		vb2_buffer_done(&vid_cap_buf->vb, dev->dqbuf_error ?
+				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
+		dprintk(dev, 2, "vid_cap buffer %d done\n",
+				vid_cap_buf->vb.v4l2_buf.index);
+	}
+
+	if (vbi_cap_buf) {
+		if (dev->stream_sliced_vbi_cap)
+			vivid_sliced_vbi_cap_process(dev, vbi_cap_buf);
+		else
+			vivid_raw_vbi_cap_process(dev, vbi_cap_buf);
+		vb2_buffer_done(&vbi_cap_buf->vb, dev->dqbuf_error ?
+				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
+		dprintk(dev, 2, "vbi_cap %d done\n",
+				vbi_cap_buf->vb.v4l2_buf.index);
+	}
+	dev->dqbuf_error = false;
+
+update_mv:
+	/* Update the test pattern movement counters */
+	tpg_update_mv_count(&dev->tpg, dev->field_cap == V4L2_FIELD_NONE ||
+				       dev->field_cap == V4L2_FIELD_ALTERNATE);
+}
+
+static int vivid_thread_vid_cap(void *data)
+{
+	struct vivid_dev *dev = data;
+	u64 numerators_since_start;
+	u64 buffers_since_start;
+	u64 next_jiffies_since_start;
+	unsigned long jiffies_since_start;
+	unsigned long cur_jiffies;
+	unsigned wait_jiffies;
+	unsigned numerator;
+	unsigned denominator;
+	int dropped_bufs;
+
+	dprintk(dev, 1, "Video Capture Thread Start\n");
+
+	set_freezable();
+
+	/* Resets frame counters */
+	dev->cap_seq_offset = 0;
+	dev->cap_seq_count = 0;
+	dev->cap_seq_resync = false;
+	dev->jiffies_vid_cap = jiffies;
+
+	for (;;) {
+		try_to_freeze();
+		if (kthread_should_stop())
+			break;
+
+		mutex_lock(&dev->mutex);
+		cur_jiffies = jiffies;
+		if (dev->cap_seq_resync) {
+			dev->jiffies_vid_cap = cur_jiffies;
+			dev->cap_seq_offset = dev->cap_seq_count + 1;
+			dev->cap_seq_count = 0;
+			dev->cap_seq_resync = false;
+		}
+		numerator = dev->timeperframe_vid_cap.numerator;
+		denominator = dev->timeperframe_vid_cap.denominator;
+
+		if (dev->field_cap == V4L2_FIELD_ALTERNATE)
+			denominator *= 2;
+
+		/* Calculate the number of jiffies since we started streaming */
+		jiffies_since_start = cur_jiffies - dev->jiffies_vid_cap;
+		/* Get the number of buffers streamed since the start */
+		buffers_since_start = (u64)jiffies_since_start * denominator +
+				      (HZ * numerator) / 2;
+		do_div(buffers_since_start, HZ * numerator);
+
+		/*
+		 * After more than 0xf0000000 (rounded down to a multiple of
+		 * 'jiffies-per-day' to ease jiffies_to_msecs calculation)
+		 * jiffies have passed since we started streaming reset the
+		 * counters and keep track of the sequence offset.
+		 */
+		if (jiffies_since_start > JIFFIES_RESYNC) {
+			dev->jiffies_vid_cap = cur_jiffies;
+			dev->cap_seq_offset = buffers_since_start;
+			buffers_since_start = 0;
+		}
+		dropped_bufs = buffers_since_start + dev->cap_seq_offset - dev->cap_seq_count;
+		dev->cap_seq_count = buffers_since_start + dev->cap_seq_offset;
+		dev->vid_cap_seq_count = dev->cap_seq_count - dev->vid_cap_seq_start;
+		dev->vbi_cap_seq_count = dev->cap_seq_count - dev->vbi_cap_seq_start;
+
+		vivid_thread_vid_cap_tick(dev, dropped_bufs);
+
+		/*
+		 * Calculate the number of 'numerators' streamed since we started,
+		 * including the current buffer.
+		 */
+		numerators_since_start = ++buffers_since_start * numerator;
+
+		/* And the number of jiffies since we started */
+		jiffies_since_start = jiffies - dev->jiffies_vid_cap;
+
+		mutex_unlock(&dev->mutex);
+
+		/*
+		 * Calculate when that next buffer is supposed to start
+		 * in jiffies since we started streaming.
+		 */
+		next_jiffies_since_start = numerators_since_start * HZ +
+					   denominator / 2;
+		do_div(next_jiffies_since_start, denominator);
+		/* If it is in the past, then just schedule asap */
+		if (next_jiffies_since_start < jiffies_since_start)
+			next_jiffies_since_start = jiffies_since_start;
+
+		wait_jiffies = next_jiffies_since_start - jiffies_since_start;
+		schedule_timeout_interruptible(wait_jiffies ? wait_jiffies : 1);
+	}
+	dprintk(dev, 1, "Video Capture Thread End\n");
+	return 0;
+}
+
+static void vivid_grab_controls(struct vivid_dev *dev, bool grab)
+{
+	v4l2_ctrl_grab(dev->ctrl_has_crop_cap, grab);
+	v4l2_ctrl_grab(dev->ctrl_has_compose_cap, grab);
+	v4l2_ctrl_grab(dev->ctrl_has_scaler_cap, grab);
+}
+
+int vivid_start_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming)
+{
+	dprintk(dev, 1, "%s\n", __func__);
+
+	if (dev->kthread_vid_cap) {
+		u32 seq_count = dev->cap_seq_count + dev->seq_wrap * 128;
+
+		if (pstreaming == &dev->vid_cap_streaming)
+			dev->vid_cap_seq_start = seq_count;
+		else
+			dev->vbi_cap_seq_start = seq_count;
+		*pstreaming = true;
+		return 0;
+	}
+
+	/* Resets frame counters */
+	tpg_init_mv_count(&dev->tpg);
+
+	dev->vid_cap_seq_start = dev->seq_wrap * 128;
+	dev->vbi_cap_seq_start = dev->seq_wrap * 128;
+
+	dev->kthread_vid_cap = kthread_run(vivid_thread_vid_cap, dev,
+			"%s-vid-cap", dev->v4l2_dev.name);
+
+	if (IS_ERR(dev->kthread_vid_cap)) {
+		v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n");
+		return PTR_ERR(dev->kthread_vid_cap);
+	}
+	*pstreaming = true;
+	vivid_grab_controls(dev, true);
+
+	dprintk(dev, 1, "returning from %s\n", __func__);
+	return 0;
+}
+
+void vivid_stop_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming)
+{
+	dprintk(dev, 1, "%s\n", __func__);
+
+	if (dev->kthread_vid_cap == NULL)
+		return;
+
+	*pstreaming = false;
+	if (pstreaming == &dev->vid_cap_streaming) {
+		/* Release all active buffers */
+		while (!list_empty(&dev->vid_cap_active)) {
+			struct vivid_buffer *buf;
+
+			buf = list_entry(dev->vid_cap_active.next,
+					 struct vivid_buffer, list);
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+			dprintk(dev, 2, "vid_cap buffer %d done\n",
+				buf->vb.v4l2_buf.index);
+		}
+	}
+
+	if (pstreaming == &dev->vbi_cap_streaming) {
+		while (!list_empty(&dev->vbi_cap_active)) {
+			struct vivid_buffer *buf;
+
+			buf = list_entry(dev->vbi_cap_active.next,
+					 struct vivid_buffer, list);
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+			dprintk(dev, 2, "vbi_cap buffer %d done\n",
+				buf->vb.v4l2_buf.index);
+		}
+	}
+
+	if (dev->vid_cap_streaming || dev->vbi_cap_streaming)
+		return;
+
+	/* shutdown control thread */
+	vivid_grab_controls(dev, false);
+	mutex_unlock(&dev->mutex);
+	kthread_stop(dev->kthread_vid_cap);
+	dev->kthread_vid_cap = NULL;
+	mutex_lock(&dev->mutex);
+}
diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.h b/drivers/media/platform/vivid/vivid-kthread-cap.h
new file mode 100644
index 000000000000..5b92fc9a0d04
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-kthread-cap.h
@@ -0,0 +1,26 @@
+/*
+ * vivid-kthread-cap.h - video/vbi capture thread support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_KTHREAD_CAP_H_
+#define _VIVID_KTHREAD_CAP_H_
+
+int vivid_start_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming);
+void vivid_stop_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-kthread-out.c b/drivers/media/platform/vivid/vivid-kthread-out.c
new file mode 100644
index 000000000000..d9f36ccd7efb
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-kthread-out.c
@@ -0,0 +1,305 @@
+/*
+ * vivid-kthread-out.h - video/vbi output thread support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/font.h>
+#include <linux/mutex.h>
+#include <linux/videodev2.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/random.h>
+#include <linux/v4l2-dv-timings.h>
+#include <asm/div64.h>
+#include <media/videobuf2-vmalloc.h>
+#include <media/v4l2-dv-timings.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-event.h>
+
+#include "vivid-core.h"
+#include "vivid-vid-common.h"
+#include "vivid-vid-cap.h"
+#include "vivid-vid-out.h"
+#include "vivid-radio-common.h"
+#include "vivid-radio-rx.h"
+#include "vivid-radio-tx.h"
+#include "vivid-sdr-cap.h"
+#include "vivid-vbi-cap.h"
+#include "vivid-vbi-out.h"
+#include "vivid-osd.h"
+#include "vivid-ctrls.h"
+#include "vivid-kthread-out.h"
+
+static void vivid_thread_vid_out_tick(struct vivid_dev *dev)
+{
+	struct vivid_buffer *vid_out_buf = NULL;
+	struct vivid_buffer *vbi_out_buf = NULL;
+
+	dprintk(dev, 1, "Video Output Thread Tick\n");
+
+	/* Drop a certain percentage of buffers. */
+	if (dev->perc_dropped_buffers &&
+	    prandom_u32_max(100) < dev->perc_dropped_buffers)
+		return;
+
+	spin_lock(&dev->slock);
+	/*
+	 * Only dequeue buffer if there is at least one more pending.
+	 * This makes video loopback possible.
+	 */
+	if (!list_empty(&dev->vid_out_active) &&
+	    !list_is_singular(&dev->vid_out_active)) {
+		vid_out_buf = list_entry(dev->vid_out_active.next,
+					 struct vivid_buffer, list);
+		list_del(&vid_out_buf->list);
+	}
+	if (!list_empty(&dev->vbi_out_active) &&
+	    (dev->field_out != V4L2_FIELD_ALTERNATE ||
+	     (dev->vbi_out_seq_count & 1))) {
+		vbi_out_buf = list_entry(dev->vbi_out_active.next,
+					 struct vivid_buffer, list);
+		list_del(&vbi_out_buf->list);
+	}
+	spin_unlock(&dev->slock);
+
+	if (!vid_out_buf && !vbi_out_buf)
+		return;
+
+	if (vid_out_buf) {
+		vid_out_buf->vb.v4l2_buf.sequence = dev->vid_out_seq_count;
+		if (dev->field_out == V4L2_FIELD_ALTERNATE) {
+			/*
+			 * The sequence counter counts frames, not fields. So divide
+			 * by two.
+			 */
+			vid_out_buf->vb.v4l2_buf.sequence /= 2;
+		}
+		v4l2_get_timestamp(&vid_out_buf->vb.v4l2_buf.timestamp);
+		vid_out_buf->vb.v4l2_buf.timestamp.tv_sec += dev->time_wrap_offset;
+		vb2_buffer_done(&vid_out_buf->vb, dev->dqbuf_error ?
+				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
+		dprintk(dev, 2, "vid_out buffer %d done\n",
+			vid_out_buf->vb.v4l2_buf.index);
+	}
+
+	if (vbi_out_buf) {
+		if (dev->stream_sliced_vbi_out)
+			vivid_sliced_vbi_out_process(dev, vbi_out_buf);
+
+		vbi_out_buf->vb.v4l2_buf.sequence = dev->vbi_out_seq_count;
+		v4l2_get_timestamp(&vbi_out_buf->vb.v4l2_buf.timestamp);
+		vbi_out_buf->vb.v4l2_buf.timestamp.tv_sec += dev->time_wrap_offset;
+		vb2_buffer_done(&vbi_out_buf->vb, dev->dqbuf_error ?
+				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
+		dprintk(dev, 2, "vbi_out buffer %d done\n",
+			vbi_out_buf->vb.v4l2_buf.index);
+	}
+	dev->dqbuf_error = false;
+}
+
+static int vivid_thread_vid_out(void *data)
+{
+	struct vivid_dev *dev = data;
+	u64 numerators_since_start;
+	u64 buffers_since_start;
+	u64 next_jiffies_since_start;
+	unsigned long jiffies_since_start;
+	unsigned long cur_jiffies;
+	unsigned wait_jiffies;
+	unsigned numerator;
+	unsigned denominator;
+
+	dprintk(dev, 1, "Video Output Thread Start\n");
+
+	set_freezable();
+
+	/* Resets frame counters */
+	dev->out_seq_offset = 0;
+	if (dev->seq_wrap)
+		dev->out_seq_count = 0xffffff80U;
+	dev->jiffies_vid_out = jiffies;
+	dev->vid_out_seq_start = dev->vbi_out_seq_start = 0;
+	dev->out_seq_resync = false;
+
+	for (;;) {
+		try_to_freeze();
+		if (kthread_should_stop())
+			break;
+
+		mutex_lock(&dev->mutex);
+		cur_jiffies = jiffies;
+		if (dev->out_seq_resync) {
+			dev->jiffies_vid_out = cur_jiffies;
+			dev->out_seq_offset = dev->out_seq_count + 1;
+			dev->out_seq_count = 0;
+			dev->out_seq_resync = false;
+		}
+		numerator = dev->timeperframe_vid_out.numerator;
+		denominator = dev->timeperframe_vid_out.denominator;
+
+		if (dev->field_out == V4L2_FIELD_ALTERNATE)
+			denominator *= 2;
+
+		/* Calculate the number of jiffies since we started streaming */
+		jiffies_since_start = cur_jiffies - dev->jiffies_vid_out;
+		/* Get the number of buffers streamed since the start */
+		buffers_since_start = (u64)jiffies_since_start * denominator +
+				      (HZ * numerator) / 2;
+		do_div(buffers_since_start, HZ * numerator);
+
+		/*
+		 * After more than 0xf0000000 (rounded down to a multiple of
+		 * 'jiffies-per-day' to ease jiffies_to_msecs calculation)
+		 * jiffies have passed since we started streaming reset the
+		 * counters and keep track of the sequence offset.
+		 */
+		if (jiffies_since_start > JIFFIES_RESYNC) {
+			dev->jiffies_vid_out = cur_jiffies;
+			dev->out_seq_offset = buffers_since_start;
+			buffers_since_start = 0;
+		}
+		dev->out_seq_count = buffers_since_start + dev->out_seq_offset;
+		dev->vid_out_seq_count = dev->out_seq_count - dev->vid_out_seq_start;
+		dev->vbi_out_seq_count = dev->out_seq_count - dev->vbi_out_seq_start;
+
+		vivid_thread_vid_out_tick(dev);
+		mutex_unlock(&dev->mutex);
+
+		/*
+		 * Calculate the number of 'numerators' streamed since we started,
+		 * not including the current buffer.
+		 */
+		numerators_since_start = buffers_since_start * numerator;
+
+		/* And the number of jiffies since we started */
+		jiffies_since_start = jiffies - dev->jiffies_vid_out;
+
+		/* Increase by the 'numerator' of one buffer */
+		numerators_since_start += numerator;
+		/*
+		 * Calculate when that next buffer is supposed to start
+		 * in jiffies since we started streaming.
+		 */
+		next_jiffies_since_start = numerators_since_start * HZ +
+					   denominator / 2;
+		do_div(next_jiffies_since_start, denominator);
+		/* If it is in the past, then just schedule asap */
+		if (next_jiffies_since_start < jiffies_since_start)
+			next_jiffies_since_start = jiffies_since_start;
+
+		wait_jiffies = next_jiffies_since_start - jiffies_since_start;
+		schedule_timeout_interruptible(wait_jiffies ? wait_jiffies : 1);
+	}
+	dprintk(dev, 1, "Video Output Thread End\n");
+	return 0;
+}
+
+static void vivid_grab_controls(struct vivid_dev *dev, bool grab)
+{
+	v4l2_ctrl_grab(dev->ctrl_has_crop_out, grab);
+	v4l2_ctrl_grab(dev->ctrl_has_compose_out, grab);
+	v4l2_ctrl_grab(dev->ctrl_has_scaler_out, grab);
+	v4l2_ctrl_grab(dev->ctrl_tx_mode, grab);
+	v4l2_ctrl_grab(dev->ctrl_tx_rgb_range, grab);
+}
+
+int vivid_start_generating_vid_out(struct vivid_dev *dev, bool *pstreaming)
+{
+	dprintk(dev, 1, "%s\n", __func__);
+
+	if (dev->kthread_vid_out) {
+		u32 seq_count = dev->out_seq_count + dev->seq_wrap * 128;
+
+		if (pstreaming == &dev->vid_out_streaming)
+			dev->vid_out_seq_start = seq_count;
+		else
+			dev->vbi_out_seq_start = seq_count;
+		*pstreaming = true;
+		return 0;
+	}
+
+	/* Resets frame counters */
+	dev->jiffies_vid_out = jiffies;
+	dev->vid_out_seq_start = dev->seq_wrap * 128;
+	dev->vbi_out_seq_start = dev->seq_wrap * 128;
+
+	dev->kthread_vid_out = kthread_run(vivid_thread_vid_out, dev,
+			"%s-vid-out", dev->v4l2_dev.name);
+
+	if (IS_ERR(dev->kthread_vid_out)) {
+		v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n");
+		return PTR_ERR(dev->kthread_vid_out);
+	}
+	*pstreaming = true;
+	vivid_grab_controls(dev, true);
+
+	dprintk(dev, 1, "returning from %s\n", __func__);
+	return 0;
+}
+
+void vivid_stop_generating_vid_out(struct vivid_dev *dev, bool *pstreaming)
+{
+	dprintk(dev, 1, "%s\n", __func__);
+
+	if (dev->kthread_vid_out == NULL)
+		return;
+
+	*pstreaming = false;
+	if (pstreaming == &dev->vid_out_streaming) {
+		/* Release all active buffers */
+		while (!list_empty(&dev->vid_out_active)) {
+			struct vivid_buffer *buf;
+
+			buf = list_entry(dev->vid_out_active.next,
+					 struct vivid_buffer, list);
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+			dprintk(dev, 2, "vid_out buffer %d done\n",
+				buf->vb.v4l2_buf.index);
+		}
+	}
+
+	if (pstreaming == &dev->vbi_out_streaming) {
+		while (!list_empty(&dev->vbi_out_active)) {
+			struct vivid_buffer *buf;
+
+			buf = list_entry(dev->vbi_out_active.next,
+					 struct vivid_buffer, list);
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+			dprintk(dev, 2, "vbi_out buffer %d done\n",
+				buf->vb.v4l2_buf.index);
+		}
+	}
+
+	if (dev->vid_out_streaming || dev->vbi_out_streaming)
+		return;
+
+	/* shutdown control thread */
+	vivid_grab_controls(dev, false);
+	mutex_unlock(&dev->mutex);
+	kthread_stop(dev->kthread_vid_out);
+	dev->kthread_vid_out = NULL;
+	mutex_lock(&dev->mutex);
+}
diff --git a/drivers/media/platform/vivid/vivid-kthread-out.h b/drivers/media/platform/vivid/vivid-kthread-out.h
new file mode 100644
index 000000000000..2bf04a17b05d
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-kthread-out.h
@@ -0,0 +1,26 @@
+/*
+ * vivid-kthread-out.h - video/vbi output thread support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_KTHREAD_OUT_H_
+#define _VIVID_KTHREAD_OUT_H_
+
+int vivid_start_generating_vid_out(struct vivid_dev *dev, bool *pstreaming);
+void vivid_stop_generating_vid_out(struct vivid_dev *dev, bool *pstreaming);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-osd.c b/drivers/media/platform/vivid/vivid-osd.c
new file mode 100644
index 000000000000..084d346fb4c4
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-osd.c
@@ -0,0 +1,400 @@
+/*
+ * vivid-osd.c - osd support for testing overlays.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/font.h>
+#include <linux/mutex.h>
+#include <linux/videodev2.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/fb.h>
+#include <media/videobuf2-vmalloc.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-common.h>
+
+#include "vivid-core.h"
+#include "vivid-osd.h"
+
+#define MAX_OSD_WIDTH  720
+#define MAX_OSD_HEIGHT 576
+
+/*
+ * Order: white, yellow, cyan, green, magenta, red, blue, black,
+ * and same again with the alpha bit set (if any)
+ */
+static const u16 rgb555[16] = {
+	0x7fff, 0x7fe0, 0x03ff, 0x03e0, 0x7c1f, 0x7c00, 0x001f, 0x0000,
+	0xffff, 0xffe0, 0x83ff, 0x83e0, 0xfc1f, 0xfc00, 0x801f, 0x8000
+};
+
+static const u16 rgb565[16] = {
+	0xffff, 0xffe0, 0x07ff, 0x07e0, 0xf81f, 0xf800, 0x001f, 0x0000,
+	0xffff, 0xffe0, 0x07ff, 0x07e0, 0xf81f, 0xf800, 0x001f, 0x0000
+};
+
+void vivid_clear_fb(struct vivid_dev *dev)
+{
+	void *p = dev->video_vbase;
+	const u16 *rgb = rgb555;
+	unsigned x, y;
+
+	if (dev->fb_defined.green.length == 6)
+		rgb = rgb565;
+
+	for (y = 0; y < dev->display_height; y++) {
+		u16 *d = p;
+
+		for (x = 0; x < dev->display_width; x++)
+			d[x] = rgb[(y / 16 + x / 16) % 16];
+		p += dev->display_byte_stride;
+	}
+}
+
+/* --------------------------------------------------------------------- */
+
+static int vivid_fb_ioctl(struct fb_info *info, unsigned cmd, unsigned long arg)
+{
+	struct vivid_dev *dev = (struct vivid_dev *)info->par;
+
+	switch (cmd) {
+	case FBIOGET_VBLANK: {
+		struct fb_vblank vblank;
+
+		vblank.flags = FB_VBLANK_HAVE_COUNT | FB_VBLANK_HAVE_VCOUNT |
+			FB_VBLANK_HAVE_VSYNC;
+		vblank.count = 0;
+		vblank.vcount = 0;
+		vblank.hcount = 0;
+		if (copy_to_user((void __user *)arg, &vblank, sizeof(vblank)))
+			return -EFAULT;
+		return 0;
+	}
+
+	default:
+		dprintk(dev, 1, "Unknown ioctl %08x\n", cmd);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Framebuffer device handling */
+
+static int vivid_fb_set_var(struct vivid_dev *dev, struct fb_var_screeninfo *var)
+{
+	dprintk(dev, 1, "vivid_fb_set_var\n");
+
+	if (var->bits_per_pixel != 16) {
+		dprintk(dev, 1, "vivid_fb_set_var - Invalid bpp\n");
+		return -EINVAL;
+	}
+	dev->display_byte_stride = var->xres * dev->bytes_per_pixel;
+
+	return 0;
+}
+
+static int vivid_fb_get_fix(struct vivid_dev *dev, struct fb_fix_screeninfo *fix)
+{
+	dprintk(dev, 1, "vivid_fb_get_fix\n");
+	memset(fix, 0, sizeof(struct fb_fix_screeninfo));
+	strlcpy(fix->id, "vioverlay fb", sizeof(fix->id));
+	fix->smem_start = dev->video_pbase;
+	fix->smem_len = dev->video_buffer_size;
+	fix->type = FB_TYPE_PACKED_PIXELS;
+	fix->visual = FB_VISUAL_TRUECOLOR;
+	fix->xpanstep = 1;
+	fix->ypanstep = 1;
+	fix->ywrapstep = 0;
+	fix->line_length = dev->display_byte_stride;
+	fix->accel = FB_ACCEL_NONE;
+	return 0;
+}
+
+/* Check the requested display mode, returning -EINVAL if we can't
+   handle it. */
+
+static int _vivid_fb_check_var(struct fb_var_screeninfo *var, struct vivid_dev *dev)
+{
+	dprintk(dev, 1, "vivid_fb_check_var\n");
+
+	var->bits_per_pixel = 16;
+	if (var->green.length == 5) {
+		var->red.offset = 10;
+		var->red.length = 5;
+		var->green.offset = 5;
+		var->green.length = 5;
+		var->blue.offset = 0;
+		var->blue.length = 5;
+		var->transp.offset = 15;
+		var->transp.length = 1;
+	} else {
+		var->red.offset = 11;
+		var->red.length = 5;
+		var->green.offset = 5;
+		var->green.length = 6;
+		var->blue.offset = 0;
+		var->blue.length = 5;
+		var->transp.offset = 0;
+		var->transp.length = 0;
+	}
+	var->xoffset = var->yoffset = 0;
+	var->left_margin = var->upper_margin = 0;
+	var->nonstd = 0;
+
+	var->vmode &= ~FB_VMODE_MASK;
+	var->vmode = FB_VMODE_NONINTERLACED;
+
+	/* Dummy values */
+	var->hsync_len = 24;
+	var->vsync_len = 2;
+	var->pixclock = 84316;
+	var->right_margin = 776;
+	var->lower_margin = 591;
+	return 0;
+}
+
+static int vivid_fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+	struct vivid_dev *dev = (struct vivid_dev *) info->par;
+
+	dprintk(dev, 1, "vivid_fb_check_var\n");
+	return _vivid_fb_check_var(var, dev);
+}
+
+static int vivid_fb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+	return 0;
+}
+
+static int vivid_fb_set_par(struct fb_info *info)
+{
+	int rc = 0;
+	struct vivid_dev *dev = (struct vivid_dev *) info->par;
+
+	dprintk(dev, 1, "vivid_fb_set_par\n");
+
+	rc = vivid_fb_set_var(dev, &info->var);
+	vivid_fb_get_fix(dev, &info->fix);
+	return rc;
+}
+
+static int vivid_fb_setcolreg(unsigned regno, unsigned red, unsigned green,
+				unsigned blue, unsigned transp,
+				struct fb_info *info)
+{
+	u32 color, *palette;
+
+	if (regno >= info->cmap.len)
+		return -EINVAL;
+
+	color = ((transp & 0xFF00) << 16) | ((red & 0xFF00) << 8) |
+		 (green & 0xFF00) | ((blue & 0xFF00) >> 8);
+	if (regno >= 16)
+		return -EINVAL;
+
+	palette = info->pseudo_palette;
+	if (info->var.bits_per_pixel == 16) {
+		switch (info->var.green.length) {
+		case 6:
+			color = (red & 0xf800) |
+				((green & 0xfc00) >> 5) |
+				((blue & 0xf800) >> 11);
+			break;
+		case 5:
+			color = ((red & 0xf800) >> 1) |
+				((green & 0xf800) >> 6) |
+				((blue & 0xf800) >> 11) |
+				(transp ? 0x8000 : 0);
+			break;
+		}
+	}
+	palette[regno] = color;
+	return 0;
+}
+
+/* We don't really support blanking. All this does is enable or
+   disable the OSD. */
+static int vivid_fb_blank(int blank_mode, struct fb_info *info)
+{
+	struct vivid_dev *dev = (struct vivid_dev *)info->par;
+
+	dprintk(dev, 1, "Set blanking mode : %d\n", blank_mode);
+	switch (blank_mode) {
+	case FB_BLANK_UNBLANK:
+		break;
+	case FB_BLANK_NORMAL:
+	case FB_BLANK_HSYNC_SUSPEND:
+	case FB_BLANK_VSYNC_SUSPEND:
+	case FB_BLANK_POWERDOWN:
+		break;
+	}
+	return 0;
+}
+
+static struct fb_ops vivid_fb_ops = {
+	.owner = THIS_MODULE,
+	.fb_check_var   = vivid_fb_check_var,
+	.fb_set_par     = vivid_fb_set_par,
+	.fb_setcolreg   = vivid_fb_setcolreg,
+	.fb_fillrect    = cfb_fillrect,
+	.fb_copyarea    = cfb_copyarea,
+	.fb_imageblit   = cfb_imageblit,
+	.fb_cursor      = NULL,
+	.fb_ioctl       = vivid_fb_ioctl,
+	.fb_pan_display = vivid_fb_pan_display,
+	.fb_blank       = vivid_fb_blank,
+};
+
+/* Initialization */
+
+
+/* Setup our initial video mode */
+static int vivid_fb_init_vidmode(struct vivid_dev *dev)
+{
+	struct v4l2_rect start_window;
+
+	/* Color mode */
+
+	dev->bits_per_pixel = 16;
+	dev->bytes_per_pixel = dev->bits_per_pixel / 8;
+
+	start_window.width = MAX_OSD_WIDTH;
+	start_window.left = 0;
+
+	dev->display_byte_stride = start_window.width * dev->bytes_per_pixel;
+
+	/* Vertical size & position */
+
+	start_window.height = MAX_OSD_HEIGHT;
+	start_window.top = 0;
+
+	dev->display_width = start_window.width;
+	dev->display_height = start_window.height;
+
+	/* Generate a valid fb_var_screeninfo */
+
+	dev->fb_defined.xres = dev->display_width;
+	dev->fb_defined.yres = dev->display_height;
+	dev->fb_defined.xres_virtual = dev->display_width;
+	dev->fb_defined.yres_virtual = dev->display_height;
+	dev->fb_defined.bits_per_pixel = dev->bits_per_pixel;
+	dev->fb_defined.vmode = FB_VMODE_NONINTERLACED;
+	dev->fb_defined.left_margin = start_window.left + 1;
+	dev->fb_defined.upper_margin = start_window.top + 1;
+	dev->fb_defined.accel_flags = FB_ACCEL_NONE;
+	dev->fb_defined.nonstd = 0;
+	/* set default to 1:5:5:5 */
+	dev->fb_defined.green.length = 5;
+
+	/* We've filled in the most data, let the usual mode check
+	   routine fill in the rest. */
+	_vivid_fb_check_var(&dev->fb_defined, dev);
+
+	/* Generate valid fb_fix_screeninfo */
+
+	vivid_fb_get_fix(dev, &dev->fb_fix);
+
+	/* Generate valid fb_info */
+
+	dev->fb_info.node = -1;
+	dev->fb_info.flags = FBINFO_FLAG_DEFAULT;
+	dev->fb_info.fbops = &vivid_fb_ops;
+	dev->fb_info.par = dev;
+	dev->fb_info.var = dev->fb_defined;
+	dev->fb_info.fix = dev->fb_fix;
+	dev->fb_info.screen_base = (u8 __iomem *)dev->video_vbase;
+	dev->fb_info.fbops = &vivid_fb_ops;
+
+	/* Supply some monitor specs. Bogus values will do for now */
+	dev->fb_info.monspecs.hfmin = 8000;
+	dev->fb_info.monspecs.hfmax = 70000;
+	dev->fb_info.monspecs.vfmin = 10;
+	dev->fb_info.monspecs.vfmax = 100;
+
+	/* Allocate color map */
+	if (fb_alloc_cmap(&dev->fb_info.cmap, 256, 1)) {
+		pr_err("abort, unable to alloc cmap\n");
+		return -ENOMEM;
+	}
+
+	/* Allocate the pseudo palette */
+	dev->fb_info.pseudo_palette = kmalloc_array(16, sizeof(u32), GFP_KERNEL);
+
+	return dev->fb_info.pseudo_palette ? 0 : -ENOMEM;
+}
+
+/* Release any memory we've grabbed */
+void vivid_fb_release_buffers(struct vivid_dev *dev)
+{
+	if (dev->video_vbase == NULL)
+		return;
+
+	/* Release cmap */
+	if (dev->fb_info.cmap.len)
+		fb_dealloc_cmap(&dev->fb_info.cmap);
+
+	/* Release pseudo palette */
+	kfree(dev->fb_info.pseudo_palette);
+	kfree((void *)dev->video_vbase);
+}
+
+/* Initialize the specified card */
+
+int vivid_fb_init(struct vivid_dev *dev)
+{
+	int ret;
+
+	dev->video_buffer_size = MAX_OSD_HEIGHT * MAX_OSD_WIDTH * 2;
+	dev->video_vbase = kzalloc(dev->video_buffer_size, GFP_KERNEL | GFP_DMA32);
+	if (dev->video_vbase == NULL)
+		return -ENOMEM;
+	dev->video_pbase = virt_to_phys(dev->video_vbase);
+
+	pr_info("Framebuffer at 0x%lx, mapped to 0x%p, size %dk\n",
+			dev->video_pbase, dev->video_vbase,
+			dev->video_buffer_size / 1024);
+
+	/* Set the startup video mode information */
+	ret = vivid_fb_init_vidmode(dev);
+	if (ret) {
+		vivid_fb_release_buffers(dev);
+		return ret;
+	}
+
+	vivid_clear_fb(dev);
+
+	/* Register the framebuffer */
+	if (register_framebuffer(&dev->fb_info) < 0) {
+		vivid_fb_release_buffers(dev);
+		return -EINVAL;
+	}
+
+	/* Set the card to the requested mode */
+	vivid_fb_set_par(&dev->fb_info);
+	return 0;
+
+}
diff --git a/drivers/media/platform/vivid/vivid-osd.h b/drivers/media/platform/vivid/vivid-osd.h
new file mode 100644
index 000000000000..57c9daa5940a
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-osd.h
@@ -0,0 +1,27 @@
+/*
+ * vivid-osd.h - output overlay support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_OSD_H_
+#define _VIVID_OSD_H_
+
+int vivid_fb_init(struct vivid_dev *dev);
+void vivid_fb_release_buffers(struct vivid_dev *dev);
+void vivid_clear_fb(struct vivid_dev *dev);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-radio-common.c b/drivers/media/platform/vivid/vivid-radio-common.c
new file mode 100644
index 000000000000..78c1e920670a
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-radio-common.c
@@ -0,0 +1,189 @@
+/*
+ * vivid-radio-common.c - common radio rx/tx support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/videodev2.h>
+
+#include "vivid-core.h"
+#include "vivid-ctrls.h"
+#include "vivid-radio-common.h"
+#include "vivid-rds-gen.h"
+
+/*
+ * These functions are shared between the vivid receiver and transmitter
+ * since both use the same frequency bands.
+ */
+
+const struct v4l2_frequency_band vivid_radio_bands[TOT_BANDS] = {
+	/* Band FM */
+	{
+		.type = V4L2_TUNER_RADIO,
+		.index = 0,
+		.capability = V4L2_TUNER_CAP_LOW | V4L2_TUNER_CAP_STEREO |
+			      V4L2_TUNER_CAP_FREQ_BANDS,
+		.rangelow   = FM_FREQ_RANGE_LOW,
+		.rangehigh  = FM_FREQ_RANGE_HIGH,
+		.modulation = V4L2_BAND_MODULATION_FM,
+	},
+	/* Band AM */
+	{
+		.type = V4L2_TUNER_RADIO,
+		.index = 1,
+		.capability = V4L2_TUNER_CAP_LOW | V4L2_TUNER_CAP_FREQ_BANDS,
+		.rangelow   = AM_FREQ_RANGE_LOW,
+		.rangehigh  = AM_FREQ_RANGE_HIGH,
+		.modulation = V4L2_BAND_MODULATION_AM,
+	},
+	/* Band SW */
+	{
+		.type = V4L2_TUNER_RADIO,
+		.index = 2,
+		.capability = V4L2_TUNER_CAP_LOW | V4L2_TUNER_CAP_FREQ_BANDS,
+		.rangelow   = SW_FREQ_RANGE_LOW,
+		.rangehigh  = SW_FREQ_RANGE_HIGH,
+		.modulation = V4L2_BAND_MODULATION_AM,
+	},
+};
+
+/*
+ * Initialize the RDS generator. If we can loop, then the RDS generator
+ * is set up with the values from the RDS TX controls, otherwise it
+ * will fill in standard values using one of two alternates.
+ */
+void vivid_radio_rds_init(struct vivid_dev *dev)
+{
+	struct vivid_rds_gen *rds = &dev->rds_gen;
+	bool alt = dev->radio_rx_rds_use_alternates;
+
+	/* Do nothing, blocks will be filled by the transmitter */
+	if (dev->radio_rds_loop && !dev->radio_tx_rds_controls)
+		return;
+
+	if (dev->radio_rds_loop) {
+		v4l2_ctrl_lock(dev->radio_tx_rds_pi);
+		rds->picode = dev->radio_tx_rds_pi->cur.val;
+		rds->pty = dev->radio_tx_rds_pty->cur.val;
+		rds->mono_stereo = dev->radio_tx_rds_mono_stereo->cur.val;
+		rds->art_head = dev->radio_tx_rds_art_head->cur.val;
+		rds->compressed = dev->radio_tx_rds_compressed->cur.val;
+		rds->dyn_pty = dev->radio_tx_rds_dyn_pty->cur.val;
+		rds->ta = dev->radio_tx_rds_ta->cur.val;
+		rds->tp = dev->radio_tx_rds_tp->cur.val;
+		rds->ms = dev->radio_tx_rds_ms->cur.val;
+		strlcpy(rds->psname,
+			dev->radio_tx_rds_psname->p_cur.p_char,
+			sizeof(rds->psname));
+		strlcpy(rds->radiotext,
+			dev->radio_tx_rds_radiotext->p_cur.p_char + alt * 64,
+			sizeof(rds->radiotext));
+		v4l2_ctrl_unlock(dev->radio_tx_rds_pi);
+	} else {
+		vivid_rds_gen_fill(rds, dev->radio_rx_freq, alt);
+	}
+	if (dev->radio_rx_rds_controls) {
+		v4l2_ctrl_s_ctrl(dev->radio_rx_rds_pty, rds->pty);
+		v4l2_ctrl_s_ctrl(dev->radio_rx_rds_ta, rds->ta);
+		v4l2_ctrl_s_ctrl(dev->radio_rx_rds_tp, rds->tp);
+		v4l2_ctrl_s_ctrl(dev->radio_rx_rds_ms, rds->ms);
+		v4l2_ctrl_s_ctrl_string(dev->radio_rx_rds_psname, rds->psname);
+		v4l2_ctrl_s_ctrl_string(dev->radio_rx_rds_radiotext, rds->radiotext);
+		if (!dev->radio_rds_loop)
+			dev->radio_rx_rds_use_alternates = !dev->radio_rx_rds_use_alternates;
+	}
+	vivid_rds_generate(rds);
+}
+
+/*
+ * Calculate the emulated signal quality taking into account the frequency
+ * the transmitter is using.
+ */
+static void vivid_radio_calc_sig_qual(struct vivid_dev *dev)
+{
+	int mod = 16000;
+	int delta = 800;
+	int sig_qual, sig_qual_tx = mod;
+
+	/*
+	 * For SW and FM there is a channel every 1000 kHz, for AM there is one
+	 * every 100 kHz.
+	 */
+	if (dev->radio_rx_freq <= AM_FREQ_RANGE_HIGH) {
+		mod /= 10;
+		delta /= 10;
+	}
+	sig_qual = (dev->radio_rx_freq + delta) % mod - delta;
+	if (dev->has_radio_tx)
+		sig_qual_tx = dev->radio_rx_freq - dev->radio_tx_freq;
+	if (abs(sig_qual_tx) <= abs(sig_qual)) {
+		sig_qual = sig_qual_tx;
+		/*
+		 * Zero the internal rds buffer if we are going to loop
+		 * rds blocks.
+		 */
+		if (!dev->radio_rds_loop && !dev->radio_tx_rds_controls)
+			memset(dev->rds_gen.data, 0,
+			       sizeof(dev->rds_gen.data));
+		dev->radio_rds_loop = dev->radio_rx_freq >= FM_FREQ_RANGE_LOW;
+	} else {
+		dev->radio_rds_loop = false;
+	}
+	if (dev->radio_rx_freq <= AM_FREQ_RANGE_HIGH)
+		sig_qual *= 10;
+	dev->radio_rx_sig_qual = sig_qual;
+}
+
+int vivid_radio_g_frequency(struct file *file, const unsigned *pfreq, struct v4l2_frequency *vf)
+{
+	if (vf->tuner != 0)
+		return -EINVAL;
+	vf->frequency = *pfreq;
+	return 0;
+}
+
+int vivid_radio_s_frequency(struct file *file, unsigned *pfreq, const struct v4l2_frequency *vf)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	unsigned freq;
+	unsigned band;
+
+	if (vf->tuner != 0)
+		return -EINVAL;
+
+	if (vf->frequency >= (FM_FREQ_RANGE_LOW + SW_FREQ_RANGE_HIGH) / 2)
+		band = BAND_FM;
+	else if (vf->frequency <= (AM_FREQ_RANGE_HIGH + SW_FREQ_RANGE_LOW) / 2)
+		band = BAND_AM;
+	else
+		band = BAND_SW;
+
+	freq = clamp_t(u32, vf->frequency, vivid_radio_bands[band].rangelow,
+					   vivid_radio_bands[band].rangehigh);
+	*pfreq = freq;
+
+	/*
+	 * For both receiver and transmitter recalculate the signal quality
+	 * (since that depends on both frequencies) and re-init the rds
+	 * generator.
+	 */
+	vivid_radio_calc_sig_qual(dev);
+	vivid_radio_rds_init(dev);
+	return 0;
+}
diff --git a/drivers/media/platform/vivid/vivid-radio-common.h b/drivers/media/platform/vivid/vivid-radio-common.h
new file mode 100644
index 000000000000..92fe589141b7
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-radio-common.h
@@ -0,0 +1,40 @@
+/*
+ * vivid-radio-common.h - common radio rx/tx support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_RADIO_COMMON_H_
+#define _VIVID_RADIO_COMMON_H_
+
+/* The supported radio frequency ranges in kHz */
+#define FM_FREQ_RANGE_LOW       (64000U * 16U)
+#define FM_FREQ_RANGE_HIGH      (108000U * 16U)
+#define AM_FREQ_RANGE_LOW       (520U * 16U)
+#define AM_FREQ_RANGE_HIGH      (1710U * 16U)
+#define SW_FREQ_RANGE_LOW       (2300U * 16U)
+#define SW_FREQ_RANGE_HIGH      (26100U * 16U)
+
+enum { BAND_FM, BAND_AM, BAND_SW, TOT_BANDS };
+
+extern const struct v4l2_frequency_band vivid_radio_bands[TOT_BANDS];
+
+int vivid_radio_g_frequency(struct file *file, const unsigned *freq, struct v4l2_frequency *vf);
+int vivid_radio_s_frequency(struct file *file, unsigned *freq, const struct v4l2_frequency *vf);
+
+void vivid_radio_rds_init(struct vivid_dev *dev);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-radio-rx.c b/drivers/media/platform/vivid/vivid-radio-rx.c
new file mode 100644
index 000000000000..c7651a506668
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-radio-rx.c
@@ -0,0 +1,287 @@
+/*
+ * vivid-radio-rx.c - radio receiver support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/videodev2.h>
+#include <linux/v4l2-dv-timings.h>
+#include <media/v4l2-common.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-dv-timings.h>
+
+#include "vivid-core.h"
+#include "vivid-ctrls.h"
+#include "vivid-radio-common.h"
+#include "vivid-rds-gen.h"
+#include "vivid-radio-rx.h"
+
+ssize_t vivid_radio_rx_read(struct file *file, char __user *buf,
+			 size_t size, loff_t *offset)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct timespec ts;
+	struct v4l2_rds_data *data = dev->rds_gen.data;
+	bool use_alternates;
+	unsigned blk;
+	int perc;
+	int i;
+
+	if (dev->radio_rx_rds_controls)
+		return -EINVAL;
+	if (size < sizeof(*data))
+		return 0;
+	size = sizeof(*data) * (size / sizeof(*data));
+
+	if (mutex_lock_interruptible(&dev->mutex))
+		return -ERESTARTSYS;
+	if (dev->radio_rx_rds_owner &&
+	    file->private_data != dev->radio_rx_rds_owner) {
+		mutex_unlock(&dev->mutex);
+		return -EBUSY;
+	}
+	if (dev->radio_rx_rds_owner == NULL) {
+		vivid_radio_rds_init(dev);
+		dev->radio_rx_rds_owner = file->private_data;
+	}
+
+retry:
+	ktime_get_ts(&ts);
+	use_alternates = ts.tv_sec % 10 >= 5;
+	if (dev->radio_rx_rds_last_block == 0 ||
+	    dev->radio_rx_rds_use_alternates != use_alternates) {
+		dev->radio_rx_rds_use_alternates = use_alternates;
+		/* Re-init the RDS generator */
+		vivid_radio_rds_init(dev);
+	}
+	ts = timespec_sub(ts, dev->radio_rds_init_ts);
+	blk = ts.tv_sec * 100 + ts.tv_nsec / 10000000;
+	blk = (blk * VIVID_RDS_GEN_BLOCKS) / 500;
+	if (blk >= dev->radio_rx_rds_last_block + VIVID_RDS_GEN_BLOCKS)
+		dev->radio_rx_rds_last_block = blk - VIVID_RDS_GEN_BLOCKS + 1;
+
+	/*
+	 * No data is available if there hasn't been time to get new data,
+	 * or if the RDS receiver has been disabled, or if we use the data
+	 * from the RDS transmitter and that RDS transmitter has been disabled,
+	 * or if the signal quality is too weak.
+	 */
+	if (blk == dev->radio_rx_rds_last_block || !dev->radio_rx_rds_enabled ||
+	    (dev->radio_rds_loop && !(dev->radio_tx_subchans & V4L2_TUNER_SUB_RDS)) ||
+	    abs(dev->radio_rx_sig_qual) > 200) {
+		mutex_unlock(&dev->mutex);
+		if (file->f_flags & O_NONBLOCK)
+			return -EWOULDBLOCK;
+		if (msleep_interruptible(20) && signal_pending(current))
+			return -EINTR;
+		if (mutex_lock_interruptible(&dev->mutex))
+			return -ERESTARTSYS;
+		goto retry;
+	}
+
+	/* abs(dev->radio_rx_sig_qual) <= 200, map that to a 0-50% range */
+	perc = abs(dev->radio_rx_sig_qual) / 4;
+
+	for (i = 0; i < size && blk > dev->radio_rx_rds_last_block;
+			dev->radio_rx_rds_last_block++) {
+		unsigned data_blk = dev->radio_rx_rds_last_block % VIVID_RDS_GEN_BLOCKS;
+		struct v4l2_rds_data rds = data[data_blk];
+
+		if (data_blk == 0 && dev->radio_rds_loop)
+			vivid_radio_rds_init(dev);
+		if (perc && prandom_u32_max(100) < perc) {
+			switch (prandom_u32_max(4)) {
+			case 0:
+				rds.block |= V4L2_RDS_BLOCK_CORRECTED;
+				break;
+			case 1:
+				rds.block |= V4L2_RDS_BLOCK_INVALID;
+				break;
+			case 2:
+				rds.block |= V4L2_RDS_BLOCK_ERROR;
+				rds.lsb = prandom_u32_max(256);
+				rds.msb = prandom_u32_max(256);
+				break;
+			case 3: /* Skip block altogether */
+				if (i)
+					continue;
+				/*
+				 * Must make sure at least one block is
+				 * returned, otherwise the application
+				 * might think that end-of-file occurred.
+				 */
+				break;
+			}
+		}
+		if (copy_to_user(buf + i, &rds, sizeof(rds))) {
+			i = -EFAULT;
+			break;
+		}
+		i += sizeof(rds);
+	}
+	mutex_unlock(&dev->mutex);
+	return i;
+}
+
+unsigned int vivid_radio_rx_poll(struct file *file, struct poll_table_struct *wait)
+{
+	return POLLIN | POLLRDNORM | v4l2_ctrl_poll(file, wait);
+}
+
+int vivid_radio_rx_enum_freq_bands(struct file *file, void *fh, struct v4l2_frequency_band *band)
+{
+	if (band->tuner != 0)
+		return -EINVAL;
+
+	if (band->index >= TOT_BANDS)
+		return -EINVAL;
+
+	*band = vivid_radio_bands[band->index];
+	return 0;
+}
+
+int vivid_radio_rx_s_hw_freq_seek(struct file *file, void *fh, const struct v4l2_hw_freq_seek *a)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	unsigned low, high;
+	unsigned freq;
+	unsigned spacing;
+	unsigned band;
+
+	if (a->tuner)
+		return -EINVAL;
+	if (a->wrap_around && dev->radio_rx_hw_seek_mode == VIVID_HW_SEEK_BOUNDED)
+		return -EINVAL;
+
+	if (!a->wrap_around && dev->radio_rx_hw_seek_mode == VIVID_HW_SEEK_WRAP)
+		return -EINVAL;
+	if (!a->rangelow ^ !a->rangehigh)
+		return -EINVAL;
+
+	if (file->f_flags & O_NONBLOCK)
+		return -EWOULDBLOCK;
+
+	if (a->rangelow) {
+		for (band = 0; band < TOT_BANDS; band++)
+			if (a->rangelow >= vivid_radio_bands[band].rangelow &&
+			    a->rangehigh <= vivid_radio_bands[band].rangehigh)
+				break;
+		if (band == TOT_BANDS)
+			return -EINVAL;
+		if (!dev->radio_rx_hw_seek_prog_lim &&
+		    (a->rangelow != vivid_radio_bands[band].rangelow ||
+		     a->rangehigh != vivid_radio_bands[band].rangehigh))
+			return -EINVAL;
+		low = a->rangelow;
+		high = a->rangehigh;
+	} else {
+		for (band = 0; band < TOT_BANDS; band++)
+			if (dev->radio_rx_freq >= vivid_radio_bands[band].rangelow &&
+			    dev->radio_rx_freq <= vivid_radio_bands[band].rangehigh)
+				break;
+		low = vivid_radio_bands[band].rangelow;
+		high = vivid_radio_bands[band].rangehigh;
+	}
+	spacing = band == BAND_AM ? 1600 : 16000;
+	freq = clamp(dev->radio_rx_freq, low, high);
+
+	if (a->seek_upward) {
+		freq = spacing * (freq / spacing) + spacing;
+		if (freq > high) {
+			if (!a->wrap_around)
+				return -ENODATA;
+			freq = spacing * (low / spacing) + spacing;
+			if (freq >= dev->radio_rx_freq)
+				return -ENODATA;
+		}
+	} else {
+		freq = spacing * ((freq + spacing - 1) / spacing) - spacing;
+		if (freq < low) {
+			if (!a->wrap_around)
+				return -ENODATA;
+			freq = spacing * ((high + spacing - 1) / spacing) - spacing;
+			if (freq <= dev->radio_rx_freq)
+				return -ENODATA;
+		}
+	}
+	return 0;
+}
+
+int vivid_radio_rx_g_tuner(struct file *file, void *fh, struct v4l2_tuner *vt)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	int delta = 800;
+	int sig_qual;
+
+	if (vt->index > 0)
+		return -EINVAL;
+
+	strlcpy(vt->name, "AM/FM/SW Receiver", sizeof(vt->name));
+	vt->capability = V4L2_TUNER_CAP_LOW | V4L2_TUNER_CAP_STEREO |
+			 V4L2_TUNER_CAP_FREQ_BANDS | V4L2_TUNER_CAP_RDS |
+			 (dev->radio_rx_rds_controls ?
+				V4L2_TUNER_CAP_RDS_CONTROLS :
+				V4L2_TUNER_CAP_RDS_BLOCK_IO) |
+			 (dev->radio_rx_hw_seek_prog_lim ?
+				V4L2_TUNER_CAP_HWSEEK_PROG_LIM : 0);
+	switch (dev->radio_rx_hw_seek_mode) {
+	case VIVID_HW_SEEK_BOUNDED:
+		vt->capability |= V4L2_TUNER_CAP_HWSEEK_BOUNDED;
+		break;
+	case VIVID_HW_SEEK_WRAP:
+		vt->capability |= V4L2_TUNER_CAP_HWSEEK_WRAP;
+		break;
+	case VIVID_HW_SEEK_BOTH:
+		vt->capability |= V4L2_TUNER_CAP_HWSEEK_WRAP |
+				  V4L2_TUNER_CAP_HWSEEK_BOUNDED;
+		break;
+	}
+	vt->rangelow = AM_FREQ_RANGE_LOW;
+	vt->rangehigh = FM_FREQ_RANGE_HIGH;
+	sig_qual = dev->radio_rx_sig_qual;
+	vt->signal = abs(sig_qual) > delta ? 0 :
+		     0xffff - (abs(sig_qual) * 0xffff) / delta;
+	vt->afc = sig_qual > delta ? 0 : sig_qual;
+	if (abs(sig_qual) > delta)
+		vt->rxsubchans = 0;
+	else if (dev->radio_rx_freq < FM_FREQ_RANGE_LOW || vt->signal < 0x8000)
+		vt->rxsubchans = V4L2_TUNER_SUB_MONO;
+	else if (dev->radio_rds_loop && !(dev->radio_tx_subchans & V4L2_TUNER_SUB_STEREO))
+		vt->rxsubchans = V4L2_TUNER_SUB_MONO;
+	else
+		vt->rxsubchans = V4L2_TUNER_SUB_STEREO;
+	if (dev->radio_rx_rds_enabled &&
+	    (!dev->radio_rds_loop || (dev->radio_tx_subchans & V4L2_TUNER_SUB_RDS)) &&
+	    dev->radio_rx_freq >= FM_FREQ_RANGE_LOW && vt->signal >= 0xc000)
+		vt->rxsubchans |= V4L2_TUNER_SUB_RDS;
+	if (dev->radio_rx_rds_controls)
+		vivid_radio_rds_init(dev);
+	vt->audmode = dev->radio_rx_audmode;
+	return 0;
+}
+
+int vivid_radio_rx_s_tuner(struct file *file, void *fh, const struct v4l2_tuner *vt)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (vt->index)
+		return -EINVAL;
+	dev->radio_rx_audmode = vt->audmode >= V4L2_TUNER_MODE_STEREO;
+	return 0;
+}
diff --git a/drivers/media/platform/vivid/vivid-radio-rx.h b/drivers/media/platform/vivid/vivid-radio-rx.h
new file mode 100644
index 000000000000..1077d8f061eb
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-radio-rx.h
@@ -0,0 +1,31 @@
+/*
+ * vivid-radio-rx.h - radio receiver support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_RADIO_RX_H_
+#define _VIVID_RADIO_RX_H_
+
+ssize_t vivid_radio_rx_read(struct file *, char __user *, size_t, loff_t *);
+unsigned int vivid_radio_rx_poll(struct file *file, struct poll_table_struct *wait);
+
+int vivid_radio_rx_enum_freq_bands(struct file *file, void *fh, struct v4l2_frequency_band *band);
+int vivid_radio_rx_s_hw_freq_seek(struct file *file, void *fh, const struct v4l2_hw_freq_seek *a);
+int vivid_radio_rx_g_tuner(struct file *file, void *fh, struct v4l2_tuner *vt);
+int vivid_radio_rx_s_tuner(struct file *file, void *fh, const struct v4l2_tuner *vt);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-radio-tx.c b/drivers/media/platform/vivid/vivid-radio-tx.c
new file mode 100644
index 000000000000..8c59d4f53200
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-radio-tx.c
@@ -0,0 +1,141 @@
+/*
+ * vivid-radio-tx.c - radio transmitter support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/videodev2.h>
+#include <linux/v4l2-dv-timings.h>
+#include <media/v4l2-common.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-dv-timings.h>
+
+#include "vivid-core.h"
+#include "vivid-ctrls.h"
+#include "vivid-radio-common.h"
+#include "vivid-radio-tx.h"
+
+ssize_t vivid_radio_tx_write(struct file *file, const char __user *buf,
+			  size_t size, loff_t *offset)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_rds_data *data = dev->rds_gen.data;
+	struct timespec ts;
+	unsigned blk;
+	int i;
+
+	if (dev->radio_tx_rds_controls)
+		return -EINVAL;
+
+	if (size < sizeof(*data))
+		return -EINVAL;
+	size = sizeof(*data) * (size / sizeof(*data));
+
+	if (mutex_lock_interruptible(&dev->mutex))
+		return -ERESTARTSYS;
+	if (dev->radio_tx_rds_owner &&
+	    file->private_data != dev->radio_tx_rds_owner) {
+		mutex_unlock(&dev->mutex);
+		return -EBUSY;
+	}
+	dev->radio_tx_rds_owner = file->private_data;
+
+retry:
+	ktime_get_ts(&ts);
+	ts = timespec_sub(ts, dev->radio_rds_init_ts);
+	blk = ts.tv_sec * 100 + ts.tv_nsec / 10000000;
+	blk = (blk * VIVID_RDS_GEN_BLOCKS) / 500;
+	if (blk - VIVID_RDS_GEN_BLOCKS >= dev->radio_tx_rds_last_block)
+		dev->radio_tx_rds_last_block = blk - VIVID_RDS_GEN_BLOCKS + 1;
+
+	/*
+	 * No data is available if there hasn't been time to get new data,
+	 * or if the RDS receiver has been disabled, or if we use the data
+	 * from the RDS transmitter and that RDS transmitter has been disabled,
+	 * or if the signal quality is too weak.
+	 */
+	if (blk == dev->radio_tx_rds_last_block ||
+	    !(dev->radio_tx_subchans & V4L2_TUNER_SUB_RDS)) {
+		mutex_unlock(&dev->mutex);
+		if (file->f_flags & O_NONBLOCK)
+			return -EWOULDBLOCK;
+		if (msleep_interruptible(20) && signal_pending(current))
+			return -EINTR;
+		if (mutex_lock_interruptible(&dev->mutex))
+			return -ERESTARTSYS;
+		goto retry;
+	}
+
+	for (i = 0; i < size && blk > dev->radio_tx_rds_last_block;
+			dev->radio_tx_rds_last_block++) {
+		unsigned data_blk = dev->radio_tx_rds_last_block % VIVID_RDS_GEN_BLOCKS;
+		struct v4l2_rds_data rds;
+
+		if (copy_from_user(&rds, buf + i, sizeof(rds))) {
+			i = -EFAULT;
+			break;
+		}
+		i += sizeof(rds);
+		if (!dev->radio_rds_loop)
+			continue;
+		if ((rds.block & V4L2_RDS_BLOCK_MSK) == V4L2_RDS_BLOCK_INVALID ||
+		    (rds.block & V4L2_RDS_BLOCK_ERROR))
+			continue;
+		rds.block &= V4L2_RDS_BLOCK_MSK;
+		data[data_blk] = rds;
+	}
+	mutex_unlock(&dev->mutex);
+	return i;
+}
+
+unsigned int vivid_radio_tx_poll(struct file *file, struct poll_table_struct *wait)
+{
+	return POLLOUT | POLLWRNORM | v4l2_ctrl_poll(file, wait);
+}
+
+int vidioc_g_modulator(struct file *file, void *fh, struct v4l2_modulator *a)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (a->index > 0)
+		return -EINVAL;
+
+	strlcpy(a->name, "AM/FM/SW Transmitter", sizeof(a->name));
+	a->capability = V4L2_TUNER_CAP_LOW | V4L2_TUNER_CAP_STEREO |
+			V4L2_TUNER_CAP_FREQ_BANDS | V4L2_TUNER_CAP_RDS |
+			(dev->radio_tx_rds_controls ?
+				V4L2_TUNER_CAP_RDS_CONTROLS :
+				V4L2_TUNER_CAP_RDS_BLOCK_IO);
+	a->rangelow = AM_FREQ_RANGE_LOW;
+	a->rangehigh = FM_FREQ_RANGE_HIGH;
+	a->txsubchans = dev->radio_tx_subchans;
+	return 0;
+}
+
+int vidioc_s_modulator(struct file *file, void *fh, const struct v4l2_modulator *a)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (a->index)
+		return -EINVAL;
+	if (a->txsubchans & ~0x13)
+		return -EINVAL;
+	dev->radio_tx_subchans = a->txsubchans;
+	return 0;
+}
diff --git a/drivers/media/platform/vivid/vivid-radio-tx.h b/drivers/media/platform/vivid/vivid-radio-tx.h
new file mode 100644
index 000000000000..7f8ff7547119
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-radio-tx.h
@@ -0,0 +1,29 @@
+/*
+ * vivid-radio-tx.h - radio transmitter support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_RADIO_TX_H_
+#define _VIVID_RADIO_TX_H_
+
+ssize_t vivid_radio_tx_write(struct file *, const char __user *, size_t, loff_t *);
+unsigned int vivid_radio_tx_poll(struct file *file, struct poll_table_struct *wait);
+
+int vidioc_g_modulator(struct file *file, void *fh, struct v4l2_modulator *a);
+int vidioc_s_modulator(struct file *file, void *fh, const struct v4l2_modulator *a);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-rds-gen.c b/drivers/media/platform/vivid/vivid-rds-gen.c
new file mode 100644
index 000000000000..c382343fdb66
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-rds-gen.c
@@ -0,0 +1,166 @@
+/*
+ * vivid-rds-gen.c - rds (radio data system) generator support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/ktime.h>
+#include <linux/string.h>
+#include <linux/videodev2.h>
+
+#include "vivid-rds-gen.h"
+
+static u8 vivid_get_di(const struct vivid_rds_gen *rds, unsigned grp)
+{
+	switch (grp) {
+	case 0:
+		return (rds->dyn_pty << 2) | (grp & 3);
+	case 1:
+		return (rds->compressed << 2) | (grp & 3);
+	case 2:
+		return (rds->art_head << 2) | (grp & 3);
+	case 3:
+		return (rds->mono_stereo << 2) | (grp & 3);
+	}
+	return 0;
+}
+
+/*
+ * This RDS generator creates 57 RDS groups (one group == four RDS blocks).
+ * Groups 0-3, 22-25 and 44-47 (spaced 22 groups apart) are filled with a
+ * standard 0B group containing the PI code and PS name.
+ *
+ * Groups 4-19 and 26-41 use group 2A for the radio text.
+ *
+ * Group 56 contains the time (group 4A).
+ *
+ * All remaining groups use a filler group 15B block that just repeats
+ * the PI and PTY codes.
+ */
+void vivid_rds_generate(struct vivid_rds_gen *rds)
+{
+	struct v4l2_rds_data *data = rds->data;
+	unsigned grp;
+	struct tm tm;
+	unsigned date;
+	unsigned time;
+	int l;
+
+	for (grp = 0; grp < VIVID_RDS_GEN_GROUPS; grp++, data += VIVID_RDS_GEN_BLKS_PER_GRP) {
+		data[0].lsb = rds->picode & 0xff;
+		data[0].msb = rds->picode >> 8;
+		data[0].block = V4L2_RDS_BLOCK_A | (V4L2_RDS_BLOCK_A << 3);
+		data[1].lsb = rds->pty << 5;
+		data[1].msb = (rds->pty >> 3) | (rds->tp << 2);
+		data[1].block = V4L2_RDS_BLOCK_B | (V4L2_RDS_BLOCK_B << 3);
+		data[3].block = V4L2_RDS_BLOCK_D | (V4L2_RDS_BLOCK_D << 3);
+
+		switch (grp) {
+		case 0 ... 3:
+		case 22 ... 25:
+		case 44 ... 47: /* Group 0B */
+			data[1].lsb |= (rds->ta << 4) | (rds->ms << 3);
+			data[1].lsb |= vivid_get_di(rds, grp % 22);
+			data[1].msb |= 1 << 3;
+			data[2].lsb = rds->picode & 0xff;
+			data[2].msb = rds->picode >> 8;
+			data[2].block = V4L2_RDS_BLOCK_C_ALT | (V4L2_RDS_BLOCK_C_ALT << 3);
+			data[3].lsb = rds->psname[2 * (grp % 22) + 1];
+			data[3].msb = rds->psname[2 * (grp % 22)];
+			break;
+		case 4 ... 19:
+		case 26 ... 41: /* Group 2A */
+			data[1].lsb |= (grp - 4) % 22;
+			data[1].msb |= 4 << 3;
+			data[2].msb = rds->radiotext[4 * ((grp - 4) % 22)];
+			data[2].lsb = rds->radiotext[4 * ((grp - 4) % 22) + 1];
+			data[2].block = V4L2_RDS_BLOCK_C | (V4L2_RDS_BLOCK_C << 3);
+			data[3].msb = rds->radiotext[4 * ((grp - 4) % 22) + 2];
+			data[3].lsb = rds->radiotext[4 * ((grp - 4) % 22) + 3];
+			break;
+		case 56:
+			/*
+			 * Group 4A
+			 *
+			 * Uses the algorithm from Annex G of the RDS standard
+			 * EN 50067:1998 to convert a UTC date to an RDS Modified
+			 * Julian Day.
+			 */
+			time_to_tm(get_seconds(), 0, &tm);
+			l = tm.tm_mon <= 1;
+			date = 14956 + tm.tm_mday + ((tm.tm_year - l) * 1461) / 4 +
+				((tm.tm_mon + 2 + l * 12) * 306001) / 10000;
+			time = (tm.tm_hour << 12) |
+			       (tm.tm_min << 6) |
+			       (sys_tz.tz_minuteswest >= 0 ? 0x20 : 0) |
+			       (abs(sys_tz.tz_minuteswest) / 30);
+			data[1].lsb &= ~3;
+			data[1].lsb |= date >> 15;
+			data[1].msb |= 8 << 3;
+			data[2].lsb = (date << 1) & 0xfe;
+			data[2].lsb |= (time >> 16) & 1;
+			data[2].msb = (date >> 7) & 0xff;
+			data[2].block = V4L2_RDS_BLOCK_C | (V4L2_RDS_BLOCK_C << 3);
+			data[3].lsb = time & 0xff;
+			data[3].msb = (time >> 8) & 0xff;
+			break;
+		default: /* Group 15B */
+			data[1].lsb |= (rds->ta << 4) | (rds->ms << 3);
+			data[1].lsb |= vivid_get_di(rds, grp % 22);
+			data[1].msb |= 0x1f << 3;
+			data[2].lsb = rds->picode & 0xff;
+			data[2].msb = rds->picode >> 8;
+			data[2].block = V4L2_RDS_BLOCK_C_ALT | (V4L2_RDS_BLOCK_C_ALT << 3);
+			data[3].lsb = rds->pty << 5;
+			data[3].lsb |= (rds->ta << 4) | (rds->ms << 3);
+			data[3].lsb |= vivid_get_di(rds, grp % 22);
+			data[3].msb |= rds->pty >> 3;
+			data[3].msb |= 0x1f << 3;
+			break;
+		}
+	}
+}
+
+void vivid_rds_gen_fill(struct vivid_rds_gen *rds, unsigned freq,
+			  bool alt)
+{
+	/* Alternate PTY between Info and Weather */
+	if (rds->use_rbds) {
+		rds->picode = 0x2e75; /* 'KLNX' call sign */
+		rds->pty = alt ? 29 : 2;
+	} else {
+		rds->picode = 0x8088;
+		rds->pty = alt ? 16 : 3;
+	}
+	rds->mono_stereo = true;
+	rds->art_head = false;
+	rds->compressed = false;
+	rds->dyn_pty = false;
+	rds->tp = true;
+	rds->ta = alt;
+	rds->ms = true;
+	snprintf(rds->psname, sizeof(rds->psname), "%6d.%1d",
+		 freq / 16, ((freq & 0xf) * 10) / 16);
+	if (alt)
+		strlcpy(rds->radiotext,
+			" The Radio Data System can switch between different Radio Texts ",
+			sizeof(rds->radiotext));
+	else
+		strlcpy(rds->radiotext,
+			"An example of Radio Text as transmitted by the Radio Data System",
+			sizeof(rds->radiotext));
+}
diff --git a/drivers/media/platform/vivid/vivid-rds-gen.h b/drivers/media/platform/vivid/vivid-rds-gen.h
new file mode 100644
index 000000000000..eff4bf552ed3
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-rds-gen.h
@@ -0,0 +1,53 @@
+/*
+ * vivid-rds-gen.h - rds (radio data system) generator support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_RDS_GEN_H_
+#define _VIVID_RDS_GEN_H_
+
+/*
+ * It takes almost exactly 5 seconds to transmit 57 RDS groups.
+ * Each group has 4 blocks and each block has a payload of 16 bits + a
+ * block identification. The driver will generate the contents of these
+ * 57 groups only when necessary and it will just be played continuously.
+ */
+#define VIVID_RDS_GEN_GROUPS 57
+#define VIVID_RDS_GEN_BLKS_PER_GRP 4
+#define VIVID_RDS_GEN_BLOCKS (VIVID_RDS_GEN_BLKS_PER_GRP * VIVID_RDS_GEN_GROUPS)
+
+struct vivid_rds_gen {
+	struct v4l2_rds_data	data[VIVID_RDS_GEN_BLOCKS];
+	bool			use_rbds;
+	u16			picode;
+	u8			pty;
+	bool			mono_stereo;
+	bool			art_head;
+	bool			compressed;
+	bool			dyn_pty;
+	bool			ta;
+	bool			tp;
+	bool			ms;
+	char			psname[8 + 1];
+	char			radiotext[64 + 1];
+};
+
+void vivid_rds_gen_fill(struct vivid_rds_gen *rds, unsigned freq,
+		    bool use_alternate);
+void vivid_rds_generate(struct vivid_rds_gen *rds);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-sdr-cap.c b/drivers/media/platform/vivid/vivid-sdr-cap.c
new file mode 100644
index 000000000000..8c5d661cfc49
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-sdr-cap.c
@@ -0,0 +1,499 @@
+/*
+ * vivid-sdr-cap.c - software defined radio support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/videodev2.h>
+#include <linux/v4l2-dv-timings.h>
+#include <media/v4l2-common.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-dv-timings.h>
+
+#include "vivid-core.h"
+#include "vivid-ctrls.h"
+#include "vivid-sdr-cap.h"
+
+static const struct v4l2_frequency_band bands_adc[] = {
+	{
+		.tuner = 0,
+		.type = V4L2_TUNER_ADC,
+		.index = 0,
+		.capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS,
+		.rangelow   =  300000,
+		.rangehigh  =  300000,
+	},
+	{
+		.tuner = 0,
+		.type = V4L2_TUNER_ADC,
+		.index = 1,
+		.capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS,
+		.rangelow   =  900001,
+		.rangehigh  = 2800000,
+	},
+	{
+		.tuner = 0,
+		.type = V4L2_TUNER_ADC,
+		.index = 2,
+		.capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS,
+		.rangelow   = 3200000,
+		.rangehigh  = 3200000,
+	},
+};
+
+/* ADC band midpoints */
+#define BAND_ADC_0 ((bands_adc[0].rangehigh + bands_adc[1].rangelow) / 2)
+#define BAND_ADC_1 ((bands_adc[1].rangehigh + bands_adc[2].rangelow) / 2)
+
+static const struct v4l2_frequency_band bands_fm[] = {
+	{
+		.tuner = 1,
+		.type = V4L2_TUNER_RF,
+		.index = 0,
+		.capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS,
+		.rangelow   =    50000000,
+		.rangehigh  =  2000000000,
+	},
+};
+
+static void vivid_thread_sdr_cap_tick(struct vivid_dev *dev)
+{
+	struct vivid_buffer *sdr_cap_buf = NULL;
+
+	dprintk(dev, 1, "SDR Capture Thread Tick\n");
+
+	/* Drop a certain percentage of buffers. */
+	if (dev->perc_dropped_buffers &&
+	    prandom_u32_max(100) < dev->perc_dropped_buffers)
+		return;
+
+	spin_lock(&dev->slock);
+	if (!list_empty(&dev->sdr_cap_active)) {
+		sdr_cap_buf = list_entry(dev->sdr_cap_active.next,
+					 struct vivid_buffer, list);
+		list_del(&sdr_cap_buf->list);
+	}
+	spin_unlock(&dev->slock);
+
+	if (sdr_cap_buf) {
+		sdr_cap_buf->vb.v4l2_buf.sequence = dev->sdr_cap_seq_count;
+		vivid_sdr_cap_process(dev, sdr_cap_buf);
+		v4l2_get_timestamp(&sdr_cap_buf->vb.v4l2_buf.timestamp);
+		sdr_cap_buf->vb.v4l2_buf.timestamp.tv_sec += dev->time_wrap_offset;
+		vb2_buffer_done(&sdr_cap_buf->vb, dev->dqbuf_error ?
+				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
+		dev->dqbuf_error = false;
+	}
+}
+
+static int vivid_thread_sdr_cap(void *data)
+{
+	struct vivid_dev *dev = data;
+	u64 samples_since_start;
+	u64 buffers_since_start;
+	u64 next_jiffies_since_start;
+	unsigned long jiffies_since_start;
+	unsigned long cur_jiffies;
+	unsigned wait_jiffies;
+
+	dprintk(dev, 1, "SDR Capture Thread Start\n");
+
+	set_freezable();
+
+	/* Resets frame counters */
+	dev->sdr_cap_seq_offset = 0;
+	if (dev->seq_wrap)
+		dev->sdr_cap_seq_offset = 0xffffff80U;
+	dev->jiffies_sdr_cap = jiffies;
+	dev->sdr_cap_seq_resync = false;
+
+	for (;;) {
+		try_to_freeze();
+		if (kthread_should_stop())
+			break;
+
+		mutex_lock(&dev->mutex);
+		cur_jiffies = jiffies;
+		if (dev->sdr_cap_seq_resync) {
+			dev->jiffies_sdr_cap = cur_jiffies;
+			dev->sdr_cap_seq_offset = dev->sdr_cap_seq_count + 1;
+			dev->sdr_cap_seq_count = 0;
+			dev->sdr_cap_seq_resync = false;
+		}
+		/* Calculate the number of jiffies since we started streaming */
+		jiffies_since_start = cur_jiffies - dev->jiffies_sdr_cap;
+		/* Get the number of buffers streamed since the start */
+		buffers_since_start = (u64)jiffies_since_start * dev->sdr_adc_freq +
+				      (HZ * SDR_CAP_SAMPLES_PER_BUF) / 2;
+		do_div(buffers_since_start, HZ * SDR_CAP_SAMPLES_PER_BUF);
+
+		/*
+		 * After more than 0xf0000000 (rounded down to a multiple of
+		 * 'jiffies-per-day' to ease jiffies_to_msecs calculation)
+		 * jiffies have passed since we started streaming reset the
+		 * counters and keep track of the sequence offset.
+		 */
+		if (jiffies_since_start > JIFFIES_RESYNC) {
+			dev->jiffies_sdr_cap = cur_jiffies;
+			dev->sdr_cap_seq_offset = buffers_since_start;
+			buffers_since_start = 0;
+		}
+		dev->sdr_cap_seq_count = buffers_since_start + dev->sdr_cap_seq_offset;
+
+		vivid_thread_sdr_cap_tick(dev);
+		mutex_unlock(&dev->mutex);
+
+		/*
+		 * Calculate the number of samples streamed since we started,
+		 * not including the current buffer.
+		 */
+		samples_since_start = buffers_since_start * SDR_CAP_SAMPLES_PER_BUF;
+
+		/* And the number of jiffies since we started */
+		jiffies_since_start = jiffies - dev->jiffies_sdr_cap;
+
+		/* Increase by the number of samples in one buffer */
+		samples_since_start += SDR_CAP_SAMPLES_PER_BUF;
+		/*
+		 * Calculate when that next buffer is supposed to start
+		 * in jiffies since we started streaming.
+		 */
+		next_jiffies_since_start = samples_since_start * HZ +
+					   dev->sdr_adc_freq / 2;
+		do_div(next_jiffies_since_start, dev->sdr_adc_freq);
+		/* If it is in the past, then just schedule asap */
+		if (next_jiffies_since_start < jiffies_since_start)
+			next_jiffies_since_start = jiffies_since_start;
+
+		wait_jiffies = next_jiffies_since_start - jiffies_since_start;
+		schedule_timeout_interruptible(wait_jiffies ? wait_jiffies : 1);
+	}
+	dprintk(dev, 1, "SDR Capture Thread End\n");
+	return 0;
+}
+
+static int sdr_cap_queue_setup(struct vb2_queue *vq, const struct v4l2_format *fmt,
+		       unsigned *nbuffers, unsigned *nplanes,
+		       unsigned sizes[], void *alloc_ctxs[])
+{
+	/* 2 = max 16-bit sample returned */
+	sizes[0] = SDR_CAP_SAMPLES_PER_BUF * 2;
+	*nplanes = 1;
+	return 0;
+}
+
+static int sdr_cap_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	unsigned size = SDR_CAP_SAMPLES_PER_BUF * 2;
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	if (dev->buf_prepare_error) {
+		/*
+		 * Error injection: test what happens if buf_prepare() returns
+		 * an error.
+		 */
+		dev->buf_prepare_error = false;
+		return -EINVAL;
+	}
+	if (vb2_plane_size(vb, 0) < size) {
+		dprintk(dev, 1, "%s data will not fit into plane (%lu < %u)\n",
+				__func__, vb2_plane_size(vb, 0), size);
+		return -EINVAL;
+	}
+	vb2_set_plane_payload(vb, 0, size);
+
+	return 0;
+}
+
+static void sdr_cap_buf_queue(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct vivid_buffer *buf = container_of(vb, struct vivid_buffer, vb);
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	spin_lock(&dev->slock);
+	list_add_tail(&buf->list, &dev->sdr_cap_active);
+	spin_unlock(&dev->slock);
+}
+
+static int sdr_cap_start_streaming(struct vb2_queue *vq, unsigned count)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	int err = 0;
+
+	dprintk(dev, 1, "%s\n", __func__);
+	dev->sdr_cap_seq_count = 0;
+	if (dev->start_streaming_error) {
+		dev->start_streaming_error = false;
+		err = -EINVAL;
+	} else if (dev->kthread_sdr_cap == NULL) {
+		dev->kthread_sdr_cap = kthread_run(vivid_thread_sdr_cap, dev,
+				"%s-sdr-cap", dev->v4l2_dev.name);
+
+		if (IS_ERR(dev->kthread_sdr_cap)) {
+			v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n");
+			err = PTR_ERR(dev->kthread_sdr_cap);
+			dev->kthread_sdr_cap = NULL;
+		}
+	}
+	if (err) {
+		struct vivid_buffer *buf, *tmp;
+
+		list_for_each_entry_safe(buf, tmp, &dev->sdr_cap_active, list) {
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
+		}
+	}
+	return err;
+}
+
+/* abort streaming and wait for last buffer */
+static void sdr_cap_stop_streaming(struct vb2_queue *vq)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+
+	if (dev->kthread_sdr_cap == NULL)
+		return;
+
+	while (!list_empty(&dev->sdr_cap_active)) {
+		struct vivid_buffer *buf;
+
+		buf = list_entry(dev->sdr_cap_active.next, struct vivid_buffer, list);
+		list_del(&buf->list);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+	}
+
+	/* shutdown control thread */
+	mutex_unlock(&dev->mutex);
+	kthread_stop(dev->kthread_sdr_cap);
+	dev->kthread_sdr_cap = NULL;
+	mutex_lock(&dev->mutex);
+}
+
+const struct vb2_ops vivid_sdr_cap_qops = {
+	.queue_setup		= sdr_cap_queue_setup,
+	.buf_prepare		= sdr_cap_buf_prepare,
+	.buf_queue		= sdr_cap_buf_queue,
+	.start_streaming	= sdr_cap_start_streaming,
+	.stop_streaming		= sdr_cap_stop_streaming,
+	.wait_prepare		= vivid_unlock,
+	.wait_finish		= vivid_lock,
+};
+
+int vivid_sdr_enum_freq_bands(struct file *file, void *fh, struct v4l2_frequency_band *band)
+{
+	switch (band->tuner) {
+	case 0:
+		if (band->index >= ARRAY_SIZE(bands_adc))
+			return -EINVAL;
+		*band = bands_adc[band->index];
+		return 0;
+	case 1:
+		if (band->index >= ARRAY_SIZE(bands_fm))
+			return -EINVAL;
+		*band = bands_fm[band->index];
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+int vivid_sdr_g_frequency(struct file *file, void *fh, struct v4l2_frequency *vf)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	switch (vf->tuner) {
+	case 0:
+		vf->frequency = dev->sdr_adc_freq;
+		vf->type = V4L2_TUNER_ADC;
+		return 0;
+	case 1:
+		vf->frequency = dev->sdr_fm_freq;
+		vf->type = V4L2_TUNER_RF;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+int vivid_sdr_s_frequency(struct file *file, void *fh, const struct v4l2_frequency *vf)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	unsigned freq = vf->frequency;
+	unsigned band;
+
+	switch (vf->tuner) {
+	case 0:
+		if (vf->type != V4L2_TUNER_ADC)
+			return -EINVAL;
+		if (freq < BAND_ADC_0)
+			band = 0;
+		else if (freq < BAND_ADC_1)
+			band = 1;
+		else
+			band = 2;
+
+		freq = clamp_t(unsigned, freq,
+				bands_adc[band].rangelow,
+				bands_adc[band].rangehigh);
+
+		if (vb2_is_streaming(&dev->vb_sdr_cap_q) &&
+		    freq != dev->sdr_adc_freq) {
+			/* resync the thread's timings */
+			dev->sdr_cap_seq_resync = true;
+		}
+		dev->sdr_adc_freq = freq;
+		return 0;
+	case 1:
+		if (vf->type != V4L2_TUNER_RF)
+			return -EINVAL;
+		dev->sdr_fm_freq = clamp_t(unsigned, freq,
+				bands_fm[0].rangelow,
+				bands_fm[0].rangehigh);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+int vivid_sdr_g_tuner(struct file *file, void *fh, struct v4l2_tuner *vt)
+{
+	switch (vt->index) {
+	case 0:
+		strlcpy(vt->name, "ADC", sizeof(vt->name));
+		vt->type = V4L2_TUNER_ADC;
+		vt->capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS;
+		vt->rangelow = bands_adc[0].rangelow;
+		vt->rangehigh = bands_adc[2].rangehigh;
+		return 0;
+	case 1:
+		strlcpy(vt->name, "RF", sizeof(vt->name));
+		vt->type = V4L2_TUNER_RF;
+		vt->capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS;
+		vt->rangelow = bands_fm[0].rangelow;
+		vt->rangehigh = bands_fm[0].rangehigh;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+int vivid_sdr_s_tuner(struct file *file, void *fh, const struct v4l2_tuner *vt)
+{
+	if (vt->index > 1)
+		return -EINVAL;
+	return 0;
+}
+
+int vidioc_enum_fmt_sdr_cap(struct file *file, void *fh, struct v4l2_fmtdesc *f)
+{
+	if (f->index)
+		return -EINVAL;
+	f->pixelformat = V4L2_SDR_FMT_CU8;
+	strlcpy(f->description, "IQ U8", sizeof(f->description));
+	return 0;
+}
+
+int vidioc_g_fmt_sdr_cap(struct file *file, void *fh, struct v4l2_format *f)
+{
+	f->fmt.sdr.pixelformat = V4L2_SDR_FMT_CU8;
+	f->fmt.sdr.buffersize = SDR_CAP_SAMPLES_PER_BUF * 2;
+	memset(f->fmt.sdr.reserved, 0, sizeof(f->fmt.sdr.reserved));
+	return 0;
+}
+
+#define FIXP_FRAC    (1 << 15)
+#define FIXP_PI      ((int)(FIXP_FRAC * 3.141592653589))
+
+/* cos() from cx88 driver: cx88-dsp.c */
+static s32 fixp_cos(unsigned int x)
+{
+	u32 t2, t4, t6, t8;
+	u16 period = x / FIXP_PI;
+
+	if (period % 2)
+		return -fixp_cos(x - FIXP_PI);
+	x = x % FIXP_PI;
+	if (x > FIXP_PI/2)
+		return -fixp_cos(FIXP_PI/2 - (x % (FIXP_PI/2)));
+	/* Now x is between 0 and FIXP_PI/2.
+	 * To calculate cos(x) we use it's Taylor polinom. */
+	t2 = x*x/FIXP_FRAC/2;
+	t4 = t2*x/FIXP_FRAC*x/FIXP_FRAC/3/4;
+	t6 = t4*x/FIXP_FRAC*x/FIXP_FRAC/5/6;
+	t8 = t6*x/FIXP_FRAC*x/FIXP_FRAC/7/8;
+	return FIXP_FRAC-t2+t4-t6+t8;
+}
+
+static inline s32 fixp_sin(unsigned int x)
+{
+	return -fixp_cos(x + (FIXP_PI / 2));
+}
+
+void vivid_sdr_cap_process(struct vivid_dev *dev, struct vivid_buffer *buf)
+{
+	u8 *vbuf = vb2_plane_vaddr(&buf->vb, 0);
+	unsigned long i;
+	unsigned long plane_size = vb2_plane_size(&buf->vb, 0);
+	int fixp_src_phase_step, fixp_i, fixp_q;
+
+	/*
+	 * TODO: Generated beep tone goes very crackly when sample rate is
+	 * increased to ~1Msps or more. That is because of huge rounding error
+	 * of phase angle caused by used cosine implementation.
+	 */
+
+	/* calculate phase step */
+	#define BEEP_FREQ 1000 /* 1kHz beep */
+	fixp_src_phase_step = DIV_ROUND_CLOSEST(2 * FIXP_PI * BEEP_FREQ,
+			dev->sdr_adc_freq);
+
+	for (i = 0; i < plane_size; i += 2) {
+		dev->sdr_fixp_mod_phase += fixp_cos(dev->sdr_fixp_src_phase);
+		dev->sdr_fixp_src_phase += fixp_src_phase_step;
+
+		/*
+		 * Transfer phases to [0 / 2xPI] in order to avoid variable
+		 * overflow and make it suitable for cosine implementation
+		 * used, which does not support negative angles.
+		 */
+		while (dev->sdr_fixp_mod_phase < (0 * FIXP_PI))
+			dev->sdr_fixp_mod_phase += (2 * FIXP_PI);
+		while (dev->sdr_fixp_mod_phase > (2 * FIXP_PI))
+			dev->sdr_fixp_mod_phase -= (2 * FIXP_PI);
+
+		while (dev->sdr_fixp_src_phase > (2 * FIXP_PI))
+			dev->sdr_fixp_src_phase -= (2 * FIXP_PI);
+
+		fixp_i = fixp_cos(dev->sdr_fixp_mod_phase);
+		fixp_q = fixp_sin(dev->sdr_fixp_mod_phase);
+
+		/* convert 'fixp float' to u8 */
+		/* u8 = X * 127.5f + 127.5f; where X is float [-1.0 / +1.0] */
+		fixp_i = fixp_i * 1275 + FIXP_FRAC * 1275;
+		fixp_q = fixp_q * 1275 + FIXP_FRAC * 1275;
+		*vbuf++ = DIV_ROUND_CLOSEST(fixp_i, FIXP_FRAC * 10);
+		*vbuf++ = DIV_ROUND_CLOSEST(fixp_q, FIXP_FRAC * 10);
+	}
+}
diff --git a/drivers/media/platform/vivid/vivid-sdr-cap.h b/drivers/media/platform/vivid/vivid-sdr-cap.h
new file mode 100644
index 000000000000..79c1890de972
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-sdr-cap.h
@@ -0,0 +1,34 @@
+/*
+ * vivid-sdr-cap.h - software defined radio support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_SDR_CAP_H_
+#define _VIVID_SDR_CAP_H_
+
+int vivid_sdr_enum_freq_bands(struct file *file, void *fh, struct v4l2_frequency_band *band);
+int vivid_sdr_g_frequency(struct file *file, void *fh, struct v4l2_frequency *vf);
+int vivid_sdr_s_frequency(struct file *file, void *fh, const struct v4l2_frequency *vf);
+int vivid_sdr_g_tuner(struct file *file, void *fh, struct v4l2_tuner *vt);
+int vivid_sdr_s_tuner(struct file *file, void *fh, const struct v4l2_tuner *vt);
+int vidioc_enum_fmt_sdr_cap(struct file *file, void *fh, struct v4l2_fmtdesc *f);
+int vidioc_g_fmt_sdr_cap(struct file *file, void *fh, struct v4l2_format *f);
+void vivid_sdr_cap_process(struct vivid_dev *dev, struct vivid_buffer *buf);
+
+extern const struct vb2_ops vivid_sdr_cap_qops;
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-tpg-colors.c b/drivers/media/platform/vivid/vivid-tpg-colors.c
new file mode 100644
index 000000000000..2adddc0ca662
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-tpg-colors.c
@@ -0,0 +1,310 @@
+/*
+ * vivid-color.c - A table that converts colors to various colorspaces
+ *
+ * The test pattern generator uses the tpg_colors for its test patterns.
+ * For testing colorspaces the first 8 colors of that table need to be
+ * converted to their equivalent in the target colorspace.
+ *
+ * The tpg_csc_colors[] table is the result of that conversion and since
+ * it is precalculated the colorspace conversion is just a simple table
+ * lookup.
+ *
+ * This source also contains the code used to generate the tpg_csc_colors
+ * table. Run the following command to compile it:
+ *
+ *	gcc vivid-colors.c -DCOMPILE_APP -o gen-colors -lm
+ *
+ * and run the utility.
+ *
+ * Note that the converted colors are in the range 0x000-0xff0 (so times 16)
+ * in order to preserve precision.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/videodev2.h>
+
+#include "vivid-tpg-colors.h"
+
+/* sRGB colors with range [0-255] */
+const struct color tpg_colors[TPG_COLOR_MAX] = {
+	/*
+	 * Colors to test colorspace conversion: converting these colors
+	 * to other colorspaces will never lead to out-of-gamut colors.
+	 */
+	{ 191, 191, 191 }, /* TPG_COLOR_CSC_WHITE */
+	{ 191, 191,  50 }, /* TPG_COLOR_CSC_YELLOW */
+	{  50, 191, 191 }, /* TPG_COLOR_CSC_CYAN */
+	{  50, 191,  50 }, /* TPG_COLOR_CSC_GREEN */
+	{ 191,  50, 191 }, /* TPG_COLOR_CSC_MAGENTA */
+	{ 191,  50,  50 }, /* TPG_COLOR_CSC_RED */
+	{  50,  50, 191 }, /* TPG_COLOR_CSC_BLUE */
+	{  50,  50,  50 }, /* TPG_COLOR_CSC_BLACK */
+
+	/* 75% colors */
+	{ 191, 191,   0 }, /* TPG_COLOR_75_YELLOW */
+	{   0, 191, 191 }, /* TPG_COLOR_75_CYAN */
+	{   0, 191,   0 }, /* TPG_COLOR_75_GREEN */
+	{ 191,   0, 191 }, /* TPG_COLOR_75_MAGENTA */
+	{ 191,   0,   0 }, /* TPG_COLOR_75_RED */
+	{   0,   0, 191 }, /* TPG_COLOR_75_BLUE */
+
+	/* 100% colors */
+	{ 255, 255, 255 }, /* TPG_COLOR_100_WHITE */
+	{ 255, 255,   0 }, /* TPG_COLOR_100_YELLOW */
+	{   0, 255, 255 }, /* TPG_COLOR_100_CYAN */
+	{   0, 255,   0 }, /* TPG_COLOR_100_GREEN */
+	{ 255,   0, 255 }, /* TPG_COLOR_100_MAGENTA */
+	{ 255,   0,   0 }, /* TPG_COLOR_100_RED */
+	{   0,   0, 255 }, /* TPG_COLOR_100_BLUE */
+	{   0,   0,   0 }, /* TPG_COLOR_100_BLACK */
+
+	{   0,   0,   0 }, /* TPG_COLOR_RANDOM placeholder */
+};
+
+#ifndef COMPILE_APP
+
+/* Generated table */
+const struct color16 tpg_csc_colors[V4L2_COLORSPACE_SRGB + 1][TPG_COLOR_CSC_BLACK + 1] = {
+	[V4L2_COLORSPACE_SMPTE170M][0] = { 2953, 2939, 2939 },
+	[V4L2_COLORSPACE_SMPTE170M][1] = { 2954, 2963, 585 },
+	[V4L2_COLORSPACE_SMPTE170M][2] = { 84, 2967, 2937 },
+	[V4L2_COLORSPACE_SMPTE170M][3] = { 93, 2990, 575 },
+	[V4L2_COLORSPACE_SMPTE170M][4] = { 3030, 259, 2933 },
+	[V4L2_COLORSPACE_SMPTE170M][5] = { 3031, 406, 557 },
+	[V4L2_COLORSPACE_SMPTE170M][6] = { 544, 428, 2931 },
+	[V4L2_COLORSPACE_SMPTE170M][7] = { 551, 547, 547 },
+	[V4L2_COLORSPACE_SMPTE240M][0] = { 2926, 2926, 2926 },
+	[V4L2_COLORSPACE_SMPTE240M][1] = { 2926, 2926, 857 },
+	[V4L2_COLORSPACE_SMPTE240M][2] = { 1594, 2901, 2901 },
+	[V4L2_COLORSPACE_SMPTE240M][3] = { 1594, 2901, 774 },
+	[V4L2_COLORSPACE_SMPTE240M][4] = { 2484, 618, 2858 },
+	[V4L2_COLORSPACE_SMPTE240M][5] = { 2484, 618, 617 },
+	[V4L2_COLORSPACE_SMPTE240M][6] = { 507, 507, 2832 },
+	[V4L2_COLORSPACE_SMPTE240M][7] = { 507, 507, 507 },
+	[V4L2_COLORSPACE_REC709][0] = { 2939, 2939, 2939 },
+	[V4L2_COLORSPACE_REC709][1] = { 2939, 2939, 547 },
+	[V4L2_COLORSPACE_REC709][2] = { 547, 2939, 2939 },
+	[V4L2_COLORSPACE_REC709][3] = { 547, 2939, 547 },
+	[V4L2_COLORSPACE_REC709][4] = { 2939, 547, 2939 },
+	[V4L2_COLORSPACE_REC709][5] = { 2939, 547, 547 },
+	[V4L2_COLORSPACE_REC709][6] = { 547, 547, 2939 },
+	[V4L2_COLORSPACE_REC709][7] = { 547, 547, 547 },
+	[V4L2_COLORSPACE_470_SYSTEM_M][0] = { 2894, 2988, 2808 },
+	[V4L2_COLORSPACE_470_SYSTEM_M][1] = { 2847, 3070, 843 },
+	[V4L2_COLORSPACE_470_SYSTEM_M][2] = { 1656, 2962, 2783 },
+	[V4L2_COLORSPACE_470_SYSTEM_M][3] = { 1572, 3045, 763 },
+	[V4L2_COLORSPACE_470_SYSTEM_M][4] = { 2477, 229, 2743 },
+	[V4L2_COLORSPACE_470_SYSTEM_M][5] = { 2422, 672, 614 },
+	[V4L2_COLORSPACE_470_SYSTEM_M][6] = { 725, 63, 2718 },
+	[V4L2_COLORSPACE_470_SYSTEM_M][7] = { 534, 561, 509 },
+	[V4L2_COLORSPACE_470_SYSTEM_BG][0] = { 2939, 2939, 2939 },
+	[V4L2_COLORSPACE_470_SYSTEM_BG][1] = { 2939, 2939, 621 },
+	[V4L2_COLORSPACE_470_SYSTEM_BG][2] = { 786, 2939, 2939 },
+	[V4L2_COLORSPACE_470_SYSTEM_BG][3] = { 786, 2939, 621 },
+	[V4L2_COLORSPACE_470_SYSTEM_BG][4] = { 2879, 547, 2923 },
+	[V4L2_COLORSPACE_470_SYSTEM_BG][5] = { 2879, 547, 547 },
+	[V4L2_COLORSPACE_470_SYSTEM_BG][6] = { 547, 547, 2923 },
+	[V4L2_COLORSPACE_470_SYSTEM_BG][7] = { 547, 547, 547 },
+	[V4L2_COLORSPACE_SRGB][0] = { 3056, 3056, 3056 },
+	[V4L2_COLORSPACE_SRGB][1] = { 3056, 3056, 800 },
+	[V4L2_COLORSPACE_SRGB][2] = { 800, 3056, 3056 },
+	[V4L2_COLORSPACE_SRGB][3] = { 800, 3056, 800 },
+	[V4L2_COLORSPACE_SRGB][4] = { 3056, 800, 3056 },
+	[V4L2_COLORSPACE_SRGB][5] = { 3056, 800, 800 },
+	[V4L2_COLORSPACE_SRGB][6] = { 800, 800, 3056 },
+	[V4L2_COLORSPACE_SRGB][7] = { 800, 800, 800 },
+};
+
+#else
+
+/* This code generates the table above */
+
+#include <math.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+static const double rec709_to_ntsc1953[3][3] = {
+	{ 0.6698, 0.2678,  0.0323 },
+	{ 0.0185, 1.0742, -0.0603 },
+	{ 0.0162, 0.0432,  0.8551 }
+};
+
+static const double rec709_to_ebu[3][3] = {
+	{ 0.9578, 0.0422, 0      },
+	{ 0     , 1     , 0      },
+	{ 0     , 0.0118, 0.9882 }
+};
+
+static const double rec709_to_170m[3][3] = {
+	{  1.0654, -0.0554, -0.0010 },
+	{ -0.0196,  1.0364, -0.0167 },
+	{  0.0016,  0.0044,  0.9940 }
+};
+
+static const double rec709_to_240m[3][3] = {
+	{ 0.7151, 0.2849, 0      },
+	{ 0.0179, 0.9821, 0      },
+	{ 0.0177, 0.0472, 0.9350 }
+};
+
+
+static void mult_matrix(double *r, double *g, double *b, const double m[3][3])
+{
+	double ir, ig, ib;
+
+	ir = m[0][0] * (*r) + m[0][1] * (*g) + m[0][2] * (*b);
+	ig = m[1][0] * (*r) + m[1][1] * (*g) + m[1][2] * (*b);
+	ib = m[2][0] * (*r) + m[2][1] * (*g) + m[2][2] * (*b);
+	*r = ir;
+	*g = ig;
+	*b = ib;
+}
+
+static double transfer_srgb_to_rgb(double v)
+{
+	return (v <= 0.03928) ? v / 12.92 : pow((v + 0.055) / 1.055, 2.4);
+}
+
+static double transfer_rgb_to_smpte240m(double v)
+{
+	return (v <= 0.0228) ? v * 4.0 : 1.1115 * pow(v, 0.45) - 0.1115;
+}
+
+static double transfer_rgb_to_rec709(double v)
+{
+	return (v < 0.018) ? v * 4.5 : 1.099 * pow(v, 0.45) - 0.099;
+}
+
+static double transfer_srgb_to_rec709(double v)
+{
+	return transfer_rgb_to_rec709(transfer_srgb_to_rgb(v));
+}
+
+static void csc(enum v4l2_colorspace colorspace, double *r, double *g, double *b)
+{
+	/* Convert the primaries of Rec. 709 Linear RGB */
+	switch (colorspace) {
+	case V4L2_COLORSPACE_SMPTE240M:
+		*r = transfer_srgb_to_rgb(*r);
+		*g = transfer_srgb_to_rgb(*g);
+		*b = transfer_srgb_to_rgb(*b);
+		mult_matrix(r, g, b, rec709_to_240m);
+		break;
+	case V4L2_COLORSPACE_SMPTE170M:
+		*r = transfer_srgb_to_rgb(*r);
+		*g = transfer_srgb_to_rgb(*g);
+		*b = transfer_srgb_to_rgb(*b);
+		mult_matrix(r, g, b, rec709_to_170m);
+		break;
+	case V4L2_COLORSPACE_470_SYSTEM_BG:
+		*r = transfer_srgb_to_rgb(*r);
+		*g = transfer_srgb_to_rgb(*g);
+		*b = transfer_srgb_to_rgb(*b);
+		mult_matrix(r, g, b, rec709_to_ebu);
+		break;
+	case V4L2_COLORSPACE_470_SYSTEM_M:
+		*r = transfer_srgb_to_rgb(*r);
+		*g = transfer_srgb_to_rgb(*g);
+		*b = transfer_srgb_to_rgb(*b);
+		mult_matrix(r, g, b, rec709_to_ntsc1953);
+		break;
+	case V4L2_COLORSPACE_SRGB:
+	case V4L2_COLORSPACE_REC709:
+	default:
+		break;
+	}
+
+	*r = ((*r) < 0) ? 0 : (((*r) > 1) ? 1 : (*r));
+	*g = ((*g) < 0) ? 0 : (((*g) > 1) ? 1 : (*g));
+	*b = ((*b) < 0) ? 0 : (((*b) > 1) ? 1 : (*b));
+
+	/* Encode to gamma corrected colorspace */
+	switch (colorspace) {
+	case V4L2_COLORSPACE_SMPTE240M:
+		*r = transfer_rgb_to_smpte240m(*r);
+		*g = transfer_rgb_to_smpte240m(*g);
+		*b = transfer_rgb_to_smpte240m(*b);
+		break;
+	case V4L2_COLORSPACE_SMPTE170M:
+	case V4L2_COLORSPACE_470_SYSTEM_M:
+	case V4L2_COLORSPACE_470_SYSTEM_BG:
+		*r = transfer_rgb_to_rec709(*r);
+		*g = transfer_rgb_to_rec709(*g);
+		*b = transfer_rgb_to_rec709(*b);
+		break;
+	case V4L2_COLORSPACE_SRGB:
+		break;
+	case V4L2_COLORSPACE_REC709:
+	default:
+		*r = transfer_srgb_to_rec709(*r);
+		*g = transfer_srgb_to_rec709(*g);
+		*b = transfer_srgb_to_rec709(*b);
+		break;
+	}
+}
+
+int main(int argc, char **argv)
+{
+	static const unsigned colorspaces[] = {
+		0,
+		V4L2_COLORSPACE_SMPTE170M,
+		V4L2_COLORSPACE_SMPTE240M,
+		V4L2_COLORSPACE_REC709,
+		0,
+		V4L2_COLORSPACE_470_SYSTEM_M,
+		V4L2_COLORSPACE_470_SYSTEM_BG,
+		0,
+		V4L2_COLORSPACE_SRGB,
+	};
+	static const char * const colorspace_names[] = {
+		"",
+		"V4L2_COLORSPACE_SMPTE170M",
+		"V4L2_COLORSPACE_SMPTE240M",
+		"V4L2_COLORSPACE_REC709",
+		"",
+		"V4L2_COLORSPACE_470_SYSTEM_M",
+		"V4L2_COLORSPACE_470_SYSTEM_BG",
+		"",
+		"V4L2_COLORSPACE_SRGB",
+	};
+	int i;
+	int c;
+
+	printf("/* Generated table */\n");
+	printf("const struct color16 tpg_csc_colors[V4L2_COLORSPACE_SRGB + 1][TPG_COLOR_CSC_BLACK + 1] = {\n");
+	for (c = 0; c <= V4L2_COLORSPACE_SRGB; c++) {
+		for (i = 0; i <= TPG_COLOR_CSC_BLACK; i++) {
+			double r, g, b;
+
+			if (colorspaces[c] == 0)
+				continue;
+
+			r = tpg_colors[i].r / 255.0;
+			g = tpg_colors[i].g / 255.0;
+			b = tpg_colors[i].b / 255.0;
+
+			csc(c, &r, &g, &b);
+
+			printf("\t[%s][%d] = { %d, %d, %d },\n", colorspace_names[c], i,
+				(int)(r * 4080), (int)(g * 4080), (int)(b * 4080));
+		}
+	}
+	printf("};\n\n");
+	return 0;
+}
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-tpg-colors.h b/drivers/media/platform/vivid/vivid-tpg-colors.h
new file mode 100644
index 000000000000..a2678fbec256
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-tpg-colors.h
@@ -0,0 +1,64 @@
+/*
+ * vivid-color.h - Color definitions for the test pattern generator
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_COLORS_H_
+#define _VIVID_COLORS_H_
+
+struct color {
+	unsigned char r, g, b;
+};
+
+struct color16 {
+	int r, g, b;
+};
+
+enum tpg_color {
+	TPG_COLOR_CSC_WHITE,
+	TPG_COLOR_CSC_YELLOW,
+	TPG_COLOR_CSC_CYAN,
+	TPG_COLOR_CSC_GREEN,
+	TPG_COLOR_CSC_MAGENTA,
+	TPG_COLOR_CSC_RED,
+	TPG_COLOR_CSC_BLUE,
+	TPG_COLOR_CSC_BLACK,
+	TPG_COLOR_75_YELLOW,
+	TPG_COLOR_75_CYAN,
+	TPG_COLOR_75_GREEN,
+	TPG_COLOR_75_MAGENTA,
+	TPG_COLOR_75_RED,
+	TPG_COLOR_75_BLUE,
+	TPG_COLOR_100_WHITE,
+	TPG_COLOR_100_YELLOW,
+	TPG_COLOR_100_CYAN,
+	TPG_COLOR_100_GREEN,
+	TPG_COLOR_100_MAGENTA,
+	TPG_COLOR_100_RED,
+	TPG_COLOR_100_BLUE,
+	TPG_COLOR_100_BLACK,
+	TPG_COLOR_TEXTFG,
+	TPG_COLOR_TEXTBG,
+	TPG_COLOR_RANDOM,
+	TPG_COLOR_RAMP,
+	TPG_COLOR_MAX = TPG_COLOR_RAMP + 256
+};
+
+extern const struct color tpg_colors[TPG_COLOR_MAX];
+extern const struct color16 tpg_csc_colors[V4L2_COLORSPACE_SRGB + 1][TPG_COLOR_CSC_BLACK + 1];
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-tpg.c b/drivers/media/platform/vivid/vivid-tpg.c
new file mode 100644
index 000000000000..0c6fa53fa646
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-tpg.c
@@ -0,0 +1,1439 @@
+/*
+ * vivid-tpg.c - Test Pattern Generator
+ *
+ * Note: gen_twopix and tpg_gen_text are based on code from vivi.c. See the
+ * vivi.c source for the copyright information of those functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "vivid-tpg.h"
+
+/* Must remain in sync with enum tpg_pattern */
+const char * const tpg_pattern_strings[] = {
+	"75% Colorbar",
+	"100% Colorbar",
+	"CSC Colorbar",
+	"Horizontal 100% Colorbar",
+	"100% Color Squares",
+	"100% Black",
+	"100% White",
+	"100% Red",
+	"100% Green",
+	"100% Blue",
+	"16x16 Checkers",
+	"1x1 Checkers",
+	"Alternating Hor Lines",
+	"Alternating Vert Lines",
+	"One Pixel Wide Cross",
+	"Two Pixels Wide Cross",
+	"Ten Pixels Wide Cross",
+	"Gray Ramp",
+	"Noise",
+	NULL
+};
+
+/* Must remain in sync with enum tpg_aspect */
+const char * const tpg_aspect_strings[] = {
+	"Source Width x Height",
+	"4x3",
+	"14x9",
+	"16x9",
+	"16x9 Anamorphic",
+	NULL
+};
+
+/*
+ * Sine table: sin[0] = 127 * sin(-180 degrees)
+ *             sin[128] = 127 * sin(0 degrees)
+ *             sin[256] = 127 * sin(180 degrees)
+ */
+static const s8 sin[257] = {
+	   0,   -4,   -7,  -11,  -13,  -18,  -20,  -22,  -26,  -29,  -33,  -35,  -37,  -41,  -43,  -48,
+	 -50,  -52,  -56,  -58,  -62,  -63,  -65,  -69,  -71,  -75,  -76,  -78,  -82,  -83,  -87,  -88,
+	 -90,  -93,  -94,  -97,  -99, -101, -103, -104, -107, -108, -110, -111, -112, -114, -115, -117,
+	-118, -119, -120, -121, -122, -123, -123, -124, -125, -125, -126, -126, -127, -127, -127, -127,
+	-127, -127, -127, -127, -126, -126, -125, -125, -124, -124, -123, -122, -121, -120, -119, -118,
+	-117, -116, -114, -113, -111, -110, -109, -107, -105, -103, -101, -100,  -97,  -96,  -93,  -91,
+	 -90,  -87,  -85,  -82,  -80,  -76,  -75,  -73,  -69,  -67,  -63,  -62,  -60,  -56,  -54,  -50,
+	 -48,  -46,  -41,  -39,  -35,  -33,  -31,  -26,  -24,  -20,  -18,  -15,  -11,   -9,   -4,   -2,
+	   0,    2,    4,    9,   11,   15,   18,   20,   24,   26,   31,   33,   35,   39,   41,   46,
+	  48,   50,   54,   56,   60,   62,   64,   67,   69,   73,   75,   76,   80,   82,   85,   87,
+	  90,   91,   93,   96,   97,  100,  101,  103,  105,  107,  109,  110,  111,  113,  114,  116,
+	 117,  118,  119,  120,  121,  122,  123,  124,  124,  125,  125,  126,  126,  127,  127,  127,
+	 127,  127,  127,  127,  127,  126,  126,  125,  125,  124,  123,  123,  122,  121,  120,  119,
+	 118,  117,  115,  114,  112,  111,  110,  108,  107,  104,  103,  101,   99,   97,   94,   93,
+	  90,   88,   87,   83,   82,   78,   76,   75,   71,   69,   65,   64,   62,   58,   56,   52,
+	  50,   48,   43,   41,   37,   35,   33,   29,   26,   22,   20,   18,   13,   11,    7,    4,
+	   0,
+};
+
+#define cos(idx) sin[((idx) + 64) % sizeof(sin)]
+
+/* Global font descriptor */
+static const u8 *font8x16;
+
+void tpg_set_font(const u8 *f)
+{
+	font8x16 = f;
+}
+
+void tpg_init(struct tpg_data *tpg, unsigned w, unsigned h)
+{
+	memset(tpg, 0, sizeof(*tpg));
+	tpg->scaled_width = tpg->src_width = w;
+	tpg->src_height = tpg->buf_height = h;
+	tpg->crop.width = tpg->compose.width = w;
+	tpg->crop.height = tpg->compose.height = h;
+	tpg->recalc_colors = true;
+	tpg->recalc_square_border = true;
+	tpg->brightness = 128;
+	tpg->contrast = 128;
+	tpg->saturation = 128;
+	tpg->hue = 0;
+	tpg->mv_hor_mode = TPG_MOVE_NONE;
+	tpg->mv_vert_mode = TPG_MOVE_NONE;
+	tpg->field = V4L2_FIELD_NONE;
+	tpg_s_fourcc(tpg, V4L2_PIX_FMT_RGB24);
+	tpg->colorspace = V4L2_COLORSPACE_SRGB;
+	tpg->perc_fill = 100;
+}
+
+int tpg_alloc(struct tpg_data *tpg, unsigned max_w)
+{
+	unsigned pat;
+	unsigned plane;
+
+	tpg->max_line_width = max_w;
+	for (pat = 0; pat < TPG_MAX_PAT_LINES; pat++) {
+		for (plane = 0; plane < TPG_MAX_PLANES; plane++) {
+			unsigned pixelsz = plane ? 1 : 4;
+
+			tpg->lines[pat][plane] = vzalloc(max_w * 2 * pixelsz);
+			if (!tpg->lines[pat][plane])
+				return -ENOMEM;
+		}
+	}
+	for (plane = 0; plane < TPG_MAX_PLANES; plane++) {
+		unsigned pixelsz = plane ? 1 : 4;
+
+		tpg->contrast_line[plane] = vzalloc(max_w * pixelsz);
+		if (!tpg->contrast_line[plane])
+			return -ENOMEM;
+		tpg->black_line[plane] = vzalloc(max_w * pixelsz);
+		if (!tpg->black_line[plane])
+			return -ENOMEM;
+		tpg->random_line[plane] = vzalloc(max_w * pixelsz);
+		if (!tpg->random_line[plane])
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+void tpg_free(struct tpg_data *tpg)
+{
+	unsigned pat;
+	unsigned plane;
+
+	for (pat = 0; pat < TPG_MAX_PAT_LINES; pat++)
+		for (plane = 0; plane < TPG_MAX_PLANES; plane++) {
+			vfree(tpg->lines[pat][plane]);
+			tpg->lines[pat][plane] = NULL;
+		}
+	for (plane = 0; plane < TPG_MAX_PLANES; plane++) {
+		vfree(tpg->contrast_line[plane]);
+		vfree(tpg->black_line[plane]);
+		vfree(tpg->random_line[plane]);
+		tpg->contrast_line[plane] = NULL;
+		tpg->black_line[plane] = NULL;
+		tpg->random_line[plane] = NULL;
+	}
+}
+
+bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc)
+{
+	tpg->fourcc = fourcc;
+	tpg->planes = 1;
+	tpg->recalc_colors = true;
+	switch (fourcc) {
+	case V4L2_PIX_FMT_RGB565:
+	case V4L2_PIX_FMT_RGB565X:
+	case V4L2_PIX_FMT_RGB555:
+	case V4L2_PIX_FMT_XRGB555:
+	case V4L2_PIX_FMT_ARGB555:
+	case V4L2_PIX_FMT_RGB555X:
+	case V4L2_PIX_FMT_RGB24:
+	case V4L2_PIX_FMT_BGR24:
+	case V4L2_PIX_FMT_RGB32:
+	case V4L2_PIX_FMT_BGR32:
+	case V4L2_PIX_FMT_XRGB32:
+	case V4L2_PIX_FMT_XBGR32:
+	case V4L2_PIX_FMT_ARGB32:
+	case V4L2_PIX_FMT_ABGR32:
+		tpg->is_yuv = false;
+		break;
+	case V4L2_PIX_FMT_NV16M:
+	case V4L2_PIX_FMT_NV61M:
+		tpg->planes = 2;
+		/* fall-through */
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_VYUY:
+		tpg->is_yuv = true;
+		break;
+	default:
+		return false;
+	}
+
+	switch (fourcc) {
+	case V4L2_PIX_FMT_RGB565:
+	case V4L2_PIX_FMT_RGB565X:
+	case V4L2_PIX_FMT_RGB555:
+	case V4L2_PIX_FMT_XRGB555:
+	case V4L2_PIX_FMT_ARGB555:
+	case V4L2_PIX_FMT_RGB555X:
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_VYUY:
+		tpg->twopixelsize[0] = 2 * 2;
+		break;
+	case V4L2_PIX_FMT_RGB24:
+	case V4L2_PIX_FMT_BGR24:
+		tpg->twopixelsize[0] = 2 * 3;
+		break;
+	case V4L2_PIX_FMT_RGB32:
+	case V4L2_PIX_FMT_BGR32:
+	case V4L2_PIX_FMT_XRGB32:
+	case V4L2_PIX_FMT_XBGR32:
+	case V4L2_PIX_FMT_ARGB32:
+	case V4L2_PIX_FMT_ABGR32:
+		tpg->twopixelsize[0] = 2 * 4;
+		break;
+	case V4L2_PIX_FMT_NV16M:
+	case V4L2_PIX_FMT_NV61M:
+		tpg->twopixelsize[0] = 2;
+		tpg->twopixelsize[1] = 2;
+		break;
+	}
+	return true;
+}
+
+void tpg_s_crop_compose(struct tpg_data *tpg, const struct v4l2_rect *crop,
+		const struct v4l2_rect *compose)
+{
+	tpg->crop = *crop;
+	tpg->compose = *compose;
+	tpg->scaled_width = (tpg->src_width * tpg->compose.width +
+				 tpg->crop.width - 1) / tpg->crop.width;
+	tpg->scaled_width &= ~1;
+	if (tpg->scaled_width > tpg->max_line_width)
+		tpg->scaled_width = tpg->max_line_width;
+	if (tpg->scaled_width < 2)
+		tpg->scaled_width = 2;
+	tpg->recalc_lines = true;
+}
+
+void tpg_reset_source(struct tpg_data *tpg, unsigned width, unsigned height,
+		       u32 field)
+{
+	unsigned p;
+
+	tpg->src_width = width;
+	tpg->src_height = height;
+	tpg->field = field;
+	tpg->buf_height = height;
+	if (V4L2_FIELD_HAS_T_OR_B(field))
+		tpg->buf_height /= 2;
+	tpg->scaled_width = width;
+	tpg->crop.top = tpg->crop.left = 0;
+	tpg->crop.width = width;
+	tpg->crop.height = height;
+	tpg->compose.top = tpg->compose.left = 0;
+	tpg->compose.width = width;
+	tpg->compose.height = tpg->buf_height;
+	for (p = 0; p < tpg->planes; p++)
+		tpg->bytesperline[p] = width * tpg->twopixelsize[p] / 2;
+	tpg->recalc_square_border = true;
+}
+
+static enum tpg_color tpg_get_textbg_color(struct tpg_data *tpg)
+{
+	switch (tpg->pattern) {
+	case TPG_PAT_BLACK:
+		return TPG_COLOR_100_WHITE;
+	case TPG_PAT_CSC_COLORBAR:
+		return TPG_COLOR_CSC_BLACK;
+	default:
+		return TPG_COLOR_100_BLACK;
+	}
+}
+
+static enum tpg_color tpg_get_textfg_color(struct tpg_data *tpg)
+{
+	switch (tpg->pattern) {
+	case TPG_PAT_75_COLORBAR:
+	case TPG_PAT_CSC_COLORBAR:
+		return TPG_COLOR_CSC_WHITE;
+	case TPG_PAT_BLACK:
+		return TPG_COLOR_100_BLACK;
+	default:
+		return TPG_COLOR_100_WHITE;
+	}
+}
+
+static u16 color_to_y(struct tpg_data *tpg, int r, int g, int b)
+{
+	switch (tpg->colorspace) {
+	case V4L2_COLORSPACE_SMPTE170M:
+	case V4L2_COLORSPACE_470_SYSTEM_M:
+	case V4L2_COLORSPACE_470_SYSTEM_BG:
+		return ((16829 * r + 33039 * g + 6416 * b + 16 * 32768) >> 16) + (16 << 4);
+	case V4L2_COLORSPACE_SMPTE240M:
+		return ((11932 * r + 39455 * g + 4897 * b + 16 * 32768) >> 16) + (16 << 4);
+	case V4L2_COLORSPACE_REC709:
+	case V4L2_COLORSPACE_SRGB:
+	default:
+		return ((11966 * r + 40254 * g + 4064 * b + 16 * 32768) >> 16) + (16 << 4);
+	}
+}
+
+static u16 color_to_cb(struct tpg_data *tpg, int r, int g, int b)
+{
+	switch (tpg->colorspace) {
+	case V4L2_COLORSPACE_SMPTE170M:
+	case V4L2_COLORSPACE_470_SYSTEM_M:
+	case V4L2_COLORSPACE_470_SYSTEM_BG:
+		return ((-9714 * r - 19070 * g + 28784 * b + 16 * 32768) >> 16) + (128 << 4);
+	case V4L2_COLORSPACE_SMPTE240M:
+		return ((-6684 * r - 22100 * g + 28784 * b + 16 * 32768) >> 16) + (128 << 4);
+	case V4L2_COLORSPACE_REC709:
+	case V4L2_COLORSPACE_SRGB:
+	default:
+		return ((-6596 * r - 22189 * g + 28784 * b + 16 * 32768) >> 16) + (128 << 4);
+	}
+}
+
+static u16 color_to_cr(struct tpg_data *tpg, int r, int g, int b)
+{
+	switch (tpg->colorspace) {
+	case V4L2_COLORSPACE_SMPTE170M:
+	case V4L2_COLORSPACE_470_SYSTEM_M:
+	case V4L2_COLORSPACE_470_SYSTEM_BG:
+		return ((28784 * r - 24103 * g - 4681 * b + 16 * 32768) >> 16) + (128 << 4);
+	case V4L2_COLORSPACE_SMPTE240M:
+		return ((28784 * r - 25606 * g - 3178 * b + 16 * 32768) >> 16) + (128 << 4);
+	case V4L2_COLORSPACE_REC709:
+	case V4L2_COLORSPACE_SRGB:
+	default:
+		return ((28784 * r - 26145 * g - 2639 * b + 16 * 32768) >> 16) + (128 << 4);
+	}
+}
+
+static u16 ycbcr_to_r(struct tpg_data *tpg, int y, int cb, int cr)
+{
+	int r;
+
+	y -= 16 << 4;
+	cb -= 128 << 4;
+	cr -= 128 << 4;
+	switch (tpg->colorspace) {
+	case V4L2_COLORSPACE_SMPTE170M:
+	case V4L2_COLORSPACE_470_SYSTEM_M:
+	case V4L2_COLORSPACE_470_SYSTEM_BG:
+		r = 4769 * y + 6537 * cr;
+		break;
+	case V4L2_COLORSPACE_SMPTE240M:
+		r = 4769 * y + 7376 * cr;
+		break;
+	case V4L2_COLORSPACE_REC709:
+	case V4L2_COLORSPACE_SRGB:
+	default:
+		r = 4769 * y + 7343 * cr;
+		break;
+	}
+	return clamp(r >> 12, 0, 0xff0);
+}
+
+static u16 ycbcr_to_g(struct tpg_data *tpg, int y, int cb, int cr)
+{
+	int g;
+
+	y -= 16 << 4;
+	cb -= 128 << 4;
+	cr -= 128 << 4;
+	switch (tpg->colorspace) {
+	case V4L2_COLORSPACE_SMPTE170M:
+	case V4L2_COLORSPACE_470_SYSTEM_M:
+	case V4L2_COLORSPACE_470_SYSTEM_BG:
+		g = 4769 * y - 1605 * cb - 3330 * cr;
+		break;
+	case V4L2_COLORSPACE_SMPTE240M:
+		g = 4769 * y - 1055 * cb - 2341 * cr;
+		break;
+	case V4L2_COLORSPACE_REC709:
+	case V4L2_COLORSPACE_SRGB:
+	default:
+		g = 4769 * y - 873 * cb - 2183 * cr;
+		break;
+	}
+	return clamp(g >> 12, 0, 0xff0);
+}
+
+static u16 ycbcr_to_b(struct tpg_data *tpg, int y, int cb, int cr)
+{
+	int b;
+
+	y -= 16 << 4;
+	cb -= 128 << 4;
+	cr -= 128 << 4;
+	switch (tpg->colorspace) {
+	case V4L2_COLORSPACE_SMPTE170M:
+	case V4L2_COLORSPACE_470_SYSTEM_M:
+	case V4L2_COLORSPACE_470_SYSTEM_BG:
+		b = 4769 * y + 7343 * cb;
+		break;
+	case V4L2_COLORSPACE_SMPTE240M:
+		b = 4769 * y + 8552 * cb;
+		break;
+	case V4L2_COLORSPACE_REC709:
+	case V4L2_COLORSPACE_SRGB:
+	default:
+		b = 4769 * y + 8652 * cb;
+		break;
+	}
+	return clamp(b >> 12, 0, 0xff0);
+}
+
+/* precalculate color bar values to speed up rendering */
+static void precalculate_color(struct tpg_data *tpg, int k)
+{
+	int col = k;
+	int r = tpg_colors[col].r;
+	int g = tpg_colors[col].g;
+	int b = tpg_colors[col].b;
+
+	if (k == TPG_COLOR_TEXTBG) {
+		col = tpg_get_textbg_color(tpg);
+
+		r = tpg_colors[col].r;
+		g = tpg_colors[col].g;
+		b = tpg_colors[col].b;
+	} else if (k == TPG_COLOR_TEXTFG) {
+		col = tpg_get_textfg_color(tpg);
+
+		r = tpg_colors[col].r;
+		g = tpg_colors[col].g;
+		b = tpg_colors[col].b;
+	} else if (tpg->pattern == TPG_PAT_NOISE) {
+		r = g = b = prandom_u32_max(256);
+	} else if (k == TPG_COLOR_RANDOM) {
+		r = g = b = tpg->qual_offset + prandom_u32_max(196);
+	} else if (k >= TPG_COLOR_RAMP) {
+		r = g = b = k - TPG_COLOR_RAMP;
+	}
+
+	if (tpg->pattern == TPG_PAT_CSC_COLORBAR && col <= TPG_COLOR_CSC_BLACK) {
+		r = tpg_csc_colors[tpg->colorspace][col].r;
+		g = tpg_csc_colors[tpg->colorspace][col].g;
+		b = tpg_csc_colors[tpg->colorspace][col].b;
+	} else {
+		r <<= 4;
+		g <<= 4;
+		b <<= 4;
+	}
+	if (tpg->qual == TPG_QUAL_GRAY)
+		r = g = b = color_to_y(tpg, r, g, b);
+
+	/*
+	 * The assumption is that the RGB output is always full range,
+	 * so only if the rgb_range overrides the 'real' rgb range do
+	 * we need to convert the RGB values.
+	 *
+	 * Currently there is no way of signalling to userspace if you
+	 * are actually giving it limited range RGB (or full range
+	 * YUV for that matter).
+	 *
+	 * Remember that r, g and b are still in the 0 - 0xff0 range.
+	 */
+	if (tpg->real_rgb_range == V4L2_DV_RGB_RANGE_LIMITED &&
+	    tpg->rgb_range == V4L2_DV_RGB_RANGE_FULL) {
+		/*
+		 * Convert from full range (which is what r, g and b are)
+		 * to limited range (which is the 'real' RGB range), which
+		 * is then interpreted as full range.
+		 */
+		r = (r * 219) / 255 + (16 << 4);
+		g = (g * 219) / 255 + (16 << 4);
+		b = (b * 219) / 255 + (16 << 4);
+	} else if (tpg->real_rgb_range != V4L2_DV_RGB_RANGE_LIMITED &&
+		   tpg->rgb_range == V4L2_DV_RGB_RANGE_LIMITED) {
+		/*
+		 * Clamp r, g and b to the limited range and convert to full
+		 * range since that's what we deliver.
+		 */
+		r = clamp(r, 16 << 4, 235 << 4);
+		g = clamp(g, 16 << 4, 235 << 4);
+		b = clamp(b, 16 << 4, 235 << 4);
+		r = (r - (16 << 4)) * 255 / 219;
+		g = (g - (16 << 4)) * 255 / 219;
+		b = (b - (16 << 4)) * 255 / 219;
+	}
+
+	if (tpg->brightness != 128 || tpg->contrast != 128 ||
+	    tpg->saturation != 128 || tpg->hue) {
+		/* Implement these operations */
+
+		/* First convert to YCbCr */
+		int y = color_to_y(tpg, r, g, b);	/* Luma */
+		int cb = color_to_cb(tpg, r, g, b);	/* Cb */
+		int cr = color_to_cr(tpg, r, g, b);	/* Cr */
+		int tmp_cb, tmp_cr;
+
+		y = (16 << 4) + ((y - (16 << 4)) * tpg->contrast) / 128;
+		y += (tpg->brightness << 4) - (128 << 4);
+
+		cb -= 128 << 4;
+		cr -= 128 << 4;
+		tmp_cb = (cb * cos(128 + tpg->hue)) / 127 + (cr * sin[128 + tpg->hue]) / 127;
+		tmp_cr = (cr * cos(128 + tpg->hue)) / 127 - (cb * sin[128 + tpg->hue]) / 127;
+
+		cb = (128 << 4) + (tmp_cb * tpg->contrast * tpg->saturation) / (128 * 128);
+		cr = (128 << 4) + (tmp_cr * tpg->contrast * tpg->saturation) / (128 * 128);
+		if (tpg->is_yuv) {
+			tpg->colors[k][0] = clamp(y >> 4, 1, 254);
+			tpg->colors[k][1] = clamp(cb >> 4, 1, 254);
+			tpg->colors[k][2] = clamp(cr >> 4, 1, 254);
+			return;
+		}
+		r = ycbcr_to_r(tpg, y, cb, cr);
+		g = ycbcr_to_g(tpg, y, cb, cr);
+		b = ycbcr_to_b(tpg, y, cb, cr);
+	}
+
+	if (tpg->is_yuv) {
+		/* Convert to YCbCr */
+		u16 y = color_to_y(tpg, r, g, b);	/* Luma */
+		u16 cb = color_to_cb(tpg, r, g, b);	/* Cb */
+		u16 cr = color_to_cr(tpg, r, g, b);	/* Cr */
+
+		tpg->colors[k][0] = clamp(y >> 4, 1, 254);
+		tpg->colors[k][1] = clamp(cb >> 4, 1, 254);
+		tpg->colors[k][2] = clamp(cr >> 4, 1, 254);
+	} else {
+		switch (tpg->fourcc) {
+		case V4L2_PIX_FMT_RGB565:
+		case V4L2_PIX_FMT_RGB565X:
+			r >>= 7;
+			g >>= 6;
+			b >>= 7;
+			break;
+		case V4L2_PIX_FMT_RGB555:
+		case V4L2_PIX_FMT_XRGB555:
+		case V4L2_PIX_FMT_ARGB555:
+		case V4L2_PIX_FMT_RGB555X:
+			r >>= 7;
+			g >>= 7;
+			b >>= 7;
+			break;
+		default:
+			r >>= 4;
+			g >>= 4;
+			b >>= 4;
+			break;
+		}
+
+		tpg->colors[k][0] = r;
+		tpg->colors[k][1] = g;
+		tpg->colors[k][2] = b;
+	}
+}
+
+static void tpg_precalculate_colors(struct tpg_data *tpg)
+{
+	int k;
+
+	for (k = 0; k < TPG_COLOR_MAX; k++)
+		precalculate_color(tpg, k);
+}
+
+/* 'odd' is true for pixels 1, 3, 5, etc. and false for pixels 0, 2, 4, etc. */
+static void gen_twopix(struct tpg_data *tpg,
+		u8 buf[TPG_MAX_PLANES][8], int color, bool odd)
+{
+	unsigned offset = odd * tpg->twopixelsize[0] / 2;
+	u8 alpha = tpg->alpha_component;
+	u8 r_y, g_u, b_v;
+
+	if (tpg->alpha_red_only && color != TPG_COLOR_CSC_RED &&
+				   color != TPG_COLOR_100_RED &&
+				   color != TPG_COLOR_75_RED)
+		alpha = 0;
+	if (color == TPG_COLOR_RANDOM)
+		precalculate_color(tpg, color);
+	r_y = tpg->colors[color][0]; /* R or precalculated Y */
+	g_u = tpg->colors[color][1]; /* G or precalculated U */
+	b_v = tpg->colors[color][2]; /* B or precalculated V */
+
+	switch (tpg->fourcc) {
+	case V4L2_PIX_FMT_NV16M:
+		buf[0][offset] = r_y;
+		buf[1][offset] = odd ? b_v : g_u;
+		break;
+	case V4L2_PIX_FMT_NV61M:
+		buf[0][offset] = r_y;
+		buf[1][offset] = odd ? g_u : b_v;
+		break;
+
+	case V4L2_PIX_FMT_YUYV:
+		buf[0][offset] = r_y;
+		buf[0][offset + 1] = odd ? b_v : g_u;
+		break;
+	case V4L2_PIX_FMT_UYVY:
+		buf[0][offset] = odd ? b_v : g_u;
+		buf[0][offset + 1] = r_y;
+		break;
+	case V4L2_PIX_FMT_YVYU:
+		buf[0][offset] = r_y;
+		buf[0][offset + 1] = odd ? g_u : b_v;
+		break;
+	case V4L2_PIX_FMT_VYUY:
+		buf[0][offset] = odd ? g_u : b_v;
+		buf[0][offset + 1] = r_y;
+		break;
+	case V4L2_PIX_FMT_RGB565:
+		buf[0][offset] = (g_u << 5) | b_v;
+		buf[0][offset + 1] = (r_y << 3) | (g_u >> 3);
+		break;
+	case V4L2_PIX_FMT_RGB565X:
+		buf[0][offset] = (r_y << 3) | (g_u >> 3);
+		buf[0][offset + 1] = (g_u << 5) | b_v;
+		break;
+	case V4L2_PIX_FMT_RGB555:
+	case V4L2_PIX_FMT_XRGB555:
+		alpha = 0;
+		/* fall through */
+	case V4L2_PIX_FMT_ARGB555:
+		buf[0][offset] = (g_u << 5) | b_v;
+		buf[0][offset + 1] = (alpha & 0x80) | (r_y << 2) | (g_u >> 3);
+		break;
+	case V4L2_PIX_FMT_RGB555X:
+		buf[0][offset] = (alpha & 0x80) | (r_y << 2) | (g_u >> 3);
+		buf[0][offset + 1] = (g_u << 5) | b_v;
+		break;
+	case V4L2_PIX_FMT_RGB24:
+		buf[0][offset] = r_y;
+		buf[0][offset + 1] = g_u;
+		buf[0][offset + 2] = b_v;
+		break;
+	case V4L2_PIX_FMT_BGR24:
+		buf[0][offset] = b_v;
+		buf[0][offset + 1] = g_u;
+		buf[0][offset + 2] = r_y;
+		break;
+	case V4L2_PIX_FMT_RGB32:
+	case V4L2_PIX_FMT_XRGB32:
+		alpha = 0;
+		/* fall through */
+	case V4L2_PIX_FMT_ARGB32:
+		buf[0][offset] = alpha;
+		buf[0][offset + 1] = r_y;
+		buf[0][offset + 2] = g_u;
+		buf[0][offset + 3] = b_v;
+		break;
+	case V4L2_PIX_FMT_BGR32:
+	case V4L2_PIX_FMT_XBGR32:
+		alpha = 0;
+		/* fall through */
+	case V4L2_PIX_FMT_ABGR32:
+		buf[0][offset] = b_v;
+		buf[0][offset + 1] = g_u;
+		buf[0][offset + 2] = r_y;
+		buf[0][offset + 3] = alpha;
+		break;
+	}
+}
+
+/* Return how many pattern lines are used by the current pattern. */
+static unsigned tpg_get_pat_lines(struct tpg_data *tpg)
+{
+	switch (tpg->pattern) {
+	case TPG_PAT_CHECKERS_16X16:
+	case TPG_PAT_CHECKERS_1X1:
+	case TPG_PAT_ALTERNATING_HLINES:
+	case TPG_PAT_CROSS_1_PIXEL:
+	case TPG_PAT_CROSS_2_PIXELS:
+	case TPG_PAT_CROSS_10_PIXELS:
+		return 2;
+	case TPG_PAT_100_COLORSQUARES:
+	case TPG_PAT_100_HCOLORBAR:
+		return 8;
+	default:
+		return 1;
+	}
+}
+
+/* Which pattern line should be used for the given frame line. */
+static unsigned tpg_get_pat_line(struct tpg_data *tpg, unsigned line)
+{
+	switch (tpg->pattern) {
+	case TPG_PAT_CHECKERS_16X16:
+		return (line >> 4) & 1;
+	case TPG_PAT_CHECKERS_1X1:
+	case TPG_PAT_ALTERNATING_HLINES:
+		return line & 1;
+	case TPG_PAT_100_COLORSQUARES:
+	case TPG_PAT_100_HCOLORBAR:
+		return (line * 8) / tpg->src_height;
+	case TPG_PAT_CROSS_1_PIXEL:
+		return line == tpg->src_height / 2;
+	case TPG_PAT_CROSS_2_PIXELS:
+		return (line + 1) / 2 == tpg->src_height / 4;
+	case TPG_PAT_CROSS_10_PIXELS:
+		return (line + 10) / 20 == tpg->src_height / 40;
+	default:
+		return 0;
+	}
+}
+
+/*
+ * Which color should be used for the given pattern line and X coordinate.
+ * Note: x is in the range 0 to 2 * tpg->src_width.
+ */
+static enum tpg_color tpg_get_color(struct tpg_data *tpg, unsigned pat_line, unsigned x)
+{
+	/* Maximum number of bars are TPG_COLOR_MAX - otherwise, the input print code
+	   should be modified */
+	static const enum tpg_color bars[3][8] = {
+		/* Standard ITU-R 75% color bar sequence */
+		{ TPG_COLOR_CSC_WHITE,   TPG_COLOR_75_YELLOW,
+		  TPG_COLOR_75_CYAN,     TPG_COLOR_75_GREEN,
+		  TPG_COLOR_75_MAGENTA,  TPG_COLOR_75_RED,
+		  TPG_COLOR_75_BLUE,     TPG_COLOR_100_BLACK, },
+		/* Standard ITU-R 100% color bar sequence */
+		{ TPG_COLOR_100_WHITE,   TPG_COLOR_100_YELLOW,
+		  TPG_COLOR_100_CYAN,    TPG_COLOR_100_GREEN,
+		  TPG_COLOR_100_MAGENTA, TPG_COLOR_100_RED,
+		  TPG_COLOR_100_BLUE,    TPG_COLOR_100_BLACK, },
+		/* Color bar sequence suitable to test CSC */
+		{ TPG_COLOR_CSC_WHITE,   TPG_COLOR_CSC_YELLOW,
+		  TPG_COLOR_CSC_CYAN,    TPG_COLOR_CSC_GREEN,
+		  TPG_COLOR_CSC_MAGENTA, TPG_COLOR_CSC_RED,
+		  TPG_COLOR_CSC_BLUE,    TPG_COLOR_CSC_BLACK, },
+	};
+
+	switch (tpg->pattern) {
+	case TPG_PAT_75_COLORBAR:
+	case TPG_PAT_100_COLORBAR:
+	case TPG_PAT_CSC_COLORBAR:
+		return bars[tpg->pattern][((x * 8) / tpg->src_width) % 8];
+	case TPG_PAT_100_COLORSQUARES:
+		return bars[1][(pat_line + (x * 8) / tpg->src_width) % 8];
+	case TPG_PAT_100_HCOLORBAR:
+		return bars[1][pat_line];
+	case TPG_PAT_BLACK:
+		return TPG_COLOR_100_BLACK;
+	case TPG_PAT_WHITE:
+		return TPG_COLOR_100_WHITE;
+	case TPG_PAT_RED:
+		return TPG_COLOR_100_RED;
+	case TPG_PAT_GREEN:
+		return TPG_COLOR_100_GREEN;
+	case TPG_PAT_BLUE:
+		return TPG_COLOR_100_BLUE;
+	case TPG_PAT_CHECKERS_16X16:
+		return (((x >> 4) & 1) ^ (pat_line & 1)) ?
+			TPG_COLOR_100_BLACK : TPG_COLOR_100_WHITE;
+	case TPG_PAT_CHECKERS_1X1:
+		return ((x & 1) ^ (pat_line & 1)) ?
+			TPG_COLOR_100_WHITE : TPG_COLOR_100_BLACK;
+	case TPG_PAT_ALTERNATING_HLINES:
+		return pat_line ? TPG_COLOR_100_WHITE : TPG_COLOR_100_BLACK;
+	case TPG_PAT_ALTERNATING_VLINES:
+		return (x & 1) ? TPG_COLOR_100_WHITE : TPG_COLOR_100_BLACK;
+	case TPG_PAT_CROSS_1_PIXEL:
+		if (pat_line || (x % tpg->src_width) == tpg->src_width / 2)
+			return TPG_COLOR_100_BLACK;
+		return TPG_COLOR_100_WHITE;
+	case TPG_PAT_CROSS_2_PIXELS:
+		if (pat_line || ((x % tpg->src_width) + 1) / 2 == tpg->src_width / 4)
+			return TPG_COLOR_100_BLACK;
+		return TPG_COLOR_100_WHITE;
+	case TPG_PAT_CROSS_10_PIXELS:
+		if (pat_line || ((x % tpg->src_width) + 10) / 20 == tpg->src_width / 40)
+			return TPG_COLOR_100_BLACK;
+		return TPG_COLOR_100_WHITE;
+	case TPG_PAT_GRAY_RAMP:
+		return TPG_COLOR_RAMP + ((x % tpg->src_width) * 256) / tpg->src_width;
+	default:
+		return TPG_COLOR_100_RED;
+	}
+}
+
+/*
+ * Given the pixel aspect ratio and video aspect ratio calculate the
+ * coordinates of a centered square and the coordinates of the border of
+ * the active video area. The coordinates are relative to the source
+ * frame rectangle.
+ */
+static void tpg_calculate_square_border(struct tpg_data *tpg)
+{
+	unsigned w = tpg->src_width;
+	unsigned h = tpg->src_height;
+	unsigned sq_w, sq_h;
+
+	sq_w = (w * 2 / 5) & ~1;
+	if (((w - sq_w) / 2) & 1)
+		sq_w += 2;
+	sq_h = sq_w;
+	tpg->square.width = sq_w;
+	if (tpg->vid_aspect == TPG_VIDEO_ASPECT_16X9_ANAMORPHIC) {
+		unsigned ana_sq_w = (sq_w / 4) * 3;
+
+		if (((w - ana_sq_w) / 2) & 1)
+			ana_sq_w += 2;
+		tpg->square.width = ana_sq_w;
+	}
+	tpg->square.left = (w - tpg->square.width) / 2;
+	if (tpg->pix_aspect == TPG_PIXEL_ASPECT_NTSC)
+		sq_h = sq_w * 10 / 11;
+	else if (tpg->pix_aspect == TPG_PIXEL_ASPECT_PAL)
+		sq_h = sq_w * 59 / 54;
+	tpg->square.height = sq_h;
+	tpg->square.top = (h - sq_h) / 2;
+	tpg->border.left = 0;
+	tpg->border.width = w;
+	tpg->border.top = 0;
+	tpg->border.height = h;
+	switch (tpg->vid_aspect) {
+	case TPG_VIDEO_ASPECT_4X3:
+		if (tpg->pix_aspect)
+			return;
+		if (3 * w >= 4 * h) {
+			tpg->border.width = ((4 * h) / 3) & ~1;
+			if (((w - tpg->border.width) / 2) & ~1)
+				tpg->border.width -= 2;
+			tpg->border.left = (w - tpg->border.width) / 2;
+			break;
+		}
+		tpg->border.height = ((3 * w) / 4) & ~1;
+		tpg->border.top = (h - tpg->border.height) / 2;
+		break;
+	case TPG_VIDEO_ASPECT_14X9_CENTRE:
+		if (tpg->pix_aspect) {
+			tpg->border.height = tpg->pix_aspect == TPG_PIXEL_ASPECT_NTSC ? 420 : 506;
+			tpg->border.top = (h - tpg->border.height) / 2;
+			break;
+		}
+		if (9 * w >= 14 * h) {
+			tpg->border.width = ((14 * h) / 9) & ~1;
+			if (((w - tpg->border.width) / 2) & ~1)
+				tpg->border.width -= 2;
+			tpg->border.left = (w - tpg->border.width) / 2;
+			break;
+		}
+		tpg->border.height = ((9 * w) / 14) & ~1;
+		tpg->border.top = (h - tpg->border.height) / 2;
+		break;
+	case TPG_VIDEO_ASPECT_16X9_CENTRE:
+		if (tpg->pix_aspect) {
+			tpg->border.height = tpg->pix_aspect == TPG_PIXEL_ASPECT_NTSC ? 368 : 442;
+			tpg->border.top = (h - tpg->border.height) / 2;
+			break;
+		}
+		if (9 * w >= 16 * h) {
+			tpg->border.width = ((16 * h) / 9) & ~1;
+			if (((w - tpg->border.width) / 2) & ~1)
+				tpg->border.width -= 2;
+			tpg->border.left = (w - tpg->border.width) / 2;
+			break;
+		}
+		tpg->border.height = ((9 * w) / 16) & ~1;
+		tpg->border.top = (h - tpg->border.height) / 2;
+		break;
+	default:
+		break;
+	}
+}
+
+static void tpg_precalculate_line(struct tpg_data *tpg)
+{
+	enum tpg_color contrast;
+	unsigned pat;
+	unsigned p;
+	unsigned x;
+
+	switch (tpg->pattern) {
+	case TPG_PAT_GREEN:
+		contrast = TPG_COLOR_100_RED;
+		break;
+	case TPG_PAT_CSC_COLORBAR:
+		contrast = TPG_COLOR_CSC_GREEN;
+		break;
+	default:
+		contrast = TPG_COLOR_100_GREEN;
+		break;
+	}
+
+	for (pat = 0; pat < tpg_get_pat_lines(tpg); pat++) {
+		/* Coarse scaling with Bresenham */
+		unsigned int_part = tpg->src_width / tpg->scaled_width;
+		unsigned fract_part = tpg->src_width % tpg->scaled_width;
+		unsigned src_x = 0;
+		unsigned error = 0;
+
+		for (x = 0; x < tpg->scaled_width * 2; x += 2) {
+			unsigned real_x = src_x;
+			enum tpg_color color1, color2;
+			u8 pix[TPG_MAX_PLANES][8];
+
+			real_x = tpg->hflip ? tpg->src_width * 2 - real_x - 2 : real_x;
+			color1 = tpg_get_color(tpg, pat, real_x);
+
+			src_x += int_part;
+			error += fract_part;
+			if (error >= tpg->scaled_width) {
+				error -= tpg->scaled_width;
+				src_x++;
+			}
+
+			real_x = src_x;
+			real_x = tpg->hflip ? tpg->src_width * 2 - real_x - 2 : real_x;
+			color2 = tpg_get_color(tpg, pat, real_x);
+
+			src_x += int_part;
+			error += fract_part;
+			if (error >= tpg->scaled_width) {
+				error -= tpg->scaled_width;
+				src_x++;
+			}
+
+			gen_twopix(tpg, pix, tpg->hflip ? color2 : color1, 0);
+			gen_twopix(tpg, pix, tpg->hflip ? color1 : color2, 1);
+			for (p = 0; p < tpg->planes; p++) {
+				unsigned twopixsize = tpg->twopixelsize[p];
+				u8 *pos = tpg->lines[pat][p] + x * twopixsize / 2;
+
+				memcpy(pos, pix[p], twopixsize);
+			}
+		}
+	}
+	for (x = 0; x < tpg->scaled_width; x += 2) {
+		u8 pix[TPG_MAX_PLANES][8];
+
+		gen_twopix(tpg, pix, contrast, 0);
+		gen_twopix(tpg, pix, contrast, 1);
+		for (p = 0; p < tpg->planes; p++) {
+			unsigned twopixsize = tpg->twopixelsize[p];
+			u8 *pos = tpg->contrast_line[p] + x * twopixsize / 2;
+
+			memcpy(pos, pix[p], twopixsize);
+		}
+	}
+	for (x = 0; x < tpg->scaled_width; x += 2) {
+		u8 pix[TPG_MAX_PLANES][8];
+
+		gen_twopix(tpg, pix, TPG_COLOR_100_BLACK, 0);
+		gen_twopix(tpg, pix, TPG_COLOR_100_BLACK, 1);
+		for (p = 0; p < tpg->planes; p++) {
+			unsigned twopixsize = tpg->twopixelsize[p];
+			u8 *pos = tpg->black_line[p] + x * twopixsize / 2;
+
+			memcpy(pos, pix[p], twopixsize);
+		}
+	}
+	for (x = 0; x < tpg->scaled_width * 2; x += 2) {
+		u8 pix[TPG_MAX_PLANES][8];
+
+		gen_twopix(tpg, pix, TPG_COLOR_RANDOM, 0);
+		gen_twopix(tpg, pix, TPG_COLOR_RANDOM, 1);
+		for (p = 0; p < tpg->planes; p++) {
+			unsigned twopixsize = tpg->twopixelsize[p];
+			u8 *pos = tpg->random_line[p] + x * twopixsize / 2;
+
+			memcpy(pos, pix[p], twopixsize);
+		}
+	}
+	gen_twopix(tpg, tpg->textbg, TPG_COLOR_TEXTBG, 0);
+	gen_twopix(tpg, tpg->textbg, TPG_COLOR_TEXTBG, 1);
+	gen_twopix(tpg, tpg->textfg, TPG_COLOR_TEXTFG, 0);
+	gen_twopix(tpg, tpg->textfg, TPG_COLOR_TEXTFG, 1);
+}
+
+/* need this to do rgb24 rendering */
+typedef struct { u16 __; u8 _; } __packed x24;
+
+void tpg_gen_text(struct tpg_data *tpg, u8 *basep[TPG_MAX_PLANES][2],
+		int y, int x, char *text)
+{
+	int line;
+	unsigned step = V4L2_FIELD_HAS_T_OR_B(tpg->field) ? 2 : 1;
+	unsigned div = step;
+	unsigned first = 0;
+	unsigned len = strlen(text);
+	unsigned p;
+
+	if (font8x16 == NULL || basep == NULL)
+		return;
+
+	/* Checks if it is possible to show string */
+	if (y + 16 >= tpg->compose.height || x + 8 >= tpg->compose.width)
+		return;
+
+	if (len > (tpg->compose.width - x) / 8)
+		len = (tpg->compose.width - x) / 8;
+	if (tpg->vflip)
+		y = tpg->compose.height - y - 16;
+	if (tpg->hflip)
+		x = tpg->compose.width - x - 8;
+	y += tpg->compose.top;
+	x += tpg->compose.left;
+	if (tpg->field == V4L2_FIELD_BOTTOM)
+		first = 1;
+	else if (tpg->field == V4L2_FIELD_SEQ_TB || tpg->field == V4L2_FIELD_SEQ_BT)
+		div = 2;
+
+	for (p = 0; p < tpg->planes; p++) {
+		/* Print stream time */
+#define PRINTSTR(PIXTYPE) do {	\
+	PIXTYPE fg;	\
+	PIXTYPE bg;	\
+	memcpy(&fg, tpg->textfg[p], sizeof(PIXTYPE));	\
+	memcpy(&bg, tpg->textbg[p], sizeof(PIXTYPE));	\
+	\
+	for (line = first; line < 16; line += step) {	\
+		int l = tpg->vflip ? 15 - line : line; \
+		PIXTYPE *pos = (PIXTYPE *)(basep[p][line & 1] + \
+			       ((y * step + l) / div) * tpg->bytesperline[p] + \
+			       x * sizeof(PIXTYPE));	\
+		unsigned s;	\
+	\
+		for (s = 0; s < len; s++) {	\
+			u8 chr = font8x16[text[s] * 16 + line];	\
+	\
+			if (tpg->hflip) { \
+				pos[7] = (chr & (0x01 << 7) ? fg : bg);	\
+				pos[6] = (chr & (0x01 << 6) ? fg : bg);	\
+				pos[5] = (chr & (0x01 << 5) ? fg : bg);	\
+				pos[4] = (chr & (0x01 << 4) ? fg : bg);	\
+				pos[3] = (chr & (0x01 << 3) ? fg : bg);	\
+				pos[2] = (chr & (0x01 << 2) ? fg : bg);	\
+				pos[1] = (chr & (0x01 << 1) ? fg : bg);	\
+				pos[0] = (chr & (0x01 << 0) ? fg : bg);	\
+			} else { \
+				pos[0] = (chr & (0x01 << 7) ? fg : bg);	\
+				pos[1] = (chr & (0x01 << 6) ? fg : bg);	\
+				pos[2] = (chr & (0x01 << 5) ? fg : bg);	\
+				pos[3] = (chr & (0x01 << 4) ? fg : bg);	\
+				pos[4] = (chr & (0x01 << 3) ? fg : bg);	\
+				pos[5] = (chr & (0x01 << 2) ? fg : bg);	\
+				pos[6] = (chr & (0x01 << 1) ? fg : bg);	\
+				pos[7] = (chr & (0x01 << 0) ? fg : bg);	\
+			} \
+	\
+			pos += tpg->hflip ? -8 : 8;	\
+		}	\
+	}	\
+} while (0)
+
+		switch (tpg->twopixelsize[p]) {
+		case 2:
+			PRINTSTR(u8); break;
+		case 4:
+			PRINTSTR(u16); break;
+		case 6:
+			PRINTSTR(x24); break;
+		case 8:
+			PRINTSTR(u32); break;
+		}
+	}
+}
+
+void tpg_update_mv_step(struct tpg_data *tpg)
+{
+	int factor = tpg->mv_hor_mode > TPG_MOVE_NONE ? -1 : 1;
+
+	if (tpg->hflip)
+		factor = -factor;
+	switch (tpg->mv_hor_mode) {
+	case TPG_MOVE_NEG_FAST:
+	case TPG_MOVE_POS_FAST:
+		tpg->mv_hor_step = ((tpg->src_width + 319) / 320) * 4;
+		break;
+	case TPG_MOVE_NEG:
+	case TPG_MOVE_POS:
+		tpg->mv_hor_step = ((tpg->src_width + 639) / 640) * 4;
+		break;
+	case TPG_MOVE_NEG_SLOW:
+	case TPG_MOVE_POS_SLOW:
+		tpg->mv_hor_step = 2;
+		break;
+	case TPG_MOVE_NONE:
+		tpg->mv_hor_step = 0;
+		break;
+	}
+	if (factor < 0)
+		tpg->mv_hor_step = tpg->src_width - tpg->mv_hor_step;
+
+	factor = tpg->mv_vert_mode > TPG_MOVE_NONE ? -1 : 1;
+	switch (tpg->mv_vert_mode) {
+	case TPG_MOVE_NEG_FAST:
+	case TPG_MOVE_POS_FAST:
+		tpg->mv_vert_step = ((tpg->src_width + 319) / 320) * 4;
+		break;
+	case TPG_MOVE_NEG:
+	case TPG_MOVE_POS:
+		tpg->mv_vert_step = ((tpg->src_width + 639) / 640) * 4;
+		break;
+	case TPG_MOVE_NEG_SLOW:
+	case TPG_MOVE_POS_SLOW:
+		tpg->mv_vert_step = 1;
+		break;
+	case TPG_MOVE_NONE:
+		tpg->mv_vert_step = 0;
+		break;
+	}
+	if (factor < 0)
+		tpg->mv_vert_step = tpg->src_height - tpg->mv_vert_step;
+}
+
+/* Map the line number relative to the crop rectangle to a frame line number */
+static unsigned tpg_calc_frameline(struct tpg_data *tpg, unsigned src_y,
+				    unsigned field)
+{
+	switch (field) {
+	case V4L2_FIELD_TOP:
+		return tpg->crop.top + src_y * 2;
+	case V4L2_FIELD_BOTTOM:
+		return tpg->crop.top + src_y * 2 + 1;
+	default:
+		return src_y + tpg->crop.top;
+	}
+}
+
+/*
+ * Map the line number relative to the compose rectangle to a destination
+ * buffer line number.
+ */
+static unsigned tpg_calc_buffer_line(struct tpg_data *tpg, unsigned y,
+				    unsigned field)
+{
+	y += tpg->compose.top;
+	switch (field) {
+	case V4L2_FIELD_SEQ_TB:
+		if (y & 1)
+			return tpg->buf_height / 2 + y / 2;
+		return y / 2;
+	case V4L2_FIELD_SEQ_BT:
+		if (y & 1)
+			return y / 2;
+		return tpg->buf_height / 2 + y / 2;
+	default:
+		return y;
+	}
+}
+
+static void tpg_recalc(struct tpg_data *tpg)
+{
+	if (tpg->recalc_colors) {
+		tpg->recalc_colors = false;
+		tpg->recalc_lines = true;
+		tpg_precalculate_colors(tpg);
+	}
+	if (tpg->recalc_square_border) {
+		tpg->recalc_square_border = false;
+		tpg_calculate_square_border(tpg);
+	}
+	if (tpg->recalc_lines) {
+		tpg->recalc_lines = false;
+		tpg_precalculate_line(tpg);
+	}
+}
+
+void tpg_calc_text_basep(struct tpg_data *tpg,
+		u8 *basep[TPG_MAX_PLANES][2], unsigned p, u8 *vbuf)
+{
+	unsigned stride = tpg->bytesperline[p];
+
+	tpg_recalc(tpg);
+
+	basep[p][0] = vbuf;
+	basep[p][1] = vbuf;
+	if (tpg->field == V4L2_FIELD_SEQ_TB)
+		basep[p][1] += tpg->buf_height * stride / 2;
+	else if (tpg->field == V4L2_FIELD_SEQ_BT)
+		basep[p][0] += tpg->buf_height * stride / 2;
+}
+
+void tpg_fillbuffer(struct tpg_data *tpg, v4l2_std_id std, unsigned p, u8 *vbuf)
+{
+	bool is_tv = std;
+	bool is_60hz = is_tv && (std & V4L2_STD_525_60);
+	unsigned mv_hor_old = tpg->mv_hor_count % tpg->src_width;
+	unsigned mv_hor_new = (tpg->mv_hor_count + tpg->mv_hor_step) % tpg->src_width;
+	unsigned mv_vert_old = tpg->mv_vert_count % tpg->src_height;
+	unsigned mv_vert_new = (tpg->mv_vert_count + tpg->mv_vert_step) % tpg->src_height;
+	unsigned wss_width;
+	unsigned f;
+	int hmax = (tpg->compose.height * tpg->perc_fill) / 100;
+	int h;
+	unsigned twopixsize = tpg->twopixelsize[p];
+	unsigned img_width = tpg->compose.width * twopixsize / 2;
+	unsigned line_offset;
+	unsigned left_pillar_width = 0;
+	unsigned right_pillar_start = img_width;
+	unsigned stride = tpg->bytesperline[p];
+	unsigned factor = V4L2_FIELD_HAS_T_OR_B(tpg->field) ? 2 : 1;
+	u8 *orig_vbuf = vbuf;
+
+	/* Coarse scaling with Bresenham */
+	unsigned int_part = (tpg->crop.height / factor) / tpg->compose.height;
+	unsigned fract_part = (tpg->crop.height / factor) % tpg->compose.height;
+	unsigned src_y = 0;
+	unsigned error = 0;
+
+	tpg_recalc(tpg);
+
+	mv_hor_old = (mv_hor_old * tpg->scaled_width / tpg->src_width) & ~1;
+	mv_hor_new = (mv_hor_new * tpg->scaled_width / tpg->src_width) & ~1;
+	wss_width = tpg->crop.left < tpg->src_width / 2 ?
+			tpg->src_width / 2 - tpg->crop.left : 0;
+	if (wss_width > tpg->crop.width)
+		wss_width = tpg->crop.width;
+	wss_width = wss_width * tpg->scaled_width / tpg->src_width;
+
+	vbuf += tpg->compose.left * twopixsize / 2;
+	line_offset = tpg->crop.left * tpg->scaled_width / tpg->src_width;
+	line_offset = (line_offset & ~1) * twopixsize / 2;
+	if (tpg->crop.left < tpg->border.left) {
+		left_pillar_width = tpg->border.left - tpg->crop.left;
+		if (left_pillar_width > tpg->crop.width)
+			left_pillar_width = tpg->crop.width;
+		left_pillar_width = (left_pillar_width * tpg->scaled_width) / tpg->src_width;
+		left_pillar_width = (left_pillar_width & ~1) * twopixsize / 2;
+	}
+	if (tpg->crop.left + tpg->crop.width > tpg->border.left + tpg->border.width) {
+		right_pillar_start = tpg->border.left + tpg->border.width - tpg->crop.left;
+		right_pillar_start = (right_pillar_start * tpg->scaled_width) / tpg->src_width;
+		right_pillar_start = (right_pillar_start & ~1) * twopixsize / 2;
+		if (right_pillar_start > img_width)
+			right_pillar_start = img_width;
+	}
+
+	f = tpg->field == (is_60hz ? V4L2_FIELD_TOP : V4L2_FIELD_BOTTOM);
+
+	for (h = 0; h < tpg->compose.height; h++) {
+		bool even;
+		bool fill_blank = false;
+		unsigned frame_line;
+		unsigned buf_line;
+		unsigned pat_line_old;
+		unsigned pat_line_new;
+		u8 *linestart_older;
+		u8 *linestart_newer;
+		u8 *linestart_top;
+		u8 *linestart_bottom;
+
+		frame_line = tpg_calc_frameline(tpg, src_y, tpg->field);
+		even = !(frame_line & 1);
+		buf_line = tpg_calc_buffer_line(tpg, h, tpg->field);
+		src_y += int_part;
+		error += fract_part;
+		if (error >= tpg->compose.height) {
+			error -= tpg->compose.height;
+			src_y++;
+		}
+
+		if (h >= hmax) {
+			if (hmax == tpg->compose.height)
+				continue;
+			if (!tpg->perc_fill_blank)
+				continue;
+			fill_blank = true;
+		}
+
+		if (tpg->vflip)
+			frame_line = tpg->src_height - frame_line - 1;
+
+		if (fill_blank) {
+			linestart_older = tpg->contrast_line[p];
+			linestart_newer = tpg->contrast_line[p];
+		} else if (tpg->qual != TPG_QUAL_NOISE &&
+			   (frame_line < tpg->border.top ||
+			    frame_line >= tpg->border.top + tpg->border.height)) {
+			linestart_older = tpg->black_line[p];
+			linestart_newer = tpg->black_line[p];
+		} else if (tpg->pattern == TPG_PAT_NOISE || tpg->qual == TPG_QUAL_NOISE) {
+			linestart_older = tpg->random_line[p] +
+					  twopixsize * prandom_u32_max(tpg->src_width / 2);
+			linestart_newer = tpg->random_line[p] +
+					  twopixsize * prandom_u32_max(tpg->src_width / 2);
+		} else {
+			pat_line_old = tpg_get_pat_line(tpg,
+						(frame_line + mv_vert_old) % tpg->src_height);
+			pat_line_new = tpg_get_pat_line(tpg,
+						(frame_line + mv_vert_new) % tpg->src_height);
+			linestart_older = tpg->lines[pat_line_old][p] +
+					  mv_hor_old * twopixsize / 2;
+			linestart_newer = tpg->lines[pat_line_new][p] +
+					  mv_hor_new * twopixsize / 2;
+			linestart_older += line_offset;
+			linestart_newer += line_offset;
+		}
+		if (is_60hz) {
+			linestart_top = linestart_newer;
+			linestart_bottom = linestart_older;
+		} else {
+			linestart_top = linestart_older;
+			linestart_bottom = linestart_newer;
+		}
+
+		switch (tpg->field) {
+		case V4L2_FIELD_INTERLACED:
+		case V4L2_FIELD_INTERLACED_TB:
+		case V4L2_FIELD_SEQ_TB:
+		case V4L2_FIELD_SEQ_BT:
+			if (even)
+				memcpy(vbuf + buf_line * stride, linestart_top, img_width);
+			else
+				memcpy(vbuf + buf_line * stride, linestart_bottom, img_width);
+			break;
+		case V4L2_FIELD_INTERLACED_BT:
+			if (even)
+				memcpy(vbuf + buf_line * stride, linestart_bottom, img_width);
+			else
+				memcpy(vbuf + buf_line * stride, linestart_top, img_width);
+			break;
+		case V4L2_FIELD_TOP:
+			memcpy(vbuf + buf_line * stride, linestart_top, img_width);
+			break;
+		case V4L2_FIELD_BOTTOM:
+			memcpy(vbuf + buf_line * stride, linestart_bottom, img_width);
+			break;
+		case V4L2_FIELD_NONE:
+		default:
+			memcpy(vbuf + buf_line * stride, linestart_older, img_width);
+			break;
+		}
+
+		if (is_tv && !is_60hz && frame_line == 0 && wss_width) {
+			/*
+			 * Replace the first half of the top line of a 50 Hz frame
+			 * with random data to simulate a WSS signal.
+			 */
+			u8 *wss = tpg->random_line[p] +
+				  twopixsize * prandom_u32_max(tpg->src_width / 2);
+
+			memcpy(vbuf + buf_line * stride, wss, wss_width * twopixsize / 2);
+		}
+	}
+
+	vbuf = orig_vbuf;
+	vbuf += tpg->compose.left * twopixsize / 2;
+	src_y = 0;
+	error = 0;
+	for (h = 0; h < tpg->compose.height; h++) {
+		unsigned frame_line = tpg_calc_frameline(tpg, src_y, tpg->field);
+		unsigned buf_line = tpg_calc_buffer_line(tpg, h, tpg->field);
+		const struct v4l2_rect *sq = &tpg->square;
+		const struct v4l2_rect *b = &tpg->border;
+		const struct v4l2_rect *c = &tpg->crop;
+
+		src_y += int_part;
+		error += fract_part;
+		if (error >= tpg->compose.height) {
+			error -= tpg->compose.height;
+			src_y++;
+		}
+
+		if (tpg->show_border && frame_line >= b->top &&
+		    frame_line < b->top + b->height) {
+			unsigned bottom = b->top + b->height - 1;
+			unsigned left = left_pillar_width;
+			unsigned right = right_pillar_start;
+
+			if (frame_line == b->top || frame_line == b->top + 1 ||
+			    frame_line == bottom || frame_line == bottom - 1) {
+				memcpy(vbuf + buf_line * stride + left, tpg->contrast_line[p],
+						right - left);
+			} else {
+				if (b->left >= c->left &&
+				    b->left < c->left + c->width)
+					memcpy(vbuf + buf_line * stride + left,
+						tpg->contrast_line[p], twopixsize);
+				if (b->left + b->width > c->left &&
+				    b->left + b->width <= c->left + c->width)
+					memcpy(vbuf + buf_line * stride + right - twopixsize,
+						tpg->contrast_line[p], twopixsize);
+			}
+		}
+		if (tpg->qual != TPG_QUAL_NOISE && frame_line >= b->top &&
+		    frame_line < b->top + b->height) {
+			memcpy(vbuf + buf_line * stride, tpg->black_line[p], left_pillar_width);
+			memcpy(vbuf + buf_line * stride + right_pillar_start, tpg->black_line[p],
+			       img_width - right_pillar_start);
+		}
+		if (tpg->show_square && frame_line >= sq->top &&
+		    frame_line < sq->top + sq->height &&
+		    sq->left < c->left + c->width &&
+		    sq->left + sq->width >= c->left) {
+			unsigned left = sq->left;
+			unsigned width = sq->width;
+
+			if (c->left > left) {
+				width -= c->left - left;
+				left = c->left;
+			}
+			if (c->left + c->width < left + width)
+				width -= left + width - c->left - c->width;
+			left -= c->left;
+			left = (left * tpg->scaled_width) / tpg->src_width;
+			left = (left & ~1) * twopixsize / 2;
+			width = (width * tpg->scaled_width) / tpg->src_width;
+			width = (width & ~1) * twopixsize / 2;
+			memcpy(vbuf + buf_line * stride + left, tpg->contrast_line[p], width);
+		}
+		if (tpg->insert_sav) {
+			unsigned offset = (tpg->compose.width / 6) * twopixsize;
+			u8 *p = vbuf + buf_line * stride + offset;
+			unsigned vact = 0, hact = 0;
+
+			p[0] = 0xff;
+			p[1] = 0;
+			p[2] = 0;
+			p[3] = 0x80 | (f << 6) | (vact << 5) | (hact << 4) |
+				((hact ^ vact) << 3) |
+				((hact ^ f) << 2) |
+				((f ^ vact) << 1) |
+				(hact ^ vact ^ f);
+		}
+		if (tpg->insert_eav) {
+			unsigned offset = (tpg->compose.width / 6) * 2 * twopixsize;
+			u8 *p = vbuf + buf_line * stride + offset;
+			unsigned vact = 0, hact = 1;
+
+			p[0] = 0xff;
+			p[1] = 0;
+			p[2] = 0;
+			p[3] = 0x80 | (f << 6) | (vact << 5) | (hact << 4) |
+				((hact ^ vact) << 3) |
+				((hact ^ f) << 2) |
+				((f ^ vact) << 1) |
+				(hact ^ vact ^ f);
+		}
+	}
+}
diff --git a/drivers/media/platform/vivid/vivid-tpg.h b/drivers/media/platform/vivid/vivid-tpg.h
new file mode 100644
index 000000000000..8ef3e52ba3be
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-tpg.h
@@ -0,0 +1,439 @@
+/*
+ * vivid-tpg.h - Test Pattern Generator
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_TPG_H_
+#define _VIVID_TPG_H_
+
+#include <linux/version.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/videodev2.h>
+
+#include "vivid-tpg-colors.h"
+
+enum tpg_pattern {
+	TPG_PAT_75_COLORBAR,
+	TPG_PAT_100_COLORBAR,
+	TPG_PAT_CSC_COLORBAR,
+	TPG_PAT_100_HCOLORBAR,
+	TPG_PAT_100_COLORSQUARES,
+	TPG_PAT_BLACK,
+	TPG_PAT_WHITE,
+	TPG_PAT_RED,
+	TPG_PAT_GREEN,
+	TPG_PAT_BLUE,
+	TPG_PAT_CHECKERS_16X16,
+	TPG_PAT_CHECKERS_1X1,
+	TPG_PAT_ALTERNATING_HLINES,
+	TPG_PAT_ALTERNATING_VLINES,
+	TPG_PAT_CROSS_1_PIXEL,
+	TPG_PAT_CROSS_2_PIXELS,
+	TPG_PAT_CROSS_10_PIXELS,
+	TPG_PAT_GRAY_RAMP,
+
+	/* Must be the last pattern */
+	TPG_PAT_NOISE,
+};
+
+extern const char * const tpg_pattern_strings[];
+
+enum tpg_quality {
+	TPG_QUAL_COLOR,
+	TPG_QUAL_GRAY,
+	TPG_QUAL_NOISE
+};
+
+enum tpg_video_aspect {
+	TPG_VIDEO_ASPECT_IMAGE,
+	TPG_VIDEO_ASPECT_4X3,
+	TPG_VIDEO_ASPECT_14X9_CENTRE,
+	TPG_VIDEO_ASPECT_16X9_CENTRE,
+	TPG_VIDEO_ASPECT_16X9_ANAMORPHIC,
+};
+
+enum tpg_pixel_aspect {
+	TPG_PIXEL_ASPECT_SQUARE,
+	TPG_PIXEL_ASPECT_NTSC,
+	TPG_PIXEL_ASPECT_PAL,
+};
+
+enum tpg_move_mode {
+	TPG_MOVE_NEG_FAST,
+	TPG_MOVE_NEG,
+	TPG_MOVE_NEG_SLOW,
+	TPG_MOVE_NONE,
+	TPG_MOVE_POS_SLOW,
+	TPG_MOVE_POS,
+	TPG_MOVE_POS_FAST,
+};
+
+extern const char * const tpg_aspect_strings[];
+
+#define TPG_MAX_PLANES 2
+#define TPG_MAX_PAT_LINES 8
+
+struct tpg_data {
+	/* Source frame size */
+	unsigned			src_width, src_height;
+	/* Buffer height */
+	unsigned			buf_height;
+	/* Scaled output frame size */
+	unsigned			scaled_width;
+	u32				field;
+	/* crop coordinates are frame-based */
+	struct v4l2_rect		crop;
+	/* compose coordinates are format-based */
+	struct v4l2_rect		compose;
+	/* border and square coordinates are frame-based */
+	struct v4l2_rect		border;
+	struct v4l2_rect		square;
+
+	/* Color-related fields */
+	enum tpg_quality		qual;
+	unsigned			qual_offset;
+	u8				alpha_component;
+	bool				alpha_red_only;
+	u8				brightness;
+	u8				contrast;
+	u8				saturation;
+	s16				hue;
+	u32				fourcc;
+	bool				is_yuv;
+	u32				colorspace;
+	enum tpg_video_aspect		vid_aspect;
+	enum tpg_pixel_aspect		pix_aspect;
+	unsigned			rgb_range;
+	unsigned			real_rgb_range;
+	unsigned			planes;
+	/* Used to store the colors in native format, either RGB or YUV */
+	u8				colors[TPG_COLOR_MAX][3];
+	u8				textfg[TPG_MAX_PLANES][8], textbg[TPG_MAX_PLANES][8];
+	/* size in bytes for two pixels in each plane */
+	unsigned			twopixelsize[TPG_MAX_PLANES];
+	unsigned			bytesperline[TPG_MAX_PLANES];
+
+	/* Configuration */
+	enum tpg_pattern		pattern;
+	bool				hflip;
+	bool				vflip;
+	unsigned			perc_fill;
+	bool				perc_fill_blank;
+	bool				show_border;
+	bool				show_square;
+	bool				insert_sav;
+	bool				insert_eav;
+
+	/* Test pattern movement */
+	enum tpg_move_mode		mv_hor_mode;
+	int				mv_hor_count;
+	int				mv_hor_step;
+	enum tpg_move_mode		mv_vert_mode;
+	int				mv_vert_count;
+	int				mv_vert_step;
+
+	bool				recalc_colors;
+	bool				recalc_lines;
+	bool				recalc_square_border;
+
+	/* Used to store TPG_MAX_PAT_LINES lines, each with up to two planes */
+	unsigned			max_line_width;
+	u8				*lines[TPG_MAX_PAT_LINES][TPG_MAX_PLANES];
+	u8				*random_line[TPG_MAX_PLANES];
+	u8				*contrast_line[TPG_MAX_PLANES];
+	u8				*black_line[TPG_MAX_PLANES];
+};
+
+void tpg_init(struct tpg_data *tpg, unsigned w, unsigned h);
+int tpg_alloc(struct tpg_data *tpg, unsigned max_w);
+void tpg_free(struct tpg_data *tpg);
+void tpg_reset_source(struct tpg_data *tpg, unsigned width, unsigned height,
+		       u32 field);
+
+void tpg_set_font(const u8 *f);
+void tpg_gen_text(struct tpg_data *tpg,
+		u8 *basep[TPG_MAX_PLANES][2], int y, int x, char *text);
+void tpg_calc_text_basep(struct tpg_data *tpg,
+		u8 *basep[TPG_MAX_PLANES][2], unsigned p, u8 *vbuf);
+void tpg_fillbuffer(struct tpg_data *tpg, v4l2_std_id std, unsigned p, u8 *vbuf);
+bool tpg_s_fourcc(struct tpg_data *tpg, u32 fourcc);
+void tpg_s_crop_compose(struct tpg_data *tpg, const struct v4l2_rect *crop,
+		const struct v4l2_rect *compose);
+
+static inline void tpg_s_pattern(struct tpg_data *tpg, enum tpg_pattern pattern)
+{
+	if (tpg->pattern == pattern)
+		return;
+	tpg->pattern = pattern;
+	tpg->recalc_colors = true;
+}
+
+static inline void tpg_s_quality(struct tpg_data *tpg,
+				    enum tpg_quality qual, unsigned qual_offset)
+{
+	if (tpg->qual == qual && tpg->qual_offset == qual_offset)
+		return;
+	tpg->qual = qual;
+	tpg->qual_offset = qual_offset;
+	tpg->recalc_colors = true;
+}
+
+static inline enum tpg_quality tpg_g_quality(const struct tpg_data *tpg)
+{
+	return tpg->qual;
+}
+
+static inline void tpg_s_alpha_component(struct tpg_data *tpg,
+					    u8 alpha_component)
+{
+	if (tpg->alpha_component == alpha_component)
+		return;
+	tpg->alpha_component = alpha_component;
+	tpg->recalc_colors = true;
+}
+
+static inline void tpg_s_alpha_mode(struct tpg_data *tpg,
+					    bool red_only)
+{
+	if (tpg->alpha_red_only == red_only)
+		return;
+	tpg->alpha_red_only = red_only;
+	tpg->recalc_colors = true;
+}
+
+static inline void tpg_s_brightness(struct tpg_data *tpg,
+					u8 brightness)
+{
+	if (tpg->brightness == brightness)
+		return;
+	tpg->brightness = brightness;
+	tpg->recalc_colors = true;
+}
+
+static inline void tpg_s_contrast(struct tpg_data *tpg,
+					u8 contrast)
+{
+	if (tpg->contrast == contrast)
+		return;
+	tpg->contrast = contrast;
+	tpg->recalc_colors = true;
+}
+
+static inline void tpg_s_saturation(struct tpg_data *tpg,
+					u8 saturation)
+{
+	if (tpg->saturation == saturation)
+		return;
+	tpg->saturation = saturation;
+	tpg->recalc_colors = true;
+}
+
+static inline void tpg_s_hue(struct tpg_data *tpg,
+					s16 hue)
+{
+	if (tpg->hue == hue)
+		return;
+	tpg->hue = hue;
+	tpg->recalc_colors = true;
+}
+
+static inline void tpg_s_rgb_range(struct tpg_data *tpg,
+					unsigned rgb_range)
+{
+	if (tpg->rgb_range == rgb_range)
+		return;
+	tpg->rgb_range = rgb_range;
+	tpg->recalc_colors = true;
+}
+
+static inline void tpg_s_real_rgb_range(struct tpg_data *tpg,
+					unsigned rgb_range)
+{
+	if (tpg->real_rgb_range == rgb_range)
+		return;
+	tpg->real_rgb_range = rgb_range;
+	tpg->recalc_colors = true;
+}
+
+static inline void tpg_s_colorspace(struct tpg_data *tpg, u32 colorspace)
+{
+	if (tpg->colorspace == colorspace)
+		return;
+	tpg->colorspace = colorspace;
+	tpg->recalc_colors = true;
+}
+
+static inline u32 tpg_g_colorspace(const struct tpg_data *tpg)
+{
+	return tpg->colorspace;
+}
+
+static inline unsigned tpg_g_planes(const struct tpg_data *tpg)
+{
+	return tpg->planes;
+}
+
+static inline unsigned tpg_g_twopixelsize(const struct tpg_data *tpg, unsigned plane)
+{
+	return tpg->twopixelsize[plane];
+}
+
+static inline unsigned tpg_g_bytesperline(const struct tpg_data *tpg, unsigned plane)
+{
+	return tpg->bytesperline[plane];
+}
+
+static inline void tpg_s_bytesperline(struct tpg_data *tpg, unsigned plane, unsigned bpl)
+{
+	tpg->bytesperline[plane] = bpl;
+}
+
+static inline void tpg_s_buf_height(struct tpg_data *tpg, unsigned h)
+{
+	tpg->buf_height = h;
+}
+
+static inline void tpg_s_field(struct tpg_data *tpg, unsigned field)
+{
+	tpg->field = field;
+}
+
+static inline void tpg_s_perc_fill(struct tpg_data *tpg,
+				      unsigned perc_fill)
+{
+	tpg->perc_fill = perc_fill;
+}
+
+static inline unsigned tpg_g_perc_fill(const struct tpg_data *tpg)
+{
+	return tpg->perc_fill;
+}
+
+static inline void tpg_s_perc_fill_blank(struct tpg_data *tpg,
+					 bool perc_fill_blank)
+{
+	tpg->perc_fill_blank = perc_fill_blank;
+}
+
+static inline void tpg_s_video_aspect(struct tpg_data *tpg,
+					enum tpg_video_aspect vid_aspect)
+{
+	if (tpg->vid_aspect == vid_aspect)
+		return;
+	tpg->vid_aspect = vid_aspect;
+	tpg->recalc_square_border = true;
+}
+
+static inline enum tpg_video_aspect tpg_g_video_aspect(const struct tpg_data *tpg)
+{
+	return tpg->vid_aspect;
+}
+
+static inline void tpg_s_pixel_aspect(struct tpg_data *tpg,
+					enum tpg_pixel_aspect pix_aspect)
+{
+	if (tpg->pix_aspect == pix_aspect)
+		return;
+	tpg->pix_aspect = pix_aspect;
+	tpg->recalc_square_border = true;
+}
+
+static inline void tpg_s_show_border(struct tpg_data *tpg,
+					bool show_border)
+{
+	tpg->show_border = show_border;
+}
+
+static inline void tpg_s_show_square(struct tpg_data *tpg,
+					bool show_square)
+{
+	tpg->show_square = show_square;
+}
+
+static inline void tpg_s_insert_sav(struct tpg_data *tpg, bool insert_sav)
+{
+	tpg->insert_sav = insert_sav;
+}
+
+static inline void tpg_s_insert_eav(struct tpg_data *tpg, bool insert_eav)
+{
+	tpg->insert_eav = insert_eav;
+}
+
+void tpg_update_mv_step(struct tpg_data *tpg);
+
+static inline void tpg_s_mv_hor_mode(struct tpg_data *tpg,
+				enum tpg_move_mode mv_hor_mode)
+{
+	tpg->mv_hor_mode = mv_hor_mode;
+	tpg_update_mv_step(tpg);
+}
+
+static inline void tpg_s_mv_vert_mode(struct tpg_data *tpg,
+				enum tpg_move_mode mv_vert_mode)
+{
+	tpg->mv_vert_mode = mv_vert_mode;
+	tpg_update_mv_step(tpg);
+}
+
+static inline void tpg_init_mv_count(struct tpg_data *tpg)
+{
+	tpg->mv_hor_count = tpg->mv_vert_count = 0;
+}
+
+static inline void tpg_update_mv_count(struct tpg_data *tpg, bool frame_is_field)
+{
+	tpg->mv_hor_count += tpg->mv_hor_step * (frame_is_field ? 1 : 2);
+	tpg->mv_vert_count += tpg->mv_vert_step * (frame_is_field ? 1 : 2);
+}
+
+static inline void tpg_s_hflip(struct tpg_data *tpg, bool hflip)
+{
+	if (tpg->hflip == hflip)
+		return;
+	tpg->hflip = hflip;
+	tpg_update_mv_step(tpg);
+	tpg->recalc_lines = true;
+}
+
+static inline bool tpg_g_hflip(const struct tpg_data *tpg)
+{
+	return tpg->hflip;
+}
+
+static inline void tpg_s_vflip(struct tpg_data *tpg, bool vflip)
+{
+	tpg->vflip = vflip;
+}
+
+static inline bool tpg_g_vflip(const struct tpg_data *tpg)
+{
+	return tpg->vflip;
+}
+
+static inline bool tpg_pattern_is_static(const struct tpg_data *tpg)
+{
+	return tpg->pattern != TPG_PAT_NOISE &&
+	       tpg->mv_hor_mode == TPG_MOVE_NONE &&
+	       tpg->mv_vert_mode == TPG_MOVE_NONE;
+}
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-vbi-cap.c b/drivers/media/platform/vivid/vivid-vbi-cap.c
new file mode 100644
index 000000000000..2166d0bf6fe2
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vbi-cap.c
@@ -0,0 +1,371 @@
+/*
+ * vivid-vbi-cap.c - vbi capture support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/videodev2.h>
+#include <media/v4l2-common.h>
+
+#include "vivid-core.h"
+#include "vivid-kthread-cap.h"
+#include "vivid-vbi-cap.h"
+#include "vivid-vbi-gen.h"
+
+static void vivid_sliced_vbi_cap_fill(struct vivid_dev *dev, unsigned seqnr)
+{
+	struct vivid_vbi_gen_data *vbi_gen = &dev->vbi_gen;
+	bool is_60hz = dev->std_cap & V4L2_STD_525_60;
+
+	vivid_vbi_gen_sliced(vbi_gen, is_60hz, seqnr);
+
+	if (!is_60hz) {
+		if (dev->loop_video) {
+			if (dev->vbi_out_have_wss) {
+				vbi_gen->data[12].data[0] = dev->vbi_out_wss[0];
+				vbi_gen->data[12].data[1] = dev->vbi_out_wss[1];
+			} else {
+				vbi_gen->data[12].id = 0;
+			}
+		} else {
+			switch (tpg_g_video_aspect(&dev->tpg)) {
+			case TPG_VIDEO_ASPECT_14X9_CENTRE:
+				vbi_gen->data[12].data[0] = 0x01;
+				break;
+			case TPG_VIDEO_ASPECT_16X9_CENTRE:
+				vbi_gen->data[12].data[0] = 0x0b;
+				break;
+			case TPG_VIDEO_ASPECT_16X9_ANAMORPHIC:
+				vbi_gen->data[12].data[0] = 0x07;
+				break;
+			case TPG_VIDEO_ASPECT_4X3:
+			default:
+				vbi_gen->data[12].data[0] = 0x08;
+				break;
+			}
+		}
+	} else if (dev->loop_video && is_60hz) {
+		if (dev->vbi_out_have_cc[0]) {
+			vbi_gen->data[0].data[0] = dev->vbi_out_cc[0][0];
+			vbi_gen->data[0].data[1] = dev->vbi_out_cc[0][1];
+		} else {
+			vbi_gen->data[0].id = 0;
+		}
+		if (dev->vbi_out_have_cc[1]) {
+			vbi_gen->data[1].data[0] = dev->vbi_out_cc[1][0];
+			vbi_gen->data[1].data[1] = dev->vbi_out_cc[1][1];
+		} else {
+			vbi_gen->data[1].id = 0;
+		}
+	}
+}
+
+static void vivid_g_fmt_vbi_cap(struct vivid_dev *dev, struct v4l2_vbi_format *vbi)
+{
+	bool is_60hz = dev->std_cap & V4L2_STD_525_60;
+
+	vbi->sampling_rate = 27000000;
+	vbi->offset = 24;
+	vbi->samples_per_line = 1440;
+	vbi->sample_format = V4L2_PIX_FMT_GREY;
+	vbi->start[0] = is_60hz ? V4L2_VBI_ITU_525_F1_START + 9 : V4L2_VBI_ITU_625_F1_START + 5;
+	vbi->start[1] = is_60hz ? V4L2_VBI_ITU_525_F2_START + 9 : V4L2_VBI_ITU_625_F2_START + 5;
+	vbi->count[0] = vbi->count[1] = is_60hz ? 12 : 18;
+	vbi->flags = dev->vbi_cap_interlaced ? V4L2_VBI_INTERLACED : 0;
+	vbi->reserved[0] = 0;
+	vbi->reserved[1] = 0;
+}
+
+void vivid_raw_vbi_cap_process(struct vivid_dev *dev, struct vivid_buffer *buf)
+{
+	struct v4l2_vbi_format vbi;
+	u8 *vbuf = vb2_plane_vaddr(&buf->vb, 0);
+
+	vivid_g_fmt_vbi_cap(dev, &vbi);
+	buf->vb.v4l2_buf.sequence = dev->vbi_cap_seq_count;
+	if (dev->field_cap == V4L2_FIELD_ALTERNATE)
+		buf->vb.v4l2_buf.sequence /= 2;
+
+	vivid_sliced_vbi_cap_fill(dev, buf->vb.v4l2_buf.sequence);
+
+	memset(vbuf, 0x10, vb2_plane_size(&buf->vb, 0));
+
+	if (!VIVID_INVALID_SIGNAL(dev->std_signal_mode))
+		vivid_vbi_gen_raw(&dev->vbi_gen, &vbi, vbuf);
+
+	v4l2_get_timestamp(&buf->vb.v4l2_buf.timestamp);
+	buf->vb.v4l2_buf.timestamp.tv_sec += dev->time_wrap_offset;
+}
+
+
+void vivid_sliced_vbi_cap_process(struct vivid_dev *dev, struct vivid_buffer *buf)
+{
+	struct v4l2_sliced_vbi_data *vbuf = vb2_plane_vaddr(&buf->vb, 0);
+
+	buf->vb.v4l2_buf.sequence = dev->vbi_cap_seq_count;
+	if (dev->field_cap == V4L2_FIELD_ALTERNATE)
+		buf->vb.v4l2_buf.sequence /= 2;
+
+	vivid_sliced_vbi_cap_fill(dev, buf->vb.v4l2_buf.sequence);
+
+	memset(vbuf, 0, vb2_plane_size(&buf->vb, 0));
+	if (!VIVID_INVALID_SIGNAL(dev->std_signal_mode)) {
+		unsigned i;
+
+		for (i = 0; i < 25; i++)
+			vbuf[i] = dev->vbi_gen.data[i];
+	}
+
+	v4l2_get_timestamp(&buf->vb.v4l2_buf.timestamp);
+	buf->vb.v4l2_buf.timestamp.tv_sec += dev->time_wrap_offset;
+}
+
+static int vbi_cap_queue_setup(struct vb2_queue *vq, const struct v4l2_format *fmt,
+		       unsigned *nbuffers, unsigned *nplanes,
+		       unsigned sizes[], void *alloc_ctxs[])
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	bool is_60hz = dev->std_cap & V4L2_STD_525_60;
+	unsigned size = vq->type == V4L2_BUF_TYPE_SLICED_VBI_CAPTURE ?
+		36 * sizeof(struct v4l2_sliced_vbi_data) :
+		1440 * 2 * (is_60hz ? 12 : 18);
+
+	if (!vivid_is_sdtv_cap(dev))
+		return -EINVAL;
+
+	sizes[0] = size;
+
+	if (vq->num_buffers + *nbuffers < 2)
+		*nbuffers = 2 - vq->num_buffers;
+
+	*nplanes = 1;
+	return 0;
+}
+
+static int vbi_cap_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	bool is_60hz = dev->std_cap & V4L2_STD_525_60;
+	unsigned size = vb->vb2_queue->type == V4L2_BUF_TYPE_SLICED_VBI_CAPTURE ?
+		36 * sizeof(struct v4l2_sliced_vbi_data) :
+		1440 * 2 * (is_60hz ? 12 : 18);
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	if (dev->buf_prepare_error) {
+		/*
+		 * Error injection: test what happens if buf_prepare() returns
+		 * an error.
+		 */
+		dev->buf_prepare_error = false;
+		return -EINVAL;
+	}
+	if (vb2_plane_size(vb, 0) < size) {
+		dprintk(dev, 1, "%s data will not fit into plane (%lu < %u)\n",
+				__func__, vb2_plane_size(vb, 0), size);
+		return -EINVAL;
+	}
+	vb2_set_plane_payload(vb, 0, size);
+
+	return 0;
+}
+
+static void vbi_cap_buf_queue(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct vivid_buffer *buf = container_of(vb, struct vivid_buffer, vb);
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	spin_lock(&dev->slock);
+	list_add_tail(&buf->list, &dev->vbi_cap_active);
+	spin_unlock(&dev->slock);
+}
+
+static int vbi_cap_start_streaming(struct vb2_queue *vq, unsigned count)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	int err;
+
+	dprintk(dev, 1, "%s\n", __func__);
+	dev->vbi_cap_seq_count = 0;
+	if (dev->start_streaming_error) {
+		dev->start_streaming_error = false;
+		err = -EINVAL;
+	} else {
+		err = vivid_start_generating_vid_cap(dev, &dev->vbi_cap_streaming);
+	}
+	if (err) {
+		struct vivid_buffer *buf, *tmp;
+
+		list_for_each_entry_safe(buf, tmp, &dev->vbi_cap_active, list) {
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
+		}
+	}
+	return err;
+}
+
+/* abort streaming and wait for last buffer */
+static void vbi_cap_stop_streaming(struct vb2_queue *vq)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+
+	dprintk(dev, 1, "%s\n", __func__);
+	vivid_stop_generating_vid_cap(dev, &dev->vbi_cap_streaming);
+}
+
+const struct vb2_ops vivid_vbi_cap_qops = {
+	.queue_setup		= vbi_cap_queue_setup,
+	.buf_prepare		= vbi_cap_buf_prepare,
+	.buf_queue		= vbi_cap_buf_queue,
+	.start_streaming	= vbi_cap_start_streaming,
+	.stop_streaming		= vbi_cap_stop_streaming,
+	.wait_prepare		= vivid_unlock,
+	.wait_finish		= vivid_lock,
+};
+
+int vidioc_g_fmt_vbi_cap(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_vbi_format *vbi = &f->fmt.vbi;
+
+	if (!vivid_is_sdtv_cap(dev) || !dev->has_raw_vbi_cap)
+		return -EINVAL;
+
+	vivid_g_fmt_vbi_cap(dev, vbi);
+	return 0;
+}
+
+int vidioc_s_fmt_vbi_cap(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	int ret = vidioc_g_fmt_vbi_cap(file, priv, f);
+
+	if (ret)
+		return ret;
+	if (dev->stream_sliced_vbi_cap && vb2_is_busy(&dev->vb_vbi_cap_q))
+		return -EBUSY;
+	dev->stream_sliced_vbi_cap = false;
+	dev->vbi_cap_dev.queue->type = V4L2_BUF_TYPE_VBI_CAPTURE;
+	return 0;
+}
+
+void vivid_fill_service_lines(struct v4l2_sliced_vbi_format *vbi, u32 service_set)
+{
+	vbi->io_size = sizeof(struct v4l2_sliced_vbi_data) * 36;
+	vbi->service_set = service_set;
+	memset(vbi->service_lines, 0, sizeof(vbi->service_lines));
+	memset(vbi->reserved, 0, sizeof(vbi->reserved));
+
+	if (vbi->service_set == 0)
+		return;
+
+	if (vbi->service_set & V4L2_SLICED_CAPTION_525) {
+		vbi->service_lines[0][21] = V4L2_SLICED_CAPTION_525;
+		vbi->service_lines[1][21] = V4L2_SLICED_CAPTION_525;
+	}
+	if (vbi->service_set & V4L2_SLICED_WSS_625) {
+		unsigned i;
+
+		for (i = 7; i <= 18; i++)
+			vbi->service_lines[0][i] =
+			vbi->service_lines[1][i] = V4L2_SLICED_TELETEXT_B;
+		vbi->service_lines[0][23] = V4L2_SLICED_WSS_625;
+	}
+}
+
+int vidioc_g_fmt_sliced_vbi_cap(struct file *file, void *fh, struct v4l2_format *fmt)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_sliced_vbi_format *vbi = &fmt->fmt.sliced;
+
+	if (!vivid_is_sdtv_cap(dev) || !dev->has_sliced_vbi_cap)
+		return -EINVAL;
+
+	vivid_fill_service_lines(vbi, dev->service_set_cap);
+	return 0;
+}
+
+int vidioc_try_fmt_sliced_vbi_cap(struct file *file, void *fh, struct v4l2_format *fmt)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_sliced_vbi_format *vbi = &fmt->fmt.sliced;
+	bool is_60hz = dev->std_cap & V4L2_STD_525_60;
+	u32 service_set = vbi->service_set;
+
+	if (!vivid_is_sdtv_cap(dev) || !dev->has_sliced_vbi_cap)
+		return -EINVAL;
+
+	service_set &= is_60hz ? V4L2_SLICED_CAPTION_525 :
+				 V4L2_SLICED_WSS_625 | V4L2_SLICED_TELETEXT_B;
+	vivid_fill_service_lines(vbi, service_set);
+	return 0;
+}
+
+int vidioc_s_fmt_sliced_vbi_cap(struct file *file, void *fh, struct v4l2_format *fmt)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_sliced_vbi_format *vbi = &fmt->fmt.sliced;
+	int ret = vidioc_try_fmt_sliced_vbi_cap(file, fh, fmt);
+
+	if (ret)
+		return ret;
+	if (!dev->stream_sliced_vbi_cap && vb2_is_busy(&dev->vb_vbi_cap_q))
+		return -EBUSY;
+	dev->service_set_cap = vbi->service_set;
+	dev->stream_sliced_vbi_cap = true;
+	dev->vbi_cap_dev.queue->type = V4L2_BUF_TYPE_SLICED_VBI_CAPTURE;
+	return 0;
+}
+
+int vidioc_g_sliced_vbi_cap(struct file *file, void *fh, struct v4l2_sliced_vbi_cap *cap)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct video_device *vdev = video_devdata(file);
+	bool is_60hz;
+
+	if (vdev->vfl_dir == VFL_DIR_RX) {
+		is_60hz = dev->std_cap & V4L2_STD_525_60;
+		if (!vivid_is_sdtv_cap(dev) || !dev->has_sliced_vbi_cap ||
+		    cap->type != V4L2_BUF_TYPE_SLICED_VBI_CAPTURE)
+			return -EINVAL;
+	} else {
+		is_60hz = dev->std_out & V4L2_STD_525_60;
+		if (!vivid_is_svid_out(dev) || !dev->has_sliced_vbi_out ||
+		    cap->type != V4L2_BUF_TYPE_SLICED_VBI_OUTPUT)
+			return -EINVAL;
+	}
+
+	cap->service_set = is_60hz ? V4L2_SLICED_CAPTION_525 :
+				     V4L2_SLICED_WSS_625 | V4L2_SLICED_TELETEXT_B;
+	if (is_60hz) {
+		cap->service_lines[0][21] = V4L2_SLICED_CAPTION_525;
+		cap->service_lines[1][21] = V4L2_SLICED_CAPTION_525;
+	} else {
+		unsigned i;
+
+		for (i = 7; i <= 18; i++)
+			cap->service_lines[0][i] =
+			cap->service_lines[1][i] = V4L2_SLICED_TELETEXT_B;
+		cap->service_lines[0][23] = V4L2_SLICED_WSS_625;
+	}
+	return 0;
+}
diff --git a/drivers/media/platform/vivid/vivid-vbi-cap.h b/drivers/media/platform/vivid/vivid-vbi-cap.h
new file mode 100644
index 000000000000..2d8ea0bac743
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vbi-cap.h
@@ -0,0 +1,40 @@
+/*
+ * vivid-vbi-cap.h - vbi capture support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_VBI_CAP_H_
+#define _VIVID_VBI_CAP_H_
+
+void vivid_fill_time_of_day_packet(u8 *packet);
+void vivid_raw_vbi_cap_process(struct vivid_dev *dev, struct vivid_buffer *buf);
+void vivid_sliced_vbi_cap_process(struct vivid_dev *dev, struct vivid_buffer *buf);
+void vivid_sliced_vbi_out_process(struct vivid_dev *dev, struct vivid_buffer *buf);
+int vidioc_g_fmt_vbi_cap(struct file *file, void *priv,
+					struct v4l2_format *f);
+int vidioc_s_fmt_vbi_cap(struct file *file, void *priv,
+					struct v4l2_format *f);
+int vidioc_g_fmt_sliced_vbi_cap(struct file *file, void *fh, struct v4l2_format *fmt);
+int vidioc_try_fmt_sliced_vbi_cap(struct file *file, void *fh, struct v4l2_format *fmt);
+int vidioc_s_fmt_sliced_vbi_cap(struct file *file, void *fh, struct v4l2_format *fmt);
+int vidioc_g_sliced_vbi_cap(struct file *file, void *fh, struct v4l2_sliced_vbi_cap *cap);
+
+void vivid_fill_service_lines(struct v4l2_sliced_vbi_format *vbi, u32 service_set);
+
+extern const struct vb2_ops vivid_vbi_cap_qops;
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-vbi-gen.c b/drivers/media/platform/vivid/vivid-vbi-gen.c
new file mode 100644
index 000000000000..a2159de83d0b
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vbi-gen.c
@@ -0,0 +1,323 @@
+/*
+ * vivid-vbi-gen.c - vbi generator support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/ktime.h>
+#include <linux/string.h>
+#include <linux/videodev2.h>
+
+#include "vivid-vbi-gen.h"
+
+static void wss_insert(u8 *wss, u32 val, unsigned size)
+{
+	while (size--)
+		*wss++ = (val & (1 << size)) ? 0xc0 : 0x10;
+}
+
+static void vivid_vbi_gen_wss_raw(const struct v4l2_sliced_vbi_data *data,
+		u8 *buf, unsigned sampling_rate)
+{
+	const unsigned rate = 5000000;	/* WSS has a 5 MHz transmission rate */
+	u8 wss[29 + 24 + 24 + 24 + 18 + 18] = { 0 };
+	const unsigned zero = 0x07;
+	const unsigned one = 0x38;
+	unsigned bit = 0;
+	u16 wss_data;
+	int i;
+
+	wss_insert(wss + bit, 0x1f1c71c7, 29); bit += 29;
+	wss_insert(wss + bit, 0x1e3c1f, 24); bit += 24;
+
+	wss_data = (data->data[1] << 8) | data->data[0];
+	for (i = 0; i <= 13; i++, bit += 6)
+		wss_insert(wss + bit, (wss_data & (1 << i)) ? one : zero, 6);
+
+	for (i = 0, bit = 0; bit < sizeof(wss); bit++) {
+		unsigned n = ((bit + 1) * sampling_rate) / rate;
+
+		while (i < n)
+			buf[i++] = wss[bit];
+	}
+}
+
+static void vivid_vbi_gen_teletext_raw(const struct v4l2_sliced_vbi_data *data,
+		u8 *buf, unsigned sampling_rate)
+{
+	const unsigned rate = 6937500 / 10;	/* Teletext has a 6.9375 MHz transmission rate */
+	u8 teletext[45] = { 0x55, 0x55, 0x27 };
+	unsigned bit = 0;
+	int i;
+
+	memcpy(teletext + 3, data->data, sizeof(teletext) - 3);
+	/* prevents 32 bit overflow */
+	sampling_rate /= 10;
+
+	for (i = 0, bit = 0; bit < sizeof(teletext) * 8; bit++) {
+		unsigned n = ((bit + 1) * sampling_rate) / rate;
+		u8 val = (teletext[bit / 8] & (1 << (bit & 7))) ? 0xc0 : 0x10;
+
+		while (i < n)
+			buf[i++] = val;
+	}
+}
+
+static void cc_insert(u8 *cc, u8 ch)
+{
+	unsigned tot = 0;
+	unsigned i;
+
+	for (i = 0; i < 7; i++) {
+		cc[2 * i] = cc[2 * i + 1] = (ch & (1 << i)) ? 1 : 0;
+		tot += cc[2 * i];
+	}
+	cc[14] = cc[15] = !(tot & 1);
+}
+
+#define CC_PREAMBLE_BITS (14 + 4 + 2)
+
+static void vivid_vbi_gen_cc_raw(const struct v4l2_sliced_vbi_data *data,
+		u8 *buf, unsigned sampling_rate)
+{
+	const unsigned rate = 1000000;	/* CC has a 1 MHz transmission rate */
+
+	u8 cc[CC_PREAMBLE_BITS + 2 * 16] = {
+		/* Clock run-in: 7 cycles */
+		0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1,
+		/* 2 cycles of 0 */
+		0, 0, 0, 0,
+		/* Start bit of 1 (each bit is two cycles) */
+		1, 1
+	};
+	unsigned bit, i;
+
+	cc_insert(cc + CC_PREAMBLE_BITS, data->data[0]);
+	cc_insert(cc + CC_PREAMBLE_BITS + 16, data->data[1]);
+
+	for (i = 0, bit = 0; bit < sizeof(cc); bit++) {
+		unsigned n = ((bit + 1) * sampling_rate) / rate;
+
+		while (i < n)
+			buf[i++] = cc[bit] ? 0xc0 : 0x10;
+	}
+}
+
+void vivid_vbi_gen_raw(const struct vivid_vbi_gen_data *vbi,
+		const struct v4l2_vbi_format *vbi_fmt, u8 *buf)
+{
+	unsigned idx;
+
+	for (idx = 0; idx < 25; idx++) {
+		const struct v4l2_sliced_vbi_data *data = vbi->data + idx;
+		unsigned start_2nd_field;
+		unsigned line = data->line;
+		u8 *linebuf = buf;
+
+		start_2nd_field = (data->id & V4L2_SLICED_VBI_525) ? 263 : 313;
+		if (data->field)
+			line += start_2nd_field;
+		line -= vbi_fmt->start[data->field];
+
+		if (vbi_fmt->flags & V4L2_VBI_INTERLACED)
+			linebuf += (line * 2 + data->field) *
+				vbi_fmt->samples_per_line;
+		else
+			linebuf += (line + data->field * vbi_fmt->count[0]) *
+				vbi_fmt->samples_per_line;
+		if (data->id == V4L2_SLICED_CAPTION_525)
+			vivid_vbi_gen_cc_raw(data, linebuf, vbi_fmt->sampling_rate);
+		else if (data->id == V4L2_SLICED_WSS_625)
+			vivid_vbi_gen_wss_raw(data, linebuf, vbi_fmt->sampling_rate);
+		else if (data->id == V4L2_SLICED_TELETEXT_B)
+			vivid_vbi_gen_teletext_raw(data, linebuf, vbi_fmt->sampling_rate);
+	}
+}
+
+static const u8 vivid_cc_sequence1[30] = {
+	0x14, 0x20,	/* Resume Caption Loading */
+	'H',  'e',
+	'l',  'l',
+	'o',  ' ',
+	'w',  'o',
+	'r',  'l',
+	'd',  '!',
+	0x14, 0x2f,	/* End of Caption */
+};
+
+static const u8 vivid_cc_sequence2[30] = {
+	0x14, 0x20,	/* Resume Caption Loading */
+	'C',  'l',
+	'o',  's',
+	'e',  'd',
+	' ',  'c',
+	'a',  'p',
+	't',  'i',
+	'o',  'n',
+	's',  ' ',
+	't',  'e',
+	's',  't',
+	0x14, 0x2f,	/* End of Caption */
+};
+
+static u8 calc_parity(u8 val)
+{
+	unsigned i;
+	unsigned tot = 0;
+
+	for (i = 0; i < 7; i++)
+		tot += (val & (1 << i)) ? 1 : 0;
+	return val | ((tot & 1) ? 0 : 0x80);
+}
+
+static void vivid_vbi_gen_set_time_of_day(u8 *packet)
+{
+	struct tm tm;
+	u8 checksum, i;
+
+	time_to_tm(get_seconds(), 0, &tm);
+	packet[0] = calc_parity(0x07);
+	packet[1] = calc_parity(0x01);
+	packet[2] = calc_parity(0x40 | tm.tm_min);
+	packet[3] = calc_parity(0x40 | tm.tm_hour);
+	packet[4] = calc_parity(0x40 | tm.tm_mday);
+	if (tm.tm_mday == 1 && tm.tm_mon == 2 &&
+	    sys_tz.tz_minuteswest > tm.tm_min + tm.tm_hour * 60)
+		packet[4] = calc_parity(0x60 | tm.tm_mday);
+	packet[5] = calc_parity(0x40 | (1 + tm.tm_mon));
+	packet[6] = calc_parity(0x40 | (1 + tm.tm_wday));
+	packet[7] = calc_parity(0x40 | ((tm.tm_year - 90) & 0x3f));
+	packet[8] = calc_parity(0x0f);
+	for (checksum = i = 0; i <= 8; i++)
+		checksum += packet[i] & 0x7f;
+	packet[9] = calc_parity(0x100 - checksum);
+	checksum = 0;
+	packet[10] = calc_parity(0x07);
+	packet[11] = calc_parity(0x04);
+	if (sys_tz.tz_minuteswest >= 0)
+		packet[12] = calc_parity(0x40 | ((sys_tz.tz_minuteswest / 60) & 0x1f));
+	else
+		packet[12] = calc_parity(0x40 | ((24 + sys_tz.tz_minuteswest / 60) & 0x1f));
+	packet[13] = calc_parity(0);
+	packet[14] = calc_parity(0x0f);
+	for (checksum = 0, i = 10; i <= 14; i++)
+		checksum += packet[i] & 0x7f;
+	packet[15] = calc_parity(0x100 - checksum);
+}
+
+static const u8 hamming[16] = {
+	0x15, 0x02, 0x49, 0x5e, 0x64, 0x73, 0x38, 0x2f,
+	0xd0, 0xc7, 0x8c, 0x9b, 0xa1, 0xb6, 0xfd, 0xea
+};
+
+static void vivid_vbi_gen_teletext(u8 *packet, unsigned line, unsigned frame)
+{
+	unsigned offset = 2;
+	unsigned i;
+
+	packet[0] = hamming[1 + ((line & 1) << 3)];
+	packet[1] = hamming[line >> 1];
+	memset(packet + 2, 0x20, 40);
+	if (line == 0) {
+		/* subcode */
+		packet[2] = hamming[frame % 10];
+		packet[3] = hamming[frame / 10];
+		packet[4] = hamming[0];
+		packet[5] = hamming[0];
+		packet[6] = hamming[0];
+		packet[7] = hamming[0];
+		packet[8] = hamming[0];
+		packet[9] = hamming[1];
+		offset = 10;
+	}
+	packet += offset;
+	memcpy(packet, "Page: 100 Row: 10", 17);
+	packet[7] = '0' + frame / 10;
+	packet[8] = '0' + frame % 10;
+	packet[15] = '0' + line / 10;
+	packet[16] = '0' + line % 10;
+	for (i = 0; i < 42 - offset; i++)
+		packet[i] = calc_parity(packet[i]);
+}
+
+void vivid_vbi_gen_sliced(struct vivid_vbi_gen_data *vbi,
+		bool is_60hz, unsigned seqnr)
+{
+	struct v4l2_sliced_vbi_data *data0 = vbi->data;
+	struct v4l2_sliced_vbi_data *data1 = vbi->data + 1;
+	unsigned frame = seqnr % 60;
+
+	memset(vbi->data, 0, sizeof(vbi->data));
+
+	if (!is_60hz) {
+		unsigned i;
+
+		for (i = 0; i <= 11; i++) {
+			data0->id = V4L2_SLICED_TELETEXT_B;
+			data0->line = 7 + i;
+			vivid_vbi_gen_teletext(data0->data, i, frame);
+			data0++;
+		}
+		data0->id = V4L2_SLICED_WSS_625;
+		data0->line = 23;
+		/* 4x3 video aspect ratio */
+		data0->data[0] = 0x08;
+		data0++;
+		for (i = 0; i <= 11; i++) {
+			data0->id = V4L2_SLICED_TELETEXT_B;
+			data0->field = 1;
+			data0->line = 7 + i;
+			vivid_vbi_gen_teletext(data0->data, 12 + i, frame);
+			data0++;
+		}
+		return;
+	}
+
+	data0->id = V4L2_SLICED_CAPTION_525;
+	data0->line = 21;
+	data1->id = V4L2_SLICED_CAPTION_525;
+	data1->field = 1;
+	data1->line = 21;
+
+	if (frame < 15) {
+		data0->data[0] = calc_parity(vivid_cc_sequence1[2 * frame]);
+		data0->data[1] = calc_parity(vivid_cc_sequence1[2 * frame + 1]);
+	} else if (frame >= 30 && frame < 45) {
+		frame -= 30;
+		data0->data[0] = calc_parity(vivid_cc_sequence2[2 * frame]);
+		data0->data[1] = calc_parity(vivid_cc_sequence2[2 * frame + 1]);
+	} else {
+		data0->data[0] = calc_parity(0);
+		data0->data[1] = calc_parity(0);
+	}
+
+	frame = seqnr % (30 * 60);
+	switch (frame) {
+	case 0:
+		vivid_vbi_gen_set_time_of_day(vbi->time_of_day_packet);
+		/* fall through */
+	case 1 ... 7:
+		data1->data[0] = vbi->time_of_day_packet[frame * 2];
+		data1->data[1] = vbi->time_of_day_packet[frame * 2 + 1];
+		break;
+	default:
+		data1->data[0] = calc_parity(0);
+		data1->data[1] = calc_parity(0);
+		break;
+	}
+}
diff --git a/drivers/media/platform/vivid/vivid-vbi-gen.h b/drivers/media/platform/vivid/vivid-vbi-gen.h
new file mode 100644
index 000000000000..8444abe905ea
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vbi-gen.h
@@ -0,0 +1,33 @@
+/*
+ * vivid-vbi-gen.h - vbi generator support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_VBI_GEN_H_
+#define _VIVID_VBI_GEN_H_
+
+struct vivid_vbi_gen_data {
+	struct v4l2_sliced_vbi_data data[25];
+	u8 time_of_day_packet[16];
+};
+
+void vivid_vbi_gen_sliced(struct vivid_vbi_gen_data *vbi,
+		bool is_60hz, unsigned seqnr);
+void vivid_vbi_gen_raw(const struct vivid_vbi_gen_data *vbi,
+		const struct v4l2_vbi_format *vbi_fmt, u8 *buf);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-vbi-out.c b/drivers/media/platform/vivid/vivid-vbi-out.c
new file mode 100644
index 000000000000..9d00a07ecdcd
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vbi-out.c
@@ -0,0 +1,248 @@
+/*
+ * vivid-vbi-out.c - vbi output support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/videodev2.h>
+#include <media/v4l2-common.h>
+
+#include "vivid-core.h"
+#include "vivid-kthread-out.h"
+#include "vivid-vbi-out.h"
+#include "vivid-vbi-cap.h"
+
+static int vbi_out_queue_setup(struct vb2_queue *vq, const struct v4l2_format *fmt,
+		       unsigned *nbuffers, unsigned *nplanes,
+		       unsigned sizes[], void *alloc_ctxs[])
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	bool is_60hz = dev->std_out & V4L2_STD_525_60;
+	unsigned size = vq->type == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT ?
+		36 * sizeof(struct v4l2_sliced_vbi_data) :
+		1440 * 2 * (is_60hz ? 12 : 18);
+
+	if (!vivid_is_svid_out(dev))
+		return -EINVAL;
+
+	sizes[0] = size;
+
+	if (vq->num_buffers + *nbuffers < 2)
+		*nbuffers = 2 - vq->num_buffers;
+
+	*nplanes = 1;
+	return 0;
+}
+
+static int vbi_out_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	bool is_60hz = dev->std_out & V4L2_STD_525_60;
+	unsigned size = vb->vb2_queue->type == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT ?
+		36 * sizeof(struct v4l2_sliced_vbi_data) :
+		1440 * 2 * (is_60hz ? 12 : 18);
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	if (dev->buf_prepare_error) {
+		/*
+		 * Error injection: test what happens if buf_prepare() returns
+		 * an error.
+		 */
+		dev->buf_prepare_error = false;
+		return -EINVAL;
+	}
+	if (vb2_plane_size(vb, 0) < size) {
+		dprintk(dev, 1, "%s data will not fit into plane (%lu < %u)\n",
+				__func__, vb2_plane_size(vb, 0), size);
+		return -EINVAL;
+	}
+	vb2_set_plane_payload(vb, 0, size);
+
+	return 0;
+}
+
+static void vbi_out_buf_queue(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct vivid_buffer *buf = container_of(vb, struct vivid_buffer, vb);
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	spin_lock(&dev->slock);
+	list_add_tail(&buf->list, &dev->vbi_out_active);
+	spin_unlock(&dev->slock);
+}
+
+static int vbi_out_start_streaming(struct vb2_queue *vq, unsigned count)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	int err;
+
+	dprintk(dev, 1, "%s\n", __func__);
+	dev->vbi_out_seq_count = 0;
+	if (dev->start_streaming_error) {
+		dev->start_streaming_error = false;
+		err = -EINVAL;
+	} else {
+		err = vivid_start_generating_vid_out(dev, &dev->vbi_out_streaming);
+	}
+	if (err) {
+		struct vivid_buffer *buf, *tmp;
+
+		list_for_each_entry_safe(buf, tmp, &dev->vbi_out_active, list) {
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
+		}
+	}
+	return err;
+}
+
+/* abort streaming and wait for last buffer */
+static void vbi_out_stop_streaming(struct vb2_queue *vq)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+
+	dprintk(dev, 1, "%s\n", __func__);
+	vivid_stop_generating_vid_out(dev, &dev->vbi_out_streaming);
+	dev->vbi_out_have_wss = false;
+	dev->vbi_out_have_cc[0] = false;
+	dev->vbi_out_have_cc[1] = false;
+}
+
+const struct vb2_ops vivid_vbi_out_qops = {
+	.queue_setup		= vbi_out_queue_setup,
+	.buf_prepare		= vbi_out_buf_prepare,
+	.buf_queue		= vbi_out_buf_queue,
+	.start_streaming	= vbi_out_start_streaming,
+	.stop_streaming		= vbi_out_stop_streaming,
+	.wait_prepare		= vivid_unlock,
+	.wait_finish		= vivid_lock,
+};
+
+int vidioc_g_fmt_vbi_out(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_vbi_format *vbi = &f->fmt.vbi;
+	bool is_60hz = dev->std_out & V4L2_STD_525_60;
+
+	if (!vivid_is_svid_out(dev) || !dev->has_raw_vbi_out)
+		return -EINVAL;
+
+	vbi->sampling_rate = 25000000;
+	vbi->offset = 24;
+	vbi->samples_per_line = 1440;
+	vbi->sample_format = V4L2_PIX_FMT_GREY;
+	vbi->start[0] = is_60hz ? V4L2_VBI_ITU_525_F1_START + 9 : V4L2_VBI_ITU_625_F1_START + 5;
+	vbi->start[1] = is_60hz ? V4L2_VBI_ITU_525_F2_START + 9 : V4L2_VBI_ITU_625_F2_START + 5;
+	vbi->count[0] = vbi->count[1] = is_60hz ? 12 : 18;
+	vbi->flags = dev->vbi_cap_interlaced ? V4L2_VBI_INTERLACED : 0;
+	vbi->reserved[0] = 0;
+	vbi->reserved[1] = 0;
+	return 0;
+}
+
+int vidioc_s_fmt_vbi_out(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	int ret = vidioc_g_fmt_vbi_out(file, priv, f);
+
+	if (ret)
+		return ret;
+	if (vb2_is_busy(&dev->vb_vbi_out_q))
+		return -EBUSY;
+	dev->stream_sliced_vbi_out = false;
+	dev->vbi_out_dev.queue->type = V4L2_BUF_TYPE_VBI_OUTPUT;
+	return 0;
+}
+
+int vidioc_g_fmt_sliced_vbi_out(struct file *file, void *fh, struct v4l2_format *fmt)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_sliced_vbi_format *vbi = &fmt->fmt.sliced;
+
+	if (!vivid_is_svid_out(dev) || !dev->has_sliced_vbi_out)
+		return -EINVAL;
+
+	vivid_fill_service_lines(vbi, dev->service_set_out);
+	return 0;
+}
+
+int vidioc_try_fmt_sliced_vbi_out(struct file *file, void *fh, struct v4l2_format *fmt)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_sliced_vbi_format *vbi = &fmt->fmt.sliced;
+	bool is_60hz = dev->std_out & V4L2_STD_525_60;
+	u32 service_set = vbi->service_set;
+
+	if (!vivid_is_svid_out(dev) || !dev->has_sliced_vbi_out)
+		return -EINVAL;
+
+	service_set &= is_60hz ? V4L2_SLICED_CAPTION_525 :
+				 V4L2_SLICED_WSS_625 | V4L2_SLICED_TELETEXT_B;
+	vivid_fill_service_lines(vbi, service_set);
+	return 0;
+}
+
+int vidioc_s_fmt_sliced_vbi_out(struct file *file, void *fh, struct v4l2_format *fmt)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_sliced_vbi_format *vbi = &fmt->fmt.sliced;
+	int ret = vidioc_try_fmt_sliced_vbi_out(file, fh, fmt);
+
+	if (ret)
+		return ret;
+	if (vb2_is_busy(&dev->vb_vbi_out_q))
+		return -EBUSY;
+	dev->service_set_out = vbi->service_set;
+	dev->stream_sliced_vbi_out = true;
+	dev->vbi_out_dev.queue->type = V4L2_BUF_TYPE_SLICED_VBI_OUTPUT;
+	return 0;
+}
+
+void vivid_sliced_vbi_out_process(struct vivid_dev *dev, struct vivid_buffer *buf)
+{
+	struct v4l2_sliced_vbi_data *vbi = vb2_plane_vaddr(&buf->vb, 0);
+	unsigned elems = vb2_get_plane_payload(&buf->vb, 0) / sizeof(*vbi);
+
+	dev->vbi_out_have_cc[0] = false;
+	dev->vbi_out_have_cc[1] = false;
+	dev->vbi_out_have_wss = false;
+	while (elems--) {
+		switch (vbi->id) {
+		case V4L2_SLICED_CAPTION_525:
+			if ((dev->std_out & V4L2_STD_525_60) && vbi->line == 21) {
+				dev->vbi_out_have_cc[!!vbi->field] = true;
+				dev->vbi_out_cc[!!vbi->field][0] = vbi->data[0];
+				dev->vbi_out_cc[!!vbi->field][1] = vbi->data[1];
+			}
+			break;
+		case V4L2_SLICED_WSS_625:
+			if ((dev->std_out & V4L2_STD_625_50) &&
+			    vbi->field == 0 && vbi->line == 23) {
+				dev->vbi_out_have_wss = true;
+				dev->vbi_out_wss[0] = vbi->data[0];
+				dev->vbi_out_wss[1] = vbi->data[1];
+			}
+			break;
+		}
+		vbi++;
+	}
+}
diff --git a/drivers/media/platform/vivid/vivid-vbi-out.h b/drivers/media/platform/vivid/vivid-vbi-out.h
new file mode 100644
index 000000000000..6555ba9d2860
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vbi-out.h
@@ -0,0 +1,34 @@
+/*
+ * vivid-vbi-out.h - vbi output support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_VBI_OUT_H_
+#define _VIVID_VBI_OUT_H_
+
+void vivid_sliced_vbi_out_process(struct vivid_dev *dev, struct vivid_buffer *buf);
+int vidioc_g_fmt_vbi_out(struct file *file, void *priv,
+					struct v4l2_format *f);
+int vidioc_s_fmt_vbi_out(struct file *file, void *priv,
+					struct v4l2_format *f);
+int vidioc_g_fmt_sliced_vbi_out(struct file *file, void *fh, struct v4l2_format *fmt);
+int vidioc_try_fmt_sliced_vbi_out(struct file *file, void *fh, struct v4l2_format *fmt);
+int vidioc_s_fmt_sliced_vbi_out(struct file *file, void *fh, struct v4l2_format *fmt);
+
+extern const struct vb2_ops vivid_vbi_out_qops;
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-vid-cap.c b/drivers/media/platform/vivid/vivid-vid-cap.c
new file mode 100644
index 000000000000..331c54429b40
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vid-cap.c
@@ -0,0 +1,1730 @@
+/*
+ * vivid-vid-cap.c - video capture support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/vmalloc.h>
+#include <linux/videodev2.h>
+#include <linux/v4l2-dv-timings.h>
+#include <media/v4l2-common.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-dv-timings.h>
+
+#include "vivid-core.h"
+#include "vivid-vid-common.h"
+#include "vivid-kthread-cap.h"
+#include "vivid-vid-cap.h"
+
+/* timeperframe: min/max and default */
+static const struct v4l2_fract
+	tpf_min     = {.numerator = 1,		.denominator = FPS_MAX},
+	tpf_max     = {.numerator = FPS_MAX,	.denominator = 1},
+	tpf_default = {.numerator = 1,		.denominator = 30};
+
+static const struct vivid_fmt formats_ovl[] = {
+	{
+		.name     = "RGB565 (LE)",
+		.fourcc   = V4L2_PIX_FMT_RGB565, /* gggbbbbb rrrrrggg */
+		.depth    = 16,
+		.planes   = 1,
+	},
+	{
+		.name     = "XRGB555 (LE)",
+		.fourcc   = V4L2_PIX_FMT_XRGB555, /* gggbbbbb arrrrrgg */
+		.depth    = 16,
+		.planes   = 1,
+	},
+	{
+		.name     = "ARGB555 (LE)",
+		.fourcc   = V4L2_PIX_FMT_ARGB555, /* gggbbbbb arrrrrgg */
+		.depth    = 16,
+		.planes   = 1,
+	},
+};
+
+/* The number of discrete webcam framesizes */
+#define VIVID_WEBCAM_SIZES 3
+/* The number of discrete webcam frameintervals */
+#define VIVID_WEBCAM_IVALS (VIVID_WEBCAM_SIZES * 2)
+
+/* Sizes must be in increasing order */
+static const struct v4l2_frmsize_discrete webcam_sizes[VIVID_WEBCAM_SIZES] = {
+	{  320, 180 },
+	{  640, 360 },
+	{ 1280, 720 },
+};
+
+/*
+ * Intervals must be in increasing order and there must be twice as many
+ * elements in this array as there are in webcam_sizes.
+ */
+static const struct v4l2_fract webcam_intervals[VIVID_WEBCAM_IVALS] = {
+	{  1, 10 },
+	{  1, 15 },
+	{  1, 25 },
+	{  1, 30 },
+	{  1, 50 },
+	{  1, 60 },
+};
+
+static const struct v4l2_discrete_probe webcam_probe = {
+	webcam_sizes,
+	VIVID_WEBCAM_SIZES
+};
+
+static int vid_cap_queue_setup(struct vb2_queue *vq, const struct v4l2_format *fmt,
+		       unsigned *nbuffers, unsigned *nplanes,
+		       unsigned sizes[], void *alloc_ctxs[])
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	unsigned planes = tpg_g_planes(&dev->tpg);
+	unsigned h = dev->fmt_cap_rect.height;
+	unsigned p;
+
+	if (dev->field_cap == V4L2_FIELD_ALTERNATE) {
+		/*
+		 * You cannot use read() with FIELD_ALTERNATE since the field
+		 * information (TOP/BOTTOM) cannot be passed back to the user.
+		 */
+		if (vb2_fileio_is_active(vq))
+			return -EINVAL;
+	}
+
+	if (dev->queue_setup_error) {
+		/*
+		 * Error injection: test what happens if queue_setup() returns
+		 * an error.
+		 */
+		dev->queue_setup_error = false;
+		return -EINVAL;
+	}
+	if (fmt) {
+		const struct v4l2_pix_format_mplane *mp;
+		struct v4l2_format mp_fmt;
+		const struct vivid_fmt *vfmt;
+
+		if (!V4L2_TYPE_IS_MULTIPLANAR(fmt->type)) {
+			fmt_sp2mp(fmt, &mp_fmt);
+			fmt = &mp_fmt;
+		}
+		mp = &fmt->fmt.pix_mp;
+		/*
+		 * Check if the number of planes in the specified format match
+		 * the number of planes in the current format. You can't mix that.
+		 */
+		if (mp->num_planes != planes)
+			return -EINVAL;
+		vfmt = vivid_get_format(dev, mp->pixelformat);
+		for (p = 0; p < planes; p++) {
+			sizes[p] = mp->plane_fmt[p].sizeimage;
+			if (sizes[0] < tpg_g_bytesperline(&dev->tpg, 0) * h +
+							vfmt->data_offset[p])
+				return -EINVAL;
+		}
+	} else {
+		for (p = 0; p < planes; p++)
+			sizes[p] = tpg_g_bytesperline(&dev->tpg, p) * h +
+					dev->fmt_cap->data_offset[p];
+	}
+
+	if (vq->num_buffers + *nbuffers < 2)
+		*nbuffers = 2 - vq->num_buffers;
+
+	*nplanes = planes;
+
+	/*
+	 * videobuf2-vmalloc allocator is context-less so no need to set
+	 * alloc_ctxs array.
+	 */
+
+	if (planes == 2)
+		dprintk(dev, 1, "%s, count=%d, sizes=%u, %u\n", __func__,
+			*nbuffers, sizes[0], sizes[1]);
+	else
+		dprintk(dev, 1, "%s, count=%d, size=%u\n", __func__,
+			*nbuffers, sizes[0]);
+
+	return 0;
+}
+
+static int vid_cap_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	unsigned long size;
+	unsigned planes = tpg_g_planes(&dev->tpg);
+	unsigned p;
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	if (WARN_ON(NULL == dev->fmt_cap))
+		return -EINVAL;
+
+	if (dev->buf_prepare_error) {
+		/*
+		 * Error injection: test what happens if buf_prepare() returns
+		 * an error.
+		 */
+		dev->buf_prepare_error = false;
+		return -EINVAL;
+	}
+	for (p = 0; p < planes; p++) {
+		size = tpg_g_bytesperline(&dev->tpg, p) * dev->fmt_cap_rect.height +
+			dev->fmt_cap->data_offset[p];
+
+		if (vb2_plane_size(vb, 0) < size) {
+			dprintk(dev, 1, "%s data will not fit into plane %u (%lu < %lu)\n",
+					__func__, p, vb2_plane_size(vb, 0), size);
+			return -EINVAL;
+		}
+
+		vb2_set_plane_payload(vb, p, size);
+		vb->v4l2_planes[p].data_offset = dev->fmt_cap->data_offset[p];
+	}
+
+	return 0;
+}
+
+static void vid_cap_buf_finish(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct v4l2_timecode *tc = &vb->v4l2_buf.timecode;
+	unsigned fps = 25;
+	unsigned seq = vb->v4l2_buf.sequence;
+
+	if (!vivid_is_sdtv_cap(dev))
+		return;
+
+	/*
+	 * Set the timecode. Rarely used, so it is interesting to
+	 * test this.
+	 */
+	vb->v4l2_buf.flags |= V4L2_BUF_FLAG_TIMECODE;
+	if (dev->std_cap & V4L2_STD_525_60)
+		fps = 30;
+	tc->type = (fps == 30) ? V4L2_TC_TYPE_30FPS : V4L2_TC_TYPE_25FPS;
+	tc->flags = 0;
+	tc->frames = seq % fps;
+	tc->seconds = (seq / fps) % 60;
+	tc->minutes = (seq / (60 * fps)) % 60;
+	tc->hours = (seq / (60 * 60 * fps)) % 24;
+}
+
+static void vid_cap_buf_queue(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct vivid_buffer *buf = container_of(vb, struct vivid_buffer, vb);
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	spin_lock(&dev->slock);
+	list_add_tail(&buf->list, &dev->vid_cap_active);
+	spin_unlock(&dev->slock);
+}
+
+static int vid_cap_start_streaming(struct vb2_queue *vq, unsigned count)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	unsigned i;
+	int err;
+
+	if (vb2_is_streaming(&dev->vb_vid_out_q))
+		dev->can_loop_video = vivid_vid_can_loop(dev);
+
+	if (dev->kthread_vid_cap)
+		return 0;
+
+	dev->vid_cap_seq_count = 0;
+	dprintk(dev, 1, "%s\n", __func__);
+	for (i = 0; i < VIDEO_MAX_FRAME; i++)
+		dev->must_blank[i] = tpg_g_perc_fill(&dev->tpg) < 100;
+	if (dev->start_streaming_error) {
+		dev->start_streaming_error = false;
+		err = -EINVAL;
+	} else {
+		err = vivid_start_generating_vid_cap(dev, &dev->vid_cap_streaming);
+	}
+	if (err) {
+		struct vivid_buffer *buf, *tmp;
+
+		list_for_each_entry_safe(buf, tmp, &dev->vid_cap_active, list) {
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
+		}
+	}
+	return err;
+}
+
+/* abort streaming and wait for last buffer */
+static void vid_cap_stop_streaming(struct vb2_queue *vq)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+
+	dprintk(dev, 1, "%s\n", __func__);
+	vivid_stop_generating_vid_cap(dev, &dev->vid_cap_streaming);
+	dev->can_loop_video = false;
+}
+
+const struct vb2_ops vivid_vid_cap_qops = {
+	.queue_setup		= vid_cap_queue_setup,
+	.buf_prepare		= vid_cap_buf_prepare,
+	.buf_finish		= vid_cap_buf_finish,
+	.buf_queue		= vid_cap_buf_queue,
+	.start_streaming	= vid_cap_start_streaming,
+	.stop_streaming		= vid_cap_stop_streaming,
+	.wait_prepare		= vivid_unlock,
+	.wait_finish		= vivid_lock,
+};
+
+/*
+ * Determine the 'picture' quality based on the current TV frequency: either
+ * COLOR for a good 'signal', GRAY (grayscale picture) for a slightly off
+ * signal or NOISE for no signal.
+ */
+void vivid_update_quality(struct vivid_dev *dev)
+{
+	unsigned freq_modulus;
+
+	if (dev->loop_video && (vivid_is_svid_cap(dev) || vivid_is_hdmi_cap(dev))) {
+		/*
+		 * The 'noise' will only be replaced by the actual video
+		 * if the output video matches the input video settings.
+		 */
+		tpg_s_quality(&dev->tpg, TPG_QUAL_NOISE, 0);
+		return;
+	}
+	if (vivid_is_hdmi_cap(dev) && VIVID_INVALID_SIGNAL(dev->dv_timings_signal_mode)) {
+		tpg_s_quality(&dev->tpg, TPG_QUAL_NOISE, 0);
+		return;
+	}
+	if (vivid_is_sdtv_cap(dev) && VIVID_INVALID_SIGNAL(dev->std_signal_mode)) {
+		tpg_s_quality(&dev->tpg, TPG_QUAL_NOISE, 0);
+		return;
+	}
+	if (!vivid_is_tv_cap(dev)) {
+		tpg_s_quality(&dev->tpg, TPG_QUAL_COLOR, 0);
+		return;
+	}
+
+	/*
+	 * There is a fake channel every 6 MHz at 49.25, 55.25, etc.
+	 * From +/- 0.25 MHz around the channel there is color, and from
+	 * +/- 1 MHz there is grayscale (chroma is lost).
+	 * Everywhere else it is just noise.
+	 */
+	freq_modulus = (dev->tv_freq - 676 /* (43.25-1) * 16 */) % (6 * 16);
+	if (freq_modulus > 2 * 16) {
+		tpg_s_quality(&dev->tpg, TPG_QUAL_NOISE,
+			next_pseudo_random32(dev->tv_freq ^ 0x55) & 0x3f);
+		return;
+	}
+	if (freq_modulus < 12 /*0.75 * 16*/ || freq_modulus > 20 /*1.25 * 16*/)
+		tpg_s_quality(&dev->tpg, TPG_QUAL_GRAY, 0);
+	else
+		tpg_s_quality(&dev->tpg, TPG_QUAL_COLOR, 0);
+}
+
+/*
+ * Get the current picture quality and the associated afc value.
+ */
+static enum tpg_quality vivid_get_quality(struct vivid_dev *dev, s32 *afc)
+{
+	unsigned freq_modulus;
+
+	if (afc)
+		*afc = 0;
+	if (tpg_g_quality(&dev->tpg) == TPG_QUAL_COLOR ||
+	    tpg_g_quality(&dev->tpg) == TPG_QUAL_NOISE)
+		return tpg_g_quality(&dev->tpg);
+
+	/*
+	 * There is a fake channel every 6 MHz at 49.25, 55.25, etc.
+	 * From +/- 0.25 MHz around the channel there is color, and from
+	 * +/- 1 MHz there is grayscale (chroma is lost).
+	 * Everywhere else it is just gray.
+	 */
+	freq_modulus = (dev->tv_freq - 676 /* (43.25-1) * 16 */) % (6 * 16);
+	if (afc)
+		*afc = freq_modulus - 1 * 16;
+	return TPG_QUAL_GRAY;
+}
+
+enum tpg_video_aspect vivid_get_video_aspect(const struct vivid_dev *dev)
+{
+	if (vivid_is_sdtv_cap(dev))
+		return dev->std_aspect_ratio;
+
+	if (vivid_is_hdmi_cap(dev))
+		return dev->dv_timings_aspect_ratio;
+
+	return TPG_VIDEO_ASPECT_IMAGE;
+}
+
+static enum tpg_pixel_aspect vivid_get_pixel_aspect(const struct vivid_dev *dev)
+{
+	if (vivid_is_sdtv_cap(dev))
+		return (dev->std_cap & V4L2_STD_525_60) ?
+			TPG_PIXEL_ASPECT_NTSC : TPG_PIXEL_ASPECT_PAL;
+
+	if (vivid_is_hdmi_cap(dev) &&
+	    dev->src_rect.width == 720 && dev->src_rect.height <= 576)
+		return dev->src_rect.height == 480 ?
+			TPG_PIXEL_ASPECT_NTSC : TPG_PIXEL_ASPECT_PAL;
+
+	return TPG_PIXEL_ASPECT_SQUARE;
+}
+
+/*
+ * Called whenever the format has to be reset which can occur when
+ * changing inputs, standard, timings, etc.
+ */
+void vivid_update_format_cap(struct vivid_dev *dev, bool keep_controls)
+{
+	struct v4l2_bt_timings *bt = &dev->dv_timings_cap.bt;
+	unsigned size;
+
+	switch (dev->input_type[dev->input]) {
+	case WEBCAM:
+	default:
+		dev->src_rect.width = webcam_sizes[dev->webcam_size_idx].width;
+		dev->src_rect.height = webcam_sizes[dev->webcam_size_idx].height;
+		dev->timeperframe_vid_cap = webcam_intervals[dev->webcam_ival_idx];
+		dev->field_cap = V4L2_FIELD_NONE;
+		tpg_s_rgb_range(&dev->tpg, V4L2_DV_RGB_RANGE_AUTO);
+		break;
+	case TV:
+	case SVID:
+		dev->field_cap = dev->tv_field_cap;
+		dev->src_rect.width = 720;
+		if (dev->std_cap & V4L2_STD_525_60) {
+			dev->src_rect.height = 480;
+			dev->timeperframe_vid_cap = (struct v4l2_fract) { 1001, 30000 };
+			dev->service_set_cap = V4L2_SLICED_CAPTION_525;
+		} else {
+			dev->src_rect.height = 576;
+			dev->timeperframe_vid_cap = (struct v4l2_fract) { 1000, 25000 };
+			dev->service_set_cap = V4L2_SLICED_WSS_625 | V4L2_SLICED_TELETEXT_B;
+		}
+		tpg_s_rgb_range(&dev->tpg, V4L2_DV_RGB_RANGE_AUTO);
+		break;
+	case HDMI:
+		dev->src_rect.width = bt->width;
+		dev->src_rect.height = bt->height;
+		size = V4L2_DV_BT_FRAME_WIDTH(bt) * V4L2_DV_BT_FRAME_HEIGHT(bt);
+		dev->timeperframe_vid_cap = (struct v4l2_fract) {
+			size / 100, (u32)bt->pixelclock / 100
+		};
+		if (bt->interlaced)
+			dev->field_cap = V4L2_FIELD_ALTERNATE;
+		else
+			dev->field_cap = V4L2_FIELD_NONE;
+
+		/*
+		 * We can be called from within s_ctrl, in that case we can't
+		 * set/get controls. Luckily we don't need to in that case.
+		 */
+		if (keep_controls || !dev->colorspace)
+			break;
+		if (bt->standards & V4L2_DV_BT_STD_CEA861) {
+			if (bt->width == 720 && bt->height <= 576)
+				v4l2_ctrl_s_ctrl(dev->colorspace, V4L2_COLORSPACE_SMPTE170M);
+			else
+				v4l2_ctrl_s_ctrl(dev->colorspace, V4L2_COLORSPACE_REC709);
+			v4l2_ctrl_s_ctrl(dev->real_rgb_range_cap, 1);
+		} else {
+			v4l2_ctrl_s_ctrl(dev->colorspace, V4L2_COLORSPACE_SRGB);
+			v4l2_ctrl_s_ctrl(dev->real_rgb_range_cap, 0);
+		}
+		tpg_s_rgb_range(&dev->tpg, v4l2_ctrl_g_ctrl(dev->rgb_range_cap));
+		break;
+	}
+	vivid_update_quality(dev);
+	tpg_reset_source(&dev->tpg, dev->src_rect.width, dev->src_rect.height, dev->field_cap);
+	dev->crop_cap = dev->src_rect;
+	dev->crop_bounds_cap = dev->src_rect;
+	dev->compose_cap = dev->crop_cap;
+	if (V4L2_FIELD_HAS_T_OR_B(dev->field_cap))
+		dev->compose_cap.height /= 2;
+	dev->fmt_cap_rect = dev->compose_cap;
+	tpg_s_video_aspect(&dev->tpg, vivid_get_video_aspect(dev));
+	tpg_s_pixel_aspect(&dev->tpg, vivid_get_pixel_aspect(dev));
+	tpg_update_mv_step(&dev->tpg);
+}
+
+/* Map the field to something that is valid for the current input */
+static enum v4l2_field vivid_field_cap(struct vivid_dev *dev, enum v4l2_field field)
+{
+	if (vivid_is_sdtv_cap(dev)) {
+		switch (field) {
+		case V4L2_FIELD_INTERLACED_TB:
+		case V4L2_FIELD_INTERLACED_BT:
+		case V4L2_FIELD_SEQ_TB:
+		case V4L2_FIELD_SEQ_BT:
+		case V4L2_FIELD_TOP:
+		case V4L2_FIELD_BOTTOM:
+		case V4L2_FIELD_ALTERNATE:
+			return field;
+		case V4L2_FIELD_INTERLACED:
+		default:
+			return V4L2_FIELD_INTERLACED;
+		}
+	}
+	if (vivid_is_hdmi_cap(dev))
+		return dev->dv_timings_cap.bt.interlaced ? V4L2_FIELD_ALTERNATE :
+						       V4L2_FIELD_NONE;
+	return V4L2_FIELD_NONE;
+}
+
+static unsigned vivid_colorspace_cap(struct vivid_dev *dev)
+{
+	if (!dev->loop_video || vivid_is_webcam(dev) || vivid_is_tv_cap(dev))
+		return tpg_g_colorspace(&dev->tpg);
+	return dev->colorspace_out;
+}
+
+int vivid_g_fmt_vid_cap(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_pix_format_mplane *mp = &f->fmt.pix_mp;
+	unsigned p;
+
+	mp->width        = dev->fmt_cap_rect.width;
+	mp->height       = dev->fmt_cap_rect.height;
+	mp->field        = dev->field_cap;
+	mp->pixelformat  = dev->fmt_cap->fourcc;
+	mp->colorspace   = vivid_colorspace_cap(dev);
+	mp->num_planes = dev->fmt_cap->planes;
+	for (p = 0; p < mp->num_planes; p++) {
+		mp->plane_fmt[p].bytesperline = tpg_g_bytesperline(&dev->tpg, p);
+		mp->plane_fmt[p].sizeimage =
+			mp->plane_fmt[p].bytesperline * mp->height +
+			dev->fmt_cap->data_offset[p];
+	}
+	return 0;
+}
+
+int vivid_try_fmt_vid_cap(struct file *file, void *priv,
+			struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *mp = &f->fmt.pix_mp;
+	struct v4l2_plane_pix_format *pfmt = mp->plane_fmt;
+	struct vivid_dev *dev = video_drvdata(file);
+	const struct vivid_fmt *fmt;
+	unsigned bytesperline, max_bpl;
+	unsigned factor = 1;
+	unsigned w, h;
+	unsigned p;
+
+	fmt = vivid_get_format(dev, mp->pixelformat);
+	if (!fmt) {
+		dprintk(dev, 1, "Fourcc format (0x%08x) unknown.\n",
+			mp->pixelformat);
+		mp->pixelformat = V4L2_PIX_FMT_YUYV;
+		fmt = vivid_get_format(dev, mp->pixelformat);
+	}
+
+	mp->field = vivid_field_cap(dev, mp->field);
+	if (vivid_is_webcam(dev)) {
+		const struct v4l2_frmsize_discrete *sz =
+			v4l2_find_nearest_format(&webcam_probe, mp->width, mp->height);
+
+		w = sz->width;
+		h = sz->height;
+	} else if (vivid_is_sdtv_cap(dev)) {
+		w = 720;
+		h = (dev->std_cap & V4L2_STD_525_60) ? 480 : 576;
+	} else {
+		w = dev->src_rect.width;
+		h = dev->src_rect.height;
+	}
+	if (V4L2_FIELD_HAS_T_OR_B(mp->field))
+		factor = 2;
+	if (vivid_is_webcam(dev) ||
+	    (!dev->has_scaler_cap && !dev->has_crop_cap && !dev->has_compose_cap)) {
+		mp->width = w;
+		mp->height = h / factor;
+	} else {
+		struct v4l2_rect r = { 0, 0, mp->width, mp->height * factor };
+
+		rect_set_min_size(&r, &vivid_min_rect);
+		rect_set_max_size(&r, &vivid_max_rect);
+		if (dev->has_scaler_cap && !dev->has_compose_cap) {
+			struct v4l2_rect max_r = { 0, 0, MAX_ZOOM * w, MAX_ZOOM * h };
+
+			rect_set_max_size(&r, &max_r);
+		} else if (!dev->has_scaler_cap && dev->has_crop_cap && !dev->has_compose_cap) {
+			rect_set_max_size(&r, &dev->src_rect);
+		} else if (!dev->has_scaler_cap && !dev->has_crop_cap) {
+			rect_set_min_size(&r, &dev->src_rect);
+		}
+		mp->width = r.width;
+		mp->height = r.height / factor;
+	}
+
+	/* This driver supports custom bytesperline values */
+
+	/* Calculate the minimum supported bytesperline value */
+	bytesperline = (mp->width * fmt->depth) >> 3;
+	/* Calculate the maximum supported bytesperline value */
+	max_bpl = (MAX_ZOOM * MAX_WIDTH * fmt->depth) >> 3;
+	mp->num_planes = fmt->planes;
+	for (p = 0; p < mp->num_planes; p++) {
+		if (pfmt[p].bytesperline > max_bpl)
+			pfmt[p].bytesperline = max_bpl;
+		if (pfmt[p].bytesperline < bytesperline)
+			pfmt[p].bytesperline = bytesperline;
+		pfmt[p].sizeimage = pfmt[p].bytesperline * mp->height +
+			fmt->data_offset[p];
+		memset(pfmt[p].reserved, 0, sizeof(pfmt[p].reserved));
+	}
+	mp->colorspace = vivid_colorspace_cap(dev);
+	memset(mp->reserved, 0, sizeof(mp->reserved));
+	return 0;
+}
+
+int vivid_s_fmt_vid_cap(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *mp = &f->fmt.pix_mp;
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_rect *crop = &dev->crop_cap;
+	struct v4l2_rect *compose = &dev->compose_cap;
+	struct vb2_queue *q = &dev->vb_vid_cap_q;
+	int ret = vivid_try_fmt_vid_cap(file, priv, f);
+	unsigned factor = 1;
+	unsigned i;
+
+	if (ret < 0)
+		return ret;
+
+	if (vb2_is_busy(q)) {
+		dprintk(dev, 1, "%s device busy\n", __func__);
+		return -EBUSY;
+	}
+
+	if (dev->overlay_cap_owner && dev->fb_cap.fmt.pixelformat != mp->pixelformat) {
+		dprintk(dev, 1, "overlay is active, can't change pixelformat\n");
+		return -EBUSY;
+	}
+
+	dev->fmt_cap = vivid_get_format(dev, mp->pixelformat);
+	if (V4L2_FIELD_HAS_T_OR_B(mp->field))
+		factor = 2;
+
+	/* Note: the webcam input doesn't support scaling, cropping or composing */
+
+	if (!vivid_is_webcam(dev) &&
+	    (dev->has_scaler_cap || dev->has_crop_cap || dev->has_compose_cap)) {
+		struct v4l2_rect r = { 0, 0, mp->width, mp->height };
+
+		if (dev->has_scaler_cap) {
+			if (dev->has_compose_cap)
+				rect_map_inside(compose, &r);
+			else
+				*compose = r;
+			if (dev->has_crop_cap && !dev->has_compose_cap) {
+				struct v4l2_rect min_r = {
+					0, 0,
+					r.width / MAX_ZOOM,
+					factor * r.height / MAX_ZOOM
+				};
+				struct v4l2_rect max_r = {
+					0, 0,
+					r.width * MAX_ZOOM,
+					factor * r.height * MAX_ZOOM
+				};
+
+				rect_set_min_size(crop, &min_r);
+				rect_set_max_size(crop, &max_r);
+				rect_map_inside(crop, &dev->crop_bounds_cap);
+			} else if (dev->has_crop_cap) {
+				struct v4l2_rect min_r = {
+					0, 0,
+					compose->width / MAX_ZOOM,
+					factor * compose->height / MAX_ZOOM
+				};
+				struct v4l2_rect max_r = {
+					0, 0,
+					compose->width * MAX_ZOOM,
+					factor * compose->height * MAX_ZOOM
+				};
+
+				rect_set_min_size(crop, &min_r);
+				rect_set_max_size(crop, &max_r);
+				rect_map_inside(crop, &dev->crop_bounds_cap);
+			}
+		} else if (dev->has_crop_cap && !dev->has_compose_cap) {
+			r.height *= factor;
+			rect_set_size_to(crop, &r);
+			rect_map_inside(crop, &dev->crop_bounds_cap);
+			r = *crop;
+			r.height /= factor;
+			rect_set_size_to(compose, &r);
+		} else if (!dev->has_crop_cap) {
+			rect_map_inside(compose, &r);
+		} else {
+			r.height *= factor;
+			rect_set_max_size(crop, &r);
+			rect_map_inside(crop, &dev->crop_bounds_cap);
+			compose->top *= factor;
+			compose->height *= factor;
+			rect_set_size_to(compose, crop);
+			rect_map_inside(compose, &r);
+			compose->top /= factor;
+			compose->height /= factor;
+		}
+	} else if (vivid_is_webcam(dev)) {
+		/* Guaranteed to be a match */
+		for (i = 0; i < ARRAY_SIZE(webcam_sizes); i++)
+			if (webcam_sizes[i].width == mp->width &&
+					webcam_sizes[i].height == mp->height)
+				break;
+		dev->webcam_size_idx = i;
+		if (dev->webcam_ival_idx >= 2 * (3 - i))
+			dev->webcam_ival_idx = 2 * (3 - i) - 1;
+		vivid_update_format_cap(dev, false);
+	} else {
+		struct v4l2_rect r = { 0, 0, mp->width, mp->height };
+
+		rect_set_size_to(compose, &r);
+		r.height *= factor;
+		rect_set_size_to(crop, &r);
+	}
+
+	dev->fmt_cap_rect.width = mp->width;
+	dev->fmt_cap_rect.height = mp->height;
+	tpg_s_buf_height(&dev->tpg, mp->height);
+	tpg_s_bytesperline(&dev->tpg, 0, mp->plane_fmt[0].bytesperline);
+	if (tpg_g_planes(&dev->tpg) > 1)
+		tpg_s_bytesperline(&dev->tpg, 1, mp->plane_fmt[1].bytesperline);
+	dev->field_cap = mp->field;
+	tpg_s_field(&dev->tpg, dev->field_cap);
+	tpg_s_crop_compose(&dev->tpg, &dev->crop_cap, &dev->compose_cap);
+	tpg_s_fourcc(&dev->tpg, dev->fmt_cap->fourcc);
+	if (vivid_is_sdtv_cap(dev))
+		dev->tv_field_cap = mp->field;
+	tpg_update_mv_step(&dev->tpg);
+	return 0;
+}
+
+int vidioc_g_fmt_vid_cap_mplane(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!dev->multiplanar)
+		return -ENOTTY;
+	return vivid_g_fmt_vid_cap(file, priv, f);
+}
+
+int vidioc_try_fmt_vid_cap_mplane(struct file *file, void *priv,
+			struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!dev->multiplanar)
+		return -ENOTTY;
+	return vivid_try_fmt_vid_cap(file, priv, f);
+}
+
+int vidioc_s_fmt_vid_cap_mplane(struct file *file, void *priv,
+			struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!dev->multiplanar)
+		return -ENOTTY;
+	return vivid_s_fmt_vid_cap(file, priv, f);
+}
+
+int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (dev->multiplanar)
+		return -ENOTTY;
+	return fmt_sp2mp_func(file, priv, f, vivid_g_fmt_vid_cap);
+}
+
+int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
+			struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (dev->multiplanar)
+		return -ENOTTY;
+	return fmt_sp2mp_func(file, priv, f, vivid_try_fmt_vid_cap);
+}
+
+int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
+			struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (dev->multiplanar)
+		return -ENOTTY;
+	return fmt_sp2mp_func(file, priv, f, vivid_s_fmt_vid_cap);
+}
+
+int vivid_vid_cap_g_selection(struct file *file, void *priv,
+			      struct v4l2_selection *sel)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!dev->has_crop_cap && !dev->has_compose_cap)
+		return -ENOTTY;
+	if (sel->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+	if (vivid_is_webcam(dev))
+		return -EINVAL;
+
+	sel->r.left = sel->r.top = 0;
+	switch (sel->target) {
+	case V4L2_SEL_TGT_CROP:
+		if (!dev->has_crop_cap)
+			return -EINVAL;
+		sel->r = dev->crop_cap;
+		break;
+	case V4L2_SEL_TGT_CROP_DEFAULT:
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+		if (!dev->has_crop_cap)
+			return -EINVAL;
+		sel->r = dev->src_rect;
+		break;
+	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
+		if (!dev->has_compose_cap)
+			return -EINVAL;
+		sel->r = vivid_max_rect;
+		break;
+	case V4L2_SEL_TGT_COMPOSE:
+		if (!dev->has_compose_cap)
+			return -EINVAL;
+		sel->r = dev->compose_cap;
+		break;
+	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
+		if (!dev->has_compose_cap)
+			return -EINVAL;
+		sel->r = dev->fmt_cap_rect;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection *s)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_rect *crop = &dev->crop_cap;
+	struct v4l2_rect *compose = &dev->compose_cap;
+	unsigned factor = V4L2_FIELD_HAS_T_OR_B(dev->field_cap) ? 2 : 1;
+	int ret;
+
+	if (!dev->has_crop_cap && !dev->has_compose_cap)
+		return -ENOTTY;
+	if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+	if (vivid_is_webcam(dev))
+		return -EINVAL;
+
+	switch (s->target) {
+	case V4L2_SEL_TGT_CROP:
+		if (!dev->has_crop_cap)
+			return -EINVAL;
+		ret = vivid_vid_adjust_sel(s->flags, &s->r);
+		if (ret)
+			return ret;
+		rect_set_min_size(&s->r, &vivid_min_rect);
+		rect_set_max_size(&s->r, &dev->src_rect);
+		rect_map_inside(&s->r, &dev->crop_bounds_cap);
+		s->r.top /= factor;
+		s->r.height /= factor;
+		if (dev->has_scaler_cap) {
+			struct v4l2_rect fmt = dev->fmt_cap_rect;
+			struct v4l2_rect max_rect = {
+				0, 0,
+				s->r.width * MAX_ZOOM,
+				s->r.height * MAX_ZOOM
+			};
+			struct v4l2_rect min_rect = {
+				0, 0,
+				s->r.width / MAX_ZOOM,
+				s->r.height / MAX_ZOOM
+			};
+
+			rect_set_min_size(&fmt, &min_rect);
+			if (!dev->has_compose_cap)
+				rect_set_max_size(&fmt, &max_rect);
+			if (!rect_same_size(&dev->fmt_cap_rect, &fmt) &&
+			    vb2_is_busy(&dev->vb_vid_cap_q))
+				return -EBUSY;
+			if (dev->has_compose_cap) {
+				rect_set_min_size(compose, &min_rect);
+				rect_set_max_size(compose, &max_rect);
+			}
+			dev->fmt_cap_rect = fmt;
+			tpg_s_buf_height(&dev->tpg, fmt.height);
+		} else if (dev->has_compose_cap) {
+			struct v4l2_rect fmt = dev->fmt_cap_rect;
+
+			rect_set_min_size(&fmt, &s->r);
+			if (!rect_same_size(&dev->fmt_cap_rect, &fmt) &&
+			    vb2_is_busy(&dev->vb_vid_cap_q))
+				return -EBUSY;
+			dev->fmt_cap_rect = fmt;
+			tpg_s_buf_height(&dev->tpg, fmt.height);
+			rect_set_size_to(compose, &s->r);
+			rect_map_inside(compose, &dev->fmt_cap_rect);
+		} else {
+			if (!rect_same_size(&s->r, &dev->fmt_cap_rect) &&
+			    vb2_is_busy(&dev->vb_vid_cap_q))
+				return -EBUSY;
+			rect_set_size_to(&dev->fmt_cap_rect, &s->r);
+			rect_set_size_to(compose, &s->r);
+			rect_map_inside(compose, &dev->fmt_cap_rect);
+			tpg_s_buf_height(&dev->tpg, dev->fmt_cap_rect.height);
+		}
+		s->r.top *= factor;
+		s->r.height *= factor;
+		*crop = s->r;
+		break;
+	case V4L2_SEL_TGT_COMPOSE:
+		if (!dev->has_compose_cap)
+			return -EINVAL;
+		ret = vivid_vid_adjust_sel(s->flags, &s->r);
+		if (ret)
+			return ret;
+		rect_set_min_size(&s->r, &vivid_min_rect);
+		rect_set_max_size(&s->r, &dev->fmt_cap_rect);
+		if (dev->has_scaler_cap) {
+			struct v4l2_rect max_rect = {
+				0, 0,
+				dev->src_rect.width * MAX_ZOOM,
+				(dev->src_rect.height / factor) * MAX_ZOOM
+			};
+
+			rect_set_max_size(&s->r, &max_rect);
+			if (dev->has_crop_cap) {
+				struct v4l2_rect min_rect = {
+					0, 0,
+					s->r.width / MAX_ZOOM,
+					(s->r.height * factor) / MAX_ZOOM
+				};
+				struct v4l2_rect max_rect = {
+					0, 0,
+					s->r.width * MAX_ZOOM,
+					(s->r.height * factor) * MAX_ZOOM
+				};
+
+				rect_set_min_size(crop, &min_rect);
+				rect_set_max_size(crop, &max_rect);
+				rect_map_inside(crop, &dev->crop_bounds_cap);
+			}
+		} else if (dev->has_crop_cap) {
+			s->r.top *= factor;
+			s->r.height *= factor;
+			rect_set_max_size(&s->r, &dev->src_rect);
+			rect_set_size_to(crop, &s->r);
+			rect_map_inside(crop, &dev->crop_bounds_cap);
+			s->r.top /= factor;
+			s->r.height /= factor;
+		} else {
+			rect_set_size_to(&s->r, &dev->src_rect);
+			s->r.height /= factor;
+		}
+		rect_map_inside(&s->r, &dev->fmt_cap_rect);
+		if (dev->bitmap_cap && (compose->width != s->r.width ||
+					compose->height != s->r.height)) {
+			kfree(dev->bitmap_cap);
+			dev->bitmap_cap = NULL;
+		}
+		*compose = s->r;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	tpg_s_crop_compose(&dev->tpg, crop, compose);
+	return 0;
+}
+
+int vivid_vid_cap_cropcap(struct file *file, void *priv,
+			      struct v4l2_cropcap *cap)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (cap->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return -EINVAL;
+
+	switch (vivid_get_pixel_aspect(dev)) {
+	case TPG_PIXEL_ASPECT_NTSC:
+		cap->pixelaspect.numerator = 11;
+		cap->pixelaspect.denominator = 10;
+		break;
+	case TPG_PIXEL_ASPECT_PAL:
+		cap->pixelaspect.numerator = 54;
+		cap->pixelaspect.denominator = 59;
+		break;
+	case TPG_PIXEL_ASPECT_SQUARE:
+		cap->pixelaspect.numerator = 1;
+		cap->pixelaspect.denominator = 1;
+		break;
+	}
+	return 0;
+}
+
+int vidioc_enum_fmt_vid_overlay(struct file *file, void  *priv,
+					struct v4l2_fmtdesc *f)
+{
+	const struct vivid_fmt *fmt;
+
+	if (f->index >= ARRAY_SIZE(formats_ovl))
+		return -EINVAL;
+
+	fmt = &formats_ovl[f->index];
+
+	strlcpy(f->description, fmt->name, sizeof(f->description));
+	f->pixelformat = fmt->fourcc;
+	return 0;
+}
+
+int vidioc_g_fmt_vid_overlay(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	const struct v4l2_rect *compose = &dev->compose_cap;
+	struct v4l2_window *win = &f->fmt.win;
+	unsigned clipcount = win->clipcount;
+
+	win->w.top = dev->overlay_cap_top;
+	win->w.left = dev->overlay_cap_left;
+	win->w.width = compose->width;
+	win->w.height = compose->height;
+	win->field = dev->overlay_cap_field;
+	win->clipcount = dev->clipcount_cap;
+	if (clipcount > dev->clipcount_cap)
+		clipcount = dev->clipcount_cap;
+	if (dev->bitmap_cap == NULL)
+		win->bitmap = NULL;
+	else if (win->bitmap) {
+		if (copy_to_user(win->bitmap, dev->bitmap_cap,
+		    ((compose->width + 7) / 8) * compose->height))
+			return -EFAULT;
+	}
+	if (clipcount && win->clips) {
+		if (copy_to_user(win->clips, dev->clips_cap,
+				 clipcount * sizeof(dev->clips_cap[0])))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+int vidioc_try_fmt_vid_overlay(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	const struct v4l2_rect *compose = &dev->compose_cap;
+	struct v4l2_window *win = &f->fmt.win;
+	int i, j;
+
+	win->w.left = clamp_t(int, win->w.left,
+			      -dev->fb_cap.fmt.width, dev->fb_cap.fmt.width);
+	win->w.top = clamp_t(int, win->w.top,
+			     -dev->fb_cap.fmt.height, dev->fb_cap.fmt.height);
+	win->w.width = compose->width;
+	win->w.height = compose->height;
+	if (win->field != V4L2_FIELD_BOTTOM && win->field != V4L2_FIELD_TOP)
+		win->field = V4L2_FIELD_ANY;
+	win->chromakey = 0;
+	win->global_alpha = 0;
+	if (win->clipcount && !win->clips)
+		win->clipcount = 0;
+	if (win->clipcount > MAX_CLIPS)
+		win->clipcount = MAX_CLIPS;
+	if (win->clipcount) {
+		if (copy_from_user(dev->try_clips_cap, win->clips,
+				   win->clipcount * sizeof(dev->clips_cap[0])))
+			return -EFAULT;
+		for (i = 0; i < win->clipcount; i++) {
+			struct v4l2_rect *r = &dev->try_clips_cap[i].c;
+
+			r->top = clamp_t(s32, r->top, 0, dev->fb_cap.fmt.height - 1);
+			r->height = clamp_t(s32, r->height, 1, dev->fb_cap.fmt.height - r->top);
+			r->left = clamp_t(u32, r->left, 0, dev->fb_cap.fmt.width - 1);
+			r->width = clamp_t(u32, r->width, 1, dev->fb_cap.fmt.width - r->left);
+		}
+		/*
+		 * Yeah, so sue me, it's an O(n^2) algorithm. But n is a small
+		 * number and it's typically a one-time deal.
+		 */
+		for (i = 0; i < win->clipcount - 1; i++) {
+			struct v4l2_rect *r1 = &dev->try_clips_cap[i].c;
+
+			for (j = i + 1; j < win->clipcount; j++) {
+				struct v4l2_rect *r2 = &dev->try_clips_cap[j].c;
+
+				if (rect_overlap(r1, r2))
+					return -EINVAL;
+			}
+		}
+		if (copy_to_user(win->clips, dev->try_clips_cap,
+				 win->clipcount * sizeof(dev->clips_cap[0])))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+int vidioc_s_fmt_vid_overlay(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	const struct v4l2_rect *compose = &dev->compose_cap;
+	struct v4l2_window *win = &f->fmt.win;
+	int ret = vidioc_try_fmt_vid_overlay(file, priv, f);
+	unsigned bitmap_size = ((compose->width + 7) / 8) * compose->height;
+	unsigned clips_size = win->clipcount * sizeof(dev->clips_cap[0]);
+	void *new_bitmap = NULL;
+
+	if (ret)
+		return ret;
+
+	if (win->bitmap) {
+		new_bitmap = vzalloc(bitmap_size);
+
+		if (new_bitmap == NULL)
+			return -ENOMEM;
+		if (copy_from_user(new_bitmap, win->bitmap, bitmap_size)) {
+			vfree(new_bitmap);
+			return -EFAULT;
+		}
+	}
+
+	dev->overlay_cap_top = win->w.top;
+	dev->overlay_cap_left = win->w.left;
+	dev->overlay_cap_field = win->field;
+	vfree(dev->bitmap_cap);
+	dev->bitmap_cap = new_bitmap;
+	dev->clipcount_cap = win->clipcount;
+	if (dev->clipcount_cap)
+		memcpy(dev->clips_cap, dev->try_clips_cap, clips_size);
+	return 0;
+}
+
+int vivid_vid_cap_overlay(struct file *file, void *fh, unsigned i)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (i && dev->fb_vbase_cap == NULL)
+		return -EINVAL;
+
+	if (i && dev->fb_cap.fmt.pixelformat != dev->fmt_cap->fourcc) {
+		dprintk(dev, 1, "mismatch between overlay and video capture pixelformats\n");
+		return -EINVAL;
+	}
+
+	if (dev->overlay_cap_owner && dev->overlay_cap_owner != fh)
+		return -EBUSY;
+	dev->overlay_cap_owner = i ? fh : NULL;
+	return 0;
+}
+
+int vivid_vid_cap_g_fbuf(struct file *file, void *fh,
+				struct v4l2_framebuffer *a)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	*a = dev->fb_cap;
+	a->capability = V4L2_FBUF_CAP_BITMAP_CLIPPING |
+			V4L2_FBUF_CAP_LIST_CLIPPING;
+	a->flags = V4L2_FBUF_FLAG_PRIMARY;
+	a->fmt.field = V4L2_FIELD_NONE;
+	a->fmt.colorspace = V4L2_COLORSPACE_SRGB;
+	a->fmt.priv = 0;
+	return 0;
+}
+
+int vivid_vid_cap_s_fbuf(struct file *file, void *fh,
+				const struct v4l2_framebuffer *a)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	const struct vivid_fmt *fmt;
+
+	if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	if (dev->overlay_cap_owner)
+		return -EBUSY;
+
+	if (a->base == NULL) {
+		dev->fb_cap.base = NULL;
+		dev->fb_vbase_cap = NULL;
+		return 0;
+	}
+
+	if (a->fmt.width < 48 || a->fmt.height < 32)
+		return -EINVAL;
+	fmt = vivid_get_format(dev, a->fmt.pixelformat);
+	if (!fmt || !fmt->can_do_overlay)
+		return -EINVAL;
+	if (a->fmt.bytesperline < (a->fmt.width * fmt->depth) / 8)
+		return -EINVAL;
+	if (a->fmt.height * a->fmt.bytesperline < a->fmt.sizeimage)
+		return -EINVAL;
+
+	dev->fb_vbase_cap = phys_to_virt((unsigned long)a->base);
+	dev->fb_cap = *a;
+	dev->overlay_cap_left = clamp_t(int, dev->overlay_cap_left,
+				    -dev->fb_cap.fmt.width, dev->fb_cap.fmt.width);
+	dev->overlay_cap_top = clamp_t(int, dev->overlay_cap_top,
+				   -dev->fb_cap.fmt.height, dev->fb_cap.fmt.height);
+	return 0;
+}
+
+static const struct v4l2_audio vivid_audio_inputs[] = {
+	{ 0, "TV", V4L2_AUDCAP_STEREO },
+	{ 1, "Line-In", V4L2_AUDCAP_STEREO },
+};
+
+int vidioc_enum_input(struct file *file, void *priv,
+				struct v4l2_input *inp)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (inp->index >= dev->num_inputs)
+		return -EINVAL;
+
+	inp->type = V4L2_INPUT_TYPE_CAMERA;
+	switch (dev->input_type[inp->index]) {
+	case WEBCAM:
+		snprintf(inp->name, sizeof(inp->name), "Webcam %u",
+				dev->input_name_counter[inp->index]);
+		inp->capabilities = 0;
+		break;
+	case TV:
+		snprintf(inp->name, sizeof(inp->name), "TV %u",
+				dev->input_name_counter[inp->index]);
+		inp->type = V4L2_INPUT_TYPE_TUNER;
+		inp->std = V4L2_STD_ALL;
+		if (dev->has_audio_inputs)
+			inp->audioset = (1 << ARRAY_SIZE(vivid_audio_inputs)) - 1;
+		inp->capabilities = V4L2_IN_CAP_STD;
+		break;
+	case SVID:
+		snprintf(inp->name, sizeof(inp->name), "S-Video %u",
+				dev->input_name_counter[inp->index]);
+		inp->std = V4L2_STD_ALL;
+		if (dev->has_audio_inputs)
+			inp->audioset = (1 << ARRAY_SIZE(vivid_audio_inputs)) - 1;
+		inp->capabilities = V4L2_IN_CAP_STD;
+		break;
+	case HDMI:
+		snprintf(inp->name, sizeof(inp->name), "HDMI %u",
+				dev->input_name_counter[inp->index]);
+		inp->capabilities = V4L2_IN_CAP_DV_TIMINGS;
+		if (dev->edid_blocks == 0 ||
+		    dev->dv_timings_signal_mode == NO_SIGNAL)
+			inp->status |= V4L2_IN_ST_NO_SIGNAL;
+		else if (dev->dv_timings_signal_mode == NO_LOCK ||
+			 dev->dv_timings_signal_mode == OUT_OF_RANGE)
+			inp->status |= V4L2_IN_ST_NO_H_LOCK;
+		break;
+	}
+	if (dev->sensor_hflip)
+		inp->status |= V4L2_IN_ST_HFLIP;
+	if (dev->sensor_vflip)
+		inp->status |= V4L2_IN_ST_VFLIP;
+	if (dev->input == inp->index && vivid_is_sdtv_cap(dev)) {
+		if (dev->std_signal_mode == NO_SIGNAL) {
+			inp->status |= V4L2_IN_ST_NO_SIGNAL;
+		} else if (dev->std_signal_mode == NO_LOCK) {
+			inp->status |= V4L2_IN_ST_NO_H_LOCK;
+		} else if (vivid_is_tv_cap(dev)) {
+			switch (tpg_g_quality(&dev->tpg)) {
+			case TPG_QUAL_GRAY:
+				inp->status |= V4L2_IN_ST_COLOR_KILL;
+				break;
+			case TPG_QUAL_NOISE:
+				inp->status |= V4L2_IN_ST_NO_H_LOCK;
+				break;
+			default:
+				break;
+			}
+		}
+	}
+	return 0;
+}
+
+int vidioc_g_input(struct file *file, void *priv, unsigned *i)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	*i = dev->input;
+	return 0;
+}
+
+int vidioc_s_input(struct file *file, void *priv, unsigned i)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_bt_timings *bt = &dev->dv_timings_cap.bt;
+	unsigned brightness;
+
+	if (i >= dev->num_inputs)
+		return -EINVAL;
+
+	if (i == dev->input)
+		return 0;
+
+	if (vb2_is_busy(&dev->vb_vid_cap_q) || vb2_is_busy(&dev->vb_vbi_cap_q))
+		return -EBUSY;
+
+	dev->input = i;
+	dev->vid_cap_dev.tvnorms = 0;
+	if (dev->input_type[i] == TV || dev->input_type[i] == SVID) {
+		dev->tv_audio_input = (dev->input_type[i] == TV) ? 0 : 1;
+		dev->vid_cap_dev.tvnorms = V4L2_STD_ALL;
+	}
+	dev->vbi_cap_dev.tvnorms = dev->vid_cap_dev.tvnorms;
+	vivid_update_format_cap(dev, false);
+
+	if (dev->colorspace) {
+		switch (dev->input_type[i]) {
+		case WEBCAM:
+			v4l2_ctrl_s_ctrl(dev->colorspace, V4L2_COLORSPACE_SRGB);
+			break;
+		case TV:
+		case SVID:
+			v4l2_ctrl_s_ctrl(dev->colorspace, V4L2_COLORSPACE_SMPTE170M);
+			break;
+		case HDMI:
+			if (bt->standards & V4L2_DV_BT_STD_CEA861) {
+				if (dev->src_rect.width == 720 && dev->src_rect.height <= 576)
+					v4l2_ctrl_s_ctrl(dev->colorspace, V4L2_COLORSPACE_SMPTE170M);
+				else
+					v4l2_ctrl_s_ctrl(dev->colorspace, V4L2_COLORSPACE_REC709);
+			} else {
+				v4l2_ctrl_s_ctrl(dev->colorspace, V4L2_COLORSPACE_SRGB);
+			}
+			break;
+		}
+	}
+
+	/*
+	 * Modify the brightness range depending on the input.
+	 * This makes it easy to use vivid to test if applications can
+	 * handle control range modifications and is also how this is
+	 * typically used in practice as different inputs may be hooked
+	 * up to different receivers with different control ranges.
+	 */
+	brightness = 128 * i + dev->input_brightness[i];
+	v4l2_ctrl_modify_range(dev->brightness,
+			128 * i, 255 + 128 * i, 1, 128 + 128 * i);
+	v4l2_ctrl_s_ctrl(dev->brightness, brightness);
+	return 0;
+}
+
+int vidioc_enumaudio(struct file *file, void *fh, struct v4l2_audio *vin)
+{
+	if (vin->index >= ARRAY_SIZE(vivid_audio_inputs))
+		return -EINVAL;
+	*vin = vivid_audio_inputs[vin->index];
+	return 0;
+}
+
+int vidioc_g_audio(struct file *file, void *fh, struct v4l2_audio *vin)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_sdtv_cap(dev))
+		return -EINVAL;
+	*vin = vivid_audio_inputs[dev->tv_audio_input];
+	return 0;
+}
+
+int vidioc_s_audio(struct file *file, void *fh, const struct v4l2_audio *vin)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_sdtv_cap(dev))
+		return -EINVAL;
+	if (vin->index >= ARRAY_SIZE(vivid_audio_inputs))
+		return -EINVAL;
+	dev->tv_audio_input = vin->index;
+	return 0;
+}
+
+int vivid_video_g_frequency(struct file *file, void *fh, struct v4l2_frequency *vf)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (vf->tuner != 0)
+		return -EINVAL;
+	vf->frequency = dev->tv_freq;
+	return 0;
+}
+
+int vivid_video_s_frequency(struct file *file, void *fh, const struct v4l2_frequency *vf)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (vf->tuner != 0)
+		return -EINVAL;
+	dev->tv_freq = clamp_t(unsigned, vf->frequency, MIN_TV_FREQ, MAX_TV_FREQ);
+	if (vivid_is_tv_cap(dev))
+		vivid_update_quality(dev);
+	return 0;
+}
+
+int vivid_video_s_tuner(struct file *file, void *fh, const struct v4l2_tuner *vt)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (vt->index != 0)
+		return -EINVAL;
+	if (vt->audmode > V4L2_TUNER_MODE_LANG1_LANG2)
+		return -EINVAL;
+	dev->tv_audmode = vt->audmode;
+	return 0;
+}
+
+int vivid_video_g_tuner(struct file *file, void *fh, struct v4l2_tuner *vt)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	enum tpg_quality qual;
+
+	if (vt->index != 0)
+		return -EINVAL;
+
+	vt->capability = V4L2_TUNER_CAP_NORM | V4L2_TUNER_CAP_STEREO |
+			 V4L2_TUNER_CAP_LANG1 | V4L2_TUNER_CAP_LANG2;
+	vt->audmode = dev->tv_audmode;
+	vt->rangelow = MIN_TV_FREQ;
+	vt->rangehigh = MAX_TV_FREQ;
+	qual = vivid_get_quality(dev, &vt->afc);
+	if (qual == TPG_QUAL_COLOR)
+		vt->signal = 0xffff;
+	else if (qual == TPG_QUAL_GRAY)
+		vt->signal = 0x8000;
+	else
+		vt->signal = 0;
+	if (qual == TPG_QUAL_NOISE) {
+		vt->rxsubchans = 0;
+	} else if (qual == TPG_QUAL_GRAY) {
+		vt->rxsubchans = V4L2_TUNER_SUB_MONO;
+	} else {
+		unsigned channel_nr = dev->tv_freq / (6 * 16);
+		unsigned options = (dev->std_cap & V4L2_STD_NTSC_M) ? 4 : 3;
+
+		switch (channel_nr % options) {
+		case 0:
+			vt->rxsubchans = V4L2_TUNER_SUB_MONO;
+			break;
+		case 1:
+			vt->rxsubchans = V4L2_TUNER_SUB_STEREO;
+			break;
+		case 2:
+			if (dev->std_cap & V4L2_STD_NTSC_M)
+				vt->rxsubchans = V4L2_TUNER_SUB_MONO | V4L2_TUNER_SUB_SAP;
+			else
+				vt->rxsubchans = V4L2_TUNER_SUB_LANG1 | V4L2_TUNER_SUB_LANG2;
+			break;
+		case 3:
+			vt->rxsubchans = V4L2_TUNER_SUB_STEREO | V4L2_TUNER_SUB_SAP;
+			break;
+		}
+	}
+	strlcpy(vt->name, "TV Tuner", sizeof(vt->name));
+	return 0;
+}
+
+/* Must remain in sync with the vivid_ctrl_standard_strings array */
+const v4l2_std_id vivid_standard[] = {
+	V4L2_STD_NTSC_M,
+	V4L2_STD_NTSC_M_JP,
+	V4L2_STD_NTSC_M_KR,
+	V4L2_STD_NTSC_443,
+	V4L2_STD_PAL_BG | V4L2_STD_PAL_H,
+	V4L2_STD_PAL_I,
+	V4L2_STD_PAL_DK,
+	V4L2_STD_PAL_M,
+	V4L2_STD_PAL_N,
+	V4L2_STD_PAL_Nc,
+	V4L2_STD_PAL_60,
+	V4L2_STD_SECAM_B | V4L2_STD_SECAM_G | V4L2_STD_SECAM_H,
+	V4L2_STD_SECAM_DK,
+	V4L2_STD_SECAM_L,
+	V4L2_STD_SECAM_LC,
+	V4L2_STD_UNKNOWN
+};
+
+/* Must remain in sync with the vivid_standard array */
+const char * const vivid_ctrl_standard_strings[] = {
+	"NTSC-M",
+	"NTSC-M-JP",
+	"NTSC-M-KR",
+	"NTSC-443",
+	"PAL-BGH",
+	"PAL-I",
+	"PAL-DK",
+	"PAL-M",
+	"PAL-N",
+	"PAL-Nc",
+	"PAL-60",
+	"SECAM-BGH",
+	"SECAM-DK",
+	"SECAM-L",
+	"SECAM-Lc",
+	NULL,
+};
+
+int vidioc_querystd(struct file *file, void *priv, v4l2_std_id *id)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_sdtv_cap(dev))
+		return -ENODATA;
+	if (dev->std_signal_mode == NO_SIGNAL ||
+	    dev->std_signal_mode == NO_LOCK) {
+		*id = V4L2_STD_UNKNOWN;
+		return 0;
+	}
+	if (vivid_is_tv_cap(dev) && tpg_g_quality(&dev->tpg) == TPG_QUAL_NOISE) {
+		*id = V4L2_STD_UNKNOWN;
+	} else if (dev->std_signal_mode == CURRENT_STD) {
+		*id = dev->std_cap;
+	} else if (dev->std_signal_mode == SELECTED_STD) {
+		*id = dev->query_std;
+	} else {
+		*id = vivid_standard[dev->query_std_last];
+		dev->query_std_last = (dev->query_std_last + 1) % ARRAY_SIZE(vivid_standard);
+	}
+
+	return 0;
+}
+
+int vivid_vid_cap_s_std(struct file *file, void *priv, v4l2_std_id id)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_sdtv_cap(dev))
+		return -ENODATA;
+	if (dev->std_cap == id)
+		return 0;
+	if (vb2_is_busy(&dev->vb_vid_cap_q) || vb2_is_busy(&dev->vb_vbi_cap_q))
+		return -EBUSY;
+	dev->std_cap = id;
+	vivid_update_format_cap(dev, false);
+	return 0;
+}
+
+int vivid_vid_cap_s_dv_timings(struct file *file, void *_fh,
+				    struct v4l2_dv_timings *timings)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_hdmi_cap(dev))
+		return -ENODATA;
+	if (vb2_is_busy(&dev->vb_vid_cap_q))
+		return -EBUSY;
+	if (!v4l2_find_dv_timings_cap(timings, &vivid_dv_timings_cap,
+				0, NULL, NULL))
+		return -EINVAL;
+	if (v4l2_match_dv_timings(timings, &dev->dv_timings_cap, 0))
+		return 0;
+	dev->dv_timings_cap = *timings;
+	vivid_update_format_cap(dev, false);
+	return 0;
+}
+
+int vidioc_query_dv_timings(struct file *file, void *_fh,
+				    struct v4l2_dv_timings *timings)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_hdmi_cap(dev))
+		return -ENODATA;
+	if (dev->dv_timings_signal_mode == NO_SIGNAL ||
+	    dev->edid_blocks == 0)
+		return -ENOLINK;
+	if (dev->dv_timings_signal_mode == NO_LOCK)
+		return -ENOLCK;
+	if (dev->dv_timings_signal_mode == OUT_OF_RANGE) {
+		timings->bt.pixelclock = vivid_dv_timings_cap.bt.max_pixelclock * 2;
+		return -ERANGE;
+	}
+	if (dev->dv_timings_signal_mode == CURRENT_DV_TIMINGS) {
+		*timings = dev->dv_timings_cap;
+	} else if (dev->dv_timings_signal_mode == SELECTED_DV_TIMINGS) {
+		*timings = v4l2_dv_timings_presets[dev->query_dv_timings];
+	} else {
+		*timings = v4l2_dv_timings_presets[dev->query_dv_timings_last];
+		dev->query_dv_timings_last = (dev->query_dv_timings_last + 1) %
+						dev->query_dv_timings_size;
+	}
+	return 0;
+}
+
+int vidioc_s_edid(struct file *file, void *_fh,
+			 struct v4l2_edid *edid)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	memset(edid->reserved, 0, sizeof(edid->reserved));
+	if (edid->pad >= dev->num_inputs)
+		return -EINVAL;
+	if (dev->input_type[edid->pad] != HDMI || edid->start_block)
+		return -EINVAL;
+	if (edid->blocks == 0) {
+		dev->edid_blocks = 0;
+		return 0;
+	}
+	if (edid->blocks > dev->edid_max_blocks) {
+		edid->blocks = dev->edid_max_blocks;
+		return -E2BIG;
+	}
+	dev->edid_blocks = edid->blocks;
+	memcpy(dev->edid, edid->edid, edid->blocks * 128);
+	return 0;
+}
+
+int vidioc_enum_framesizes(struct file *file, void *fh,
+					 struct v4l2_frmsizeenum *fsize)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_webcam(dev) && !dev->has_scaler_cap)
+		return -EINVAL;
+	if (vivid_get_format(dev, fsize->pixel_format) == NULL)
+		return -EINVAL;
+	if (vivid_is_webcam(dev)) {
+		if (fsize->index >= ARRAY_SIZE(webcam_sizes))
+			return -EINVAL;
+		fsize->type = V4L2_FRMSIZE_TYPE_DISCRETE;
+		fsize->discrete = webcam_sizes[fsize->index];
+		return 0;
+	}
+	if (fsize->index)
+		return -EINVAL;
+	fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE;
+	fsize->stepwise.min_width = MIN_WIDTH;
+	fsize->stepwise.max_width = MAX_WIDTH * MAX_ZOOM;
+	fsize->stepwise.step_width = 2;
+	fsize->stepwise.min_height = MIN_HEIGHT;
+	fsize->stepwise.max_height = MAX_HEIGHT * MAX_ZOOM;
+	fsize->stepwise.step_height = 2;
+	return 0;
+}
+
+/* timeperframe is arbitrary and continuous */
+int vidioc_enum_frameintervals(struct file *file, void *priv,
+					     struct v4l2_frmivalenum *fival)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	const struct vivid_fmt *fmt;
+	int i;
+
+	fmt = vivid_get_format(dev, fival->pixel_format);
+	if (!fmt)
+		return -EINVAL;
+
+	if (!vivid_is_webcam(dev)) {
+		static const struct v4l2_fract step = { 1, 1 };
+
+		if (fival->index)
+			return -EINVAL;
+		if (fival->width < MIN_WIDTH || fival->width > MAX_WIDTH * MAX_ZOOM)
+			return -EINVAL;
+		if (fival->height < MIN_HEIGHT || fival->height > MAX_HEIGHT * MAX_ZOOM)
+			return -EINVAL;
+		fival->type = V4L2_FRMIVAL_TYPE_CONTINUOUS;
+		fival->stepwise.min = tpf_min;
+		fival->stepwise.max = tpf_max;
+		fival->stepwise.step = step;
+		return 0;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(webcam_sizes); i++)
+		if (fival->width == webcam_sizes[i].width &&
+		    fival->height == webcam_sizes[i].height)
+			break;
+	if (i == ARRAY_SIZE(webcam_sizes))
+		return -EINVAL;
+	if (fival->index >= 2 * (3 - i))
+		return -EINVAL;
+	fival->type = V4L2_FRMIVAL_TYPE_DISCRETE;
+	fival->discrete = webcam_intervals[fival->index];
+	return 0;
+}
+
+int vivid_vid_cap_g_parm(struct file *file, void *priv,
+			  struct v4l2_streamparm *parm)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (parm->type != (dev->multiplanar ?
+			   V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE :
+			   V4L2_BUF_TYPE_VIDEO_CAPTURE))
+		return -EINVAL;
+
+	parm->parm.capture.capability   = V4L2_CAP_TIMEPERFRAME;
+	parm->parm.capture.timeperframe = dev->timeperframe_vid_cap;
+	parm->parm.capture.readbuffers  = 1;
+	return 0;
+}
+
+#define FRACT_CMP(a, OP, b)	\
+	((u64)(a).numerator * (b).denominator  OP  (u64)(b).numerator * (a).denominator)
+
+int vivid_vid_cap_s_parm(struct file *file, void *priv,
+			  struct v4l2_streamparm *parm)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	unsigned ival_sz = 2 * (3 - dev->webcam_size_idx);
+	struct v4l2_fract tpf;
+	unsigned i;
+
+	if (parm->type != (dev->multiplanar ?
+			   V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE :
+			   V4L2_BUF_TYPE_VIDEO_CAPTURE))
+		return -EINVAL;
+	if (!vivid_is_webcam(dev))
+		return vivid_vid_cap_g_parm(file, priv, parm);
+
+	tpf = parm->parm.capture.timeperframe;
+
+	if (tpf.denominator == 0)
+		tpf = webcam_intervals[ival_sz - 1];
+	for (i = 0; i < ival_sz; i++)
+		if (FRACT_CMP(tpf, >=, webcam_intervals[i]))
+			break;
+	if (i == ival_sz)
+		i = ival_sz - 1;
+	dev->webcam_ival_idx = i;
+	tpf = webcam_intervals[dev->webcam_ival_idx];
+	tpf = FRACT_CMP(tpf, <, tpf_min) ? tpf_min : tpf;
+	tpf = FRACT_CMP(tpf, >, tpf_max) ? tpf_max : tpf;
+
+	/* resync the thread's timings */
+	dev->cap_seq_resync = true;
+	dev->timeperframe_vid_cap = tpf;
+	parm->parm.capture.timeperframe = tpf;
+	parm->parm.capture.readbuffers  = 1;
+	return 0;
+}
diff --git a/drivers/media/platform/vivid/vivid-vid-cap.h b/drivers/media/platform/vivid/vivid-vid-cap.h
new file mode 100644
index 000000000000..94079815dbc2
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vid-cap.h
@@ -0,0 +1,71 @@
+/*
+ * vivid-vid-cap.h - video capture support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_VID_CAP_H_
+#define _VIVID_VID_CAP_H_
+
+void vivid_update_quality(struct vivid_dev *dev);
+void vivid_update_format_cap(struct vivid_dev *dev, bool keep_controls);
+enum tpg_video_aspect vivid_get_video_aspect(const struct vivid_dev *dev);
+
+extern const v4l2_std_id vivid_standard[];
+extern const char * const vivid_ctrl_standard_strings[];
+
+extern const struct vb2_ops vivid_vid_cap_qops;
+
+int vivid_g_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f);
+int vivid_try_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f);
+int vivid_s_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_g_fmt_vid_cap_mplane(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_try_fmt_vid_cap_mplane(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_s_fmt_vid_cap_mplane(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_g_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_try_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_s_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f);
+int vivid_vid_cap_g_selection(struct file *file, void *priv, struct v4l2_selection *sel);
+int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection *s);
+int vivid_vid_cap_cropcap(struct file *file, void *priv, struct v4l2_cropcap *cap);
+int vidioc_enum_fmt_vid_overlay(struct file *file, void  *priv, struct v4l2_fmtdesc *f);
+int vidioc_g_fmt_vid_overlay(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_try_fmt_vid_overlay(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_s_fmt_vid_overlay(struct file *file, void *priv, struct v4l2_format *f);
+int vivid_vid_cap_overlay(struct file *file, void *fh, unsigned i);
+int vivid_vid_cap_g_fbuf(struct file *file, void *fh, struct v4l2_framebuffer *a);
+int vivid_vid_cap_s_fbuf(struct file *file, void *fh, const struct v4l2_framebuffer *a);
+int vidioc_enum_input(struct file *file, void *priv, struct v4l2_input *inp);
+int vidioc_g_input(struct file *file, void *priv, unsigned *i);
+int vidioc_s_input(struct file *file, void *priv, unsigned i);
+int vidioc_enumaudio(struct file *file, void *fh, struct v4l2_audio *vin);
+int vidioc_g_audio(struct file *file, void *fh, struct v4l2_audio *vin);
+int vidioc_s_audio(struct file *file, void *fh, const struct v4l2_audio *vin);
+int vivid_video_g_frequency(struct file *file, void *fh, struct v4l2_frequency *vf);
+int vivid_video_s_frequency(struct file *file, void *fh, const struct v4l2_frequency *vf);
+int vivid_video_s_tuner(struct file *file, void *fh, const struct v4l2_tuner *vt);
+int vivid_video_g_tuner(struct file *file, void *fh, struct v4l2_tuner *vt);
+int vidioc_querystd(struct file *file, void *priv, v4l2_std_id *id);
+int vivid_vid_cap_s_std(struct file *file, void *priv, v4l2_std_id id);
+int vivid_vid_cap_s_dv_timings(struct file *file, void *_fh, struct v4l2_dv_timings *timings);
+int vidioc_query_dv_timings(struct file *file, void *_fh, struct v4l2_dv_timings *timings);
+int vidioc_s_edid(struct file *file, void *_fh, struct v4l2_edid *edid);
+int vidioc_enum_framesizes(struct file *file, void *fh, struct v4l2_frmsizeenum *fsize);
+int vidioc_enum_frameintervals(struct file *file, void *priv, struct v4l2_frmivalenum *fival);
+int vivid_vid_cap_g_parm(struct file *file, void *priv, struct v4l2_streamparm *parm);
+int vivid_vid_cap_s_parm(struct file *file, void *priv, struct v4l2_streamparm *parm);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-vid-common.c b/drivers/media/platform/vivid/vivid-vid-common.c
new file mode 100644
index 000000000000..16cd6d2d2ed6
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vid-common.c
@@ -0,0 +1,571 @@
+/*
+ * vivid-vid-common.c - common video support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/videodev2.h>
+#include <linux/v4l2-dv-timings.h>
+#include <media/v4l2-common.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-dv-timings.h>
+
+#include "vivid-core.h"
+#include "vivid-vid-common.h"
+
+const struct v4l2_dv_timings_cap vivid_dv_timings_cap = {
+	.type = V4L2_DV_BT_656_1120,
+	/* keep this initialization for compatibility with GCC < 4.4.6 */
+	.reserved = { 0 },
+	V4L2_INIT_BT_TIMINGS(0, MAX_WIDTH, 0, MAX_HEIGHT, 25000000, 600000000,
+		V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT,
+		V4L2_DV_BT_CAP_PROGRESSIVE | V4L2_DV_BT_CAP_INTERLACED)
+};
+
+/* ------------------------------------------------------------------
+	Basic structures
+   ------------------------------------------------------------------*/
+
+struct vivid_fmt vivid_formats[] = {
+	{
+		.name     = "4:2:2, packed, YUYV",
+		.fourcc   = V4L2_PIX_FMT_YUYV,
+		.depth    = 16,
+		.is_yuv   = true,
+		.planes   = 1,
+		.data_offset = { PLANE0_DATA_OFFSET, 0 },
+	},
+	{
+		.name     = "4:2:2, packed, UYVY",
+		.fourcc   = V4L2_PIX_FMT_UYVY,
+		.depth    = 16,
+		.is_yuv   = true,
+		.planes   = 1,
+	},
+	{
+		.name     = "4:2:2, packed, YVYU",
+		.fourcc   = V4L2_PIX_FMT_YVYU,
+		.depth    = 16,
+		.is_yuv   = true,
+		.planes   = 1,
+	},
+	{
+		.name     = "4:2:2, packed, VYUY",
+		.fourcc   = V4L2_PIX_FMT_VYUY,
+		.depth    = 16,
+		.is_yuv   = true,
+		.planes   = 1,
+	},
+	{
+		.name     = "RGB565 (LE)",
+		.fourcc   = V4L2_PIX_FMT_RGB565, /* gggbbbbb rrrrrggg */
+		.depth    = 16,
+		.planes   = 1,
+		.can_do_overlay = true,
+	},
+	{
+		.name     = "RGB565 (BE)",
+		.fourcc   = V4L2_PIX_FMT_RGB565X, /* rrrrrggg gggbbbbb */
+		.depth    = 16,
+		.planes   = 1,
+		.can_do_overlay = true,
+	},
+	{
+		.name     = "RGB555 (LE)",
+		.fourcc   = V4L2_PIX_FMT_RGB555, /* gggbbbbb arrrrrgg */
+		.depth    = 16,
+		.planes   = 1,
+		.can_do_overlay = true,
+	},
+	{
+		.name     = "XRGB555 (LE)",
+		.fourcc   = V4L2_PIX_FMT_XRGB555, /* gggbbbbb arrrrrgg */
+		.depth    = 16,
+		.planes   = 1,
+		.can_do_overlay = true,
+	},
+	{
+		.name     = "ARGB555 (LE)",
+		.fourcc   = V4L2_PIX_FMT_ARGB555, /* gggbbbbb arrrrrgg */
+		.depth    = 16,
+		.planes   = 1,
+		.can_do_overlay = true,
+		.alpha_mask = 0x8000,
+	},
+	{
+		.name     = "RGB555 (BE)",
+		.fourcc   = V4L2_PIX_FMT_RGB555X, /* arrrrrgg gggbbbbb */
+		.depth    = 16,
+		.planes   = 1,
+		.can_do_overlay = true,
+	},
+	{
+		.name     = "RGB24 (LE)",
+		.fourcc   = V4L2_PIX_FMT_RGB24, /* rgb */
+		.depth    = 24,
+		.planes   = 1,
+	},
+	{
+		.name     = "RGB24 (BE)",
+		.fourcc   = V4L2_PIX_FMT_BGR24, /* bgr */
+		.depth    = 24,
+		.planes   = 1,
+	},
+	{
+		.name     = "RGB32 (LE)",
+		.fourcc   = V4L2_PIX_FMT_RGB32, /* argb */
+		.depth    = 32,
+		.planes   = 1,
+	},
+	{
+		.name     = "RGB32 (BE)",
+		.fourcc   = V4L2_PIX_FMT_BGR32, /* bgra */
+		.depth    = 32,
+		.planes   = 1,
+	},
+	{
+		.name     = "XRGB32 (LE)",
+		.fourcc   = V4L2_PIX_FMT_XRGB32, /* argb */
+		.depth    = 32,
+		.planes   = 1,
+	},
+	{
+		.name     = "XRGB32 (BE)",
+		.fourcc   = V4L2_PIX_FMT_XBGR32, /* bgra */
+		.depth    = 32,
+		.planes   = 1,
+	},
+	{
+		.name     = "ARGB32 (LE)",
+		.fourcc   = V4L2_PIX_FMT_ARGB32, /* argb */
+		.depth    = 32,
+		.planes   = 1,
+		.alpha_mask = 0x000000ff,
+	},
+	{
+		.name     = "ARGB32 (BE)",
+		.fourcc   = V4L2_PIX_FMT_ABGR32, /* bgra */
+		.depth    = 32,
+		.planes   = 1,
+		.alpha_mask = 0xff000000,
+	},
+	{
+		.name     = "4:2:2, planar, YUV",
+		.fourcc   = V4L2_PIX_FMT_NV16M,
+		.depth    = 8,
+		.is_yuv   = true,
+		.planes   = 2,
+		.data_offset = { PLANE0_DATA_OFFSET, 0 },
+	},
+	{
+		.name     = "4:2:2, planar, YVU",
+		.fourcc   = V4L2_PIX_FMT_NV61M,
+		.depth    = 8,
+		.is_yuv   = true,
+		.planes   = 2,
+		.data_offset = { 0, PLANE0_DATA_OFFSET },
+	},
+};
+
+/* There are 2 multiplanar formats in the list */
+#define VIVID_MPLANAR_FORMATS 2
+
+const struct vivid_fmt *vivid_get_format(struct vivid_dev *dev, u32 pixelformat)
+{
+	const struct vivid_fmt *fmt;
+	unsigned k;
+
+	for (k = 0; k < ARRAY_SIZE(vivid_formats); k++) {
+		fmt = &vivid_formats[k];
+		if (fmt->fourcc == pixelformat)
+			if (fmt->planes == 1 || dev->multiplanar)
+				return fmt;
+	}
+
+	return NULL;
+}
+
+bool vivid_vid_can_loop(struct vivid_dev *dev)
+{
+	if (dev->src_rect.width != dev->sink_rect.width ||
+	    dev->src_rect.height != dev->sink_rect.height)
+		return false;
+	if (dev->fmt_cap->fourcc != dev->fmt_out->fourcc)
+		return false;
+	if (dev->field_cap != dev->field_out)
+		return false;
+	if (vivid_is_svid_cap(dev) && vivid_is_svid_out(dev)) {
+		if (!(dev->std_cap & V4L2_STD_525_60) !=
+		    !(dev->std_out & V4L2_STD_525_60))
+			return false;
+		return true;
+	}
+	if (vivid_is_hdmi_cap(dev) && vivid_is_hdmi_out(dev))
+		return true;
+	return false;
+}
+
+void vivid_send_source_change(struct vivid_dev *dev, unsigned type)
+{
+	struct v4l2_event ev = {
+		.type = V4L2_EVENT_SOURCE_CHANGE,
+		.u.src_change.changes = V4L2_EVENT_SRC_CH_RESOLUTION,
+	};
+	unsigned i;
+
+	for (i = 0; i < dev->num_inputs; i++) {
+		ev.id = i;
+		if (dev->input_type[i] == type) {
+			if (video_is_registered(&dev->vid_cap_dev) && dev->has_vid_cap)
+				v4l2_event_queue(&dev->vid_cap_dev, &ev);
+			if (video_is_registered(&dev->vbi_cap_dev) && dev->has_vbi_cap)
+				v4l2_event_queue(&dev->vbi_cap_dev, &ev);
+		}
+	}
+}
+
+/*
+ * Conversion function that converts a single-planar format to a
+ * single-plane multiplanar format.
+ */
+void fmt_sp2mp(const struct v4l2_format *sp_fmt, struct v4l2_format *mp_fmt)
+{
+	struct v4l2_pix_format_mplane *mp = &mp_fmt->fmt.pix_mp;
+	struct v4l2_plane_pix_format *ppix = &mp->plane_fmt[0];
+	const struct v4l2_pix_format *pix = &sp_fmt->fmt.pix;
+	bool is_out = sp_fmt->type == V4L2_BUF_TYPE_VIDEO_OUTPUT;
+
+	memset(mp->reserved, 0, sizeof(mp->reserved));
+	mp_fmt->type = is_out ? V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE :
+			   V4L2_CAP_VIDEO_CAPTURE_MPLANE;
+	mp->width = pix->width;
+	mp->height = pix->height;
+	mp->pixelformat = pix->pixelformat;
+	mp->field = pix->field;
+	mp->colorspace = pix->colorspace;
+	mp->num_planes = 1;
+	mp->flags = pix->flags;
+	ppix->sizeimage = pix->sizeimage;
+	ppix->bytesperline = pix->bytesperline;
+	memset(ppix->reserved, 0, sizeof(ppix->reserved));
+}
+
+int fmt_sp2mp_func(struct file *file, void *priv,
+		struct v4l2_format *f, fmtfunc func)
+{
+	struct v4l2_format fmt;
+	struct v4l2_pix_format_mplane *mp = &fmt.fmt.pix_mp;
+	struct v4l2_plane_pix_format *ppix = &mp->plane_fmt[0];
+	struct v4l2_pix_format *pix = &f->fmt.pix;
+	int ret;
+
+	/* Converts to a mplane format */
+	fmt_sp2mp(f, &fmt);
+	/* Passes it to the generic mplane format function */
+	ret = func(file, priv, &fmt);
+	/* Copies back the mplane data to the single plane format */
+	pix->width = mp->width;
+	pix->height = mp->height;
+	pix->pixelformat = mp->pixelformat;
+	pix->field = mp->field;
+	pix->colorspace = mp->colorspace;
+	pix->sizeimage = ppix->sizeimage;
+	pix->bytesperline = ppix->bytesperline;
+	pix->flags = mp->flags;
+	return ret;
+}
+
+/* v4l2_rect helper function: copy the width/height values */
+void rect_set_size_to(struct v4l2_rect *r, const struct v4l2_rect *size)
+{
+	r->width = size->width;
+	r->height = size->height;
+}
+
+/* v4l2_rect helper function: width and height of r should be >= min_size */
+void rect_set_min_size(struct v4l2_rect *r, const struct v4l2_rect *min_size)
+{
+	if (r->width < min_size->width)
+		r->width = min_size->width;
+	if (r->height < min_size->height)
+		r->height = min_size->height;
+}
+
+/* v4l2_rect helper function: width and height of r should be <= max_size */
+void rect_set_max_size(struct v4l2_rect *r, const struct v4l2_rect *max_size)
+{
+	if (r->width > max_size->width)
+		r->width = max_size->width;
+	if (r->height > max_size->height)
+		r->height = max_size->height;
+}
+
+/* v4l2_rect helper function: r should be inside boundary */
+void rect_map_inside(struct v4l2_rect *r, const struct v4l2_rect *boundary)
+{
+	rect_set_max_size(r, boundary);
+	if (r->left < boundary->left)
+		r->left = boundary->left;
+	if (r->top < boundary->top)
+		r->top = boundary->top;
+	if (r->left + r->width > boundary->width)
+		r->left = boundary->width - r->width;
+	if (r->top + r->height > boundary->height)
+		r->top = boundary->height - r->height;
+}
+
+/* v4l2_rect helper function: return true if r1 has the same size as r2 */
+bool rect_same_size(const struct v4l2_rect *r1, const struct v4l2_rect *r2)
+{
+	return r1->width == r2->width && r1->height == r2->height;
+}
+
+/* v4l2_rect helper function: calculate the intersection of two rects */
+struct v4l2_rect rect_intersect(const struct v4l2_rect *a, const struct v4l2_rect *b)
+{
+	struct v4l2_rect r;
+	int right, bottom;
+
+	r.top = max(a->top, b->top);
+	r.left = max(a->left, b->left);
+	bottom = min(a->top + a->height, b->top + b->height);
+	right = min(a->left + a->width, b->left + b->width);
+	r.height = max(0, bottom - r.top);
+	r.width = max(0, right - r.left);
+	return r;
+}
+
+/*
+ * v4l2_rect helper function: scale rect r by to->width / from->width and
+ * to->height / from->height.
+ */
+void rect_scale(struct v4l2_rect *r, const struct v4l2_rect *from,
+				     const struct v4l2_rect *to)
+{
+	if (from->width == 0 || from->height == 0) {
+		r->left = r->top = r->width = r->height = 0;
+		return;
+	}
+	r->left = (((r->left - from->left) * to->width) / from->width) & ~1;
+	r->width = ((r->width * to->width) / from->width) & ~1;
+	r->top = ((r->top - from->top) * to->height) / from->height;
+	r->height = (r->height * to->height) / from->height;
+}
+
+bool rect_overlap(const struct v4l2_rect *r1, const struct v4l2_rect *r2)
+{
+	/*
+	 * IF the left side of r1 is to the right of the right side of r2 OR
+	 *    the left side of r2 is to the right of the right side of r1 THEN
+	 * they do not overlap.
+	 */
+	if (r1->left >= r2->left + r2->width ||
+	    r2->left >= r1->left + r1->width)
+		return false;
+	/*
+	 * IF the top side of r1 is below the bottom of r2 OR
+	 *    the top side of r2 is below the bottom of r1 THEN
+	 * they do not overlap.
+	 */
+	if (r1->top >= r2->top + r2->height ||
+	    r2->top >= r1->top + r1->height)
+		return false;
+	return true;
+}
+int vivid_vid_adjust_sel(unsigned flags, struct v4l2_rect *r)
+{
+	unsigned w = r->width;
+	unsigned h = r->height;
+
+	if (!(flags & V4L2_SEL_FLAG_LE)) {
+		w++;
+		h++;
+		if (w < 2)
+			w = 2;
+		if (h < 2)
+			h = 2;
+	}
+	if (!(flags & V4L2_SEL_FLAG_GE)) {
+		if (w > MAX_WIDTH)
+			w = MAX_WIDTH;
+		if (h > MAX_HEIGHT)
+			h = MAX_HEIGHT;
+	}
+	w = w & ~1;
+	h = h & ~1;
+	if (w < 2 || h < 2)
+		return -ERANGE;
+	if (w > MAX_WIDTH || h > MAX_HEIGHT)
+		return -ERANGE;
+	if (r->top < 0)
+		r->top = 0;
+	if (r->left < 0)
+		r->left = 0;
+	r->left &= ~1;
+	r->top &= ~1;
+	if (r->left + w > MAX_WIDTH)
+		r->left = MAX_WIDTH - w;
+	if (r->top + h > MAX_HEIGHT)
+		r->top = MAX_HEIGHT - h;
+	if ((flags & (V4L2_SEL_FLAG_GE | V4L2_SEL_FLAG_LE)) ==
+			(V4L2_SEL_FLAG_GE | V4L2_SEL_FLAG_LE) &&
+	    (r->width != w || r->height != h))
+		return -ERANGE;
+	r->width = w;
+	r->height = h;
+	return 0;
+}
+
+int vivid_enum_fmt_vid(struct file *file, void  *priv,
+					struct v4l2_fmtdesc *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	const struct vivid_fmt *fmt;
+
+	if (f->index >= ARRAY_SIZE(vivid_formats) -
+	    (dev->multiplanar ? 0 : VIVID_MPLANAR_FORMATS))
+		return -EINVAL;
+
+	fmt = &vivid_formats[f->index];
+
+	strlcpy(f->description, fmt->name, sizeof(f->description));
+	f->pixelformat = fmt->fourcc;
+	return 0;
+}
+
+int vidioc_enum_fmt_vid_mplane(struct file *file, void  *priv,
+					struct v4l2_fmtdesc *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!dev->multiplanar)
+		return -ENOTTY;
+	return vivid_enum_fmt_vid(file, priv, f);
+}
+
+int vidioc_enum_fmt_vid(struct file *file, void  *priv,
+					struct v4l2_fmtdesc *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (dev->multiplanar)
+		return -ENOTTY;
+	return vivid_enum_fmt_vid(file, priv, f);
+}
+
+int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *id)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX) {
+		if (!vivid_is_sdtv_cap(dev))
+			return -ENODATA;
+		*id = dev->std_cap;
+	} else {
+		if (!vivid_is_svid_out(dev))
+			return -ENODATA;
+		*id = dev->std_out;
+	}
+	return 0;
+}
+
+int vidioc_g_dv_timings(struct file *file, void *_fh,
+				    struct v4l2_dv_timings *timings)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX) {
+		if (!vivid_is_hdmi_cap(dev))
+			return -ENODATA;
+		*timings = dev->dv_timings_cap;
+	} else {
+		if (!vivid_is_hdmi_out(dev))
+			return -ENODATA;
+		*timings = dev->dv_timings_out;
+	}
+	return 0;
+}
+
+int vidioc_enum_dv_timings(struct file *file, void *_fh,
+				    struct v4l2_enum_dv_timings *timings)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX) {
+		if (!vivid_is_hdmi_cap(dev))
+			return -ENODATA;
+	} else {
+		if (!vivid_is_hdmi_out(dev))
+			return -ENODATA;
+	}
+	return v4l2_enum_dv_timings_cap(timings, &vivid_dv_timings_cap,
+			NULL, NULL);
+}
+
+int vidioc_dv_timings_cap(struct file *file, void *_fh,
+				    struct v4l2_dv_timings_cap *cap)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_dir == VFL_DIR_RX) {
+		if (!vivid_is_hdmi_cap(dev))
+			return -ENODATA;
+	} else {
+		if (!vivid_is_hdmi_out(dev))
+			return -ENODATA;
+	}
+	*cap = vivid_dv_timings_cap;
+	return 0;
+}
+
+int vidioc_g_edid(struct file *file, void *_fh,
+			 struct v4l2_edid *edid)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct video_device *vdev = video_devdata(file);
+
+	memset(edid->reserved, 0, sizeof(edid->reserved));
+	if (vdev->vfl_dir == VFL_DIR_RX) {
+		if (edid->pad >= dev->num_inputs)
+			return -EINVAL;
+		if (dev->input_type[edid->pad] != HDMI)
+			return -EINVAL;
+	} else {
+		if (edid->pad >= dev->num_outputs)
+			return -EINVAL;
+		if (dev->output_type[edid->pad] != HDMI)
+			return -EINVAL;
+	}
+	if (edid->start_block == 0 && edid->blocks == 0) {
+		edid->blocks = dev->edid_blocks;
+		return 0;
+	}
+	if (dev->edid_blocks == 0)
+		return -ENODATA;
+	if (edid->start_block >= dev->edid_blocks)
+		return -EINVAL;
+	if (edid->start_block + edid->blocks > dev->edid_blocks)
+		edid->blocks = dev->edid_blocks - edid->start_block;
+	memcpy(edid->edid, dev->edid, edid->blocks * 128);
+	return 0;
+}
diff --git a/drivers/media/platform/vivid/vivid-vid-common.h b/drivers/media/platform/vivid/vivid-vid-common.h
new file mode 100644
index 000000000000..3ec4fa85c9b9
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vid-common.h
@@ -0,0 +1,61 @@
+/*
+ * vivid-vid-common.h - common video support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_VID_COMMON_H_
+#define _VIVID_VID_COMMON_H_
+
+typedef int (*fmtfunc)(struct file *file, void *priv, struct v4l2_format *f);
+
+/*
+ * Conversion function that converts a single-planar format to a
+ * single-plane multiplanar format.
+ */
+void fmt_sp2mp(const struct v4l2_format *sp_fmt, struct v4l2_format *mp_fmt);
+int fmt_sp2mp_func(struct file *file, void *priv,
+		struct v4l2_format *f, fmtfunc func);
+
+extern const struct v4l2_dv_timings_cap vivid_dv_timings_cap;
+
+const struct vivid_fmt *vivid_get_format(struct vivid_dev *dev, u32 pixelformat);
+
+bool vivid_vid_can_loop(struct vivid_dev *dev);
+void vivid_send_source_change(struct vivid_dev *dev, unsigned type);
+
+bool rect_overlap(const struct v4l2_rect *r1, const struct v4l2_rect *r2);
+void rect_set_size_to(struct v4l2_rect *r, const struct v4l2_rect *size);
+void rect_set_min_size(struct v4l2_rect *r, const struct v4l2_rect *min_size);
+void rect_set_max_size(struct v4l2_rect *r, const struct v4l2_rect *max_size);
+void rect_map_inside(struct v4l2_rect *r, const struct v4l2_rect *boundary);
+bool rect_same_size(const struct v4l2_rect *r1, const struct v4l2_rect *r2);
+struct v4l2_rect rect_intersect(const struct v4l2_rect *a, const struct v4l2_rect *b);
+void rect_scale(struct v4l2_rect *r, const struct v4l2_rect *from,
+				     const struct v4l2_rect *to);
+int vivid_vid_adjust_sel(unsigned flags, struct v4l2_rect *r);
+
+int vivid_enum_fmt_vid(struct file *file, void  *priv, struct v4l2_fmtdesc *f);
+int vidioc_enum_fmt_vid_mplane(struct file *file, void  *priv, struct v4l2_fmtdesc *f);
+int vidioc_enum_fmt_vid(struct file *file, void  *priv, struct v4l2_fmtdesc *f);
+int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *id);
+int vidioc_g_dv_timings(struct file *file, void *_fh, struct v4l2_dv_timings *timings);
+int vidioc_enum_dv_timings(struct file *file, void *_fh, struct v4l2_enum_dv_timings *timings);
+int vidioc_dv_timings_cap(struct file *file, void *_fh, struct v4l2_dv_timings_cap *cap);
+int vidioc_g_edid(struct file *file, void *_fh, struct v4l2_edid *edid);
+int vidioc_subscribe_event(struct v4l2_fh *fh, const struct v4l2_event_subscription *sub);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-vid-out.c b/drivers/media/platform/vivid/vivid-vid-out.c
new file mode 100644
index 000000000000..69c2dbd2d165
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vid-out.c
@@ -0,0 +1,1146 @@
+/*
+ * vivid-vid-out.c - video output support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/videodev2.h>
+#include <linux/v4l2-dv-timings.h>
+#include <media/v4l2-common.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-dv-timings.h>
+
+#include "vivid-core.h"
+#include "vivid-vid-common.h"
+#include "vivid-kthread-out.h"
+#include "vivid-vid-out.h"
+
+static int vid_out_queue_setup(struct vb2_queue *vq, const struct v4l2_format *fmt,
+		       unsigned *nbuffers, unsigned *nplanes,
+		       unsigned sizes[], void *alloc_ctxs[])
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	unsigned planes = dev->fmt_out->planes;
+	unsigned h = dev->fmt_out_rect.height;
+	unsigned size = dev->bytesperline_out[0] * h;
+
+	if (dev->field_out == V4L2_FIELD_ALTERNATE) {
+		/*
+		 * You cannot use write() with FIELD_ALTERNATE since the field
+		 * information (TOP/BOTTOM) cannot be passed to the kernel.
+		 */
+		if (vb2_fileio_is_active(vq))
+			return -EINVAL;
+	}
+
+	if (dev->queue_setup_error) {
+		/*
+		 * Error injection: test what happens if queue_setup() returns
+		 * an error.
+		 */
+		dev->queue_setup_error = false;
+		return -EINVAL;
+	}
+
+	if (fmt) {
+		const struct v4l2_pix_format_mplane *mp;
+		struct v4l2_format mp_fmt;
+
+		if (!V4L2_TYPE_IS_MULTIPLANAR(fmt->type)) {
+			fmt_sp2mp(fmt, &mp_fmt);
+			fmt = &mp_fmt;
+		}
+		mp = &fmt->fmt.pix_mp;
+		/*
+		 * Check if the number of planes in the specified format match
+		 * the number of planes in the current format. You can't mix that.
+		 */
+		if (mp->num_planes != planes)
+			return -EINVAL;
+		sizes[0] = mp->plane_fmt[0].sizeimage;
+		if (planes == 2) {
+			sizes[1] = mp->plane_fmt[1].sizeimage;
+			if (sizes[0] < dev->bytesperline_out[0] * h ||
+			    sizes[1] < dev->bytesperline_out[1] * h)
+				return -EINVAL;
+		} else if (sizes[0] < size) {
+			return -EINVAL;
+		}
+	} else {
+		if (planes == 2) {
+			sizes[0] = dev->bytesperline_out[0] * h;
+			sizes[1] = dev->bytesperline_out[1] * h;
+		} else {
+			sizes[0] = size;
+		}
+	}
+
+	if (vq->num_buffers + *nbuffers < 2)
+		*nbuffers = 2 - vq->num_buffers;
+
+	*nplanes = planes;
+
+	/*
+	 * videobuf2-vmalloc allocator is context-less so no need to set
+	 * alloc_ctxs array.
+	 */
+
+	if (planes == 2)
+		dprintk(dev, 1, "%s, count=%d, sizes=%u, %u\n", __func__,
+			*nbuffers, sizes[0], sizes[1]);
+	else
+		dprintk(dev, 1, "%s, count=%d, size=%u\n", __func__,
+			*nbuffers, sizes[0]);
+	return 0;
+}
+
+static int vid_out_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	unsigned long size;
+	unsigned planes = dev->fmt_out->planes;
+	unsigned p;
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	if (WARN_ON(NULL == dev->fmt_out))
+		return -EINVAL;
+
+	if (dev->buf_prepare_error) {
+		/*
+		 * Error injection: test what happens if buf_prepare() returns
+		 * an error.
+		 */
+		dev->buf_prepare_error = false;
+		return -EINVAL;
+	}
+
+	if (dev->field_out != V4L2_FIELD_ALTERNATE)
+		vb->v4l2_buf.field = dev->field_out;
+	else if (vb->v4l2_buf.field != V4L2_FIELD_TOP &&
+		 vb->v4l2_buf.field != V4L2_FIELD_BOTTOM)
+		return -EINVAL;
+
+	for (p = 0; p < planes; p++) {
+		size = dev->bytesperline_out[p] * dev->fmt_out_rect.height +
+			vb->v4l2_planes[p].data_offset;
+
+		if (vb2_get_plane_payload(vb, p) < size) {
+			dprintk(dev, 1, "%s the payload is too small for plane %u (%lu < %lu)\n",
+					__func__, p, vb2_get_plane_payload(vb, p), size);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static void vid_out_buf_queue(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct vivid_buffer *buf = container_of(vb, struct vivid_buffer, vb);
+
+	dprintk(dev, 1, "%s\n", __func__);
+
+	spin_lock(&dev->slock);
+	list_add_tail(&buf->list, &dev->vid_out_active);
+	spin_unlock(&dev->slock);
+}
+
+static int vid_out_start_streaming(struct vb2_queue *vq, unsigned count)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	int err;
+
+	if (vb2_is_streaming(&dev->vb_vid_cap_q))
+		dev->can_loop_video = vivid_vid_can_loop(dev);
+
+	if (dev->kthread_vid_out)
+		return 0;
+
+	dev->vid_out_seq_count = 0;
+	dprintk(dev, 1, "%s\n", __func__);
+	if (dev->start_streaming_error) {
+		dev->start_streaming_error = false;
+		err = -EINVAL;
+	} else {
+		err = vivid_start_generating_vid_out(dev, &dev->vid_out_streaming);
+	}
+	if (err) {
+		struct vivid_buffer *buf, *tmp;
+
+		list_for_each_entry_safe(buf, tmp, &dev->vid_out_active, list) {
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
+		}
+	}
+	return err;
+}
+
+/* abort streaming and wait for last buffer */
+static void vid_out_stop_streaming(struct vb2_queue *vq)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+
+	dprintk(dev, 1, "%s\n", __func__);
+	vivid_stop_generating_vid_out(dev, &dev->vid_out_streaming);
+	dev->can_loop_video = false;
+}
+
+const struct vb2_ops vivid_vid_out_qops = {
+	.queue_setup		= vid_out_queue_setup,
+	.buf_prepare		= vid_out_buf_prepare,
+	.buf_queue		= vid_out_buf_queue,
+	.start_streaming	= vid_out_start_streaming,
+	.stop_streaming		= vid_out_stop_streaming,
+	.wait_prepare		= vivid_unlock,
+	.wait_finish		= vivid_lock,
+};
+
+/*
+ * Called whenever the format has to be reset which can occur when
+ * changing outputs, standard, timings, etc.
+ */
+void vivid_update_format_out(struct vivid_dev *dev)
+{
+	struct v4l2_bt_timings *bt = &dev->dv_timings_out.bt;
+	unsigned size;
+
+	switch (dev->output_type[dev->output]) {
+	case SVID:
+	default:
+		dev->field_out = dev->tv_field_out;
+		dev->sink_rect.width = 720;
+		if (dev->std_out & V4L2_STD_525_60) {
+			dev->sink_rect.height = 480;
+			dev->timeperframe_vid_out = (struct v4l2_fract) { 1001, 30000 };
+			dev->service_set_out = V4L2_SLICED_CAPTION_525;
+		} else {
+			dev->sink_rect.height = 576;
+			dev->timeperframe_vid_out = (struct v4l2_fract) { 1000, 25000 };
+			dev->service_set_out = V4L2_SLICED_WSS_625 | V4L2_SLICED_TELETEXT_B;
+		}
+		dev->colorspace_out = V4L2_COLORSPACE_SMPTE170M;
+		break;
+	case HDMI:
+		dev->sink_rect.width = bt->width;
+		dev->sink_rect.height = bt->height;
+		size = V4L2_DV_BT_FRAME_WIDTH(bt) * V4L2_DV_BT_FRAME_HEIGHT(bt);
+		dev->timeperframe_vid_out = (struct v4l2_fract) {
+			size / 100, (u32)bt->pixelclock / 100
+		};
+		if (bt->interlaced)
+			dev->field_out = V4L2_FIELD_ALTERNATE;
+		else
+			dev->field_out = V4L2_FIELD_NONE;
+		if (!dev->dvi_d_out && (bt->standards & V4L2_DV_BT_STD_CEA861)) {
+			if (bt->width == 720 && bt->height <= 576)
+				dev->colorspace_out = V4L2_COLORSPACE_SMPTE170M;
+			else
+				dev->colorspace_out = V4L2_COLORSPACE_REC709;
+		} else {
+			dev->colorspace_out = V4L2_COLORSPACE_SRGB;
+		}
+		break;
+	}
+	dev->compose_out = dev->sink_rect;
+	dev->compose_bounds_out = dev->sink_rect;
+	dev->crop_out = dev->compose_out;
+	if (V4L2_FIELD_HAS_T_OR_B(dev->field_out))
+		dev->crop_out.height /= 2;
+	dev->fmt_out_rect = dev->crop_out;
+	dev->bytesperline_out[0] = (dev->sink_rect.width * dev->fmt_out->depth) / 8;
+	if (dev->fmt_out->planes == 2)
+		dev->bytesperline_out[1] = (dev->sink_rect.width * dev->fmt_out->depth) / 8;
+}
+
+/* Map the field to something that is valid for the current output */
+static enum v4l2_field vivid_field_out(struct vivid_dev *dev, enum v4l2_field field)
+{
+	if (vivid_is_svid_out(dev)) {
+		switch (field) {
+		case V4L2_FIELD_INTERLACED_TB:
+		case V4L2_FIELD_INTERLACED_BT:
+		case V4L2_FIELD_SEQ_TB:
+		case V4L2_FIELD_SEQ_BT:
+		case V4L2_FIELD_ALTERNATE:
+			return field;
+		case V4L2_FIELD_INTERLACED:
+		default:
+			return V4L2_FIELD_INTERLACED;
+		}
+	}
+	if (vivid_is_hdmi_out(dev))
+		return dev->dv_timings_out.bt.interlaced ? V4L2_FIELD_ALTERNATE :
+						       V4L2_FIELD_NONE;
+	return V4L2_FIELD_NONE;
+}
+
+static enum tpg_pixel_aspect vivid_get_pixel_aspect(const struct vivid_dev *dev)
+{
+	if (vivid_is_svid_out(dev))
+		return (dev->std_out & V4L2_STD_525_60) ?
+			TPG_PIXEL_ASPECT_NTSC : TPG_PIXEL_ASPECT_PAL;
+
+	if (vivid_is_hdmi_out(dev) &&
+	    dev->sink_rect.width == 720 && dev->sink_rect.height <= 576)
+		return dev->sink_rect.height == 480 ?
+			TPG_PIXEL_ASPECT_NTSC : TPG_PIXEL_ASPECT_PAL;
+
+	return TPG_PIXEL_ASPECT_SQUARE;
+}
+
+int vivid_g_fmt_vid_out(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_pix_format_mplane *mp = &f->fmt.pix_mp;
+	unsigned p;
+
+	mp->width        = dev->fmt_out_rect.width;
+	mp->height       = dev->fmt_out_rect.height;
+	mp->field        = dev->field_out;
+	mp->pixelformat  = dev->fmt_out->fourcc;
+	mp->colorspace   = dev->colorspace_out;
+	mp->num_planes = dev->fmt_out->planes;
+	for (p = 0; p < mp->num_planes; p++) {
+		mp->plane_fmt[p].bytesperline = dev->bytesperline_out[p];
+		mp->plane_fmt[p].sizeimage =
+			mp->plane_fmt[p].bytesperline * mp->height;
+	}
+	return 0;
+}
+
+int vivid_try_fmt_vid_out(struct file *file, void *priv,
+			struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_bt_timings *bt = &dev->dv_timings_out.bt;
+	struct v4l2_pix_format_mplane *mp = &f->fmt.pix_mp;
+	struct v4l2_plane_pix_format *pfmt = mp->plane_fmt;
+	const struct vivid_fmt *fmt;
+	unsigned bytesperline, max_bpl;
+	unsigned factor = 1;
+	unsigned w, h;
+	unsigned p;
+
+	fmt = vivid_get_format(dev, mp->pixelformat);
+	if (!fmt) {
+		dprintk(dev, 1, "Fourcc format (0x%08x) unknown.\n",
+			mp->pixelformat);
+		mp->pixelformat = V4L2_PIX_FMT_YUYV;
+		fmt = vivid_get_format(dev, mp->pixelformat);
+	}
+
+	mp->field = vivid_field_out(dev, mp->field);
+	if (vivid_is_svid_out(dev)) {
+		w = 720;
+		h = (dev->std_out & V4L2_STD_525_60) ? 480 : 576;
+	} else {
+		w = dev->sink_rect.width;
+		h = dev->sink_rect.height;
+	}
+	if (V4L2_FIELD_HAS_T_OR_B(mp->field))
+		factor = 2;
+	if (!dev->has_scaler_out && !dev->has_crop_out && !dev->has_compose_out) {
+		mp->width = w;
+		mp->height = h / factor;
+	} else {
+		struct v4l2_rect r = { 0, 0, mp->width, mp->height * factor };
+
+		rect_set_min_size(&r, &vivid_min_rect);
+		rect_set_max_size(&r, &vivid_max_rect);
+		if (dev->has_scaler_out && !dev->has_crop_out) {
+			struct v4l2_rect max_r = { 0, 0, MAX_ZOOM * w, MAX_ZOOM * h };
+
+			rect_set_max_size(&r, &max_r);
+		} else if (!dev->has_scaler_out && dev->has_compose_out && !dev->has_crop_out) {
+			rect_set_max_size(&r, &dev->sink_rect);
+		} else if (!dev->has_scaler_out && !dev->has_compose_out) {
+			rect_set_min_size(&r, &dev->sink_rect);
+		}
+		mp->width = r.width;
+		mp->height = r.height / factor;
+	}
+
+	/* This driver supports custom bytesperline values */
+
+	/* Calculate the minimum supported bytesperline value */
+	bytesperline = (mp->width * fmt->depth) >> 3;
+	/* Calculate the maximum supported bytesperline value */
+	max_bpl = (MAX_ZOOM * MAX_WIDTH * fmt->depth) >> 3;
+	mp->num_planes = fmt->planes;
+	for (p = 0; p < mp->num_planes; p++) {
+		if (pfmt[p].bytesperline > max_bpl)
+			pfmt[p].bytesperline = max_bpl;
+		if (pfmt[p].bytesperline < bytesperline)
+			pfmt[p].bytesperline = bytesperline;
+		pfmt[p].sizeimage = pfmt[p].bytesperline * mp->height;
+		memset(pfmt[p].reserved, 0, sizeof(pfmt[p].reserved));
+	}
+	if (vivid_is_svid_out(dev))
+		mp->colorspace = V4L2_COLORSPACE_SMPTE170M;
+	else if (dev->dvi_d_out || !(bt->standards & V4L2_DV_BT_STD_CEA861))
+		mp->colorspace = V4L2_COLORSPACE_SRGB;
+	else if (bt->width == 720 && bt->height <= 576)
+		mp->colorspace = V4L2_COLORSPACE_SMPTE170M;
+	else if (mp->colorspace != V4L2_COLORSPACE_SMPTE170M &&
+		 mp->colorspace != V4L2_COLORSPACE_REC709 &&
+		 mp->colorspace != V4L2_COLORSPACE_SRGB)
+		mp->colorspace = V4L2_COLORSPACE_REC709;
+	memset(mp->reserved, 0, sizeof(mp->reserved));
+	return 0;
+}
+
+int vivid_s_fmt_vid_out(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *mp = &f->fmt.pix_mp;
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_rect *crop = &dev->crop_out;
+	struct v4l2_rect *compose = &dev->compose_out;
+	struct vb2_queue *q = &dev->vb_vid_out_q;
+	int ret = vivid_try_fmt_vid_out(file, priv, f);
+	unsigned factor = 1;
+
+	if (ret < 0)
+		return ret;
+
+	if (vb2_is_busy(q) &&
+	    (vivid_is_svid_out(dev) ||
+	     mp->width != dev->fmt_out_rect.width ||
+	     mp->height != dev->fmt_out_rect.height ||
+	     mp->pixelformat != dev->fmt_out->fourcc ||
+	     mp->field != dev->field_out)) {
+		dprintk(dev, 1, "%s device busy\n", __func__);
+		return -EBUSY;
+	}
+
+	/*
+	 * Allow for changing the colorspace on the fly. Useful for testing
+	 * purposes, and it is something that HDMI transmitters are able
+	 * to do.
+	 */
+	if (vb2_is_busy(q))
+		goto set_colorspace;
+
+	dev->fmt_out = vivid_get_format(dev, mp->pixelformat);
+	if (V4L2_FIELD_HAS_T_OR_B(mp->field))
+		factor = 2;
+
+	if (dev->has_scaler_out || dev->has_crop_out || dev->has_compose_out) {
+		struct v4l2_rect r = { 0, 0, mp->width, mp->height };
+
+		if (dev->has_scaler_out) {
+			if (dev->has_crop_out)
+				rect_map_inside(crop, &r);
+			else
+				*crop = r;
+			if (dev->has_compose_out && !dev->has_crop_out) {
+				struct v4l2_rect min_r = {
+					0, 0,
+					r.width / MAX_ZOOM,
+					factor * r.height / MAX_ZOOM
+				};
+				struct v4l2_rect max_r = {
+					0, 0,
+					r.width * MAX_ZOOM,
+					factor * r.height * MAX_ZOOM
+				};
+
+				rect_set_min_size(compose, &min_r);
+				rect_set_max_size(compose, &max_r);
+				rect_map_inside(compose, &dev->compose_bounds_out);
+			} else if (dev->has_compose_out) {
+				struct v4l2_rect min_r = {
+					0, 0,
+					crop->width / MAX_ZOOM,
+					factor * crop->height / MAX_ZOOM
+				};
+				struct v4l2_rect max_r = {
+					0, 0,
+					crop->width * MAX_ZOOM,
+					factor * crop->height * MAX_ZOOM
+				};
+
+				rect_set_min_size(compose, &min_r);
+				rect_set_max_size(compose, &max_r);
+				rect_map_inside(compose, &dev->compose_bounds_out);
+			}
+		} else if (dev->has_compose_out && !dev->has_crop_out) {
+			rect_set_size_to(crop, &r);
+			r.height *= factor;
+			rect_set_size_to(compose, &r);
+			rect_map_inside(compose, &dev->compose_bounds_out);
+		} else if (!dev->has_compose_out) {
+			rect_map_inside(crop, &r);
+			r.height /= factor;
+			rect_set_size_to(compose, &r);
+		} else {
+			r.height *= factor;
+			rect_set_max_size(compose, &r);
+			rect_map_inside(compose, &dev->compose_bounds_out);
+			crop->top *= factor;
+			crop->height *= factor;
+			rect_set_size_to(crop, compose);
+			rect_map_inside(crop, &r);
+			crop->top /= factor;
+			crop->height /= factor;
+		}
+	} else {
+		struct v4l2_rect r = { 0, 0, mp->width, mp->height };
+
+		rect_set_size_to(crop, &r);
+		r.height /= factor;
+		rect_set_size_to(compose, &r);
+	}
+
+	dev->fmt_out_rect.width = mp->width;
+	dev->fmt_out_rect.height = mp->height;
+	dev->bytesperline_out[0] = mp->plane_fmt[0].bytesperline;
+	if (mp->num_planes > 1)
+		dev->bytesperline_out[1] = mp->plane_fmt[1].bytesperline;
+	dev->field_out = mp->field;
+	if (vivid_is_svid_out(dev))
+		dev->tv_field_out = mp->field;
+
+set_colorspace:
+	dev->colorspace_out = mp->colorspace;
+	if (dev->loop_video) {
+		vivid_send_source_change(dev, SVID);
+		vivid_send_source_change(dev, HDMI);
+	}
+	return 0;
+}
+
+int vidioc_g_fmt_vid_out_mplane(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!dev->multiplanar)
+		return -ENOTTY;
+	return vivid_g_fmt_vid_out(file, priv, f);
+}
+
+int vidioc_try_fmt_vid_out_mplane(struct file *file, void *priv,
+			struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!dev->multiplanar)
+		return -ENOTTY;
+	return vivid_try_fmt_vid_out(file, priv, f);
+}
+
+int vidioc_s_fmt_vid_out_mplane(struct file *file, void *priv,
+			struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!dev->multiplanar)
+		return -ENOTTY;
+	return vivid_s_fmt_vid_out(file, priv, f);
+}
+
+int vidioc_g_fmt_vid_out(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (dev->multiplanar)
+		return -ENOTTY;
+	return fmt_sp2mp_func(file, priv, f, vivid_g_fmt_vid_out);
+}
+
+int vidioc_try_fmt_vid_out(struct file *file, void *priv,
+			struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (dev->multiplanar)
+		return -ENOTTY;
+	return fmt_sp2mp_func(file, priv, f, vivid_try_fmt_vid_out);
+}
+
+int vidioc_s_fmt_vid_out(struct file *file, void *priv,
+			struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (dev->multiplanar)
+		return -ENOTTY;
+	return fmt_sp2mp_func(file, priv, f, vivid_s_fmt_vid_out);
+}
+
+int vivid_vid_out_g_selection(struct file *file, void *priv,
+			      struct v4l2_selection *sel)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!dev->has_crop_out && !dev->has_compose_out)
+		return -ENOTTY;
+	if (sel->type != V4L2_BUF_TYPE_VIDEO_OUTPUT)
+		return -EINVAL;
+
+	sel->r.left = sel->r.top = 0;
+	switch (sel->target) {
+	case V4L2_SEL_TGT_CROP:
+		if (!dev->has_crop_out)
+			return -EINVAL;
+		sel->r = dev->crop_out;
+		break;
+	case V4L2_SEL_TGT_CROP_DEFAULT:
+		if (!dev->has_crop_out)
+			return -EINVAL;
+		sel->r = dev->fmt_out_rect;
+		break;
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+		if (!dev->has_compose_out)
+			return -EINVAL;
+		sel->r = vivid_max_rect;
+		break;
+	case V4L2_SEL_TGT_COMPOSE:
+		if (!dev->has_compose_out)
+			return -EINVAL;
+		sel->r = dev->compose_out;
+		break;
+	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
+	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
+		if (!dev->has_compose_out)
+			return -EINVAL;
+		sel->r = dev->sink_rect;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int vivid_vid_out_s_selection(struct file *file, void *fh, struct v4l2_selection *s)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_rect *crop = &dev->crop_out;
+	struct v4l2_rect *compose = &dev->compose_out;
+	unsigned factor = V4L2_FIELD_HAS_T_OR_B(dev->field_out) ? 2 : 1;
+	int ret;
+
+	if (!dev->has_crop_out && !dev->has_compose_out)
+		return -ENOTTY;
+	if (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT)
+		return -EINVAL;
+
+	switch (s->target) {
+	case V4L2_SEL_TGT_CROP:
+		if (!dev->has_crop_out)
+			return -EINVAL;
+		ret = vivid_vid_adjust_sel(s->flags, &s->r);
+		if (ret)
+			return ret;
+		rect_set_min_size(&s->r, &vivid_min_rect);
+		rect_set_max_size(&s->r, &dev->fmt_out_rect);
+		if (dev->has_scaler_out) {
+			struct v4l2_rect max_rect = {
+				0, 0,
+				dev->sink_rect.width * MAX_ZOOM,
+				(dev->sink_rect.height / factor) * MAX_ZOOM
+			};
+
+			rect_set_max_size(&s->r, &max_rect);
+			if (dev->has_compose_out) {
+				struct v4l2_rect min_rect = {
+					0, 0,
+					s->r.width / MAX_ZOOM,
+					(s->r.height * factor) / MAX_ZOOM
+				};
+				struct v4l2_rect max_rect = {
+					0, 0,
+					s->r.width * MAX_ZOOM,
+					(s->r.height * factor) * MAX_ZOOM
+				};
+
+				rect_set_min_size(compose, &min_rect);
+				rect_set_max_size(compose, &max_rect);
+				rect_map_inside(compose, &dev->compose_bounds_out);
+			}
+		} else if (dev->has_compose_out) {
+			s->r.top *= factor;
+			s->r.height *= factor;
+			rect_set_max_size(&s->r, &dev->sink_rect);
+			rect_set_size_to(compose, &s->r);
+			rect_map_inside(compose, &dev->compose_bounds_out);
+			s->r.top /= factor;
+			s->r.height /= factor;
+		} else {
+			rect_set_size_to(&s->r, &dev->sink_rect);
+			s->r.height /= factor;
+		}
+		rect_map_inside(&s->r, &dev->fmt_out_rect);
+		*crop = s->r;
+		break;
+	case V4L2_SEL_TGT_COMPOSE:
+		if (!dev->has_compose_out)
+			return -EINVAL;
+		ret = vivid_vid_adjust_sel(s->flags, &s->r);
+		if (ret)
+			return ret;
+		rect_set_min_size(&s->r, &vivid_min_rect);
+		rect_set_max_size(&s->r, &dev->sink_rect);
+		rect_map_inside(&s->r, &dev->compose_bounds_out);
+		s->r.top /= factor;
+		s->r.height /= factor;
+		if (dev->has_scaler_out) {
+			struct v4l2_rect fmt = dev->fmt_out_rect;
+			struct v4l2_rect max_rect = {
+				0, 0,
+				s->r.width * MAX_ZOOM,
+				s->r.height * MAX_ZOOM
+			};
+			struct v4l2_rect min_rect = {
+				0, 0,
+				s->r.width / MAX_ZOOM,
+				s->r.height / MAX_ZOOM
+			};
+
+			rect_set_min_size(&fmt, &min_rect);
+			if (!dev->has_crop_out)
+				rect_set_max_size(&fmt, &max_rect);
+			if (!rect_same_size(&dev->fmt_out_rect, &fmt) &&
+			    vb2_is_busy(&dev->vb_vid_out_q))
+				return -EBUSY;
+			if (dev->has_crop_out) {
+				rect_set_min_size(crop, &min_rect);
+				rect_set_max_size(crop, &max_rect);
+			}
+			dev->fmt_out_rect = fmt;
+		} else if (dev->has_crop_out) {
+			struct v4l2_rect fmt = dev->fmt_out_rect;
+
+			rect_set_min_size(&fmt, &s->r);
+			if (!rect_same_size(&dev->fmt_out_rect, &fmt) &&
+			    vb2_is_busy(&dev->vb_vid_out_q))
+				return -EBUSY;
+			dev->fmt_out_rect = fmt;
+			rect_set_size_to(crop, &s->r);
+			rect_map_inside(crop, &dev->fmt_out_rect);
+		} else {
+			if (!rect_same_size(&s->r, &dev->fmt_out_rect) &&
+			    vb2_is_busy(&dev->vb_vid_out_q))
+				return -EBUSY;
+			rect_set_size_to(&dev->fmt_out_rect, &s->r);
+			rect_set_size_to(crop, &s->r);
+			crop->height /= factor;
+			rect_map_inside(crop, &dev->fmt_out_rect);
+		}
+		s->r.top *= factor;
+		s->r.height *= factor;
+		if (dev->bitmap_out && (compose->width != s->r.width ||
+					compose->height != s->r.height)) {
+			kfree(dev->bitmap_out);
+			dev->bitmap_out = NULL;
+		}
+		*compose = s->r;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int vivid_vid_out_cropcap(struct file *file, void *priv,
+			      struct v4l2_cropcap *cap)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (cap->type != V4L2_BUF_TYPE_VIDEO_OUTPUT)
+		return -EINVAL;
+
+	switch (vivid_get_pixel_aspect(dev)) {
+	case TPG_PIXEL_ASPECT_NTSC:
+		cap->pixelaspect.numerator = 11;
+		cap->pixelaspect.denominator = 10;
+		break;
+	case TPG_PIXEL_ASPECT_PAL:
+		cap->pixelaspect.numerator = 54;
+		cap->pixelaspect.denominator = 59;
+		break;
+	case TPG_PIXEL_ASPECT_SQUARE:
+		cap->pixelaspect.numerator = 1;
+		cap->pixelaspect.denominator = 1;
+		break;
+	}
+	return 0;
+}
+
+int vidioc_g_fmt_vid_out_overlay(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	const struct v4l2_rect *compose = &dev->compose_out;
+	struct v4l2_window *win = &f->fmt.win;
+	unsigned clipcount = win->clipcount;
+
+	if (!dev->has_fb)
+		return -EINVAL;
+	win->w.top = dev->overlay_out_top;
+	win->w.left = dev->overlay_out_left;
+	win->w.width = compose->width;
+	win->w.height = compose->height;
+	win->clipcount = dev->clipcount_out;
+	win->field = V4L2_FIELD_ANY;
+	win->chromakey = dev->chromakey_out;
+	win->global_alpha = dev->global_alpha_out;
+	if (clipcount > dev->clipcount_out)
+		clipcount = dev->clipcount_out;
+	if (dev->bitmap_out == NULL)
+		win->bitmap = NULL;
+	else if (win->bitmap) {
+		if (copy_to_user(win->bitmap, dev->bitmap_out,
+		    ((dev->compose_out.width + 7) / 8) * dev->compose_out.height))
+			return -EFAULT;
+	}
+	if (clipcount && win->clips) {
+		if (copy_to_user(win->clips, dev->clips_out,
+				 clipcount * sizeof(dev->clips_out[0])))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+int vidioc_try_fmt_vid_out_overlay(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	const struct v4l2_rect *compose = &dev->compose_out;
+	struct v4l2_window *win = &f->fmt.win;
+	int i, j;
+
+	if (!dev->has_fb)
+		return -EINVAL;
+	win->w.left = clamp_t(int, win->w.left,
+			      -dev->display_width, dev->display_width);
+	win->w.top = clamp_t(int, win->w.top,
+			     -dev->display_height, dev->display_height);
+	win->w.width = compose->width;
+	win->w.height = compose->height;
+	/*
+	 * It makes no sense for an OSD to overlay only top or bottom fields,
+	 * so always set this to ANY.
+	 */
+	win->field = V4L2_FIELD_ANY;
+	if (win->clipcount && !win->clips)
+		win->clipcount = 0;
+	if (win->clipcount > MAX_CLIPS)
+		win->clipcount = MAX_CLIPS;
+	if (win->clipcount) {
+		if (copy_from_user(dev->try_clips_out, win->clips,
+				   win->clipcount * sizeof(dev->clips_out[0])))
+			return -EFAULT;
+		for (i = 0; i < win->clipcount; i++) {
+			struct v4l2_rect *r = &dev->try_clips_out[i].c;
+
+			r->top = clamp_t(s32, r->top, 0, dev->display_height - 1);
+			r->height = clamp_t(s32, r->height, 1, dev->display_height - r->top);
+			r->left = clamp_t(u32, r->left, 0, dev->display_width - 1);
+			r->width = clamp_t(u32, r->width, 1, dev->display_width - r->left);
+		}
+		/*
+		 * Yeah, so sue me, it's an O(n^2) algorithm. But n is a small
+		 * number and it's typically a one-time deal.
+		 */
+		for (i = 0; i < win->clipcount - 1; i++) {
+			struct v4l2_rect *r1 = &dev->try_clips_out[i].c;
+
+			for (j = i + 1; j < win->clipcount; j++) {
+				struct v4l2_rect *r2 = &dev->try_clips_out[j].c;
+
+				if (rect_overlap(r1, r2))
+					return -EINVAL;
+			}
+		}
+		if (copy_to_user(win->clips, dev->try_clips_out,
+				 win->clipcount * sizeof(dev->clips_out[0])))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+int vidioc_s_fmt_vid_out_overlay(struct file *file, void *priv,
+					struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	const struct v4l2_rect *compose = &dev->compose_out;
+	struct v4l2_window *win = &f->fmt.win;
+	int ret = vidioc_try_fmt_vid_out_overlay(file, priv, f);
+	unsigned bitmap_size = ((compose->width + 7) / 8) * compose->height;
+	unsigned clips_size = win->clipcount * sizeof(dev->clips_out[0]);
+	void *new_bitmap = NULL;
+
+	if (ret)
+		return ret;
+
+	if (win->bitmap) {
+		new_bitmap = memdup_user(win->bitmap, bitmap_size);
+
+		if (IS_ERR(new_bitmap))
+			return PTR_ERR(new_bitmap);
+	}
+
+	dev->overlay_out_top = win->w.top;
+	dev->overlay_out_left = win->w.left;
+	kfree(dev->bitmap_out);
+	dev->bitmap_out = new_bitmap;
+	dev->clipcount_out = win->clipcount;
+	if (dev->clipcount_out)
+		memcpy(dev->clips_out, dev->try_clips_out, clips_size);
+	dev->chromakey_out = win->chromakey;
+	dev->global_alpha_out = win->global_alpha;
+	return ret;
+}
+
+int vivid_vid_out_overlay(struct file *file, void *fh, unsigned i)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (i && !dev->fmt_out->can_do_overlay) {
+		dprintk(dev, 1, "unsupported output format for output overlay\n");
+		return -EINVAL;
+	}
+
+	dev->overlay_out_enabled = i;
+	return 0;
+}
+
+int vivid_vid_out_g_fbuf(struct file *file, void *fh,
+				struct v4l2_framebuffer *a)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	a->capability = V4L2_FBUF_CAP_EXTERNOVERLAY |
+			V4L2_FBUF_CAP_BITMAP_CLIPPING |
+			V4L2_FBUF_CAP_LIST_CLIPPING |
+			V4L2_FBUF_CAP_CHROMAKEY |
+			V4L2_FBUF_CAP_SRC_CHROMAKEY |
+			V4L2_FBUF_CAP_GLOBAL_ALPHA |
+			V4L2_FBUF_CAP_LOCAL_ALPHA |
+			V4L2_FBUF_CAP_LOCAL_INV_ALPHA;
+	a->flags = V4L2_FBUF_FLAG_OVERLAY | dev->fbuf_out_flags;
+	a->base = (void *)dev->video_pbase;
+	a->fmt.width = dev->display_width;
+	a->fmt.height = dev->display_height;
+	if (dev->fb_defined.green.length == 5)
+		a->fmt.pixelformat = V4L2_PIX_FMT_ARGB555;
+	else
+		a->fmt.pixelformat = V4L2_PIX_FMT_RGB565;
+	a->fmt.bytesperline = dev->display_byte_stride;
+	a->fmt.sizeimage = a->fmt.height * a->fmt.bytesperline;
+	a->fmt.field = V4L2_FIELD_NONE;
+	a->fmt.colorspace = V4L2_COLORSPACE_SRGB;
+	a->fmt.priv = 0;
+	return 0;
+}
+
+int vivid_vid_out_s_fbuf(struct file *file, void *fh,
+				const struct v4l2_framebuffer *a)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	const unsigned chroma_flags = V4L2_FBUF_FLAG_CHROMAKEY |
+				      V4L2_FBUF_FLAG_SRC_CHROMAKEY;
+	const unsigned alpha_flags = V4L2_FBUF_FLAG_GLOBAL_ALPHA |
+				     V4L2_FBUF_FLAG_LOCAL_ALPHA |
+				     V4L2_FBUF_FLAG_LOCAL_INV_ALPHA;
+
+
+	if ((a->flags & chroma_flags) == chroma_flags)
+		return -EINVAL;
+	switch (a->flags & alpha_flags) {
+	case 0:
+	case V4L2_FBUF_FLAG_GLOBAL_ALPHA:
+	case V4L2_FBUF_FLAG_LOCAL_ALPHA:
+	case V4L2_FBUF_FLAG_LOCAL_INV_ALPHA:
+		break;
+	default:
+		return -EINVAL;
+	}
+	dev->fbuf_out_flags &= ~(chroma_flags | alpha_flags);
+	dev->fbuf_out_flags = a->flags & (chroma_flags | alpha_flags);
+	return 0;
+}
+
+static const struct v4l2_audioout vivid_audio_outputs[] = {
+	{ 0, "Line-Out 1" },
+	{ 1, "Line-Out 2" },
+};
+
+int vidioc_enum_output(struct file *file, void *priv,
+				struct v4l2_output *out)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (out->index >= dev->num_outputs)
+		return -EINVAL;
+
+	out->type = V4L2_OUTPUT_TYPE_ANALOG;
+	switch (dev->output_type[out->index]) {
+	case SVID:
+		snprintf(out->name, sizeof(out->name), "S-Video %u",
+				dev->output_name_counter[out->index]);
+		out->std = V4L2_STD_ALL;
+		if (dev->has_audio_outputs)
+			out->audioset = (1 << ARRAY_SIZE(vivid_audio_outputs)) - 1;
+		out->capabilities = V4L2_OUT_CAP_STD;
+		break;
+	case HDMI:
+		snprintf(out->name, sizeof(out->name), "HDMI %u",
+				dev->output_name_counter[out->index]);
+		out->capabilities = V4L2_OUT_CAP_DV_TIMINGS;
+		break;
+	}
+	return 0;
+}
+
+int vidioc_g_output(struct file *file, void *priv, unsigned *o)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	*o = dev->output;
+	return 0;
+}
+
+int vidioc_s_output(struct file *file, void *priv, unsigned o)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (o >= dev->num_outputs)
+		return -EINVAL;
+
+	if (o == dev->output)
+		return 0;
+
+	if (vb2_is_busy(&dev->vb_vid_out_q) || vb2_is_busy(&dev->vb_vbi_out_q))
+		return -EBUSY;
+
+	dev->output = o;
+	dev->tv_audio_output = 0;
+	if (dev->output_type[o] == SVID)
+		dev->vid_out_dev.tvnorms = V4L2_STD_ALL;
+	else
+		dev->vid_out_dev.tvnorms = 0;
+
+	dev->vbi_out_dev.tvnorms = dev->vid_out_dev.tvnorms;
+	vivid_update_format_out(dev);
+	return 0;
+}
+
+int vidioc_enumaudout(struct file *file, void *fh, struct v4l2_audioout *vout)
+{
+	if (vout->index >= ARRAY_SIZE(vivid_audio_outputs))
+		return -EINVAL;
+	*vout = vivid_audio_outputs[vout->index];
+	return 0;
+}
+
+int vidioc_g_audout(struct file *file, void *fh, struct v4l2_audioout *vout)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_svid_out(dev))
+		return -EINVAL;
+	*vout = vivid_audio_outputs[dev->tv_audio_output];
+	return 0;
+}
+
+int vidioc_s_audout(struct file *file, void *fh, const struct v4l2_audioout *vout)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_svid_out(dev))
+		return -EINVAL;
+	if (vout->index >= ARRAY_SIZE(vivid_audio_outputs))
+		return -EINVAL;
+	dev->tv_audio_output = vout->index;
+	return 0;
+}
+
+int vivid_vid_out_s_std(struct file *file, void *priv, v4l2_std_id id)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_svid_out(dev))
+		return -ENODATA;
+	if (dev->std_out == id)
+		return 0;
+	if (vb2_is_busy(&dev->vb_vid_out_q) || vb2_is_busy(&dev->vb_vbi_out_q))
+		return -EBUSY;
+	dev->std_out = id;
+	vivid_update_format_out(dev);
+	return 0;
+}
+
+int vivid_vid_out_s_dv_timings(struct file *file, void *_fh,
+				    struct v4l2_dv_timings *timings)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (!vivid_is_hdmi_out(dev))
+		return -ENODATA;
+	if (vb2_is_busy(&dev->vb_vid_out_q))
+		return -EBUSY;
+	if (!v4l2_find_dv_timings_cap(timings, &vivid_dv_timings_cap,
+				0, NULL, NULL))
+		return -EINVAL;
+	if (v4l2_match_dv_timings(timings, &dev->dv_timings_out, 0))
+		return 0;
+	dev->dv_timings_out = *timings;
+	vivid_update_format_out(dev);
+	return 0;
+}
+
+int vivid_vid_out_g_parm(struct file *file, void *priv,
+			  struct v4l2_streamparm *parm)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (parm->type != (dev->multiplanar ?
+			   V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE :
+			   V4L2_BUF_TYPE_VIDEO_OUTPUT))
+		return -EINVAL;
+
+	parm->parm.output.capability   = V4L2_CAP_TIMEPERFRAME;
+	parm->parm.output.timeperframe = dev->timeperframe_vid_out;
+	parm->parm.output.writebuffers  = 1;
+return 0;
+}
+
+int vidioc_subscribe_event(struct v4l2_fh *fh,
+			const struct v4l2_event_subscription *sub)
+{
+	switch (sub->type) {
+	case V4L2_EVENT_CTRL:
+		return v4l2_ctrl_subscribe_event(fh, sub);
+	case V4L2_EVENT_SOURCE_CHANGE:
+		if (fh->vdev->vfl_dir == VFL_DIR_RX)
+			return v4l2_src_change_event_subscribe(fh, sub);
+		break;
+	default:
+		break;
+	}
+	return -EINVAL;
+}
diff --git a/drivers/media/platform/vivid/vivid-vid-out.h b/drivers/media/platform/vivid/vivid-vid-out.h
new file mode 100644
index 000000000000..dfa84db184ed
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-vid-out.h
@@ -0,0 +1,56 @@
+/*
+ * vivid-vid-out.h - video output support functions.
+ *
+ * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _VIVID_VID_OUT_H_
+#define _VIVID_VID_OUT_H_
+
+extern const struct vb2_ops vivid_vid_out_qops;
+
+void vivid_update_format_out(struct vivid_dev *dev);
+
+int vivid_g_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f);
+int vivid_try_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f);
+int vivid_s_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_g_fmt_vid_out_mplane(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_try_fmt_vid_out_mplane(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_s_fmt_vid_out_mplane(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_g_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_try_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_s_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f);
+int vivid_vid_out_g_selection(struct file *file, void *priv, struct v4l2_selection *sel);
+int vivid_vid_out_s_selection(struct file *file, void *fh, struct v4l2_selection *s);
+int vivid_vid_out_cropcap(struct file *file, void *fh, struct v4l2_cropcap *cap);
+int vidioc_enum_fmt_vid_out_overlay(struct file *file, void  *priv, struct v4l2_fmtdesc *f);
+int vidioc_g_fmt_vid_out_overlay(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_try_fmt_vid_out_overlay(struct file *file, void *priv, struct v4l2_format *f);
+int vidioc_s_fmt_vid_out_overlay(struct file *file, void *priv, struct v4l2_format *f);
+int vivid_vid_out_overlay(struct file *file, void *fh, unsigned i);
+int vivid_vid_out_g_fbuf(struct file *file, void *fh, struct v4l2_framebuffer *a);
+int vivid_vid_out_s_fbuf(struct file *file, void *fh, const struct v4l2_framebuffer *a);
+int vidioc_enum_output(struct file *file, void *priv, struct v4l2_output *out);
+int vidioc_g_output(struct file *file, void *priv, unsigned *i);
+int vidioc_s_output(struct file *file, void *priv, unsigned i);
+int vidioc_enumaudout(struct file *file, void *fh, struct v4l2_audioout *vout);
+int vidioc_g_audout(struct file *file, void *fh, struct v4l2_audioout *vout);
+int vidioc_s_audout(struct file *file, void *fh, const struct v4l2_audioout *vout);
+int vivid_vid_out_s_std(struct file *file, void *priv, v4l2_std_id id);
+int vivid_vid_out_s_dv_timings(struct file *file, void *_fh, struct v4l2_dv_timings *timings);
+int vivid_vid_out_g_parm(struct file *file, void *priv, struct v4l2_streamparm *parm);
+
+#endif
diff --git a/drivers/media/radio/radio-gemtek.c b/drivers/media/radio/radio-gemtek.c
index 235c0e349820..cff1eb144a5c 100644
--- a/drivers/media/radio/radio-gemtek.c
+++ b/drivers/media/radio/radio-gemtek.c
@@ -332,7 +332,7 @@ static int __init gemtek_init(void)
 
 static void __exit gemtek_exit(void)
 {
-	hardmute = 1;	/* Turn off PLL */
+	hardmute = true;	/* Turn off PLL */
 #ifdef CONFIG_PNP
 	pnp_unregister_driver(&gemtek_driver.pnp_driver);
 #endif
diff --git a/drivers/media/radio/radio-sf16fmi.c b/drivers/media/radio/radio-sf16fmi.c
index d7ce8fe6b5ae..28a89466cddc 100644
--- a/drivers/media/radio/radio-sf16fmi.c
+++ b/drivers/media/radio/radio-sf16fmi.c
@@ -56,7 +56,7 @@ struct fmi
 
 static struct fmi fmi_card;
 static struct pnp_dev *dev;
-bool pnp_attached;
+static bool pnp_attached;
 
 #define RSF16_MINFREQ (87U * 16000)
 #define RSF16_MAXFREQ (108U * 16000)
@@ -285,7 +285,7 @@ static int __init fmi_init(void)
 				io = isapnp_fmi_probe();
 				if (io < 0)
 					continue;
-				pnp_attached = 1;
+				pnp_attached = true;
 			}
 			if (!request_region(io, 2, "radio-sf16fmi")) {
 				if (pnp_attached)
@@ -349,7 +349,7 @@ static int __init fmi_init(void)
 	mutex_init(&fmi->lock);
 
 	/* mute card and set default frequency */
-	fmi->mute = 1;
+	fmi->mute = true;
 	fmi->curfreq = RSF16_MINFREQ;
 	fmi_set_freq(fmi);
 
diff --git a/drivers/media/radio/radio-sf16fmr2.c b/drivers/media/radio/radio-sf16fmr2.c
index 93d864eb8306..b8d61cbc18cb 100644
--- a/drivers/media/radio/radio-sf16fmr2.c
+++ b/drivers/media/radio/radio-sf16fmr2.c
@@ -305,7 +305,7 @@ static void fmr2_pnp_remove(struct pnp_dev *pdev)
 	pnp_set_drvdata(pdev, NULL);
 }
 
-struct isa_driver fmr2_isa_driver = {
+static struct isa_driver fmr2_isa_driver = {
 	.match		= fmr2_isa_match,
 	.remove		= fmr2_isa_remove,
 	.driver		= {
@@ -313,7 +313,7 @@ struct isa_driver fmr2_isa_driver = {
 	},
 };
 
-struct pnp_driver fmr2_pnp_driver = {
+static struct pnp_driver fmr2_pnp_driver = {
 	.name		= "radio-sf16fmr2",
 	.id_table	= fmr2_pnp_ids,
 	.probe		= fmr2_pnp_probe,
diff --git a/drivers/media/radio/radio-tea5764.c b/drivers/media/radio/radio-tea5764.c
index 925049654c5b..cc3990111411 100644
--- a/drivers/media/radio/radio-tea5764.c
+++ b/drivers/media/radio/radio-tea5764.c
@@ -124,11 +124,11 @@ struct tea5764_regs {
 
 struct tea5764_write_regs {
 	u8 intreg;				/* INTMSK */
-	u16 frqset;				/* FRQSETMSB & FRQSETLSB */
-	u16 tnctrl;				/* TNCTRL1 & TNCTRL2 */
-	u16 testreg;				/* TESTBITS & TESTMODE */
-	u16 rdsctrl;				/* RDSCTRL1 & RDSCTRL2 */
-	u16 rdsbbl;				/* PAUSEDET & RDSBBL */
+	__be16 frqset;				/* FRQSETMSB & FRQSETLSB */
+	__be16 tnctrl;				/* TNCTRL1 & TNCTRL2 */
+	__be16 testreg;				/* TESTBITS & TESTMODE */
+	__be16 rdsctrl;				/* RDSCTRL1 & RDSCTRL2 */
+	__be16 rdsbbl;				/* PAUSEDET & RDSBBL */
 } __attribute__ ((packed));
 
 #ifdef CONFIG_RADIO_TEA5764_XTAL
@@ -165,7 +165,7 @@ static int tea5764_i2c_read(struct tea5764_device *radio)
 	if (i2c_transfer(radio->i2c_client->adapter, msgs, 1) != 1)
 		return -EIO;
 	for (i = 0; i < sizeof(struct tea5764_regs) / sizeof(u16); i++)
-		p[i] = __be16_to_cpu(p[i]);
+		p[i] = __be16_to_cpu((__force __be16)p[i]);
 
 	return 0;
 }
diff --git a/drivers/media/radio/si470x/radio-si470x-common.c b/drivers/media/radio/si470x/radio-si470x-common.c
index 0e750aef656a..909c3f92d839 100644
--- a/drivers/media/radio/si470x/radio-si470x-common.c
+++ b/drivers/media/radio/si470x/radio-si470x-common.c
@@ -208,7 +208,7 @@ static int si470x_set_band(struct si470x_device *radio, int band)
 static int si470x_set_chan(struct si470x_device *radio, unsigned short chan)
 {
 	int retval;
-	bool timed_out = 0;
+	bool timed_out = false;
 
 	/* start tuning */
 	radio->registers[CHANNEL] &= ~CHANNEL_CHAN;
@@ -300,7 +300,7 @@ static int si470x_set_seek(struct si470x_device *radio,
 {
 	int band, retval;
 	unsigned int freq;
-	bool timed_out = 0;
+	bool timed_out = false;
 
 	/* set band */
 	if (seek->rangelow || seek->rangehigh) {
diff --git a/drivers/media/radio/si470x/radio-si470x-usb.c b/drivers/media/radio/si470x/radio-si470x-usb.c
index 494fac061306..57f0bc3b60e7 100644
--- a/drivers/media/radio/si470x/radio-si470x-usb.c
+++ b/drivers/media/radio/si470x/radio-si470x-usb.c
@@ -607,9 +607,7 @@ static int si470x_usb_driver_probe(struct usb_interface *intf,
 	/* Set up interrupt endpoint information. */
 	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
 		endpoint = &iface_desc->endpoint[i].desc;
-		if (((endpoint->bEndpointAddress & USB_ENDPOINT_DIR_MASK) ==
-		 USB_DIR_IN) && ((endpoint->bmAttributes &
-		 USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_INT))
+		if (usb_endpoint_is_int_in(endpoint))
 			radio->int_in_endpoint = endpoint;
 	}
 	if (!radio->int_in_endpoint) {
diff --git a/drivers/media/radio/wl128x/fmdrv_common.c b/drivers/media/radio/wl128x/fmdrv_common.c
index 4b2e9e8298e1..6f28f6e02ea5 100644
--- a/drivers/media/radio/wl128x/fmdrv_common.c
+++ b/drivers/media/radio/wl128x/fmdrv_common.c
@@ -440,7 +440,7 @@ static int fm_send_cmd(struct fmdev *fmdev, u8 fm_op, u16 type,	void *payload,
 		 * command with u16 payload - convert to be16
 		 */
 		if (payload != NULL)
-			*(u16 *)payload = cpu_to_be16(*(u16 *)payload);
+			*(__be16 *)payload = cpu_to_be16(*(u16 *)payload);
 
 	} else if (payload != NULL) {
 		fm_cb(skb)->fm_op = *((u8 *)payload + 2);
@@ -595,7 +595,7 @@ static void fm_irq_handle_flag_getcmd_resp(struct fmdev *fmdev)
 	skb_pull(skb, sizeof(struct fm_event_msg_hdr));
 	memcpy(&fmdev->irq_info.flag, skb->data, fm_evt_hdr->dlen);
 
-	fmdev->irq_info.flag = be16_to_cpu(fmdev->irq_info.flag);
+	fmdev->irq_info.flag = be16_to_cpu((__force __be16)fmdev->irq_info.flag);
 	fmdbg("irq: flag register(0x%x)\n", fmdev->irq_info.flag);
 
 	/* Continue next function in interrupt handler table */
@@ -764,7 +764,7 @@ static void fm_irq_handle_rdsdata_getcmd_resp(struct fmdev *fmdev)
 			 * Extract PI code and store in local cache.
 			 * We need this during AF switch processing.
 			 */
-			cur_picode = be16_to_cpu(rds_fmt.data.groupgeneral.pidata);
+			cur_picode = be16_to_cpu((__force __be16)rds_fmt.data.groupgeneral.pidata);
 			if (fmdev->rx.stat_info.picode != cur_picode)
 				fmdev->rx.stat_info.picode = cur_picode;
 
@@ -989,7 +989,7 @@ static void fm_irq_afjump_rd_freq_resp(struct fmdev *fmdev)
 	/* Skip header info and copy only response data */
 	skb_pull(skb, sizeof(struct fm_event_msg_hdr));
 	memcpy(&read_freq, skb->data, sizeof(read_freq));
-	read_freq = be16_to_cpu(read_freq);
+	read_freq = be16_to_cpu((__force __be16)read_freq);
 	curr_freq = fmdev->rx.region.bot_freq + ((u32)read_freq * FM_FREQ_MUL);
 
 	jumped_freq = fmdev->rx.stat_info.af_cache[fmdev->rx.afjump_idx];
@@ -1317,7 +1317,8 @@ static int load_default_rx_configuration(struct fmdev *fmdev)
 /* Does FM power on sequence */
 static int fm_power_up(struct fmdev *fmdev, u8 mode)
 {
-	u16 payload, asic_id, asic_ver;
+	u16 payload;
+	__be16 asic_id, asic_ver;
 	int resp_len, ret;
 	u8 fw_name[50];
 
diff --git a/drivers/media/radio/wl128x/fmdrv_rx.c b/drivers/media/radio/wl128x/fmdrv_rx.c
index ebf09a3927de..09632cb26cb6 100644
--- a/drivers/media/radio/wl128x/fmdrv_rx.c
+++ b/drivers/media/radio/wl128x/fmdrv_rx.c
@@ -116,7 +116,7 @@ int fm_rx_set_freq(struct fmdev *fmdev, u32 freq)
 	if (ret < 0)
 		goto exit;
 
-	curr_frq = be16_to_cpu(curr_frq);
+	curr_frq = be16_to_cpu((__force __be16)curr_frq);
 	curr_frq_in_khz = (fmdev->rx.region.bot_freq + ((u32)curr_frq * FM_FREQ_MUL));
 
 	if (curr_frq_in_khz != freq) {
@@ -189,7 +189,7 @@ int fm_rx_seek(struct fmdev *fmdev, u32 seek_upward,
 	if (ret < 0)
 		return ret;
 
-	curr_frq = be16_to_cpu(curr_frq);
+	curr_frq = be16_to_cpu((__force __be16)curr_frq);
 	last_frq = (fmdev->rx.region.top_freq - fmdev->rx.region.bot_freq) / FM_FREQ_MUL;
 
 	/* Check the offset in order to be aligned to the channel spacing*/
@@ -285,7 +285,7 @@ again:
 		if (ret < 0)
 			return ret;
 
-		curr_frq = be16_to_cpu(curr_frq);
+		curr_frq = be16_to_cpu((__force __be16)curr_frq);
 		fmdev->rx.freq = (fmdev->rx.region.bot_freq +
 				((u32)curr_frq * FM_FREQ_MUL));
 
@@ -517,7 +517,7 @@ int fm_rx_set_rfdepend_softmute(struct fmdev *fmdev, u8 rfdepend_mute)
 /* Returns the signal strength level of current channel */
 int fm_rx_get_rssi_level(struct fmdev *fmdev, u16 *rssilvl)
 {
-	u16 curr_rssi_lel;
+	__be16 curr_rssi_lel;
 	u32 resp_len;
 	int ret;
 
@@ -608,7 +608,7 @@ int fm_rx_set_stereo_mono(struct fmdev *fmdev, u16 mode)
 /* Gets current RX stereo/mono mode */
 int fm_rx_get_stereo_mono(struct fmdev *fmdev, u16 *mode)
 {
-	u16 curr_mode;
+	__be16 curr_mode;
 	u32 resp_len;
 	int ret;
 
diff --git a/drivers/media/radio/wl128x/fmdrv_tx.c b/drivers/media/radio/wl128x/fmdrv_tx.c
index 6ea33e09d63b..839970b0f313 100644
--- a/drivers/media/radio/wl128x/fmdrv_tx.c
+++ b/drivers/media/radio/wl128x/fmdrv_tx.c
@@ -374,7 +374,7 @@ int fm_tx_get_tune_cap_val(struct fmdev *fmdev)
 	if (ret < 0)
 		return ret;
 
-	curr_val = be16_to_cpu(curr_val);
+	curr_val = be16_to_cpu((__force __be16)curr_val);
 
 	return curr_val;
 }
diff --git a/drivers/media/rc/Kconfig b/drivers/media/rc/Kconfig
index 5e626af8e313..8ce08107a69d 100644
--- a/drivers/media/rc/Kconfig
+++ b/drivers/media/rc/Kconfig
@@ -164,6 +164,16 @@ config IR_ENE
 	   To compile this driver as a module, choose M here: the
 	   module will be called ene_ir.
 
+config IR_HIX5HD2
+	tristate "Hisilicon hix5hd2 IR remote control"
+	depends on RC_CORE
+	help
+	 Say Y here if you want to use hisilicon hix5hd2 remote control.
+	 To compile this driver as a module, choose M here: the module will be
+	 called ir-hix5hd2.
+
+	 If you're not sure, select N here
+
 config IR_IMON
 	tristate "SoundGraph iMON Receiver and Display"
 	depends on USB_ARCH_HAS_HCD
@@ -333,7 +343,8 @@ config IR_GPIO_CIR
 
 config RC_ST
 	tristate "ST remote control receiver"
-	depends on ARCH_STI && RC_CORE
+	depends on RC_CORE
+	depends on ARCH_STI || COMPILE_TEST
 	help
 	 Say Y here if you want support for ST remote control driver
 	 which allows both IR and UHF RX.
@@ -344,7 +355,7 @@ config RC_ST
 config IR_SUNXI
     tristate "SUNXI IR remote control"
     depends on RC_CORE
-    depends on ARCH_SUNXI
+    depends on ARCH_SUNXI || COMPILE_TEST
     ---help---
       Say Y if you want to use sunXi internal IR Controller
 
diff --git a/drivers/media/rc/Makefile b/drivers/media/rc/Makefile
index 9f9843a1af5f..0989f940e9cf 100644
--- a/drivers/media/rc/Makefile
+++ b/drivers/media/rc/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_IR_XMP_DECODER) += ir-xmp-decoder.o
 
 # stand-alone IR receivers/transmitters
 obj-$(CONFIG_RC_ATI_REMOTE) += ati_remote.o
+obj-$(CONFIG_IR_HIX5HD2) += ir-hix5hd2.o
 obj-$(CONFIG_IR_IMON) += imon.o
 obj-$(CONFIG_IR_ITE_CIR) += ite-cir.o
 obj-$(CONFIG_IR_MCEUSB) += mceusb.o
diff --git a/drivers/media/rc/ene_ir.c b/drivers/media/rc/ene_ir.c
index d16d9b496b92..e80f2c6c5f1a 100644
--- a/drivers/media/rc/ene_ir.c
+++ b/drivers/media/rc/ene_ir.c
@@ -979,7 +979,7 @@ static int ene_transmit(struct rc_dev *rdev, unsigned *buf, unsigned n)
 	dev->tx_reg = 0;
 	dev->tx_done = 0;
 	dev->tx_sample = 0;
-	dev->tx_sample_pulse = 0;
+	dev->tx_sample_pulse = false;
 
 	dbg("TX: %d samples", dev->tx_len);
 
diff --git a/drivers/media/rc/fintek-cir.c b/drivers/media/rc/fintek-cir.c
index f0a1f7d31ee6..b5167573240e 100644
--- a/drivers/media/rc/fintek-cir.c
+++ b/drivers/media/rc/fintek-cir.c
@@ -148,7 +148,6 @@ static int fintek_hw_detect(struct fintek_dev *fintek)
 	u8 vendor_major, vendor_minor;
 	u8 portsel, ir_class;
 	u16 vendor, chip;
-	int ret = 0;
 
 	fintek_config_mode_enable(fintek);
 
@@ -208,7 +207,7 @@ static int fintek_hw_detect(struct fintek_dev *fintek)
 
 	spin_unlock_irqrestore(&fintek->fintek_lock, flags);
 
-	return ret;
+	return 0;
 }
 
 static void fintek_cir_ldev_init(struct fintek_dev *fintek)
@@ -644,7 +643,6 @@ static int fintek_suspend(struct pnp_dev *pdev, pm_message_t state)
 
 static int fintek_resume(struct pnp_dev *pdev)
 {
-	int ret = 0;
 	struct fintek_dev *fintek = pnp_get_drvdata(pdev);
 
 	fit_dbg("%s called", __func__);
@@ -661,7 +659,7 @@ static int fintek_resume(struct pnp_dev *pdev)
 
 	fintek_cir_regs_init(fintek);
 
-	return ret;
+	return 0;
 }
 
 static void fintek_shutdown(struct pnp_dev *pdev)
diff --git a/drivers/media/rc/img-ir/img-ir-hw.c b/drivers/media/rc/img-ir/img-ir-hw.c
index bfb282a714e8..ec49f94425fc 100644
--- a/drivers/media/rc/img-ir/img-ir-hw.c
+++ b/drivers/media/rc/img-ir/img-ir-hw.c
@@ -25,12 +25,6 @@
 /* Decoders lock (only modified to preprocess them) */
 static DEFINE_SPINLOCK(img_ir_decoders_lock);
 
-extern struct img_ir_decoder img_ir_nec;
-extern struct img_ir_decoder img_ir_jvc;
-extern struct img_ir_decoder img_ir_sony;
-extern struct img_ir_decoder img_ir_sharp;
-extern struct img_ir_decoder img_ir_sanyo;
-
 static bool img_ir_decoders_preprocessed;
 static struct img_ir_decoder *img_ir_decoders[] = {
 #ifdef CONFIG_IR_IMG_NEC
diff --git a/drivers/media/rc/img-ir/img-ir-hw.h b/drivers/media/rc/img-ir/img-ir-hw.h
index 3e40ce87b898..8fcc16c32c5b 100644
--- a/drivers/media/rc/img-ir/img-ir-hw.h
+++ b/drivers/media/rc/img-ir/img-ir-hw.h
@@ -168,6 +168,12 @@ struct img_ir_decoder {
 		      struct img_ir_filter *out, u64 protocols);
 };
 
+extern struct img_ir_decoder img_ir_nec;
+extern struct img_ir_decoder img_ir_jvc;
+extern struct img_ir_decoder img_ir_sony;
+extern struct img_ir_decoder img_ir_sharp;
+extern struct img_ir_decoder img_ir_sanyo;
+
 /**
  * struct img_ir_reg_timings - Reg values for decoder timings at clock rate.
  * @ctrl:	Processed control register value.
diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c
index 7115e68ba697..b8837dd39bb2 100644
--- a/drivers/media/rc/imon.c
+++ b/drivers/media/rc/imon.c
@@ -87,6 +87,18 @@ static ssize_t lcd_write(struct file *file, const char __user *buf,
 
 /*** G L O B A L S ***/
 
+struct imon_panel_key_table {
+	u64 hw_code;
+	u32 keycode;
+};
+
+struct imon_usb_dev_descr {
+	__u16 flags;
+#define IMON_NO_FLAGS 0
+#define IMON_NEED_20MS_PKT_DELAY 1
+	struct imon_panel_key_table key_table[];
+};
+
 struct imon_context {
 	struct device *dev;
 	/* Newer devices have two interfaces */
@@ -150,6 +162,8 @@ struct imon_context {
 	struct timer_list ttimer;	/* touch screen timer */
 	int touch_x;			/* x coordinate on touchscreen */
 	int touch_y;			/* y coordinate on touchscreen */
+	struct imon_usb_dev_descr *dev_descr; /* device description with key
+						 table for front panels */
 };
 
 #define TOUCH_TIMEOUT	(HZ/30)
@@ -186,8 +200,132 @@ enum {
 	IMON_KEY_PANEL	= 2,
 };
 
-enum {
-	IMON_NEED_20MS_PKT_DELAY = 1
+static struct usb_class_driver imon_vfd_class = {
+	.name		= DEVICE_NAME,
+	.fops		= &vfd_fops,
+	.minor_base	= DISPLAY_MINOR_BASE,
+};
+
+static struct usb_class_driver imon_lcd_class = {
+	.name		= DEVICE_NAME,
+	.fops		= &lcd_fops,
+	.minor_base	= DISPLAY_MINOR_BASE,
+};
+
+/* imon receiver front panel/knob key table */
+static const struct imon_usb_dev_descr imon_default_table = {
+	.flags = IMON_NO_FLAGS,
+	.key_table = {
+		{ 0x000000000f00ffeell, KEY_MEDIA }, /* Go */
+		{ 0x000000001200ffeell, KEY_UP },
+		{ 0x000000001300ffeell, KEY_DOWN },
+		{ 0x000000001400ffeell, KEY_LEFT },
+		{ 0x000000001500ffeell, KEY_RIGHT },
+		{ 0x000000001600ffeell, KEY_ENTER },
+		{ 0x000000001700ffeell, KEY_ESC },
+		{ 0x000000001f00ffeell, KEY_AUDIO },
+		{ 0x000000002000ffeell, KEY_VIDEO },
+		{ 0x000000002100ffeell, KEY_CAMERA },
+		{ 0x000000002700ffeell, KEY_DVD },
+		{ 0x000000002300ffeell, KEY_TV },
+		{ 0x000000002b00ffeell, KEY_EXIT },
+		{ 0x000000002c00ffeell, KEY_SELECT },
+		{ 0x000000002d00ffeell, KEY_MENU },
+		{ 0x000000000500ffeell, KEY_PREVIOUS },
+		{ 0x000000000700ffeell, KEY_REWIND },
+		{ 0x000000000400ffeell, KEY_STOP },
+		{ 0x000000003c00ffeell, KEY_PLAYPAUSE },
+		{ 0x000000000800ffeell, KEY_FASTFORWARD },
+		{ 0x000000000600ffeell, KEY_NEXT },
+		{ 0x000000010000ffeell, KEY_RIGHT },
+		{ 0x000001000000ffeell, KEY_LEFT },
+		{ 0x000000003d00ffeell, KEY_SELECT },
+		{ 0x000100000000ffeell, KEY_VOLUMEUP },
+		{ 0x010000000000ffeell, KEY_VOLUMEDOWN },
+		{ 0x000000000100ffeell, KEY_MUTE },
+		/* 0xffdc iMON MCE VFD */
+		{ 0x00010000ffffffeell, KEY_VOLUMEUP },
+		{ 0x01000000ffffffeell, KEY_VOLUMEDOWN },
+		{ 0x00000001ffffffeell, KEY_MUTE },
+		{ 0x0000000fffffffeell, KEY_MEDIA },
+		{ 0x00000012ffffffeell, KEY_UP },
+		{ 0x00000013ffffffeell, KEY_DOWN },
+		{ 0x00000014ffffffeell, KEY_LEFT },
+		{ 0x00000015ffffffeell, KEY_RIGHT },
+		{ 0x00000016ffffffeell, KEY_ENTER },
+		{ 0x00000017ffffffeell, KEY_ESC },
+		/* iMON Knob values */
+		{ 0x000100ffffffffeell, KEY_VOLUMEUP },
+		{ 0x010000ffffffffeell, KEY_VOLUMEDOWN },
+		{ 0x000008ffffffffeell, KEY_MUTE },
+		{ 0, KEY_RESERVED },
+	}
+};
+
+static const struct imon_usb_dev_descr imon_OEM_VFD = {
+	.flags = IMON_NEED_20MS_PKT_DELAY,
+	.key_table = {
+		{ 0x000000000f00ffeell, KEY_MEDIA }, /* Go */
+		{ 0x000000001200ffeell, KEY_UP },
+		{ 0x000000001300ffeell, KEY_DOWN },
+		{ 0x000000001400ffeell, KEY_LEFT },
+		{ 0x000000001500ffeell, KEY_RIGHT },
+		{ 0x000000001600ffeell, KEY_ENTER },
+		{ 0x000000001700ffeell, KEY_ESC },
+		{ 0x000000001f00ffeell, KEY_AUDIO },
+		{ 0x000000002b00ffeell, KEY_EXIT },
+		{ 0x000000002c00ffeell, KEY_SELECT },
+		{ 0x000000002d00ffeell, KEY_MENU },
+		{ 0x000000000500ffeell, KEY_PREVIOUS },
+		{ 0x000000000700ffeell, KEY_REWIND },
+		{ 0x000000000400ffeell, KEY_STOP },
+		{ 0x000000003c00ffeell, KEY_PLAYPAUSE },
+		{ 0x000000000800ffeell, KEY_FASTFORWARD },
+		{ 0x000000000600ffeell, KEY_NEXT },
+		{ 0x000000010000ffeell, KEY_RIGHT },
+		{ 0x000001000000ffeell, KEY_LEFT },
+		{ 0x000000003d00ffeell, KEY_SELECT },
+		{ 0x000100000000ffeell, KEY_VOLUMEUP },
+		{ 0x010000000000ffeell, KEY_VOLUMEDOWN },
+		{ 0x000000000100ffeell, KEY_MUTE },
+		/* 0xffdc iMON MCE VFD */
+		{ 0x00010000ffffffeell, KEY_VOLUMEUP },
+		{ 0x01000000ffffffeell, KEY_VOLUMEDOWN },
+		{ 0x00000001ffffffeell, KEY_MUTE },
+		{ 0x0000000fffffffeell, KEY_MEDIA },
+		{ 0x00000012ffffffeell, KEY_UP },
+		{ 0x00000013ffffffeell, KEY_DOWN },
+		{ 0x00000014ffffffeell, KEY_LEFT },
+		{ 0x00000015ffffffeell, KEY_RIGHT },
+		{ 0x00000016ffffffeell, KEY_ENTER },
+		{ 0x00000017ffffffeell, KEY_ESC },
+		/* iMON Knob values */
+		{ 0x000100ffffffffeell, KEY_VOLUMEUP },
+		{ 0x010000ffffffffeell, KEY_VOLUMEDOWN },
+		{ 0x000008ffffffffeell, KEY_MUTE },
+		{ 0, KEY_RESERVED },
+	}
+};
+
+/* imon receiver front panel/knob key table for DH102*/
+static const struct imon_usb_dev_descr imon_DH102 = {
+	.flags = IMON_NO_FLAGS,
+	.key_table = {
+		{ 0x000100000000ffeell, KEY_VOLUMEUP },
+		{ 0x010000000000ffeell, KEY_VOLUMEDOWN },
+		{ 0x000000010000ffeell, KEY_MUTE },
+		{ 0x0000000f0000ffeell, KEY_MEDIA },
+		{ 0x000000120000ffeell, KEY_UP },
+		{ 0x000000130000ffeell, KEY_DOWN },
+		{ 0x000000140000ffeell, KEY_LEFT },
+		{ 0x000000150000ffeell, KEY_RIGHT },
+		{ 0x000000160000ffeell, KEY_ENTER },
+		{ 0x000000170000ffeell, KEY_ESC },
+		{ 0x0000002b0000ffeell, KEY_EXIT },
+		{ 0x0000002c0000ffeell, KEY_SELECT },
+		{ 0x0000002d0000ffeell, KEY_MENU },
+		{ 0, KEY_RESERVED }
+	}
 };
 
 /*
@@ -208,7 +346,8 @@ static struct usb_device_id imon_usb_id_table[] = {
 	 * SoundGraph iMON PAD (IR & LCD)
 	 * SoundGraph iMON Knob (IR only)
 	 */
-	{ USB_DEVICE(0x15c2, 0xffdc) },
+	{ USB_DEVICE(0x15c2, 0xffdc),
+	  .driver_info = (unsigned long)&imon_default_table },
 
 	/*
 	 * Newer devices, all driven by the latest iMON Windows driver, full
@@ -216,43 +355,62 @@ static struct usb_device_id imon_usb_id_table[] = {
 	 * Need user input to fill in details on unknown devices.
 	 */
 	/* SoundGraph iMON OEM Touch LCD (IR & 7" VGA LCD) */
-	{ USB_DEVICE(0x15c2, 0x0034) },
+	{ USB_DEVICE(0x15c2, 0x0034),
+	  .driver_info = (unsigned long)&imon_DH102 },
 	/* SoundGraph iMON OEM Touch LCD (IR & 4.3" VGA LCD) */
-	{ USB_DEVICE(0x15c2, 0x0035) },
+	{ USB_DEVICE(0x15c2, 0x0035),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* SoundGraph iMON OEM VFD (IR & VFD) */
-	{ USB_DEVICE(0x15c2, 0x0036), .driver_info = IMON_NEED_20MS_PKT_DELAY },
+	{ USB_DEVICE(0x15c2, 0x0036),
+	  .driver_info = (unsigned long)&imon_OEM_VFD },
 	/* device specifics unknown */
-	{ USB_DEVICE(0x15c2, 0x0037) },
+	{ USB_DEVICE(0x15c2, 0x0037),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* SoundGraph iMON OEM LCD (IR & LCD) */
-	{ USB_DEVICE(0x15c2, 0x0038) },
+	{ USB_DEVICE(0x15c2, 0x0038),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* SoundGraph iMON UltraBay (IR & LCD) */
-	{ USB_DEVICE(0x15c2, 0x0039) },
+	{ USB_DEVICE(0x15c2, 0x0039),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* device specifics unknown */
-	{ USB_DEVICE(0x15c2, 0x003a) },
+	{ USB_DEVICE(0x15c2, 0x003a),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* device specifics unknown */
-	{ USB_DEVICE(0x15c2, 0x003b) },
+	{ USB_DEVICE(0x15c2, 0x003b),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* SoundGraph iMON OEM Inside (IR only) */
-	{ USB_DEVICE(0x15c2, 0x003c) },
+	{ USB_DEVICE(0x15c2, 0x003c),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* device specifics unknown */
-	{ USB_DEVICE(0x15c2, 0x003d) },
+	{ USB_DEVICE(0x15c2, 0x003d),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* device specifics unknown */
-	{ USB_DEVICE(0x15c2, 0x003e) },
+	{ USB_DEVICE(0x15c2, 0x003e),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* device specifics unknown */
-	{ USB_DEVICE(0x15c2, 0x003f) },
+	{ USB_DEVICE(0x15c2, 0x003f),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* device specifics unknown */
-	{ USB_DEVICE(0x15c2, 0x0040) },
+	{ USB_DEVICE(0x15c2, 0x0040),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* SoundGraph iMON MINI (IR only) */
-	{ USB_DEVICE(0x15c2, 0x0041) },
+	{ USB_DEVICE(0x15c2, 0x0041),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* Antec Veris Multimedia Station EZ External (IR only) */
-	{ USB_DEVICE(0x15c2, 0x0042) },
+	{ USB_DEVICE(0x15c2, 0x0042),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* Antec Veris Multimedia Station Basic Internal (IR only) */
-	{ USB_DEVICE(0x15c2, 0x0043) },
+	{ USB_DEVICE(0x15c2, 0x0043),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* Antec Veris Multimedia Station Elite (IR & VFD) */
-	{ USB_DEVICE(0x15c2, 0x0044) },
+	{ USB_DEVICE(0x15c2, 0x0044),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* Antec Veris Multimedia Station Premiere (IR & LCD) */
-	{ USB_DEVICE(0x15c2, 0x0045) },
+	{ USB_DEVICE(0x15c2, 0x0045),
+	  .driver_info = (unsigned long)&imon_default_table},
 	/* device specifics unknown */
-	{ USB_DEVICE(0x15c2, 0x0046) },
+	{ USB_DEVICE(0x15c2, 0x0046),
+	  .driver_info = (unsigned long)&imon_default_table},
 	{}
 };
 
@@ -266,67 +424,6 @@ static struct usb_driver imon_driver = {
 	.id_table	= imon_usb_id_table,
 };
 
-static struct usb_class_driver imon_vfd_class = {
-	.name		= DEVICE_NAME,
-	.fops		= &vfd_fops,
-	.minor_base	= DISPLAY_MINOR_BASE,
-};
-
-static struct usb_class_driver imon_lcd_class = {
-	.name		= DEVICE_NAME,
-	.fops		= &lcd_fops,
-	.minor_base	= DISPLAY_MINOR_BASE,
-};
-
-/* imon receiver front panel/knob key table */
-static const struct {
-	u64 hw_code;
-	u32 keycode;
-} imon_panel_key_table[] = {
-	{ 0x000000000f00ffeell, KEY_MEDIA }, /* Go */
-	{ 0x000000001200ffeell, KEY_UP },
-	{ 0x000000001300ffeell, KEY_DOWN },
-	{ 0x000000001400ffeell, KEY_LEFT },
-	{ 0x000000001500ffeell, KEY_RIGHT },
-	{ 0x000000001600ffeell, KEY_ENTER },
-	{ 0x000000001700ffeell, KEY_ESC },
-	{ 0x000000001f00ffeell, KEY_AUDIO },
-	{ 0x000000002000ffeell, KEY_VIDEO },
-	{ 0x000000002100ffeell, KEY_CAMERA },
-	{ 0x000000002700ffeell, KEY_DVD },
-	{ 0x000000002300ffeell, KEY_TV },
-	{ 0x000000002b00ffeell, KEY_EXIT },
-	{ 0x000000002c00ffeell, KEY_SELECT },
-	{ 0x000000002d00ffeell, KEY_MENU },
-	{ 0x000000000500ffeell, KEY_PREVIOUS },
-	{ 0x000000000700ffeell, KEY_REWIND },
-	{ 0x000000000400ffeell, KEY_STOP },
-	{ 0x000000003c00ffeell, KEY_PLAYPAUSE },
-	{ 0x000000000800ffeell, KEY_FASTFORWARD },
-	{ 0x000000000600ffeell, KEY_NEXT },
-	{ 0x000000010000ffeell, KEY_RIGHT },
-	{ 0x000001000000ffeell, KEY_LEFT },
-	{ 0x000000003d00ffeell, KEY_SELECT },
-	{ 0x000100000000ffeell, KEY_VOLUMEUP },
-	{ 0x010000000000ffeell, KEY_VOLUMEDOWN },
-	{ 0x000000000100ffeell, KEY_MUTE },
-	/* 0xffdc iMON MCE VFD */
-	{ 0x00010000ffffffeell, KEY_VOLUMEUP },
-	{ 0x01000000ffffffeell, KEY_VOLUMEDOWN },
-	{ 0x00000001ffffffeell, KEY_MUTE },
-	{ 0x0000000fffffffeell, KEY_MEDIA },
-	{ 0x00000012ffffffeell, KEY_UP },
-	{ 0x00000013ffffffeell, KEY_DOWN },
-	{ 0x00000014ffffffeell, KEY_LEFT },
-	{ 0x00000015ffffffeell, KEY_RIGHT },
-	{ 0x00000016ffffffeell, KEY_ENTER },
-	{ 0x00000017ffffffeell, KEY_ESC },
-	/* iMON Knob values */
-	{ 0x000100ffffffffeell, KEY_VOLUMEUP },
-	{ 0x010000ffffffffeell, KEY_VOLUMEDOWN },
-	{ 0x000008ffffffffeell, KEY_MUTE },
-};
-
 /* to prevent races between open() and disconnect(), probing, etc */
 static DEFINE_MUTEX(driver_lock);
 
@@ -1210,18 +1307,19 @@ static u32 imon_mce_key_lookup(struct imon_context *ictx, u32 scancode)
 	return keycode;
 }
 
-static u32 imon_panel_key_lookup(u64 code)
+static u32 imon_panel_key_lookup(struct imon_context *ictx, u64 code)
 {
 	int i;
 	u32 keycode = KEY_RESERVED;
+	struct imon_panel_key_table *key_table = ictx->dev_descr->key_table;
 
-	for (i = 0; i < ARRAY_SIZE(imon_panel_key_table); i++) {
-		if (imon_panel_key_table[i].hw_code == (code | 0xffee)) {
-			keycode = imon_panel_key_table[i].keycode;
+	for (i = 0; key_table[i].hw_code != 0; i++) {
+		if (key_table[i].hw_code == (code | 0xffee)) {
+			keycode = key_table[i].keycode;
 			break;
 		}
 	}
-
+	ictx->release_code = false;
 	return keycode;
 }
 
@@ -1340,7 +1438,7 @@ static void imon_pad_to_keys(struct imon_context *ictx, unsigned char *buf)
 				}
 				buf[2] = dir & 0xFF;
 				buf[3] = (dir >> 8) & 0xFF;
-				scancode = be32_to_cpu(*((u32 *)buf));
+				scancode = be32_to_cpu(*((__be32 *)buf));
 			}
 		} else {
 			/*
@@ -1404,7 +1502,7 @@ static void imon_pad_to_keys(struct imon_context *ictx, unsigned char *buf)
 			}
 			buf[2] = dir & 0xFF;
 			buf[3] = (dir >> 8) & 0xFF;
-			scancode = be32_to_cpu(*((u32 *)buf));
+			scancode = be32_to_cpu(*((__be32 *)buf));
 		} else {
 			/*
 			 * Hack alert: instead of using keycodes, we have
@@ -1509,11 +1607,12 @@ static void imon_incoming_packet(struct imon_context *ictx,
 
 	/* Figure out what key was pressed */
 	if (len == 8 && buf[7] == 0xee) {
-		scancode = be64_to_cpu(*((u64 *)buf));
+		scancode = be64_to_cpu(*((__be64 *)buf));
 		ktype = IMON_KEY_PANEL;
-		kc = imon_panel_key_lookup(scancode);
+		kc = imon_panel_key_lookup(ictx, scancode);
+		ictx->release_code = false;
 	} else {
-		scancode = be32_to_cpu(*((u32 *)buf));
+		scancode = be32_to_cpu(*((__be32 *)buf));
 		if (ictx->rc_type == RC_BIT_RC6_MCE) {
 			ktype = IMON_KEY_IMON;
 			if (buf[0] == 0x80)
@@ -1908,6 +2007,7 @@ out:
 
 static struct input_dev *imon_init_idev(struct imon_context *ictx)
 {
+	struct imon_panel_key_table *key_table = ictx->dev_descr->key_table;
 	struct input_dev *idev;
 	int ret, i;
 
@@ -1933,8 +2033,8 @@ static struct input_dev *imon_init_idev(struct imon_context *ictx)
 		BIT_MASK(REL_WHEEL);
 
 	/* panel and/or knob code support */
-	for (i = 0; i < ARRAY_SIZE(imon_panel_key_table); i++) {
-		u32 kc = imon_panel_key_table[i].keycode;
+	for (i = 0; key_table[i].hw_code != 0; i++) {
+		u32 kc = key_table[i].keycode;
 		__set_bit(kc, idev->keybit);
 	}
 
@@ -2023,7 +2123,7 @@ static bool imon_find_endpoints(struct imon_context *ictx,
 	for (i = 0; i < num_endpts && !(ir_ep_found && display_ep_found); ++i) {
 		ep = &iface_desc->endpoint[i].desc;
 		ep_dir = ep->bEndpointAddress & USB_ENDPOINT_DIR_MASK;
-		ep_type = ep->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK;
+		ep_type = usb_endpoint_type(ep);
 
 		if (!ir_ep_found && ep_dir == USB_DIR_IN &&
 		    ep_type == USB_ENDPOINT_XFER_INT) {
@@ -2135,9 +2235,11 @@ static struct imon_context *imon_init_intf0(struct usb_interface *intf,
 	ictx->vendor  = le16_to_cpu(ictx->usbdev_intf0->descriptor.idVendor);
 	ictx->product = le16_to_cpu(ictx->usbdev_intf0->descriptor.idProduct);
 
+	/* save drive info for later accessing the panel/knob key table */
+	ictx->dev_descr = (struct imon_usb_dev_descr *)id->driver_info;
 	/* default send_packet delay is 5ms but some devices need more */
-	ictx->send_packet_delay = id->driver_info & IMON_NEED_20MS_PKT_DELAY ?
-				  20 : 5;
+	ictx->send_packet_delay = ictx->dev_descr->flags &
+				  IMON_NEED_20MS_PKT_DELAY ? 20 : 5;
 
 	ret = -ENODEV;
 	iface_desc = intf->cur_altsetting;
@@ -2181,6 +2283,7 @@ idev_setup_failed:
 	usb_kill_urb(ictx->rx_urb_intf0);
 urb_submit_failed:
 find_endpoint_failed:
+	usb_put_dev(ictx->usbdev_intf0);
 	mutex_unlock(&ictx->lock);
 	usb_free_urb(tx_urb);
 tx_urb_alloc_failed:
@@ -2253,6 +2356,7 @@ urb_submit_failed:
 		input_unregister_device(ictx->touch);
 touch_setup_failed:
 find_endpoint_failed:
+	usb_put_dev(ictx->usbdev_intf1);
 	mutex_unlock(&ictx->lock);
 	usb_free_urb(rx_urb);
 rx_urb_alloc_failed:
@@ -2366,11 +2470,13 @@ static int imon_probe(struct usb_interface *interface,
 		 usbdev->bus->busnum, usbdev->devnum);
 
 	mutex_unlock(&driver_lock);
+	usb_put_dev(usbdev);
 
 	return 0;
 
 fail:
 	mutex_unlock(&driver_lock);
+	usb_put_dev(usbdev);
 	dev_err(dev, "unable to register, err %d\n", ret);
 
 	return ret;
@@ -2410,6 +2516,7 @@ static void imon_disconnect(struct usb_interface *interface)
 	if (ifnum == 0) {
 		ictx->dev_present_intf0 = false;
 		usb_kill_urb(ictx->rx_urb_intf0);
+		usb_put_dev(ictx->usbdev_intf0);
 		input_unregister_device(ictx->idev);
 		rc_unregister_device(ictx->rdev);
 		if (ictx->display_supported) {
@@ -2421,6 +2528,7 @@ static void imon_disconnect(struct usb_interface *interface)
 	} else {
 		ictx->dev_present_intf1 = false;
 		usb_kill_urb(ictx->rx_urb_intf1);
+		usb_put_dev(ictx->usbdev_intf1);
 		if (ictx->display_type == IMON_DISPLAY_TYPE_VGA) {
 			input_unregister_device(ictx->touch);
 			del_timer_sync(&ictx->ttimer);
diff --git a/drivers/media/rc/ir-hix5hd2.c b/drivers/media/rc/ir-hix5hd2.c
new file mode 100644
index 000000000000..08bbd4f508cd
--- /dev/null
+++ b/drivers/media/rc/ir-hix5hd2.c
@@ -0,0 +1,351 @@
+/*
+ * Copyright (c) 2014 Linaro Ltd.
+ * Copyright (c) 2014 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <media/rc-core.h>
+
+/* Allow the driver to compile on all architectures */
+#ifndef writel_relaxed
+# define writel_relaxed writel
+#endif
+#ifndef readl_relaxed
+# define readl_relaxed readl
+#endif
+
+#define IR_ENABLE		0x00
+#define IR_CONFIG		0x04
+#define CNT_LEADS		0x08
+#define CNT_LEADE		0x0c
+#define CNT_SLEADE		0x10
+#define CNT0_B			0x14
+#define CNT1_B			0x18
+#define IR_BUSY			0x1c
+#define IR_DATAH		0x20
+#define IR_DATAL		0x24
+#define IR_INTM			0x28
+#define IR_INTS			0x2c
+#define IR_INTC			0x30
+#define IR_START		0x34
+
+/* interrupt mask */
+#define INTMS_SYMBRCV		(BIT(24) | BIT(8))
+#define INTMS_TIMEOUT		(BIT(25) | BIT(9))
+#define INTMS_OVERFLOW		(BIT(26) | BIT(10))
+#define INT_CLR_OVERFLOW	BIT(18)
+#define INT_CLR_TIMEOUT		BIT(17)
+#define INT_CLR_RCV		BIT(16)
+#define INT_CLR_RCVTIMEOUT	(BIT(16) | BIT(17))
+
+#define IR_CLK			0x48
+#define IR_CLK_ENABLE		BIT(4)
+#define IR_CLK_RESET		BIT(5)
+
+#define IR_CFG_WIDTH_MASK	0xffff
+#define IR_CFG_WIDTH_SHIFT	16
+#define IR_CFG_FORMAT_MASK	0x3
+#define IR_CFG_FORMAT_SHIFT	14
+#define IR_CFG_INT_LEVEL_MASK	0x3f
+#define IR_CFG_INT_LEVEL_SHIFT	8
+/* only support raw mode */
+#define IR_CFG_MODE_RAW		BIT(7)
+#define IR_CFG_FREQ_MASK	0x7f
+#define IR_CFG_FREQ_SHIFT	0
+#define IR_CFG_INT_THRESHOLD	1
+/* symbol start from low to high, symbol stream end at high*/
+#define IR_CFG_SYMBOL_FMT	0
+#define IR_CFG_SYMBOL_MAXWIDTH	0x3e80
+
+#define IR_HIX5HD2_NAME		"hix5hd2-ir"
+
+struct hix5hd2_ir_priv {
+	int			irq;
+	void volatile __iomem	*base;
+	struct device		*dev;
+	struct rc_dev		*rdev;
+	struct regmap		*regmap;
+	struct clk		*clock;
+	unsigned long		rate;
+};
+
+static void hix5hd2_ir_enable(struct hix5hd2_ir_priv *dev, bool on)
+{
+	u32 val;
+
+	regmap_read(dev->regmap, IR_CLK, &val);
+	if (on) {
+		val &= ~IR_CLK_RESET;
+		val |= IR_CLK_ENABLE;
+	} else {
+		val &= ~IR_CLK_ENABLE;
+		val |= IR_CLK_RESET;
+	}
+	regmap_write(dev->regmap, IR_CLK, val);
+}
+
+static int hix5hd2_ir_config(struct hix5hd2_ir_priv *priv)
+{
+	int timeout = 10000;
+	u32 val, rate;
+
+	writel_relaxed(0x01, priv->base + IR_ENABLE);
+	while (readl_relaxed(priv->base + IR_BUSY)) {
+		if (timeout--) {
+			udelay(1);
+		} else {
+			dev_err(priv->dev, "IR_BUSY timeout\n");
+			return -ETIMEDOUT;
+		}
+	}
+
+	/* Now only support raw mode, with symbol start from low to high */
+	rate = DIV_ROUND_CLOSEST(priv->rate, 1000000);
+	val = IR_CFG_SYMBOL_MAXWIDTH & IR_CFG_WIDTH_MASK << IR_CFG_WIDTH_SHIFT;
+	val |= IR_CFG_SYMBOL_FMT & IR_CFG_FORMAT_MASK << IR_CFG_FORMAT_SHIFT;
+	val |= (IR_CFG_INT_THRESHOLD - 1) & IR_CFG_INT_LEVEL_MASK
+	       << IR_CFG_INT_LEVEL_SHIFT;
+	val |= IR_CFG_MODE_RAW;
+	val |= (rate - 1) & IR_CFG_FREQ_MASK << IR_CFG_FREQ_SHIFT;
+	writel_relaxed(val, priv->base + IR_CONFIG);
+
+	writel_relaxed(0x00, priv->base + IR_INTM);
+	/* write arbitrary value to start  */
+	writel_relaxed(0x01, priv->base + IR_START);
+	return 0;
+}
+
+static int hix5hd2_ir_open(struct rc_dev *rdev)
+{
+	struct hix5hd2_ir_priv *priv = rdev->priv;
+
+	hix5hd2_ir_enable(priv, true);
+	return hix5hd2_ir_config(priv);
+}
+
+static void hix5hd2_ir_close(struct rc_dev *rdev)
+{
+	struct hix5hd2_ir_priv *priv = rdev->priv;
+
+	hix5hd2_ir_enable(priv, false);
+}
+
+static irqreturn_t hix5hd2_ir_rx_interrupt(int irq, void *data)
+{
+	u32 symb_num, symb_val, symb_time;
+	u32 data_l, data_h;
+	u32 irq_sr, i;
+	struct hix5hd2_ir_priv *priv = data;
+
+	irq_sr = readl_relaxed(priv->base + IR_INTS);
+	if (irq_sr & INTMS_OVERFLOW) {
+		/*
+		 * we must read IR_DATAL first, then we can clean up
+		 * IR_INTS availably since logic would not clear
+		 * fifo when overflow, drv do the job
+		 */
+		ir_raw_event_reset(priv->rdev);
+		symb_num = readl_relaxed(priv->base + IR_DATAH);
+		for (i = 0; i < symb_num; i++)
+			readl_relaxed(priv->base + IR_DATAL);
+
+		writel_relaxed(INT_CLR_OVERFLOW, priv->base + IR_INTC);
+		dev_info(priv->dev, "overflow, level=%d\n",
+			 IR_CFG_INT_THRESHOLD);
+	}
+
+	if ((irq_sr & INTMS_SYMBRCV) || (irq_sr & INTMS_TIMEOUT)) {
+		DEFINE_IR_RAW_EVENT(ev);
+
+		symb_num = readl_relaxed(priv->base + IR_DATAH);
+		for (i = 0; i < symb_num; i++) {
+			symb_val = readl_relaxed(priv->base + IR_DATAL);
+			data_l = ((symb_val & 0xffff) * 10);
+			data_h =  ((symb_val >> 16) & 0xffff) * 10;
+			symb_time = (data_l + data_h) / 10;
+
+			ev.duration = US_TO_NS(data_l);
+			ev.pulse = true;
+			ir_raw_event_store(priv->rdev, &ev);
+
+			if (symb_time < IR_CFG_SYMBOL_MAXWIDTH) {
+				ev.duration = US_TO_NS(data_h);
+				ev.pulse = false;
+				ir_raw_event_store(priv->rdev, &ev);
+			} else {
+				ir_raw_event_set_idle(priv->rdev, true);
+			}
+		}
+
+		if (irq_sr & INTMS_SYMBRCV)
+			writel_relaxed(INT_CLR_RCV, priv->base + IR_INTC);
+		if (irq_sr & INTMS_TIMEOUT)
+			writel_relaxed(INT_CLR_TIMEOUT, priv->base + IR_INTC);
+	}
+
+	/* Empty software fifo */
+	ir_raw_event_handle(priv->rdev);
+	return IRQ_HANDLED;
+}
+
+static int hix5hd2_ir_probe(struct platform_device *pdev)
+{
+	struct rc_dev *rdev;
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct hix5hd2_ir_priv *priv;
+	struct device_node *node = pdev->dev.of_node;
+	const char *map_name;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->regmap = syscon_regmap_lookup_by_phandle(node,
+						       "hisilicon,power-syscon");
+	if (IS_ERR(priv->regmap)) {
+		dev_err(dev, "no power-reg\n");
+		return -EINVAL;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR((__force void *)priv->base))
+		return PTR_ERR((__force void *)priv->base);
+
+	priv->irq = platform_get_irq(pdev, 0);
+	if (priv->irq < 0) {
+		dev_err(dev, "irq can not get\n");
+		return priv->irq;
+	}
+
+	rdev = rc_allocate_device();
+	if (!rdev)
+		return -ENOMEM;
+
+	priv->clock = devm_clk_get(dev, NULL);
+	if (IS_ERR(priv->clock)) {
+		dev_err(dev, "clock not found\n");
+		ret = PTR_ERR(priv->clock);
+		goto err;
+	}
+	clk_prepare_enable(priv->clock);
+	priv->rate = clk_get_rate(priv->clock);
+
+	rdev->driver_type = RC_DRIVER_IR_RAW;
+	rdev->allowed_protocols = RC_BIT_ALL;
+	rdev->priv = priv;
+	rdev->open = hix5hd2_ir_open;
+	rdev->close = hix5hd2_ir_close;
+	rdev->driver_name = IR_HIX5HD2_NAME;
+	map_name = of_get_property(node, "linux,rc-map-name", NULL);
+	rdev->map_name = map_name ?: RC_MAP_EMPTY;
+	rdev->input_name = IR_HIX5HD2_NAME;
+	rdev->input_phys = IR_HIX5HD2_NAME "/input0";
+	rdev->input_id.bustype = BUS_HOST;
+	rdev->input_id.vendor = 0x0001;
+	rdev->input_id.product = 0x0001;
+	rdev->input_id.version = 0x0100;
+	rdev->rx_resolution = US_TO_NS(10);
+	rdev->timeout = US_TO_NS(IR_CFG_SYMBOL_MAXWIDTH * 10);
+
+	ret = rc_register_device(rdev);
+	if (ret < 0)
+		goto clkerr;
+
+	if (devm_request_irq(dev, priv->irq, hix5hd2_ir_rx_interrupt,
+			     IRQF_NO_SUSPEND, pdev->name, priv) < 0) {
+		dev_err(dev, "IRQ %d register failed\n", priv->irq);
+		ret = -EINVAL;
+		goto regerr;
+	}
+
+	priv->rdev = rdev;
+	priv->dev = dev;
+	platform_set_drvdata(pdev, priv);
+
+	return ret;
+
+regerr:
+	rc_unregister_device(rdev);
+	rdev = NULL;
+clkerr:
+	clk_disable_unprepare(priv->clock);
+err:
+	rc_free_device(rdev);
+	dev_err(dev, "Unable to register device (%d)\n", ret);
+	return ret;
+}
+
+static int hix5hd2_ir_remove(struct platform_device *pdev)
+{
+	struct hix5hd2_ir_priv *priv = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(priv->clock);
+	rc_unregister_device(priv->rdev);
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int hix5hd2_ir_suspend(struct device *dev)
+{
+	struct hix5hd2_ir_priv *priv = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(priv->clock);
+	hix5hd2_ir_enable(priv, false);
+
+	return 0;
+}
+
+static int hix5hd2_ir_resume(struct device *dev)
+{
+	struct hix5hd2_ir_priv *priv = dev_get_drvdata(dev);
+
+	hix5hd2_ir_enable(priv, true);
+	clk_prepare_enable(priv->clock);
+
+	writel_relaxed(0x01, priv->base + IR_ENABLE);
+	writel_relaxed(0x00, priv->base + IR_INTM);
+	writel_relaxed(0xff, priv->base + IR_INTC);
+	writel_relaxed(0x01, priv->base + IR_START);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(hix5hd2_ir_pm_ops, hix5hd2_ir_suspend,
+			 hix5hd2_ir_resume);
+
+static struct of_device_id hix5hd2_ir_table[] = {
+	{ .compatible = "hisilicon,hix5hd2-ir", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, hix5hd2_ir_table);
+
+static struct platform_driver hix5hd2_ir_driver = {
+	.driver = {
+		.name = IR_HIX5HD2_NAME,
+		.of_match_table = hix5hd2_ir_table,
+		.pm     = &hix5hd2_ir_pm_ops,
+	},
+	.probe = hix5hd2_ir_probe,
+	.remove = hix5hd2_ir_remove,
+};
+
+module_platform_driver(hix5hd2_ir_driver);
+
+MODULE_DESCRIPTION("IR controller driver for hix5hd2 platforms");
+MODULE_AUTHOR("Guoxiong Yan <yanguoxiong@huawei.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:hix5hd2-ir");
diff --git a/drivers/media/rc/ite-cir.c b/drivers/media/rc/ite-cir.c
index 447fe35862dc..56abf9120cc2 100644
--- a/drivers/media/rc/ite-cir.c
+++ b/drivers/media/rc/ite-cir.c
@@ -1666,7 +1666,6 @@ static int ite_suspend(struct pnp_dev *pdev, pm_message_t state)
 
 static int ite_resume(struct pnp_dev *pdev)
 {
-	int ret = 0;
 	struct ite_dev *dev = pnp_get_drvdata(pdev);
 	unsigned long flags;
 
@@ -1681,7 +1680,7 @@ static int ite_resume(struct pnp_dev *pdev)
 
 	spin_unlock_irqrestore(&dev->lock, flags);
 
-	return ret;
+	return 0;
 }
 
 static void ite_shutdown(struct pnp_dev *pdev)
diff --git a/drivers/media/rc/keymaps/Makefile b/drivers/media/rc/keymaps/Makefile
index 0b8c54919010..abf60794223d 100644
--- a/drivers/media/rc/keymaps/Makefile
+++ b/drivers/media/rc/keymaps/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_RC_MAP) += rc-adstech-dvb-t-pci.o \
 			rc-dm1105-nec.o \
 			rc-dntv-live-dvb-t.o \
 			rc-dntv-live-dvbt-pro.o \
+			rc-dvbsky.o \
 			rc-em-terratec.o \
 			rc-encore-enltv2.o \
 			rc-encore-enltv.o \
diff --git a/drivers/media/rc/keymaps/rc-dvbsky.c b/drivers/media/rc/keymaps/rc-dvbsky.c
new file mode 100644
index 000000000000..c5115a1165d1
--- /dev/null
+++ b/drivers/media/rc/keymaps/rc-dvbsky.c
@@ -0,0 +1,78 @@
+/* rc-dvbsky.c - Keytable for DVBSky Remote Controllers
+ *
+ * keymap imported from ir-keymaps.c
+ *
+ *
+ * Copyright (c) 2010-2012 by Nibble Max <nibble.max@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <media/rc-map.h>
+#include <linux/module.h>
+/*
+ * This table contains the complete RC5 code, instead of just the data part
+ */
+
+static struct rc_map_table rc5_dvbsky[] = {
+	{ 0x0000, KEY_0 },
+	{ 0x0001, KEY_1 },
+	{ 0x0002, KEY_2 },
+	{ 0x0003, KEY_3 },
+	{ 0x0004, KEY_4 },
+	{ 0x0005, KEY_5 },
+	{ 0x0006, KEY_6 },
+	{ 0x0007, KEY_7 },
+	{ 0x0008, KEY_8 },
+	{ 0x0009, KEY_9 },
+	{ 0x000a, KEY_MUTE },
+	{ 0x000d, KEY_OK },
+	{ 0x000b, KEY_STOP },
+	{ 0x000c, KEY_EXIT },
+	{ 0x000e, KEY_CAMERA }, /*Snap shot*/
+	{ 0x000f, KEY_SUBTITLE }, /*PIP*/
+	{ 0x0010, KEY_VOLUMEUP },
+	{ 0x0011, KEY_VOLUMEDOWN },
+	{ 0x0012, KEY_FAVORITES },
+	{ 0x0013, KEY_LIST }, /*Info*/
+	{ 0x0016, KEY_PAUSE },
+	{ 0x0017, KEY_PLAY },
+	{ 0x001f, KEY_RECORD },
+	{ 0x0020, KEY_CHANNELDOWN },
+	{ 0x0021, KEY_CHANNELUP },
+	{ 0x0025, KEY_POWER2 },
+	{ 0x0026, KEY_REWIND },
+	{ 0x0027, KEY_FASTFORWARD },
+	{ 0x0029, KEY_LAST },
+	{ 0x002b, KEY_MENU },
+	{ 0x002c, KEY_EPG },
+	{ 0x002d, KEY_ZOOM },
+};
+
+static struct rc_map_list rc5_dvbsky_map = {
+	.map = {
+		.scan    = rc5_dvbsky,
+		.size    = ARRAY_SIZE(rc5_dvbsky),
+		.rc_type = RC_TYPE_RC5,
+		.name    = RC_MAP_DVBSKY,
+	}
+};
+
+static int __init init_rc_map_rc5_dvbsky(void)
+{
+	return rc_map_register(&rc5_dvbsky_map);
+}
+
+static void __exit exit_rc_map_rc5_dvbsky(void)
+{
+	rc_map_unregister(&rc5_dvbsky_map);
+}
+
+module_init(init_rc_map_rc5_dvbsky)
+module_exit(exit_rc_map_rc5_dvbsky)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nibble Max <nibble.max@gmail.com>");
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index dc5cbffcd5a2..249d2fbc8f37 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -595,7 +595,7 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	switch (cmd) {
 	case LIRC_GET_FEATURES:
-		result = put_user(ir->d.features, (__u32 *)arg);
+		result = put_user(ir->d.features, (__u32 __user *)arg);
 		break;
 	case LIRC_GET_REC_MODE:
 		if (!(ir->d.features & LIRC_CAN_REC_MASK)) {
@@ -605,7 +605,7 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 		result = put_user(LIRC_REC2MODE
 				  (ir->d.features & LIRC_CAN_REC_MASK),
-				  (__u32 *)arg);
+				  (__u32 __user *)arg);
 		break;
 	case LIRC_SET_REC_MODE:
 		if (!(ir->d.features & LIRC_CAN_REC_MASK)) {
@@ -613,7 +613,7 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			break;
 		}
 
-		result = get_user(mode, (__u32 *)arg);
+		result = get_user(mode, (__u32 __user *)arg);
 		if (!result && !(LIRC_MODE2REC(mode) & ir->d.features))
 			result = -EINVAL;
 		/*
@@ -622,7 +622,7 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		 */
 		break;
 	case LIRC_GET_LENGTH:
-		result = put_user(ir->d.code_length, (__u32 *)arg);
+		result = put_user(ir->d.code_length, (__u32 __user *)arg);
 		break;
 	case LIRC_GET_MIN_TIMEOUT:
 		if (!(ir->d.features & LIRC_CAN_SET_REC_TIMEOUT) ||
@@ -631,7 +631,7 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			break;
 		}
 
-		result = put_user(ir->d.min_timeout, (__u32 *)arg);
+		result = put_user(ir->d.min_timeout, (__u32 __user *)arg);
 		break;
 	case LIRC_GET_MAX_TIMEOUT:
 		if (!(ir->d.features & LIRC_CAN_SET_REC_TIMEOUT) ||
@@ -640,7 +640,7 @@ long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			break;
 		}
 
-		result = put_user(ir->d.max_timeout, (__u32 *)arg);
+		result = put_user(ir->d.max_timeout, (__u32 __user *)arg);
 		break;
 	default:
 		result = -EINVAL;
@@ -736,7 +736,7 @@ ssize_t lirc_dev_fop_read(struct file *file,
 			}
 		} else {
 			lirc_buffer_read(ir->buf, buf);
-			ret = copy_to_user((void *)buffer+written, buf,
+			ret = copy_to_user((void __user *)buffer+written, buf,
 					   ir->buf->chunk_size);
 			if (!ret)
 				written += ir->buf->chunk_size;
diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c
index 45b0894288e5..2cdb740cde48 100644
--- a/drivers/media/rc/mceusb.c
+++ b/drivers/media/rc/mceusb.c
@@ -397,6 +397,10 @@ static struct usb_device_id mceusb_dev_table[] = {
 	  .driver_info = HAUPPAUGE_CX_HYBRID_TV },
 	{ USB_DEVICE(VENDOR_HAUPPAUGE, 0xb131),
 	  .driver_info = HAUPPAUGE_CX_HYBRID_TV },
+	{ USB_DEVICE(VENDOR_HAUPPAUGE, 0xb138),
+	  .driver_info = HAUPPAUGE_CX_HYBRID_TV },
+	{ USB_DEVICE(VENDOR_HAUPPAUGE, 0xb139),
+	  .driver_info = HAUPPAUGE_CX_HYBRID_TV },
 	{ USB_DEVICE(VENDOR_PCTV, 0x0259),
 	  .driver_info = HAUPPAUGE_CX_HYBRID_TV },
 	{ USB_DEVICE(VENDOR_PCTV, 0x025e),
@@ -1198,10 +1202,9 @@ static void mceusb_flash_led(struct mceusb_dev *ir)
 	mce_async_out(ir, FLASH_LED, sizeof(FLASH_LED));
 }
 
-static struct rc_dev *mceusb_init_rc_dev(struct mceusb_dev *ir,
-					 struct usb_interface *intf)
+static struct rc_dev *mceusb_init_rc_dev(struct mceusb_dev *ir)
 {
-	struct usb_device *udev = usb_get_dev(interface_to_usbdev(intf));
+	struct usb_device *udev = ir->usbdev;
 	struct device *dev = ir->dev;
 	struct rc_dev *rc;
 	int ret;
@@ -1341,7 +1344,7 @@ static int mceusb_dev_probe(struct usb_interface *intf,
 	if (!ir->urb_in)
 		goto urb_in_alloc_fail;
 
-	ir->usbdev = dev;
+	ir->usbdev = usb_get_dev(dev);
 	ir->dev = &intf->dev;
 	ir->len_in = maxp;
 	ir->flags.microsoft_gen1 = is_microsoft_gen1;
@@ -1362,7 +1365,7 @@ static int mceusb_dev_probe(struct usb_interface *intf,
 		snprintf(name + strlen(name), sizeof(name) - strlen(name),
 			 " %s", buf);
 
-	ir->rc = mceusb_init_rc_dev(ir, intf);
+	ir->rc = mceusb_init_rc_dev(ir);
 	if (!ir->rc)
 		goto rc_dev_fail;
 
@@ -1408,6 +1411,7 @@ static int mceusb_dev_probe(struct usb_interface *intf,
 
 	/* Error-handling path */
 rc_dev_fail:
+	usb_put_dev(ir->usbdev);
 	usb_free_urb(ir->urb_in);
 urb_in_alloc_fail:
 	usb_free_coherent(dev, maxp, ir->buf_in, ir->dma_in);
@@ -1435,6 +1439,7 @@ static void mceusb_dev_disconnect(struct usb_interface *intf)
 	usb_kill_urb(ir->urb_in);
 	usb_free_urb(ir->urb_in);
 	usb_free_coherent(dev, ir->len_in, ir->buf_in, ir->dma_in);
+	usb_put_dev(dev);
 
 	kfree(ir);
 }
diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c
index 7f4fd859bba5..9c2c8635ff33 100644
--- a/drivers/media/rc/nuvoton-cir.c
+++ b/drivers/media/rc/nuvoton-cir.c
@@ -229,7 +229,6 @@ static int nvt_hw_detect(struct nvt_dev *nvt)
 {
 	unsigned long flags;
 	u8 chip_major, chip_minor;
-	int ret = 0;
 	char chip_id[12];
 	bool chip_unknown = false;
 
@@ -285,7 +284,7 @@ static int nvt_hw_detect(struct nvt_dev *nvt)
 	nvt->chip_minor = chip_minor;
 	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
 
-	return ret;
+	return 0;
 }
 
 static void nvt_cir_ldev_init(struct nvt_dev *nvt)
@@ -1177,7 +1176,6 @@ static int nvt_suspend(struct pnp_dev *pdev, pm_message_t state)
 
 static int nvt_resume(struct pnp_dev *pdev)
 {
-	int ret = 0;
 	struct nvt_dev *nvt = pnp_get_drvdata(pdev);
 
 	nvt_dbg("%s called", __func__);
@@ -1195,7 +1193,7 @@ static int nvt_resume(struct pnp_dev *pdev)
 	nvt_cir_regs_init(nvt);
 	nvt_cir_wake_regs_init(nvt);
 
-	return ret;
+	return 0;
 }
 
 static void nvt_shutdown(struct pnp_dev *pdev)
diff --git a/drivers/media/rc/st_rc.c b/drivers/media/rc/st_rc.c
index 5c151351afa4..0e758ae2e529 100644
--- a/drivers/media/rc/st_rc.c
+++ b/drivers/media/rc/st_rc.c
@@ -22,8 +22,8 @@ struct st_rc_device {
 	int				irq;
 	int				irq_wake;
 	struct clk			*sys_clock;
-	void				*base;	/* Register base address */
-	void				*rx_base;/* RX Register base address */
+	volatile void __iomem		*base;	/* Register base address */
+	volatile void __iomem		*rx_base;/* RX Register base address */
 	struct rc_dev			*rdev;
 	bool				overclocking;
 	int				sample_mult;
@@ -267,8 +267,8 @@ static int st_rc_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
 	rc_dev->base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(rc_dev->base)) {
-		ret = PTR_ERR(rc_dev->base);
+	if (IS_ERR((__force void *)rc_dev->base)) {
+		ret = PTR_ERR((__force void *)rc_dev->base);
 		goto err;
 	}
 
@@ -278,7 +278,7 @@ static int st_rc_probe(struct platform_device *pdev)
 		rc_dev->rx_base = rc_dev->base;
 
 
-	rc_dev->rstc = reset_control_get(dev, NULL);
+	rc_dev->rstc = reset_control_get_optional(dev, NULL);
 	if (IS_ERR(rc_dev->rstc))
 		rc_dev->rstc = NULL;
 
@@ -376,9 +376,10 @@ static int st_rc_resume(struct device *dev)
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(st_rc_pm_ops, st_rc_suspend, st_rc_resume);
 #endif
 
+static SIMPLE_DEV_PM_OPS(st_rc_pm_ops, st_rc_suspend, st_rc_resume);
+
 #ifdef CONFIG_OF
 static struct of_device_id st_rc_match[] = {
 	{ .compatible = "st,comms-irb", },
@@ -391,11 +392,8 @@ MODULE_DEVICE_TABLE(of, st_rc_match);
 static struct platform_driver st_rc_driver = {
 	.driver = {
 		.name = IR_ST_NAME,
-		.owner	= THIS_MODULE,
 		.of_match_table = of_match_ptr(st_rc_match),
-#ifdef CONFIG_PM
 		.pm     = &st_rc_pm_ops,
-#endif
 	},
 	.probe = st_rc_probe,
 	.remove = st_rc_remove,
diff --git a/drivers/media/rc/streamzap.c b/drivers/media/rc/streamzap.c
index 80c4feeb01ea..bf4a44272f0e 100644
--- a/drivers/media/rc/streamzap.c
+++ b/drivers/media/rc/streamzap.c
@@ -362,16 +362,14 @@ static int streamzap_probe(struct usb_interface *intf,
 	}
 
 	sz->endpoint = &(iface_host->endpoint[0].desc);
-	if ((sz->endpoint->bEndpointAddress & USB_ENDPOINT_DIR_MASK)
-	    != USB_DIR_IN) {
+	if (!usb_endpoint_dir_in(sz->endpoint)) {
 		dev_err(&intf->dev, "%s: endpoint doesn't match input device "
 			"02%02x\n", __func__, sz->endpoint->bEndpointAddress);
 		retval = -ENODEV;
 		goto free_sz;
 	}
 
-	if ((sz->endpoint->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK)
-	    != USB_ENDPOINT_XFER_INT) {
+	if (!usb_endpoint_xfer_int(sz->endpoint)) {
 		dev_err(&intf->dev, "%s: endpoint attributes don't match xfer "
 			"02%02x\n", __func__, sz->endpoint->bmAttributes);
 		retval = -ENODEV;
diff --git a/drivers/media/tuners/Kconfig b/drivers/media/tuners/Kconfig
index d79fd1ce5a18..f039dc2a21cf 100644
--- a/drivers/media/tuners/Kconfig
+++ b/drivers/media/tuners/Kconfig
@@ -204,6 +204,7 @@ config MEDIA_TUNER_FC0013
 config MEDIA_TUNER_TDA18212
 	tristate "NXP TDA18212 silicon tuner"
 	depends on MEDIA_SUPPORT && I2C
+	select REGMAP_I2C
 	default m if !MEDIA_SUBDRV_AUTOSELECT
 	help
 	  NXP TDA18212 silicon tuner driver.
@@ -226,6 +227,7 @@ config MEDIA_TUNER_FC2580
 config MEDIA_TUNER_M88TS2022
 	tristate "Montage M88TS2022 silicon tuner"
 	depends on MEDIA_SUPPORT && I2C
+	select REGMAP_I2C
 	default m if !MEDIA_SUBDRV_AUTOSELECT
 	help
 	  Montage M88TS2022 silicon tuner driver.
@@ -247,6 +249,7 @@ config MEDIA_TUNER_SI2157
 config MEDIA_TUNER_IT913X
 	tristate "ITE Tech IT913x silicon tuner"
 	depends on MEDIA_SUPPORT && I2C
+	select REGMAP_I2C
 	default m if !MEDIA_SUBDRV_AUTOSELECT
 	help
 	  ITE Tech IT913x silicon tuner driver.
@@ -257,4 +260,18 @@ config MEDIA_TUNER_R820T
 	default m if !MEDIA_SUBDRV_AUTOSELECT
 	help
 	  Rafael Micro R820T silicon tuner driver.
+
+config MEDIA_TUNER_MXL301RF
+	tristate "MaxLinear MxL301RF tuner"
+	depends on MEDIA_SUPPORT && I2C
+	default m if !MEDIA_SUBDRV_AUTOSELECT
+	help
+	  MaxLinear MxL301RF OFDM tuner driver.
+
+config MEDIA_TUNER_QM1D1C0042
+	tristate "Sharp QM1D1C0042 tuner"
+	depends on MEDIA_SUPPORT && I2C
+	default m if !MEDIA_SUBDRV_AUTOSELECT
+	help
+	  Sharp QM1D1C0042 trellis coded 8PSK tuner driver.
 endmenu
diff --git a/drivers/media/tuners/Makefile b/drivers/media/tuners/Makefile
index 5591699755ba..49fcf8033848 100644
--- a/drivers/media/tuners/Makefile
+++ b/drivers/media/tuners/Makefile
@@ -37,8 +37,10 @@ obj-$(CONFIG_MEDIA_TUNER_M88TS2022) += m88ts2022.o
 obj-$(CONFIG_MEDIA_TUNER_FC0011) += fc0011.o
 obj-$(CONFIG_MEDIA_TUNER_FC0012) += fc0012.o
 obj-$(CONFIG_MEDIA_TUNER_FC0013) += fc0013.o
-obj-$(CONFIG_MEDIA_TUNER_IT913X) += tuner_it913x.o
+obj-$(CONFIG_MEDIA_TUNER_IT913X) += it913x.o
 obj-$(CONFIG_MEDIA_TUNER_R820T) += r820t.o
+obj-$(CONFIG_MEDIA_TUNER_MXL301RF) += mxl301rf.o
+obj-$(CONFIG_MEDIA_TUNER_QM1D1C0042) += qm1d1c0042.o
 
 ccflags-y += -I$(srctree)/drivers/media/dvb-core
 ccflags-y += -I$(srctree)/drivers/media/dvb-frontends
diff --git a/drivers/media/tuners/e4000.c b/drivers/media/tuners/e4000.c
index 90d93348f20c..510239f80c0d 100644
--- a/drivers/media/tuners/e4000.c
+++ b/drivers/media/tuners/e4000.c
@@ -26,7 +26,7 @@ static int e4000_init(struct dvb_frontend *fe)
 	struct e4000 *s = fe->tuner_priv;
 	int ret;
 
-	dev_dbg(&s->client->dev, "%s:\n", __func__);
+	dev_dbg(&s->client->dev, "\n");
 
 	/* dummy I2C to ensure I2C wakes up */
 	ret = regmap_write(s->regmap, 0x02, 0x40);
@@ -87,7 +87,7 @@ static int e4000_init(struct dvb_frontend *fe)
 	s->active = true;
 err:
 	if (ret)
-		dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&s->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -97,7 +97,7 @@ static int e4000_sleep(struct dvb_frontend *fe)
 	struct e4000 *s = fe->tuner_priv;
 	int ret;
 
-	dev_dbg(&s->client->dev, "%s:\n", __func__);
+	dev_dbg(&s->client->dev, "\n");
 
 	s->active = false;
 
@@ -106,7 +106,7 @@ static int e4000_sleep(struct dvb_frontend *fe)
 		goto err;
 err:
 	if (ret)
-		dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&s->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -121,9 +121,8 @@ static int e4000_set_params(struct dvb_frontend *fe)
 	u8 buf[5], i_data[4], q_data[4];
 
 	dev_dbg(&s->client->dev,
-			"%s: delivery_system=%d frequency=%u bandwidth_hz=%u\n",
-			__func__, c->delivery_system, c->frequency,
-			c->bandwidth_hz);
+			"delivery_system=%d frequency=%u bandwidth_hz=%u\n",
+			c->delivery_system, c->frequency, c->bandwidth_hz);
 
 	/* gain control manual */
 	ret = regmap_write(s->regmap, 0x1a, 0x00);
@@ -150,9 +149,8 @@ static int e4000_set_params(struct dvb_frontend *fe)
 	buf[3] = 0x00;
 	buf[4] = e4000_pll_lut[i].div;
 
-	dev_dbg(&s->client->dev,
-			"%s: f_vco=%llu pll div=%d sigma_delta=%04x\n",
-			__func__, f_vco, buf[0], sigma_delta);
+	dev_dbg(&s->client->dev, "f_vco=%llu pll div=%d sigma_delta=%04x\n",
+			f_vco, buf[0], sigma_delta);
 
 	ret = regmap_bulk_write(s->regmap, 0x09, buf, 5);
 	if (ret)
@@ -253,7 +251,7 @@ static int e4000_set_params(struct dvb_frontend *fe)
 		goto err;
 err:
 	if (ret)
-		dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&s->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -262,7 +260,7 @@ static int e4000_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 {
 	struct e4000 *s = fe->tuner_priv;
 
-	dev_dbg(&s->client->dev, "%s:\n", __func__);
+	dev_dbg(&s->client->dev, "\n");
 
 	*frequency = 0; /* Zero-IF */
 
@@ -276,10 +274,9 @@ static int e4000_set_lna_gain(struct dvb_frontend *fe)
 	int ret;
 	u8 u8tmp;
 
-	dev_dbg(&s->client->dev, "%s: lna auto=%d->%d val=%d->%d\n",
-			__func__, s->lna_gain_auto->cur.val,
-			s->lna_gain_auto->val, s->lna_gain->cur.val,
-			s->lna_gain->val);
+	dev_dbg(&s->client->dev, "lna auto=%d->%d val=%d->%d\n",
+			s->lna_gain_auto->cur.val, s->lna_gain_auto->val,
+			s->lna_gain->cur.val, s->lna_gain->val);
 
 	if (s->lna_gain_auto->val && s->if_gain_auto->cur.val)
 		u8tmp = 0x17;
@@ -301,7 +298,7 @@ static int e4000_set_lna_gain(struct dvb_frontend *fe)
 	}
 err:
 	if (ret)
-		dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&s->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -312,10 +309,9 @@ static int e4000_set_mixer_gain(struct dvb_frontend *fe)
 	int ret;
 	u8 u8tmp;
 
-	dev_dbg(&s->client->dev, "%s: mixer auto=%d->%d val=%d->%d\n",
-			__func__, s->mixer_gain_auto->cur.val,
-			s->mixer_gain_auto->val, s->mixer_gain->cur.val,
-			s->mixer_gain->val);
+	dev_dbg(&s->client->dev, "mixer auto=%d->%d val=%d->%d\n",
+			s->mixer_gain_auto->cur.val, s->mixer_gain_auto->val,
+			s->mixer_gain->cur.val, s->mixer_gain->val);
 
 	if (s->mixer_gain_auto->val)
 		u8tmp = 0x15;
@@ -333,7 +329,7 @@ static int e4000_set_mixer_gain(struct dvb_frontend *fe)
 	}
 err:
 	if (ret)
-		dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&s->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -345,10 +341,9 @@ static int e4000_set_if_gain(struct dvb_frontend *fe)
 	u8 buf[2];
 	u8 u8tmp;
 
-	dev_dbg(&s->client->dev, "%s: if auto=%d->%d val=%d->%d\n",
-			__func__, s->if_gain_auto->cur.val,
-			s->if_gain_auto->val, s->if_gain->cur.val,
-			s->if_gain->val);
+	dev_dbg(&s->client->dev, "if auto=%d->%d val=%d->%d\n",
+			s->if_gain_auto->cur.val, s->if_gain_auto->val,
+			s->if_gain->cur.val, s->if_gain->val);
 
 	if (s->if_gain_auto->val && s->lna_gain_auto->cur.val)
 		u8tmp = 0x17;
@@ -372,7 +367,7 @@ static int e4000_set_if_gain(struct dvb_frontend *fe)
 	}
 err:
 	if (ret)
-		dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&s->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -390,7 +385,7 @@ static int e4000_pll_lock(struct dvb_frontend *fe)
 	s->pll_lock->val = (utmp & 0x01);
 err:
 	if (ret)
-		dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&s->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -400,7 +395,7 @@ static int e4000_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 	struct e4000 *s = container_of(ctrl->handler, struct e4000, hdl);
 	int ret;
 
-	if (s->active == false)
+	if (!s->active)
 		return 0;
 
 	switch (ctrl->id) {
@@ -408,8 +403,8 @@ static int e4000_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 		ret = e4000_pll_lock(s->fe);
 		break;
 	default:
-		dev_dbg(&s->client->dev, "%s: unknown ctrl: id=%d name=%s\n",
-				__func__, ctrl->id, ctrl->name);
+		dev_dbg(&s->client->dev, "unknown ctrl: id=%d name=%s\n",
+				ctrl->id, ctrl->name);
 		ret = -EINVAL;
 	}
 
@@ -423,7 +418,7 @@ static int e4000_s_ctrl(struct v4l2_ctrl *ctrl)
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
 
-	if (s->active == false)
+	if (!s->active)
 		return 0;
 
 	switch (ctrl->id) {
@@ -445,8 +440,8 @@ static int e4000_s_ctrl(struct v4l2_ctrl *ctrl)
 		ret = e4000_set_if_gain(s->fe);
 		break;
 	default:
-		dev_dbg(&s->client->dev, "%s: unknown ctrl: id=%d name=%s\n",
-				__func__, ctrl->id, ctrl->name);
+		dev_dbg(&s->client->dev, "unknown ctrl: id=%d name=%s\n",
+				ctrl->id, ctrl->name);
 		ret = -EINVAL;
 	}
 
@@ -494,7 +489,7 @@ static int e4000_probe(struct i2c_client *client,
 	s = kzalloc(sizeof(struct e4000), GFP_KERNEL);
 	if (!s) {
 		ret = -ENOMEM;
-		dev_err(&client->dev, "%s: kzalloc() failed\n", KBUILD_MODNAME);
+		dev_err(&client->dev, "kzalloc() failed\n");
 		goto err;
 	}
 
@@ -512,7 +507,7 @@ static int e4000_probe(struct i2c_client *client,
 	if (ret)
 		goto err;
 
-	dev_dbg(&s->client->dev, "%s: chip id=%02x\n", __func__, utmp);
+	dev_dbg(&s->client->dev, "chip id=%02x\n", utmp);
 
 	if (utmp != 0x40) {
 		ret = -ENODEV;
@@ -559,9 +554,7 @@ static int e4000_probe(struct i2c_client *client,
 	s->sd.ctrl_handler = &s->hdl;
 #endif
 
-	dev_info(&s->client->dev,
-			"%s: Elonics E4000 successfully identified\n",
-			KBUILD_MODNAME);
+	dev_info(&s->client->dev, "Elonics E4000 successfully identified\n");
 
 	fe->tuner_priv = s;
 	memcpy(&fe->ops.tuner_ops, &e4000_tuner_ops,
@@ -573,7 +566,7 @@ static int e4000_probe(struct i2c_client *client,
 	return 0;
 err:
 	if (ret) {
-		dev_dbg(&client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&client->dev, "failed=%d\n", ret);
 		kfree(s);
 	}
 
@@ -586,7 +579,7 @@ static int e4000_remove(struct i2c_client *client)
 	struct e4000 *s = container_of(sd, struct e4000, sd);
 	struct dvb_frontend *fe = s->fe;
 
-	dev_dbg(&client->dev, "%s:\n", __func__);
+	dev_dbg(&client->dev, "\n");
 
 #if IS_ENABLED(CONFIG_VIDEO_V4L2)
 	v4l2_ctrl_handler_free(&s->hdl);
diff --git a/drivers/media/tuners/it913x.c b/drivers/media/tuners/it913x.c
new file mode 100644
index 000000000000..a076c87eda7a
--- /dev/null
+++ b/drivers/media/tuners/it913x.c
@@ -0,0 +1,478 @@
+/*
+ * ITE IT913X silicon tuner driver
+ *
+ *  Copyright (C) 2011 Malcolm Priestley (tvboxspy@gmail.com)
+ *  IT9137 Copyright (C) ITE Tech Inc.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.=
+ */
+
+#include "it913x.h"
+#include <linux/regmap.h>
+
+struct it913x_dev {
+	struct i2c_client *client;
+	struct regmap *regmap;
+	struct dvb_frontend *fe;
+	u8 chip_ver:2;
+	u8 role:2;
+	u16 xtal;
+	u8 fdiv;
+	u8 clk_mode;
+	u32 fn_min;
+	bool active;
+};
+
+static int it913x_init(struct dvb_frontend *fe)
+{
+	struct it913x_dev *dev = fe->tuner_priv;
+	int ret;
+	unsigned int utmp;
+	u8 iqik_m_cal, nv_val, buf[2];
+	static const u8 nv[] = {48, 32, 24, 16, 12, 8, 6, 4, 2};
+	unsigned long timeout;
+
+	dev_dbg(&dev->client->dev, "role %u\n", dev->role);
+
+	ret = regmap_write(dev->regmap, 0x80ec4c, 0x68);
+	if (ret)
+		goto err;
+
+	usleep_range(10000, 100000);
+
+	ret = regmap_read(dev->regmap, 0x80ec86, &utmp);
+	if (ret)
+		goto err;
+
+	switch (utmp) {
+	case 0:
+		/* 12.000 MHz */
+		dev->clk_mode = utmp;
+		dev->xtal = 2000;
+		dev->fdiv = 3;
+		iqik_m_cal = 16;
+		break;
+	case 1:
+		/* 20.480 MHz */
+		dev->clk_mode = utmp;
+		dev->xtal = 640;
+		dev->fdiv = 1;
+		iqik_m_cal = 6;
+		break;
+	default:
+		dev_err(&dev->client->dev, "unknown clock identifier %d\n", utmp);
+		goto err;
+	}
+
+	ret = regmap_read(dev->regmap, 0x80ed03,  &utmp);
+	if (ret)
+		goto err;
+
+	else if (utmp < ARRAY_SIZE(nv))
+		nv_val = nv[utmp];
+	else
+		nv_val = 2;
+
+	#define TIMEOUT 50
+	timeout = jiffies + msecs_to_jiffies(TIMEOUT);
+	while (!time_after(jiffies, timeout)) {
+		ret = regmap_bulk_read(dev->regmap, 0x80ed23, buf, 2);
+		if (ret)
+			goto err;
+
+		utmp = (buf[1] << 8) | (buf[0] << 0);
+		if (utmp)
+			break;
+	}
+
+	dev_dbg(&dev->client->dev, "r_fbc_m_bdry took %u ms, val %u\n",
+			jiffies_to_msecs(jiffies) -
+			(jiffies_to_msecs(timeout) - TIMEOUT), utmp);
+
+	dev->fn_min = dev->xtal * utmp;
+	dev->fn_min /= (dev->fdiv * nv_val);
+	dev->fn_min *= 1000;
+	dev_dbg(&dev->client->dev, "fn_min %u\n", dev->fn_min);
+
+	/*
+	 * Chip version BX never sets that flag so we just wait 50ms in that
+	 * case. It is possible poll BX similarly than AX and then timeout in
+	 * order to get 50ms delay, but that causes about 120 extra I2C
+	 * messages. As for now, we just wait and reduce IO.
+	 */
+	if (dev->chip_ver == 1) {
+		#define TIMEOUT 50
+		timeout = jiffies + msecs_to_jiffies(TIMEOUT);
+		while (!time_after(jiffies, timeout)) {
+			ret = regmap_read(dev->regmap, 0x80ec82, &utmp);
+			if (ret)
+				goto err;
+
+			if (utmp)
+				break;
+		}
+
+		dev_dbg(&dev->client->dev, "p_tsm_init_mode took %u ms, val %u\n",
+				jiffies_to_msecs(jiffies) -
+				(jiffies_to_msecs(timeout) - TIMEOUT), utmp);
+	} else {
+		msleep(50);
+	}
+
+	ret = regmap_write(dev->regmap, 0x80ed81, iqik_m_cal);
+	if (ret)
+		goto err;
+
+	ret = regmap_write(dev->regmap, 0x80ec57, 0x00);
+	if (ret)
+		goto err;
+
+	ret = regmap_write(dev->regmap, 0x80ec58, 0x00);
+	if (ret)
+		goto err;
+
+	ret = regmap_write(dev->regmap, 0x80ec40, 0x01);
+	if (ret)
+		goto err;
+
+	dev->active = true;
+
+	return 0;
+err:
+	dev_dbg(&dev->client->dev, "failed %d\n", ret);
+	return ret;
+}
+
+static int it913x_sleep(struct dvb_frontend *fe)
+{
+	struct it913x_dev *dev = fe->tuner_priv;
+	int ret, len;
+
+	dev_dbg(&dev->client->dev, "role %u\n", dev->role);
+
+	dev->active = false;
+
+	ret  = regmap_bulk_write(dev->regmap, 0x80ec40, "\x00", 1);
+	if (ret)
+		goto err;
+
+	/*
+	 * Writing '0x00' to master tuner register '0x80ec08' causes slave tuner
+	 * communication lost. Due to that, we cannot put master full sleep.
+	 */
+	if (dev->role == IT913X_ROLE_DUAL_MASTER)
+		len = 4;
+	else
+		len = 15;
+
+	dev_dbg(&dev->client->dev, "role %u, len %d\n", dev->role, len);
+
+	ret = regmap_bulk_write(dev->regmap, 0x80ec02,
+			"\x3f\x1f\x3f\x3e\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00",
+			len);
+	if (ret)
+		goto err;
+
+	ret = regmap_bulk_write(dev->regmap, 0x80ec12, "\x00\x00\x00\x00", 4);
+	if (ret)
+		goto err;
+
+	ret = regmap_bulk_write(dev->regmap, 0x80ec17,
+			"\x00\x00\x00\x00\x00\x00\x00\x00\x00", 9);
+	if (ret)
+		goto err;
+
+	ret = regmap_bulk_write(dev->regmap, 0x80ec22,
+			"\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00", 10);
+	if (ret)
+		goto err;
+
+	ret = regmap_bulk_write(dev->regmap, 0x80ec20, "\x00", 1);
+	if (ret)
+		goto err;
+
+	ret = regmap_bulk_write(dev->regmap, 0x80ec3f, "\x01", 1);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	dev_dbg(&dev->client->dev, "failed %d\n", ret);
+	return ret;
+}
+
+static int it913x_set_params(struct dvb_frontend *fe)
+{
+	struct it913x_dev *dev = fe->tuner_priv;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	int ret;
+	unsigned int utmp;
+	u32 pre_lo_freq, t_cal_freq;
+	u16 iqik_m_cal, n_div;
+	u8 u8tmp, n, l_band, lna_band;
+
+	dev_dbg(&dev->client->dev, "role=%u, frequency %u, bandwidth_hz %u\n",
+			dev->role, c->frequency, c->bandwidth_hz);
+
+	if (!dev->active) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	if (c->frequency <=         74000000) {
+		n_div = 48;
+		n = 0;
+	} else if (c->frequency <= 111000000) {
+		n_div = 32;
+		n = 1;
+	} else if (c->frequency <= 148000000) {
+		n_div = 24;
+		n = 2;
+	} else if (c->frequency <= 222000000) {
+		n_div = 16;
+		n = 3;
+	} else if (c->frequency <= 296000000) {
+		n_div = 12;
+		n = 4;
+	} else if (c->frequency <= 445000000) {
+		n_div = 8;
+		n = 5;
+	} else if (c->frequency <= dev->fn_min) {
+		n_div = 6;
+		n = 6;
+	} else if (c->frequency <= 950000000) {
+		n_div = 4;
+		n = 7;
+	} else {
+		n_div = 2;
+		n = 0;
+	}
+
+	ret = regmap_read(dev->regmap, 0x80ed81, &utmp);
+	if (ret)
+		goto err;
+
+	iqik_m_cal = utmp * n_div;
+
+	if (utmp < 0x20) {
+		if (dev->clk_mode == 0)
+			iqik_m_cal = (iqik_m_cal * 9) >> 5;
+		else
+			iqik_m_cal >>= 1;
+	} else {
+		iqik_m_cal = 0x40 - iqik_m_cal;
+		if (dev->clk_mode == 0)
+			iqik_m_cal = ~((iqik_m_cal * 9) >> 5);
+		else
+			iqik_m_cal = ~(iqik_m_cal >> 1);
+	}
+
+	t_cal_freq = (c->frequency / 1000) * n_div * dev->fdiv;
+	pre_lo_freq = t_cal_freq / dev->xtal;
+	utmp = pre_lo_freq * dev->xtal;
+
+	if ((t_cal_freq - utmp) >= (dev->xtal >> 1))
+		pre_lo_freq++;
+
+	pre_lo_freq += (u32) n << 13;
+	/* Frequency OMEGA_IQIK_M_CAL_MID*/
+	t_cal_freq = pre_lo_freq + (u32)iqik_m_cal;
+	dev_dbg(&dev->client->dev, "t_cal_freq %u, pre_lo_freq %u\n",
+			t_cal_freq, pre_lo_freq);
+
+	if (c->frequency <=         440000000) {
+		l_band = 0;
+		lna_band = 0;
+	} else if (c->frequency <=  484000000) {
+		l_band = 1;
+		lna_band = 1;
+	} else if (c->frequency <=  533000000) {
+		l_band = 1;
+		lna_band = 2;
+	} else if (c->frequency <=  587000000) {
+		l_band = 1;
+		lna_band = 3;
+	} else if (c->frequency <=  645000000) {
+		l_band = 1;
+		lna_band = 4;
+	} else if (c->frequency <=  710000000) {
+		l_band = 1;
+		lna_band = 5;
+	} else if (c->frequency <=  782000000) {
+		l_band = 1;
+		lna_band = 6;
+	} else if (c->frequency <=  860000000) {
+		l_band = 1;
+		lna_band = 7;
+	} else if (c->frequency <= 1492000000) {
+		l_band = 1;
+		lna_band = 0;
+	} else if (c->frequency <= 1685000000) {
+		l_band = 1;
+		lna_band = 1;
+	} else {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	/* XXX: latest windows driver does not set that at all */
+	ret = regmap_write(dev->regmap, 0x80ee06, lna_band);
+	if (ret)
+		goto err;
+
+	if (c->bandwidth_hz <=      5000000)
+		u8tmp = 0;
+	else if (c->bandwidth_hz <= 6000000)
+		u8tmp = 2;
+	else if (c->bandwidth_hz <= 7000000)
+		u8tmp = 4;
+	else
+		u8tmp = 6;       /* 8000000 */
+
+	ret = regmap_write(dev->regmap, 0x80ec56, u8tmp);
+	if (ret)
+		goto err;
+
+	/* XXX: latest windows driver sets different value (a8 != 68) */
+	ret = regmap_write(dev->regmap, 0x80ec4c, 0xa0 | (l_band << 3));
+	if (ret)
+		goto err;
+
+	ret = regmap_write(dev->regmap, 0x80ec4d, (t_cal_freq >> 0) & 0xff);
+	if (ret)
+		goto err;
+
+	ret = regmap_write(dev->regmap, 0x80ec4e, (t_cal_freq >> 8) & 0xff);
+	if (ret)
+		goto err;
+
+	ret = regmap_write(dev->regmap, 0x80011e, (pre_lo_freq >> 0) & 0xff);
+	if (ret)
+		goto err;
+
+	ret = regmap_write(dev->regmap, 0x80011f, (pre_lo_freq >> 8) & 0xff);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	dev_dbg(&dev->client->dev, "failed %d\n", ret);
+	return ret;
+}
+
+static const struct dvb_tuner_ops it913x_tuner_ops = {
+	.info = {
+		.name           = "ITE IT913X",
+		.frequency_min  = 174000000,
+		.frequency_max  = 862000000,
+	},
+
+	.init = it913x_init,
+	.sleep = it913x_sleep,
+	.set_params = it913x_set_params,
+};
+
+static int it913x_probe(struct i2c_client *client,
+		const struct i2c_device_id *id)
+{
+	struct it913x_config *cfg = client->dev.platform_data;
+	struct dvb_frontend *fe = cfg->fe;
+	struct it913x_dev *dev;
+	int ret;
+	char *chip_ver_str;
+	static const struct regmap_config regmap_config = {
+		.reg_bits = 24,
+		.val_bits = 8,
+	};
+
+	dev = kzalloc(sizeof(struct it913x_dev), GFP_KERNEL);
+	if (dev == NULL) {
+		ret = -ENOMEM;
+		dev_err(&client->dev, "kzalloc() failed\n");
+		goto err;
+	}
+
+	dev->client = client;
+	dev->fe = cfg->fe;
+	dev->chip_ver = cfg->chip_ver;
+	dev->role = cfg->role;
+	dev->regmap = regmap_init_i2c(client, &regmap_config);
+	if (IS_ERR(dev->regmap)) {
+		ret = PTR_ERR(dev->regmap);
+		goto err_kfree;
+	}
+
+	fe->tuner_priv = dev;
+	memcpy(&fe->ops.tuner_ops, &it913x_tuner_ops,
+			sizeof(struct dvb_tuner_ops));
+	i2c_set_clientdata(client, dev);
+
+	if (dev->chip_ver == 1)
+		chip_ver_str = "AX";
+	else if (dev->chip_ver == 2)
+		chip_ver_str = "BX";
+	else
+		chip_ver_str = "??";
+
+	dev_info(&dev->client->dev, "ITE IT913X %s successfully attached\n",
+			chip_ver_str);
+	dev_dbg(&dev->client->dev, "chip_ver %u, role %u\n",
+			dev->chip_ver, dev->role);
+	return 0;
+
+err_kfree:
+	kfree(dev);
+err:
+	dev_dbg(&client->dev, "failed %d\n", ret);
+	return ret;
+}
+
+static int it913x_remove(struct i2c_client *client)
+{
+	struct it913x_dev *dev = i2c_get_clientdata(client);
+	struct dvb_frontend *fe = dev->fe;
+
+	dev_dbg(&client->dev, "\n");
+
+	memset(&fe->ops.tuner_ops, 0, sizeof(struct dvb_tuner_ops));
+	fe->tuner_priv = NULL;
+	regmap_exit(dev->regmap);
+	kfree(dev);
+
+	return 0;
+}
+
+static const struct i2c_device_id it913x_id_table[] = {
+	{"it913x", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, it913x_id_table);
+
+static struct i2c_driver it913x_driver = {
+	.driver = {
+		.owner	= THIS_MODULE,
+		.name	= "it913x",
+	},
+	.probe		= it913x_probe,
+	.remove		= it913x_remove,
+	.id_table	= it913x_id_table,
+};
+
+module_i2c_driver(it913x_driver);
+
+MODULE_DESCRIPTION("ITE IT913X silicon tuner driver");
+MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/tuners/tuner_it913x.h b/drivers/media/tuners/it913x.h
index 12dd36bd9e79..33de53d4a566 100644
--- a/drivers/media/tuners/tuner_it913x.h
+++ b/drivers/media/tuners/it913x.h
@@ -25,21 +25,30 @@
 
 #include "dvb_frontend.h"
 
-#if defined(CONFIG_MEDIA_TUNER_IT913X) || \
-	(defined(CONFIG_MEDIA_TUNER_IT913X_MODULE) && defined(MODULE))
-extern struct dvb_frontend *it913x_attach(struct dvb_frontend *fe,
-	struct i2c_adapter *i2c_adap,
-	u8 i2c_addr,
-	u8 config);
-#else
-static inline struct dvb_frontend *it913x_attach(struct dvb_frontend *fe,
-	struct i2c_adapter *i2c_adap,
-	u8 i2c_addr,
-	u8 config)
-{
-	pr_warn("%s: driver disabled by Kconfig\n", __func__);
-	return NULL;
-}
-#endif
+/*
+ * I2C address
+ * 0x38, 0x3a, 0x3c, 0x3e
+ */
+struct it913x_config {
+	/*
+	 * pointer to DVB frontend
+	 */
+	struct dvb_frontend *fe;
+
+	/*
+	 * chip version
+	 * 1 = IT9135 AX
+	 * 2 = IT9135 BX
+	 */
+	unsigned int chip_ver:2;
+
+	/*
+	 * tuner role
+	 */
+#define IT913X_ROLE_SINGLE         0
+#define IT913X_ROLE_DUAL_MASTER    1
+#define IT913X_ROLE_DUAL_SLAVE     2
+	unsigned int role:2;
+};
 
 #endif
diff --git a/drivers/media/tuners/m88ts2022.c b/drivers/media/tuners/m88ts2022.c
index 40c42dec721b..caa542346891 100644
--- a/drivers/media/tuners/m88ts2022.c
+++ b/drivers/media/tuners/m88ts2022.c
@@ -18,120 +18,11 @@
 
 #include "m88ts2022_priv.h"
 
-/* write multiple registers */
-static int m88ts2022_wr_regs(struct m88ts2022_priv *priv,
-		u8 reg, const u8 *val, int len)
+static int m88ts2022_cmd(struct m88ts2022_dev *dev, int op, int sleep, u8 reg,
+		u8 mask, u8 val, u8 *reg_val)
 {
-#define MAX_WR_LEN 3
-#define MAX_WR_XFER_LEN (MAX_WR_LEN + 1)
-	int ret;
-	u8 buf[MAX_WR_XFER_LEN];
-	struct i2c_msg msg[1] = {
-		{
-			.addr = priv->client->addr,
-			.flags = 0,
-			.len = 1 + len,
-			.buf = buf,
-		}
-	};
-
-	if (WARN_ON(len > MAX_WR_LEN))
-		return -EINVAL;
-
-	buf[0] = reg;
-	memcpy(&buf[1], val, len);
-
-	ret = i2c_transfer(priv->client->adapter, msg, 1);
-	if (ret == 1) {
-		ret = 0;
-	} else {
-		dev_warn(&priv->client->dev,
-				"%s: i2c wr failed=%d reg=%02x len=%d\n",
-				KBUILD_MODNAME, ret, reg, len);
-		ret = -EREMOTEIO;
-	}
-
-	return ret;
-}
-
-/* read multiple registers */
-static int m88ts2022_rd_regs(struct m88ts2022_priv *priv, u8 reg,
-		u8 *val, int len)
-{
-#define MAX_RD_LEN 1
-#define MAX_RD_XFER_LEN (MAX_RD_LEN)
-	int ret;
-	u8 buf[MAX_RD_XFER_LEN];
-	struct i2c_msg msg[2] = {
-		{
-			.addr = priv->client->addr,
-			.flags = 0,
-			.len = 1,
-			.buf = &reg,
-		}, {
-			.addr = priv->client->addr,
-			.flags = I2C_M_RD,
-			.len = len,
-			.buf = buf,
-		}
-	};
-
-	if (WARN_ON(len > MAX_RD_LEN))
-		return -EINVAL;
-
-	ret = i2c_transfer(priv->client->adapter, msg, 2);
-	if (ret == 2) {
-		memcpy(val, buf, len);
-		ret = 0;
-	} else {
-		dev_warn(&priv->client->dev,
-				"%s: i2c rd failed=%d reg=%02x len=%d\n",
-				KBUILD_MODNAME, ret, reg, len);
-		ret = -EREMOTEIO;
-	}
-
-	return ret;
-}
-
-/* write single register */
-static int m88ts2022_wr_reg(struct m88ts2022_priv *priv, u8 reg, u8 val)
-{
-	return m88ts2022_wr_regs(priv, reg, &val, 1);
-}
-
-/* read single register */
-static int m88ts2022_rd_reg(struct m88ts2022_priv *priv, u8 reg, u8 *val)
-{
-	return m88ts2022_rd_regs(priv, reg, val, 1);
-}
-
-/* write single register with mask */
-static int m88ts2022_wr_reg_mask(struct m88ts2022_priv *priv,
-		u8 reg, u8 val, u8 mask)
-{
-	int ret;
-	u8 u8tmp;
-
-	/* no need for read if whole reg is written */
-	if (mask != 0xff) {
-		ret = m88ts2022_rd_regs(priv, reg, &u8tmp, 1);
-		if (ret)
-			return ret;
-
-		val &= mask;
-		u8tmp &= ~mask;
-		val |= u8tmp;
-	}
-
-	return m88ts2022_wr_regs(priv, reg, &val, 1);
-}
-
-static int m88ts2022_cmd(struct dvb_frontend *fe,
-		int op, int sleep, u8 reg, u8 mask, u8 val, u8 *reg_val)
-{
-	struct m88ts2022_priv *priv = fe->tuner_priv;
 	int ret, i;
-	u8 u8tmp;
+	unsigned int utmp;
 	struct m88ts2022_reg_val reg_vals[] = {
 		{0x51, 0x1f - op},
 		{0x51, 0x1f},
@@ -140,12 +31,12 @@ static int m88ts2022_cmd(struct dvb_frontend *fe,
 	};
 
 	for (i = 0; i < 2; i++) {
-		dev_dbg(&priv->client->dev,
-				"%s: i=%d op=%02x reg=%02x mask=%02x val=%02x\n",
-				__func__, i, op, reg, mask, val);
+		dev_dbg(&dev->client->dev,
+				"i=%d op=%02x reg=%02x mask=%02x val=%02x\n",
+				i, op, reg, mask, val);
 
 		for (i = 0; i < ARRAY_SIZE(reg_vals); i++) {
-			ret = m88ts2022_wr_reg(priv, reg_vals[i].reg,
+			ret = regmap_write(dev->regmap, reg_vals[i].reg,
 					reg_vals[i].val);
 			if (ret)
 				goto err;
@@ -153,37 +44,38 @@ static int m88ts2022_cmd(struct dvb_frontend *fe,
 
 		usleep_range(sleep * 1000, sleep * 10000);
 
-		ret = m88ts2022_rd_reg(priv, reg, &u8tmp);
+		ret = regmap_read(dev->regmap, reg, &utmp);
 		if (ret)
 			goto err;
 
-		if ((u8tmp & mask) != val)
+		if ((utmp & mask) != val)
 			break;
 	}
 
 	if (reg_val)
-		*reg_val = u8tmp;
+		*reg_val = utmp;
 err:
 	return ret;
 }
 
 static int m88ts2022_set_params(struct dvb_frontend *fe)
 {
-	struct m88ts2022_priv *priv = fe->tuner_priv;
+	struct m88ts2022_dev *dev = fe->tuner_priv;
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret;
-	unsigned int frequency_khz, frequency_offset_khz, f_3db_hz;
+	unsigned int utmp, frequency_khz, frequency_offset_khz, f_3db_hz;
 	unsigned int f_ref_khz, f_vco_khz, div_ref, div_out, pll_n, gdiv28;
 	u8 buf[3], u8tmp, cap_code, lpf_gm, lpf_mxdiv, div_max, div_min;
 	u16 u16tmp;
-	dev_dbg(&priv->client->dev,
-			"%s: frequency=%d symbol_rate=%d rolloff=%d\n",
-			__func__, c->frequency, c->symbol_rate, c->rolloff);
+
+	dev_dbg(&dev->client->dev,
+			"frequency=%d symbol_rate=%d rolloff=%d\n",
+			c->frequency, c->symbol_rate, c->rolloff);
 	/*
 	 * Integer-N PLL synthesizer
 	 * kHz is used for all calculations to keep calculations within 32-bit
 	 */
-	f_ref_khz = DIV_ROUND_CLOSEST(priv->cfg.clock, 1000);
+	f_ref_khz = DIV_ROUND_CLOSEST(dev->cfg.clock, 1000);
 	div_ref = DIV_ROUND_CLOSEST(f_ref_khz, 2000);
 
 	if (c->symbol_rate < 5000000)
@@ -203,14 +95,14 @@ static int m88ts2022_set_params(struct dvb_frontend *fe)
 
 	buf[0] = u8tmp;
 	buf[1] = 0x40;
-	ret = m88ts2022_wr_regs(priv, 0x10, buf, 2);
+	ret = regmap_bulk_write(dev->regmap, 0x10, buf, 2);
 	if (ret)
 		goto err;
 
 	f_vco_khz = frequency_khz * div_out;
 	pll_n = f_vco_khz * div_ref / f_ref_khz;
 	pll_n += pll_n % 2;
-	priv->frequency_khz = pll_n * f_ref_khz / div_ref / div_out;
+	dev->frequency_khz = pll_n * f_ref_khz / div_ref / div_out;
 
 	if (pll_n < 4095)
 		u16tmp = pll_n - 1024;
@@ -222,88 +114,87 @@ static int m88ts2022_set_params(struct dvb_frontend *fe)
 	buf[0] = (u16tmp >> 8) & 0x3f;
 	buf[1] = (u16tmp >> 0) & 0xff;
 	buf[2] = div_ref - 8;
-	ret = m88ts2022_wr_regs(priv, 0x01, buf, 3);
+	ret = regmap_bulk_write(dev->regmap, 0x01, buf, 3);
 	if (ret)
 		goto err;
 
-	dev_dbg(&priv->client->dev,
-			"%s: frequency=%u offset=%d f_vco_khz=%u pll_n=%u div_ref=%u div_out=%u\n",
-			__func__, priv->frequency_khz,
-			priv->frequency_khz - c->frequency, f_vco_khz, pll_n,
-			div_ref, div_out);
+	dev_dbg(&dev->client->dev,
+			"frequency=%u offset=%d f_vco_khz=%u pll_n=%u div_ref=%u div_out=%u\n",
+			dev->frequency_khz, dev->frequency_khz - c->frequency,
+			f_vco_khz, pll_n, div_ref, div_out);
 
-	ret = m88ts2022_cmd(fe, 0x10, 5, 0x15, 0x40, 0x00, NULL);
+	ret = m88ts2022_cmd(dev, 0x10, 5, 0x15, 0x40, 0x00, NULL);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_rd_reg(priv, 0x14, &u8tmp);
+	ret = regmap_read(dev->regmap, 0x14, &utmp);
 	if (ret)
 		goto err;
 
-	u8tmp &= 0x7f;
-	if (u8tmp < 64) {
-		ret = m88ts2022_wr_reg_mask(priv, 0x10, 0x80, 0x80);
+	utmp &= 0x7f;
+	if (utmp < 64) {
+		ret = regmap_update_bits(dev->regmap, 0x10, 0x80, 0x80);
 		if (ret)
 			goto err;
 
-		ret = m88ts2022_wr_reg(priv, 0x11, 0x6f);
+		ret = regmap_write(dev->regmap, 0x11, 0x6f);
 		if (ret)
 			goto err;
 
-		ret = m88ts2022_cmd(fe, 0x10, 5, 0x15, 0x40, 0x00, NULL);
+		ret = m88ts2022_cmd(dev, 0x10, 5, 0x15, 0x40, 0x00, NULL);
 		if (ret)
 			goto err;
 	}
 
-	ret = m88ts2022_rd_reg(priv, 0x14, &u8tmp);
+	ret = regmap_read(dev->regmap, 0x14, &utmp);
 	if (ret)
 		goto err;
 
-	u8tmp &= 0x1f;
-	if (u8tmp > 19) {
-		ret = m88ts2022_wr_reg_mask(priv, 0x10, 0x00, 0x02);
+	utmp &= 0x1f;
+	if (utmp > 19) {
+		ret = regmap_update_bits(dev->regmap, 0x10, 0x02, 0x00);
 		if (ret)
 			goto err;
 	}
 
-	ret = m88ts2022_cmd(fe, 0x08, 5, 0x3c, 0xff, 0x00, NULL);
+	ret = m88ts2022_cmd(dev, 0x08, 5, 0x3c, 0xff, 0x00, NULL);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_wr_reg(priv, 0x25, 0x00);
+	ret = regmap_write(dev->regmap, 0x25, 0x00);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_wr_reg(priv, 0x27, 0x70);
+	ret = regmap_write(dev->regmap, 0x27, 0x70);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_wr_reg(priv, 0x41, 0x09);
+	ret = regmap_write(dev->regmap, 0x41, 0x09);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_wr_reg(priv, 0x08, 0x0b);
+	ret = regmap_write(dev->regmap, 0x08, 0x0b);
 	if (ret)
 		goto err;
 
 	/* filters */
 	gdiv28 = DIV_ROUND_CLOSEST(f_ref_khz * 1694U, 1000000U);
 
-	ret = m88ts2022_wr_reg(priv, 0x04, gdiv28);
+	ret = regmap_write(dev->regmap, 0x04, gdiv28);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_cmd(fe, 0x04, 2, 0x26, 0xff, 0x00, &u8tmp);
+	ret = m88ts2022_cmd(dev, 0x04, 2, 0x26, 0xff, 0x00, &u8tmp);
 	if (ret)
 		goto err;
 
 	cap_code = u8tmp & 0x3f;
 
-	ret = m88ts2022_wr_reg(priv, 0x41, 0x0d);
+	ret = regmap_write(dev->regmap, 0x41, 0x0d);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_cmd(fe, 0x04, 2, 0x26, 0xff, 0x00, &u8tmp);
+	ret = m88ts2022_cmd(dev, 0x04, 2, 0x26, 0xff, 0x00, &u8tmp);
 	if (ret)
 		goto err;
 
@@ -314,7 +205,7 @@ static int m88ts2022_set_params(struct dvb_frontend *fe)
 	div_min = gdiv28 * 78 / 100;
 	div_max = clamp_val(div_max, 0U, 63U);
 
-	f_3db_hz = c->symbol_rate * 135UL / 200UL;
+	f_3db_hz = mult_frac(c->symbol_rate, 135, 200);
 	f_3db_hz +=  2000000U + (frequency_offset_khz * 1000U);
 	f_3db_hz = clamp(f_3db_hz, 7000000U, 40000000U);
 
@@ -327,25 +218,25 @@ static int m88ts2022_set_params(struct dvb_frontend *fe)
 		lpf_mxdiv = DIV_ROUND_CLOSEST(++lpf_gm * LPF_COEFF * f_ref_khz, f_3db_hz);
 	lpf_mxdiv = clamp_val(lpf_mxdiv, 0U, div_max);
 
-	ret = m88ts2022_wr_reg(priv, 0x04, lpf_mxdiv);
+	ret = regmap_write(dev->regmap, 0x04, lpf_mxdiv);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_wr_reg(priv, 0x06, lpf_gm);
+	ret = regmap_write(dev->regmap, 0x06, lpf_gm);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_cmd(fe, 0x04, 2, 0x26, 0xff, 0x00, &u8tmp);
+	ret = m88ts2022_cmd(dev, 0x04, 2, 0x26, 0xff, 0x00, &u8tmp);
 	if (ret)
 		goto err;
 
 	cap_code = u8tmp & 0x3f;
 
-	ret = m88ts2022_wr_reg(priv, 0x41, 0x09);
+	ret = regmap_write(dev->regmap, 0x41, 0x09);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_cmd(fe, 0x04, 2, 0x26, 0xff, 0x00, &u8tmp);
+	ret = m88ts2022_cmd(dev, 0x04, 2, 0x26, 0xff, 0x00, &u8tmp);
 	if (ret)
 		goto err;
 
@@ -353,31 +244,31 @@ static int m88ts2022_set_params(struct dvb_frontend *fe)
 	cap_code = (cap_code + u8tmp) / 2;
 
 	u8tmp = cap_code | 0x80;
-	ret = m88ts2022_wr_reg(priv, 0x25, u8tmp);
+	ret = regmap_write(dev->regmap, 0x25, u8tmp);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_wr_reg(priv, 0x27, 0x30);
+	ret = regmap_write(dev->regmap, 0x27, 0x30);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_wr_reg(priv, 0x08, 0x09);
+	ret = regmap_write(dev->regmap, 0x08, 0x09);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_cmd(fe, 0x01, 20, 0x21, 0xff, 0x00, NULL);
+	ret = m88ts2022_cmd(dev, 0x01, 20, 0x21, 0xff, 0x00, NULL);
 	if (ret)
 		goto err;
 err:
 	if (ret)
-		dev_dbg(&priv->client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 
 	return ret;
 }
 
 static int m88ts2022_init(struct dvb_frontend *fe)
 {
-	struct m88ts2022_priv *priv = fe->tuner_priv;
+	struct m88ts2022_dev *dev = fe->tuner_priv;
 	int ret, i;
 	u8 u8tmp;
 	static const struct m88ts2022_reg_val reg_vals[] = {
@@ -393,23 +284,24 @@ static int m88ts2022_init(struct dvb_frontend *fe)
 		{0x24, 0x02},
 		{0x12, 0xa0},
 	};
-	dev_dbg(&priv->client->dev, "%s:\n", __func__);
 
-	ret = m88ts2022_wr_reg(priv, 0x00, 0x01);
+	dev_dbg(&dev->client->dev, "\n");
+
+	ret = regmap_write(dev->regmap, 0x00, 0x01);
 	if (ret)
 		goto err;
 
-	ret = m88ts2022_wr_reg(priv, 0x00, 0x03);
+	ret = regmap_write(dev->regmap, 0x00, 0x03);
 	if (ret)
 		goto err;
 
-	switch (priv->cfg.clock_out) {
+	switch (dev->cfg.clock_out) {
 	case M88TS2022_CLOCK_OUT_DISABLED:
 		u8tmp = 0x60;
 		break;
 	case M88TS2022_CLOCK_OUT_ENABLED:
 		u8tmp = 0x70;
-		ret = m88ts2022_wr_reg(priv, 0x05, priv->cfg.clock_out_div);
+		ret = regmap_write(dev->regmap, 0x05, dev->cfg.clock_out_div);
 		if (ret)
 			goto err;
 		break;
@@ -420,58 +312,61 @@ static int m88ts2022_init(struct dvb_frontend *fe)
 		goto err;
 	}
 
-	ret = m88ts2022_wr_reg(priv, 0x42, u8tmp);
+	ret = regmap_write(dev->regmap, 0x42, u8tmp);
 	if (ret)
 		goto err;
 
-	if (priv->cfg.loop_through)
+	if (dev->cfg.loop_through)
 		u8tmp = 0xec;
 	else
 		u8tmp = 0x6c;
 
-	ret = m88ts2022_wr_reg(priv, 0x62, u8tmp);
+	ret = regmap_write(dev->regmap, 0x62, u8tmp);
 	if (ret)
 		goto err;
 
 	for (i = 0; i < ARRAY_SIZE(reg_vals); i++) {
-		ret = m88ts2022_wr_reg(priv, reg_vals[i].reg, reg_vals[i].val);
+		ret = regmap_write(dev->regmap, reg_vals[i].reg, reg_vals[i].val);
 		if (ret)
 			goto err;
 	}
 err:
 	if (ret)
-		dev_dbg(&priv->client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
 static int m88ts2022_sleep(struct dvb_frontend *fe)
 {
-	struct m88ts2022_priv *priv = fe->tuner_priv;
+	struct m88ts2022_dev *dev = fe->tuner_priv;
 	int ret;
-	dev_dbg(&priv->client->dev, "%s:\n", __func__);
 
-	ret = m88ts2022_wr_reg(priv, 0x00, 0x00);
+	dev_dbg(&dev->client->dev, "\n");
+
+	ret = regmap_write(dev->regmap, 0x00, 0x00);
 	if (ret)
 		goto err;
 err:
 	if (ret)
-		dev_dbg(&priv->client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
 static int m88ts2022_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 {
-	struct m88ts2022_priv *priv = fe->tuner_priv;
-	dev_dbg(&priv->client->dev, "%s:\n", __func__);
+	struct m88ts2022_dev *dev = fe->tuner_priv;
 
-	*frequency = priv->frequency_khz;
+	dev_dbg(&dev->client->dev, "\n");
+
+	*frequency = dev->frequency_khz;
 	return 0;
 }
 
 static int m88ts2022_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 {
-	struct m88ts2022_priv *priv = fe->tuner_priv;
-	dev_dbg(&priv->client->dev, "%s:\n", __func__);
+	struct m88ts2022_dev *dev = fe->tuner_priv;
+
+	dev_dbg(&dev->client->dev, "\n");
 
 	*frequency = 0; /* Zero-IF */
 	return 0;
@@ -479,31 +374,30 @@ static int m88ts2022_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static int m88ts2022_get_rf_strength(struct dvb_frontend *fe, u16 *strength)
 {
-	struct m88ts2022_priv *priv = fe->tuner_priv;
+	struct m88ts2022_dev *dev = fe->tuner_priv;
 	int ret;
-	u8 u8tmp;
 	u16 gain, u16tmp;
-	unsigned int gain1, gain2, gain3;
+	unsigned int utmp, gain1, gain2, gain3;
 
-	ret = m88ts2022_rd_reg(priv, 0x3d, &u8tmp);
+	ret = regmap_read(dev->regmap, 0x3d, &utmp);
 	if (ret)
 		goto err;
 
-	gain1 = (u8tmp >> 0) & 0x1f;
+	gain1 = (utmp >> 0) & 0x1f;
 	gain1 = clamp(gain1, 0U, 15U);
 
-	ret = m88ts2022_rd_reg(priv, 0x21, &u8tmp);
+	ret = regmap_read(dev->regmap, 0x21, &utmp);
 	if (ret)
 		goto err;
 
-	gain2 = (u8tmp >> 0) & 0x1f;
+	gain2 = (utmp >> 0) & 0x1f;
 	gain2 = clamp(gain2, 2U, 16U);
 
-	ret = m88ts2022_rd_reg(priv, 0x66, &u8tmp);
+	ret = regmap_read(dev->regmap, 0x66, &utmp);
 	if (ret)
 		goto err;
 
-	gain3 = (u8tmp >> 3) & 0x07;
+	gain3 = (utmp >> 3) & 0x07;
 	gain3 = clamp(gain3, 0U, 6U);
 
 	gain = gain1 * 265 + gain2 * 338 + gain3 * 285;
@@ -515,7 +409,7 @@ static int m88ts2022_get_rf_strength(struct dvb_frontend *fe, u16 *strength)
 	*strength = (u16tmp - 59000) * 0xffff / (61500 - 59000);
 err:
 	if (ret)
-		dev_dbg(&priv->client->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -540,46 +434,56 @@ static int m88ts2022_probe(struct i2c_client *client,
 {
 	struct m88ts2022_config *cfg = client->dev.platform_data;
 	struct dvb_frontend *fe = cfg->fe;
-	struct m88ts2022_priv *priv;
+	struct m88ts2022_dev *dev;
 	int ret;
-	u8 chip_id, u8tmp;
+	u8 u8tmp;
+	unsigned int utmp;
+	static const struct regmap_config regmap_config = {
+		.reg_bits = 8,
+		.val_bits = 8,
+	};
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev) {
 		ret = -ENOMEM;
-		dev_err(&client->dev, "%s: kzalloc() failed\n", KBUILD_MODNAME);
+		dev_err(&client->dev, "kzalloc() failed\n");
 		goto err;
 	}
 
-	memcpy(&priv->cfg, cfg, sizeof(struct m88ts2022_config));
-	priv->client = client;
+	memcpy(&dev->cfg, cfg, sizeof(struct m88ts2022_config));
+	dev->client = client;
+	dev->regmap = devm_regmap_init_i2c(client, &regmap_config);
+	if (IS_ERR(dev->regmap)) {
+		ret = PTR_ERR(dev->regmap);
+		goto err;
+	}
 
 	/* check if the tuner is there */
-	ret = m88ts2022_rd_reg(priv, 0x00, &u8tmp);
+	ret = regmap_read(dev->regmap, 0x00, &utmp);
 	if (ret)
 		goto err;
 
-	if ((u8tmp & 0x03) == 0x00) {
-		ret = m88ts2022_wr_reg(priv, 0x00, 0x01);
-		if (ret < 0)
+	if ((utmp & 0x03) == 0x00) {
+		ret = regmap_write(dev->regmap, 0x00, 0x01);
+		if (ret)
 			goto err;
 
 		usleep_range(2000, 50000);
 	}
 
-	ret = m88ts2022_wr_reg(priv, 0x00, 0x03);
+	ret = regmap_write(dev->regmap, 0x00, 0x03);
 	if (ret)
 		goto err;
 
 	usleep_range(2000, 50000);
 
-	ret = m88ts2022_rd_reg(priv, 0x00, &chip_id);
+	ret = regmap_read(dev->regmap, 0x00, &utmp);
 	if (ret)
 		goto err;
 
-	dev_dbg(&priv->client->dev, "%s: chip_id=%02x\n", __func__, chip_id);
+	dev_dbg(&dev->client->dev, "chip_id=%02x\n", utmp);
 
-	switch (chip_id) {
+	switch (utmp) {
 	case 0xc3:
 	case 0x83:
 		break;
@@ -587,13 +491,13 @@ static int m88ts2022_probe(struct i2c_client *client,
 		goto err;
 	}
 
-	switch (priv->cfg.clock_out) {
+	switch (dev->cfg.clock_out) {
 	case M88TS2022_CLOCK_OUT_DISABLED:
 		u8tmp = 0x60;
 		break;
 	case M88TS2022_CLOCK_OUT_ENABLED:
 		u8tmp = 0x70;
-		ret = m88ts2022_wr_reg(priv, 0x05, priv->cfg.clock_out_div);
+		ret = regmap_write(dev->regmap, 0x05, dev->cfg.clock_out_div);
 		if (ret)
 			goto err;
 		break;
@@ -604,49 +508,48 @@ static int m88ts2022_probe(struct i2c_client *client,
 		goto err;
 	}
 
-	ret = m88ts2022_wr_reg(priv, 0x42, u8tmp);
+	ret = regmap_write(dev->regmap, 0x42, u8tmp);
 	if (ret)
 		goto err;
 
-	if (priv->cfg.loop_through)
+	if (dev->cfg.loop_through)
 		u8tmp = 0xec;
 	else
 		u8tmp = 0x6c;
 
-	ret = m88ts2022_wr_reg(priv, 0x62, u8tmp);
+	ret = regmap_write(dev->regmap, 0x62, u8tmp);
 	if (ret)
 		goto err;
 
 	/* sleep */
-	ret = m88ts2022_wr_reg(priv, 0x00, 0x00);
+	ret = regmap_write(dev->regmap, 0x00, 0x00);
 	if (ret)
 		goto err;
 
-	dev_info(&priv->client->dev,
-			"%s: Montage M88TS2022 successfully identified\n",
-			KBUILD_MODNAME);
+	dev_info(&dev->client->dev, "Montage M88TS2022 successfully identified\n");
 
-	fe->tuner_priv = priv;
+	fe->tuner_priv = dev;
 	memcpy(&fe->ops.tuner_ops, &m88ts2022_tuner_ops,
 			sizeof(struct dvb_tuner_ops));
 
-	i2c_set_clientdata(client, priv);
+	i2c_set_clientdata(client, dev);
 	return 0;
 err:
-	dev_dbg(&client->dev, "%s: failed=%d\n", __func__, ret);
-	kfree(priv);
+	dev_dbg(&client->dev, "failed=%d\n", ret);
+	kfree(dev);
 	return ret;
 }
 
 static int m88ts2022_remove(struct i2c_client *client)
 {
-	struct m88ts2022_priv *priv = i2c_get_clientdata(client);
-	struct dvb_frontend *fe = priv->cfg.fe;
-	dev_dbg(&client->dev, "%s:\n", __func__);
+	struct m88ts2022_dev *dev = i2c_get_clientdata(client);
+	struct dvb_frontend *fe = dev->cfg.fe;
+
+	dev_dbg(&client->dev, "\n");
 
 	memset(&fe->ops.tuner_ops, 0, sizeof(struct dvb_tuner_ops));
 	fe->tuner_priv = NULL;
-	kfree(priv);
+	kfree(dev);
 
 	return 0;
 }
diff --git a/drivers/media/tuners/m88ts2022_priv.h b/drivers/media/tuners/m88ts2022_priv.h
index 0363dd866a2d..feeb5ad6beef 100644
--- a/drivers/media/tuners/m88ts2022_priv.h
+++ b/drivers/media/tuners/m88ts2022_priv.h
@@ -18,11 +18,12 @@
 #define M88TS2022_PRIV_H
 
 #include "m88ts2022.h"
+#include <linux/regmap.h>
 
-struct m88ts2022_priv {
+struct m88ts2022_dev {
 	struct m88ts2022_config cfg;
 	struct i2c_client *client;
-	struct dvb_frontend *fe;
+	struct regmap *regmap;
 	u32 frequency_khz;
 };
 
diff --git a/drivers/media/tuners/msi001.c b/drivers/media/tuners/msi001.c
index ee99e372c943..26019e731993 100644
--- a/drivers/media/tuners/msi001.c
+++ b/drivers/media/tuners/msi001.c
@@ -67,7 +67,8 @@ static int msi001_set_gain(struct msi001 *s, int lna_gain, int mixer_gain,
 {
 	int ret;
 	u32 reg;
-	dev_dbg(&s->spi->dev, "%s: lna=%d mixer=%d if=%d\n", __func__,
+
+	dev_dbg(&s->spi->dev, "lna=%d mixer=%d if=%d\n",
 			lna_gain, mixer_gain, if_gain);
 
 	reg = 1 << 0;
@@ -83,7 +84,7 @@ static int msi001_set_gain(struct msi001 *s, int lna_gain, int mixer_gain,
 
 	return 0;
 err:
-	dev_dbg(&s->spi->dev, "%s: failed %d\n", __func__, ret);
+	dev_dbg(&s->spi->dev, "failed %d\n", ret);
 	return ret;
 };
 
@@ -94,6 +95,7 @@ static int msi001_set_tuner(struct msi001 *s)
 	u32 reg;
 	u64 f_vco, tmp64;
 	u8 mode, filter_mode, lo_div;
+
 	static const struct {
 		u32 rf;
 		u8 mode;
@@ -145,9 +147,7 @@ static int msi001_set_tuner(struct msi001 *s)
 	#define R_REF 4
 	#define F_OUT_STEP 1
 
-	dev_dbg(&s->spi->dev,
-			"%s: f_rf=%d f_if=%d\n",
-			__func__, f_rf, f_if);
+	dev_dbg(&s->spi->dev, "f_rf=%d f_if=%d\n", f_rf, f_if);
 
 	for (i = 0; i < ARRAY_SIZE(band_lut); i++) {
 		if (f_rf <= band_lut[i].rf) {
@@ -198,8 +198,7 @@ static int msi001_set_tuner(struct msi001 *s)
 
 	s->bandwidth->val = bandwidth_lut[i].freq;
 
-	dev_dbg(&s->spi->dev, "%s: bandwidth selected=%d\n",
-			__func__, bandwidth_lut[i].freq);
+	dev_dbg(&s->spi->dev, "bandwidth selected=%d\n", bandwidth_lut[i].freq);
 
 	f_vco = (u64) (f_rf + f_if + f_if1) * lo_div;
 	tmp64 = f_vco;
@@ -225,9 +224,8 @@ static int msi001_set_tuner(struct msi001 *s)
 	tmp += 1ul * F_REF * R_REF * frac / thresh;
 	tmp /= lo_div;
 
-	dev_dbg(&s->spi->dev,
-			"%s: rf=%u:%u n=%d thresh=%d frac=%d\n",
-				__func__, f_rf, tmp, n, thresh, frac);
+	dev_dbg(&s->spi->dev, "rf=%u:%u n=%d thresh=%d frac=%d\n",
+				f_rf, tmp, n, thresh, frac);
 
 	ret = msi001_wreg(s, 0x00000e);
 	if (ret)
@@ -276,7 +274,7 @@ static int msi001_set_tuner(struct msi001 *s)
 
 	return 0;
 err:
-	dev_dbg(&s->spi->dev, "%s: failed %d\n", __func__, ret);
+	dev_dbg(&s->spi->dev, "failed %d\n", ret);
 	return ret;
 };
 
@@ -284,7 +282,8 @@ static int msi001_s_power(struct v4l2_subdev *sd, int on)
 {
 	struct msi001 *s = sd_to_msi001(sd);
 	int ret;
-	dev_dbg(&s->spi->dev, "%s: on=%d\n", __func__, on);
+
+	dev_dbg(&s->spi->dev, "on=%d\n", on);
 
 	if (on)
 		ret = 0;
@@ -301,7 +300,8 @@ static const struct v4l2_subdev_core_ops msi001_core_ops = {
 static int msi001_g_tuner(struct v4l2_subdev *sd, struct v4l2_tuner *v)
 {
 	struct msi001 *s = sd_to_msi001(sd);
-	dev_dbg(&s->spi->dev, "%s: index=%d\n", __func__, v->index);
+
+	dev_dbg(&s->spi->dev, "index=%d\n", v->index);
 
 	strlcpy(v->name, "Mirics MSi001", sizeof(v->name));
 	v->type = V4L2_TUNER_RF;
@@ -315,14 +315,16 @@ static int msi001_g_tuner(struct v4l2_subdev *sd, struct v4l2_tuner *v)
 static int msi001_s_tuner(struct v4l2_subdev *sd, const struct v4l2_tuner *v)
 {
 	struct msi001 *s = sd_to_msi001(sd);
-	dev_dbg(&s->spi->dev, "%s: index=%d\n", __func__, v->index);
+
+	dev_dbg(&s->spi->dev, "index=%d\n", v->index);
 	return 0;
 }
 
 static int msi001_g_frequency(struct v4l2_subdev *sd, struct v4l2_frequency *f)
 {
 	struct msi001 *s = sd_to_msi001(sd);
-	dev_dbg(&s->spi->dev, "%s: tuner=%d\n", __func__, f->tuner);
+
+	dev_dbg(&s->spi->dev, "tuner=%d\n", f->tuner);
 	f->frequency = s->f_tuner;
 	return 0;
 }
@@ -332,8 +334,9 @@ static int msi001_s_frequency(struct v4l2_subdev *sd,
 {
 	struct msi001 *s = sd_to_msi001(sd);
 	unsigned int band;
-	dev_dbg(&s->spi->dev, "%s: tuner=%d type=%d frequency=%u\n",
-			__func__, f->tuner, f->type, f->frequency);
+
+	dev_dbg(&s->spi->dev, "tuner=%d type=%d frequency=%u\n",
+			f->tuner, f->type, f->frequency);
 
 	if (f->frequency < ((bands[0].rangehigh + bands[1].rangelow) / 2))
 		band = 0;
@@ -349,8 +352,9 @@ static int msi001_enum_freq_bands(struct v4l2_subdev *sd,
 		struct v4l2_frequency_band *band)
 {
 	struct msi001 *s = sd_to_msi001(sd);
-	dev_dbg(&s->spi->dev, "%s: tuner=%d type=%d index=%d\n",
-			__func__, band->tuner, band->type, band->index);
+
+	dev_dbg(&s->spi->dev, "tuner=%d type=%d index=%d\n",
+			band->tuner, band->type, band->index);
 
 	if (band->index >= ARRAY_SIZE(bands))
 		return -EINVAL;
@@ -380,9 +384,10 @@ static int msi001_s_ctrl(struct v4l2_ctrl *ctrl)
 	struct msi001 *s = container_of(ctrl->handler, struct msi001, hdl);
 
 	int ret;
+
 	dev_dbg(&s->spi->dev,
-			"%s: id=%d name=%s val=%d min=%lld max=%lld step=%lld\n",
-			__func__, ctrl->id, ctrl->name, ctrl->val,
+			"id=%d name=%s val=%d min=%lld max=%lld step=%lld\n",
+			ctrl->id, ctrl->name, ctrl->val,
 			ctrl->minimum, ctrl->maximum, ctrl->step);
 
 	switch (ctrl->id) {
@@ -403,8 +408,7 @@ static int msi001_s_ctrl(struct v4l2_ctrl *ctrl)
 				s->mixer_gain->cur.val, s->if_gain->val);
 		break;
 	default:
-		dev_dbg(&s->spi->dev, "%s: unkown control %d\n",
-				__func__, ctrl->id);
+		dev_dbg(&s->spi->dev, "unkown control %d\n", ctrl->id);
 		ret = -EINVAL;
 	}
 
@@ -419,7 +423,8 @@ static int msi001_probe(struct spi_device *spi)
 {
 	struct msi001 *s;
 	int ret;
-	dev_dbg(&spi->dev, "%s:\n", __func__);
+
+	dev_dbg(&spi->dev, "\n");
 
 	s = kzalloc(sizeof(struct msi001), GFP_KERNEL);
 	if (s == NULL) {
@@ -466,7 +471,8 @@ static int msi001_remove(struct spi_device *spi)
 {
 	struct v4l2_subdev *sd = spi_get_drvdata(spi);
 	struct msi001 *s = sd_to_msi001(sd);
-	dev_dbg(&spi->dev, "%s:\n", __func__);
+
+	dev_dbg(&spi->dev, "\n");
 
 	/*
 	 * Registered by v4l2_spi_new_subdev() from master driver, but we must
diff --git a/drivers/media/tuners/mt2060.c b/drivers/media/tuners/mt2060.c
index 13381de58a84..b87b2549d58d 100644
--- a/drivers/media/tuners/mt2060.c
+++ b/drivers/media/tuners/mt2060.c
@@ -157,7 +157,6 @@ static int mt2060_set_params(struct dvb_frontend *fe)
 {
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	struct mt2060_priv *priv;
-	int ret=0;
 	int i=0;
 	u32 freq;
 	u8  lnaband;
@@ -240,7 +239,7 @@ static int mt2060_set_params(struct dvb_frontend *fe)
 	if (fe->ops.i2c_gate_ctrl)
 		fe->ops.i2c_gate_ctrl(fe, 0); /* close i2c_gate */
 
-	return ret;
+	return 0;
 }
 
 static void mt2060_calibrate(struct mt2060_priv *priv)
diff --git a/drivers/media/tuners/mt2063.c b/drivers/media/tuners/mt2063.c
index f640dcf4a81d..9e9c5eb4cb66 100644
--- a/drivers/media/tuners/mt2063.c
+++ b/drivers/media/tuners/mt2063.c
@@ -1216,7 +1216,7 @@ static u32 MT2063_SetReceiverMode(struct mt2063_state *state,
 	if (status >= 0) {
 		val =
 		    (state->
-		     reg[MT2063_REG_PD1_TGT] & (u8) ~0x40) | (RFAGCEN[Mode]
+		     reg[MT2063_REG_PD1_TGT] & ~0x40) | (RFAGCEN[Mode]
 								   ? 0x40 :
 								   0x00);
 		if (state->reg[MT2063_REG_PD1_TGT] != val)
@@ -1225,7 +1225,7 @@ static u32 MT2063_SetReceiverMode(struct mt2063_state *state,
 
 	/* LNARin */
 	if (status >= 0) {
-		u8 val = (state->reg[MT2063_REG_CTRL_2C] & (u8) ~0x03) |
+		u8 val = (state->reg[MT2063_REG_CTRL_2C] & ~0x03) |
 			 (LNARIN[Mode] & 0x03);
 		if (state->reg[MT2063_REG_CTRL_2C] != val)
 			status |= mt2063_setreg(state, MT2063_REG_CTRL_2C, val);
@@ -1235,19 +1235,19 @@ static u32 MT2063_SetReceiverMode(struct mt2063_state *state,
 	if (status >= 0) {
 		val =
 		    (state->
-		     reg[MT2063_REG_FIFF_CTRL2] & (u8) ~0xF0) |
+		     reg[MT2063_REG_FIFF_CTRL2] & ~0xF0) |
 		    (FIFFQEN[Mode] << 7) | (FIFFQ[Mode] << 4);
 		if (state->reg[MT2063_REG_FIFF_CTRL2] != val) {
 			status |=
 			    mt2063_setreg(state, MT2063_REG_FIFF_CTRL2, val);
 			/* trigger FIFF calibration, needed after changing FIFFQ */
 			val =
-			    (state->reg[MT2063_REG_FIFF_CTRL] | (u8) 0x01);
+			    (state->reg[MT2063_REG_FIFF_CTRL] | 0x01);
 			status |=
 			    mt2063_setreg(state, MT2063_REG_FIFF_CTRL, val);
 			val =
 			    (state->
-			     reg[MT2063_REG_FIFF_CTRL] & (u8) ~0x01);
+			     reg[MT2063_REG_FIFF_CTRL] & ~0x01);
 			status |=
 			    mt2063_setreg(state, MT2063_REG_FIFF_CTRL, val);
 		}
@@ -1259,7 +1259,7 @@ static u32 MT2063_SetReceiverMode(struct mt2063_state *state,
 
 	/* acLNAmax */
 	if (status >= 0) {
-		u8 val = (state->reg[MT2063_REG_LNA_OV] & (u8) ~0x1F) |
+		u8 val = (state->reg[MT2063_REG_LNA_OV] & ~0x1F) |
 			 (ACLNAMAX[Mode] & 0x1F);
 		if (state->reg[MT2063_REG_LNA_OV] != val)
 			status |= mt2063_setreg(state, MT2063_REG_LNA_OV, val);
@@ -1267,7 +1267,7 @@ static u32 MT2063_SetReceiverMode(struct mt2063_state *state,
 
 	/* LNATGT */
 	if (status >= 0) {
-		u8 val = (state->reg[MT2063_REG_LNA_TGT] & (u8) ~0x3F) |
+		u8 val = (state->reg[MT2063_REG_LNA_TGT] & ~0x3F) |
 			 (LNATGT[Mode] & 0x3F);
 		if (state->reg[MT2063_REG_LNA_TGT] != val)
 			status |= mt2063_setreg(state, MT2063_REG_LNA_TGT, val);
@@ -1275,7 +1275,7 @@ static u32 MT2063_SetReceiverMode(struct mt2063_state *state,
 
 	/* ACRF */
 	if (status >= 0) {
-		u8 val = (state->reg[MT2063_REG_RF_OV] & (u8) ~0x1F) |
+		u8 val = (state->reg[MT2063_REG_RF_OV] & ~0x1F) |
 			 (ACRFMAX[Mode] & 0x1F);
 		if (state->reg[MT2063_REG_RF_OV] != val)
 			status |= mt2063_setreg(state, MT2063_REG_RF_OV, val);
@@ -1283,7 +1283,7 @@ static u32 MT2063_SetReceiverMode(struct mt2063_state *state,
 
 	/* PD1TGT */
 	if (status >= 0) {
-		u8 val = (state->reg[MT2063_REG_PD1_TGT] & (u8) ~0x3F) |
+		u8 val = (state->reg[MT2063_REG_PD1_TGT] & ~0x3F) |
 			 (PD1TGT[Mode] & 0x3F);
 		if (state->reg[MT2063_REG_PD1_TGT] != val)
 			status |= mt2063_setreg(state, MT2063_REG_PD1_TGT, val);
@@ -1294,7 +1294,7 @@ static u32 MT2063_SetReceiverMode(struct mt2063_state *state,
 		u8 val = ACFIFMAX[Mode];
 		if (state->reg[MT2063_REG_PART_REV] != MT2063_B3 && val > 5)
 			val = 5;
-		val = (state->reg[MT2063_REG_FIF_OV] & (u8) ~0x1F) |
+		val = (state->reg[MT2063_REG_FIF_OV] & ~0x1F) |
 		      (val & 0x1F);
 		if (state->reg[MT2063_REG_FIF_OV] != val)
 			status |= mt2063_setreg(state, MT2063_REG_FIF_OV, val);
@@ -1302,7 +1302,7 @@ static u32 MT2063_SetReceiverMode(struct mt2063_state *state,
 
 	/* PD2TGT */
 	if (status >= 0) {
-		u8 val = (state->reg[MT2063_REG_PD2_TGT] & (u8) ~0x3F) |
+		u8 val = (state->reg[MT2063_REG_PD2_TGT] & ~0x3F) |
 		    (PD2TGT[Mode] & 0x3F);
 		if (state->reg[MT2063_REG_PD2_TGT] != val)
 			status |= mt2063_setreg(state, MT2063_REG_PD2_TGT, val);
@@ -1310,7 +1310,7 @@ static u32 MT2063_SetReceiverMode(struct mt2063_state *state,
 
 	/* Ignore ATN Overload */
 	if (status >= 0) {
-		val = (state->reg[MT2063_REG_LNA_TGT] & (u8) ~0x80) |
+		val = (state->reg[MT2063_REG_LNA_TGT] & ~0x80) |
 		      (RFOVDIS[Mode] ? 0x80 : 0x00);
 		if (state->reg[MT2063_REG_LNA_TGT] != val)
 			status |= mt2063_setreg(state, MT2063_REG_LNA_TGT, val);
@@ -1318,7 +1318,7 @@ static u32 MT2063_SetReceiverMode(struct mt2063_state *state,
 
 	/* Ignore FIF Overload */
 	if (status >= 0) {
-		val = (state->reg[MT2063_REG_PD1_TGT] & (u8) ~0x80) |
+		val = (state->reg[MT2063_REG_PD1_TGT] & ~0x80) |
 		      (FIFOVDIS[Mode] ? 0x80 : 0x00);
 		if (state->reg[MT2063_REG_PD1_TGT] != val)
 			status |= mt2063_setreg(state, MT2063_REG_PD1_TGT, val);
diff --git a/drivers/media/tuners/mxl301rf.c b/drivers/media/tuners/mxl301rf.c
new file mode 100644
index 000000000000..1575a5db776a
--- /dev/null
+++ b/drivers/media/tuners/mxl301rf.c
@@ -0,0 +1,349 @@
+/*
+ * MaxLinear MxL301RF OFDM tuner driver
+ *
+ * Copyright (C) 2014 Akihiro Tsukada <tskd08@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * NOTICE:
+ * This driver is incomplete and lacks init/config of the chips,
+ * as the necessary info is not disclosed.
+ * Other features like get_if_frequency() are missing as well.
+ * It assumes that users of this driver (such as a PCI bridge of
+ * DTV receiver cards) properly init and configure the chip
+ * via I2C *before* calling this driver's init() function.
+ *
+ * Currently, PT3 driver is the only one that uses this driver,
+ * and contains init/config code in its firmware.
+ * Thus some part of the code might be dependent on PT3 specific config.
+ */
+
+#include <linux/kernel.h>
+#include "mxl301rf.h"
+
+struct mxl301rf_state {
+	struct mxl301rf_config cfg;
+	struct i2c_client *i2c;
+};
+
+static struct mxl301rf_state *cfg_to_state(struct mxl301rf_config *c)
+{
+	return container_of(c, struct mxl301rf_state, cfg);
+}
+
+static int raw_write(struct mxl301rf_state *state, const u8 *buf, int len)
+{
+	int ret;
+
+	ret = i2c_master_send(state->i2c, buf, len);
+	if (ret >= 0 && ret < len)
+		ret = -EIO;
+	return (ret == len) ? 0 : ret;
+}
+
+static int reg_write(struct mxl301rf_state *state, u8 reg, u8 val)
+{
+	u8 buf[2] = { reg, val };
+
+	return raw_write(state, buf, 2);
+}
+
+static int reg_read(struct mxl301rf_state *state, u8 reg, u8 *val)
+{
+	u8 wbuf[2] = { 0xfb, reg };
+	int ret;
+
+	ret = raw_write(state, wbuf, sizeof(wbuf));
+	if (ret == 0)
+		ret = i2c_master_recv(state->i2c, val, 1);
+	if (ret >= 0 && ret < 1)
+		ret = -EIO;
+	return (ret == 1) ? 0 : ret;
+}
+
+/* tuner_ops */
+
+/* get RSSI and update propery cache, set to *out in % */
+static int mxl301rf_get_rf_strength(struct dvb_frontend *fe, u16 *out)
+{
+	struct mxl301rf_state *state;
+	int ret;
+	u8  rf_in1, rf_in2, rf_off1, rf_off2;
+	u16 rf_in, rf_off;
+	s64 level;
+	struct dtv_fe_stats *rssi;
+
+	rssi = &fe->dtv_property_cache.strength;
+	rssi->len = 1;
+	rssi->stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	*out = 0;
+
+	state = fe->tuner_priv;
+	ret = reg_write(state, 0x14, 0x01);
+	if (ret < 0)
+		return ret;
+	usleep_range(1000, 2000);
+
+	ret = reg_read(state, 0x18, &rf_in1);
+	if (ret == 0)
+		ret = reg_read(state, 0x19, &rf_in2);
+	if (ret == 0)
+		ret = reg_read(state, 0xd6, &rf_off1);
+	if (ret == 0)
+		ret = reg_read(state, 0xd7, &rf_off2);
+	if (ret != 0)
+		return ret;
+
+	rf_in = (rf_in2 & 0x07) << 8 | rf_in1;
+	rf_off = (rf_off2 & 0x0f) << 5 | (rf_off1 >> 3);
+	level = rf_in - rf_off - (113 << 3); /* x8 dBm */
+	level = level * 1000 / 8;
+	rssi->stat[0].svalue = level;
+	rssi->stat[0].scale = FE_SCALE_DECIBEL;
+	/* *out = (level - min) * 100 / (max - min) */
+	*out = (rf_in - rf_off + (1 << 9) - 1) * 100 / ((5 << 9) - 2);
+	return 0;
+}
+
+/* spur shift parameters */
+struct shf {
+	u32	freq;		/* Channel center frequency */
+	u32	ofst_th;	/* Offset frequency threshold */
+	u8	shf_val;	/* Spur shift value */
+	u8	shf_dir;	/* Spur shift direction */
+};
+
+static const struct shf shf_tab[] = {
+	{  64500, 500, 0x92, 0x07 },
+	{ 191500, 300, 0xe2, 0x07 },
+	{ 205500, 500, 0x2c, 0x04 },
+	{ 212500, 500, 0x1e, 0x04 },
+	{ 226500, 500, 0xd4, 0x07 },
+	{  99143, 500, 0x9c, 0x07 },
+	{ 173143, 500, 0xd4, 0x07 },
+	{ 191143, 300, 0xd4, 0x07 },
+	{ 207143, 500, 0xce, 0x07 },
+	{ 225143, 500, 0xce, 0x07 },
+	{ 243143, 500, 0xd4, 0x07 },
+	{ 261143, 500, 0xd4, 0x07 },
+	{ 291143, 500, 0xd4, 0x07 },
+	{ 339143, 500, 0x2c, 0x04 },
+	{ 117143, 500, 0x7a, 0x07 },
+	{ 135143, 300, 0x7a, 0x07 },
+	{ 153143, 500, 0x01, 0x07 }
+};
+
+struct reg_val {
+	u8 reg;
+	u8 val;
+} __attribute__ ((__packed__));
+
+static const struct reg_val set_idac[] = {
+	{ 0x0d, 0x00 },
+	{ 0x0c, 0x67 },
+	{ 0x6f, 0x89 },
+	{ 0x70, 0x0c },
+	{ 0x6f, 0x8a },
+	{ 0x70, 0x0e },
+	{ 0x6f, 0x8b },
+	{ 0x70, 0x1c },
+};
+
+static int mxl301rf_set_params(struct dvb_frontend *fe)
+{
+	struct reg_val tune0[] = {
+		{ 0x13, 0x00 },		/* abort tuning */
+		{ 0x3b, 0xc0 },
+		{ 0x3b, 0x80 },
+		{ 0x10, 0x95 },		/* BW */
+		{ 0x1a, 0x05 },
+		{ 0x61, 0x00 },		/* spur shift value (placeholder) */
+		{ 0x62, 0xa0 }		/* spur shift direction (placeholder) */
+	};
+
+	struct reg_val tune1[] = {
+		{ 0x11, 0x40 },		/* RF frequency L (placeholder) */
+		{ 0x12, 0x0e },		/* RF frequency H (placeholder) */
+		{ 0x13, 0x01 }		/* start tune */
+	};
+
+	struct mxl301rf_state *state;
+	u32 freq;
+	u16 f;
+	u32 tmp, div;
+	int i, ret;
+
+	state = fe->tuner_priv;
+	freq = fe->dtv_property_cache.frequency;
+
+	/* spur shift function (for analog) */
+	for (i = 0; i < ARRAY_SIZE(shf_tab); i++) {
+		if (freq >= (shf_tab[i].freq - shf_tab[i].ofst_th) * 1000 &&
+		    freq <= (shf_tab[i].freq + shf_tab[i].ofst_th) * 1000) {
+			tune0[5].val = shf_tab[i].shf_val;
+			tune0[6].val = 0xa0 | shf_tab[i].shf_dir;
+			break;
+		}
+	}
+	ret = raw_write(state, (u8 *) tune0, sizeof(tune0));
+	if (ret < 0)
+		goto failed;
+	usleep_range(3000, 4000);
+
+	/* convert freq to 10.6 fixed point float [MHz] */
+	f = freq / 1000000;
+	tmp = freq % 1000000;
+	div = 1000000;
+	for (i = 0; i < 6; i++) {
+		f <<= 1;
+		div >>= 1;
+		if (tmp > div) {
+			tmp -= div;
+			f |= 1;
+		}
+	}
+	if (tmp > 7812)
+		f++;
+	tune1[0].val = f & 0xff;
+	tune1[1].val = f >> 8;
+	ret = raw_write(state, (u8 *) tune1, sizeof(tune1));
+	if (ret < 0)
+		goto failed;
+	msleep(31);
+
+	ret = reg_write(state, 0x1a, 0x0d);
+	if (ret < 0)
+		goto failed;
+	ret = raw_write(state, (u8 *) set_idac, sizeof(set_idac));
+	if (ret < 0)
+		goto failed;
+	return 0;
+
+failed:
+	dev_warn(&state->i2c->dev, "(%s) failed. [adap%d-fe%d]\n",
+		__func__, fe->dvb->num, fe->id);
+	return ret;
+}
+
+static const struct reg_val standby_data[] = {
+	{ 0x01, 0x00 },
+	{ 0x13, 0x00 }
+};
+
+static int mxl301rf_sleep(struct dvb_frontend *fe)
+{
+	struct mxl301rf_state *state;
+	int ret;
+
+	state = fe->tuner_priv;
+	ret = raw_write(state, (u8 *)standby_data, sizeof(standby_data));
+	if (ret < 0)
+		dev_warn(&state->i2c->dev, "(%s) failed. [adap%d-fe%d]\n",
+			__func__, fe->dvb->num, fe->id);
+	return ret;
+}
+
+
+/* init sequence is not public.
+ * the parent must have init'ed the device.
+ * just wake up here.
+ */
+static int mxl301rf_init(struct dvb_frontend *fe)
+{
+	struct mxl301rf_state *state;
+	int ret;
+
+	state = fe->tuner_priv;
+
+	ret = reg_write(state, 0x01, 0x01);
+	if (ret < 0) {
+		dev_warn(&state->i2c->dev, "(%s) failed. [adap%d-fe%d]\n",
+			 __func__, fe->dvb->num, fe->id);
+		return ret;
+	}
+	return 0;
+}
+
+/* I2C driver functions */
+
+static const struct dvb_tuner_ops mxl301rf_ops = {
+	.info = {
+		.name = "MaxLinear MxL301RF",
+
+		.frequency_min =  93000000,
+		.frequency_max = 803142857,
+	},
+
+	.init = mxl301rf_init,
+	.sleep = mxl301rf_sleep,
+
+	.set_params = mxl301rf_set_params,
+	.get_rf_strength = mxl301rf_get_rf_strength,
+};
+
+
+static int mxl301rf_probe(struct i2c_client *client,
+			  const struct i2c_device_id *id)
+{
+	struct mxl301rf_state *state;
+	struct mxl301rf_config *cfg;
+	struct dvb_frontend *fe;
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+
+	state->i2c = client;
+	cfg = client->dev.platform_data;
+
+	memcpy(&state->cfg, cfg, sizeof(state->cfg));
+	fe = cfg->fe;
+	fe->tuner_priv = state;
+	memcpy(&fe->ops.tuner_ops, &mxl301rf_ops, sizeof(mxl301rf_ops));
+
+	i2c_set_clientdata(client, &state->cfg);
+	dev_info(&client->dev, "MaxLinear MxL301RF attached.\n");
+	return 0;
+}
+
+static int mxl301rf_remove(struct i2c_client *client)
+{
+	struct mxl301rf_state *state;
+
+	state = cfg_to_state(i2c_get_clientdata(client));
+	state->cfg.fe->tuner_priv = NULL;
+	kfree(state);
+	return 0;
+}
+
+
+static const struct i2c_device_id mxl301rf_id[] = {
+	{"mxl301rf", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, mxl301rf_id);
+
+static struct i2c_driver mxl301rf_driver = {
+	.driver = {
+		.name	= "mxl301rf",
+	},
+	.probe		= mxl301rf_probe,
+	.remove		= mxl301rf_remove,
+	.id_table	= mxl301rf_id,
+};
+
+module_i2c_driver(mxl301rf_driver);
+
+MODULE_DESCRIPTION("MaxLinear MXL301RF tuner");
+MODULE_AUTHOR("Akihiro TSUKADA");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/tuners/mxl301rf.h b/drivers/media/tuners/mxl301rf.h
new file mode 100644
index 000000000000..19e68405f00d
--- /dev/null
+++ b/drivers/media/tuners/mxl301rf.h
@@ -0,0 +1,26 @@
+/*
+ * MaxLinear MxL301RF OFDM tuner driver
+ *
+ * Copyright (C) 2014 Akihiro Tsukada <tskd08@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef MXL301RF_H
+#define MXL301RF_H
+
+#include "dvb_frontend.h"
+
+struct mxl301rf_config {
+	struct dvb_frontend *fe;
+};
+
+#endif /* MXL301RF_H */
diff --git a/drivers/media/tuners/mxl5005s.c b/drivers/media/tuners/mxl5005s.c
index b473b76cb278..92a3be4fde87 100644
--- a/drivers/media/tuners/mxl5005s.c
+++ b/drivers/media/tuners/mxl5005s.c
@@ -1692,7 +1692,6 @@ static u16 MXL5005_TunerConfig(struct dvb_frontend *fe,
 	)
 {
 	struct mxl5005s_state *state = fe->tuner_priv;
-	u16 status = 0;
 
 	state->Mode = Mode;
 	state->IF_Mode = IF_mode;
@@ -1715,7 +1714,7 @@ static u16 MXL5005_TunerConfig(struct dvb_frontend *fe,
 	/* Synthesizer LO frequency calculation */
 	MXL_SynthIFLO_Calc(fe);
 
-	return status;
+	return 0;
 }
 
 static void MXL_SynthIFLO_Calc(struct dvb_frontend *fe)
diff --git a/drivers/media/tuners/qm1d1c0042.c b/drivers/media/tuners/qm1d1c0042.c
new file mode 100644
index 000000000000..18bc745ed108
--- /dev/null
+++ b/drivers/media/tuners/qm1d1c0042.c
@@ -0,0 +1,448 @@
+/*
+ * Sharp QM1D1C0042 8PSK tuner driver
+ *
+ * Copyright (C) 2014 Akihiro Tsukada <tskd08@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * NOTICE:
+ * As the disclosed information on the chip is very limited,
+ * this driver lacks some features, including chip config like IF freq.
+ * It assumes that users of this driver (such as a PCI bridge of
+ * DTV receiver cards) know the relevant info and
+ * configure the chip via I2C if necessary.
+ *
+ * Currently, PT3 driver is the only one that uses this driver,
+ * and contains init/config code in its firmware.
+ * Thus some part of the code might be dependent on PT3 specific config.
+ */
+
+#include <linux/kernel.h>
+#include <linux/math64.h>
+#include "qm1d1c0042.h"
+
+#define QM1D1C0042_NUM_REGS 0x20
+
+static const u8 reg_initval[QM1D1C0042_NUM_REGS] = {
+	0x48, 0x1c, 0xa0, 0x10, 0xbc, 0xc5, 0x20, 0x33,
+	0x06, 0x00, 0x00, 0x00, 0x03, 0x00, 0x00, 0x00,
+	0x00, 0xff, 0xf3, 0x00, 0x2a, 0x64, 0xa6, 0x86,
+	0x8c, 0xcf, 0xb8, 0xf1, 0xa8, 0xf2, 0x89, 0x00
+};
+
+static const struct qm1d1c0042_config default_cfg = {
+	.xtal_freq = 16000,
+	.lpf = 1,
+	.fast_srch = 0,
+	.lpf_wait = 20,
+	.fast_srch_wait = 4,
+	.normal_srch_wait = 15,
+};
+
+struct qm1d1c0042_state {
+	struct qm1d1c0042_config cfg;
+	struct i2c_client *i2c;
+	u8 regs[QM1D1C0042_NUM_REGS];
+};
+
+static struct qm1d1c0042_state *cfg_to_state(struct qm1d1c0042_config *c)
+{
+	return container_of(c, struct qm1d1c0042_state, cfg);
+}
+
+static int reg_write(struct qm1d1c0042_state *state, u8 reg, u8 val)
+{
+	u8 wbuf[2] = { reg, val };
+	int ret;
+
+	ret = i2c_master_send(state->i2c, wbuf, sizeof(wbuf));
+	if (ret >= 0 && ret < sizeof(wbuf))
+		ret = -EIO;
+	return (ret == sizeof(wbuf)) ? 0 : ret;
+}
+
+static int reg_read(struct qm1d1c0042_state *state, u8 reg, u8 *val)
+{
+	struct i2c_msg msgs[2] = {
+		{
+			.addr = state->i2c->addr,
+			.flags = 0,
+			.buf = &reg,
+			.len = 1,
+		},
+		{
+			.addr = state->i2c->addr,
+			.flags = I2C_M_RD,
+			.buf = val,
+			.len = 1,
+		},
+	};
+	int ret;
+
+	ret = i2c_transfer(state->i2c->adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret >= 0 && ret < ARRAY_SIZE(msgs))
+		ret = -EIO;
+	return (ret == ARRAY_SIZE(msgs)) ? 0 : ret;
+}
+
+
+static int qm1d1c0042_set_srch_mode(struct qm1d1c0042_state *state, bool fast)
+{
+	if (fast)
+		state->regs[0x03] |= 0x01; /* set fast search mode */
+	else
+		state->regs[0x03] &= ~0x01 & 0xff;
+
+	return reg_write(state, 0x03, state->regs[0x03]);
+}
+
+static int qm1d1c0042_wakeup(struct qm1d1c0042_state *state)
+{
+	int ret;
+
+	state->regs[0x01] |= 1 << 3;             /* BB_Reg_enable */
+	state->regs[0x01] &= (~(1 << 0)) & 0xff; /* NORMAL (wake-up) */
+	state->regs[0x05] &= (~(1 << 3)) & 0xff; /* pfd_rst NORMAL */
+	ret = reg_write(state, 0x01, state->regs[0x01]);
+	if (ret == 0)
+		ret = reg_write(state, 0x05, state->regs[0x05]);
+
+	if (ret < 0)
+		dev_warn(&state->i2c->dev, "(%s) failed. [adap%d-fe%d]\n",
+			__func__, state->cfg.fe->dvb->num, state->cfg.fe->id);
+	return ret;
+}
+
+/* tuner_ops */
+
+static int qm1d1c0042_set_config(struct dvb_frontend *fe, void *priv_cfg)
+{
+	struct qm1d1c0042_state *state;
+	struct qm1d1c0042_config *cfg;
+
+	state = fe->tuner_priv;
+	cfg = priv_cfg;
+
+	if (cfg->fe)
+		state->cfg.fe = cfg->fe;
+
+	if (cfg->xtal_freq != QM1D1C0042_CFG_XTAL_DFLT)
+		dev_warn(&state->i2c->dev,
+			"(%s) changing xtal_freq not supported. ", __func__);
+	state->cfg.xtal_freq = default_cfg.xtal_freq;
+
+	state->cfg.lpf = cfg->lpf;
+	state->cfg.fast_srch = cfg->fast_srch;
+
+	if (cfg->lpf_wait != QM1D1C0042_CFG_WAIT_DFLT)
+		state->cfg.lpf_wait = cfg->lpf_wait;
+	else
+		state->cfg.lpf_wait = default_cfg.lpf_wait;
+
+	if (cfg->fast_srch_wait != QM1D1C0042_CFG_WAIT_DFLT)
+		state->cfg.fast_srch_wait = cfg->fast_srch_wait;
+	else
+		state->cfg.fast_srch_wait = default_cfg.fast_srch_wait;
+
+	if (cfg->normal_srch_wait != QM1D1C0042_CFG_WAIT_DFLT)
+		state->cfg.normal_srch_wait = cfg->normal_srch_wait;
+	else
+		state->cfg.normal_srch_wait = default_cfg.normal_srch_wait;
+	return 0;
+}
+
+/* divisor, vco_band parameters */
+/*  {maxfreq,  param1(band?), param2(div?) */
+static const u32 conv_table[9][3] = {
+	{ 2151000, 1, 7 },
+	{ 1950000, 1, 6 },
+	{ 1800000, 1, 5 },
+	{ 1600000, 1, 4 },
+	{ 1450000, 1, 3 },
+	{ 1250000, 1, 2 },
+	{ 1200000, 0, 7 },
+	{  975000, 0, 6 },
+	{  950000, 0, 0 }
+};
+
+static int qm1d1c0042_set_params(struct dvb_frontend *fe)
+{
+	struct qm1d1c0042_state *state;
+	u32 freq;
+	int i, ret;
+	u8 val, mask;
+	u32 a, sd;
+	s32 b;
+
+	state = fe->tuner_priv;
+	freq = fe->dtv_property_cache.frequency;
+
+	state->regs[0x08] &= 0xf0;
+	state->regs[0x08] |= 0x09;
+
+	state->regs[0x13] &= 0x9f;
+	state->regs[0x13] |= 0x20;
+
+	/* div2/vco_band */
+	val = state->regs[0x02] & 0x0f;
+	for (i = 0; i < 8; i++)
+		if (freq < conv_table[i][0] && freq >= conv_table[i + 1][0]) {
+			val |= conv_table[i][1] << 7;
+			val |= conv_table[i][2] << 4;
+			break;
+		}
+	ret = reg_write(state, 0x02, val);
+	if (ret < 0)
+		return ret;
+
+	a = (freq + state->cfg.xtal_freq / 2) / state->cfg.xtal_freq;
+
+	state->regs[0x06] &= 0x40;
+	state->regs[0x06] |= (a - 12) / 4;
+	ret = reg_write(state, 0x06, state->regs[0x06]);
+	if (ret < 0)
+		return ret;
+
+	state->regs[0x07] &= 0xf0;
+	state->regs[0x07] |= (a - 4 * ((a - 12) / 4 + 1) - 5) & 0x0f;
+	ret = reg_write(state, 0x07, state->regs[0x07]);
+	if (ret < 0)
+		return ret;
+
+	/* LPF */
+	val = state->regs[0x08];
+	if (state->cfg.lpf) {
+		/* LPF_CLK, LPF_FC */
+		val &= 0xf0;
+		val |= 0x02;
+	}
+	ret = reg_write(state, 0x08, val);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * b = (freq / state->cfg.xtal_freq - a) << 20;
+	 * sd = b          (b >= 0)
+	 *      1<<22 + b  (b < 0)
+	 */
+	b = (s32)div64_s64(((s64) freq) << 20, state->cfg.xtal_freq)
+			   - (((s64) a) << 20);
+
+	if (b >= 0)
+		sd = b;
+	else
+		sd = (1 << 22) + b;
+
+	state->regs[0x09] &= 0xc0;
+	state->regs[0x09] |= (sd >> 16) & 0x3f;
+	state->regs[0x0a] = (sd >> 8) & 0xff;
+	state->regs[0x0b] = sd & 0xff;
+	ret = reg_write(state, 0x09, state->regs[0x09]);
+	if (ret == 0)
+		ret = reg_write(state, 0x0a, state->regs[0x0a]);
+	if (ret == 0)
+		ret = reg_write(state, 0x0b, state->regs[0x0b]);
+	if (ret != 0)
+		return ret;
+
+	if (!state->cfg.lpf) {
+		/* CSEL_Offset */
+		ret = reg_write(state, 0x13, state->regs[0x13]);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* VCO_TM, LPF_TM */
+	mask = state->cfg.lpf ? 0x3f : 0x7f;
+	val = state->regs[0x0c] & mask;
+	ret = reg_write(state, 0x0c, val);
+	if (ret < 0)
+		return ret;
+	usleep_range(2000, 3000);
+	val = state->regs[0x0c] | ~mask;
+	ret = reg_write(state, 0x0c, val);
+	if (ret < 0)
+		return ret;
+
+	if (state->cfg.lpf)
+		msleep(state->cfg.lpf_wait);
+	else if (state->regs[0x03] & 0x01)
+		msleep(state->cfg.fast_srch_wait);
+	else
+		msleep(state->cfg.normal_srch_wait);
+
+	if (state->cfg.lpf) {
+		/* LPF_FC */
+		ret = reg_write(state, 0x08, 0x09);
+		if (ret < 0)
+			return ret;
+
+		/* CSEL_Offset */
+		ret = reg_write(state, 0x13, state->regs[0x13]);
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+static int qm1d1c0042_sleep(struct dvb_frontend *fe)
+{
+	struct qm1d1c0042_state *state;
+	int ret;
+
+	state = fe->tuner_priv;
+	state->regs[0x01] &= (~(1 << 3)) & 0xff; /* BB_Reg_disable */
+	state->regs[0x01] |= 1 << 0;             /* STDBY */
+	state->regs[0x05] |= 1 << 3;             /* pfd_rst STANDBY */
+	ret = reg_write(state, 0x05, state->regs[0x05]);
+	if (ret == 0)
+		ret = reg_write(state, 0x01, state->regs[0x01]);
+	if (ret < 0)
+		dev_warn(&state->i2c->dev, "(%s) failed. [adap%d-fe%d]\n",
+			__func__, fe->dvb->num, fe->id);
+	return ret;
+}
+
+static int qm1d1c0042_init(struct dvb_frontend *fe)
+{
+	struct qm1d1c0042_state *state;
+	u8 val;
+	int i, ret;
+
+	state = fe->tuner_priv;
+	memcpy(state->regs, reg_initval, sizeof(reg_initval));
+
+	reg_write(state, 0x01, 0x0c);
+	reg_write(state, 0x01, 0x0c);
+
+	ret = reg_write(state, 0x01, 0x0c); /* soft reset on */
+	if (ret < 0)
+		goto failed;
+	usleep_range(2000, 3000);
+
+	val = state->regs[0x01] | 0x10;
+	ret = reg_write(state, 0x01, val); /* soft reset off */
+	if (ret < 0)
+		goto failed;
+
+	/* check ID */
+	ret = reg_read(state, 0x00, &val);
+	if (ret < 0 || val != 0x48)
+		goto failed;
+	usleep_range(2000, 3000);
+
+	state->regs[0x0c] |= 0x40;
+	ret = reg_write(state, 0x0c, state->regs[0x0c]);
+	if (ret < 0)
+		goto failed;
+	msleep(state->cfg.lpf_wait);
+
+	/* set all writable registers */
+	for (i = 1; i <= 0x0c ; i++) {
+		ret = reg_write(state, i, state->regs[i]);
+		if (ret < 0)
+			goto failed;
+	}
+	for (i = 0x11; i < QM1D1C0042_NUM_REGS; i++) {
+		ret = reg_write(state, i, state->regs[i]);
+		if (ret < 0)
+			goto failed;
+	}
+
+	ret = qm1d1c0042_wakeup(state);
+	if (ret < 0)
+		goto failed;
+
+	ret = qm1d1c0042_set_srch_mode(state, state->cfg.fast_srch);
+	if (ret < 0)
+		goto failed;
+
+	return ret;
+
+failed:
+	dev_warn(&state->i2c->dev, "(%s) failed. [adap%d-fe%d]\n",
+		__func__, fe->dvb->num, fe->id);
+	return ret;
+}
+
+/* I2C driver functions */
+
+static const struct dvb_tuner_ops qm1d1c0042_ops = {
+	.info = {
+		.name = "Sharp QM1D1C0042",
+
+		.frequency_min =  950000,
+		.frequency_max = 2150000,
+	},
+
+	.init = qm1d1c0042_init,
+	.sleep = qm1d1c0042_sleep,
+	.set_config = qm1d1c0042_set_config,
+	.set_params = qm1d1c0042_set_params,
+};
+
+
+static int qm1d1c0042_probe(struct i2c_client *client,
+			    const struct i2c_device_id *id)
+{
+	struct qm1d1c0042_state *state;
+	struct qm1d1c0042_config *cfg;
+	struct dvb_frontend *fe;
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+	state->i2c = client;
+
+	cfg = client->dev.platform_data;
+	fe = cfg->fe;
+	fe->tuner_priv = state;
+	qm1d1c0042_set_config(fe, cfg);
+	memcpy(&fe->ops.tuner_ops, &qm1d1c0042_ops, sizeof(qm1d1c0042_ops));
+
+	i2c_set_clientdata(client, &state->cfg);
+	dev_info(&client->dev, "Sharp QM1D1C0042 attached.\n");
+	return 0;
+}
+
+static int qm1d1c0042_remove(struct i2c_client *client)
+{
+	struct qm1d1c0042_state *state;
+
+	state = cfg_to_state(i2c_get_clientdata(client));
+	state->cfg.fe->tuner_priv = NULL;
+	kfree(state);
+	return 0;
+}
+
+
+static const struct i2c_device_id qm1d1c0042_id[] = {
+	{"qm1d1c0042", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, qm1d1c0042_id);
+
+static struct i2c_driver qm1d1c0042_driver = {
+	.driver = {
+		.name	= "qm1d1c0042",
+	},
+	.probe		= qm1d1c0042_probe,
+	.remove		= qm1d1c0042_remove,
+	.id_table	= qm1d1c0042_id,
+};
+
+module_i2c_driver(qm1d1c0042_driver);
+
+MODULE_DESCRIPTION("Sharp QM1D1C0042 tuner");
+MODULE_AUTHOR("Akihiro TSUKADA");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/tuners/qm1d1c0042.h b/drivers/media/tuners/qm1d1c0042.h
new file mode 100644
index 000000000000..4f5c18816c44
--- /dev/null
+++ b/drivers/media/tuners/qm1d1c0042.h
@@ -0,0 +1,37 @@
+/*
+ * Sharp QM1D1C0042 8PSK tuner driver
+ *
+ * Copyright (C) 2014 Akihiro Tsukada <tskd08@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef QM1D1C0042_H
+#define QM1D1C0042_H
+
+#include "dvb_frontend.h"
+
+
+struct qm1d1c0042_config {
+	struct dvb_frontend *fe;
+
+	u32  xtal_freq;    /* [kHz] */ /* currently ignored */
+	bool lpf;          /* enable LPF */
+	bool fast_srch;    /* enable fast search mode, no LPF */
+	u32  lpf_wait;         /* wait in tuning with LPF enabled. [ms] */
+	u32  fast_srch_wait;   /* with fast-search mode, no LPF. [ms] */
+	u32  normal_srch_wait; /* with no LPF/fast-search mode. [ms] */
+};
+/* special values indicating to use the default in qm1d1c0042_config */
+#define QM1D1C0042_CFG_XTAL_DFLT 0
+#define QM1D1C0042_CFG_WAIT_DFLT 0
+
+#endif /* QM1D1C0042_H */
diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c
index 6c53edb73a63..cf97142e01e6 100644
--- a/drivers/media/tuners/si2157.c
+++ b/drivers/media/tuners/si2157.c
@@ -1,5 +1,5 @@
 /*
- * Silicon Labs Si2157/2158 silicon tuner driver
+ * Silicon Labs Si2147/2157/2158 silicon tuner driver
  *
  * Copyright (C) 2014 Antti Palosaari <crope@iki.fi>
  *
@@ -55,8 +55,7 @@ static int si2157_cmd_execute(struct si2157 *s, struct si2157_cmd *cmd)
 				break;
 		}
 
-		dev_dbg(&s->client->dev, "%s: cmd execution took %d ms\n",
-				__func__,
+		dev_dbg(&s->client->dev, "cmd execution took %d ms\n",
 				jiffies_to_msecs(jiffies) -
 				(jiffies_to_msecs(timeout) - TIMEOUT));
 
@@ -75,7 +74,7 @@ err_mutex_unlock:
 
 	return 0;
 err:
-	dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&s->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -88,9 +87,12 @@ static int si2157_init(struct dvb_frontend *fe)
 	u8 *fw_file;
 	unsigned int chip_id;
 
-	dev_dbg(&s->client->dev, "%s:\n", __func__);
+	dev_dbg(&s->client->dev, "\n");
 
-	/* configure? */
+	if (s->fw_loaded)
+		goto warm;
+
+	/* power up */
 	memcpy(cmd.args, "\xc0\x00\x0c\x00\x00\x01\x01\x01\x01\x01\x01\x02\x00\x00\x01", 15);
 	cmd.wlen = 15;
 	cmd.rlen = 1;
@@ -111,45 +113,47 @@ static int si2157_init(struct dvb_frontend *fe)
 
 	#define SI2158_A20 ('A' << 24 | 58 << 16 | '2' << 8 | '0' << 0)
 	#define SI2157_A30 ('A' << 24 | 57 << 16 | '3' << 8 | '0' << 0)
+	#define SI2147_A30 ('A' << 24 | 47 << 16 | '3' << 8 | '0' << 0)
 
 	switch (chip_id) {
 	case SI2158_A20:
 		fw_file = SI2158_A20_FIRMWARE;
 		break;
 	case SI2157_A30:
+	case SI2147_A30:
 		goto skip_fw_download;
 		break;
 	default:
 		dev_err(&s->client->dev,
-				"%s: unkown chip version Si21%d-%c%c%c\n",
-				KBUILD_MODNAME, cmd.args[2], cmd.args[1],
+				"unknown chip version Si21%d-%c%c%c\n",
+				cmd.args[2], cmd.args[1],
 				cmd.args[3], cmd.args[4]);
 		ret = -EINVAL;
 		goto err;
 	}
 
 	/* cold state - try to download firmware */
-	dev_info(&s->client->dev, "%s: found a '%s' in cold state\n",
-			KBUILD_MODNAME, si2157_ops.info.name);
+	dev_info(&s->client->dev, "found a '%s' in cold state\n",
+			si2157_ops.info.name);
 
 	/* request the firmware, this will block and timeout */
 	ret = request_firmware(&fw, fw_file, &s->client->dev);
 	if (ret) {
-		dev_err(&s->client->dev, "%s: firmware file '%s' not found\n",
-				KBUILD_MODNAME, fw_file);
+		dev_err(&s->client->dev, "firmware file '%s' not found\n",
+				fw_file);
 		goto err;
 	}
 
 	/* firmware should be n chunks of 17 bytes */
 	if (fw->size % 17 != 0) {
-		dev_err(&s->client->dev, "%s: firmware file '%s' is invalid\n",
-				KBUILD_MODNAME, fw_file);
+		dev_err(&s->client->dev, "firmware file '%s' is invalid\n",
+				fw_file);
 		ret = -EINVAL;
 		goto err;
 	}
 
-	dev_info(&s->client->dev, "%s: downloading firmware from file '%s'\n",
-			KBUILD_MODNAME, fw_file);
+	dev_info(&s->client->dev, "downloading firmware from file '%s'\n",
+			fw_file);
 
 	for (remaining = fw->size; remaining > 0; remaining -= 17) {
 		len = fw->data[fw->size - remaining];
@@ -159,8 +163,8 @@ static int si2157_init(struct dvb_frontend *fe)
 		ret = si2157_cmd_execute(s, &cmd);
 		if (ret) {
 			dev_err(&s->client->dev,
-					"%s: firmware download failed=%d\n",
-					KBUILD_MODNAME, ret);
+					"firmware download failed=%d\n",
+					ret);
 			goto err;
 		}
 	}
@@ -177,14 +181,17 @@ skip_fw_download:
 	if (ret)
 		goto err;
 
-	s->active = true;
+	s->fw_loaded = true;
 
+warm:
+	s->active = true;
 	return 0;
+
 err:
 	if (fw)
 		release_firmware(fw);
 
-	dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&s->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -194,20 +201,21 @@ static int si2157_sleep(struct dvb_frontend *fe)
 	int ret;
 	struct si2157_cmd cmd;
 
-	dev_dbg(&s->client->dev, "%s:\n", __func__);
+	dev_dbg(&s->client->dev, "\n");
 
 	s->active = false;
 
-	memcpy(cmd.args, "\x13", 1);
-	cmd.wlen = 1;
-	cmd.rlen = 0;
+	/* standby */
+	memcpy(cmd.args, "\x16\x00", 2);
+	cmd.wlen = 2;
+	cmd.rlen = 1;
 	ret = si2157_cmd_execute(s, &cmd);
 	if (ret)
 		goto err;
 
 	return 0;
 err:
-	dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&s->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -220,8 +228,8 @@ static int si2157_set_params(struct dvb_frontend *fe)
 	u8 bandwidth, delivery_system;
 
 	dev_dbg(&s->client->dev,
-			"%s: delivery_system=%d frequency=%u bandwidth_hz=%u\n",
-			__func__, c->delivery_system, c->frequency,
+			"delivery_system=%d frequency=%u bandwidth_hz=%u\n",
+			c->delivery_system, c->frequency,
 			c->bandwidth_hz);
 
 	if (!s->active) {
@@ -239,6 +247,9 @@ static int si2157_set_params(struct dvb_frontend *fe)
 		bandwidth = 0x0f;
 
 	switch (c->delivery_system) {
+	case SYS_ATSC:
+			delivery_system = 0x00;
+			break;
 	case SYS_DVBT:
 	case SYS_DVBT2: /* it seems DVB-T and DVB-T2 both are 0x20 here */
 			delivery_system = 0x20;
@@ -256,7 +267,14 @@ static int si2157_set_params(struct dvb_frontend *fe)
 	if (s->inversion)
 		cmd.args[5] = 0x01;
 	cmd.wlen = 6;
-	cmd.rlen = 1;
+	cmd.rlen = 4;
+	ret = si2157_cmd_execute(s, &cmd);
+	if (ret)
+		goto err;
+
+	memcpy(cmd.args, "\x14\x00\x02\x07\x01\x00", 6);
+	cmd.wlen = 6;
+	cmd.rlen = 4;
 	ret = si2157_cmd_execute(s, &cmd);
 	if (ret)
 		goto err;
@@ -275,7 +293,7 @@ static int si2157_set_params(struct dvb_frontend *fe)
 
 	return 0;
 err:
-	dev_dbg(&s->client->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&s->client->dev, "failed=%d\n", ret);
 	return ret;
 }
 
@@ -310,13 +328,14 @@ static int si2157_probe(struct i2c_client *client,
 	s = kzalloc(sizeof(struct si2157), GFP_KERNEL);
 	if (!s) {
 		ret = -ENOMEM;
-		dev_err(&client->dev, "%s: kzalloc() failed\n", KBUILD_MODNAME);
+		dev_err(&client->dev, "kzalloc() failed\n");
 		goto err;
 	}
 
 	s->client = client;
 	s->fe = cfg->fe;
 	s->inversion = cfg->inversion;
+	s->fw_loaded = false;
 	mutex_init(&s->i2c_mutex);
 
 	/* check if the tuner is there */
@@ -333,11 +352,10 @@ static int si2157_probe(struct i2c_client *client,
 	i2c_set_clientdata(client, s);
 
 	dev_info(&s->client->dev,
-			"%s: Silicon Labs Si2157/Si2158 successfully attached\n",
-			KBUILD_MODNAME);
+			"Silicon Labs Si2157/Si2158 successfully attached\n");
 	return 0;
 err:
-	dev_dbg(&client->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&client->dev, "failed=%d\n", ret);
 	kfree(s);
 
 	return ret;
@@ -348,7 +366,7 @@ static int si2157_remove(struct i2c_client *client)
 	struct si2157 *s = i2c_get_clientdata(client);
 	struct dvb_frontend *fe = s->fe;
 
-	dev_dbg(&client->dev, "%s:\n", __func__);
+	dev_dbg(&client->dev, "\n");
 
 	memset(&fe->ops.tuner_ops, 0, sizeof(struct dvb_tuner_ops));
 	fe->tuner_priv = NULL;
diff --git a/drivers/media/tuners/si2157.h b/drivers/media/tuners/si2157.h
index 6da4d5d1c817..d3b19cadb4a1 100644
--- a/drivers/media/tuners/si2157.h
+++ b/drivers/media/tuners/si2157.h
@@ -1,5 +1,5 @@
 /*
- * Silicon Labs Si2157/2158 silicon tuner driver
+ * Silicon Labs Si2147/2157/2158 silicon tuner driver
  *
  * Copyright (C) 2014 Antti Palosaari <crope@iki.fi>
  *
diff --git a/drivers/media/tuners/si2157_priv.h b/drivers/media/tuners/si2157_priv.h
index 3ddab5e6b500..e71ffafed951 100644
--- a/drivers/media/tuners/si2157_priv.h
+++ b/drivers/media/tuners/si2157_priv.h
@@ -1,5 +1,5 @@
 /*
- * Silicon Labs Si2157/2158 silicon tuner driver
+ * Silicon Labs Si2147/2157/2158 silicon tuner driver
  *
  * Copyright (C) 2014 Antti Palosaari <crope@iki.fi>
  *
@@ -26,6 +26,7 @@ struct si2157 {
 	struct i2c_client *client;
 	struct dvb_frontend *fe;
 	bool active;
+	bool fw_loaded;
 	bool inversion;
 };
 
diff --git a/drivers/media/tuners/tda18212.c b/drivers/media/tuners/tda18212.c
index 05a4ac9edb6b..d93e0667b46b 100644
--- a/drivers/media/tuners/tda18212.c
+++ b/drivers/media/tuners/tda18212.c
@@ -19,125 +19,19 @@
  */
 
 #include "tda18212.h"
+#include <linux/regmap.h>
 
-/* Max transfer size done by I2C transfer functions */
-#define MAX_XFER_SIZE  64
-
-struct tda18212_priv {
-	struct tda18212_config *cfg;
-	struct i2c_adapter *i2c;
+struct tda18212_dev {
+	struct tda18212_config cfg;
+	struct i2c_client *client;
+	struct regmap *regmap;
 
 	u32 if_frequency;
 };
 
-/* write multiple registers */
-static int tda18212_wr_regs(struct tda18212_priv *priv, u8 reg, u8 *val,
-	int len)
-{
-	int ret;
-	u8 buf[MAX_XFER_SIZE];
-	struct i2c_msg msg[1] = {
-		{
-			.addr = priv->cfg->i2c_address,
-			.flags = 0,
-			.len = 1 + len,
-			.buf = buf,
-		}
-	};
-
-	if (1 + len > sizeof(buf)) {
-		dev_warn(&priv->i2c->dev,
-			 "%s: i2c wr reg=%04x: len=%d is too big!\n",
-			 KBUILD_MODNAME, reg, len);
-		return -EINVAL;
-	}
-
-	buf[0] = reg;
-	memcpy(&buf[1], val, len);
-
-	ret = i2c_transfer(priv->i2c, msg, 1);
-	if (ret == 1) {
-		ret = 0;
-	} else {
-		dev_warn(&priv->i2c->dev, "%s: i2c wr failed=%d reg=%02x " \
-				"len=%d\n", KBUILD_MODNAME, ret, reg, len);
-		ret = -EREMOTEIO;
-	}
-	return ret;
-}
-
-/* read multiple registers */
-static int tda18212_rd_regs(struct tda18212_priv *priv, u8 reg, u8 *val,
-	int len)
-{
-	int ret;
-	u8 buf[MAX_XFER_SIZE];
-	struct i2c_msg msg[2] = {
-		{
-			.addr = priv->cfg->i2c_address,
-			.flags = 0,
-			.len = 1,
-			.buf = &reg,
-		}, {
-			.addr = priv->cfg->i2c_address,
-			.flags = I2C_M_RD,
-			.len = len,
-			.buf = buf,
-		}
-	};
-
-	if (len > sizeof(buf)) {
-		dev_warn(&priv->i2c->dev,
-			 "%s: i2c rd reg=%04x: len=%d is too big!\n",
-			 KBUILD_MODNAME, reg, len);
-		return -EINVAL;
-	}
-
-	ret = i2c_transfer(priv->i2c, msg, 2);
-	if (ret == 2) {
-		memcpy(val, buf, len);
-		ret = 0;
-	} else {
-		dev_warn(&priv->i2c->dev, "%s: i2c rd failed=%d reg=%02x " \
-				"len=%d\n", KBUILD_MODNAME, ret, reg, len);
-		ret = -EREMOTEIO;
-	}
-
-	return ret;
-}
-
-/* write single register */
-static int tda18212_wr_reg(struct tda18212_priv *priv, u8 reg, u8 val)
-{
-	return tda18212_wr_regs(priv, reg, &val, 1);
-}
-
-/* read single register */
-static int tda18212_rd_reg(struct tda18212_priv *priv, u8 reg, u8 *val)
-{
-	return tda18212_rd_regs(priv, reg, val, 1);
-}
-
-#if 0 /* keep, useful when developing driver */
-static void tda18212_dump_regs(struct tda18212_priv *priv)
-{
-	int i;
-	u8 buf[256];
-
-	#define TDA18212_RD_LEN 32
-	for (i = 0; i < sizeof(buf); i += TDA18212_RD_LEN)
-		tda18212_rd_regs(priv, i, &buf[i], TDA18212_RD_LEN);
-
-	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 32, 1, buf,
-		sizeof(buf), true);
-
-	return;
-}
-#endif
-
 static int tda18212_set_params(struct dvb_frontend *fe)
 {
-	struct tda18212_priv *priv = fe->tuner_priv;
+	struct tda18212_dev *dev = fe->tuner_priv;
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret, i;
 	u32 if_khz;
@@ -166,9 +60,9 @@ static int tda18212_set_params(struct dvb_frontend *fe)
 		[ATSC_QAM] = { 0x7d, 0x20, 0x63 },
 	};
 
-	dev_dbg(&priv->i2c->dev,
-			"%s: delivery_system=%d frequency=%d bandwidth_hz=%d\n",
-			__func__, c->delivery_system, c->frequency,
+	dev_dbg(&dev->client->dev,
+			"delivery_system=%d frequency=%d bandwidth_hz=%d\n",
+			c->delivery_system, c->frequency,
 			c->bandwidth_hz);
 
 	if (fe->ops.i2c_gate_ctrl)
@@ -176,25 +70,25 @@ static int tda18212_set_params(struct dvb_frontend *fe)
 
 	switch (c->delivery_system) {
 	case SYS_ATSC:
-		if_khz = priv->cfg->if_atsc_vsb;
+		if_khz = dev->cfg.if_atsc_vsb;
 		i = ATSC_VSB;
 		break;
 	case SYS_DVBC_ANNEX_B:
-		if_khz = priv->cfg->if_atsc_qam;
+		if_khz = dev->cfg.if_atsc_qam;
 		i = ATSC_QAM;
 		break;
 	case SYS_DVBT:
 		switch (c->bandwidth_hz) {
 		case 6000000:
-			if_khz = priv->cfg->if_dvbt_6;
+			if_khz = dev->cfg.if_dvbt_6;
 			i = DVBT_6;
 			break;
 		case 7000000:
-			if_khz = priv->cfg->if_dvbt_7;
+			if_khz = dev->cfg.if_dvbt_7;
 			i = DVBT_7;
 			break;
 		case 8000000:
-			if_khz = priv->cfg->if_dvbt_8;
+			if_khz = dev->cfg.if_dvbt_8;
 			i = DVBT_8;
 			break;
 		default:
@@ -205,15 +99,15 @@ static int tda18212_set_params(struct dvb_frontend *fe)
 	case SYS_DVBT2:
 		switch (c->bandwidth_hz) {
 		case 6000000:
-			if_khz = priv->cfg->if_dvbt2_6;
+			if_khz = dev->cfg.if_dvbt2_6;
 			i = DVBT2_6;
 			break;
 		case 7000000:
-			if_khz = priv->cfg->if_dvbt2_7;
+			if_khz = dev->cfg.if_dvbt2_7;
 			i = DVBT2_7;
 			break;
 		case 8000000:
-			if_khz = priv->cfg->if_dvbt2_8;
+			if_khz = dev->cfg.if_dvbt2_8;
 			i = DVBT2_8;
 			break;
 		default:
@@ -223,7 +117,7 @@ static int tda18212_set_params(struct dvb_frontend *fe)
 		break;
 	case SYS_DVBC_ANNEX_A:
 	case SYS_DVBC_ANNEX_C:
-		if_khz = priv->cfg->if_dvbc;
+		if_khz = dev->cfg.if_dvbc;
 		i = DVBC_8;
 		break;
 	default:
@@ -231,15 +125,15 @@ static int tda18212_set_params(struct dvb_frontend *fe)
 		goto error;
 	}
 
-	ret = tda18212_wr_reg(priv, 0x23, bw_params[i][2]);
+	ret = regmap_write(dev->regmap, 0x23, bw_params[i][2]);
 	if (ret)
 		goto error;
 
-	ret = tda18212_wr_reg(priv, 0x06, 0x00);
+	ret = regmap_write(dev->regmap, 0x06, 0x00);
 	if (ret)
 		goto error;
 
-	ret = tda18212_wr_reg(priv, 0x0f, bw_params[i][0]);
+	ret = regmap_write(dev->regmap, 0x0f, bw_params[i][0]);
 	if (ret)
 		goto error;
 
@@ -252,12 +146,12 @@ static int tda18212_set_params(struct dvb_frontend *fe)
 	buf[6] = ((c->frequency / 1000) >>  0) & 0xff;
 	buf[7] = 0xc1;
 	buf[8] = 0x01;
-	ret = tda18212_wr_regs(priv, 0x12, buf, sizeof(buf));
+	ret = regmap_bulk_write(dev->regmap, 0x12, buf, sizeof(buf));
 	if (ret)
 		goto error;
 
 	/* actual IF rounded as it is on register */
-	priv->if_frequency = buf[3] * 50 * 1000;
+	dev->if_frequency = buf[3] * 50 * 1000;
 
 exit:
 	if (fe->ops.i2c_gate_ctrl)
@@ -266,26 +160,19 @@ exit:
 	return ret;
 
 error:
-	dev_dbg(&priv->i2c->dev, "%s: failed=%d\n", __func__, ret);
+	dev_dbg(&dev->client->dev, "failed=%d\n", ret);
 	goto exit;
 }
 
 static int tda18212_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 {
-	struct tda18212_priv *priv = fe->tuner_priv;
+	struct tda18212_dev *dev = fe->tuner_priv;
 
-	*frequency = priv->if_frequency;
+	*frequency = dev->if_frequency;
 
 	return 0;
 }
 
-static int tda18212_release(struct dvb_frontend *fe)
-{
-	kfree(fe->tuner_priv);
-	fe->tuner_priv = NULL;
-	return 0;
-}
-
 static const struct dvb_tuner_ops tda18212_tuner_ops = {
 	.info = {
 		.name           = "NXP TDA18212",
@@ -295,53 +182,110 @@ static const struct dvb_tuner_ops tda18212_tuner_ops = {
 		.frequency_step =      1000,
 	},
 
-	.release       = tda18212_release,
-
 	.set_params    = tda18212_set_params,
 	.get_if_frequency = tda18212_get_if_frequency,
 };
 
-struct dvb_frontend *tda18212_attach(struct dvb_frontend *fe,
-	struct i2c_adapter *i2c, struct tda18212_config *cfg)
+static int tda18212_probe(struct i2c_client *client,
+		const struct i2c_device_id *id)
 {
-	struct tda18212_priv *priv = NULL;
+	struct tda18212_config *cfg = client->dev.platform_data;
+	struct dvb_frontend *fe = cfg->fe;
+	struct tda18212_dev *dev;
 	int ret;
-	u8 val;
+	unsigned int chip_id;
+	char *version;
+	static const struct regmap_config regmap_config = {
+		.reg_bits = 8,
+		.val_bits = 8,
+	};
 
-	priv = kzalloc(sizeof(struct tda18212_priv), GFP_KERNEL);
-	if (priv == NULL)
-		return NULL;
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (dev == NULL) {
+		ret = -ENOMEM;
+		dev_err(&client->dev, "kzalloc() failed\n");
+		goto err;
+	}
 
-	priv->cfg = cfg;
-	priv->i2c = i2c;
-	fe->tuner_priv = priv;
+	memcpy(&dev->cfg, cfg, sizeof(struct tda18212_config));
+	dev->client = client;
+	dev->regmap = devm_regmap_init_i2c(client, &regmap_config);
+	if (IS_ERR(dev->regmap)) {
+		ret = PTR_ERR(dev->regmap);
+		goto err;
+	}
 
+	/* check if the tuner is there */
 	if (fe->ops.i2c_gate_ctrl)
 		fe->ops.i2c_gate_ctrl(fe, 1); /* open I2C-gate */
 
-	/* check if the tuner is there */
-	ret = tda18212_rd_reg(priv, 0x00, &val);
+	ret = regmap_read(dev->regmap, 0x00, &chip_id);
+	dev_dbg(&dev->client->dev, "chip_id=%02x\n", chip_id);
 
 	if (fe->ops.i2c_gate_ctrl)
 		fe->ops.i2c_gate_ctrl(fe, 0); /* close I2C-gate */
 
-	if (!ret)
-		dev_dbg(&priv->i2c->dev, "%s: chip id=%02x\n", __func__, val);
-	if (ret || val != 0xc7) {
-		kfree(priv);
-		return NULL;
+	if (ret)
+		goto err;
+
+	switch (chip_id) {
+	case 0xc7:
+		version = "M"; /* master */
+		break;
+	case 0x47:
+		version = "S"; /* slave */
+		break;
+	default:
+		ret = -ENODEV;
+		goto err;
 	}
 
-	dev_info(&priv->i2c->dev,
-			"%s: NXP TDA18212HN successfully identified\n",
-			KBUILD_MODNAME);
+	dev_info(&dev->client->dev,
+			"NXP TDA18212HN/%s successfully identified\n", version);
 
+	fe->tuner_priv = dev;
 	memcpy(&fe->ops.tuner_ops, &tda18212_tuner_ops,
-		sizeof(struct dvb_tuner_ops));
+			sizeof(struct dvb_tuner_ops));
+	i2c_set_clientdata(client, dev);
 
-	return fe;
+	return 0;
+err:
+	dev_dbg(&client->dev, "failed=%d\n", ret);
+	kfree(dev);
+	return ret;
 }
-EXPORT_SYMBOL(tda18212_attach);
+
+static int tda18212_remove(struct i2c_client *client)
+{
+	struct tda18212_dev *dev = i2c_get_clientdata(client);
+	struct dvb_frontend *fe = dev->cfg.fe;
+
+	dev_dbg(&client->dev, "\n");
+
+	memset(&fe->ops.tuner_ops, 0, sizeof(struct dvb_tuner_ops));
+	fe->tuner_priv = NULL;
+	kfree(dev);
+
+	return 0;
+}
+
+static const struct i2c_device_id tda18212_id[] = {
+	{"tda18212", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, tda18212_id);
+
+static struct i2c_driver tda18212_driver = {
+	.driver = {
+		.owner	= THIS_MODULE,
+		.name	= "tda18212",
+	},
+	.probe		= tda18212_probe,
+	.remove		= tda18212_remove,
+	.id_table	= tda18212_id,
+};
+
+module_i2c_driver(tda18212_driver);
 
 MODULE_DESCRIPTION("NXP TDA18212HN silicon tuner driver");
 MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>");
diff --git a/drivers/media/tuners/tda18212.h b/drivers/media/tuners/tda18212.h
index c36b49e4b274..e58c9096d79c 100644
--- a/drivers/media/tuners/tda18212.h
+++ b/drivers/media/tuners/tda18212.h
@@ -25,8 +25,6 @@
 #include "dvb_frontend.h"
 
 struct tda18212_config {
-	u8 i2c_address;
-
 	u16 if_dvbt_6;
 	u16 if_dvbt_7;
 	u16 if_dvbt_8;
@@ -37,18 +35,11 @@ struct tda18212_config {
 	u16 if_dvbc;
 	u16 if_atsc_vsb;
 	u16 if_atsc_qam;
-};
 
-#if IS_ENABLED(CONFIG_MEDIA_TUNER_TDA18212)
-extern struct dvb_frontend *tda18212_attach(struct dvb_frontend *fe,
-	struct i2c_adapter *i2c, struct tda18212_config *cfg);
-#else
-static inline struct dvb_frontend *tda18212_attach(struct dvb_frontend *fe,
-	struct i2c_adapter *i2c, struct tda18212_config *cfg)
-{
-	printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
-	return NULL;
-}
-#endif
+	/*
+	 * pointer to DVB frontend
+	 */
+	struct dvb_frontend *fe;
+};
 
 #endif
diff --git a/drivers/media/tuners/tda18271-common.c b/drivers/media/tuners/tda18271-common.c
index 18c77afe2e4f..86e5e3110118 100644
--- a/drivers/media/tuners/tda18271-common.c
+++ b/drivers/media/tuners/tda18271-common.c
@@ -714,12 +714,11 @@ fail:
 	return ret;
 }
 
-int _tda_printk(struct tda18271_priv *state, const char *level,
-		const char *func, const char *fmt, ...)
+void _tda_printk(struct tda18271_priv *state, const char *level,
+		 const char *func, const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	int rtn;
 
 	va_start(args, fmt);
 
@@ -727,15 +726,13 @@ int _tda_printk(struct tda18271_priv *state, const char *level,
 	vaf.va = &args;
 
 	if (state)
-		rtn = printk("%s%s: [%d-%04x|%c] %pV",
-			     level, func, i2c_adapter_id(state->i2c_props.adap),
-			     state->i2c_props.addr,
-			     (state->role == TDA18271_MASTER) ? 'M' : 'S',
-			     &vaf);
+		printk("%s%s: [%d-%04x|%c] %pV",
+		       level, func, i2c_adapter_id(state->i2c_props.adap),
+		       state->i2c_props.addr,
+		       (state->role == TDA18271_MASTER) ? 'M' : 'S',
+		       &vaf);
 	else
-		rtn = printk("%s%s: %pV", level, func, &vaf);
+		printk("%s%s: %pV", level, func, &vaf);
 
 	va_end(args);
-
-	return rtn;
 }
diff --git a/drivers/media/tuners/tda18271-priv.h b/drivers/media/tuners/tda18271-priv.h
index 454c152ccaa0..b36a7b754772 100644
--- a/drivers/media/tuners/tda18271-priv.h
+++ b/drivers/media/tuners/tda18271-priv.h
@@ -139,8 +139,8 @@ extern int tda18271_debug;
 #define DBG_CAL  16
 
 __attribute__((format(printf, 4, 5)))
-int _tda_printk(struct tda18271_priv *state, const char *level,
-		const char *func, const char *fmt, ...);
+void _tda_printk(struct tda18271_priv *state, const char *level,
+		 const char *func, const char *fmt, ...);
 
 #define tda_printk(st, lvl, fmt, arg...)			\
 	_tda_printk(st, lvl, __func__, fmt, ##arg)
diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c
index 565eeebb3aeb..d12f5e4ad8bf 100644
--- a/drivers/media/tuners/tuner-xc2028.c
+++ b/drivers/media/tuners/tuner-xc2028.c
@@ -178,67 +178,67 @@ static int xc2028_get_reg(struct xc2028_data *priv, u16 reg, u16 *val)
 #define dump_firm_type(t) 	dump_firm_type_and_int_freq(t, 0)
 static void dump_firm_type_and_int_freq(unsigned int type, u16 int_freq)
 {
-	 if (type & BASE)
+	if (type & BASE)
 		printk("BASE ");
-	 if (type & INIT1)
+	if (type & INIT1)
 		printk("INIT1 ");
-	 if (type & F8MHZ)
+	if (type & F8MHZ)
 		printk("F8MHZ ");
-	 if (type & MTS)
+	if (type & MTS)
 		printk("MTS ");
-	 if (type & D2620)
+	if (type & D2620)
 		printk("D2620 ");
-	 if (type & D2633)
+	if (type & D2633)
 		printk("D2633 ");
-	 if (type & DTV6)
+	if (type & DTV6)
 		printk("DTV6 ");
-	 if (type & QAM)
+	if (type & QAM)
 		printk("QAM ");
-	 if (type & DTV7)
+	if (type & DTV7)
 		printk("DTV7 ");
-	 if (type & DTV78)
+	if (type & DTV78)
 		printk("DTV78 ");
-	 if (type & DTV8)
+	if (type & DTV8)
 		printk("DTV8 ");
-	 if (type & FM)
+	if (type & FM)
 		printk("FM ");
-	 if (type & INPUT1)
+	if (type & INPUT1)
 		printk("INPUT1 ");
-	 if (type & LCD)
+	if (type & LCD)
 		printk("LCD ");
-	 if (type & NOGD)
+	if (type & NOGD)
 		printk("NOGD ");
-	 if (type & MONO)
+	if (type & MONO)
 		printk("MONO ");
-	 if (type & ATSC)
+	if (type & ATSC)
 		printk("ATSC ");
-	 if (type & IF)
+	if (type & IF)
 		printk("IF ");
-	 if (type & LG60)
+	if (type & LG60)
 		printk("LG60 ");
-	 if (type & ATI638)
+	if (type & ATI638)
 		printk("ATI638 ");
-	 if (type & OREN538)
+	if (type & OREN538)
 		printk("OREN538 ");
-	 if (type & OREN36)
+	if (type & OREN36)
 		printk("OREN36 ");
-	 if (type & TOYOTA388)
+	if (type & TOYOTA388)
 		printk("TOYOTA388 ");
-	 if (type & TOYOTA794)
+	if (type & TOYOTA794)
 		printk("TOYOTA794 ");
-	 if (type & DIBCOM52)
+	if (type & DIBCOM52)
 		printk("DIBCOM52 ");
-	 if (type & ZARLINK456)
+	if (type & ZARLINK456)
 		printk("ZARLINK456 ");
-	 if (type & CHINA)
+	if (type & CHINA)
 		printk("CHINA ");
-	 if (type & F6MHZ)
+	if (type & F6MHZ)
 		printk("F6MHZ ");
-	 if (type & INPUT2)
+	if (type & INPUT2)
 		printk("INPUT2 ");
-	 if (type & SCODE)
+	if (type & SCODE)
 		printk("SCODE ");
-	 if (type & HAS_IF)
+	if (type & HAS_IF)
 		printk("HAS_IF_%d ", int_freq);
 }
 
diff --git a/drivers/media/tuners/tuner_it913x.c b/drivers/media/tuners/tuner_it913x.c
deleted file mode 100644
index 3d83c425bccf..000000000000
--- a/drivers/media/tuners/tuner_it913x.c
+++ /dev/null
@@ -1,453 +0,0 @@
-/*
- * ITE Tech IT9137 silicon tuner driver
- *
- *  Copyright (C) 2011 Malcolm Priestley (tvboxspy@gmail.com)
- *  IT9137 Copyright (C) ITE Tech Inc.
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.=
- */
-
-#include "tuner_it913x_priv.h"
-
-struct it913x_state {
-	struct i2c_adapter *i2c_adap;
-	u8 i2c_addr;
-	u8 chip_ver;
-	u8 tuner_type;
-	u8 firmware_ver;
-	u16 tun_xtal;
-	u8 tun_fdiv;
-	u8 tun_clk_mode;
-	u32 tun_fn_min;
-};
-
-/* read multiple registers */
-static int it913x_rd_regs(struct it913x_state *state,
-		u32 reg, u8 *data, u8 count)
-{
-	int ret;
-	u8 b[3];
-	struct i2c_msg msg[2] = {
-		{ .addr = state->i2c_addr, .flags = 0,
-			.buf = b, .len = sizeof(b) },
-		{ .addr = state->i2c_addr, .flags = I2C_M_RD,
-			.buf = data, .len = count }
-	};
-	b[0] = (u8)(reg >> 16) & 0xff;
-	b[1] = (u8)(reg >> 8) & 0xff;
-	b[2] = (u8) reg & 0xff;
-	b[0] |= 0x80; /* All reads from demodulator */
-
-	ret = i2c_transfer(state->i2c_adap, msg, 2);
-
-	return ret;
-}
-
-/* read single register */
-static int it913x_rd_reg(struct it913x_state *state, u32 reg)
-{
-	int ret;
-	u8 b[1];
-	ret = it913x_rd_regs(state, reg, &b[0], sizeof(b));
-	return (ret < 0) ? -ENODEV : b[0];
-}
-
-/* write multiple registers */
-static int it913x_wr_regs(struct it913x_state *state,
-		u8 pro, u32 reg, u8 buf[], u8 count)
-{
-	u8 b[256];
-	struct i2c_msg msg[1] = {
-		{ .addr = state->i2c_addr, .flags = 0,
-		  .buf = b, .len = 3 + count }
-	};
-	int ret;
-	b[0] = (u8)(reg >> 16) & 0xff;
-	b[1] = (u8)(reg >> 8) & 0xff;
-	b[2] = (u8) reg & 0xff;
-	memcpy(&b[3], buf, count);
-
-	if (pro == PRO_DMOD)
-		b[0] |= 0x80;
-
-	ret = i2c_transfer(state->i2c_adap, msg, 1);
-
-	if (ret < 0)
-		return -EIO;
-
-	return 0;
-}
-
-/* write single register */
-static int it913x_wr_reg(struct it913x_state *state,
-		u8 pro, u32 reg, u32 data)
-{
-	int ret;
-	u8 b[4];
-	u8 s;
-
-	b[0] = data >> 24;
-	b[1] = (data >> 16) & 0xff;
-	b[2] = (data >> 8) & 0xff;
-	b[3] = data & 0xff;
-	/* expand write as needed */
-	if (data < 0x100)
-		s = 3;
-	else if (data < 0x1000)
-		s = 2;
-	else if (data < 0x100000)
-		s = 1;
-	else
-		s = 0;
-
-	ret = it913x_wr_regs(state, pro, reg, &b[s], sizeof(b) - s);
-
-	return ret;
-}
-
-static int it913x_script_loader(struct it913x_state *state,
-		struct it913xset *loadscript)
-{
-	int ret, i;
-	if (loadscript == NULL)
-		return -EINVAL;
-
-	for (i = 0; i < 1000; ++i) {
-		if (loadscript[i].pro == 0xff)
-			break;
-		ret = it913x_wr_regs(state, loadscript[i].pro,
-			loadscript[i].address,
-			loadscript[i].reg, loadscript[i].count);
-		if (ret < 0)
-			return -ENODEV;
-	}
-	return 0;
-}
-
-static int it913x_init(struct dvb_frontend *fe)
-{
-	struct it913x_state *state = fe->tuner_priv;
-	int ret, i, reg;
-	u8 val, nv_val;
-	u8 nv[] = {48, 32, 24, 16, 12, 8, 6, 4, 2};
-	u8 b[2];
-
-	reg = it913x_rd_reg(state, 0xec86);
-	switch (reg) {
-	case 0:
-		state->tun_clk_mode = reg;
-		state->tun_xtal = 2000;
-		state->tun_fdiv = 3;
-		val = 16;
-		break;
-	case -ENODEV:
-		return -ENODEV;
-	case 1:
-	default:
-		state->tun_clk_mode = reg;
-		state->tun_xtal = 640;
-		state->tun_fdiv = 1;
-		val = 6;
-		break;
-	}
-
-	reg = it913x_rd_reg(state, 0xed03);
-
-	if (reg < 0)
-		return -ENODEV;
-	else if (reg < ARRAY_SIZE(nv))
-		nv_val = nv[reg];
-	else
-		nv_val = 2;
-
-	for (i = 0; i < 50; i++) {
-		ret = it913x_rd_regs(state, 0xed23, &b[0], sizeof(b));
-		reg = (b[1] << 8) + b[0];
-		if (reg > 0)
-			break;
-		if (ret < 0)
-			return -ENODEV;
-		udelay(2000);
-	}
-	state->tun_fn_min = state->tun_xtal * reg;
-	state->tun_fn_min /= (state->tun_fdiv * nv_val);
-	dev_dbg(&state->i2c_adap->dev, "%s: Tuner fn_min %d\n", __func__,
-			state->tun_fn_min);
-
-	if (state->chip_ver > 1)
-		msleep(50);
-	else {
-		for (i = 0; i < 50; i++) {
-			reg = it913x_rd_reg(state, 0xec82);
-			if (reg > 0)
-				break;
-			if (reg < 0)
-				return -ENODEV;
-			udelay(2000);
-		}
-	}
-
-	/* Power Up Tuner - common all versions */
-	ret = it913x_wr_reg(state, PRO_DMOD, 0xec40, 0x1);
-	ret |= it913x_wr_reg(state, PRO_DMOD, 0xfba8, 0x0);
-	ret |= it913x_wr_reg(state, PRO_DMOD, 0xec57, 0x0);
-	ret |= it913x_wr_reg(state, PRO_DMOD, 0xec58, 0x0);
-
-	return it913x_wr_reg(state, PRO_DMOD, 0xed81, val);
-}
-
-static int it9137_set_params(struct dvb_frontend *fe)
-{
-	struct it913x_state *state = fe->tuner_priv;
-	struct it913xset *set_tuner = set_it9137_template;
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-	u32 bandwidth = p->bandwidth_hz;
-	u32 frequency_m = p->frequency;
-	int ret, reg;
-	u32 frequency = frequency_m / 1000;
-	u32 freq, temp_f, tmp;
-	u16 iqik_m_cal;
-	u16 n_div;
-	u8 n;
-	u8 l_band;
-	u8 lna_band;
-	u8 bw;
-
-	if (state->firmware_ver == 1)
-		set_tuner = set_it9135_template;
-	else
-		set_tuner = set_it9137_template;
-
-	dev_dbg(&state->i2c_adap->dev, "%s: Tuner Frequency %d Bandwidth %d\n",
-			__func__, frequency, bandwidth);
-
-	if (frequency >= 51000 && frequency <= 440000) {
-		l_band = 0;
-		lna_band = 0;
-	} else if (frequency > 440000 && frequency <= 484000) {
-		l_band = 1;
-		lna_band = 1;
-	} else if (frequency > 484000 && frequency <= 533000) {
-		l_band = 1;
-		lna_band = 2;
-	} else if (frequency > 533000 && frequency <= 587000) {
-		l_band = 1;
-		lna_band = 3;
-	} else if (frequency > 587000 && frequency <= 645000) {
-		l_band = 1;
-		lna_band = 4;
-	} else if (frequency > 645000 && frequency <= 710000) {
-		l_band = 1;
-		lna_band = 5;
-	} else if (frequency > 710000 && frequency <= 782000) {
-		l_band = 1;
-		lna_band = 6;
-	} else if (frequency > 782000 && frequency <= 860000) {
-		l_band = 1;
-		lna_band = 7;
-	} else if (frequency > 1450000 && frequency <= 1492000) {
-		l_band = 1;
-		lna_band = 0;
-	} else if (frequency > 1660000 && frequency <= 1685000) {
-		l_band = 1;
-		lna_band = 1;
-	} else
-		return -EINVAL;
-	set_tuner[0].reg[0] = lna_band;
-
-	switch (bandwidth) {
-	case 5000000:
-		bw = 0;
-		break;
-	case 6000000:
-		bw = 2;
-		break;
-	case 7000000:
-		bw = 4;
-		break;
-	default:
-	case 8000000:
-		bw = 6;
-		break;
-	}
-
-	set_tuner[1].reg[0] = bw;
-	set_tuner[2].reg[0] = 0xa0 | (l_band << 3);
-
-	if (frequency > 53000 && frequency <= 74000) {
-		n_div = 48;
-		n = 0;
-	} else if (frequency > 74000 && frequency <= 111000) {
-		n_div = 32;
-		n = 1;
-	} else if (frequency > 111000 && frequency <= 148000) {
-		n_div = 24;
-		n = 2;
-	} else if (frequency > 148000 && frequency <= 222000) {
-		n_div = 16;
-		n = 3;
-	} else if (frequency > 222000 && frequency <= 296000) {
-		n_div = 12;
-		n = 4;
-	} else if (frequency > 296000 && frequency <= 445000) {
-		n_div = 8;
-		n = 5;
-	} else if (frequency > 445000 && frequency <= state->tun_fn_min) {
-		n_div = 6;
-		n = 6;
-	} else if (frequency > state->tun_fn_min && frequency <= 950000) {
-		n_div = 4;
-		n = 7;
-	} else if (frequency > 1450000 && frequency <= 1680000) {
-		n_div = 2;
-		n = 0;
-	} else
-		return -EINVAL;
-
-	reg = it913x_rd_reg(state, 0xed81);
-	iqik_m_cal = (u16)reg * n_div;
-
-	if (reg < 0x20) {
-		if (state->tun_clk_mode == 0)
-			iqik_m_cal = (iqik_m_cal * 9) >> 5;
-		else
-			iqik_m_cal >>= 1;
-	} else {
-		iqik_m_cal = 0x40 - iqik_m_cal;
-		if (state->tun_clk_mode == 0)
-			iqik_m_cal = ~((iqik_m_cal * 9) >> 5);
-		else
-			iqik_m_cal = ~(iqik_m_cal >> 1);
-	}
-
-	temp_f = frequency * (u32)n_div * (u32)state->tun_fdiv;
-	freq = temp_f / state->tun_xtal;
-	tmp = freq * state->tun_xtal;
-
-	if ((temp_f - tmp) >= (state->tun_xtal >> 1))
-		freq++;
-
-	freq += (u32) n << 13;
-	/* Frequency OMEGA_IQIK_M_CAL_MID*/
-	temp_f = freq + (u32)iqik_m_cal;
-
-	set_tuner[3].reg[0] =  temp_f & 0xff;
-	set_tuner[4].reg[0] =  (temp_f >> 8) & 0xff;
-
-	dev_dbg(&state->i2c_adap->dev, "%s: High Frequency = %04x\n",
-			__func__, temp_f);
-
-	/* Lower frequency */
-	set_tuner[5].reg[0] =  freq & 0xff;
-	set_tuner[6].reg[0] =  (freq >> 8) & 0xff;
-
-	dev_dbg(&state->i2c_adap->dev, "%s: low Frequency = %04x\n",
-			__func__, freq);
-
-	ret = it913x_script_loader(state, set_tuner);
-
-	return (ret < 0) ? -ENODEV : 0;
-}
-
-/* Power sequence */
-/* Power Up	Tuner on -> Frontend suspend off -> Tuner clk on */
-/* Power Down	Frontend suspend on -> Tuner clk off -> Tuner off */
-
-static int it913x_sleep(struct dvb_frontend *fe)
-{
-	struct it913x_state *state = fe->tuner_priv;
-	return it913x_script_loader(state, it9137_tuner_off);
-}
-
-static int it913x_release(struct dvb_frontend *fe)
-{
-	kfree(fe->tuner_priv);
-	return 0;
-}
-
-static const struct dvb_tuner_ops it913x_tuner_ops = {
-	.info = {
-		.name           = "ITE Tech IT913X",
-		.frequency_min  = 174000000,
-		.frequency_max  = 862000000,
-	},
-
-	.release = it913x_release,
-
-	.init = it913x_init,
-	.sleep = it913x_sleep,
-	.set_params = it9137_set_params,
-};
-
-struct dvb_frontend *it913x_attach(struct dvb_frontend *fe,
-		struct i2c_adapter *i2c_adap, u8 i2c_addr, u8 config)
-{
-	struct it913x_state *state = NULL;
-	int ret;
-
-	/* allocate memory for the internal state */
-	state = kzalloc(sizeof(struct it913x_state), GFP_KERNEL);
-	if (state == NULL)
-		return NULL;
-
-	state->i2c_adap = i2c_adap;
-	state->i2c_addr = i2c_addr;
-
-	switch (config) {
-	case AF9033_TUNER_IT9135_38:
-	case AF9033_TUNER_IT9135_51:
-	case AF9033_TUNER_IT9135_52:
-		state->chip_ver = 0x01;
-		break;
-	case AF9033_TUNER_IT9135_60:
-	case AF9033_TUNER_IT9135_61:
-	case AF9033_TUNER_IT9135_62:
-		state->chip_ver = 0x02;
-		break;
-	default:
-		dev_dbg(&i2c_adap->dev,
-				"%s: invalid config=%02x\n", __func__, config);
-		goto error;
-	}
-
-	state->tuner_type = config;
-	state->firmware_ver = 1;
-
-	/* tuner RF initial */
-	ret = it913x_wr_reg(state, PRO_DMOD, 0xec4c, 0x68);
-	if (ret < 0)
-		goto error;
-
-	fe->tuner_priv = state;
-	memcpy(&fe->ops.tuner_ops, &it913x_tuner_ops,
-			sizeof(struct dvb_tuner_ops));
-
-	dev_info(&i2c_adap->dev,
-			"%s: ITE Tech IT913X successfully attached\n",
-			KBUILD_MODNAME);
-	dev_dbg(&i2c_adap->dev, "%s: config=%02x chip_ver=%02x\n",
-			__func__, config, state->chip_ver);
-
-	return fe;
-error:
-	kfree(state);
-	return NULL;
-}
-EXPORT_SYMBOL(it913x_attach);
-
-MODULE_DESCRIPTION("ITE Tech IT913X silicon tuner driver");
-MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/media/tuners/tuner_it913x_priv.h b/drivers/media/tuners/tuner_it913x_priv.h
deleted file mode 100644
index ce652108aa5d..000000000000
--- a/drivers/media/tuners/tuner_it913x_priv.h
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- * ITE Tech IT9137 silicon tuner driver
- *
- *  Copyright (C) 2011 Malcolm Priestley (tvboxspy@gmail.com)
- *  IT9137 Copyright (C) ITE Tech Inc.
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.=
- */
-
-#ifndef IT913X_PRIV_H
-#define IT913X_PRIV_H
-
-#include "tuner_it913x.h"
-#include "af9033.h"
-
-#define PRO_LINK		0x0
-#define PRO_DMOD		0x1
-#define TRIGGER_OFSM		0x0000
-
-struct it913xset {	u32 pro;
-			u32 address;
-			u8 reg[15];
-			u8 count;
-};
-
-/* Tuner setting scripts (still keeping it9137) */
-static struct it913xset it9137_tuner_off[] = {
-	{PRO_DMOD, 0xfba8, {0x01}, 0x01}, /* Tuner Clock Off  */
-	{PRO_DMOD, 0xec40, {0x00}, 0x01}, /* Power Down Tuner */
-	{PRO_DMOD, 0xec02, {0x3f, 0x1f, 0x3f, 0x3f}, 0x04},
-	{PRO_DMOD, 0xec06, {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-				0x00, 0x00, 0x00, 0x00}, 0x0c},
-	{PRO_DMOD, 0xec12, {0x00, 0x00, 0x00, 0x00}, 0x04},
-	{PRO_DMOD, 0xec17, {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-				0x00}, 0x09},
-	{PRO_DMOD, 0xec22, {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-				0x00, 0x00}, 0x0a},
-	{PRO_DMOD, 0xec20, {0x00}, 0x01},
-	{PRO_DMOD, 0xec3f, {0x01}, 0x01},
-	{0xff, 0x0000, {0x00}, 0x00}, /* Terminating Entry */
-};
-
-static struct it913xset set_it9135_template[] = {
-	{PRO_DMOD, 0xee06, {0x00}, 0x01},
-	{PRO_DMOD, 0xec56, {0x00}, 0x01},
-	{PRO_DMOD, 0xec4c, {0x00}, 0x01},
-	{PRO_DMOD, 0xec4d, {0x00}, 0x01},
-	{PRO_DMOD, 0xec4e, {0x00}, 0x01},
-	{PRO_DMOD, 0x011e, {0x00}, 0x01}, /* Older Devices */
-	{PRO_DMOD, 0x011f, {0x00}, 0x01},
-	{0xff, 0x0000, {0x00}, 0x00}, /* Terminating Entry */
-};
-
-static struct it913xset set_it9137_template[] = {
-	{PRO_DMOD, 0xee06, {0x00}, 0x01},
-	{PRO_DMOD, 0xec56, {0x00}, 0x01},
-	{PRO_DMOD, 0xec4c, {0x00}, 0x01},
-	{PRO_DMOD, 0xec4d, {0x00}, 0x01},
-	{PRO_DMOD, 0xec4e, {0x00}, 0x01},
-	{PRO_DMOD, 0xec4f, {0x00}, 0x01},
-	{PRO_DMOD, 0xec50, {0x00}, 0x01},
-	{0xff, 0x0000, {0x00}, 0x00}, /* Terminating Entry */
-};
-
-#endif
diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c
index f9ab79e3432d..219ebafae70f 100644
--- a/drivers/media/tuners/xc4000.c
+++ b/drivers/media/tuners/xc4000.c
@@ -569,67 +569,67 @@ static int xc4000_readreg(struct xc4000_priv *priv, u16 reg, u16 *val)
 #define dump_firm_type(t)	dump_firm_type_and_int_freq(t, 0)
 static void dump_firm_type_and_int_freq(unsigned int type, u16 int_freq)
 {
-	 if (type & BASE)
+	if (type & BASE)
 		printk(KERN_CONT "BASE ");
-	 if (type & INIT1)
+	if (type & INIT1)
 		printk(KERN_CONT "INIT1 ");
-	 if (type & F8MHZ)
+	if (type & F8MHZ)
 		printk(KERN_CONT "F8MHZ ");
-	 if (type & MTS)
+	if (type & MTS)
 		printk(KERN_CONT "MTS ");
-	 if (type & D2620)
+	if (type & D2620)
 		printk(KERN_CONT "D2620 ");
-	 if (type & D2633)
+	if (type & D2633)
 		printk(KERN_CONT "D2633 ");
-	 if (type & DTV6)
+	if (type & DTV6)
 		printk(KERN_CONT "DTV6 ");
-	 if (type & QAM)
+	if (type & QAM)
 		printk(KERN_CONT "QAM ");
-	 if (type & DTV7)
+	if (type & DTV7)
 		printk(KERN_CONT "DTV7 ");
-	 if (type & DTV78)
+	if (type & DTV78)
 		printk(KERN_CONT "DTV78 ");
-	 if (type & DTV8)
+	if (type & DTV8)
 		printk(KERN_CONT "DTV8 ");
-	 if (type & FM)
+	if (type & FM)
 		printk(KERN_CONT "FM ");
-	 if (type & INPUT1)
+	if (type & INPUT1)
 		printk(KERN_CONT "INPUT1 ");
-	 if (type & LCD)
+	if (type & LCD)
 		printk(KERN_CONT "LCD ");
-	 if (type & NOGD)
+	if (type & NOGD)
 		printk(KERN_CONT "NOGD ");
-	 if (type & MONO)
+	if (type & MONO)
 		printk(KERN_CONT "MONO ");
-	 if (type & ATSC)
+	if (type & ATSC)
 		printk(KERN_CONT "ATSC ");
-	 if (type & IF)
+	if (type & IF)
 		printk(KERN_CONT "IF ");
-	 if (type & LG60)
+	if (type & LG60)
 		printk(KERN_CONT "LG60 ");
-	 if (type & ATI638)
+	if (type & ATI638)
 		printk(KERN_CONT "ATI638 ");
-	 if (type & OREN538)
+	if (type & OREN538)
 		printk(KERN_CONT "OREN538 ");
-	 if (type & OREN36)
+	if (type & OREN36)
 		printk(KERN_CONT "OREN36 ");
-	 if (type & TOYOTA388)
+	if (type & TOYOTA388)
 		printk(KERN_CONT "TOYOTA388 ");
-	 if (type & TOYOTA794)
+	if (type & TOYOTA794)
 		printk(KERN_CONT "TOYOTA794 ");
-	 if (type & DIBCOM52)
+	if (type & DIBCOM52)
 		printk(KERN_CONT "DIBCOM52 ");
-	 if (type & ZARLINK456)
+	if (type & ZARLINK456)
 		printk(KERN_CONT "ZARLINK456 ");
-	 if (type & CHINA)
+	if (type & CHINA)
 		printk(KERN_CONT "CHINA ");
-	 if (type & F6MHZ)
+	if (type & F6MHZ)
 		printk(KERN_CONT "F6MHZ ");
-	 if (type & INPUT2)
+	if (type & INPUT2)
 		printk(KERN_CONT "INPUT2 ");
-	 if (type & SCODE)
+	if (type & SCODE)
 		printk(KERN_CONT "SCODE ");
-	 if (type & HAS_IF)
+	if (type & HAS_IF)
 		printk(KERN_CONT "HAS_IF_%d ", int_freq);
 }
 
diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c
index e135760f7d48..e44c8aba6074 100644
--- a/drivers/media/tuners/xc5000.c
+++ b/drivers/media/tuners/xc5000.c
@@ -59,6 +59,7 @@ struct xc5000_priv {
 	u32 freq_hz, freq_offset;
 	u32 bandwidth;
 	u8  video_standard;
+	unsigned int mode;
 	u8  rf_mode;
 	u8  radio_input;
 
@@ -69,6 +70,8 @@ struct xc5000_priv {
 
 	struct dvb_frontend *fe;
 	struct delayed_work timer_sleep;
+
+	const struct firmware   *firmware;
 };
 
 /* Misc Defines */
@@ -712,9 +715,50 @@ static void xc_debug_dump(struct xc5000_priv *priv)
 	}
 }
 
-static int xc5000_set_params(struct dvb_frontend *fe)
+static int xc5000_tune_digital(struct dvb_frontend *fe)
+{
+	struct xc5000_priv *priv = fe->tuner_priv;
+	int ret;
+	u32 bw = fe->dtv_property_cache.bandwidth_hz;
+
+	ret = xc_set_signal_source(priv, priv->rf_mode);
+	if (ret != 0) {
+		printk(KERN_ERR
+			"xc5000: xc_set_signal_source(%d) failed\n",
+			priv->rf_mode);
+		return -EREMOTEIO;
+	}
+
+	ret = xc_set_tv_standard(priv,
+		xc5000_standard[priv->video_standard].video_mode,
+		xc5000_standard[priv->video_standard].audio_mode, 0);
+	if (ret != 0) {
+		printk(KERN_ERR "xc5000: xc_set_tv_standard failed\n");
+		return -EREMOTEIO;
+	}
+
+	ret = xc_set_IF_frequency(priv, priv->if_khz);
+	if (ret != 0) {
+		printk(KERN_ERR "xc5000: xc_Set_IF_frequency(%d) failed\n",
+		       priv->if_khz);
+		return -EIO;
+	}
+
+	xc_write_reg(priv, XREG_OUTPUT_AMP, 0x8a);
+
+	xc_tune_channel(priv, priv->freq_hz, XC_TUNE_DIGITAL);
+
+	if (debug)
+		xc_debug_dump(priv);
+
+	priv->bandwidth = bw;
+
+	return 0;
+}
+
+static int xc5000_set_digital_params(struct dvb_frontend *fe)
 {
-	int ret, b;
+	int b;
 	struct xc5000_priv *priv = fe->tuner_priv;
 	u32 bw = fe->dtv_property_cache.bandwidth_hz;
 	u32 freq = fe->dtv_property_cache.frequency;
@@ -794,43 +838,12 @@ static int xc5000_set_params(struct dvb_frontend *fe)
 	}
 
 	priv->freq_hz = freq - priv->freq_offset;
+	priv->mode = V4L2_TUNER_DIGITAL_TV;
 
 	dprintk(1, "%s() frequency=%d (compensated to %d)\n",
 		__func__, freq, priv->freq_hz);
 
-	ret = xc_set_signal_source(priv, priv->rf_mode);
-	if (ret != 0) {
-		printk(KERN_ERR
-			"xc5000: xc_set_signal_source(%d) failed\n",
-			priv->rf_mode);
-		return -EREMOTEIO;
-	}
-
-	ret = xc_set_tv_standard(priv,
-		xc5000_standard[priv->video_standard].video_mode,
-		xc5000_standard[priv->video_standard].audio_mode, 0);
-	if (ret != 0) {
-		printk(KERN_ERR "xc5000: xc_set_tv_standard failed\n");
-		return -EREMOTEIO;
-	}
-
-	ret = xc_set_IF_frequency(priv, priv->if_khz);
-	if (ret != 0) {
-		printk(KERN_ERR "xc5000: xc_Set_IF_frequency(%d) failed\n",
-		       priv->if_khz);
-		return -EIO;
-	}
-
-	xc_write_reg(priv, XREG_OUTPUT_AMP, 0x8a);
-
-	xc_tune_channel(priv, priv->freq_hz, XC_TUNE_DIGITAL);
-
-	if (debug)
-		xc_debug_dump(priv);
-
-	priv->bandwidth = bw;
-
-	return 0;
+	return xc5000_tune_digital(fe);
 }
 
 static int xc5000_is_firmware_loaded(struct dvb_frontend *fe)
@@ -852,12 +865,10 @@ static int xc5000_is_firmware_loaded(struct dvb_frontend *fe)
 	return ret;
 }
 
-static int xc5000_set_tv_freq(struct dvb_frontend *fe,
-	struct analog_parameters *params)
+static void xc5000_config_tv(struct dvb_frontend *fe,
+			     struct analog_parameters *params)
 {
 	struct xc5000_priv *priv = fe->tuner_priv;
-	u16 pll_lock_status;
-	int ret;
 
 	dprintk(1, "%s() frequency=%d (in units of 62.5khz)\n",
 		__func__, params->frequency);
@@ -876,42 +887,49 @@ static int xc5000_set_tv_freq(struct dvb_frontend *fe,
 	if (params->std & V4L2_STD_MN) {
 		/* default to BTSC audio standard */
 		priv->video_standard = MN_NTSC_PAL_BTSC;
-		goto tune_channel;
+		return;
 	}
 
 	if (params->std & V4L2_STD_PAL_BG) {
 		/* default to NICAM audio standard */
 		priv->video_standard = BG_PAL_NICAM;
-		goto tune_channel;
+		return;
 	}
 
 	if (params->std & V4L2_STD_PAL_I) {
 		/* default to NICAM audio standard */
 		priv->video_standard = I_PAL_NICAM;
-		goto tune_channel;
+		return;
 	}
 
 	if (params->std & V4L2_STD_PAL_DK) {
 		/* default to NICAM audio standard */
 		priv->video_standard = DK_PAL_NICAM;
-		goto tune_channel;
+		return;
 	}
 
 	if (params->std & V4L2_STD_SECAM_DK) {
 		/* default to A2 DK1 audio standard */
 		priv->video_standard = DK_SECAM_A2DK1;
-		goto tune_channel;
+		return;
 	}
 
 	if (params->std & V4L2_STD_SECAM_L) {
 		priv->video_standard = L_SECAM_NICAM;
-		goto tune_channel;
+		return;
 	}
 
 	if (params->std & V4L2_STD_SECAM_LC) {
 		priv->video_standard = LC_SECAM_NICAM;
-		goto tune_channel;
+		return;
 	}
+}
+
+static int xc5000_set_tv_freq(struct dvb_frontend *fe)
+{
+	struct xc5000_priv *priv = fe->tuner_priv;
+	u16 pll_lock_status;
+	int ret;
 
 tune_channel:
 	ret = xc_set_signal_source(priv, priv->rf_mode);
@@ -955,12 +973,11 @@ tune_channel:
 	return 0;
 }
 
-static int xc5000_set_radio_freq(struct dvb_frontend *fe,
-	struct analog_parameters *params)
+static int xc5000_config_radio(struct dvb_frontend *fe,
+			       struct analog_parameters *params)
+
 {
 	struct xc5000_priv *priv = fe->tuner_priv;
-	int ret = -EINVAL;
-	u8 radio_input;
 
 	dprintk(1, "%s() frequency=%d (in units of khz)\n",
 		__func__, params->frequency);
@@ -970,6 +987,18 @@ static int xc5000_set_radio_freq(struct dvb_frontend *fe,
 		return -EINVAL;
 	}
 
+	priv->freq_hz = params->frequency * 125 / 2;
+	priv->rf_mode = XC_RF_MODE_AIR;
+
+	return 0;
+}
+
+static int xc5000_set_radio_freq(struct dvb_frontend *fe)
+{
+	struct xc5000_priv *priv = fe->tuner_priv;
+	int ret;
+	u8 radio_input;
+
 	if (priv->radio_input == XC5000_RADIO_FM1)
 		radio_input = FM_RADIO_INPUT1;
 	else if  (priv->radio_input == XC5000_RADIO_FM2)
@@ -982,10 +1011,6 @@ static int xc5000_set_radio_freq(struct dvb_frontend *fe,
 		return -EINVAL;
 	}
 
-	priv->freq_hz = params->frequency * 125 / 2;
-
-	priv->rf_mode = XC_RF_MODE_AIR;
-
 	ret = xc_set_tv_standard(priv, xc5000_standard[radio_input].video_mode,
 			       xc5000_standard[radio_input].audio_mode, radio_input);
 
@@ -1013,34 +1038,53 @@ static int xc5000_set_radio_freq(struct dvb_frontend *fe,
 	return 0;
 }
 
-static int xc5000_set_analog_params(struct dvb_frontend *fe,
-			     struct analog_parameters *params)
+static int xc5000_set_params(struct dvb_frontend *fe)
 {
 	struct xc5000_priv *priv = fe->tuner_priv;
-	int ret = -EINVAL;
-
-	if (priv->i2c_props.adap == NULL)
-		return -EINVAL;
 
 	if (xc_load_fw_and_init_tuner(fe, 0) != 0) {
 		dprintk(1, "Unable to load firmware and init tuner\n");
 		return -EINVAL;
 	}
 
+	switch (priv->mode) {
+	case V4L2_TUNER_RADIO:
+		return xc5000_set_radio_freq(fe);
+	case V4L2_TUNER_ANALOG_TV:
+		return xc5000_set_tv_freq(fe);
+	case V4L2_TUNER_DIGITAL_TV:
+		return xc5000_tune_digital(fe);
+	}
+
+	return 0;
+}
+
+static int xc5000_set_analog_params(struct dvb_frontend *fe,
+			     struct analog_parameters *params)
+{
+	struct xc5000_priv *priv = fe->tuner_priv;
+	int ret;
+
+	if (priv->i2c_props.adap == NULL)
+		return -EINVAL;
+
 	switch (params->mode) {
 	case V4L2_TUNER_RADIO:
-		ret = xc5000_set_radio_freq(fe, params);
+		ret = xc5000_config_radio(fe, params);
+		if (ret)
+			return ret;
 		break;
 	case V4L2_TUNER_ANALOG_TV:
-	case V4L2_TUNER_DIGITAL_TV:
-		ret = xc5000_set_tv_freq(fe, params);
+		xc5000_config_tv(fe, params);
+		break;
+	default:
 		break;
 	}
+	priv->mode = params->mode;
 
-	return ret;
+	return xc5000_set_params(fe);
 }
 
-
 static int xc5000_get_frequency(struct dvb_frontend *fe, u32 *freq)
 {
 	struct xc5000_priv *priv = fe->tuner_priv;
@@ -1094,20 +1138,23 @@ static int xc_load_fw_and_init_tuner(struct dvb_frontend *fe, int force)
 	if (!force && xc5000_is_firmware_loaded(fe) == 0)
 		return 0;
 
-	ret = request_firmware(&fw, desired_fw->name,
-			       priv->i2c_props.adap->dev.parent);
-	if (ret) {
-		printk(KERN_ERR "xc5000: Upload failed. (file not found?)\n");
-		return ret;
-	}
-
-	dprintk(1, "firmware read %Zu bytes.\n", fw->size);
+	if (!priv->firmware) {
+		ret = request_firmware(&fw, desired_fw->name,
+					priv->i2c_props.adap->dev.parent);
+		if (ret) {
+			pr_err("xc5000: Upload failed. rc %d\n", ret);
+			return ret;
+		}
+		dprintk(1, "firmware read %Zu bytes.\n", fw->size);
 
-	if (fw->size != desired_fw->size) {
-		printk(KERN_ERR "xc5000: Firmware file with incorrect size\n");
-		ret = -EINVAL;
-		goto err;
-	}
+		if (fw->size != desired_fw->size) {
+			pr_err("xc5000: Firmware file with incorrect size\n");
+			release_firmware(fw);
+			return -EINVAL;
+		}
+		priv->firmware = fw;
+	} else
+		fw = priv->firmware;
 
 	/* Try up to 5 times to load firmware */
 	for (i = 0; i < 5; i++) {
@@ -1190,7 +1237,6 @@ err:
 	else
 		printk(KERN_CONT " - too many retries. Giving up\n");
 
-	release_firmware(fw);
 	return ret;
 }
 
@@ -1229,6 +1275,38 @@ static int xc5000_sleep(struct dvb_frontend *fe)
 	return 0;
 }
 
+static int xc5000_suspend(struct dvb_frontend *fe)
+{
+	struct xc5000_priv *priv = fe->tuner_priv;
+	int ret;
+
+	dprintk(1, "%s()\n", __func__);
+
+	cancel_delayed_work(&priv->timer_sleep);
+
+	ret = xc5000_tuner_reset(fe);
+	if (ret != 0)
+		printk(KERN_ERR
+			"xc5000: %s() unable to shutdown tuner\n",
+			__func__);
+
+	return 0;
+}
+
+static int xc5000_resume(struct dvb_frontend *fe)
+{
+	struct xc5000_priv *priv = fe->tuner_priv;
+
+	dprintk(1, "%s()\n", __func__);
+
+	/* suspended before firmware is loaded.
+	   Avoid firmware load in resume path. */
+	if (!priv->firmware)
+		return 0;
+
+	return xc5000_set_params(fe);
+}
+
 static int xc5000_init(struct dvb_frontend *fe)
 {
 	struct xc5000_priv *priv = fe->tuner_priv;
@@ -1256,6 +1334,8 @@ static int xc5000_release(struct dvb_frontend *fe)
 	if (priv) {
 		cancel_delayed_work(&priv->timer_sleep);
 		hybrid_tuner_release_state(priv);
+		if (priv->firmware)
+			release_firmware(priv->firmware);
 	}
 
 	mutex_unlock(&xc5000_list_mutex);
@@ -1293,9 +1373,11 @@ static const struct dvb_tuner_ops xc5000_tuner_ops = {
 	.release	   = xc5000_release,
 	.init		   = xc5000_init,
 	.sleep		   = xc5000_sleep,
+	.suspend	   = xc5000_suspend,
+	.resume		   = xc5000_resume,
 
 	.set_config	   = xc5000_set_config,
-	.set_params	   = xc5000_set_params,
+	.set_params	   = xc5000_set_digital_params,
 	.set_analog_params = xc5000_set_analog_params,
 	.get_frequency	   = xc5000_get_frequency,
 	.get_if_frequency  = xc5000_get_if_frequency,
diff --git a/drivers/media/usb/Kconfig b/drivers/media/usb/Kconfig
index 94d51e092db3..056181f2f569 100644
--- a/drivers/media/usb/Kconfig
+++ b/drivers/media/usb/Kconfig
@@ -46,6 +46,7 @@ source "drivers/media/usb/ttusb-budget/Kconfig"
 source "drivers/media/usb/ttusb-dec/Kconfig"
 source "drivers/media/usb/siano/Kconfig"
 source "drivers/media/usb/b2c2/Kconfig"
+source "drivers/media/usb/as102/Kconfig"
 endif
 
 if (MEDIA_CAMERA_SUPPORT || MEDIA_ANALOG_TV_SUPPORT || MEDIA_DIGITAL_TV_SUPPORT)
@@ -55,8 +56,9 @@ endif
 
 if MEDIA_SDR_SUPPORT
 	comment "Software defined radio USB devices"
-source "drivers/media/usb/msi2500/Kconfig"
 source "drivers/media/usb/airspy/Kconfig"
+source "drivers/media/usb/hackrf/Kconfig"
+source "drivers/media/usb/msi2500/Kconfig"
 endif
 
 endif #MEDIA_USB_SUPPORT
diff --git a/drivers/media/usb/Makefile b/drivers/media/usb/Makefile
index f438efffefc5..6f2eb7c8416c 100644
--- a/drivers/media/usb/Makefile
+++ b/drivers/media/usb/Makefile
@@ -9,8 +9,9 @@ obj-y += zr364xx/ stkwebcam/ s2255/
 obj-$(CONFIG_USB_VIDEO_CLASS)	+= uvc/
 obj-$(CONFIG_USB_GSPCA)         += gspca/
 obj-$(CONFIG_USB_PWC)           += pwc/
-obj-$(CONFIG_USB_MSI2500)       += msi2500/
 obj-$(CONFIG_USB_AIRSPY)        += airspy/
+obj-$(CONFIG_USB_HACKRF)        += hackrf/
+obj-$(CONFIG_USB_MSI2500)       += msi2500/
 obj-$(CONFIG_VIDEO_CPIA2) += cpia2/
 obj-$(CONFIG_VIDEO_AU0828) += au0828/
 obj-$(CONFIG_VIDEO_HDPVR)	+= hdpvr/
@@ -23,3 +24,4 @@ obj-$(CONFIG_VIDEO_TM6000) += tm6000/
 obj-$(CONFIG_VIDEO_EM28XX) += em28xx/
 obj-$(CONFIG_VIDEO_USBTV) += usbtv/
 obj-$(CONFIG_VIDEO_GO7007) += go7007/
+obj-$(CONFIG_DVB_AS102) += as102/
diff --git a/drivers/media/usb/airspy/airspy.c b/drivers/media/usb/airspy/airspy.c
index cb0e515d80ae..4069234abed5 100644
--- a/drivers/media/usb/airspy/airspy.c
+++ b/drivers/media/usb/airspy/airspy.c
@@ -107,6 +107,7 @@ struct airspy {
 #define USB_STATE_URB_BUF  (1 << 3)
 	unsigned long flags;
 
+	struct device *dev;
 	struct usb_device *udev;
 	struct video_device vdev;
 	struct v4l2_device v4l2_dev;
@@ -154,16 +155,15 @@ struct airspy {
 	unsigned int sample_measured;
 };
 
-#define airspy_dbg_usb_control_msg(_udev, _r, _t, _v, _i, _b, _l) { \
+#define airspy_dbg_usb_control_msg(_dev, _r, _t, _v, _i, _b, _l) { \
 	char *_direction; \
 	if (_t & USB_DIR_IN) \
 		_direction = "<<<"; \
 	else \
 		_direction = ">>>"; \
-	dev_dbg(&_udev->dev, "%s: %02x %02x %02x %02x %02x %02x %02x %02x " \
-			"%s %*ph\n",  __func__, _t, _r, _v & 0xff, _v >> 8, \
-			_i & 0xff, _i >> 8, _l & 0xff, _l >> 8, _direction, \
-			_l, _b); \
+	dev_dbg(_dev, "%02x %02x %02x %02x %02x %02x %02x %02x %s %*ph\n", \
+			_t, _r, _v & 0xff, _v >> 8, _i & 0xff, _i >> 8, \
+			_l & 0xff, _l >> 8, _direction, _l, _b); \
 }
 
 /* execute firmware command */
@@ -192,7 +192,7 @@ static int airspy_ctrl_msg(struct airspy *s, u8 request, u16 value, u16 index,
 		requesttype = (USB_TYPE_VENDOR | USB_DIR_IN);
 		break;
 	default:
-		dev_err(&s->udev->dev, "Unknown command %02x\n", request);
+		dev_err(s->dev, "Unknown command %02x\n", request);
 		ret = -EINVAL;
 		goto err;
 	}
@@ -203,11 +203,10 @@ static int airspy_ctrl_msg(struct airspy *s, u8 request, u16 value, u16 index,
 
 	ret = usb_control_msg(s->udev, pipe, request, requesttype, value,
 			index, s->buf, size, 1000);
-	airspy_dbg_usb_control_msg(s->udev, request, requesttype, value,
+	airspy_dbg_usb_control_msg(s->dev, request, requesttype, value,
 			index, s->buf, size);
 	if (ret < 0) {
-		dev_err(&s->udev->dev,
-				"usb_control_msg() failed %d request %02x\n",
+		dev_err(s->dev, "usb_control_msg() failed %d request %02x\n",
 				ret, request);
 		goto err;
 	}
@@ -224,7 +223,7 @@ err:
 /* Private functions */
 static struct airspy_frame_buf *airspy_get_next_fill_buf(struct airspy *s)
 {
-	unsigned long flags = 0;
+	unsigned long flags;
 	struct airspy_frame_buf *buf = NULL;
 
 	spin_lock_irqsave(&s->queued_bufs_lock, flags);
@@ -251,16 +250,18 @@ static unsigned int airspy_convert_stream(struct airspy *s,
 		dst_len = 0;
 	}
 
-	/* calculate samping rate and output it in 10 seconds intervals */
+	/* calculate sample rate and output it in 10 seconds intervals */
 	if (unlikely(time_is_before_jiffies(s->jiffies_next))) {
 		#define MSECS 10000UL
+		unsigned int msecs = jiffies_to_msecs(jiffies -
+				s->jiffies_next + msecs_to_jiffies(MSECS));
 		unsigned int samples = s->sample - s->sample_measured;
+
 		s->jiffies_next = jiffies + msecs_to_jiffies(MSECS);
 		s->sample_measured = s->sample;
-		dev_dbg(&s->udev->dev,
-				"slen=%d samples=%u msecs=%lu sample rate=%lu\n",
-				src_len, samples, MSECS,
-				samples * 1000UL / MSECS);
+		dev_dbg(s->dev, "slen=%u samples=%u msecs=%u sample rate=%lu\n",
+				src_len, samples, msecs,
+				samples * 1000UL / msecs);
 	}
 
 	/* total number of samples */
@@ -278,9 +279,8 @@ static void airspy_urb_complete(struct urb *urb)
 	struct airspy *s = urb->context;
 	struct airspy_frame_buf *fbuf;
 
-	dev_dbg_ratelimited(&s->udev->dev,
-			"%s: status=%d length=%d/%d errors=%d\n",
-			__func__, urb->status, urb->actual_length,
+	dev_dbg_ratelimited(s->dev, "status=%d length=%d/%d errors=%d\n",
+			urb->status, urb->actual_length,
 			urb->transfer_buffer_length, urb->error_count);
 
 	switch (urb->status) {
@@ -292,8 +292,7 @@ static void airspy_urb_complete(struct urb *urb)
 	case -ESHUTDOWN:
 		return;
 	default:            /* error */
-		dev_err_ratelimited(&s->udev->dev, "URB failed %d\n",
-				urb->status);
+		dev_err_ratelimited(s->dev, "URB failed %d\n", urb->status);
 		break;
 	}
 
@@ -304,7 +303,7 @@ static void airspy_urb_complete(struct urb *urb)
 		fbuf = airspy_get_next_fill_buf(s);
 		if (unlikely(fbuf == NULL)) {
 			s->vb_full++;
-			dev_notice_ratelimited(&s->udev->dev,
+			dev_notice_ratelimited(s->dev,
 					"videobuf is full, %d packets dropped\n",
 					s->vb_full);
 			goto skip;
@@ -328,7 +327,7 @@ static int airspy_kill_urbs(struct airspy *s)
 	int i;
 
 	for (i = s->urbs_submitted - 1; i >= 0; i--) {
-		dev_dbg(&s->udev->dev, "%s: kill urb=%d\n", __func__, i);
+		dev_dbg(s->dev, "kill urb=%d\n", i);
 		/* stop the URB */
 		usb_kill_urb(s->urb_list[i]);
 	}
@@ -342,11 +341,10 @@ static int airspy_submit_urbs(struct airspy *s)
 	int i, ret;
 
 	for (i = 0; i < s->urbs_initialized; i++) {
-		dev_dbg(&s->udev->dev, "%s: submit urb=%d\n", __func__, i);
+		dev_dbg(s->dev, "submit urb=%d\n", i);
 		ret = usb_submit_urb(s->urb_list[i], GFP_ATOMIC);
 		if (ret) {
-			dev_err(&s->udev->dev,
-					"Could not submit URB no. %d - get them all back\n",
+			dev_err(s->dev, "Could not submit URB no. %d - get them all back\n",
 					i);
 			airspy_kill_urbs(s);
 			return ret;
@@ -362,8 +360,7 @@ static int airspy_free_stream_bufs(struct airspy *s)
 	if (s->flags & USB_STATE_URB_BUF) {
 		while (s->buf_num) {
 			s->buf_num--;
-			dev_dbg(&s->udev->dev, "%s: free buf=%d\n",
-					__func__, s->buf_num);
+			dev_dbg(s->dev, "free buf=%d\n", s->buf_num);
 			usb_free_coherent(s->udev, s->buf_size,
 					  s->buf_list[s->buf_num],
 					  s->dma_addr[s->buf_num]);
@@ -379,23 +376,20 @@ static int airspy_alloc_stream_bufs(struct airspy *s)
 	s->buf_num = 0;
 	s->buf_size = BULK_BUFFER_SIZE;
 
-	dev_dbg(&s->udev->dev,
-			"%s: all in all I will use %u bytes for streaming\n",
-			__func__,  MAX_BULK_BUFS * BULK_BUFFER_SIZE);
+	dev_dbg(s->dev, "all in all I will use %u bytes for streaming\n",
+			MAX_BULK_BUFS * BULK_BUFFER_SIZE);
 
 	for (s->buf_num = 0; s->buf_num < MAX_BULK_BUFS; s->buf_num++) {
 		s->buf_list[s->buf_num] = usb_alloc_coherent(s->udev,
 				BULK_BUFFER_SIZE, GFP_ATOMIC,
 				&s->dma_addr[s->buf_num]);
 		if (!s->buf_list[s->buf_num]) {
-			dev_dbg(&s->udev->dev, "%s: alloc buf=%d failed\n",
-					__func__, s->buf_num);
+			dev_dbg(s->dev, "alloc buf=%d failed\n", s->buf_num);
 			airspy_free_stream_bufs(s);
 			return -ENOMEM;
 		}
 
-		dev_dbg(&s->udev->dev, "%s: alloc buf=%d %p (dma %llu)\n",
-				__func__, s->buf_num,
+		dev_dbg(s->dev, "alloc buf=%d %p (dma %llu)\n", s->buf_num,
 				s->buf_list[s->buf_num],
 				(long long)s->dma_addr[s->buf_num]);
 		s->flags |= USB_STATE_URB_BUF;
@@ -412,8 +406,7 @@ static int airspy_free_urbs(struct airspy *s)
 
 	for (i = s->urbs_initialized - 1; i >= 0; i--) {
 		if (s->urb_list[i]) {
-			dev_dbg(&s->udev->dev, "%s: free urb=%d\n",
-					__func__, i);
+			dev_dbg(s->dev, "free urb=%d\n", i);
 			/* free the URBs */
 			usb_free_urb(s->urb_list[i]);
 		}
@@ -429,10 +422,10 @@ static int airspy_alloc_urbs(struct airspy *s)
 
 	/* allocate the URBs */
 	for (i = 0; i < MAX_BULK_BUFS; i++) {
-		dev_dbg(&s->udev->dev, "%s: alloc urb=%d\n", __func__, i);
+		dev_dbg(s->dev, "alloc urb=%d\n", i);
 		s->urb_list[i] = usb_alloc_urb(0, GFP_ATOMIC);
 		if (!s->urb_list[i]) {
-			dev_dbg(&s->udev->dev, "%s: failed\n", __func__);
+			dev_dbg(s->dev, "failed\n");
 			for (j = 0; j < i; j++)
 				usb_free_urb(s->urb_list[j]);
 			return -ENOMEM;
@@ -455,13 +448,14 @@ static int airspy_alloc_urbs(struct airspy *s)
 /* Must be called with vb_queue_lock hold */
 static void airspy_cleanup_queued_bufs(struct airspy *s)
 {
-	unsigned long flags = 0;
+	unsigned long flags;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	spin_lock_irqsave(&s->queued_bufs_lock, flags);
 	while (!list_empty(&s->queued_bufs)) {
 		struct airspy_frame_buf *buf;
+
 		buf = list_entry(s->queued_bufs.next,
 				struct airspy_frame_buf, list);
 		list_del(&buf->list);
@@ -476,7 +470,7 @@ static void airspy_disconnect(struct usb_interface *intf)
 	struct v4l2_device *v = usb_get_intfdata(intf);
 	struct airspy *s = container_of(v, struct airspy, v4l2_dev);
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	mutex_lock(&s->vb_queue_lock);
 	mutex_lock(&s->v4l2_lock);
@@ -497,7 +491,7 @@ static int airspy_queue_setup(struct vb2_queue *vq,
 {
 	struct airspy *s = vb2_get_drv_priv(vq);
 
-	dev_dbg(&s->udev->dev, "%s: *nbuffers=%d\n", __func__, *nbuffers);
+	dev_dbg(s->dev, "nbuffers=%d\n", *nbuffers);
 
 	/* Need at least 8 buffers */
 	if (vq->num_buffers + *nbuffers < 8)
@@ -505,8 +499,7 @@ static int airspy_queue_setup(struct vb2_queue *vq,
 	*nplanes = 1;
 	sizes[0] = PAGE_ALIGN(s->buffersize);
 
-	dev_dbg(&s->udev->dev, "%s: nbuffers=%d sizes[0]=%d\n",
-			__func__, *nbuffers, sizes[0]);
+	dev_dbg(s->dev, "nbuffers=%d sizes[0]=%d\n", *nbuffers, sizes[0]);
 	return 0;
 }
 
@@ -515,7 +508,7 @@ static void airspy_buf_queue(struct vb2_buffer *vb)
 	struct airspy *s = vb2_get_drv_priv(vb->vb2_queue);
 	struct airspy_frame_buf *buf =
 			container_of(vb, struct airspy_frame_buf, vb);
-	unsigned long flags = 0;
+	unsigned long flags;
 
 	/* Check the device has not disconnected between prep and queuing */
 	if (unlikely(!s->udev)) {
@@ -533,34 +526,56 @@ static int airspy_start_streaming(struct vb2_queue *vq, unsigned int count)
 	struct airspy *s = vb2_get_drv_priv(vq);
 	int ret;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	if (!s->udev)
 		return -ENODEV;
 
 	mutex_lock(&s->v4l2_lock);
 
-	set_bit(POWER_ON, &s->flags);
-
 	s->sequence = 0;
 
+	set_bit(POWER_ON, &s->flags);
+
 	ret = airspy_alloc_stream_bufs(s);
 	if (ret)
-		goto err;
+		goto err_clear_bit;
 
 	ret = airspy_alloc_urbs(s);
 	if (ret)
-		goto err;
+		goto err_free_stream_bufs;
 
 	ret = airspy_submit_urbs(s);
 	if (ret)
-		goto err;
+		goto err_free_urbs;
 
 	/* start hardware streaming */
 	ret = airspy_ctrl_msg(s, CMD_RECEIVER_MODE, 1, 0, NULL, 0);
 	if (ret)
-		goto err;
-err:
+		goto err_kill_urbs;
+
+	goto exit_mutex_unlock;
+
+err_kill_urbs:
+	airspy_kill_urbs(s);
+err_free_urbs:
+	airspy_free_urbs(s);
+err_free_stream_bufs:
+	airspy_free_stream_bufs(s);
+err_clear_bit:
+	clear_bit(POWER_ON, &s->flags);
+
+	/* return all queued buffers to vb2 */
+	{
+		struct airspy_frame_buf *buf, *tmp;
+
+		list_for_each_entry_safe(buf, tmp, &s->queued_bufs, list) {
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
+		}
+	}
+
+exit_mutex_unlock:
 	mutex_unlock(&s->v4l2_lock);
 
 	return ret;
@@ -570,7 +585,7 @@ static void airspy_stop_streaming(struct vb2_queue *vq)
 {
 	struct airspy *s = vb2_get_drv_priv(vq);
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	mutex_lock(&s->v4l2_lock);
 
@@ -602,8 +617,6 @@ static int airspy_querycap(struct file *file, void *fh,
 {
 	struct airspy *s = video_drvdata(file);
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
-
 	strlcpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver));
 	strlcpy(cap->card, s->vdev.name, sizeof(cap->card));
 	usb_make_path(s->udev, cap->bus_info, sizeof(cap->bus_info));
@@ -617,10 +630,6 @@ static int airspy_querycap(struct file *file, void *fh,
 static int airspy_enum_fmt_sdr_cap(struct file *file, void *priv,
 		struct v4l2_fmtdesc *f)
 {
-	struct airspy *s = video_drvdata(file);
-
-	dev_dbg(&s->udev->dev, "%s: index=%d\n", __func__, f->index);
-
 	if (f->index >= NUM_FORMATS)
 		return -EINVAL;
 
@@ -635,9 +644,6 @@ static int airspy_g_fmt_sdr_cap(struct file *file, void *priv,
 {
 	struct airspy *s = video_drvdata(file);
 
-	dev_dbg(&s->udev->dev, "%s: pixelformat fourcc %4.4s\n", __func__,
-			(char *)&s->pixelformat);
-
 	f->fmt.sdr.pixelformat = s->pixelformat;
 	f->fmt.sdr.buffersize = s->buffersize;
 	memset(f->fmt.sdr.reserved, 0, sizeof(f->fmt.sdr.reserved));
@@ -652,9 +658,6 @@ static int airspy_s_fmt_sdr_cap(struct file *file, void *priv,
 	struct vb2_queue *q = &s->vb_queue;
 	int i;
 
-	dev_dbg(&s->udev->dev, "%s: pixelformat fourcc %4.4s\n", __func__,
-			(char *)&f->fmt.sdr.pixelformat);
-
 	if (vb2_is_busy(q))
 		return -EBUSY;
 
@@ -679,12 +682,8 @@ static int airspy_s_fmt_sdr_cap(struct file *file, void *priv,
 static int airspy_try_fmt_sdr_cap(struct file *file, void *priv,
 		struct v4l2_format *f)
 {
-	struct airspy *s = video_drvdata(file);
 	int i;
 
-	dev_dbg(&s->udev->dev, "%s: pixelformat fourcc %4.4s\n", __func__,
-			(char *)&f->fmt.sdr.pixelformat);
-
 	memset(f->fmt.sdr.reserved, 0, sizeof(f->fmt.sdr.reserved));
 	for (i = 0; i < NUM_FORMATS; i++) {
 		if (formats[i].pixelformat == f->fmt.sdr.pixelformat) {
@@ -702,11 +701,8 @@ static int airspy_try_fmt_sdr_cap(struct file *file, void *priv,
 static int airspy_s_tuner(struct file *file, void *priv,
 		const struct v4l2_tuner *v)
 {
-	struct airspy *s = video_drvdata(file);
 	int ret;
 
-	dev_dbg(&s->udev->dev, "%s: index=%d\n", __func__, v->index);
-
 	if (v->index == 0)
 		ret = 0;
 	else if (v->index == 1)
@@ -719,11 +715,8 @@ static int airspy_s_tuner(struct file *file, void *priv,
 
 static int airspy_g_tuner(struct file *file, void *priv, struct v4l2_tuner *v)
 {
-	struct airspy *s = video_drvdata(file);
 	int ret;
 
-	dev_dbg(&s->udev->dev, "%s: index=%d\n", __func__, v->index);
-
 	if (v->index == 0) {
 		strlcpy(v->name, "AirSpy ADC", sizeof(v->name));
 		v->type = V4L2_TUNER_ADC;
@@ -749,17 +742,18 @@ static int airspy_g_frequency(struct file *file, void *priv,
 		struct v4l2_frequency *f)
 {
 	struct airspy *s = video_drvdata(file);
-	int ret  = 0;
-	dev_dbg(&s->udev->dev, "%s: tuner=%d type=%d\n",
-			__func__, f->tuner, f->type);
+	int ret;
 
 	if (f->tuner == 0) {
 		f->type = V4L2_TUNER_ADC;
 		f->frequency = s->f_adc;
+		dev_dbg(s->dev, "ADC frequency=%u Hz\n", s->f_adc);
 		ret = 0;
 	} else if (f->tuner == 1) {
 		f->type = V4L2_TUNER_RF;
 		f->frequency = s->f_rf;
+		dev_dbg(s->dev, "RF frequency=%u Hz\n", s->f_rf);
+		ret = 0;
 	} else {
 		ret = -EINVAL;
 	}
@@ -774,22 +768,17 @@ static int airspy_s_frequency(struct file *file, void *priv,
 	int ret;
 	u8 buf[4];
 
-	dev_dbg(&s->udev->dev, "%s: tuner=%d type=%d frequency=%u\n",
-			__func__, f->tuner, f->type, f->frequency);
-
 	if (f->tuner == 0) {
 		s->f_adc = clamp_t(unsigned int, f->frequency,
 				bands[0].rangelow,
 				bands[0].rangehigh);
-		dev_dbg(&s->udev->dev, "%s: ADC frequency=%u Hz\n",
-				__func__, s->f_adc);
+		dev_dbg(s->dev, "ADC frequency=%u Hz\n", s->f_adc);
 		ret = 0;
 	} else if (f->tuner == 1) {
 		s->f_rf = clamp_t(unsigned int, f->frequency,
 				bands_rf[0].rangelow,
 				bands_rf[0].rangehigh);
-		dev_dbg(&s->udev->dev, "%s: RF frequency=%u Hz\n",
-				__func__, s->f_rf);
+		dev_dbg(s->dev, "RF frequency=%u Hz\n", s->f_rf);
 		buf[0] = (s->f_rf >>  0) & 0xff;
 		buf[1] = (s->f_rf >>  8) & 0xff;
 		buf[2] = (s->f_rf >> 16) & 0xff;
@@ -805,10 +794,7 @@ static int airspy_s_frequency(struct file *file, void *priv,
 static int airspy_enum_freq_bands(struct file *file, void *priv,
 		struct v4l2_frequency_band *band)
 {
-	struct airspy *s = video_drvdata(file);
 	int ret;
-	dev_dbg(&s->udev->dev, "%s: tuner=%d type=%d index=%d\n",
-			__func__, band->tuner, band->type, band->index);
 
 	if (band->tuner == 0) {
 		if (band->index >= ARRAY_SIZE(bands)) {
@@ -892,10 +878,9 @@ static int airspy_set_lna_gain(struct airspy *s)
 	int ret;
 	u8 u8tmp;
 
-	dev_dbg(&s->udev->dev, "%s: lna auto=%d->%d val=%d->%d\n",
-			__func__, s->lna_gain_auto->cur.val,
-			s->lna_gain_auto->val, s->lna_gain->cur.val,
-			s->lna_gain->val);
+	dev_dbg(s->dev, "lna auto=%d->%d val=%d->%d\n",
+			s->lna_gain_auto->cur.val, s->lna_gain_auto->val,
+			s->lna_gain->cur.val, s->lna_gain->val);
 
 	ret = airspy_ctrl_msg(s, CMD_SET_LNA_AGC, 0, s->lna_gain_auto->val,
 			&u8tmp, 1);
@@ -910,7 +895,7 @@ static int airspy_set_lna_gain(struct airspy *s)
 	}
 err:
 	if (ret)
-		dev_dbg(&s->udev->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(s->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -920,10 +905,9 @@ static int airspy_set_mixer_gain(struct airspy *s)
 	int ret;
 	u8 u8tmp;
 
-	dev_dbg(&s->udev->dev, "%s: mixer auto=%d->%d val=%d->%d\n",
-			__func__, s->mixer_gain_auto->cur.val,
-			s->mixer_gain_auto->val, s->mixer_gain->cur.val,
-			s->mixer_gain->val);
+	dev_dbg(s->dev, "mixer auto=%d->%d val=%d->%d\n",
+			s->mixer_gain_auto->cur.val, s->mixer_gain_auto->val,
+			s->mixer_gain->cur.val, s->mixer_gain->val);
 
 	ret = airspy_ctrl_msg(s, CMD_SET_MIXER_AGC, 0, s->mixer_gain_auto->val,
 			&u8tmp, 1);
@@ -938,7 +922,7 @@ static int airspy_set_mixer_gain(struct airspy *s)
 	}
 err:
 	if (ret)
-		dev_dbg(&s->udev->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(s->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -948,8 +932,7 @@ static int airspy_set_if_gain(struct airspy *s)
 	int ret;
 	u8 u8tmp;
 
-	dev_dbg(&s->udev->dev, "%s: val=%d->%d\n",
-			__func__, s->if_gain->cur.val, s->if_gain->val);
+	dev_dbg(s->dev, "val=%d->%d\n", s->if_gain->cur.val, s->if_gain->val);
 
 	ret = airspy_ctrl_msg(s, CMD_SET_VGA_GAIN, 0, s->if_gain->val,
 			&u8tmp, 1);
@@ -957,7 +940,7 @@ static int airspy_set_if_gain(struct airspy *s)
 		goto err;
 err:
 	if (ret)
-		dev_dbg(&s->udev->dev, "%s: failed=%d\n", __func__, ret);
+		dev_dbg(s->dev, "failed=%d\n", ret);
 
 	return ret;
 }
@@ -980,8 +963,8 @@ static int airspy_s_ctrl(struct v4l2_ctrl *ctrl)
 		ret = airspy_set_if_gain(s);
 		break;
 	default:
-		dev_dbg(&s->udev->dev, "%s: unknown ctrl: id=%d name=%s\n",
-				__func__, ctrl->id, ctrl->name);
+		dev_dbg(s->dev, "unknown ctrl: id=%d name=%s\n",
+				ctrl->id, ctrl->name);
 		ret = -EINVAL;
 	}
 
@@ -995,15 +978,13 @@ static const struct v4l2_ctrl_ops airspy_ctrl_ops = {
 static int airspy_probe(struct usb_interface *intf,
 		const struct usb_device_id *id)
 {
-	struct usb_device *udev = interface_to_usbdev(intf);
-	struct airspy *s = NULL;
+	struct airspy *s;
 	int ret;
 	u8 u8tmp, buf[BUF_SIZE];
 
 	s = kzalloc(sizeof(struct airspy), GFP_KERNEL);
 	if (s == NULL) {
-		dev_err(&udev->dev,
-				"Could not allocate memory for airspy state\n");
+		dev_err(&intf->dev, "Could not allocate memory for state\n");
 		return -ENOMEM;
 	}
 
@@ -1011,7 +992,8 @@ static int airspy_probe(struct usb_interface *intf,
 	mutex_init(&s->vb_queue_lock);
 	spin_lock_init(&s->queued_bufs_lock);
 	INIT_LIST_HEAD(&s->queued_bufs);
-	s->udev = udev;
+	s->dev = &intf->dev;
+	s->udev = interface_to_usbdev(intf);
 	s->f_adc = bands[0].rangelow;
 	s->f_rf = bands_rf[0].rangelow;
 	s->pixelformat = formats[0].pixelformat;
@@ -1023,14 +1005,14 @@ static int airspy_probe(struct usb_interface *intf,
 		ret = airspy_ctrl_msg(s, CMD_VERSION_STRING_READ, 0, 0,
 				buf, BUF_SIZE);
 	if (ret) {
-		dev_err(&s->udev->dev, "Could not detect board\n");
+		dev_err(s->dev, "Could not detect board\n");
 		goto err_free_mem;
 	}
 
 	buf[BUF_SIZE - 1] = '\0';
 
-	dev_info(&s->udev->dev, "Board ID: %02x\n", u8tmp);
-	dev_info(&s->udev->dev, "Firmware version: %s\n", buf);
+	dev_info(s->dev, "Board ID: %02x\n", u8tmp);
+	dev_info(s->dev, "Firmware version: %s\n", buf);
 
 	/* Init videobuf2 queue structure */
 	s->vb_queue.type = V4L2_BUF_TYPE_SDR_CAPTURE;
@@ -1042,7 +1024,7 @@ static int airspy_probe(struct usb_interface *intf,
 	s->vb_queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	ret = vb2_queue_init(&s->vb_queue);
 	if (ret) {
-		dev_err(&s->udev->dev, "Could not initialize vb2 queue\n");
+		dev_err(s->dev, "Could not initialize vb2 queue\n");
 		goto err_free_mem;
 	}
 
@@ -1056,8 +1038,7 @@ static int airspy_probe(struct usb_interface *intf,
 	s->v4l2_dev.release = airspy_video_release;
 	ret = v4l2_device_register(&intf->dev, &s->v4l2_dev);
 	if (ret) {
-		dev_err(&s->udev->dev,
-				"Failed to register v4l2-device (%d)\n", ret);
+		dev_err(s->dev, "Failed to register v4l2-device (%d)\n", ret);
 		goto err_free_mem;
 	}
 
@@ -1077,7 +1058,7 @@ static int airspy_probe(struct usb_interface *intf,
 			V4L2_CID_RF_TUNER_IF_GAIN, 0, 15, 1, 0);
 	if (s->hdl.error) {
 		ret = s->hdl.error;
-		dev_err(&s->udev->dev, "Could not initialize controls\n");
+		dev_err(s->dev, "Could not initialize controls\n");
 		goto err_free_controls;
 	}
 
@@ -1089,16 +1070,13 @@ static int airspy_probe(struct usb_interface *intf,
 
 	ret = video_register_device(&s->vdev, VFL_TYPE_SDR, -1);
 	if (ret) {
-		dev_err(&s->udev->dev,
-				"Failed to register as video device (%d)\n",
+		dev_err(s->dev, "Failed to register as video device (%d)\n",
 				ret);
 		goto err_unregister_v4l2_dev;
 	}
-	dev_info(&s->udev->dev, "Registered as %s\n",
+	dev_info(s->dev, "Registered as %s\n",
 			video_device_node_name(&s->vdev));
-	dev_notice(&s->udev->dev,
-			"%s: SDR API is still slightly experimental and functionality changes may follow\n",
-			KBUILD_MODNAME);
+	dev_notice(s->dev, "SDR API is still slightly experimental and functionality changes may follow\n");
 	return 0;
 
 err_free_controls:
diff --git a/drivers/staging/media/as102/Kconfig b/drivers/media/usb/as102/Kconfig
index 28aba00dc629..28aba00dc629 100644
--- a/drivers/staging/media/as102/Kconfig
+++ b/drivers/media/usb/as102/Kconfig
diff --git a/drivers/staging/media/as102/Makefile b/drivers/media/usb/as102/Makefile
index 8916d8a909bc..22f43eee4a3b 100644
--- a/drivers/staging/media/as102/Makefile
+++ b/drivers/media/usb/as102/Makefile
@@ -1,6 +1,7 @@
 dvb-as102-objs := as102_drv.o as102_fw.o as10x_cmd.o as10x_cmd_stream.o \
-		as102_fe.o as102_usb_drv.o as10x_cmd_cfg.o
+		  as102_usb_drv.o as10x_cmd_cfg.o
 
 obj-$(CONFIG_DVB_AS102) += dvb-as102.o
 
 ccflags-y += -Idrivers/media/dvb-core
+ccflags-y += -Idrivers/media/dvb-frontends
diff --git a/drivers/staging/media/as102/as102_drv.c b/drivers/media/usb/as102/as102_drv.c
index 09d64cd67502..8be1474b2c36 100644
--- a/drivers/staging/media/as102/as102_drv.c
+++ b/drivers/media/usb/as102/as102_drv.c
@@ -12,10 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -28,13 +24,11 @@
 
 /* header file for usb device driver*/
 #include "as102_drv.h"
+#include "as10x_cmd.h"
+#include "as102_fe.h"
 #include "as102_fw.h"
 #include "dvbdev.h"
 
-int as102_debug;
-module_param_named(debug, as102_debug, int, 0644);
-MODULE_PARM_DESC(debug, "Turn on/off debugging (default: off)");
-
 int dual_tuner;
 module_param_named(dual_tuner, dual_tuner, int, 0644);
 MODULE_PARM_DESC(dual_tuner, "Activate Dual-Tuner config (default: off)");
@@ -74,7 +68,8 @@ static void as102_stop_stream(struct as102_dev_t *dev)
 			return;
 
 		if (as10x_cmd_stop_streaming(bus_adap) < 0)
-			dprintk(debug, "as10x_cmd_stop_streaming failed\n");
+			dev_dbg(&dev->bus_adap.usb_dev->dev,
+				"as10x_cmd_stop_streaming failed\n");
 
 		mutex_unlock(&dev->bus_adap.lock);
 	}
@@ -112,14 +107,16 @@ static int as10x_pid_filter(struct as102_dev_t *dev,
 	int ret = -EFAULT;
 
 	if (mutex_lock_interruptible(&dev->bus_adap.lock)) {
-		dprintk(debug, "mutex_lock_interruptible(lock) failed !\n");
+		dev_dbg(&dev->bus_adap.usb_dev->dev,
+			"amutex_lock_interruptible(lock) failed !\n");
 		return -EBUSY;
 	}
 
 	switch (onoff) {
 	case 0:
 		ret = as10x_cmd_del_PID_filter(bus_adap, (uint16_t) pid);
-		dprintk(debug, "DEL_PID_FILTER([%02d] 0x%04x) ret = %d\n",
+		dev_dbg(&dev->bus_adap.usb_dev->dev,
+			"DEL_PID_FILTER([%02d] 0x%04x) ret = %d\n",
 			index, pid, ret);
 		break;
 	case 1:
@@ -131,7 +128,7 @@ static int as10x_pid_filter(struct as102_dev_t *dev,
 		filter.pid = pid;
 
 		ret = as10x_cmd_add_PID_filter(bus_adap, &filter);
-		dprintk(debug,
+		dev_dbg(&dev->bus_adap.usb_dev->dev,
 			"ADD_PID_FILTER([%02d -> %02d], 0x%04x) ret = %d\n",
 			index, filter.idx, filter.pid, ret);
 		break;
@@ -181,6 +178,119 @@ static int as102_dvb_dmx_stop_feed(struct dvb_demux_feed *dvbdmxfeed)
 	return 0;
 }
 
+static int as102_set_tune(void *priv, struct as10x_tune_args *tune_args)
+{
+	struct as10x_bus_adapter_t *bus_adap = priv;
+	int ret;
+
+	/* Set frontend arguments */
+	if (mutex_lock_interruptible(&bus_adap->lock))
+		return -EBUSY;
+
+	ret =  as10x_cmd_set_tune(bus_adap, tune_args);
+	if (ret != 0)
+		dev_dbg(&bus_adap->usb_dev->dev,
+			"as10x_cmd_set_tune failed. (err = %d)\n", ret);
+
+	mutex_unlock(&bus_adap->lock);
+
+	return ret;
+}
+
+static int as102_get_tps(void *priv, struct as10x_tps *tps)
+{
+	struct as10x_bus_adapter_t *bus_adap = priv;
+	int ret;
+
+	if (mutex_lock_interruptible(&bus_adap->lock))
+		return -EBUSY;
+
+	/* send abilis command: GET_TPS */
+	ret = as10x_cmd_get_tps(bus_adap, tps);
+
+	mutex_unlock(&bus_adap->lock);
+
+	return ret;
+}
+
+static int as102_get_status(void *priv, struct as10x_tune_status *tstate)
+{
+	struct as10x_bus_adapter_t *bus_adap = priv;
+	int ret;
+
+	if (mutex_lock_interruptible(&bus_adap->lock))
+		return -EBUSY;
+
+	/* send abilis command: GET_TUNE_STATUS */
+	ret = as10x_cmd_get_tune_status(bus_adap, tstate);
+	if (ret < 0) {
+		dev_dbg(&bus_adap->usb_dev->dev,
+			"as10x_cmd_get_tune_status failed (err = %d)\n",
+			ret);
+	}
+
+	mutex_unlock(&bus_adap->lock);
+
+	return ret;
+}
+
+static int as102_get_stats(void *priv, struct as10x_demod_stats *demod_stats)
+{
+	struct as10x_bus_adapter_t *bus_adap = priv;
+	int ret;
+
+	if (mutex_lock_interruptible(&bus_adap->lock))
+		return -EBUSY;
+
+	/* send abilis command: GET_TUNE_STATUS */
+	ret = as10x_cmd_get_demod_stats(bus_adap, demod_stats);
+	if (ret < 0) {
+		dev_dbg(&bus_adap->usb_dev->dev,
+			"as10x_cmd_get_demod_stats failed (probably not tuned)\n");
+	} else {
+		dev_dbg(&bus_adap->usb_dev->dev,
+			"demod status: fc: 0x%08x, bad fc: 0x%08x, bytes corrected: 0x%08x , MER: 0x%04x\n",
+			demod_stats->frame_count,
+			demod_stats->bad_frame_count,
+			demod_stats->bytes_fixed_by_rs,
+			demod_stats->mer);
+	}
+	mutex_unlock(&bus_adap->lock);
+
+	return ret;
+}
+
+static int as102_stream_ctrl(void *priv, int acquire, uint32_t elna_cfg)
+{
+	struct as10x_bus_adapter_t *bus_adap = priv;
+	int ret;
+
+	if (mutex_lock_interruptible(&bus_adap->lock))
+		return -EBUSY;
+
+	if (acquire) {
+		if (elna_enable)
+			as10x_cmd_set_context(bus_adap,
+					      CONTEXT_LNA, elna_cfg);
+
+		ret = as10x_cmd_turn_on(bus_adap);
+	} else {
+		ret = as10x_cmd_turn_off(bus_adap);
+	}
+
+	mutex_unlock(&bus_adap->lock);
+
+	return ret;
+}
+
+static const struct as102_fe_ops as102_fe_ops = {
+	.set_tune = as102_set_tune,
+	.get_tps  = as102_get_tps,
+	.get_status = as102_get_status,
+	.get_stats = as102_get_stats,
+	.stream_ctrl = as102_stream_ctrl,
+};
+
 int as102_dvb_register(struct as102_dev_t *as102_dev)
 {
 	struct device *dev = &as102_dev->bus_adap.usb_dev->dev;
@@ -221,7 +331,18 @@ int as102_dvb_register(struct as102_dev_t *as102_dev)
 		goto edmxdinit;
 	}
 
-	ret = as102_dvb_register_fe(as102_dev, &as102_dev->dvb_fe);
+	/* Attach the frontend */
+	as102_dev->dvb_fe = dvb_attach(as102_attach, as102_dev->name,
+				       &as102_fe_ops,
+				       &as102_dev->bus_adap,
+				       as102_dev->elna_cfg);
+	if (!as102_dev->dvb_fe) {
+		dev_err(dev, "%s: as102_attach() failed: %d",
+		    __func__, ret);
+		goto efereg;
+	}
+
+	ret =  dvb_register_frontend(&as102_dev->dvb_adap, as102_dev->dvb_fe);
 	if (ret < 0) {
 		dev_err(dev, "%s: as102_dvb_register_frontend() failed: %d",
 		    __func__, ret);
@@ -257,7 +378,10 @@ edmxinit:
 void as102_dvb_unregister(struct as102_dev_t *as102_dev)
 {
 	/* unregister as102 frontend */
-	as102_dvb_unregister_fe(&as102_dev->dvb_fe);
+	dvb_unregister_frontend(as102_dev->dvb_fe);
+
+	/* detach frontend */
+	dvb_frontend_detach(as102_dev->dvb_fe);
 
 	/* unregister demux device */
 	dvb_dmxdev_release(&as102_dev->dvb_dmxdev);
diff --git a/drivers/staging/media/as102/as102_drv.h b/drivers/media/usb/as102/as102_drv.h
index a06837dcc05d..aee2d76e8dfc 100644
--- a/drivers/staging/media/as102/as102_drv.h
+++ b/drivers/media/usb/as102/as102_drv.h
@@ -11,33 +11,25 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#ifndef _AS102_DRV_H
+#define _AS102_DRV_H
 #include <linux/usb.h>
 #include <dvb_demux.h>
 #include <dvb_frontend.h>
 #include <dmxdev.h>
+#include "as10x_handle.h"
 #include "as10x_cmd.h"
 #include "as102_usb_drv.h"
 
 #define DRIVER_FULL_NAME "Abilis Systems as10x usb driver"
 #define DRIVER_NAME "as10x_usb"
 
-extern int as102_debug;
 #define debug	as102_debug
 extern struct usb_driver as102_usb_driver;
 extern int elna_enable;
 
-#define dprintk(debug, args...) \
-	do { if (debug) {	\
-		pr_debug("%s: ", __func__);	\
-		printk(args);	\
-	} } while (0)
-
 #define AS102_DEVICE_MAJOR	192
 
 #define AS102_USB_BUF_SIZE	512
@@ -71,17 +63,10 @@ struct as102_dev_t {
 	uint8_t elna_cfg;
 
 	struct dvb_adapter dvb_adap;
-	struct dvb_frontend dvb_fe;
+	struct dvb_frontend *dvb_fe;
 	struct dvb_demux dvb_dmx;
 	struct dmxdev dvb_dmxdev;
 
-	/* demodulator stats */
-	struct as10x_demod_stats demod_stats;
-	/* signal strength */
-	uint16_t signal_strength;
-	/* bit error rate */
-	uint32_t ber;
-
 	/* timer handle to trig ts stream download */
 	struct timer_list timer_handle;
 
@@ -95,5 +80,4 @@ struct as102_dev_t {
 int as102_dvb_register(struct as102_dev_t *dev);
 void as102_dvb_unregister(struct as102_dev_t *dev);
 
-int as102_dvb_register_fe(struct as102_dev_t *dev, struct dvb_frontend *fe);
-int as102_dvb_unregister_fe(struct dvb_frontend *dev);
+#endif
diff --git a/drivers/staging/media/as102/as102_fw.c b/drivers/media/usb/as102/as102_fw.c
index f33f752c0aad..07d08c49f4d4 100644
--- a/drivers/staging/media/as102/as102_fw.c
+++ b/drivers/media/usb/as102/as102_fw.c
@@ -12,10 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/kernel.h>
 #include <linux/errno.h>
diff --git a/drivers/staging/media/as102/as102_fw.h b/drivers/media/usb/as102/as102_fw.h
index 4bfc6849d95a..2732b784216d 100644
--- a/drivers/staging/media/as102/as102_fw.h
+++ b/drivers/media/usb/as102/as102_fw.h
@@ -11,10 +11,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #define MAX_FW_PKT_SIZE	64
 
diff --git a/drivers/staging/media/as102/as102_usb_drv.c b/drivers/media/usb/as102/as102_usb_drv.c
index e6f6278e97d6..3f669066ccf6 100644
--- a/drivers/staging/media/as102/as102_usb_drv.c
+++ b/drivers/media/usb/as102/as102_usb_drv.c
@@ -12,10 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -104,21 +100,22 @@ static int as102_usb_xfer_cmd(struct as10x_bus_adapter_t *bus_adap,
 				      send_buf, send_buf_len,
 				      USB_CTRL_SET_TIMEOUT /* 200 */);
 		if (ret < 0) {
-			dprintk(debug, "usb_control_msg(send) failed, err %i\n",
-					ret);
+			dev_dbg(&bus_adap->usb_dev->dev,
+				"usb_control_msg(send) failed, err %i\n", ret);
 			return ret;
 		}
 
 		if (ret != send_buf_len) {
-			dprintk(debug, "only wrote %d of %d bytes\n",
-					ret, send_buf_len);
+			dev_dbg(&bus_adap->usb_dev->dev,
+			"only wrote %d of %d bytes\n", ret, send_buf_len);
 			return -1;
 		}
 	}
 
 	if (recv_buf != NULL) {
 #ifdef TRACE
-		dprintk(debug, "want to read: %d bytes\n", recv_buf_len);
+		dev_dbg(bus_adap->usb_dev->dev,
+			"want to read: %d bytes\n", recv_buf_len);
 #endif
 		ret = usb_control_msg(bus_adap->usb_dev,
 				      usb_rcvctrlpipe(bus_adap->usb_dev, 0),
@@ -130,12 +127,13 @@ static int as102_usb_xfer_cmd(struct as10x_bus_adapter_t *bus_adap,
 				      recv_buf, recv_buf_len,
 				      USB_CTRL_GET_TIMEOUT /* 200 */);
 		if (ret < 0) {
-			dprintk(debug, "usb_control_msg(recv) failed, err %i\n",
-					ret);
+			dev_dbg(&bus_adap->usb_dev->dev,
+				"usb_control_msg(recv) failed, err %i\n", ret);
 			return ret;
 		}
 #ifdef TRACE
-		dprintk(debug, "read %d bytes\n", recv_buf_len);
+		dev_dbg(bus_adap->usb_dev->dev,
+			"read %d bytes\n", recv_buf_len);
 #endif
 	}
 
@@ -147,28 +145,29 @@ static int as102_send_ep1(struct as10x_bus_adapter_t *bus_adap,
 			  int send_buf_len,
 			  int swap32)
 {
-	int ret = 0, actual_len;
+	int ret, actual_len;
 
 	ret = usb_bulk_msg(bus_adap->usb_dev,
 			   usb_sndbulkpipe(bus_adap->usb_dev, 1),
 			   send_buf, send_buf_len, &actual_len, 200);
 	if (ret) {
-		dprintk(debug, "usb_bulk_msg(send) failed, err %i\n", ret);
+		dev_dbg(&bus_adap->usb_dev->dev,
+			"usb_bulk_msg(send) failed, err %i\n", ret);
 		return ret;
 	}
 
 	if (actual_len != send_buf_len) {
-		dprintk(debug, "only wrote %d of %d bytes\n",
-				actual_len, send_buf_len);
+		dev_dbg(&bus_adap->usb_dev->dev, "only wrote %d of %d bytes\n",
+			actual_len, send_buf_len);
 		return -1;
 	}
-	return ret ? ret : actual_len;
+	return actual_len;
 }
 
 static int as102_read_ep2(struct as10x_bus_adapter_t *bus_adap,
 		   unsigned char *recv_buf, int recv_buf_len)
 {
-	int ret = 0, actual_len;
+	int ret, actual_len;
 
 	if (recv_buf == NULL)
 		return -EINVAL;
@@ -177,16 +176,17 @@ static int as102_read_ep2(struct as10x_bus_adapter_t *bus_adap,
 			   usb_rcvbulkpipe(bus_adap->usb_dev, 2),
 			   recv_buf, recv_buf_len, &actual_len, 200);
 	if (ret) {
-		dprintk(debug, "usb_bulk_msg(recv) failed, err %i\n", ret);
+		dev_dbg(&bus_adap->usb_dev->dev,
+			"usb_bulk_msg(recv) failed, err %i\n", ret);
 		return ret;
 	}
 
 	if (actual_len != recv_buf_len) {
-		dprintk(debug, "only read %d of %d bytes\n",
-				actual_len, recv_buf_len);
+		dev_dbg(&bus_adap->usb_dev->dev, "only read %d of %d bytes\n",
+			actual_len, recv_buf_len);
 		return -1;
 	}
-	return ret ? ret : actual_len;
+	return actual_len;
 }
 
 static struct as102_priv_ops_t as102_priv_ops = {
@@ -211,7 +211,8 @@ static int as102_submit_urb_stream(struct as102_dev_t *dev, struct urb *urb)
 
 	err = usb_submit_urb(urb, GFP_ATOMIC);
 	if (err)
-		dprintk(debug, "%s: usb_submit_urb failed\n", __func__);
+		dev_dbg(&urb->dev->dev,
+			"%s: usb_submit_urb failed\n", __func__);
 
 	return err;
 }
@@ -256,7 +257,8 @@ static int as102_alloc_usb_stream_buffer(struct as102_dev_t *dev)
 				       GFP_KERNEL,
 				       &dev->dma_addr);
 	if (!dev->stream) {
-		dprintk(debug, "%s: usb_buffer_alloc failed\n", __func__);
+		dev_dbg(&dev->bus_adap.usb_dev->dev,
+			"%s: usb_buffer_alloc failed\n", __func__);
 		return -ENOMEM;
 	}
 
@@ -268,7 +270,8 @@ static int as102_alloc_usb_stream_buffer(struct as102_dev_t *dev)
 
 		urb = usb_alloc_urb(0, GFP_ATOMIC);
 		if (urb == NULL) {
-			dprintk(debug, "%s: usb_alloc_urb failed\n", __func__);
+			dev_dbg(&dev->bus_adap.usb_dev->dev,
+				"%s: usb_alloc_urb failed\n", __func__);
 			as102_free_usb_stream_buffer(dev);
 			return -ENOMEM;
 		}
diff --git a/drivers/staging/media/as102/as102_usb_drv.h b/drivers/media/usb/as102/as102_usb_drv.h
index 1ad1ec52b11e..4fb1baa8cac0 100644
--- a/drivers/staging/media/as102/as102_usb_drv.h
+++ b/drivers/media/usb/as102/as102_usb_drv.h
@@ -12,10 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #ifndef _AS102_USB_DRV_H_
 #define _AS102_USB_DRV_H_
diff --git a/drivers/staging/media/as102/as10x_cmd.c b/drivers/media/usb/as102/as10x_cmd.c
index 9e49f15a7c9f..870617994410 100644
--- a/drivers/staging/media/as102/as10x_cmd.c
+++ b/drivers/media/usb/as102/as10x_cmd.c
@@ -12,15 +12,10 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/kernel.h>
 #include "as102_drv.h"
-#include "as10x_types.h"
 #include "as10x_cmd.h"
 
 /**
@@ -126,7 +121,7 @@ int as10x_cmd_set_tune(struct as10x_bus_adapter_t *adap,
 
 	/* fill command */
 	preq->body.set_tune.req.proc_id = cpu_to_le16(CONTROL_PROC_SETTUNE);
-	preq->body.set_tune.req.args.freq = cpu_to_le32(ptune->freq);
+	preq->body.set_tune.req.args.freq = (__force __u32)cpu_to_le32(ptune->freq);
 	preq->body.set_tune.req.args.bandwidth = ptune->bandwidth;
 	preq->body.set_tune.req.args.hier_select = ptune->hier_select;
 	preq->body.set_tune.req.args.modulation = ptune->modulation;
@@ -204,9 +199,9 @@ int as10x_cmd_get_tune_status(struct as10x_bus_adapter_t *adap,
 	/* Response OK -> get response data */
 	pstatus->tune_state = prsp->body.get_tune_status.rsp.sts.tune_state;
 	pstatus->signal_strength  =
-		le16_to_cpu(prsp->body.get_tune_status.rsp.sts.signal_strength);
-	pstatus->PER = le16_to_cpu(prsp->body.get_tune_status.rsp.sts.PER);
-	pstatus->BER = le16_to_cpu(prsp->body.get_tune_status.rsp.sts.BER);
+		le16_to_cpu((__force __le16)prsp->body.get_tune_status.rsp.sts.signal_strength);
+	pstatus->PER = le16_to_cpu((__force __le16)prsp->body.get_tune_status.rsp.sts.PER);
+	pstatus->BER = le16_to_cpu((__force __le16)prsp->body.get_tune_status.rsp.sts.BER);
 
 out:
 	return error;
@@ -264,7 +259,7 @@ int as10x_cmd_get_tps(struct as10x_bus_adapter_t *adap, struct as10x_tps *ptps)
 	ptps->transmission_mode  = prsp->body.get_tps.rsp.tps.transmission_mode;
 	ptps->DVBH_mask_HP = prsp->body.get_tps.rsp.tps.DVBH_mask_HP;
 	ptps->DVBH_mask_LP = prsp->body.get_tps.rsp.tps.DVBH_mask_LP;
-	ptps->cell_ID = le16_to_cpu(prsp->body.get_tps.rsp.tps.cell_ID);
+	ptps->cell_ID = le16_to_cpu((__force __le16)prsp->body.get_tps.rsp.tps.cell_ID);
 
 out:
 	return error;
@@ -315,13 +310,13 @@ int as10x_cmd_get_demod_stats(struct as10x_bus_adapter_t *adap,
 
 	/* Response OK -> get response data */
 	pdemod_stats->frame_count =
-		le32_to_cpu(prsp->body.get_demod_stats.rsp.stats.frame_count);
+		le32_to_cpu((__force __le32)prsp->body.get_demod_stats.rsp.stats.frame_count);
 	pdemod_stats->bad_frame_count =
-		le32_to_cpu(prsp->body.get_demod_stats.rsp.stats.bad_frame_count);
+		le32_to_cpu((__force __le32)prsp->body.get_demod_stats.rsp.stats.bad_frame_count);
 	pdemod_stats->bytes_fixed_by_rs =
-		le32_to_cpu(prsp->body.get_demod_stats.rsp.stats.bytes_fixed_by_rs);
+		le32_to_cpu((__force __le32)prsp->body.get_demod_stats.rsp.stats.bytes_fixed_by_rs);
 	pdemod_stats->mer =
-		le16_to_cpu(prsp->body.get_demod_stats.rsp.stats.mer);
+		le16_to_cpu((__force __le16)prsp->body.get_demod_stats.rsp.stats.mer);
 	pdemod_stats->has_started =
 		prsp->body.get_demod_stats.rsp.stats.has_started;
 
diff --git a/drivers/staging/media/as102/as10x_cmd.h b/drivers/media/usb/as102/as10x_cmd.h
index e21ec6c702a9..e06b84e2ff79 100644
--- a/drivers/staging/media/as102/as10x_cmd.h
+++ b/drivers/media/usb/as102/as10x_cmd.h
@@ -11,19 +11,13 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #ifndef _AS10X_CMD_H_
 #define _AS10X_CMD_H_
 
-#ifdef __KERNEL__
 #include <linux/kernel.h>
-#endif
 
-#include "as10x_types.h"
+#include "as102_fe_types.h"
 
 /*********************************/
 /*       MACRO DEFINITIONS       */
@@ -98,12 +92,12 @@ union as10x_turn_on {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* error */
 		uint8_t error;
 	} __packed rsp;
@@ -113,12 +107,12 @@ union as10x_turn_off {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* error */
 		uint8_t err;
 	} __packed rsp;
@@ -128,14 +122,14 @@ union as10x_set_tune {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* tune params */
 		struct as10x_tune_args args;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* response error */
 		uint8_t error;
 	} __packed rsp;
@@ -145,12 +139,12 @@ union as10x_get_tune_status {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* response error */
 		uint8_t error;
 		/* tune status */
@@ -162,12 +156,12 @@ union as10x_get_tps {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* response error */
 		uint8_t error;
 		/* tps details */
@@ -179,12 +173,12 @@ union as10x_common {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t  proc_id;
+		__le16  proc_id;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* response error */
 		uint8_t error;
 	} __packed rsp;
@@ -194,9 +188,9 @@ union as10x_add_pid_filter {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t  proc_id;
+		__le16  proc_id;
 		/* PID to filter */
-		uint16_t  pid;
+		__le16  pid;
 		/* stream type (MPE, PSI/SI or PES )*/
 		uint8_t stream_type;
 		/* PID index in filter table */
@@ -205,7 +199,7 @@ union as10x_add_pid_filter {
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* response error */
 		uint8_t error;
 		/* Filter id */
@@ -217,14 +211,14 @@ union as10x_del_pid_filter {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t  proc_id;
+		__le16  proc_id;
 		/* PID to remove */
-		uint16_t  pid;
+		__le16  pid;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* response error */
 		uint8_t error;
 	} __packed rsp;
@@ -234,12 +228,12 @@ union as10x_start_streaming {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* error */
 		uint8_t error;
 	} __packed rsp;
@@ -249,12 +243,12 @@ union as10x_stop_streaming {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* error */
 		uint8_t error;
 	} __packed rsp;
@@ -264,12 +258,12 @@ union as10x_get_demod_stats {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* error */
 		uint8_t error;
 		/* demod stats */
@@ -281,12 +275,12 @@ union as10x_get_impulse_resp {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* error */
 		uint8_t error;
 		/* impulse response ready */
@@ -298,22 +292,22 @@ union as10x_fw_context {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* value to write (for set context)*/
 		struct as10x_register_value reg_val;
 		/* context tag */
-		uint16_t tag;
+		__le16 tag;
 		/* context request type */
-		uint16_t type;
+		__le16 type;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* value read (for get context) */
 		struct as10x_register_value reg_val;
 		/* context request type */
-		uint16_t type;
+		__le16 type;
 		/* error */
 		uint8_t error;
 	} __packed rsp;
@@ -323,7 +317,7 @@ union as10x_set_register {
 	/* request */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* register description */
 		struct as10x_register_addr reg_addr;
 		/* register content */
@@ -332,7 +326,7 @@ union as10x_set_register {
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* error */
 		uint8_t error;
 	} __packed rsp;
@@ -342,14 +336,14 @@ union as10x_get_register {
 	/* request */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* register description */
 		struct as10x_register_addr reg_addr;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* error */
 		uint8_t error;
 		/* register content */
@@ -361,24 +355,24 @@ union as10x_cfg_change_mode {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* mode */
 		uint8_t mode;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* error */
 		uint8_t error;
 	} __packed rsp;
 } __packed;
 
 struct as10x_cmd_header_t {
-	uint16_t req_id;
-	uint16_t prog;
-	uint16_t version;
-	uint16_t data_len;
+	__le16 req_id;
+	__le16 prog;
+	__le16 version;
+	__le16 data_len;
 } __packed;
 
 #define DUMP_BLOCK_SIZE 16
@@ -387,18 +381,18 @@ union as10x_dump_memory {
 	/* request */
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* dump memory type request */
 		uint8_t dump_req;
 		/* register description */
 		struct as10x_register_addr reg_addr;
 		/* nb blocks to read */
-		uint16_t num_blocks;
+		__le16 num_blocks;
 	} __packed req;
 	/* response */
 	struct {
 		/* response identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* error */
 		uint8_t error;
 		/* dump response */
@@ -406,8 +400,8 @@ union as10x_dump_memory {
 		/* data */
 		union {
 			uint8_t  data8[DUMP_BLOCK_SIZE];
-			uint16_t data16[DUMP_BLOCK_SIZE / sizeof(uint16_t)];
-			uint32_t data32[DUMP_BLOCK_SIZE / sizeof(uint32_t)];
+			__le16 data16[DUMP_BLOCK_SIZE / sizeof(__le16)];
+			__le32 data32[DUMP_BLOCK_SIZE / sizeof(__le32)];
 		} __packed u;
 	} __packed rsp;
 } __packed;
@@ -415,13 +409,13 @@ union as10x_dump_memory {
 union as10x_dumplog_memory {
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* dump memory type request */
 		uint8_t dump_req;
 	} __packed req;
 	struct {
 		/* request identifier */
-		uint16_t proc_id;
+		__le16 proc_id;
 		/* error */
 		uint8_t error;
 		/* dump response */
@@ -434,13 +428,13 @@ union as10x_dumplog_memory {
 union as10x_raw_data {
 	/* request */
 	struct {
-		uint16_t proc_id;
+		__le16 proc_id;
 		uint8_t data[64 - sizeof(struct as10x_cmd_header_t)
 			     - 2 /* proc_id */];
 	} __packed req;
 	/* response */
 	struct {
-		uint16_t proc_id;
+		__le16 proc_id;
 		uint8_t error;
 		uint8_t data[64 - sizeof(struct as10x_cmd_header_t)
 			     - 2 /* proc_id */ - 1 /* rc */];
diff --git a/drivers/staging/media/as102/as10x_cmd_cfg.c b/drivers/media/usb/as102/as10x_cmd_cfg.c
index b1e300d88753..c87f2ca223a2 100644
--- a/drivers/staging/media/as102/as10x_cmd_cfg.c
+++ b/drivers/media/usb/as102/as10x_cmd_cfg.c
@@ -11,15 +11,10 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/kernel.h>
 #include "as102_drv.h"
-#include "as10x_types.h"
 #include "as10x_cmd.h"
 
 /***************************/
@@ -74,7 +69,7 @@ int as10x_cmd_get_context(struct as10x_bus_adapter_t *adap, uint16_t tag,
 
 	if (error == 0) {
 		/* Response OK -> get response data */
-		*pvalue = le32_to_cpu(prsp->body.context.rsp.reg_val.u.value32);
+		*pvalue = le32_to_cpu((__force __le32)prsp->body.context.rsp.reg_val.u.value32);
 		/* value returned is always a 32-bit value */
 	}
 
@@ -106,7 +101,7 @@ int as10x_cmd_set_context(struct as10x_bus_adapter_t *adap, uint16_t tag,
 	/* fill command */
 	pcmd->body.context.req.proc_id = cpu_to_le16(CONTROL_PROC_CONTEXT);
 	/* pcmd->body.context.req.reg_val.mode initialization is not required */
-	pcmd->body.context.req.reg_val.u.value32 = cpu_to_le32(value);
+	pcmd->body.context.req.reg_val.u.value32 = (__force u32)cpu_to_le32(value);
 	pcmd->body.context.req.tag = cpu_to_le16(tag);
 	pcmd->body.context.req.type = cpu_to_le16(SET_CONTEXT_DATA);
 
diff --git a/drivers/staging/media/as102/as10x_cmd_stream.c b/drivers/media/usb/as102/as10x_cmd_stream.c
index 1088ca1fe92f..126aea976639 100644
--- a/drivers/staging/media/as102/as10x_cmd_stream.c
+++ b/drivers/media/usb/as102/as10x_cmd_stream.c
@@ -11,10 +11,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/staging/media/as102/as10x_handle.h b/drivers/media/usb/as102/as10x_handle.h
index 5638b191b780..d6b58c770500 100644
--- a/drivers/staging/media/as102/as10x_handle.h
+++ b/drivers/media/usb/as102/as10x_handle.h
@@ -11,12 +11,9 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#ifdef __KERNEL__
+#ifndef _AS10X_HANDLE_H
+#define _AS10X_HANDLE_H
 struct as10x_bus_adapter_t;
 struct as102_dev_t;
 
diff --git a/drivers/media/usb/au0828/au0828-cards.c b/drivers/media/usb/au0828/au0828-cards.c
index 2c6b7da137ed..9eb77ac2153b 100644
--- a/drivers/media/usb/au0828/au0828-cards.c
+++ b/drivers/media/usb/au0828/au0828-cards.c
@@ -46,6 +46,8 @@ struct au0828_board au0828_boards[] = {
 		.name	= "Hauppauge HVR850",
 		.tuner_type = TUNER_XC5000,
 		.tuner_addr = 0x61,
+		.has_ir_i2c = 1,
+		.has_analog = 1,
 		.i2c_clk_divider = AU0828_I2C_CLK_250KHZ,
 		.input = {
 			{
@@ -72,12 +74,7 @@ struct au0828_board au0828_boards[] = {
 		.tuner_type = TUNER_XC5000,
 		.tuner_addr = 0x61,
 		.has_ir_i2c = 1,
-		/* The au0828 hardware i2c implementation does not properly
-		   support the xc5000's i2c clock stretching.  So we need to
-		   lower the clock frequency enough where the 15us clock
-		   stretch fits inside of a normal clock cycle, or else the
-		   au0828 fails to set the STOP bit.  A 30 KHz clock puts the
-		   clock pulse width at 18us */
+		.has_analog = 1,
 		.i2c_clk_divider = AU0828_I2C_CLK_250KHZ,
 		.input = {
 			{
@@ -101,20 +98,20 @@ struct au0828_board au0828_boards[] = {
 	},
 	[AU0828_BOARD_HAUPPAUGE_HVR950Q_MXL] = {
 		.name	= "Hauppauge HVR950Q rev xxF8",
-		.tuner_type = UNSET,
-		.tuner_addr = ADDR_UNSET,
+		.tuner_type = TUNER_XC5000,
+		.tuner_addr = 0x61,
 		.i2c_clk_divider = AU0828_I2C_CLK_250KHZ,
 	},
 	[AU0828_BOARD_DVICO_FUSIONHDTV7] = {
 		.name	= "DViCO FusionHDTV USB",
-		.tuner_type = UNSET,
-		.tuner_addr = ADDR_UNSET,
+		.tuner_type = TUNER_XC5000,
+		.tuner_addr = 0x61,
 		.i2c_clk_divider = AU0828_I2C_CLK_250KHZ,
 	},
 	[AU0828_BOARD_HAUPPAUGE_WOODBURY] = {
 		.name = "Hauppauge Woodbury",
-		.tuner_type = UNSET,
-		.tuner_addr = ADDR_UNSET,
+		.tuner_type = TUNER_NXP_TDA18271,
+		.tuner_addr = 0x60,
 		.i2c_clk_divider = AU0828_I2C_CLK_250KHZ,
 	},
 };
@@ -142,8 +139,7 @@ int au0828_tuner_callback(void *priv, int component, int command, int arg)
 			mdelay(10);
 			return 0;
 		} else {
-			printk(KERN_ERR
-				"%s(): Unknown command.\n", __func__);
+			pr_err("%s(): Unknown command.\n", __func__);
 			return -EINVAL;
 		}
 		break;
@@ -177,12 +173,12 @@ static void hauppauge_eeprom(struct au0828_dev *dev, u8 *eeprom_data)
 	case 72500: /* WinTV-HVR950q (OEM, No IR, ATSC/QAM */
 		break;
 	default:
-		printk(KERN_WARNING "%s: warning: "
-		       "unknown hauppauge model #%d\n", __func__, tv.model);
+		pr_warn("%s: warning: unknown hauppauge model #%d\n",
+			__func__, tv.model);
 		break;
 	}
 
-	printk(KERN_INFO "%s: hauppauge eeprom: model=%d\n",
+	pr_info("%s: hauppauge eeprom: model=%d\n",
 	       __func__, tv.model);
 }
 
@@ -228,16 +224,16 @@ void au0828_card_analog_fe_setup(struct au0828_dev *dev)
 		sd = v4l2_i2c_new_subdev(&dev->v4l2_dev, &dev->i2c_adap,
 				"au8522", 0x8e >> 1, NULL);
 		if (sd == NULL)
-			printk(KERN_ERR "analog subdev registration failed\n");
+			pr_err("analog subdev registration failed\n");
 	}
 
 	/* Setup tuners */
-	if (dev->board.tuner_type != TUNER_ABSENT) {
+	if (dev->board.tuner_type != TUNER_ABSENT && dev->board.has_analog) {
 		/* Load the tuner module, which does the attach */
 		sd = v4l2_i2c_new_subdev(&dev->v4l2_dev, &dev->i2c_adap,
 				"tuner", dev->board.tuner_addr, NULL);
 		if (sd == NULL)
-			printk(KERN_ERR "tuner subdev registration fail\n");
+			pr_err("tuner subdev registration fail\n");
 
 		tun_setup.mode_mask      = mode_mask;
 		tun_setup.type           = dev->board.tuner_type;
diff --git a/drivers/media/usb/au0828/au0828-core.c b/drivers/media/usb/au0828/au0828-core.c
index 56025e689442..bc064803b6c7 100644
--- a/drivers/media/usb/au0828/au0828-core.c
+++ b/drivers/media/usb/au0828/au0828-core.c
@@ -19,14 +19,14 @@
  *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include "au0828.h"
+
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-common.h>
 #include <linux/mutex.h>
 
-#include "au0828.h"
-
 /*
  * 1 = General debug messages
  * 2 = USB handling
@@ -90,7 +90,7 @@ static int send_control_msg(struct au0828_dev *dev, u16 request, u32 value,
 		status = min(status, 0);
 
 		if (status < 0) {
-			printk(KERN_ERR "%s() Failed sending control message, error %d.\n",
+			pr_err("%s() Failed sending control message, error %d.\n",
 				__func__, status);
 		}
 
@@ -115,7 +115,7 @@ static int recv_control_msg(struct au0828_dev *dev, u16 request, u32 value,
 		status = min(status, 0);
 
 		if (status < 0) {
-			printk(KERN_ERR "%s() Failed receiving control message, error %d.\n",
+			pr_err("%s() Failed receiving control message, error %d.\n",
 				__func__, status);
 		}
 
@@ -153,9 +153,7 @@ static void au0828_usb_disconnect(struct usb_interface *interface)
 
 	dprintk(1, "%s()\n", __func__);
 
-#ifdef CONFIG_VIDEO_AU0828_RC
 	au0828_rc_unregister(dev);
-#endif
 	/* Digital TV */
 	au0828_dvb_unregister(dev);
 
@@ -199,15 +197,14 @@ static int au0828_usb_probe(struct usb_interface *interface,
 	 * not enough even for most Digital TV streams.
 	 */
 	if (usbdev->speed != USB_SPEED_HIGH && disable_usb_speed_check == 0) {
-		printk(KERN_ERR "au0828: Device initialization failed.\n");
-		printk(KERN_ERR "au0828: Device must be connected to a "
-		       "high-speed USB 2.0 port.\n");
+		pr_err("au0828: Device initialization failed.\n");
+		pr_err("au0828: Device must be connected to a high-speed USB 2.0 port.\n");
 		return -ENODEV;
 	}
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (dev == NULL) {
-		printk(KERN_ERR "%s() Unable to allocate memory\n", __func__);
+		pr_err("%s() Unable to allocate memory\n", __func__);
 		return -ENOMEM;
 	}
 
@@ -266,10 +263,8 @@ static int au0828_usb_probe(struct usb_interface *interface,
 		pr_err("%s() au0282_dev_register failed\n",
 		       __func__);
 
-#ifdef CONFIG_VIDEO_AU0828_RC
 	/* Remote controller */
 	au0828_rc_register(dev);
-#endif
 
 	/*
 	 * Store the pointer to the au0828_dev so it can be accessed in
@@ -277,7 +272,7 @@ static int au0828_usb_probe(struct usb_interface *interface,
 	 */
 	usb_set_intfdata(interface, dev);
 
-	printk(KERN_INFO "Registered device AU0828 [%s]\n",
+	pr_info("Registered device AU0828 [%s]\n",
 		dev->board.name == NULL ? "Unset" : dev->board.name);
 
 	mutex_unlock(&dev->lock);
@@ -285,13 +280,56 @@ static int au0828_usb_probe(struct usb_interface *interface,
 	return retval;
 }
 
+static int au0828_suspend(struct usb_interface *interface,
+				pm_message_t message)
+{
+	struct au0828_dev *dev = usb_get_intfdata(interface);
+
+	if (!dev)
+		return 0;
+
+	pr_info("Suspend\n");
+
+	au0828_rc_suspend(dev);
+	au0828_v4l2_suspend(dev);
+	au0828_dvb_suspend(dev);
+
+	/* FIXME: should suspend also ATV/DTV */
+
+	return 0;
+}
+
+static int au0828_resume(struct usb_interface *interface)
+{
+	struct au0828_dev *dev = usb_get_intfdata(interface);
+	if (!dev)
+		return 0;
+
+	pr_info("Resume\n");
+
+	/* Power Up the bridge */
+	au0828_write(dev, REG_600, 1 << 4);
+
+	/* Bring up the GPIO's and supporting devices */
+	au0828_gpio_setup(dev);
+
+	au0828_rc_resume(dev);
+	au0828_v4l2_resume(dev);
+	au0828_dvb_resume(dev);
+
+	/* FIXME: should resume also ATV/DTV */
+
+	return 0;
+}
+
 static struct usb_driver au0828_usb_driver = {
-	.name		= DRIVER_NAME,
+	.name		= KBUILD_MODNAME,
 	.probe		= au0828_usb_probe,
 	.disconnect	= au0828_usb_disconnect,
 	.id_table	= au0828_usb_id_table,
-
-	/* FIXME: Add suspend and resume functions */
+	.suspend	= au0828_suspend,
+	.resume		= au0828_resume,
+	.reset_resume	= au0828_resume,
 };
 
 static int __init au0828_init(void)
@@ -299,27 +337,27 @@ static int __init au0828_init(void)
 	int ret;
 
 	if (au0828_debug & 1)
-		printk(KERN_INFO "%s() Debugging is enabled\n", __func__);
+		pr_info("%s() Debugging is enabled\n", __func__);
 
 	if (au0828_debug & 2)
-		printk(KERN_INFO "%s() USB Debugging is enabled\n", __func__);
+		pr_info("%s() USB Debugging is enabled\n", __func__);
 
 	if (au0828_debug & 4)
-		printk(KERN_INFO "%s() I2C Debugging is enabled\n", __func__);
+		pr_info("%s() I2C Debugging is enabled\n", __func__);
 
 	if (au0828_debug & 8)
-		printk(KERN_INFO "%s() Bridge Debugging is enabled\n",
+		pr_info("%s() Bridge Debugging is enabled\n",
 		       __func__);
 
 	if (au0828_debug & 16)
-		printk(KERN_INFO "%s() IR Debugging is enabled\n",
+		pr_info("%s() IR Debugging is enabled\n",
 		       __func__);
 
-	printk(KERN_INFO "au0828 driver loaded\n");
+	pr_info("au0828 driver loaded\n");
 
 	ret = usb_register(&au0828_usb_driver);
 	if (ret)
-		printk(KERN_ERR "usb_register failed, error = %d\n", ret);
+		pr_err("usb_register failed, error = %d\n", ret);
 
 	return ret;
 }
diff --git a/drivers/media/usb/au0828/au0828-dvb.c b/drivers/media/usb/au0828/au0828-dvb.c
index d8b5d9480279..00ab1563d142 100644
--- a/drivers/media/usb/au0828/au0828-dvb.c
+++ b/drivers/media/usb/au0828/au0828-dvb.c
@@ -19,15 +19,15 @@
  *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include "au0828.h"
+
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/device.h>
-#include <linux/suspend.h>
 #include <media/v4l2-common.h>
 #include <media/tuner.h>
 
-#include "au0828.h"
 #include "au8522.h"
 #include "xc5000.h"
 #include "mxl5007t.h"
@@ -121,13 +121,13 @@ static void urb_completion(struct urb *purb)
 		return;
 	}
 
-	if (dev->urb_streaming == 0) {
+	if (!dev->urb_streaming) {
 		dprintk(2, "%s: not streaming!\n", __func__);
 		return;
 	}
 
 	if (ptype != PIPE_BULK) {
-		printk(KERN_ERR "%s: Unsupported URB type %d\n",
+		pr_err("%s: Unsupported URB type %d\n",
 		       __func__, ptype);
 		return;
 	}
@@ -159,7 +159,10 @@ static int stop_urb_transfer(struct au0828_dev *dev)
 
 	dprintk(2, "%s()\n", __func__);
 
-	dev->urb_streaming = 0;
+	if (!dev->urb_streaming)
+		return 0;
+
+	dev->urb_streaming = false;
 	for (i = 0; i < URB_COUNT; i++) {
 		if (dev->urbs[i]) {
 			usb_kill_urb(dev->urbs[i]);
@@ -202,8 +205,7 @@ static int start_urb_transfer(struct au0828_dev *dev)
 		if (!purb->transfer_buffer) {
 			usb_free_urb(purb);
 			dev->urbs[i] = NULL;
-			printk(KERN_ERR
-			       "%s: failed big buffer allocation, err = %d\n",
+			pr_err("%s: failed big buffer allocation, err = %d\n",
 			       __func__, ret);
 			goto err;
 		}
@@ -224,13 +226,13 @@ static int start_urb_transfer(struct au0828_dev *dev)
 		ret = usb_submit_urb(dev->urbs[i], GFP_ATOMIC);
 		if (ret != 0) {
 			stop_urb_transfer(dev);
-			printk(KERN_ERR "%s: failed urb submission, "
-			       "err = %d\n", __func__, ret);
+			pr_err("%s: failed urb submission, err = %d\n",
+			       __func__, ret);
 			return ret;
 		}
 	}
 
-	dev->urb_streaming = 1;
+	dev->urb_streaming = true;
 	ret = 0;
 
 err:
@@ -268,7 +270,7 @@ static int au0828_dvb_start_feed(struct dvb_demux_feed *feed)
 	if (!demux->dmx.frontend)
 		return -EINVAL;
 
-	if (dvb) {
+	if (dvb->frontend) {
 		mutex_lock(&dvb->lock);
 		dvb->start_count++;
 		dprintk(1, "%s(), start_count: %d, stop_count: %d\n", __func__,
@@ -297,7 +299,7 @@ static int au0828_dvb_stop_feed(struct dvb_demux_feed *feed)
 
 	dprintk(1, "%s()\n", __func__);
 
-	if (dvb) {
+	if (dvb->frontend) {
 		cancel_work_sync(&dev->restart_streaming);
 
 		mutex_lock(&dvb->lock);
@@ -324,7 +326,7 @@ static void au0828_restart_dvb_streaming(struct work_struct *work)
 					      restart_streaming);
 	struct au0828_dvb *dvb = &dev->dvb;
 
-	if (dev->urb_streaming == 0)
+	if (!dev->urb_streaming)
 		return;
 
 	dprintk(1, "Restarting streaming...!\n");
@@ -393,9 +395,8 @@ static int dvb_register(struct au0828_dev *dev)
 			if (!dev->dig_transfer_buffer[i]) {
 				result = -ENOMEM;
 
-				printk(KERN_ERR
-				       "%s: failed buffer allocation (errno = %d)\n",
-				       DRIVER_NAME, result);
+				pr_err("failed buffer allocation (errno = %d)\n",
+				       result);
 				goto fail_adapter;
 			}
 		}
@@ -404,11 +405,12 @@ static int dvb_register(struct au0828_dev *dev)
 	INIT_WORK(&dev->restart_streaming, au0828_restart_dvb_streaming);
 
 	/* register adapter */
-	result = dvb_register_adapter(&dvb->adapter, DRIVER_NAME, THIS_MODULE,
+	result = dvb_register_adapter(&dvb->adapter,
+				      KBUILD_MODNAME, THIS_MODULE,
 				      &dev->usbdev->dev, adapter_nr);
 	if (result < 0) {
-		printk(KERN_ERR "%s: dvb_register_adapter failed "
-		       "(errno = %d)\n", DRIVER_NAME, result);
+		pr_err("dvb_register_adapter failed (errno = %d)\n",
+		       result);
 		goto fail_adapter;
 	}
 	dvb->adapter.priv = dev;
@@ -416,8 +418,8 @@ static int dvb_register(struct au0828_dev *dev)
 	/* register frontend */
 	result = dvb_register_frontend(&dvb->adapter, dvb->frontend);
 	if (result < 0) {
-		printk(KERN_ERR "%s: dvb_register_frontend failed "
-		       "(errno = %d)\n", DRIVER_NAME, result);
+		pr_err("dvb_register_frontend failed (errno = %d)\n",
+		       result);
 		goto fail_frontend;
 	}
 
@@ -436,8 +438,7 @@ static int dvb_register(struct au0828_dev *dev)
 	dvb->demux.stop_feed  = au0828_dvb_stop_feed;
 	result = dvb_dmx_init(&dvb->demux);
 	if (result < 0) {
-		printk(KERN_ERR "%s: dvb_dmx_init failed (errno = %d)\n",
-		       DRIVER_NAME, result);
+		pr_err("dvb_dmx_init failed (errno = %d)\n", result);
 		goto fail_dmx;
 	}
 
@@ -446,31 +447,29 @@ static int dvb_register(struct au0828_dev *dev)
 	dvb->dmxdev.capabilities = 0;
 	result = dvb_dmxdev_init(&dvb->dmxdev, &dvb->adapter);
 	if (result < 0) {
-		printk(KERN_ERR "%s: dvb_dmxdev_init failed (errno = %d)\n",
-		       DRIVER_NAME, result);
+		pr_err("dvb_dmxdev_init failed (errno = %d)\n", result);
 		goto fail_dmxdev;
 	}
 
 	dvb->fe_hw.source = DMX_FRONTEND_0;
 	result = dvb->demux.dmx.add_frontend(&dvb->demux.dmx, &dvb->fe_hw);
 	if (result < 0) {
-		printk(KERN_ERR "%s: add_frontend failed "
-		       "(DMX_FRONTEND_0, errno = %d)\n", DRIVER_NAME, result);
+		pr_err("add_frontend failed (DMX_FRONTEND_0, errno = %d)\n",
+		       result);
 		goto fail_fe_hw;
 	}
 
 	dvb->fe_mem.source = DMX_MEMORY_FE;
 	result = dvb->demux.dmx.add_frontend(&dvb->demux.dmx, &dvb->fe_mem);
 	if (result < 0) {
-		printk(KERN_ERR "%s: add_frontend failed "
-		       "(DMX_MEMORY_FE, errno = %d)\n", DRIVER_NAME, result);
+		pr_err("add_frontend failed (DMX_MEMORY_FE, errno = %d)\n",
+		       result);
 		goto fail_fe_mem;
 	}
 
 	result = dvb->demux.dmx.connect_frontend(&dvb->demux.dmx, &dvb->fe_hw);
 	if (result < 0) {
-		printk(KERN_ERR "%s: connect_frontend failed (errno = %d)\n",
-		       DRIVER_NAME, result);
+		pr_err("connect_frontend failed (errno = %d)\n", result);
 		goto fail_fe_conn;
 	}
 
@@ -530,8 +529,7 @@ void au0828_dvb_unregister(struct au0828_dev *dev)
 		for (i = 0; i < URB_COUNT; i++)
 			kfree(dev->dig_transfer_buffer[i]);
 	}
-
-
+	dvb->frontend = NULL;
 }
 
 /* All the DVB attach calls go here, this function get's modified
@@ -596,12 +594,11 @@ int au0828_dvb_register(struct au0828_dev *dev)
 		}
 		break;
 	default:
-		printk(KERN_WARNING "The frontend of your DVB/ATSC card "
-		       "isn't supported yet\n");
+		pr_warn("The frontend of your DVB/ATSC card isn't supported yet\n");
 		break;
 	}
 	if (NULL == dvb->frontend) {
-		printk(KERN_ERR "%s() Frontend initialization failed\n",
+		pr_err("%s() Frontend initialization failed\n",
 		       __func__);
 		return -1;
 	}
@@ -613,8 +610,49 @@ int au0828_dvb_register(struct au0828_dev *dev)
 	if (ret < 0) {
 		if (dvb->frontend->ops.release)
 			dvb->frontend->ops.release(dvb->frontend);
+		dvb->frontend = NULL;
 		return ret;
 	}
 
 	return 0;
 }
+
+void au0828_dvb_suspend(struct au0828_dev *dev)
+{
+	struct au0828_dvb *dvb = &dev->dvb;
+	int rc;
+
+	if (dvb->frontend) {
+		if (dev->urb_streaming) {
+			cancel_work_sync(&dev->restart_streaming);
+			/* Stop transport */
+			mutex_lock(&dvb->lock);
+			stop_urb_transfer(dev);
+			au0828_stop_transport(dev, 1);
+			mutex_unlock(&dvb->lock);
+			dev->need_urb_start = true;
+		}
+		/* suspend frontend - does tuner and fe to sleep */
+		rc = dvb_frontend_suspend(dvb->frontend);
+		pr_info("au0828_dvb_suspend(): Suspending DVB fe %d\n", rc);
+	}
+}
+
+void au0828_dvb_resume(struct au0828_dev *dev)
+{
+	struct au0828_dvb *dvb = &dev->dvb;
+	int rc;
+
+	if (dvb->frontend) {
+		/* resume frontend - does fe and tuner init */
+		rc = dvb_frontend_resume(dvb->frontend);
+		pr_info("au0828_dvb_resume(): Resuming DVB fe %d\n", rc);
+		if (dev->need_urb_start) {
+			/* Start transport */
+			mutex_lock(&dvb->lock);
+			au0828_start_transport(dev);
+			start_urb_transfer(dev);
+			mutex_unlock(&dvb->lock);
+		}
+	}
+}
diff --git a/drivers/media/usb/au0828/au0828-i2c.c b/drivers/media/usb/au0828/au0828-i2c.c
index daaeaf1b089c..ae7ac6669769 100644
--- a/drivers/media/usb/au0828/au0828-i2c.c
+++ b/drivers/media/usb/au0828/au0828-i2c.c
@@ -19,13 +19,14 @@
  *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include "au0828.h"
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 
-#include "au0828.h"
 #include "media/tuner.h"
 #include <media/v4l2-common.h>
 
@@ -340,7 +341,7 @@ static struct i2c_algorithm au0828_i2c_algo_template = {
 /* ----------------------------------------------------------------------- */
 
 static struct i2c_adapter au0828_i2c_adap_template = {
-	.name              = DRIVER_NAME,
+	.name              = KBUILD_MODNAME,
 	.owner             = THIS_MODULE,
 	.algo              = &au0828_i2c_algo_template,
 };
@@ -365,7 +366,7 @@ static void do_i2c_scan(char *name, struct i2c_client *c)
 		rc = i2c_master_recv(c, &buf, 0);
 		if (rc < 0)
 			continue;
-		printk(KERN_INFO "%s: i2c scan: found device @ 0x%x  [%s]\n",
+		pr_info("%s: i2c scan: found device @ 0x%x  [%s]\n",
 		       name, i << 1, i2c_devs[i] ? i2c_devs[i] : "???");
 	}
 }
@@ -381,7 +382,7 @@ int au0828_i2c_register(struct au0828_dev *dev)
 
 	dev->i2c_adap.dev.parent = &dev->usbdev->dev;
 
-	strlcpy(dev->i2c_adap.name, DRIVER_NAME,
+	strlcpy(dev->i2c_adap.name, KBUILD_MODNAME,
 		sizeof(dev->i2c_adap.name));
 
 	dev->i2c_adap.algo = &dev->i2c_algo;
@@ -396,11 +397,11 @@ int au0828_i2c_register(struct au0828_dev *dev)
 	dev->i2c_client.adapter = &dev->i2c_adap;
 
 	if (0 == dev->i2c_rc) {
-		printk(KERN_INFO "%s: i2c bus registered\n", DRIVER_NAME);
+		pr_info("i2c bus registered\n");
 		if (i2c_scan)
-			do_i2c_scan(DRIVER_NAME, &dev->i2c_client);
+			do_i2c_scan(KBUILD_MODNAME, &dev->i2c_client);
 	} else
-		printk(KERN_INFO "%s: i2c bus register FAILED\n", DRIVER_NAME);
+		pr_info("i2c bus register FAILED\n");
 
 	return dev->i2c_rc;
 }
diff --git a/drivers/media/usb/au0828/au0828-input.c b/drivers/media/usb/au0828/au0828-input.c
index fd0d3a90ce7d..63995f97dc65 100644
--- a/drivers/media/usb/au0828/au0828-input.c
+++ b/drivers/media/usb/au0828/au0828-input.c
@@ -17,6 +17,8 @@
   GNU General Public License for more details.
  */
 
+#include "au0828.h"
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/delay.h>
@@ -25,7 +27,9 @@
 #include <linux/slab.h>
 #include <media/rc-core.h>
 
-#include "au0828.h"
+static int disable_ir;
+module_param(disable_ir,        int, 0444);
+MODULE_PARM_DESC(disable_ir, "disable infrared remote support");
 
 struct au0828_rc {
 	struct au0828_dev *dev;
@@ -90,14 +94,19 @@ static int au8522_rc_read(struct au0828_rc *ir, u16 reg, int val,
 static int au8522_rc_andor(struct au0828_rc *ir, u16 reg, u8 mask, u8 value)
 {
 	int rc;
-	char buf;
+	char buf, oldbuf;
 
 	rc = au8522_rc_read(ir, reg, -1, &buf, 1);
 	if (rc < 0)
 		return rc;
 
+	oldbuf = buf;
 	buf = (buf & ~mask) | (value & mask);
 
+	/* Nothing to do, just return */
+	if (buf == oldbuf)
+		return 0;
+
 	return au8522_rc_write(ir, reg, buf);
 }
 
@@ -122,8 +131,11 @@ static int au0828_get_key_au8522(struct au0828_rc *ir)
 
 	/* Check IR int */
 	rc = au8522_rc_read(ir, 0xe1, -1, buf, 1);
-	if (rc < 0 || !(buf[0] & (1 << 4)))
+	if (rc < 0 || !(buf[0] & (1 << 4))) {
+		/* Be sure that IR is enabled */
+		au8522_rc_set(ir, 0xe0, 1 << 4);
 		return 0;
+	}
 
 	/* Something arrived. Get the data */
 	rc = au8522_rc_read(ir, 0xe3, 0x11, buf, sizeof(buf));
@@ -135,8 +147,6 @@ static int au0828_get_key_au8522(struct au0828_rc *ir)
 	/* Disable IR */
 	au8522_rc_clear(ir, 0xe0, 1 << 4);
 
-	usleep_range(45000, 46000);
-
 	/* Enable IR */
 	au8522_rc_set(ir, 0xe0, 1 << 4);
 
@@ -243,10 +253,10 @@ static void au0828_rc_stop(struct rc_dev *rc)
 {
 	struct au0828_rc *ir = rc->priv;
 
+	cancel_delayed_work_sync(&ir->work);
+
 	/* Disable IR */
 	au8522_rc_clear(ir, 0xe0, 1 << 4);
-
-	cancel_delayed_work_sync(&ir->work);
 }
 
 static int au0828_probe_i2c_ir(struct au0828_dev *dev)
@@ -273,7 +283,7 @@ int au0828_rc_register(struct au0828_dev *dev)
 	int err = -ENOMEM;
 	u16 i2c_rc_dev_addr = 0;
 
-	if (!dev->board.has_ir_i2c)
+	if (!dev->board.has_ir_i2c || disable_ir)
 		return 0;
 
 	i2c_rc_dev_addr = au0828_probe_i2c_ir(dev);
@@ -368,8 +378,13 @@ int au0828_rc_suspend(struct au0828_dev *dev)
 	if (!ir)
 		return 0;
 
+	pr_info("Stopping RC\n");
+
 	cancel_delayed_work_sync(&ir->work);
 
+	/* Disable IR */
+	au8522_rc_clear(ir, 0xe0, 1 << 4);
+
 	return 0;
 }
 
@@ -380,6 +395,11 @@ int au0828_rc_resume(struct au0828_dev *dev)
 	if (!ir)
 		return 0;
 
+	pr_info("Restarting RC\n");
+
+	/* Enable IR */
+	au8522_rc_set(ir, 0xe0, 1 << 4);
+
 	schedule_delayed_work(&ir->work, msecs_to_jiffies(ir->polling));
 
 	return 0;
diff --git a/drivers/media/usb/au0828/au0828-vbi.c b/drivers/media/usb/au0828/au0828-vbi.c
index 63f593070ee8..932d24f42b24 100644
--- a/drivers/media/usb/au0828/au0828-vbi.c
+++ b/drivers/media/usb/au0828/au0828-vbi.c
@@ -21,13 +21,13 @@
    02110-1301, USA.
  */
 
+#include "au0828.h"
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 
-#include "au0828.h"
-
 static unsigned int vbibufs = 5;
 module_param(vbibufs, int, 0644);
 MODULE_PARM_DESC(vbibufs, "number of vbi buffers, range 2-32");
diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c
index 98f7ea1d6d63..5f337b118bff 100644
--- a/drivers/media/usb/au0828/au0828-video.c
+++ b/drivers/media/usb/au0828/au0828-video.c
@@ -28,16 +28,16 @@
  *
  */
 
+#include "au0828.h"
+
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/device.h>
-#include <linux/suspend.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-event.h>
 #include <media/tuner.h>
-#include "au0828.h"
 #include "au0828-reg.h"
 
 static DEFINE_MUTEX(au0828_sysfs_lock);
@@ -53,7 +53,7 @@ MODULE_PARM_DESC(isoc_debug, "enable debug messages [isoc transfers]");
 #define au0828_isocdbg(fmt, arg...) \
 do {\
 	if (isoc_debug) { \
-		printk(KERN_INFO "au0828 %s :"fmt, \
+		pr_info("au0828 %s :"fmt, \
 		       __func__ , ##arg);	   \
 	} \
   } while (0)
@@ -106,12 +106,12 @@ static inline void print_err_status(struct au0828_dev *dev,
 static int check_dev(struct au0828_dev *dev)
 {
 	if (dev->dev_state & DEV_DISCONNECTED) {
-		printk(KERN_INFO "v4l2 ioctl: device not present\n");
+		pr_info("v4l2 ioctl: device not present\n");
 		return -ENODEV;
 	}
 
 	if (dev->dev_state & DEV_MISCONFIGURED) {
-		printk(KERN_INFO "v4l2 ioctl: device is misconfigured; "
+		pr_info("v4l2 ioctl: device is misconfigured; "
 		       "close and open it again\n");
 		return -EIO;
 	}
@@ -159,6 +159,7 @@ static void au0828_irq_callback(struct urb *urb)
 		au0828_isocdbg("urb resubmit failed (error=%i)\n",
 			       urb->status);
 	}
+	dev->stream_state = STREAM_ON;
 }
 
 /*
@@ -198,6 +199,8 @@ static void au0828_uninit_isoc(struct au0828_dev *dev)
 	dev->isoc_ctl.urb = NULL;
 	dev->isoc_ctl.transfer_buffer = NULL;
 	dev->isoc_ctl.num_bufs = 0;
+
+	dev->stream_state = STREAM_OFF;
 }
 
 /*
@@ -717,7 +720,7 @@ buffer_prepare(struct videobuf_queue *vq, struct videobuf_buffer *vb,
 	if (VIDEOBUF_NEEDS_INIT == buf->vb.state) {
 		rc = videobuf_iolock(vq, &buf->vb, NULL);
 		if (rc < 0) {
-			printk(KERN_INFO "videobuf_iolock failed\n");
+			pr_info("videobuf_iolock failed\n");
 			goto fail;
 		}
 	}
@@ -730,7 +733,7 @@ buffer_prepare(struct videobuf_queue *vq, struct videobuf_buffer *vb,
 				      AU0828_MAX_ISO_BUFS, dev->max_pkt_size,
 				      au0828_isoc_copy);
 		if (rc < 0) {
-			printk(KERN_INFO "au0828_init_isoc failed\n");
+			pr_info("au0828_init_isoc failed\n");
 			goto fail;
 		}
 	}
@@ -801,7 +804,7 @@ static int au0828_analog_stream_enable(struct au0828_dev *d)
 		/* set au0828 interface0 to AS5 here again */
 		ret = usb_set_interface(d->usbdev, 0, 5);
 		if (ret < 0) {
-			printk(KERN_INFO "Au0828 can't set alt setting to 5!\n");
+			pr_info("Au0828 can't set alt setting to 5!\n");
 			return -EBUSY;
 		}
 	}
@@ -1090,7 +1093,7 @@ static int au0828_v4l2_close(struct file *filp)
 		   USB bandwidth */
 		ret = usb_set_interface(dev->usbdev, 0, 0);
 		if (ret < 0)
-			printk(KERN_INFO "Au0828 can't set alternate to 0!\n");
+			pr_info("Au0828 can't set alternate to 0!\n");
 	}
 	mutex_unlock(&dev->lock);
 
@@ -1344,7 +1347,7 @@ static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
 		return rc;
 
 	if (videobuf_queue_is_busy(&fh->vb_vidq)) {
-		printk(KERN_INFO "%s queue busy\n", __func__);
+		pr_info("%s queue busy\n", __func__);
 		rc = -EBUSY;
 		goto out;
 	}
@@ -1868,6 +1871,69 @@ static int vidioc_dqbuf(struct file *file, void *priv, struct v4l2_buffer *b)
 	return rc;
 }
 
+void au0828_v4l2_suspend(struct au0828_dev *dev)
+{
+	struct urb *urb;
+	int i;
+
+	pr_info("stopping V4L2\n");
+
+	if (dev->stream_state == STREAM_ON) {
+		pr_info("stopping V4L2 active URBs\n");
+		au0828_analog_stream_disable(dev);
+		/* stop urbs */
+		for (i = 0; i < dev->isoc_ctl.num_bufs; i++) {
+			urb = dev->isoc_ctl.urb[i];
+			if (urb) {
+				if (!irqs_disabled())
+					usb_kill_urb(urb);
+				else
+					usb_unlink_urb(urb);
+			}
+		}
+	}
+
+	if (dev->vid_timeout_running)
+		del_timer_sync(&dev->vid_timeout);
+	if (dev->vbi_timeout_running)
+		del_timer_sync(&dev->vbi_timeout);
+}
+
+void au0828_v4l2_resume(struct au0828_dev *dev)
+{
+	int i, rc;
+
+	pr_info("restarting V4L2\n");
+
+	if (dev->stream_state == STREAM_ON) {
+		au0828_stream_interrupt(dev);
+		au0828_init_tuner(dev);
+	}
+
+	if (dev->vid_timeout_running)
+		mod_timer(&dev->vid_timeout, jiffies + (HZ / 10));
+	if (dev->vbi_timeout_running)
+		mod_timer(&dev->vbi_timeout, jiffies + (HZ / 10));
+
+	/* If we were doing ac97 instead of i2s, it would go here...*/
+	au0828_i2s_init(dev);
+
+	au0828_analog_stream_enable(dev);
+
+	if (!(dev->stream_state == STREAM_ON)) {
+		au0828_analog_stream_reset(dev);
+		/* submit urbs */
+		for (i = 0; i < dev->isoc_ctl.num_bufs; i++) {
+			rc = usb_submit_urb(dev->isoc_ctl.urb[i], GFP_ATOMIC);
+			if (rc) {
+				au0828_isocdbg("submit of urb %i failed (error=%i)\n",
+					       i, rc);
+				au0828_uninit_isoc(dev);
+			}
+		}
+	}
+}
+
 static struct v4l2_file_operations au0828_v4l_fops = {
 	.owner      = THIS_MODULE,
 	.open       = au0828_v4l2_open,
@@ -1939,7 +2005,7 @@ int au0828_analog_register(struct au0828_dev *dev,
 	retval = usb_set_interface(dev->usbdev,
 			interface->cur_altsetting->desc.bInterfaceNumber, 5);
 	if (retval != 0) {
-		printk(KERN_INFO "Failure setting usb interface0 to as5\n");
+		pr_info("Failure setting usb interface0 to as5\n");
 		return retval;
 	}
 
@@ -1963,7 +2029,7 @@ int au0828_analog_register(struct au0828_dev *dev,
 		}
 	}
 	if (!(dev->isoc_in_endpointaddr)) {
-		printk(KERN_INFO "Could not locate isoc endpoint\n");
+		pr_info("Could not locate isoc endpoint\n");
 		kfree(dev);
 		return -ENODEV;
 	}
diff --git a/drivers/media/usb/au0828/au0828.h b/drivers/media/usb/au0828/au0828.h
index 96bec05d7dac..36815a369c68 100644
--- a/drivers/media/usb/au0828/au0828.h
+++ b/drivers/media/usb/au0828/au0828.h
@@ -19,6 +19,8 @@
  *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/usb.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
@@ -42,7 +44,6 @@
 #include "au0828-reg.h"
 #include "au0828-cards.h"
 
-#define DRIVER_NAME "au0828"
 #define URB_COUNT   16
 #define URB_BUFSIZE (0xe522)
 
@@ -89,6 +90,7 @@ struct au0828_board {
 	unsigned char tuner_addr;
 	unsigned char i2c_clk_divider;
 	unsigned char has_ir_i2c:1;
+	unsigned char has_analog:1;
 	struct au0828_input input[AU0828_MAX_INPUT];
 
 };
@@ -266,8 +268,8 @@ struct au0828_dev {
 	char *transfer_buffer[AU0828_MAX_ISO_BUFS];/* transfer buffers for isoc
 						   transfer */
 
-	/* USB / URB Related */
-	int		urb_streaming;
+	/* DVB USB / URB Related */
+	bool		urb_streaming, need_urb_start;
 	struct urb	*urbs[URB_COUNT];
 
 	/* Preallocated transfer digital transfer buffers */
@@ -311,22 +313,38 @@ int au0828_analog_register(struct au0828_dev *dev,
 			   struct usb_interface *interface);
 int au0828_analog_stream_disable(struct au0828_dev *d);
 void au0828_analog_unregister(struct au0828_dev *dev);
+#ifdef CONFIG_VIDEO_AU0828_V4L2
+void au0828_v4l2_suspend(struct au0828_dev *dev);
+void au0828_v4l2_resume(struct au0828_dev *dev);
+#else
+static inline void au0828_v4l2_suspend(struct au0828_dev *dev) { };
+static inline void au0828_v4l2_resume(struct au0828_dev *dev) { };
+#endif
 
 /* ----------------------------------------------------------- */
 /* au0828-dvb.c */
 extern int au0828_dvb_register(struct au0828_dev *dev);
 extern void au0828_dvb_unregister(struct au0828_dev *dev);
+void au0828_dvb_suspend(struct au0828_dev *dev);
+void au0828_dvb_resume(struct au0828_dev *dev);
 
 /* au0828-vbi.c */
 extern struct videobuf_queue_ops au0828_vbi_qops;
 
 #define dprintk(level, fmt, arg...)\
 	do { if (au0828_debug & level)\
-		printk(KERN_DEBUG DRIVER_NAME "/0: " fmt, ## arg);\
+		printk(KERN_DEBUG pr_fmt(fmt), ## arg);\
 	} while (0)
 
 /* au0828-input.c */
-int au0828_rc_register(struct au0828_dev *dev);
-void au0828_rc_unregister(struct au0828_dev *dev);
-int au0828_rc_suspend(struct au0828_dev *dev);
-int au0828_rc_resume(struct au0828_dev *dev);
+#ifdef CONFIG_VIDEO_AU0828_RC
+extern int au0828_rc_register(struct au0828_dev *dev);
+extern void au0828_rc_unregister(struct au0828_dev *dev);
+extern int au0828_rc_suspend(struct au0828_dev *dev);
+extern int au0828_rc_resume(struct au0828_dev *dev);
+#else
+static inline int au0828_rc_register(struct au0828_dev *dev) { return 0; }
+static inline void au0828_rc_unregister(struct au0828_dev *dev) { }
+static inline int au0828_rc_suspend(struct au0828_dev *dev) { return 0; }
+static inline int au0828_rc_resume(struct au0828_dev *dev) { return 0; }
+#endif
diff --git a/drivers/media/usb/cx231xx/cx231xx-avcore.c b/drivers/media/usb/cx231xx/cx231xx-avcore.c
index a428c10e1a16..40a69879fc0a 100644
--- a/drivers/media/usb/cx231xx/cx231xx-avcore.c
+++ b/drivers/media/usb/cx231xx/cx231xx-avcore.c
@@ -1595,7 +1595,7 @@ void cx231xx_set_DIF_bandpass(struct cx231xx *dev, u32 if_freq,
 		if_freq = 16000000;
 	}
 
-	cx231xx_info("Enter IF=%zd\n",
+	cx231xx_info("Enter IF=%zu\n",
 			ARRAY_SIZE(Dif_set_array));
 	for (i = 0; i < ARRAY_SIZE(Dif_set_array); i++) {
 		if (Dif_set_array[i].if_freq == if_freq) {
@@ -2223,7 +2223,7 @@ int cx231xx_set_power_mode(struct cx231xx *dev, enum AV_MODE mode)
 	if (status < 0)
 		return status;
 
-	tmp = le32_to_cpu(*((u32 *) value));
+	tmp = le32_to_cpu(*((__le32 *) value));
 
 	switch (mode) {
 	case POLARIS_AVMODE_ENXTERNAL_AV:
@@ -2444,7 +2444,7 @@ int cx231xx_power_suspend(struct cx231xx *dev)
 	if (status > 0)
 		return status;
 
-	tmp = le32_to_cpu(*((u32 *) value));
+	tmp = le32_to_cpu(*((__le32 *) value));
 	tmp &= (~PWR_MODE_MASK);
 
 	value[0] = (u8) tmp;
@@ -2472,7 +2472,7 @@ int cx231xx_start_stream(struct cx231xx *dev, u32 ep_mask)
 	if (status < 0)
 		return status;
 
-	tmp = le32_to_cpu(*((u32 *) value));
+	tmp = le32_to_cpu(*((__le32 *) value));
 	tmp |= ep_mask;
 	value[0] = (u8) tmp;
 	value[1] = (u8) (tmp >> 8);
@@ -2497,7 +2497,7 @@ int cx231xx_stop_stream(struct cx231xx *dev, u32 ep_mask)
 	if (status < 0)
 		return status;
 
-	tmp = le32_to_cpu(*((u32 *) value));
+	tmp = le32_to_cpu(*((__le32 *) value));
 	tmp &= (~ep_mask);
 	value[0] = (u8) tmp;
 	value[1] = (u8) (tmp >> 8);
@@ -2644,7 +2644,7 @@ static int cx231xx_set_gpio_bit(struct cx231xx *dev, u32 gpio_bit, u32 gpio_val)
 {
 	int status = 0;
 
-	gpio_val = cpu_to_le32(gpio_val);
+	gpio_val = (__force u32)cpu_to_le32(gpio_val);
 	status = cx231xx_send_gpio_cmd(dev, gpio_bit, (u8 *)&gpio_val, 4, 0, 0);
 
 	return status;
@@ -2652,7 +2652,7 @@ static int cx231xx_set_gpio_bit(struct cx231xx *dev, u32 gpio_bit, u32 gpio_val)
 
 static int cx231xx_get_gpio_bit(struct cx231xx *dev, u32 gpio_bit, u32 *gpio_val)
 {
-	u32 tmp;
+	__le32 tmp;
 	int status = 0;
 
 	status = cx231xx_send_gpio_cmd(dev, gpio_bit, (u8 *)&tmp, 4, 0, 1);
diff --git a/drivers/media/usb/cx231xx/cx231xx-cards.c b/drivers/media/usb/cx231xx/cx231xx-cards.c
index 8039b769f258..791f00c6276b 100644
--- a/drivers/media/usb/cx231xx/cx231xx-cards.c
+++ b/drivers/media/usb/cx231xx/cx231xx-cards.c
@@ -705,7 +705,7 @@ struct cx231xx_board cx231xx_boards[] = {
 		},
 	},
 	[CX231XX_BOARD_HAUPPAUGE_930C_HD_1113xx] = {
-		.name = "Hauppauge WinTV 930C-HD (1113xx) / PCTV QuatroStick 521e",
+		.name = "Hauppauge WinTV 930C-HD (1113xx) / HVR-900H (111xxx) / PCTV QuatroStick 521e",
 		.tuner_type = TUNER_NXP_TDA18271,
 		.tuner_addr = 0x60,
 		.tuner_gpio = RDE250_XCV_TUNER,
@@ -744,7 +744,7 @@ struct cx231xx_board cx231xx_boards[] = {
 		} },
 	},
 	[CX231XX_BOARD_HAUPPAUGE_930C_HD_1114xx] = {
-		.name = "Hauppauge WinTV 930C-HD (1114xx) / PCTV QuatroStick 522e",
+		.name = "Hauppauge WinTV 930C-HD (1114xx) / HVR-901H (1114xx) / PCTV QuatroStick 522e",
 		.tuner_type = TUNER_ABSENT,
 		.tuner_addr = 0x60,
 		.tuner_gpio = RDE250_XCV_TUNER,
@@ -815,6 +815,12 @@ struct usb_device_id cx231xx_id_table[] = {
 	 .driver_info = CX231XX_BOARD_HAUPPAUGE_930C_HD_1113xx},
 	{USB_DEVICE(0x2040, 0xb131),
 	 .driver_info = CX231XX_BOARD_HAUPPAUGE_930C_HD_1114xx},
+	/* Hauppauge WinTV-HVR-900-H */
+	{USB_DEVICE(0x2040, 0xb138),
+	 .driver_info = CX231XX_BOARD_HAUPPAUGE_930C_HD_1113xx},
+	/* Hauppauge WinTV-HVR-901-H */
+	{USB_DEVICE(0x2040, 0xb139),
+	 .driver_info = CX231XX_BOARD_HAUPPAUGE_930C_HD_1114xx},
 	{USB_DEVICE(0x2040, 0xb140),
 	 .driver_info = CX231XX_BOARD_HAUPPAUGE_EXETER},
 	{USB_DEVICE(0x2040, 0xc200),
diff --git a/drivers/media/usb/cx231xx/cx231xx-core.c b/drivers/media/usb/cx231xx/cx231xx-core.c
index 513194aa6561..180103e48036 100644
--- a/drivers/media/usb/cx231xx/cx231xx-core.c
+++ b/drivers/media/usb/cx231xx/cx231xx-core.c
@@ -1491,7 +1491,7 @@ int cx231xx_mode_register(struct cx231xx *dev, u16 address, u32 mode)
 	if (status < 0)
 		return status;
 
-	tmp = le32_to_cpu(*((u32 *) value));
+	tmp = le32_to_cpu(*((__le32 *) value));
 	tmp |= mode;
 
 	value[0] = (u8) tmp;
diff --git a/drivers/media/usb/cx231xx/cx231xx-dvb.c b/drivers/media/usb/cx231xx/cx231xx-dvb.c
index 1fa79741d199..6c7b5e250eed 100644
--- a/drivers/media/usb/cx231xx/cx231xx-dvb.c
+++ b/drivers/media/usb/cx231xx/cx231xx-dvb.c
@@ -403,8 +403,6 @@ static int attach_xc5000(u8 addr, struct cx231xx *dev)
 
 int cx231xx_set_analog_freq(struct cx231xx *dev, u32 freq)
 {
-	int status = 0;
-
 	if ((dev->dvb != NULL) && (dev->dvb->frontend != NULL)) {
 
 		struct dvb_tuner_ops *dops = &dev->dvb->frontend->ops.tuner_ops;
@@ -423,7 +421,7 @@ int cx231xx_set_analog_freq(struct cx231xx *dev, u32 freq)
 
 	}
 
-	return status;
+	return 0;
 }
 
 int cx231xx_reset_analog_tuner(struct cx231xx *dev)
@@ -740,7 +738,7 @@ static int dvb_init(struct cx231xx *dev)
 			goto out_free;
 		}
 
-		dev->dvb->frontend->ops.i2c_gate_ctrl = 0;
+		dev->dvb->frontend->ops.i2c_gate_ctrl = NULL;
 
 		/* define general-purpose callback pointer */
 		dvb->frontend->callback = cx231xx_tuner_callback;
@@ -773,7 +771,7 @@ static int dvb_init(struct cx231xx *dev)
 			goto out_free;
 		}
 
-		dev->dvb->frontend->ops.i2c_gate_ctrl = 0;
+		dev->dvb->frontend->ops.i2c_gate_ctrl = NULL;
 
 		/* define general-purpose callback pointer */
 		dvb->frontend->callback = cx231xx_tuner_callback;
diff --git a/drivers/media/usb/dvb-usb-v2/Kconfig b/drivers/media/usb/dvb-usb-v2/Kconfig
index 66645b02c854..5b34323ad207 100644
--- a/drivers/media/usb/dvb-usb-v2/Kconfig
+++ b/drivers/media/usb/dvb-usb-v2/Kconfig
@@ -141,3 +141,10 @@ config DVB_USB_RTL28XXU
 	help
 	  Say Y here to support the Realtek RTL28xxU DVB USB receiver.
 
+config DVB_USB_DVBSKY
+	tristate "DVBSky USB support"
+	depends on DVB_USB_V2
+	select DVB_M88DS3103 if MEDIA_SUBDRV_AUTOSELECT
+	select MEDIA_TUNER_M88TS2022 if MEDIA_SUBDRV_AUTOSELECT
+	help
+	  Say Y here to support the USB receivers from DVBSky.
diff --git a/drivers/media/usb/dvb-usb-v2/Makefile b/drivers/media/usb/dvb-usb-v2/Makefile
index bc38f03394cd..f10d4df0eae5 100644
--- a/drivers/media/usb/dvb-usb-v2/Makefile
+++ b/drivers/media/usb/dvb-usb-v2/Makefile
@@ -37,6 +37,9 @@ obj-$(CONFIG_DVB_USB_MXL111SF) += mxl111sf-tuner.o
 dvb-usb-rtl28xxu-objs := rtl28xxu.o
 obj-$(CONFIG_DVB_USB_RTL28XXU) += dvb-usb-rtl28xxu.o
 
+dvb-usb-dvbsky-objs := dvbsky.o
+obj-$(CONFIG_DVB_USB_DVBSKY) += dvb-usb-dvbsky.o
+
 ccflags-y += -I$(srctree)/drivers/media/dvb-core
 ccflags-y += -I$(srctree)/drivers/media/dvb-frontends
 ccflags-y += -I$(srctree)/drivers/media/tuners
diff --git a/drivers/media/usb/dvb-usb-v2/af9015.c b/drivers/media/usb/dvb-usb-v2/af9015.c
index 5ca738ab44e0..16c0b7d4f8e7 100644
--- a/drivers/media/usb/dvb-usb-v2/af9015.c
+++ b/drivers/media/usb/dvb-usb-v2/af9015.c
@@ -419,7 +419,7 @@ static int af9015_eeprom_hash(struct dvb_usb_device *d)
 	/* calculate checksum */
 	for (i = 0; i < AF9015_EEPROM_SIZE / sizeof(u32); i++) {
 		state->eeprom_sum *= GOLDEN_RATIO_PRIME_32;
-		state->eeprom_sum += le32_to_cpu(((u32 *)buf)[i]);
+		state->eeprom_sum += le32_to_cpu(((__le32 *)buf)[i]);
 	}
 
 	for (i = 0; i < AF9015_EEPROM_SIZE; i += 16)
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index c82beac0e0cb..00758c83eec7 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -193,6 +193,92 @@ static int af9035_wr_reg_mask(struct dvb_usb_device *d, u32 reg, u8 val,
 	return af9035_wr_regs(d, reg, &val, 1);
 }
 
+static int af9035_add_i2c_dev(struct dvb_usb_device *d, char *type, u8 addr,
+		void *platform_data, struct i2c_adapter *adapter)
+{
+	int ret, num;
+	struct state *state = d_to_priv(d);
+	struct i2c_client *client;
+	struct i2c_board_info board_info = {
+		.addr = addr,
+		.platform_data = platform_data,
+	};
+
+	strlcpy(board_info.type, type, I2C_NAME_SIZE);
+
+	/* find first free client */
+	for (num = 0; num < AF9035_I2C_CLIENT_MAX; num++) {
+		if (state->i2c_client[num] == NULL)
+			break;
+	}
+
+	dev_dbg(&d->udev->dev, "%s: num=%d\n", __func__, num);
+
+	if (num == AF9035_I2C_CLIENT_MAX) {
+		dev_err(&d->udev->dev, "%s: I2C client out of index\n",
+				KBUILD_MODNAME);
+		ret = -ENODEV;
+		goto err;
+	}
+
+	request_module(board_info.type);
+
+	/* register I2C device */
+	client = i2c_new_device(adapter, &board_info);
+	if (client == NULL || client->dev.driver == NULL) {
+		ret = -ENODEV;
+		goto err;
+	}
+
+	/* increase I2C driver usage count */
+	if (!try_module_get(client->dev.driver->owner)) {
+		i2c_unregister_device(client);
+		ret = -ENODEV;
+		goto err;
+	}
+
+	state->i2c_client[num] = client;
+	return 0;
+err:
+	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	return ret;
+}
+
+static void af9035_del_i2c_dev(struct dvb_usb_device *d)
+{
+	int num;
+	struct state *state = d_to_priv(d);
+	struct i2c_client *client;
+
+	/* find last used client */
+	num = AF9035_I2C_CLIENT_MAX;
+	while (num--) {
+		if (state->i2c_client[num] != NULL)
+			break;
+	}
+
+	dev_dbg(&d->udev->dev, "%s: num=%d\n", __func__, num);
+
+	if (num == -1) {
+		dev_err(&d->udev->dev, "%s: I2C client out of index\n",
+				KBUILD_MODNAME);
+		goto err;
+	}
+
+	client = state->i2c_client[num];
+
+	/* decrease I2C driver usage count */
+	module_put(client->dev.driver->owner);
+
+	/* unregister I2C device */
+	i2c_unregister_device(client);
+
+	state->i2c_client[num] = NULL;
+	return;
+err:
+	dev_dbg(&d->udev->dev, "%s: failed\n", __func__);
+}
+
 static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
 		struct i2c_msg msg[], int num)
 {
@@ -204,7 +290,7 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
 		return -EAGAIN;
 
 	/*
-	 * I2C sub header is 5 bytes long. Meaning of those bytes are:
+	 * AF9035 I2C sub header is 5 bytes long. Meaning of those bytes are:
 	 * 0: data len
 	 * 1: I2C addr << 1
 	 * 2: reg addr len
@@ -218,110 +304,156 @@ static int af9035_i2c_master_xfer(struct i2c_adapter *adap,
 	 * NOTE: As a firmware knows tuner type there is very small possibility
 	 * there could be some tuner I2C hacks done by firmware and this may
 	 * lead problems if firmware expects those bytes are used.
+	 *
+	 * TODO: Here is few hacks. AF9035 chip integrates AF9033 demodulator.
+	 * IT9135 chip integrates AF9033 demodulator and RF tuner. For dual
+	 * tuner devices, there is also external AF9033 demodulator connected
+	 * via external I2C bus. All AF9033 demod I2C traffic, both single and
+	 * dual tuner configuration, is covered by firmware - actual USB IO
+	 * looks just like a memory access.
+	 * In case of IT913x chip, there is own tuner driver. It is implemented
+	 * currently as a I2C driver, even tuner IP block is likely build
+	 * directly into the demodulator memory space and there is no own I2C
+	 * bus. I2C subsystem does not allow register multiple devices to same
+	 * bus, having same slave address. Due to that we reuse demod address,
+	 * shifted by one bit, on that case.
+	 *
+	 * For IT930x we use a different command and the sub header is
+	 * different as well:
+	 * 0: data len
+	 * 1: I2C bus (0x03 seems to be only value used)
+	 * 2: I2C addr << 1
 	 */
-	if (num == 2 && !(msg[0].flags & I2C_M_RD) &&
-			(msg[1].flags & I2C_M_RD)) {
+#define AF9035_IS_I2C_XFER_WRITE_READ(_msg, _num) \
+	(_num == 2 && !(_msg[0].flags & I2C_M_RD) && (_msg[1].flags & I2C_M_RD))
+#define AF9035_IS_I2C_XFER_WRITE(_msg, _num) \
+	(_num == 1 && !(_msg[0].flags & I2C_M_RD))
+#define AF9035_IS_I2C_XFER_READ(_msg, _num) \
+	(_num == 1 && (_msg[0].flags & I2C_M_RD))
+
+	if (AF9035_IS_I2C_XFER_WRITE_READ(msg, num)) {
 		if (msg[0].len > 40 || msg[1].len > 40) {
 			/* TODO: correct limits > 40 */
 			ret = -EOPNOTSUPP;
-		} else if ((msg[0].addr == state->af9033_config[0].i2c_addr) ||
-			   (msg[0].addr == state->af9033_config[1].i2c_addr)) {
+		} else if ((msg[0].addr == state->af9033_i2c_addr[0]) ||
+			   (msg[0].addr == state->af9033_i2c_addr[1]) ||
+			   (state->chip_type == 0x9135)) {
 			/* demod access via firmware interface */
 			u32 reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 |
 					msg[0].buf[2];
 
-			if (msg[0].addr == state->af9033_config[1].i2c_addr)
+			if (msg[0].addr == state->af9033_i2c_addr[1] ||
+			    msg[0].addr == (state->af9033_i2c_addr[1] >> 1))
 				reg |= 0x100000;
 
 			ret = af9035_rd_regs(d, reg, &msg[1].buf[0],
 					msg[1].len);
 		} else {
-			/* I2C */
+			/* I2C write + read */
 			u8 buf[MAX_XFER_SIZE];
 			struct usb_req req = { CMD_I2C_RD, 0, 5 + msg[0].len,
 					buf, msg[1].len, msg[1].buf };
 
-			if (5 + msg[0].len > sizeof(buf)) {
-				dev_warn(&d->udev->dev,
-					 "%s: i2c xfer: len=%d is too big!\n",
-					 KBUILD_MODNAME, msg[0].len);
-				ret = -EOPNOTSUPP;
-				goto unlock;
+			if (state->chip_type == 0x9306) {
+				req.cmd = CMD_GENERIC_I2C_RD;
+				req.wlen = 3 + msg[0].len;
 			}
 			req.mbox |= ((msg[0].addr & 0x80)  >>  3);
+
 			buf[0] = msg[1].len;
-			buf[1] = msg[0].addr << 1;
-			buf[2] = 0x00; /* reg addr len */
-			buf[3] = 0x00; /* reg addr MSB */
-			buf[4] = 0x00; /* reg addr LSB */
-			memcpy(&buf[5], msg[0].buf, msg[0].len);
+			if (state->chip_type == 0x9306) {
+				buf[1] = 0x03; /* I2C bus */
+				buf[2] = msg[0].addr << 1;
+				memcpy(&buf[3], msg[0].buf, msg[0].len);
+			} else {
+				buf[1] = msg[0].addr << 1;
+				buf[2] = 0x00; /* reg addr len */
+				buf[3] = 0x00; /* reg addr MSB */
+				buf[4] = 0x00; /* reg addr LSB */
+				memcpy(&buf[5], msg[0].buf, msg[0].len);
+			}
 			ret = af9035_ctrl_msg(d, &req);
 		}
-	} else if (num == 1 && !(msg[0].flags & I2C_M_RD)) {
+	} else if (AF9035_IS_I2C_XFER_WRITE(msg, num)) {
 		if (msg[0].len > 40) {
 			/* TODO: correct limits > 40 */
 			ret = -EOPNOTSUPP;
-		} else if ((msg[0].addr == state->af9033_config[0].i2c_addr) ||
-			   (msg[0].addr == state->af9033_config[1].i2c_addr)) {
+		} else if ((msg[0].addr == state->af9033_i2c_addr[0]) ||
+			   (msg[0].addr == state->af9033_i2c_addr[1]) ||
+			   (state->chip_type == 0x9135)) {
 			/* demod access via firmware interface */
 			u32 reg = msg[0].buf[0] << 16 | msg[0].buf[1] << 8 |
 					msg[0].buf[2];
 
-			if (msg[0].addr == state->af9033_config[1].i2c_addr)
+			if (msg[0].addr == state->af9033_i2c_addr[1] ||
+			    msg[0].addr == (state->af9033_i2c_addr[1] >> 1))
 				reg |= 0x100000;
 
 			ret = af9035_wr_regs(d, reg, &msg[0].buf[3],
 					msg[0].len - 3);
 		} else {
-			/* I2C */
+			/* I2C write */
 			u8 buf[MAX_XFER_SIZE];
 			struct usb_req req = { CMD_I2C_WR, 0, 5 + msg[0].len,
 					buf, 0, NULL };
 
-			if (5 + msg[0].len > sizeof(buf)) {
-				dev_warn(&d->udev->dev,
-					 "%s: i2c xfer: len=%d is too big!\n",
-					 KBUILD_MODNAME, msg[0].len);
-				ret = -EOPNOTSUPP;
-				goto unlock;
+			if (state->chip_type == 0x9306) {
+				req.cmd = CMD_GENERIC_I2C_WR;
+				req.wlen = 3 + msg[0].len;
 			}
+
 			req.mbox |= ((msg[0].addr & 0x80)  >>  3);
 			buf[0] = msg[0].len;
-			buf[1] = msg[0].addr << 1;
-			buf[2] = 0x00; /* reg addr len */
-			buf[3] = 0x00; /* reg addr MSB */
-			buf[4] = 0x00; /* reg addr LSB */
-			memcpy(&buf[5], msg[0].buf, msg[0].len);
+			if (state->chip_type == 0x9306) {
+				buf[1] = 0x03; /* I2C bus */
+				buf[2] = msg[0].addr << 1;
+				memcpy(&buf[3], msg[0].buf, msg[0].len);
+			} else {
+				buf[1] = msg[0].addr << 1;
+				buf[2] = 0x00; /* reg addr len */
+				buf[3] = 0x00; /* reg addr MSB */
+				buf[4] = 0x00; /* reg addr LSB */
+				memcpy(&buf[5], msg[0].buf, msg[0].len);
+			}
 			ret = af9035_ctrl_msg(d, &req);
 		}
-	} else if (num == 1 && (msg[0].flags & I2C_M_RD)) {
+	} else if (AF9035_IS_I2C_XFER_READ(msg, num)) {
 		if (msg[0].len > 40) {
 			/* TODO: correct limits > 40 */
 			ret = -EOPNOTSUPP;
 		} else {
-			/* I2C */
+			/* I2C read */
 			u8 buf[5];
 			struct usb_req req = { CMD_I2C_RD, 0, sizeof(buf),
-					buf, msg[0].len, msg[0].buf };
+						buf, msg[0].len, msg[0].buf };
+
+			if (state->chip_type == 0x9306) {
+				req.cmd = CMD_GENERIC_I2C_RD;
+				req.wlen = 3;
+			}
 			req.mbox |= ((msg[0].addr & 0x80)  >>  3);
 			buf[0] = msg[0].len;
-			buf[1] = msg[0].addr << 1;
-			buf[2] = 0x00; /* reg addr len */
-			buf[3] = 0x00; /* reg addr MSB */
-			buf[4] = 0x00; /* reg addr LSB */
+			if (state->chip_type == 0x9306) {
+				buf[1] = 0x03; /* I2C bus */
+				buf[2] = msg[0].addr << 1;
+			} else {
+				buf[1] = msg[0].addr << 1;
+				buf[2] = 0x00; /* reg addr len */
+				buf[3] = 0x00; /* reg addr MSB */
+				buf[4] = 0x00; /* reg addr LSB */
+			}
 			ret = af9035_ctrl_msg(d, &req);
 		}
 	} else {
 		/*
 		 * We support only three kind of I2C transactions:
-		 * 1) 1 x read + 1 x write (repeated start)
+		 * 1) 1 x write + 1 x read (repeated start)
 		 * 2) 1 x write
 		 * 3) 1 x read
 		 */
 		ret = -EOPNOTSUPP;
 	}
 
-unlock:
 	mutex_unlock(&d->i2c_mutex);
 
 	if (ret < 0)
@@ -371,6 +503,9 @@ static int af9035_identify_state(struct dvb_usb_device *d, const char **name)
 		else
 			*name = AF9035_FIRMWARE_IT9135_V1;
 		state->eeprom_addr = EEPROM_BASE_IT9135;
+	} else if (state->chip_type == 0x9306) {
+		*name = AF9035_FIRMWARE_IT9303;
+		state->eeprom_addr = EEPROM_BASE_IT9135;
 	} else {
 		*name = AF9035_FIRMWARE_AF9035;
 		state->eeprom_addr = EEPROM_BASE_AF9035;
@@ -536,6 +671,7 @@ static int af9035_download_firmware(struct dvb_usb_device *d,
 	u8 tmp;
 	struct usb_req req = { 0, 0, 0, NULL, 0, NULL };
 	struct usb_req req_fw_ver = { CMD_FW_QUERYINFO, 0, 1, wbuf, 4, rbuf };
+
 	dev_dbg(&d->udev->dev, "%s:\n", __func__);
 
 	/*
@@ -579,7 +715,8 @@ static int af9035_download_firmware(struct dvb_usb_device *d,
 		if (!tmp)
 			tmp = 0x3a;
 
-		if (state->chip_type == 0x9135) {
+		if ((state->chip_type == 0x9135) ||
+				(state->chip_type == 0x9306)) {
 			ret = af9035_wr_reg(d, 0x004bfb, tmp);
 			if (ret < 0)
 				goto err;
@@ -640,23 +777,26 @@ static int af9035_read_config(struct dvb_usb_device *d)
 	u16 tmp16, addr;
 
 	/* demod I2C "address" */
-	state->af9033_config[0].i2c_addr = 0x38;
-	state->af9033_config[1].i2c_addr = 0x3a;
+	state->af9033_i2c_addr[0] = 0x38;
+	state->af9033_i2c_addr[1] = 0x3a;
 	state->af9033_config[0].adc_multiplier = AF9033_ADC_MULTIPLIER_2X;
 	state->af9033_config[1].adc_multiplier = AF9033_ADC_MULTIPLIER_2X;
 	state->af9033_config[0].ts_mode = AF9033_TS_MODE_USB;
 	state->af9033_config[1].ts_mode = AF9033_TS_MODE_SERIAL;
 
-	/* eeprom memory mapped location */
 	if (state->chip_type == 0x9135) {
+		/* feed clock for integrated RF tuner */
+		state->af9033_config[0].dyn0_clk = true;
+		state->af9033_config[1].dyn0_clk = true;
+
 		if (state->chip_version == 0x02) {
 			state->af9033_config[0].tuner = AF9033_TUNER_IT9135_60;
 			state->af9033_config[1].tuner = AF9033_TUNER_IT9135_60;
-			tmp16 = 0x00461d;
+			tmp16 = 0x00461d; /* eeprom memory mapped location */
 		} else {
 			state->af9033_config[0].tuner = AF9033_TUNER_IT9135_38;
 			state->af9033_config[1].tuner = AF9033_TUNER_IT9135_38;
-			tmp16 = 0x00461b;
+			tmp16 = 0x00461b; /* eeprom memory mapped location */
 		}
 
 		/* check if eeprom exists */
@@ -668,8 +808,16 @@ static int af9035_read_config(struct dvb_usb_device *d)
 			dev_dbg(&d->udev->dev, "%s: no eeprom\n", __func__);
 			goto skip_eeprom;
 		}
+	} else if (state->chip_type == 0x9306) {
+		/*
+		 * IT930x is an USB bridge, only single demod-single tuner
+		 * configurations seen so far.
+		 */
+		return 0;
 	}
 
+
+
 	/* check if there is dual tuners */
 	ret = af9035_rd_reg(d, state->eeprom_addr + EEPROM_TS_MODE, &tmp);
 	if (ret < 0)
@@ -690,7 +838,7 @@ static int af9035_read_config(struct dvb_usb_device *d)
 			goto err;
 
 		if (tmp)
-			state->af9033_config[1].i2c_addr = tmp;
+			state->af9033_i2c_addr[1] = tmp;
 
 		dev_dbg(&d->udev->dev, "%s: 2nd demod I2C addr=%02x\n",
 				__func__, tmp);
@@ -799,25 +947,6 @@ static int af9035_read_config(struct dvb_usb_device *d)
 		addr += 0x10; /* shift for the 2nd tuner params */
 	}
 
-	/*
-	 * These AVerMedia devices has a bad EEPROM content :-(
-	 * Override some wrong values here.
-	 */
-	if (le16_to_cpu(d->udev->descriptor.idVendor) == USB_VID_AVERMEDIA) {
-		switch (le16_to_cpu(d->udev->descriptor.idProduct)) {
-		case USB_PID_AVERMEDIA_A835B_1835:
-		case USB_PID_AVERMEDIA_A835B_2835:
-		case USB_PID_AVERMEDIA_A835B_3835:
-			dev_info(&d->udev->dev,
-				 "%s: overriding tuner from %02x to %02x\n",
-				 KBUILD_MODNAME, state->af9033_config[0].tuner,
-				 AF9033_TUNER_IT9135_60);
-
-			state->af9033_config[0].tuner = AF9033_TUNER_IT9135_60;
-			break;
-		}
-	}
-
 skip_eeprom:
 	/* get demod clock */
 	ret = af9035_rd_reg(d, 0x00d800, &tmp);
@@ -990,6 +1119,7 @@ static int af9035_frontend_callback(void *adapter_priv, int component,
 static int af9035_get_adapter_count(struct dvb_usb_device *d)
 {
 	struct state *state = d_to_priv(d);
+
 	return state->dual_mode + 1;
 }
 
@@ -998,7 +1128,8 @@ static int af9035_frontend_attach(struct dvb_usb_adapter *adap)
 	struct state *state = adap_to_priv(adap);
 	struct dvb_usb_device *d = adap_to_d(adap);
 	int ret;
-	dev_dbg(&d->udev->dev, "%s:\n", __func__);
+
+	dev_dbg(&d->udev->dev, "%s: adap->id=%d\n", __func__, adap->id);
 
 	if (!state->af9033_config[adap->id].tuner) {
 		/* unsupported tuner */
@@ -1006,9 +1137,13 @@ static int af9035_frontend_attach(struct dvb_usb_adapter *adap)
 		goto err;
 	}
 
-	/* attach demodulator */
-	adap->fe[0] = dvb_attach(af9033_attach, &state->af9033_config[adap->id],
-			&d->i2c_adap, &state->ops);
+	state->af9033_config[adap->id].fe = &adap->fe[0];
+	state->af9033_config[adap->id].ops = &state->ops;
+	ret = af9035_add_i2c_dev(d, "af9033", state->af9033_i2c_addr[adap->id],
+			&state->af9033_config[adap->id], &d->i2c_adap);
+	if (ret)
+		goto err;
+
 	if (adap->fe[0] == NULL) {
 		ret = -ENODEV;
 		goto err;
@@ -1026,6 +1161,78 @@ err:
 	return ret;
 }
 
+static int it930x_frontend_attach(struct dvb_usb_adapter *adap)
+{
+	struct state *state = adap_to_priv(adap);
+	struct dvb_usb_device *d = adap_to_d(adap);
+	int ret;
+	struct si2168_config si2168_config;
+	struct i2c_adapter *adapter;
+
+	dev_dbg(&d->udev->dev, "adap->id=%d\n", adap->id);
+
+	si2168_config.i2c_adapter = &adapter;
+	si2168_config.fe = &adap->fe[0];
+	si2168_config.ts_mode = SI2168_TS_SERIAL;
+
+	state->af9033_config[adap->id].fe = &adap->fe[0];
+	state->af9033_config[adap->id].ops = &state->ops;
+	ret = af9035_add_i2c_dev(d, "si2168", 0x67, &si2168_config,
+				&d->i2c_adap);
+	if (ret)
+		goto err;
+
+	if (adap->fe[0] == NULL) {
+		ret = -ENODEV;
+		goto err;
+	}
+	state->i2c_adapter_demod = adapter;
+
+	return 0;
+
+err:
+	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+
+	return ret;
+}
+
+static int af9035_frontend_detach(struct dvb_usb_adapter *adap)
+{
+	struct state *state = adap_to_priv(adap);
+	struct dvb_usb_device *d = adap_to_d(adap);
+	int demod2;
+
+	dev_dbg(&d->udev->dev, "%s: adap->id=%d\n", __func__, adap->id);
+
+	/*
+	 * For dual tuner devices we have to resolve 2nd demod client, as there
+	 * is two different kind of tuner drivers; one is using I2C binding
+	 * and the other is using DVB attach/detach binding.
+	 */
+	switch (state->af9033_config[adap->id].tuner) {
+	case AF9033_TUNER_IT9135_38:
+	case AF9033_TUNER_IT9135_51:
+	case AF9033_TUNER_IT9135_52:
+	case AF9033_TUNER_IT9135_60:
+	case AF9033_TUNER_IT9135_61:
+	case AF9033_TUNER_IT9135_62:
+		demod2 = 2;
+		break;
+	default:
+		demod2 = 1;
+	}
+
+	if (adap->id == 1) {
+		if (state->i2c_client[demod2])
+			af9035_del_i2c_dev(d);
+	} else if (adap->id == 0) {
+		if (state->i2c_client[0])
+			af9035_del_i2c_dev(d);
+	}
+
+	return 0;
+}
+
 static struct tua9001_config af9035_tua9001_config = {
 	.i2c_addr = 0x60,
 };
@@ -1084,7 +1291,8 @@ static int af9035_tuner_attach(struct dvb_usb_adapter *adap)
 	struct dvb_frontend *fe;
 	struct i2c_msg msg[1];
 	u8 tuner_addr;
-	dev_dbg(&d->udev->dev, "%s:\n", __func__);
+
+	dev_dbg(&d->udev->dev, "%s: adap->id=%d\n", __func__, adap->id);
 
 	/*
 	 * XXX: Hack used in that function: we abuse unused I2C address bit [7]
@@ -1243,14 +1451,53 @@ static int af9035_tuner_attach(struct dvb_usb_adapter *adap)
 	case AF9033_TUNER_IT9135_38:
 	case AF9033_TUNER_IT9135_51:
 	case AF9033_TUNER_IT9135_52:
+	{
+		struct it913x_config it913x_config = {
+			.fe = adap->fe[0],
+			.chip_ver = 1,
+		};
+
+		if (state->dual_mode) {
+			if (adap->id == 0)
+				it913x_config.role = IT913X_ROLE_DUAL_MASTER;
+			else
+				it913x_config.role = IT913X_ROLE_DUAL_SLAVE;
+		}
+
+		ret = af9035_add_i2c_dev(d, "it913x",
+				state->af9033_i2c_addr[adap->id] >> 1,
+				&it913x_config, &d->i2c_adap);
+		if (ret)
+			goto err;
+
+		fe = adap->fe[0];
+		break;
+	}
 	case AF9033_TUNER_IT9135_60:
 	case AF9033_TUNER_IT9135_61:
 	case AF9033_TUNER_IT9135_62:
-		/* attach tuner */
-		fe = dvb_attach(it913x_attach, adap->fe[0], &d->i2c_adap,
-				state->af9033_config[adap->id].i2c_addr,
-				state->af9033_config[0].tuner);
+	{
+		struct it913x_config it913x_config = {
+			.fe = adap->fe[0],
+			.chip_ver = 2,
+		};
+
+		if (state->dual_mode) {
+			if (adap->id == 0)
+				it913x_config.role = IT913X_ROLE_DUAL_MASTER;
+			else
+				it913x_config.role = IT913X_ROLE_DUAL_SLAVE;
+		}
+
+		ret = af9035_add_i2c_dev(d, "it913x",
+				state->af9033_i2c_addr[adap->id] >> 1,
+				&it913x_config, &d->i2c_adap);
+		if (ret)
+			goto err;
+
+		fe = adap->fe[0];
 		break;
+	}
 	default:
 		fe = NULL;
 	}
@@ -1268,6 +1515,119 @@ err:
 	return ret;
 }
 
+static int it930x_tuner_attach(struct dvb_usb_adapter *adap)
+{
+	struct state *state = adap_to_priv(adap);
+	struct dvb_usb_device *d = adap_to_d(adap);
+	int ret;
+	struct si2157_config si2157_config;
+
+	dev_dbg(&d->udev->dev, "%s: adap->id=%d\n", __func__, adap->id);
+
+	/* I2C master bus 2 clock speed 300k */
+	ret = af9035_wr_reg(d, 0x00f6a7, 0x07);
+	if (ret < 0)
+		goto err;
+
+	/* I2C master bus 1,3 clock speed 300k */
+	ret = af9035_wr_reg(d, 0x00f103, 0x07);
+	if (ret < 0)
+		goto err;
+
+	/* set gpio11 low */
+	ret = af9035_wr_reg_mask(d, 0xd8d4, 0x01, 0x01);
+	if (ret < 0)
+		goto err;
+
+	ret = af9035_wr_reg_mask(d, 0xd8d5, 0x01, 0x01);
+	if (ret < 0)
+		goto err;
+
+	ret = af9035_wr_reg_mask(d, 0xd8d3, 0x01, 0x01);
+	if (ret < 0)
+		goto err;
+
+	/* Tuner enable using gpiot2_en, gpiot2_on and gpiot2_o (reset) */
+	ret = af9035_wr_reg_mask(d, 0xd8b8, 0x01, 0x01);
+	if (ret < 0)
+		goto err;
+
+	ret = af9035_wr_reg_mask(d, 0xd8b9, 0x01, 0x01);
+	if (ret < 0)
+		goto err;
+
+	ret = af9035_wr_reg_mask(d, 0xd8b7, 0x00, 0x01);
+	if (ret < 0)
+		goto err;
+
+	msleep(200);
+
+	ret = af9035_wr_reg_mask(d, 0xd8b7, 0x01, 0x01);
+	if (ret < 0)
+		goto err;
+
+	memset(&si2157_config, 0, sizeof(si2157_config));
+	si2157_config.fe = adap->fe[0];
+	ret = af9035_add_i2c_dev(d, "si2157", 0x63,
+			&si2157_config, state->i2c_adapter_demod);
+
+	if (ret)
+		goto err;
+
+	return 0;
+
+err:
+	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+
+	return ret;
+}
+
+
+static int it930x_tuner_detach(struct dvb_usb_adapter *adap)
+{
+	struct state *state = adap_to_priv(adap);
+	struct dvb_usb_device *d = adap_to_d(adap);
+
+	dev_dbg(&d->udev->dev, "adap->id=%d\n", adap->id);
+
+	if (adap->id == 1) {
+		if (state->i2c_client[3])
+			af9035_del_i2c_dev(d);
+	} else if (adap->id == 0) {
+		if (state->i2c_client[1])
+			af9035_del_i2c_dev(d);
+	}
+
+	return 0;
+}
+
+
+static int af9035_tuner_detach(struct dvb_usb_adapter *adap)
+{
+	struct state *state = adap_to_priv(adap);
+	struct dvb_usb_device *d = adap_to_d(adap);
+
+	dev_dbg(&d->udev->dev, "%s: adap->id=%d\n", __func__, adap->id);
+
+	switch (state->af9033_config[adap->id].tuner) {
+	case AF9033_TUNER_IT9135_38:
+	case AF9033_TUNER_IT9135_51:
+	case AF9033_TUNER_IT9135_52:
+	case AF9033_TUNER_IT9135_60:
+	case AF9033_TUNER_IT9135_61:
+	case AF9033_TUNER_IT9135_62:
+		if (adap->id == 1) {
+			if (state->i2c_client[3])
+				af9035_del_i2c_dev(d);
+		} else if (adap->id == 0) {
+			if (state->i2c_client[1])
+				af9035_del_i2c_dev(d);
+		}
+	}
+
+	return 0;
+}
+
 static int af9035_init(struct dvb_usb_device *d)
 {
 	struct state *state = d_to_priv(d);
@@ -1315,6 +1675,89 @@ err:
 	return ret;
 }
 
+static int it930x_init(struct dvb_usb_device *d)
+{
+	struct state *state = d_to_priv(d);
+	int ret, i;
+	u16 frame_size = (d->udev->speed == USB_SPEED_FULL ? 5 : 816) * 188 / 4;
+	u8 packet_size = (d->udev->speed == USB_SPEED_FULL ? 64 : 512) / 4;
+	struct reg_val_mask tab[] = {
+		{ 0x00da1a, 0x00, 0x01 }, /* ignore_sync_byte */
+		{ 0x00f41f, 0x04, 0x04 }, /* dvbt_inten */
+		{ 0x00da10, 0x00, 0x01 }, /* mpeg_full_speed */
+		{ 0x00f41a, 0x01, 0x01 }, /* dvbt_en */
+		{ 0x00da1d, 0x01, 0x01 }, /* mp2_sw_rst, reset EP4 */
+		{ 0x00dd11, 0x00, 0x20 }, /* ep4_tx_en, disable EP4 */
+		{ 0x00dd13, 0x00, 0x20 }, /* ep4_tx_nak, disable EP4 NAK */
+		{ 0x00dd11, 0x20, 0x20 }, /* ep4_tx_en, enable EP4 */
+		{ 0x00dd11, 0x00, 0x40 }, /* ep5_tx_en, disable EP5 */
+		{ 0x00dd13, 0x00, 0x40 }, /* ep5_tx_nak, disable EP5 NAK */
+		{ 0x00dd11, state->dual_mode << 6, 0x40 }, /* enable EP5 */
+		{ 0x00dd88, (frame_size >> 0) & 0xff, 0xff},
+		{ 0x00dd89, (frame_size >> 8) & 0xff, 0xff},
+		{ 0x00dd0c, packet_size, 0xff},
+		{ 0x00dd8a, (frame_size >> 0) & 0xff, 0xff},
+		{ 0x00dd8b, (frame_size >> 8) & 0xff, 0xff},
+		{ 0x00dd0d, packet_size, 0xff },
+		{ 0x00da1d, 0x00, 0x01 }, /* mp2_sw_rst, disable */
+		{ 0x00d833, 0x01, 0xff }, /* slew rate ctrl: slew rate boosts */
+		{ 0x00d830, 0x00, 0xff }, /* Bit 0 of output driving control */
+		{ 0x00d831, 0x01, 0xff }, /* Bit 1 of output driving control */
+		{ 0x00d832, 0x00, 0xff }, /* Bit 2 of output driving control */
+
+		/* suspend gpio1 for TS-C */
+		{ 0x00d8b0, 0x01, 0xff }, /* gpio1 */
+		{ 0x00d8b1, 0x01, 0xff }, /* gpio1 */
+		{ 0x00d8af, 0x00, 0xff }, /* gpio1 */
+
+		/* suspend gpio7 for TS-D */
+		{ 0x00d8c4, 0x01, 0xff }, /* gpio7 */
+		{ 0x00d8c5, 0x01, 0xff }, /* gpio7 */
+		{ 0x00d8c3, 0x00, 0xff }, /* gpio7 */
+
+		/* suspend gpio13 for TS-B */
+		{ 0x00d8dc, 0x01, 0xff }, /* gpio13 */
+		{ 0x00d8dd, 0x01, 0xff }, /* gpio13 */
+		{ 0x00d8db, 0x00, 0xff }, /* gpio13 */
+
+		/* suspend gpio14 for TS-E */
+		{ 0x00d8e4, 0x01, 0xff }, /* gpio14 */
+		{ 0x00d8e5, 0x01, 0xff }, /* gpio14 */
+		{ 0x00d8e3, 0x00, 0xff }, /* gpio14 */
+
+		/* suspend gpio15 for TS-A */
+		{ 0x00d8e8, 0x01, 0xff }, /* gpio15 */
+		{ 0x00d8e9, 0x01, 0xff }, /* gpio15 */
+		{ 0x00d8e7, 0x00, 0xff }, /* gpio15 */
+
+		{ 0x00da58, 0x00, 0x01 }, /* ts_in_src, serial */
+		{ 0x00da73, 0x01, 0xff }, /* ts0_aggre_mode */
+		{ 0x00da78, 0x47, 0xff }, /* ts0_sync_byte */
+		{ 0x00da4c, 0x01, 0xff }, /* ts0_en */
+		{ 0x00da5a, 0x1f, 0xff }, /* ts_fail_ignore */
+	};
+
+	dev_dbg(&d->udev->dev,
+			"%s: USB speed=%d frame_size=%04x packet_size=%02x\n",
+			__func__, d->udev->speed, frame_size, packet_size);
+
+	/* init endpoints */
+	for (i = 0; i < ARRAY_SIZE(tab); i++) {
+		ret = af9035_wr_reg_mask(d, tab[i].reg,
+				tab[i].val, tab[i].mask);
+
+		if (ret < 0)
+			goto err;
+	}
+
+	return 0;
+err:
+	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+
+	return ret;
+}
+
+
 #if IS_ENABLED(CONFIG_RC_CORE)
 static int af9035_rc_query(struct dvb_usb_device *d)
 {
@@ -1409,6 +1852,7 @@ static int af9035_get_stream_config(struct dvb_frontend *fe, u8 *ts_type,
 		struct usb_data_stream_properties *stream)
 {
 	struct dvb_usb_device *d = fe_to_d(fe);
+
 	dev_dbg(&d->udev->dev, "%s: adap=%d\n", __func__, fe_to_adap(fe)->id);
 
 	if (d->udev->speed == USB_SPEED_FULL)
@@ -1486,7 +1930,9 @@ static const struct dvb_usb_device_properties af9035_props = {
 	.i2c_algo = &af9035_i2c_algo,
 	.read_config = af9035_read_config,
 	.frontend_attach = af9035_frontend_attach,
+	.frontend_detach = af9035_frontend_detach,
 	.tuner_attach = af9035_tuner_attach,
+	.tuner_detach = af9035_tuner_detach,
 	.init = af9035_init,
 	.get_rc_config = af9035_get_rc_config,
 	.get_stream_config = af9035_get_stream_config,
@@ -1515,6 +1961,37 @@ static const struct dvb_usb_device_properties af9035_props = {
 	},
 };
 
+static const struct dvb_usb_device_properties it930x_props = {
+	.driver_name = KBUILD_MODNAME,
+	.owner = THIS_MODULE,
+	.adapter_nr = adapter_nr,
+	.size_of_priv = sizeof(struct state),
+
+	.generic_bulk_ctrl_endpoint = 0x02,
+	.generic_bulk_ctrl_endpoint_response = 0x81,
+
+	.identify_state = af9035_identify_state,
+	.download_firmware = af9035_download_firmware,
+
+	.i2c_algo = &af9035_i2c_algo,
+	.read_config = af9035_read_config,
+	.frontend_attach = it930x_frontend_attach,
+	.frontend_detach = af9035_frontend_detach,
+	.tuner_attach = it930x_tuner_attach,
+	.tuner_detach = it930x_tuner_detach,
+	.init = it930x_init,
+	.get_stream_config = af9035_get_stream_config,
+
+	.get_adapter_count = af9035_get_adapter_count,
+	.adapter = {
+		{
+			.stream = DVB_USB_STREAM_BULK(0x84, 4, 816 * 188),
+		}, {
+			.stream = DVB_USB_STREAM_BULK(0x85, 4, 816 * 188),
+		},
+	},
+};
+
 static const struct usb_device_id af9035_id_table[] = {
 	/* AF9035 devices */
 	{ DVB_USB_DEVICE(USB_VID_AFATECH, USB_PID_AFATECH_AF9035_9035,
@@ -1568,17 +2045,21 @@ static const struct usb_device_id af9035_id_table[] = {
 	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, USB_PID_CTVDIGDUAL_V2,
 		&af9035_props, "Digital Dual TV Receiver CTVDIGDUAL_V2",
 							RC_MAP_IT913X_V1) },
+	/* IT930x devices */
+	{ DVB_USB_DEVICE(USB_VID_ITETECH, USB_PID_ITETECH_IT9303,
+		&it930x_props, "ITE 9303 Generic", NULL) },
 	/* XXX: that same ID [0ccd:0099] is used by af9015 driver too */
 	{ DVB_USB_DEVICE(USB_VID_TERRATEC, 0x0099,
-		&af9035_props, "TerraTec Cinergy T Stick Dual RC (rev. 2)", NULL) },
+		&af9035_props, "TerraTec Cinergy T Stick Dual RC (rev. 2)",
+		NULL) },
 	{ DVB_USB_DEVICE(USB_VID_LEADTEK, 0x6a05,
 		&af9035_props, "Leadtek WinFast DTV Dongle Dual", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_HAUPPAUGE, 0xf900,
 		&af9035_props, "Hauppauge WinTV-MiniStick 2", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_78E,
-		&af9035_props, "PCTV 78e", RC_MAP_IT913X_V1) },
+		&af9035_props, "PCTV AndroiDTV (78e)", RC_MAP_IT913X_V1) },
 	{ DVB_USB_DEVICE(USB_VID_PCTV, USB_PID_PCTV_79E,
-		&af9035_props, "PCTV 79e", RC_MAP_IT913X_V2) },
+		&af9035_props, "PCTV microStick (79e)", RC_MAP_IT913X_V2) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, af9035_id_table);
@@ -1603,3 +2084,4 @@ MODULE_LICENSE("GPL");
 MODULE_FIRMWARE(AF9035_FIRMWARE_AF9035);
 MODULE_FIRMWARE(AF9035_FIRMWARE_IT9135_V1);
 MODULE_FIRMWARE(AF9035_FIRMWARE_IT9135_V2);
+MODULE_FIRMWARE(AF9035_FIRMWARE_IT9303);
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.h b/drivers/media/usb/dvb-usb-v2/af9035.h
index c21902fdd4c4..416a97f05ec8 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.h
+++ b/drivers/media/usb/dvb-usb-v2/af9035.h
@@ -30,7 +30,9 @@
 #include "mxl5007t.h"
 #include "tda18218.h"
 #include "fc2580.h"
-#include "tuner_it913x.h"
+#include "it913x.h"
+#include "si2168.h"
+#include "si2157.h"
 
 struct reg_val {
 	u32 reg;
@@ -61,9 +63,12 @@ struct state {
 	u16 chip_type;
 	u8 dual_mode:1;
 	u16 eeprom_addr;
+	u8 af9033_i2c_addr[2];
 	struct af9033_config af9033_config[2];
-
 	struct af9033_ops ops;
+	#define AF9035_I2C_CLIENT_MAX 4
+	struct i2c_client *i2c_client[AF9035_I2C_CLIENT_MAX];
+	struct i2c_adapter *i2c_adapter_demod;
 };
 
 static const u32 clock_lut_af9035[] = {
@@ -97,6 +102,7 @@ static const u32 clock_lut_it9135[] = {
 #define AF9035_FIRMWARE_AF9035 "dvb-usb-af9035-02.fw"
 #define AF9035_FIRMWARE_IT9135_V1 "dvb-usb-it9135-01.fw"
 #define AF9035_FIRMWARE_IT9135_V2 "dvb-usb-it9135-02.fw"
+#define AF9035_FIRMWARE_IT9303 "dvb-usb-it9303-01.fw"
 
 /*
  * eeprom is memory mapped as read only. Writing that memory mapped address
@@ -138,5 +144,7 @@ static const u32 clock_lut_it9135[] = {
 #define CMD_FW_DL_BEGIN             0x24
 #define CMD_FW_DL_END               0x25
 #define CMD_FW_SCATTER_WR           0x29
+#define CMD_GENERIC_I2C_RD          0x2a
+#define CMD_GENERIC_I2C_WR          0x2b
 
 #endif
diff --git a/drivers/media/usb/dvb-usb-v2/anysee.c b/drivers/media/usb/dvb-usb-v2/anysee.c
index e4a2382196f0..d3c5f230e97a 100644
--- a/drivers/media/usb/dvb-usb-v2/anysee.c
+++ b/drivers/media/usb/dvb-usb-v2/anysee.c
@@ -332,7 +332,6 @@ static struct tda10023_config anysee_tda10023_tda18212_config = {
 };
 
 static struct tda18212_config anysee_tda18212_config = {
-	.i2c_address = (0xc0 >> 1),
 	.if_dvbt_6 = 4150,
 	.if_dvbt_7 = 4150,
 	.if_dvbt_8 = 4150,
@@ -340,7 +339,6 @@ static struct tda18212_config anysee_tda18212_config = {
 };
 
 static struct tda18212_config anysee_tda18212_config2 = {
-	.i2c_address = 0x60 /* (0xc0 >> 1) */,
 	.if_dvbt_6 = 3550,
 	.if_dvbt_7 = 3700,
 	.if_dvbt_8 = 4150,
@@ -632,6 +630,92 @@ error:
 	return ret;
 }
 
+static int anysee_add_i2c_dev(struct dvb_usb_device *d, char *type, u8 addr,
+		void *platform_data)
+{
+	int ret, num;
+	struct anysee_state *state = d_to_priv(d);
+	struct i2c_client *client;
+	struct i2c_adapter *adapter = &d->i2c_adap;
+	struct i2c_board_info board_info = {
+		.addr = addr,
+		.platform_data = platform_data,
+	};
+
+	strlcpy(board_info.type, type, I2C_NAME_SIZE);
+
+	/* find first free client */
+	for (num = 0; num < ANYSEE_I2C_CLIENT_MAX; num++) {
+		if (state->i2c_client[num] == NULL)
+			break;
+	}
+
+	dev_dbg(&d->udev->dev, "%s: num=%d\n", __func__, num);
+
+	if (num == ANYSEE_I2C_CLIENT_MAX) {
+		dev_err(&d->udev->dev, "%s: I2C client out of index\n",
+				KBUILD_MODNAME);
+		ret = -ENODEV;
+		goto err;
+	}
+
+	request_module(board_info.type);
+
+	/* register I2C device */
+	client = i2c_new_device(adapter, &board_info);
+	if (client == NULL || client->dev.driver == NULL) {
+		ret = -ENODEV;
+		goto err;
+	}
+
+	/* increase I2C driver usage count */
+	if (!try_module_get(client->dev.driver->owner)) {
+		i2c_unregister_device(client);
+		ret = -ENODEV;
+		goto err;
+	}
+
+	state->i2c_client[num] = client;
+	return 0;
+err:
+	dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, ret);
+	return ret;
+}
+
+static void anysee_del_i2c_dev(struct dvb_usb_device *d)
+{
+	int num;
+	struct anysee_state *state = d_to_priv(d);
+	struct i2c_client *client;
+
+	/* find last used client */
+	num = ANYSEE_I2C_CLIENT_MAX;
+	while (num--) {
+		if (state->i2c_client[num] != NULL)
+			break;
+	}
+
+	dev_dbg(&d->udev->dev, "%s: num=%d\n", __func__, num);
+
+	if (num == -1) {
+		dev_err(&d->udev->dev, "%s: I2C client out of index\n",
+				KBUILD_MODNAME);
+		goto err;
+	}
+
+	client = state->i2c_client[num];
+
+	/* decrease I2C driver usage count */
+	module_put(client->dev.driver->owner);
+
+	/* unregister I2C device */
+	i2c_unregister_device(client);
+
+	state->i2c_client[num] = NULL;
+err:
+	dev_dbg(&d->udev->dev, "%s: failed\n", __func__);
+}
+
 static int anysee_frontend_attach(struct dvb_usb_adapter *adap)
 {
 	struct anysee_state *state = adap_to_priv(adap);
@@ -640,12 +724,12 @@ static int anysee_frontend_attach(struct dvb_usb_adapter *adap)
 	u8 tmp;
 	struct i2c_msg msg[2] = {
 		{
-			.addr = anysee_tda18212_config.i2c_address,
+			.addr = 0x60,
 			.flags = 0,
 			.len = 1,
 			.buf = "\x00",
 		}, {
-			.addr = anysee_tda18212_config.i2c_address,
+			.addr = 0x60,
 			.flags = I2C_M_RD,
 			.len = 1,
 			.buf = &tmp,
@@ -723,9 +807,11 @@ static int anysee_frontend_attach(struct dvb_usb_adapter *adap)
 		/* probe TDA18212 */
 		tmp = 0;
 		ret = i2c_transfer(&d->i2c_adap, msg, 2);
-		if (ret == 2 && tmp == 0xc7)
+		if (ret == 2 && tmp == 0xc7) {
 			dev_dbg(&d->udev->dev, "%s: TDA18212 found\n",
 					__func__);
+			state->has_tda18212 = true;
+		}
 		else
 			tmp = 0;
 
@@ -939,46 +1025,63 @@ static int anysee_tuner_attach(struct dvb_usb_adapter *adap)
 		 * fails attach old simple PLL. */
 
 		/* attach tuner */
-		fe = dvb_attach(tda18212_attach, adap->fe[0], &d->i2c_adap,
-				&anysee_tda18212_config);
+		if (state->has_tda18212) {
+			struct tda18212_config tda18212_config =
+					anysee_tda18212_config;
 
-		if (fe && adap->fe[1]) {
-			/* attach tuner for 2nd FE */
-			fe = dvb_attach(tda18212_attach, adap->fe[1],
-					&d->i2c_adap, &anysee_tda18212_config);
-			break;
-		} else if (fe) {
-			break;
-		}
-
-		/* attach tuner */
-		fe = dvb_attach(dvb_pll_attach, adap->fe[0], (0xc0 >> 1),
-				&d->i2c_adap, DVB_PLL_SAMSUNG_DTOS403IH102A);
+			tda18212_config.fe = adap->fe[0];
+			ret = anysee_add_i2c_dev(d, "tda18212", 0x60,
+					&tda18212_config);
+			if (ret)
+				goto err;
+
+			/* copy tuner ops for 2nd FE as tuner is shared */
+			if (adap->fe[1]) {
+				adap->fe[1]->tuner_priv =
+						adap->fe[0]->tuner_priv;
+				memcpy(&adap->fe[1]->ops.tuner_ops,
+						&adap->fe[0]->ops.tuner_ops,
+						sizeof(struct dvb_tuner_ops));
+			}
 
-		if (fe && adap->fe[1]) {
-			/* attach tuner for 2nd FE */
-			fe = dvb_attach(dvb_pll_attach, adap->fe[1],
+			return 0;
+		} else {
+			/* attach tuner */
+			fe = dvb_attach(dvb_pll_attach, adap->fe[0],
 					(0xc0 >> 1), &d->i2c_adap,
 					DVB_PLL_SAMSUNG_DTOS403IH102A);
+
+			if (fe && adap->fe[1]) {
+				/* attach tuner for 2nd FE */
+				fe = dvb_attach(dvb_pll_attach, adap->fe[1],
+						(0xc0 >> 1), &d->i2c_adap,
+						DVB_PLL_SAMSUNG_DTOS403IH102A);
+			}
 		}
 
 		break;
 	case ANYSEE_HW_508TC: /* 18 */
 	case ANYSEE_HW_508PTC: /* 21 */
+	{
 		/* E7 TC */
 		/* E7 PTC */
+		struct tda18212_config tda18212_config = anysee_tda18212_config;
 
-		/* attach tuner */
-		fe = dvb_attach(tda18212_attach, adap->fe[0], &d->i2c_adap,
-				&anysee_tda18212_config);
-
-		if (fe) {
-			/* attach tuner for 2nd FE */
-			fe = dvb_attach(tda18212_attach, adap->fe[1],
-					&d->i2c_adap, &anysee_tda18212_config);
+		tda18212_config.fe = adap->fe[0];
+		ret = anysee_add_i2c_dev(d, "tda18212", 0x60, &tda18212_config);
+		if (ret)
+			goto err;
+
+		/* copy tuner ops for 2nd FE as tuner is shared */
+		if (adap->fe[1]) {
+			adap->fe[1]->tuner_priv = adap->fe[0]->tuner_priv;
+			memcpy(&adap->fe[1]->ops.tuner_ops,
+					&adap->fe[0]->ops.tuner_ops,
+					sizeof(struct dvb_tuner_ops));
 		}
 
-		break;
+		return 0;
+	}
 	case ANYSEE_HW_508S2: /* 19 */
 	case ANYSEE_HW_508PS2: /* 22 */
 		/* E7 S2 */
@@ -997,13 +1100,18 @@ static int anysee_tuner_attach(struct dvb_usb_adapter *adap)
 		break;
 
 	case ANYSEE_HW_508T2C: /* 20 */
+	{
 		/* E7 T2C */
+		struct tda18212_config tda18212_config =
+				anysee_tda18212_config2;
 
-		/* attach tuner */
-		fe = dvb_attach(tda18212_attach, adap->fe[0], &d->i2c_adap,
-				&anysee_tda18212_config2);
+		tda18212_config.fe = adap->fe[0];
+		ret = anysee_add_i2c_dev(d, "tda18212", 0x60, &tda18212_config);
+		if (ret)
+			goto err;
 
-		break;
+		return 0;
+	}
 	default:
 		fe = NULL;
 	}
@@ -1012,7 +1120,7 @@ static int anysee_tuner_attach(struct dvb_usb_adapter *adap)
 		ret = 0;
 	else
 		ret = -ENODEV;
-
+err:
 	return ret;
 }
 
@@ -1270,6 +1378,11 @@ static int anysee_init(struct dvb_usb_device *d)
 
 static void anysee_exit(struct dvb_usb_device *d)
 {
+	struct anysee_state *state = d_to_priv(d);
+
+	if (state->i2c_client[0])
+		anysee_del_i2c_dev(d);
+
 	return anysee_ci_release(d);
 }
 
diff --git a/drivers/media/usb/dvb-usb-v2/anysee.h b/drivers/media/usb/dvb-usb-v2/anysee.h
index 8f426d9fc6e1..3ca2bca4ebaf 100644
--- a/drivers/media/usb/dvb-usb-v2/anysee.h
+++ b/drivers/media/usb/dvb-usb-v2/anysee.h
@@ -55,8 +55,11 @@ struct anysee_state {
 	u8 buf[64];
 	u8 seq;
 	u8 hw; /* PCB ID */
+	#define ANYSEE_I2C_CLIENT_MAX 1
+	struct i2c_client *i2c_client[ANYSEE_I2C_CLIENT_MAX];
 	u8 fe_id:1; /* frondend ID */
 	u8 has_ci:1;
+	u8 has_tda18212:1;
 	u8 ci_attached:1;
 	struct dvb_ca_en50221 ci;
 	unsigned long ci_cam_ready; /* jiffies */
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb.h b/drivers/media/usb/dvb-usb-v2/dvb_usb.h
index 124b4baa7e97..14e111e13e54 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb.h
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb.h
@@ -214,6 +214,7 @@ struct dvb_usb_adapter_properties {
  * @read_config: called to resolve device configuration
  * @read_mac_address: called to resolve adapter mac-address
  * @frontend_attach: called to attach the possible frontends
+ * @frontend_detach: called to detach the possible frontends
  * @tuner_attach: called to attach the possible tuners
  * @frontend_ctrl: called to power on/off active frontend
  * @streaming_ctrl: called to start/stop the usb streaming of adapter
@@ -254,7 +255,9 @@ struct dvb_usb_device_properties {
 	int (*read_config) (struct dvb_usb_device *d);
 	int (*read_mac_address) (struct dvb_usb_adapter *, u8 []);
 	int (*frontend_attach) (struct dvb_usb_adapter *);
+	int (*frontend_detach)(struct dvb_usb_adapter *);
 	int (*tuner_attach) (struct dvb_usb_adapter *);
+	int (*tuner_detach)(struct dvb_usb_adapter *);
 	int (*frontend_ctrl) (struct dvb_frontend *, int);
 	int (*streaming_ctrl) (struct dvb_frontend *, int);
 	int (*init) (struct dvb_usb_device *);
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
index 2e90310be2af..1950f37df835 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
@@ -21,7 +21,7 @@
 
 #include "dvb_usb_common.h"
 
-int dvb_usbv2_disable_rc_polling;
+static int dvb_usbv2_disable_rc_polling;
 module_param_named(disable_rc_polling, dvb_usbv2_disable_rc_polling, int, 0644);
 MODULE_PARM_DESC(disable_rc_polling,
 		"disable remote control polling (default: 0)");
@@ -664,9 +664,10 @@ err:
 
 static int dvb_usbv2_adapter_frontend_exit(struct dvb_usb_adapter *adap)
 {
-	int i;
-	dev_dbg(&adap_to_d(adap)->udev->dev, "%s: adap=%d\n", __func__,
-			adap->id);
+	int ret, i;
+	struct dvb_usb_device *d = adap_to_d(adap);
+
+	dev_dbg(&d->udev->dev, "%s: adap=%d\n", __func__, adap->id);
 
 	for (i = MAX_NO_OF_FE_PER_ADAP - 1; i >= 0; i--) {
 		if (adap->fe[i]) {
@@ -675,6 +676,23 @@ static int dvb_usbv2_adapter_frontend_exit(struct dvb_usb_adapter *adap)
 		}
 	}
 
+	if (d->props->tuner_detach) {
+		ret = d->props->tuner_detach(adap);
+		if (ret < 0) {
+			dev_dbg(&d->udev->dev, "%s: tuner_detach() failed=%d\n",
+					__func__, ret);
+		}
+	}
+
+	if (d->props->frontend_detach) {
+		ret = d->props->frontend_detach(adap);
+		if (ret < 0) {
+			dev_dbg(&d->udev->dev,
+					"%s: frontend_detach() failed=%d\n",
+					__func__, ret);
+		}
+	}
+
 	return 0;
 }
 
@@ -762,9 +780,9 @@ static int dvb_usbv2_adapter_exit(struct dvb_usb_device *d)
 
 	for (i = MAX_NO_OF_ADAPTER_PER_DEVICE - 1; i >= 0; i--) {
 		if (d->adapter[i].props) {
-			dvb_usbv2_adapter_frontend_exit(&d->adapter[i]);
 			dvb_usbv2_adapter_dvb_exit(&d->adapter[i]);
 			dvb_usbv2_adapter_stream_exit(&d->adapter[i]);
+			dvb_usbv2_adapter_frontend_exit(&d->adapter[i]);
 		}
 	}
 
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb_urb.c b/drivers/media/usb/dvb-usb-v2/dvb_usb_urb.c
index 33ff97e708e3..22bdce15ecf3 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb_urb.c
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_urb.c
@@ -26,7 +26,7 @@ static int dvb_usb_v2_generic_io(struct dvb_usb_device *d,
 {
 	int ret, actual_length;
 
-	if (!d || !wbuf || !wlen || !d->props->generic_bulk_ctrl_endpoint ||
+	if (!wbuf || !wlen || !d->props->generic_bulk_ctrl_endpoint ||
 			!d->props->generic_bulk_ctrl_endpoint_response) {
 		dev_dbg(&d->udev->dev, "%s: failed=%d\n", __func__, -EINVAL);
 		return -EINVAL;
diff --git a/drivers/media/usb/dvb-usb-v2/dvbsky.c b/drivers/media/usb/dvb-usb-v2/dvbsky.c
new file mode 100644
index 000000000000..34688c89df11
--- /dev/null
+++ b/drivers/media/usb/dvb-usb-v2/dvbsky.c
@@ -0,0 +1,460 @@
+/*
+ * Driver for DVBSky USB2.0 receiver
+ *
+ * Copyright (C) 2013 Max nibble <nibble.max@gmail.com>
+ *
+ *    This program is free software; you can redistribute it and/or modify
+ *    it under the terms of the GNU General Public License as published by
+ *    the Free Software Foundation; either version 2 of the License, or
+ *    (at your option) any later version.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU General Public License for more details.
+ *
+ *    You should have received a copy of the GNU General Public License
+ *    along with this program; if not, write to the Free Software
+ *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include "dvb_usb.h"
+#include "m88ds3103.h"
+#include "m88ts2022.h"
+
+#define DVBSKY_MSG_DELAY	0/*2000*/
+#define DVBSKY_BUF_LEN	64
+
+DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
+
+struct dvbsky_state {
+	struct mutex stream_mutex;
+	u8 ibuf[DVBSKY_BUF_LEN];
+	u8 obuf[DVBSKY_BUF_LEN];
+	u8 last_lock;
+	struct i2c_client *i2c_client_tuner;
+
+	/* fe hook functions*/
+	int (*fe_set_voltage)(struct dvb_frontend *fe,
+		fe_sec_voltage_t voltage);
+	int (*fe_read_status)(struct dvb_frontend *fe,
+		fe_status_t *status);
+};
+
+static int dvbsky_usb_generic_rw(struct dvb_usb_device *d,
+		u8 *wbuf, u16 wlen, u8 *rbuf, u16 rlen)
+{
+	int ret;
+	struct dvbsky_state *state = d_to_priv(d);
+
+	mutex_lock(&d->usb_mutex);
+	if (wlen != 0)
+		memcpy(state->obuf, wbuf, wlen);
+
+	ret = dvb_usbv2_generic_rw_locked(d, state->obuf, wlen,
+			state->ibuf, rlen);
+
+	if (!ret && (rlen != 0))
+		memcpy(rbuf, state->ibuf, rlen);
+
+	mutex_unlock(&d->usb_mutex);
+	return ret;
+}
+
+static int dvbsky_stream_ctrl(struct dvb_usb_device *d, u8 onoff)
+{
+	struct dvbsky_state *state = d_to_priv(d);
+	int ret;
+	u8 obuf_pre[3] = { 0x37, 0, 0 };
+	u8 obuf_post[3] = { 0x36, 3, 0 };
+
+	mutex_lock(&state->stream_mutex);
+	ret = dvbsky_usb_generic_rw(d, obuf_pre, 3, NULL, 0);
+	if (!ret && onoff) {
+		msleep(20);
+		ret = dvbsky_usb_generic_rw(d, obuf_post, 3, NULL, 0);
+	}
+	mutex_unlock(&state->stream_mutex);
+	return ret;
+}
+
+static int dvbsky_streaming_ctrl(struct dvb_frontend *fe, int onoff)
+{
+	struct dvb_usb_device *d = fe_to_d(fe);
+
+	return dvbsky_stream_ctrl(d, (onoff == 0) ? 0 : 1);
+}
+
+/* GPIO */
+static int dvbsky_gpio_ctrl(struct dvb_usb_device *d, u8 gport, u8 value)
+{
+	int ret;
+	u8 obuf[3], ibuf[2];
+
+	obuf[0] = 0x0e;
+	obuf[1] = gport;
+	obuf[2] = value;
+	ret = dvbsky_usb_generic_rw(d, obuf, 3, ibuf, 1);
+	if (ret)
+		dev_err(&d->udev->dev, "%s: %s() failed=%d\n",
+			KBUILD_MODNAME, __func__, ret);
+	return ret;
+}
+
+/* I2C */
+static int dvbsky_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
+	int num)
+{
+	struct dvb_usb_device *d = i2c_get_adapdata(adap);
+	int ret = 0;
+	u8 ibuf[64], obuf[64];
+
+	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
+		return -EAGAIN;
+
+	if (num > 2) {
+		dev_err(&d->udev->dev,
+		"dvbsky_usb: too many i2c messages[%d] than 2.", num);
+		ret = -EOPNOTSUPP;
+		goto i2c_error;
+	}
+
+	if (num == 1) {
+		if (msg[0].len > 60) {
+			dev_err(&d->udev->dev,
+			"dvbsky_usb: too many i2c bytes[%d] than 60.",
+			msg[0].len);
+			ret = -EOPNOTSUPP;
+			goto i2c_error;
+		}
+		if (msg[0].flags & I2C_M_RD) {
+			/* single read */
+			obuf[0] = 0x09;
+			obuf[1] = 0;
+			obuf[2] = msg[0].len;
+			obuf[3] = msg[0].addr;
+			ret = dvbsky_usb_generic_rw(d, obuf, 4,
+					ibuf, msg[0].len + 1);
+			if (ret)
+				dev_err(&d->udev->dev, "%s: %s() failed=%d\n",
+					KBUILD_MODNAME, __func__, ret);
+			if (!ret)
+				memcpy(msg[0].buf, &ibuf[1], msg[0].len);
+		} else {
+			/* write */
+			obuf[0] = 0x08;
+			obuf[1] = msg[0].addr;
+			obuf[2] = msg[0].len;
+			memcpy(&obuf[3], msg[0].buf, msg[0].len);
+			ret = dvbsky_usb_generic_rw(d, obuf,
+					msg[0].len + 3, ibuf, 1);
+			if (ret)
+				dev_err(&d->udev->dev, "%s: %s() failed=%d\n",
+					KBUILD_MODNAME, __func__, ret);
+		}
+	} else {
+		if ((msg[0].len > 60) || (msg[1].len > 60)) {
+			dev_err(&d->udev->dev,
+			"dvbsky_usb: too many i2c bytes[w-%d][r-%d] than 60.",
+			msg[0].len, msg[1].len);
+			ret = -EOPNOTSUPP;
+			goto i2c_error;
+		}
+		/* write then read */
+		obuf[0] = 0x09;
+		obuf[1] = msg[0].len;
+		obuf[2] = msg[1].len;
+		obuf[3] = msg[0].addr;
+		memcpy(&obuf[4], msg[0].buf, msg[0].len);
+		ret = dvbsky_usb_generic_rw(d, obuf,
+			msg[0].len + 4, ibuf, msg[1].len + 1);
+		if (ret)
+			dev_err(&d->udev->dev, "%s: %s() failed=%d\n",
+				KBUILD_MODNAME, __func__, ret);
+
+		if (!ret)
+			memcpy(msg[1].buf, &ibuf[1], msg[1].len);
+	}
+i2c_error:
+	mutex_unlock(&d->i2c_mutex);
+	return (ret) ? ret : num;
+}
+
+static u32 dvbsky_i2c_func(struct i2c_adapter *adapter)
+{
+	return I2C_FUNC_I2C;
+}
+
+static struct i2c_algorithm dvbsky_i2c_algo = {
+	.master_xfer   = dvbsky_i2c_xfer,
+	.functionality = dvbsky_i2c_func,
+};
+
+#if IS_ENABLED(CONFIG_RC_CORE)
+static int dvbsky_rc_query(struct dvb_usb_device *d)
+{
+	u32 code = 0xffff, scancode;
+	u8 rc5_command, rc5_system;
+	u8 obuf[2], ibuf[2], toggle;
+	int ret;
+
+	obuf[0] = 0x10;
+	ret = dvbsky_usb_generic_rw(d, obuf, 1, ibuf, 2);
+	if (ret)
+		dev_err(&d->udev->dev, "%s: %s() failed=%d\n",
+			KBUILD_MODNAME, __func__, ret);
+	if (ret == 0)
+		code = (ibuf[0] << 8) | ibuf[1];
+	if (code != 0xffff) {
+		dev_dbg(&d->udev->dev, "rc code: %x\n", code);
+		rc5_command = code & 0x3F;
+		rc5_system = (code & 0x7C0) >> 6;
+		toggle = (code & 0x800) ? 1 : 0;
+		scancode = rc5_system << 8 | rc5_command;
+		rc_keydown(d->rc_dev, RC_TYPE_RC5, scancode, toggle);
+	}
+	return 0;
+}
+
+static int dvbsky_get_rc_config(struct dvb_usb_device *d, struct dvb_usb_rc *rc)
+{
+	rc->allowed_protos = RC_BIT_RC5;
+	rc->query          = dvbsky_rc_query;
+	rc->interval       = 300;
+	return 0;
+}
+#else
+	#define dvbsky_get_rc_config NULL
+#endif
+
+static int dvbsky_usb_set_voltage(struct dvb_frontend *fe,
+	fe_sec_voltage_t voltage)
+{
+	struct dvb_usb_device *d = fe_to_d(fe);
+	struct dvbsky_state *state = d_to_priv(d);
+	u8 value;
+
+	if (voltage == SEC_VOLTAGE_OFF)
+		value = 0;
+	else
+		value = 1;
+	dvbsky_gpio_ctrl(d, 0x80, value);
+
+	return state->fe_set_voltage(fe, voltage);
+}
+
+static int dvbsky_read_mac_addr(struct dvb_usb_adapter *adap, u8 mac[6])
+{
+	struct dvb_usb_device *d = adap_to_d(adap);
+	u8 obuf[] = { 0x1e, 0x00 };
+	u8 ibuf[6] = { 0 };
+	struct i2c_msg msg[] = {
+		{
+			.addr = 0x51,
+			.flags = 0,
+			.buf = obuf,
+			.len = 2,
+		}, {
+			.addr = 0x51,
+			.flags = I2C_M_RD,
+			.buf = ibuf,
+			.len = 6,
+		}
+	};
+
+	if (i2c_transfer(&d->i2c_adap, msg, 2) == 2)
+		memcpy(mac, ibuf, 6);
+
+	dev_info(&d->udev->dev, "dvbsky_usb MAC address=%pM\n", mac);
+
+	return 0;
+}
+
+static int dvbsky_usb_read_status(struct dvb_frontend *fe, fe_status_t *status)
+{
+	struct dvb_usb_device *d = fe_to_d(fe);
+	struct dvbsky_state *state = d_to_priv(d);
+	int ret;
+
+	ret = state->fe_read_status(fe, status);
+
+	/* it need resync slave fifo when signal change from unlock to lock.*/
+	if ((*status & FE_HAS_LOCK) && (!state->last_lock))
+		dvbsky_stream_ctrl(d, 1);
+
+	state->last_lock = (*status & FE_HAS_LOCK) ? 1 : 0;
+	return ret;
+}
+
+static const struct m88ds3103_config dvbsky_s960_m88ds3103_config = {
+	.i2c_addr = 0x68,
+	.clock = 27000000,
+	.i2c_wr_max = 33,
+	.clock_out = 0,
+	.ts_mode = M88DS3103_TS_CI,
+	.ts_clk = 16000,
+	.ts_clk_pol = 0,
+	.agc = 0x99,
+	.lnb_hv_pol = 1,
+	.lnb_en_pol = 1,
+};
+
+static int dvbsky_s960_attach(struct dvb_usb_adapter *adap)
+{
+	struct dvbsky_state *state = adap_to_priv(adap);
+	struct dvb_usb_device *d = adap_to_d(adap);
+	int ret = 0;
+	/* demod I2C adapter */
+	struct i2c_adapter *i2c_adapter;
+	struct i2c_client *client;
+	struct i2c_board_info info;
+	struct m88ts2022_config m88ts2022_config = {
+			.clock = 27000000,
+		};
+	memset(&info, 0, sizeof(struct i2c_board_info));
+
+	/* attach demod */
+	adap->fe[0] = dvb_attach(m88ds3103_attach,
+			&dvbsky_s960_m88ds3103_config,
+			&d->i2c_adap,
+			&i2c_adapter);
+	if (!adap->fe[0]) {
+		dev_err(&d->udev->dev, "dvbsky_s960_attach fail.\n");
+		ret = -ENODEV;
+		goto fail_attach;
+	}
+
+	/* attach tuner */
+	m88ts2022_config.fe = adap->fe[0];
+	strlcpy(info.type, "m88ts2022", I2C_NAME_SIZE);
+	info.addr = 0x60;
+	info.platform_data = &m88ts2022_config;
+	request_module("m88ts2022");
+	client = i2c_new_device(i2c_adapter, &info);
+	if (client == NULL || client->dev.driver == NULL) {
+		dvb_frontend_detach(adap->fe[0]);
+		ret = -ENODEV;
+		goto fail_attach;
+	}
+
+	if (!try_module_get(client->dev.driver->owner)) {
+		i2c_unregister_device(client);
+		dvb_frontend_detach(adap->fe[0]);
+		ret = -ENODEV;
+		goto fail_attach;
+	}
+
+	/* delegate signal strength measurement to tuner */
+	adap->fe[0]->ops.read_signal_strength =
+			adap->fe[0]->ops.tuner_ops.get_rf_strength;
+
+	/* hook fe: need to resync the slave fifo when signal locks. */
+	state->fe_read_status = adap->fe[0]->ops.read_status;
+	adap->fe[0]->ops.read_status = dvbsky_usb_read_status;
+
+	/* hook fe: LNB off/on is control by Cypress usb chip. */
+	state->fe_set_voltage = adap->fe[0]->ops.set_voltage;
+	adap->fe[0]->ops.set_voltage = dvbsky_usb_set_voltage;
+
+	state->i2c_client_tuner = client;
+
+fail_attach:
+	return ret;
+}
+
+static int dvbsky_identify_state(struct dvb_usb_device *d, const char **name)
+{
+	dvbsky_gpio_ctrl(d, 0x04, 1);
+	msleep(20);
+	dvbsky_gpio_ctrl(d, 0x83, 0);
+	dvbsky_gpio_ctrl(d, 0xc0, 1);
+	msleep(100);
+	dvbsky_gpio_ctrl(d, 0x83, 1);
+	dvbsky_gpio_ctrl(d, 0xc0, 0);
+	msleep(50);
+
+	return WARM;
+}
+
+static int dvbsky_init(struct dvb_usb_device *d)
+{
+	struct dvbsky_state *state = d_to_priv(d);
+
+	/* use default interface */
+	/*
+	ret = usb_set_interface(d->udev, 0, 0);
+	if (ret)
+		return ret;
+	*/
+	mutex_init(&state->stream_mutex);
+
+	state->last_lock = 0;
+
+	return 0;
+}
+
+static void dvbsky_exit(struct dvb_usb_device *d)
+{
+	struct dvbsky_state *state = d_to_priv(d);
+	struct i2c_client *client;
+
+	client = state->i2c_client_tuner;
+	/* remove I2C tuner */
+	if (client) {
+		module_put(client->dev.driver->owner);
+		i2c_unregister_device(client);
+	}
+}
+
+/* DVB USB Driver stuff */
+static struct dvb_usb_device_properties dvbsky_s960_props = {
+	.driver_name = KBUILD_MODNAME,
+	.owner = THIS_MODULE,
+	.adapter_nr = adapter_nr,
+	.size_of_priv = sizeof(struct dvbsky_state),
+
+	.generic_bulk_ctrl_endpoint = 0x01,
+	.generic_bulk_ctrl_endpoint_response = 0x81,
+	.generic_bulk_ctrl_delay = DVBSKY_MSG_DELAY,
+
+	.i2c_algo         = &dvbsky_i2c_algo,
+	.frontend_attach  = dvbsky_s960_attach,
+	.init             = dvbsky_init,
+	.get_rc_config    = dvbsky_get_rc_config,
+	.streaming_ctrl   = dvbsky_streaming_ctrl,
+	.identify_state	  = dvbsky_identify_state,
+	.exit             = dvbsky_exit,
+	.read_mac_address = dvbsky_read_mac_addr,
+
+	.num_adapters = 1,
+	.adapter = {
+		{
+			.stream = DVB_USB_STREAM_BULK(0x82, 8, 4096),
+		}
+	}
+};
+
+static const struct usb_device_id dvbsky_id_table[] = {
+	{ DVB_USB_DEVICE(0x0572, 0x6831,
+		&dvbsky_s960_props, "DVBSky S960/S860", RC_MAP_DVBSKY) },
+	{ }
+};
+MODULE_DEVICE_TABLE(usb, dvbsky_id_table);
+
+static struct usb_driver dvbsky_usb_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = dvbsky_id_table,
+	.probe = dvb_usbv2_probe,
+	.disconnect = dvb_usbv2_disconnect,
+	.suspend = dvb_usbv2_suspend,
+	.resume = dvb_usbv2_resume,
+	.reset_resume = dvb_usbv2_reset_resume,
+	.no_dynamic_id = 1,
+	.soft_unbind = 1,
+};
+
+module_usb_driver(dvbsky_usb_driver);
+
+MODULE_AUTHOR("Max nibble <nibble.max@gmail.com>");
+MODULE_DESCRIPTION("Driver for DVBSky USB");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/dvb-usb-v2/lmedm04.c b/drivers/media/usb/dvb-usb-v2/lmedm04.c
index e332af731187..9f2c5459b73a 100644
--- a/drivers/media/usb/dvb-usb-v2/lmedm04.c
+++ b/drivers/media/usb/dvb-usb-v2/lmedm04.c
@@ -1252,7 +1252,7 @@ static int lme2510_get_stream_config(struct dvb_frontend *fe, u8 *ts_type,
 
 	/* Turn PID filter on the fly by module option */
 	if (pid_filter == 2) {
-		adap->pid_filtering  = 1;
+		adap->pid_filtering  = true;
 		adap->max_feed_count = 15;
 	}
 
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf.c b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
index b8a707e57b99..c3447eaf1104 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
@@ -31,11 +31,11 @@ module_param_named(debug, dvb_usb_mxl111sf_debug, int, 0644);
 MODULE_PARM_DESC(debug, "set debugging level "
 		 "(1=info, 2=xfer, 4=i2c, 8=reg, 16=adv (or-able)).");
 
-int dvb_usb_mxl111sf_isoc;
+static int dvb_usb_mxl111sf_isoc;
 module_param_named(isoc, dvb_usb_mxl111sf_isoc, int, 0644);
 MODULE_PARM_DESC(isoc, "enable usb isoc xfer (0=bulk, 1=isoc).");
 
-int dvb_usb_mxl111sf_spi;
+static int dvb_usb_mxl111sf_spi;
 module_param_named(spi, dvb_usb_mxl111sf_spi, int, 0644);
 MODULE_PARM_DESC(spi, "use spi rather than tp for data xfer (0=tp, 1=spi).");
 
@@ -43,7 +43,7 @@ MODULE_PARM_DESC(spi, "use spi rather than tp for data xfer (0=tp, 1=spi).");
 #define ANT_PATH_EXTERNAL 1
 #define ANT_PATH_INTERNAL 2
 
-int dvb_usb_mxl111sf_rfswitch =
+static int dvb_usb_mxl111sf_rfswitch =
 #if 0
 		ANT_PATH_AUTO;
 #else
@@ -887,7 +887,7 @@ static u32 mxl111sf_i2c_func(struct i2c_adapter *adapter)
 	return I2C_FUNC_I2C;
 }
 
-struct i2c_algorithm mxl111sf_i2c_algo = {
+static struct i2c_algorithm mxl111sf_i2c_algo = {
 	.master_xfer   = mxl111sf_i2c_xfer,
 	.functionality = mxl111sf_i2c_func,
 #ifdef NEED_ALGO_CONTROL
diff --git a/drivers/media/usb/dvb-usb/Kconfig b/drivers/media/usb/dvb-usb/Kconfig
index 10aef2188fbe..41d3eb922a00 100644
--- a/drivers/media/usb/dvb-usb/Kconfig
+++ b/drivers/media/usb/dvb-usb/Kconfig
@@ -130,7 +130,7 @@ config DVB_USB_CXUSB
 
 	  Medion MD95700 hybrid USB2.0 device.
 	  DViCO FusionHDTV (Bluebird) USB2.0 devices
-	  TechnoTrend TVStick CT2-4400
+	  TechnoTrend TVStick CT2-4400 and CT2-4650 CI devices
 
 config DVB_USB_M920X
 	tristate "Uli m920x DVB-T USB2.0 support"
diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c
index af176b6ce738..3f4361e48a32 100644
--- a/drivers/media/usb/dvb-usb/af9005.c
+++ b/drivers/media/usb/dvb-usb/af9005.c
@@ -30,7 +30,7 @@ MODULE_PARM_DESC(debug,
 		 "set debugging level (1=info,xfer=2,rc=4,reg=8,i2c=16,fw=32 (or-able))."
 		 DVB_USB_DEBUG_STATUS);
 /* enable obnoxious led */
-bool dvb_usb_af9005_led = 1;
+bool dvb_usb_af9005_led = true;
 module_param_named(led, dvb_usb_af9005_led, bool, 0644);
 MODULE_PARM_DESC(led, "enable led (default: 1).");
 
diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c
index 16bc579d1404..356abb369c20 100644
--- a/drivers/media/usb/dvb-usb/cxusb.c
+++ b/drivers/media/usb/dvb-usb/cxusb.c
@@ -44,6 +44,7 @@
 #include "atbm8830.h"
 #include "si2168.h"
 #include "si2157.h"
+#include "sp2.h"
 
 /* Max transfer size done by I2C transfer functions */
 #define MAX_XFER_SIZE  80
@@ -175,7 +176,7 @@ static int cxusb_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 
 	for (i = 0; i < num; i++) {
 
-		if (d->udev->descriptor.idVendor == USB_VID_MEDION)
+		if (le16_to_cpu(d->udev->descriptor.idVendor) == USB_VID_MEDION)
 			switch (msg[i].addr) {
 			case 0x63:
 				cxusb_gpio_tuner(d, 0);
@@ -672,6 +673,70 @@ static struct rc_map_table rc_map_d680_dmb_table[] = {
 	{ 0x0025, KEY_POWER },
 };
 
+static int cxusb_tt_ct2_4400_read_mac_address(struct dvb_usb_device *d, u8 mac[6])
+{
+	u8 wbuf[2];
+	u8 rbuf[6];
+	int ret;
+	struct i2c_msg msg[] = {
+		{
+			.addr = 0x51,
+			.flags = 0,
+			.buf = wbuf,
+			.len = 2,
+		}, {
+			.addr = 0x51,
+			.flags = I2C_M_RD,
+			.buf = rbuf,
+			.len = 6,
+		}
+	};
+
+	wbuf[0] = 0x1e;
+	wbuf[1] = 0x00;
+	ret = cxusb_i2c_xfer(&d->i2c_adap, msg, 2);
+
+	if (ret == 2) {
+		memcpy(mac, rbuf, 6);
+		return 0;
+	} else {
+		if (ret < 0)
+			return ret;
+		return -EIO;
+	}
+}
+
+static int cxusb_tt_ct2_4650_ci_ctrl(void *priv, u8 read, int addr,
+					u8 data, int *mem)
+{
+	struct dvb_usb_device *d = priv;
+	u8 wbuf[3];
+	u8 rbuf[2];
+	int ret;
+
+	wbuf[0] = (addr >> 8) & 0xff;
+	wbuf[1] = addr & 0xff;
+
+	if (read) {
+		ret = cxusb_ctrl_msg(d, CMD_SP2_CI_READ, wbuf, 2, rbuf, 2);
+	} else {
+		wbuf[2] = data;
+		ret = cxusb_ctrl_msg(d, CMD_SP2_CI_WRITE, wbuf, 3, rbuf, 1);
+	}
+
+	if (ret)
+		goto err;
+
+	if (read)
+		*mem = rbuf[1];
+
+	return 0;
+err:
+	deb_info("%s: ci usb write returned %d\n", __func__, ret);
+	return ret;
+
+}
+
 static int cxusb_dee1601_demod_init(struct dvb_frontend* fe)
 {
 	static u8 clock_config []  = { CLOCK_CTL,  0x38, 0x28 };
@@ -1350,9 +1415,12 @@ static int cxusb_tt_ct2_4400_attach(struct dvb_usb_adapter *adap)
 	struct i2c_adapter *adapter;
 	struct i2c_client *client_demod;
 	struct i2c_client *client_tuner;
+	struct i2c_client *client_ci;
 	struct i2c_board_info info;
 	struct si2168_config si2168_config;
 	struct si2157_config si2157_config;
+	struct sp2_config sp2_config;
+	u8 o[2], i;
 
 	/* reset the tuner */
 	if (cxusb_tt_ct2_4400_gpio_tuner(d, 0) < 0) {
@@ -1369,6 +1437,7 @@ static int cxusb_tt_ct2_4400_attach(struct dvb_usb_adapter *adap)
 	/* attach frontend */
 	si2168_config.i2c_adapter = &adapter;
 	si2168_config.fe = &adap->fe_adap[0].fe;
+	si2168_config.ts_mode = SI2168_TS_PARALLEL;
 	memset(&info, 0, sizeof(struct i2c_board_info));
 	strlcpy(info.type, "si2168", I2C_NAME_SIZE);
 	info.addr = 0x64;
@@ -1408,6 +1477,48 @@ static int cxusb_tt_ct2_4400_attach(struct dvb_usb_adapter *adap)
 
 	st->i2c_client_tuner = client_tuner;
 
+	/* initialize CI */
+	if (d->udev->descriptor.idProduct ==
+		USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI) {
+
+		memcpy(o, "\xc0\x01", 2);
+		cxusb_ctrl_msg(d, CMD_GPIO_WRITE, o, 2, &i, 1);
+		msleep(100);
+
+		memcpy(o, "\xc0\x00", 2);
+		cxusb_ctrl_msg(d, CMD_GPIO_WRITE, o, 2, &i, 1);
+		msleep(100);
+
+		memset(&sp2_config, 0, sizeof(sp2_config));
+		sp2_config.dvb_adap = &adap->dvb_adap;
+		sp2_config.priv = d;
+		sp2_config.ci_control = cxusb_tt_ct2_4650_ci_ctrl;
+		memset(&info, 0, sizeof(struct i2c_board_info));
+		strlcpy(info.type, "sp2", I2C_NAME_SIZE);
+		info.addr = 0x40;
+		info.platform_data = &sp2_config;
+		request_module(info.type);
+		client_ci = i2c_new_device(&d->i2c_adap, &info);
+		if (client_ci == NULL || client_ci->dev.driver == NULL) {
+			module_put(client_tuner->dev.driver->owner);
+			i2c_unregister_device(client_tuner);
+			module_put(client_demod->dev.driver->owner);
+			i2c_unregister_device(client_demod);
+			return -ENODEV;
+		}
+		if (!try_module_get(client_ci->dev.driver->owner)) {
+			i2c_unregister_device(client_ci);
+			module_put(client_tuner->dev.driver->owner);
+			i2c_unregister_device(client_tuner);
+			module_put(client_demod->dev.driver->owner);
+			i2c_unregister_device(client_demod);
+			return -ENODEV;
+		}
+
+		st->i2c_client_ci = client_ci;
+
+	}
+
 	return 0;
 }
 
@@ -1537,6 +1648,13 @@ static void cxusb_disconnect(struct usb_interface *intf)
 	struct cxusb_state *st = d->priv;
 	struct i2c_client *client;
 
+	/* remove I2C client for CI */
+	client = st->i2c_client_ci;
+	if (client) {
+		module_put(client->dev.driver->owner);
+		i2c_unregister_device(client);
+	}
+
 	/* remove I2C client for tuner */
 	client = st->i2c_client_tuner;
 	if (client) {
@@ -1576,6 +1694,7 @@ static struct usb_device_id cxusb_table [] = {
 	{ USB_DEVICE(USB_VID_CONEXANT, USB_PID_CONEXANT_D680_DMB) },
 	{ USB_DEVICE(USB_VID_CONEXANT, USB_PID_MYGICA_D689) },
 	{ USB_DEVICE(USB_VID_TECHNOTREND, USB_PID_TECHNOTREND_TVSTICK_CT2_4400) },
+	{ USB_DEVICE(USB_VID_TECHNOTREND, USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI) },
 	{}		/* Terminating entry */
 };
 MODULE_DEVICE_TABLE (usb, cxusb_table);
@@ -2230,6 +2349,8 @@ static struct dvb_usb_device_properties cxusb_tt_ct2_4400_properties = {
 	.size_of_priv     = sizeof(struct cxusb_state),
 
 	.num_adapters = 1,
+	.read_mac_address = cxusb_tt_ct2_4400_read_mac_address,
+
 	.adapter = {
 		{
 		.num_frontends = 1,
@@ -2265,13 +2386,18 @@ static struct dvb_usb_device_properties cxusb_tt_ct2_4400_properties = {
 		.rc_interval    = 150,
 	},
 
-	.num_device_descs = 1,
+	.num_device_descs = 2,
 	.devices = {
 		{
 			"TechnoTrend TVStick CT2-4400",
 			{ NULL },
 			{ &cxusb_table[20], NULL },
 		},
+		{
+			"TechnoTrend TT-connect CT2-4650 CI",
+			{ NULL },
+			{ &cxusb_table[21], NULL },
+		},
 	}
 };
 
diff --git a/drivers/media/usb/dvb-usb/cxusb.h b/drivers/media/usb/dvb-usb/cxusb.h
index 527ff7905e15..29f3e2ea2476 100644
--- a/drivers/media/usb/dvb-usb/cxusb.h
+++ b/drivers/media/usb/dvb-usb/cxusb.h
@@ -28,10 +28,14 @@
 #define CMD_ANALOG        0x50
 #define CMD_DIGITAL       0x51
 
+#define CMD_SP2_CI_WRITE  0x70
+#define CMD_SP2_CI_READ   0x71
+
 struct cxusb_state {
 	u8 gpio_write_state[3];
 	struct i2c_client *i2c_client_demod;
 	struct i2c_client *i2c_client_tuner;
+	struct i2c_client *i2c_client_ci;
 };
 
 #endif
diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c
index ce47d3f1c850..e1757b8f5f5d 100644
--- a/drivers/media/usb/dvb-usb/dib0700_devices.c
+++ b/drivers/media/usb/dvb-usb/dib0700_devices.c
@@ -220,12 +220,21 @@ static struct dibx000_agc_config stk7700d_7000p_mt2266_agc_config[2] = {
 };
 
 static struct dibx000_bandwidth_config stk7700d_mt2266_pll_config = {
-	60000, 30000,
-	1, 8, 3, 1, 0,
-	0, 0, 1, 1, 2,
-	(3 << 14) | (1 << 12) | (524 << 0),
-	0,
-	20452225,
+	.internal = 60000,
+	.sampling = 30000,
+	.pll_prediv = 1,
+	.pll_ratio = 8,
+	.pll_range = 3,
+	.pll_reset = 1,
+	.pll_bypass = 0,
+	.enable_refdiv = 0,
+	.bypclk_div = 0,
+	.IO_CLK_en_core = 1,
+	.ADClkSrc = 1,
+	.modulo = 2,
+	.sad_cfg = (3 << 14) | (1 << 12) | (524 << 0),
+	.ifreq = 0,
+	.timf = 20452225,
 };
 
 static struct dib7000p_config stk7700d_dib7000p_mt2266_config[] = {
@@ -342,57 +351,57 @@ static int stk7700d_tuner_attach(struct dvb_usb_adapter *adap)
 
 /* STK7700-PH: Digital/Analog Hybrid Tuner, e.h. Cinergy HT USB HE */
 static struct dibx000_agc_config xc3028_agc_config = {
-	BAND_VHF | BAND_UHF,       /* band_caps */
-
+	.band_caps = BAND_VHF | BAND_UHF,
 	/* P_agc_use_sd_mod1=0, P_agc_use_sd_mod2=0, P_agc_freq_pwm_div=0,
 	 * P_agc_inv_pwm1=0, P_agc_inv_pwm2=0, P_agc_inh_dc_rv_est=0,
 	 * P_agc_time_est=3, P_agc_freeze=0, P_agc_nb_est=2, P_agc_write=0 */
-	(0 << 15) | (0 << 14) | (0 << 11) | (0 << 10) | (0 << 9) | (0 << 8) |
-	(3 << 5) | (0 << 4) | (2 << 1) | (0 << 0), /* setup */
-
-	712,	/* inv_gain */
-	21,	/* time_stabiliz */
-
-	0,	/* alpha_level */
-	118,	/* thlock */
-
-	0,	/* wbd_inv */
-	2867,	/* wbd_ref */
-	0,	/* wbd_sel */
-	2,	/* wbd_alpha */
-
-	0,	/* agc1_max */
-	0,	/* agc1_min */
-	39718,	/* agc2_max */
-	9930,	/* agc2_min */
-	0,	/* agc1_pt1 */
-	0,	/* agc1_pt2 */
-	0,	/* agc1_pt3 */
-	0,	/* agc1_slope1 */
-	0,	/* agc1_slope2 */
-	0,	/* agc2_pt1 */
-	128,	/* agc2_pt2 */
-	29,	/* agc2_slope1 */
-	29,	/* agc2_slope2 */
-
-	17,	/* alpha_mant */
-	27,	/* alpha_exp */
-	23,	/* beta_mant */
-	51,	/* beta_exp */
-
-	1,	/* perform_agc_softsplit */
+	.setup = (0 << 15) | (0 << 14) | (0 << 11) | (0 << 10) | (0 << 9) | (0 << 8) | (3 << 5) | (0 << 4) | (2 << 1) | (0 << 0),
+	.inv_gain = 712,
+	.time_stabiliz = 21,
+	.alpha_level = 0,
+	.thlock = 118,
+	.wbd_inv = 0,
+	.wbd_ref = 2867,
+	.wbd_sel = 0,
+	.wbd_alpha = 2,
+	.agc1_max = 0,
+	.agc1_min = 0,
+	.agc2_max = 39718,
+	.agc2_min = 9930,
+	.agc1_pt1 = 0,
+	.agc1_pt2 = 0,
+	.agc1_pt3 = 0,
+	.agc1_slope1 = 0,
+	.agc1_slope2 = 0,
+	.agc2_pt1 = 0,
+	.agc2_pt2 = 128,
+	.agc2_slope1 = 29,
+	.agc2_slope2 = 29,
+	.alpha_mant = 17,
+	.alpha_exp = 27,
+	.beta_mant = 23,
+	.beta_exp = 51,
+	.perform_agc_softsplit = 1,
 };
 
 /* PLL Configuration for COFDM BW_MHz = 8.00 with external clock = 30.00 */
 static struct dibx000_bandwidth_config xc3028_bw_config = {
-	60000, 30000, /* internal, sampling */
-	1, 8, 3, 1, 0, /* pll_cfg: prediv, ratio, range, reset, bypass */
-	0, 0, 1, 1, 0, /* misc: refdiv, bypclk_div, IO_CLK_en_core, ADClkSrc,
-			  modulo */
-	(3 << 14) | (1 << 12) | (524 << 0), /* sad_cfg: refsel, sel, freq_15k */
-	(1 << 25) | 5816102, /* ifreq = 5.200000 MHz */
-	20452225, /* timf */
-	30000000, /* xtal_hz */
+	.internal = 60000,
+	.sampling = 30000,
+	.pll_prediv = 1,
+	.pll_ratio = 8,
+	.pll_range = 3,
+	.pll_reset = 1,
+	.pll_bypass = 0,
+	.enable_refdiv = 0,
+	.bypclk_div = 0,
+	.IO_CLK_en_core = 1,
+	.ADClkSrc = 1,
+	.modulo = 0,
+	.sad_cfg = (3 << 14) | (1 << 12) | (524 << 0), /* sad_cfg: refsel, sel, freq_15k */
+	.ifreq = (1 << 25) | 5816102,  /* ifreq = 5.200000 MHz */
+	.timf = 20452225,
+	.xtal_hz = 30000000,
 };
 
 static struct dib7000p_config stk7700ph_dib7700_xc3028_config = {
@@ -614,59 +623,55 @@ static struct dibx000_agc_config stk7700p_7000m_mt2060_agc_config = {
 };
 
 static struct dibx000_agc_config stk7700p_7000p_mt2060_agc_config = {
-	BAND_UHF | BAND_VHF,
-
+	.band_caps = BAND_UHF | BAND_VHF,
 	/* P_agc_use_sd_mod1=0, P_agc_use_sd_mod2=0, P_agc_freq_pwm_div=5, P_agc_inv_pwm1=0, P_agc_inv_pwm2=0,
 	 * P_agc_inh_dc_rv_est=0, P_agc_time_est=3, P_agc_freeze=0, P_agc_nb_est=2, P_agc_write=0 */
-	(0 << 15) | (0 << 14) | (5 << 11) | (0 << 10) | (0 << 9) | (0 << 8)
-	| (3 << 5) | (0 << 4) | (2 << 1) | (0 << 0),
-
-	712,
-	41,
-
-	0,
-	118,
-
-	0,
-	4095,
-	0,
-	0,
-
-	42598,
-	16384,
-	42598,
-	    0,
-
-	  0,
-	137,
-	255,
-
-	  0,
-	255,
-
-	0,
-	0,
-
-	 0,
-	41,
-
-	15,
-	25,
-
-	28,
-	48,
-
-	0,
+	.setup = (0 << 15) | (0 << 14) | (5 << 11) | (0 << 10) | (0 << 9) | (0 << 8) | (3 << 5) | (0 << 4) | (2 << 1) | (0 << 0),
+	.inv_gain = 712,
+	.time_stabiliz = 41,
+	.alpha_level = 0,
+	.thlock = 118,
+	.wbd_inv = 0,
+	.wbd_ref = 4095,
+	.wbd_sel = 0,
+	.wbd_alpha = 0,
+	.agc1_max = 42598,
+	.agc1_min = 16384,
+	.agc2_max = 42598,
+	.agc2_min = 0,
+	.agc1_pt1 = 0,
+	.agc1_pt2 = 137,
+	.agc1_pt3 = 255,
+	.agc1_slope1 = 0,
+	.agc1_slope2 = 255,
+	.agc2_pt1 = 0,
+	.agc2_pt2 = 0,
+	.agc2_slope1 = 0,
+	.agc2_slope2 = 41,
+	.alpha_mant = 15,
+	.alpha_exp = 25,
+	.beta_mant = 28,
+	.beta_exp = 48,
+	.perform_agc_softsplit = 0,
 };
 
 static struct dibx000_bandwidth_config stk7700p_pll_config = {
-	60000, 30000,
-	1, 8, 3, 1, 0,
-	0, 0, 1, 1, 0,
-	(3 << 14) | (1 << 12) | (524 << 0),
-	60258167,
-	20452225,
-	30000000,
+	.internal = 60000,
+	.sampling = 30000,
+	.pll_prediv = 1,
+	.pll_ratio = 8,
+	.pll_range = 3,
+	.pll_reset = 1,
+	.pll_bypass = 0,
+	.enable_refdiv = 0,
+	.bypclk_div = 0,
+	.IO_CLK_en_core = 1,
+	.ADClkSrc = 1,
+	.modulo = 0,
+	.sad_cfg = (3 << 14) | (1 << 12) | (524 << 0),
+	.ifreq = 60258167,
+	.timf = 20452225,
+	.xtal_hz = 30000000,
 };
 
 static struct dib7000m_config stk7700p_dib7000m_config = {
@@ -758,45 +763,36 @@ static int stk7700p_tuner_attach(struct dvb_usb_adapter *adap)
 
 /* DIB7070 generic */
 static struct dibx000_agc_config dib7070_agc_config = {
-	BAND_UHF | BAND_VHF | BAND_LBAND | BAND_SBAND,
+	.band_caps = BAND_UHF | BAND_VHF | BAND_LBAND | BAND_SBAND,
 	/* P_agc_use_sd_mod1=0, P_agc_use_sd_mod2=0, P_agc_freq_pwm_div=5, P_agc_inv_pwm1=0, P_agc_inv_pwm2=0,
 	 * P_agc_inh_dc_rv_est=0, P_agc_time_est=3, P_agc_freeze=0, P_agc_nb_est=5, P_agc_write=0 */
-	(0 << 15) | (0 << 14) | (5 << 11) | (0 << 10) | (0 << 9) | (0 << 8)
-	| (3 << 5) | (0 << 4) | (5 << 1) | (0 << 0),
-
-	600,
-	10,
-
-	0,
-	118,
-
-	0,
-	3530,
-	1,
-	5,
-
-	65535,
-		0,
-
-	65535,
-	0,
-
-	0,
-	40,
-	183,
-	206,
-	255,
-	72,
-	152,
-	88,
-	90,
-
-	17,
-	27,
-	23,
-	51,
-
-	0,
+	.setup = (0 << 15) | (0 << 14) | (5 << 11) | (0 << 10) | (0 << 9) | (0 << 8) | (3 << 5) | (0 << 4) | (5 << 1) | (0 << 0),
+	.inv_gain = 600,
+	.time_stabiliz = 10,
+	.alpha_level = 0,
+	.thlock = 118,
+	.wbd_inv = 0,
+	.wbd_ref = 3530,
+	.wbd_sel = 1,
+	.wbd_alpha = 5,
+	.agc1_max = 65535,
+	.agc1_min = 0,
+	.agc2_max = 65535,
+	.agc2_min = 0,
+	.agc1_pt1 = 0,
+	.agc1_pt2 = 40,
+	.agc1_pt3 = 183,
+	.agc1_slope1 = 206,
+	.agc1_slope2 = 255,
+	.agc2_pt1 = 72,
+	.agc2_pt2 = 152,
+	.agc2_slope1 = 88,
+	.agc2_slope2 = 90,
+	.alpha_mant = 17,
+	.alpha_exp = 27,
+	.beta_mant = 23,
+	.beta_exp = 51,
+	.perform_agc_softsplit = 0,
 };
 
 static int dib7070_tuner_reset(struct dvb_frontend *fe, int onoff)
@@ -952,13 +948,22 @@ static int stk70x0p_pid_filter_ctrl(struct dvb_usb_adapter *adapter, int onoff)
 }
 
 static struct dibx000_bandwidth_config dib7070_bw_config_12_mhz = {
-	60000, 15000,
-	1, 20, 3, 1, 0,
-	0, 0, 1, 1, 2,
-	(3 << 14) | (1 << 12) | (524 << 0),
-	(0 << 25) | 0,
-	20452225,
-	12000000,
+	.internal = 60000,
+	.sampling = 15000,
+	.pll_prediv = 1,
+	.pll_ratio = 20,
+	.pll_range = 3,
+	.pll_reset = 1,
+	.pll_bypass = 0,
+	.enable_refdiv = 0,
+	.bypclk_div = 0,
+	.IO_CLK_en_core = 1,
+	.ADClkSrc = 1,
+	.modulo = 2,
+	.sad_cfg = (3 << 14) | (1 << 12) | (524 << 0),
+	.ifreq = (0 << 25) | 0,
+	.timf = 20452225,
+	.xtal_hz = 12000000,
 };
 
 static struct dib7000p_config dib7070p_dib7000p_config = {
@@ -1169,14 +1174,22 @@ static struct dibx000_agc_config dib807x_agc_config[2] = {
 };
 
 static struct dibx000_bandwidth_config dib807x_bw_config_12_mhz = {
-	60000, 15000, /* internal, sampling*/
-	1, 20, 3, 1, 0, /* pll_cfg: prediv, ratio, range, reset, bypass*/
-	0, 0, 1, 1, 2, /* misc: refdiv, bypclk_div, IO_CLK_en_core,
-			  ADClkSrc, modulo */
-	(3 << 14) | (1 << 12) | (599 << 0), /* sad_cfg: refsel, sel, freq_15k*/
-	(0 << 25) | 0, /* ifreq = 0.000000 MHz*/
-	18179755, /* timf*/
-	12000000, /* xtal_hz*/
+	.internal = 60000,
+	.sampling = 15000,
+	.pll_prediv = 1,
+	.pll_ratio = 20,
+	.pll_range = 3,
+	.pll_reset = 1,
+	.pll_bypass = 0,
+	.enable_refdiv = 0,
+	.bypclk_div = 0,
+	.IO_CLK_en_core = 1,
+	.ADClkSrc = 1,
+	.modulo = 2,
+	.sad_cfg = (3 << 14) | (1 << 12) | (599 << 0),	/* sad_cfg: refsel, sel, freq_15k*/
+	.ifreq = (0 << 25) | 0,				/* ifreq = 0.000000 MHz*/
+	.timf = 18179755,
+	.xtal_hz = 12000000,
 };
 
 static struct dib8000_config dib807x_dib8000_config[2] = {
@@ -1921,13 +1934,22 @@ static struct dibx000_agc_config dib8096p_agc_config[2] = {
 };
 
 static struct dibx000_bandwidth_config dib8096p_clock_config_12_mhz = {
-	108000, 13500,
-	1, 9, 1, 0, 0,
-	0, 0, 0, 0, 2,
-	(3 << 14) | (1 << 12) | (524 << 0),
-	(0 << 25) | 0,
-	20199729,
-	12000000,
+	.internal = 108000,
+	.sampling = 13500,
+	.pll_prediv = 1,
+	.pll_ratio = 9,
+	.pll_range = 1,
+	.pll_reset = 0,
+	.pll_bypass = 0,
+	.enable_refdiv = 0,
+	.bypclk_div = 0,
+	.IO_CLK_en_core = 0,
+	.ADClkSrc = 0,
+	.modulo = 2,
+	.sad_cfg = (3 << 14) | (1 << 12) | (524 << 0),
+	.ifreq = (0 << 25) | 0,
+	.timf = 20199729,
+	.xtal_hz = 12000000,
 };
 
 static struct dib8000_config tfe8096p_dib8000_config = {
@@ -2724,13 +2746,22 @@ static struct dibx000_agc_config dib7090_agc_config[2] = {
 };
 
 static struct dibx000_bandwidth_config dib7090_clock_config_12_mhz = {
-	60000, 15000,
-	1, 5, 0, 0, 0,
-	0, 0, 1, 1, 2,
-	(3 << 14) | (1 << 12) | (524 << 0),
-	(0 << 25) | 0,
-	20452225,
-	15000000,
+	.internal = 60000,
+	.sampling = 15000,
+	.pll_prediv = 1,
+	.pll_ratio = 5,
+	.pll_range = 0,
+	.pll_reset = 0,
+	.pll_bypass = 0,
+	.enable_refdiv = 0,
+	.bypclk_div = 0,
+	.IO_CLK_en_core = 1,
+	.ADClkSrc = 1,
+	.modulo = 2,
+	.sad_cfg = (3 << 14) | (1 << 12) | (524 << 0),
+	.ifreq = (0 << 25) | 0,
+	.timf = 20452225,
+	.xtal_hz = 15000000,
 };
 
 static struct dib7000p_config nim7090_dib7000p_config = {
@@ -3498,14 +3529,22 @@ static struct dibx000_agc_config stk7700p_7000p_xc4000_agc_config = {
 };
 
 static struct dibx000_bandwidth_config stk7700p_xc4000_pll_config = {
-	60000, 30000,	/* internal, sampling */
-	1, 8, 3, 1, 0,	/* pll_cfg: prediv, ratio, range, reset, bypass */
-	0, 0, 1, 1, 0,	/* misc: refdiv, bypclk_div, IO_CLK_en_core, */
-			/* ADClkSrc, modulo */
-	(3 << 14) | (1 << 12) | 524,	/* sad_cfg: refsel, sel, freq_15k */
-	39370534,	/* ifreq */
-	20452225,	/* timf */
-	30000000	/* xtal */
+	.internal = 60000,
+	.sampling = 30000,
+	.pll_prediv = 1,
+	.pll_ratio = 8,
+	.pll_range = 3,
+	.pll_reset = 1,
+	.pll_bypass = 0,
+	.enable_refdiv = 0,
+	.bypclk_div = 0,
+	.IO_CLK_en_core = 1,
+	.ADClkSrc = 1,
+	.modulo = 0,
+	.sad_cfg = (3 << 14) | (1 << 12) | 524, /* sad_cfg: refsel, sel, freq_15k */
+	.ifreq = 39370534,
+	.timf = 20452225,
+	.xtal_hz = 30000000
 };
 
 /* FIXME: none of these inputs are validated yet */
diff --git a/drivers/media/usb/dvb-usb/dibusb-common.c b/drivers/media/usb/dvb-usb/dibusb-common.c
index 6d68af0c49c8..ef3a8f75f82e 100644
--- a/drivers/media/usb/dvb-usb/dibusb-common.c
+++ b/drivers/media/usb/dvb-usb/dibusb-common.c
@@ -258,8 +258,8 @@ static struct dib3000mc_config mod3000p_dib3000p_config = {
 
 int dibusb_dib3000mc_frontend_attach(struct dvb_usb_adapter *adap)
 {
-	if (adap->dev->udev->descriptor.idVendor  == USB_VID_LITEON &&
-			adap->dev->udev->descriptor.idProduct ==
+	if (le16_to_cpu(adap->dev->udev->descriptor.idVendor) == USB_VID_LITEON &&
+	    le16_to_cpu(adap->dev->udev->descriptor.idProduct) ==
 			USB_PID_LITEON_DVB_T_WARM) {
 		msleep(1000);
 	}
@@ -297,8 +297,8 @@ int dibusb_dib3000mc_tuner_attach(struct dvb_usb_adapter *adap)
 	struct i2c_adapter *tun_i2c;
 
 	// First IF calibration for Liteon Sticks
-	if (adap->dev->udev->descriptor.idVendor  == USB_VID_LITEON &&
-		adap->dev->udev->descriptor.idProduct == USB_PID_LITEON_DVB_T_WARM) {
+	if (le16_to_cpu(adap->dev->udev->descriptor.idVendor) == USB_VID_LITEON &&
+	    le16_to_cpu(adap->dev->udev->descriptor.idProduct) == USB_PID_LITEON_DVB_T_WARM) {
 
 		dibusb_read_eeprom_byte(adap->dev,0x7E,&a);
 		dibusb_read_eeprom_byte(adap->dev,0x7F,&b);
@@ -310,8 +310,8 @@ int dibusb_dib3000mc_tuner_attach(struct dvb_usb_adapter *adap)
 		else
 			warn("LITE-ON DVB-T: Strange IF1 calibration :%2X %2X\n", a, b);
 
-	} else if (adap->dev->udev->descriptor.idVendor  == USB_VID_DIBCOM &&
-		   adap->dev->udev->descriptor.idProduct == USB_PID_DIBCOM_MOD3001_WARM) {
+	} else if (le16_to_cpu(adap->dev->udev->descriptor.idVendor) == USB_VID_DIBCOM &&
+		   le16_to_cpu(adap->dev->udev->descriptor.idProduct) == USB_PID_DIBCOM_MOD3001_WARM) {
 		u8 desc;
 		dibusb_read_eeprom_byte(adap->dev, 7, &desc);
 		if (desc == 2) {
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 2add8c507ec9..1a3df10d6bad 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -667,7 +667,7 @@ static int s6x0_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 				obuf[1] = (msg[j].addr << 1);
 				memcpy(obuf + 2, msg[j].buf, msg[j].len);
 				dw210x_op_rw(d->udev,
-						udev->descriptor.idProduct ==
+						le16_to_cpu(udev->descriptor.idProduct) ==
 						0x7500 ? 0x92 : 0x90, 0, 0,
 						obuf, msg[j].len + 2,
 						DW210X_WRITE_MSG);
@@ -1598,7 +1598,7 @@ static int dw2102_load_firmware(struct usb_device *dev,
 	u8 reset16[] = {0, 0, 0, 0, 0, 0, 0};
 	const struct firmware *fw;
 
-	switch (dev->descriptor.idProduct) {
+	switch (le16_to_cpu(dev->descriptor.idProduct)) {
 	case 0x2101:
 		ret = request_firmware(&fw, DW2101_FIRMWARE, &dev->dev);
 		if (ret != 0) {
@@ -1641,7 +1641,7 @@ static int dw2102_load_firmware(struct usb_device *dev,
 			ret = -EINVAL;
 		}
 		/* init registers */
-		switch (dev->descriptor.idProduct) {
+		switch (le16_to_cpu(dev->descriptor.idProduct)) {
 		case USB_PID_TEVII_S650:
 			dw2104_properties.rc.core.rc_codes = RC_MAP_TEVII_NEC;
 		case USB_PID_DW2104:
@@ -1901,14 +1901,14 @@ static struct dvb_usb_device_properties s6x0_properties = {
 	}
 };
 
-struct dvb_usb_device_properties *p1100;
+static struct dvb_usb_device_properties *p1100;
 static struct dvb_usb_device_description d1100 = {
 	"Prof 1100 USB ",
 	{&dw2102_table[PROF_1100], NULL},
 	{NULL},
 };
 
-struct dvb_usb_device_properties *s660;
+static struct dvb_usb_device_properties *s660;
 static struct dvb_usb_device_description d660 = {
 	"TeVii S660 USB",
 	{&dw2102_table[TEVII_S660], NULL},
@@ -1927,14 +1927,14 @@ static struct dvb_usb_device_description d480_2 = {
 	{NULL},
 };
 
-struct dvb_usb_device_properties *p7500;
+static struct dvb_usb_device_properties *p7500;
 static struct dvb_usb_device_description d7500 = {
 	"Prof 7500 USB DVB-S2",
 	{&dw2102_table[PROF_7500], NULL},
 	{NULL},
 };
 
-struct dvb_usb_device_properties *s421;
+static struct dvb_usb_device_properties *s421;
 static struct dvb_usb_device_description d421 = {
 	"TeVii S421 PCI",
 	{&dw2102_table[TEVII_S421], NULL},
diff --git a/drivers/media/usb/dvb-usb/opera1.c b/drivers/media/usb/dvb-usb/opera1.c
index 16ba90acf539..14a2119912ba 100644
--- a/drivers/media/usb/dvb-usb/opera1.c
+++ b/drivers/media/usb/dvb-usb/opera1.c
@@ -554,8 +554,8 @@ static int opera1_probe(struct usb_interface *intf,
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
 
-	if (udev->descriptor.idProduct == USB_PID_OPERA1_WARM &&
-		udev->descriptor.idVendor == USB_VID_OPERA1 &&
+	if (le16_to_cpu(udev->descriptor.idProduct) == USB_PID_OPERA1_WARM &&
+	    le16_to_cpu(udev->descriptor.idVendor) == USB_VID_OPERA1 &&
 		opera1_xilinx_load_firmware(udev, "dvb-usb-opera1-fpga-01.fw") != 0
 	    ) {
 		return -EINVAL;
diff --git a/drivers/media/usb/dvb-usb/pctv452e.c b/drivers/media/usb/dvb-usb/pctv452e.c
index bdfe8963591c..d17618fe8f5c 100644
--- a/drivers/media/usb/dvb-usb/pctv452e.c
+++ b/drivers/media/usb/dvb-usb/pctv452e.c
@@ -883,7 +883,7 @@ static int pctv452e_frontend_attach(struct dvb_usb_adapter *a)
 	if (!a->fe_adap[0].fe)
 		return -ENODEV;
 	if ((dvb_attach(lnbp22_attach, a->fe_adap[0].fe,
-					&a->dev->i2c_adap)) == 0)
+					&a->dev->i2c_adap)) == NULL)
 		err("Cannot attach lnbp22\n");
 
 	id = a->dev->desc->warm_ids[0];
@@ -900,7 +900,7 @@ static int pctv452e_tuner_attach(struct dvb_usb_adapter *a)
 	if (!a->fe_adap[0].fe)
 		return -ENODEV;
 	if (dvb_attach(stb6100_attach, a->fe_adap[0].fe, &stb6100_config,
-					&a->dev->i2c_adap) == 0) {
+					&a->dev->i2c_adap) == NULL) {
 		err("%s failed\n", __func__);
 		return -ENODEV;
 	}
@@ -965,7 +965,7 @@ static struct dvb_usb_device_properties pctv452e_properties = {
 		  .cold_ids = { NULL, NULL }, /* this is a warm only device */
 		  .warm_ids = { &pctv452e_usb_table[0], NULL }
 		},
-		{ 0 },
+		{ NULL },
 	}
 };
 
@@ -1023,7 +1023,7 @@ static struct dvb_usb_device_properties tt_connect_s2_3600_properties = {
 		  .cold_ids = { NULL, NULL },
 		  .warm_ids = { &pctv452e_usb_table[2], NULL }
 		},
-		{ 0 },
+		{ NULL },
 	}
 };
 
diff --git a/drivers/media/usb/em28xx/em28xx-audio.c b/drivers/media/usb/em28xx/em28xx-audio.c
index e881ef7b6445..957c7ae30efe 100644
--- a/drivers/media/usb/em28xx/em28xx-audio.c
+++ b/drivers/media/usb/em28xx/em28xx-audio.c
@@ -268,7 +268,7 @@ static int snd_em28xx_capture_open(struct snd_pcm_substream *substream)
 	nonblock = !!(substream->f_flags & O_NONBLOCK);
 	if (nonblock) {
 		if (!mutex_trylock(&dev->lock))
-		return -EAGAIN;
+			return -EAGAIN;
 	} else
 		mutex_lock(&dev->lock);
 
@@ -893,7 +893,7 @@ static int em28xx_audio_init(struct em28xx *dev)
 	static int          devnr;
 	int		    err;
 
-	if (!dev->has_alsa_audio) {
+	if (dev->usb_audio_type != EM28XX_USB_AUDIO_VENDOR) {
 		/* This device does not support the extension (in this case
 		   the device is expecting the snd-usb-audio module or
 		   doesn't have analog audio support at all) */
@@ -975,7 +975,7 @@ static int em28xx_audio_fini(struct em28xx *dev)
 	if (dev == NULL)
 		return 0;
 
-	if (!dev->has_alsa_audio) {
+	if (dev->usb_audio_type != EM28XX_USB_AUDIO_VENDOR) {
 		/* This device does not support the extension (in this case
 		   the device is expecting the snd-usb-audio module or
 		   doesn't have analog audio support at all) */
@@ -1003,7 +1003,7 @@ static int em28xx_audio_suspend(struct em28xx *dev)
 	if (dev == NULL)
 		return 0;
 
-	if (!dev->has_alsa_audio)
+	if (dev->usb_audio_type != EM28XX_USB_AUDIO_VENDOR)
 		return 0;
 
 	em28xx_info("Suspending audio extension");
@@ -1017,7 +1017,7 @@ static int em28xx_audio_resume(struct em28xx *dev)
 	if (dev == NULL)
 		return 0;
 
-	if (!dev->has_alsa_audio)
+	if (dev->usb_audio_type != EM28XX_USB_AUDIO_VENDOR)
 		return 0;
 
 	em28xx_info("Resuming audio extension");
diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index 9da812b8a786..71fa51e7984e 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -2246,7 +2246,7 @@ struct em28xx_board em28xx_boards[] = {
 };
 EXPORT_SYMBOL_GPL(em28xx_boards);
 
-const unsigned int em28xx_bcount = ARRAY_SIZE(em28xx_boards);
+static const unsigned int em28xx_bcount = ARRAY_SIZE(em28xx_boards);
 
 /* table of devices that work with this driver */
 struct usb_device_id em28xx_id_table[] = {
@@ -2931,9 +2931,9 @@ static void request_module_async(struct work_struct *work)
 #if defined(CONFIG_MODULES) && defined(MODULE)
 	if (dev->has_video)
 		request_module("em28xx-v4l");
-	if (dev->has_audio_class)
+	if (dev->usb_audio_type == EM28XX_USB_AUDIO_CLASS)
 		request_module("snd-usb-audio");
-	else if (dev->has_alsa_audio)
+	else if (dev->usb_audio_type == EM28XX_USB_AUDIO_VENDOR)
 		request_module("em28xx-alsa");
 	if (dev->board.has_dvb)
 		request_module("em28xx-dvb");
@@ -3098,16 +3098,6 @@ static int em28xx_init_dev(struct em28xx *dev, struct usb_device *udev,
 		}
 	}
 
-	if (dev->chip_id == CHIP_ID_EM2870 ||
-	    dev->chip_id == CHIP_ID_EM2874 ||
-	    dev->chip_id == CHIP_ID_EM28174 ||
-	    dev->chip_id == CHIP_ID_EM28178) {
-		/* Digital only device - don't load any alsa module */
-		dev->audio_mode.has_audio = false;
-		dev->has_audio_class = false;
-		dev->has_alsa_audio = false;
-	}
-
 	if (chip_name != default_chip_name)
 		printk(KERN_INFO DRIVER_NAME
 		       ": chip ID is %s\n", chip_name);
@@ -3190,7 +3180,7 @@ static int em28xx_usb_probe(struct usb_interface *interface,
 	struct usb_device *udev;
 	struct em28xx *dev = NULL;
 	int retval;
-	bool has_audio = false, has_video = false, has_dvb = false;
+	bool has_vendor_audio = false, has_video = false, has_dvb = false;
 	int i, nr, try_bulk;
 	const int ifnum = interface->altsetting[0].desc.bInterfaceNumber;
 	char *speed;
@@ -3272,7 +3262,7 @@ static int em28xx_usb_probe(struct usb_interface *interface,
 					break;
 				case 0x83:
 					if (usb_endpoint_xfer_isoc(e)) {
-						has_audio = true;
+						has_vendor_audio = true;
 					} else {
 						printk(KERN_INFO DRIVER_NAME
 						": error: skipping audio endpoint 0x83, because it uses bulk transfers !\n");
@@ -3328,7 +3318,7 @@ static int em28xx_usb_probe(struct usb_interface *interface,
 		}
 	}
 
-	if (!(has_audio || has_video || has_dvb)) {
+	if (!(has_vendor_audio || has_video || has_dvb)) {
 		retval = -ENODEV;
 		goto err_free;
 	}
@@ -3375,26 +3365,27 @@ static int em28xx_usb_probe(struct usb_interface *interface,
 	dev->devno = nr;
 	dev->model = id->driver_info;
 	dev->alt   = -1;
-	dev->is_audio_only = has_audio && !(has_video || has_dvb);
-	dev->has_alsa_audio = has_audio;
-	dev->audio_mode.has_audio = has_audio;
+	dev->is_audio_only = has_vendor_audio && !(has_video || has_dvb);
 	dev->has_video = has_video;
 	dev->ifnum = ifnum;
 
-	/* Checks if audio is provided by some interface */
+	if (has_vendor_audio) {
+		printk(KERN_INFO DRIVER_NAME ": Audio interface %i found %s\n",
+		       ifnum, "(Vendor Class)");
+		dev->usb_audio_type = EM28XX_USB_AUDIO_VENDOR;
+	}
+	/* Checks if audio is provided by a USB Audio Class interface */
 	for (i = 0; i < udev->config->desc.bNumInterfaces; i++) {
 		struct usb_interface *uif = udev->config->interface[i];
 		if (uif->altsetting[0].desc.bInterfaceClass == USB_CLASS_AUDIO) {
-			dev->has_audio_class = 1;
+			if (has_vendor_audio)
+				em28xx_err("em28xx: device seems to have vendor AND usb audio class interfaces !\n"
+					   "\t\tThe vendor interface will be ignored. Please contact the developers <linux-media@vger.kernel.org>\n");
+			dev->usb_audio_type = EM28XX_USB_AUDIO_CLASS;
 			break;
 		}
 	}
 
-	if (has_audio)
-		printk(KERN_INFO DRIVER_NAME
-		       ": Audio interface %i found %s\n",
-		       ifnum,
-		       dev->has_audio_class ? "(USB Audio Class)" : "(Vendor Class)");
 	if (has_video)
 		printk(KERN_INFO DRIVER_NAME
 		       ": Video interface %i found:%s%s\n",
diff --git a/drivers/media/usb/em28xx/em28xx-core.c b/drivers/media/usb/em28xx/em28xx-core.c
index 523d7e92bf47..b5e52fe7957a 100644
--- a/drivers/media/usb/em28xx/em28xx-core.c
+++ b/drivers/media/usb/em28xx/em28xx-core.c
@@ -279,7 +279,7 @@ int em28xx_read_ac97(struct em28xx *dev, u8 reg)
 {
 	int ret;
 	u8 addr = (reg & 0x7f) | 0x80;
-	u16 val;
+	__le16 val;
 
 	ret = em28xx_is_ac97_ready(dev);
 	if (ret < 0)
@@ -433,7 +433,7 @@ int em28xx_audio_analog_set(struct em28xx *dev)
 	int ret, i;
 	u8 xclk;
 
-	if (!dev->audio_mode.has_audio)
+	if (dev->int_audio_type == EM28XX_INT_AUDIO_NONE)
 		return 0;
 
 	/* It is assumed that all devices use master volume for output.
@@ -505,37 +505,48 @@ int em28xx_audio_setup(struct em28xx *dev)
 {
 	int vid1, vid2, feat, cfg;
 	u32 vid;
+	u8 i2s_samplerates;
 
-	if (!dev->audio_mode.has_audio)
+	if (dev->chip_id == CHIP_ID_EM2870 ||
+	    dev->chip_id == CHIP_ID_EM2874 ||
+	    dev->chip_id == CHIP_ID_EM28174 ||
+	    dev->chip_id == CHIP_ID_EM28178) {
+		/* Digital only device - don't load any alsa module */
+		dev->int_audio_type = EM28XX_INT_AUDIO_NONE;
+		dev->usb_audio_type = EM28XX_USB_AUDIO_NONE;
 		return 0;
+	}
 
 	/* See how this device is configured */
 	cfg = em28xx_read_reg(dev, EM28XX_R00_CHIPCFG);
 	em28xx_info("Config register raw data: 0x%02x\n", cfg);
-	if (cfg < 0) {
-		/* Register read error?  */
-		cfg = EM28XX_CHIPCFG_AC97; /* Be conservative */
+	if (cfg < 0) { /* Register read error */
+		/* Be conservative */
+		dev->int_audio_type = EM28XX_INT_AUDIO_AC97;
 	} else if ((cfg & EM28XX_CHIPCFG_AUDIOMASK) == 0x00) {
 		/* The device doesn't have vendor audio at all */
-		dev->has_alsa_audio = false;
-		dev->audio_mode.has_audio = false;
+		dev->int_audio_type = EM28XX_INT_AUDIO_NONE;
+		dev->usb_audio_type = EM28XX_USB_AUDIO_NONE;
 		return 0;
 	} else if ((cfg & EM28XX_CHIPCFG_AUDIOMASK) != EM28XX_CHIPCFG_AC97) {
+		dev->int_audio_type = EM28XX_INT_AUDIO_I2S;
 		if (dev->chip_id < CHIP_ID_EM2860 &&
 	            (cfg & EM28XX_CHIPCFG_AUDIOMASK) ==
 		    EM2820_CHIPCFG_I2S_1_SAMPRATE)
-			dev->audio_mode.i2s_samplerates = 1;
+			i2s_samplerates = 1;
 		else if (dev->chip_id >= CHIP_ID_EM2860 &&
 			 (cfg & EM28XX_CHIPCFG_AUDIOMASK) ==
 			 EM2860_CHIPCFG_I2S_5_SAMPRATES)
-			dev->audio_mode.i2s_samplerates = 5;
+			i2s_samplerates = 5;
 		else
-			dev->audio_mode.i2s_samplerates = 3;
+			i2s_samplerates = 3;
 		em28xx_info("I2S Audio (%d sample rate(s))\n",
-					       dev->audio_mode.i2s_samplerates);
+					       i2s_samplerates);
 		/* Skip the code that does AC97 vendor detection */
 		dev->audio_mode.ac97 = EM28XX_NO_AC97;
 		goto init_audio;
+	} else {
+		dev->int_audio_type = EM28XX_INT_AUDIO_AC97;
 	}
 
 	dev->audio_mode.ac97 = EM28XX_AC97_OTHER;
@@ -549,8 +560,9 @@ int em28xx_audio_setup(struct em28xx *dev)
 		 */
 		em28xx_warn("AC97 chip type couldn't be determined\n");
 		dev->audio_mode.ac97 = EM28XX_NO_AC97;
-		dev->has_alsa_audio = false;
-		dev->audio_mode.has_audio = false;
+		if (dev->usb_audio_type == EM28XX_USB_AUDIO_VENDOR)
+			dev->usb_audio_type = EM28XX_USB_AUDIO_NONE;
+		dev->int_audio_type = EM28XX_INT_AUDIO_NONE;
 		goto init_audio;
 	}
 
@@ -559,15 +571,12 @@ int em28xx_audio_setup(struct em28xx *dev)
 		goto init_audio;
 
 	vid = vid1 << 16 | vid2;
-
-	dev->audio_mode.ac97_vendor_id = vid;
 	em28xx_warn("AC97 vendor ID = 0x%08x\n", vid);
 
 	feat = em28xx_read_ac97(dev, AC97_RESET);
 	if (feat < 0)
 		goto init_audio;
 
-	dev->audio_mode.ac97_feat = feat;
 	em28xx_warn("AC97 features = 0x%04x\n", feat);
 
 	/* Try to identify what audio processor we have */
@@ -586,8 +595,8 @@ init_audio:
 		em28xx_info("Empia 202 AC97 audio processor detected\n");
 		break;
 	case EM28XX_AC97_SIGMATEL:
-		em28xx_info("Sigmatel audio processor detected(stac 97%02x)\n",
-			    dev->audio_mode.ac97_vendor_id & 0xff);
+		em28xx_info("Sigmatel audio processor detected (stac 97%02x)\n",
+			    vid & 0xff);
 		break;
 	case EM28XX_AC97_OTHER:
 		em28xx_warn("Unknown AC97 audio processor detected!\n");
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index 3a3e243edf89..9682c52d67d1 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -373,7 +373,6 @@ static struct tda18271_config kworld_ub435q_v2_config = {
 };
 
 static struct tda18212_config kworld_ub435q_v3_config = {
-	.i2c_address	= 0x60,
 	.if_atsc_vsb	= 3600,
 	.if_atsc_qam	= 3600,
 };
@@ -856,7 +855,9 @@ static const struct m88ds3103_config pctv_461e_m88ds3103_config = {
 	.clock = 27000000,
 	.i2c_wr_max = 33,
 	.clock_out = 0,
-	.ts_mode = M88DS3103_TS_PARALLEL_16,
+	.ts_mode = M88DS3103_TS_PARALLEL,
+	.ts_clk = 16000,
+	.ts_clk_pol = 1,
 	.agc = 0x99,
 };
 
@@ -1435,6 +1436,15 @@ static int em28xx_dvb_init(struct em28xx *dev)
 		}
 		break;
 	case EM2874_BOARD_KWORLD_UB435Q_V3:
+	{
+		struct i2c_client *client;
+		struct i2c_adapter *adapter = &dev->i2c_adap[dev->def_i2c_bus];
+		struct i2c_board_info board_info = {
+			.type = "tda18212",
+			.addr = 0x60,
+			.platform_data = &kworld_ub435q_v3_config,
+		};
+
 		dvb->fe[0] = dvb_attach(lgdt3305_attach,
 					&em2874_lgdt3305_nogate_dev,
 					&dev->i2c_adap[dev->def_i2c_bus]);
@@ -1443,14 +1453,26 @@ static int em28xx_dvb_init(struct em28xx *dev)
 			goto out_free;
 		}
 
-		/* Attach the demodulator. */
-		if (!dvb_attach(tda18212_attach, dvb->fe[0],
-				&dev->i2c_adap[dev->def_i2c_bus],
-				&kworld_ub435q_v3_config)) {
-			result = -EINVAL;
+		/* attach tuner */
+		kworld_ub435q_v3_config.fe = dvb->fe[0];
+		request_module("tda18212");
+		client = i2c_new_device(adapter, &board_info);
+		if (client == NULL || client->dev.driver == NULL) {
+			dvb_frontend_detach(dvb->fe[0]);
+			result = -ENODEV;
 			goto out_free;
 		}
+
+		if (!try_module_get(client->dev.driver->owner)) {
+			i2c_unregister_device(client);
+			dvb_frontend_detach(dvb->fe[0]);
+			result = -ENODEV;
+			goto out_free;
+		}
+
+		dvb->i2c_client_tuner = client;
 		break;
+	}
 	case EM2874_BOARD_PCTV_HD_MINI_80E:
 		dvb->fe[0] = dvb_attach(drx39xxj_attach, &dev->i2c_adap[dev->def_i2c_bus]);
 		if (dvb->fe[0] != NULL) {
@@ -1533,6 +1555,7 @@ static int em28xx_dvb_init(struct em28xx *dev)
 			/* attach demod */
 			si2168_config.i2c_adapter = &adapter;
 			si2168_config.fe = &dvb->fe[0];
+			si2168_config.ts_mode = SI2168_TS_PARALLEL;
 			memset(&info, 0, sizeof(struct i2c_board_info));
 			strlcpy(info.type, "si2168", I2C_NAME_SIZE);
 			info.addr = 0x64;
diff --git a/drivers/media/usb/em28xx/em28xx-input.c b/drivers/media/usb/em28xx/em28xx-input.c
index ed843bd221ea..581f6dad4ca9 100644
--- a/drivers/media/usb/em28xx/em28xx-input.c
+++ b/drivers/media/usb/em28xx/em28xx-input.c
@@ -71,8 +71,7 @@ struct em28xx_IR {
 	unsigned int last_readcount;
 	u64 rc_type;
 
-	/* i2c slave address of external device (if used) */
-	u16 i2c_dev_addr;
+	struct i2c_client *i2c_client;
 
 	int  (*get_key_i2c)(struct i2c_client *ir, enum rc_type *protocol, u32 *scancode);
 	int  (*get_key)(struct em28xx_IR *, struct em28xx_ir_poll_result *);
@@ -294,16 +293,11 @@ static int em2874_polling_getkey(struct em28xx_IR *ir,
 
 static int em28xx_i2c_ir_handle_key(struct em28xx_IR *ir)
 {
-	struct em28xx *dev = ir->dev;
 	static u32 scancode;
 	enum rc_type protocol;
 	int rc;
-	struct i2c_client client;
-
-	client.adapter = &ir->dev->i2c_adap[dev->def_i2c_bus];
-	client.addr = ir->i2c_dev_addr;
 
-	rc = ir->get_key_i2c(&client, &protocol, &scancode);
+	rc = ir->get_key_i2c(ir->i2c_client, &protocol, &scancode);
 	if (rc < 0) {
 		dprintk("ir->get_key_i2c() failed: %d\n", rc);
 		return rc;
@@ -361,7 +355,7 @@ static void em28xx_ir_work(struct work_struct *work)
 {
 	struct em28xx_IR *ir = container_of(work, struct em28xx_IR, work.work);
 
-	if (ir->i2c_dev_addr) /* external i2c device */
+	if (ir->i2c_client) /* external i2c device */
 		em28xx_i2c_ir_handle_key(ir);
 	else /* internal device */
 		em28xx_ir_handle_key(ir);
@@ -609,17 +603,17 @@ static int em28xx_register_snapshot_button(struct em28xx *dev)
 static void em28xx_init_buttons(struct em28xx *dev)
 {
 	u8  i = 0, j = 0;
-	bool addr_new = 0;
+	bool addr_new = false;
 
 	dev->button_polling_interval = EM28XX_BUTTONS_DEBOUNCED_QUERY_INTERVAL;
 	while (dev->board.buttons[i].role >= 0 &&
 			 dev->board.buttons[i].role < EM28XX_NUM_BUTTON_ROLES) {
 		struct em28xx_button *button = &dev->board.buttons[i];
 		/* Check if polling address is already on the list */
-		addr_new = 1;
+		addr_new = true;
 		for (j = 0; j < dev->num_button_polling_addresses; j++) {
 			if (button->reg_r == dev->button_polling_addresses[j]) {
-				addr_new = 0;
+				addr_new = false;
 				break;
 			}
 		}
@@ -756,7 +750,13 @@ static int em28xx_ir_init(struct em28xx *dev)
 			goto error;
 		}
 
-		ir->i2c_dev_addr = i2c_rc_dev_addr;
+		ir->i2c_client = kzalloc(sizeof(struct i2c_client), GFP_KERNEL);
+		if (!ir->i2c_client)
+			goto error;
+		ir->i2c_client->adapter = &ir->dev->i2c_adap[dev->def_i2c_bus];
+		ir->i2c_client->addr = i2c_rc_dev_addr;
+		ir->i2c_client->flags = 0;
+		/* NOTE: all other fields of i2c_client are unused */
 	} else {	/* internal device */
 		switch (dev->chip_id) {
 		case CHIP_ID_EM2860:
@@ -815,6 +815,7 @@ static int em28xx_ir_init(struct em28xx *dev)
 	return 0;
 
 error:
+	kfree(ir->i2c_client);
 	dev->ir = NULL;
 	rc_free_device(rc);
 	kfree(ir);
@@ -841,6 +842,8 @@ static int em28xx_ir_fini(struct em28xx *dev)
 	if (ir->rc)
 		rc_unregister_device(ir->rc);
 
+	kfree(ir->i2c_client);
+
 	/* done */
 	kfree(ir);
 	dev->ir = NULL;
diff --git a/drivers/media/usb/em28xx/em28xx-vbi.c b/drivers/media/usb/em28xx/em28xx-vbi.c
index 6d7f657f6f55..34ee1e03a732 100644
--- a/drivers/media/usb/em28xx/em28xx-vbi.c
+++ b/drivers/media/usb/em28xx/em28xx-vbi.c
@@ -29,17 +29,6 @@
 #include "em28xx.h"
 #include "em28xx-v4l.h"
 
-static unsigned int vbibufs = 5;
-module_param(vbibufs, int, 0644);
-MODULE_PARM_DESC(vbibufs, "number of vbi buffers, range 2-32");
-
-static unsigned int vbi_debug;
-module_param(vbi_debug, int, 0644);
-MODULE_PARM_DESC(vbi_debug, "enable debug messages [vbi]");
-
-#define dprintk(level, fmt, arg...)	if (vbi_debug >= level) \
-	printk(KERN_DEBUG "%s: " fmt, dev->core->name , ## arg)
-
 /* ------------------------------------------------------------------ */
 
 static int vbi_queue_setup(struct vb2_queue *vq, const struct v4l2_format *fmt,
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index 29abc379551e..03d5ece0319c 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -435,7 +435,10 @@ static inline void finish_buffer(struct em28xx *dev,
 	em28xx_isocdbg("[%p/%d] wakeup\n", buf, buf->top_field);
 
 	buf->vb.v4l2_buf.sequence = dev->v4l2->field_count++;
-	buf->vb.v4l2_buf.field = V4L2_FIELD_INTERLACED;
+	if (dev->v4l2->progressive)
+		buf->vb.v4l2_buf.field = V4L2_FIELD_NONE;
+	else
+		buf->vb.v4l2_buf.field = V4L2_FIELD_INTERLACED;
 	v4l2_get_timestamp(&buf->vb.v4l2_buf.timestamp);
 
 	vb2_buffer_done(&buf->vb, VB2_BUF_STATE_DONE);
@@ -478,7 +481,7 @@ static void em28xx_copy_video(struct em28xx *dev,
 	lencopy = lencopy > remain ? remain : lencopy;
 
 	if ((char *)startwrite + lencopy > (char *)buf->vb_buf + buf->length) {
-		em28xx_isocdbg("Overflow of %zi bytes past buffer end (1)\n",
+		em28xx_isocdbg("Overflow of %zu bytes past buffer end (1)\n",
 			      ((char *)startwrite + lencopy) -
 			      ((char *)buf->vb_buf + buf->length));
 		remain = (char *)buf->vb_buf + buf->length -
@@ -504,7 +507,7 @@ static void em28xx_copy_video(struct em28xx *dev,
 
 		if ((char *)startwrite + lencopy > (char *)buf->vb_buf +
 		    buf->length) {
-			em28xx_isocdbg("Overflow of %zi bytes past buffer end"
+			em28xx_isocdbg("Overflow of %zu bytes past buffer end"
 				       "(2)\n",
 				       ((char *)startwrite + lencopy) -
 				       ((char *)buf->vb_buf + buf->length));
@@ -718,7 +721,7 @@ static inline void process_frame_data_em25xx(struct em28xx *dev,
 	struct em28xx_buffer    *buf = dev->usb_ctl.vid_buf;
 	struct em28xx_dmaqueue  *dmaq = &dev->vidq;
 	struct em28xx_v4l2      *v4l2 = dev->v4l2;
-	bool frame_end = 0;
+	bool frame_end = false;
 
 	/* Check for header */
 	/* NOTE: at least with bulk transfers, only the first packet
@@ -994,13 +997,16 @@ static void em28xx_stop_streaming(struct vb2_queue *vq)
 	}
 
 	spin_lock_irqsave(&dev->slock, flags);
+	if (dev->usb_ctl.vid_buf != NULL) {
+		vb2_buffer_done(&dev->usb_ctl.vid_buf->vb, VB2_BUF_STATE_ERROR);
+		dev->usb_ctl.vid_buf = NULL;
+	}
 	while (!list_empty(&vidq->active)) {
 		struct em28xx_buffer *buf;
 		buf = list_entry(vidq->active.next, struct em28xx_buffer, list);
 		list_del(&buf->list);
 		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
 	}
-	dev->usb_ctl.vid_buf = NULL;
 	spin_unlock_irqrestore(&dev->slock, flags);
 }
 
@@ -1021,13 +1027,16 @@ void em28xx_stop_vbi_streaming(struct vb2_queue *vq)
 	}
 
 	spin_lock_irqsave(&dev->slock, flags);
+	if (dev->usb_ctl.vbi_buf != NULL) {
+		vb2_buffer_done(&dev->usb_ctl.vbi_buf->vb, VB2_BUF_STATE_ERROR);
+		dev->usb_ctl.vbi_buf = NULL;
+	}
 	while (!list_empty(&vbiq->active)) {
 		struct em28xx_buffer *buf;
 		buf = list_entry(vbiq->active.next, struct em28xx_buffer, list);
 		list_del(&buf->list);
 		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
 	}
-	dev->usb_ctl.vbi_buf = NULL;
 	spin_unlock_irqrestore(&dev->slock, flags);
 }
 
@@ -1711,7 +1720,7 @@ static int vidioc_querycap(struct file *file, void  *priv,
 	else
 		cap->device_caps = V4L2_CAP_READWRITE | V4L2_CAP_VBI_CAPTURE;
 
-	if (dev->audio_mode.has_audio)
+	if (dev->int_audio_type != EM28XX_INT_AUDIO_NONE)
 		cap->device_caps |= V4L2_CAP_AUDIO;
 
 	if (dev->tuner_type != TUNER_ABSENT)
@@ -2296,7 +2305,7 @@ static int em28xx_v4l2_init(struct em28xx *dev)
 	v4l2->v4l2_dev.ctrl_handler = hdl;
 
 	if (dev->board.is_webcam)
-		v4l2->progressive = 1;
+		v4l2->progressive = true;
 
 	/*
 	 * Default format, used for tvp5150 or saa711x output formats
@@ -2502,7 +2511,7 @@ static int em28xx_v4l2_init(struct em28xx *dev)
 		v4l2_disable_ioctl(v4l2->vdev, VIDIOC_G_FREQUENCY);
 		v4l2_disable_ioctl(v4l2->vdev, VIDIOC_S_FREQUENCY);
 	}
-	if (!dev->audio_mode.has_audio) {
+	if (dev->int_audio_type == EM28XX_INT_AUDIO_NONE) {
 		v4l2_disable_ioctl(v4l2->vdev, VIDIOC_G_AUDIO);
 		v4l2_disable_ioctl(v4l2->vdev, VIDIOC_S_AUDIO);
 	}
@@ -2532,7 +2541,7 @@ static int em28xx_v4l2_init(struct em28xx *dev)
 			v4l2_disable_ioctl(v4l2->vbi_dev, VIDIOC_G_FREQUENCY);
 			v4l2_disable_ioctl(v4l2->vbi_dev, VIDIOC_S_FREQUENCY);
 		}
-		if (!dev->audio_mode.has_audio) {
+		if (dev->int_audio_type == EM28XX_INT_AUDIO_NONE) {
 			v4l2_disable_ioctl(v4l2->vbi_dev, VIDIOC_G_AUDIO);
 			v4l2_disable_ioctl(v4l2->vbi_dev, VIDIOC_S_AUDIO);
 		}
diff --git a/drivers/media/usb/em28xx/em28xx.h b/drivers/media/usb/em28xx/em28xx.h
index 4360338e7b31..a21a7463b557 100644
--- a/drivers/media/usb/em28xx/em28xx.h
+++ b/drivers/media/usb/em28xx/em28xx.h
@@ -309,13 +309,18 @@ enum em28xx_ac97_mode {
 
 struct em28xx_audio_mode {
 	enum em28xx_ac97_mode ac97;
+};
 
-	u16 ac97_feat;
-	u32 ac97_vendor_id;
-
-	unsigned int has_audio:1;
+enum em28xx_int_audio_type {
+	EM28XX_INT_AUDIO_NONE = 0,
+	EM28XX_INT_AUDIO_AC97,
+	EM28XX_INT_AUDIO_I2S,
+};
 
-	u8 i2s_samplerates;
+enum em28xx_usb_audio_type {
+	EM28XX_USB_AUDIO_NONE = 0,
+	EM28XX_USB_AUDIO_CLASS,
+	EM28XX_USB_AUDIO_VENDOR,
 };
 
 /* em28xx has two audio inputs: tuner and line in.
@@ -608,9 +613,9 @@ struct em28xx {
 	unsigned int is_em25xx:1;	/* em25xx/em276x/7x/8x family bridge */
 	unsigned char disconnected:1;	/* device has been diconnected */
 	unsigned int has_video:1;
-	unsigned int has_audio_class:1;
-	unsigned int has_alsa_audio:1;
 	unsigned int is_audio_only:1;
+	enum em28xx_int_audio_type int_audio_type;
+	enum em28xx_usb_audio_type usb_audio_type;
 
 	struct em28xx_board board;
 
diff --git a/drivers/media/usb/go7007/go7007-usb.c b/drivers/media/usb/go7007/go7007-usb.c
index ece27ece8115..3f986e1178ce 100644
--- a/drivers/media/usb/go7007/go7007-usb.c
+++ b/drivers/media/usb/go7007/go7007-usb.c
@@ -696,7 +696,7 @@ static int go7007_usb_ezusb_write_interrupt(struct go7007 *go,
 				sizeof(status_reg), timeout);
 		if (r < 0)
 			break;
-		status_reg = le16_to_cpu(*((u16 *)go->usb_buf));
+		status_reg = le16_to_cpu(*((__le16 *)go->usb_buf));
 		if (!(status_reg & 0x0010))
 			break;
 		msleep(10);
@@ -751,7 +751,7 @@ static int go7007_usb_onboard_write_interrupt(struct go7007 *go,
 static void go7007_usb_readinterrupt_complete(struct urb *urb)
 {
 	struct go7007 *go = (struct go7007 *)urb->context;
-	u16 *regs = (u16 *)urb->transfer_buffer;
+	__le16 *regs = (__le16 *)urb->transfer_buffer;
 	int status = urb->status;
 
 	if (status) {
diff --git a/drivers/media/usb/gspca/gspca.c b/drivers/media/usb/gspca/gspca.c
index e8cf23c91cef..43d65057a5fe 100644
--- a/drivers/media/usb/gspca/gspca.c
+++ b/drivers/media/usb/gspca/gspca.c
@@ -876,9 +876,8 @@ static int gspca_init_transfer(struct gspca_dev *gspca_dev)
 		ep_tb[0].alt = gspca_dev->alt;
 		alt_idx = 1;
 	} else {
-
-	/* else, compute the minimum bandwidth
-	 * and build the endpoint table */
+		/* else, compute the minimum bandwidth
+		 * and build the endpoint table */
 		alt_idx = build_isoc_ep_tb(gspca_dev, intf, ep_tb);
 		if (alt_idx <= 0) {
 			pr_err("no transfer endpoint found\n");
diff --git a/drivers/media/usb/gspca/gspca.h b/drivers/media/usb/gspca/gspca.h
index f06253cd7469..d39adf90303b 100644
--- a/drivers/media/usb/gspca/gspca.h
+++ b/drivers/media/usb/gspca/gspca.h
@@ -235,6 +235,6 @@ int gspca_resume(struct usb_interface *intf);
 int gspca_expo_autogain(struct gspca_dev *gspca_dev, int avg_lum,
 	int desired_avg_lum, int deadzone, int gain_knee, int exposure_knee);
 int gspca_coarse_grained_expo_autogain(struct gspca_dev *gspca_dev,
-        int avg_lum, int desired_avg_lum, int deadzone);
+	int avg_lum, int desired_avg_lum, int deadzone);
 
 #endif /* GSPCAV2_H */
diff --git a/drivers/media/usb/gspca/kinect.c b/drivers/media/usb/gspca/kinect.c
index 45bc1f51c5d8..3cb30a37d6ac 100644
--- a/drivers/media/usb/gspca/kinect.c
+++ b/drivers/media/usb/gspca/kinect.c
@@ -51,9 +51,9 @@ struct pkt_hdr {
 
 struct cam_hdr {
 	uint8_t magic[2];
-	uint16_t len;
-	uint16_t cmd;
-	uint16_t tag;
+	__le16 len;
+	__le16 cmd;
+	__le16 tag;
 };
 
 /* specific webcam descriptor */
@@ -188,9 +188,9 @@ static int send_cmd(struct gspca_dev *gspca_dev, uint16_t cmd, void *cmdbuf,
 		       rhdr->tag, chdr->tag);
 		return -1;
 	}
-	if (cpu_to_le16(rhdr->len) != (actual_len/2)) {
+	if (le16_to_cpu(rhdr->len) != (actual_len/2)) {
 		pr_err("send_cmd: Bad len %04x != %04x\n",
-		       cpu_to_le16(rhdr->len), (int)(actual_len/2));
+		       le16_to_cpu(rhdr->len), (int)(actual_len/2));
 		return -1;
 	}
 
@@ -211,7 +211,7 @@ static int write_register(struct gspca_dev *gspca_dev, uint16_t reg,
 			uint16_t data)
 {
 	uint16_t reply[2];
-	uint16_t cmd[2];
+	__le16 cmd[2];
 	int res;
 
 	cmd[0] = cpu_to_le16(reg);
diff --git a/drivers/media/usb/gspca/sn9c20x.c b/drivers/media/usb/gspca/sn9c20x.c
index 41a9a892f79c..d0ee899584a9 100644
--- a/drivers/media/usb/gspca/sn9c20x.c
+++ b/drivers/media/usb/gspca/sn9c20x.c
@@ -1297,7 +1297,7 @@ static void set_cmatrix(struct gspca_dev *gspca_dev,
 	s32 hue_coord, hue_index = 180 + hue;
 	u8 cmatrix[21];
 
-	memset(cmatrix, 0, sizeof cmatrix);
+	memset(cmatrix, 0, sizeof(cmatrix));
 	cmatrix[2] = (contrast * 0x25 / 0x100) + 0x26;
 	cmatrix[0] = 0x13 + (cmatrix[2] - 0x26) * 0x13 / 0x25;
 	cmatrix[4] = 0x07 + (cmatrix[2] - 0x26) * 0x07 / 0x25;
@@ -1787,8 +1787,9 @@ static int sd_init(struct gspca_dev *gspca_dev)
 	struct sd *sd = (struct sd *) gspca_dev;
 	int i;
 	u8 value;
-	u8 i2c_init[9] =
-		{0x80, sd->i2c_addr, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03};
+	u8 i2c_init[9] = {
+		0x80, sd->i2c_addr, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03
+	};
 
 	for (i = 0; i < ARRAY_SIZE(bridge_init); i++) {
 		value = bridge_init[i][1];
@@ -2242,8 +2243,9 @@ static void sd_pkt_scan(struct gspca_dev *gspca_dev,
 {
 	struct sd *sd = (struct sd *) gspca_dev;
 	int avg_lum, is_jpeg;
-	static const u8 frame_header[] =
-		{0xff, 0xff, 0x00, 0xc4, 0xc4, 0x96};
+	static const u8 frame_header[] = {
+		0xff, 0xff, 0x00, 0xc4, 0xc4, 0x96
+	};
 
 	is_jpeg = (sd->fmt & 0x03) == 0;
 	if (len >= 64 && memcmp(data, frame_header, 6) == 0) {
diff --git a/drivers/media/usb/hackrf/Kconfig b/drivers/media/usb/hackrf/Kconfig
new file mode 100644
index 000000000000..937e6f5c1e8e
--- /dev/null
+++ b/drivers/media/usb/hackrf/Kconfig
@@ -0,0 +1,10 @@
+config USB_HACKRF
+	tristate "HackRF"
+	depends on VIDEO_V4L2
+	select VIDEOBUF2_VMALLOC
+	---help---
+	  This is a video4linux2 driver for HackRF SDR device.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called hackrf
+
diff --git a/drivers/media/usb/hackrf/Makefile b/drivers/media/usb/hackrf/Makefile
new file mode 100644
index 000000000000..73064a24cd4e
--- /dev/null
+++ b/drivers/media/usb/hackrf/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_USB_HACKRF)              += hackrf.o
diff --git a/drivers/media/usb/hackrf/hackrf.c b/drivers/media/usb/hackrf/hackrf.c
new file mode 100644
index 000000000000..328b5ba47a0a
--- /dev/null
+++ b/drivers/media/usb/hackrf/hackrf.c
@@ -0,0 +1,1142 @@
+/*
+ * HackRF driver
+ *
+ * Copyright (C) 2014 Antti Palosaari <crope@iki.fi>
+ *
+ *    This program is free software; you can redistribute it and/or modify
+ *    it under the terms of the GNU General Public License as published by
+ *    the Free Software Foundation; either version 2 of the License, or
+ *    (at your option) any later version.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/usb.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-event.h>
+#include <media/videobuf2-vmalloc.h>
+
+/* HackRF USB API commands (from HackRF Library) */
+enum {
+	CMD_SET_TRANSCEIVER_MODE           = 0x01,
+	CMD_SAMPLE_RATE_SET                = 0x06,
+	CMD_BASEBAND_FILTER_BANDWIDTH_SET  = 0x07,
+	CMD_BOARD_ID_READ                  = 0x0e,
+	CMD_VERSION_STRING_READ            = 0x0f,
+	CMD_SET_FREQ                       = 0x10,
+	CMD_SET_LNA_GAIN                   = 0x13,
+	CMD_SET_VGA_GAIN                   = 0x14,
+};
+
+/*
+ *       bEndpointAddress     0x81  EP 1 IN
+ *         Transfer Type            Bulk
+ *       wMaxPacketSize     0x0200  1x 512 bytes
+ */
+#define MAX_BULK_BUFS            (6)
+#define BULK_BUFFER_SIZE         (128 * 512)
+
+static const struct v4l2_frequency_band bands_adc[] = {
+	{
+		.tuner = 0,
+		.type = V4L2_TUNER_ADC,
+		.index = 0,
+		.capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS,
+		.rangelow   =   200000,
+		.rangehigh  = 24000000,
+	},
+};
+
+static const struct v4l2_frequency_band bands_rf[] = {
+	{
+		.tuner = 1,
+		.type = V4L2_TUNER_RF,
+		.index = 0,
+		.capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS,
+		.rangelow   =          1,
+		.rangehigh  = 4294967294LL, /* max u32, hw goes over 7GHz */
+	},
+};
+
+/* stream formats */
+struct hackrf_format {
+	char	*name;
+	u32	pixelformat;
+	u32	buffersize;
+};
+
+/* format descriptions for capture and preview */
+static struct hackrf_format formats[] = {
+	{
+		.name		= "Complex S8",
+		.pixelformat	= V4L2_SDR_FMT_CS8,
+		.buffersize	= BULK_BUFFER_SIZE,
+	},
+};
+
+static const unsigned int NUM_FORMATS = ARRAY_SIZE(formats);
+
+/* intermediate buffers with raw data from the USB device */
+struct hackrf_frame_buf {
+	struct vb2_buffer vb;   /* common v4l buffer stuff -- must be first */
+	struct list_head list;
+};
+
+struct hackrf_dev {
+#define POWER_ON           (1 << 1)
+#define URB_BUF            (1 << 2)
+#define USB_STATE_URB_BUF  (1 << 3)
+	unsigned long flags;
+
+	struct device *dev;
+	struct usb_device *udev;
+	struct video_device vdev;
+	struct v4l2_device v4l2_dev;
+
+	/* videobuf2 queue and queued buffers list */
+	struct vb2_queue vb_queue;
+	struct list_head queued_bufs;
+	spinlock_t queued_bufs_lock; /* Protects queued_bufs */
+	unsigned sequence;	     /* Buffer sequence counter */
+	unsigned int vb_full;        /* vb is full and packets dropped */
+
+	/* Note if taking both locks v4l2_lock must always be locked first! */
+	struct mutex v4l2_lock;      /* Protects everything else */
+	struct mutex vb_queue_lock;  /* Protects vb_queue */
+
+	struct urb     *urb_list[MAX_BULK_BUFS];
+	int            buf_num;
+	unsigned long  buf_size;
+	u8             *buf_list[MAX_BULK_BUFS];
+	dma_addr_t     dma_addr[MAX_BULK_BUFS];
+	int            urbs_initialized;
+	int            urbs_submitted;
+
+	/* USB control message buffer */
+	#define BUF_SIZE 24
+	u8 buf[BUF_SIZE];
+
+	/* Current configuration */
+	unsigned int f_adc;
+	unsigned int f_rf;
+	u32 pixelformat;
+	u32 buffersize;
+
+	/* Controls */
+	struct v4l2_ctrl_handler hdl;
+	struct v4l2_ctrl *bandwidth_auto;
+	struct v4l2_ctrl *bandwidth;
+	struct v4l2_ctrl *lna_gain;
+	struct v4l2_ctrl *if_gain;
+
+	/* Sample rate calc */
+	unsigned long jiffies_next;
+	unsigned int sample;
+	unsigned int sample_measured;
+};
+
+#define hackrf_dbg_usb_control_msg(_dev, _r, _t, _v, _i, _b, _l) { \
+	char *_direction; \
+	if (_t & USB_DIR_IN) \
+		_direction = "<<<"; \
+	else \
+		_direction = ">>>"; \
+	dev_dbg(_dev, "%02x %02x %02x %02x %02x %02x %02x %02x %s %*ph\n", \
+			_t, _r, _v & 0xff, _v >> 8, _i & 0xff, \
+			_i >> 8, _l & 0xff, _l >> 8, _direction, _l, _b); \
+}
+
+/* execute firmware command */
+static int hackrf_ctrl_msg(struct hackrf_dev *dev, u8 request, u16 value,
+		u16 index, u8 *data, u16 size)
+{
+	int ret;
+	unsigned int pipe;
+	u8 requesttype;
+
+	switch (request) {
+	case CMD_SET_TRANSCEIVER_MODE:
+	case CMD_SET_FREQ:
+	case CMD_SAMPLE_RATE_SET:
+	case CMD_BASEBAND_FILTER_BANDWIDTH_SET:
+		pipe = usb_sndctrlpipe(dev->udev, 0);
+		requesttype = (USB_TYPE_VENDOR | USB_DIR_OUT);
+		break;
+	case CMD_BOARD_ID_READ:
+	case CMD_VERSION_STRING_READ:
+	case CMD_SET_LNA_GAIN:
+	case CMD_SET_VGA_GAIN:
+		pipe = usb_rcvctrlpipe(dev->udev, 0);
+		requesttype = (USB_TYPE_VENDOR | USB_DIR_IN);
+		break;
+	default:
+		dev_err(dev->dev, "Unknown command %02x\n", request);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	/* write request */
+	if (!(requesttype & USB_DIR_IN))
+		memcpy(dev->buf, data, size);
+
+	ret = usb_control_msg(dev->udev, pipe, request, requesttype, value,
+			index, dev->buf, size, 1000);
+	hackrf_dbg_usb_control_msg(dev->dev, request, requesttype, value,
+			index, dev->buf, size);
+	if (ret < 0) {
+		dev_err(dev->dev, "usb_control_msg() failed %d request %02x\n",
+				ret, request);
+		goto err;
+	}
+
+	/* read request */
+	if (requesttype & USB_DIR_IN)
+		memcpy(data, dev->buf, size);
+
+	return 0;
+err:
+	return ret;
+}
+
+/* Private functions */
+static struct hackrf_frame_buf *hackrf_get_next_fill_buf(struct hackrf_dev *dev)
+{
+	unsigned long flags;
+	struct hackrf_frame_buf *buf = NULL;
+
+	spin_lock_irqsave(&dev->queued_bufs_lock, flags);
+	if (list_empty(&dev->queued_bufs))
+		goto leave;
+
+	buf = list_entry(dev->queued_bufs.next, struct hackrf_frame_buf, list);
+	list_del(&buf->list);
+leave:
+	spin_unlock_irqrestore(&dev->queued_bufs_lock, flags);
+	return buf;
+}
+
+static unsigned int hackrf_convert_stream(struct hackrf_dev *dev,
+		void *dst, void *src, unsigned int src_len)
+{
+	memcpy(dst, src, src_len);
+
+	/* calculate sample rate and output it in 10 seconds intervals */
+	if (unlikely(time_is_before_jiffies(dev->jiffies_next))) {
+		#define MSECS 10000UL
+		unsigned int msecs = jiffies_to_msecs(jiffies -
+				dev->jiffies_next + msecs_to_jiffies(MSECS));
+		unsigned int samples = dev->sample - dev->sample_measured;
+
+		dev->jiffies_next = jiffies + msecs_to_jiffies(MSECS);
+		dev->sample_measured = dev->sample;
+		dev_dbg(dev->dev, "slen=%u samples=%u msecs=%u sample rate=%lu\n",
+				src_len, samples, msecs,
+				samples * 1000UL / msecs);
+	}
+
+	/* total number of samples */
+	dev->sample += src_len / 2;
+
+	return src_len;
+}
+
+/*
+ * This gets called for the bulk stream pipe. This is done in interrupt
+ * time, so it has to be fast, not crash, and not stall. Neat.
+ */
+static void hackrf_urb_complete(struct urb *urb)
+{
+	struct hackrf_dev *dev = urb->context;
+	struct hackrf_frame_buf *fbuf;
+
+	dev_dbg_ratelimited(dev->dev, "status=%d length=%d/%d errors=%d\n",
+			urb->status, urb->actual_length,
+			urb->transfer_buffer_length, urb->error_count);
+
+	switch (urb->status) {
+	case 0:             /* success */
+	case -ETIMEDOUT:    /* NAK */
+		break;
+	case -ECONNRESET:   /* kill */
+	case -ENOENT:
+	case -ESHUTDOWN:
+		return;
+	default:            /* error */
+		dev_err_ratelimited(dev->dev, "URB failed %d\n", urb->status);
+		break;
+	}
+
+	if (likely(urb->actual_length > 0)) {
+		void *ptr;
+		unsigned int len;
+		/* get free framebuffer */
+		fbuf = hackrf_get_next_fill_buf(dev);
+		if (unlikely(fbuf == NULL)) {
+			dev->vb_full++;
+			dev_notice_ratelimited(dev->dev,
+					"videobuf is full, %d packets dropped\n",
+					dev->vb_full);
+			goto skip;
+		}
+
+		/* fill framebuffer */
+		ptr = vb2_plane_vaddr(&fbuf->vb, 0);
+		len = hackrf_convert_stream(dev, ptr, urb->transfer_buffer,
+				urb->actual_length);
+		vb2_set_plane_payload(&fbuf->vb, 0, len);
+		v4l2_get_timestamp(&fbuf->vb.v4l2_buf.timestamp);
+		fbuf->vb.v4l2_buf.sequence = dev->sequence++;
+		vb2_buffer_done(&fbuf->vb, VB2_BUF_STATE_DONE);
+	}
+skip:
+	usb_submit_urb(urb, GFP_ATOMIC);
+}
+
+static int hackrf_kill_urbs(struct hackrf_dev *dev)
+{
+	int i;
+
+	for (i = dev->urbs_submitted - 1; i >= 0; i--) {
+		dev_dbg(dev->dev, "kill urb=%d\n", i);
+		/* stop the URB */
+		usb_kill_urb(dev->urb_list[i]);
+	}
+	dev->urbs_submitted = 0;
+
+	return 0;
+}
+
+static int hackrf_submit_urbs(struct hackrf_dev *dev)
+{
+	int i, ret;
+
+	for (i = 0; i < dev->urbs_initialized; i++) {
+		dev_dbg(dev->dev, "submit urb=%d\n", i);
+		ret = usb_submit_urb(dev->urb_list[i], GFP_ATOMIC);
+		if (ret) {
+			dev_err(dev->dev, "Could not submit URB no. %d - get them all back\n",
+					i);
+			hackrf_kill_urbs(dev);
+			return ret;
+		}
+		dev->urbs_submitted++;
+	}
+
+	return 0;
+}
+
+static int hackrf_free_stream_bufs(struct hackrf_dev *dev)
+{
+	if (dev->flags & USB_STATE_URB_BUF) {
+		while (dev->buf_num) {
+			dev->buf_num--;
+			dev_dbg(dev->dev, "free buf=%d\n", dev->buf_num);
+			usb_free_coherent(dev->udev, dev->buf_size,
+					  dev->buf_list[dev->buf_num],
+					  dev->dma_addr[dev->buf_num]);
+		}
+	}
+	dev->flags &= ~USB_STATE_URB_BUF;
+
+	return 0;
+}
+
+static int hackrf_alloc_stream_bufs(struct hackrf_dev *dev)
+{
+	dev->buf_num = 0;
+	dev->buf_size = BULK_BUFFER_SIZE;
+
+	dev_dbg(dev->dev, "all in all I will use %u bytes for streaming\n",
+			MAX_BULK_BUFS * BULK_BUFFER_SIZE);
+
+	for (dev->buf_num = 0; dev->buf_num < MAX_BULK_BUFS; dev->buf_num++) {
+		dev->buf_list[dev->buf_num] = usb_alloc_coherent(dev->udev,
+				BULK_BUFFER_SIZE, GFP_ATOMIC,
+				&dev->dma_addr[dev->buf_num]);
+		if (!dev->buf_list[dev->buf_num]) {
+			dev_dbg(dev->dev, "alloc buf=%d failed\n",
+					dev->buf_num);
+			hackrf_free_stream_bufs(dev);
+			return -ENOMEM;
+		}
+
+		dev_dbg(dev->dev, "alloc buf=%d %p (dma %llu)\n", dev->buf_num,
+				dev->buf_list[dev->buf_num],
+				(long long)dev->dma_addr[dev->buf_num]);
+		dev->flags |= USB_STATE_URB_BUF;
+	}
+
+	return 0;
+}
+
+static int hackrf_free_urbs(struct hackrf_dev *dev)
+{
+	int i;
+
+	hackrf_kill_urbs(dev);
+
+	for (i = dev->urbs_initialized - 1; i >= 0; i--) {
+		if (dev->urb_list[i]) {
+			dev_dbg(dev->dev, "free urb=%d\n", i);
+			/* free the URBs */
+			usb_free_urb(dev->urb_list[i]);
+		}
+	}
+	dev->urbs_initialized = 0;
+
+	return 0;
+}
+
+static int hackrf_alloc_urbs(struct hackrf_dev *dev)
+{
+	int i, j;
+
+	/* allocate the URBs */
+	for (i = 0; i < MAX_BULK_BUFS; i++) {
+		dev_dbg(dev->dev, "alloc urb=%d\n", i);
+		dev->urb_list[i] = usb_alloc_urb(0, GFP_ATOMIC);
+		if (!dev->urb_list[i]) {
+			dev_dbg(dev->dev, "failed\n");
+			for (j = 0; j < i; j++)
+				usb_free_urb(dev->urb_list[j]);
+			return -ENOMEM;
+		}
+		usb_fill_bulk_urb(dev->urb_list[i],
+				dev->udev,
+				usb_rcvbulkpipe(dev->udev, 0x81),
+				dev->buf_list[i],
+				BULK_BUFFER_SIZE,
+				hackrf_urb_complete, dev);
+
+		dev->urb_list[i]->transfer_flags = URB_NO_TRANSFER_DMA_MAP;
+		dev->urb_list[i]->transfer_dma = dev->dma_addr[i];
+		dev->urbs_initialized++;
+	}
+
+	return 0;
+}
+
+/* Must be called with vb_queue_lock hold */
+static void hackrf_cleanup_queued_bufs(struct hackrf_dev *dev)
+{
+	unsigned long flags;
+
+	dev_dbg(dev->dev, "\n");
+
+	spin_lock_irqsave(&dev->queued_bufs_lock, flags);
+	while (!list_empty(&dev->queued_bufs)) {
+		struct hackrf_frame_buf *buf;
+
+		buf = list_entry(dev->queued_bufs.next,
+				struct hackrf_frame_buf, list);
+		list_del(&buf->list);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+	}
+	spin_unlock_irqrestore(&dev->queued_bufs_lock, flags);
+}
+
+/* The user yanked out the cable... */
+static void hackrf_disconnect(struct usb_interface *intf)
+{
+	struct v4l2_device *v = usb_get_intfdata(intf);
+	struct hackrf_dev *dev = container_of(v, struct hackrf_dev, v4l2_dev);
+
+	dev_dbg(dev->dev, "\n");
+
+	mutex_lock(&dev->vb_queue_lock);
+	mutex_lock(&dev->v4l2_lock);
+	/* No need to keep the urbs around after disconnection */
+	dev->udev = NULL;
+	v4l2_device_disconnect(&dev->v4l2_dev);
+	video_unregister_device(&dev->vdev);
+	mutex_unlock(&dev->v4l2_lock);
+	mutex_unlock(&dev->vb_queue_lock);
+
+	v4l2_device_put(&dev->v4l2_dev);
+}
+
+/* Videobuf2 operations */
+static int hackrf_queue_setup(struct vb2_queue *vq,
+		const struct v4l2_format *fmt, unsigned int *nbuffers,
+		unsigned int *nplanes, unsigned int sizes[], void *alloc_ctxs[])
+{
+	struct hackrf_dev *dev = vb2_get_drv_priv(vq);
+
+	dev_dbg(dev->dev, "nbuffers=%d\n", *nbuffers);
+
+	/* Need at least 8 buffers */
+	if (vq->num_buffers + *nbuffers < 8)
+		*nbuffers = 8 - vq->num_buffers;
+	*nplanes = 1;
+	sizes[0] = PAGE_ALIGN(dev->buffersize);
+
+	dev_dbg(dev->dev, "nbuffers=%d sizes[0]=%d\n", *nbuffers, sizes[0]);
+	return 0;
+}
+
+static void hackrf_buf_queue(struct vb2_buffer *vb)
+{
+	struct hackrf_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct hackrf_frame_buf *buf =
+			container_of(vb, struct hackrf_frame_buf, vb);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->queued_bufs_lock, flags);
+	list_add_tail(&buf->list, &dev->queued_bufs);
+	spin_unlock_irqrestore(&dev->queued_bufs_lock, flags);
+}
+
+static int hackrf_start_streaming(struct vb2_queue *vq, unsigned int count)
+{
+	struct hackrf_dev *dev = vb2_get_drv_priv(vq);
+	int ret;
+
+	dev_dbg(dev->dev, "\n");
+
+	if (!dev->udev)
+		return -ENODEV;
+
+	mutex_lock(&dev->v4l2_lock);
+
+	dev->sequence = 0;
+
+	set_bit(POWER_ON, &dev->flags);
+
+	ret = hackrf_alloc_stream_bufs(dev);
+	if (ret)
+		goto err;
+
+	ret = hackrf_alloc_urbs(dev);
+	if (ret)
+		goto err;
+
+	ret = hackrf_submit_urbs(dev);
+	if (ret)
+		goto err;
+
+	/* start hardware streaming */
+	ret = hackrf_ctrl_msg(dev, CMD_SET_TRANSCEIVER_MODE, 1, 0, NULL, 0);
+	if (ret)
+		goto err;
+
+	goto exit_mutex_unlock;
+err:
+	hackrf_kill_urbs(dev);
+	hackrf_free_urbs(dev);
+	hackrf_free_stream_bufs(dev);
+	clear_bit(POWER_ON, &dev->flags);
+
+	/* return all queued buffers to vb2 */
+	{
+		struct hackrf_frame_buf *buf, *tmp;
+
+		list_for_each_entry_safe(buf, tmp, &dev->queued_bufs, list) {
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
+		}
+	}
+
+exit_mutex_unlock:
+	mutex_unlock(&dev->v4l2_lock);
+
+	return ret;
+}
+
+static void hackrf_stop_streaming(struct vb2_queue *vq)
+{
+	struct hackrf_dev *dev = vb2_get_drv_priv(vq);
+
+	dev_dbg(dev->dev, "\n");
+
+	mutex_lock(&dev->v4l2_lock);
+
+	/* stop hardware streaming */
+	hackrf_ctrl_msg(dev, CMD_SET_TRANSCEIVER_MODE, 0, 0, NULL, 0);
+
+	hackrf_kill_urbs(dev);
+	hackrf_free_urbs(dev);
+	hackrf_free_stream_bufs(dev);
+
+	hackrf_cleanup_queued_bufs(dev);
+
+	clear_bit(POWER_ON, &dev->flags);
+
+	mutex_unlock(&dev->v4l2_lock);
+}
+
+static struct vb2_ops hackrf_vb2_ops = {
+	.queue_setup            = hackrf_queue_setup,
+	.buf_queue              = hackrf_buf_queue,
+	.start_streaming        = hackrf_start_streaming,
+	.stop_streaming         = hackrf_stop_streaming,
+	.wait_prepare           = vb2_ops_wait_prepare,
+	.wait_finish            = vb2_ops_wait_finish,
+};
+
+static int hackrf_querycap(struct file *file, void *fh,
+		struct v4l2_capability *cap)
+{
+	struct hackrf_dev *dev = video_drvdata(file);
+
+	dev_dbg(dev->dev, "\n");
+
+	strlcpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver));
+	strlcpy(cap->card, dev->vdev.name, sizeof(cap->card));
+	usb_make_path(dev->udev, cap->bus_info, sizeof(cap->bus_info));
+	cap->device_caps = V4L2_CAP_SDR_CAPTURE | V4L2_CAP_STREAMING |
+			V4L2_CAP_READWRITE | V4L2_CAP_TUNER;
+	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
+
+	return 0;
+}
+
+static int hackrf_s_fmt_sdr_cap(struct file *file, void *priv,
+		struct v4l2_format *f)
+{
+	struct hackrf_dev *dev = video_drvdata(file);
+	struct vb2_queue *q = &dev->vb_queue;
+	int i;
+
+	dev_dbg(dev->dev, "pixelformat fourcc %4.4s\n",
+			(char *)&f->fmt.sdr.pixelformat);
+
+	if (vb2_is_busy(q))
+		return -EBUSY;
+
+	memset(f->fmt.sdr.reserved, 0, sizeof(f->fmt.sdr.reserved));
+	for (i = 0; i < NUM_FORMATS; i++) {
+		if (f->fmt.sdr.pixelformat == formats[i].pixelformat) {
+			dev->pixelformat = formats[i].pixelformat;
+			dev->buffersize = formats[i].buffersize;
+			f->fmt.sdr.buffersize = formats[i].buffersize;
+			return 0;
+		}
+	}
+
+	dev->pixelformat = formats[0].pixelformat;
+	dev->buffersize = formats[0].buffersize;
+	f->fmt.sdr.pixelformat = formats[0].pixelformat;
+	f->fmt.sdr.buffersize = formats[0].buffersize;
+
+	return 0;
+}
+
+static int hackrf_g_fmt_sdr_cap(struct file *file, void *priv,
+		struct v4l2_format *f)
+{
+	struct hackrf_dev *dev = video_drvdata(file);
+
+	dev_dbg(dev->dev, "pixelformat fourcc %4.4s\n",
+			(char *)&dev->pixelformat);
+
+	memset(f->fmt.sdr.reserved, 0, sizeof(f->fmt.sdr.reserved));
+	f->fmt.sdr.pixelformat = dev->pixelformat;
+	f->fmt.sdr.buffersize = dev->buffersize;
+
+	return 0;
+}
+
+static int hackrf_try_fmt_sdr_cap(struct file *file, void *priv,
+		struct v4l2_format *f)
+{
+	struct hackrf_dev *dev = video_drvdata(file);
+	int i;
+
+	dev_dbg(dev->dev, "pixelformat fourcc %4.4s\n",
+			(char *)&f->fmt.sdr.pixelformat);
+
+	memset(f->fmt.sdr.reserved, 0, sizeof(f->fmt.sdr.reserved));
+	for (i = 0; i < NUM_FORMATS; i++) {
+		if (formats[i].pixelformat == f->fmt.sdr.pixelformat) {
+			f->fmt.sdr.buffersize = formats[i].buffersize;
+			return 0;
+		}
+	}
+
+	f->fmt.sdr.pixelformat = formats[0].pixelformat;
+	f->fmt.sdr.buffersize = formats[0].buffersize;
+
+	return 0;
+}
+
+static int hackrf_enum_fmt_sdr_cap(struct file *file, void *priv,
+		struct v4l2_fmtdesc *f)
+{
+	struct hackrf_dev *dev = video_drvdata(file);
+
+	dev_dbg(dev->dev, "index=%d\n", f->index);
+
+	if (f->index >= NUM_FORMATS)
+		return -EINVAL;
+
+	strlcpy(f->description, formats[f->index].name, sizeof(f->description));
+	f->pixelformat = formats[f->index].pixelformat;
+
+	return 0;
+}
+
+static int hackrf_s_tuner(struct file *file, void *priv,
+		const struct v4l2_tuner *v)
+{
+	struct hackrf_dev *dev = video_drvdata(file);
+	int ret;
+
+	dev_dbg(dev->dev, "index=%d\n", v->index);
+
+	if (v->index == 0)
+		ret = 0;
+	else if (v->index == 1)
+		ret = 0;
+	else
+		ret = -EINVAL;
+
+	return ret;
+}
+
+static int hackrf_g_tuner(struct file *file, void *priv, struct v4l2_tuner *v)
+{
+	struct hackrf_dev *dev = video_drvdata(file);
+	int ret;
+
+	dev_dbg(dev->dev, "index=%d\n", v->index);
+
+	if (v->index == 0) {
+		strlcpy(v->name, "HackRF ADC", sizeof(v->name));
+		v->type = V4L2_TUNER_ADC;
+		v->capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS;
+		v->rangelow  = bands_adc[0].rangelow;
+		v->rangehigh = bands_adc[0].rangehigh;
+		ret = 0;
+	} else if (v->index == 1) {
+		strlcpy(v->name, "HackRF RF", sizeof(v->name));
+		v->type = V4L2_TUNER_RF;
+		v->capability = V4L2_TUNER_CAP_1HZ | V4L2_TUNER_CAP_FREQ_BANDS;
+		v->rangelow  = bands_rf[0].rangelow;
+		v->rangehigh = bands_rf[0].rangehigh;
+		ret = 0;
+	} else {
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int hackrf_s_frequency(struct file *file, void *priv,
+		const struct v4l2_frequency *f)
+{
+	struct hackrf_dev *dev = video_drvdata(file);
+	int ret;
+	unsigned int upper, lower;
+	u8 buf[8];
+
+	dev_dbg(dev->dev, "tuner=%d type=%d frequency=%u\n",
+			f->tuner, f->type, f->frequency);
+
+	if (f->tuner == 0) {
+		dev->f_adc = clamp_t(unsigned int, f->frequency,
+				bands_adc[0].rangelow, bands_adc[0].rangehigh);
+		dev_dbg(dev->dev, "ADC frequency=%u Hz\n", dev->f_adc);
+		upper = dev->f_adc;
+		lower = 1;
+		buf[0] = (upper >>  0) & 0xff;
+		buf[1] = (upper >>  8) & 0xff;
+		buf[2] = (upper >> 16) & 0xff;
+		buf[3] = (upper >> 24) & 0xff;
+		buf[4] = (lower >>  0) & 0xff;
+		buf[5] = (lower >>  8) & 0xff;
+		buf[6] = (lower >> 16) & 0xff;
+		buf[7] = (lower >> 24) & 0xff;
+		ret = hackrf_ctrl_msg(dev, CMD_SAMPLE_RATE_SET, 0, 0, buf, 8);
+	} else if (f->tuner == 1) {
+		dev->f_rf = clamp_t(unsigned int, f->frequency,
+				bands_rf[0].rangelow, bands_rf[0].rangehigh);
+		dev_dbg(dev->dev, "RF frequency=%u Hz\n", dev->f_rf);
+		upper = dev->f_rf / 1000000;
+		lower = dev->f_rf % 1000000;
+		buf[0] = (upper >>  0) & 0xff;
+		buf[1] = (upper >>  8) & 0xff;
+		buf[2] = (upper >> 16) & 0xff;
+		buf[3] = (upper >> 24) & 0xff;
+		buf[4] = (lower >>  0) & 0xff;
+		buf[5] = (lower >>  8) & 0xff;
+		buf[6] = (lower >> 16) & 0xff;
+		buf[7] = (lower >> 24) & 0xff;
+		ret = hackrf_ctrl_msg(dev, CMD_SET_FREQ, 0, 0, buf, 8);
+	} else {
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int hackrf_g_frequency(struct file *file, void *priv,
+		struct v4l2_frequency *f)
+{
+	struct hackrf_dev *dev = video_drvdata(file);
+	int ret;
+
+	dev_dbg(dev->dev, "tuner=%d type=%d\n", f->tuner, f->type);
+
+	if (f->tuner == 0) {
+		f->type = V4L2_TUNER_ADC;
+		f->frequency = dev->f_adc;
+		ret = 0;
+	} else if (f->tuner == 1) {
+		f->type = V4L2_TUNER_RF;
+		f->frequency = dev->f_rf;
+		ret = 0;
+	} else {
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int hackrf_enum_freq_bands(struct file *file, void *priv,
+		struct v4l2_frequency_band *band)
+{
+	struct hackrf_dev *dev = video_drvdata(file);
+	int ret;
+
+	dev_dbg(dev->dev, "tuner=%d type=%d index=%d\n",
+			band->tuner, band->type, band->index);
+
+	if (band->tuner == 0) {
+		if (band->index >= ARRAY_SIZE(bands_adc)) {
+			ret = -EINVAL;
+		} else {
+			*band = bands_adc[band->index];
+			ret = 0;
+		}
+	} else if (band->tuner == 1) {
+		if (band->index >= ARRAY_SIZE(bands_rf)) {
+			ret = -EINVAL;
+		} else {
+			*band = bands_rf[band->index];
+			ret = 0;
+		}
+	} else {
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static const struct v4l2_ioctl_ops hackrf_ioctl_ops = {
+	.vidioc_querycap          = hackrf_querycap,
+
+	.vidioc_s_fmt_sdr_cap     = hackrf_s_fmt_sdr_cap,
+	.vidioc_g_fmt_sdr_cap     = hackrf_g_fmt_sdr_cap,
+	.vidioc_enum_fmt_sdr_cap  = hackrf_enum_fmt_sdr_cap,
+	.vidioc_try_fmt_sdr_cap   = hackrf_try_fmt_sdr_cap,
+
+	.vidioc_reqbufs           = vb2_ioctl_reqbufs,
+	.vidioc_create_bufs       = vb2_ioctl_create_bufs,
+	.vidioc_prepare_buf       = vb2_ioctl_prepare_buf,
+	.vidioc_querybuf          = vb2_ioctl_querybuf,
+	.vidioc_qbuf              = vb2_ioctl_qbuf,
+	.vidioc_dqbuf             = vb2_ioctl_dqbuf,
+
+	.vidioc_streamon          = vb2_ioctl_streamon,
+	.vidioc_streamoff         = vb2_ioctl_streamoff,
+
+	.vidioc_s_tuner           = hackrf_s_tuner,
+	.vidioc_g_tuner           = hackrf_g_tuner,
+
+	.vidioc_s_frequency       = hackrf_s_frequency,
+	.vidioc_g_frequency       = hackrf_g_frequency,
+	.vidioc_enum_freq_bands   = hackrf_enum_freq_bands,
+
+	.vidioc_subscribe_event   = v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
+	.vidioc_log_status        = v4l2_ctrl_log_status,
+};
+
+static const struct v4l2_file_operations hackrf_fops = {
+	.owner                    = THIS_MODULE,
+	.open                     = v4l2_fh_open,
+	.release                  = vb2_fop_release,
+	.read                     = vb2_fop_read,
+	.poll                     = vb2_fop_poll,
+	.mmap                     = vb2_fop_mmap,
+	.unlocked_ioctl           = video_ioctl2,
+};
+
+static struct video_device hackrf_template = {
+	.name                     = "HackRF One",
+	.release                  = video_device_release_empty,
+	.fops                     = &hackrf_fops,
+	.ioctl_ops                = &hackrf_ioctl_ops,
+};
+
+static void hackrf_video_release(struct v4l2_device *v)
+{
+	struct hackrf_dev *dev = container_of(v, struct hackrf_dev, v4l2_dev);
+
+	v4l2_ctrl_handler_free(&dev->hdl);
+	v4l2_device_unregister(&dev->v4l2_dev);
+	kfree(dev);
+}
+
+static int hackrf_set_bandwidth(struct hackrf_dev *dev)
+{
+	int ret, i;
+	u16 u16tmp, u16tmp2;
+	unsigned int bandwidth;
+
+	static const struct {
+		u32 freq;
+	} bandwidth_lut[] = {
+		{ 1750000}, /*  1.75 MHz */
+		{ 2500000}, /*  2.5  MHz */
+		{ 3500000}, /*  3.5  MHz */
+		{ 5000000}, /*  5    MHz */
+		{ 5500000}, /*  5.5  MHz */
+		{ 6000000}, /*  6    MHz */
+		{ 7000000}, /*  7    MHz */
+		{ 8000000}, /*  8    MHz */
+		{ 9000000}, /*  9    MHz */
+		{10000000}, /* 10    MHz */
+		{12000000}, /* 12    MHz */
+		{14000000}, /* 14    MHz */
+		{15000000}, /* 15    MHz */
+		{20000000}, /* 20    MHz */
+		{24000000}, /* 24    MHz */
+		{28000000}, /* 28    MHz */
+	};
+
+	dev_dbg(dev->dev, "bandwidth auto=%d->%d val=%d->%d f_adc=%u\n",
+			dev->bandwidth_auto->cur.val,
+			dev->bandwidth_auto->val, dev->bandwidth->cur.val,
+			dev->bandwidth->val, dev->f_adc);
+
+	if (dev->bandwidth_auto->val == true)
+		bandwidth = dev->f_adc;
+	else
+		bandwidth = dev->bandwidth->val;
+
+	for (i = 0; i < ARRAY_SIZE(bandwidth_lut); i++) {
+		if (bandwidth <= bandwidth_lut[i].freq) {
+			bandwidth = bandwidth_lut[i].freq;
+			break;
+		}
+	}
+
+	dev->bandwidth->val = bandwidth;
+	dev->bandwidth->cur.val = bandwidth;
+
+	dev_dbg(dev->dev, "bandwidth selected=%d\n", bandwidth_lut[i].freq);
+
+	u16tmp = 0;
+	u16tmp |= ((bandwidth >> 0) & 0xff) << 0;
+	u16tmp |= ((bandwidth >> 8) & 0xff) << 8;
+	u16tmp2 = 0;
+	u16tmp2 |= ((bandwidth >> 16) & 0xff) << 0;
+	u16tmp2 |= ((bandwidth >> 24) & 0xff) << 8;
+
+	ret = hackrf_ctrl_msg(dev, CMD_BASEBAND_FILTER_BANDWIDTH_SET,
+				u16tmp, u16tmp2, NULL, 0);
+	if (ret)
+		dev_dbg(dev->dev, "failed=%d\n", ret);
+
+	return ret;
+}
+
+static int hackrf_set_lna_gain(struct hackrf_dev *dev)
+{
+	int ret;
+	u8 u8tmp;
+
+	dev_dbg(dev->dev, "lna val=%d->%d\n",
+			dev->lna_gain->cur.val, dev->lna_gain->val);
+
+	ret = hackrf_ctrl_msg(dev, CMD_SET_LNA_GAIN, 0, dev->lna_gain->val,
+			&u8tmp, 1);
+	if (ret)
+		dev_dbg(dev->dev, "failed=%d\n", ret);
+
+	return ret;
+}
+
+static int hackrf_set_if_gain(struct hackrf_dev *dev)
+{
+	int ret;
+	u8 u8tmp;
+
+	dev_dbg(dev->dev, "val=%d->%d\n",
+			dev->if_gain->cur.val, dev->if_gain->val);
+
+	ret = hackrf_ctrl_msg(dev, CMD_SET_VGA_GAIN, 0, dev->if_gain->val,
+			&u8tmp, 1);
+	if (ret)
+		dev_dbg(dev->dev, "failed=%d\n", ret);
+
+	return ret;
+}
+
+static int hackrf_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct hackrf_dev *dev = container_of(ctrl->handler,
+			struct hackrf_dev, hdl);
+	int ret;
+
+	switch (ctrl->id) {
+	case V4L2_CID_RF_TUNER_BANDWIDTH_AUTO:
+	case V4L2_CID_RF_TUNER_BANDWIDTH:
+		ret = hackrf_set_bandwidth(dev);
+		break;
+	case  V4L2_CID_RF_TUNER_LNA_GAIN:
+		ret = hackrf_set_lna_gain(dev);
+		break;
+	case  V4L2_CID_RF_TUNER_IF_GAIN:
+		ret = hackrf_set_if_gain(dev);
+		break;
+	default:
+		dev_dbg(dev->dev, "unknown ctrl: id=%d name=%s\n",
+				ctrl->id, ctrl->name);
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static const struct v4l2_ctrl_ops hackrf_ctrl_ops = {
+	.s_ctrl = hackrf_s_ctrl,
+};
+
+static int hackrf_probe(struct usb_interface *intf,
+		const struct usb_device_id *id)
+{
+	struct hackrf_dev *dev;
+	int ret;
+	u8 u8tmp, buf[BUF_SIZE];
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (dev == NULL)
+		return -ENOMEM;
+
+	mutex_init(&dev->v4l2_lock);
+	mutex_init(&dev->vb_queue_lock);
+	spin_lock_init(&dev->queued_bufs_lock);
+	INIT_LIST_HEAD(&dev->queued_bufs);
+	dev->dev = &intf->dev;
+	dev->udev = interface_to_usbdev(intf);
+	dev->f_adc = bands_adc[0].rangelow;
+	dev->f_rf = bands_rf[0].rangelow;
+	dev->pixelformat = formats[0].pixelformat;
+	dev->buffersize = formats[0].buffersize;
+
+	/* Detect device */
+	ret = hackrf_ctrl_msg(dev, CMD_BOARD_ID_READ, 0, 0, &u8tmp, 1);
+	if (ret == 0)
+		ret = hackrf_ctrl_msg(dev, CMD_VERSION_STRING_READ, 0, 0,
+				buf, BUF_SIZE);
+	if (ret) {
+		dev_err(dev->dev, "Could not detect board\n");
+		goto err_free_mem;
+	}
+
+	buf[BUF_SIZE - 1] = '\0';
+
+	dev_info(dev->dev, "Board ID: %02x\n", u8tmp);
+	dev_info(dev->dev, "Firmware version: %s\n", buf);
+
+	/* Init videobuf2 queue structure */
+	dev->vb_queue.type = V4L2_BUF_TYPE_SDR_CAPTURE;
+	dev->vb_queue.io_modes = VB2_MMAP | VB2_USERPTR | VB2_READ;
+	dev->vb_queue.drv_priv = dev;
+	dev->vb_queue.buf_struct_size = sizeof(struct hackrf_frame_buf);
+	dev->vb_queue.ops = &hackrf_vb2_ops;
+	dev->vb_queue.mem_ops = &vb2_vmalloc_memops;
+	dev->vb_queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	ret = vb2_queue_init(&dev->vb_queue);
+	if (ret) {
+		dev_err(dev->dev, "Could not initialize vb2 queue\n");
+		goto err_free_mem;
+	}
+
+	/* Init video_device structure */
+	dev->vdev = hackrf_template;
+	dev->vdev.queue = &dev->vb_queue;
+	dev->vdev.queue->lock = &dev->vb_queue_lock;
+	video_set_drvdata(&dev->vdev, dev);
+
+	/* Register the v4l2_device structure */
+	dev->v4l2_dev.release = hackrf_video_release;
+	ret = v4l2_device_register(&intf->dev, &dev->v4l2_dev);
+	if (ret) {
+		dev_err(dev->dev, "Failed to register v4l2-device (%d)\n", ret);
+		goto err_free_mem;
+	}
+
+	/* Register controls */
+	v4l2_ctrl_handler_init(&dev->hdl, 4);
+	dev->bandwidth_auto = v4l2_ctrl_new_std(&dev->hdl, &hackrf_ctrl_ops,
+			V4L2_CID_RF_TUNER_BANDWIDTH_AUTO, 0, 1, 1, 1);
+	dev->bandwidth = v4l2_ctrl_new_std(&dev->hdl, &hackrf_ctrl_ops,
+			V4L2_CID_RF_TUNER_BANDWIDTH,
+			1750000, 28000000, 50000, 1750000);
+	v4l2_ctrl_auto_cluster(2, &dev->bandwidth_auto, 0, false);
+	dev->lna_gain = v4l2_ctrl_new_std(&dev->hdl, &hackrf_ctrl_ops,
+			V4L2_CID_RF_TUNER_LNA_GAIN, 0, 40, 8, 0);
+	dev->if_gain = v4l2_ctrl_new_std(&dev->hdl, &hackrf_ctrl_ops,
+			V4L2_CID_RF_TUNER_IF_GAIN, 0, 62, 2, 0);
+	if (dev->hdl.error) {
+		ret = dev->hdl.error;
+		dev_err(dev->dev, "Could not initialize controls\n");
+		goto err_free_controls;
+	}
+
+	v4l2_ctrl_handler_setup(&dev->hdl);
+
+	dev->v4l2_dev.ctrl_handler = &dev->hdl;
+	dev->vdev.v4l2_dev = &dev->v4l2_dev;
+	dev->vdev.lock = &dev->v4l2_lock;
+
+	ret = video_register_device(&dev->vdev, VFL_TYPE_SDR, -1);
+	if (ret) {
+		dev_err(dev->dev, "Failed to register as video device (%d)\n",
+				ret);
+		goto err_unregister_v4l2_dev;
+	}
+	dev_info(dev->dev, "Registered as %s\n",
+			video_device_node_name(&dev->vdev));
+	dev_notice(dev->dev, "SDR API is still slightly experimental and functionality changes may follow\n");
+	return 0;
+
+err_free_controls:
+	v4l2_ctrl_handler_free(&dev->hdl);
+err_unregister_v4l2_dev:
+	v4l2_device_unregister(&dev->v4l2_dev);
+err_free_mem:
+	kfree(dev);
+	return ret;
+}
+
+/* USB device ID list */
+static struct usb_device_id hackrf_id_table[] = {
+	{ USB_DEVICE(0x1d50, 0x6089) }, /* HackRF One */
+	{ }
+};
+MODULE_DEVICE_TABLE(usb, hackrf_id_table);
+
+/* USB subsystem interface */
+static struct usb_driver hackrf_driver = {
+	.name                     = KBUILD_MODNAME,
+	.probe                    = hackrf_probe,
+	.disconnect               = hackrf_disconnect,
+	.id_table                 = hackrf_id_table,
+};
+
+module_usb_driver(hackrf_driver);
+
+MODULE_AUTHOR("Antti Palosaari <crope@iki.fi>");
+MODULE_DESCRIPTION("HackRF");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/usb/hdpvr/hdpvr-control.c b/drivers/media/usb/hdpvr/hdpvr-control.c
index 6053661dc04b..6e86032ea5db 100644
--- a/drivers/media/usb/hdpvr/hdpvr-control.c
+++ b/drivers/media/usb/hdpvr/hdpvr-control.c
@@ -59,13 +59,10 @@ int get_video_info(struct hdpvr_device *dev, struct hdpvr_video_info *vidinf)
 			      1000);
 
 #ifdef HDPVR_DEBUG
-	if (hdpvr_debug & MSG_INFO) {
-		char print_buf[15];
-		hex_dump_to_buffer(dev->usbc_buf, 5, 16, 1, print_buf,
-				   sizeof(print_buf), 0);
+	if (hdpvr_debug & MSG_INFO)
 		v4l2_dbg(MSG_INFO, hdpvr_debug, &dev->v4l2_dev,
-			 "get video info returned: %d, %s\n", ret, print_buf);
-	}
+			 "get video info returned: %d, %5ph\n", ret,
+			 dev->usbc_buf);
 #endif
 	mutex_unlock(&dev->usbc_mutex);
 
@@ -82,9 +79,6 @@ int get_video_info(struct hdpvr_device *dev, struct hdpvr_video_info *vidinf)
 
 int get_input_lines_info(struct hdpvr_device *dev)
 {
-#ifdef HDPVR_DEBUG
-	char print_buf[9];
-#endif
 	int ret, lines;
 
 	mutex_lock(&dev->usbc_mutex);
@@ -96,13 +90,10 @@ int get_input_lines_info(struct hdpvr_device *dev)
 			      1000);
 
 #ifdef HDPVR_DEBUG
-	if (hdpvr_debug & MSG_INFO) {
-		hex_dump_to_buffer(dev->usbc_buf, 3, 16, 1, print_buf,
-				   sizeof(print_buf), 0);
+	if (hdpvr_debug & MSG_INFO)
 		v4l2_dbg(MSG_INFO, hdpvr_debug, &dev->v4l2_dev,
-			 "get input lines info returned: %d, %s\n", ret,
-			 print_buf);
-	}
+			 "get input lines info returned: %d, %3ph\n", ret,
+			 dev->usbc_buf);
 #else
 	(void)ret;	/* suppress compiler warning */
 #endif
diff --git a/drivers/media/usb/hdpvr/hdpvr-core.c b/drivers/media/usb/hdpvr/hdpvr-core.c
index c5638964c3f2..42b4cdf28cfd 100644
--- a/drivers/media/usb/hdpvr/hdpvr-core.c
+++ b/drivers/media/usb/hdpvr/hdpvr-core.c
@@ -124,14 +124,6 @@ static int device_authorization(struct hdpvr_device *dev)
 	int ret, retval = -ENOMEM;
 	char request_type = 0x38, rcv_request = 0x81;
 	char *response;
-#ifdef HDPVR_DEBUG
-	size_t buf_size = 46;
-	char *print_buf = kzalloc(5*buf_size+1, GFP_KERNEL);
-	if (!print_buf) {
-		v4l2_err(&dev->v4l2_dev, "Out of memory\n");
-		return retval;
-	}
-#endif
 
 	mutex_lock(&dev->usbc_mutex);
 	ret = usb_control_msg(dev->udev,
@@ -147,11 +139,9 @@ static int device_authorization(struct hdpvr_device *dev)
 	}
 #ifdef HDPVR_DEBUG
 	else {
-		hex_dump_to_buffer(dev->usbc_buf, 46, 16, 1, print_buf,
-				   5*buf_size+1, 0);
 		v4l2_dbg(MSG_INFO, hdpvr_debug, &dev->v4l2_dev,
-			 "Status request returned, len %d: %s\n",
-			 ret, print_buf);
+			 "Status request returned, len %d: %46ph\n",
+			 ret, dev->usbc_buf);
 	}
 #endif
 
@@ -189,15 +179,13 @@ static int device_authorization(struct hdpvr_device *dev)
 
 	response = dev->usbc_buf+38;
 #ifdef HDPVR_DEBUG
-	hex_dump_to_buffer(response, 8, 16, 1, print_buf, 5*buf_size+1, 0);
-	v4l2_dbg(MSG_INFO, hdpvr_debug, &dev->v4l2_dev, "challenge: %s\n",
-		 print_buf);
+	v4l2_dbg(MSG_INFO, hdpvr_debug, &dev->v4l2_dev, "challenge: %8ph\n",
+		 response);
 #endif
 	challenge(response);
 #ifdef HDPVR_DEBUG
-	hex_dump_to_buffer(response, 8, 16, 1, print_buf, 5*buf_size+1, 0);
-	v4l2_dbg(MSG_INFO, hdpvr_debug, &dev->v4l2_dev, " response: %s\n",
-		 print_buf);
+	v4l2_dbg(MSG_INFO, hdpvr_debug, &dev->v4l2_dev, " response: %8ph\n",
+		 response);
 #endif
 
 	msleep(100);
@@ -213,9 +201,6 @@ static int device_authorization(struct hdpvr_device *dev)
 	retval = ret != 8;
 unlock:
 	mutex_unlock(&dev->usbc_mutex);
-#ifdef HDPVR_DEBUG
-	kfree(print_buf);
-#endif
 	return retval;
 }
 
diff --git a/drivers/media/usb/msi2500/msi2500.c b/drivers/media/usb/msi2500/msi2500.c
index 26b133414032..efc761c78f72 100644
--- a/drivers/media/usb/msi2500/msi2500.c
+++ b/drivers/media/usb/msi2500/msi2500.c
@@ -120,6 +120,7 @@ struct msi2500_frame_buf {
 };
 
 struct msi2500_state {
+	struct device *dev;
 	struct video_device vdev;
 	struct v4l2_device v4l2_dev;
 	struct v4l2_subdev *v4l2_subdev;
@@ -153,14 +154,13 @@ struct msi2500_state {
 	u32 next_sample; /* for track lost packets */
 	u32 sample; /* for sample rate calc */
 	unsigned long jiffies_next;
-	unsigned int sample_ctrl_bit[4];
 };
 
 /* Private functions */
 static struct msi2500_frame_buf *msi2500_get_next_fill_buf(
 		struct msi2500_state *s)
 {
-	unsigned long flags = 0;
+	unsigned long flags;
 	struct msi2500_frame_buf *buf = NULL;
 
 	spin_lock_irqsave(&s->queued_bufs_lock, flags);
@@ -269,7 +269,7 @@ static int msi2500_convert_stream(struct msi2500_state *s, u8 *dst, u8 *src,
 		sample[i] = src[3] << 24 | src[2] << 16 | src[1] << 8 |
 				src[0] << 0;
 		if (i == 0 && s->next_sample != sample[0]) {
-			dev_dbg_ratelimited(&s->udev->dev,
+			dev_dbg_ratelimited(s->dev,
 					"%d samples lost, %d %08x:%08x\n",
 					sample[0] - s->next_sample,
 					src_len, s->next_sample, sample[0]);
@@ -279,7 +279,7 @@ static int msi2500_convert_stream(struct msi2500_state *s, u8 *dst, u8 *src,
 		 * Dump all unknown 'garbage' data - maybe we will discover
 		 * someday if there is something rational...
 		 */
-		dev_dbg_ratelimited(&s->udev->dev, "%*ph\n", 12, &src[4]);
+		dev_dbg_ratelimited(s->dev, "%*ph\n", 12, &src[4]);
 
 		src += 16; /* skip header */
 
@@ -322,8 +322,7 @@ static int msi2500_convert_stream(struct msi2500_state *s, u8 *dst, u8 *src,
 		}
 		case MSI2500_PIX_FMT_SDR_MSI2500_384: /* 384 x IQ samples */
 			/* Dump unknown 'garbage' data */
-			dev_dbg_ratelimited(&s->udev->dev,
-					"%*ph\n", 24, &src[1000]);
+			dev_dbg_ratelimited(s->dev, "%*ph\n", 24, &src[1000]);
 			memcpy(dst, src, 984);
 			src += 984 + 24;
 			dst += 984;
@@ -365,8 +364,7 @@ static int msi2500_convert_stream(struct msi2500_state *s, u8 *dst, u8 *src,
 
 		s->jiffies_next = jiffies + msecs_to_jiffies(MSECS);
 		s->sample = s->next_sample;
-		dev_dbg(&s->udev->dev,
-				"size=%u samples=%u msecs=%u sample rate=%lu\n",
+		dev_dbg(s->dev, "size=%u samples=%u msecs=%u sample rate=%lu\n",
 				src_len, samples, msecs,
 				samples * 1000UL / msecs);
 	}
@@ -387,19 +385,16 @@ static void msi2500_isoc_handler(struct urb *urb)
 
 	if (unlikely(urb->status == -ENOENT || urb->status == -ECONNRESET ||
 			urb->status == -ESHUTDOWN)) {
-		dev_dbg(&s->udev->dev, "URB (%p) unlinked %ssynchronuously\n",
+		dev_dbg(s->dev, "URB (%p) unlinked %ssynchronuously\n",
 				urb, urb->status == -ENOENT ? "" : "a");
 		return;
 	}
 
 	if (unlikely(urb->status != 0)) {
-		dev_dbg(&s->udev->dev,
-				"msi2500_isoc_handler() called with status %d\n",
-				urb->status);
+		dev_dbg(s->dev, "called with status %d\n", urb->status);
 		/* Give up after a number of contiguous errors */
 		if (++s->isoc_errors > MAX_ISOC_ERRORS)
-			dev_dbg(&s->udev->dev,
-					"Too many ISOC errors, bailing out\n");
+			dev_dbg(s->dev, "Too many ISOC errors, bailing out\n");
 		goto handler_end;
 	} else {
 		/* Reset ISOC error counter. We did get here, after all. */
@@ -413,7 +408,7 @@ static void msi2500_isoc_handler(struct urb *urb)
 		/* Check frame error */
 		fstatus = urb->iso_frame_desc[i].status;
 		if (unlikely(fstatus)) {
-			dev_dbg_ratelimited(&s->udev->dev,
+			dev_dbg_ratelimited(s->dev,
 					"frame=%d/%d has error %d skipping\n",
 					i, urb->number_of_packets, fstatus);
 			continue;
@@ -430,7 +425,7 @@ static void msi2500_isoc_handler(struct urb *urb)
 		fbuf = msi2500_get_next_fill_buf(s);
 		if (unlikely(fbuf == NULL)) {
 			s->vb_full++;
-			dev_dbg_ratelimited(&s->udev->dev,
+			dev_dbg_ratelimited(s->dev,
 					"videobuf is full, %d packets dropped\n",
 					s->vb_full);
 			continue;
@@ -446,22 +441,19 @@ static void msi2500_isoc_handler(struct urb *urb)
 handler_end:
 	i = usb_submit_urb(urb, GFP_ATOMIC);
 	if (unlikely(i != 0))
-		dev_dbg(&s->udev->dev,
-				"Error (%d) re-submitting urb in msi2500_isoc_handler\n",
-				i);
+		dev_dbg(s->dev, "Error (%d) re-submitting urb\n", i);
 }
 
 static void msi2500_iso_stop(struct msi2500_state *s)
 {
 	int i;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	/* Unlinking ISOC buffers one by one */
 	for (i = 0; i < MAX_ISO_BUFS; i++) {
 		if (s->urbs[i]) {
-			dev_dbg(&s->udev->dev, "Unlinking URB %p\n",
-					s->urbs[i]);
+			dev_dbg(s->dev, "Unlinking URB %p\n", s->urbs[i]);
 			usb_kill_urb(s->urbs[i]);
 		}
 	}
@@ -471,12 +463,12 @@ static void msi2500_iso_free(struct msi2500_state *s)
 {
 	int i;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	/* Freeing ISOC buffers one by one */
 	for (i = 0; i < MAX_ISO_BUFS; i++) {
 		if (s->urbs[i]) {
-			dev_dbg(&s->udev->dev, "Freeing URB\n");
+			dev_dbg(s->dev, "Freeing URB\n");
 			if (s->urbs[i]->transfer_buffer) {
 				usb_free_coherent(s->udev,
 					s->urbs[i]->transfer_buffer_length,
@@ -492,7 +484,7 @@ static void msi2500_iso_free(struct msi2500_state *s)
 /* Both v4l2_lock and vb_queue_lock should be locked when calling this */
 static void msi2500_isoc_cleanup(struct msi2500_state *s)
 {
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	msi2500_iso_stop(s);
 	msi2500_iso_free(s);
@@ -501,14 +493,12 @@ static void msi2500_isoc_cleanup(struct msi2500_state *s)
 /* Both v4l2_lock and vb_queue_lock should be locked when calling this */
 static int msi2500_isoc_init(struct msi2500_state *s)
 {
-	struct usb_device *udev;
 	struct urb *urb;
 	int i, j, ret;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	s->isoc_errors = 0;
-	udev = s->udev;
 
 	ret = usb_set_interface(s->udev, 0, 1);
 	if (ret)
@@ -518,23 +508,22 @@ static int msi2500_isoc_init(struct msi2500_state *s)
 	for (i = 0; i < MAX_ISO_BUFS; i++) {
 		urb = usb_alloc_urb(ISO_FRAMES_PER_DESC, GFP_KERNEL);
 		if (urb == NULL) {
-			dev_err(&s->udev->dev,
-					"Failed to allocate urb %d\n", i);
+			dev_err(s->dev, "Failed to allocate urb %d\n", i);
 			msi2500_isoc_cleanup(s);
 			return -ENOMEM;
 		}
 		s->urbs[i] = urb;
-		dev_dbg(&s->udev->dev, "Allocated URB at 0x%p\n", urb);
+		dev_dbg(s->dev, "Allocated URB at 0x%p\n", urb);
 
 		urb->interval = 1;
-		urb->dev = udev;
-		urb->pipe = usb_rcvisocpipe(udev, 0x81);
+		urb->dev = s->udev;
+		urb->pipe = usb_rcvisocpipe(s->udev, 0x81);
 		urb->transfer_flags = URB_ISO_ASAP | URB_NO_TRANSFER_DMA_MAP;
-		urb->transfer_buffer = usb_alloc_coherent(udev, ISO_BUFFER_SIZE,
+		urb->transfer_buffer = usb_alloc_coherent(s->udev,
+				ISO_BUFFER_SIZE,
 				GFP_KERNEL, &urb->transfer_dma);
 		if (urb->transfer_buffer == NULL) {
-			dev_err(&s->udev->dev,
-					"Failed to allocate urb buffer %d\n",
+			dev_err(s->dev, "Failed to allocate urb buffer %d\n",
 					i);
 			msi2500_isoc_cleanup(s);
 			return -ENOMEM;
@@ -554,13 +543,12 @@ static int msi2500_isoc_init(struct msi2500_state *s)
 	for (i = 0; i < MAX_ISO_BUFS; i++) {
 		ret = usb_submit_urb(s->urbs[i], GFP_KERNEL);
 		if (ret) {
-			dev_err(&s->udev->dev,
-					"isoc_init() submit_urb %d failed with error %d\n",
+			dev_err(s->dev, "usb_submit_urb %d failed with error %d\n",
 					i, ret);
 			msi2500_isoc_cleanup(s);
 			return ret;
 		}
-		dev_dbg(&s->udev->dev, "URB 0x%p submitted.\n", s->urbs[i]);
+		dev_dbg(s->dev, "URB 0x%p submitted.\n", s->urbs[i]);
 	}
 
 	/* All is done... */
@@ -570,9 +558,9 @@ static int msi2500_isoc_init(struct msi2500_state *s)
 /* Must be called with vb_queue_lock hold */
 static void msi2500_cleanup_queued_bufs(struct msi2500_state *s)
 {
-	unsigned long flags = 0;
+	unsigned long flags;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	spin_lock_irqsave(&s->queued_bufs_lock, flags);
 	while (!list_empty(&s->queued_bufs)) {
@@ -593,7 +581,7 @@ static void msi2500_disconnect(struct usb_interface *intf)
 	struct msi2500_state *s =
 			container_of(v, struct msi2500_state, v4l2_dev);
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	mutex_lock(&s->vb_queue_lock);
 	mutex_lock(&s->v4l2_lock);
@@ -613,7 +601,7 @@ static int msi2500_querycap(struct file *file, void *fh,
 {
 	struct msi2500_state *s = video_drvdata(file);
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	strlcpy(cap->driver, KBUILD_MODNAME, sizeof(cap->driver));
 	strlcpy(cap->card, s->vdev.name, sizeof(cap->card));
@@ -631,14 +619,13 @@ static int msi2500_queue_setup(struct vb2_queue *vq,
 {
 	struct msi2500_state *s = vb2_get_drv_priv(vq);
 
-	dev_dbg(&s->udev->dev, "%s: *nbuffers=%d\n", __func__, *nbuffers);
+	dev_dbg(s->dev, "nbuffers=%d\n", *nbuffers);
 
 	/* Absolute min and max number of buffers available for mmap() */
 	*nbuffers = clamp_t(unsigned int, *nbuffers, 8, 32);
 	*nplanes = 1;
 	sizes[0] = PAGE_ALIGN(s->buffersize);
-	dev_dbg(&s->udev->dev, "%s: nbuffers=%d sizes[0]=%d\n",
-			__func__, *nbuffers, sizes[0]);
+	dev_dbg(s->dev, "nbuffers=%d sizes[0]=%d\n", *nbuffers, sizes[0]);
 	return 0;
 }
 
@@ -647,7 +634,7 @@ static void msi2500_buf_queue(struct vb2_buffer *vb)
 	struct msi2500_state *s = vb2_get_drv_priv(vb->vb2_queue);
 	struct msi2500_frame_buf *buf =
 			container_of(vb, struct msi2500_frame_buf, vb);
-	unsigned long flags = 0;
+	unsigned long flags;
 
 	/* Check the device has not disconnected between prep and queuing */
 	if (unlikely(!s->udev)) {
@@ -665,16 +652,15 @@ static void msi2500_buf_queue(struct vb2_buffer *vb)
 #define CMD_STOP_STREAMING     0x45
 #define CMD_READ_UNKNOW        0x48
 
-#define msi2500_dbg_usb_control_msg(_udev, _r, _t, _v, _i, _b, _l) { \
+#define msi2500_dbg_usb_control_msg(_dev, _r, _t, _v, _i, _b, _l) { \
 	char *_direction; \
 	if (_t & USB_DIR_IN) \
 		_direction = "<<<"; \
 	else \
 		_direction = ">>>"; \
-	dev_dbg(&_udev->dev, "%s: %02x %02x %02x %02x %02x %02x %02x %02x " \
-			"%s %*ph\n",  __func__, _t, _r, _v & 0xff, _v >> 8, \
-			_i & 0xff, _i >> 8, _l & 0xff, _l >> 8, _direction, \
-			_l, _b); \
+	dev_dbg(_dev, "%02x %02x %02x %02x %02x %02x %02x %02x %s %*ph\n", \
+			_t, _r, _v & 0xff, _v >> 8, _i & 0xff, _i >> 8, \
+			_l & 0xff, _l >> 8, _direction, _l, _b); \
 }
 
 static int msi2500_ctrl_msg(struct msi2500_state *s, u8 cmd, u32 data)
@@ -685,18 +671,16 @@ static int msi2500_ctrl_msg(struct msi2500_state *s, u8 cmd, u32 data)
 	u16 value = (data >> 0) & 0xffff;
 	u16 index = (data >> 16) & 0xffff;
 
-	msi2500_dbg_usb_control_msg(s->udev,
+	msi2500_dbg_usb_control_msg(s->dev,
 			request, requesttype, value, index, NULL, 0);
-
 	ret = usb_control_msg(s->udev, usb_sndctrlpipe(s->udev, 0),
 			request, requesttype, value, index, NULL, 0, 2000);
-
 	if (ret)
-		dev_err(&s->udev->dev, "%s: failed %d, cmd %02x, data %04x\n",
-				__func__, ret, cmd, data);
+		dev_err(s->dev, "failed %d, cmd %02x, data %04x\n",
+				ret, cmd, data);
 
 	return ret;
-};
+}
 
 #define F_REF 24000000
 #define DIV_R_IN 2
@@ -785,8 +769,7 @@ static int msi2500_set_usb_adc(struct msi2500_state *s)
 
 	for (div_r_out = 4; div_r_out < 16; div_r_out += 2) {
 		f_vco = f_sr * div_r_out * 12;
-		dev_dbg(&s->udev->dev, "%s: div_r_out=%d f_vco=%d\n",
-				__func__, div_r_out, f_vco);
+		dev_dbg(s->dev, "div_r_out=%d f_vco=%d\n", div_r_out, f_vco);
 		if (f_vco >= 202000000)
 			break;
 	}
@@ -800,10 +783,8 @@ static int msi2500_set_usb_adc(struct msi2500_state *s)
 	reg3 |= ((fract >> 20) & 0x000001) << 15; /* [20] */
 	reg4 |= ((fract >>  0) & 0x0fffff) <<  8; /* [19:0] */
 
-	dev_dbg(&s->udev->dev,
-			"%s: f_sr=%d f_vco=%d div_n=%d div_m=%d div_r_out=%d reg3=%08x reg4=%08x\n",
-			__func__, f_sr, f_vco, div_n, div_m, div_r_out, reg3,
-			reg4);
+	dev_dbg(s->dev, "f_sr=%d f_vco=%d div_n=%d div_m=%d div_r_out=%d reg3=%08x reg4=%08x\n",
+			f_sr, f_vco, div_n, div_m, div_r_out, reg3, reg4);
 
 	ret = msi2500_ctrl_msg(s, CMD_WREG, 0x00608008);
 	if (ret)
@@ -838,14 +819,14 @@ static int msi2500_set_usb_adc(struct msi2500_state *s)
 		goto err;
 err:
 	return ret;
-};
+}
 
 static int msi2500_start_streaming(struct vb2_queue *vq, unsigned int count)
 {
 	struct msi2500_state *s = vb2_get_drv_priv(vq);
 	int ret;
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	if (!s->udev)
 		return -ENODEV;
@@ -873,7 +854,7 @@ static void msi2500_stop_streaming(struct vb2_queue *vq)
 {
 	struct msi2500_state *s = vb2_get_drv_priv(vq);
 
-	dev_dbg(&s->udev->dev, "%s:\n", __func__);
+	dev_dbg(s->dev, "\n");
 
 	mutex_lock(&s->v4l2_lock);
 
@@ -909,7 +890,7 @@ static int msi2500_enum_fmt_sdr_cap(struct file *file, void *priv,
 {
 	struct msi2500_state *s = video_drvdata(file);
 
-	dev_dbg(&s->udev->dev, "%s: index=%d\n", __func__, f->index);
+	dev_dbg(s->dev, "index=%d\n", f->index);
 
 	if (f->index >= s->num_formats)
 		return -EINVAL;
@@ -925,7 +906,7 @@ static int msi2500_g_fmt_sdr_cap(struct file *file, void *priv,
 {
 	struct msi2500_state *s = video_drvdata(file);
 
-	dev_dbg(&s->udev->dev, "%s: pixelformat fourcc %4.4s\n", __func__,
+	dev_dbg(s->dev, "pixelformat fourcc %4.4s\n",
 			(char *)&s->pixelformat);
 
 	f->fmt.sdr.pixelformat = s->pixelformat;
@@ -942,7 +923,7 @@ static int msi2500_s_fmt_sdr_cap(struct file *file, void *priv,
 	struct vb2_queue *q = &s->vb_queue;
 	int i;
 
-	dev_dbg(&s->udev->dev, "%s: pixelformat fourcc %4.4s\n", __func__,
+	dev_dbg(s->dev, "pixelformat fourcc %4.4s\n",
 			(char *)&f->fmt.sdr.pixelformat);
 
 	if (vb2_is_busy(q))
@@ -972,7 +953,7 @@ static int msi2500_try_fmt_sdr_cap(struct file *file, void *priv,
 	struct msi2500_state *s = video_drvdata(file);
 	int i;
 
-	dev_dbg(&s->udev->dev, "%s: pixelformat fourcc %4.4s\n", __func__,
+	dev_dbg(s->dev, "pixelformat fourcc %4.4s\n",
 			(char *)&f->fmt.sdr.pixelformat);
 
 	memset(f->fmt.sdr.reserved, 0, sizeof(f->fmt.sdr.reserved));
@@ -995,7 +976,7 @@ static int msi2500_s_tuner(struct file *file, void *priv,
 	struct msi2500_state *s = video_drvdata(file);
 	int ret;
 
-	dev_dbg(&s->udev->dev, "%s: index=%d\n", __func__, v->index);
+	dev_dbg(s->dev, "index=%d\n", v->index);
 
 	if (v->index == 0)
 		ret = 0;
@@ -1012,7 +993,7 @@ static int msi2500_g_tuner(struct file *file, void *priv, struct v4l2_tuner *v)
 	struct msi2500_state *s = video_drvdata(file);
 	int ret;
 
-	dev_dbg(&s->udev->dev, "%s: index=%d\n", __func__, v->index);
+	dev_dbg(s->dev, "index=%d\n", v->index);
 
 	if (v->index == 0) {
 		strlcpy(v->name, "Mirics MSi2500", sizeof(v->name));
@@ -1036,8 +1017,7 @@ static int msi2500_g_frequency(struct file *file, void *priv,
 	struct msi2500_state *s = video_drvdata(file);
 	int ret  = 0;
 
-	dev_dbg(&s->udev->dev, "%s: tuner=%d type=%d\n",
-			__func__, f->tuner, f->type);
+	dev_dbg(s->dev, "tuner=%d type=%d\n", f->tuner, f->type);
 
 	if (f->tuner == 0) {
 		f->frequency = s->f_adc;
@@ -1058,15 +1038,14 @@ static int msi2500_s_frequency(struct file *file, void *priv,
 	struct msi2500_state *s = video_drvdata(file);
 	int ret;
 
-	dev_dbg(&s->udev->dev, "%s: tuner=%d type=%d frequency=%u\n",
-			__func__, f->tuner, f->type, f->frequency);
+	dev_dbg(s->dev, "tuner=%d type=%d frequency=%u\n",
+			f->tuner, f->type, f->frequency);
 
 	if (f->tuner == 0) {
 		s->f_adc = clamp_t(unsigned int, f->frequency,
 				bands[0].rangelow,
 				bands[0].rangehigh);
-		dev_dbg(&s->udev->dev, "%s: ADC frequency=%u Hz\n",
-				__func__, s->f_adc);
+		dev_dbg(s->dev, "ADC frequency=%u Hz\n", s->f_adc);
 		ret = msi2500_set_usb_adc(s);
 	} else if (f->tuner == 1) {
 		ret = v4l2_subdev_call(s->v4l2_subdev, tuner, s_frequency, f);
@@ -1083,8 +1062,8 @@ static int msi2500_enum_freq_bands(struct file *file, void *priv,
 	struct msi2500_state *s = video_drvdata(file);
 	int ret;
 
-	dev_dbg(&s->udev->dev, "%s: tuner=%d type=%d index=%d\n",
-			__func__, band->tuner, band->type, band->index);
+	dev_dbg(s->dev, "tuner=%d type=%d index=%d\n",
+			band->tuner, band->type, band->index);
 
 	if (band->tuner == 0) {
 		if (band->index >= ARRAY_SIZE(bands)) {
@@ -1169,8 +1148,7 @@ static int msi2500_transfer_one_message(struct spi_master *master,
 	u32 data;
 
 	list_for_each_entry(t, &m->transfers, transfer_list) {
-		dev_dbg(&s->udev->dev, "%s: msg=%*ph\n",
-				__func__, t->len, t->tx_buf);
+		dev_dbg(s->dev, "msg=%*ph\n", t->len, t->tx_buf);
 		data = 0x09; /* reg 9 is SPI adapter */
 		data |= ((u8 *)t->tx_buf)[0] << 8;
 		data |= ((u8 *)t->tx_buf)[1] << 16;
@@ -1186,8 +1164,7 @@ static int msi2500_transfer_one_message(struct spi_master *master,
 static int msi2500_probe(struct usb_interface *intf,
 		const struct usb_device_id *id)
 {
-	struct usb_device *udev = interface_to_usbdev(intf);
-	struct msi2500_state *s = NULL;
+	struct msi2500_state *s;
 	struct v4l2_subdev *sd;
 	struct spi_master *master;
 	int ret;
@@ -1200,7 +1177,7 @@ static int msi2500_probe(struct usb_interface *intf,
 
 	s = kzalloc(sizeof(struct msi2500_state), GFP_KERNEL);
 	if (s == NULL) {
-		pr_err("Could not allocate memory for msi2500_state\n");
+		dev_err(&intf->dev, "Could not allocate memory for state\n");
 		return -ENOMEM;
 	}
 
@@ -1208,12 +1185,13 @@ static int msi2500_probe(struct usb_interface *intf,
 	mutex_init(&s->vb_queue_lock);
 	spin_lock_init(&s->queued_bufs_lock);
 	INIT_LIST_HEAD(&s->queued_bufs);
-	s->udev = udev;
+	s->dev = &intf->dev;
+	s->udev = interface_to_usbdev(intf);
 	s->f_adc = bands[0].rangelow;
 	s->pixelformat = formats[0].pixelformat;
 	s->buffersize = formats[0].buffersize;
 	s->num_formats = NUM_FORMATS;
-	if (msi2500_emulated_fmt == false)
+	if (!msi2500_emulated_fmt)
 		s->num_formats -= 2;
 
 	/* Init videobuf2 queue structure */
@@ -1226,7 +1204,7 @@ static int msi2500_probe(struct usb_interface *intf,
 	s->vb_queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	ret = vb2_queue_init(&s->vb_queue);
 	if (ret) {
-		dev_err(&s->udev->dev, "Could not initialize vb2 queue\n");
+		dev_err(s->dev, "Could not initialize vb2 queue\n");
 		goto err_free_mem;
 	}
 
@@ -1240,13 +1218,12 @@ static int msi2500_probe(struct usb_interface *intf,
 	s->v4l2_dev.release = msi2500_video_release;
 	ret = v4l2_device_register(&intf->dev, &s->v4l2_dev);
 	if (ret) {
-		dev_err(&s->udev->dev,
-				"Failed to register v4l2-device (%d)\n", ret);
+		dev_err(s->dev, "Failed to register v4l2-device (%d)\n", ret);
 		goto err_free_mem;
 	}
 
 	/* SPI master adapter */
-	master = spi_alloc_master(&s->udev->dev, 0);
+	master = spi_alloc_master(s->dev, 0);
 	if (master == NULL) {
 		ret = -ENOMEM;
 		goto err_unregister_v4l2_dev;
@@ -1267,7 +1244,7 @@ static int msi2500_probe(struct usb_interface *intf,
 	sd = v4l2_spi_new_subdev(&s->v4l2_dev, master, &board_info);
 	s->v4l2_subdev = sd;
 	if (sd == NULL) {
-		dev_err(&s->udev->dev, "cannot get v4l2 subdevice\n");
+		dev_err(s->dev, "cannot get v4l2 subdevice\n");
 		ret = -ENODEV;
 		goto err_unregister_master;
 	}
@@ -1276,7 +1253,7 @@ static int msi2500_probe(struct usb_interface *intf,
 	v4l2_ctrl_handler_init(&s->hdl, 0);
 	if (s->hdl.error) {
 		ret = s->hdl.error;
-		dev_err(&s->udev->dev, "Could not initialize controls\n");
+		dev_err(s->dev, "Could not initialize controls\n");
 		goto err_free_controls;
 	}
 
@@ -1289,16 +1266,13 @@ static int msi2500_probe(struct usb_interface *intf,
 
 	ret = video_register_device(&s->vdev, VFL_TYPE_SDR, -1);
 	if (ret) {
-		dev_err(&s->udev->dev,
-				"Failed to register as video device (%d)\n",
+		dev_err(s->dev, "Failed to register as video device (%d)\n",
 				ret);
 		goto err_unregister_v4l2_dev;
 	}
-	dev_info(&s->udev->dev, "Registered as %s\n",
+	dev_info(s->dev, "Registered as %s\n",
 			video_device_node_name(&s->vdev));
-	dev_notice(&s->udev->dev,
-			"%s: SDR API is still slightly experimental and functionality changes may follow\n",
-			KBUILD_MODNAME);
+	dev_notice(s->dev, "SDR API is still slightly experimental and functionality changes may follow\n");
 
 	return 0;
 
diff --git a/drivers/media/usb/pwc/pwc-v4l.c b/drivers/media/usb/pwc/pwc-v4l.c
index aa7449eaca08..3d987984602f 100644
--- a/drivers/media/usb/pwc/pwc-v4l.c
+++ b/drivers/media/usb/pwc/pwc-v4l.c
@@ -52,7 +52,7 @@ enum { custom_autocontour, custom_contour, custom_noise_reduction,
 	custom_awb_speed, custom_awb_delay,
 	custom_save_user, custom_restore_user, custom_restore_factory };
 
-const char * const pwc_auto_whitebal_qmenu[] = {
+static const char * const pwc_auto_whitebal_qmenu[] = {
 	"Indoor (Incandescant Lighting) Mode",
 	"Outdoor (Sunlight) Mode",
 	"Indoor (Fluorescent Lighting) Mode",
diff --git a/drivers/media/usb/s2255/s2255drv.c b/drivers/media/usb/s2255/s2255drv.c
index 2c901861034a..ccc00099b261 100644
--- a/drivers/media/usb/s2255/s2255drv.c
+++ b/drivers/media/usb/s2255/s2255drv.c
@@ -2245,7 +2245,7 @@ static int s2255_probe(struct usb_interface *interface,
 	}
 
 	atomic_set(&dev->num_channels, 0);
-	dev->pid = le16_to_cpu(id->idProduct);
+	dev->pid = id->idProduct;
 	dev->fw_data = kzalloc(sizeof(struct s2255_fw), GFP_KERNEL);
 	if (!dev->fw_data)
 		goto errorFWDATA1;
diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c
index 1836a416d806..94e10b10b66e 100644
--- a/drivers/media/usb/siano/smsusb.c
+++ b/drivers/media/usb/siano/smsusb.c
@@ -277,14 +277,14 @@ static int smsusb1_load_firmware(struct usb_device *udev, int id, int board_id)
 		rc = usb_bulk_msg(udev, usb_sndbulkpipe(udev, 2),
 				  fw_buffer, fw->size, &dummy, 1000);
 
-		sms_info("sent %zd(%d) bytes, rc %d", fw->size, dummy, rc);
+		sms_info("sent %zu(%d) bytes, rc %d", fw->size, dummy, rc);
 
 		kfree(fw_buffer);
 	} else {
 		sms_err("failed to allocate firmware buffer");
 		rc = -ENOMEM;
 	}
-	sms_info("read FW %s, size=%zd", fw_filename, fw->size);
+	sms_info("read FW %s, size=%zu", fw_filename, fw->size);
 
 	release_firmware(fw);
 
@@ -655,6 +655,8 @@ static const struct usb_device_id smsusb_id_table[] = {
 		.driver_info = SMS1XXX_BOARD_ONDA_MDTV_DATA_CARD },
 	{ USB_DEVICE(0x3275, 0x0080),
 		.driver_info = SMS1XXX_BOARD_SIANO_RIO },
+	{ USB_DEVICE(0x2013, 0x0257),
+		.driver_info = SMS1XXX_BOARD_PCTV_77E },
 	{ } /* Terminating entry */
 	};
 
diff --git a/drivers/media/usb/ttusb-dec/ttusbdecfe.c b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
index 5c45c9d0712d..9c29552aedec 100644
--- a/drivers/media/usb/ttusb-dec/ttusbdecfe.c
+++ b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
@@ -156,6 +156,9 @@ static int ttusbdecfe_dvbs_diseqc_send_master_cmd(struct dvb_frontend* fe, struc
 		   0x00, 0x00, 0x00, 0x00,
 		   0x00, 0x00 };
 
+	if (cmd->msg_len > sizeof(b) - 4)
+		return -EINVAL;
+
 	memcpy(&b[4], cmd->msg, cmd->msg_len);
 
 	state->config->send_command(fe, 0x72,
diff --git a/drivers/media/usb/usbtv/Kconfig b/drivers/media/usb/usbtv/Kconfig
index 7c5b86006ee6..b833c5b9094e 100644
--- a/drivers/media/usb/usbtv/Kconfig
+++ b/drivers/media/usb/usbtv/Kconfig
@@ -1,6 +1,7 @@
 config VIDEO_USBTV
         tristate "USBTV007 video capture support"
-        depends on VIDEO_V4L2
+        depends on VIDEO_V4L2 && SND
+        select SND_PCM
         select VIDEOBUF2_VMALLOC
 
         ---help---
diff --git a/drivers/media/usb/usbtv/Makefile b/drivers/media/usb/usbtv/Makefile
index 775316a88ea6..f555cf8a3dd2 100644
--- a/drivers/media/usb/usbtv/Makefile
+++ b/drivers/media/usb/usbtv/Makefile
@@ -1,4 +1,5 @@
 usbtv-y := usbtv-core.o \
-	usbtv-video.o
+	usbtv-video.o \
+	usbtv-audio.o
 
 obj-$(CONFIG_VIDEO_USBTV) += usbtv.o
diff --git a/drivers/media/usb/usbtv/usbtv-audio.c b/drivers/media/usb/usbtv/usbtv-audio.c
new file mode 100644
index 000000000000..78c12d22dfbb
--- /dev/null
+++ b/drivers/media/usb/usbtv/usbtv-audio.c
@@ -0,0 +1,385 @@
+/*
+ * Fushicai USBTV007 Audio-Video Grabber Driver
+ *
+ * Product web site:
+ * http://www.fushicai.com/products_detail/&productId=d05449ee-b690-42f9-a661-aa7353894bed.html
+ *
+ * Copyright (c) 2013 Federico Simoncelli
+ * All rights reserved.
+ * No physical hardware was harmed running Windows during the
+ * reverse-engineering activity
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. The name of the author may not be used to endorse or promote products
+ *    derived from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL").
+ */
+
+#include <sound/core.h>
+#include <sound/initval.h>
+#include <sound/ac97_codec.h>
+#include <sound/pcm_params.h>
+
+#include "usbtv.h"
+
+static struct snd_pcm_hardware snd_usbtv_digital_hw = {
+	.info = SNDRV_PCM_INFO_BATCH |
+		SNDRV_PCM_INFO_MMAP |
+		SNDRV_PCM_INFO_INTERLEAVED |
+		SNDRV_PCM_INFO_BLOCK_TRANSFER |
+		SNDRV_PCM_INFO_MMAP_VALID,
+	.formats = SNDRV_PCM_FMTBIT_S16_LE,
+	.rates = SNDRV_PCM_RATE_48000,
+	.rate_min = 48000,
+	.rate_max = 48000,
+	.channels_min = 2,
+	.channels_max = 2,
+	.period_bytes_min = 11059,
+	.period_bytes_max = 13516,
+	.periods_min = 2,
+	.periods_max = 98,
+	.buffer_bytes_max = 62720 * 8, /* value in usbaudio.c */
+};
+
+static int snd_usbtv_pcm_open(struct snd_pcm_substream *substream)
+{
+	struct usbtv *chip = snd_pcm_substream_chip(substream);
+	struct snd_pcm_runtime *runtime = substream->runtime;
+
+	chip->snd_substream = substream;
+	runtime->hw = snd_usbtv_digital_hw;
+
+	return 0;
+}
+
+static int snd_usbtv_pcm_close(struct snd_pcm_substream *substream)
+{
+	struct usbtv *chip = snd_pcm_substream_chip(substream);
+
+	if (atomic_read(&chip->snd_stream)) {
+		atomic_set(&chip->snd_stream, 0);
+		schedule_work(&chip->snd_trigger);
+	}
+
+	return 0;
+}
+
+static int snd_usbtv_hw_params(struct snd_pcm_substream *substream,
+		struct snd_pcm_hw_params *hw_params)
+{
+	int rv;
+	struct usbtv *chip = snd_pcm_substream_chip(substream);
+
+	rv = snd_pcm_lib_malloc_pages(substream,
+		params_buffer_bytes(hw_params));
+
+	if (rv < 0) {
+		dev_warn(chip->dev, "pcm audio buffer allocation failure %i\n",
+			rv);
+		return rv;
+	}
+
+	return 0;
+}
+
+static int snd_usbtv_hw_free(struct snd_pcm_substream *substream)
+{
+	snd_pcm_lib_free_pages(substream);
+	return 0;
+}
+
+static int snd_usbtv_prepare(struct snd_pcm_substream *substream)
+{
+	struct usbtv *chip = snd_pcm_substream_chip(substream);
+
+	chip->snd_buffer_pos = 0;
+	chip->snd_period_pos = 0;
+
+	return 0;
+}
+
+static void usbtv_audio_urb_received(struct urb *urb)
+{
+	struct usbtv *chip = urb->context;
+	struct snd_pcm_substream *substream = chip->snd_substream;
+	struct snd_pcm_runtime *runtime = substream->runtime;
+	size_t i, frame_bytes, chunk_length, buffer_pos, period_pos;
+	int period_elapsed;
+	void *urb_current;
+
+	switch (urb->status) {
+	case 0:
+	case -ETIMEDOUT:
+		break;
+	case -ENOENT:
+	case -EPROTO:
+	case -ECONNRESET:
+	case -ESHUTDOWN:
+		return;
+	default:
+		dev_warn(chip->dev, "unknown audio urb status %i\n",
+			urb->status);
+	}
+
+	if (!atomic_read(&chip->snd_stream))
+		return;
+
+	frame_bytes = runtime->frame_bits >> 3;
+	chunk_length = USBTV_CHUNK / frame_bytes;
+
+	buffer_pos = chip->snd_buffer_pos;
+	period_pos = chip->snd_period_pos;
+	period_elapsed = 0;
+
+	for (i = 0; i < urb->actual_length; i += USBTV_CHUNK_SIZE) {
+		urb_current = urb->transfer_buffer + i + USBTV_AUDIO_HDRSIZE;
+
+		if (buffer_pos + chunk_length >= runtime->buffer_size) {
+			size_t cnt = (runtime->buffer_size - buffer_pos) *
+				frame_bytes;
+			memcpy(runtime->dma_area + buffer_pos * frame_bytes,
+				urb_current, cnt);
+			memcpy(runtime->dma_area, urb_current + cnt,
+				chunk_length * frame_bytes - cnt);
+		} else {
+			memcpy(runtime->dma_area + buffer_pos * frame_bytes,
+				urb_current, chunk_length * frame_bytes);
+		}
+
+		buffer_pos += chunk_length;
+		period_pos += chunk_length;
+
+		if (buffer_pos >= runtime->buffer_size)
+			buffer_pos -= runtime->buffer_size;
+
+		if (period_pos >= runtime->period_size) {
+			period_pos -= runtime->period_size;
+			period_elapsed = 1;
+		}
+	}
+
+	snd_pcm_stream_lock(substream);
+
+	chip->snd_buffer_pos = buffer_pos;
+	chip->snd_period_pos = period_pos;
+
+	snd_pcm_stream_unlock(substream);
+
+	if (period_elapsed)
+		snd_pcm_period_elapsed(substream);
+
+	usb_submit_urb(urb, GFP_ATOMIC);
+}
+
+static int usbtv_audio_start(struct usbtv *chip)
+{
+	unsigned int pipe;
+	static const u16 setup[][2] = {
+		/* These seem to enable the device. */
+		{ USBTV_BASE + 0x0008, 0x0001 },
+		{ USBTV_BASE + 0x01d0, 0x00ff },
+		{ USBTV_BASE + 0x01d9, 0x0002 },
+
+		{ USBTV_BASE + 0x01da, 0x0013 },
+		{ USBTV_BASE + 0x01db, 0x0012 },
+		{ USBTV_BASE + 0x01e9, 0x0002 },
+		{ USBTV_BASE + 0x01ec, 0x006c },
+		{ USBTV_BASE + 0x0294, 0x0020 },
+		{ USBTV_BASE + 0x0255, 0x00cf },
+		{ USBTV_BASE + 0x0256, 0x0020 },
+		{ USBTV_BASE + 0x01eb, 0x0030 },
+		{ USBTV_BASE + 0x027d, 0x00a6 },
+		{ USBTV_BASE + 0x0280, 0x0011 },
+		{ USBTV_BASE + 0x0281, 0x0040 },
+		{ USBTV_BASE + 0x0282, 0x0011 },
+		{ USBTV_BASE + 0x0283, 0x0040 },
+		{ 0xf891, 0x0010 },
+
+		/* this sets the input from composite */
+		{ USBTV_BASE + 0x0284, 0x00aa },
+	};
+
+	chip->snd_bulk_urb = usb_alloc_urb(0, GFP_KERNEL);
+	if (chip->snd_bulk_urb == NULL)
+		goto err_alloc_urb;
+
+	pipe = usb_rcvbulkpipe(chip->udev, USBTV_AUDIO_ENDP);
+
+	chip->snd_bulk_urb->transfer_buffer = kzalloc(
+		USBTV_AUDIO_URBSIZE, GFP_KERNEL);
+	if (chip->snd_bulk_urb->transfer_buffer == NULL)
+		goto err_transfer_buffer;
+
+	usb_fill_bulk_urb(chip->snd_bulk_urb, chip->udev, pipe,
+		chip->snd_bulk_urb->transfer_buffer, USBTV_AUDIO_URBSIZE,
+		usbtv_audio_urb_received, chip);
+
+	/* starting the stream */
+	usbtv_set_regs(chip, setup, ARRAY_SIZE(setup));
+
+	usb_clear_halt(chip->udev, pipe);
+	usb_submit_urb(chip->snd_bulk_urb, GFP_ATOMIC);
+
+	return 0;
+
+err_transfer_buffer:
+	usb_free_urb(chip->snd_bulk_urb);
+	chip->snd_bulk_urb = NULL;
+
+err_alloc_urb:
+	return -ENOMEM;
+}
+
+static int usbtv_audio_stop(struct usbtv *chip)
+{
+	static const u16 setup[][2] = {
+	/* The original windows driver sometimes sends also:
+	 *   { USBTV_BASE + 0x00a2, 0x0013 }
+	 * but it seems useless and its real effects are untested at
+	 * the moment.
+	 */
+		{ USBTV_BASE + 0x027d, 0x0000 },
+		{ USBTV_BASE + 0x0280, 0x0010 },
+		{ USBTV_BASE + 0x0282, 0x0010 },
+	};
+
+	if (chip->snd_bulk_urb) {
+		usb_kill_urb(chip->snd_bulk_urb);
+		kfree(chip->snd_bulk_urb->transfer_buffer);
+		usb_free_urb(chip->snd_bulk_urb);
+		chip->snd_bulk_urb = NULL;
+	}
+
+	usbtv_set_regs(chip, setup, ARRAY_SIZE(setup));
+
+	return 0;
+}
+
+void usbtv_audio_suspend(struct usbtv *usbtv)
+{
+	if (atomic_read(&usbtv->snd_stream) && usbtv->snd_bulk_urb)
+		usb_kill_urb(usbtv->snd_bulk_urb);
+}
+
+void usbtv_audio_resume(struct usbtv *usbtv)
+{
+	if (atomic_read(&usbtv->snd_stream) && usbtv->snd_bulk_urb)
+		usb_submit_urb(usbtv->snd_bulk_urb, GFP_ATOMIC);
+}
+
+static void snd_usbtv_trigger(struct work_struct *work)
+{
+	struct usbtv *chip = container_of(work, struct usbtv, snd_trigger);
+
+	if (atomic_read(&chip->snd_stream))
+		usbtv_audio_start(chip);
+	else
+		usbtv_audio_stop(chip);
+}
+
+static int snd_usbtv_card_trigger(struct snd_pcm_substream *substream, int cmd)
+{
+	struct usbtv *chip = snd_pcm_substream_chip(substream);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		atomic_set(&chip->snd_stream, 1);
+		break;
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		atomic_set(&chip->snd_stream, 0);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	schedule_work(&chip->snd_trigger);
+
+	return 0;
+}
+
+static snd_pcm_uframes_t snd_usbtv_pointer(struct snd_pcm_substream *substream)
+{
+	struct usbtv *chip = snd_pcm_substream_chip(substream);
+
+	return chip->snd_buffer_pos;
+}
+
+static struct snd_pcm_ops snd_usbtv_pcm_ops = {
+	.open = snd_usbtv_pcm_open,
+	.close = snd_usbtv_pcm_close,
+	.ioctl = snd_pcm_lib_ioctl,
+	.hw_params = snd_usbtv_hw_params,
+	.hw_free = snd_usbtv_hw_free,
+	.prepare = snd_usbtv_prepare,
+	.trigger = snd_usbtv_card_trigger,
+	.pointer = snd_usbtv_pointer,
+};
+
+int usbtv_audio_init(struct usbtv *usbtv)
+{
+	int rv;
+	struct snd_card *card;
+	struct snd_pcm *pcm;
+
+	INIT_WORK(&usbtv->snd_trigger, snd_usbtv_trigger);
+	atomic_set(&usbtv->snd_stream, 0);
+
+	rv = snd_card_new(&usbtv->udev->dev, SNDRV_DEFAULT_IDX1, "usbtv",
+		THIS_MODULE, 0, &card);
+	if (rv < 0)
+		return rv;
+
+	strlcpy(card->driver, usbtv->dev->driver->name, sizeof(card->driver));
+	strlcpy(card->shortname, "usbtv", sizeof(card->shortname));
+	snprintf(card->longname, sizeof(card->longname),
+		"USBTV Audio at bus %d device %d", usbtv->udev->bus->busnum,
+		usbtv->udev->devnum);
+
+	snd_card_set_dev(card, usbtv->dev);
+
+	usbtv->snd = card;
+
+	rv = snd_pcm_new(card, "USBTV Audio", 0, 0, 1, &pcm);
+	if (rv < 0)
+		goto err;
+
+	strlcpy(pcm->name, "USBTV Audio Input", sizeof(pcm->name));
+	pcm->info_flags = 0;
+	pcm->private_data = usbtv;
+
+	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_usbtv_pcm_ops);
+	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
+		snd_dma_continuous_data(GFP_KERNEL), USBTV_AUDIO_BUFFER,
+		USBTV_AUDIO_BUFFER);
+
+	rv = snd_card_register(card);
+	if (rv)
+		goto err;
+
+	return 0;
+
+err:
+	usbtv->snd = NULL;
+	snd_card_free(card);
+
+	return rv;
+}
+
+void usbtv_audio_free(struct usbtv *usbtv)
+{
+	if (usbtv->snd && usbtv->udev) {
+		snd_card_free(usbtv->snd);
+		usbtv->snd = NULL;
+	}
+}
diff --git a/drivers/media/usb/usbtv/usbtv-core.c b/drivers/media/usb/usbtv/usbtv-core.c
index 473fab81b602..29428bef272c 100644
--- a/drivers/media/usb/usbtv/usbtv-core.c
+++ b/drivers/media/usb/usbtv/usbtv-core.c
@@ -1,5 +1,5 @@
 /*
- * Fushicai USBTV007 Video Grabber Driver
+ * Fushicai USBTV007 Audio-Video Grabber Driver
  *
  * Product web site:
  * http://www.fushicai.com/products_detail/&productId=d05449ee-b690-42f9-a661-aa7353894bed.html
@@ -84,12 +84,19 @@ static int usbtv_probe(struct usb_interface *intf,
 	if (ret < 0)
 		goto usbtv_video_fail;
 
+	ret = usbtv_audio_init(usbtv);
+	if (ret < 0)
+		goto usbtv_audio_fail;
+
 	/* for simplicity we exploit the v4l2_device reference counting */
 	v4l2_device_get(&usbtv->v4l2_dev);
 
-	dev_info(dev, "Fushicai USBTV007 Video Grabber\n");
+	dev_info(dev, "Fushicai USBTV007 Audio-Video Grabber\n");
 	return 0;
 
+usbtv_audio_fail:
+	usbtv_video_free(usbtv);
+
 usbtv_video_fail:
 	usb_set_intfdata(intf, NULL);
 	usb_put_dev(usbtv->udev);
@@ -101,11 +108,13 @@ usbtv_video_fail:
 static void usbtv_disconnect(struct usb_interface *intf)
 {
 	struct usbtv *usbtv = usb_get_intfdata(intf);
+
 	usb_set_intfdata(intf, NULL);
 
 	if (!usbtv)
 		return;
 
+	usbtv_audio_free(usbtv);
 	usbtv_video_free(usbtv);
 
 	usb_put_dev(usbtv->udev);
@@ -122,8 +131,8 @@ static struct usb_device_id usbtv_id_table[] = {
 };
 MODULE_DEVICE_TABLE(usb, usbtv_id_table);
 
-MODULE_AUTHOR("Lubomir Rintel");
-MODULE_DESCRIPTION("Fushicai USBTV007 Video Grabber Driver");
+MODULE_AUTHOR("Lubomir Rintel, Federico Simoncelli");
+MODULE_DESCRIPTION("Fushicai USBTV007 Audio-Video Grabber Driver");
 MODULE_LICENSE("Dual BSD/GPL");
 
 static struct usb_driver usbtv_usb_driver = {
diff --git a/drivers/media/usb/usbtv/usbtv-video.c b/drivers/media/usb/usbtv/usbtv-video.c
index 030c5854b4b3..9d3525f659f0 100644
--- a/drivers/media/usb/usbtv/usbtv-video.c
+++ b/drivers/media/usb/usbtv/usbtv-video.c
@@ -1,5 +1,5 @@
 /*
- * Fushicai USBTV007 Video Grabber Driver
+ * Fushicai USBTV007 Audio-Video Grabber Driver
  *
  * Product web site:
  * http://www.fushicai.com/products_detail/&productId=d05449ee-b690-42f9-a661-aa7353894bed.html
@@ -79,7 +79,6 @@ static int usbtv_select_input(struct usbtv *usbtv, int input)
 		{ USBTV_BASE + 0x011f, 0x00f2 },
 		{ USBTV_BASE + 0x0127, 0x0060 },
 		{ USBTV_BASE + 0x00ae, 0x0010 },
-		{ USBTV_BASE + 0x0284, 0x00aa },
 		{ USBTV_BASE + 0x0239, 0x0060 },
 	};
 
@@ -88,7 +87,6 @@ static int usbtv_select_input(struct usbtv *usbtv, int input)
 		{ USBTV_BASE + 0x011f, 0x00ff },
 		{ USBTV_BASE + 0x0127, 0x0060 },
 		{ USBTV_BASE + 0x00ae, 0x0030 },
-		{ USBTV_BASE + 0x0284, 0x0088 },
 		{ USBTV_BASE + 0x0239, 0x0060 },
 	};
 
@@ -225,7 +223,6 @@ static int usbtv_setup_capture(struct usbtv *usbtv)
 		{ USBTV_BASE + 0x0159, 0x0006 },
 		{ USBTV_BASE + 0x015d, 0x0000 },
 
-		{ USBTV_BASE + 0x0284, 0x0088 },
 		{ USBTV_BASE + 0x0003, 0x0004 },
 		{ USBTV_BASE + 0x0100, 0x00d3 },
 		{ USBTV_BASE + 0x0115, 0x0015 },
@@ -256,7 +253,7 @@ static int usbtv_setup_capture(struct usbtv *usbtv)
  * 720 pixel lines, as the chunk is 240 words long, which is 480 pixels.
  * Therefore, we break down the chunk into two halves before copyting,
  * so that we can interleave a line if needed. */
-static void usbtv_chunk_to_vbuf(u32 *frame, u32 *src, int chunk_no, int odd)
+static void usbtv_chunk_to_vbuf(u32 *frame, __be32 *src, int chunk_no, int odd)
 {
 	int half;
 
@@ -266,6 +263,7 @@ static void usbtv_chunk_to_vbuf(u32 *frame, u32 *src, int chunk_no, int odd)
 		int part_index = (line * 2 + !odd) * 3 + (part_no % 3);
 
 		u32 *dst = &frame[part_index * USBTV_CHUNK/2];
+
 		memcpy(dst, src, USBTV_CHUNK/2 * sizeof(*src));
 		src += USBTV_CHUNK/2;
 	}
@@ -274,7 +272,7 @@ static void usbtv_chunk_to_vbuf(u32 *frame, u32 *src, int chunk_no, int odd)
 /* Called for each 256-byte image chunk.
  * First word identifies the chunk, followed by 240 words of image
  * data and padding. */
-static void usbtv_image_chunk(struct usbtv *usbtv, u32 *chunk)
+static void usbtv_image_chunk(struct usbtv *usbtv, __be32 *chunk)
 {
 	int frame_id, odd, chunk_no;
 	u32 *frame;
@@ -365,7 +363,7 @@ static void usbtv_iso_cb(struct urb *ip)
 
 		for (offset = 0; USBTV_CHUNK_SIZE * offset < size; offset++)
 			usbtv_image_chunk(usbtv,
-				(u32 *)&data[USBTV_CHUNK_SIZE * offset]);
+				(__be32 *)&data[USBTV_CHUNK_SIZE * offset]);
 	}
 
 resubmit:
@@ -410,6 +408,7 @@ static void usbtv_stop(struct usbtv *usbtv)
 	/* Cancel running transfers. */
 	for (i = 0; i < USBTV_ISOC_TRANSFERS; i++) {
 		struct urb *ip = usbtv->isoc_urbs[i];
+
 		if (ip == NULL)
 			continue;
 		usb_kill_urb(ip);
@@ -434,6 +433,8 @@ static int usbtv_start(struct usbtv *usbtv)
 	int i;
 	int ret;
 
+	usbtv_audio_suspend(usbtv);
+
 	ret = usb_set_interface(usbtv->udev, 0, 0);
 	if (ret < 0)
 		return ret;
@@ -446,6 +447,8 @@ static int usbtv_start(struct usbtv *usbtv)
 	if (ret < 0)
 		return ret;
 
+	usbtv_audio_resume(usbtv);
+
 	for (i = 0; i < USBTV_ISOC_TRANSFERS; i++) {
 		struct urb *ip;
 
@@ -559,6 +562,7 @@ static int usbtv_g_input(struct file *file, void *priv, unsigned int *i)
 static int usbtv_s_input(struct file *file, void *priv, unsigned int i)
 {
 	struct usbtv *usbtv = video_drvdata(file);
+
 	return usbtv_select_input(usbtv, i);
 }
 
diff --git a/drivers/media/usb/usbtv/usbtv.h b/drivers/media/usb/usbtv/usbtv.h
index cb1d388cc647..968119581fab 100644
--- a/drivers/media/usb/usbtv/usbtv.h
+++ b/drivers/media/usb/usbtv/usbtv.h
@@ -1,5 +1,5 @@
 /*
- * Fushicai USBTV007 Video Grabber Driver
+ * Fushicai USBTV007 Audio-Video Grabber Driver
  *
  * Copyright (c) 2013 Lubomir Rintel
  * All rights reserved.
@@ -28,6 +28,7 @@
 
 /* Hardware. */
 #define USBTV_VIDEO_ENDP	0x81
+#define USBTV_AUDIO_ENDP	0x83
 #define USBTV_BASE		0xc000
 #define USBTV_REQUEST_REG	12
 
@@ -39,6 +40,10 @@
 #define USBTV_CHUNK_SIZE	256
 #define USBTV_CHUNK		240
 
+#define USBTV_AUDIO_URBSIZE	20480
+#define USBTV_AUDIO_HDRSIZE	4
+#define USBTV_AUDIO_BUFFER	65536
+
 /* Chunk header. */
 #define USBTV_MAGIC_OK(chunk)	((be32_to_cpu(chunk[0]) & 0xff000000) \
 							== 0x88000000)
@@ -91,9 +96,23 @@ struct usbtv {
 	int iso_size;
 	unsigned int sequence;
 	struct urb *isoc_urbs[USBTV_ISOC_TRANSFERS];
+
+	/* audio */
+	struct snd_card *snd;
+	struct snd_pcm_substream *snd_substream;
+	atomic_t snd_stream;
+	struct work_struct snd_trigger;
+	struct urb *snd_bulk_urb;
+	size_t snd_buffer_pos;
+	size_t snd_period_pos;
 };
 
 int usbtv_set_regs(struct usbtv *usbtv, const u16 regs[][2], int size);
 
 int usbtv_video_init(struct usbtv *usbtv);
 void usbtv_video_free(struct usbtv *usbtv);
+
+int usbtv_audio_init(struct usbtv *usbtv);
+void usbtv_audio_free(struct usbtv *usbtv);
+void usbtv_audio_suspend(struct usbtv *usbtv);
+void usbtv_audio_resume(struct usbtv *usbtv);
diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c
index 0eb82106d2ff..3e59b288b8a8 100644
--- a/drivers/media/usb/uvc/uvc_ctrl.c
+++ b/drivers/media/usb/uvc/uvc_ctrl.c
@@ -309,9 +309,8 @@ static struct uvc_control_info uvc_ctrls[] = {
 		.selector	= UVC_CT_PANTILT_RELATIVE_CONTROL,
 		.index		= 12,
 		.size		= 4,
-		.flags		= UVC_CTRL_FLAG_SET_CUR | UVC_CTRL_FLAG_GET_MIN
-				| UVC_CTRL_FLAG_GET_MAX | UVC_CTRL_FLAG_GET_RES
-				| UVC_CTRL_FLAG_GET_DEF
+		.flags		= UVC_CTRL_FLAG_SET_CUR
+				| UVC_CTRL_FLAG_GET_RANGE
 				| UVC_CTRL_FLAG_AUTO_UPDATE,
 	},
 	{
@@ -391,6 +390,35 @@ static void uvc_ctrl_set_zoom(struct uvc_control_mapping *mapping,
 	data[2] = min((int)abs(value), 0xff);
 }
 
+static __s32 uvc_ctrl_get_rel_speed(struct uvc_control_mapping *mapping,
+	__u8 query, const __u8 *data)
+{
+	unsigned int first = mapping->offset / 8;
+	__s8 rel = (__s8)data[first];
+
+	switch (query) {
+	case UVC_GET_CUR:
+		return (rel == 0) ? 0 : (rel > 0 ? data[first+1]
+						 : -data[first+1]);
+	case UVC_GET_MIN:
+		return -data[first+1];
+	case UVC_GET_MAX:
+	case UVC_GET_RES:
+	case UVC_GET_DEF:
+	default:
+		return data[first+1];
+	}
+}
+
+static void uvc_ctrl_set_rel_speed(struct uvc_control_mapping *mapping,
+	__s32 value, __u8 *data)
+{
+	unsigned int first = mapping->offset / 8;
+
+	data[first] = value == 0 ? 0 : (value > 0) ? 1 : 0xff;
+	data[first+1] = min_t(int, abs(value), 0xff);
+}
+
 static struct uvc_control_mapping uvc_ctrl_mappings[] = {
 	{
 		.id		= V4L2_CID_BRIGHTNESS,
@@ -677,6 +705,30 @@ static struct uvc_control_mapping uvc_ctrl_mappings[] = {
 		.data_type	= UVC_CTRL_DATA_TYPE_SIGNED,
 	},
 	{
+		.id		= V4L2_CID_PAN_SPEED,
+		.name		= "Pan (Speed)",
+		.entity		= UVC_GUID_UVC_CAMERA,
+		.selector	= UVC_CT_PANTILT_RELATIVE_CONTROL,
+		.size		= 16,
+		.offset		= 0,
+		.v4l2_type	= V4L2_CTRL_TYPE_INTEGER,
+		.data_type	= UVC_CTRL_DATA_TYPE_SIGNED,
+		.get		= uvc_ctrl_get_rel_speed,
+		.set		= uvc_ctrl_set_rel_speed,
+	},
+	{
+		.id		= V4L2_CID_TILT_SPEED,
+		.name		= "Tilt (Speed)",
+		.entity		= UVC_GUID_UVC_CAMERA,
+		.selector	= UVC_CT_PANTILT_RELATIVE_CONTROL,
+		.size		= 16,
+		.offset		= 16,
+		.v4l2_type	= V4L2_CTRL_TYPE_INTEGER,
+		.data_type	= UVC_CTRL_DATA_TYPE_SIGNED,
+		.get		= uvc_ctrl_get_rel_speed,
+		.set		= uvc_ctrl_set_rel_speed,
+	},
+	{
 		.id		= V4L2_CID_PRIVACY,
 		.name		= "Privacy",
 		.entity		= UVC_GUID_UVC_CAMERA,
@@ -1795,7 +1847,7 @@ done:
  * - Handle restore order (Auto-Exposure Mode should be restored before
  *   Exposure Time).
  */
-int uvc_ctrl_resume_device(struct uvc_device *dev)
+int uvc_ctrl_restore_values(struct uvc_device *dev)
 {
 	struct uvc_control *ctrl;
 	struct uvc_entity *entity;
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index f8135f4e3b52..7c8322d4fc63 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -2000,7 +2000,7 @@ static int __uvc_resume(struct usb_interface *intf, int reset)
 		int ret = 0;
 
 		if (reset) {
-			ret = uvc_ctrl_resume_device(dev);
+			ret = uvc_ctrl_restore_values(dev);
 			if (ret < 0)
 				return ret;
 		}
@@ -2175,6 +2175,15 @@ static struct usb_device_id uvc_ids[] = {
 	  .bInterfaceClass	= USB_CLASS_VENDOR_SPEC,
 	  .bInterfaceSubClass	= 1,
 	  .bInterfaceProtocol	= 0 },
+	/* Logitech HD Pro Webcam C920 */
+	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
+				| USB_DEVICE_ID_MATCH_INT_INFO,
+	  .idVendor		= 0x046d,
+	  .idProduct		= 0x082d,
+	  .bInterfaceClass	= USB_CLASS_VIDEO,
+	  .bInterfaceSubClass	= 1,
+	  .bInterfaceProtocol	= 0,
+	  .driver_info		= UVC_QUIRK_RESTORE_CTRLS_ON_INIT },
 	/* Chicony CNF7129 (Asus EEE 100HE) */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
 				| USB_DEVICE_ID_MATCH_INT_INFO,
@@ -2229,6 +2238,15 @@ static struct usb_device_id uvc_ids[] = {
 	  .bInterfaceSubClass	= 1,
 	  .bInterfaceProtocol	= 0,
 	  .driver_info		= UVC_QUIRK_PROBE_DEF },
+	/* Dell XPS M1330 (OmniVision OV7670 webcam) */
+	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
+				| USB_DEVICE_ID_MATCH_INT_INFO,
+	  .idVendor		= 0x05a9,
+	  .idProduct		= 0x7670,
+	  .bInterfaceClass	= USB_CLASS_VIDEO,
+	  .bInterfaceSubClass	= 1,
+	  .bInterfaceProtocol	= 0,
+	  .driver_info		= UVC_QUIRK_PROBE_DEF },
 	/* Apple Built-In iSight */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
 				| USB_DEVICE_ID_MATCH_INT_INFO,
diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c
index 378ae02e593b..60a8e2c3631e 100644
--- a/drivers/media/usb/uvc/uvc_v4l2.c
+++ b/drivers/media/usb/uvc/uvc_v4l2.c
@@ -318,6 +318,7 @@ static int uvc_v4l2_set_format(struct uvc_streaming *stream,
 	stream->ctrl = probe;
 	stream->cur_format = format;
 	stream->cur_frame = frame;
+	stream->frame_size = fmt->fmt.pix.sizeimage;
 
 done:
 	mutex_unlock(&stream->mutex);
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index 9144a2f3ed82..9ace520bb079 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -1143,7 +1143,7 @@ static int uvc_video_encode_data(struct uvc_streaming *stream,
 static void uvc_video_validate_buffer(const struct uvc_streaming *stream,
 				      struct uvc_buffer *buf)
 {
-	if (buf->length != buf->bytesused &&
+	if (stream->frame_size != buf->bytesused &&
 	    !(stream->cur_format->flags & UVC_FMT_FLAG_COMPRESSED))
 		buf->error = 1;
 }
@@ -1463,7 +1463,7 @@ static unsigned int uvc_endpoint_max_bpi(struct usb_device *dev,
 
 	switch (dev->speed) {
 	case USB_SPEED_SUPER:
-		return ep->ss_ep_comp.wBytesPerInterval;
+		return le16_to_cpu(ep->ss_ep_comp.wBytesPerInterval);
 	case USB_SPEED_HIGH:
 		psize = usb_endpoint_maxp(&ep->desc);
 		return (psize & 0x07ff) * (1 + ((psize >> 11) & 3));
@@ -1678,6 +1678,12 @@ static int uvc_init_video(struct uvc_streaming *stream, gfp_t gfp_flags)
 		}
 	}
 
+	/* The Logitech C920 temporarily forgets that it should not be adjusting
+	 * Exposure Absolute during init so restore controls to stored values.
+	 */
+	if (stream->dev->quirks & UVC_QUIRK_RESTORE_CTRLS_ON_INIT)
+		uvc_ctrl_restore_values(stream->dev);
+
 	return 0;
 }
 
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index b1f69a6d4068..6f676c29ec09 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -147,6 +147,7 @@
 #define UVC_QUIRK_FIX_BANDWIDTH		0x00000080
 #define UVC_QUIRK_PROBE_DEF		0x00000100
 #define UVC_QUIRK_RESTRICT_FRAME_RATE	0x00000200
+#define UVC_QUIRK_RESTORE_CTRLS_ON_INIT	0x00000400
 
 /* Format flags */
 #define UVC_FMT_FLAG_COMPRESSED		0x00000001
@@ -456,6 +457,8 @@ struct uvc_streaming {
 	struct uvc_format *def_format;
 	struct uvc_format *cur_format;
 	struct uvc_frame *cur_frame;
+	size_t frame_size;
+
 	/* Protect access to ctrl, cur_format, cur_frame and hardware video
 	 * probe control.
 	 */
@@ -688,7 +691,7 @@ extern int uvc_ctrl_add_mapping(struct uvc_video_chain *chain,
 		const struct uvc_control_mapping *mapping);
 extern int uvc_ctrl_init_device(struct uvc_device *dev);
 extern void uvc_ctrl_cleanup_device(struct uvc_device *dev);
-extern int uvc_ctrl_resume_device(struct uvc_device *dev);
+extern int uvc_ctrl_restore_values(struct uvc_device *dev);
 
 extern int uvc_ctrl_begin(struct uvc_video_chain *chain);
 extern int __uvc_ctrl_commit(struct uvc_fh *handle, int rollback,
diff --git a/drivers/media/v4l2-core/tuner-core.c b/drivers/media/v4l2-core/tuner-core.c
index 06c18ba16fa0..559f8372e2eb 100644
--- a/drivers/media/v4l2-core/tuner-core.c
+++ b/drivers/media/v4l2-core/tuner-core.c
@@ -601,7 +601,7 @@ static int tuner_probe(struct i2c_client *client,
 	t->name = "(tuner unset)";
 	t->type = UNSET;
 	t->audmode = V4L2_TUNER_MODE_STEREO;
-	t->standby = 1;
+	t->standby = true;
 	t->radio_freq = 87.5 * 16000;	/* Initial freq range */
 	t->tv_freq = 400 * 16; /* Sets freq to VHF High - needed for some PLL's to properly start */
 
@@ -1260,7 +1260,9 @@ static int tuner_suspend(struct device *dev)
 
 	tuner_dbg("suspend\n");
 
-	if (!t->standby && analog_ops->standby)
+	if (t->fe.ops.tuner_ops.suspend)
+		t->fe.ops.tuner_ops.suspend(&t->fe);
+	else if (!t->standby && analog_ops->standby)
 		analog_ops->standby(&t->fe);
 
 	return 0;
@@ -1273,7 +1275,9 @@ static int tuner_resume(struct device *dev)
 
 	tuner_dbg("resume\n");
 
-	if (!t->standby)
+	if (t->fe.ops.tuner_ops.resume)
+		t->fe.ops.tuner_ops.resume(&t->fe);
+	else if (!t->standby)
 		if (set_mode(t, t->mode) == 0)
 			set_freq(t, 0);
 
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index ccaa38f65cf1..2e9d81f4c1a5 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -435,16 +435,13 @@ static unsigned int clamp_align(unsigned int x, unsigned int min,
 	/* Bits that must be zero to be aligned */
 	unsigned int mask = ~((1 << align) - 1);
 
+	/* Clamp to aligned min and max */
+	x = clamp(x, (min + ~mask) & mask, max & mask);
+
 	/* Round to nearest aligned value */
 	if (align)
 		x = (x + (1 << (align - 1))) & mask;
 
-	/* Clamp to aligned value of min and max */
-	if (x < min)
-		x = (min + ~mask) & mask;
-	else if (x > max)
-		x = max & mask;
-
 	return x;
 }
 
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index cca6c2f76b3a..e502a5fb2994 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -328,7 +328,7 @@ struct v4l2_buffer32 {
 	__u32			reserved;
 };
 
-static int get_v4l2_plane32(struct v4l2_plane *up, struct v4l2_plane32 *up32,
+static int get_v4l2_plane32(struct v4l2_plane __user *up, struct v4l2_plane32 __user *up32,
 				enum v4l2_memory memory)
 {
 	void __user *up_pln;
@@ -357,7 +357,7 @@ static int get_v4l2_plane32(struct v4l2_plane *up, struct v4l2_plane32 *up32,
 	return 0;
 }
 
-static int put_v4l2_plane32(struct v4l2_plane *up, struct v4l2_plane32 *up32,
+static int put_v4l2_plane32(struct v4l2_plane __user *up, struct v4l2_plane32 __user *up32,
 				enum v4l2_memory memory)
 {
 	if (copy_in_user(up32, up, 2 * sizeof(__u32)) ||
@@ -427,7 +427,7 @@ static int get_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 		 * by passing a very big num_planes value */
 		uplane = compat_alloc_user_space(num_planes *
 						sizeof(struct v4l2_plane));
-		kp->m.planes = uplane;
+		kp->m.planes = (__force struct v4l2_plane *)uplane;
 
 		while (--num_planes >= 0) {
 			ret = get_v4l2_plane32(uplane, uplane32, kp->memory);
@@ -498,7 +498,7 @@ static int put_v4l2_buffer32(struct v4l2_buffer *kp, struct v4l2_buffer32 __user
 		if (num_planes == 0)
 			return 0;
 
-		uplane = kp->m.planes;
+		uplane = (__force struct v4l2_plane __user *)kp->m.planes;
 		if (get_user(p, &up->m.planes))
 			return -EFAULT;
 		uplane32 = compat_ptr(p);
@@ -562,7 +562,7 @@ static int get_v4l2_framebuffer32(struct v4l2_framebuffer *kp, struct v4l2_frame
 		get_user(kp->flags, &up->flags) ||
 		copy_from_user(&kp->fmt, &up->fmt, sizeof(up->fmt)))
 			return -EFAULT;
-	kp->base = compat_ptr(tmp);
+	kp->base = (__force void *)compat_ptr(tmp);
 	return 0;
 }
 
@@ -667,11 +667,15 @@ static int get_v4l2_ext_controls32(struct v4l2_ext_controls *kp, struct v4l2_ext
 			n * sizeof(struct v4l2_ext_control32)))
 		return -EFAULT;
 	kcontrols = compat_alloc_user_space(n * sizeof(struct v4l2_ext_control));
-	kp->controls = kcontrols;
+	kp->controls = (__force struct v4l2_ext_control *)kcontrols;
 	while (--n >= 0) {
+		u32 id;
+
 		if (copy_in_user(kcontrols, ucontrols, sizeof(*ucontrols)))
 			return -EFAULT;
-		if (ctrl_is_pointer(kcontrols->id)) {
+		if (get_user(id, &kcontrols->id))
+			return -EFAULT;
+		if (ctrl_is_pointer(id)) {
 			void __user *s;
 
 			if (get_user(p, &ucontrols->string))
@@ -689,7 +693,8 @@ static int get_v4l2_ext_controls32(struct v4l2_ext_controls *kp, struct v4l2_ext
 static int put_v4l2_ext_controls32(struct v4l2_ext_controls *kp, struct v4l2_ext_controls32 __user *up)
 {
 	struct v4l2_ext_control32 __user *ucontrols;
-	struct v4l2_ext_control __user *kcontrols = kp->controls;
+	struct v4l2_ext_control __user *kcontrols =
+		(__force struct v4l2_ext_control __user *)kp->controls;
 	int n = kp->count;
 	compat_caddr_t p;
 
@@ -711,11 +716,14 @@ static int put_v4l2_ext_controls32(struct v4l2_ext_controls *kp, struct v4l2_ext
 
 	while (--n >= 0) {
 		unsigned size = sizeof(*ucontrols);
+		u32 id;
 
+		if (get_user(id, &kcontrols->id))
+			return -EFAULT;
 		/* Do not modify the pointer when copying a pointer control.
 		   The contents of the pointer was changed, not the pointer
 		   itself. */
-		if (ctrl_is_pointer(kcontrols->id))
+		if (ctrl_is_pointer(id))
 			size -= sizeof(ucontrols->value64);
 		if (copy_in_user(ucontrols, kcontrols, size))
 			return -EFAULT;
@@ -770,7 +778,7 @@ static int get_v4l2_edid32(struct v4l2_edid *kp, struct v4l2_edid32 __user *up)
 		get_user(tmp, &up->edid) ||
 		copy_from_user(kp->reserved, up->reserved, sizeof(kp->reserved)))
 			return -EFAULT;
-	kp->edid = compat_ptr(tmp);
+	kp->edid = (__force u8 *)compat_ptr(tmp);
 	return 0;
 }
 
@@ -783,7 +791,7 @@ static int put_v4l2_edid32(struct v4l2_edid *kp, struct v4l2_edid32 __user *up)
 		put_user(kp->start_block, &up->start_block) ||
 		put_user(kp->blocks, &up->blocks) ||
 		put_user(tmp, &up->edid) ||
-		copy_to_user(kp->reserved, up->reserved, sizeof(kp->reserved)))
+		copy_to_user(up->reserved, kp->reserved, sizeof(up->reserved)))
 			return -EFAULT;
 	return 0;
 }
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index f030d6a9e044..86012140923f 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -796,6 +796,8 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_AUTO_FOCUS_STOP:		return "Auto Focus, Stop";
 	case V4L2_CID_AUTO_FOCUS_STATUS:	return "Auto Focus, Status";
 	case V4L2_CID_AUTO_FOCUS_RANGE:		return "Auto Focus, Range";
+	case V4L2_CID_PAN_SPEED:		return "Pan, Speed";
+	case V4L2_CID_TILT_SPEED:		return "Tilt, Speed";
 
 	/* FM Radio Modulator controls */
 	/* Keep the order of the 'case's the same as in v4l2-controls.h! */
@@ -859,6 +861,10 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_VBLANK:			return "Vertical Blanking";
 	case V4L2_CID_HBLANK:			return "Horizontal Blanking";
 	case V4L2_CID_ANALOGUE_GAIN:		return "Analogue Gain";
+	case V4L2_CID_TEST_PATTERN_RED:		return "Red Pixel Value";
+	case V4L2_CID_TEST_PATTERN_GREENR:	return "Green (Red) Pixel Value";
+	case V4L2_CID_TEST_PATTERN_BLUE:	return "Blue Pixel Value";
+	case V4L2_CID_TEST_PATTERN_GREENB:	return "Green (Blue) Pixel Value";
 
 	/* Image processing controls */
 	/* Keep the order of the 'case's the same as in v4l2-controls.h! */
diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c
index ce1c9f5d9dee..b1d8dbb39665 100644
--- a/drivers/media/v4l2-core/v4l2-dv-timings.c
+++ b/drivers/media/v4l2-core/v4l2-dv-timings.c
@@ -164,7 +164,8 @@ bool v4l2_valid_dv_timings(const struct v4l2_dv_timings *t,
 	    bt->width > cap->max_width ||
 	    bt->pixelclock < cap->min_pixelclock ||
 	    bt->pixelclock > cap->max_pixelclock ||
-	    (cap->standards && !(bt->standards & cap->standards)) ||
+	    (cap->standards && bt->standards &&
+	     !(bt->standards & cap->standards)) ||
 	    (bt->interlaced && !(caps & V4L2_DV_BT_CAP_INTERLACED)) ||
 	    (!bt->interlaced && !(caps & V4L2_DV_BT_CAP_PROGRESSIVE)))
 		return false;
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index d15e16737eef..9ccb19a435ef 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -562,7 +562,7 @@ static void v4l_print_ext_controls(const void *arg, bool write_only)
 	pr_cont("class=0x%x, count=%d, error_idx=%d",
 			p->ctrl_class, p->count, p->error_idx);
 	for (i = 0; i < p->count; i++) {
-		if (p->controls[i].size)
+		if (!p->controls[i].size)
 			pr_cont(", id/val=0x%x/0x%x",
 				p->controls[i].id, p->controls[i].value);
 		else
@@ -1153,9 +1153,9 @@ static int v4l_g_fmt(const struct v4l2_ioctl_ops *ops,
 	switch (p->type) {
 	case V4L2_BUF_TYPE_VIDEO_OVERLAY:
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY: {
-		struct v4l2_clip *clips = p->fmt.win.clips;
+		struct v4l2_clip __user *clips = p->fmt.win.clips;
 		u32 clipcount = p->fmt.win.clipcount;
-		void *bitmap = p->fmt.win.bitmap;
+		void __user *bitmap = p->fmt.win.bitmap;
 
 		memset(&p->fmt, 0, sizeof(p->fmt));
 		p->fmt.win.clips = clips;
diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index b4d235c13fbf..543631c3557a 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -501,11 +501,20 @@ int v4l2_subdev_link_validate_default(struct v4l2_subdev *sd,
 				      struct v4l2_subdev_format *source_fmt,
 				      struct v4l2_subdev_format *sink_fmt)
 {
+	/* The width, height and code must match. */
 	if (source_fmt->format.width != sink_fmt->format.width
 	    || source_fmt->format.height != sink_fmt->format.height
 	    || source_fmt->format.code != sink_fmt->format.code)
 		return -EINVAL;
 
+	/* The field order must match, or the sink field order must be NONE
+	 * to support interlaced hardware connected to bridges that support
+	 * progressive formats only.
+	 */
+	if (source_fmt->format.field != sink_fmt->format.field &&
+	    sink_fmt->format.field != V4L2_FIELD_NONE)
+		return -EINVAL;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(v4l2_subdev_link_validate_default);
diff --git a/drivers/media/v4l2-core/videobuf-core.c b/drivers/media/v4l2-core/videobuf-core.c
index fb5ee5dd8fe9..b91a266d0b7e 100644
--- a/drivers/media/v4l2-core/videobuf-core.c
+++ b/drivers/media/v4l2-core/videobuf-core.c
@@ -441,11 +441,6 @@ int videobuf_reqbufs(struct videobuf_queue *q,
 	unsigned int size, count;
 	int retval;
 
-	if (req->count < 1) {
-		dprintk(1, "reqbufs: count invalid (%d)\n", req->count);
-		return -EINVAL;
-	}
-
 	if (req->memory != V4L2_MEMORY_MMAP     &&
 	    req->memory != V4L2_MEMORY_USERPTR  &&
 	    req->memory != V4L2_MEMORY_OVERLAY) {
@@ -471,6 +466,12 @@ int videobuf_reqbufs(struct videobuf_queue *q,
 		goto done;
 	}
 
+	if (req->count == 0) {
+		dprintk(1, "reqbufs: count invalid (%d)\n", req->count);
+		retval = __videobuf_free(q);
+		goto done;
+	}
+
 	count = req->count;
 	if (count > VIDEO_MAX_FRAME)
 		count = VIDEO_MAX_FRAME;
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 3c8cc023a5a5..3ff15f1c9d70 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -253,9 +253,11 @@ int videobuf_dma_init_kernel(struct videobuf_dmabuf *dma, int direction,
 	return 0;
 out_free_pages:
 	while (i > 0) {
-		void *addr = page_address(dma->vaddr_pages[i]);
-		dma_free_coherent(dma->dev, PAGE_SIZE, addr, dma->dma_addr[i]);
+		void *addr;
+
 		i--;
+		addr = page_address(dma->vaddr_pages[i]);
+		dma_free_coherent(dma->dev, PAGE_SIZE, addr, dma->dma_addr[i]);
 	}
 	kfree(dma->dma_addr);
 	dma->dma_addr = NULL;
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 25d3ae2188cb..f2e43de3dd87 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -36,7 +36,7 @@ module_param(debug, int, 0644);
 #define dprintk(level, fmt, arg...)					      \
 	do {								      \
 		if (debug >= level)					      \
-			pr_debug("vb2: %s: " fmt, __func__, ## arg); \
+			pr_info("vb2: %s: " fmt, __func__, ## arg); \
 	} while (0)
 
 #ifdef CONFIG_VIDEO_ADV_DEBUG
@@ -882,7 +882,9 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 		 * We already have buffers allocated, so first check if they
 		 * are not in use and can be freed.
 		 */
+		mutex_lock(&q->mmap_lock);
 		if (q->memory == V4L2_MEMORY_MMAP && __buffers_in_use(q)) {
+			mutex_unlock(&q->mmap_lock);
 			dprintk(1, "memory in use, cannot free\n");
 			return -EBUSY;
 		}
@@ -894,6 +896,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 		 */
 		__vb2_queue_cancel(q);
 		ret = __vb2_queue_free(q, q->num_buffers);
+		mutex_unlock(&q->mmap_lock);
 		if (ret)
 			return ret;
 
@@ -955,6 +958,7 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 		 */
 	}
 
+	mutex_lock(&q->mmap_lock);
 	q->num_buffers = allocated_buffers;
 
 	if (ret < 0) {
@@ -963,8 +967,10 @@ static int __reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req)
 		 * from q->num_buffers.
 		 */
 		__vb2_queue_free(q, allocated_buffers);
+		mutex_unlock(&q->mmap_lock);
 		return ret;
 	}
+	mutex_unlock(&q->mmap_lock);
 
 	/*
 	 * Return the number of successfully allocated buffers
@@ -1063,6 +1069,7 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create
 		 */
 	}
 
+	mutex_lock(&q->mmap_lock);
 	q->num_buffers += allocated_buffers;
 
 	if (ret < 0) {
@@ -1071,8 +1078,10 @@ static int __create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create
 		 * from q->num_buffers.
 		 */
 		__vb2_queue_free(q, allocated_buffers);
+		mutex_unlock(&q->mmap_lock);
 		return -ENOMEM;
 	}
+	mutex_unlock(&q->mmap_lock);
 
 	/*
 	 * Return the number of successfully allocated buffers
@@ -1581,7 +1590,6 @@ static void __enqueue_in_driver(struct vb2_buffer *vb)
 static int __buf_prepare(struct vb2_buffer *vb, const struct v4l2_buffer *b)
 {
 	struct vb2_queue *q = vb->vb2_queue;
-	struct rw_semaphore *mmap_sem;
 	int ret;
 
 	ret = __verify_length(vb, b);
@@ -1618,26 +1626,9 @@ static int __buf_prepare(struct vb2_buffer *vb, const struct v4l2_buffer *b)
 		ret = __qbuf_mmap(vb, b);
 		break;
 	case V4L2_MEMORY_USERPTR:
-		/*
-		 * In case of user pointer buffers vb2 allocators need to get
-		 * direct access to userspace pages. This requires getting
-		 * the mmap semaphore for read access in the current process
-		 * structure. The same semaphore is taken before calling mmap
-		 * operation, while both qbuf/prepare_buf and mmap are called
-		 * by the driver or v4l2 core with the driver's lock held.
-		 * To avoid an AB-BA deadlock (mmap_sem then driver's lock in
-		 * mmap and driver's lock then mmap_sem in qbuf/prepare_buf),
-		 * the videobuf2 core releases the driver's lock, takes
-		 * mmap_sem and then takes the driver's lock again.
-		 */
-		mmap_sem = &current->mm->mmap_sem;
-		call_void_qop(q, wait_prepare, q);
-		down_read(mmap_sem);
-		call_void_qop(q, wait_finish, q);
-
+		down_read(&current->mm->mmap_sem);
 		ret = __qbuf_userptr(vb, b);
-
-		up_read(mmap_sem);
+		up_read(&current->mm->mmap_sem);
 		break;
 	case V4L2_MEMORY_DMABUF:
 		ret = __qbuf_dmabuf(vb, b);
@@ -2504,7 +2495,9 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma)
 		return -EINVAL;
 	}
 
+	mutex_lock(&q->mmap_lock);
 	ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma);
+	mutex_unlock(&q->mmap_lock);
 	if (ret)
 		return ret;
 
@@ -2523,6 +2516,7 @@ unsigned long vb2_get_unmapped_area(struct vb2_queue *q,
 	unsigned long off = pgoff << PAGE_SHIFT;
 	struct vb2_buffer *vb;
 	unsigned int buffer, plane;
+	void *vaddr;
 	int ret;
 
 	if (q->memory != V4L2_MEMORY_MMAP) {
@@ -2539,7 +2533,8 @@ unsigned long vb2_get_unmapped_area(struct vb2_queue *q,
 
 	vb = q->bufs[buffer];
 
-	return (unsigned long)vb2_plane_vaddr(vb, plane);
+	vaddr = vb2_plane_vaddr(vb, plane);
+	return vaddr ? (unsigned long)vaddr : -EINVAL;
 }
 EXPORT_SYMBOL_GPL(vb2_get_unmapped_area);
 #endif
@@ -2686,6 +2681,7 @@ int vb2_queue_init(struct vb2_queue *q)
 	INIT_LIST_HEAD(&q->queued_list);
 	INIT_LIST_HEAD(&q->done_list);
 	spin_lock_init(&q->done_lock);
+	mutex_init(&q->mmap_lock);
 	init_waitqueue_head(&q->done_wq);
 
 	if (q->buf_struct_size == 0)
@@ -2707,7 +2703,9 @@ void vb2_queue_release(struct vb2_queue *q)
 {
 	__vb2_cleanup_fileio(q);
 	__vb2_queue_cancel(q);
+	mutex_lock(&q->mmap_lock);
 	__vb2_queue_free(q, q->num_buffers);
+	mutex_unlock(&q->mmap_lock);
 }
 EXPORT_SYMBOL_GPL(vb2_queue_release);
 
@@ -2985,6 +2983,12 @@ static size_t __vb2_perform_fileio(struct vb2_queue *q, char __user *data, size_
 		buf->queued = 0;
 		buf->size = read ? vb2_get_plane_payload(q->bufs[index], 0)
 				 : vb2_plane_size(q->bufs[index], 0);
+		/* Compensate for data_offset on read in the multiplanar case. */
+		if (is_multiplanar && read &&
+		    fileio->b.m.planes[0].data_offset < buf->size) {
+			buf->pos = fileio->b.m.planes[0].data_offset;
+			buf->size -= buf->pos;
+		}
 	} else {
 		buf = &fileio->bufs[index];
 	}
@@ -3372,15 +3376,8 @@ EXPORT_SYMBOL_GPL(vb2_ioctl_expbuf);
 int vb2_fop_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct video_device *vdev = video_devdata(file);
-	struct mutex *lock = vdev->queue->lock ? vdev->queue->lock : vdev->lock;
-	int err;
 
-	if (lock && mutex_lock_interruptible(lock))
-		return -ERESTARTSYS;
-	err = vb2_mmap(vdev->queue, vma);
-	if (lock)
-		mutex_unlock(lock);
-	return err;
+	return vb2_mmap(vdev->queue, vma);
 }
 EXPORT_SYMBOL_GPL(vb2_fop_mmap);
 
@@ -3499,15 +3496,8 @@ unsigned long vb2_fop_get_unmapped_area(struct file *file, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
 	struct video_device *vdev = video_devdata(file);
-	struct mutex *lock = vdev->queue->lock ? vdev->queue->lock : vdev->lock;
-	int ret;
 
-	if (lock && mutex_lock_interruptible(lock))
-		return -ERESTARTSYS;
-	ret = vb2_get_unmapped_area(vdev->queue, addr, len, pgoff, flags);
-	if (lock)
-		mutex_unlock(lock);
-	return ret;
+	return vb2_get_unmapped_area(vdev->queue, addr, len, pgoff, flags);
 }
 EXPORT_SYMBOL_GPL(vb2_fop_get_unmapped_area);
 #endif
diff --git a/drivers/memstick/host/r592.c b/drivers/memstick/host/r592.c
index 31727bf285d0..e2a4f5f415b2 100644
--- a/drivers/memstick/host/r592.c
+++ b/drivers/memstick/host/r592.c
@@ -188,6 +188,7 @@ static void r592_host_reset(struct r592_device *dev)
 	r592_set_mode(dev, dev->parallel_mode);
 }
 
+#ifdef CONFIG_PM_SLEEP
 /* Disable all hardware interrupts */
 static void r592_clear_interrupts(struct r592_device *dev)
 {
@@ -195,6 +196,7 @@ static void r592_clear_interrupts(struct r592_device *dev)
 	r592_clear_reg_mask(dev, R592_REG_MSC, IRQ_ALL_ACK_MASK);
 	r592_clear_reg_mask(dev, R592_REG_MSC, IRQ_ALL_EN_MASK);
 }
+#endif
 
 /* Tests if there is an CRC error */
 static int r592_test_io_error(struct r592_device *dev)
diff --git a/drivers/mfd/88pm860x-i2c.c b/drivers/mfd/88pm860x-i2c.c
index a93b4d0134a2..84e313107233 100644
--- a/drivers/mfd/88pm860x-i2c.c
+++ b/drivers/mfd/88pm860x-i2c.c
@@ -122,7 +122,7 @@ static int read_device(struct i2c_client *i2c, int reg,
 static int write_device(struct i2c_client *i2c, int reg,
 			int bytes, void *src)
 {
-	unsigned char buf[bytes + 1];
+	unsigned char buf[2];
 	struct i2c_adapter *adap = i2c->adapter;
 	struct i2c_msg msg;
 	int ret;
@@ -140,26 +140,6 @@ static int write_device(struct i2c_client *i2c, int reg,
 	return 0;
 }
 
-int pm860x_page_reg_read(struct i2c_client *i2c, int reg)
-{
-	unsigned char zero = 0;
-	unsigned char data;
-	int ret;
-
-	i2c_lock_adapter(i2c->adapter);
-	read_device(i2c, 0xFA, 0, &zero);
-	read_device(i2c, 0xFB, 0, &zero);
-	read_device(i2c, 0xFF, 0, &zero);
-	ret = read_device(i2c, reg, 1, &data);
-	if (ret >= 0)
-		ret = (int)data;
-	read_device(i2c, 0xFE, 0, &zero);
-	read_device(i2c, 0xFC, 0, &zero);
-	i2c_unlock_adapter(i2c->adapter);
-	return ret;
-}
-EXPORT_SYMBOL(pm860x_page_reg_read);
-
 int pm860x_page_reg_write(struct i2c_client *i2c, int reg,
 			  unsigned char data)
 {
@@ -195,47 +175,3 @@ int pm860x_page_bulk_read(struct i2c_client *i2c, int reg,
 	return ret;
 }
 EXPORT_SYMBOL(pm860x_page_bulk_read);
-
-int pm860x_page_bulk_write(struct i2c_client *i2c, int reg,
-			   int count, unsigned char *buf)
-{
-	unsigned char zero = 0;
-	int ret;
-
-	i2c_lock_adapter(i2c->adapter);
-	read_device(i2c, 0xFA, 0, &zero);
-	read_device(i2c, 0xFB, 0, &zero);
-	read_device(i2c, 0xFF, 0, &zero);
-	ret = write_device(i2c, reg, count, buf);
-	read_device(i2c, 0xFE, 0, &zero);
-	read_device(i2c, 0xFC, 0, &zero);
-	i2c_unlock_adapter(i2c->adapter);
-	i2c_unlock_adapter(i2c->adapter);
-	return ret;
-}
-EXPORT_SYMBOL(pm860x_page_bulk_write);
-
-int pm860x_page_set_bits(struct i2c_client *i2c, int reg,
-			 unsigned char mask, unsigned char data)
-{
-	unsigned char zero;
-	unsigned char value;
-	int ret;
-
-	i2c_lock_adapter(i2c->adapter);
-	read_device(i2c, 0xFA, 0, &zero);
-	read_device(i2c, 0xFB, 0, &zero);
-	read_device(i2c, 0xFF, 0, &zero);
-	ret = read_device(i2c, reg, 1, &value);
-	if (ret < 0)
-		goto out;
-	value &= ~mask;
-	value |= data;
-	ret = write_device(i2c, reg, 1, &value);
-out:
-	read_device(i2c, 0xFE, 0, &zero);
-	read_device(i2c, 0xFC, 0, &zero);
-	i2c_unlock_adapter(i2c->adapter);
-	return ret;
-}
-EXPORT_SYMBOL(pm860x_page_set_bits);
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index de5abf244746..1456ea70bbc7 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -210,6 +210,19 @@ config MFD_MC13XXX_I2C
 	help
 	  Select this if your MC13xxx is connected via an I2C bus.
 
+config MFD_HI6421_PMIC
+	tristate "HiSilicon Hi6421 PMU/Codec IC"
+	depends on OF
+	select MFD_CORE
+	select REGMAP_MMIO
+	help
+	  Add support for HiSilicon Hi6421 PMIC. Hi6421 includes multi-
+	  functions, such as regulators, RTC, codec, Coulomb counter, etc.
+	  This driver includes core APIs _only_. You have to select
+	  individul components like voltage regulators under corresponding
+	  menus in order to enable them.
+	  We communicate with the Hi6421 via memory-mapped I/O.
+
 config HTC_EGPIO
 	bool "HTC EGPIO support"
 	depends on GPIOLIB && ARM
@@ -454,6 +467,21 @@ config MFD_MAX8998
 	  additional drivers must be enabled in order to use the functionality
 	  of the device.
 
+config MFD_MENF21BMC
+	tristate "MEN 14F021P00 Board Management Controller Support"
+	depends on I2C
+	select MFD_CORE
+	help
+	  Say yes here to add support for the MEN 14F021P00 BMC
+	  which is a Board Management Controller connected to the I2C bus.
+	  The device supports multiple sub-devices like LED, HWMON and WDT.
+	  This driver provides common support for accessing the devices;
+	  additional drivers must be enabled in order to use the
+	  functionality of the BMC device.
+
+	  This driver can also be built as a module. If so the module
+	  will be called menf21bmc.
+
 config EZX_PCAP
 	bool "Motorola EZXPCAP Support"
 	depends on SPI_MASTER
@@ -539,6 +567,21 @@ config MFD_PM8921_CORE
 	  Say M here if you want to include support for PM8921 chip as a module.
 	  This will build a module called "pm8921-core".
 
+config MFD_SPMI_PMIC
+	tristate "Qualcomm SPMI PMICs"
+	depends on ARCH_QCOM || COMPILE_TEST
+	depends on OF
+	depends on SPMI
+	select REGMAP_SPMI
+	help
+	  This enables support for the Qualcomm SPMI PMICs.
+	  These PMICs are currently used with the Snapdragon 800 series of
+	  SoCs.  Note, that this will only be useful paired with descriptions
+	  of the independent functions as children nodes in the device tree.
+
+	  Say M here if you want to include support for the SPMI PMIC
+	  series as a module.  The module will be called "qcom-spmi-pmic".
+
 config MFD_RDC321X
 	tristate "RDC R-321x southbridge"
 	select MFD_CORE
@@ -582,6 +625,30 @@ config MFD_RC5T583
 	  Additional drivers must be enabled in order to use the
 	  different functionality of the device.
 
+config MFD_RK808
+	tristate "Rockchip RK808 Power Management chip"
+	depends on I2C && OF
+	select MFD_CORE
+	select REGMAP_I2C
+	select REGMAP_IRQ
+	help
+	  If you say yes here you get support for the RK808
+	  Power Management chips.
+	  This driver provides common support for accessing the device
+	  through I2C interface. The device supports multiple sub-devices
+	  including interrupts, RTC, LDO & DCDC regulators, and onkey.
+
+config MFD_RN5T618
+	tristate "Ricoh RN5T5618 PMIC"
+	depends on I2C
+	select MFD_CORE
+	select REGMAP_I2C
+	help
+	  Say yes here to add support for the Ricoh RN5T618 PMIC. This
+	  driver provides common support for accessing the device,
+	  additional drivers must be enabled in order to use the
+	  functionality of the device.
+
 config MFD_SEC_CORE
 	bool "SAMSUNG Electronics PMIC Series Support"
 	depends on I2C=y
@@ -1228,11 +1295,11 @@ config MFD_WM8350_I2C
 	  selected to enable support for the functionality of the chip.
 
 config MFD_WM8994
-	bool "Wolfson Microelectronics WM8994"
+	tristate "Wolfson Microelectronics WM8994"
 	select MFD_CORE
 	select REGMAP_I2C
 	select REGMAP_IRQ
-	depends on I2C=y
+	depends on I2C
 	help
 	  The WM8994 is a highly integrated hi-fi CODEC designed for
 	  smartphone applicatiosn.  As well as audio functionality it
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index f00148782d9b..8bd54b1253af 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -153,6 +153,7 @@ obj-$(CONFIG_MFD_SI476X_CORE)	+= si476x-core.o
 obj-$(CONFIG_MFD_CS5535)	+= cs5535-mfd.o
 obj-$(CONFIG_MFD_OMAP_USB_HOST)	+= omap-usb-host.o omap-usb-tll.o
 obj-$(CONFIG_MFD_PM8921_CORE) 	+= pm8921-core.o ssbi.o
+obj-$(CONFIG_MFD_SPMI_PMIC)	+= qcom-spmi-pmic.o
 obj-$(CONFIG_TPS65911_COMPARATOR)	+= tps65911-comparator.o
 obj-$(CONFIG_MFD_TPS65090)	+= tps65090.o
 obj-$(CONFIG_MFD_AAT2870_CORE)	+= aat2870-core.o
@@ -160,6 +161,8 @@ obj-$(CONFIG_MFD_INTEL_MSIC)	+= intel_msic.o
 obj-$(CONFIG_MFD_PALMAS)	+= palmas.o
 obj-$(CONFIG_MFD_VIPERBOARD)    += viperboard.o
 obj-$(CONFIG_MFD_RC5T583)	+= rc5t583.o rc5t583-irq.o
+obj-$(CONFIG_MFD_RK808)		+= rk808.o
+obj-$(CONFIG_MFD_RN5T618)	+= rn5t618.o
 obj-$(CONFIG_MFD_SEC_CORE)	+= sec-core.o sec-irq.o
 obj-$(CONFIG_MFD_SYSCON)	+= syscon.o
 obj-$(CONFIG_MFD_LM3533)	+= lm3533-core.o lm3533-ctrlbank.o
@@ -169,6 +172,8 @@ obj-$(CONFIG_MFD_AS3711)	+= as3711.o
 obj-$(CONFIG_MFD_AS3722)	+= as3722.o
 obj-$(CONFIG_MFD_STW481X)	+= stw481x.o
 obj-$(CONFIG_MFD_IPAQ_MICRO)	+= ipaq-micro.o
+obj-$(CONFIG_MFD_MENF21BMC)	+= menf21bmc.o
+obj-$(CONFIG_MFD_HI6421_PMIC)	+= hi6421-pmic-core.o
 
 intel-soc-pmic-objs		:= intel_soc_pmic_core.o intel_soc_pmic_crc.o
 obj-$(CONFIG_INTEL_SOC_PMIC)	+= intel-soc-pmic.o
diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c
index 10a0cb90619a..bce7c0784b6b 100644
--- a/drivers/mfd/arizona-core.c
+++ b/drivers/mfd/arizona-core.c
@@ -393,18 +393,6 @@ static int arizona_runtime_resume(struct device *dev)
 		break;
 	}
 
-	switch (arizona->type) {
-	case WM5102:
-		ret = wm5102_patch(arizona);
-		if (ret != 0) {
-			dev_err(arizona->dev, "Failed to apply patch: %d\n",
-				ret);
-			goto err;
-		}
-	default:
-		break;
-	}
-
 	ret = regcache_sync(arizona->regmap);
 	if (ret != 0) {
 		dev_err(arizona->dev, "Failed to restore register cache\n");
@@ -534,7 +522,11 @@ EXPORT_SYMBOL_GPL(arizona_of_get_named_gpio);
 static int arizona_of_get_core_pdata(struct arizona *arizona)
 {
 	struct arizona_pdata *pdata = &arizona->pdata;
+	struct property *prop;
+	const __be32 *cur;
+	u32 val;
 	int ret, i;
+	int count = 0;
 
 	pdata->reset = arizona_of_get_named_gpio(arizona, "wlf,reset", true);
 
@@ -560,6 +552,15 @@ static int arizona_of_get_core_pdata(struct arizona *arizona)
 			ret);
 	}
 
+	of_property_for_each_u32(arizona->dev->of_node, "wlf,inmode", prop,
+				 cur, val) {
+		if (count == ARRAY_SIZE(arizona->pdata.inmode))
+			break;
+
+		arizona->pdata.inmode[count] = val;
+		count++;
+	}
+
 	return 0;
 }
 
@@ -784,7 +785,8 @@ int arizona_dev_init(struct arizona *arizona)
 	/* Ensure device startup is complete */
 	switch (arizona->type) {
 	case WM5102:
-		ret = regmap_read(arizona->regmap, 0x19, &val);
+		ret = regmap_read(arizona->regmap,
+				  ARIZONA_WRITE_SEQUENCER_CTRL_3, &val);
 		if (ret != 0)
 			dev_err(dev,
 				"Failed to check write sequencer state: %d\n",
@@ -945,6 +947,7 @@ int arizona_dev_init(struct arizona *arizona)
 		regmap_update_bits(arizona->regmap,
 				   ARIZONA_MIC_BIAS_CTRL_1 + i,
 				   ARIZONA_MICB1_LVL_MASK |
+				   ARIZONA_MICB1_EXT_CAP |
 				   ARIZONA_MICB1_DISCH |
 				   ARIZONA_MICB1_BYPASS |
 				   ARIZONA_MICB1_RATE, val);
diff --git a/drivers/mfd/arizona-irq.c b/drivers/mfd/arizona-irq.c
index d420dbc0e2b0..3a3fe7cc6d61 100644
--- a/drivers/mfd/arizona-irq.c
+++ b/drivers/mfd/arizona-irq.c
@@ -152,10 +152,18 @@ static void arizona_irq_disable(struct irq_data *data)
 {
 }
 
+static int arizona_irq_set_wake(struct irq_data *data, unsigned int on)
+{
+	struct arizona *arizona = irq_data_get_irq_chip_data(data);
+
+	return irq_set_irq_wake(arizona->irq, on);
+}
+
 static struct irq_chip arizona_irq_chip = {
 	.name			= "arizona",
 	.irq_disable		= arizona_irq_disable,
 	.irq_enable		= arizona_irq_enable,
+	.irq_set_wake		= arizona_irq_set_wake,
 };
 
 static int arizona_irq_map(struct irq_domain *h, unsigned int virq,
@@ -164,7 +172,7 @@ static int arizona_irq_map(struct irq_domain *h, unsigned int virq,
 	struct regmap_irq_chip_data *data = h->host_data;
 
 	irq_set_chip_data(virq, data);
-	irq_set_chip_and_handler(virq, &arizona_irq_chip, handle_edge_irq);
+	irq_set_chip_and_handler(virq, &arizona_irq_chip, handle_simple_irq);
 	irq_set_nested_thread(virq, 1);
 
 	/* ARM needs us to explicitly flag the IRQ as valid
@@ -282,7 +290,7 @@ int arizona_irq_init(struct arizona *arizona)
 
 	ret = regmap_add_irq_chip(arizona->regmap,
 				  irq_create_mapping(arizona->virq, 0),
-				  IRQF_ONESHOT, -1, aod,
+				  IRQF_ONESHOT, 0, aod,
 				  &arizona->aod_irq_chip);
 	if (ret != 0) {
 		dev_err(arizona->dev, "Failed to add AOD IRQs: %d\n", ret);
@@ -291,7 +299,7 @@ int arizona_irq_init(struct arizona *arizona)
 
 	ret = regmap_add_irq_chip(arizona->regmap,
 				  irq_create_mapping(arizona->virq, 1),
-				  IRQF_ONESHOT, -1, irq,
+				  IRQF_ONESHOT, 0, irq,
 				  &arizona->irq_chip);
 	if (ret != 0) {
 		dev_err(arizona->dev, "Failed to add main IRQs: %d\n", ret);
diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c
index 9fc4186d4132..977bd3a3eed0 100644
--- a/drivers/mfd/asic3.c
+++ b/drivers/mfd/asic3.c
@@ -605,7 +605,8 @@ static int asic3_gpio_remove(struct platform_device *pdev)
 {
 	struct asic3 *asic = platform_get_drvdata(pdev);
 
-	return gpiochip_remove(&asic->gpio);
+	gpiochip_remove(&asic->gpio);
+	return 0;
 }
 
 static void asic3_clk_enable(struct asic3 *asic, struct asic3_clk *clk)
diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c
index dee653989e3a..6231adbb295d 100644
--- a/drivers/mfd/axp20x.c
+++ b/drivers/mfd/axp20x.c
@@ -140,15 +140,6 @@ static const struct regmap_irq_chip axp20x_regmap_irq_chip = {
 	.init_ack_masked	= true,
 };
 
-static const char * const axp20x_supplies[] = {
-	"acin",
-	"vin2",
-	"vin3",
-	"ldo24in",
-	"ldo3in",
-	"ldo5in",
-};
-
 static struct mfd_cell axp20x_cells[] = {
 	{
 		.name			= "axp20x-pek",
@@ -156,8 +147,6 @@ static struct mfd_cell axp20x_cells[] = {
 		.resources		= axp20x_pek_resources,
 	}, {
 		.name			= "axp20x-regulator",
-		.parent_supplies	= axp20x_supplies,
-		.num_parent_supplies	= ARRAY_SIZE(axp20x_supplies),
 	},
 };
 
diff --git a/drivers/mfd/cros_ec.c b/drivers/mfd/cros_ec.c
index 4873f9c50452..fc0c81ef04ff 100644
--- a/drivers/mfd/cros_ec.c
+++ b/drivers/mfd/cros_ec.c
@@ -23,6 +23,9 @@
 #include <linux/mfd/core.h>
 #include <linux/mfd/cros_ec.h>
 #include <linux/mfd/cros_ec_commands.h>
+#include <linux/delay.h>
+
+#define EC_COMMAND_RETRIES	50
 
 int cros_ec_prepare_tx(struct cros_ec_device *ec_dev,
 		       struct cros_ec_command *msg)
@@ -62,6 +65,49 @@ int cros_ec_check_result(struct cros_ec_device *ec_dev,
 }
 EXPORT_SYMBOL(cros_ec_check_result);
 
+int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
+		     struct cros_ec_command *msg)
+{
+	int ret;
+
+	mutex_lock(&ec_dev->lock);
+	ret = ec_dev->cmd_xfer(ec_dev, msg);
+	if (msg->result == EC_RES_IN_PROGRESS) {
+		int i;
+		struct cros_ec_command status_msg;
+		struct ec_response_get_comms_status status;
+
+		status_msg.version = 0;
+		status_msg.command = EC_CMD_GET_COMMS_STATUS;
+		status_msg.outdata = NULL;
+		status_msg.outsize = 0;
+		status_msg.indata = (uint8_t *)&status;
+		status_msg.insize = sizeof(status);
+
+		/*
+		 * Query the EC's status until it's no longer busy or
+		 * we encounter an error.
+		 */
+		for (i = 0; i < EC_COMMAND_RETRIES; i++) {
+			usleep_range(10000, 11000);
+
+			ret = ec_dev->cmd_xfer(ec_dev, &status_msg);
+			if (ret < 0)
+				break;
+
+			msg->result = status_msg.result;
+			if (status_msg.result != EC_RES_SUCCESS)
+				break;
+			if (!(status.flags & EC_COMMS_STATUS_PROCESSING))
+				break;
+		}
+	}
+	mutex_unlock(&ec_dev->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(cros_ec_cmd_xfer);
+
 static const struct mfd_cell cros_devs[] = {
 	{
 		.name = "cros-ec-keyb",
@@ -91,6 +137,8 @@ int cros_ec_register(struct cros_ec_device *ec_dev)
 			return -ENOMEM;
 	}
 
+	mutex_init(&ec_dev->lock);
+
 	err = mfd_add_devices(dev, 0, cros_devs,
 			      ARRAY_SIZE(cros_devs),
 			      NULL, ec_dev->irq, NULL);
diff --git a/drivers/mfd/cros_ec_spi.c b/drivers/mfd/cros_ec_spi.c
index 588c700af39c..bf6e08e8013e 100644
--- a/drivers/mfd/cros_ec_spi.c
+++ b/drivers/mfd/cros_ec_spi.c
@@ -65,6 +65,12 @@
   */
 #define EC_SPI_RECOVERY_TIME_NS	(200 * 1000)
 
+/*
+ * The EC is unresponsive for a time after a reboot command.  Add a
+ * simple delay to make sure that the bus stays locked.
+ */
+#define EC_REBOOT_DELAY_MS	50
+
 /**
  * struct cros_ec_spi - information about a SPI-connected EC
  *
@@ -73,13 +79,11 @@
  *	if no record
  * @end_of_msg_delay: used to set the delay_usecs on the spi_transfer that
  *      is sent when we want to turn off CS at the end of a transaction.
- * @lock: mutex to ensure only one user of cros_ec_cmd_xfer_spi at a time
  */
 struct cros_ec_spi {
 	struct spi_device *spi;
 	s64 last_transfer_ns;
 	unsigned int end_of_msg_delay;
-	struct mutex lock;
 };
 
 static void debug_packet(struct device *dev, const char *name, u8 *ptr,
@@ -226,13 +230,6 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
 	int sum;
 	int ret = 0, final_ret;
 
-	/*
-	 * We have the shared ec_dev buffer plus we do lots of separate spi_sync
-	 * calls, so we need to make sure only one person is using this at a
-	 * time.
-	 */
-	mutex_lock(&ec_spi->lock);
-
 	len = cros_ec_prepare_tx(ec_dev, ec_msg);
 	dev_dbg(ec_dev->dev, "prepared, len=%d\n", len);
 
@@ -318,7 +315,9 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
 
 	ret = len;
 exit:
-	mutex_unlock(&ec_spi->lock);
+	if (ec_msg->command == EC_CMD_REBOOT_EC)
+		msleep(EC_REBOOT_DELAY_MS);
+
 	return ret;
 }
 
@@ -350,7 +349,6 @@ static int cros_ec_spi_probe(struct spi_device *spi)
 	if (ec_spi == NULL)
 		return -ENOMEM;
 	ec_spi->spi = spi;
-	mutex_init(&ec_spi->lock);
 	ec_dev = devm_kzalloc(dev, sizeof(*ec_dev), GFP_KERNEL);
 	if (!ec_dev)
 		return -ENOMEM;
diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c
index e8af816d73a9..52a0c2f6264f 100644
--- a/drivers/mfd/da9052-core.c
+++ b/drivers/mfd/da9052-core.c
@@ -522,7 +522,7 @@ static const struct mfd_cell da9052_subdev_info[] = {
 	},
 };
 
-struct regmap_config da9052_regmap_config = {
+const struct regmap_config da9052_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 
diff --git a/drivers/mfd/da9052-i2c.c b/drivers/mfd/da9052-i2c.c
index 6da8ec8ff800..ec39287a245b 100644
--- a/drivers/mfd/da9052-i2c.c
+++ b/drivers/mfd/da9052-i2c.c
@@ -140,13 +140,6 @@ static int da9052_i2c_probe(struct i2c_client *client,
 	if (!da9052)
 		return -ENOMEM;
 
-	if (!i2c_check_functionality(client->adapter,
-				     I2C_FUNC_SMBUS_BYTE_DATA)) {
-		dev_info(&client->dev, "Error in %s:i2c_check_functionality\n",
-			 __func__);
-		return  -ENODEV;
-	}
-
 	da9052->dev = &client->dev;
 	da9052->chip_irq = client->irq;
 	da9052->fix_io = da9052_i2c_fix;
diff --git a/drivers/mfd/da9052-spi.c b/drivers/mfd/da9052-spi.c
index 17666b40b70c..45ae0b7d13ef 100644
--- a/drivers/mfd/da9052-spi.c
+++ b/drivers/mfd/da9052-spi.c
@@ -23,6 +23,7 @@
 
 static int da9052_spi_probe(struct spi_device *spi)
 {
+	struct regmap_config config;
 	int ret;
 	const struct spi_device_id *id = spi_get_device_id(spi);
 	struct da9052 *da9052;
@@ -40,10 +41,10 @@ static int da9052_spi_probe(struct spi_device *spi)
 
 	spi_set_drvdata(spi, da9052);
 
-	da9052_regmap_config.read_flag_mask = 1;
-	da9052_regmap_config.write_flag_mask = 0;
+	config = da9052_regmap_config;
+	config.read_flag_mask = 1;
 
-	da9052->regmap = devm_regmap_init_spi(spi, &da9052_regmap_config);
+	da9052->regmap = devm_regmap_init_spi(spi, &config);
 	if (IS_ERR(da9052->regmap)) {
 		ret = PTR_ERR(da9052->regmap);
 		dev_err(&spi->dev, "Failed to allocate register map: %d\n",
diff --git a/drivers/mfd/hi6421-pmic-core.c b/drivers/mfd/hi6421-pmic-core.c
new file mode 100644
index 000000000000..321a2656fd00
--- /dev/null
+++ b/drivers/mfd/hi6421-pmic-core.c
@@ -0,0 +1,113 @@
+/*
+ * Device driver for Hi6421 IC
+ *
+ * Copyright (c) <2011-2014> HiSilicon Technologies Co., Ltd.
+ *              http://www.hisilicon.com
+ * Copyright (c) <2013-2014> Linaro Ltd.
+ *              http://www.linaro.org
+ *
+ * Author: Guodong Xu <guodong.xu@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/mfd/hi6421-pmic.h>
+
+static const struct mfd_cell hi6421_devs[] = {
+	{ .name = "hi6421-regulator", },
+};
+
+static struct regmap_config hi6421_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 8,
+	.max_register = HI6421_REG_TO_BUS_ADDR(HI6421_REG_MAX),
+};
+
+static int hi6421_pmic_probe(struct platform_device *pdev)
+{
+	struct hi6421_pmic *pmic;
+	struct resource *res;
+	void __iomem *base;
+	int ret;
+
+	pmic = devm_kzalloc(&pdev->dev, sizeof(*pmic), GFP_KERNEL);
+	if (!pmic)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	pmic->regmap = devm_regmap_init_mmio_clk(&pdev->dev, NULL, base,
+						 &hi6421_regmap_config);
+	if (IS_ERR(pmic->regmap)) {
+		dev_err(&pdev->dev,
+			"regmap init failed: %ld\n", PTR_ERR(pmic->regmap));
+		return PTR_ERR(pmic->regmap);
+	}
+
+	/* set over-current protection debounce 8ms */
+	regmap_update_bits(pmic->regmap, HI6421_OCP_DEB_CTRL_REG,
+				(HI6421_OCP_DEB_SEL_MASK
+				 | HI6421_OCP_EN_DEBOUNCE_MASK
+				 | HI6421_OCP_AUTO_STOP_MASK),
+				(HI6421_OCP_DEB_SEL_8MS
+				 | HI6421_OCP_EN_DEBOUNCE_ENABLE));
+
+	platform_set_drvdata(pdev, pmic);
+
+	ret = mfd_add_devices(&pdev->dev, 0, hi6421_devs,
+			ARRAY_SIZE(hi6421_devs), NULL, 0, NULL);
+	if (ret) {
+		dev_err(&pdev->dev, "add mfd devices failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int hi6421_pmic_remove(struct platform_device *pdev)
+{
+	mfd_remove_devices(&pdev->dev);
+
+	return 0;
+}
+
+static struct of_device_id of_hi6421_pmic_match_tbl[] = {
+	{ .compatible = "hisilicon,hi6421-pmic", },
+	{ },
+};
+
+static struct platform_driver hi6421_pmic_driver = {
+	.driver = {
+		.name	= "hi6421_pmic",
+		.of_match_table = of_hi6421_pmic_match_tbl,
+	},
+	.probe	= hi6421_pmic_probe,
+	.remove	= hi6421_pmic_remove,
+};
+module_platform_driver(hi6421_pmic_driver);
+
+MODULE_AUTHOR("Guodong Xu <guodong.xu@linaro.org>");
+MODULE_DESCRIPTION("Hi6421 PMIC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/htc-i2cpld.c b/drivers/mfd/htc-i2cpld.c
index 6bdb78c2ac77..ebb9cf19e347 100644
--- a/drivers/mfd/htc-i2cpld.c
+++ b/drivers/mfd/htc-i2cpld.c
@@ -227,15 +227,12 @@ static irqreturn_t htcpld_handler(int irq, void *dev)
 static void htcpld_chip_set(struct gpio_chip *chip, unsigned offset, int val)
 {
 	struct i2c_client *client;
-	struct htcpld_chip *chip_data;
+	struct htcpld_chip *chip_data =
+		container_of(chip, struct htcpld_chip, chip_out);
 	unsigned long flags;
 
-	chip_data = container_of(chip, struct htcpld_chip, chip_out);
-	if (!chip_data)
-		return;
-
 	client = chip_data->client;
-	if (client == NULL)
+	if (!client)
 		return;
 
 	spin_lock_irqsave(&chip_data->lock, flags);
@@ -261,31 +258,18 @@ static void htcpld_chip_set_ni(struct work_struct *work)
 static int htcpld_chip_get(struct gpio_chip *chip, unsigned offset)
 {
 	struct htcpld_chip *chip_data;
-	int val = 0;
-	int is_input = 0;
-
-	/* Try out first */
-	chip_data = container_of(chip, struct htcpld_chip, chip_out);
-	if (!chip_data) {
-		/* Try in */
-		is_input = 1;
-		chip_data = container_of(chip, struct htcpld_chip, chip_in);
-		if (!chip_data)
-			return -EINVAL;
-	}
+	u8 cache;
 
-	/* Determine if this is an input or output GPIO */
-	if (!is_input)
-		/* Use the output cache */
-		val = (chip_data->cache_out >> offset) & 1;
-	else
-		/* Use the input cache */
-		val = (chip_data->cache_in >> offset) & 1;
+	if (!strncmp(chip->label, "htcpld-out", 10)) {
+		chip_data = container_of(chip, struct htcpld_chip, chip_out);
+		cache = chip_data->cache_out;
+	} else if (!strncmp(chip->label, "htcpld-in", 9)) {
+		chip_data = container_of(chip, struct htcpld_chip, chip_in);
+		cache = chip_data->cache_in;
+	} else
+		return -EINVAL;
 
-	if (val)
-		return 1;
-	else
-		return 0;
+	return (cache >> offset) & 1;
 }
 
 static int htcpld_direction_output(struct gpio_chip *chip,
@@ -376,7 +360,7 @@ static int htcpld_register_chip_i2c(
 	plat_chip_data = &pdata->chip[chip_index];
 
 	adapter = i2c_get_adapter(pdata->i2c_adapter_id);
-	if (adapter == NULL) {
+	if (!adapter) {
 		/* Eek, no such I2C adapter!  Bail out. */
 		dev_warn(dev, "Chip at i2c address 0x%x: Invalid i2c adapter %d\n",
 			 plat_chip_data->addr, pdata->i2c_adapter_id);
@@ -481,15 +465,9 @@ static int htcpld_register_chip_gpio(
 
 	ret = gpiochip_add(&(chip->chip_in));
 	if (ret) {
-		int error;
-
 		dev_warn(dev, "Unable to register input GPIOs for 0x%x: %d\n",
 			 plat_chip_data->addr, ret);
-
-		error = gpiochip_remove(&(chip->chip_out));
-		if (error)
-			dev_warn(dev, "Error while trying to unregister gpio chip: %d\n", error);
-
+		gpiochip_remove(&(chip->chip_out));
 		return ret;
 	}
 
diff --git a/drivers/mfd/intel_soc_pmic_core.c b/drivers/mfd/intel_soc_pmic_core.c
index 2720922f90b4..df7b0642a5b4 100644
--- a/drivers/mfd/intel_soc_pmic_core.c
+++ b/drivers/mfd/intel_soc_pmic_core.c
@@ -115,6 +115,7 @@ static void intel_soc_pmic_shutdown(struct i2c_client *i2c)
 	return;
 }
 
+#if defined(CONFIG_PM_SLEEP)
 static int intel_soc_pmic_suspend(struct device *dev)
 {
 	struct intel_soc_pmic *pmic = dev_get_drvdata(dev);
@@ -132,6 +133,7 @@ static int intel_soc_pmic_resume(struct device *dev)
 
 	return 0;
 }
+#endif
 
 static SIMPLE_DEV_PM_OPS(intel_soc_pmic_pm_ops, intel_soc_pmic_suspend,
 			 intel_soc_pmic_resume);
diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
index 7d8482ff5868..f35d4280b2f7 100644
--- a/drivers/mfd/lpc_ich.c
+++ b/drivers/mfd/lpc_ich.c
@@ -54,6 +54,7 @@
  *	document number TBD : Avoton SoC
  *	document number TBD : Coleto Creek
  *	document number TBD : Wildcat Point-LP
+ *	document number TBD : 9 Series
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -216,6 +217,8 @@ enum lpc_chipsets {
 	LPC_BAYTRAIL,   /* Bay Trail SoC */
 	LPC_COLETO,	/* Coleto Creek */
 	LPC_WPT_LP,	/* Wildcat Point-LP */
+	LPC_BRASWELL,	/* Braswell SoC */
+	LPC_9S,		/* 9 Series */
 };
 
 static struct lpc_ich_info lpc_chipset_info[] = {
@@ -519,6 +522,14 @@ static struct lpc_ich_info lpc_chipset_info[] = {
 		.name = "Wildcat Point_LP",
 		.iTCO_version = 2,
 	},
+	[LPC_BRASWELL] = {
+		.name = "Braswell SoC",
+		.iTCO_version = 3,
+	},
+	[LPC_9S] = {
+		.name = "9 Series",
+		.iTCO_version = 2,
+	},
 };
 
 /*
@@ -745,6 +756,12 @@ static const struct pci_device_id lpc_ich_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x9cc6), LPC_WPT_LP},
 	{ PCI_VDEVICE(INTEL, 0x9cc7), LPC_WPT_LP},
 	{ PCI_VDEVICE(INTEL, 0x9cc9), LPC_WPT_LP},
+	{ PCI_VDEVICE(INTEL, 0x229c), LPC_BRASWELL},
+	{ PCI_VDEVICE(INTEL, 0x8cc1), LPC_9S},
+	{ PCI_VDEVICE(INTEL, 0x8cc2), LPC_9S},
+	{ PCI_VDEVICE(INTEL, 0x8cc3), LPC_9S},
+	{ PCI_VDEVICE(INTEL, 0x8cc4), LPC_9S},
+	{ PCI_VDEVICE(INTEL, 0x8cc6), LPC_9S},
 	{ 0, },			/* End of list */
 };
 MODULE_DEVICE_TABLE(pci, lpc_ich_ids);
diff --git a/drivers/mfd/lpc_sch.c b/drivers/mfd/lpc_sch.c
index 4ee755034f3b..c980da479a35 100644
--- a/drivers/mfd/lpc_sch.c
+++ b/drivers/mfd/lpc_sch.c
@@ -7,6 +7,7 @@
  *  Configuration Registers.
  *
  *  Copyright (c) 2010 CompuLab Ltd
+ *  Copyright (c) 2014 Intel Corp.
  *  Author: Denis Turischev <denis@compulab.co.il>
  *
  *  This program is free software; you can redistribute it and/or modify
@@ -17,10 +18,6 @@
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; see the file COPYING.  If not, write to
- *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/kernel.h>
@@ -37,123 +34,165 @@
 #define GPIO_IO_SIZE	64
 #define GPIO_IO_SIZE_CENTERTON	128
 
+/* Intel Quark X1000 GPIO IRQ Number */
+#define GPIO_IRQ_QUARK_X1000	9
+
 #define WDTBASE		0x84
 #define WDT_IO_SIZE	64
 
-static struct resource smbus_sch_resource = {
-		.flags = IORESOURCE_IO,
-};
-
-static struct resource gpio_sch_resource = {
-		.flags = IORESOURCE_IO,
-};
-
-static struct resource wdt_sch_resource = {
-		.flags = IORESOURCE_IO,
+enum sch_chipsets {
+	LPC_SCH = 0,		/* Intel Poulsbo SCH */
+	LPC_ITC,		/* Intel Tunnel Creek */
+	LPC_CENTERTON,		/* Intel Centerton */
+	LPC_QUARK_X1000,	/* Intel Quark X1000 */
 };
 
-static struct mfd_cell lpc_sch_cells[3];
-
-static struct mfd_cell isch_smbus_cell = {
-	.name = "isch_smbus",
-	.num_resources = 1,
-	.resources = &smbus_sch_resource,
-	.ignore_resource_conflicts = true,
+struct lpc_sch_info {
+	unsigned int io_size_smbus;
+	unsigned int io_size_gpio;
+	unsigned int io_size_wdt;
+	int irq_gpio;
 };
 
-static struct mfd_cell sch_gpio_cell = {
-	.name = "sch_gpio",
-	.num_resources = 1,
-	.resources = &gpio_sch_resource,
-	.ignore_resource_conflicts = true,
-};
-
-static struct mfd_cell wdt_sch_cell = {
-	.name = "ie6xx_wdt",
-	.num_resources = 1,
-	.resources = &wdt_sch_resource,
-	.ignore_resource_conflicts = true,
+static struct lpc_sch_info sch_chipset_info[] = {
+	[LPC_SCH] = {
+		.io_size_smbus = SMBUS_IO_SIZE,
+		.io_size_gpio = GPIO_IO_SIZE,
+		.irq_gpio = -1,
+	},
+	[LPC_ITC] = {
+		.io_size_smbus = SMBUS_IO_SIZE,
+		.io_size_gpio = GPIO_IO_SIZE,
+		.io_size_wdt = WDT_IO_SIZE,
+		.irq_gpio = -1,
+	},
+	[LPC_CENTERTON] = {
+		.io_size_smbus = SMBUS_IO_SIZE,
+		.io_size_gpio = GPIO_IO_SIZE_CENTERTON,
+		.io_size_wdt = WDT_IO_SIZE,
+		.irq_gpio = -1,
+	},
+	[LPC_QUARK_X1000] = {
+		.io_size_gpio = GPIO_IO_SIZE,
+		.irq_gpio = GPIO_IRQ_QUARK_X1000,
+	},
 };
 
 static const struct pci_device_id lpc_sch_ids[] = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SCH_LPC) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ITC_LPC) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CENTERTON_ILB) },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_SCH_LPC), LPC_SCH },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ITC_LPC), LPC_ITC },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CENTERTON_ILB), LPC_CENTERTON },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB), LPC_QUARK_X1000 },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, lpc_sch_ids);
 
-static int lpc_sch_probe(struct pci_dev *dev,
-				const struct pci_device_id *id)
+#define LPC_NO_RESOURCE		1
+#define LPC_SKIP_RESOURCE	2
+
+static int lpc_sch_get_io(struct pci_dev *pdev, int where, const char *name,
+			  struct resource *res, int size)
 {
 	unsigned int base_addr_cfg;
 	unsigned short base_addr;
-	int i, cells = 0;
-	int ret;
 
-	pci_read_config_dword(dev, SMBASE, &base_addr_cfg);
+	if (size == 0)
+		return LPC_NO_RESOURCE;
+
+	pci_read_config_dword(pdev, where, &base_addr_cfg);
 	base_addr = 0;
 	if (!(base_addr_cfg & (1 << 31)))
-		dev_warn(&dev->dev, "Decode of the SMBus I/O range disabled\n");
+		dev_warn(&pdev->dev, "Decode of the %s I/O range disabled\n",
+			 name);
 	else
 		base_addr = (unsigned short)base_addr_cfg;
 
 	if (base_addr == 0) {
-		dev_warn(&dev->dev, "I/O space for SMBus uninitialized\n");
-	} else {
-		lpc_sch_cells[cells++] = isch_smbus_cell;
-		smbus_sch_resource.start = base_addr;
-		smbus_sch_resource.end = base_addr + SMBUS_IO_SIZE - 1;
+		dev_warn(&pdev->dev, "I/O space for %s uninitialized\n", name);
+		return LPC_SKIP_RESOURCE;
 	}
 
-	pci_read_config_dword(dev, GPIOBASE, &base_addr_cfg);
-	base_addr = 0;
-	if (!(base_addr_cfg & (1 << 31)))
-		dev_warn(&dev->dev, "Decode of the GPIO I/O range disabled\n");
-	else
-		base_addr = (unsigned short)base_addr_cfg;
+	res->start = base_addr;
+	res->end = base_addr + size - 1;
+	res->flags = IORESOURCE_IO;
 
-	if (base_addr == 0) {
-		dev_warn(&dev->dev, "I/O space for GPIO uninitialized\n");
-	} else {
-		lpc_sch_cells[cells++] = sch_gpio_cell;
-		gpio_sch_resource.start = base_addr;
-		if (id->device == PCI_DEVICE_ID_INTEL_CENTERTON_ILB)
-			gpio_sch_resource.end = base_addr + GPIO_IO_SIZE_CENTERTON - 1;
-		else
-			gpio_sch_resource.end = base_addr + GPIO_IO_SIZE - 1;
-	}
+	return 0;
+}
 
-	if (id->device == PCI_DEVICE_ID_INTEL_ITC_LPC
-	    || id->device == PCI_DEVICE_ID_INTEL_CENTERTON_ILB) {
-		pci_read_config_dword(dev, WDTBASE, &base_addr_cfg);
-		base_addr = 0;
-		if (!(base_addr_cfg & (1 << 31)))
-			dev_warn(&dev->dev, "Decode of the WDT I/O range disabled\n");
-		else
-			base_addr = (unsigned short)base_addr_cfg;
-		if (base_addr == 0)
-			dev_warn(&dev->dev, "I/O space for WDT uninitialized\n");
-		else {
-			lpc_sch_cells[cells++] = wdt_sch_cell;
-			wdt_sch_resource.start = base_addr;
-			wdt_sch_resource.end = base_addr + WDT_IO_SIZE - 1;
-		}
-	}
+static int lpc_sch_populate_cell(struct pci_dev *pdev, int where,
+				 const char *name, int size, int irq,
+				 int id, struct mfd_cell *cell)
+{
+	struct resource *res;
+	int ret;
 
-	if (WARN_ON(cells > ARRAY_SIZE(lpc_sch_cells))) {
-		dev_err(&dev->dev, "Cell count exceeds array size");
-		return -ENODEV;
-	}
+	res = devm_kcalloc(&pdev->dev, 2, sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+
+	ret = lpc_sch_get_io(pdev, where, name, res, size);
+	if (ret)
+		return ret;
+
+	memset(cell, 0, sizeof(*cell));
+
+	cell->name = name;
+	cell->resources = res;
+	cell->num_resources = 1;
+	cell->ignore_resource_conflicts = true;
+	cell->id = id;
+
+	/* Check if we need to add an IRQ resource */
+	if (irq < 0)
+		return 0;
+
+	res++;
+
+	res->start = irq;
+	res->end = irq;
+	res->flags = IORESOURCE_IRQ;
+
+	cell->num_resources++;
+
+	return 0;
+}
+
+static int lpc_sch_probe(struct pci_dev *dev, const struct pci_device_id *id)
+{
+	struct mfd_cell lpc_sch_cells[3];
+	struct lpc_sch_info *info = &sch_chipset_info[id->driver_data];
+	unsigned int cells = 0;
+	int ret;
+
+	ret = lpc_sch_populate_cell(dev, SMBASE, "isch_smbus",
+				    info->io_size_smbus, -1,
+				    id->device, &lpc_sch_cells[cells]);
+	if (ret < 0)
+		return ret;
+	if (ret == 0)
+		cells++;
+
+	ret = lpc_sch_populate_cell(dev, GPIOBASE, "sch_gpio",
+				    info->io_size_gpio, info->irq_gpio,
+				    id->device, &lpc_sch_cells[cells]);
+	if (ret < 0)
+		return ret;
+	if (ret == 0)
+		cells++;
+
+	ret = lpc_sch_populate_cell(dev, WDTBASE, "ie6xx_wdt",
+				    info->io_size_wdt, -1,
+				    id->device, &lpc_sch_cells[cells]);
+	if (ret < 0)
+		return ret;
+	if (ret == 0)
+		cells++;
 
 	if (cells == 0) {
 		dev_err(&dev->dev, "All decode registers disabled.\n");
 		return -ENODEV;
 	}
 
-	for (i = 0; i < cells; i++)
-		lpc_sch_cells[i].id = id->device;
-
 	ret = mfd_add_devices(&dev->dev, 0, lpc_sch_cells, cells, NULL, 0, NULL);
 	if (ret)
 		mfd_remove_devices(&dev->dev);
diff --git a/drivers/mfd/max14577.c b/drivers/mfd/max14577.c
index 4a5e885383f8..de96b7fb1f6d 100644
--- a/drivers/mfd/max14577.c
+++ b/drivers/mfd/max14577.c
@@ -26,6 +26,87 @@
 #include <linux/mfd/max14577.h>
 #include <linux/mfd/max14577-private.h>
 
+/*
+ * Table of valid charger currents for different Maxim chipsets.
+ * It is placed here because it is used by both charger and regulator driver.
+ */
+const struct maxim_charger_current maxim_charger_currents[] = {
+	[MAXIM_DEVICE_TYPE_UNKNOWN] = { 0, 0, 0, 0 },
+	[MAXIM_DEVICE_TYPE_MAX14577] = {
+		.min		= MAX14577_CHARGER_CURRENT_LIMIT_MIN,
+		.high_start	= MAX14577_CHARGER_CURRENT_LIMIT_HIGH_START,
+		.high_step	= MAX14577_CHARGER_CURRENT_LIMIT_HIGH_STEP,
+		.max		= MAX14577_CHARGER_CURRENT_LIMIT_MAX,
+	},
+	[MAXIM_DEVICE_TYPE_MAX77836] = {
+		.min		= MAX77836_CHARGER_CURRENT_LIMIT_MIN,
+		.high_start	= MAX77836_CHARGER_CURRENT_LIMIT_HIGH_START,
+		.high_step	= MAX77836_CHARGER_CURRENT_LIMIT_HIGH_STEP,
+		.max		= MAX77836_CHARGER_CURRENT_LIMIT_MAX,
+	},
+};
+EXPORT_SYMBOL_GPL(maxim_charger_currents);
+
+/*
+ * maxim_charger_calc_reg_current - Calculate register value for current
+ * @limits:	constraints for charger, matching the MBCICHWRC register
+ * @min_ua:	minimal requested current, micro Amps
+ * @max_ua:	maximum requested current, micro Amps
+ * @dst:	destination to store calculated register value
+ *
+ * Calculates the value of MBCICHWRC (Fast Battery Charge Current) register
+ * for given current and stores it under pointed 'dst'. The stored value
+ * combines low bit (MBCICHWRCL) and high bits (MBCICHWRCH). It is also
+ * properly shifted.
+ *
+ * The calculated register value matches the current which:
+ *  - is always between <limits.min, limits.max>;
+ *  - is always less or equal to max_ua;
+ *  - is the highest possible value;
+ *  - may be lower than min_ua.
+ *
+ * On success returns 0. On error returns -EINVAL (requested min/max current
+ * is outside of given charger limits) and 'dst' is not set.
+ */
+int maxim_charger_calc_reg_current(const struct maxim_charger_current *limits,
+		unsigned int min_ua, unsigned int max_ua, u8 *dst)
+{
+	unsigned int current_bits = 0xf;
+
+	if (min_ua > max_ua)
+		return -EINVAL;
+
+	if (min_ua > limits->max || max_ua < limits->min)
+		return -EINVAL;
+
+	if (max_ua < limits->high_start) {
+		/*
+		 * Less than high_start, so set the minimal current
+		 * (turn Low Bit off, 0 as high bits).
+		 */
+		*dst = 0x0;
+		return 0;
+	}
+
+	/* max_ua is in range: <high_start, infinite>, cut it to limits.max */
+	max_ua = min(limits->max, max_ua);
+	max_ua -= limits->high_start;
+	/*
+	 * There is no risk of overflow 'max_ua' here because:
+	 *  - max_ua >= limits.high_start
+	 *  - BUILD_BUG checks that 'limits' are: max >= high_start + high_step
+	 */
+	current_bits = max_ua / limits->high_step;
+
+	/* Turn Low Bit on (use range <limits.high_start, limits.max>) ... */
+	*dst = 0x1 << CHGCTRL4_MBCICHWRCL_SHIFT;
+	/* and set proper High Bits */
+	*dst |= current_bits << CHGCTRL4_MBCICHWRCH_SHIFT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(maxim_charger_calc_reg_current);
+
 static const struct mfd_cell max14577_devs[] = {
 	{
 		.name = "max14577-muic",
@@ -35,7 +116,10 @@ static const struct mfd_cell max14577_devs[] = {
 		.name = "max14577-regulator",
 		.of_compatible = "maxim,max14577-regulator",
 	},
-	{ .name = "max14577-charger", },
+	{
+		.name = "max14577-charger",
+		.of_compatible = "maxim,max14577-charger",
+	},
 };
 
 static const struct mfd_cell max77836_devs[] = {
@@ -372,8 +456,7 @@ static int max14577_i2c_probe(struct i2c_client *i2c,
 	}
 
 	ret = mfd_add_devices(max14577->dev, -1, mfd_devs,
-			mfd_devs_size, NULL, 0,
-			regmap_irq_get_domain(max14577->irq_data));
+			mfd_devs_size, NULL, 0, NULL);
 	if (ret < 0)
 		goto err_mfd;
 
@@ -463,6 +546,20 @@ static int __init max14577_i2c_init(void)
 	BUILD_BUG_ON(ARRAY_SIZE(max14577_i2c_id) != MAXIM_DEVICE_TYPE_NUM);
 	BUILD_BUG_ON(ARRAY_SIZE(max14577_dt_match) != MAXIM_DEVICE_TYPE_NUM);
 
+	/* Valid charger current values must be provided for each chipset */
+	BUILD_BUG_ON(ARRAY_SIZE(maxim_charger_currents) != MAXIM_DEVICE_TYPE_NUM);
+
+	/* Check for valid values for charger */
+	BUILD_BUG_ON(MAX14577_CHARGER_CURRENT_LIMIT_HIGH_START +
+			MAX14577_CHARGER_CURRENT_LIMIT_HIGH_STEP * 0xf !=
+			MAX14577_CHARGER_CURRENT_LIMIT_MAX);
+	BUILD_BUG_ON(MAX14577_CHARGER_CURRENT_LIMIT_HIGH_STEP == 0);
+
+	BUILD_BUG_ON(MAX77836_CHARGER_CURRENT_LIMIT_HIGH_START +
+			MAX77836_CHARGER_CURRENT_LIMIT_HIGH_STEP * 0xf !=
+			MAX77836_CHARGER_CURRENT_LIMIT_MAX);
+	BUILD_BUG_ON(MAX77836_CHARGER_CURRENT_LIMIT_HIGH_STEP == 0);
+
 	return i2c_add_driver(&max14577_i2c_driver);
 }
 subsys_initcall(max14577_i2c_init);
diff --git a/drivers/mfd/max77686.c b/drivers/mfd/max77686.c
index 86e552348db4..929795eae9fc 100644
--- a/drivers/mfd/max77686.c
+++ b/drivers/mfd/max77686.c
@@ -52,7 +52,7 @@ static const struct mfd_cell max77802_devs[] = {
 static bool max77802_pmic_is_accessible_reg(struct device *dev,
 					    unsigned int reg)
 {
-	return (reg >= MAX77802_REG_DEVICE_ID && reg < MAX77802_REG_PMIC_END);
+	return reg < MAX77802_REG_PMIC_END;
 }
 
 static bool max77802_rtc_is_accessible_reg(struct device *dev,
diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c
index 249c139ef04a..cf008f45968c 100644
--- a/drivers/mfd/max77693.c
+++ b/drivers/mfd/max77693.c
@@ -44,9 +44,12 @@
 static const struct mfd_cell max77693_devs[] = {
 	{ .name = "max77693-pmic", },
 	{ .name = "max77693-charger", },
-	{ .name = "max77693-flash", },
 	{ .name = "max77693-muic", },
 	{ .name = "max77693-haptic", },
+	{
+		.name = "max77693-flash",
+		.of_compatible = "maxim,max77693-flash",
+	},
 };
 
 static const struct regmap_config max77693_regmap_config = {
diff --git a/drivers/mfd/max8925-i2c.c b/drivers/mfd/max8925-i2c.c
index ecbe78ead3b6..c880c895c5a6 100644
--- a/drivers/mfd/max8925-i2c.c
+++ b/drivers/mfd/max8925-i2c.c
@@ -37,7 +37,7 @@ static inline int max8925_read_device(struct i2c_client *i2c,
 static inline int max8925_write_device(struct i2c_client *i2c,
 				       int reg, int bytes, void *src)
 {
-	unsigned char buf[bytes + 1];
+	unsigned char buf[9];
 	int ret;
 
 	buf[0] = (unsigned char)reg;
diff --git a/drivers/mfd/mc13xxx-core.c b/drivers/mfd/mc13xxx-core.c
index 2b6bc868cd3d..64dde5d24b32 100644
--- a/drivers/mfd/mc13xxx-core.c
+++ b/drivers/mfd/mc13xxx-core.c
@@ -36,6 +36,9 @@
 #define MC34708_REVISION_FIN		(0x07 <<  6)
 #define MC34708_REVISION_FAB		(0x07 <<  9)
 
+#define MC13XXX_PWRCTRL		15
+#define MC13XXX_PWRCTRL_WDIRESET	(1 << 12)
+
 #define MC13XXX_ADC1		44
 #define MC13XXX_ADC1_ADEN		(1 << 0)
 #define MC13XXX_ADC1_RAND		(1 << 1)
@@ -416,6 +419,11 @@ int mc13xxx_common_init(struct device *dev)
 
 	mc13xxx->variant->print_revision(mc13xxx, revision);
 
+	ret = mc13xxx_reg_rmw(mc13xxx, MC13XXX_PWRCTRL,
+			MC13XXX_PWRCTRL_WDIRESET, MC13XXX_PWRCTRL_WDIRESET);
+	if (ret)
+		return ret;
+
 	for (i = 0; i < ARRAY_SIZE(mc13xxx->irqs); i++) {
 		mc13xxx->irqs[i].reg_offset = i / MC13XXX_IRQ_PER_REG;
 		mc13xxx->irqs[i].mask = BIT(i % MC13XXX_IRQ_PER_REG);
diff --git a/drivers/mfd/menelaus.c b/drivers/mfd/menelaus.c
index 5e2667afe2bc..9f01aef539dd 100644
--- a/drivers/mfd/menelaus.c
+++ b/drivers/mfd/menelaus.c
@@ -466,8 +466,6 @@ static int menelaus_set_voltage(const struct menelaus_vtg *vtg, int mV,
 	struct i2c_client *c = the_menelaus->client;
 
 	mutex_lock(&the_menelaus->lock);
-	if (!vtg)
-		goto set_voltage;
 
 	ret = menelaus_read_reg(vtg->vtg_reg);
 	if (ret < 0)
@@ -482,7 +480,6 @@ static int menelaus_set_voltage(const struct menelaus_vtg *vtg, int mV,
 	ret = menelaus_write_reg(vtg->vtg_reg, val);
 	if (ret < 0)
 		goto out;
-set_voltage:
 	ret = menelaus_write_reg(vtg->mode_reg, mode);
 out:
 	mutex_unlock(&the_menelaus->lock);
@@ -1186,7 +1183,7 @@ static int menelaus_probe(struct i2c_client *client,
 			  const struct i2c_device_id *id)
 {
 	struct menelaus_chip	*menelaus;
-	int			rev = 0, val;
+	int			rev = 0;
 	int			err = 0;
 	struct menelaus_platform_data *menelaus_pdata =
 					dev_get_platdata(&client->dev);
@@ -1239,10 +1236,10 @@ static int menelaus_probe(struct i2c_client *client,
 
 	pr_info("Menelaus rev %d.%d\n", rev >> 4, rev & 0x0f);
 
-	val = menelaus_read_reg(MENELAUS_VCORE_CTRL1);
-	if (val < 0)
+	err = menelaus_read_reg(MENELAUS_VCORE_CTRL1);
+	if (err < 0)
 		goto fail;
-	if (val & (1 << 7))
+	if (err & BIT(7))
 		menelaus->vcore_hw_mode = 1;
 	else
 		menelaus->vcore_hw_mode = 0;
diff --git a/drivers/mfd/menf21bmc.c b/drivers/mfd/menf21bmc.c
new file mode 100644
index 000000000000..1c274345820c
--- /dev/null
+++ b/drivers/mfd/menf21bmc.c
@@ -0,0 +1,132 @@
+/*
+ *  MEN 14F021P00 Board Management Controller (BMC) MFD Core Driver.
+ *
+ *  Copyright (C) 2014 MEN Mikro Elektronik Nuernberg GmbH
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/mfd/core.h>
+
+#define BMC_CMD_WDT_EXIT_PROD	0x18
+#define BMC_CMD_WDT_PROD_STAT	0x19
+#define BMC_CMD_REV_MAJOR	0x80
+#define BMC_CMD_REV_MINOR	0x81
+#define BMC_CMD_REV_MAIN	0x82
+
+static struct mfd_cell menf21bmc_cell[] = {
+	{ .name = "menf21bmc_wdt", },
+	{ .name = "menf21bmc_led", },
+	{ .name = "menf21bmc_hwmon", }
+};
+
+static int menf21bmc_wdt_exit_prod_mode(struct i2c_client *client)
+{
+	int val, ret;
+
+	val = i2c_smbus_read_byte_data(client, BMC_CMD_WDT_PROD_STAT);
+	if (val < 0)
+		return val;
+
+	/*
+	 * Production mode should be not active after delivery of the Board.
+	 * To be sure we check it, inform the user and exit the mode
+	 * if active.
+	 */
+	if (val == 0x00) {
+		dev_info(&client->dev,
+			"BMC in production mode. Exit production mode\n");
+
+		ret = i2c_smbus_write_byte(client, BMC_CMD_WDT_EXIT_PROD);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int
+menf21bmc_probe(struct i2c_client *client, const struct i2c_device_id *ids)
+{
+	int rev_major, rev_minor, rev_main;
+	int ret;
+
+	ret = i2c_check_functionality(client->adapter,
+				      I2C_FUNC_SMBUS_BYTE_DATA |
+				      I2C_FUNC_SMBUS_WORD_DATA |
+				      I2C_FUNC_SMBUS_BYTE);
+	if (!ret)
+		return -ENODEV;
+
+	rev_major = i2c_smbus_read_word_data(client, BMC_CMD_REV_MAJOR);
+	if (rev_major < 0) {
+		dev_err(&client->dev, "failed to get BMC major revision\n");
+		return rev_major;
+	}
+
+	rev_minor = i2c_smbus_read_word_data(client, BMC_CMD_REV_MINOR);
+	if (rev_minor < 0) {
+		dev_err(&client->dev, "failed to get BMC minor revision\n");
+		return rev_minor;
+	}
+
+	rev_main = i2c_smbus_read_word_data(client, BMC_CMD_REV_MAIN);
+	if (rev_main < 0) {
+		dev_err(&client->dev, "failed to get BMC main revision\n");
+		return rev_main;
+	}
+
+	dev_info(&client->dev, "FW Revision: %02d.%02d.%02d\n",
+		 rev_major, rev_minor, rev_main);
+
+	/*
+	 * We have to exit the Production Mode of the BMC to activate the
+	 * Watchdog functionality and the BIOS life sign monitoring.
+	 */
+	ret = menf21bmc_wdt_exit_prod_mode(client);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed to leave production mode\n");
+		return ret;
+	}
+
+	ret = mfd_add_devices(&client->dev, 0, menf21bmc_cell,
+			      ARRAY_SIZE(menf21bmc_cell), NULL, 0, NULL);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed to add BMC sub-devices\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int menf21bmc_remove(struct i2c_client *client)
+{
+	mfd_remove_devices(&client->dev);
+	return 0;
+}
+
+static const struct i2c_device_id menf21bmc_id_table[] = {
+	{ "menf21bmc" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, menf21bmc_id_table);
+
+static struct i2c_driver menf21bmc_driver = {
+	.driver.name	= "menf21bmc",
+	.id_table	= menf21bmc_id_table,
+	.probe		= menf21bmc_probe,
+	.remove		= menf21bmc_remove,
+};
+
+module_i2c_driver(menf21bmc_driver);
+
+MODULE_DESCRIPTION("MEN 14F021P00 BMC mfd core driver");
+MODULE_AUTHOR("Andreas Werner <andreas.werner@men.de>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index 892d343193ad..f3338fe9d069 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -78,6 +78,44 @@ static int mfd_platform_add_cell(struct platform_device *pdev,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_ACPI)
+static void mfd_acpi_add_device(const struct mfd_cell *cell,
+				struct platform_device *pdev)
+{
+	struct acpi_device *parent_adev;
+	struct acpi_device *adev;
+
+	parent_adev = ACPI_COMPANION(pdev->dev.parent);
+	if (!parent_adev)
+		return;
+
+	/*
+	 * MFD child device gets its ACPI handle either from the ACPI
+	 * device directly under the parent that matches the acpi_pnpid or
+	 * it will use the parent handle if is no acpi_pnpid is given.
+	 */
+	adev = parent_adev;
+	if (cell->acpi_pnpid) {
+		struct acpi_device_id ids[2] = {};
+		struct acpi_device *child_adev;
+
+		strlcpy(ids[0].id, cell->acpi_pnpid, sizeof(ids[0].id));
+		list_for_each_entry(child_adev, &parent_adev->children, node)
+			if (acpi_match_device_ids(child_adev, ids)) {
+				adev = child_adev;
+				break;
+			}
+	}
+
+	ACPI_COMPANION_SET(&pdev->dev, adev);
+}
+#else
+static inline void mfd_acpi_add_device(const struct mfd_cell *cell,
+				       struct platform_device *pdev)
+{
+}
+#endif
+
 static int mfd_add_device(struct device *parent, int id,
 			  const struct mfd_cell *cell, atomic_t *usage_count,
 			  struct resource *mem_base,
@@ -101,6 +139,7 @@ static int mfd_add_device(struct device *parent, int id,
 	pdev->dev.type = &mfd_dev_type;
 	pdev->dev.dma_mask = parent->dma_mask;
 	pdev->dev.dma_parms = parent->dma_parms;
+	pdev->dev.coherent_dma_mask = parent->coherent_dma_mask;
 
 	ret = regulator_bulk_register_supply_alias(
 			&pdev->dev, cell->parent_supplies,
@@ -118,6 +157,8 @@ static int mfd_add_device(struct device *parent, int id,
 		}
 	}
 
+	mfd_acpi_add_device(cell, pdev);
+
 	if (cell->pdata_size) {
 		ret = platform_device_add_data(pdev,
 					cell->platform_data, cell->pdata_size);
diff --git a/drivers/mfd/pcf50633-core.c b/drivers/mfd/pcf50633-core.c
index c87f7a0a53f8..43664eb69c93 100644
--- a/drivers/mfd/pcf50633-core.c
+++ b/drivers/mfd/pcf50633-core.c
@@ -106,10 +106,7 @@ static ssize_t show_dump_regs(struct device *dev, struct device_attribute *attr,
 			} else
 				dump[n1] = pcf50633_reg_read(pcf, n + n1);
 
-		hex_dump_to_buffer(dump, sizeof(dump), 16, 1, buf1, 128, 0);
-		buf1 += strlen(buf1);
-		*buf1++ = '\n';
-		*buf1 = '\0';
+		buf1 += sprintf(buf1, "%*ph\n", (int)sizeof(dump), dump);
 	}
 
 	return buf1 - buf;
@@ -195,8 +192,9 @@ static int pcf50633_probe(struct i2c_client *client,
 				const struct i2c_device_id *ids)
 {
 	struct pcf50633 *pcf;
+	struct platform_device *pdev;
 	struct pcf50633_platform_data *pdata = dev_get_platdata(&client->dev);
-	int i, ret;
+	int i, j, ret;
 	int version, variant;
 
 	if (!client->irq) {
@@ -243,9 +241,6 @@ static int pcf50633_probe(struct i2c_client *client,
 
 
 	for (i = 0; i < PCF50633_NUM_REGULATORS; i++) {
-		struct platform_device *pdev;
-		int j;
-
 		pdev = platform_device_alloc("pcf50633-regulator", i);
 		if (!pdev)
 			return -ENOMEM;
@@ -253,25 +248,31 @@ static int pcf50633_probe(struct i2c_client *client,
 		pdev->dev.parent = pcf->dev;
 		ret = platform_device_add_data(pdev, &pdata->reg_init_data[i],
 					       sizeof(pdata->reg_init_data[i]));
-		if (ret) {
-			platform_device_put(pdev);
-			for (j = 0; j < i; j++)
-				platform_device_put(pcf->regulator_pdev[j]);
-			return ret;
-		}
-		pcf->regulator_pdev[i] = pdev;
+		if (ret)
+			goto err;
+
+		ret = platform_device_add(pdev);
+		if (ret)
+			goto err;
 
-		platform_device_add(pdev);
+		pcf->regulator_pdev[i] = pdev;
 	}
 
 	ret = sysfs_create_group(&client->dev.kobj, &pcf_attr_group);
 	if (ret)
-		dev_err(pcf->dev, "error creating sysfs entries\n");
+		dev_warn(pcf->dev, "error creating sysfs entries\n");
 
 	if (pdata->probe_done)
 		pdata->probe_done(pcf);
 
 	return 0;
+
+err:
+	platform_device_put(pdev);
+	for (j = 0; j < i; j++)
+		platform_device_put(pcf->regulator_pdev[j]);
+
+	return ret;
 }
 
 static int pcf50633_remove(struct i2c_client *client)
diff --git a/drivers/mfd/qcom-spmi-pmic.c b/drivers/mfd/qcom-spmi-pmic.c
new file mode 100644
index 000000000000..4b8beb2a1579
--- /dev/null
+++ b/drivers/mfd/qcom-spmi-pmic.c
@@ -0,0 +1,67 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/spmi.h>
+#include <linux/regmap.h>
+#include <linux/of_platform.h>
+
+static const struct regmap_config spmi_regmap_config = {
+	.reg_bits	= 16,
+	.val_bits	= 8,
+	.max_register	= 0xffff,
+	.fast_io	= true,
+};
+
+static int pmic_spmi_probe(struct spmi_device *sdev)
+{
+	struct device_node *root = sdev->dev.of_node;
+	struct regmap *regmap;
+
+	regmap = devm_regmap_init_spmi_ext(sdev, &spmi_regmap_config);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	return of_platform_populate(root, NULL, NULL, &sdev->dev);
+}
+
+static void pmic_spmi_remove(struct spmi_device *sdev)
+{
+	of_platform_depopulate(&sdev->dev);
+}
+
+static const struct of_device_id pmic_spmi_id_table[] = {
+	{ .compatible = "qcom,spmi-pmic" },
+	{ .compatible = "qcom,pm8941" },
+	{ .compatible = "qcom,pm8841" },
+	{ .compatible = "qcom,pma8084" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, pmic_spmi_id_table);
+
+static struct spmi_driver pmic_spmi_driver = {
+	.probe = pmic_spmi_probe,
+	.remove = pmic_spmi_remove,
+	.driver = {
+		.name = "pmic-spmi",
+		.of_match_table = pmic_spmi_id_table,
+	},
+};
+module_spmi_driver(pmic_spmi_driver);
+
+MODULE_DESCRIPTION("Qualcomm SPMI PMIC driver");
+MODULE_ALIAS("spmi:spmi-pmic");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Josh Cartwright <joshc@codeaurora.org>");
+MODULE_AUTHOR("Stanimir Varbanov <svarbanov@mm-sol.com>");
diff --git a/drivers/mfd/rk808.c b/drivers/mfd/rk808.c
new file mode 100644
index 000000000000..bd0215069875
--- /dev/null
+++ b/drivers/mfd/rk808.c
@@ -0,0 +1,275 @@
+/*
+ * MFD core driver for Rockchip RK808
+ *
+ * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * Author: Chris Zhong <zyw@rock-chips.com>
+ * Author: Zhang Qing <zhangqing@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/rk808.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+
+struct rk808_reg_data {
+	int addr;
+	int mask;
+	int value;
+};
+
+static bool rk808_is_volatile_reg(struct device *dev, unsigned int reg)
+{
+	/*
+	 * Notes:
+	 * - Technically the ROUND_30s bit makes RTC_CTRL_REG volatile, but
+	 *   we don't use that feature.  It's better to cache.
+	 * - It's unlikely we care that RK808_DEVCTRL_REG is volatile since
+	 *   bits are cleared in case when we shutoff anyway, but better safe.
+	 */
+
+	switch (reg) {
+	case RK808_SECONDS_REG ... RK808_WEEKS_REG:
+	case RK808_RTC_STATUS_REG:
+	case RK808_VB_MON_REG:
+	case RK808_THERMAL_REG:
+	case RK808_DCDC_UV_STS_REG:
+	case RK808_LDO_UV_STS_REG:
+	case RK808_DCDC_PG_REG:
+	case RK808_LDO_PG_REG:
+	case RK808_DEVCTRL_REG:
+	case RK808_INT_STS_REG1:
+	case RK808_INT_STS_REG2:
+		return true;
+	}
+
+	return false;
+}
+
+static const struct regmap_config rk808_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = RK808_IO_POL_REG,
+	.cache_type = REGCACHE_RBTREE,
+	.volatile_reg = rk808_is_volatile_reg,
+};
+
+static struct resource rtc_resources[] = {
+	{
+		.start  = RK808_IRQ_RTC_ALARM,
+		.end    = RK808_IRQ_RTC_ALARM,
+		.flags  = IORESOURCE_IRQ,
+	}
+};
+
+static const struct mfd_cell rk808s[] = {
+	{ .name = "rk808-clkout", },
+	{ .name = "rk808-regulator", },
+	{
+		.name = "rk808-rtc",
+		.num_resources = ARRAY_SIZE(rtc_resources),
+		.resources = &rtc_resources[0],
+	},
+};
+
+static const struct rk808_reg_data pre_init_reg[] = {
+	{ RK808_BUCK3_CONFIG_REG, BUCK_ILMIN_MASK,  BUCK_ILMIN_150MA },
+	{ RK808_BUCK4_CONFIG_REG, BUCK_ILMIN_MASK,  BUCK_ILMIN_200MA },
+	{ RK808_BOOST_CONFIG_REG, BOOST_ILMIN_MASK, BOOST_ILMIN_100MA },
+	{ RK808_BUCK1_CONFIG_REG, BUCK1_RATE_MASK,  BUCK_ILMIN_200MA },
+	{ RK808_BUCK2_CONFIG_REG, BUCK2_RATE_MASK,  BUCK_ILMIN_200MA },
+	{ RK808_VB_MON_REG,       MASK_ALL,         VB_LO_ACT |
+						    VB_LO_SEL_3500MV },
+};
+
+static const struct regmap_irq rk808_irqs[] = {
+	/* INT_STS */
+	[RK808_IRQ_VOUT_LO] = {
+		.mask = RK808_IRQ_VOUT_LO_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_VB_LO] = {
+		.mask = RK808_IRQ_VB_LO_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_PWRON] = {
+		.mask = RK808_IRQ_PWRON_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_PWRON_LP] = {
+		.mask = RK808_IRQ_PWRON_LP_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_HOTDIE] = {
+		.mask = RK808_IRQ_HOTDIE_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_RTC_ALARM] = {
+		.mask = RK808_IRQ_RTC_ALARM_MSK,
+		.reg_offset = 0,
+	},
+	[RK808_IRQ_RTC_PERIOD] = {
+		.mask = RK808_IRQ_RTC_PERIOD_MSK,
+		.reg_offset = 0,
+	},
+
+	/* INT_STS2 */
+	[RK808_IRQ_PLUG_IN_INT] = {
+		.mask = RK808_IRQ_PLUG_IN_INT_MSK,
+		.reg_offset = 1,
+	},
+	[RK808_IRQ_PLUG_OUT_INT] = {
+		.mask = RK808_IRQ_PLUG_OUT_INT_MSK,
+		.reg_offset = 1,
+	},
+};
+
+static struct regmap_irq_chip rk808_irq_chip = {
+	.name = "rk808",
+	.irqs = rk808_irqs,
+	.num_irqs = ARRAY_SIZE(rk808_irqs),
+	.num_regs = 2,
+	.irq_reg_stride = 2,
+	.status_base = RK808_INT_STS_REG1,
+	.mask_base = RK808_INT_STS_MSK_REG1,
+	.ack_base = RK808_INT_STS_REG1,
+	.init_ack_masked = true,
+};
+
+static struct i2c_client *rk808_i2c_client;
+static void rk808_device_shutdown(void)
+{
+	int ret;
+	struct rk808 *rk808 = i2c_get_clientdata(rk808_i2c_client);
+
+	if (!rk808) {
+		dev_warn(&rk808_i2c_client->dev,
+			 "have no rk808, so do nothing here\n");
+		return;
+	}
+
+	ret = regmap_update_bits(rk808->regmap,
+				 RK808_DEVCTRL_REG,
+				 DEV_OFF_RST, DEV_OFF_RST);
+	if (ret)
+		dev_err(&rk808_i2c_client->dev, "power off error!\n");
+}
+
+static int rk808_probe(struct i2c_client *client,
+		       const struct i2c_device_id *id)
+{
+	struct device_node *np = client->dev.of_node;
+	struct rk808 *rk808;
+	int pm_off = 0;
+	int ret;
+	int i;
+
+	if (!client->irq) {
+		dev_err(&client->dev, "No interrupt support, no core IRQ\n");
+		return -EINVAL;
+	}
+
+	rk808 = devm_kzalloc(&client->dev, sizeof(*rk808), GFP_KERNEL);
+	if (!rk808)
+		return -ENOMEM;
+
+	rk808->regmap = devm_regmap_init_i2c(client, &rk808_regmap_config);
+	if (IS_ERR(rk808->regmap)) {
+		dev_err(&client->dev, "regmap initialization failed\n");
+		return PTR_ERR(rk808->regmap);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(pre_init_reg); i++) {
+		ret = regmap_update_bits(rk808->regmap, pre_init_reg[i].addr,
+					 pre_init_reg[i].mask,
+					 pre_init_reg[i].value);
+		if (ret) {
+			dev_err(&client->dev,
+				"0x%x write err\n", pre_init_reg[i].addr);
+			return ret;
+		}
+	}
+
+	ret = regmap_add_irq_chip(rk808->regmap, client->irq,
+				  IRQF_ONESHOT, -1,
+				  &rk808_irq_chip, &rk808->irq_data);
+	if (ret) {
+		dev_err(&client->dev, "Failed to add irq_chip %d\n", ret);
+		return ret;
+	}
+
+	rk808->i2c = client;
+	i2c_set_clientdata(client, rk808);
+
+	ret = mfd_add_devices(&client->dev, -1,
+			      rk808s, ARRAY_SIZE(rk808s),
+			      NULL, 0, regmap_irq_get_domain(rk808->irq_data));
+	if (ret) {
+		dev_err(&client->dev, "failed to add MFD devices %d\n", ret);
+		goto err_irq;
+	}
+
+	pm_off = of_property_read_bool(np,
+				"rockchip,system-power-controller");
+	if (pm_off && !pm_power_off) {
+		rk808_i2c_client = client;
+		pm_power_off = rk808_device_shutdown;
+	}
+
+	return 0;
+
+err_irq:
+	regmap_del_irq_chip(client->irq, rk808->irq_data);
+	return ret;
+}
+
+static int rk808_remove(struct i2c_client *client)
+{
+	struct rk808 *rk808 = i2c_get_clientdata(client);
+
+	regmap_del_irq_chip(client->irq, rk808->irq_data);
+	mfd_remove_devices(&client->dev);
+	pm_power_off = NULL;
+
+	return 0;
+}
+
+static struct of_device_id rk808_of_match[] = {
+	{ .compatible = "rockchip,rk808" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, rk808_of_match);
+
+static const struct i2c_device_id rk808_ids[] = {
+	{ "rk808" },
+	{ },
+};
+MODULE_DEVICE_TABLE(i2c, rk808_ids);
+
+static struct i2c_driver rk808_i2c_driver = {
+	.driver = {
+		.name = "rk808",
+		.of_match_table = rk808_of_match,
+	},
+	.probe    = rk808_probe,
+	.remove   = rk808_remove,
+	.id_table = rk808_ids,
+};
+
+module_i2c_driver(rk808_i2c_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Chris Zhong <zyw@rock-chips.com>");
+MODULE_AUTHOR("Zhang Qing <zhangqing@rock-chips.com>");
+MODULE_DESCRIPTION("RK808 PMIC driver");
diff --git a/drivers/mfd/rn5t618.c b/drivers/mfd/rn5t618.c
new file mode 100644
index 000000000000..666857192dbe
--- /dev/null
+++ b/drivers/mfd/rn5t618.c
@@ -0,0 +1,134 @@
+/*
+ * MFD core driver for Ricoh RN5T618 PMIC
+ *
+ * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/i2c.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/rn5t618.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+
+static const struct mfd_cell rn5t618_cells[] = {
+	{ .name = "rn5t618-regulator" },
+	{ .name = "rn5t618-wdt" },
+};
+
+static bool rn5t618_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case RN5T618_WATCHDOGCNT:
+	case RN5T618_DCIRQ:
+	case RN5T618_ILIMDATAH ... RN5T618_AIN0DATAL:
+	case RN5T618_IR_ADC1 ... RN5T618_IR_ADC3:
+	case RN5T618_IR_GPR:
+	case RN5T618_IR_GPF:
+	case RN5T618_MON_IOIN:
+	case RN5T618_INTMON:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const struct regmap_config rn5t618_regmap_config = {
+	.reg_bits	= 8,
+	.val_bits	= 8,
+	.volatile_reg	= rn5t618_volatile_reg,
+	.max_register	= RN5T618_MAX_REG,
+	.cache_type	= REGCACHE_RBTREE,
+};
+
+static struct rn5t618 *rn5t618_pm_power_off;
+
+static void rn5t618_power_off(void)
+{
+	/* disable automatic repower-on */
+	regmap_update_bits(rn5t618_pm_power_off->regmap, RN5T618_REPCNT,
+			   RN5T618_REPCNT_REPWRON, 0);
+	/* start power-off sequence */
+	regmap_update_bits(rn5t618_pm_power_off->regmap, RN5T618_SLPCNT,
+			   RN5T618_SLPCNT_SWPWROFF, RN5T618_SLPCNT_SWPWROFF);
+}
+
+static int rn5t618_i2c_probe(struct i2c_client *i2c,
+			     const struct i2c_device_id *id)
+{
+	struct rn5t618 *priv;
+	int ret;
+
+	priv = devm_kzalloc(&i2c->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c, priv);
+
+	priv->regmap = devm_regmap_init_i2c(i2c, &rn5t618_regmap_config);
+	if (IS_ERR(priv->regmap)) {
+		ret = PTR_ERR(priv->regmap);
+		dev_err(&i2c->dev, "regmap init failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = mfd_add_devices(&i2c->dev, -1, rn5t618_cells,
+			      ARRAY_SIZE(rn5t618_cells), NULL, 0, NULL);
+	if (ret) {
+		dev_err(&i2c->dev, "failed to add sub-devices: %d\n", ret);
+		return ret;
+	}
+
+	if (!pm_power_off) {
+		rn5t618_pm_power_off = priv;
+		pm_power_off = rn5t618_power_off;
+	}
+
+	return 0;
+}
+
+static int rn5t618_i2c_remove(struct i2c_client *i2c)
+{
+	struct rn5t618 *priv = i2c_get_clientdata(i2c);
+
+	if (priv == rn5t618_pm_power_off) {
+		rn5t618_pm_power_off = NULL;
+		pm_power_off = NULL;
+	}
+
+	mfd_remove_devices(&i2c->dev);
+	return 0;
+}
+
+static const struct of_device_id rn5t618_of_match[] = {
+	{ .compatible = "ricoh,rn5t618" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, rn5t618_of_match);
+
+static const struct i2c_device_id rn5t618_i2c_id[] = {
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, rn5t618_i2c_id);
+
+static struct i2c_driver rn5t618_i2c_driver = {
+	.driver = {
+		.name = "rn5t618",
+		.of_match_table = of_match_ptr(rn5t618_of_match),
+	},
+	.probe = rn5t618_i2c_probe,
+	.remove = rn5t618_i2c_remove,
+	.id_table = rn5t618_i2c_id,
+};
+
+module_i2c_driver(rn5t618_i2c_driver);
+
+MODULE_AUTHOR("Beniamino Galvani <b.galvani@gmail.com>");
+MODULE_DESCRIPTION("Ricoh RN5T618 MFD driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
index d01b8c249231..f2643c221d34 100644
--- a/drivers/mfd/rtsx_pcr.c
+++ b/drivers/mfd/rtsx_pcr.c
@@ -1197,7 +1197,7 @@ static int rtsx_pci_probe(struct pci_dev *pcidev,
 	pcr->msi_en = msi_en;
 	if (pcr->msi_en) {
 		ret = pci_enable_msi(pcidev);
-		if (ret < 0)
+		if (ret)
 			pcr->msi_en = false;
 	}
 
diff --git a/drivers/mfd/rtsx_usb.c b/drivers/mfd/rtsx_usb.c
index 71f387ce8cbd..9cf98d142d9a 100644
--- a/drivers/mfd/rtsx_usb.c
+++ b/drivers/mfd/rtsx_usb.c
@@ -684,7 +684,7 @@ static int rtsx_usb_suspend(struct usb_interface *intf, pm_message_t message)
 	struct rtsx_ucr *ucr =
 		(struct rtsx_ucr *)usb_get_intfdata(intf);
 
-	dev_dbg(&intf->dev, "%s called with pm message 0x%04u\n",
+	dev_dbg(&intf->dev, "%s called with pm message 0x%04x\n",
 			__func__, message.event);
 
 	/*
diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c
index 81e6d0932bf0..6ce6e6200359 100644
--- a/drivers/mfd/sm501.c
+++ b/drivers/mfd/sm501.c
@@ -514,9 +514,9 @@ unsigned long sm501_set_clock(struct device *dev,
 	unsigned long mode = smc501_readl(sm->regs + SM501_POWER_MODE_CONTROL);
 	unsigned long gate = smc501_readl(sm->regs + SM501_CURRENT_GATE);
 	unsigned long clock = smc501_readl(sm->regs + SM501_CURRENT_CLOCK);
-	unsigned char reg;
 	unsigned int pll_reg = 0;
 	unsigned long sm501_freq; /* the actual frequency achieved */
+	u64 reg;
 
 	struct sm501_clock to;
 
@@ -1047,7 +1047,6 @@ static int sm501_register_gpio(struct sm501_devdata *sm)
 	struct sm501_gpio *gpio = &sm->gpio;
 	resource_size_t iobase = sm->io_res->start + SM501_GPIO;
 	int ret;
-	int tmp;
 
 	dev_dbg(sm->dev, "registering gpio block %08llx\n",
 		(unsigned long long)iobase);
@@ -1086,11 +1085,7 @@ static int sm501_register_gpio(struct sm501_devdata *sm)
 	return 0;
 
  err_low_chip:
-	tmp = gpiochip_remove(&gpio->low.gpio);
-	if (tmp) {
-		dev_err(sm->dev, "cannot remove low chip, cannot tidy up\n");
-		return ret;
-	}
+	gpiochip_remove(&gpio->low.gpio);
 
  err_mapped:
 	iounmap(gpio->regs);
@@ -1105,18 +1100,12 @@ static int sm501_register_gpio(struct sm501_devdata *sm)
 static void sm501_gpio_remove(struct sm501_devdata *sm)
 {
 	struct sm501_gpio *gpio = &sm->gpio;
-	int ret;
 
 	if (!sm->gpio.registered)
 		return;
 
-	ret = gpiochip_remove(&gpio->low.gpio);
-	if (ret)
-		dev_err(sm->dev, "cannot remove low chip, cannot tidy up\n");
-
-	ret = gpiochip_remove(&gpio->high.gpio);
-	if (ret)
-		dev_err(sm->dev, "cannot remove high chip, cannot tidy up\n");
+	gpiochip_remove(&gpio->low.gpio);
+	gpiochip_remove(&gpio->high.gpio);
 
 	iounmap(gpio->regs);
 	release_resource(gpio->regs_res);
diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c
index 02a17c388e87..e2f9df1c0c36 100644
--- a/drivers/mfd/stmpe.c
+++ b/drivers/mfd/stmpe.c
@@ -249,7 +249,7 @@ int stmpe_set_altfunc(struct stmpe *stmpe, u32 pins, enum stmpe_block block)
 	int af_bits = variant->af_bits;
 	int numregs = DIV_ROUND_UP(stmpe->num_gpios * af_bits, 8);
 	int mask = (1 << af_bits) - 1;
-	u8 regs[numregs];
+	u8 regs[8];
 	int af, afperreg, ret;
 
 	if (!variant->get_altfunc)
@@ -854,7 +854,7 @@ static irqreturn_t stmpe_irq(int irq, void *data)
 	struct stmpe_variant_info *variant = stmpe->variant;
 	int num = DIV_ROUND_UP(variant->num_irqs, 8);
 	u8 israddr;
-	u8 isr[num];
+	u8 isr[3];
 	int ret;
 	int i;
 
@@ -1122,7 +1122,12 @@ static void stmpe_of_probe(struct stmpe_platform_data *pdata,
 	if (pdata->id < 0)
 		pdata->id = -1;
 
-	pdata->irq_trigger = IRQF_TRIGGER_NONE;
+	pdata->irq_gpio = of_get_named_gpio_flags(np, "irq-gpio", 0,
+				&pdata->irq_trigger);
+	if (gpio_is_valid(pdata->irq_gpio))
+		pdata->irq_over_gpio = 1;
+	else
+		pdata->irq_trigger = IRQF_TRIGGER_NONE;
 
 	of_property_read_u32(np, "st,autosleep-timeout",
 			&pdata->autosleep_timeout);
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index 11c19e538551..4fac16bcd732 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -607,7 +607,7 @@ static int tc6393xb_probe(struct platform_device *dev)
 	struct tc6393xb_platform_data *tcpd = dev_get_platdata(&dev->dev);
 	struct tc6393xb *tc6393xb;
 	struct resource *iomem, *rscr;
-	int ret, temp;
+	int ret;
 
 	iomem = platform_get_resource(dev, IORESOURCE_MEM, 0);
 	if (!iomem)
@@ -714,7 +714,7 @@ err_setup:
 
 err_gpio_add:
 	if (tc6393xb->gpio.base != -1)
-		temp = gpiochip_remove(&tc6393xb->gpio);
+		gpiochip_remove(&tc6393xb->gpio);
 	tcpd->disable(dev);
 err_enable:
 	clk_disable(tc6393xb->clk);
@@ -744,13 +744,8 @@ static int tc6393xb_remove(struct platform_device *dev)
 
 	tc6393xb_detach_irq(dev);
 
-	if (tc6393xb->gpio.base != -1) {
-		ret = gpiochip_remove(&tc6393xb->gpio);
-		if (ret) {
-			dev_err(&dev->dev, "Can't remove gpio chip: %d\n", ret);
-			return ret;
-		}
-	}
+	if (tc6393xb->gpio.base != -1)
+		gpiochip_remove(&tc6393xb->gpio);
 
 	ret = tcpd->disable(dev);
 	clk_disable(tc6393xb->clk);
diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c
index dd4bf5816221..d877e777cce6 100644
--- a/drivers/mfd/ti_am335x_tscadc.c
+++ b/drivers/mfd/ti_am335x_tscadc.c
@@ -53,11 +53,11 @@ void am335x_tsc_se_set_cache(struct ti_tscadc_dev *tsadc, u32 val)
 	unsigned long flags;
 
 	spin_lock_irqsave(&tsadc->reg_lock, flags);
-	tsadc->reg_se_cache = val;
+	tsadc->reg_se_cache |= val;
 	if (tsadc->adc_waiting)
 		wake_up(&tsadc->reg_se_wait);
 	else if (!tsadc->adc_in_use)
-		tscadc_writel(tsadc, REG_SE, val);
+		tscadc_writel(tsadc, REG_SE, tsadc->reg_se_cache);
 
 	spin_unlock_irqrestore(&tsadc->reg_lock, flags);
 }
@@ -96,6 +96,7 @@ static void am335x_tscadc_need_adc(struct ti_tscadc_dev *tsadc)
 void am335x_tsc_se_set_once(struct ti_tscadc_dev *tsadc, u32 val)
 {
 	spin_lock_irq(&tsadc->reg_lock);
+	tsadc->reg_se_cache |= val;
 	am335x_tscadc_need_adc(tsadc);
 
 	tscadc_writel(tsadc, REG_SE, val);
@@ -241,18 +242,20 @@ static	int ti_tscadc_probe(struct platform_device *pdev)
 	tscadc_writel(tscadc, REG_CLKDIV, tscadc->clk_div);
 
 	/* Set the control register bits */
-	ctrl = CNTRLREG_STEPCONFIGWRT |
-			CNTRLREG_STEPID;
-	if (tsc_wires > 0)
-		ctrl |= CNTRLREG_4WIRE | CNTRLREG_TSCENB;
+	ctrl = CNTRLREG_STEPCONFIGWRT |	CNTRLREG_STEPID;
 	tscadc_writel(tscadc, REG_CTRL, ctrl);
 
 	/* Set register bits for Idle Config Mode */
-	if (tsc_wires > 0)
+	if (tsc_wires > 0) {
+		tscadc->tsc_wires = tsc_wires;
+		if (tsc_wires == 5)
+			ctrl |= CNTRLREG_5WIRE | CNTRLREG_TSCENB;
+		else
+			ctrl |= CNTRLREG_4WIRE | CNTRLREG_TSCENB;
 		tscadc_idle_config(tscadc);
+	}
 
 	/* Enable the TSC module enable bit */
-	ctrl = tscadc_readl(tscadc, REG_CTRL);
 	ctrl |= CNTRLREG_TSCSSENB;
 	tscadc_writel(tscadc, REG_CTRL, ctrl);
 
@@ -324,21 +327,23 @@ static int tscadc_suspend(struct device *dev)
 static int tscadc_resume(struct device *dev)
 {
 	struct ti_tscadc_dev	*tscadc_dev = dev_get_drvdata(dev);
-	unsigned int restore, ctrl;
+	u32 ctrl;
 
 	pm_runtime_get_sync(dev);
 
 	/* context restore */
 	ctrl = CNTRLREG_STEPCONFIGWRT |	CNTRLREG_STEPID;
-	if (tscadc_dev->tsc_cell != -1)
-		ctrl |= CNTRLREG_TSCENB | CNTRLREG_4WIRE;
 	tscadc_writel(tscadc_dev, REG_CTRL, ctrl);
 
-	if (tscadc_dev->tsc_cell != -1)
+	if (tscadc_dev->tsc_cell != -1) {
+		if (tscadc_dev->tsc_wires == 5)
+			ctrl |= CNTRLREG_5WIRE | CNTRLREG_TSCENB;
+		else
+			ctrl |= CNTRLREG_4WIRE | CNTRLREG_TSCENB;
 		tscadc_idle_config(tscadc_dev);
-	restore = tscadc_readl(tscadc_dev, REG_CTRL);
-	tscadc_writel(tscadc_dev, REG_CTRL,
-			(restore | CNTRLREG_TSCSSENB));
+	}
+	ctrl |= CNTRLREG_TSCSSENB;
+	tscadc_writel(tscadc_dev, REG_CTRL, ctrl);
 
 	tscadc_writel(tscadc_dev, REG_CLKDIV, tscadc_dev->clk_div);
 
diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c
index 3cc4c7084b92..a8ee52c95f2f 100644
--- a/drivers/mfd/tps65217.c
+++ b/drivers/mfd/tps65217.c
@@ -146,6 +146,8 @@ EXPORT_SYMBOL_GPL(tps65217_clear_bits);
 static struct regmap_config tps65217_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
+
+	.max_register = TPS65217_REG_MAX,
 };
 
 static const struct of_device_id tps65217_of_match[] = {
diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
index f243e75d28f3..7612d89850dd 100644
--- a/drivers/mfd/tps65910.c
+++ b/drivers/mfd/tps65910.c
@@ -486,6 +486,11 @@ static int tps65910_i2c_probe(struct i2c_client *i2c,
 	tps65910->i2c_client = i2c;
 	tps65910->id = chip_id;
 
+	/* Work around silicon erratum SWCZ010: the tps65910 may miss the
+	 * first I2C transfer. So issue a dummy transfer before the first
+	 * real transfer.
+	 */
+	i2c_master_send(i2c, "", 1);
 	tps65910->regmap = devm_regmap_init_i2c(i2c, &tps65910_regmap_config);
 	if (IS_ERR(tps65910->regmap)) {
 		ret = PTR_ERR(tps65910->regmap);
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
index b1dabba763cf..1b772ef761cb 100644
--- a/drivers/mfd/twl4030-irq.c
+++ b/drivers/mfd/twl4030-irq.c
@@ -396,13 +396,17 @@ static int twl4030_init_sih_modules(unsigned line)
 			status = twl_i2c_read(sih->module, rxbuf,
 				sih->mask[line].isr_offset, sih->bytes_ixr);
 			if (status < 0)
-				pr_err("twl4030: err %d initializing %s %s\n",
+				pr_warn("twl4030: err %d initializing %s %s\n",
 					status, sih->name, "ISR");
 
-			if (!sih->set_cor)
+			if (!sih->set_cor) {
 				status = twl_i2c_write(sih->module, buf,
 					sih->mask[line].isr_offset,
 					sih->bytes_ixr);
+				if (status < 0)
+					pr_warn("twl4030: write failed: %d\n",
+						status);
+			}
 			/*
 			 * else COR=1 means read sufficed.
 			 * (for most SIH modules...)
diff --git a/drivers/mfd/twl4030-power.c b/drivers/mfd/twl4030-power.c
index 4d3ff3771491..cf92a6d1c532 100644
--- a/drivers/mfd/twl4030-power.c
+++ b/drivers/mfd/twl4030-power.c
@@ -627,6 +627,9 @@ static bool twl4030_power_use_poweroff(const struct twl4030_power_data *pdata,
 	if (pdata && pdata->use_poweroff)
 		return true;
 
+	if (of_property_read_bool(node, "ti,system-power-controller"))
+		return true;
+
 	if (of_property_read_bool(node, "ti,use_poweroff"))
 		return true;
 
diff --git a/drivers/mfd/twl6040.c b/drivers/mfd/twl6040.c
index f9c06c542a41..9687645162ae 100644
--- a/drivers/mfd/twl6040.c
+++ b/drivers/mfd/twl6040.c
@@ -679,6 +679,7 @@ static int twl6040_probe(struct i2c_client *client,
 	if (twl6040->rev < 0) {
 		dev_err(&client->dev, "Failed to read revision register: %d\n",
 			twl6040->rev);
+		ret = twl6040->rev;
 		goto gpio_err;
 	}
 
diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c
index 153d595afaac..58ea9fdd3a15 100644
--- a/drivers/mfd/ucb1x00-core.c
+++ b/drivers/mfd/ucb1x00-core.c
@@ -621,7 +621,6 @@ static void ucb1x00_remove(struct mcp *mcp)
 	struct ucb1x00_plat_data *pdata = mcp->attached_device.platform_data;
 	struct ucb1x00 *ucb = mcp_get_drvdata(mcp);
 	struct list_head *l, *n;
-	int ret;
 
 	mutex_lock(&ucb1x00_mutex);
 	list_del(&ucb->node);
@@ -631,11 +630,8 @@ static void ucb1x00_remove(struct mcp *mcp)
 	}
 	mutex_unlock(&ucb1x00_mutex);
 
-	if (ucb->gpio.base != -1) {
-		ret = gpiochip_remove(&ucb->gpio);
-		if (ret)
-			dev_err(&ucb->dev, "Can't remove gpio chip: %d\n", ret);
-	}
+	if (ucb->gpio.base != -1)
+		gpiochip_remove(&ucb->gpio);
 
 	irq_set_chained_handler(ucb->irq, NULL);
 	irq_free_descs(ucb->irq_base, 16);
diff --git a/drivers/mfd/wm5102-tables.c b/drivers/mfd/wm5102-tables.c
index fb4d4bb0f47d..d6f35bbf795b 100644
--- a/drivers/mfd/wm5102-tables.c
+++ b/drivers/mfd/wm5102-tables.c
@@ -87,6 +87,7 @@ int wm5102_patch(struct arizona *arizona)
 	case 0:
 		wm5102_patch = wm5102_reva_patch;
 		patch_size = ARRAY_SIZE(wm5102_reva_patch);
+		break;
 	default:
 		wm5102_patch = wm5102_revb_patch;
 		patch_size = ARRAY_SIZE(wm5102_revb_patch);
@@ -245,9 +246,6 @@ const struct regmap_irq_chip wm5102_irq = {
 static const struct reg_default wm5102_reg_default[] = {
 	{ 0x00000008, 0x0019 },   /* R8     - Ctrl IF SPI CFG 1 */ 
 	{ 0x00000009, 0x0001 },   /* R9     - Ctrl IF I2C1 CFG 1 */ 
-	{ 0x00000016, 0x0000 },   /* R22    - Write Sequencer Ctrl 0 */ 
-	{ 0x00000017, 0x0000 },   /* R23    - Write Sequencer Ctrl 1 */ 
-	{ 0x00000018, 0x0000 },   /* R24    - Write Sequencer Ctrl 2 */ 
 	{ 0x00000020, 0x0000 },   /* R32    - Tone Generator 1 */ 
 	{ 0x00000021, 0x1000 },   /* R33    - Tone Generator 2 */ 
 	{ 0x00000022, 0x0000 },   /* R34    - Tone Generator 3 */ 
@@ -1016,6 +1014,7 @@ static bool wm5102_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_WRITE_SEQUENCER_CTRL_0:
 	case ARIZONA_WRITE_SEQUENCER_CTRL_1:
 	case ARIZONA_WRITE_SEQUENCER_CTRL_2:
+	case ARIZONA_WRITE_SEQUENCER_CTRL_3:
 	case ARIZONA_WRITE_SEQUENCER_PROM:
 	case ARIZONA_TONE_GENERATOR_1:
 	case ARIZONA_TONE_GENERATOR_2:
@@ -1060,6 +1059,8 @@ static bool wm5102_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_ASYNC_CLOCK_1:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS:
 	case ARIZONA_OUTPUT_SYSTEM_CLOCK:
 	case ARIZONA_OUTPUT_ASYNC_CLOCK:
 	case ARIZONA_RATE_ESTIMATOR_1:
@@ -1880,6 +1881,10 @@ static bool wm5102_volatile_register(struct device *dev, unsigned int reg)
 	switch (reg) {
 	case ARIZONA_SOFTWARE_RESET:
 	case ARIZONA_DEVICE_REVISION:
+	case ARIZONA_WRITE_SEQUENCER_CTRL_0:
+	case ARIZONA_WRITE_SEQUENCER_CTRL_1:
+	case ARIZONA_WRITE_SEQUENCER_CTRL_2:
+	case ARIZONA_WRITE_SEQUENCER_CTRL_3:
 	case ARIZONA_OUTPUT_STATUS_1:
 	case ARIZONA_RAW_OUTPUT_STATUS_1:
 	case ARIZONA_SLIMBUS_RX_PORT_STATUS:
@@ -1889,8 +1894,13 @@ static bool wm5102_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_SAMPLE_RATE_3_STATUS:
 	case ARIZONA_HAPTICS_STATUS:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS:
 	case ARIZONA_FLL1_NCO_TEST_0:
 	case ARIZONA_FLL2_NCO_TEST_0:
+	case ARIZONA_DAC_COMP_1:
+	case ARIZONA_DAC_COMP_2:
+	case ARIZONA_DAC_COMP_3:
+	case ARIZONA_DAC_COMP_4:
 	case ARIZONA_FX_CTRL2:
 	case ARIZONA_INTERRUPT_STATUS_1:
 	case ARIZONA_INTERRUPT_STATUS_2:
diff --git a/drivers/mfd/wm5110-tables.c b/drivers/mfd/wm5110-tables.c
index 9b98ee559188..4642b5b816a0 100644
--- a/drivers/mfd/wm5110-tables.c
+++ b/drivers/mfd/wm5110-tables.c
@@ -666,9 +666,6 @@ static const struct reg_default wm5110_reg_default[] = {
 	{ 0x0000000A, 0x0001 },    /* R10    - Ctrl IF I2C2 CFG 1 */
 	{ 0x0000000B, 0x0036 },    /* R11    - Ctrl IF I2C1 CFG 2 */
 	{ 0x0000000C, 0x0036 },    /* R12    - Ctrl IF I2C2 CFG 2 */
-	{ 0x00000016, 0x0000 },    /* R22    - Write Sequencer Ctrl 0 */
-	{ 0x00000017, 0x0000 },    /* R23    - Write Sequencer Ctrl 1 */
-	{ 0x00000018, 0x0000 },    /* R24    - Write Sequencer Ctrl 2 */
 	{ 0x00000020, 0x0000 },    /* R32    - Tone Generator 1 */
 	{ 0x00000021, 0x1000 },    /* R33    - Tone Generator 2 */
 	{ 0x00000022, 0x0000 },    /* R34    - Tone Generator 3 */
@@ -705,6 +702,7 @@ static const struct reg_default wm5110_reg_default[] = {
 	{ 0x00000104, 0x0011 },    /* R260   - Sample rate 3 */
 	{ 0x00000112, 0x0305 },    /* R274   - Async clock 1 */
 	{ 0x00000113, 0x0011 },    /* R275   - Async sample rate 1 */
+	{ 0x00000114, 0x0011 },    /* R276   - Async sample rate 2 */
 	{ 0x00000149, 0x0000 },    /* R329   - Output system clock */
 	{ 0x0000014A, 0x0000 },    /* R330   - Output async clock */
 	{ 0x00000152, 0x0000 },    /* R338   - Rate Estimator 1 */
@@ -1741,6 +1739,8 @@ static bool wm5110_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_ASYNC_CLOCK_1:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS:
 	case ARIZONA_OUTPUT_SYSTEM_CLOCK:
 	case ARIZONA_OUTPUT_ASYNC_CLOCK:
 	case ARIZONA_RATE_ESTIMATOR_1:
@@ -2815,11 +2815,15 @@ static bool wm5110_volatile_register(struct device *dev, unsigned int reg)
 	switch (reg) {
 	case ARIZONA_SOFTWARE_RESET:
 	case ARIZONA_DEVICE_REVISION:
+	case ARIZONA_WRITE_SEQUENCER_CTRL_0:
+	case ARIZONA_WRITE_SEQUENCER_CTRL_1:
+	case ARIZONA_WRITE_SEQUENCER_CTRL_2:
 	case ARIZONA_HAPTICS_STATUS:
 	case ARIZONA_SAMPLE_RATE_1_STATUS:
 	case ARIZONA_SAMPLE_RATE_2_STATUS:
 	case ARIZONA_SAMPLE_RATE_3_STATUS:
 	case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS:
+	case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS:
 	case ARIZONA_MIC_DETECT_3:
 	case ARIZONA_HEADPHONE_DETECT_2:
 	case ARIZONA_INPUT_ENABLES_STATUS:
diff --git a/drivers/mfd/wm8994-irq.c b/drivers/mfd/wm8994-irq.c
index e74dedda5b55..a14407edbd89 100644
--- a/drivers/mfd/wm8994-irq.c
+++ b/drivers/mfd/wm8994-irq.c
@@ -262,8 +262,10 @@ int wm8994_irq_init(struct wm8994 *wm8994)
 
 	return 0;
 }
+EXPORT_SYMBOL(wm8994_irq_init);
 
 void wm8994_irq_exit(struct wm8994 *wm8994)
 {
 	regmap_del_irq_chip(wm8994->irq, wm8994->irq_data);
 }
+EXPORT_SYMBOL(wm8994_irq_exit);
diff --git a/drivers/mfd/wm8994-regmap.c b/drivers/mfd/wm8994-regmap.c
index 770a25696468..300e9b6a2e96 100644
--- a/drivers/mfd/wm8994-regmap.c
+++ b/drivers/mfd/wm8994-regmap.c
@@ -1252,6 +1252,7 @@ struct regmap_config wm1811_regmap_config = {
 	.volatile_reg = wm1811_volatile_register,
 	.readable_reg = wm1811_readable_register,
 };
+EXPORT_SYMBOL(wm1811_regmap_config);
 
 struct regmap_config wm8994_regmap_config = {
 	.reg_bits = 16,
@@ -1266,6 +1267,7 @@ struct regmap_config wm8994_regmap_config = {
 	.volatile_reg = wm8994_volatile_register,
 	.readable_reg = wm8994_readable_register,
 };
+EXPORT_SYMBOL(wm8994_regmap_config);
 
 struct regmap_config wm8958_regmap_config = {
 	.reg_bits = 16,
@@ -1280,8 +1282,10 @@ struct regmap_config wm8958_regmap_config = {
 	.volatile_reg = wm8958_volatile_register,
 	.readable_reg = wm8958_readable_register,
 };
+EXPORT_SYMBOL(wm8958_regmap_config);
 
 struct regmap_config wm8994_base_regmap_config = {
 	.reg_bits = 16,
 	.val_bits = 16,
 };
+EXPORT_SYMBOL(wm8994_base_regmap_config);
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index b841180c7c74..bbeb4516facf 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -527,4 +527,5 @@ source "drivers/misc/vmw_vmci/Kconfig"
 source "drivers/misc/mic/Kconfig"
 source "drivers/misc/genwqe/Kconfig"
 source "drivers/misc/echo/Kconfig"
+source "drivers/misc/cxl/Kconfig"
 endmenu
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 5497d026e651..7d5c4cd118c4 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -55,3 +55,4 @@ obj-y				+= mic/
 obj-$(CONFIG_GENWQE)		+= genwqe/
 obj-$(CONFIG_ECHO)		+= echo/
 obj-$(CONFIG_VEXPRESS_SYSCFG)	+= vexpress-syscfg.o
+obj-$(CONFIG_CXL_BASE)		+= cxl/
diff --git a/drivers/misc/altera-stapl/altera.c b/drivers/misc/altera-stapl/altera.c
index 24272e022bec..bca2630d006f 100644
--- a/drivers/misc/altera-stapl/altera.c
+++ b/drivers/misc/altera-stapl/altera.c
@@ -454,7 +454,7 @@ exit_done:
 
 				name = &p[str_table + name_id];
 
-				if (strnicmp(aconf->action, name, strlen(name)) == 0) {
+				if (strncasecmp(aconf->action, name, strlen(name)) == 0) {
 					action_found = 1;
 					current_proc =
 						get_unaligned_be32(&p[action_table +
@@ -2176,7 +2176,7 @@ static int altera_get_note(u8 *p, s32 program_size,
 			key_ptr = &p[note_strings +
 					get_unaligned_be32(
 					&p[note_table + (8 * i)])];
-			if ((strnicmp(key, key_ptr, strlen(key_ptr)) == 0) &&
+			if ((strncasecmp(key, key_ptr, strlen(key_ptr)) == 0) &&
 						(key != NULL)) {
 				status = 0;
 
diff --git a/drivers/misc/carma/carma-fpga-program.c b/drivers/misc/carma/carma-fpga-program.c
index 7be89832db19..339b252fcedd 100644
--- a/drivers/misc/carma/carma-fpga-program.c
+++ b/drivers/misc/carma/carma-fpga-program.c
@@ -16,6 +16,7 @@
 #include <linux/completion.h>
 #include <linux/miscdevice.h>
 #include <linux/dmaengine.h>
+#include <linux/fsldma.h>
 #include <linux/interrupt.h>
 #include <linux/highmem.h>
 #include <linux/kernel.h>
@@ -518,23 +519,22 @@ static noinline int fpga_program_dma(struct fpga_dev *priv)
 	config.direction = DMA_MEM_TO_DEV;
 	config.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	config.dst_maxburst = fpga_fifo_size(priv->regs) / 2 / 4;
-	ret = chan->device->device_control(chan, DMA_SLAVE_CONFIG,
-					   (unsigned long)&config);
+	ret = dmaengine_slave_config(chan, &config);
 	if (ret) {
 		dev_err(priv->dev, "DMA slave configuration failed\n");
 		goto out_dma_unmap;
 	}
 
-	ret = chan->device->device_control(chan, FSLDMA_EXTERNAL_START, 1);
+	ret = fsl_dma_external_start(chan, 1)
 	if (ret) {
 		dev_err(priv->dev, "DMA external control setup failed\n");
 		goto out_dma_unmap;
 	}
 
 	/* setup and submit the DMA transaction */
-	tx = chan->device->device_prep_dma_sg(chan,
-					      table.sgl, num_pages,
-					      vb->sglist, vb->sglen, 0);
+
+	tx = dmaengine_prep_dma_sg(chan, table.sgl, num_pages,
+			vb->sglist, vb->sglen, 0);
 	if (!tx) {
 		dev_err(priv->dev, "Unable to prep DMA transaction\n");
 		ret = -ENOMEM;
@@ -749,13 +749,8 @@ static ssize_t fpga_read(struct file *filp, char __user *buf, size_t count,
 			 loff_t *f_pos)
 {
 	struct fpga_dev *priv = filp->private_data;
-
-	count = min_t(size_t, priv->bytes - *f_pos, count);
-	if (copy_to_user(buf, priv->vb.vaddr + *f_pos, count))
-		return -EFAULT;
-
-	*f_pos += count;
-	return count;
+	return simple_read_from_buffer(buf, count, ppos,
+				       priv->vb.vaddr, priv->bytes);
 }
 
 static loff_t fpga_llseek(struct file *filp, loff_t offset, int origin)
@@ -767,26 +762,7 @@ static loff_t fpga_llseek(struct file *filp, loff_t offset, int origin)
 	if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
 		return -EINVAL;
 
-	switch (origin) {
-	case SEEK_SET: /* seek relative to the beginning of the file */
-		newpos = offset;
-		break;
-	case SEEK_CUR: /* seek relative to current position in the file */
-		newpos = filp->f_pos + offset;
-		break;
-	case SEEK_END: /* seek relative to the end of the file */
-		newpos = priv->fw_size - offset;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* check for sanity */
-	if (newpos > priv->fw_size)
-		return -EINVAL;
-
-	filp->f_pos = newpos;
-	return newpos;
+	return fixed_size_llseek(file, offset, origin, priv->fw_size);
 }
 
 static const struct file_operations fpga_fops = {
diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig
new file mode 100644
index 000000000000..a990b39b4dfb
--- /dev/null
+++ b/drivers/misc/cxl/Kconfig
@@ -0,0 +1,25 @@
+#
+# IBM Coherent Accelerator (CXL) compatible devices
+#
+
+config CXL_BASE
+	bool
+	default n
+	select PPC_COPRO_BASE
+
+config CXL
+	tristate "Support for IBM Coherent Accelerators (CXL)"
+	depends on PPC_POWERNV && PCI_MSI
+	select CXL_BASE
+	default m
+	help
+	  Select this option to enable driver support for IBM Coherent
+	  Accelerators (CXL).  CXL is otherwise known as Coherent Accelerator
+	  Processor Interface (CAPI).  CAPI allows accelerators in FPGAs to be
+	  coherently attached to a CPU via an MMU.  This driver enables
+	  userspace programs to access these accelerators via /dev/cxl/afuM.N
+	  devices.
+
+	  CAPI adapters are found in POWER8 based systems.
+
+	  If unsure, say N.
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
new file mode 100644
index 000000000000..165e98fef2c2
--- /dev/null
+++ b/drivers/misc/cxl/Makefile
@@ -0,0 +1,3 @@
+cxl-y				+= main.o file.o irq.o fault.o native.o context.o sysfs.o debugfs.o pci.o
+obj-$(CONFIG_CXL)		+= cxl.o
+obj-$(CONFIG_CXL_BASE)		+= base.o
diff --git a/drivers/misc/cxl/base.c b/drivers/misc/cxl/base.c
new file mode 100644
index 000000000000..0654ad83675e
--- /dev/null
+++ b/drivers/misc/cxl/base.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/rcupdate.h>
+#include <asm/errno.h>
+#include <misc/cxl.h>
+#include "cxl.h"
+
+/* protected by rcu */
+static struct cxl_calls *cxl_calls;
+
+atomic_t cxl_use_count = ATOMIC_INIT(0);
+EXPORT_SYMBOL(cxl_use_count);
+
+#ifdef CONFIG_CXL_MODULE
+
+static inline struct cxl_calls *cxl_calls_get(void)
+{
+	struct cxl_calls *calls = NULL;
+
+	rcu_read_lock();
+	calls = rcu_dereference(cxl_calls);
+	if (calls && !try_module_get(calls->owner))
+		calls = NULL;
+	rcu_read_unlock();
+
+	return calls;
+}
+
+static inline void cxl_calls_put(struct cxl_calls *calls)
+{
+	BUG_ON(calls != cxl_calls);
+
+	/* we don't need to rcu this, as we hold a reference to the module */
+	module_put(cxl_calls->owner);
+}
+
+#else /* !defined CONFIG_CXL_MODULE */
+
+static inline struct cxl_calls *cxl_calls_get(void)
+{
+	return cxl_calls;
+}
+
+static inline void cxl_calls_put(struct cxl_calls *calls) { }
+
+#endif /* CONFIG_CXL_MODULE */
+
+void cxl_slbia(struct mm_struct *mm)
+{
+	struct cxl_calls *calls;
+
+	calls = cxl_calls_get();
+	if (!calls)
+		return;
+
+	if (cxl_ctx_in_use())
+	    calls->cxl_slbia(mm);
+
+	cxl_calls_put(calls);
+}
+
+int register_cxl_calls(struct cxl_calls *calls)
+{
+	if (cxl_calls)
+		return -EBUSY;
+
+	rcu_assign_pointer(cxl_calls, calls);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(register_cxl_calls);
+
+void unregister_cxl_calls(struct cxl_calls *calls)
+{
+	BUG_ON(cxl_calls->owner != calls->owner);
+	RCU_INIT_POINTER(cxl_calls, NULL);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(unregister_cxl_calls);
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
new file mode 100644
index 000000000000..cca472109135
--- /dev/null
+++ b/drivers/misc/cxl/context.c
@@ -0,0 +1,193 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/bitmap.h>
+#include <linux/sched.h>
+#include <linux/pid.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+#include <linux/idr.h>
+#include <asm/cputable.h>
+#include <asm/current.h>
+#include <asm/copro.h>
+
+#include "cxl.h"
+
+/*
+ * Allocates space for a CXL context.
+ */
+struct cxl_context *cxl_context_alloc(void)
+{
+	return kzalloc(sizeof(struct cxl_context), GFP_KERNEL);
+}
+
+/*
+ * Initialises a CXL context.
+ */
+int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master)
+{
+	int i;
+
+	spin_lock_init(&ctx->sste_lock);
+	ctx->afu = afu;
+	ctx->master = master;
+	ctx->pid = NULL; /* Set in start work ioctl */
+
+	/*
+	 * Allocate the segment table before we put it in the IDR so that we
+	 * can always access it when dereferenced from IDR. For the same
+	 * reason, the segment table is only destroyed after the context is
+	 * removed from the IDR.  Access to this in the IOCTL is protected by
+	 * Linux filesytem symantics (can't IOCTL until open is complete).
+	 */
+	i = cxl_alloc_sst(ctx);
+	if (i)
+		return i;
+
+	INIT_WORK(&ctx->fault_work, cxl_handle_fault);
+
+	init_waitqueue_head(&ctx->wq);
+	spin_lock_init(&ctx->lock);
+
+	ctx->irq_bitmap = NULL;
+	ctx->pending_irq = false;
+	ctx->pending_fault = false;
+	ctx->pending_afu_err = false;
+
+	/*
+	 * When we have to destroy all contexts in cxl_context_detach_all() we
+	 * end up with afu_release_irqs() called from inside a
+	 * idr_for_each_entry(). Hence we need to make sure that anything
+	 * dereferenced from this IDR is ok before we allocate the IDR here.
+	 * This clears out the IRQ ranges to ensure this.
+	 */
+	for (i = 0; i < CXL_IRQ_RANGES; i++)
+		ctx->irqs.range[i] = 0;
+
+	mutex_init(&ctx->status_mutex);
+
+	ctx->status = OPENED;
+
+	/*
+	 * Allocating IDR! We better make sure everything's setup that
+	 * dereferences from it.
+	 */
+	idr_preload(GFP_KERNEL);
+	spin_lock(&afu->contexts_lock);
+	i = idr_alloc(&ctx->afu->contexts_idr, ctx, 0,
+		      ctx->afu->num_procs, GFP_NOWAIT);
+	spin_unlock(&afu->contexts_lock);
+	idr_preload_end();
+	if (i < 0)
+		return i;
+
+	ctx->pe = i;
+	ctx->elem = &ctx->afu->spa[i];
+	ctx->pe_inserted = false;
+	return 0;
+}
+
+/*
+ * Map a per-context mmio space into the given vma.
+ */
+int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma)
+{
+	u64 len = vma->vm_end - vma->vm_start;
+	len = min(len, ctx->psn_size);
+
+	if (ctx->afu->current_mode == CXL_MODE_DEDICATED) {
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+		return vm_iomap_memory(vma, ctx->afu->psn_phys, ctx->afu->adapter->ps_size);
+	}
+
+	/* make sure there is a valid per process space for this AFU */
+	if ((ctx->master && !ctx->afu->psa) || (!ctx->afu->pp_psa)) {
+		pr_devel("AFU doesn't support mmio space\n");
+		return -EINVAL;
+	}
+
+	/* Can't mmap until the AFU is enabled */
+	if (!ctx->afu->enabled)
+		return -EBUSY;
+
+	pr_devel("%s: mmio physical: %llx pe: %i master:%i\n", __func__,
+		 ctx->psn_phys, ctx->pe , ctx->master);
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	return vm_iomap_memory(vma, ctx->psn_phys, len);
+}
+
+/*
+ * Detach a context from the hardware. This disables interrupts and doesn't
+ * return until all outstanding interrupts for this context have completed. The
+ * hardware should no longer access *ctx after this has returned.
+ */
+static void __detach_context(struct cxl_context *ctx)
+{
+	enum cxl_context_status status;
+
+	mutex_lock(&ctx->status_mutex);
+	status = ctx->status;
+	ctx->status = CLOSED;
+	mutex_unlock(&ctx->status_mutex);
+	if (status != STARTED)
+		return;
+
+	WARN_ON(cxl_detach_process(ctx));
+	afu_release_irqs(ctx);
+	flush_work(&ctx->fault_work); /* Only needed for dedicated process */
+	wake_up_all(&ctx->wq);
+}
+
+/*
+ * Detach the given context from the AFU. This doesn't actually
+ * free the context but it should stop the context running in hardware
+ * (ie. prevent this context from generating any further interrupts
+ * so that it can be freed).
+ */
+void cxl_context_detach(struct cxl_context *ctx)
+{
+	__detach_context(ctx);
+}
+
+/*
+ * Detach all contexts on the given AFU.
+ */
+void cxl_context_detach_all(struct cxl_afu *afu)
+{
+	struct cxl_context *ctx;
+	int tmp;
+
+	rcu_read_lock();
+	idr_for_each_entry(&afu->contexts_idr, ctx, tmp)
+		/*
+		 * Anything done in here needs to be setup before the IDR is
+		 * created and torn down after the IDR removed
+		 */
+		__detach_context(ctx);
+	rcu_read_unlock();
+}
+
+void cxl_context_free(struct cxl_context *ctx)
+{
+	spin_lock(&ctx->afu->contexts_lock);
+	idr_remove(&ctx->afu->contexts_idr, ctx->pe);
+	spin_unlock(&ctx->afu->contexts_lock);
+	synchronize_rcu();
+
+	free_page((u64)ctx->sstp);
+	ctx->sstp = NULL;
+
+	put_pid(ctx->pid);
+	kfree(ctx);
+}
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
new file mode 100644
index 000000000000..3d2b8677ec8a
--- /dev/null
+++ b/drivers/misc/cxl/cxl.h
@@ -0,0 +1,629 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _CXL_H_
+#define _CXL_H_
+
+#include <linux/interrupt.h>
+#include <linux/semaphore.h>
+#include <linux/device.h>
+#include <linux/types.h>
+#include <linux/cdev.h>
+#include <linux/pid.h>
+#include <linux/io.h>
+#include <linux/pci.h>
+#include <asm/cputable.h>
+#include <asm/mmu.h>
+#include <asm/reg.h>
+#include <misc/cxl.h>
+
+#include <uapi/misc/cxl.h>
+
+extern uint cxl_verbose;
+
+#define CXL_TIMEOUT 5
+
+/*
+ * Bump version each time a user API change is made, whether it is
+ * backwards compatible ot not.
+ */
+#define CXL_API_VERSION 1
+#define CXL_API_VERSION_COMPATIBLE 1
+
+/*
+ * Opaque types to avoid accidentally passing registers for the wrong MMIO
+ *
+ * At the end of the day, I'm not married to using typedef here, but it might
+ * (and has!) help avoid bugs like mixing up CXL_PSL_CtxTime and
+ * CXL_PSL_CtxTime_An, or calling cxl_p1n_write instead of cxl_p1_write.
+ *
+ * I'm quite happy if these are changed back to #defines before upstreaming, it
+ * should be little more than a regexp search+replace operation in this file.
+ */
+typedef struct {
+	const int x;
+} cxl_p1_reg_t;
+typedef struct {
+	const int x;
+} cxl_p1n_reg_t;
+typedef struct {
+	const int x;
+} cxl_p2n_reg_t;
+#define cxl_reg_off(reg) \
+	(reg.x)
+
+/* Memory maps. Ref CXL Appendix A */
+
+/* PSL Privilege 1 Memory Map */
+/* Configuration and Control area */
+static const cxl_p1_reg_t CXL_PSL_CtxTime = {0x0000};
+static const cxl_p1_reg_t CXL_PSL_ErrIVTE = {0x0008};
+static const cxl_p1_reg_t CXL_PSL_KEY1    = {0x0010};
+static const cxl_p1_reg_t CXL_PSL_KEY2    = {0x0018};
+static const cxl_p1_reg_t CXL_PSL_Control = {0x0020};
+/* Downloading */
+static const cxl_p1_reg_t CXL_PSL_DLCNTL  = {0x0060};
+static const cxl_p1_reg_t CXL_PSL_DLADDR  = {0x0068};
+
+/* PSL Lookaside Buffer Management Area */
+static const cxl_p1_reg_t CXL_PSL_LBISEL  = {0x0080};
+static const cxl_p1_reg_t CXL_PSL_SLBIE   = {0x0088};
+static const cxl_p1_reg_t CXL_PSL_SLBIA   = {0x0090};
+static const cxl_p1_reg_t CXL_PSL_TLBIE   = {0x00A0};
+static const cxl_p1_reg_t CXL_PSL_TLBIA   = {0x00A8};
+static const cxl_p1_reg_t CXL_PSL_AFUSEL  = {0x00B0};
+
+/* 0x00C0:7EFF Implementation dependent area */
+static const cxl_p1_reg_t CXL_PSL_FIR1      = {0x0100};
+static const cxl_p1_reg_t CXL_PSL_FIR2      = {0x0108};
+static const cxl_p1_reg_t CXL_PSL_VERSION   = {0x0118};
+static const cxl_p1_reg_t CXL_PSL_RESLCKTO  = {0x0128};
+static const cxl_p1_reg_t CXL_PSL_FIR_CNTL  = {0x0148};
+static const cxl_p1_reg_t CXL_PSL_DSNDCTL   = {0x0150};
+static const cxl_p1_reg_t CXL_PSL_SNWRALLOC = {0x0158};
+static const cxl_p1_reg_t CXL_PSL_TRACE     = {0x0170};
+/* 0x7F00:7FFF Reserved PCIe MSI-X Pending Bit Array area */
+/* 0x8000:FFFF Reserved PCIe MSI-X Table Area */
+
+/* PSL Slice Privilege 1 Memory Map */
+/* Configuration Area */
+static const cxl_p1n_reg_t CXL_PSL_SR_An          = {0x00};
+static const cxl_p1n_reg_t CXL_PSL_LPID_An        = {0x08};
+static const cxl_p1n_reg_t CXL_PSL_AMBAR_An       = {0x10};
+static const cxl_p1n_reg_t CXL_PSL_SPOffset_An    = {0x18};
+static const cxl_p1n_reg_t CXL_PSL_ID_An          = {0x20};
+static const cxl_p1n_reg_t CXL_PSL_SERR_An        = {0x28};
+/* Memory Management and Lookaside Buffer Management */
+static const cxl_p1n_reg_t CXL_PSL_SDR_An         = {0x30};
+static const cxl_p1n_reg_t CXL_PSL_AMOR_An        = {0x38};
+/* Pointer Area */
+static const cxl_p1n_reg_t CXL_HAURP_An           = {0x80};
+static const cxl_p1n_reg_t CXL_PSL_SPAP_An        = {0x88};
+static const cxl_p1n_reg_t CXL_PSL_LLCMD_An       = {0x90};
+/* Control Area */
+static const cxl_p1n_reg_t CXL_PSL_SCNTL_An       = {0xA0};
+static const cxl_p1n_reg_t CXL_PSL_CtxTime_An     = {0xA8};
+static const cxl_p1n_reg_t CXL_PSL_IVTE_Offset_An = {0xB0};
+static const cxl_p1n_reg_t CXL_PSL_IVTE_Limit_An  = {0xB8};
+/* 0xC0:FF Implementation Dependent Area */
+static const cxl_p1n_reg_t CXL_PSL_FIR_SLICE_An   = {0xC0};
+static const cxl_p1n_reg_t CXL_AFU_DEBUG_An       = {0xC8};
+static const cxl_p1n_reg_t CXL_PSL_APCALLOC_A     = {0xD0};
+static const cxl_p1n_reg_t CXL_PSL_COALLOC_A      = {0xD8};
+static const cxl_p1n_reg_t CXL_PSL_RXCTL_A        = {0xE0};
+static const cxl_p1n_reg_t CXL_PSL_SLICE_TRACE    = {0xE8};
+
+/* PSL Slice Privilege 2 Memory Map */
+/* Configuration and Control Area */
+static const cxl_p2n_reg_t CXL_PSL_PID_TID_An = {0x000};
+static const cxl_p2n_reg_t CXL_CSRP_An        = {0x008};
+static const cxl_p2n_reg_t CXL_AURP0_An       = {0x010};
+static const cxl_p2n_reg_t CXL_AURP1_An       = {0x018};
+static const cxl_p2n_reg_t CXL_SSTP0_An       = {0x020};
+static const cxl_p2n_reg_t CXL_SSTP1_An       = {0x028};
+static const cxl_p2n_reg_t CXL_PSL_AMR_An     = {0x030};
+/* Segment Lookaside Buffer Management */
+static const cxl_p2n_reg_t CXL_SLBIE_An       = {0x040};
+static const cxl_p2n_reg_t CXL_SLBIA_An       = {0x048};
+static const cxl_p2n_reg_t CXL_SLBI_Select_An = {0x050};
+/* Interrupt Registers */
+static const cxl_p2n_reg_t CXL_PSL_DSISR_An   = {0x060};
+static const cxl_p2n_reg_t CXL_PSL_DAR_An     = {0x068};
+static const cxl_p2n_reg_t CXL_PSL_DSR_An     = {0x070};
+static const cxl_p2n_reg_t CXL_PSL_TFC_An     = {0x078};
+static const cxl_p2n_reg_t CXL_PSL_PEHandle_An = {0x080};
+static const cxl_p2n_reg_t CXL_PSL_ErrStat_An = {0x088};
+/* AFU Registers */
+static const cxl_p2n_reg_t CXL_AFU_Cntl_An    = {0x090};
+static const cxl_p2n_reg_t CXL_AFU_ERR_An     = {0x098};
+/* Work Element Descriptor */
+static const cxl_p2n_reg_t CXL_PSL_WED_An     = {0x0A0};
+/* 0x0C0:FFF Implementation Dependent Area */
+
+#define CXL_PSL_SPAP_Addr 0x0ffffffffffff000ULL
+#define CXL_PSL_SPAP_Size 0x0000000000000ff0ULL
+#define CXL_PSL_SPAP_Size_Shift 4
+#define CXL_PSL_SPAP_V    0x0000000000000001ULL
+
+/****** CXL_PSL_DLCNTL *****************************************************/
+#define CXL_PSL_DLCNTL_D (0x1ull << (63-28))
+#define CXL_PSL_DLCNTL_C (0x1ull << (63-29))
+#define CXL_PSL_DLCNTL_E (0x1ull << (63-30))
+#define CXL_PSL_DLCNTL_S (0x1ull << (63-31))
+#define CXL_PSL_DLCNTL_CE (CXL_PSL_DLCNTL_C | CXL_PSL_DLCNTL_E)
+#define CXL_PSL_DLCNTL_DCES (CXL_PSL_DLCNTL_D | CXL_PSL_DLCNTL_CE | CXL_PSL_DLCNTL_S)
+
+/****** CXL_PSL_SR_An ******************************************************/
+#define CXL_PSL_SR_An_SF  MSR_SF            /* 64bit */
+#define CXL_PSL_SR_An_TA  (1ull << (63-1))  /* Tags active,   GA1: 0 */
+#define CXL_PSL_SR_An_HV  MSR_HV            /* Hypervisor,    GA1: 0 */
+#define CXL_PSL_SR_An_PR  MSR_PR            /* Problem state, GA1: 1 */
+#define CXL_PSL_SR_An_ISL (1ull << (63-53)) /* Ignore Segment Large Page */
+#define CXL_PSL_SR_An_TC  (1ull << (63-54)) /* Page Table secondary hash */
+#define CXL_PSL_SR_An_US  (1ull << (63-56)) /* User state,    GA1: X */
+#define CXL_PSL_SR_An_SC  (1ull << (63-58)) /* Segment Table secondary hash */
+#define CXL_PSL_SR_An_R   MSR_DR            /* Relocate,      GA1: 1 */
+#define CXL_PSL_SR_An_MP  (1ull << (63-62)) /* Master Process */
+#define CXL_PSL_SR_An_LE  (1ull << (63-63)) /* Little Endian */
+
+/****** CXL_PSL_LLCMD_An ****************************************************/
+#define CXL_LLCMD_TERMINATE   0x0001000000000000ULL
+#define CXL_LLCMD_REMOVE      0x0002000000000000ULL
+#define CXL_LLCMD_SUSPEND     0x0003000000000000ULL
+#define CXL_LLCMD_RESUME      0x0004000000000000ULL
+#define CXL_LLCMD_ADD         0x0005000000000000ULL
+#define CXL_LLCMD_UPDATE      0x0006000000000000ULL
+#define CXL_LLCMD_HANDLE_MASK 0x000000000000ffffULL
+
+/****** CXL_PSL_ID_An ****************************************************/
+#define CXL_PSL_ID_An_F	(1ull << (63-31))
+#define CXL_PSL_ID_An_L	(1ull << (63-30))
+
+/****** CXL_PSL_SCNTL_An ****************************************************/
+#define CXL_PSL_SCNTL_An_CR          (0x1ull << (63-15))
+/* Programming Modes: */
+#define CXL_PSL_SCNTL_An_PM_MASK     (0xffffull << (63-31))
+#define CXL_PSL_SCNTL_An_PM_Shared   (0x0000ull << (63-31))
+#define CXL_PSL_SCNTL_An_PM_OS       (0x0001ull << (63-31))
+#define CXL_PSL_SCNTL_An_PM_Process  (0x0002ull << (63-31))
+#define CXL_PSL_SCNTL_An_PM_AFU      (0x0004ull << (63-31))
+#define CXL_PSL_SCNTL_An_PM_AFU_PBT  (0x0104ull << (63-31))
+/* Purge Status (ro) */
+#define CXL_PSL_SCNTL_An_Ps_MASK     (0x3ull << (63-39))
+#define CXL_PSL_SCNTL_An_Ps_Pending  (0x1ull << (63-39))
+#define CXL_PSL_SCNTL_An_Ps_Complete (0x3ull << (63-39))
+/* Purge */
+#define CXL_PSL_SCNTL_An_Pc          (0x1ull << (63-48))
+/* Suspend Status (ro) */
+#define CXL_PSL_SCNTL_An_Ss_MASK     (0x3ull << (63-55))
+#define CXL_PSL_SCNTL_An_Ss_Pending  (0x1ull << (63-55))
+#define CXL_PSL_SCNTL_An_Ss_Complete (0x3ull << (63-55))
+/* Suspend Control */
+#define CXL_PSL_SCNTL_An_Sc          (0x1ull << (63-63))
+
+/* AFU Slice Enable Status (ro) */
+#define CXL_AFU_Cntl_An_ES_MASK     (0x7ull << (63-2))
+#define CXL_AFU_Cntl_An_ES_Disabled (0x0ull << (63-2))
+#define CXL_AFU_Cntl_An_ES_Enabled  (0x4ull << (63-2))
+/* AFU Slice Enable */
+#define CXL_AFU_Cntl_An_E           (0x1ull << (63-3))
+/* AFU Slice Reset status (ro) */
+#define CXL_AFU_Cntl_An_RS_MASK     (0x3ull << (63-5))
+#define CXL_AFU_Cntl_An_RS_Pending  (0x1ull << (63-5))
+#define CXL_AFU_Cntl_An_RS_Complete (0x2ull << (63-5))
+/* AFU Slice Reset */
+#define CXL_AFU_Cntl_An_RA          (0x1ull << (63-7))
+
+/****** CXL_SSTP0/1_An ******************************************************/
+/* These top bits are for the segment that CONTAINS the segment table */
+#define CXL_SSTP0_An_B_SHIFT    SLB_VSID_SSIZE_SHIFT
+#define CXL_SSTP0_An_KS             (1ull << (63-2))
+#define CXL_SSTP0_An_KP             (1ull << (63-3))
+#define CXL_SSTP0_An_N              (1ull << (63-4))
+#define CXL_SSTP0_An_L              (1ull << (63-5))
+#define CXL_SSTP0_An_C              (1ull << (63-6))
+#define CXL_SSTP0_An_TA             (1ull << (63-7))
+#define CXL_SSTP0_An_LP_SHIFT                (63-9)  /* 2 Bits */
+/* And finally, the virtual address & size of the segment table: */
+#define CXL_SSTP0_An_SegTableSize_SHIFT      (63-31) /* 12 Bits */
+#define CXL_SSTP0_An_SegTableSize_MASK \
+	(((1ull << 12) - 1) << CXL_SSTP0_An_SegTableSize_SHIFT)
+#define CXL_SSTP0_An_STVA_U_MASK   ((1ull << (63-49))-1)
+#define CXL_SSTP1_An_STVA_L_MASK (~((1ull << (63-55))-1))
+#define CXL_SSTP1_An_V              (1ull << (63-63))
+
+/****** CXL_PSL_SLBIE_[An] **************************************************/
+/* write: */
+#define CXL_SLBIE_C        PPC_BIT(36)         /* Class */
+#define CXL_SLBIE_SS       PPC_BITMASK(37, 38) /* Segment Size */
+#define CXL_SLBIE_SS_SHIFT PPC_BITLSHIFT(38)
+#define CXL_SLBIE_TA       PPC_BIT(38)         /* Tags Active */
+/* read: */
+#define CXL_SLBIE_MAX      PPC_BITMASK(24, 31)
+#define CXL_SLBIE_PENDING  PPC_BITMASK(56, 63)
+
+/****** Common to all CXL_TLBIA/SLBIA_[An] **********************************/
+#define CXL_TLB_SLB_P          (1ull) /* Pending (read) */
+
+/****** Common to all CXL_TLB/SLB_IA/IE_[An] registers **********************/
+#define CXL_TLB_SLB_IQ_ALL     (0ull) /* Inv qualifier */
+#define CXL_TLB_SLB_IQ_LPID    (1ull) /* Inv qualifier */
+#define CXL_TLB_SLB_IQ_LPIDPID (3ull) /* Inv qualifier */
+
+/****** CXL_PSL_AFUSEL ******************************************************/
+#define CXL_PSL_AFUSEL_A (1ull << (63-55)) /* Adapter wide invalidates affect all AFUs */
+
+/****** CXL_PSL_DSISR_An ****************************************************/
+#define CXL_PSL_DSISR_An_DS (1ull << (63-0))  /* Segment not found */
+#define CXL_PSL_DSISR_An_DM (1ull << (63-1))  /* PTE not found (See also: M) or protection fault */
+#define CXL_PSL_DSISR_An_ST (1ull << (63-2))  /* Segment Table PTE not found */
+#define CXL_PSL_DSISR_An_UR (1ull << (63-3))  /* AURP PTE not found */
+#define CXL_PSL_DSISR_TRANS (CXL_PSL_DSISR_An_DS | CXL_PSL_DSISR_An_DM | CXL_PSL_DSISR_An_ST | CXL_PSL_DSISR_An_UR)
+#define CXL_PSL_DSISR_An_PE (1ull << (63-4))  /* PSL Error (implementation specific) */
+#define CXL_PSL_DSISR_An_AE (1ull << (63-5))  /* AFU Error */
+#define CXL_PSL_DSISR_An_OC (1ull << (63-6))  /* OS Context Warning */
+/* NOTE: Bits 32:63 are undefined if DSISR[DS] = 1 */
+#define CXL_PSL_DSISR_An_M  DSISR_NOHPTE      /* PTE not found */
+#define CXL_PSL_DSISR_An_P  DSISR_PROTFAULT   /* Storage protection violation */
+#define CXL_PSL_DSISR_An_A  (1ull << (63-37)) /* AFU lock access to write through or cache inhibited storage */
+#define CXL_PSL_DSISR_An_S  DSISR_ISSTORE     /* Access was afu_wr or afu_zero */
+#define CXL_PSL_DSISR_An_K  DSISR_KEYFAULT    /* Access not permitted by virtual page class key protection */
+
+/****** CXL_PSL_TFC_An ******************************************************/
+#define CXL_PSL_TFC_An_A  (1ull << (63-28)) /* Acknowledge non-translation fault */
+#define CXL_PSL_TFC_An_C  (1ull << (63-29)) /* Continue (abort transaction) */
+#define CXL_PSL_TFC_An_AE (1ull << (63-30)) /* Restart PSL with address error */
+#define CXL_PSL_TFC_An_R  (1ull << (63-31)) /* Restart PSL transaction */
+
+/* cxl_process_element->software_status */
+#define CXL_PE_SOFTWARE_STATE_V (1ul << (31 -  0)) /* Valid */
+#define CXL_PE_SOFTWARE_STATE_C (1ul << (31 - 29)) /* Complete */
+#define CXL_PE_SOFTWARE_STATE_S (1ul << (31 - 30)) /* Suspend */
+#define CXL_PE_SOFTWARE_STATE_T (1ul << (31 - 31)) /* Terminate */
+
+/* SPA->sw_command_status */
+#define CXL_SPA_SW_CMD_MASK         0xffff000000000000ULL
+#define CXL_SPA_SW_CMD_TERMINATE    0x0001000000000000ULL
+#define CXL_SPA_SW_CMD_REMOVE       0x0002000000000000ULL
+#define CXL_SPA_SW_CMD_SUSPEND      0x0003000000000000ULL
+#define CXL_SPA_SW_CMD_RESUME       0x0004000000000000ULL
+#define CXL_SPA_SW_CMD_ADD          0x0005000000000000ULL
+#define CXL_SPA_SW_CMD_UPDATE       0x0006000000000000ULL
+#define CXL_SPA_SW_STATE_MASK       0x0000ffff00000000ULL
+#define CXL_SPA_SW_STATE_TERMINATED 0x0000000100000000ULL
+#define CXL_SPA_SW_STATE_REMOVED    0x0000000200000000ULL
+#define CXL_SPA_SW_STATE_SUSPENDED  0x0000000300000000ULL
+#define CXL_SPA_SW_STATE_RESUMED    0x0000000400000000ULL
+#define CXL_SPA_SW_STATE_ADDED      0x0000000500000000ULL
+#define CXL_SPA_SW_STATE_UPDATED    0x0000000600000000ULL
+#define CXL_SPA_SW_PSL_ID_MASK      0x00000000ffff0000ULL
+#define CXL_SPA_SW_LINK_MASK        0x000000000000ffffULL
+
+#define CXL_MAX_SLICES 4
+#define MAX_AFU_MMIO_REGS 3
+
+#define CXL_MODE_DEDICATED   0x1
+#define CXL_MODE_DIRECTED    0x2
+#define CXL_MODE_TIME_SLICED 0x4
+#define CXL_SUPPORTED_MODES (CXL_MODE_DEDICATED | CXL_MODE_DIRECTED)
+
+enum cxl_context_status {
+	CLOSED,
+	OPENED,
+	STARTED
+};
+
+enum prefault_modes {
+	CXL_PREFAULT_NONE,
+	CXL_PREFAULT_WED,
+	CXL_PREFAULT_ALL,
+};
+
+struct cxl_sste {
+	__be64 esid_data;
+	__be64 vsid_data;
+};
+
+#define to_cxl_adapter(d) container_of(d, struct cxl, dev)
+#define to_cxl_afu(d) container_of(d, struct cxl_afu, dev)
+
+struct cxl_afu {
+	irq_hw_number_t psl_hwirq;
+	irq_hw_number_t serr_hwirq;
+	unsigned int serr_virq;
+	void __iomem *p1n_mmio;
+	void __iomem *p2n_mmio;
+	phys_addr_t psn_phys;
+	u64 pp_offset;
+	u64 pp_size;
+	void __iomem *afu_desc_mmio;
+	struct cxl *adapter;
+	struct device dev;
+	struct cdev afu_cdev_s, afu_cdev_m, afu_cdev_d;
+	struct device *chardev_s, *chardev_m, *chardev_d;
+	struct idr contexts_idr;
+	struct dentry *debugfs;
+	spinlock_t contexts_lock;
+	struct mutex spa_mutex;
+	spinlock_t afu_cntl_lock;
+
+	/*
+	 * Only the first part of the SPA is used for the process element
+	 * linked list. The only other part that software needs to worry about
+	 * is sw_command_status, which we store a separate pointer to.
+	 * Everything else in the SPA is only used by hardware
+	 */
+	struct cxl_process_element *spa;
+	__be64 *sw_command_status;
+	unsigned int spa_size;
+	int spa_order;
+	int spa_max_procs;
+	unsigned int psl_virq;
+
+	int pp_irqs;
+	int irqs_max;
+	int num_procs;
+	int max_procs_virtualised;
+	int slice;
+	int modes_supported;
+	int current_mode;
+	enum prefault_modes prefault_mode;
+	bool psa;
+	bool pp_psa;
+	bool enabled;
+};
+
+/*
+ * This is a cxl context.  If the PSL is in dedicated mode, there will be one
+ * of these per AFU.  If in AFU directed there can be lots of these.
+ */
+struct cxl_context {
+	struct cxl_afu *afu;
+
+	/* Problem state MMIO */
+	phys_addr_t psn_phys;
+	u64 psn_size;
+
+	spinlock_t sste_lock; /* Protects segment table entries */
+	struct cxl_sste *sstp;
+	u64 sstp0, sstp1;
+	unsigned int sst_size, sst_lru;
+
+	wait_queue_head_t wq;
+	struct pid *pid;
+	spinlock_t lock; /* Protects pending_irq_mask, pending_fault and fault_addr */
+	/* Only used in PR mode */
+	u64 process_token;
+
+	unsigned long *irq_bitmap; /* Accessed from IRQ context */
+	struct cxl_irq_ranges irqs;
+	u64 fault_addr;
+	u64 fault_dsisr;
+	u64 afu_err;
+
+	/*
+	 * This status and it's lock pretects start and detach context
+	 * from racing.  It also prevents detach from racing with
+	 * itself
+	 */
+	enum cxl_context_status status;
+	struct mutex status_mutex;
+
+
+	/* XXX: Is it possible to need multiple work items at once? */
+	struct work_struct fault_work;
+	u64 dsisr;
+	u64 dar;
+
+	struct cxl_process_element *elem;
+
+	int pe; /* process element handle */
+	u32 irq_count;
+	bool pe_inserted;
+	bool master;
+	bool kernel;
+	bool pending_irq;
+	bool pending_fault;
+	bool pending_afu_err;
+};
+
+struct cxl {
+	void __iomem *p1_mmio;
+	void __iomem *p2_mmio;
+	irq_hw_number_t err_hwirq;
+	unsigned int err_virq;
+	spinlock_t afu_list_lock;
+	struct cxl_afu *afu[CXL_MAX_SLICES];
+	struct device dev;
+	struct dentry *trace;
+	struct dentry *psl_err_chk;
+	struct dentry *debugfs;
+	struct bin_attribute cxl_attr;
+	int adapter_num;
+	int user_irqs;
+	u64 afu_desc_off;
+	u64 afu_desc_size;
+	u64 ps_off;
+	u64 ps_size;
+	u16 psl_rev;
+	u16 base_image;
+	u8 vsec_status;
+	u8 caia_major;
+	u8 caia_minor;
+	u8 slices;
+	bool user_image_loaded;
+	bool perst_loads_image;
+	bool perst_select_user;
+};
+
+int cxl_alloc_one_irq(struct cxl *adapter);
+void cxl_release_one_irq(struct cxl *adapter, int hwirq);
+int cxl_alloc_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter, unsigned int num);
+void cxl_release_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter);
+int cxl_setup_irq(struct cxl *adapter, unsigned int hwirq, unsigned int virq);
+
+/* common == phyp + powernv */
+struct cxl_process_element_common {
+	__be32 tid;
+	__be32 pid;
+	__be64 csrp;
+	__be64 aurp0;
+	__be64 aurp1;
+	__be64 sstp0;
+	__be64 sstp1;
+	__be64 amr;
+	u8     reserved3[4];
+	__be64 wed;
+} __packed;
+
+/* just powernv */
+struct cxl_process_element {
+	__be64 sr;
+	__be64 SPOffset;
+	__be64 sdr;
+	__be64 haurp;
+	__be32 ctxtime;
+	__be16 ivte_offsets[4];
+	__be16 ivte_ranges[4];
+	__be32 lpid;
+	struct cxl_process_element_common common;
+	__be32 software_state;
+} __packed;
+
+static inline void __iomem *_cxl_p1_addr(struct cxl *cxl, cxl_p1_reg_t reg)
+{
+	WARN_ON(!cpu_has_feature(CPU_FTR_HVMODE));
+	return cxl->p1_mmio + cxl_reg_off(reg);
+}
+
+#define cxl_p1_write(cxl, reg, val) \
+	out_be64(_cxl_p1_addr(cxl, reg), val)
+#define cxl_p1_read(cxl, reg) \
+	in_be64(_cxl_p1_addr(cxl, reg))
+
+static inline void __iomem *_cxl_p1n_addr(struct cxl_afu *afu, cxl_p1n_reg_t reg)
+{
+	WARN_ON(!cpu_has_feature(CPU_FTR_HVMODE));
+	return afu->p1n_mmio + cxl_reg_off(reg);
+}
+
+#define cxl_p1n_write(afu, reg, val) \
+	out_be64(_cxl_p1n_addr(afu, reg), val)
+#define cxl_p1n_read(afu, reg) \
+	in_be64(_cxl_p1n_addr(afu, reg))
+
+static inline void __iomem *_cxl_p2n_addr(struct cxl_afu *afu, cxl_p2n_reg_t reg)
+{
+	return afu->p2n_mmio + cxl_reg_off(reg);
+}
+
+#define cxl_p2n_write(afu, reg, val) \
+	out_be64(_cxl_p2n_addr(afu, reg), val)
+#define cxl_p2n_read(afu, reg) \
+	in_be64(_cxl_p2n_addr(afu, reg))
+
+struct cxl_calls {
+	void (*cxl_slbia)(struct mm_struct *mm);
+	struct module *owner;
+};
+int register_cxl_calls(struct cxl_calls *calls);
+void unregister_cxl_calls(struct cxl_calls *calls);
+
+int cxl_alloc_adapter_nr(struct cxl *adapter);
+void cxl_remove_adapter_nr(struct cxl *adapter);
+
+int cxl_file_init(void);
+void cxl_file_exit(void);
+int cxl_register_adapter(struct cxl *adapter);
+int cxl_register_afu(struct cxl_afu *afu);
+int cxl_chardev_d_afu_add(struct cxl_afu *afu);
+int cxl_chardev_m_afu_add(struct cxl_afu *afu);
+int cxl_chardev_s_afu_add(struct cxl_afu *afu);
+void cxl_chardev_afu_remove(struct cxl_afu *afu);
+
+void cxl_context_detach_all(struct cxl_afu *afu);
+void cxl_context_free(struct cxl_context *ctx);
+void cxl_context_detach(struct cxl_context *ctx);
+
+int cxl_sysfs_adapter_add(struct cxl *adapter);
+void cxl_sysfs_adapter_remove(struct cxl *adapter);
+int cxl_sysfs_afu_add(struct cxl_afu *afu);
+void cxl_sysfs_afu_remove(struct cxl_afu *afu);
+int cxl_sysfs_afu_m_add(struct cxl_afu *afu);
+void cxl_sysfs_afu_m_remove(struct cxl_afu *afu);
+
+int cxl_afu_activate_mode(struct cxl_afu *afu, int mode);
+int _cxl_afu_deactivate_mode(struct cxl_afu *afu, int mode);
+int cxl_afu_deactivate_mode(struct cxl_afu *afu);
+int cxl_afu_select_best_mode(struct cxl_afu *afu);
+
+unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq,
+		         irq_handler_t handler, void *cookie);
+void cxl_unmap_irq(unsigned int virq, void *cookie);
+int cxl_register_psl_irq(struct cxl_afu *afu);
+void cxl_release_psl_irq(struct cxl_afu *afu);
+int cxl_register_psl_err_irq(struct cxl *adapter);
+void cxl_release_psl_err_irq(struct cxl *adapter);
+int cxl_register_serr_irq(struct cxl_afu *afu);
+void cxl_release_serr_irq(struct cxl_afu *afu);
+int afu_register_irqs(struct cxl_context *ctx, u32 count);
+void afu_release_irqs(struct cxl_context *ctx);
+irqreturn_t cxl_slice_irq_err(int irq, void *data);
+
+int cxl_debugfs_init(void);
+void cxl_debugfs_exit(void);
+int cxl_debugfs_adapter_add(struct cxl *adapter);
+void cxl_debugfs_adapter_remove(struct cxl *adapter);
+int cxl_debugfs_afu_add(struct cxl_afu *afu);
+void cxl_debugfs_afu_remove(struct cxl_afu *afu);
+
+void cxl_handle_fault(struct work_struct *work);
+void cxl_prefault(struct cxl_context *ctx, u64 wed);
+
+struct cxl *get_cxl_adapter(int num);
+int cxl_alloc_sst(struct cxl_context *ctx);
+
+void init_cxl_native(void);
+
+struct cxl_context *cxl_context_alloc(void);
+int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master);
+void cxl_context_free(struct cxl_context *ctx);
+int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma);
+
+/* This matches the layout of the H_COLLECT_CA_INT_INFO retbuf */
+struct cxl_irq_info {
+	u64 dsisr;
+	u64 dar;
+	u64 dsr;
+	u32 pid;
+	u32 tid;
+	u64 afu_err;
+	u64 errstat;
+	u64 padding[3]; /* to match the expected retbuf size for plpar_hcall9 */
+};
+
+int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed,
+			    u64 amr);
+int cxl_detach_process(struct cxl_context *ctx);
+
+int cxl_get_irq(struct cxl_context *ctx, struct cxl_irq_info *info);
+int cxl_ack_irq(struct cxl_context *ctx, u64 tfc, u64 psl_reset_mask);
+
+int cxl_check_error(struct cxl_afu *afu);
+int cxl_afu_slbia(struct cxl_afu *afu);
+int cxl_tlb_slb_invalidate(struct cxl *adapter);
+int cxl_afu_disable(struct cxl_afu *afu);
+int cxl_afu_reset(struct cxl_afu *afu);
+int cxl_psl_purge(struct cxl_afu *afu);
+
+void cxl_stop_trace(struct cxl *cxl);
+
+extern struct pci_driver cxl_pci_driver;
+
+#endif
diff --git a/drivers/misc/cxl/debugfs.c b/drivers/misc/cxl/debugfs.c
new file mode 100644
index 000000000000..825c412580bc
--- /dev/null
+++ b/drivers/misc/cxl/debugfs.c
@@ -0,0 +1,132 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "cxl.h"
+
+static struct dentry *cxl_debugfs;
+
+void cxl_stop_trace(struct cxl *adapter)
+{
+	int slice;
+
+	/* Stop the trace */
+	cxl_p1_write(adapter, CXL_PSL_TRACE, 0x8000000000000017LL);
+
+	/* Stop the slice traces */
+	spin_lock(&adapter->afu_list_lock);
+	for (slice = 0; slice < adapter->slices; slice++) {
+		if (adapter->afu[slice])
+			cxl_p1n_write(adapter->afu[slice], CXL_PSL_SLICE_TRACE, 0x8000000000000000LL);
+	}
+	spin_unlock(&adapter->afu_list_lock);
+}
+
+/* Helpers to export CXL mmaped IO registers via debugfs */
+static int debugfs_io_u64_get(void *data, u64 *val)
+{
+	*val = in_be64((u64 __iomem *)data);
+	return 0;
+}
+
+static int debugfs_io_u64_set(void *data, u64 val)
+{
+	out_be64((u64 __iomem *)data, val);
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fops_io_x64, debugfs_io_u64_get, debugfs_io_u64_set, "0x%016llx\n");
+
+static struct dentry *debugfs_create_io_x64(const char *name, umode_t mode,
+					    struct dentry *parent, u64 __iomem *value)
+{
+	return debugfs_create_file(name, mode, parent, (void *)value, &fops_io_x64);
+}
+
+int cxl_debugfs_adapter_add(struct cxl *adapter)
+{
+	struct dentry *dir;
+	char buf[32];
+
+	if (!cxl_debugfs)
+		return -ENODEV;
+
+	snprintf(buf, 32, "card%i", adapter->adapter_num);
+	dir = debugfs_create_dir(buf, cxl_debugfs);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+	adapter->debugfs = dir;
+
+	debugfs_create_io_x64("fir1",     S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR1));
+	debugfs_create_io_x64("fir2",     S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR2));
+	debugfs_create_io_x64("fir_cntl", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR_CNTL));
+	debugfs_create_io_x64("err_ivte", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_ErrIVTE));
+
+	debugfs_create_io_x64("trace", S_IRUSR | S_IWUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_TRACE));
+
+	return 0;
+}
+
+void cxl_debugfs_adapter_remove(struct cxl *adapter)
+{
+	debugfs_remove_recursive(adapter->debugfs);
+}
+
+int cxl_debugfs_afu_add(struct cxl_afu *afu)
+{
+	struct dentry *dir;
+	char buf[32];
+
+	if (!afu->adapter->debugfs)
+		return -ENODEV;
+
+	snprintf(buf, 32, "psl%i.%i", afu->adapter->adapter_num, afu->slice);
+	dir = debugfs_create_dir(buf, afu->adapter->debugfs);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+	afu->debugfs = dir;
+
+	debugfs_create_io_x64("fir",        S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_FIR_SLICE_An));
+	debugfs_create_io_x64("serr",       S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SERR_An));
+	debugfs_create_io_x64("afu_debug",  S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_AFU_DEBUG_An));
+	debugfs_create_io_x64("sr",         S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SR_An));
+
+	debugfs_create_io_x64("dsisr",      S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_DSISR_An));
+	debugfs_create_io_x64("dar",        S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_DAR_An));
+	debugfs_create_io_x64("sstp0",      S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_SSTP0_An));
+	debugfs_create_io_x64("sstp1",      S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_SSTP1_An));
+	debugfs_create_io_x64("err_status", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_ErrStat_An));
+
+	debugfs_create_io_x64("trace", S_IRUSR | S_IWUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SLICE_TRACE));
+
+	return 0;
+}
+
+void cxl_debugfs_afu_remove(struct cxl_afu *afu)
+{
+	debugfs_remove_recursive(afu->debugfs);
+}
+
+int __init cxl_debugfs_init(void)
+{
+	struct dentry *ent;
+	ent = debugfs_create_dir("cxl", NULL);
+	if (IS_ERR(ent))
+		return PTR_ERR(ent);
+	cxl_debugfs = ent;
+
+	return 0;
+}
+
+void cxl_debugfs_exit(void)
+{
+	debugfs_remove_recursive(cxl_debugfs);
+}
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
new file mode 100644
index 000000000000..69506ebd4d07
--- /dev/null
+++ b/drivers/misc/cxl/fault.c
@@ -0,0 +1,291 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/pid.h>
+#include <linux/mm.h>
+#include <linux/moduleparam.h>
+
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX "cxl" "."
+#include <asm/current.h>
+#include <asm/copro.h>
+#include <asm/mmu.h>
+
+#include "cxl.h"
+
+static struct cxl_sste* find_free_sste(struct cxl_sste *primary_group,
+				       bool sec_hash,
+				       struct cxl_sste *secondary_group,
+				       unsigned int *lru)
+{
+	unsigned int i, entry;
+	struct cxl_sste *sste, *group = primary_group;
+
+	for (i = 0; i < 2; i++) {
+		for (entry = 0; entry < 8; entry++) {
+			sste = group + entry;
+			if (!(be64_to_cpu(sste->esid_data) & SLB_ESID_V))
+				return sste;
+		}
+		if (!sec_hash)
+			break;
+		group = secondary_group;
+	}
+	/* Nothing free, select an entry to cast out */
+	if (sec_hash && (*lru & 0x8))
+		sste = secondary_group + (*lru & 0x7);
+	else
+		sste = primary_group + (*lru & 0x7);
+	*lru = (*lru + 1) & 0xf;
+
+	return sste;
+}
+
+static void cxl_load_segment(struct cxl_context *ctx, struct copro_slb *slb)
+{
+	/* mask is the group index, we search primary and secondary here. */
+	unsigned int mask = (ctx->sst_size >> 7)-1; /* SSTP0[SegTableSize] */
+	bool sec_hash = 1;
+	struct cxl_sste *sste;
+	unsigned int hash;
+	unsigned long flags;
+
+
+	sec_hash = !!(cxl_p1n_read(ctx->afu, CXL_PSL_SR_An) & CXL_PSL_SR_An_SC);
+
+	if (slb->vsid & SLB_VSID_B_1T)
+		hash = (slb->esid >> SID_SHIFT_1T) & mask;
+	else /* 256M */
+		hash = (slb->esid >> SID_SHIFT) & mask;
+
+	spin_lock_irqsave(&ctx->sste_lock, flags);
+	sste = find_free_sste(ctx->sstp + (hash << 3), sec_hash,
+			      ctx->sstp + ((~hash & mask) << 3), &ctx->sst_lru);
+
+	pr_devel("CXL Populating SST[%li]: %#llx %#llx\n",
+			sste - ctx->sstp, slb->vsid, slb->esid);
+
+	sste->vsid_data = cpu_to_be64(slb->vsid);
+	sste->esid_data = cpu_to_be64(slb->esid);
+	spin_unlock_irqrestore(&ctx->sste_lock, flags);
+}
+
+static int cxl_fault_segment(struct cxl_context *ctx, struct mm_struct *mm,
+			     u64 ea)
+{
+	struct copro_slb slb = {0,0};
+	int rc;
+
+	if (!(rc = copro_calculate_slb(mm, ea, &slb))) {
+		cxl_load_segment(ctx, &slb);
+	}
+
+	return rc;
+}
+
+static void cxl_ack_ae(struct cxl_context *ctx)
+{
+	unsigned long flags;
+
+	cxl_ack_irq(ctx, CXL_PSL_TFC_An_AE, 0);
+
+	spin_lock_irqsave(&ctx->lock, flags);
+	ctx->pending_fault = true;
+	ctx->fault_addr = ctx->dar;
+	ctx->fault_dsisr = ctx->dsisr;
+	spin_unlock_irqrestore(&ctx->lock, flags);
+
+	wake_up_all(&ctx->wq);
+}
+
+static int cxl_handle_segment_miss(struct cxl_context *ctx,
+				   struct mm_struct *mm, u64 ea)
+{
+	int rc;
+
+	pr_devel("CXL interrupt: Segment fault pe: %i ea: %#llx\n", ctx->pe, ea);
+
+	if ((rc = cxl_fault_segment(ctx, mm, ea)))
+		cxl_ack_ae(ctx);
+	else {
+
+		mb(); /* Order seg table write to TFC MMIO write */
+		cxl_ack_irq(ctx, CXL_PSL_TFC_An_R, 0);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void cxl_handle_page_fault(struct cxl_context *ctx,
+				  struct mm_struct *mm, u64 dsisr, u64 dar)
+{
+	unsigned flt = 0;
+	int result;
+	unsigned long access, flags;
+
+	if ((result = copro_handle_mm_fault(mm, dar, dsisr, &flt))) {
+		pr_devel("copro_handle_mm_fault failed: %#x\n", result);
+		return cxl_ack_ae(ctx);
+	}
+
+	/*
+	 * update_mmu_cache() will not have loaded the hash since current->trap
+	 * is not a 0x400 or 0x300, so just call hash_page_mm() here.
+	 */
+	access = _PAGE_PRESENT;
+	if (dsisr & CXL_PSL_DSISR_An_S)
+		access |= _PAGE_RW;
+	if ((!ctx->kernel) || ~(dar & (1ULL << 63)))
+		access |= _PAGE_USER;
+	local_irq_save(flags);
+	hash_page_mm(mm, dar, access, 0x300);
+	local_irq_restore(flags);
+
+	pr_devel("Page fault successfully handled for pe: %i!\n", ctx->pe);
+	cxl_ack_irq(ctx, CXL_PSL_TFC_An_R, 0);
+}
+
+void cxl_handle_fault(struct work_struct *fault_work)
+{
+	struct cxl_context *ctx =
+		container_of(fault_work, struct cxl_context, fault_work);
+	u64 dsisr = ctx->dsisr;
+	u64 dar = ctx->dar;
+	struct task_struct *task;
+	struct mm_struct *mm;
+
+	if (cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An) != dsisr ||
+	    cxl_p2n_read(ctx->afu, CXL_PSL_DAR_An) != dar ||
+	    cxl_p2n_read(ctx->afu, CXL_PSL_PEHandle_An) != ctx->pe) {
+		/* Most likely explanation is harmless - a dedicated process
+		 * has detached and these were cleared by the PSL purge, but
+		 * warn about it just in case */
+		dev_notice(&ctx->afu->dev, "cxl_handle_fault: Translation fault regs changed\n");
+		return;
+	}
+
+	pr_devel("CXL BOTTOM HALF handling fault for afu pe: %i. "
+		"DSISR: %#llx DAR: %#llx\n", ctx->pe, dsisr, dar);
+
+	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
+		pr_devel("cxl_handle_fault unable to get task %i\n",
+			 pid_nr(ctx->pid));
+		cxl_ack_ae(ctx);
+		return;
+	}
+	if (!(mm = get_task_mm(task))) {
+		pr_devel("cxl_handle_fault unable to get mm %i\n",
+			 pid_nr(ctx->pid));
+		cxl_ack_ae(ctx);
+		goto out;
+	}
+
+	if (dsisr & CXL_PSL_DSISR_An_DS)
+		cxl_handle_segment_miss(ctx, mm, dar);
+	else if (dsisr & CXL_PSL_DSISR_An_DM)
+		cxl_handle_page_fault(ctx, mm, dsisr, dar);
+	else
+		WARN(1, "cxl_handle_fault has nothing to handle\n");
+
+	mmput(mm);
+out:
+	put_task_struct(task);
+}
+
+static void cxl_prefault_one(struct cxl_context *ctx, u64 ea)
+{
+	int rc;
+	struct task_struct *task;
+	struct mm_struct *mm;
+
+	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
+		pr_devel("cxl_prefault_one unable to get task %i\n",
+			 pid_nr(ctx->pid));
+		return;
+	}
+	if (!(mm = get_task_mm(task))) {
+		pr_devel("cxl_prefault_one unable to get mm %i\n",
+			 pid_nr(ctx->pid));
+		put_task_struct(task);
+		return;
+	}
+
+	rc = cxl_fault_segment(ctx, mm, ea);
+
+	mmput(mm);
+	put_task_struct(task);
+}
+
+static u64 next_segment(u64 ea, u64 vsid)
+{
+	if (vsid & SLB_VSID_B_1T)
+		ea |= (1ULL << 40) - 1;
+	else
+		ea |= (1ULL << 28) - 1;
+
+	return ea + 1;
+}
+
+static void cxl_prefault_vma(struct cxl_context *ctx)
+{
+	u64 ea, last_esid = 0;
+	struct copro_slb slb;
+	struct vm_area_struct *vma;
+	int rc;
+	struct task_struct *task;
+	struct mm_struct *mm;
+
+	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
+		pr_devel("cxl_prefault_vma unable to get task %i\n",
+			 pid_nr(ctx->pid));
+		return;
+	}
+	if (!(mm = get_task_mm(task))) {
+		pr_devel("cxl_prefault_vm unable to get mm %i\n",
+			 pid_nr(ctx->pid));
+		goto out1;
+	}
+
+	down_read(&mm->mmap_sem);
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		for (ea = vma->vm_start; ea < vma->vm_end;
+				ea = next_segment(ea, slb.vsid)) {
+			rc = copro_calculate_slb(mm, ea, &slb);
+			if (rc)
+				continue;
+
+			if (last_esid == slb.esid)
+				continue;
+
+			cxl_load_segment(ctx, &slb);
+			last_esid = slb.esid;
+		}
+	}
+	up_read(&mm->mmap_sem);
+
+	mmput(mm);
+out1:
+	put_task_struct(task);
+}
+
+void cxl_prefault(struct cxl_context *ctx, u64 wed)
+{
+	switch (ctx->afu->prefault_mode) {
+	case CXL_PREFAULT_WED:
+		cxl_prefault_one(ctx, wed);
+		break;
+	case CXL_PREFAULT_ALL:
+		cxl_prefault_vma(ctx);
+		break;
+	default:
+		break;
+	}
+}
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
new file mode 100644
index 000000000000..378b099e7c0b
--- /dev/null
+++ b/drivers/misc/cxl/file.c
@@ -0,0 +1,518 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/bitmap.h>
+#include <linux/sched.h>
+#include <linux/poll.h>
+#include <linux/pid.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/cputable.h>
+#include <asm/current.h>
+#include <asm/copro.h>
+
+#include "cxl.h"
+
+#define CXL_NUM_MINORS 256 /* Total to reserve */
+#define CXL_DEV_MINORS 13   /* 1 control + 4 AFUs * 3 (dedicated/master/shared) */
+
+#define CXL_CARD_MINOR(adapter) (adapter->adapter_num * CXL_DEV_MINORS)
+#define CXL_AFU_MINOR_D(afu) (CXL_CARD_MINOR(afu->adapter) + 1 + (3 * afu->slice))
+#define CXL_AFU_MINOR_M(afu) (CXL_AFU_MINOR_D(afu) + 1)
+#define CXL_AFU_MINOR_S(afu) (CXL_AFU_MINOR_D(afu) + 2)
+#define CXL_AFU_MKDEV_D(afu) MKDEV(MAJOR(cxl_dev), CXL_AFU_MINOR_D(afu))
+#define CXL_AFU_MKDEV_M(afu) MKDEV(MAJOR(cxl_dev), CXL_AFU_MINOR_M(afu))
+#define CXL_AFU_MKDEV_S(afu) MKDEV(MAJOR(cxl_dev), CXL_AFU_MINOR_S(afu))
+
+#define CXL_DEVT_ADAPTER(dev) (MINOR(dev) / CXL_DEV_MINORS)
+#define CXL_DEVT_AFU(dev) ((MINOR(dev) % CXL_DEV_MINORS - 1) / 3)
+
+#define CXL_DEVT_IS_CARD(dev) (MINOR(dev) % CXL_DEV_MINORS == 0)
+
+static dev_t cxl_dev;
+
+static struct class *cxl_class;
+
+static int __afu_open(struct inode *inode, struct file *file, bool master)
+{
+	struct cxl *adapter;
+	struct cxl_afu *afu;
+	struct cxl_context *ctx;
+	int adapter_num = CXL_DEVT_ADAPTER(inode->i_rdev);
+	int slice = CXL_DEVT_AFU(inode->i_rdev);
+	int rc = -ENODEV;
+
+	pr_devel("afu_open afu%i.%i\n", slice, adapter_num);
+
+	if (!(adapter = get_cxl_adapter(adapter_num)))
+		return -ENODEV;
+
+	if (slice > adapter->slices)
+		goto err_put_adapter;
+
+	spin_lock(&adapter->afu_list_lock);
+	if (!(afu = adapter->afu[slice])) {
+		spin_unlock(&adapter->afu_list_lock);
+		goto err_put_adapter;
+	}
+	get_device(&afu->dev);
+	spin_unlock(&adapter->afu_list_lock);
+
+	if (!afu->current_mode)
+		goto err_put_afu;
+
+	if (!(ctx = cxl_context_alloc())) {
+		rc = -ENOMEM;
+		goto err_put_afu;
+	}
+
+	if ((rc = cxl_context_init(ctx, afu, master)))
+		goto err_put_afu;
+
+	pr_devel("afu_open pe: %i\n", ctx->pe);
+	file->private_data = ctx;
+	cxl_ctx_get();
+
+	/* Our ref on the AFU will now hold the adapter */
+	put_device(&adapter->dev);
+
+	return 0;
+
+err_put_afu:
+	put_device(&afu->dev);
+err_put_adapter:
+	put_device(&adapter->dev);
+	return rc;
+}
+static int afu_open(struct inode *inode, struct file *file)
+{
+	return __afu_open(inode, file, false);
+}
+
+static int afu_master_open(struct inode *inode, struct file *file)
+{
+	return __afu_open(inode, file, true);
+}
+
+static int afu_release(struct inode *inode, struct file *file)
+{
+	struct cxl_context *ctx = file->private_data;
+
+	pr_devel("%s: closing cxl file descriptor. pe: %i\n",
+		 __func__, ctx->pe);
+	cxl_context_detach(ctx);
+
+	put_device(&ctx->afu->dev);
+
+	/*
+	 * At this this point all bottom halfs have finished and we should be
+	 * getting no more IRQs from the hardware for this context.  Once it's
+	 * removed from the IDR (and RCU synchronised) it's safe to free the
+	 * sstp and context.
+	 */
+	cxl_context_free(ctx);
+
+	cxl_ctx_put();
+	return 0;
+}
+
+static long afu_ioctl_start_work(struct cxl_context *ctx,
+				 struct cxl_ioctl_start_work __user *uwork)
+{
+	struct cxl_ioctl_start_work work;
+	u64 amr = 0;
+	int rc;
+
+	pr_devel("%s: pe: %i\n", __func__, ctx->pe);
+
+	mutex_lock(&ctx->status_mutex);
+	if (ctx->status != OPENED) {
+		rc = -EIO;
+		goto out;
+	}
+
+	if (copy_from_user(&work, uwork,
+			   sizeof(struct cxl_ioctl_start_work))) {
+		rc = -EFAULT;
+		goto out;
+	}
+
+	/*
+	 * if any of the reserved fields are set or any of the unused
+	 * flags are set it's invalid
+	 */
+	if (work.reserved1 || work.reserved2 || work.reserved3 ||
+	    work.reserved4 || work.reserved5 || work.reserved6 ||
+	    (work.flags & ~CXL_START_WORK_ALL)) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	if (!(work.flags & CXL_START_WORK_NUM_IRQS))
+		work.num_interrupts = ctx->afu->pp_irqs;
+	else if ((work.num_interrupts < ctx->afu->pp_irqs) ||
+		 (work.num_interrupts > ctx->afu->irqs_max)) {
+		rc =  -EINVAL;
+		goto out;
+	}
+	if ((rc = afu_register_irqs(ctx, work.num_interrupts)))
+		goto out;
+
+	if (work.flags & CXL_START_WORK_AMR)
+		amr = work.amr & mfspr(SPRN_UAMOR);
+
+	/*
+	 * We grab the PID here and not in the file open to allow for the case
+	 * where a process (master, some daemon, etc) has opened the chardev on
+	 * behalf of another process, so the AFU's mm gets bound to the process
+	 * that performs this ioctl and not the process that opened the file.
+	 */
+	ctx->pid = get_pid(get_task_pid(current, PIDTYPE_PID));
+
+	if ((rc = cxl_attach_process(ctx, false, work.work_element_descriptor,
+				     amr)))
+		goto out;
+
+	ctx->status = STARTED;
+	rc = 0;
+out:
+	mutex_unlock(&ctx->status_mutex);
+	return rc;
+}
+static long afu_ioctl_process_element(struct cxl_context *ctx,
+				      int __user *upe)
+{
+	pr_devel("%s: pe: %i\n", __func__, ctx->pe);
+
+	if (copy_to_user(upe, &ctx->pe, sizeof(__u32)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct cxl_context *ctx = file->private_data;
+
+	if (ctx->status == CLOSED)
+		return -EIO;
+
+	pr_devel("afu_ioctl\n");
+	switch (cmd) {
+	case CXL_IOCTL_START_WORK:
+		return afu_ioctl_start_work(ctx, (struct cxl_ioctl_start_work __user *)arg);
+	case CXL_IOCTL_GET_PROCESS_ELEMENT:
+		return afu_ioctl_process_element(ctx, (__u32 __user *)arg);
+	}
+	return -EINVAL;
+}
+
+static long afu_compat_ioctl(struct file *file, unsigned int cmd,
+			     unsigned long arg)
+{
+	return afu_ioctl(file, cmd, arg);
+}
+
+static int afu_mmap(struct file *file, struct vm_area_struct *vm)
+{
+	struct cxl_context *ctx = file->private_data;
+
+	/* AFU must be started before we can MMIO */
+	if (ctx->status != STARTED)
+		return -EIO;
+
+	return cxl_context_iomap(ctx, vm);
+}
+
+static unsigned int afu_poll(struct file *file, struct poll_table_struct *poll)
+{
+	struct cxl_context *ctx = file->private_data;
+	int mask = 0;
+	unsigned long flags;
+
+
+	poll_wait(file, &ctx->wq, poll);
+
+	pr_devel("afu_poll wait done pe: %i\n", ctx->pe);
+
+	spin_lock_irqsave(&ctx->lock, flags);
+	if (ctx->pending_irq || ctx->pending_fault ||
+	    ctx->pending_afu_err)
+		mask |= POLLIN | POLLRDNORM;
+	else if (ctx->status == CLOSED)
+		/* Only error on closed when there are no futher events pending
+		 */
+		mask |= POLLERR;
+	spin_unlock_irqrestore(&ctx->lock, flags);
+
+	pr_devel("afu_poll pe: %i returning %#x\n", ctx->pe, mask);
+
+	return mask;
+}
+
+static inline int ctx_event_pending(struct cxl_context *ctx)
+{
+	return (ctx->pending_irq || ctx->pending_fault ||
+	    ctx->pending_afu_err || (ctx->status == CLOSED));
+}
+
+static ssize_t afu_read(struct file *file, char __user *buf, size_t count,
+			loff_t *off)
+{
+	struct cxl_context *ctx = file->private_data;
+	struct cxl_event event;
+	unsigned long flags;
+	int rc;
+	DEFINE_WAIT(wait);
+
+	if (count < CXL_READ_MIN_SIZE)
+		return -EINVAL;
+
+	spin_lock_irqsave(&ctx->lock, flags);
+
+	for (;;) {
+		prepare_to_wait(&ctx->wq, &wait, TASK_INTERRUPTIBLE);
+		if (ctx_event_pending(ctx))
+			break;
+
+		if (file->f_flags & O_NONBLOCK) {
+			rc = -EAGAIN;
+			goto out;
+		}
+
+		if (signal_pending(current)) {
+			rc = -ERESTARTSYS;
+			goto out;
+		}
+
+		spin_unlock_irqrestore(&ctx->lock, flags);
+		pr_devel("afu_read going to sleep...\n");
+		schedule();
+		pr_devel("afu_read woken up\n");
+		spin_lock_irqsave(&ctx->lock, flags);
+	}
+
+	finish_wait(&ctx->wq, &wait);
+
+	memset(&event, 0, sizeof(event));
+	event.header.process_element = ctx->pe;
+	event.header.size = sizeof(struct cxl_event_header);
+	if (ctx->pending_irq) {
+		pr_devel("afu_read delivering AFU interrupt\n");
+		event.header.size += sizeof(struct cxl_event_afu_interrupt);
+		event.header.type = CXL_EVENT_AFU_INTERRUPT;
+		event.irq.irq = find_first_bit(ctx->irq_bitmap, ctx->irq_count) + 1;
+		clear_bit(event.irq.irq - 1, ctx->irq_bitmap);
+		if (bitmap_empty(ctx->irq_bitmap, ctx->irq_count))
+			ctx->pending_irq = false;
+	} else if (ctx->pending_fault) {
+		pr_devel("afu_read delivering data storage fault\n");
+		event.header.size += sizeof(struct cxl_event_data_storage);
+		event.header.type = CXL_EVENT_DATA_STORAGE;
+		event.fault.addr = ctx->fault_addr;
+		event.fault.dsisr = ctx->fault_dsisr;
+		ctx->pending_fault = false;
+	} else if (ctx->pending_afu_err) {
+		pr_devel("afu_read delivering afu error\n");
+		event.header.size += sizeof(struct cxl_event_afu_error);
+		event.header.type = CXL_EVENT_AFU_ERROR;
+		event.afu_error.error = ctx->afu_err;
+		ctx->pending_afu_err = false;
+	} else if (ctx->status == CLOSED) {
+		pr_devel("afu_read fatal error\n");
+		spin_unlock_irqrestore(&ctx->lock, flags);
+		return -EIO;
+	} else
+		WARN(1, "afu_read must be buggy\n");
+
+	spin_unlock_irqrestore(&ctx->lock, flags);
+
+	if (copy_to_user(buf, &event, event.header.size))
+		return -EFAULT;
+	return event.header.size;
+
+out:
+	finish_wait(&ctx->wq, &wait);
+	spin_unlock_irqrestore(&ctx->lock, flags);
+	return rc;
+}
+
+static const struct file_operations afu_fops = {
+	.owner		= THIS_MODULE,
+	.open           = afu_open,
+	.poll		= afu_poll,
+	.read		= afu_read,
+	.release        = afu_release,
+	.unlocked_ioctl = afu_ioctl,
+	.compat_ioctl   = afu_compat_ioctl,
+	.mmap           = afu_mmap,
+};
+
+static const struct file_operations afu_master_fops = {
+	.owner		= THIS_MODULE,
+	.open           = afu_master_open,
+	.poll		= afu_poll,
+	.read		= afu_read,
+	.release        = afu_release,
+	.unlocked_ioctl = afu_ioctl,
+	.compat_ioctl   = afu_compat_ioctl,
+	.mmap           = afu_mmap,
+};
+
+
+static char *cxl_devnode(struct device *dev, umode_t *mode)
+{
+	if (CXL_DEVT_IS_CARD(dev->devt)) {
+		/*
+		 * These minor numbers will eventually be used to program the
+		 * PSL and AFUs once we have dynamic reprogramming support
+		 */
+		return NULL;
+	}
+	return kasprintf(GFP_KERNEL, "cxl/%s", dev_name(dev));
+}
+
+extern struct class *cxl_class;
+
+static int cxl_add_chardev(struct cxl_afu *afu, dev_t devt, struct cdev *cdev,
+			   struct device **chardev, char *postfix, char *desc,
+			   const struct file_operations *fops)
+{
+	struct device *dev;
+	int rc;
+
+	cdev_init(cdev, fops);
+	if ((rc = cdev_add(cdev, devt, 1))) {
+		dev_err(&afu->dev, "Unable to add %s chardev: %i\n", desc, rc);
+		return rc;
+	}
+
+	dev = device_create(cxl_class, &afu->dev, devt, afu,
+			"afu%i.%i%s", afu->adapter->adapter_num, afu->slice, postfix);
+	if (IS_ERR(dev)) {
+		dev_err(&afu->dev, "Unable to create %s chardev in sysfs: %i\n", desc, rc);
+		rc = PTR_ERR(dev);
+		goto err;
+	}
+
+	*chardev = dev;
+
+	return 0;
+err:
+	cdev_del(cdev);
+	return rc;
+}
+
+int cxl_chardev_d_afu_add(struct cxl_afu *afu)
+{
+	return cxl_add_chardev(afu, CXL_AFU_MKDEV_D(afu), &afu->afu_cdev_d,
+			       &afu->chardev_d, "d", "dedicated",
+			       &afu_master_fops); /* Uses master fops */
+}
+
+int cxl_chardev_m_afu_add(struct cxl_afu *afu)
+{
+	return cxl_add_chardev(afu, CXL_AFU_MKDEV_M(afu), &afu->afu_cdev_m,
+			       &afu->chardev_m, "m", "master",
+			       &afu_master_fops);
+}
+
+int cxl_chardev_s_afu_add(struct cxl_afu *afu)
+{
+	return cxl_add_chardev(afu, CXL_AFU_MKDEV_S(afu), &afu->afu_cdev_s,
+			       &afu->chardev_s, "s", "shared",
+			       &afu_fops);
+}
+
+void cxl_chardev_afu_remove(struct cxl_afu *afu)
+{
+	if (afu->chardev_d) {
+		cdev_del(&afu->afu_cdev_d);
+		device_unregister(afu->chardev_d);
+		afu->chardev_d = NULL;
+	}
+	if (afu->chardev_m) {
+		cdev_del(&afu->afu_cdev_m);
+		device_unregister(afu->chardev_m);
+		afu->chardev_m = NULL;
+	}
+	if (afu->chardev_s) {
+		cdev_del(&afu->afu_cdev_s);
+		device_unregister(afu->chardev_s);
+		afu->chardev_s = NULL;
+	}
+}
+
+int cxl_register_afu(struct cxl_afu *afu)
+{
+	afu->dev.class = cxl_class;
+
+	return device_register(&afu->dev);
+}
+
+int cxl_register_adapter(struct cxl *adapter)
+{
+	adapter->dev.class = cxl_class;
+
+	/*
+	 * Future: When we support dynamically reprogramming the PSL & AFU we
+	 * will expose the interface to do that via a chardev:
+	 * adapter->dev.devt = CXL_CARD_MKDEV(adapter);
+	 */
+
+	return device_register(&adapter->dev);
+}
+
+int __init cxl_file_init(void)
+{
+	int rc;
+
+	/*
+	 * If these change we really need to update API.  Either change some
+	 * flags or update API version number CXL_API_VERSION.
+	 */
+	BUILD_BUG_ON(CXL_API_VERSION != 1);
+	BUILD_BUG_ON(sizeof(struct cxl_ioctl_start_work) != 64);
+	BUILD_BUG_ON(sizeof(struct cxl_event_header) != 8);
+	BUILD_BUG_ON(sizeof(struct cxl_event_afu_interrupt) != 8);
+	BUILD_BUG_ON(sizeof(struct cxl_event_data_storage) != 32);
+	BUILD_BUG_ON(sizeof(struct cxl_event_afu_error) != 16);
+
+	if ((rc = alloc_chrdev_region(&cxl_dev, 0, CXL_NUM_MINORS, "cxl"))) {
+		pr_err("Unable to allocate CXL major number: %i\n", rc);
+		return rc;
+	}
+
+	pr_devel("CXL device allocated, MAJOR %i\n", MAJOR(cxl_dev));
+
+	cxl_class = class_create(THIS_MODULE, "cxl");
+	if (IS_ERR(cxl_class)) {
+		pr_err("Unable to create CXL class\n");
+		rc = PTR_ERR(cxl_class);
+		goto err;
+	}
+	cxl_class->devnode = cxl_devnode;
+
+	return 0;
+
+err:
+	unregister_chrdev_region(cxl_dev, CXL_NUM_MINORS);
+	return rc;
+}
+
+void cxl_file_exit(void)
+{
+	unregister_chrdev_region(cxl_dev, CXL_NUM_MINORS);
+	class_destroy(cxl_class);
+}
diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c
new file mode 100644
index 000000000000..336020c8e1af
--- /dev/null
+++ b/drivers/misc/cxl/irq.c
@@ -0,0 +1,402 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/slab.h>
+#include <linux/pid.h>
+#include <asm/cputable.h>
+#include <misc/cxl.h>
+
+#include "cxl.h"
+
+/* XXX: This is implementation specific */
+static irqreturn_t handle_psl_slice_error(struct cxl_context *ctx, u64 dsisr, u64 errstat)
+{
+	u64 fir1, fir2, fir_slice, serr, afu_debug;
+
+	fir1 = cxl_p1_read(ctx->afu->adapter, CXL_PSL_FIR1);
+	fir2 = cxl_p1_read(ctx->afu->adapter, CXL_PSL_FIR2);
+	fir_slice = cxl_p1n_read(ctx->afu, CXL_PSL_FIR_SLICE_An);
+	serr = cxl_p1n_read(ctx->afu, CXL_PSL_SERR_An);
+	afu_debug = cxl_p1n_read(ctx->afu, CXL_AFU_DEBUG_An);
+
+	dev_crit(&ctx->afu->dev, "PSL ERROR STATUS: 0x%.16llx\n", errstat);
+	dev_crit(&ctx->afu->dev, "PSL_FIR1: 0x%.16llx\n", fir1);
+	dev_crit(&ctx->afu->dev, "PSL_FIR2: 0x%.16llx\n", fir2);
+	dev_crit(&ctx->afu->dev, "PSL_SERR_An: 0x%.16llx\n", serr);
+	dev_crit(&ctx->afu->dev, "PSL_FIR_SLICE_An: 0x%.16llx\n", fir_slice);
+	dev_crit(&ctx->afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%.16llx\n", afu_debug);
+
+	dev_crit(&ctx->afu->dev, "STOPPING CXL TRACE\n");
+	cxl_stop_trace(ctx->afu->adapter);
+
+	return cxl_ack_irq(ctx, 0, errstat);
+}
+
+irqreturn_t cxl_slice_irq_err(int irq, void *data)
+{
+	struct cxl_afu *afu = data;
+	u64 fir_slice, errstat, serr, afu_debug;
+
+	WARN(irq, "CXL SLICE ERROR interrupt %i\n", irq);
+
+	serr = cxl_p1n_read(afu, CXL_PSL_SERR_An);
+	fir_slice = cxl_p1n_read(afu, CXL_PSL_FIR_SLICE_An);
+	errstat = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
+	afu_debug = cxl_p1n_read(afu, CXL_AFU_DEBUG_An);
+	dev_crit(&afu->dev, "PSL_SERR_An: 0x%.16llx\n", serr);
+	dev_crit(&afu->dev, "PSL_FIR_SLICE_An: 0x%.16llx\n", fir_slice);
+	dev_crit(&afu->dev, "CXL_PSL_ErrStat_An: 0x%.16llx\n", errstat);
+	dev_crit(&afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%.16llx\n", afu_debug);
+
+	cxl_p1n_write(afu, CXL_PSL_SERR_An, serr);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t cxl_irq_err(int irq, void *data)
+{
+	struct cxl *adapter = data;
+	u64 fir1, fir2, err_ivte;
+
+	WARN(1, "CXL ERROR interrupt %i\n", irq);
+
+	err_ivte = cxl_p1_read(adapter, CXL_PSL_ErrIVTE);
+	dev_crit(&adapter->dev, "PSL_ErrIVTE: 0x%.16llx\n", err_ivte);
+
+	dev_crit(&adapter->dev, "STOPPING CXL TRACE\n");
+	cxl_stop_trace(adapter);
+
+	fir1 = cxl_p1_read(adapter, CXL_PSL_FIR1);
+	fir2 = cxl_p1_read(adapter, CXL_PSL_FIR2);
+
+	dev_crit(&adapter->dev, "PSL_FIR1: 0x%.16llx\nPSL_FIR2: 0x%.16llx\n", fir1, fir2);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t schedule_cxl_fault(struct cxl_context *ctx, u64 dsisr, u64 dar)
+{
+	ctx->dsisr = dsisr;
+	ctx->dar = dar;
+	schedule_work(&ctx->fault_work);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t cxl_irq(int irq, void *data)
+{
+	struct cxl_context *ctx = data;
+	struct cxl_irq_info irq_info;
+	u64 dsisr, dar;
+	int result;
+
+	if ((result = cxl_get_irq(ctx, &irq_info))) {
+		WARN(1, "Unable to get CXL IRQ Info: %i\n", result);
+		return IRQ_HANDLED;
+	}
+
+	dsisr = irq_info.dsisr;
+	dar = irq_info.dar;
+
+	pr_devel("CXL interrupt %i for afu pe: %i DSISR: %#llx DAR: %#llx\n", irq, ctx->pe, dsisr, dar);
+
+	if (dsisr & CXL_PSL_DSISR_An_DS) {
+		/*
+		 * We don't inherently need to sleep to handle this, but we do
+		 * need to get a ref to the task's mm, which we can't do from
+		 * irq context without the potential for a deadlock since it
+		 * takes the task_lock. An alternate option would be to keep a
+		 * reference to the task's mm the entire time it has cxl open,
+		 * but to do that we need to solve the issue where we hold a
+		 * ref to the mm, but the mm can hold a ref to the fd after an
+		 * mmap preventing anything from being cleaned up.
+		 */
+		pr_devel("Scheduling segment miss handling for later pe: %i\n", ctx->pe);
+		return schedule_cxl_fault(ctx, dsisr, dar);
+	}
+
+	if (dsisr & CXL_PSL_DSISR_An_M)
+		pr_devel("CXL interrupt: PTE not found\n");
+	if (dsisr & CXL_PSL_DSISR_An_P)
+		pr_devel("CXL interrupt: Storage protection violation\n");
+	if (dsisr & CXL_PSL_DSISR_An_A)
+		pr_devel("CXL interrupt: AFU lock access to write through or cache inhibited storage\n");
+	if (dsisr & CXL_PSL_DSISR_An_S)
+		pr_devel("CXL interrupt: Access was afu_wr or afu_zero\n");
+	if (dsisr & CXL_PSL_DSISR_An_K)
+		pr_devel("CXL interrupt: Access not permitted by virtual page class key protection\n");
+
+	if (dsisr & CXL_PSL_DSISR_An_DM) {
+		/*
+		 * In some cases we might be able to handle the fault
+		 * immediately if hash_page would succeed, but we still need
+		 * the task's mm, which as above we can't get without a lock
+		 */
+		pr_devel("Scheduling page fault handling for later pe: %i\n", ctx->pe);
+		return schedule_cxl_fault(ctx, dsisr, dar);
+	}
+	if (dsisr & CXL_PSL_DSISR_An_ST)
+		WARN(1, "CXL interrupt: Segment Table PTE not found\n");
+	if (dsisr & CXL_PSL_DSISR_An_UR)
+		pr_devel("CXL interrupt: AURP PTE not found\n");
+	if (dsisr & CXL_PSL_DSISR_An_PE)
+		return handle_psl_slice_error(ctx, dsisr, irq_info.errstat);
+	if (dsisr & CXL_PSL_DSISR_An_AE) {
+		pr_devel("CXL interrupt: AFU Error %.llx\n", irq_info.afu_err);
+
+		if (ctx->pending_afu_err) {
+			/*
+			 * This shouldn't happen - the PSL treats these errors
+			 * as fatal and will have reset the AFU, so there's not
+			 * much point buffering multiple AFU errors.
+			 * OTOH if we DO ever see a storm of these come in it's
+			 * probably best that we log them somewhere:
+			 */
+			dev_err_ratelimited(&ctx->afu->dev, "CXL AFU Error "
+					    "undelivered to pe %i: %.llx\n",
+					    ctx->pe, irq_info.afu_err);
+		} else {
+			spin_lock(&ctx->lock);
+			ctx->afu_err = irq_info.afu_err;
+			ctx->pending_afu_err = 1;
+			spin_unlock(&ctx->lock);
+
+			wake_up_all(&ctx->wq);
+		}
+
+		cxl_ack_irq(ctx, CXL_PSL_TFC_An_A, 0);
+	}
+	if (dsisr & CXL_PSL_DSISR_An_OC)
+		pr_devel("CXL interrupt: OS Context Warning\n");
+
+	WARN(1, "Unhandled CXL PSL IRQ\n");
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t cxl_irq_multiplexed(int irq, void *data)
+{
+	struct cxl_afu *afu = data;
+	struct cxl_context *ctx;
+	int ph = cxl_p2n_read(afu, CXL_PSL_PEHandle_An) & 0xffff;
+	int ret;
+
+	rcu_read_lock();
+	ctx = idr_find(&afu->contexts_idr, ph);
+	if (ctx) {
+		ret = cxl_irq(irq, ctx);
+		rcu_read_unlock();
+		return ret;
+	}
+	rcu_read_unlock();
+
+	WARN(1, "Unable to demultiplex CXL PSL IRQ\n");
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t cxl_irq_afu(int irq, void *data)
+{
+	struct cxl_context *ctx = data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(irq_get_irq_data(irq));
+	int irq_off, afu_irq = 1;
+	__u16 range;
+	int r;
+
+	for (r = 1; r < CXL_IRQ_RANGES; r++) {
+		irq_off = hwirq - ctx->irqs.offset[r];
+		range = ctx->irqs.range[r];
+		if (irq_off >= 0 && irq_off < range) {
+			afu_irq += irq_off;
+			break;
+		}
+		afu_irq += range;
+	}
+	if (unlikely(r >= CXL_IRQ_RANGES)) {
+		WARN(1, "Recieved AFU IRQ out of range for pe %i (virq %i hwirq %lx)\n",
+		     ctx->pe, irq, hwirq);
+		return IRQ_HANDLED;
+	}
+
+	pr_devel("Received AFU interrupt %i for pe: %i (virq %i hwirq %lx)\n",
+	       afu_irq, ctx->pe, irq, hwirq);
+
+	if (unlikely(!ctx->irq_bitmap)) {
+		WARN(1, "Recieved AFU IRQ for context with no IRQ bitmap\n");
+		return IRQ_HANDLED;
+	}
+	spin_lock(&ctx->lock);
+	set_bit(afu_irq - 1, ctx->irq_bitmap);
+	ctx->pending_irq = true;
+	spin_unlock(&ctx->lock);
+
+	wake_up_all(&ctx->wq);
+
+	return IRQ_HANDLED;
+}
+
+unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq,
+			 irq_handler_t handler, void *cookie)
+{
+	unsigned int virq;
+	int result;
+
+	/* IRQ Domain? */
+	virq = irq_create_mapping(NULL, hwirq);
+	if (!virq) {
+		dev_warn(&adapter->dev, "cxl_map_irq: irq_create_mapping failed\n");
+		return 0;
+	}
+
+	cxl_setup_irq(adapter, hwirq, virq);
+
+	pr_devel("hwirq %#lx mapped to virq %u\n", hwirq, virq);
+
+	result = request_irq(virq, handler, 0, "cxl", cookie);
+	if (result) {
+		dev_warn(&adapter->dev, "cxl_map_irq: request_irq failed: %i\n", result);
+		return 0;
+	}
+
+	return virq;
+}
+
+void cxl_unmap_irq(unsigned int virq, void *cookie)
+{
+	free_irq(virq, cookie);
+	irq_dispose_mapping(virq);
+}
+
+static int cxl_register_one_irq(struct cxl *adapter,
+				irq_handler_t handler,
+				void *cookie,
+				irq_hw_number_t *dest_hwirq,
+				unsigned int *dest_virq)
+{
+	int hwirq, virq;
+
+	if ((hwirq = cxl_alloc_one_irq(adapter)) < 0)
+		return hwirq;
+
+	if (!(virq = cxl_map_irq(adapter, hwirq, handler, cookie)))
+		goto err;
+
+	*dest_hwirq = hwirq;
+	*dest_virq = virq;
+
+	return 0;
+
+err:
+	cxl_release_one_irq(adapter, hwirq);
+	return -ENOMEM;
+}
+
+int cxl_register_psl_err_irq(struct cxl *adapter)
+{
+	int rc;
+
+	if ((rc = cxl_register_one_irq(adapter, cxl_irq_err, adapter,
+				       &adapter->err_hwirq,
+				       &adapter->err_virq)))
+		return rc;
+
+	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, adapter->err_hwirq & 0xffff);
+
+	return 0;
+}
+
+void cxl_release_psl_err_irq(struct cxl *adapter)
+{
+	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
+	cxl_unmap_irq(adapter->err_virq, adapter);
+	cxl_release_one_irq(adapter, adapter->err_hwirq);
+}
+
+int cxl_register_serr_irq(struct cxl_afu *afu)
+{
+	u64 serr;
+	int rc;
+
+	if ((rc = cxl_register_one_irq(afu->adapter, cxl_slice_irq_err, afu,
+				       &afu->serr_hwirq,
+				       &afu->serr_virq)))
+		return rc;
+
+	serr = cxl_p1n_read(afu, CXL_PSL_SERR_An);
+	serr = (serr & 0x00ffffffffff0000ULL) | (afu->serr_hwirq & 0xffff);
+	cxl_p1n_write(afu, CXL_PSL_SERR_An, serr);
+
+	return 0;
+}
+
+void cxl_release_serr_irq(struct cxl_afu *afu)
+{
+	cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000);
+	cxl_unmap_irq(afu->serr_virq, afu);
+	cxl_release_one_irq(afu->adapter, afu->serr_hwirq);
+}
+
+int cxl_register_psl_irq(struct cxl_afu *afu)
+{
+	return cxl_register_one_irq(afu->adapter, cxl_irq_multiplexed, afu,
+			&afu->psl_hwirq, &afu->psl_virq);
+}
+
+void cxl_release_psl_irq(struct cxl_afu *afu)
+{
+	cxl_unmap_irq(afu->psl_virq, afu);
+	cxl_release_one_irq(afu->adapter, afu->psl_hwirq);
+}
+
+int afu_register_irqs(struct cxl_context *ctx, u32 count)
+{
+	irq_hw_number_t hwirq;
+	int rc, r, i;
+
+	if ((rc = cxl_alloc_irq_ranges(&ctx->irqs, ctx->afu->adapter, count)))
+		return rc;
+
+	/* Multiplexed PSL Interrupt */
+	ctx->irqs.offset[0] = ctx->afu->psl_hwirq;
+	ctx->irqs.range[0] = 1;
+
+	ctx->irq_count = count;
+	ctx->irq_bitmap = kcalloc(BITS_TO_LONGS(count),
+				  sizeof(*ctx->irq_bitmap), GFP_KERNEL);
+	if (!ctx->irq_bitmap)
+		return -ENOMEM;
+	for (r = 1; r < CXL_IRQ_RANGES; r++) {
+		hwirq = ctx->irqs.offset[r];
+		for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) {
+			cxl_map_irq(ctx->afu->adapter, hwirq,
+				     cxl_irq_afu, ctx);
+		}
+	}
+
+	return 0;
+}
+
+void afu_release_irqs(struct cxl_context *ctx)
+{
+	irq_hw_number_t hwirq;
+	unsigned int virq;
+	int r, i;
+
+	for (r = 1; r < CXL_IRQ_RANGES; r++) {
+		hwirq = ctx->irqs.offset[r];
+		for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) {
+			virq = irq_find_mapping(NULL, hwirq);
+			if (virq)
+				cxl_unmap_irq(virq, ctx);
+		}
+	}
+
+	cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
+}
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
new file mode 100644
index 000000000000..4cde9b661642
--- /dev/null
+++ b/drivers/misc/cxl/main.c
@@ -0,0 +1,230 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/idr.h>
+#include <linux/pci.h>
+#include <asm/cputable.h>
+#include <misc/cxl.h>
+
+#include "cxl.h"
+
+static DEFINE_SPINLOCK(adapter_idr_lock);
+static DEFINE_IDR(cxl_adapter_idr);
+
+uint cxl_verbose;
+module_param_named(verbose, cxl_verbose, uint, 0600);
+MODULE_PARM_DESC(verbose, "Enable verbose dmesg output");
+
+static inline void _cxl_slbia(struct cxl_context *ctx, struct mm_struct *mm)
+{
+	struct task_struct *task;
+	unsigned long flags;
+	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
+		pr_devel("%s unable to get task %i\n",
+			 __func__, pid_nr(ctx->pid));
+		return;
+	}
+
+	if (task->mm != mm)
+		goto out_put;
+
+	pr_devel("%s matched mm - card: %i afu: %i pe: %i\n", __func__,
+		 ctx->afu->adapter->adapter_num, ctx->afu->slice, ctx->pe);
+
+	spin_lock_irqsave(&ctx->sste_lock, flags);
+	memset(ctx->sstp, 0, ctx->sst_size);
+	spin_unlock_irqrestore(&ctx->sste_lock, flags);
+	mb();
+	cxl_afu_slbia(ctx->afu);
+out_put:
+	put_task_struct(task);
+}
+
+static inline void cxl_slbia_core(struct mm_struct *mm)
+{
+	struct cxl *adapter;
+	struct cxl_afu *afu;
+	struct cxl_context *ctx;
+	int card, slice, id;
+
+	pr_devel("%s called\n", __func__);
+
+	spin_lock(&adapter_idr_lock);
+	idr_for_each_entry(&cxl_adapter_idr, adapter, card) {
+		/* XXX: Make this lookup faster with link from mm to ctx */
+		spin_lock(&adapter->afu_list_lock);
+		for (slice = 0; slice < adapter->slices; slice++) {
+			afu = adapter->afu[slice];
+			if (!afu->enabled)
+				continue;
+			rcu_read_lock();
+			idr_for_each_entry(&afu->contexts_idr, ctx, id)
+				_cxl_slbia(ctx, mm);
+			rcu_read_unlock();
+		}
+		spin_unlock(&adapter->afu_list_lock);
+	}
+	spin_unlock(&adapter_idr_lock);
+}
+
+static struct cxl_calls cxl_calls = {
+	.cxl_slbia = cxl_slbia_core,
+	.owner = THIS_MODULE,
+};
+
+int cxl_alloc_sst(struct cxl_context *ctx)
+{
+	unsigned long vsid;
+	u64 ea_mask, size, sstp0, sstp1;
+
+	sstp0 = 0;
+	sstp1 = 0;
+
+	ctx->sst_size = PAGE_SIZE;
+	ctx->sst_lru = 0;
+	ctx->sstp = (struct cxl_sste *)get_zeroed_page(GFP_KERNEL);
+	if (!ctx->sstp) {
+		pr_err("cxl_alloc_sst: Unable to allocate segment table\n");
+		return -ENOMEM;
+	}
+	pr_devel("SSTP allocated at 0x%p\n", ctx->sstp);
+
+	vsid  = get_kernel_vsid((u64)ctx->sstp, mmu_kernel_ssize) << 12;
+
+	sstp0 |= (u64)mmu_kernel_ssize << CXL_SSTP0_An_B_SHIFT;
+	sstp0 |= (SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp) << 50;
+
+	size = (((u64)ctx->sst_size >> 8) - 1) << CXL_SSTP0_An_SegTableSize_SHIFT;
+	if (unlikely(size & ~CXL_SSTP0_An_SegTableSize_MASK)) {
+		WARN(1, "Impossible segment table size\n");
+		return -EINVAL;
+	}
+	sstp0 |= size;
+
+	if (mmu_kernel_ssize == MMU_SEGSIZE_256M)
+		ea_mask = 0xfffff00ULL;
+	else
+		ea_mask = 0xffffffff00ULL;
+
+	sstp0 |=  vsid >>     (50-14);  /*   Top 14 bits of VSID */
+	sstp1 |= (vsid << (64-(50-14))) & ~ea_mask;
+	sstp1 |= (u64)ctx->sstp & ea_mask;
+	sstp1 |= CXL_SSTP1_An_V;
+
+	pr_devel("Looked up %#llx: slbfee. %#llx (ssize: %x, vsid: %#lx), copied to SSTP0: %#llx, SSTP1: %#llx\n",
+			(u64)ctx->sstp, (u64)ctx->sstp & ESID_MASK, mmu_kernel_ssize, vsid, sstp0, sstp1);
+
+	/* Store calculated sstp hardware points for use later */
+	ctx->sstp0 = sstp0;
+	ctx->sstp1 = sstp1;
+
+	return 0;
+}
+
+/* Find a CXL adapter by it's number and increase it's refcount */
+struct cxl *get_cxl_adapter(int num)
+{
+	struct cxl *adapter;
+
+	spin_lock(&adapter_idr_lock);
+	if ((adapter = idr_find(&cxl_adapter_idr, num)))
+		get_device(&adapter->dev);
+	spin_unlock(&adapter_idr_lock);
+
+	return adapter;
+}
+
+int cxl_alloc_adapter_nr(struct cxl *adapter)
+{
+	int i;
+
+	idr_preload(GFP_KERNEL);
+	spin_lock(&adapter_idr_lock);
+	i = idr_alloc(&cxl_adapter_idr, adapter, 0, 0, GFP_NOWAIT);
+	spin_unlock(&adapter_idr_lock);
+	idr_preload_end();
+	if (i < 0)
+		return i;
+
+	adapter->adapter_num = i;
+
+	return 0;
+}
+
+void cxl_remove_adapter_nr(struct cxl *adapter)
+{
+	idr_remove(&cxl_adapter_idr, adapter->adapter_num);
+}
+
+int cxl_afu_select_best_mode(struct cxl_afu *afu)
+{
+	if (afu->modes_supported & CXL_MODE_DIRECTED)
+		return cxl_afu_activate_mode(afu, CXL_MODE_DIRECTED);
+
+	if (afu->modes_supported & CXL_MODE_DEDICATED)
+		return cxl_afu_activate_mode(afu, CXL_MODE_DEDICATED);
+
+	dev_warn(&afu->dev, "No supported programming modes available\n");
+	/* We don't fail this so the user can inspect sysfs */
+	return 0;
+}
+
+static int __init init_cxl(void)
+{
+	int rc = 0;
+
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
+		return -EPERM;
+
+	if ((rc = cxl_file_init()))
+		return rc;
+
+	cxl_debugfs_init();
+
+	if ((rc = register_cxl_calls(&cxl_calls)))
+		goto err;
+
+	if ((rc = pci_register_driver(&cxl_pci_driver)))
+		goto err1;
+
+	return 0;
+err1:
+	unregister_cxl_calls(&cxl_calls);
+err:
+	cxl_debugfs_exit();
+	cxl_file_exit();
+
+	return rc;
+}
+
+static void exit_cxl(void)
+{
+	pci_unregister_driver(&cxl_pci_driver);
+
+	cxl_debugfs_exit();
+	cxl_file_exit();
+	unregister_cxl_calls(&cxl_calls);
+}
+
+module_init(init_cxl);
+module_exit(exit_cxl);
+
+MODULE_DESCRIPTION("IBM Coherent Accelerator");
+MODULE_AUTHOR("Ian Munsie <imunsie@au1.ibm.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
new file mode 100644
index 000000000000..623286a77114
--- /dev/null
+++ b/drivers/misc/cxl/native.c
@@ -0,0 +1,683 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/mutex.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <asm/synch.h>
+#include <misc/cxl.h>
+
+#include "cxl.h"
+
+static int afu_control(struct cxl_afu *afu, u64 command,
+		       u64 result, u64 mask, bool enabled)
+{
+	u64 AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+	unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT);
+
+	spin_lock(&afu->afu_cntl_lock);
+	pr_devel("AFU command starting: %llx\n", command);
+
+	cxl_p2n_write(afu, CXL_AFU_Cntl_An, AFU_Cntl | command);
+
+	AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+	while ((AFU_Cntl & mask) != result) {
+		if (time_after_eq(jiffies, timeout)) {
+			dev_warn(&afu->dev, "WARNING: AFU control timed out!\n");
+			spin_unlock(&afu->afu_cntl_lock);
+			return -EBUSY;
+		}
+		pr_devel_ratelimited("AFU control... (0x%.16llx)\n",
+				     AFU_Cntl | command);
+		cpu_relax();
+		AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+	};
+	pr_devel("AFU command complete: %llx\n", command);
+	afu->enabled = enabled;
+	spin_unlock(&afu->afu_cntl_lock);
+
+	return 0;
+}
+
+static int afu_enable(struct cxl_afu *afu)
+{
+	pr_devel("AFU enable request\n");
+
+	return afu_control(afu, CXL_AFU_Cntl_An_E,
+			   CXL_AFU_Cntl_An_ES_Enabled,
+			   CXL_AFU_Cntl_An_ES_MASK, true);
+}
+
+int cxl_afu_disable(struct cxl_afu *afu)
+{
+	pr_devel("AFU disable request\n");
+
+	return afu_control(afu, 0, CXL_AFU_Cntl_An_ES_Disabled,
+			   CXL_AFU_Cntl_An_ES_MASK, false);
+}
+
+/* This will disable as well as reset */
+int cxl_afu_reset(struct cxl_afu *afu)
+{
+	pr_devel("AFU reset request\n");
+
+	return afu_control(afu, CXL_AFU_Cntl_An_RA,
+			   CXL_AFU_Cntl_An_RS_Complete | CXL_AFU_Cntl_An_ES_Disabled,
+			   CXL_AFU_Cntl_An_RS_MASK | CXL_AFU_Cntl_An_ES_MASK,
+			   false);
+}
+
+static int afu_check_and_enable(struct cxl_afu *afu)
+{
+	if (afu->enabled)
+		return 0;
+	return afu_enable(afu);
+}
+
+int cxl_psl_purge(struct cxl_afu *afu)
+{
+	u64 PSL_CNTL = cxl_p1n_read(afu, CXL_PSL_SCNTL_An);
+	u64 AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+	u64 dsisr, dar;
+	u64 start, end;
+	unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT);
+
+	pr_devel("PSL purge request\n");
+
+	if ((AFU_Cntl & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) {
+		WARN(1, "psl_purge request while AFU not disabled!\n");
+		cxl_afu_disable(afu);
+	}
+
+	cxl_p1n_write(afu, CXL_PSL_SCNTL_An,
+		       PSL_CNTL | CXL_PSL_SCNTL_An_Pc);
+	start = local_clock();
+	PSL_CNTL = cxl_p1n_read(afu, CXL_PSL_SCNTL_An);
+	while ((PSL_CNTL &  CXL_PSL_SCNTL_An_Ps_MASK)
+			== CXL_PSL_SCNTL_An_Ps_Pending) {
+		if (time_after_eq(jiffies, timeout)) {
+			dev_warn(&afu->dev, "WARNING: PSL Purge timed out!\n");
+			return -EBUSY;
+		}
+		dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
+		pr_devel_ratelimited("PSL purging... PSL_CNTL: 0x%.16llx  PSL_DSISR: 0x%.16llx\n", PSL_CNTL, dsisr);
+		if (dsisr & CXL_PSL_DSISR_TRANS) {
+			dar = cxl_p2n_read(afu, CXL_PSL_DAR_An);
+			dev_notice(&afu->dev, "PSL purge terminating pending translation, DSISR: 0x%.16llx, DAR: 0x%.16llx\n", dsisr, dar);
+			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE);
+		} else if (dsisr) {
+			dev_notice(&afu->dev, "PSL purge acknowledging pending non-translation fault, DSISR: 0x%.16llx\n", dsisr);
+			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A);
+		} else {
+			cpu_relax();
+		}
+		PSL_CNTL = cxl_p1n_read(afu, CXL_PSL_SCNTL_An);
+	};
+	end = local_clock();
+	pr_devel("PSL purged in %lld ns\n", end - start);
+
+	cxl_p1n_write(afu, CXL_PSL_SCNTL_An,
+		       PSL_CNTL & ~CXL_PSL_SCNTL_An_Pc);
+	return 0;
+}
+
+static int spa_max_procs(int spa_size)
+{
+	/*
+	 * From the CAIA:
+	 *    end_of_SPA_area = SPA_Base + ((n+4) * 128) + (( ((n*8) + 127) >> 7) * 128) + 255
+	 * Most of that junk is really just an overly-complicated way of saying
+	 * the last 256 bytes are __aligned(128), so it's really:
+	 *    end_of_SPA_area = end_of_PSL_queue_area + __aligned(128) 255
+	 * and
+	 *    end_of_PSL_queue_area = SPA_Base + ((n+4) * 128) + (n*8) - 1
+	 * so
+	 *    sizeof(SPA) = ((n+4) * 128) + (n*8) + __aligned(128) 256
+	 * Ignore the alignment (which is safe in this case as long as we are
+	 * careful with our rounding) and solve for n:
+	 */
+	return ((spa_size / 8) - 96) / 17;
+}
+
+static int alloc_spa(struct cxl_afu *afu)
+{
+	u64 spap;
+
+	/* Work out how many pages to allocate */
+	afu->spa_order = 0;
+	do {
+		afu->spa_order++;
+		afu->spa_size = (1 << afu->spa_order) * PAGE_SIZE;
+		afu->spa_max_procs = spa_max_procs(afu->spa_size);
+	} while (afu->spa_max_procs < afu->num_procs);
+
+	WARN_ON(afu->spa_size > 0x100000); /* Max size supported by the hardware */
+
+	if (!(afu->spa = (struct cxl_process_element *)
+	      __get_free_pages(GFP_KERNEL | __GFP_ZERO, afu->spa_order))) {
+		pr_err("cxl_alloc_spa: Unable to allocate scheduled process area\n");
+		return -ENOMEM;
+	}
+	pr_devel("spa pages: %i afu->spa_max_procs: %i   afu->num_procs: %i\n",
+		 1<<afu->spa_order, afu->spa_max_procs, afu->num_procs);
+
+	afu->sw_command_status = (__be64 *)((char *)afu->spa +
+					    ((afu->spa_max_procs + 3) * 128));
+
+	spap = virt_to_phys(afu->spa) & CXL_PSL_SPAP_Addr;
+	spap |= ((afu->spa_size >> (12 - CXL_PSL_SPAP_Size_Shift)) - 1) & CXL_PSL_SPAP_Size;
+	spap |= CXL_PSL_SPAP_V;
+	pr_devel("cxl: SPA allocated at 0x%p. Max processes: %i, sw_command_status: 0x%p CXL_PSL_SPAP_An=0x%016llx\n", afu->spa, afu->spa_max_procs, afu->sw_command_status, spap);
+	cxl_p1n_write(afu, CXL_PSL_SPAP_An, spap);
+
+	return 0;
+}
+
+static void release_spa(struct cxl_afu *afu)
+{
+	free_pages((unsigned long) afu->spa, afu->spa_order);
+}
+
+int cxl_tlb_slb_invalidate(struct cxl *adapter)
+{
+	unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT);
+
+	pr_devel("CXL adapter wide TLBIA & SLBIA\n");
+
+	cxl_p1_write(adapter, CXL_PSL_AFUSEL, CXL_PSL_AFUSEL_A);
+
+	cxl_p1_write(adapter, CXL_PSL_TLBIA, CXL_TLB_SLB_IQ_ALL);
+	while (cxl_p1_read(adapter, CXL_PSL_TLBIA) & CXL_TLB_SLB_P) {
+		if (time_after_eq(jiffies, timeout)) {
+			dev_warn(&adapter->dev, "WARNING: CXL adapter wide TLBIA timed out!\n");
+			return -EBUSY;
+		}
+		cpu_relax();
+	}
+
+	cxl_p1_write(adapter, CXL_PSL_SLBIA, CXL_TLB_SLB_IQ_ALL);
+	while (cxl_p1_read(adapter, CXL_PSL_SLBIA) & CXL_TLB_SLB_P) {
+		if (time_after_eq(jiffies, timeout)) {
+			dev_warn(&adapter->dev, "WARNING: CXL adapter wide SLBIA timed out!\n");
+			return -EBUSY;
+		}
+		cpu_relax();
+	}
+	return 0;
+}
+
+int cxl_afu_slbia(struct cxl_afu *afu)
+{
+	unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT);
+
+	pr_devel("cxl_afu_slbia issuing SLBIA command\n");
+	cxl_p2n_write(afu, CXL_SLBIA_An, CXL_TLB_SLB_IQ_ALL);
+	while (cxl_p2n_read(afu, CXL_SLBIA_An) & CXL_TLB_SLB_P) {
+		if (time_after_eq(jiffies, timeout)) {
+			dev_warn(&afu->dev, "WARNING: CXL AFU SLBIA timed out!\n");
+			return -EBUSY;
+		}
+		cpu_relax();
+	}
+	return 0;
+}
+
+static int cxl_write_sstp(struct cxl_afu *afu, u64 sstp0, u64 sstp1)
+{
+	int rc;
+
+	/* 1. Disable SSTP by writing 0 to SSTP1[V] */
+	cxl_p2n_write(afu, CXL_SSTP1_An, 0);
+
+	/* 2. Invalidate all SLB entries */
+	if ((rc = cxl_afu_slbia(afu)))
+		return rc;
+
+	/* 3. Set SSTP0_An */
+	cxl_p2n_write(afu, CXL_SSTP0_An, sstp0);
+
+	/* 4. Set SSTP1_An */
+	cxl_p2n_write(afu, CXL_SSTP1_An, sstp1);
+
+	return 0;
+}
+
+/* Using per slice version may improve performance here. (ie. SLBIA_An) */
+static void slb_invalid(struct cxl_context *ctx)
+{
+	struct cxl *adapter = ctx->afu->adapter;
+	u64 slbia;
+
+	WARN_ON(!mutex_is_locked(&ctx->afu->spa_mutex));
+
+	cxl_p1_write(adapter, CXL_PSL_LBISEL,
+			((u64)be32_to_cpu(ctx->elem->common.pid) << 32) |
+			be32_to_cpu(ctx->elem->lpid));
+	cxl_p1_write(adapter, CXL_PSL_SLBIA, CXL_TLB_SLB_IQ_LPIDPID);
+
+	while (1) {
+		slbia = cxl_p1_read(adapter, CXL_PSL_SLBIA);
+		if (!(slbia & CXL_TLB_SLB_P))
+			break;
+		cpu_relax();
+	}
+}
+
+static int do_process_element_cmd(struct cxl_context *ctx,
+				  u64 cmd, u64 pe_state)
+{
+	u64 state;
+
+	WARN_ON(!ctx->afu->enabled);
+
+	ctx->elem->software_state = cpu_to_be32(pe_state);
+	smp_wmb();
+	*(ctx->afu->sw_command_status) = cpu_to_be64(cmd | 0 | ctx->pe);
+	smp_mb();
+	cxl_p1n_write(ctx->afu, CXL_PSL_LLCMD_An, cmd | ctx->pe);
+	while (1) {
+		state = be64_to_cpup(ctx->afu->sw_command_status);
+		if (state == ~0ULL) {
+			pr_err("cxl: Error adding process element to AFU\n");
+			return -1;
+		}
+		if ((state & (CXL_SPA_SW_CMD_MASK | CXL_SPA_SW_STATE_MASK  | CXL_SPA_SW_LINK_MASK)) ==
+		    (cmd | (cmd >> 16) | ctx->pe))
+			break;
+		/*
+		 * The command won't finish in the PSL if there are
+		 * outstanding DSIs.  Hence we need to yield here in
+		 * case there are outstanding DSIs that we need to
+		 * service.  Tuning possiblity: we could wait for a
+		 * while before sched
+		 */
+		schedule();
+
+	}
+	return 0;
+}
+
+static int add_process_element(struct cxl_context *ctx)
+{
+	int rc = 0;
+
+	mutex_lock(&ctx->afu->spa_mutex);
+	pr_devel("%s Adding pe: %i started\n", __func__, ctx->pe);
+	if (!(rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_ADD, CXL_PE_SOFTWARE_STATE_V)))
+		ctx->pe_inserted = true;
+	pr_devel("%s Adding pe: %i finished\n", __func__, ctx->pe);
+	mutex_unlock(&ctx->afu->spa_mutex);
+	return rc;
+}
+
+static int terminate_process_element(struct cxl_context *ctx)
+{
+	int rc = 0;
+
+	/* fast path terminate if it's already invalid */
+	if (!(ctx->elem->software_state & cpu_to_be32(CXL_PE_SOFTWARE_STATE_V)))
+		return rc;
+
+	mutex_lock(&ctx->afu->spa_mutex);
+	pr_devel("%s Terminate pe: %i started\n", __func__, ctx->pe);
+	rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_TERMINATE,
+				    CXL_PE_SOFTWARE_STATE_V | CXL_PE_SOFTWARE_STATE_T);
+	ctx->elem->software_state = 0;	/* Remove Valid bit */
+	pr_devel("%s Terminate pe: %i finished\n", __func__, ctx->pe);
+	mutex_unlock(&ctx->afu->spa_mutex);
+	return rc;
+}
+
+static int remove_process_element(struct cxl_context *ctx)
+{
+	int rc = 0;
+
+	mutex_lock(&ctx->afu->spa_mutex);
+	pr_devel("%s Remove pe: %i started\n", __func__, ctx->pe);
+	if (!(rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_REMOVE, 0)))
+		ctx->pe_inserted = false;
+	slb_invalid(ctx);
+	pr_devel("%s Remove pe: %i finished\n", __func__, ctx->pe);
+	mutex_unlock(&ctx->afu->spa_mutex);
+
+	return rc;
+}
+
+
+static void assign_psn_space(struct cxl_context *ctx)
+{
+	if (!ctx->afu->pp_size || ctx->master) {
+		ctx->psn_phys = ctx->afu->psn_phys;
+		ctx->psn_size = ctx->afu->adapter->ps_size;
+	} else {
+		ctx->psn_phys = ctx->afu->psn_phys +
+			(ctx->afu->pp_offset + ctx->afu->pp_size * ctx->pe);
+		ctx->psn_size = ctx->afu->pp_size;
+	}
+}
+
+static int activate_afu_directed(struct cxl_afu *afu)
+{
+	int rc;
+
+	dev_info(&afu->dev, "Activating AFU directed mode\n");
+
+	if (alloc_spa(afu))
+		return -ENOMEM;
+
+	cxl_p1n_write(afu, CXL_PSL_SCNTL_An, CXL_PSL_SCNTL_An_PM_AFU);
+	cxl_p1n_write(afu, CXL_PSL_AMOR_An, 0xFFFFFFFFFFFFFFFFULL);
+	cxl_p1n_write(afu, CXL_PSL_ID_An, CXL_PSL_ID_An_F | CXL_PSL_ID_An_L);
+
+	afu->current_mode = CXL_MODE_DIRECTED;
+	afu->num_procs = afu->max_procs_virtualised;
+
+	if ((rc = cxl_chardev_m_afu_add(afu)))
+		return rc;
+
+	if ((rc = cxl_sysfs_afu_m_add(afu)))
+		goto err;
+
+	if ((rc = cxl_chardev_s_afu_add(afu)))
+		goto err1;
+
+	return 0;
+err1:
+	cxl_sysfs_afu_m_remove(afu);
+err:
+	cxl_chardev_afu_remove(afu);
+	return rc;
+}
+
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define set_endian(sr) ((sr) |= CXL_PSL_SR_An_LE)
+#else
+#define set_endian(sr) ((sr) &= ~(CXL_PSL_SR_An_LE))
+#endif
+
+static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
+{
+	u64 sr;
+	int r, result;
+
+	assign_psn_space(ctx);
+
+	ctx->elem->ctxtime = 0; /* disable */
+	ctx->elem->lpid = cpu_to_be32(mfspr(SPRN_LPID));
+	ctx->elem->haurp = 0; /* disable */
+	ctx->elem->sdr = cpu_to_be64(mfspr(SPRN_SDR1));
+
+	sr = CXL_PSL_SR_An_SC;
+	if (ctx->master)
+		sr |= CXL_PSL_SR_An_MP;
+	if (mfspr(SPRN_LPCR) & LPCR_TC)
+		sr |= CXL_PSL_SR_An_TC;
+	/* HV=0, PR=1, R=1 for userspace
+	 * For kernel contexts: this would need to change
+	 */
+	sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
+	set_endian(sr);
+	sr &= ~(CXL_PSL_SR_An_HV);
+	if (!test_tsk_thread_flag(current, TIF_32BIT))
+		sr |= CXL_PSL_SR_An_SF;
+	ctx->elem->common.pid = cpu_to_be32(current->pid);
+	ctx->elem->common.tid = 0;
+	ctx->elem->sr = cpu_to_be64(sr);
+
+	ctx->elem->common.csrp = 0; /* disable */
+	ctx->elem->common.aurp0 = 0; /* disable */
+	ctx->elem->common.aurp1 = 0; /* disable */
+
+	cxl_prefault(ctx, wed);
+
+	ctx->elem->common.sstp0 = cpu_to_be64(ctx->sstp0);
+	ctx->elem->common.sstp1 = cpu_to_be64(ctx->sstp1);
+
+	for (r = 0; r < CXL_IRQ_RANGES; r++) {
+		ctx->elem->ivte_offsets[r] = cpu_to_be16(ctx->irqs.offset[r]);
+		ctx->elem->ivte_ranges[r] = cpu_to_be16(ctx->irqs.range[r]);
+	}
+
+	ctx->elem->common.amr = cpu_to_be64(amr);
+	ctx->elem->common.wed = cpu_to_be64(wed);
+
+	/* first guy needs to enable */
+	if ((result = afu_check_and_enable(ctx->afu)))
+		return result;
+
+	add_process_element(ctx);
+
+	return 0;
+}
+
+static int deactivate_afu_directed(struct cxl_afu *afu)
+{
+	dev_info(&afu->dev, "Deactivating AFU directed mode\n");
+
+	afu->current_mode = 0;
+	afu->num_procs = 0;
+
+	cxl_sysfs_afu_m_remove(afu);
+	cxl_chardev_afu_remove(afu);
+
+	cxl_afu_reset(afu);
+	cxl_afu_disable(afu);
+	cxl_psl_purge(afu);
+
+	release_spa(afu);
+
+	return 0;
+}
+
+static int activate_dedicated_process(struct cxl_afu *afu)
+{
+	dev_info(&afu->dev, "Activating dedicated process mode\n");
+
+	cxl_p1n_write(afu, CXL_PSL_SCNTL_An, CXL_PSL_SCNTL_An_PM_Process);
+
+	cxl_p1n_write(afu, CXL_PSL_CtxTime_An, 0); /* disable */
+	cxl_p1n_write(afu, CXL_PSL_SPAP_An, 0);    /* disable */
+	cxl_p1n_write(afu, CXL_PSL_AMOR_An, 0xFFFFFFFFFFFFFFFFULL);
+	cxl_p1n_write(afu, CXL_PSL_LPID_An, mfspr(SPRN_LPID));
+	cxl_p1n_write(afu, CXL_HAURP_An, 0);       /* disable */
+	cxl_p1n_write(afu, CXL_PSL_SDR_An, mfspr(SPRN_SDR1));
+
+	cxl_p2n_write(afu, CXL_CSRP_An, 0);        /* disable */
+	cxl_p2n_write(afu, CXL_AURP0_An, 0);       /* disable */
+	cxl_p2n_write(afu, CXL_AURP1_An, 0);       /* disable */
+
+	afu->current_mode = CXL_MODE_DEDICATED;
+	afu->num_procs = 1;
+
+	return cxl_chardev_d_afu_add(afu);
+}
+
+static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr)
+{
+	struct cxl_afu *afu = ctx->afu;
+	u64 sr;
+	int rc;
+
+	sr = CXL_PSL_SR_An_SC;
+	set_endian(sr);
+	if (ctx->master)
+		sr |= CXL_PSL_SR_An_MP;
+	if (mfspr(SPRN_LPCR) & LPCR_TC)
+		sr |= CXL_PSL_SR_An_TC;
+	sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
+	if (!test_tsk_thread_flag(current, TIF_32BIT))
+		sr |= CXL_PSL_SR_An_SF;
+	cxl_p2n_write(afu, CXL_PSL_PID_TID_An, (u64)current->pid << 32);
+	cxl_p1n_write(afu, CXL_PSL_SR_An, sr);
+
+	if ((rc = cxl_write_sstp(afu, ctx->sstp0, ctx->sstp1)))
+		return rc;
+
+	cxl_prefault(ctx, wed);
+
+	cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An,
+		       (((u64)ctx->irqs.offset[0] & 0xffff) << 48) |
+		       (((u64)ctx->irqs.offset[1] & 0xffff) << 32) |
+		       (((u64)ctx->irqs.offset[2] & 0xffff) << 16) |
+			((u64)ctx->irqs.offset[3] & 0xffff));
+	cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, (u64)
+		       (((u64)ctx->irqs.range[0] & 0xffff) << 48) |
+		       (((u64)ctx->irqs.range[1] & 0xffff) << 32) |
+		       (((u64)ctx->irqs.range[2] & 0xffff) << 16) |
+			((u64)ctx->irqs.range[3] & 0xffff));
+
+	cxl_p2n_write(afu, CXL_PSL_AMR_An, amr);
+
+	/* master only context for dedicated */
+	assign_psn_space(ctx);
+
+	if ((rc = cxl_afu_reset(afu)))
+		return rc;
+
+	cxl_p2n_write(afu, CXL_PSL_WED_An, wed);
+
+	return afu_enable(afu);
+}
+
+static int deactivate_dedicated_process(struct cxl_afu *afu)
+{
+	dev_info(&afu->dev, "Deactivating dedicated process mode\n");
+
+	afu->current_mode = 0;
+	afu->num_procs = 0;
+
+	cxl_chardev_afu_remove(afu);
+
+	return 0;
+}
+
+int _cxl_afu_deactivate_mode(struct cxl_afu *afu, int mode)
+{
+	if (mode == CXL_MODE_DIRECTED)
+		return deactivate_afu_directed(afu);
+	if (mode == CXL_MODE_DEDICATED)
+		return deactivate_dedicated_process(afu);
+	return 0;
+}
+
+int cxl_afu_deactivate_mode(struct cxl_afu *afu)
+{
+	return _cxl_afu_deactivate_mode(afu, afu->current_mode);
+}
+
+int cxl_afu_activate_mode(struct cxl_afu *afu, int mode)
+{
+	if (!mode)
+		return 0;
+	if (!(mode & afu->modes_supported))
+		return -EINVAL;
+
+	if (mode == CXL_MODE_DIRECTED)
+		return activate_afu_directed(afu);
+	if (mode == CXL_MODE_DEDICATED)
+		return activate_dedicated_process(afu);
+
+	return -EINVAL;
+}
+
+int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed, u64 amr)
+{
+	ctx->kernel = kernel;
+	if (ctx->afu->current_mode == CXL_MODE_DIRECTED)
+		return attach_afu_directed(ctx, wed, amr);
+
+	if (ctx->afu->current_mode == CXL_MODE_DEDICATED)
+		return attach_dedicated(ctx, wed, amr);
+
+	return -EINVAL;
+}
+
+static inline int detach_process_native_dedicated(struct cxl_context *ctx)
+{
+	cxl_afu_reset(ctx->afu);
+	cxl_afu_disable(ctx->afu);
+	cxl_psl_purge(ctx->afu);
+	return 0;
+}
+
+/*
+ * TODO: handle case when this is called inside a rcu_read_lock() which may
+ * happen when we unbind the driver (ie. cxl_context_detach_all()) .  Terminate
+ * & remove use a mutex lock and schedule which will not good with lock held.
+ * May need to write do_process_element_cmd() that handles outstanding page
+ * faults synchronously.
+ */
+static inline int detach_process_native_afu_directed(struct cxl_context *ctx)
+{
+	if (!ctx->pe_inserted)
+		return 0;
+	if (terminate_process_element(ctx))
+		return -1;
+	if (remove_process_element(ctx))
+		return -1;
+
+	return 0;
+}
+
+int cxl_detach_process(struct cxl_context *ctx)
+{
+	if (ctx->afu->current_mode == CXL_MODE_DEDICATED)
+		return detach_process_native_dedicated(ctx);
+
+	return detach_process_native_afu_directed(ctx);
+}
+
+int cxl_get_irq(struct cxl_context *ctx, struct cxl_irq_info *info)
+{
+	u64 pidtid;
+
+	info->dsisr = cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An);
+	info->dar = cxl_p2n_read(ctx->afu, CXL_PSL_DAR_An);
+	info->dsr = cxl_p2n_read(ctx->afu, CXL_PSL_DSR_An);
+	pidtid = cxl_p2n_read(ctx->afu, CXL_PSL_PID_TID_An);
+	info->pid = pidtid >> 32;
+	info->tid = pidtid & 0xffffffff;
+	info->afu_err = cxl_p2n_read(ctx->afu, CXL_AFU_ERR_An);
+	info->errstat = cxl_p2n_read(ctx->afu, CXL_PSL_ErrStat_An);
+
+	return 0;
+}
+
+static void recover_psl_err(struct cxl_afu *afu, u64 errstat)
+{
+	u64 dsisr;
+
+	pr_devel("RECOVERING FROM PSL ERROR... (0x%.16llx)\n", errstat);
+
+	/* Clear PSL_DSISR[PE] */
+	dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
+	cxl_p2n_write(afu, CXL_PSL_DSISR_An, dsisr & ~CXL_PSL_DSISR_An_PE);
+
+	/* Write 1s to clear error status bits */
+	cxl_p2n_write(afu, CXL_PSL_ErrStat_An, errstat);
+}
+
+int cxl_ack_irq(struct cxl_context *ctx, u64 tfc, u64 psl_reset_mask)
+{
+	if (tfc)
+		cxl_p2n_write(ctx->afu, CXL_PSL_TFC_An, tfc);
+	if (psl_reset_mask)
+		recover_psl_err(ctx->afu, psl_reset_mask);
+
+	return 0;
+}
+
+int cxl_check_error(struct cxl_afu *afu)
+{
+	return (cxl_p1n_read(afu, CXL_PSL_SCNTL_An) == ~0ULL);
+}
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
new file mode 100644
index 000000000000..10c98ab7f46e
--- /dev/null
+++ b/drivers/misc/cxl/pci.c
@@ -0,0 +1,1000 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/pci_regs.h>
+#include <linux/pci_ids.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/pci.h>
+#include <linux/of.h>
+#include <linux/delay.h>
+#include <asm/opal.h>
+#include <asm/msi_bitmap.h>
+#include <asm/pci-bridge.h> /* for struct pci_controller */
+#include <asm/pnv-pci.h>
+
+#include "cxl.h"
+
+
+#define CXL_PCI_VSEC_ID	0x1280
+#define CXL_VSEC_MIN_SIZE 0x80
+
+#define CXL_READ_VSEC_LENGTH(dev, vsec, dest)			\
+	{							\
+		pci_read_config_word(dev, vsec + 0x6, dest);	\
+		*dest >>= 4;					\
+	}
+#define CXL_READ_VSEC_NAFUS(dev, vsec, dest) \
+	pci_read_config_byte(dev, vsec + 0x8, dest)
+
+#define CXL_READ_VSEC_STATUS(dev, vsec, dest) \
+	pci_read_config_byte(dev, vsec + 0x9, dest)
+#define CXL_STATUS_SECOND_PORT  0x80
+#define CXL_STATUS_MSI_X_FULL   0x40
+#define CXL_STATUS_MSI_X_SINGLE 0x20
+#define CXL_STATUS_FLASH_RW     0x08
+#define CXL_STATUS_FLASH_RO     0x04
+#define CXL_STATUS_LOADABLE_AFU 0x02
+#define CXL_STATUS_LOADABLE_PSL 0x01
+/* If we see these features we won't try to use the card */
+#define CXL_UNSUPPORTED_FEATURES \
+	(CXL_STATUS_MSI_X_FULL | CXL_STATUS_MSI_X_SINGLE)
+
+#define CXL_READ_VSEC_MODE_CONTROL(dev, vsec, dest) \
+	pci_read_config_byte(dev, vsec + 0xa, dest)
+#define CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val) \
+	pci_write_config_byte(dev, vsec + 0xa, val)
+#define CXL_VSEC_PROTOCOL_MASK   0xe0
+#define CXL_VSEC_PROTOCOL_1024TB 0x80
+#define CXL_VSEC_PROTOCOL_512TB  0x40
+#define CXL_VSEC_PROTOCOL_256TB  0x20 /* Power 8 uses this */
+#define CXL_VSEC_PROTOCOL_ENABLE 0x01
+
+#define CXL_READ_VSEC_PSL_REVISION(dev, vsec, dest) \
+	pci_read_config_word(dev, vsec + 0xc, dest)
+#define CXL_READ_VSEC_CAIA_MINOR(dev, vsec, dest) \
+	pci_read_config_byte(dev, vsec + 0xe, dest)
+#define CXL_READ_VSEC_CAIA_MAJOR(dev, vsec, dest) \
+	pci_read_config_byte(dev, vsec + 0xf, dest)
+#define CXL_READ_VSEC_BASE_IMAGE(dev, vsec, dest) \
+	pci_read_config_word(dev, vsec + 0x10, dest)
+
+#define CXL_READ_VSEC_IMAGE_STATE(dev, vsec, dest) \
+	pci_read_config_byte(dev, vsec + 0x13, dest)
+#define CXL_WRITE_VSEC_IMAGE_STATE(dev, vsec, val) \
+	pci_write_config_byte(dev, vsec + 0x13, val)
+#define CXL_VSEC_USER_IMAGE_LOADED 0x80 /* RO */
+#define CXL_VSEC_PERST_LOADS_IMAGE 0x20 /* RW */
+#define CXL_VSEC_PERST_SELECT_USER 0x10 /* RW */
+
+#define CXL_READ_VSEC_AFU_DESC_OFF(dev, vsec, dest) \
+	pci_read_config_dword(dev, vsec + 0x20, dest)
+#define CXL_READ_VSEC_AFU_DESC_SIZE(dev, vsec, dest) \
+	pci_read_config_dword(dev, vsec + 0x24, dest)
+#define CXL_READ_VSEC_PS_OFF(dev, vsec, dest) \
+	pci_read_config_dword(dev, vsec + 0x28, dest)
+#define CXL_READ_VSEC_PS_SIZE(dev, vsec, dest) \
+	pci_read_config_dword(dev, vsec + 0x2c, dest)
+
+
+/* This works a little different than the p1/p2 register accesses to make it
+ * easier to pull out individual fields */
+#define AFUD_READ(afu, off)		in_be64(afu->afu_desc_mmio + off)
+#define EXTRACT_PPC_BIT(val, bit)	(!!(val & PPC_BIT(bit)))
+#define EXTRACT_PPC_BITS(val, bs, be)	((val & PPC_BITMASK(bs, be)) >> PPC_BITLSHIFT(be))
+
+#define AFUD_READ_INFO(afu)		AFUD_READ(afu, 0x0)
+#define   AFUD_NUM_INTS_PER_PROC(val)	EXTRACT_PPC_BITS(val,  0, 15)
+#define   AFUD_NUM_PROCS(val)		EXTRACT_PPC_BITS(val, 16, 31)
+#define   AFUD_NUM_CRS(val)		EXTRACT_PPC_BITS(val, 32, 47)
+#define   AFUD_MULTIMODE(val)		EXTRACT_PPC_BIT(val, 48)
+#define   AFUD_PUSH_BLOCK_TRANSFER(val)	EXTRACT_PPC_BIT(val, 55)
+#define   AFUD_DEDICATED_PROCESS(val)	EXTRACT_PPC_BIT(val, 59)
+#define   AFUD_AFU_DIRECTED(val)	EXTRACT_PPC_BIT(val, 61)
+#define   AFUD_TIME_SLICED(val)		EXTRACT_PPC_BIT(val, 63)
+#define AFUD_READ_CR(afu)		AFUD_READ(afu, 0x20)
+#define   AFUD_CR_LEN(val)		EXTRACT_PPC_BITS(val, 8, 63)
+#define AFUD_READ_CR_OFF(afu)		AFUD_READ(afu, 0x28)
+#define AFUD_READ_PPPSA(afu)		AFUD_READ(afu, 0x30)
+#define   AFUD_PPPSA_PP(val)		EXTRACT_PPC_BIT(val, 6)
+#define   AFUD_PPPSA_PSA(val)		EXTRACT_PPC_BIT(val, 7)
+#define   AFUD_PPPSA_LEN(val)		EXTRACT_PPC_BITS(val, 8, 63)
+#define AFUD_READ_PPPSA_OFF(afu)	AFUD_READ(afu, 0x38)
+#define AFUD_READ_EB(afu)		AFUD_READ(afu, 0x40)
+#define   AFUD_EB_LEN(val)		EXTRACT_PPC_BITS(val, 8, 63)
+#define AFUD_READ_EB_OFF(afu)		AFUD_READ(afu, 0x48)
+
+static DEFINE_PCI_DEVICE_TABLE(cxl_pci_tbl) = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0477), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x044b), },
+	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x04cf), },
+	{ PCI_DEVICE_CLASS(0x120000, ~0), },
+
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, cxl_pci_tbl);
+
+
+/*
+ * Mostly using these wrappers to avoid confusion:
+ * priv 1 is BAR2, while priv 2 is BAR0
+ */
+static inline resource_size_t p1_base(struct pci_dev *dev)
+{
+	return pci_resource_start(dev, 2);
+}
+
+static inline resource_size_t p1_size(struct pci_dev *dev)
+{
+	return pci_resource_len(dev, 2);
+}
+
+static inline resource_size_t p2_base(struct pci_dev *dev)
+{
+	return pci_resource_start(dev, 0);
+}
+
+static inline resource_size_t p2_size(struct pci_dev *dev)
+{
+	return pci_resource_len(dev, 0);
+}
+
+static int find_cxl_vsec(struct pci_dev *dev)
+{
+	int vsec = 0;
+	u16 val;
+
+	while ((vsec = pci_find_next_ext_capability(dev, vsec, PCI_EXT_CAP_ID_VNDR))) {
+		pci_read_config_word(dev, vsec + 0x4, &val);
+		if (val == CXL_PCI_VSEC_ID)
+			return vsec;
+	}
+	return 0;
+
+}
+
+static void dump_cxl_config_space(struct pci_dev *dev)
+{
+	int vsec;
+	u32 val;
+
+	dev_info(&dev->dev, "dump_cxl_config_space\n");
+
+	pci_read_config_dword(dev, PCI_BASE_ADDRESS_0, &val);
+	dev_info(&dev->dev, "BAR0: %#.8x\n", val);
+	pci_read_config_dword(dev, PCI_BASE_ADDRESS_1, &val);
+	dev_info(&dev->dev, "BAR1: %#.8x\n", val);
+	pci_read_config_dword(dev, PCI_BASE_ADDRESS_2, &val);
+	dev_info(&dev->dev, "BAR2: %#.8x\n", val);
+	pci_read_config_dword(dev, PCI_BASE_ADDRESS_3, &val);
+	dev_info(&dev->dev, "BAR3: %#.8x\n", val);
+	pci_read_config_dword(dev, PCI_BASE_ADDRESS_4, &val);
+	dev_info(&dev->dev, "BAR4: %#.8x\n", val);
+	pci_read_config_dword(dev, PCI_BASE_ADDRESS_5, &val);
+	dev_info(&dev->dev, "BAR5: %#.8x\n", val);
+
+	dev_info(&dev->dev, "p1 regs: %#llx, len: %#llx\n",
+		p1_base(dev), p1_size(dev));
+	dev_info(&dev->dev, "p2 regs: %#llx, len: %#llx\n",
+		p1_base(dev), p2_size(dev));
+	dev_info(&dev->dev, "BAR 4/5: %#llx, len: %#llx\n",
+		pci_resource_start(dev, 4), pci_resource_len(dev, 4));
+
+	if (!(vsec = find_cxl_vsec(dev)))
+		return;
+
+#define show_reg(name, what) \
+	dev_info(&dev->dev, "cxl vsec: %30s: %#x\n", name, what)
+
+	pci_read_config_dword(dev, vsec + 0x0, &val);
+	show_reg("Cap ID", (val >> 0) & 0xffff);
+	show_reg("Cap Ver", (val >> 16) & 0xf);
+	show_reg("Next Cap Ptr", (val >> 20) & 0xfff);
+	pci_read_config_dword(dev, vsec + 0x4, &val);
+	show_reg("VSEC ID", (val >> 0) & 0xffff);
+	show_reg("VSEC Rev", (val >> 16) & 0xf);
+	show_reg("VSEC Length",	(val >> 20) & 0xfff);
+	pci_read_config_dword(dev, vsec + 0x8, &val);
+	show_reg("Num AFUs", (val >> 0) & 0xff);
+	show_reg("Status", (val >> 8) & 0xff);
+	show_reg("Mode Control", (val >> 16) & 0xff);
+	show_reg("Reserved", (val >> 24) & 0xff);
+	pci_read_config_dword(dev, vsec + 0xc, &val);
+	show_reg("PSL Rev", (val >> 0) & 0xffff);
+	show_reg("CAIA Ver", (val >> 16) & 0xffff);
+	pci_read_config_dword(dev, vsec + 0x10, &val);
+	show_reg("Base Image Rev", (val >> 0) & 0xffff);
+	show_reg("Reserved", (val >> 16) & 0x0fff);
+	show_reg("Image Control", (val >> 28) & 0x3);
+	show_reg("Reserved", (val >> 30) & 0x1);
+	show_reg("Image Loaded", (val >> 31) & 0x1);
+
+	pci_read_config_dword(dev, vsec + 0x14, &val);
+	show_reg("Reserved", val);
+	pci_read_config_dword(dev, vsec + 0x18, &val);
+	show_reg("Reserved", val);
+	pci_read_config_dword(dev, vsec + 0x1c, &val);
+	show_reg("Reserved", val);
+
+	pci_read_config_dword(dev, vsec + 0x20, &val);
+	show_reg("AFU Descriptor Offset", val);
+	pci_read_config_dword(dev, vsec + 0x24, &val);
+	show_reg("AFU Descriptor Size", val);
+	pci_read_config_dword(dev, vsec + 0x28, &val);
+	show_reg("Problem State Offset", val);
+	pci_read_config_dword(dev, vsec + 0x2c, &val);
+	show_reg("Problem State Size", val);
+
+	pci_read_config_dword(dev, vsec + 0x30, &val);
+	show_reg("Reserved", val);
+	pci_read_config_dword(dev, vsec + 0x34, &val);
+	show_reg("Reserved", val);
+	pci_read_config_dword(dev, vsec + 0x38, &val);
+	show_reg("Reserved", val);
+	pci_read_config_dword(dev, vsec + 0x3c, &val);
+	show_reg("Reserved", val);
+
+	pci_read_config_dword(dev, vsec + 0x40, &val);
+	show_reg("PSL Programming Port", val);
+	pci_read_config_dword(dev, vsec + 0x44, &val);
+	show_reg("PSL Programming Control", val);
+
+	pci_read_config_dword(dev, vsec + 0x48, &val);
+	show_reg("Reserved", val);
+	pci_read_config_dword(dev, vsec + 0x4c, &val);
+	show_reg("Reserved", val);
+
+	pci_read_config_dword(dev, vsec + 0x50, &val);
+	show_reg("Flash Address Register", val);
+	pci_read_config_dword(dev, vsec + 0x54, &val);
+	show_reg("Flash Size Register", val);
+	pci_read_config_dword(dev, vsec + 0x58, &val);
+	show_reg("Flash Status/Control Register", val);
+	pci_read_config_dword(dev, vsec + 0x58, &val);
+	show_reg("Flash Data Port", val);
+
+#undef show_reg
+}
+
+static void dump_afu_descriptor(struct cxl_afu *afu)
+{
+	u64 val;
+
+#define show_reg(name, what) \
+	dev_info(&afu->dev, "afu desc: %30s: %#llx\n", name, what)
+
+	val = AFUD_READ_INFO(afu);
+	show_reg("num_ints_per_process", AFUD_NUM_INTS_PER_PROC(val));
+	show_reg("num_of_processes", AFUD_NUM_PROCS(val));
+	show_reg("num_of_afu_CRs", AFUD_NUM_CRS(val));
+	show_reg("req_prog_mode", val & 0xffffULL);
+
+	val = AFUD_READ(afu, 0x8);
+	show_reg("Reserved", val);
+	val = AFUD_READ(afu, 0x10);
+	show_reg("Reserved", val);
+	val = AFUD_READ(afu, 0x18);
+	show_reg("Reserved", val);
+
+	val = AFUD_READ_CR(afu);
+	show_reg("Reserved", (val >> (63-7)) & 0xff);
+	show_reg("AFU_CR_len", AFUD_CR_LEN(val));
+
+	val = AFUD_READ_CR_OFF(afu);
+	show_reg("AFU_CR_offset", val);
+
+	val = AFUD_READ_PPPSA(afu);
+	show_reg("PerProcessPSA_control", (val >> (63-7)) & 0xff);
+	show_reg("PerProcessPSA Length", AFUD_PPPSA_LEN(val));
+
+	val = AFUD_READ_PPPSA_OFF(afu);
+	show_reg("PerProcessPSA_offset", val);
+
+	val = AFUD_READ_EB(afu);
+	show_reg("Reserved", (val >> (63-7)) & 0xff);
+	show_reg("AFU_EB_len", AFUD_EB_LEN(val));
+
+	val = AFUD_READ_EB_OFF(afu);
+	show_reg("AFU_EB_offset", val);
+
+#undef show_reg
+}
+
+static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev *dev)
+{
+	struct device_node *np;
+	const __be32 *prop;
+	u64 psl_dsnctl;
+	u64 chipid;
+
+	if (!(np = pnv_pci_to_phb_node(dev)))
+		return -ENODEV;
+
+	while (np && !(prop = of_get_property(np, "ibm,chip-id", NULL)))
+		np = of_get_next_parent(np);
+	if (!np)
+		return -ENODEV;
+	chipid = be32_to_cpup(prop);
+	of_node_put(np);
+
+	/* Tell PSL where to route data to */
+	psl_dsnctl = 0x02E8900002000000ULL | (chipid << (63-5));
+	cxl_p1_write(adapter, CXL_PSL_DSNDCTL, psl_dsnctl);
+	cxl_p1_write(adapter, CXL_PSL_RESLCKTO, 0x20000000200ULL);
+	/* snoop write mask */
+	cxl_p1_write(adapter, CXL_PSL_SNWRALLOC, 0x00000000FFFFFFFFULL);
+	/* set fir_accum */
+	cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, 0x0800000000000000ULL);
+	/* for debugging with trace arrays */
+	cxl_p1_write(adapter, CXL_PSL_TRACE, 0x0000FF7C00000000ULL);
+
+	return 0;
+}
+
+static int init_implementation_afu_regs(struct cxl_afu *afu)
+{
+	/* read/write masks for this slice */
+	cxl_p1n_write(afu, CXL_PSL_APCALLOC_A, 0xFFFFFFFEFEFEFEFEULL);
+	/* APC read/write masks for this slice */
+	cxl_p1n_write(afu, CXL_PSL_COALLOC_A, 0xFF000000FEFEFEFEULL);
+	/* for debugging with trace arrays */
+	cxl_p1n_write(afu, CXL_PSL_SLICE_TRACE, 0x0000FFFF00000000ULL);
+	cxl_p1n_write(afu, CXL_PSL_RXCTL_A, 0xF000000000000000ULL);
+
+	return 0;
+}
+
+int cxl_setup_irq(struct cxl *adapter, unsigned int hwirq,
+			 unsigned int virq)
+{
+	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+
+	return pnv_cxl_ioda_msi_setup(dev, hwirq, virq);
+}
+
+int cxl_alloc_one_irq(struct cxl *adapter)
+{
+	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+
+	return pnv_cxl_alloc_hwirqs(dev, 1);
+}
+
+void cxl_release_one_irq(struct cxl *adapter, int hwirq)
+{
+	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+
+	return pnv_cxl_release_hwirqs(dev, hwirq, 1);
+}
+
+int cxl_alloc_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter, unsigned int num)
+{
+	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+
+	return pnv_cxl_alloc_hwirq_ranges(irqs, dev, num);
+}
+
+void cxl_release_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter)
+{
+	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+
+	pnv_cxl_release_hwirq_ranges(irqs, dev);
+}
+
+static int setup_cxl_bars(struct pci_dev *dev)
+{
+	/* Safety check in case we get backported to < 3.17 without M64 */
+	if ((p1_base(dev) < 0x100000000ULL) ||
+	    (p2_base(dev) < 0x100000000ULL)) {
+		dev_err(&dev->dev, "ABORTING: M32 BAR assignment incompatible with CXL\n");
+		return -ENODEV;
+	}
+
+	/*
+	 * BAR 4/5 has a special meaning for CXL and must be programmed with a
+	 * special value corresponding to the CXL protocol address range.
+	 * For POWER 8 that means bits 48:49 must be set to 10
+	 */
+	pci_write_config_dword(dev, PCI_BASE_ADDRESS_4, 0x00000000);
+	pci_write_config_dword(dev, PCI_BASE_ADDRESS_5, 0x00020000);
+
+	return 0;
+}
+
+/* pciex node: ibm,opal-m64-window = <0x3d058 0x0 0x3d058 0x0 0x8 0x0>; */
+static int switch_card_to_cxl(struct pci_dev *dev)
+{
+	int vsec;
+	u8 val;
+	int rc;
+
+	dev_info(&dev->dev, "switch card to CXL\n");
+
+	if (!(vsec = find_cxl_vsec(dev))) {
+		dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n");
+		return -ENODEV;
+	}
+
+	if ((rc = CXL_READ_VSEC_MODE_CONTROL(dev, vsec, &val))) {
+		dev_err(&dev->dev, "failed to read current mode control: %i", rc);
+		return rc;
+	}
+	val &= ~CXL_VSEC_PROTOCOL_MASK;
+	val |= CXL_VSEC_PROTOCOL_256TB | CXL_VSEC_PROTOCOL_ENABLE;
+	if ((rc = CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val))) {
+		dev_err(&dev->dev, "failed to enable CXL protocol: %i", rc);
+		return rc;
+	}
+	/*
+	 * The CAIA spec (v0.12 11.6 Bi-modal Device Support) states
+	 * we must wait 100ms after this mode switch before touching
+	 * PCIe config space.
+	 */
+	msleep(100);
+
+	return 0;
+}
+
+static int cxl_map_slice_regs(struct cxl_afu *afu, struct cxl *adapter, struct pci_dev *dev)
+{
+	u64 p1n_base, p2n_base, afu_desc;
+	const u64 p1n_size = 0x100;
+	const u64 p2n_size = 0x1000;
+
+	p1n_base = p1_base(dev) + 0x10000 + (afu->slice * p1n_size);
+	p2n_base = p2_base(dev) + (afu->slice * p2n_size);
+	afu->psn_phys = p2_base(dev) + (adapter->ps_off + (afu->slice * adapter->ps_size));
+	afu_desc = p2_base(dev) + adapter->afu_desc_off + (afu->slice * adapter->afu_desc_size);
+
+	if (!(afu->p1n_mmio = ioremap(p1n_base, p1n_size)))
+		goto err;
+	if (!(afu->p2n_mmio = ioremap(p2n_base, p2n_size)))
+		goto err1;
+	if (afu_desc) {
+		if (!(afu->afu_desc_mmio = ioremap(afu_desc, adapter->afu_desc_size)))
+			goto err2;
+	}
+
+	return 0;
+err2:
+	iounmap(afu->p2n_mmio);
+err1:
+	iounmap(afu->p1n_mmio);
+err:
+	dev_err(&afu->dev, "Error mapping AFU MMIO regions\n");
+	return -ENOMEM;
+}
+
+static void cxl_unmap_slice_regs(struct cxl_afu *afu)
+{
+	if (afu->p1n_mmio)
+		iounmap(afu->p2n_mmio);
+	if (afu->p1n_mmio)
+		iounmap(afu->p1n_mmio);
+}
+
+static void cxl_release_afu(struct device *dev)
+{
+	struct cxl_afu *afu = to_cxl_afu(dev);
+
+	pr_devel("cxl_release_afu\n");
+
+	kfree(afu);
+}
+
+static struct cxl_afu *cxl_alloc_afu(struct cxl *adapter, int slice)
+{
+	struct cxl_afu *afu;
+
+	if (!(afu = kzalloc(sizeof(struct cxl_afu), GFP_KERNEL)))
+		return NULL;
+
+	afu->adapter = adapter;
+	afu->dev.parent = &adapter->dev;
+	afu->dev.release = cxl_release_afu;
+	afu->slice = slice;
+	idr_init(&afu->contexts_idr);
+	spin_lock_init(&afu->contexts_lock);
+	spin_lock_init(&afu->afu_cntl_lock);
+	mutex_init(&afu->spa_mutex);
+
+	afu->prefault_mode = CXL_PREFAULT_NONE;
+	afu->irqs_max = afu->adapter->user_irqs;
+
+	return afu;
+}
+
+/* Expects AFU struct to have recently been zeroed out */
+static int cxl_read_afu_descriptor(struct cxl_afu *afu)
+{
+	u64 val;
+
+	val = AFUD_READ_INFO(afu);
+	afu->pp_irqs = AFUD_NUM_INTS_PER_PROC(val);
+	afu->max_procs_virtualised = AFUD_NUM_PROCS(val);
+
+	if (AFUD_AFU_DIRECTED(val))
+		afu->modes_supported |= CXL_MODE_DIRECTED;
+	if (AFUD_DEDICATED_PROCESS(val))
+		afu->modes_supported |= CXL_MODE_DEDICATED;
+	if (AFUD_TIME_SLICED(val))
+		afu->modes_supported |= CXL_MODE_TIME_SLICED;
+
+	val = AFUD_READ_PPPSA(afu);
+	afu->pp_size = AFUD_PPPSA_LEN(val) * 4096;
+	afu->psa = AFUD_PPPSA_PSA(val);
+	if ((afu->pp_psa = AFUD_PPPSA_PP(val)))
+		afu->pp_offset = AFUD_READ_PPPSA_OFF(afu);
+
+	return 0;
+}
+
+static int cxl_afu_descriptor_looks_ok(struct cxl_afu *afu)
+{
+	if (afu->psa && afu->adapter->ps_size <
+			(afu->pp_offset + afu->pp_size*afu->max_procs_virtualised)) {
+		dev_err(&afu->dev, "per-process PSA can't fit inside the PSA!\n");
+		return -ENODEV;
+	}
+
+	if (afu->pp_psa && (afu->pp_size < PAGE_SIZE))
+		dev_warn(&afu->dev, "AFU uses < PAGE_SIZE per-process PSA!");
+
+	return 0;
+}
+
+static int sanitise_afu_regs(struct cxl_afu *afu)
+{
+	u64 reg;
+
+	/*
+	 * Clear out any regs that contain either an IVTE or address or may be
+	 * waiting on an acknowledgement to try to be a bit safer as we bring
+	 * it online
+	 */
+	reg = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
+	if ((reg & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) {
+		dev_warn(&afu->dev, "WARNING: AFU was not disabled: %#.16llx\n", reg);
+		if (cxl_afu_reset(afu))
+			return -EIO;
+		if (cxl_afu_disable(afu))
+			return -EIO;
+		if (cxl_psl_purge(afu))
+			return -EIO;
+	}
+	cxl_p1n_write(afu, CXL_PSL_SPAP_An, 0x0000000000000000);
+	cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, 0x0000000000000000);
+	cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An, 0x0000000000000000);
+	cxl_p1n_write(afu, CXL_PSL_AMBAR_An, 0x0000000000000000);
+	cxl_p1n_write(afu, CXL_PSL_SPOffset_An, 0x0000000000000000);
+	cxl_p1n_write(afu, CXL_HAURP_An, 0x0000000000000000);
+	cxl_p2n_write(afu, CXL_CSRP_An, 0x0000000000000000);
+	cxl_p2n_write(afu, CXL_AURP1_An, 0x0000000000000000);
+	cxl_p2n_write(afu, CXL_AURP0_An, 0x0000000000000000);
+	cxl_p2n_write(afu, CXL_SSTP1_An, 0x0000000000000000);
+	cxl_p2n_write(afu, CXL_SSTP0_An, 0x0000000000000000);
+	reg = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
+	if (reg) {
+		dev_warn(&afu->dev, "AFU had pending DSISR: %#.16llx\n", reg);
+		if (reg & CXL_PSL_DSISR_TRANS)
+			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE);
+		else
+			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A);
+	}
+	reg = cxl_p1n_read(afu, CXL_PSL_SERR_An);
+	if (reg) {
+		if (reg & ~0xffff)
+			dev_warn(&afu->dev, "AFU had pending SERR: %#.16llx\n", reg);
+		cxl_p1n_write(afu, CXL_PSL_SERR_An, reg & ~0xffff);
+	}
+	reg = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
+	if (reg) {
+		dev_warn(&afu->dev, "AFU had pending error status: %#.16llx\n", reg);
+		cxl_p2n_write(afu, CXL_PSL_ErrStat_An, reg);
+	}
+
+	return 0;
+}
+
+static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
+{
+	struct cxl_afu *afu;
+	bool free = true;
+	int rc;
+
+	if (!(afu = cxl_alloc_afu(adapter, slice)))
+		return -ENOMEM;
+
+	if ((rc = dev_set_name(&afu->dev, "afu%i.%i", adapter->adapter_num, slice)))
+		goto err1;
+
+	if ((rc = cxl_map_slice_regs(afu, adapter, dev)))
+		goto err1;
+
+	if ((rc = sanitise_afu_regs(afu)))
+		goto err2;
+
+	/* We need to reset the AFU before we can read the AFU descriptor */
+	if ((rc = cxl_afu_reset(afu)))
+		goto err2;
+
+	if (cxl_verbose)
+		dump_afu_descriptor(afu);
+
+	if ((rc = cxl_read_afu_descriptor(afu)))
+		goto err2;
+
+	if ((rc = cxl_afu_descriptor_looks_ok(afu)))
+		goto err2;
+
+	if ((rc = init_implementation_afu_regs(afu)))
+		goto err2;
+
+	if ((rc = cxl_register_serr_irq(afu)))
+		goto err2;
+
+	if ((rc = cxl_register_psl_irq(afu)))
+		goto err3;
+
+	/* Don't care if this fails */
+	cxl_debugfs_afu_add(afu);
+
+	/*
+	 * After we call this function we must not free the afu directly, even
+	 * if it returns an error!
+	 */
+	if ((rc = cxl_register_afu(afu)))
+		goto err_put1;
+
+	if ((rc = cxl_sysfs_afu_add(afu)))
+		goto err_put1;
+
+
+	if ((rc = cxl_afu_select_best_mode(afu)))
+		goto err_put2;
+
+	adapter->afu[afu->slice] = afu;
+
+	return 0;
+
+err_put2:
+	cxl_sysfs_afu_remove(afu);
+err_put1:
+	device_unregister(&afu->dev);
+	free = false;
+	cxl_debugfs_afu_remove(afu);
+	cxl_release_psl_irq(afu);
+err3:
+	cxl_release_serr_irq(afu);
+err2:
+	cxl_unmap_slice_regs(afu);
+err1:
+	if (free)
+		kfree(afu);
+	return rc;
+}
+
+static void cxl_remove_afu(struct cxl_afu *afu)
+{
+	pr_devel("cxl_remove_afu\n");
+
+	if (!afu)
+		return;
+
+	cxl_sysfs_afu_remove(afu);
+	cxl_debugfs_afu_remove(afu);
+
+	spin_lock(&afu->adapter->afu_list_lock);
+	afu->adapter->afu[afu->slice] = NULL;
+	spin_unlock(&afu->adapter->afu_list_lock);
+
+	cxl_context_detach_all(afu);
+	cxl_afu_deactivate_mode(afu);
+
+	cxl_release_psl_irq(afu);
+	cxl_release_serr_irq(afu);
+	cxl_unmap_slice_regs(afu);
+
+	device_unregister(&afu->dev);
+}
+
+
+static int cxl_map_adapter_regs(struct cxl *adapter, struct pci_dev *dev)
+{
+	if (pci_request_region(dev, 2, "priv 2 regs"))
+		goto err1;
+	if (pci_request_region(dev, 0, "priv 1 regs"))
+		goto err2;
+
+	pr_devel("cxl_map_adapter_regs: p1: %#.16llx %#llx, p2: %#.16llx %#llx",
+			p1_base(dev), p1_size(dev), p2_base(dev), p2_size(dev));
+
+	if (!(adapter->p1_mmio = ioremap(p1_base(dev), p1_size(dev))))
+		goto err3;
+
+	if (!(adapter->p2_mmio = ioremap(p2_base(dev), p2_size(dev))))
+		goto err4;
+
+	return 0;
+
+err4:
+	iounmap(adapter->p1_mmio);
+	adapter->p1_mmio = NULL;
+err3:
+	pci_release_region(dev, 0);
+err2:
+	pci_release_region(dev, 2);
+err1:
+	return -ENOMEM;
+}
+
+static void cxl_unmap_adapter_regs(struct cxl *adapter)
+{
+	if (adapter->p1_mmio)
+		iounmap(adapter->p1_mmio);
+	if (adapter->p2_mmio)
+		iounmap(adapter->p2_mmio);
+}
+
+static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev)
+{
+	int vsec;
+	u32 afu_desc_off, afu_desc_size;
+	u32 ps_off, ps_size;
+	u16 vseclen;
+	u8 image_state;
+
+	if (!(vsec = find_cxl_vsec(dev))) {
+		dev_err(&adapter->dev, "ABORTING: CXL VSEC not found!\n");
+		return -ENODEV;
+	}
+
+	CXL_READ_VSEC_LENGTH(dev, vsec, &vseclen);
+	if (vseclen < CXL_VSEC_MIN_SIZE) {
+		pr_err("ABORTING: CXL VSEC too short\n");
+		return -EINVAL;
+	}
+
+	CXL_READ_VSEC_STATUS(dev, vsec, &adapter->vsec_status);
+	CXL_READ_VSEC_PSL_REVISION(dev, vsec, &adapter->psl_rev);
+	CXL_READ_VSEC_CAIA_MAJOR(dev, vsec, &adapter->caia_major);
+	CXL_READ_VSEC_CAIA_MINOR(dev, vsec, &adapter->caia_minor);
+	CXL_READ_VSEC_BASE_IMAGE(dev, vsec, &adapter->base_image);
+	CXL_READ_VSEC_IMAGE_STATE(dev, vsec, &image_state);
+	adapter->user_image_loaded = !!(image_state & CXL_VSEC_USER_IMAGE_LOADED);
+	adapter->perst_loads_image = !!(image_state & CXL_VSEC_PERST_LOADS_IMAGE);
+	adapter->perst_select_user = !!(image_state & CXL_VSEC_PERST_SELECT_USER);
+
+	CXL_READ_VSEC_NAFUS(dev, vsec, &adapter->slices);
+	CXL_READ_VSEC_AFU_DESC_OFF(dev, vsec, &afu_desc_off);
+	CXL_READ_VSEC_AFU_DESC_SIZE(dev, vsec, &afu_desc_size);
+	CXL_READ_VSEC_PS_OFF(dev, vsec, &ps_off);
+	CXL_READ_VSEC_PS_SIZE(dev, vsec, &ps_size);
+
+	/* Convert everything to bytes, because there is NO WAY I'd look at the
+	 * code a month later and forget what units these are in ;-) */
+	adapter->ps_off = ps_off * 64 * 1024;
+	adapter->ps_size = ps_size * 64 * 1024;
+	adapter->afu_desc_off = afu_desc_off * 64 * 1024;
+	adapter->afu_desc_size = afu_desc_size *64 * 1024;
+
+	/* Total IRQs - 1 PSL ERROR - #AFU*(1 slice error + 1 DSI) */
+	adapter->user_irqs = pnv_cxl_get_irq_count(dev) - 1 - 2*adapter->slices;
+
+	return 0;
+}
+
+static int cxl_vsec_looks_ok(struct cxl *adapter, struct pci_dev *dev)
+{
+	if (adapter->vsec_status & CXL_STATUS_SECOND_PORT)
+		return -EBUSY;
+
+	if (adapter->vsec_status & CXL_UNSUPPORTED_FEATURES) {
+		dev_err(&adapter->dev, "ABORTING: CXL requires unsupported features\n");
+		return -EINVAL;
+	}
+
+	if (!adapter->slices) {
+		/* Once we support dynamic reprogramming we can use the card if
+		 * it supports loadable AFUs */
+		dev_err(&adapter->dev, "ABORTING: Device has no AFUs\n");
+		return -EINVAL;
+	}
+
+	if (!adapter->afu_desc_off || !adapter->afu_desc_size) {
+		dev_err(&adapter->dev, "ABORTING: VSEC shows no AFU descriptors\n");
+		return -EINVAL;
+	}
+
+	if (adapter->ps_size > p2_size(dev) - adapter->ps_off) {
+		dev_err(&adapter->dev, "ABORTING: Problem state size larger than "
+				   "available in BAR2: 0x%llx > 0x%llx\n",
+			 adapter->ps_size, p2_size(dev) - adapter->ps_off);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void cxl_release_adapter(struct device *dev)
+{
+	struct cxl *adapter = to_cxl_adapter(dev);
+
+	pr_devel("cxl_release_adapter\n");
+
+	kfree(adapter);
+}
+
+static struct cxl *cxl_alloc_adapter(struct pci_dev *dev)
+{
+	struct cxl *adapter;
+
+	if (!(adapter = kzalloc(sizeof(struct cxl), GFP_KERNEL)))
+		return NULL;
+
+	adapter->dev.parent = &dev->dev;
+	adapter->dev.release = cxl_release_adapter;
+	pci_set_drvdata(dev, adapter);
+	spin_lock_init(&adapter->afu_list_lock);
+
+	return adapter;
+}
+
+static int sanitise_adapter_regs(struct cxl *adapter)
+{
+	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
+	return cxl_tlb_slb_invalidate(adapter);
+}
+
+static struct cxl *cxl_init_adapter(struct pci_dev *dev)
+{
+	struct cxl *adapter;
+	bool free = true;
+	int rc;
+
+
+	if (!(adapter = cxl_alloc_adapter(dev)))
+		return ERR_PTR(-ENOMEM);
+
+	if ((rc = switch_card_to_cxl(dev)))
+		goto err1;
+
+	if ((rc = cxl_alloc_adapter_nr(adapter)))
+		goto err1;
+
+	if ((rc = dev_set_name(&adapter->dev, "card%i", adapter->adapter_num)))
+		goto err2;
+
+	if ((rc = cxl_read_vsec(adapter, dev)))
+		goto err2;
+
+	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
+		goto err2;
+
+	if ((rc = cxl_map_adapter_regs(adapter, dev)))
+		goto err2;
+
+	if ((rc = sanitise_adapter_regs(adapter)))
+		goto err2;
+
+	if ((rc = init_implementation_adapter_regs(adapter, dev)))
+		goto err3;
+
+	if ((rc = pnv_phb_to_cxl(dev)))
+		goto err3;
+
+	if ((rc = cxl_register_psl_err_irq(adapter)))
+		goto err3;
+
+	/* Don't care if this one fails: */
+	cxl_debugfs_adapter_add(adapter);
+
+	/*
+	 * After we call this function we must not free the adapter directly,
+	 * even if it returns an error!
+	 */
+	if ((rc = cxl_register_adapter(adapter)))
+		goto err_put1;
+
+	if ((rc = cxl_sysfs_adapter_add(adapter)))
+		goto err_put1;
+
+	return adapter;
+
+err_put1:
+	device_unregister(&adapter->dev);
+	free = false;
+	cxl_debugfs_adapter_remove(adapter);
+	cxl_release_psl_err_irq(adapter);
+err3:
+	cxl_unmap_adapter_regs(adapter);
+err2:
+	cxl_remove_adapter_nr(adapter);
+err1:
+	if (free)
+		kfree(adapter);
+	return ERR_PTR(rc);
+}
+
+static void cxl_remove_adapter(struct cxl *adapter)
+{
+	struct pci_dev *pdev = to_pci_dev(adapter->dev.parent);
+
+	pr_devel("cxl_release_adapter\n");
+
+	cxl_sysfs_adapter_remove(adapter);
+	cxl_debugfs_adapter_remove(adapter);
+	cxl_release_psl_err_irq(adapter);
+	cxl_unmap_adapter_regs(adapter);
+	cxl_remove_adapter_nr(adapter);
+
+	device_unregister(&adapter->dev);
+
+	pci_release_region(pdev, 0);
+	pci_release_region(pdev, 2);
+	pci_disable_device(pdev);
+}
+
+static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
+{
+	struct cxl *adapter;
+	int slice;
+	int rc;
+
+	pci_dev_get(dev);
+
+	if (cxl_verbose)
+		dump_cxl_config_space(dev);
+
+	if ((rc = setup_cxl_bars(dev)))
+		return rc;
+
+	if ((rc = pci_enable_device(dev))) {
+		dev_err(&dev->dev, "pci_enable_device failed: %i\n", rc);
+		return rc;
+	}
+
+	adapter = cxl_init_adapter(dev);
+	if (IS_ERR(adapter)) {
+		dev_err(&dev->dev, "cxl_init_adapter failed: %li\n", PTR_ERR(adapter));
+		return PTR_ERR(adapter);
+	}
+
+	for (slice = 0; slice < adapter->slices; slice++) {
+		if ((rc = cxl_init_afu(adapter, slice, dev)))
+			dev_err(&dev->dev, "AFU %i failed to initialise: %i\n", slice, rc);
+	}
+
+	return 0;
+}
+
+static void cxl_remove(struct pci_dev *dev)
+{
+	struct cxl *adapter = pci_get_drvdata(dev);
+	int afu;
+
+	dev_warn(&dev->dev, "pci remove\n");
+
+	/*
+	 * Lock to prevent someone grabbing a ref through the adapter list as
+	 * we are removing it
+	 */
+	for (afu = 0; afu < adapter->slices; afu++)
+		cxl_remove_afu(adapter->afu[afu]);
+	cxl_remove_adapter(adapter);
+}
+
+struct pci_driver cxl_pci_driver = {
+	.name = "cxl-pci",
+	.id_table = cxl_pci_tbl,
+	.probe = cxl_probe,
+	.remove = cxl_remove,
+};
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
new file mode 100644
index 000000000000..ce7ec06d87d1
--- /dev/null
+++ b/drivers/misc/cxl/sysfs.c
@@ -0,0 +1,385 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/sysfs.h>
+
+#include "cxl.h"
+
+#define to_afu_chardev_m(d) dev_get_drvdata(d)
+
+/*********  Adapter attributes  **********************************************/
+
+static ssize_t caia_version_show(struct device *device,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct cxl *adapter = to_cxl_adapter(device);
+
+	return scnprintf(buf, PAGE_SIZE, "%i.%i\n", adapter->caia_major,
+			 adapter->caia_minor);
+}
+
+static ssize_t psl_revision_show(struct device *device,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct cxl *adapter = to_cxl_adapter(device);
+
+	return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->psl_rev);
+}
+
+static ssize_t base_image_show(struct device *device,
+			       struct device_attribute *attr,
+			       char *buf)
+{
+	struct cxl *adapter = to_cxl_adapter(device);
+
+	return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->base_image);
+}
+
+static ssize_t image_loaded_show(struct device *device,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct cxl *adapter = to_cxl_adapter(device);
+
+	if (adapter->user_image_loaded)
+		return scnprintf(buf, PAGE_SIZE, "user\n");
+	return scnprintf(buf, PAGE_SIZE, "factory\n");
+}
+
+static struct device_attribute adapter_attrs[] = {
+	__ATTR_RO(caia_version),
+	__ATTR_RO(psl_revision),
+	__ATTR_RO(base_image),
+	__ATTR_RO(image_loaded),
+};
+
+
+/*********  AFU master specific attributes  **********************************/
+
+static ssize_t mmio_size_show_master(struct device *device,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct cxl_afu *afu = to_afu_chardev_m(device);
+
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->adapter->ps_size);
+}
+
+static ssize_t pp_mmio_off_show(struct device *device,
+				struct device_attribute *attr,
+				char *buf)
+{
+	struct cxl_afu *afu = to_afu_chardev_m(device);
+
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->pp_offset);
+}
+
+static ssize_t pp_mmio_len_show(struct device *device,
+				struct device_attribute *attr,
+				char *buf)
+{
+	struct cxl_afu *afu = to_afu_chardev_m(device);
+
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->pp_size);
+}
+
+static struct device_attribute afu_master_attrs[] = {
+	__ATTR(mmio_size, S_IRUGO, mmio_size_show_master, NULL),
+	__ATTR_RO(pp_mmio_off),
+	__ATTR_RO(pp_mmio_len),
+};
+
+
+/*********  AFU attributes  **************************************************/
+
+static ssize_t mmio_size_show(struct device *device,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct cxl_afu *afu = to_cxl_afu(device);
+
+	if (afu->pp_size)
+		return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->pp_size);
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->adapter->ps_size);
+}
+
+static ssize_t reset_store_afu(struct device *device,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count)
+{
+	struct cxl_afu *afu = to_cxl_afu(device);
+	int rc;
+
+	/* Not safe to reset if it is currently in use */
+	spin_lock(&afu->contexts_lock);
+	if (!idr_is_empty(&afu->contexts_idr)) {
+		rc = -EBUSY;
+		goto err;
+	}
+
+	if ((rc = cxl_afu_reset(afu)))
+		goto err;
+
+	rc = count;
+err:
+	spin_unlock(&afu->contexts_lock);
+	return rc;
+}
+
+static ssize_t irqs_min_show(struct device *device,
+			     struct device_attribute *attr,
+			     char *buf)
+{
+	struct cxl_afu *afu = to_cxl_afu(device);
+
+	return scnprintf(buf, PAGE_SIZE, "%i\n", afu->pp_irqs);
+}
+
+static ssize_t irqs_max_show(struct device *device,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	struct cxl_afu *afu = to_cxl_afu(device);
+
+	return scnprintf(buf, PAGE_SIZE, "%i\n", afu->irqs_max);
+}
+
+static ssize_t irqs_max_store(struct device *device,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct cxl_afu *afu = to_cxl_afu(device);
+	ssize_t ret;
+	int irqs_max;
+
+	ret = sscanf(buf, "%i", &irqs_max);
+	if (ret != 1)
+		return -EINVAL;
+
+	if (irqs_max < afu->pp_irqs)
+		return -EINVAL;
+
+	if (irqs_max > afu->adapter->user_irqs)
+		return -EINVAL;
+
+	afu->irqs_max = irqs_max;
+	return count;
+}
+
+static ssize_t modes_supported_show(struct device *device,
+				    struct device_attribute *attr, char *buf)
+{
+	struct cxl_afu *afu = to_cxl_afu(device);
+	char *p = buf, *end = buf + PAGE_SIZE;
+
+	if (afu->modes_supported & CXL_MODE_DEDICATED)
+		p += scnprintf(p, end - p, "dedicated_process\n");
+	if (afu->modes_supported & CXL_MODE_DIRECTED)
+		p += scnprintf(p, end - p, "afu_directed\n");
+	return (p - buf);
+}
+
+static ssize_t prefault_mode_show(struct device *device,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	struct cxl_afu *afu = to_cxl_afu(device);
+
+	switch (afu->prefault_mode) {
+	case CXL_PREFAULT_WED:
+		return scnprintf(buf, PAGE_SIZE, "work_element_descriptor\n");
+	case CXL_PREFAULT_ALL:
+		return scnprintf(buf, PAGE_SIZE, "all\n");
+	default:
+		return scnprintf(buf, PAGE_SIZE, "none\n");
+	}
+}
+
+static ssize_t prefault_mode_store(struct device *device,
+			  struct device_attribute *attr,
+			  const char *buf, size_t count)
+{
+	struct cxl_afu *afu = to_cxl_afu(device);
+	enum prefault_modes mode = -1;
+
+	if (!strncmp(buf, "work_element_descriptor", 23))
+		mode = CXL_PREFAULT_WED;
+	if (!strncmp(buf, "all", 3))
+		mode = CXL_PREFAULT_ALL;
+	if (!strncmp(buf, "none", 4))
+		mode = CXL_PREFAULT_NONE;
+
+	if (mode == -1)
+		return -EINVAL;
+
+	afu->prefault_mode = mode;
+	return count;
+}
+
+static ssize_t mode_show(struct device *device,
+			 struct device_attribute *attr,
+			 char *buf)
+{
+	struct cxl_afu *afu = to_cxl_afu(device);
+
+	if (afu->current_mode == CXL_MODE_DEDICATED)
+		return scnprintf(buf, PAGE_SIZE, "dedicated_process\n");
+	if (afu->current_mode == CXL_MODE_DIRECTED)
+		return scnprintf(buf, PAGE_SIZE, "afu_directed\n");
+	return scnprintf(buf, PAGE_SIZE, "none\n");
+}
+
+static ssize_t mode_store(struct device *device, struct device_attribute *attr,
+			  const char *buf, size_t count)
+{
+	struct cxl_afu *afu = to_cxl_afu(device);
+	int old_mode, mode = -1;
+	int rc = -EBUSY;
+
+	/* can't change this if we have a user */
+	spin_lock(&afu->contexts_lock);
+	if (!idr_is_empty(&afu->contexts_idr))
+		goto err;
+
+	if (!strncmp(buf, "dedicated_process", 17))
+		mode = CXL_MODE_DEDICATED;
+	if (!strncmp(buf, "afu_directed", 12))
+		mode = CXL_MODE_DIRECTED;
+	if (!strncmp(buf, "none", 4))
+		mode = 0;
+
+	if (mode == -1) {
+		rc = -EINVAL;
+		goto err;
+	}
+
+	/*
+	 * cxl_afu_deactivate_mode needs to be done outside the lock, prevent
+	 * other contexts coming in before we are ready:
+	 */
+	old_mode = afu->current_mode;
+	afu->current_mode = 0;
+	afu->num_procs = 0;
+
+	spin_unlock(&afu->contexts_lock);
+
+	if ((rc = _cxl_afu_deactivate_mode(afu, old_mode)))
+		return rc;
+	if ((rc = cxl_afu_activate_mode(afu, mode)))
+		return rc;
+
+	return count;
+err:
+	spin_unlock(&afu->contexts_lock);
+	return rc;
+}
+
+static ssize_t api_version_show(struct device *device,
+				struct device_attribute *attr,
+				char *buf)
+{
+	return scnprintf(buf, PAGE_SIZE, "%i\n", CXL_API_VERSION);
+}
+
+static ssize_t api_version_compatible_show(struct device *device,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	return scnprintf(buf, PAGE_SIZE, "%i\n", CXL_API_VERSION_COMPATIBLE);
+}
+
+static struct device_attribute afu_attrs[] = {
+	__ATTR_RO(mmio_size),
+	__ATTR_RO(irqs_min),
+	__ATTR_RW(irqs_max),
+	__ATTR_RO(modes_supported),
+	__ATTR_RW(mode),
+	__ATTR_RW(prefault_mode),
+	__ATTR_RO(api_version),
+	__ATTR_RO(api_version_compatible),
+	__ATTR(reset, S_IWUSR, NULL, reset_store_afu),
+};
+
+
+
+int cxl_sysfs_adapter_add(struct cxl *adapter)
+{
+	int i, rc;
+
+	for (i = 0; i < ARRAY_SIZE(adapter_attrs); i++) {
+		if ((rc = device_create_file(&adapter->dev, &adapter_attrs[i])))
+			goto err;
+	}
+	return 0;
+err:
+	for (i--; i >= 0; i--)
+		device_remove_file(&adapter->dev, &adapter_attrs[i]);
+	return rc;
+}
+void cxl_sysfs_adapter_remove(struct cxl *adapter)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(adapter_attrs); i++)
+		device_remove_file(&adapter->dev, &adapter_attrs[i]);
+}
+
+int cxl_sysfs_afu_add(struct cxl_afu *afu)
+{
+	int i, rc;
+
+	for (i = 0; i < ARRAY_SIZE(afu_attrs); i++) {
+		if ((rc = device_create_file(&afu->dev, &afu_attrs[i])))
+			goto err;
+	}
+
+	return 0;
+
+err:
+	for (i--; i >= 0; i--)
+		device_remove_file(&afu->dev, &afu_attrs[i]);
+	return rc;
+}
+
+void cxl_sysfs_afu_remove(struct cxl_afu *afu)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(afu_attrs); i++)
+		device_remove_file(&afu->dev, &afu_attrs[i]);
+}
+
+int cxl_sysfs_afu_m_add(struct cxl_afu *afu)
+{
+	int i, rc;
+
+	for (i = 0; i < ARRAY_SIZE(afu_master_attrs); i++) {
+		if ((rc = device_create_file(afu->chardev_m, &afu_master_attrs[i])))
+			goto err;
+	}
+
+	return 0;
+
+err:
+	for (i--; i >= 0; i--)
+		device_remove_file(afu->chardev_m, &afu_master_attrs[i]);
+	return rc;
+}
+
+void cxl_sysfs_afu_m_remove(struct cxl_afu *afu)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(afu_master_attrs); i++)
+		device_remove_file(afu->chardev_m, &afu_master_attrs[i]);
+}
diff --git a/drivers/misc/mic/card/mic_virtio.c b/drivers/misc/mic/card/mic_virtio.c
index f14b60080c21..e64794730e21 100644
--- a/drivers/misc/mic/card/mic_virtio.c
+++ b/drivers/misc/mic/card/mic_virtio.c
@@ -462,16 +462,12 @@ static void mic_handle_config_change(struct mic_device_desc __iomem *d,
 	struct mic_device_ctrl __iomem *dc
 		= (void __iomem *)d + mic_aligned_desc_size(d);
 	struct mic_vdev *mvdev = (struct mic_vdev *)ioread64(&dc->vdev);
-	struct virtio_driver *drv;
 
 	if (ioread8(&dc->config_change) != MIC_VIRTIO_PARAM_CONFIG_CHANGED)
 		return;
 
 	dev_dbg(mdrv->dev, "%s %d\n", __func__, __LINE__);
-	drv = container_of(mvdev->vdev.dev.driver,
-				struct virtio_driver, driver);
-	if (drv->config_changed)
-		drv->config_changed(&mvdev->vdev);
+	virtio_config_changed(&mvdev->vdev);
 	iowrite8(1, &dc->guest_ack);
 }
 
diff --git a/drivers/misc/vmw_vmci/vmci_guest.c b/drivers/misc/vmw_vmci/vmci_guest.c
index 248399a881af..189b32519748 100644
--- a/drivers/misc/vmw_vmci/vmci_guest.c
+++ b/drivers/misc/vmw_vmci/vmci_guest.c
@@ -35,7 +35,6 @@
 #include "vmci_driver.h"
 #include "vmci_event.h"
 
-#define PCI_VENDOR_ID_VMWARE		0x15AD
 #define PCI_DEVICE_ID_VMWARE_VMCI	0x0740
 
 #define VMCI_UTIL_NUM_RESOURCES 1
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index ede41f05c392..1fa4c80ff886 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -977,7 +977,7 @@ static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req,
 		return ERR_CONTINUE;
 
 	/* Now for stop errors.  These aren't fatal to the transfer. */
-	pr_err("%s: error %d sending stop command, original cmd response %#x, card status %#x\n",
+	pr_info("%s: error %d sending stop command, original cmd response %#x, card status %#x\n",
 	       req->rq_disk->disk_name, brq->stop.error,
 	       brq->cmd.resp[0], status);
 
@@ -1398,10 +1398,15 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 		if (disable_multi)
 			brq->data.blocks = 1;
 
-		/* Some controllers can't do multiblock reads due to hw bugs */
-		if (card->host->caps2 & MMC_CAP2_NO_MULTI_READ &&
-		    rq_data_dir(req) == READ)
-			brq->data.blocks = 1;
+		/*
+		 * Some controllers have HW issues while operating
+		 * in multiple I/O mode
+		 */
+		if (card->host->ops->multi_io_quirk)
+			brq->data.blocks = card->host->ops->multi_io_quirk(card,
+						(rq_data_dir(req) == READ) ?
+						MMC_DATA_READ : MMC_DATA_WRITE,
+						brq->data.blocks);
 	}
 
 	if (brq->data.blocks > 1 || do_rel_wr) {
@@ -1923,8 +1928,8 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 		case MMC_BLK_ECC_ERR:
 			if (brq->data.blocks > 1) {
 				/* Redo read one sector at a time */
-				pr_warning("%s: retrying using single block read\n",
-					   req->rq_disk->disk_name);
+				pr_warn("%s: retrying using single block read\n",
+					req->rq_disk->disk_name);
 				disable_multi = 1;
 				break;
 			}
@@ -2131,7 +2136,7 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 	md->disk->queue = md->queue.queue;
 	md->disk->driverfs_dev = parent;
 	set_disk_ro(md->disk, md->read_only || default_ro);
-	if (area_type & MMC_BLK_DATA_AREA_RPMB)
+	if (area_type & (MMC_BLK_DATA_AREA_RPMB | MMC_BLK_DATA_AREA_BOOT))
 		md->disk->flags |= GENHD_FL_NO_PART_SCAN;
 
 	/*
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index 3e049c13429c..cfa6110632c3 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -210,6 +210,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 
 	blk_queue_prep_rq(mq->queue, mmc_prep_request);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue);
+	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, mq->queue);
 	if (mmc_can_erase(card))
 		mmc_queue_setup_discard(mq->queue, card);
 
@@ -229,14 +230,12 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 		if (bouncesz > 512) {
 			mqrq_cur->bounce_buf = kmalloc(bouncesz, GFP_KERNEL);
 			if (!mqrq_cur->bounce_buf) {
-				pr_warning("%s: unable to "
-					"allocate bounce cur buffer\n",
+				pr_warn("%s: unable to allocate bounce cur buffer\n",
 					mmc_card_name(card));
 			}
 			mqrq_prev->bounce_buf = kmalloc(bouncesz, GFP_KERNEL);
 			if (!mqrq_prev->bounce_buf) {
-				pr_warning("%s: unable to "
-					"allocate bounce prev buffer\n",
+				pr_warn("%s: unable to allocate bounce prev buffer\n",
 					mmc_card_name(card));
 				kfree(mqrq_cur->bounce_buf);
 				mqrq_cur->bounce_buf = NULL;
diff --git a/drivers/mmc/card/sdio_uart.c b/drivers/mmc/card/sdio_uart.c
index f093cea0d060..d2de5925b73e 100644
--- a/drivers/mmc/card/sdio_uart.c
+++ b/drivers/mmc/card/sdio_uart.c
@@ -1063,8 +1063,8 @@ static int sdio_uart_probe(struct sdio_func *func,
 		return -ENOMEM;
 
 	if (func->class == SDIO_CLASS_UART) {
-		pr_warning("%s: need info on UART class basic setup\n",
-		       sdio_func_id(func));
+		pr_warn("%s: need info on UART class basic setup\n",
+			sdio_func_id(func));
 		kfree(port);
 		return -ENOSYS;
 	} else if (func->class == SDIO_CLASS_GPS) {
@@ -1082,9 +1082,8 @@ static int sdio_uart_probe(struct sdio_func *func,
 				break;
 		}
 		if (!tpl) {
-			pr_warning(
-       "%s: can't find tuple 0x91 subtuple 0 (SUBTPL_SIOREG) for GPS class\n",
-			       sdio_func_id(func));
+			pr_warn("%s: can't find tuple 0x91 subtuple 0 (SUBTPL_SIOREG) for GPS class\n",
+				sdio_func_id(func));
 			kfree(port);
 			return -EINVAL;
 		}
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index d03a080fb9cd..f26a5f1d926d 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -433,8 +433,8 @@ static void mmc_wait_for_req_done(struct mmc_host *host,
 		 */
 		if (cmd->sanitize_busy && cmd->error == -ETIMEDOUT) {
 			if (!mmc_interrupt_hpi(host->card)) {
-				pr_warning("%s: %s: Interrupted sanitize\n",
-					   mmc_hostname(host), __func__);
+				pr_warn("%s: %s: Interrupted sanitize\n",
+					mmc_hostname(host), __func__);
 				cmd->error = 0;
 				break;
 			} else {
@@ -995,7 +995,7 @@ void mmc_set_chip_select(struct mmc_host *host, int mode)
  */
 static void __mmc_set_clock(struct mmc_host *host, unsigned int hz)
 {
-	WARN_ON(hz < host->f_min);
+	WARN_ON(hz && hz < host->f_min);
 
 	if (hz > host->f_max)
 		hz = host->f_max;
@@ -1221,15 +1221,14 @@ int mmc_regulator_get_ocrmask(struct regulator *supply)
 	int			result = 0;
 	int			count;
 	int			i;
+	int			vdd_uV;
+	int			vdd_mV;
 
 	count = regulator_count_voltages(supply);
 	if (count < 0)
 		return count;
 
 	for (i = 0; i < count; i++) {
-		int		vdd_uV;
-		int		vdd_mV;
-
 		vdd_uV = regulator_list_voltage(supply, i);
 		if (vdd_uV <= 0)
 			continue;
@@ -1238,6 +1237,15 @@ int mmc_regulator_get_ocrmask(struct regulator *supply)
 		result |= mmc_vddrange_to_ocrmask(vdd_mV, vdd_mV);
 	}
 
+	if (!result) {
+		vdd_uV = regulator_get_voltage(supply);
+		if (vdd_uV <= 0)
+			return vdd_uV;
+
+		vdd_mV = vdd_uV / 1000;
+		result = mmc_vddrange_to_ocrmask(vdd_mV, vdd_mV);
+	}
+
 	return result;
 }
 EXPORT_SYMBOL_GPL(mmc_regulator_get_ocrmask);
@@ -1263,7 +1271,6 @@ int mmc_regulator_set_ocr(struct mmc_host *mmc,
 
 	if (vdd_bit) {
 		int		tmp;
-		int		voltage;
 
 		/*
 		 * REVISIT mmc_vddrange_to_ocrmask() may have set some
@@ -1280,22 +1287,7 @@ int mmc_regulator_set_ocr(struct mmc_host *mmc,
 			max_uV = min_uV + 100 * 1000;
 		}
 
-		/*
-		 * If we're using a fixed/static regulator, don't call
-		 * regulator_set_voltage; it would fail.
-		 */
-		voltage = regulator_get_voltage(supply);
-
-		if (!regulator_can_change_voltage(supply))
-			min_uV = max_uV = voltage;
-
-		if (voltage < 0)
-			result = voltage;
-		else if (voltage < min_uV || voltage > max_uV)
-			result = regulator_set_voltage(supply, min_uV, max_uV);
-		else
-			result = 0;
-
+		result = regulator_set_voltage(supply, min_uV, max_uV);
 		if (result == 0 && !mmc->regulator_enabled) {
 			result = regulator_enable(supply);
 			if (!result)
@@ -1425,8 +1417,8 @@ int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage, u32 ocr)
 	if (!host->ops->start_signal_voltage_switch)
 		return -EPERM;
 	if (!host->ops->card_busy)
-		pr_warning("%s: cannot verify signal voltage switch\n",
-				mmc_hostname(host));
+		pr_warn("%s: cannot verify signal voltage switch\n",
+			mmc_hostname(host));
 
 	cmd.opcode = SD_SWITCH_VOLTAGE;
 	cmd.arg = 0;
@@ -1761,7 +1753,7 @@ void mmc_init_erase(struct mmc_card *card)
 		card->erase_shift = ffs(card->ssr.au) - 1;
 	} else if (card->ext_csd.hc_erase_size) {
 		card->pref_erase = card->ext_csd.hc_erase_size;
-	} else {
+	} else if (card->erase_size) {
 		sz = (card->csd.capacity << (card->csd.read_blkbits - 9)) >> 11;
 		if (sz < 128)
 			card->pref_erase = 512 * 1024 / 512;
@@ -1778,7 +1770,8 @@ void mmc_init_erase(struct mmc_card *card)
 			if (sz)
 				card->pref_erase += card->erase_size - sz;
 		}
-	}
+	} else
+		card->pref_erase = 0;
 }
 
 static unsigned int mmc_mmc_erase_timeout(struct mmc_card *card,
@@ -2489,6 +2482,7 @@ void mmc_start_host(struct mmc_host *host)
 {
 	host->f_init = max(freqs[0], host->f_min);
 	host->rescan_disable = 0;
+	host->ios.power_mode = MMC_POWER_UNDEFINED;
 	if (host->caps2 & MMC_CAP2_NO_PRESCAN_POWERUP)
 		mmc_power_off(host);
 	else
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 95cceae96944..03c53b72a2d6 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -310,9 +310,8 @@ int mmc_of_parse(struct mmc_host *host)
 {
 	struct device_node *np;
 	u32 bus_width;
-	bool explicit_inv_wp, gpio_inv_wp = false;
-	enum of_gpio_flags flags;
-	int len, ret, gpio;
+	int len, ret;
+	bool cap_invert, gpio_invert;
 
 	if (!host->parent || !host->parent->of_node)
 		return 0;
@@ -360,59 +359,62 @@ int mmc_of_parse(struct mmc_host *host)
 	if (of_find_property(np, "non-removable", &len)) {
 		host->caps |= MMC_CAP_NONREMOVABLE;
 	} else {
-		bool explicit_inv_cd, gpio_inv_cd = false;
-
-		explicit_inv_cd = of_property_read_bool(np, "cd-inverted");
+		if (of_property_read_bool(np, "cd-inverted"))
+			cap_invert = true;
+		else
+			cap_invert = false;
 
 		if (of_find_property(np, "broken-cd", &len))
 			host->caps |= MMC_CAP_NEEDS_POLL;
 
-		gpio = of_get_named_gpio_flags(np, "cd-gpios", 0, &flags);
-		if (gpio == -EPROBE_DEFER)
-			return gpio;
-		if (gpio_is_valid(gpio)) {
-			if (!(flags & OF_GPIO_ACTIVE_LOW))
-				gpio_inv_cd = true;
-
-			ret = mmc_gpio_request_cd(host, gpio, 0);
-			if (ret < 0) {
-				dev_err(host->parent,
-					"Failed to request CD GPIO #%d: %d!\n",
-					gpio, ret);
+		ret = mmc_gpiod_request_cd(host, "cd", 0, true,
+					   0, &gpio_invert);
+		if (ret) {
+			if (ret == -EPROBE_DEFER)
 				return ret;
-			} else {
-				dev_info(host->parent, "Got CD GPIO #%d.\n",
-					 gpio);
+			if (ret != -ENOENT) {
+				dev_err(host->parent,
+					"Failed to request CD GPIO: %d\n",
+					ret);
 			}
-		}
-
-		if (explicit_inv_cd ^ gpio_inv_cd)
+		} else
+			dev_info(host->parent, "Got CD GPIO\n");
+
+		/*
+		 * There are two ways to flag that the CD line is inverted:
+		 * through the cd-inverted flag and by the GPIO line itself
+		 * being inverted from the GPIO subsystem. This is a leftover
+		 * from the times when the GPIO subsystem did not make it
+		 * possible to flag a line as inverted.
+		 *
+		 * If the capability on the host AND the GPIO line are
+		 * both inverted, the end result is that the CD line is
+		 * not inverted.
+		 */
+		if (cap_invert ^ gpio_invert)
 			host->caps2 |= MMC_CAP2_CD_ACTIVE_HIGH;
 	}
 
 	/* Parse Write Protection */
-	explicit_inv_wp = of_property_read_bool(np, "wp-inverted");
-
-	gpio = of_get_named_gpio_flags(np, "wp-gpios", 0, &flags);
-	if (gpio == -EPROBE_DEFER) {
-		ret = -EPROBE_DEFER;
-		goto out;
-	}
-	if (gpio_is_valid(gpio)) {
-		if (!(flags & OF_GPIO_ACTIVE_LOW))
-			gpio_inv_wp = true;
+	if (of_property_read_bool(np, "wp-inverted"))
+		cap_invert = true;
+	else
+		cap_invert = false;
 
-		ret = mmc_gpio_request_ro(host, gpio);
-		if (ret < 0) {
-			dev_err(host->parent,
-				"Failed to request WP GPIO: %d!\n", ret);
+	ret = mmc_gpiod_request_ro(host, "wp", 0, false, 0, &gpio_invert);
+	if (ret) {
+		if (ret == -EPROBE_DEFER)
 			goto out;
-		} else {
-				dev_info(host->parent, "Got WP GPIO #%d.\n",
-					 gpio);
+		if (ret != -ENOENT) {
+			dev_err(host->parent,
+				"Failed to request WP GPIO: %d\n",
+				ret);
 		}
-	}
-	if (explicit_inv_wp ^ gpio_inv_wp)
+	} else
+		dev_info(host->parent, "Got WP GPIO\n");
+
+	/* See the comment on CD inversion above */
+	if (cap_invert ^ gpio_invert)
 		host->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
 
 	if (of_find_property(np, "cap-sd-highspeed", &len))
@@ -452,6 +454,14 @@ int mmc_of_parse(struct mmc_host *host)
 	if (of_find_property(np, "mmc-hs400-1_2v", &len))
 		host->caps2 |= MMC_CAP2_HS400_1_2V | MMC_CAP2_HS200_1_2V_SDR;
 
+	host->dsr_req = !of_property_read_u32(np, "dsr", &host->dsr);
+	if (host->dsr_req && (host->dsr & ~0xffff)) {
+		dev_err(host->parent,
+			"device tree specified broken value for DSR: 0x%x, ignoring\n",
+			host->dsr);
+		host->dsr_req = 0;
+	}
+
 	return 0;
 
 out:
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 1eda8dd8c867..a301a78a2bd1 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -162,6 +162,7 @@ static int mmc_decode_csd(struct mmc_card *card)
 	csd->read_partial = UNSTUFF_BITS(resp, 79, 1);
 	csd->write_misalign = UNSTUFF_BITS(resp, 78, 1);
 	csd->read_misalign = UNSTUFF_BITS(resp, 77, 1);
+	csd->dsr_imp = UNSTUFF_BITS(resp, 76, 1);
 	csd->r2w_factor = UNSTUFF_BITS(resp, 26, 3);
 	csd->write_blkbits = UNSTUFF_BITS(resp, 22, 4);
 	csd->write_partial = UNSTUFF_BITS(resp, 21, 1);
@@ -225,9 +226,7 @@ static int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd)
 				"Card will be ignored.\n",
 				mmc_hostname(card->host));
 		} else {
-			pr_warning("%s: unable to read "
-				"EXT_CSD, performance might "
-				"suffer.\n",
+			pr_warn("%s: unable to read EXT_CSD, performance might suffer\n",
 				mmc_hostname(card->host));
 			err = 0;
 		}
@@ -298,6 +297,97 @@ static void mmc_select_card_type(struct mmc_card *card)
 	card->mmc_avail_type = avail_type;
 }
 
+static void mmc_manage_enhanced_area(struct mmc_card *card, u8 *ext_csd)
+{
+	u8 hc_erase_grp_sz, hc_wp_grp_sz;
+
+	/*
+	 * Disable these attributes by default
+	 */
+	card->ext_csd.enhanced_area_offset = -EINVAL;
+	card->ext_csd.enhanced_area_size = -EINVAL;
+
+	/*
+	 * Enhanced area feature support -- check whether the eMMC
+	 * card has the Enhanced area enabled.  If so, export enhanced
+	 * area offset and size to user by adding sysfs interface.
+	 */
+	if ((ext_csd[EXT_CSD_PARTITION_SUPPORT] & 0x2) &&
+	    (ext_csd[EXT_CSD_PARTITION_ATTRIBUTE] & 0x1)) {
+		if (card->ext_csd.partition_setting_completed) {
+			hc_erase_grp_sz =
+				ext_csd[EXT_CSD_HC_ERASE_GRP_SIZE];
+			hc_wp_grp_sz =
+				ext_csd[EXT_CSD_HC_WP_GRP_SIZE];
+
+			/*
+			 * calculate the enhanced data area offset, in bytes
+			 */
+			card->ext_csd.enhanced_area_offset =
+				(ext_csd[139] << 24) + (ext_csd[138] << 16) +
+				(ext_csd[137] << 8) + ext_csd[136];
+			if (mmc_card_blockaddr(card))
+				card->ext_csd.enhanced_area_offset <<= 9;
+			/*
+			 * calculate the enhanced data area size, in kilobytes
+			 */
+			card->ext_csd.enhanced_area_size =
+				(ext_csd[142] << 16) + (ext_csd[141] << 8) +
+				ext_csd[140];
+			card->ext_csd.enhanced_area_size *=
+				(size_t)(hc_erase_grp_sz * hc_wp_grp_sz);
+			card->ext_csd.enhanced_area_size <<= 9;
+		} else {
+			pr_warn("%s: defines enhanced area without partition setting complete\n",
+				mmc_hostname(card->host));
+		}
+	}
+}
+
+static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd)
+{
+	int idx;
+	u8 hc_erase_grp_sz, hc_wp_grp_sz;
+	unsigned int part_size;
+
+	/*
+	 * General purpose partition feature support --
+	 * If ext_csd has the size of general purpose partitions,
+	 * set size, part_cfg, partition name in mmc_part.
+	 */
+	if (ext_csd[EXT_CSD_PARTITION_SUPPORT] &
+	    EXT_CSD_PART_SUPPORT_PART_EN) {
+		hc_erase_grp_sz =
+			ext_csd[EXT_CSD_HC_ERASE_GRP_SIZE];
+		hc_wp_grp_sz =
+			ext_csd[EXT_CSD_HC_WP_GRP_SIZE];
+
+		for (idx = 0; idx < MMC_NUM_GP_PARTITION; idx++) {
+			if (!ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3] &&
+			    !ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 1] &&
+			    !ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 2])
+				continue;
+			if (card->ext_csd.partition_setting_completed == 0) {
+				pr_warn("%s: has partition size defined without partition complete\n",
+					mmc_hostname(card->host));
+				break;
+			}
+			part_size =
+				(ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 2]
+				<< 16) +
+				(ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 1]
+				<< 8) +
+				ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3];
+			part_size *= (size_t)(hc_erase_grp_sz *
+				hc_wp_grp_sz);
+			mmc_part_add(card, part_size << 19,
+				EXT_CSD_PART_CONFIG_ACC_GP0 + idx,
+				"gp%d", idx, false,
+				MMC_BLK_DATA_AREA_GP);
+		}
+	}
+}
+
 /*
  * Decode extended CSD.
  */
@@ -305,7 +395,6 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd)
 {
 	int err = 0, idx;
 	unsigned int part_size;
-	u8 hc_erase_grp_sz = 0, hc_wp_grp_sz = 0;
 
 	BUG_ON(!card);
 
@@ -402,80 +491,16 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		ext_csd[EXT_CSD_TRIM_MULT];
 	card->ext_csd.raw_partition_support = ext_csd[EXT_CSD_PARTITION_SUPPORT];
 	if (card->ext_csd.rev >= 4) {
-		/*
-		 * Enhanced area feature support -- check whether the eMMC
-		 * card has the Enhanced area enabled.  If so, export enhanced
-		 * area offset and size to user by adding sysfs interface.
-		 */
-		if ((ext_csd[EXT_CSD_PARTITION_SUPPORT] & 0x2) &&
-		    (ext_csd[EXT_CSD_PARTITION_ATTRIBUTE] & 0x1)) {
-			hc_erase_grp_sz =
-				ext_csd[EXT_CSD_HC_ERASE_GRP_SIZE];
-			hc_wp_grp_sz =
-				ext_csd[EXT_CSD_HC_WP_GRP_SIZE];
+		if (ext_csd[EXT_CSD_PARTITION_SETTING_COMPLETED] &
+		    EXT_CSD_PART_SETTING_COMPLETED)
+			card->ext_csd.partition_setting_completed = 1;
+		else
+			card->ext_csd.partition_setting_completed = 0;
 
-			card->ext_csd.enhanced_area_en = 1;
-			/*
-			 * calculate the enhanced data area offset, in bytes
-			 */
-			card->ext_csd.enhanced_area_offset =
-				(ext_csd[139] << 24) + (ext_csd[138] << 16) +
-				(ext_csd[137] << 8) + ext_csd[136];
-			if (mmc_card_blockaddr(card))
-				card->ext_csd.enhanced_area_offset <<= 9;
-			/*
-			 * calculate the enhanced data area size, in kilobytes
-			 */
-			card->ext_csd.enhanced_area_size =
-				(ext_csd[142] << 16) + (ext_csd[141] << 8) +
-				ext_csd[140];
-			card->ext_csd.enhanced_area_size *=
-				(size_t)(hc_erase_grp_sz * hc_wp_grp_sz);
-			card->ext_csd.enhanced_area_size <<= 9;
-		} else {
-			/*
-			 * If the enhanced area is not enabled, disable these
-			 * device attributes.
-			 */
-			card->ext_csd.enhanced_area_offset = -EINVAL;
-			card->ext_csd.enhanced_area_size = -EINVAL;
-		}
+		mmc_manage_enhanced_area(card, ext_csd);
 
-		/*
-		 * General purpose partition feature support --
-		 * If ext_csd has the size of general purpose partitions,
-		 * set size, part_cfg, partition name in mmc_part.
-		 */
-		if (ext_csd[EXT_CSD_PARTITION_SUPPORT] &
-			EXT_CSD_PART_SUPPORT_PART_EN) {
-			if (card->ext_csd.enhanced_area_en != 1) {
-				hc_erase_grp_sz =
-					ext_csd[EXT_CSD_HC_ERASE_GRP_SIZE];
-				hc_wp_grp_sz =
-					ext_csd[EXT_CSD_HC_WP_GRP_SIZE];
-
-				card->ext_csd.enhanced_area_en = 1;
-			}
+		mmc_manage_gp_partitions(card, ext_csd);
 
-			for (idx = 0; idx < MMC_NUM_GP_PARTITION; idx++) {
-				if (!ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3] &&
-				!ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 1] &&
-				!ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 2])
-					continue;
-				part_size =
-				(ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 2]
-					<< 16) +
-				(ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 1]
-					<< 8) +
-				ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3];
-				part_size *= (size_t)(hc_erase_grp_sz *
-					hc_wp_grp_sz);
-				mmc_part_add(card, part_size << 19,
-					EXT_CSD_PART_CONFIG_ACC_GP0 + idx,
-					"gp%d", idx, false,
-					MMC_BLK_DATA_AREA_GP);
-			}
-		}
 		card->ext_csd.sec_trim_mult =
 			ext_csd[EXT_CSD_SEC_TRIM_MULT];
 		card->ext_csd.sec_erase_mult =
@@ -789,8 +814,8 @@ static int __mmc_select_powerclass(struct mmc_card *card,
 				ext_csd->raw_pwr_cl_200_360;
 		break;
 	default:
-		pr_warning("%s: Voltage range not supported "
-			   "for power class.\n", mmc_hostname(host));
+		pr_warn("%s: Voltage range not supported for power class\n",
+			mmc_hostname(host));
 		return -EINVAL;
 	}
 
@@ -987,19 +1012,35 @@ static int mmc_select_hs_ddr(struct mmc_card *card)
 	 * 1.8V vccq at 3.3V core voltage (vcc) is not required
 	 * in the JEDEC spec for DDR.
 	 *
-	 * Do not force change in vccq since we are obviously
-	 * working and no change to vccq is needed.
+	 * Even (e)MMC card can support 3.3v to 1.2v vccq, but not all
+	 * host controller can support this, like some of the SDHCI
+	 * controller which connect to an eMMC device. Some of these
+	 * host controller still needs to use 1.8v vccq for supporting
+	 * DDR mode.
+	 *
+	 * So the sequence will be:
+	 * if (host and device can both support 1.2v IO)
+	 *	use 1.2v IO;
+	 * else if (host and device can both support 1.8v IO)
+	 *	use 1.8v IO;
+	 * so if host and device can only support 3.3v IO, this is the
+	 * last choice.
 	 *
 	 * WARNING: eMMC rules are NOT the same as SD DDR
 	 */
-	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_DDR_1_2V) {
-		err = __mmc_set_signal_voltage(host,
-				MMC_SIGNAL_VOLTAGE_120);
-		if (err)
-			return err;
-	}
+	err = -EINVAL;
+	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_DDR_1_2V)
+		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
+
+	if (err && (card->mmc_avail_type & EXT_CSD_CARD_TYPE_DDR_1_8V))
+		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180);
 
-	mmc_set_timing(host, MMC_TIMING_MMC_DDR52);
+	/* make sure vccq is 3.3v after switching disaster */
+	if (err)
+		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330);
+
+	if (!err)
+		mmc_set_timing(host, MMC_TIMING_MMC_DDR52);
 
 	return err;
 }
@@ -1134,6 +1175,38 @@ bus_speed:
 	return err;
 }
 
+const u8 tuning_blk_pattern_4bit[MMC_TUNING_BLK_PATTERN_4BIT_SIZE] = {
+	0xff, 0x0f, 0xff, 0x00, 0xff, 0xcc, 0xc3, 0xcc,
+	0xc3, 0x3c, 0xcc, 0xff, 0xfe, 0xff, 0xfe, 0xef,
+	0xff, 0xdf, 0xff, 0xdd, 0xff, 0xfb, 0xff, 0xfb,
+	0xbf, 0xff, 0x7f, 0xff, 0x77, 0xf7, 0xbd, 0xef,
+	0xff, 0xf0, 0xff, 0xf0, 0x0f, 0xfc, 0xcc, 0x3c,
+	0xcc, 0x33, 0xcc, 0xcf, 0xff, 0xef, 0xff, 0xee,
+	0xff, 0xfd, 0xff, 0xfd, 0xdf, 0xff, 0xbf, 0xff,
+	0xbb, 0xff, 0xf7, 0xff, 0xf7, 0x7f, 0x7b, 0xde,
+};
+EXPORT_SYMBOL(tuning_blk_pattern_4bit);
+
+const u8 tuning_blk_pattern_8bit[MMC_TUNING_BLK_PATTERN_8BIT_SIZE] = {
+	0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00, 0x00,
+	0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc, 0xcc,
+	0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff, 0xff,
+	0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee, 0xff,
+	0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd, 0xdd,
+	0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff, 0xbb,
+	0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff, 0xff,
+	0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee, 0xff,
+	0xff, 0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00,
+	0x00, 0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc,
+	0xcc, 0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff,
+	0xff, 0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee,
+	0xff, 0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd,
+	0xdd, 0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff,
+	0xbb, 0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff,
+	0xff, 0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee,
+};
+EXPORT_SYMBOL(tuning_blk_pattern_8bit);
+
 /*
  * Execute tuning sequence to seek the proper bus operating
  * conditions for HS200 and HS400, which sends CMD21 to the device.
@@ -1272,6 +1345,13 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	}
 
 	/*
+	 * handling only for cards supporting DSR and hosts requesting
+	 * DSR configuration
+	 */
+	if (card->csd.dsr_imp && host->dsr_req)
+		mmc_set_dsr(host);
+
+	/*
 	 * Select card, as all following commands rely on that.
 	 */
 	if (!mmc_host_is_spi(host)) {
@@ -1308,7 +1388,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	 * If enhanced_area_en is TRUE, host needs to enable ERASE_GRP_DEF
 	 * bit.  This bit will be lost every time after a reset or power off.
 	 */
-	if (card->ext_csd.enhanced_area_en ||
+	if (card->ext_csd.partition_setting_completed ||
 	    (card->ext_csd.rev >= 3 && (host->caps2 & MMC_CAP2_HC_ERASE_SZ))) {
 		err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 				 EXT_CSD_ERASE_GROUP_DEF, 1,
@@ -1408,8 +1488,8 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		if (err && err != -EBADMSG)
 			goto free_card;
 		if (err) {
-			pr_warning("%s: Enabling HPI failed\n",
-				   mmc_hostname(card->host));
+			pr_warn("%s: Enabling HPI failed\n",
+				mmc_hostname(card->host));
 			err = 0;
 		} else
 			card->ext_csd.hpi_en = 1;
@@ -1430,9 +1510,8 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		 * Only if no error, cache is turned on successfully.
 		 */
 		if (err) {
-			pr_warning("%s: Cache is supported, "
-					"but failed to turn on (%d)\n",
-					mmc_hostname(card->host), err);
+			pr_warn("%s: Cache is supported, but failed to turn on (%d)\n",
+				mmc_hostname(card->host), err);
 			card->ext_csd.cache_ctrl = 0;
 			err = 0;
 		} else {
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index f51b5ba3bbea..7911e0510a1d 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -93,6 +93,26 @@ int mmc_deselect_cards(struct mmc_host *host)
 	return _mmc_select_card(host, NULL);
 }
 
+/*
+ * Write the value specified in the device tree or board code into the optional
+ * 16 bit Driver Stage Register. This can be used to tune raise/fall times and
+ * drive strength of the DAT and CMD outputs. The actual meaning of a given
+ * value is hardware dependant.
+ * The presence of the DSR register can be determined from the CSD register,
+ * bit 76.
+ */
+int mmc_set_dsr(struct mmc_host *host)
+{
+	struct mmc_command cmd = {0};
+
+	cmd.opcode = MMC_SET_DSR;
+
+	cmd.arg = (host->dsr << 16) | 0xffff;
+	cmd.flags = MMC_RSP_NONE | MMC_CMD_AC;
+
+	return mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES);
+}
+
 int mmc_go_idle(struct mmc_host *host)
 {
 	int err;
@@ -629,8 +649,8 @@ int mmc_send_hpi_cmd(struct mmc_card *card, u32 *status)
 	int err;
 
 	if (!card->ext_csd.hpi) {
-		pr_warning("%s: Card didn't support HPI command\n",
-			   mmc_hostname(card->host));
+		pr_warn("%s: Card didn't support HPI command\n",
+			mmc_hostname(card->host));
 		return -EINVAL;
 	}
 
diff --git a/drivers/mmc/core/mmc_ops.h b/drivers/mmc/core/mmc_ops.h
index 80ae9f4e0293..390dac665b2a 100644
--- a/drivers/mmc/core/mmc_ops.h
+++ b/drivers/mmc/core/mmc_ops.h
@@ -14,6 +14,7 @@
 
 int mmc_select_card(struct mmc_card *card);
 int mmc_deselect_cards(struct mmc_host *host);
+int mmc_set_dsr(struct mmc_host *host);
 int mmc_go_idle(struct mmc_host *host);
 int mmc_send_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr);
 int mmc_all_send_cid(struct mmc_host *host, u32 *cid);
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 0c44510bf717..d90a6de7901d 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -127,6 +127,7 @@ static int mmc_decode_csd(struct mmc_card *card)
 		csd->read_partial = UNSTUFF_BITS(resp, 79, 1);
 		csd->write_misalign = UNSTUFF_BITS(resp, 78, 1);
 		csd->read_misalign = UNSTUFF_BITS(resp, 77, 1);
+		csd->dsr_imp = UNSTUFF_BITS(resp, 76, 1);
 		csd->r2w_factor = UNSTUFF_BITS(resp, 26, 3);
 		csd->write_blkbits = UNSTUFF_BITS(resp, 22, 4);
 		csd->write_partial = UNSTUFF_BITS(resp, 21, 1);
@@ -228,8 +229,8 @@ static int mmc_read_ssr(struct mmc_card *card)
 	u32 *ssr;
 
 	if (!(card->csd.cmdclass & CCC_APP_SPEC)) {
-		pr_warning("%s: card lacks mandatory SD Status "
-			"function.\n", mmc_hostname(card->host));
+		pr_warn("%s: card lacks mandatory SD Status function\n",
+			mmc_hostname(card->host));
 		return 0;
 	}
 
@@ -239,8 +240,8 @@ static int mmc_read_ssr(struct mmc_card *card)
 
 	err = mmc_app_sd_status(card, ssr);
 	if (err) {
-		pr_warning("%s: problem reading SD Status "
-			"register.\n", mmc_hostname(card->host));
+		pr_warn("%s: problem reading SD Status register\n",
+			mmc_hostname(card->host));
 		err = 0;
 		goto out;
 	}
@@ -264,8 +265,8 @@ static int mmc_read_ssr(struct mmc_card *card)
 				card->ssr.erase_offset = eo * 1000;
 			}
 		} else {
-			pr_warning("%s: SD Status: Invalid Allocation Unit size.\n",
-				   mmc_hostname(card->host));
+			pr_warn("%s: SD Status: Invalid Allocation Unit size\n",
+				mmc_hostname(card->host));
 		}
 	}
 out:
@@ -285,8 +286,7 @@ static int mmc_read_switch(struct mmc_card *card)
 		return 0;
 
 	if (!(card->csd.cmdclass & CCC_SWITCH)) {
-		pr_warning("%s: card lacks mandatory switch "
-			"function, performance might suffer.\n",
+		pr_warn("%s: card lacks mandatory switch function, performance might suffer\n",
 			mmc_hostname(card->host));
 		return 0;
 	}
@@ -315,7 +315,7 @@ static int mmc_read_switch(struct mmc_card *card)
 		if (err != -EINVAL && err != -ENOSYS && err != -EFAULT)
 			goto out;
 
-		pr_warning("%s: problem reading Bus Speed modes.\n",
+		pr_warn("%s: problem reading Bus Speed modes\n",
 			mmc_hostname(card->host));
 		err = 0;
 
@@ -371,8 +371,7 @@ int mmc_sd_switch_hs(struct mmc_card *card)
 		goto out;
 
 	if ((status[16] & 0xF) != 1) {
-		pr_warning("%s: Problem switching card "
-			"into high-speed mode!\n",
+		pr_warn("%s: Problem switching card into high-speed mode!\n",
 			mmc_hostname(card->host));
 		err = 0;
 	} else {
@@ -439,7 +438,7 @@ static int sd_select_driver_type(struct mmc_card *card, u8 *status)
 		return err;
 
 	if ((status[15] & 0xF) != drive_strength) {
-		pr_warning("%s: Problem setting drive strength!\n",
+		pr_warn("%s: Problem setting drive strength!\n",
 			mmc_hostname(card->host));
 		return 0;
 	}
@@ -517,7 +516,7 @@ static int sd_set_bus_speed_mode(struct mmc_card *card, u8 *status)
 		return err;
 
 	if ((status[16] & 0xF) != card->sd_bus_speed)
-		pr_warning("%s: Problem setting bus speed mode!\n",
+		pr_warn("%s: Problem setting bus speed mode!\n",
 			mmc_hostname(card->host));
 	else {
 		mmc_set_timing(card->host, timing);
@@ -597,7 +596,7 @@ static int sd_set_current_limit(struct mmc_card *card, u8 *status)
 			return err;
 
 		if (((status[15] >> 4) & 0x0F) != current_limit)
-			pr_warning("%s: Problem setting current limit!\n",
+			pr_warn("%s: Problem setting current limit!\n",
 				mmc_hostname(card->host));
 
 	}
@@ -726,8 +725,7 @@ int mmc_sd_get_cid(struct mmc_host *host, u32 ocr, u32 *cid, u32 *rocr)
 try_again:
 	if (!retries) {
 		ocr &= ~SD_OCR_S18R;
-		pr_warning("%s: Skipping voltage switch\n",
-			mmc_hostname(host));
+		pr_warn("%s: Skipping voltage switch\n", mmc_hostname(host));
 	}
 
 	/*
@@ -871,9 +869,7 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
 		}
 
 		if (ro < 0) {
-			pr_warning("%s: host does not "
-				"support reading read-only "
-				"switch. assuming write-enable.\n",
+			pr_warn("%s: host does not support reading read-only switch, assuming write-enable\n",
 				mmc_hostname(host));
 		} else if (ro > 0) {
 			mmc_card_set_readonly(card);
@@ -954,6 +950,13 @@ static int mmc_sd_init_card(struct mmc_host *host, u32 ocr,
 	}
 
 	/*
+	 * handling only for cards supporting DSR and hosts requesting
+	 * DSR configuration
+	 */
+	if (card->csd.dsr_imp && host->dsr_req)
+		mmc_set_dsr(host);
+
+	/*
 	 * Select card, as all following commands rely on that.
 	 */
 	if (!mmc_host_is_spi(host)) {
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index e636d9e99e4a..2439e717655b 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -216,8 +216,8 @@ static int sdio_enable_wide(struct mmc_card *card)
 		return ret;
 
 	if ((ctrl & SDIO_BUS_WIDTH_MASK) == SDIO_BUS_WIDTH_RESERVED)
-		pr_warning("%s: SDIO_CCCR_IF is invalid: 0x%02x\n",
-			   mmc_hostname(card->host), ctrl);
+		pr_warn("%s: SDIO_CCCR_IF is invalid: 0x%02x\n",
+			mmc_hostname(card->host), ctrl);
 
 	/* set as 4-bit bus width */
 	ctrl &= ~SDIO_BUS_WIDTH_MASK;
@@ -605,8 +605,7 @@ static int mmc_sdio_init_card(struct mmc_host *host, u32 ocr,
 
 try_again:
 	if (!retries) {
-		pr_warning("%s: Skipping voltage switch\n",
-				mmc_hostname(host));
+		pr_warn("%s: Skipping voltage switch\n", mmc_hostname(host));
 		ocr &= ~R4_18V_PRESENT;
 	}
 
@@ -992,8 +991,16 @@ static int mmc_sdio_resume(struct mmc_host *host)
 		}
 	}
 
-	if (!err && host->sdio_irqs)
-		wake_up_process(host->sdio_irq_thread);
+	if (!err && host->sdio_irqs) {
+		if (!(host->caps2 & MMC_CAP2_SDIO_IRQ_NOTHREAD)) {
+			wake_up_process(host->sdio_irq_thread);
+		} else if (host->caps & MMC_CAP_SDIO_IRQ) {
+			mmc_host_clk_hold(host);
+			host->ops->enable_sdio_irq(host, 1);
+			mmc_host_clk_release(host);
+		}
+	}
+
 	mmc_release_host(host);
 
 	host->pm_flags &= ~MMC_PM_KEEP_POWER;
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index 4fa8fef9147f..6da97b170563 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/acpi.h>
 
 #include <linux/mmc/card.h>
@@ -177,8 +178,8 @@ static int sdio_bus_remove(struct device *dev)
 	drv->remove(func);
 
 	if (func->irq_handler) {
-		pr_warning("WARNING: driver %s did not remove "
-			"its interrupt handler!\n", drv->name);
+		pr_warn("WARNING: driver %s did not remove its interrupt handler!\n",
+			drv->name);
 		sdio_claim_host(func);
 		sdio_release_irq(func);
 		sdio_release_host(func);
@@ -315,7 +316,7 @@ int sdio_add_func(struct sdio_func *func)
 	ret = device_add(&func->dev);
 	if (ret == 0) {
 		sdio_func_set_present(func);
-		acpi_dev_pm_attach(&func->dev, false);
+		dev_pm_domain_attach(&func->dev, false);
 	}
 
 	return ret;
@@ -332,7 +333,7 @@ void sdio_remove_func(struct sdio_func *func)
 	if (!sdio_func_present(func))
 		return;
 
-	acpi_dev_pm_detach(&func->dev, false);
+	dev_pm_domain_detach(&func->dev, false);
 	device_del(&func->dev);
 	put_device(&func->dev);
 }
diff --git a/drivers/mmc/core/sdio_irq.c b/drivers/mmc/core/sdio_irq.c
index 5cc13c8d35bb..09cc67d028f0 100644
--- a/drivers/mmc/core/sdio_irq.c
+++ b/drivers/mmc/core/sdio_irq.c
@@ -69,16 +69,15 @@ static int process_sdio_pending_irqs(struct mmc_host *host)
 		if (pending & (1 << i)) {
 			func = card->sdio_func[i - 1];
 			if (!func) {
-				pr_warning("%s: pending IRQ for "
-					"non-existent function\n",
+				pr_warn("%s: pending IRQ for non-existent function\n",
 					mmc_card_id(card));
 				ret = -EINVAL;
 			} else if (func->irq_handler) {
 				func->irq_handler(func);
 				count++;
 			} else {
-				pr_warning("%s: pending IRQ with no handler\n",
-				       sdio_func_id(func));
+				pr_warn("%s: pending IRQ with no handler\n",
+					sdio_func_id(func));
 				ret = -EINVAL;
 			}
 		}
@@ -208,7 +207,7 @@ static int sdio_card_irq_get(struct mmc_card *card)
 				host->sdio_irqs--;
 				return err;
 			}
-		} else {
+		} else if (host->caps & MMC_CAP_SDIO_IRQ) {
 			mmc_host_clk_hold(host);
 			host->ops->enable_sdio_irq(host, 1);
 			mmc_host_clk_release(host);
@@ -229,7 +228,7 @@ static int sdio_card_irq_put(struct mmc_card *card)
 		if (!(host->caps2 & MMC_CAP2_SDIO_IRQ_NOTHREAD)) {
 			atomic_set(&host->sdio_irq_thread_abort, 1);
 			kthread_stop(host->sdio_irq_thread);
-		} else {
+		} else if (host->caps & MMC_CAP_SDIO_IRQ) {
 			mmc_host_clk_hold(host);
 			host->ops->enable_sdio_irq(host, 0);
 			mmc_host_clk_release(host);
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 5f89cb83d5f0..69bbf2adb329 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -221,8 +221,6 @@ int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio,
 	ctx->override_cd_active_level = true;
 	ctx->cd_gpio = gpio_to_desc(gpio);
 
-	mmc_gpiod_request_cd_irq(host);
-
 	return 0;
 }
 EXPORT_SYMBOL(mmc_gpio_request_cd);
@@ -283,6 +281,8 @@ EXPORT_SYMBOL(mmc_gpio_free_cd);
  * @idx: index of the GPIO to obtain in the consumer
  * @override_active_level: ignore %GPIO_ACTIVE_LOW flag
  * @debounce: debounce time in microseconds
+ * @gpio_invert: will return whether the GPIO line is inverted or not, set
+ * to NULL to ignore
  *
  * Use this function in place of mmc_gpio_request_cd() to use the GPIO
  * descriptor API.  Note that it is paired with mmc_gpiod_free_cd() not
@@ -293,7 +293,7 @@ EXPORT_SYMBOL(mmc_gpio_free_cd);
  */
 int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
-			 unsigned int debounce)
+			 unsigned int debounce, bool *gpio_invert)
 {
 	struct mmc_gpio *ctx;
 	struct gpio_desc *desc;
@@ -308,20 +308,19 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 	if (!con_id)
 		con_id = ctx->cd_label;
 
-	desc = devm_gpiod_get_index(host->parent, con_id, idx);
+	desc = devm_gpiod_get_index(host->parent, con_id, idx, GPIOD_IN);
 	if (IS_ERR(desc))
 		return PTR_ERR(desc);
 
-	ret = gpiod_direction_input(desc);
-	if (ret < 0)
-		return ret;
-
 	if (debounce) {
 		ret = gpiod_set_debounce(desc, debounce);
 		if (ret < 0)
 			return ret;
 	}
 
+	if (gpio_invert)
+		*gpio_invert = !gpiod_is_active_low(desc);
+
 	ctx->override_cd_active_level = override_active_level;
 	ctx->cd_gpio = desc;
 
@@ -330,6 +329,59 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 EXPORT_SYMBOL(mmc_gpiod_request_cd);
 
 /**
+ * mmc_gpiod_request_ro - request a gpio descriptor for write protection
+ * @host: mmc host
+ * @con_id: function within the GPIO consumer
+ * @idx: index of the GPIO to obtain in the consumer
+ * @override_active_level: ignore %GPIO_ACTIVE_LOW flag
+ * @debounce: debounce time in microseconds
+ * @gpio_invert: will return whether the GPIO line is inverted or not,
+ * set to NULL to ignore
+ *
+ * Use this function in place of mmc_gpio_request_ro() to use the GPIO
+ * descriptor API.  Note that it is paired with mmc_gpiod_free_ro() not
+ * mmc_gpio_free_ro().
+ *
+ * Returns zero on success, else an error.
+ */
+int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
+			 unsigned int idx, bool override_active_level,
+			 unsigned int debounce, bool *gpio_invert)
+{
+	struct mmc_gpio *ctx;
+	struct gpio_desc *desc;
+	int ret;
+
+	ret = mmc_gpio_alloc(host);
+	if (ret < 0)
+		return ret;
+
+	ctx = host->slot.handler_priv;
+
+	if (!con_id)
+		con_id = ctx->ro_label;
+
+	desc = devm_gpiod_get_index(host->parent, con_id, idx, GPIOD_IN);
+	if (IS_ERR(desc))
+		return PTR_ERR(desc);
+
+	if (debounce) {
+		ret = gpiod_set_debounce(desc, debounce);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (gpio_invert)
+		*gpio_invert = !gpiod_is_active_low(desc);
+
+	ctx->override_ro_active_level = override_active_level;
+	ctx->ro_gpio = desc;
+
+	return 0;
+}
+EXPORT_SYMBOL(mmc_gpiod_request_ro);
+
+/**
  * mmc_gpiod_free_cd - free the card-detection gpio descriptor
  * @host: mmc host
  *
@@ -348,7 +400,7 @@ void mmc_gpiod_free_cd(struct mmc_host *host)
 		host->slot.cd_irq = -EINVAL;
 	}
 
-	devm_gpiod_put(&host->class_dev, ctx->cd_gpio);
+	devm_gpiod_put(host->parent, ctx->cd_gpio);
 
 	ctx->cd_gpio = NULL;
 }
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 451135822464..13860656104b 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -14,6 +14,17 @@ config MMC_ARMMMCI
 
 	  If unsure, say N.
 
+config MMC_QCOM_DML
+	tristate "Qualcomm Data Mover for SD Card Controller"
+	depends on MMC_ARMMMCI && QCOM_BAM_DMA
+	default y
+	help
+	  This selects the Qualcomm Data Mover lite/local on SD Card controller.
+	  This option will enable the dma to work correctly, if you are using
+	  Qcom SOCs and MMC, you would probably need this option to get DMA working.
+
+	  if unsure, say N.
+
 config MMC_PXA
 	tristate "Intel PXA25x/26x/27x Multimedia Card Interface support"
 	depends on ARCH_PXA
@@ -568,7 +579,8 @@ config SDH_BFIN_MISSING_CMD_PULLUP_WORKAROUND
 
 config MMC_DW
 	tristate "Synopsys DesignWare Memory Card Interface"
-	depends on ARC || ARM
+	depends on HAS_DMA
+	depends on ARC || ARM || MIPS || COMPILE_TEST
 	help
 	  This selects support for the Synopsys DesignWare Mobile Storage IP
 	  block, this provides host support for SD and MMC interfaces, in both
@@ -626,6 +638,15 @@ config MMC_DW_PCI
 
 	  If unsure, say N.
 
+config MMC_DW_ROCKCHIP
+	tristate "Rockchip specific extensions for Synopsys DW Memory Card Interface"
+	depends on MMC_DW && ARCH_ROCKCHIP
+	select MMC_DW_PLTFM
+	help
+	  This selects support for Rockchip SoC specific extensions to the
+	  Synopsys DesignWare Memory Card Interface driver. Select this option
+	  for platforms based on RK3066, RK3188 and RK3288 SoC's.
+
 config MMC_SH_MMCIF
 	tristate "SuperH Internal MMCIF support"
 	depends on MMC_BLOCK && HAS_DMA
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index f211eede8db5..b09ecfb88269 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -3,6 +3,7 @@
 #
 
 obj-$(CONFIG_MMC_ARMMMCI)	+= mmci.o
+obj-$(CONFIG_MMC_QCOM_DML)	+= mmci_qcom_dml.o
 obj-$(CONFIG_MMC_PXA)		+= pxamci.o
 obj-$(CONFIG_MMC_MXC)		+= mxcmmc.o
 obj-$(CONFIG_MMC_MXS)		+= mxs-mmc.o
@@ -45,6 +46,7 @@ obj-$(CONFIG_MMC_DW_PLTFM)	+= dw_mmc-pltfm.o
 obj-$(CONFIG_MMC_DW_EXYNOS)	+= dw_mmc-exynos.o
 obj-$(CONFIG_MMC_DW_K3)		+= dw_mmc-k3.o
 obj-$(CONFIG_MMC_DW_PCI)	+= dw_mmc-pci.o
+obj-$(CONFIG_MMC_DW_ROCKCHIP)	+= dw_mmc-rockchip.o
 obj-$(CONFIG_MMC_SH_MMCIF)	+= sh_mmcif.o
 obj-$(CONFIG_MMC_JZ4740)	+= jz4740_mmc.o
 obj-$(CONFIG_MMC_VUB300)	+= vub300.o
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index bb585d940901..77250d4b1979 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -17,6 +17,7 @@
 #include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -2195,7 +2196,8 @@ static int __init atmci_init_slot(struct atmel_mci *host,
 	/* Assume card is present initially */
 	set_bit(ATMCI_CARD_PRESENT, &slot->flags);
 	if (gpio_is_valid(slot->detect_pin)) {
-		if (gpio_request(slot->detect_pin, "mmc_detect")) {
+		if (devm_gpio_request(&host->pdev->dev, slot->detect_pin,
+				      "mmc_detect")) {
 			dev_dbg(&mmc->class_dev, "no detect pin available\n");
 			slot->detect_pin = -EBUSY;
 		} else if (gpio_get_value(slot->detect_pin) ^
@@ -2208,7 +2210,8 @@ static int __init atmci_init_slot(struct atmel_mci *host,
 		mmc->caps |= MMC_CAP_NEEDS_POLL;
 
 	if (gpio_is_valid(slot->wp_pin)) {
-		if (gpio_request(slot->wp_pin, "mmc_wp")) {
+		if (devm_gpio_request(&host->pdev->dev, slot->wp_pin,
+				      "mmc_wp")) {
 			dev_dbg(&mmc->class_dev, "no WP pin available\n");
 			slot->wp_pin = -EBUSY;
 		}
@@ -2232,7 +2235,6 @@ static int __init atmci_init_slot(struct atmel_mci *host,
 			dev_dbg(&mmc->class_dev,
 				"could not request IRQ %d for detect pin\n",
 				gpio_to_irq(slot->detect_pin));
-			gpio_free(slot->detect_pin);
 			slot->detect_pin = -EBUSY;
 		}
 	}
@@ -2242,7 +2244,7 @@ static int __init atmci_init_slot(struct atmel_mci *host,
 	return 0;
 }
 
-static void __exit atmci_cleanup_slot(struct atmel_mci_slot *slot,
+static void atmci_cleanup_slot(struct atmel_mci_slot *slot,
 		unsigned int id)
 {
 	/* Debugfs stuff is cleaned up by mmc core */
@@ -2257,10 +2259,7 @@ static void __exit atmci_cleanup_slot(struct atmel_mci_slot *slot,
 
 		free_irq(gpio_to_irq(pin), slot);
 		del_timer_sync(&slot->detect_timer);
-		gpio_free(pin);
 	}
-	if (gpio_is_valid(slot->wp_pin))
-		gpio_free(slot->wp_pin);
 
 	slot->host->slot[id] = NULL;
 	mmc_free_host(slot->mmc);
@@ -2344,6 +2343,7 @@ static void __init atmci_get_cap(struct atmel_mci *host)
 
 	/* keep only major version number */
 	switch (version & 0xf00) {
+	case 0x600:
 	case 0x500:
 		host->caps.has_odd_clk_div = 1;
 	case 0x400:
@@ -2377,7 +2377,7 @@ static int __init atmci_probe(struct platform_device *pdev)
 	struct resource			*regs;
 	unsigned int			nr_slots;
 	int				irq;
-	int				ret;
+	int				ret, i;
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!regs)
@@ -2395,7 +2395,7 @@ static int __init atmci_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return irq;
 
-	host = kzalloc(sizeof(struct atmel_mci), GFP_KERNEL);
+	host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL);
 	if (!host)
 		return -ENOMEM;
 
@@ -2403,20 +2403,18 @@ static int __init atmci_probe(struct platform_device *pdev)
 	spin_lock_init(&host->lock);
 	INIT_LIST_HEAD(&host->queue);
 
-	host->mck = clk_get(&pdev->dev, "mci_clk");
-	if (IS_ERR(host->mck)) {
-		ret = PTR_ERR(host->mck);
-		goto err_clk_get;
-	}
+	host->mck = devm_clk_get(&pdev->dev, "mci_clk");
+	if (IS_ERR(host->mck))
+		return PTR_ERR(host->mck);
 
-	ret = -ENOMEM;
-	host->regs = ioremap(regs->start, resource_size(regs));
+	host->regs = devm_ioremap(&pdev->dev, regs->start, resource_size(regs));
 	if (!host->regs)
-		goto err_ioremap;
+		return -ENOMEM;
 
 	ret = clk_prepare_enable(host->mck);
 	if (ret)
-		goto err_request_irq;
+		return ret;
+
 	atmci_writel(host, ATMCI_CR, ATMCI_CR_SWRST);
 	host->bus_hz = clk_get_rate(host->mck);
 	clk_disable_unprepare(host->mck);
@@ -2427,7 +2425,7 @@ static int __init atmci_probe(struct platform_device *pdev)
 
 	ret = request_irq(irq, atmci_interrupt, 0, dev_name(&pdev->dev), host);
 	if (ret)
-		goto err_request_irq;
+		return ret;
 
 	/* Get MCI capabilities and set operations according to it */
 	atmci_get_cap(host);
@@ -2485,7 +2483,7 @@ static int __init atmci_probe(struct platform_device *pdev)
 		if (!host->buffer) {
 			ret = -ENOMEM;
 			dev_err(&pdev->dev, "buffer allocation failed\n");
-			goto err_init_slot;
+			goto err_dma_alloc;
 		}
 	}
 
@@ -2495,16 +2493,16 @@ static int __init atmci_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_dma_alloc:
+	for (i = 0; i < ATMCI_MAX_NR_SLOTS; i++) {
+		if (host->slot[i])
+			atmci_cleanup_slot(host->slot[i], i);
+	}
 err_init_slot:
+	del_timer_sync(&host->timer);
 	if (host->dma.chan)
 		dma_release_channel(host->dma.chan);
 	free_irq(irq, host);
-err_request_irq:
-	iounmap(host->regs);
-err_ioremap:
-	clk_put(host->mck);
-err_clk_get:
-	kfree(host);
 	return ret;
 }
 
@@ -2528,14 +2526,11 @@ static int __exit atmci_remove(struct platform_device *pdev)
 	atmci_readl(host, ATMCI_SR);
 	clk_disable_unprepare(host->mck);
 
+	del_timer_sync(&host->timer);
 	if (host->dma.chan)
 		dma_release_channel(host->dma.chan);
 
 	free_irq(platform_get_irq(pdev, 0), host);
-	iounmap(host->regs);
-
-	clk_put(host->mck);
-	kfree(host);
 
 	return 0;
 }
diff --git a/drivers/mmc/host/au1xmmc.c b/drivers/mmc/host/au1xmmc.c
index 9c9f6af29251..725f6a6fd89b 100644
--- a/drivers/mmc/host/au1xmmc.c
+++ b/drivers/mmc/host/au1xmmc.c
@@ -1028,9 +1028,12 @@ static int au1xmmc_probe(struct platform_device *pdev)
 	host->clk = clk_get(&pdev->dev, ALCHEMY_PERIPH_CLK);
 	if (IS_ERR(host->clk)) {
 		dev_err(&pdev->dev, "cannot find clock\n");
+		ret = PTR_ERR(host->clk);
 		goto out_irq;
 	}
-	if (clk_prepare_enable(host->clk)) {
+
+	ret = clk_prepare_enable(host->clk);
+	if (ret) {
 		dev_err(&pdev->dev, "cannot enable clock\n");
 		goto out_clk;
 	}
diff --git a/drivers/mmc/host/dw_mmc-pci.c b/drivers/mmc/host/dw_mmc-pci.c
index 6ada1b36685b..4c69fbd29811 100644
--- a/drivers/mmc/host/dw_mmc-pci.c
+++ b/drivers/mmc/host/dw_mmc-pci.c
@@ -95,9 +95,6 @@ static int dw_mci_pci_resume(struct device *dev)
 
 	return dw_mci_resume(host);
 }
-#else
-#define dw_mci_pci_suspend	NULL
-#define dw_mci_pci_resume	NULL
 #endif /* CONFIG_PM_SLEEP */
 
 static SIMPLE_DEV_PM_OPS(dw_mci_pci_pmops, dw_mci_pci_suspend, dw_mci_pci_resume);
diff --git a/drivers/mmc/host/dw_mmc-pltfm.c b/drivers/mmc/host/dw_mmc-pltfm.c
index d4a47a9f5584..8b6572162ed9 100644
--- a/drivers/mmc/host/dw_mmc-pltfm.c
+++ b/drivers/mmc/host/dw_mmc-pltfm.c
@@ -21,6 +21,7 @@
 #include <linux/mmc/mmc.h>
 #include <linux/mmc/dw_mmc.h>
 #include <linux/of.h>
+#include <linux/clk.h>
 
 #include "dw_mmc.h"
 #include "dw_mmc-pltfm.h"
@@ -30,10 +31,6 @@ static void dw_mci_pltfm_prepare_command(struct dw_mci *host, u32 *cmdr)
 	*cmdr |= SDMMC_CMD_USE_HOLD_REG;
 }
 
-static const struct dw_mci_drv_data rockchip_drv_data = {
-	.prepare_command	= dw_mci_pltfm_prepare_command,
-};
-
 static const struct dw_mci_drv_data socfpga_drv_data = {
 	.prepare_command	= dw_mci_pltfm_prepare_command,
 };
@@ -84,9 +81,6 @@ static int dw_mci_pltfm_resume(struct device *dev)
 
 	return dw_mci_resume(host);
 }
-#else
-#define dw_mci_pltfm_suspend	NULL
-#define dw_mci_pltfm_resume	NULL
 #endif /* CONFIG_PM_SLEEP */
 
 SIMPLE_DEV_PM_OPS(dw_mci_pltfm_pmops, dw_mci_pltfm_suspend, dw_mci_pltfm_resume);
@@ -94,8 +88,6 @@ EXPORT_SYMBOL_GPL(dw_mci_pltfm_pmops);
 
 static const struct of_device_id dw_mci_pltfm_match[] = {
 	{ .compatible = "snps,dw-mshc", },
-	{ .compatible = "rockchip,rk2928-dw-mshc",
-		.data = &rockchip_drv_data },
 	{ .compatible = "altr,socfpga-dw-mshc",
 		.data = &socfpga_drv_data },
 	{},
diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
new file mode 100644
index 000000000000..f0c2cb1a210d
--- /dev/null
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -0,0 +1,136 @@
+/*
+ * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/dw_mmc.h>
+#include <linux/of_address.h>
+
+#include "dw_mmc.h"
+#include "dw_mmc-pltfm.h"
+
+#define RK3288_CLKGEN_DIV       2
+
+static void dw_mci_rockchip_prepare_command(struct dw_mci *host, u32 *cmdr)
+{
+	*cmdr |= SDMMC_CMD_USE_HOLD_REG;
+}
+
+static int dw_mci_rk3288_setup_clock(struct dw_mci *host)
+{
+	host->bus_hz /= RK3288_CLKGEN_DIV;
+
+	return 0;
+}
+
+static void dw_mci_rk3288_set_ios(struct dw_mci *host, struct mmc_ios *ios)
+{
+	int ret;
+	unsigned int cclkin;
+	u32 bus_hz;
+
+	/*
+	 * cclkin: source clock of mmc controller
+	 * bus_hz: card interface clock generated by CLKGEN
+	 * bus_hz = cclkin / RK3288_CLKGEN_DIV
+	 * ios->clock = (div == 0) ? bus_hz : (bus_hz / (2 * div))
+	 *
+	 * Note: div can only be 0 or 1
+	 *       if DDR50 8bit mode(only emmc work in 8bit mode),
+	 *       div must be set 1
+	 */
+	if (ios->bus_width == MMC_BUS_WIDTH_8 &&
+	    ios->timing == MMC_TIMING_MMC_DDR52)
+		cclkin = 2 * ios->clock * RK3288_CLKGEN_DIV;
+	else
+		cclkin = ios->clock * RK3288_CLKGEN_DIV;
+
+	ret = clk_set_rate(host->ciu_clk, cclkin);
+	if (ret)
+		dev_warn(host->dev, "failed to set rate %uHz\n", ios->clock);
+
+	bus_hz = clk_get_rate(host->ciu_clk) / RK3288_CLKGEN_DIV;
+	if (bus_hz != host->bus_hz) {
+		host->bus_hz = bus_hz;
+		/* force dw_mci_setup_bus() */
+		host->current_speed = 0;
+	}
+}
+
+static const struct dw_mci_drv_data rk2928_drv_data = {
+	.prepare_command        = dw_mci_rockchip_prepare_command,
+};
+
+static const struct dw_mci_drv_data rk3288_drv_data = {
+	.prepare_command        = dw_mci_rockchip_prepare_command,
+	.set_ios		= dw_mci_rk3288_set_ios,
+	.setup_clock    = dw_mci_rk3288_setup_clock,
+};
+
+static const struct of_device_id dw_mci_rockchip_match[] = {
+	{ .compatible = "rockchip,rk2928-dw-mshc",
+		.data = &rk2928_drv_data },
+	{ .compatible = "rockchip,rk3288-dw-mshc",
+		.data = &rk3288_drv_data },
+	{},
+};
+MODULE_DEVICE_TABLE(of, dw_mci_rockchip_match);
+
+static int dw_mci_rockchip_probe(struct platform_device *pdev)
+{
+	const struct dw_mci_drv_data *drv_data;
+	const struct of_device_id *match;
+
+	if (!pdev->dev.of_node)
+		return -ENODEV;
+
+	match = of_match_node(dw_mci_rockchip_match, pdev->dev.of_node);
+	drv_data = match->data;
+
+	return dw_mci_pltfm_register(pdev, drv_data);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int dw_mci_rockchip_suspend(struct device *dev)
+{
+	struct dw_mci *host = dev_get_drvdata(dev);
+
+	return dw_mci_suspend(host);
+}
+
+static int dw_mci_rockchip_resume(struct device *dev)
+{
+	struct dw_mci *host = dev_get_drvdata(dev);
+
+	return dw_mci_resume(host);
+}
+#endif /* CONFIG_PM_SLEEP */
+
+static SIMPLE_DEV_PM_OPS(dw_mci_rockchip_pmops,
+			 dw_mci_rockchip_suspend,
+			 dw_mci_rockchip_resume);
+
+static struct platform_driver dw_mci_rockchip_pltfm_driver = {
+	.probe		= dw_mci_rockchip_probe,
+	.remove		= __exit_p(dw_mci_pltfm_remove),
+	.driver		= {
+		.name		= "dwmmc_rockchip",
+		.of_match_table	= dw_mci_rockchip_match,
+		.pm		= &dw_mci_rockchip_pmops,
+	},
+};
+
+module_platform_driver(dw_mci_rockchip_pltfm_driver);
+
+MODULE_AUTHOR("Addy Ke <addy.ke@rock-chips.com>");
+MODULE_DESCRIPTION("Rockchip Specific DW-MSHC Driver Extension");
+MODULE_ALIAS("platform:dwmmc-rockchip");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 8f216edbdf08..69f0cc68d5b2 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -29,6 +29,7 @@
 #include <linux/irq.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
+#include <linux/mmc/sd.h>
 #include <linux/mmc/sdio.h>
 #include <linux/mmc/dw_mmc.h>
 #include <linux/bitops.h>
@@ -81,36 +82,6 @@ struct idmac_desc {
 };
 #endif /* CONFIG_MMC_DW_IDMAC */
 
-static const u8 tuning_blk_pattern_4bit[] = {
-	0xff, 0x0f, 0xff, 0x00, 0xff, 0xcc, 0xc3, 0xcc,
-	0xc3, 0x3c, 0xcc, 0xff, 0xfe, 0xff, 0xfe, 0xef,
-	0xff, 0xdf, 0xff, 0xdd, 0xff, 0xfb, 0xff, 0xfb,
-	0xbf, 0xff, 0x7f, 0xff, 0x77, 0xf7, 0xbd, 0xef,
-	0xff, 0xf0, 0xff, 0xf0, 0x0f, 0xfc, 0xcc, 0x3c,
-	0xcc, 0x33, 0xcc, 0xcf, 0xff, 0xef, 0xff, 0xee,
-	0xff, 0xfd, 0xff, 0xfd, 0xdf, 0xff, 0xbf, 0xff,
-	0xbb, 0xff, 0xf7, 0xff, 0xf7, 0x7f, 0x7b, 0xde,
-};
-
-static const u8 tuning_blk_pattern_8bit[] = {
-	0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00, 0x00,
-	0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc, 0xcc,
-	0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff, 0xff,
-	0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee, 0xff,
-	0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd, 0xdd,
-	0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff, 0xbb,
-	0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff, 0xff,
-	0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee, 0xff,
-	0xff, 0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00,
-	0x00, 0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc,
-	0xcc, 0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff,
-	0xff, 0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee,
-	0xff, 0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd,
-	0xdd, 0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff,
-	0xbb, 0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff,
-	0xff, 0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee,
-};
-
 static bool dw_mci_reset(struct dw_mci *host);
 
 #if defined(CONFIG_DEBUG_FS)
@@ -234,10 +205,13 @@ err:
 }
 #endif /* defined(CONFIG_DEBUG_FS) */
 
+static void mci_send_cmd(struct dw_mci_slot *slot, u32 cmd, u32 arg);
+
 static u32 dw_mci_prepare_command(struct mmc_host *mmc, struct mmc_command *cmd)
 {
 	struct mmc_data	*data;
 	struct dw_mci_slot *slot = mmc_priv(mmc);
+	struct dw_mci *host = slot->host;
 	const struct dw_mci_drv_data *drv_data = slot->host->drv_data;
 	u32 cmdr;
 	cmd->error = -EINPROGRESS;
@@ -253,6 +227,34 @@ static u32 dw_mci_prepare_command(struct mmc_host *mmc, struct mmc_command *cmd)
 	else if (cmd->opcode != MMC_SEND_STATUS && cmd->data)
 		cmdr |= SDMMC_CMD_PRV_DAT_WAIT;
 
+	if (cmd->opcode == SD_SWITCH_VOLTAGE) {
+		u32 clk_en_a;
+
+		/* Special bit makes CMD11 not die */
+		cmdr |= SDMMC_CMD_VOLT_SWITCH;
+
+		/* Change state to continue to handle CMD11 weirdness */
+		WARN_ON(slot->host->state != STATE_SENDING_CMD);
+		slot->host->state = STATE_SENDING_CMD11;
+
+		/*
+		 * We need to disable low power mode (automatic clock stop)
+		 * while doing voltage switch so we don't confuse the card,
+		 * since stopping the clock is a specific part of the UHS
+		 * voltage change dance.
+		 *
+		 * Note that low power mode (SDMMC_CLKEN_LOW_PWR) will be
+		 * unconditionally turned back on in dw_mci_setup_bus() if it's
+		 * ever called with a non-zero clock.  That shouldn't happen
+		 * until the voltage change is all done.
+		 */
+		clk_en_a = mci_readl(host, CLKENA);
+		clk_en_a &= ~(SDMMC_CLKEN_LOW_PWR << slot->id);
+		mci_writel(host, CLKENA, clk_en_a);
+		mci_send_cmd(slot, SDMMC_CMD_UPD_CLK |
+			     SDMMC_CMD_PRV_DAT_WAIT, 0);
+	}
+
 	if (cmd->flags & MMC_RSP_PRESENT) {
 		/* We expect a response, so set this bit */
 		cmdr |= SDMMC_CMD_RESP_EXP;
@@ -775,11 +777,15 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 	unsigned int clock = slot->clock;
 	u32 div;
 	u32 clk_en_a;
+	u32 sdmmc_cmd_bits = SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT;
+
+	/* We must continue to set bit 28 in CMD until the change is complete */
+	if (host->state == STATE_WAITING_CMD11_DONE)
+		sdmmc_cmd_bits |= SDMMC_CMD_VOLT_SWITCH;
 
 	if (!clock) {
 		mci_writel(host, CLKENA, 0);
-		mci_send_cmd(slot,
-			     SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT, 0);
+		mci_send_cmd(slot, sdmmc_cmd_bits, 0);
 	} else if (clock != host->current_speed || force_clkinit) {
 		div = host->bus_hz / clock;
 		if (host->bus_hz % clock && host->bus_hz > clock)
@@ -803,15 +809,13 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 		mci_writel(host, CLKSRC, 0);
 
 		/* inform CIU */
-		mci_send_cmd(slot,
-			     SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT, 0);
+		mci_send_cmd(slot, sdmmc_cmd_bits, 0);
 
 		/* set clock to desired speed */
 		mci_writel(host, CLKDIV, div);
 
 		/* inform CIU */
-		mci_send_cmd(slot,
-			     SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT, 0);
+		mci_send_cmd(slot, sdmmc_cmd_bits, 0);
 
 		/* enable clock; only low power if no SDIO */
 		clk_en_a = SDMMC_CLKEN_ENABLE << slot->id;
@@ -820,8 +824,7 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 		mci_writel(host, CLKENA, clk_en_a);
 
 		/* inform CIU */
-		mci_send_cmd(slot,
-			     SDMMC_CMD_UPD_CLK | SDMMC_CMD_PRV_DAT_WAIT, 0);
+		mci_send_cmd(slot, sdmmc_cmd_bits, 0);
 
 		/* keep the clock with reflecting clock dividor */
 		slot->__clk_old = clock << div;
@@ -897,6 +900,17 @@ static void dw_mci_queue_request(struct dw_mci *host, struct dw_mci_slot *slot,
 
 	slot->mrq = mrq;
 
+	if (host->state == STATE_WAITING_CMD11_DONE) {
+		dev_warn(&slot->mmc->class_dev,
+			 "Voltage change didn't complete\n");
+		/*
+		 * this case isn't expected to happen, so we can
+		 * either crash here or just try to continue on
+		 * in the closest possible state
+		 */
+		host->state = STATE_IDLE;
+	}
+
 	if (host->state == STATE_IDLE) {
 		host->state = STATE_SENDING_CMD;
 		dw_mci_start_request(host, slot);
@@ -936,6 +950,7 @@ static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	struct dw_mci_slot *slot = mmc_priv(mmc);
 	const struct dw_mci_drv_data *drv_data = slot->host->drv_data;
 	u32 regs;
+	int ret;
 
 	switch (ios->bus_width) {
 	case MMC_BUS_WIDTH_4:
@@ -972,14 +987,43 @@ static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	/* Slot specific timing and width adjustment */
 	dw_mci_setup_bus(slot, false);
 
+	if (slot->host->state == STATE_WAITING_CMD11_DONE && ios->clock != 0)
+		slot->host->state = STATE_IDLE;
+
 	switch (ios->power_mode) {
 	case MMC_POWER_UP:
+		if (!IS_ERR(mmc->supply.vmmc)) {
+			ret = mmc_regulator_set_ocr(mmc, mmc->supply.vmmc,
+					ios->vdd);
+			if (ret) {
+				dev_err(slot->host->dev,
+					"failed to enable vmmc regulator\n");
+				/*return, if failed turn on vmmc*/
+				return;
+			}
+		}
+		if (!IS_ERR(mmc->supply.vqmmc) && !slot->host->vqmmc_enabled) {
+			ret = regulator_enable(mmc->supply.vqmmc);
+			if (ret < 0)
+				dev_err(slot->host->dev,
+					"failed to enable vqmmc regulator\n");
+			else
+				slot->host->vqmmc_enabled = true;
+		}
 		set_bit(DW_MMC_CARD_NEED_INIT, &slot->flags);
 		regs = mci_readl(slot->host, PWREN);
 		regs |= (1 << slot->id);
 		mci_writel(slot->host, PWREN, regs);
 		break;
 	case MMC_POWER_OFF:
+		if (!IS_ERR(mmc->supply.vmmc))
+			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
+
+		if (!IS_ERR(mmc->supply.vqmmc) && slot->host->vqmmc_enabled) {
+			regulator_disable(mmc->supply.vqmmc);
+			slot->host->vqmmc_enabled = false;
+		}
+
 		regs = mci_readl(slot->host, PWREN);
 		regs &= ~(1 << slot->id);
 		mci_writel(slot->host, PWREN, regs);
@@ -989,6 +1033,59 @@ static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	}
 }
 
+static int dw_mci_card_busy(struct mmc_host *mmc)
+{
+	struct dw_mci_slot *slot = mmc_priv(mmc);
+	u32 status;
+
+	/*
+	 * Check the busy bit which is low when DAT[3:0]
+	 * (the data lines) are 0000
+	 */
+	status = mci_readl(slot->host, STATUS);
+
+	return !!(status & SDMMC_STATUS_BUSY);
+}
+
+static int dw_mci_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct dw_mci_slot *slot = mmc_priv(mmc);
+	struct dw_mci *host = slot->host;
+	u32 uhs;
+	u32 v18 = SDMMC_UHS_18V << slot->id;
+	int min_uv, max_uv;
+	int ret;
+
+	/*
+	 * Program the voltage.  Note that some instances of dw_mmc may use
+	 * the UHS_REG for this.  For other instances (like exynos) the UHS_REG
+	 * does no harm but you need to set the regulator directly.  Try both.
+	 */
+	uhs = mci_readl(host, UHS_REG);
+	if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) {
+		min_uv = 2700000;
+		max_uv = 3600000;
+		uhs &= ~v18;
+	} else {
+		min_uv = 1700000;
+		max_uv = 1950000;
+		uhs |= v18;
+	}
+	if (!IS_ERR(mmc->supply.vqmmc)) {
+		ret = regulator_set_voltage(mmc->supply.vqmmc, min_uv, max_uv);
+
+		if (ret) {
+			dev_err(&mmc->class_dev,
+					 "Regulator set error %d: %d - %d\n",
+					 ret, min_uv, max_uv);
+			return ret;
+		}
+	}
+	mci_writel(host, UHS_REG, uhs);
+
+	return 0;
+}
+
 static int dw_mci_get_ro(struct mmc_host *mmc)
 {
 	int read_only;
@@ -1131,6 +1228,9 @@ static const struct mmc_host_ops dw_mci_ops = {
 	.get_cd			= dw_mci_get_cd,
 	.enable_sdio_irq	= dw_mci_enable_sdio_irq,
 	.execute_tuning		= dw_mci_execute_tuning,
+	.card_busy		= dw_mci_card_busy,
+	.start_signal_voltage_switch = dw_mci_switch_voltage,
+
 };
 
 static void dw_mci_request_end(struct dw_mci *host, struct mmc_request *mrq)
@@ -1154,7 +1254,11 @@ static void dw_mci_request_end(struct dw_mci *host, struct mmc_request *mrq)
 		dw_mci_start_request(host, slot);
 	} else {
 		dev_vdbg(host->dev, "list empty\n");
-		host->state = STATE_IDLE;
+
+		if (host->state == STATE_SENDING_CMD11)
+			host->state = STATE_WAITING_CMD11_DONE;
+		else
+			host->state = STATE_IDLE;
 	}
 
 	spin_unlock(&host->lock);
@@ -1265,8 +1369,10 @@ static void dw_mci_tasklet_func(unsigned long priv)
 
 		switch (state) {
 		case STATE_IDLE:
+		case STATE_WAITING_CMD11_DONE:
 			break;
 
+		case STATE_SENDING_CMD11:
 		case STATE_SENDING_CMD:
 			if (!test_and_clear_bit(EVENT_CMD_COMPLETE,
 						&host->pending_events))
@@ -1299,6 +1405,14 @@ static void dw_mci_tasklet_func(unsigned long priv)
 			/* fall through */
 
 		case STATE_SENDING_DATA:
+			/*
+			 * We could get a data error and never a transfer
+			 * complete so we'd better check for it here.
+			 *
+			 * Note that we don't really care if we also got a
+			 * transfer complete; stopping the DMA and sending an
+			 * abort won't hurt.
+			 */
 			if (test_and_clear_bit(EVENT_DATA_ERROR,
 					       &host->pending_events)) {
 				dw_mci_stop_dma(host);
@@ -1312,7 +1426,29 @@ static void dw_mci_tasklet_func(unsigned long priv)
 				break;
 
 			set_bit(EVENT_XFER_COMPLETE, &host->completed_events);
+
+			/*
+			 * Handle an EVENT_DATA_ERROR that might have shown up
+			 * before the transfer completed.  This might not have
+			 * been caught by the check above because the interrupt
+			 * could have gone off between the previous check and
+			 * the check for transfer complete.
+			 *
+			 * Technically this ought not be needed assuming we
+			 * get a DATA_COMPLETE eventually (we'll notice the
+			 * error and end the request), but it shouldn't hurt.
+			 *
+			 * This has the advantage of sending the stop command.
+			 */
+			if (test_and_clear_bit(EVENT_DATA_ERROR,
+					       &host->pending_events)) {
+				dw_mci_stop_dma(host);
+				send_stop_abort(host, data);
+				state = STATE_DATA_ERROR;
+				break;
+			}
 			prev_state = state = STATE_DATA_BUSY;
+
 			/* fall through */
 
 		case STATE_DATA_BUSY:
@@ -1335,6 +1471,22 @@ static void dw_mci_tasklet_func(unsigned long priv)
 				/* stop command for open-ended transfer*/
 				if (data->stop)
 					send_stop_abort(host, data);
+			} else {
+				/*
+				 * If we don't have a command complete now we'll
+				 * never get one since we just reset everything;
+				 * better end the request.
+				 *
+				 * If we do have a command complete we'll fall
+				 * through to the SENDING_STOP command and
+				 * everything will be peachy keen.
+				 */
+				if (!test_bit(EVENT_CMD_COMPLETE,
+					      &host->pending_events)) {
+					host->cmd = NULL;
+					dw_mci_request_end(host, mrq);
+					goto unlock;
+				}
 			}
 
 			/*
@@ -1821,6 +1973,14 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 	}
 
 	if (pending) {
+		/* Check volt switch first, since it can look like an error */
+		if ((host->state == STATE_SENDING_CMD11) &&
+		    (pending & SDMMC_INT_VOLT_SWITCH)) {
+			mci_writel(host, RINTSTS, SDMMC_INT_VOLT_SWITCH);
+			pending &= ~SDMMC_INT_VOLT_SWITCH;
+			dw_mci_cmd_interrupt(host, pending);
+		}
+
 		if (pending & DW_MCI_CMD_ERROR_FLAGS) {
 			mci_writel(host, RINTSTS, DW_MCI_CMD_ERROR_FLAGS);
 			host->cmd_status = pending;
@@ -1926,7 +2086,9 @@ static void dw_mci_work_routine_card(struct work_struct *work)
 
 					switch (host->state) {
 					case STATE_IDLE:
+					case STATE_WAITING_CMD11_DONE:
 						break;
+					case STATE_SENDING_CMD11:
 					case STATE_SENDING_CMD:
 						mrq->cmd->error = -ENOMEDIUM;
 						if (!mrq->data)
@@ -2028,10 +2190,6 @@ static int dw_mci_of_get_slot_quirks(struct device *dev, u8 slot)
 {
 	return 0;
 }
-static struct device_node *dw_mci_of_find_slot_node(struct device *dev, u8 slot)
-{
-	return NULL;
-}
 #endif /* CONFIG_OF */
 
 static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
@@ -2064,7 +2222,13 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 		mmc->f_max = freq[1];
 	}
 
-	mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
+	/*if there are external regulators, get them*/
+	ret = mmc_regulator_get_supply(mmc);
+	if (ret == -EPROBE_DEFER)
+		goto err_host_allocated;
+
+	if (!mmc->ocr_avail)
+		mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
 
 	if (host->pdata->caps)
 		mmc->caps = host->pdata->caps;
@@ -2085,7 +2249,9 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	if (host->pdata->caps2)
 		mmc->caps2 = host->pdata->caps2;
 
-	mmc_of_parse(mmc);
+	ret = mmc_of_parse(mmc);
+	if (ret)
+		goto err_host_allocated;
 
 	if (host->pdata->blk_settings) {
 		mmc->max_segs = host->pdata->blk_settings->max_segs;
@@ -2117,7 +2283,7 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 
 	ret = mmc_add_host(mmc);
 	if (ret)
-		goto err_setup_bus;
+		goto err_host_allocated;
 
 #if defined(CONFIG_DEBUG_FS)
 	dw_mci_init_debugfs(slot);
@@ -2128,9 +2294,9 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 
 	return 0;
 
-err_setup_bus:
+err_host_allocated:
 	mmc_free_host(mmc);
-	return -EINVAL;
+	return ret;
 }
 
 static void dw_mci_cleanup_slot(struct dw_mci_slot *slot, unsigned int id)
@@ -2423,24 +2589,6 @@ int dw_mci_probe(struct dw_mci *host)
 		}
 	}
 
-	host->vmmc = devm_regulator_get_optional(host->dev, "vmmc");
-	if (IS_ERR(host->vmmc)) {
-		ret = PTR_ERR(host->vmmc);
-		if (ret == -EPROBE_DEFER)
-			goto err_clk_ciu;
-
-		dev_info(host->dev, "no vmmc regulator found: %d\n", ret);
-		host->vmmc = NULL;
-	} else {
-		ret = regulator_enable(host->vmmc);
-		if (ret) {
-			if (ret != -EPROBE_DEFER)
-				dev_err(host->dev,
-					"regulator_enable fail: %d\n", ret);
-			goto err_clk_ciu;
-		}
-	}
-
 	host->quirks = host->pdata->quirks;
 
 	spin_lock_init(&host->lock);
@@ -2584,8 +2732,6 @@ err_workqueue:
 err_dmaunmap:
 	if (host->use_dma && host->dma_ops->exit)
 		host->dma_ops->exit(host);
-	if (host->vmmc)
-		regulator_disable(host->vmmc);
 
 err_clk_ciu:
 	if (!IS_ERR(host->ciu_clk))
@@ -2621,9 +2767,6 @@ void dw_mci_remove(struct dw_mci *host)
 	if (host->use_dma && host->dma_ops->exit)
 		host->dma_ops->exit(host);
 
-	if (host->vmmc)
-		regulator_disable(host->vmmc);
-
 	if (!IS_ERR(host->ciu_clk))
 		clk_disable_unprepare(host->ciu_clk);
 
@@ -2640,9 +2783,6 @@ EXPORT_SYMBOL(dw_mci_remove);
  */
 int dw_mci_suspend(struct dw_mci *host)
 {
-	if (host->vmmc)
-		regulator_disable(host->vmmc);
-
 	return 0;
 }
 EXPORT_SYMBOL(dw_mci_suspend);
@@ -2651,15 +2791,6 @@ int dw_mci_resume(struct dw_mci *host)
 {
 	int i, ret;
 
-	if (host->vmmc) {
-		ret = regulator_enable(host->vmmc);
-		if (ret) {
-			dev_err(host->dev,
-				"failed to enable regulator: %d\n", ret);
-			return ret;
-		}
-	}
-
 	if (!dw_mci_ctrl_reset(host, SDMMC_CTRL_ALL_RESET_FLAGS)) {
 		ret = -ENODEV;
 		return ret;
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index 08fd956d81f3..01b99e8a9190 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -99,6 +99,7 @@
 #define SDMMC_INT_HLE			BIT(12)
 #define SDMMC_INT_FRUN			BIT(11)
 #define SDMMC_INT_HTO			BIT(10)
+#define SDMMC_INT_VOLT_SWITCH		BIT(10) /* overloads bit 10! */
 #define SDMMC_INT_DRTO			BIT(9)
 #define SDMMC_INT_RTO			BIT(8)
 #define SDMMC_INT_DCRC			BIT(7)
@@ -113,6 +114,7 @@
 /* Command register defines */
 #define SDMMC_CMD_START			BIT(31)
 #define SDMMC_CMD_USE_HOLD_REG	BIT(29)
+#define SDMMC_CMD_VOLT_SWITCH		BIT(28)
 #define SDMMC_CMD_CCS_EXP		BIT(23)
 #define SDMMC_CMD_CEATA_RD		BIT(22)
 #define SDMMC_CMD_UPD_CLK		BIT(21)
@@ -130,6 +132,7 @@
 /* Status register defines */
 #define SDMMC_GET_FCNT(x)		(((x)>>17) & 0x1FFF)
 #define SDMMC_STATUS_DMA_REQ		BIT(31)
+#define SDMMC_STATUS_BUSY		BIT(9)
 /* FIFOTH register defines */
 #define SDMMC_SET_FIFOTH(m, r, t)	(((m) & 0x7) << 28 | \
 					 ((r) & 0xFFF) << 16 | \
@@ -150,7 +153,7 @@
 #define SDMMC_GET_VERID(x)		((x) & 0xFFFF)
 /* Card read threshold */
 #define SDMMC_SET_RD_THLD(v, x)		(((v) & 0x1FFF) << 16 | (x))
-
+#define SDMMC_UHS_18V			BIT(0)
 /* All ctrl reset bits */
 #define SDMMC_CTRL_ALL_RESET_FLAGS \
 	(SDMMC_CTRL_RESET | SDMMC_CTRL_FIFO_RESET | SDMMC_CTRL_DMA_RESET)
diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c
index 537d6c7a5ae4..76e8bce6f46e 100644
--- a/drivers/mmc/host/jz4740_mmc.c
+++ b/drivers/mmc/host/jz4740_mmc.c
@@ -30,7 +30,9 @@
 #include <asm/mach-jz4740/gpio.h>
 #include <asm/cacheflush.h>
 #include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
 
+#include <asm/mach-jz4740/dma.h>
 #include <asm/mach-jz4740/jz4740_mmc.h>
 
 #define JZ_REG_MMC_STRPCL	0x00
@@ -112,6 +114,11 @@ enum jz4740_mmc_state {
 	JZ4740_MMC_STATE_DONE,
 };
 
+struct jz4740_mmc_host_next {
+	int sg_len;
+	s32 cookie;
+};
+
 struct jz4740_mmc_host {
 	struct mmc_host *mmc;
 	struct platform_device *pdev;
@@ -122,6 +129,7 @@ struct jz4740_mmc_host {
 	int card_detect_irq;
 
 	void __iomem *base;
+	struct resource *mem_res;
 	struct mmc_request *req;
 	struct mmc_command *cmd;
 
@@ -136,8 +144,220 @@ struct jz4740_mmc_host {
 	struct timer_list timeout_timer;
 	struct sg_mapping_iter miter;
 	enum jz4740_mmc_state state;
+
+	/* DMA support */
+	struct dma_chan *dma_rx;
+	struct dma_chan *dma_tx;
+	struct jz4740_mmc_host_next next_data;
+	bool use_dma;
+	int sg_len;
+
+/* The DMA trigger level is 8 words, that is to say, the DMA read
+ * trigger is when data words in MSC_RXFIFO is >= 8 and the DMA write
+ * trigger is when data words in MSC_TXFIFO is < 8.
+ */
+#define JZ4740_MMC_FIFO_HALF_SIZE 8
 };
 
+/*----------------------------------------------------------------------------*/
+/* DMA infrastructure */
+
+static void jz4740_mmc_release_dma_channels(struct jz4740_mmc_host *host)
+{
+	if (!host->use_dma)
+		return;
+
+	dma_release_channel(host->dma_tx);
+	dma_release_channel(host->dma_rx);
+}
+
+static int jz4740_mmc_acquire_dma_channels(struct jz4740_mmc_host *host)
+{
+	dma_cap_mask_t mask;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	host->dma_tx = dma_request_channel(mask, NULL, host);
+	if (!host->dma_tx) {
+		dev_err(mmc_dev(host->mmc), "Failed to get dma_tx channel\n");
+		return -ENODEV;
+	}
+
+	host->dma_rx = dma_request_channel(mask, NULL, host);
+	if (!host->dma_rx) {
+		dev_err(mmc_dev(host->mmc), "Failed to get dma_rx channel\n");
+		goto free_master_write;
+	}
+
+	/* Initialize DMA pre request cookie */
+	host->next_data.cookie = 1;
+
+	return 0;
+
+free_master_write:
+	dma_release_channel(host->dma_tx);
+	return -ENODEV;
+}
+
+static inline int jz4740_mmc_get_dma_dir(struct mmc_data *data)
+{
+	return (data->flags & MMC_DATA_READ) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+}
+
+static inline struct dma_chan *jz4740_mmc_get_dma_chan(struct jz4740_mmc_host *host,
+						       struct mmc_data *data)
+{
+	return (data->flags & MMC_DATA_READ) ? host->dma_rx : host->dma_tx;
+}
+
+static void jz4740_mmc_dma_unmap(struct jz4740_mmc_host *host,
+				 struct mmc_data *data)
+{
+	struct dma_chan *chan = jz4740_mmc_get_dma_chan(host, data);
+	enum dma_data_direction dir = jz4740_mmc_get_dma_dir(data);
+
+	dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, dir);
+}
+
+/* Prepares DMA data for current/next transfer, returns non-zero on failure */
+static int jz4740_mmc_prepare_dma_data(struct jz4740_mmc_host *host,
+				       struct mmc_data *data,
+				       struct jz4740_mmc_host_next *next,
+				       struct dma_chan *chan)
+{
+	struct jz4740_mmc_host_next *next_data = &host->next_data;
+	enum dma_data_direction dir = jz4740_mmc_get_dma_dir(data);
+	int sg_len;
+
+	if (!next && data->host_cookie &&
+	    data->host_cookie != host->next_data.cookie) {
+		dev_warn(mmc_dev(host->mmc),
+			 "[%s] invalid cookie: data->host_cookie %d host->next_data.cookie %d\n",
+			 __func__,
+			 data->host_cookie,
+			 host->next_data.cookie);
+		data->host_cookie = 0;
+	}
+
+	/* Check if next job is already prepared */
+	if (next || data->host_cookie != host->next_data.cookie) {
+		sg_len = dma_map_sg(chan->device->dev,
+				    data->sg,
+				    data->sg_len,
+				    dir);
+
+	} else {
+		sg_len = next_data->sg_len;
+		next_data->sg_len = 0;
+	}
+
+	if (sg_len <= 0) {
+		dev_err(mmc_dev(host->mmc),
+			"Failed to map scatterlist for DMA operation\n");
+		return -EINVAL;
+	}
+
+	if (next) {
+		next->sg_len = sg_len;
+		data->host_cookie = ++next->cookie < 0 ? 1 : next->cookie;
+	} else
+		host->sg_len = sg_len;
+
+	return 0;
+}
+
+static int jz4740_mmc_start_dma_transfer(struct jz4740_mmc_host *host,
+					 struct mmc_data *data)
+{
+	int ret;
+	struct dma_chan *chan;
+	struct dma_async_tx_descriptor *desc;
+	struct dma_slave_config conf = {
+		.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+		.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+		.src_maxburst = JZ4740_MMC_FIFO_HALF_SIZE,
+		.dst_maxburst = JZ4740_MMC_FIFO_HALF_SIZE,
+	};
+
+	if (data->flags & MMC_DATA_WRITE) {
+		conf.direction = DMA_MEM_TO_DEV;
+		conf.dst_addr = host->mem_res->start + JZ_REG_MMC_TXFIFO;
+		conf.slave_id = JZ4740_DMA_TYPE_MMC_TRANSMIT;
+		chan = host->dma_tx;
+	} else {
+		conf.direction = DMA_DEV_TO_MEM;
+		conf.src_addr = host->mem_res->start + JZ_REG_MMC_RXFIFO;
+		conf.slave_id = JZ4740_DMA_TYPE_MMC_RECEIVE;
+		chan = host->dma_rx;
+	}
+
+	ret = jz4740_mmc_prepare_dma_data(host, data, NULL, chan);
+	if (ret)
+		return ret;
+
+	dmaengine_slave_config(chan, &conf);
+	desc = dmaengine_prep_slave_sg(chan,
+				       data->sg,
+				       host->sg_len,
+				       conf.direction,
+				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc) {
+		dev_err(mmc_dev(host->mmc),
+			"Failed to allocate DMA %s descriptor",
+			 conf.direction == DMA_MEM_TO_DEV ? "TX" : "RX");
+		goto dma_unmap;
+	}
+
+	dmaengine_submit(desc);
+	dma_async_issue_pending(chan);
+
+	return 0;
+
+dma_unmap:
+	jz4740_mmc_dma_unmap(host, data);
+	return -ENOMEM;
+}
+
+static void jz4740_mmc_pre_request(struct mmc_host *mmc,
+				   struct mmc_request *mrq,
+				   bool is_first_req)
+{
+	struct jz4740_mmc_host *host = mmc_priv(mmc);
+	struct mmc_data *data = mrq->data;
+	struct jz4740_mmc_host_next *next_data = &host->next_data;
+
+	BUG_ON(data->host_cookie);
+
+	if (host->use_dma) {
+		struct dma_chan *chan = jz4740_mmc_get_dma_chan(host, data);
+
+		if (jz4740_mmc_prepare_dma_data(host, data, next_data, chan))
+			data->host_cookie = 0;
+	}
+}
+
+static void jz4740_mmc_post_request(struct mmc_host *mmc,
+				    struct mmc_request *mrq,
+				    int err)
+{
+	struct jz4740_mmc_host *host = mmc_priv(mmc);
+	struct mmc_data *data = mrq->data;
+
+	if (host->use_dma && data->host_cookie) {
+		jz4740_mmc_dma_unmap(host, data);
+		data->host_cookie = 0;
+	}
+
+	if (err) {
+		struct dma_chan *chan = jz4740_mmc_get_dma_chan(host, data);
+
+		dmaengine_terminate_all(chan);
+	}
+}
+
+/*----------------------------------------------------------------------------*/
+
 static void jz4740_mmc_set_irq_enabled(struct jz4740_mmc_host *host,
 	unsigned int irq, bool enabled)
 {
@@ -442,6 +662,8 @@ static void jz4740_mmc_send_command(struct jz4740_mmc_host *host,
 			cmdat |= JZ_MMC_CMDAT_WRITE;
 		if (cmd->data->flags & MMC_DATA_STREAM)
 			cmdat |= JZ_MMC_CMDAT_STREAM;
+		if (host->use_dma)
+			cmdat |= JZ_MMC_CMDAT_DMA_EN;
 
 		writew(cmd->data->blksz, host->base + JZ_REG_MMC_BLKLEN);
 		writew(cmd->data->blocks, host->base + JZ_REG_MMC_NOB);
@@ -474,6 +696,7 @@ static irqreturn_t jz_mmc_irq_worker(int irq, void *devid)
 	struct jz4740_mmc_host *host = (struct jz4740_mmc_host *)devid;
 	struct mmc_command *cmd = host->req->cmd;
 	struct mmc_request *req = host->req;
+	struct mmc_data *data = cmd->data;
 	bool timeout = false;
 
 	if (cmd->error)
@@ -484,23 +707,37 @@ static irqreturn_t jz_mmc_irq_worker(int irq, void *devid)
 		if (cmd->flags & MMC_RSP_PRESENT)
 			jz4740_mmc_read_response(host, cmd);
 
-		if (!cmd->data)
+		if (!data)
 			break;
 
 		jz_mmc_prepare_data_transfer(host);
 
 	case JZ4740_MMC_STATE_TRANSFER_DATA:
-		if (cmd->data->flags & MMC_DATA_READ)
-			timeout = jz4740_mmc_read_data(host, cmd->data);
+		if (host->use_dma) {
+			/* Use DMA if enabled.
+			 * Data transfer direction is defined later by
+			 * relying on data flags in
+			 * jz4740_mmc_prepare_dma_data() and
+			 * jz4740_mmc_start_dma_transfer().
+			 */
+			timeout = jz4740_mmc_start_dma_transfer(host, data);
+			data->bytes_xfered = data->blocks * data->blksz;
+		} else if (data->flags & MMC_DATA_READ)
+			/* Use PIO if DMA is not enabled.
+			 * Data transfer direction was defined before
+			 * by relying on data flags in
+			 * jz_mmc_prepare_data_transfer().
+			 */
+			timeout = jz4740_mmc_read_data(host, data);
 		else
-			timeout = jz4740_mmc_write_data(host, cmd->data);
+			timeout = jz4740_mmc_write_data(host, data);
 
 		if (unlikely(timeout)) {
 			host->state = JZ4740_MMC_STATE_TRANSFER_DATA;
 			break;
 		}
 
-		jz4740_mmc_transfer_check_state(host, cmd->data);
+		jz4740_mmc_transfer_check_state(host, data);
 
 		timeout = jz4740_mmc_poll_irq(host, JZ_MMC_IRQ_DATA_TRAN_DONE);
 		if (unlikely(timeout)) {
@@ -664,6 +901,8 @@ static void jz4740_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
 
 static const struct mmc_host_ops jz4740_mmc_ops = {
 	.request	= jz4740_mmc_request,
+	.pre_req	= jz4740_mmc_pre_request,
+	.post_req	= jz4740_mmc_post_request,
 	.set_ios	= jz4740_mmc_set_ios,
 	.get_ro		= mmc_gpio_get_ro,
 	.get_cd		= mmc_gpio_get_cd,
@@ -757,7 +996,6 @@ static int jz4740_mmc_probe(struct platform_device* pdev)
 	struct mmc_host *mmc;
 	struct jz4740_mmc_host *host;
 	struct jz4740_mmc_platform_data *pdata;
-	struct resource *res;
 
 	pdata = pdev->dev.platform_data;
 
@@ -784,10 +1022,11 @@ static int jz4740_mmc_probe(struct platform_device* pdev)
 		goto err_free_host;
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	host->base = devm_ioremap_resource(&pdev->dev, res);
+	host->mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	host->base = devm_ioremap_resource(&pdev->dev, host->mem_res);
 	if (IS_ERR(host->base)) {
 		ret = PTR_ERR(host->base);
+		dev_err(&pdev->dev, "Failed to ioremap base memory\n");
 		goto err_free_host;
 	}
 
@@ -834,6 +1073,10 @@ static int jz4740_mmc_probe(struct platform_device* pdev)
 	/* It is not important when it times out, it just needs to timeout. */
 	set_timer_slack(&host->timeout_timer, HZ);
 
+	host->use_dma = true;
+	if (host->use_dma && jz4740_mmc_acquire_dma_channels(host) != 0)
+		host->use_dma = false;
+
 	platform_set_drvdata(pdev, host);
 	ret = mmc_add_host(mmc);
 
@@ -843,6 +1086,10 @@ static int jz4740_mmc_probe(struct platform_device* pdev)
 	}
 	dev_info(&pdev->dev, "JZ SD/MMC card driver registered\n");
 
+	dev_info(&pdev->dev, "Using %s, %d-bit mode\n",
+		 host->use_dma ? "DMA" : "PIO",
+		 (mmc->caps & MMC_CAP_4_BIT_DATA) ? 4 : 1);
+
 	return 0;
 
 err_free_irq:
@@ -850,6 +1097,8 @@ err_free_irq:
 err_free_gpios:
 	jz4740_mmc_free_gpios(pdev);
 err_gpio_bulk_free:
+	if (host->use_dma)
+		jz4740_mmc_release_dma_channels(host);
 	jz_gpio_bulk_free(jz4740_mmc_pins, jz4740_mmc_num_pins(host));
 err_free_host:
 	mmc_free_host(mmc);
@@ -872,6 +1121,9 @@ static int jz4740_mmc_remove(struct platform_device *pdev)
 	jz4740_mmc_free_gpios(pdev);
 	jz_gpio_bulk_free(jz4740_mmc_pins, jz4740_mmc_num_pins(host));
 
+	if (host->use_dma)
+		jz4740_mmc_release_dma_channels(host);
+
 	mmc_free_host(host->mmc);
 
 	return 0;
@@ -909,7 +1161,6 @@ static struct platform_driver jz4740_mmc_driver = {
 	.remove = jz4740_mmc_remove,
 	.driver = {
 		.name = "jz4740-mmc",
-		.owner = THIS_MODULE,
 		.pm = JZ4740_MMC_PM_OPS,
 	},
 };
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index cc8d4a6099cd..e4a07546f8b6 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1436,6 +1436,7 @@ static int mmc_spi_probe(struct spi_device *spi)
 					     host->pdata->cd_debounce);
 		if (status != 0)
 			goto fail_add_host;
+		mmc_gpiod_request_cd_irq(mmc);
 	}
 
 	if (host->pdata && host->pdata->flags & MMC_SPI_USE_RO_GPIO) {
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index e4d470704150..43af791e2e45 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -43,6 +43,7 @@
 #include <asm/sizes.h>
 
 #include "mmci.h"
+#include "mmci_qcom_dml.h"
 
 #define DRIVER_NAME "mmci-pl18x"
 
@@ -60,12 +61,13 @@ static unsigned int fmax = 515633;
  * @fifohalfsize: number of bytes that can be written when MCI_TXFIFOHALFEMPTY
  *		  is asserted (likewise for RX)
  * @data_cmd_enable: enable value for data commands.
- * @sdio: variant supports SDIO
+ * @st_sdio: enable ST specific SDIO logic
  * @st_clkdiv: true if using a ST-specific clock divider algorithm
  * @datactrl_mask_ddrmode: ddr mode mask in datactrl register.
  * @blksz_datactrl16: true if Block size is at b16..b30 position in datactrl register
  * @blksz_datactrl4: true if Block size is at b4..b16 position in datactrl
  *		     register
+ * @datactrl_mask_sdio: SDIO enable mask in datactrl register
  * @pwrreg_powerup: power up value for MMCIPOWER register
  * @f_max: maximum clk frequency supported by the controller.
  * @signal_direction: input/out direction of bus signals can be indicated
@@ -74,6 +76,7 @@ static unsigned int fmax = 515633;
  * @pwrreg_nopower: bits in MMCIPOWER don't controls ext. power supply
  * @explicit_mclk_control: enable explicit mclk control in driver.
  * @qcom_fifo: enables qcom specific fifo pio read logic.
+ * @qcom_dml: enables qcom specific dma glue for dma transfers.
  * @reversed_irq_handling: handle data irq before cmd irq.
  */
 struct variant_data {
@@ -86,7 +89,8 @@ struct variant_data {
 	unsigned int		fifohalfsize;
 	unsigned int		data_cmd_enable;
 	unsigned int		datactrl_mask_ddrmode;
-	bool			sdio;
+	unsigned int		datactrl_mask_sdio;
+	bool			st_sdio;
 	bool			st_clkdiv;
 	bool			blksz_datactrl16;
 	bool			blksz_datactrl4;
@@ -98,6 +102,7 @@ struct variant_data {
 	bool			pwrreg_nopower;
 	bool			explicit_mclk_control;
 	bool			qcom_fifo;
+	bool			qcom_dml;
 	bool			reversed_irq_handling;
 };
 
@@ -133,7 +138,8 @@ static struct variant_data variant_u300 = {
 	.clkreg_enable		= MCI_ST_U300_HWFCEN,
 	.clkreg_8bit_bus_enable = MCI_ST_8BIT_BUS,
 	.datalength_bits	= 16,
-	.sdio			= true,
+	.datactrl_mask_sdio	= MCI_ST_DPSM_SDIOEN,
+	.st_sdio			= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.f_max			= 100000000,
 	.signal_direction	= true,
@@ -146,7 +152,8 @@ static struct variant_data variant_nomadik = {
 	.fifohalfsize		= 8 * 4,
 	.clkreg			= MCI_CLK_ENABLE,
 	.datalength_bits	= 24,
-	.sdio			= true,
+	.datactrl_mask_sdio	= MCI_ST_DPSM_SDIOEN,
+	.st_sdio		= true,
 	.st_clkdiv		= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.f_max			= 100000000,
@@ -163,7 +170,8 @@ static struct variant_data variant_ux500 = {
 	.clkreg_8bit_bus_enable = MCI_ST_8BIT_BUS,
 	.clkreg_neg_edge_enable	= MCI_ST_UX500_NEG_EDGE,
 	.datalength_bits	= 24,
-	.sdio			= true,
+	.datactrl_mask_sdio	= MCI_ST_DPSM_SDIOEN,
+	.st_sdio		= true,
 	.st_clkdiv		= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.f_max			= 100000000,
@@ -182,7 +190,8 @@ static struct variant_data variant_ux500v2 = {
 	.clkreg_neg_edge_enable	= MCI_ST_UX500_NEG_EDGE,
 	.datactrl_mask_ddrmode	= MCI_ST_DPSM_DDRMODE,
 	.datalength_bits	= 24,
-	.sdio			= true,
+	.datactrl_mask_sdio	= MCI_ST_DPSM_SDIOEN,
+	.st_sdio		= true,
 	.st_clkdiv		= true,
 	.blksz_datactrl16	= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
@@ -208,6 +217,7 @@ static struct variant_data variant_qcom = {
 	.f_max			= 208000000,
 	.explicit_mclk_control	= true,
 	.qcom_fifo		= true,
+	.qcom_dml		= true,
 };
 
 static int mmci_card_busy(struct mmc_host *mmc)
@@ -421,6 +431,7 @@ static void mmci_dma_setup(struct mmci_host *host)
 {
 	const char *rxname, *txname;
 	dma_cap_mask_t mask;
+	struct variant_data *variant = host->variant;
 
 	host->dma_rx_channel = dma_request_slave_channel(mmc_dev(host->mmc), "rx");
 	host->dma_tx_channel = dma_request_slave_channel(mmc_dev(host->mmc), "tx");
@@ -471,6 +482,10 @@ static void mmci_dma_setup(struct mmci_host *host)
 		if (max_seg_size < host->mmc->max_seg_size)
 			host->mmc->max_seg_size = max_seg_size;
 	}
+
+	if (variant->qcom_dml && host->dma_rx_channel && host->dma_tx_channel)
+		if (dml_hw_init(host, host->mmc->parent->of_node))
+			variant->qcom_dml = false;
 }
 
 /*
@@ -572,6 +587,7 @@ static int __mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
 	struct dma_async_tx_descriptor *desc;
 	enum dma_data_direction buffer_dirn;
 	int nr_sg;
+	unsigned long flags = DMA_CTRL_ACK;
 
 	if (data->flags & MMC_DATA_READ) {
 		conf.direction = DMA_DEV_TO_MEM;
@@ -596,9 +612,12 @@ static int __mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
 	if (nr_sg == 0)
 		return -EINVAL;
 
+	if (host->variant->qcom_dml)
+		flags |= DMA_PREP_INTERRUPT;
+
 	dmaengine_slave_config(chan, &conf);
 	desc = dmaengine_prep_slave_sg(chan, data->sg, nr_sg,
-					    conf.direction, DMA_CTRL_ACK);
+					    conf.direction, flags);
 	if (!desc)
 		goto unmap_exit;
 
@@ -647,6 +666,9 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
 	dmaengine_submit(host->dma_desc_current);
 	dma_async_issue_pending(host->dma_current);
 
+	if (host->variant->qcom_dml)
+		dml_start_xfer(host, data);
+
 	datactrl |= MCI_DPSM_DMAENABLE;
 
 	/* Trigger the DMA transfer */
@@ -792,32 +814,26 @@ static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
 	if (data->flags & MMC_DATA_READ)
 		datactrl |= MCI_DPSM_DIRECTION;
 
-	/* The ST Micro variants has a special bit to enable SDIO */
-	if (variant->sdio && host->mmc->card)
-		if (mmc_card_sdio(host->mmc->card)) {
-			/*
-			 * The ST Micro variants has a special bit
-			 * to enable SDIO.
-			 */
-			u32 clk;
+	if (host->mmc->card && mmc_card_sdio(host->mmc->card)) {
+		u32 clk;
 
-			datactrl |= MCI_ST_DPSM_SDIOEN;
+		datactrl |= variant->datactrl_mask_sdio;
 
-			/*
-			 * The ST Micro variant for SDIO small write transfers
-			 * needs to have clock H/W flow control disabled,
-			 * otherwise the transfer will not start. The threshold
-			 * depends on the rate of MCLK.
-			 */
-			if (data->flags & MMC_DATA_WRITE &&
-			    (host->size < 8 ||
-			     (host->size <= 8 && host->mclk > 50000000)))
-				clk = host->clk_reg & ~variant->clkreg_enable;
-			else
-				clk = host->clk_reg | variant->clkreg_enable;
+		/*
+		 * The ST Micro variant for SDIO small write transfers
+		 * needs to have clock H/W flow control disabled,
+		 * otherwise the transfer will not start. The threshold
+		 * depends on the rate of MCLK.
+		 */
+		if (variant->st_sdio && data->flags & MMC_DATA_WRITE &&
+		    (host->size < 8 ||
+		     (host->size <= 8 && host->mclk > 50000000)))
+			clk = host->clk_reg & ~variant->clkreg_enable;
+		else
+			clk = host->clk_reg | variant->clkreg_enable;
 
-			mmci_write_clkreg(host, clk);
-		}
+		mmci_write_clkreg(host, clk);
+	}
 
 	if (host->mmc->ios.timing == MMC_TIMING_UHS_DDR50 ||
 	    host->mmc->ios.timing == MMC_TIMING_MMC_DDR52)
@@ -1658,16 +1674,35 @@ static int mmci_probe(struct amba_device *dev,
 	writel(0, host->base + MMCIMASK1);
 	writel(0xfff, host->base + MMCICLEAR);
 
-	/* If DT, cd/wp gpios must be supplied through it. */
-	if (!np && gpio_is_valid(plat->gpio_cd)) {
-		ret = mmc_gpio_request_cd(mmc, plat->gpio_cd, 0);
-		if (ret)
-			goto clk_disable;
-	}
-	if (!np && gpio_is_valid(plat->gpio_wp)) {
-		ret = mmc_gpio_request_ro(mmc, plat->gpio_wp);
-		if (ret)
-			goto clk_disable;
+	/*
+	 * If:
+	 * - not using DT but using a descriptor table, or
+	 * - using a table of descriptors ALONGSIDE DT, or
+	 * look up these descriptors named "cd" and "wp" right here, fail
+	 * silently of these do not exist and proceed to try platform data
+	 */
+	if (!np) {
+		ret = mmc_gpiod_request_cd(mmc, "cd", 0, false, 0, NULL);
+		if (ret < 0) {
+			if (ret == -EPROBE_DEFER)
+				goto clk_disable;
+			else if (gpio_is_valid(plat->gpio_cd)) {
+				ret = mmc_gpio_request_cd(mmc, plat->gpio_cd, 0);
+				if (ret)
+					goto clk_disable;
+			}
+		}
+
+		ret = mmc_gpiod_request_ro(mmc, "wp", 0, false, 0, NULL);
+		if (ret < 0) {
+			if (ret == -EPROBE_DEFER)
+				goto clk_disable;
+			else if (gpio_is_valid(plat->gpio_wp)) {
+				ret = mmc_gpio_request_ro(mmc, plat->gpio_wp);
+				if (ret)
+					goto clk_disable;
+			}
+		}
 	}
 
 	ret = devm_request_irq(&dev->dev, dev->irq[0], mmci_irq, IRQF_SHARED,
diff --git a/drivers/mmc/host/mmci_qcom_dml.c b/drivers/mmc/host/mmci_qcom_dml.c
new file mode 100644
index 000000000000..2b7fc3764803
--- /dev/null
+++ b/drivers/mmc/host/mmci_qcom_dml.c
@@ -0,0 +1,177 @@
+/*
+ *
+ * Copyright (c) 2011, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/bitops.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/card.h>
+#include "mmci.h"
+
+/* Registers */
+#define DML_CONFIG			0x00
+#define PRODUCER_CRCI_MSK		GENMASK(1, 0)
+#define PRODUCER_CRCI_DISABLE		0
+#define PRODUCER_CRCI_X_SEL		BIT(0)
+#define PRODUCER_CRCI_Y_SEL		BIT(1)
+#define CONSUMER_CRCI_MSK		GENMASK(3, 2)
+#define CONSUMER_CRCI_DISABLE		0
+#define CONSUMER_CRCI_X_SEL		BIT(2)
+#define CONSUMER_CRCI_Y_SEL		BIT(3)
+#define PRODUCER_TRANS_END_EN		BIT(4)
+#define BYPASS				BIT(16)
+#define DIRECT_MODE			BIT(17)
+#define INFINITE_CONS_TRANS		BIT(18)
+
+#define DML_SW_RESET			0x08
+#define DML_PRODUCER_START		0x0c
+#define DML_CONSUMER_START		0x10
+#define DML_PRODUCER_PIPE_LOGICAL_SIZE	0x14
+#define DML_CONSUMER_PIPE_LOGICAL_SIZE	0x18
+#define DML_PIPE_ID			0x1c
+#define PRODUCER_PIPE_ID_SHFT		0
+#define PRODUCER_PIPE_ID_MSK		GENMASK(4, 0)
+#define CONSUMER_PIPE_ID_SHFT		16
+#define CONSUMER_PIPE_ID_MSK		GENMASK(20, 16)
+
+#define DML_PRODUCER_BAM_BLOCK_SIZE	0x24
+#define DML_PRODUCER_BAM_TRANS_SIZE	0x28
+
+/* other definitions */
+#define PRODUCER_PIPE_LOGICAL_SIZE	4096
+#define CONSUMER_PIPE_LOGICAL_SIZE	4096
+
+#define DML_OFFSET			0x800
+
+void dml_start_xfer(struct mmci_host *host, struct mmc_data *data)
+{
+	u32 config;
+	void __iomem *base = host->base + DML_OFFSET;
+
+	if (data->flags & MMC_DATA_READ) {
+		/* Read operation: configure DML for producer operation */
+		/* Set producer CRCI-x and disable consumer CRCI */
+		config = readl_relaxed(base + DML_CONFIG);
+		config = (config & ~PRODUCER_CRCI_MSK) | PRODUCER_CRCI_X_SEL;
+		config = (config & ~CONSUMER_CRCI_MSK) | CONSUMER_CRCI_DISABLE;
+		writel_relaxed(config, base + DML_CONFIG);
+
+		/* Set the Producer BAM block size */
+		writel_relaxed(data->blksz, base + DML_PRODUCER_BAM_BLOCK_SIZE);
+
+		/* Set Producer BAM Transaction size */
+		writel_relaxed(data->blocks * data->blksz,
+			       base + DML_PRODUCER_BAM_TRANS_SIZE);
+		/* Set Producer Transaction End bit */
+		config = readl_relaxed(base + DML_CONFIG);
+		config |= PRODUCER_TRANS_END_EN;
+		writel_relaxed(config, base + DML_CONFIG);
+		/* Trigger producer */
+		writel_relaxed(1, base + DML_PRODUCER_START);
+	} else {
+		/* Write operation: configure DML for consumer operation */
+		/* Set consumer CRCI-x and disable producer CRCI*/
+		config = readl_relaxed(base + DML_CONFIG);
+		config = (config & ~CONSUMER_CRCI_MSK) | CONSUMER_CRCI_X_SEL;
+		config = (config & ~PRODUCER_CRCI_MSK) | PRODUCER_CRCI_DISABLE;
+		writel_relaxed(config, base + DML_CONFIG);
+		/* Clear Producer Transaction End bit */
+		config = readl_relaxed(base + DML_CONFIG);
+		config &= ~PRODUCER_TRANS_END_EN;
+		writel_relaxed(config, base + DML_CONFIG);
+		/* Trigger consumer */
+		writel_relaxed(1, base + DML_CONSUMER_START);
+	}
+
+	/* make sure the dml is configured before dma is triggered */
+	wmb();
+}
+
+static int of_get_dml_pipe_index(struct device_node *np, const char *name)
+{
+	int index;
+	struct of_phandle_args	dma_spec;
+
+	index = of_property_match_string(np, "dma-names", name);
+
+	if (index < 0)
+		return -ENODEV;
+
+	if (of_parse_phandle_with_args(np, "dmas", "#dma-cells", index,
+				       &dma_spec))
+		return -ENODEV;
+
+	if (dma_spec.args_count)
+		return dma_spec.args[0];
+
+	return -ENODEV;
+}
+
+/* Initialize the dml hardware connected to SD Card controller */
+int dml_hw_init(struct mmci_host *host, struct device_node *np)
+{
+	u32 config;
+	void __iomem *base;
+	int consumer_id, producer_id;
+
+	consumer_id = of_get_dml_pipe_index(np, "tx");
+	producer_id = of_get_dml_pipe_index(np, "rx");
+
+	if (producer_id < 0 || consumer_id < 0)
+		return -ENODEV;
+
+	base = host->base + DML_OFFSET;
+
+	/* Reset the DML block */
+	writel_relaxed(1, base + DML_SW_RESET);
+
+	/* Disable the producer and consumer CRCI */
+	config = (PRODUCER_CRCI_DISABLE | CONSUMER_CRCI_DISABLE);
+	/*
+	 * Disable the bypass mode. Bypass mode will only be used
+	 * if data transfer is to happen in PIO mode and don't
+	 * want the BAM interface to connect with SDCC-DML.
+	 */
+	config &= ~BYPASS;
+	/*
+	 * Disable direct mode as we don't DML to MASTER the AHB bus.
+	 * BAM connected with DML should MASTER the AHB bus.
+	 */
+	config &= ~DIRECT_MODE;
+	/*
+	 * Disable infinite mode transfer as we won't be doing any
+	 * infinite size data transfers. All data transfer will be
+	 * of finite data size.
+	 */
+	config &= ~INFINITE_CONS_TRANS;
+	writel_relaxed(config, base + DML_CONFIG);
+
+	/*
+	 * Initialize the logical BAM pipe size for producer
+	 * and consumer.
+	 */
+	writel_relaxed(PRODUCER_PIPE_LOGICAL_SIZE,
+		       base + DML_PRODUCER_PIPE_LOGICAL_SIZE);
+	writel_relaxed(CONSUMER_PIPE_LOGICAL_SIZE,
+		       base + DML_CONSUMER_PIPE_LOGICAL_SIZE);
+
+	/* Initialize Producer/consumer pipe id */
+	writel_relaxed(producer_id | (consumer_id << CONSUMER_PIPE_ID_SHFT),
+		       base + DML_PIPE_ID);
+
+	/* Make sure dml intialization is finished */
+	mb();
+
+	return 0;
+}
diff --git a/drivers/mmc/host/mmci_qcom_dml.h b/drivers/mmc/host/mmci_qcom_dml.h
new file mode 100644
index 000000000000..6e405d09d534
--- /dev/null
+++ b/drivers/mmc/host/mmci_qcom_dml.h
@@ -0,0 +1,31 @@
+/*
+ *
+ * Copyright (c) 2011, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#ifndef __MMC_QCOM_DML_H__
+#define __MMC_QCOM_DML_H__
+
+#ifdef CONFIG_MMC_QCOM_DML
+int dml_hw_init(struct mmci_host *host, struct device_node *np);
+void dml_start_xfer(struct mmci_host *host, struct mmc_data *data);
+#else
+static inline int dml_hw_init(struct mmci_host *host, struct device_node *np)
+{
+	return -ENOSYS;
+}
+static inline void dml_start_xfer(struct mmci_host *host, struct mmc_data *data)
+{
+}
+#endif /* CONFIG_MMC_QCOM_DML */
+
+#endif /* __MMC_QCOM_DML_H__ */
diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c
index b4b1efbf6c16..f3e18d08e852 100644
--- a/drivers/mmc/host/moxart-mmc.c
+++ b/drivers/mmc/host/moxart-mmc.c
@@ -717,7 +717,6 @@ static struct platform_driver moxart_mmc_driver = {
 	.remove     = moxart_remove,
 	.driver     = {
 		.name		= "mmc-moxart",
-		.owner		= THIS_MODULE,
 		.of_match_table	= moxart_mmc_match,
 	},
 };
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index ed1cb93c3784..ad111422ad55 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -1238,7 +1238,6 @@ static struct platform_driver mxcmci_driver = {
 	.id_table	= mxcmci_devtype,
 	.driver		= {
 		.name		= DRIVER_NAME,
-		.owner		= THIS_MODULE,
 		.pm	= &mxcmci_pm_ops,
 		.of_match_table	= mxcmci_of_match,
 	}
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index 140885a5a4e7..cd74e5143c36 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -735,7 +735,6 @@ static struct platform_driver mxs_mmc_driver = {
 	.id_table	= mxs_ssp_ids,
 	.driver		= {
 		.name	= DRIVER_NAME,
-		.owner	= THIS_MODULE,
 #ifdef CONFIG_PM
 		.pm	= &mxs_mmc_pm_ops,
 #endif
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index 81974ecdfcbc..68dd6c79c378 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -1494,7 +1494,6 @@ static struct platform_driver mmc_omap_driver = {
 	.remove		= mmc_omap_remove,
 	.driver		= {
 		.name	= DRIVER_NAME,
-		.owner	= THIS_MODULE,
 		.of_match_table = of_match_ptr(mmc_omap_match),
 	},
 };
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 965672663ef0..df27bb4fc098 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -1829,7 +1829,17 @@ static int omap_hsmmc_disable_fclk(struct mmc_host *mmc)
 	return 0;
 }
 
-static const struct mmc_host_ops omap_hsmmc_ops = {
+static int omap_hsmmc_multi_io_quirk(struct mmc_card *card,
+				     unsigned int direction, int blk_size)
+{
+	/* This controller can't do multiblock reads due to hw bugs */
+	if (direction == MMC_DATA_READ)
+		return 1;
+
+	return blk_size;
+}
+
+static struct mmc_host_ops omap_hsmmc_ops = {
 	.enable = omap_hsmmc_enable_fclk,
 	.disable = omap_hsmmc_disable_fclk,
 	.post_req = omap_hsmmc_post_req,
@@ -2101,7 +2111,7 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 
 	if (host->pdata->controller_flags & OMAP_HSMMC_BROKEN_MULTIBLOCK_READ) {
 		dev_info(&pdev->dev, "multiblock reads disabled due to 35xx erratum 2.1.1.128; MMC read performance may suffer\n");
-		mmc->caps2 |= MMC_CAP2_NO_MULTI_READ;
+		omap_hsmmc_ops.multi_io_quirk = omap_hsmmc_multi_io_quirk;
 	}
 
 	pm_runtime_enable(host->dev);
@@ -2489,7 +2499,6 @@ static struct platform_driver omap_hsmmc_driver = {
 	.remove		= omap_hsmmc_remove,
 	.driver		= {
 		.name = DRIVER_NAME,
-		.owner = THIS_MODULE,
 		.pm = &omap_hsmmc_dev_pm_ops,
 		.of_match_table = of_match_ptr(omap_mmc_of_match),
 	},
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 32fe11323f39..1b6d0bfe35f5 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -474,7 +474,7 @@ static void pxamci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		unsigned int clk = rate / ios->clock;
 
 		if (host->clkrt == CLKRT_OFF)
-			clk_enable(host->clk);
+			clk_prepare_enable(host->clk);
 
 		if (ios->clock == 26000000) {
 			/* to support 26MHz */
@@ -501,7 +501,7 @@ static void pxamci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		pxamci_stop_clock(host);
 		if (host->clkrt != CLKRT_OFF) {
 			host->clkrt = CLKRT_OFF;
-			clk_disable(host->clk);
+			clk_disable_unprepare(host->clk);
 		}
 	}
 
@@ -885,7 +885,6 @@ static struct platform_driver pxamci_driver = {
 	.remove		= pxamci_remove,
 	.driver		= {
 		.name	= DRIVER_NAME,
-		.owner	= THIS_MODULE,
 		.of_match_table = of_match_ptr(pxa_mmc_dt_ids),
 	},
 };
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index dfde4a210238..c70b602f8f1e 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -412,6 +412,13 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 	}
 
 	if (rsp_type == SD_RSP_TYPE_R2) {
+		/*
+		 * The controller offloads the last byte {CRC-7, end bit 1'b1}
+		 * of response type R2. Assign dummy CRC, 0, and end bit to the
+		 * byte(ptr[16], goes into the LSB of resp[3] later).
+		 */
+		ptr[16] = 1;
+
 		for (i = 0; i < 4; i++) {
 			cmd->resp[i] = get_unaligned_be32(ptr + 1 + i * 4);
 			dev_dbg(sdmmc_dev(host), "cmd->resp[%d] = 0x%08x\n",
@@ -1292,6 +1299,7 @@ static void realtek_init_host(struct realtek_pci_sdmmc *host)
 	mmc->caps = MMC_CAP_4_BIT_DATA | MMC_CAP_SD_HIGHSPEED |
 		MMC_CAP_MMC_HIGHSPEED | MMC_CAP_BUS_WIDTH_TEST |
 		MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25;
+	mmc->caps2 = MMC_CAP2_NO_PRESCAN_POWERUP | MMC_CAP2_FULL_PWR_CYCLE;
 	mmc->max_current_330 = 400;
 	mmc->max_current_180 = 800;
 	mmc->ops = &realtek_pci_sdmmc_ops;
@@ -1416,7 +1424,6 @@ static struct platform_driver rtsx_pci_sdmmc_driver = {
 	.remove		= rtsx_pci_sdmmc_drv_remove,
 	.id_table       = rtsx_pci_sdmmc_ids,
 	.driver		= {
-		.owner	= THIS_MODULE,
 		.name	= DRV_NAME_RTSX_PCI_SDMMC,
 	},
 };
diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c
index 5d3766e792f0..88af827e086b 100644
--- a/drivers/mmc/host/rtsx_usb_sdmmc.c
+++ b/drivers/mmc/host/rtsx_usb_sdmmc.c
@@ -435,6 +435,13 @@ static void sd_send_cmd_get_rsp(struct rtsx_usb_sdmmc *host,
 	}
 
 	if (rsp_type == SD_RSP_TYPE_R2) {
+		/*
+		 * The controller offloads the last byte {CRC-7, end bit 1'b1}
+		 * of response type R2. Assign dummy CRC, 0, and end bit to the
+		 * byte(ptr[16], goes into the LSB of resp[3] later).
+		 */
+		ptr[16] = 1;
+
 		for (i = 0; i < 4; i++) {
 			cmd->resp[i] = get_unaligned_be32(ptr + 1 + i * 4);
 			dev_dbg(sdmmc_dev(host), "cmd->resp[%d] = 0x%08x\n",
@@ -1329,6 +1336,7 @@ static void rtsx_usb_init_host(struct rtsx_usb_sdmmc *host)
 		MMC_CAP_MMC_HIGHSPEED | MMC_CAP_BUS_WIDTH_TEST |
 		MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 | MMC_CAP_UHS_SDR50 |
 		MMC_CAP_NEEDS_POLL;
+	mmc->caps2 = MMC_CAP2_NO_PRESCAN_POWERUP | MMC_CAP2_FULL_PWR_CYCLE;
 
 	mmc->max_current_330 = 400;
 	mmc->max_current_180 = 800;
@@ -1445,7 +1453,6 @@ static struct platform_driver rtsx_usb_sdmmc_driver = {
 	.remove		= rtsx_usb_sdmmc_drv_remove,
 	.id_table       = rtsx_usb_sdmmc_ids,
 	.driver		= {
-		.owner	= THIS_MODULE,
 		.name	= "rtsx_usb_sdmmc",
 	},
 };
diff --git a/drivers/mmc/host/s3cmci.c b/drivers/mmc/host/s3cmci.c
index e5516a226362..94cddf381ba3 100644
--- a/drivers/mmc/host/s3cmci.c
+++ b/drivers/mmc/host/s3cmci.c
@@ -985,7 +985,8 @@ static int s3cmci_setup_data(struct s3cmci_host *host, struct mmc_data *data)
 		 * one block being transferred. */
 
 		if (data->blocks > 1) {
-			pr_warning("%s: can't do non-word sized block transfers (blksz %d)\n", __func__, data->blksz);
+			pr_warn("%s: can't do non-word sized block transfers (blksz %d)\n",
+				__func__, data->blksz);
 			return -EINVAL;
 		}
 	}
@@ -1874,7 +1875,6 @@ MODULE_DEVICE_TABLE(platform, s3cmci_driver_ids);
 static struct platform_driver s3cmci_driver = {
 	.driver	= {
 		.name	= "s3c-sdi",
-		.owner	= THIS_MODULE,
 	},
 	.id_table	= s3cmci_driver_ids,
 	.probe		= s3cmci_probe,
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 8c5337002c51..9cccc0e89b04 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -67,6 +67,8 @@ struct sdhci_acpi_slot {
 	unsigned int	caps2;
 	mmc_pm_flag_t	pm_caps;
 	unsigned int	flags;
+	int (*probe_slot)(struct platform_device *, const char *, const char *);
+	int (*remove_slot)(struct platform_device *);
 };
 
 struct sdhci_acpi_host {
@@ -122,13 +124,67 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = {
 	.ops = &sdhci_acpi_ops_int,
 };
 
+static int sdhci_acpi_emmc_probe_slot(struct platform_device *pdev,
+				      const char *hid, const char *uid)
+{
+	struct sdhci_acpi_host *c = platform_get_drvdata(pdev);
+	struct sdhci_host *host;
+
+	if (!c || !c->host)
+		return 0;
+
+	host = c->host;
+
+	/* Platform specific code during emmc proble slot goes here */
+
+	if (hid && uid && !strcmp(hid, "80860F14") && !strcmp(uid, "1") &&
+	    sdhci_readl(host, SDHCI_CAPABILITIES) == 0x446cc8b2 &&
+	    sdhci_readl(host, SDHCI_CAPABILITIES_1) == 0x00000807)
+		host->timeout_clk = 1000; /* 1000 kHz i.e. 1 MHz */
+
+	return 0;
+}
+
+static int sdhci_acpi_sdio_probe_slot(struct platform_device *pdev,
+				      const char *hid, const char *uid)
+{
+	struct sdhci_acpi_host *c = platform_get_drvdata(pdev);
+	struct sdhci_host *host;
+
+	if (!c || !c->host)
+		return 0;
+
+	host = c->host;
+
+	/* Platform specific code during emmc proble slot goes here */
+
+	return 0;
+}
+
+static int sdhci_acpi_sd_probe_slot(struct platform_device *pdev,
+				    const char *hid, const char *uid)
+{
+	struct sdhci_acpi_host *c = platform_get_drvdata(pdev);
+	struct sdhci_host *host;
+
+	if (!c || !c->host || !c->slot)
+		return 0;
+
+	host = c->host;
+
+	/* Platform specific code during emmc proble slot goes here */
+
+	return 0;
+}
+
 static const struct sdhci_acpi_slot sdhci_acpi_slot_int_emmc = {
 	.chip    = &sdhci_acpi_chip_int,
 	.caps    = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
 		   MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR,
 	.caps2   = MMC_CAP2_HC_ERASE_SZ,
 	.flags   = SDHCI_ACPI_RUNTIME_PM,
-	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | SDHCI_QUIRK2_STOP_WITH_TC,
+	.probe_slot	= sdhci_acpi_emmc_probe_slot,
 };
 
 static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sdio = {
@@ -137,12 +193,15 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sdio = {
 	.caps    = MMC_CAP_NONREMOVABLE | MMC_CAP_POWER_OFF_CARD,
 	.flags   = SDHCI_ACPI_RUNTIME_PM,
 	.pm_caps = MMC_PM_KEEP_POWER,
+	.probe_slot	= sdhci_acpi_sdio_probe_slot,
 };
 
 static const struct sdhci_acpi_slot sdhci_acpi_slot_int_sd = {
 	.flags   = SDHCI_ACPI_SD_CD | SDHCI_ACPI_SD_CD_OVERRIDE_LEVEL |
 		   SDHCI_ACPI_RUNTIME_PM,
-	.quirks2 = SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON,
+	.quirks2 = SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON |
+		   SDHCI_QUIRK2_STOP_WITH_TC,
+	.probe_slot	= sdhci_acpi_sd_probe_slot,
 };
 
 struct sdhci_acpi_uid_slot {
@@ -156,6 +215,7 @@ static const struct sdhci_acpi_uid_slot sdhci_acpi_uids[] = {
 	{ "80860F14" , "3" , &sdhci_acpi_slot_int_sd   },
 	{ "80860F16" , NULL, &sdhci_acpi_slot_int_sd   },
 	{ "INT33BB"  , "2" , &sdhci_acpi_slot_int_sdio },
+	{ "INT33BB"  , "3" , &sdhci_acpi_slot_int_sd },
 	{ "INT33C6"  , NULL, &sdhci_acpi_slot_int_sdio },
 	{ "INT3436"  , NULL, &sdhci_acpi_slot_int_sdio },
 	{ "PNP0D40"  },
@@ -173,8 +233,8 @@ static const struct acpi_device_id sdhci_acpi_ids[] = {
 };
 MODULE_DEVICE_TABLE(acpi, sdhci_acpi_ids);
 
-static const struct sdhci_acpi_slot *sdhci_acpi_get_slot_by_ids(const char *hid,
-								const char *uid)
+static const struct sdhci_acpi_slot *sdhci_acpi_get_slot(const char *hid,
+							 const char *uid)
 {
 	const struct sdhci_acpi_uid_slot *u;
 
@@ -189,24 +249,6 @@ static const struct sdhci_acpi_slot *sdhci_acpi_get_slot_by_ids(const char *hid,
 	return NULL;
 }
 
-static const struct sdhci_acpi_slot *sdhci_acpi_get_slot(acpi_handle handle,
-							 const char *hid)
-{
-	const struct sdhci_acpi_slot *slot;
-	struct acpi_device_info *info;
-	const char *uid = NULL;
-	acpi_status status;
-
-	status = acpi_get_object_info(handle, &info);
-	if (!ACPI_FAILURE(status) && (info->valid & ACPI_VALID_UID))
-		uid = info->unique_id.string;
-
-	slot = sdhci_acpi_get_slot_by_ids(hid, uid);
-
-	kfree(info);
-	return slot;
-}
-
 static int sdhci_acpi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -217,6 +259,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 	struct resource *iomem;
 	resource_size_t len;
 	const char *hid;
+	const char *uid;
 	int err;
 
 	if (acpi_bus_get_device(handle, &device))
@@ -226,6 +269,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	hid = acpi_device_hid(device);
+	uid = device->pnp.unique_id;
 
 	iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!iomem)
@@ -244,7 +288,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 
 	c = sdhci_priv(host);
 	c->host = host;
-	c->slot = sdhci_acpi_get_slot(handle, hid);
+	c->slot = sdhci_acpi_get_slot(hid, uid);
 	c->pdev = pdev;
 	c->use_runtime_pm = sdhci_acpi_flag(c, SDHCI_ACPI_RUNTIME_PM);
 
@@ -277,6 +321,11 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 	}
 
 	if (c->slot) {
+		if (c->slot->probe_slot) {
+			err = c->slot->probe_slot(pdev, hid, uid);
+			if (err)
+				goto err_free;
+		}
 		if (c->slot->chip) {
 			host->ops            = c->slot->chip->ops;
 			host->quirks        |= c->slot->chip->quirks;
@@ -297,7 +346,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 	if (sdhci_acpi_flag(c, SDHCI_ACPI_SD_CD)) {
 		bool v = sdhci_acpi_flag(c, SDHCI_ACPI_SD_CD_OVERRIDE_LEVEL);
 
-		if (mmc_gpiod_request_cd(host->mmc, NULL, 0, v, 0)) {
+		if (mmc_gpiod_request_cd(host->mmc, NULL, 0, v, 0, NULL)) {
 			dev_warn(dev, "failed to setup card detect gpio\n");
 			c->use_runtime_pm = false;
 		}
@@ -334,6 +383,9 @@ static int sdhci_acpi_remove(struct platform_device *pdev)
 		pm_runtime_put_noidle(dev);
 	}
 
+	if (c->slot && c->slot->remove_slot)
+		c->slot->remove_slot(pdev);
+
 	dead = (sdhci_readl(c->host, SDHCI_INT_STATUS) == ~0);
 	sdhci_remove_host(c->host, dead);
 	sdhci_free_host(c->host);
@@ -385,20 +437,13 @@ static int sdhci_acpi_runtime_idle(struct device *dev)
 	return 0;
 }
 
-#else
-
-#define sdhci_acpi_runtime_suspend	NULL
-#define sdhci_acpi_runtime_resume	NULL
-#define sdhci_acpi_runtime_idle		NULL
-
 #endif
 
 static const struct dev_pm_ops sdhci_acpi_pm_ops = {
 	.suspend		= sdhci_acpi_suspend,
 	.resume			= sdhci_acpi_resume,
-	.runtime_suspend	= sdhci_acpi_runtime_suspend,
-	.runtime_resume		= sdhci_acpi_runtime_resume,
-	.runtime_idle		= sdhci_acpi_runtime_idle,
+	SET_RUNTIME_PM_OPS(sdhci_acpi_runtime_suspend,
+			sdhci_acpi_runtime_resume, sdhci_acpi_runtime_idle)
 };
 
 static struct platform_driver sdhci_acpi_driver = {
diff --git a/drivers/mmc/host/sdhci-bcm-kona.c b/drivers/mmc/host/sdhci-bcm-kona.c
index dd780c315a63..e7e4fbdcbfe0 100644
--- a/drivers/mmc/host/sdhci-bcm-kona.c
+++ b/drivers/mmc/host/sdhci-bcm-kona.c
@@ -225,7 +225,7 @@ static struct sdhci_pltfm_data sdhci_pltfm_data_kona = {
 		SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
 };
 
-static struct __initconst of_device_id sdhci_bcm_kona_of_match[] = {
+static const struct of_device_id sdhci_bcm_kona_of_match[] = {
 	{ .compatible = "brcm,kona-sdhci"},
 	{ .compatible = "bcm,kona-sdhci"}, /* deprecated name */
 	{}
@@ -359,7 +359,6 @@ static int sdhci_bcm_kona_remove(struct platform_device *pdev)
 static struct platform_driver sdhci_bcm_kona_driver = {
 	.driver		= {
 		.name	= "sdhci-kona",
-		.owner	= THIS_MODULE,
 		.pm	= SDHCI_PLTFM_PMOPS,
 		.of_match_table = sdhci_bcm_kona_of_match,
 	},
diff --git a/drivers/mmc/host/sdhci-bcm2835.c b/drivers/mmc/host/sdhci-bcm2835.c
index 46af9a439d7b..439d259fdf1d 100644
--- a/drivers/mmc/host/sdhci-bcm2835.c
+++ b/drivers/mmc/host/sdhci-bcm2835.c
@@ -194,7 +194,6 @@ MODULE_DEVICE_TABLE(of, bcm2835_sdhci_of_match);
 static struct platform_driver bcm2835_sdhci_driver = {
 	.driver = {
 		.name = "sdhci-bcm2835",
-		.owner = THIS_MODULE,
 		.of_match_table = bcm2835_sdhci_of_match,
 		.pm = SDHCI_PLTFM_PMOPS,
 	},
diff --git a/drivers/mmc/host/sdhci-cns3xxx.c b/drivers/mmc/host/sdhci-cns3xxx.c
index 14b74075589a..a7935a8d0922 100644
--- a/drivers/mmc/host/sdhci-cns3xxx.c
+++ b/drivers/mmc/host/sdhci-cns3xxx.c
@@ -106,7 +106,6 @@ static int sdhci_cns3xxx_remove(struct platform_device *pdev)
 static struct platform_driver sdhci_cns3xxx_driver = {
 	.driver		= {
 		.name	= "sdhci-cns3xxx",
-		.owner	= THIS_MODULE,
 		.pm	= SDHCI_PLTFM_PMOPS,
 	},
 	.probe		= sdhci_cns3xxx_probe,
diff --git a/drivers/mmc/host/sdhci-dove.c b/drivers/mmc/host/sdhci-dove.c
index e6278ec007d7..ca969d271a27 100644
--- a/drivers/mmc/host/sdhci-dove.c
+++ b/drivers/mmc/host/sdhci-dove.c
@@ -146,7 +146,6 @@ MODULE_DEVICE_TABLE(of, sdhci_dove_of_match_table);
 static struct platform_driver sdhci_dove_driver = {
 	.driver		= {
 		.name	= "sdhci-dove",
-		.owner	= THIS_MODULE,
 		.pm	= SDHCI_PLTFM_PMOPS,
 		.of_match_table = sdhci_dove_of_match_table,
 	},
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index ccec0e32590f..587ee0edeb57 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -880,6 +880,24 @@ static void esdhc_reset(struct sdhci_host *host, u8 mask)
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 }
 
+static unsigned int esdhc_get_max_timeout_count(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct pltfm_imx_data *imx_data = pltfm_host->priv;
+
+	return esdhc_is_usdhc(imx_data) ? 1 << 28 : 1 << 27;
+}
+
+static void esdhc_set_timeout(struct sdhci_host *host, struct mmc_command *cmd)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct pltfm_imx_data *imx_data = pltfm_host->priv;
+
+	/* use maximum timeout counter */
+	sdhci_writeb(host, esdhc_is_usdhc(imx_data) ? 0xF : 0xE,
+			SDHCI_TIMEOUT_CONTROL);
+}
+
 static struct sdhci_ops sdhci_esdhc_ops = {
 	.read_l = esdhc_readl_le,
 	.read_w = esdhc_readw_le,
@@ -889,7 +907,9 @@ static struct sdhci_ops sdhci_esdhc_ops = {
 	.set_clock = esdhc_pltfm_set_clock,
 	.get_max_clock = esdhc_pltfm_get_max_clock,
 	.get_min_clock = esdhc_pltfm_get_min_clock,
+	.get_max_timeout_count = esdhc_get_max_timeout_count,
 	.get_ro = esdhc_pltfm_get_ro,
+	.set_timeout = esdhc_set_timeout,
 	.set_bus_width = esdhc_pltfm_set_bus_width,
 	.set_uhs_signaling = esdhc_set_uhs_signaling,
 	.reset = esdhc_reset,
@@ -1207,7 +1227,6 @@ static const struct dev_pm_ops sdhci_esdhc_pmops = {
 static struct platform_driver sdhci_esdhc_imx_driver = {
 	.driver		= {
 		.name	= "sdhci-esdhc-imx",
-		.owner	= THIS_MODULE,
 		.of_match_table = imx_esdhc_dt_ids,
 		.pm	= &sdhci_esdhc_pmops,
 	},
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 1a6661ed6205..30804385af6d 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -46,24 +46,6 @@
 #define CMUX_SHIFT_PHASE_SHIFT	24
 #define CMUX_SHIFT_PHASE_MASK	(7 << CMUX_SHIFT_PHASE_SHIFT)
 
-static const u32 tuning_block_64[] = {
-	0x00ff0fff, 0xccc3ccff, 0xffcc3cc3, 0xeffefffe,
-	0xddffdfff, 0xfbfffbff, 0xff7fffbf, 0xefbdf777,
-	0xf0fff0ff, 0x3cccfc0f, 0xcfcc33cc, 0xeeffefff,
-	0xfdfffdff, 0xffbfffdf, 0xfff7ffbb, 0xde7b7ff7
-};
-
-static const u32 tuning_block_128[] = {
-	0xff00ffff, 0x0000ffff, 0xccccffff, 0xcccc33cc,
-	0xcc3333cc, 0xffffcccc, 0xffffeeff, 0xffeeeeff,
-	0xffddffff, 0xddddffff, 0xbbffffff, 0xbbffffff,
-	0xffffffbb, 0xffffff77, 0x77ff7777, 0xffeeddbb,
-	0x00ffffff, 0x00ffffff, 0xccffff00, 0xcc33cccc,
-	0x3333cccc, 0xffcccccc, 0xffeeffff, 0xeeeeffff,
-	0xddffffff, 0xddffffff, 0xffffffdd, 0xffffffbb,
-	0xffffbbbb, 0xffff77ff, 0xff7777ff, 0xeeddbb77
-};
-
 struct sdhci_msm_host {
 	struct platform_device *pdev;
 	void __iomem *core_mem;	/* MSM SDCC mapped address */
@@ -358,8 +340,8 @@ static int sdhci_msm_execute_tuning(struct sdhci_host *host, u32 opcode)
 {
 	int tuning_seq_cnt = 3;
 	u8 phase, *data_buf, tuned_phases[16], tuned_phase_cnt = 0;
-	const u32 *tuning_block_pattern = tuning_block_64;
-	int size = sizeof(tuning_block_64);	/* Pattern size in bytes */
+	const u8 *tuning_block_pattern = tuning_blk_pattern_4bit;
+	int size = sizeof(tuning_blk_pattern_4bit);
 	int rc;
 	struct mmc_host *mmc = host->mmc;
 	struct mmc_ios ios = host->mmc->ios;
@@ -375,8 +357,8 @@ static int sdhci_msm_execute_tuning(struct sdhci_host *host, u32 opcode)
 
 	if ((opcode == MMC_SEND_TUNING_BLOCK_HS200) &&
 	    (mmc->ios.bus_width == MMC_BUS_WIDTH_8)) {
-		tuning_block_pattern = tuning_block_128;
-		size = sizeof(tuning_block_128);
+		tuning_block_pattern = tuning_blk_pattern_8bit;
+		size = sizeof(tuning_blk_pattern_8bit);
 	}
 
 	data_buf = kmalloc(size, GFP_KERNEL);
@@ -610,7 +592,6 @@ static struct platform_driver sdhci_msm_driver = {
 	.remove = sdhci_msm_remove,
 	.driver = {
 		   .name = "sdhci_msm",
-		   .owner = THIS_MODULE,
 		   .of_match_table = sdhci_msm_dt_match,
 	},
 };
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index 5bd1092310f2..981d66e5c023 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -213,7 +213,6 @@ MODULE_DEVICE_TABLE(of, sdhci_arasan_of_match);
 static struct platform_driver sdhci_arasan_driver = {
 	.driver = {
 		.name = "sdhci-arasan",
-		.owner = THIS_MODULE,
 		.of_match_table = sdhci_arasan_of_match,
 		.pm = &sdhci_arasan_dev_pm_ops,
 	},
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 8be4dcfb49a0..8872c85c63d4 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -388,7 +388,6 @@ MODULE_DEVICE_TABLE(of, sdhci_esdhc_of_match);
 static struct platform_driver sdhci_esdhc_driver = {
 	.driver = {
 		.name = "sdhci-esdhc",
-		.owner = THIS_MODULE,
 		.of_match_table = sdhci_esdhc_of_match,
 		.pm = ESDHC_PMOPS,
 	},
diff --git a/drivers/mmc/host/sdhci-of-hlwd.c b/drivers/mmc/host/sdhci-of-hlwd.c
index b341661369a2..be479279a1d5 100644
--- a/drivers/mmc/host/sdhci-of-hlwd.c
+++ b/drivers/mmc/host/sdhci-of-hlwd.c
@@ -89,7 +89,6 @@ MODULE_DEVICE_TABLE(of, sdhci_hlwd_of_match);
 static struct platform_driver sdhci_hlwd_driver = {
 	.driver = {
 		.name = "sdhci-hlwd",
-		.owner = THIS_MODULE,
 		.of_match_table = sdhci_hlwd_of_match,
 		.pm = SDHCI_PLTFM_PMOPS,
 	},
diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c
index c3a1debc9289..61192973e7cb 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci.c
@@ -24,6 +24,7 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
 #include <linux/pm_runtime.h>
+#include <linux/mmc/slot-gpio.h>
 #include <linux/mmc/sdhci-pci-data.h>
 
 #include "sdhci.h"
@@ -271,6 +272,8 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 				 MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR;
 	slot->host->mmc->caps2 |= MMC_CAP2_HC_ERASE_SZ;
 	slot->hw_reset = sdhci_pci_int_hw_reset;
+	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BSW_EMMC)
+		slot->host->timeout_clk = 1000; /* 1000 kHz i.e. 1 MHz */
 	return 0;
 }
 
@@ -280,22 +283,35 @@ static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot)
 	return 0;
 }
 
+static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
+{
+	slot->cd_con_id = NULL;
+	slot->cd_idx = 0;
+	slot->cd_override_level = true;
+	return 0;
+}
+
 static const struct sdhci_pci_fixes sdhci_intel_byt_emmc = {
 	.allow_runtime_pm = true,
 	.probe_slot	= byt_emmc_probe_slot,
-	.quirks2	= SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+	.quirks2	= SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+			  SDHCI_QUIRK2_STOP_WITH_TC,
 };
 
 static const struct sdhci_pci_fixes sdhci_intel_byt_sdio = {
-	.quirks2	= SDHCI_QUIRK2_HOST_OFF_CARD_ON,
+	.quirks2	= SDHCI_QUIRK2_HOST_OFF_CARD_ON |
+			SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 	.allow_runtime_pm = true,
 	.probe_slot	= byt_sdio_probe_slot,
 };
 
 static const struct sdhci_pci_fixes sdhci_intel_byt_sd = {
-	.quirks2	= SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON,
+	.quirks2	= SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON |
+			  SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+			  SDHCI_QUIRK2_STOP_WITH_TC,
 	.allow_runtime_pm = true,
 	.own_cd_for_runtime_pm = true,
+	.probe_slot	= byt_sd_probe_slot,
 };
 
 /* Define Host controllers for Intel Merrifield platform */
@@ -317,7 +333,9 @@ static int intel_mrfl_mmc_probe_slot(struct sdhci_pci_slot *slot)
 
 static const struct sdhci_pci_fixes sdhci_intel_mrfl_mmc = {
 	.quirks		= SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
-	.quirks2	= SDHCI_QUIRK2_BROKEN_HS200,
+	.quirks2	= SDHCI_QUIRK2_BROKEN_HS200 |
+			SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
+	.allow_runtime_pm = true,
 	.probe_slot	= intel_mrfl_mmc_probe_slot,
 };
 
@@ -876,6 +894,29 @@ static const struct pci_device_id pci_ids[] = {
 		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_emmc,
 	},
 
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_BSW_EMMC,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_emmc,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_BSW_SDIO,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_sdio,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_BSW_SD,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_sd,
+	},
 
 	{
 		.vendor		= PCI_VENDOR_ID_INTEL,
@@ -1269,20 +1310,13 @@ static int sdhci_pci_runtime_idle(struct device *dev)
 	return 0;
 }
 
-#else
-
-#define sdhci_pci_runtime_suspend	NULL
-#define sdhci_pci_runtime_resume	NULL
-#define sdhci_pci_runtime_idle		NULL
-
 #endif
 
 static const struct dev_pm_ops sdhci_pci_pm_ops = {
 	.suspend = sdhci_pci_suspend,
 	.resume = sdhci_pci_resume,
-	.runtime_suspend = sdhci_pci_runtime_suspend,
-	.runtime_resume = sdhci_pci_runtime_resume,
-	.runtime_idle = sdhci_pci_runtime_idle,
+	SET_RUNTIME_PM_OPS(sdhci_pci_runtime_suspend,
+			sdhci_pci_runtime_resume, sdhci_pci_runtime_idle)
 };
 
 /*****************************************************************************\
@@ -1332,6 +1366,7 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 	slot->pci_bar = bar;
 	slot->rst_n_gpio = -EINVAL;
 	slot->cd_gpio = -EINVAL;
+	slot->cd_idx = -1;
 
 	/* Retrieve platform data if there is any */
 	if (*sdhci_pci_get_data)
@@ -1390,6 +1425,13 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 	host->mmc->slotno = slotno;
 	host->mmc->caps2 |= MMC_CAP2_NO_PRESCAN_POWERUP;
 
+	if (slot->cd_idx >= 0 &&
+	    mmc_gpiod_request_cd(host->mmc, slot->cd_con_id, slot->cd_idx,
+				 slot->cd_override_level, 0, NULL)) {
+		dev_warn(&pdev->dev, "failed to setup card detect gpio\n");
+		slot->cd_idx = -1;
+	}
+
 	ret = sdhci_add_host(host);
 	if (ret)
 		goto remove;
@@ -1402,7 +1444,7 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 	 * Note sdhci_pci_add_own_cd() sets slot->cd_gpio to -EINVAL on failure.
 	 */
 	if (chip->fixes && chip->fixes->own_cd_for_runtime_pm &&
-	    !gpio_is_valid(slot->cd_gpio))
+	    !gpio_is_valid(slot->cd_gpio) && slot->cd_idx < 0)
 		chip->allow_runtime_pm = false;
 
 	return slot;
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index c101477ef3be..d57c3d169914 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -11,6 +11,9 @@
 #define PCI_DEVICE_ID_INTEL_BYT_SDIO	0x0f15
 #define PCI_DEVICE_ID_INTEL_BYT_SD	0x0f16
 #define PCI_DEVICE_ID_INTEL_BYT_EMMC2	0x0f50
+#define PCI_DEVICE_ID_INTEL_BSW_EMMC	0x2294
+#define PCI_DEVICE_ID_INTEL_BSW_SDIO	0x2295
+#define PCI_DEVICE_ID_INTEL_BSW_SD	0x2296
 #define PCI_DEVICE_ID_INTEL_MRFL_MMC	0x1190
 #define PCI_DEVICE_ID_INTEL_CLV_SDIO0	0x08f9
 #define PCI_DEVICE_ID_INTEL_CLV_SDIO1	0x08fa
@@ -61,6 +64,10 @@ struct sdhci_pci_slot {
 	int			cd_gpio;
 	int			cd_irq;
 
+	char			*cd_con_id;
+	int			cd_idx;
+	bool			cd_override_level;
+
 	void (*hw_reset)(struct sdhci_host *host);
 };
 
diff --git a/drivers/mmc/host/sdhci-pltfm.c b/drivers/mmc/host/sdhci-pltfm.c
index 7e834fb78f42..c5b01d6bb85d 100644
--- a/drivers/mmc/host/sdhci-pltfm.c
+++ b/drivers/mmc/host/sdhci-pltfm.c
@@ -123,7 +123,6 @@ struct sdhci_host *sdhci_pltfm_init(struct platform_device *pdev,
 				    size_t priv_size)
 {
 	struct sdhci_host *host;
-	struct device_node *np = pdev->dev.of_node;
 	struct resource *iomem;
 	int ret;
 
@@ -136,13 +135,8 @@ struct sdhci_host *sdhci_pltfm_init(struct platform_device *pdev,
 	if (resource_size(iomem) < 0x100)
 		dev_err(&pdev->dev, "Invalid iomem size!\n");
 
-	/* Some PCI-based MFD need the parent here */
-	if (pdev->dev.parent != &platform_bus && !np)
-		host = sdhci_alloc_host(pdev->dev.parent,
-			sizeof(struct sdhci_pltfm_host) + priv_size);
-	else
-		host = sdhci_alloc_host(&pdev->dev,
-			sizeof(struct sdhci_pltfm_host) + priv_size);
+	host = sdhci_alloc_host(&pdev->dev,
+		sizeof(struct sdhci_pltfm_host) + priv_size);
 
 	if (IS_ERR(host)) {
 		ret = PTR_ERR(host);
diff --git a/drivers/mmc/host/sdhci-pxav2.c b/drivers/mmc/host/sdhci-pxav2.c
index 3c0f3c0a1cc8..b4c23e983baf 100644
--- a/drivers/mmc/host/sdhci-pxav2.c
+++ b/drivers/mmc/host/sdhci-pxav2.c
@@ -261,7 +261,6 @@ static int sdhci_pxav2_remove(struct platform_device *pdev)
 static struct platform_driver sdhci_pxav2_driver = {
 	.driver		= {
 		.name	= "sdhci-pxav2",
-		.owner	= THIS_MODULE,
 #ifdef CONFIG_OF
 		.of_match_table = sdhci_pxav2_of_match,
 #endif
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index 6f842fb8e6b8..5036d7d39529 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -224,12 +224,11 @@ static void pxav3_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs)
 
 static const struct sdhci_ops pxav3_sdhci_ops = {
 	.set_clock = sdhci_set_clock,
-	.set_uhs_signaling = pxav3_set_uhs_signaling,
 	.platform_send_init_74_clocks = pxav3_gen_init_74_clocks,
 	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
 	.set_bus_width = sdhci_set_bus_width,
 	.reset = pxav3_reset,
-	.set_uhs_signaling = sdhci_set_uhs_signaling,
+	.set_uhs_signaling = pxav3_set_uhs_signaling,
 };
 
 static struct sdhci_pltfm_data sdhci_pxav3_pdata = {
@@ -381,11 +380,11 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 
 	return 0;
 
-err_of_parse:
-err_cd_req:
 err_add_host:
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+err_of_parse:
+err_cd_req:
 	clk_disable_unprepare(clk);
 err_clk_get:
 err_mbus_win:
@@ -492,7 +491,6 @@ static struct platform_driver sdhci_pxav3_driver = {
 #ifdef CONFIG_OF
 		.of_match_table = sdhci_pxav3_of_match,
 #endif
-		.owner	= THIS_MODULE,
 		.pm	= SDHCI_PXAV3_PMOPS,
 	},
 	.probe		= sdhci_pxav3_probe,
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index fa5954a05449..0ce6eb17deaf 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -606,8 +606,6 @@ static int sdhci_s3c_probe(struct platform_device *pdev)
 	ret = sdhci_add_host(host);
 	if (ret) {
 		dev_err(dev, "sdhci_add_host() failed\n");
-		pm_runtime_forbid(&pdev->dev);
-		pm_runtime_get_noresume(&pdev->dev);
 		goto err_req_regs;
 	}
 
@@ -618,6 +616,8 @@ static int sdhci_s3c_probe(struct platform_device *pdev)
 	return 0;
 
  err_req_regs:
+	pm_runtime_disable(&pdev->dev);
+
  err_no_busclks:
 	clk_disable_unprepare(sc->clk_io);
 
@@ -747,7 +747,6 @@ static struct platform_driver sdhci_s3c_driver = {
 	.remove		= sdhci_s3c_remove,
 	.id_table	= sdhci_s3c_driver_ids,
 	.driver		= {
-		.owner	= THIS_MODULE,
 		.name	= "s3c-sdhci",
 		.of_match_table = of_match_ptr(sdhci_s3c_dt_match),
 		.pm	= SDHCI_S3C_PMOPS,
diff --git a/drivers/mmc/host/sdhci-sirf.c b/drivers/mmc/host/sdhci-sirf.c
index 17004531d089..dd29d47c07aa 100644
--- a/drivers/mmc/host/sdhci-sirf.c
+++ b/drivers/mmc/host/sdhci-sirf.c
@@ -15,6 +15,8 @@
 #include <linux/mmc/slot-gpio.h>
 #include "sdhci-pltfm.h"
 
+#define SDHCI_SIRF_8BITBUS BIT(3)
+
 struct sdhci_sirf_priv {
 	struct clk *clk;
 	int gpio_cd;
@@ -27,10 +29,30 @@ static unsigned int sdhci_sirf_get_max_clk(struct sdhci_host *host)
 	return clk_get_rate(priv->clk);
 }
 
+static void sdhci_sirf_set_bus_width(struct sdhci_host *host, int width)
+{
+	u8 ctrl;
+
+	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
+	ctrl &= ~(SDHCI_CTRL_4BITBUS | SDHCI_SIRF_8BITBUS);
+
+	/*
+	 * CSR atlas7 and prima2 SD host version is not 3.0
+	 * 8bit-width enable bit of CSR SD hosts is 3,
+	 * while stardard hosts use bit 5
+	 */
+	if (width == MMC_BUS_WIDTH_8)
+		ctrl |= SDHCI_SIRF_8BITBUS;
+	else if (width == MMC_BUS_WIDTH_4)
+		ctrl |= SDHCI_CTRL_4BITBUS;
+
+	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
+}
+
 static struct sdhci_ops sdhci_sirf_ops = {
 	.set_clock = sdhci_set_clock,
 	.get_max_clock	= sdhci_sirf_get_max_clk,
-	.set_bus_width = sdhci_set_bus_width,
+	.set_bus_width = sdhci_sirf_set_bus_width,
 	.reset = sdhci_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
@@ -94,6 +116,7 @@ static int sdhci_sirf_probe(struct platform_device *pdev)
 				ret);
 			goto err_request_cd;
 		}
+		mmc_gpiod_request_cd_irq(host->mmc);
 	}
 
 	return 0;
@@ -167,7 +190,6 @@ MODULE_DEVICE_TABLE(of, sdhci_sirf_of_match);
 static struct platform_driver sdhci_sirf_driver = {
 	.driver		= {
 		.name	= "sdhci-sirf",
-		.owner	= THIS_MODULE,
 		.of_match_table = sdhci_sirf_of_match,
 #ifdef CONFIG_PM_SLEEP
 		.pm	= &sdhci_sirf_pm_ops,
diff --git a/drivers/mmc/host/sdhci-spear.c b/drivers/mmc/host/sdhci-spear.c
index 9d535c7336ef..22e58268545f 100644
--- a/drivers/mmc/host/sdhci-spear.c
+++ b/drivers/mmc/host/sdhci-spear.c
@@ -230,7 +230,6 @@ MODULE_DEVICE_TABLE(of, sdhci_spear_id_table);
 static struct platform_driver sdhci_driver = {
 	.driver = {
 		.name	= "sdhci",
-		.owner	= THIS_MODULE,
 		.pm	= &sdhci_pm_ops,
 		.of_match_table = of_match_ptr(sdhci_spear_id_table),
 	},
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index 33100d10d176..59797106af93 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -318,7 +318,6 @@ static int sdhci_tegra_remove(struct platform_device *pdev)
 static struct platform_driver sdhci_tegra_driver = {
 	.driver		= {
 		.name	= "sdhci-tegra",
-		.owner	= THIS_MODULE,
 		.of_match_table = sdhci_tegra_dt_match,
 		.pm	= SDHCI_PLTFM_PMOPS,
 	},
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 37b2a9ae52ef..ada1a3ea3a87 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -707,19 +707,28 @@ static void sdhci_set_transfer_irqs(struct sdhci_host *host)
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 }
 
-static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
+static void sdhci_set_timeout(struct sdhci_host *host, struct mmc_command *cmd)
 {
 	u8 count;
+
+	if (host->ops->set_timeout) {
+		host->ops->set_timeout(host, cmd);
+	} else {
+		count = sdhci_calc_timeout(host, cmd);
+		sdhci_writeb(host, count, SDHCI_TIMEOUT_CONTROL);
+	}
+}
+
+static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
+{
 	u8 ctrl;
 	struct mmc_data *data = cmd->data;
 	int ret;
 
 	WARN_ON(host->data);
 
-	if (data || (cmd->flags & MMC_RSP_BUSY)) {
-		count = sdhci_calc_timeout(host, cmd);
-		sdhci_writeb(host, count, SDHCI_TIMEOUT_CONTROL);
-	}
+	if (data || (cmd->flags & MMC_RSP_BUSY))
+		sdhci_set_timeout(host, cmd);
 
 	if (!data)
 		return;
@@ -1007,6 +1016,7 @@ void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 	mod_timer(&host->timer, timeout);
 
 	host->cmd = cmd;
+	host->busy_handle = 0;
 
 	sdhci_prepare_data(host, cmd);
 
@@ -1194,7 +1204,6 @@ void sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
 clock_set:
 	if (real_div)
 		host->mmc->actual_clock = (host->max_clk * clk_mul) / real_div;
-
 	clk |= (div & SDHCI_DIV_MASK) << SDHCI_DIVIDER_SHIFT;
 	clk |= ((div & SDHCI_DIV_HI_MASK) >> SDHCI_DIV_MASK_LEN)
 		<< SDHCI_DIVIDER_HI_SHIFT;
@@ -1357,11 +1366,12 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 		present_state = sdhci_readl(host, SDHCI_PRESENT_STATE);
 		/*
 		 * Check if the re-tuning timer has already expired and there
-		 * is no on-going data transfer. If so, we need to execute
-		 * tuning procedure before sending command.
+		 * is no on-going data transfer and DAT0 is not busy. If so,
+		 * we need to execute tuning procedure before sending command.
 		 */
 		if ((host->flags & SDHCI_NEEDS_RETUNING) &&
-		    !(present_state & (SDHCI_DOING_WRITE | SDHCI_DOING_READ))) {
+		    !(present_state & (SDHCI_DOING_WRITE | SDHCI_DOING_READ)) &&
+		    (present_state & SDHCI_DATA_0_LVL_MASK)) {
 			if (mmc->card) {
 				/* eMMC uses cmd21 but sd and sdio use cmd19 */
 				tuning_opcode =
@@ -1471,6 +1481,18 @@ static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 	if (!ios->clock || ios->clock != host->clock) {
 		host->ops->set_clock(host, ios->clock);
 		host->clock = ios->clock;
+
+		if (host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK &&
+		    host->clock) {
+			host->timeout_clk = host->mmc->actual_clock ?
+						host->mmc->actual_clock / 1000 :
+						host->clock / 1000;
+			host->mmc->max_busy_timeout =
+				host->ops->get_max_timeout_count ?
+				host->ops->get_max_timeout_count(host) :
+				1 << 27;
+			host->mmc->max_busy_timeout /= host->timeout_clk;
+		}
 	}
 
 	sdhci_set_power(host, ios->power_mode, ios->vdd);
@@ -1733,8 +1755,8 @@ static int sdhci_do_start_signal_voltage_switch(struct sdhci_host *host,
 			ret = regulator_set_voltage(mmc->supply.vqmmc, 2700000,
 						    3600000);
 			if (ret) {
-				pr_warning("%s: Switching to 3.3V signalling voltage "
-						" failed\n", mmc_hostname(mmc));
+				pr_warn("%s: Switching to 3.3V signalling voltage failed\n",
+					mmc_hostname(mmc));
 				return -EIO;
 			}
 		}
@@ -1746,8 +1768,8 @@ static int sdhci_do_start_signal_voltage_switch(struct sdhci_host *host,
 		if (!(ctrl & SDHCI_CTRL_VDD_180))
 			return 0;
 
-		pr_warning("%s: 3.3V regulator output did not became stable\n",
-				mmc_hostname(mmc));
+		pr_warn("%s: 3.3V regulator output did not became stable\n",
+			mmc_hostname(mmc));
 
 		return -EAGAIN;
 	case MMC_SIGNAL_VOLTAGE_180:
@@ -1755,8 +1777,8 @@ static int sdhci_do_start_signal_voltage_switch(struct sdhci_host *host,
 			ret = regulator_set_voltage(mmc->supply.vqmmc,
 					1700000, 1950000);
 			if (ret) {
-				pr_warning("%s: Switching to 1.8V signalling voltage "
-						" failed\n", mmc_hostname(mmc));
+				pr_warn("%s: Switching to 1.8V signalling voltage failed\n",
+					mmc_hostname(mmc));
 				return -EIO;
 			}
 		}
@@ -1773,8 +1795,8 @@ static int sdhci_do_start_signal_voltage_switch(struct sdhci_host *host,
 		if (ctrl & SDHCI_CTRL_VDD_180)
 			return 0;
 
-		pr_warning("%s: 1.8V regulator output did not became stable\n",
-				mmc_hostname(mmc));
+		pr_warn("%s: 1.8V regulator output did not became stable\n",
+			mmc_hostname(mmc));
 
 		return -EAGAIN;
 	case MMC_SIGNAL_VOLTAGE_120:
@@ -1782,8 +1804,8 @@ static int sdhci_do_start_signal_voltage_switch(struct sdhci_host *host,
 			ret = regulator_set_voltage(mmc->supply.vqmmc, 1100000,
 						    1300000);
 			if (ret) {
-				pr_warning("%s: Switching to 1.2V signalling voltage "
-						" failed\n", mmc_hostname(mmc));
+				pr_warn("%s: Switching to 1.2V signalling voltage failed\n",
+					mmc_hostname(mmc));
 				return -EIO;
 			}
 		}
@@ -2203,7 +2225,7 @@ static void sdhci_tuning_timer(unsigned long data)
  *                                                                           *
 \*****************************************************************************/
 
-static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask)
+static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask, u32 *mask)
 {
 	BUG_ON(intmask == 0);
 
@@ -2241,11 +2263,18 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask)
 		if (host->cmd->data)
 			DBG("Cannot wait for busy signal when also "
 				"doing a data transfer");
-		else if (!(host->quirks & SDHCI_QUIRK_NO_BUSY_IRQ))
+		else if (!(host->quirks & SDHCI_QUIRK_NO_BUSY_IRQ)
+				&& !host->busy_handle) {
+			/* Mark that command complete before busy is ended */
+			host->busy_handle = 1;
 			return;
+		}
 
 		/* The controller does not support the end-of-busy IRQ,
 		 * fall through and take the SDHCI_INT_RESPONSE */
+	} else if ((host->quirks2 & SDHCI_QUIRK2_STOP_WITH_TC) &&
+		   host->cmd->opcode == MMC_STOP_TRANSMISSION && !host->data) {
+		*mask &= ~SDHCI_INT_DATA_END;
 	}
 
 	if (intmask & SDHCI_INT_RESPONSE)
@@ -2304,8 +2333,21 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 		 * above in sdhci_cmd_irq().
 		 */
 		if (host->cmd && (host->cmd->flags & MMC_RSP_BUSY)) {
+			if (intmask & SDHCI_INT_DATA_TIMEOUT) {
+				host->cmd->error = -ETIMEDOUT;
+				tasklet_schedule(&host->finish_tasklet);
+				return;
+			}
 			if (intmask & SDHCI_INT_DATA_END) {
-				sdhci_finish_command(host);
+				/*
+				 * Some cards handle busy-end interrupt
+				 * before the command completed, so make
+				 * sure we do things in the proper order.
+				 */
+				if (host->busy_handle)
+					sdhci_finish_command(host);
+				else
+					host->busy_handle = 1;
 				return;
 			}
 		}
@@ -2442,7 +2484,8 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 		}
 
 		if (intmask & SDHCI_INT_CMD_MASK)
-			sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK);
+			sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK,
+				      &intmask);
 
 		if (intmask & SDHCI_INT_DATA_MASK)
 			sdhci_data_irq(host, intmask & SDHCI_INT_DATA_MASK);
@@ -2534,7 +2577,7 @@ void sdhci_enable_irq_wakeups(struct sdhci_host *host)
 }
 EXPORT_SYMBOL_GPL(sdhci_enable_irq_wakeups);
 
-void sdhci_disable_irq_wakeups(struct sdhci_host *host)
+static void sdhci_disable_irq_wakeups(struct sdhci_host *host)
 {
 	u8 val;
 	u8 mask = SDHCI_WAKE_ON_INSERT | SDHCI_WAKE_ON_REMOVE
@@ -2544,7 +2587,6 @@ void sdhci_disable_irq_wakeups(struct sdhci_host *host)
 	val &= ~mask;
 	sdhci_writeb(host, val, SDHCI_WAKE_UP_CONTROL);
 }
-EXPORT_SYMBOL_GPL(sdhci_disable_irq_wakeups);
 
 int sdhci_suspend_host(struct sdhci_host *host)
 {
@@ -2749,6 +2791,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	u32 caps[2] = {0, 0};
 	u32 max_current_caps;
 	unsigned int ocr_avail;
+	unsigned int override_timeout_clk;
 	int ret;
 
 	WARN_ON(host == NULL);
@@ -2762,6 +2805,8 @@ int sdhci_add_host(struct sdhci_host *host)
 	if (debug_quirks2)
 		host->quirks2 = debug_quirks2;
 
+	override_timeout_clk = host->timeout_clk;
+
 	sdhci_do_reset(host, SDHCI_RESET_ALL);
 
 	host->version = sdhci_readw(host, SDHCI_HOST_VERSION);
@@ -2807,8 +2852,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	if (host->flags & (SDHCI_USE_SDMA | SDHCI_USE_ADMA)) {
 		if (host->ops->enable_dma) {
 			if (host->ops->enable_dma(host)) {
-				pr_warning("%s: No suitable DMA "
-					"available. Falling back to PIO.\n",
+				pr_warn("%s: No suitable DMA available - falling back to PIO\n",
 					mmc_hostname(mmc));
 				host->flags &=
 					~(SDHCI_USE_SDMA | SDHCI_USE_ADMA);
@@ -2830,15 +2874,14 @@ int sdhci_add_host(struct sdhci_host *host)
 			dma_free_coherent(mmc_dev(mmc), ADMA_SIZE,
 					  host->adma_desc, host->adma_addr);
 			kfree(host->align_buffer);
-			pr_warning("%s: Unable to allocate ADMA "
-				"buffers. Falling back to standard DMA.\n",
+			pr_warn("%s: Unable to allocate ADMA buffers - falling back to standard DMA\n",
 				mmc_hostname(mmc));
 			host->flags &= ~SDHCI_USE_ADMA;
 			host->adma_desc = NULL;
 			host->align_buffer = NULL;
 		} else if (host->adma_addr & 3) {
-			pr_warning("%s: unable to allocate aligned ADMA descriptor\n",
-				   mmc_hostname(mmc));
+			pr_warn("%s: unable to allocate aligned ADMA descriptor\n",
+				mmc_hostname(mmc));
 			host->flags &= ~SDHCI_USE_ADMA;
 			dma_free_coherent(mmc_dev(mmc), ADMA_SIZE,
 					  host->adma_desc, host->adma_addr);
@@ -2908,25 +2951,30 @@ int sdhci_add_host(struct sdhci_host *host)
 	} else
 		mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_200;
 
-	host->timeout_clk =
-		(caps[0] & SDHCI_TIMEOUT_CLK_MASK) >> SDHCI_TIMEOUT_CLK_SHIFT;
-	if (host->timeout_clk == 0) {
-		if (host->ops->get_timeout_clock) {
-			host->timeout_clk = host->ops->get_timeout_clock(host);
-		} else if (!(host->quirks &
-				SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK)) {
-			pr_err("%s: Hardware doesn't specify timeout clock "
-			       "frequency.\n", mmc_hostname(mmc));
-			return -ENODEV;
+	if (!(host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK)) {
+		host->timeout_clk = (caps[0] & SDHCI_TIMEOUT_CLK_MASK) >>
+					SDHCI_TIMEOUT_CLK_SHIFT;
+		if (host->timeout_clk == 0) {
+			if (host->ops->get_timeout_clock) {
+				host->timeout_clk =
+					host->ops->get_timeout_clock(host);
+			} else {
+				pr_err("%s: Hardware doesn't specify timeout clock frequency.\n",
+					mmc_hostname(mmc));
+				return -ENODEV;
+			}
 		}
-	}
-	if (caps[0] & SDHCI_TIMEOUT_CLK_UNIT)
-		host->timeout_clk *= 1000;
 
-	if (host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK)
-		host->timeout_clk = mmc->f_max / 1000;
+		if (caps[0] & SDHCI_TIMEOUT_CLK_UNIT)
+			host->timeout_clk *= 1000;
 
-	mmc->max_busy_timeout = (1 << 27) / host->timeout_clk;
+		mmc->max_busy_timeout = host->ops->get_max_timeout_count ?
+			host->ops->get_max_timeout_count(host) : 1 << 27;
+		mmc->max_busy_timeout /= host->timeout_clk;
+	}
+
+	if (override_timeout_clk)
+		host->timeout_clk = override_timeout_clk;
 
 	mmc->caps |= MMC_CAP_SDIO_IRQ | MMC_CAP_ERASE | MMC_CAP_CMD23;
 	mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD;
@@ -2998,8 +3046,13 @@ int sdhci_add_host(struct sdhci_host *host)
 		/* SD3.0: SDR104 is supported so (for eMMC) the caps2
 		 * field can be promoted to support HS200.
 		 */
-		if (!(host->quirks2 & SDHCI_QUIRK2_BROKEN_HS200))
+		if (!(host->quirks2 & SDHCI_QUIRK2_BROKEN_HS200)) {
 			mmc->caps2 |= MMC_CAP2_HS200;
+			if (IS_ERR(mmc->supply.vqmmc) ||
+					!regulator_is_supported_voltage
+					(mmc->supply.vqmmc, 1100000, 1300000))
+				mmc->caps2 &= ~MMC_CAP2_HS200_1_2V_SDR;
+		}
 	} else if (caps[1] & SDHCI_SUPPORT_SDR50)
 		mmc->caps |= MMC_CAP_UHS_SDR50;
 
@@ -3049,7 +3102,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	 */
 	max_current_caps = sdhci_readl(host, SDHCI_MAX_CURRENT);
 	if (!max_current_caps && !IS_ERR(mmc->supply.vmmc)) {
-		u32 curr = regulator_get_current_limit(mmc->supply.vmmc);
+		int curr = regulator_get_current_limit(mmc->supply.vmmc);
 		if (curr > 0) {
 
 			/* convert to SDHCI_MAX_CURRENT format */
@@ -3158,8 +3211,8 @@ int sdhci_add_host(struct sdhci_host *host)
 		mmc->max_blk_size = (caps[0] & SDHCI_MAX_BLOCK_MASK) >>
 				SDHCI_MAX_BLOCK_SHIFT;
 		if (mmc->max_blk_size >= 3) {
-			pr_warning("%s: Invalid maximum block size, "
-				"assuming 512 bytes\n", mmc_hostname(mmc));
+			pr_warn("%s: Invalid maximum block size, assuming 512 bytes\n",
+				mmc_hostname(mmc));
 			mmc->max_blk_size = 0;
 		}
 	}
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 4a5cd5e3fa3e..31896a779d4e 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -72,6 +72,7 @@
 #define  SDHCI_WRITE_PROTECT	0x00080000
 #define  SDHCI_DATA_LVL_MASK	0x00F00000
 #define   SDHCI_DATA_LVL_SHIFT	20
+#define   SDHCI_DATA_0_LVL_MASK	0x00100000
 
 #define SDHCI_HOST_CONTROL	0x28
 #define  SDHCI_CTRL_LED		0x01
@@ -281,6 +282,9 @@ struct sdhci_ops {
 	unsigned int	(*get_max_clock)(struct sdhci_host *host);
 	unsigned int	(*get_min_clock)(struct sdhci_host *host);
 	unsigned int	(*get_timeout_clock)(struct sdhci_host *host);
+	unsigned int	(*get_max_timeout_count)(struct sdhci_host *host);
+	void		(*set_timeout)(struct sdhci_host *host,
+				       struct mmc_command *cmd);
 	void		(*set_bus_width)(struct sdhci_host *host, int width);
 	void (*platform_send_init_74_clocks)(struct sdhci_host *host,
 					     u8 power_mode);
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index d11708c815d7..7d9d6a321521 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -1553,7 +1553,6 @@ static struct platform_driver sh_mmcif_driver = {
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.pm	= &sh_mmcif_dev_pm_ops,
-		.owner	= THIS_MODULE,
 		.of_match_table = mmcif_of_match,
 	},
 };
diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 91058dabd11a..a2e81a1ea6af 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -39,6 +39,7 @@ struct sh_mobile_sdhi_of_data {
 	unsigned long tmio_flags;
 	unsigned long capabilities;
 	unsigned long capabilities2;
+	dma_addr_t dma_rx_offset;
 };
 
 static const struct sh_mobile_sdhi_of_data sh_mobile_sdhi_of_cfg[] = {
@@ -48,14 +49,16 @@ static const struct sh_mobile_sdhi_of_data sh_mobile_sdhi_of_cfg[] = {
 };
 
 static const struct sh_mobile_sdhi_of_data of_rcar_gen1_compatible = {
-	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_WRPROTECT_DISABLE,
+	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_WRPROTECT_DISABLE |
+			  TMIO_MMC_CLK_ACTUAL,
 	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ,
 };
 
 static const struct sh_mobile_sdhi_of_data of_rcar_gen2_compatible = {
-	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_WRPROTECT_DISABLE,
+	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT | TMIO_MMC_WRPROTECT_DISABLE |
+			  TMIO_MMC_CLK_ACTUAL,
 	.capabilities	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ,
-	.capabilities2	= MMC_CAP2_NO_MULTI_READ,
+	.dma_rx_offset	= 0x2000,
 };
 
 static const struct of_device_id sh_mobile_sdhi_of_match[] = {
@@ -68,6 +71,9 @@ static const struct of_device_id sh_mobile_sdhi_of_match[] = {
 	{ .compatible = "renesas,sdhi-r8a7779", .data = &of_rcar_gen1_compatible, },
 	{ .compatible = "renesas,sdhi-r8a7790", .data = &of_rcar_gen2_compatible, },
 	{ .compatible = "renesas,sdhi-r8a7791", .data = &of_rcar_gen2_compatible, },
+	{ .compatible = "renesas,sdhi-r8a7792", .data = &of_rcar_gen2_compatible, },
+	{ .compatible = "renesas,sdhi-r8a7793", .data = &of_rcar_gen2_compatible, },
+	{ .compatible = "renesas,sdhi-r8a7794", .data = &of_rcar_gen2_compatible, },
 	{},
 };
 MODULE_DEVICE_TABLE(of, sh_mobile_sdhi_of_match);
@@ -132,6 +138,24 @@ static int sh_mobile_sdhi_write16_hook(struct tmio_mmc_host *host, int addr)
 	return 0;
 }
 
+static int sh_mobile_sdhi_multi_io_quirk(struct mmc_card *card,
+					 unsigned int direction, int blk_size)
+{
+	/*
+	 * In Renesas controllers, when performing a
+	 * multiple block read of one or two blocks,
+	 * depending on the timing with which the
+	 * response register is read, the response
+	 * value may not be read properly.
+	 * Use single block read for this HW bug
+	 */
+	if ((direction == MMC_DATA_READ) &&
+	    blk_size == 2)
+		return 1;
+
+	return blk_size;
+}
+
 static void sh_mobile_sdhi_cd_wakeup(const struct platform_device *pdev)
 {
 	mmc_detect_change(platform_get_drvdata(pdev), msecs_to_jiffies(100));
@@ -187,6 +211,7 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	mmc_data->clk_disable = sh_mobile_sdhi_clk_disable;
 	mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED;
 	mmc_data->write16_hook = sh_mobile_sdhi_write16_hook;
+	mmc_data->multi_io_quirk = sh_mobile_sdhi_multi_io_quirk;
 	if (p) {
 		mmc_data->flags = p->tmio_flags;
 		mmc_data->ocr_mask = p->tmio_ocr_mask;
@@ -223,11 +248,27 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	 */
 	mmc_data->flags |= TMIO_MMC_SDIO_IRQ;
 
+	/*
+	 * All SDHI have CMD12 controll bit
+	 */
+	mmc_data->flags |= TMIO_MMC_HAVE_CMD12_CTRL;
+
+	/*
+	 * All SDHI need SDIO_INFO1 reserved bit
+	 */
+	mmc_data->flags |= TMIO_MMC_SDIO_STATUS_QUIRK;
+
+	/*
+	 * All SDHI have DMA control register
+	 */
+	mmc_data->flags |= TMIO_MMC_HAVE_CTL_DMA_REG;
+
 	if (of_id && of_id->data) {
 		const struct sh_mobile_sdhi_of_data *of_data = of_id->data;
 		mmc_data->flags |= of_data->tmio_flags;
 		mmc_data->capabilities |= of_data->capabilities;
 		mmc_data->capabilities2 |= of_data->capabilities2;
+		dma_priv->dma_rx_offset = of_data->dma_rx_offset;
 	}
 
 	/* SD control register space size is 0x100, 0x200 for bus_shift=1 */
@@ -332,8 +373,9 @@ static int sh_mobile_sdhi_remove(struct platform_device *pdev)
 }
 
 static const struct dev_pm_ops tmio_mmc_dev_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(tmio_mmc_host_suspend, tmio_mmc_host_resume)
-	SET_RUNTIME_PM_OPS(tmio_mmc_host_runtime_suspend,
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+			pm_runtime_force_resume)
+	SET_PM_RUNTIME_PM_OPS(tmio_mmc_host_runtime_suspend,
 			tmio_mmc_host_runtime_resume,
 			NULL)
 };
@@ -341,7 +383,6 @@ static const struct dev_pm_ops tmio_mmc_dev_pm_ops = {
 static struct platform_driver sh_mobile_sdhi_driver = {
 	.driver		= {
 		.name	= "sh_mobile_sdhi",
-		.owner	= THIS_MODULE,
 		.pm	= &tmio_mmc_dev_pm_ops,
 		.of_match_table = sh_mobile_sdhi_of_match,
 	},
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index 024f67c98cdc..d1663b3c4143 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -990,7 +990,8 @@ static int sunxi_mmc_probe(struct platform_device *pdev)
 	/* 400kHz ~ 50MHz */
 	mmc->f_min		=   400000;
 	mmc->f_max		= 50000000;
-	mmc->caps	       |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED;
+	mmc->caps	       |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED |
+				  MMC_CAP_ERASE;
 
 	ret = mmc_of_parse(mmc);
 	if (ret)
@@ -1035,7 +1036,6 @@ static int sunxi_mmc_remove(struct platform_device *pdev)
 static struct platform_driver sunxi_mmc_driver = {
 	.driver = {
 		.name	= "sunxi-mmc",
-		.owner	= THIS_MODULE,
 		.of_match_table = of_match_ptr(sunxi_mmc_of_match),
 	},
 	.probe		= sunxi_mmc_probe,
diff --git a/drivers/mmc/host/tifm_sd.c b/drivers/mmc/host/tifm_sd.c
index d1760ebcac03..93c4b40df90a 100644
--- a/drivers/mmc/host/tifm_sd.c
+++ b/drivers/mmc/host/tifm_sd.c
@@ -952,8 +952,8 @@ static int tifm_sd_probe(struct tifm_dev *sock)
 
 	if (!(TIFM_SOCK_STATE_OCCUPIED
 	      & readl(sock->addr + SOCK_PRESENT_STATE))) {
-		pr_warning("%s : card gone, unexpectedly\n",
-		       dev_name(&sock->dev));
+		pr_warn("%s : card gone, unexpectedly\n",
+			dev_name(&sock->dev));
 		return rc;
 	}
 
diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c
index cfad844730d8..659028ddb8b1 100644
--- a/drivers/mmc/host/tmio_mmc.c
+++ b/drivers/mmc/host/tmio_mmc.c
@@ -30,7 +30,7 @@ static int tmio_mmc_suspend(struct device *dev)
 	const struct mfd_cell *cell = mfd_get_cell(pdev);
 	int ret;
 
-	ret = tmio_mmc_host_suspend(dev);
+	ret = pm_runtime_force_suspend(dev);
 
 	/* Tell MFD core it can disable us now.*/
 	if (!ret && cell->disable)
@@ -50,7 +50,7 @@ static int tmio_mmc_resume(struct device *dev)
 		ret = cell->resume(pdev);
 
 	if (!ret)
-		ret = tmio_mmc_host_resume(dev);
+		ret = pm_runtime_force_resume(dev);
 
 	return ret;
 }
@@ -135,6 +135,9 @@ static int tmio_mmc_remove(struct platform_device *pdev)
 
 static const struct dev_pm_ops tmio_mmc_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(tmio_mmc_suspend, tmio_mmc_resume)
+	SET_PM_RUNTIME_PM_OPS(tmio_mmc_host_runtime_suspend,
+			tmio_mmc_host_runtime_resume,
+			NULL)
 };
 
 static struct platform_driver tmio_mmc_driver = {
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 100ffe0b2faf..a34ecbe1c1ad 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -40,22 +40,6 @@
 
 struct tmio_mmc_data;
 
-/*
- * We differentiate between the following 3 power states:
- * 1. card slot powered off, controller stopped. This is used, when either there
- *    is no card in the slot, or the card really has to be powered down.
- * 2. card slot powered on, controller stopped. This is used, when a card is in
- *    the slot, but no activity is currently taking place. This is a power-
- *    saving mode with card-state preserved. This state can be entered, e.g.
- *    when MMC clock-gating is used.
- * 3. card slot powered on, controller running. This is the actual active state.
- */
-enum tmio_mmc_power {
-	TMIO_MMC_OFF_STOP,	/* card power off, controller stopped */
-	TMIO_MMC_ON_STOP,	/* card power on, controller stopped */
-	TMIO_MMC_ON_RUN,	/* card power on, controller running */
-};
-
 struct tmio_mmc_host {
 	void __iomem *ctl;
 	struct mmc_command      *cmd;
@@ -63,9 +47,6 @@ struct tmio_mmc_host {
 	struct mmc_data         *data;
 	struct mmc_host         *mmc;
 
-	/* Controller and card power state */
-	enum tmio_mmc_power	power;
-
 	/* Callbacks for clock / power control */
 	void (*set_pwr)(struct platform_device *host, int state);
 	void (*set_clk_div)(struct platform_device *host, int state);
@@ -92,15 +73,16 @@ struct tmio_mmc_host {
 	struct delayed_work	delayed_reset_work;
 	struct work_struct	done;
 
-	/* Cache IRQ mask */
+	/* Cache */
 	u32			sdcard_irq_mask;
 	u32			sdio_irq_mask;
+	unsigned int		clk_cache;
 
 	spinlock_t		lock;		/* protect host private data */
 	unsigned long		last_req_ts;
 	struct mutex		ios_lock;	/* protect set_ios() context */
 	bool			native_hotplug;
-	bool			resuming;
+	bool			sdio_irq_enabled;
 };
 
 int tmio_mmc_host_probe(struct tmio_mmc_host **host,
@@ -162,12 +144,7 @@ static inline void tmio_mmc_abort_dma(struct tmio_mmc_host *host)
 }
 #endif
 
-#ifdef CONFIG_PM_SLEEP
-int tmio_mmc_host_suspend(struct device *dev);
-int tmio_mmc_host_resume(struct device *dev);
-#endif
-
-#ifdef CONFIG_PM_RUNTIME
+#ifdef CONFIG_PM
 int tmio_mmc_host_runtime_suspend(struct device *dev);
 int tmio_mmc_host_runtime_resume(struct device *dev);
 #endif
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index eb8f1d5c34b1..7d077388b9eb 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -28,10 +28,8 @@ void tmio_mmc_enable_dma(struct tmio_mmc_host *host, bool enable)
 	if (!host->chan_tx || !host->chan_rx)
 		return;
 
-#if defined(CONFIG_SUPERH) || defined(CONFIG_ARCH_SHMOBILE)
-	/* Switch DMA mode on or off - SuperH specific? */
-	sd_ctrl_write16(host, CTL_DMA_ENABLE, enable ? 2 : 0);
-#endif
+	if (host->pdata->flags & TMIO_MMC_HAVE_CTL_DMA_REG)
+		sd_ctrl_write16(host, CTL_DMA_ENABLE, enable ? 2 : 0);
 }
 
 void tmio_mmc_abort_dma(struct tmio_mmc_host *host)
@@ -312,7 +310,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat
 		if (pdata->dma->chan_priv_rx)
 			cfg.slave_id = pdata->dma->slave_id_rx;
 		cfg.direction = DMA_DEV_TO_MEM;
-		cfg.src_addr = cfg.dst_addr;
+		cfg.src_addr = cfg.dst_addr + pdata->dma->dma_rx_offset;
 		cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
 		cfg.dst_addr = 0;
 		ret = dmaengine_slave_config(host->chan_rx, &cfg);
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index faf0924e71cb..250bf8c9f998 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -44,6 +44,7 @@
 #include <linux/pm_qos.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
+#include <linux/mmc/sdio.h>
 #include <linux/scatterlist.h>
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
@@ -129,19 +130,28 @@ static void tmio_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
 {
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 
-	if (enable) {
+	if (enable && !host->sdio_irq_enabled) {
+		/* Keep device active while SDIO irq is enabled */
+		pm_runtime_get_sync(mmc_dev(mmc));
+		host->sdio_irq_enabled = true;
+
 		host->sdio_irq_mask = TMIO_SDIO_MASK_ALL &
 					~TMIO_SDIO_STAT_IOIRQ;
 		sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0001);
 		sd_ctrl_write16(host, CTL_SDIO_IRQ_MASK, host->sdio_irq_mask);
-	} else {
+	} else if (!enable && host->sdio_irq_enabled) {
 		host->sdio_irq_mask = TMIO_SDIO_MASK_ALL;
 		sd_ctrl_write16(host, CTL_SDIO_IRQ_MASK, host->sdio_irq_mask);
 		sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0000);
+
+		host->sdio_irq_enabled = false;
+		pm_runtime_mark_last_busy(mmc_dev(mmc));
+		pm_runtime_put_autosuspend(mmc_dev(mmc));
 	}
 }
 
-static void tmio_mmc_set_clock(struct tmio_mmc_host *host, int new_clock)
+static void tmio_mmc_set_clock(struct tmio_mmc_host *host,
+				unsigned int new_clock)
 {
 	u32 clk = 0, clock;
 
@@ -149,7 +159,11 @@ static void tmio_mmc_set_clock(struct tmio_mmc_host *host, int new_clock)
 		for (clock = host->mmc->f_min, clk = 0x80000080;
 			new_clock >= (clock<<1); clk >>= 1)
 			clock <<= 1;
-		clk |= 0x100;
+
+		/* 1/1 clock is option */
+		if ((host->pdata->flags & TMIO_MMC_CLK_ACTUAL) &&
+		    ((clk >> 22) & 0x1))
+			clk |= 0xff;
 	}
 
 	if (host->set_clk_div)
@@ -245,6 +259,9 @@ static void tmio_mmc_reset_work(struct work_struct *work)
 
 	tmio_mmc_abort_dma(host);
 	mmc_request_done(host->mmc, mrq);
+
+	pm_runtime_mark_last_busy(mmc_dev(host->mmc));
+	pm_runtime_put_autosuspend(mmc_dev(host->mmc));
 }
 
 /* called with host->lock held, interrupts disabled */
@@ -274,6 +291,9 @@ static void tmio_mmc_finish_request(struct tmio_mmc_host *host)
 		tmio_mmc_abort_dma(host);
 
 	mmc_request_done(host->mmc, mrq);
+
+	pm_runtime_mark_last_busy(mmc_dev(host->mmc));
+	pm_runtime_put_autosuspend(mmc_dev(host->mmc));
 }
 
 static void tmio_mmc_done_work(struct work_struct *work)
@@ -295,6 +315,7 @@ static void tmio_mmc_done_work(struct work_struct *work)
 #define TRANSFER_READ  0x1000
 #define TRANSFER_MULTI 0x2000
 #define SECURITY_CMD   0x4000
+#define NO_CMD12_ISSUE 0x4000 /* TMIO_MMC_HAVE_CMD12_CTRL */
 
 static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command *cmd)
 {
@@ -331,6 +352,14 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command
 		if (data->blocks > 1) {
 			sd_ctrl_write16(host, CTL_STOP_INTERNAL_ACTION, 0x100);
 			c |= TRANSFER_MULTI;
+
+			/*
+			 * Disable auto CMD12 at IO_RW_EXTENDED when
+			 * multiple block transfer
+			 */
+			if ((host->pdata->flags & TMIO_MMC_HAVE_CMD12_CTRL) &&
+			    (cmd->opcode == SD_IO_RW_EXTENDED))
+				c |= NO_CMD12_ISSUE;
 		}
 		if (data->flags & MMC_DATA_READ)
 			c |= TRANSFER_READ;
@@ -347,6 +376,40 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command
 	return 0;
 }
 
+static void tmio_mmc_transfer_data(struct tmio_mmc_host *host,
+				   unsigned short *buf,
+				   unsigned int count)
+{
+	int is_read = host->data->flags & MMC_DATA_READ;
+	u8  *buf8;
+
+	/*
+	 * Transfer the data
+	 */
+	if (is_read)
+		sd_ctrl_read16_rep(host, CTL_SD_DATA_PORT, buf, count >> 1);
+	else
+		sd_ctrl_write16_rep(host, CTL_SD_DATA_PORT, buf, count >> 1);
+
+	/* if count was even number */
+	if (!(count & 0x1))
+		return;
+
+	/* if count was odd number */
+	buf8 = (u8 *)(buf + (count >> 1));
+
+	/*
+	 * FIXME
+	 *
+	 * driver and this function are assuming that
+	 * it is used as little endian
+	 */
+	if (is_read)
+		*buf8 = sd_ctrl_read16(host, CTL_SD_DATA_PORT) & 0xff;
+	else
+		sd_ctrl_write16(host, CTL_SD_DATA_PORT, *buf8);
+}
+
 /*
  * This chip always returns (at least?) as much data as you ask for.
  * I'm unsure what happens if you ask for less than a block. This should be
@@ -379,10 +442,7 @@ static void tmio_mmc_pio_irq(struct tmio_mmc_host *host)
 		 count, host->sg_off, data->flags);
 
 	/* Transfer the data */
-	if (data->flags & MMC_DATA_READ)
-		sd_ctrl_read16_rep(host, CTL_SD_DATA_PORT, buf, count >> 1);
-	else
-		sd_ctrl_write16_rep(host, CTL_SD_DATA_PORT, buf, count >> 1);
+	tmio_mmc_transfer_data(host, buf, count);
 
 	host->sg_off += count;
 
@@ -465,6 +525,9 @@ static void tmio_mmc_data_irq(struct tmio_mmc_host *host)
 		goto out;
 
 	if (host->chan_tx && (data->flags & MMC_DATA_WRITE) && !host->force_pio) {
+		u32 status = sd_ctrl_read32(host, CTL_STATUS);
+		bool done = false;
+
 		/*
 		 * Has all data been written out yet? Testing on SuperH showed,
 		 * that in most cases the first interrupt comes already with the
@@ -473,7 +536,15 @@ static void tmio_mmc_data_irq(struct tmio_mmc_host *host)
 		 * DATAEND interrupt with the BUSY bit set, in this cases
 		 * waiting for one more interrupt fixes the problem.
 		 */
-		if (!(sd_ctrl_read32(host, CTL_STATUS) & TMIO_STAT_CMD_BUSY)) {
+		if (host->pdata->flags & TMIO_MMC_HAS_IDLE_WAIT) {
+			if (status & TMIO_STAT_ILL_FUNC)
+				done = true;
+		} else {
+			if (!(status & TMIO_STAT_CMD_BUSY))
+				done = true;
+		}
+
+		if (done) {
 			tmio_mmc_disable_mmc_irqs(host, TMIO_STAT_DATAEND);
 			tasklet_schedule(&host->dma_complete);
 		}
@@ -557,6 +628,9 @@ static void tmio_mmc_card_irq_status(struct tmio_mmc_host *host,
 
 	pr_debug_status(*status);
 	pr_debug_status(*ireg);
+
+	/* Clear the status except the interrupt status */
+	sd_ctrl_write32(host, CTL_STATUS, TMIO_MASK_IRQ);
 }
 
 static bool __tmio_mmc_card_detect_irq(struct tmio_mmc_host *host,
@@ -637,6 +711,7 @@ irqreturn_t tmio_mmc_sdio_irq(int irq, void *devid)
 	struct mmc_host *mmc = host->mmc;
 	struct tmio_mmc_data *pdata = host->pdata;
 	unsigned int ireg, status;
+	unsigned int sdio_status;
 
 	if (!(pdata->flags & TMIO_MMC_SDIO_IRQ))
 		return IRQ_HANDLED;
@@ -644,7 +719,11 @@ irqreturn_t tmio_mmc_sdio_irq(int irq, void *devid)
 	status = sd_ctrl_read16(host, CTL_SDIO_STATUS);
 	ireg = status & TMIO_SDIO_MASK_ALL & ~host->sdcard_irq_mask;
 
-	sd_ctrl_write16(host, CTL_SDIO_STATUS, status & ~TMIO_SDIO_MASK_ALL);
+	sdio_status = status & ~TMIO_SDIO_MASK_ALL;
+	if (pdata->flags & TMIO_MMC_SDIO_STATUS_QUIRK)
+		sdio_status |= 6;
+
+	sd_ctrl_write16(host, CTL_SDIO_STATUS, sdio_status);
 
 	if (mmc->caps & MMC_CAP_SDIO_IRQ && ireg & TMIO_SDIO_STAT_IOIRQ)
 		mmc_signal_sdio_irq(mmc);
@@ -728,6 +807,8 @@ static void tmio_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 	spin_unlock_irqrestore(&host->lock, flags);
 
+	pm_runtime_get_sync(mmc_dev(mmc));
+
 	if (mrq->data) {
 		ret = tmio_mmc_start_data(host, mrq->data);
 		if (ret)
@@ -746,11 +827,14 @@ fail:
 	host->mrq = NULL;
 	mrq->cmd->error = ret;
 	mmc_request_done(mmc, mrq);
+
+	pm_runtime_mark_last_busy(mmc_dev(mmc));
+	pm_runtime_put_autosuspend(mmc_dev(mmc));
 }
 
-static int tmio_mmc_clk_update(struct mmc_host *mmc)
+static int tmio_mmc_clk_update(struct tmio_mmc_host *host)
 {
-	struct tmio_mmc_host *host = mmc_priv(mmc);
+	struct mmc_host *mmc = host->mmc;
 	struct tmio_mmc_data *pdata = host->pdata;
 	int ret;
 
@@ -812,6 +896,19 @@ static void tmio_mmc_power_off(struct tmio_mmc_host *host)
 		host->set_pwr(host->pdev, 0);
 }
 
+static void tmio_mmc_set_bus_width(struct tmio_mmc_host *host,
+				unsigned char bus_width)
+{
+	switch (bus_width) {
+	case MMC_BUS_WIDTH_1:
+		sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, 0x80e0);
+		break;
+	case MMC_BUS_WIDTH_4:
+		sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, 0x00e0);
+		break;
+	}
+}
+
 /* Set MMC clock / power.
  * Note: This controller uses a simple divider scheme therefore it cannot
  * run a MMC card at full speed (20MHz). The max clock is 24MHz on SD, but as
@@ -824,6 +921,8 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	struct device *dev = &host->pdev->dev;
 	unsigned long flags;
 
+	pm_runtime_get_sync(mmc_dev(mmc));
+
 	mutex_lock(&host->ios_lock);
 
 	spin_lock_irqsave(&host->lock, flags);
@@ -850,60 +949,22 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 	spin_unlock_irqrestore(&host->lock, flags);
 
-	/*
-	 * host->power toggles between false and true in both cases - either
-	 * or not the controller can be runtime-suspended during inactivity.
-	 * But if the controller has to be kept on, the runtime-pm usage_count
-	 * is kept positive, so no suspending actually takes place.
-	 */
-	if (ios->power_mode == MMC_POWER_ON && ios->clock) {
-		if (host->power != TMIO_MMC_ON_RUN) {
-			tmio_mmc_clk_update(mmc);
-			pm_runtime_get_sync(dev);
-			if (host->resuming) {
-				tmio_mmc_reset(host);
-				host->resuming = false;
-			}
-		}
-		if (host->power == TMIO_MMC_OFF_STOP)
-			tmio_mmc_reset(host);
+	switch (ios->power_mode) {
+	case MMC_POWER_OFF:
+		tmio_mmc_power_off(host);
+		tmio_mmc_clk_stop(host);
+		break;
+	case MMC_POWER_UP:
 		tmio_mmc_set_clock(host, ios->clock);
-		if (host->power == TMIO_MMC_OFF_STOP)
-			/* power up SD card and the bus */
-			tmio_mmc_power_on(host, ios->vdd);
-		host->power = TMIO_MMC_ON_RUN;
-		/* start bus clock */
+		tmio_mmc_power_on(host, ios->vdd);
 		tmio_mmc_clk_start(host);
-	} else if (ios->power_mode != MMC_POWER_UP) {
-		struct tmio_mmc_data *pdata = host->pdata;
-		unsigned int old_power = host->power;
-
-		if (old_power != TMIO_MMC_OFF_STOP) {
-			if (ios->power_mode == MMC_POWER_OFF) {
-				tmio_mmc_power_off(host);
-				host->power = TMIO_MMC_OFF_STOP;
-			} else {
-				host->power = TMIO_MMC_ON_STOP;
-			}
-		}
-
-		if (old_power == TMIO_MMC_ON_RUN) {
-			tmio_mmc_clk_stop(host);
-			pm_runtime_put(dev);
-			if (pdata->clk_disable)
-				pdata->clk_disable(host->pdev);
-		}
-	}
-
-	if (host->power != TMIO_MMC_OFF_STOP) {
-		switch (ios->bus_width) {
-		case MMC_BUS_WIDTH_1:
-			sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, 0x80e0);
+		tmio_mmc_set_bus_width(host, ios->bus_width);
 		break;
-		case MMC_BUS_WIDTH_4:
-			sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, 0x00e0);
+	case MMC_POWER_ON:
+		tmio_mmc_set_clock(host, ios->clock);
+		tmio_mmc_clk_start(host);
+		tmio_mmc_set_bus_width(host, ios->bus_width);
 		break;
-		}
 	}
 
 	/* Let things settle. delay taken from winCE driver */
@@ -915,7 +976,12 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 			ios->clock, ios->power_mode);
 	host->mrq = NULL;
 
+	host->clk_cache = ios->clock;
+
 	mutex_unlock(&host->ios_lock);
+
+	pm_runtime_mark_last_busy(mmc_dev(mmc));
+	pm_runtime_put_autosuspend(mmc_dev(mmc));
 }
 
 static int tmio_mmc_get_ro(struct mmc_host *mmc)
@@ -926,8 +992,25 @@ static int tmio_mmc_get_ro(struct mmc_host *mmc)
 	if (ret >= 0)
 		return ret;
 
-	return !((pdata->flags & TMIO_MMC_WRPROTECT_DISABLE) ||
-		 (sd_ctrl_read32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT));
+	pm_runtime_get_sync(mmc_dev(mmc));
+	ret = !((pdata->flags & TMIO_MMC_WRPROTECT_DISABLE) ||
+		(sd_ctrl_read32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT));
+	pm_runtime_mark_last_busy(mmc_dev(mmc));
+	pm_runtime_put_autosuspend(mmc_dev(mmc));
+
+	return ret;
+}
+
+static int tmio_multi_io_quirk(struct mmc_card *card,
+			       unsigned int direction, int blk_size)
+{
+	struct tmio_mmc_host *host = mmc_priv(card->host);
+	struct tmio_mmc_data *pdata = host->pdata;
+
+	if (pdata->multi_io_quirk)
+		return pdata->multi_io_quirk(card, direction, blk_size);
+
+	return blk_size;
 }
 
 static const struct mmc_host_ops tmio_mmc_ops = {
@@ -936,6 +1019,7 @@ static const struct mmc_host_ops tmio_mmc_ops = {
 	.get_ro         = tmio_mmc_get_ro,
 	.get_cd		= mmc_gpio_get_cd,
 	.enable_sdio_irq = tmio_mmc_enable_sdio_irq,
+	.multi_io_quirk	= tmio_multi_io_quirk,
 };
 
 static int tmio_mmc_init_ocr(struct tmio_mmc_host *host)
@@ -1032,28 +1116,23 @@ int tmio_mmc_host_probe(struct tmio_mmc_host **host,
 				  mmc->caps & MMC_CAP_NONREMOVABLE ||
 				  mmc->slot.cd_irq >= 0);
 
-	_host->power = TMIO_MMC_OFF_STOP;
-	pm_runtime_enable(&pdev->dev);
-	ret = pm_runtime_resume(&pdev->dev);
-	if (ret < 0)
-		goto pm_disable;
-
-	if (tmio_mmc_clk_update(mmc) < 0) {
+	if (tmio_mmc_clk_update(_host) < 0) {
 		mmc->f_max = pdata->hclk;
 		mmc->f_min = mmc->f_max / 512;
 	}
 
 	/*
-	 * There are 4 different scenarios for the card detection:
-	 *  1) an external gpio irq handles the cd (best for power savings)
-	 *  2) internal sdhi irq handles the cd
-	 *  3) a worker thread polls the sdhi - indicated by MMC_CAP_NEEDS_POLL
-	 *  4) the medium is non-removable - indicated by MMC_CAP_NONREMOVABLE
-	 *
-	 *  While we increment the runtime PM counter for all scenarios when
-	 *  the mmc core activates us by calling an appropriate set_ios(), we
-	 *  must additionally ensure that in case 2) the tmio mmc hardware stays
-	 *  powered on during runtime for the card detection to work.
+	 * Check the sanity of mmc->f_min to prevent tmio_mmc_set_clock() from
+	 * looping forever...
+	 */
+	if (mmc->f_min == 0) {
+		ret = -EINVAL;
+		goto host_free;
+	}
+
+	/*
+	 * While using internal tmio hardware logic for card detection, we need
+	 * to ensure it stays powered for it to work.
 	 */
 	if (_host->native_hotplug)
 		pm_runtime_get_noresume(&pdev->dev);
@@ -1074,8 +1153,12 @@ int tmio_mmc_host_probe(struct tmio_mmc_host **host,
 
 	_host->sdcard_irq_mask &= ~irq_mask;
 
-	if (pdata->flags & TMIO_MMC_SDIO_IRQ)
-		tmio_mmc_enable_sdio_irq(mmc, 0);
+	_host->sdio_irq_enabled = false;
+	if (pdata->flags & TMIO_MMC_SDIO_IRQ) {
+		_host->sdio_irq_mask = TMIO_SDIO_MASK_ALL;
+		sd_ctrl_write16(_host, CTL_SDIO_IRQ_MASK, _host->sdio_irq_mask);
+		sd_ctrl_write16(_host, CTL_TRANSACTION_CTL, 0x0000);
+	}
 
 	spin_lock_init(&_host->lock);
 	mutex_init(&_host->ios_lock);
@@ -1087,9 +1170,12 @@ int tmio_mmc_host_probe(struct tmio_mmc_host **host,
 	/* See if we also get DMA */
 	tmio_mmc_request_dma(_host, pdata);
 
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, 50);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
 	ret = mmc_add_host(mmc);
-	if (pdata->clk_disable)
-		pdata->clk_disable(pdev);
 	if (ret < 0) {
 		tmio_mmc_host_remove(_host);
 		return ret;
@@ -1103,15 +1189,13 @@ int tmio_mmc_host_probe(struct tmio_mmc_host **host,
 			tmio_mmc_host_remove(_host);
 			return ret;
 		}
+		mmc_gpiod_request_cd_irq(mmc);
 	}
 
 	*host = _host;
 
 	return 0;
 
-pm_disable:
-	pm_runtime_disable(&pdev->dev);
-	iounmap(_host->ctl);
 host_free:
 	mmc_free_host(mmc);
 
@@ -1142,34 +1226,20 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host)
 }
 EXPORT_SYMBOL(tmio_mmc_host_remove);
 
-#ifdef CONFIG_PM_SLEEP
-int tmio_mmc_host_suspend(struct device *dev)
+#ifdef CONFIG_PM
+int tmio_mmc_host_runtime_suspend(struct device *dev)
 {
 	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 
 	tmio_mmc_disable_mmc_irqs(host, TMIO_MASK_ALL);
-	return 0;
-}
-EXPORT_SYMBOL(tmio_mmc_host_suspend);
-
-int tmio_mmc_host_resume(struct device *dev)
-{
-	struct mmc_host *mmc = dev_get_drvdata(dev);
-	struct tmio_mmc_host *host = mmc_priv(mmc);
 
-	tmio_mmc_enable_dma(host, true);
+	if (host->clk_cache)
+		tmio_mmc_clk_stop(host);
 
-	/* The MMC core will perform the complete set up */
-	host->resuming = true;
-	return 0;
-}
-EXPORT_SYMBOL(tmio_mmc_host_resume);
-#endif
+	if (host->pdata->clk_disable)
+		host->pdata->clk_disable(host->pdev);
 
-#ifdef CONFIG_PM_RUNTIME
-int tmio_mmc_host_runtime_suspend(struct device *dev)
-{
 	return 0;
 }
 EXPORT_SYMBOL(tmio_mmc_host_runtime_suspend);
@@ -1179,6 +1249,14 @@ int tmio_mmc_host_runtime_resume(struct device *dev)
 	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 
+	tmio_mmc_reset(host);
+	tmio_mmc_clk_update(host);
+
+	if (host->clk_cache) {
+		tmio_mmc_set_clock(host, host->clk_cache);
+		tmio_mmc_clk_start(host);
+	}
+
 	tmio_mmc_enable_dma(host, true);
 
 	return 0;
diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c
index 1defd5ed3236..9a6dfb0c4ecc 100644
--- a/drivers/mmc/host/wbsd.c
+++ b/drivers/mmc/host/wbsd.c
@@ -803,8 +803,7 @@ static void wbsd_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 		default:
 #ifdef CONFIG_MMC_DEBUG
-			pr_warning("%s: Data command %d is not "
-				"supported by this controller.\n",
+			pr_warn("%s: Data command %d is not supported by this controller\n",
 				mmc_hostname(host->mmc), cmd->opcode);
 #endif
 			cmd->error = -EINVAL;
@@ -1429,8 +1428,8 @@ free:
 	free_dma(dma);
 
 err:
-	pr_warning(DRIVER_NAME ": Unable to allocate DMA %d. "
-		"Falling back on FIFO.\n", dma);
+	pr_warn(DRIVER_NAME ": Unable to allocate DMA %d - falling back on FIFO\n",
+		dma);
 }
 
 static void wbsd_release_dma(struct wbsd_host *host)
@@ -1664,9 +1663,7 @@ static int wbsd_init(struct device *dev, int base, int irq, int dma,
 	ret = wbsd_scan(host);
 	if (ret) {
 		if (pnp && (ret == -ENODEV)) {
-			pr_warning(DRIVER_NAME
-				": Unable to confirm device presence. You may "
-				"experience lock-ups.\n");
+			pr_warn(DRIVER_NAME ": Unable to confirm device presence - you may experience lock-ups\n");
 		} else {
 			wbsd_free_mmc(dev);
 			return ret;
@@ -1688,10 +1685,7 @@ static int wbsd_init(struct device *dev, int base, int irq, int dma,
 	 */
 	if (pnp) {
 		if ((host->config != 0) && !wbsd_chip_validate(host)) {
-			pr_warning(DRIVER_NAME
-				": PnP active but chip not configured! "
-				"You probably have a buggy BIOS. "
-				"Configuring chip manually.\n");
+			pr_warn(DRIVER_NAME ": PnP active but chip not configured! You probably have a buggy BIOS. Configuring chip manually.\n");
 			wbsd_chip_config(host);
 		}
 	} else
@@ -1884,10 +1878,7 @@ static int wbsd_pnp_resume(struct pnp_dev *pnp_dev)
 	 */
 	if (host->config != 0) {
 		if (!wbsd_chip_validate(host)) {
-			pr_warning(DRIVER_NAME
-				": PnP active but chip not configured! "
-				"You probably have a buggy BIOS. "
-				"Configuring chip manually.\n");
+			pr_warn(DRIVER_NAME ": PnP active but chip not configured! You probably have a buggy BIOS. Configuring chip manually.\n");
 			wbsd_chip_config(host);
 		}
 	}
diff --git a/drivers/mtd/bcm47xxpart.c b/drivers/mtd/bcm47xxpart.c
index adfa74c1bc45..8057f52a45b7 100644
--- a/drivers/mtd/bcm47xxpart.c
+++ b/drivers/mtd/bcm47xxpart.c
@@ -199,6 +199,17 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 			continue;
 		}
 
+		/*
+		 * New (ARM?) devices may have NVRAM in some middle block. Last
+		 * block will be checked later, so skip it.
+		 */
+		if (offset != master->size - blocksize &&
+		    buf[0x000 / 4] == NVRAM_HEADER) {
+			bcm47xxpart_add_part(&parts[curr_part++], "nvram",
+					     offset, 0);
+			continue;
+		}
+
 		/* Read middle of the block */
 		if (mtd_read(master, offset + 0x8000, 0x4,
 			     &bytes_read, (uint8_t *)buf) < 0) {
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index 46c4643b7a07..c50d8cf0f60d 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -2033,6 +2033,8 @@ static int cfi_amdstd_panic_wait(struct map_info *map, struct flchip *chip,
 
 			udelay(1);
 		}
+
+		retries--;
 	}
 
 	/* the chip never became ready */
diff --git a/drivers/mtd/devices/Makefile b/drivers/mtd/devices/Makefile
index c68868f60588..f0b0e611d1d6 100644
--- a/drivers/mtd/devices/Makefile
+++ b/drivers/mtd/devices/Makefile
@@ -12,7 +12,6 @@ obj-$(CONFIG_MTD_LART)		+= lart.o
 obj-$(CONFIG_MTD_BLOCK2MTD)	+= block2mtd.o
 obj-$(CONFIG_MTD_DATAFLASH)	+= mtd_dataflash.o
 obj-$(CONFIG_MTD_M25P80)	+= m25p80.o
-obj-$(CONFIG_MTD_NAND_OMAP_BCH)	+= elm.o
 obj-$(CONFIG_MTD_SPEAR_SMI)	+= spear_smi.o
 obj-$(CONFIG_MTD_SST25L)	+= sst25l.o
 obj-$(CONFIG_MTD_BCM47XXSFLASH)	+= bcm47xxsflash.o
diff --git a/drivers/mtd/devices/docg3.c b/drivers/mtd/devices/docg3.c
index 91a169c44b39..21cc4b66feaa 100644
--- a/drivers/mtd/devices/docg3.c
+++ b/drivers/mtd/devices/docg3.c
@@ -1697,16 +1697,16 @@ static int dbg_asicmode_show(struct seq_file *s, void *p)
 
 	switch (mode) {
 	case DOC_ASICMODE_RESET:
-		pos += seq_printf(s, "reset");
+		pos += seq_puts(s, "reset");
 		break;
 	case DOC_ASICMODE_NORMAL:
-		pos += seq_printf(s, "normal");
+		pos += seq_puts(s, "normal");
 		break;
 	case DOC_ASICMODE_POWERDOWN:
-		pos += seq_printf(s, "powerdown");
+		pos += seq_puts(s, "powerdown");
 		break;
 	}
-	pos += seq_printf(s, ")\n");
+	pos += seq_puts(s, ")\n");
 	return pos;
 }
 DEBUGFS_RO_ATTR(asic_mode, dbg_asicmode_show);
@@ -1745,22 +1745,22 @@ static int dbg_protection_show(struct seq_file *s, void *p)
 	pos += seq_printf(s, "Protection = 0x%02x (",
 			 protect);
 	if (protect & DOC_PROTECT_FOUNDRY_OTP_LOCK)
-		pos += seq_printf(s, "FOUNDRY_OTP_LOCK,");
+		pos += seq_puts(s, "FOUNDRY_OTP_LOCK,");
 	if (protect & DOC_PROTECT_CUSTOMER_OTP_LOCK)
-		pos += seq_printf(s, "CUSTOMER_OTP_LOCK,");
+		pos += seq_puts(s, "CUSTOMER_OTP_LOCK,");
 	if (protect & DOC_PROTECT_LOCK_INPUT)
-		pos += seq_printf(s, "LOCK_INPUT,");
+		pos += seq_puts(s, "LOCK_INPUT,");
 	if (protect & DOC_PROTECT_STICKY_LOCK)
-		pos += seq_printf(s, "STICKY_LOCK,");
+		pos += seq_puts(s, "STICKY_LOCK,");
 	if (protect & DOC_PROTECT_PROTECTION_ENABLED)
-		pos += seq_printf(s, "PROTECTION ON,");
+		pos += seq_puts(s, "PROTECTION ON,");
 	if (protect & DOC_PROTECT_IPL_DOWNLOAD_LOCK)
-		pos += seq_printf(s, "IPL_DOWNLOAD_LOCK,");
+		pos += seq_puts(s, "IPL_DOWNLOAD_LOCK,");
 	if (protect & DOC_PROTECT_PROTECTION_ERROR)
-		pos += seq_printf(s, "PROTECT_ERR,");
+		pos += seq_puts(s, "PROTECT_ERR,");
 	else
-		pos += seq_printf(s, "NO_PROTECT_ERR");
-	pos += seq_printf(s, ")\n");
+		pos += seq_puts(s, "NO_PROTECT_ERR");
+	pos += seq_puts(s, ")\n");
 
 	pos += seq_printf(s, "DPS0 = 0x%02x : "
 			 "Protected area [0x%x - 0x%x] : OTP=%d, READ=%d, "
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index ed7e0a1bed3c..dcda6287228d 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -193,11 +193,14 @@ static int m25p_probe(struct spi_device *spi)
 {
 	struct mtd_part_parser_data	ppdata;
 	struct flash_platform_data	*data;
+	const struct spi_device_id *id = NULL;
 	struct m25p *flash;
 	struct spi_nor *nor;
 	enum read_mode mode = SPI_NOR_NORMAL;
 	int ret;
 
+	data = dev_get_platdata(&spi->dev);
+
 	flash = devm_kzalloc(&spi->dev, sizeof(*flash), GFP_KERNEL);
 	if (!flash)
 		return -ENOMEM;
@@ -223,11 +226,26 @@ static int m25p_probe(struct spi_device *spi)
 		mode = SPI_NOR_QUAD;
 	else if (spi->mode & SPI_RX_DUAL)
 		mode = SPI_NOR_DUAL;
-	ret = spi_nor_scan(nor, spi_get_device_id(spi), mode);
+
+	if (data && data->name)
+		flash->mtd.name = data->name;
+
+	/* For some (historical?) reason many platforms provide two different
+	 * names in flash_platform_data: "name" and "type". Quite often name is
+	 * set to "m25p80" and then "type" provides a real chip name.
+	 * If that's the case, respect "type" and ignore a "name".
+	 */
+	if (data && data->type)
+		id = spi_nor_match_id(data->type);
+
+	/* If we didn't get name from platform, simply use "modalias". */
+	if (!id)
+		id = spi_get_device_id(spi);
+
+	ret = spi_nor_scan(nor, id, mode);
 	if (ret)
 		return ret;
 
-	data = dev_get_platdata(&spi->dev);
 	ppdata.of_node = spi->dev.of_node;
 
 	return mtd_device_parse_register(&flash->mtd, NULL, &ppdata,
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index 21b2874a303b..ba801d2c6dcc 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -249,7 +249,7 @@ config MTD_CFI_FLAGADM
 
 config MTD_SOLUTIONENGINE
 	tristate "CFI Flash device mapped on Hitachi SolutionEngine"
-	depends on SUPERH && SOLUTION_ENGINE && MTD_CFI && MTD_REDBOOT_PARTS
+	depends on SOLUTION_ENGINE && MTD_CFI && MTD_REDBOOT_PARTS
 	help
 	  This enables access to the flash chips on the Hitachi SolutionEngine and
 	  similar boards. Say 'Y' if you are building a kernel for such a board.
diff --git a/drivers/mtd/maps/gpio-addr-flash.c b/drivers/mtd/maps/gpio-addr-flash.c
index a4c477b9fdd6..2fb346091af2 100644
--- a/drivers/mtd/maps/gpio-addr-flash.c
+++ b/drivers/mtd/maps/gpio-addr-flash.c
@@ -99,22 +99,28 @@ static map_word gf_read(struct map_info *map, unsigned long ofs)
  *	@from: flash offset to copy from
  *	@len:  how much to copy
  *
- * We rely on the MTD layer to chunk up copies such that a single request here
- * will not cross a window size.  This allows us to only wiggle the GPIOs once
- * before falling back to a normal memcpy.  Reading the higher layer code shows
- * that this is indeed the case, but add a BUG_ON() to future proof.
+ * The "from" region may straddle more than one window, so toggle the GPIOs for
+ * each window region before reading its data.
  */
 static void gf_copy_from(struct map_info *map, void *to, unsigned long from, ssize_t len)
 {
 	struct async_state *state = gf_map_info_to_state(map);
 
-	gf_set_gpios(state, from);
+	int this_len;
 
-	/* BUG if operation crosses the win_size */
-	BUG_ON(!((from + len) % state->win_size <= (from + len)));
+	while (len) {
+		if ((from % state->win_size) + len > state->win_size)
+			this_len = state->win_size - (from % state->win_size);
+		else
+			this_len = len;
 
-	/* operation does not cross the win_size, so one shot it */
-	memcpy_fromio(to, map->virt + (from % state->win_size), len);
+		gf_set_gpios(state, from);
+		memcpy_fromio(to, map->virt + (from % state->win_size),
+			 this_len);
+		len -= this_len;
+		from += this_len;
+		to += this_len;
+	}
 }
 
 /**
@@ -147,13 +153,21 @@ static void gf_copy_to(struct map_info *map, unsigned long to,
 {
 	struct async_state *state = gf_map_info_to_state(map);
 
-	gf_set_gpios(state, to);
+	int this_len;
+
+	while (len) {
+		if ((to % state->win_size) + len > state->win_size)
+			this_len = state->win_size - (to % state->win_size);
+		else
+			this_len = len;
 
-	/* BUG if operation crosses the win_size */
-	BUG_ON(!((to + len) % state->win_size <= (to + len)));
+		gf_set_gpios(state, to);
+		memcpy_toio(map->virt + (to % state->win_size), from, len);
 
-	/* operation does not cross the win_size, so one shot it */
-	memcpy_toio(map->virt + (to % state->win_size), from, len);
+		len -= this_len;
+		to += this_len;
+		from += this_len;
+	}
 }
 
 static const char * const part_probe_types[] = {
diff --git a/drivers/mtd/maps/pcmciamtd.c b/drivers/mtd/maps/pcmciamtd.c
index a3cfad392ed6..af747af5eee9 100644
--- a/drivers/mtd/maps/pcmciamtd.c
+++ b/drivers/mtd/maps/pcmciamtd.c
@@ -89,7 +89,7 @@ static caddr_t remap_window(struct map_info *map, unsigned long to)
 
 	if (!pcmcia_dev_present(dev->p_dev)) {
 		pr_debug("device removed\n");
-		return 0;
+		return NULL;
 	}
 
 	offset = to & ~(dev->win_size-1);
diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c
index 217c25d7381b..c1d21cb501ca 100644
--- a/drivers/mtd/maps/physmap_of.c
+++ b/drivers/mtd/maps/physmap_of.c
@@ -103,7 +103,7 @@ static struct mtd_info *obsolete_probe(struct platform_device *dev,
 		if (strcmp(of_probe, "ROM") != 0)
 			dev_warn(&dev->dev, "obsolete_probe: don't know probe "
 				 "type '%s', mapping as rom\n", of_probe);
-		return do_map_probe("mtd_rom", map);
+		return do_map_probe("map_rom", map);
 	}
 }
 
@@ -340,6 +340,10 @@ static struct of_device_id of_flash_match[] = {
 		.data           = (void *)"map_ram",
 	},
 	{
+		.compatible     = "mtd-rom",
+		.data           = (void *)"map_rom",
+	},
+	{
 		.type		= "rom",
 		.compatible	= "direct-mapped"
 	},
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 43e30992a369..d08229eb44d8 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -417,6 +417,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 	blk_queue_logical_block_size(new->rq, tr->blksize);
 
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, new->rq);
+	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, new->rq);
 
 	if (tr->discard) {
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, new->rq);
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index a0f54e80670c..53563955931b 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -549,6 +549,9 @@ static int mtdchar_blkpg_ioctl(struct mtd_info *mtd,
 		if (mtd_is_partition(mtd))
 			return -EINVAL;
 
+		/* Sanitize user input */
+		p.devname[BLKPG_DEVNAMELTH - 1] = '\0';
+
 		return mtd_add_partition(mtd, p.devname, p.start, p.length);
 
 	case BLKPG_DEL_PARTITION:
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index e4831b4159db..4c611871d7e6 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -105,12 +105,11 @@ static LIST_HEAD(mtd_notifiers);
  */
 static void mtd_release(struct device *dev)
 {
-	struct mtd_info __maybe_unused *mtd = dev_get_drvdata(dev);
+	struct mtd_info *mtd = dev_get_drvdata(dev);
 	dev_t index = MTD_DEVT(mtd->index);
 
-	/* remove /dev/mtdXro node if needed */
-	if (index)
-		device_destroy(&mtd_class, index + 1);
+	/* remove /dev/mtdXro node */
+	device_destroy(&mtd_class, index + 1);
 }
 
 static int mtd_cls_suspend(struct device *dev, pm_message_t state)
@@ -442,10 +441,8 @@ int add_mtd_device(struct mtd_info *mtd)
 	if (device_register(&mtd->dev) != 0)
 		goto fail_added;
 
-	if (MTD_DEVT(i))
-		device_create(&mtd_class, mtd->dev.parent,
-			      MTD_DEVT(i) + 1,
-			      NULL, "mtd%dro", i);
+	device_create(&mtd_class, mtd->dev.parent, MTD_DEVT(i) + 1, NULL,
+		      "mtd%dro", i);
 
 	pr_debug("mtd: Giving out device %d to %s\n", i, mtd->name);
 	/* No need to get a refcount on the module containing
@@ -778,7 +775,7 @@ EXPORT_SYMBOL_GPL(__put_mtd_device);
  */
 int mtd_erase(struct mtd_info *mtd, struct erase_info *instr)
 {
-	if (instr->addr > mtd->size || instr->len > mtd->size - instr->addr)
+	if (instr->addr >= mtd->size || instr->len > mtd->size - instr->addr)
 		return -EINVAL;
 	if (!(mtd->flags & MTD_WRITEABLE))
 		return -EROFS;
@@ -804,7 +801,7 @@ int mtd_point(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen,
 		*phys = 0;
 	if (!mtd->_point)
 		return -EOPNOTSUPP;
-	if (from < 0 || from > mtd->size || len > mtd->size - from)
+	if (from < 0 || from >= mtd->size || len > mtd->size - from)
 		return -EINVAL;
 	if (!len)
 		return 0;
@@ -817,7 +814,7 @@ int mtd_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 {
 	if (!mtd->_point)
 		return -EOPNOTSUPP;
-	if (from < 0 || from > mtd->size || len > mtd->size - from)
+	if (from < 0 || from >= mtd->size || len > mtd->size - from)
 		return -EINVAL;
 	if (!len)
 		return 0;
@@ -835,7 +832,7 @@ unsigned long mtd_get_unmapped_area(struct mtd_info *mtd, unsigned long len,
 {
 	if (!mtd->_get_unmapped_area)
 		return -EOPNOTSUPP;
-	if (offset > mtd->size || len > mtd->size - offset)
+	if (offset >= mtd->size || len > mtd->size - offset)
 		return -EINVAL;
 	return mtd->_get_unmapped_area(mtd, len, offset, flags);
 }
@@ -846,7 +843,7 @@ int mtd_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen,
 {
 	int ret_code;
 	*retlen = 0;
-	if (from < 0 || from > mtd->size || len > mtd->size - from)
+	if (from < 0 || from >= mtd->size || len > mtd->size - from)
 		return -EINVAL;
 	if (!len)
 		return 0;
@@ -869,7 +866,7 @@ int mtd_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
 	      const u_char *buf)
 {
 	*retlen = 0;
-	if (to < 0 || to > mtd->size || len > mtd->size - to)
+	if (to < 0 || to >= mtd->size || len > mtd->size - to)
 		return -EINVAL;
 	if (!mtd->_write || !(mtd->flags & MTD_WRITEABLE))
 		return -EROFS;
@@ -892,7 +889,7 @@ int mtd_panic_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
 	*retlen = 0;
 	if (!mtd->_panic_write)
 		return -EOPNOTSUPP;
-	if (to < 0 || to > mtd->size || len > mtd->size - to)
+	if (to < 0 || to >= mtd->size || len > mtd->size - to)
 		return -EINVAL;
 	if (!(mtd->flags & MTD_WRITEABLE))
 		return -EROFS;
@@ -1011,7 +1008,7 @@ int mtd_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	if (!mtd->_lock)
 		return -EOPNOTSUPP;
-	if (ofs < 0 || ofs > mtd->size || len > mtd->size - ofs)
+	if (ofs < 0 || ofs >= mtd->size || len > mtd->size - ofs)
 		return -EINVAL;
 	if (!len)
 		return 0;
@@ -1023,7 +1020,7 @@ int mtd_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	if (!mtd->_unlock)
 		return -EOPNOTSUPP;
-	if (ofs < 0 || ofs > mtd->size || len > mtd->size - ofs)
+	if (ofs < 0 || ofs >= mtd->size || len > mtd->size - ofs)
 		return -EINVAL;
 	if (!len)
 		return 0;
@@ -1035,7 +1032,7 @@ int mtd_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	if (!mtd->_is_locked)
 		return -EOPNOTSUPP;
-	if (ofs < 0 || ofs > mtd->size || len > mtd->size - ofs)
+	if (ofs < 0 || ofs >= mtd->size || len > mtd->size - ofs)
 		return -EINVAL;
 	if (!len)
 		return 0;
@@ -1045,7 +1042,7 @@ EXPORT_SYMBOL_GPL(mtd_is_locked);
 
 int mtd_block_isreserved(struct mtd_info *mtd, loff_t ofs)
 {
-	if (ofs < 0 || ofs > mtd->size)
+	if (ofs < 0 || ofs >= mtd->size)
 		return -EINVAL;
 	if (!mtd->_block_isreserved)
 		return 0;
@@ -1055,7 +1052,7 @@ EXPORT_SYMBOL_GPL(mtd_block_isreserved);
 
 int mtd_block_isbad(struct mtd_info *mtd, loff_t ofs)
 {
-	if (ofs < 0 || ofs > mtd->size)
+	if (ofs < 0 || ofs >= mtd->size)
 		return -EINVAL;
 	if (!mtd->_block_isbad)
 		return 0;
@@ -1067,7 +1064,7 @@ int mtd_block_markbad(struct mtd_info *mtd, loff_t ofs)
 {
 	if (!mtd->_block_markbad)
 		return -EOPNOTSUPP;
-	if (ofs < 0 || ofs > mtd->size)
+	if (ofs < 0 || ofs >= mtd->size)
 		return -EINVAL;
 	if (!(mtd->flags & MTD_WRITEABLE))
 		return -EROFS;
diff --git a/drivers/mtd/mtdswap.c b/drivers/mtd/mtdswap.c
index 8b33b26eb12b..fc8b3d16cce7 100644
--- a/drivers/mtd/mtdswap.c
+++ b/drivers/mtd/mtdswap.c
@@ -145,7 +145,7 @@ struct mtdswap_dev {
 struct mtdswap_oobdata {
 	__le16 magic;
 	__le32 count;
-} __attribute__((packed));
+} __packed;
 
 #define MTDSWAP_MAGIC_CLEAN	0x2095
 #define MTDSWAP_MAGIC_DIRTY	(MTDSWAP_MAGIC_CLEAN + 1)
@@ -1287,7 +1287,7 @@ static int mtdswap_show(struct seq_file *s, void *data)
 
 	seq_printf(s, "total erasures: %lu\n", sum);
 
-	seq_printf(s, "\n");
+	seq_puts(s, "\n");
 
 	seq_printf(s, "mtdswap_readsect count: %llu\n", d->sect_read_count);
 	seq_printf(s, "mtdswap_writesect count: %llu\n", d->sect_write_count);
@@ -1296,7 +1296,7 @@ static int mtdswap_show(struct seq_file *s, void *data)
 	seq_printf(s, "mtd write count: %llu\n", d->mtd_write_count);
 	seq_printf(s, "discarded pages count: %llu\n", d->discard_page_count);
 
-	seq_printf(s, "\n");
+	seq_puts(s, "\n");
 	seq_printf(s, "total pages: %u\n", pages);
 	seq_printf(s, "pages mapped: %u\n", mapped);
 
@@ -1474,7 +1474,7 @@ static void mtdswap_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
 	}
 
 	eblocks = mtd_div_by_eb(use_size, mtd);
-	use_size = eblocks * mtd->erasesize;
+	use_size = (uint64_t)eblocks * mtd->erasesize;
 	bad_blocks = mtdswap_badblocks(mtd, use_size);
 	eavailable = eblocks - bad_blocks;
 
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index f1cf503517fd..dd10646982ae 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -96,7 +96,7 @@ config MTD_NAND_OMAP2
 
 config MTD_NAND_OMAP_BCH
 	depends on MTD_NAND_OMAP2
-	tristate "Support hardware based BCH error correction"
+	bool "Support hardware based BCH error correction"
 	default n
 	select BCH
 	help
@@ -104,7 +104,10 @@ config MTD_NAND_OMAP_BCH
 	  locate and correct errors when using BCH ECC scheme. This offloads
 	  the cpu from doing ECC error searching and correction. However some
 	  legacy OMAP families like OMAP2xxx, OMAP3xxx do not have ELM engine
-	  so they should not enable this config symbol.
+	  so this is optional for them.
+
+config MTD_NAND_OMAP_BCH_BUILD
+	def_tristate MTD_NAND_OMAP2 && MTD_NAND_OMAP_BCH
 
 config MTD_NAND_IDS
 	tristate
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index a035e7cc6d46..9c847e469ca7 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_MTD_NAND_NDFC)		+= ndfc.o
 obj-$(CONFIG_MTD_NAND_ATMEL)		+= atmel_nand.o
 obj-$(CONFIG_MTD_NAND_GPIO)		+= gpio.o
 obj-$(CONFIG_MTD_NAND_OMAP2) 		+= omap2.o
+obj-$(CONFIG_MTD_NAND_OMAP_BCH_BUILD)	+= omap_elm.o
 obj-$(CONFIG_MTD_NAND_CM_X270)		+= cmx270_nand.o
 obj-$(CONFIG_MTD_NAND_PXA3xx)		+= pxa3xx_nand.o
 obj-$(CONFIG_MTD_NAND_TMIO)		+= tmio_nand.o
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index e321c564ff05..19d1e9d17bf9 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -27,6 +27,7 @@
  *
  */
 
+#include <linux/clk.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -96,6 +97,8 @@ struct atmel_nfc {
 	bool			use_nfc_sram;
 	bool			write_by_sram;
 
+	struct clk		*clk;
+
 	bool			is_initialized;
 	struct completion	comp_ready;
 	struct completion	comp_cmd_done;
@@ -128,8 +131,6 @@ struct atmel_nand_host {
 	u32			pmecc_lookup_table_offset_512;
 	u32			pmecc_lookup_table_offset_1024;
 
-	int			pmecc_bytes_per_sector;
-	int			pmecc_sector_number;
 	int			pmecc_degree;	/* Degree of remainders */
 	int			pmecc_cw_len;	/* Length of codeword */
 
@@ -841,7 +842,7 @@ static void pmecc_correct_data(struct mtd_info *mtd, uint8_t *buf, uint8_t *ecc,
 				pos, bit_pos, err_byte, *(buf + byte_pos));
 		} else {
 			/* Bit flip in OOB area */
-			tmp = sector_num * host->pmecc_bytes_per_sector
+			tmp = sector_num * nand_chip->ecc.bytes
 					+ (byte_pos - sector_size);
 			err_byte = ecc[tmp];
 			ecc[tmp] ^= (1 << bit_pos);
@@ -874,7 +875,7 @@ static int pmecc_correction(struct mtd_info *mtd, u32 pmecc_stat, uint8_t *buf,
 	return 0;
 
 normal_check:
-	for (i = 0; i < host->pmecc_sector_number; i++) {
+	for (i = 0; i < nand_chip->ecc.steps; i++) {
 		err_nbr = 0;
 		if (pmecc_stat & 0x1) {
 			buf_pos = buf + i * host->pmecc_sector_size;
@@ -890,7 +891,7 @@ normal_check:
 				return -EIO;
 			} else {
 				pmecc_correct_data(mtd, buf_pos, ecc, i,
-					host->pmecc_bytes_per_sector, err_nbr);
+					nand_chip->ecc.bytes, err_nbr);
 				mtd->ecc_stats.corrected += err_nbr;
 				total_err += err_nbr;
 			}
@@ -984,11 +985,11 @@ static int atmel_nand_pmecc_write_page(struct mtd_info *mtd,
 		cpu_relax();
 	}
 
-	for (i = 0; i < host->pmecc_sector_number; i++) {
-		for (j = 0; j < host->pmecc_bytes_per_sector; j++) {
+	for (i = 0; i < chip->ecc.steps; i++) {
+		for (j = 0; j < chip->ecc.bytes; j++) {
 			int pos;
 
-			pos = i * host->pmecc_bytes_per_sector + j;
+			pos = i * chip->ecc.bytes + j;
 			chip->oob_poi[eccpos[pos]] =
 				pmecc_readb_ecc_relaxed(host->ecc, i, j);
 		}
@@ -1031,7 +1032,7 @@ static void atmel_pmecc_core_init(struct mtd_info *mtd)
 	else if (host->pmecc_sector_size == 1024)
 		val |= PMECC_CFG_SECTOR1024;
 
-	switch (host->pmecc_sector_number) {
+	switch (nand_chip->ecc.steps) {
 	case 1:
 		val |= PMECC_CFG_PAGE_1SECTOR;
 		break;
@@ -1148,7 +1149,6 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev,
 
 	host->ecc = devm_ioremap_resource(&pdev->dev, regs);
 	if (IS_ERR(host->ecc)) {
-		dev_err(host->dev, "ioremap failed\n");
 		err_no = PTR_ERR(host->ecc);
 		goto err;
 	}
@@ -1156,8 +1156,6 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev,
 	regs_pmerr = platform_get_resource(pdev, IORESOURCE_MEM, 2);
 	host->pmerrloc_base = devm_ioremap_resource(&pdev->dev, regs_pmerr);
 	if (IS_ERR(host->pmerrloc_base)) {
-		dev_err(host->dev,
-			"Can not get I/O resource for PMECC ERRLOC controller!\n");
 		err_no = PTR_ERR(host->pmerrloc_base);
 		goto err;
 	}
@@ -1165,7 +1163,6 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev,
 	regs_rom = platform_get_resource(pdev, IORESOURCE_MEM, 3);
 	host->pmecc_rom_base = devm_ioremap_resource(&pdev->dev, regs_rom);
 	if (IS_ERR(host->pmecc_rom_base)) {
-		dev_err(host->dev, "Can not get I/O resource for ROM!\n");
 		err_no = PTR_ERR(host->pmecc_rom_base);
 		goto err;
 	}
@@ -1174,22 +1171,29 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev,
 
 	/* set ECC page size and oob layout */
 	switch (mtd->writesize) {
+	case 512:
+	case 1024:
 	case 2048:
+	case 4096:
+	case 8192:
+		if (sector_size > mtd->writesize) {
+			dev_err(host->dev, "pmecc sector size is bigger than the page size!\n");
+			err_no = -EINVAL;
+			goto err;
+		}
+
 		host->pmecc_degree = (sector_size == 512) ?
 			PMECC_GF_DIMENSION_13 : PMECC_GF_DIMENSION_14;
 		host->pmecc_cw_len = (1 << host->pmecc_degree) - 1;
-		host->pmecc_sector_number = mtd->writesize / sector_size;
-		host->pmecc_bytes_per_sector = pmecc_get_ecc_bytes(
-			cap, sector_size);
 		host->pmecc_alpha_to = pmecc_get_alpha_to(host);
 		host->pmecc_index_of = host->pmecc_rom_base +
 			host->pmecc_lookup_table_offset;
 
-		nand_chip->ecc.steps = host->pmecc_sector_number;
 		nand_chip->ecc.strength = cap;
-		nand_chip->ecc.bytes = host->pmecc_bytes_per_sector;
-		nand_chip->ecc.total = host->pmecc_bytes_per_sector *
-				       host->pmecc_sector_number;
+		nand_chip->ecc.bytes = pmecc_get_ecc_bytes(cap, sector_size);
+		nand_chip->ecc.steps = mtd->writesize / sector_size;
+		nand_chip->ecc.total = nand_chip->ecc.bytes *
+			nand_chip->ecc.steps;
 		if (nand_chip->ecc.total > mtd->oobsize - 2) {
 			dev_err(host->dev, "No room for ECC bytes\n");
 			err_no = -EINVAL;
@@ -1201,13 +1205,9 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev,
 
 		nand_chip->ecc.layout = &atmel_pmecc_oobinfo;
 		break;
-	case 512:
-	case 1024:
-	case 4096:
-		/* TODO */
+	default:
 		dev_warn(host->dev,
 			"Unsupported page size for PMECC, use Software ECC\n");
-	default:
 		/* page size not handled by HW ECC */
 		/* switching back to soft ECC */
 		nand_chip->ecc.mode = NAND_ECC_SOFT;
@@ -1530,10 +1530,8 @@ static int atmel_hw_nand_init_params(struct platform_device *pdev,
 	}
 
 	host->ecc = devm_ioremap_resource(&pdev->dev, regs);
-	if (IS_ERR(host->ecc)) {
-		dev_err(host->dev, "ioremap failed\n");
+	if (IS_ERR(host->ecc))
 		return PTR_ERR(host->ecc);
-	}
 
 	/* ECC is calculated for the whole page (1 step) */
 	nand_chip->ecc.size = mtd->writesize;
@@ -1907,15 +1905,7 @@ static int nfc_sram_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	if (offset || (data_len < mtd->writesize))
 		return -EINVAL;
 
-	cfg = nfc_readl(host->nfc->hsmc_regs, CFG);
 	len = mtd->writesize;
-
-	if (unlikely(raw)) {
-		len += mtd->oobsize;
-		nfc_writel(host->nfc->hsmc_regs, CFG, cfg | NFC_CFG_WSPARE);
-	} else
-		nfc_writel(host->nfc->hsmc_regs, CFG, cfg & ~NFC_CFG_WSPARE);
-
 	/* Copy page data to sram that will write to nand via NFC */
 	if (use_dma) {
 		if (atmel_nand_dma_op(mtd, (void *)buf, len, 0) != 0)
@@ -1925,6 +1915,15 @@ static int nfc_sram_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 		memcpy32_toio(sram, buf, len);
 	}
 
+	cfg = nfc_readl(host->nfc->hsmc_regs, CFG);
+	if (unlikely(raw) && oob_required) {
+		memcpy32_toio(sram + len, chip->oob_poi, mtd->oobsize);
+		len += mtd->oobsize;
+		nfc_writel(host->nfc->hsmc_regs, CFG, cfg | NFC_CFG_WSPARE);
+	} else {
+		nfc_writel(host->nfc->hsmc_regs, CFG, cfg & ~NFC_CFG_WSPARE);
+	}
+
 	if (chip->ecc.mode == NAND_ECC_HW && host->has_pmecc)
 		/*
 		 * When use NFC sram, need set up PMECC before send
@@ -2040,7 +2039,6 @@ static int atmel_nand_probe(struct platform_device *pdev)
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->io_base = devm_ioremap_resource(&pdev->dev, mem);
 	if (IS_ERR(host->io_base)) {
-		dev_err(&pdev->dev, "atmel_nand: ioremap resource failed\n");
 		res = PTR_ERR(host->io_base);
 		goto err_nand_ioremap;
 	}
@@ -2099,7 +2097,7 @@ static int atmel_nand_probe(struct platform_device *pdev)
 	}
 
 	nand_chip->ecc.mode = host->board.ecc_mode;
-	nand_chip->chip_delay = 20;		/* 20us command delay time */
+	nand_chip->chip_delay = 40;		/* 40us command delay time */
 
 	if (host->board.bus_width_16)	/* 16-bit bus width */
 		nand_chip->options |= NAND_BUSWIDTH_16;
@@ -2248,6 +2246,7 @@ static int atmel_nand_nfc_probe(struct platform_device *pdev)
 {
 	struct atmel_nfc *nfc = &nand_nfc;
 	struct resource *nfc_cmd_regs, *nfc_hsmc_regs, *nfc_sram;
+	int ret;
 
 	nfc_cmd_regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	nfc->base_cmd_regs = devm_ioremap_resource(&pdev->dev, nfc_cmd_regs);
@@ -2279,8 +2278,28 @@ static int atmel_nand_nfc_probe(struct platform_device *pdev)
 	nfc_writel(nfc->hsmc_regs, IDR, 0xffffffff);
 	nfc_readl(nfc->hsmc_regs, SR);	/* clear the NFC_SR */
 
+	nfc->clk = devm_clk_get(&pdev->dev, NULL);
+	if (!IS_ERR(nfc->clk)) {
+		ret = clk_prepare_enable(nfc->clk);
+		if (ret)
+			return ret;
+	} else {
+		dev_warn(&pdev->dev, "NFC clock missing, update your Device Tree");
+	}
+
 	nfc->is_initialized = true;
 	dev_info(&pdev->dev, "NFC is probed.\n");
+
+	return 0;
+}
+
+static int atmel_nand_nfc_remove(struct platform_device *pdev)
+{
+	struct atmel_nfc *nfc = &nand_nfc;
+
+	if (!IS_ERR(nfc->clk))
+		clk_disable_unprepare(nfc->clk);
+
 	return 0;
 }
 
@@ -2297,6 +2316,7 @@ static struct platform_driver atmel_nand_nfc_driver = {
 		.of_match_table = of_match_ptr(atmel_nand_nfc_match),
 	},
 	.probe = atmel_nand_nfc_probe,
+	.remove = atmel_nand_nfc_remove,
 };
 
 static struct platform_driver atmel_nand_driver = {
diff --git a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
index b2ab373c9eef..592befc7ffa1 100644
--- a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
+++ b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/delay.h>
 #include <linux/bcma/bcma.h>
 
 /* Broadcom uses 1'000'000 but it seems to be too many. Tests on WNDR4500 has
@@ -23,6 +24,8 @@
 #define NFLASH_SECTOR_SIZE		512
 
 #define NCTL_CMD0			0x00010000
+#define NCTL_COL			0x00020000	/* Update column with value from BCMA_CC_NFLASH_COL_ADDR */
+#define NCTL_ROW			0x00040000	/* Update row (page) with value from BCMA_CC_NFLASH_ROW_ADDR */
 #define NCTL_CMD1W			0x00080000
 #define NCTL_READ			0x00100000
 #define NCTL_WRITE			0x00200000
@@ -109,7 +112,7 @@ static void bcm47xxnflash_ops_bcm4706_read(struct mtd_info *mtd, uint8_t *buf,
 				b47n->curr_page_addr);
 
 		/* Prepare to read */
-		ctlcode = NCTL_CSA | NCTL_CMD1W | 0x00040000 | 0x00020000 |
+		ctlcode = NCTL_CSA | NCTL_CMD1W | NCTL_ROW | NCTL_COL |
 			  NCTL_CMD0;
 		ctlcode |= NAND_CMD_READSTART << 8;
 		if (bcm47xxnflash_ops_bcm4706_ctl_cmd(b47n->cc, ctlcode))
@@ -167,6 +170,26 @@ static void bcm47xxnflash_ops_bcm4706_write(struct mtd_info *mtd,
  * NAND chip ops
  **************************************************/
 
+static void bcm47xxnflash_ops_bcm4706_cmd_ctrl(struct mtd_info *mtd, int cmd,
+					       unsigned int ctrl)
+{
+	struct nand_chip *nand_chip = (struct nand_chip *)mtd->priv;
+	struct bcm47xxnflash *b47n = (struct bcm47xxnflash *)nand_chip->priv;
+	u32 code = 0;
+
+	if (cmd == NAND_CMD_NONE)
+		return;
+
+	if (cmd & NAND_CTRL_CLE)
+		code = cmd | NCTL_CMD0;
+
+	/* nCS is not needed for reset command */
+	if (cmd != NAND_CMD_RESET)
+		code |= NCTL_CSA;
+
+	bcm47xxnflash_ops_bcm4706_ctl_cmd(b47n->cc, code);
+}
+
 /* Default nand_select_chip calls cmd_ctrl, which is not used in BCM4706 */
 static void bcm47xxnflash_ops_bcm4706_select_chip(struct mtd_info *mtd,
 						  int chip)
@@ -174,6 +197,14 @@ static void bcm47xxnflash_ops_bcm4706_select_chip(struct mtd_info *mtd,
 	return;
 }
 
+static int bcm47xxnflash_ops_bcm4706_dev_ready(struct mtd_info *mtd)
+{
+	struct nand_chip *nand_chip = (struct nand_chip *)mtd->priv;
+	struct bcm47xxnflash *b47n = (struct bcm47xxnflash *)nand_chip->priv;
+
+	return !!(bcma_cc_read32(b47n->cc, BCMA_CC_NFLASH_CTL) & NCTL_READY);
+}
+
 /*
  * Default nand_command and nand_command_lp don't match BCM4706 hardware layout.
  * For example, reading chip id is performed in a non-standard way.
@@ -198,7 +229,10 @@ static void bcm47xxnflash_ops_bcm4706_cmdfunc(struct mtd_info *mtd,
 
 	switch (command) {
 	case NAND_CMD_RESET:
-		pr_warn("Chip reset not implemented yet\n");
+		nand_chip->cmd_ctrl(mtd, command, NAND_CTRL_CLE);
+
+		ndelay(100);
+		nand_wait_ready(mtd);
 		break;
 	case NAND_CMD_READID:
 		ctlcode = NCTL_CSA | 0x01000000 | NCTL_CMD1W | NCTL_CMD0;
@@ -242,7 +276,7 @@ static void bcm47xxnflash_ops_bcm4706_cmdfunc(struct mtd_info *mtd,
 	case NAND_CMD_ERASE1:
 		bcma_cc_write32(cc, BCMA_CC_NFLASH_ROW_ADDR,
 				b47n->curr_page_addr);
-		ctlcode = 0x00040000 | NCTL_CMD1W | NCTL_CMD0 |
+		ctlcode = NCTL_ROW | NCTL_CMD1W | NCTL_CMD0 |
 			  NAND_CMD_ERASE1 | (NAND_CMD_ERASE2 << 8);
 		if (bcm47xxnflash_ops_bcm4706_ctl_cmd(cc, ctlcode))
 			pr_err("ERASE1 failed\n");
@@ -257,13 +291,13 @@ static void bcm47xxnflash_ops_bcm4706_cmdfunc(struct mtd_info *mtd,
 				b47n->curr_page_addr);
 
 		/* Prepare to write */
-		ctlcode = 0x40000000 | 0x00040000 | 0x00020000 | 0x00010000;
+		ctlcode = 0x40000000 | NCTL_ROW | NCTL_COL | NCTL_CMD0;
 		ctlcode |= NAND_CMD_SEQIN;
 		if (bcm47xxnflash_ops_bcm4706_ctl_cmd(cc, ctlcode))
 			pr_err("SEQIN failed\n");
 		break;
 	case NAND_CMD_PAGEPROG:
-		if (bcm47xxnflash_ops_bcm4706_ctl_cmd(cc, 0x00010000 |
+		if (bcm47xxnflash_ops_bcm4706_ctl_cmd(cc, NCTL_CMD0 |
 							  NAND_CMD_PAGEPROG))
 			pr_err("PAGEPROG failed\n");
 		if (bcm47xxnflash_ops_bcm4706_poll(cc))
@@ -341,6 +375,7 @@ static void bcm47xxnflash_ops_bcm4706_write_buf(struct mtd_info *mtd,
 
 int bcm47xxnflash_ops_bcm4706_init(struct bcm47xxnflash *b47n)
 {
+	struct nand_chip *nand_chip = (struct nand_chip *)&b47n->nand_chip;
 	int err;
 	u32 freq;
 	u16 clock;
@@ -351,10 +386,14 @@ int bcm47xxnflash_ops_bcm4706_init(struct bcm47xxnflash *b47n)
 	u32 val;
 
 	b47n->nand_chip.select_chip = bcm47xxnflash_ops_bcm4706_select_chip;
+	nand_chip->cmd_ctrl = bcm47xxnflash_ops_bcm4706_cmd_ctrl;
+	nand_chip->dev_ready = bcm47xxnflash_ops_bcm4706_dev_ready;
 	b47n->nand_chip.cmdfunc = bcm47xxnflash_ops_bcm4706_cmdfunc;
 	b47n->nand_chip.read_byte = bcm47xxnflash_ops_bcm4706_read_byte;
 	b47n->nand_chip.read_buf = bcm47xxnflash_ops_bcm4706_read_buf;
 	b47n->nand_chip.write_buf = bcm47xxnflash_ops_bcm4706_write_buf;
+
+	nand_chip->chip_delay = 50;
 	b47n->nand_chip.bbt_options = NAND_BBT_USE_FLASH;
 	b47n->nand_chip.ecc.mode = NAND_ECC_NONE; /* TODO: implement ECC */
 
@@ -364,11 +403,13 @@ int bcm47xxnflash_ops_bcm4706_init(struct bcm47xxnflash *b47n)
 
 	/* Configure wait counters */
 	if (b47n->cc->status & BCMA_CC_CHIPST_4706_PKG_OPTION) {
-		freq = 100000000;
+		/* 400 MHz */
+		freq = 400000000 / 4;
 	} else {
 		freq = bcma_chipco_pll_read(b47n->cc, 4);
-		freq = (freq * 0xFFF) >> 3;
-		freq = (freq * 25000000) >> 3;
+		freq = (freq & 0xFFF) >> 3;
+		/* Fixed reference clock 25 MHz and m = 2 */
+		freq = (freq * 25000000 / 2) / 4;
 	}
 	clock = freq / 1000000;
 	w0 = bcm47xxnflash_ops_bcm4706_ns_to_cycle(15, clock);
diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c
index 0b071a3136a2..b3b7ca1bafb8 100644
--- a/drivers/mtd/nand/denali.c
+++ b/drivers/mtd/nand/denali.c
@@ -29,20 +29,23 @@
 
 MODULE_LICENSE("GPL");
 
-/* We define a module parameter that allows the user to override
+/*
+ * We define a module parameter that allows the user to override
  * the hardware and decide what timing mode should be used.
  */
 #define NAND_DEFAULT_TIMINGS	-1
 
 static int onfi_timing_mode = NAND_DEFAULT_TIMINGS;
 module_param(onfi_timing_mode, int, S_IRUGO);
-MODULE_PARM_DESC(onfi_timing_mode, "Overrides default ONFI setting."
-			" -1 indicates use default timings");
+MODULE_PARM_DESC(onfi_timing_mode,
+	   "Overrides default ONFI setting. -1 indicates use default timings");
 
 #define DENALI_NAND_NAME    "denali-nand"
 
-/* We define a macro here that combines all interrupts this driver uses into
- * a single constant value, for convenience. */
+/*
+ * We define a macro here that combines all interrupts this driver uses into
+ * a single constant value, for convenience.
+ */
 #define DENALI_IRQ_ALL	(INTR_STATUS__DMA_CMD_COMP | \
 			INTR_STATUS__ECC_TRANSACTION_DONE | \
 			INTR_STATUS__ECC_ERR | \
@@ -54,26 +57,34 @@ MODULE_PARM_DESC(onfi_timing_mode, "Overrides default ONFI setting."
 			INTR_STATUS__RST_COMP | \
 			INTR_STATUS__ERASE_COMP)
 
-/* indicates whether or not the internal value for the flash bank is
- * valid or not */
+/*
+ * indicates whether or not the internal value for the flash bank is
+ * valid or not
+ */
 #define CHIP_SELECT_INVALID	-1
 
 #define SUPPORT_8BITECC		1
 
-/* This macro divides two integers and rounds fractional values up
- * to the nearest integer value. */
+/*
+ * This macro divides two integers and rounds fractional values up
+ * to the nearest integer value.
+ */
 #define CEIL_DIV(X, Y) (((X)%(Y)) ? ((X)/(Y)+1) : ((X)/(Y)))
 
-/* this macro allows us to convert from an MTD structure to our own
+/*
+ * this macro allows us to convert from an MTD structure to our own
  * device context (denali) structure.
  */
 #define mtd_to_denali(m) container_of(m, struct denali_nand_info, mtd)
 
-/* These constants are defined by the driver to enable common driver
- * configuration options. */
+/*
+ * These constants are defined by the driver to enable common driver
+ * configuration options.
+ */
 #define SPARE_ACCESS		0x41
 #define MAIN_ACCESS		0x42
 #define MAIN_SPARE_ACCESS	0x43
+#define PIPELINE_ACCESS		0x2000
 
 #define DENALI_READ	0
 #define DENALI_WRITE	0x100
@@ -83,8 +94,10 @@ MODULE_PARM_DESC(onfi_timing_mode, "Overrides default ONFI setting."
 #define ADDR_CYCLE	1
 #define STATUS_CYCLE	2
 
-/* this is a helper macro that allows us to
- * format the bank into the proper bits for the controller */
+/*
+ * this is a helper macro that allows us to
+ * format the bank into the proper bits for the controller
+ */
 #define BANK(x) ((x) << 24)
 
 /* forward declarations */
@@ -95,12 +108,12 @@ static void denali_irq_enable(struct denali_nand_info *denali,
 							uint32_t int_mask);
 static uint32_t read_interrupt_status(struct denali_nand_info *denali);
 
-/* Certain operations for the denali NAND controller use
- * an indexed mode to read/write data. The operation is
- * performed by writing the address value of the command
- * to the device memory followed by the data. This function
+/*
+ * Certain operations for the denali NAND controller use an indexed mode to
+ * read/write data. The operation is performed by writing the address value
+ * of the command to the device memory followed by the data. This function
  * abstracts this common operation.
-*/
+ */
 static void index_addr(struct denali_nand_info *denali,
 				uint32_t address, uint32_t data)
 {
@@ -116,8 +129,10 @@ static void index_addr_read_data(struct denali_nand_info *denali,
 	*pdata = ioread32(denali->flash_mem + 0x10);
 }
 
-/* We need to buffer some data for some of the NAND core routines.
- * The operations manage buffering that data. */
+/*
+ * We need to buffer some data for some of the NAND core routines.
+ * The operations manage buffering that data.
+ */
 static void reset_buf(struct denali_nand_info *denali)
 {
 	denali->buf.head = denali->buf.tail = 0;
@@ -131,7 +146,7 @@ static void write_byte_to_buf(struct denali_nand_info *denali, uint8_t byte)
 /* reads the status of the device */
 static void read_status(struct denali_nand_info *denali)
 {
-	uint32_t cmd = 0x0;
+	uint32_t cmd;
 
 	/* initialize the data buffer to store status */
 	reset_buf(denali);
@@ -146,9 +161,8 @@ static void read_status(struct denali_nand_info *denali)
 /* resets a specific device connected to the core */
 static void reset_bank(struct denali_nand_info *denali)
 {
-	uint32_t irq_status = 0;
-	uint32_t irq_mask = INTR_STATUS__RST_COMP |
-			    INTR_STATUS__TIME_OUT;
+	uint32_t irq_status;
+	uint32_t irq_mask = INTR_STATUS__RST_COMP | INTR_STATUS__TIME_OUT;
 
 	clear_interrupts(denali);
 
@@ -163,19 +177,18 @@ static void reset_bank(struct denali_nand_info *denali)
 /* Reset the flash controller */
 static uint16_t denali_nand_reset(struct denali_nand_info *denali)
 {
-	uint32_t i;
+	int i;
 
 	dev_dbg(denali->dev, "%s, Line %d, Function: %s\n",
-		       __FILE__, __LINE__, __func__);
+		__FILE__, __LINE__, __func__);
 
-	for (i = 0 ; i < denali->max_banks; i++)
+	for (i = 0; i < denali->max_banks; i++)
 		iowrite32(INTR_STATUS__RST_COMP | INTR_STATUS__TIME_OUT,
 		denali->flash_reg + INTR_STATUS(i));
 
-	for (i = 0 ; i < denali->max_banks; i++) {
+	for (i = 0; i < denali->max_banks; i++) {
 		iowrite32(1 << i, denali->flash_reg + DEVICE_RESET);
-		while (!(ioread32(denali->flash_reg +
-				INTR_STATUS(i)) &
+		while (!(ioread32(denali->flash_reg + INTR_STATUS(i)) &
 			(INTR_STATUS__RST_COMP | INTR_STATUS__TIME_OUT)))
 			cpu_relax();
 		if (ioread32(denali->flash_reg + INTR_STATUS(i)) &
@@ -186,12 +199,13 @@ static uint16_t denali_nand_reset(struct denali_nand_info *denali)
 
 	for (i = 0; i < denali->max_banks; i++)
 		iowrite32(INTR_STATUS__RST_COMP | INTR_STATUS__TIME_OUT,
-			denali->flash_reg + INTR_STATUS(i));
+			  denali->flash_reg + INTR_STATUS(i));
 
 	return PASS;
 }
 
-/* this routine calculates the ONFI timing values for a given mode and
+/*
+ * this routine calculates the ONFI timing values for a given mode and
  * programs the clocking register accordingly. The mode is determined by
  * the get_onfi_nand_para routine.
  */
@@ -219,7 +233,7 @@ static void nand_onfi_timing_set(struct denali_nand_info *denali,
 	uint16_t addr_2_data, re_2_we, re_2_re, we_2_re, cs_cnt;
 
 	dev_dbg(denali->dev, "%s, Line %d, Function: %s\n",
-		       __FILE__, __LINE__, __func__);
+		__FILE__, __LINE__, __func__);
 
 	en_lo = CEIL_DIV(Trp[mode], CLK_X);
 	en_hi = CEIL_DIV(Treh[mode], CLK_X);
@@ -239,9 +253,8 @@ static void nand_onfi_timing_set(struct denali_nand_info *denali,
 
 		data_invalid_rloh = (en_lo + en_hi) * CLK_X + Trloh[mode];
 
-		data_invalid =
-		    data_invalid_rhoh <
-		    data_invalid_rloh ? data_invalid_rhoh : data_invalid_rloh;
+		data_invalid = data_invalid_rhoh < data_invalid_rloh ?
+					data_invalid_rhoh : data_invalid_rloh;
 
 		dv_window = data_invalid - Trea[mode];
 
@@ -251,12 +264,12 @@ static void nand_onfi_timing_set(struct denali_nand_info *denali,
 
 	acc_clks = CEIL_DIV(Trea[mode], CLK_X);
 
-	while (((acc_clks * CLK_X) - Trea[mode]) < 3)
+	while (acc_clks * CLK_X - Trea[mode] < 3)
 		acc_clks++;
 
-	if ((data_invalid - acc_clks * CLK_X) < 2)
+	if (data_invalid - acc_clks * CLK_X < 2)
 		dev_warn(denali->dev, "%s, Line %d: Warning!\n",
-			__FILE__, __LINE__);
+			 __FILE__, __LINE__);
 
 	addr_2_data = CEIL_DIV(Tadl[mode], CLK_X);
 	re_2_we = CEIL_DIV(Trhw[mode], CLK_X);
@@ -269,7 +282,7 @@ static void nand_onfi_timing_set(struct denali_nand_info *denali,
 		cs_cnt = 1;
 
 	if (Tcea[mode]) {
-		while (((cs_cnt * CLK_X) + Trea[mode]) < Tcea[mode])
+		while (cs_cnt * CLK_X + Trea[mode] < Tcea[mode])
 			cs_cnt++;
 	}
 
@@ -279,8 +292,8 @@ static void nand_onfi_timing_set(struct denali_nand_info *denali,
 #endif
 
 	/* Sighting 3462430: Temporary hack for MT29F128G08CJABAWP:B */
-	if ((ioread32(denali->flash_reg + MANUFACTURER_ID) == 0) &&
-		(ioread32(denali->flash_reg + DEVICE_ID) == 0x88))
+	if (ioread32(denali->flash_reg + MANUFACTURER_ID) == 0 &&
+		ioread32(denali->flash_reg + DEVICE_ID) == 0x88)
 		acc_clks = 6;
 
 	iowrite32(acc_clks, denali->flash_reg + ACC_CLKS);
@@ -297,9 +310,11 @@ static void nand_onfi_timing_set(struct denali_nand_info *denali,
 static uint16_t get_onfi_nand_para(struct denali_nand_info *denali)
 {
 	int i;
-	/* we needn't to do a reset here because driver has already
+
+	/*
+	 * we needn't to do a reset here because driver has already
 	 * reset all the banks before
-	 * */
+	 */
 	if (!(ioread32(denali->flash_reg + ONFI_TIMING_MODE) &
 		ONFI_TIMING_MODE__VALUE))
 		return FAIL;
@@ -312,8 +327,10 @@ static uint16_t get_onfi_nand_para(struct denali_nand_info *denali)
 
 	nand_onfi_timing_set(denali, i);
 
-	/* By now, all the ONFI devices we know support the page cache */
-	/* rw feature. So here we enable the pipeline_rw_ahead feature */
+	/*
+	 * By now, all the ONFI devices we know support the page cache
+	 * rw feature. So here we enable the pipeline_rw_ahead feature
+	 */
 	/* iowrite32(1, denali->flash_reg + CACHE_WRITE_ENABLE); */
 	/* iowrite32(1, denali->flash_reg + CACHE_READ_ENABLE);  */
 
@@ -339,8 +356,10 @@ static void get_toshiba_nand_para(struct denali_nand_info *denali)
 {
 	uint32_t tmp;
 
-	/* Workaround to fix a controller bug which reports a wrong */
-	/* spare area size for some kind of Toshiba NAND device */
+	/*
+	 * Workaround to fix a controller bug which reports a wrong
+	 * spare area size for some kind of Toshiba NAND device
+	 */
 	if ((ioread32(denali->flash_reg + DEVICE_MAIN_AREA_SIZE) == 4096) &&
 		(ioread32(denali->flash_reg + DEVICE_SPARE_AREA_SIZE) == 64)) {
 		iowrite32(216, denali->flash_reg + DEVICE_SPARE_AREA_SIZE);
@@ -384,13 +403,14 @@ static void get_hynix_nand_para(struct denali_nand_info *denali,
 		break;
 	default:
 		dev_warn(denali->dev,
-			"Spectra: Unknown Hynix NAND (Device ID: 0x%x)."
-			"Will use default parameter values instead.\n",
-			device_id);
+			 "Spectra: Unknown Hynix NAND (Device ID: 0x%x).\n"
+			 "Will use default parameter values instead.\n",
+			 device_id);
 	}
 }
 
-/* determines how many NAND chips are connected to the controller. Note for
+/*
+ * determines how many NAND chips are connected to the controller. Note for
  * Intel CE4100 devices we don't support more than one device.
  */
 static void find_valid_banks(struct denali_nand_info *denali)
@@ -400,10 +420,9 @@ static void find_valid_banks(struct denali_nand_info *denali)
 
 	denali->total_used_banks = 1;
 	for (i = 0; i < denali->max_banks; i++) {
-		index_addr(denali, (uint32_t)(MODE_11 | (i << 24) | 0), 0x90);
-		index_addr(denali, (uint32_t)(MODE_11 | (i << 24) | 1), 0);
-		index_addr_read_data(denali,
-				(uint32_t)(MODE_11 | (i << 24) | 2), &id[i]);
+		index_addr(denali, MODE_11 | (i << 24) | 0, 0x90);
+		index_addr(denali, MODE_11 | (i << 24) | 1, 0);
+		index_addr_read_data(denali, MODE_11 | (i << 24) | 2, &id[i]);
 
 		dev_dbg(denali->dev,
 			"Return 1st ID for bank[%d]: %x\n", i, id[i]);
@@ -420,14 +439,14 @@ static void find_valid_banks(struct denali_nand_info *denali)
 	}
 
 	if (denali->platform == INTEL_CE4100) {
-		/* Platform limitations of the CE4100 device limit
+		/*
+		 * Platform limitations of the CE4100 device limit
 		 * users to a single chip solution for NAND.
 		 * Multichip support is not enabled.
 		 */
 		if (denali->total_used_banks != 1) {
 			dev_err(denali->dev,
-					"Sorry, Intel CE4100 only supports "
-					"a single NAND device.\n");
+				"Sorry, Intel CE4100 only supports a single NAND device.\n");
 			BUG();
 		}
 	}
@@ -448,12 +467,13 @@ static void detect_max_banks(struct denali_nand_info *denali)
 
 static void detect_partition_feature(struct denali_nand_info *denali)
 {
-	/* For MRST platform, denali->fwblks represent the
+	/*
+	 * For MRST platform, denali->fwblks represent the
 	 * number of blocks firmware is taken,
 	 * FW is in protect partition and MTD driver has no
 	 * permission to access it. So let driver know how many
 	 * blocks it can't touch.
-	 * */
+	 */
 	if (ioread32(denali->flash_reg + FEATURES) & FEATURES__PARTITION) {
 		if ((ioread32(denali->flash_reg + PERM_SRC_ID(1)) &
 			PERM_SRC_ID__SRCID) == SPECTRA_PARTITION_ID) {
@@ -464,30 +484,32 @@ static void detect_partition_feature(struct denali_nand_info *denali)
 			    +
 			    (ioread32(denali->flash_reg + MIN_BLK_ADDR(1)) &
 			    MIN_BLK_ADDR__VALUE);
-		} else
+		} else {
 			denali->fwblks = SPECTRA_START_BLOCK;
-	} else
+		}
+	} else {
 		denali->fwblks = SPECTRA_START_BLOCK;
+	}
 }
 
 static uint16_t denali_nand_timing_set(struct denali_nand_info *denali)
 {
 	uint16_t status = PASS;
 	uint32_t id_bytes[8], addr;
-	uint8_t i, maf_id, device_id;
+	uint8_t maf_id, device_id;
+	int i;
 
-	dev_dbg(denali->dev,
-			"%s, Line %d, Function: %s\n",
+	dev_dbg(denali->dev, "%s, Line %d, Function: %s\n",
 			__FILE__, __LINE__, __func__);
 
-	/* Use read id method to get device ID and other
-	 * params. For some NAND chips, controller can't
-	 * report the correct device ID by reading from
-	 * DEVICE_ID register
-	 * */
-	addr = (uint32_t)MODE_11 | BANK(denali->flash_bank);
-	index_addr(denali, (uint32_t)addr | 0, 0x90);
-	index_addr(denali, (uint32_t)addr | 1, 0);
+	/*
+	 * Use read id method to get device ID and other params.
+	 * For some NAND chips, controller can't report the correct
+	 * device ID by reading from DEVICE_ID register
+	 */
+	addr = MODE_11 | BANK(denali->flash_bank);
+	index_addr(denali, addr | 0, 0x90);
+	index_addr(denali, addr | 1, 0);
 	for (i = 0; i < 8; i++)
 		index_addr_read_data(denali, addr | 2, &id_bytes[i]);
 	maf_id = id_bytes[0];
@@ -506,7 +528,7 @@ static uint16_t denali_nand_timing_set(struct denali_nand_info *denali)
 	}
 
 	dev_info(denali->dev,
-			"Dump timing register values:"
+			"Dump timing register values:\n"
 			"acc_clks: %d, re_2_we: %d, re_2_re: %d\n"
 			"we_2_re: %d, addr_2_data: %d, rdwr_en_lo_cnt: %d\n"
 			"rdwr_en_hi_cnt: %d, cs_setup_cnt: %d\n",
@@ -523,7 +545,8 @@ static uint16_t denali_nand_timing_set(struct denali_nand_info *denali)
 
 	detect_partition_feature(denali);
 
-	/* If the user specified to override the default timings
+	/*
+	 * If the user specified to override the default timings
 	 * with a specific ONFI mode, we apply those changes here.
 	 */
 	if (onfi_timing_mode != NAND_DEFAULT_TIMINGS)
@@ -536,7 +559,7 @@ static void denali_set_intr_modes(struct denali_nand_info *denali,
 					uint16_t INT_ENABLE)
 {
 	dev_dbg(denali->dev, "%s, Line %d, Function: %s\n",
-		       __FILE__, __LINE__, __func__);
+		__FILE__, __LINE__, __func__);
 
 	if (INT_ENABLE)
 		iowrite32(1, denali->flash_reg + GLOBAL_INT_ENABLE);
@@ -544,17 +567,18 @@ static void denali_set_intr_modes(struct denali_nand_info *denali,
 		iowrite32(0, denali->flash_reg + GLOBAL_INT_ENABLE);
 }
 
-/* validation function to verify that the controlling software is making
+/*
+ * validation function to verify that the controlling software is making
  * a valid request
  */
 static inline bool is_flash_bank_valid(int flash_bank)
 {
-	return (flash_bank >= 0 && flash_bank < 4);
+	return flash_bank >= 0 && flash_bank < 4;
 }
 
 static void denali_irq_init(struct denali_nand_info *denali)
 {
-	uint32_t int_mask = 0;
+	uint32_t int_mask;
 	int i;
 
 	/* Disable global interrupts */
@@ -584,7 +608,8 @@ static void denali_irq_enable(struct denali_nand_info *denali,
 		iowrite32(int_mask, denali->flash_reg + INTR_EN(i));
 }
 
-/* This function only returns when an interrupt that this driver cares about
+/*
+ * This function only returns when an interrupt that this driver cares about
  * occurs. This is to reduce the overhead of servicing interrupts
  */
 static inline uint32_t denali_irq_detected(struct denali_nand_info *denali)
@@ -596,7 +621,7 @@ static inline uint32_t denali_irq_detected(struct denali_nand_info *denali)
 static inline void clear_interrupt(struct denali_nand_info *denali,
 							uint32_t irq_mask)
 {
-	uint32_t intr_status_reg = 0;
+	uint32_t intr_status_reg;
 
 	intr_status_reg = INTR_STATUS(denali->flash_bank);
 
@@ -605,7 +630,8 @@ static inline void clear_interrupt(struct denali_nand_info *denali,
 
 static void clear_interrupts(struct denali_nand_info *denali)
 {
-	uint32_t status = 0x0;
+	uint32_t status;
+
 	spin_lock_irq(&denali->irq_lock);
 
 	status = read_interrupt_status(denali);
@@ -617,38 +643,40 @@ static void clear_interrupts(struct denali_nand_info *denali)
 
 static uint32_t read_interrupt_status(struct denali_nand_info *denali)
 {
-	uint32_t intr_status_reg = 0;
+	uint32_t intr_status_reg;
 
 	intr_status_reg = INTR_STATUS(denali->flash_bank);
 
 	return ioread32(denali->flash_reg + intr_status_reg);
 }
 
-/* This is the interrupt service routine. It handles all interrupts
- * sent to this device. Note that on CE4100, this is a shared
- * interrupt.
+/*
+ * This is the interrupt service routine. It handles all interrupts
+ * sent to this device. Note that on CE4100, this is a shared interrupt.
  */
 static irqreturn_t denali_isr(int irq, void *dev_id)
 {
 	struct denali_nand_info *denali = dev_id;
-	uint32_t irq_status = 0x0;
+	uint32_t irq_status;
 	irqreturn_t result = IRQ_NONE;
 
 	spin_lock(&denali->irq_lock);
 
-	/* check to see if a valid NAND chip has
-	 * been selected.
-	 */
+	/* check to see if a valid NAND chip has been selected. */
 	if (is_flash_bank_valid(denali->flash_bank)) {
-		/* check to see if controller generated
-		 * the interrupt, since this is a shared interrupt */
+		/*
+		 * check to see if controller generated the interrupt,
+		 * since this is a shared interrupt
+		 */
 		irq_status = denali_irq_detected(denali);
 		if (irq_status != 0) {
 			/* handle interrupt */
 			/* first acknowledge it */
 			clear_interrupt(denali, irq_status);
-			/* store the status in the device context for someone
-			   to read */
+			/*
+			 * store the status in the device context for someone
+			 * to read
+			 */
 			denali->irq_status |= irq_status;
 			/* notify anyone who cares that it happened */
 			complete(&denali->complete);
@@ -663,9 +691,8 @@ static irqreturn_t denali_isr(int irq, void *dev_id)
 
 static uint32_t wait_for_irq(struct denali_nand_info *denali, uint32_t irq_mask)
 {
-	unsigned long comp_res = 0;
-	uint32_t intr_status = 0;
-	bool retry = false;
+	unsigned long comp_res;
+	uint32_t intr_status;
 	unsigned long timeout = msecs_to_jiffies(1000);
 
 	do {
@@ -679,12 +706,13 @@ static uint32_t wait_for_irq(struct denali_nand_info *denali, uint32_t irq_mask)
 			spin_unlock_irq(&denali->irq_lock);
 			/* our interrupt was detected */
 			break;
-		} else {
-			/* these are not the interrupts you are looking for -
-			 * need to wait again */
-			spin_unlock_irq(&denali->irq_lock);
-			retry = true;
 		}
+
+		/*
+		 * these are not the interrupts you are looking for -
+		 * need to wait again
+		 */
+		spin_unlock_irq(&denali->irq_lock);
 	} while (comp_res != 0);
 
 	if (comp_res == 0) {
@@ -697,12 +725,14 @@ static uint32_t wait_for_irq(struct denali_nand_info *denali, uint32_t irq_mask)
 	return intr_status;
 }
 
-/* This helper function setups the registers for ECC and whether or not
- * the spare area will be transferred. */
+/*
+ * This helper function setups the registers for ECC and whether or not
+ * the spare area will be transferred.
+ */
 static void setup_ecc_for_xfer(struct denali_nand_info *denali, bool ecc_en,
 				bool transfer_spare)
 {
-	int ecc_en_flag = 0, transfer_spare_flag = 0;
+	int ecc_en_flag, transfer_spare_flag;
 
 	/* set ECC, transfer spare bits if needed */
 	ecc_en_flag = ecc_en ? ECC_ENABLE__FLAG : 0;
@@ -710,22 +740,20 @@ static void setup_ecc_for_xfer(struct denali_nand_info *denali, bool ecc_en,
 
 	/* Enable spare area/ECC per user's request. */
 	iowrite32(ecc_en_flag, denali->flash_reg + ECC_ENABLE);
-	iowrite32(transfer_spare_flag,
-			denali->flash_reg + TRANSFER_SPARE_REG);
+	iowrite32(transfer_spare_flag, denali->flash_reg + TRANSFER_SPARE_REG);
 }
 
-/* sends a pipeline command operation to the controller. See the Denali NAND
+/*
+ * sends a pipeline command operation to the controller. See the Denali NAND
  * controller's user guide for more information (section 4.2.3.6).
  */
 static int denali_send_pipeline_cmd(struct denali_nand_info *denali,
-							bool ecc_en,
-							bool transfer_spare,
-							int access_type,
-							int op)
+				    bool ecc_en, bool transfer_spare,
+				    int access_type, int op)
 {
 	int status = PASS;
-	uint32_t addr = 0x0, cmd = 0x0, page_count = 1, irq_status = 0,
-		 irq_mask = 0;
+	uint32_t page_count = 1;
+	uint32_t addr, cmd, irq_status, irq_mask;
 
 	if (op == DENALI_READ)
 		irq_mask = INTR_STATUS__LOAD_COMP;
@@ -736,7 +764,6 @@ static int denali_send_pipeline_cmd(struct denali_nand_info *denali,
 
 	setup_ecc_for_xfer(denali, ecc_en, transfer_spare);
 
-	/* clear interrupts */
 	clear_interrupts(denali);
 
 	addr = BANK(denali->flash_bank) | denali->page;
@@ -747,37 +774,38 @@ static int denali_send_pipeline_cmd(struct denali_nand_info *denali,
 	} else if (op == DENALI_WRITE && access_type == SPARE_ACCESS) {
 		/* read spare area */
 		cmd = MODE_10 | addr;
-		index_addr(denali, (uint32_t)cmd, access_type);
+		index_addr(denali, cmd, access_type);
 
 		cmd = MODE_01 | addr;
 		iowrite32(cmd, denali->flash_mem);
 	} else if (op == DENALI_READ) {
 		/* setup page read request for access type */
 		cmd = MODE_10 | addr;
-		index_addr(denali, (uint32_t)cmd, access_type);
+		index_addr(denali, cmd, access_type);
 
-		/* page 33 of the NAND controller spec indicates we should not
-		   use the pipeline commands in Spare area only mode. So we
-		   don't.
+		/*
+		 * page 33 of the NAND controller spec indicates we should not
+		 * use the pipeline commands in Spare area only mode.
+		 * So we don't.
 		 */
 		if (access_type == SPARE_ACCESS) {
 			cmd = MODE_01 | addr;
 			iowrite32(cmd, denali->flash_mem);
 		} else {
-			index_addr(denali, (uint32_t)cmd,
-					0x2000 | op | page_count);
+			index_addr(denali, cmd,
+					PIPELINE_ACCESS | op | page_count);
 
-			/* wait for command to be accepted
+			/*
+			 * wait for command to be accepted
 			 * can always use status0 bit as the
-			 * mask is identical for each
-			 * bank. */
+			 * mask is identical for each bank.
+			 */
 			irq_status = wait_for_irq(denali, irq_mask);
 
 			if (irq_status == 0) {
 				dev_err(denali->dev,
-						"cmd, page, addr on timeout "
-						"(0x%x, 0x%x, 0x%x)\n",
-						cmd, denali->page, addr);
+					"cmd, page, addr on timeout (0x%x, 0x%x, 0x%x)\n",
+					cmd, denali->page, addr);
 				status = FAIL;
 			} else {
 				cmd = MODE_01 | addr;
@@ -790,51 +818,51 @@ static int denali_send_pipeline_cmd(struct denali_nand_info *denali,
 
 /* helper function that simply writes a buffer to the flash */
 static int write_data_to_flash_mem(struct denali_nand_info *denali,
-							const uint8_t *buf,
-							int len)
+				   const uint8_t *buf, int len)
 {
-	uint32_t i = 0, *buf32;
+	uint32_t *buf32;
+	int i;
 
-	/* verify that the len is a multiple of 4. see comment in
-	 * read_data_from_flash_mem() */
+	/*
+	 * verify that the len is a multiple of 4.
+	 * see comment in read_data_from_flash_mem()
+	 */
 	BUG_ON((len % 4) != 0);
 
 	/* write the data to the flash memory */
 	buf32 = (uint32_t *)buf;
 	for (i = 0; i < len / 4; i++)
 		iowrite32(*buf32++, denali->flash_mem + 0x10);
-	return i*4; /* intent is to return the number of bytes read */
+	return i * 4; /* intent is to return the number of bytes read */
 }
 
 /* helper function that simply reads a buffer from the flash */
 static int read_data_from_flash_mem(struct denali_nand_info *denali,
-								uint8_t *buf,
-								int len)
+				    uint8_t *buf, int len)
 {
-	uint32_t i = 0, *buf32;
-
-	/* we assume that len will be a multiple of 4, if not
-	 * it would be nice to know about it ASAP rather than
-	 * have random failures...
-	 * This assumption is based on the fact that this
-	 * function is designed to be used to read flash pages,
-	 * which are typically multiples of 4...
-	 */
+	uint32_t *buf32;
+	int i;
 
+	/*
+	 * we assume that len will be a multiple of 4, if not it would be nice
+	 * to know about it ASAP rather than have random failures...
+	 * This assumption is based on the fact that this function is designed
+	 * to be used to read flash pages, which are typically multiples of 4.
+	 */
 	BUG_ON((len % 4) != 0);
 
 	/* transfer the data from the flash */
 	buf32 = (uint32_t *)buf;
 	for (i = 0; i < len / 4; i++)
 		*buf32++ = ioread32(denali->flash_mem + 0x10);
-	return i*4; /* intent is to return the number of bytes read */
+	return i * 4; /* intent is to return the number of bytes read */
 }
 
 /* writes OOB data to the device */
 static int write_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	uint32_t irq_status = 0;
+	uint32_t irq_status;
 	uint32_t irq_mask = INTR_STATUS__PROGRAM_COMP |
 						INTR_STATUS__PROGRAM_FAIL;
 	int status = 0;
@@ -863,8 +891,8 @@ static int write_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
 static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	uint32_t irq_mask = INTR_STATUS__LOAD_COMP,
-			 irq_status = 0, addr = 0x0, cmd = 0x0;
+	uint32_t irq_mask = INTR_STATUS__LOAD_COMP;
+	uint32_t irq_status, addr, cmd;
 
 	denali->page = page;
 
@@ -872,16 +900,19 @@ static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
 							DENALI_READ) == PASS) {
 		read_data_from_flash_mem(denali, buf, mtd->oobsize);
 
-		/* wait for command to be accepted
-		 * can always use status0 bit as the mask is identical for each
-		 * bank. */
+		/*
+		 * wait for command to be accepted
+		 * can always use status0 bit as the
+		 * mask is identical for each bank.
+		 */
 		irq_status = wait_for_irq(denali, irq_mask);
 
 		if (irq_status == 0)
 			dev_err(denali->dev, "page on OOB timeout %d\n",
 					denali->page);
 
-		/* We set the device back to MAIN_ACCESS here as I observed
+		/*
+		 * We set the device back to MAIN_ACCESS here as I observed
 		 * instability with the controller if you do a block erase
 		 * and the last transaction was a SPARE_ACCESS. Block erase
 		 * is reliable (according to the MTD test infrastructure)
@@ -889,16 +920,18 @@ static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
 		 */
 		addr = BANK(denali->flash_bank) | denali->page;
 		cmd = MODE_10 | addr;
-		index_addr(denali, (uint32_t)cmd, MAIN_ACCESS);
+		index_addr(denali, cmd, MAIN_ACCESS);
 	}
 }
 
-/* this function examines buffers to see if they contain data that
+/*
+ * this function examines buffers to see if they contain data that
  * indicate that the buffer is part of an erased region of flash.
  */
 static bool is_erased(uint8_t *buf, int len)
 {
-	int i = 0;
+	int i;
+
 	for (i = 0; i < len; i++)
 		if (buf[i] != 0xFF)
 			return false;
@@ -921,9 +954,8 @@ static bool handle_ecc(struct denali_nand_info *denali, uint8_t *buf,
 
 	if (irq_status & INTR_STATUS__ECC_ERR) {
 		/* read the ECC errors. we'll ignore them for now */
-		uint32_t err_address = 0, err_correction_info = 0;
-		uint32_t err_byte = 0, err_sector = 0, err_device = 0;
-		uint32_t err_correction_value = 0;
+		uint32_t err_address, err_correction_info, err_byte,
+			 err_sector, err_device, err_correction_value;
 		denali_set_intr_modes(denali, false);
 
 		do {
@@ -939,15 +971,17 @@ static bool handle_ecc(struct denali_nand_info *denali, uint8_t *buf,
 			err_device = ECC_ERR_DEVICE(err_correction_info);
 
 			if (ECC_ERROR_CORRECTABLE(err_correction_info)) {
-				/* If err_byte is larger than ECC_SECTOR_SIZE,
+				/*
+				 * If err_byte is larger than ECC_SECTOR_SIZE,
 				 * means error happened in OOB, so we ignore
 				 * it. It's no need for us to correct it
 				 * err_device is represented the NAND error
 				 * bits are happened in if there are more
 				 * than one NAND connected.
-				 * */
+				 */
 				if (err_byte < ECC_SECTOR_SIZE) {
 					int offset;
+
 					offset = (err_sector *
 							ECC_SECTOR_SIZE +
 							err_byte) *
@@ -959,17 +993,19 @@ static bool handle_ecc(struct denali_nand_info *denali, uint8_t *buf,
 					bitflips++;
 				}
 			} else {
-				/* if the error is not correctable, need to
+				/*
+				 * if the error is not correctable, need to
 				 * look at the page to see if it is an erased
 				 * page. if so, then it's not a real ECC error
-				 * */
+				 */
 				check_erased_page = true;
 			}
 		} while (!ECC_LAST_ERR(err_correction_info));
-		/* Once handle all ecc errors, controller will triger
+		/*
+		 * Once handle all ecc errors, controller will triger
 		 * a ECC_TRANSACTION_DONE interrupt, so here just wait
 		 * for a while for this interrupt
-		 * */
+		 */
 		while (!(read_interrupt_status(denali) &
 				INTR_STATUS__ECC_TRANSACTION_DONE))
 			cpu_relax();
@@ -983,21 +1019,16 @@ static bool handle_ecc(struct denali_nand_info *denali, uint8_t *buf,
 /* programs the controller to either enable/disable DMA transfers */
 static void denali_enable_dma(struct denali_nand_info *denali, bool en)
 {
-	uint32_t reg_val = 0x0;
-
-	if (en)
-		reg_val = DMA_ENABLE__FLAG;
-
-	iowrite32(reg_val, denali->flash_reg + DMA_ENABLE);
+	iowrite32(en ? DMA_ENABLE__FLAG : 0, denali->flash_reg + DMA_ENABLE);
 	ioread32(denali->flash_reg + DMA_ENABLE);
 }
 
 /* setups the HW to perform the data DMA */
 static void denali_setup_dma(struct denali_nand_info *denali, int op)
 {
-	uint32_t mode = 0x0;
+	uint32_t mode;
 	const int page_count = 1;
-	dma_addr_t addr = denali->buf.dma_buf;
+	uint32_t addr = denali->buf.dma_buf;
 
 	mode = MODE_10 | BANK(denali->flash_bank);
 
@@ -1007,31 +1038,31 @@ static void denali_setup_dma(struct denali_nand_info *denali, int op)
 	index_addr(denali, mode | denali->page, 0x2000 | op | page_count);
 
 	/* 2. set memory high address bits 23:8 */
-	index_addr(denali, mode | ((uint16_t)(addr >> 16) << 8), 0x2200);
+	index_addr(denali, mode | ((addr >> 16) << 8), 0x2200);
 
 	/* 3. set memory low address bits 23:8 */
-	index_addr(denali, mode | ((uint16_t)addr << 8), 0x2300);
+	index_addr(denali, mode | ((addr & 0xff) << 8), 0x2300);
 
-	/* 4.  interrupt when complete, burst len = 64 bytes*/
+	/* 4. interrupt when complete, burst len = 64 bytes */
 	index_addr(denali, mode | 0x14000, 0x2400);
 }
 
-/* writes a page. user specifies type, and this function handles the
- * configuration details. */
+/*
+ * writes a page. user specifies type, and this function handles the
+ * configuration details.
+ */
 static int write_page(struct mtd_info *mtd, struct nand_chip *chip,
 			const uint8_t *buf, bool raw_xfer)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-
 	dma_addr_t addr = denali->buf.dma_buf;
 	size_t size = denali->mtd.writesize + denali->mtd.oobsize;
-
-	uint32_t irq_status = 0;
+	uint32_t irq_status;
 	uint32_t irq_mask = INTR_STATUS__DMA_CMD_COMP |
 						INTR_STATUS__PROGRAM_FAIL;
 
-	/* if it is a raw xfer, we want to disable ecc, and send
-	 * the spare area.
+	/*
+	 * if it is a raw xfer, we want to disable ecc and send the spare area.
 	 * !raw_xfer - enable ecc
 	 * raw_xfer - transfer spare
 	 */
@@ -1058,12 +1089,9 @@ static int write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	irq_status = wait_for_irq(denali, irq_mask);
 
 	if (irq_status == 0) {
-		dev_err(denali->dev,
-				"timeout on write_page (type = %d)\n",
-				raw_xfer);
-		denali->status =
-			(irq_status & INTR_STATUS__PROGRAM_FAIL) ?
-			NAND_STATUS_FAIL : PASS;
+		dev_err(denali->dev, "timeout on write_page (type = %d)\n",
+			raw_xfer);
+		denali->status = NAND_STATUS_FAIL;
 	}
 
 	denali_enable_dma(denali, false);
@@ -1074,27 +1102,33 @@ static int write_page(struct mtd_info *mtd, struct nand_chip *chip,
 
 /* NAND core entry points */
 
-/* this is the callback that the NAND core calls to write a page. Since
+/*
+ * this is the callback that the NAND core calls to write a page. Since
  * writing a page with ECC or without is similar, all the work is done
  * by write_page above.
- * */
+ */
 static int denali_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 				const uint8_t *buf, int oob_required)
 {
-	/* for regular page writes, we let HW handle all the ECC
-	 * data written to the device. */
+	/*
+	 * for regular page writes, we let HW handle all the ECC
+	 * data written to the device.
+	 */
 	return write_page(mtd, chip, buf, false);
 }
 
-/* This is the callback that the NAND core calls to write a page without ECC.
+/*
+ * This is the callback that the NAND core calls to write a page without ECC.
  * raw access is similar to ECC page writes, so all the work is done in the
  * write_page() function above.
  */
 static int denali_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 					const uint8_t *buf, int oob_required)
 {
-	/* for raw page writes, we want to disable ECC and simply write
-	   whatever data is in the buffer. */
+	/*
+	 * for raw page writes, we want to disable ECC and simply write
+	 * whatever data is in the buffer.
+	 */
 	return write_page(mtd, chip, buf, true);
 }
 
@@ -1121,15 +1155,15 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 	dma_addr_t addr = denali->buf.dma_buf;
 	size_t size = denali->mtd.writesize + denali->mtd.oobsize;
 
-	uint32_t irq_status = 0;
+	uint32_t irq_status;
 	uint32_t irq_mask = INTR_STATUS__ECC_TRANSACTION_DONE |
 			    INTR_STATUS__ECC_ERR;
 	bool check_erased_page = false;
 
 	if (page != denali->page) {
-		dev_err(denali->dev, "IN %s: page %d is not"
-				" equal to denali->page %d, investigate!!",
-				__func__, page, denali->page);
+		dev_err(denali->dev,
+			"IN %s: page %d is not equal to denali->page %d",
+			__func__, page, denali->page);
 		BUG();
 	}
 
@@ -1169,17 +1203,14 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 				uint8_t *buf, int oob_required, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-
 	dma_addr_t addr = denali->buf.dma_buf;
 	size_t size = denali->mtd.writesize + denali->mtd.oobsize;
-
-	uint32_t irq_status = 0;
 	uint32_t irq_mask = INTR_STATUS__DMA_CMD_COMP;
 
 	if (page != denali->page) {
-		dev_err(denali->dev, "IN %s: page %d is not"
-				" equal to denali->page %d, investigate!!",
-				__func__, page, denali->page);
+		dev_err(denali->dev,
+			"IN %s: page %d is not equal to denali->page %d",
+			__func__, page, denali->page);
 		BUG();
 	}
 
@@ -1192,7 +1223,7 @@ static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 	denali_setup_dma(denali, DENALI_READ);
 
 	/* wait for operation to complete */
-	irq_status = wait_for_irq(denali, irq_mask);
+	wait_for_irq(denali, irq_mask);
 
 	dma_sync_single_for_cpu(denali->dev, addr, size, DMA_FROM_DEVICE);
 
@@ -1228,6 +1259,7 @@ static int denali_waitfunc(struct mtd_info *mtd, struct nand_chip *chip)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
 	int status = denali->status;
+
 	denali->status = 0;
 
 	return status;
@@ -1237,20 +1269,19 @@ static int denali_erase(struct mtd_info *mtd, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
 
-	uint32_t cmd = 0x0, irq_status = 0;
+	uint32_t cmd, irq_status;
 
-	/* clear interrupts */
 	clear_interrupts(denali);
 
 	/* setup page read request for access type */
 	cmd = MODE_10 | BANK(denali->flash_bank) | page;
-	index_addr(denali, (uint32_t)cmd, 0x1);
+	index_addr(denali, cmd, 0x1);
 
 	/* wait for erase to complete or failure to occur */
 	irq_status = wait_for_irq(denali, INTR_STATUS__ERASE_COMP |
 					INTR_STATUS__ERASE_FAIL);
 
-	return (irq_status & INTR_STATUS__ERASE_FAIL) ? NAND_STATUS_FAIL : PASS;
+	return irq_status & INTR_STATUS__ERASE_FAIL ? NAND_STATUS_FAIL : PASS;
 }
 
 static void denali_cmdfunc(struct mtd_info *mtd, unsigned int cmd, int col,
@@ -1269,17 +1300,16 @@ static void denali_cmdfunc(struct mtd_info *mtd, unsigned int cmd, int col,
 	case NAND_CMD_READID:
 	case NAND_CMD_PARAM:
 		reset_buf(denali);
-		/*sometimes ManufactureId read from register is not right
+		/*
+		 * sometimes ManufactureId read from register is not right
 		 * e.g. some of Micron MT29F32G08QAA MLC NAND chips
 		 * So here we send READID cmd to NAND insteand
-		 * */
-		addr = (uint32_t)MODE_11 | BANK(denali->flash_bank);
-		index_addr(denali, (uint32_t)addr | 0, 0x90);
-		index_addr(denali, (uint32_t)addr | 1, 0);
+		 */
+		addr = MODE_11 | BANK(denali->flash_bank);
+		index_addr(denali, addr | 0, 0x90);
+		index_addr(denali, addr | 1, 0);
 		for (i = 0; i < 8; i++) {
-			index_addr_read_data(denali,
-						(uint32_t)addr | 2,
-						&id);
+			index_addr_read_data(denali, addr | 2, &id);
 			write_byte_to_buf(denali, id);
 		}
 		break;
@@ -1304,8 +1334,8 @@ static int denali_ecc_calculate(struct mtd_info *mtd, const uint8_t *data,
 				uint8_t *ecc_code)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	dev_err(denali->dev,
-			"denali_ecc_calculate called unexpectedly\n");
+
+	dev_err(denali->dev, "denali_ecc_calculate called unexpectedly\n");
 	BUG();
 	return -EIO;
 }
@@ -1314,8 +1344,8 @@ static int denali_ecc_correct(struct mtd_info *mtd, uint8_t *data,
 				uint8_t *read_ecc, uint8_t *calc_ecc)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	dev_err(denali->dev,
-			"denali_ecc_correct called unexpectedly\n");
+
+	dev_err(denali->dev, "denali_ecc_correct called unexpectedly\n");
 	BUG();
 	return -EIO;
 }
@@ -1323,8 +1353,8 @@ static int denali_ecc_correct(struct mtd_info *mtd, uint8_t *data,
 static void denali_ecc_hwctl(struct mtd_info *mtd, int mode)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	dev_err(denali->dev,
-			"denali_ecc_hwctl called unexpectedly\n");
+
+	dev_err(denali->dev, "denali_ecc_hwctl called unexpectedly\n");
 	BUG();
 }
 /* end NAND core entry points */
@@ -1332,11 +1362,12 @@ static void denali_ecc_hwctl(struct mtd_info *mtd, int mode)
 /* Initialization code to bring the device up to a known good state */
 static void denali_hw_init(struct denali_nand_info *denali)
 {
-	/* tell driver how many bit controller will skip before
+	/*
+	 * tell driver how many bit controller will skip before
 	 * writing ECC code in OOB, this register may be already
 	 * set by firmware. So we read this value out.
 	 * if this value is 0, just let it be.
-	 * */
+	 */
 	denali->bbtskipbytes = ioread32(denali->flash_reg +
 						SPARE_AREA_SKIP_BYTES);
 	detect_max_banks(denali);
@@ -1354,10 +1385,11 @@ static void denali_hw_init(struct denali_nand_info *denali)
 	denali_irq_init(denali);
 }
 
-/* Althogh controller spec said SLC ECC is forceb to be 4bit,
+/*
+ * Althogh controller spec said SLC ECC is forceb to be 4bit,
  * but denali controller in MRST only support 15bit and 8bit ECC
  * correction
- * */
+ */
 #define ECC_8BITS	14
 static struct nand_ecclayout nand_8bit_oob = {
 	.eccbytes = 14,
@@ -1397,13 +1429,16 @@ static void denali_drv_init(struct denali_nand_info *denali)
 	denali->idx = 0;
 
 	/* setup interrupt handler */
-	/* the completion object will be used to notify
-	 * the callee that the interrupt is done */
+	/*
+	 * the completion object will be used to notify
+	 * the callee that the interrupt is done
+	 */
 	init_completion(&denali->complete);
 
-	/* the spinlock will be used to synchronize the ISR
-	 * with any element that might be access shared
-	 * data (interrupt status) */
+	/*
+	 * the spinlock will be used to synchronize the ISR with any
+	 * element that might be access shared data (interrupt status)
+	 */
 	spin_lock_init(&denali->irq_lock);
 
 	/* indicate that MTD has not selected a valid bank yet */
@@ -1418,7 +1453,8 @@ int denali_init(struct denali_nand_info *denali)
 	int ret;
 
 	if (denali->platform == INTEL_CE4100) {
-		/* Due to a silicon limitation, we can only support
+		/*
+		 * Due to a silicon limitation, we can only support
 		 * ONFI timing mode 1 and below.
 		 */
 		if (onfi_timing_mode < -1 || onfi_timing_mode > 1) {
@@ -1437,8 +1473,10 @@ int denali_init(struct denali_nand_info *denali)
 	denali_hw_init(denali);
 	denali_drv_init(denali);
 
-	/* denali_isr register is done after all the hardware
-	 * initilization is finished*/
+	/*
+	 * denali_isr register is done after all the hardware
+	 * initilization is finished
+	 */
 	if (request_irq(denali->irq, denali_isr, IRQF_SHARED,
 			DENALI_NAND_NAME, denali)) {
 		pr_err("Spectra: Unable to allocate IRQ\n");
@@ -1457,9 +1495,11 @@ int denali_init(struct denali_nand_info *denali)
 	denali->nand.read_byte = denali_read_byte;
 	denali->nand.waitfunc = denali_waitfunc;
 
-	/* scan for NAND devices attached to the controller
+	/*
+	 * scan for NAND devices attached to the controller
 	 * this is the first stage in a two step process to register
-	 * with the nand subsystem */
+	 * with the nand subsystem
+	 */
 	if (nand_scan_ident(&denali->mtd, denali->max_banks, NULL)) {
 		ret = -ENXIO;
 		goto failed_req_irq;
@@ -1491,10 +1531,10 @@ int denali_init(struct denali_nand_info *denali)
 		goto failed_req_irq;
 	}
 
-	/* support for multi nand
-	 * MTD known nothing about multi nand,
-	 * so we should tell it the real pagesize
-	 * and anything necessery
+	/*
+	 * support for multi nand
+	 * MTD known nothing about multi nand, so we should tell it
+	 * the real pagesize and anything necessery
 	 */
 	denali->devnum = ioread32(denali->flash_reg + DEVICES_CONNECTED);
 	denali->nand.chipsize <<= (denali->devnum - 1);
@@ -1510,9 +1550,11 @@ int denali_init(struct denali_nand_info *denali)
 	denali->mtd.size = denali->nand.numchips * denali->nand.chipsize;
 	denali->bbtskipbytes *= denali->devnum;
 
-	/* second stage of the NAND scan
+	/*
+	 * second stage of the NAND scan
 	 * this stage requires information regarding ECC and
-	 * bad block management. */
+	 * bad block management.
+	 */
 
 	/* Bad block management */
 	denali->nand.bbt_td = &bbt_main_descr;
@@ -1523,7 +1565,8 @@ int denali_init(struct denali_nand_info *denali)
 	denali->nand.options |= NAND_SKIP_BBTSCAN;
 	denali->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
 
-	/* Denali Controller only support 15bit and 8bit ECC in MRST,
+	/*
+	 * Denali Controller only support 15bit and 8bit ECC in MRST,
 	 * so just let controller do 15bit ECC for MLC and 8bit ECC for
 	 * SLC if possible.
 	 * */
@@ -1539,8 +1582,7 @@ int denali_init(struct denali_nand_info *denali)
 	} else if (denali->mtd.oobsize < (denali->bbtskipbytes +
 			ECC_8BITS * (denali->mtd.writesize /
 			ECC_SECTOR_SIZE))) {
-		pr_err("Your NAND chip OOB is not large enough to \
-				contain 8bit ECC correction codes");
+		pr_err("Your NAND chip OOB is not large enough to contain 8bit ECC correction codes");
 		goto failed_req_irq;
 	} else {
 		denali->nand.ecc.strength = 8;
@@ -1559,18 +1601,19 @@ int denali_init(struct denali_nand_info *denali)
 		denali->mtd.oobsize - denali->nand.ecc.layout->eccbytes -
 		denali->bbtskipbytes;
 
-	/* Let driver know the total blocks number and
-	 * how many blocks contained by each nand chip.
-	 * blksperchip will help driver to know how many
-	 * blocks is taken by FW.
-	 * */
-	denali->totalblks = denali->mtd.size >>
-				denali->nand.phys_erase_shift;
+	/*
+	 * Let driver know the total blocks number and how many blocks
+	 * contained by each nand chip. blksperchip will help driver to
+	 * know how many blocks is taken by FW.
+	 */
+	denali->totalblks = denali->mtd.size >> denali->nand.phys_erase_shift;
 	denali->blksperchip = denali->totalblks / denali->nand.numchips;
 
-	/* These functions are required by the NAND core framework, otherwise,
+	/*
+	 * These functions are required by the NAND core framework, otherwise,
 	 * the NAND core will assert. However, we don't need them, so we'll stub
-	 * them out. */
+	 * them out.
+	 */
 	denali->nand.ecc.calculate = denali_ecc_calculate;
 	denali->nand.ecc.correct = denali_ecc_correct;
 	denali->nand.ecc.hwctl = denali_ecc_hwctl;
@@ -1610,7 +1653,7 @@ void denali_remove(struct denali_nand_info *denali)
 {
 	denali_irq_cleanup(denali->irq, denali);
 	dma_unmap_single(denali->dev, denali->buf.dma_buf,
-			denali->mtd.writesize + denali->mtd.oobsize,
-			DMA_BIDIRECTIONAL);
+			 denali->mtd.writesize + denali->mtd.oobsize,
+			 DMA_BIDIRECTIONAL);
 }
 EXPORT_SYMBOL(denali_remove);
diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h
index 966817462421..145bf88930e8 100644
--- a/drivers/mtd/nand/denali.h
+++ b/drivers/mtd/nand/denali.h
@@ -17,6 +17,9 @@
  *
  */
 
+#ifndef __DENALI_H__
+#define __DENALI_H__
+
 #include <linux/mtd/nand.h>
 
 #define DEVICE_RESET				0x0
@@ -400,28 +403,6 @@
 #define ONFI_BLOOM_TIME         1
 #define MODE5_WORKAROUND        0
 
-/* lld_nand.h */
-/*
- * NAND Flash Controller Device Driver
- * Copyright (c) 2009, Intel Corporation and its suppliers.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
- *
- */
-
-#ifndef _LLD_NAND_
-#define _LLD_NAND_
 
 #define MODE_00    0x00000000
 #define MODE_01    0x04000000
@@ -499,4 +480,4 @@ struct denali_nand_info {
 extern int denali_init(struct denali_nand_info *denali);
 extern void denali_remove(struct denali_nand_info *denali);
 
-#endif /*_LLD_NAND_*/
+#endif /* __DENALI_H__ */
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index 1550692973dc..7a915870d9d6 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -605,7 +605,7 @@ static int dma_xfer(struct fsmc_nand_data *host, void *buffer, int len,
 	wait_for_completion_timeout(&host->dma_access_complete,
 				msecs_to_jiffies(3000));
 	if (ret <= 0) {
-		chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
+		dmaengine_terminate_all(chan);
 		dev_err(host->dev, "wait_for_completion_timeout\n");
 		if (!ret)
 			ret = -ETIMEDOUT;
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index d8cdf06343fb..5b5c62712814 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -982,6 +982,15 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 
 	chip->select_chip(mtd, chipnr);
 
+	/*
+	 * Reset the chip.
+	 * If we want to check the WP through READ STATUS and check the bit 7
+	 * we must reset the chip
+	 * some operation can also clear the bit 7 of status register
+	 * eg. erase/program a locked block
+	 */
+	chip->cmdfunc(mtd, NAND_CMD_RESET, -1, -1);
+
 	/* Check, if it is write protected */
 	if (nand_check_wp(mtd)) {
 		pr_debug("%s: device is write protected!\n",
@@ -1032,6 +1041,15 @@ int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 
 	chip->select_chip(mtd, chipnr);
 
+	/*
+	 * Reset the chip.
+	 * If we want to check the WP through READ STATUS and check the bit 7
+	 * we must reset the chip
+	 * some operation can also clear the bit 7 of status register
+	 * eg. erase/program a locked block
+	 */
+	chip->cmdfunc(mtd, NAND_CMD_RESET, -1, -1);
+
 	/* Check, if it is write protected */
 	if (nand_check_wp(mtd)) {
 		pr_debug("%s: device is write protected!\n",
@@ -2391,8 +2409,8 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
 	blockmask = (1 << (chip->phys_erase_shift - chip->page_shift)) - 1;
 
 	/* Invalidate the page cache, when we write to the cached page */
-	if (to <= (chip->pagebuf << chip->page_shift) &&
-	    (chip->pagebuf << chip->page_shift) < (to + ops->len))
+	if (to <= ((loff_t)chip->pagebuf << chip->page_shift) &&
+	    ((loff_t)chip->pagebuf << chip->page_shift) < (to + ops->len))
 		chip->pagebuf = -1;
 
 	/* Don't allow multipage oob writes with offset */
@@ -3576,6 +3594,8 @@ static bool find_full_id_nand(struct mtd_info *mtd, struct nand_chip *chip,
 		chip->options |= type->options;
 		chip->ecc_strength_ds = NAND_ECC_STRENGTH(type);
 		chip->ecc_step_ds = NAND_ECC_STEP(type);
+		chip->onfi_timing_mode_default =
+					type->onfi_timing_mode_default;
 
 		*busw = type->options & NAND_BUSWIDTH_16;
 
@@ -3918,8 +3938,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 	case NAND_ECC_HW_OOB_FIRST:
 		/* Similar to NAND_ECC_HW, but a separate read_page handle */
 		if (!ecc->calculate || !ecc->correct || !ecc->hwctl) {
-			pr_warn("No ECC functions supplied; "
-				   "hardware ECC not possible\n");
+			pr_warn("No ECC functions supplied; hardware ECC not possible\n");
 			BUG();
 		}
 		if (!ecc->read_page)
@@ -3950,8 +3969,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 		     ecc->read_page == nand_read_page_hwecc ||
 		     !ecc->write_page ||
 		     ecc->write_page == nand_write_page_hwecc)) {
-			pr_warn("No ECC functions supplied; "
-				   "hardware ECC not possible\n");
+			pr_warn("No ECC functions supplied; hardware ECC not possible\n");
 			BUG();
 		}
 		/* Use standard syndrome read/write page function? */
@@ -3975,9 +3993,8 @@ int nand_scan_tail(struct mtd_info *mtd)
 			}
 			break;
 		}
-		pr_warn("%d byte HW ECC not possible on "
-			   "%d byte page size, fallback to SW ECC\n",
-			   ecc->size, mtd->writesize);
+		pr_warn("%d byte HW ECC not possible on %d byte page size, fallback to SW ECC\n",
+			ecc->size, mtd->writesize);
 		ecc->mode = NAND_ECC_SOFT;
 
 	case NAND_ECC_SOFT:
@@ -4030,8 +4047,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 		break;
 
 	case NAND_ECC_NONE:
-		pr_warn("NAND_ECC_NONE selected by board driver. "
-			   "This is not recommended!\n");
+		pr_warn("NAND_ECC_NONE selected by board driver. This is not recommended!\n");
 		ecc->read_page = nand_read_page_raw;
 		ecc->write_page = nand_write_page_raw;
 		ecc->read_oob = nand_read_oob_std;
diff --git a/drivers/mtd/nand/nand_bbt.c b/drivers/mtd/nand/nand_bbt.c
index 443fa82cde6a..9bb8453d224e 100644
--- a/drivers/mtd/nand/nand_bbt.c
+++ b/drivers/mtd/nand/nand_bbt.c
@@ -201,12 +201,12 @@ static int read_bbt(struct mtd_info *mtd, uint8_t *buf, int page, int num,
 		res = mtd_read(mtd, from, len, &retlen, buf);
 		if (res < 0) {
 			if (mtd_is_eccerr(res)) {
-				pr_info("nand_bbt: ECC error in BBT at "
-					"0x%012llx\n", from & ~mtd->writesize);
+				pr_info("nand_bbt: ECC error in BBT at 0x%012llx\n",
+					from & ~mtd->writesize);
 				return res;
 			} else if (mtd_is_bitflip(res)) {
-				pr_info("nand_bbt: corrected error in BBT at "
-					"0x%012llx\n", from & ~mtd->writesize);
+				pr_info("nand_bbt: corrected error in BBT at 0x%012llx\n",
+					from & ~mtd->writesize);
 				ret = res;
 			} else {
 				pr_info("nand_bbt: error reading BBT\n");
@@ -580,8 +580,8 @@ static int search_bbt(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_descr
 		if (td->pages[i] == -1)
 			pr_warn("Bad block table not found for chip %d\n", i);
 		else
-			pr_info("Bad block table found at page %d, version "
-				 "0x%02X\n", td->pages[i], td->version[i]);
+			pr_info("Bad block table found at page %d, version 0x%02X\n",
+				td->pages[i], td->version[i]);
 	}
 	return 0;
 }
@@ -725,12 +725,10 @@ static int write_bbt(struct mtd_info *mtd, uint8_t *buf,
 			res = mtd_read(mtd, to, len, &retlen, buf);
 			if (res < 0) {
 				if (retlen != len) {
-					pr_info("nand_bbt: error reading block "
-						"for writing the bad block table\n");
+					pr_info("nand_bbt: error reading block for writing the bad block table\n");
 					return res;
 				}
-				pr_warn("nand_bbt: ECC error while reading "
-					"block for writing bad block table\n");
+				pr_warn("nand_bbt: ECC error while reading block for writing bad block table\n");
 			}
 			/* Read oob data */
 			ops.ooblen = (len >> this->page_shift) * mtd->oobsize;
@@ -1338,9 +1336,8 @@ int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt)
 	block = (int)(offs >> this->bbt_erase_shift);
 	res = bbt_get_entry(this, block);
 
-	pr_debug("nand_isbad_bbt(): bbt info for offs 0x%08x: "
-			"(block %d) 0x%02x\n",
-			(unsigned int)offs, block, res);
+	pr_debug("nand_isbad_bbt(): bbt info for offs 0x%08x: (block %d) 0x%02x\n",
+		 (unsigned int)offs, block, res);
 
 	switch (res) {
 	case BBT_BLOCK_GOOD:
diff --git a/drivers/mtd/nand/nand_ids.c b/drivers/mtd/nand/nand_ids.c
index 3d7c89fc1031..fbde89105245 100644
--- a/drivers/mtd/nand/nand_ids.c
+++ b/drivers/mtd/nand/nand_ids.c
@@ -46,6 +46,10 @@ struct nand_flash_dev nand_flash_ids[] = {
 	{"SDTNRGAMA 64G 3.3V 8-bit",
 		{ .id = {0x45, 0xde, 0x94, 0x93, 0x76, 0x50} },
 		  SZ_16K, SZ_8K, SZ_4M, 0, 6, 1280, NAND_ECC_INFO(40, SZ_1K) },
+	{"H27UCG8T2ATR-BC 64G 3.3V 8-bit",
+		{ .id = {0xad, 0xde, 0x94, 0xda, 0x74, 0xc4} },
+		  SZ_8K, SZ_8K, SZ_2M, 0, 6, 640, NAND_ECC_INFO(40, SZ_1K),
+		  4 },
 
 	LEGACY_ID_NAND("NAND 4MiB 5V 8-bit",   0x6B, 4, SZ_8K, SP_OPTIONS),
 	LEGACY_ID_NAND("NAND 4MiB 3,3V 8-bit", 0xE3, 4, SZ_8K, SP_OPTIONS),
diff --git a/drivers/mtd/nand/nand_timings.c b/drivers/mtd/nand/nand_timings.c
index 8b36253420fa..e81470a8ac67 100644
--- a/drivers/mtd/nand/nand_timings.c
+++ b/drivers/mtd/nand/nand_timings.c
@@ -42,7 +42,7 @@ static const struct nand_sdr_timings onfi_sdr_timings[] = {
 		.tRHZ_max = 200000,
 		.tRLOH_min = 0,
 		.tRP_min = 50000,
-		.tRST_max = 250000000000,
+		.tRST_max = 250000000000ULL,
 		.tWB_max = 200000,
 		.tRR_min = 40000,
 		.tWC_min = 100000,
diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c
index 4f0d83648e5a..7dc1dd28d896 100644
--- a/drivers/mtd/nand/nandsim.c
+++ b/drivers/mtd/nand/nandsim.c
@@ -827,7 +827,7 @@ static int parse_badblocks(struct nandsim *ns, struct mtd_info *mtd)
 			NS_ERR("invalid badblocks.\n");
 			return -EINVAL;
 		}
-		offset = erase_block_no * ns->geom.secsz;
+		offset = (loff_t)erase_block_no * ns->geom.secsz;
 		if (mtd_block_markbad(mtd, offset)) {
 			NS_ERR("invalid badblocks.\n");
 			return -EINVAL;
diff --git a/drivers/mtd/nand/ndfc.c b/drivers/mtd/nand/ndfc.c
index 69eaba690a99..253a644da76a 100644
--- a/drivers/mtd/nand/ndfc.c
+++ b/drivers/mtd/nand/ndfc.c
@@ -203,7 +203,8 @@ static int ndfc_probe(struct platform_device *ofdev)
 	struct ndfc_controller *ndfc;
 	const __be32 *reg;
 	u32 ccr;
-	int err, len, cs;
+	u32 cs;
+	int err, len;
 
 	/* Read the reg property to get the chip select */
 	reg = of_get_property(ofdev->dev.of_node, "reg", &len);
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 5967b385141b..3b357e920a0c 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -136,7 +136,6 @@
 
 #define BADBLOCK_MARKER_LENGTH		2
 
-#ifdef CONFIG_MTD_NAND_OMAP_BCH
 static u_char bch16_vector[] = {0xf5, 0x24, 0x1c, 0xd0, 0x61, 0xb3, 0xf1, 0x55,
 				0x2e, 0x2c, 0x86, 0xa3, 0xed, 0x36, 0x1b, 0x78,
 				0x48, 0x76, 0xa9, 0x3b, 0x97, 0xd1, 0x7a, 0x93,
@@ -144,7 +143,6 @@ static u_char bch16_vector[] = {0xf5, 0x24, 0x1c, 0xd0, 0x61, 0xb3, 0xf1, 0x55,
 static u_char bch8_vector[] = {0xf3, 0xdb, 0x14, 0x16, 0x8b, 0xd2, 0xbe, 0xcc,
 	0xac, 0x6b, 0xff, 0x99, 0x7b};
 static u_char bch4_vector[] = {0x00, 0x6b, 0x31, 0xdd, 0x41, 0xbc, 0x10};
-#endif
 
 /* oob info generated runtime depending on ecc algorithm and layout selected */
 static struct nand_ecclayout omap_oobinfo;
@@ -1292,7 +1290,6 @@ static int __maybe_unused omap_calculate_ecc_bch(struct mtd_info *mtd,
 	return 0;
 }
 
-#ifdef CONFIG_MTD_NAND_OMAP_BCH
 /**
  * erased_sector_bitflips - count bit flips
  * @data:	data sector buffer
@@ -1378,7 +1375,7 @@ static int omap_elm_correct_data(struct mtd_info *mtd, u_char *data,
 		erased_ecc_vec = bch16_vector;
 		break;
 	default:
-		pr_err("invalid driver configuration\n");
+		dev_err(&info->pdev->dev, "invalid driver configuration\n");
 		return -EINVAL;
 	}
 
@@ -1449,7 +1446,8 @@ static int omap_elm_correct_data(struct mtd_info *mtd, u_char *data,
 	err = 0;
 	for (i = 0; i < eccsteps; i++) {
 		if (err_vec[i].error_uncorrectable) {
-			pr_err("nand: uncorrectable bit-flips found\n");
+			dev_err(&info->pdev->dev,
+				"uncorrectable bit-flips found\n");
 			err = -EBADMSG;
 		} else if (err_vec[i].error_reported) {
 			for (j = 0; j < err_vec[i].error_count; j++) {
@@ -1486,8 +1484,9 @@ static int omap_elm_correct_data(struct mtd_info *mtd, u_char *data,
 							1 << bit_pos;
 					}
 				} else {
-					pr_err("invalid bit-flip @ %d:%d\n",
-							 byte_pos, bit_pos);
+					dev_err(&info->pdev->dev,
+						"invalid bit-flip @ %d:%d\n",
+						byte_pos, bit_pos);
 					err = -EBADMSG;
 				}
 			}
@@ -1593,33 +1592,71 @@ static int omap_read_page_bch(struct mtd_info *mtd, struct nand_chip *chip,
 /**
  * is_elm_present - checks for presence of ELM module by scanning DT nodes
  * @omap_nand_info: NAND device structure containing platform data
- * @bch_type: 0x0=BCH4, 0x1=BCH8, 0x2=BCH16
  */
-static int is_elm_present(struct omap_nand_info *info,
-			struct device_node *elm_node, enum bch_ecc bch_type)
+static bool is_elm_present(struct omap_nand_info *info,
+			   struct device_node *elm_node)
 {
 	struct platform_device *pdev;
-	struct nand_ecc_ctrl *ecc = &info->nand.ecc;
-	int err;
+
 	/* check whether elm-id is passed via DT */
 	if (!elm_node) {
-		pr_err("nand: error: ELM DT node not found\n");
-		return -ENODEV;
+		dev_err(&info->pdev->dev, "ELM devicetree node not found\n");
+		return false;
 	}
 	pdev = of_find_device_by_node(elm_node);
 	/* check whether ELM device is registered */
 	if (!pdev) {
-		pr_err("nand: error: ELM device not found\n");
-		return -ENODEV;
+		dev_err(&info->pdev->dev, "ELM device not found\n");
+		return false;
 	}
 	/* ELM module available, now configure it */
 	info->elm_dev = &pdev->dev;
-	err = elm_config(info->elm_dev, bch_type,
-		(info->mtd.writesize / ecc->size), ecc->size, ecc->bytes);
+	return true;
+}
 
-	return err;
+static bool omap2_nand_ecc_check(struct omap_nand_info *info,
+				 struct omap_nand_platform_data	*pdata)
+{
+	bool ecc_needs_bch, ecc_needs_omap_bch, ecc_needs_elm;
+
+	switch (info->ecc_opt) {
+	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
+	case OMAP_ECC_BCH8_CODE_HW_DETECTION_SW:
+		ecc_needs_omap_bch = false;
+		ecc_needs_bch = true;
+		ecc_needs_elm = false;
+		break;
+	case OMAP_ECC_BCH4_CODE_HW:
+	case OMAP_ECC_BCH8_CODE_HW:
+	case OMAP_ECC_BCH16_CODE_HW:
+		ecc_needs_omap_bch = true;
+		ecc_needs_bch = false;
+		ecc_needs_elm = true;
+		break;
+	default:
+		ecc_needs_omap_bch = false;
+		ecc_needs_bch = false;
+		ecc_needs_elm = false;
+		break;
+	}
+
+	if (ecc_needs_bch && !IS_ENABLED(CONFIG_MTD_NAND_ECC_BCH)) {
+		dev_err(&info->pdev->dev,
+			"CONFIG_MTD_NAND_ECC_BCH not enabled\n");
+		return false;
+	}
+	if (ecc_needs_omap_bch && !IS_ENABLED(CONFIG_MTD_NAND_OMAP_BCH)) {
+		dev_err(&info->pdev->dev,
+			"CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
+		return false;
+	}
+	if (ecc_needs_elm && !is_elm_present(info, pdata->elm_of_node)) {
+		dev_err(&info->pdev->dev, "ELM not available\n");
+		return false;
+	}
+
+	return true;
 }
-#endif /* CONFIG_MTD_NAND_ECC_BCH */
 
 static int omap_nand_probe(struct platform_device *pdev)
 {
@@ -1663,7 +1700,6 @@ static int omap_nand_probe(struct platform_device *pdev)
 	mtd->owner		= THIS_MODULE;
 	nand_chip		= &info->nand;
 	nand_chip->ecc.priv	= NULL;
-	nand_chip->options	|= NAND_SKIP_BBTSCAN;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
@@ -1692,17 +1728,22 @@ static int omap_nand_probe(struct platform_device *pdev)
 		nand_chip->chip_delay = 50;
 	}
 
+	if (pdata->flash_bbt)
+		nand_chip->bbt_options |= NAND_BBT_USE_FLASH | NAND_BBT_NO_OOB;
+	else
+		nand_chip->options |= NAND_SKIP_BBTSCAN;
+
 	/* scan NAND device connected to chip controller */
 	nand_chip->options |= pdata->devsize & NAND_BUSWIDTH_16;
 	if (nand_scan_ident(mtd, 1, NULL)) {
-		pr_err("nand device scan failed, may be bus-width mismatch\n");
+		dev_err(&info->pdev->dev, "scan failed, may be bus-width mismatch\n");
 		err = -ENXIO;
 		goto return_error;
 	}
 
 	/* check for small page devices */
 	if ((mtd->oobsize < 64) && (pdata->ecc_opt != OMAP_ECC_HAM1_CODE_HW)) {
-		pr_err("small page devices are not supported\n");
+		dev_err(&info->pdev->dev, "small page devices are not supported\n");
 		err = -EINVAL;
 		goto return_error;
 	}
@@ -1793,6 +1834,11 @@ static int omap_nand_probe(struct platform_device *pdev)
 		goto return_error;
 	}
 
+	if (!omap2_nand_ecc_check(info, pdata)) {
+		err = -EINVAL;
+		goto return_error;
+	}
+
 	/* populate MTD interface based on ECC scheme */
 	ecclayout		= &omap_oobinfo;
 	switch (info->ecc_opt) {
@@ -1825,7 +1871,6 @@ static int omap_nand_probe(struct platform_device *pdev)
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
-#ifdef CONFIG_MTD_NAND_ECC_BCH
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW_DETECTION_SW\n");
 		nand_chip->ecc.mode		= NAND_ECC_HW;
 		nand_chip->ecc.size		= 512;
@@ -1853,18 +1898,13 @@ static int omap_nand_probe(struct platform_device *pdev)
 							nand_chip->ecc.bytes,
 							&ecclayout);
 		if (!nand_chip->ecc.priv) {
-			pr_err("nand: error: unable to use s/w BCH library\n");
+			dev_err(&info->pdev->dev, "unable to use BCH library\n");
 			err = -EINVAL;
+			goto return_error;
 		}
 		break;
-#else
-		pr_err("nand: error: CONFIG_MTD_NAND_ECC_BCH not enabled\n");
-		err = -EINVAL;
-		goto return_error;
-#endif
 
 	case OMAP_ECC_BCH4_CODE_HW:
-#ifdef CONFIG_MTD_NAND_OMAP_BCH
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW ECC scheme\n");
 		nand_chip->ecc.mode		= NAND_ECC_HW;
 		nand_chip->ecc.size		= 512;
@@ -1886,21 +1926,15 @@ static int omap_nand_probe(struct platform_device *pdev)
 		/* reserved marker already included in ecclayout->eccbytes */
 		ecclayout->oobfree->offset	=
 				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
-		/* This ECC scheme requires ELM H/W block */
-		if (is_elm_present(info, pdata->elm_of_node, BCH4_ECC) < 0) {
-			pr_err("nand: error: could not initialize ELM\n");
-			err = -ENODEV;
+
+		err = elm_config(info->elm_dev, BCH4_ECC,
+				 info->mtd.writesize / nand_chip->ecc.size,
+				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+		if (err < 0)
 			goto return_error;
-		}
 		break;
-#else
-		pr_err("nand: error: CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
-		err = -EINVAL;
-		goto return_error;
-#endif
 
 	case OMAP_ECC_BCH8_CODE_HW_DETECTION_SW:
-#ifdef CONFIG_MTD_NAND_ECC_BCH
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW_DETECTION_SW\n");
 		nand_chip->ecc.mode		= NAND_ECC_HW;
 		nand_chip->ecc.size		= 512;
@@ -1928,19 +1962,13 @@ static int omap_nand_probe(struct platform_device *pdev)
 							nand_chip->ecc.bytes,
 							&ecclayout);
 		if (!nand_chip->ecc.priv) {
-			pr_err("nand: error: unable to use s/w BCH library\n");
+			dev_err(&info->pdev->dev, "unable to use BCH library\n");
 			err = -EINVAL;
 			goto return_error;
 		}
 		break;
-#else
-		pr_err("nand: error: CONFIG_MTD_NAND_ECC_BCH not enabled\n");
-		err = -EINVAL;
-		goto return_error;
-#endif
 
 	case OMAP_ECC_BCH8_CODE_HW:
-#ifdef CONFIG_MTD_NAND_OMAP_BCH
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW ECC scheme\n");
 		nand_chip->ecc.mode		= NAND_ECC_HW;
 		nand_chip->ecc.size		= 512;
@@ -1952,12 +1980,13 @@ static int omap_nand_probe(struct platform_device *pdev)
 		nand_chip->ecc.calculate	= omap_calculate_ecc_bch;
 		nand_chip->ecc.read_page	= omap_read_page_bch;
 		nand_chip->ecc.write_page	= omap_write_page_bch;
-		/* This ECC scheme requires ELM H/W block */
-		err = is_elm_present(info, pdata->elm_of_node, BCH8_ECC);
-		if (err < 0) {
-			pr_err("nand: error: could not initialize ELM\n");
+
+		err = elm_config(info->elm_dev, BCH8_ECC,
+				 info->mtd.writesize / nand_chip->ecc.size,
+				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+		if (err < 0)
 			goto return_error;
-		}
+
 		/* define ECC layout */
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
@@ -1969,14 +1998,8 @@ static int omap_nand_probe(struct platform_device *pdev)
 		ecclayout->oobfree->offset	=
 				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		break;
-#else
-		pr_err("nand: error: CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
-		err = -EINVAL;
-		goto return_error;
-#endif
 
 	case OMAP_ECC_BCH16_CODE_HW:
-#ifdef CONFIG_MTD_NAND_OMAP_BCH
 		pr_info("using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
 		nand_chip->ecc.mode		= NAND_ECC_HW;
 		nand_chip->ecc.size		= 512;
@@ -1987,12 +2010,13 @@ static int omap_nand_probe(struct platform_device *pdev)
 		nand_chip->ecc.calculate	= omap_calculate_ecc_bch;
 		nand_chip->ecc.read_page	= omap_read_page_bch;
 		nand_chip->ecc.write_page	= omap_write_page_bch;
-		/* This ECC scheme requires ELM H/W block */
-		err = is_elm_present(info, pdata->elm_of_node, BCH16_ECC);
-		if (err < 0) {
-			pr_err("ELM is required for this ECC scheme\n");
+
+		err = elm_config(info->elm_dev, BCH16_ECC,
+				 info->mtd.writesize / nand_chip->ecc.size,
+				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+		if (err < 0)
 			goto return_error;
-		}
+
 		/* define ECC layout */
 		ecclayout->eccbytes		= nand_chip->ecc.bytes *
 							(mtd->writesize /
@@ -2004,13 +2028,8 @@ static int omap_nand_probe(struct platform_device *pdev)
 		ecclayout->oobfree->offset	=
 				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
 		break;
-#else
-		pr_err("nand: error: CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
-		err = -EINVAL;
-		goto return_error;
-#endif
 	default:
-		pr_err("nand: error: invalid or unsupported ECC scheme\n");
+		dev_err(&info->pdev->dev, "invalid or unsupported ECC scheme\n");
 		err = -EINVAL;
 		goto return_error;
 	}
@@ -2022,8 +2041,9 @@ static int omap_nand_probe(struct platform_device *pdev)
 	ecclayout->oobfree->length = mtd->oobsize - ecclayout->oobfree->offset;
 	/* check if NAND device's OOB is enough to store ECC signatures */
 	if (mtd->oobsize < (ecclayout->eccbytes + BADBLOCK_MARKER_LENGTH)) {
-		pr_err("not enough OOB bytes required = %d, available=%d\n",
-					   ecclayout->eccbytes, mtd->oobsize);
+		dev_err(&info->pdev->dev,
+			"not enough OOB bytes required = %d, available=%d\n",
+			ecclayout->eccbytes, mtd->oobsize);
 		err = -EINVAL;
 		goto return_error;
 	}
diff --git a/drivers/mtd/devices/elm.c b/drivers/mtd/nand/omap_elm.c
index b4f61c7fc161..b4f61c7fc161 100644
--- a/drivers/mtd/devices/elm.c
+++ b/drivers/mtd/nand/omap_elm.c
diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index c0670237e7a2..0ed7c603298f 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -395,7 +395,7 @@ static int flctl_dma_fifo0_transfer(struct sh_flctl *flctl, unsigned long *buf,
 				msecs_to_jiffies(3000));
 
 	if (ret <= 0) {
-		chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
+		dmaengine_terminate_all(chan);
 		dev_err(&flctl->pdev->dev, "wait_for_completion_timeout\n");
 	}
 
diff --git a/drivers/mtd/nand/sm_common.h b/drivers/mtd/nand/sm_common.h
index 00f4a83359b2..d3e028e58b0f 100644
--- a/drivers/mtd/nand/sm_common.h
+++ b/drivers/mtd/nand/sm_common.h
@@ -18,7 +18,7 @@ struct sm_oob {
 	uint8_t ecc2[3];
 	uint8_t lba_copy2[2];
 	uint8_t ecc1[3];
-} __attribute__((packed));
+} __packed;
 
 
 /* one sector is always 512 bytes, but it can consist of two nand pages */
diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c
index cf49c22673b9..c23184a47fc4 100644
--- a/drivers/mtd/sm_ftl.c
+++ b/drivers/mtd/sm_ftl.c
@@ -1058,7 +1058,7 @@ static int sm_write(struct mtd_blktrans_dev *dev,
 {
 	struct sm_ftl *ftl = dev->priv;
 	struct ftl_zone *zone;
-	int error, zone_num, block, boffset;
+	int error = 0, zone_num, block, boffset;
 
 	BUG_ON(ftl->readonly);
 	sm_break_offset(ftl, sec_no << 9, &zone_num, &block, &boffset);
diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig
index f8acfa4310ef..64a4f0edabc7 100644
--- a/drivers/mtd/spi-nor/Kconfig
+++ b/drivers/mtd/spi-nor/Kconfig
@@ -7,6 +7,20 @@ menuconfig MTD_SPI_NOR
 
 if MTD_SPI_NOR
 
+config MTD_SPI_NOR_USE_4K_SECTORS
+	bool "Use small 4096 B erase sectors"
+	default y
+	help
+	  Many flash memories support erasing small (4096 B) sectors. Depending
+	  on the usage this feature may provide performance gain in comparison
+	  to erasing whole blocks (32/64 KiB).
+	  Changing a small part of the flash's contents is usually faster with
+	  small sectors. On the other hand erasing should be faster when using
+	  64 KiB block instead of 16 × 4 KiB sectors.
+
+	  Please note that some tools/drivers/filesystems may not work with
+	  4096 B erase size (e.g. UBIFS requires 15 KiB as a minimum).
+
 config SPI_FSL_QUADSPI
 	tristate "Freescale Quad SPI controller"
 	depends on ARCH_MXC
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index b5ad6bebf5e7..ae16aa2f6885 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -611,6 +611,7 @@ const struct spi_device_id spi_nor_ids[] = {
 	{ "m25px32-s0", INFO(0x207316,  0, 64 * 1024, 64, SECT_4K) },
 	{ "m25px32-s1", INFO(0x206316,  0, 64 * 1024, 64, SECT_4K) },
 	{ "m25px64",    INFO(0x207117,  0, 64 * 1024, 128, 0) },
+	{ "m25px80",    INFO(0x207114,  0, 64 * 1024, 16, 0) },
 
 	/* Winbond -- w25x "blocks" are 64K, "sectors" are 4KiB */
 	{ "w25x10", INFO(0xef3011, 0, 64 * 1024,  2,  SECT_4K) },
@@ -623,7 +624,6 @@ const struct spi_device_id spi_nor_ids[] = {
 	{ "w25q32dw", INFO(0xef6016, 0, 64 * 1024,  64, SECT_4K) },
 	{ "w25x64", INFO(0xef3017, 0, 64 * 1024, 128, SECT_4K) },
 	{ "w25q64", INFO(0xef4017, 0, 64 * 1024, 128, SECT_4K) },
-	{ "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) },
 	{ "w25q80", INFO(0xef5014, 0, 64 * 1024,  16, SECT_4K) },
 	{ "w25q80bl", INFO(0xef4014, 0, 64 * 1024,  16, SECT_4K) },
 	{ "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) },
@@ -671,11 +671,6 @@ static const struct spi_device_id *spi_nor_read_id(struct spi_nor *nor)
 	return ERR_PTR(-ENODEV);
 }
 
-static const struct spi_device_id *jedec_probe(struct spi_nor *nor)
-{
-	return nor->read_id(nor);
-}
-
 static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len,
 			size_t *retlen, u_char *buf)
 {
@@ -920,7 +915,6 @@ int spi_nor_scan(struct spi_nor *nor, const struct spi_device_id *id,
 			enum read_mode mode)
 {
 	struct flash_info		*info;
-	struct flash_platform_data	*data;
 	struct device *dev = nor->dev;
 	struct mtd_info *mtd = nor->mtd;
 	struct device_node *np = dev->of_node;
@@ -931,34 +925,12 @@ int spi_nor_scan(struct spi_nor *nor, const struct spi_device_id *id,
 	if (ret)
 		return ret;
 
-	/* Platform data helps sort out which chip type we have, as
-	 * well as how this board partitions it.  If we don't have
-	 * a chip ID, try the JEDEC id commands; they'll work for most
-	 * newer chips, even if we don't recognize the particular chip.
-	 */
-	data = dev_get_platdata(dev);
-	if (data && data->type) {
-		const struct spi_device_id *plat_id;
-
-		for (i = 0; i < ARRAY_SIZE(spi_nor_ids) - 1; i++) {
-			plat_id = &spi_nor_ids[i];
-			if (strcmp(data->type, plat_id->name))
-				continue;
-			break;
-		}
-
-		if (i < ARRAY_SIZE(spi_nor_ids) - 1)
-			id = plat_id;
-		else
-			dev_warn(dev, "unrecognized id %s\n", data->type);
-	}
-
 	info = (void *)id->driver_data;
 
 	if (info->jedec_id) {
 		const struct spi_device_id *jid;
 
-		jid = jedec_probe(nor);
+		jid = nor->read_id(nor);
 		if (IS_ERR(jid)) {
 			return PTR_ERR(jid);
 		} else if (jid != id) {
@@ -990,11 +962,8 @@ int spi_nor_scan(struct spi_nor *nor, const struct spi_device_id *id,
 		write_sr(nor, 0);
 	}
 
-	if (data && data->name)
-		mtd->name = data->name;
-	else
+	if (!mtd->name)
 		mtd->name = dev_name(dev);
-
 	mtd->type = MTD_NORFLASH;
 	mtd->writesize = 1;
 	mtd->flags = MTD_CAP_NORFLASH;
@@ -1018,6 +987,7 @@ int spi_nor_scan(struct spi_nor *nor, const struct spi_device_id *id,
 	    nor->wait_till_ready == spi_nor_wait_till_ready)
 		nor->wait_till_ready = spi_nor_wait_till_fsr_ready;
 
+#ifdef CONFIG_MTD_SPI_NOR_USE_4K_SECTORS
 	/* prefer "small sector" erase if possible */
 	if (info->flags & SECT_4K) {
 		nor->erase_opcode = SPINOR_OP_BE_4K;
@@ -1025,7 +995,9 @@ int spi_nor_scan(struct spi_nor *nor, const struct spi_device_id *id,
 	} else if (info->flags & SECT_4K_PMC) {
 		nor->erase_opcode = SPINOR_OP_BE_4K_PMC;
 		mtd->erasesize = 4096;
-	} else {
+	} else
+#endif
+	{
 		nor->erase_opcode = SPINOR_OP_SE;
 		mtd->erasesize = info->sector_size;
 	}
diff --git a/drivers/mtd/tests/mtd_test.c b/drivers/mtd/tests/mtd_test.c
index 111ee46a7428..34736bbcc07b 100644
--- a/drivers/mtd/tests/mtd_test.c
+++ b/drivers/mtd/tests/mtd_test.c
@@ -10,7 +10,7 @@ int mtdtest_erase_eraseblock(struct mtd_info *mtd, unsigned int ebnum)
 {
 	int err;
 	struct erase_info ei;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	memset(&ei, 0, sizeof(struct erase_info));
 	ei.mtd  = mtd;
@@ -33,7 +33,7 @@ int mtdtest_erase_eraseblock(struct mtd_info *mtd, unsigned int ebnum)
 static int is_block_bad(struct mtd_info *mtd, unsigned int ebnum)
 {
 	int ret;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	ret = mtd_block_isbad(mtd, addr);
 	if (ret)
diff --git a/drivers/mtd/tests/nandbiterrs.c b/drivers/mtd/tests/nandbiterrs.c
index 6f976159611f..273f7e553954 100644
--- a/drivers/mtd/tests/nandbiterrs.c
+++ b/drivers/mtd/tests/nandbiterrs.c
@@ -364,7 +364,7 @@ static int __init mtd_nandbiterrs_init(void)
 
 	pr_info("Device uses %d subpages of %d bytes\n", subcount, subsize);
 
-	offset     = page_offset * mtd->writesize;
+	offset     = (loff_t)page_offset * mtd->writesize;
 	eraseblock = mtd_div_by_eb(offset, mtd);
 
 	pr_info("Using page=%u, offset=%llu, eraseblock=%u\n",
diff --git a/drivers/mtd/tests/oobtest.c b/drivers/mtd/tests/oobtest.c
index f19ab1acde1f..dc4f9602b97e 100644
--- a/drivers/mtd/tests/oobtest.c
+++ b/drivers/mtd/tests/oobtest.c
@@ -120,7 +120,7 @@ static int verify_eraseblock(int ebnum)
 	int i;
 	struct mtd_oob_ops ops;
 	int err = 0;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	prandom_bytes_state(&rnd_state, writebuf, use_len_max * pgcnt);
 	for (i = 0; i < pgcnt; ++i, addr += mtd->writesize) {
@@ -214,7 +214,7 @@ static int verify_eraseblock_in_one_go(int ebnum)
 {
 	struct mtd_oob_ops ops;
 	int err = 0;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 	size_t len = mtd->ecclayout->oobavail * pgcnt;
 
 	prandom_bytes_state(&rnd_state, writebuf, len);
@@ -568,7 +568,7 @@ static int __init mtd_oobtest_init(void)
 		size_t sz = mtd->ecclayout->oobavail;
 		if (bbt[i] || bbt[i + 1])
 			continue;
-		addr = (i + 1) * mtd->erasesize - mtd->writesize;
+		addr = (loff_t)(i + 1) * mtd->erasesize - mtd->writesize;
 		prandom_bytes_state(&rnd_state, writebuf, sz * cnt);
 		for (pg = 0; pg < cnt; ++pg) {
 			ops.mode      = MTD_OPS_AUTO_OOB;
@@ -598,7 +598,7 @@ static int __init mtd_oobtest_init(void)
 			continue;
 		prandom_bytes_state(&rnd_state, writebuf,
 					mtd->ecclayout->oobavail * 2);
-		addr = (i + 1) * mtd->erasesize - mtd->writesize;
+		addr = (loff_t)(i + 1) * mtd->erasesize - mtd->writesize;
 		ops.mode      = MTD_OPS_AUTO_OOB;
 		ops.len       = 0;
 		ops.retlen    = 0;
diff --git a/drivers/mtd/tests/pagetest.c b/drivers/mtd/tests/pagetest.c
index ed2d3f656fd2..88296e888e9d 100644
--- a/drivers/mtd/tests/pagetest.c
+++ b/drivers/mtd/tests/pagetest.c
@@ -52,7 +52,7 @@ static struct rnd_state rnd_state;
 
 static int write_eraseblock(int ebnum)
 {
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	prandom_bytes_state(&rnd_state, writebuf, mtd->erasesize);
 	cond_resched();
@@ -64,7 +64,7 @@ static int verify_eraseblock(int ebnum)
 	uint32_t j;
 	int err = 0, i;
 	loff_t addr0, addrn;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	addr0 = 0;
 	for (i = 0; i < ebcnt && bbt[i]; ++i)
diff --git a/drivers/mtd/tests/readtest.c b/drivers/mtd/tests/readtest.c
index 626e66d0f7e7..a54cf1511114 100644
--- a/drivers/mtd/tests/readtest.c
+++ b/drivers/mtd/tests/readtest.c
@@ -47,7 +47,7 @@ static int pgcnt;
 static int read_eraseblock_by_page(int ebnum)
 {
 	int i, ret, err = 0;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 	void *buf = iobuf;
 	void *oobbuf = iobuf1;
 
diff --git a/drivers/mtd/tests/speedtest.c b/drivers/mtd/tests/speedtest.c
index 87ff6a29f84e..5ee9f7021020 100644
--- a/drivers/mtd/tests/speedtest.c
+++ b/drivers/mtd/tests/speedtest.c
@@ -55,7 +55,7 @@ static int multiblock_erase(int ebnum, int blocks)
 {
 	int err;
 	struct erase_info ei;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	memset(&ei, 0, sizeof(struct erase_info));
 	ei.mtd  = mtd;
@@ -80,7 +80,7 @@ static int multiblock_erase(int ebnum, int blocks)
 
 static int write_eraseblock(int ebnum)
 {
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	return mtdtest_write(mtd, addr, mtd->erasesize, iobuf);
 }
@@ -88,7 +88,7 @@ static int write_eraseblock(int ebnum)
 static int write_eraseblock_by_page(int ebnum)
 {
 	int i, err = 0;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 	void *buf = iobuf;
 
 	for (i = 0; i < pgcnt; i++) {
@@ -106,7 +106,7 @@ static int write_eraseblock_by_2pages(int ebnum)
 {
 	size_t sz = pgsize * 2;
 	int i, n = pgcnt / 2, err = 0;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 	void *buf = iobuf;
 
 	for (i = 0; i < n; i++) {
@@ -124,7 +124,7 @@ static int write_eraseblock_by_2pages(int ebnum)
 
 static int read_eraseblock(int ebnum)
 {
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	return mtdtest_read(mtd, addr, mtd->erasesize, iobuf);
 }
@@ -132,7 +132,7 @@ static int read_eraseblock(int ebnum)
 static int read_eraseblock_by_page(int ebnum)
 {
 	int i, err = 0;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 	void *buf = iobuf;
 
 	for (i = 0; i < pgcnt; i++) {
@@ -150,7 +150,7 @@ static int read_eraseblock_by_2pages(int ebnum)
 {
 	size_t sz = pgsize * 2;
 	int i, n = pgcnt / 2, err = 0;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 	void *buf = iobuf;
 
 	for (i = 0; i < n; i++) {
diff --git a/drivers/mtd/tests/subpagetest.c b/drivers/mtd/tests/subpagetest.c
index a876371ad410..7b59ef522d5e 100644
--- a/drivers/mtd/tests/subpagetest.c
+++ b/drivers/mtd/tests/subpagetest.c
@@ -57,7 +57,7 @@ static int write_eraseblock(int ebnum)
 {
 	size_t written;
 	int err = 0;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	prandom_bytes_state(&rnd_state, writebuf, subpgsize);
 	err = mtd_write(mtd, addr, subpgsize, &written, writebuf);
@@ -92,7 +92,7 @@ static int write_eraseblock2(int ebnum)
 {
 	size_t written;
 	int err = 0, k;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	for (k = 1; k < 33; ++k) {
 		if (addr + (subpgsize * k) > (ebnum + 1) * mtd->erasesize)
@@ -131,7 +131,7 @@ static int verify_eraseblock(int ebnum)
 {
 	size_t read;
 	int err = 0;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	prandom_bytes_state(&rnd_state, writebuf, subpgsize);
 	clear_data(readbuf, subpgsize);
@@ -192,7 +192,7 @@ static int verify_eraseblock2(int ebnum)
 {
 	size_t read;
 	int err = 0, k;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	for (k = 1; k < 33; ++k) {
 		if (addr + (subpgsize * k) > (ebnum + 1) * mtd->erasesize)
@@ -227,7 +227,7 @@ static int verify_eraseblock_ff(int ebnum)
 	uint32_t j;
 	size_t read;
 	int err = 0;
-	loff_t addr = ebnum * mtd->erasesize;
+	loff_t addr = (loff_t)ebnum * mtd->erasesize;
 
 	memset(writebuf, 0xff, subpgsize);
 	for (j = 0; j < mtd->erasesize / subpgsize; ++j) {
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index 33c64955d4d7..8876c7d3d712 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -188,8 +188,9 @@ static int ubiblock_read_to_buf(struct ubiblock *dev, char *buffer,
 
 	ret = ubi_read(dev->desc, leb, buffer, offset, len);
 	if (ret) {
-		ubi_err("%s ubi_read error %d",
-			dev->gd->disk_name, ret);
+		ubi_err("%s: error %d while reading from LEB %d (offset %d, "
+		        "length %d)", dev->gd->disk_name, ret, leb, offset,
+			len);
 		return ret;
 	}
 	return 0;
@@ -378,7 +379,7 @@ int ubiblock_create(struct ubi_volume_info *vi)
 {
 	struct ubiblock *dev;
 	struct gendisk *gd;
-	u64 disk_capacity = ((u64)vi->size * vi->usable_leb_size) >> 9;
+	u64 disk_capacity = vi->used_bytes >> 9;
 	int ret;
 
 	if ((sector_t)disk_capacity != disk_capacity)
@@ -502,13 +503,8 @@ int ubiblock_remove(struct ubi_volume_info *vi)
 static int ubiblock_resize(struct ubi_volume_info *vi)
 {
 	struct ubiblock *dev;
-	u64 disk_capacity = ((u64)vi->size * vi->usable_leb_size) >> 9;
+	u64 disk_capacity = vi->used_bytes >> 9;
 
-	if ((sector_t)disk_capacity != disk_capacity) {
-		ubi_warn("%s: the volume is too big, cannot resize (%d LEBs)",
-			 dev->gd->disk_name, vi->size);
-		return -EFBIG;
-	}
 	/*
 	 * Need to lock the device list until we stop using the device,
 	 * otherwise the device struct might get released in
@@ -520,10 +516,20 @@ static int ubiblock_resize(struct ubi_volume_info *vi)
 		mutex_unlock(&devices_mutex);
 		return -ENODEV;
 	}
+	if ((sector_t)disk_capacity != disk_capacity) {
+		mutex_unlock(&devices_mutex);
+		ubi_warn("%s: the volume is too big (%d LEBs), cannot resize",
+			 dev->gd->disk_name, vi->size);
+		return -EFBIG;
+	}
 
 	mutex_lock(&dev->dev_mutex);
-	set_capacity(dev->gd, disk_capacity);
-	ubi_msg("%s resized to %d LEBs", dev->gd->disk_name, vi->size);
+
+	if (get_capacity(dev->gd) != disk_capacity) {
+		set_capacity(dev->gd, disk_capacity);
+		ubi_msg("%s resized to %lld bytes", dev->gd->disk_name,
+			vi->used_bytes);
+	}
 	mutex_unlock(&dev->dev_mutex);
 	mutex_unlock(&devices_mutex);
 	return 0;
@@ -547,6 +553,14 @@ static int ubiblock_notify(struct notifier_block *nb,
 	case UBI_VOLUME_RESIZED:
 		ubiblock_resize(&nt->vi);
 		break;
+	case UBI_VOLUME_UPDATED:
+		/*
+		 * If the volume is static, a content update might mean the
+		 * size (i.e. used_bytes) was also changed.
+		 */
+		if (nt->vi.vol_type == UBI_STATIC_VOLUME)
+			ubiblock_resize(&nt->vi);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c
index 7646220ca6e2..59de69a24e40 100644
--- a/drivers/mtd/ubi/cdev.c
+++ b/drivers/mtd/ubi/cdev.c
@@ -425,8 +425,10 @@ static long vol_cdev_ioctl(struct file *file, unsigned int cmd,
 			break;
 
 		err = ubi_start_update(ubi, vol, bytes);
-		if (bytes == 0)
+		if (bytes == 0) {
+			ubi_volume_notify(ubi, vol, UBI_VOLUME_UPDATED);
 			revoke_exclusive(desc, UBI_READWRITE);
+		}
 		break;
 	}
 
@@ -699,7 +701,7 @@ static int rename_volumes(struct ubi_device *ubi,
 		req->ents[i].name[req->ents[i].name_len] = '\0';
 		n = strlen(req->ents[i].name);
 		if (n != req->ents[i].name_len)
-			err = -EINVAL;
+			return -EINVAL;
 	}
 
 	/* Make sure volume IDs and names are unique */
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index 0e11671dadc4..2402d3b50171 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -441,10 +441,9 @@ retry:
 
 	err = ubi_io_read_data(ubi, buf, pnum, offset, len);
 	if (err) {
-		if (err == UBI_IO_BITFLIPS) {
+		if (err == UBI_IO_BITFLIPS)
 			scrub = 1;
-			err = 0;
-		} else if (mtd_is_eccerr(err)) {
+		else if (mtd_is_eccerr(err)) {
 			if (vol->vol_type == UBI_DYNAMIC_VOLUME)
 				goto out_unlock;
 			scrub = 1;
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index 0431b46d9fd9..cfd5b5e90156 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -24,7 +24,8 @@ size_t ubi_calc_fm_size(struct ubi_device *ubi)
 {
 	size_t size;
 
-	size = sizeof(struct ubi_fm_hdr) + \
+	size = sizeof(struct ubi_fm_sb) + \
+		sizeof(struct ubi_fm_hdr) + \
 		sizeof(struct ubi_fm_scan_pool) + \
 		sizeof(struct ubi_fm_scan_pool) + \
 		(ubi->peb_count * sizeof(struct ubi_fm_ec)) + \
@@ -330,6 +331,7 @@ static int process_pool_aeb(struct ubi_device *ubi, struct ubi_attach_info *ai,
 		av = tmp_av;
 	else {
 		ubi_err("orphaned volume in fastmap pool!");
+		kmem_cache_free(ai->aeb_slab_cache, new_aeb);
 		return UBI_BAD_FASTMAP;
 	}
 
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index 7bf416329c19..320fc38fa2a1 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -439,7 +439,8 @@ struct ubi_debug_info {
  *	     @move_to, @move_to_put @erase_pending, @wl_scheduled, @works,
  *	     @erroneous, and @erroneous_peb_count fields
  * @move_mutex: serializes eraseblock moves
- * @work_sem: synchronizes the WL worker with use tasks
+ * @work_sem: used to wait for all the scheduled works to finish and prevent
+ * new works from being submitted
  * @wl_scheduled: non-zero if the wear-leveling was scheduled
  * @lookuptbl: a table to quickly find a &struct ubi_wl_entry object for any
  *             physical eraseblock
@@ -713,14 +714,15 @@ struct ubi_attach_info {
  * @torture: if the physical eraseblock has to be tortured
  * @anchor: produce a anchor PEB to by used by fastmap
  *
- * The @func pointer points to the worker function. If the @cancel argument is
- * not zero, the worker has to free the resources and exit immediately. The
- * worker has to return zero in case of success and a negative error code in
+ * The @func pointer points to the worker function. If the @shutdown argument is
+ * not zero, the worker has to free the resources and exit immediately as the
+ * WL sub-system is shutting down.
+ * The worker has to return zero in case of success and a negative error code in
  * case of failure.
  */
 struct ubi_work {
 	struct list_head list;
-	int (*func)(struct ubi_device *ubi, struct ubi_work *wrk, int cancel);
+	int (*func)(struct ubi_device *ubi, struct ubi_work *wrk, int shutdown);
 	/* The below fields are only relevant to erasure works */
 	struct ubi_wl_entry *e;
 	int vol_id;
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 20f491713145..6654f191868e 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -272,7 +272,7 @@ static int produce_free_peb(struct ubi_device *ubi)
 {
 	int err;
 
-	while (!ubi->free.rb_node) {
+	while (!ubi->free.rb_node && ubi->works_count) {
 		spin_unlock(&ubi->wl_lock);
 
 		dbg_wl("do one work synchronously");
@@ -835,7 +835,7 @@ repeat:
  * @wrk: the work to schedule
  *
  * This function adds a work defined by @wrk to the tail of the pending works
- * list. Can only be used of ubi->work_sem is already held in read mode!
+ * list. Can only be used if ubi->work_sem is already held in read mode!
  */
 static void __schedule_ubi_work(struct ubi_device *ubi, struct ubi_work *wrk)
 {
@@ -864,7 +864,7 @@ static void schedule_ubi_work(struct ubi_device *ubi, struct ubi_work *wrk)
 }
 
 static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
-			int cancel);
+			int shutdown);
 
 #ifdef CONFIG_MTD_UBI_FASTMAP
 /**
@@ -990,14 +990,15 @@ int ubi_wl_put_fm_peb(struct ubi_device *ubi, struct ubi_wl_entry *fm_e,
  * wear_leveling_worker - wear-leveling worker function.
  * @ubi: UBI device description object
  * @wrk: the work object
- * @cancel: non-zero if the worker has to free memory and exit
+ * @shutdown: non-zero if the worker has to free memory and exit
+ * because the WL-subsystem is shutting down
  *
  * This function copies a more worn out physical eraseblock to a less worn out
  * one. Returns zero in case of success and a negative error code in case of
  * failure.
  */
 static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
-				int cancel)
+				int shutdown)
 {
 	int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0;
 	int vol_id = -1, uninitialized_var(lnum);
@@ -1008,7 +1009,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 	struct ubi_vid_hdr *vid_hdr;
 
 	kfree(wrk);
-	if (cancel)
+	if (shutdown)
 		return 0;
 
 	vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS);
@@ -1407,7 +1408,8 @@ int ubi_ensure_anchor_pebs(struct ubi_device *ubi)
  * erase_worker - physical eraseblock erase worker function.
  * @ubi: UBI device description object
  * @wl_wrk: the work object
- * @cancel: non-zero if the worker has to free memory and exit
+ * @shutdown: non-zero if the worker has to free memory and exit
+ * because the WL sub-system is shutting down
  *
  * This function erases a physical eraseblock and perform torture testing if
  * needed. It also takes care about marking the physical eraseblock bad if
@@ -1415,7 +1417,7 @@ int ubi_ensure_anchor_pebs(struct ubi_device *ubi)
  * failure.
  */
 static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
-			int cancel)
+			int shutdown)
 {
 	struct ubi_wl_entry *e = wl_wrk->e;
 	int pnum = e->pnum;
@@ -1423,7 +1425,7 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
 	int lnum = wl_wrk->lnum;
 	int err, available_consumed = 0;
 
-	if (cancel) {
+	if (shutdown) {
 		dbg_wl("cancel erasure of PEB %d EC %d", pnum, e->ec);
 		kfree(wl_wrk);
 		kmem_cache_free(ubi_wl_entry_slab, e);
@@ -1845,10 +1847,10 @@ int ubi_thread(void *u)
 }
 
 /**
- * cancel_pending - cancel all pending works.
+ * shutdown_work - shutdown all pending works.
  * @ubi: UBI device description object
  */
-static void cancel_pending(struct ubi_device *ubi)
+static void shutdown_work(struct ubi_device *ubi)
 {
 	while (!list_empty(&ubi->works)) {
 		struct ubi_work *wrk;
@@ -1997,7 +1999,7 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
 	return 0;
 
 out_free:
-	cancel_pending(ubi);
+	shutdown_work(ubi);
 	tree_destroy(&ubi->used);
 	tree_destroy(&ubi->free);
 	tree_destroy(&ubi->scrub);
@@ -2029,7 +2031,7 @@ static void protection_queue_destroy(struct ubi_device *ubi)
 void ubi_wl_close(struct ubi_device *ubi)
 {
 	dbg_wl("close the WL sub-system");
-	cancel_pending(ubi);
+	shutdown_work(ubi);
 	protection_queue_destroy(ubi);
 	tree_destroy(&ubi->used);
 	tree_destroy(&ubi->erroneous);
diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c
index 822616e3c375..0c33b92a5a81 100644
--- a/drivers/net/ethernet/micrel/ks8842.c
+++ b/drivers/net/ethernet/micrel/ks8842.c
@@ -875,13 +875,11 @@ static void ks8842_stop_dma(struct ks8842_adapter *adapter)
 
 	tx_ctl->adesc = NULL;
 	if (tx_ctl->chan)
-		tx_ctl->chan->device->device_control(tx_ctl->chan,
-			DMA_TERMINATE_ALL, 0);
+		dmaengine_terminate_all(tx_ctl->chan);
 
 	rx_ctl->adesc = NULL;
 	if (rx_ctl->chan)
-		rx_ctl->chan->device->device_control(rx_ctl->chan,
-			DMA_TERMINATE_ALL, 0);
+		dmaengine_terminate_all(rx_ctl->chan);
 
 	if (sg_dma_address(&rx_ctl->sg))
 		dma_unmap_single(adapter->dev, sg_dma_address(&rx_ctl->sg),
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 15396720f489..3652afd3ec78 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -954,7 +954,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	spin_lock_irqsave(&port->vio.lock, flags);
 
 	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
-	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
 		if (!netif_queue_stopped(dev)) {
 			netif_stop_queue(dev);
 
@@ -1049,7 +1049,7 @@ ldc_start_done:
 	dev->stats.tx_bytes += port->tx_bufs[txi].skb->len;
 
 	dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
-	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
 		netif_stop_queue(dev);
 		if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr))
 			netif_wake_queue(dev);
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 69557a26f749..049747f558c9 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -423,7 +423,7 @@ static void tile_net_pop_all_buffers(int instance, int stack)
 /* Provide linux buffers to mPIPE. */
 static void tile_net_provide_needed_buffers(void)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	int instance, kind;
 	for (instance = 0; instance < NR_MPIPE_MAX &&
 		     info->mpipe[instance].has_iqueue; instance++)	{
@@ -551,7 +551,7 @@ static inline bool filter_packet(struct net_device *dev, void *buf)
 static void tile_net_receive_skb(struct net_device *dev, struct sk_buff *skb,
 				 gxio_mpipe_idesc_t *idesc, unsigned long len)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	struct tile_net_priv *priv = netdev_priv(dev);
 	int instance = priv->instance;
 
@@ -585,7 +585,7 @@ static void tile_net_receive_skb(struct net_device *dev, struct sk_buff *skb,
 /* Handle a packet.  Return true if "processed", false if "filtered". */
 static bool tile_net_handle_packet(int instance, gxio_mpipe_idesc_t *idesc)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	struct mpipe_data *md = &mpipe_data[instance];
 	struct net_device *dev = md->tile_net_devs_for_channel[idesc->channel];
 	uint8_t l2_offset;
@@ -651,7 +651,7 @@ drop:
  */
 static int tile_net_poll(struct napi_struct *napi, int budget)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	unsigned int work = 0;
 	gxio_mpipe_idesc_t *idesc;
 	int instance, i, n;
@@ -700,7 +700,7 @@ done:
 /* Handle an ingress interrupt from an instance on the current cpu. */
 static irqreturn_t tile_net_handle_ingress_irq(int irq, void *id)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	napi_schedule(&info->mpipe[(uint64_t)id].napi);
 	return IRQ_HANDLED;
 }
@@ -763,7 +763,7 @@ static enum hrtimer_restart tile_net_handle_tx_wake_timer(struct hrtimer *t)
 /* Make sure the egress timer is scheduled. */
 static void tile_net_schedule_egress_timer(void)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 
 	if (!info->egress_timer_scheduled) {
 		hrtimer_start(&info->egress_timer,
@@ -780,7 +780,7 @@ static void tile_net_schedule_egress_timer(void)
  */
 static enum hrtimer_restart tile_net_handle_egress_timer(struct hrtimer *t)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	unsigned long irqflags;
 	bool pending = false;
 	int i, instance;
@@ -1927,7 +1927,7 @@ static void tso_egress(struct net_device *dev, gxio_mpipe_equeue_t *equeue,
  */
 static int tile_net_tx_tso(struct sk_buff *skb, struct net_device *dev)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	struct tile_net_priv *priv = netdev_priv(dev);
 	int channel = priv->echannel;
 	int instance = priv->instance;
@@ -1996,7 +1996,7 @@ static unsigned int tile_net_tx_frags(struct frag *frags,
 /* Help the kernel transmit a packet. */
 static int tile_net_tx(struct sk_buff *skb, struct net_device *dev)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	struct tile_net_priv *priv = netdev_priv(dev);
 	int instance = priv->instance;
 	struct mpipe_data *md = &mpipe_data[instance];
@@ -2138,7 +2138,7 @@ static int tile_net_set_mac_address(struct net_device *dev, void *p)
 static void tile_net_netpoll(struct net_device *dev)
 {
 	int instance = mpipe_instance(dev);
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	struct mpipe_data *md = &mpipe_data[instance];
 
 	disable_percpu_irq(md->ingress_irq);
@@ -2237,7 +2237,7 @@ static void tile_net_dev_init(const char *name, const uint8_t *mac)
 /* Per-cpu module initialization. */
 static void tile_net_init_module_percpu(void *unused)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	int my_cpu = smp_processor_id();
 	int instance;
 
diff --git a/drivers/net/ethernet/tile/tilepro.c b/drivers/net/ethernet/tile/tilepro.c
index 88818d5054ab..fb12d31cfcf6 100644
--- a/drivers/net/ethernet/tile/tilepro.c
+++ b/drivers/net/ethernet/tile/tilepro.c
@@ -996,13 +996,13 @@ static void tile_net_register(void *dev_ptr)
 	PDEBUG("tile_net_register(queue_id %d)\n", queue_id);
 
 	if (!strcmp(dev->name, "xgbe0"))
-		info = &__get_cpu_var(hv_xgbe0);
+		info = this_cpu_ptr(&hv_xgbe0);
 	else if (!strcmp(dev->name, "xgbe1"))
-		info = &__get_cpu_var(hv_xgbe1);
+		info = this_cpu_ptr(&hv_xgbe1);
 	else if (!strcmp(dev->name, "gbe0"))
-		info = &__get_cpu_var(hv_gbe0);
+		info = this_cpu_ptr(&hv_gbe0);
 	else if (!strcmp(dev->name, "gbe1"))
-		info = &__get_cpu_var(hv_gbe1);
+		info = this_cpu_ptr(&hv_gbe1);
 	else
 		BUG();
 
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 80e6f3430f65..68c3a3f4e0ab 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -594,7 +594,7 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			if (file == ppp->owner)
 				ppp_shutdown_interface(ppp);
 		}
-		if (atomic_long_read(&file->f_count) <= 2) {
+		if (atomic_long_read(&file->f_count) < 2) {
 			ppp_release(NULL, file);
 			err = 0;
 		} else
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index acaaf6784179..186ce541c657 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2152,9 +2152,7 @@ static int tun_chr_fasync(int fd, struct file *file, int on)
 		goto out;
 
 	if (on) {
-		ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0);
-		if (ret)
-			goto out;
+		__f_setown(file, task_pid(current), PIDTYPE_PID, 0);
 		tfile->flags |= TUN_FASYNC;
 	} else
 		tfile->flags &= ~TUN_FASYNC;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 13d0a8bc8bf3..d75256bd1a6a 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -123,9 +123,6 @@ struct virtnet_info {
 	/* Host can handle any s/g split between our header and packet data */
 	bool any_header_sg;
 
-	/* enable config space updates */
-	bool config_enable;
-
 	/* Active statistics */
 	struct virtnet_stats __percpu *stats;
 
@@ -135,9 +132,6 @@ struct virtnet_info {
 	/* Work struct for config space updates */
 	struct work_struct config_work;
 
-	/* Lock for config space updates */
-	struct mutex config_lock;
-
 	/* Does the affinity hint is set for virtqueues? */
 	bool affinity_hint_set;
 
@@ -1414,13 +1408,9 @@ static void virtnet_config_changed_work(struct work_struct *work)
 		container_of(work, struct virtnet_info, config_work);
 	u16 v;
 
-	mutex_lock(&vi->config_lock);
-	if (!vi->config_enable)
-		goto done;
-
 	if (virtio_cread_feature(vi->vdev, VIRTIO_NET_F_STATUS,
 				 struct virtio_net_config, status, &v) < 0)
-		goto done;
+		return;
 
 	if (v & VIRTIO_NET_S_ANNOUNCE) {
 		netdev_notify_peers(vi->dev);
@@ -1431,7 +1421,7 @@ static void virtnet_config_changed_work(struct work_struct *work)
 	v &= VIRTIO_NET_S_LINK_UP;
 
 	if (vi->status == v)
-		goto done;
+		return;
 
 	vi->status = v;
 
@@ -1442,8 +1432,6 @@ static void virtnet_config_changed_work(struct work_struct *work)
 		netif_carrier_off(vi->dev);
 		netif_tx_stop_all_queues(vi->dev);
 	}
-done:
-	mutex_unlock(&vi->config_lock);
 }
 
 static void virtnet_config_changed(struct virtio_device *vdev)
@@ -1764,8 +1752,6 @@ static int virtnet_probe(struct virtio_device *vdev)
 		u64_stats_init(&virtnet_stats->rx_syncp);
 	}
 
-	mutex_init(&vi->config_lock);
-	vi->config_enable = true;
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
 
 	/* If we can receive ANY GSO packets, we must allocate large ones. */
@@ -1813,6 +1799,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 		goto free_vqs;
 	}
 
+	virtio_device_ready(vdev);
+
 	/* Last of all, set up some receive buffers. */
 	for (i = 0; i < vi->curr_queue_pairs; i++) {
 		try_fill_recv(&vi->rq[i], GFP_KERNEL);
@@ -1849,6 +1837,8 @@ static int virtnet_probe(struct virtio_device *vdev)
 	return 0;
 
 free_recv_bufs:
+	vi->vdev->config->reset(vdev);
+
 	free_receive_bufs(vi);
 	unregister_netdev(dev);
 free_vqs:
@@ -1882,17 +1872,13 @@ static void virtnet_remove(struct virtio_device *vdev)
 
 	unregister_hotcpu_notifier(&vi->nb);
 
-	/* Prevent config work handler from accessing the device. */
-	mutex_lock(&vi->config_lock);
-	vi->config_enable = false;
-	mutex_unlock(&vi->config_lock);
+	/* Make sure no work handler is accessing the device. */
+	flush_work(&vi->config_work);
 
 	unregister_netdev(vi->dev);
 
 	remove_vq_common(vi);
 
-	flush_work(&vi->config_work);
-
 	free_percpu(vi->stats);
 	free_netdev(vi->dev);
 }
@@ -1905,10 +1891,8 @@ static int virtnet_freeze(struct virtio_device *vdev)
 
 	unregister_hotcpu_notifier(&vi->nb);
 
-	/* Prevent config work handler from accessing the device */
-	mutex_lock(&vi->config_lock);
-	vi->config_enable = false;
-	mutex_unlock(&vi->config_lock);
+	/* Make sure no work handler is accessing the device */
+	flush_work(&vi->config_work);
 
 	netif_device_detach(vi->dev);
 	cancel_delayed_work_sync(&vi->refill);
@@ -1923,8 +1907,6 @@ static int virtnet_freeze(struct virtio_device *vdev)
 
 	remove_vq_common(vi);
 
-	flush_work(&vi->config_work);
-
 	return 0;
 }
 
@@ -1937,6 +1919,8 @@ static int virtnet_restore(struct virtio_device *vdev)
 	if (err)
 		return err;
 
+	virtio_device_ready(vdev);
+
 	if (netif_running(vi->dev)) {
 		for (i = 0; i < vi->curr_queue_pairs; i++)
 			if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
@@ -1948,10 +1932,6 @@ static int virtnet_restore(struct virtio_device *vdev)
 
 	netif_device_attach(vi->dev);
 
-	mutex_lock(&vi->config_lock);
-	vi->config_enable = true;
-	mutex_unlock(&vi->config_lock);
-
 	rtnl_lock();
 	virtnet_set_queues(vi, vi->curr_queue_pairs);
 	rtnl_unlock();
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 3759479f959a..5f0199f6c31e 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -117,7 +117,6 @@ enum {
 /*
  * PCI vendor and device IDs.
  */
-#define PCI_VENDOR_ID_VMWARE            0x15AD
 #define PCI_DEVICE_ID_VMWARE_VMXNET3    0x07B0
 #define MAX_ETHERNET_CARDS		10
 #define MAX_PCI_PASSTHRU_DEVICE		6
diff --git a/drivers/net/wimax/Makefile b/drivers/net/wimax/Makefile
index 992bc02bc016..692184dd674a 100644
--- a/drivers/net/wimax/Makefile
+++ b/drivers/net/wimax/Makefile
@@ -1,5 +1 @@
-
 obj-$(CONFIG_WIMAX_I2400M)	+= i2400m/
-
-# (from Sam Ravnborg) force kbuild to create built-in.o
-obj- := dummy.o
diff --git a/drivers/net/wireless/hostap/hostap_proc.c b/drivers/net/wireless/hostap/hostap_proc.c
index 8efd17c52f65..dd84557cf957 100644
--- a/drivers/net/wireless/hostap/hostap_proc.c
+++ b/drivers/net/wireless/hostap/hostap_proc.c
@@ -168,7 +168,6 @@ static int prism2_bss_list_proc_show(struct seq_file *m, void *v)
 	local_info_t *local = m->private;
 	struct list_head *ptr = v;
 	struct hostap_bss_info *bss;
-	int i;
 
 	if (ptr == &local->bss_list) {
 		seq_printf(m, "#BSSID\tlast_update\tcount\tcapab_info\tSSID(txt)\t"
@@ -181,9 +180,7 @@ static int prism2_bss_list_proc_show(struct seq_file *m, void *v)
 		   bss->bssid, bss->last_update,
 		   bss->count, bss->capab_info);
 
-	for (i = 0; i < bss->ssid_len; i++)
-		seq_putc(m,bss->ssid[i] >= 32 && bss->ssid[i] < 127 ?
-			   bss->ssid[i] : '_');
+	seq_printf(m, "%*pE", (int)bss->ssid_len, bss->ssid);
 
 	seq_putc(m, '\t');
 	seq_printf(m, "%*phN", (int)bss->ssid_len, bss->ssid);
diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c
index c3d726f334e3..6fabea0309dd 100644
--- a/drivers/net/wireless/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/ipw2x00/ipw2100.c
@@ -2005,7 +2005,6 @@ static void isr_indicate_associated(struct ipw2100_priv *priv, u32 status)
 	u32 chan;
 	char *txratename;
 	u8 bssid[ETH_ALEN];
-	DECLARE_SSID_BUF(ssid);
 
 	/*
 	 * TBD: BSSID is usually 00:00:00:00:00:00 here and not
@@ -2067,8 +2066,8 @@ static void isr_indicate_associated(struct ipw2100_priv *priv, u32 status)
 		break;
 	}
 
-	IPW_DEBUG_INFO("%s: Associated with '%s' at %s, channel %d (BSSID=%pM)\n",
-		       priv->net_dev->name, print_ssid(ssid, essid, essid_len),
+	IPW_DEBUG_INFO("%s: Associated with '%*pE' at %s, channel %d (BSSID=%pM)\n",
+		       priv->net_dev->name, essid_len, essid,
 		       txratename, chan, bssid);
 
 	/* now we copy read ssid into dev */
@@ -2095,9 +2094,8 @@ static int ipw2100_set_essid(struct ipw2100_priv *priv, char *essid,
 		.host_command_length = ssid_len
 	};
 	int err;
-	DECLARE_SSID_BUF(ssid);
 
-	IPW_DEBUG_HC("SSID: '%s'\n", print_ssid(ssid, essid, ssid_len));
+	IPW_DEBUG_HC("SSID: '%*pE'\n", ssid_len, essid);
 
 	if (ssid_len)
 		memcpy(cmd.host_command_parameters, essid, ssid_len);
@@ -2138,11 +2136,8 @@ static int ipw2100_set_essid(struct ipw2100_priv *priv, char *essid,
 
 static void isr_indicate_association_lost(struct ipw2100_priv *priv, u32 status)
 {
-	DECLARE_SSID_BUF(ssid);
-
 	IPW_DEBUG(IPW_DL_NOTIF | IPW_DL_STATE | IPW_DL_ASSOC,
-		  "disassociated: '%s' %pM\n",
-		  print_ssid(ssid, priv->essid, priv->essid_len),
+		  "disassociated: '%*pE' %pM\n", priv->essid_len, priv->essid,
 		  priv->bssid);
 
 	priv->status &= ~(STATUS_ASSOCIATED | STATUS_ASSOCIATING);
@@ -6975,7 +6970,6 @@ static int ipw2100_wx_set_essid(struct net_device *dev,
 	char *essid = "";	/* ANY */
 	int length = 0;
 	int err = 0;
-	DECLARE_SSID_BUF(ssid);
 
 	mutex_lock(&priv->action_mutex);
 	if (!(priv->status & STATUS_INITIALIZED)) {
@@ -7005,8 +6999,7 @@ static int ipw2100_wx_set_essid(struct net_device *dev,
 		goto done;
 	}
 
-	IPW_DEBUG_WX("Setting ESSID: '%s' (%d)\n",
-		     print_ssid(ssid, essid, length), length);
+	IPW_DEBUG_WX("Setting ESSID: '%*pE' (%d)\n", length, essid, length);
 
 	priv->essid_len = length;
 	memcpy(priv->essid, essid, priv->essid_len);
@@ -7027,13 +7020,12 @@ static int ipw2100_wx_get_essid(struct net_device *dev,
 	 */
 
 	struct ipw2100_priv *priv = libipw_priv(dev);
-	DECLARE_SSID_BUF(ssid);
 
 	/* If we are associated, trying to associate, or have a statically
 	 * configured ESSID then return that; otherwise return ANY */
 	if (priv->config & CFG_STATIC_ESSID || priv->status & STATUS_ASSOCIATED) {
-		IPW_DEBUG_WX("Getting essid: '%s'\n",
-			     print_ssid(ssid, priv->essid, priv->essid_len));
+		IPW_DEBUG_WX("Getting essid: '%*pE'\n",
+			     priv->essid_len, priv->essid);
 		memcpy(extra, priv->essid, priv->essid_len);
 		wrqu->essid.length = priv->essid_len;
 		wrqu->essid.flags = 1;	/* active */
diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c
index f0c3c77a48d3..edc344334a75 100644
--- a/drivers/net/wireless/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/ipw2x00/ipw2200.c
@@ -4496,7 +4496,6 @@ static void handle_scan_event(struct ipw_priv *priv)
 static void ipw_rx_notification(struct ipw_priv *priv,
 				       struct ipw_rx_notification *notif)
 {
-	DECLARE_SSID_BUF(ssid);
 	u16 size = le16_to_cpu(notif->size);
 
 	IPW_DEBUG_NOTIF("type = %i (%d bytes)\n", notif->subtype, size);
@@ -4509,9 +4508,8 @@ static void ipw_rx_notification(struct ipw_priv *priv,
 			case CMAS_ASSOCIATED:{
 					IPW_DEBUG(IPW_DL_NOTIF | IPW_DL_STATE |
 						  IPW_DL_ASSOC,
-						  "associated: '%s' %pM\n",
-						  print_ssid(ssid, priv->essid,
-							     priv->essid_len),
+						  "associated: '%*pE' %pM\n",
+						  priv->essid_len, priv->essid,
 						  priv->bssid);
 
 					switch (priv->ieee->iw_mode) {
@@ -4585,14 +4583,9 @@ static void ipw_rx_notification(struct ipw_priv *priv,
 						IPW_DEBUG(IPW_DL_NOTIF |
 							  IPW_DL_STATE |
 							  IPW_DL_ASSOC,
-							  "deauthenticated: '%s' "
-							  "%pM"
-							  ": (0x%04X) - %s\n",
-							  print_ssid(ssid,
-								     priv->
-								     essid,
-								     priv->
-								     essid_len),
+							  "deauthenticated: '%*pE' %pM: (0x%04X) - %s\n",
+							  priv->essid_len,
+							  priv->essid,
 							  priv->bssid,
 							  le16_to_cpu(auth->status),
 							  ipw_get_status_code
@@ -4610,9 +4603,8 @@ static void ipw_rx_notification(struct ipw_priv *priv,
 
 					IPW_DEBUG(IPW_DL_NOTIF | IPW_DL_STATE |
 						  IPW_DL_ASSOC,
-						  "authenticated: '%s' %pM\n",
-						  print_ssid(ssid, priv->essid,
-							     priv->essid_len),
+						  "authenticated: '%*pE' %pM\n",
+						  priv->essid_len, priv->essid,
 						  priv->bssid);
 					break;
 				}
@@ -4638,9 +4630,8 @@ static void ipw_rx_notification(struct ipw_priv *priv,
 
 					IPW_DEBUG(IPW_DL_NOTIF | IPW_DL_STATE |
 						  IPW_DL_ASSOC,
-						  "disassociated: '%s' %pM\n",
-						  print_ssid(ssid, priv->essid,
-							     priv->essid_len),
+						  "disassociated: '%*pE' %pM\n",
+						  priv->essid_len, priv->essid,
 						  priv->bssid);
 
 					priv->status &=
@@ -4676,9 +4667,8 @@ static void ipw_rx_notification(struct ipw_priv *priv,
 			switch (auth->state) {
 			case CMAS_AUTHENTICATED:
 				IPW_DEBUG(IPW_DL_NOTIF | IPW_DL_STATE,
-					  "authenticated: '%s' %pM\n",
-					  print_ssid(ssid, priv->essid,
-						     priv->essid_len),
+					  "authenticated: '%*pE' %pM\n",
+					  priv->essid_len, priv->essid,
 					  priv->bssid);
 				priv->status |= STATUS_AUTH;
 				break;
@@ -4695,9 +4685,8 @@ static void ipw_rx_notification(struct ipw_priv *priv,
 				}
 				IPW_DEBUG(IPW_DL_NOTIF | IPW_DL_STATE |
 					  IPW_DL_ASSOC,
-					  "deauthenticated: '%s' %pM\n",
-					  print_ssid(ssid, priv->essid,
-						     priv->essid_len),
+					  "deauthenticated: '%*pE' %pM\n",
+					  priv->essid_len, priv->essid,
 					  priv->bssid);
 
 				priv->status &= ~(STATUS_ASSOCIATING |
@@ -5516,16 +5505,13 @@ static int ipw_find_adhoc_network(struct ipw_priv *priv,
 				  int roaming)
 {
 	struct ipw_supported_rates rates;
-	DECLARE_SSID_BUF(ssid);
 
 	/* Verify that this network's capability is compatible with the
 	 * current mode (AdHoc or Infrastructure) */
 	if ((priv->ieee->iw_mode == IW_MODE_ADHOC &&
 	     !(network->capability & WLAN_CAPABILITY_IBSS))) {
-		IPW_DEBUG_MERGE("Network '%s (%pM)' excluded due to "
-				"capability mismatch.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_MERGE("Network '%*pE (%pM)' excluded due to capability mismatch.\n",
+				network->ssid_len, network->ssid,
 				network->bssid);
 		return 0;
 	}
@@ -5536,10 +5522,8 @@ static int ipw_find_adhoc_network(struct ipw_priv *priv,
 		if ((network->ssid_len != match->network->ssid_len) ||
 		    memcmp(network->ssid, match->network->ssid,
 			   network->ssid_len)) {
-			IPW_DEBUG_MERGE("Network '%s (%pM)' excluded "
-					"because of non-network ESSID.\n",
-					print_ssid(ssid, network->ssid,
-						   network->ssid_len),
+			IPW_DEBUG_MERGE("Network '%*pE (%pM)' excluded because of non-network ESSID.\n",
+					network->ssid_len, network->ssid,
 					network->bssid);
 			return 0;
 		}
@@ -5550,17 +5534,10 @@ static int ipw_find_adhoc_network(struct ipw_priv *priv,
 		    ((network->ssid_len != priv->essid_len) ||
 		     memcmp(network->ssid, priv->essid,
 			    min(network->ssid_len, priv->essid_len)))) {
-			char escaped[IW_ESSID_MAX_SIZE * 2 + 1];
-
-			strlcpy(escaped,
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
-				sizeof(escaped));
-			IPW_DEBUG_MERGE("Network '%s (%pM)' excluded "
-					"because of ESSID mismatch: '%s'.\n",
-					escaped, network->bssid,
-					print_ssid(ssid, priv->essid,
-						   priv->essid_len));
+			IPW_DEBUG_MERGE("Network '%*pE (%pM)' excluded because of ESSID mismatch: '%*pE'.\n",
+					network->ssid_len, network->ssid,
+					network->bssid, priv->essid_len,
+					priv->essid);
 			return 0;
 		}
 	}
@@ -5569,26 +5546,20 @@ static int ipw_find_adhoc_network(struct ipw_priv *priv,
 	 * testing everything else. */
 
 	if (network->time_stamp[0] < match->network->time_stamp[0]) {
-		IPW_DEBUG_MERGE("Network '%s excluded because newer than "
-				"current network.\n",
-				print_ssid(ssid, match->network->ssid,
-					   match->network->ssid_len));
+		IPW_DEBUG_MERGE("Network '%*pE excluded because newer than current network.\n",
+				match->network->ssid_len, match->network->ssid);
 		return 0;
 	} else if (network->time_stamp[1] < match->network->time_stamp[1]) {
-		IPW_DEBUG_MERGE("Network '%s excluded because newer than "
-				"current network.\n",
-				print_ssid(ssid, match->network->ssid,
-					   match->network->ssid_len));
+		IPW_DEBUG_MERGE("Network '%*pE excluded because newer than current network.\n",
+				match->network->ssid_len, match->network->ssid);
 		return 0;
 	}
 
 	/* Now go through and see if the requested network is valid... */
 	if (priv->ieee->scan_age != 0 &&
 	    time_after(jiffies, network->last_scanned + priv->ieee->scan_age)) {
-		IPW_DEBUG_MERGE("Network '%s (%pM)' excluded "
-				"because of age: %ums.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_MERGE("Network '%*pE (%pM)' excluded because of age: %ums.\n",
+				network->ssid_len, network->ssid,
 				network->bssid,
 				jiffies_to_msecs(jiffies -
 						 network->last_scanned));
@@ -5597,10 +5568,8 @@ static int ipw_find_adhoc_network(struct ipw_priv *priv,
 
 	if ((priv->config & CFG_STATIC_CHANNEL) &&
 	    (network->channel != priv->channel)) {
-		IPW_DEBUG_MERGE("Network '%s (%pM)' excluded "
-				"because of channel mismatch: %d != %d.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_MERGE("Network '%*pE (%pM)' excluded because of channel mismatch: %d != %d.\n",
+				network->ssid_len, network->ssid,
 				network->bssid,
 				network->channel, priv->channel);
 		return 0;
@@ -5609,10 +5578,8 @@ static int ipw_find_adhoc_network(struct ipw_priv *priv,
 	/* Verify privacy compatibility */
 	if (((priv->capability & CAP_PRIVACY_ON) ? 1 : 0) !=
 	    ((network->capability & WLAN_CAPABILITY_PRIVACY) ? 1 : 0)) {
-		IPW_DEBUG_MERGE("Network '%s (%pM)' excluded "
-				"because of privacy mismatch: %s != %s.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_MERGE("Network '%*pE (%pM)' excluded because of privacy mismatch: %s != %s.\n",
+				network->ssid_len, network->ssid,
 				network->bssid,
 				priv->
 				capability & CAP_PRIVACY_ON ? "on" : "off",
@@ -5623,22 +5590,16 @@ static int ipw_find_adhoc_network(struct ipw_priv *priv,
 	}
 
 	if (ether_addr_equal(network->bssid, priv->bssid)) {
-		IPW_DEBUG_MERGE("Network '%s (%pM)' excluded "
-				"because of the same BSSID match: %pM"
-				".\n", print_ssid(ssid, network->ssid,
-						  network->ssid_len),
-				network->bssid,
-				priv->bssid);
+		IPW_DEBUG_MERGE("Network '%*pE (%pM)' excluded because of the same BSSID match: %pM.\n",
+				network->ssid_len, network->ssid,
+				network->bssid, priv->bssid);
 		return 0;
 	}
 
 	/* Filter out any incompatible freq / mode combinations */
 	if (!libipw_is_valid_mode(priv->ieee, network->mode)) {
-		IPW_DEBUG_MERGE("Network '%s (%pM)' excluded "
-				"because of invalid frequency/mode "
-				"combination.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_MERGE("Network '%*pE (%pM)' excluded because of invalid frequency/mode combination.\n",
+				network->ssid_len, network->ssid,
 				network->bssid);
 		return 0;
 	}
@@ -5646,20 +5607,15 @@ static int ipw_find_adhoc_network(struct ipw_priv *priv,
 	/* Ensure that the rates supported by the driver are compatible with
 	 * this AP, including verification of basic rates (mandatory) */
 	if (!ipw_compatible_rates(priv, network, &rates)) {
-		IPW_DEBUG_MERGE("Network '%s (%pM)' excluded "
-				"because configured rate mask excludes "
-				"AP mandatory rate.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_MERGE("Network '%*pE (%pM)' excluded because configured rate mask excludes AP mandatory rate.\n",
+				network->ssid_len, network->ssid,
 				network->bssid);
 		return 0;
 	}
 
 	if (rates.num_rates == 0) {
-		IPW_DEBUG_MERGE("Network '%s (%pM)' excluded "
-				"because of no compatible rates.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_MERGE("Network '%*pE (%pM)' excluded because of no compatible rates.\n",
+				network->ssid_len, network->ssid,
 				network->bssid);
 		return 0;
 	}
@@ -5671,16 +5627,14 @@ static int ipw_find_adhoc_network(struct ipw_priv *priv,
 	/* Set up 'new' AP to this network */
 	ipw_copy_rates(&match->rates, &rates);
 	match->network = network;
-	IPW_DEBUG_MERGE("Network '%s (%pM)' is a viable match.\n",
-			print_ssid(ssid, network->ssid, network->ssid_len),
-			network->bssid);
+	IPW_DEBUG_MERGE("Network '%*pE (%pM)' is a viable match.\n",
+			network->ssid_len, network->ssid, network->bssid);
 
 	return 1;
 }
 
 static void ipw_merge_adhoc_network(struct work_struct *work)
 {
-	DECLARE_SSID_BUF(ssid);
 	struct ipw_priv *priv =
 		container_of(work, struct ipw_priv, merge_networks);
 	struct libipw_network *network = NULL;
@@ -5710,9 +5664,8 @@ static void ipw_merge_adhoc_network(struct work_struct *work)
 
 		mutex_lock(&priv->mutex);
 		if ((priv->ieee->iw_mode == IW_MODE_ADHOC)) {
-			IPW_DEBUG_MERGE("remove network %s\n",
-					print_ssid(ssid, priv->essid,
-						   priv->essid_len));
+			IPW_DEBUG_MERGE("remove network %*pE\n",
+					priv->essid_len, priv->essid);
 			ipw_remove_current_network(priv);
 		}
 
@@ -5728,7 +5681,6 @@ static int ipw_best_network(struct ipw_priv *priv,
 			    struct libipw_network *network, int roaming)
 {
 	struct ipw_supported_rates rates;
-	DECLARE_SSID_BUF(ssid);
 
 	/* Verify that this network's capability is compatible with the
 	 * current mode (AdHoc or Infrastructure) */
@@ -5736,10 +5688,8 @@ static int ipw_best_network(struct ipw_priv *priv,
 	     !(network->capability & WLAN_CAPABILITY_ESS)) ||
 	    (priv->ieee->iw_mode == IW_MODE_ADHOC &&
 	     !(network->capability & WLAN_CAPABILITY_IBSS))) {
-		IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded due to "
-				"capability mismatch.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded due to capability mismatch.\n",
+				network->ssid_len, network->ssid,
 				network->bssid);
 		return 0;
 	}
@@ -5750,10 +5700,8 @@ static int ipw_best_network(struct ipw_priv *priv,
 		if ((network->ssid_len != match->network->ssid_len) ||
 		    memcmp(network->ssid, match->network->ssid,
 			   network->ssid_len)) {
-			IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded "
-					"because of non-network ESSID.\n",
-					print_ssid(ssid, network->ssid,
-						   network->ssid_len),
+			IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because of non-network ESSID.\n",
+					network->ssid_len, network->ssid,
 					network->bssid);
 			return 0;
 		}
@@ -5764,16 +5712,10 @@ static int ipw_best_network(struct ipw_priv *priv,
 		    ((network->ssid_len != priv->essid_len) ||
 		     memcmp(network->ssid, priv->essid,
 			    min(network->ssid_len, priv->essid_len)))) {
-			char escaped[IW_ESSID_MAX_SIZE * 2 + 1];
-			strlcpy(escaped,
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
-				sizeof(escaped));
-			IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded "
-					"because of ESSID mismatch: '%s'.\n",
-					escaped, network->bssid,
-					print_ssid(ssid, priv->essid,
-						   priv->essid_len));
+			IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because of ESSID mismatch: '%*pE'.\n",
+					network->ssid_len, network->ssid,
+					network->bssid, priv->essid_len,
+					priv->essid);
 			return 0;
 		}
 	}
@@ -5781,16 +5723,10 @@ static int ipw_best_network(struct ipw_priv *priv,
 	/* If the old network rate is better than this one, don't bother
 	 * testing everything else. */
 	if (match->network && match->network->stats.rssi > network->stats.rssi) {
-		char escaped[IW_ESSID_MAX_SIZE * 2 + 1];
-		strlcpy(escaped,
-			print_ssid(ssid, network->ssid, network->ssid_len),
-			sizeof(escaped));
-		IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded because "
-				"'%s (%pM)' has a stronger signal.\n",
-				escaped, network->bssid,
-				print_ssid(ssid, match->network->ssid,
-					   match->network->ssid_len),
-				match->network->bssid);
+		IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because '%*pE (%pM)' has a stronger signal.\n",
+				network->ssid_len, network->ssid,
+				network->bssid, match->network->ssid_len,
+				match->network->ssid, match->network->bssid);
 		return 0;
 	}
 
@@ -5798,11 +5734,8 @@ static int ipw_best_network(struct ipw_priv *priv,
 	 * last 3 seconds, do not try and associate again... */
 	if (network->last_associate &&
 	    time_after(network->last_associate + (HZ * 3UL), jiffies)) {
-		IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded "
-				"because of storming (%ums since last "
-				"assoc attempt).\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because of storming (%ums since last assoc attempt).\n",
+				network->ssid_len, network->ssid,
 				network->bssid,
 				jiffies_to_msecs(jiffies -
 						 network->last_associate));
@@ -5812,10 +5745,8 @@ static int ipw_best_network(struct ipw_priv *priv,
 	/* Now go through and see if the requested network is valid... */
 	if (priv->ieee->scan_age != 0 &&
 	    time_after(jiffies, network->last_scanned + priv->ieee->scan_age)) {
-		IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded "
-				"because of age: %ums.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because of age: %ums.\n",
+				network->ssid_len, network->ssid,
 				network->bssid,
 				jiffies_to_msecs(jiffies -
 						 network->last_scanned));
@@ -5824,10 +5755,8 @@ static int ipw_best_network(struct ipw_priv *priv,
 
 	if ((priv->config & CFG_STATIC_CHANNEL) &&
 	    (network->channel != priv->channel)) {
-		IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded "
-				"because of channel mismatch: %d != %d.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because of channel mismatch: %d != %d.\n",
+				network->ssid_len, network->ssid,
 				network->bssid,
 				network->channel, priv->channel);
 		return 0;
@@ -5836,10 +5765,8 @@ static int ipw_best_network(struct ipw_priv *priv,
 	/* Verify privacy compatibility */
 	if (((priv->capability & CAP_PRIVACY_ON) ? 1 : 0) !=
 	    ((network->capability & WLAN_CAPABILITY_PRIVACY) ? 1 : 0)) {
-		IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded "
-				"because of privacy mismatch: %s != %s.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because of privacy mismatch: %s != %s.\n",
+				network->ssid_len, network->ssid,
 				network->bssid,
 				priv->capability & CAP_PRIVACY_ON ? "on" :
 				"off",
@@ -5850,31 +5777,24 @@ static int ipw_best_network(struct ipw_priv *priv,
 
 	if ((priv->config & CFG_STATIC_BSSID) &&
 	    !ether_addr_equal(network->bssid, priv->bssid)) {
-		IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded "
-				"because of BSSID mismatch: %pM.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because of BSSID mismatch: %pM.\n",
+				network->ssid_len, network->ssid,
 				network->bssid, priv->bssid);
 		return 0;
 	}
 
 	/* Filter out any incompatible freq / mode combinations */
 	if (!libipw_is_valid_mode(priv->ieee, network->mode)) {
-		IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded "
-				"because of invalid frequency/mode "
-				"combination.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because of invalid frequency/mode combination.\n",
+				network->ssid_len, network->ssid,
 				network->bssid);
 		return 0;
 	}
 
 	/* Filter out invalid channel in current GEO */
 	if (!libipw_is_valid_channel(priv->ieee, network->channel)) {
-		IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded "
-				"because of invalid channel in current GEO\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because of invalid channel in current GEO\n",
+				network->ssid_len, network->ssid,
 				network->bssid);
 		return 0;
 	}
@@ -5882,20 +5802,15 @@ static int ipw_best_network(struct ipw_priv *priv,
 	/* Ensure that the rates supported by the driver are compatible with
 	 * this AP, including verification of basic rates (mandatory) */
 	if (!ipw_compatible_rates(priv, network, &rates)) {
-		IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded "
-				"because configured rate mask excludes "
-				"AP mandatory rate.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because configured rate mask excludes AP mandatory rate.\n",
+				network->ssid_len, network->ssid,
 				network->bssid);
 		return 0;
 	}
 
 	if (rates.num_rates == 0) {
-		IPW_DEBUG_ASSOC("Network '%s (%pM)' excluded "
-				"because of no compatible rates.\n",
-				print_ssid(ssid, network->ssid,
-					   network->ssid_len),
+		IPW_DEBUG_ASSOC("Network '%*pE (%pM)' excluded because of no compatible rates.\n",
+				network->ssid_len, network->ssid,
 				network->bssid);
 		return 0;
 	}
@@ -5908,9 +5823,8 @@ static int ipw_best_network(struct ipw_priv *priv,
 	ipw_copy_rates(&match->rates, &rates);
 	match->network = network;
 
-	IPW_DEBUG_ASSOC("Network '%s (%pM)' is a viable match.\n",
-			print_ssid(ssid, network->ssid, network->ssid_len),
-			network->bssid);
+	IPW_DEBUG_ASSOC("Network '%*pE (%pM)' is a viable match.\n",
+			network->ssid_len, network->ssid, network->bssid);
 
 	return 1;
 }
@@ -6152,7 +6066,6 @@ static void ipw_bg_adhoc_check(struct work_struct *work)
 
 static void ipw_debug_config(struct ipw_priv *priv)
 {
-	DECLARE_SSID_BUF(ssid);
 	IPW_DEBUG_INFO("Scan completed, no valid APs matched "
 		       "[CFG 0x%08X]\n", priv->config);
 	if (priv->config & CFG_STATIC_CHANNEL)
@@ -6160,8 +6073,8 @@ static void ipw_debug_config(struct ipw_priv *priv)
 	else
 		IPW_DEBUG_INFO("Channel unlocked.\n");
 	if (priv->config & CFG_STATIC_ESSID)
-		IPW_DEBUG_INFO("ESSID locked to '%s'\n",
-			       print_ssid(ssid, priv->essid, priv->essid_len));
+		IPW_DEBUG_INFO("ESSID locked to '%*pE'\n",
+			       priv->essid_len, priv->essid);
 	else
 		IPW_DEBUG_INFO("ESSID unlocked.\n");
 	if (priv->config & CFG_STATIC_BSSID)
@@ -7385,7 +7298,6 @@ static int ipw_associate_network(struct ipw_priv *priv,
 				 struct ipw_supported_rates *rates, int roaming)
 {
 	int err;
-	DECLARE_SSID_BUF(ssid);
 
 	if (priv->config & CFG_FIXED_RATE)
 		ipw_set_fixed_rate(priv, network->mode);
@@ -7451,10 +7363,9 @@ static int ipw_associate_network(struct ipw_priv *priv,
 		priv->assoc_request.capability &=
 		    ~cpu_to_le16(WLAN_CAPABILITY_SHORT_SLOT_TIME);
 
-	IPW_DEBUG_ASSOC("%ssociation attempt: '%s', channel %d, "
-			"802.11%c [%d], %s[:%s], enc=%s%s%s%c%c\n",
+	IPW_DEBUG_ASSOC("%ssociation attempt: '%*pE', channel %d, 802.11%c [%d], %s[:%s], enc=%s%s%s%c%c\n",
 			roaming ? "Rea" : "A",
-			print_ssid(ssid, priv->essid, priv->essid_len),
+			priv->essid_len, priv->essid,
 			network->channel,
 			ipw_modes[priv->assoc_request.ieee_mode],
 			rates->num_rates,
@@ -7553,9 +7464,8 @@ static int ipw_associate_network(struct ipw_priv *priv,
 		return err;
 	}
 
-	IPW_DEBUG(IPW_DL_STATE, "associating: '%s' %pM\n",
-		  print_ssid(ssid, priv->essid, priv->essid_len),
-		  priv->bssid);
+	IPW_DEBUG(IPW_DL_STATE, "associating: '%*pE' %pM\n",
+		  priv->essid_len, priv->essid, priv->bssid);
 
 	return 0;
 }
@@ -7645,7 +7555,6 @@ static int ipw_associate(void *data)
 	struct ipw_supported_rates *rates;
 	struct list_head *element;
 	unsigned long flags;
-	DECLARE_SSID_BUF(ssid);
 
 	if (priv->ieee->iw_mode == IW_MODE_MONITOR) {
 		IPW_DEBUG_ASSOC("Not attempting association (monitor mode)\n");
@@ -7704,10 +7613,8 @@ static int ipw_associate(void *data)
 			/* If there are no more slots, expire the oldest */
 			list_del(&oldest->list);
 			target = oldest;
-			IPW_DEBUG_ASSOC("Expired '%s' (%pM) from "
-					"network list.\n",
-					print_ssid(ssid, target->ssid,
-						   target->ssid_len),
+			IPW_DEBUG_ASSOC("Expired '%*pE' (%pM) from network list.\n",
+					target->ssid_len, target->ssid,
 					target->bssid);
 			list_add_tail(&target->list,
 				      &priv->ieee->network_free_list);
@@ -9093,7 +9000,6 @@ static int ipw_wx_set_essid(struct net_device *dev,
 {
 	struct ipw_priv *priv = libipw_priv(dev);
         int length;
-	DECLARE_SSID_BUF(ssid);
 
         mutex_lock(&priv->mutex);
 
@@ -9118,8 +9024,7 @@ static int ipw_wx_set_essid(struct net_device *dev,
 		return 0;
 	}
 
-	IPW_DEBUG_WX("Setting ESSID: '%s' (%d)\n",
-		     print_ssid(ssid, extra, length), length);
+	IPW_DEBUG_WX("Setting ESSID: '%*pE' (%d)\n", length, extra, length);
 
 	priv->essid_len = length;
 	memcpy(priv->essid, extra, priv->essid_len);
@@ -9138,15 +9043,14 @@ static int ipw_wx_get_essid(struct net_device *dev,
 			    union iwreq_data *wrqu, char *extra)
 {
 	struct ipw_priv *priv = libipw_priv(dev);
-	DECLARE_SSID_BUF(ssid);
 
 	/* If we are associated, trying to associate, or have a statically
 	 * configured ESSID then return that; otherwise return ANY */
 	mutex_lock(&priv->mutex);
 	if (priv->config & CFG_STATIC_ESSID ||
 	    priv->status & (STATUS_ASSOCIATED | STATUS_ASSOCIATING)) {
-		IPW_DEBUG_WX("Getting essid: '%s'\n",
-			     print_ssid(ssid, priv->essid, priv->essid_len));
+		IPW_DEBUG_WX("Getting essid: '%*pE'\n",
+			     priv->essid_len, priv->essid);
 		memcpy(extra, priv->essid, priv->essid_len);
 		wrqu->essid.length = priv->essid_len;
 		wrqu->essid.flags = 1;	/* active */
diff --git a/drivers/net/wireless/ipw2x00/libipw_rx.c b/drivers/net/wireless/ipw2x00/libipw_rx.c
index a586a85bfcfe..2d66984079bb 100644
--- a/drivers/net/wireless/ipw2x00/libipw_rx.c
+++ b/drivers/net/wireless/ipw2x00/libipw_rx.c
@@ -1120,7 +1120,6 @@ static int libipw_parse_info_param(struct libipw_info_element
 				      *info_element, u16 length,
 				      struct libipw_network *network)
 {
-	DECLARE_SSID_BUF(ssid);
 	u8 i;
 #ifdef CONFIG_LIBIPW_DEBUG
 	char rates_str[64];
@@ -1151,10 +1150,9 @@ static int libipw_parse_info_param(struct libipw_info_element
 				memset(network->ssid + network->ssid_len, 0,
 				       IW_ESSID_MAX_SIZE - network->ssid_len);
 
-			LIBIPW_DEBUG_MGMT("WLAN_EID_SSID: '%s' len=%d.\n",
-					     print_ssid(ssid, network->ssid,
-							network->ssid_len),
-					     network->ssid_len);
+			LIBIPW_DEBUG_MGMT("WLAN_EID_SSID: '%*pE' len=%d.\n",
+					  network->ssid_len, network->ssid,
+					  network->ssid_len);
 			break;
 
 		case WLAN_EID_SUPP_RATES:
@@ -1399,8 +1397,6 @@ static int libipw_network_init(struct libipw_device *ieee, struct libipw_probe_r
 					 struct libipw_network *network,
 					 struct libipw_rx_stats *stats)
 {
-	DECLARE_SSID_BUF(ssid);
-
 	network->qos_data.active = 0;
 	network->qos_data.supported = 0;
 	network->qos_data.param_count = 0;
@@ -1447,11 +1443,9 @@ static int libipw_network_init(struct libipw_device *ieee, struct libipw_probe_r
 	}
 
 	if (network->mode == 0) {
-		LIBIPW_DEBUG_SCAN("Filtered out '%s (%pM)' "
-				     "network.\n",
-				     print_ssid(ssid, network->ssid,
-						 network->ssid_len),
-				     network->bssid);
+		LIBIPW_DEBUG_SCAN("Filtered out '%*pE (%pM)' network.\n",
+				  network->ssid_len, network->ssid,
+				  network->bssid);
 		return 1;
 	}
 
@@ -1563,11 +1557,9 @@ static void libipw_process_probe_response(struct libipw_device
 	struct libipw_info_element *info_element = beacon->info_element;
 #endif
 	unsigned long flags;
-	DECLARE_SSID_BUF(ssid);
 
-	LIBIPW_DEBUG_SCAN("'%s' (%pM"
-		     "): %c%c%c%c %c%c%c%c-%c%c%c%c %c%c%c%c\n",
-		     print_ssid(ssid, info_element->data, info_element->len),
+	LIBIPW_DEBUG_SCAN("'%*pE' (%pM): %c%c%c%c %c%c%c%c-%c%c%c%c %c%c%c%c\n",
+		     info_element->len, info_element->data,
 		     beacon->header.addr3,
 		     (beacon->capability & cpu_to_le16(1 << 0xf)) ? '1' : '0',
 		     (beacon->capability & cpu_to_le16(1 << 0xe)) ? '1' : '0',
@@ -1587,12 +1579,11 @@ static void libipw_process_probe_response(struct libipw_device
 		     (beacon->capability & cpu_to_le16(1 << 0x0)) ? '1' : '0');
 
 	if (libipw_network_init(ieee, beacon, &network, stats)) {
-		LIBIPW_DEBUG_SCAN("Dropped '%s' (%pM) via %s.\n",
-				     print_ssid(ssid, info_element->data,
-						 info_element->len),
-				     beacon->header.addr3,
-				     is_beacon(beacon->header.frame_ctl) ?
-				     "BEACON" : "PROBE RESPONSE");
+		LIBIPW_DEBUG_SCAN("Dropped '%*pE' (%pM) via %s.\n",
+				  info_element->len, info_element->data,
+				  beacon->header.addr3,
+				  is_beacon(beacon->header.frame_ctl) ?
+				  "BEACON" : "PROBE RESPONSE");
 		return;
 	}
 
@@ -1624,11 +1615,9 @@ static void libipw_process_probe_response(struct libipw_device
 			/* If there are no more slots, expire the oldest */
 			list_del(&oldest->list);
 			target = oldest;
-			LIBIPW_DEBUG_SCAN("Expired '%s' (%pM) from "
-					     "network list.\n",
-					     print_ssid(ssid, target->ssid,
-							 target->ssid_len),
-					     target->bssid);
+			LIBIPW_DEBUG_SCAN("Expired '%*pE' (%pM) from network list.\n",
+					  target->ssid_len, target->ssid,
+					  target->bssid);
 			libipw_network_reset(target);
 		} else {
 			/* Otherwise just pull from the free list */
@@ -1638,23 +1627,21 @@ static void libipw_process_probe_response(struct libipw_device
 		}
 
 #ifdef CONFIG_LIBIPW_DEBUG
-		LIBIPW_DEBUG_SCAN("Adding '%s' (%pM) via %s.\n",
-				     print_ssid(ssid, network.ssid,
-						 network.ssid_len),
-				     network.bssid,
-				     is_beacon(beacon->header.frame_ctl) ?
-				     "BEACON" : "PROBE RESPONSE");
+		LIBIPW_DEBUG_SCAN("Adding '%*pE' (%pM) via %s.\n",
+				  network.ssid_len, network.ssid,
+				  network.bssid,
+				  is_beacon(beacon->header.frame_ctl) ?
+				  "BEACON" : "PROBE RESPONSE");
 #endif
 		memcpy(target, &network, sizeof(*target));
 		network.ibss_dfs = NULL;
 		list_add_tail(&target->list, &ieee->network_list);
 	} else {
-		LIBIPW_DEBUG_SCAN("Updating '%s' (%pM) via %s.\n",
-				     print_ssid(ssid, target->ssid,
-						 target->ssid_len),
-				     target->bssid,
-				     is_beacon(beacon->header.frame_ctl) ?
-				     "BEACON" : "PROBE RESPONSE");
+		LIBIPW_DEBUG_SCAN("Updating '%*pE' (%pM) via %s.\n",
+				  target->ssid_len, target->ssid,
+				  target->bssid,
+				  is_beacon(beacon->header.frame_ctl) ?
+				  "BEACON" : "PROBE RESPONSE");
 		update_network(target, &network);
 		network.ibss_dfs = NULL;
 	}
diff --git a/drivers/net/wireless/ipw2x00/libipw_wx.c b/drivers/net/wireless/ipw2x00/libipw_wx.c
index 54aba4744438..dd29f46d086b 100644
--- a/drivers/net/wireless/ipw2x00/libipw_wx.c
+++ b/drivers/net/wireless/ipw2x00/libipw_wx.c
@@ -272,7 +272,6 @@ int libipw_wx_get_scan(struct libipw_device *ieee,
 	char *ev = extra;
 	char *stop = ev + wrqu->data.length;
 	int i = 0;
-	DECLARE_SSID_BUF(ssid);
 
 	LIBIPW_DEBUG_WX("Getting scan\n");
 
@@ -290,12 +289,10 @@ int libipw_wx_get_scan(struct libipw_device *ieee,
 			ev = libipw_translate_scan(ieee, ev, stop, network,
 						      info);
 		else {
-			LIBIPW_DEBUG_SCAN("Not showing network '%s ("
-					     "%pM)' due to age (%ums).\n",
-					     print_ssid(ssid, network->ssid,
-							 network->ssid_len),
-					     network->bssid,
-					     elapsed_jiffies_msecs(
+			LIBIPW_DEBUG_SCAN("Not showing network '%*pE (%pM)' due to age (%ums).\n",
+					  network->ssid_len, network->ssid,
+					  network->bssid,
+					  elapsed_jiffies_msecs(
 					               network->last_scanned));
 		}
 	}
@@ -322,7 +319,6 @@ int libipw_wx_set_encode(struct libipw_device *ieee,
 	int i, key, key_provided, len;
 	struct lib80211_crypt_data **crypt;
 	int host_crypto = ieee->host_encrypt || ieee->host_decrypt;
-	DECLARE_SSID_BUF(ssid);
 
 	LIBIPW_DEBUG_WX("SET_ENCODE\n");
 
@@ -417,8 +413,8 @@ int libipw_wx_set_encode(struct libipw_device *ieee,
 		if (len > erq->length)
 			memset(sec.keys[key] + erq->length, 0,
 			       len - erq->length);
-		LIBIPW_DEBUG_WX("Setting key %d to '%s' (%d:%d bytes)\n",
-				   key, print_ssid(ssid, sec.keys[key], len),
+		LIBIPW_DEBUG_WX("Setting key %d to '%*pE' (%d:%d bytes)\n",
+				   key, len, sec.keys[key],
 				   erq->length, len);
 		sec.key_sizes[key] = len;
 		if (*crypt)
diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c
index 818b1edaaa9a..34f09ef90bb3 100644
--- a/drivers/net/wireless/libertas/cfg.c
+++ b/drivers/net/wireless/libertas/cfg.c
@@ -590,7 +590,6 @@ static int lbs_ret_scan(struct lbs_private *priv, unsigned long dummy,
 		int chan_no = -1;
 		const u8 *ssid = NULL;
 		u8 ssid_len = 0;
-		DECLARE_SSID_BUF(ssid_buf);
 
 		int len = get_unaligned_le16(pos);
 		pos += 2;
@@ -644,10 +643,8 @@ static int lbs_ret_scan(struct lbs_private *priv, unsigned long dummy,
 			struct ieee80211_channel *channel =
 				ieee80211_get_channel(wiphy, freq);
 
-			lbs_deb_scan("scan: %pM, capa %04x, chan %2d, %s, "
-				     "%d dBm\n",
-				     bssid, capa, chan_no,
-				     print_ssid(ssid_buf, ssid, ssid_len),
+			lbs_deb_scan("scan: %pM, capa %04x, chan %2d, %*pE, %d dBm\n",
+				     bssid, capa, chan_no, ssid_len, ssid,
 				     LBS_SCAN_RSSI_TO_MBM(rssi)/100);
 
 			if (channel &&
@@ -1984,7 +1981,6 @@ static int lbs_join_ibss(struct wiphy *wiphy, struct net_device *dev,
 	struct lbs_private *priv = wiphy_priv(wiphy);
 	int ret = 0;
 	struct cfg80211_bss *bss;
-	DECLARE_SSID_BUF(ssid_buf);
 
 	if (dev == priv->mesh_dev)
 		return -EOPNOTSUPP;
diff --git a/drivers/net/wireless/libertas/mesh.c b/drivers/net/wireless/libertas/mesh.c
index 01a67f62696f..d0c881dd5846 100644
--- a/drivers/net/wireless/libertas/mesh.c
+++ b/drivers/net/wireless/libertas/mesh.c
@@ -93,7 +93,6 @@ static int lbs_mesh_config(struct lbs_private *priv, uint16_t action,
 {
 	struct cmd_ds_mesh_config cmd;
 	struct mrvl_meshie *ie;
-	DECLARE_SSID_BUF(ssid);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.channel = cpu_to_le16(chan);
@@ -122,9 +121,9 @@ static int lbs_mesh_config(struct lbs_private *priv, uint16_t action,
 	default:
 		return -1;
 	}
-	lbs_deb_cmd("mesh config action %d type %x channel %d SSID %s\n",
-		    action, priv->mesh_tlv, chan,
-		    print_ssid(ssid, priv->mesh_ssid, priv->mesh_ssid_len));
+	lbs_deb_cmd("mesh config action %d type %x channel %d SSID %*pE\n",
+		    action, priv->mesh_tlv, chan, priv->mesh_ssid_len,
+		    priv->mesh_ssid);
 
 	return __lbs_mesh_config_send(priv, &cmd, action, priv->mesh_tlv);
 }
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 9c47b897b6d2..8079c31ac5e6 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -937,22 +937,18 @@ static int read_xenbus_vif_flags(struct backend_info *be)
 	return 0;
 }
 
-
-/* ** Driver Registration ** */
-
-
 static const struct xenbus_device_id netback_ids[] = {
 	{ "vif" },
 	{ "" }
 };
 
-
-static DEFINE_XENBUS_DRIVER(netback, ,
+static struct xenbus_driver netback_driver = {
+	.ids = netback_ids,
 	.probe = netback_probe,
 	.remove = netback_remove,
 	.uevent = netback_uevent,
 	.otherend_changed = frontend_changed,
-);
+};
 
 int xenvif_xenbus_init(void)
 {
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 3c0b37574d05..cca871346a0f 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -2300,12 +2300,6 @@ static void xennet_sysfs_delif(struct net_device *netdev)
 
 #endif /* CONFIG_SYSFS */
 
-static const struct xenbus_device_id netfront_ids[] = {
-	{ "vif" },
-	{ "" }
-};
-
-
 static int xennet_remove(struct xenbus_device *dev)
 {
 	struct netfront_info *info = dev_get_drvdata(&dev->dev);
@@ -2338,12 +2332,18 @@ static int xennet_remove(struct xenbus_device *dev)
 	return 0;
 }
 
-static DEFINE_XENBUS_DRIVER(netfront, ,
+static const struct xenbus_device_id netfront_ids[] = {
+	{ "vif" },
+	{ "" }
+};
+
+static struct xenbus_driver netfront_driver = {
+	.ids = netfront_ids,
 	.probe = netfront_probe,
 	.remove = xennet_remove,
 	.resume = netfront_resume,
 	.otherend_changed = netback_changed,
-);
+};
 
 static int __init netif_init(void)
 {
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 5160c4eb73c2..1a13f5b722c5 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -11,6 +11,7 @@ config OF_SELFTEST
 	bool "Device Tree Runtime self tests"
 	depends on OF_IRQ && OF_EARLY_FLATTREE
 	select OF_DYNAMIC
+	select OF_RESOLVE
 	help
 	  This option builds in test cases for the device tree infrastructure
 	  that are executed once at boot time, and the results dumped to the
@@ -79,4 +80,7 @@ config OF_RESERVED_MEM
 	help
 	  Helpers to allow for reservation of memory regions
 
+config OF_RESOLVE
+	bool
+
 endmenu # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index 2b6a7b129d10..ca9209ce50cd 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_OF_PCI)	+= of_pci.o
 obj-$(CONFIG_OF_PCI_IRQ)  += of_pci_irq.o
 obj-$(CONFIG_OF_MTD)	+= of_mtd.o
 obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
+obj-$(CONFIG_OF_RESOLVE)  += resolver.o
 
 CFLAGS_fdt.o = -I$(src)/../../scripts/dtc/libfdt
 CFLAGS_fdt_address.o = -I$(src)/../../scripts/dtc/libfdt
diff --git a/drivers/of/address.c b/drivers/of/address.c
index e3718250d66e..afdb78299f61 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -5,6 +5,8 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/pci_regs.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 
 /* Max address size we deal with */
@@ -293,6 +295,51 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser,
 }
 EXPORT_SYMBOL_GPL(of_pci_range_parser_one);
 
+/*
+ * of_pci_range_to_resource - Create a resource from an of_pci_range
+ * @range:	the PCI range that describes the resource
+ * @np:		device node where the range belongs to
+ * @res:	pointer to a valid resource that will be updated to
+ *              reflect the values contained in the range.
+ *
+ * Returns EINVAL if the range cannot be converted to resource.
+ *
+ * Note that if the range is an IO range, the resource will be converted
+ * using pci_address_to_pio() which can fail if it is called too early or
+ * if the range cannot be matched to any host bridge IO space (our case here).
+ * To guard against that we try to register the IO range first.
+ * If that fails we know that pci_address_to_pio() will do too.
+ */
+int of_pci_range_to_resource(struct of_pci_range *range,
+			     struct device_node *np, struct resource *res)
+{
+	int err;
+	res->flags = range->flags;
+	res->parent = res->child = res->sibling = NULL;
+	res->name = np->full_name;
+
+	if (res->flags & IORESOURCE_IO) {
+		unsigned long port;
+		err = pci_register_io_range(range->cpu_addr, range->size);
+		if (err)
+			goto invalid_range;
+		port = pci_address_to_pio(range->cpu_addr);
+		if (port == (unsigned long)-1) {
+			err = -EINVAL;
+			goto invalid_range;
+		}
+		res->start = port;
+	} else {
+		res->start = range->cpu_addr;
+	}
+	res->end = res->start + range->size - 1;
+	return 0;
+
+invalid_range:
+	res->start = (resource_size_t)OF_BAD_ADDR;
+	res->end = (resource_size_t)OF_BAD_ADDR;
+	return err;
+}
 #endif /* CONFIG_PCI */
 
 /*
@@ -601,12 +648,119 @@ const __be32 *of_get_address(struct device_node *dev, int index, u64 *size,
 }
 EXPORT_SYMBOL(of_get_address);
 
+#ifdef PCI_IOBASE
+struct io_range {
+	struct list_head list;
+	phys_addr_t start;
+	resource_size_t size;
+};
+
+static LIST_HEAD(io_range_list);
+static DEFINE_SPINLOCK(io_range_lock);
+#endif
+
+/*
+ * Record the PCI IO range (expressed as CPU physical address + size).
+ * Return a negative value if an error has occured, zero otherwise
+ */
+int __weak pci_register_io_range(phys_addr_t addr, resource_size_t size)
+{
+	int err = 0;
+
+#ifdef PCI_IOBASE
+	struct io_range *range;
+	resource_size_t allocated_size = 0;
+
+	/* check if the range hasn't been previously recorded */
+	spin_lock(&io_range_lock);
+	list_for_each_entry(range, &io_range_list, list) {
+		if (addr >= range->start && addr + size <= range->start + size) {
+			/* range already registered, bail out */
+			goto end_register;
+		}
+		allocated_size += range->size;
+	}
+
+	/* range not registed yet, check for available space */
+	if (allocated_size + size - 1 > IO_SPACE_LIMIT) {
+		/* if it's too big check if 64K space can be reserved */
+		if (allocated_size + SZ_64K - 1 > IO_SPACE_LIMIT) {
+			err = -E2BIG;
+			goto end_register;
+		}
+
+		size = SZ_64K;
+		pr_warn("Requested IO range too big, new size set to 64K\n");
+	}
+
+	/* add the range to the list */
+	range = kzalloc(sizeof(*range), GFP_KERNEL);
+	if (!range) {
+		err = -ENOMEM;
+		goto end_register;
+	}
+
+	range->start = addr;
+	range->size = size;
+
+	list_add_tail(&range->list, &io_range_list);
+
+end_register:
+	spin_unlock(&io_range_lock);
+#endif
+
+	return err;
+}
+
+phys_addr_t pci_pio_to_address(unsigned long pio)
+{
+	phys_addr_t address = (phys_addr_t)OF_BAD_ADDR;
+
+#ifdef PCI_IOBASE
+	struct io_range *range;
+	resource_size_t allocated_size = 0;
+
+	if (pio > IO_SPACE_LIMIT)
+		return address;
+
+	spin_lock(&io_range_lock);
+	list_for_each_entry(range, &io_range_list, list) {
+		if (pio >= allocated_size && pio < allocated_size + range->size) {
+			address = range->start + pio - allocated_size;
+			break;
+		}
+		allocated_size += range->size;
+	}
+	spin_unlock(&io_range_lock);
+#endif
+
+	return address;
+}
+
 unsigned long __weak pci_address_to_pio(phys_addr_t address)
 {
+#ifdef PCI_IOBASE
+	struct io_range *res;
+	resource_size_t offset = 0;
+	unsigned long addr = -1;
+
+	spin_lock(&io_range_lock);
+	list_for_each_entry(res, &io_range_list, list) {
+		if (address >= res->start && address < res->start + res->size) {
+			addr = res->start - address + offset;
+			break;
+		}
+		offset += res->size;
+	}
+	spin_unlock(&io_range_lock);
+
+	return addr;
+#else
 	if (address > IO_SPACE_LIMIT)
 		return (unsigned long)-1;
 
 	return (unsigned long) address;
+#endif
 }
 
 static int __of_address_to_resource(struct device_node *dev,
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 293ed4b687ba..2305dc0382bc 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1021,6 +1021,9 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 	struct device_node *np;
 	unsigned long flags;
 
+	if (!handle)
+		return NULL;
+
 	raw_spin_lock_irqsave(&devtree_lock, flags);
 	for (np = of_allnodes; np; np = np->allnext)
 		if (np->phandle == handle)
diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c
index 848199633798..8882b467be95 100644
--- a/drivers/of/of_pci.c
+++ b/drivers/of/of_pci.c
@@ -1,7 +1,9 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_pci.h>
+#include <linux/slab.h>
 
 static inline int __of_pci_pci_compare(struct device_node *node,
 				       unsigned int data)
@@ -89,6 +91,146 @@ int of_pci_parse_bus_range(struct device_node *node, struct resource *res)
 }
 EXPORT_SYMBOL_GPL(of_pci_parse_bus_range);
 
+/**
+ * This function will try to obtain the host bridge domain number by
+ * finding a property called "linux,pci-domain" of the given device node.
+ *
+ * @node: device tree node with the domain information
+ *
+ * Returns the associated domain number from DT in the range [0-0xffff], or
+ * a negative value if the required property is not found.
+ */
+int of_get_pci_domain_nr(struct device_node *node)
+{
+	const __be32 *value;
+	int len;
+	u16 domain;
+
+	value = of_get_property(node, "linux,pci-domain", &len);
+	if (!value || len < sizeof(*value))
+		return -EINVAL;
+
+	domain = (u16)be32_to_cpup(value);
+
+	return domain;
+}
+EXPORT_SYMBOL_GPL(of_get_pci_domain_nr);
+
+#if defined(CONFIG_OF_ADDRESS)
+/**
+ * of_pci_get_host_bridge_resources - Parse PCI host bridge resources from DT
+ * @dev: device node of the host bridge having the range property
+ * @busno: bus number associated with the bridge root bus
+ * @bus_max: maximum number of buses for this bridge
+ * @resources: list where the range of resources will be added after DT parsing
+ * @io_base: pointer to a variable that will contain on return the physical
+ * address for the start of the I/O range. Can be NULL if the caller doesn't
+ * expect IO ranges to be present in the device tree.
+ *
+ * It is the caller's job to free the @resources list.
+ *
+ * This function will parse the "ranges" property of a PCI host bridge device
+ * node and setup the resource mapping based on its content. It is expected
+ * that the property conforms with the Power ePAPR document.
+ *
+ * It returns zero if the range parsing has been successful or a standard error
+ * value if it failed.
+ */
+int of_pci_get_host_bridge_resources(struct device_node *dev,
+			unsigned char busno, unsigned char bus_max,
+			struct list_head *resources, resource_size_t *io_base)
+{
+	struct resource *res;
+	struct resource *bus_range;
+	struct of_pci_range range;
+	struct of_pci_range_parser parser;
+	char range_type[4];
+	int err;
+
+	if (io_base)
+		*io_base = (resource_size_t)OF_BAD_ADDR;
+
+	bus_range = kzalloc(sizeof(*bus_range), GFP_KERNEL);
+	if (!bus_range)
+		return -ENOMEM;
+
+	pr_info("PCI host bridge %s ranges:\n", dev->full_name);
+
+	err = of_pci_parse_bus_range(dev, bus_range);
+	if (err) {
+		bus_range->start = busno;
+		bus_range->end = bus_max;
+		bus_range->flags = IORESOURCE_BUS;
+		pr_info("  No bus range found for %s, using %pR\n",
+			dev->full_name, bus_range);
+	} else {
+		if (bus_range->end > bus_range->start + bus_max)
+			bus_range->end = bus_range->start + bus_max;
+	}
+	pci_add_resource(resources, bus_range);
+
+	/* Check for ranges property */
+	err = of_pci_range_parser_init(&parser, dev);
+	if (err)
+		goto parse_failed;
+
+	pr_debug("Parsing ranges property...\n");
+	for_each_of_pci_range(&parser, &range) {
+		/* Read next ranges element */
+		if ((range.flags & IORESOURCE_TYPE_BITS) == IORESOURCE_IO)
+			snprintf(range_type, 4, " IO");
+		else if ((range.flags & IORESOURCE_TYPE_BITS) == IORESOURCE_MEM)
+			snprintf(range_type, 4, "MEM");
+		else
+			snprintf(range_type, 4, "err");
+		pr_info("  %s %#010llx..%#010llx -> %#010llx\n", range_type,
+			range.cpu_addr, range.cpu_addr + range.size - 1,
+			range.pci_addr);
+
+		/*
+		 * If we failed translation or got a zero-sized region
+		 * then skip this range
+		 */
+		if (range.cpu_addr == OF_BAD_ADDR || range.size == 0)
+			continue;
+
+		res = kzalloc(sizeof(struct resource), GFP_KERNEL);
+		if (!res) {
+			err = -ENOMEM;
+			goto parse_failed;
+		}
+
+		err = of_pci_range_to_resource(&range, dev, res);
+		if (err)
+			goto conversion_failed;
+
+		if (resource_type(res) == IORESOURCE_IO) {
+			if (!io_base) {
+				pr_err("I/O range found for %s. Please provide an io_base pointer to save CPU base address\n",
+					dev->full_name);
+				err = -EINVAL;
+				goto conversion_failed;
+			}
+			if (*io_base != (resource_size_t)OF_BAD_ADDR)
+				pr_warn("More than one I/O resource converted for %s. CPU base address for old range lost!\n",
+					dev->full_name);
+			*io_base = range.cpu_addr;
+		}
+
+		pci_add_resource_offset(resources, res,	res->start - range.pci_addr);
+	}
+
+	return 0;
+
+conversion_failed:
+	kfree(res);
+parse_failed:
+	pci_free_resource_list(resources);
+	return err;
+}
+EXPORT_SYMBOL_GPL(of_pci_get_host_bridge_resources);
+#endif /* CONFIG_OF_ADDRESS */
+
 #ifdef CONFIG_PCI_MSI
 
 static LIST_HEAD(of_pci_msi_chip_list);
diff --git a/drivers/of/resolver.c b/drivers/of/resolver.c
new file mode 100644
index 000000000000..aed7959f800d
--- /dev/null
+++ b/drivers/of/resolver.c
@@ -0,0 +1,336 @@
+/*
+ * Functions for dealing with DT resolution
+ *
+ * Copyright (C) 2012 Pantelis Antoniou <panto@antoniou-consulting.com>
+ * Copyright (C) 2012 Texas Instruments Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+
+/* illegal phandle value (set when unresolved) */
+#define OF_PHANDLE_ILLEGAL	0xdeadbeef
+
+/**
+ * Find a node with the give full name by recursively following any of
+ * the child node links.
+ */
+static struct device_node *__of_find_node_by_full_name(struct device_node *node,
+		const char *full_name)
+{
+	struct device_node *child, *found;
+
+	if (node == NULL)
+		return NULL;
+
+	/* check */
+	if (of_node_cmp(node->full_name, full_name) == 0)
+		return node;
+
+	for_each_child_of_node(node, child) {
+		found = __of_find_node_by_full_name(child, full_name);
+		if (found != NULL)
+			return found;
+	}
+
+	return NULL;
+}
+
+/*
+ * Find live tree's maximum phandle value.
+ */
+static phandle of_get_tree_max_phandle(void)
+{
+	struct device_node *node;
+	phandle phandle;
+	unsigned long flags;
+
+	/* now search recursively */
+	raw_spin_lock_irqsave(&devtree_lock, flags);
+	phandle = 0;
+	for_each_of_allnodes(node) {
+		if (node->phandle != OF_PHANDLE_ILLEGAL &&
+				node->phandle > phandle)
+			phandle = node->phandle;
+	}
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
+	return phandle;
+}
+
+/*
+ * Adjust a subtree's phandle values by a given delta.
+ * Makes sure not to just adjust the device node's phandle value,
+ * but modify the phandle properties values as well.
+ */
+static void __of_adjust_tree_phandles(struct device_node *node,
+		int phandle_delta)
+{
+	struct device_node *child;
+	struct property *prop;
+	phandle phandle;
+
+	/* first adjust the node's phandle direct value */
+	if (node->phandle != 0 && node->phandle != OF_PHANDLE_ILLEGAL)
+		node->phandle += phandle_delta;
+
+	/* now adjust phandle & linux,phandle values */
+	for_each_property_of_node(node, prop) {
+
+		/* only look for these two */
+		if (of_prop_cmp(prop->name, "phandle") != 0 &&
+		    of_prop_cmp(prop->name, "linux,phandle") != 0)
+			continue;
+
+		/* must be big enough */
+		if (prop->length < 4)
+			continue;
+
+		/* read phandle value */
+		phandle = be32_to_cpup(prop->value);
+		if (phandle == OF_PHANDLE_ILLEGAL)	/* unresolved */
+			continue;
+
+		/* adjust */
+		*(uint32_t *)prop->value = cpu_to_be32(node->phandle);
+	}
+
+	/* now do the children recursively */
+	for_each_child_of_node(node, child)
+		__of_adjust_tree_phandles(child, phandle_delta);
+}
+
+static int __of_adjust_phandle_ref(struct device_node *node, struct property *rprop, int value, bool is_delta)
+{
+	phandle phandle;
+	struct device_node *refnode;
+	struct property *sprop;
+	char *propval, *propcur, *propend, *nodestr, *propstr, *s;
+	int offset, propcurlen;
+	int err = 0;
+
+	/* make a copy */
+	propval = kmalloc(rprop->length, GFP_KERNEL);
+	if (!propval) {
+		pr_err("%s: Could not copy value of '%s'\n",
+				__func__, rprop->name);
+		return -ENOMEM;
+	}
+	memcpy(propval, rprop->value, rprop->length);
+
+	propend = propval + rprop->length;
+	for (propcur = propval; propcur < propend; propcur += propcurlen + 1) {
+		propcurlen = strlen(propcur);
+
+		nodestr = propcur;
+		s = strchr(propcur, ':');
+		if (!s) {
+			pr_err("%s: Illegal symbol entry '%s' (1)\n",
+				__func__, propcur);
+			err = -EINVAL;
+			goto err_fail;
+		}
+		*s++ = '\0';
+
+		propstr = s;
+		s = strchr(s, ':');
+		if (!s) {
+			pr_err("%s: Illegal symbol entry '%s' (2)\n",
+				__func__, (char *)rprop->value);
+			err = -EINVAL;
+			goto err_fail;
+		}
+
+		*s++ = '\0';
+		err = kstrtoint(s, 10, &offset);
+		if (err != 0) {
+			pr_err("%s: Could get offset '%s'\n",
+				__func__, (char *)rprop->value);
+			goto err_fail;
+		}
+
+		/* look into the resolve node for the full path */
+		refnode = __of_find_node_by_full_name(node, nodestr);
+		if (!refnode) {
+			pr_warn("%s: Could not find refnode '%s'\n",
+				__func__, (char *)rprop->value);
+			continue;
+		}
+
+		/* now find the property */
+		for_each_property_of_node(refnode, sprop) {
+			if (of_prop_cmp(sprop->name, propstr) == 0)
+				break;
+		}
+
+		if (!sprop) {
+			pr_err("%s: Could not find property '%s'\n",
+				__func__, (char *)rprop->value);
+			err = -ENOENT;
+			goto err_fail;
+		}
+
+		phandle = is_delta ? be32_to_cpup(sprop->value + offset) + value : value;
+		*(__be32 *)(sprop->value + offset) = cpu_to_be32(phandle);
+	}
+
+err_fail:
+	kfree(propval);
+	return err;
+}
+
+/*
+ * Adjust the local phandle references by the given phandle delta.
+ * Assumes the existances of a __local_fixups__ node at the root
+ * of the tree. Does not take any devtree locks so make sure you
+ * call this on a tree which is at the detached state.
+ */
+static int __of_adjust_tree_phandle_references(struct device_node *node,
+		int phandle_delta)
+{
+	struct device_node *child;
+	struct property *rprop;
+	int err;
+
+	/* locate the symbols & fixups nodes on resolve */
+	for_each_child_of_node(node, child)
+		if (of_node_cmp(child->name, "__local_fixups__") == 0)
+			break;
+
+	/* no local fixups */
+	if (!child)
+		return 0;
+
+	/* find the local fixups property */
+	for_each_property_of_node(child, rprop) {
+		/* skip properties added automatically */
+		if (of_prop_cmp(rprop->name, "name") == 0)
+			continue;
+
+		err = __of_adjust_phandle_ref(node, rprop, phandle_delta, true);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * of_resolve	- Resolve the given node against the live tree.
+ *
+ * @resolve:	Node to resolve
+ *
+ * Perform dynamic Device Tree resolution against the live tree
+ * to the given node to resolve. This depends on the live tree
+ * having a __symbols__ node, and the resolve node the __fixups__ &
+ * __local_fixups__ nodes (if needed).
+ * The result of the operation is a resolve node that it's contents
+ * are fit to be inserted or operate upon the live tree.
+ * Returns 0 on success or a negative error value on error.
+ */
+int of_resolve_phandles(struct device_node *resolve)
+{
+	struct device_node *child, *refnode;
+	struct device_node *root_sym, *resolve_sym, *resolve_fix;
+	struct property *rprop;
+	const char *refpath;
+	phandle phandle, phandle_delta;
+	int err;
+
+	/* the resolve node must exist, and be detached */
+	if (!resolve || !of_node_check_flag(resolve, OF_DETACHED))
+		return -EINVAL;
+
+	/* first we need to adjust the phandles */
+	phandle_delta = of_get_tree_max_phandle() + 1;
+	__of_adjust_tree_phandles(resolve, phandle_delta);
+	err = __of_adjust_tree_phandle_references(resolve, phandle_delta);
+	if (err != 0)
+		return err;
+
+	root_sym = NULL;
+	resolve_sym = NULL;
+	resolve_fix = NULL;
+
+	/* this may fail (if no fixups are required) */
+	root_sym = of_find_node_by_path("/__symbols__");
+
+	/* locate the symbols & fixups nodes on resolve */
+	for_each_child_of_node(resolve, child) {
+
+		if (!resolve_sym &&
+				of_node_cmp(child->name, "__symbols__") == 0)
+			resolve_sym = child;
+
+		if (!resolve_fix &&
+				of_node_cmp(child->name, "__fixups__") == 0)
+			resolve_fix = child;
+
+		/* both found, don't bother anymore */
+		if (resolve_sym && resolve_fix)
+			break;
+	}
+
+	/* we do allow for the case where no fixups are needed */
+	if (!resolve_fix) {
+		err = 0;	/* no error */
+		goto out;
+	}
+
+	/* we need to fixup, but no root symbols... */
+	if (!root_sym) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	for_each_property_of_node(resolve_fix, rprop) {
+
+		/* skip properties added automatically */
+		if (of_prop_cmp(rprop->name, "name") == 0)
+			continue;
+
+		err = of_property_read_string(root_sym,
+				rprop->name, &refpath);
+		if (err != 0) {
+			pr_err("%s: Could not find symbol '%s'\n",
+					__func__, rprop->name);
+			goto out;
+		}
+
+		refnode = of_find_node_by_path(refpath);
+		if (!refnode) {
+			pr_err("%s: Could not find node by path '%s'\n",
+					__func__, refpath);
+			err = -ENOENT;
+			goto out;
+		}
+
+		phandle = refnode->phandle;
+		of_node_put(refnode);
+
+		pr_debug("%s: %s phandle is 0x%08x\n",
+				__func__, rprop->name, phandle);
+
+		err = __of_adjust_phandle_ref(resolve, rprop, phandle, false);
+		if (err)
+			break;
+	}
+
+out:
+	/* NULL is handled by of_node_put as NOP */
+	of_node_put(root_sym);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(of_resolve_phandles);
diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c
index a737cb5974de..78001270a598 100644
--- a/drivers/of/selftest.c
+++ b/drivers/of/selftest.c
@@ -7,6 +7,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/errno.h>
+#include <linux/hashtable.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
@@ -24,7 +25,7 @@ static struct selftest_results {
 	int failed;
 } selftest_results;
 
-#define NO_OF_NODES 2
+#define NO_OF_NODES 3
 static struct device_node *nodes[NO_OF_NODES];
 static int last_node_index;
 static bool selftest_live_tree;
@@ -145,6 +146,97 @@ static void __init of_selftest_dynamic(void)
 			 "Adding a large property should have passed\n");
 }
 
+static int __init of_selftest_check_node_linkage(struct device_node *np)
+{
+	struct device_node *child, *allnext_index = np;
+	int count = 0, rc;
+
+	for_each_child_of_node(np, child) {
+		if (child->parent != np) {
+			pr_err("Child node %s links to wrong parent %s\n",
+				 child->name, np->name);
+			return -EINVAL;
+		}
+
+		while (allnext_index && allnext_index != child)
+			allnext_index = allnext_index->allnext;
+		if (allnext_index != child) {
+			pr_err("Node %s is ordered differently in sibling and allnode lists\n",
+				 child->name);
+			return -EINVAL;
+		}
+
+		rc = of_selftest_check_node_linkage(child);
+		if (rc < 0)
+			return rc;
+		count += rc;
+	}
+
+	return count + 1;
+}
+
+static void __init of_selftest_check_tree_linkage(void)
+{
+	struct device_node *np;
+	int allnode_count = 0, child_count;
+
+	if (!of_allnodes)
+		return;
+
+	for_each_of_allnodes(np)
+		allnode_count++;
+	child_count = of_selftest_check_node_linkage(of_allnodes);
+
+	selftest(child_count > 0, "Device node data structure is corrupted\n");
+	selftest(child_count == allnode_count, "allnodes list size (%i) doesn't match"
+		 "sibling lists size (%i)\n", allnode_count, child_count);
+	pr_debug("allnodes list size (%i); sibling lists size (%i)\n", allnode_count, child_count);
+}
+
+struct node_hash {
+	struct hlist_node node;
+	struct device_node *np;
+};
+
+static DEFINE_HASHTABLE(phandle_ht, 8);
+static void __init of_selftest_check_phandles(void)
+{
+	struct device_node *np;
+	struct node_hash *nh;
+	struct hlist_node *tmp;
+	int i, dup_count = 0, phandle_count = 0;
+
+	for_each_of_allnodes(np) {
+		if (!np->phandle)
+			continue;
+
+		hash_for_each_possible(phandle_ht, nh, node, np->phandle) {
+			if (nh->np->phandle == np->phandle) {
+				pr_info("Duplicate phandle! %i used by %s and %s\n",
+					np->phandle, nh->np->full_name, np->full_name);
+				dup_count++;
+				break;
+			}
+		}
+
+		nh = kzalloc(sizeof(*nh), GFP_KERNEL);
+		if (WARN_ON(!nh))
+			return;
+
+		nh->np = np;
+		hash_add(phandle_ht, &nh->node, np->phandle);
+		phandle_count++;
+	}
+	selftest(dup_count == 0, "Found %i duplicates in %i phandles\n",
+		 dup_count, phandle_count);
+
+	/* Clean up */
+	hash_for_each_safe(phandle_ht, i, tmp, nh, node) {
+		hash_del(&nh->node);
+		kfree(nh);
+	}
+}
+
 static void __init of_selftest_parse_phandle_with_args(void)
 {
 	struct device_node *np;
@@ -637,6 +729,8 @@ static int attach_node_and_children(struct device_node *np)
 	dup = np;
 
 	while (dup) {
+		if (WARN_ON(last_node_index >= NO_OF_NODES))
+			return -EINVAL;
 		nodes[last_node_index++] = dup;
 		dup = dup->sibling;
 	}
@@ -670,6 +764,7 @@ static int __init selftest_data_add(void)
 	extern uint8_t __dtb_testcases_begin[];
 	extern uint8_t __dtb_testcases_end[];
 	const int size = __dtb_testcases_end - __dtb_testcases_begin;
+	int rc;
 
 	if (!size) {
 		pr_warn("%s: No testcase data to attach; not running tests\n",
@@ -690,6 +785,12 @@ static int __init selftest_data_add(void)
 		pr_warn("%s: No tree to attach; not running tests\n", __func__);
 		return -ENODATA;
 	}
+	of_node_set_flag(selftest_data_node, OF_DETACHED);
+	rc = of_resolve_phandles(selftest_data_node);
+	if (rc) {
+		pr_err("%s: Failed to resolve phandles (rc=%i)\n", __func__, rc);
+		return -EINVAL;
+	}
 
 	if (!of_allnodes) {
 		/* enabling flag for removing nodes */
@@ -717,10 +818,6 @@ static void detach_node_and_children(struct device_node *np)
 {
 	while (np->child)
 		detach_node_and_children(np->child);
-
-	while (np->sibling)
-		detach_node_and_children(np->sibling);
-
 	of_detach_node(np);
 }
 
@@ -749,8 +846,7 @@ static void selftest_data_remove(void)
 		if (nodes[last_node_index]) {
 			np = of_find_node_by_path(nodes[last_node_index]->full_name);
 			if (strcmp(np->full_name, "/aliases") != 0) {
-				detach_node_and_children(np->child);
-				of_detach_node(np);
+				detach_node_and_children(np);
 			} else {
 				for_each_property_of_node(np, prop) {
 					if (strcmp(prop->name, "testcase-alias") == 0)
@@ -780,6 +876,8 @@ static int __init of_selftest(void)
 	of_node_put(np);
 
 	pr_info("start of selftest - you will see error messages\n");
+	of_selftest_check_tree_linkage();
+	of_selftest_check_phandles();
 	of_selftest_find_node_by_name();
 	of_selftest_dynamic();
 	of_selftest_parse_phandle_with_args();
@@ -790,12 +888,16 @@ static int __init of_selftest(void)
 	of_selftest_parse_interrupts_extended();
 	of_selftest_match_node();
 	of_selftest_platform_populate();
-	pr_info("end of selftest - %i passed, %i failed\n",
-		selftest_results.passed, selftest_results.failed);
 
 	/* removing selftest data from live tree */
 	selftest_data_remove();
 
+	/* Double check linkage after removing testcase data */
+	of_selftest_check_tree_linkage();
+
+	pr_info("end of selftest - %i passed, %i failed\n",
+		selftest_results.passed, selftest_results.failed);
+
 	return 0;
 }
 late_initcall(of_selftest);
diff --git a/drivers/of/testcase-data/testcases.dts b/drivers/of/testcase-data/testcases.dts
index 219ef9324e9c..6994e15c24bf 100644
--- a/drivers/of/testcase-data/testcases.dts
+++ b/drivers/of/testcase-data/testcases.dts
@@ -13,3 +13,38 @@
 #include "tests-interrupts.dtsi"
 #include "tests-match.dtsi"
 #include "tests-platform.dtsi"
+
+/*
+ * phandle fixup data - generated by dtc patches that aren't upstream.
+ * This data must be regenerated whenever phandle references are modified in
+ * the testdata tree.
+ *
+ * The format of this data may be subject to change. For the time being consider
+ * this a kernel-internal data format.
+ */
+/ { __local_fixups__ {
+	fixup = "/testcase-data/testcase-device2:interrupt-parent:0",
+		"/testcase-data/testcase-device1:interrupt-parent:0",
+		"/testcase-data/interrupts/interrupts-extended0:interrupts-extended:60",
+		"/testcase-data/interrupts/interrupts-extended0:interrupts-extended:52",
+		"/testcase-data/interrupts/interrupts-extended0:interrupts-extended:44",
+		"/testcase-data/interrupts/interrupts-extended0:interrupts-extended:36",
+		"/testcase-data/interrupts/interrupts-extended0:interrupts-extended:24",
+		"/testcase-data/interrupts/interrupts-extended0:interrupts-extended:8",
+		"/testcase-data/interrupts/interrupts-extended0:interrupts-extended:0",
+		"/testcase-data/interrupts/interrupts1:interrupt-parent:0",
+		"/testcase-data/interrupts/interrupts0:interrupt-parent:0",
+		"/testcase-data/interrupts/intmap1:interrupt-map:12",
+		"/testcase-data/interrupts/intmap0:interrupt-map:52",
+		"/testcase-data/interrupts/intmap0:interrupt-map:36",
+		"/testcase-data/interrupts/intmap0:interrupt-map:16",
+		"/testcase-data/interrupts/intmap0:interrupt-map:4",
+		"/testcase-data/phandle-tests/consumer-a:phandle-list-bad-args:12",
+		"/testcase-data/phandle-tests/consumer-a:phandle-list-bad-args:0",
+		"/testcase-data/phandle-tests/consumer-a:phandle-list:56",
+		"/testcase-data/phandle-tests/consumer-a:phandle-list:52",
+		"/testcase-data/phandle-tests/consumer-a:phandle-list:40",
+		"/testcase-data/phandle-tests/consumer-a:phandle-list:24",
+		"/testcase-data/phandle-tests/consumer-a:phandle-list:8",
+		"/testcase-data/phandle-tests/consumer-a:phandle-list:0";
+}; };
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index 8aa73fac6ad4..0581461c3a67 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -45,7 +45,7 @@ unsigned long oprofile_get_cpu_buffer_size(void)
 
 void oprofile_cpu_buffer_inc_smpl_lost(void)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 
 	cpu_buf->sample_lost_overflow++;
 }
@@ -297,7 +297,7 @@ __oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs,
 			  unsigned long event, int is_kernel,
 			  struct task_struct *task)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 	unsigned long backtrace = oprofile_backtrace_depth;
 
 	/*
@@ -357,7 +357,7 @@ oprofile_write_reserve(struct op_entry *entry, struct pt_regs * const regs,
 {
 	struct op_sample *sample;
 	int is_kernel = !user_mode(regs);
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 
 	cpu_buf->sample_received++;
 
@@ -412,13 +412,13 @@ int oprofile_write_commit(struct op_entry *entry)
 
 void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 	log_sample(cpu_buf, pc, 0, is_kernel, event, NULL);
 }
 
 void oprofile_add_trace(unsigned long pc)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 
 	if (!cpu_buf->tracing)
 		return;
diff --git a/drivers/oprofile/timer_int.c b/drivers/oprofile/timer_int.c
index 61be1d9c16c8..bdef916e5dda 100644
--- a/drivers/oprofile/timer_int.c
+++ b/drivers/oprofile/timer_int.c
@@ -32,7 +32,7 @@ static enum hrtimer_restart oprofile_hrtimer_notify(struct hrtimer *hrtimer)
 
 static void __oprofile_hrtimer_start(void *unused)
 {
-	struct hrtimer *hrtimer = &__get_cpu_var(oprofile_hrtimer);
+	struct hrtimer *hrtimer = this_cpu_ptr(&oprofile_hrtimer);
 
 	if (!ctr_running)
 		return;
diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c
index 90cca5e3805f..ef31b77404ef 100644
--- a/drivers/parisc/power.c
+++ b/drivers/parisc/power.c
@@ -121,7 +121,6 @@ static int kpowerswd(void *param)
 		unsigned long soft_power_reg = (unsigned long) param;
 
 		schedule_timeout_interruptible(pwrsw_enabled ? HZ : HZ/POWERSWITCH_POLL_PER_SEC);
-		__set_current_state(TASK_RUNNING);
 
 		if (unlikely(!pwrsw_enabled))
 			continue;
diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig
index 90f5ccacce4b..3dc25fad490c 100644
--- a/drivers/pci/host/Kconfig
+++ b/drivers/pci/host/Kconfig
@@ -63,4 +63,32 @@ config PCIE_SPEAR13XX
 	help
 	  Say Y here if you want PCIe support on SPEAr13XX SoCs.
 
+config PCI_KEYSTONE
+	bool "TI Keystone PCIe controller"
+	depends on ARCH_KEYSTONE
+	select PCIE_DW
+	select PCIEPORTBUS
+	help
+	  Say Y here if you want to enable PCI controller support on Keystone
+	  SoCs. The PCI controller on Keystone is based on Designware hardware
+	  and therefore the driver re-uses the Designware core functions to
+	  implement the driver.
+
+config PCIE_XILINX
+	bool "Xilinx AXI PCIe host bridge support"
+	depends on ARCH_ZYNQ
+	help
+	  Say 'Y' here if you want kernel to support the Xilinx AXI PCIe
+	  Host Bridge driver.
+
+config PCI_XGENE
+	bool "X-Gene PCIe controller"
+	depends on ARCH_XGENE
+	depends on OF
+	select PCIEPORTBUS
+	help
+	  Say Y here if you want internal PCI support on APM X-Gene SoC.
+	  There are 5 internal PCIe ports available. Each port is GEN3 capable
+	  and have varied lanes from x1 to x8.
+
 endmenu
diff --git a/drivers/pci/host/Makefile b/drivers/pci/host/Makefile
index d0e88f114ff9..26b3461d68d7 100644
--- a/drivers/pci/host/Makefile
+++ b/drivers/pci/host/Makefile
@@ -8,3 +8,6 @@ obj-$(CONFIG_PCI_RCAR_GEN2) += pci-rcar-gen2.o
 obj-$(CONFIG_PCI_RCAR_GEN2_PCIE) += pcie-rcar.o
 obj-$(CONFIG_PCI_HOST_GENERIC) += pci-host-generic.o
 obj-$(CONFIG_PCIE_SPEAR13XX) += pcie-spear13xx.o
+obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone-dw.o pci-keystone.o
+obj-$(CONFIG_PCIE_XILINX) += pcie-xilinx.o
+obj-$(CONFIG_PCI_XGENE) += pci-xgene.o
diff --git a/drivers/pci/host/pci-imx6.c b/drivers/pci/host/pci-imx6.c
index 35fc73a8d0b3..233fe8a88264 100644
--- a/drivers/pci/host/pci-imx6.c
+++ b/drivers/pci/host/pci-imx6.c
@@ -257,11 +257,6 @@ static int imx6_pcie_deassert_core_reset(struct pcie_port *pp)
 	struct imx6_pcie *imx6_pcie = to_imx6_pcie(pp);
 	int ret;
 
-	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
-			IMX6Q_GPR1_PCIE_TEST_PD, 0 << 18);
-	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
-			IMX6Q_GPR1_PCIE_REF_CLK_EN, 1 << 16);
-
 	ret = clk_prepare_enable(imx6_pcie->pcie_phy);
 	if (ret) {
 		dev_err(pp->dev, "unable to enable pcie_phy clock\n");
@@ -283,6 +278,12 @@ static int imx6_pcie_deassert_core_reset(struct pcie_port *pp)
 	/* allow the clocks to stabilize */
 	usleep_range(200, 500);
 
+	/* power up core phy and enable ref clock */
+	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+			IMX6Q_GPR1_PCIE_TEST_PD, 0 << 18);
+	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+			IMX6Q_GPR1_PCIE_REF_CLK_EN, 1 << 16);
+
 	/* Some boards don't have PCIe reset GPIO. */
 	if (gpio_is_valid(imx6_pcie->reset_gpio)) {
 		gpio_set_value(imx6_pcie->reset_gpio, 0);
@@ -647,7 +648,7 @@ static int __init imx6_pcie_init(void)
 {
 	return platform_driver_probe(&imx6_pcie_driver, imx6_pcie_probe);
 }
-fs_initcall(imx6_pcie_init);
+module_init(imx6_pcie_init);
 
 MODULE_AUTHOR("Sean Cross <xobs@kosagi.com>");
 MODULE_DESCRIPTION("Freescale i.MX6 PCIe host controller driver");
diff --git a/drivers/pci/host/pci-keystone-dw.c b/drivers/pci/host/pci-keystone-dw.c
new file mode 100644
index 000000000000..34086ce88e8e
--- /dev/null
+++ b/drivers/pci/host/pci-keystone-dw.c
@@ -0,0 +1,516 @@
+/*
+ * Designware application register space functions for Keystone PCI controller
+ *
+ * Copyright (C) 2013-2014 Texas Instruments., Ltd.
+ *		http://www.ti.com
+ *
+ * Author: Murali Karicheri <m-karicheri2@ti.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_pci.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+
+#include "pcie-designware.h"
+#include "pci-keystone.h"
+
+/* Application register defines */
+#define LTSSM_EN_VAL		        1
+#define LTSSM_STATE_MASK		0x1f
+#define LTSSM_STATE_L0			0x11
+#define DBI_CS2_EN_VAL			0x20
+#define OB_XLAT_EN_VAL		        2
+
+/* Application registers */
+#define CMD_STATUS			0x004
+#define CFG_SETUP			0x008
+#define OB_SIZE				0x030
+#define CFG_PCIM_WIN_SZ_IDX		3
+#define CFG_PCIM_WIN_CNT		32
+#define SPACE0_REMOTE_CFG_OFFSET	0x1000
+#define OB_OFFSET_INDEX(n)		(0x200 + (8 * n))
+#define OB_OFFSET_HI(n)			(0x204 + (8 * n))
+
+/* IRQ register defines */
+#define IRQ_EOI				0x050
+#define IRQ_STATUS			0x184
+#define IRQ_ENABLE_SET			0x188
+#define IRQ_ENABLE_CLR			0x18c
+
+#define MSI_IRQ				0x054
+#define MSI0_IRQ_STATUS			0x104
+#define MSI0_IRQ_ENABLE_SET		0x108
+#define MSI0_IRQ_ENABLE_CLR		0x10c
+#define IRQ_STATUS			0x184
+#define MSI_IRQ_OFFSET			4
+
+/* Config space registers */
+#define DEBUG0				0x728
+
+#define to_keystone_pcie(x)	container_of(x, struct keystone_pcie, pp)
+
+static inline struct pcie_port *sys_to_pcie(struct pci_sys_data *sys)
+{
+	return sys->private_data;
+}
+
+static inline void update_reg_offset_bit_pos(u32 offset, u32 *reg_offset,
+					     u32 *bit_pos)
+{
+	*reg_offset = offset % 8;
+	*bit_pos = offset >> 3;
+}
+
+u32 ks_dw_pcie_get_msi_addr(struct pcie_port *pp)
+{
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pp);
+
+	return ks_pcie->app.start + MSI_IRQ;
+}
+
+void ks_dw_pcie_handle_msi_irq(struct keystone_pcie *ks_pcie, int offset)
+{
+	struct pcie_port *pp = &ks_pcie->pp;
+	u32 pending, vector;
+	int src, virq;
+
+	pending = readl(ks_pcie->va_app_base + MSI0_IRQ_STATUS + (offset << 4));
+
+	/*
+	 * MSI0 status bit 0-3 shows vectors 0, 8, 16, 24, MSI1 status bit
+	 * shows 1, 9, 17, 25 and so forth
+	 */
+	for (src = 0; src < 4; src++) {
+		if (BIT(src) & pending) {
+			vector = offset + (src << 3);
+			virq = irq_linear_revmap(pp->irq_domain, vector);
+			dev_dbg(pp->dev, "irq: bit %d, vector %d, virq %d\n",
+				src, vector, virq);
+			generic_handle_irq(virq);
+		}
+	}
+}
+
+static void ks_dw_pcie_msi_irq_ack(struct irq_data *d)
+{
+	u32 offset, reg_offset, bit_pos;
+	struct keystone_pcie *ks_pcie;
+	unsigned int irq = d->irq;
+	struct msi_desc *msi;
+	struct pcie_port *pp;
+
+	msi = irq_get_msi_desc(irq);
+	pp = sys_to_pcie(msi->dev->bus->sysdata);
+	ks_pcie = to_keystone_pcie(pp);
+	offset = irq - irq_linear_revmap(pp->irq_domain, 0);
+	update_reg_offset_bit_pos(offset, &reg_offset, &bit_pos);
+
+	writel(BIT(bit_pos),
+	       ks_pcie->va_app_base + MSI0_IRQ_STATUS + (reg_offset << 4));
+	writel(reg_offset + MSI_IRQ_OFFSET, ks_pcie->va_app_base + IRQ_EOI);
+}
+
+void ks_dw_pcie_msi_set_irq(struct pcie_port *pp, int irq)
+{
+	u32 reg_offset, bit_pos;
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pp);
+
+	update_reg_offset_bit_pos(irq, &reg_offset, &bit_pos);
+	writel(BIT(bit_pos),
+	       ks_pcie->va_app_base + MSI0_IRQ_ENABLE_SET + (reg_offset << 4));
+}
+
+void ks_dw_pcie_msi_clear_irq(struct pcie_port *pp, int irq)
+{
+	u32 reg_offset, bit_pos;
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pp);
+
+	update_reg_offset_bit_pos(irq, &reg_offset, &bit_pos);
+	writel(BIT(bit_pos),
+	       ks_pcie->va_app_base + MSI0_IRQ_ENABLE_CLR + (reg_offset << 4));
+}
+
+static void ks_dw_pcie_msi_irq_mask(struct irq_data *d)
+{
+	struct keystone_pcie *ks_pcie;
+	unsigned int irq = d->irq;
+	struct msi_desc *msi;
+	struct pcie_port *pp;
+	u32 offset;
+
+	msi = irq_get_msi_desc(irq);
+	pp = sys_to_pcie(msi->dev->bus->sysdata);
+	ks_pcie = to_keystone_pcie(pp);
+	offset = irq - irq_linear_revmap(pp->irq_domain, 0);
+
+	/* Mask the end point if PVM implemented */
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		if (msi->msi_attrib.maskbit)
+			mask_msi_irq(d);
+	}
+
+	ks_dw_pcie_msi_clear_irq(pp, offset);
+}
+
+static void ks_dw_pcie_msi_irq_unmask(struct irq_data *d)
+{
+	struct keystone_pcie *ks_pcie;
+	unsigned int irq = d->irq;
+	struct msi_desc *msi;
+	struct pcie_port *pp;
+	u32 offset;
+
+	msi = irq_get_msi_desc(irq);
+	pp = sys_to_pcie(msi->dev->bus->sysdata);
+	ks_pcie = to_keystone_pcie(pp);
+	offset = irq - irq_linear_revmap(pp->irq_domain, 0);
+
+	/* Mask the end point if PVM implemented */
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		if (msi->msi_attrib.maskbit)
+			unmask_msi_irq(d);
+	}
+
+	ks_dw_pcie_msi_set_irq(pp, offset);
+}
+
+static struct irq_chip ks_dw_pcie_msi_irq_chip = {
+	.name = "Keystone-PCIe-MSI-IRQ",
+	.irq_ack = ks_dw_pcie_msi_irq_ack,
+	.irq_mask = ks_dw_pcie_msi_irq_mask,
+	.irq_unmask = ks_dw_pcie_msi_irq_unmask,
+};
+
+static int ks_dw_pcie_msi_map(struct irq_domain *domain, unsigned int irq,
+			      irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(irq, &ks_dw_pcie_msi_irq_chip,
+				 handle_level_irq);
+	irq_set_chip_data(irq, domain->host_data);
+	set_irq_flags(irq, IRQF_VALID);
+
+	return 0;
+}
+
+const struct irq_domain_ops ks_dw_pcie_msi_domain_ops = {
+	.map = ks_dw_pcie_msi_map,
+};
+
+int ks_dw_pcie_msi_host_init(struct pcie_port *pp, struct msi_chip *chip)
+{
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pp);
+	int i;
+
+	pp->irq_domain = irq_domain_add_linear(ks_pcie->msi_intc_np,
+					MAX_MSI_IRQS,
+					&ks_dw_pcie_msi_domain_ops,
+					chip);
+	if (!pp->irq_domain) {
+		dev_err(pp->dev, "irq domain init failed\n");
+		return -ENXIO;
+	}
+
+	for (i = 0; i < MAX_MSI_IRQS; i++)
+		irq_create_mapping(pp->irq_domain, i);
+
+	return 0;
+}
+
+void ks_dw_pcie_enable_legacy_irqs(struct keystone_pcie *ks_pcie)
+{
+	int i;
+
+	for (i = 0; i < MAX_LEGACY_IRQS; i++)
+		writel(0x1, ks_pcie->va_app_base + IRQ_ENABLE_SET + (i << 4));
+}
+
+void ks_dw_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie, int offset)
+{
+	struct pcie_port *pp = &ks_pcie->pp;
+	u32 pending;
+	int virq;
+
+	pending = readl(ks_pcie->va_app_base + IRQ_STATUS + (offset << 4));
+
+	if (BIT(0) & pending) {
+		virq = irq_linear_revmap(ks_pcie->legacy_irq_domain, offset);
+		dev_dbg(pp->dev, ": irq: irq_offset %d, virq %d\n", offset,
+			virq);
+		generic_handle_irq(virq);
+	}
+
+	/* EOI the INTx interrupt */
+	writel(offset, ks_pcie->va_app_base + IRQ_EOI);
+}
+
+static void ks_dw_pcie_ack_legacy_irq(struct irq_data *d)
+{
+}
+
+static void ks_dw_pcie_mask_legacy_irq(struct irq_data *d)
+{
+}
+
+static void ks_dw_pcie_unmask_legacy_irq(struct irq_data *d)
+{
+}
+
+static struct irq_chip ks_dw_pcie_legacy_irq_chip = {
+	.name = "Keystone-PCI-Legacy-IRQ",
+	.irq_ack = ks_dw_pcie_ack_legacy_irq,
+	.irq_mask = ks_dw_pcie_mask_legacy_irq,
+	.irq_unmask = ks_dw_pcie_unmask_legacy_irq,
+};
+
+static int ks_dw_pcie_init_legacy_irq_map(struct irq_domain *d,
+				unsigned int irq, irq_hw_number_t hw_irq)
+{
+	irq_set_chip_and_handler(irq, &ks_dw_pcie_legacy_irq_chip,
+				 handle_level_irq);
+	irq_set_chip_data(irq, d->host_data);
+	set_irq_flags(irq, IRQF_VALID);
+
+	return 0;
+}
+
+static const struct irq_domain_ops ks_dw_pcie_legacy_irq_domain_ops = {
+	.map = ks_dw_pcie_init_legacy_irq_map,
+	.xlate = irq_domain_xlate_onetwocell,
+};
+
+/**
+ * ks_dw_pcie_set_dbi_mode() - Set DBI mode to access overlaid BAR mask
+ * registers
+ *
+ * Since modification of dbi_cs2 involves different clock domain, read the
+ * status back to ensure the transition is complete.
+ */
+static void ks_dw_pcie_set_dbi_mode(void __iomem *reg_virt)
+{
+	u32 val;
+
+	writel(DBI_CS2_EN_VAL | readl(reg_virt + CMD_STATUS),
+	       reg_virt + CMD_STATUS);
+
+	do {
+		val = readl(reg_virt + CMD_STATUS);
+	} while (!(val & DBI_CS2_EN_VAL));
+}
+
+/**
+ * ks_dw_pcie_clear_dbi_mode() - Disable DBI mode
+ *
+ * Since modification of dbi_cs2 involves different clock domain, read the
+ * status back to ensure the transition is complete.
+ */
+static void ks_dw_pcie_clear_dbi_mode(void __iomem *reg_virt)
+{
+	u32 val;
+
+	writel(~DBI_CS2_EN_VAL & readl(reg_virt + CMD_STATUS),
+		     reg_virt + CMD_STATUS);
+
+	do {
+		val = readl(reg_virt + CMD_STATUS);
+	} while (val & DBI_CS2_EN_VAL);
+}
+
+void ks_dw_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie)
+{
+	struct pcie_port *pp = &ks_pcie->pp;
+	u32 start = pp->mem.start, end = pp->mem.end;
+	int i, tr_size;
+
+	/* Disable BARs for inbound access */
+	ks_dw_pcie_set_dbi_mode(ks_pcie->va_app_base);
+	writel(0, pp->dbi_base + PCI_BASE_ADDRESS_0);
+	writel(0, pp->dbi_base + PCI_BASE_ADDRESS_1);
+	ks_dw_pcie_clear_dbi_mode(ks_pcie->va_app_base);
+
+	/* Set outbound translation size per window division */
+	writel(CFG_PCIM_WIN_SZ_IDX & 0x7, ks_pcie->va_app_base + OB_SIZE);
+
+	tr_size = (1 << (CFG_PCIM_WIN_SZ_IDX & 0x7)) * SZ_1M;
+
+	/* Using Direct 1:1 mapping of RC <-> PCI memory space */
+	for (i = 0; (i < CFG_PCIM_WIN_CNT) && (start < end); i++) {
+		writel(start | 1, ks_pcie->va_app_base + OB_OFFSET_INDEX(i));
+		writel(0, ks_pcie->va_app_base + OB_OFFSET_HI(i));
+		start += tr_size;
+	}
+
+	/* Enable OB translation */
+	writel(OB_XLAT_EN_VAL | readl(ks_pcie->va_app_base + CMD_STATUS),
+	       ks_pcie->va_app_base + CMD_STATUS);
+}
+
+/**
+ * ks_pcie_cfg_setup() - Set up configuration space address for a device
+ *
+ * @ks_pcie: ptr to keystone_pcie structure
+ * @bus: Bus number the device is residing on
+ * @devfn: device, function number info
+ *
+ * Forms and returns the address of configuration space mapped in PCIESS
+ * address space 0.  Also configures CFG_SETUP for remote configuration space
+ * access.
+ *
+ * The address space has two regions to access configuration - local and remote.
+ * We access local region for bus 0 (as RC is attached on bus 0) and remote
+ * region for others with TYPE 1 access when bus > 1.  As for device on bus = 1,
+ * we will do TYPE 0 access as it will be on our secondary bus (logical).
+ * CFG_SETUP is needed only for remote configuration access.
+ */
+static void __iomem *ks_pcie_cfg_setup(struct keystone_pcie *ks_pcie, u8 bus,
+				       unsigned int devfn)
+{
+	u8 device = PCI_SLOT(devfn), function = PCI_FUNC(devfn);
+	struct pcie_port *pp = &ks_pcie->pp;
+	u32 regval;
+
+	if (bus == 0)
+		return pp->dbi_base;
+
+	regval = (bus << 16) | (device << 8) | function;
+
+	/*
+	 * Since Bus#1 will be a virtual bus, we need to have TYPE0
+	 * access only.
+	 * TYPE 1
+	 */
+	if (bus != 1)
+		regval |= BIT(24);
+
+	writel(regval, ks_pcie->va_app_base + CFG_SETUP);
+	return pp->va_cfg0_base;
+}
+
+int ks_dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
+			     unsigned int devfn, int where, int size, u32 *val)
+{
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pp);
+	u8 bus_num = bus->number;
+	void __iomem *addr;
+
+	addr = ks_pcie_cfg_setup(ks_pcie, bus_num, devfn);
+
+	return dw_pcie_cfg_read(addr + (where & ~0x3), where, size, val);
+}
+
+int ks_dw_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus,
+			     unsigned int devfn, int where, int size, u32 val)
+{
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pp);
+	u8 bus_num = bus->number;
+	void __iomem *addr;
+
+	addr = ks_pcie_cfg_setup(ks_pcie, bus_num, devfn);
+
+	return dw_pcie_cfg_write(addr + (where & ~0x3), where, size, val);
+}
+
+/**
+ * ks_dw_pcie_v3_65_scan_bus() - keystone scan_bus post initialization
+ *
+ * This sets BAR0 to enable inbound access for MSI_IRQ register
+ */
+void ks_dw_pcie_v3_65_scan_bus(struct pcie_port *pp)
+{
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pp);
+
+	/* Configure and set up BAR0 */
+	ks_dw_pcie_set_dbi_mode(ks_pcie->va_app_base);
+
+	/* Enable BAR0 */
+	writel(1, pp->dbi_base + PCI_BASE_ADDRESS_0);
+	writel(SZ_4K - 1, pp->dbi_base + PCI_BASE_ADDRESS_0);
+
+	ks_dw_pcie_clear_dbi_mode(ks_pcie->va_app_base);
+
+	 /*
+	  * For BAR0, just setting bus address for inbound writes (MSI) should
+	  * be sufficient.  Use physical address to avoid any conflicts.
+	  */
+	writel(ks_pcie->app.start, pp->dbi_base + PCI_BASE_ADDRESS_0);
+}
+
+/**
+ * ks_dw_pcie_link_up() - Check if link up
+ */
+int ks_dw_pcie_link_up(struct pcie_port *pp)
+{
+	u32 val = readl(pp->dbi_base + DEBUG0);
+
+	return (val & LTSSM_STATE_MASK) == LTSSM_STATE_L0;
+}
+
+void ks_dw_pcie_initiate_link_train(struct keystone_pcie *ks_pcie)
+{
+	u32 val;
+
+	/* Disable Link training */
+	val = readl(ks_pcie->va_app_base + CMD_STATUS);
+	val &= ~LTSSM_EN_VAL;
+	writel(LTSSM_EN_VAL | val,  ks_pcie->va_app_base + CMD_STATUS);
+
+	/* Initiate Link Training */
+	val = readl(ks_pcie->va_app_base + CMD_STATUS);
+	writel(LTSSM_EN_VAL | val,  ks_pcie->va_app_base + CMD_STATUS);
+}
+
+/**
+ * ks_dw_pcie_host_init() - initialize host for v3_65 dw hardware
+ *
+ * Ioremap the register resources, initialize legacy irq domain
+ * and call dw_pcie_v3_65_host_init() API to initialize the Keystone
+ * PCI host controller.
+ */
+int __init ks_dw_pcie_host_init(struct keystone_pcie *ks_pcie,
+				struct device_node *msi_intc_np)
+{
+	struct pcie_port *pp = &ks_pcie->pp;
+	struct platform_device *pdev = to_platform_device(pp->dev);
+	struct resource *res;
+
+	/* Index 0 is the config reg. space address */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	pp->dbi_base = devm_ioremap_resource(pp->dev, res);
+	if (IS_ERR(pp->dbi_base))
+		return PTR_ERR(pp->dbi_base);
+
+	/*
+	 * We set these same and is used in pcie rd/wr_other_conf
+	 * functions
+	 */
+	pp->va_cfg0_base = pp->dbi_base + SPACE0_REMOTE_CFG_OFFSET;
+	pp->va_cfg1_base = pp->va_cfg0_base;
+
+	/* Index 1 is the application reg. space address */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	ks_pcie->app = *res;
+	ks_pcie->va_app_base = devm_ioremap_resource(pp->dev, res);
+	if (IS_ERR(ks_pcie->va_app_base))
+		return PTR_ERR(ks_pcie->va_app_base);
+
+	/* Create legacy IRQ domain */
+	ks_pcie->legacy_irq_domain =
+			irq_domain_add_linear(ks_pcie->legacy_intc_np,
+					MAX_LEGACY_IRQS,
+					&ks_dw_pcie_legacy_irq_domain_ops,
+					NULL);
+	if (!ks_pcie->legacy_irq_domain) {
+		dev_err(pp->dev, "Failed to add irq domain for legacy irqs\n");
+		return -EINVAL;
+	}
+
+	return dw_pcie_host_init(pp);
+}
diff --git a/drivers/pci/host/pci-keystone.c b/drivers/pci/host/pci-keystone.c
new file mode 100644
index 000000000000..1b893bc8b842
--- /dev/null
+++ b/drivers/pci/host/pci-keystone.c
@@ -0,0 +1,415 @@
+/*
+ * PCIe host controller driver for Texas Instruments Keystone SoCs
+ *
+ * Copyright (C) 2013-2014 Texas Instruments., Ltd.
+ *		http://www.ti.com
+ *
+ * Author: Murali Karicheri <m-karicheri2@ti.com>
+ * Implementation based on pci-exynos.c and pcie-designware.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/irqchip/chained_irq.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of_irq.h>
+#include <linux/of.h>
+#include <linux/of_pci.h>
+#include <linux/platform_device.h>
+#include <linux/phy/phy.h>
+#include <linux/resource.h>
+#include <linux/signal.h>
+
+#include "pcie-designware.h"
+#include "pci-keystone.h"
+
+#define DRIVER_NAME	"keystone-pcie"
+
+/* driver specific constants */
+#define MAX_MSI_HOST_IRQS		8
+#define MAX_LEGACY_HOST_IRQS		4
+
+/* DEV_STAT_CTRL */
+#define PCIE_CAP_BASE		0x70
+
+/* PCIE controller device IDs */
+#define PCIE_RC_K2HK		0xb008
+#define PCIE_RC_K2E		0xb009
+#define PCIE_RC_K2L		0xb00a
+
+#define to_keystone_pcie(x)	container_of(x, struct keystone_pcie, pp)
+
+static void quirk_limit_mrrs(struct pci_dev *dev)
+{
+	struct pci_bus *bus = dev->bus;
+	struct pci_dev *bridge = bus->self;
+	static const struct pci_device_id rc_pci_devids[] = {
+		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2HK),
+		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2E),
+		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2L),
+		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		{ 0, },
+	};
+
+	if (pci_is_root_bus(bus))
+		return;
+
+	/* look for the host bridge */
+	while (!pci_is_root_bus(bus)) {
+		bridge = bus->self;
+		bus = bus->parent;
+	}
+
+	if (bridge) {
+		/*
+		 * Keystone PCI controller has a h/w limitation of
+		 * 256 bytes maximum read request size.  It can't handle
+		 * anything higher than this.  So force this limit on
+		 * all downstream devices.
+		 */
+		if (pci_match_id(rc_pci_devids, bridge)) {
+			if (pcie_get_readrq(dev) > 256) {
+				dev_info(&dev->dev, "limiting MRRS to 256\n");
+				pcie_set_readrq(dev, 256);
+			}
+		}
+	}
+}
+DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, quirk_limit_mrrs);
+
+static int ks_pcie_establish_link(struct keystone_pcie *ks_pcie)
+{
+	struct pcie_port *pp = &ks_pcie->pp;
+	int count = 200;
+
+	dw_pcie_setup_rc(pp);
+
+	if (dw_pcie_link_up(pp)) {
+		dev_err(pp->dev, "Link already up\n");
+		return 0;
+	}
+
+	ks_dw_pcie_initiate_link_train(ks_pcie);
+	/* check if the link is up or not */
+	while (!dw_pcie_link_up(pp)) {
+		usleep_range(100, 1000);
+		if (--count) {
+			ks_dw_pcie_initiate_link_train(ks_pcie);
+			continue;
+		}
+		dev_err(pp->dev, "phy link never came up\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void ks_pcie_msi_irq_handler(unsigned int irq, struct irq_desc *desc)
+{
+	struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc);
+	u32 offset = irq - ks_pcie->msi_host_irqs[0];
+	struct pcie_port *pp = &ks_pcie->pp;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	dev_dbg(pp->dev, "ks_pci_msi_irq_handler, irq %d\n", irq);
+
+	/*
+	 * The chained irq handler installation would have replaced normal
+	 * interrupt driver handler so we need to take care of mask/unmask and
+	 * ack operation.
+	 */
+	chained_irq_enter(chip, desc);
+	ks_dw_pcie_handle_msi_irq(ks_pcie, offset);
+	chained_irq_exit(chip, desc);
+}
+
+/**
+ * ks_pcie_legacy_irq_handler() - Handle legacy interrupt
+ * @irq: IRQ line for legacy interrupts
+ * @desc: Pointer to irq descriptor
+ *
+ * Traverse through pending legacy interrupts and invoke handler for each. Also
+ * takes care of interrupt controller level mask/ack operation.
+ */
+static void ks_pcie_legacy_irq_handler(unsigned int irq, struct irq_desc *desc)
+{
+	struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc);
+	struct pcie_port *pp = &ks_pcie->pp;
+	u32 irq_offset = irq - ks_pcie->legacy_host_irqs[0];
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	dev_dbg(pp->dev, ": Handling legacy irq %d\n", irq);
+
+	/*
+	 * The chained irq handler installation would have replaced normal
+	 * interrupt driver handler so we need to take care of mask/unmask and
+	 * ack operation.
+	 */
+	chained_irq_enter(chip, desc);
+	ks_dw_pcie_handle_legacy_irq(ks_pcie, irq_offset);
+	chained_irq_exit(chip, desc);
+}
+
+static int ks_pcie_get_irq_controller_info(struct keystone_pcie *ks_pcie,
+					   char *controller, int *num_irqs)
+{
+	int temp, max_host_irqs, legacy = 1, *host_irqs, ret = -EINVAL;
+	struct device *dev = ks_pcie->pp.dev;
+	struct device_node *np_pcie = dev->of_node, **np_temp;
+
+	if (!strcmp(controller, "msi-interrupt-controller"))
+		legacy = 0;
+
+	if (legacy) {
+		np_temp = &ks_pcie->legacy_intc_np;
+		max_host_irqs = MAX_LEGACY_HOST_IRQS;
+		host_irqs = &ks_pcie->legacy_host_irqs[0];
+	} else {
+		np_temp = &ks_pcie->msi_intc_np;
+		max_host_irqs = MAX_MSI_HOST_IRQS;
+		host_irqs =  &ks_pcie->msi_host_irqs[0];
+	}
+
+	/* interrupt controller is in a child node */
+	*np_temp = of_find_node_by_name(np_pcie, controller);
+	if (!(*np_temp)) {
+		dev_err(dev, "Node for %s is absent\n", controller);
+		goto out;
+	}
+	temp = of_irq_count(*np_temp);
+	if (!temp)
+		goto out;
+	if (temp > max_host_irqs)
+		dev_warn(dev, "Too many %s interrupts defined %u\n",
+			(legacy ? "legacy" : "MSI"), temp);
+
+	/*
+	 * support upto max_host_irqs. In dt from index 0 to 3 (legacy) or 0 to
+	 * 7 (MSI)
+	 */
+	for (temp = 0; temp < max_host_irqs; temp++) {
+		host_irqs[temp] = irq_of_parse_and_map(*np_temp, temp);
+		if (host_irqs[temp] < 0)
+			break;
+	}
+	if (temp) {
+		*num_irqs = temp;
+		ret = 0;
+	}
+out:
+	return ret;
+}
+
+static void ks_pcie_setup_interrupts(struct keystone_pcie *ks_pcie)
+{
+	int i;
+
+	/* Legacy IRQ */
+	for (i = 0; i < ks_pcie->num_legacy_host_irqs; i++) {
+		irq_set_handler_data(ks_pcie->legacy_host_irqs[i], ks_pcie);
+		irq_set_chained_handler(ks_pcie->legacy_host_irqs[i],
+					ks_pcie_legacy_irq_handler);
+	}
+	ks_dw_pcie_enable_legacy_irqs(ks_pcie);
+
+	/* MSI IRQ */
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		for (i = 0; i < ks_pcie->num_msi_host_irqs; i++) {
+			irq_set_chained_handler(ks_pcie->msi_host_irqs[i],
+						ks_pcie_msi_irq_handler);
+			irq_set_handler_data(ks_pcie->msi_host_irqs[i],
+					     ks_pcie);
+		}
+	}
+}
+
+/*
+ * When a PCI device does not exist during config cycles, keystone host gets a
+ * bus error instead of returning 0xffffffff. This handler always returns 0
+ * for this kind of faults.
+ */
+static int keystone_pcie_fault(unsigned long addr, unsigned int fsr,
+				struct pt_regs *regs)
+{
+	unsigned long instr = *(unsigned long *) instruction_pointer(regs);
+
+	if ((instr & 0x0e100090) == 0x00100090) {
+		int reg = (instr >> 12) & 15;
+
+		regs->uregs[reg] = -1;
+		regs->ARM_pc += 4;
+	}
+
+	return 0;
+}
+
+static void __init ks_pcie_host_init(struct pcie_port *pp)
+{
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pp);
+	u32 val;
+
+	ks_pcie_establish_link(ks_pcie);
+	ks_dw_pcie_setup_rc_app_regs(ks_pcie);
+	ks_pcie_setup_interrupts(ks_pcie);
+	writew(PCI_IO_RANGE_TYPE_32 | (PCI_IO_RANGE_TYPE_32 << 8),
+			pp->dbi_base + PCI_IO_BASE);
+
+	/* update the Vendor ID */
+	writew(ks_pcie->device_id, pp->dbi_base + PCI_DEVICE_ID);
+
+	/* update the DEV_STAT_CTRL to publish right mrrs */
+	val = readl(pp->dbi_base + PCIE_CAP_BASE + PCI_EXP_DEVCTL);
+	val &= ~PCI_EXP_DEVCTL_READRQ;
+	/* set the mrrs to 256 bytes */
+	val |= BIT(12);
+	writel(val, pp->dbi_base + PCIE_CAP_BASE + PCI_EXP_DEVCTL);
+
+	/*
+	 * PCIe access errors that result into OCP errors are caught by ARM as
+	 * "External aborts"
+	 */
+	hook_fault_code(17, keystone_pcie_fault, SIGBUS, 0,
+			"Asynchronous external abort");
+}
+
+static struct pcie_host_ops keystone_pcie_host_ops = {
+	.rd_other_conf = ks_dw_pcie_rd_other_conf,
+	.wr_other_conf = ks_dw_pcie_wr_other_conf,
+	.link_up = ks_dw_pcie_link_up,
+	.host_init = ks_pcie_host_init,
+	.msi_set_irq = ks_dw_pcie_msi_set_irq,
+	.msi_clear_irq = ks_dw_pcie_msi_clear_irq,
+	.get_msi_addr = ks_dw_pcie_get_msi_addr,
+	.msi_host_init = ks_dw_pcie_msi_host_init,
+	.scan_bus = ks_dw_pcie_v3_65_scan_bus,
+};
+
+static int __init ks_add_pcie_port(struct keystone_pcie *ks_pcie,
+			 struct platform_device *pdev)
+{
+	struct pcie_port *pp = &ks_pcie->pp;
+	int ret;
+
+	ret = ks_pcie_get_irq_controller_info(ks_pcie,
+					"legacy-interrupt-controller",
+					&ks_pcie->num_legacy_host_irqs);
+	if (ret)
+		return ret;
+
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		ret = ks_pcie_get_irq_controller_info(ks_pcie,
+						"msi-interrupt-controller",
+						&ks_pcie->num_msi_host_irqs);
+		if (ret)
+			return ret;
+	}
+
+	pp->root_bus_nr = -1;
+	pp->ops = &keystone_pcie_host_ops;
+	ret = ks_dw_pcie_host_init(ks_pcie, ks_pcie->msi_intc_np);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to initialize host\n");
+		return ret;
+	}
+
+	return ret;
+}
+
+static const struct of_device_id ks_pcie_of_match[] = {
+	{
+		.type = "pci",
+		.compatible = "ti,keystone-pcie",
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ks_pcie_of_match);
+
+static int __exit ks_pcie_remove(struct platform_device *pdev)
+{
+	struct keystone_pcie *ks_pcie = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(ks_pcie->clk);
+
+	return 0;
+}
+
+static int __init ks_pcie_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct keystone_pcie *ks_pcie;
+	struct pcie_port *pp;
+	struct resource *res;
+	void __iomem *reg_p;
+	struct phy *phy;
+	int ret = 0;
+
+	ks_pcie = devm_kzalloc(&pdev->dev, sizeof(*ks_pcie),
+				GFP_KERNEL);
+	if (!ks_pcie) {
+		dev_err(dev, "no memory for keystone pcie\n");
+		return -ENOMEM;
+	}
+	pp = &ks_pcie->pp;
+
+	/* initialize SerDes Phy if present */
+	phy = devm_phy_get(dev, "pcie-phy");
+	if (!IS_ERR_OR_NULL(phy)) {
+		ret = phy_init(phy);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* index 2 is to read PCI DEVICE_ID */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	reg_p = devm_ioremap_resource(dev, res);
+	if (IS_ERR(reg_p))
+		return PTR_ERR(reg_p);
+	ks_pcie->device_id = readl(reg_p) >> 16;
+	devm_iounmap(dev, reg_p);
+	devm_release_mem_region(dev, res->start, resource_size(res));
+
+	pp->dev = dev;
+	platform_set_drvdata(pdev, ks_pcie);
+	ks_pcie->clk = devm_clk_get(dev, "pcie");
+	if (IS_ERR(ks_pcie->clk)) {
+		dev_err(dev, "Failed to get pcie rc clock\n");
+		return PTR_ERR(ks_pcie->clk);
+	}
+	ret = clk_prepare_enable(ks_pcie->clk);
+	if (ret)
+		return ret;
+
+	ret = ks_add_pcie_port(ks_pcie, pdev);
+	if (ret < 0)
+		goto fail_clk;
+
+	return 0;
+fail_clk:
+	clk_disable_unprepare(ks_pcie->clk);
+
+	return ret;
+}
+
+static struct platform_driver ks_pcie_driver __refdata = {
+	.probe  = ks_pcie_probe,
+	.remove = __exit_p(ks_pcie_remove),
+	.driver = {
+		.name	= "keystone-pcie",
+		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(ks_pcie_of_match),
+	},
+};
+
+module_platform_driver(ks_pcie_driver);
+
+MODULE_AUTHOR("Murali Karicheri <m-karicheri2@ti.com>");
+MODULE_DESCRIPTION("Keystone PCIe host controller driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pci-keystone.h b/drivers/pci/host/pci-keystone.h
new file mode 100644
index 000000000000..1fc1fceede9e
--- /dev/null
+++ b/drivers/pci/host/pci-keystone.h
@@ -0,0 +1,58 @@
+/*
+ * Keystone PCI Controller's common includes
+ *
+ * Copyright (C) 2013-2014 Texas Instruments., Ltd.
+ *		http://www.ti.com
+ *
+ * Author: Murali Karicheri <m-karicheri2@ti.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define MAX_LEGACY_IRQS			4
+#define MAX_MSI_HOST_IRQS		8
+#define MAX_LEGACY_HOST_IRQS		4
+
+struct keystone_pcie {
+	struct	clk		*clk;
+	struct	pcie_port	pp;
+	/* PCI Device ID */
+	u32			device_id;
+	int			num_legacy_host_irqs;
+	int			legacy_host_irqs[MAX_LEGACY_HOST_IRQS];
+	struct			device_node *legacy_intc_np;
+
+	int			num_msi_host_irqs;
+	int			msi_host_irqs[MAX_MSI_HOST_IRQS];
+	struct			device_node *msi_intc_np;
+	struct irq_domain	*legacy_irq_domain;
+
+	/* Application register space */
+	void __iomem		*va_app_base;
+	struct resource		app;
+};
+
+/* Keystone DW specific MSI controller APIs/definitions */
+void ks_dw_pcie_handle_msi_irq(struct keystone_pcie *ks_pcie, int offset);
+u32 ks_dw_pcie_get_msi_addr(struct pcie_port *pp);
+
+/* Keystone specific PCI controller APIs */
+void ks_dw_pcie_enable_legacy_irqs(struct keystone_pcie *ks_pcie);
+void ks_dw_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie, int offset);
+int  ks_dw_pcie_host_init(struct keystone_pcie *ks_pcie,
+			struct device_node *msi_intc_np);
+int ks_dw_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus,
+		unsigned int devfn, int where, int size, u32 val);
+int ks_dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
+		unsigned int devfn, int where, int size, u32 *val);
+void ks_dw_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie);
+int ks_dw_pcie_link_up(struct pcie_port *pp);
+void ks_dw_pcie_initiate_link_train(struct keystone_pcie *ks_pcie);
+void ks_dw_pcie_msi_set_irq(struct pcie_port *pp, int irq);
+void ks_dw_pcie_msi_clear_irq(struct pcie_port *pp, int irq);
+void ks_dw_pcie_v3_65_scan_bus(struct pcie_port *pp);
+int ks_dw_pcie_msi_host_init(struct pcie_port *pp,
+		struct msi_chip *chip);
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index a8c6f1a92e0f..b1315e197ffb 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -873,7 +873,7 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn,
 	rangesz = pna + na + ns;
 	nranges = rlen / sizeof(__be32) / rangesz;
 
-	for (i = 0; i < nranges; i++) {
+	for (i = 0; i < nranges; i++, range += rangesz) {
 		u32 flags = of_read_number(range, 1);
 		u32 slot = of_read_number(range + 1, 1);
 		u64 cpuaddr = of_read_number(range + na, pna);
@@ -883,14 +883,14 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn,
 			rtype = IORESOURCE_IO;
 		else if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_MEM32)
 			rtype = IORESOURCE_MEM;
+		else
+			continue;
 
 		if (slot == PCI_SLOT(devfn) && type == rtype) {
 			*tgt = DT_CPUADDR_TO_TARGET(cpuaddr);
 			*attr = DT_CPUADDR_TO_ATTR(cpuaddr);
 			return 0;
 		}
-
-		range += rangesz;
 	}
 
 	return -ENOENT;
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index 0fb0fdb223d5..3d43874319be 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -38,6 +38,7 @@
 #include <linux/of_pci.h>
 #include <linux/of_platform.h>
 #include <linux/pci.h>
+#include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/sizes.h>
@@ -115,13 +116,20 @@
 
 #define AFI_INTR_CODE			0xb8
 #define  AFI_INTR_CODE_MASK		0xf
-#define  AFI_INTR_AXI_SLAVE_ERROR	1
-#define  AFI_INTR_AXI_DECODE_ERROR	2
+#define  AFI_INTR_INI_SLAVE_ERROR	1
+#define  AFI_INTR_INI_DECODE_ERROR	2
 #define  AFI_INTR_TARGET_ABORT		3
 #define  AFI_INTR_MASTER_ABORT		4
 #define  AFI_INTR_INVALID_WRITE		5
 #define  AFI_INTR_LEGACY		6
 #define  AFI_INTR_FPCI_DECODE_ERROR	7
+#define  AFI_INTR_AXI_DECODE_ERROR	8
+#define  AFI_INTR_FPCI_TIMEOUT		9
+#define  AFI_INTR_PE_PRSNT_SENSE	10
+#define  AFI_INTR_PE_CLKREQ_SENSE	11
+#define  AFI_INTR_CLKCLAMP_SENSE	12
+#define  AFI_INTR_RDY4PD_SENSE		13
+#define  AFI_INTR_P2P_ERROR		14
 
 #define AFI_INTR_SIGNATURE	0xbc
 #define AFI_UPPER_FPCI_ADDRESS	0xc0
@@ -152,8 +160,10 @@
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK	(0xf << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_SINGLE	(0x0 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_420	(0x0 << 20)
+#define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_X2_X1	(0x0 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_DUAL	(0x1 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_222	(0x1 << 20)
+#define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_X4_X1	(0x1 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_411	(0x2 << 20)
 
 #define AFI_FUSE			0x104
@@ -165,12 +175,21 @@
 #define  AFI_PEX_CTRL_RST		(1 << 0)
 #define  AFI_PEX_CTRL_CLKREQ_EN		(1 << 1)
 #define  AFI_PEX_CTRL_REFCLK_EN		(1 << 3)
+#define  AFI_PEX_CTRL_OVERRIDE_EN	(1 << 4)
+
+#define AFI_PLLE_CONTROL		0x160
+#define  AFI_PLLE_CONTROL_BYPASS_PADS2PLLE_CONTROL (1 << 9)
+#define  AFI_PLLE_CONTROL_PADS2PLLE_CONTROL_EN (1 << 1)
 
 #define AFI_PEXBIAS_CTRL_0		0x168
 
 #define RP_VEND_XP	0x00000F00
 #define  RP_VEND_XP_DL_UP	(1 << 30)
 
+#define RP_PRIV_MISC	0x00000FE0
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT (0xE << 0)
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT (0xF << 0)
+
 #define RP_LINK_CONTROL_STATUS			0x00000090
 #define  RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE	0x20000000
 #define  RP_LINK_CONTROL_STATUS_LINKSTAT_MASK	0x3fff0000
@@ -197,6 +216,7 @@
 
 #define PADS_REFCLK_CFG0			0x000000C8
 #define PADS_REFCLK_CFG1			0x000000CC
+#define PADS_REFCLK_BIAS			0x000000D0
 
 /*
  * Fields in PADS_REFCLK_CFG*. Those registers form an array of 16-bit
@@ -236,6 +256,7 @@ struct tegra_pcie_soc_data {
 	bool has_pex_bias_ctrl;
 	bool has_intr_prsnt_sense;
 	bool has_cml_clk;
+	bool has_gen2;
 };
 
 static inline struct tegra_msi *to_tegra_msi(struct msi_chip *chip)
@@ -253,6 +274,7 @@ struct tegra_pcie {
 	struct list_head buses;
 	struct resource *cs;
 
+	struct resource all;
 	struct resource io;
 	struct resource mem;
 	struct resource prefetch;
@@ -267,6 +289,8 @@ struct tegra_pcie {
 	struct reset_control *afi_rst;
 	struct reset_control *pcie_xrst;
 
+	struct phy *phy;
+
 	struct tegra_msi msi;
 
 	struct list_head ports;
@@ -382,7 +406,7 @@ static struct tegra_pcie_bus *tegra_pcie_bus_alloc(struct tegra_pcie *pcie,
 	for (i = 0; i < 16; i++) {
 		unsigned long virt = (unsigned long)bus->area->addr +
 				     i * SZ_64K;
-		phys_addr_t phys = cs + i * SZ_1M + busnr * SZ_64K;
+		phys_addr_t phys = cs + i * SZ_16M + busnr * SZ_64K;
 
 		err = ioremap_page_range(virt, virt + SZ_64K, phys, prot);
 		if (err < 0) {
@@ -561,6 +585,8 @@ static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
 	if (soc->has_pex_clkreq_en)
 		value |= AFI_PEX_CTRL_CLKREQ_EN;
 
+	value |= AFI_PEX_CTRL_OVERRIDE_EN;
+
 	afi_writel(port->pcie, value, ctrl);
 
 	tegra_pcie_port_reset(port);
@@ -568,6 +594,7 @@ static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
 
 static void tegra_pcie_port_disable(struct tegra_pcie_port *port)
 {
+	const struct tegra_pcie_soc_data *soc = port->pcie->soc_data;
 	unsigned long ctrl = tegra_pcie_port_get_pex_ctrl(port);
 	unsigned long value;
 
@@ -578,6 +605,10 @@ static void tegra_pcie_port_disable(struct tegra_pcie_port *port)
 
 	/* disable reference clock */
 	value = afi_readl(port->pcie, ctrl);
+
+	if (soc->has_pex_clkreq_en)
+		value &= ~AFI_PEX_CTRL_CLKREQ_EN;
+
 	value &= ~AFI_PEX_CTRL_REFCLK_EN;
 	afi_writel(port->pcie, value, ctrl);
 }
@@ -626,13 +657,25 @@ DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, tegra_pcie_relax_enable);
 static int tegra_pcie_setup(int nr, struct pci_sys_data *sys)
 {
 	struct tegra_pcie *pcie = sys_to_pcie(sys);
+	int err;
+	phys_addr_t io_start;
+
+	err = devm_request_resource(pcie->dev, &pcie->all, &pcie->mem);
+	if (err < 0)
+		return err;
+
+	err = devm_request_resource(pcie->dev, &pcie->all, &pcie->prefetch);
+	if (err)
+		return err;
+
+	io_start = pci_pio_to_address(pcie->io.start);
 
 	pci_add_resource_offset(&sys->resources, &pcie->mem, sys->mem_offset);
 	pci_add_resource_offset(&sys->resources, &pcie->prefetch,
 				sys->mem_offset);
 	pci_add_resource(&sys->resources, &pcie->busn);
 
-	pci_ioremap_io(nr * SZ_64K, pcie->io.start);
+	pci_ioremap_io(nr * SZ_64K, io_start);
 
 	return 1;
 }
@@ -684,9 +727,15 @@ static irqreturn_t tegra_pcie_isr(int irq, void *arg)
 		"Target abort",
 		"Master abort",
 		"Invalid write",
+		"Legacy interrupt",
 		"Response decoding error",
 		"AXI response decoding error",
 		"Transaction timeout",
+		"Slot present pin change",
+		"Slot clock request change",
+		"TMS clock ramp change",
+		"TMS ready for power down",
+		"Peer2Peer error",
 	};
 	struct tegra_pcie *pcie = arg;
 	u32 code, signature;
@@ -737,6 +786,7 @@ static irqreturn_t tegra_pcie_isr(int irq, void *arg)
 static void tegra_pcie_setup_translations(struct tegra_pcie *pcie)
 {
 	u32 fpci_bar, size, axi_address;
+	phys_addr_t io_start = pci_pio_to_address(pcie->io.start);
 
 	/* Bar 0: type 1 extended configuration space */
 	fpci_bar = 0xfe100000;
@@ -749,7 +799,7 @@ static void tegra_pcie_setup_translations(struct tegra_pcie *pcie)
 	/* Bar 1: downstream IO bar */
 	fpci_bar = 0xfdfc0000;
 	size = resource_size(&pcie->io);
-	axi_address = pcie->io.start;
+	axi_address = io_start;
 	afi_writel(pcie, axi_address, AFI_AXI_BAR1_START);
 	afi_writel(pcie, size >> 12, AFI_AXI_BAR1_SZ);
 	afi_writel(pcie, fpci_bar, AFI_FPCI_BAR1);
@@ -792,30 +842,27 @@ static void tegra_pcie_setup_translations(struct tegra_pcie *pcie)
 	afi_writel(pcie, 0, AFI_MSI_BAR_SZ);
 }
 
-static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
+static int tegra_pcie_pll_wait(struct tegra_pcie *pcie, unsigned long timeout)
 {
 	const struct tegra_pcie_soc_data *soc = pcie->soc_data;
-	struct tegra_pcie_port *port;
-	unsigned int timeout;
-	unsigned long value;
+	u32 value;
 
-	/* power down PCIe slot clock bias pad */
-	if (soc->has_pex_bias_ctrl)
-		afi_writel(pcie, 0, AFI_PEXBIAS_CTRL_0);
+	timeout = jiffies + msecs_to_jiffies(timeout);
 
-	/* configure mode and disable all ports */
-	value = afi_readl(pcie, AFI_PCIE_CONFIG);
-	value &= ~AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK;
-	value |= AFI_PCIE_CONFIG_PCIE_DISABLE_ALL | pcie->xbar_config;
-
-	list_for_each_entry(port, &pcie->ports, list)
-		value &= ~AFI_PCIE_CONFIG_PCIE_DISABLE(port->index);
+	while (time_before(jiffies, timeout)) {
+		value = pads_readl(pcie, soc->pads_pll_ctl);
+		if (value & PADS_PLL_CTL_LOCKDET)
+			return 0;
+	}
 
-	afi_writel(pcie, value, AFI_PCIE_CONFIG);
+	return -ETIMEDOUT;
+}
 
-	value = afi_readl(pcie, AFI_FUSE);
-	value |= AFI_FUSE_PCIE_T0_GEN2_DIS;
-	afi_writel(pcie, value, AFI_FUSE);
+static int tegra_pcie_phy_enable(struct tegra_pcie *pcie)
+{
+	const struct tegra_pcie_soc_data *soc = pcie->soc_data;
+	u32 value;
+	int err;
 
 	/* initialize internal PHY, enable up to 16 PCIE lanes */
 	pads_writel(pcie, 0x0, PADS_CTL_SEL);
@@ -834,6 +881,13 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 	value |= PADS_PLL_CTL_REFCLK_INTERNAL_CML | soc->tx_ref_sel;
 	pads_writel(pcie, value, soc->pads_pll_ctl);
 
+	/* reset PLL */
+	value = pads_readl(pcie, soc->pads_pll_ctl);
+	value &= ~PADS_PLL_CTL_RST_B4SM;
+	pads_writel(pcie, value, soc->pads_pll_ctl);
+
+	usleep_range(20, 100);
+
 	/* take PLL out of reset  */
 	value = pads_readl(pcie, soc->pads_pll_ctl);
 	value |= PADS_PLL_CTL_RST_B4SM;
@@ -846,15 +900,11 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 		pads_writel(pcie, PADS_REFCLK_CFG_VALUE, PADS_REFCLK_CFG1);
 
 	/* wait for the PLL to lock */
-	timeout = 300;
-	do {
-		value = pads_readl(pcie, soc->pads_pll_ctl);
-		usleep_range(1000, 2000);
-		if (--timeout == 0) {
-			pr_err("Tegra PCIe error: timeout waiting for PLL\n");
-			return -EBUSY;
-		}
-	} while (!(value & PADS_PLL_CTL_LOCKDET));
+	err = tegra_pcie_pll_wait(pcie, 500);
+	if (err < 0) {
+		dev_err(pcie->dev, "PLL failed to lock: %d\n", err);
+		return err;
+	}
 
 	/* turn off IDDQ override */
 	value = pads_readl(pcie, PADS_CTL);
@@ -866,6 +916,58 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 	value |= PADS_CTL_TX_DATA_EN_1L | PADS_CTL_RX_DATA_EN_1L;
 	pads_writel(pcie, value, PADS_CTL);
 
+	return 0;
+}
+
+static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
+{
+	const struct tegra_pcie_soc_data *soc = pcie->soc_data;
+	struct tegra_pcie_port *port;
+	unsigned long value;
+	int err;
+
+	/* enable PLL power down */
+	if (pcie->phy) {
+		value = afi_readl(pcie, AFI_PLLE_CONTROL);
+		value &= ~AFI_PLLE_CONTROL_BYPASS_PADS2PLLE_CONTROL;
+		value |= AFI_PLLE_CONTROL_PADS2PLLE_CONTROL_EN;
+		afi_writel(pcie, value, AFI_PLLE_CONTROL);
+	}
+
+	/* power down PCIe slot clock bias pad */
+	if (soc->has_pex_bias_ctrl)
+		afi_writel(pcie, 0, AFI_PEXBIAS_CTRL_0);
+
+	/* configure mode and disable all ports */
+	value = afi_readl(pcie, AFI_PCIE_CONFIG);
+	value &= ~AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK;
+	value |= AFI_PCIE_CONFIG_PCIE_DISABLE_ALL | pcie->xbar_config;
+
+	list_for_each_entry(port, &pcie->ports, list)
+		value &= ~AFI_PCIE_CONFIG_PCIE_DISABLE(port->index);
+
+	afi_writel(pcie, value, AFI_PCIE_CONFIG);
+
+	if (soc->has_gen2) {
+		value = afi_readl(pcie, AFI_FUSE);
+		value &= ~AFI_FUSE_PCIE_T0_GEN2_DIS;
+		afi_writel(pcie, value, AFI_FUSE);
+	} else {
+		value = afi_readl(pcie, AFI_FUSE);
+		value |= AFI_FUSE_PCIE_T0_GEN2_DIS;
+		afi_writel(pcie, value, AFI_FUSE);
+	}
+
+	if (!pcie->phy)
+		err = tegra_pcie_phy_enable(pcie);
+	else
+		err = phy_power_on(pcie->phy);
+
+	if (err < 0) {
+		dev_err(pcie->dev, "failed to power on PHY: %d\n", err);
+		return err;
+	}
+
 	/* take the PCIe interface module out of reset */
 	reset_control_deassert(pcie->pcie_xrst);
 
@@ -899,6 +1001,10 @@ static void tegra_pcie_power_off(struct tegra_pcie *pcie)
 
 	/* TODO: disable and unprepare clocks? */
 
+	err = phy_power_off(pcie->phy);
+	if (err < 0)
+		dev_warn(pcie->dev, "failed to power off PHY: %d\n", err);
+
 	reset_control_assert(pcie->pcie_xrst);
 	reset_control_assert(pcie->afi_rst);
 	reset_control_assert(pcie->pex_rst);
@@ -1020,6 +1126,19 @@ static int tegra_pcie_get_resources(struct tegra_pcie *pcie)
 		return err;
 	}
 
+	pcie->phy = devm_phy_optional_get(pcie->dev, "pcie");
+	if (IS_ERR(pcie->phy)) {
+		err = PTR_ERR(pcie->phy);
+		dev_err(&pdev->dev, "failed to get PHY: %d\n", err);
+		return err;
+	}
+
+	err = phy_init(pcie->phy);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to initialize PHY: %d\n", err);
+		return err;
+	}
+
 	err = tegra_pcie_power_on(pcie);
 	if (err) {
 		dev_err(&pdev->dev, "failed to power up: %d\n", err);
@@ -1078,10 +1197,17 @@ poweroff:
 
 static int tegra_pcie_put_resources(struct tegra_pcie *pcie)
 {
+	int err;
+
 	if (pcie->irq > 0)
 		free_irq(pcie->irq, pcie);
 
 	tegra_pcie_power_off(pcie);
+
+	err = phy_exit(pcie->phy);
+	if (err < 0)
+		dev_err(pcie->dev, "failed to teardown PHY: %d\n", err);
+
 	return 0;
 }
 
@@ -1170,8 +1296,10 @@ static int tegra_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
 		return hwirq;
 
 	irq = irq_create_mapping(msi->domain, hwirq);
-	if (!irq)
+	if (!irq) {
+		tegra_msi_free(msi, hwirq);
 		return -EINVAL;
+	}
 
 	irq_set_msi_desc(irq, desc);
 
@@ -1189,8 +1317,10 @@ static void tegra_msi_teardown_irq(struct msi_chip *chip, unsigned int irq)
 {
 	struct tegra_msi *msi = to_tegra_msi(chip);
 	struct irq_data *d = irq_get_irq_data(irq);
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 
-	tegra_msi_free(msi, d->hwirq);
+	irq_dispose_mapping(irq);
+	tegra_msi_free(msi, hwirq);
 }
 
 static struct irq_chip tegra_msi_irq_chip = {
@@ -1327,7 +1457,19 @@ static int tegra_pcie_get_xbar_config(struct tegra_pcie *pcie, u32 lanes,
 {
 	struct device_node *np = pcie->dev->of_node;
 
-	if (of_device_is_compatible(np, "nvidia,tegra30-pcie")) {
+	if (of_device_is_compatible(np, "nvidia,tegra124-pcie")) {
+		switch (lanes) {
+		case 0x0000104:
+			dev_info(pcie->dev, "4x1, 1x1 configuration\n");
+			*xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_X4_X1;
+			return 0;
+
+		case 0x0000102:
+			dev_info(pcie->dev, "2x1, 1x1 configuration\n");
+			*xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_X2_X1;
+			return 0;
+		}
+	} else if (of_device_is_compatible(np, "nvidia,tegra30-pcie")) {
 		switch (lanes) {
 		case 0x00000204:
 			dev_info(pcie->dev, "4x1, 2x1 configuration\n");
@@ -1435,7 +1577,23 @@ static int tegra_pcie_get_regulators(struct tegra_pcie *pcie, u32 lane_mask)
 	struct device_node *np = pcie->dev->of_node;
 	unsigned int i = 0;
 
-	if (of_device_is_compatible(np, "nvidia,tegra30-pcie")) {
+	if (of_device_is_compatible(np, "nvidia,tegra124-pcie")) {
+		pcie->num_supplies = 7;
+
+		pcie->supplies = devm_kcalloc(pcie->dev, pcie->num_supplies,
+					      sizeof(*pcie->supplies),
+					      GFP_KERNEL);
+		if (!pcie->supplies)
+			return -ENOMEM;
+
+		pcie->supplies[i++].supply = "avddio-pex";
+		pcie->supplies[i++].supply = "dvddio-pex";
+		pcie->supplies[i++].supply = "avdd-pex-pll";
+		pcie->supplies[i++].supply = "hvdd-pex";
+		pcie->supplies[i++].supply = "hvdd-pex-pll-e";
+		pcie->supplies[i++].supply = "vddio-pex-ctl";
+		pcie->supplies[i++].supply = "avdd-pll-erefe";
+	} else if (of_device_is_compatible(np, "nvidia,tegra30-pcie")) {
 		bool need_pexa = false, need_pexb = false;
 
 		/* VDD_PEXA and AVDD_PEXA supply lanes 0 to 3 */
@@ -1514,32 +1672,50 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 	struct resource res;
 	int err;
 
+	memset(&pcie->all, 0, sizeof(pcie->all));
+	pcie->all.flags = IORESOURCE_MEM;
+	pcie->all.name = np->full_name;
+	pcie->all.start = ~0;
+	pcie->all.end = 0;
+
 	if (of_pci_range_parser_init(&parser, np)) {
 		dev_err(pcie->dev, "missing \"ranges\" property\n");
 		return -EINVAL;
 	}
 
 	for_each_of_pci_range(&parser, &range) {
-		of_pci_range_to_resource(&range, np, &res);
+		err = of_pci_range_to_resource(&range, np, &res);
+		if (err < 0)
+			return err;
 
 		switch (res.flags & IORESOURCE_TYPE_BITS) {
 		case IORESOURCE_IO:
 			memcpy(&pcie->io, &res, sizeof(res));
-			pcie->io.name = "I/O";
+			pcie->io.name = np->full_name;
 			break;
 
 		case IORESOURCE_MEM:
 			if (res.flags & IORESOURCE_PREFETCH) {
 				memcpy(&pcie->prefetch, &res, sizeof(res));
-				pcie->prefetch.name = "PREFETCH";
+				pcie->prefetch.name = "prefetchable";
 			} else {
 				memcpy(&pcie->mem, &res, sizeof(res));
-				pcie->mem.name = "MEM";
+				pcie->mem.name = "non-prefetchable";
 			}
 			break;
 		}
+
+		if (res.start <= pcie->all.start)
+			pcie->all.start = res.start;
+
+		if (res.end >= pcie->all.end)
+			pcie->all.end = res.end;
 	}
 
+	err = devm_request_resource(pcie->dev, &iomem_resource, &pcie->all);
+	if (err < 0)
+		return err;
+
 	err = of_pci_parse_bus_range(np, &pcie->busn);
 	if (err < 0) {
 		dev_err(pcie->dev, "failed to parse ranges property: %d\n",
@@ -1641,6 +1817,12 @@ static bool tegra_pcie_port_check_link(struct tegra_pcie_port *port)
 	unsigned int retries = 3;
 	unsigned long value;
 
+	/* override presence detection */
+	value = readl(port->base + RP_PRIV_MISC);
+	value &= ~RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT;
+	value |= RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT;
+	writel(value, port->base + RP_PRIV_MISC);
+
 	do {
 		unsigned int timeout = TEGRA_PCIE_LINKUP_TIMEOUT;
 
@@ -1721,6 +1903,7 @@ static const struct tegra_pcie_soc_data tegra20_pcie_data = {
 	.has_pex_bias_ctrl = false,
 	.has_intr_prsnt_sense = false,
 	.has_cml_clk = false,
+	.has_gen2 = false,
 };
 
 static const struct tegra_pcie_soc_data tegra30_pcie_data = {
@@ -1732,9 +1915,23 @@ static const struct tegra_pcie_soc_data tegra30_pcie_data = {
 	.has_pex_bias_ctrl = true,
 	.has_intr_prsnt_sense = true,
 	.has_cml_clk = true,
+	.has_gen2 = false,
+};
+
+static const struct tegra_pcie_soc_data tegra124_pcie_data = {
+	.num_ports = 2,
+	.msi_base_shift = 8,
+	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
+	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
+	.has_pex_clkreq_en = true,
+	.has_pex_bias_ctrl = true,
+	.has_intr_prsnt_sense = true,
+	.has_cml_clk = true,
+	.has_gen2 = true,
 };
 
 static const struct of_device_id tegra_pcie_of_match[] = {
+	{ .compatible = "nvidia,tegra124-pcie", .data = &tegra124_pcie_data },
 	{ .compatible = "nvidia,tegra30-pcie", .data = &tegra30_pcie_data },
 	{ .compatible = "nvidia,tegra20-pcie", .data = &tegra20_pcie_data },
 	{ },
diff --git a/drivers/pci/host/pci-xgene.c b/drivers/pci/host/pci-xgene.c
new file mode 100644
index 000000000000..9ecabfa8c634
--- /dev/null
+++ b/drivers/pci/host/pci-xgene.c
@@ -0,0 +1,659 @@
+/**
+ * APM X-Gene PCIe Driver
+ *
+ * Copyright (c) 2014 Applied Micro Circuits Corporation.
+ *
+ * Author: Tanmay Inamdar <tinamdar@apm.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/clk-private.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/jiffies.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#define PCIECORE_CTLANDSTATUS		0x50
+#define PIM1_1L				0x80
+#define IBAR2				0x98
+#define IR2MSK				0x9c
+#define PIM2_1L				0xa0
+#define IBAR3L				0xb4
+#define IR3MSKL				0xbc
+#define PIM3_1L				0xc4
+#define OMR1BARL			0x100
+#define OMR2BARL			0x118
+#define OMR3BARL			0x130
+#define CFGBARL				0x154
+#define CFGBARH				0x158
+#define CFGCTL				0x15c
+#define RTDID				0x160
+#define BRIDGE_CFG_0			0x2000
+#define BRIDGE_CFG_4			0x2010
+#define BRIDGE_STATUS_0			0x2600
+
+#define LINK_UP_MASK			0x00000100
+#define AXI_EP_CFG_ACCESS		0x10000
+#define EN_COHERENCY			0xF0000000
+#define EN_REG				0x00000001
+#define OB_LO_IO			0x00000002
+#define XGENE_PCIE_VENDORID		0x10E8
+#define XGENE_PCIE_DEVICEID		0xE004
+#define SZ_1T				(SZ_1G*1024ULL)
+#define PIPE_PHY_RATE_RD(src)		((0xc000 & (u32)(src)) >> 0xe)
+
+struct xgene_pcie_port {
+	struct device_node	*node;
+	struct device		*dev;
+	struct clk		*clk;
+	void __iomem		*csr_base;
+	void __iomem		*cfg_base;
+	unsigned long		cfg_addr;
+	bool			link_up;
+};
+
+static inline u32 pcie_bar_low_val(u32 addr, u32 flags)
+{
+	return (addr & PCI_BASE_ADDRESS_MEM_MASK) | flags;
+}
+
+/* PCIe Configuration Out/In */
+static inline void xgene_pcie_cfg_out32(void __iomem *addr, int offset, u32 val)
+{
+	writel(val, addr + offset);
+}
+
+static inline void xgene_pcie_cfg_out16(void __iomem *addr, int offset, u16 val)
+{
+	u32 val32 = readl(addr + (offset & ~0x3));
+
+	switch (offset & 0x3) {
+	case 2:
+		val32 &= ~0xFFFF0000;
+		val32 |= (u32)val << 16;
+		break;
+	case 0:
+	default:
+		val32 &= ~0xFFFF;
+		val32 |= val;
+		break;
+	}
+	writel(val32, addr + (offset & ~0x3));
+}
+
+static inline void xgene_pcie_cfg_out8(void __iomem *addr, int offset, u8 val)
+{
+	u32 val32 = readl(addr + (offset & ~0x3));
+
+	switch (offset & 0x3) {
+	case 0:
+		val32 &= ~0xFF;
+		val32 |= val;
+		break;
+	case 1:
+		val32 &= ~0xFF00;
+		val32 |= (u32)val << 8;
+		break;
+	case 2:
+		val32 &= ~0xFF0000;
+		val32 |= (u32)val << 16;
+		break;
+	case 3:
+	default:
+		val32 &= ~0xFF000000;
+		val32 |= (u32)val << 24;
+		break;
+	}
+	writel(val32, addr + (offset & ~0x3));
+}
+
+static inline void xgene_pcie_cfg_in32(void __iomem *addr, int offset, u32 *val)
+{
+	*val = readl(addr + offset);
+}
+
+static inline void xgene_pcie_cfg_in16(void __iomem *addr, int offset, u32 *val)
+{
+	*val = readl(addr + (offset & ~0x3));
+
+	switch (offset & 0x3) {
+	case 2:
+		*val >>= 16;
+		break;
+	}
+
+	*val &= 0xFFFF;
+}
+
+static inline void xgene_pcie_cfg_in8(void __iomem *addr, int offset, u32 *val)
+{
+	*val = readl(addr + (offset & ~0x3));
+
+	switch (offset & 0x3) {
+	case 3:
+		*val = *val >> 24;
+		break;
+	case 2:
+		*val = *val >> 16;
+		break;
+	case 1:
+		*val = *val >> 8;
+		break;
+	}
+	*val &= 0xFF;
+}
+
+/*
+ * When the address bit [17:16] is 2'b01, the Configuration access will be
+ * treated as Type 1 and it will be forwarded to external PCIe device.
+ */
+static void __iomem *xgene_pcie_get_cfg_base(struct pci_bus *bus)
+{
+	struct xgene_pcie_port *port = bus->sysdata;
+
+	if (bus->number >= (bus->primary + 1))
+		return port->cfg_base + AXI_EP_CFG_ACCESS;
+
+	return port->cfg_base;
+}
+
+/*
+ * For Configuration request, RTDID register is used as Bus Number,
+ * Device Number and Function number of the header fields.
+ */
+static void xgene_pcie_set_rtdid_reg(struct pci_bus *bus, uint devfn)
+{
+	struct xgene_pcie_port *port = bus->sysdata;
+	unsigned int b, d, f;
+	u32 rtdid_val = 0;
+
+	b = bus->number;
+	d = PCI_SLOT(devfn);
+	f = PCI_FUNC(devfn);
+
+	if (!pci_is_root_bus(bus))
+		rtdid_val = (b << 8) | (d << 3) | f;
+
+	writel(rtdid_val, port->csr_base + RTDID);
+	/* read the register back to ensure flush */
+	readl(port->csr_base + RTDID);
+}
+
+/*
+ * X-Gene PCIe port uses BAR0-BAR1 of RC's configuration space as
+ * the translation from PCI bus to native BUS.  Entire DDR region
+ * is mapped into PCIe space using these registers, so it can be
+ * reached by DMA from EP devices.  The BAR0/1 of bridge should be
+ * hidden during enumeration to avoid the sizing and resource allocation
+ * by PCIe core.
+ */
+static bool xgene_pcie_hide_rc_bars(struct pci_bus *bus, int offset)
+{
+	if (pci_is_root_bus(bus) && ((offset == PCI_BASE_ADDRESS_0) ||
+				     (offset == PCI_BASE_ADDRESS_1)))
+		return true;
+
+	return false;
+}
+
+static int xgene_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
+				  int offset, int len, u32 *val)
+{
+	struct xgene_pcie_port *port = bus->sysdata;
+	void __iomem *addr;
+
+	if ((pci_is_root_bus(bus) && devfn != 0) || !port->link_up)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (xgene_pcie_hide_rc_bars(bus, offset)) {
+		*val = 0;
+		return PCIBIOS_SUCCESSFUL;
+	}
+
+	xgene_pcie_set_rtdid_reg(bus, devfn);
+	addr = xgene_pcie_get_cfg_base(bus);
+	switch (len) {
+	case 1:
+		xgene_pcie_cfg_in8(addr, offset, val);
+		break;
+	case 2:
+		xgene_pcie_cfg_in16(addr, offset, val);
+		break;
+	default:
+		xgene_pcie_cfg_in32(addr, offset, val);
+		break;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int xgene_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
+				   int offset, int len, u32 val)
+{
+	struct xgene_pcie_port *port = bus->sysdata;
+	void __iomem *addr;
+
+	if ((pci_is_root_bus(bus) && devfn != 0) || !port->link_up)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (xgene_pcie_hide_rc_bars(bus, offset))
+		return PCIBIOS_SUCCESSFUL;
+
+	xgene_pcie_set_rtdid_reg(bus, devfn);
+	addr = xgene_pcie_get_cfg_base(bus);
+	switch (len) {
+	case 1:
+		xgene_pcie_cfg_out8(addr, offset, (u8)val);
+		break;
+	case 2:
+		xgene_pcie_cfg_out16(addr, offset, (u16)val);
+		break;
+	default:
+		xgene_pcie_cfg_out32(addr, offset, val);
+		break;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops xgene_pcie_ops = {
+	.read = xgene_pcie_read_config,
+	.write = xgene_pcie_write_config
+};
+
+static u64 xgene_pcie_set_ib_mask(void __iomem *csr_base, u32 addr,
+				  u32 flags, u64 size)
+{
+	u64 mask = (~(size - 1) & PCI_BASE_ADDRESS_MEM_MASK) | flags;
+	u32 val32 = 0;
+	u32 val;
+
+	val32 = readl(csr_base + addr);
+	val = (val32 & 0x0000ffff) | (lower_32_bits(mask) << 16);
+	writel(val, csr_base + addr);
+
+	val32 = readl(csr_base + addr + 0x04);
+	val = (val32 & 0xffff0000) | (lower_32_bits(mask) >> 16);
+	writel(val, csr_base + addr + 0x04);
+
+	val32 = readl(csr_base + addr + 0x04);
+	val = (val32 & 0x0000ffff) | (upper_32_bits(mask) << 16);
+	writel(val, csr_base + addr + 0x04);
+
+	val32 = readl(csr_base + addr + 0x08);
+	val = (val32 & 0xffff0000) | (upper_32_bits(mask) >> 16);
+	writel(val, csr_base + addr + 0x08);
+
+	return mask;
+}
+
+static void xgene_pcie_linkup(struct xgene_pcie_port *port,
+				   u32 *lanes, u32 *speed)
+{
+	void __iomem *csr_base = port->csr_base;
+	u32 val32;
+
+	port->link_up = false;
+	val32 = readl(csr_base + PCIECORE_CTLANDSTATUS);
+	if (val32 & LINK_UP_MASK) {
+		port->link_up = true;
+		*speed = PIPE_PHY_RATE_RD(val32);
+		val32 = readl(csr_base + BRIDGE_STATUS_0);
+		*lanes = val32 >> 26;
+	}
+}
+
+static int xgene_pcie_init_port(struct xgene_pcie_port *port)
+{
+	int rc;
+
+	port->clk = clk_get(port->dev, NULL);
+	if (IS_ERR(port->clk)) {
+		dev_err(port->dev, "clock not available\n");
+		return -ENODEV;
+	}
+
+	rc = clk_prepare_enable(port->clk);
+	if (rc) {
+		dev_err(port->dev, "clock enable failed\n");
+		return rc;
+	}
+
+	return 0;
+}
+
+static int xgene_pcie_map_reg(struct xgene_pcie_port *port,
+			      struct platform_device *pdev)
+{
+	struct resource *res;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "csr");
+	port->csr_base = devm_ioremap_resource(port->dev, res);
+	if (IS_ERR(port->csr_base))
+		return PTR_ERR(port->csr_base);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg");
+	port->cfg_base = devm_ioremap_resource(port->dev, res);
+	if (IS_ERR(port->cfg_base))
+		return PTR_ERR(port->cfg_base);
+	port->cfg_addr = res->start;
+
+	return 0;
+}
+
+static void xgene_pcie_setup_ob_reg(struct xgene_pcie_port *port,
+				    struct resource *res, u32 offset,
+				    u64 cpu_addr, u64 pci_addr)
+{
+	void __iomem *base = port->csr_base + offset;
+	resource_size_t size = resource_size(res);
+	u64 restype = resource_type(res);
+	u64 mask = 0;
+	u32 min_size;
+	u32 flag = EN_REG;
+
+	if (restype == IORESOURCE_MEM) {
+		min_size = SZ_128M;
+	} else {
+		min_size = 128;
+		flag |= OB_LO_IO;
+	}
+
+	if (size >= min_size)
+		mask = ~(size - 1) | flag;
+	else
+		dev_warn(port->dev, "res size 0x%llx less than minimum 0x%x\n",
+			 (u64)size, min_size);
+
+	writel(lower_32_bits(cpu_addr), base);
+	writel(upper_32_bits(cpu_addr), base + 0x04);
+	writel(lower_32_bits(mask), base + 0x08);
+	writel(upper_32_bits(mask), base + 0x0c);
+	writel(lower_32_bits(pci_addr), base + 0x10);
+	writel(upper_32_bits(pci_addr), base + 0x14);
+}
+
+static void xgene_pcie_setup_cfg_reg(void __iomem *csr_base, u64 addr)
+{
+	writel(lower_32_bits(addr), csr_base + CFGBARL);
+	writel(upper_32_bits(addr), csr_base + CFGBARH);
+	writel(EN_REG, csr_base + CFGCTL);
+}
+
+static int xgene_pcie_map_ranges(struct xgene_pcie_port *port,
+				 struct list_head *res,
+				 resource_size_t io_base)
+{
+	struct pci_host_bridge_window *window;
+	struct device *dev = port->dev;
+	int ret;
+
+	list_for_each_entry(window, res, list) {
+		struct resource *res = window->res;
+		u64 restype = resource_type(res);
+
+		dev_dbg(port->dev, "%pR\n", res);
+
+		switch (restype) {
+		case IORESOURCE_IO:
+			xgene_pcie_setup_ob_reg(port, res, OMR3BARL, io_base,
+						res->start - window->offset);
+			ret = pci_remap_iospace(res, io_base);
+			if (ret < 0)
+				return ret;
+			break;
+		case IORESOURCE_MEM:
+			xgene_pcie_setup_ob_reg(port, res, OMR1BARL, res->start,
+						res->start - window->offset);
+			break;
+		case IORESOURCE_BUS:
+			break;
+		default:
+			dev_err(dev, "invalid resource %pR\n", res);
+			return -EINVAL;
+		}
+	}
+	xgene_pcie_setup_cfg_reg(port->csr_base, port->cfg_addr);
+
+	return 0;
+}
+
+static void xgene_pcie_setup_pims(void *addr, u64 pim, u64 size)
+{
+	writel(lower_32_bits(pim), addr);
+	writel(upper_32_bits(pim) | EN_COHERENCY, addr + 0x04);
+	writel(lower_32_bits(size), addr + 0x10);
+	writel(upper_32_bits(size), addr + 0x14);
+}
+
+/*
+ * X-Gene PCIe support maximum 3 inbound memory regions
+ * This function helps to select a region based on size of region
+ */
+static int xgene_pcie_select_ib_reg(u8 *ib_reg_mask, u64 size)
+{
+	if ((size > 4) && (size < SZ_16M) && !(*ib_reg_mask & (1 << 1))) {
+		*ib_reg_mask |= (1 << 1);
+		return 1;
+	}
+
+	if ((size > SZ_1K) && (size < SZ_1T) && !(*ib_reg_mask & (1 << 0))) {
+		*ib_reg_mask |= (1 << 0);
+		return 0;
+	}
+
+	if ((size > SZ_1M) && (size < SZ_1T) && !(*ib_reg_mask & (1 << 2))) {
+		*ib_reg_mask |= (1 << 2);
+		return 2;
+	}
+
+	return -EINVAL;
+}
+
+static void xgene_pcie_setup_ib_reg(struct xgene_pcie_port *port,
+				    struct of_pci_range *range, u8 *ib_reg_mask)
+{
+	void __iomem *csr_base = port->csr_base;
+	void __iomem *cfg_base = port->cfg_base;
+	void *bar_addr;
+	void *pim_addr;
+	u64 cpu_addr = range->cpu_addr;
+	u64 pci_addr = range->pci_addr;
+	u64 size = range->size;
+	u64 mask = ~(size - 1) | EN_REG;
+	u32 flags = PCI_BASE_ADDRESS_MEM_TYPE_64;
+	u32 bar_low;
+	int region;
+
+	region = xgene_pcie_select_ib_reg(ib_reg_mask, range->size);
+	if (region < 0) {
+		dev_warn(port->dev, "invalid pcie dma-range config\n");
+		return;
+	}
+
+	if (range->flags & IORESOURCE_PREFETCH)
+		flags |= PCI_BASE_ADDRESS_MEM_PREFETCH;
+
+	bar_low = pcie_bar_low_val((u32)cpu_addr, flags);
+	switch (region) {
+	case 0:
+		xgene_pcie_set_ib_mask(csr_base, BRIDGE_CFG_4, flags, size);
+		bar_addr = cfg_base + PCI_BASE_ADDRESS_0;
+		writel(bar_low, bar_addr);
+		writel(upper_32_bits(cpu_addr), bar_addr + 0x4);
+		pim_addr = csr_base + PIM1_1L;
+		break;
+	case 1:
+		bar_addr = csr_base + IBAR2;
+		writel(bar_low, bar_addr);
+		writel(lower_32_bits(mask), csr_base + IR2MSK);
+		pim_addr = csr_base + PIM2_1L;
+		break;
+	case 2:
+		bar_addr = csr_base + IBAR3L;
+		writel(bar_low, bar_addr);
+		writel(upper_32_bits(cpu_addr), bar_addr + 0x4);
+		writel(lower_32_bits(mask), csr_base + IR3MSKL);
+		writel(upper_32_bits(mask), csr_base + IR3MSKL + 0x4);
+		pim_addr = csr_base + PIM3_1L;
+		break;
+	}
+
+	xgene_pcie_setup_pims(pim_addr, pci_addr, ~(size - 1));
+}
+
+static int pci_dma_range_parser_init(struct of_pci_range_parser *parser,
+				     struct device_node *node)
+{
+	const int na = 3, ns = 2;
+	int rlen;
+
+	parser->node = node;
+	parser->pna = of_n_addr_cells(node);
+	parser->np = parser->pna + na + ns;
+
+	parser->range = of_get_property(node, "dma-ranges", &rlen);
+	if (!parser->range)
+		return -ENOENT;
+	parser->end = parser->range + rlen / sizeof(__be32);
+
+	return 0;
+}
+
+static int xgene_pcie_parse_map_dma_ranges(struct xgene_pcie_port *port)
+{
+	struct device_node *np = port->node;
+	struct of_pci_range range;
+	struct of_pci_range_parser parser;
+	struct device *dev = port->dev;
+	u8 ib_reg_mask = 0;
+
+	if (pci_dma_range_parser_init(&parser, np)) {
+		dev_err(dev, "missing dma-ranges property\n");
+		return -EINVAL;
+	}
+
+	/* Get the dma-ranges from DT */
+	for_each_of_pci_range(&parser, &range) {
+		u64 end = range.cpu_addr + range.size - 1;
+
+		dev_dbg(port->dev, "0x%08x 0x%016llx..0x%016llx -> 0x%016llx\n",
+			range.flags, range.cpu_addr, end, range.pci_addr);
+		xgene_pcie_setup_ib_reg(port, &range, &ib_reg_mask);
+	}
+	return 0;
+}
+
+/* clear BAR configuration which was done by firmware */
+static void xgene_pcie_clear_config(struct xgene_pcie_port *port)
+{
+	int i;
+
+	for (i = PIM1_1L; i <= CFGCTL; i += 4)
+		writel(0x0, port->csr_base + i);
+}
+
+static int xgene_pcie_setup(struct xgene_pcie_port *port,
+			    struct list_head *res,
+			    resource_size_t io_base)
+{
+	u32 val, lanes = 0, speed = 0;
+	int ret;
+
+	xgene_pcie_clear_config(port);
+
+	/* setup the vendor and device IDs correctly */
+	val = (XGENE_PCIE_DEVICEID << 16) | XGENE_PCIE_VENDORID;
+	writel(val, port->csr_base + BRIDGE_CFG_0);
+
+	ret = xgene_pcie_map_ranges(port, res, io_base);
+	if (ret)
+		return ret;
+
+	ret = xgene_pcie_parse_map_dma_ranges(port);
+	if (ret)
+		return ret;
+
+	xgene_pcie_linkup(port, &lanes, &speed);
+	if (!port->link_up)
+		dev_info(port->dev, "(rc) link down\n");
+	else
+		dev_info(port->dev, "(rc) x%d gen-%d link up\n",
+				lanes, speed + 1);
+	return 0;
+}
+
+static int xgene_pcie_probe_bridge(struct platform_device *pdev)
+{
+	struct device_node *dn = pdev->dev.of_node;
+	struct xgene_pcie_port *port;
+	resource_size_t iobase = 0;
+	struct pci_bus *bus;
+	int ret;
+	LIST_HEAD(res);
+
+	port = devm_kzalloc(&pdev->dev, sizeof(*port), GFP_KERNEL);
+	if (!port)
+		return -ENOMEM;
+	port->node = of_node_get(pdev->dev.of_node);
+	port->dev = &pdev->dev;
+
+	ret = xgene_pcie_map_reg(port, pdev);
+	if (ret)
+		return ret;
+
+	ret = xgene_pcie_init_port(port);
+	if (ret)
+		return ret;
+
+	ret = of_pci_get_host_bridge_resources(dn, 0, 0xff, &res, &iobase);
+	if (ret)
+		return ret;
+
+	ret = xgene_pcie_setup(port, &res, iobase);
+	if (ret)
+		return ret;
+
+	bus = pci_scan_root_bus(&pdev->dev, 0, &xgene_pcie_ops, port, &res);
+	if (!bus)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, port);
+	return 0;
+}
+
+static const struct of_device_id xgene_pcie_match_table[] = {
+	{.compatible = "apm,xgene-pcie",},
+	{},
+};
+
+static struct platform_driver xgene_pcie_driver = {
+	.driver = {
+		   .name = "xgene-pcie",
+		   .owner = THIS_MODULE,
+		   .of_match_table = of_match_ptr(xgene_pcie_match_table),
+	},
+	.probe = xgene_pcie_probe_bridge,
+};
+module_platform_driver(xgene_pcie_driver);
+
+MODULE_AUTHOR("Tanmay Inamdar <tinamdar@apm.com>");
+MODULE_DESCRIPTION("APM X-Gene PCIe driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index 52bd3a143563..dfed00aa3ac0 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -73,6 +73,8 @@ static unsigned long global_io_offset;
 
 static inline struct pcie_port *sys_to_pcie(struct pci_sys_data *sys)
 {
+	BUG_ON(!sys->private_data);
+
 	return sys->private_data;
 }
 
@@ -194,30 +196,6 @@ void dw_pcie_msi_init(struct pcie_port *pp)
 	dw_pcie_wr_own_conf(pp, PCIE_MSI_ADDR_HI, 4, 0);
 }
 
-static int find_valid_pos0(struct pcie_port *pp, int msgvec, int pos, int *pos0)
-{
-	int flag = 1;
-
-	do {
-		pos = find_next_zero_bit(pp->msi_irq_in_use,
-				MAX_MSI_IRQS, pos);
-		/*if you have reached to the end then get out from here.*/
-		if (pos == MAX_MSI_IRQS)
-			return -ENOSPC;
-		/*
-		 * Check if this position is at correct offset.nvec is always a
-		 * power of two. pos0 must be nvec bit aligned.
-		 */
-		if (pos % msgvec)
-			pos += msgvec - (pos % msgvec);
-		else
-			flag = 0;
-	} while (flag);
-
-	*pos0 = pos;
-	return 0;
-}
-
 static void dw_pcie_msi_clear_irq(struct pcie_port *pp, int irq)
 {
 	unsigned int res, bit, val;
@@ -236,13 +214,14 @@ static void clear_irq_range(struct pcie_port *pp, unsigned int irq_base,
 
 	for (i = 0; i < nvec; i++) {
 		irq_set_msi_desc_off(irq_base, i, NULL);
-		clear_bit(pos + i, pp->msi_irq_in_use);
 		/* Disable corresponding interrupt on MSI controller */
 		if (pp->ops->msi_clear_irq)
 			pp->ops->msi_clear_irq(pp, pos + i);
 		else
 			dw_pcie_msi_clear_irq(pp, pos + i);
 	}
+
+	bitmap_release_region(pp->msi_irq_in_use, pos, order_base_2(nvec));
 }
 
 static void dw_pcie_msi_set_irq(struct pcie_port *pp, int irq)
@@ -258,31 +237,13 @@ static void dw_pcie_msi_set_irq(struct pcie_port *pp, int irq)
 
 static int assign_irq(int no_irqs, struct msi_desc *desc, int *pos)
 {
-	int irq, pos0, pos1, i;
+	int irq, pos0, i;
 	struct pcie_port *pp = sys_to_pcie(desc->dev->bus->sysdata);
 
-	if (!pp) {
-		BUG();
-		return -EINVAL;
-	}
-
-	pos0 = find_first_zero_bit(pp->msi_irq_in_use,
-			MAX_MSI_IRQS);
-	if (pos0 % no_irqs) {
-		if (find_valid_pos0(pp, no_irqs, pos0, &pos0))
-			goto no_valid_irq;
-	}
-	if (no_irqs > 1) {
-		pos1 = find_next_bit(pp->msi_irq_in_use,
-				MAX_MSI_IRQS, pos0);
-		/* there must be nvec number of consecutive free bits */
-		while ((pos1 - pos0) < no_irqs) {
-			if (find_valid_pos0(pp, no_irqs, pos1, &pos0))
-				goto no_valid_irq;
-			pos1 = find_next_bit(pp->msi_irq_in_use,
-					MAX_MSI_IRQS, pos0);
-		}
-	}
+	pos0 = bitmap_find_free_region(pp->msi_irq_in_use, MAX_MSI_IRQS,
+				       order_base_2(no_irqs));
+	if (pos0 < 0)
+		goto no_valid_irq;
 
 	irq = irq_find_mapping(pp->irq_domain, pos0);
 	if (!irq)
@@ -300,7 +261,6 @@ static int assign_irq(int no_irqs, struct msi_desc *desc, int *pos)
 			clear_irq_range(pp, irq, i, pos0);
 			goto no_valid_irq;
 		}
-		set_bit(pos0 + i, pp->msi_irq_in_use);
 		/*Enable corresponding interrupt in MSI interrupt controller */
 		if (pp->ops->msi_set_irq)
 			pp->ops->msi_set_irq(pp, pos0 + i);
@@ -316,69 +276,28 @@ no_valid_irq:
 	return -ENOSPC;
 }
 
-static void clear_irq(unsigned int irq)
-{
-	unsigned int pos, nvec;
-	struct msi_desc *msi;
-	struct pcie_port *pp;
-	struct irq_data *data = irq_get_irq_data(irq);
-
-	/* get the port structure */
-	msi = irq_data_get_msi(data);
-	pp = sys_to_pcie(msi->dev->bus->sysdata);
-	if (!pp) {
-		BUG();
-		return;
-	}
-
-	/* undo what was done in assign_irq */
-	pos = data->hwirq;
-	nvec = 1 << msi->msi_attrib.multiple;
-
-	clear_irq_range(pp, irq, nvec, pos);
-
-	/* all irqs cleared; reset attributes */
-	msi->irq = 0;
-	msi->msi_attrib.multiple = 0;
-}
-
 static int dw_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
 			struct msi_desc *desc)
 {
-	int irq, pos, msgvec;
-	u16 msg_ctr;
+	int irq, pos;
 	struct msi_msg msg;
 	struct pcie_port *pp = sys_to_pcie(pdev->bus->sysdata);
 
-	if (!pp) {
-		BUG();
-		return -EINVAL;
-	}
-
-	pci_read_config_word(pdev, desc->msi_attrib.pos+PCI_MSI_FLAGS,
-				&msg_ctr);
-	msgvec = (msg_ctr&PCI_MSI_FLAGS_QSIZE) >> 4;
-	if (msgvec == 0)
-		msgvec = (msg_ctr & PCI_MSI_FLAGS_QMASK) >> 1;
-	if (msgvec > 5)
-		msgvec = 0;
-
-	irq = assign_irq((1 << msgvec), desc, &pos);
+	irq = assign_irq(1, desc, &pos);
 	if (irq < 0)
 		return irq;
 
-	/*
-	 * write_msi_msg() will update PCI_MSI_FLAGS so there is
-	 * no need to explicitly call pci_write_config_word().
-	 */
-	desc->msi_attrib.multiple = msgvec;
-
-	if (pp->ops->get_msi_data)
-		msg.address_lo = pp->ops->get_msi_data(pp);
+	if (pp->ops->get_msi_addr)
+		msg.address_lo = pp->ops->get_msi_addr(pp);
 	else
 		msg.address_lo = virt_to_phys((void *)pp->msi_data);
 	msg.address_hi = 0x0;
-	msg.data = pos;
+
+	if (pp->ops->get_msi_data)
+		msg.data = pp->ops->get_msi_data(pp, pos);
+	else
+		msg.data = pos;
+
 	write_msi_msg(irq, &msg);
 
 	return 0;
@@ -386,7 +305,11 @@ static int dw_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
 
 static void dw_msi_teardown_irq(struct msi_chip *chip, unsigned int irq)
 {
-	clear_irq(irq);
+	struct irq_data *data = irq_get_irq_data(irq);
+	struct msi_desc *msi = irq_data_get_msi(data);
+	struct pcie_port *pp = sys_to_pcie(msi->dev->bus->sysdata);
+
+	clear_irq_range(pp, irq, 1, data->hwirq);
 }
 
 static struct msi_chip dw_pcie_msi_chip = {
@@ -425,7 +348,7 @@ int __init dw_pcie_host_init(struct pcie_port *pp)
 	struct resource *cfg_res;
 	u32 val, na, ns;
 	const __be32 *addrp;
-	int i, index;
+	int i, index, ret;
 
 	/* Find the address cell size and the number of cells in order to get
 	 * the untranslated address.
@@ -435,16 +358,16 @@ int __init dw_pcie_host_init(struct pcie_port *pp)
 
 	cfg_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config");
 	if (cfg_res) {
-		pp->config.cfg0_size = resource_size(cfg_res)/2;
-		pp->config.cfg1_size = resource_size(cfg_res)/2;
+		pp->cfg0_size = resource_size(cfg_res)/2;
+		pp->cfg1_size = resource_size(cfg_res)/2;
 		pp->cfg0_base = cfg_res->start;
-		pp->cfg1_base = cfg_res->start + pp->config.cfg0_size;
+		pp->cfg1_base = cfg_res->start + pp->cfg0_size;
 
 		/* Find the untranslated configuration space address */
 		index = of_property_match_string(np, "reg-names", "config");
-		addrp = of_get_address(np, index, false, false);
+		addrp = of_get_address(np, index, NULL, NULL);
 		pp->cfg0_mod_base = of_read_number(addrp, ns);
-		pp->cfg1_mod_base = pp->cfg0_mod_base + pp->config.cfg0_size;
+		pp->cfg1_mod_base = pp->cfg0_mod_base + pp->cfg0_size;
 	} else {
 		dev_err(pp->dev, "missing *config* reg space\n");
 	}
@@ -466,9 +389,9 @@ int __init dw_pcie_host_init(struct pcie_port *pp)
 			pp->io.end = min_t(resource_size_t,
 					   IO_SPACE_LIMIT,
 					   range.pci_addr + range.size
-					   + global_io_offset);
-			pp->config.io_size = resource_size(&pp->io);
-			pp->config.io_bus_addr = range.pci_addr;
+					   + global_io_offset - 1);
+			pp->io_size = resource_size(&pp->io);
+			pp->io_bus_addr = range.pci_addr;
 			pp->io_base = range.cpu_addr;
 
 			/* Find the untranslated IO space address */
@@ -478,8 +401,8 @@ int __init dw_pcie_host_init(struct pcie_port *pp)
 		if (restype == IORESOURCE_MEM) {
 			of_pci_range_to_resource(&range, np, &pp->mem);
 			pp->mem.name = "MEM";
-			pp->config.mem_size = resource_size(&pp->mem);
-			pp->config.mem_bus_addr = range.pci_addr;
+			pp->mem_size = resource_size(&pp->mem);
+			pp->mem_bus_addr = range.pci_addr;
 
 			/* Find the untranslated MEM space address */
 			pp->mem_mod_base = of_read_number(parser.range -
@@ -487,19 +410,29 @@ int __init dw_pcie_host_init(struct pcie_port *pp)
 		}
 		if (restype == 0) {
 			of_pci_range_to_resource(&range, np, &pp->cfg);
-			pp->config.cfg0_size = resource_size(&pp->cfg)/2;
-			pp->config.cfg1_size = resource_size(&pp->cfg)/2;
+			pp->cfg0_size = resource_size(&pp->cfg)/2;
+			pp->cfg1_size = resource_size(&pp->cfg)/2;
 			pp->cfg0_base = pp->cfg.start;
-			pp->cfg1_base = pp->cfg.start + pp->config.cfg0_size;
+			pp->cfg1_base = pp->cfg.start + pp->cfg0_size;
 
 			/* Find the untranslated configuration space address */
 			pp->cfg0_mod_base = of_read_number(parser.range -
 							   parser.np + na, ns);
 			pp->cfg1_mod_base = pp->cfg0_mod_base +
-					    pp->config.cfg0_size;
+					    pp->cfg0_size;
 		}
 	}
 
+	ret = of_pci_parse_bus_range(np, &pp->busn);
+	if (ret < 0) {
+		pp->busn.name = np->name;
+		pp->busn.start = 0;
+		pp->busn.end = 0xff;
+		pp->busn.flags = IORESOURCE_BUS;
+		dev_dbg(pp->dev, "failed to parse bus-range property: %d, using default %pR\n",
+			ret, &pp->busn);
+	}
+
 	if (!pp->dbi_base) {
 		pp->dbi_base = devm_ioremap(pp->dev, pp->cfg.start,
 					resource_size(&pp->cfg));
@@ -511,17 +444,22 @@ int __init dw_pcie_host_init(struct pcie_port *pp)
 
 	pp->mem_base = pp->mem.start;
 
-	pp->va_cfg0_base = devm_ioremap(pp->dev, pp->cfg0_base,
-					pp->config.cfg0_size);
 	if (!pp->va_cfg0_base) {
-		dev_err(pp->dev, "error with ioremap in function\n");
-		return -ENOMEM;
+		pp->va_cfg0_base = devm_ioremap(pp->dev, pp->cfg0_base,
+						pp->cfg0_size);
+		if (!pp->va_cfg0_base) {
+			dev_err(pp->dev, "error with ioremap in function\n");
+			return -ENOMEM;
+		}
 	}
-	pp->va_cfg1_base = devm_ioremap(pp->dev, pp->cfg1_base,
-					pp->config.cfg1_size);
+
 	if (!pp->va_cfg1_base) {
-		dev_err(pp->dev, "error with ioremap\n");
-		return -ENOMEM;
+		pp->va_cfg1_base = devm_ioremap(pp->dev, pp->cfg1_base,
+						pp->cfg1_size);
+		if (!pp->va_cfg1_base) {
+			dev_err(pp->dev, "error with ioremap\n");
+			return -ENOMEM;
+		}
 	}
 
 	if (of_property_read_u32(np, "num-lanes", &pp->lanes)) {
@@ -530,16 +468,22 @@ int __init dw_pcie_host_init(struct pcie_port *pp)
 	}
 
 	if (IS_ENABLED(CONFIG_PCI_MSI)) {
-		pp->irq_domain = irq_domain_add_linear(pp->dev->of_node,
-					MAX_MSI_IRQS, &msi_domain_ops,
-					&dw_pcie_msi_chip);
-		if (!pp->irq_domain) {
-			dev_err(pp->dev, "irq domain init failed\n");
-			return -ENXIO;
-		}
+		if (!pp->ops->msi_host_init) {
+			pp->irq_domain = irq_domain_add_linear(pp->dev->of_node,
+						MAX_MSI_IRQS, &msi_domain_ops,
+						&dw_pcie_msi_chip);
+			if (!pp->irq_domain) {
+				dev_err(pp->dev, "irq domain init failed\n");
+				return -ENXIO;
+			}
 
-		for (i = 0; i < MAX_MSI_IRQS; i++)
-			irq_create_mapping(pp->irq_domain, i);
+			for (i = 0; i < MAX_MSI_IRQS; i++)
+				irq_create_mapping(pp->irq_domain, i);
+		} else {
+			ret = pp->ops->msi_host_init(pp, &dw_pcie_msi_chip);
+			if (ret < 0)
+				return ret;
+		}
 	}
 
 	if (pp->ops->host_init)
@@ -558,7 +502,6 @@ int __init dw_pcie_host_init(struct pcie_port *pp)
 	dw_pci.private_data = (void **)&pp;
 
 	pci_common_init_dev(pp->dev, &dw_pci);
-	pci_assign_unassigned_resources();
 #ifdef CONFIG_PCI_DOMAINS
 	dw_pci.domain++;
 #endif
@@ -573,7 +516,7 @@ static void dw_pcie_prog_viewport_cfg0(struct pcie_port *pp, u32 busdev)
 			  PCIE_ATU_VIEWPORT);
 	dw_pcie_writel_rc(pp, pp->cfg0_mod_base, PCIE_ATU_LOWER_BASE);
 	dw_pcie_writel_rc(pp, (pp->cfg0_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->cfg0_mod_base + pp->config.cfg0_size - 1,
+	dw_pcie_writel_rc(pp, pp->cfg0_mod_base + pp->cfg0_size - 1,
 			  PCIE_ATU_LIMIT);
 	dw_pcie_writel_rc(pp, busdev, PCIE_ATU_LOWER_TARGET);
 	dw_pcie_writel_rc(pp, 0, PCIE_ATU_UPPER_TARGET);
@@ -589,7 +532,7 @@ static void dw_pcie_prog_viewport_cfg1(struct pcie_port *pp, u32 busdev)
 	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_CFG1, PCIE_ATU_CR1);
 	dw_pcie_writel_rc(pp, pp->cfg1_mod_base, PCIE_ATU_LOWER_BASE);
 	dw_pcie_writel_rc(pp, (pp->cfg1_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->cfg1_mod_base + pp->config.cfg1_size - 1,
+	dw_pcie_writel_rc(pp, pp->cfg1_mod_base + pp->cfg1_size - 1,
 			  PCIE_ATU_LIMIT);
 	dw_pcie_writel_rc(pp, busdev, PCIE_ATU_LOWER_TARGET);
 	dw_pcie_writel_rc(pp, 0, PCIE_ATU_UPPER_TARGET);
@@ -604,10 +547,10 @@ static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp)
 	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_MEM, PCIE_ATU_CR1);
 	dw_pcie_writel_rc(pp, pp->mem_mod_base, PCIE_ATU_LOWER_BASE);
 	dw_pcie_writel_rc(pp, (pp->mem_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->mem_mod_base + pp->config.mem_size - 1,
+	dw_pcie_writel_rc(pp, pp->mem_mod_base + pp->mem_size - 1,
 			  PCIE_ATU_LIMIT);
-	dw_pcie_writel_rc(pp, pp->config.mem_bus_addr, PCIE_ATU_LOWER_TARGET);
-	dw_pcie_writel_rc(pp, upper_32_bits(pp->config.mem_bus_addr),
+	dw_pcie_writel_rc(pp, pp->mem_bus_addr, PCIE_ATU_LOWER_TARGET);
+	dw_pcie_writel_rc(pp, upper_32_bits(pp->mem_bus_addr),
 			  PCIE_ATU_UPPER_TARGET);
 	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
 }
@@ -620,10 +563,10 @@ static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp)
 	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_IO, PCIE_ATU_CR1);
 	dw_pcie_writel_rc(pp, pp->io_mod_base, PCIE_ATU_LOWER_BASE);
 	dw_pcie_writel_rc(pp, (pp->io_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->io_mod_base + pp->config.io_size - 1,
+	dw_pcie_writel_rc(pp, pp->io_mod_base + pp->io_size - 1,
 			  PCIE_ATU_LIMIT);
-	dw_pcie_writel_rc(pp, pp->config.io_bus_addr, PCIE_ATU_LOWER_TARGET);
-	dw_pcie_writel_rc(pp, upper_32_bits(pp->config.io_bus_addr),
+	dw_pcie_writel_rc(pp, pp->io_bus_addr, PCIE_ATU_LOWER_TARGET);
+	dw_pcie_writel_rc(pp, upper_32_bits(pp->io_bus_addr),
 			  PCIE_ATU_UPPER_TARGET);
 	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
 }
@@ -707,11 +650,6 @@ static int dw_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where,
 	struct pcie_port *pp = sys_to_pcie(bus->sysdata);
 	int ret;
 
-	if (!pp) {
-		BUG();
-		return -EINVAL;
-	}
-
 	if (dw_pcie_valid_config(pp, bus, PCI_SLOT(devfn)) == 0) {
 		*val = 0xffffffff;
 		return PCIBIOS_DEVICE_NOT_FOUND;
@@ -736,11 +674,6 @@ static int dw_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	struct pcie_port *pp = sys_to_pcie(bus->sysdata);
 	int ret;
 
-	if (!pp) {
-		BUG();
-		return -EINVAL;
-	}
-
 	if (dw_pcie_valid_config(pp, bus, PCI_SLOT(devfn)) == 0)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
@@ -768,19 +701,17 @@ static int dw_pcie_setup(int nr, struct pci_sys_data *sys)
 
 	pp = sys_to_pcie(sys);
 
-	if (!pp)
-		return 0;
-
-	if (global_io_offset < SZ_1M && pp->config.io_size > 0) {
-		sys->io_offset = global_io_offset - pp->config.io_bus_addr;
+	if (global_io_offset < SZ_1M && pp->io_size > 0) {
+		sys->io_offset = global_io_offset - pp->io_bus_addr;
 		pci_ioremap_io(global_io_offset, pp->io_base);
 		global_io_offset += SZ_64K;
 		pci_add_resource_offset(&sys->resources, &pp->io,
 					sys->io_offset);
 	}
 
-	sys->mem_offset = pp->mem.start - pp->config.mem_bus_addr;
+	sys->mem_offset = pp->mem.start - pp->mem_bus_addr;
 	pci_add_resource_offset(&sys->resources, &pp->mem, sys->mem_offset);
+	pci_add_resource(&sys->resources, &pp->busn);
 
 	return 1;
 }
@@ -790,14 +721,16 @@ static struct pci_bus *dw_pcie_scan_bus(int nr, struct pci_sys_data *sys)
 	struct pci_bus *bus;
 	struct pcie_port *pp = sys_to_pcie(sys);
 
-	if (pp) {
-		pp->root_bus_nr = sys->busnr;
-		bus = pci_scan_root_bus(pp->dev, sys->busnr, &dw_pcie_ops,
-					sys, &sys->resources);
-	} else {
-		bus = NULL;
-		BUG();
-	}
+	pp->root_bus_nr = sys->busnr;
+	bus = pci_create_root_bus(pp->dev, sys->busnr,
+				  &dw_pcie_ops, sys, &sys->resources);
+	if (!bus)
+		return NULL;
+
+	pci_scan_child_bus(bus);
+
+	if (bus && pp->ops->scan_bus)
+		pp->ops->scan_bus(pp);
 
 	return bus;
 }
@@ -833,7 +766,6 @@ static struct hw_pci dw_pci = {
 
 void dw_pcie_setup_rc(struct pcie_port *pp)
 {
-	struct pcie_port_info *config = &pp->config;
 	u32 val;
 	u32 membase;
 	u32 memlimit;
@@ -888,7 +820,7 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 
 	/* setup memory base, memory limit */
 	membase = ((u32)pp->mem_base & 0xfff00000) >> 16;
-	memlimit = (config->mem_size + (u32)pp->mem_base) & 0xfff00000;
+	memlimit = (pp->mem_size + (u32)pp->mem_base) & 0xfff00000;
 	val = memlimit | membase;
 	dw_pcie_writel_rc(pp, val, PCI_MEMORY_BASE);
 
diff --git a/drivers/pci/host/pcie-designware.h b/drivers/pci/host/pcie-designware.h
index daf81f922cda..c6256751daff 100644
--- a/drivers/pci/host/pcie-designware.h
+++ b/drivers/pci/host/pcie-designware.h
@@ -14,15 +14,6 @@
 #ifndef _PCIE_DESIGNWARE_H
 #define _PCIE_DESIGNWARE_H
 
-struct pcie_port_info {
-	u32		cfg0_size;
-	u32		cfg1_size;
-	u32		io_size;
-	u32		mem_size;
-	phys_addr_t	io_bus_addr;
-	phys_addr_t	mem_bus_addr;
-};
-
 /*
  * Maximum number of MSI IRQs can be 256 per controller. But keep
  * it 32 as of now. Probably we will never need more than 32. If needed,
@@ -38,17 +29,23 @@ struct pcie_port {
 	u64			cfg0_base;
 	u64			cfg0_mod_base;
 	void __iomem		*va_cfg0_base;
+	u32			cfg0_size;
 	u64			cfg1_base;
 	u64			cfg1_mod_base;
 	void __iomem		*va_cfg1_base;
+	u32			cfg1_size;
 	u64			io_base;
 	u64			io_mod_base;
+	phys_addr_t		io_bus_addr;
+	u32			io_size;
 	u64			mem_base;
 	u64			mem_mod_base;
+	phys_addr_t		mem_bus_addr;
+	u32			mem_size;
 	struct resource		cfg;
 	struct resource		io;
 	struct resource		mem;
-	struct pcie_port_info	config;
+	struct resource		busn;
 	int			irq;
 	u32			lanes;
 	struct pcie_host_ops	*ops;
@@ -73,7 +70,10 @@ struct pcie_host_ops {
 	void (*host_init)(struct pcie_port *pp);
 	void (*msi_set_irq)(struct pcie_port *pp, int irq);
 	void (*msi_clear_irq)(struct pcie_port *pp, int irq);
-	u32 (*get_msi_data)(struct pcie_port *pp);
+	u32 (*get_msi_addr)(struct pcie_port *pp);
+	u32 (*get_msi_data)(struct pcie_port *pp, int pos);
+	void (*scan_bus)(struct pcie_port *pp);
+	int (*msi_host_init)(struct pcie_port *pp, struct msi_chip *chip);
 };
 
 int dw_pcie_cfg_read(void __iomem *addr, int where, int size, u32 *val);
diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c
index 4884ee5e07d4..61158e03ab5f 100644
--- a/drivers/pci/host/pcie-rcar.c
+++ b/drivers/pci/host/pcie-rcar.c
@@ -323,6 +323,7 @@ static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie)
 
 	/* Setup PCIe address space mappings for each resource */
 	resource_size_t size;
+	resource_size_t res_start;
 	u32 mask;
 
 	rcar_pci_write_reg(pcie, 0x00000000, PCIEPTCTLR(win));
@@ -335,8 +336,13 @@ static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie)
 	mask = (roundup_pow_of_two(size) / SZ_128) - 1;
 	rcar_pci_write_reg(pcie, mask << 7, PCIEPAMR(win));
 
-	rcar_pci_write_reg(pcie, upper_32_bits(res->start), PCIEPARH(win));
-	rcar_pci_write_reg(pcie, lower_32_bits(res->start), PCIEPARL(win));
+	if (res->flags & IORESOURCE_IO)
+		res_start = pci_pio_to_address(res->start);
+	else
+		res_start = res->start;
+
+	rcar_pci_write_reg(pcie, upper_32_bits(res_start), PCIEPARH(win));
+	rcar_pci_write_reg(pcie, lower_32_bits(res_start), PCIEPARL(win));
 
 	/* First resource is for IO */
 	mask = PAR_ENABLE;
@@ -363,9 +369,10 @@ static int rcar_pcie_setup(int nr, struct pci_sys_data *sys)
 
 		rcar_pcie_setup_window(i, pcie);
 
-		if (res->flags & IORESOURCE_IO)
-			pci_ioremap_io(nr * SZ_64K, res->start);
-		else
+		if (res->flags & IORESOURCE_IO) {
+			phys_addr_t io_start = pci_pio_to_address(res->start);
+			pci_ioremap_io(nr * SZ_64K, io_start);
+		} else
 			pci_add_resource(&sys->resources, res);
 	}
 	pci_add_resource(&sys->resources, &pcie->busn);
@@ -935,8 +942,10 @@ static int rcar_pcie_probe(struct platform_device *pdev)
 	}
 
 	for_each_of_pci_range(&parser, &range) {
-		of_pci_range_to_resource(&range, pdev->dev.of_node,
+		err = of_pci_range_to_resource(&range, pdev->dev.of_node,
 						&pcie->res[win++]);
+		if (err < 0)
+			return err;
 
 		if (win > RCAR_PCI_MAX_RESOURCES)
 			break;
diff --git a/drivers/pci/host/pcie-spear13xx.c b/drivers/pci/host/pcie-spear13xx.c
index 6dea9e43a75c..85f594e1708f 100644
--- a/drivers/pci/host/pcie-spear13xx.c
+++ b/drivers/pci/host/pcie-spear13xx.c
@@ -340,7 +340,7 @@ static int __init spear13xx_pcie_probe(struct platform_device *pdev)
 
 	pp->dev = dev;
 
-	dbi_base = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi");
 	pp->dbi_base = devm_ioremap_resource(dev, dbi_base);
 	if (IS_ERR(pp->dbi_base)) {
 		dev_err(dev, "couldn't remap dbi base %p\n", dbi_base);
diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c
new file mode 100644
index 000000000000..ccc496b33a97
--- /dev/null
+++ b/drivers/pci/host/pcie-xilinx.c
@@ -0,0 +1,970 @@
+/*
+ * PCIe host controller driver for Xilinx AXI PCIe Bridge
+ *
+ * Copyright (c) 2012 - 2014 Xilinx, Inc.
+ *
+ * Based on the Tegra PCIe driver
+ *
+ * Bits taken from Synopsys Designware Host controller driver and
+ * ARM PCI Host generic driver.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of_address.h>
+#include <linux/of_pci.h>
+#include <linux/of_platform.h>
+#include <linux/of_irq.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+
+/* Register definitions */
+#define XILINX_PCIE_REG_BIR		0x00000130
+#define XILINX_PCIE_REG_IDR		0x00000138
+#define XILINX_PCIE_REG_IMR		0x0000013c
+#define XILINX_PCIE_REG_PSCR		0x00000144
+#define XILINX_PCIE_REG_RPSC		0x00000148
+#define XILINX_PCIE_REG_MSIBASE1	0x0000014c
+#define XILINX_PCIE_REG_MSIBASE2	0x00000150
+#define XILINX_PCIE_REG_RPEFR		0x00000154
+#define XILINX_PCIE_REG_RPIFR1		0x00000158
+#define XILINX_PCIE_REG_RPIFR2		0x0000015c
+
+/* Interrupt registers definitions */
+#define XILINX_PCIE_INTR_LINK_DOWN	BIT(0)
+#define XILINX_PCIE_INTR_ECRC_ERR	BIT(1)
+#define XILINX_PCIE_INTR_STR_ERR	BIT(2)
+#define XILINX_PCIE_INTR_HOT_RESET	BIT(3)
+#define XILINX_PCIE_INTR_CFG_TIMEOUT	BIT(8)
+#define XILINX_PCIE_INTR_CORRECTABLE	BIT(9)
+#define XILINX_PCIE_INTR_NONFATAL	BIT(10)
+#define XILINX_PCIE_INTR_FATAL		BIT(11)
+#define XILINX_PCIE_INTR_INTX		BIT(16)
+#define XILINX_PCIE_INTR_MSI		BIT(17)
+#define XILINX_PCIE_INTR_SLV_UNSUPP	BIT(20)
+#define XILINX_PCIE_INTR_SLV_UNEXP	BIT(21)
+#define XILINX_PCIE_INTR_SLV_COMPL	BIT(22)
+#define XILINX_PCIE_INTR_SLV_ERRP	BIT(23)
+#define XILINX_PCIE_INTR_SLV_CMPABT	BIT(24)
+#define XILINX_PCIE_INTR_SLV_ILLBUR	BIT(25)
+#define XILINX_PCIE_INTR_MST_DECERR	BIT(26)
+#define XILINX_PCIE_INTR_MST_SLVERR	BIT(27)
+#define XILINX_PCIE_INTR_MST_ERRP	BIT(28)
+#define XILINX_PCIE_IMR_ALL_MASK	0x1FF30FED
+#define XILINX_PCIE_IDR_ALL_MASK	0xFFFFFFFF
+
+/* Root Port Error FIFO Read Register definitions */
+#define XILINX_PCIE_RPEFR_ERR_VALID	BIT(18)
+#define XILINX_PCIE_RPEFR_REQ_ID	GENMASK(15, 0)
+#define XILINX_PCIE_RPEFR_ALL_MASK	0xFFFFFFFF
+
+/* Root Port Interrupt FIFO Read Register 1 definitions */
+#define XILINX_PCIE_RPIFR1_INTR_VALID	BIT(31)
+#define XILINX_PCIE_RPIFR1_MSI_INTR	BIT(30)
+#define XILINX_PCIE_RPIFR1_INTR_MASK	GENMASK(28, 27)
+#define XILINX_PCIE_RPIFR1_ALL_MASK	0xFFFFFFFF
+#define XILINX_PCIE_RPIFR1_INTR_SHIFT	27
+
+/* Bridge Info Register definitions */
+#define XILINX_PCIE_BIR_ECAM_SZ_MASK	GENMASK(18, 16)
+#define XILINX_PCIE_BIR_ECAM_SZ_SHIFT	16
+
+/* Root Port Interrupt FIFO Read Register 2 definitions */
+#define XILINX_PCIE_RPIFR2_MSG_DATA	GENMASK(15, 0)
+
+/* Root Port Status/control Register definitions */
+#define XILINX_PCIE_REG_RPSC_BEN	BIT(0)
+
+/* Phy Status/Control Register definitions */
+#define XILINX_PCIE_REG_PSCR_LNKUP	BIT(11)
+
+/* ECAM definitions */
+#define ECAM_BUS_NUM_SHIFT		20
+#define ECAM_DEV_NUM_SHIFT		12
+
+/* Number of MSI IRQs */
+#define XILINX_NUM_MSI_IRQS		128
+
+/* Number of Memory Resources */
+#define XILINX_MAX_NUM_RESOURCES	3
+
+/**
+ * struct xilinx_pcie_port - PCIe port information
+ * @reg_base: IO Mapped Register Base
+ * @irq: Interrupt number
+ * @msi_pages: MSI pages
+ * @root_busno: Root Bus number
+ * @dev: Device pointer
+ * @irq_domain: IRQ domain pointer
+ * @bus_range: Bus range
+ * @resources: Bus Resources
+ */
+struct xilinx_pcie_port {
+	void __iomem *reg_base;
+	u32 irq;
+	unsigned long msi_pages;
+	u8 root_busno;
+	struct device *dev;
+	struct irq_domain *irq_domain;
+	struct resource bus_range;
+	struct list_head resources;
+};
+
+static DECLARE_BITMAP(msi_irq_in_use, XILINX_NUM_MSI_IRQS);
+
+static inline struct xilinx_pcie_port *sys_to_pcie(struct pci_sys_data *sys)
+{
+	return sys->private_data;
+}
+
+static inline u32 pcie_read(struct xilinx_pcie_port *port, u32 reg)
+{
+	return readl(port->reg_base + reg);
+}
+
+static inline void pcie_write(struct xilinx_pcie_port *port, u32 val, u32 reg)
+{
+	writel(val, port->reg_base + reg);
+}
+
+static inline bool xilinx_pcie_link_is_up(struct xilinx_pcie_port *port)
+{
+	return (pcie_read(port, XILINX_PCIE_REG_PSCR) &
+		XILINX_PCIE_REG_PSCR_LNKUP) ? 1 : 0;
+}
+
+/**
+ * xilinx_pcie_clear_err_interrupts - Clear Error Interrupts
+ * @port: PCIe port information
+ */
+static void xilinx_pcie_clear_err_interrupts(struct xilinx_pcie_port *port)
+{
+	u32 val = pcie_read(port, XILINX_PCIE_REG_RPEFR);
+
+	if (val & XILINX_PCIE_RPEFR_ERR_VALID) {
+		dev_dbg(port->dev, "Requester ID %d\n",
+			val & XILINX_PCIE_RPEFR_REQ_ID);
+		pcie_write(port, XILINX_PCIE_RPEFR_ALL_MASK,
+			   XILINX_PCIE_REG_RPEFR);
+	}
+}
+
+/**
+ * xilinx_pcie_valid_device - Check if a valid device is present on bus
+ * @bus: PCI Bus structure
+ * @devfn: device/function
+ *
+ * Return: 'true' on success and 'false' if invalid device is found
+ */
+static bool xilinx_pcie_valid_device(struct pci_bus *bus, unsigned int devfn)
+{
+	struct xilinx_pcie_port *port = sys_to_pcie(bus->sysdata);
+
+	/* Check if link is up when trying to access downstream ports */
+	if (bus->number != port->root_busno)
+		if (!xilinx_pcie_link_is_up(port))
+			return false;
+
+	/* Only one device down on each root port */
+	if (bus->number == port->root_busno && devfn > 0)
+		return false;
+
+	/*
+	 * Do not read more than one device on the bus directly attached
+	 * to RC.
+	 */
+	if (bus->primary == port->root_busno && devfn > 0)
+		return false;
+
+	return true;
+}
+
+/**
+ * xilinx_pcie_config_base - Get configuration base
+ * @bus: PCI Bus structure
+ * @devfn: Device/function
+ * @where: Offset from base
+ *
+ * Return: Base address of the configuration space needed to be
+ *	   accessed.
+ */
+static void __iomem *xilinx_pcie_config_base(struct pci_bus *bus,
+					     unsigned int devfn, int where)
+{
+	struct xilinx_pcie_port *port = sys_to_pcie(bus->sysdata);
+	int relbus;
+
+	relbus = (bus->number << ECAM_BUS_NUM_SHIFT) |
+		 (devfn << ECAM_DEV_NUM_SHIFT);
+
+	return port->reg_base + relbus + where;
+}
+
+/**
+ * xilinx_pcie_read_config - Read configuration space
+ * @bus: PCI Bus structure
+ * @devfn: Device/function
+ * @where: Offset from base
+ * @size: Byte/word/dword
+ * @val: Value to be read
+ *
+ * Return: PCIBIOS_SUCCESSFUL on success
+ *	   PCIBIOS_DEVICE_NOT_FOUND on failure
+ */
+static int xilinx_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
+				   int where, int size, u32 *val)
+{
+	void __iomem *addr;
+
+	if (!xilinx_pcie_valid_device(bus, devfn)) {
+		*val = 0xFFFFFFFF;
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	}
+
+	addr = xilinx_pcie_config_base(bus, devfn, where);
+
+	switch (size) {
+	case 1:
+		*val = readb(addr);
+		break;
+	case 2:
+		*val = readw(addr);
+		break;
+	default:
+		*val = readl(addr);
+		break;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+/**
+ * xilinx_pcie_write_config - Write configuration space
+ * @bus: PCI Bus structure
+ * @devfn: Device/function
+ * @where: Offset from base
+ * @size: Byte/word/dword
+ * @val: Value to be written to device
+ *
+ * Return: PCIBIOS_SUCCESSFUL on success
+ *	   PCIBIOS_DEVICE_NOT_FOUND on failure
+ */
+static int xilinx_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
+				    int where, int size, u32 val)
+{
+	void __iomem *addr;
+
+	if (!xilinx_pcie_valid_device(bus, devfn))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	addr = xilinx_pcie_config_base(bus, devfn, where);
+
+	switch (size) {
+	case 1:
+		writeb(val, addr);
+		break;
+	case 2:
+		writew(val, addr);
+		break;
+	default:
+		writel(val, addr);
+		break;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+/* PCIe operations */
+static struct pci_ops xilinx_pcie_ops = {
+	.read  = xilinx_pcie_read_config,
+	.write = xilinx_pcie_write_config,
+};
+
+/* MSI functions */
+
+/**
+ * xilinx_pcie_destroy_msi - Free MSI number
+ * @irq: IRQ to be freed
+ */
+static void xilinx_pcie_destroy_msi(unsigned int irq)
+{
+	struct irq_desc *desc;
+	struct msi_desc *msi;
+	struct xilinx_pcie_port *port;
+
+	desc = irq_to_desc(irq);
+	msi = irq_desc_get_msi_desc(desc);
+	port = sys_to_pcie(msi->dev->bus->sysdata);
+
+	if (!test_bit(irq, msi_irq_in_use))
+		dev_err(port->dev, "Trying to free unused MSI#%d\n", irq);
+	else
+		clear_bit(irq, msi_irq_in_use);
+}
+
+/**
+ * xilinx_pcie_assign_msi - Allocate MSI number
+ * @port: PCIe port structure
+ *
+ * Return: A valid IRQ on success and error value on failure.
+ */
+static int xilinx_pcie_assign_msi(struct xilinx_pcie_port *port)
+{
+	int pos;
+
+	pos = find_first_zero_bit(msi_irq_in_use, XILINX_NUM_MSI_IRQS);
+	if (pos < XILINX_NUM_MSI_IRQS)
+		set_bit(pos, msi_irq_in_use);
+	else
+		return -ENOSPC;
+
+	return pos;
+}
+
+/**
+ * xilinx_msi_teardown_irq - Destroy the MSI
+ * @chip: MSI Chip descriptor
+ * @irq: MSI IRQ to destroy
+ */
+static void xilinx_msi_teardown_irq(struct msi_chip *chip, unsigned int irq)
+{
+	xilinx_pcie_destroy_msi(irq);
+}
+
+/**
+ * xilinx_pcie_msi_setup_irq - Setup MSI request
+ * @chip: MSI chip pointer
+ * @pdev: PCIe device pointer
+ * @desc: MSI descriptor pointer
+ *
+ * Return: '0' on success and error value on failure
+ */
+static int xilinx_pcie_msi_setup_irq(struct msi_chip *chip,
+				     struct pci_dev *pdev,
+				     struct msi_desc *desc)
+{
+	struct xilinx_pcie_port *port = sys_to_pcie(pdev->bus->sysdata);
+	unsigned int irq;
+	int hwirq;
+	struct msi_msg msg;
+	phys_addr_t msg_addr;
+
+	hwirq = xilinx_pcie_assign_msi(port);
+	if (hwirq < 0)
+		return hwirq;
+
+	irq = irq_create_mapping(port->irq_domain, hwirq);
+	if (!irq)
+		return -EINVAL;
+
+	irq_set_msi_desc(irq, desc);
+
+	msg_addr = virt_to_phys((void *)port->msi_pages);
+
+	msg.address_hi = 0;
+	msg.address_lo = msg_addr;
+	msg.data = irq;
+
+	write_msi_msg(irq, &msg);
+
+	return 0;
+}
+
+/* MSI Chip Descriptor */
+static struct msi_chip xilinx_pcie_msi_chip = {
+	.setup_irq = xilinx_pcie_msi_setup_irq,
+	.teardown_irq = xilinx_msi_teardown_irq,
+};
+
+/* HW Interrupt Chip Descriptor */
+static struct irq_chip xilinx_msi_irq_chip = {
+	.name = "Xilinx PCIe MSI",
+	.irq_enable = unmask_msi_irq,
+	.irq_disable = mask_msi_irq,
+	.irq_mask = mask_msi_irq,
+	.irq_unmask = unmask_msi_irq,
+};
+
+/**
+ * xilinx_pcie_msi_map - Set the handler for the MSI and mark IRQ as valid
+ * @domain: IRQ domain
+ * @irq: Virtual IRQ number
+ * @hwirq: HW interrupt number
+ *
+ * Return: Always returns 0.
+ */
+static int xilinx_pcie_msi_map(struct irq_domain *domain, unsigned int irq,
+			       irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(irq, &xilinx_msi_irq_chip, handle_simple_irq);
+	irq_set_chip_data(irq, domain->host_data);
+	set_irq_flags(irq, IRQF_VALID);
+
+	return 0;
+}
+
+/* IRQ Domain operations */
+static const struct irq_domain_ops msi_domain_ops = {
+	.map = xilinx_pcie_msi_map,
+};
+
+/**
+ * xilinx_pcie_enable_msi - Enable MSI support
+ * @port: PCIe port information
+ */
+static void xilinx_pcie_enable_msi(struct xilinx_pcie_port *port)
+{
+	phys_addr_t msg_addr;
+
+	port->msi_pages = __get_free_pages(GFP_KERNEL, 0);
+	msg_addr = virt_to_phys((void *)port->msi_pages);
+	pcie_write(port, 0x0, XILINX_PCIE_REG_MSIBASE1);
+	pcie_write(port, msg_addr, XILINX_PCIE_REG_MSIBASE2);
+}
+
+/**
+ * xilinx_pcie_add_bus - Add MSI chip info to PCIe bus
+ * @bus: PCIe bus
+ */
+static void xilinx_pcie_add_bus(struct pci_bus *bus)
+{
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		struct xilinx_pcie_port *port = sys_to_pcie(bus->sysdata);
+
+		xilinx_pcie_msi_chip.dev = port->dev;
+		bus->msi = &xilinx_pcie_msi_chip;
+	}
+}
+
+/* INTx Functions */
+
+/**
+ * xilinx_pcie_intx_map - Set the handler for the INTx and mark IRQ as valid
+ * @domain: IRQ domain
+ * @irq: Virtual IRQ number
+ * @hwirq: HW interrupt number
+ *
+ * Return: Always returns 0.
+ */
+static int xilinx_pcie_intx_map(struct irq_domain *domain, unsigned int irq,
+				irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(irq, &dummy_irq_chip, handle_simple_irq);
+	irq_set_chip_data(irq, domain->host_data);
+	set_irq_flags(irq, IRQF_VALID);
+
+	return 0;
+}
+
+/* INTx IRQ Domain operations */
+static const struct irq_domain_ops intx_domain_ops = {
+	.map = xilinx_pcie_intx_map,
+};
+
+/* PCIe HW Functions */
+
+/**
+ * xilinx_pcie_intr_handler - Interrupt Service Handler
+ * @irq: IRQ number
+ * @data: PCIe port information
+ *
+ * Return: IRQ_HANDLED on success and IRQ_NONE on failure
+ */
+static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data)
+{
+	struct xilinx_pcie_port *port = (struct xilinx_pcie_port *)data;
+	u32 val, mask, status, msi_data;
+
+	/* Read interrupt decode and mask registers */
+	val = pcie_read(port, XILINX_PCIE_REG_IDR);
+	mask = pcie_read(port, XILINX_PCIE_REG_IMR);
+
+	status = val & mask;
+	if (!status)
+		return IRQ_NONE;
+
+	if (status & XILINX_PCIE_INTR_LINK_DOWN)
+		dev_warn(port->dev, "Link Down\n");
+
+	if (status & XILINX_PCIE_INTR_ECRC_ERR)
+		dev_warn(port->dev, "ECRC failed\n");
+
+	if (status & XILINX_PCIE_INTR_STR_ERR)
+		dev_warn(port->dev, "Streaming error\n");
+
+	if (status & XILINX_PCIE_INTR_HOT_RESET)
+		dev_info(port->dev, "Hot reset\n");
+
+	if (status & XILINX_PCIE_INTR_CFG_TIMEOUT)
+		dev_warn(port->dev, "ECAM access timeout\n");
+
+	if (status & XILINX_PCIE_INTR_CORRECTABLE) {
+		dev_warn(port->dev, "Correctable error message\n");
+		xilinx_pcie_clear_err_interrupts(port);
+	}
+
+	if (status & XILINX_PCIE_INTR_NONFATAL) {
+		dev_warn(port->dev, "Non fatal error message\n");
+		xilinx_pcie_clear_err_interrupts(port);
+	}
+
+	if (status & XILINX_PCIE_INTR_FATAL) {
+		dev_warn(port->dev, "Fatal error message\n");
+		xilinx_pcie_clear_err_interrupts(port);
+	}
+
+	if (status & XILINX_PCIE_INTR_INTX) {
+		/* INTx interrupt received */
+		val = pcie_read(port, XILINX_PCIE_REG_RPIFR1);
+
+		/* Check whether interrupt valid */
+		if (!(val & XILINX_PCIE_RPIFR1_INTR_VALID)) {
+			dev_warn(port->dev, "RP Intr FIFO1 read error\n");
+			return IRQ_HANDLED;
+		}
+
+		/* Clear interrupt FIFO register 1 */
+		pcie_write(port, XILINX_PCIE_RPIFR1_ALL_MASK,
+			   XILINX_PCIE_REG_RPIFR1);
+
+		/* Handle INTx Interrupt */
+		val = ((val & XILINX_PCIE_RPIFR1_INTR_MASK) >>
+			XILINX_PCIE_RPIFR1_INTR_SHIFT) + 1;
+		generic_handle_irq(irq_find_mapping(port->irq_domain, val));
+	}
+
+	if (status & XILINX_PCIE_INTR_MSI) {
+		/* MSI Interrupt */
+		val = pcie_read(port, XILINX_PCIE_REG_RPIFR1);
+
+		if (!(val & XILINX_PCIE_RPIFR1_INTR_VALID)) {
+			dev_warn(port->dev, "RP Intr FIFO1 read error\n");
+			return IRQ_HANDLED;
+		}
+
+		if (val & XILINX_PCIE_RPIFR1_MSI_INTR) {
+			msi_data = pcie_read(port, XILINX_PCIE_REG_RPIFR2) &
+				   XILINX_PCIE_RPIFR2_MSG_DATA;
+
+			/* Clear interrupt FIFO register 1 */
+			pcie_write(port, XILINX_PCIE_RPIFR1_ALL_MASK,
+				   XILINX_PCIE_REG_RPIFR1);
+
+			if (IS_ENABLED(CONFIG_PCI_MSI)) {
+				/* Handle MSI Interrupt */
+				generic_handle_irq(msi_data);
+			}
+		}
+	}
+
+	if (status & XILINX_PCIE_INTR_SLV_UNSUPP)
+		dev_warn(port->dev, "Slave unsupported request\n");
+
+	if (status & XILINX_PCIE_INTR_SLV_UNEXP)
+		dev_warn(port->dev, "Slave unexpected completion\n");
+
+	if (status & XILINX_PCIE_INTR_SLV_COMPL)
+		dev_warn(port->dev, "Slave completion timeout\n");
+
+	if (status & XILINX_PCIE_INTR_SLV_ERRP)
+		dev_warn(port->dev, "Slave Error Poison\n");
+
+	if (status & XILINX_PCIE_INTR_SLV_CMPABT)
+		dev_warn(port->dev, "Slave Completer Abort\n");
+
+	if (status & XILINX_PCIE_INTR_SLV_ILLBUR)
+		dev_warn(port->dev, "Slave Illegal Burst\n");
+
+	if (status & XILINX_PCIE_INTR_MST_DECERR)
+		dev_warn(port->dev, "Master decode error\n");
+
+	if (status & XILINX_PCIE_INTR_MST_SLVERR)
+		dev_warn(port->dev, "Master slave error\n");
+
+	if (status & XILINX_PCIE_INTR_MST_ERRP)
+		dev_warn(port->dev, "Master error poison\n");
+
+	/* Clear the Interrupt Decode register */
+	pcie_write(port, status, XILINX_PCIE_REG_IDR);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * xilinx_pcie_free_irq_domain - Free IRQ domain
+ * @port: PCIe port information
+ */
+static void xilinx_pcie_free_irq_domain(struct xilinx_pcie_port *port)
+{
+	int i;
+	u32 irq, num_irqs;
+
+	/* Free IRQ Domain */
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+
+		free_pages(port->msi_pages, 0);
+
+		num_irqs = XILINX_NUM_MSI_IRQS;
+	} else {
+		/* INTx */
+		num_irqs = 4;
+	}
+
+	for (i = 0; i < num_irqs; i++) {
+		irq = irq_find_mapping(port->irq_domain, i);
+		if (irq > 0)
+			irq_dispose_mapping(irq);
+	}
+
+	irq_domain_remove(port->irq_domain);
+}
+
+/**
+ * xilinx_pcie_init_irq_domain - Initialize IRQ domain
+ * @port: PCIe port information
+ *
+ * Return: '0' on success and error value on failure
+ */
+static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port)
+{
+	struct device *dev = port->dev;
+	struct device_node *node = dev->of_node;
+	struct device_node *pcie_intc_node;
+
+	/* Setup INTx */
+	pcie_intc_node = of_get_next_child(node, NULL);
+	if (!pcie_intc_node) {
+		dev_err(dev, "No PCIe Intc node found\n");
+		return PTR_ERR(pcie_intc_node);
+	}
+
+	port->irq_domain = irq_domain_add_linear(pcie_intc_node, 4,
+						 &intx_domain_ops,
+						 port);
+	if (!port->irq_domain) {
+		dev_err(dev, "Failed to get a INTx IRQ domain\n");
+		return PTR_ERR(port->irq_domain);
+	}
+
+	/* Setup MSI */
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		port->irq_domain = irq_domain_add_linear(node,
+							 XILINX_NUM_MSI_IRQS,
+							 &msi_domain_ops,
+							 &xilinx_pcie_msi_chip);
+		if (!port->irq_domain) {
+			dev_err(dev, "Failed to get a MSI IRQ domain\n");
+			return PTR_ERR(port->irq_domain);
+		}
+
+		xilinx_pcie_enable_msi(port);
+	}
+
+	return 0;
+}
+
+/**
+ * xilinx_pcie_init_port - Initialize hardware
+ * @port: PCIe port information
+ */
+static void xilinx_pcie_init_port(struct xilinx_pcie_port *port)
+{
+	if (xilinx_pcie_link_is_up(port))
+		dev_info(port->dev, "PCIe Link is UP\n");
+	else
+		dev_info(port->dev, "PCIe Link is DOWN\n");
+
+	/* Disable all interrupts */
+	pcie_write(port, ~XILINX_PCIE_IDR_ALL_MASK,
+		   XILINX_PCIE_REG_IMR);
+
+	/* Clear pending interrupts */
+	pcie_write(port, pcie_read(port, XILINX_PCIE_REG_IDR) &
+			 XILINX_PCIE_IMR_ALL_MASK,
+		   XILINX_PCIE_REG_IDR);
+
+	/* Enable all interrupts */
+	pcie_write(port, XILINX_PCIE_IMR_ALL_MASK, XILINX_PCIE_REG_IMR);
+
+	/* Enable the Bridge enable bit */
+	pcie_write(port, pcie_read(port, XILINX_PCIE_REG_RPSC) |
+			 XILINX_PCIE_REG_RPSC_BEN,
+		   XILINX_PCIE_REG_RPSC);
+}
+
+/**
+ * xilinx_pcie_setup - Setup memory resources
+ * @nr: Bus number
+ * @sys: Per controller structure
+ *
+ * Return: '1' on success and error value on failure
+ */
+static int xilinx_pcie_setup(int nr, struct pci_sys_data *sys)
+{
+	struct xilinx_pcie_port *port = sys_to_pcie(sys);
+
+	list_splice_init(&port->resources, &sys->resources);
+
+	return 1;
+}
+
+/**
+ * xilinx_pcie_scan_bus - Scan PCIe bus for devices
+ * @nr: Bus number
+ * @sys: Per controller structure
+ *
+ * Return: Valid Bus pointer on success and NULL on failure
+ */
+static struct pci_bus *xilinx_pcie_scan_bus(int nr, struct pci_sys_data *sys)
+{
+	struct xilinx_pcie_port *port = sys_to_pcie(sys);
+	struct pci_bus *bus;
+
+	port->root_busno = sys->busnr;
+	bus = pci_scan_root_bus(port->dev, sys->busnr, &xilinx_pcie_ops,
+				sys, &sys->resources);
+
+	return bus;
+}
+
+/**
+ * xilinx_pcie_parse_and_add_res - Add resources by parsing ranges
+ * @port: PCIe port information
+ *
+ * Return: '0' on success and error value on failure
+ */
+static int xilinx_pcie_parse_and_add_res(struct xilinx_pcie_port *port)
+{
+	struct device *dev = port->dev;
+	struct device_node *node = dev->of_node;
+	struct resource *mem;
+	resource_size_t offset;
+	struct of_pci_range_parser parser;
+	struct of_pci_range range;
+	struct pci_host_bridge_window *win;
+	int err = 0, mem_resno = 0;
+
+	/* Get the ranges */
+	if (of_pci_range_parser_init(&parser, node)) {
+		dev_err(dev, "missing \"ranges\" property\n");
+		return -EINVAL;
+	}
+
+	/* Parse the ranges and add the resources found to the list */
+	for_each_of_pci_range(&parser, &range) {
+
+		if (mem_resno >= XILINX_MAX_NUM_RESOURCES) {
+			dev_err(dev, "Maximum memory resources exceeded\n");
+			return -EINVAL;
+		}
+
+		mem = devm_kmalloc(dev, sizeof(*mem), GFP_KERNEL);
+		if (!mem) {
+			err = -ENOMEM;
+			goto free_resources;
+		}
+
+		of_pci_range_to_resource(&range, node, mem);
+
+		switch (mem->flags & IORESOURCE_TYPE_BITS) {
+		case IORESOURCE_MEM:
+			offset = range.cpu_addr - range.pci_addr;
+			mem_resno++;
+			break;
+		default:
+			err = -EINVAL;
+			break;
+		}
+
+		if (err < 0) {
+			dev_warn(dev, "Invalid resource found %pR\n", mem);
+			continue;
+		}
+
+		err = request_resource(&iomem_resource, mem);
+		if (err)
+			goto free_resources;
+
+		pci_add_resource_offset(&port->resources, mem, offset);
+	}
+
+	/* Get the bus range */
+	if (of_pci_parse_bus_range(node, &port->bus_range)) {
+		u32 val = pcie_read(port, XILINX_PCIE_REG_BIR);
+		u8 last;
+
+		last = (val & XILINX_PCIE_BIR_ECAM_SZ_MASK) >>
+			XILINX_PCIE_BIR_ECAM_SZ_SHIFT;
+
+		port->bus_range = (struct resource) {
+			.name	= node->name,
+			.start	= 0,
+			.end	= last,
+			.flags	= IORESOURCE_BUS,
+		};
+	}
+
+	/* Register bus resource */
+	pci_add_resource(&port->resources, &port->bus_range);
+
+	return 0;
+
+free_resources:
+	release_child_resources(&iomem_resource);
+	list_for_each_entry(win, &port->resources, list)
+		devm_kfree(dev, win->res);
+	pci_free_resource_list(&port->resources);
+
+	return err;
+}
+
+/**
+ * xilinx_pcie_parse_dt - Parse Device tree
+ * @port: PCIe port information
+ *
+ * Return: '0' on success and error value on failure
+ */
+static int xilinx_pcie_parse_dt(struct xilinx_pcie_port *port)
+{
+	struct device *dev = port->dev;
+	struct device_node *node = dev->of_node;
+	struct resource regs;
+	const char *type;
+	int err;
+
+	type = of_get_property(node, "device_type", NULL);
+	if (!type || strcmp(type, "pci")) {
+		dev_err(dev, "invalid \"device_type\" %s\n", type);
+		return -EINVAL;
+	}
+
+	err = of_address_to_resource(node, 0, &regs);
+	if (err) {
+		dev_err(dev, "missing \"reg\" property\n");
+		return err;
+	}
+
+	port->reg_base = devm_ioremap_resource(dev, &regs);
+	if (IS_ERR(port->reg_base))
+		return PTR_ERR(port->reg_base);
+
+	port->irq = irq_of_parse_and_map(node, 0);
+	err = devm_request_irq(dev, port->irq, xilinx_pcie_intr_handler,
+			       IRQF_SHARED, "xilinx-pcie", port);
+	if (err) {
+		dev_err(dev, "unable to request irq %d\n", port->irq);
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * xilinx_pcie_probe - Probe function
+ * @pdev: Platform device pointer
+ *
+ * Return: '0' on success and error value on failure
+ */
+static int xilinx_pcie_probe(struct platform_device *pdev)
+{
+	struct xilinx_pcie_port *port;
+	struct hw_pci hw;
+	struct device *dev = &pdev->dev;
+	int err;
+
+	if (!dev->of_node)
+		return -ENODEV;
+
+	port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL);
+	if (!port)
+		return -ENOMEM;
+
+	port->dev = dev;
+
+	err = xilinx_pcie_parse_dt(port);
+	if (err) {
+		dev_err(dev, "Parsing DT failed\n");
+		return err;
+	}
+
+	xilinx_pcie_init_port(port);
+
+	err = xilinx_pcie_init_irq_domain(port);
+	if (err) {
+		dev_err(dev, "Failed creating IRQ Domain\n");
+		return err;
+	}
+
+	/*
+	 * Parse PCI ranges, configuration bus range and
+	 * request their resources
+	 */
+	INIT_LIST_HEAD(&port->resources);
+	err = xilinx_pcie_parse_and_add_res(port);
+	if (err) {
+		dev_err(dev, "Failed adding resources\n");
+		return err;
+	}
+
+	platform_set_drvdata(pdev, port);
+
+	/* Register the device */
+	memset(&hw, 0, sizeof(hw));
+	hw = (struct hw_pci) {
+		.nr_controllers	= 1,
+		.private_data	= (void **)&port,
+		.setup		= xilinx_pcie_setup,
+		.map_irq	= of_irq_parse_and_map_pci,
+		.add_bus	= xilinx_pcie_add_bus,
+		.scan		= xilinx_pcie_scan_bus,
+		.ops		= &xilinx_pcie_ops,
+	};
+	pci_common_init_dev(dev, &hw);
+
+	return 0;
+}
+
+/**
+ * xilinx_pcie_remove - Remove function
+ * @pdev: Platform device pointer
+ *
+ * Return: '0' always
+ */
+static int xilinx_pcie_remove(struct platform_device *pdev)
+{
+	struct xilinx_pcie_port *port = platform_get_drvdata(pdev);
+
+	xilinx_pcie_free_irq_domain(port);
+
+	return 0;
+}
+
+static struct of_device_id xilinx_pcie_of_match[] = {
+	{ .compatible = "xlnx,axi-pcie-host-1.00.a", },
+	{}
+};
+
+static struct platform_driver xilinx_pcie_driver = {
+	.driver = {
+		.name = "xilinx-pcie",
+		.owner = THIS_MODULE,
+		.of_match_table = xilinx_pcie_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = xilinx_pcie_probe,
+	.remove = xilinx_pcie_remove,
+};
+module_platform_driver(xilinx_pcie_driver);
+
+MODULE_AUTHOR("Xilinx Inc");
+MODULE_DESCRIPTION("Xilinx AXI PCIe driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/hotplug/Makefile b/drivers/pci/hotplug/Makefile
index 3e6532b945c1..4a9aa08b08f1 100644
--- a/drivers/pci/hotplug/Makefile
+++ b/drivers/pci/hotplug/Makefile
@@ -24,7 +24,7 @@ obj-$(CONFIG_HOTPLUG_PCI_S390)		+= s390_pci_hpc.o
 
 obj-$(CONFIG_HOTPLUG_PCI_ACPI_IBM)	+= acpiphp_ibm.o
 
-pci_hotplug-objs	:=	pci_hotplug_core.o pcihp_slot.o
+pci_hotplug-objs	:=	pci_hotplug_core.o
 
 ifdef CONFIG_HOTPLUG_PCI_CPCI
 pci_hotplug-objs	+=	cpci_hotplug_core.o	\
diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c
index a94d850ae228..876ccc620440 100644
--- a/drivers/pci/hotplug/acpi_pcihp.c
+++ b/drivers/pci/hotplug/acpi_pcihp.c
@@ -46,215 +46,6 @@
 
 static bool debug_acpi;
 
-static acpi_status
-decode_type0_hpx_record(union acpi_object *record, struct hotplug_params *hpx)
-{
-	int i;
-	union acpi_object *fields = record->package.elements;
-	u32 revision = fields[1].integer.value;
-
-	switch (revision) {
-	case 1:
-		if (record->package.count != 6)
-			return AE_ERROR;
-		for (i = 2; i < 6; i++)
-			if (fields[i].type != ACPI_TYPE_INTEGER)
-				return AE_ERROR;
-		hpx->t0 = &hpx->type0_data;
-		hpx->t0->revision        = revision;
-		hpx->t0->cache_line_size = fields[2].integer.value;
-		hpx->t0->latency_timer   = fields[3].integer.value;
-		hpx->t0->enable_serr     = fields[4].integer.value;
-		hpx->t0->enable_perr     = fields[5].integer.value;
-		break;
-	default:
-		printk(KERN_WARNING
-		       "%s: Type 0 Revision %d record not supported\n",
-		       __func__, revision);
-		return AE_ERROR;
-	}
-	return AE_OK;
-}
-
-static acpi_status
-decode_type1_hpx_record(union acpi_object *record, struct hotplug_params *hpx)
-{
-	int i;
-	union acpi_object *fields = record->package.elements;
-	u32 revision = fields[1].integer.value;
-
-	switch (revision) {
-	case 1:
-		if (record->package.count != 5)
-			return AE_ERROR;
-		for (i = 2; i < 5; i++)
-			if (fields[i].type != ACPI_TYPE_INTEGER)
-				return AE_ERROR;
-		hpx->t1 = &hpx->type1_data;
-		hpx->t1->revision      = revision;
-		hpx->t1->max_mem_read  = fields[2].integer.value;
-		hpx->t1->avg_max_split = fields[3].integer.value;
-		hpx->t1->tot_max_split = fields[4].integer.value;
-		break;
-	default:
-		printk(KERN_WARNING
-		       "%s: Type 1 Revision %d record not supported\n",
-		       __func__, revision);
-		return AE_ERROR;
-	}
-	return AE_OK;
-}
-
-static acpi_status
-decode_type2_hpx_record(union acpi_object *record, struct hotplug_params *hpx)
-{
-	int i;
-	union acpi_object *fields = record->package.elements;
-	u32 revision = fields[1].integer.value;
-
-	switch (revision) {
-	case 1:
-		if (record->package.count != 18)
-			return AE_ERROR;
-		for (i = 2; i < 18; i++)
-			if (fields[i].type != ACPI_TYPE_INTEGER)
-				return AE_ERROR;
-		hpx->t2 = &hpx->type2_data;
-		hpx->t2->revision      = revision;
-		hpx->t2->unc_err_mask_and      = fields[2].integer.value;
-		hpx->t2->unc_err_mask_or       = fields[3].integer.value;
-		hpx->t2->unc_err_sever_and     = fields[4].integer.value;
-		hpx->t2->unc_err_sever_or      = fields[5].integer.value;
-		hpx->t2->cor_err_mask_and      = fields[6].integer.value;
-		hpx->t2->cor_err_mask_or       = fields[7].integer.value;
-		hpx->t2->adv_err_cap_and       = fields[8].integer.value;
-		hpx->t2->adv_err_cap_or        = fields[9].integer.value;
-		hpx->t2->pci_exp_devctl_and    = fields[10].integer.value;
-		hpx->t2->pci_exp_devctl_or     = fields[11].integer.value;
-		hpx->t2->pci_exp_lnkctl_and    = fields[12].integer.value;
-		hpx->t2->pci_exp_lnkctl_or     = fields[13].integer.value;
-		hpx->t2->sec_unc_err_sever_and = fields[14].integer.value;
-		hpx->t2->sec_unc_err_sever_or  = fields[15].integer.value;
-		hpx->t2->sec_unc_err_mask_and  = fields[16].integer.value;
-		hpx->t2->sec_unc_err_mask_or   = fields[17].integer.value;
-		break;
-	default:
-		printk(KERN_WARNING
-		       "%s: Type 2 Revision %d record not supported\n",
-		       __func__, revision);
-		return AE_ERROR;
-	}
-	return AE_OK;
-}
-
-static acpi_status
-acpi_run_hpx(acpi_handle handle, struct hotplug_params *hpx)
-{
-	acpi_status status;
-	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
-	union acpi_object *package, *record, *fields;
-	u32 type;
-	int i;
-
-	/* Clear the return buffer with zeros */
-	memset(hpx, 0, sizeof(struct hotplug_params));
-
-	status = acpi_evaluate_object(handle, "_HPX", NULL, &buffer);
-	if (ACPI_FAILURE(status))
-		return status;
-
-	package = (union acpi_object *)buffer.pointer;
-	if (package->type != ACPI_TYPE_PACKAGE) {
-		status = AE_ERROR;
-		goto exit;
-	}
-
-	for (i = 0; i < package->package.count; i++) {
-		record = &package->package.elements[i];
-		if (record->type != ACPI_TYPE_PACKAGE) {
-			status = AE_ERROR;
-			goto exit;
-		}
-
-		fields = record->package.elements;
-		if (fields[0].type != ACPI_TYPE_INTEGER ||
-		    fields[1].type != ACPI_TYPE_INTEGER) {
-			status = AE_ERROR;
-			goto exit;
-		}
-
-		type = fields[0].integer.value;
-		switch (type) {
-		case 0:
-			status = decode_type0_hpx_record(record, hpx);
-			if (ACPI_FAILURE(status))
-				goto exit;
-			break;
-		case 1:
-			status = decode_type1_hpx_record(record, hpx);
-			if (ACPI_FAILURE(status))
-				goto exit;
-			break;
-		case 2:
-			status = decode_type2_hpx_record(record, hpx);
-			if (ACPI_FAILURE(status))
-				goto exit;
-			break;
-		default:
-			printk(KERN_ERR "%s: Type %d record not supported\n",
-			       __func__, type);
-			status = AE_ERROR;
-			goto exit;
-		}
-	}
- exit:
-	kfree(buffer.pointer);
-	return status;
-}
-
-static acpi_status
-acpi_run_hpp(acpi_handle handle, struct hotplug_params *hpp)
-{
-	acpi_status status;
-	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	union acpi_object *package, *fields;
-	int i;
-
-	memset(hpp, 0, sizeof(struct hotplug_params));
-
-	status = acpi_evaluate_object(handle, "_HPP", NULL, &buffer);
-	if (ACPI_FAILURE(status))
-		return status;
-
-	package = (union acpi_object *) buffer.pointer;
-	if (package->type != ACPI_TYPE_PACKAGE ||
-	    package->package.count != 4) {
-		status = AE_ERROR;
-		goto exit;
-	}
-
-	fields = package->package.elements;
-	for (i = 0; i < 4; i++) {
-		if (fields[i].type != ACPI_TYPE_INTEGER) {
-			status = AE_ERROR;
-			goto exit;
-		}
-	}
-
-	hpp->t0 = &hpp->type0_data;
-	hpp->t0->revision        = 1;
-	hpp->t0->cache_line_size = fields[0].integer.value;
-	hpp->t0->latency_timer   = fields[1].integer.value;
-	hpp->t0->enable_serr     = fields[2].integer.value;
-	hpp->t0->enable_perr     = fields[3].integer.value;
-
-exit:
-	kfree(buffer.pointer);
-	return status;
-}
-
-
-
 /* acpi_run_oshp - get control of hotplug from the firmware
  *
  * @handle - the handle of the hotplug controller.
@@ -283,48 +74,6 @@ static acpi_status acpi_run_oshp(acpi_handle handle)
 	return status;
 }
 
-/* pci_get_hp_params
- *
- * @dev - the pci_dev for which we want parameters
- * @hpp - allocated by the caller
- */
-int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp)
-{
-	acpi_status status;
-	acpi_handle handle, phandle;
-	struct pci_bus *pbus;
-
-	handle = NULL;
-	for (pbus = dev->bus; pbus; pbus = pbus->parent) {
-		handle = acpi_pci_get_bridge_handle(pbus);
-		if (handle)
-			break;
-	}
-
-	/*
-	 * _HPP settings apply to all child buses, until another _HPP is
-	 * encountered. If we don't find an _HPP for the input pci dev,
-	 * look for it in the parent device scope since that would apply to
-	 * this pci dev.
-	 */
-	while (handle) {
-		status = acpi_run_hpx(handle, hpp);
-		if (ACPI_SUCCESS(status))
-			return 0;
-		status = acpi_run_hpp(handle, hpp);
-		if (ACPI_SUCCESS(status))
-			return 0;
-		if (acpi_is_root_bridge(handle))
-			break;
-		status = acpi_get_parent(handle, &phandle);
-		if (ACPI_FAILURE(status))
-			break;
-		handle = phandle;
-	}
-	return -ENODEV;
-}
-EXPORT_SYMBOL_GPL(pci_get_hp_params);
-
 /**
  * acpi_get_hp_hw_control_from_firmware
  * @dev: the pci_dev of the bridge that has a hotplug controller
@@ -433,7 +182,8 @@ int acpi_pci_check_ejectable(struct pci_bus *pbus, acpi_handle handle)
 {
 	acpi_handle bridge_handle, parent_handle;
 
-	if (!(bridge_handle = acpi_pci_get_bridge_handle(pbus)))
+	bridge_handle = acpi_pci_get_bridge_handle(pbus);
+	if (!bridge_handle)
 		return 0;
 	if ((ACPI_FAILURE(acpi_get_parent(handle, &parent_handle))))
 		return 0;
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 6cd5160fc057..bcb90e4888dd 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -61,7 +61,6 @@ static DEFINE_MUTEX(bridge_mutex);
 static int acpiphp_hotplug_notify(struct acpi_device *adev, u32 type);
 static void acpiphp_post_dock_fixup(struct acpi_device *adev);
 static void acpiphp_sanitize_bus(struct pci_bus *bus);
-static void acpiphp_set_hpp_values(struct pci_bus *bus);
 static void hotplug_event(u32 type, struct acpiphp_context *context);
 static void free_bridge(struct kref *kref);
 
@@ -510,7 +509,7 @@ static void enable_slot(struct acpiphp_slot *slot)
 	__pci_bus_assign_resources(bus, &add_list, NULL);
 
 	acpiphp_sanitize_bus(bus);
-	acpiphp_set_hpp_values(bus);
+	pcie_bus_configure_settings(bus);
 	acpiphp_set_acpi_region(slot);
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
@@ -698,14 +697,6 @@ static void acpiphp_check_bridge(struct acpiphp_bridge *bridge)
 	}
 }
 
-static void acpiphp_set_hpp_values(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	list_for_each_entry(dev, &bus->devices, bus_list)
-		pci_configure_slot(dev);
-}
-
 /*
  * Remove devices for which we could not assign resources, call
  * arch specific code to fix-up the bus
diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c
index 8dcccffd6e21..6ca23998ee8f 100644
--- a/drivers/pci/hotplug/acpiphp_ibm.c
+++ b/drivers/pci/hotplug/acpiphp_ibm.c
@@ -302,7 +302,7 @@ static int ibm_get_table_from_acpi(char **bufp)
 		goto read_table_done;
 	}
 
-	for(size = 0, i = 0; i < package->package.count; i++) {
+	for (size = 0, i = 0; i < package->package.count; i++) {
 		if (package->package.elements[i].type != ACPI_TYPE_BUFFER) {
 			pr_err("%s:  Invalid APCI element %d\n", __func__, i);
 			goto read_table_done;
diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c
index e09cf7827d68..a5a7fd8332ac 100644
--- a/drivers/pci/hotplug/cpci_hotplug_core.c
+++ b/drivers/pci/hotplug/cpci_hotplug_core.c
@@ -125,7 +125,8 @@ disable_slot(struct hotplug_slot *hotplug_slot)
 
 	/* Unconfigure device */
 	dbg("%s - unconfiguring slot %s", __func__, slot_name(slot));
-	if ((retval = cpci_unconfigure_slot(slot))) {
+	retval = cpci_unconfigure_slot(slot);
+	if (retval) {
 		err("%s - could not unconfigure slot %s",
 		    __func__, slot_name(slot));
 		goto disable_error;
@@ -141,9 +142,11 @@ disable_slot(struct hotplug_slot *hotplug_slot)
 	}
 	cpci_led_on(slot);
 
-	if (controller->ops->set_power)
-		if ((retval = controller->ops->set_power(slot, 0)))
+	if (controller->ops->set_power) {
+		retval = controller->ops->set_power(slot, 0);
+		if (retval)
 			goto disable_error;
+	}
 
 	if (update_adapter_status(slot->hotplug_slot, 0))
 		warn("failure to update adapter file");
@@ -467,9 +470,9 @@ check_slots(void)
 			    __func__, slot_name(slot), hs_csr);
 
 			if (!slot->extracting) {
-				if (update_latch_status(slot->hotplug_slot, 0)) {
+				if (update_latch_status(slot->hotplug_slot, 0))
 					warn("failure to update latch file");
-				}
+
 				slot->extracting = 1;
 				atomic_inc(&extracting);
 			}
diff --git a/drivers/pci/hotplug/cpcihp_generic.c b/drivers/pci/hotplug/cpcihp_generic.c
index 04fcd7811400..66b7bbebe493 100644
--- a/drivers/pci/hotplug/cpcihp_generic.c
+++ b/drivers/pci/hotplug/cpcihp_generic.c
@@ -56,7 +56,7 @@
 		if (debug)					\
 			printk (KERN_DEBUG "%s: " format "\n",	\
 				MY_NAME , ## arg);		\
-	} while(0)
+	} while (0)
 #define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
 #define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
 #define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME , ## arg)
@@ -82,28 +82,28 @@ static int __init validate_parameters(void)
 	char *p;
 	unsigned long tmp;
 
-	if(!bridge) {
+	if (!bridge) {
 		info("not configured, disabling.");
 		return -EINVAL;
 	}
 	str = bridge;
-	if(!*str)
+	if (!*str)
 		return -EINVAL;
 
 	tmp = simple_strtoul(str, &p, 16);
-	if(p == str || tmp > 0xff) {
+	if (p == str || tmp > 0xff) {
 		err("Invalid hotplug bus bridge device bus number");
 		return -EINVAL;
 	}
 	bridge_busnr = (u8) tmp;
 	dbg("bridge_busnr = 0x%02x", bridge_busnr);
-	if(*p != ':') {
+	if (*p != ':') {
 		err("Invalid hotplug bus bridge device");
 		return -EINVAL;
 	}
 	str = p + 1;
 	tmp = simple_strtoul(str, &p, 16);
-	if(p == str || tmp > 0x1f) {
+	if (p == str || tmp > 0x1f) {
 		err("Invalid hotplug bus bridge device slot number");
 		return -EINVAL;
 	}
@@ -112,18 +112,18 @@ static int __init validate_parameters(void)
 
 	dbg("first_slot = 0x%02x", first_slot);
 	dbg("last_slot = 0x%02x", last_slot);
-	if(!(first_slot && last_slot)) {
+	if (!(first_slot && last_slot)) {
 		err("Need to specify first_slot and last_slot");
 		return -EINVAL;
 	}
-	if(last_slot < first_slot) {
+	if (last_slot < first_slot) {
 		err("first_slot must be less than last_slot");
 		return -EINVAL;
 	}
 
 	dbg("port = 0x%04x", port);
 	dbg("enum_bit = 0x%02x", enum_bit);
-	if(enum_bit > 7) {
+	if (enum_bit > 7) {
 		err("Invalid #ENUM bit");
 		return -EINVAL;
 	}
@@ -151,12 +151,12 @@ static int __init cpcihp_generic_init(void)
 		return status;
 
 	r = request_region(port, 1, "#ENUM hotswap signal register");
-	if(!r)
+	if (!r)
 		return -EBUSY;
 
 	dev = pci_get_domain_bus_and_slot(0, bridge_busnr,
 					  PCI_DEVFN(bridge_slot, 0));
-	if(!dev || dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) {
+	if (!dev || dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) {
 		err("Invalid bridge device %s", bridge);
 		pci_dev_put(dev);
 		return -EINVAL;
@@ -169,21 +169,21 @@ static int __init cpcihp_generic_init(void)
 	generic_hpc.ops = &generic_hpc_ops;
 
 	status = cpci_hp_register_controller(&generic_hpc);
-	if(status != 0) {
+	if (status != 0) {
 		err("Could not register cPCI hotplug controller");
 		return -ENODEV;
 	}
 	dbg("registered controller");
 
 	status = cpci_hp_register_bus(bus, first_slot, last_slot);
-	if(status != 0) {
+	if (status != 0) {
 		err("Could not register cPCI hotplug bus");
 		goto init_bus_register_error;
 	}
 	dbg("registered bus");
 
 	status = cpci_hp_start();
-	if(status != 0) {
+	if (status != 0) {
 		err("Could not started cPCI hotplug system");
 		goto init_start_error;
 	}
diff --git a/drivers/pci/hotplug/cpcihp_zt5550.c b/drivers/pci/hotplug/cpcihp_zt5550.c
index 6757b3ef7e10..7ecf34e76a61 100644
--- a/drivers/pci/hotplug/cpcihp_zt5550.c
+++ b/drivers/pci/hotplug/cpcihp_zt5550.c
@@ -51,7 +51,7 @@
 		if (debug)					\
 			printk (KERN_DEBUG "%s: " format "\n",	\
 				MY_NAME , ## arg);		\
-	} while(0)
+	} while (0)
 #define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
 #define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME , ## arg)
 #define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME , ## arg)
@@ -82,13 +82,13 @@ static int zt5550_hc_config(struct pci_dev *pdev)
 	int ret;
 
 	/* Since we know that no boards exist with two HC chips, treat it as an error */
-	if(hc_dev) {
+	if (hc_dev) {
 		err("too many host controller devices?");
 		return -EBUSY;
 	}
 
 	ret = pci_enable_device(pdev);
-	if(ret) {
+	if (ret) {
 		err("cannot enable %s\n", pci_name(pdev));
 		return ret;
 	}
@@ -98,7 +98,7 @@ static int zt5550_hc_config(struct pci_dev *pdev)
 	dbg("pci resource start %llx", (unsigned long long)pci_resource_start(hc_dev, 1));
 	dbg("pci resource len %llx", (unsigned long long)pci_resource_len(hc_dev, 1));
 
-	if(!request_mem_region(pci_resource_start(hc_dev, 1),
+	if (!request_mem_region(pci_resource_start(hc_dev, 1),
 				pci_resource_len(hc_dev, 1), MY_NAME)) {
 		err("cannot reserve MMIO region");
 		ret = -ENOMEM;
@@ -107,7 +107,7 @@ static int zt5550_hc_config(struct pci_dev *pdev)
 
 	hc_registers =
 	    ioremap(pci_resource_start(hc_dev, 1), pci_resource_len(hc_dev, 1));
-	if(!hc_registers) {
+	if (!hc_registers) {
 		err("cannot remap MMIO region %llx @ %llx",
 			(unsigned long long)pci_resource_len(hc_dev, 1),
 			(unsigned long long)pci_resource_start(hc_dev, 1));
@@ -146,7 +146,7 @@ exit_disable_device:
 
 static int zt5550_hc_cleanup(void)
 {
-	if(!hc_dev)
+	if (!hc_dev)
 		return -ENODEV;
 
 	iounmap(hc_registers);
@@ -170,9 +170,9 @@ static int zt5550_hc_check_irq(void *dev_id)
 	u8 reg;
 
 	ret = 0;
-	if(dev_id == zt5550_hpc.dev_id) {
+	if (dev_id == zt5550_hpc.dev_id) {
 		reg = readb(csr_int_status);
-		if(reg)
+		if (reg)
 			ret = 1;
 	}
 	return ret;
@@ -182,9 +182,9 @@ static int zt5550_hc_enable_irq(void)
 {
 	u8 reg;
 
-	if(hc_dev == NULL) {
+	if (hc_dev == NULL)
 		return -ENODEV;
-	}
+
 	reg = readb(csr_int_mask);
 	reg = reg & ~ENUM_INT_MASK;
 	writeb(reg, csr_int_mask);
@@ -195,9 +195,8 @@ static int zt5550_hc_disable_irq(void)
 {
 	u8 reg;
 
-	if(hc_dev == NULL) {
+	if (hc_dev == NULL)
 		return -ENODEV;
-	}
 
 	reg = readb(csr_int_mask);
 	reg = reg | ENUM_INT_MASK;
@@ -210,15 +209,15 @@ static int zt5550_hc_init_one (struct pci_dev *pdev, const struct pci_device_id
 	int status;
 
 	status = zt5550_hc_config(pdev);
-	if(status != 0) {
+	if (status != 0)
 		return status;
-	}
+
 	dbg("returned from zt5550_hc_config");
 
 	memset(&zt5550_hpc, 0, sizeof (struct cpci_hp_controller));
 	zt5550_hpc_ops.query_enum = zt5550_hc_query_enum;
 	zt5550_hpc.ops = &zt5550_hpc_ops;
-	if(!poll) {
+	if (!poll) {
 		zt5550_hpc.irq = hc_dev->irq;
 		zt5550_hpc.irq_flags = IRQF_SHARED;
 		zt5550_hpc.dev_id = hc_dev;
@@ -231,15 +230,16 @@ static int zt5550_hc_init_one (struct pci_dev *pdev, const struct pci_device_id
 	}
 
 	status = cpci_hp_register_controller(&zt5550_hpc);
-	if(status != 0) {
+	if (status != 0) {
 		err("could not register cPCI hotplug controller");
 		goto init_hc_error;
 	}
 	dbg("registered controller");
 
 	/* Look for first device matching cPCI bus's bridge vendor and device IDs */
-	if(!(bus0_dev = pci_get_device(PCI_VENDOR_ID_DEC,
-					 PCI_DEVICE_ID_DEC_21154, NULL))) {
+	bus0_dev = pci_get_device(PCI_VENDOR_ID_DEC,
+				  PCI_DEVICE_ID_DEC_21154, NULL);
+	if (!bus0_dev) {
 		status = -ENODEV;
 		goto init_register_error;
 	}
@@ -247,14 +247,14 @@ static int zt5550_hc_init_one (struct pci_dev *pdev, const struct pci_device_id
 	pci_dev_put(bus0_dev);
 
 	status = cpci_hp_register_bus(bus0, 0x0a, 0x0f);
-	if(status != 0) {
+	if (status != 0) {
 		err("could not register cPCI hotplug bus");
 		goto init_register_error;
 	}
 	dbg("registered bus");
 
 	status = cpci_hp_start();
-	if(status != 0) {
+	if (status != 0) {
 		err("could not started cPCI hotplug system");
 		cpci_hp_unregister_bus(bus0);
 		goto init_register_error;
@@ -300,11 +300,11 @@ static int __init zt5550_init(void)
 
 	info(DRIVER_DESC " version: " DRIVER_VERSION);
 	r = request_region(ENUM_PORT, 1, "#ENUM hotswap signal register");
-	if(!r)
+	if (!r)
 		return -EBUSY;
 
 	rc = pci_register_driver(&zt5550_hc_driver);
-	if(rc < 0)
+	if (rc < 0)
 		release_region(ENUM_PORT, 1);
 	return rc;
 }
diff --git a/drivers/pci/hotplug/cpqphp.h b/drivers/pci/hotplug/cpqphp.h
index 0450f405807d..b28b2d2184cd 100644
--- a/drivers/pci/hotplug/cpqphp.h
+++ b/drivers/pci/hotplug/cpqphp.h
@@ -690,7 +690,7 @@ static inline int cpq_get_latch_status(struct controller *ctrl,
 
 	status = (readl(ctrl->hpc_reg + INT_INPUT_CLEAR) & (0x01L << hp_slot));
 
-	return(status == 0) ? 1 : 0;
+	return (status == 0) ? 1 : 0;
 }
 
 
diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c
index 4aaee746df88..a53084ddc118 100644
--- a/drivers/pci/hotplug/cpqphp_core.c
+++ b/drivers/pci/hotplug/cpqphp_core.c
@@ -1096,9 +1096,8 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* initialize our threads if they haven't already been started up */
 	rc = one_time_init();
-	if (rc) {
+	if (rc)
 		goto err_free_bus;
-	}
 
 	dbg("pdev = %p\n", pdev);
 	dbg("pci resource start %llx\n", (unsigned long long)pci_resource_start(pdev, 0));
diff --git a/drivers/pci/hotplug/cpqphp_ctrl.c b/drivers/pci/hotplug/cpqphp_ctrl.c
index bde47fce3248..c5cbefee5236 100644
--- a/drivers/pci/hotplug/cpqphp_ctrl.c
+++ b/drivers/pci/hotplug/cpqphp_ctrl.c
@@ -705,9 +705,8 @@ static struct pci_resource *get_max_resource(struct pci_resource **head, u32 siz
 		if (temp == max) {
 			*head = max->next;
 		} else {
-			while (temp && temp->next != max) {
+			while (temp && temp->next != max)
 				temp = temp->next;
-			}
 
 			if (temp)
 				temp->next = max->next;
@@ -903,9 +902,8 @@ irqreturn_t cpqhp_ctrl_intr(int IRQ, void *data)
 	/*
 	 * Check to see if it was our interrupt
 	 */
-	if (!(misc & 0x000C)) {
+	if (!(misc & 0x000C))
 		return IRQ_NONE;
-	}
 
 	if (misc & 0x0004) {
 		/*
@@ -1143,7 +1141,7 @@ static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_
 	/* We don't allow freq/mode changes if we find another adapter running
 	 * in another slot on this controller
 	 */
-	for(slot = ctrl->slot; slot; slot = slot->next) {
+	for (slot = ctrl->slot; slot; slot = slot->next) {
 		if (slot->device == (hp_slot + ctrl->slot_device_offset))
 			continue;
 		if (!slot->hotplug_slot || !slot->hotplug_slot->info)
@@ -1193,7 +1191,7 @@ static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_
 
 	reg16 = readw(ctrl->hpc_reg + NEXT_CURR_FREQ);
 	reg16 &= ~0x000F;
-	switch(adapter_speed) {
+	switch (adapter_speed) {
 		case(PCI_SPEED_133MHz_PCIX):
 			reg = 0x75;
 			reg16 |= 0xB;
@@ -2006,9 +2004,8 @@ int cpqhp_process_SI(struct controller *ctrl, struct pci_func *func)
 	/* Check to see if the interlock is closed */
 	tempdword = readl(ctrl->hpc_reg + INT_INPUT_CLEAR);
 
-	if (tempdword & (0x01 << hp_slot)) {
+	if (tempdword & (0x01 << hp_slot))
 		return 1;
-	}
 
 	if (func->is_a_board) {
 		rc = board_replaced(func, ctrl);
@@ -2070,9 +2067,8 @@ int cpqhp_process_SI(struct controller *ctrl, struct pci_func *func)
 		}
 	}
 
-	if (rc) {
+	if (rc)
 		dbg("%s: rc = %d\n", __func__, rc);
-	}
 
 	if (p_slot)
 		update_slot_info(ctrl, p_slot);
@@ -2095,9 +2091,8 @@ int cpqhp_process_SS(struct controller *ctrl, struct pci_func *func)
 	device = func->device;
 	func = cpqhp_slot_find(ctrl->bus, device, index++);
 	p_slot = cpqhp_find_slot(ctrl, device);
-	if (p_slot) {
+	if (p_slot)
 		physical_slot = p_slot->number;
-	}
 
 	/* Make sure there are no video controllers here */
 	while (func && !rc) {
diff --git a/drivers/pci/hotplug/cpqphp_nvram.c b/drivers/pci/hotplug/cpqphp_nvram.c
index 0968a9bcb345..1e08ff8c229c 100644
--- a/drivers/pci/hotplug/cpqphp_nvram.c
+++ b/drivers/pci/hotplug/cpqphp_nvram.c
@@ -204,9 +204,8 @@ static int load_HRT (void __iomem *rom_start)
 	u8 temp_byte = 0xFF;
 	u32 rc;
 
-	if (!check_for_compaq_ROM(rom_start)) {
+	if (!check_for_compaq_ROM(rom_start))
 		return -ENODEV;
-	}
 
 	available = 1024;
 
@@ -250,9 +249,8 @@ static u32 store_HRT (void __iomem *rom_start)
 
 	available = 1024;
 
-	if (!check_for_compaq_ROM(rom_start)) {
+	if (!check_for_compaq_ROM(rom_start))
 		return(1);
-	}
 
 	buffer = (u32*) evbuffer;
 
@@ -427,9 +425,9 @@ static u32 store_HRT (void __iomem *rom_start)
 
 void compaq_nvram_init (void __iomem *rom_start)
 {
-	if (rom_start) {
+	if (rom_start)
 		compaq_int15_entry_point = (rom_start + ROM_INT15_PHY_ADDR - ROM_PHY_ADDR);
-	}
+
 	dbg("int15 entry  = %p\n", compaq_int15_entry_point);
 
 	/* initialize our int15 lock */
@@ -661,9 +659,8 @@ int compaq_nvram_store (void __iomem *rom_start)
 
 	if (evbuffer_init) {
 		rc = store_HRT(rom_start);
-		if (rc) {
+		if (rc)
 			err(msg_unable_to_save);
-		}
 	}
 	return rc;
 }
diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c
index f7b8684a7739..3efaf4c38528 100644
--- a/drivers/pci/hotplug/ibmphp_core.c
+++ b/drivers/pci/hotplug/ibmphp_core.c
@@ -1023,7 +1023,8 @@ static int enable_slot(struct hotplug_slot *hs)
 	debug("ENABLING SLOT........\n");
 	slot_cur = hs->private;
 
-	if ((rc = validate(slot_cur, ENABLE))) {
+	rc = validate(slot_cur, ENABLE);
+	if (rc) {
 		err("validate function failed\n");
 		goto error_nopower;
 	}
@@ -1199,9 +1200,8 @@ int ibmphp_do_disable_slot(struct slot *slot_cur)
 
 	debug("DISABLING SLOT...\n");
 
-	if ((slot_cur == NULL) || (slot_cur->ctrl == NULL)) {
+	if ((slot_cur == NULL) || (slot_cur->ctrl == NULL))
 		return -ENODEV;
-	}
 
 	flag = slot_cur->flag;
 	slot_cur->flag = 1;
@@ -1336,17 +1336,20 @@ static int __init ibmphp_init(void)
 	for (i = 0; i < 16; i++)
 		irqs[i] = 0;
 
-	if ((rc = ibmphp_access_ebda()))
+	rc = ibmphp_access_ebda();
+	if (rc)
 		goto error;
 	debug("after ibmphp_access_ebda()\n");
 
-	if ((rc = ibmphp_rsrc_init()))
+	rc = ibmphp_rsrc_init();
+	if (rc)
 		goto error;
 	debug("AFTER Resource & EBDA INITIALIZATIONS\n");
 
 	max_slots = get_max_slots();
 
-	if ((rc = ibmphp_register_pci()))
+	rc = ibmphp_register_pci();
+	if (rc)
 		goto error;
 
 	if (init_ops()) {
@@ -1355,9 +1358,9 @@ static int __init ibmphp_init(void)
 	}
 
 	ibmphp_print_test();
-	if ((rc = ibmphp_hpc_start_poll_thread())) {
+	rc = ibmphp_hpc_start_poll_thread();
+	if (rc)
 		goto error;
-	}
 
 exit:
 	return rc;
diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c
index 0f65ac555434..d9b197d5c6b4 100644
--- a/drivers/pci/hotplug/ibmphp_ebda.c
+++ b/drivers/pci/hotplug/ibmphp_ebda.c
@@ -215,9 +215,8 @@ static void __init print_ebda_hpc (void)
 			debug ("%s - cap of the slot: %x\n", __func__, hpc_ptr->slots[index].slot_cap);
 		}
 
-		for (index = 0; index < hpc_ptr->bus_count; index++) {
+		for (index = 0; index < hpc_ptr->bus_count; index++)
 			debug ("%s - bus# of each bus controlled by this ctlr: %x\n", __func__, hpc_ptr->buses[index].bus_num);
-		}
 
 		debug ("%s - type of hpc: %x\n", __func__, hpc_ptr->ctlr_type);
 		switch (hpc_ptr->ctlr_type) {
diff --git a/drivers/pci/hotplug/ibmphp_hpc.c b/drivers/pci/hotplug/ibmphp_hpc.c
index a936022956e6..220876715a08 100644
--- a/drivers/pci/hotplug/ibmphp_hpc.c
+++ b/drivers/pci/hotplug/ibmphp_hpc.c
@@ -997,9 +997,8 @@ static int process_changeinstatus (struct slot *pslot, struct slot *poldslot)
 		rc = ibmphp_do_disable_slot (pslot);
 	}
 
-	if (update || disable) {
+	if (update || disable)
 		ibmphp_update_slot_info (pslot);
-	}
 
 	debug ("%s - Exit rc[%d] disable[%x] update[%x]\n", __func__, rc, disable, update);
 
diff --git a/drivers/pci/hotplug/ibmphp_pci.c b/drivers/pci/hotplug/ibmphp_pci.c
index 2fd296706ce7..814cea22a9fa 100644
--- a/drivers/pci/hotplug/ibmphp_pci.c
+++ b/drivers/pci/hotplug/ibmphp_pci.c
@@ -145,7 +145,8 @@ int ibmphp_configure_card (struct pci_func *func, u8 slotno)
 				case PCI_HEADER_TYPE_NORMAL:
 					debug ("single device case.... vendor id = %x, hdr_type = %x, class = %x\n", vendor_id, hdr_type, class);
 					assign_alt_irq (cur_func, class_code);
-					if ((rc = configure_device (cur_func)) < 0) {
+					rc = configure_device(cur_func);
+					if (rc < 0) {
 						/* We need to do this in case some other BARs were properly inserted */
 						err ("was not able to configure devfunc %x on bus %x.\n",
 						     cur_func->device, cur_func->busno);
@@ -157,7 +158,8 @@ int ibmphp_configure_card (struct pci_func *func, u8 slotno)
 					break;
 				case PCI_HEADER_TYPE_MULTIDEVICE:
 					assign_alt_irq (cur_func, class_code);
-					if ((rc = configure_device (cur_func)) < 0) {
+					rc = configure_device(cur_func);
+					if (rc < 0) {
 						/* We need to do this in case some other BARs were properly inserted */
 						err ("was not able to configure devfunc %x on bus %x...bailing out\n",
 						     cur_func->device, cur_func->busno);
diff --git a/drivers/pci/hotplug/ibmphp_res.c b/drivers/pci/hotplug/ibmphp_res.c
index f34745abd5b6..219ba8090a37 100644
--- a/drivers/pci/hotplug/ibmphp_res.c
+++ b/drivers/pci/hotplug/ibmphp_res.c
@@ -224,7 +224,8 @@ int __init ibmphp_rsrc_init (void)
 			if ((curr->rsrc_type & RESTYPE) == MMASK) {
 				/* no bus structure exists in place yet */
 				if (list_empty (&gbuses)) {
-					if ((rc = alloc_bus_range (&newbus, &newrange, curr, MEM, 1)))
+					rc = alloc_bus_range(&newbus, &newrange, curr, MEM, 1);
+					if (rc)
 						return rc;
 					list_add_tail (&newbus->bus_list, &gbuses);
 					debug ("gbuses = NULL, Memory Primary Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
@@ -237,7 +238,8 @@ int __init ibmphp_rsrc_init (void)
 							return rc;
 					} else {
 						/* went through all the buses and didn't find ours, need to create a new bus node */
-						if ((rc = alloc_bus_range (&newbus, &newrange, curr, MEM, 1)))
+						rc = alloc_bus_range(&newbus, &newrange, curr, MEM, 1);
+						if (rc)
 							return rc;
 
 						list_add_tail (&newbus->bus_list, &gbuses);
@@ -248,7 +250,8 @@ int __init ibmphp_rsrc_init (void)
 				/* prefetchable memory */
 				if (list_empty (&gbuses)) {
 					/* no bus structure exists in place yet */
-					if ((rc = alloc_bus_range (&newbus, &newrange, curr, PFMEM, 1)))
+					rc = alloc_bus_range(&newbus, &newrange, curr, PFMEM, 1);
+					if (rc)
 						return rc;
 					list_add_tail (&newbus->bus_list, &gbuses);
 					debug ("gbuses = NULL, PFMemory Primary Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
@@ -261,7 +264,8 @@ int __init ibmphp_rsrc_init (void)
 							return rc;
 					} else {
 						/* went through all the buses and didn't find ours, need to create a new bus node */
-						if ((rc = alloc_bus_range (&newbus, &newrange, curr, PFMEM, 1)))
+						rc = alloc_bus_range(&newbus, &newrange, curr, PFMEM, 1);
+						if (rc)
 							return rc;
 						list_add_tail (&newbus->bus_list, &gbuses);
 						debug ("1st Bus, PFMemory Primary Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
@@ -271,7 +275,8 @@ int __init ibmphp_rsrc_init (void)
 				/* IO */
 				if (list_empty (&gbuses)) {
 					/* no bus structure exists in place yet */
-					if ((rc = alloc_bus_range (&newbus, &newrange, curr, IO, 1)))
+					rc = alloc_bus_range(&newbus, &newrange, curr, IO, 1);
+					if (rc)
 						return rc;
 					list_add_tail (&newbus->bus_list, &gbuses);
 					debug ("gbuses = NULL, IO Primary Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
@@ -283,7 +288,8 @@ int __init ibmphp_rsrc_init (void)
 							return rc;
 					} else {
 						/* went through all the buses and didn't find ours, need to create a new bus node */
-						if ((rc = alloc_bus_range (&newbus, &newrange, curr, IO, 1)))
+						rc = alloc_bus_range(&newbus, &newrange, curr, IO, 1);
+						if (rc)
 							return rc;
 						list_add_tail (&newbus->bus_list, &gbuses);
 						debug ("1st Bus, IO Primary Bus %x [%x - %x]\n", newbus->busno, newrange->start, newrange->end);
@@ -1038,7 +1044,9 @@ int ibmphp_check_resource (struct resource_node *res, u8 bridge)
 		/* found our range */
 		if (!res_prev) {
 			/* first time in the loop */
-			if ((res_cur->start != range->start) && ((len_tmp = res_cur->start - 1 - range->start) >= res->len)) {
+			len_tmp = res_cur->start - 1 - range->start;
+
+			if ((res_cur->start != range->start) && (len_tmp >= res->len)) {
 				debug ("len_tmp = %x\n", len_tmp);
 
 				if ((len_tmp < len_cur) || (len_cur == 0)) {
@@ -1078,7 +1086,9 @@ int ibmphp_check_resource (struct resource_node *res, u8 bridge)
 		}
 		if (!res_cur->next) {
 			/* last device on the range */
-			if ((range->end != res_cur->end) && ((len_tmp = range->end - (res_cur->end + 1)) >= res->len)) {
+			len_tmp = range->end - (res_cur->end + 1);
+
+			if ((range->end != res_cur->end) && (len_tmp >= res->len)) {
 				debug ("len_tmp = %x\n", len_tmp);
 				if ((len_tmp < len_cur) || (len_cur == 0)) {
 
@@ -1117,8 +1127,9 @@ int ibmphp_check_resource (struct resource_node *res, u8 bridge)
 		if (res_prev) {
 			if (res_prev->rangeno != res_cur->rangeno) {
 				/* 1st device on this range */
-				if ((res_cur->start != range->start) &&
-					((len_tmp = res_cur->start - 1 - range->start) >= res->len)) {
+				len_tmp = res_cur->start - 1 - range->start;
+
+				if ((res_cur->start != range->start) &&	(len_tmp >= res->len)) {
 					if ((len_tmp < len_cur) || (len_cur == 0)) {
 						if ((range->start % tmp_divide) == 0) {
 							/* just perfect, starting address is divisible by length */
@@ -1153,7 +1164,9 @@ int ibmphp_check_resource (struct resource_node *res, u8 bridge)
 				}
 			} else {
 				/* in the same range */
-				if ((len_tmp = res_cur->start - 1 - res_prev->end - 1) >= res->len) {
+				len_tmp = res_cur->start - 1 - res_prev->end - 1;
+
+				if (len_tmp >= res->len) {
 					if ((len_tmp < len_cur) || (len_cur == 0)) {
 						if (((res_prev->end + 1) % tmp_divide) == 0) {
 							/* just perfect, starting address's divisible by length */
@@ -1212,7 +1225,9 @@ int ibmphp_check_resource (struct resource_node *res, u8 bridge)
 				break;
 		}
 		while (range) {
-			if ((len_tmp = range->end - range->start) >= res->len) {
+			len_tmp = range->end - range->start;
+
+			if (len_tmp >= res->len) {
 				if ((len_tmp < len_cur) || (len_cur == 0)) {
 					if ((range->start % tmp_divide) == 0) {
 						/* just perfect, starting address's divisible by length */
@@ -1276,7 +1291,9 @@ int ibmphp_check_resource (struct resource_node *res, u8 bridge)
 					break;
 			}
 			while (range) {
-				if ((len_tmp = range->end - range->start) >= res->len) {
+				len_tmp = range->end - range->start;
+
+				if (len_tmp >= res->len) {
 					if ((len_tmp < len_cur) || (len_cur == 0)) {
 						if ((range->start % tmp_divide) == 0) {
 							/* just perfect, starting address's divisible by length */
@@ -1335,7 +1352,7 @@ int ibmphp_check_resource (struct resource_node *res, u8 bridge)
 				return -EINVAL;
 			}
 		}
-	}	/* end if(!res_cur) */
+	}	/* end if (!res_cur) */
 	return -EINVAL;
 }
 
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 9e5a9fbb93d7..b11521953485 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -92,7 +92,7 @@ struct controller {
 	struct slot *slot;
 	wait_queue_head_t queue;	/* sleep & wake process */
 	u32 slot_cap;
-	u32 slot_ctrl;
+	u16 slot_ctrl;
 	struct timer_list poll_timer;
 	unsigned long cmd_started;	/* jiffies */
 	unsigned int cmd_busy:1;
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 07aa722bb12c..3a5e7e28b874 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -262,6 +262,13 @@ static int pciehp_probe(struct pcie_device *dev)
 		goto err_out_none;
 	}
 
+	if (!dev->port->subordinate) {
+		/* Can happen if we run out of bus numbers during probe */
+		dev_err(&dev->device,
+			"Hotplug bridge without secondary bus, ignoring\n");
+		goto err_out_none;
+	}
+
 	ctrl = pcie_init(dev);
 	if (!ctrl) {
 		dev_err(&dev->device, "Controller initialization failed\n");
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 2a412fa3b338..0ebf754fc177 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -171,9 +171,9 @@ static void pcie_wait_cmd(struct controller *ctrl)
 	 * interrupts.
 	 */
 	if (!rc)
-		ctrl_info(ctrl, "Timeout on hotplug command %#010x (issued %u msec ago)\n",
+		ctrl_info(ctrl, "Timeout on hotplug command %#06x (issued %u msec ago)\n",
 			  ctrl->slot_ctrl,
-			  jiffies_to_msecs(now - ctrl->cmd_started));
+			  jiffies_to_msecs(jiffies - ctrl->cmd_started));
 }
 
 /**
@@ -422,9 +422,9 @@ void pciehp_set_attention_status(struct slot *slot, u8 value)
 	default:
 		return;
 	}
+	pcie_write_cmd(ctrl, slot_cmd, PCI_EXP_SLTCTL_AIC);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
-	pcie_write_cmd(ctrl, slot_cmd, PCI_EXP_SLTCTL_AIC);
 }
 
 void pciehp_green_led_on(struct slot *slot)
@@ -614,6 +614,8 @@ void pcie_enable_notification(struct controller *ctrl)
 		PCI_EXP_SLTCTL_DLLSCE);
 
 	pcie_write_cmd(ctrl, cmd, mask);
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, cmd);
 }
 
 static void pcie_disable_notification(struct controller *ctrl)
@@ -625,6 +627,8 @@ static void pcie_disable_notification(struct controller *ctrl)
 		PCI_EXP_SLTCTL_HPIE | PCI_EXP_SLTCTL_CCIE |
 		PCI_EXP_SLTCTL_DLLSCE);
 	pcie_write_cmd(ctrl, 0, mask);
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0);
 }
 
 /*
@@ -652,6 +656,8 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	stat_mask |= PCI_EXP_SLTSTA_DLLSC;
 
 	pcie_write_cmd(ctrl, 0, ctrl_mask);
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0);
 	if (pciehp_poll_mode)
 		del_timer_sync(&ctrl->poll_timer);
 
@@ -659,6 +665,8 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, stat_mask);
 	pcie_write_cmd(ctrl, ctrl_mask, ctrl_mask);
+	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
+		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask);
 	if (pciehp_poll_mode)
 		int_poll_timeout(ctrl->poll_timer.data);
 
@@ -797,9 +805,6 @@ struct controller *pcie_init(struct pcie_device *dev)
 		PCI_EXP_SLTSTA_MRLSC | PCI_EXP_SLTSTA_PDC |
 		PCI_EXP_SLTSTA_CC | PCI_EXP_SLTSTA_DLLSC);
 
-	/* Disable software notification */
-	pcie_disable_notification(ctrl);
-
 	ctrl_info(ctrl, "Slot #%d AttnBtn%c AttnInd%c PwrInd%c PwrCtrl%c MRL%c Interlock%c NoCompl%c LLActRep%c\n",
 		(slot_cap & PCI_EXP_SLTCAP_PSN) >> 19,
 		FLAG(slot_cap, PCI_EXP_SLTCAP_ABP),
diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c
index 5f871f4c4af1..9e69403be632 100644
--- a/drivers/pci/hotplug/pciehp_pci.c
+++ b/drivers/pci/hotplug/pciehp_pci.c
@@ -65,14 +65,7 @@ int pciehp_configure_device(struct slot *p_slot)
 			pci_hp_add_bridge(dev);
 
 	pci_assign_unassigned_bridge_resources(bridge);
-
-	list_for_each_entry(dev, &parent->devices, bus_list) {
-		if ((dev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
-			continue;
-
-		pci_configure_slot(dev);
-	}
-
+	pcie_bus_configure_settings(parent);
 	pci_bus_add_devices(parent);
 
  out:
diff --git a/drivers/pci/hotplug/pcihp_slot.c b/drivers/pci/hotplug/pcihp_slot.c
deleted file mode 100644
index 3e36ec8d708a..000000000000
--- a/drivers/pci/hotplug/pcihp_slot.c
+++ /dev/null
@@ -1,176 +0,0 @@
-/*
- * Copyright (C) 1995,2001 Compaq Computer Corporation
- * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com)
- * Copyright (C) 2001 IBM Corp.
- * Copyright (C) 2003-2004 Intel Corporation
- * (c) Copyright 2009 Hewlett-Packard Development Company, L.P.
- *
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or (at
- * your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/pci.h>
-#include <linux/export.h>
-#include <linux/pci_hotplug.h>
-
-static struct hpp_type0 pci_default_type0 = {
-	.revision = 1,
-	.cache_line_size = 8,
-	.latency_timer = 0x40,
-	.enable_serr = 0,
-	.enable_perr = 0,
-};
-
-static void program_hpp_type0(struct pci_dev *dev, struct hpp_type0 *hpp)
-{
-	u16 pci_cmd, pci_bctl;
-
-	if (!hpp) {
-		/*
-		 * Perhaps we *should* use default settings for PCIe, but
-		 * pciehp didn't, so we won't either.
-		 */
-		if (pci_is_pcie(dev))
-			return;
-		hpp = &pci_default_type0;
-	}
-
-	if (hpp->revision > 1) {
-		dev_warn(&dev->dev,
-			 "PCI settings rev %d not supported; using defaults\n",
-			 hpp->revision);
-		hpp = &pci_default_type0;
-	}
-
-	pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, hpp->cache_line_size);
-	pci_write_config_byte(dev, PCI_LATENCY_TIMER, hpp->latency_timer);
-	pci_read_config_word(dev, PCI_COMMAND, &pci_cmd);
-	if (hpp->enable_serr)
-		pci_cmd |= PCI_COMMAND_SERR;
-	else
-		pci_cmd &= ~PCI_COMMAND_SERR;
-	if (hpp->enable_perr)
-		pci_cmd |= PCI_COMMAND_PARITY;
-	else
-		pci_cmd &= ~PCI_COMMAND_PARITY;
-	pci_write_config_word(dev, PCI_COMMAND, pci_cmd);
-
-	/* Program bridge control value */
-	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
-		pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER,
-				      hpp->latency_timer);
-		pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &pci_bctl);
-		if (hpp->enable_serr)
-			pci_bctl |= PCI_BRIDGE_CTL_SERR;
-		else
-			pci_bctl &= ~PCI_BRIDGE_CTL_SERR;
-		if (hpp->enable_perr)
-			pci_bctl |= PCI_BRIDGE_CTL_PARITY;
-		else
-			pci_bctl &= ~PCI_BRIDGE_CTL_PARITY;
-		pci_write_config_word(dev, PCI_BRIDGE_CONTROL, pci_bctl);
-	}
-}
-
-static void program_hpp_type1(struct pci_dev *dev, struct hpp_type1 *hpp)
-{
-	if (hpp)
-		dev_warn(&dev->dev, "PCI-X settings not supported\n");
-}
-
-static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp)
-{
-	int pos;
-	u32 reg32;
-
-	if (!hpp)
-		return;
-
-	if (hpp->revision > 1) {
-		dev_warn(&dev->dev, "PCIe settings rev %d not supported\n",
-			 hpp->revision);
-		return;
-	}
-
-	/* Initialize Device Control Register */
-	pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL,
-			~hpp->pci_exp_devctl_and, hpp->pci_exp_devctl_or);
-
-	/* Initialize Link Control Register */
-	if (dev->subordinate)
-		pcie_capability_clear_and_set_word(dev, PCI_EXP_LNKCTL,
-			~hpp->pci_exp_lnkctl_and, hpp->pci_exp_lnkctl_or);
-
-	/* Find Advanced Error Reporting Enhanced Capability */
-	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
-	if (!pos)
-		return;
-
-	/* Initialize Uncorrectable Error Mask Register */
-	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &reg32);
-	reg32 = (reg32 & hpp->unc_err_mask_and) | hpp->unc_err_mask_or;
-	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, reg32);
-
-	/* Initialize Uncorrectable Error Severity Register */
-	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &reg32);
-	reg32 = (reg32 & hpp->unc_err_sever_and) | hpp->unc_err_sever_or;
-	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, reg32);
-
-	/* Initialize Correctable Error Mask Register */
-	pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, &reg32);
-	reg32 = (reg32 & hpp->cor_err_mask_and) | hpp->cor_err_mask_or;
-	pci_write_config_dword(dev, pos + PCI_ERR_COR_MASK, reg32);
-
-	/* Initialize Advanced Error Capabilities and Control Register */
-	pci_read_config_dword(dev, pos + PCI_ERR_CAP, &reg32);
-	reg32 = (reg32 & hpp->adv_err_cap_and) | hpp->adv_err_cap_or;
-	pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32);
-
-	/*
-	 * FIXME: The following two registers are not supported yet.
-	 *
-	 *   o Secondary Uncorrectable Error Severity Register
-	 *   o Secondary Uncorrectable Error Mask Register
-	 */
-}
-
-void pci_configure_slot(struct pci_dev *dev)
-{
-	struct pci_dev *cdev;
-	struct hotplug_params hpp;
-
-	if (!(dev->hdr_type == PCI_HEADER_TYPE_NORMAL ||
-			(dev->hdr_type == PCI_HEADER_TYPE_BRIDGE &&
-			(dev->class >> 8) == PCI_CLASS_BRIDGE_PCI)))
-		return;
-
-	pcie_bus_configure_settings(dev->bus);
-
-	memset(&hpp, 0, sizeof(hpp));
-	pci_get_hp_params(dev, &hpp);
-
-	program_hpp_type2(dev, hpp.t2);
-	program_hpp_type1(dev, hpp.t1);
-	program_hpp_type0(dev, hpp.t0);
-
-	if (dev->subordinate) {
-		list_for_each_entry(cdev, &dev->subordinate->devices,
-				    bus_list)
-			pci_configure_slot(cdev);
-	}
-}
-EXPORT_SYMBOL_GPL(pci_configure_slot);
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
index a81fb67ea9a1..10c7927599b3 100644
--- a/drivers/pci/hotplug/shpchp_ctrl.c
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -195,7 +195,8 @@ static int change_bus_speed(struct controller *ctrl, struct slot *p_slot,
 	int rc = 0;
 
 	ctrl_dbg(ctrl, "Change speed to %d\n", speed);
-	if ((rc = p_slot->hpc_ops->set_bus_speed_mode(p_slot, speed))) {
+	rc = p_slot->hpc_ops->set_bus_speed_mode(p_slot, speed);
+	if (rc) {
 		ctrl_err(ctrl, "%s: Issue of set bus speed mode command failed\n",
 			 __func__);
 		return WRONG_BUS_FREQUENCY;
@@ -261,14 +262,16 @@ static int board_added(struct slot *p_slot)
 	}
 
 	if ((ctrl->pci_dev->vendor == 0x8086) && (ctrl->pci_dev->device == 0x0332)) {
-		if ((rc = p_slot->hpc_ops->set_bus_speed_mode(p_slot, PCI_SPEED_33MHz))) {
+		rc = p_slot->hpc_ops->set_bus_speed_mode(p_slot, PCI_SPEED_33MHz);
+		if (rc) {
 			ctrl_err(ctrl, "%s: Issue of set bus speed mode command failed\n",
 				 __func__);
 			return WRONG_BUS_FREQUENCY;
 		}
 
 		/* turn on board, blink green LED, turn off Amber LED */
-		if ((rc = p_slot->hpc_ops->slot_enable(p_slot))) {
+		rc = p_slot->hpc_ops->slot_enable(p_slot);
+		if (rc) {
 			ctrl_err(ctrl, "Issue of Slot Enable command failed\n");
 			return rc;
 		}
@@ -296,7 +299,8 @@ static int board_added(struct slot *p_slot)
 		return rc;
 
 	/* turn on board, blink green LED, turn off Amber LED */
-	if ((rc = p_slot->hpc_ops->slot_enable(p_slot))) {
+	rc = p_slot->hpc_ops->slot_enable(p_slot);
+	if (rc) {
 		ctrl_err(ctrl, "Issue of Slot Enable command failed\n");
 		return rc;
 	}
@@ -595,7 +599,7 @@ static int shpchp_enable_slot (struct slot *p_slot)
 	ctrl_dbg(ctrl, "%s: p_slot->pwr_save %x\n", __func__, p_slot->pwr_save);
 	p_slot->hpc_ops->get_latch_status(p_slot, &getstatus);
 
-	if(((p_slot->ctrl->pci_dev->vendor == PCI_VENDOR_ID_AMD) ||
+	if (((p_slot->ctrl->pci_dev->vendor == PCI_VENDOR_ID_AMD) ||
 	    (p_slot->ctrl->pci_dev->device == PCI_DEVICE_ID_AMD_POGO_7458))
 	     && p_slot->ctrl->num_slots == 1) {
 		/* handle amd pogo errata; this must be done before enable  */
diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c
index 29e22352822c..7d223e9080ef 100644
--- a/drivers/pci/hotplug/shpchp_hpc.c
+++ b/drivers/pci/hotplug/shpchp_hpc.c
@@ -466,7 +466,8 @@ static int hpc_get_adapter_speed(struct slot *slot, enum pci_bus_speed *value)
 	u8 m66_cap  = !!(slot_reg & MHZ66_CAP);
 	u8 pi, pcix_cap;
 
-	if ((retval = hpc_get_prog_int(slot, &pi)))
+	retval = hpc_get_prog_int(slot, &pi);
+	if (retval)
 		return retval;
 
 	switch (pi) {
@@ -798,7 +799,7 @@ static irqreturn_t shpc_isr(int irq, void *dev_id)
 
 	ctrl_dbg(ctrl, "%s: intr_loc = %x\n", __func__, intr_loc);
 
-	if(!shpchp_poll_mode) {
+	if (!shpchp_poll_mode) {
 		/*
 		 * Mask Global Interrupt Mask - see implementation
 		 * note on p. 139 of SHPC spec rev 1.0
diff --git a/drivers/pci/hotplug/shpchp_pci.c b/drivers/pci/hotplug/shpchp_pci.c
index 469454e0cc48..f8cd3a27e351 100644
--- a/drivers/pci/hotplug/shpchp_pci.c
+++ b/drivers/pci/hotplug/shpchp_pci.c
@@ -69,13 +69,7 @@ int shpchp_configure_device(struct slot *p_slot)
 	}
 
 	pci_assign_unassigned_bridge_resources(bridge);
-
-	list_for_each_entry(dev, &parent->devices, bus_list) {
-		if (PCI_SLOT(dev->devfn) != p_slot->device)
-			continue;
-		pci_configure_slot(dev);
-	}
-
+	pcie_bus_configure_settings(parent);
 	pci_bus_add_devices(parent);
 
  out:
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index cb6f24740ee3..4d109c07294a 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -633,7 +633,7 @@ int pci_vfs_assigned(struct pci_dev *dev)
 		 * our dev as the physical function and the assigned bit is set
 		 */
 		if (vfdev->is_virtfn && (vfdev->physfn == dev) &&
-		    (vfdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED))
+			pci_is_dev_assigned(vfdev))
 			vfs_assigned++;
 
 		vfdev = pci_get_device(dev->vendor, dev_id, vfdev);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 5a40516444f3..9fab30af0e75 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -56,16 +56,6 @@ void __weak arch_teardown_msi_irq(unsigned int irq)
 	chip->teardown_irq(chip, irq);
 }
 
-int __weak arch_msi_check_device(struct pci_dev *dev, int nvec, int type)
-{
-	struct msi_chip *chip = dev->bus->msi;
-
-	if (!chip || !chip->check_device)
-		return 0;
-
-	return chip->check_device(chip, dev, nvec, type);
-}
-
 int __weak arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
 	struct msi_desc *entry;
@@ -130,7 +120,7 @@ static void default_restore_msi_irq(struct pci_dev *dev, int irq)
 	}
 
 	if (entry)
-		write_msi_msg(irq, &entry->msg);
+		__write_msi_msg(entry, &entry->msg);
 }
 
 void __weak arch_restore_msi_irqs(struct pci_dev *dev)
@@ -312,6 +302,7 @@ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
 
 	__get_cached_msi_msg(entry, msg);
 }
+EXPORT_SYMBOL_GPL(get_cached_msi_msg);
 
 void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
@@ -356,6 +347,7 @@ void write_msi_msg(unsigned int irq, struct msi_msg *msg)
 
 	__write_msi_msg(entry, msg);
 }
+EXPORT_SYMBOL_GPL(write_msi_msg);
 
 static void free_msi_irqs(struct pci_dev *dev)
 {
@@ -384,17 +376,6 @@ static void free_msi_irqs(struct pci_dev *dev)
 				iounmap(entry->mask_base);
 		}
 
-		/*
-		 * Its possible that we get into this path
-		 * When populate_msi_sysfs fails, which means the entries
-		 * were not registered with sysfs.  In that case don't
-		 * unregister them.
-		 */
-		if (entry->kobj.parent) {
-			kobject_del(&entry->kobj);
-			kobject_put(&entry->kobj);
-		}
-
 		list_del(&entry->list);
 		kfree(entry);
 	}
@@ -595,7 +576,6 @@ static struct msi_desc *msi_setup_entry(struct pci_dev *dev)
 	entry->msi_attrib.entry_nr	= 0;
 	entry->msi_attrib.maskbit	= !!(control & PCI_MSI_FLAGS_MASKBIT);
 	entry->msi_attrib.default_irq	= dev->irq;	/* Save IOAPIC IRQ */
-	entry->msi_attrib.pos		= dev->msi_cap;
 	entry->msi_attrib.multi_cap	= (control & PCI_MSI_FLAGS_QMASK) >> 1;
 
 	if (control & PCI_MSI_FLAGS_64BIT)
@@ -699,7 +679,6 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 		entry->msi_attrib.is_64		= 1;
 		entry->msi_attrib.entry_nr	= entries[i].entry;
 		entry->msi_attrib.default_irq	= dev->irq;
-		entry->msi_attrib.pos		= dev->msix_cap;
 		entry->mask_base		= base;
 
 		list_add_tail(&entry->list, &dev->msi_list);
@@ -806,23 +785,24 @@ out_free:
 }
 
 /**
- * pci_msi_check_device - check whether MSI may be enabled on a device
+ * pci_msi_supported - check whether MSI may be enabled on a device
  * @dev: pointer to the pci_dev data structure of MSI device function
  * @nvec: how many MSIs have been requested ?
- * @type: are we checking for MSI or MSI-X ?
  *
  * Look at global flags, the device itself, and its parent buses
  * to determine if MSI/-X are supported for the device. If MSI/-X is
- * supported return 0, else return an error code.
+ * supported return 1, else return 0.
  **/
-static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type)
+static int pci_msi_supported(struct pci_dev *dev, int nvec)
 {
 	struct pci_bus *bus;
-	int ret;
 
 	/* MSI must be globally enabled and supported by the device */
-	if (!pci_msi_enable || !dev || dev->no_msi)
-		return -EINVAL;
+	if (!pci_msi_enable)
+		return 0;
+
+	if (!dev || dev->no_msi || dev->current_state != PCI_D0)
+		return 0;
 
 	/*
 	 * You can't ask to have 0 or less MSIs configured.
@@ -830,7 +810,7 @@ static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type)
 	 *  b) the list manipulation code assumes nvec >= 1.
 	 */
 	if (nvec < 1)
-		return -ERANGE;
+		return 0;
 
 	/*
 	 * Any bridge which does NOT route MSI transactions from its
@@ -841,13 +821,9 @@ static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type)
 	 */
 	for (bus = dev->bus; bus; bus = bus->parent)
 		if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
-			return -EINVAL;
-
-	ret = arch_msi_check_device(dev, nvec, type);
-	if (ret)
-		return ret;
+			return 0;
 
-	return 0;
+	return 1;
 }
 
 /**
@@ -946,15 +922,14 @@ EXPORT_SYMBOL(pci_msix_vec_count);
  **/
 int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
 {
-	int status, nr_entries;
+	int nr_entries;
 	int i, j;
 
-	if (!entries || !dev->msix_cap || dev->current_state != PCI_D0)
+	if (!pci_msi_supported(dev, nvec))
 		return -EINVAL;
 
-	status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSIX);
-	if (status)
-		return status;
+	if (!entries)
+		return -EINVAL;
 
 	nr_entries = pci_msix_vec_count(dev);
 	if (nr_entries < 0)
@@ -978,8 +953,7 @@ int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
 		dev_info(&dev->dev, "can't enable MSI-X (MSI IRQ already assigned)\n");
 		return -EINVAL;
 	}
-	status = msix_capability_init(dev, entries, nvec);
-	return status;
+	return msix_capability_init(dev, entries, nvec);
 }
 EXPORT_SYMBOL(pci_enable_msix);
 
@@ -1062,7 +1036,7 @@ int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
 	int nvec;
 	int rc;
 
-	if (dev->current_state != PCI_D0)
+	if (!pci_msi_supported(dev, minvec))
 		return -EINVAL;
 
 	WARN_ON(!!dev->msi_enabled);
@@ -1086,17 +1060,6 @@ int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
 		nvec = maxvec;
 
 	do {
-		rc = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSI);
-		if (rc < 0) {
-			return rc;
-		} else if (rc > 0) {
-			if (rc < minvec)
-				return -ENOSPC;
-			nvec = rc;
-		}
-	} while (rc);
-
-	do {
 		rc = msi_capability_init(dev, nvec);
 		if (rc < 0) {
 			return rc;
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 37263b0ebfe3..6ebf8edc5f3c 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -10,6 +10,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/pci.h>
+#include <linux/pci_hotplug.h>
 #include <linux/module.h>
 #include <linux/pci-aspm.h>
 #include <linux/pci-acpi.h>
@@ -17,6 +18,267 @@
 #include <linux/pm_qos.h>
 #include "pci.h"
 
+phys_addr_t acpi_pci_root_get_mcfg_addr(acpi_handle handle)
+{
+	acpi_status status = AE_NOT_EXIST;
+	unsigned long long mcfg_addr;
+
+	if (handle)
+		status = acpi_evaluate_integer(handle, METHOD_NAME__CBA,
+					       NULL, &mcfg_addr);
+	if (ACPI_FAILURE(status))
+		return 0;
+
+	return (phys_addr_t)mcfg_addr;
+}
+
+static acpi_status decode_type0_hpx_record(union acpi_object *record,
+					   struct hotplug_params *hpx)
+{
+	int i;
+	union acpi_object *fields = record->package.elements;
+	u32 revision = fields[1].integer.value;
+
+	switch (revision) {
+	case 1:
+		if (record->package.count != 6)
+			return AE_ERROR;
+		for (i = 2; i < 6; i++)
+			if (fields[i].type != ACPI_TYPE_INTEGER)
+				return AE_ERROR;
+		hpx->t0 = &hpx->type0_data;
+		hpx->t0->revision        = revision;
+		hpx->t0->cache_line_size = fields[2].integer.value;
+		hpx->t0->latency_timer   = fields[3].integer.value;
+		hpx->t0->enable_serr     = fields[4].integer.value;
+		hpx->t0->enable_perr     = fields[5].integer.value;
+		break;
+	default:
+		printk(KERN_WARNING
+		       "%s: Type 0 Revision %d record not supported\n",
+		       __func__, revision);
+		return AE_ERROR;
+	}
+	return AE_OK;
+}
+
+static acpi_status decode_type1_hpx_record(union acpi_object *record,
+					   struct hotplug_params *hpx)
+{
+	int i;
+	union acpi_object *fields = record->package.elements;
+	u32 revision = fields[1].integer.value;
+
+	switch (revision) {
+	case 1:
+		if (record->package.count != 5)
+			return AE_ERROR;
+		for (i = 2; i < 5; i++)
+			if (fields[i].type != ACPI_TYPE_INTEGER)
+				return AE_ERROR;
+		hpx->t1 = &hpx->type1_data;
+		hpx->t1->revision      = revision;
+		hpx->t1->max_mem_read  = fields[2].integer.value;
+		hpx->t1->avg_max_split = fields[3].integer.value;
+		hpx->t1->tot_max_split = fields[4].integer.value;
+		break;
+	default:
+		printk(KERN_WARNING
+		       "%s: Type 1 Revision %d record not supported\n",
+		       __func__, revision);
+		return AE_ERROR;
+	}
+	return AE_OK;
+}
+
+static acpi_status decode_type2_hpx_record(union acpi_object *record,
+					   struct hotplug_params *hpx)
+{
+	int i;
+	union acpi_object *fields = record->package.elements;
+	u32 revision = fields[1].integer.value;
+
+	switch (revision) {
+	case 1:
+		if (record->package.count != 18)
+			return AE_ERROR;
+		for (i = 2; i < 18; i++)
+			if (fields[i].type != ACPI_TYPE_INTEGER)
+				return AE_ERROR;
+		hpx->t2 = &hpx->type2_data;
+		hpx->t2->revision      = revision;
+		hpx->t2->unc_err_mask_and      = fields[2].integer.value;
+		hpx->t2->unc_err_mask_or       = fields[3].integer.value;
+		hpx->t2->unc_err_sever_and     = fields[4].integer.value;
+		hpx->t2->unc_err_sever_or      = fields[5].integer.value;
+		hpx->t2->cor_err_mask_and      = fields[6].integer.value;
+		hpx->t2->cor_err_mask_or       = fields[7].integer.value;
+		hpx->t2->adv_err_cap_and       = fields[8].integer.value;
+		hpx->t2->adv_err_cap_or        = fields[9].integer.value;
+		hpx->t2->pci_exp_devctl_and    = fields[10].integer.value;
+		hpx->t2->pci_exp_devctl_or     = fields[11].integer.value;
+		hpx->t2->pci_exp_lnkctl_and    = fields[12].integer.value;
+		hpx->t2->pci_exp_lnkctl_or     = fields[13].integer.value;
+		hpx->t2->sec_unc_err_sever_and = fields[14].integer.value;
+		hpx->t2->sec_unc_err_sever_or  = fields[15].integer.value;
+		hpx->t2->sec_unc_err_mask_and  = fields[16].integer.value;
+		hpx->t2->sec_unc_err_mask_or   = fields[17].integer.value;
+		break;
+	default:
+		printk(KERN_WARNING
+		       "%s: Type 2 Revision %d record not supported\n",
+		       __func__, revision);
+		return AE_ERROR;
+	}
+	return AE_OK;
+}
+
+static acpi_status acpi_run_hpx(acpi_handle handle, struct hotplug_params *hpx)
+{
+	acpi_status status;
+	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
+	union acpi_object *package, *record, *fields;
+	u32 type;
+	int i;
+
+	/* Clear the return buffer with zeros */
+	memset(hpx, 0, sizeof(struct hotplug_params));
+
+	status = acpi_evaluate_object(handle, "_HPX", NULL, &buffer);
+	if (ACPI_FAILURE(status))
+		return status;
+
+	package = (union acpi_object *)buffer.pointer;
+	if (package->type != ACPI_TYPE_PACKAGE) {
+		status = AE_ERROR;
+		goto exit;
+	}
+
+	for (i = 0; i < package->package.count; i++) {
+		record = &package->package.elements[i];
+		if (record->type != ACPI_TYPE_PACKAGE) {
+			status = AE_ERROR;
+			goto exit;
+		}
+
+		fields = record->package.elements;
+		if (fields[0].type != ACPI_TYPE_INTEGER ||
+		    fields[1].type != ACPI_TYPE_INTEGER) {
+			status = AE_ERROR;
+			goto exit;
+		}
+
+		type = fields[0].integer.value;
+		switch (type) {
+		case 0:
+			status = decode_type0_hpx_record(record, hpx);
+			if (ACPI_FAILURE(status))
+				goto exit;
+			break;
+		case 1:
+			status = decode_type1_hpx_record(record, hpx);
+			if (ACPI_FAILURE(status))
+				goto exit;
+			break;
+		case 2:
+			status = decode_type2_hpx_record(record, hpx);
+			if (ACPI_FAILURE(status))
+				goto exit;
+			break;
+		default:
+			printk(KERN_ERR "%s: Type %d record not supported\n",
+			       __func__, type);
+			status = AE_ERROR;
+			goto exit;
+		}
+	}
+ exit:
+	kfree(buffer.pointer);
+	return status;
+}
+
+static acpi_status acpi_run_hpp(acpi_handle handle, struct hotplug_params *hpp)
+{
+	acpi_status status;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object *package, *fields;
+	int i;
+
+	memset(hpp, 0, sizeof(struct hotplug_params));
+
+	status = acpi_evaluate_object(handle, "_HPP", NULL, &buffer);
+	if (ACPI_FAILURE(status))
+		return status;
+
+	package = (union acpi_object *) buffer.pointer;
+	if (package->type != ACPI_TYPE_PACKAGE ||
+	    package->package.count != 4) {
+		status = AE_ERROR;
+		goto exit;
+	}
+
+	fields = package->package.elements;
+	for (i = 0; i < 4; i++) {
+		if (fields[i].type != ACPI_TYPE_INTEGER) {
+			status = AE_ERROR;
+			goto exit;
+		}
+	}
+
+	hpp->t0 = &hpp->type0_data;
+	hpp->t0->revision        = 1;
+	hpp->t0->cache_line_size = fields[0].integer.value;
+	hpp->t0->latency_timer   = fields[1].integer.value;
+	hpp->t0->enable_serr     = fields[2].integer.value;
+	hpp->t0->enable_perr     = fields[3].integer.value;
+
+exit:
+	kfree(buffer.pointer);
+	return status;
+}
+
+/* pci_get_hp_params
+ *
+ * @dev - the pci_dev for which we want parameters
+ * @hpp - allocated by the caller
+ */
+int pci_get_hp_params(struct pci_dev *dev, struct hotplug_params *hpp)
+{
+	acpi_status status;
+	acpi_handle handle, phandle;
+	struct pci_bus *pbus;
+
+	handle = NULL;
+	for (pbus = dev->bus; pbus; pbus = pbus->parent) {
+		handle = acpi_pci_get_bridge_handle(pbus);
+		if (handle)
+			break;
+	}
+
+	/*
+	 * _HPP settings apply to all child buses, until another _HPP is
+	 * encountered. If we don't find an _HPP for the input pci dev,
+	 * look for it in the parent device scope since that would apply to
+	 * this pci dev.
+	 */
+	while (handle) {
+		status = acpi_run_hpx(handle, hpp);
+		if (ACPI_SUCCESS(status))
+			return 0;
+		status = acpi_run_hpp(handle, hpp);
+		if (ACPI_SUCCESS(status))
+			return 0;
+		if (acpi_is_root_bridge(handle))
+			break;
+		status = acpi_get_parent(handle, &phandle);
+		if (ACPI_FAILURE(status))
+			break;
+		handle = phandle;
+	}
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(pci_get_hp_params);
+
 /**
  * pci_acpi_wake_bus - Root bus wakeup notification fork function.
  * @work: Work item to handle.
@@ -84,20 +346,6 @@ acpi_status pci_acpi_add_pm_notifier(struct acpi_device *dev,
 	return acpi_add_pm_notifier(dev, &pci_dev->dev, pci_acpi_wake_dev);
 }
 
-phys_addr_t acpi_pci_root_get_mcfg_addr(acpi_handle handle)
-{
-	acpi_status status = AE_NOT_EXIST;
-	unsigned long long mcfg_addr;
-
-	if (handle)
-		status = acpi_evaluate_integer(handle, METHOD_NAME__CBA,
-					       NULL, &mcfg_addr);
-	if (ACPI_FAILURE(status))
-		return 0;
-
-	return (phys_addr_t)mcfg_addr;
-}
-
 /*
  * _SxD returns the D-state with the highest power
  * (lowest D-state number) supported in the S-state "x".
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index d04c5adafc16..2b3c89425bb5 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -55,7 +55,6 @@ int pci_add_dynid(struct pci_driver *drv,
 		  unsigned long driver_data)
 {
 	struct pci_dynid *dynid;
-	int retval;
 
 	dynid = kzalloc(sizeof(*dynid), GFP_KERNEL);
 	if (!dynid)
@@ -73,9 +72,7 @@ int pci_add_dynid(struct pci_driver *drv,
 	list_add_tail(&dynid->node, &drv->dynids.list);
 	spin_unlock(&drv->dynids.lock);
 
-	retval = driver_attach(&drv->driver);
-
-	return retval;
+	return driver_attach(&drv->driver);
 }
 EXPORT_SYMBOL_GPL(pci_add_dynid);
 
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 9ff0a901ecf7..92b6d9ab00e4 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -177,7 +177,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 
-	return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x\n",
+	return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X\n",
 		       pci_dev->vendor, pci_dev->device,
 		       pci_dev->subsystem_vendor, pci_dev->subsystem_device,
 		       (u8)(pci_dev->class >> 16), (u8)(pci_dev->class >> 8),
@@ -250,46 +250,45 @@ static ssize_t msi_bus_show(struct device *dev, struct device_attribute *attr,
 			    char *buf)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_bus *subordinate = pdev->subordinate;
 
-	if (!pdev->subordinate)
-		return 0;
-
-	return sprintf(buf, "%u\n",
-		       !(pdev->subordinate->bus_flags & PCI_BUS_FLAGS_NO_MSI));
+	return sprintf(buf, "%u\n", subordinate ?
+		       !(subordinate->bus_flags & PCI_BUS_FLAGS_NO_MSI)
+			   : !pdev->no_msi);
 }
 
 static ssize_t msi_bus_store(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_bus *subordinate = pdev->subordinate;
 	unsigned long val;
 
 	if (kstrtoul(buf, 0, &val) < 0)
 		return -EINVAL;
 
-	/*
-	 * Bad things may happen if the no_msi flag is changed
-	 * while drivers are loaded.
-	 */
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/*
-	 * Maybe devices without subordinate buses shouldn't have this
-	 * attribute in the first place?
+	 * "no_msi" and "bus_flags" only affect what happens when a driver
+	 * requests MSI or MSI-X.  They don't affect any drivers that have
+	 * already requested MSI or MSI-X.
 	 */
-	if (!pdev->subordinate)
+	if (!subordinate) {
+		pdev->no_msi = !val;
+		dev_info(&pdev->dev, "MSI/MSI-X %s for future drivers\n",
+			 val ? "allowed" : "disallowed");
 		return count;
-
-	/* Is the flag going to change, or keep the value it already had? */
-	if (!(pdev->subordinate->bus_flags & PCI_BUS_FLAGS_NO_MSI) ^
-	    !!val) {
-		pdev->subordinate->bus_flags ^= PCI_BUS_FLAGS_NO_MSI;
-
-		dev_warn(&pdev->dev, "forced subordinate bus to%s support MSI, bad things could happen\n",
-			 val ? "" : " not");
 	}
 
+	if (val)
+		subordinate->bus_flags &= ~PCI_BUS_FLAGS_NO_MSI;
+	else
+		subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
+
+	dev_info(&subordinate->dev, "MSI/MSI-X %s for future drivers of devices on this bus\n",
+		 val ? "allowed" : "disallowed");
 	return count;
 }
 static DEVICE_ATTR_RW(msi_bus);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 2c9ac70254e2..625a4ace10b4 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1003,12 +1003,19 @@ int pci_save_state(struct pci_dev *dev)
 	for (i = 0; i < 16; i++)
 		pci_read_config_dword(dev, i * 4, &dev->saved_config_space[i]);
 	dev->state_saved = true;
-	if ((i = pci_save_pcie_state(dev)) != 0)
+
+	i = pci_save_pcie_state(dev);
+	if (i != 0)
 		return i;
-	if ((i = pci_save_pcix_state(dev)) != 0)
+
+	i = pci_save_pcix_state(dev);
+	if (i != 0)
 		return i;
-	if ((i = pci_save_vc_state(dev)) != 0)
+
+	i = pci_save_vc_state(dev);
+	if (i != 0)
 		return i;
+
 	return 0;
 }
 EXPORT_SYMBOL(pci_save_state);
@@ -1907,10 +1914,6 @@ int pci_prepare_to_sleep(struct pci_dev *dev)
 	if (target_state == PCI_POWER_ERROR)
 		return -EIO;
 
-	/* D3cold during system suspend/hibernate is not supported */
-	if (target_state > PCI_D3hot)
-		target_state = PCI_D3hot;
-
 	pci_enable_wake(dev, target_state, device_may_wakeup(&dev->dev));
 
 	error = pci_set_power_state(dev, target_state);
@@ -2704,6 +2707,37 @@ int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name)
 }
 EXPORT_SYMBOL(pci_request_regions_exclusive);
 
+/**
+ *	pci_remap_iospace - Remap the memory mapped I/O space
+ *	@res: Resource describing the I/O space
+ *	@phys_addr: physical address of range to be mapped
+ *
+ *	Remap the memory mapped I/O space described by the @res
+ *	and the CPU physical address @phys_addr into virtual address space.
+ *	Only architectures that have memory mapped IO functions defined
+ *	(and the PCI_IOBASE value defined) should call this function.
+ */
+int __weak pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
+{
+#if defined(PCI_IOBASE) && defined(CONFIG_MMU)
+	unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start;
+
+	if (!(res->flags & IORESOURCE_IO))
+		return -EINVAL;
+
+	if (res->end > IO_SPACE_LIMIT)
+		return -EINVAL;
+
+	return ioremap_page_range(vaddr, vaddr + resource_size(res), phys_addr,
+				  pgprot_device(PAGE_KERNEL));
+#else
+	/* this architecture does not have memory mapped I/O space,
+	   so this function should never be called */
+	WARN_ONCE(1, "This architecture does not support memory mapped I/O\n");
+	return -ENODEV;
+#endif
+}
+
 static void __pci_set_master(struct pci_dev *dev, bool enable)
 {
 	u16 old_cmd, cmd;
@@ -4406,6 +4440,15 @@ static void pci_no_domains(void)
 #endif
 }
 
+#ifdef CONFIG_PCI_DOMAINS
+static atomic_t __domain_nr = ATOMIC_INIT(-1);
+
+int pci_get_new_domain_nr(void)
+{
+	return atomic_inc_return(&__domain_nr);
+}
+#endif
+
 /**
  * pci_ext_cfg_avail - can we access extended PCI config space?
  *
diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c
index 35d06e177917..c6849d9e86ce 100644
--- a/drivers/pci/pcie/aer/aerdrv_errprint.c
+++ b/drivers/pci/pcie/aer/aerdrv_errprint.c
@@ -89,15 +89,17 @@ static const char *aer_correctable_error_string[] = {
 	NULL,
 	"Replay Timer Timeout",		/* Bit Position 12	*/
 	"Advisory Non-Fatal",		/* Bit Position 13	*/
+	"Corrected Internal Error",	/* Bit Position 14	*/
+	"Header Log Overflow",		/* Bit Position 15	*/
 };
 
 static const char *aer_uncorrectable_error_string[] = {
-	NULL,
+	"Undefined",			/* Bit Position 0	*/
 	NULL,
 	NULL,
 	NULL,
 	"Data Link Protocol",		/* Bit Position 4	*/
-	NULL,
+	"Surprise Down Error",		/* Bit Position 5	*/
 	NULL,
 	NULL,
 	NULL,
@@ -113,6 +115,11 @@ static const char *aer_uncorrectable_error_string[] = {
 	"Malformed TLP",		/* Bit Position 18	*/
 	"ECRC",				/* Bit Position 19	*/
 	"Unsupported Request",		/* Bit Position 20	*/
+	"ACS Violation",		/* Bit Position 21	*/
+	"Uncorrectable Internal Error",	/* Bit Position 22	*/
+	"MC Blocked TLP",		/* Bit Position 23	*/
+	"AtomicOp Egress Blocked",	/* Bit Position 24	*/
+	"TLP Prefix Blocked Error",	/* Bit Position 25	*/
 };
 
 static const char *aer_agent_string[] = {
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index 82e06a86cd77..a9f9c46e5022 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -41,11 +41,17 @@ static int __init pcie_pme_setup(char *str)
 }
 __setup("pcie_pme=", pcie_pme_setup);
 
+enum pme_suspend_level {
+	PME_SUSPEND_NONE = 0,
+	PME_SUSPEND_WAKEUP,
+	PME_SUSPEND_NOIRQ,
+};
+
 struct pcie_pme_service_data {
 	spinlock_t lock;
 	struct pcie_device *srv;
 	struct work_struct work;
-	bool noirq; /* Don't enable the PME interrupt used by this service. */
+	enum pme_suspend_level suspend_level;
 };
 
 /**
@@ -223,7 +229,7 @@ static void pcie_pme_work_fn(struct work_struct *work)
 	spin_lock_irq(&data->lock);
 
 	for (;;) {
-		if (data->noirq)
+		if (data->suspend_level != PME_SUSPEND_NONE)
 			break;
 
 		pcie_capability_read_dword(port, PCI_EXP_RTSTA, &rtsta);
@@ -250,7 +256,7 @@ static void pcie_pme_work_fn(struct work_struct *work)
 		spin_lock_irq(&data->lock);
 	}
 
-	if (!data->noirq)
+	if (data->suspend_level == PME_SUSPEND_NONE)
 		pcie_pme_interrupt_enable(port, true);
 
 	spin_unlock_irq(&data->lock);
@@ -367,6 +373,21 @@ static int pcie_pme_probe(struct pcie_device *srv)
 	return ret;
 }
 
+static bool pcie_pme_check_wakeup(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	if (!bus)
+		return false;
+
+	list_for_each_entry(dev, &bus->devices, bus_list)
+		if (device_may_wakeup(&dev->dev)
+		    || pcie_pme_check_wakeup(dev->subordinate))
+			return true;
+
+	return false;
+}
+
 /**
  * pcie_pme_suspend - Suspend PCIe PME service device.
  * @srv: PCIe service device to suspend.
@@ -375,11 +396,26 @@ static int pcie_pme_suspend(struct pcie_device *srv)
 {
 	struct pcie_pme_service_data *data = get_service_data(srv);
 	struct pci_dev *port = srv->port;
+	bool wakeup;
 
+	if (device_may_wakeup(&port->dev)) {
+		wakeup = true;
+	} else {
+		down_read(&pci_bus_sem);
+		wakeup = pcie_pme_check_wakeup(port->subordinate);
+		up_read(&pci_bus_sem);
+	}
 	spin_lock_irq(&data->lock);
-	pcie_pme_interrupt_enable(port, false);
-	pcie_clear_root_pme_status(port);
-	data->noirq = true;
+	if (wakeup) {
+		enable_irq_wake(srv->irq);
+		data->suspend_level = PME_SUSPEND_WAKEUP;
+	} else {
+		struct pci_dev *port = srv->port;
+
+		pcie_pme_interrupt_enable(port, false);
+		pcie_clear_root_pme_status(port);
+		data->suspend_level = PME_SUSPEND_NOIRQ;
+	}
 	spin_unlock_irq(&data->lock);
 
 	synchronize_irq(srv->irq);
@@ -394,12 +430,17 @@ static int pcie_pme_suspend(struct pcie_device *srv)
 static int pcie_pme_resume(struct pcie_device *srv)
 {
 	struct pcie_pme_service_data *data = get_service_data(srv);
-	struct pci_dev *port = srv->port;
 
 	spin_lock_irq(&data->lock);
-	data->noirq = false;
-	pcie_clear_root_pme_status(port);
-	pcie_pme_interrupt_enable(port, true);
+	if (data->suspend_level == PME_SUSPEND_NOIRQ) {
+		struct pci_dev *port = srv->port;
+
+		pcie_clear_root_pme_status(port);
+		pcie_pme_interrupt_enable(port, true);
+	} else {
+		disable_irq_wake(srv->irq);
+	}
+	data->suspend_level = PME_SUSPEND_NONE;
 	spin_unlock_irq(&data->lock);
 
 	return 0;
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 2ccc9b926ea7..be35da2e105e 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -93,77 +93,6 @@ static int pcie_port_resume_noirq(struct device *dev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_RUNTIME
-struct d3cold_info {
-	bool no_d3cold;
-	unsigned int d3cold_delay;
-};
-
-static int pci_dev_d3cold_info(struct pci_dev *pdev, void *data)
-{
-	struct d3cold_info *info = data;
-
-	info->d3cold_delay = max_t(unsigned int, pdev->d3cold_delay,
-				   info->d3cold_delay);
-	if (pdev->no_d3cold)
-		info->no_d3cold = true;
-	return 0;
-}
-
-static int pcie_port_runtime_suspend(struct device *dev)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct d3cold_info d3cold_info = {
-		.no_d3cold	= false,
-		.d3cold_delay	= PCI_PM_D3_WAIT,
-	};
-
-	/*
-	 * If any subordinate device disable D3cold, we should not put
-	 * the port into D3cold.  The D3cold delay of port should be
-	 * the max of that of all subordinate devices.
-	 */
-	pci_walk_bus(pdev->subordinate, pci_dev_d3cold_info, &d3cold_info);
-	pdev->no_d3cold = d3cold_info.no_d3cold;
-	pdev->d3cold_delay = d3cold_info.d3cold_delay;
-	return 0;
-}
-
-static int pcie_port_runtime_resume(struct device *dev)
-{
-	return 0;
-}
-
-static int pci_dev_pme_poll(struct pci_dev *pdev, void *data)
-{
-	bool *pme_poll = data;
-
-	if (pdev->pme_poll)
-		*pme_poll = true;
-	return 0;
-}
-
-static int pcie_port_runtime_idle(struct device *dev)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-	bool pme_poll = false;
-
-	/*
-	 * If any subordinate device needs pme poll, we should keep
-	 * the port in D0, because we need port in D0 to poll it.
-	 */
-	pci_walk_bus(pdev->subordinate, pci_dev_pme_poll, &pme_poll);
-	/* Delay for a short while to prevent too frequent suspend/resume */
-	if (!pme_poll)
-		pm_schedule_suspend(dev, 10);
-	return -EBUSY;
-}
-#else
-#define pcie_port_runtime_suspend	NULL
-#define pcie_port_runtime_resume	NULL
-#define pcie_port_runtime_idle		NULL
-#endif
-
 static const struct dev_pm_ops pcie_portdrv_pm_ops = {
 	.suspend	= pcie_port_device_suspend,
 	.resume		= pcie_port_device_resume,
@@ -172,9 +101,6 @@ static const struct dev_pm_ops pcie_portdrv_pm_ops = {
 	.poweroff	= pcie_port_device_suspend,
 	.restore	= pcie_port_device_resume,
 	.resume_noirq	= pcie_port_resume_noirq,
-	.runtime_suspend = pcie_port_runtime_suspend,
-	.runtime_resume = pcie_port_runtime_resume,
-	.runtime_idle	= pcie_port_runtime_idle,
 };
 
 #define PCIE_PORTDRV_PM_OPS	(&pcie_portdrv_pm_ops)
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4170113cde61..5ed99309c758 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -6,6 +6,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/pci.h>
+#include <linux/pci_hotplug.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/cpumask.h>
@@ -485,7 +486,7 @@ void pci_read_bridge_bases(struct pci_bus *child)
 	}
 }
 
-static struct pci_bus *pci_alloc_bus(void)
+static struct pci_bus *pci_alloc_bus(struct pci_bus *parent)
 {
 	struct pci_bus *b;
 
@@ -500,6 +501,10 @@ static struct pci_bus *pci_alloc_bus(void)
 	INIT_LIST_HEAD(&b->resources);
 	b->max_bus_speed = PCI_SPEED_UNKNOWN;
 	b->cur_bus_speed = PCI_SPEED_UNKNOWN;
+#ifdef CONFIG_PCI_DOMAINS_GENERIC
+	if (parent)
+		b->domain_nr = parent->domain_nr;
+#endif
 	return b;
 }
 
@@ -671,7 +676,7 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
 	/*
 	 * Allocate a new bus, and inherit stuff from the parent..
 	 */
-	child = pci_alloc_bus();
+	child = pci_alloc_bus(parent);
 	if (!child)
 		return NULL;
 
@@ -740,6 +745,17 @@ struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev,
 }
 EXPORT_SYMBOL(pci_add_new_bus);
 
+static void pci_enable_crs(struct pci_dev *pdev)
+{
+	u16 root_cap = 0;
+
+	/* Enable CRS Software Visibility if supported */
+	pcie_capability_read_word(pdev, PCI_EXP_RTCAP, &root_cap);
+	if (root_cap & PCI_EXP_RTCAP_CRSVIS)
+		pcie_capability_set_word(pdev, PCI_EXP_RTCTL,
+					 PCI_EXP_RTCTL_CRSSVE);
+}
+
 /*
  * If it's a bridge, configure it and scan the bus behind it.
  * For CardBus bridges, we don't scan behind as the devices will
@@ -787,6 +803,8 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 	pci_write_config_word(dev, PCI_BRIDGE_CONTROL,
 			      bctl & ~PCI_BRIDGE_CTL_MASTER_ABORT);
 
+	pci_enable_crs(dev);
+
 	if ((secondary || subordinate) && !pcibios_assign_all_busses() &&
 	    !is_cardbus && !broken) {
 		unsigned int cmax;
@@ -1226,6 +1244,137 @@ int pci_setup_device(struct pci_dev *dev)
 	return 0;
 }
 
+static struct hpp_type0 pci_default_type0 = {
+	.revision = 1,
+	.cache_line_size = 8,
+	.latency_timer = 0x40,
+	.enable_serr = 0,
+	.enable_perr = 0,
+};
+
+static void program_hpp_type0(struct pci_dev *dev, struct hpp_type0 *hpp)
+{
+	u16 pci_cmd, pci_bctl;
+
+	if (!hpp)
+		hpp = &pci_default_type0;
+
+	if (hpp->revision > 1) {
+		dev_warn(&dev->dev,
+			 "PCI settings rev %d not supported; using defaults\n",
+			 hpp->revision);
+		hpp = &pci_default_type0;
+	}
+
+	pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, hpp->cache_line_size);
+	pci_write_config_byte(dev, PCI_LATENCY_TIMER, hpp->latency_timer);
+	pci_read_config_word(dev, PCI_COMMAND, &pci_cmd);
+	if (hpp->enable_serr)
+		pci_cmd |= PCI_COMMAND_SERR;
+	if (hpp->enable_perr)
+		pci_cmd |= PCI_COMMAND_PARITY;
+	pci_write_config_word(dev, PCI_COMMAND, pci_cmd);
+
+	/* Program bridge control value */
+	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
+		pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER,
+				      hpp->latency_timer);
+		pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &pci_bctl);
+		if (hpp->enable_serr)
+			pci_bctl |= PCI_BRIDGE_CTL_SERR;
+		if (hpp->enable_perr)
+			pci_bctl |= PCI_BRIDGE_CTL_PARITY;
+		pci_write_config_word(dev, PCI_BRIDGE_CONTROL, pci_bctl);
+	}
+}
+
+static void program_hpp_type1(struct pci_dev *dev, struct hpp_type1 *hpp)
+{
+	if (hpp)
+		dev_warn(&dev->dev, "PCI-X settings not supported\n");
+}
+
+static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp)
+{
+	int pos;
+	u32 reg32;
+
+	if (!hpp)
+		return;
+
+	if (hpp->revision > 1) {
+		dev_warn(&dev->dev, "PCIe settings rev %d not supported\n",
+			 hpp->revision);
+		return;
+	}
+
+	/*
+	 * Don't allow _HPX to change MPS or MRRS settings.  We manage
+	 * those to make sure they're consistent with the rest of the
+	 * platform.
+	 */
+	hpp->pci_exp_devctl_and |= PCI_EXP_DEVCTL_PAYLOAD |
+				    PCI_EXP_DEVCTL_READRQ;
+	hpp->pci_exp_devctl_or &= ~(PCI_EXP_DEVCTL_PAYLOAD |
+				    PCI_EXP_DEVCTL_READRQ);
+
+	/* Initialize Device Control Register */
+	pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL,
+			~hpp->pci_exp_devctl_and, hpp->pci_exp_devctl_or);
+
+	/* Initialize Link Control Register */
+	if (dev->subordinate)
+		pcie_capability_clear_and_set_word(dev, PCI_EXP_LNKCTL,
+			~hpp->pci_exp_lnkctl_and, hpp->pci_exp_lnkctl_or);
+
+	/* Find Advanced Error Reporting Enhanced Capability */
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return;
+
+	/* Initialize Uncorrectable Error Mask Register */
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &reg32);
+	reg32 = (reg32 & hpp->unc_err_mask_and) | hpp->unc_err_mask_or;
+	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, reg32);
+
+	/* Initialize Uncorrectable Error Severity Register */
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &reg32);
+	reg32 = (reg32 & hpp->unc_err_sever_and) | hpp->unc_err_sever_or;
+	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, reg32);
+
+	/* Initialize Correctable Error Mask Register */
+	pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, &reg32);
+	reg32 = (reg32 & hpp->cor_err_mask_and) | hpp->cor_err_mask_or;
+	pci_write_config_dword(dev, pos + PCI_ERR_COR_MASK, reg32);
+
+	/* Initialize Advanced Error Capabilities and Control Register */
+	pci_read_config_dword(dev, pos + PCI_ERR_CAP, &reg32);
+	reg32 = (reg32 & hpp->adv_err_cap_and) | hpp->adv_err_cap_or;
+	pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32);
+
+	/*
+	 * FIXME: The following two registers are not supported yet.
+	 *
+	 *   o Secondary Uncorrectable Error Severity Register
+	 *   o Secondary Uncorrectable Error Mask Register
+	 */
+}
+
+static void pci_configure_device(struct pci_dev *dev)
+{
+	struct hotplug_params hpp;
+	int ret;
+
+	memset(&hpp, 0, sizeof(hpp));
+	ret = pci_get_hp_params(dev, &hpp);
+	if (ret)
+		return;
+
+	program_hpp_type2(dev, hpp.t2);
+	program_hpp_type1(dev, hpp.t1);
+	program_hpp_type0(dev, hpp.t0);
+}
+
 static void pci_release_capabilities(struct pci_dev *dev)
 {
 	pci_vpd_release(dev);
@@ -1282,8 +1431,13 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
 	    *l == 0x0000ffff || *l == 0xffff0000)
 		return false;
 
-	/* Configuration request Retry Status */
-	while (*l == 0xffff0001) {
+	/*
+	 * Configuration Request Retry Status.  Some root ports return the
+	 * actual device ID instead of the synthetic ID (0xFFFF) required
+	 * by the PCIe spec.  Ignore the device ID and only check for
+	 * (vendor id == 1).
+	 */
+	while ((*l & 0xffff) == 0x0001) {
 		if (!crs_timeout)
 			return false;
 
@@ -1363,6 +1517,8 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus)
 {
 	int ret;
 
+	pci_configure_device(dev);
+
 	device_initialize(&dev->dev);
 	dev->dev.release = pci_release_dev;
 
@@ -1751,13 +1907,14 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 	char bus_addr[64];
 	char *fmt;
 
-	b = pci_alloc_bus();
+	b = pci_alloc_bus(NULL);
 	if (!b)
 		return NULL;
 
 	b->sysdata = sysdata;
 	b->ops = ops;
 	b->number = b->busn_res.start = bus;
+	pci_bus_assign_domain_nr(b, parent);
 	b2 = pci_find_bus(pci_domain_nr(b), bus);
 	if (b2) {
 		/* If we already got to this bus through a different bridge, ignore it */
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 80c2d014283d..90acb32c85b1 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -24,6 +24,7 @@
 #include <linux/ioport.h>
 #include <linux/sched.h>
 #include <linux/ktime.h>
+#include <linux/mm.h>
 #include <asm/dma.h>	/* isa_dma_bridge_buggy */
 #include "pci.h"
 
@@ -287,6 +288,25 @@ static void quirk_citrine(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM,	PCI_DEVICE_ID_IBM_CITRINE,	quirk_citrine);
 
+/*  On IBM Crocodile ipr SAS adapters, expand BAR to system page size */
+static void quirk_extend_bar_to_page(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < PCI_STD_RESOURCE_END; i++) {
+		struct resource *r = &dev->resource[i];
+
+		if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) {
+			r->end = PAGE_SIZE - 1;
+			r->start = 0;
+			r->flags |= IORESOURCE_UNSET;
+			dev_info(&dev->dev, "expanded BAR %d to page size: %pR\n",
+				 i, r);
+		}
+	}
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, 0x034a, quirk_extend_bar_to_page);
+
 /*
  *  S3 868 and 968 chips report region size equal to 32M, but they decode 64M.
  *  If it's needed, re-allocate the region.
@@ -2985,6 +3005,8 @@ DECLARE_PCI_FIXUP_HEADER(0x1814, 0x0601, /* Ralink RT2800 802.11n PCI */
  */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_REALTEK, 0x8169,
 			 quirk_broken_intx_masking);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, PCI_ANY_ID,
+			 quirk_broken_intx_masking);
 
 #ifdef CONFIG_ACPI
 /*
@@ -3512,57 +3534,6 @@ DECLARE_PCI_FIXUP_HEADER(0x1283, 0x8892, quirk_use_pcie_bridge_dma_alias);
 /* Intel 82801, https://bugzilla.kernel.org/show_bug.cgi?id=44881#c49 */
 DECLARE_PCI_FIXUP_HEADER(0x8086, 0x244e, quirk_use_pcie_bridge_dma_alias);
 
-static struct pci_dev *pci_func_0_dma_source(struct pci_dev *dev)
-{
-	if (!PCI_FUNC(dev->devfn))
-		return pci_dev_get(dev);
-
-	return pci_get_slot(dev->bus, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
-}
-
-static const struct pci_dev_dma_source {
-	u16 vendor;
-	u16 device;
-	struct pci_dev *(*dma_source)(struct pci_dev *dev);
-} pci_dev_dma_source[] = {
-	/*
-	 * https://bugzilla.redhat.com/show_bug.cgi?id=605888
-	 *
-	 * Some Ricoh devices use the function 0 source ID for DMA on
-	 * other functions of a multifunction device.  The DMA devices
-	 * is therefore function 0, which will have implications of the
-	 * iommu grouping of these devices.
-	 */
-	{ PCI_VENDOR_ID_RICOH, 0xe822, pci_func_0_dma_source },
-	{ PCI_VENDOR_ID_RICOH, 0xe230, pci_func_0_dma_source },
-	{ PCI_VENDOR_ID_RICOH, 0xe832, pci_func_0_dma_source },
-	{ PCI_VENDOR_ID_RICOH, 0xe476, pci_func_0_dma_source },
-	{ 0 }
-};
-
-/*
- * IOMMUs with isolation capabilities need to be programmed with the
- * correct source ID of a device.  In most cases, the source ID matches
- * the device doing the DMA, but sometimes hardware is broken and will
- * tag the DMA as being sourced from a different device.  This function
- * allows that translation.  Note that the reference count of the
- * returned device is incremented on all paths.
- */
-struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
-{
-	const struct pci_dev_dma_source *i;
-
-	for (i = pci_dev_dma_source; i->dma_source; i++) {
-		if ((i->vendor == dev->vendor ||
-		     i->vendor == (u16)PCI_ANY_ID) &&
-		    (i->device == dev->device ||
-		     i->device == (u16)PCI_ANY_ID))
-			return i->dma_source(dev);
-	}
-
-	return pci_dev_get(dev);
-}
-
 /*
  * AMD has indicated that the devices below do not support peer-to-peer
  * in any system where they are found in the southbridge with an AMD
@@ -3582,6 +3553,11 @@ struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
  * 1002:439d SB7x0/SB8x0/SB9x0 LPC host controller
  * 1002:4384 SBx00 PCI to PCI Bridge
  * 1002:4399 SB7x0/SB8x0/SB9x0 USB OHCI2 Controller
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=81841#c15
+ *
+ * 1022:780f [AMD] FCH PCI Bridge
+ * 1022:7809 [AMD] FCH USB OHCI Controller
  */
 static int pci_quirk_amd_sb_acs(struct pci_dev *dev, u16 acs_flags)
 {
@@ -3664,6 +3640,23 @@ static int pci_quirk_intel_pch_acs(struct pci_dev *dev, u16 acs_flags)
 	return acs_flags & ~flags ? 0 : 1;
 }
 
+static int pci_quirk_mf_endpoint_acs(struct pci_dev *dev, u16 acs_flags)
+{
+	/*
+	 * SV, TB, and UF are not relevant to multifunction endpoints.
+	 *
+	 * Multifunction devices are only required to implement RR, CR, and DT
+	 * in their ACS capability if they support peer-to-peer transactions.
+	 * Devices matching this quirk have been verified by the vendor to not
+	 * perform peer-to-peer with other functions, allowing us to mask out
+	 * these bits as if they were unimplemented in the ACS capability.
+	 */
+	acs_flags &= ~(PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR |
+		       PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_DT);
+
+	return acs_flags ? 0 : 1;
+}
+
 static const struct pci_dev_acs_enabled {
 	u16 vendor;
 	u16 device;
@@ -3675,6 +3668,30 @@ static const struct pci_dev_acs_enabled {
 	{ PCI_VENDOR_ID_ATI, 0x439d, pci_quirk_amd_sb_acs },
 	{ PCI_VENDOR_ID_ATI, 0x4384, pci_quirk_amd_sb_acs },
 	{ PCI_VENDOR_ID_ATI, 0x4399, pci_quirk_amd_sb_acs },
+	{ PCI_VENDOR_ID_AMD, 0x780f, pci_quirk_amd_sb_acs },
+	{ PCI_VENDOR_ID_AMD, 0x7809, pci_quirk_amd_sb_acs },
+	{ PCI_VENDOR_ID_SOLARFLARE, 0x0903, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_SOLARFLARE, 0x0923, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x10C6, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x10DB, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x10DD, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x10E1, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x10F1, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x10F7, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x10F8, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x10F9, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x10FA, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x10FB, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x10FC, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x1507, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x1514, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x151C, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x1529, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x152A, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x154D, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x154F, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x1551, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_INTEL, 0x1558, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_intel_pch_acs },
 	{ 0 }
 };
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index 827ad831f1dd..a81f413083e4 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -103,40 +103,6 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
 	return ret;
 }
 
-/*
- * find the upstream PCIe-to-PCI bridge of a PCI device
- * if the device is PCIE, return NULL
- * if the device isn't connected to a PCIe bridge (that is its parent is a
- * legacy PCI bridge and the bridge is directly connected to bus 0), return its
- * parent
- */
-struct pci_dev *pci_find_upstream_pcie_bridge(struct pci_dev *pdev)
-{
-	struct pci_dev *tmp = NULL;
-
-	if (pci_is_pcie(pdev))
-		return NULL;
-	while (1) {
-		if (pci_is_root_bus(pdev->bus))
-			break;
-		pdev = pdev->bus->self;
-		/* a p2p bridge */
-		if (!pci_is_pcie(pdev)) {
-			tmp = pdev;
-			continue;
-		}
-		/* PCI device should connect to a PCIe bridge */
-		if (pci_pcie_type(pdev) != PCI_EXP_TYPE_PCI_BRIDGE) {
-			/* Busted hardware? */
-			WARN_ON_ONCE(1);
-			return NULL;
-		}
-		return pdev;
-	}
-
-	return tmp;
-}
-
 static struct pci_bus *pci_do_find_bus(struct pci_bus *bus, unsigned char busnr)
 {
 	struct pci_bus *child;
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 6373985ad3f7..0482235eee92 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1652,7 +1652,7 @@ void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge)
 	struct pci_dev_resource *fail_res;
 	int retval;
 	unsigned long type_mask = IORESOURCE_IO | IORESOURCE_MEM |
-				  IORESOURCE_PREFETCH;
+				  IORESOURCE_PREFETCH | IORESOURCE_MEM_64;
 
 again:
 	__pci_bus_size_bridges(parent, &add_list);
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 53df39a22c8a..116ca3746adb 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -1136,11 +1136,13 @@ static const struct xenbus_device_id xenpci_ids[] = {
 	{""},
 };
 
-static DEFINE_XENBUS_DRIVER(xenpci, "pcifront",
+static struct xenbus_driver xenpci_driver = {
+	.name			= "pcifront",
+	.ids			= xenpci_ids,
 	.probe			= pcifront_xenbus_probe,
 	.remove			= pcifront_xenbus_remove,
 	.otherend_changed	= pcifront_backend_changed,
-);
+};
 
 static int __init pcifront_init(void)
 {
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index 64d06b52f98a..c6a66de6ed72 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -86,7 +86,7 @@ config PINCTRL_BCM2835
 
 config PINCTRL_BCM281XX
 	bool "Broadcom BCM281xx pinctrl driver"
-	depends on OF
+	depends on OF && (ARCH_BCM_MOBILE || COMPILE_TEST)
 	select PINMUX
 	select PINCONF
 	select GENERIC_PINCONF
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index 47f493149863..228972827132 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -1174,7 +1174,7 @@ static int abx500_gpio_probe(struct platform_device *pdev)
 	const struct of_device_id *match;
 	struct abx500_pinctrl *pct;
 	unsigned int id = -1;
-	int ret, err;
+	int ret;
 	int i;
 
 	if (!np) {
@@ -1266,10 +1266,7 @@ static int abx500_gpio_probe(struct platform_device *pdev)
 	return 0;
 
 out_rem_chip:
-	err = gpiochip_remove(&pct->chip);
-	if (err)
-		dev_info(&pdev->dev, "failed to remove gpiochip\n");
-
+	gpiochip_remove(&pct->chip);
 	return ret;
 }
 
@@ -1280,15 +1277,8 @@ out_rem_chip:
 static int abx500_gpio_remove(struct platform_device *pdev)
 {
 	struct abx500_pinctrl *pct = platform_get_drvdata(pdev);
-	int ret;
-
-	ret = gpiochip_remove(&pct->chip);
-	if (ret < 0) {
-		dev_err(pct->dev, "unable to remove gpiochip: %d\n",
-			ret);
-		return ret;
-	}
 
+	gpiochip_remove(&pct->chip);
 	return 0;
 }
 
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index 3c29d9187146..746db6acf648 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -1276,7 +1276,7 @@ static int nmk_gpio_probe(struct platform_device *dev)
 				   IRQ_TYPE_EDGE_FALLING);
 	if (ret) {
 		dev_err(&dev->dev, "could not add irqchip\n");
-		ret = gpiochip_remove(&nmk_chip->chip);
+		gpiochip_remove(&nmk_chip->chip);
 		return -ENODEV;
 	}
 	/* Then register the chain on the parent IRQ */
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index d30dddd21323..e730935fa457 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -936,14 +936,8 @@ EXPORT_SYMBOL(msm_pinctrl_probe);
 int msm_pinctrl_remove(struct platform_device *pdev)
 {
 	struct msm_pinctrl *pctrl = platform_get_drvdata(pdev);
-	int ret;
-
-	ret = gpiochip_remove(&pctrl->chip);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to remove gpiochip\n");
-		return ret;
-	}
 
+	gpiochip_remove(&pctrl->chip);
 	pinctrl_unregister(pctrl->pctrl);
 
 	unregister_restart_handler(&pctrl->restart_nb);
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos5440.c b/drivers/pinctrl/samsung/pinctrl-exynos5440.c
index b995ec2c5d16..88acfc0efd54 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos5440.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos5440.c
@@ -874,11 +874,7 @@ static int exynos5440_gpiolib_register(struct platform_device *pdev,
 static int exynos5440_gpiolib_unregister(struct platform_device *pdev,
 				struct exynos5440_pinctrl_priv_data *priv)
 {
-	int ret = gpiochip_remove(priv->gc);
-	if (ret) {
-		dev_err(&pdev->dev, "gpio chip remove failed\n");
-		return ret;
-	}
+	gpiochip_remove(priv->gc);
 	return 0;
 }
 
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index 4a47691c32b1..2d37c8f49f3c 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -946,9 +946,7 @@ static int samsung_gpiolib_register(struct platform_device *pdev,
 
 fail:
 	for (--i, --bank; i >= 0; --i, --bank)
-		if (gpiochip_remove(&bank->gpio_chip))
-			dev_err(&pdev->dev, "gpio chip %s remove failed\n",
-							bank->gpio_chip.label);
+		gpiochip_remove(&bank->gpio_chip);
 	return ret;
 }
 
@@ -958,16 +956,11 @@ static int samsung_gpiolib_unregister(struct platform_device *pdev,
 {
 	struct samsung_pin_ctrl *ctrl = drvdata->ctrl;
 	struct samsung_pin_bank *bank = ctrl->pin_banks;
-	int ret = 0;
 	int i;
 
-	for (i = 0; !ret && i < ctrl->nr_banks; ++i, ++bank)
-		ret = gpiochip_remove(&bank->gpio_chip);
-
-	if (ret)
-		dev_err(&pdev->dev, "gpio chip remove failed\n");
-
-	return ret;
+	for (i = 0; i < ctrl->nr_banks; ++i, ++bank)
+		gpiochip_remove(&bank->gpio_chip);
+	return 0;
 }
 
 static const struct of_device_id samsung_pinctrl_dt_match[];
diff --git a/drivers/pinctrl/sirf/pinctrl-sirf.c b/drivers/pinctrl/sirf/pinctrl-sirf.c
index b713bd59ffbb..4c831fdfcc2f 100644
--- a/drivers/pinctrl/sirf/pinctrl-sirf.c
+++ b/drivers/pinctrl/sirf/pinctrl-sirf.c
@@ -891,8 +891,7 @@ static int sirfsoc_gpio_probe(struct device_node *np)
 
 out_no_range:
 out_banks:
-	if (gpiochip_remove(&sgpio->chip.gc))
-		dev_err(&pdev->dev, "could not remove gpio chip\n");
+	gpiochip_remove(&sgpio->chip.gc);
 out:
 	iounmap(regs);
 	return err;
diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c
index 390e8e33d5e3..25721bf20092 100644
--- a/drivers/platform/x86/dell-wmi.c
+++ b/drivers/platform/x86/dell-wmi.c
@@ -163,18 +163,24 @@ static void dell_wmi_notify(u32 value, void *context)
 		const struct key_entry *key;
 		int reported_key;
 		u16 *buffer_entry = (u16 *)obj->buffer.pointer;
+		int buffer_size = obj->buffer.length/2;
 
-		if (dell_new_hk_type && (buffer_entry[1] != 0x10)) {
+		if (buffer_size >= 2 && dell_new_hk_type && buffer_entry[1] != 0x10) {
 			pr_info("Received unknown WMI event (0x%x)\n",
 				buffer_entry[1]);
 			kfree(obj);
 			return;
 		}
 
-		if (dell_new_hk_type || buffer_entry[1] == 0x0)
+		if (buffer_size >= 3 && (dell_new_hk_type || buffer_entry[1] == 0x0))
 			reported_key = (int)buffer_entry[2];
-		else
+		else if (buffer_size >= 2)
 			reported_key = (int)buffer_entry[1] & 0xffff;
+		else {
+			pr_info("Received unknown WMI event\n");
+			kfree(obj);
+			return;
+		}
 
 		key = sparse_keymap_entry_from_scancode(dell_wmi_input_dev,
 							reported_key);
diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c
index bd533c22be57..db79902c4a8e 100644
--- a/drivers/platform/x86/eeepc-laptop.c
+++ b/drivers/platform/x86/eeepc-laptop.c
@@ -263,13 +263,11 @@ static int acpi_setter_handle(struct eeepc_laptop *eeepc, int cm,
 /*
  * Sys helpers
  */
-static int parse_arg(const char *buf, unsigned long count, int *val)
+static int parse_arg(const char *buf, int *val)
 {
-	if (!count)
-		return 0;
 	if (sscanf(buf, "%i", val) != 1)
 		return -EINVAL;
-	return count;
+	return 0;
 }
 
 static ssize_t store_sys_acpi(struct device *dev, int cm,
@@ -278,12 +276,13 @@ static ssize_t store_sys_acpi(struct device *dev, int cm,
 	struct eeepc_laptop *eeepc = dev_get_drvdata(dev);
 	int rv, value;
 
-	rv = parse_arg(buf, count, &value);
-	if (rv > 0)
-		value = set_acpi(eeepc, cm, value);
-	if (value < 0)
+	rv = parse_arg(buf, &value);
+	if (rv < 0)
+		return rv;
+	rv = set_acpi(eeepc, cm, value);
+	if (rv < 0)
 		return -EIO;
-	return rv;
+	return count;
 }
 
 static ssize_t show_sys_acpi(struct device *dev, int cm, char *buf)
@@ -296,30 +295,34 @@ static ssize_t show_sys_acpi(struct device *dev, int cm, char *buf)
 	return sprintf(buf, "%d\n", value);
 }
 
-#define EEEPC_CREATE_DEVICE_ATTR(_name, _mode, _cm)			\
-	static ssize_t show_##_name(struct device *dev,			\
+#define EEEPC_ACPI_SHOW_FUNC(_name, _cm)				\
+	static ssize_t _name##_show(struct device *dev,			\
 				    struct device_attribute *attr,	\
 				    char *buf)				\
 	{								\
 		return show_sys_acpi(dev, _cm, buf);			\
-	}								\
-	static ssize_t store_##_name(struct device *dev,		\
+	}
+
+#define EEEPC_ACPI_STORE_FUNC(_name, _cm)				\
+	static ssize_t _name##_store(struct device *dev,		\
 				     struct device_attribute *attr,	\
 				     const char *buf, size_t count)	\
 	{								\
 		return store_sys_acpi(dev, _cm, buf, count);		\
-	}								\
-	static struct device_attribute dev_attr_##_name = {		\
-		.attr = {						\
-			.name = __stringify(_name),			\
-			.mode = _mode },				\
-		.show   = show_##_name,					\
-		.store  = store_##_name,				\
 	}
 
-EEEPC_CREATE_DEVICE_ATTR(camera, 0644, CM_ASL_CAMERA);
-EEEPC_CREATE_DEVICE_ATTR(cardr, 0644, CM_ASL_CARDREADER);
-EEEPC_CREATE_DEVICE_ATTR(disp, 0200, CM_ASL_DISPLAYSWITCH);
+#define EEEPC_CREATE_DEVICE_ATTR_RW(_name, _cm)				\
+	EEEPC_ACPI_SHOW_FUNC(_name, _cm)				\
+	EEEPC_ACPI_STORE_FUNC(_name, _cm)				\
+	static DEVICE_ATTR_RW(_name)
+
+#define EEEPC_CREATE_DEVICE_ATTR_WO(_name, _cm)				\
+	EEEPC_ACPI_STORE_FUNC(_name, _cm)				\
+	static DEVICE_ATTR_WO(_name)
+
+EEEPC_CREATE_DEVICE_ATTR_RW(camera, CM_ASL_CAMERA);
+EEEPC_CREATE_DEVICE_ATTR_RW(cardr, CM_ASL_CARDREADER);
+EEEPC_CREATE_DEVICE_ATTR_WO(disp, CM_ASL_DISPLAYSWITCH);
 
 struct eeepc_cpufv {
 	int num;
@@ -329,14 +332,17 @@ struct eeepc_cpufv {
 static int get_cpufv(struct eeepc_laptop *eeepc, struct eeepc_cpufv *c)
 {
 	c->cur = get_acpi(eeepc, CM_ASL_CPUFV);
+	if (c->cur < 0)
+		return -ENODEV;
+
 	c->num = (c->cur >> 8) & 0xff;
 	c->cur &= 0xff;
-	if (c->cur < 0 || c->num <= 0 || c->num > 12)
+	if (c->num == 0 || c->num > 12)
 		return -ENODEV;
 	return 0;
 }
 
-static ssize_t show_available_cpufv(struct device *dev,
+static ssize_t available_cpufv_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
 {
@@ -353,7 +359,7 @@ static ssize_t show_available_cpufv(struct device *dev,
 	return len;
 }
 
-static ssize_t show_cpufv(struct device *dev,
+static ssize_t cpufv_show(struct device *dev,
 			  struct device_attribute *attr,
 			  char *buf)
 {
@@ -365,7 +371,7 @@ static ssize_t show_cpufv(struct device *dev,
 	return sprintf(buf, "%#x\n", (c.num << 8) | c.cur);
 }
 
-static ssize_t store_cpufv(struct device *dev,
+static ssize_t cpufv_store(struct device *dev,
 			   struct device_attribute *attr,
 			   const char *buf, size_t count)
 {
@@ -377,16 +383,18 @@ static ssize_t store_cpufv(struct device *dev,
 		return -EPERM;
 	if (get_cpufv(eeepc, &c))
 		return -ENODEV;
-	rv = parse_arg(buf, count, &value);
+	rv = parse_arg(buf, &value);
 	if (rv < 0)
 		return rv;
-	if (!rv || value < 0 || value >= c.num)
+	if (value < 0 || value >= c.num)
 		return -EINVAL;
-	set_acpi(eeepc, CM_ASL_CPUFV, value);
-	return rv;
+	rv = set_acpi(eeepc, CM_ASL_CPUFV, value);
+	if (rv)
+		return rv;
+	return count;
 }
 
-static ssize_t show_cpufv_disabled(struct device *dev,
+static ssize_t cpufv_disabled_show(struct device *dev,
 			  struct device_attribute *attr,
 			  char *buf)
 {
@@ -395,14 +403,14 @@ static ssize_t show_cpufv_disabled(struct device *dev,
 	return sprintf(buf, "%d\n", eeepc->cpufv_disabled);
 }
 
-static ssize_t store_cpufv_disabled(struct device *dev,
+static ssize_t cpufv_disabled_store(struct device *dev,
 			   struct device_attribute *attr,
 			   const char *buf, size_t count)
 {
 	struct eeepc_laptop *eeepc = dev_get_drvdata(dev);
 	int rv, value;
 
-	rv = parse_arg(buf, count, &value);
+	rv = parse_arg(buf, &value);
 	if (rv < 0)
 		return rv;
 
@@ -412,7 +420,7 @@ static ssize_t store_cpufv_disabled(struct device *dev,
 			pr_warn("cpufv enabled (not officially supported "
 				"on this model)\n");
 		eeepc->cpufv_disabled = false;
-		return rv;
+		return count;
 	case 1:
 		return -EPERM;
 	default:
@@ -421,29 +429,9 @@ static ssize_t store_cpufv_disabled(struct device *dev,
 }
 
 
-static struct device_attribute dev_attr_cpufv = {
-	.attr = {
-		.name = "cpufv",
-		.mode = 0644 },
-	.show   = show_cpufv,
-	.store  = store_cpufv
-};
-
-static struct device_attribute dev_attr_available_cpufv = {
-	.attr = {
-		.name = "available_cpufv",
-		.mode = 0444 },
-	.show   = show_available_cpufv
-};
-
-static struct device_attribute dev_attr_cpufv_disabled = {
-	.attr = {
-		.name = "cpufv_disabled",
-		.mode = 0644 },
-	.show   = show_cpufv_disabled,
-	.store  = store_cpufv_disabled
-};
-
+static DEVICE_ATTR_RW(cpufv);
+static DEVICE_ATTR_RO(available_cpufv);
+static DEVICE_ATTR_RW(cpufv_disabled);
 
 static struct attribute *platform_attributes[] = {
 	&dev_attr_camera.attr,
@@ -545,7 +533,7 @@ static int eeepc_led_init(struct eeepc_laptop *eeepc)
 	eeepc->tpd_led.name = "eeepc::touchpad";
 	eeepc->tpd_led.brightness_set = tpd_led_set;
 	if (get_acpi(eeepc, CM_ASL_TPD) >= 0) /* if method is available */
-	  eeepc->tpd_led.brightness_get = tpd_led_get;
+		eeepc->tpd_led.brightness_get = tpd_led_get;
 	eeepc->tpd_led.max_brightness = 1;
 
 	rv = led_classdev_register(&eeepc->platform_device->dev,
@@ -680,22 +668,21 @@ static int eeepc_register_rfkill_notifier(struct eeepc_laptop *eeepc,
 
 	status = acpi_get_handle(NULL, node, &handle);
 
-	if (ACPI_SUCCESS(status)) {
-		status = acpi_install_notify_handler(handle,
-						     ACPI_SYSTEM_NOTIFY,
-						     eeepc_rfkill_notify,
-						     eeepc);
-		if (ACPI_FAILURE(status))
-			pr_warn("Failed to register notify on %s\n", node);
-
-		/*
-		 * Refresh pci hotplug in case the rfkill state was
-		 * changed during setup.
-		 */
-		eeepc_rfkill_hotplug(eeepc, handle);
-	} else
+	if (ACPI_FAILURE(status))
 		return -ENODEV;
 
+	status = acpi_install_notify_handler(handle,
+					     ACPI_SYSTEM_NOTIFY,
+					     eeepc_rfkill_notify,
+					     eeepc);
+	if (ACPI_FAILURE(status))
+		pr_warn("Failed to register notify on %s\n", node);
+
+	/*
+	 * Refresh pci hotplug in case the rfkill state was
+	 * changed during setup.
+	 */
+	eeepc_rfkill_hotplug(eeepc, handle);
 	return 0;
 }
 
@@ -707,20 +694,21 @@ static void eeepc_unregister_rfkill_notifier(struct eeepc_laptop *eeepc,
 
 	status = acpi_get_handle(NULL, node, &handle);
 
-	if (ACPI_SUCCESS(status)) {
-		status = acpi_remove_notify_handler(handle,
-						     ACPI_SYSTEM_NOTIFY,
-						     eeepc_rfkill_notify);
-		if (ACPI_FAILURE(status))
-			pr_err("Error removing rfkill notify handler %s\n",
-				node);
-			/*
-			 * Refresh pci hotplug in case the rfkill
-			 * state was changed after
-			 * eeepc_unregister_rfkill_notifier()
-			 */
-		eeepc_rfkill_hotplug(eeepc, handle);
-	}
+	if (ACPI_FAILURE(status))
+		return;
+
+	status = acpi_remove_notify_handler(handle,
+					     ACPI_SYSTEM_NOTIFY,
+					     eeepc_rfkill_notify);
+	if (ACPI_FAILURE(status))
+		pr_err("Error removing rfkill notify handler %s\n",
+			node);
+		/*
+		 * Refresh pci hotplug in case the rfkill
+		 * state was changed after
+		 * eeepc_unregister_rfkill_notifier()
+		 */
+	eeepc_rfkill_hotplug(eeepc, handle);
 }
 
 static int eeepc_get_adapter_status(struct hotplug_slot *hotplug_slot,
@@ -1042,10 +1030,11 @@ static ssize_t store_sys_hwmon(void (*set)(int), const char *buf, size_t count)
 {
 	int rv, value;
 
-	rv = parse_arg(buf, count, &value);
-	if (rv > 0)
-		set(value);
-	return rv;
+	rv = parse_arg(buf, &value);
+	if (rv < 0)
+		return rv;
+	set(value);
+	return count;
 }
 
 static ssize_t show_sys_hwmon(int (*get)(void), char *buf)
@@ -1053,26 +1042,36 @@ static ssize_t show_sys_hwmon(int (*get)(void), char *buf)
 	return sprintf(buf, "%d\n", get());
 }
 
-#define EEEPC_CREATE_SENSOR_ATTR(_name, _mode, _get, _set)		\
-	static ssize_t show_##_name(struct device *dev,			\
+#define EEEPC_SENSOR_SHOW_FUNC(_name, _get)				\
+	static ssize_t _name##_show(struct device *dev,			\
 				    struct device_attribute *attr,	\
 				    char *buf)				\
 	{								\
 		return show_sys_hwmon(_get, buf);			\
-	}								\
-	static ssize_t store_##_name(struct device *dev,		\
+	}
+
+#define EEEPC_SENSOR_STORE_FUNC(_name, _set)				\
+	static ssize_t _name##_store(struct device *dev,		\
 				     struct device_attribute *attr,	\
 				     const char *buf, size_t count)	\
 	{								\
 		return store_sys_hwmon(_set, buf, count);		\
-	}								\
-	static DEVICE_ATTR(_name, _mode, show_##_name, store_##_name)
+	}
+
+#define EEEPC_CREATE_SENSOR_ATTR_RW(_name, _get, _set)			\
+	EEEPC_SENSOR_SHOW_FUNC(_name, _get)				\
+	EEEPC_SENSOR_STORE_FUNC(_name, _set)				\
+	static DEVICE_ATTR_RW(_name)
 
-EEEPC_CREATE_SENSOR_ATTR(fan1_input, S_IRUGO, eeepc_get_fan_rpm, NULL);
-EEEPC_CREATE_SENSOR_ATTR(pwm1, S_IRUGO | S_IWUSR,
-			 eeepc_get_fan_pwm, eeepc_set_fan_pwm);
-EEEPC_CREATE_SENSOR_ATTR(pwm1_enable, S_IRUGO | S_IWUSR,
-			 eeepc_get_fan_ctrl, eeepc_set_fan_ctrl);
+#define EEEPC_CREATE_SENSOR_ATTR_RO(_name, _get)			\
+	EEEPC_SENSOR_SHOW_FUNC(_name, _get)				\
+	static DEVICE_ATTR_RO(_name)
+
+EEEPC_CREATE_SENSOR_ATTR_RO(fan1_input, eeepc_get_fan_rpm);
+EEEPC_CREATE_SENSOR_ATTR_RW(pwm1, eeepc_get_fan_pwm,
+			    eeepc_set_fan_pwm);
+EEEPC_CREATE_SENSOR_ATTR_RW(pwm1_enable, eeepc_get_fan_ctrl,
+			    eeepc_set_fan_ctrl);
 
 static struct attribute *hwmon_attrs[] = {
 	&dev_attr_pwm1.attr,
@@ -1424,8 +1423,9 @@ static int eeepc_acpi_add(struct acpi_device *device)
 		result = eeepc_backlight_init(eeepc);
 		if (result)
 			goto fail_backlight;
-	} else
+	} else {
 		pr_info("Backlight controlled by ACPI video driver\n");
+	}
 
 	result = eeepc_input_init(eeepc);
 	if (result)
diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c
index 87aa28c4280f..2655d4a988f3 100644
--- a/drivers/platform/x86/fujitsu-laptop.c
+++ b/drivers/platform/x86/fujitsu-laptop.c
@@ -1050,6 +1050,13 @@ static struct acpi_driver acpi_fujitsu_hotkey_driver = {
 		},
 };
 
+static const struct acpi_device_id fujitsu_ids[] __used = {
+	{ACPI_FUJITSU_HID, 0},
+	{ACPI_FUJITSU_HOTKEY_HID, 0},
+	{"", 0}
+};
+MODULE_DEVICE_TABLE(acpi, fujitsu_ids);
+
 static int __init fujitsu_init(void)
 {
 	int ret, result, max_brightness;
@@ -1208,12 +1215,3 @@ MODULE_LICENSE("GPL");
 MODULE_ALIAS("dmi:*:svnFUJITSUSIEMENS:*:pvr:rvnFUJITSU:rnFJNB1D3:*:cvrS6410:*");
 MODULE_ALIAS("dmi:*:svnFUJITSUSIEMENS:*:pvr:rvnFUJITSU:rnFJNB1E6:*:cvrS6420:*");
 MODULE_ALIAS("dmi:*:svnFUJITSU:*:pvr:rvnFUJITSU:rnFJNB19C:*:cvrS7020:*");
-
-static struct pnp_device_id pnp_ids[] __used = {
-	{.id = "FUJ02bf"},
-	{.id = "FUJ02B1"},
-	{.id = "FUJ02E3"},
-	{.id = ""}
-};
-
-MODULE_DEVICE_TABLE(pnp, pnp_ids);
diff --git a/drivers/platform/x86/intel-rst.c b/drivers/platform/x86/intel-rst.c
index d45bca34bf1b..7344d841f4d9 100644
--- a/drivers/platform/x86/intel-rst.c
+++ b/drivers/platform/x86/intel-rst.c
@@ -35,7 +35,7 @@ static ssize_t irst_show_wakeup_events(struct device *dev,
 	acpi = to_acpi_device(dev);
 
 	status = acpi_evaluate_integer(acpi->handle, "GFFS", NULL, &value);
-	if (!ACPI_SUCCESS(status))
+	if (ACPI_FAILURE(status))
 		return -EINVAL;
 
 	return sprintf(buf, "%lld\n", value);
@@ -59,7 +59,7 @@ static ssize_t irst_store_wakeup_events(struct device *dev,
 
 	status = acpi_execute_simple_method(acpi->handle, "SFFS", value);
 
-	if (!ACPI_SUCCESS(status))
+	if (ACPI_FAILURE(status))
 		return -EINVAL;
 
 	return count;
@@ -81,7 +81,7 @@ static ssize_t irst_show_wakeup_time(struct device *dev,
 	acpi = to_acpi_device(dev);
 
 	status = acpi_evaluate_integer(acpi->handle, "GFTV", NULL, &value);
-	if (!ACPI_SUCCESS(status))
+	if (ACPI_FAILURE(status))
 		return -EINVAL;
 
 	return sprintf(buf, "%lld\n", value);
@@ -105,7 +105,7 @@ static ssize_t irst_store_wakeup_time(struct device *dev,
 
 	status = acpi_execute_simple_method(acpi->handle, "SFTV", value);
 
-	if (!ACPI_SUCCESS(status))
+	if (ACPI_FAILURE(status))
 		return -EINVAL;
 
 	return count;
@@ -119,21 +119,16 @@ static struct device_attribute irst_timeout_attr = {
 
 static int irst_add(struct acpi_device *acpi)
 {
-	int error = 0;
+	int error;
 
 	error = device_create_file(&acpi->dev, &irst_timeout_attr);
-	if (error)
-		goto out;
+	if (unlikely(error))
+		return error;
 
 	error = device_create_file(&acpi->dev, &irst_wakeup_attr);
-	if (error)
-		goto out_timeout;
+	if (unlikely(error))
+		device_remove_file(&acpi->dev, &irst_timeout_attr);
 
-	return 0;
-
-out_timeout:
-	device_remove_file(&acpi->dev, &irst_timeout_attr);
-out:
 	return error;
 }
 
diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c
index 40929e4f7ad7..04fed00b88e9 100644
--- a/drivers/platform/x86/intel_pmic_gpio.c
+++ b/drivers/platform/x86/intel_pmic_gpio.c
@@ -301,8 +301,7 @@ static int platform_pmic_gpio_probe(struct platform_device *pdev)
 	return 0;
 
 fail_request_irq:
-	if (gpiochip_remove(&pg->chip))
-		pr_err("gpiochip_remove failed\n");
+	gpiochip_remove(&pg->chip);
 err:
 	iounmap(pg->gpiointr);
 err2:
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 3bbc6eb60de5..cf0f89364d44 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -3440,7 +3440,7 @@ err_exit:
 	delete_attr_set(hotkey_dev_attributes, &tpacpi_pdev->dev.kobj);
 	hotkey_dev_attributes = NULL;
 
-	return (res < 0)? res : 1;
+	return (res < 0) ? res : 1;
 }
 
 /* Thinkpad X1 Carbon support 5 modes including Home mode, Web browser
@@ -4576,7 +4576,7 @@ static int __init video_init(struct ibm_init_struct *iibm)
 		str_supported(video_supported != TPACPI_VIDEO_NONE),
 		video_supported);
 
-	return (video_supported != TPACPI_VIDEO_NONE)? 0 : 1;
+	return (video_supported != TPACPI_VIDEO_NONE) ? 0 : 1;
 }
 
 static void video_exit(void)
@@ -4669,7 +4669,7 @@ static int video_outputsw_set(int status)
 		return -ENOSYS;
 	}
 
-	return (res)? 0 : -EIO;
+	return (res) ? 0 : -EIO;
 }
 
 static int video_autosw_get(void)
@@ -4695,7 +4695,7 @@ static int video_autosw_get(void)
 
 static int video_autosw_set(int enable)
 {
-	if (!acpi_evalf(vid_handle, NULL, "_DOS", "vd", (enable)? 1 : 0))
+	if (!acpi_evalf(vid_handle, NULL, "_DOS", "vd", (enable) ? 1 : 0))
 		return -EIO;
 	return 0;
 }
@@ -4730,20 +4730,20 @@ static int video_outputsw_cycle(void)
 		return -EIO;
 	}
 
-	return (res)? 0 : -EIO;
+	return (res) ? 0 : -EIO;
 }
 
 static int video_expand_toggle(void)
 {
 	switch (video_supported) {
 	case TPACPI_VIDEO_570:
-		return acpi_evalf(ec_handle, NULL, "_Q17", "v")?
+		return acpi_evalf(ec_handle, NULL, "_Q17", "v") ?
 			0 : -EIO;
 	case TPACPI_VIDEO_770:
-		return acpi_evalf(vid_handle, NULL, "VEXP", "v")?
+		return acpi_evalf(vid_handle, NULL, "VEXP", "v") ?
 			0 : -EIO;
 	case TPACPI_VIDEO_NEW:
-		return acpi_evalf(NULL, NULL, "\\VEXP", "v")?
+		return acpi_evalf(NULL, NULL, "\\VEXP", "v") ?
 			0 : -EIO;
 	default:
 		return -ENOSYS;
@@ -4887,14 +4887,14 @@ static int light_set_status(int status)
 	if (tp_features.light) {
 		if (cmos_handle) {
 			rc = acpi_evalf(cmos_handle, NULL, NULL, "vd",
-					(status)?
+					(status) ?
 						TP_CMOS_THINKLIGHT_ON :
 						TP_CMOS_THINKLIGHT_OFF);
 		} else {
 			rc = acpi_evalf(lght_handle, NULL, NULL, "vd",
-					(status)? 1 : 0);
+					(status) ? 1 : 0);
 		}
-		return (rc)? 0 : -EIO;
+		return (rc) ? 0 : -EIO;
 	}
 
 	return -ENXIO;
@@ -4923,7 +4923,7 @@ static void light_sysfs_set(struct led_classdev *led_cdev,
 
 static enum led_brightness light_sysfs_get(struct led_classdev *led_cdev)
 {
-	return (light_get_status() == 1)? LED_FULL : LED_OFF;
+	return (light_get_status() == 1) ? LED_FULL : LED_OFF;
 }
 
 static struct tpacpi_led_classdev tpacpi_led_thinklight = {
@@ -5045,7 +5045,7 @@ static ssize_t cmos_command_store(struct device *dev,
 		return -EINVAL;
 
 	res = issue_thinkpad_cmos_command(cmos_cmd);
-	return (res)? res : count;
+	return (res) ? res : count;
 }
 
 static struct device_attribute dev_attr_cmos_command =
@@ -5069,7 +5069,7 @@ static int __init cmos_init(struct ibm_init_struct *iibm)
 	if (res)
 		return res;
 
-	return (cmos_handle)? 0 : 1;
+	return (cmos_handle) ? 0 : 1;
 }
 
 static void cmos_exit(void)
@@ -5179,9 +5179,9 @@ static int led_get_status(const unsigned int led)
 		if (!acpi_evalf(ec_handle,
 				&status, "GLED", "dd", 1 << led))
 			return -EIO;
-		led_s = (status == 0)?
+		led_s = (status == 0) ?
 				TPACPI_LED_OFF :
-				((status == 1)?
+				((status == 1) ?
 					TPACPI_LED_ON :
 					TPACPI_LED_BLINK);
 		tpacpi_led_state_cache[led] = led_s;
@@ -5578,7 +5578,7 @@ static int __init beep_init(struct ibm_init_struct *iibm)
 
 	tp_features.beep_needs_two_args = !!(quirks & TPACPI_BEEP_Q1);
 
-	return (beep_handle)? 0 : 1;
+	return (beep_handle) ? 0 : 1;
 }
 
 static int beep_read(struct seq_file *m)
@@ -6527,7 +6527,7 @@ static int brightness_write(char *buf)
 	if (!rc && ibm_backlight_device)
 		backlight_force_update(ibm_backlight_device,
 					BACKLIGHT_UPDATE_SYSFS);
-	return (rc == -EINTR)? -ERESTARTSYS : rc;
+	return (rc == -EINTR) ? -ERESTARTSYS : rc;
 }
 
 static struct ibm_struct brightness_driver_data = {
@@ -7984,7 +7984,7 @@ static ssize_t fan_pwm1_store(struct device *dev,
 	}
 
 	mutex_unlock(&fan_mutex);
-	return (rc)? rc : count;
+	return (rc) ? rc : count;
 }
 
 static struct device_attribute dev_attr_fan_pwm1 =
@@ -8662,7 +8662,7 @@ static const char * __init str_supported(int is_supported)
 {
 	static char text_unsupported[] __initdata = "not supported";
 
-	return (is_supported)? &text_unsupported[4] : &text_unsupported[0];
+	return (is_supported) ? &text_unsupported[4] : &text_unsupported[0];
 }
 #endif /* CONFIG_THINKPAD_ACPI_DEBUG */
 
@@ -8783,7 +8783,7 @@ err_out:
 		ibm->name, ret);
 
 	ibm_exit(ibm);
-	return (ret < 0)? ret : 0;
+	return (ret < 0) ? ret : 0;
 }
 
 /* Probing */
@@ -8794,7 +8794,7 @@ static bool __pure __init tpacpi_is_fw_digit(const char c)
 }
 
 /* Most models: xxyTkkWW (#.##c); Ancient 570/600 and -SL lacks (#.##c) */
-static bool __pure __init tpacpi_is_valid_fw_id(const char* const s,
+static bool __pure __init tpacpi_is_valid_fw_id(const char * const s,
 						const char t)
 {
 	return s && strlen(s) >= 8 &&
@@ -8878,13 +8878,13 @@ static int __must_check __init get_thinkpad_model_data(
 	}
 
 	s = dmi_get_system_info(DMI_PRODUCT_VERSION);
-	if (s && !(strnicmp(s, "ThinkPad", 8) && strnicmp(s, "Lenovo", 6))) {
+	if (s && !(strncasecmp(s, "ThinkPad", 8) && strncasecmp(s, "Lenovo", 6))) {
 		tp->model_str = kstrdup(s, GFP_KERNEL);
 		if (!tp->model_str)
 			return -ENOMEM;
 	} else {
 		s = dmi_get_system_info(DMI_BIOS_VENDOR);
-		if (s && !(strnicmp(s, "Lenovo", 6))) {
+		if (s && !(strncasecmp(s, "Lenovo", 6))) {
 			tp->model_str = kstrdup(s, GFP_KERNEL);
 			if (!tp->model_str)
 				return -ENOMEM;
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index d0dce734b2ed..ef3a1904e92f 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -71,7 +71,8 @@ MODULE_LICENSE("GPL");
 /* Toshiba ACPI method paths */
 #define METHOD_VIDEO_OUT	"\\_SB_.VALX.DSSX"
 
-/* Toshiba HCI interface definitions
+/* The Toshiba configuration interface is composed of the HCI and the SCI,
+ * which are defined as follows:
  *
  * HCI is Toshiba's "Hardware Control Interface" which is supposed to
  * be uniform across all their models.  Ideally we would just call
@@ -84,7 +85,7 @@ MODULE_LICENSE("GPL");
  * conceal differences in hardware between different models.
  */
 
-#define HCI_WORDS			6
+#define TCI_WORDS			6
 
 /* operations */
 #define HCI_SET				0xff00
@@ -95,17 +96,18 @@ MODULE_LICENSE("GPL");
 #define SCI_SET				0xf400
 
 /* return codes */
-#define HCI_SUCCESS			0x0000
-#define HCI_FAILURE			0x1000
-#define HCI_NOT_SUPPORTED		0x8000
-#define HCI_EMPTY			0x8c00
-#define HCI_DATA_NOT_AVAILABLE		0x8d20
-#define HCI_NOT_INITIALIZED		0x8d50
-#define SCI_OPEN_CLOSE_OK		0x0044
-#define SCI_ALREADY_OPEN		0x8100
-#define SCI_NOT_OPENED			0x8200
-#define SCI_INPUT_DATA_ERROR		0x8300
-#define SCI_NOT_PRESENT			0x8600
+#define TOS_SUCCESS			0x0000
+#define TOS_OPEN_CLOSE_OK		0x0044
+#define TOS_FAILURE			0x1000
+#define TOS_NOT_SUPPORTED		0x8000
+#define TOS_ALREADY_OPEN		0x8100
+#define TOS_NOT_OPENED			0x8200
+#define TOS_INPUT_DATA_ERROR		0x8300
+#define TOS_WRITE_PROTECTED		0x8400
+#define TOS_NOT_PRESENT			0x8600
+#define TOS_FIFO_EMPTY			0x8c00
+#define TOS_DATA_NOT_AVAILABLE		0x8d20
+#define TOS_NOT_INITIALIZED		0x8d50
 
 /* registers */
 #define HCI_FAN				0x0004
@@ -138,8 +140,12 @@ MODULE_LICENSE("GPL");
 #define HCI_WIRELESS_BT_PRESENT		0x0f
 #define HCI_WIRELESS_BT_ATTACH		0x40
 #define HCI_WIRELESS_BT_POWER		0x80
+#define SCI_KBD_MODE_MASK		0x1f
 #define SCI_KBD_MODE_FNZ		0x1
 #define SCI_KBD_MODE_AUTO		0x2
+#define SCI_KBD_MODE_ON			0x8
+#define SCI_KBD_MODE_OFF		0x10
+#define SCI_KBD_TIME_MAX		0x3c001a
 
 struct toshiba_acpi_dev {
 	struct acpi_device *acpi_dev;
@@ -155,6 +161,7 @@ struct toshiba_acpi_dev {
 	int force_fan;
 	int last_key_event;
 	int key_event_valid;
+	int kbd_type;
 	int kbd_mode;
 	int kbd_time;
 
@@ -190,6 +197,7 @@ static const struct key_entry toshiba_acpi_keymap[] = {
 	{ KE_KEY, 0x101, { KEY_MUTE } },
 	{ KE_KEY, 0x102, { KEY_ZOOMOUT } },
 	{ KE_KEY, 0x103, { KEY_ZOOMIN } },
+	{ KE_KEY, 0x10f, { KEY_TAB } },
 	{ KE_KEY, 0x12c, { KEY_KBDILLUMTOGGLE } },
 	{ KE_KEY, 0x139, { KEY_ZOOMRESET } },
 	{ KE_KEY, 0x13b, { KEY_COFFEE } },
@@ -210,7 +218,11 @@ static const struct key_entry toshiba_acpi_keymap[] = {
 	{ KE_KEY, 0xb32, { KEY_NEXTSONG } },
 	{ KE_KEY, 0xb33, { KEY_PLAYPAUSE } },
 	{ KE_KEY, 0xb5a, { KEY_MEDIA } },
-	{ KE_IGNORE, 0x1430, { KEY_RESERVED } },
+	{ KE_IGNORE, 0x1430, { KEY_RESERVED } }, /* Wake from sleep */
+	{ KE_IGNORE, 0x1501, { KEY_RESERVED } }, /* Output changed */
+	{ KE_IGNORE, 0x1502, { KEY_RESERVED } }, /* HDMI plugged/unplugged */
+	{ KE_IGNORE, 0x1ABE, { KEY_RESERVED } }, /* Protection level set */
+	{ KE_IGNORE, 0x1ABF, { KEY_RESERVED } }, /* Protection level off */
 	{ KE_END, 0 },
 };
 
@@ -264,22 +276,22 @@ static int write_acpi_int(const char *methodName, int val)
 	return (status == AE_OK) ? 0 : -EIO;
 }
 
-/* Perform a raw HCI call.  Here we don't care about input or output buffer
- * format.
+/* Perform a raw configuration call.  Here we don't care about input or output
+ * buffer format.
  */
-static acpi_status hci_raw(struct toshiba_acpi_dev *dev,
-			   const u32 in[HCI_WORDS], u32 out[HCI_WORDS])
+static acpi_status tci_raw(struct toshiba_acpi_dev *dev,
+			   const u32 in[TCI_WORDS], u32 out[TCI_WORDS])
 {
 	struct acpi_object_list params;
-	union acpi_object in_objs[HCI_WORDS];
+	union acpi_object in_objs[TCI_WORDS];
 	struct acpi_buffer results;
-	union acpi_object out_objs[HCI_WORDS + 1];
+	union acpi_object out_objs[TCI_WORDS + 1];
 	acpi_status status;
 	int i;
 
-	params.count = HCI_WORDS;
+	params.count = TCI_WORDS;
 	params.pointer = in_objs;
-	for (i = 0; i < HCI_WORDS; ++i) {
+	for (i = 0; i < TCI_WORDS; ++i) {
 		in_objs[i].type = ACPI_TYPE_INTEGER;
 		in_objs[i].integer.value = in[i];
 	}
@@ -290,7 +302,7 @@ static acpi_status hci_raw(struct toshiba_acpi_dev *dev,
 	status = acpi_evaluate_object(dev->acpi_dev->handle,
 				      (char *)dev->method_hci, &params,
 				      &results);
-	if ((status == AE_OK) && (out_objs->package.count <= HCI_WORDS)) {
+	if ((status == AE_OK) && (out_objs->package.count <= TCI_WORDS)) {
 		for (i = 0; i < out_objs->package.count; ++i) {
 			out[i] = out_objs->package.elements[i].integer.value;
 		}
@@ -305,47 +317,49 @@ static acpi_status hci_raw(struct toshiba_acpi_dev *dev,
  * may be useful (such as "not supported").
  */
 
-static acpi_status hci_write1(struct toshiba_acpi_dev *dev, u32 reg,
-			      u32 in1, u32 *result)
+static u32 hci_write1(struct toshiba_acpi_dev *dev, u32 reg, u32 in1)
 {
-	u32 in[HCI_WORDS] = { HCI_SET, reg, in1, 0, 0, 0 };
-	u32 out[HCI_WORDS];
-	acpi_status status = hci_raw(dev, in, out);
-	*result = (status == AE_OK) ? out[0] : HCI_FAILURE;
-	return status;
+	u32 in[TCI_WORDS] = { HCI_SET, reg, in1, 0, 0, 0 };
+	u32 out[TCI_WORDS];
+	acpi_status status = tci_raw(dev, in, out);
+
+	return ACPI_SUCCESS(status) ? out[0] : TOS_FAILURE;
 }
 
-static acpi_status hci_read1(struct toshiba_acpi_dev *dev, u32 reg,
-			     u32 *out1, u32 *result)
+static u32 hci_read1(struct toshiba_acpi_dev *dev, u32 reg, u32 *out1)
 {
-	u32 in[HCI_WORDS] = { HCI_GET, reg, 0, 0, 0, 0 };
-	u32 out[HCI_WORDS];
-	acpi_status status = hci_raw(dev, in, out);
+	u32 in[TCI_WORDS] = { HCI_GET, reg, 0, 0, 0, 0 };
+	u32 out[TCI_WORDS];
+	acpi_status status = tci_raw(dev, in, out);
+	if (ACPI_FAILURE(status))
+		return TOS_FAILURE;
+
 	*out1 = out[2];
-	*result = (status == AE_OK) ? out[0] : HCI_FAILURE;
-	return status;
+
+	return out[0];
 }
 
-static acpi_status hci_write2(struct toshiba_acpi_dev *dev, u32 reg,
-			      u32 in1, u32 in2, u32 *result)
+static u32 hci_write2(struct toshiba_acpi_dev *dev, u32 reg, u32 in1, u32 in2)
 {
-	u32 in[HCI_WORDS] = { HCI_SET, reg, in1, in2, 0, 0 };
-	u32 out[HCI_WORDS];
-	acpi_status status = hci_raw(dev, in, out);
-	*result = (status == AE_OK) ? out[0] : HCI_FAILURE;
-	return status;
+	u32 in[TCI_WORDS] = { HCI_SET, reg, in1, in2, 0, 0 };
+	u32 out[TCI_WORDS];
+	acpi_status status = tci_raw(dev, in, out);
+
+	return ACPI_SUCCESS(status) ? out[0] : TOS_FAILURE;
 }
 
-static acpi_status hci_read2(struct toshiba_acpi_dev *dev, u32 reg,
-			     u32 *out1, u32 *out2, u32 *result)
+static u32 hci_read2(struct toshiba_acpi_dev *dev, u32 reg, u32 *out1, u32 *out2)
 {
-	u32 in[HCI_WORDS] = { HCI_GET, reg, *out1, *out2, 0, 0 };
-	u32 out[HCI_WORDS];
-	acpi_status status = hci_raw(dev, in, out);
+	u32 in[TCI_WORDS] = { HCI_GET, reg, *out1, *out2, 0, 0 };
+	u32 out[TCI_WORDS];
+	acpi_status status = tci_raw(dev, in, out);
+	if (ACPI_FAILURE(status))
+		return TOS_FAILURE;
+
 	*out1 = out[2];
 	*out2 = out[3];
-	*result = (status == AE_OK) ? out[0] : HCI_FAILURE;
-	return status;
+
+	return out[0];
 }
 
 /* common sci tasks
@@ -353,22 +367,22 @@ static acpi_status hci_read2(struct toshiba_acpi_dev *dev, u32 reg,
 
 static int sci_open(struct toshiba_acpi_dev *dev)
 {
-	u32 in[HCI_WORDS] = { SCI_OPEN, 0, 0, 0, 0, 0 };
-	u32 out[HCI_WORDS];
+	u32 in[TCI_WORDS] = { SCI_OPEN, 0, 0, 0, 0, 0 };
+	u32 out[TCI_WORDS];
 	acpi_status status;
 
-	status = hci_raw(dev, in, out);
-	if  (ACPI_FAILURE(status) || out[0] == HCI_FAILURE) {
+	status = tci_raw(dev, in, out);
+	if  (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
 		pr_err("ACPI call to open SCI failed\n");
 		return 0;
 	}
 
-	if (out[0] == SCI_OPEN_CLOSE_OK) {
+	if (out[0] == TOS_OPEN_CLOSE_OK) {
 		return 1;
-	} else if (out[0] == SCI_ALREADY_OPEN) {
+	} else if (out[0] == TOS_ALREADY_OPEN) {
 		pr_info("Toshiba SCI already opened\n");
 		return 1;
-	} else if (out[0] == SCI_NOT_PRESENT) {
+	} else if (out[0] == TOS_NOT_PRESENT) {
 		pr_info("Toshiba SCI is not present\n");
 	}
 
@@ -377,61 +391,62 @@ static int sci_open(struct toshiba_acpi_dev *dev)
 
 static void sci_close(struct toshiba_acpi_dev *dev)
 {
-	u32 in[HCI_WORDS] = { SCI_CLOSE, 0, 0, 0, 0, 0 };
-	u32 out[HCI_WORDS];
+	u32 in[TCI_WORDS] = { SCI_CLOSE, 0, 0, 0, 0, 0 };
+	u32 out[TCI_WORDS];
 	acpi_status status;
 
-	status = hci_raw(dev, in, out);
-	if (ACPI_FAILURE(status) || out[0] == HCI_FAILURE) {
+	status = tci_raw(dev, in, out);
+	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
 		pr_err("ACPI call to close SCI failed\n");
 		return;
 	}
 
-	if (out[0] == SCI_OPEN_CLOSE_OK)
+	if (out[0] == TOS_OPEN_CLOSE_OK)
 		return;
-	else if (out[0] == SCI_NOT_OPENED)
+	else if (out[0] == TOS_NOT_OPENED)
 		pr_info("Toshiba SCI not opened\n");
-	else if (out[0] == SCI_NOT_PRESENT)
+	else if (out[0] == TOS_NOT_PRESENT)
 		pr_info("Toshiba SCI is not present\n");
 }
 
-static acpi_status sci_read(struct toshiba_acpi_dev *dev, u32 reg,
-			    u32 *out1, u32 *result)
+static u32 sci_read(struct toshiba_acpi_dev *dev, u32 reg, u32 *out1)
 {
-	u32 in[HCI_WORDS] = { SCI_GET, reg, 0, 0, 0, 0 };
-	u32 out[HCI_WORDS];
-	acpi_status status = hci_raw(dev, in, out);
+	u32 in[TCI_WORDS] = { SCI_GET, reg, 0, 0, 0, 0 };
+	u32 out[TCI_WORDS];
+	acpi_status status = tci_raw(dev, in, out);
+	if (ACPI_FAILURE(status))
+		return TOS_FAILURE;
+
 	*out1 = out[2];
-	*result = (ACPI_SUCCESS(status)) ? out[0] : HCI_FAILURE;
-	return status;
+
+	return out[0];
 }
 
-static acpi_status sci_write(struct toshiba_acpi_dev *dev, u32 reg,
-			     u32 in1, u32 *result)
+static u32 sci_write(struct toshiba_acpi_dev *dev, u32 reg, u32 in1)
 {
-	u32 in[HCI_WORDS] = { SCI_SET, reg, in1, 0, 0, 0 };
-	u32 out[HCI_WORDS];
-	acpi_status status = hci_raw(dev, in, out);
-	*result = (ACPI_SUCCESS(status)) ? out[0] : HCI_FAILURE;
-	return status;
+	u32 in[TCI_WORDS] = { SCI_SET, reg, in1, 0, 0, 0 };
+	u32 out[TCI_WORDS];
+	acpi_status status = tci_raw(dev, in, out);
+
+	return ACPI_SUCCESS(status) ? out[0] : TOS_FAILURE;
 }
 
 /* Illumination support */
 static int toshiba_illumination_available(struct toshiba_acpi_dev *dev)
 {
-	u32 in[HCI_WORDS] = { SCI_GET, SCI_ILLUMINATION, 0, 0, 0, 0 };
-	u32 out[HCI_WORDS];
+	u32 in[TCI_WORDS] = { SCI_GET, SCI_ILLUMINATION, 0, 0, 0, 0 };
+	u32 out[TCI_WORDS];
 	acpi_status status;
 
 	if (!sci_open(dev))
 		return 0;
 
-	status = hci_raw(dev, in, out);
+	status = tci_raw(dev, in, out);
 	sci_close(dev);
-	if (ACPI_FAILURE(status) || out[0] == HCI_FAILURE) {
+	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
 		pr_err("ACPI call to query Illumination support failed\n");
 		return 0;
-	} else if (out[0] == HCI_NOT_SUPPORTED || out[1] != 1) {
+	} else if (out[0] == TOS_NOT_SUPPORTED) {
 		pr_info("Illumination device not available\n");
 		return 0;
 	}
@@ -445,7 +460,6 @@ static void toshiba_illumination_set(struct led_classdev *cdev,
 	struct toshiba_acpi_dev *dev = container_of(cdev,
 			struct toshiba_acpi_dev, led_dev);
 	u32 state, result;
-	acpi_status status;
 
 	/* First request : initialize communication. */
 	if (!sci_open(dev))
@@ -453,12 +467,12 @@ static void toshiba_illumination_set(struct led_classdev *cdev,
 
 	/* Switch the illumination on/off */
 	state = brightness ? 1 : 0;
-	status = sci_write(dev, SCI_ILLUMINATION, state, &result);
+	result = sci_write(dev, SCI_ILLUMINATION, state);
 	sci_close(dev);
-	if (ACPI_FAILURE(status)) {
+	if (result == TOS_FAILURE) {
 		pr_err("ACPI call for illumination failed\n");
 		return;
-	} else if (result == HCI_NOT_SUPPORTED) {
+	} else if (result == TOS_NOT_SUPPORTED) {
 		pr_info("Illumination not supported\n");
 		return;
 	}
@@ -469,19 +483,18 @@ static enum led_brightness toshiba_illumination_get(struct led_classdev *cdev)
 	struct toshiba_acpi_dev *dev = container_of(cdev,
 			struct toshiba_acpi_dev, led_dev);
 	u32 state, result;
-	acpi_status status;
 
 	/* First request : initialize communication. */
 	if (!sci_open(dev))
 		return LED_OFF;
 
 	/* Check the illumination */
-	status = sci_read(dev, SCI_ILLUMINATION, &state, &result);
+	result = sci_read(dev, SCI_ILLUMINATION, &state);
 	sci_close(dev);
-	if (ACPI_FAILURE(status) || result == SCI_INPUT_DATA_ERROR) {
+	if (result == TOS_FAILURE || result == TOS_INPUT_DATA_ERROR) {
 		pr_err("ACPI call for illumination failed\n");
 		return LED_OFF;
-	} else if (result == HCI_NOT_SUPPORTED) {
+	} else if (result == TOS_NOT_SUPPORTED) {
 		pr_info("Illumination not supported\n");
 		return LED_OFF;
 	}
@@ -490,20 +503,55 @@ static enum led_brightness toshiba_illumination_get(struct led_classdev *cdev)
 }
 
 /* KBD Illumination */
+static int toshiba_kbd_illum_available(struct toshiba_acpi_dev *dev)
+{
+	u32 in[TCI_WORDS] = { SCI_GET, SCI_KBD_ILLUM_STATUS, 0, 0, 0, 0 };
+	u32 out[TCI_WORDS];
+	acpi_status status;
+
+	if (!sci_open(dev))
+		return 0;
+
+	status = tci_raw(dev, in, out);
+	sci_close(dev);
+	if (ACPI_FAILURE(status) || out[0] == TOS_INPUT_DATA_ERROR) {
+		pr_err("ACPI call to query kbd illumination support failed\n");
+		return 0;
+	} else if (out[0] == TOS_NOT_SUPPORTED) {
+		pr_info("Keyboard illumination not available\n");
+		return 0;
+	}
+
+	/* Check for keyboard backlight timeout max value,
+	 * previous kbd backlight implementation set this to
+	 * 0x3c0003, and now the new implementation set this
+	 * to 0x3c001a, use this to distinguish between them
+	 */
+	if (out[3] == SCI_KBD_TIME_MAX)
+		dev->kbd_type = 2;
+	else
+		dev->kbd_type = 1;
+	/* Get the current keyboard backlight mode */
+	dev->kbd_mode = out[2] & SCI_KBD_MODE_MASK;
+	/* Get the current time (1-60 seconds) */
+	dev->kbd_time = out[2] >> HCI_MISC_SHIFT;
+
+	return 1;
+}
+
 static int toshiba_kbd_illum_status_set(struct toshiba_acpi_dev *dev, u32 time)
 {
 	u32 result;
-	acpi_status status;
 
 	if (!sci_open(dev))
 		return -EIO;
 
-	status = sci_write(dev, SCI_KBD_ILLUM_STATUS, time, &result);
+	result = sci_write(dev, SCI_KBD_ILLUM_STATUS, time);
 	sci_close(dev);
-	if (ACPI_FAILURE(status) || result == SCI_INPUT_DATA_ERROR) {
+	if (result == TOS_FAILURE || result == TOS_INPUT_DATA_ERROR) {
 		pr_err("ACPI call to set KBD backlight status failed\n");
 		return -EIO;
-	} else if (result == HCI_NOT_SUPPORTED) {
+	} else if (result == TOS_NOT_SUPPORTED) {
 		pr_info("Keyboard backlight status not supported\n");
 		return -ENODEV;
 	}
@@ -514,17 +562,16 @@ static int toshiba_kbd_illum_status_set(struct toshiba_acpi_dev *dev, u32 time)
 static int toshiba_kbd_illum_status_get(struct toshiba_acpi_dev *dev, u32 *time)
 {
 	u32 result;
-	acpi_status status;
 
 	if (!sci_open(dev))
 		return -EIO;
 
-	status = sci_read(dev, SCI_KBD_ILLUM_STATUS, time, &result);
+	result = sci_read(dev, SCI_KBD_ILLUM_STATUS, time);
 	sci_close(dev);
-	if (ACPI_FAILURE(status) || result == SCI_INPUT_DATA_ERROR) {
+	if (result == TOS_FAILURE || result == TOS_INPUT_DATA_ERROR) {
 		pr_err("ACPI call to get KBD backlight status failed\n");
 		return -EIO;
-	} else if (result == HCI_NOT_SUPPORTED) {
+	} else if (result == TOS_NOT_SUPPORTED) {
 		pr_info("Keyboard backlight status not supported\n");
 		return -ENODEV;
 	}
@@ -537,14 +584,13 @@ static enum led_brightness toshiba_kbd_backlight_get(struct led_classdev *cdev)
 	struct toshiba_acpi_dev *dev = container_of(cdev,
 			struct toshiba_acpi_dev, kbd_led);
 	u32 state, result;
-	acpi_status status;
 
 	/* Check the keyboard backlight state */
-	status = hci_read1(dev, HCI_KBD_ILLUMINATION, &state, &result);
-	if (ACPI_FAILURE(status) || result == SCI_INPUT_DATA_ERROR) {
+	result = hci_read1(dev, HCI_KBD_ILLUMINATION, &state);
+	if (result == TOS_FAILURE || result == TOS_INPUT_DATA_ERROR) {
 		pr_err("ACPI call to get the keyboard backlight failed\n");
 		return LED_OFF;
-	} else if (result == HCI_NOT_SUPPORTED) {
+	} else if (result == TOS_NOT_SUPPORTED) {
 		pr_info("Keyboard backlight not supported\n");
 		return LED_OFF;
 	}
@@ -558,15 +604,14 @@ static void toshiba_kbd_backlight_set(struct led_classdev *cdev,
 	struct toshiba_acpi_dev *dev = container_of(cdev,
 			struct toshiba_acpi_dev, kbd_led);
 	u32 state, result;
-	acpi_status status;
 
 	/* Set the keyboard backlight state */
 	state = brightness ? 1 : 0;
-	status = hci_write1(dev, HCI_KBD_ILLUMINATION, state, &result);
-	if (ACPI_FAILURE(status) || result == SCI_INPUT_DATA_ERROR) {
+	result = hci_write1(dev, HCI_KBD_ILLUMINATION, state);
+	if (result == TOS_FAILURE || result == TOS_INPUT_DATA_ERROR) {
 		pr_err("ACPI call to set KBD Illumination mode failed\n");
 		return;
-	} else if (result == HCI_NOT_SUPPORTED) {
+	} else if (result == TOS_NOT_SUPPORTED) {
 		pr_info("Keyboard backlight not supported\n");
 		return;
 	}
@@ -576,17 +621,16 @@ static void toshiba_kbd_backlight_set(struct led_classdev *cdev,
 static int toshiba_touchpad_set(struct toshiba_acpi_dev *dev, u32 state)
 {
 	u32 result;
-	acpi_status status;
 
 	if (!sci_open(dev))
 		return -EIO;
 
-	status = sci_write(dev, SCI_TOUCHPAD, state, &result);
+	result = sci_write(dev, SCI_TOUCHPAD, state);
 	sci_close(dev);
-	if (ACPI_FAILURE(status)) {
+	if (result == TOS_FAILURE) {
 		pr_err("ACPI call to set the touchpad failed\n");
 		return -EIO;
-	} else if (result == HCI_NOT_SUPPORTED) {
+	} else if (result == TOS_NOT_SUPPORTED) {
 		return -ENODEV;
 	}
 
@@ -596,17 +640,16 @@ static int toshiba_touchpad_set(struct toshiba_acpi_dev *dev, u32 state)
 static int toshiba_touchpad_get(struct toshiba_acpi_dev *dev, u32 *state)
 {
 	u32 result;
-	acpi_status status;
 
 	if (!sci_open(dev))
 		return -EIO;
 
-	status = sci_read(dev, SCI_TOUCHPAD, state, &result);
+	result = sci_read(dev, SCI_TOUCHPAD, state);
 	sci_close(dev);
-	if (ACPI_FAILURE(status)) {
+	if (result == TOS_FAILURE) {
 		pr_err("ACPI call to query the touchpad failed\n");
 		return -EIO;
-	} else if (result == HCI_NOT_SUPPORTED) {
+	} else if (result == TOS_NOT_SUPPORTED) {
 		return -ENODEV;
 	}
 
@@ -617,11 +660,11 @@ static int toshiba_touchpad_get(struct toshiba_acpi_dev *dev, u32 *state)
 static int toshiba_eco_mode_available(struct toshiba_acpi_dev *dev)
 {
 	acpi_status status;
-	u32 in[HCI_WORDS] = { HCI_GET, HCI_ECO_MODE, 0, 1, 0, 0 };
-	u32 out[HCI_WORDS];
+	u32 in[TCI_WORDS] = { HCI_GET, HCI_ECO_MODE, 0, 1, 0, 0 };
+	u32 out[TCI_WORDS];
 
-	status = hci_raw(dev, in, out);
-	if (ACPI_FAILURE(status) || out[0] == SCI_INPUT_DATA_ERROR) {
+	status = tci_raw(dev, in, out);
+	if (ACPI_FAILURE(status) || out[0] == TOS_INPUT_DATA_ERROR) {
 		pr_info("ACPI call to get ECO led failed\n");
 		return 0;
 	}
@@ -633,12 +676,12 @@ static enum led_brightness toshiba_eco_mode_get_status(struct led_classdev *cdev
 {
 	struct toshiba_acpi_dev *dev = container_of(cdev,
 			struct toshiba_acpi_dev, eco_led);
-	u32 in[HCI_WORDS] = { HCI_GET, HCI_ECO_MODE, 0, 1, 0, 0 };
-	u32 out[HCI_WORDS];
+	u32 in[TCI_WORDS] = { HCI_GET, HCI_ECO_MODE, 0, 1, 0, 0 };
+	u32 out[TCI_WORDS];
 	acpi_status status;
 
-	status = hci_raw(dev, in, out);
-	if (ACPI_FAILURE(status) || out[0] == SCI_INPUT_DATA_ERROR) {
+	status = tci_raw(dev, in, out);
+	if (ACPI_FAILURE(status) || out[0] == TOS_INPUT_DATA_ERROR) {
 		pr_err("ACPI call to get ECO led failed\n");
 		return LED_OFF;
 	}
@@ -651,14 +694,14 @@ static void toshiba_eco_mode_set_status(struct led_classdev *cdev,
 {
 	struct toshiba_acpi_dev *dev = container_of(cdev,
 			struct toshiba_acpi_dev, eco_led);
-	u32 in[HCI_WORDS] = { HCI_SET, HCI_ECO_MODE, 0, 1, 0, 0 };
-	u32 out[HCI_WORDS];
+	u32 in[TCI_WORDS] = { HCI_SET, HCI_ECO_MODE, 0, 1, 0, 0 };
+	u32 out[TCI_WORDS];
 	acpi_status status;
 
 	/* Switch the Eco Mode led on/off */
 	in[2] = (brightness) ? 1 : 0;
-	status = hci_raw(dev, in, out);
-	if (ACPI_FAILURE(status) || out[0] == SCI_INPUT_DATA_ERROR) {
+	status = tci_raw(dev, in, out);
+	if (ACPI_FAILURE(status) || out[0] == TOS_INPUT_DATA_ERROR) {
 		pr_err("ACPI call to set ECO led failed\n");
 		return;
 	}
@@ -667,22 +710,22 @@ static void toshiba_eco_mode_set_status(struct led_classdev *cdev,
 /* Accelerometer support */
 static int toshiba_accelerometer_supported(struct toshiba_acpi_dev *dev)
 {
-	u32 in[HCI_WORDS] = { HCI_GET, HCI_ACCELEROMETER2, 0, 0, 0, 0 };
-	u32 out[HCI_WORDS];
+	u32 in[TCI_WORDS] = { HCI_GET, HCI_ACCELEROMETER2, 0, 0, 0, 0 };
+	u32 out[TCI_WORDS];
 	acpi_status status;
 
 	/* Check if the accelerometer call exists,
 	 * this call also serves as initialization
 	 */
-	status = hci_raw(dev, in, out);
-	if (ACPI_FAILURE(status) || out[0] == SCI_INPUT_DATA_ERROR) {
+	status = tci_raw(dev, in, out);
+	if (ACPI_FAILURE(status) || out[0] == TOS_INPUT_DATA_ERROR) {
 		pr_err("ACPI call to query the accelerometer failed\n");
 		return -EIO;
-	} else if (out[0] == HCI_DATA_NOT_AVAILABLE ||
-		   out[0] == HCI_NOT_INITIALIZED) {
+	} else if (out[0] == TOS_DATA_NOT_AVAILABLE ||
+		   out[0] == TOS_NOT_INITIALIZED) {
 		pr_err("Accelerometer not initialized\n");
 		return -EIO;
-	} else if (out[0] == HCI_NOT_SUPPORTED) {
+	} else if (out[0] == TOS_NOT_SUPPORTED) {
 		pr_info("Accelerometer not supported\n");
 		return -ENODEV;
 	}
@@ -693,13 +736,13 @@ static int toshiba_accelerometer_supported(struct toshiba_acpi_dev *dev)
 static int toshiba_accelerometer_get(struct toshiba_acpi_dev *dev,
 				      u32 *xy, u32 *z)
 {
-	u32 in[HCI_WORDS] = { HCI_GET, HCI_ACCELEROMETER, 0, 1, 0, 0 };
-	u32 out[HCI_WORDS];
+	u32 in[TCI_WORDS] = { HCI_GET, HCI_ACCELEROMETER, 0, 1, 0, 0 };
+	u32 out[TCI_WORDS];
 	acpi_status status;
 
 	/* Check the Accelerometer status */
-	status = hci_raw(dev, in, out);
-	if (ACPI_FAILURE(status) || out[0] == SCI_INPUT_DATA_ERROR) {
+	status = tci_raw(dev, in, out);
+	if (ACPI_FAILURE(status) || out[0] == TOS_INPUT_DATA_ERROR) {
 		pr_err("ACPI call to query the accelerometer failed\n");
 		return -EIO;
 	}
@@ -719,8 +762,8 @@ static u32 hci_get_bt_present(struct toshiba_acpi_dev *dev, bool *present)
 
 	value = 0;
 	value2 = 0;
-	hci_read2(dev, HCI_WIRELESS, &value, &value2, &hci_result);
-	if (hci_result == HCI_SUCCESS)
+	hci_result = hci_read2(dev, HCI_WIRELESS, &value, &value2);
+	if (hci_result == TOS_SUCCESS)
 		*present = (value & HCI_WIRELESS_BT_PRESENT) ? true : false;
 
 	return hci_result;
@@ -733,7 +776,7 @@ static u32 hci_get_radio_state(struct toshiba_acpi_dev *dev, bool *radio_state)
 
 	value = 0;
 	value2 = 0x0001;
-	hci_read2(dev, HCI_WIRELESS, &value, &value2, &hci_result);
+	hci_result = hci_read2(dev, HCI_WIRELESS, &value, &value2);
 
 	*radio_state = value & HCI_WIRELESS_KILL_SWITCH;
 	return hci_result;
@@ -750,7 +793,7 @@ static int bt_rfkill_set_block(void *data, bool blocked)
 	value = (blocked == false);
 
 	mutex_lock(&dev->mutex);
-	if (hci_get_radio_state(dev, &radio_state) != HCI_SUCCESS) {
+	if (hci_get_radio_state(dev, &radio_state) != TOS_SUCCESS) {
 		err = -EIO;
 		goto out;
 	}
@@ -760,10 +803,10 @@ static int bt_rfkill_set_block(void *data, bool blocked)
 		goto out;
 	}
 
-	hci_write2(dev, HCI_WIRELESS, value, HCI_WIRELESS_BT_POWER, &result1);
-	hci_write2(dev, HCI_WIRELESS, value, HCI_WIRELESS_BT_ATTACH, &result2);
+	result1 = hci_write2(dev, HCI_WIRELESS, value, HCI_WIRELESS_BT_POWER);
+	result2 = hci_write2(dev, HCI_WIRELESS, value, HCI_WIRELESS_BT_ATTACH);
 
-	if (result1 != HCI_SUCCESS || result2 != HCI_SUCCESS)
+	if (result1 != TOS_SUCCESS || result2 != TOS_SUCCESS)
 		err = -EIO;
 	else
 		err = 0;
@@ -782,7 +825,7 @@ static void bt_rfkill_poll(struct rfkill *rfkill, void *data)
 	mutex_lock(&dev->mutex);
 
 	hci_result = hci_get_radio_state(dev, &value);
-	if (hci_result != HCI_SUCCESS) {
+	if (hci_result != TOS_SUCCESS) {
 		/* Can't do anything useful */
 		mutex_unlock(&dev->mutex);
 		return;
@@ -806,9 +849,9 @@ static int get_tr_backlight_status(struct toshiba_acpi_dev *dev, bool *enabled)
 	u32 hci_result;
 	u32 status;
 
-	hci_read1(dev, HCI_TR_BACKLIGHT, &status, &hci_result);
+	hci_result = hci_read1(dev, HCI_TR_BACKLIGHT, &status);
 	*enabled = !status;
-	return hci_result == HCI_SUCCESS ? 0 : -EIO;
+	return hci_result == TOS_SUCCESS ? 0 : -EIO;
 }
 
 static int set_tr_backlight_status(struct toshiba_acpi_dev *dev, bool enable)
@@ -816,8 +859,8 @@ static int set_tr_backlight_status(struct toshiba_acpi_dev *dev, bool enable)
 	u32 hci_result;
 	u32 value = !enable;
 
-	hci_write1(dev, HCI_TR_BACKLIGHT, value, &hci_result);
-	return hci_result == HCI_SUCCESS ? 0 : -EIO;
+	hci_result = hci_write1(dev, HCI_TR_BACKLIGHT, value);
+	return hci_result == TOS_SUCCESS ? 0 : -EIO;
 }
 
 static struct proc_dir_entry *toshiba_proc_dir /*= 0*/ ;
@@ -838,8 +881,8 @@ static int __get_lcd_brightness(struct toshiba_acpi_dev *dev)
 		brightness++;
 	}
 
-	hci_read1(dev, HCI_LCD_BRIGHTNESS, &value, &hci_result);
-	if (hci_result == HCI_SUCCESS)
+	hci_result = hci_read1(dev, HCI_LCD_BRIGHTNESS, &value);
+	if (hci_result == TOS_SUCCESS)
 		return brightness + (value >> HCI_LCD_BRIGHTNESS_SHIFT);
 
 	return -EIO;
@@ -879,8 +922,8 @@ static int lcd_proc_open(struct inode *inode, struct file *file)
 
 static int set_lcd_brightness(struct toshiba_acpi_dev *dev, int value)
 {
-	u32 in[HCI_WORDS] = { HCI_SET, HCI_LCD_BRIGHTNESS, 0, 0, 0, 0 };
-	u32 out[HCI_WORDS];
+	u32 in[TCI_WORDS] = { HCI_SET, HCI_LCD_BRIGHTNESS, 0, 0, 0, 0 };
+	u32 out[TCI_WORDS];
 	acpi_status status;
 
 	if (dev->tr_backlight_supported) {
@@ -893,19 +936,19 @@ static int set_lcd_brightness(struct toshiba_acpi_dev *dev, int value)
 	}
 
 	in[2] = value << HCI_LCD_BRIGHTNESS_SHIFT;
-	status = hci_raw(dev, in, out);
-	if (ACPI_FAILURE(status) || out[0] == HCI_FAILURE) {
+	status = tci_raw(dev, in, out);
+	if (ACPI_FAILURE(status) || out[0] == TOS_FAILURE) {
 		pr_err("ACPI call to set brightness failed");
 		return -EIO;
 	}
 	/* Extra check for "incomplete" backlight method, where the AML code
-	 * doesn't check for HCI_SET or HCI_GET and returns HCI_SUCCESS,
+	 * doesn't check for HCI_SET or HCI_GET and returns TOS_SUCCESS,
 	 * the actual brightness, and in some cases the max brightness.
 	 */
 	if (out[2] > 0  || out[3] == 0xE000)
 		return -ENODEV;
 
-	return out[0] == HCI_SUCCESS ? 0 : -EIO;
+	return out[0] == TOS_SUCCESS ? 0 : -EIO;
 }
 
 static int set_lcd_status(struct backlight_device *bd)
@@ -953,8 +996,8 @@ static int get_video_status(struct toshiba_acpi_dev *dev, u32 *status)
 {
 	u32 hci_result;
 
-	hci_read1(dev, HCI_VIDEO_OUT, status, &hci_result);
-	return hci_result == HCI_SUCCESS ? 0 : -EIO;
+	hci_result = hci_read1(dev, HCI_VIDEO_OUT, status);
+	return hci_result == TOS_SUCCESS ? 0 : -EIO;
 }
 
 static int video_proc_show(struct seq_file *m, void *v)
@@ -1057,8 +1100,8 @@ static int get_fan_status(struct toshiba_acpi_dev *dev, u32 *status)
 {
 	u32 hci_result;
 
-	hci_read1(dev, HCI_FAN, status, &hci_result);
-	return hci_result == HCI_SUCCESS ? 0 : -EIO;
+	hci_result = hci_read1(dev, HCI_FAN, status);
+	return hci_result == TOS_SUCCESS ? 0 : -EIO;
 }
 
 static int fan_proc_show(struct seq_file *m, void *v)
@@ -1097,8 +1140,8 @@ static ssize_t fan_proc_write(struct file *file, const char __user *buf,
 
 	if (sscanf(cmd, " force_on : %i", &value) == 1 &&
 	    value >= 0 && value <= 1) {
-		hci_write1(dev, HCI_FAN, value, &hci_result);
-		if (hci_result != HCI_SUCCESS)
+		hci_result = hci_write1(dev, HCI_FAN, value);
+		if (hci_result != TOS_SUCCESS)
 			return -EIO;
 		else
 			dev->force_fan = value;
@@ -1125,17 +1168,17 @@ static int keys_proc_show(struct seq_file *m, void *v)
 	u32 value;
 
 	if (!dev->key_event_valid && dev->system_event_supported) {
-		hci_read1(dev, HCI_SYSTEM_EVENT, &value, &hci_result);
-		if (hci_result == HCI_SUCCESS) {
+		hci_result = hci_read1(dev, HCI_SYSTEM_EVENT, &value);
+		if (hci_result == TOS_SUCCESS) {
 			dev->key_event_valid = 1;
 			dev->last_key_event = value;
-		} else if (hci_result == HCI_EMPTY) {
+		} else if (hci_result == TOS_FIFO_EMPTY) {
 			/* better luck next time */
-		} else if (hci_result == HCI_NOT_SUPPORTED) {
+		} else if (hci_result == TOS_NOT_SUPPORTED) {
 			/* This is a workaround for an unresolved issue on
 			 * some machines where system events sporadically
 			 * become disabled. */
-			hci_write1(dev, HCI_SYSTEM_EVENT, 1, &hci_result);
+			hci_result = hci_write1(dev, HCI_SYSTEM_EVENT, 1);
 			pr_notice("Re-enabled hotkeys\n");
 		} else {
 			pr_err("Error reading hotkey status\n");
@@ -1249,6 +1292,62 @@ static const struct backlight_ops toshiba_backlight_data = {
 /*
  * Sysfs files
  */
+static ssize_t toshiba_kbd_bl_mode_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t count);
+static ssize_t toshiba_kbd_bl_mode_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf);
+static ssize_t toshiba_kbd_type_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf);
+static ssize_t toshiba_available_kbd_modes_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf);
+static ssize_t toshiba_kbd_bl_timeout_store(struct device *dev,
+					    struct device_attribute *attr,
+					    const char *buf, size_t count);
+static ssize_t toshiba_kbd_bl_timeout_show(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf);
+static ssize_t toshiba_touchpad_store(struct device *dev,
+				      struct device_attribute *attr,
+				      const char *buf, size_t count);
+static ssize_t toshiba_touchpad_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf);
+static ssize_t toshiba_position_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf);
+
+static DEVICE_ATTR(kbd_backlight_mode, S_IRUGO | S_IWUSR,
+		   toshiba_kbd_bl_mode_show, toshiba_kbd_bl_mode_store);
+static DEVICE_ATTR(kbd_type, S_IRUGO, toshiba_kbd_type_show, NULL);
+static DEVICE_ATTR(available_kbd_modes, S_IRUGO,
+		   toshiba_available_kbd_modes_show, NULL);
+static DEVICE_ATTR(kbd_backlight_timeout, S_IRUGO | S_IWUSR,
+		   toshiba_kbd_bl_timeout_show, toshiba_kbd_bl_timeout_store);
+static DEVICE_ATTR(touchpad, S_IRUGO | S_IWUSR,
+		   toshiba_touchpad_show, toshiba_touchpad_store);
+static DEVICE_ATTR(position, S_IRUGO, toshiba_position_show, NULL);
+
+static struct attribute *toshiba_attributes[] = {
+	&dev_attr_kbd_backlight_mode.attr,
+	&dev_attr_kbd_type.attr,
+	&dev_attr_available_kbd_modes.attr,
+	&dev_attr_kbd_backlight_timeout.attr,
+	&dev_attr_touchpad.attr,
+	&dev_attr_position.attr,
+	NULL,
+};
+
+static umode_t toshiba_sysfs_is_visible(struct kobject *,
+					struct attribute *, int);
+
+static struct attribute_group toshiba_attr_group = {
+	.is_visible = toshiba_sysfs_is_visible,
+	.attrs = toshiba_attributes,
+};
 
 static ssize_t toshiba_kbd_bl_mode_store(struct device *dev,
 					 struct device_attribute *attr,
@@ -1263,20 +1362,50 @@ static ssize_t toshiba_kbd_bl_mode_store(struct device *dev,
 	ret = kstrtoint(buf, 0, &mode);
 	if (ret)
 		return ret;
-	if (mode != SCI_KBD_MODE_FNZ && mode != SCI_KBD_MODE_AUTO)
-		return -EINVAL;
+
+	/* Check for supported modes depending on keyboard backlight type */
+	if (toshiba->kbd_type == 1) {
+		/* Type 1 supports SCI_KBD_MODE_FNZ and SCI_KBD_MODE_AUTO */
+		if (mode != SCI_KBD_MODE_FNZ && mode != SCI_KBD_MODE_AUTO)
+			return -EINVAL;
+	} else if (toshiba->kbd_type == 2) {
+		/* Type 2 doesn't support SCI_KBD_MODE_FNZ */
+		if (mode != SCI_KBD_MODE_AUTO && mode != SCI_KBD_MODE_ON &&
+		    mode != SCI_KBD_MODE_OFF)
+			return -EINVAL;
+	}
 
 	/* Set the Keyboard Backlight Mode where:
-	 * Mode - Auto (2) | FN-Z (1)
 	 *	Auto - KBD backlight turns off automatically in given time
 	 *	FN-Z - KBD backlight "toggles" when hotkey pressed
+	 *	ON   - KBD backlight is always on
+	 *	OFF  - KBD backlight is always off
 	 */
+
+	/* Only make a change if the actual mode has changed */
 	if (toshiba->kbd_mode != mode) {
+		/* Shift the time to "base time" (0x3c0000 == 60 seconds) */
 		time = toshiba->kbd_time << HCI_MISC_SHIFT;
-		time = time + toshiba->kbd_mode;
+
+		/* OR the "base time" to the actual method format */
+		if (toshiba->kbd_type == 1) {
+			/* Type 1 requires the current mode */
+			time |= toshiba->kbd_mode;
+		} else if (toshiba->kbd_type == 2) {
+			/* Type 2 requires the desired mode */
+			time |= mode;
+		}
+
 		ret = toshiba_kbd_illum_status_set(toshiba, time);
 		if (ret)
 			return ret;
+
+		/* Update sysfs entries on successful mode change*/
+		ret = sysfs_update_group(&toshiba->acpi_dev->dev.kobj,
+					 &toshiba_attr_group);
+		if (ret)
+			return ret;
+
 		toshiba->kbd_mode = mode;
 	}
 
@@ -1293,7 +1422,30 @@ static ssize_t toshiba_kbd_bl_mode_show(struct device *dev,
 	if (toshiba_kbd_illum_status_get(toshiba, &time) < 0)
 		return -EIO;
 
-	return sprintf(buf, "%i\n", time & 0x07);
+	return sprintf(buf, "%i\n", time & SCI_KBD_MODE_MASK);
+}
+
+static ssize_t toshiba_kbd_type_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct toshiba_acpi_dev *toshiba = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", toshiba->kbd_type);
+}
+
+static ssize_t toshiba_available_kbd_modes_show(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
+{
+	struct toshiba_acpi_dev *toshiba = dev_get_drvdata(dev);
+
+	if (toshiba->kbd_type == 1)
+		return sprintf(buf, "%x %x\n",
+			       SCI_KBD_MODE_FNZ, SCI_KBD_MODE_AUTO);
+
+	return sprintf(buf, "%x %x %x\n",
+		       SCI_KBD_MODE_AUTO, SCI_KBD_MODE_ON, SCI_KBD_MODE_OFF);
 }
 
 static ssize_t toshiba_kbd_bl_timeout_store(struct device *dev,
@@ -1301,18 +1453,38 @@ static ssize_t toshiba_kbd_bl_timeout_store(struct device *dev,
 					    const char *buf, size_t count)
 {
 	struct toshiba_acpi_dev *toshiba = dev_get_drvdata(dev);
-	int time = -1;
+	int time;
+	int ret;
 
-	if (sscanf(buf, "%i", &time) != 1 && (time < 0 || time > 60))
-		return -EINVAL;
+	ret = kstrtoint(buf, 0, &time);
+	if (ret)
+		return ret;
 
-	/* Set the Keyboard Backlight Timeout: 0-60 seconds */
-	if (time != -1 && toshiba->kbd_time != time) {
+	/* Check for supported values depending on kbd_type */
+	if (toshiba->kbd_type == 1) {
+		if (time < 0 || time > 60)
+			return -EINVAL;
+	} else if (toshiba->kbd_type == 2) {
+		if (time < 1 || time > 60)
+			return -EINVAL;
+	}
+
+	/* Set the Keyboard Backlight Timeout */
+
+	/* Only make a change if the actual timeout has changed */
+	if (toshiba->kbd_time != time) {
+		/* Shift the time to "base time" (0x3c0000 == 60 seconds) */
 		time = time << HCI_MISC_SHIFT;
-		time = (toshiba->kbd_mode == SCI_KBD_MODE_AUTO) ?
-							time + 1 : time + 2;
-		if (toshiba_kbd_illum_status_set(toshiba, time) < 0)
-			return -EIO;
+		/* OR the "base time" to the actual method format */
+		if (toshiba->kbd_type == 1)
+			time |= SCI_KBD_MODE_FNZ;
+		else if (toshiba->kbd_type == 2)
+			time |= SCI_KBD_MODE_AUTO;
+
+		ret = toshiba_kbd_illum_status_set(toshiba, time);
+		if (ret)
+			return ret;
+
 		toshiba->kbd_time = time >> HCI_MISC_SHIFT;
 	}
 
@@ -1338,12 +1510,18 @@ static ssize_t toshiba_touchpad_store(struct device *dev,
 {
 	struct toshiba_acpi_dev *toshiba = dev_get_drvdata(dev);
 	int state;
+	int ret;
 
 	/* Set the TouchPad on/off, 0 - Disable | 1 - Enable */
-	if (sscanf(buf, "%i", &state) == 1 && (state == 0 || state == 1)) {
-		if (toshiba_touchpad_set(toshiba, state) < 0)
-			return -EIO;
-	}
+	ret = kstrtoint(buf, 0, &state);
+	if (ret)
+		return ret;
+	if (state != 0 && state != 1)
+		return -EINVAL;
+
+	ret = toshiba_touchpad_set(toshiba, state);
+	if (ret)
+		return ret;
 
 	return count;
 }
@@ -1383,22 +1561,6 @@ static ssize_t toshiba_position_show(struct device *dev,
 	return sprintf(buf, "%d %d %d\n", x, y, z);
 }
 
-static DEVICE_ATTR(kbd_backlight_mode, S_IRUGO | S_IWUSR,
-		   toshiba_kbd_bl_mode_show, toshiba_kbd_bl_mode_store);
-static DEVICE_ATTR(kbd_backlight_timeout, S_IRUGO | S_IWUSR,
-		   toshiba_kbd_bl_timeout_show, toshiba_kbd_bl_timeout_store);
-static DEVICE_ATTR(touchpad, S_IRUGO | S_IWUSR,
-		   toshiba_touchpad_show, toshiba_touchpad_store);
-static DEVICE_ATTR(position, S_IRUGO, toshiba_position_show, NULL);
-
-static struct attribute *toshiba_attributes[] = {
-	&dev_attr_kbd_backlight_mode.attr,
-	&dev_attr_kbd_backlight_timeout.attr,
-	&dev_attr_touchpad.attr,
-	&dev_attr_position.attr,
-	NULL,
-};
-
 static umode_t toshiba_sysfs_is_visible(struct kobject *kobj,
 					struct attribute *attr, int idx)
 {
@@ -1418,11 +1580,6 @@ static umode_t toshiba_sysfs_is_visible(struct kobject *kobj,
 	return exists ? attr->mode : 0;
 }
 
-static struct attribute_group toshiba_attr_group = {
-	.is_visible = toshiba_sysfs_is_visible,
-	.attrs = toshiba_attributes,
-};
-
 static bool toshiba_acpi_i8042_filter(unsigned char data, unsigned char str,
 				      struct serio *port)
 {
@@ -1535,8 +1692,8 @@ static int toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev)
 	if (acpi_has_method(dev->acpi_dev->handle, "INFO"))
 		dev->info_supported = 1;
 	else {
-		hci_write1(dev, HCI_SYSTEM_EVENT, 1, &hci_result);
-		if (hci_result == HCI_SUCCESS)
+		hci_result = hci_write1(dev, HCI_SYSTEM_EVENT, 1);
+		if (hci_result == TOS_SUCCESS)
 			dev->system_event_supported = 1;
 	}
 
@@ -1558,7 +1715,7 @@ static int toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev)
 		goto err_remove_filter;
 	}
 
-	hci_write1(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_ENABLE, &hci_result);
+	hci_result = hci_write1(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_ENABLE);
 	return 0;
 
  err_remove_filter:
@@ -1716,7 +1873,7 @@ static int toshiba_acpi_add(struct acpi_device *acpi_dev)
 		goto error;
 
 	/* Register rfkill switch for Bluetooth */
-	if (hci_get_bt_present(dev, &bt_present) == HCI_SUCCESS && bt_present) {
+	if (hci_get_bt_present(dev, &bt_present) == TOS_SUCCESS && bt_present) {
 		dev->bt_rfk = rfkill_alloc("Toshiba Bluetooth",
 					   &acpi_dev->dev,
 					   RFKILL_TYPE_BLUETOOTH,
@@ -1754,12 +1911,7 @@ static int toshiba_acpi_add(struct acpi_device *acpi_dev)
 			dev->eco_supported = 1;
 	}
 
-	ret = toshiba_kbd_illum_status_get(dev, &dummy);
-	if (!ret) {
-		dev->kbd_time = dummy >> HCI_MISC_SHIFT;
-		dev->kbd_mode = dummy & 0x07;
-	}
-	dev->kbd_illum_supported = !ret;
+	dev->kbd_illum_supported = toshiba_kbd_illum_available(dev);
 	/*
 	 * Only register the LED if KBD illumination is supported
 	 * and the keyboard backlight operation mode is set to FN-Z
@@ -1824,26 +1976,26 @@ static void toshiba_acpi_notify(struct acpi_device *acpi_dev, u32 event)
 			toshiba_acpi_report_hotkey(dev, scancode);
 	} else if (dev->system_event_supported) {
 		do {
-			hci_read1(dev, HCI_SYSTEM_EVENT, &value, &hci_result);
+			hci_result = hci_read1(dev, HCI_SYSTEM_EVENT, &value);
 			switch (hci_result) {
-			case HCI_SUCCESS:
+			case TOS_SUCCESS:
 				toshiba_acpi_report_hotkey(dev, (int)value);
 				break;
-			case HCI_NOT_SUPPORTED:
+			case TOS_NOT_SUPPORTED:
 				/*
 				 * This is a workaround for an unresolved
 				 * issue on some machines where system events
 				 * sporadically become disabled.
 				 */
-				hci_write1(dev, HCI_SYSTEM_EVENT, 1,
-					   &hci_result);
+				hci_result =
+					hci_write1(dev, HCI_SYSTEM_EVENT, 1);
 				pr_notice("Re-enabled hotkeys\n");
 				/* fall through */
 			default:
 				retries--;
 				break;
 			}
-		} while (retries && hci_result != HCI_EMPTY);
+		} while (retries && hci_result != TOS_FIFO_EMPTY);
 	}
 }
 
@@ -1854,7 +2006,7 @@ static int toshiba_acpi_suspend(struct device *device)
 	u32 result;
 
 	if (dev->hotkey_dev)
-		hci_write1(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_DISABLE, &result);
+		result = hci_write1(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_DISABLE);
 
 	return 0;
 }
@@ -1871,7 +2023,7 @@ static int toshiba_acpi_resume(struct device *device)
 		if (ACPI_FAILURE(status))
 			pr_info("Unable to re-enable hotkeys\n");
 
-		hci_write1(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_ENABLE, &result);
+		result = hci_write1(dev, HCI_HOTKEY_EVENT, HCI_HOTKEY_ENABLE);
 	}
 
 	return 0;
diff --git a/drivers/pnp/interface.c b/drivers/pnp/interface.c
index e6c403be09a9..4b6808ff0e5d 100644
--- a/drivers/pnp/interface.c
+++ b/drivers/pnp/interface.c
@@ -346,41 +346,41 @@ static ssize_t resources_store(struct device *dmdev,
 	}
 
 	buf = skip_spaces(buf);
-	if (!strnicmp(buf, "disable", 7)) {
+	if (!strncasecmp(buf, "disable", 7)) {
 		retval = pnp_disable_dev(dev);
 		goto done;
 	}
-	if (!strnicmp(buf, "activate", 8)) {
+	if (!strncasecmp(buf, "activate", 8)) {
 		retval = pnp_activate_dev(dev);
 		goto done;
 	}
-	if (!strnicmp(buf, "fill", 4)) {
+	if (!strncasecmp(buf, "fill", 4)) {
 		if (dev->active)
 			goto done;
 		retval = pnp_auto_config_dev(dev);
 		goto done;
 	}
-	if (!strnicmp(buf, "auto", 4)) {
+	if (!strncasecmp(buf, "auto", 4)) {
 		if (dev->active)
 			goto done;
 		pnp_init_resources(dev);
 		retval = pnp_auto_config_dev(dev);
 		goto done;
 	}
-	if (!strnicmp(buf, "clear", 5)) {
+	if (!strncasecmp(buf, "clear", 5)) {
 		if (dev->active)
 			goto done;
 		pnp_init_resources(dev);
 		goto done;
 	}
-	if (!strnicmp(buf, "get", 3)) {
+	if (!strncasecmp(buf, "get", 3)) {
 		mutex_lock(&pnp_res_mutex);
 		if (pnp_can_read(dev))
 			dev->protocol->get(dev);
 		mutex_unlock(&pnp_res_mutex);
 		goto done;
 	}
-	if (!strnicmp(buf, "set", 3)) {
+	if (!strncasecmp(buf, "set", 3)) {
 		resource_size_t start;
 		resource_size_t end;
 		unsigned long flags;
@@ -392,31 +392,31 @@ static ssize_t resources_store(struct device *dmdev,
 		mutex_lock(&pnp_res_mutex);
 		while (1) {
 			buf = skip_spaces(buf);
-			if (!strnicmp(buf, "io", 2)) {
+			if (!strncasecmp(buf, "io", 2)) {
 				buf = pnp_get_resource_value(buf + 2,
 							     IORESOURCE_IO,
 							     &start, &end,
 							     &flags);
 				pnp_add_io_resource(dev, start, end, flags);
-			} else if (!strnicmp(buf, "mem", 3)) {
+			} else if (!strncasecmp(buf, "mem", 3)) {
 				buf = pnp_get_resource_value(buf + 3,
 							     IORESOURCE_MEM,
 							     &start, &end,
 							     &flags);
 				pnp_add_mem_resource(dev, start, end, flags);
-			} else if (!strnicmp(buf, "irq", 3)) {
+			} else if (!strncasecmp(buf, "irq", 3)) {
 				buf = pnp_get_resource_value(buf + 3,
 							     IORESOURCE_IRQ,
 							     &start, NULL,
 							     &flags);
 				pnp_add_irq_resource(dev, start, flags);
-			} else if (!strnicmp(buf, "dma", 3)) {
+			} else if (!strncasecmp(buf, "dma", 3)) {
 				buf = pnp_get_resource_value(buf + 3,
 							     IORESOURCE_DMA,
 							     &start, NULL,
 							     &flags);
 				pnp_add_dma_resource(dev, start, flags);
-			} else if (!strnicmp(buf, "bus", 3)) {
+			} else if (!strncasecmp(buf, "bus", 3)) {
 				buf = pnp_get_resource_value(buf + 3,
 							     IORESOURCE_BUS,
 							     &start, &end,
diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index 73cfcdf28a36..0108c2af005b 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -325,11 +325,12 @@ config CHARGER_MANAGER
           with help of suspend_again support.
 
 config CHARGER_MAX14577
-	tristate "Maxim MAX14577 MUIC battery charger driver"
+	tristate "Maxim MAX14577/77836 battery charger driver"
 	depends on MFD_MAX14577
+	depends on SYSFS
 	help
 	  Say Y to enable support for the battery charger control sysfs and
-	  platform data of MAX14577 MUICs.
+	  platform data of MAX14577/77836 MUICs.
 
 config CHARGER_MAX8997
 	tristate "Maxim MAX8997/MAX8966 PMIC battery charger driver"
diff --git a/drivers/power/ab8500_fg.c b/drivers/power/ab8500_fg.c
index 3cb4178e397c..217da4b2ca86 100644
--- a/drivers/power/ab8500_fg.c
+++ b/drivers/power/ab8500_fg.c
@@ -2969,7 +2969,7 @@ static struct device_attribute ab8505_fg_sysfs_psy_attrs[] = {
 
 static int ab8500_fg_sysfs_psy_create_attrs(struct device *dev)
 {
-	unsigned int i, j;
+	unsigned int i;
 	struct power_supply *psy = dev_get_drvdata(dev);
 	struct ab8500_fg *di;
 
@@ -2978,14 +2978,15 @@ static int ab8500_fg_sysfs_psy_create_attrs(struct device *dev)
 	if (((is_ab8505(di->parent) || is_ab9540(di->parent)) &&
 	     abx500_get_chip_id(dev->parent) >= AB8500_CUT2P0)
 	    || is_ab8540(di->parent)) {
-		for (j = 0; j < ARRAY_SIZE(ab8505_fg_sysfs_psy_attrs); j++)
-			if (device_create_file(dev, &ab8505_fg_sysfs_psy_attrs[j]))
+		for (i = 0; i < ARRAY_SIZE(ab8505_fg_sysfs_psy_attrs); i++)
+			if (device_create_file(dev,
+					       &ab8505_fg_sysfs_psy_attrs[i]))
 				goto sysfs_psy_create_attrs_failed_ab8505;
 	}
 	return 0;
 sysfs_psy_create_attrs_failed_ab8505:
 	dev_err(dev, "Failed creating sysfs psy attrs for ab8505.\n");
-	while (j--)
+	while (i--)
 		device_remove_file(dev, &ab8505_fg_sysfs_psy_attrs[i]);
 
 	return -EIO;
diff --git a/drivers/power/avs/Kconfig b/drivers/power/avs/Kconfig
index 2a1008b61121..7f3d389bd601 100644
--- a/drivers/power/avs/Kconfig
+++ b/drivers/power/avs/Kconfig
@@ -10,3 +10,11 @@ menuconfig POWER_AVS
 	  AVS is also called SmartReflex on OMAP devices.
 
 	  Say Y here to enable Adaptive Voltage Scaling class support.
+
+config ROCKCHIP_IODOMAIN
+        tristate "Rockchip IO domain support"
+        depends on ARCH_ROCKCHIP && OF
+        help
+          Say y here to enable support io domains on Rockchip SoCs. It is
+          necessary for the io domain setting of the SoC to match the
+          voltage supplied by the regulators.
diff --git a/drivers/power/avs/Makefile b/drivers/power/avs/Makefile
index 0843386a6c19..ba4c7bc69225 100644
--- a/drivers/power/avs/Makefile
+++ b/drivers/power/avs/Makefile
@@ -1 +1,2 @@
 obj-$(CONFIG_POWER_AVS_OMAP)		+= smartreflex.o
+obj-$(CONFIG_ROCKCHIP_IODOMAIN)		+= rockchip-io-domain.o
diff --git a/drivers/power/avs/rockchip-io-domain.c b/drivers/power/avs/rockchip-io-domain.c
new file mode 100644
index 000000000000..3ae35d0590d2
--- /dev/null
+++ b/drivers/power/avs/rockchip-io-domain.c
@@ -0,0 +1,351 @@
+/*
+ * Rockchip IO Voltage Domain driver
+ *
+ * Copyright 2014 MundoReader S.L.
+ * Copyright 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+
+#define MAX_SUPPLIES		16
+
+/*
+ * The max voltage for 1.8V and 3.3V come from the Rockchip datasheet under
+ * "Recommended Operating Conditions" for "Digital GPIO".   When the typical
+ * is 3.3V the max is 3.6V.  When the typical is 1.8V the max is 1.98V.
+ *
+ * They are used like this:
+ * - If the voltage on a rail is above the "1.8" voltage (1.98V) we'll tell the
+ *   SoC we're at 3.3.
+ * - If the voltage on a rail is above the "3.3" voltage (3.6V) we'll consider
+ *   that to be an error.
+ */
+#define MAX_VOLTAGE_1_8		1980000
+#define MAX_VOLTAGE_3_3		3600000
+
+#define RK3288_SOC_CON2			0x24c
+#define RK3288_SOC_CON2_FLASH0		BIT(7)
+#define RK3288_SOC_FLASH_SUPPLY_NUM	2
+
+struct rockchip_iodomain;
+
+/**
+ * @supplies: voltage settings matching the register bits.
+ */
+struct rockchip_iodomain_soc_data {
+	int grf_offset;
+	const char *supply_names[MAX_SUPPLIES];
+	void (*init)(struct rockchip_iodomain *iod);
+};
+
+struct rockchip_iodomain_supply {
+	struct rockchip_iodomain *iod;
+	struct regulator *reg;
+	struct notifier_block nb;
+	int idx;
+};
+
+struct rockchip_iodomain {
+	struct device *dev;
+	struct regmap *grf;
+	struct rockchip_iodomain_soc_data *soc_data;
+	struct rockchip_iodomain_supply supplies[MAX_SUPPLIES];
+};
+
+static int rockchip_iodomain_write(struct rockchip_iodomain_supply *supply,
+				   int uV)
+{
+	struct rockchip_iodomain *iod = supply->iod;
+	u32 val;
+	int ret;
+
+	/* set value bit */
+	val = (uV > MAX_VOLTAGE_1_8) ? 0 : 1;
+	val <<= supply->idx;
+
+	/* apply hiword-mask */
+	val |= (BIT(supply->idx) << 16);
+
+	ret = regmap_write(iod->grf, iod->soc_data->grf_offset, val);
+	if (ret)
+		dev_err(iod->dev, "Couldn't write to GRF\n");
+
+	return ret;
+}
+
+static int rockchip_iodomain_notify(struct notifier_block *nb,
+				    unsigned long event,
+				    void *data)
+{
+	struct rockchip_iodomain_supply *supply =
+			container_of(nb, struct rockchip_iodomain_supply, nb);
+	int uV;
+	int ret;
+
+	/*
+	 * According to Rockchip it's important to keep the SoC IO domain
+	 * higher than (or equal to) the external voltage.  That means we need
+	 * to change it before external voltage changes happen in the case
+	 * of an increase.
+	 *
+	 * Note that in the "pre" change we pick the max possible voltage that
+	 * the regulator might end up at (the client requests a range and we
+	 * don't know for certain the exact voltage).  Right now we rely on the
+	 * slop in MAX_VOLTAGE_1_8 and MAX_VOLTAGE_3_3 to save us if clients
+	 * request something like a max of 3.6V when they really want 3.3V.
+	 * We could attempt to come up with better rules if this fails.
+	 */
+	if (event & REGULATOR_EVENT_PRE_VOLTAGE_CHANGE) {
+		struct pre_voltage_change_data *pvc_data = data;
+
+		uV = max_t(unsigned long, pvc_data->old_uV, pvc_data->max_uV);
+	} else if (event & (REGULATOR_EVENT_VOLTAGE_CHANGE |
+			    REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE)) {
+		uV = (unsigned long)data;
+	} else {
+		return NOTIFY_OK;
+	}
+
+	dev_dbg(supply->iod->dev, "Setting to %d\n", uV);
+
+	if (uV > MAX_VOLTAGE_3_3) {
+		dev_err(supply->iod->dev, "Voltage too high: %d\n", uV);
+
+		if (event == REGULATOR_EVENT_PRE_VOLTAGE_CHANGE)
+			return NOTIFY_BAD;
+	}
+
+	ret = rockchip_iodomain_write(supply, uV);
+	if (ret && event == REGULATOR_EVENT_PRE_VOLTAGE_CHANGE)
+		return NOTIFY_BAD;
+
+	dev_info(supply->iod->dev, "Setting to %d done\n", uV);
+	return NOTIFY_OK;
+}
+
+static void rk3288_iodomain_init(struct rockchip_iodomain *iod)
+{
+	int ret;
+	u32 val;
+
+	/* if no flash supply we should leave things alone */
+	if (!iod->supplies[RK3288_SOC_FLASH_SUPPLY_NUM].reg)
+		return;
+
+	/*
+	 * set flash0 iodomain to also use this framework
+	 * instead of a special gpio.
+	 */
+	val = RK3288_SOC_CON2_FLASH0 | (RK3288_SOC_CON2_FLASH0 << 16);
+	ret = regmap_write(iod->grf, RK3288_SOC_CON2, val);
+	if (ret < 0)
+		dev_warn(iod->dev, "couldn't update flash0 ctrl\n");
+}
+
+/*
+ * On the rk3188 the io-domains are handled by a shared register with the
+ * lower 8 bits being still being continuing drive-strength settings.
+ */
+static const struct rockchip_iodomain_soc_data soc_data_rk3188 = {
+	.grf_offset = 0x104,
+	.supply_names = {
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		"ap0",
+		"ap1",
+		"cif",
+		"flash",
+		"vccio0",
+		"vccio1",
+		"lcdc0",
+		"lcdc1",
+	},
+};
+
+static const struct rockchip_iodomain_soc_data soc_data_rk3288 = {
+	.grf_offset = 0x380,
+	.supply_names = {
+		"lcdc",		/* LCDC_VDD */
+		"dvp",		/* DVPIO_VDD */
+		"flash0",	/* FLASH0_VDD (emmc) */
+		"flash1",	/* FLASH1_VDD (sdio1) */
+		"wifi",		/* APIO3_VDD  (sdio0) */
+		"bb",		/* APIO5_VDD */
+		"audio",	/* APIO4_VDD */
+		"sdcard",	/* SDMMC0_VDD (sdmmc) */
+		"gpio30",	/* APIO1_VDD */
+		"gpio1830",	/* APIO2_VDD */
+	},
+	.init = rk3288_iodomain_init,
+};
+
+static const struct of_device_id rockchip_iodomain_match[] = {
+	{
+		.compatible = "rockchip,rk3188-io-voltage-domain",
+		.data = (void *)&soc_data_rk3188
+	},
+	{
+		.compatible = "rockchip,rk3288-io-voltage-domain",
+		.data = (void *)&soc_data_rk3288
+	},
+	{ /* sentinel */ },
+};
+
+static int rockchip_iodomain_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	const struct of_device_id *match;
+	struct rockchip_iodomain *iod;
+	int i, ret = 0;
+
+	if (!np)
+		return -ENODEV;
+
+	iod = devm_kzalloc(&pdev->dev, sizeof(*iod), GFP_KERNEL);
+	if (!iod)
+		return -ENOMEM;
+
+	iod->dev = &pdev->dev;
+	platform_set_drvdata(pdev, iod);
+
+	match = of_match_node(rockchip_iodomain_match, np);
+	iod->soc_data = (struct rockchip_iodomain_soc_data *)match->data;
+
+	iod->grf = syscon_regmap_lookup_by_phandle(np, "rockchip,grf");
+	if (IS_ERR(iod->grf)) {
+		dev_err(&pdev->dev, "couldn't find grf regmap\n");
+		return PTR_ERR(iod->grf);
+	}
+
+	for (i = 0; i < MAX_SUPPLIES; i++) {
+		const char *supply_name = iod->soc_data->supply_names[i];
+		struct rockchip_iodomain_supply *supply = &iod->supplies[i];
+		struct regulator *reg;
+		int uV;
+
+		if (!supply_name)
+			continue;
+
+		reg = devm_regulator_get_optional(iod->dev, supply_name);
+		if (IS_ERR(reg)) {
+			ret = PTR_ERR(reg);
+
+			/* If a supply wasn't specified, that's OK */
+			if (ret == -ENODEV)
+				continue;
+			else if (ret != -EPROBE_DEFER)
+				dev_err(iod->dev, "couldn't get regulator %s\n",
+					supply_name);
+			goto unreg_notify;
+		}
+
+		/* set initial correct value */
+		uV = regulator_get_voltage(reg);
+
+		/* must be a regulator we can get the voltage of */
+		if (uV < 0) {
+			dev_err(iod->dev, "Can't determine voltage: %s\n",
+				supply_name);
+			goto unreg_notify;
+		}
+
+		if (uV > MAX_VOLTAGE_3_3) {
+			dev_crit(iod->dev,
+				 "%d uV is too high. May damage SoC!\n",
+				 uV);
+			ret = -EINVAL;
+			goto unreg_notify;
+		}
+
+		/* setup our supply */
+		supply->idx = i;
+		supply->iod = iod;
+		supply->reg = reg;
+		supply->nb.notifier_call = rockchip_iodomain_notify;
+
+		ret = rockchip_iodomain_write(supply, uV);
+		if (ret) {
+			supply->reg = NULL;
+			goto unreg_notify;
+		}
+
+		/* register regulator notifier */
+		ret = regulator_register_notifier(reg, &supply->nb);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"regulator notifier request failed\n");
+			supply->reg = NULL;
+			goto unreg_notify;
+		}
+	}
+
+	if (iod->soc_data->init)
+		iod->soc_data->init(iod);
+
+	return 0;
+
+unreg_notify:
+	for (i = MAX_SUPPLIES - 1; i >= 0; i--) {
+		struct rockchip_iodomain_supply *io_supply = &iod->supplies[i];
+
+		if (io_supply->reg)
+			regulator_unregister_notifier(io_supply->reg,
+						      &io_supply->nb);
+	}
+
+	return ret;
+}
+
+static int rockchip_iodomain_remove(struct platform_device *pdev)
+{
+	struct rockchip_iodomain *iod = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = MAX_SUPPLIES - 1; i >= 0; i--) {
+		struct rockchip_iodomain_supply *io_supply = &iod->supplies[i];
+
+		if (io_supply->reg)
+			regulator_unregister_notifier(io_supply->reg,
+						      &io_supply->nb);
+	}
+
+	return 0;
+}
+
+static struct platform_driver rockchip_iodomain_driver = {
+	.probe   = rockchip_iodomain_probe,
+	.remove  = rockchip_iodomain_remove,
+	.driver  = {
+		.name  = "rockchip-iodomain",
+		.of_match_table = rockchip_iodomain_match,
+	},
+};
+
+module_platform_driver(rockchip_iodomain_driver);
+
+MODULE_DESCRIPTION("Rockchip IO-domain driver");
+MODULE_AUTHOR("Heiko Stuebner <heiko@sntech.de>");
+MODULE_AUTHOR("Doug Anderson <dianders@chromium.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/bq27x00_battery.c b/drivers/power/bq27x00_battery.c
index e10763e3a1d5..e3bacfe3bcd0 100644
--- a/drivers/power/bq27x00_battery.c
+++ b/drivers/power/bq27x00_battery.c
@@ -23,6 +23,7 @@
  * http://focus.ti.com/docs/prod/folders/print/bq27000.html
  * http://focus.ti.com/docs/prod/folders/print/bq27500.html
  * http://www.ti.com/product/bq27425-g1
+ * http://www.ti.com/product/BQ27742-G1
  */
 
 #include <linux/device.h>
@@ -71,6 +72,8 @@
 #define BQ27500_FLAG_FC			BIT(9)
 #define BQ27500_FLAG_OTC		BIT(15)
 
+#define BQ27742_POWER_AVG		0x76
+
 /* bq27425 register addresses are same as bq27x00 addresses minus 4 */
 #define BQ27425_REG_OFFSET		0x04
 #define BQ27425_REG_SOC			0x18 /* Register address plus offset */
@@ -83,7 +86,7 @@ struct bq27x00_access_methods {
 	int (*read)(struct bq27x00_device_info *di, u8 reg, bool single);
 };
 
-enum bq27x00_chip { BQ27000, BQ27500, BQ27425};
+enum bq27x00_chip { BQ27000, BQ27500, BQ27425, BQ27742};
 
 struct bq27x00_reg_cache {
 	int temperature;
@@ -152,6 +155,24 @@ static enum power_supply_property bq27425_battery_props[] = {
 	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
 };
 
+static enum power_supply_property bq27742_battery_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_HEALTH,
+};
+
 static unsigned int poll_interval = 360;
 module_param(poll_interval, uint, 0644);
 MODULE_PARM_DESC(poll_interval, "battery poll interval in seconds - " \
@@ -176,7 +197,7 @@ static inline int bq27x00_read(struct bq27x00_device_info *di, u8 reg,
  */
 static bool bq27xxx_is_chip_version_higher(struct bq27x00_device_info *di)
 {
-	if (di->chip == BQ27425 || di->chip == BQ27500)
+	if (di->chip == BQ27425 || di->chip == BQ27500 || di->chip == BQ27742)
 		return true;
 	return false;
 }
@@ -189,7 +210,7 @@ static int bq27x00_battery_read_rsoc(struct bq27x00_device_info *di)
 {
 	int rsoc;
 
-	if (di->chip == BQ27500)
+	if (di->chip == BQ27500 || di->chip == BQ27742)
 		rsoc = bq27x00_read(di, BQ27500_REG_SOC, false);
 	else if (di->chip == BQ27425)
 		rsoc = bq27x00_read(di, BQ27425_REG_SOC, false);
@@ -233,9 +254,11 @@ static inline int bq27x00_battery_read_nac(struct bq27x00_device_info *di)
 {
 	int flags;
 	bool is_bq27500 = di->chip == BQ27500;
+	bool is_bq27742 = di->chip == BQ27742;
 	bool is_higher = bq27xxx_is_chip_version_higher(di);
+	bool flags_1b = !(is_bq27500 || is_bq27742);
 
-	flags = bq27x00_read(di, BQ27x00_REG_FLAGS, !is_bq27500);
+	flags = bq27x00_read(di, BQ27x00_REG_FLAGS, flags_1b);
 	if (flags >= 0 && !is_higher && (flags & BQ27000_FLAG_CI))
 		return -ENODATA;
 
@@ -414,13 +437,15 @@ static void bq27x00_update(struct bq27x00_device_info *di)
 	struct bq27x00_reg_cache cache = {0, };
 	bool is_bq27500 = di->chip == BQ27500;
 	bool is_bq27425 = di->chip == BQ27425;
+	bool is_bq27742 = di->chip == BQ27742;
+	bool flags_1b = !(is_bq27500 || is_bq27742);
 
-	cache.flags = bq27x00_read(di, BQ27x00_REG_FLAGS, !is_bq27500);
+	cache.flags = bq27x00_read(di, BQ27x00_REG_FLAGS, flags_1b);
 	if ((cache.flags & 0xff) == 0xff)
 		/* read error */
 		cache.flags = -1;
 	if (cache.flags >= 0) {
-		if (!is_bq27500 && !is_bq27425
+		if (!is_bq27500 && !is_bq27425 && !is_bq27742
 				&& (cache.flags & BQ27000_FLAG_CI)) {
 			dev_info(di->dev, "battery is not calibrated! ignoring capacity values\n");
 			cache.capacity = -ENODATA;
@@ -432,7 +457,11 @@ static void bq27x00_update(struct bq27x00_device_info *di)
 			cache.health = -ENODATA;
 		} else {
 			cache.capacity = bq27x00_battery_read_rsoc(di);
-			if (!is_bq27425) {
+			if (is_bq27742)
+				cache.time_to_empty =
+					bq27x00_battery_read_time(di,
+							BQ27x00_REG_TTE);
+			else if (!is_bq27425) {
 				cache.energy = bq27x00_battery_read_energy(di);
 				cache.time_to_empty =
 					bq27x00_battery_read_time(di,
@@ -450,8 +479,14 @@ static void bq27x00_update(struct bq27x00_device_info *di)
 		cache.temperature = bq27x00_battery_read_temperature(di);
 		if (!is_bq27425)
 			cache.cycle_count = bq27x00_battery_read_cyct(di);
-		cache.power_avg =
-			bq27x00_battery_read_pwr_avg(di, BQ27x00_POWER_AVG);
+		if (is_bq27742)
+			cache.power_avg =
+				bq27x00_battery_read_pwr_avg(di,
+						BQ27742_POWER_AVG);
+		else
+			cache.power_avg =
+				bq27x00_battery_read_pwr_avg(di,
+						BQ27x00_POWER_AVG);
 
 		/* We only have to read charge design full once */
 		if (di->charge_design_full <= 0)
@@ -702,6 +737,9 @@ static int bq27x00_powersupply_init(struct bq27x00_device_info *di)
 	if (di->chip == BQ27425) {
 		di->bat.properties = bq27425_battery_props;
 		di->bat.num_properties = ARRAY_SIZE(bq27425_battery_props);
+	} else if (di->chip == BQ27742) {
+		di->bat.properties = bq27742_battery_props;
+		di->bat.num_properties = ARRAY_SIZE(bq27742_battery_props);
 	} else {
 		di->bat.properties = bq27x00_battery_props;
 		di->bat.num_properties = ARRAY_SIZE(bq27x00_battery_props);
@@ -858,6 +896,7 @@ static const struct i2c_device_id bq27x00_id[] = {
 	{ "bq27200", BQ27000 },	/* bq27200 is same as bq27000, but with i2c */
 	{ "bq27500", BQ27500 },
 	{ "bq27425", BQ27425 },
+	{ "bq27742", BQ27742 },
 	{},
 };
 MODULE_DEVICE_TABLE(i2c, bq27x00_id);
diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c
index 9e4dab46eefd..7098a1ce2d3c 100644
--- a/drivers/power/charger-manager.c
+++ b/drivers/power/charger-manager.c
@@ -1656,7 +1656,7 @@ static inline struct charger_desc *cm_get_drv_data(struct platform_device *pdev)
 {
 	if (pdev->dev.of_node)
 		return of_cm_parse_desc(&pdev->dev);
-	return (struct charger_desc *)dev_get_platdata(&pdev->dev);
+	return dev_get_platdata(&pdev->dev);
 }
 
 static int charger_manager_probe(struct platform_device *pdev)
@@ -1677,7 +1677,7 @@ static int charger_manager_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (!desc) {
+	if (IS_ERR(desc)) {
 		dev_err(&pdev->dev, "No platform data (desc) found\n");
 		return -ENODEV;
 	}
@@ -1720,6 +1720,11 @@ static int charger_manager_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	if (!desc->psy_fuel_gauge) {
+		dev_err(&pdev->dev, "No fuel gauge power supply defined\n");
+		return -EINVAL;
+	}
+
 	/* Counting index only */
 	while (desc->psy_charger_stat[i])
 		i++;
@@ -1839,6 +1844,13 @@ static int charger_manager_probe(struct platform_device *pdev)
 	device_init_wakeup(&pdev->dev, true);
 	device_set_wakeup_capable(&pdev->dev, false);
 
+	/*
+	 * Charger-manager have to check the charging state right after
+	 * tialization of charger-manager and then update current charging
+	 * state.
+	 */
+	cm_monitor();
+
 	schedule_work(&setup_polling);
 
 	return 0;
diff --git a/drivers/power/gpio-charger.c b/drivers/power/gpio-charger.c
index a0024b252197..7536933d0ab9 100644
--- a/drivers/power/gpio-charger.c
+++ b/drivers/power/gpio-charger.c
@@ -55,7 +55,7 @@ static int gpio_charger_get_property(struct power_supply *psy,
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_ONLINE:
-		val->intval = gpio_get_value_cansleep(pdata->gpio);
+		val->intval = !!gpio_get_value_cansleep(pdata->gpio);
 		val->intval ^= pdata->gpio_active_low;
 		break;
 	default:
diff --git a/drivers/power/max14577_charger.c b/drivers/power/max14577_charger.c
index fad2a75b3604..0a2bc7277026 100644
--- a/drivers/power/max14577_charger.c
+++ b/drivers/power/max14577_charger.c
@@ -1,7 +1,7 @@
 /*
- * Battery charger driver for the Maxim 14577
+ * max14577_charger.c - Battery charger driver for the Maxim 14577/77836
  *
- * Copyright (C) 2013 Samsung Electronics
+ * Copyright (C) 2013,2014 Samsung Electronics
  * Krzysztof Kozlowski <k.kozlowski@samsung.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -19,16 +19,44 @@
 #include <linux/platform_device.h>
 #include <linux/power_supply.h>
 #include <linux/mfd/max14577-private.h>
+#include <linux/mfd/max14577.h>
 
 struct max14577_charger {
 	struct device *dev;
 	struct max14577	*max14577;
 	struct power_supply	charger;
 
-	unsigned int	charging_state;
-	unsigned int	battery_state;
+	unsigned int		charging_state;
+	unsigned int		battery_state;
+
+	struct max14577_charger_platform_data	*pdata;
 };
 
+/*
+ * Helper function for mapping values of STATUS2/CHGTYP register on max14577
+ * and max77836 chipsets to enum maxim_muic_charger_type.
+ */
+static enum max14577_muic_charger_type maxim_get_charger_type(
+		enum maxim_device_type dev_type, u8 val) {
+	switch (val) {
+	case MAX14577_CHARGER_TYPE_NONE:
+	case MAX14577_CHARGER_TYPE_USB:
+	case MAX14577_CHARGER_TYPE_DOWNSTREAM_PORT:
+	case MAX14577_CHARGER_TYPE_DEDICATED_CHG:
+	case MAX14577_CHARGER_TYPE_SPECIAL_500MA:
+	case MAX14577_CHARGER_TYPE_SPECIAL_1A:
+		return val;
+	case MAX14577_CHARGER_TYPE_DEAD_BATTERY:
+	case MAX14577_CHARGER_TYPE_RESERVED:
+		if (dev_type == MAXIM_DEVICE_TYPE_MAX77836)
+			val |= 0x8;
+		return val;
+	default:
+		WARN_ONCE(1, "max14577: Unsupported chgtyp register value 0x%02x", val);
+		return val;
+	}
+}
+
 static int max14577_get_charger_state(struct max14577_charger *chg)
 {
 	struct regmap *rmap = chg->max14577->regmap;
@@ -89,19 +117,23 @@ static int max14577_get_online(struct max14577_charger *chg)
 {
 	struct regmap *rmap = chg->max14577->regmap;
 	u8 reg_data;
+	enum max14577_muic_charger_type chg_type;
 
 	max14577_read_reg(rmap, MAX14577_MUIC_REG_STATUS2, &reg_data);
 	reg_data = ((reg_data & STATUS2_CHGTYP_MASK) >> STATUS2_CHGTYP_SHIFT);
-	switch (reg_data) {
+	chg_type = maxim_get_charger_type(chg->max14577->dev_type, reg_data);
+	switch (chg_type) {
 	case MAX14577_CHARGER_TYPE_USB:
 	case MAX14577_CHARGER_TYPE_DEDICATED_CHG:
 	case MAX14577_CHARGER_TYPE_SPECIAL_500MA:
 	case MAX14577_CHARGER_TYPE_SPECIAL_1A:
 	case MAX14577_CHARGER_TYPE_DEAD_BATTERY:
+	case MAX77836_CHARGER_TYPE_SPECIAL_BIAS:
 		return 1;
 	case MAX14577_CHARGER_TYPE_NONE:
 	case MAX14577_CHARGER_TYPE_DOWNSTREAM_PORT:
 	case MAX14577_CHARGER_TYPE_RESERVED:
+	case MAX77836_CHARGER_TYPE_RESERVED:
 	default:
 		return 0;
 	}
@@ -118,10 +150,12 @@ static int max14577_get_battery_health(struct max14577_charger *chg)
 	struct regmap *rmap = chg->max14577->regmap;
 	int state = POWER_SUPPLY_HEALTH_GOOD;
 	u8 reg_data;
+	enum max14577_muic_charger_type chg_type;
 
 	max14577_read_reg(rmap, MAX14577_MUIC_REG_STATUS2, &reg_data);
 	reg_data = ((reg_data & STATUS2_CHGTYP_MASK) >> STATUS2_CHGTYP_SHIFT);
-	if (reg_data == MAX14577_CHARGER_TYPE_DEAD_BATTERY) {
+	chg_type = maxim_get_charger_type(chg->max14577->dev_type, reg_data);
+	if (chg_type == MAX14577_CHARGER_TYPE_DEAD_BATTERY) {
 		state = POWER_SUPPLY_HEALTH_DEAD;
 		goto state_set;
 	}
@@ -147,15 +181,131 @@ static int max14577_get_present(struct max14577_charger *chg)
 	return 1;
 }
 
+static int max14577_set_fast_charge_timer(struct max14577_charger *chg,
+		unsigned long hours)
+{
+	u8 reg_data;
+
+	switch (hours) {
+	case 5 ... 7:
+		reg_data = hours - 3;
+		break;
+	case 0:
+		/* Disable */
+		reg_data = 0x7;
+		break;
+	default:
+		dev_err(chg->dev, "Wrong value for Fast-Charge Timer: %lu\n",
+				hours);
+		return -EINVAL;
+	}
+	reg_data <<= CHGCTRL1_TCHW_SHIFT;
+
+	return max14577_update_reg(chg->max14577->regmap,
+			MAX14577_REG_CHGCTRL1, CHGCTRL1_TCHW_MASK, reg_data);
+}
+
+static int max14577_init_constant_voltage(struct max14577_charger *chg,
+		unsigned int uvolt)
+{
+	u8 reg_data;
+
+	if (uvolt < MAXIM_CHARGER_CONSTANT_VOLTAGE_MIN ||
+			uvolt > MAXIM_CHARGER_CONSTANT_VOLTAGE_MAX)
+		return -EINVAL;
+
+	if (uvolt == 4200000)
+		reg_data = 0x0;
+	else if (uvolt == MAXIM_CHARGER_CONSTANT_VOLTAGE_MAX)
+		reg_data = 0x1f;
+	else if (uvolt <= 4280000) {
+		unsigned int val = uvolt;
+
+		val -= MAXIM_CHARGER_CONSTANT_VOLTAGE_MIN;
+		val /= MAXIM_CHARGER_CONSTANT_VOLTAGE_STEP;
+		if (uvolt <= 4180000)
+			reg_data = 0x1 + val;
+		else
+			reg_data = val; /* Fix for gap between 4.18V and 4.22V */
+	} else
+		return -EINVAL;
+
+	reg_data <<= CHGCTRL3_MBCCVWRC_SHIFT;
+
+	return max14577_write_reg(chg->max14577->regmap,
+			MAX14577_CHG_REG_CHG_CTRL3, reg_data);
+}
+
+static int max14577_init_eoc(struct max14577_charger *chg,
+		unsigned int uamp)
+{
+	unsigned int current_bits = 0xf;
+	u8 reg_data;
+
+	switch (chg->max14577->dev_type) {
+	case MAXIM_DEVICE_TYPE_MAX77836:
+		if (uamp < 5000)
+			return -EINVAL; /* Requested current is too low */
+
+		if (uamp >= 7500 && uamp < 10000)
+			current_bits = 0x0;
+		else if (uamp <= 50000) {
+			/* <5000, 7499> and <10000, 50000> */
+			current_bits = uamp / 5000;
+		} else {
+			uamp = min(uamp, 100000U) - 50000U;
+			current_bits = 0xa + uamp / 10000;
+		}
+		break;
+
+	case MAXIM_DEVICE_TYPE_MAX14577:
+	default:
+		if (uamp < MAX14577_CHARGER_EOC_CURRENT_LIMIT_MIN)
+			return -EINVAL; /* Requested current is too low */
+
+		uamp = min(uamp, MAX14577_CHARGER_EOC_CURRENT_LIMIT_MAX);
+		uamp -= MAX14577_CHARGER_EOC_CURRENT_LIMIT_MIN;
+		current_bits = uamp / MAX14577_CHARGER_EOC_CURRENT_LIMIT_STEP;
+		break;
+	}
+
+	reg_data = current_bits << CHGCTRL5_EOCS_SHIFT;
+
+	return max14577_update_reg(chg->max14577->regmap,
+			MAX14577_CHG_REG_CHG_CTRL5, CHGCTRL5_EOCS_MASK,
+			reg_data);
+}
+
+static int max14577_init_fast_charge(struct max14577_charger *chg,
+		unsigned int uamp)
+{
+	u8 reg_data;
+	int ret;
+	const struct maxim_charger_current *limits =
+		&maxim_charger_currents[chg->max14577->dev_type];
+
+	ret = maxim_charger_calc_reg_current(limits, uamp, uamp, &reg_data);
+	if (ret) {
+		dev_err(chg->dev, "Wrong value for fast charge: %u\n", uamp);
+		return ret;
+	}
+
+	return max14577_update_reg(chg->max14577->regmap,
+			MAX14577_CHG_REG_CHG_CTRL4,
+			CHGCTRL4_MBCICHWRCL_MASK | CHGCTRL4_MBCICHWRCH_MASK,
+			reg_data);
+}
+
 /*
  * Sets charger registers to proper and safe default values.
  * Some of these values are equal to defaults in MAX14577E
  * data sheet but there are minor differences.
  */
-static void max14577_charger_reg_init(struct max14577_charger *chg)
+static int max14577_charger_reg_init(struct max14577_charger *chg)
 {
 	struct regmap *rmap = chg->max14577->regmap;
 	u8 reg_data;
+	int ret;
 
 	/*
 	 * Charger-Type Manual Detection, default off (set CHGTYPMAN to 0)
@@ -167,10 +317,6 @@ static void max14577_charger_reg_init(struct max14577_charger *chg)
 			CDETCTRL1_CHGDETEN_MASK | CDETCTRL1_CHGTYPMAN_MASK,
 			reg_data);
 
-	/* Battery Fast-Charge Timer, from SM-V700: 6hrs */
-	reg_data = 0x3 << CHGCTRL1_TCHW_SHIFT;
-	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL1, reg_data);
-
 	/*
 	 * Wall-Adapter Rapid Charge, default on
 	 * Battery-Charger, default on
@@ -179,29 +325,46 @@ static void max14577_charger_reg_init(struct max14577_charger *chg)
 	reg_data |= 0x1 << CHGCTRL2_MBCHOSTEN_SHIFT;
 	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL2, reg_data);
 
-	/* Battery-Charger Constant Voltage (CV) Mode, from SM-V700: 4.35V */
-	reg_data = 0xf << CHGCTRL3_MBCCVWRC_SHIFT;
-	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL3, reg_data);
-
-	/*
-	 * Fast Battery-Charge Current Low, default 200-950mA
-	 * Fast Battery-Charge Current High, from SM-V700: 450mA
-	 */
-	reg_data = 0x1 << CHGCTRL4_MBCICHWRCL_SHIFT;
-	reg_data |= 0x5 << CHGCTRL4_MBCICHWRCH_SHIFT;
-	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL4, reg_data);
-
-	/* End-of-Charge Current, from SM-V700: 50mA */
-	reg_data = 0x0 << CHGCTRL5_EOCS_SHIFT;
-	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL5, reg_data);
-
 	/* Auto Charging Stop, default off */
 	reg_data = 0x0 << CHGCTRL6_AUTOSTOP_SHIFT;
 	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL6, reg_data);
 
-	/* Overvoltage-Protection Threshold, from SM-V700: 6.5V */
-	reg_data = 0x2 << CHGCTRL7_OTPCGHCVS_SHIFT;
+	ret = max14577_init_constant_voltage(chg, chg->pdata->constant_uvolt);
+	if (ret)
+		return ret;
+
+	ret = max14577_init_eoc(chg, chg->pdata->eoc_uamp);
+	if (ret)
+		return ret;
+
+	ret = max14577_init_fast_charge(chg, chg->pdata->fast_charge_uamp);
+	if (ret)
+		return ret;
+
+	ret = max14577_set_fast_charge_timer(chg,
+			MAXIM_CHARGER_FAST_CHARGE_TIMER_DEFAULT);
+	if (ret)
+		return ret;
+
+	/* Initialize Overvoltage-Protection Threshold */
+	switch (chg->pdata->ovp_uvolt) {
+	case 7500000:
+		reg_data = 0x0;
+		break;
+	case 6000000:
+	case 6500000:
+	case 7000000:
+		reg_data = 0x1 + (chg->pdata->ovp_uvolt - 6000000) / 500000;
+		break;
+	default:
+		dev_err(chg->dev, "Wrong value for OVP: %u\n",
+				chg->pdata->ovp_uvolt);
+		return -EINVAL;
+	}
+	reg_data <<= CHGCTRL7_OTPCGHCVS_SHIFT;
 	max14577_write_reg(rmap, MAX14577_REG_CHGCTRL7, reg_data);
+
+	return 0;
 }
 
 /* Support property from charger */
@@ -215,7 +378,11 @@ static enum power_supply_property max14577_charger_props[] = {
 	POWER_SUPPLY_PROP_MANUFACTURER,
 };
 
-static const char *model_name = "MAX14577";
+static const char * const model_names[] = {
+	[MAXIM_DEVICE_TYPE_UNKNOWN]	= "MAX14577-like",
+	[MAXIM_DEVICE_TYPE_MAX14577]	= "MAX14577",
+	[MAXIM_DEVICE_TYPE_MAX77836]	= "MAX77836",
+};
 static const char *manufacturer = "Maxim Integrated";
 
 static int max14577_charger_get_property(struct power_supply *psy,
@@ -244,7 +411,8 @@ static int max14577_charger_get_property(struct power_supply *psy,
 		val->intval = max14577_get_online(chg);
 		break;
 	case POWER_SUPPLY_PROP_MODEL_NAME:
-		val->strval = model_name;
+		BUILD_BUG_ON(ARRAY_SIZE(model_names) != MAXIM_DEVICE_TYPE_NUM);
+		val->strval = model_names[chg->max14577->dev_type];
 		break;
 	case POWER_SUPPLY_PROP_MANUFACTURER:
 		val->strval = manufacturer;
@@ -256,6 +424,110 @@ static int max14577_charger_get_property(struct power_supply *psy,
 	return ret;
 }
 
+#ifdef CONFIG_OF
+static struct max14577_charger_platform_data *max14577_charger_dt_init(
+		struct platform_device *pdev)
+{
+	struct max14577_charger_platform_data *pdata;
+	struct device_node *np = pdev->dev.of_node;
+	int ret;
+
+	if (!np) {
+		dev_err(&pdev->dev, "No charger OF node\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	ret = of_property_read_u32(np, "maxim,constant-uvolt",
+			&pdata->constant_uvolt);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot parse maxim,constant-uvolt field from DT\n");
+		return ERR_PTR(ret);
+	}
+
+	ret = of_property_read_u32(np, "maxim,fast-charge-uamp",
+			&pdata->fast_charge_uamp);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot parse maxim,fast-charge-uamp field from DT\n");
+		return ERR_PTR(ret);
+	}
+
+	ret = of_property_read_u32(np, "maxim,eoc-uamp", &pdata->eoc_uamp);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot parse maxim,eoc-uamp field from DT\n");
+		return ERR_PTR(ret);
+	}
+
+	ret = of_property_read_u32(np, "maxim,ovp-uvolt", &pdata->ovp_uvolt);
+	if (ret) {
+		dev_err(&pdev->dev, "Cannot parse maxim,ovp-uvolt field from DT\n");
+		return ERR_PTR(ret);
+	}
+
+	return pdata;
+}
+#else /* CONFIG_OF */
+static struct max14577_charger_platform_data *max14577_charger_dt_init(
+		struct platform_device *pdev)
+{
+	return NULL;
+}
+#endif /* CONFIG_OF */
+
+static ssize_t show_fast_charge_timer(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct max14577_charger *chg = dev_get_drvdata(dev);
+	u8 reg_data;
+	int ret;
+	unsigned int val;
+
+	ret = max14577_read_reg(chg->max14577->regmap, MAX14577_REG_CHGCTRL1,
+			&reg_data);
+	if (ret)
+		return ret;
+
+	reg_data &= CHGCTRL1_TCHW_MASK;
+	reg_data >>= CHGCTRL1_TCHW_SHIFT;
+	switch (reg_data) {
+	case 0x2 ... 0x4:
+		val = reg_data + 3;
+		break;
+	case 0x7:
+		val = 0;
+		break;
+	default:
+		val = 5;
+		break;
+	}
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+}
+
+static ssize_t store_fast_charge_timer(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct max14577_charger *chg = dev_get_drvdata(dev);
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	ret = max14577_set_fast_charge_timer(chg, val);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static DEVICE_ATTR(fast_charge_timer, S_IRUGO | S_IWUSR,
+		show_fast_charge_timer, store_fast_charge_timer);
+
 static int max14577_charger_probe(struct platform_device *pdev)
 {
 	struct max14577_charger *chg;
@@ -270,7 +542,13 @@ static int max14577_charger_probe(struct platform_device *pdev)
 	chg->dev = &pdev->dev;
 	chg->max14577 = max14577;
 
-	max14577_charger_reg_init(chg);
+	chg->pdata = max14577_charger_dt_init(pdev);
+	if (IS_ERR_OR_NULL(chg->pdata))
+		return PTR_ERR(chg->pdata);
+
+	ret = max14577_charger_reg_init(chg);
+	if (ret)
+		return ret;
 
 	chg->charger.name = "max14577-charger",
 	chg->charger.type = POWER_SUPPLY_TYPE_BATTERY,
@@ -278,24 +556,47 @@ static int max14577_charger_probe(struct platform_device *pdev)
 	chg->charger.num_properties = ARRAY_SIZE(max14577_charger_props),
 	chg->charger.get_property = max14577_charger_get_property,
 
+	ret = device_create_file(&pdev->dev, &dev_attr_fast_charge_timer);
+	if (ret) {
+		dev_err(&pdev->dev, "failed: create sysfs entry\n");
+		return ret;
+	}
+
 	ret = power_supply_register(&pdev->dev, &chg->charger);
 	if (ret) {
 		dev_err(&pdev->dev, "failed: power supply register\n");
-		return ret;
+		goto err;
 	}
 
+	/* Check for valid values for charger */
+	BUILD_BUG_ON(MAX14577_CHARGER_EOC_CURRENT_LIMIT_MIN +
+			MAX14577_CHARGER_EOC_CURRENT_LIMIT_STEP * 0xf !=
+			MAX14577_CHARGER_EOC_CURRENT_LIMIT_MAX);
 	return 0;
+
+err:
+	device_remove_file(&pdev->dev, &dev_attr_fast_charge_timer);
+
+	return ret;
 }
 
 static int max14577_charger_remove(struct platform_device *pdev)
 {
 	struct max14577_charger *chg = platform_get_drvdata(pdev);
 
+	device_remove_file(&pdev->dev, &dev_attr_fast_charge_timer);
 	power_supply_unregister(&chg->charger);
 
 	return 0;
 }
 
+static const struct platform_device_id max14577_charger_id[] = {
+	{ "max14577-charger", MAXIM_DEVICE_TYPE_MAX14577, },
+	{ "max77836-charger", MAXIM_DEVICE_TYPE_MAX77836, },
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, max14577_charger_id);
+
 static struct platform_driver max14577_charger_driver = {
 	.driver = {
 		.owner	= THIS_MODULE,
@@ -303,9 +604,10 @@ static struct platform_driver max14577_charger_driver = {
 	},
 	.probe		= max14577_charger_probe,
 	.remove		= max14577_charger_remove,
+	.id_table	= max14577_charger_id,
 };
 module_platform_driver(max14577_charger_driver);
 
 MODULE_AUTHOR("Krzysztof Kozlowski <k.kozlowski@samsung.com>");
-MODULE_DESCRIPTION("MAXIM 14577 charger driver");
+MODULE_DESCRIPTION("Maxim 14577/77836 charger driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/power/max17040_battery.c b/drivers/power/max17040_battery.c
index 0fbac861080d..14d44706327b 100644
--- a/drivers/power/max17040_battery.c
+++ b/drivers/power/max17040_battery.c
@@ -277,7 +277,8 @@ static SIMPLE_DEV_PM_OPS(max17040_pm_ops, max17040_suspend, max17040_resume);
 #endif /* CONFIG_PM_SLEEP */
 
 static const struct i2c_device_id max17040_id[] = {
-	{ "max17040", 0 },
+	{ "max17040" },
+	{ "max77836-battery" },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, max17040_id);
diff --git a/drivers/power/max8925_power.c b/drivers/power/max8925_power.c
index b4513f284bbc..a6d45eef64dd 100644
--- a/drivers/power/max8925_power.c
+++ b/drivers/power/max8925_power.c
@@ -443,7 +443,7 @@ max8925_power_dt_init(struct platform_device *pdev)
 	if (!nproot)
 		return pdev->dev.platform_data;
 
-	np = of_find_node_by_name(nproot, "charger");
+	np = of_get_child_by_name(nproot, "charger");
 	if (!np) {
 		dev_err(&pdev->dev, "failed to find charger node\n");
 		return NULL;
@@ -452,13 +452,14 @@ max8925_power_dt_init(struct platform_device *pdev)
 	pdata = devm_kzalloc(&pdev->dev,
 			sizeof(struct max8925_power_pdata),
 			GFP_KERNEL);
+	if (!pdata)
+		goto ret;
 
 	of_property_read_u32(np, "topoff-threshold", &topoff_threshold);
 	of_property_read_u32(np, "batt-detect", &batt_detect);
 	of_property_read_u32(np, "fast-charge", &fast_charge);
 	of_property_read_u32(np, "no-insert-detect", &no_insert_detect);
 	of_property_read_u32(np, "no-temp-support", &no_temp_support);
-	of_node_put(np);
 
 	pdata->batt_detect = batt_detect;
 	pdata->fast_charge = fast_charge;
@@ -466,6 +467,8 @@ max8925_power_dt_init(struct platform_device *pdev)
 	pdata->no_insert_detect = no_insert_detect;
 	pdata->no_temp_support = no_temp_support;
 
+ret:
+	of_node_put(np);
 	return pdata;
 }
 #else
diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index 078afd61490d..6cb7fe5c022d 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -58,7 +58,7 @@ static bool __power_supply_is_supplied_by(struct power_supply *supplier,
 
 static int __power_supply_changed_work(struct device *dev, void *data)
 {
-	struct power_supply *psy = (struct power_supply *)data;
+	struct power_supply *psy = data;
 	struct power_supply *pst = dev_get_drvdata(dev);
 
 	if (__power_supply_is_supplied_by(psy, pst)) {
@@ -78,7 +78,14 @@ static void power_supply_changed_work(struct work_struct *work)
 	dev_dbg(psy->dev, "%s\n", __func__);
 
 	spin_lock_irqsave(&psy->changed_lock, flags);
-	if (psy->changed) {
+	/*
+	 * Check 'changed' here to avoid issues due to race between
+	 * power_supply_changed() and this routine. In worst case
+	 * power_supply_changed() can be called again just before we take above
+	 * lock. During the first call of this routine we will mark 'changed' as
+	 * false and it will stay false for the next call as well.
+	 */
+	if (likely(psy->changed)) {
 		psy->changed = false;
 		spin_unlock_irqrestore(&psy->changed_lock, flags);
 		class_for_each_device(power_supply_class, NULL, psy,
@@ -89,12 +96,13 @@ static void power_supply_changed_work(struct work_struct *work)
 		kobject_uevent(&psy->dev->kobj, KOBJ_CHANGE);
 		spin_lock_irqsave(&psy->changed_lock, flags);
 	}
+
 	/*
-	 * Dependent power supplies (e.g. battery) may have changed state
-	 * as a result of this event, so poll again and hold the
-	 * wakeup_source until all events are processed.
+	 * Hold the wakeup_source until all events are processed.
+	 * power_supply_changed() might have called again and have set 'changed'
+	 * to true.
 	 */
-	if (!psy->changed)
+	if (likely(!psy->changed))
 		pm_relax(psy->dev);
 	spin_unlock_irqrestore(&psy->changed_lock, flags);
 }
@@ -119,7 +127,7 @@ EXPORT_SYMBOL_GPL(power_supply_changed);
 static int __power_supply_populate_supplied_from(struct device *dev,
 						 void *data)
 {
-	struct power_supply *psy = (struct power_supply *)data;
+	struct power_supply *psy = data;
 	struct power_supply *epsy = dev_get_drvdata(dev);
 	struct device_node *np;
 	int i = 0;
@@ -127,7 +135,7 @@ static int __power_supply_populate_supplied_from(struct device *dev,
 	do {
 		np = of_parse_phandle(psy->of_node, "power-supplies", i++);
 		if (!np)
-			continue;
+			break;
 
 		if (np == epsy->of_node) {
 			dev_info(psy->dev, "%s: Found supply : %s\n",
@@ -158,12 +166,12 @@ static int power_supply_populate_supplied_from(struct power_supply *psy)
 static int  __power_supply_find_supply_from_node(struct device *dev,
 						 void *data)
 {
-	struct device_node *np = (struct device_node *)data;
+	struct device_node *np = data;
 	struct power_supply *epsy = dev_get_drvdata(dev);
 
-	/* return error breaks out of class_for_each_device loop */
+	/* returning non-zero breaks out of class_for_each_device loop */
 	if (epsy->of_node == np)
-		return -EINVAL;
+		return 1;
 
 	return 0;
 }
@@ -171,30 +179,21 @@ static int  __power_supply_find_supply_from_node(struct device *dev,
 static int power_supply_find_supply_from_node(struct device_node *supply_node)
 {
 	int error;
-	struct device *dev;
-	struct class_dev_iter iter;
 
 	/*
-	 * Use iterator to see if any other device is registered.
-	 * This is required since class_for_each_device returns 0
-	 * if there are no devices registered.
-	 */
-	class_dev_iter_init(&iter, power_supply_class, NULL, NULL);
-	dev = class_dev_iter_next(&iter);
-
-	if (!dev)
-		return -EPROBE_DEFER;
-
-	/*
-	 * We have to treat the return value as inverted, because if
-	 * we return error on not found, then it won't continue looking.
-	 * So we trick it by returning error on success to stop looking
-	 * once the matching device is found.
+	 * class_for_each_device() either returns its own errors or values
+	 * returned by __power_supply_find_supply_from_node().
+	 *
+	 * __power_supply_find_supply_from_node() will return 0 (no match)
+	 * or 1 (match).
+	 *
+	 * We return 0 if class_for_each_device() returned 1, -EPROBE_DEFER if
+	 * it returned 0, or error as returned by it.
 	 */
 	error = class_for_each_device(power_supply_class, NULL, supply_node,
 				       __power_supply_find_supply_from_node);
 
-	return error ? 0 : -EPROBE_DEFER;
+	return error ? (error == 1 ? 0 : error) : -EPROBE_DEFER;
 }
 
 static int power_supply_check_supplies(struct power_supply *psy)
@@ -215,17 +214,21 @@ static int power_supply_check_supplies(struct power_supply *psy)
 
 		np = of_parse_phandle(psy->of_node, "power-supplies", cnt++);
 		if (!np)
-			continue;
+			break;
 
 		ret = power_supply_find_supply_from_node(np);
+		of_node_put(np);
+
 		if (ret) {
-			dev_dbg(psy->dev, "Failed to find supply, defer!\n");
-			of_node_put(np);
-			return -EPROBE_DEFER;
+			dev_dbg(psy->dev, "Failed to find supply!\n");
+			return ret;
 		}
-		of_node_put(np);
 	} while (np);
 
+	/* Missing valid "power-supplies" entries */
+	if (cnt == 1)
+		return 0;
+
 	/* All supplies found, allocate char ** array for filling */
 	psy->supplied_from = devm_kzalloc(psy->dev, sizeof(psy->supplied_from),
 					  GFP_KERNEL);
@@ -234,7 +237,7 @@ static int power_supply_check_supplies(struct power_supply *psy)
 		return -ENOMEM;
 	}
 
-	*psy->supplied_from = devm_kzalloc(psy->dev, sizeof(char *) * cnt,
+	*psy->supplied_from = devm_kzalloc(psy->dev, sizeof(char *) * (cnt - 1),
 					   GFP_KERNEL);
 	if (!*psy->supplied_from) {
 		dev_err(psy->dev, "Couldn't allocate memory for supply list\n");
@@ -253,14 +256,12 @@ static inline int power_supply_check_supplies(struct power_supply *psy)
 static int __power_supply_am_i_supplied(struct device *dev, void *data)
 {
 	union power_supply_propval ret = {0,};
-	struct power_supply *psy = (struct power_supply *)data;
+	struct power_supply *psy = data;
 	struct power_supply *epsy = dev_get_drvdata(dev);
 
 	if (__power_supply_is_supplied_by(epsy, psy))
-		if (!epsy->get_property(epsy, POWER_SUPPLY_PROP_ONLINE, &ret)) {
-			if (ret.intval)
-				return ret.intval;
-		}
+		if (!epsy->get_property(epsy, POWER_SUPPLY_PROP_ONLINE, &ret))
+			return ret.intval;
 
 	return 0;
 }
@@ -285,12 +286,10 @@ static int __power_supply_is_system_supplied(struct device *dev, void *data)
 	unsigned int *count = data;
 
 	(*count)++;
-	if (psy->type != POWER_SUPPLY_TYPE_BATTERY) {
-		if (psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &ret))
-			return 0;
-		if (ret.intval)
+	if (psy->type != POWER_SUPPLY_TYPE_BATTERY)
+		if (!psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &ret))
 			return ret.intval;
-	}
+
 	return 0;
 }
 
@@ -423,9 +422,7 @@ static int psy_register_thermal(struct power_supply *psy)
 		if (psy->properties[i] == POWER_SUPPLY_PROP_TEMP) {
 			psy->tzd = thermal_zone_device_register(psy->name, 0, 0,
 					psy, &psy_tzd_ops, NULL, 0, 0);
-			if (IS_ERR(psy->tzd))
-				return PTR_ERR(psy->tzd);
-			break;
+			return PTR_ERR_OR_ZERO(psy->tzd);
 		}
 	}
 	return 0;
@@ -503,9 +500,7 @@ static int psy_register_cooler(struct power_supply *psy)
 			psy->tcd = thermal_cooling_device_register(
 							(char *)psy->name,
 							psy, &psy_tcd_ops);
-			if (IS_ERR(psy->tcd))
-				return PTR_ERR(psy->tcd);
-			break;
+			return PTR_ERR_OR_ZERO(psy->tcd);
 		}
 	}
 	return 0;
@@ -591,7 +586,7 @@ static int __power_supply_register(struct device *parent,
 
 	power_supply_changed(psy);
 
-	goto success;
+	return 0;
 
 create_triggers_failed:
 	psy_unregister_cooler(psy);
@@ -604,7 +599,6 @@ wakeup_init_failed:
 check_supplies_failed:
 dev_set_name_failed:
 	put_device(dev);
-success:
 	return rc;
 }
 
diff --git a/drivers/power/power_supply_leds.c b/drivers/power/power_supply_leds.c
index 995f966ed5b7..effa093c37b0 100644
--- a/drivers/power/power_supply_leds.c
+++ b/drivers/power/power_supply_leds.c
@@ -57,8 +57,6 @@ static void power_supply_update_bat_leds(struct power_supply *psy)
 
 static int power_supply_create_bat_triggers(struct power_supply *psy)
 {
-	int rc = 0;
-
 	psy->charging_full_trig_name = kasprintf(GFP_KERNEL,
 					"%s-charging-or-full", psy->name);
 	if (!psy->charging_full_trig_name)
@@ -87,7 +85,7 @@ static int power_supply_create_bat_triggers(struct power_supply *psy)
 	led_trigger_register_simple(psy->charging_blink_full_solid_trig_name,
 				    &psy->charging_blink_full_solid_trig);
 
-	goto success;
+	return 0;
 
 charging_blink_full_solid_failed:
 	kfree(psy->full_trig_name);
@@ -96,9 +94,7 @@ full_failed:
 charging_failed:
 	kfree(psy->charging_full_trig_name);
 charging_full_failed:
-	rc = -ENOMEM;
-success:
-	return rc;
+	return -ENOMEM;
 }
 
 static void power_supply_remove_bat_triggers(struct power_supply *psy)
@@ -132,20 +128,13 @@ static void power_supply_update_gen_leds(struct power_supply *psy)
 
 static int power_supply_create_gen_triggers(struct power_supply *psy)
 {
-	int rc = 0;
-
 	psy->online_trig_name = kasprintf(GFP_KERNEL, "%s-online", psy->name);
 	if (!psy->online_trig_name)
-		goto online_failed;
+		return -ENOMEM;
 
 	led_trigger_register_simple(psy->online_trig_name, &psy->online_trig);
 
-	goto success;
-
-online_failed:
-	rc = -ENOMEM;
-success:
-	return rc;
+	return 0;
 }
 
 static void power_supply_remove_gen_triggers(struct power_supply *psy)
diff --git a/drivers/power/power_supply_sysfs.c b/drivers/power/power_supply_sysfs.c
index 750a20275664..62653f50a524 100644
--- a/drivers/power/power_supply_sysfs.c
+++ b/drivers/power/power_supply_sysfs.c
@@ -73,19 +73,20 @@ static ssize_t power_supply_show_property(struct device *dev,
 	const ptrdiff_t off = attr - power_supply_attrs;
 	union power_supply_propval value;
 
-	if (off == POWER_SUPPLY_PROP_TYPE)
+	if (off == POWER_SUPPLY_PROP_TYPE) {
 		value.intval = psy->type;
-	else
+	} else {
 		ret = psy->get_property(psy, off, &value);
 
-	if (ret < 0) {
-		if (ret == -ENODATA)
-			dev_dbg(dev, "driver has no data for `%s' property\n",
-				attr->attr.name);
-		else if (ret != -ENODEV)
-			dev_err(dev, "driver failed to report `%s' property: %zd\n",
-				attr->attr.name, ret);
-		return ret;
+		if (ret < 0) {
+			if (ret == -ENODATA)
+				dev_dbg(dev, "driver has no data for `%s' property\n",
+					attr->attr.name);
+			else if (ret != -ENODEV)
+				dev_err(dev, "driver failed to report `%s' property: %zd\n",
+					attr->attr.name, ret);
+			return ret;
+		}
 	}
 
 	if (off == POWER_SUPPLY_PROP_STATUS)
@@ -149,9 +150,11 @@ static struct device_attribute power_supply_attrs[] = {
 	POWER_SUPPLY_ATTR(voltage_now),
 	POWER_SUPPLY_ATTR(voltage_avg),
 	POWER_SUPPLY_ATTR(voltage_ocv),
+	POWER_SUPPLY_ATTR(voltage_boot),
 	POWER_SUPPLY_ATTR(current_max),
 	POWER_SUPPLY_ATTR(current_now),
 	POWER_SUPPLY_ATTR(current_avg),
+	POWER_SUPPLY_ATTR(current_boot),
 	POWER_SUPPLY_ATTR(power_now),
 	POWER_SUPPLY_ATTR(power_avg),
 	POWER_SUPPLY_ATTR(charge_full_design),
@@ -193,6 +196,7 @@ static struct device_attribute power_supply_attrs[] = {
 	POWER_SUPPLY_ATTR(type),
 	POWER_SUPPLY_ATTR(scope),
 	POWER_SUPPLY_ATTR(charge_term_current),
+	POWER_SUPPLY_ATTR(calibrate),
 	/* Properties of type `const char *' */
 	POWER_SUPPLY_ATTR(model_name),
 	POWER_SUPPLY_ATTR(manufacturer),
diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index 527a0f47ef44..f65ff49bb275 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -40,7 +40,7 @@ config POWER_RESET_AXXIA
 
 config POWER_RESET_BRCMSTB
 	bool "Broadcom STB reset driver" if COMPILE_TEST
-	depends on POWER_RESET && ARM
+	depends on ARM
 	default ARCH_BRCMSTB
 	help
 	  This driver provides restart support for ARM-based Broadcom STB
@@ -57,9 +57,17 @@ config POWER_RESET_GPIO
 	  If your board needs a GPIO high/low to power down, say Y and
 	  create a binding in your devicetree.
 
+config POWER_RESET_GPIO_RESTART
+	bool "GPIO restart driver"
+	depends on OF_GPIO
+	help
+	  This driver supports restarting your board via a GPIO line.
+	  If your board needs a GPIO high/low to restart, say Y and
+	  create a binding in your devicetree.
+
 config POWER_RESET_HISI
 	bool "Hisilicon power-off driver"
-	depends on POWER_RESET && ARCH_HISI
+	depends on ARCH_HISI
 	help
 	  Reboot support for Hisilicon boards.
 
@@ -69,6 +77,13 @@ config POWER_RESET_MSM
 	help
 	  Power off and restart support for Qualcomm boards.
 
+config POWER_RESET_LTC2952
+	bool "LTC2952 PowerPath power-off driver"
+	depends on OF_GPIO
+	help
+	  This driver supports an external powerdown trigger and board power
+	  down via the LTC2952. Bindings are made in the device tree.
+
 config POWER_RESET_QNAP
 	bool "QNAP power-off driver"
 	depends on OF_GPIO && PLAT_ORION
@@ -92,6 +107,12 @@ config POWER_RESET_SUN6I
 	help
 	  Reboot support for the Allwinner A31 SoCs.
 
+config POWER_RESET_ST
+	bool "ST restart power-off driver"
+	depends on ARCH_STI
+	help
+	  Power off and reset support for STMicroelectronics boards.
+
 config POWER_RESET_VERSATILE
 	bool "ARM Versatile family reboot driver"
 	depends on ARM
@@ -122,4 +143,12 @@ config POWER_RESET_KEYSTONE
 	help
 	  Reboot support for the KEYSTONE SoCs.
 
+config POWER_RESET_SYSCON
+	bool "Generic SYSCON regmap reset driver"
+	depends on OF
+	select MFD_SYSCON
+	help
+	  Reboot support for generic SYSCON mapped register reset.
+
 endif
+
diff --git a/drivers/power/reset/Makefile b/drivers/power/reset/Makefile
index 73221009f2bf..76ce1c59469b 100644
--- a/drivers/power/reset/Makefile
+++ b/drivers/power/reset/Makefile
@@ -4,12 +4,16 @@ obj-$(CONFIG_POWER_RESET_AT91_RESET) += at91-reset.o
 obj-$(CONFIG_POWER_RESET_AXXIA) += axxia-reset.o
 obj-$(CONFIG_POWER_RESET_BRCMSTB) += brcmstb-reboot.o
 obj-$(CONFIG_POWER_RESET_GPIO) += gpio-poweroff.o
+obj-$(CONFIG_POWER_RESET_GPIO_RESTART) += gpio-restart.o
 obj-$(CONFIG_POWER_RESET_HISI) += hisi-reboot.o
 obj-$(CONFIG_POWER_RESET_MSM) += msm-poweroff.o
+obj-$(CONFIG_POWER_RESET_LTC2952) += ltc2952-poweroff.o
 obj-$(CONFIG_POWER_RESET_QNAP) += qnap-poweroff.o
 obj-$(CONFIG_POWER_RESET_RESTART) += restart-poweroff.o
 obj-$(CONFIG_POWER_RESET_SUN6I) += sun6i-reboot.o
+obj-$(CONFIG_POWER_RESET_ST) += st-poweroff.o
 obj-$(CONFIG_POWER_RESET_VERSATILE) += arm-versatile-reboot.o
 obj-$(CONFIG_POWER_RESET_VEXPRESS) += vexpress-poweroff.o
 obj-$(CONFIG_POWER_RESET_XGENE) += xgene-reboot.o
 obj-$(CONFIG_POWER_RESET_KEYSTONE) += keystone-reset.o
+obj-$(CONFIG_POWER_RESET_SYSCON) += syscon-reboot.o
diff --git a/drivers/power/reset/gpio-restart.c b/drivers/power/reset/gpio-restart.c
new file mode 100644
index 000000000000..a76829b3f1cd
--- /dev/null
+++ b/drivers/power/reset/gpio-restart.c
@@ -0,0 +1,149 @@
+/*
+ * Toggles a GPIO pin to restart a device
+ *
+ * Copyright (C) 2014 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Based on the gpio-poweroff driver.
+ */
+#include <linux/reboot.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of_platform.h>
+#include <linux/module.h>
+
+struct gpio_restart {
+	struct gpio_desc *reset_gpio;
+	struct notifier_block restart_handler;
+	u32 active_delay_ms;
+	u32 inactive_delay_ms;
+	u32 wait_delay_ms;
+};
+
+static int gpio_restart_notify(struct notifier_block *this,
+				unsigned long mode, void *cmd)
+{
+	struct gpio_restart *gpio_restart =
+		container_of(this, struct gpio_restart, restart_handler);
+
+	/* drive it active, also inactive->active edge */
+	gpiod_direction_output(gpio_restart->reset_gpio, 1);
+	mdelay(gpio_restart->active_delay_ms);
+
+	/* drive inactive, also active->inactive edge */
+	gpiod_set_value(gpio_restart->reset_gpio, 0);
+	mdelay(gpio_restart->inactive_delay_ms);
+
+	/* drive it active, also inactive->active edge */
+	gpiod_set_value(gpio_restart->reset_gpio, 1);
+
+	/* give it some time */
+	mdelay(gpio_restart->wait_delay_ms);
+
+	WARN_ON(1);
+
+	return NOTIFY_DONE;
+}
+
+static int gpio_restart_probe(struct platform_device *pdev)
+{
+	struct gpio_restart *gpio_restart;
+	bool open_source = false;
+	u32 property;
+	int ret;
+
+	gpio_restart = devm_kzalloc(&pdev->dev, sizeof(*gpio_restart),
+			GFP_KERNEL);
+	if (!gpio_restart)
+		return -ENOMEM;
+
+	open_source = of_property_read_bool(pdev->dev.of_node, "open-source");
+
+	gpio_restart->reset_gpio = devm_gpiod_get(&pdev->dev, NULL,
+			open_source ? GPIOD_IN : GPIOD_OUT_LOW);
+	if (IS_ERR(gpio_restart->reset_gpio)) {
+		dev_err(&pdev->dev, "Could net get reset GPIO\n");
+		return PTR_ERR(gpio_restart->reset_gpio);
+	}
+
+	gpio_restart->restart_handler.notifier_call = gpio_restart_notify;
+	gpio_restart->restart_handler.priority = 128;
+	gpio_restart->active_delay_ms = 100;
+	gpio_restart->inactive_delay_ms = 100;
+	gpio_restart->wait_delay_ms = 3000;
+
+	ret = of_property_read_u32(pdev->dev.of_node, "priority", &property);
+	if (!ret) {
+		if (property > 255)
+			dev_err(&pdev->dev, "Invalid priority property: %u\n",
+					property);
+		else
+			gpio_restart->restart_handler.priority = property;
+	}
+
+	of_property_read_u32(pdev->dev.of_node, "active-delay",
+			&gpio_restart->active_delay_ms);
+	of_property_read_u32(pdev->dev.of_node, "inactive-delay",
+			&gpio_restart->inactive_delay_ms);
+	of_property_read_u32(pdev->dev.of_node, "wait-delay",
+			&gpio_restart->wait_delay_ms);
+
+	platform_set_drvdata(pdev, gpio_restart);
+
+	ret = register_restart_handler(&gpio_restart->restart_handler);
+	if (ret) {
+		dev_err(&pdev->dev, "%s: cannot register restart handler, %d\n",
+				__func__, ret);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int gpio_restart_remove(struct platform_device *pdev)
+{
+	struct gpio_restart *gpio_restart = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = unregister_restart_handler(&gpio_restart->restart_handler);
+	if (ret) {
+		dev_err(&pdev->dev,
+				"%s: cannot unregister restart handler, %d\n",
+				__func__, ret);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id of_gpio_restart_match[] = {
+	{ .compatible = "gpio-restart", },
+	{},
+};
+
+static struct platform_driver gpio_restart_driver = {
+	.probe = gpio_restart_probe,
+	.remove = gpio_restart_remove,
+	.driver = {
+		.name = "restart-gpio",
+		.owner = THIS_MODULE,
+		.of_match_table = of_gpio_restart_match,
+	},
+};
+
+module_platform_driver(gpio_restart_driver);
+
+MODULE_AUTHOR("David Riley <davidriley@chromium.org>");
+MODULE_DESCRIPTION("GPIO restart driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/power/reset/ltc2952-poweroff.c b/drivers/power/reset/ltc2952-poweroff.c
new file mode 100644
index 000000000000..116a1cef8f7b
--- /dev/null
+++ b/drivers/power/reset/ltc2952-poweroff.c
@@ -0,0 +1,386 @@
+/*
+ * LTC2952 (PowerPath) driver
+ *
+ * Copyright (C) 2014, Xsens Technologies BV <info@xsens.com>
+ * Maintainer: René Moll <linux@r-moll.nl>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * ----------------------------------------
+ * - Description
+ * ----------------------------------------
+ *
+ * This driver is to be used with an external PowerPath Controller (LTC2952).
+ * Its function is to determine when a external shut down is triggered
+ * and react by properly shutting down the system.
+ *
+ * This driver expects a device tree with a ltc2952 entry for pin mapping.
+ *
+ * ----------------------------------------
+ * - GPIO
+ * ----------------------------------------
+ *
+ * The following GPIOs are used:
+ * - trigger (input)
+ *     A level change indicates the shut-down trigger. If it's state reverts
+ *     within the time-out defined by trigger_delay, the shut down is not
+ *     executed.
+ *
+ * - watchdog (output)
+ *     Once a shut down is triggered, the driver will toggle this signal,
+ *     with an internal (wde_interval) to stall the hardware shut down.
+ *
+ * - kill (output)
+ *     The last action during shut down is triggering this signalling, such
+ *     that the PowerPath Control will power down the hardware.
+ *
+ * ----------------------------------------
+ * - Interrupts
+ * ----------------------------------------
+ *
+ * The driver requires a non-shared, edge-triggered interrupt on the trigger
+ * GPIO.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/ktime.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/module.h>
+#include <linux/gpio/consumer.h>
+#include <linux/reboot.h>
+
+struct ltc2952_poweroff_data {
+	struct hrtimer timer_trigger;
+	struct hrtimer timer_wde;
+
+	ktime_t trigger_delay;
+	ktime_t wde_interval;
+
+	struct device *dev;
+
+	unsigned int virq;
+
+	/**
+	 * 0: trigger
+	 * 1: watchdog
+	 * 2: kill
+	 */
+	struct gpio_desc *gpio[3];
+};
+
+static int ltc2952_poweroff_panic;
+static struct ltc2952_poweroff_data *ltc2952_data;
+
+#define POWERPATH_IO_TRIGGER	0
+#define POWERPATH_IO_WATCHDOG	1
+#define POWERPATH_IO_KILL	2
+
+/**
+ * ltc2952_poweroff_timer_wde - Timer callback
+ * Toggles the watchdog reset signal each wde_interval
+ *
+ * @timer: corresponding timer
+ *
+ * Returns HRTIMER_RESTART for an infinite loop which will only stop when the
+ * machine actually shuts down
+ */
+static enum hrtimer_restart ltc2952_poweroff_timer_wde(struct hrtimer *timer)
+{
+	ktime_t now;
+	int state;
+	unsigned long overruns;
+
+	if (ltc2952_poweroff_panic)
+		return HRTIMER_NORESTART;
+
+	state = gpiod_get_value(ltc2952_data->gpio[POWERPATH_IO_WATCHDOG]);
+	gpiod_set_value(ltc2952_data->gpio[POWERPATH_IO_WATCHDOG], !state);
+
+	now = hrtimer_cb_get_time(timer);
+	overruns = hrtimer_forward(timer, now, ltc2952_data->wde_interval);
+
+	return HRTIMER_RESTART;
+}
+
+static enum hrtimer_restart ltc2952_poweroff_timer_trigger(
+	struct hrtimer *timer)
+{
+	int ret;
+
+	ret = hrtimer_start(&ltc2952_data->timer_wde,
+		ltc2952_data->wde_interval, HRTIMER_MODE_REL);
+
+	if (ret) {
+		dev_err(ltc2952_data->dev, "unable to start the timer\n");
+		/*
+		 * The device will not toggle the watchdog reset,
+		 * thus shut down is only safe if the PowerPath controller
+		 * has a long enough time-off before triggering a hardware
+		 * power-off.
+		 *
+		 * Only sending a warning as the system will power-off anyway
+		 */
+	}
+
+	dev_info(ltc2952_data->dev, "executing shutdown\n");
+
+	orderly_poweroff(true);
+
+	return HRTIMER_NORESTART;
+}
+
+/**
+ * ltc2952_poweroff_handler - Interrupt handler
+ * Triggered each time the trigger signal changes state and (de)activates a
+ * time-out (timer_trigger). Once the time-out is actually reached the shut
+ * down is executed.
+ *
+ * @irq: IRQ number
+ * @dev_id: pointer to the main data structure
+ */
+static irqreturn_t ltc2952_poweroff_handler(int irq, void *dev_id)
+{
+	int ret;
+	struct ltc2952_poweroff_data *data = dev_id;
+
+	if (ltc2952_poweroff_panic)
+		goto irq_ok;
+
+	if (hrtimer_active(&data->timer_wde)) {
+		/* shutdown is already triggered, nothing to do any more */
+		goto irq_ok;
+	}
+
+	if (!hrtimer_active(&data->timer_trigger)) {
+		ret = hrtimer_start(&data->timer_trigger, data->trigger_delay,
+			HRTIMER_MODE_REL);
+
+		if (ret)
+			dev_err(data->dev, "unable to start the wait timer\n");
+	} else {
+		ret = hrtimer_cancel(&data->timer_trigger);
+		/* omitting return value check, timer should have been valid */
+	}
+
+irq_ok:
+	return IRQ_HANDLED;
+}
+
+static void ltc2952_poweroff_kill(void)
+{
+	gpiod_set_value(ltc2952_data->gpio[POWERPATH_IO_KILL], 1);
+}
+
+static int ltc2952_poweroff_suspend(struct platform_device *pdev,
+	pm_message_t state)
+{
+	return -ENOSYS;
+}
+
+static int ltc2952_poweroff_resume(struct platform_device *pdev)
+{
+	return -ENOSYS;
+}
+
+static void ltc2952_poweroff_default(struct ltc2952_poweroff_data *data)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(data->gpio); i++)
+		data->gpio[i] = NULL;
+
+	data->wde_interval = ktime_set(0, 300L*1E6L);
+	data->trigger_delay = ktime_set(2, 500L*1E6L);
+
+	hrtimer_init(&data->timer_trigger, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	data->timer_trigger.function = &ltc2952_poweroff_timer_trigger;
+
+	hrtimer_init(&data->timer_wde, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	data->timer_wde.function = &ltc2952_poweroff_timer_wde;
+}
+
+static int ltc2952_poweroff_init(struct platform_device *pdev)
+{
+	int ret, virq;
+	unsigned int i;
+	struct ltc2952_poweroff_data *data;
+
+	static char *name[] = {
+		"trigger",
+		"watchdog",
+		"kill",
+		NULL
+	};
+
+	data = ltc2952_data;
+	ltc2952_poweroff_default(ltc2952_data);
+
+	for (i = 0; i < ARRAY_SIZE(ltc2952_data->gpio); i++) {
+		ltc2952_data->gpio[i] = gpiod_get(&pdev->dev, name[i]);
+
+		if (IS_ERR(ltc2952_data->gpio[i])) {
+			ret = PTR_ERR(ltc2952_data->gpio[i]);
+			dev_err(&pdev->dev,
+				"unable to claim the following gpio: %s\n",
+				name[i]);
+			goto err_io;
+		}
+	}
+
+	ret = gpiod_direction_output(
+		ltc2952_data->gpio[POWERPATH_IO_WATCHDOG], 0);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to use watchdog-gpio as output\n");
+		goto err_io;
+	}
+
+	ret = gpiod_direction_output(ltc2952_data->gpio[POWERPATH_IO_KILL], 0);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to use kill-gpio as output\n");
+		goto err_io;
+	}
+
+	virq = gpiod_to_irq(ltc2952_data->gpio[POWERPATH_IO_TRIGGER]);
+	if (virq < 0) {
+		dev_err(&pdev->dev, "cannot map GPIO as interrupt");
+		goto err_io;
+	}
+
+	ltc2952_data->virq = virq;
+	ret = request_irq(virq,
+		ltc2952_poweroff_handler,
+		(IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING),
+		"ltc2952-poweroff",
+		ltc2952_data
+	);
+
+	if (ret) {
+		dev_err(&pdev->dev, "cannot configure an interrupt handler\n");
+		goto err_io;
+	}
+
+	return 0;
+
+err_io:
+	for (i = 0; i < ARRAY_SIZE(ltc2952_data->gpio); i++)
+		if (ltc2952_data->gpio[i])
+			gpiod_put(ltc2952_data->gpio[i]);
+
+	return ret;
+}
+
+static int ltc2952_poweroff_probe(struct platform_device *pdev)
+{
+	int ret;
+
+	if (pm_power_off) {
+		dev_err(&pdev->dev, "pm_power_off already registered");
+		return -EBUSY;
+	}
+
+	ltc2952_data = kzalloc(sizeof(*ltc2952_data), GFP_KERNEL);
+	if (!ltc2952_data)
+		return -ENOMEM;
+
+	ltc2952_data->dev = &pdev->dev;
+
+	ret = ltc2952_poweroff_init(pdev);
+	if (ret)
+		goto err;
+
+	pm_power_off = &ltc2952_poweroff_kill;
+
+	dev_info(&pdev->dev, "probe successful\n");
+
+	return 0;
+
+err:
+	kfree(ltc2952_data);
+	return ret;
+}
+
+static int ltc2952_poweroff_remove(struct platform_device *pdev)
+{
+	unsigned int i;
+
+	pm_power_off = NULL;
+
+	if (ltc2952_data) {
+		free_irq(ltc2952_data->virq, ltc2952_data);
+
+		for (i = 0; i < ARRAY_SIZE(ltc2952_data->gpio); i++)
+			gpiod_put(ltc2952_data->gpio[i]);
+
+		kfree(ltc2952_data);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id of_ltc2952_poweroff_match[] = {
+	{ .compatible = "lltc,ltc2952"},
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_ltc2952_poweroff_match);
+
+static struct platform_driver ltc2952_poweroff_driver = {
+	.probe = ltc2952_poweroff_probe,
+	.remove = ltc2952_poweroff_remove,
+	.driver = {
+		.name = "ltc2952-poweroff",
+		.owner = THIS_MODULE,
+		.of_match_table = of_ltc2952_poweroff_match,
+	},
+	.suspend = ltc2952_poweroff_suspend,
+	.resume = ltc2952_poweroff_resume,
+};
+
+static int ltc2952_poweroff_notify_panic(struct notifier_block *nb,
+	unsigned long code, void *unused)
+{
+	ltc2952_poweroff_panic = 1;
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block ltc2952_poweroff_panic_nb = {
+	.notifier_call = ltc2952_poweroff_notify_panic,
+};
+
+static int __init ltc2952_poweroff_platform_init(void)
+{
+	ltc2952_poweroff_panic = 0;
+
+	atomic_notifier_chain_register(&panic_notifier_list,
+		&ltc2952_poweroff_panic_nb);
+
+	return platform_driver_register(&ltc2952_poweroff_driver);
+}
+
+static void __exit ltc2952_poweroff_platform_exit(void)
+{
+	atomic_notifier_chain_unregister(&panic_notifier_list,
+		&ltc2952_poweroff_panic_nb);
+
+	platform_driver_unregister(&ltc2952_poweroff_driver);
+}
+
+module_init(ltc2952_poweroff_platform_init);
+module_exit(ltc2952_poweroff_platform_exit);
+
+MODULE_AUTHOR("René Moll <rene.moll@xsens.com>");
+MODULE_DESCRIPTION("LTC PowerPath power-off driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/reset/msm-poweroff.c b/drivers/power/reset/msm-poweroff.c
index 774f9a3b310d..4702efdfe466 100644
--- a/drivers/power/reset/msm-poweroff.c
+++ b/drivers/power/reset/msm-poweroff.c
@@ -20,21 +20,27 @@
 #include <linux/platform_device.h>
 #include <linux/module.h>
 #include <linux/reboot.h>
-
-#include <asm/system_misc.h>
+#include <linux/pm.h>
 
 static void __iomem *msm_ps_hold;
-
-static void do_msm_restart(enum reboot_mode reboot_mode, const char *cmd)
+static int do_msm_restart(struct notifier_block *nb, unsigned long action,
+			   void *data)
 {
 	writel(0, msm_ps_hold);
 	mdelay(10000);
+
+	return NOTIFY_DONE;
 }
 
+static struct notifier_block restart_nb = {
+	.notifier_call = do_msm_restart,
+	.priority = 128,
+};
+
 static void do_msm_poweroff(void)
 {
 	/* TODO: Add poweroff capability */
-	do_msm_restart(REBOOT_HARD, NULL);
+	do_msm_restart(&restart_nb, 0, NULL);
 }
 
 static int msm_restart_probe(struct platform_device *pdev)
@@ -47,8 +53,10 @@ static int msm_restart_probe(struct platform_device *pdev)
 	if (IS_ERR(msm_ps_hold))
 		return PTR_ERR(msm_ps_hold);
 
+	register_restart_handler(&restart_nb);
+
 	pm_power_off = do_msm_poweroff;
-	arm_pm_restart = do_msm_restart;
+
 	return 0;
 }
 
diff --git a/drivers/power/reset/restart-poweroff.c b/drivers/power/reset/restart-poweroff.c
index 3e51f8d29bfe..edd707ee7281 100644
--- a/drivers/power/reset/restart-poweroff.c
+++ b/drivers/power/reset/restart-poweroff.c
@@ -20,7 +20,8 @@
 
 static void restart_poweroff_do_poweroff(void)
 {
-	arm_pm_restart(REBOOT_HARD, NULL);
+	reboot_mode = REBOOT_HARD;
+	machine_restart(NULL);
 }
 
 static int restart_poweroff_probe(struct platform_device *pdev)
diff --git a/drivers/power/reset/st-poweroff.c b/drivers/power/reset/st-poweroff.c
new file mode 100644
index 000000000000..a0acf25ee2a2
--- /dev/null
+++ b/drivers/power/reset/st-poweroff.c
@@ -0,0 +1,151 @@
+/*
+ * Copyright (C) 2014 STMicroelectronics
+ *
+ * Power off Restart driver, used in STMicroelectronics devices.
+ *
+ * Author: Christophe Kerello <christophe.kerello@st.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+
+#include <asm/system_misc.h>
+
+struct reset_syscfg {
+	struct regmap *regmap;
+	/* syscfg used for reset */
+	unsigned int offset_rst;
+	unsigned int mask_rst;
+	/* syscfg used for unmask the reset */
+	unsigned int offset_rst_msk;
+	unsigned int mask_rst_msk;
+};
+
+/* STiH415 */
+#define STIH415_SYSCFG_11	0x2c
+#define STIH415_SYSCFG_15	0x3c
+
+static struct reset_syscfg stih415_reset = {
+	.offset_rst = STIH415_SYSCFG_11,
+	.mask_rst = BIT(0),
+	.offset_rst_msk = STIH415_SYSCFG_15,
+	.mask_rst_msk = BIT(0)
+};
+
+/* STiH416 */
+#define STIH416_SYSCFG_500	0x7d0
+#define STIH416_SYSCFG_504	0x7e0
+
+static struct reset_syscfg stih416_reset = {
+	.offset_rst = STIH416_SYSCFG_500,
+	.mask_rst = BIT(0),
+	.offset_rst_msk = STIH416_SYSCFG_504,
+	.mask_rst_msk = BIT(0)
+};
+
+/* STiH407 */
+#define STIH407_SYSCFG_4000	0x0
+#define STIH407_SYSCFG_4008	0x20
+
+static struct reset_syscfg stih407_reset = {
+	.offset_rst = STIH407_SYSCFG_4000,
+	.mask_rst = BIT(0),
+	.offset_rst_msk = STIH407_SYSCFG_4008,
+	.mask_rst_msk = BIT(0)
+};
+
+/* STiD127 */
+#define STID127_SYSCFG_700	0x0
+#define STID127_SYSCFG_773	0x124
+
+static struct reset_syscfg stid127_reset = {
+	.offset_rst = STID127_SYSCFG_773,
+	.mask_rst = BIT(0),
+	.offset_rst_msk = STID127_SYSCFG_700,
+	.mask_rst_msk = BIT(8)
+};
+
+static struct reset_syscfg *st_restart_syscfg;
+
+static void st_restart(enum reboot_mode reboot_mode, const char *cmd)
+{
+	/* reset syscfg updated */
+	regmap_update_bits(st_restart_syscfg->regmap,
+			   st_restart_syscfg->offset_rst,
+			   st_restart_syscfg->mask_rst,
+			   0);
+
+	/* unmask the reset */
+	regmap_update_bits(st_restart_syscfg->regmap,
+			   st_restart_syscfg->offset_rst_msk,
+			   st_restart_syscfg->mask_rst_msk,
+			   0);
+}
+
+static struct of_device_id st_reset_of_match[] = {
+	{
+		.compatible = "st,stih415-restart",
+		.data = (void *)&stih415_reset,
+	}, {
+		.compatible = "st,stih416-restart",
+		.data = (void *)&stih416_reset,
+	}, {
+		.compatible = "st,stih407-restart",
+		.data = (void *)&stih407_reset,
+	}, {
+		.compatible = "st,stid127-restart",
+		.data = (void *)&stid127_reset,
+	},
+	{}
+};
+
+static int st_reset_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	const struct of_device_id *match;
+	struct device *dev = &pdev->dev;
+
+	match = of_match_device(st_reset_of_match, dev);
+	if (!match)
+		return -ENODEV;
+
+	st_restart_syscfg = (struct reset_syscfg *)match->data;
+
+	st_restart_syscfg->regmap =
+		syscon_regmap_lookup_by_phandle(np, "st,syscfg");
+	if (IS_ERR(st_restart_syscfg->regmap)) {
+		dev_err(dev, "No syscfg phandle specified\n");
+		return PTR_ERR(st_restart_syscfg->regmap);
+	}
+
+	arm_pm_restart = st_restart;
+
+	return 0;
+}
+
+static struct platform_driver st_reset_driver = {
+	.probe = st_reset_probe,
+	.driver = {
+		.name = "st_reset",
+		.of_match_table = st_reset_of_match,
+	},
+};
+
+static int __init st_reset_init(void)
+{
+	return platform_driver_register(&st_reset_driver);
+}
+
+device_initcall(st_reset_init);
+
+MODULE_AUTHOR("Christophe Kerello <christophe.kerello@st.com>");
+MODULE_DESCRIPTION("STMicroelectronics Power off Restart driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/reset/syscon-reboot.c b/drivers/power/reset/syscon-reboot.c
new file mode 100644
index 000000000000..815b901822cf
--- /dev/null
+++ b/drivers/power/reset/syscon-reboot.c
@@ -0,0 +1,91 @@
+/*
+ * Generic Syscon Reboot Driver
+ *
+ * Copyright (c) 2013, Applied Micro Circuits Corporation
+ * Author: Feng Kan <fkan@apm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/notifier.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/reboot.h>
+#include <linux/regmap.h>
+
+struct syscon_reboot_context {
+	struct regmap *map;
+	u32 offset;
+	u32 mask;
+	struct notifier_block restart_handler;
+};
+
+static int syscon_restart_handle(struct notifier_block *this,
+					unsigned long mode, void *cmd)
+{
+	struct syscon_reboot_context *ctx =
+			container_of(this, struct syscon_reboot_context,
+					restart_handler);
+
+	/* Issue the reboot */
+	regmap_write(ctx->map, ctx->offset, ctx->mask);
+
+	mdelay(1000);
+
+	pr_emerg("Unable to restart system\n");
+	return NOTIFY_DONE;
+}
+
+static int syscon_reboot_probe(struct platform_device *pdev)
+{
+	struct syscon_reboot_context *ctx;
+	struct device *dev = &pdev->dev;
+	int err;
+
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->map = syscon_regmap_lookup_by_phandle(dev->of_node, "regmap");
+	if (IS_ERR(ctx->map))
+		return PTR_ERR(ctx->map);
+
+	if (of_property_read_u32(pdev->dev.of_node, "offset", &ctx->offset))
+		return -EINVAL;
+
+	if (of_property_read_u32(pdev->dev.of_node, "mask", &ctx->mask))
+		return -EINVAL;
+
+	ctx->restart_handler.notifier_call = syscon_restart_handle;
+	ctx->restart_handler.priority = 128;
+	err = register_restart_handler(&ctx->restart_handler);
+	if (err)
+		dev_err(dev, "can't register restart notifier (err=%d)\n", err);
+
+	return err;
+}
+
+static struct of_device_id syscon_reboot_of_match[] = {
+	{ .compatible = "syscon-reboot" },
+	{}
+};
+
+static struct platform_driver syscon_reboot_driver = {
+	.probe = syscon_reboot_probe,
+	.driver = {
+		.name = "syscon-reboot",
+		.of_match_table = syscon_reboot_of_match,
+	},
+};
+module_platform_driver(syscon_reboot_driver);
diff --git a/drivers/power/reset/xgene-reboot.c b/drivers/power/reset/xgene-reboot.c
index ecd55f81b9d1..6b49be6867ab 100644
--- a/drivers/power/reset/xgene-reboot.c
+++ b/drivers/power/reset/xgene-reboot.c
@@ -40,7 +40,7 @@ struct xgene_reboot_context {
 
 static struct xgene_reboot_context *xgene_restart_ctx;
 
-static void xgene_restart(char str, const char *cmd)
+static void xgene_restart(enum reboot_mode mode, const char *cmd)
 {
 	struct xgene_reboot_context *ctx = xgene_restart_ctx;
 	unsigned long timeout;
diff --git a/drivers/power/sbs-battery.c b/drivers/power/sbs-battery.c
index b5f2a76b6cdf..c7b7b4018df3 100644
--- a/drivers/power/sbs-battery.c
+++ b/drivers/power/sbs-battery.c
@@ -48,7 +48,10 @@ enum {
 	REG_FULL_CHARGE_CAPACITY_CHARGE,
 	REG_DESIGN_CAPACITY,
 	REG_DESIGN_CAPACITY_CHARGE,
-	REG_DESIGN_VOLTAGE,
+	REG_DESIGN_VOLTAGE_MIN,
+	REG_DESIGN_VOLTAGE_MAX,
+	REG_MANUFACTURER,
+	REG_MODEL_NAME,
 };
 
 /* Battery Mode defines */
@@ -68,6 +71,7 @@ enum sbs_battery_mode {
 #define BATTERY_FULL_CHARGED		0x20
 #define BATTERY_FULL_DISCHARGED		0x10
 
+/* min_value and max_value are only valid for numerical data */
 #define SBS_DATA(_psp, _addr, _min_value, _max_value) { \
 	.psp = _psp, \
 	.addr = _addr, \
@@ -111,10 +115,17 @@ static const struct chip_data {
 		SBS_DATA(POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN, 0x18, 0, 65535),
 	[REG_DESIGN_CAPACITY_CHARGE] =
 		SBS_DATA(POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, 0x18, 0, 65535),
-	[REG_DESIGN_VOLTAGE] =
+	[REG_DESIGN_VOLTAGE_MIN] =
+		SBS_DATA(POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN, 0x19, 0, 65535),
+	[REG_DESIGN_VOLTAGE_MAX] =
 		SBS_DATA(POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN, 0x19, 0, 65535),
 	[REG_SERIAL_NUMBER] =
 		SBS_DATA(POWER_SUPPLY_PROP_SERIAL_NUMBER, 0x1C, 0, 65535),
+	/* Properties of type `const char *' */
+	[REG_MANUFACTURER] =
+		SBS_DATA(POWER_SUPPLY_PROP_MANUFACTURER, 0x20, 0, 65535),
+	[REG_MODEL_NAME] =
+		SBS_DATA(POWER_SUPPLY_PROP_MODEL_NAME, 0x21, 0, 65535)
 };
 
 static enum power_supply_property sbs_properties[] = {
@@ -130,6 +141,7 @@ static enum power_supply_property sbs_properties[] = {
 	POWER_SUPPLY_PROP_TIME_TO_EMPTY_AVG,
 	POWER_SUPPLY_PROP_TIME_TO_FULL_AVG,
 	POWER_SUPPLY_PROP_SERIAL_NUMBER,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
 	POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN,
 	POWER_SUPPLY_PROP_ENERGY_NOW,
 	POWER_SUPPLY_PROP_ENERGY_FULL,
@@ -137,6 +149,9 @@ static enum power_supply_property sbs_properties[] = {
 	POWER_SUPPLY_PROP_CHARGE_NOW,
 	POWER_SUPPLY_PROP_CHARGE_FULL,
 	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	/* Properties of type `const char *' */
+	POWER_SUPPLY_PROP_MANUFACTURER,
+	POWER_SUPPLY_PROP_MODEL_NAME
 };
 
 struct sbs_info {
@@ -153,6 +168,9 @@ struct sbs_info {
 	int				ignore_changes;
 };
 
+static char model_name[I2C_SMBUS_BLOCK_MAX + 1];
+static char manufacturer[I2C_SMBUS_BLOCK_MAX + 1];
+
 static int sbs_read_word_data(struct i2c_client *client, u8 address)
 {
 	struct sbs_info *chip = i2c_get_clientdata(client);
@@ -179,6 +197,74 @@ static int sbs_read_word_data(struct i2c_client *client, u8 address)
 	return le16_to_cpu(ret);
 }
 
+static int sbs_read_string_data(struct i2c_client *client, u8 address,
+				char *values)
+{
+	struct sbs_info *chip = i2c_get_clientdata(client);
+	s32 ret = 0, block_length = 0;
+	int retries_length = 1, retries_block = 1;
+	u8 block_buffer[I2C_SMBUS_BLOCK_MAX + 1];
+
+	if (chip->pdata) {
+		retries_length = max(chip->pdata->i2c_retry_count + 1, 1);
+		retries_block = max(chip->pdata->i2c_retry_count + 1, 1);
+	}
+
+	/* Adapter needs to support these two functions */
+	if (!i2c_check_functionality(client->adapter,
+				     I2C_FUNC_SMBUS_BYTE_DATA |
+				     I2C_FUNC_SMBUS_I2C_BLOCK)){
+		return -ENODEV;
+	}
+
+	/* Get the length of block data */
+	while (retries_length > 0) {
+		ret = i2c_smbus_read_byte_data(client, address);
+		if (ret >= 0)
+			break;
+		retries_length--;
+	}
+
+	if (ret < 0) {
+		dev_dbg(&client->dev,
+			"%s: i2c read at address 0x%x failed\n",
+			__func__, address);
+		return ret;
+	}
+
+	/* block_length does not include NULL terminator */
+	block_length = ret;
+	if (block_length > I2C_SMBUS_BLOCK_MAX) {
+		dev_err(&client->dev,
+			"%s: Returned block_length is longer than 0x%x\n",
+			__func__, I2C_SMBUS_BLOCK_MAX);
+		return -EINVAL;
+	}
+
+	/* Get the block data */
+	while (retries_block > 0) {
+		ret = i2c_smbus_read_i2c_block_data(
+				client, address,
+				block_length + 1, block_buffer);
+		if (ret >= 0)
+			break;
+		retries_block--;
+	}
+
+	if (ret < 0) {
+		dev_dbg(&client->dev,
+			"%s: i2c read at address 0x%x failed\n",
+			__func__, address);
+		return ret;
+	}
+
+	/* block_buffer[0] == block_length */
+	memcpy(values, block_buffer + 1, block_length);
+	values[block_length] = '\0';
+
+	return le16_to_cpu(ret);
+}
+
 static int sbs_write_word_data(struct i2c_client *client, u8 address,
 	u16 value)
 {
@@ -318,6 +404,19 @@ static int sbs_get_battery_property(struct i2c_client *client,
 	return 0;
 }
 
+static int sbs_get_battery_string_property(struct i2c_client *client,
+	int reg_offset, enum power_supply_property psp, char *val)
+{
+	s32 ret;
+
+	ret = sbs_read_string_data(client, sbs_data[reg_offset].addr, val);
+
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static void  sbs_unit_adjustment(struct i2c_client *client,
 	enum power_supply_property psp, union power_supply_propval *val)
 {
@@ -336,6 +435,7 @@ static void  sbs_unit_adjustment(struct i2c_client *client,
 		break;
 
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
 	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
 	case POWER_SUPPLY_PROP_CURRENT_NOW:
 	case POWER_SUPPLY_PROP_CHARGE_NOW:
@@ -497,6 +597,7 @@ static int sbs_get_property(struct power_supply *psy,
 	case POWER_SUPPLY_PROP_TEMP:
 	case POWER_SUPPLY_PROP_TIME_TO_EMPTY_AVG:
 	case POWER_SUPPLY_PROP_TIME_TO_FULL_AVG:
+	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
 	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
 		ret = sbs_get_property_index(client, psp);
 		if (ret < 0)
@@ -505,6 +606,26 @@ static int sbs_get_property(struct power_supply *psy,
 		ret = sbs_get_battery_property(client, ret, psp, val);
 		break;
 
+	case POWER_SUPPLY_PROP_MODEL_NAME:
+		ret = sbs_get_property_index(client, psp);
+		if (ret < 0)
+			break;
+
+		ret = sbs_get_battery_string_property(client, ret, psp,
+						      model_name);
+		val->strval = model_name;
+		break;
+
+	case POWER_SUPPLY_PROP_MANUFACTURER:
+		ret = sbs_get_property_index(client, psp);
+		if (ret < 0)
+			break;
+
+		ret = sbs_get_battery_string_property(client, ret, psp,
+						      manufacturer);
+		val->strval = manufacturer;
+		break;
+
 	default:
 		dev_err(&client->dev,
 			"%s: INVALID property\n", __func__);
diff --git a/drivers/regulator/max14577.c b/drivers/regulator/max14577.c
index 5d9c605cf534..0ff5a20ac958 100644
--- a/drivers/regulator/max14577.c
+++ b/drivers/regulator/max14577.c
@@ -22,42 +22,6 @@
 #include <linux/mfd/max14577-private.h>
 #include <linux/regulator/of_regulator.h>
 
-/*
- * Valid limits of current for max14577 and max77836 chargers.
- * They must correspond to MBCICHWRCL and MBCICHWRCH fields in CHGCTRL4
- * register for given chipset.
- */
-struct maxim_charger_current {
-	/* Minimal current, set in CHGCTRL4/MBCICHWRCL, uA */
-	unsigned int min;
-	/*
-	 * Minimal current when high setting is active,
-	 * set in CHGCTRL4/MBCICHWRCH, uA
-	 */
-	unsigned int high_start;
-	/* Value of one step in high setting, uA */
-	unsigned int high_step;
-	/* Maximum current of high setting, uA */
-	unsigned int max;
-};
-
-/* Table of valid charger currents for different Maxim chipsets */
-static const struct maxim_charger_current maxim_charger_currents[] = {
-	[MAXIM_DEVICE_TYPE_UNKNOWN] = { 0, 0, 0, 0 },
-	[MAXIM_DEVICE_TYPE_MAX14577] = {
-		.min		= MAX14577_REGULATOR_CURRENT_LIMIT_MIN,
-		.high_start	= MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_START,
-		.high_step	= MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_STEP,
-		.max		= MAX14577_REGULATOR_CURRENT_LIMIT_MAX,
-	},
-	[MAXIM_DEVICE_TYPE_MAX77836] = {
-		.min		= MAX77836_REGULATOR_CURRENT_LIMIT_MIN,
-		.high_start	= MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_START,
-		.high_step	= MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_STEP,
-		.max		= MAX77836_REGULATOR_CURRENT_LIMIT_MAX,
-	},
-};
-
 static int max14577_reg_is_enabled(struct regulator_dev *rdev)
 {
 	int rid = rdev_get_id(rdev);
@@ -103,8 +67,8 @@ static int max14577_reg_get_current_limit(struct regulator_dev *rdev)
 static int max14577_reg_set_current_limit(struct regulator_dev *rdev,
 		int min_uA, int max_uA)
 {
-	int i, current_bits = 0xf;
 	u8 reg_data;
+	int ret;
 	struct max14577 *max14577 = rdev_get_drvdata(rdev);
 	const struct maxim_charger_current *limits =
 		&maxim_charger_currents[max14577->dev_type];
@@ -112,35 +76,9 @@ static int max14577_reg_set_current_limit(struct regulator_dev *rdev,
 	if (rdev_get_id(rdev) != MAX14577_CHARGER)
 		return -EINVAL;
 
-	if (min_uA > limits->max || max_uA < limits->min)
-		return -EINVAL;
-
-	if (max_uA < limits->high_start) {
-		/*
-		 * Less than high_start,
-		 * so set the minimal current (turn only Low Bit off)
-		 */
-		u8 reg_data = 0x0 << CHGCTRL4_MBCICHWRCL_SHIFT;
-		return max14577_update_reg(rdev->regmap,
-				MAX14577_CHG_REG_CHG_CTRL4,
-				CHGCTRL4_MBCICHWRCL_MASK, reg_data);
-	}
-
-	/*
-	 * max_uA is in range: <high_start, inifinite>, so search for
-	 * valid current starting from maximum current.
-	 */
-	for (i = limits->max; i >= limits->high_start; i -= limits->high_step) {
-		if (i <= max_uA)
-			break;
-		current_bits--;
-	}
-	BUG_ON(current_bits < 0); /* Cannot happen */
-
-	/* Turn Low Bit on (use range high_start-max)... */
-	reg_data = 0x1 << CHGCTRL4_MBCICHWRCL_SHIFT;
-	/* and set proper High Bits */
-	reg_data |= current_bits << CHGCTRL4_MBCICHWRCH_SHIFT;
+	ret = maxim_charger_calc_reg_current(limits, min_uA, max_uA, &reg_data);
+	if (ret)
+		return ret;
 
 	return max14577_update_reg(rdev->regmap, MAX14577_CHG_REG_CHG_CTRL4,
 			CHGCTRL4_MBCICHWRCL_MASK | CHGCTRL4_MBCICHWRCH_MASK,
@@ -442,16 +380,6 @@ static struct platform_driver max14577_regulator_driver = {
 
 static int __init max14577_regulator_init(void)
 {
-	/* Check for valid values for charger */
-	BUILD_BUG_ON(MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_START +
-			MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_STEP * 0xf !=
-			MAX14577_REGULATOR_CURRENT_LIMIT_MAX);
-	BUILD_BUG_ON(MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_START +
-			MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_STEP * 0xf !=
-			MAX77836_REGULATOR_CURRENT_LIMIT_MAX);
-	/* Valid charger current values must be provided for each chipset */
-	BUILD_BUG_ON(ARRAY_SIZE(maxim_charger_currents) != MAXIM_DEVICE_TYPE_NUM);
-
 	BUILD_BUG_ON(ARRAY_SIZE(max14577_supported_regulators) != MAX14577_REGULATOR_NUM);
 	BUILD_BUG_ON(ARRAY_SIZE(max77836_supported_regulators) != MAX77836_REGULATOR_NUM);
 
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 1bea0fc43464..8cd0beebdc3f 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -288,6 +288,26 @@ config RTC_DRV_MAX77686
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-max77686.
 
+config RTC_DRV_RK808
+	tristate "Rockchip RK808 RTC"
+	depends on MFD_RK808
+	help
+	  If you say yes here you will get support for the
+	  RTC of RK808 PMIC.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rk808-rtc.
+
+config RTC_DRV_MAX77802
+	tristate "Maxim 77802 RTC"
+	depends on MFD_MAX77686
+	help
+	  If you say yes here you will get support for the
+	  RTC of Maxim MAX77802 PMIC.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-max77802.
+
 config RTC_DRV_RS5C372
 	tristate "Ricoh R2025S/D, RS5C372A/B, RV5C386, RV5C387A"
 	help
@@ -732,6 +752,7 @@ config RTC_DRV_DS1216
 
 config RTC_DRV_DS1286
 	tristate "Dallas DS1286"
+	depends on HAS_IOMEM
 	help
 	  If you say yes here you get support for the Dallas DS1286 RTC chips.
 
@@ -743,6 +764,7 @@ config RTC_DRV_DS1302
 
 config RTC_DRV_DS1511
 	tristate "Dallas DS1511"
+	depends on HAS_IOMEM
 	help
 	  If you say yes here you get support for the
 	  Dallas DS1511 timekeeping/watchdog chip.
@@ -752,6 +774,7 @@ config RTC_DRV_DS1511
 
 config RTC_DRV_DS1553
 	tristate "Maxim/Dallas DS1553"
+	depends on HAS_IOMEM
 	help
 	  If you say yes here you get support for the
 	  Maxim/Dallas DS1553 timekeeping chip.
@@ -761,6 +784,7 @@ config RTC_DRV_DS1553
 
 config RTC_DRV_DS1742
 	tristate "Maxim/Dallas DS1742/1743"
+	depends on HAS_IOMEM
 	help
 	  If you say yes here you get support for the
 	  Maxim/Dallas DS1742/1743 timekeeping chip.
@@ -816,6 +840,7 @@ config RTC_DRV_EFI
 
 config RTC_DRV_STK17TA8
 	tristate "Simtek STK17TA8"
+	depends on HAS_IOMEM
 	help
 	  If you say yes here you get support for the
 	  Simtek STK17TA8 timekeeping chip.
@@ -834,6 +859,7 @@ config RTC_DRV_M48T86
 
 config RTC_DRV_M48T35
 	tristate "ST M48T35"
+	depends on HAS_IOMEM
 	help
 	  If you say Y here you will get support for the
 	  ST M48T35 RTC chip.
@@ -843,6 +869,7 @@ config RTC_DRV_M48T35
 
 config RTC_DRV_M48T59
 	tristate "ST M48T59/M48T08/M48T02"
+	depends on HAS_IOMEM
 	help
 	  If you say Y here you will get support for the
 	  ST M48T59 RTC chip and compatible ST M48T08 and M48T02.
@@ -855,6 +882,7 @@ config RTC_DRV_M48T59
 
 config RTC_DRV_MSM6242
 	tristate "Oki MSM6242"
+	depends on HAS_IOMEM
 	help
 	  If you say yes here you get support for the Oki MSM6242
 	  timekeeping chip. It is used in some Amiga models (e.g. A2000).
@@ -864,6 +892,7 @@ config RTC_DRV_MSM6242
 
 config RTC_DRV_BQ4802
 	tristate "TI BQ4802"
+	depends on HAS_IOMEM
 	help
 	  If you say Y here you will get support for the TI
 	  BQ4802 RTC chip.
@@ -873,6 +902,7 @@ config RTC_DRV_BQ4802
 
 config RTC_DRV_RP5C01
 	tristate "Ricoh RP5C01"
+	depends on HAS_IOMEM
 	help
 	  If you say yes here you get support for the Ricoh RP5C01
 	  timekeeping chip. It is used in some Amiga models (e.g. A3000
@@ -1374,6 +1404,7 @@ config RTC_DRV_MOXART
 
 config RTC_DRV_XGENE
 	tristate "APM X-Gene RTC"
+	depends on HAS_IOMEM
 	help
 	  If you say yes here you get support for the APM X-Gene SoC real time
 	  clock.
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 9055b7dd3dc5..b188323c096a 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -85,6 +85,7 @@ obj-$(CONFIG_RTC_DRV_MAX8998)	+= rtc-max8998.o
 obj-$(CONFIG_RTC_DRV_MAX8997)	+= rtc-max8997.o
 obj-$(CONFIG_RTC_DRV_MAX6902)	+= rtc-max6902.o
 obj-$(CONFIG_RTC_DRV_MAX77686)	+= rtc-max77686.o
+obj-$(CONFIG_RTC_DRV_MAX77802)  += rtc-max77802.o
 obj-$(CONFIG_RTC_DRV_MC13XXX)	+= rtc-mc13xxx.o
 obj-$(CONFIG_RTC_DRV_MCP795)	+= rtc-mcp795.o
 obj-$(CONFIG_RTC_DRV_MSM6242)	+= rtc-msm6242.o
@@ -109,6 +110,7 @@ obj-$(CONFIG_RTC_DRV_PUV3)	+= rtc-puv3.o
 obj-$(CONFIG_RTC_DRV_PXA)	+= rtc-pxa.o
 obj-$(CONFIG_RTC_DRV_R9701)	+= rtc-r9701.o
 obj-$(CONFIG_RTC_DRV_RC5T583)	+= rtc-rc5t583.o
+obj-$(CONFIG_RTC_DRV_RK808)	+= rtc-rk808.o
 obj-$(CONFIG_RTC_DRV_RP5C01)	+= rtc-rp5c01.o
 obj-$(CONFIG_RTC_DRV_RS5C313)	+= rtc-rs5c313.o
 obj-$(CONFIG_RTC_DRV_RS5C348)	+= rtc-rs5c348.o
diff --git a/drivers/rtc/rtc-bq32k.c b/drivers/rtc/rtc-bq32k.c
index c74bf0dc52cc..314129e66d6e 100644
--- a/drivers/rtc/rtc-bq32k.c
+++ b/drivers/rtc/rtc-bq32k.c
@@ -2,10 +2,14 @@
  * Driver for TI BQ32000 RTC.
  *
  * Copyright (C) 2009 Semihalf.
+ * Copyright (C) 2014 Pavel Machek <pavel@denx.de>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
+ *
+ * You can get hardware description at
+ * http://www.ti.com/lit/ds/symlink/bq32000.pdf
  */
 
 #include <linux/module.h>
@@ -27,6 +31,10 @@
 #define BQ32K_CENT		0x40	/* Century flag */
 #define BQ32K_CENT_EN		0x80	/* Century flag enable bit */
 
+#define BQ32K_CALIBRATION	0x07	/* CAL_CFG1, calibration and control */
+#define BQ32K_TCH2		0x08	/* Trickle charge enable */
+#define BQ32K_CFG2		0x09	/* Trickle charger control */
+
 struct bq32k_regs {
 	uint8_t		seconds;
 	uint8_t		minutes;
@@ -122,6 +130,57 @@ static const struct rtc_class_ops bq32k_rtc_ops = {
 	.set_time	= bq32k_rtc_set_time,
 };
 
+static int trickle_charger_of_init(struct device *dev, struct device_node *node)
+{
+	unsigned char reg;
+	int error;
+	u32 ohms = 0;
+
+	if (of_property_read_u32(node, "trickle-resistor-ohms" , &ohms))
+		return 0;
+
+	switch (ohms) {
+	case 180+940:
+		/*
+		 * TCHE[3:0] == 0x05, TCH2 == 1, TCFE == 0 (charging
+		 * over diode and 940ohm resistor)
+		 */
+
+		if (of_property_read_bool(node, "trickle-diode-disable")) {
+			dev_err(dev, "diode and resistor mismatch\n");
+			return -EINVAL;
+		}
+		reg = 0x05;
+		break;
+
+	case 180+20000:
+		/* diode disabled */
+
+		if (!of_property_read_bool(node, "trickle-diode-disable")) {
+			dev_err(dev, "bq32k: diode and resistor mismatch\n");
+			return -EINVAL;
+		}
+		reg = 0x25;
+		break;
+
+	default:
+		dev_err(dev, "invalid resistor value (%d)\n", ohms);
+		return -EINVAL;
+	}
+
+	error = bq32k_write(dev, &reg, BQ32K_CFG2, 1);
+	if (error)
+		return error;
+
+	reg = 0x20;
+	error = bq32k_write(dev, &reg, BQ32K_TCH2, 1);
+	if (error)
+		return error;
+
+	dev_info(dev, "Enabled trickle RTC battery charge.\n");
+	return 0;
+}
+
 static int bq32k_probe(struct i2c_client *client,
 				const struct i2c_device_id *id)
 {
@@ -153,6 +212,9 @@ static int bq32k_probe(struct i2c_client *client,
 	if (error)
 		return error;
 
+	if (client && client->dev.of_node)
+		trickle_charger_of_init(dev, client->dev.of_node);
+
 	rtc = devm_rtc_device_register(&client->dev, bq32k_driver.driver.name,
 						&bq32k_rtc_ops, THIS_MODULE);
 	if (IS_ERR(rtc))
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index b0e4a3eb33c7..5b2e76159b41 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -856,7 +856,7 @@ static void __exit cmos_do_remove(struct device *dev)
 	cmos->dev = NULL;
 }
 
-#ifdef	CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
 
 static int cmos_suspend(struct device *dev)
 {
@@ -907,6 +907,8 @@ static inline int cmos_poweroff(struct device *dev)
 	return cmos_suspend(dev);
 }
 
+#ifdef	CONFIG_PM_SLEEP
+
 static int cmos_resume(struct device *dev)
 {
 	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
@@ -954,6 +956,7 @@ static int cmos_resume(struct device *dev)
 	return 0;
 }
 
+#endif
 #else
 
 static inline int cmos_poweroff(struct device *dev)
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index f03d5ba96db1..bb43cf703efc 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -126,9 +126,14 @@ struct chip_desc {
 	u16			nvram_offset;
 	u16			nvram_size;
 	u16			trickle_charger_reg;
+	u8			trickle_charger_setup;
+	u8			(*do_trickle_setup)(struct i2c_client *, uint32_t, bool);
 };
 
-static const struct chip_desc chips[last_ds_type] = {
+static u8 do_trickle_setup_ds1339(struct i2c_client *,
+				  uint32_t ohms, bool diode);
+
+static struct chip_desc chips[last_ds_type] = {
 	[ds_1307] = {
 		.nvram_offset	= 8,
 		.nvram_size	= 56,
@@ -143,6 +148,7 @@ static const struct chip_desc chips[last_ds_type] = {
 	[ds_1339] = {
 		.alarm		= 1,
 		.trickle_charger_reg = 0x10,
+		.do_trickle_setup = &do_trickle_setup_ds1339,
 	},
 	[ds_1340] = {
 		.trickle_charger_reg = 0x08,
@@ -833,15 +839,58 @@ ds1307_nvram_write(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
+
 /*----------------------------------------------------------------------*/
 
+static u8 do_trickle_setup_ds1339(struct i2c_client *client,
+				  uint32_t ohms, bool diode)
+{
+	u8 setup = (diode) ? DS1307_TRICKLE_CHARGER_DIODE :
+		DS1307_TRICKLE_CHARGER_NO_DIODE;
+
+	switch (ohms) {
+	case 250:
+		setup |= DS1307_TRICKLE_CHARGER_250_OHM;
+		break;
+	case 2000:
+		setup |= DS1307_TRICKLE_CHARGER_2K_OHM;
+		break;
+	case 4000:
+		setup |= DS1307_TRICKLE_CHARGER_4K_OHM;
+		break;
+	default:
+		dev_warn(&client->dev,
+			 "Unsupported ohm value %u in dt\n", ohms);
+		return 0;
+	}
+	return setup;
+}
+
+static void ds1307_trickle_of_init(struct i2c_client *client,
+				   struct chip_desc *chip)
+{
+	uint32_t ohms = 0;
+	bool diode = true;
+
+	if (!chip->do_trickle_setup)
+		goto out;
+	if (of_property_read_u32(client->dev.of_node, "trickle-resistor-ohms" , &ohms))
+		goto out;
+	if (of_property_read_bool(client->dev.of_node, "trickle-diode-disable"))
+		diode = false;
+	chip->trickle_charger_setup = chip->do_trickle_setup(client,
+							     ohms, diode);
+out:
+	return;
+}
+
 static int ds1307_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
 	struct ds1307		*ds1307;
 	int			err = -ENODEV;
 	int			tmp;
-	const struct chip_desc	*chip = &chips[id->driver_data];
+	struct chip_desc	*chip = &chips[id->driver_data];
 	struct i2c_adapter	*adapter = to_i2c_adapter(client->dev.parent);
 	bool			want_irq = false;
 	unsigned char		*buf;
@@ -866,9 +915,19 @@ static int ds1307_probe(struct i2c_client *client,
 	ds1307->client	= client;
 	ds1307->type	= id->driver_data;
 
-	if (pdata && pdata->trickle_charger_setup && chip->trickle_charger_reg)
+	if (!pdata && client->dev.of_node)
+		ds1307_trickle_of_init(client, chip);
+	else if (pdata && pdata->trickle_charger_setup)
+		chip->trickle_charger_setup = pdata->trickle_charger_setup;
+
+	if (chip->trickle_charger_setup && chip->trickle_charger_reg) {
+		dev_dbg(&client->dev, "writing trickle charger info 0x%x to 0x%x\n",
+		    DS13XX_TRICKLE_CHARGER_MAGIC | chip->trickle_charger_setup,
+		    chip->trickle_charger_reg);
 		i2c_smbus_write_byte_data(client, chip->trickle_charger_reg,
-			DS13XX_TRICKLE_CHARGER_MAGIC | pdata->trickle_charger_setup);
+		    DS13XX_TRICKLE_CHARGER_MAGIC |
+		    chip->trickle_charger_setup);
+	}
 
 	buf = ds1307->regs;
 	if (i2c_check_functionality(adapter, I2C_FUNC_SMBUS_I2C_BLOCK)) {
diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c
index aa55f081c505..ee3ba7e6b45e 100644
--- a/drivers/rtc/rtc-isl12022.c
+++ b/drivers/rtc/rtc-isl12022.c
@@ -274,7 +274,7 @@ static int isl12022_probe(struct i2c_client *client,
 }
 
 #ifdef CONFIG_OF
-static struct of_device_id isl12022_dt_match[] = {
+static const struct of_device_id isl12022_dt_match[] = {
 	{ .compatible = "isl,isl12022" },
 	{ },
 };
diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c
index d20a7f0786eb..cf73e969c8cc 100644
--- a/drivers/rtc/rtc-max77686.c
+++ b/drivers/rtc/rtc-max77686.c
@@ -32,15 +32,6 @@
 #define RTC_UDR_MASK			(1 << RTC_UDR_SHIFT)
 #define RTC_RBUDR_SHIFT			4
 #define RTC_RBUDR_MASK			(1 << RTC_RBUDR_SHIFT)
-/* WTSR and SMPL Register */
-#define WTSRT_SHIFT			0
-#define SMPLT_SHIFT			2
-#define WTSR_EN_SHIFT			6
-#define SMPL_EN_SHIFT			7
-#define WTSRT_MASK			(3 << WTSRT_SHIFT)
-#define SMPLT_MASK			(3 << SMPLT_SHIFT)
-#define WTSR_EN_MASK			(1 << WTSR_EN_SHIFT)
-#define SMPL_EN_MASK			(1 << SMPL_EN_SHIFT)
 /* RTC Hour register */
 #define HOUR_PM_SHIFT			6
 #define HOUR_PM_MASK			(1 << HOUR_PM_SHIFT)
@@ -49,7 +40,6 @@
 #define ALARM_ENABLE_MASK		(1 << ALARM_ENABLE_SHIFT)
 
 #define MAX77686_RTC_UPDATE_DELAY	16
-#undef MAX77686_RTC_WTSR_SMPL
 
 enum {
 	RTC_SEC = 0,
@@ -80,16 +70,6 @@ enum MAX77686_RTC_OP {
 	MAX77686_RTC_READ,
 };
 
-static inline int max77686_rtc_calculate_wday(u8 shifted)
-{
-	int counter = -1;
-	while (shifted) {
-		shifted >>= 1;
-		counter++;
-	}
-	return counter;
-}
-
 static void max77686_rtc_data_to_tm(u8 *data, struct rtc_time *tm,
 				   int rtc_24hr_mode)
 {
@@ -103,7 +83,8 @@ static void max77686_rtc_data_to_tm(u8 *data, struct rtc_time *tm,
 			tm->tm_hour += 12;
 	}
 
-	tm->tm_wday = max77686_rtc_calculate_wday(data[RTC_WEEKDAY] & 0x7f);
+	/* Only a single bit is set in data[], so fls() would be equivalent */
+	tm->tm_wday = ffs(data[RTC_WEEKDAY] & 0x7f) - 1;
 	tm->tm_mday = data[RTC_DATE] & 0x1f;
 	tm->tm_mon = (data[RTC_MONTH] & 0x0f) - 1;
 	tm->tm_year = (data[RTC_YEAR] & 0x7f) + 100;
@@ -412,64 +393,6 @@ static const struct rtc_class_ops max77686_rtc_ops = {
 	.alarm_irq_enable = max77686_rtc_alarm_irq_enable,
 };
 
-#ifdef MAX77686_RTC_WTSR_SMPL
-static void max77686_rtc_enable_wtsr(struct max77686_rtc_info *info, bool enable)
-{
-	int ret;
-	unsigned int val, mask;
-
-	if (enable)
-		val = (1 << WTSR_EN_SHIFT) | (3 << WTSRT_SHIFT);
-	else
-		val = 0;
-
-	mask = WTSR_EN_MASK | WTSRT_MASK;
-
-	dev_info(info->dev, "%s: %s WTSR\n", __func__,
-			enable ? "enable" : "disable");
-
-	ret = regmap_update_bits(info->max77686->rtc_regmap,
-				 MAX77686_WTSR_SMPL_CNTL, mask, val);
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to update WTSR reg(%d)\n",
-				__func__, ret);
-		return;
-	}
-
-	max77686_rtc_update(info, MAX77686_RTC_WRITE);
-}
-
-static void max77686_rtc_enable_smpl(struct max77686_rtc_info *info, bool enable)
-{
-	int ret;
-	unsigned int val, mask;
-
-	if (enable)
-		val = (1 << SMPL_EN_SHIFT) | (0 << SMPLT_SHIFT);
-	else
-		val = 0;
-
-	mask = SMPL_EN_MASK | SMPLT_MASK;
-
-	dev_info(info->dev, "%s: %s SMPL\n", __func__,
-			enable ? "enable" : "disable");
-
-	ret = regmap_update_bits(info->max77686->rtc_regmap,
-				 MAX77686_WTSR_SMPL_CNTL, mask, val);
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to update SMPL reg(%d)\n",
-				__func__, ret);
-		return;
-	}
-
-	max77686_rtc_update(info, MAX77686_RTC_WRITE);
-
-	val = 0;
-	regmap_read(info->max77686->rtc_regmap, MAX77686_WTSR_SMPL_CNTL, &val);
-	dev_info(info->dev, "%s: WTSR_SMPL(0x%02x)\n", __func__, val);
-}
-#endif /* MAX77686_RTC_WTSR_SMPL */
-
 static int max77686_rtc_init_reg(struct max77686_rtc_info *info)
 {
 	u8 data[2];
@@ -519,19 +442,12 @@ static int max77686_rtc_probe(struct platform_device *pdev)
 		goto err_rtc;
 	}
 
-#ifdef MAX77686_RTC_WTSR_SMPL
-	max77686_rtc_enable_wtsr(info, true);
-	max77686_rtc_enable_smpl(info, true);
-#endif
-
 	device_init_wakeup(&pdev->dev, 1);
 
 	info->rtc_dev = devm_rtc_device_register(&pdev->dev, "max77686-rtc",
 					&max77686_rtc_ops, THIS_MODULE);
 
 	if (IS_ERR(info->rtc_dev)) {
-		dev_info(&pdev->dev, "%s: fail\n", __func__);
-
 		ret = PTR_ERR(info->rtc_dev);
 		dev_err(&pdev->dev, "Failed to register RTC device: %d\n", ret);
 		if (ret == 0)
@@ -539,6 +455,12 @@ static int max77686_rtc_probe(struct platform_device *pdev)
 		goto err_rtc;
 	}
 
+	if (!max77686->rtc_irq_data) {
+		ret = -EINVAL;
+		dev_err(&pdev->dev, "%s: no RTC regmap IRQ chip\n", __func__);
+		goto err_rtc;
+	}
+
 	info->virq = regmap_irq_get_virq(max77686->rtc_irq_data,
 					 MAX77686_RTCIRQ_RTCA1);
 	if (!info->virq) {
@@ -556,33 +478,33 @@ err_rtc:
 	return ret;
 }
 
-static void max77686_rtc_shutdown(struct platform_device *pdev)
+#ifdef CONFIG_PM_SLEEP
+static int max77686_rtc_suspend(struct device *dev)
 {
-#ifdef MAX77686_RTC_WTSR_SMPL
-	struct max77686_rtc_info *info = platform_get_drvdata(pdev);
-	int i;
-	u8 val = 0;
-
-	for (i = 0; i < 3; i++) {
-		max77686_rtc_enable_wtsr(info, false);
-		regmap_read(info->max77686->rtc_regmap, MAX77686_WTSR_SMPL_CNTL, &val);
-		dev_info(info->dev, "%s: WTSR_SMPL reg(0x%02x)\n", __func__,
-				val);
-		if (val & WTSR_EN_MASK) {
-			dev_emerg(info->dev, "%s: fail to disable WTSR\n",
-					__func__);
-		} else {
-			dev_info(info->dev, "%s: success to disable WTSR\n",
-					__func__);
-			break;
-		}
+	if (device_may_wakeup(dev)) {
+		struct max77686_rtc_info *info = dev_get_drvdata(dev);
+
+		return enable_irq_wake(info->virq);
 	}
 
-	/* Disable SMPL when power off */
-	max77686_rtc_enable_smpl(info, false);
-#endif /* MAX77686_RTC_WTSR_SMPL */
+	return 0;
 }
 
+static int max77686_rtc_resume(struct device *dev)
+{
+	if (device_may_wakeup(dev)) {
+		struct max77686_rtc_info *info = dev_get_drvdata(dev);
+
+		return disable_irq_wake(info->virq);
+	}
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(max77686_rtc_pm_ops,
+			 max77686_rtc_suspend, max77686_rtc_resume);
+
 static const struct platform_device_id rtc_id[] = {
 	{ "max77686-rtc", 0 },
 	{},
@@ -592,9 +514,9 @@ static struct platform_driver max77686_rtc_driver = {
 	.driver		= {
 		.name	= "max77686-rtc",
 		.owner	= THIS_MODULE,
+		.pm	= &max77686_rtc_pm_ops,
 	},
 	.probe		= max77686_rtc_probe,
-	.shutdown	= max77686_rtc_shutdown,
 	.id_table	= rtc_id,
 };
 
diff --git a/drivers/rtc/rtc-max77802.c b/drivers/rtc/rtc-max77802.c
new file mode 100644
index 000000000000..566471335b33
--- /dev/null
+++ b/drivers/rtc/rtc-max77802.c
@@ -0,0 +1,502 @@
+/*
+ * RTC driver for Maxim MAX77802
+ *
+ * Copyright (C) 2013 Google, Inc
+ *
+ * Copyright (C) 2012 Samsung Electronics Co.Ltd
+ *
+ *  based on rtc-max8997.c
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/rtc.h>
+#include <linux/delay.h>
+#include <linux/mutex.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/max77686-private.h>
+#include <linux/irqdomain.h>
+#include <linux/regmap.h>
+
+/* RTC Control Register */
+#define BCD_EN_SHIFT			0
+#define BCD_EN_MASK			(1 << BCD_EN_SHIFT)
+#define MODEL24_SHIFT			1
+#define MODEL24_MASK			(1 << MODEL24_SHIFT)
+/* RTC Update Register1 */
+#define RTC_UDR_SHIFT			0
+#define RTC_UDR_MASK			(1 << RTC_UDR_SHIFT)
+#define RTC_RBUDR_SHIFT			4
+#define RTC_RBUDR_MASK			(1 << RTC_RBUDR_SHIFT)
+/* RTC Hour register */
+#define HOUR_PM_SHIFT			6
+#define HOUR_PM_MASK			(1 << HOUR_PM_SHIFT)
+/* RTC Alarm Enable */
+#define ALARM_ENABLE_SHIFT		7
+#define ALARM_ENABLE_MASK		(1 << ALARM_ENABLE_SHIFT)
+
+/* For the RTCAE1 register, we write this value to enable the alarm */
+#define ALARM_ENABLE_VALUE		0x77
+
+#define MAX77802_RTC_UPDATE_DELAY_US	200
+
+enum {
+	RTC_SEC = 0,
+	RTC_MIN,
+	RTC_HOUR,
+	RTC_WEEKDAY,
+	RTC_MONTH,
+	RTC_YEAR,
+	RTC_DATE,
+	RTC_NR_TIME
+};
+
+struct max77802_rtc_info {
+	struct device		*dev;
+	struct max77686_dev	*max77802;
+	struct i2c_client	*rtc;
+	struct rtc_device	*rtc_dev;
+	struct mutex		lock;
+
+	struct regmap		*regmap;
+
+	int virq;
+	int rtc_24hr_mode;
+};
+
+enum MAX77802_RTC_OP {
+	MAX77802_RTC_WRITE,
+	MAX77802_RTC_READ,
+};
+
+static void max77802_rtc_data_to_tm(u8 *data, struct rtc_time *tm,
+				   int rtc_24hr_mode)
+{
+	tm->tm_sec = data[RTC_SEC] & 0xff;
+	tm->tm_min = data[RTC_MIN] & 0xff;
+	if (rtc_24hr_mode)
+		tm->tm_hour = data[RTC_HOUR] & 0x1f;
+	else {
+		tm->tm_hour = data[RTC_HOUR] & 0x0f;
+		if (data[RTC_HOUR] & HOUR_PM_MASK)
+			tm->tm_hour += 12;
+	}
+
+	/* Only a single bit is set in data[], so fls() would be equivalent */
+	tm->tm_wday = ffs(data[RTC_WEEKDAY] & 0xff) - 1;
+	tm->tm_mday = data[RTC_DATE] & 0x1f;
+	tm->tm_mon = (data[RTC_MONTH] & 0x0f) - 1;
+
+	tm->tm_year = data[RTC_YEAR] & 0xff;
+	tm->tm_yday = 0;
+	tm->tm_isdst = 0;
+}
+
+static int max77802_rtc_tm_to_data(struct rtc_time *tm, u8 *data)
+{
+	data[RTC_SEC] = tm->tm_sec;
+	data[RTC_MIN] = tm->tm_min;
+	data[RTC_HOUR] = tm->tm_hour;
+	data[RTC_WEEKDAY] = 1 << tm->tm_wday;
+	data[RTC_DATE] = tm->tm_mday;
+	data[RTC_MONTH] = tm->tm_mon + 1;
+	data[RTC_YEAR] = tm->tm_year;
+
+	return 0;
+}
+
+static int max77802_rtc_update(struct max77802_rtc_info *info,
+	enum MAX77802_RTC_OP op)
+{
+	int ret;
+	unsigned int data;
+
+	if (op == MAX77802_RTC_WRITE)
+		data = 1 << RTC_UDR_SHIFT;
+	else
+		data = 1 << RTC_RBUDR_SHIFT;
+
+	ret = regmap_update_bits(info->max77802->regmap,
+				 MAX77802_RTC_UPDATE0, data, data);
+	if (ret < 0)
+		dev_err(info->dev, "%s: fail to write update reg(ret=%d, data=0x%x)\n",
+				__func__, ret, data);
+	else {
+		/* Minimum delay required before RTC update. */
+		usleep_range(MAX77802_RTC_UPDATE_DELAY_US,
+			     MAX77802_RTC_UPDATE_DELAY_US * 2);
+	}
+
+	return ret;
+}
+
+static int max77802_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct max77802_rtc_info *info = dev_get_drvdata(dev);
+	u8 data[RTC_NR_TIME];
+	int ret;
+
+	mutex_lock(&info->lock);
+
+	ret = max77802_rtc_update(info, MAX77802_RTC_READ);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_bulk_read(info->max77802->regmap,
+				MAX77802_RTC_SEC, data, RTC_NR_TIME);
+	if (ret < 0) {
+		dev_err(info->dev, "%s: fail to read time reg(%d)\n", __func__,
+			ret);
+		goto out;
+	}
+
+	max77802_rtc_data_to_tm(data, tm, info->rtc_24hr_mode);
+
+	ret = rtc_valid_tm(tm);
+
+out:
+	mutex_unlock(&info->lock);
+	return ret;
+}
+
+static int max77802_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct max77802_rtc_info *info = dev_get_drvdata(dev);
+	u8 data[RTC_NR_TIME];
+	int ret;
+
+	ret = max77802_rtc_tm_to_data(tm, data);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&info->lock);
+
+	ret = regmap_bulk_write(info->max77802->regmap,
+				 MAX77802_RTC_SEC, data, RTC_NR_TIME);
+	if (ret < 0) {
+		dev_err(info->dev, "%s: fail to write time reg(%d)\n", __func__,
+			ret);
+		goto out;
+	}
+
+	ret = max77802_rtc_update(info, MAX77802_RTC_WRITE);
+
+out:
+	mutex_unlock(&info->lock);
+	return ret;
+}
+
+static int max77802_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct max77802_rtc_info *info = dev_get_drvdata(dev);
+	u8 data[RTC_NR_TIME];
+	unsigned int val;
+	int ret;
+
+	mutex_lock(&info->lock);
+
+	ret = max77802_rtc_update(info, MAX77802_RTC_READ);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_bulk_read(info->max77802->regmap,
+				 MAX77802_ALARM1_SEC, data, RTC_NR_TIME);
+	if (ret < 0) {
+		dev_err(info->dev, "%s:%d fail to read alarm reg(%d)\n",
+				__func__, __LINE__, ret);
+		goto out;
+	}
+
+	max77802_rtc_data_to_tm(data, &alrm->time, info->rtc_24hr_mode);
+
+	alrm->enabled = 0;
+	ret = regmap_read(info->max77802->regmap,
+			  MAX77802_RTC_AE1, &val);
+	if (ret < 0) {
+		dev_err(info->dev, "%s:%d fail to read alarm enable(%d)\n",
+			__func__, __LINE__, ret);
+		goto out;
+	}
+	if (val)
+		alrm->enabled = 1;
+
+	alrm->pending = 0;
+	ret = regmap_read(info->max77802->regmap, MAX77802_REG_STATUS2, &val);
+	if (ret < 0) {
+		dev_err(info->dev, "%s:%d fail to read status2 reg(%d)\n",
+				__func__, __LINE__, ret);
+		goto out;
+	}
+
+	if (val & (1 << 2)) /* RTCA1 */
+		alrm->pending = 1;
+
+out:
+	mutex_unlock(&info->lock);
+	return 0;
+}
+
+static int max77802_rtc_stop_alarm(struct max77802_rtc_info *info)
+{
+	int ret;
+
+	if (!mutex_is_locked(&info->lock))
+		dev_warn(info->dev, "%s: should have mutex locked\n", __func__);
+
+	ret = max77802_rtc_update(info, MAX77802_RTC_READ);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_write(info->max77802->regmap,
+			   MAX77802_RTC_AE1, 0);
+	if (ret < 0) {
+		dev_err(info->dev, "%s: fail to write alarm reg(%d)\n",
+			__func__, ret);
+		goto out;
+	}
+
+	ret = max77802_rtc_update(info, MAX77802_RTC_WRITE);
+out:
+	return ret;
+}
+
+static int max77802_rtc_start_alarm(struct max77802_rtc_info *info)
+{
+	int ret;
+
+	if (!mutex_is_locked(&info->lock))
+		dev_warn(info->dev, "%s: should have mutex locked\n",
+			 __func__);
+
+	ret = max77802_rtc_update(info, MAX77802_RTC_READ);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_write(info->max77802->regmap,
+				   MAX77802_RTC_AE1,
+				   ALARM_ENABLE_VALUE);
+
+	if (ret < 0) {
+		dev_err(info->dev, "%s: fail to read alarm reg(%d)\n",
+				__func__, ret);
+		goto out;
+	}
+
+	ret = max77802_rtc_update(info, MAX77802_RTC_WRITE);
+out:
+	return ret;
+}
+
+static int max77802_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct max77802_rtc_info *info = dev_get_drvdata(dev);
+	u8 data[RTC_NR_TIME];
+	int ret;
+
+	ret = max77802_rtc_tm_to_data(&alrm->time, data);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&info->lock);
+
+	ret = max77802_rtc_stop_alarm(info);
+	if (ret < 0)
+		goto out;
+
+	ret = regmap_bulk_write(info->max77802->regmap,
+				 MAX77802_ALARM1_SEC, data, RTC_NR_TIME);
+
+	if (ret < 0) {
+		dev_err(info->dev, "%s: fail to write alarm reg(%d)\n",
+				__func__, ret);
+		goto out;
+	}
+
+	ret = max77802_rtc_update(info, MAX77802_RTC_WRITE);
+	if (ret < 0)
+		goto out;
+
+	if (alrm->enabled)
+		ret = max77802_rtc_start_alarm(info);
+out:
+	mutex_unlock(&info->lock);
+	return ret;
+}
+
+static int max77802_rtc_alarm_irq_enable(struct device *dev,
+					 unsigned int enabled)
+{
+	struct max77802_rtc_info *info = dev_get_drvdata(dev);
+	int ret;
+
+	mutex_lock(&info->lock);
+	if (enabled)
+		ret = max77802_rtc_start_alarm(info);
+	else
+		ret = max77802_rtc_stop_alarm(info);
+	mutex_unlock(&info->lock);
+
+	return ret;
+}
+
+static irqreturn_t max77802_rtc_alarm_irq(int irq, void *data)
+{
+	struct max77802_rtc_info *info = data;
+
+	dev_dbg(info->dev, "%s:irq(%d)\n", __func__, irq);
+
+	rtc_update_irq(info->rtc_dev, 1, RTC_IRQF | RTC_AF);
+
+	return IRQ_HANDLED;
+}
+
+static const struct rtc_class_ops max77802_rtc_ops = {
+	.read_time = max77802_rtc_read_time,
+	.set_time = max77802_rtc_set_time,
+	.read_alarm = max77802_rtc_read_alarm,
+	.set_alarm = max77802_rtc_set_alarm,
+	.alarm_irq_enable = max77802_rtc_alarm_irq_enable,
+};
+
+static int max77802_rtc_init_reg(struct max77802_rtc_info *info)
+{
+	u8 data[2];
+	int ret;
+
+	max77802_rtc_update(info, MAX77802_RTC_READ);
+
+	/* Set RTC control register : Binary mode, 24hour mdoe */
+	data[0] = (1 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT);
+	data[1] = (0 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT);
+
+	info->rtc_24hr_mode = 1;
+
+	ret = regmap_bulk_write(info->max77802->regmap,
+				MAX77802_RTC_CONTROLM, data, ARRAY_SIZE(data));
+	if (ret < 0) {
+		dev_err(info->dev, "%s: fail to write controlm reg(%d)\n",
+				__func__, ret);
+		return ret;
+	}
+
+	ret = max77802_rtc_update(info, MAX77802_RTC_WRITE);
+	return ret;
+}
+
+static int max77802_rtc_probe(struct platform_device *pdev)
+{
+	struct max77686_dev *max77802 = dev_get_drvdata(pdev->dev.parent);
+	struct max77802_rtc_info *info;
+	int ret;
+
+	dev_dbg(&pdev->dev, "%s\n", __func__);
+
+	info = devm_kzalloc(&pdev->dev, sizeof(struct max77802_rtc_info),
+			    GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	mutex_init(&info->lock);
+	info->dev = &pdev->dev;
+	info->max77802 = max77802;
+	info->rtc = max77802->i2c;
+
+	platform_set_drvdata(pdev, info);
+
+	ret = max77802_rtc_init_reg(info);
+
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to initialize RTC reg:%d\n", ret);
+		return ret;
+	}
+
+	device_init_wakeup(&pdev->dev, 1);
+
+	info->rtc_dev = devm_rtc_device_register(&pdev->dev, "max77802-rtc",
+						 &max77802_rtc_ops, THIS_MODULE);
+
+	if (IS_ERR(info->rtc_dev)) {
+		ret = PTR_ERR(info->rtc_dev);
+		dev_err(&pdev->dev, "Failed to register RTC device: %d\n", ret);
+		if (ret == 0)
+			ret = -EINVAL;
+		return ret;
+	}
+
+	if (!max77802->rtc_irq_data) {
+		dev_err(&pdev->dev, "No RTC regmap IRQ chip\n");
+		return -EINVAL;
+	}
+
+	info->virq = regmap_irq_get_virq(max77802->rtc_irq_data,
+					 MAX77686_RTCIRQ_RTCA1);
+
+	if (info->virq <= 0) {
+		dev_err(&pdev->dev, "Failed to get virtual IRQ %d\n",
+			MAX77686_RTCIRQ_RTCA1);
+		return -EINVAL;
+	}
+
+	ret = devm_request_threaded_irq(&pdev->dev, info->virq, NULL,
+					max77802_rtc_alarm_irq, 0, "rtc-alarm1",
+					info);
+	if (ret < 0)
+		dev_err(&pdev->dev, "Failed to request alarm IRQ: %d: %d\n",
+			info->virq, ret);
+
+	return ret;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int max77802_rtc_suspend(struct device *dev)
+{
+	if (device_may_wakeup(dev)) {
+		struct max77802_rtc_info *info = dev_get_drvdata(dev);
+
+		return enable_irq_wake(info->virq);
+	}
+
+	return 0;
+}
+
+static int max77802_rtc_resume(struct device *dev)
+{
+	if (device_may_wakeup(dev)) {
+		struct max77802_rtc_info *info = dev_get_drvdata(dev);
+
+		return disable_irq_wake(info->virq);
+	}
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(max77802_rtc_pm_ops,
+			 max77802_rtc_suspend, max77802_rtc_resume);
+
+static const struct platform_device_id rtc_id[] = {
+	{ "max77802-rtc", 0 },
+	{},
+};
+
+static struct platform_driver max77802_rtc_driver = {
+	.driver		= {
+		.name	= "max77802-rtc",
+		.owner	= THIS_MODULE,
+		.pm	= &max77802_rtc_pm_ops,
+	},
+	.probe		= max77802_rtc_probe,
+	.id_table	= rtc_id,
+};
+
+module_platform_driver(max77802_rtc_driver);
+
+MODULE_DESCRIPTION("Maxim MAX77802 RTC driver");
+MODULE_AUTHOR("Simon Glass <sjg@chromium.org>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c
index dc4f14255cc3..3b965ad6f4d5 100644
--- a/drivers/rtc/rtc-mpc5121.c
+++ b/drivers/rtc/rtc-mpc5121.c
@@ -401,7 +401,7 @@ static int mpc5121_rtc_remove(struct platform_device *op)
 }
 
 #ifdef CONFIG_OF
-static struct of_device_id mpc5121_rtc_match[] = {
+static const struct of_device_id mpc5121_rtc_match[] = {
 	{ .compatible = "fsl,mpc5121-rtc", },
 	{ .compatible = "fsl,mpc5200-rtc", },
 	{},
diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c
index 5a197d9dc7e7..c2ef0a22ee94 100644
--- a/drivers/rtc/rtc-pcf8563.c
+++ b/drivers/rtc/rtc-pcf8563.c
@@ -167,8 +167,8 @@ static irqreturn_t pcf8563_irq(int irq, void *dev_id)
 	char pending;
 
 	err = pcf8563_get_alarm_mode(pcf8563->client, NULL, &pending);
-	if (err < 0)
-		return err;
+	if (err)
+		return IRQ_NONE;
 
 	if (pending) {
 		rtc_update_irq(pcf8563->rtc, 1, RTC_IRQF | RTC_AF);
diff --git a/drivers/rtc/rtc-pcf8583.c b/drivers/rtc/rtc-pcf8583.c
index c2639845186b..5911a6dca291 100644
--- a/drivers/rtc/rtc-pcf8583.c
+++ b/drivers/rtc/rtc-pcf8583.c
@@ -176,7 +176,11 @@ static int pcf8583_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	unsigned char ctrl, year[2];
-	struct rtc_mem mem = { CMOS_YEAR, sizeof(year), year };
+	struct rtc_mem mem = {
+		.loc = CMOS_YEAR,
+		.nr = sizeof(year),
+		.data = year
+	};
 	int real_year, year_offset, err;
 
 	/*
@@ -222,8 +226,16 @@ static int pcf8583_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	unsigned char year[2], chk;
-	struct rtc_mem cmos_year  = { CMOS_YEAR, sizeof(year), year };
-	struct rtc_mem cmos_check = { CMOS_CHECKSUM, 1, &chk };
+	struct rtc_mem cmos_year  = {
+		.loc = CMOS_YEAR,
+		.nr = sizeof(year),
+		.data = year
+	};
+	struct rtc_mem cmos_check = {
+		.loc = CMOS_CHECKSUM,
+		.nr = 1,
+		.data = &chk
+	};
 	unsigned int proper_year = tm->tm_year + 1900;
 	int ret;
 
diff --git a/drivers/rtc/rtc-rk808.c b/drivers/rtc/rtc-rk808.c
new file mode 100644
index 000000000000..df42257668ac
--- /dev/null
+++ b/drivers/rtc/rtc-rk808.c
@@ -0,0 +1,414 @@
+/*
+ * RTC driver for Rockchip RK808
+ *
+ * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * Author: Chris Zhong <zyw@rock-chips.com>
+ * Author: Zhang Qing <zhangqing@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/rtc.h>
+#include <linux/bcd.h>
+#include <linux/mfd/rk808.h>
+#include <linux/platform_device.h>
+#include <linux/i2c.h>
+
+/* RTC_CTRL_REG bitfields */
+#define BIT_RTC_CTRL_REG_STOP_RTC_M		BIT(0)
+
+/* RK808 has a shadowed register for saving a "frozen" RTC time.
+ * When user setting "GET_TIME" to 1, the time will save in this shadowed
+ * register. If set "READSEL" to 1, user read rtc time register, actually
+ * get the time of that moment. If we need the real time, clr this bit.
+ */
+#define BIT_RTC_CTRL_REG_RTC_GET_TIME		BIT(6)
+#define BIT_RTC_CTRL_REG_RTC_READSEL_M		BIT(7)
+#define BIT_RTC_INTERRUPTS_REG_IT_ALARM_M	BIT(3)
+#define RTC_STATUS_MASK		0xFE
+
+#define SECONDS_REG_MSK		0x7F
+#define MINUTES_REG_MAK		0x7F
+#define HOURS_REG_MSK		0x3F
+#define DAYS_REG_MSK		0x3F
+#define MONTHS_REG_MSK		0x1F
+#define YEARS_REG_MSK		0xFF
+#define WEEKS_REG_MSK		0x7
+
+/* REG_SECONDS_REG through REG_YEARS_REG is how many registers? */
+
+#define NUM_TIME_REGS	(RK808_WEEKS_REG - RK808_SECONDS_REG + 1)
+#define NUM_ALARM_REGS	(RK808_ALARM_YEARS_REG - RK808_ALARM_SECONDS_REG + 1)
+
+struct rk808_rtc {
+	struct rk808 *rk808;
+	struct rtc_device *rtc;
+	int irq;
+};
+
+/* Read current time and date in RTC */
+static int rk808_rtc_readtime(struct device *dev, struct rtc_time *tm)
+{
+	struct rk808_rtc *rk808_rtc = dev_get_drvdata(dev);
+	struct rk808 *rk808 = rk808_rtc->rk808;
+	u8 rtc_data[NUM_TIME_REGS];
+	int ret;
+
+	/* Force an update of the shadowed registers right now */
+	ret = regmap_update_bits(rk808->regmap, RK808_RTC_CTRL_REG,
+				 BIT_RTC_CTRL_REG_RTC_GET_TIME,
+				 0);
+	if (ret) {
+		dev_err(dev, "Failed to update bits rtc_ctrl: %d\n", ret);
+		return ret;
+	}
+
+	ret = regmap_update_bits(rk808->regmap, RK808_RTC_CTRL_REG,
+				 BIT_RTC_CTRL_REG_RTC_GET_TIME,
+				 BIT_RTC_CTRL_REG_RTC_GET_TIME);
+	if (ret) {
+		dev_err(dev, "Failed to update bits rtc_ctrl: %d\n", ret);
+		return ret;
+	}
+
+	ret = regmap_bulk_read(rk808->regmap, RK808_SECONDS_REG,
+			       rtc_data, NUM_TIME_REGS);
+	if (ret) {
+		dev_err(dev, "Failed to bulk read rtc_data: %d\n", ret);
+		return ret;
+	}
+
+	tm->tm_sec = bcd2bin(rtc_data[0] & SECONDS_REG_MSK);
+	tm->tm_min = bcd2bin(rtc_data[1] & MINUTES_REG_MAK);
+	tm->tm_hour = bcd2bin(rtc_data[2] & HOURS_REG_MSK);
+	tm->tm_mday = bcd2bin(rtc_data[3] & DAYS_REG_MSK);
+	tm->tm_mon = (bcd2bin(rtc_data[4] & MONTHS_REG_MSK)) - 1;
+	tm->tm_year = (bcd2bin(rtc_data[5] & YEARS_REG_MSK)) + 100;
+	tm->tm_wday = bcd2bin(rtc_data[6] & WEEKS_REG_MSK);
+	dev_dbg(dev, "RTC date/time %4d-%02d-%02d(%d) %02d:%02d:%02d\n",
+		1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday,
+		tm->tm_wday, tm->tm_hour , tm->tm_min, tm->tm_sec);
+
+	return ret;
+}
+
+/* Set current time and date in RTC */
+static int rk808_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct rk808_rtc *rk808_rtc = dev_get_drvdata(dev);
+	struct rk808 *rk808 = rk808_rtc->rk808;
+	u8 rtc_data[NUM_TIME_REGS];
+	int ret;
+
+	rtc_data[0] = bin2bcd(tm->tm_sec);
+	rtc_data[1] = bin2bcd(tm->tm_min);
+	rtc_data[2] = bin2bcd(tm->tm_hour);
+	rtc_data[3] = bin2bcd(tm->tm_mday);
+	rtc_data[4] = bin2bcd(tm->tm_mon + 1);
+	rtc_data[5] = bin2bcd(tm->tm_year - 100);
+	rtc_data[6] = bin2bcd(tm->tm_wday);
+	dev_dbg(dev, "set RTC date/time %4d-%02d-%02d(%d) %02d:%02d:%02d\n",
+		1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday,
+		tm->tm_wday, tm->tm_hour , tm->tm_min, tm->tm_sec);
+
+	/* Stop RTC while updating the RTC registers */
+	ret = regmap_update_bits(rk808->regmap, RK808_RTC_CTRL_REG,
+				 BIT_RTC_CTRL_REG_STOP_RTC_M,
+				 BIT_RTC_CTRL_REG_STOP_RTC_M);
+	if (ret) {
+		dev_err(dev, "Failed to update RTC control: %d\n", ret);
+		return ret;
+	}
+
+	ret = regmap_bulk_write(rk808->regmap, RK808_SECONDS_REG,
+				rtc_data, NUM_TIME_REGS);
+	if (ret) {
+		dev_err(dev, "Failed to bull write rtc_data: %d\n", ret);
+		return ret;
+	}
+	/* Start RTC again */
+	ret = regmap_update_bits(rk808->regmap, RK808_RTC_CTRL_REG,
+				 BIT_RTC_CTRL_REG_STOP_RTC_M, 0);
+	if (ret) {
+		dev_err(dev, "Failed to update RTC control: %d\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+/* Read alarm time and date in RTC */
+static int rk808_rtc_readalarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct rk808_rtc *rk808_rtc = dev_get_drvdata(dev);
+	struct rk808 *rk808 = rk808_rtc->rk808;
+	u8 alrm_data[NUM_ALARM_REGS];
+	uint32_t int_reg;
+	int ret;
+
+	ret = regmap_bulk_read(rk808->regmap, RK808_ALARM_SECONDS_REG,
+			       alrm_data, NUM_ALARM_REGS);
+
+	alrm->time.tm_sec = bcd2bin(alrm_data[0] & SECONDS_REG_MSK);
+	alrm->time.tm_min = bcd2bin(alrm_data[1] & MINUTES_REG_MAK);
+	alrm->time.tm_hour = bcd2bin(alrm_data[2] & HOURS_REG_MSK);
+	alrm->time.tm_mday = bcd2bin(alrm_data[3] & DAYS_REG_MSK);
+	alrm->time.tm_mon = (bcd2bin(alrm_data[4] & MONTHS_REG_MSK)) - 1;
+	alrm->time.tm_year = (bcd2bin(alrm_data[5] & YEARS_REG_MSK)) + 100;
+
+	ret = regmap_read(rk808->regmap, RK808_RTC_INT_REG, &int_reg);
+	if (ret) {
+		dev_err(dev, "Failed to read RTC INT REG: %d\n", ret);
+		return ret;
+	}
+
+	dev_dbg(dev, "alrm read RTC date/time %4d-%02d-%02d(%d) %02d:%02d:%02d\n",
+		1900 + alrm->time.tm_year, alrm->time.tm_mon + 1,
+		alrm->time.tm_mday, alrm->time.tm_wday, alrm->time.tm_hour,
+		alrm->time.tm_min, alrm->time.tm_sec);
+
+	alrm->enabled = (int_reg & BIT_RTC_INTERRUPTS_REG_IT_ALARM_M) ? 1 : 0;
+
+	return 0;
+}
+
+static int rk808_rtc_stop_alarm(struct rk808_rtc *rk808_rtc)
+{
+	struct rk808 *rk808 = rk808_rtc->rk808;
+	int ret;
+
+	ret = regmap_update_bits(rk808->regmap, RK808_RTC_INT_REG,
+				 BIT_RTC_INTERRUPTS_REG_IT_ALARM_M, 0);
+
+	return ret;
+}
+
+static int rk808_rtc_start_alarm(struct rk808_rtc *rk808_rtc)
+{
+	struct rk808 *rk808 = rk808_rtc->rk808;
+	int ret;
+
+	ret = regmap_update_bits(rk808->regmap, RK808_RTC_INT_REG,
+				 BIT_RTC_INTERRUPTS_REG_IT_ALARM_M,
+				 BIT_RTC_INTERRUPTS_REG_IT_ALARM_M);
+
+	return ret;
+}
+
+static int rk808_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct rk808_rtc *rk808_rtc = dev_get_drvdata(dev);
+	struct rk808 *rk808 = rk808_rtc->rk808;
+	u8 alrm_data[NUM_ALARM_REGS];
+	int ret;
+
+	ret = rk808_rtc_stop_alarm(rk808_rtc);
+	if (ret) {
+		dev_err(dev, "Failed to stop alarm: %d\n", ret);
+		return ret;
+	}
+	dev_dbg(dev, "alrm set RTC date/time %4d-%02d-%02d(%d) %02d:%02d:%02d\n",
+		1900 + alrm->time.tm_year, alrm->time.tm_mon + 1,
+		alrm->time.tm_mday, alrm->time.tm_wday, alrm->time.tm_hour,
+		alrm->time.tm_min, alrm->time.tm_sec);
+
+	alrm_data[0] = bin2bcd(alrm->time.tm_sec);
+	alrm_data[1] = bin2bcd(alrm->time.tm_min);
+	alrm_data[2] = bin2bcd(alrm->time.tm_hour);
+	alrm_data[3] = bin2bcd(alrm->time.tm_mday);
+	alrm_data[4] = bin2bcd(alrm->time.tm_mon + 1);
+	alrm_data[5] = bin2bcd(alrm->time.tm_year - 100);
+
+	ret = regmap_bulk_write(rk808->regmap, RK808_ALARM_SECONDS_REG,
+				alrm_data, NUM_ALARM_REGS);
+	if (ret) {
+		dev_err(dev, "Failed to bulk write: %d\n", ret);
+		return ret;
+	}
+	if (alrm->enabled) {
+		ret = rk808_rtc_start_alarm(rk808_rtc);
+		if (ret) {
+			dev_err(dev, "Failed to start alarm: %d\n", ret);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+static int rk808_rtc_alarm_irq_enable(struct device *dev,
+				      unsigned int enabled)
+{
+	struct rk808_rtc *rk808_rtc = dev_get_drvdata(dev);
+
+	if (enabled)
+		return rk808_rtc_start_alarm(rk808_rtc);
+
+	return rk808_rtc_stop_alarm(rk808_rtc);
+}
+
+/*
+ * We will just handle setting the frequency and make use the framework for
+ * reading the periodic interupts.
+ *
+ * @freq: Current periodic IRQ freq:
+ * bit 0: every second
+ * bit 1: every minute
+ * bit 2: every hour
+ * bit 3: every day
+ */
+static irqreturn_t rk808_alarm_irq(int irq, void *data)
+{
+	struct rk808_rtc *rk808_rtc = data;
+	struct rk808 *rk808 = rk808_rtc->rk808;
+	struct i2c_client *client = rk808->i2c;
+	int ret;
+
+	ret = regmap_write(rk808->regmap, RK808_RTC_STATUS_REG,
+			   RTC_STATUS_MASK);
+	if (ret) {
+		dev_err(&client->dev,
+			"%s:Failed to update RTC status: %d\n", __func__, ret);
+		return ret;
+	}
+
+	rtc_update_irq(rk808_rtc->rtc, 1, RTC_IRQF | RTC_AF);
+	dev_dbg(&client->dev,
+		 "%s:irq=%d\n", __func__, irq);
+	return IRQ_HANDLED;
+}
+
+static const struct rtc_class_ops rk808_rtc_ops = {
+	.read_time = rk808_rtc_readtime,
+	.set_time = rk808_rtc_set_time,
+	.read_alarm = rk808_rtc_readalarm,
+	.set_alarm = rk808_rtc_setalarm,
+	.alarm_irq_enable = rk808_rtc_alarm_irq_enable,
+};
+
+#ifdef CONFIG_PM_SLEEP
+/* Turn off the alarm if it should not be a wake source. */
+static int rk808_rtc_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct rk808_rtc *rk808_rtc = dev_get_drvdata(&pdev->dev);
+
+	if (device_may_wakeup(dev))
+		enable_irq_wake(rk808_rtc->irq);
+
+	return 0;
+}
+
+/* Enable the alarm if it should be enabled (in case it was disabled to
+ * prevent use as a wake source).
+ */
+static int rk808_rtc_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct rk808_rtc *rk808_rtc = dev_get_drvdata(&pdev->dev);
+
+	if (device_may_wakeup(dev))
+		disable_irq_wake(rk808_rtc->irq);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(rk808_rtc_pm_ops,
+	rk808_rtc_suspend, rk808_rtc_resume);
+
+static int rk808_rtc_probe(struct platform_device *pdev)
+{
+	struct rk808 *rk808 = dev_get_drvdata(pdev->dev.parent);
+	struct rk808_rtc *rk808_rtc;
+	struct rtc_time tm;
+	int ret;
+
+	rk808_rtc = devm_kzalloc(&pdev->dev, sizeof(*rk808_rtc), GFP_KERNEL);
+	if (rk808_rtc == NULL)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, rk808_rtc);
+	rk808_rtc->rk808 = rk808;
+
+	/* start rtc running by default, and use shadowed timer. */
+	ret = regmap_update_bits(rk808->regmap, RK808_RTC_CTRL_REG,
+				 BIT_RTC_CTRL_REG_STOP_RTC_M |
+				 BIT_RTC_CTRL_REG_RTC_READSEL_M,
+				 BIT_RTC_CTRL_REG_RTC_READSEL_M);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Failed to update RTC control: %d\n", ret);
+		return ret;
+	}
+
+	ret = regmap_write(rk808->regmap, RK808_RTC_STATUS_REG,
+			   RTC_STATUS_MASK);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Failed to write RTC status: %d\n", ret);
+			return ret;
+	}
+
+	/* set init time */
+	ret = rk808_rtc_readtime(&pdev->dev, &tm);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to read RTC time\n");
+		return ret;
+	}
+	ret = rtc_valid_tm(&tm);
+	if (ret)
+		dev_warn(&pdev->dev, "invalid date/time\n");
+
+	device_init_wakeup(&pdev->dev, 1);
+
+	rk808_rtc->rtc = devm_rtc_device_register(&pdev->dev, "rk808-rtc",
+						  &rk808_rtc_ops, THIS_MODULE);
+	if (IS_ERR(rk808_rtc->rtc)) {
+		ret = PTR_ERR(rk808_rtc->rtc);
+		return ret;
+	}
+
+	rk808_rtc->irq = platform_get_irq(pdev, 0);
+	if (rk808_rtc->irq < 0) {
+		if (rk808_rtc->irq != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "Wake up is not possible as irq = %d\n",
+				rk808_rtc->irq);
+		return rk808_rtc->irq;
+	}
+
+	/* request alarm irq of rk808 */
+	ret = devm_request_threaded_irq(&pdev->dev, rk808_rtc->irq, NULL,
+					rk808_alarm_irq, 0,
+					"RTC alarm", rk808_rtc);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to request alarm IRQ %d: %d\n",
+			rk808_rtc->irq, ret);
+	}
+
+	return ret;
+}
+
+static struct platform_driver rk808_rtc_driver = {
+	.probe = rk808_rtc_probe,
+	.driver = {
+		.name = "rk808-rtc",
+		.pm = &rk808_rtc_pm_ops,
+	},
+};
+
+module_platform_driver(rk808_rtc_driver);
+
+MODULE_DESCRIPTION("RTC driver for the rk808 series PMICs");
+MODULE_AUTHOR("Chris Zhong <zyw@rock-chips.com>");
+MODULE_AUTHOR("Zhang Qing <zhangqing@rock-chips.com>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:rk808-rtc");
diff --git a/drivers/rtc/rtc-rs5c372.c b/drivers/rtc/rtc-rs5c372.c
index ccf54f06396b..28871cd7e3b5 100644
--- a/drivers/rtc/rtc-rs5c372.c
+++ b/drivers/rtc/rtc-rs5c372.c
@@ -142,12 +142,11 @@ static int rs5c_get_regs(struct rs5c372 *rs5c)
 	}
 
 	dev_dbg(&client->dev,
-		"%02x %02x %02x (%02x) %02x %02x %02x (%02x), "
-		"%02x %02x %02x, %02x %02x %02x; %02x %02x\n",
-		rs5c->regs[0],  rs5c->regs[1],  rs5c->regs[2],  rs5c->regs[3],
-		rs5c->regs[4],  rs5c->regs[5],  rs5c->regs[6],  rs5c->regs[7],
-		rs5c->regs[8],  rs5c->regs[9],  rs5c->regs[10], rs5c->regs[11],
-		rs5c->regs[12], rs5c->regs[13], rs5c->regs[14], rs5c->regs[15]);
+		"%3ph (%02x) %3ph (%02x), %3ph, %3ph; %02x %02x\n",
+		rs5c->regs + 0, rs5c->regs[3],
+		rs5c->regs + 4, rs5c->regs[7],
+		rs5c->regs + 8, rs5c->regs + 11,
+		rs5c->regs[14], rs5c->regs[15]);
 
 	return 0;
 }
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index 4958a363b2c7..a6b1252c9941 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -32,155 +32,150 @@
 #include <asm/irq.h>
 #include "rtc-s3c.h"
 
-enum s3c_cpu_type {
-	TYPE_S3C2410,
-	TYPE_S3C2416,
-	TYPE_S3C2443,
-	TYPE_S3C64XX,
-};
+struct s3c_rtc {
+	struct device *dev;
+	struct rtc_device *rtc;
 
-struct s3c_rtc_drv_data {
-	int cpu_type;
-};
+	void __iomem *base;
+	struct clk *rtc_clk;
+	struct clk *rtc_src_clk;
+	bool enabled;
+
+	struct s3c_rtc_data *data;
 
-/* I have yet to find an S3C implementation with more than one
- * of these rtc blocks in */
+	int irq_alarm;
+	int irq_tick;
 
-static struct clk *rtc_clk;
-static void __iomem *s3c_rtc_base;
-static int s3c_rtc_alarmno;
-static int s3c_rtc_tickno;
-static enum s3c_cpu_type s3c_rtc_cpu_type;
+	spinlock_t pie_lock;
+	spinlock_t alarm_clk_lock;
 
-static DEFINE_SPINLOCK(s3c_rtc_pie_lock);
+	int ticnt_save, ticnt_en_save;
+	bool wake_en;
+};
+
+struct s3c_rtc_data {
+	int max_user_freq;
+	bool needs_src_clk;
+
+	void (*irq_handler) (struct s3c_rtc *info, int mask);
+	void (*set_freq) (struct s3c_rtc *info, int freq);
+	void (*enable_tick) (struct s3c_rtc *info, struct seq_file *seq);
+	void (*select_tick_clk) (struct s3c_rtc *info);
+	void (*save_tick_cnt) (struct s3c_rtc *info);
+	void (*restore_tick_cnt) (struct s3c_rtc *info);
+	void (*enable) (struct s3c_rtc *info);
+	void (*disable) (struct s3c_rtc *info);
+};
 
-static void s3c_rtc_alarm_clk_enable(bool enable)
+static void s3c_rtc_alarm_clk_enable(struct s3c_rtc *info, bool enable)
 {
-	static DEFINE_SPINLOCK(s3c_rtc_alarm_clk_lock);
-	static bool alarm_clk_enabled;
 	unsigned long irq_flags;
 
-	spin_lock_irqsave(&s3c_rtc_alarm_clk_lock, irq_flags);
+	spin_lock_irqsave(&info->alarm_clk_lock, irq_flags);
 	if (enable) {
-		if (!alarm_clk_enabled) {
-			clk_enable(rtc_clk);
-			alarm_clk_enabled = true;
+		if (!info->enabled) {
+			clk_enable(info->rtc_clk);
+			if (info->data->needs_src_clk)
+				clk_enable(info->rtc_src_clk);
+			info->enabled = true;
 		}
 	} else {
-		if (alarm_clk_enabled) {
-			clk_disable(rtc_clk);
-			alarm_clk_enabled = false;
+		if (info->enabled) {
+			if (info->data->needs_src_clk)
+				clk_disable(info->rtc_src_clk);
+			clk_disable(info->rtc_clk);
+			info->enabled = false;
 		}
 	}
-	spin_unlock_irqrestore(&s3c_rtc_alarm_clk_lock, irq_flags);
+	spin_unlock_irqrestore(&info->alarm_clk_lock, irq_flags);
 }
 
 /* IRQ Handlers */
-
-static irqreturn_t s3c_rtc_alarmirq(int irq, void *id)
+static irqreturn_t s3c_rtc_tickirq(int irq, void *id)
 {
-	struct rtc_device *rdev = id;
-
-	clk_enable(rtc_clk);
-	rtc_update_irq(rdev, 1, RTC_AF | RTC_IRQF);
-
-	if (s3c_rtc_cpu_type == TYPE_S3C64XX)
-		writeb(S3C2410_INTP_ALM, s3c_rtc_base + S3C2410_INTP);
-
-	clk_disable(rtc_clk);
+	struct s3c_rtc *info = (struct s3c_rtc *)id;
 
-	s3c_rtc_alarm_clk_enable(false);
+	if (info->data->irq_handler)
+		info->data->irq_handler(info, S3C2410_INTP_TIC);
 
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t s3c_rtc_tickirq(int irq, void *id)
+static irqreturn_t s3c_rtc_alarmirq(int irq, void *id)
 {
-	struct rtc_device *rdev = id;
+	struct s3c_rtc *info = (struct s3c_rtc *)id;
 
-	clk_enable(rtc_clk);
-	rtc_update_irq(rdev, 1, RTC_PF | RTC_IRQF);
+	if (info->data->irq_handler)
+		info->data->irq_handler(info, S3C2410_INTP_ALM);
 
-	if (s3c_rtc_cpu_type == TYPE_S3C64XX)
-		writeb(S3C2410_INTP_TIC, s3c_rtc_base + S3C2410_INTP);
-
-	clk_disable(rtc_clk);
 	return IRQ_HANDLED;
 }
 
 /* Update control registers */
 static int s3c_rtc_setaie(struct device *dev, unsigned int enabled)
 {
+	struct s3c_rtc *info = dev_get_drvdata(dev);
 	unsigned int tmp;
 
-	dev_dbg(dev, "%s: aie=%d\n", __func__, enabled);
+	dev_dbg(info->dev, "%s: aie=%d\n", __func__, enabled);
 
-	clk_enable(rtc_clk);
-	tmp = readb(s3c_rtc_base + S3C2410_RTCALM) & ~S3C2410_RTCALM_ALMEN;
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
+	tmp = readb(info->base + S3C2410_RTCALM) & ~S3C2410_RTCALM_ALMEN;
 
 	if (enabled)
 		tmp |= S3C2410_RTCALM_ALMEN;
 
-	writeb(tmp, s3c_rtc_base + S3C2410_RTCALM);
-	clk_disable(rtc_clk);
+	writeb(tmp, info->base + S3C2410_RTCALM);
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
 
-	s3c_rtc_alarm_clk_enable(enabled);
+	s3c_rtc_alarm_clk_enable(info, enabled);
 
 	return 0;
 }
 
-static int s3c_rtc_setfreq(struct device *dev, int freq)
+/* Set RTC frequency */
+static int s3c_rtc_setfreq(struct s3c_rtc *info, int freq)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct rtc_device *rtc_dev = platform_get_drvdata(pdev);
-	unsigned int tmp = 0;
-	int val;
-
 	if (!is_power_of_2(freq))
 		return -EINVAL;
 
-	clk_enable(rtc_clk);
-	spin_lock_irq(&s3c_rtc_pie_lock);
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
+	spin_lock_irq(&info->pie_lock);
 
-	if (s3c_rtc_cpu_type != TYPE_S3C64XX) {
-		tmp = readb(s3c_rtc_base + S3C2410_TICNT);
-		tmp &= S3C2410_TICNT_ENABLE;
-	}
+	if (info->data->set_freq)
+		info->data->set_freq(info, freq);
 
-	val = (rtc_dev->max_user_freq / freq) - 1;
-
-	if (s3c_rtc_cpu_type == TYPE_S3C2416 || s3c_rtc_cpu_type == TYPE_S3C2443) {
-		tmp |= S3C2443_TICNT_PART(val);
-		writel(S3C2443_TICNT1_PART(val), s3c_rtc_base + S3C2443_TICNT1);
-
-		if (s3c_rtc_cpu_type == TYPE_S3C2416)
-			writel(S3C2416_TICNT2_PART(val), s3c_rtc_base + S3C2416_TICNT2);
-	} else {
-		tmp |= val;
-	}
-
-	writel(tmp, s3c_rtc_base + S3C2410_TICNT);
-	spin_unlock_irq(&s3c_rtc_pie_lock);
-	clk_disable(rtc_clk);
+	spin_unlock_irq(&info->pie_lock);
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
 
 	return 0;
 }
 
 /* Time read/write */
-
 static int s3c_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm)
 {
+	struct s3c_rtc *info = dev_get_drvdata(dev);
 	unsigned int have_retried = 0;
-	void __iomem *base = s3c_rtc_base;
 
-	clk_enable(rtc_clk);
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
+
  retry_get_time:
-	rtc_tm->tm_min  = readb(base + S3C2410_RTCMIN);
-	rtc_tm->tm_hour = readb(base + S3C2410_RTCHOUR);
-	rtc_tm->tm_mday = readb(base + S3C2410_RTCDATE);
-	rtc_tm->tm_mon  = readb(base + S3C2410_RTCMON);
-	rtc_tm->tm_year = readb(base + S3C2410_RTCYEAR);
-	rtc_tm->tm_sec  = readb(base + S3C2410_RTCSEC);
+	rtc_tm->tm_min  = readb(info->base + S3C2410_RTCMIN);
+	rtc_tm->tm_hour = readb(info->base + S3C2410_RTCHOUR);
+	rtc_tm->tm_mday = readb(info->base + S3C2410_RTCDATE);
+	rtc_tm->tm_mon  = readb(info->base + S3C2410_RTCMON);
+	rtc_tm->tm_year = readb(info->base + S3C2410_RTCYEAR);
+	rtc_tm->tm_sec  = readb(info->base + S3C2410_RTCSEC);
 
 	/* the only way to work out whether the system was mid-update
 	 * when we read it is to check the second counter, and if it
@@ -207,13 +202,16 @@ static int s3c_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm)
 
 	rtc_tm->tm_mon -= 1;
 
-	clk_disable(rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
+
 	return rtc_valid_tm(rtc_tm);
 }
 
 static int s3c_rtc_settime(struct device *dev, struct rtc_time *tm)
 {
-	void __iomem *base = s3c_rtc_base;
+	struct s3c_rtc *info = dev_get_drvdata(dev);
 	int year = tm->tm_year - 100;
 
 	dev_dbg(dev, "set time %04d.%02d.%02d %02d:%02d:%02d\n",
@@ -227,33 +225,42 @@ static int s3c_rtc_settime(struct device *dev, struct rtc_time *tm)
 		return -EINVAL;
 	}
 
-	clk_enable(rtc_clk);
-	writeb(bin2bcd(tm->tm_sec),  base + S3C2410_RTCSEC);
-	writeb(bin2bcd(tm->tm_min),  base + S3C2410_RTCMIN);
-	writeb(bin2bcd(tm->tm_hour), base + S3C2410_RTCHOUR);
-	writeb(bin2bcd(tm->tm_mday), base + S3C2410_RTCDATE);
-	writeb(bin2bcd(tm->tm_mon + 1), base + S3C2410_RTCMON);
-	writeb(bin2bcd(year), base + S3C2410_RTCYEAR);
-	clk_disable(rtc_clk);
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
+
+	writeb(bin2bcd(tm->tm_sec),  info->base + S3C2410_RTCSEC);
+	writeb(bin2bcd(tm->tm_min),  info->base + S3C2410_RTCMIN);
+	writeb(bin2bcd(tm->tm_hour), info->base + S3C2410_RTCHOUR);
+	writeb(bin2bcd(tm->tm_mday), info->base + S3C2410_RTCDATE);
+	writeb(bin2bcd(tm->tm_mon + 1), info->base + S3C2410_RTCMON);
+	writeb(bin2bcd(year), info->base + S3C2410_RTCYEAR);
+
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
 
 	return 0;
 }
 
 static int s3c_rtc_getalarm(struct device *dev, struct rtc_wkalrm *alrm)
 {
+	struct s3c_rtc *info = dev_get_drvdata(dev);
 	struct rtc_time *alm_tm = &alrm->time;
-	void __iomem *base = s3c_rtc_base;
 	unsigned int alm_en;
 
-	clk_enable(rtc_clk);
-	alm_tm->tm_sec  = readb(base + S3C2410_ALMSEC);
-	alm_tm->tm_min  = readb(base + S3C2410_ALMMIN);
-	alm_tm->tm_hour = readb(base + S3C2410_ALMHOUR);
-	alm_tm->tm_mon  = readb(base + S3C2410_ALMMON);
-	alm_tm->tm_mday = readb(base + S3C2410_ALMDATE);
-	alm_tm->tm_year = readb(base + S3C2410_ALMYEAR);
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
 
-	alm_en = readb(base + S3C2410_RTCALM);
+	alm_tm->tm_sec  = readb(info->base + S3C2410_ALMSEC);
+	alm_tm->tm_min  = readb(info->base + S3C2410_ALMMIN);
+	alm_tm->tm_hour = readb(info->base + S3C2410_ALMHOUR);
+	alm_tm->tm_mon  = readb(info->base + S3C2410_ALMMON);
+	alm_tm->tm_mday = readb(info->base + S3C2410_ALMDATE);
+	alm_tm->tm_year = readb(info->base + S3C2410_ALMYEAR);
+
+	alm_en = readb(info->base + S3C2410_RTCALM);
 
 	alrm->enabled = (alm_en & S3C2410_RTCALM_ALMEN) ? 1 : 0;
 
@@ -297,65 +304,74 @@ static int s3c_rtc_getalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	else
 		alm_tm->tm_year = -1;
 
-	clk_disable(rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
+
 	return 0;
 }
 
 static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 {
+	struct s3c_rtc *info = dev_get_drvdata(dev);
 	struct rtc_time *tm = &alrm->time;
-	void __iomem *base = s3c_rtc_base;
 	unsigned int alrm_en;
 
-	clk_enable(rtc_clk);
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
+
 	dev_dbg(dev, "s3c_rtc_setalarm: %d, %04d.%02d.%02d %02d:%02d:%02d\n",
 		 alrm->enabled,
 		 1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday,
 		 tm->tm_hour, tm->tm_min, tm->tm_sec);
 
-	alrm_en = readb(base + S3C2410_RTCALM) & S3C2410_RTCALM_ALMEN;
-	writeb(0x00, base + S3C2410_RTCALM);
+	alrm_en = readb(info->base + S3C2410_RTCALM) & S3C2410_RTCALM_ALMEN;
+	writeb(0x00, info->base + S3C2410_RTCALM);
 
 	if (tm->tm_sec < 60 && tm->tm_sec >= 0) {
 		alrm_en |= S3C2410_RTCALM_SECEN;
-		writeb(bin2bcd(tm->tm_sec), base + S3C2410_ALMSEC);
+		writeb(bin2bcd(tm->tm_sec), info->base + S3C2410_ALMSEC);
 	}
 
 	if (tm->tm_min < 60 && tm->tm_min >= 0) {
 		alrm_en |= S3C2410_RTCALM_MINEN;
-		writeb(bin2bcd(tm->tm_min), base + S3C2410_ALMMIN);
+		writeb(bin2bcd(tm->tm_min), info->base + S3C2410_ALMMIN);
 	}
 
 	if (tm->tm_hour < 24 && tm->tm_hour >= 0) {
 		alrm_en |= S3C2410_RTCALM_HOUREN;
-		writeb(bin2bcd(tm->tm_hour), base + S3C2410_ALMHOUR);
+		writeb(bin2bcd(tm->tm_hour), info->base + S3C2410_ALMHOUR);
 	}
 
 	dev_dbg(dev, "setting S3C2410_RTCALM to %08x\n", alrm_en);
 
-	writeb(alrm_en, base + S3C2410_RTCALM);
+	writeb(alrm_en, info->base + S3C2410_RTCALM);
 
 	s3c_rtc_setaie(dev, alrm->enabled);
 
-	clk_disable(rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
+
 	return 0;
 }
 
 static int s3c_rtc_proc(struct device *dev, struct seq_file *seq)
 {
-	unsigned int ticnt;
+	struct s3c_rtc *info = dev_get_drvdata(dev);
 
-	clk_enable(rtc_clk);
-	if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
-		ticnt = readw(s3c_rtc_base + S3C2410_RTCCON);
-		ticnt &= S3C64XX_RTCCON_TICEN;
-	} else {
-		ticnt = readb(s3c_rtc_base + S3C2410_TICNT);
-		ticnt &= S3C2410_TICNT_ENABLE;
-	}
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
+
+	if (info->data->enable_tick)
+		info->data->enable_tick(info, seq);
+
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
 
-	seq_printf(seq, "periodic_IRQ\t: %s\n", ticnt  ? "yes" : "no");
-	clk_disable(rtc_clk);
 	return 0;
 }
 
@@ -368,152 +384,199 @@ static const struct rtc_class_ops s3c_rtcops = {
 	.alarm_irq_enable = s3c_rtc_setaie,
 };
 
-static void s3c_rtc_enable(struct platform_device *pdev, int en)
+static void s3c24xx_rtc_enable(struct s3c_rtc *info)
 {
-	void __iomem *base = s3c_rtc_base;
-	unsigned int tmp;
+	unsigned int con, tmp;
 
-	if (s3c_rtc_base == NULL)
-		return;
-
-	clk_enable(rtc_clk);
-	if (!en) {
-		tmp = readw(base + S3C2410_RTCCON);
-		if (s3c_rtc_cpu_type == TYPE_S3C64XX)
-			tmp &= ~S3C64XX_RTCCON_TICEN;
-		tmp &= ~S3C2410_RTCCON_RTCEN;
-		writew(tmp, base + S3C2410_RTCCON);
-
-		if (s3c_rtc_cpu_type != TYPE_S3C64XX) {
-			tmp = readb(base + S3C2410_TICNT);
-			tmp &= ~S3C2410_TICNT_ENABLE;
-			writeb(tmp, base + S3C2410_TICNT);
-		}
-	} else {
-		/* re-enable the device, and check it is ok */
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
 
-		if ((readw(base+S3C2410_RTCCON) & S3C2410_RTCCON_RTCEN) == 0) {
-			dev_info(&pdev->dev, "rtc disabled, re-enabling\n");
+	con = readw(info->base + S3C2410_RTCCON);
+	/* re-enable the device, and check it is ok */
+	if ((con & S3C2410_RTCCON_RTCEN) == 0) {
+		dev_info(info->dev, "rtc disabled, re-enabling\n");
 
-			tmp = readw(base + S3C2410_RTCCON);
-			writew(tmp | S3C2410_RTCCON_RTCEN,
-				base + S3C2410_RTCCON);
-		}
+		tmp = readw(info->base + S3C2410_RTCCON);
+		writew(tmp | S3C2410_RTCCON_RTCEN,
+			info->base + S3C2410_RTCCON);
+	}
 
-		if ((readw(base + S3C2410_RTCCON) & S3C2410_RTCCON_CNTSEL)) {
-			dev_info(&pdev->dev, "removing RTCCON_CNTSEL\n");
+	if (con & S3C2410_RTCCON_CNTSEL) {
+		dev_info(info->dev, "removing RTCCON_CNTSEL\n");
 
-			tmp = readw(base + S3C2410_RTCCON);
-			writew(tmp & ~S3C2410_RTCCON_CNTSEL,
-				base + S3C2410_RTCCON);
-		}
+		tmp = readw(info->base + S3C2410_RTCCON);
+		writew(tmp & ~S3C2410_RTCCON_CNTSEL,
+			info->base + S3C2410_RTCCON);
+	}
 
-		if ((readw(base + S3C2410_RTCCON) & S3C2410_RTCCON_CLKRST)) {
-			dev_info(&pdev->dev, "removing RTCCON_CLKRST\n");
+	if (con & S3C2410_RTCCON_CLKRST) {
+		dev_info(info->dev, "removing RTCCON_CLKRST\n");
 
-			tmp = readw(base + S3C2410_RTCCON);
-			writew(tmp & ~S3C2410_RTCCON_CLKRST,
-				base + S3C2410_RTCCON);
-		}
+		tmp = readw(info->base + S3C2410_RTCCON);
+		writew(tmp & ~S3C2410_RTCCON_CLKRST,
+			info->base + S3C2410_RTCCON);
 	}
-	clk_disable(rtc_clk);
+
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
 }
 
-static int s3c_rtc_remove(struct platform_device *dev)
+static void s3c24xx_rtc_disable(struct s3c_rtc *info)
 {
-	s3c_rtc_setaie(&dev->dev, 0);
+	unsigned int con;
+
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
+
+	con = readw(info->base + S3C2410_RTCCON);
+	con &= ~S3C2410_RTCCON_RTCEN;
+	writew(con, info->base + S3C2410_RTCCON);
 
-	clk_unprepare(rtc_clk);
-	rtc_clk = NULL;
+	con = readb(info->base + S3C2410_TICNT);
+	con &= ~S3C2410_TICNT_ENABLE;
+	writeb(con, info->base + S3C2410_TICNT);
+
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
+}
+
+static void s3c6410_rtc_disable(struct s3c_rtc *info)
+{
+	unsigned int con;
+
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
+
+	con = readw(info->base + S3C2410_RTCCON);
+	con &= ~S3C64XX_RTCCON_TICEN;
+	con &= ~S3C2410_RTCCON_RTCEN;
+	writew(con, info->base + S3C2410_RTCCON);
+
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
+}
+
+static int s3c_rtc_remove(struct platform_device *pdev)
+{
+	struct s3c_rtc *info = platform_get_drvdata(pdev);
+
+	s3c_rtc_setaie(info->dev, 0);
+
+	clk_unprepare(info->rtc_clk);
+	info->rtc_clk = NULL;
 
 	return 0;
 }
 
 static const struct of_device_id s3c_rtc_dt_match[];
 
-static inline int s3c_rtc_get_driver_data(struct platform_device *pdev)
+static struct s3c_rtc_data *s3c_rtc_get_data(struct platform_device *pdev)
 {
-#ifdef CONFIG_OF
-	struct s3c_rtc_drv_data *data;
-	if (pdev->dev.of_node) {
-		const struct of_device_id *match;
-		match = of_match_node(s3c_rtc_dt_match, pdev->dev.of_node);
-		data = (struct s3c_rtc_drv_data *) match->data;
-		return data->cpu_type;
-	}
-#endif
-	return platform_get_device_id(pdev)->driver_data;
+	const struct of_device_id *match;
+
+	match = of_match_node(s3c_rtc_dt_match, pdev->dev.of_node);
+	return (struct s3c_rtc_data *)match->data;
 }
 
 static int s3c_rtc_probe(struct platform_device *pdev)
 {
-	struct rtc_device *rtc;
+	struct s3c_rtc *info = NULL;
 	struct rtc_time rtc_tm;
 	struct resource *res;
 	int ret;
-	int tmp;
 
-	dev_dbg(&pdev->dev, "%s: probe=%p\n", __func__, pdev);
+	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
 
 	/* find the IRQs */
-
-	s3c_rtc_tickno = platform_get_irq(pdev, 1);
-	if (s3c_rtc_tickno < 0) {
+	info->irq_tick = platform_get_irq(pdev, 1);
+	if (info->irq_tick < 0) {
 		dev_err(&pdev->dev, "no irq for rtc tick\n");
-		return s3c_rtc_tickno;
+		return info->irq_tick;
+	}
+
+	info->dev = &pdev->dev;
+	info->data = s3c_rtc_get_data(pdev);
+	if (!info->data) {
+		dev_err(&pdev->dev, "failed getting s3c_rtc_data\n");
+		return -EINVAL;
 	}
+	spin_lock_init(&info->pie_lock);
+	spin_lock_init(&info->alarm_clk_lock);
+
+	platform_set_drvdata(pdev, info);
 
-	s3c_rtc_alarmno = platform_get_irq(pdev, 0);
-	if (s3c_rtc_alarmno < 0) {
+	info->irq_alarm = platform_get_irq(pdev, 0);
+	if (info->irq_alarm < 0) {
 		dev_err(&pdev->dev, "no irq for alarm\n");
-		return s3c_rtc_alarmno;
+		return info->irq_alarm;
 	}
 
 	dev_dbg(&pdev->dev, "s3c2410_rtc: tick irq %d, alarm irq %d\n",
-		 s3c_rtc_tickno, s3c_rtc_alarmno);
+		 info->irq_tick, info->irq_alarm);
 
 	/* get the memory region */
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	s3c_rtc_base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(s3c_rtc_base))
-		return PTR_ERR(s3c_rtc_base);
-
-	rtc_clk = devm_clk_get(&pdev->dev, "rtc");
-	if (IS_ERR(rtc_clk)) {
-		dev_err(&pdev->dev, "failed to find rtc clock source\n");
-		ret = PTR_ERR(rtc_clk);
-		rtc_clk = NULL;
-		return ret;
+	info->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(info->base))
+		return PTR_ERR(info->base);
+
+	info->rtc_clk = devm_clk_get(&pdev->dev, "rtc");
+	if (IS_ERR(info->rtc_clk)) {
+		dev_err(&pdev->dev, "failed to find rtc clock\n");
+		return PTR_ERR(info->rtc_clk);
 	}
+	clk_prepare_enable(info->rtc_clk);
 
-	clk_prepare_enable(rtc_clk);
+	info->rtc_src_clk = devm_clk_get(&pdev->dev, "rtc_src");
+	if (IS_ERR(info->rtc_src_clk)) {
+		dev_err(&pdev->dev, "failed to find rtc source clock\n");
+		return PTR_ERR(info->rtc_src_clk);
+	}
+	clk_prepare_enable(info->rtc_src_clk);
 
-	/* check to see if everything is setup correctly */
 
-	s3c_rtc_enable(pdev, 1);
+	/* check to see if everything is setup correctly */
+	if (info->data->enable)
+		info->data->enable(info);
 
 	dev_dbg(&pdev->dev, "s3c2410_rtc: RTCCON=%02x\n",
-		 readw(s3c_rtc_base + S3C2410_RTCCON));
+		 readw(info->base + S3C2410_RTCCON));
 
 	device_init_wakeup(&pdev->dev, 1);
 
 	/* register RTC and exit */
-
-	rtc = devm_rtc_device_register(&pdev->dev, "s3c", &s3c_rtcops,
+	info->rtc = devm_rtc_device_register(&pdev->dev, "s3c", &s3c_rtcops,
 				  THIS_MODULE);
-
-	if (IS_ERR(rtc)) {
+	if (IS_ERR(info->rtc)) {
 		dev_err(&pdev->dev, "cannot attach rtc\n");
-		ret = PTR_ERR(rtc);
+		ret = PTR_ERR(info->rtc);
 		goto err_nortc;
 	}
 
-	s3c_rtc_cpu_type = s3c_rtc_get_driver_data(pdev);
+	ret = devm_request_irq(&pdev->dev, info->irq_alarm, s3c_rtc_alarmirq,
+			  0,  "s3c2410-rtc alarm", info);
+	if (ret) {
+		dev_err(&pdev->dev, "IRQ%d error %d\n", info->irq_alarm, ret);
+		goto err_nortc;
+	}
 
-	/* Check RTC Time */
+	ret = devm_request_irq(&pdev->dev, info->irq_tick, s3c_rtc_tickirq,
+			  0,  "s3c2410-rtc tick", info);
+	if (ret) {
+		dev_err(&pdev->dev, "IRQ%d error %d\n", info->irq_tick, ret);
+		goto err_nortc;
+	}
 
-	s3c_rtc_gettime(NULL, &rtc_tm);
+	/* Check RTC Time */
+	s3c_rtc_gettime(&pdev->dev, &rtc_tm);
 
 	if (rtc_valid_tm(&rtc_tm)) {
 		rtc_tm.tm_year	= 100;
@@ -523,163 +586,312 @@ static int s3c_rtc_probe(struct platform_device *pdev)
 		rtc_tm.tm_min	= 0;
 		rtc_tm.tm_sec	= 0;
 
-		s3c_rtc_settime(NULL, &rtc_tm);
+		s3c_rtc_settime(&pdev->dev, &rtc_tm);
 
 		dev_warn(&pdev->dev, "warning: invalid RTC value so initializing it\n");
 	}
 
-	if (s3c_rtc_cpu_type != TYPE_S3C2410)
-		rtc->max_user_freq = 32768;
-	else
-		rtc->max_user_freq = 128;
-
-	if (s3c_rtc_cpu_type == TYPE_S3C2416 || s3c_rtc_cpu_type == TYPE_S3C2443) {
-		tmp = readw(s3c_rtc_base + S3C2410_RTCCON);
-		tmp |= S3C2443_RTCCON_TICSEL;
-		writew(tmp, s3c_rtc_base + S3C2410_RTCCON);
-	}
+	if (info->data->select_tick_clk)
+		info->data->select_tick_clk(info);
 
-	platform_set_drvdata(pdev, rtc);
+	s3c_rtc_setfreq(info, 1);
 
-	s3c_rtc_setfreq(&pdev->dev, 1);
-
-	ret = devm_request_irq(&pdev->dev, s3c_rtc_alarmno, s3c_rtc_alarmirq,
-			  0,  "s3c2410-rtc alarm", rtc);
-	if (ret) {
-		dev_err(&pdev->dev, "IRQ%d error %d\n", s3c_rtc_alarmno, ret);
-		goto err_nortc;
-	}
-
-	ret = devm_request_irq(&pdev->dev, s3c_rtc_tickno, s3c_rtc_tickirq,
-			  0,  "s3c2410-rtc tick", rtc);
-	if (ret) {
-		dev_err(&pdev->dev, "IRQ%d error %d\n", s3c_rtc_tickno, ret);
-		goto err_nortc;
-	}
-
-	clk_disable(rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
 
 	return 0;
 
  err_nortc:
-	s3c_rtc_enable(pdev, 0);
-	clk_disable_unprepare(rtc_clk);
+	if (info->data->disable)
+		info->data->disable(info);
+	clk_disable_unprepare(info->rtc_clk);
 
 	return ret;
 }
 
 #ifdef CONFIG_PM_SLEEP
-/* RTC Power management control */
-
-static int ticnt_save, ticnt_en_save;
-static bool wake_en;
 
 static int s3c_rtc_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
+	struct s3c_rtc *info = dev_get_drvdata(dev);
+
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
 
-	clk_enable(rtc_clk);
 	/* save TICNT for anyone using periodic interrupts */
-	if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
-		ticnt_en_save = readw(s3c_rtc_base + S3C2410_RTCCON);
-		ticnt_en_save &= S3C64XX_RTCCON_TICEN;
-		ticnt_save = readl(s3c_rtc_base + S3C2410_TICNT);
-	} else {
-		ticnt_save = readb(s3c_rtc_base + S3C2410_TICNT);
-	}
-	s3c_rtc_enable(pdev, 0);
+	if (info->data->save_tick_cnt)
+		info->data->save_tick_cnt(info);
+
+	if (info->data->disable)
+		info->data->disable(info);
 
-	if (device_may_wakeup(dev) && !wake_en) {
-		if (enable_irq_wake(s3c_rtc_alarmno) == 0)
-			wake_en = true;
+	if (device_may_wakeup(dev) && !info->wake_en) {
+		if (enable_irq_wake(info->irq_alarm) == 0)
+			info->wake_en = true;
 		else
 			dev_err(dev, "enable_irq_wake failed\n");
 	}
-	clk_disable(rtc_clk);
+
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
 
 	return 0;
 }
 
 static int s3c_rtc_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	unsigned int tmp;
+	struct s3c_rtc *info = dev_get_drvdata(dev);
 
-	clk_enable(rtc_clk);
-	s3c_rtc_enable(pdev, 1);
-	if (s3c_rtc_cpu_type == TYPE_S3C64XX) {
-		writel(ticnt_save, s3c_rtc_base + S3C2410_TICNT);
-		if (ticnt_en_save) {
-			tmp = readw(s3c_rtc_base + S3C2410_RTCCON);
-			writew(tmp | ticnt_en_save,
-					s3c_rtc_base + S3C2410_RTCCON);
-		}
-	} else {
-		writeb(ticnt_save, s3c_rtc_base + S3C2410_TICNT);
-	}
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
 
-	if (device_may_wakeup(dev) && wake_en) {
-		disable_irq_wake(s3c_rtc_alarmno);
-		wake_en = false;
+	if (info->data->enable)
+		info->data->enable(info);
+
+	if (info->data->restore_tick_cnt)
+		info->data->restore_tick_cnt(info);
+
+	if (device_may_wakeup(dev) && info->wake_en) {
+		disable_irq_wake(info->irq_alarm);
+		info->wake_en = false;
 	}
-	clk_disable(rtc_clk);
+
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
 
 	return 0;
 }
 #endif
-
 static SIMPLE_DEV_PM_OPS(s3c_rtc_pm_ops, s3c_rtc_suspend, s3c_rtc_resume);
 
-#ifdef CONFIG_OF
-static struct s3c_rtc_drv_data s3c_rtc_drv_data_array[] = {
-	[TYPE_S3C2410] = { TYPE_S3C2410 },
-	[TYPE_S3C2416] = { TYPE_S3C2416 },
-	[TYPE_S3C2443] = { TYPE_S3C2443 },
-	[TYPE_S3C64XX] = { TYPE_S3C64XX },
+static void s3c24xx_rtc_irq(struct s3c_rtc *info, int mask)
+{
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
+	rtc_update_irq(info->rtc, 1, RTC_AF | RTC_IRQF);
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
+
+	s3c_rtc_alarm_clk_enable(info, false);
+}
+
+static void s3c6410_rtc_irq(struct s3c_rtc *info, int mask)
+{
+	clk_enable(info->rtc_clk);
+	if (info->data->needs_src_clk)
+		clk_enable(info->rtc_src_clk);
+	rtc_update_irq(info->rtc, 1, RTC_AF | RTC_IRQF);
+	writeb(mask, info->base + S3C2410_INTP);
+	if (info->data->needs_src_clk)
+		clk_disable(info->rtc_src_clk);
+	clk_disable(info->rtc_clk);
+
+	s3c_rtc_alarm_clk_enable(info, false);
+}
+
+static void s3c2410_rtc_setfreq(struct s3c_rtc *info, int freq)
+{
+	unsigned int tmp = 0;
+	int val;
+
+	tmp = readb(info->base + S3C2410_TICNT);
+	tmp &= S3C2410_TICNT_ENABLE;
+
+	val = (info->rtc->max_user_freq / freq) - 1;
+	tmp |= val;
+
+	writel(tmp, info->base + S3C2410_TICNT);
+}
+
+static void s3c2416_rtc_setfreq(struct s3c_rtc *info, int freq)
+{
+	unsigned int tmp = 0;
+	int val;
+
+	tmp = readb(info->base + S3C2410_TICNT);
+	tmp &= S3C2410_TICNT_ENABLE;
+
+	val = (info->rtc->max_user_freq / freq) - 1;
+
+	tmp |= S3C2443_TICNT_PART(val);
+	writel(S3C2443_TICNT1_PART(val), info->base + S3C2443_TICNT1);
+
+	writel(S3C2416_TICNT2_PART(val), info->base + S3C2416_TICNT2);
+
+	writel(tmp, info->base + S3C2410_TICNT);
+}
+
+static void s3c2443_rtc_setfreq(struct s3c_rtc *info, int freq)
+{
+	unsigned int tmp = 0;
+	int val;
+
+	tmp = readb(info->base + S3C2410_TICNT);
+	tmp &= S3C2410_TICNT_ENABLE;
+
+	val = (info->rtc->max_user_freq / freq) - 1;
+
+	tmp |= S3C2443_TICNT_PART(val);
+	writel(S3C2443_TICNT1_PART(val), info->base + S3C2443_TICNT1);
+
+	writel(tmp, info->base + S3C2410_TICNT);
+}
+
+static void s3c6410_rtc_setfreq(struct s3c_rtc *info, int freq)
+{
+	int val;
+
+	val = (info->rtc->max_user_freq / freq) - 1;
+	writel(val, info->base + S3C2410_TICNT);
+}
+
+static void s3c24xx_rtc_enable_tick(struct s3c_rtc *info, struct seq_file *seq)
+{
+	unsigned int ticnt;
+
+	ticnt = readb(info->base + S3C2410_TICNT);
+	ticnt &= S3C2410_TICNT_ENABLE;
+
+	seq_printf(seq, "periodic_IRQ\t: %s\n", ticnt  ? "yes" : "no");
+}
+
+static void s3c2416_rtc_select_tick_clk(struct s3c_rtc *info)
+{
+	unsigned int con;
+
+	con = readw(info->base + S3C2410_RTCCON);
+	con |= S3C2443_RTCCON_TICSEL;
+	writew(con, info->base + S3C2410_RTCCON);
+}
+
+static void s3c6410_rtc_enable_tick(struct s3c_rtc *info, struct seq_file *seq)
+{
+	unsigned int ticnt;
+
+	ticnt = readw(info->base + S3C2410_RTCCON);
+	ticnt &= S3C64XX_RTCCON_TICEN;
+
+	seq_printf(seq, "periodic_IRQ\t: %s\n", ticnt  ? "yes" : "no");
+}
+
+static void s3c24xx_rtc_save_tick_cnt(struct s3c_rtc *info)
+{
+	info->ticnt_save = readb(info->base + S3C2410_TICNT);
+}
+
+static void s3c24xx_rtc_restore_tick_cnt(struct s3c_rtc *info)
+{
+	writeb(info->ticnt_save, info->base + S3C2410_TICNT);
+}
+
+static void s3c6410_rtc_save_tick_cnt(struct s3c_rtc *info)
+{
+	info->ticnt_en_save = readw(info->base + S3C2410_RTCCON);
+	info->ticnt_en_save &= S3C64XX_RTCCON_TICEN;
+	info->ticnt_save = readl(info->base + S3C2410_TICNT);
+}
+
+static void s3c6410_rtc_restore_tick_cnt(struct s3c_rtc *info)
+{
+	unsigned int con;
+
+	writel(info->ticnt_save, info->base + S3C2410_TICNT);
+	if (info->ticnt_en_save) {
+		con = readw(info->base + S3C2410_RTCCON);
+		writew(con | info->ticnt_en_save,
+				info->base + S3C2410_RTCCON);
+	}
+}
+
+static struct s3c_rtc_data const s3c2410_rtc_data = {
+	.max_user_freq		= 128,
+	.irq_handler		= s3c24xx_rtc_irq,
+	.set_freq		= s3c2410_rtc_setfreq,
+	.enable_tick		= s3c24xx_rtc_enable_tick,
+	.save_tick_cnt		= s3c24xx_rtc_save_tick_cnt,
+	.restore_tick_cnt	= s3c24xx_rtc_restore_tick_cnt,
+	.enable			= s3c24xx_rtc_enable,
+	.disable		= s3c24xx_rtc_disable,
+};
+
+static struct s3c_rtc_data const s3c2416_rtc_data = {
+	.max_user_freq		= 32768,
+	.irq_handler		= s3c24xx_rtc_irq,
+	.set_freq		= s3c2416_rtc_setfreq,
+	.enable_tick		= s3c24xx_rtc_enable_tick,
+	.select_tick_clk	= s3c2416_rtc_select_tick_clk,
+	.save_tick_cnt		= s3c24xx_rtc_save_tick_cnt,
+	.restore_tick_cnt	= s3c24xx_rtc_restore_tick_cnt,
+	.enable			= s3c24xx_rtc_enable,
+	.disable		= s3c24xx_rtc_disable,
+};
+
+static struct s3c_rtc_data const s3c2443_rtc_data = {
+	.max_user_freq		= 32768,
+	.irq_handler		= s3c24xx_rtc_irq,
+	.set_freq		= s3c2443_rtc_setfreq,
+	.enable_tick		= s3c24xx_rtc_enable_tick,
+	.select_tick_clk	= s3c2416_rtc_select_tick_clk,
+	.save_tick_cnt		= s3c24xx_rtc_save_tick_cnt,
+	.restore_tick_cnt	= s3c24xx_rtc_restore_tick_cnt,
+	.enable			= s3c24xx_rtc_enable,
+	.disable		= s3c24xx_rtc_disable,
+};
+
+static struct s3c_rtc_data const s3c6410_rtc_data = {
+	.max_user_freq		= 32768,
+	.irq_handler		= s3c6410_rtc_irq,
+	.set_freq		= s3c6410_rtc_setfreq,
+	.enable_tick		= s3c6410_rtc_enable_tick,
+	.save_tick_cnt		= s3c6410_rtc_save_tick_cnt,
+	.restore_tick_cnt	= s3c6410_rtc_restore_tick_cnt,
+	.enable			= s3c24xx_rtc_enable,
+	.disable		= s3c6410_rtc_disable,
+};
+
+static struct s3c_rtc_data const exynos3250_rtc_data = {
+	.max_user_freq		= 32768,
+	.needs_src_clk		= true,
+	.irq_handler		= s3c6410_rtc_irq,
+	.set_freq		= s3c6410_rtc_setfreq,
+	.enable_tick		= s3c6410_rtc_enable_tick,
+	.save_tick_cnt		= s3c6410_rtc_save_tick_cnt,
+	.restore_tick_cnt	= s3c6410_rtc_restore_tick_cnt,
+	.enable			= s3c24xx_rtc_enable,
+	.disable		= s3c6410_rtc_disable,
 };
 
 static const struct of_device_id s3c_rtc_dt_match[] = {
 	{
 		.compatible = "samsung,s3c2410-rtc",
-		.data = &s3c_rtc_drv_data_array[TYPE_S3C2410],
+		.data = (void *)&s3c2410_rtc_data,
 	}, {
 		.compatible = "samsung,s3c2416-rtc",
-		.data = &s3c_rtc_drv_data_array[TYPE_S3C2416],
+		.data = (void *)&s3c2416_rtc_data,
 	}, {
 		.compatible = "samsung,s3c2443-rtc",
-		.data = &s3c_rtc_drv_data_array[TYPE_S3C2443],
+		.data = (void *)&s3c2443_rtc_data,
 	}, {
 		.compatible = "samsung,s3c6410-rtc",
-		.data = &s3c_rtc_drv_data_array[TYPE_S3C64XX],
-	},
-	{},
-};
-MODULE_DEVICE_TABLE(of, s3c_rtc_dt_match);
-#endif
-
-static struct platform_device_id s3c_rtc_driver_ids[] = {
-	{
-		.name		= "s3c2410-rtc",
-		.driver_data	= TYPE_S3C2410,
-	}, {
-		.name		= "s3c2416-rtc",
-		.driver_data	= TYPE_S3C2416,
-	}, {
-		.name		= "s3c2443-rtc",
-		.driver_data	= TYPE_S3C2443,
+		.data = (void *)&s3c6410_rtc_data,
 	}, {
-		.name		= "s3c64xx-rtc",
-		.driver_data	= TYPE_S3C64XX,
+		.compatible = "samsung,exynos3250-rtc",
+		.data = (void *)&exynos3250_rtc_data,
 	},
-	{ }
+	{ /* sentinel */ },
 };
-
-MODULE_DEVICE_TABLE(platform, s3c_rtc_driver_ids);
+MODULE_DEVICE_TABLE(of, s3c_rtc_dt_match);
 
 static struct platform_driver s3c_rtc_driver = {
 	.probe		= s3c_rtc_probe,
 	.remove		= s3c_rtc_remove,
-	.id_table	= s3c_rtc_driver_ids,
 	.driver		= {
 		.name	= "s3c-rtc",
 		.owner	= THIS_MODULE,
@@ -687,7 +899,6 @@ static struct platform_driver s3c_rtc_driver = {
 		.of_match_table	= of_match_ptr(s3c_rtc_dt_match),
 	},
 };
-
 module_platform_driver(s3c_rtc_driver);
 
 MODULE_DESCRIPTION("Samsung S3C RTC Driver");
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 5df05f26b7d9..329db997ee66 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -1660,6 +1660,14 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm,
 		device->discipline->check_for_device_change(device, cqr, irb);
 		dasd_put_device(device);
 	}
+
+	/* check for for attention message */
+	if (scsw_dstat(&irb->scsw) & DEV_STAT_ATTENTION) {
+		device = dasd_device_from_cdev_locked(cdev);
+		device->discipline->check_attention(device, irb->esw.esw1.lpum);
+		dasd_put_device(device);
+	}
+
 	if (!cqr)
 		return;
 
@@ -2261,8 +2269,8 @@ static inline int _wait_for_wakeup_queue(struct list_head *ccw_queue)
 static int _dasd_sleep_on_queue(struct list_head *ccw_queue, int interruptible)
 {
 	struct dasd_device *device;
-	int rc;
 	struct dasd_ccw_req *cqr, *n;
+	int rc;
 
 retry:
 	list_for_each_entry_safe(cqr, n, ccw_queue, blocklist) {
@@ -2310,21 +2318,26 @@ retry:
 		/*
 		 * for alias devices simplify error recovery and
 		 * return to upper layer
+		 * do not skip ERP requests
 		 */
-		if (cqr->startdev != cqr->basedev &&
+		if (cqr->startdev != cqr->basedev && !cqr->refers &&
 		    (cqr->status == DASD_CQR_TERMINATED ||
 		     cqr->status == DASD_CQR_NEED_ERP))
 			return -EAGAIN;
-		else {
-			/* normal recovery for basedev IO */
-			if (__dasd_sleep_on_erp(cqr)) {
-				if (!cqr->status == DASD_CQR_TERMINATED &&
-				    !cqr->status == DASD_CQR_NEED_ERP)
-					break;
-				rc = 1;
-			}
+
+		/* normal recovery for basedev IO */
+		if (__dasd_sleep_on_erp(cqr)) {
+			goto retry;
+			/* remember that ERP was needed */
+			rc = 1;
+			/* skip processing for active cqr */
+			if (cqr->status != DASD_CQR_TERMINATED &&
+			    cqr->status != DASD_CQR_NEED_ERP)
+				break;
 		}
 	}
+
+	/* start ERP requests in upper loop */
 	if (rc)
 		goto retry;
 
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index 14ba80bfa571..8286f742436b 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -1432,6 +1432,29 @@ static ssize_t dasd_reservation_state_store(struct device *dev,
 static DEVICE_ATTR(last_known_reservation_state, 0644,
 		   dasd_reservation_state_show, dasd_reservation_state_store);
 
+static ssize_t dasd_pm_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct dasd_device *device;
+	u8 opm, nppm, cablepm, cuirpm, hpfpm;
+
+	device = dasd_device_from_cdev(to_ccwdev(dev));
+	if (IS_ERR(device))
+		return sprintf(buf, "0\n");
+
+	opm = device->path_data.opm;
+	nppm = device->path_data.npm;
+	cablepm = device->path_data.cablepm;
+	cuirpm = device->path_data.cuirpm;
+	hpfpm = device->path_data.hpfpm;
+	dasd_put_device(device);
+
+	return sprintf(buf, "%02x %02x %02x %02x %02x\n", opm, nppm,
+		       cablepm, cuirpm, hpfpm);
+}
+
+static DEVICE_ATTR(path_masks, 0444, dasd_pm_show, NULL);
+
 static struct attribute * dasd_attrs[] = {
 	&dev_attr_readonly.attr,
 	&dev_attr_discipline.attr,
@@ -1450,6 +1473,7 @@ static struct attribute * dasd_attrs[] = {
 	&dev_attr_reservation_policy.attr,
 	&dev_attr_last_known_reservation_state.attr,
 	&dev_attr_safe_offline.attr,
+	&dev_attr_path_masks.attr,
 	NULL,
 };
 
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 51dea7baf02c..d47f5b99623a 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -29,6 +29,8 @@
 #include <asm/cio.h>
 #include <asm/ccwdev.h>
 #include <asm/itcw.h>
+#include <asm/schid.h>
+#include <asm/chpid.h>
 
 #include "dasd_int.h"
 #include "dasd_eckd.h"
@@ -112,6 +114,12 @@ struct path_verification_work_data {
 static struct path_verification_work_data *path_verification_worker;
 static DEFINE_MUTEX(dasd_path_verification_mutex);
 
+struct check_attention_work_data {
+	struct work_struct worker;
+	struct dasd_device *device;
+	__u8 lpum;
+};
+
 /* initial attempt at a probe function. this can be simplified once
  * the other detection code is gone */
 static int
@@ -1126,6 +1134,7 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
 					"device %s instead of %s\n", lpm,
 					print_path_uid, print_device_uid);
 				path_err = -EINVAL;
+				path_data->cablepm |= lpm;
 				continue;
 			}
 
@@ -1141,6 +1150,13 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
 			break;
 		}
 		path_data->opm |= lpm;
+		/*
+		 * if the path is used
+		 * it should not be in one of the negative lists
+		 */
+		path_data->cablepm &= ~lpm;
+		path_data->hpfpm &= ~lpm;
+		path_data->cuirpm &= ~lpm;
 
 		if (conf_data != private->conf_data)
 			kfree(conf_data);
@@ -1230,7 +1246,7 @@ static void do_path_verification_work(struct work_struct *work)
 	struct dasd_eckd_private path_private;
 	struct dasd_uid *uid;
 	__u8 path_rcd_buf[DASD_ECKD_RCD_DATA_SIZE];
-	__u8 lpm, opm, npm, ppm, epm;
+	__u8 lpm, opm, npm, ppm, epm, hpfpm, cablepm;
 	unsigned long flags;
 	char print_uid[60];
 	int rc;
@@ -1248,6 +1264,9 @@ static void do_path_verification_work(struct work_struct *work)
 	npm = 0;
 	ppm = 0;
 	epm = 0;
+	hpfpm = 0;
+	cablepm = 0;
+
 	for (lpm = 0x80; lpm; lpm >>= 1) {
 		if (!(lpm & data->tbvpm))
 			continue;
@@ -1289,6 +1308,7 @@ static void do_path_verification_work(struct work_struct *work)
 			opm &= ~lpm;
 			npm &= ~lpm;
 			ppm &= ~lpm;
+			hpfpm |= lpm;
 			continue;
 		}
 
@@ -1350,6 +1370,7 @@ static void do_path_verification_work(struct work_struct *work)
 				opm &= ~lpm;
 				npm &= ~lpm;
 				ppm &= ~lpm;
+				cablepm |= lpm;
 				continue;
 			}
 		}
@@ -1364,12 +1385,21 @@ static void do_path_verification_work(struct work_struct *work)
 		spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
 		if (!device->path_data.opm && opm) {
 			device->path_data.opm = opm;
+			device->path_data.cablepm &= ~opm;
+			device->path_data.cuirpm &= ~opm;
+			device->path_data.hpfpm &= ~opm;
 			dasd_generic_path_operational(device);
-		} else
+		} else {
 			device->path_data.opm |= opm;
+			device->path_data.cablepm &= ~opm;
+			device->path_data.cuirpm &= ~opm;
+			device->path_data.hpfpm &= ~opm;
+		}
 		device->path_data.npm |= npm;
 		device->path_data.ppm |= ppm;
 		device->path_data.tbvpm |= epm;
+		device->path_data.cablepm |= cablepm;
+		device->path_data.hpfpm |= hpfpm;
 		spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
 	}
 
@@ -4475,6 +4505,343 @@ out_err:
 	return -1;
 }
 
+static int dasd_eckd_read_message_buffer(struct dasd_device *device,
+					 struct dasd_rssd_messages *messages,
+					 __u8 lpum)
+{
+	struct dasd_rssd_messages *message_buf;
+	struct dasd_psf_prssd_data *prssdp;
+	struct dasd_eckd_private *private;
+	struct dasd_ccw_req *cqr;
+	struct ccw1 *ccw;
+	int rc;
+
+	private = (struct dasd_eckd_private *) device->private;
+	cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */	+ 1 /* RSSD */,
+				   (sizeof(struct dasd_psf_prssd_data) +
+				    sizeof(struct dasd_rssd_messages)),
+				   device);
+	if (IS_ERR(cqr)) {
+		DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s",
+				"Could not allocate read message buffer request");
+		return PTR_ERR(cqr);
+	}
+
+	cqr->startdev = device;
+	cqr->memdev = device;
+	cqr->block = NULL;
+	cqr->retries = 256;
+	cqr->expires = 10 * HZ;
+
+	/* we need to check for messages on exactly this path */
+	set_bit(DASD_CQR_VERIFY_PATH, &cqr->flags);
+	cqr->lpm = lpum;
+
+	/* Prepare for Read Subsystem Data */
+	prssdp = (struct dasd_psf_prssd_data *) cqr->data;
+	memset(prssdp, 0, sizeof(struct dasd_psf_prssd_data));
+	prssdp->order = PSF_ORDER_PRSSD;
+	prssdp->suborder = 0x03;	/* Message Buffer */
+	/* all other bytes of prssdp must be zero */
+
+	ccw = cqr->cpaddr;
+	ccw->cmd_code = DASD_ECKD_CCW_PSF;
+	ccw->count = sizeof(struct dasd_psf_prssd_data);
+	ccw->flags |= CCW_FLAG_CC;
+	ccw->flags |= CCW_FLAG_SLI;
+	ccw->cda = (__u32)(addr_t) prssdp;
+
+	/* Read Subsystem Data - message buffer */
+	message_buf = (struct dasd_rssd_messages *) (prssdp + 1);
+	memset(message_buf, 0, sizeof(struct dasd_rssd_messages));
+
+	ccw++;
+	ccw->cmd_code = DASD_ECKD_CCW_RSSD;
+	ccw->count = sizeof(struct dasd_rssd_messages);
+	ccw->flags |= CCW_FLAG_SLI;
+	ccw->cda = (__u32)(addr_t) message_buf;
+
+	cqr->buildclk = get_tod_clock();
+	cqr->status = DASD_CQR_FILLED;
+	rc = dasd_sleep_on_immediatly(cqr);
+	if (rc == 0) {
+		prssdp = (struct dasd_psf_prssd_data *) cqr->data;
+		message_buf = (struct dasd_rssd_messages *)
+			(prssdp + 1);
+		memcpy(messages, message_buf,
+		       sizeof(struct dasd_rssd_messages));
+	} else
+		DBF_EVENT_DEVID(DBF_WARNING, device->cdev,
+				"Reading messages failed with rc=%d\n"
+				, rc);
+	dasd_sfree_request(cqr, cqr->memdev);
+	return rc;
+}
+
+/*
+ * Perform Subsystem Function - CUIR response
+ */
+static int
+dasd_eckd_psf_cuir_response(struct dasd_device *device, int response,
+			    __u32 message_id,
+			    struct channel_path_desc *desc,
+			    struct subchannel_id sch_id)
+{
+	struct dasd_psf_cuir_response *psf_cuir;
+	struct dasd_ccw_req *cqr;
+	struct ccw1 *ccw;
+	int rc;
+
+	cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ ,
+				  sizeof(struct dasd_psf_cuir_response),
+				  device);
+
+	if (IS_ERR(cqr)) {
+		DBF_DEV_EVENT(DBF_WARNING, device, "%s",
+			   "Could not allocate PSF-CUIR request");
+		return PTR_ERR(cqr);
+	}
+
+	psf_cuir = (struct dasd_psf_cuir_response *)cqr->data;
+	psf_cuir->order = PSF_ORDER_CUIR_RESPONSE;
+	psf_cuir->cc = response;
+	if (desc)
+		psf_cuir->chpid = desc->chpid;
+	psf_cuir->message_id = message_id;
+	psf_cuir->cssid = sch_id.cssid;
+	psf_cuir->ssid = sch_id.ssid;
+
+	ccw = cqr->cpaddr;
+	ccw->cmd_code = DASD_ECKD_CCW_PSF;
+	ccw->cda = (__u32)(addr_t)psf_cuir;
+	ccw->count = sizeof(struct dasd_psf_cuir_response);
+
+	cqr->startdev = device;
+	cqr->memdev = device;
+	cqr->block = NULL;
+	cqr->retries = 256;
+	cqr->expires = 10*HZ;
+	cqr->buildclk = get_tod_clock();
+	cqr->status = DASD_CQR_FILLED;
+
+	rc = dasd_sleep_on(cqr);
+
+	dasd_sfree_request(cqr, cqr->memdev);
+	return rc;
+}
+
+static int dasd_eckd_cuir_change_state(struct dasd_device *device, __u8 lpum)
+{
+	unsigned long flags;
+	__u8 tbcpm;
+
+	spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
+	tbcpm = device->path_data.opm & ~lpum;
+	if (tbcpm) {
+		device->path_data.opm = tbcpm;
+		device->path_data.cuirpm |= lpum;
+	}
+	spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
+	return tbcpm ? 0 : PSF_CUIR_LAST_PATH;
+}
+
+/*
+ * walk through all devices and quiesce them
+ * if it is the last path return error
+ *
+ * if only part of the devices are quiesced and an error
+ * occurs no onlining necessary, the storage server will
+ * notify the already set offline devices again
+ */
+static int dasd_eckd_cuir_quiesce(struct dasd_device *device, __u8 lpum,
+				 struct channel_path_desc *desc,
+				 struct subchannel_id sch_id)
+{
+	struct alias_pav_group *pavgroup, *tempgroup;
+	struct dasd_eckd_private *private;
+	struct dasd_device *dev, *n;
+	int rc;
+
+	private = (struct dasd_eckd_private *) device->private;
+	rc = 0;
+
+	/* active devices */
+	list_for_each_entry_safe(dev, n,
+				 &private->lcu->active_devices,
+				 alias_list) {
+		rc = dasd_eckd_cuir_change_state(dev, lpum);
+		if (rc)
+			goto out;
+	}
+
+	/* inactive devices */
+	list_for_each_entry_safe(dev, n,
+				 &private->lcu->inactive_devices,
+				 alias_list) {
+		rc = dasd_eckd_cuir_change_state(dev, lpum);
+		if (rc)
+			goto out;
+	}
+
+	/* devices in PAV groups */
+	list_for_each_entry_safe(pavgroup, tempgroup,
+				 &private->lcu->grouplist, group) {
+		list_for_each_entry_safe(dev, n, &pavgroup->baselist,
+					 alias_list) {
+			rc = dasd_eckd_cuir_change_state(dev, lpum);
+			if (rc)
+				goto out;
+		}
+		list_for_each_entry_safe(dev, n, &pavgroup->aliaslist,
+					 alias_list) {
+			rc = dasd_eckd_cuir_change_state(dev, lpum);
+			if (rc)
+				goto out;
+		}
+	}
+
+	pr_warn("Service on the storage server caused path %x.%02x to go offline",
+		sch_id.cssid, desc ? desc->chpid : 0);
+	rc = PSF_CUIR_COMPLETED;
+out:
+	return rc;
+}
+
+static int dasd_eckd_cuir_resume(struct dasd_device *device, __u8 lpum,
+				 struct channel_path_desc *desc,
+				 struct subchannel_id sch_id)
+{
+	struct alias_pav_group *pavgroup, *tempgroup;
+	struct dasd_eckd_private *private;
+	struct dasd_device *dev, *n;
+
+	pr_info("Path %x.%02x is back online after service on the storage server",
+		sch_id.cssid, desc ? desc->chpid : 0);
+	private = (struct dasd_eckd_private *) device->private;
+
+	/*
+	 * the path may have been added through a generic path event before
+	 * only trigger path verification if the path is not already in use
+	 */
+
+	list_for_each_entry_safe(dev, n,
+				 &private->lcu->active_devices,
+				 alias_list) {
+		if (!(dev->path_data.opm & lpum)) {
+			dev->path_data.tbvpm |= lpum;
+			dasd_schedule_device_bh(dev);
+		}
+	}
+
+	list_for_each_entry_safe(dev, n,
+				 &private->lcu->inactive_devices,
+				 alias_list) {
+		if (!(dev->path_data.opm & lpum)) {
+			dev->path_data.tbvpm |= lpum;
+			dasd_schedule_device_bh(dev);
+		}
+	}
+
+	/* devices in PAV groups */
+	list_for_each_entry_safe(pavgroup, tempgroup,
+				 &private->lcu->grouplist,
+				 group) {
+		list_for_each_entry_safe(dev, n,
+					 &pavgroup->baselist,
+					 alias_list) {
+			if (!(dev->path_data.opm & lpum)) {
+				dev->path_data.tbvpm |= lpum;
+				dasd_schedule_device_bh(dev);
+			}
+		}
+		list_for_each_entry_safe(dev, n,
+					 &pavgroup->aliaslist,
+					 alias_list) {
+			if (!(dev->path_data.opm & lpum)) {
+				dev->path_data.tbvpm |= lpum;
+				dasd_schedule_device_bh(dev);
+			}
+		}
+	}
+	return PSF_CUIR_COMPLETED;
+}
+
+static void dasd_eckd_handle_cuir(struct dasd_device *device, void *messages,
+				 __u8 lpum)
+{
+	struct dasd_cuir_message *cuir = messages;
+	struct channel_path_desc *desc;
+	struct subchannel_id sch_id;
+	int pos, response;
+	ccw_device_get_schid(device->cdev, &sch_id);
+
+	/* get position of path in mask */
+	pos = 8 - ffs(lpum);
+	/* get channel path descriptor from this position */
+	desc = ccw_device_get_chp_desc(device->cdev, pos);
+
+	if (cuir->code == CUIR_QUIESCE) {
+		/* quiesce */
+		response = dasd_eckd_cuir_quiesce(device, lpum, desc, sch_id);
+	} else if (cuir->code == CUIR_RESUME) {
+		/* resume */
+		response = dasd_eckd_cuir_resume(device, lpum, desc, sch_id);
+	} else
+		response = PSF_CUIR_NOT_SUPPORTED;
+
+	dasd_eckd_psf_cuir_response(device, response, cuir->message_id,
+				    desc, sch_id);
+
+	/* free descriptor copy */
+	kfree(desc);
+}
+
+static void dasd_eckd_check_attention_work(struct work_struct *work)
+{
+	struct check_attention_work_data *data;
+	struct dasd_rssd_messages *messages;
+	struct dasd_device *device;
+	int rc;
+
+	data = container_of(work, struct check_attention_work_data, worker);
+	device = data->device;
+
+	messages = kzalloc(sizeof(*messages), GFP_KERNEL);
+	if (!messages) {
+		DBF_DEV_EVENT(DBF_WARNING, device, "%s",
+			      "Could not allocate attention message buffer");
+		goto out;
+	}
+
+	rc = dasd_eckd_read_message_buffer(device, messages, data->lpum);
+	if (rc)
+		goto out;
+
+	if (messages->length == ATTENTION_LENGTH_CUIR &&
+	    messages->format == ATTENTION_FORMAT_CUIR)
+		dasd_eckd_handle_cuir(device, messages, data->lpum);
+
+out:
+	dasd_put_device(device);
+	kfree(messages);
+	kfree(data);
+}
+
+static int dasd_eckd_check_attention(struct dasd_device *device, __u8 lpum)
+{
+	struct check_attention_work_data *data;
+
+	data = kzalloc(sizeof(*data), GFP_ATOMIC);
+	if (!data)
+		return -ENOMEM;
+	INIT_WORK(&data->worker, dasd_eckd_check_attention_work);
+	dasd_get_device(device);
+	data->device = device;
+	data->lpum = lpum;
+	schedule_work(&data->worker);
+	return 0;
+}
+
 static struct ccw_driver dasd_eckd_driver = {
 	.driver = {
 		.name	= "dasd-eckd",
@@ -4539,6 +4906,7 @@ static struct dasd_discipline dasd_eckd_discipline = {
 	.reload = dasd_eckd_reload_device,
 	.get_uid = dasd_eckd_get_uid,
 	.kick_validate = dasd_eckd_kick_validate_server,
+	.check_attention = dasd_eckd_check_attention,
 };
 
 static int __init
diff --git a/drivers/s390/block/dasd_eckd.h b/drivers/s390/block/dasd_eckd.h
index 2555e494591f..ddab7df36e25 100644
--- a/drivers/s390/block/dasd_eckd.h
+++ b/drivers/s390/block/dasd_eckd.h
@@ -51,8 +51,35 @@
 /*
  * Perform Subsystem Function / Sub-Orders
  */
-#define PSF_ORDER_PRSSD 0x18
-#define PSF_ORDER_SSC	0x1D
+#define PSF_ORDER_PRSSD			 0x18
+#define PSF_ORDER_CUIR_RESPONSE		 0x1A
+#define PSF_ORDER_SSC			 0x1D
+
+/*
+ * CUIR response condition codes
+ */
+#define PSF_CUIR_INVALID		 0x00
+#define PSF_CUIR_COMPLETED		 0x01
+#define PSF_CUIR_NOT_SUPPORTED		 0x02
+#define PSF_CUIR_ERROR_IN_REQ		 0x03
+#define PSF_CUIR_DENIED			 0x04
+#define PSF_CUIR_LAST_PATH		 0x05
+#define PSF_CUIR_DEVICE_ONLINE		 0x06
+#define PSF_CUIR_VARY_FAILURE		 0x07
+#define PSF_CUIR_SOFTWARE_FAILURE	 0x08
+#define PSF_CUIR_NOT_RECOGNIZED		 0x09
+
+/*
+ * CUIR codes
+ */
+#define CUIR_QUIESCE			 0x01
+#define CUIR_RESUME			 0x02
+
+/*
+ * attention message definitions
+ */
+#define ATTENTION_LENGTH_CUIR		 0x0e
+#define ATTENTION_FORMAT_CUIR		 0x01
 
 /*
  * Size that is reportet for large volumes in the old 16-bit no_cyl field
@@ -342,6 +369,38 @@ struct dasd_rssd_features {
 	char feature[256];
 } __attribute__((packed));
 
+struct dasd_rssd_messages {
+	__u16 length;
+	__u8 format;
+	__u8 code;
+	__u32 message_id;
+	__u8 flags;
+	char messages[4087];
+} __packed;
+
+struct dasd_cuir_message {
+	__u16 length;
+	__u8 format;
+	__u8 code;
+	__u32 message_id;
+	__u8 flags;
+	__u8 neq_map[3];
+	__u8 ned_map;
+	__u8 record_selector;
+} __packed;
+
+struct dasd_psf_cuir_response {
+	__u8 order;
+	__u8 flags;
+	__u8 cc;
+	__u8 chpid;
+	__u16 device_nr;
+	__u16 reserved;
+	__u32 message_id;
+	__u64 system_id;
+	__u8 cssid;
+	__u8 ssid;
+} __packed;
 
 /*
  * Perform Subsystem Function - Prepare for Read Subsystem Data
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index c20170166909..8b5d4100abf7 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -357,6 +357,7 @@ struct dasd_discipline {
 
 	int (*get_uid) (struct dasd_device *, struct dasd_uid *);
 	void (*kick_validate) (struct dasd_device *);
+	int (*check_attention)(struct dasd_device *, __u8);
 };
 
 extern struct dasd_discipline *dasd_diag_discipline_pointer;
@@ -382,6 +383,10 @@ struct dasd_path {
 	__u8 tbvpm;
 	__u8 ppm;
 	__u8 npm;
+	/* paths that are not used because of a special condition */
+	__u8 cablepm; /* miss-cabled */
+	__u8 hpfpm;   /* the HPF requirements of the other paths are not met */
+	__u8 cuirpm;  /* CUIR varied offline */
 };
 
 struct dasd_profile_info {
@@ -501,7 +506,10 @@ struct dasd_block {
 	struct dasd_profile profile;
 };
 
-
+struct dasd_attention_data {
+	struct dasd_device *device;
+	__u8 lpum;
+};
 
 /* reasons why device (ccw_device_start) was stopped */
 #define DASD_STOPPED_NOT_ACC 1         /* not accessible */
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index 76bed1743db1..56046ab39629 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -386,6 +386,7 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
 	blk_queue_max_hw_sectors(rq, nr_max_blk << 3); /* 8 * 512 = blk_size */
 	blk_queue_max_segments(rq, nr_max_blk);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, rq);
+	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, rq);
 	scm_blk_dev_cluster_setup(bdev);
 
 	bdev->gendisk = alloc_disk(SCM_NR_PARTS);
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 6969d39f1e2e..9e0de9c9a6fc 100644
--- a/drivers/s390/block/xpram.c
+++ b/drivers/s390/block/xpram.c
@@ -346,6 +346,7 @@ static int __init xpram_setup_blkdev(void)
 			goto out;
 		}
 		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, xpram_queues[i]);
+		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, xpram_queues[i]);
 		blk_queue_make_request(xpram_queues[i], xpram_make_request);
 		blk_queue_logical_block_size(xpram_queues[i], 4096);
 	}
diff --git a/drivers/s390/char/Kconfig b/drivers/s390/char/Kconfig
index 71bf959732fe..dc24ecfac2d1 100644
--- a/drivers/s390/char/Kconfig
+++ b/drivers/s390/char/Kconfig
@@ -102,6 +102,19 @@ config SCLP_ASYNC
 	  want for inform other people about your kernel panics,
 	  need this feature and intend to run your kernel in LPAR.
 
+config HMC_DRV
+	def_tristate m
+	prompt "Support for file transfers from HMC drive CD/DVD-ROM"
+	depends on 64BIT
+	select CRC16
+	help
+	  This option enables support for file transfers from a Hardware
+	  Management Console (HMC) drive CD/DVD-ROM. It is available as a
+	  module, called 'hmcdrv', and also as kernel built-in. There is one
+	  optional parameter for this module: cachesize=N, which modifies the
+	  transfer cache size from it's default value 0.5MB to N bytes. If N
+	  is zero, then no caching is performed.
+
 config S390_TAPE
 	def_tristate m
 	prompt "S/390 tape device support"
diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile
index 78b6ace7edcb..6fa9364d1c07 100644
--- a/drivers/s390/char/Makefile
+++ b/drivers/s390/char/Makefile
@@ -33,3 +33,6 @@ obj-$(CONFIG_S390_VMUR) += vmur.o
 
 zcore_mod-objs := sclp_sdias.o zcore.o
 obj-$(CONFIG_CRASH_DUMP) += zcore_mod.o
+
+hmcdrv-objs := hmcdrv_mod.o hmcdrv_dev.o hmcdrv_ftp.o hmcdrv_cache.o diag_ftp.o sclp_ftp.o
+obj-$(CONFIG_HMC_DRV) += hmcdrv.o
diff --git a/drivers/s390/char/diag_ftp.c b/drivers/s390/char/diag_ftp.c
new file mode 100644
index 000000000000..93889632fdf9
--- /dev/null
+++ b/drivers/s390/char/diag_ftp.c
@@ -0,0 +1,237 @@
+/*
+ *    DIAGNOSE X'2C4' instruction based HMC FTP services, useable on z/VM
+ *
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ *
+ */
+
+#define KMSG_COMPONENT "hmcdrv"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/wait.h>
+#include <linux/string.h>
+#include <asm/ctl_reg.h>
+
+#include "hmcdrv_ftp.h"
+#include "diag_ftp.h"
+
+/* DIAGNOSE X'2C4' return codes in Ry */
+#define DIAG_FTP_RET_OK	0 /* HMC FTP started successfully */
+#define DIAG_FTP_RET_EBUSY	4 /* HMC FTP service currently busy */
+#define DIAG_FTP_RET_EIO	8 /* HMC FTP service I/O error */
+/* and an artificial extension */
+#define DIAG_FTP_RET_EPERM	2 /* HMC FTP service privilege error */
+
+/* FTP service status codes (after INTR at guest real location 133) */
+#define DIAG_FTP_STAT_OK	0U /* request completed successfully */
+#define DIAG_FTP_STAT_PGCC	4U /* program check condition */
+#define DIAG_FTP_STAT_PGIOE	8U /* paging I/O error */
+#define DIAG_FTP_STAT_TIMEOUT	12U /* timeout */
+#define DIAG_FTP_STAT_EBASE	16U /* base of error codes from SCLP */
+#define DIAG_FTP_STAT_LDFAIL	(DIAG_FTP_STAT_EBASE + 1U) /* failed */
+#define DIAG_FTP_STAT_LDNPERM	(DIAG_FTP_STAT_EBASE + 2U) /* not allowed */
+#define DIAG_FTP_STAT_LDRUNS	(DIAG_FTP_STAT_EBASE + 3U) /* runs */
+#define DIAG_FTP_STAT_LDNRUNS	(DIAG_FTP_STAT_EBASE + 4U) /* not runs */
+
+/**
+ * struct diag_ftp_ldfpl - load file FTP parameter list (LDFPL)
+ * @bufaddr: real buffer address (at 4k boundary)
+ * @buflen: length of buffer
+ * @offset: dir/file offset
+ * @intparm: interruption parameter (unused)
+ * @transferred: bytes transferred
+ * @fsize: file size, filled on GET
+ * @failaddr: failing address
+ * @spare: padding
+ * @fident: file name - ASCII
+ */
+struct diag_ftp_ldfpl {
+	u64 bufaddr;
+	u64 buflen;
+	u64 offset;
+	u64 intparm;
+	u64 transferred;
+	u64 fsize;
+	u64 failaddr;
+	u64 spare;
+	u8 fident[HMCDRV_FTP_FIDENT_MAX];
+} __packed;
+
+static DECLARE_COMPLETION(diag_ftp_rx_complete);
+static int diag_ftp_subcode;
+
+/**
+ * diag_ftp_handler() - FTP services IRQ handler
+ * @extirq: external interrupt (sub-) code
+ * @param32: 32-bit interruption parameter from &struct diag_ftp_ldfpl
+ * @param64: unused (for 64-bit interrupt parameters)
+ */
+static void diag_ftp_handler(struct ext_code extirq,
+			     unsigned int param32,
+			     unsigned long param64)
+{
+	if ((extirq.subcode >> 8) != 8)
+		return; /* not a FTP services sub-code */
+
+	inc_irq_stat(IRQEXT_FTP);
+	diag_ftp_subcode = extirq.subcode & 0xffU;
+	complete(&diag_ftp_rx_complete);
+}
+
+/**
+ * diag_ftp_2c4() - DIAGNOSE X'2C4' service call
+ * @fpl: pointer to prepared LDFPL
+ * @cmd: FTP command to be executed
+ *
+ * Performs a DIAGNOSE X'2C4' call with (input/output) FTP parameter list
+ * @fpl and FTP function code @cmd. In case of an error the function does
+ * nothing and returns an (negative) error code.
+ *
+ * Notes:
+ * 1. This function only initiates a transfer, so the caller must wait
+ *    for completion (asynchronous execution).
+ * 2. The FTP parameter list @fpl must be aligned to a double-word boundary.
+ * 3. fpl->bufaddr must be a real address, 4k aligned
+ */
+static int diag_ftp_2c4(struct diag_ftp_ldfpl *fpl,
+			enum hmcdrv_ftp_cmdid cmd)
+{
+	int rc;
+
+	asm volatile(
+		"	diag	%[addr],%[cmd],0x2c4\n"
+		"0:	j	2f\n"
+		"1:	la	%[rc],%[err]\n"
+		"2:\n"
+		EX_TABLE(0b, 1b)
+		: [rc] "=d" (rc), "+m" (*fpl)
+		: [cmd] "0" (cmd), [addr] "d" (virt_to_phys(fpl)),
+		  [err] "i" (DIAG_FTP_RET_EPERM)
+		: "cc");
+
+	switch (rc) {
+	case DIAG_FTP_RET_OK:
+		return 0;
+	case DIAG_FTP_RET_EBUSY:
+		return -EBUSY;
+	case DIAG_FTP_RET_EPERM:
+		return -EPERM;
+	case DIAG_FTP_RET_EIO:
+	default:
+		return -EIO;
+	}
+}
+
+/**
+ * diag_ftp_cmd() - executes a DIAG X'2C4' FTP command, targeting a HMC
+ * @ftp: pointer to FTP command specification
+ * @fsize: return of file size (or NULL if undesirable)
+ *
+ * Attention: Notice that this function is not reentrant - so the caller
+ * must ensure locking.
+ *
+ * Return: number of bytes read/written or a (negative) error code
+ */
+ssize_t diag_ftp_cmd(const struct hmcdrv_ftp_cmdspec *ftp, size_t *fsize)
+{
+	struct diag_ftp_ldfpl *ldfpl;
+	ssize_t len;
+#ifdef DEBUG
+	unsigned long start_jiffies;
+
+	pr_debug("starting DIAG X'2C4' on '%s', requesting %zd bytes\n",
+		 ftp->fname, ftp->len);
+	start_jiffies = jiffies;
+#endif
+	init_completion(&diag_ftp_rx_complete);
+
+	ldfpl = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!ldfpl) {
+		len = -ENOMEM;
+		goto out;
+	}
+
+	len = strlcpy(ldfpl->fident, ftp->fname, sizeof(ldfpl->fident));
+	if (len >= HMCDRV_FTP_FIDENT_MAX) {
+		len = -EINVAL;
+		goto out_free;
+	}
+
+	ldfpl->transferred = 0;
+	ldfpl->fsize = 0;
+	ldfpl->offset = ftp->ofs;
+	ldfpl->buflen = ftp->len;
+	ldfpl->bufaddr = virt_to_phys(ftp->buf);
+
+	len = diag_ftp_2c4(ldfpl, ftp->id);
+	if (len)
+		goto out_free;
+
+	/*
+	 * There is no way to cancel the running diag X'2C4', the code
+	 * needs to wait unconditionally until the transfer is complete.
+	 */
+	wait_for_completion(&diag_ftp_rx_complete);
+
+#ifdef DEBUG
+	pr_debug("completed DIAG X'2C4' after %lu ms\n",
+		 (jiffies - start_jiffies) * 1000 / HZ);
+	pr_debug("status of DIAG X'2C4' is %u, with %lld/%lld bytes\n",
+		 diag_ftp_subcode, ldfpl->transferred, ldfpl->fsize);
+#endif
+
+	switch (diag_ftp_subcode) {
+	case DIAG_FTP_STAT_OK: /* success */
+		len = ldfpl->transferred;
+		if (fsize)
+			*fsize = ldfpl->fsize;
+		break;
+	case DIAG_FTP_STAT_LDNPERM:
+		len = -EPERM;
+		break;
+	case DIAG_FTP_STAT_LDRUNS:
+		len = -EBUSY;
+		break;
+	case DIAG_FTP_STAT_LDFAIL:
+		len = -ENOENT; /* no such file or media */
+		break;
+	default:
+		len = -EIO;
+		break;
+	}
+
+out_free:
+	free_page((unsigned long) ldfpl);
+out:
+	return len;
+}
+
+/**
+ * diag_ftp_startup() - startup of FTP services, when running on z/VM
+ *
+ * Return: 0 on success, else an (negative) error code
+ */
+int diag_ftp_startup(void)
+{
+	int rc;
+
+	rc = register_external_irq(EXT_IRQ_CP_SERVICE, diag_ftp_handler);
+	if (rc)
+		return rc;
+
+	ctl_set_bit(0, 63 - 22);
+	return 0;
+}
+
+/**
+ * diag_ftp_shutdown() - shutdown of FTP services, when running on z/VM
+ */
+void diag_ftp_shutdown(void)
+{
+	ctl_clear_bit(0, 63 - 22);
+	unregister_external_irq(EXT_IRQ_CP_SERVICE, diag_ftp_handler);
+}
diff --git a/drivers/s390/char/diag_ftp.h b/drivers/s390/char/diag_ftp.h
new file mode 100644
index 000000000000..3abd2614053a
--- /dev/null
+++ b/drivers/s390/char/diag_ftp.h
@@ -0,0 +1,21 @@
+/*
+ *    DIAGNOSE X'2C4' instruction based SE/HMC FTP Services, useable on z/VM
+ *
+ *    Notice that all functions exported here are not reentrant.
+ *    So usage should be exclusive, ensured by the caller (e.g. using a
+ *    mutex).
+ *
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ */
+
+#ifndef __DIAG_FTP_H__
+#define __DIAG_FTP_H__
+
+#include "hmcdrv_ftp.h"
+
+int diag_ftp_startup(void);
+void diag_ftp_shutdown(void);
+ssize_t diag_ftp_cmd(const struct hmcdrv_ftp_cmdspec *ftp, size_t *fsize);
+
+#endif	 /* __DIAG_FTP_H__ */
diff --git a/drivers/s390/char/hmcdrv_cache.c b/drivers/s390/char/hmcdrv_cache.c
new file mode 100644
index 000000000000..4cda5ada143a
--- /dev/null
+++ b/drivers/s390/char/hmcdrv_cache.c
@@ -0,0 +1,252 @@
+/*
+ *    SE/HMC Drive (Read) Cache Functions
+ *
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ *
+ */
+
+#define KMSG_COMPONENT "hmcdrv"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/jiffies.h>
+
+#include "hmcdrv_ftp.h"
+#include "hmcdrv_cache.h"
+
+#define HMCDRV_CACHE_TIMEOUT		30 /* aging timeout in seconds */
+
+/**
+ * struct hmcdrv_cache_entry - file cache (only used on read/dir)
+ * @id: FTP command ID
+ * @content: kernel-space buffer, 4k aligned
+ * @len: size of @content cache (0 if caching disabled)
+ * @ofs: start of content within file (-1 if no cached content)
+ * @fname: file name
+ * @fsize: file size
+ * @timeout: cache timeout in jiffies
+ *
+ * Notice that the first three members (id, fname, fsize) are cached on all
+ * read/dir requests. But content is cached only under some preconditions.
+ * Uncached content is signalled by a negative value of @ofs.
+ */
+struct hmcdrv_cache_entry {
+	enum hmcdrv_ftp_cmdid id;
+	char fname[HMCDRV_FTP_FIDENT_MAX];
+	size_t fsize;
+	loff_t ofs;
+	unsigned long timeout;
+	void *content;
+	size_t len;
+};
+
+static int hmcdrv_cache_order; /* cache allocated page order */
+
+static struct hmcdrv_cache_entry hmcdrv_cache_file = {
+	.fsize = SIZE_MAX,
+	.ofs = -1,
+	.len = 0,
+	.fname = {'\0'}
+};
+
+/**
+ * hmcdrv_cache_get() - looks for file data/content in read cache
+ * @ftp: pointer to FTP command specification
+ *
+ * Return: number of bytes read from cache or a negative number if nothing
+ * in content cache (for the file/cmd specified in @ftp)
+ */
+static ssize_t hmcdrv_cache_get(const struct hmcdrv_ftp_cmdspec *ftp)
+{
+	loff_t pos; /* position in cache (signed) */
+	ssize_t len;
+
+	if ((ftp->id != hmcdrv_cache_file.id) ||
+	    strcmp(hmcdrv_cache_file.fname, ftp->fname))
+		return -1;
+
+	if (ftp->ofs >= hmcdrv_cache_file.fsize) /* EOF ? */
+		return 0;
+
+	if ((hmcdrv_cache_file.ofs < 0) || /* has content? */
+	    time_after(jiffies, hmcdrv_cache_file.timeout))
+		return -1;
+
+	/* there seems to be cached content - calculate the maximum number
+	 * of bytes that can be returned (regarding file size and offset)
+	 */
+	len = hmcdrv_cache_file.fsize - ftp->ofs;
+
+	if (len > ftp->len)
+		len = ftp->len;
+
+	/* check if the requested chunk falls into our cache (which starts
+	 * at offset 'hmcdrv_cache_file.ofs' in the file of interest)
+	 */
+	pos = ftp->ofs - hmcdrv_cache_file.ofs;
+
+	if ((pos >= 0) &&
+	    ((pos + len) <= hmcdrv_cache_file.len)) {
+
+		memcpy(ftp->buf,
+		       hmcdrv_cache_file.content + pos,
+		       len);
+		pr_debug("using cached content of '%s', returning %zd/%zd bytes\n",
+			 hmcdrv_cache_file.fname, len,
+			 hmcdrv_cache_file.fsize);
+
+		return len;
+	}
+
+	return -1;
+}
+
+/**
+ * hmcdrv_cache_do() - do a HMC drive CD/DVD transfer with cache update
+ * @ftp: pointer to FTP command specification
+ * @func: FTP transfer function to be used
+ *
+ * Return: number of bytes read/written or a (negative) error code
+ */
+static ssize_t hmcdrv_cache_do(const struct hmcdrv_ftp_cmdspec *ftp,
+			       hmcdrv_cache_ftpfunc func)
+{
+	ssize_t len;
+
+	/* only cache content if the read/dir cache really exists
+	 * (hmcdrv_cache_file.len > 0), is large enough to handle the
+	 * request (hmcdrv_cache_file.len >= ftp->len) and there is a need
+	 * to do so (ftp->len > 0)
+	 */
+	if ((ftp->len > 0) && (hmcdrv_cache_file.len >= ftp->len)) {
+
+		/* because the cache is not located at ftp->buf, we have to
+		 * assemble a new HMC drive FTP cmd specification (pointing
+		 * to our cache, and using the increased size)
+		 */
+		struct hmcdrv_ftp_cmdspec cftp = *ftp; /* make a copy */
+		cftp.buf = hmcdrv_cache_file.content;  /* and update */
+		cftp.len = hmcdrv_cache_file.len;      /* buffer data */
+
+		len = func(&cftp, &hmcdrv_cache_file.fsize); /* now do */
+
+		if (len > 0) {
+			pr_debug("caching %zd bytes content for '%s'\n",
+				 len, ftp->fname);
+
+			if (len > ftp->len)
+				len = ftp->len;
+
+			hmcdrv_cache_file.ofs = ftp->ofs;
+			hmcdrv_cache_file.timeout = jiffies +
+				HMCDRV_CACHE_TIMEOUT * HZ;
+			memcpy(ftp->buf, hmcdrv_cache_file.content, len);
+		}
+	} else {
+		len = func(ftp, &hmcdrv_cache_file.fsize);
+		hmcdrv_cache_file.ofs = -1; /* invalidate content */
+	}
+
+	if (len > 0) {
+		/* cache some file info (FTP command, file name and file
+		 * size) unconditionally
+		 */
+		strlcpy(hmcdrv_cache_file.fname, ftp->fname,
+			HMCDRV_FTP_FIDENT_MAX);
+		hmcdrv_cache_file.id = ftp->id;
+		pr_debug("caching cmd %d, file size %zu for '%s'\n",
+			 ftp->id, hmcdrv_cache_file.fsize, ftp->fname);
+	}
+
+	return len;
+}
+
+/**
+ * hmcdrv_cache_cmd() - perform a cached HMC drive CD/DVD transfer
+ * @ftp: pointer to FTP command specification
+ * @func: FTP transfer function to be used
+ *
+ * Attention: Notice that this function is not reentrant - so the caller
+ * must ensure exclusive execution.
+ *
+ * Return: number of bytes read/written or a (negative) error code
+ */
+ssize_t hmcdrv_cache_cmd(const struct hmcdrv_ftp_cmdspec *ftp,
+			 hmcdrv_cache_ftpfunc func)
+{
+	ssize_t len;
+
+	if ((ftp->id == HMCDRV_FTP_DIR) || /* read cache */
+	    (ftp->id == HMCDRV_FTP_NLIST) ||
+	    (ftp->id == HMCDRV_FTP_GET)) {
+
+		len = hmcdrv_cache_get(ftp);
+
+		if (len >= 0) /* got it from cache ? */
+			return len; /* yes */
+
+		len = hmcdrv_cache_do(ftp, func);
+
+		if (len >= 0)
+			return len;
+
+	} else {
+		len = func(ftp, NULL); /* simply do original command */
+	}
+
+	/* invalidate the (read) cache in case there was a write operation
+	 * or an error on read/dir
+	 */
+	hmcdrv_cache_file.id = HMCDRV_FTP_NOOP;
+	hmcdrv_cache_file.fsize = LLONG_MAX;
+	hmcdrv_cache_file.ofs = -1;
+
+	return len;
+}
+
+/**
+ * hmcdrv_cache_startup() - startup of HMC drive cache
+ * @cachesize: cache size
+ *
+ * Return: 0 on success, else a (negative) error code
+ */
+int hmcdrv_cache_startup(size_t cachesize)
+{
+	if (cachesize > 0) { /* perform caching ? */
+		hmcdrv_cache_order = get_order(cachesize);
+		hmcdrv_cache_file.content =
+			(void *) __get_free_pages(GFP_KERNEL | GFP_DMA,
+						  hmcdrv_cache_order);
+
+		if (!hmcdrv_cache_file.content) {
+			pr_err("Allocating the requested cache size of %zu bytes failed\n",
+			       cachesize);
+			return -ENOMEM;
+		}
+
+		pr_debug("content cache enabled, size is %zu bytes\n",
+			 cachesize);
+	}
+
+	hmcdrv_cache_file.len = cachesize;
+	return 0;
+}
+
+/**
+ * hmcdrv_cache_shutdown() - shutdown of HMC drive cache
+ */
+void hmcdrv_cache_shutdown(void)
+{
+	if (hmcdrv_cache_file.content) {
+		free_pages((unsigned long) hmcdrv_cache_file.content,
+			   hmcdrv_cache_order);
+		hmcdrv_cache_file.content = NULL;
+	}
+
+	hmcdrv_cache_file.id = HMCDRV_FTP_NOOP;
+	hmcdrv_cache_file.fsize = LLONG_MAX;
+	hmcdrv_cache_file.ofs = -1;
+	hmcdrv_cache_file.len = 0; /* no cache */
+}
diff --git a/drivers/s390/char/hmcdrv_cache.h b/drivers/s390/char/hmcdrv_cache.h
new file mode 100644
index 000000000000..a14b57526781
--- /dev/null
+++ b/drivers/s390/char/hmcdrv_cache.h
@@ -0,0 +1,24 @@
+/*
+ *    SE/HMC Drive (Read) Cache Functions
+ *
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ */
+
+#ifndef __HMCDRV_CACHE_H__
+#define __HMCDRV_CACHE_H__
+
+#include <linux/mmzone.h>
+#include "hmcdrv_ftp.h"
+
+#define HMCDRV_CACHE_SIZE_DFLT	(MAX_ORDER_NR_PAGES * PAGE_SIZE / 2UL)
+
+typedef ssize_t (*hmcdrv_cache_ftpfunc)(const struct hmcdrv_ftp_cmdspec *ftp,
+					size_t *fsize);
+
+ssize_t hmcdrv_cache_cmd(const struct hmcdrv_ftp_cmdspec *ftp,
+			 hmcdrv_cache_ftpfunc func);
+int hmcdrv_cache_startup(size_t cachesize);
+void hmcdrv_cache_shutdown(void);
+
+#endif	 /* __HMCDRV_CACHE_H__ */
diff --git a/drivers/s390/char/hmcdrv_dev.c b/drivers/s390/char/hmcdrv_dev.c
new file mode 100644
index 000000000000..0c5176179c17
--- /dev/null
+++ b/drivers/s390/char/hmcdrv_dev.c
@@ -0,0 +1,370 @@
+/*
+ *    HMC Drive CD/DVD Device
+ *
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ *
+ *    This file provides a Linux "misc" character device for access to an
+ *    assigned HMC drive CD/DVD-ROM. It works as follows: First create the
+ *    device by calling hmcdrv_dev_init(). After open() a lseek(fd, 0,
+ *    SEEK_END) indicates that a new FTP command follows (not needed on the
+ *    first command after open). Then write() the FTP command ASCII string
+ *    to it, e.g. "dir /" or "nls <directory>" or "get <filename>". At the
+ *    end read() the response.
+ */
+
+#define KMSG_COMPONENT "hmcdrv"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/cdev.h>
+#include <linux/miscdevice.h>
+#include <linux/device.h>
+#include <linux/capability.h>
+#include <linux/delay.h>
+#include <linux/uaccess.h>
+
+#include "hmcdrv_dev.h"
+#include "hmcdrv_ftp.h"
+
+/* If the following macro is defined, then the HMC device creates it's own
+ * separated device class (and dynamically assigns a major number). If not
+ * defined then the HMC device is assigned to the "misc" class devices.
+ *
+#define HMCDRV_DEV_CLASS "hmcftp"
+ */
+
+#define HMCDRV_DEV_NAME  "hmcdrv"
+#define HMCDRV_DEV_BUSY_DELAY	 500 /* delay between -EBUSY trials in ms */
+#define HMCDRV_DEV_BUSY_RETRIES  3   /* number of retries on -EBUSY */
+
+struct hmcdrv_dev_node {
+
+#ifdef HMCDRV_DEV_CLASS
+	struct cdev dev; /* character device structure */
+	umode_t mode;	 /* mode of device node (unused, zero) */
+#else
+	struct miscdevice dev; /* "misc" device structure */
+#endif
+
+};
+
+static int hmcdrv_dev_open(struct inode *inode, struct file *fp);
+static int hmcdrv_dev_release(struct inode *inode, struct file *fp);
+static loff_t hmcdrv_dev_seek(struct file *fp, loff_t pos, int whence);
+static ssize_t hmcdrv_dev_read(struct file *fp, char __user *ubuf,
+			       size_t len, loff_t *pos);
+static ssize_t hmcdrv_dev_write(struct file *fp, const char __user *ubuf,
+				size_t len, loff_t *pos);
+static ssize_t hmcdrv_dev_transfer(char __kernel *cmd, loff_t offset,
+				   char __user *buf, size_t len);
+
+/*
+ * device operations
+ */
+static const struct file_operations hmcdrv_dev_fops = {
+	.open = hmcdrv_dev_open,
+	.llseek = hmcdrv_dev_seek,
+	.release = hmcdrv_dev_release,
+	.read = hmcdrv_dev_read,
+	.write = hmcdrv_dev_write,
+};
+
+static struct hmcdrv_dev_node hmcdrv_dev; /* HMC device struct (static) */
+
+#ifdef HMCDRV_DEV_CLASS
+
+static struct class *hmcdrv_dev_class; /* device class pointer */
+static dev_t hmcdrv_dev_no; /* device number (major/minor) */
+
+/**
+ * hmcdrv_dev_name() - provides a naming hint for a device node in /dev
+ * @dev: device for which the naming/mode hint is
+ * @mode: file mode for device node created in /dev
+ *
+ * See: devtmpfs.c, function devtmpfs_create_node()
+ *
+ * Return: recommended device file name in /dev
+ */
+static char *hmcdrv_dev_name(struct device *dev, umode_t *mode)
+{
+	char *nodename = NULL;
+	const char *devname = dev_name(dev); /* kernel device name */
+
+	if (devname)
+		nodename = kasprintf(GFP_KERNEL, "%s", devname);
+
+	/* on device destroy (rmmod) the mode pointer may be NULL
+	 */
+	if (mode)
+		*mode = hmcdrv_dev.mode;
+
+	return nodename;
+}
+
+#endif	/* HMCDRV_DEV_CLASS */
+
+/*
+ * open()
+ */
+static int hmcdrv_dev_open(struct inode *inode, struct file *fp)
+{
+	int rc;
+
+	/* check for non-blocking access, which is really unsupported
+	 */
+	if (fp->f_flags & O_NONBLOCK)
+		return -EINVAL;
+
+	/* Because it makes no sense to open this device read-only (then a
+	 * FTP command cannot be emitted), we respond with an error.
+	 */
+	if ((fp->f_flags & O_ACCMODE) == O_RDONLY)
+		return -EINVAL;
+
+	/* prevent unloading this module as long as anyone holds the
+	 * device file open - so increment the reference count here
+	 */
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	fp->private_data = NULL; /* no command yet */
+	rc = hmcdrv_ftp_startup();
+	if (rc)
+		module_put(THIS_MODULE);
+
+	pr_debug("open file '/dev/%s' with return code %d\n",
+		 fp->f_dentry->d_name.name, rc);
+	return rc;
+}
+
+/*
+ * release()
+ */
+static int hmcdrv_dev_release(struct inode *inode, struct file *fp)
+{
+	pr_debug("closing file '/dev/%s'\n", fp->f_dentry->d_name.name);
+	kfree(fp->private_data);
+	fp->private_data = NULL;
+	hmcdrv_ftp_shutdown();
+	module_put(THIS_MODULE);
+	return 0;
+}
+
+/*
+ * lseek()
+ */
+static loff_t hmcdrv_dev_seek(struct file *fp, loff_t pos, int whence)
+{
+	switch (whence) {
+	case SEEK_CUR: /* relative to current file position */
+		pos += fp->f_pos; /* new position stored in 'pos' */
+		break;
+
+	case SEEK_SET: /* absolute (relative to beginning of file) */
+		break; /* SEEK_SET */
+
+		/* We use SEEK_END as a special indicator for a SEEK_SET
+		 * (set absolute position), combined with a FTP command
+		 * clear.
+		 */
+	case SEEK_END:
+		if (fp->private_data) {
+			kfree(fp->private_data);
+			fp->private_data = NULL;
+		}
+
+		break; /* SEEK_END */
+
+	default: /* SEEK_DATA, SEEK_HOLE: unsupported */
+		return -EINVAL;
+	}
+
+	if (pos < 0)
+		return -EINVAL;
+
+	if (fp->f_pos != pos)
+		++fp->f_version;
+
+	fp->f_pos = pos;
+	return pos;
+}
+
+/*
+ * transfer (helper function)
+ */
+static ssize_t hmcdrv_dev_transfer(char __kernel *cmd, loff_t offset,
+				   char __user *buf, size_t len)
+{
+	ssize_t retlen;
+	unsigned trials = HMCDRV_DEV_BUSY_RETRIES;
+
+	do {
+		retlen = hmcdrv_ftp_cmd(cmd, offset, buf, len);
+
+		if (retlen != -EBUSY)
+			break;
+
+		msleep(HMCDRV_DEV_BUSY_DELAY);
+
+	} while (--trials > 0);
+
+	return retlen;
+}
+
+/*
+ * read()
+ */
+static ssize_t hmcdrv_dev_read(struct file *fp, char __user *ubuf,
+			       size_t len, loff_t *pos)
+{
+	ssize_t retlen;
+
+	if (((fp->f_flags & O_ACCMODE) == O_WRONLY) ||
+	    (fp->private_data == NULL)) { /* no FTP cmd defined ? */
+		return -EBADF;
+	}
+
+	retlen = hmcdrv_dev_transfer((char *) fp->private_data,
+				     *pos, ubuf, len);
+
+	pr_debug("read from file '/dev/%s' at %lld returns %zd/%zu\n",
+		 fp->f_dentry->d_name.name, (long long) *pos, retlen, len);
+
+	if (retlen > 0)
+		*pos += retlen;
+
+	return retlen;
+}
+
+/*
+ * write()
+ */
+static ssize_t hmcdrv_dev_write(struct file *fp, const char __user *ubuf,
+				size_t len, loff_t *pos)
+{
+	ssize_t retlen;
+
+	pr_debug("writing file '/dev/%s' at pos. %lld with length %zd\n",
+		 fp->f_dentry->d_name.name, (long long) *pos, len);
+
+	if (!fp->private_data) { /* first expect a cmd write */
+		fp->private_data = kmalloc(len + 1, GFP_KERNEL);
+
+		if (!fp->private_data)
+			return -ENOMEM;
+
+		if (!copy_from_user(fp->private_data, ubuf, len)) {
+			((char *)fp->private_data)[len] = '\0';
+			return len;
+		}
+
+		kfree(fp->private_data);
+		fp->private_data = NULL;
+		return -EFAULT;
+	}
+
+	retlen = hmcdrv_dev_transfer((char *) fp->private_data,
+				     *pos, (char __user *) ubuf, len);
+	if (retlen > 0)
+		*pos += retlen;
+
+	pr_debug("write to file '/dev/%s' returned %zd\n",
+		 fp->f_dentry->d_name.name, retlen);
+
+	return retlen;
+}
+
+/**
+ * hmcdrv_dev_init() - creates a HMC drive CD/DVD device
+ *
+ * This function creates a HMC drive CD/DVD kernel device and an associated
+ * device under /dev, using a dynamically allocated major number.
+ *
+ * Return: 0 on success, else an error code.
+ */
+int hmcdrv_dev_init(void)
+{
+	int rc;
+
+#ifdef HMCDRV_DEV_CLASS
+	struct device *dev;
+
+	rc = alloc_chrdev_region(&hmcdrv_dev_no, 0, 1, HMCDRV_DEV_NAME);
+
+	if (rc)
+		goto out_err;
+
+	cdev_init(&hmcdrv_dev.dev, &hmcdrv_dev_fops);
+	hmcdrv_dev.dev.owner = THIS_MODULE;
+	rc = cdev_add(&hmcdrv_dev.dev, hmcdrv_dev_no, 1);
+
+	if (rc)
+		goto out_unreg;
+
+	/* At this point the character device exists in the kernel (see
+	 * /proc/devices), but not under /dev nor /sys/devices/virtual. So
+	 * we have to create an associated class (see /sys/class).
+	 */
+	hmcdrv_dev_class = class_create(THIS_MODULE, HMCDRV_DEV_CLASS);
+
+	if (IS_ERR(hmcdrv_dev_class)) {
+		rc = PTR_ERR(hmcdrv_dev_class);
+		goto out_devdel;
+	}
+
+	/* Finally a device node in /dev has to be established (as 'mkdev'
+	 * does from the command line). Notice that assignment of a device
+	 * node name/mode function is optional (only for mode != 0600).
+	 */
+	hmcdrv_dev.mode = 0; /* "unset" */
+	hmcdrv_dev_class->devnode = hmcdrv_dev_name;
+
+	dev = device_create(hmcdrv_dev_class, NULL, hmcdrv_dev_no, NULL,
+			    "%s", HMCDRV_DEV_NAME);
+	if (!IS_ERR(dev))
+		return 0;
+
+	rc = PTR_ERR(dev);
+	class_destroy(hmcdrv_dev_class);
+	hmcdrv_dev_class = NULL;
+
+out_devdel:
+	cdev_del(&hmcdrv_dev.dev);
+
+out_unreg:
+	unregister_chrdev_region(hmcdrv_dev_no, 1);
+
+out_err:
+
+#else  /* !HMCDRV_DEV_CLASS */
+	hmcdrv_dev.dev.minor = MISC_DYNAMIC_MINOR;
+	hmcdrv_dev.dev.name = HMCDRV_DEV_NAME;
+	hmcdrv_dev.dev.fops = &hmcdrv_dev_fops;
+	hmcdrv_dev.dev.mode = 0; /* finally produces 0600 */
+	rc = misc_register(&hmcdrv_dev.dev);
+#endif	/* HMCDRV_DEV_CLASS */
+
+	return rc;
+}
+
+/**
+ * hmcdrv_dev_exit() - destroys a HMC drive CD/DVD device
+ */
+void hmcdrv_dev_exit(void)
+{
+#ifdef HMCDRV_DEV_CLASS
+	if (!IS_ERR_OR_NULL(hmcdrv_dev_class)) {
+		device_destroy(hmcdrv_dev_class, hmcdrv_dev_no);
+		class_destroy(hmcdrv_dev_class);
+	}
+
+	cdev_del(&hmcdrv_dev.dev);
+	unregister_chrdev_region(hmcdrv_dev_no, 1);
+#else  /* !HMCDRV_DEV_CLASS */
+	misc_deregister(&hmcdrv_dev.dev);
+#endif	/* HMCDRV_DEV_CLASS */
+}
diff --git a/drivers/s390/char/hmcdrv_dev.h b/drivers/s390/char/hmcdrv_dev.h
new file mode 100644
index 000000000000..cb17f07e02de
--- /dev/null
+++ b/drivers/s390/char/hmcdrv_dev.h
@@ -0,0 +1,14 @@
+/*
+ *    SE/HMC Drive FTP Device
+ *
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ */
+
+#ifndef __HMCDRV_DEV_H__
+#define __HMCDRV_DEV_H__
+
+int hmcdrv_dev_init(void);
+void hmcdrv_dev_exit(void);
+
+#endif	 /* __HMCDRV_DEV_H__ */
diff --git a/drivers/s390/char/hmcdrv_ftp.c b/drivers/s390/char/hmcdrv_ftp.c
new file mode 100644
index 000000000000..4bd63322fc29
--- /dev/null
+++ b/drivers/s390/char/hmcdrv_ftp.c
@@ -0,0 +1,343 @@
+/*
+ *    HMC Drive FTP Services
+ *
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ */
+
+#define KMSG_COMPONENT "hmcdrv"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/export.h>
+
+#include <linux/ctype.h>
+#include <linux/crc16.h>
+
+#include "hmcdrv_ftp.h"
+#include "hmcdrv_cache.h"
+#include "sclp_ftp.h"
+#include "diag_ftp.h"
+
+/**
+ * struct hmcdrv_ftp_ops - HMC drive FTP operations
+ * @startup: startup function
+ * @shutdown: shutdown function
+ * @cmd: FTP transfer function
+ */
+struct hmcdrv_ftp_ops {
+	int (*startup)(void);
+	void (*shutdown)(void);
+	ssize_t (*transfer)(const struct hmcdrv_ftp_cmdspec *ftp,
+			    size_t *fsize);
+};
+
+static enum hmcdrv_ftp_cmdid hmcdrv_ftp_cmd_getid(const char *cmd, int len);
+static int hmcdrv_ftp_parse(char *cmd, struct hmcdrv_ftp_cmdspec *ftp);
+
+static struct hmcdrv_ftp_ops *hmcdrv_ftp_funcs; /* current operations */
+static DEFINE_MUTEX(hmcdrv_ftp_mutex); /* mutex for hmcdrv_ftp_funcs */
+static unsigned hmcdrv_ftp_refcnt; /* start/shutdown reference counter */
+
+/**
+ * hmcdrv_ftp_cmd_getid() - determine FTP command ID from a command string
+ * @cmd: FTP command string (NOT zero-terminated)
+ * @len: length of FTP command string in @cmd
+ */
+static enum hmcdrv_ftp_cmdid hmcdrv_ftp_cmd_getid(const char *cmd, int len)
+{
+	/* HMC FTP command descriptor */
+	struct hmcdrv_ftp_cmd_desc {
+		const char *str;	   /* command string */
+		enum hmcdrv_ftp_cmdid cmd; /* associated command as enum */
+	};
+
+	/* Description of all HMC drive FTP commands
+	 *
+	 * Notes:
+	 * 1. Array size should be a prime number.
+	 * 2. Do not change the order of commands in table (because the
+	 *    index is determined by CRC % ARRAY_SIZE).
+	 * 3. Original command 'nlist' was renamed, else the CRC would
+	 *    collide with 'append' (see point 2).
+	 */
+	static const struct hmcdrv_ftp_cmd_desc ftpcmds[7] = {
+
+		{.str = "get", /* [0] get (CRC = 0x68eb) */
+		 .cmd = HMCDRV_FTP_GET},
+		{.str = "dir", /* [1] dir (CRC = 0x6a9e) */
+		 .cmd = HMCDRV_FTP_DIR},
+		{.str = "delete", /* [2] delete (CRC = 0x53ae) */
+		 .cmd = HMCDRV_FTP_DELETE},
+		{.str = "nls", /* [3] nls (CRC = 0xf87c) */
+		 .cmd = HMCDRV_FTP_NLIST},
+		{.str = "put", /* [4] put (CRC = 0xac56) */
+		 .cmd = HMCDRV_FTP_PUT},
+		{.str = "append", /* [5] append (CRC = 0xf56e) */
+		 .cmd = HMCDRV_FTP_APPEND},
+		{.str = NULL} /* [6] unused */
+	};
+
+	const struct hmcdrv_ftp_cmd_desc *pdesc;
+
+	u16 crc = 0xffffU;
+
+	if (len == 0)
+		return HMCDRV_FTP_NOOP; /* error indiactor */
+
+	crc = crc16(crc, cmd, len);
+	pdesc = ftpcmds + (crc % ARRAY_SIZE(ftpcmds));
+	pr_debug("FTP command '%s' has CRC 0x%04x, at table pos. %lu\n",
+		 cmd, crc, (crc % ARRAY_SIZE(ftpcmds)));
+
+	if (!pdesc->str || strncmp(pdesc->str, cmd, len))
+		return HMCDRV_FTP_NOOP;
+
+	pr_debug("FTP command '%s' found, with ID %d\n",
+		 pdesc->str, pdesc->cmd);
+
+	return pdesc->cmd;
+}
+
+/**
+ * hmcdrv_ftp_parse() - HMC drive FTP command parser
+ * @cmd: FTP command string "<cmd> <filename>"
+ * @ftp: Pointer to FTP command specification buffer (output)
+ *
+ * Return: 0 on success, else a (negative) error code
+ */
+static int hmcdrv_ftp_parse(char *cmd, struct hmcdrv_ftp_cmdspec *ftp)
+{
+	char *start;
+	int argc = 0;
+
+	ftp->id = HMCDRV_FTP_NOOP;
+	ftp->fname = NULL;
+
+	while (*cmd != '\0') {
+
+		while (isspace(*cmd))
+			++cmd;
+
+		if (*cmd == '\0')
+			break;
+
+		start = cmd;
+
+		switch (argc) {
+		case 0: /* 1st argument (FTP command) */
+			while ((*cmd != '\0') && !isspace(*cmd))
+				++cmd;
+			ftp->id = hmcdrv_ftp_cmd_getid(start, cmd - start);
+			break;
+		case 1: /* 2nd / last argument (rest of line) */
+			while ((*cmd != '\0') && !iscntrl(*cmd))
+				++cmd;
+			ftp->fname = start;
+			/* fall through */
+		default:
+			*cmd = '\0';
+			break;
+		} /* switch */
+
+		++argc;
+	} /* while */
+
+	if (!ftp->fname || (ftp->id == HMCDRV_FTP_NOOP))
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * hmcdrv_ftp_do() - perform a HMC drive FTP, with data from kernel-space
+ * @ftp: pointer to FTP command specification
+ *
+ * Return: number of bytes read/written or a negative error code
+ */
+ssize_t hmcdrv_ftp_do(const struct hmcdrv_ftp_cmdspec *ftp)
+{
+	ssize_t len;
+
+	mutex_lock(&hmcdrv_ftp_mutex);
+
+	if (hmcdrv_ftp_funcs && hmcdrv_ftp_refcnt) {
+		pr_debug("starting transfer, cmd %d for '%s' at %lld with %zd bytes\n",
+			 ftp->id, ftp->fname, (long long) ftp->ofs, ftp->len);
+		len = hmcdrv_cache_cmd(ftp, hmcdrv_ftp_funcs->transfer);
+	} else {
+		len = -ENXIO;
+	}
+
+	mutex_unlock(&hmcdrv_ftp_mutex);
+	return len;
+}
+EXPORT_SYMBOL(hmcdrv_ftp_do);
+
+/**
+ * hmcdrv_ftp_probe() - probe for the HMC drive FTP service
+ *
+ * Return: 0 if service is available, else an (negative) error code
+ */
+int hmcdrv_ftp_probe(void)
+{
+	int rc;
+
+	struct hmcdrv_ftp_cmdspec ftp = {
+		.id = HMCDRV_FTP_NOOP,
+		.ofs = 0,
+		.fname = "",
+		.len = PAGE_SIZE
+	};
+
+	ftp.buf = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+
+	if (!ftp.buf)
+		return -ENOMEM;
+
+	rc = hmcdrv_ftp_startup();
+
+	if (rc)
+		return rc;
+
+	rc = hmcdrv_ftp_do(&ftp);
+	free_page((unsigned long) ftp.buf);
+	hmcdrv_ftp_shutdown();
+
+	switch (rc) {
+	case -ENOENT: /* no such file/media or currently busy, */
+	case -EBUSY:  /* but service seems to be available */
+		rc = 0;
+		break;
+	default: /* leave 'rc' as it is for [0, -EPERM, -E...] */
+		if (rc > 0)
+			rc = 0; /* clear length (success) */
+		break;
+	} /* switch */
+
+	return rc;
+}
+EXPORT_SYMBOL(hmcdrv_ftp_probe);
+
+/**
+ * hmcdrv_ftp_cmd() - Perform a HMC drive FTP, with data from user-space
+ *
+ * @cmd: FTP command string "<cmd> <filename>"
+ * @offset: file position to read/write
+ * @buf: user-space buffer for read/written directory/file
+ * @len: size of @buf (read/dir) or number of bytes to write
+ *
+ * This function must not be called before hmcdrv_ftp_startup() was called.
+ *
+ * Return: number of bytes read/written or a negative error code
+ */
+ssize_t hmcdrv_ftp_cmd(char __kernel *cmd, loff_t offset,
+		       char __user *buf, size_t len)
+{
+	int order;
+
+	struct hmcdrv_ftp_cmdspec ftp = {.len = len, .ofs = offset};
+	ssize_t retlen = hmcdrv_ftp_parse(cmd, &ftp);
+
+	if (retlen)
+		return retlen;
+
+	order = get_order(ftp.len);
+	ftp.buf = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, order);
+
+	if (!ftp.buf)
+		return -ENOMEM;
+
+	switch (ftp.id) {
+	case HMCDRV_FTP_DIR:
+	case HMCDRV_FTP_NLIST:
+	case HMCDRV_FTP_GET:
+		retlen = hmcdrv_ftp_do(&ftp);
+
+		if ((retlen >= 0) &&
+		    copy_to_user(buf, ftp.buf, retlen))
+			retlen = -EFAULT;
+		break;
+
+	case HMCDRV_FTP_PUT:
+	case HMCDRV_FTP_APPEND:
+		if (!copy_from_user(ftp.buf, buf, ftp.len))
+			retlen = hmcdrv_ftp_do(&ftp);
+		else
+			retlen = -EFAULT;
+		break;
+
+	case HMCDRV_FTP_DELETE:
+		retlen = hmcdrv_ftp_do(&ftp);
+		break;
+
+	default:
+		retlen = -EOPNOTSUPP;
+		break;
+	}
+
+	free_pages((unsigned long) ftp.buf, order);
+	return retlen;
+}
+
+/**
+ * hmcdrv_ftp_startup() - startup of HMC drive FTP functionality for a
+ * dedicated (owner) instance
+ *
+ * Return: 0 on success, else an (negative) error code
+ */
+int hmcdrv_ftp_startup(void)
+{
+	static struct hmcdrv_ftp_ops hmcdrv_ftp_zvm = {
+		.startup = diag_ftp_startup,
+		.shutdown = diag_ftp_shutdown,
+		.transfer = diag_ftp_cmd
+	};
+
+	static struct hmcdrv_ftp_ops hmcdrv_ftp_lpar = {
+		.startup = sclp_ftp_startup,
+		.shutdown = sclp_ftp_shutdown,
+		.transfer = sclp_ftp_cmd
+	};
+
+	int rc = 0;
+
+	mutex_lock(&hmcdrv_ftp_mutex); /* block transfers while start-up */
+
+	if (hmcdrv_ftp_refcnt == 0) {
+		if (MACHINE_IS_VM)
+			hmcdrv_ftp_funcs = &hmcdrv_ftp_zvm;
+		else if (MACHINE_IS_LPAR || MACHINE_IS_KVM)
+			hmcdrv_ftp_funcs = &hmcdrv_ftp_lpar;
+		else
+			rc = -EOPNOTSUPP;
+
+		if (hmcdrv_ftp_funcs)
+			rc = hmcdrv_ftp_funcs->startup();
+	}
+
+	if (!rc)
+		++hmcdrv_ftp_refcnt;
+
+	mutex_unlock(&hmcdrv_ftp_mutex);
+	return rc;
+}
+EXPORT_SYMBOL(hmcdrv_ftp_startup);
+
+/**
+ * hmcdrv_ftp_shutdown() - shutdown of HMC drive FTP functionality for a
+ * dedicated (owner) instance
+ */
+void hmcdrv_ftp_shutdown(void)
+{
+	mutex_lock(&hmcdrv_ftp_mutex);
+	--hmcdrv_ftp_refcnt;
+
+	if ((hmcdrv_ftp_refcnt == 0) && hmcdrv_ftp_funcs)
+		hmcdrv_ftp_funcs->shutdown();
+
+	mutex_unlock(&hmcdrv_ftp_mutex);
+}
+EXPORT_SYMBOL(hmcdrv_ftp_shutdown);
diff --git a/drivers/s390/char/hmcdrv_ftp.h b/drivers/s390/char/hmcdrv_ftp.h
new file mode 100644
index 000000000000..f3643a7b3676
--- /dev/null
+++ b/drivers/s390/char/hmcdrv_ftp.h
@@ -0,0 +1,63 @@
+/*
+ *    SE/HMC Drive FTP Services
+ *
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ */
+
+#ifndef __HMCDRV_FTP_H__
+#define __HMCDRV_FTP_H__
+
+#include <linux/types.h> /* size_t, loff_t */
+
+/*
+ * HMC drive FTP Service max. length of path (w/ EOS)
+ */
+#define HMCDRV_FTP_FIDENT_MAX 192
+
+/**
+ * enum hmcdrv_ftp_cmdid - HMC drive FTP commands
+ * @HMCDRV_FTP_NOOP: do nothing (only for probing)
+ * @HMCDRV_FTP_GET: read a file
+ * @HMCDRV_FTP_PUT: (over-) write a file
+ * @HMCDRV_FTP_APPEND: append to a file
+ * @HMCDRV_FTP_DIR: list directory long (ls -l)
+ * @HMCDRV_FTP_NLIST: list files, no directories (name list)
+ * @HMCDRV_FTP_DELETE: delete a file
+ * @HMCDRV_FTP_CANCEL: cancel operation (SCLP/LPAR only)
+ */
+enum hmcdrv_ftp_cmdid {
+	HMCDRV_FTP_NOOP = 0,
+	HMCDRV_FTP_GET = 1,
+	HMCDRV_FTP_PUT = 2,
+	HMCDRV_FTP_APPEND = 3,
+	HMCDRV_FTP_DIR = 4,
+	HMCDRV_FTP_NLIST = 5,
+	HMCDRV_FTP_DELETE = 6,
+	HMCDRV_FTP_CANCEL = 7
+};
+
+/**
+ * struct hmcdrv_ftp_cmdspec - FTP command specification
+ * @id: FTP command ID
+ * @ofs: offset in file
+ * @fname: filename (ASCII), null-terminated
+ * @buf: kernel-space transfer data buffer, 4k aligned
+ * @len: (max) number of bytes to transfer from/to @buf
+ */
+struct hmcdrv_ftp_cmdspec {
+	enum hmcdrv_ftp_cmdid id;
+	loff_t ofs;
+	const char *fname;
+	void __kernel *buf;
+	size_t len;
+};
+
+int hmcdrv_ftp_startup(void);
+void hmcdrv_ftp_shutdown(void);
+int hmcdrv_ftp_probe(void);
+ssize_t hmcdrv_ftp_do(const struct hmcdrv_ftp_cmdspec *ftp);
+ssize_t hmcdrv_ftp_cmd(char __kernel *cmd, loff_t offset,
+		       char __user *buf, size_t len);
+
+#endif	 /* __HMCDRV_FTP_H__ */
diff --git a/drivers/s390/char/hmcdrv_mod.c b/drivers/s390/char/hmcdrv_mod.c
new file mode 100644
index 000000000000..505c6a78ee1a
--- /dev/null
+++ b/drivers/s390/char/hmcdrv_mod.c
@@ -0,0 +1,64 @@
+/*
+ *    HMC Drive DVD Module
+ *
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ */
+
+#define KMSG_COMPONENT "hmcdrv"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/version.h>
+#include <linux/stat.h>
+
+#include "hmcdrv_ftp.h"
+#include "hmcdrv_dev.h"
+#include "hmcdrv_cache.h"
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Copyright 2013 IBM Corporation");
+MODULE_DESCRIPTION("HMC drive DVD access");
+
+/*
+ * module parameter 'cachesize'
+ */
+static size_t hmcdrv_mod_cachesize = HMCDRV_CACHE_SIZE_DFLT;
+module_param_named(cachesize, hmcdrv_mod_cachesize, ulong, S_IRUGO);
+
+/**
+ * hmcdrv_mod_init() - module init function
+ */
+static int __init hmcdrv_mod_init(void)
+{
+	int rc = hmcdrv_ftp_probe(); /* perform w/o cache */
+
+	if (rc)
+		return rc;
+
+	rc = hmcdrv_cache_startup(hmcdrv_mod_cachesize);
+
+	if (rc)
+		return rc;
+
+	rc = hmcdrv_dev_init();
+
+	if (rc)
+		hmcdrv_cache_shutdown();
+
+	return rc;
+}
+
+/**
+ * hmcdrv_mod_exit() - module exit function
+ */
+static void __exit hmcdrv_mod_exit(void)
+{
+	hmcdrv_dev_exit();
+	hmcdrv_cache_shutdown();
+}
+
+module_init(hmcdrv_mod_init);
+module_exit(hmcdrv_mod_exit);
diff --git a/drivers/s390/char/sclp.h b/drivers/s390/char/sclp.h
index a68b5ec7d042..a88069f8c677 100644
--- a/drivers/s390/char/sclp.h
+++ b/drivers/s390/char/sclp.h
@@ -19,6 +19,7 @@
 
 #define EVTYP_OPCMD		0x01
 #define EVTYP_MSG		0x02
+#define EVTYP_DIAG_TEST		0x07
 #define EVTYP_STATECHANGE	0x08
 #define EVTYP_PMSGCMD		0x09
 #define EVTYP_CNTLPROGOPCMD	0x20
@@ -32,6 +33,7 @@
 
 #define EVTYP_OPCMD_MASK	0x80000000
 #define EVTYP_MSG_MASK		0x40000000
+#define EVTYP_DIAG_TEST_MASK	0x02000000
 #define EVTYP_STATECHANGE_MASK	0x01000000
 #define EVTYP_PMSGCMD_MASK	0x00800000
 #define EVTYP_CTLPROGOPCMD_MASK	0x00000001
diff --git a/drivers/s390/char/sclp_diag.h b/drivers/s390/char/sclp_diag.h
new file mode 100644
index 000000000000..59c4afa5e670
--- /dev/null
+++ b/drivers/s390/char/sclp_diag.h
@@ -0,0 +1,89 @@
+/*
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ */
+
+#ifndef _SCLP_DIAG_H
+#define _SCLP_DIAG_H
+
+#include <linux/types.h>
+
+/* return codes for Diagnostic Test FTP Service, as indicated in member
+ * sclp_diag_ftp::ldflg
+ */
+#define SCLP_DIAG_FTP_OK	0x80U /* success */
+#define SCLP_DIAG_FTP_LDFAIL	0x01U /* load failed */
+#define SCLP_DIAG_FTP_LDNPERM	0x02U /* not allowed */
+#define SCLP_DIAG_FTP_LDRUNS	0x03U /* LD runs */
+#define SCLP_DIAG_FTP_LDNRUNS	0x04U /* LD does not run */
+
+#define SCLP_DIAG_FTP_XPCX	0x80 /* PCX communication code */
+#define SCLP_DIAG_FTP_ROUTE	4 /* routing code for new FTP service */
+
+/*
+ * length of Diagnostic Test FTP Service event buffer
+ */
+#define SCLP_DIAG_FTP_EVBUF_LEN				\
+	(offsetof(struct sclp_diag_evbuf, mdd) +	\
+	 sizeof(struct sclp_diag_ftp))
+
+/**
+ * struct sclp_diag_ftp - Diagnostic Test FTP Service model-dependent data
+ * @pcx: code for PCX communication (should be 0x80)
+ * @ldflg: load flag (see defines above)
+ * @cmd: FTP command
+ * @pgsize: page size (0 = 4kB, 1 = large page size)
+ * @srcflg: source flag
+ * @spare: reserved (zeroes)
+ * @offset: file offset
+ * @fsize: file size
+ * @length: buffer size resp. bytes transferred
+ * @failaddr: failing address
+ * @bufaddr: buffer address, virtual
+ * @asce: region or segment table designation
+ * @fident: file name (ASCII, zero-terminated)
+ */
+struct sclp_diag_ftp {
+	u8 pcx;
+	u8 ldflg;
+	u8 cmd;
+	u8 pgsize;
+	u8 srcflg;
+	u8 spare;
+	u64 offset;
+	u64 fsize;
+	u64 length;
+	u64 failaddr;
+	u64 bufaddr;
+	u64 asce;
+
+	u8 fident[256];
+} __packed;
+
+/**
+ * struct sclp_diag_evbuf - Diagnostic Test (ET7) Event Buffer
+ * @hdr: event buffer header
+ * @route: diagnostic route
+ * @mdd: model-dependent data (@route dependent)
+ */
+struct sclp_diag_evbuf {
+	struct evbuf_header hdr;
+	u16 route;
+
+	union {
+		struct sclp_diag_ftp ftp;
+	} mdd;
+} __packed;
+
+/**
+ * struct sclp_diag_sccb - Diagnostic Test (ET7) SCCB
+ * @hdr: SCCB header
+ * @evbuf: event buffer
+ */
+struct sclp_diag_sccb {
+
+	struct sccb_header hdr;
+	struct sclp_diag_evbuf evbuf;
+} __packed;
+
+#endif /* _SCLP_DIAG_H */
diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index 1918d9dff45d..5bd6cb145a87 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -281,7 +281,7 @@ out:
 
 static unsigned int __init sclp_con_check_linemode(struct init_sccb *sccb)
 {
-	if (!(sccb->sclp_send_mask & (EVTYP_OPCMD_MASK | EVTYP_PMSGCMD_MASK)))
+	if (!(sccb->sclp_send_mask & EVTYP_OPCMD_MASK))
 		return 0;
 	if (!(sccb->sclp_receive_mask & (EVTYP_MSG_MASK | EVTYP_PMSGCMD_MASK)))
 		return 0;
diff --git a/drivers/s390/char/sclp_ftp.c b/drivers/s390/char/sclp_ftp.c
new file mode 100644
index 000000000000..6561cc5b2d5d
--- /dev/null
+++ b/drivers/s390/char/sclp_ftp.c
@@ -0,0 +1,275 @@
+/*
+ *    SCLP Event Type (ET) 7 - Diagnostic Test FTP Services, useable on LPAR
+ *
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ *
+ */
+
+#define KMSG_COMPONENT "hmcdrv"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/wait.h>
+#include <linux/string.h>
+#include <linux/jiffies.h>
+#include <asm/sysinfo.h>
+#include <asm/ebcdic.h>
+
+#include "sclp.h"
+#include "sclp_diag.h"
+#include "sclp_ftp.h"
+
+static DECLARE_COMPLETION(sclp_ftp_rx_complete);
+static u8 sclp_ftp_ldflg;
+static u64 sclp_ftp_fsize;
+static u64 sclp_ftp_length;
+
+/**
+ * sclp_ftp_txcb() - Diagnostic Test FTP services SCLP command callback
+ */
+static void sclp_ftp_txcb(struct sclp_req *req, void *data)
+{
+	struct completion *completion = data;
+
+#ifdef DEBUG
+	pr_debug("SCLP (ET7) TX-IRQ, SCCB @ 0x%p: %*phN\n",
+		 req->sccb, 24, req->sccb);
+#endif
+	complete(completion);
+}
+
+/**
+ * sclp_ftp_rxcb() - Diagnostic Test FTP services receiver event callback
+ */
+static void sclp_ftp_rxcb(struct evbuf_header *evbuf)
+{
+	struct sclp_diag_evbuf *diag = (struct sclp_diag_evbuf *) evbuf;
+
+	/*
+	 * Check for Diagnostic Test FTP Service
+	 */
+	if (evbuf->type != EVTYP_DIAG_TEST ||
+	    diag->route != SCLP_DIAG_FTP_ROUTE ||
+	    diag->mdd.ftp.pcx != SCLP_DIAG_FTP_XPCX ||
+	    evbuf->length < SCLP_DIAG_FTP_EVBUF_LEN)
+		return;
+
+#ifdef DEBUG
+	pr_debug("SCLP (ET7) RX-IRQ, Event @ 0x%p: %*phN\n",
+		 evbuf, 24, evbuf);
+#endif
+
+	/*
+	 * Because the event buffer is located in a page which is owned
+	 * by the SCLP core, all data of interest must be copied. The
+	 * error indication is in 'sclp_ftp_ldflg'
+	 */
+	sclp_ftp_ldflg = diag->mdd.ftp.ldflg;
+	sclp_ftp_fsize = diag->mdd.ftp.fsize;
+	sclp_ftp_length = diag->mdd.ftp.length;
+
+	complete(&sclp_ftp_rx_complete);
+}
+
+/**
+ * sclp_ftp_et7() - start a Diagnostic Test FTP Service SCLP request
+ * @ftp: pointer to FTP descriptor
+ *
+ * Return: 0 on success, else a (negative) error code
+ */
+static int sclp_ftp_et7(const struct hmcdrv_ftp_cmdspec *ftp)
+{
+	struct completion completion;
+	struct sclp_diag_sccb *sccb;
+	struct sclp_req *req;
+	size_t len;
+	int rc;
+
+	req = kzalloc(sizeof(*req), GFP_KERNEL);
+	sccb = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!req || !sccb) {
+		rc = -ENOMEM;
+		goto out_free;
+	}
+
+	sccb->hdr.length = SCLP_DIAG_FTP_EVBUF_LEN +
+		sizeof(struct sccb_header);
+	sccb->evbuf.hdr.type = EVTYP_DIAG_TEST;
+	sccb->evbuf.hdr.length = SCLP_DIAG_FTP_EVBUF_LEN;
+	sccb->evbuf.hdr.flags = 0; /* clear processed-buffer */
+	sccb->evbuf.route = SCLP_DIAG_FTP_ROUTE;
+	sccb->evbuf.mdd.ftp.pcx = SCLP_DIAG_FTP_XPCX;
+	sccb->evbuf.mdd.ftp.srcflg = 0;
+	sccb->evbuf.mdd.ftp.pgsize = 0;
+	sccb->evbuf.mdd.ftp.asce = _ASCE_REAL_SPACE;
+	sccb->evbuf.mdd.ftp.ldflg = SCLP_DIAG_FTP_LDFAIL;
+	sccb->evbuf.mdd.ftp.fsize = 0;
+	sccb->evbuf.mdd.ftp.cmd = ftp->id;
+	sccb->evbuf.mdd.ftp.offset = ftp->ofs;
+	sccb->evbuf.mdd.ftp.length = ftp->len;
+	sccb->evbuf.mdd.ftp.bufaddr = virt_to_phys(ftp->buf);
+
+	len = strlcpy(sccb->evbuf.mdd.ftp.fident, ftp->fname,
+		      HMCDRV_FTP_FIDENT_MAX);
+	if (len >= HMCDRV_FTP_FIDENT_MAX) {
+		rc = -EINVAL;
+		goto out_free;
+	}
+
+	req->command = SCLP_CMDW_WRITE_EVENT_DATA;
+	req->sccb = sccb;
+	req->status = SCLP_REQ_FILLED;
+	req->callback = sclp_ftp_txcb;
+	req->callback_data = &completion;
+
+	init_completion(&completion);
+
+	rc = sclp_add_request(req);
+	if (rc)
+		goto out_free;
+
+	/* Wait for end of ftp sclp command. */
+	wait_for_completion(&completion);
+
+#ifdef DEBUG
+	pr_debug("status of SCLP (ET7) request is 0x%04x (0x%02x)\n",
+		 sccb->hdr.response_code, sccb->evbuf.hdr.flags);
+#endif
+
+	/*
+	 * Check if sclp accepted the request. The data transfer runs
+	 * asynchronously and the completion is indicated with an
+	 * sclp ET7 event.
+	 */
+	if (req->status != SCLP_REQ_DONE ||
+	    (sccb->evbuf.hdr.flags & 0x80) == 0 || /* processed-buffer */
+	    (sccb->hdr.response_code & 0xffU) != 0x20U) {
+		rc = -EIO;
+	}
+
+out_free:
+	free_page((unsigned long) sccb);
+	kfree(req);
+	return rc;
+}
+
+/**
+ * sclp_ftp_cmd() - executes a HMC related SCLP Diagnose (ET7) FTP command
+ * @ftp: pointer to FTP command specification
+ * @fsize: return of file size (or NULL if undesirable)
+ *
+ * Attention: Notice that this function is not reentrant - so the caller
+ * must ensure locking.
+ *
+ * Return: number of bytes read/written or a (negative) error code
+ */
+ssize_t sclp_ftp_cmd(const struct hmcdrv_ftp_cmdspec *ftp, size_t *fsize)
+{
+	ssize_t len;
+#ifdef DEBUG
+	unsigned long start_jiffies;
+
+	pr_debug("starting SCLP (ET7), cmd %d for '%s' at %lld with %zd bytes\n",
+		 ftp->id, ftp->fname, (long long) ftp->ofs, ftp->len);
+	start_jiffies = jiffies;
+#endif
+
+	init_completion(&sclp_ftp_rx_complete);
+
+	/* Start ftp sclp command. */
+	len = sclp_ftp_et7(ftp);
+	if (len)
+		goto out_unlock;
+
+	/*
+	 * There is no way to cancel the sclp ET7 request, the code
+	 * needs to wait unconditionally until the transfer is complete.
+	 */
+	wait_for_completion(&sclp_ftp_rx_complete);
+
+#ifdef DEBUG
+	pr_debug("completed SCLP (ET7) request after %lu ms (all)\n",
+		 (jiffies - start_jiffies) * 1000 / HZ);
+	pr_debug("return code of SCLP (ET7) FTP Service is 0x%02x, with %lld/%lld bytes\n",
+		 sclp_ftp_ldflg, sclp_ftp_length, sclp_ftp_fsize);
+#endif
+
+	switch (sclp_ftp_ldflg) {
+	case SCLP_DIAG_FTP_OK:
+		len = sclp_ftp_length;
+		if (fsize)
+			*fsize = sclp_ftp_fsize;
+		break;
+	case SCLP_DIAG_FTP_LDNPERM:
+		len = -EPERM;
+		break;
+	case SCLP_DIAG_FTP_LDRUNS:
+		len = -EBUSY;
+		break;
+	case SCLP_DIAG_FTP_LDFAIL:
+		len = -ENOENT;
+		break;
+	default:
+		len = -EIO;
+		break;
+	}
+
+out_unlock:
+	return len;
+}
+
+/*
+ * ET7 event listener
+ */
+static struct sclp_register sclp_ftp_event = {
+	.send_mask = EVTYP_DIAG_TEST_MASK,    /* want tx events */
+	.receive_mask = EVTYP_DIAG_TEST_MASK, /* want rx events */
+	.receiver_fn = sclp_ftp_rxcb,	      /* async callback (rx) */
+	.state_change_fn = NULL,
+	.pm_event_fn = NULL,
+};
+
+/**
+ * sclp_ftp_startup() - startup of FTP services, when running on LPAR
+ */
+int sclp_ftp_startup(void)
+{
+#ifdef DEBUG
+	unsigned long info;
+#endif
+	int rc;
+
+	rc = sclp_register(&sclp_ftp_event);
+	if (rc)
+		return rc;
+
+#ifdef DEBUG
+	info = get_zeroed_page(GFP_KERNEL);
+
+	if (info != 0) {
+		struct sysinfo_2_2_2 *info222 = (struct sysinfo_2_2_2 *)info;
+
+		if (!stsi(info222, 2, 2, 2)) { /* get SYSIB 2.2.2 */
+			info222->name[sizeof(info222->name) - 1] = '\0';
+			EBCASC_500(info222->name, sizeof(info222->name) - 1);
+			pr_debug("SCLP (ET7) FTP Service working on LPAR %u (%s)\n",
+				 info222->lpar_number, info222->name);
+		}
+
+		free_page(info);
+	}
+#endif	/* DEBUG */
+	return 0;
+}
+
+/**
+ * sclp_ftp_shutdown() - shutdown of FTP services, when running on LPAR
+ */
+void sclp_ftp_shutdown(void)
+{
+	sclp_unregister(&sclp_ftp_event);
+}
diff --git a/drivers/s390/char/sclp_ftp.h b/drivers/s390/char/sclp_ftp.h
new file mode 100644
index 000000000000..98ba3183e7d9
--- /dev/null
+++ b/drivers/s390/char/sclp_ftp.h
@@ -0,0 +1,21 @@
+/*
+ *    SCLP Event Type (ET) 7 - Diagnostic Test FTP Services, useable on LPAR
+ *
+ *    Notice that all functions exported here are not reentrant.
+ *    So usage should be exclusive, ensured by the caller (e.g. using a
+ *    mutex).
+ *
+ *    Copyright IBM Corp. 2013
+ *    Author(s): Ralf Hoppe (rhoppe@de.ibm.com)
+ */
+
+#ifndef __SCLP_FTP_H__
+#define __SCLP_FTP_H__
+
+#include "hmcdrv_ftp.h"
+
+int sclp_ftp_startup(void);
+void sclp_ftp_shutdown(void);
+ssize_t sclp_ftp_cmd(const struct hmcdrv_ftp_cmdspec *ftp, size_t *fsize);
+
+#endif	 /* __SCLP_FTP_H__ */
diff --git a/drivers/s390/char/sclp_rw.c b/drivers/s390/char/sclp_rw.c
index 3b13d58fe87b..35a84af875ee 100644
--- a/drivers/s390/char/sclp_rw.c
+++ b/drivers/s390/char/sclp_rw.c
@@ -33,7 +33,7 @@ static void sclp_rw_pm_event(struct sclp_register *reg,
 
 /* Event type structure for write message and write priority message */
 static struct sclp_register sclp_rw_event = {
-	.send_mask = EVTYP_MSG_MASK | EVTYP_PMSGCMD_MASK,
+	.send_mask = EVTYP_MSG_MASK,
 	.pm_event_fn = sclp_rw_pm_event,
 };
 
@@ -456,14 +456,9 @@ sclp_emit_buffer(struct sclp_buffer *buffer,
 		return -EIO;
 
 	sccb = buffer->sccb;
-	if (sclp_rw_event.sclp_receive_mask & EVTYP_MSG_MASK)
-		/* Use normal write message */
-		sccb->msg_buf.header.type = EVTYP_MSG;
-	else if (sclp_rw_event.sclp_receive_mask & EVTYP_PMSGCMD_MASK)
-		/* Use write priority message */
-		sccb->msg_buf.header.type = EVTYP_PMSGCMD;
-	else
-		return -EOPNOTSUPP;
+	/* Use normal write message */
+	sccb->msg_buf.header.type = EVTYP_MSG;
+
 	buffer->request.command = SCLP_CMDW_WRITE_EVENT_DATA;
 	buffer->request.status = SCLP_REQ_FILLED;
 	buffer->request.callback = sclp_writedata_callback;
diff --git a/drivers/s390/char/sclp_vt220.c b/drivers/s390/char/sclp_vt220.c
index b9a9f721716d..ae67386c03d3 100644
--- a/drivers/s390/char/sclp_vt220.c
+++ b/drivers/s390/char/sclp_vt220.c
@@ -206,10 +206,6 @@ sclp_vt220_callback(struct sclp_req *request, void *data)
 static int
 __sclp_vt220_emit(struct sclp_vt220_request *request)
 {
-	if (!(sclp_vt220_register.sclp_receive_mask & EVTYP_VT220MSG_MASK)) {
-		request->sclp_req.status = SCLP_REQ_FAILED;
-		return -EIO;
-	}
 	request->sclp_req.command = SCLP_CMDW_WRITE_EVENT_DATA;
 	request->sclp_req.status = SCLP_REQ_FILLED;
 	request->sclp_req.callback = sclp_vt220_callback;
diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c
index 6dc60725de92..77f9b9c2f701 100644
--- a/drivers/s390/char/tape_char.c
+++ b/drivers/s390/char/tape_char.c
@@ -402,7 +402,9 @@ __tapechar_ioctl(struct tape_device *device,
 		memset(&get, 0, sizeof(get));
 		get.mt_type = MT_ISUNKNOWN;
 		get.mt_resid = 0 /* device->devstat.rescnt */;
-		get.mt_dsreg = device->tape_state;
+		get.mt_dsreg =
+			((device->char_data.block_size << MT_ST_BLKSIZE_SHIFT)
+			 & MT_ST_BLKSIZE_MASK);
 		/* FIXME: mt_gstat, mt_erreg, mt_fileno */
 		get.mt_gstat = 0;
 		get.mt_erreg = 0;
diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c
index a8848db7b09d..9bb48d70957c 100644
--- a/drivers/s390/char/vmlogrdr.c
+++ b/drivers/s390/char/vmlogrdr.c
@@ -338,7 +338,6 @@ static int vmlogrdr_open (struct inode *inode, struct file *filp)
 
 	/* set the file options */
 	filp->private_data = logptr;
-	filp->f_op = &vmlogrdr_fops;
 
 	/* start recording for this service*/
 	if (logptr->autorecording) {
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index 1884653e4472..efcf48481c5f 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -28,6 +28,7 @@
 #include <asm/processor.h>
 #include <asm/irqflags.h>
 #include <asm/checksum.h>
+#include <asm/switch_to.h>
 #include "sclp.h"
 
 #define TRACE(x...) debug_sprintf_event(zcore_dbf, 1, x)
@@ -149,18 +150,21 @@ static int memcpy_hsa_kernel(void *dest, unsigned long src, size_t count)
 
 static int __init init_cpu_info(enum arch_id arch)
 {
-	struct save_area *sa;
+	struct save_area_ext *sa_ext;
 
 	/* get info for boot cpu from lowcore, stored in the HSA */
 
-	sa = dump_save_area_create(0);
-	if (!sa)
+	sa_ext = dump_save_area_create(0);
+	if (!sa_ext)
 		return -ENOMEM;
-	if (memcpy_hsa_kernel(sa, sys_info.sa_base, sys_info.sa_size) < 0) {
+	if (memcpy_hsa_kernel(&sa_ext->sa, sys_info.sa_base,
+			      sys_info.sa_size) < 0) {
 		TRACE("could not copy from HSA\n");
-		kfree(sa);
+		kfree(sa_ext);
 		return -EIO;
 	}
+	if (MACHINE_HAS_VX)
+		save_vx_regs_safe(sa_ext->vx_regs);
 	return 0;
 }
 
@@ -258,7 +262,7 @@ static int zcore_add_lc(char __user *buf, unsigned long start, size_t count)
 		unsigned long sa_start, sa_end; /* save area range */
 		unsigned long prefix;
 		unsigned long sa_off, len, buf_off;
-		struct save_area *save_area = dump_save_areas.areas[i];
+		struct save_area *save_area = &dump_save_areas.areas[i]->sa;
 
 		prefix = save_area->pref_reg;
 		sa_start = prefix + sys_info.sa_base;
@@ -612,7 +616,7 @@ static void __init zcore_header_init(int arch, struct zcore_header *hdr,
 	hdr->tod = get_tod_clock();
 	get_cpu_id(&hdr->cpu_id);
 	for (i = 0; i < dump_save_areas.count; i++) {
-		prefix = dump_save_areas.areas[i]->pref_reg;
+		prefix = dump_save_areas.areas[i]->sa.pref_reg;
 		hdr->real_cpu_cnt++;
 		if (!prefix)
 			continue;
diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c
index 00bfbee0af9e..56eb4ee4deba 100644
--- a/drivers/s390/cio/airq.c
+++ b/drivers/s390/cio/airq.c
@@ -87,7 +87,7 @@ static irqreturn_t do_airq_interrupt(int irq, void *dummy)
 	struct airq_struct *airq;
 	struct hlist_head *head;
 
-	__this_cpu_write(s390_idle.nohz_delay, 1);
+	set_cpu_flag(CIF_NOHZ_DELAY);
 	tpi_info = (struct tpi_info *) &get_irq_regs()->int_code;
 	head = &airq_lists[tpi_info->isc];
 	rcu_read_lock();
diff --git a/drivers/s390/cio/ccwreq.c b/drivers/s390/cio/ccwreq.c
index 07676c22d514..79f59915f71b 100644
--- a/drivers/s390/cio/ccwreq.c
+++ b/drivers/s390/cio/ccwreq.c
@@ -252,7 +252,7 @@ static void ccwreq_log_status(struct ccw_device *cdev, enum io_status status)
  */
 void ccw_request_handler(struct ccw_device *cdev)
 {
-	struct irb *irb = &__get_cpu_var(cio_irb);
+	struct irb *irb = this_cpu_ptr(&cio_irb);
 	struct ccw_request *req = &cdev->private->req;
 	enum io_status status;
 	int rc = -EOPNOTSUPP;
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index d497aa05a72f..c692dfebd0ba 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -257,11 +257,11 @@ static ssize_t chp_status_write(struct device *dev,
 	if (!num_args)
 		return count;
 
-	if (!strnicmp(cmd, "on", 2) || !strcmp(cmd, "1")) {
+	if (!strncasecmp(cmd, "on", 2) || !strcmp(cmd, "1")) {
 		mutex_lock(&cp->lock);
 		error = s390_vary_chpid(cp->chpid, 1);
 		mutex_unlock(&cp->lock);
-	} else if (!strnicmp(cmd, "off", 3) || !strcmp(cmd, "0")) {
+	} else if (!strncasecmp(cmd, "off", 3) || !strcmp(cmd, "0")) {
 		mutex_lock(&cp->lock);
 		error = s390_vary_chpid(cp->chpid, 0);
 		mutex_unlock(&cp->lock);
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index 3d22d2a4ce14..213159dec89e 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -58,7 +58,7 @@ static void chsc_subchannel_irq(struct subchannel *sch)
 {
 	struct chsc_private *private = dev_get_drvdata(&sch->dev);
 	struct chsc_request *request = private->request;
-	struct irb *irb = &__get_cpu_var(cio_irb);
+	struct irb *irb = this_cpu_ptr(&cio_irb);
 
 	CHSC_LOG(4, "irb");
 	CHSC_LOG_HEX(4, irb, sizeof(*irb));
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 2905d8b0ec95..10eb738fc81a 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -561,9 +561,9 @@ static irqreturn_t do_cio_interrupt(int irq, void *dummy)
 	struct subchannel *sch;
 	struct irb *irb;
 
-	__this_cpu_write(s390_idle.nohz_delay, 1);
+	set_cpu_flag(CIF_NOHZ_DELAY);
 	tpi_info = (struct tpi_info *) &get_irq_regs()->int_code;
-	irb = &__get_cpu_var(cio_irb);
+	irb = this_cpu_ptr(&cio_irb);
 	sch = (struct subchannel *)(unsigned long) tpi_info->intparm;
 	if (!sch) {
 		/* Clear pending interrupt condition. */
@@ -613,7 +613,7 @@ void cio_tsch(struct subchannel *sch)
 	struct irb *irb;
 	int irq_context;
 
-	irb = &__get_cpu_var(cio_irb);
+	irb = this_cpu_ptr(&cio_irb);
 	/* Store interrupt response block to lowcore. */
 	if (tsch(sch->schid, irb) != 0)
 		/* Not status pending or not operational. */
@@ -751,7 +751,7 @@ __clear_io_subchannel_easy(struct subchannel_id schid)
 		struct tpi_info ti;
 
 		if (tpi(&ti)) {
-			tsch(ti.schid, &__get_cpu_var(cio_irb));
+			tsch(ti.schid, this_cpu_ptr(&cio_irb));
 			if (schid_equal(&ti.schid, &schid))
 				return 0;
 		}
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 0bc902b3cd84..83da53c8e54c 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -739,7 +739,7 @@ ccw_device_irq(struct ccw_device *cdev, enum dev_event dev_event)
 	struct irb *irb;
 	int is_cmd;
 
-	irb = &__get_cpu_var(cio_irb);
+	irb = this_cpu_ptr(&cio_irb);
 	is_cmd = !scsw_is_tm(&irb->scsw);
 	/* Check for unsolicited interrupt. */
 	if (!scsw_is_solicited(&irb->scsw)) {
@@ -805,7 +805,7 @@ ccw_device_w4sense(struct ccw_device *cdev, enum dev_event dev_event)
 {
 	struct irb *irb;
 
-	irb = &__get_cpu_var(cio_irb);
+	irb = this_cpu_ptr(&cio_irb);
 	/* Check for unsolicited interrupt. */
 	if (scsw_stctl(&irb->scsw) ==
 	    (SCSW_STCTL_STATUS_PEND | SCSW_STCTL_ALERT_STATUS)) {
diff --git a/drivers/s390/cio/eadm_sch.c b/drivers/s390/cio/eadm_sch.c
index c4f7bf3e24c2..37f0834300ea 100644
--- a/drivers/s390/cio/eadm_sch.c
+++ b/drivers/s390/cio/eadm_sch.c
@@ -134,7 +134,7 @@ static void eadm_subchannel_irq(struct subchannel *sch)
 {
 	struct eadm_private *private = get_eadm_private(sch);
 	struct eadm_scsw *scsw = &sch->schib.scsw.eadm;
-	struct irb *irb = &__get_cpu_var(cio_irb);
+	struct irb *irb = this_cpu_ptr(&cio_irb);
 	int error = 0;
 
 	EADM_LOG(6, "irq");
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 4038437ff033..99485415dcc2 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -664,6 +664,17 @@ static ssize_t ap_hwtype_show(struct device *dev,
 }
 
 static DEVICE_ATTR(hwtype, 0444, ap_hwtype_show, NULL);
+
+static ssize_t ap_raw_hwtype_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct ap_device *ap_dev = to_ap_dev(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", ap_dev->raw_hwtype);
+}
+
+static DEVICE_ATTR(raw_hwtype, 0444, ap_raw_hwtype_show, NULL);
+
 static ssize_t ap_depth_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
@@ -734,6 +745,7 @@ static DEVICE_ATTR(ap_functions, 0444, ap_functions_show, NULL);
 
 static struct attribute *ap_dev_attrs[] = {
 	&dev_attr_hwtype.attr,
+	&dev_attr_raw_hwtype.attr,
 	&dev_attr_depth.attr,
 	&dev_attr_request_count.attr,
 	&dev_attr_requestq_count.attr,
@@ -1188,6 +1200,10 @@ static int ap_select_domain(void)
 	ap_qid_t qid;
 	int rc, i, j;
 
+	/* IF APXA isn't installed, only 16 domains could be defined */
+	if (!ap_configuration->ap_extended && (ap_domain_index > 15))
+		return -EINVAL;
+
 	/*
 	 * We want to use a single domain. Either the one specified with
 	 * the "domain=" parameter or the domain with the maximum number
@@ -1413,9 +1429,13 @@ static void ap_scan_bus(struct work_struct *unused)
 				continue;
 			}
 			break;
+		case 11:
+			ap_dev->device_type = 10;
+			break;
 		default:
 			ap_dev->device_type = device_type;
 		}
+		ap_dev->raw_hwtype = device_type;
 
 		rc = ap_query_functions(qid, &device_functions);
 		if (!rc)
@@ -1900,9 +1920,15 @@ static void ap_reset_all(void)
 {
 	int i, j;
 
-	for (i = 0; i < AP_DOMAINS; i++)
-		for (j = 0; j < AP_DEVICES; j++)
+	for (i = 0; i < AP_DOMAINS; i++) {
+		if (!ap_test_config_domain(i))
+			continue;
+		for (j = 0; j < AP_DEVICES; j++) {
+			if (!ap_test_config_card_id(j))
+				continue;
 			ap_reset_queue(AP_MKQID(j, i));
+		}
+	}
 }
 
 static struct reset_call ap_reset_call = {
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 6405ae24a7a6..055a0f956d17 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -31,7 +31,7 @@
 #include <linux/types.h>
 
 #define AP_DEVICES 64		/* Number of AP devices. */
-#define AP_DOMAINS 16		/* Number of AP domains. */
+#define AP_DOMAINS 256		/* Number of AP domains. */
 #define AP_MAX_RESET 90		/* Maximum number of resets. */
 #define AP_RESET_TIMEOUT (HZ*0.7)	/* Time in ticks for reset timeouts. */
 #define AP_CONFIG_TIME 30	/* Time in seconds between AP bus rescans. */
@@ -45,9 +45,9 @@ extern int ap_domain_index;
  */
 typedef unsigned int ap_qid_t;
 
-#define AP_MKQID(_device,_queue) (((_device) & 63) << 8 | ((_queue) & 15))
+#define AP_MKQID(_device, _queue) (((_device) & 63) << 8 | ((_queue) & 255))
 #define AP_QID_DEVICE(_qid) (((_qid) >> 8) & 63)
-#define AP_QID_QUEUE(_qid) ((_qid) & 15)
+#define AP_QID_QUEUE(_qid) ((_qid) & 255)
 
 /**
  * structy ap_queue_status - Holds the AP queue status.
@@ -161,6 +161,7 @@ struct ap_device {
 	ap_qid_t qid;			/* AP queue id. */
 	int queue_depth;		/* AP queue depth.*/
 	int device_type;		/* AP device type. */
+	int raw_hwtype;			/* AP raw hardware type. */
 	unsigned int functions;		/* AP device function bitfield. */
 	int unregistered;		/* marks AP device as unregistered */
 	struct timer_list timeout;	/* Timer for request timeouts. */
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 0e18c5dcd91f..08f1830cbfc4 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -343,10 +343,11 @@ struct zcrypt_ops *__ops_lookup(unsigned char *name, int variant)
 			break;
 		}
 	}
+	if (!found || !try_module_get(zops->owner))
+		zops = NULL;
+
 	spin_unlock_bh(&zcrypt_ops_list_lock);
 
-	if (!found)
-		return NULL;
 	return zops;
 }
 
@@ -359,8 +360,6 @@ struct zcrypt_ops *zcrypt_msgtype_request(unsigned char *name, int variant)
 		request_module("%s", name);
 		zops = __ops_lookup(name, variant);
 	}
-	if ((!zops) || (!try_module_get(zops->owner)))
-		return NULL;
 	return zops;
 }
 EXPORT_SYMBOL(zcrypt_msgtype_request);
diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c
index a1349653c6d9..643129070c51 100644
--- a/drivers/s390/kvm/kvm_virtio.c
+++ b/drivers/s390/kvm/kvm_virtio.c
@@ -406,15 +406,8 @@ static void kvm_extint_handler(struct ext_code ext_code,
 
 	switch (param) {
 	case VIRTIO_PARAM_CONFIG_CHANGED:
-	{
-		struct virtio_driver *drv;
-		drv = container_of(vq->vdev->dev.driver,
-				   struct virtio_driver, driver);
-		if (drv->config_changed)
-			drv->config_changed(vq->vdev);
-
+		virtio_config_changed(vq->vdev);
 		break;
-	}
 	case VIRTIO_PARAM_DEV_ADD:
 		schedule_work(&hotplug_work);
 		break;
diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c
index d2c0b442bce5..6cbe6ef3c889 100644
--- a/drivers/s390/kvm/virtio_ccw.c
+++ b/drivers/s390/kvm/virtio_ccw.c
@@ -940,11 +940,7 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev,
 		vring_interrupt(0, vq);
 	}
 	if (test_bit(0, &vcdev->indicators2)) {
-		drv = container_of(vcdev->vdev.dev.driver,
-				   struct virtio_driver, driver);
-
-		if (drv && drv->config_changed)
-			drv->config_changed(&vcdev->vdev);
+		virtio_config_changed(&vcdev->vdev);
 		clear_bit(0, &vcdev->indicators2);
 	}
 }
diff --git a/drivers/s390/net/claw.c b/drivers/s390/net/claw.c
index fbc6701bef30..213e54ee8a66 100644
--- a/drivers/s390/net/claw.c
+++ b/drivers/s390/net/claw.c
@@ -481,7 +481,6 @@ claw_open(struct net_device *dev)
                 spin_unlock_irqrestore(
 			get_ccwdev_lock(privptr->channel[i].cdev), saveflags);
                 schedule();
-		set_current_state(TASK_RUNNING);
                 remove_wait_queue(&privptr->channel[i].wait, &wait);
                 if(rc != 0)
                         ccw_check_return_code(privptr->channel[i].cdev, rc);
@@ -828,7 +827,6 @@ claw_release(struct net_device *dev)
 	        spin_unlock_irqrestore(
 			get_ccwdev_lock(privptr->channel[i].cdev), saveflags);
 	        schedule();
-		set_current_state(TASK_RUNNING);
 	        remove_wait_queue(&privptr->channel[i].wait, &wait);
 	        if (rc != 0) {
                         ccw_check_return_code(privptr->channel[i].cdev, rc);
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index e85e64a07d02..3a820f61ce65 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -73,7 +73,6 @@ comment "SCSI support type (disk, tape, CD-ROM)"
 config BLK_DEV_SD
 	tristate "SCSI disk support"
 	depends on SCSI
-	select CRC_T10DIF if BLK_DEV_INTEGRITY
 	---help---
 	  If you want to use SCSI hard disks, Fibre Channel disks,
 	  Serial ATA (SATA) or Parallel ATA (PATA) hard disks,
@@ -587,6 +586,16 @@ config VMWARE_PVSCSI
 	  To compile this driver as a module, choose M here: the
 	  module will be called vmw_pvscsi.
 
+config XEN_SCSI_FRONTEND
+	tristate "XEN SCSI frontend driver"
+	depends on SCSI && XEN
+	select XEN_XENBUS_FRONTEND
+	help
+	  The XEN SCSI frontend driver allows the kernel to access SCSI Devices
+	  within another guest OS (usually Dom0).
+	  Only needed if the kernel is running in a XEN guest and generic
+	  SCSI access to a device is needed.
+
 config HYPERV_STORAGE
 	tristate "Microsoft Hyper-V virtual storage driver"
 	depends on SCSI && HYPERV
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 5f0d299b0093..59f1ce6df2d6 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -141,6 +141,7 @@ obj-$(CONFIG_SCSI_ESAS2R)	+= esas2r/
 obj-$(CONFIG_SCSI_PMCRAID)	+= pmcraid.o
 obj-$(CONFIG_SCSI_VIRTIO)	+= virtio_scsi.o
 obj-$(CONFIG_VMWARE_PVSCSI)	+= vmw_pvscsi.o
+obj-$(CONFIG_XEN_SCSI_FRONTEND)	+= xen-scsifront.o
 obj-$(CONFIG_HYPERV_STORAGE)	+= hv_storvsc.o
 
 obj-$(CONFIG_ARM)		+= arm/
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 7bcf67eec921..e99507ed0e3c 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -115,7 +115,7 @@ static struct request *get_alua_req(struct scsi_device *sdev,
 
 	rq = blk_get_request(q, rw, GFP_NOIO);
 
-	if (!rq) {
+	if (IS_ERR(rq)) {
 		sdev_printk(KERN_INFO, sdev,
 			    "%s: blk_get_request failed\n", __func__);
 		return NULL;
diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index 6f07f7fe3aa1..84765384c47c 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -275,7 +275,7 @@ static struct request *get_req(struct scsi_device *sdev, int cmd,
 
 	rq = blk_get_request(sdev->request_queue,
 			(cmd != INQUIRY) ? WRITE : READ, GFP_NOIO);
-	if (!rq) {
+	if (IS_ERR(rq)) {
 		sdev_printk(KERN_INFO, sdev, "get_req: blk_get_request failed");
 		return NULL;
 	}
diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index e9d9fea9e272..4ee2759f5299 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -117,7 +117,7 @@ static int hp_sw_tur(struct scsi_device *sdev, struct hp_sw_dh_data *h)
 
 retry:
 	req = blk_get_request(sdev->request_queue, WRITE, GFP_NOIO);
-	if (!req)
+	if (IS_ERR(req))
 		return SCSI_DH_RES_TEMP_UNAVAIL;
 
 	blk_rq_set_block_pc(req);
@@ -247,7 +247,7 @@ static int hp_sw_start_stop(struct hp_sw_dh_data *h)
 	struct request *req;
 
 	req = blk_get_request(h->sdev->request_queue, WRITE, GFP_ATOMIC);
-	if (!req)
+	if (IS_ERR(req))
 		return SCSI_DH_RES_TEMP_UNAVAIL;
 
 	blk_rq_set_block_pc(req);
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index 826069db9848..1b5bc9293e37 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -274,7 +274,7 @@ static struct request *get_rdac_req(struct scsi_device *sdev,
 
 	rq = blk_get_request(q, rw, GFP_NOIO);
 
-	if (!rq) {
+	if (IS_ERR(rq)) {
 		sdev_printk(KERN_INFO, sdev,
 				"get_rdac_req: blk_get_request failed.\n");
 		return NULL;
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 00ee0ed642aa..4a8ac7d8c76b 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1884,7 +1884,6 @@ retry:
 			set_current_state(TASK_INTERRUPTIBLE);
 			spin_unlock_bh(&p->fcoe_rx_list.lock);
 			schedule();
-			set_current_state(TASK_RUNNING);
 			goto retry;
 		}
 
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index 52a216f21ae5..e5afc3884d74 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -528,7 +528,7 @@ ips_setup(char *ips_str)
 		 * Update the variables
 		 */
 		for (i = 0; i < ARRAY_SIZE(options); i++) {
-			if (strnicmp
+			if (strncasecmp
 			    (key, options[i].option_name,
 			     strlen(options[i].option_name)) == 0) {
 				if (value)
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index 5f4cbf0c4759..fd19fd8468ac 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -1567,8 +1567,8 @@ static struct request *_make_request(struct request_queue *q, bool has_write,
 		struct request *req;
 
 		req = blk_get_request(q, has_write ? WRITE : READ, flags);
-		if (unlikely(!req))
-			return ERR_PTR(-ENOMEM);
+		if (IS_ERR(req))
+			return req;
 
 		blk_rq_set_block_pc(req);
 		return req;
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index 0727ea7cc387..dff37a250d79 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -362,7 +362,7 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
 	int write = (data_direction == DMA_TO_DEVICE);
 
 	req = blk_get_request(SRpnt->stp->device->request_queue, write, GFP_KERNEL);
-	if (!req)
+	if (IS_ERR(req))
 		return DRIVER_ERROR << 24;
 
 	blk_rq_set_block_pc(req);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index dabd25429c58..db3dbd999cb6 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -4875,7 +4875,6 @@ qla2x00_do_dpc(void *data)
 		    "DPC handler sleeping.\n");
 
 		schedule();
-		__set_current_state(TASK_RUNNING);
 
 		if (!base_vha->flags.init_done || ha->flags.mbox_busy)
 			goto end_loop;
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 2b6d447ad6d6..238e06f13b8a 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -3371,7 +3371,7 @@ static ssize_t opts_store(struct device_driver *ddp, const char *buf,
 	char work[20];
 
         if (1 == sscanf(buf, "%10s", work)) {
-		if (0 == strnicmp(work,"0x", 2)) {
+		if (0 == strncasecmp(work,"0x", 2)) {
 			if (1 == sscanf(&work[2], "%x", &opts))
 				goto opts_done;
 		} else {
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 6b20ef3fee54..9a6f8468225f 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1961,6 +1961,8 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
 	 * request becomes available
 	 */
 	req = blk_get_request(sdev->request_queue, READ, GFP_KERNEL);
+	if (IS_ERR(req))
+		return;
 
 	blk_rq_set_block_pc(req);
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index db8c449282f9..9eff8a375132 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -221,7 +221,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	int ret = DRIVER_ERROR << 24;
 
 	req = blk_get_request(sdev->request_queue, write, __GFP_WAIT);
-	if (!req)
+	if (IS_ERR(req))
 		return ret;
 	blk_rq_set_block_pc(req);
 
@@ -715,7 +715,7 @@ static bool scsi_end_request(struct request *req, int error,
 
 	if (req->mq_ctx) {
 		/*
-		 * In the MQ case the command gets freed by __blk_mq_end_io,
+		 * In the MQ case the command gets freed by __blk_mq_end_request,
 		 * so we have to do all cleanup that depends on it earlier.
 		 *
 		 * We also can't kick the queues from irq context, so we
@@ -723,7 +723,7 @@ static bool scsi_end_request(struct request *req, int error,
 		 */
 		scsi_mq_uninit_cmd(cmd);
 
-		__blk_mq_end_io(req, error);
+		__blk_mq_end_request(req, error);
 
 		if (scsi_target(sdev)->single_lun ||
 		    !list_empty(&sdev->host->starved_list))
@@ -1847,6 +1847,8 @@ static int scsi_mq_prep_fn(struct request *req)
 		next_rq->special = bidi_sdb;
 	}
 
+	blk_mq_start_request(req);
+
 	return scsi_setup_cmnd(sdev, req);
 }
 
@@ -1856,7 +1858,8 @@ static void scsi_mq_done(struct scsi_cmnd *cmd)
 	blk_mq_complete_request(cmd->request);
 }
 
-static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
+static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req,
+		bool last)
 {
 	struct request_queue *q = req->q;
 	struct scsi_device *sdev = q->queuedata;
@@ -1880,11 +1883,14 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 	if (!scsi_host_queue_ready(q, shost, sdev))
 		goto out_dec_target_busy;
 
+
 	if (!(req->cmd_flags & REQ_DONTPREP)) {
 		ret = prep_to_mq(scsi_mq_prep_fn(req));
 		if (ret)
 			goto out_dec_host_busy;
 		req->cmd_flags |= REQ_DONTPREP;
+	} else {
+		blk_mq_start_request(req);
 	}
 
 	scsi_init_cmd_errh(cmd);
@@ -1931,6 +1937,14 @@ out:
 	return ret;
 }
 
+static enum blk_eh_timer_return scsi_timeout(struct request *req,
+		bool reserved)
+{
+	if (reserved)
+		return BLK_EH_RESET_TIMER;
+	return scsi_times_out(req);
+}
+
 static int scsi_init_request(void *data, struct request *rq,
 		unsigned int hctx_idx, unsigned int request_idx,
 		unsigned int numa_node)
@@ -2042,7 +2056,7 @@ static struct blk_mq_ops scsi_mq_ops = {
 	.map_queue	= blk_mq_map_queue,
 	.queue_rq	= scsi_queue_rq,
 	.complete	= scsi_softirq_done,
-	.timeout	= scsi_times_out,
+	.timeout	= scsi_timeout,
 	.init_request	= scsi_init_request,
 	.exit_request	= scsi_exit_request,
 };
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 0cb5c9f0c743..cfba74cd8e8b 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -610,29 +610,44 @@ static void scsi_disk_put(struct scsi_disk *sdkp)
 	mutex_unlock(&sd_ref_mutex);
 }
 
-static void sd_prot_op(struct scsi_cmnd *scmd, unsigned int dif)
-{
-	unsigned int prot_op = SCSI_PROT_NORMAL;
-	unsigned int dix = scsi_prot_sg_count(scmd);
-
-	if (scmd->sc_data_direction == DMA_FROM_DEVICE) {
-		if (dif && dix)
-			prot_op = SCSI_PROT_READ_PASS;
-		else if (dif && !dix)
-			prot_op = SCSI_PROT_READ_STRIP;
-		else if (!dif && dix)
-			prot_op = SCSI_PROT_READ_INSERT;
-	} else {
-		if (dif && dix)
-			prot_op = SCSI_PROT_WRITE_PASS;
-		else if (dif && !dix)
-			prot_op = SCSI_PROT_WRITE_INSERT;
-		else if (!dif && dix)
-			prot_op = SCSI_PROT_WRITE_STRIP;
+
+
+static unsigned char sd_setup_protect_cmnd(struct scsi_cmnd *scmd,
+					   unsigned int dix, unsigned int dif)
+{
+	struct bio *bio = scmd->request->bio;
+	unsigned int prot_op = sd_prot_op(rq_data_dir(scmd->request), dix, dif);
+	unsigned int protect = 0;
+
+	if (dix) {				/* DIX Type 0, 1, 2, 3 */
+		if (bio_integrity_flagged(bio, BIP_IP_CHECKSUM))
+			scmd->prot_flags |= SCSI_PROT_IP_CHECKSUM;
+
+		if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false)
+			scmd->prot_flags |= SCSI_PROT_GUARD_CHECK;
+	}
+
+	if (dif != SD_DIF_TYPE3_PROTECTION) {	/* DIX/DIF Type 0, 1, 2 */
+		scmd->prot_flags |= SCSI_PROT_REF_INCREMENT;
+
+		if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false)
+			scmd->prot_flags |= SCSI_PROT_REF_CHECK;
+	}
+
+	if (dif) {				/* DIX/DIF Type 1, 2, 3 */
+		scmd->prot_flags |= SCSI_PROT_TRANSFER_PI;
+
+		if (bio_integrity_flagged(bio, BIP_DISK_NOCHECK))
+			protect = 3 << 5;	/* Disable target PI checking */
+		else
+			protect = 1 << 5;	/* Enable target PI checking */
 	}
 
 	scsi_set_prot_op(scmd, prot_op);
 	scsi_set_prot_type(scmd, dif);
+	scmd->prot_flags &= sd_prot_flag_mask(prot_op);
+
+	return protect;
 }
 
 static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
@@ -893,7 +908,8 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	sector_t block = blk_rq_pos(rq);
 	sector_t threshold;
 	unsigned int this_count = blk_rq_sectors(rq);
-	int ret, host_dif;
+	unsigned int dif, dix;
+	int ret;
 	unsigned char protect;
 
 	ret = scsi_init_io(SCpnt, GFP_ATOMIC);
@@ -995,7 +1011,7 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 		SCpnt->cmnd[0] = WRITE_6;
 
 		if (blk_integrity_rq(rq))
-			sd_dif_prepare(rq, block, sdp->sector_size);
+			sd_dif_prepare(SCpnt);
 
 	} else if (rq_data_dir(rq) == READ) {
 		SCpnt->cmnd[0] = READ_6;
@@ -1010,14 +1026,15 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 					"writing" : "reading", this_count,
 					blk_rq_sectors(rq)));
 
-	/* Set RDPROTECT/WRPROTECT if disk is formatted with DIF */
-	host_dif = scsi_host_dif_capable(sdp->host, sdkp->protection_type);
-	if (host_dif)
-		protect = 1 << 5;
+	dix = scsi_prot_sg_count(SCpnt);
+	dif = scsi_host_dif_capable(SCpnt->device->host, sdkp->protection_type);
+
+	if (dif || dix)
+		protect = sd_setup_protect_cmnd(SCpnt, dix, dif);
 	else
 		protect = 0;
 
-	if (host_dif == SD_DIF_TYPE2_PROTECTION) {
+	if (protect && sdkp->protection_type == SD_DIF_TYPE2_PROTECTION) {
 		SCpnt->cmnd = mempool_alloc(sd_cdb_pool, GFP_ATOMIC);
 
 		if (unlikely(SCpnt->cmnd == NULL)) {
@@ -1102,10 +1119,6 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	}
 	SCpnt->sdb.length = this_count * sdp->sector_size;
 
-	/* If DIF or DIX is enabled, tell HBA how to handle request */
-	if (host_dif || scsi_prot_sg_count(SCpnt))
-		sd_prot_op(SCpnt, host_dif);
-
 	/*
 	 * We shouldn't disconnect in the middle of a sector, so with a dumb
 	 * host adapter, it's safe to assume that we can at least transfer
@@ -2664,8 +2677,10 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
 
 	rot = get_unaligned_be16(&buffer[4]);
 
-	if (rot == 1)
+	if (rot == 1) {
 		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, sdkp->disk->queue);
+		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, sdkp->disk->queue);
+	}
 
  out:
 	kfree(buffer);
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 4c3ab8377fd3..467377884b63 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -167,6 +167,68 @@ enum sd_dif_target_protection_types {
 };
 
 /*
+ * Look up the DIX operation based on whether the command is read or
+ * write and whether dix and dif are enabled.
+ */
+static inline unsigned int sd_prot_op(bool write, bool dix, bool dif)
+{
+	/* Lookup table: bit 2 (write), bit 1 (dix), bit 0 (dif) */
+	const unsigned int ops[] = {	/* wrt dix dif */
+		SCSI_PROT_NORMAL,	/*  0	0   0  */
+		SCSI_PROT_READ_STRIP,	/*  0	0   1  */
+		SCSI_PROT_READ_INSERT,	/*  0	1   0  */
+		SCSI_PROT_READ_PASS,	/*  0	1   1  */
+		SCSI_PROT_NORMAL,	/*  1	0   0  */
+		SCSI_PROT_WRITE_INSERT, /*  1	0   1  */
+		SCSI_PROT_WRITE_STRIP,	/*  1	1   0  */
+		SCSI_PROT_WRITE_PASS,	/*  1	1   1  */
+	};
+
+	return ops[write << 2 | dix << 1 | dif];
+}
+
+/*
+ * Returns a mask of the protection flags that are valid for a given DIX
+ * operation.
+ */
+static inline unsigned int sd_prot_flag_mask(unsigned int prot_op)
+{
+	const unsigned int flag_mask[] = {
+		[SCSI_PROT_NORMAL]		= 0,
+
+		[SCSI_PROT_READ_STRIP]		= SCSI_PROT_TRANSFER_PI |
+						  SCSI_PROT_GUARD_CHECK |
+						  SCSI_PROT_REF_CHECK |
+						  SCSI_PROT_REF_INCREMENT,
+
+		[SCSI_PROT_READ_INSERT]		= SCSI_PROT_REF_INCREMENT |
+						  SCSI_PROT_IP_CHECKSUM,
+
+		[SCSI_PROT_READ_PASS]		= SCSI_PROT_TRANSFER_PI |
+						  SCSI_PROT_GUARD_CHECK |
+						  SCSI_PROT_REF_CHECK |
+						  SCSI_PROT_REF_INCREMENT |
+						  SCSI_PROT_IP_CHECKSUM,
+
+		[SCSI_PROT_WRITE_INSERT]	= SCSI_PROT_TRANSFER_PI |
+						  SCSI_PROT_REF_INCREMENT,
+
+		[SCSI_PROT_WRITE_STRIP]		= SCSI_PROT_GUARD_CHECK |
+						  SCSI_PROT_REF_CHECK |
+						  SCSI_PROT_REF_INCREMENT |
+						  SCSI_PROT_IP_CHECKSUM,
+
+		[SCSI_PROT_WRITE_PASS]		= SCSI_PROT_TRANSFER_PI |
+						  SCSI_PROT_GUARD_CHECK |
+						  SCSI_PROT_REF_CHECK |
+						  SCSI_PROT_REF_INCREMENT |
+						  SCSI_PROT_IP_CHECKSUM,
+	};
+
+	return flag_mask[prot_op];
+}
+
+/*
  * Data Integrity Field tuple.
  */
 struct sd_dif_tuple {
@@ -178,7 +240,7 @@ struct sd_dif_tuple {
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 
 extern void sd_dif_config_host(struct scsi_disk *);
-extern void sd_dif_prepare(struct request *rq, sector_t, unsigned int);
+extern void sd_dif_prepare(struct scsi_cmnd *scmd);
 extern void sd_dif_complete(struct scsi_cmnd *, unsigned int);
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
@@ -186,7 +248,7 @@ extern void sd_dif_complete(struct scsi_cmnd *, unsigned int);
 static inline void sd_dif_config_host(struct scsi_disk *disk)
 {
 }
-static inline int sd_dif_prepare(struct request *rq, sector_t s, unsigned int a)
+static inline int sd_dif_prepare(struct scsi_cmnd *scmd)
 {
 	return 0;
 }
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index a7a691d0af7d..14c7d42a11c2 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -21,7 +21,7 @@
  */
 
 #include <linux/blkdev.h>
-#include <linux/crc-t10dif.h>
+#include <linux/t10-pi.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -33,268 +33,8 @@
 #include <scsi/scsi_ioctl.h>
 #include <scsi/scsicam.h>
 
-#include <net/checksum.h>
-
 #include "sd.h"
 
-typedef __u16 (csum_fn) (void *, unsigned int);
-
-static __u16 sd_dif_crc_fn(void *data, unsigned int len)
-{
-	return cpu_to_be16(crc_t10dif(data, len));
-}
-
-static __u16 sd_dif_ip_fn(void *data, unsigned int len)
-{
-	return ip_compute_csum(data, len);
-}
-
-/*
- * Type 1 and Type 2 protection use the same format: 16 bit guard tag,
- * 16 bit app tag, 32 bit reference tag.
- */
-static void sd_dif_type1_generate(struct blk_integrity_exchg *bix, csum_fn *fn)
-{
-	void *buf = bix->data_buf;
-	struct sd_dif_tuple *sdt = bix->prot_buf;
-	sector_t sector = bix->sector;
-	unsigned int i;
-
-	for (i = 0 ; i < bix->data_size ; i += bix->sector_size, sdt++) {
-		sdt->guard_tag = fn(buf, bix->sector_size);
-		sdt->ref_tag = cpu_to_be32(sector & 0xffffffff);
-		sdt->app_tag = 0;
-
-		buf += bix->sector_size;
-		sector++;
-	}
-}
-
-static void sd_dif_type1_generate_crc(struct blk_integrity_exchg *bix)
-{
-	sd_dif_type1_generate(bix, sd_dif_crc_fn);
-}
-
-static void sd_dif_type1_generate_ip(struct blk_integrity_exchg *bix)
-{
-	sd_dif_type1_generate(bix, sd_dif_ip_fn);
-}
-
-static int sd_dif_type1_verify(struct blk_integrity_exchg *bix, csum_fn *fn)
-{
-	void *buf = bix->data_buf;
-	struct sd_dif_tuple *sdt = bix->prot_buf;
-	sector_t sector = bix->sector;
-	unsigned int i;
-	__u16 csum;
-
-	for (i = 0 ; i < bix->data_size ; i += bix->sector_size, sdt++) {
-		/* Unwritten sectors */
-		if (sdt->app_tag == 0xffff)
-			return 0;
-
-		if (be32_to_cpu(sdt->ref_tag) != (sector & 0xffffffff)) {
-			printk(KERN_ERR
-			       "%s: ref tag error on sector %lu (rcvd %u)\n",
-			       bix->disk_name, (unsigned long)sector,
-			       be32_to_cpu(sdt->ref_tag));
-			return -EIO;
-		}
-
-		csum = fn(buf, bix->sector_size);
-
-		if (sdt->guard_tag != csum) {
-			printk(KERN_ERR "%s: guard tag error on sector %lu " \
-			       "(rcvd %04x, data %04x)\n", bix->disk_name,
-			       (unsigned long)sector,
-			       be16_to_cpu(sdt->guard_tag), be16_to_cpu(csum));
-			return -EIO;
-		}
-
-		buf += bix->sector_size;
-		sector++;
-	}
-
-	return 0;
-}
-
-static int sd_dif_type1_verify_crc(struct blk_integrity_exchg *bix)
-{
-	return sd_dif_type1_verify(bix, sd_dif_crc_fn);
-}
-
-static int sd_dif_type1_verify_ip(struct blk_integrity_exchg *bix)
-{
-	return sd_dif_type1_verify(bix, sd_dif_ip_fn);
-}
-
-/*
- * Functions for interleaving and deinterleaving application tags
- */
-static void sd_dif_type1_set_tag(void *prot, void *tag_buf, unsigned int sectors)
-{
-	struct sd_dif_tuple *sdt = prot;
-	u8 *tag = tag_buf;
-	unsigned int i, j;
-
-	for (i = 0, j = 0 ; i < sectors ; i++, j += 2, sdt++) {
-		sdt->app_tag = tag[j] << 8 | tag[j+1];
-		BUG_ON(sdt->app_tag == 0xffff);
-	}
-}
-
-static void sd_dif_type1_get_tag(void *prot, void *tag_buf, unsigned int sectors)
-{
-	struct sd_dif_tuple *sdt = prot;
-	u8 *tag = tag_buf;
-	unsigned int i, j;
-
-	for (i = 0, j = 0 ; i < sectors ; i++, j += 2, sdt++) {
-		tag[j] = (sdt->app_tag & 0xff00) >> 8;
-		tag[j+1] = sdt->app_tag & 0xff;
-	}
-}
-
-static struct blk_integrity dif_type1_integrity_crc = {
-	.name			= "T10-DIF-TYPE1-CRC",
-	.generate_fn		= sd_dif_type1_generate_crc,
-	.verify_fn		= sd_dif_type1_verify_crc,
-	.get_tag_fn		= sd_dif_type1_get_tag,
-	.set_tag_fn		= sd_dif_type1_set_tag,
-	.tuple_size		= sizeof(struct sd_dif_tuple),
-	.tag_size		= 0,
-};
-
-static struct blk_integrity dif_type1_integrity_ip = {
-	.name			= "T10-DIF-TYPE1-IP",
-	.generate_fn		= sd_dif_type1_generate_ip,
-	.verify_fn		= sd_dif_type1_verify_ip,
-	.get_tag_fn		= sd_dif_type1_get_tag,
-	.set_tag_fn		= sd_dif_type1_set_tag,
-	.tuple_size		= sizeof(struct sd_dif_tuple),
-	.tag_size		= 0,
-};
-
-
-/*
- * Type 3 protection has a 16-bit guard tag and 16 + 32 bits of opaque
- * tag space.
- */
-static void sd_dif_type3_generate(struct blk_integrity_exchg *bix, csum_fn *fn)
-{
-	void *buf = bix->data_buf;
-	struct sd_dif_tuple *sdt = bix->prot_buf;
-	unsigned int i;
-
-	for (i = 0 ; i < bix->data_size ; i += bix->sector_size, sdt++) {
-		sdt->guard_tag = fn(buf, bix->sector_size);
-		sdt->ref_tag = 0;
-		sdt->app_tag = 0;
-
-		buf += bix->sector_size;
-	}
-}
-
-static void sd_dif_type3_generate_crc(struct blk_integrity_exchg *bix)
-{
-	sd_dif_type3_generate(bix, sd_dif_crc_fn);
-}
-
-static void sd_dif_type3_generate_ip(struct blk_integrity_exchg *bix)
-{
-	sd_dif_type3_generate(bix, sd_dif_ip_fn);
-}
-
-static int sd_dif_type3_verify(struct blk_integrity_exchg *bix, csum_fn *fn)
-{
-	void *buf = bix->data_buf;
-	struct sd_dif_tuple *sdt = bix->prot_buf;
-	sector_t sector = bix->sector;
-	unsigned int i;
-	__u16 csum;
-
-	for (i = 0 ; i < bix->data_size ; i += bix->sector_size, sdt++) {
-		/* Unwritten sectors */
-		if (sdt->app_tag == 0xffff && sdt->ref_tag == 0xffffffff)
-			return 0;
-
-		csum = fn(buf, bix->sector_size);
-
-		if (sdt->guard_tag != csum) {
-			printk(KERN_ERR "%s: guard tag error on sector %lu " \
-			       "(rcvd %04x, data %04x)\n", bix->disk_name,
-			       (unsigned long)sector,
-			       be16_to_cpu(sdt->guard_tag), be16_to_cpu(csum));
-			return -EIO;
-		}
-
-		buf += bix->sector_size;
-		sector++;
-	}
-
-	return 0;
-}
-
-static int sd_dif_type3_verify_crc(struct blk_integrity_exchg *bix)
-{
-	return sd_dif_type3_verify(bix, sd_dif_crc_fn);
-}
-
-static int sd_dif_type3_verify_ip(struct blk_integrity_exchg *bix)
-{
-	return sd_dif_type3_verify(bix, sd_dif_ip_fn);
-}
-
-static void sd_dif_type3_set_tag(void *prot, void *tag_buf, unsigned int sectors)
-{
-	struct sd_dif_tuple *sdt = prot;
-	u8 *tag = tag_buf;
-	unsigned int i, j;
-
-	for (i = 0, j = 0 ; i < sectors ; i++, j += 6, sdt++) {
-		sdt->app_tag = tag[j] << 8 | tag[j+1];
-		sdt->ref_tag = tag[j+2] << 24 | tag[j+3] << 16 |
-			tag[j+4] << 8 | tag[j+5];
-	}
-}
-
-static void sd_dif_type3_get_tag(void *prot, void *tag_buf, unsigned int sectors)
-{
-	struct sd_dif_tuple *sdt = prot;
-	u8 *tag = tag_buf;
-	unsigned int i, j;
-
-	for (i = 0, j = 0 ; i < sectors ; i++, j += 2, sdt++) {
-		tag[j] = (sdt->app_tag & 0xff00) >> 8;
-		tag[j+1] = sdt->app_tag & 0xff;
-		tag[j+2] = (sdt->ref_tag & 0xff000000) >> 24;
-		tag[j+3] = (sdt->ref_tag & 0xff0000) >> 16;
-		tag[j+4] = (sdt->ref_tag & 0xff00) >> 8;
-		tag[j+5] = sdt->ref_tag & 0xff;
-		BUG_ON(sdt->app_tag == 0xffff || sdt->ref_tag == 0xffffffff);
-	}
-}
-
-static struct blk_integrity dif_type3_integrity_crc = {
-	.name			= "T10-DIF-TYPE3-CRC",
-	.generate_fn		= sd_dif_type3_generate_crc,
-	.verify_fn		= sd_dif_type3_verify_crc,
-	.get_tag_fn		= sd_dif_type3_get_tag,
-	.set_tag_fn		= sd_dif_type3_set_tag,
-	.tuple_size		= sizeof(struct sd_dif_tuple),
-	.tag_size		= 0,
-};
-
-static struct blk_integrity dif_type3_integrity_ip = {
-	.name			= "T10-DIF-TYPE3-IP",
-	.generate_fn		= sd_dif_type3_generate_ip,
-	.verify_fn		= sd_dif_type3_verify_ip,
-	.get_tag_fn		= sd_dif_type3_get_tag,
-	.set_tag_fn		= sd_dif_type3_set_tag,
-	.tuple_size		= sizeof(struct sd_dif_tuple),
-	.tag_size		= 0,
-};
-
 /*
  * Configure exchange of protection information between OS and HBA.
  */
@@ -316,22 +56,30 @@ void sd_dif_config_host(struct scsi_disk *sdkp)
 		return;
 
 	/* Enable DMA of protection information */
-	if (scsi_host_get_guard(sdkp->device->host) & SHOST_DIX_GUARD_IP)
+	if (scsi_host_get_guard(sdkp->device->host) & SHOST_DIX_GUARD_IP) {
 		if (type == SD_DIF_TYPE3_PROTECTION)
-			blk_integrity_register(disk, &dif_type3_integrity_ip);
+			blk_integrity_register(disk, &t10_pi_type3_ip);
 		else
-			blk_integrity_register(disk, &dif_type1_integrity_ip);
-	else
+			blk_integrity_register(disk, &t10_pi_type1_ip);
+
+		disk->integrity->flags |= BLK_INTEGRITY_IP_CHECKSUM;
+	} else
 		if (type == SD_DIF_TYPE3_PROTECTION)
-			blk_integrity_register(disk, &dif_type3_integrity_crc);
+			blk_integrity_register(disk, &t10_pi_type3_crc);
 		else
-			blk_integrity_register(disk, &dif_type1_integrity_crc);
+			blk_integrity_register(disk, &t10_pi_type1_crc);
 
 	sd_printk(KERN_NOTICE, sdkp,
 		  "Enabling DIX %s protection\n", disk->integrity->name);
 
 	/* Signal to block layer that we support sector tagging */
-	if (dif && type && sdkp->ATO) {
+	if (dif && type) {
+
+		disk->integrity->flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+
+		if (!sdkp)
+			return;
+
 		if (type == SD_DIF_TYPE3_PROTECTION)
 			disk->integrity->tag_size = sizeof(u16) + sizeof(u32);
 		else
@@ -358,50 +106,49 @@ void sd_dif_config_host(struct scsi_disk *sdkp)
  *
  * Type 3 does not have a reference tag so no remapping is required.
  */
-void sd_dif_prepare(struct request *rq, sector_t hw_sector,
-		    unsigned int sector_sz)
+void sd_dif_prepare(struct scsi_cmnd *scmd)
 {
-	const int tuple_sz = sizeof(struct sd_dif_tuple);
+	const int tuple_sz = sizeof(struct t10_pi_tuple);
 	struct bio *bio;
 	struct scsi_disk *sdkp;
-	struct sd_dif_tuple *sdt;
+	struct t10_pi_tuple *pi;
 	u32 phys, virt;
 
-	sdkp = rq->bio->bi_bdev->bd_disk->private_data;
+	sdkp = scsi_disk(scmd->request->rq_disk);
 
 	if (sdkp->protection_type == SD_DIF_TYPE3_PROTECTION)
 		return;
 
-	phys = hw_sector & 0xffffffff;
+	phys = scsi_prot_ref_tag(scmd);
 
-	__rq_for_each_bio(bio, rq) {
+	__rq_for_each_bio(bio, scmd->request) {
+		struct bio_integrity_payload *bip = bio_integrity(bio);
 		struct bio_vec iv;
 		struct bvec_iter iter;
 		unsigned int j;
 
 		/* Already remapped? */
-		if (bio_flagged(bio, BIO_MAPPED_INTEGRITY))
+		if (bip->bip_flags & BIP_MAPPED_INTEGRITY)
 			break;
 
-		virt = bio->bi_integrity->bip_iter.bi_sector & 0xffffffff;
+		virt = bip_get_seed(bip) & 0xffffffff;
 
-		bip_for_each_vec(iv, bio->bi_integrity, iter) {
-			sdt = kmap_atomic(iv.bv_page)
-				+ iv.bv_offset;
+		bip_for_each_vec(iv, bip, iter) {
+			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
 
-			for (j = 0; j < iv.bv_len; j += tuple_sz, sdt++) {
+			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
 
-				if (be32_to_cpu(sdt->ref_tag) == virt)
-					sdt->ref_tag = cpu_to_be32(phys);
+				if (be32_to_cpu(pi->ref_tag) == virt)
+					pi->ref_tag = cpu_to_be32(phys);
 
 				virt++;
 				phys++;
 			}
 
-			kunmap_atomic(sdt);
+			kunmap_atomic(pi);
 		}
 
-		bio->bi_flags |= (1 << BIO_MAPPED_INTEGRITY);
+		bip->bip_flags |= BIP_MAPPED_INTEGRITY;
 	}
 }
 
@@ -411,11 +158,11 @@ void sd_dif_prepare(struct request *rq, sector_t hw_sector,
  */
 void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 {
-	const int tuple_sz = sizeof(struct sd_dif_tuple);
+	const int tuple_sz = sizeof(struct t10_pi_tuple);
 	struct scsi_disk *sdkp;
 	struct bio *bio;
-	struct sd_dif_tuple *sdt;
-	unsigned int j, sectors, sector_sz;
+	struct t10_pi_tuple *pi;
+	unsigned int j, intervals;
 	u32 phys, virt;
 
 	sdkp = scsi_disk(scmd->request->rq_disk);
@@ -423,39 +170,35 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 	if (sdkp->protection_type == SD_DIF_TYPE3_PROTECTION || good_bytes == 0)
 		return;
 
-	sector_sz = scmd->device->sector_size;
-	sectors = good_bytes / sector_sz;
-
-	phys = blk_rq_pos(scmd->request) & 0xffffffff;
-	if (sector_sz == 4096)
-		phys >>= 3;
+	intervals = good_bytes / scsi_prot_interval(scmd);
+	phys = scsi_prot_ref_tag(scmd);
 
 	__rq_for_each_bio(bio, scmd->request) {
+		struct bio_integrity_payload *bip = bio_integrity(bio);
 		struct bio_vec iv;
 		struct bvec_iter iter;
 
-		virt = bio->bi_integrity->bip_iter.bi_sector & 0xffffffff;
+		virt = bip_get_seed(bip) & 0xffffffff;
 
-		bip_for_each_vec(iv, bio->bi_integrity, iter) {
-			sdt = kmap_atomic(iv.bv_page)
-				+ iv.bv_offset;
+		bip_for_each_vec(iv, bip, iter) {
+			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
 
-			for (j = 0; j < iv.bv_len; j += tuple_sz, sdt++) {
+			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
 
-				if (sectors == 0) {
-					kunmap_atomic(sdt);
+				if (intervals == 0) {
+					kunmap_atomic(pi);
 					return;
 				}
 
-				if (be32_to_cpu(sdt->ref_tag) == phys)
-					sdt->ref_tag = cpu_to_be32(virt);
+				if (be32_to_cpu(pi->ref_tag) == phys)
+					pi->ref_tag = cpu_to_be32(virt);
 
 				virt++;
 				phys++;
-				sectors--;
+				intervals--;
 			}
 
-			kunmap_atomic(sdt);
+			kunmap_atomic(pi);
 		}
 	}
 }
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 01cf88888797..60354449d9ed 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1711,9 +1711,9 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 	}
 
 	rq = blk_get_request(q, rw, GFP_ATOMIC);
-	if (!rq) {
+	if (IS_ERR(rq)) {
 		kfree(long_cmdp);
-		return -ENOMEM;
+		return PTR_ERR(rq);
 	}
 
 	blk_rq_set_block_pc(rq);
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index d3fd6e8fb378..4daa372ed381 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -490,7 +490,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
 
 	req = blk_get_request(SRpnt->stp->device->request_queue, write,
 			      GFP_KERNEL);
-	if (!req)
+	if (IS_ERR(req))
 		return DRIVER_ERROR << 24;
 
 	blk_rq_set_block_pc(req);
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index eee1bc0b506e..b83846fc7859 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -110,6 +110,9 @@ struct virtio_scsi {
 	/* CPU hotplug notifier */
 	struct notifier_block nb;
 
+	/* Protected by event_vq lock */
+	bool stop_events;
+
 	struct virtio_scsi_vq ctrl_vq;
 	struct virtio_scsi_vq event_vq;
 	struct virtio_scsi_vq req_vqs[];
@@ -303,6 +306,11 @@ static void virtscsi_cancel_event_work(struct virtio_scsi *vscsi)
 {
 	int i;
 
+	/* Stop scheduling work before calling cancel_work_sync.  */
+	spin_lock_irq(&vscsi->event_vq.vq_lock);
+	vscsi->stop_events = true;
+	spin_unlock_irq(&vscsi->event_vq.vq_lock);
+
 	for (i = 0; i < VIRTIO_SCSI_EVENT_LEN; i++)
 		cancel_work_sync(&vscsi->event_list[i].work);
 }
@@ -390,7 +398,8 @@ static void virtscsi_complete_event(struct virtio_scsi *vscsi, void *buf)
 {
 	struct virtio_scsi_event_node *event_node = buf;
 
-	schedule_work(&event_node->work);
+	if (!vscsi->stop_events)
+		queue_work(system_freezable_wq, &event_node->work);
 }
 
 static void virtscsi_event_done(struct virtqueue *vq)
@@ -851,13 +860,6 @@ static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq,
 	virtscsi_vq->vq = vq;
 }
 
-static void virtscsi_scan(struct virtio_device *vdev)
-{
-	struct Scsi_Host *shost = (struct Scsi_Host *)vdev->priv;
-
-	scsi_scan_host(shost);
-}
-
 static void virtscsi_remove_vqs(struct virtio_device *vdev)
 {
 	struct Scsi_Host *sh = virtio_scsi_host(vdev);
@@ -916,9 +918,6 @@ static int virtscsi_init(struct virtio_device *vdev,
 	virtscsi_config_set(vdev, cdb_size, VIRTIO_SCSI_CDB_SIZE);
 	virtscsi_config_set(vdev, sense_size, VIRTIO_SCSI_SENSE_SIZE);
 
-	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG))
-		virtscsi_kick_event_all(vscsi);
-
 	err = 0;
 
 out:
@@ -997,10 +996,13 @@ static int virtscsi_probe(struct virtio_device *vdev)
 	err = scsi_add_host(shost, &vdev->dev);
 	if (err)
 		goto scsi_add_host_failed;
-	/*
-	 * scsi_scan_host() happens in virtscsi_scan() via virtio_driver->scan()
-	 * after VIRTIO_CONFIG_S_DRIVER_OK has been set..
-	 */
+
+	virtio_device_ready(vdev);
+
+	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG))
+		virtscsi_kick_event_all(vscsi);
+
+	scsi_scan_host(shost);
 	return 0;
 
 scsi_add_host_failed:
@@ -1048,8 +1050,15 @@ static int virtscsi_restore(struct virtio_device *vdev)
 		return err;
 
 	err = register_hotcpu_notifier(&vscsi->nb);
-	if (err)
+	if (err) {
 		vdev->config->del_vqs(vdev);
+		return err;
+	}
+
+	virtio_device_ready(vdev);
+
+	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG))
+		virtscsi_kick_event_all(vscsi);
 
 	return err;
 }
@@ -1073,7 +1082,6 @@ static struct virtio_driver virtio_scsi_driver = {
 	.driver.owner = THIS_MODULE,
 	.id_table = id_table,
 	.probe = virtscsi_probe,
-	.scan = virtscsi_scan,
 #ifdef CONFIG_PM_SLEEP
 	.freeze = virtscsi_freeze,
 	.restore = virtscsi_restore,
diff --git a/drivers/scsi/vmw_pvscsi.h b/drivers/scsi/vmw_pvscsi.h
index ce4588851274..ee16f0c5c47d 100644
--- a/drivers/scsi/vmw_pvscsi.h
+++ b/drivers/scsi/vmw_pvscsi.h
@@ -32,7 +32,6 @@
 
 #define MASK(n)        ((1 << (n)) - 1)        /* make an n-bit mask */
 
-#define PCI_VENDOR_ID_VMWARE		0x15AD
 #define PCI_DEVICE_ID_VMWARE_PVSCSI	0x07C0
 
 /*
diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c
new file mode 100644
index 000000000000..34199d206ba6
--- /dev/null
+++ b/drivers/scsi/xen-scsifront.c
@@ -0,0 +1,1026 @@
+/*
+ * Xen SCSI frontend driver
+ *
+ * Copyright (c) 2008, FUJITSU Limited
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/wait.h>
+#include <linux/interrupt.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+#include <linux/blkdev.h>
+#include <linux/pfn.h>
+#include <linux/slab.h>
+#include <linux/bitops.h>
+
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_device.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_host.h>
+
+#include <xen/xen.h>
+#include <xen/xenbus.h>
+#include <xen/grant_table.h>
+#include <xen/events.h>
+#include <xen/page.h>
+
+#include <xen/interface/grant_table.h>
+#include <xen/interface/io/vscsiif.h>
+#include <xen/interface/io/protocols.h>
+
+#include <asm/xen/hypervisor.h>
+
+
+#define GRANT_INVALID_REF	0
+
+#define VSCSIFRONT_OP_ADD_LUN	1
+#define VSCSIFRONT_OP_DEL_LUN	2
+
+/* Tuning point. */
+#define VSCSIIF_DEFAULT_CMD_PER_LUN 10
+#define VSCSIIF_MAX_TARGET          64
+#define VSCSIIF_MAX_LUN             255
+
+#define VSCSIIF_RING_SIZE	__CONST_RING_SIZE(vscsiif, PAGE_SIZE)
+#define VSCSIIF_MAX_REQS	VSCSIIF_RING_SIZE
+
+#define vscsiif_grants_sg(_sg)	(PFN_UP((_sg) *		\
+				sizeof(struct scsiif_request_segment)))
+
+struct vscsifrnt_shadow {
+	/* command between backend and frontend */
+	unsigned char act;
+	uint16_t rqid;
+
+	unsigned int nr_grants;		/* number of grants in gref[] */
+	struct scsiif_request_segment *sg;	/* scatter/gather elements */
+
+	/* Do reset or abort function. */
+	wait_queue_head_t wq_reset;	/* reset work queue           */
+	int wait_reset;			/* reset work queue condition */
+	int32_t rslt_reset;		/* reset response status:     */
+					/* SUCCESS or FAILED or:      */
+#define RSLT_RESET_WAITING	0
+#define RSLT_RESET_ERR		-1
+
+	/* Requested struct scsi_cmnd is stored from kernel. */
+	struct scsi_cmnd *sc;
+	int gref[vscsiif_grants_sg(SG_ALL) + SG_ALL];
+};
+
+struct vscsifrnt_info {
+	struct xenbus_device *dev;
+
+	struct Scsi_Host *host;
+	int host_active;
+
+	unsigned int evtchn;
+	unsigned int irq;
+
+	grant_ref_t ring_ref;
+	struct vscsiif_front_ring ring;
+	struct vscsiif_response	ring_rsp;
+
+	spinlock_t shadow_lock;
+	DECLARE_BITMAP(shadow_free_bitmap, VSCSIIF_MAX_REQS);
+	struct vscsifrnt_shadow *shadow[VSCSIIF_MAX_REQS];
+
+	wait_queue_head_t wq_sync;
+	unsigned int wait_ring_available:1;
+
+	char dev_state_path[64];
+	struct task_struct *curr;
+};
+
+static DEFINE_MUTEX(scsifront_mutex);
+
+static void scsifront_wake_up(struct vscsifrnt_info *info)
+{
+	info->wait_ring_available = 0;
+	wake_up(&info->wq_sync);
+}
+
+static int scsifront_get_rqid(struct vscsifrnt_info *info)
+{
+	unsigned long flags;
+	int free;
+
+	spin_lock_irqsave(&info->shadow_lock, flags);
+
+	free = find_first_bit(info->shadow_free_bitmap, VSCSIIF_MAX_REQS);
+	__clear_bit(free, info->shadow_free_bitmap);
+
+	spin_unlock_irqrestore(&info->shadow_lock, flags);
+
+	return free;
+}
+
+static int _scsifront_put_rqid(struct vscsifrnt_info *info, uint32_t id)
+{
+	int empty = bitmap_empty(info->shadow_free_bitmap, VSCSIIF_MAX_REQS);
+
+	__set_bit(id, info->shadow_free_bitmap);
+	info->shadow[id] = NULL;
+
+	return empty || info->wait_ring_available;
+}
+
+static void scsifront_put_rqid(struct vscsifrnt_info *info, uint32_t id)
+{
+	unsigned long flags;
+	int kick;
+
+	spin_lock_irqsave(&info->shadow_lock, flags);
+	kick = _scsifront_put_rqid(info, id);
+	spin_unlock_irqrestore(&info->shadow_lock, flags);
+
+	if (kick)
+		scsifront_wake_up(info);
+}
+
+static struct vscsiif_request *scsifront_pre_req(struct vscsifrnt_info *info)
+{
+	struct vscsiif_front_ring *ring = &(info->ring);
+	struct vscsiif_request *ring_req;
+	uint32_t id;
+
+	id = scsifront_get_rqid(info);	/* use id in response */
+	if (id >= VSCSIIF_MAX_REQS)
+		return NULL;
+
+	ring_req = RING_GET_REQUEST(&(info->ring), ring->req_prod_pvt);
+
+	ring->req_prod_pvt++;
+
+	ring_req->rqid = (uint16_t)id;
+
+	return ring_req;
+}
+
+static void scsifront_do_request(struct vscsifrnt_info *info)
+{
+	struct vscsiif_front_ring *ring = &(info->ring);
+	int notify;
+
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(ring, notify);
+	if (notify)
+		notify_remote_via_irq(info->irq);
+}
+
+static void scsifront_gnttab_done(struct vscsifrnt_info *info, uint32_t id)
+{
+	struct vscsifrnt_shadow *s = info->shadow[id];
+	int i;
+
+	if (s->sc->sc_data_direction == DMA_NONE)
+		return;
+
+	for (i = 0; i < s->nr_grants; i++) {
+		if (unlikely(gnttab_query_foreign_access(s->gref[i]) != 0)) {
+			shost_printk(KERN_ALERT, info->host, KBUILD_MODNAME
+				     "grant still in use by backend\n");
+			BUG();
+		}
+		gnttab_end_foreign_access(s->gref[i], 0, 0UL);
+	}
+
+	kfree(s->sg);
+}
+
+static void scsifront_cdb_cmd_done(struct vscsifrnt_info *info,
+				   struct vscsiif_response *ring_rsp)
+{
+	struct scsi_cmnd *sc;
+	uint32_t id;
+	uint8_t sense_len;
+
+	id = ring_rsp->rqid;
+	sc = info->shadow[id]->sc;
+
+	BUG_ON(sc == NULL);
+
+	scsifront_gnttab_done(info, id);
+	scsifront_put_rqid(info, id);
+
+	sc->result = ring_rsp->rslt;
+	scsi_set_resid(sc, ring_rsp->residual_len);
+
+	sense_len = min_t(uint8_t, VSCSIIF_SENSE_BUFFERSIZE,
+			  ring_rsp->sense_len);
+
+	if (sense_len)
+		memcpy(sc->sense_buffer, ring_rsp->sense_buffer, sense_len);
+
+	sc->scsi_done(sc);
+}
+
+static void scsifront_sync_cmd_done(struct vscsifrnt_info *info,
+				    struct vscsiif_response *ring_rsp)
+{
+	uint16_t id = ring_rsp->rqid;
+	unsigned long flags;
+	struct vscsifrnt_shadow *shadow = info->shadow[id];
+	int kick;
+
+	spin_lock_irqsave(&info->shadow_lock, flags);
+	shadow->wait_reset = 1;
+	switch (shadow->rslt_reset) {
+	case RSLT_RESET_WAITING:
+		shadow->rslt_reset = ring_rsp->rslt;
+		break;
+	case RSLT_RESET_ERR:
+		kick = _scsifront_put_rqid(info, id);
+		spin_unlock_irqrestore(&info->shadow_lock, flags);
+		kfree(shadow);
+		if (kick)
+			scsifront_wake_up(info);
+		return;
+	default:
+		shost_printk(KERN_ERR, info->host, KBUILD_MODNAME
+			     "bad reset state %d, possibly leaking %u\n",
+			     shadow->rslt_reset, id);
+		break;
+	}
+	spin_unlock_irqrestore(&info->shadow_lock, flags);
+
+	wake_up(&shadow->wq_reset);
+}
+
+static int scsifront_cmd_done(struct vscsifrnt_info *info)
+{
+	struct vscsiif_response *ring_rsp;
+	RING_IDX i, rp;
+	int more_to_do = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(info->host->host_lock, flags);
+
+	rp = info->ring.sring->rsp_prod;
+	rmb();	/* ordering required respective to dom0 */
+	for (i = info->ring.rsp_cons; i != rp; i++) {
+
+		ring_rsp = RING_GET_RESPONSE(&info->ring, i);
+
+		if (WARN(ring_rsp->rqid >= VSCSIIF_MAX_REQS ||
+			 test_bit(ring_rsp->rqid, info->shadow_free_bitmap),
+			 "illegal rqid %u returned by backend!\n",
+			 ring_rsp->rqid))
+			continue;
+
+		if (info->shadow[ring_rsp->rqid]->act == VSCSIIF_ACT_SCSI_CDB)
+			scsifront_cdb_cmd_done(info, ring_rsp);
+		else
+			scsifront_sync_cmd_done(info, ring_rsp);
+	}
+
+	info->ring.rsp_cons = i;
+
+	if (i != info->ring.req_prod_pvt)
+		RING_FINAL_CHECK_FOR_RESPONSES(&info->ring, more_to_do);
+	else
+		info->ring.sring->rsp_event = i + 1;
+
+	info->wait_ring_available = 0;
+
+	spin_unlock_irqrestore(info->host->host_lock, flags);
+
+	wake_up(&info->wq_sync);
+
+	return more_to_do;
+}
+
+static irqreturn_t scsifront_irq_fn(int irq, void *dev_id)
+{
+	struct vscsifrnt_info *info = dev_id;
+
+	while (scsifront_cmd_done(info))
+		/* Yield point for this unbounded loop. */
+		cond_resched();
+
+	return IRQ_HANDLED;
+}
+
+static int map_data_for_request(struct vscsifrnt_info *info,
+				struct scsi_cmnd *sc,
+				struct vscsiif_request *ring_req,
+				struct vscsifrnt_shadow *shadow)
+{
+	grant_ref_t gref_head;
+	struct page *page;
+	int err, ref, ref_cnt = 0;
+	int grant_ro = (sc->sc_data_direction == DMA_TO_DEVICE);
+	unsigned int i, off, len, bytes;
+	unsigned int data_len = scsi_bufflen(sc);
+	unsigned int data_grants = 0, seg_grants = 0;
+	struct scatterlist *sg;
+	unsigned long mfn;
+	struct scsiif_request_segment *seg;
+
+	ring_req->nr_segments = 0;
+	if (sc->sc_data_direction == DMA_NONE || !data_len)
+		return 0;
+
+	scsi_for_each_sg(sc, sg, scsi_sg_count(sc), i)
+		data_grants += PFN_UP(sg->offset + sg->length);
+
+	if (data_grants > VSCSIIF_SG_TABLESIZE) {
+		if (data_grants > info->host->sg_tablesize) {
+			shost_printk(KERN_ERR, info->host, KBUILD_MODNAME
+			     "Unable to map request_buffer for command!\n");
+			return -E2BIG;
+		}
+		seg_grants = vscsiif_grants_sg(data_grants);
+		shadow->sg = kcalloc(data_grants,
+			sizeof(struct scsiif_request_segment), GFP_ATOMIC);
+		if (!shadow->sg)
+			return -ENOMEM;
+	}
+	seg = shadow->sg ? : ring_req->seg;
+
+	err = gnttab_alloc_grant_references(seg_grants + data_grants,
+					    &gref_head);
+	if (err) {
+		kfree(shadow->sg);
+		shost_printk(KERN_ERR, info->host, KBUILD_MODNAME
+			     "gnttab_alloc_grant_references() error\n");
+		return -ENOMEM;
+	}
+
+	if (seg_grants) {
+		page = virt_to_page(seg);
+		off = (unsigned long)seg & ~PAGE_MASK;
+		len = sizeof(struct scsiif_request_segment) * data_grants;
+		while (len > 0) {
+			bytes = min_t(unsigned int, len, PAGE_SIZE - off);
+
+			ref = gnttab_claim_grant_reference(&gref_head);
+			BUG_ON(ref == -ENOSPC);
+
+			mfn = pfn_to_mfn(page_to_pfn(page));
+			gnttab_grant_foreign_access_ref(ref,
+				info->dev->otherend_id, mfn, 1);
+			shadow->gref[ref_cnt] = ref;
+			ring_req->seg[ref_cnt].gref   = ref;
+			ring_req->seg[ref_cnt].offset = (uint16_t)off;
+			ring_req->seg[ref_cnt].length = (uint16_t)bytes;
+
+			page++;
+			len -= bytes;
+			off = 0;
+			ref_cnt++;
+		}
+		BUG_ON(seg_grants < ref_cnt);
+		seg_grants = ref_cnt;
+	}
+
+	scsi_for_each_sg(sc, sg, scsi_sg_count(sc), i) {
+		page = sg_page(sg);
+		off = sg->offset;
+		len = sg->length;
+
+		while (len > 0 && data_len > 0) {
+			/*
+			 * sg sends a scatterlist that is larger than
+			 * the data_len it wants transferred for certain
+			 * IO sizes.
+			 */
+			bytes = min_t(unsigned int, len, PAGE_SIZE - off);
+			bytes = min(bytes, data_len);
+
+			ref = gnttab_claim_grant_reference(&gref_head);
+			BUG_ON(ref == -ENOSPC);
+
+			mfn = pfn_to_mfn(page_to_pfn(page));
+			gnttab_grant_foreign_access_ref(ref,
+				info->dev->otherend_id, mfn, grant_ro);
+
+			shadow->gref[ref_cnt] = ref;
+			seg->gref   = ref;
+			seg->offset = (uint16_t)off;
+			seg->length = (uint16_t)bytes;
+
+			page++;
+			seg++;
+			len -= bytes;
+			data_len -= bytes;
+			off = 0;
+			ref_cnt++;
+		}
+	}
+
+	if (seg_grants)
+		ring_req->nr_segments = VSCSIIF_SG_GRANT | seg_grants;
+	else
+		ring_req->nr_segments = (uint8_t)ref_cnt;
+	shadow->nr_grants = ref_cnt;
+
+	return 0;
+}
+
+static struct vscsiif_request *scsifront_command2ring(
+		struct vscsifrnt_info *info, struct scsi_cmnd *sc,
+		struct vscsifrnt_shadow *shadow)
+{
+	struct vscsiif_request *ring_req;
+
+	memset(shadow, 0, sizeof(*shadow));
+
+	ring_req = scsifront_pre_req(info);
+	if (!ring_req)
+		return NULL;
+
+	info->shadow[ring_req->rqid] = shadow;
+	shadow->rqid = ring_req->rqid;
+
+	ring_req->id      = sc->device->id;
+	ring_req->lun     = sc->device->lun;
+	ring_req->channel = sc->device->channel;
+	ring_req->cmd_len = sc->cmd_len;
+
+	BUG_ON(sc->cmd_len > VSCSIIF_MAX_COMMAND_SIZE);
+
+	memcpy(ring_req->cmnd, sc->cmnd, sc->cmd_len);
+
+	ring_req->sc_data_direction   = (uint8_t)sc->sc_data_direction;
+	ring_req->timeout_per_command = sc->request->timeout / HZ;
+
+	return ring_req;
+}
+
+static int scsifront_queuecommand(struct Scsi_Host *shost,
+				  struct scsi_cmnd *sc)
+{
+	struct vscsifrnt_info *info = shost_priv(shost);
+	struct vscsiif_request *ring_req;
+	struct vscsifrnt_shadow *shadow = scsi_cmd_priv(sc);
+	unsigned long flags;
+	int err;
+	uint16_t rqid;
+
+	spin_lock_irqsave(shost->host_lock, flags);
+	if (RING_FULL(&info->ring))
+		goto busy;
+
+	ring_req = scsifront_command2ring(info, sc, shadow);
+	if (!ring_req)
+		goto busy;
+
+	sc->result = 0;
+
+	rqid = ring_req->rqid;
+	ring_req->act = VSCSIIF_ACT_SCSI_CDB;
+
+	shadow->sc  = sc;
+	shadow->act = VSCSIIF_ACT_SCSI_CDB;
+
+	err = map_data_for_request(info, sc, ring_req, shadow);
+	if (err < 0) {
+		pr_debug("%s: err %d\n", __func__, err);
+		scsifront_put_rqid(info, rqid);
+		spin_unlock_irqrestore(shost->host_lock, flags);
+		if (err == -ENOMEM)
+			return SCSI_MLQUEUE_HOST_BUSY;
+		sc->result = DID_ERROR << 16;
+		sc->scsi_done(sc);
+		return 0;
+	}
+
+	scsifront_do_request(info);
+	spin_unlock_irqrestore(shost->host_lock, flags);
+
+	return 0;
+
+busy:
+	spin_unlock_irqrestore(shost->host_lock, flags);
+	pr_debug("%s: busy\n", __func__);
+	return SCSI_MLQUEUE_HOST_BUSY;
+}
+
+/*
+ * Any exception handling (reset or abort) must be forwarded to the backend.
+ * We have to wait until an answer is returned. This answer contains the
+ * result to be returned to the requestor.
+ */
+static int scsifront_action_handler(struct scsi_cmnd *sc, uint8_t act)
+{
+	struct Scsi_Host *host = sc->device->host;
+	struct vscsifrnt_info *info = shost_priv(host);
+	struct vscsifrnt_shadow *shadow, *s = scsi_cmd_priv(sc);
+	struct vscsiif_request *ring_req;
+	int err = 0;
+
+	shadow = kmalloc(sizeof(*shadow), GFP_NOIO);
+	if (!shadow)
+		return FAILED;
+
+	spin_lock_irq(host->host_lock);
+
+	for (;;) {
+		if (!RING_FULL(&info->ring)) {
+			ring_req = scsifront_command2ring(info, sc, shadow);
+			if (ring_req)
+				break;
+		}
+		if (err) {
+			spin_unlock_irq(host->host_lock);
+			kfree(shadow);
+			return FAILED;
+		}
+		info->wait_ring_available = 1;
+		spin_unlock_irq(host->host_lock);
+		err = wait_event_interruptible(info->wq_sync,
+					       !info->wait_ring_available);
+		spin_lock_irq(host->host_lock);
+	}
+
+	ring_req->act = act;
+	ring_req->ref_rqid = s->rqid;
+
+	shadow->act = act;
+	shadow->rslt_reset = RSLT_RESET_WAITING;
+	init_waitqueue_head(&shadow->wq_reset);
+
+	ring_req->nr_segments = 0;
+
+	scsifront_do_request(info);
+
+	spin_unlock_irq(host->host_lock);
+	err = wait_event_interruptible(shadow->wq_reset, shadow->wait_reset);
+	spin_lock_irq(host->host_lock);
+
+	if (!err) {
+		err = shadow->rslt_reset;
+		scsifront_put_rqid(info, shadow->rqid);
+		kfree(shadow);
+	} else {
+		spin_lock(&info->shadow_lock);
+		shadow->rslt_reset = RSLT_RESET_ERR;
+		spin_unlock(&info->shadow_lock);
+		err = FAILED;
+	}
+
+	spin_unlock_irq(host->host_lock);
+	return err;
+}
+
+static int scsifront_eh_abort_handler(struct scsi_cmnd *sc)
+{
+	pr_debug("%s\n", __func__);
+	return scsifront_action_handler(sc, VSCSIIF_ACT_SCSI_ABORT);
+}
+
+static int scsifront_dev_reset_handler(struct scsi_cmnd *sc)
+{
+	pr_debug("%s\n", __func__);
+	return scsifront_action_handler(sc, VSCSIIF_ACT_SCSI_RESET);
+}
+
+static int scsifront_sdev_configure(struct scsi_device *sdev)
+{
+	struct vscsifrnt_info *info = shost_priv(sdev->host);
+
+	if (info && current == info->curr)
+		xenbus_printf(XBT_NIL, info->dev->nodename,
+			      info->dev_state_path, "%d", XenbusStateConnected);
+
+	return 0;
+}
+
+static void scsifront_sdev_destroy(struct scsi_device *sdev)
+{
+	struct vscsifrnt_info *info = shost_priv(sdev->host);
+
+	if (info && current == info->curr)
+		xenbus_printf(XBT_NIL, info->dev->nodename,
+			      info->dev_state_path, "%d", XenbusStateClosed);
+}
+
+static struct scsi_host_template scsifront_sht = {
+	.module			= THIS_MODULE,
+	.name			= "Xen SCSI frontend driver",
+	.queuecommand		= scsifront_queuecommand,
+	.eh_abort_handler	= scsifront_eh_abort_handler,
+	.eh_device_reset_handler = scsifront_dev_reset_handler,
+	.slave_configure	= scsifront_sdev_configure,
+	.slave_destroy		= scsifront_sdev_destroy,
+	.cmd_per_lun		= VSCSIIF_DEFAULT_CMD_PER_LUN,
+	.can_queue		= VSCSIIF_MAX_REQS,
+	.this_id		= -1,
+	.cmd_size		= sizeof(struct vscsifrnt_shadow),
+	.sg_tablesize		= VSCSIIF_SG_TABLESIZE,
+	.use_clustering		= DISABLE_CLUSTERING,
+	.proc_name		= "scsifront",
+};
+
+static int scsifront_alloc_ring(struct vscsifrnt_info *info)
+{
+	struct xenbus_device *dev = info->dev;
+	struct vscsiif_sring *sring;
+	int err = -ENOMEM;
+
+	/***** Frontend to Backend ring start *****/
+	sring = (struct vscsiif_sring *)__get_free_page(GFP_KERNEL);
+	if (!sring) {
+		xenbus_dev_fatal(dev, err,
+			"fail to allocate shared ring (Front to Back)");
+		return err;
+	}
+	SHARED_RING_INIT(sring);
+	FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE);
+
+	err = xenbus_grant_ring(dev, virt_to_mfn(sring));
+	if (err < 0) {
+		free_page((unsigned long)sring);
+		xenbus_dev_fatal(dev, err,
+			"fail to grant shared ring (Front to Back)");
+		return err;
+	}
+	info->ring_ref = err;
+
+	err = xenbus_alloc_evtchn(dev, &info->evtchn);
+	if (err) {
+		xenbus_dev_fatal(dev, err, "xenbus_alloc_evtchn");
+		goto free_gnttab;
+	}
+
+	err = bind_evtchn_to_irq(info->evtchn);
+	if (err <= 0) {
+		xenbus_dev_fatal(dev, err, "bind_evtchn_to_irq");
+		goto free_gnttab;
+	}
+
+	info->irq = err;
+
+	err = request_threaded_irq(info->irq, NULL, scsifront_irq_fn,
+				   IRQF_ONESHOT, "scsifront", info);
+	if (err) {
+		xenbus_dev_fatal(dev, err, "request_threaded_irq");
+		goto free_irq;
+	}
+
+	return 0;
+
+/* free resource */
+free_irq:
+	unbind_from_irqhandler(info->irq, info);
+free_gnttab:
+	gnttab_end_foreign_access(info->ring_ref, 0,
+				  (unsigned long)info->ring.sring);
+
+	return err;
+}
+
+static int scsifront_init_ring(struct vscsifrnt_info *info)
+{
+	struct xenbus_device *dev = info->dev;
+	struct xenbus_transaction xbt;
+	int err;
+
+	pr_debug("%s\n", __func__);
+
+	err = scsifront_alloc_ring(info);
+	if (err)
+		return err;
+	pr_debug("%s: %u %u\n", __func__, info->ring_ref, info->evtchn);
+
+again:
+	err = xenbus_transaction_start(&xbt);
+	if (err)
+		xenbus_dev_fatal(dev, err, "starting transaction");
+
+	err = xenbus_printf(xbt, dev->nodename, "ring-ref", "%u",
+			    info->ring_ref);
+	if (err) {
+		xenbus_dev_fatal(dev, err, "%s", "writing ring-ref");
+		goto fail;
+	}
+
+	err = xenbus_printf(xbt, dev->nodename, "event-channel", "%u",
+			    info->evtchn);
+
+	if (err) {
+		xenbus_dev_fatal(dev, err, "%s", "writing event-channel");
+		goto fail;
+	}
+
+	err = xenbus_transaction_end(xbt, 0);
+	if (err) {
+		if (err == -EAGAIN)
+			goto again;
+		xenbus_dev_fatal(dev, err, "completing transaction");
+		goto free_sring;
+	}
+
+	return 0;
+
+fail:
+	xenbus_transaction_end(xbt, 1);
+free_sring:
+	unbind_from_irqhandler(info->irq, info);
+	gnttab_end_foreign_access(info->ring_ref, 0,
+				  (unsigned long)info->ring.sring);
+
+	return err;
+}
+
+
+static int scsifront_probe(struct xenbus_device *dev,
+			   const struct xenbus_device_id *id)
+{
+	struct vscsifrnt_info *info;
+	struct Scsi_Host *host;
+	int err = -ENOMEM;
+	char name[TASK_COMM_LEN];
+
+	host = scsi_host_alloc(&scsifront_sht, sizeof(*info));
+	if (!host) {
+		xenbus_dev_fatal(dev, err, "fail to allocate scsi host");
+		return err;
+	}
+	info = (struct vscsifrnt_info *)host->hostdata;
+
+	dev_set_drvdata(&dev->dev, info);
+	info->dev = dev;
+
+	bitmap_fill(info->shadow_free_bitmap, VSCSIIF_MAX_REQS);
+
+	err = scsifront_init_ring(info);
+	if (err) {
+		scsi_host_put(host);
+		return err;
+	}
+
+	init_waitqueue_head(&info->wq_sync);
+	spin_lock_init(&info->shadow_lock);
+
+	snprintf(name, TASK_COMM_LEN, "vscsiif.%d", host->host_no);
+
+	host->max_id      = VSCSIIF_MAX_TARGET;
+	host->max_channel = 0;
+	host->max_lun     = VSCSIIF_MAX_LUN;
+	host->max_sectors = (host->sg_tablesize - 1) * PAGE_SIZE / 512;
+	host->max_cmd_len = VSCSIIF_MAX_COMMAND_SIZE;
+
+	err = scsi_add_host(host, &dev->dev);
+	if (err) {
+		dev_err(&dev->dev, "fail to add scsi host %d\n", err);
+		goto free_sring;
+	}
+	info->host = host;
+	info->host_active = 1;
+
+	xenbus_switch_state(dev, XenbusStateInitialised);
+
+	return 0;
+
+free_sring:
+	unbind_from_irqhandler(info->irq, info);
+	gnttab_end_foreign_access(info->ring_ref, 0,
+				  (unsigned long)info->ring.sring);
+	scsi_host_put(host);
+	return err;
+}
+
+static int scsifront_remove(struct xenbus_device *dev)
+{
+	struct vscsifrnt_info *info = dev_get_drvdata(&dev->dev);
+
+	pr_debug("%s: %s removed\n", __func__, dev->nodename);
+
+	mutex_lock(&scsifront_mutex);
+	if (info->host_active) {
+		/* Scsi_host not yet removed */
+		scsi_remove_host(info->host);
+		info->host_active = 0;
+	}
+	mutex_unlock(&scsifront_mutex);
+
+	gnttab_end_foreign_access(info->ring_ref, 0,
+				  (unsigned long)info->ring.sring);
+	unbind_from_irqhandler(info->irq, info);
+
+	scsi_host_put(info->host);
+
+	return 0;
+}
+
+static void scsifront_disconnect(struct vscsifrnt_info *info)
+{
+	struct xenbus_device *dev = info->dev;
+	struct Scsi_Host *host = info->host;
+
+	pr_debug("%s: %s disconnect\n", __func__, dev->nodename);
+
+	/*
+	 * When this function is executed, all devices of
+	 * Frontend have been deleted.
+	 * Therefore, it need not block I/O before remove_host.
+	 */
+
+	mutex_lock(&scsifront_mutex);
+	if (info->host_active) {
+		scsi_remove_host(host);
+		info->host_active = 0;
+	}
+	mutex_unlock(&scsifront_mutex);
+
+	xenbus_frontend_closed(dev);
+}
+
+static void scsifront_do_lun_hotplug(struct vscsifrnt_info *info, int op)
+{
+	struct xenbus_device *dev = info->dev;
+	int i, err = 0;
+	char str[64];
+	char **dir;
+	unsigned int dir_n = 0;
+	unsigned int device_state;
+	unsigned int hst, chn, tgt, lun;
+	struct scsi_device *sdev;
+
+	dir = xenbus_directory(XBT_NIL, dev->otherend, "vscsi-devs", &dir_n);
+	if (IS_ERR(dir))
+		return;
+
+	/* mark current task as the one allowed to modify device states */
+	BUG_ON(info->curr);
+	info->curr = current;
+
+	for (i = 0; i < dir_n; i++) {
+		/* read status */
+		snprintf(str, sizeof(str), "vscsi-devs/%s/state", dir[i]);
+		err = xenbus_scanf(XBT_NIL, dev->otherend, str, "%u",
+				   &device_state);
+		if (XENBUS_EXIST_ERR(err))
+			continue;
+
+		/* virtual SCSI device */
+		snprintf(str, sizeof(str), "vscsi-devs/%s/v-dev", dir[i]);
+		err = xenbus_scanf(XBT_NIL, dev->otherend, str,
+				   "%u:%u:%u:%u", &hst, &chn, &tgt, &lun);
+		if (XENBUS_EXIST_ERR(err))
+			continue;
+
+		/*
+		 * Front device state path, used in slave_configure called
+		 * on successfull scsi_add_device, and in slave_destroy called
+		 * on remove of a device.
+		 */
+		snprintf(info->dev_state_path, sizeof(info->dev_state_path),
+			 "vscsi-devs/%s/state", dir[i]);
+
+		switch (op) {
+		case VSCSIFRONT_OP_ADD_LUN:
+			if (device_state != XenbusStateInitialised)
+				break;
+
+			if (scsi_add_device(info->host, chn, tgt, lun)) {
+				dev_err(&dev->dev, "scsi_add_device\n");
+				xenbus_printf(XBT_NIL, dev->nodename,
+					      info->dev_state_path,
+					      "%d", XenbusStateClosed);
+			}
+			break;
+		case VSCSIFRONT_OP_DEL_LUN:
+			if (device_state != XenbusStateClosing)
+				break;
+
+			sdev = scsi_device_lookup(info->host, chn, tgt, lun);
+			if (sdev) {
+				scsi_remove_device(sdev);
+				scsi_device_put(sdev);
+			}
+			break;
+		default:
+			break;
+		}
+	}
+
+	info->curr = NULL;
+
+	kfree(dir);
+}
+
+static void scsifront_read_backend_params(struct xenbus_device *dev,
+					  struct vscsifrnt_info *info)
+{
+	unsigned int sg_grant;
+	int ret;
+	struct Scsi_Host *host = info->host;
+
+	ret = xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg-grant", "%u",
+			   &sg_grant);
+	if (ret == 1 && sg_grant) {
+		sg_grant = min_t(unsigned int, sg_grant, SG_ALL);
+		sg_grant = max_t(unsigned int, sg_grant, VSCSIIF_SG_TABLESIZE);
+		host->sg_tablesize = min_t(unsigned int, sg_grant,
+			VSCSIIF_SG_TABLESIZE * PAGE_SIZE /
+			sizeof(struct scsiif_request_segment));
+		host->max_sectors = (host->sg_tablesize - 1) * PAGE_SIZE / 512;
+	}
+	dev_info(&dev->dev, "using up to %d SG entries\n", host->sg_tablesize);
+}
+
+static void scsifront_backend_changed(struct xenbus_device *dev,
+				      enum xenbus_state backend_state)
+{
+	struct vscsifrnt_info *info = dev_get_drvdata(&dev->dev);
+
+	pr_debug("%s: %p %u %u\n", __func__, dev, dev->state, backend_state);
+
+	switch (backend_state) {
+	case XenbusStateUnknown:
+	case XenbusStateInitialising:
+	case XenbusStateInitWait:
+	case XenbusStateInitialised:
+		break;
+
+	case XenbusStateConnected:
+		scsifront_read_backend_params(dev, info);
+		if (xenbus_read_driver_state(dev->nodename) ==
+		    XenbusStateInitialised)
+			scsifront_do_lun_hotplug(info, VSCSIFRONT_OP_ADD_LUN);
+
+		if (dev->state != XenbusStateConnected)
+			xenbus_switch_state(dev, XenbusStateConnected);
+		break;
+
+	case XenbusStateClosed:
+		if (dev->state == XenbusStateClosed)
+			break;
+		/* Missed the backend's Closing state -- fallthrough */
+	case XenbusStateClosing:
+		scsifront_disconnect(info);
+		break;
+
+	case XenbusStateReconfiguring:
+		scsifront_do_lun_hotplug(info, VSCSIFRONT_OP_DEL_LUN);
+		xenbus_switch_state(dev, XenbusStateReconfiguring);
+		break;
+
+	case XenbusStateReconfigured:
+		scsifront_do_lun_hotplug(info, VSCSIFRONT_OP_ADD_LUN);
+		xenbus_switch_state(dev, XenbusStateConnected);
+		break;
+	}
+}
+
+static const struct xenbus_device_id scsifront_ids[] = {
+	{ "vscsi" },
+	{ "" }
+};
+
+static struct xenbus_driver scsifront_driver = {
+	.ids			= scsifront_ids,
+	.probe			= scsifront_probe,
+	.remove			= scsifront_remove,
+	.otherend_changed	= scsifront_backend_changed,
+};
+
+static int __init scsifront_init(void)
+{
+	if (!xen_domain())
+		return -ENODEV;
+
+	return xenbus_register_frontend(&scsifront_driver);
+}
+module_init(scsifront_init);
+
+static void __exit scsifront_exit(void)
+{
+	xenbus_unregister_driver(&scsifront_driver);
+}
+module_exit(scsifront_exit);
+
+MODULE_DESCRIPTION("Xen SCSI frontend driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:vscsi");
+MODULE_AUTHOR("Juergen Gross <jgross@suse.com>");
diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c
index 72f63817a1a0..fe2c2d595f59 100644
--- a/drivers/sh/pm_runtime.c
+++ b/drivers/sh/pm_runtime.c
@@ -75,8 +75,6 @@ static struct pm_clk_notifier_block platform_bus_notifier = {
 	.con_ids = { NULL, },
 };
 
-static bool default_pm_on;
-
 static int __init sh_pm_runtime_init(void)
 {
 	if (IS_ENABLED(CONFIG_ARCH_SHMOBILE_MULTI)) {
@@ -96,16 +94,7 @@ static int __init sh_pm_runtime_init(void)
 			return 0;
 	}
 
-	default_pm_on = true;
 	pm_clk_add_notifier(&platform_bus_type, &platform_bus_notifier);
 	return 0;
 }
 core_initcall(sh_pm_runtime_init);
-
-static int __init sh_pm_runtime_late_init(void)
-{
-	if (default_pm_on)
-		pm_genpd_poweroff_unused();
-	return 0;
-}
-late_initcall(sh_pm_runtime_late_init);
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index c41ff148a2b4..62a9297e96ac 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -157,7 +157,6 @@ static struct dma_async_tx_descriptor *
 pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
 			   enum dma_transfer_direction dir)
 {
-	struct pxa2xx_spi_master *pdata = drv_data->master_info;
 	struct chip_data *chip = drv_data->cur_chip;
 	enum dma_slave_buswidth width;
 	struct dma_slave_config cfg;
@@ -184,7 +183,6 @@ pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
 		cfg.dst_addr = drv_data->ssdr_physical;
 		cfg.dst_addr_width = width;
 		cfg.dst_maxburst = chip->dma_burst_size;
-		cfg.slave_id = pdata->tx_slave_id;
 
 		sgt = &drv_data->tx_sgt;
 		nents = drv_data->tx_nents;
@@ -193,7 +191,6 @@ pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
 		cfg.src_addr = drv_data->ssdr_physical;
 		cfg.src_addr_width = width;
 		cfg.src_maxburst = chip->dma_burst_size;
-		cfg.slave_id = pdata->rx_slave_id;
 
 		sgt = &drv_data->rx_sgt;
 		nents = drv_data->rx_nents;
@@ -210,14 +207,6 @@ pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
 				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 }
 
-static bool pxa2xx_spi_dma_filter(struct dma_chan *chan, void *param)
-{
-	const struct pxa2xx_spi_master *pdata = param;
-
-	return chan->chan_id == pdata->tx_chan_id ||
-	       chan->chan_id == pdata->rx_chan_id;
-}
-
 bool pxa2xx_spi_dma_is_possible(size_t len)
 {
 	return len <= MAX_DMA_LEN;
@@ -321,12 +310,12 @@ int pxa2xx_spi_dma_setup(struct driver_data *drv_data)
 		return -ENOMEM;
 
 	drv_data->tx_chan = dma_request_slave_channel_compat(mask,
-				pxa2xx_spi_dma_filter, pdata, dev, "tx");
+				pdata->dma_filter, pdata->tx_param, dev, "tx");
 	if (!drv_data->tx_chan)
 		return -ENODEV;
 
 	drv_data->rx_chan = dma_request_slave_channel_compat(mask,
-				pxa2xx_spi_dma_filter, pdata, dev, "rx");
+				pdata->dma_filter, pdata->rx_param, dev, "rx");
 	if (!drv_data->rx_chan) {
 		dma_release_channel(drv_data->tx_chan);
 		drv_data->tx_chan = NULL;
diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index 536c863bebf1..6beee8ce2d68 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -10,42 +10,87 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 
+#include <linux/dmaengine.h>
+#include <linux/platform_data/dma-dw.h>
+
 enum {
 	PORT_CE4100,
 	PORT_BYT,
+	PORT_BSW0,
+	PORT_BSW1,
+	PORT_BSW2,
 };
 
 struct pxa_spi_info {
 	enum pxa_ssp_type type;
 	int port_id;
 	int num_chipselect;
-	int tx_slave_id;
-	int tx_chan_id;
-	int rx_slave_id;
-	int rx_chan_id;
 	unsigned long max_clk_rate;
+
+	/* DMA channel request parameters */
+	void *tx_param;
+	void *rx_param;
 };
 
+static struct dw_dma_slave byt_tx_param = { .dst_id = 0 };
+static struct dw_dma_slave byt_rx_param = { .src_id = 1 };
+
+static struct dw_dma_slave bsw0_tx_param = { .dst_id = 0 };
+static struct dw_dma_slave bsw0_rx_param = { .src_id = 1 };
+static struct dw_dma_slave bsw1_tx_param = { .dst_id = 6 };
+static struct dw_dma_slave bsw1_rx_param = { .src_id = 7 };
+static struct dw_dma_slave bsw2_tx_param = { .dst_id = 8 };
+static struct dw_dma_slave bsw2_rx_param = { .src_id = 9 };
+
+static bool lpss_dma_filter(struct dma_chan *chan, void *param)
+{
+	struct dw_dma_slave *dws = param;
+
+	if (dws->dma_dev != chan->device->dev)
+		return false;
+
+	chan->private = dws;
+	return true;
+}
+
 static struct pxa_spi_info spi_info_configs[] = {
 	[PORT_CE4100] = {
 		.type = PXA25x_SSP,
 		.port_id =  -1,
 		.num_chipselect = -1,
-		.tx_slave_id = -1,
-		.tx_chan_id = -1,
-		.rx_slave_id = -1,
-		.rx_chan_id = -1,
 		.max_clk_rate = 3686400,
 	},
 	[PORT_BYT] = {
 		.type = LPSS_SSP,
 		.port_id = 0,
 		.num_chipselect = 1,
-		.tx_slave_id = 0,
-		.tx_chan_id = 0,
-		.rx_slave_id = 1,
-		.rx_chan_id = 1,
 		.max_clk_rate = 50000000,
+		.tx_param = &byt_tx_param,
+		.rx_param = &byt_rx_param,
+	},
+	[PORT_BSW0] = {
+		.type = LPSS_SSP,
+		.port_id = 0,
+		.num_chipselect = 1,
+		.max_clk_rate = 50000000,
+		.tx_param = &bsw0_tx_param,
+		.rx_param = &bsw0_rx_param,
+	},
+	[PORT_BSW1] = {
+		.type = LPSS_SSP,
+		.port_id = 1,
+		.num_chipselect = 1,
+		.max_clk_rate = 50000000,
+		.tx_param = &bsw1_tx_param,
+		.rx_param = &bsw1_rx_param,
+	},
+	[PORT_BSW2] = {
+		.type = LPSS_SSP,
+		.port_id = 2,
+		.num_chipselect = 1,
+		.max_clk_rate = 50000000,
+		.tx_param = &bsw2_tx_param,
+		.rx_param = &bsw2_rx_param,
 	},
 };
 
@@ -59,6 +104,7 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
 	struct ssp_device *ssp;
 	struct pxa_spi_info *c;
 	char buf[40];
+	struct pci_dev *dma_dev;
 
 	ret = pcim_enable_device(dev);
 	if (ret)
@@ -73,11 +119,29 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
 	memset(&spi_pdata, 0, sizeof(spi_pdata));
 	spi_pdata.num_chipselect = (c->num_chipselect > 0) ?
 					c->num_chipselect : dev->devfn;
-	spi_pdata.tx_slave_id = c->tx_slave_id;
-	spi_pdata.tx_chan_id = c->tx_chan_id;
-	spi_pdata.rx_slave_id = c->rx_slave_id;
-	spi_pdata.rx_chan_id = c->rx_chan_id;
-	spi_pdata.enable_dma = c->rx_slave_id >= 0 && c->tx_slave_id >= 0;
+
+	dma_dev = pci_get_slot(dev->bus, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
+
+	if (c->tx_param) {
+		struct dw_dma_slave *slave = c->tx_param;
+
+		slave->dma_dev = &dma_dev->dev;
+		slave->src_master = 1;
+		slave->dst_master = 0;
+	}
+
+	if (c->rx_param) {
+		struct dw_dma_slave *slave = c->rx_param;
+
+		slave->dma_dev = &dma_dev->dev;
+		slave->src_master = 1;
+		slave->dst_master = 0;
+	}
+
+	spi_pdata.dma_filter = lpss_dma_filter;
+	spi_pdata.tx_param = c->tx_param;
+	spi_pdata.rx_param = c->rx_param;
+	spi_pdata.enable_dma = c->rx_param && c->tx_param;
 
 	ssp = &spi_pdata.ssp;
 	ssp->phys_base = pci_resource_start(dev, 0);
@@ -128,6 +192,9 @@ static void pxa2xx_spi_pci_remove(struct pci_dev *dev)
 static const struct pci_device_id pxa2xx_spi_pci_devices[] = {
 	{ PCI_VDEVICE(INTEL, 0x2e6a), PORT_CE4100 },
 	{ PCI_VDEVICE(INTEL, 0x0f0e), PORT_BYT },
+	{ PCI_VDEVICE(INTEL, 0x228e), PORT_BSW0 },
+	{ PCI_VDEVICE(INTEL, 0x2290), PORT_BSW1 },
+	{ PCI_VDEVICE(INTEL, 0x22ac), PORT_BSW2 },
 	{ },
 };
 MODULE_DEVICE_TABLE(pci, pxa2xx_spi_pci_devices);
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 46f45ca2c694..d8a105f76837 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1062,8 +1062,6 @@ pxa2xx_spi_acpi_get_pdata(struct platform_device *pdev)
 
 	pdata->num_chipselect = 1;
 	pdata->enable_dma = true;
-	pdata->tx_chan_id = -1;
-	pdata->rx_chan_id = -1;
 
 	return pdata;
 }
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index e19512ffc40e..ebcb33df2eb2 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -35,6 +35,7 @@
 #include <linux/spi/spi.h>
 #include <linux/of_gpio.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/export.h>
 #include <linux/sched/rt.h>
 #include <linux/delay.h>
@@ -264,10 +265,12 @@ static int spi_drv_probe(struct device *dev)
 	if (ret)
 		return ret;
 
-	acpi_dev_pm_attach(dev, true);
-	ret = sdrv->probe(to_spi_device(dev));
-	if (ret)
-		acpi_dev_pm_detach(dev, true);
+	ret = dev_pm_domain_attach(dev, true);
+	if (ret != -EPROBE_DEFER) {
+		ret = sdrv->probe(to_spi_device(dev));
+		if (ret)
+			dev_pm_domain_detach(dev, true);
+	}
 
 	return ret;
 }
@@ -278,7 +281,7 @@ static int spi_drv_remove(struct device *dev)
 	int ret;
 
 	ret = sdrv->remove(to_spi_device(dev));
-	acpi_dev_pm_detach(dev, true);
+	dev_pm_domain_detach(dev, true);
 
 	return ret;
 }
diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c
index ba350d2035c0..f92e266d48f8 100644
--- a/drivers/ssb/driver_gpio.c
+++ b/drivers/ssb/driver_gpio.c
@@ -475,7 +475,8 @@ int ssb_gpio_unregister(struct ssb_bus *bus)
 {
 	if (ssb_chipco_available(&bus->chipco) ||
 	    ssb_extif_available(&bus->extif)) {
-		return gpiochip_remove(&bus->gpio);
+		gpiochip_remove(&bus->gpio);
+		return 0;
 	} else {
 		SSB_WARN_ON(1);
 	}
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 713a97226787..ad4f5790a76f 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -339,7 +339,7 @@ static loff_t ashmem_llseek(struct file *file, loff_t offset, int origin)
 		goto out;
 	}
 
-	ret = asma->file->f_op->llseek(asma->file, offset, origin);
+	ret = vfs_llseek(asma->file, offset, origin);
 	if (ret < 0)
 		goto out;
 
diff --git a/drivers/staging/android/ion/compat_ion.c b/drivers/staging/android/ion/compat_ion.c
index ee3a7380e53b..a402fdaf54ca 100644
--- a/drivers/staging/android/ion/compat_ion.c
+++ b/drivers/staging/android/ion/compat_ion.c
@@ -125,7 +125,7 @@ long compat_ion_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	long ret;
 
-	if (!filp->f_op || !filp->f_op->unlocked_ioctl)
+	if (!filp->f_op->unlocked_ioctl)
 		return -ENOTTY;
 
 	switch (cmd) {
diff --git a/drivers/staging/android/logger.c b/drivers/staging/android/logger.c
index 0bf0d24d12d5..28b93d39a94e 100644
--- a/drivers/staging/android/logger.c
+++ b/drivers/staging/android/logger.c
@@ -411,69 +411,18 @@ static void fix_up_readers(struct logger_log *log, size_t len)
 }
 
 /*
- * do_write_log - writes 'len' bytes from 'buf' to 'log'
- *
- * The caller needs to hold log->mutex.
- */
-static void do_write_log(struct logger_log *log, const void *buf, size_t count)
-{
-	size_t len;
-
-	len = min(count, log->size - log->w_off);
-	memcpy(log->buffer + log->w_off, buf, len);
-
-	if (count != len)
-		memcpy(log->buffer, buf + len, count - len);
-
-	log->w_off = logger_offset(log, log->w_off + count);
-
-}
-
-/*
- * do_write_log_user - writes 'len' bytes from the user-space buffer 'buf' to
- * the log 'log'
- *
- * The caller needs to hold log->mutex.
- *
- * Returns 'count' on success, negative error code on failure.
- */
-static ssize_t do_write_log_from_user(struct logger_log *log,
-				      const void __user *buf, size_t count)
-{
-	size_t len;
-
-	len = min(count, log->size - log->w_off);
-	if (len && copy_from_user(log->buffer + log->w_off, buf, len))
-		return -EFAULT;
-
-	if (count != len)
-		if (copy_from_user(log->buffer, buf + len, count - len))
-			/*
-			 * Note that by not updating w_off, this abandons the
-			 * portion of the new entry that *was* successfully
-			 * copied, just above.  This is intentional to avoid
-			 * message corruption from missing fragments.
-			 */
-			return -EFAULT;
-
-	log->w_off = logger_offset(log, log->w_off + count);
-
-	return count;
-}
-
-/*
- * logger_aio_write - our write method, implementing support for write(),
+ * logger_write_iter - our write method, implementing support for write(),
  * writev(), and aio_write(). Writes are our fast path, and we try to optimize
  * them above all else.
  */
-static ssize_t logger_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			 unsigned long nr_segs, loff_t ppos)
+static ssize_t logger_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct logger_log *log = file_get_log(iocb->ki_filp);
-	size_t orig;
 	struct logger_entry header;
 	struct timespec now;
-	ssize_t ret = 0;
+	size_t len, count;
+
+	count = min_t(size_t, iocb->ki_nbytes, LOGGER_ENTRY_MAX_PAYLOAD);
 
 	now = current_kernel_time();
 
@@ -482,7 +431,7 @@ static ssize_t logger_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	header.sec = now.tv_sec;
 	header.nsec = now.tv_nsec;
 	header.euid = current_euid();
-	header.len = min_t(size_t, iocb->ki_nbytes, LOGGER_ENTRY_MAX_PAYLOAD);
+	header.len = count;
 	header.hdr_size = sizeof(struct logger_entry);
 
 	/* null writes succeed, return zero */
@@ -491,8 +440,6 @@ static ssize_t logger_aio_write(struct kiocb *iocb, const struct iovec *iov,
 
 	mutex_lock(&log->mutex);
 
-	orig = log->w_off;
-
 	/*
 	 * Fix up any readers, pulling them forward to the first readable
 	 * entry after (what will be) the new write offset. We do this now
@@ -501,33 +448,35 @@ static ssize_t logger_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	 */
 	fix_up_readers(log, sizeof(struct logger_entry) + header.len);
 
-	do_write_log(log, &header, sizeof(struct logger_entry));
-
-	while (nr_segs-- > 0) {
-		size_t len;
-		ssize_t nr;
+	len = min(sizeof(header), log->size - log->w_off);
+	memcpy(log->buffer + log->w_off, &header, len);
+	memcpy(log->buffer, (char *)&header + len, sizeof(header) - len);
 
-		/* figure out how much of this vector we can keep */
-		len = min_t(size_t, iov->iov_len, header.len - ret);
+	len = min(count, log->size - log->w_off);
 
-		/* write out this segment's payload */
-		nr = do_write_log_from_user(log, iov->iov_base, len);
-		if (unlikely(nr < 0)) {
-			log->w_off = orig;
-			mutex_unlock(&log->mutex);
-			return nr;
-		}
+	if (copy_from_iter(log->buffer + log->w_off, len, from) != len) {
+		/*
+		 * Note that by not updating w_off, this abandons the
+		 * portion of the new entry that *was* successfully
+		 * copied, just above.  This is intentional to avoid
+		 * message corruption from missing fragments.
+		 */
+		mutex_unlock(&log->mutex);
+		return -EFAULT;
+	}
 
-		iov++;
-		ret += nr;
+	if (copy_from_iter(log->buffer, count - len, from) != count - len) {
+		mutex_unlock(&log->mutex);
+		return -EFAULT;
 	}
 
+	log->w_off = logger_offset(log, log->w_off + count);
 	mutex_unlock(&log->mutex);
 
 	/* wake up any blocked readers */
 	wake_up_interruptible(&log->wq);
 
-	return ret;
+	return len;
 }
 
 static struct logger_log *get_log_from_minor(int minor)
@@ -736,7 +685,7 @@ static long logger_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 static const struct file_operations logger_fops = {
 	.owner = THIS_MODULE,
 	.read = logger_read,
-	.aio_write = logger_aio_write,
+	.write_iter = logger_write_iter,
 	.poll = logger_poll,
 	.unlocked_ioctl = logger_ioctl,
 	.compat_ioctl = logger_ioctl,
diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c
index b18847827759..9cb222e2996f 100644
--- a/drivers/staging/imx-drm/imx-drm-core.c
+++ b/drivers/staging/imx-drm/imx-drm-core.c
@@ -531,6 +531,7 @@ static struct drm_driver imx_drm_driver = {
 	.unload			= imx_drm_driver_unload,
 	.lastclose		= imx_drm_driver_lastclose,
 	.preclose		= imx_drm_driver_preclose,
+	.set_busid		= drm_platform_set_busid,
 	.gem_free_object	= drm_gem_cma_free_object,
 	.gem_vm_ops		= &drm_gem_cma_vm_ops,
 	.dumb_create		= drm_gem_cma_dumb_create,
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
index 86f1a91e896f..14c9c8d18d02 100644
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
+++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
@@ -3215,7 +3215,6 @@ kiblnd_connd (void *arg)
 
 		schedule_timeout(timeout);
 
-		set_current_state(TASK_RUNNING);
 		remove_wait_queue(&kiblnd_data.kib_connd_waitq, &wait);
 		spin_lock_irqsave(&kiblnd_data.kib_connd_lock, flags);
 	}
@@ -3432,7 +3431,6 @@ kiblnd_scheduler(void *arg)
 		busy_loops = 0;
 
 		remove_wait_queue(&sched->ibs_waitq, &wait);
-		set_current_state(TASK_RUNNING);
 		spin_lock_irqsave(&sched->ibs_lock, flags);
 	}
 
@@ -3507,7 +3505,6 @@ kiblnd_failover_thread(void *arg)
 
 		rc = schedule_timeout(long_sleep ? cfs_time_seconds(10) :
 						   cfs_time_seconds(1));
-		set_current_state(TASK_RUNNING);
 		remove_wait_queue(&kiblnd_data.kib_failover_waitq, &wait);
 		write_lock_irqsave(glock, flags);
 
diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
index bcfee7c21942..d29f5f134b89 100644
--- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
+++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c
@@ -2232,7 +2232,6 @@ ksocknal_connd (void *arg)
 		nloops = 0;
 		schedule_timeout(timeout);
 
-		set_current_state(TASK_RUNNING);
 		remove_wait_queue(&ksocknal_data.ksnd_connd_waitq, &wait);
 		spin_lock_bh(connd_lock);
 	}
diff --git a/drivers/staging/lustre/lustre/libcfs/fail.c b/drivers/staging/lustre/lustre/libcfs/fail.c
index 1bf9c90b4789..e73ca3df9734 100644
--- a/drivers/staging/lustre/lustre/libcfs/fail.c
+++ b/drivers/staging/lustre/lustre/libcfs/fail.c
@@ -131,7 +131,6 @@ int __cfs_fail_timeout_set(__u32 id, __u32 value, int ms, int set)
 		       id, ms);
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		schedule_timeout(cfs_time_seconds(ms) / 1000);
-		set_current_state(TASK_RUNNING);
 		CERROR("cfs_fail_timeout id %x awake\n", id);
 	}
 	return ret;
diff --git a/drivers/staging/media/Kconfig b/drivers/staging/media/Kconfig
index 3323eb5e77b0..655cf5037b0b 100644
--- a/drivers/staging/media/Kconfig
+++ b/drivers/staging/media/Kconfig
@@ -19,8 +19,6 @@ menuconfig STAGING_MEDIA
 if STAGING_MEDIA
 
 # Please keep them in alphabetic order
-source "drivers/staging/media/as102/Kconfig"
-
 source "drivers/staging/media/bcm2048/Kconfig"
 
 source "drivers/staging/media/cxd2099/Kconfig"
diff --git a/drivers/staging/media/Makefile b/drivers/staging/media/Makefile
index 7db83f373f63..6dbe578178cd 100644
--- a/drivers/staging/media/Makefile
+++ b/drivers/staging/media/Makefile
@@ -1,4 +1,3 @@
-obj-$(CONFIG_DVB_AS102)		+= as102/
 obj-$(CONFIG_I2C_BCM2048)	+= bcm2048/
 obj-$(CONFIG_DVB_CXD2099)	+= cxd2099/
 obj-$(CONFIG_LIRC_STAGING)	+= lirc/
diff --git a/drivers/staging/media/as102/as102_fe.c b/drivers/staging/media/as102/as102_fe.c
deleted file mode 100644
index b686b7617cdc..000000000000
--- a/drivers/staging/media/as102/as102_fe.c
+++ /dev/null
@@ -1,571 +0,0 @@
-/*
- * Abilis Systems Single DVB-T Receiver
- * Copyright (C) 2008 Pierrick Hascoet <pierrick.hascoet@abilis.com>
- * Copyright (C) 2010 Devin Heitmueller <dheitmueller@kernellabs.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-#include "as102_drv.h"
-#include "as10x_types.h"
-#include "as10x_cmd.h"
-
-static void as10x_fe_copy_tps_parameters(struct dtv_frontend_properties *dst,
-					 struct as10x_tps *src);
-
-static void as102_fe_copy_tune_parameters(struct as10x_tune_args *dst,
-					  struct dtv_frontend_properties *src);
-
-static int as102_fe_set_frontend(struct dvb_frontend *fe)
-{
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-	int ret = 0;
-	struct as102_dev_t *dev;
-	struct as10x_tune_args tune_args = { 0 };
-
-	dev = (struct as102_dev_t *) fe->tuner_priv;
-	if (dev == NULL)
-		return -ENODEV;
-
-	if (mutex_lock_interruptible(&dev->bus_adap.lock))
-		return -EBUSY;
-
-	as102_fe_copy_tune_parameters(&tune_args, p);
-
-	/* send abilis command: SET_TUNE */
-	ret =  as10x_cmd_set_tune(&dev->bus_adap, &tune_args);
-	if (ret != 0)
-		dprintk(debug, "as10x_cmd_set_tune failed. (err = %d)\n", ret);
-
-	mutex_unlock(&dev->bus_adap.lock);
-
-	return (ret < 0) ? -EINVAL : 0;
-}
-
-static int as102_fe_get_frontend(struct dvb_frontend *fe)
-{
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-	int ret = 0;
-	struct as102_dev_t *dev;
-	struct as10x_tps tps = { 0 };
-
-	dev = (struct as102_dev_t *) fe->tuner_priv;
-	if (dev == NULL)
-		return -EINVAL;
-
-	if (mutex_lock_interruptible(&dev->bus_adap.lock))
-		return -EBUSY;
-
-	/* send abilis command: GET_TPS */
-	ret = as10x_cmd_get_tps(&dev->bus_adap, &tps);
-
-	if (ret == 0)
-		as10x_fe_copy_tps_parameters(p, &tps);
-
-	mutex_unlock(&dev->bus_adap.lock);
-
-	return (ret < 0) ? -EINVAL : 0;
-}
-
-static int as102_fe_get_tune_settings(struct dvb_frontend *fe,
-			struct dvb_frontend_tune_settings *settings) {
-
-#if 0
-	dprintk(debug, "step_size    = %d\n", settings->step_size);
-	dprintk(debug, "max_drift    = %d\n", settings->max_drift);
-	dprintk(debug, "min_delay_ms = %d -> %d\n", settings->min_delay_ms,
-		1000);
-#endif
-
-	settings->min_delay_ms = 1000;
-
-	return 0;
-}
-
-
-static int as102_fe_read_status(struct dvb_frontend *fe, fe_status_t *status)
-{
-	int ret = 0;
-	struct as102_dev_t *dev;
-	struct as10x_tune_status tstate = { 0 };
-
-	dev = (struct as102_dev_t *) fe->tuner_priv;
-	if (dev == NULL)
-		return -ENODEV;
-
-	if (mutex_lock_interruptible(&dev->bus_adap.lock))
-		return -EBUSY;
-
-	/* send abilis command: GET_TUNE_STATUS */
-	ret = as10x_cmd_get_tune_status(&dev->bus_adap, &tstate);
-	if (ret < 0) {
-		dprintk(debug, "as10x_cmd_get_tune_status failed (err = %d)\n",
-			ret);
-		goto out;
-	}
-
-	dev->signal_strength  = tstate.signal_strength;
-	dev->ber  = tstate.BER;
-
-	switch (tstate.tune_state) {
-	case TUNE_STATUS_SIGNAL_DVB_OK:
-		*status = FE_HAS_SIGNAL | FE_HAS_CARRIER;
-		break;
-	case TUNE_STATUS_STREAM_DETECTED:
-		*status = FE_HAS_SIGNAL | FE_HAS_CARRIER | FE_HAS_SYNC;
-		break;
-	case TUNE_STATUS_STREAM_TUNED:
-		*status = FE_HAS_SIGNAL | FE_HAS_CARRIER | FE_HAS_SYNC |
-			FE_HAS_LOCK;
-		break;
-	default:
-		*status = TUNE_STATUS_NOT_TUNED;
-	}
-
-	dprintk(debug, "tuner status: 0x%02x, strength %d, per: %d, ber: %d\n",
-			tstate.tune_state, tstate.signal_strength,
-			tstate.PER, tstate.BER);
-
-	if (*status & FE_HAS_LOCK) {
-		if (as10x_cmd_get_demod_stats(&dev->bus_adap,
-			(struct as10x_demod_stats *) &dev->demod_stats) < 0) {
-			memset(&dev->demod_stats, 0, sizeof(dev->demod_stats));
-			dprintk(debug,
-				"as10x_cmd_get_demod_stats failed (probably not tuned)\n");
-		} else {
-			dprintk(debug,
-				"demod status: fc: 0x%08x, bad fc: 0x%08x, "
-				"bytes corrected: 0x%08x , MER: 0x%04x\n",
-				dev->demod_stats.frame_count,
-				dev->demod_stats.bad_frame_count,
-				dev->demod_stats.bytes_fixed_by_rs,
-				dev->demod_stats.mer);
-		}
-	} else {
-		memset(&dev->demod_stats, 0, sizeof(dev->demod_stats));
-	}
-
-out:
-	mutex_unlock(&dev->bus_adap.lock);
-	return ret;
-}
-
-/*
- * Note:
- * - in AS102 SNR=MER
- *   - the SNR will be returned in linear terms, i.e. not in dB
- *   - the accuracy equals ±2dB for a SNR range from 4dB to 30dB
- *   - the accuracy is >2dB for SNR values outside this range
- */
-static int as102_fe_read_snr(struct dvb_frontend *fe, u16 *snr)
-{
-	struct as102_dev_t *dev;
-
-	dev = (struct as102_dev_t *) fe->tuner_priv;
-	if (dev == NULL)
-		return -ENODEV;
-
-	*snr = dev->demod_stats.mer;
-
-	return 0;
-}
-
-static int as102_fe_read_ber(struct dvb_frontend *fe, u32 *ber)
-{
-	struct as102_dev_t *dev;
-
-	dev = (struct as102_dev_t *) fe->tuner_priv;
-	if (dev == NULL)
-		return -ENODEV;
-
-	*ber = dev->ber;
-
-	return 0;
-}
-
-static int as102_fe_read_signal_strength(struct dvb_frontend *fe,
-					 u16 *strength)
-{
-	struct as102_dev_t *dev;
-
-	dev = (struct as102_dev_t *) fe->tuner_priv;
-	if (dev == NULL)
-		return -ENODEV;
-
-	*strength = (((0xffff * 400) * dev->signal_strength + 41000) * 2);
-
-	return 0;
-}
-
-static int as102_fe_read_ucblocks(struct dvb_frontend *fe, u32 *ucblocks)
-{
-	struct as102_dev_t *dev;
-
-	dev = (struct as102_dev_t *) fe->tuner_priv;
-	if (dev == NULL)
-		return -ENODEV;
-
-	if (dev->demod_stats.has_started)
-		*ucblocks = dev->demod_stats.bad_frame_count;
-	else
-		*ucblocks = 0;
-
-	return 0;
-}
-
-static int as102_fe_ts_bus_ctrl(struct dvb_frontend *fe, int acquire)
-{
-	struct as102_dev_t *dev;
-	int ret;
-
-	dev = (struct as102_dev_t *) fe->tuner_priv;
-	if (dev == NULL)
-		return -ENODEV;
-
-	if (mutex_lock_interruptible(&dev->bus_adap.lock))
-		return -EBUSY;
-
-	if (acquire) {
-		if (elna_enable)
-			as10x_cmd_set_context(&dev->bus_adap,
-					      CONTEXT_LNA, dev->elna_cfg);
-
-		ret = as10x_cmd_turn_on(&dev->bus_adap);
-	} else {
-		ret = as10x_cmd_turn_off(&dev->bus_adap);
-	}
-
-	mutex_unlock(&dev->bus_adap.lock);
-
-	return ret;
-}
-
-static struct dvb_frontend_ops as102_fe_ops = {
-	.delsys = { SYS_DVBT },
-	.info = {
-		.name			= "Unknown AS102 device",
-		.frequency_min		= 174000000,
-		.frequency_max		= 862000000,
-		.frequency_stepsize	= 166667,
-		.caps = FE_CAN_INVERSION_AUTO
-			| FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4
-			| FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO
-			| FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QPSK
-			| FE_CAN_QAM_AUTO
-			| FE_CAN_TRANSMISSION_MODE_AUTO
-			| FE_CAN_GUARD_INTERVAL_AUTO
-			| FE_CAN_HIERARCHY_AUTO
-			| FE_CAN_RECOVER
-			| FE_CAN_MUTE_TS
-	},
-
-	.set_frontend		= as102_fe_set_frontend,
-	.get_frontend		= as102_fe_get_frontend,
-	.get_tune_settings	= as102_fe_get_tune_settings,
-
-	.read_status		= as102_fe_read_status,
-	.read_snr		= as102_fe_read_snr,
-	.read_ber		= as102_fe_read_ber,
-	.read_signal_strength	= as102_fe_read_signal_strength,
-	.read_ucblocks		= as102_fe_read_ucblocks,
-	.ts_bus_ctrl		= as102_fe_ts_bus_ctrl,
-};
-
-int as102_dvb_unregister_fe(struct dvb_frontend *fe)
-{
-	/* unregister frontend */
-	dvb_unregister_frontend(fe);
-
-	/* detach frontend */
-	dvb_frontend_detach(fe);
-
-	return 0;
-}
-
-int as102_dvb_register_fe(struct as102_dev_t *as102_dev,
-			  struct dvb_frontend *dvb_fe)
-{
-	int errno;
-	struct dvb_adapter *dvb_adap;
-
-	if (as102_dev == NULL)
-		return -EINVAL;
-
-	/* extract dvb_adapter */
-	dvb_adap = &as102_dev->dvb_adap;
-
-	/* init frontend callback ops */
-	memcpy(&dvb_fe->ops, &as102_fe_ops, sizeof(struct dvb_frontend_ops));
-	strncpy(dvb_fe->ops.info.name, as102_dev->name,
-		sizeof(dvb_fe->ops.info.name));
-
-	/* register dvb frontend */
-	errno = dvb_register_frontend(dvb_adap, dvb_fe);
-	if (errno == 0)
-		dvb_fe->tuner_priv = as102_dev;
-
-	return errno;
-}
-
-static void as10x_fe_copy_tps_parameters(struct dtv_frontend_properties *fe_tps,
-					 struct as10x_tps *as10x_tps)
-{
-
-	/* extract constellation */
-	switch (as10x_tps->modulation) {
-	case CONST_QPSK:
-		fe_tps->modulation = QPSK;
-		break;
-	case CONST_QAM16:
-		fe_tps->modulation = QAM_16;
-		break;
-	case CONST_QAM64:
-		fe_tps->modulation = QAM_64;
-		break;
-	}
-
-	/* extract hierarchy */
-	switch (as10x_tps->hierarchy) {
-	case HIER_NONE:
-		fe_tps->hierarchy = HIERARCHY_NONE;
-		break;
-	case HIER_ALPHA_1:
-		fe_tps->hierarchy = HIERARCHY_1;
-		break;
-	case HIER_ALPHA_2:
-		fe_tps->hierarchy = HIERARCHY_2;
-		break;
-	case HIER_ALPHA_4:
-		fe_tps->hierarchy = HIERARCHY_4;
-		break;
-	}
-
-	/* extract code rate HP */
-	switch (as10x_tps->code_rate_HP) {
-	case CODE_RATE_1_2:
-		fe_tps->code_rate_HP = FEC_1_2;
-		break;
-	case CODE_RATE_2_3:
-		fe_tps->code_rate_HP = FEC_2_3;
-		break;
-	case CODE_RATE_3_4:
-		fe_tps->code_rate_HP = FEC_3_4;
-		break;
-	case CODE_RATE_5_6:
-		fe_tps->code_rate_HP = FEC_5_6;
-		break;
-	case CODE_RATE_7_8:
-		fe_tps->code_rate_HP = FEC_7_8;
-		break;
-	}
-
-	/* extract code rate LP */
-	switch (as10x_tps->code_rate_LP) {
-	case CODE_RATE_1_2:
-		fe_tps->code_rate_LP = FEC_1_2;
-		break;
-	case CODE_RATE_2_3:
-		fe_tps->code_rate_LP = FEC_2_3;
-		break;
-	case CODE_RATE_3_4:
-		fe_tps->code_rate_LP = FEC_3_4;
-		break;
-	case CODE_RATE_5_6:
-		fe_tps->code_rate_LP = FEC_5_6;
-		break;
-	case CODE_RATE_7_8:
-		fe_tps->code_rate_LP = FEC_7_8;
-		break;
-	}
-
-	/* extract guard interval */
-	switch (as10x_tps->guard_interval) {
-	case GUARD_INT_1_32:
-		fe_tps->guard_interval = GUARD_INTERVAL_1_32;
-		break;
-	case GUARD_INT_1_16:
-		fe_tps->guard_interval = GUARD_INTERVAL_1_16;
-		break;
-	case GUARD_INT_1_8:
-		fe_tps->guard_interval = GUARD_INTERVAL_1_8;
-		break;
-	case GUARD_INT_1_4:
-		fe_tps->guard_interval = GUARD_INTERVAL_1_4;
-		break;
-	}
-
-	/* extract transmission mode */
-	switch (as10x_tps->transmission_mode) {
-	case TRANS_MODE_2K:
-		fe_tps->transmission_mode = TRANSMISSION_MODE_2K;
-		break;
-	case TRANS_MODE_8K:
-		fe_tps->transmission_mode = TRANSMISSION_MODE_8K;
-		break;
-	}
-}
-
-static uint8_t as102_fe_get_code_rate(fe_code_rate_t arg)
-{
-	uint8_t c;
-
-	switch (arg) {
-	case FEC_1_2:
-		c = CODE_RATE_1_2;
-		break;
-	case FEC_2_3:
-		c = CODE_RATE_2_3;
-		break;
-	case FEC_3_4:
-		c = CODE_RATE_3_4;
-		break;
-	case FEC_5_6:
-		c = CODE_RATE_5_6;
-		break;
-	case FEC_7_8:
-		c = CODE_RATE_7_8;
-		break;
-	default:
-		c = CODE_RATE_UNKNOWN;
-		break;
-	}
-
-	return c;
-}
-
-static void as102_fe_copy_tune_parameters(struct as10x_tune_args *tune_args,
-			  struct dtv_frontend_properties *params)
-{
-
-	/* set frequency */
-	tune_args->freq = params->frequency / 1000;
-
-	/* fix interleaving_mode */
-	tune_args->interleaving_mode = INTLV_NATIVE;
-
-	switch (params->bandwidth_hz) {
-	case 8000000:
-		tune_args->bandwidth = BW_8_MHZ;
-		break;
-	case 7000000:
-		tune_args->bandwidth = BW_7_MHZ;
-		break;
-	case 6000000:
-		tune_args->bandwidth = BW_6_MHZ;
-		break;
-	default:
-		tune_args->bandwidth = BW_8_MHZ;
-	}
-
-	switch (params->guard_interval) {
-	case GUARD_INTERVAL_1_32:
-		tune_args->guard_interval = GUARD_INT_1_32;
-		break;
-	case GUARD_INTERVAL_1_16:
-		tune_args->guard_interval = GUARD_INT_1_16;
-		break;
-	case GUARD_INTERVAL_1_8:
-		tune_args->guard_interval = GUARD_INT_1_8;
-		break;
-	case GUARD_INTERVAL_1_4:
-		tune_args->guard_interval = GUARD_INT_1_4;
-		break;
-	case GUARD_INTERVAL_AUTO:
-	default:
-		tune_args->guard_interval = GUARD_UNKNOWN;
-		break;
-	}
-
-	switch (params->modulation) {
-	case QPSK:
-		tune_args->modulation = CONST_QPSK;
-		break;
-	case QAM_16:
-		tune_args->modulation = CONST_QAM16;
-		break;
-	case QAM_64:
-		tune_args->modulation = CONST_QAM64;
-		break;
-	default:
-		tune_args->modulation = CONST_UNKNOWN;
-		break;
-	}
-
-	switch (params->transmission_mode) {
-	case TRANSMISSION_MODE_2K:
-		tune_args->transmission_mode = TRANS_MODE_2K;
-		break;
-	case TRANSMISSION_MODE_8K:
-		tune_args->transmission_mode = TRANS_MODE_8K;
-		break;
-	default:
-		tune_args->transmission_mode = TRANS_MODE_UNKNOWN;
-	}
-
-	switch (params->hierarchy) {
-	case HIERARCHY_NONE:
-		tune_args->hierarchy = HIER_NONE;
-		break;
-	case HIERARCHY_1:
-		tune_args->hierarchy = HIER_ALPHA_1;
-		break;
-	case HIERARCHY_2:
-		tune_args->hierarchy = HIER_ALPHA_2;
-		break;
-	case HIERARCHY_4:
-		tune_args->hierarchy = HIER_ALPHA_4;
-		break;
-	case HIERARCHY_AUTO:
-		tune_args->hierarchy = HIER_UNKNOWN;
-		break;
-	}
-
-	dprintk(debug, "tuner parameters: freq: %d  bw: 0x%02x  gi: 0x%02x\n",
-			params->frequency,
-			tune_args->bandwidth,
-			tune_args->guard_interval);
-
-	/*
-	 * Detect a hierarchy selection
-	 * if HP/LP are both set to FEC_NONE, HP will be selected.
-	 */
-	if ((tune_args->hierarchy != HIER_NONE) &&
-		       ((params->code_rate_LP == FEC_NONE) ||
-			(params->code_rate_HP == FEC_NONE))) {
-
-		if (params->code_rate_LP == FEC_NONE) {
-			tune_args->hier_select = HIER_HIGH_PRIORITY;
-			tune_args->code_rate =
-			   as102_fe_get_code_rate(params->code_rate_HP);
-		}
-
-		if (params->code_rate_HP == FEC_NONE) {
-			tune_args->hier_select = HIER_LOW_PRIORITY;
-			tune_args->code_rate =
-			   as102_fe_get_code_rate(params->code_rate_LP);
-		}
-
-		dprintk(debug,
-			"\thierarchy: 0x%02x  selected: %s  code_rate_%s: 0x%02x\n",
-			tune_args->hierarchy,
-			tune_args->hier_select == HIER_HIGH_PRIORITY ?
-			"HP" : "LP",
-			tune_args->hier_select == HIER_HIGH_PRIORITY ?
-			"HP" : "LP",
-			tune_args->code_rate);
-	} else {
-		tune_args->code_rate =
-			as102_fe_get_code_rate(params->code_rate_HP);
-	}
-}
diff --git a/drivers/staging/media/davinci_vpfe/Kconfig b/drivers/staging/media/davinci_vpfe/Kconfig
index 12f321dd2399..4de2f082491d 100644
--- a/drivers/staging/media/davinci_vpfe/Kconfig
+++ b/drivers/staging/media/davinci_vpfe/Kconfig
@@ -1,6 +1,7 @@
 config VIDEO_DM365_VPFE
 	tristate "DM365 VPFE Media Controller Capture Driver"
 	depends on VIDEO_V4L2 && ARCH_DAVINCI_DM365 && !VIDEO_DM365_ISIF
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	help
 	  Support for DM365 VPFE based Media Controller Capture driver.
diff --git a/drivers/staging/media/dt3155v4l/Kconfig b/drivers/staging/media/dt3155v4l/Kconfig
index 226a1ca90b3c..2d496001b6e8 100644
--- a/drivers/staging/media/dt3155v4l/Kconfig
+++ b/drivers/staging/media/dt3155v4l/Kconfig
@@ -1,6 +1,7 @@
 config VIDEO_DT3155
 	tristate "DT3155 frame grabber, Video4Linux interface"
 	depends on PCI && VIDEO_DEV && VIDEO_V4L2
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	default n
 	---help---
diff --git a/drivers/staging/media/lirc/lirc_imon.c b/drivers/staging/media/lirc/lirc_imon.c
index 726cc3a31856..7aca44f28c5a 100644
--- a/drivers/staging/media/lirc/lirc_imon.c
+++ b/drivers/staging/media/lirc/lirc_imon.c
@@ -414,6 +414,7 @@ static ssize_t vfd_write(struct file *file, const char __user *buf,
 	data_buf = memdup_user(buf, n_bytes);
 	if (IS_ERR(data_buf)) {
 		retval = PTR_ERR(data_buf);
+		data_buf = NULL;
 		goto exit;
 	}
 
diff --git a/drivers/staging/media/lirc/lirc_sasem.c b/drivers/staging/media/lirc/lirc_sasem.c
index 86ad811fda24..c20ef56202bf 100644
--- a/drivers/staging/media/lirc/lirc_sasem.c
+++ b/drivers/staging/media/lirc/lirc_sasem.c
@@ -392,6 +392,7 @@ static ssize_t vfd_write(struct file *file, const char __user *buf,
 	data_buf = memdup_user((void const __user *)buf, n_bytes);
 	if (IS_ERR(data_buf)) {
 		retval = PTR_ERR(data_buf);
+		data_buf = NULL;
 		goto exit;
 	}
 
diff --git a/drivers/staging/media/omap4iss/Kconfig b/drivers/staging/media/omap4iss/Kconfig
index 8afc6fee40c5..b78643f907e7 100644
--- a/drivers/staging/media/omap4iss/Kconfig
+++ b/drivers/staging/media/omap4iss/Kconfig
@@ -1,6 +1,7 @@
 config VIDEO_OMAP4
 	bool "OMAP 4 Camera support"
 	depends on VIDEO_V4L2=y && VIDEO_V4L2_SUBDEV_API && I2C=y && ARCH_OMAP4
+	depends on HAS_DMA
 	select VIDEOBUF2_DMA_CONTIG
 	---help---
 	  Driver for an OMAP 4 ISS controller.
diff --git a/drivers/staging/rtl8188eu/os_dep/rtw_android.c b/drivers/staging/rtl8188eu/os_dep/rtw_android.c
index 1718229f6278..d9d55d12fd5f 100644
--- a/drivers/staging/rtl8188eu/os_dep/rtw_android.c
+++ b/drivers/staging/rtl8188eu/os_dep/rtw_android.c
@@ -79,7 +79,7 @@ int rtw_android_cmdstr_to_num(char *cmdstr)
 {
 	int cmd_num;
 	for (cmd_num = 0; cmd_num < ANDROID_WIFI_CMD_MAX; cmd_num++)
-		if (0 == strnicmp(cmdstr , android_wifi_cmd_str[cmd_num],
+		if (0 == strncasecmp(cmdstr , android_wifi_cmd_str[cmd_num],
 				  strlen(android_wifi_cmd_str[cmd_num])))
 			break;
 	return cmd_num;
diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h
index 91d35df286c3..2d82f8993ea1 100644
--- a/drivers/staging/rtl8192e/rtllib.h
+++ b/drivers/staging/rtl8192e/rtllib.h
@@ -2957,25 +2957,13 @@ extern inline int rtllib_get_scans(struct rtllib_device *ieee)
 static inline const char *escape_essid(const char *essid, u8 essid_len)
 {
 	static char escaped[IW_ESSID_MAX_SIZE * 2 + 1];
-	const char *s = essid;
-	char *d = escaped;
 
 	if (rtllib_is_empty_essid(essid, essid_len)) {
 		memcpy(escaped, "<hidden>", sizeof("<hidden>"));
 		return escaped;
 	}
 
-	essid_len = min(essid_len, (u8)IW_ESSID_MAX_SIZE);
-	while (essid_len--) {
-		if (*s == '\0') {
-			*d++ = '\\';
-			*d++ = '0';
-			s++;
-		} else {
-			*d++ = *s++;
-		}
-	}
-	*d = '\0';
+	snprintf(escaped, sizeof(escaped), "%*pEn", essid_len, essid);
 	return escaped;
 }
 
diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211.h b/drivers/staging/rtl8192u/ieee80211/ieee80211.h
index 9ecfa4a2421d..b44aa17d30a7 100644
--- a/drivers/staging/rtl8192u/ieee80211/ieee80211.h
+++ b/drivers/staging/rtl8192u/ieee80211/ieee80211.h
@@ -2593,25 +2593,13 @@ static inline int ieee80211_get_scans(struct ieee80211_device *ieee)
 
 static inline const char *escape_essid(const char *essid, u8 essid_len) {
 	static char escaped[IW_ESSID_MAX_SIZE * 2 + 1];
-	const char *s = essid;
-	char *d = escaped;
 
 	if (ieee80211_is_empty_essid(essid, essid_len)) {
 		memcpy(escaped, "<hidden>", sizeof("<hidden>"));
 		return escaped;
 	}
 
-	essid_len = min(essid_len, (u8)IW_ESSID_MAX_SIZE);
-	while (essid_len--) {
-		if (*s == '\0') {
-			*d++ = '\\';
-			*d++ = '0';
-			s++;
-		} else {
-			*d++ = *s++;
-		}
-	}
-	*d = '\0';
+	snprintf(escaped, sizeof(escaped), "%*pEn", essid_len, essid);
 	return escaped;
 }
 
diff --git a/drivers/staging/vme/devices/vme_pio2_gpio.c b/drivers/staging/vme/devices/vme_pio2_gpio.c
index d8a118d39566..c64776f71809 100644
--- a/drivers/staging/vme/devices/vme_pio2_gpio.c
+++ b/drivers/staging/vme/devices/vme_pio2_gpio.c
@@ -221,9 +221,7 @@ void pio2_gpio_exit(struct pio2_card *card)
 {
 	const char *label = card->gc.label;
 
-	if (gpiochip_remove(&(card->gc)))
-		dev_err(&card->vdev->dev, "Failed to remove GPIO\n");
-
+	gpiochip_remove(&(card->gc));
 	kfree(label);
 }
 
diff --git a/drivers/staging/vme/devices/vme_user.c b/drivers/staging/vme/devices/vme_user.c
index 73cec14cbf56..8b1f53331433 100644
--- a/drivers/staging/vme/devices/vme_user.c
+++ b/drivers/staging/vme/devices/vme_user.c
@@ -410,41 +410,19 @@ static ssize_t vme_user_write(struct file *file, const char __user *buf,
 
 static loff_t vme_user_llseek(struct file *file, loff_t off, int whence)
 {
-	loff_t absolute = -1;
 	unsigned int minor = MINOR(file_inode(file)->i_rdev);
 	size_t image_size;
+	loff_t res;
 
 	if (minor == CONTROL_MINOR)
 		return -EINVAL;
 
 	mutex_lock(&image[minor].mutex);
 	image_size = vme_get_size(image[minor].resource);
-
-	switch (whence) {
-	case SEEK_SET:
-		absolute = off;
-		break;
-	case SEEK_CUR:
-		absolute = file->f_pos + off;
-		break;
-	case SEEK_END:
-		absolute = image_size + off;
-		break;
-	default:
-		mutex_unlock(&image[minor].mutex);
-		return -EINVAL;
-	}
-
-	if ((absolute < 0) || (absolute >= image_size)) {
-		mutex_unlock(&image[minor].mutex);
-		return -EINVAL;
-	}
-
-	file->f_pos = absolute;
-
+	res = fixed_size_llseek(file, off, whence, image_size);
 	mutex_unlock(&image[minor].mutex);
 
-	return absolute;
+	return res;
 }
 
 /*
diff --git a/drivers/staging/wlan-ng/prism2sta.c b/drivers/staging/wlan-ng/prism2sta.c
index 799ce8aa70ef..df577dfe7ffb 100644
--- a/drivers/staging/wlan-ng/prism2sta.c
+++ b/drivers/staging/wlan-ng/prism2sta.c
@@ -60,7 +60,6 @@
 #include <linux/netdevice.h>
 #include <linux/workqueue.h>
 #include <linux/byteorder/generic.h>
-#include <linux/ctype.h>
 
 #include <linux/io.h>
 #include <linux/delay.h>
@@ -81,27 +80,6 @@
 #include "hfa384x.h"
 #include "prism2mgmt.h"
 
-/* Create a string of printable chars from something that might not be */
-/* It's recommended that the str be 4*len + 1 bytes long */
-#define wlan_mkprintstr(buf, buflen, str, strlen) \
-{ \
-	int i = 0; \
-	int j = 0; \
-	memset(str, 0, (strlen)); \
-	for (i = 0; i < (buflen); i++) { \
-		if (isprint((buf)[i])) { \
-			(str)[j] = (buf)[i]; \
-			j++; \
-		} else { \
-			(str)[j] = '\\'; \
-			(str)[j+1] = 'x'; \
-			(str)[j+2] = hex_asc_hi((buf)[i]); \
-			(str)[j+3] = hex_asc_lo((buf)[i]); \
-			j += 4; \
-		} \
-	} \
-}
-
 static char *dev_info = "prism2_usb";
 static wlandevice_t *create_wlan(void);
 
@@ -607,7 +585,6 @@ static int prism2sta_getcardinfo(wlandevice_t *wlandev)
 	hfa384x_t *hw = (hfa384x_t *) wlandev->priv;
 	u16 temp;
 	u8 snum[HFA384x_RID_NICSERIALNUMBER_LEN];
-	char pstr[(HFA384x_RID_NICSERIALNUMBER_LEN * 4) + 1];
 
 	/* Collect version and compatibility info */
 	/*  Some are critical, some are not */
@@ -862,9 +839,8 @@ static int prism2sta_getcardinfo(wlandevice_t *wlandev)
 	result = hfa384x_drvr_getconfig(hw, HFA384x_RID_NICSERIALNUMBER,
 					snum, HFA384x_RID_NICSERIALNUMBER_LEN);
 	if (!result) {
-		wlan_mkprintstr(snum, HFA384x_RID_NICSERIALNUMBER_LEN,
-				pstr, sizeof(pstr));
-		netdev_info(wlandev->netdev, "Prism2 card SN: %s\n", pstr);
+		netdev_info(wlandev->netdev, "Prism2 card SN: %*pEhp\n",
+			    HFA384x_RID_NICSERIALNUMBER_LEN, snum);
 	} else {
 		netdev_err(wlandev->netdev, "Failed to retrieve Prism2 Card SN\n");
 		goto failed;
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 943b1dbe859a..70d9f6dabba0 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -1050,7 +1050,7 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 		req = blk_get_request(pdv->pdv_sd->request_queue,
 				(data_direction == DMA_TO_DEVICE),
 				GFP_KERNEL);
-		if (!req) {
+		if (IS_ERR(req)) {
 			pr_err("PSCSI: blk_get_request() failed\n");
 			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 			goto fail;
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index fddfae61222f..be783f717f19 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -819,7 +819,8 @@ int core_tpg_add_lun(
 {
 	int ret;
 
-	ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release);
+	ret = percpu_ref_init(&lun->lun_ref, core_tpg_lun_ref_release, 0,
+			      GFP_KERNEL);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 71b0ec0c370d..1e23f4f8d2c2 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -66,7 +66,7 @@ static struct thermal_governor *__find_governor(const char *name)
 		return def_governor;
 
 	list_for_each_entry(pos, &thermal_governor_list, governor_list)
-		if (!strnicmp(name, pos->name, THERMAL_NAME_LENGTH))
+		if (!strncasecmp(name, pos->name, THERMAL_NAME_LENGTH))
 			return pos;
 
 	return NULL;
@@ -104,7 +104,7 @@ int thermal_register_governor(struct thermal_governor *governor)
 
 		name = pos->tzp->governor_name;
 
-		if (!strnicmp(name, governor->name, THERMAL_NAME_LENGTH))
+		if (!strncasecmp(name, governor->name, THERMAL_NAME_LENGTH))
 			pos->governor = governor;
 	}
 
@@ -129,7 +129,7 @@ void thermal_unregister_governor(struct thermal_governor *governor)
 	mutex_lock(&thermal_list_lock);
 
 	list_for_each_entry(pos, &thermal_tz_list, node) {
-		if (!strnicmp(pos->governor->name, governor->name,
+		if (!strncasecmp(pos->governor->name, governor->name,
 						THERMAL_NAME_LENGTH))
 			pos->governor = NULL;
 	}
@@ -1665,7 +1665,7 @@ struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name)
 
 	mutex_lock(&thermal_list_lock);
 	list_for_each_entry(pos, &thermal_tz_list, node)
-		if (!strnicmp(name, pos->type, THERMAL_NAME_LENGTH)) {
+		if (!strncasecmp(name, pos->type, THERMAL_NAME_LENGTH)) {
 			found++;
 			ref = pos;
 		}
diff --git a/drivers/tty/bfin_jtag_comm.c b/drivers/tty/bfin_jtag_comm.c
index 8096fcbe2dc1..d7b198c400c7 100644
--- a/drivers/tty/bfin_jtag_comm.c
+++ b/drivers/tty/bfin_jtag_comm.c
@@ -77,7 +77,6 @@ bfin_jc_emudat_manager(void *arg)
 			pr_debug("waiting for readers\n");
 			__set_current_state(TASK_UNINTERRUPTIBLE);
 			schedule();
-			__set_current_state(TASK_RUNNING);
 			continue;
 		}
 
diff --git a/drivers/tty/hvc/hvc_vio.c b/drivers/tty/hvc/hvc_vio.c
index 5618b5fc7500..f575a9b5ede7 100644
--- a/drivers/tty/hvc/hvc_vio.c
+++ b/drivers/tty/hvc/hvc_vio.c
@@ -452,7 +452,7 @@ void __init hvc_vio_init_early(void)
 		return;
 #endif
 	/* Check whether the user has requested a different console. */
-	if (!strstr(cmd_line, "console="))
+	if (!strstr(boot_command_line, "console="))
 		add_preferred_console("hvc", 0, NULL);
 	hvc_instantiate(0, 0, ops);
 }
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 2967f0388d2c..f1e57425e39f 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -347,8 +347,6 @@ static int xen_console_remove(struct xencons_info *info)
 }
 
 #ifdef CONFIG_HVC_XEN_FRONTEND
-static struct xenbus_driver xencons_driver;
-
 static int xencons_remove(struct xenbus_device *dev)
 {
 	return xen_console_remove(dev_get_drvdata(&dev->dev));
@@ -499,13 +497,14 @@ static const struct xenbus_device_id xencons_ids[] = {
 	{ "" }
 };
 
-
-static DEFINE_XENBUS_DRIVER(xencons, "xenconsole",
+static struct xenbus_driver xencons_driver = {
+	.name = "xenconsole",
+	.ids = xencons_ids,
 	.probe = xencons_probe,
 	.remove = xencons_remove,
 	.resume = xencons_resume,
 	.otherend_changed = xencons_backend_changed,
-);
+};
 #endif /* CONFIG_HVC_XEN_FRONTEND */
 
 static int __init xen_hvc_init(void)
diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h
index 1bcb4b2141a6..cb51be55989e 100644
--- a/drivers/tty/serial/8250/8250.h
+++ b/drivers/tty/serial/8250/8250.h
@@ -16,13 +16,13 @@
 #include <linux/dmaengine.h>
 
 struct uart_8250_dma {
+	/* Filter function */
 	dma_filter_fn		fn;
+
+	/* Parameter to the filter function */
 	void			*rx_param;
 	void			*tx_param;
 
-	int			rx_chan_id;
-	int			tx_chan_id;
-
 	struct dma_slave_config	rxconf;
 	struct dma_slave_config	txconf;
 
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 57d9df84ce5d..beea6ca73ee5 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -216,10 +216,7 @@ out:
 
 static bool dw8250_dma_filter(struct dma_chan *chan, void *param)
 {
-	struct dw8250_data *data = param;
-
-	return chan->chan_id == data->dma.tx_chan_id ||
-	       chan->chan_id == data->dma.rx_chan_id;
+	return false;
 }
 
 static void dw8250_setup_port(struct uart_8250_port *up)
@@ -399,8 +396,6 @@ static int dw8250_probe(struct platform_device *pdev)
 	if (!IS_ERR(data->rst))
 		reset_control_deassert(data->rst);
 
-	data->dma.rx_chan_id = -1;
-	data->dma.tx_chan_id = -1;
 	data->dma.rx_param = data;
 	data->dma.tx_param = data;
 	data->dma.fn = dw8250_dma_filter;
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 4f1cd296f1b1..beb9d71cd47a 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -25,6 +25,9 @@
 #include <asm/byteorder.h>
 #include <asm/io.h>
 
+#include <linux/dmaengine.h>
+#include <linux/platform_data/dma-dw.h>
+
 #include "8250.h"
 
 /*
@@ -1349,6 +1352,9 @@ ce4100_serial_setup(struct serial_private *priv,
 #define PCI_DEVICE_ID_INTEL_BYT_UART1	0x0f0a
 #define PCI_DEVICE_ID_INTEL_BYT_UART2	0x0f0c
 
+#define PCI_DEVICE_ID_INTEL_BSW_UART1	0x228a
+#define PCI_DEVICE_ID_INTEL_BSW_UART2	0x228c
+
 #define BYT_PRV_CLK			0x800
 #define BYT_PRV_CLK_EN			(1 << 0)
 #define BYT_PRV_CLK_M_VAL_SHIFT		1
@@ -1414,7 +1420,13 @@ byt_set_termios(struct uart_port *p, struct ktermios *termios,
 
 static bool byt_dma_filter(struct dma_chan *chan, void *param)
 {
-	return chan->chan_id == *(int *)param;
+	struct dw_dma_slave *dws = param;
+
+	if (dws->dma_dev != chan->device->dev)
+		return false;
+
+	chan->private = dws;
+	return true;
 }
 
 static int
@@ -1422,35 +1434,57 @@ byt_serial_setup(struct serial_private *priv,
 		 const struct pciserial_board *board,
 		 struct uart_8250_port *port, int idx)
 {
+	struct pci_dev *pdev = priv->dev;
+	struct device *dev = port->port.dev;
 	struct uart_8250_dma *dma;
+	struct dw_dma_slave *tx_param, *rx_param;
+	struct pci_dev *dma_dev;
 	int ret;
 
-	dma = devm_kzalloc(port->port.dev, sizeof(*dma), GFP_KERNEL);
+	dma = devm_kzalloc(dev, sizeof(*dma), GFP_KERNEL);
 	if (!dma)
 		return -ENOMEM;
 
-	switch (priv->dev->device) {
+	tx_param = devm_kzalloc(dev, sizeof(*tx_param), GFP_KERNEL);
+	if (!tx_param)
+		return -ENOMEM;
+
+	rx_param = devm_kzalloc(dev, sizeof(*rx_param), GFP_KERNEL);
+	if (!rx_param)
+		return -ENOMEM;
+
+	switch (pdev->device) {
 	case PCI_DEVICE_ID_INTEL_BYT_UART1:
-		dma->rx_chan_id = 3;
-		dma->tx_chan_id = 2;
+	case PCI_DEVICE_ID_INTEL_BSW_UART1:
+		rx_param->src_id = 3;
+		tx_param->dst_id = 2;
 		break;
 	case PCI_DEVICE_ID_INTEL_BYT_UART2:
-		dma->rx_chan_id = 5;
-		dma->tx_chan_id = 4;
+	case PCI_DEVICE_ID_INTEL_BSW_UART2:
+		rx_param->src_id = 5;
+		tx_param->dst_id = 4;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	dma->rxconf.slave_id = dma->rx_chan_id;
+	rx_param->src_master = 1;
+	rx_param->dst_master = 0;
+
 	dma->rxconf.src_maxburst = 16;
 
-	dma->txconf.slave_id = dma->tx_chan_id;
+	tx_param->src_master = 1;
+	tx_param->dst_master = 0;
+
 	dma->txconf.dst_maxburst = 16;
 
+	dma_dev = pci_get_slot(pdev->bus, PCI_DEVFN(PCI_SLOT(pdev->devfn), 0));
+	rx_param->dma_dev = &dma_dev->dev;
+	tx_param->dma_dev = &dma_dev->dev;
+
 	dma->fn = byt_dma_filter;
-	dma->rx_param = &dma->rx_chan_id;
-	dma->tx_param = &dma->tx_chan_id;
+	dma->rx_param = rx_param;
+	dma->tx_param = tx_param;
 
 	ret = pci_default_setup(priv, board, port, idx);
 	port->port.iotype = UPIO_MEM;
@@ -1893,6 +1927,20 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = {
 		.subdevice	= PCI_ANY_ID,
 		.setup		= pci_default_setup,
 	},
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_BSW_UART1,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= byt_serial_setup,
+	},
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_BSW_UART2,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.setup		= byt_serial_setup,
+	},
 	/*
 	 * ITE
 	 */
@@ -5192,6 +5240,14 @@ static struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID,  PCI_ANY_ID,
 		PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000,
 		pbn_byt },
+	{	PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BSW_UART1,
+		PCI_ANY_ID,  PCI_ANY_ID,
+		PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000,
+		pbn_byt },
+	{	PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BSW_UART2,
+		PCI_ANY_ID,  PCI_ANY_ID,
+		PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000,
+		pbn_byt },
 
 	/*
 	 * Intel Quark x1000
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index d7d4584549a5..edde3eca055d 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -37,6 +37,7 @@
 #include <linux/of_device.h>
 #include <linux/of_gpio.h>
 #include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
 #include <linux/atmel_pdc.h>
 #include <linux/atmel_serial.h>
 #include <linux/uaccess.h>
diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 82573dc4d8cf..0041a64cc86e 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -1248,7 +1248,7 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 	mutex_destroy(&s->mutex);
 
 #ifdef CONFIG_GPIOLIB
-	WARN_ON(gpiochip_remove(&s->gpio));
+	gpiochip_remove(&s->gpio);
 
 out_uart:
 #endif
@@ -1263,12 +1263,10 @@ out_clk:
 static int max310x_remove(struct device *dev)
 {
 	struct max310x_port *s = dev_get_drvdata(dev);
-	int i, ret = 0;
+	int i;
 
 #ifdef CONFIG_GPIOLIB
-	ret = gpiochip_remove(&s->gpio);
-	if (ret)
-		return ret;
+	gpiochip_remove(&s->gpio);
 #endif
 
 	for (i = 0; i < s->uart.nr; i++) {
@@ -1282,7 +1280,7 @@ static int max310x_remove(struct device *dev)
 	uart_unregister_driver(&s->uart);
 	clk_disable_unprepare(s->clk);
 
-	return ret;
+	return 0;
 }
 
 static const struct of_device_id __maybe_unused max310x_dt_ids[] = {
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 3284c31085a7..6246820d7f05 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1157,7 +1157,7 @@ static int sc16is7xx_probe(struct device *dev,
 
 #ifdef CONFIG_GPIOLIB
 	if (devtype->nr_gpio)
-		WARN_ON(gpiochip_remove(&s->gpio));
+		gpiochip_remove(&s->gpio);
 
 out_uart:
 #endif
@@ -1173,14 +1173,11 @@ out_clk:
 static int sc16is7xx_remove(struct device *dev)
 {
 	struct sc16is7xx_port *s = dev_get_drvdata(dev);
-	int i, ret = 0;
+	int i;
 
 #ifdef CONFIG_GPIOLIB
-	if (s->devtype->nr_gpio) {
-		ret = gpiochip_remove(&s->gpio);
-		if (ret)
-			return ret;
-	}
+	if (s->devtype->nr_gpio)
+		gpiochip_remove(&s->gpio);
 #endif
 
 	for (i = 0; i < s->uart.nr; i++) {
@@ -1195,7 +1192,7 @@ static int sc16is7xx_remove(struct device *dev)
 	if (!IS_ERR(s->clk))
 		clk_disable_unprepare(s->clk);
 
-	return ret;
+	return 0;
 }
 
 static const struct of_device_id __maybe_unused sc16is7xx_dt_ids[] = {
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 3081e46085ce..eb17c7124e72 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -1403,7 +1403,7 @@ static void work_fn_rx(struct work_struct *work)
 		unsigned long flags;
 		int count;
 
-		chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
+		dmaengine_terminate_all(chan);
 		dev_dbg(port->dev, "Read %zu bytes with cookie %d\n",
 			sh_desc->partial, sh_desc->cookie);
 
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 2f6f9b5e4891..16a2c0237dd6 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2186,8 +2186,9 @@ static int __tty_fasync(int fd, struct file *filp, int on)
 		}
 		get_pid(pid);
 		spin_unlock_irqrestore(&tty->ctrl_lock, flags);
-		retval = __f_setown(filp, pid, type, 0);
+		__f_setown(filp, pid, type, 0);
 		put_pid(pid);
+		retval = 0;
 	}
 out:
 	return retval;
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 4ad11e03cf54..7c6771d027a2 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -164,10 +164,9 @@ struct ffs_desc_helper {
 static int  __must_check ffs_epfiles_create(struct ffs_data *ffs);
 static void ffs_epfiles_destroy(struct ffs_epfile *epfiles, unsigned count);
 
-static struct inode *__must_check
+static struct dentry *
 ffs_sb_create_file(struct super_block *sb, const char *name, void *data,
-		   const struct file_operations *fops,
-		   struct dentry **dentry_p);
+		   const struct file_operations *fops);
 
 /* Devices management *******************************************************/
 
@@ -1119,10 +1118,9 @@ ffs_sb_make_inode(struct super_block *sb, void *data,
 }
 
 /* Create "regular" file */
-static struct inode *ffs_sb_create_file(struct super_block *sb,
+static struct dentry *ffs_sb_create_file(struct super_block *sb,
 					const char *name, void *data,
-					const struct file_operations *fops,
-					struct dentry **dentry_p)
+					const struct file_operations *fops)
 {
 	struct ffs_data	*ffs = sb->s_fs_info;
 	struct dentry	*dentry;
@@ -1141,10 +1139,7 @@ static struct inode *ffs_sb_create_file(struct super_block *sb,
 	}
 
 	d_add(dentry, inode);
-	if (dentry_p)
-		*dentry_p = dentry;
-
-	return inode;
+	return dentry;
 }
 
 /* Super block */
@@ -1189,7 +1184,7 @@ static int ffs_sb_fill(struct super_block *sb, void *_data, int silent)
 
 	/* EP0 file */
 	if (unlikely(!ffs_sb_create_file(sb, "ep0", ffs,
-					 &ffs_ep0_operations, NULL)))
+					 &ffs_ep0_operations)))
 		return -ENOMEM;
 
 	return 0;
@@ -1561,9 +1556,10 @@ static int ffs_epfiles_create(struct ffs_data *ffs)
 			sprintf(epfiles->name, "ep%02x", ffs->eps_addrmap[i]);
 		else
 			sprintf(epfiles->name, "ep%u", i);
-		if (!unlikely(ffs_sb_create_file(ffs->sb, epfiles->name, epfile,
-						 &ffs_epfile_operations,
-						 &epfile->dentry))) {
+		epfile->dentry = ffs_sb_create_file(ffs->sb, epfiles->name,
+						 epfile,
+						 &ffs_epfile_operations);
+		if (unlikely(!epfile->dentry)) {
 			ffs_epfiles_destroy(epfiles, i - 1);
 			return -ENOMEM;
 		}
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index edefec2cc584..c744e4975d74 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -198,7 +198,6 @@ struct ep_data {
 	struct list_head		epfiles;
 	wait_queue_head_t		wait;
 	struct dentry			*dentry;
-	struct inode			*inode;
 };
 
 static inline void get_ep (struct ep_data *data)
@@ -1618,10 +1617,9 @@ static void destroy_ep_files (struct dev_data *dev)
 }
 
 
-static struct inode *
+static struct dentry *
 gadgetfs_create_file (struct super_block *sb, char const *name,
-		void *data, const struct file_operations *fops,
-		struct dentry **dentry_p);
+		void *data, const struct file_operations *fops);
 
 static int activate_ep_files (struct dev_data *dev)
 {
@@ -1649,10 +1647,9 @@ static int activate_ep_files (struct dev_data *dev)
 		if (!data->req)
 			goto enomem1;
 
-		data->inode = gadgetfs_create_file (dev->sb, data->name,
-				data, &ep_config_operations,
-				&data->dentry);
-		if (!data->inode)
+		data->dentry = gadgetfs_create_file (dev->sb, data->name,
+				data, &ep_config_operations);
+		if (!data->dentry)
 			goto enomem2;
 		list_add_tail (&data->epfiles, &dev->epfiles);
 	}
@@ -2012,10 +2009,9 @@ gadgetfs_make_inode (struct super_block *sb,
 /* creates in fs root directory, so non-renamable and non-linkable.
  * so inode and dentry are paired, until device reconfig.
  */
-static struct inode *
+static struct dentry *
 gadgetfs_create_file (struct super_block *sb, char const *name,
-		void *data, const struct file_operations *fops,
-		struct dentry **dentry_p)
+		void *data, const struct file_operations *fops)
 {
 	struct dentry	*dentry;
 	struct inode	*inode;
@@ -2031,8 +2027,7 @@ gadgetfs_create_file (struct super_block *sb, char const *name,
 		return NULL;
 	}
 	d_add (dentry, inode);
-	*dentry_p = dentry;
-	return inode;
+	return dentry;
 }
 
 static const struct super_operations gadget_fs_operations = {
@@ -2080,9 +2075,8 @@ gadgetfs_fill_super (struct super_block *sb, void *opts, int silent)
 		goto Enomem;
 
 	dev->sb = sb;
-	if (!gadgetfs_create_file (sb, CHIP,
-				dev, &dev_init_operations,
-				&dev->dentry)) {
+	dev->dentry = gadgetfs_create_file(sb, CHIP, dev, &dev_init_operations);
+	if (!dev->dentry) {
 		put_dev(dev);
 		goto Enomem;
 	}
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index f7825332a325..9558da3f06a0 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -876,15 +876,11 @@ static void vfio_pci_remove(struct pci_dev *pdev)
 {
 	struct vfio_pci_device *vdev;
 
-	mutex_lock(&driver_lock);
-
 	vdev = vfio_del_group_dev(&pdev->dev);
 	if (vdev) {
 		iommu_group_put(pdev->dev.iommu_group);
 		kfree(vdev);
 	}
-
-	mutex_unlock(&driver_lock);
 }
 
 static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
@@ -927,108 +923,90 @@ static struct pci_driver vfio_pci_driver = {
 	.err_handler	= &vfio_err_handlers,
 };
 
-/*
- * Test whether a reset is necessary and possible.  We mark devices as
- * needs_reset when they are released, but don't have a function-local reset
- * available.  If any of these exist in the affected devices, we want to do
- * a bus/slot reset.  We also need all of the affected devices to be unused,
- * so we abort if any device has a non-zero refcnt.  driver_lock prevents a
- * device from being opened during the scan or unbound from vfio-pci.
- */
-static int vfio_pci_test_bus_reset(struct pci_dev *pdev, void *data)
-{
-	bool *needs_reset = data;
-	struct pci_driver *pci_drv = ACCESS_ONCE(pdev->driver);
-	int ret = -EBUSY;
-
-	if (pci_drv == &vfio_pci_driver) {
-		struct vfio_device *device;
-		struct vfio_pci_device *vdev;
-
-		device = vfio_device_get_from_dev(&pdev->dev);
-		if (!device)
-			return ret;
-
-		vdev = vfio_device_data(device);
-		if (vdev) {
-			if (vdev->needs_reset)
-				*needs_reset = true;
-
-			if (!vdev->refcnt)
-				ret = 0;
-		}
-
-		vfio_device_put(device);
-	}
-
-	/*
-	 * TODO: vfio-core considers groups to be viable even if some devices
-	 * are attached to known drivers, like pci-stub or pcieport.  We can't
-	 * freeze devices from being unbound to those drivers like we can
-	 * here though, so it would be racy to test for them.  We also can't
-	 * use device_lock() to prevent changes as that would interfere with
-	 * PCI-core taking device_lock during bus reset.  For now, we require
-	 * devices to be bound to vfio-pci to get a bus/slot reset on release.
-	 */
-
-	return ret;
-}
+struct vfio_devices {
+	struct vfio_device **devices;
+	int cur_index;
+	int max_index;
+};
 
-/* Clear needs_reset on all affected devices after successful bus/slot reset */
-static int vfio_pci_clear_needs_reset(struct pci_dev *pdev, void *data)
+static int vfio_pci_get_devs(struct pci_dev *pdev, void *data)
 {
+	struct vfio_devices *devs = data;
 	struct pci_driver *pci_drv = ACCESS_ONCE(pdev->driver);
 
-	if (pci_drv == &vfio_pci_driver) {
-		struct vfio_device *device;
-		struct vfio_pci_device *vdev;
+	if (pci_drv != &vfio_pci_driver)
+		return -EBUSY;
 
-		device = vfio_device_get_from_dev(&pdev->dev);
-		if (!device)
-			return 0;
+	if (devs->cur_index == devs->max_index)
+		return -ENOSPC;
 
-		vdev = vfio_device_data(device);
-		if (vdev)
-			vdev->needs_reset = false;
-
-		vfio_device_put(device);
-	}
+	devs->devices[devs->cur_index] = vfio_device_get_from_dev(&pdev->dev);
+	if (!devs->devices[devs->cur_index])
+		return -EINVAL;
 
+	devs->cur_index++;
 	return 0;
 }
 
 /*
  * Attempt to do a bus/slot reset if there are devices affected by a reset for
  * this device that are needs_reset and all of the affected devices are unused
- * (!refcnt).  Callers of this function are required to hold driver_lock such
- * that devices can not be unbound from vfio-pci or opened by a user while we
- * test for and perform a bus/slot reset.
+ * (!refcnt).  Callers are required to hold driver_lock when calling this to
+ * prevent device opens and concurrent bus reset attempts.  We prevent device
+ * unbinds by acquiring and holding a reference to the vfio_device.
+ *
+ * NB: vfio-core considers a group to be viable even if some devices are
+ * bound to drivers like pci-stub or pcieport.  Here we require all devices
+ * to be bound to vfio_pci since that's the only way we can be sure they
+ * stay put.
  */
 static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
 {
+	struct vfio_devices devs = { .cur_index = 0 };
+	int i = 0, ret = -EINVAL;
 	bool needs_reset = false, slot = false;
-	int ret;
+	struct vfio_pci_device *tmp;
 
 	if (!pci_probe_reset_slot(vdev->pdev->slot))
 		slot = true;
 	else if (pci_probe_reset_bus(vdev->pdev->bus))
 		return;
 
-	if (vfio_pci_for_each_slot_or_bus(vdev->pdev,
-					  vfio_pci_test_bus_reset,
-					  &needs_reset, slot) || !needs_reset)
+	if (vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs,
+					  &i, slot) || !i)
 		return;
 
-	if (slot)
-		ret = pci_try_reset_slot(vdev->pdev->slot);
-	else
-		ret = pci_try_reset_bus(vdev->pdev->bus);
-
-	if (ret)
+	devs.max_index = i;
+	devs.devices = kcalloc(i, sizeof(struct vfio_device *), GFP_KERNEL);
+	if (!devs.devices)
 		return;
 
-	vfio_pci_for_each_slot_or_bus(vdev->pdev,
-				      vfio_pci_clear_needs_reset, NULL, slot);
+	if (vfio_pci_for_each_slot_or_bus(vdev->pdev,
+					  vfio_pci_get_devs, &devs, slot))
+		goto put_devs;
+
+	for (i = 0; i < devs.cur_index; i++) {
+		tmp = vfio_device_data(devs.devices[i]);
+		if (tmp->needs_reset)
+			needs_reset = true;
+		if (tmp->refcnt)
+			goto put_devs;
+	}
+
+	if (needs_reset)
+		ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
+			     pci_try_reset_bus(vdev->pdev->bus);
+
+put_devs:
+	for (i = 0; i < devs.cur_index; i++) {
+		if (!ret) {
+			tmp = vfio_device_data(devs.devices[i]);
+			tmp->needs_reset = false;
+		}
+		vfio_device_put(devs.devices[i]);
+	}
+
+	kfree(devs.devices);
 }
 
 static void __exit vfio_pci_cleanup(void)
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index e50790e91f76..1de3f94aa7de 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -727,7 +727,7 @@ static int __init init_pci_ext_cap_err_perm(struct perm_bits *perm)
 	p_setd(perm, 0, ALL_VIRT, NO_WRITE);
 
 	/* Writable bits mask */
-	mask =	PCI_ERR_UNC_TRAIN |		/* Training */
+	mask =	PCI_ERR_UNC_UND |		/* Undefined */
 		PCI_ERR_UNC_DLP |		/* Data Link Protocol */
 		PCI_ERR_UNC_SURPDN |		/* Surprise Down */
 		PCI_ERR_UNC_POISON_TLP |	/* Poisoned TLP */
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 9dd49c9839ac..553212f037c3 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -16,6 +16,7 @@
 #include <linux/device.h>
 #include <linux/interrupt.h>
 #include <linux/eventfd.h>
+#include <linux/msi.h>
 #include <linux/pci.h>
 #include <linux/file.h>
 #include <linux/poll.h>
@@ -548,6 +549,20 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
 		return PTR_ERR(trigger);
 	}
 
+	/*
+	 * The MSIx vector table resides in device memory which may be cleared
+	 * via backdoor resets. We don't allow direct access to the vector
+	 * table so even if a userspace driver attempts to save/restore around
+	 * such a reset it would be unsuccessful. To avoid this, restore the
+	 * cached value of the message prior to enabling.
+	 */
+	if (msix) {
+		struct msi_msg msg;
+
+		get_cached_msi_msg(irq, &msg);
+		write_msi_msg(irq, &msg);
+	}
+
 	ret = request_irq(irq, vfio_msihandler, 0,
 			  vdev->ctx[vector].name, trigger);
 	if (ret) {
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 0734fbe5b651..4a9d666f1e91 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -57,7 +57,8 @@ struct vfio_iommu {
 	struct list_head	domain_list;
 	struct mutex		lock;
 	struct rb_root		dma_list;
-	bool v2;
+	bool			v2;
+	bool			nesting;
 };
 
 struct vfio_domain {
@@ -705,6 +706,15 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 		goto out_free;
 	}
 
+	if (iommu->nesting) {
+		int attr = 1;
+
+		ret = iommu_domain_set_attr(domain->domain, DOMAIN_ATTR_NESTING,
+					    &attr);
+		if (ret)
+			goto out_domain;
+	}
+
 	ret = iommu_attach_group(domain->domain, iommu_group);
 	if (ret)
 		goto out_domain;
@@ -713,14 +723,14 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	list_add(&group->next, &domain->group_list);
 
 	if (!allow_unsafe_interrupts &&
-	    !iommu_domain_has_cap(domain->domain, IOMMU_CAP_INTR_REMAP)) {
+	    !iommu_capable(bus, IOMMU_CAP_INTR_REMAP)) {
 		pr_warn("%s: No interrupt remapping support.  Use the module param \"allow_unsafe_interrupts\" to enable VFIO IOMMU support on this platform\n",
 		       __func__);
 		ret = -EPERM;
 		goto out_detach;
 	}
 
-	if (iommu_domain_has_cap(domain->domain, IOMMU_CAP_CACHE_COHERENCY))
+	if (iommu_capable(bus, IOMMU_CAP_CACHE_COHERENCY))
 		domain->prot |= IOMMU_CACHE;
 
 	/*
@@ -819,17 +829,26 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 {
 	struct vfio_iommu *iommu;
 
-	if (arg != VFIO_TYPE1_IOMMU && arg != VFIO_TYPE1v2_IOMMU)
-		return ERR_PTR(-EINVAL);
-
 	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
 	if (!iommu)
 		return ERR_PTR(-ENOMEM);
 
+	switch (arg) {
+	case VFIO_TYPE1_IOMMU:
+		break;
+	case VFIO_TYPE1_NESTING_IOMMU:
+		iommu->nesting = true;
+	case VFIO_TYPE1v2_IOMMU:
+		iommu->v2 = true;
+		break;
+	default:
+		kfree(iommu);
+		return ERR_PTR(-EINVAL);
+	}
+
 	INIT_LIST_HEAD(&iommu->domain_list);
 	iommu->dma_list = RB_ROOT;
 	mutex_init(&iommu->lock);
-	iommu->v2 = (arg == VFIO_TYPE1v2_IOMMU);
 
 	return iommu;
 }
@@ -885,6 +904,7 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 		switch (arg) {
 		case VFIO_TYPE1_IOMMU:
 		case VFIO_TYPE1v2_IOMMU:
+		case VFIO_TYPE1_NESTING_IOMMU:
 			return 1;
 		case VFIO_DMA_CC_IOMMU:
 			if (!iommu)
diff --git a/drivers/vfio/vfio_spapr_eeh.c b/drivers/vfio/vfio_spapr_eeh.c
index 86dfceb9201f..5fa42db769ee 100644
--- a/drivers/vfio/vfio_spapr_eeh.c
+++ b/drivers/vfio/vfio_spapr_eeh.c
@@ -92,7 +92,7 @@ long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
 
 	return ret;
 }
-EXPORT_SYMBOL(vfio_spapr_iommu_eeh_ioctl);
+EXPORT_SYMBOL_GPL(vfio_spapr_iommu_eeh_ioctl);
 
 MODULE_VERSION(DRIVER_VERSION);
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/video/backlight/88pm860x_bl.c b/drivers/video/backlight/88pm860x_bl.c
index a6f7cc0a0883..9a23698b6fe8 100644
--- a/drivers/video/backlight/88pm860x_bl.c
+++ b/drivers/video/backlight/88pm860x_bl.c
@@ -265,7 +265,6 @@ static int pm860x_backlight_probe(struct platform_device *pdev)
 static struct platform_driver pm860x_backlight_driver = {
 	.driver		= {
 		.name	= "88pm860x-backlight",
-		.owner	= THIS_MODULE,
 	},
 	.probe		= pm860x_backlight_probe,
 };
diff --git a/drivers/video/backlight/aat2870_bl.c b/drivers/video/backlight/aat2870_bl.c
index 86234c31d79c..50774e657700 100644
--- a/drivers/video/backlight/aat2870_bl.c
+++ b/drivers/video/backlight/aat2870_bl.c
@@ -211,7 +211,6 @@ static int aat2870_bl_remove(struct platform_device *pdev)
 static struct platform_driver aat2870_bl_driver = {
 	.driver = {
 		.name	= "aat2870-backlight",
-		.owner	= THIS_MODULE,
 	},
 	.probe		= aat2870_bl_probe,
 	.remove		= aat2870_bl_remove,
diff --git a/drivers/video/backlight/adp5520_bl.c b/drivers/video/backlight/adp5520_bl.c
index f37097a261a2..dd88ba1d71ce 100644
--- a/drivers/video/backlight/adp5520_bl.c
+++ b/drivers/video/backlight/adp5520_bl.c
@@ -67,6 +67,7 @@ static int adp5520_bl_set(struct backlight_device *bl, int brightness)
 static int adp5520_bl_update_status(struct backlight_device *bl)
 {
 	int brightness = bl->props.brightness;
+
 	if (bl->props.power != FB_BLANK_UNBLANK)
 		brightness = 0;
 
@@ -374,7 +375,6 @@ static SIMPLE_DEV_PM_OPS(adp5520_bl_pm_ops, adp5520_bl_suspend,
 static struct platform_driver adp5520_bl_driver = {
 	.driver		= {
 		.name	= "adp5520-backlight",
-		.owner	= THIS_MODULE,
 		.pm	= &adp5520_bl_pm_ops,
 	},
 	.probe		= adp5520_bl_probe,
diff --git a/drivers/video/backlight/adp8860_bl.c b/drivers/video/backlight/adp8860_bl.c
index be8d83deca7d..71147f4461b8 100644
--- a/drivers/video/backlight/adp8860_bl.c
+++ b/drivers/video/backlight/adp8860_bl.c
@@ -181,6 +181,7 @@ static int adp8860_clr_bits(struct i2c_client *client, int reg, uint8_t bit_mask
 static void adp8860_led_work(struct work_struct *work)
 {
 	struct adp8860_led *led = container_of(work, struct adp8860_led, work);
+
 	adp8860_write(led->client, ADP8860_ISC1 - led->id + 1,
 			 led->new_brightness >> 1);
 }
@@ -362,6 +363,7 @@ static int adp8860_bl_set(struct backlight_device *bl, int brightness)
 static int adp8860_bl_update_status(struct backlight_device *bl)
 {
 	int brightness = bl->props.brightness;
+
 	if (bl->props.power != FB_BLANK_UNBLANK)
 		brightness = 0;
 
@@ -499,6 +501,7 @@ static ssize_t adp8860_bl_l1_daylight_max_store(struct device *dev,
 {
 	struct adp8860_bl *data = dev_get_drvdata(dev);
 	int ret = kstrtoul(buf, 10, &data->cached_daylight_max);
+
 	if (ret)
 		return ret;
 
diff --git a/drivers/video/backlight/adp8870_bl.c b/drivers/video/backlight/adp8870_bl.c
index 251af4d38d86..037e43083343 100644
--- a/drivers/video/backlight/adp8870_bl.c
+++ b/drivers/video/backlight/adp8870_bl.c
@@ -144,6 +144,7 @@ static int adp8870_read(struct i2c_client *client, int reg, uint8_t *val)
 static int adp8870_write(struct i2c_client *client, u8 reg, u8 val)
 {
 	int ret = i2c_smbus_write_byte_data(client, reg, val);
+
 	if (ret)
 		dev_err(&client->dev, "failed to write\n");
 
@@ -195,6 +196,7 @@ static int adp8870_clr_bits(struct i2c_client *client, int reg, uint8_t bit_mask
 static void adp8870_led_work(struct work_struct *work)
 {
 	struct adp8870_led *led = container_of(work, struct adp8870_led, work);
+
 	adp8870_write(led->client, ADP8870_ISC1 + led->id - 1,
 			 led->new_brightness >> 1);
 }
@@ -399,6 +401,7 @@ static int adp8870_bl_set(struct backlight_device *bl, int brightness)
 static int adp8870_bl_update_status(struct backlight_device *bl)
 {
 	int brightness = bl->props.brightness;
+
 	if (bl->props.power != FB_BLANK_UNBLANK)
 		brightness = 0;
 
@@ -649,6 +652,7 @@ static ssize_t adp8870_bl_l1_daylight_max_store(struct device *dev,
 {
 	struct adp8870_bl *data = dev_get_drvdata(dev);
 	int ret = kstrtoul(buf, 10, &data->cached_daylight_max);
+
 	if (ret)
 		return ret;
 
diff --git a/drivers/video/backlight/ams369fg06.c b/drivers/video/backlight/ams369fg06.c
index 4726c8be626f..5f897f99cc9b 100644
--- a/drivers/video/backlight/ams369fg06.c
+++ b/drivers/video/backlight/ams369fg06.c
@@ -325,11 +325,11 @@ static int ams369fg06_power_on(struct ams369fg06 *lcd)
 	if (!pd->reset) {
 		dev_err(lcd->dev, "reset is NULL.\n");
 		return -EINVAL;
-	} else {
-		pd->reset(lcd->ld);
-		msleep(pd->reset_delay);
 	}
 
+	pd->reset(lcd->ld);
+	msleep(pd->reset_delay);
+
 	ret = ams369fg06_ldi_init(lcd);
 	if (ret) {
 		dev_err(lcd->dev, "failed to initialize ldi.\n");
diff --git a/drivers/video/backlight/as3711_bl.c b/drivers/video/backlight/as3711_bl.c
index bb1fc45b7549..734a9158946b 100644
--- a/drivers/video/backlight/as3711_bl.c
+++ b/drivers/video/backlight/as3711_bl.c
@@ -467,7 +467,6 @@ static int as3711_backlight_probe(struct platform_device *pdev)
 static struct platform_driver as3711_backlight_driver = {
 	.driver		= {
 		.name	= "as3711-backlight",
-		.owner	= THIS_MODULE,
 	},
 	.probe		= as3711_backlight_probe,
 };
diff --git a/drivers/video/backlight/corgi_lcd.c b/drivers/video/backlight/corgi_lcd.c
index 51d18d637e2b..d7c37a8ccd1f 100644
--- a/drivers/video/backlight/corgi_lcd.c
+++ b/drivers/video/backlight/corgi_lcd.c
@@ -143,6 +143,7 @@ static void lcdtg_i2c_send_byte(struct corgi_lcd *lcd,
 				uint8_t base, uint8_t data)
 {
 	int i;
+
 	for (i = 0; i < 8; i++) {
 		if (data & 0x80)
 			lcdtg_i2c_send_bit(lcd, base | POWER0_COM_DOUT);
diff --git a/drivers/video/backlight/cr_bllcd.c b/drivers/video/backlight/cr_bllcd.c
index f3fed9ef745f..3e3880fc8c8e 100644
--- a/drivers/video/backlight/cr_bllcd.c
+++ b/drivers/video/backlight/cr_bllcd.c
@@ -235,6 +235,7 @@ static int cr_backlight_probe(struct platform_device *pdev)
 static int cr_backlight_remove(struct platform_device *pdev)
 {
 	struct cr_panel *crp = platform_get_drvdata(pdev);
+
 	crp->cr_backlight_device->props.power = FB_BLANK_POWERDOWN;
 	crp->cr_backlight_device->props.brightness = 0;
 	crp->cr_backlight_device->props.max_brightness = 0;
diff --git a/drivers/video/backlight/da903x_bl.c b/drivers/video/backlight/da903x_bl.c
index 12c5d840c590..f793738f06fb 100644
--- a/drivers/video/backlight/da903x_bl.c
+++ b/drivers/video/backlight/da903x_bl.c
@@ -162,7 +162,6 @@ static int da903x_backlight_probe(struct platform_device *pdev)
 static struct platform_driver da903x_backlight_driver = {
 	.driver		= {
 		.name	= "da903x-backlight",
-		.owner	= THIS_MODULE,
 	},
 	.probe		= da903x_backlight_probe,
 };
diff --git a/drivers/video/backlight/da9052_bl.c b/drivers/video/backlight/da9052_bl.c
index 20d55becaa74..d4bd74bd5070 100644
--- a/drivers/video/backlight/da9052_bl.c
+++ b/drivers/video/backlight/da9052_bl.c
@@ -173,7 +173,6 @@ static struct platform_driver da9052_wled_driver = {
 	.id_table	= da9052_wled_ids,
 	.driver	= {
 		.name	= "da9052-wled",
-		.owner	= THIS_MODULE,
 	},
 };
 
diff --git a/drivers/video/backlight/ep93xx_bl.c b/drivers/video/backlight/ep93xx_bl.c
index 0d1f633c6480..0067931821c6 100644
--- a/drivers/video/backlight/ep93xx_bl.c
+++ b/drivers/video/backlight/ep93xx_bl.c
@@ -128,7 +128,6 @@ static SIMPLE_DEV_PM_OPS(ep93xxbl_pm_ops, ep93xxbl_suspend, ep93xxbl_resume);
 static struct platform_driver ep93xxbl_driver = {
 	.driver		= {
 		.name	= "ep93xx-bl",
-		.owner	= THIS_MODULE,
 		.pm	= &ep93xxbl_pm_ops,
 	},
 	.probe		= ep93xxbl_probe,
diff --git a/drivers/video/backlight/generic_bl.c b/drivers/video/backlight/generic_bl.c
index 5d8d65200db7..67dfb939a514 100644
--- a/drivers/video/backlight/generic_bl.c
+++ b/drivers/video/backlight/generic_bl.c
@@ -52,24 +52,6 @@ static int genericbl_get_intensity(struct backlight_device *bd)
 	return genericbl_intensity;
 }
 
-/*
- * Called when the battery is low to limit the backlight intensity.
- * If limit==0 clear any limit, otherwise limit the intensity
- */
-void genericbl_limit_intensity(int limit)
-{
-	struct backlight_device *bd = generic_backlight_device;
-
-	mutex_lock(&bd->ops_lock);
-	if (limit)
-		bd->props.state |= GENERICBL_BATTLOW;
-	else
-		bd->props.state &= ~GENERICBL_BATTLOW;
-	backlight_update_status(generic_backlight_device);
-	mutex_unlock(&bd->ops_lock);
-}
-EXPORT_SYMBOL(genericbl_limit_intensity);
-
 static const struct backlight_ops genericbl_ops = {
 	.options = BL_CORE_SUSPENDRESUME,
 	.get_brightness = genericbl_get_intensity,
diff --git a/drivers/video/backlight/gpio_backlight.c b/drivers/video/backlight/gpio_backlight.c
index aaead04a2d54..439feb2389a8 100644
--- a/drivers/video/backlight/gpio_backlight.c
+++ b/drivers/video/backlight/gpio_backlight.c
@@ -151,7 +151,6 @@ static struct of_device_id gpio_backlight_of_match[] = {
 static struct platform_driver gpio_backlight_driver = {
 	.driver		= {
 		.name		= "gpio-backlight",
-		.owner		= THIS_MODULE,
 		.of_match_table = of_match_ptr(gpio_backlight_of_match),
 	},
 	.probe		= gpio_backlight_probe,
diff --git a/drivers/video/backlight/ili922x.c b/drivers/video/backlight/ili922x.c
index ea67fe199e34..e7f0890cc211 100644
--- a/drivers/video/backlight/ili922x.c
+++ b/drivers/video/backlight/ili922x.c
@@ -495,17 +495,18 @@ static int ili922x_probe(struct spi_device *spi)
 			"no LCD found: Chip ID 0x%x, ret %d\n",
 			reg, ret);
 		return -ENODEV;
-	} else {
-		dev_info(&spi->dev, "ILI%x found, SPI freq %d, mode %d\n",
-			 reg, spi->max_speed_hz, spi->mode);
 	}
 
+	dev_info(&spi->dev, "ILI%x found, SPI freq %d, mode %d\n",
+		 reg, spi->max_speed_hz, spi->mode);
+
 	ret = ili922x_read_status(spi, &reg);
 	if (ret) {
 		dev_err(&spi->dev, "reading RS failed...\n");
 		return ret;
-	} else
-		dev_dbg(&spi->dev, "status: 0x%x\n", reg);
+	}
+
+	dev_dbg(&spi->dev, "status: 0x%x\n", reg);
 
 	ili922x_display_init(spi);
 
diff --git a/drivers/video/backlight/jornada720_bl.c b/drivers/video/backlight/jornada720_bl.c
index 6ce96b4a8796..7e6ff5346892 100644
--- a/drivers/video/backlight/jornada720_bl.c
+++ b/drivers/video/backlight/jornada720_bl.c
@@ -41,11 +41,11 @@ static int jornada_bl_get_brightness(struct backlight_device *bd)
 		dev_err(&bd->dev, "get brightness timeout\n");
 		jornada_ssp_end();
 		return -ETIMEDOUT;
-	} else {
-		/* exchange txdummy for value */
-		ret = jornada_ssp_byte(TXDUMMY);
 	}
 
+	/* exchange txdummy for value */
+	ret = jornada_ssp_byte(TXDUMMY);
+
 	jornada_ssp_end();
 
 	return BL_MAX_BRIGHT - ret;
diff --git a/drivers/video/backlight/jornada720_lcd.c b/drivers/video/backlight/jornada720_lcd.c
index 228bc319de19..dfa0fa0d5c78 100644
--- a/drivers/video/backlight/jornada720_lcd.c
+++ b/drivers/video/backlight/jornada720_lcd.c
@@ -27,11 +27,7 @@
 
 static int jornada_lcd_get_power(struct lcd_device *ld)
 {
-	/* LDD2 in PPC = LCD POWER */
-	if (PPSR & PPC_LDD2)
-		return FB_BLANK_UNBLANK;	/* PW ON */
-	else
-		return FB_BLANK_POWERDOWN;	/* PW OFF */
+	return PPSR & PPC_LDD2 ? FB_BLANK_UNBLANK : FB_BLANK_POWERDOWN;
 }
 
 static int jornada_lcd_get_contrast(struct lcd_device *ld)
diff --git a/drivers/video/backlight/ld9040.c b/drivers/video/backlight/ld9040.c
index ccb44e8e4927..f71eaf10c4eb 100644
--- a/drivers/video/backlight/ld9040.c
+++ b/drivers/video/backlight/ld9040.c
@@ -566,11 +566,11 @@ static int ld9040_power_on(struct ld9040 *lcd)
 	if (!pd->reset) {
 		dev_err(lcd->dev, "reset is NULL.\n");
 		return -EINVAL;
-	} else {
-		pd->reset(lcd->ld);
-		msleep(pd->reset_delay);
 	}
 
+	pd->reset(lcd->ld);
+	msleep(pd->reset_delay);
+
 	ret = ld9040_ldi_init(lcd);
 	if (ret) {
 		dev_err(lcd->dev, "failed to initialize ldi.\n");
diff --git a/drivers/video/backlight/lm3533_bl.c b/drivers/video/backlight/lm3533_bl.c
index cff1fbe89a1b..0e2337f367b6 100644
--- a/drivers/video/backlight/lm3533_bl.c
+++ b/drivers/video/backlight/lm3533_bl.c
@@ -397,7 +397,6 @@ static void lm3533_bl_shutdown(struct platform_device *pdev)
 static struct platform_driver lm3533_bl_driver = {
 	.driver = {
 		.name	= "lm3533-backlight",
-		.owner	= THIS_MODULE,
 		.pm	= &lm3533_bl_pm_ops,
 	},
 	.probe		= lm3533_bl_probe,
diff --git a/drivers/video/backlight/lm3639_bl.c b/drivers/video/backlight/lm3639_bl.c
index 5f36808d214f..cd50df5807ea 100644
--- a/drivers/video/backlight/lm3639_bl.c
+++ b/drivers/video/backlight/lm3639_bl.c
@@ -254,7 +254,6 @@ static void lm3639_torch_brightness_set(struct led_classdev *cdev,
 	return;
 out:
 	dev_err(pchip->dev, "i2c failed to access register\n");
-	return;
 }
 
 /* flash */
@@ -293,7 +292,6 @@ static void lm3639_flash_brightness_set(struct led_classdev *cdev,
 	return;
 out:
 	dev_err(pchip->dev, "i2c failed to access register\n");
-	return;
 }
 
 static const struct regmap_config lm3639_regmap = {
diff --git a/drivers/video/backlight/lms501kf03.c b/drivers/video/backlight/lms501kf03.c
index 77258b7b04be..7e3810308c3e 100644
--- a/drivers/video/backlight/lms501kf03.c
+++ b/drivers/video/backlight/lms501kf03.c
@@ -232,19 +232,19 @@ static int lms501kf03_power_on(struct lms501kf03 *lcd)
 	if (!pd->power_on) {
 		dev_err(lcd->dev, "power_on is NULL.\n");
 		return -EINVAL;
-	} else {
-		pd->power_on(lcd->ld, 1);
-		msleep(pd->power_on_delay);
 	}
 
+	pd->power_on(lcd->ld, 1);
+	msleep(pd->power_on_delay);
+
 	if (!pd->reset) {
 		dev_err(lcd->dev, "reset is NULL.\n");
 		return -EINVAL;
-	} else {
-		pd->reset(lcd->ld);
-		msleep(pd->reset_delay);
 	}
 
+	pd->reset(lcd->ld);
+	msleep(pd->reset_delay);
+
 	ret = lms501kf03_ldi_init(lcd);
 	if (ret) {
 		dev_err(lcd->dev, "failed to initialize ldi.\n");
diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index dcdd5443efcf..25fb8e3d75b1 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -268,6 +268,7 @@ static int lp855x_bl_update_status(struct backlight_device *bl)
 
 	} else if (lp->mode == REGISTER_BASED) {
 		u8 val = bl->props.brightness;
+
 		lp855x_write_byte(lp, lp->cfg->reg_brightness, val);
 	}
 
@@ -308,6 +309,7 @@ static ssize_t lp855x_get_chip_id(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct lp855x *lp = dev_get_drvdata(dev);
+
 	return scnprintf(buf, PAGE_SIZE, "%s\n", lp->chipname);
 }
 
diff --git a/drivers/video/backlight/lp8788_bl.c b/drivers/video/backlight/lp8788_bl.c
index d6c4f6a2d43e..e418d5b1aa55 100644
--- a/drivers/video/backlight/lp8788_bl.c
+++ b/drivers/video/backlight/lp8788_bl.c
@@ -315,7 +315,6 @@ static struct platform_driver lp8788_bl_driver = {
 	.remove = lp8788_backlight_remove,
 	.driver = {
 		.name = LP8788_DEV_BACKLIGHT,
-		.owner = THIS_MODULE,
 	},
 };
 module_platform_driver(lp8788_bl_driver);
diff --git a/drivers/video/backlight/max8925_bl.c b/drivers/video/backlight/max8925_bl.c
index 66fa08c920d2..7b738d60ecc2 100644
--- a/drivers/video/backlight/max8925_bl.c
+++ b/drivers/video/backlight/max8925_bl.c
@@ -197,7 +197,6 @@ static int max8925_backlight_probe(struct platform_device *pdev)
 static struct platform_driver max8925_backlight_driver = {
 	.driver		= {
 		.name	= "max8925-backlight",
-		.owner	= THIS_MODULE,
 	},
 	.probe		= max8925_backlight_probe,
 };
diff --git a/drivers/video/backlight/omap1_bl.c b/drivers/video/backlight/omap1_bl.c
index a0dcd88ac74f..546d94df21d5 100644
--- a/drivers/video/backlight/omap1_bl.c
+++ b/drivers/video/backlight/omap1_bl.c
@@ -120,6 +120,7 @@ static int omapbl_update_status(struct backlight_device *dev)
 static int omapbl_get_intensity(struct backlight_device *dev)
 {
 	struct omap_backlight *bl = bl_get_data(dev);
+
 	return bl->current_intensity;
 }
 
diff --git a/drivers/video/backlight/ot200_bl.c b/drivers/video/backlight/ot200_bl.c
index f5a5202dd79d..3acdb9f646ed 100644
--- a/drivers/video/backlight/ot200_bl.c
+++ b/drivers/video/backlight/ot200_bl.c
@@ -152,7 +152,6 @@ static int ot200_backlight_remove(struct platform_device *pdev)
 static struct platform_driver ot200_backlight_driver = {
 	.driver		= {
 		.name	= "ot200-backlight",
-		.owner	= THIS_MODULE,
 	},
 	.probe		= ot200_backlight_probe,
 	.remove		= ot200_backlight_remove,
diff --git a/drivers/video/backlight/pandora_bl.c b/drivers/video/backlight/pandora_bl.c
index 2e3f82063c03..5d8bb8b20183 100644
--- a/drivers/video/backlight/pandora_bl.c
+++ b/drivers/video/backlight/pandora_bl.c
@@ -142,7 +142,6 @@ static int pandora_backlight_probe(struct platform_device *pdev)
 static struct platform_driver pandora_backlight_driver = {
 	.driver		= {
 		.name	= "pandora-backlight",
-		.owner	= THIS_MODULE,
 	},
 	.probe		= pandora_backlight_probe,
 };
diff --git a/drivers/video/backlight/pcf50633-backlight.c b/drivers/video/backlight/pcf50633-backlight.c
index b95d3b0aaffe..85bd573b6d15 100644
--- a/drivers/video/backlight/pcf50633-backlight.c
+++ b/drivers/video/backlight/pcf50633-backlight.c
@@ -90,6 +90,7 @@ static int pcf50633_bl_update_status(struct backlight_device *bl)
 static int pcf50633_bl_get_brightness(struct backlight_device *bl)
 {
 	struct pcf50633_bl *pcf_bl = bl_get_data(bl);
+
 	return pcf_bl->brightness;
 }
 
diff --git a/drivers/video/backlight/platform_lcd.c b/drivers/video/backlight/platform_lcd.c
index c3d2e209fc8f..872a3bf21faf 100644
--- a/drivers/video/backlight/platform_lcd.c
+++ b/drivers/video/backlight/platform_lcd.c
@@ -148,7 +148,6 @@ MODULE_DEVICE_TABLE(of, platform_lcd_of_match);
 static struct platform_driver platform_lcd_driver = {
 	.driver		= {
 		.name	= "platform-lcd",
-		.owner	= THIS_MODULE,
 		.pm	= &platform_lcd_pm_ops,
 		.of_match_table = of_match_ptr(platform_lcd_of_match),
 	},
diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c
index b85983e97f0a..cb5ae4c08469 100644
--- a/drivers/video/backlight/pwm_bl.c
+++ b/drivers/video/backlight/pwm_bl.c
@@ -390,7 +390,6 @@ static const struct dev_pm_ops pwm_backlight_pm_ops = {
 static struct platform_driver pwm_backlight_driver = {
 	.driver		= {
 		.name		= "pwm-backlight",
-		.owner		= THIS_MODULE,
 		.pm		= &pwm_backlight_pm_ops,
 		.of_match_table	= of_match_ptr(pwm_backlight_of_match),
 	},
diff --git a/drivers/video/backlight/s6e63m0.c b/drivers/video/backlight/s6e63m0.c
index f3a65c8940ed..28bfa127fee4 100644
--- a/drivers/video/backlight/s6e63m0.c
+++ b/drivers/video/backlight/s6e63m0.c
@@ -507,19 +507,19 @@ static int s6e63m0_power_on(struct s6e63m0 *lcd)
 	if (!pd->power_on) {
 		dev_err(lcd->dev, "power_on is NULL.\n");
 		return -EINVAL;
-	} else {
-		pd->power_on(lcd->ld, 1);
-		msleep(pd->power_on_delay);
 	}
 
+	pd->power_on(lcd->ld, 1);
+	msleep(pd->power_on_delay);
+
 	if (!pd->reset) {
 		dev_err(lcd->dev, "reset is NULL.\n");
 		return -EINVAL;
-	} else {
-		pd->reset(lcd->ld);
-		msleep(pd->reset_delay);
 	}
 
+	pd->reset(lcd->ld);
+	msleep(pd->reset_delay);
+
 	ret = s6e63m0_ldi_init(lcd);
 	if (ret) {
 		dev_err(lcd->dev, "failed to initialize ldi.\n");
diff --git a/drivers/video/backlight/tdo24m.c b/drivers/video/backlight/tdo24m.c
index 908016fc5829..30afce33ef2a 100644
--- a/drivers/video/backlight/tdo24m.c
+++ b/drivers/video/backlight/tdo24m.c
@@ -300,12 +300,14 @@ static int tdo24m_power(struct tdo24m *lcd, int power)
 static int tdo24m_set_power(struct lcd_device *ld, int power)
 {
 	struct tdo24m *lcd = lcd_get_data(ld);
+
 	return tdo24m_power(lcd, power);
 }
 
 static int tdo24m_get_power(struct lcd_device *ld)
 {
 	struct tdo24m *lcd = lcd_get_data(ld);
+
 	return lcd->power;
 }
 
diff --git a/drivers/video/backlight/tps65217_bl.c b/drivers/video/backlight/tps65217_bl.c
index 2e04d93aa0ef..61d72bffd402 100644
--- a/drivers/video/backlight/tps65217_bl.c
+++ b/drivers/video/backlight/tps65217_bl.c
@@ -323,7 +323,6 @@ static int tps65217_bl_probe(struct platform_device *pdev)
 static struct platform_driver tps65217_bl_driver = {
 	.probe		= tps65217_bl_probe,
 	.driver		= {
-		.owner	= THIS_MODULE,
 		.name	= "tps65217-bl",
 	},
 };
diff --git a/drivers/video/backlight/wm831x_bl.c b/drivers/video/backlight/wm831x_bl.c
index 8b9455e93069..6eab0d6c262a 100644
--- a/drivers/video/backlight/wm831x_bl.c
+++ b/drivers/video/backlight/wm831x_bl.c
@@ -111,6 +111,7 @@ static int wm831x_backlight_update_status(struct backlight_device *bl)
 static int wm831x_backlight_get_brightness(struct backlight_device *bl)
 {
 	struct wm831x_backlight_data *data = bl_get_data(bl);
+
 	return data->current_brightness;
 }
 
@@ -217,7 +218,6 @@ static int wm831x_backlight_probe(struct platform_device *pdev)
 static struct platform_driver wm831x_backlight_driver = {
 	.driver		= {
 		.name	= "wm831x-backlight",
-		.owner	= THIS_MODULE,
 	},
 	.probe		= wm831x_backlight_probe,
 };
diff --git a/drivers/video/console/bitblit.c b/drivers/video/console/bitblit.c
index 61b182bf32a2..dbfe4eecf12e 100644
--- a/drivers/video/console/bitblit.c
+++ b/drivers/video/console/bitblit.c
@@ -205,7 +205,6 @@ static void bit_putcs(struct vc_data *vc, struct fb_info *info,
 static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 			      int bottom_only)
 {
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 	unsigned int cw = vc->vc_font.width;
 	unsigned int ch = vc->vc_font.height;
 	unsigned int rw = info->var.xres - (vc->vc_cols*cw);
@@ -214,7 +213,7 @@ static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int bs = info->var.yres - bh;
 	struct fb_fillrect region;
 
-	region.color = attr_bgcol_ec(bgshift, vc, info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon_ccw.c b/drivers/video/console/fbcon_ccw.c
index 41b32ae23dac..5a3cbf6dff4d 100644
--- a/drivers/video/console/fbcon_ccw.c
+++ b/drivers/video/console/fbcon_ccw.c
@@ -197,9 +197,8 @@ static void ccw_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int bh = info->var.xres - (vc->vc_rows*ch);
 	unsigned int bs = vc->vc_rows*ch;
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon_cw.c b/drivers/video/console/fbcon_cw.c
index a93670ef7f89..e7ee44db4e98 100644
--- a/drivers/video/console/fbcon_cw.c
+++ b/drivers/video/console/fbcon_cw.c
@@ -180,9 +180,8 @@ static void cw_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int bh = info->var.xres - (vc->vc_rows*ch);
 	unsigned int rs = info->var.yres - rw;
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon_ud.c b/drivers/video/console/fbcon_ud.c
index ff0872c0498b..19e3714abfe8 100644
--- a/drivers/video/console/fbcon_ud.c
+++ b/drivers/video/console/fbcon_ud.c
@@ -227,9 +227,8 @@ static void ud_clear_margins(struct vc_data *vc, struct fb_info *info,
 	unsigned int rw = info->var.xres - (vc->vc_cols*cw);
 	unsigned int bh = info->var.yres - (vc->vc_rows*ch);
 	struct fb_fillrect region;
-	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
 
-	region.color = attr_bgcol_ec(bgshift,vc,info);
+	region.color = 0;
 	region.rop = ROP_COPY;
 
 	if (rw && !bottom_only) {
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index e911b9c96e19..c7bf606a8706 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -4,6 +4,7 @@
 
 menuconfig FB
 	tristate "Support for frame buffer devices"
+	select FB_CMDLINE
 	---help---
 	  The frame buffer device provides an abstraction for the graphics
 	  hardware. It represents the frame buffer of some video hardware and
@@ -52,6 +53,9 @@ config FIRMWARE_EDID
 	 combination with certain motherboards and monitors are known to
 	 suffer from this problem.
 
+config FB_CMDLINE
+	bool
+
 config FB_DDC
        tristate
        depends on FB
@@ -2352,10 +2356,11 @@ config FB_MSM
 config FB_MX3
 	tristate "MX3 Framebuffer support"
 	depends on FB && MX3_IPU
+	select BACKLIGHT_CLASS_DEVICE
+	select BACKLIGHT_LCD_SUPPORT
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
-	select BACKLIGHT_CLASS_DEVICE
 	default y
 	help
 	  This is a framebuffer device for the i.MX31 LCD Controller. So
diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c
index 1d8bdb92939b..3bf403150a2d 100644
--- a/drivers/video/fbdev/atmel_lcdfb.c
+++ b/drivers/video/fbdev/atmel_lcdfb.c
@@ -24,6 +24,7 @@
 #include <linux/of_device.h>
 #include <linux/of_gpio.h>
 #include <video/of_display_timing.h>
+#include <linux/regulator/consumer.h>
 #include <video/videomode.h>
 
 #include <mach/cpu.h>
@@ -60,6 +61,7 @@ struct atmel_lcdfb_info {
 	struct atmel_lcdfb_pdata pdata;
 
 	struct atmel_lcdfb_config *config;
+	struct regulator	*reg_lcd;
 };
 
 struct atmel_lcdfb_power_ctrl_gpio {
@@ -302,10 +304,24 @@ static void init_contrast(struct atmel_lcdfb_info *sinfo)
 
 static inline void atmel_lcdfb_power_control(struct atmel_lcdfb_info *sinfo, int on)
 {
+	int ret;
 	struct atmel_lcdfb_pdata *pdata = &sinfo->pdata;
 
 	if (pdata->atmel_lcdfb_power_control)
 		pdata->atmel_lcdfb_power_control(pdata, on);
+	else if (sinfo->reg_lcd) {
+		if (on) {
+			ret = regulator_enable(sinfo->reg_lcd);
+			if (ret)
+				dev_err(&sinfo->pdev->dev,
+					"lcd regulator enable failed:	%d\n", ret);
+		} else {
+			ret = regulator_disable(sinfo->reg_lcd);
+			if (ret)
+				dev_err(&sinfo->pdev->dev,
+					"lcd regulator disable failed: %d\n", ret);
+		}
+	}
 }
 
 static struct fb_fix_screeninfo atmel_lcdfb_fix __initdata = {
@@ -1195,6 +1211,10 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev)
 	if (!sinfo->config)
 		goto free_info;
 
+	sinfo->reg_lcd = devm_regulator_get(&pdev->dev, "lcd");
+	if (IS_ERR(sinfo->reg_lcd))
+		sinfo->reg_lcd = NULL;
+
 	info->flags = ATMEL_LCDFB_FBINFO_DEFAULT;
 	info->pseudo_palette = sinfo->pseudo_palette;
 	info->fbops = &atmel_lcdfb_ops;
diff --git a/drivers/video/fbdev/aty/aty128fb.c b/drivers/video/fbdev/aty/aty128fb.c
index ff6070170d01..aedf2fbf9bf6 100644
--- a/drivers/video/fbdev/aty/aty128fb.c
+++ b/drivers/video/fbdev/aty/aty128fb.c
@@ -324,14 +324,61 @@ struct aty128_meminfo {
 };
 
 /* various memory configurations */
-static const struct aty128_meminfo sdr_128   =
-	{ 4, 4, 3, 3, 1, 3, 1, 16, 30, 16, "128-bit SDR SGRAM (1:1)" };
-static const struct aty128_meminfo sdr_64    =
-	{ 4, 8, 3, 3, 1, 3, 1, 17, 46, 17, "64-bit SDR SGRAM (1:1)" };
-static const struct aty128_meminfo sdr_sgram =
-	{ 4, 4, 1, 2, 1, 2, 1, 16, 24, 16, "64-bit SDR SGRAM (2:1)" };
-static const struct aty128_meminfo ddr_sgram =
-	{ 4, 4, 3, 3, 2, 3, 1, 16, 31, 16, "64-bit DDR SGRAM" };
+static const struct aty128_meminfo sdr_128 = {
+	.ML = 4,
+	.MB = 4,
+	.Trcd = 3,
+	.Trp = 3,
+	.Twr = 1,
+	.CL = 3,
+	.Tr2w = 1,
+	.LoopLatency = 16,
+	.DspOn = 30,
+	.Rloop = 16,
+	.name = "128-bit SDR SGRAM (1:1)",
+};
+
+static const struct aty128_meminfo sdr_64 = {
+	.ML = 4,
+	.MB = 8,
+	.Trcd = 3,
+	.Trp = 3,
+	.Twr = 1,
+	.CL = 3,
+	.Tr2w = 1,
+	.LoopLatency = 17,
+	.DspOn = 46,
+	.Rloop = 17,
+	.name = "64-bit SDR SGRAM (1:1)",
+};
+
+static const struct aty128_meminfo sdr_sgram = {
+	.ML = 4,
+	.MB = 4,
+	.Trcd = 1,
+	.Trp = 2,
+	.Twr = 1,
+	.CL = 2,
+	.Tr2w = 1,
+	.LoopLatency = 16,
+	.DspOn = 24,
+	.Rloop = 16,
+	.name = "64-bit SDR SGRAM (2:1)",
+};
+
+static const struct aty128_meminfo ddr_sgram = {
+	.ML = 4,
+	.MB = 4,
+	.Trcd = 3,
+	.Trp = 3,
+	.Twr = 2,
+	.CL = 3,
+	.Tr2w = 1,
+	.LoopLatency = 16,
+	.DspOn = 31,
+	.Rloop = 16,
+	.name = "64-bit DDR SGRAM",
+};
 
 static struct fb_fix_screeninfo aty128fb_fix = {
 	.id		= "ATY Rage128",
diff --git a/drivers/video/fbdev/au1200fb.c b/drivers/video/fbdev/au1200fb.c
index 40494dbdf519..18600d4e1b3f 100644
--- a/drivers/video/fbdev/au1200fb.c
+++ b/drivers/video/fbdev/au1200fb.c
@@ -1254,7 +1254,6 @@ static void set_global(u_int cmd, struct au1200_lcd_global_regs_t *pdata)
 			pdata->brightness = 30;
 		}
 		divider = (lcd->pwmdiv & 0x3FFFF) + 1;
-		hi1 = (lcd->pwmhi >> 16) + 1;
 		hi1 = (((pdata->brightness & 0xFF)+1) * divider >> 8);
 		lcd->pwmhi &= 0xFFFF;
 		lcd->pwmhi |= (hi1 << 16);
diff --git a/drivers/video/fbdev/controlfb.c b/drivers/video/fbdev/controlfb.c
index fdadef979238..080fdd2a70f3 100644
--- a/drivers/video/fbdev/controlfb.c
+++ b/drivers/video/fbdev/controlfb.c
@@ -218,7 +218,8 @@ static int controlfb_check_var (struct fb_var_screeninfo *var, struct fb_info *i
  */
 static int controlfb_set_par (struct fb_info *info)
 {
-	struct fb_info_control *p = (struct fb_info_control *) info;
+	struct fb_info_control *p =
+		container_of(info, struct fb_info_control, info);
 	struct fb_par_control par;
 	int err;
 
@@ -258,7 +259,8 @@ static int controlfb_pan_display(struct fb_var_screeninfo *var,
 				 struct fb_info *info)
 {
 	unsigned int xoffset, hstep;
-	struct fb_info_control *p = (struct fb_info_control *)info;
+	struct fb_info_control *p =
+		container_of(info, struct fb_info_control, info);
 	struct fb_par_control *par = &p->par;
 
 	/*
@@ -309,7 +311,8 @@ static int controlfb_mmap(struct fb_info *info,
 
 static int controlfb_blank(int blank_mode, struct fb_info *info)
 {
-	struct fb_info_control *p = (struct fb_info_control *) info;
+	struct fb_info_control *p =
+		container_of(info, struct fb_info_control, info);
 	unsigned ctrl;
 
 	ctrl = ld_le32(CNTRL_REG(p,ctrl));
@@ -342,7 +345,8 @@ static int controlfb_blank(int blank_mode, struct fb_info *info)
 static int controlfb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 			     u_int transp, struct fb_info *info)
 {
-	struct fb_info_control *p = (struct fb_info_control *) info;
+	struct fb_info_control *p =
+		container_of(info, struct fb_info_control, info);
 	__u8 r, g, b;
 
 	if (regno > 255)
@@ -833,7 +837,8 @@ static int control_var_to_par(struct fb_var_screeninfo *var,
 	unsigned hperiod, hssync, hsblank, hesync, heblank, piped, heq, hlfln,
 		 hserr, vperiod, vssync, vesync, veblank, vsblank, vswin, vewin;
 	unsigned long pixclock;
-	struct fb_info_control *p = (struct fb_info_control *) fb_info;
+	struct fb_info_control *p =
+		container_of(fb_info, struct fb_info_control, info);
 	struct control_regvals *r = &par->regvals;
 
 	switch (var->bits_per_pixel) {
diff --git a/drivers/video/fbdev/core/Makefile b/drivers/video/fbdev/core/Makefile
index fa306538dac2..67f28e20a892 100644
--- a/drivers/video/fbdev/core/Makefile
+++ b/drivers/video/fbdev/core/Makefile
@@ -1,4 +1,5 @@
 obj-y                             += fb_notify.o
+obj-$(CONFIG_FB_CMDLINE)          += fb_cmdline.o
 obj-$(CONFIG_FB)                  += fb.o
 fb-y                              := fbmem.o fbmon.o fbcmap.o fbsysfs.o \
                                      modedb.o fbcvt.o
diff --git a/drivers/video/fbdev/core/cfbcopyarea.c b/drivers/video/fbdev/core/cfbcopyarea.c
index bcb57235fcc7..6d4bfeecee35 100644
--- a/drivers/video/fbdev/core/cfbcopyarea.c
+++ b/drivers/video/fbdev/core/cfbcopyarea.c
@@ -55,8 +55,8 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
 	 * If you suspect bug in this function, compare it with this simple
 	 * memmove implementation.
 	 */
-	fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
-		   (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+	memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+		(char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
 	return;
 #endif
 
@@ -221,8 +221,8 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
 	 * If you suspect bug in this function, compare it with this simple
 	 * memmove implementation.
 	 */
-	fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
-		   (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+	memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+		(char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
 	return;
 #endif
 
@@ -324,7 +324,10 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
 				d0 = d0 << left | d1 >> right;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
-			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
+			if (!first)
+				FB_WRITEL(d0, dst);
+			else
+				FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
 			d0 = d1;
 			dst--;
 			n -= dst_idx+1;
diff --git a/drivers/video/fbdev/core/fb_cmdline.c b/drivers/video/fbdev/core/fb_cmdline.c
new file mode 100644
index 000000000000..39509ccd92f1
--- /dev/null
+++ b/drivers/video/fbdev/core/fb_cmdline.c
@@ -0,0 +1,110 @@
+/*
+ *  linux/drivers/video/fb_cmdline.c
+ *
+ *  Copyright (C) 2014 Intel Corp
+ *  Copyright (C) 1994 Martin Schaller
+ *
+ *	2001 - Documented with DocBook
+ *	- Brad Douglas <brad@neruo.com>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ * Authors:
+ *    Vetter <danie.vetter@ffwll.ch>
+ */
+#include <linux/init.h>
+#include <linux/fb.h>
+
+static char *video_options[FB_MAX] __read_mostly;
+static int ofonly __read_mostly;
+
+const char *fb_mode_option;
+EXPORT_SYMBOL_GPL(fb_mode_option);
+
+/**
+ * fb_get_options - get kernel boot parameters
+ * @name:   framebuffer name as it would appear in
+ *          the boot parameter line
+ *          (video=<name>:<options>)
+ * @option: the option will be stored here
+ *
+ * NOTE: Needed to maintain backwards compatibility
+ */
+int fb_get_options(const char *name, char **option)
+{
+	char *opt, *options = NULL;
+	int retval = 0;
+	int name_len = strlen(name), i;
+
+	if (name_len && ofonly && strncmp(name, "offb", 4))
+		retval = 1;
+
+	if (name_len && !retval) {
+		for (i = 0; i < FB_MAX; i++) {
+			if (video_options[i] == NULL)
+				continue;
+			if (!video_options[i][0])
+				continue;
+			opt = video_options[i];
+			if (!strncmp(name, opt, name_len) &&
+			    opt[name_len] == ':')
+				options = opt + name_len + 1;
+		}
+	}
+	/* No match, pass global option */
+	if (!options && option && fb_mode_option)
+		options = kstrdup(fb_mode_option, GFP_KERNEL);
+	if (options && !strncmp(options, "off", 3))
+		retval = 1;
+
+	if (option)
+		*option = options;
+
+	return retval;
+}
+EXPORT_SYMBOL(fb_get_options);
+
+/**
+ *	video_setup - process command line options
+ *	@options: string of options
+ *
+ *	Process command line options for frame buffer subsystem.
+ *
+ *	NOTE: This function is a __setup and __init function.
+ *            It only stores the options.  Drivers have to call
+ *            fb_get_options() as necessary.
+ *
+ *	Returns zero.
+ *
+ */
+static int __init video_setup(char *options)
+{
+	int i, global = 0;
+
+	if (!options || !*options)
+		global = 1;
+
+	if (!global && !strncmp(options, "ofonly", 6)) {
+		ofonly = 1;
+		global = 1;
+	}
+
+	if (!global && !strchr(options, ':')) {
+		fb_mode_option = options;
+		global = 1;
+	}
+
+	if (!global) {
+		for (i = 0; i < FB_MAX; i++) {
+			if (video_options[i] == NULL) {
+				video_options[i] = options;
+				break;
+			}
+		}
+	}
+
+	return 1;
+}
+__setup("video=", video_setup);
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index b5e85f6c1c26..0705d8883ede 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -1908,96 +1908,4 @@ int fb_new_modelist(struct fb_info *info)
 	return err;
 }
 
-static char *video_options[FB_MAX] __read_mostly;
-static int ofonly __read_mostly;
-
-/**
- * fb_get_options - get kernel boot parameters
- * @name:   framebuffer name as it would appear in
- *          the boot parameter line
- *          (video=<name>:<options>)
- * @option: the option will be stored here
- *
- * NOTE: Needed to maintain backwards compatibility
- */
-int fb_get_options(const char *name, char **option)
-{
-	char *opt, *options = NULL;
-	int retval = 0;
-	int name_len = strlen(name), i;
-
-	if (name_len && ofonly && strncmp(name, "offb", 4))
-		retval = 1;
-
-	if (name_len && !retval) {
-		for (i = 0; i < FB_MAX; i++) {
-			if (video_options[i] == NULL)
-				continue;
-			if (!video_options[i][0])
-				continue;
-			opt = video_options[i];
-			if (!strncmp(name, opt, name_len) &&
-			    opt[name_len] == ':')
-				options = opt + name_len + 1;
-		}
-	}
-	/* No match, pass global option */
-	if (!options && option && fb_mode_option)
-		options = kstrdup(fb_mode_option, GFP_KERNEL);
-	if (options && !strncmp(options, "off", 3))
-		retval = 1;
-
-	if (option)
-		*option = options;
-
-	return retval;
-}
-EXPORT_SYMBOL(fb_get_options);
-
-#ifndef MODULE
-/**
- *	video_setup - process command line options
- *	@options: string of options
- *
- *	Process command line options for frame buffer subsystem.
- *
- *	NOTE: This function is a __setup and __init function.
- *            It only stores the options.  Drivers have to call
- *            fb_get_options() as necessary.
- *
- *	Returns zero.
- *
- */
-static int __init video_setup(char *options)
-{
-	int i, global = 0;
-
-	if (!options || !*options)
- 		global = 1;
-
- 	if (!global && !strncmp(options, "ofonly", 6)) {
- 		ofonly = 1;
- 		global = 1;
- 	}
-
- 	if (!global && !strchr(options, ':')) {
- 		fb_mode_option = options;
- 		global = 1;
- 	}
-
- 	if (!global) {
- 		for (i = 0; i < FB_MAX; i++) {
- 			if (video_options[i] == NULL) {
- 				video_options[i] = options;
- 				break;
- 			}
-
-		}
-	}
-
-	return 1;
-}
-__setup("video=", video_setup);
-#endif
-
 MODULE_LICENSE("GPL");
diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c
index 53444ac19fe0..60c3f0a16341 100644
--- a/drivers/video/fbdev/core/fbsysfs.c
+++ b/drivers/video/fbdev/core/fbsysfs.c
@@ -485,16 +485,8 @@ static ssize_t show_bl_curve(struct device *device,
 
 	mutex_lock(&fb_info->bl_curve_mutex);
 	for (i = 0; i < FB_BACKLIGHT_LEVELS; i += 8)
-		len += snprintf(&buf[len], PAGE_SIZE,
-				"%02x %02x %02x %02x %02x %02x %02x %02x\n",
-				fb_info->bl_curve[i + 0],
-				fb_info->bl_curve[i + 1],
-				fb_info->bl_curve[i + 2],
-				fb_info->bl_curve[i + 3],
-				fb_info->bl_curve[i + 4],
-				fb_info->bl_curve[i + 5],
-				fb_info->bl_curve[i + 6],
-				fb_info->bl_curve[i + 7]);
+		len += snprintf(&buf[len], PAGE_SIZE, "%8ph\n",
+				fb_info->bl_curve + i);
 	mutex_unlock(&fb_info->bl_curve_mutex);
 
 	return len;
diff --git a/drivers/video/fbdev/core/modedb.c b/drivers/video/fbdev/core/modedb.c
index a9a907c440d7..388f7971494b 100644
--- a/drivers/video/fbdev/core/modedb.c
+++ b/drivers/video/fbdev/core/modedb.c
@@ -29,9 +29,6 @@
 #define DPRINTK(fmt, args...)
 #endif
 
-const char *fb_mode_option;
-EXPORT_SYMBOL_GPL(fb_mode_option);
-
 /*
  *  Standard video mode definitions (taken from XFree86)
  */
diff --git a/drivers/video/fbdev/cyber2000fb.c b/drivers/video/fbdev/cyber2000fb.c
index b0a950f36970..99acf538a8b8 100644
--- a/drivers/video/fbdev/cyber2000fb.c
+++ b/drivers/video/fbdev/cyber2000fb.c
@@ -159,7 +159,7 @@ cyber2000_seqw(unsigned int reg, unsigned int val, struct cfb_info *cfb)
 static void
 cyber2000fb_fillrect(struct fb_info *info, const struct fb_fillrect *rect)
 {
-	struct cfb_info *cfb = (struct cfb_info *)info;
+	struct cfb_info *cfb = container_of(info, struct cfb_info, fb);
 	unsigned long dst, col;
 
 	if (!(cfb->fb.var.accel_flags & FB_ACCELF_TEXT)) {
@@ -191,7 +191,7 @@ cyber2000fb_fillrect(struct fb_info *info, const struct fb_fillrect *rect)
 static void
 cyber2000fb_copyarea(struct fb_info *info, const struct fb_copyarea *region)
 {
-	struct cfb_info *cfb = (struct cfb_info *)info;
+	struct cfb_info *cfb = container_of(info, struct cfb_info, fb);
 	unsigned int cmd = CO_CMD_L_PATTERN_FGCOL;
 	unsigned long src, dst;
 
@@ -241,7 +241,7 @@ cyber2000fb_imageblit(struct fb_info *info, const struct fb_image *image)
 
 static int cyber2000fb_sync(struct fb_info *info)
 {
-	struct cfb_info *cfb = (struct cfb_info *)info;
+	struct cfb_info *cfb = container_of(info, struct cfb_info, fb);
 	int count = 100000;
 
 	if (!(cfb->fb.var.accel_flags & FB_ACCELF_TEXT))
@@ -276,7 +276,7 @@ static int
 cyber2000fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 		      u_int transp, struct fb_info *info)
 {
-	struct cfb_info *cfb = (struct cfb_info *)info;
+	struct cfb_info *cfb = container_of(info, struct cfb_info, fb);
 	struct fb_var_screeninfo *var = &cfb->fb.var;
 	u32 pseudo_val;
 	int ret = 1;
@@ -758,7 +758,7 @@ cyber2000fb_decode_clock(struct par_info *hw, struct cfb_info *cfb,
 static int
 cyber2000fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 {
-	struct cfb_info *cfb = (struct cfb_info *)info;
+	struct cfb_info *cfb = container_of(info, struct cfb_info, fb);
 	struct par_info hw;
 	unsigned int mem;
 	int err;
@@ -861,7 +861,7 @@ cyber2000fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 
 static int cyber2000fb_set_par(struct fb_info *info)
 {
-	struct cfb_info *cfb = (struct cfb_info *)info;
+	struct cfb_info *cfb = container_of(info, struct cfb_info, fb);
 	struct fb_var_screeninfo *var = &cfb->fb.var;
 	struct par_info hw;
 	unsigned int mem;
@@ -971,7 +971,7 @@ static int cyber2000fb_set_par(struct fb_info *info)
 static int
 cyber2000fb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
 {
-	struct cfb_info *cfb = (struct cfb_info *)info;
+	struct cfb_info *cfb = container_of(info, struct cfb_info, fb);
 
 	if (cyber2000fb_update_start(cfb, var))
 		return -EINVAL;
@@ -1007,7 +1007,7 @@ cyber2000fb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
  */
 static int cyber2000fb_blank(int blank, struct fb_info *info)
 {
-	struct cfb_info *cfb = (struct cfb_info *)info;
+	struct cfb_info *cfb = container_of(info, struct cfb_info, fb);
 	unsigned int sync = 0;
 	int i;
 
diff --git a/drivers/video/fbdev/intelfb/intelfbhw.c b/drivers/video/fbdev/intelfb/intelfbhw.c
index fbad61da359f..d31ed4e2c46f 100644
--- a/drivers/video/fbdev/intelfb/intelfbhw.c
+++ b/drivers/video/fbdev/intelfb/intelfbhw.c
@@ -1191,7 +1191,6 @@ int intelfbhw_mode_to_hw(struct intelfb_info *dinfo,
 	vsync_end = vsync_start + var->vsync_len;
 	vtotal = vsync_end + var->upper_margin;
 	vblank_start = vactive;
-	vblank_end = vtotal;
 	vblank_end = vsync_end + 1;
 
 	DBG_MSG("V: act %d, ss %d, se %d, tot %d bs %d, be %d\n",
@@ -1859,7 +1858,7 @@ void intelfbhw_cursor_init(struct intelfb_info *dinfo)
 		tmp = INREG(CURSOR_CONTROL);
 		tmp &= ~(CURSOR_FORMAT_MASK | CURSOR_GAMMA_ENABLE |
 			 CURSOR_ENABLE | CURSOR_STRIDE_MASK);
-		tmp = CURSOR_FORMAT_3C;
+		tmp |= CURSOR_FORMAT_3C;
 		OUTREG(CURSOR_CONTROL, tmp);
 		OUTREG(CURSOR_A_BASEADDR, dinfo->cursor.offset << 12);
 		tmp = (64 << CURSOR_SIZE_H_SHIFT) |
diff --git a/drivers/video/fbdev/matrox/matroxfb_base.c b/drivers/video/fbdev/matrox/matroxfb_base.c
index 7116c5309c7d..62539ca1cfa9 100644
--- a/drivers/video/fbdev/matrox/matroxfb_base.c
+++ b/drivers/video/fbdev/matrox/matroxfb_base.c
@@ -1341,19 +1341,57 @@ struct video_board {
 	struct matrox_switch* lowlevel;
 		 };
 #ifdef CONFIG_FB_MATROX_MILLENIUM
-static struct video_board vbMillennium		= {0x0800000, 0x0800000, FB_ACCEL_MATROX_MGA2064W,	&matrox_millennium};
-static struct video_board vbMillennium2		= {0x1000000, 0x0800000, FB_ACCEL_MATROX_MGA2164W,	&matrox_millennium};
-static struct video_board vbMillennium2A	= {0x1000000, 0x0800000, FB_ACCEL_MATROX_MGA2164W_AGP,	&matrox_millennium};
+static struct video_board vbMillennium = {
+	.maxvram = 0x0800000,
+	.maxdisplayable = 0x0800000,
+	.accelID = FB_ACCEL_MATROX_MGA2064W,
+	.lowlevel = &matrox_millennium
+};
+
+static struct video_board vbMillennium2 = {
+	.maxvram = 0x1000000,
+	.maxdisplayable = 0x0800000,
+	.accelID = FB_ACCEL_MATROX_MGA2164W,
+	.lowlevel = &matrox_millennium
+};
+
+static struct video_board vbMillennium2A = {
+	.maxvram = 0x1000000,
+	.maxdisplayable = 0x0800000,
+	.accelID = FB_ACCEL_MATROX_MGA2164W_AGP,
+	.lowlevel = &matrox_millennium
+};
 #endif	/* CONFIG_FB_MATROX_MILLENIUM */
 #ifdef CONFIG_FB_MATROX_MYSTIQUE
-static struct video_board vbMystique		= {0x0800000, 0x0800000, FB_ACCEL_MATROX_MGA1064SG,	&matrox_mystique};
+static struct video_board vbMystique = {
+	.maxvram = 0x0800000,
+	.maxdisplayable = 0x0800000,
+	.accelID = FB_ACCEL_MATROX_MGA1064SG,
+	.lowlevel = &matrox_mystique
+};
 #endif	/* CONFIG_FB_MATROX_MYSTIQUE */
 #ifdef CONFIG_FB_MATROX_G
-static struct video_board vbG100		= {0x0800000, 0x0800000, FB_ACCEL_MATROX_MGAG100,	&matrox_G100};
-static struct video_board vbG200		= {0x1000000, 0x1000000, FB_ACCEL_MATROX_MGAG200,	&matrox_G100};
+static struct video_board vbG100 = {
+	.maxvram = 0x0800000,
+	.maxdisplayable = 0x0800000,
+	.accelID = FB_ACCEL_MATROX_MGAG100,
+	.lowlevel = &matrox_G100
+};
+
+static struct video_board vbG200 = {
+	.maxvram = 0x1000000,
+	.maxdisplayable = 0x1000000,
+	.accelID = FB_ACCEL_MATROX_MGAG200,
+	.lowlevel = &matrox_G100
+};
 /* from doc it looks like that accelerator can draw only to low 16MB :-( Direct accesses & displaying are OK for
    whole 32MB */
-static struct video_board vbG400		= {0x2000000, 0x1000000, FB_ACCEL_MATROX_MGAG400,	&matrox_G100};
+static struct video_board vbG400 = {
+	.maxvram = 0x2000000,
+	.maxdisplayable = 0x1000000,
+	.accelID = FB_ACCEL_MATROX_MGAG400,
+	.lowlevel = &matrox_G100
+};
 #endif
 
 #define DEVF_VIDEO64BIT		0x0001
diff --git a/drivers/video/fbdev/matrox/matroxfb_maven.c b/drivers/video/fbdev/matrox/matroxfb_maven.c
index ee41a0f276b2..bf5ce04f9aea 100644
--- a/drivers/video/fbdev/matrox/matroxfb_maven.c
+++ b/drivers/video/fbdev/matrox/matroxfb_maven.c
@@ -201,21 +201,23 @@ struct matrox_pll_ctl {
 };
 
 static const struct matrox_pll_features2 maven1000_pll = {
-	 50000000,
-	300000000,
-	 5, 128,
-	 3,  32,
-	 3
+	.vco_freq_min = 50000000,
+	.vco_freq_max = 300000000,
+	.feed_div_min = 5,
+	.feed_div_max = 128,
+	.in_div_min = 3,
+	.in_div_max = 32,
+	.post_shift_max = 3
 };
 
 static const struct matrox_pll_ctl maven_PAL = {
-	540000,
-	    50
+	.ref_freq = 540000,
+	.den = 50
 };
 
 static const struct matrox_pll_ctl maven_NTSC = {
-	450450,	/* 27027000/60 == 27000000/59.94005994 */
-	    60
+	.ref_freq = 450450,	/* 27027000/60 == 27000000/59.94005994 */
+	.den = 60
 };
 
 static int matroxfb_PLL_mavenclock(const struct matrox_pll_features2* pll,
diff --git a/drivers/video/fbdev/msm/msm_fb.c b/drivers/video/fbdev/msm/msm_fb.c
index 1374803fbcd9..2979d7e72126 100644
--- a/drivers/video/fbdev/msm/msm_fb.c
+++ b/drivers/video/fbdev/msm/msm_fb.c
@@ -569,8 +569,13 @@ static int msmfb_probe(struct platform_device *pdev)
 	mutex_init(&msmfb->panel_init_lock);
 	init_waitqueue_head(&msmfb->frame_wq);
 	INIT_WORK(&msmfb->resume_work, power_on_panel);
-	msmfb->black = kzalloc(msmfb->fb->var.bits_per_pixel*msmfb->xres,
-			       GFP_KERNEL);
+	msmfb->black = devm_kzalloc(&pdev->dev,
+				    msmfb->fb->var.bits_per_pixel*msmfb->xres,
+				    GFP_KERNEL);
+	if (!msmfb->black) {
+		ret = -ENOMEM;
+		goto error_register_framebuffer;
+	}
 
 	printk(KERN_INFO "msmfb_probe() installing %d x %d panel\n",
 	       msmfb->xres, msmfb->yres);
@@ -589,6 +594,8 @@ static int msmfb_probe(struct platform_device *pdev)
 
 	msmfb->sleeping = WAKING;
 
+	platform_set_drvdata(pdev, msmfb);
+
 	return 0;
 
 error_register_framebuffer:
@@ -598,9 +605,23 @@ error_setup_fbmem:
 	return ret;
 }
 
+static int msmfb_remove(struct platform_device *pdev)
+{
+	struct msmfb_info *msmfb;
+
+	msmfb = platform_get_drvdata(pdev);
+
+	unregister_framebuffer(msmfb->fb);
+	iounmap(msmfb->fb->screen_base);
+	framebuffer_release(msmfb->fb);
+
+	return 0;
+}
+
 static struct platform_driver msm_panel_driver = {
 	/* need to write remove */
 	.probe = msmfb_probe,
+	.remove = msmfb_remove,
 	.driver = {.name = "msm_panel"},
 };
 
diff --git a/drivers/video/fbdev/mx3fb.c b/drivers/video/fbdev/mx3fb.c
index c645a0a0c341..23ec781e9a61 100644
--- a/drivers/video/fbdev/mx3fb.c
+++ b/drivers/video/fbdev/mx3fb.c
@@ -461,8 +461,7 @@ static void sdc_disable_channel(struct mx3fb_info *mx3_fbi)
 
 	spin_unlock_irqrestore(&mx3fb->lock, flags);
 
-	mx3_fbi->txd->chan->device->device_control(mx3_fbi->txd->chan,
-						   DMA_TERMINATE_ALL, 0);
+	dmaengine_terminate_all(mx3_fbi->txd->chan);
 	mx3_fbi->txd = NULL;
 	mx3_fbi->cookie = -EINVAL;
 }
@@ -1179,7 +1178,7 @@ static int mx3fb_pan_display(struct fb_var_screeninfo *var,
 
 	/*
 	 * We enable the End of Frame interrupt, which will free a tx-descriptor,
-	 * which we will need for the next device_prep_slave_sg(). The
+	 * which we will need for the next dmaengine_prep_slave_sg(). The
 	 * IRQ-handler will disable the IRQ again.
 	 */
 	init_completion(&mx3_fbi->flip_cmpl);
diff --git a/drivers/video/fbdev/omap2/dss/dispc-compat.c b/drivers/video/fbdev/omap2/dss/dispc-compat.c
index 83779c2b292a..633c461fbc6e 100644
--- a/drivers/video/fbdev/omap2/dss/dispc-compat.c
+++ b/drivers/video/fbdev/omap2/dss/dispc-compat.c
@@ -634,13 +634,14 @@ void dispc_mgr_disable_sync(enum omap_channel channel)
 		WARN_ON(1);
 }
 
+static inline void dispc_irq_wait_handler(void *data, u32 mask)
+{
+	complete((struct completion *)data);
+}
+
 int omap_dispc_wait_for_irq_interruptible_timeout(u32 irqmask,
 		unsigned long timeout)
 {
-	void dispc_irq_wait_handler(void *data, u32 mask)
-	{
-		complete((struct completion *)data);
-	}
 
 	int r;
 	DECLARE_COMPLETION_ONSTACK(completion);
diff --git a/drivers/video/fbdev/omap2/dss/dsi.c b/drivers/video/fbdev/omap2/dss/dsi.c
index 56b92444c54f..b6f6ae1d4664 100644
--- a/drivers/video/fbdev/omap2/dss/dsi.c
+++ b/drivers/video/fbdev/omap2/dss/dsi.c
@@ -2571,7 +2571,10 @@ static int dsi_sync_vc_vp(struct platform_device *dsidev, int channel)
 {
 	struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
 	DECLARE_COMPLETION_ONSTACK(completion);
-	struct dsi_packet_sent_handler_data vp_data = { dsidev, &completion };
+	struct dsi_packet_sent_handler_data vp_data = {
+		.dsidev = dsidev,
+		.completion = &completion
+	};
 	int r = 0;
 	u8 bit;
 
@@ -2617,7 +2620,10 @@ static void dsi_packet_sent_handler_l4(void *data, u32 mask)
 static int dsi_sync_vc_l4(struct platform_device *dsidev, int channel)
 {
 	DECLARE_COMPLETION_ONSTACK(completion);
-	struct dsi_packet_sent_handler_data l4_data = { dsidev, &completion };
+	struct dsi_packet_sent_handler_data l4_data = {
+		.dsidev = dsidev,
+		.completion = &completion
+	};
 	int r = 0;
 
 	r = dsi_register_isr_vc(dsidev, channel, dsi_packet_sent_handler_l4,
diff --git a/drivers/video/fbdev/omap2/dss/manager-sysfs.c b/drivers/video/fbdev/omap2/dss/manager-sysfs.c
index 37b59fe28dc8..a7414fb12830 100644
--- a/drivers/video/fbdev/omap2/dss/manager-sysfs.c
+++ b/drivers/video/fbdev/omap2/dss/manager-sysfs.c
@@ -44,6 +44,13 @@ static ssize_t manager_display_show(struct omap_overlay_manager *mgr, char *buf)
 			dssdev->name : "<none>");
 }
 
+static int manager_display_match(struct omap_dss_device *dssdev, void *data)
+{
+	const char *str = data;
+
+	return sysfs_streq(dssdev->name, str);
+}
+
 static ssize_t manager_display_store(struct omap_overlay_manager *mgr,
 		const char *buf, size_t size)
 {
@@ -52,17 +59,12 @@ static ssize_t manager_display_store(struct omap_overlay_manager *mgr,
 	struct omap_dss_device *dssdev = NULL;
 	struct omap_dss_device *old_dssdev;
 
-	int match(struct omap_dss_device *dssdev, void *data)
-	{
-		const char *str = data;
-		return sysfs_streq(dssdev->name, str);
-	}
-
 	if (buf[size-1] == '\n')
 		--len;
 
 	if (len > 0)
-		dssdev = omap_dss_find_device((void *)buf, match);
+		dssdev = omap_dss_find_device((void *)buf,
+			manager_display_match);
 
 	if (len > 0 && dssdev == NULL)
 		return -EINVAL;
diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
index ec2d132c782d..15872433e0c6 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
@@ -273,16 +273,16 @@ static struct omapfb_colormode omapfb_colormodes[] = {
 	},
 };
 
+static bool cmp_component(struct fb_bitfield *f1, struct fb_bitfield *f2)
+{
+	return f1->length == f2->length &&
+		f1->offset == f2->offset &&
+		f1->msb_right == f2->msb_right;
+}
+
 static bool cmp_var_to_colormode(struct fb_var_screeninfo *var,
 		struct omapfb_colormode *color)
 {
-	bool cmp_component(struct fb_bitfield *f1, struct fb_bitfield *f2)
-	{
-		return f1->length == f2->length &&
-			f1->offset == f2->offset &&
-			f1->msb_right == f2->msb_right;
-	}
-
 	if (var->bits_per_pixel == 0 ||
 			var->red.length == 0 ||
 			var->blue.length == 0 ||
diff --git a/drivers/video/fbdev/pvr2fb.c b/drivers/video/fbdev/pvr2fb.c
index 167cffff3d4e..7c74f58fc101 100644
--- a/drivers/video/fbdev/pvr2fb.c
+++ b/drivers/video/fbdev/pvr2fb.c
@@ -1001,7 +1001,7 @@ static int pvr2_get_param(const struct pvr2_params *p, const char *s, int val,
 
 	for (i = 0 ; i < size ; i++ ) {
 		if (s != NULL) {
-			if (!strnicmp(p[i].name, s, strlen(s)))
+			if (!strncasecmp(p[i].name, s, strlen(s)))
 				return p[i].val;
 		} else {
 			if (p[i].val == val)
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index 1ecd9cec2921..a5acca88fa63 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -138,7 +138,7 @@ static int
 pxafb_setpalettereg(u_int regno, u_int red, u_int green, u_int blue,
 		       u_int trans, struct fb_info *info)
 {
-	struct pxafb_info *fbi = (struct pxafb_info *)info;
+	struct pxafb_info *fbi = container_of(info, struct pxafb_info, fb);
 	u_int val;
 
 	if (regno >= fbi->palette_size)
@@ -183,7 +183,7 @@ static int
 pxafb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 		   u_int trans, struct fb_info *info)
 {
-	struct pxafb_info *fbi = (struct pxafb_info *)info;
+	struct pxafb_info *fbi = container_of(info, struct pxafb_info, fb);
 	unsigned int val;
 	int ret = 1;
 
@@ -456,7 +456,7 @@ static int pxafb_adjust_timing(struct pxafb_info *fbi,
  */
 static int pxafb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 {
-	struct pxafb_info *fbi = (struct pxafb_info *)info;
+	struct pxafb_info *fbi = container_of(info, struct pxafb_info, fb);
 	struct pxafb_mach_info *inf = dev_get_platdata(fbi->dev);
 	int err;
 
@@ -494,7 +494,7 @@ static int pxafb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
  */
 static int pxafb_set_par(struct fb_info *info)
 {
-	struct pxafb_info *fbi = (struct pxafb_info *)info;
+	struct pxafb_info *fbi = container_of(info, struct pxafb_info, fb);
 	struct fb_var_screeninfo *var = &info->var;
 
 	if (var->bits_per_pixel >= 16)
@@ -533,7 +533,7 @@ static int pxafb_set_par(struct fb_info *info)
 static int pxafb_pan_display(struct fb_var_screeninfo *var,
 			     struct fb_info *info)
 {
-	struct pxafb_info *fbi = (struct pxafb_info *)info;
+	struct pxafb_info *fbi = container_of(info, struct pxafb_info, fb);
 	struct fb_var_screeninfo newvar;
 	int dma = DMA_MAX + DMA_BASE;
 
@@ -566,7 +566,7 @@ static int pxafb_pan_display(struct fb_var_screeninfo *var,
  */
 static int pxafb_blank(int blank, struct fb_info *info)
 {
-	struct pxafb_info *fbi = (struct pxafb_info *)info;
+	struct pxafb_info *fbi = container_of(info, struct pxafb_info, fb);
 	int i;
 
 	switch (blank) {
@@ -725,7 +725,7 @@ static struct pxafb_layer_ops ofb_ops[] = {
 
 static int overlayfb_open(struct fb_info *info, int user)
 {
-	struct pxafb_layer *ofb = (struct pxafb_layer *)info;
+	struct pxafb_layer *ofb = container_of(info, struct pxafb_layer, fb);
 
 	/* no support for framebuffer console on overlay */
 	if (user == 0)
@@ -743,7 +743,7 @@ static int overlayfb_open(struct fb_info *info, int user)
 
 static int overlayfb_release(struct fb_info *info, int user)
 {
-	struct pxafb_layer *ofb = (struct pxafb_layer*) info;
+	struct pxafb_layer *ofb = container_of(info, struct pxafb_layer, fb);
 
 	if (ofb->usage == 1) {
 		ofb->ops->disable(ofb);
@@ -760,7 +760,7 @@ static int overlayfb_release(struct fb_info *info, int user)
 static int overlayfb_check_var(struct fb_var_screeninfo *var,
 			       struct fb_info *info)
 {
-	struct pxafb_layer *ofb = (struct pxafb_layer *)info;
+	struct pxafb_layer *ofb = container_of(info, struct pxafb_layer, fb);
 	struct fb_var_screeninfo *base_var = &ofb->fbi->fb.var;
 	int xpos, ypos, pfor, bpp;
 
@@ -836,7 +836,7 @@ static int overlayfb_check_video_memory(struct pxafb_layer *ofb)
 
 static int overlayfb_set_par(struct fb_info *info)
 {
-	struct pxafb_layer *ofb = (struct pxafb_layer *)info;
+	struct pxafb_layer *ofb = container_of(info, struct pxafb_layer, fb);
 	struct fb_var_screeninfo *var = &info->var;
 	int xpos, ypos, pfor, bpp, ret;
 
diff --git a/drivers/video/fbdev/riva/riva_hw.c b/drivers/video/fbdev/riva/riva_hw.c
index 78fdbf5178d7..8bdf37f3013b 100644
--- a/drivers/video/fbdev/riva/riva_hw.c
+++ b/drivers/video/fbdev/riva/riva_hw.c
@@ -430,7 +430,6 @@ static char nv3_arb(nv3_fifo_info * res_info, nv3_sim_state * state,  nv3_arb_in
     int mmisses, gmisses, vmisses, eburst_size, mburst_size;
     int refresh_cycle;
 
-    refresh_cycle = 0;
     refresh_cycle = 2*(state->mclk_khz/state->pclk_khz) + 5;
     mmisses = 2;
     if (state->mem_aligned) gmisses = 2;
diff --git a/drivers/video/fbdev/s3c2410fb.c b/drivers/video/fbdev/s3c2410fb.c
index 43c63a4f3178..e350eb57f11d 100644
--- a/drivers/video/fbdev/s3c2410fb.c
+++ b/drivers/video/fbdev/s3c2410fb.c
@@ -601,12 +601,12 @@ static int s3c2410fb_debug_store(struct device *dev,
 	if (len < 1)
 		return -EINVAL;
 
-	if (strnicmp(buf, "on", 2) == 0 ||
-	    strnicmp(buf, "1", 1) == 0) {
+	if (strncasecmp(buf, "on", 2) == 0 ||
+	    strncasecmp(buf, "1", 1) == 0) {
 		debug = 1;
 		dev_dbg(dev, "s3c2410fb: Debug On");
-	} else if (strnicmp(buf, "off", 3) == 0 ||
-		   strnicmp(buf, "0", 1) == 0) {
+	} else if (strncasecmp(buf, "off", 3) == 0 ||
+		   strncasecmp(buf, "0", 1) == 0) {
 		debug = 0;
 		dev_dbg(dev, "s3c2410fb: Debug Off");
 	} else {
diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c
index 580c444ec301..9690216d38ff 100644
--- a/drivers/video/fbdev/sa1100fb.c
+++ b/drivers/video/fbdev/sa1100fb.c
@@ -268,7 +268,8 @@ static int
 sa1100fb_setpalettereg(u_int regno, u_int red, u_int green, u_int blue,
 		       u_int trans, struct fb_info *info)
 {
-	struct sa1100fb_info *fbi = (struct sa1100fb_info *)info;
+	struct sa1100fb_info *fbi =
+		container_of(info, struct sa1100fb_info, fb);
 	u_int val, ret = 1;
 
 	if (regno < fbi->palette_size) {
@@ -289,7 +290,8 @@ static int
 sa1100fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 		   u_int trans, struct fb_info *info)
 {
-	struct sa1100fb_info *fbi = (struct sa1100fb_info *)info;
+	struct sa1100fb_info *fbi =
+		container_of(info, struct sa1100fb_info, fb);
 	unsigned int val;
 	int ret = 1;
 
@@ -366,7 +368,8 @@ static inline unsigned int sa1100fb_display_dma_period(struct fb_var_screeninfo
 static int
 sa1100fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 {
-	struct sa1100fb_info *fbi = (struct sa1100fb_info *)info;
+	struct sa1100fb_info *fbi =
+		container_of(info, struct sa1100fb_info, fb);
 	int rgbidx;
 
 	if (var->xres < MIN_XRES)
@@ -433,7 +436,8 @@ static void sa1100fb_set_visual(struct sa1100fb_info *fbi, u32 visual)
  */
 static int sa1100fb_set_par(struct fb_info *info)
 {
-	struct sa1100fb_info *fbi = (struct sa1100fb_info *)info;
+	struct sa1100fb_info *fbi =
+		container_of(info, struct sa1100fb_info, fb);
 	struct fb_var_screeninfo *var = &info->var;
 	unsigned long palette_mem_size;
 
@@ -526,7 +530,8 @@ sa1100fb_set_cmap(struct fb_cmap *cmap, int kspc, int con,
  */
 static int sa1100fb_blank(int blank, struct fb_info *info)
 {
-	struct sa1100fb_info *fbi = (struct sa1100fb_info *)info;
+	struct sa1100fb_info *fbi =
+		container_of(info, struct sa1100fb_info, fb);
 	int i;
 
 	dev_dbg(fbi->dev, "sa1100fb_blank: blank=%d\n", blank);
@@ -555,7 +560,8 @@ static int sa1100fb_blank(int blank, struct fb_info *info)
 static int sa1100fb_mmap(struct fb_info *info,
 			 struct vm_area_struct *vma)
 {
-	struct sa1100fb_info *fbi = (struct sa1100fb_info *)info;
+	struct sa1100fb_info *fbi =
+		container_of(info, struct sa1100fb_info, fb);
 	unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
 
 	if (off < info->fix.smem_len) {
diff --git a/drivers/video/fbdev/sh_mobile_hdmi.c b/drivers/video/fbdev/sh_mobile_hdmi.c
index 9a33ee0413fb..7c72a3f02056 100644
--- a/drivers/video/fbdev/sh_mobile_hdmi.c
+++ b/drivers/video/fbdev/sh_mobile_hdmi.c
@@ -281,6 +281,7 @@ struct sh_hdmi {
 	u8 edid_block_addr;
 	u8 edid_segment_nr;
 	u8 edid_blocks;
+	int irq;
 	struct clk *hdmi_clk;
 	struct device *dev;
 	struct delayed_work edid_work;
@@ -1299,6 +1300,7 @@ static int __init sh_hdmi_probe(struct platform_device *pdev)
 	hdmi->dev = &pdev->dev;
 	hdmi->entity.owner = THIS_MODULE;
 	hdmi->entity.ops = &sh_hdmi_ops;
+	hdmi->irq = irq;
 
 	hdmi->hdmi_clk = clk_get(&pdev->dev, "ick");
 	if (IS_ERR(hdmi->hdmi_clk)) {
@@ -1415,12 +1417,11 @@ static int __exit sh_hdmi_remove(struct platform_device *pdev)
 {
 	struct sh_hdmi *hdmi = entity_to_sh_hdmi(platform_get_drvdata(pdev));
 	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	int irq = platform_get_irq(pdev, 0);
 
 	snd_soc_unregister_codec(&pdev->dev);
 
 	/* No new work will be scheduled, wait for running ISR */
-	free_irq(irq, hdmi);
+	free_irq(hdmi->irq, hdmi);
 	/* Wait for already scheduled work */
 	cancel_delayed_work_sync(&hdmi->edid_work);
 	pm_runtime_put(&pdev->dev);
@@ -1435,10 +1436,49 @@ static int __exit sh_hdmi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int sh_hdmi_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct sh_hdmi *hdmi = entity_to_sh_hdmi(platform_get_drvdata(pdev));
+
+	disable_irq(hdmi->irq);
+	/* Wait for already scheduled work */
+	cancel_delayed_work_sync(&hdmi->edid_work);
+	return 0;
+}
+
+static int sh_hdmi_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct sh_mobile_hdmi_info *pdata = dev_get_platdata(dev);
+	struct sh_hdmi *hdmi = entity_to_sh_hdmi(platform_get_drvdata(pdev));
+
+	/* Re-init interrupt polarity */
+	if (pdata->flags & HDMI_OUTPUT_PUSH_PULL)
+		hdmi_bit_set(hdmi, 0x02, 0x02, HDMI_SYSTEM_CTRL);
+
+	if (pdata->flags & HDMI_OUTPUT_POLARITY_HI)
+		hdmi_bit_set(hdmi, 0x01, 0x01, HDMI_SYSTEM_CTRL);
+
+	/* Re-init htop1 */
+	if (hdmi->htop1)
+		sh_hdmi_htop1_init(hdmi);
+
+	/* Now it's safe to enable interrupts again */
+	enable_irq(hdmi->irq);
+	return 0;
+}
+
+static const struct dev_pm_ops sh_hdmi_pm_ops = {
+	.suspend	= sh_hdmi_suspend,
+	.resume		= sh_hdmi_resume,
+};
+
 static struct platform_driver sh_hdmi_driver = {
 	.remove		= __exit_p(sh_hdmi_remove),
 	.driver = {
 		.name	= "sh-mobile-hdmi",
+		.pm	= &sh_hdmi_pm_ops,
 	},
 };
 
diff --git a/drivers/video/fbdev/sis/init301.c b/drivers/video/fbdev/sis/init301.c
index a89e3cafd5ad..295e0dedaf1f 100644
--- a/drivers/video/fbdev/sis/init301.c
+++ b/drivers/video/fbdev/sis/init301.c
@@ -1714,7 +1714,7 @@ SiS_GetLCDResInfo(struct SiS_Private *SiS_Pr, unsigned short ModeNo, unsigned sh
 			       SiS_Pr->PanelVCLKIdx315 = VCLK81_315; /* ? */
 			    } else {
 			       SiS_Pr->PanelHT   = 1688; SiS_Pr->PanelVT   =  802;
-			       SiS_Pr->PanelHRS  =   48; SiS_Pr->PanelHRS  =  112;
+			       SiS_Pr->PanelHRS  =   48; SiS_Pr->PanelHRE  =  112;
 			       SiS_Pr->PanelVRS  =    3; SiS_Pr->PanelVRE  =    6;
 			       SiS_Pr->PanelVCLKIdx300 = VCLK81_300;
 			       SiS_Pr->PanelVCLKIdx315 = VCLK81_315;
diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c
index 3f12a2dd959a..e5d11b1892e8 100644
--- a/drivers/video/fbdev/sis/sis_main.c
+++ b/drivers/video/fbdev/sis/sis_main.c
@@ -162,7 +162,7 @@ static void sisfb_search_mode(char *name, bool quiet)
 		return;
 	}
 
-	if(!strnicmp(name, sisbios_mode[MODE_INDEX_NONE].name, strlen(name))) {
+	if(!strncasecmp(name, sisbios_mode[MODE_INDEX_NONE].name, strlen(name))) {
 		if(!quiet)
 			printk(KERN_ERR "sisfb: Mode 'none' not supported anymore. Using default.\n");
 
@@ -201,7 +201,7 @@ static void sisfb_search_mode(char *name, bool quiet)
 
 	i = 0; j = 0;
 	while(sisbios_mode[i].mode_no[0] != 0) {
-		if(!strnicmp(nameptr, sisbios_mode[i++].name, strlen(nameptr))) {
+		if(!strncasecmp(nameptr, sisbios_mode[i++].name, strlen(nameptr))) {
 			if(sisfb_fstn) {
 				if(sisbios_mode[i-1].mode_no[1] == 0x50 ||
 				   sisbios_mode[i-1].mode_no[1] == 0x56 ||
@@ -262,7 +262,7 @@ sisfb_search_crt2type(const char *name)
 	if(name == NULL) return;
 
 	while(sis_crt2type[i].type_no != -1) {
-		if(!strnicmp(name, sis_crt2type[i].name, strlen(sis_crt2type[i].name))) {
+		if(!strncasecmp(name, sis_crt2type[i].name, strlen(sis_crt2type[i].name))) {
 			sisfb_crt2type = sis_crt2type[i].type_no;
 			sisfb_tvplug = sis_crt2type[i].tvplug_no;
 			sisfb_crt2flags = sis_crt2type[i].flags;
@@ -289,7 +289,7 @@ sisfb_search_tvstd(const char *name)
 		return;
 
 	while(sis_tvtype[i].type_no != -1) {
-		if(!strnicmp(name, sis_tvtype[i].name, strlen(sis_tvtype[i].name))) {
+		if(!strncasecmp(name, sis_tvtype[i].name, strlen(sis_tvtype[i].name))) {
 			sisfb_tvstd = sis_tvtype[i].type_no;
 			break;
 		}
@@ -308,12 +308,12 @@ sisfb_search_specialtiming(const char *name)
 	if(name == NULL)
 		return;
 
-	if(!strnicmp(name, "none", 4)) {
+	if(!strncasecmp(name, "none", 4)) {
 		sisfb_specialtiming = CUT_FORCENONE;
 		printk(KERN_DEBUG "sisfb: Special timing disabled\n");
 	} else {
 		while(mycustomttable[i].chipID != 0) {
-			if(!strnicmp(name,mycustomttable[i].optionName,
+			if(!strncasecmp(name,mycustomttable[i].optionName,
 			   strlen(mycustomttable[i].optionName))) {
 				sisfb_specialtiming = mycustomttable[i].SpecialID;
 				found = true;
@@ -3952,68 +3952,68 @@ static int __init sisfb_setup(char *options)
 
 		if(!(*this_opt)) continue;
 
-		if(!strnicmp(this_opt, "off", 3)) {
+		if(!strncasecmp(this_opt, "off", 3)) {
 			sisfb_off = 1;
-		} else if(!strnicmp(this_opt, "forcecrt2type:", 14)) {
+		} else if(!strncasecmp(this_opt, "forcecrt2type:", 14)) {
 			/* Need to check crt2 type first for fstn/dstn */
 			sisfb_search_crt2type(this_opt + 14);
-		} else if(!strnicmp(this_opt, "tvmode:",7)) {
+		} else if(!strncasecmp(this_opt, "tvmode:",7)) {
 			sisfb_search_tvstd(this_opt + 7);
-		} else if(!strnicmp(this_opt, "tvstandard:",11)) {
+		} else if(!strncasecmp(this_opt, "tvstandard:",11)) {
 			sisfb_search_tvstd(this_opt + 11);
-		} else if(!strnicmp(this_opt, "mode:", 5)) {
+		} else if(!strncasecmp(this_opt, "mode:", 5)) {
 			sisfb_search_mode(this_opt + 5, false);
-		} else if(!strnicmp(this_opt, "vesa:", 5)) {
+		} else if(!strncasecmp(this_opt, "vesa:", 5)) {
 			sisfb_search_vesamode(simple_strtoul(this_opt + 5, NULL, 0), false);
-		} else if(!strnicmp(this_opt, "rate:", 5)) {
+		} else if(!strncasecmp(this_opt, "rate:", 5)) {
 			sisfb_parm_rate = simple_strtoul(this_opt + 5, NULL, 0);
-		} else if(!strnicmp(this_opt, "forcecrt1:", 10)) {
+		} else if(!strncasecmp(this_opt, "forcecrt1:", 10)) {
 			sisfb_forcecrt1 = (int)simple_strtoul(this_opt + 10, NULL, 0);
-		} else if(!strnicmp(this_opt, "mem:",4)) {
+		} else if(!strncasecmp(this_opt, "mem:",4)) {
 			sisfb_parm_mem = simple_strtoul(this_opt + 4, NULL, 0);
-		} else if(!strnicmp(this_opt, "pdc:", 4)) {
+		} else if(!strncasecmp(this_opt, "pdc:", 4)) {
 			sisfb_pdc = simple_strtoul(this_opt + 4, NULL, 0);
-		} else if(!strnicmp(this_opt, "pdc1:", 5)) {
+		} else if(!strncasecmp(this_opt, "pdc1:", 5)) {
 			sisfb_pdca = simple_strtoul(this_opt + 5, NULL, 0);
-		} else if(!strnicmp(this_opt, "noaccel", 7)) {
+		} else if(!strncasecmp(this_opt, "noaccel", 7)) {
 			sisfb_accel = 0;
-		} else if(!strnicmp(this_opt, "accel", 5)) {
+		} else if(!strncasecmp(this_opt, "accel", 5)) {
 			sisfb_accel = -1;
-		} else if(!strnicmp(this_opt, "noypan", 6)) {
+		} else if(!strncasecmp(this_opt, "noypan", 6)) {
 			sisfb_ypan = 0;
-		} else if(!strnicmp(this_opt, "ypan", 4)) {
+		} else if(!strncasecmp(this_opt, "ypan", 4)) {
 			sisfb_ypan = -1;
-		} else if(!strnicmp(this_opt, "nomax", 5)) {
+		} else if(!strncasecmp(this_opt, "nomax", 5)) {
 			sisfb_max = 0;
-		} else if(!strnicmp(this_opt, "max", 3)) {
+		} else if(!strncasecmp(this_opt, "max", 3)) {
 			sisfb_max = -1;
-		} else if(!strnicmp(this_opt, "userom:", 7)) {
+		} else if(!strncasecmp(this_opt, "userom:", 7)) {
 			sisfb_userom = (int)simple_strtoul(this_opt + 7, NULL, 0);
-		} else if(!strnicmp(this_opt, "useoem:", 7)) {
+		} else if(!strncasecmp(this_opt, "useoem:", 7)) {
 			sisfb_useoem = (int)simple_strtoul(this_opt + 7, NULL, 0);
-		} else if(!strnicmp(this_opt, "nocrt2rate", 10)) {
+		} else if(!strncasecmp(this_opt, "nocrt2rate", 10)) {
 			sisfb_nocrt2rate = 1;
-		} else if(!strnicmp(this_opt, "scalelcd:", 9)) {
+		} else if(!strncasecmp(this_opt, "scalelcd:", 9)) {
 			unsigned long temp = 2;
 			temp = simple_strtoul(this_opt + 9, NULL, 0);
 			if((temp == 0) || (temp == 1)) {
 			   sisfb_scalelcd = temp ^ 1;
 			}
-		} else if(!strnicmp(this_opt, "tvxposoffset:", 13)) {
+		} else if(!strncasecmp(this_opt, "tvxposoffset:", 13)) {
 			int temp = 0;
 			temp = (int)simple_strtol(this_opt + 13, NULL, 0);
 			if((temp >= -32) && (temp <= 32)) {
 			   sisfb_tvxposoffset = temp;
 			}
-		} else if(!strnicmp(this_opt, "tvyposoffset:", 13)) {
+		} else if(!strncasecmp(this_opt, "tvyposoffset:", 13)) {
 			int temp = 0;
 			temp = (int)simple_strtol(this_opt + 13, NULL, 0);
 			if((temp >= -32) && (temp <= 32)) {
 			   sisfb_tvyposoffset = temp;
 			}
-		} else if(!strnicmp(this_opt, "specialtiming:", 14)) {
+		} else if(!strncasecmp(this_opt, "specialtiming:", 14)) {
 			sisfb_search_specialtiming(this_opt + 14);
-		} else if(!strnicmp(this_opt, "lvdshl:", 7)) {
+		} else if(!strncasecmp(this_opt, "lvdshl:", 7)) {
 			int temp = 4;
 			temp = simple_strtoul(this_opt + 7, NULL, 0);
 			if((temp >= 0) && (temp <= 3)) {
@@ -4022,9 +4022,9 @@ static int __init sisfb_setup(char *options)
 		} else if(this_opt[0] >= '0' && this_opt[0] <= '9') {
 			sisfb_search_mode(this_opt, true);
 #if !defined(__i386__) && !defined(__x86_64__)
-		} else if(!strnicmp(this_opt, "resetcard", 9)) {
+		} else if(!strncasecmp(this_opt, "resetcard", 9)) {
 			sisfb_resetcard = 1;
-	        } else if(!strnicmp(this_opt, "videoram:", 9)) {
+	        } else if(!strncasecmp(this_opt, "videoram:", 9)) {
 			sisfb_videoram = simple_strtoul(this_opt + 9, NULL, 0);
 #endif
 		} else {
@@ -5830,7 +5830,7 @@ static int sisfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			ivideo->cardnumber++;
 	}
 
-	strncpy(ivideo->myid, chipinfo->chip_name, 30);
+	strlcpy(ivideo->myid, chipinfo->chip_name, sizeof(ivideo->myid));
 
 	ivideo->warncount = 0;
 	ivideo->chip_id = pdev->device;
diff --git a/drivers/video/fbdev/sm501fb.c b/drivers/video/fbdev/sm501fb.c
index c2c8eb668784..9e74e8fbe074 100644
--- a/drivers/video/fbdev/sm501fb.c
+++ b/drivers/video/fbdev/sm501fb.c
@@ -1187,9 +1187,9 @@ static ssize_t sm501fb_crtsrc_store(struct device *dev,
 	if (len < 1)
 		return -EINVAL;
 
-	if (strnicmp(buf, "crt", 3) == 0)
+	if (strncasecmp(buf, "crt", 3) == 0)
 		head = HEAD_CRT;
-	else if (strnicmp(buf, "panel", 5) == 0)
+	else if (strncasecmp(buf, "panel", 5) == 0)
 		head = HEAD_PANEL;
 	else
 		return -EINVAL;
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index cfe8a2f905c5..86621fabbb8b 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -918,7 +918,7 @@ static int
 stifb_setcolreg(u_int regno, u_int red, u_int green,
 	      u_int blue, u_int transp, struct fb_info *info)
 {
-	struct stifb_info *fb = (struct stifb_info *) info;
+	struct stifb_info *fb = container_of(info, struct stifb_info, info);
 	u32 color;
 
 	if (regno >= NR_PALETTE)
@@ -978,7 +978,7 @@ stifb_setcolreg(u_int regno, u_int red, u_int green,
 static int
 stifb_blank(int blank_mode, struct fb_info *info)
 {
-	struct stifb_info *fb = (struct stifb_info *) info;
+	struct stifb_info *fb = container_of(info, struct stifb_info, info);
 	int enable = (blank_mode == 0) ? ENABLE : DISABLE;
 
 	switch (fb->id) {
diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c
index 77b890e4d296..046d51d83d74 100644
--- a/drivers/video/fbdev/udlfb.c
+++ b/drivers/video/fbdev/udlfb.c
@@ -1528,11 +1528,8 @@ static int dlfb_parse_vendor_descriptor(struct dlfb_data *dev,
 	}
 
 	if (total_len > 5) {
-		pr_info("vendor descriptor length:%x data:%02x %02x %02x %02x" \
-			"%02x %02x %02x %02x %02x %02x %02x\n",
-			total_len, desc[0],
-			desc[1], desc[2], desc[3], desc[4], desc[5], desc[6],
-			desc[7], desc[8], desc[9], desc[10]);
+		pr_info("vendor descriptor length:%x data:%11ph\n", total_len,
+			desc);
 
 		if ((desc[0] != total_len) || /* descriptor length */
 		    (desc[1] != 0x5f) ||   /* vendor descriptor type */
diff --git a/drivers/video/fbdev/valkyriefb.c b/drivers/video/fbdev/valkyriefb.c
index 97cb9bd1d1dd..275fb98236d3 100644
--- a/drivers/video/fbdev/valkyriefb.c
+++ b/drivers/video/fbdev/valkyriefb.c
@@ -136,7 +136,8 @@ static struct fb_ops valkyriefb_ops = {
 /* Sets the video mode according to info->var */
 static int valkyriefb_set_par(struct fb_info *info)
 {
-	struct fb_info_valkyrie *p = (struct fb_info_valkyrie *) info;
+	struct fb_info_valkyrie *p =
+		container_of(info, struct fb_info_valkyrie, info);
 	volatile struct valkyrie_regs __iomem *valkyrie_regs = p->valkyrie_regs;
 	struct fb_par_valkyrie *par = info->par;
 	struct valkyrie_regvals	*init;
@@ -194,7 +195,8 @@ valkyriefb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
  */
 static int valkyriefb_blank(int blank_mode, struct fb_info *info)
 {
-	struct fb_info_valkyrie *p = (struct fb_info_valkyrie *) info;
+	struct fb_info_valkyrie *p =
+		container_of(info, struct fb_info_valkyrie, info);
 	struct fb_par_valkyrie *par = info->par;
 	struct valkyrie_regvals	*init = par->init;
 
@@ -226,7 +228,8 @@ static int valkyriefb_blank(int blank_mode, struct fb_info *info)
 static int valkyriefb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 			     u_int transp, struct fb_info *info)
 {
-	struct fb_info_valkyrie *p = (struct fb_info_valkyrie *) info;
+	struct fb_info_valkyrie *p =
+		container_of(info, struct fb_info_valkyrie, info);
 	volatile struct cmap_regs __iomem *cmap_regs = p->cmap_regs;
 	struct fb_par_valkyrie *par = info->par;
 
@@ -263,10 +266,10 @@ static inline int valkyrie_vram_reqd(int video_mode, int color_mode)
 
 static void set_valkyrie_clock(unsigned char *params)
 {
+#ifdef CONFIG_ADB_CUDA
 	struct adb_request req;
 	int i;
 
-#ifdef CONFIG_ADB_CUDA
 	for (i = 0; i < 3; ++i) {
 		cuda_request(&req, NULL, 5, CUDA_PACKET, CUDA_GET_SET_IIC,
 			     0x50, i + 1, params[i]);
@@ -465,7 +468,8 @@ static int valkyrie_var_to_par(struct fb_var_screeninfo *var,
 {
 	int vmode, cmode;
 	struct valkyrie_regvals *init;
-	struct fb_info_valkyrie *p = (struct fb_info_valkyrie *) fb_info;
+	struct fb_info_valkyrie *p =
+		container_of(fb_info, struct fb_info_valkyrie, info);
 
 	if (mac_var_to_vmode(var, &vmode, &cmode) != 0) {
 		printk(KERN_ERR "valkyriefb: can't do %dx%dx%d.\n",
diff --git a/drivers/video/fbdev/vermilion/vermilion.c b/drivers/video/fbdev/vermilion/vermilion.c
index 048a66640b03..5f930aeccf1f 100644
--- a/drivers/video/fbdev/vermilion/vermilion.c
+++ b/drivers/video/fbdev/vermilion/vermilion.c
@@ -481,7 +481,6 @@ static int vml_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	default:
 		err = -ENODEV;
 		goto out_err_1;
-		break;
 	}
 
 	info = &vinfo->info;
diff --git a/drivers/video/fbdev/via/via-gpio.c b/drivers/video/fbdev/via/via-gpio.c
index e408679081ab..6f433b8cee12 100644
--- a/drivers/video/fbdev/via/via-gpio.c
+++ b/drivers/video/fbdev/via/via-gpio.c
@@ -270,7 +270,7 @@ static int viafb_gpio_probe(struct platform_device *platdev)
 static int viafb_gpio_remove(struct platform_device *platdev)
 {
 	unsigned long flags;
-	int ret = 0, i;
+	int i;
 
 #ifdef CONFIG_PM
 	viafb_pm_unregister(&viafb_gpio_pm_hooks);
@@ -280,11 +280,7 @@ static int viafb_gpio_remove(struct platform_device *platdev)
 	 * Get unregistered.
 	 */
 	if (viafb_gpio_config.gpio_chip.ngpio > 0) {
-		ret = gpiochip_remove(&viafb_gpio_config.gpio_chip);
-		if (ret) { /* Somebody still using it? */
-			printk(KERN_ERR "Viafb: GPIO remove failed\n");
-			return ret;
-		}
+		gpiochip_remove(&viafb_gpio_config.gpio_chip);
 	}
 	/*
 	 * Disable the ports.
@@ -294,7 +290,7 @@ static int viafb_gpio_remove(struct platform_device *platdev)
 		viafb_gpio_disable(viafb_gpio_config.active_gpios[i]);
 	viafb_gpio_config.gpio_chip.ngpio = 0;
 	spin_unlock_irqrestore(&viafb_gpio_config.vdev->reg_lock, flags);
-	return ret;
+	return 0;
 }
 
 static struct platform_driver via_gpio_driver = {
diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c
index 901014bbc821..09dc44736c1a 100644
--- a/drivers/video/fbdev/xen-fbfront.c
+++ b/drivers/video/fbdev/xen-fbfront.c
@@ -684,12 +684,13 @@ static const struct xenbus_device_id xenfb_ids[] = {
 	{ "" }
 };
 
-static DEFINE_XENBUS_DRIVER(xenfb, ,
+static struct xenbus_driver xenfb_driver = {
+	.ids = xenfb_ids,
 	.probe = xenfb_probe,
 	.remove = xenfb_remove,
 	.resume = xenfb_resume,
 	.otherend_changed = xenfb_backend_changed,
-);
+};
 
 static int __init xenfb_init(void)
 {
diff --git a/drivers/video/of_display_timing.c b/drivers/video/of_display_timing.c
index 5c098d5b4043..32d8275e4c88 100644
--- a/drivers/video/of_display_timing.c
+++ b/drivers/video/of_display_timing.c
@@ -233,8 +233,7 @@ struct display_timings *of_get_display_timings(struct device_node *np)
 	return disp;
 
 timingfail:
-	if (native_mode)
-		of_node_put(native_mode);
+	of_node_put(native_mode);
 	display_timings_release(disp);
 	disp = NULL;
 entryfail:
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index c6683f2e396c..00b228638274 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -25,6 +25,7 @@ config VIRTIO_PCI
 config VIRTIO_BALLOON
 	tristate "Virtio balloon driver"
 	depends on VIRTIO
+	select MEMORY_BALLOON
 	---help---
 	 This driver supports increasing and decreasing the amount
 	 of memory within a KVM guest.
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index fed0ce198ae3..df598dd8c5c8 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -117,6 +117,43 @@ void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
 }
 EXPORT_SYMBOL_GPL(virtio_check_driver_offered_feature);
 
+static void __virtio_config_changed(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	if (!dev->config_enabled)
+		dev->config_change_pending = true;
+	else if (drv && drv->config_changed)
+		drv->config_changed(dev);
+}
+
+void virtio_config_changed(struct virtio_device *dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->config_lock, flags);
+	__virtio_config_changed(dev);
+	spin_unlock_irqrestore(&dev->config_lock, flags);
+}
+EXPORT_SYMBOL_GPL(virtio_config_changed);
+
+static void virtio_config_disable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_enabled = false;
+	spin_unlock_irq(&dev->config_lock);
+}
+
+static void virtio_config_enable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_enabled = true;
+	if (dev->config_change_pending)
+		__virtio_config_changed(dev);
+	dev->config_change_pending = false;
+	spin_unlock_irq(&dev->config_lock);
+}
+
 static int virtio_dev_probe(struct device *_d)
 {
 	int err, i;
@@ -153,6 +190,8 @@ static int virtio_dev_probe(struct device *_d)
 		add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
 		if (drv->scan)
 			drv->scan(dev);
+
+		virtio_config_enable(dev);
 	}
 
 	return err;
@@ -163,6 +202,8 @@ static int virtio_dev_remove(struct device *_d)
 	struct virtio_device *dev = dev_to_virtio(_d);
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 
+	virtio_config_disable(dev);
+
 	drv->remove(dev);
 
 	/* Driver should have reset device. */
@@ -211,6 +252,10 @@ int register_virtio_device(struct virtio_device *dev)
 	dev->index = err;
 	dev_set_name(&dev->dev, "virtio%u", dev->index);
 
+	spin_lock_init(&dev->config_lock);
+	dev->config_enabled = false;
+	dev->config_change_pending = false;
+
 	/* We always start by resetting the device, in case a previous
 	 * driver messed it up.  This also tests that code path a little. */
 	dev->config->reset(dev);
@@ -239,6 +284,64 @@ void unregister_virtio_device(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(unregister_virtio_device);
 
+#ifdef CONFIG_PM_SLEEP
+int virtio_device_freeze(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	virtio_config_disable(dev);
+
+	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
+
+	if (drv && drv->freeze)
+		return drv->freeze(dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_freeze);
+
+int virtio_device_restore(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	/* We always start by resetting the device, in case a previous
+	 * driver messed it up. */
+	dev->config->reset(dev);
+
+	/* Acknowledge that we've seen the device. */
+	add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+	/* Maybe driver failed before freeze.
+	 * Restore the failed status, for debugging. */
+	if (dev->failed)
+		add_status(dev, VIRTIO_CONFIG_S_FAILED);
+
+	if (!drv)
+		return 0;
+
+	/* We have a driver! */
+	add_status(dev, VIRTIO_CONFIG_S_DRIVER);
+
+	dev->config->finalize_features(dev);
+
+	if (drv->restore) {
+		int ret = drv->restore(dev);
+		if (ret) {
+			add_status(dev, VIRTIO_CONFIG_S_FAILED);
+			return ret;
+		}
+	}
+
+	/* Finally, tell the device we're all set */
+	add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
+
+	virtio_config_enable(dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_restore);
+#endif
+
 static int virtio_init(void)
 {
 	if (bus_register(&virtio_bus) != 0)
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 25ebe8eecdb7..c9703d4d6f67 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -59,7 +59,7 @@ struct virtio_balloon
 	 * Each page on this list adds VIRTIO_BALLOON_PAGES_PER_PAGE
 	 * to num_pages above.
 	 */
-	struct balloon_dev_info *vb_dev_info;
+	struct balloon_dev_info vb_dev_info;
 
 	/* Synchronize access/update to this struct virtio_balloon elements */
 	struct mutex balloon_lock;
@@ -127,7 +127,7 @@ static void set_page_pfns(u32 pfns[], struct page *page)
 
 static void fill_balloon(struct virtio_balloon *vb, size_t num)
 {
-	struct balloon_dev_info *vb_dev_info = vb->vb_dev_info;
+	struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
 
 	/* We can only do one array worth at a time. */
 	num = min(num, ARRAY_SIZE(vb->pfns));
@@ -163,15 +163,15 @@ static void release_pages_by_pfn(const u32 pfns[], unsigned int num)
 	/* Find pfns pointing at start of each page, get pages and free them. */
 	for (i = 0; i < num; i += VIRTIO_BALLOON_PAGES_PER_PAGE) {
 		struct page *page = balloon_pfn_to_page(pfns[i]);
-		balloon_page_free(page);
 		adjust_managed_page_count(page, 1);
+		put_page(page); /* balloon reference */
 	}
 }
 
 static void leak_balloon(struct virtio_balloon *vb, size_t num)
 {
 	struct page *page;
-	struct balloon_dev_info *vb_dev_info = vb->vb_dev_info;
+	struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
 
 	/* We can only do one array worth at a time. */
 	num = min(num, ARRAY_SIZE(vb->pfns));
@@ -353,12 +353,11 @@ static int init_vqs(struct virtio_balloon *vb)
 	return 0;
 }
 
-static const struct address_space_operations virtio_balloon_aops;
 #ifdef CONFIG_BALLOON_COMPACTION
 /*
  * virtballoon_migratepage - perform the balloon page migration on behalf of
  *			     a compation thread.     (called under page lock)
- * @mapping: the page->mapping which will be assigned to the new migrated page.
+ * @vb_dev_info: the balloon device
  * @newpage: page that will replace the isolated page after migration finishes.
  * @page   : the isolated (old) page that is about to be migrated to newpage.
  * @mode   : compaction mode -- not used for balloon page migration.
@@ -373,17 +372,13 @@ static const struct address_space_operations virtio_balloon_aops;
  * This function preforms the balloon page migration task.
  * Called through balloon_mapping->a_ops->migratepage
  */
-static int virtballoon_migratepage(struct address_space *mapping,
+static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
 		struct page *newpage, struct page *page, enum migrate_mode mode)
 {
-	struct balloon_dev_info *vb_dev_info = balloon_page_device(page);
-	struct virtio_balloon *vb;
+	struct virtio_balloon *vb = container_of(vb_dev_info,
+			struct virtio_balloon, vb_dev_info);
 	unsigned long flags;
 
-	BUG_ON(!vb_dev_info);
-
-	vb = vb_dev_info->balloon_device;
-
 	/*
 	 * In order to avoid lock contention while migrating pages concurrently
 	 * to leak_balloon() or fill_balloon() we just give up the balloon_lock
@@ -395,21 +390,19 @@ static int virtballoon_migratepage(struct address_space *mapping,
 	if (!mutex_trylock(&vb->balloon_lock))
 		return -EAGAIN;
 
+	get_page(newpage); /* balloon reference */
+
 	/* balloon's page migration 1st step  -- inflate "newpage" */
 	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
-	balloon_page_insert(newpage, mapping, &vb_dev_info->pages);
+	balloon_page_insert(vb_dev_info, newpage);
 	vb_dev_info->isolated_pages--;
+	__count_vm_event(BALLOON_MIGRATE);
 	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
 	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
 	set_page_pfns(vb->pfns, newpage);
 	tell_host(vb, vb->inflate_vq);
 
-	/*
-	 * balloon's page migration 2nd step -- deflate "page"
-	 *
-	 * It's safe to delete page->lru here because this page is at
-	 * an isolated migration list, and this step is expected to happen here
-	 */
+	/* balloon's page migration 2nd step -- deflate "page" */
 	balloon_page_delete(page);
 	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
 	set_page_pfns(vb->pfns, page);
@@ -417,20 +410,15 @@ static int virtballoon_migratepage(struct address_space *mapping,
 
 	mutex_unlock(&vb->balloon_lock);
 
-	return MIGRATEPAGE_BALLOON_SUCCESS;
-}
+	put_page(page); /* balloon reference */
 
-/* define the balloon_mapping->a_ops callback to allow balloon page migration */
-static const struct address_space_operations virtio_balloon_aops = {
-			.migratepage = virtballoon_migratepage,
-};
+	return MIGRATEPAGE_SUCCESS;
+}
 #endif /* CONFIG_BALLOON_COMPACTION */
 
 static int virtballoon_probe(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb;
-	struct address_space *vb_mapping;
-	struct balloon_dev_info *vb_devinfo;
 	int err;
 
 	vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
@@ -446,30 +434,14 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	vb->vdev = vdev;
 	vb->need_stats_update = 0;
 
-	vb_devinfo = balloon_devinfo_alloc(vb);
-	if (IS_ERR(vb_devinfo)) {
-		err = PTR_ERR(vb_devinfo);
-		goto out_free_vb;
-	}
-
-	vb_mapping = balloon_mapping_alloc(vb_devinfo,
-					   (balloon_compaction_check()) ?
-					   &virtio_balloon_aops : NULL);
-	if (IS_ERR(vb_mapping)) {
-		/*
-		 * IS_ERR(vb_mapping) && PTR_ERR(vb_mapping) == -EOPNOTSUPP
-		 * This means !CONFIG_BALLOON_COMPACTION, otherwise we get off.
-		 */
-		err = PTR_ERR(vb_mapping);
-		if (err != -EOPNOTSUPP)
-			goto out_free_vb_devinfo;
-	}
-
-	vb->vb_dev_info = vb_devinfo;
+	balloon_devinfo_init(&vb->vb_dev_info);
+#ifdef CONFIG_BALLOON_COMPACTION
+	vb->vb_dev_info.migratepage = virtballoon_migratepage;
+#endif
 
 	err = init_vqs(vb);
 	if (err)
-		goto out_free_vb_mapping;
+		goto out_free_vb;
 
 	vb->thread = kthread_run(balloon, vb, "vballoon");
 	if (IS_ERR(vb->thread)) {
@@ -481,10 +453,6 @@ static int virtballoon_probe(struct virtio_device *vdev)
 
 out_del_vqs:
 	vdev->config->del_vqs(vdev);
-out_free_vb_mapping:
-	balloon_mapping_free(vb_mapping);
-out_free_vb_devinfo:
-	balloon_devinfo_free(vb_devinfo);
 out_free_vb:
 	kfree(vb);
 out:
@@ -510,8 +478,6 @@ static void virtballoon_remove(struct virtio_device *vdev)
 
 	kthread_stop(vb->thread);
 	remove_common(vb);
-	balloon_mapping_free(vb->vb_dev_info->mapping);
-	balloon_devinfo_free(vb->vb_dev_info);
 	kfree(vb);
 }
 
@@ -538,6 +504,8 @@ static int virtballoon_restore(struct virtio_device *vdev)
 	if (ret)
 		return ret;
 
+	virtio_device_ready(vdev);
+
 	fill_balloon(vb, towards_target(vb));
 	update_balloon_size(vb);
 	return 0;
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index c600ccfd6922..ef9a1650bb80 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -234,8 +234,6 @@ static irqreturn_t vm_interrupt(int irq, void *opaque)
 {
 	struct virtio_mmio_device *vm_dev = opaque;
 	struct virtio_mmio_vq_info *info;
-	struct virtio_driver *vdrv = container_of(vm_dev->vdev.dev.driver,
-			struct virtio_driver, driver);
 	unsigned long status;
 	unsigned long flags;
 	irqreturn_t ret = IRQ_NONE;
@@ -244,9 +242,8 @@ static irqreturn_t vm_interrupt(int irq, void *opaque)
 	status = readl(vm_dev->base + VIRTIO_MMIO_INTERRUPT_STATUS);
 	writel(status, vm_dev->base + VIRTIO_MMIO_INTERRUPT_ACK);
 
-	if (unlikely(status & VIRTIO_MMIO_INT_CONFIG)
-			&& vdrv && vdrv->config_changed) {
-		vdrv->config_changed(&vm_dev->vdev);
+	if (unlikely(status & VIRTIO_MMIO_INT_CONFIG)) {
+		virtio_config_changed(&vm_dev->vdev);
 		ret = IRQ_HANDLED;
 	}
 
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 3d1463c6b120..d34ebfa604f3 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -57,9 +57,6 @@ struct virtio_pci_device
 	/* Vectors allocated, excluding per-vq vectors if any */
 	unsigned msix_used_vectors;
 
-	/* Status saved during hibernate/restore */
-	u8 saved_status;
-
 	/* Whether we have vector per vq */
 	bool per_vq_vectors;
 };
@@ -211,12 +208,8 @@ static bool vp_notify(struct virtqueue *vq)
 static irqreturn_t vp_config_changed(int irq, void *opaque)
 {
 	struct virtio_pci_device *vp_dev = opaque;
-	struct virtio_driver *drv;
-	drv = container_of(vp_dev->vdev.dev.driver,
-			   struct virtio_driver, driver);
 
-	if (drv && drv->config_changed)
-		drv->config_changed(&vp_dev->vdev);
+	virtio_config_changed(&vp_dev->vdev);
 	return IRQ_HANDLED;
 }
 
@@ -768,16 +761,9 @@ static int virtio_pci_freeze(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
-	struct virtio_driver *drv;
 	int ret;
 
-	drv = container_of(vp_dev->vdev.dev.driver,
-			   struct virtio_driver, driver);
-
-	ret = 0;
-	vp_dev->saved_status = vp_get_status(&vp_dev->vdev);
-	if (drv && drv->freeze)
-		ret = drv->freeze(&vp_dev->vdev);
+	ret = virtio_device_freeze(&vp_dev->vdev);
 
 	if (!ret)
 		pci_disable_device(pci_dev);
@@ -788,27 +774,14 @@ static int virtio_pci_restore(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
-	struct virtio_driver *drv;
 	int ret;
 
-	drv = container_of(vp_dev->vdev.dev.driver,
-			   struct virtio_driver, driver);
-
 	ret = pci_enable_device(pci_dev);
 	if (ret)
 		return ret;
 
 	pci_set_master(pci_dev);
-	vp_finalize_features(&vp_dev->vdev);
-
-	if (drv && drv->restore)
-		ret = drv->restore(&vp_dev->vdev);
-
-	/* Finally, tell the device we're all set */
-	if (!ret)
-		vp_set_status(&vp_dev->vdev, vp_dev->saved_status);
-
-	return ret;
+	return virtio_device_restore(&vp_dev->vdev);
 }
 
 static const struct dev_pm_ops virtio_pci_pm_ops = {
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 1d1330a78af3..e3d5bf0a5021 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -95,6 +95,16 @@ config GPIO_WATCHDOG
 	  If you say yes here you get support for watchdog device
 	  controlled through GPIO-line.
 
+config MENF21BMC_WATCHDOG
+	tristate "MEN 14F021P00 BMC Watchdog"
+	depends on MFD_MENF21BMC
+	select WATCHDOG_CORE
+	help
+	  Say Y here to include support for the MEN 14F021P00 BMC Watchdog.
+
+	  This driver can also be built as a module. If so the module
+	  will be called menf21bmc_wdt.
+
 config WM831X_WATCHDOG
 	tristate "WM831x watchdog"
 	depends on MFD_WM831X
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index 468c3204c3b1..de1701470c14 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -178,3 +178,4 @@ obj-$(CONFIG_WM831X_WATCHDOG) += wm831x_wdt.o
 obj-$(CONFIG_WM8350_WATCHDOG) += wm8350_wdt.o
 obj-$(CONFIG_MAX63XX_WATCHDOG) += max63xx_wdt.o
 obj-$(CONFIG_SOFT_WATCHDOG) += softdog.o
+obj-$(CONFIG_MENF21BMC_WATCHDOG) += menf21bmc_wdt.o
diff --git a/drivers/watchdog/alim7101_wdt.c b/drivers/watchdog/alim7101_wdt.c
index 996b2f7d330e..665e0e7dfe1e 100644
--- a/drivers/watchdog/alim7101_wdt.c
+++ b/drivers/watchdog/alim7101_wdt.c
@@ -301,6 +301,28 @@ static struct miscdevice wdt_miscdev = {
 	.fops	=	&wdt_fops,
 };
 
+static int wdt_restart_handle(struct notifier_block *this, unsigned long mode,
+			      void *cmd)
+{
+	/*
+	 * Cobalt devices have no way of rebooting themselves other
+	 * than getting the watchdog to pull reset, so we restart the
+	 * watchdog on reboot with no heartbeat.
+	 */
+	wdt_change(WDT_ENABLE);
+
+	/* loop until the watchdog fires */
+	while (true)
+		;
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block wdt_restart_handler = {
+	.notifier_call = wdt_restart_handle,
+	.priority = 128,
+};
+
 /*
  *	Notifier for system down
  */
@@ -311,15 +333,6 @@ static int wdt_notify_sys(struct notifier_block *this,
 	if (code == SYS_DOWN || code == SYS_HALT)
 		wdt_turnoff();
 
-	if (code == SYS_RESTART) {
-		/*
-		 * Cobalt devices have no way of rebooting themselves other
-		 * than getting the watchdog to pull reset, so we restart the
-		 * watchdog on reboot with no heartbeat
-		 */
-		wdt_change(WDT_ENABLE);
-		pr_info("Watchdog timer is now enabled with no heartbeat - should reboot in ~1 second\n");
-	}
 	return NOTIFY_DONE;
 }
 
@@ -338,6 +351,7 @@ static void __exit alim7101_wdt_unload(void)
 	/* Deregister */
 	misc_deregister(&wdt_miscdev);
 	unregister_reboot_notifier(&wdt_notifier);
+	unregister_restart_handler(&wdt_restart_handler);
 	pci_dev_put(alim7101_pmu);
 }
 
@@ -390,11 +404,17 @@ static int __init alim7101_wdt_init(void)
 		goto err_out;
 	}
 
+	rc = register_restart_handler(&wdt_restart_handler);
+	if (rc) {
+		pr_err("cannot register restart handler (err=%d)\n", rc);
+		goto err_out_reboot;
+	}
+
 	rc = misc_register(&wdt_miscdev);
 	if (rc) {
 		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
 		       wdt_miscdev.minor, rc);
-		goto err_out_reboot;
+		goto err_out_restart;
 	}
 
 	if (nowayout)
@@ -404,6 +424,8 @@ static int __init alim7101_wdt_init(void)
 		timeout, nowayout);
 	return 0;
 
+err_out_restart:
+	unregister_restart_handler(&wdt_restart_handler);
 err_out_reboot:
 	unregister_reboot_notifier(&wdt_notifier);
 err_out:
diff --git a/drivers/watchdog/menf21bmc_wdt.c b/drivers/watchdog/menf21bmc_wdt.c
new file mode 100644
index 000000000000..2042874d5ce3
--- /dev/null
+++ b/drivers/watchdog/menf21bmc_wdt.c
@@ -0,0 +1,203 @@
+/*
+ *  MEN 14F021P00 Board Management Controller (BMC) Watchdog Driver.
+ *
+ *  Copyright (C) 2014 MEN Mikro Elektronik Nuernberg GmbH
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/watchdog.h>
+#include <linux/platform_device.h>
+#include <linux/i2c.h>
+
+#define DEVNAME "menf21bmc_wdt"
+
+#define BMC_CMD_WD_ON		0x11
+#define BMC_CMD_WD_OFF		0x12
+#define BMC_CMD_WD_TRIG		0x13
+#define BMC_CMD_WD_TIME		0x14
+#define BMC_CMD_WD_STATE	0x17
+#define BMC_WD_OFF_VAL		0x69
+#define BMC_CMD_RST_RSN		0x92
+
+#define BMC_WD_TIMEOUT_MIN	1	/* in sec */
+#define BMC_WD_TIMEOUT_MAX	6553	/* in sec */
+
+static bool nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, bool, 0);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
+				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
+
+struct menf21bmc_wdt {
+	struct watchdog_device wdt;
+	struct i2c_client *i2c_client;
+};
+
+static int menf21bmc_wdt_set_bootstatus(struct menf21bmc_wdt *data)
+{
+	int rst_rsn;
+
+	rst_rsn = i2c_smbus_read_byte_data(data->i2c_client, BMC_CMD_RST_RSN);
+	if (rst_rsn < 0)
+		return rst_rsn;
+
+	if (rst_rsn == 0x02)
+		data->wdt.bootstatus |= WDIOF_CARDRESET;
+	else if (rst_rsn == 0x05)
+		data->wdt.bootstatus |= WDIOF_EXTERN1;
+	else if (rst_rsn == 0x06)
+		data->wdt.bootstatus |= WDIOF_EXTERN2;
+	else if (rst_rsn == 0x0A)
+		data->wdt.bootstatus |= WDIOF_POWERUNDER;
+
+	return 0;
+}
+
+static int menf21bmc_wdt_start(struct watchdog_device *wdt)
+{
+	struct menf21bmc_wdt *drv_data = watchdog_get_drvdata(wdt);
+
+	return i2c_smbus_write_byte(drv_data->i2c_client, BMC_CMD_WD_ON);
+}
+
+static int menf21bmc_wdt_stop(struct watchdog_device *wdt)
+{
+	struct menf21bmc_wdt *drv_data = watchdog_get_drvdata(wdt);
+
+	return i2c_smbus_write_byte_data(drv_data->i2c_client,
+					 BMC_CMD_WD_OFF, BMC_WD_OFF_VAL);
+}
+
+static int
+menf21bmc_wdt_settimeout(struct watchdog_device *wdt, unsigned int timeout)
+{
+	int ret;
+	struct menf21bmc_wdt *drv_data = watchdog_get_drvdata(wdt);
+
+	/*
+	 *  BMC Watchdog does have a resolution of 100ms.
+	 *  Watchdog API defines the timeout in seconds, so we have to
+	 *  multiply the value.
+	 */
+	ret = i2c_smbus_write_word_data(drv_data->i2c_client,
+					BMC_CMD_WD_TIME, timeout * 10);
+	if (ret < 0)
+		return ret;
+
+	wdt->timeout = timeout;
+
+	return 0;
+}
+
+static int menf21bmc_wdt_ping(struct watchdog_device *wdt)
+{
+	struct menf21bmc_wdt *drv_data = watchdog_get_drvdata(wdt);
+
+	return i2c_smbus_write_byte(drv_data->i2c_client, BMC_CMD_WD_TRIG);
+}
+
+static const struct watchdog_info menf21bmc_wdt_info = {
+	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING,
+	.identity = DEVNAME,
+};
+
+static const struct watchdog_ops menf21bmc_wdt_ops = {
+	.owner		= THIS_MODULE,
+	.start		= menf21bmc_wdt_start,
+	.stop		= menf21bmc_wdt_stop,
+	.ping		= menf21bmc_wdt_ping,
+	.set_timeout	= menf21bmc_wdt_settimeout,
+};
+
+static int menf21bmc_wdt_probe(struct platform_device *pdev)
+{
+	int ret, bmc_timeout;
+	struct menf21bmc_wdt *drv_data;
+	struct i2c_client *i2c_client = to_i2c_client(pdev->dev.parent);
+
+	drv_data = devm_kzalloc(&pdev->dev,
+				sizeof(struct menf21bmc_wdt), GFP_KERNEL);
+	if (!drv_data)
+		return -ENOMEM;
+
+	drv_data->wdt.ops = &menf21bmc_wdt_ops;
+	drv_data->wdt.info = &menf21bmc_wdt_info;
+	drv_data->wdt.min_timeout = BMC_WD_TIMEOUT_MIN;
+	drv_data->wdt.max_timeout = BMC_WD_TIMEOUT_MAX;
+	drv_data->i2c_client = i2c_client;
+
+	/*
+	 * Get the current wdt timeout value from the BMC because
+	 * the BMC will save the value set before if the system restarts.
+	 */
+	bmc_timeout = i2c_smbus_read_word_data(drv_data->i2c_client,
+					       BMC_CMD_WD_TIME);
+	if (bmc_timeout < 0) {
+		dev_err(&pdev->dev, "failed to get current WDT timeout\n");
+		return bmc_timeout;
+	}
+
+	watchdog_init_timeout(&drv_data->wdt, bmc_timeout / 10, &pdev->dev);
+	watchdog_set_nowayout(&drv_data->wdt, nowayout);
+	watchdog_set_drvdata(&drv_data->wdt, drv_data);
+	platform_set_drvdata(pdev, drv_data);
+
+	ret = menf21bmc_wdt_set_bootstatus(drv_data);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to set Watchdog bootstatus\n");
+		return ret;
+	}
+
+	ret = watchdog_register_device(&drv_data->wdt);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register Watchdog device\n");
+		return ret;
+	}
+
+	dev_info(&pdev->dev, "MEN 14F021P00 BMC Watchdog device enabled\n");
+
+	return 0;
+}
+
+static int menf21bmc_wdt_remove(struct platform_device *pdev)
+{
+	struct menf21bmc_wdt *drv_data = platform_get_drvdata(pdev);
+
+	dev_warn(&pdev->dev,
+		 "Unregister MEN 14F021P00 BMC Watchdog device, board may reset\n");
+
+	watchdog_unregister_device(&drv_data->wdt);
+
+	return 0;
+}
+
+static void menf21bmc_wdt_shutdown(struct platform_device *pdev)
+{
+	struct menf21bmc_wdt *drv_data = platform_get_drvdata(pdev);
+
+	i2c_smbus_write_word_data(drv_data->i2c_client,
+				  BMC_CMD_WD_OFF, BMC_WD_OFF_VAL);
+}
+
+static struct  platform_driver menf21bmc_wdt = {
+	.driver		= {
+		.owner = THIS_MODULE,
+		.name	= DEVNAME,
+	},
+	.probe		= menf21bmc_wdt_probe,
+	.remove		= menf21bmc_wdt_remove,
+	.shutdown	= menf21bmc_wdt_shutdown,
+};
+
+module_platform_driver(menf21bmc_wdt);
+
+MODULE_DESCRIPTION("MEN 14F021P00 BMC Watchdog driver");
+MODULE_AUTHOR("Andreas Werner <andreas.werner@men.de>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:menf21bmc_wdt");
diff --git a/drivers/watchdog/moxart_wdt.c b/drivers/watchdog/moxart_wdt.c
index 4aa3a8a876fe..a64405b82596 100644
--- a/drivers/watchdog/moxart_wdt.c
+++ b/drivers/watchdog/moxart_wdt.c
@@ -15,12 +15,12 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
+#include <linux/notifier.h>
 #include <linux/platform_device.h>
+#include <linux/reboot.h>
 #include <linux/watchdog.h>
 #include <linux/moduleparam.h>
 
-#include <asm/system_misc.h>
-
 #define REG_COUNT			0x4
 #define REG_MODE			0x8
 #define REG_ENABLE			0xC
@@ -29,17 +29,22 @@ struct moxart_wdt_dev {
 	struct watchdog_device dev;
 	void __iomem *base;
 	unsigned int clock_frequency;
+	struct notifier_block restart_handler;
 };
 
-static struct moxart_wdt_dev *moxart_restart_ctx;
-
 static int heartbeat;
 
-static void moxart_wdt_restart(enum reboot_mode reboot_mode, const char *cmd)
+static int moxart_restart_handle(struct notifier_block *this,
+				 unsigned long mode, void *cmd)
 {
-	writel(1, moxart_restart_ctx->base + REG_COUNT);
-	writel(0x5ab9, moxart_restart_ctx->base + REG_MODE);
-	writel(0x03, moxart_restart_ctx->base + REG_ENABLE);
+	struct moxart_wdt_dev *moxart_wdt = container_of(this,
+							 struct moxart_wdt_dev,
+							 restart_handler);
+	writel(1, moxart_wdt->base + REG_COUNT);
+	writel(0x5ab9, moxart_wdt->base + REG_MODE);
+	writel(0x03, moxart_wdt->base + REG_ENABLE);
+
+	return NOTIFY_DONE;
 }
 
 static int moxart_wdt_stop(struct watchdog_device *wdt_dev)
@@ -136,8 +141,12 @@ static int moxart_wdt_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	moxart_restart_ctx = moxart_wdt;
-	arm_pm_restart = moxart_wdt_restart;
+	moxart_wdt->restart_handler.notifier_call = moxart_restart_handle;
+	moxart_wdt->restart_handler.priority = 128;
+	err = register_restart_handler(&moxart_wdt->restart_handler);
+	if (err)
+		dev_err(dev, "cannot register restart notifier (err=%d)\n",
+			err);
 
 	dev_dbg(dev, "Watchdog enabled (heartbeat=%d sec, nowayout=%d)\n",
 		moxart_wdt->dev.timeout, nowayout);
@@ -149,9 +158,8 @@ static int moxart_wdt_remove(struct platform_device *pdev)
 {
 	struct moxart_wdt_dev *moxart_wdt = platform_get_drvdata(pdev);
 
-	arm_pm_restart = NULL;
+	unregister_restart_handler(&moxart_wdt->restart_handler);
 	moxart_wdt_stop(&moxart_wdt->dev);
-	watchdog_unregister_device(&moxart_wdt->dev);
 
 	return 0;
 }
diff --git a/drivers/watchdog/sunxi_wdt.c b/drivers/watchdog/sunxi_wdt.c
index 60deb9d304c0..480bb557f353 100644
--- a/drivers/watchdog/sunxi_wdt.c
+++ b/drivers/watchdog/sunxi_wdt.c
@@ -21,14 +21,13 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/notifier.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/reboot.h>
 #include <linux/types.h>
 #include <linux/watchdog.h>
 
-#include <asm/system_misc.h>
-
 #define WDT_MAX_TIMEOUT         16
 #define WDT_MIN_TIMEOUT         1
 #define WDT_MODE_TIMEOUT(n)     ((n) << 3)
@@ -50,6 +49,7 @@ static unsigned int timeout = WDT_MAX_TIMEOUT;
 struct sunxi_wdt_dev {
 	struct watchdog_device wdt_dev;
 	void __iomem *wdt_base;
+	struct notifier_block restart_handler;
 };
 
 /*
@@ -74,24 +74,29 @@ static const int wdt_timeout_map[] = {
 	[16] = 0xB, /* 16s */
 };
 
-static void __iomem *reboot_wdt_base;
 
-static void sun4i_wdt_restart(enum reboot_mode mode, const char *cmd)
+static int sunxi_restart_handle(struct notifier_block *this, unsigned long mode,
+				void *cmd)
 {
+	struct sunxi_wdt_dev *sunxi_wdt = container_of(this,
+						       struct sunxi_wdt_dev,
+						       restart_handler);
+	void __iomem *wdt_base = sunxi_wdt->wdt_base;
+
 	/* Enable timer and set reset bit in the watchdog */
-	writel(WDT_MODE_EN | WDT_MODE_RST_EN, reboot_wdt_base + WDT_MODE);
+	writel(WDT_MODE_EN | WDT_MODE_RST_EN, wdt_base + WDT_MODE);
 
 	/*
 	 * Restart the watchdog. The default (and lowest) interval
 	 * value for the watchdog is 0.5s.
 	 */
-	writel(WDT_CTRL_RELOAD, reboot_wdt_base + WDT_CTRL);
+	writel(WDT_CTRL_RELOAD, wdt_base + WDT_CTRL);
 
 	while (1) {
 		mdelay(5);
-		writel(WDT_MODE_EN | WDT_MODE_RST_EN,
-		       reboot_wdt_base + WDT_MODE);
+		writel(WDT_MODE_EN | WDT_MODE_RST_EN, wdt_base + WDT_MODE);
 	}
+	return NOTIFY_DONE;
 }
 
 static int sunxi_wdt_ping(struct watchdog_device *wdt_dev)
@@ -205,8 +210,12 @@ static int sunxi_wdt_probe(struct platform_device *pdev)
 	if (unlikely(err))
 		return err;
 
-	reboot_wdt_base = sunxi_wdt->wdt_base;
-	arm_pm_restart = sun4i_wdt_restart;
+	sunxi_wdt->restart_handler.notifier_call = sunxi_restart_handle;
+	sunxi_wdt->restart_handler.priority = 128;
+	err = register_restart_handler(&sunxi_wdt->restart_handler);
+	if (err)
+		dev_err(&pdev->dev,
+			"cannot register restart handler (err=%d)\n", err);
 
 	dev_info(&pdev->dev, "Watchdog enabled (timeout=%d sec, nowayout=%d)",
 			sunxi_wdt->wdt_dev.timeout, nowayout);
@@ -218,7 +227,7 @@ static int sunxi_wdt_remove(struct platform_device *pdev)
 {
 	struct sunxi_wdt_dev *sunxi_wdt = platform_get_drvdata(pdev);
 
-	arm_pm_restart = NULL;
+	unregister_restart_handler(&sunxi_wdt->restart_handler);
 
 	watchdog_unregister_device(&sunxi_wdt->wdt_dev);
 	watchdog_set_drvdata(&sunxi_wdt->wdt_dev, NULL);
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 8bc01838daf9..b812462083fc 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -172,6 +172,15 @@ config XEN_PCIDEV_BACKEND
 
 	  If in doubt, say m.
 
+config XEN_SCSI_BACKEND
+	tristate "XEN SCSI backend driver"
+	depends on XEN && XEN_BACKEND && TARGET_CORE
+	help
+	  The SCSI backend driver allows the kernel to export its SCSI Devices
+	  to other guests via a high-performance shared-memory interface.
+	  Only needed for systems running as XEN driver domains (e.g. Dom0) and
+	  if guests need generic access to SCSI devices.
+
 config XEN_PRIVCMD
 	tristate
 	depends on XEN
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 84044b554e33..2140398a2a8c 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -36,6 +36,7 @@ obj-$(CONFIG_XEN_ACPI_HOTPLUG_MEMORY)	+= xen-acpi-memhotplug.o
 obj-$(CONFIG_XEN_ACPI_HOTPLUG_CPU)	+= xen-acpi-cpuhotplug.o
 obj-$(CONFIG_XEN_ACPI_PROCESSOR)	+= xen-acpi-processor.o
 obj-$(CONFIG_XEN_EFI)			+= efi.o
+obj-$(CONFIG_XEN_SCSI_BACKEND)		+= xen-scsiback.o
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
 xen-gntalloc-y				:= gntalloc.o
diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c
index 31f618a49661..1f850c97482f 100644
--- a/drivers/xen/efi.c
+++ b/drivers/xen/efi.c
@@ -27,6 +27,8 @@
 #include <xen/interface/platform.h>
 #include <xen/xen.h>
 
+#include <asm/page.h>
+
 #include <asm/xen/hypercall.h>
 
 #define INIT_EFI_OP(name) \
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 5b5c5ff273fd..b4bca2d4a7e5 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -900,8 +900,8 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 	return irq;
 }
 
-static int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
-					  unsigned int remote_port)
+int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
+				   unsigned int remote_port)
 {
 	struct evtchn_bind_interdomain bind_interdomain;
 	int err;
@@ -914,6 +914,7 @@ static int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
 
 	return err ? : bind_evtchn_to_irq(bind_interdomain.local_port);
 }
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq);
 
 static int find_virq(unsigned int virq, unsigned int cpu)
 {
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index c254ae036f18..7786291ba229 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -592,7 +592,7 @@ static int grow_gnttab_list(unsigned int more_frames)
 	return 0;
 
 grow_nomem:
-	for ( ; i >= nr_glist_frames; i--)
+	while (i-- > nr_glist_frames)
 		free_page((unsigned long) gnttab_list[i]);
 	return -ENOMEM;
 }
diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
index 259ba2661543..017069a455d4 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -133,7 +133,7 @@ static void pcistub_device_release(struct kref *kref)
 	xen_pcibk_config_free_dyn_fields(dev);
 	xen_pcibk_config_free_dev(dev);
 
-	dev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
+	pci_clear_dev_assigned(dev);
 	pci_dev_put(dev);
 
 	kfree(psdev);
@@ -413,7 +413,7 @@ static int pcistub_init_device(struct pci_dev *dev)
 	dev_dbg(&dev->dev, "reset device\n");
 	xen_pcibk_reset_device(dev);
 
-	dev->dev_flags |= PCI_DEV_FLAGS_ASSIGNED;
+	pci_set_dev_assigned(dev);
 	return 0;
 
 config_release:
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index c214daab4829..ad8d30c088fe 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -719,11 +719,13 @@ static const struct xenbus_device_id xen_pcibk_ids[] = {
 	{""},
 };
 
-static DEFINE_XENBUS_DRIVER(xen_pcibk, DRV_NAME,
+static struct xenbus_driver xen_pcibk_driver = {
+	.name                   = DRV_NAME,
+	.ids                    = xen_pcibk_ids,
 	.probe			= xen_pcibk_xenbus_probe,
 	.remove			= xen_pcibk_xenbus_remove,
 	.otherend_changed	= xen_pcibk_frontend_changed,
-);
+};
 
 const struct xen_pcibk_backend *__read_mostly xen_pcibk_backend;
 
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
new file mode 100644
index 000000000000..3e32146472a5
--- /dev/null
+++ b/drivers/xen/xen-scsiback.c
@@ -0,0 +1,2126 @@
+/*
+ * Xen SCSI backend driver
+ *
+ * Copyright (c) 2008, FUJITSU Limited
+ *
+ * Based on the blkback driver code.
+ * Adaption to kernel taget core infrastructure taken from vhost/scsi.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <stdarg.h>
+
+#include <linux/module.h>
+#include <linux/utsname.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+#include <linux/list.h>
+#include <linux/gfp.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/configfs.h>
+
+#include <generated/utsrelease.h>
+
+#include <scsi/scsi_dbg.h>
+#include <scsi/scsi_eh.h>
+#include <scsi/scsi_tcq.h>
+
+#include <target/target_core_base.h>
+#include <target/target_core_fabric.h>
+#include <target/target_core_configfs.h>
+#include <target/target_core_fabric_configfs.h>
+
+#include <asm/hypervisor.h>
+
+#include <xen/xen.h>
+#include <xen/balloon.h>
+#include <xen/events.h>
+#include <xen/xenbus.h>
+#include <xen/grant_table.h>
+#include <xen/page.h>
+
+#include <xen/interface/grant_table.h>
+#include <xen/interface/io/vscsiif.h>
+
+#define DPRINTK(_f, _a...)			\
+	pr_debug("(file=%s, line=%d) " _f, __FILE__ , __LINE__ , ## _a)
+
+#define VSCSI_VERSION	"v0.1"
+#define VSCSI_NAMELEN	32
+
+struct ids_tuple {
+	unsigned int hst;		/* host    */
+	unsigned int chn;		/* channel */
+	unsigned int tgt;		/* target  */
+	unsigned int lun;		/* LUN     */
+};
+
+struct v2p_entry {
+	struct ids_tuple v;		/* translate from */
+	struct scsiback_tpg *tpg;	/* translate to   */
+	unsigned int lun;
+	struct kref kref;
+	struct list_head l;
+};
+
+struct vscsibk_info {
+	struct xenbus_device *dev;
+
+	domid_t domid;
+	unsigned int irq;
+
+	struct vscsiif_back_ring ring;
+	int ring_error;
+
+	spinlock_t ring_lock;
+	atomic_t nr_unreplied_reqs;
+
+	spinlock_t v2p_lock;
+	struct list_head v2p_entry_lists;
+
+	wait_queue_head_t waiting_to_free;
+};
+
+/* theoretical maximum of grants for one request */
+#define VSCSI_MAX_GRANTS	(SG_ALL + VSCSIIF_SG_TABLESIZE)
+
+/*
+ * VSCSI_GRANT_BATCH is the maximum number of grants to be processed in one
+ * call to map/unmap grants. Don't choose it too large, as there are arrays
+ * with VSCSI_GRANT_BATCH elements allocated on the stack.
+ */
+#define VSCSI_GRANT_BATCH	16
+
+struct vscsibk_pend {
+	uint16_t rqid;
+
+	uint8_t cmnd[VSCSIIF_MAX_COMMAND_SIZE];
+	uint8_t cmd_len;
+
+	uint8_t sc_data_direction;
+	uint16_t n_sg;		/* real length of SG list */
+	uint16_t n_grants;	/* SG pages and potentially SG list */
+	uint32_t data_len;
+	uint32_t result;
+
+	struct vscsibk_info *info;
+	struct v2p_entry *v2p;
+	struct scatterlist *sgl;
+
+	uint8_t sense_buffer[VSCSIIF_SENSE_BUFFERSIZE];
+
+	grant_handle_t grant_handles[VSCSI_MAX_GRANTS];
+	struct page *pages[VSCSI_MAX_GRANTS];
+
+	struct se_cmd se_cmd;
+};
+
+struct scsiback_tmr {
+	atomic_t tmr_complete;
+	wait_queue_head_t tmr_wait;
+};
+
+struct scsiback_nexus {
+	/* Pointer to TCM session for I_T Nexus */
+	struct se_session *tvn_se_sess;
+};
+
+struct scsiback_tport {
+	/* SCSI protocol the tport is providing */
+	u8 tport_proto_id;
+	/* Binary World Wide unique Port Name for pvscsi Target port */
+	u64 tport_wwpn;
+	/* ASCII formatted WWPN for pvscsi Target port */
+	char tport_name[VSCSI_NAMELEN];
+	/* Returned by scsiback_make_tport() */
+	struct se_wwn tport_wwn;
+};
+
+struct scsiback_tpg {
+	/* scsiback port target portal group tag for TCM */
+	u16 tport_tpgt;
+	/* track number of TPG Port/Lun Links wrt explicit I_T Nexus shutdown */
+	int tv_tpg_port_count;
+	/* xen-pvscsi references to tpg_nexus, protected by tv_tpg_mutex */
+	int tv_tpg_fe_count;
+	/* list for scsiback_list */
+	struct list_head tv_tpg_list;
+	/* Used to protect access for tpg_nexus */
+	struct mutex tv_tpg_mutex;
+	/* Pointer to the TCM pvscsi I_T Nexus for this TPG endpoint */
+	struct scsiback_nexus *tpg_nexus;
+	/* Pointer back to scsiback_tport */
+	struct scsiback_tport *tport;
+	/* Returned by scsiback_make_tpg() */
+	struct se_portal_group se_tpg;
+	/* alias used in xenstore */
+	char param_alias[VSCSI_NAMELEN];
+	/* list of info structures related to this target portal group */
+	struct list_head info_list;
+};
+
+#define SCSIBACK_INVALID_HANDLE (~0)
+
+static bool log_print_stat;
+module_param(log_print_stat, bool, 0644);
+
+static int scsiback_max_buffer_pages = 1024;
+module_param_named(max_buffer_pages, scsiback_max_buffer_pages, int, 0644);
+MODULE_PARM_DESC(max_buffer_pages,
+"Maximum number of free pages to keep in backend buffer");
+
+static struct kmem_cache *scsiback_cachep;
+static DEFINE_SPINLOCK(free_pages_lock);
+static int free_pages_num;
+static LIST_HEAD(scsiback_free_pages);
+
+/* Global spinlock to protect scsiback TPG list */
+static DEFINE_MUTEX(scsiback_mutex);
+static LIST_HEAD(scsiback_list);
+
+/* Local pointer to allocated TCM configfs fabric module */
+static struct target_fabric_configfs *scsiback_fabric_configfs;
+
+static void scsiback_get(struct vscsibk_info *info)
+{
+	atomic_inc(&info->nr_unreplied_reqs);
+}
+
+static void scsiback_put(struct vscsibk_info *info)
+{
+	if (atomic_dec_and_test(&info->nr_unreplied_reqs))
+		wake_up(&info->waiting_to_free);
+}
+
+static void put_free_pages(struct page **page, int num)
+{
+	unsigned long flags;
+	int i = free_pages_num + num, n = num;
+
+	if (num == 0)
+		return;
+	if (i > scsiback_max_buffer_pages) {
+		n = min(num, i - scsiback_max_buffer_pages);
+		free_xenballooned_pages(n, page + num - n);
+		n = num - n;
+	}
+	spin_lock_irqsave(&free_pages_lock, flags);
+	for (i = 0; i < n; i++)
+		list_add(&page[i]->lru, &scsiback_free_pages);
+	free_pages_num += n;
+	spin_unlock_irqrestore(&free_pages_lock, flags);
+}
+
+static int get_free_page(struct page **page)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&free_pages_lock, flags);
+	if (list_empty(&scsiback_free_pages)) {
+		spin_unlock_irqrestore(&free_pages_lock, flags);
+		return alloc_xenballooned_pages(1, page, false);
+	}
+	page[0] = list_first_entry(&scsiback_free_pages, struct page, lru);
+	list_del(&page[0]->lru);
+	free_pages_num--;
+	spin_unlock_irqrestore(&free_pages_lock, flags);
+	return 0;
+}
+
+static unsigned long vaddr_page(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+
+	return (unsigned long)pfn_to_kaddr(pfn);
+}
+
+static unsigned long vaddr(struct vscsibk_pend *req, int seg)
+{
+	return vaddr_page(req->pages[seg]);
+}
+
+static void scsiback_print_status(char *sense_buffer, int errors,
+					struct vscsibk_pend *pending_req)
+{
+	struct scsiback_tpg *tpg = pending_req->v2p->tpg;
+
+	pr_err("xen-pvscsi[%s:%d] cmnd[0]=%02x -> st=%02x msg=%02x host=%02x drv=%02x\n",
+	       tpg->tport->tport_name, pending_req->v2p->lun,
+	       pending_req->cmnd[0], status_byte(errors), msg_byte(errors),
+	       host_byte(errors), driver_byte(errors));
+
+	if (CHECK_CONDITION & status_byte(errors))
+		__scsi_print_sense("xen-pvscsi", sense_buffer,
+				   SCSI_SENSE_BUFFERSIZE);
+}
+
+static void scsiback_fast_flush_area(struct vscsibk_pend *req)
+{
+	struct gnttab_unmap_grant_ref unmap[VSCSI_GRANT_BATCH];
+	struct page *pages[VSCSI_GRANT_BATCH];
+	unsigned int i, invcount = 0;
+	grant_handle_t handle;
+	int err;
+
+	kfree(req->sgl);
+	req->sgl = NULL;
+	req->n_sg = 0;
+
+	if (!req->n_grants)
+		return;
+
+	for (i = 0; i < req->n_grants; i++) {
+		handle = req->grant_handles[i];
+		if (handle == SCSIBACK_INVALID_HANDLE)
+			continue;
+		gnttab_set_unmap_op(&unmap[invcount], vaddr(req, i),
+				    GNTMAP_host_map, handle);
+		req->grant_handles[i] = SCSIBACK_INVALID_HANDLE;
+		pages[invcount] = req->pages[i];
+		put_page(pages[invcount]);
+		invcount++;
+		if (invcount < VSCSI_GRANT_BATCH)
+			continue;
+		err = gnttab_unmap_refs(unmap, NULL, pages, invcount);
+		BUG_ON(err);
+		invcount = 0;
+	}
+
+	if (invcount) {
+		err = gnttab_unmap_refs(unmap, NULL, pages, invcount);
+		BUG_ON(err);
+	}
+
+	put_free_pages(req->pages, req->n_grants);
+	req->n_grants = 0;
+}
+
+static void scsiback_free_translation_entry(struct kref *kref)
+{
+	struct v2p_entry *entry = container_of(kref, struct v2p_entry, kref);
+	struct scsiback_tpg *tpg = entry->tpg;
+
+	mutex_lock(&tpg->tv_tpg_mutex);
+	tpg->tv_tpg_fe_count--;
+	mutex_unlock(&tpg->tv_tpg_mutex);
+
+	kfree(entry);
+}
+
+static void scsiback_do_resp_with_sense(char *sense_buffer, int32_t result,
+			uint32_t resid, struct vscsibk_pend *pending_req)
+{
+	struct vscsiif_response *ring_res;
+	struct vscsibk_info *info = pending_req->info;
+	int notify;
+	struct scsi_sense_hdr sshdr;
+	unsigned long flags;
+	unsigned len;
+
+	spin_lock_irqsave(&info->ring_lock, flags);
+
+	ring_res = RING_GET_RESPONSE(&info->ring, info->ring.rsp_prod_pvt);
+	info->ring.rsp_prod_pvt++;
+
+	ring_res->rslt   = result;
+	ring_res->rqid   = pending_req->rqid;
+
+	if (sense_buffer != NULL &&
+	    scsi_normalize_sense(sense_buffer, VSCSIIF_SENSE_BUFFERSIZE,
+				 &sshdr)) {
+		len = min_t(unsigned, 8 + sense_buffer[7],
+			    VSCSIIF_SENSE_BUFFERSIZE);
+		memcpy(ring_res->sense_buffer, sense_buffer, len);
+		ring_res->sense_len = len;
+	} else {
+		ring_res->sense_len = 0;
+	}
+
+	ring_res->residual_len = resid;
+
+	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&info->ring, notify);
+	spin_unlock_irqrestore(&info->ring_lock, flags);
+
+	if (notify)
+		notify_remote_via_irq(info->irq);
+
+	if (pending_req->v2p)
+		kref_put(&pending_req->v2p->kref,
+			 scsiback_free_translation_entry);
+}
+
+static void scsiback_cmd_done(struct vscsibk_pend *pending_req)
+{
+	struct vscsibk_info *info = pending_req->info;
+	unsigned char *sense_buffer;
+	unsigned int resid;
+	int errors;
+
+	sense_buffer = pending_req->sense_buffer;
+	resid        = pending_req->se_cmd.residual_count;
+	errors       = pending_req->result;
+
+	if (errors && log_print_stat)
+		scsiback_print_status(sense_buffer, errors, pending_req);
+
+	scsiback_fast_flush_area(pending_req);
+	scsiback_do_resp_with_sense(sense_buffer, errors, resid, pending_req);
+	scsiback_put(info);
+}
+
+static void scsiback_cmd_exec(struct vscsibk_pend *pending_req)
+{
+	struct se_cmd *se_cmd = &pending_req->se_cmd;
+	struct se_session *sess = pending_req->v2p->tpg->tpg_nexus->tvn_se_sess;
+	int rc;
+
+	memset(pending_req->sense_buffer, 0, VSCSIIF_SENSE_BUFFERSIZE);
+
+	memset(se_cmd, 0, sizeof(*se_cmd));
+
+	scsiback_get(pending_req->info);
+	rc = target_submit_cmd_map_sgls(se_cmd, sess, pending_req->cmnd,
+			pending_req->sense_buffer, pending_req->v2p->lun,
+			pending_req->data_len, 0,
+			pending_req->sc_data_direction, 0,
+			pending_req->sgl, pending_req->n_sg,
+			NULL, 0, NULL, 0);
+	if (rc < 0) {
+		transport_send_check_condition_and_sense(se_cmd,
+				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0);
+		transport_generic_free_cmd(se_cmd, 0);
+	}
+}
+
+static int scsiback_gnttab_data_map_batch(struct gnttab_map_grant_ref *map,
+	struct page **pg, grant_handle_t *grant, int cnt)
+{
+	int err, i;
+
+	if (!cnt)
+		return 0;
+
+	err = gnttab_map_refs(map, NULL, pg, cnt);
+	BUG_ON(err);
+	for (i = 0; i < cnt; i++) {
+		if (unlikely(map[i].status != GNTST_okay)) {
+			pr_err("xen-pvscsi: invalid buffer -- could not remap it\n");
+			map[i].handle = SCSIBACK_INVALID_HANDLE;
+			err = -ENOMEM;
+		} else {
+			get_page(pg[i]);
+		}
+		grant[i] = map[i].handle;
+	}
+	return err;
+}
+
+static int scsiback_gnttab_data_map_list(struct vscsibk_pend *pending_req,
+			struct scsiif_request_segment *seg, struct page **pg,
+			grant_handle_t *grant, int cnt, u32 flags)
+{
+	int mapcount = 0, i, err = 0;
+	struct gnttab_map_grant_ref map[VSCSI_GRANT_BATCH];
+	struct vscsibk_info *info = pending_req->info;
+
+	for (i = 0; i < cnt; i++) {
+		if (get_free_page(pg + mapcount)) {
+			put_free_pages(pg, mapcount);
+			pr_err("xen-pvscsi: no grant page\n");
+			return -ENOMEM;
+		}
+		gnttab_set_map_op(&map[mapcount], vaddr_page(pg[mapcount]),
+				  flags, seg[i].gref, info->domid);
+		mapcount++;
+		if (mapcount < VSCSI_GRANT_BATCH)
+			continue;
+		err = scsiback_gnttab_data_map_batch(map, pg, grant, mapcount);
+		pg += mapcount;
+		grant += mapcount;
+		pending_req->n_grants += mapcount;
+		if (err)
+			return err;
+		mapcount = 0;
+	}
+	err = scsiback_gnttab_data_map_batch(map, pg, grant, mapcount);
+	pending_req->n_grants += mapcount;
+	return err;
+}
+
+static int scsiback_gnttab_data_map(struct vscsiif_request *ring_req,
+					struct vscsibk_pend *pending_req)
+{
+	u32 flags;
+	int i, err, n_segs, i_seg = 0;
+	struct page **pg;
+	struct scsiif_request_segment *seg;
+	unsigned long end_seg = 0;
+	unsigned int nr_segments = (unsigned int)ring_req->nr_segments;
+	unsigned int nr_sgl = 0;
+	struct scatterlist *sg;
+	grant_handle_t *grant;
+
+	pending_req->n_sg = 0;
+	pending_req->n_grants = 0;
+	pending_req->data_len = 0;
+
+	nr_segments &= ~VSCSIIF_SG_GRANT;
+	if (!nr_segments)
+		return 0;
+
+	if (nr_segments > VSCSIIF_SG_TABLESIZE) {
+		DPRINTK("xen-pvscsi: invalid parameter nr_seg = %d\n",
+			ring_req->nr_segments);
+		return -EINVAL;
+	}
+
+	if (ring_req->nr_segments & VSCSIIF_SG_GRANT) {
+		err = scsiback_gnttab_data_map_list(pending_req, ring_req->seg,
+			pending_req->pages, pending_req->grant_handles,
+			nr_segments, GNTMAP_host_map | GNTMAP_readonly);
+		if (err)
+			return err;
+		nr_sgl = nr_segments;
+		nr_segments = 0;
+		for (i = 0; i < nr_sgl; i++) {
+			n_segs = ring_req->seg[i].length /
+				 sizeof(struct scsiif_request_segment);
+			if ((unsigned)ring_req->seg[i].offset +
+			    (unsigned)ring_req->seg[i].length > PAGE_SIZE ||
+			    n_segs * sizeof(struct scsiif_request_segment) !=
+			    ring_req->seg[i].length)
+				return -EINVAL;
+			nr_segments += n_segs;
+		}
+		if (nr_segments > SG_ALL) {
+			DPRINTK("xen-pvscsi: invalid nr_seg = %d\n",
+				nr_segments);
+			return -EINVAL;
+		}
+	}
+
+	/* free of (sgl) in fast_flush_area()*/
+	pending_req->sgl = kmalloc_array(nr_segments,
+					sizeof(struct scatterlist), GFP_KERNEL);
+	if (!pending_req->sgl)
+		return -ENOMEM;
+
+	sg_init_table(pending_req->sgl, nr_segments);
+	pending_req->n_sg = nr_segments;
+
+	flags = GNTMAP_host_map;
+	if (pending_req->sc_data_direction == DMA_TO_DEVICE)
+		flags |= GNTMAP_readonly;
+
+	pg = pending_req->pages + nr_sgl;
+	grant = pending_req->grant_handles + nr_sgl;
+	if (!nr_sgl) {
+		seg = ring_req->seg;
+		err = scsiback_gnttab_data_map_list(pending_req, seg,
+			pg, grant, nr_segments, flags);
+		if (err)
+			return err;
+	} else {
+		for (i = 0; i < nr_sgl; i++) {
+			seg = (struct scsiif_request_segment *)(
+			      vaddr(pending_req, i) + ring_req->seg[i].offset);
+			n_segs = ring_req->seg[i].length /
+				 sizeof(struct scsiif_request_segment);
+			err = scsiback_gnttab_data_map_list(pending_req, seg,
+				pg, grant, n_segs, flags);
+			if (err)
+				return err;
+			pg += n_segs;
+			grant += n_segs;
+		}
+		end_seg = vaddr(pending_req, 0) + ring_req->seg[0].offset;
+		seg = (struct scsiif_request_segment *)end_seg;
+		end_seg += ring_req->seg[0].length;
+		pg = pending_req->pages + nr_sgl;
+	}
+
+	for_each_sg(pending_req->sgl, sg, nr_segments, i) {
+		sg_set_page(sg, pg[i], seg->length, seg->offset);
+		pending_req->data_len += seg->length;
+		seg++;
+		if (nr_sgl && (unsigned long)seg >= end_seg) {
+			i_seg++;
+			end_seg = vaddr(pending_req, i_seg) +
+				  ring_req->seg[i_seg].offset;
+			seg = (struct scsiif_request_segment *)end_seg;
+			end_seg += ring_req->seg[i_seg].length;
+		}
+		if (sg->offset >= PAGE_SIZE ||
+		    sg->length > PAGE_SIZE ||
+		    sg->offset + sg->length > PAGE_SIZE)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void scsiback_disconnect(struct vscsibk_info *info)
+{
+	wait_event(info->waiting_to_free,
+		atomic_read(&info->nr_unreplied_reqs) == 0);
+
+	unbind_from_irqhandler(info->irq, info);
+	info->irq = 0;
+	xenbus_unmap_ring_vfree(info->dev, info->ring.sring);
+}
+
+static void scsiback_device_action(struct vscsibk_pend *pending_req,
+	enum tcm_tmreq_table act, int tag)
+{
+	int rc, err = FAILED;
+	struct scsiback_tpg *tpg = pending_req->v2p->tpg;
+	struct se_cmd *se_cmd = &pending_req->se_cmd;
+	struct scsiback_tmr *tmr;
+
+	tmr = kzalloc(sizeof(struct scsiback_tmr), GFP_KERNEL);
+	if (!tmr)
+		goto out;
+
+	init_waitqueue_head(&tmr->tmr_wait);
+
+	transport_init_se_cmd(se_cmd, tpg->se_tpg.se_tpg_tfo,
+		tpg->tpg_nexus->tvn_se_sess, 0, DMA_NONE, MSG_SIMPLE_TAG,
+		&pending_req->sense_buffer[0]);
+
+	rc = core_tmr_alloc_req(se_cmd, tmr, act, GFP_KERNEL);
+	if (rc < 0)
+		goto out;
+
+	se_cmd->se_tmr_req->ref_task_tag = tag;
+
+	if (transport_lookup_tmr_lun(se_cmd, pending_req->v2p->lun) < 0)
+		goto out;
+
+	transport_generic_handle_tmr(se_cmd);
+	wait_event(tmr->tmr_wait, atomic_read(&tmr->tmr_complete));
+
+	err = (se_cmd->se_tmr_req->response == TMR_FUNCTION_COMPLETE) ?
+		SUCCESS : FAILED;
+
+out:
+	if (tmr) {
+		transport_generic_free_cmd(&pending_req->se_cmd, 1);
+		kfree(tmr);
+	}
+
+	scsiback_do_resp_with_sense(NULL, err, 0, pending_req);
+
+	kmem_cache_free(scsiback_cachep, pending_req);
+}
+
+/*
+  Perform virtual to physical translation
+*/
+static struct v2p_entry *scsiback_do_translation(struct vscsibk_info *info,
+			struct ids_tuple *v)
+{
+	struct v2p_entry *entry;
+	struct list_head *head = &(info->v2p_entry_lists);
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->v2p_lock, flags);
+	list_for_each_entry(entry, head, l) {
+		if ((entry->v.chn == v->chn) &&
+		    (entry->v.tgt == v->tgt) &&
+		    (entry->v.lun == v->lun)) {
+			kref_get(&entry->kref);
+			goto out;
+		}
+	}
+	entry = NULL;
+
+out:
+	spin_unlock_irqrestore(&info->v2p_lock, flags);
+	return entry;
+}
+
+static int prepare_pending_reqs(struct vscsibk_info *info,
+				struct vscsiif_request *ring_req,
+				struct vscsibk_pend *pending_req)
+{
+	struct v2p_entry *v2p;
+	struct ids_tuple vir;
+
+	pending_req->rqid       = ring_req->rqid;
+	pending_req->info       = info;
+
+	vir.chn = ring_req->channel;
+	vir.tgt = ring_req->id;
+	vir.lun = ring_req->lun;
+
+	v2p = scsiback_do_translation(info, &vir);
+	if (!v2p) {
+		pending_req->v2p = NULL;
+		DPRINTK("xen-pvscsi: doesn't exist.\n");
+		return -ENODEV;
+	}
+	pending_req->v2p = v2p;
+
+	/* request range check from frontend */
+	pending_req->sc_data_direction = ring_req->sc_data_direction;
+	if ((pending_req->sc_data_direction != DMA_BIDIRECTIONAL) &&
+		(pending_req->sc_data_direction != DMA_TO_DEVICE) &&
+		(pending_req->sc_data_direction != DMA_FROM_DEVICE) &&
+		(pending_req->sc_data_direction != DMA_NONE)) {
+		DPRINTK("xen-pvscsi: invalid parameter data_dir = %d\n",
+			pending_req->sc_data_direction);
+		return -EINVAL;
+	}
+
+	pending_req->cmd_len = ring_req->cmd_len;
+	if (pending_req->cmd_len > VSCSIIF_MAX_COMMAND_SIZE) {
+		DPRINTK("xen-pvscsi: invalid parameter cmd_len = %d\n",
+			pending_req->cmd_len);
+		return -EINVAL;
+	}
+	memcpy(pending_req->cmnd, ring_req->cmnd, pending_req->cmd_len);
+
+	return 0;
+}
+
+static int scsiback_do_cmd_fn(struct vscsibk_info *info)
+{
+	struct vscsiif_back_ring *ring = &info->ring;
+	struct vscsiif_request *ring_req;
+	struct vscsibk_pend *pending_req;
+	RING_IDX rc, rp;
+	int err, more_to_do;
+	uint32_t result;
+	uint8_t act;
+
+	rc = ring->req_cons;
+	rp = ring->sring->req_prod;
+	rmb();	/* guest system is accessing ring, too */
+
+	if (RING_REQUEST_PROD_OVERFLOW(ring, rp)) {
+		rc = ring->rsp_prod_pvt;
+		pr_warn("xen-pvscsi: Dom%d provided bogus ring requests (%#x - %#x = %u). Halting ring processing\n",
+			   info->domid, rp, rc, rp - rc);
+		info->ring_error = 1;
+		return 0;
+	}
+
+	while ((rc != rp)) {
+		if (RING_REQUEST_CONS_OVERFLOW(ring, rc))
+			break;
+		pending_req = kmem_cache_alloc(scsiback_cachep, GFP_KERNEL);
+		if (!pending_req)
+			return 1;
+
+		ring_req = RING_GET_REQUEST(ring, rc);
+		ring->req_cons = ++rc;
+
+		act = ring_req->act;
+		err = prepare_pending_reqs(info, ring_req, pending_req);
+		if (err) {
+			switch (err) {
+			case -ENODEV:
+				result = DID_NO_CONNECT;
+				break;
+			default:
+				result = DRIVER_ERROR;
+				break;
+			}
+			scsiback_do_resp_with_sense(NULL, result << 24, 0,
+						    pending_req);
+			kmem_cache_free(scsiback_cachep, pending_req);
+			return 1;
+		}
+
+		switch (act) {
+		case VSCSIIF_ACT_SCSI_CDB:
+			if (scsiback_gnttab_data_map(ring_req, pending_req)) {
+				scsiback_fast_flush_area(pending_req);
+				scsiback_do_resp_with_sense(NULL,
+					DRIVER_ERROR << 24, 0, pending_req);
+				kmem_cache_free(scsiback_cachep, pending_req);
+			} else {
+				scsiback_cmd_exec(pending_req);
+			}
+			break;
+		case VSCSIIF_ACT_SCSI_ABORT:
+			scsiback_device_action(pending_req, TMR_ABORT_TASK,
+				ring_req->ref_rqid);
+			break;
+		case VSCSIIF_ACT_SCSI_RESET:
+			scsiback_device_action(pending_req, TMR_LUN_RESET, 0);
+			break;
+		default:
+			pr_err_ratelimited("xen-pvscsi: invalid request\n");
+			scsiback_do_resp_with_sense(NULL, DRIVER_ERROR << 24,
+						    0, pending_req);
+			kmem_cache_free(scsiback_cachep, pending_req);
+			break;
+		}
+
+		/* Yield point for this unbounded loop. */
+		cond_resched();
+	}
+
+	RING_FINAL_CHECK_FOR_REQUESTS(&info->ring, more_to_do);
+	return more_to_do;
+}
+
+static irqreturn_t scsiback_irq_fn(int irq, void *dev_id)
+{
+	struct vscsibk_info *info = dev_id;
+
+	if (info->ring_error)
+		return IRQ_HANDLED;
+
+	while (scsiback_do_cmd_fn(info))
+		cond_resched();
+
+	return IRQ_HANDLED;
+}
+
+static int scsiback_init_sring(struct vscsibk_info *info, grant_ref_t ring_ref,
+			evtchn_port_t evtchn)
+{
+	void *area;
+	struct vscsiif_sring *sring;
+	int err;
+
+	if (info->irq)
+		return -1;
+
+	err = xenbus_map_ring_valloc(info->dev, ring_ref, &area);
+	if (err)
+		return err;
+
+	sring = (struct vscsiif_sring *)area;
+	BACK_RING_INIT(&info->ring, sring, PAGE_SIZE);
+
+	err = bind_interdomain_evtchn_to_irq(info->domid, evtchn);
+	if (err < 0)
+		goto unmap_page;
+
+	info->irq = err;
+
+	err = request_threaded_irq(info->irq, NULL, scsiback_irq_fn,
+				   IRQF_ONESHOT, "vscsiif-backend", info);
+	if (err)
+		goto free_irq;
+
+	return 0;
+
+free_irq:
+	unbind_from_irqhandler(info->irq, info);
+	info->irq = 0;
+unmap_page:
+	xenbus_unmap_ring_vfree(info->dev, area);
+
+	return err;
+}
+
+static int scsiback_map(struct vscsibk_info *info)
+{
+	struct xenbus_device *dev = info->dev;
+	unsigned int ring_ref, evtchn;
+	int err;
+
+	err = xenbus_gather(XBT_NIL, dev->otherend,
+			"ring-ref", "%u", &ring_ref,
+			"event-channel", "%u", &evtchn, NULL);
+	if (err) {
+		xenbus_dev_fatal(dev, err, "reading %s ring", dev->otherend);
+		return err;
+	}
+
+	return scsiback_init_sring(info, ring_ref, evtchn);
+}
+
+/*
+  Add a new translation entry
+*/
+static int scsiback_add_translation_entry(struct vscsibk_info *info,
+					  char *phy, struct ids_tuple *v)
+{
+	int err = 0;
+	struct v2p_entry *entry;
+	struct v2p_entry *new;
+	struct list_head *head = &(info->v2p_entry_lists);
+	unsigned long flags;
+	char *lunp;
+	unsigned int lun;
+	struct scsiback_tpg *tpg_entry, *tpg = NULL;
+	char *error = "doesn't exist";
+
+	lunp = strrchr(phy, ':');
+	if (!lunp) {
+		pr_err("xen-pvscsi: illegal format of physical device %s\n",
+			phy);
+		return -EINVAL;
+	}
+	*lunp = 0;
+	lunp++;
+	if (kstrtouint(lunp, 10, &lun) || lun >= TRANSPORT_MAX_LUNS_PER_TPG) {
+		pr_err("xen-pvscsi: lun number not valid: %s\n", lunp);
+		return -EINVAL;
+	}
+
+	mutex_lock(&scsiback_mutex);
+	list_for_each_entry(tpg_entry, &scsiback_list, tv_tpg_list) {
+		if (!strcmp(phy, tpg_entry->tport->tport_name) ||
+		    !strcmp(phy, tpg_entry->param_alias)) {
+			spin_lock(&tpg_entry->se_tpg.tpg_lun_lock);
+			if (tpg_entry->se_tpg.tpg_lun_list[lun]->lun_status ==
+			    TRANSPORT_LUN_STATUS_ACTIVE) {
+				if (!tpg_entry->tpg_nexus)
+					error = "nexus undefined";
+				else
+					tpg = tpg_entry;
+			}
+			spin_unlock(&tpg_entry->se_tpg.tpg_lun_lock);
+			break;
+		}
+	}
+	if (tpg) {
+		mutex_lock(&tpg->tv_tpg_mutex);
+		tpg->tv_tpg_fe_count++;
+		mutex_unlock(&tpg->tv_tpg_mutex);
+	}
+	mutex_unlock(&scsiback_mutex);
+
+	if (!tpg) {
+		pr_err("xen-pvscsi: %s:%d %s\n", phy, lun, error);
+		return -ENODEV;
+	}
+
+	new = kmalloc(sizeof(struct v2p_entry), GFP_KERNEL);
+	if (new == NULL) {
+		err = -ENOMEM;
+		goto out_free;
+	}
+
+	spin_lock_irqsave(&info->v2p_lock, flags);
+
+	/* Check double assignment to identical virtual ID */
+	list_for_each_entry(entry, head, l) {
+		if ((entry->v.chn == v->chn) &&
+		    (entry->v.tgt == v->tgt) &&
+		    (entry->v.lun == v->lun)) {
+			pr_warn("xen-pvscsi: Virtual ID is already used. Assignment was not performed.\n");
+			err = -EEXIST;
+			goto out;
+		}
+
+	}
+
+	/* Create a new translation entry and add to the list */
+	kref_init(&new->kref);
+	new->v = *v;
+	new->tpg = tpg;
+	new->lun = lun;
+	list_add_tail(&new->l, head);
+
+out:
+	spin_unlock_irqrestore(&info->v2p_lock, flags);
+
+out_free:
+	mutex_lock(&tpg->tv_tpg_mutex);
+	tpg->tv_tpg_fe_count--;
+	mutex_unlock(&tpg->tv_tpg_mutex);
+
+	if (err)
+		kfree(new);
+
+	return err;
+}
+
+static void __scsiback_del_translation_entry(struct v2p_entry *entry)
+{
+	list_del(&entry->l);
+	kref_put(&entry->kref, scsiback_free_translation_entry);
+}
+
+/*
+  Delete the translation entry specfied
+*/
+static int scsiback_del_translation_entry(struct vscsibk_info *info,
+					  struct ids_tuple *v)
+{
+	struct v2p_entry *entry;
+	struct list_head *head = &(info->v2p_entry_lists);
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->v2p_lock, flags);
+	/* Find out the translation entry specified */
+	list_for_each_entry(entry, head, l) {
+		if ((entry->v.chn == v->chn) &&
+		    (entry->v.tgt == v->tgt) &&
+		    (entry->v.lun == v->lun)) {
+			goto found;
+		}
+	}
+
+	spin_unlock_irqrestore(&info->v2p_lock, flags);
+	return 1;
+
+found:
+	/* Delete the translation entry specfied */
+	__scsiback_del_translation_entry(entry);
+
+	spin_unlock_irqrestore(&info->v2p_lock, flags);
+	return 0;
+}
+
+static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state,
+				char *phy, struct ids_tuple *vir)
+{
+	if (!scsiback_add_translation_entry(info, phy, vir)) {
+		if (xenbus_printf(XBT_NIL, info->dev->nodename, state,
+				  "%d", XenbusStateInitialised)) {
+			pr_err("xen-pvscsi: xenbus_printf error %s\n", state);
+			scsiback_del_translation_entry(info, vir);
+		}
+	} else {
+		xenbus_printf(XBT_NIL, info->dev->nodename, state,
+			      "%d", XenbusStateClosed);
+	}
+}
+
+static void scsiback_do_del_lun(struct vscsibk_info *info, const char *state,
+				struct ids_tuple *vir)
+{
+	if (!scsiback_del_translation_entry(info, vir)) {
+		if (xenbus_printf(XBT_NIL, info->dev->nodename, state,
+				  "%d", XenbusStateClosed))
+			pr_err("xen-pvscsi: xenbus_printf error %s\n", state);
+	}
+}
+
+#define VSCSIBACK_OP_ADD_OR_DEL_LUN	1
+#define VSCSIBACK_OP_UPDATEDEV_STATE	2
+
+static void scsiback_do_1lun_hotplug(struct vscsibk_info *info, int op,
+				     char *ent)
+{
+	int err;
+	struct ids_tuple vir;
+	char *val;
+	int device_state;
+	char phy[VSCSI_NAMELEN];
+	char str[64];
+	char state[64];
+	struct xenbus_device *dev = info->dev;
+
+	/* read status */
+	snprintf(state, sizeof(state), "vscsi-devs/%s/state", ent);
+	err = xenbus_scanf(XBT_NIL, dev->nodename, state, "%u", &device_state);
+	if (XENBUS_EXIST_ERR(err))
+		return;
+
+	/* physical SCSI device */
+	snprintf(str, sizeof(str), "vscsi-devs/%s/p-dev", ent);
+	val = xenbus_read(XBT_NIL, dev->nodename, str, NULL);
+	if (IS_ERR(val)) {
+		xenbus_printf(XBT_NIL, dev->nodename, state,
+			      "%d", XenbusStateClosed);
+		return;
+	}
+	strlcpy(phy, val, VSCSI_NAMELEN);
+	kfree(val);
+
+	/* virtual SCSI device */
+	snprintf(str, sizeof(str), "vscsi-devs/%s/v-dev", ent);
+	err = xenbus_scanf(XBT_NIL, dev->nodename, str, "%u:%u:%u:%u",
+			   &vir.hst, &vir.chn, &vir.tgt, &vir.lun);
+	if (XENBUS_EXIST_ERR(err)) {
+		xenbus_printf(XBT_NIL, dev->nodename, state,
+			      "%d", XenbusStateClosed);
+		return;
+	}
+
+	switch (op) {
+	case VSCSIBACK_OP_ADD_OR_DEL_LUN:
+		if (device_state == XenbusStateInitialising)
+			scsiback_do_add_lun(info, state, phy, &vir);
+		if (device_state == XenbusStateClosing)
+			scsiback_do_del_lun(info, state, &vir);
+		break;
+
+	case VSCSIBACK_OP_UPDATEDEV_STATE:
+		if (device_state == XenbusStateInitialised) {
+			/* modify vscsi-devs/dev-x/state */
+			if (xenbus_printf(XBT_NIL, dev->nodename, state,
+					  "%d", XenbusStateConnected)) {
+				pr_err("xen-pvscsi: xenbus_printf error %s\n",
+				       str);
+				scsiback_del_translation_entry(info, &vir);
+				xenbus_printf(XBT_NIL, dev->nodename, state,
+					      "%d", XenbusStateClosed);
+			}
+		}
+		break;
+	/*When it is necessary, processing is added here.*/
+	default:
+		break;
+	}
+}
+
+static void scsiback_do_lun_hotplug(struct vscsibk_info *info, int op)
+{
+	int i;
+	char **dir;
+	unsigned int ndir = 0;
+
+	dir = xenbus_directory(XBT_NIL, info->dev->nodename, "vscsi-devs",
+			       &ndir);
+	if (IS_ERR(dir))
+		return;
+
+	for (i = 0; i < ndir; i++)
+		scsiback_do_1lun_hotplug(info, op, dir[i]);
+
+	kfree(dir);
+}
+
+static void scsiback_frontend_changed(struct xenbus_device *dev,
+					enum xenbus_state frontend_state)
+{
+	struct vscsibk_info *info = dev_get_drvdata(&dev->dev);
+
+	switch (frontend_state) {
+	case XenbusStateInitialising:
+		break;
+
+	case XenbusStateInitialised:
+		if (scsiback_map(info))
+			break;
+
+		scsiback_do_lun_hotplug(info, VSCSIBACK_OP_ADD_OR_DEL_LUN);
+		xenbus_switch_state(dev, XenbusStateConnected);
+		break;
+
+	case XenbusStateConnected:
+		scsiback_do_lun_hotplug(info, VSCSIBACK_OP_UPDATEDEV_STATE);
+
+		if (dev->state == XenbusStateConnected)
+			break;
+
+		xenbus_switch_state(dev, XenbusStateConnected);
+		break;
+
+	case XenbusStateClosing:
+		if (info->irq)
+			scsiback_disconnect(info);
+
+		xenbus_switch_state(dev, XenbusStateClosing);
+		break;
+
+	case XenbusStateClosed:
+		xenbus_switch_state(dev, XenbusStateClosed);
+		if (xenbus_dev_is_online(dev))
+			break;
+		/* fall through if not online */
+	case XenbusStateUnknown:
+		device_unregister(&dev->dev);
+		break;
+
+	case XenbusStateReconfiguring:
+		scsiback_do_lun_hotplug(info, VSCSIBACK_OP_ADD_OR_DEL_LUN);
+		xenbus_switch_state(dev, XenbusStateReconfigured);
+
+		break;
+
+	default:
+		xenbus_dev_fatal(dev, -EINVAL, "saw state %d at frontend",
+					frontend_state);
+		break;
+	}
+}
+
+/*
+  Release the translation entry specfied
+*/
+static void scsiback_release_translation_entry(struct vscsibk_info *info)
+{
+	struct v2p_entry *entry, *tmp;
+	struct list_head *head = &(info->v2p_entry_lists);
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->v2p_lock, flags);
+
+	list_for_each_entry_safe(entry, tmp, head, l)
+		__scsiback_del_translation_entry(entry);
+
+	spin_unlock_irqrestore(&info->v2p_lock, flags);
+}
+
+static int scsiback_remove(struct xenbus_device *dev)
+{
+	struct vscsibk_info *info = dev_get_drvdata(&dev->dev);
+
+	if (info->irq)
+		scsiback_disconnect(info);
+
+	scsiback_release_translation_entry(info);
+
+	dev_set_drvdata(&dev->dev, NULL);
+
+	return 0;
+}
+
+static int scsiback_probe(struct xenbus_device *dev,
+			   const struct xenbus_device_id *id)
+{
+	int err;
+
+	struct vscsibk_info *info = kzalloc(sizeof(struct vscsibk_info),
+					    GFP_KERNEL);
+
+	DPRINTK("%p %d\n", dev, dev->otherend_id);
+
+	if (!info) {
+		xenbus_dev_fatal(dev, -ENOMEM, "allocating backend structure");
+		return -ENOMEM;
+	}
+	info->dev = dev;
+	dev_set_drvdata(&dev->dev, info);
+
+	info->domid = dev->otherend_id;
+	spin_lock_init(&info->ring_lock);
+	info->ring_error = 0;
+	atomic_set(&info->nr_unreplied_reqs, 0);
+	init_waitqueue_head(&info->waiting_to_free);
+	info->dev = dev;
+	info->irq = 0;
+	INIT_LIST_HEAD(&info->v2p_entry_lists);
+	spin_lock_init(&info->v2p_lock);
+
+	err = xenbus_printf(XBT_NIL, dev->nodename, "feature-sg-grant", "%u",
+			    SG_ALL);
+	if (err)
+		xenbus_dev_error(dev, err, "writing feature-sg-grant");
+
+	err = xenbus_switch_state(dev, XenbusStateInitWait);
+	if (err)
+		goto fail;
+
+	return 0;
+
+fail:
+	pr_warn("xen-pvscsi: %s failed\n", __func__);
+	scsiback_remove(dev);
+
+	return err;
+}
+
+static char *scsiback_dump_proto_id(struct scsiback_tport *tport)
+{
+	switch (tport->tport_proto_id) {
+	case SCSI_PROTOCOL_SAS:
+		return "SAS";
+	case SCSI_PROTOCOL_FCP:
+		return "FCP";
+	case SCSI_PROTOCOL_ISCSI:
+		return "iSCSI";
+	default:
+		break;
+	}
+
+	return "Unknown";
+}
+
+static u8 scsiback_get_fabric_proto_ident(struct se_portal_group *se_tpg)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg,
+				struct scsiback_tpg, se_tpg);
+	struct scsiback_tport *tport = tpg->tport;
+
+	switch (tport->tport_proto_id) {
+	case SCSI_PROTOCOL_SAS:
+		return sas_get_fabric_proto_ident(se_tpg);
+	case SCSI_PROTOCOL_FCP:
+		return fc_get_fabric_proto_ident(se_tpg);
+	case SCSI_PROTOCOL_ISCSI:
+		return iscsi_get_fabric_proto_ident(se_tpg);
+	default:
+		pr_err("Unknown tport_proto_id: 0x%02x, using SAS emulation\n",
+			tport->tport_proto_id);
+		break;
+	}
+
+	return sas_get_fabric_proto_ident(se_tpg);
+}
+
+static char *scsiback_get_fabric_wwn(struct se_portal_group *se_tpg)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg,
+				struct scsiback_tpg, se_tpg);
+	struct scsiback_tport *tport = tpg->tport;
+
+	return &tport->tport_name[0];
+}
+
+static u16 scsiback_get_tag(struct se_portal_group *se_tpg)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg,
+				struct scsiback_tpg, se_tpg);
+	return tpg->tport_tpgt;
+}
+
+static u32 scsiback_get_default_depth(struct se_portal_group *se_tpg)
+{
+	return 1;
+}
+
+static u32
+scsiback_get_pr_transport_id(struct se_portal_group *se_tpg,
+			      struct se_node_acl *se_nacl,
+			      struct t10_pr_registration *pr_reg,
+			      int *format_code,
+			      unsigned char *buf)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg,
+				struct scsiback_tpg, se_tpg);
+	struct scsiback_tport *tport = tpg->tport;
+
+	switch (tport->tport_proto_id) {
+	case SCSI_PROTOCOL_SAS:
+		return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
+					format_code, buf);
+	case SCSI_PROTOCOL_FCP:
+		return fc_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
+					format_code, buf);
+	case SCSI_PROTOCOL_ISCSI:
+		return iscsi_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
+					format_code, buf);
+	default:
+		pr_err("Unknown tport_proto_id: 0x%02x, using SAS emulation\n",
+			tport->tport_proto_id);
+		break;
+	}
+
+	return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg,
+			format_code, buf);
+}
+
+static u32
+scsiback_get_pr_transport_id_len(struct se_portal_group *se_tpg,
+				  struct se_node_acl *se_nacl,
+				  struct t10_pr_registration *pr_reg,
+				  int *format_code)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg,
+				struct scsiback_tpg, se_tpg);
+	struct scsiback_tport *tport = tpg->tport;
+
+	switch (tport->tport_proto_id) {
+	case SCSI_PROTOCOL_SAS:
+		return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
+					format_code);
+	case SCSI_PROTOCOL_FCP:
+		return fc_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
+					format_code);
+	case SCSI_PROTOCOL_ISCSI:
+		return iscsi_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
+					format_code);
+	default:
+		pr_err("Unknown tport_proto_id: 0x%02x, using SAS emulation\n",
+			tport->tport_proto_id);
+		break;
+	}
+
+	return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg,
+			format_code);
+}
+
+static char *
+scsiback_parse_pr_out_transport_id(struct se_portal_group *se_tpg,
+				    const char *buf,
+				    u32 *out_tid_len,
+				    char **port_nexus_ptr)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg,
+				struct scsiback_tpg, se_tpg);
+	struct scsiback_tport *tport = tpg->tport;
+
+	switch (tport->tport_proto_id) {
+	case SCSI_PROTOCOL_SAS:
+		return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
+					port_nexus_ptr);
+	case SCSI_PROTOCOL_FCP:
+		return fc_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
+					port_nexus_ptr);
+	case SCSI_PROTOCOL_ISCSI:
+		return iscsi_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
+					port_nexus_ptr);
+	default:
+		pr_err("Unknown tport_proto_id: 0x%02x, using SAS emulation\n",
+			tport->tport_proto_id);
+		break;
+	}
+
+	return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len,
+			port_nexus_ptr);
+}
+
+static struct se_wwn *
+scsiback_make_tport(struct target_fabric_configfs *tf,
+		     struct config_group *group,
+		     const char *name)
+{
+	struct scsiback_tport *tport;
+	char *ptr;
+	u64 wwpn = 0;
+	int off = 0;
+
+	tport = kzalloc(sizeof(struct scsiback_tport), GFP_KERNEL);
+	if (!tport)
+		return ERR_PTR(-ENOMEM);
+
+	tport->tport_wwpn = wwpn;
+	/*
+	 * Determine the emulated Protocol Identifier and Target Port Name
+	 * based on the incoming configfs directory name.
+	 */
+	ptr = strstr(name, "naa.");
+	if (ptr) {
+		tport->tport_proto_id = SCSI_PROTOCOL_SAS;
+		goto check_len;
+	}
+	ptr = strstr(name, "fc.");
+	if (ptr) {
+		tport->tport_proto_id = SCSI_PROTOCOL_FCP;
+		off = 3; /* Skip over "fc." */
+		goto check_len;
+	}
+	ptr = strstr(name, "iqn.");
+	if (ptr) {
+		tport->tport_proto_id = SCSI_PROTOCOL_ISCSI;
+		goto check_len;
+	}
+
+	pr_err("Unable to locate prefix for emulated Target Port: %s\n", name);
+	kfree(tport);
+	return ERR_PTR(-EINVAL);
+
+check_len:
+	if (strlen(name) >= VSCSI_NAMELEN) {
+		pr_err("Emulated %s Address: %s, exceeds max: %d\n", name,
+			scsiback_dump_proto_id(tport), VSCSI_NAMELEN);
+		kfree(tport);
+		return ERR_PTR(-EINVAL);
+	}
+	snprintf(&tport->tport_name[0], VSCSI_NAMELEN, "%s", &name[off]);
+
+	pr_debug("xen-pvscsi: Allocated emulated Target %s Address: %s\n",
+		 scsiback_dump_proto_id(tport), name);
+
+	return &tport->tport_wwn;
+}
+
+static void scsiback_drop_tport(struct se_wwn *wwn)
+{
+	struct scsiback_tport *tport = container_of(wwn,
+				struct scsiback_tport, tport_wwn);
+
+	pr_debug("xen-pvscsi: Deallocating emulated Target %s Address: %s\n",
+		 scsiback_dump_proto_id(tport), tport->tport_name);
+
+	kfree(tport);
+}
+
+static struct se_node_acl *
+scsiback_alloc_fabric_acl(struct se_portal_group *se_tpg)
+{
+	return kzalloc(sizeof(struct se_node_acl), GFP_KERNEL);
+}
+
+static void
+scsiback_release_fabric_acl(struct se_portal_group *se_tpg,
+			     struct se_node_acl *se_nacl)
+{
+	kfree(se_nacl);
+}
+
+static u32 scsiback_tpg_get_inst_index(struct se_portal_group *se_tpg)
+{
+	return 1;
+}
+
+static int scsiback_check_stop_free(struct se_cmd *se_cmd)
+{
+	/*
+	 * Do not release struct se_cmd's containing a valid TMR
+	 * pointer.  These will be released directly in scsiback_device_action()
+	 * with transport_generic_free_cmd().
+	 */
+	if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)
+		return 0;
+
+	transport_generic_free_cmd(se_cmd, 0);
+	return 1;
+}
+
+static void scsiback_release_cmd(struct se_cmd *se_cmd)
+{
+	struct vscsibk_pend *pending_req = container_of(se_cmd,
+				struct vscsibk_pend, se_cmd);
+
+	kmem_cache_free(scsiback_cachep, pending_req);
+}
+
+static int scsiback_shutdown_session(struct se_session *se_sess)
+{
+	return 0;
+}
+
+static void scsiback_close_session(struct se_session *se_sess)
+{
+}
+
+static u32 scsiback_sess_get_index(struct se_session *se_sess)
+{
+	return 0;
+}
+
+static int scsiback_write_pending(struct se_cmd *se_cmd)
+{
+	/* Go ahead and process the write immediately */
+	target_execute_cmd(se_cmd);
+
+	return 0;
+}
+
+static int scsiback_write_pending_status(struct se_cmd *se_cmd)
+{
+	return 0;
+}
+
+static void scsiback_set_default_node_attrs(struct se_node_acl *nacl)
+{
+}
+
+static u32 scsiback_get_task_tag(struct se_cmd *se_cmd)
+{
+	struct vscsibk_pend *pending_req = container_of(se_cmd,
+				struct vscsibk_pend, se_cmd);
+
+	return pending_req->rqid;
+}
+
+static int scsiback_get_cmd_state(struct se_cmd *se_cmd)
+{
+	return 0;
+}
+
+static int scsiback_queue_data_in(struct se_cmd *se_cmd)
+{
+	struct vscsibk_pend *pending_req = container_of(se_cmd,
+				struct vscsibk_pend, se_cmd);
+
+	pending_req->result = SAM_STAT_GOOD;
+	scsiback_cmd_done(pending_req);
+	return 0;
+}
+
+static int scsiback_queue_status(struct se_cmd *se_cmd)
+{
+	struct vscsibk_pend *pending_req = container_of(se_cmd,
+				struct vscsibk_pend, se_cmd);
+
+	if (se_cmd->sense_buffer &&
+	    ((se_cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) ||
+	     (se_cmd->se_cmd_flags & SCF_EMULATED_TASK_SENSE)))
+		pending_req->result = (DRIVER_SENSE << 24) |
+				      SAM_STAT_CHECK_CONDITION;
+	else
+		pending_req->result = se_cmd->scsi_status;
+
+	scsiback_cmd_done(pending_req);
+	return 0;
+}
+
+static void scsiback_queue_tm_rsp(struct se_cmd *se_cmd)
+{
+	struct se_tmr_req *se_tmr = se_cmd->se_tmr_req;
+	struct scsiback_tmr *tmr = se_tmr->fabric_tmr_ptr;
+
+	atomic_set(&tmr->tmr_complete, 1);
+	wake_up(&tmr->tmr_wait);
+}
+
+static void scsiback_aborted_task(struct se_cmd *se_cmd)
+{
+}
+
+static ssize_t scsiback_tpg_param_show_alias(struct se_portal_group *se_tpg,
+					     char *page)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg, struct scsiback_tpg,
+						se_tpg);
+	ssize_t rb;
+
+	mutex_lock(&tpg->tv_tpg_mutex);
+	rb = snprintf(page, PAGE_SIZE, "%s\n", tpg->param_alias);
+	mutex_unlock(&tpg->tv_tpg_mutex);
+
+	return rb;
+}
+
+static ssize_t scsiback_tpg_param_store_alias(struct se_portal_group *se_tpg,
+					      const char *page, size_t count)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg, struct scsiback_tpg,
+						se_tpg);
+	int len;
+
+	if (strlen(page) >= VSCSI_NAMELEN) {
+		pr_err("param alias: %s, exceeds max: %d\n", page,
+			VSCSI_NAMELEN);
+		return -EINVAL;
+	}
+
+	mutex_lock(&tpg->tv_tpg_mutex);
+	len = snprintf(tpg->param_alias, VSCSI_NAMELEN, "%s", page);
+	if (tpg->param_alias[len - 1] == '\n')
+		tpg->param_alias[len - 1] = '\0';
+	mutex_unlock(&tpg->tv_tpg_mutex);
+
+	return count;
+}
+
+TF_TPG_PARAM_ATTR(scsiback, alias, S_IRUGO | S_IWUSR);
+
+static struct configfs_attribute *scsiback_param_attrs[] = {
+	&scsiback_tpg_param_alias.attr,
+	NULL,
+};
+
+static int scsiback_make_nexus(struct scsiback_tpg *tpg,
+				const char *name)
+{
+	struct se_portal_group *se_tpg;
+	struct se_session *se_sess;
+	struct scsiback_nexus *tv_nexus;
+
+	mutex_lock(&tpg->tv_tpg_mutex);
+	if (tpg->tpg_nexus) {
+		mutex_unlock(&tpg->tv_tpg_mutex);
+		pr_debug("tpg->tpg_nexus already exists\n");
+		return -EEXIST;
+	}
+	se_tpg = &tpg->se_tpg;
+
+	tv_nexus = kzalloc(sizeof(struct scsiback_nexus), GFP_KERNEL);
+	if (!tv_nexus) {
+		mutex_unlock(&tpg->tv_tpg_mutex);
+		return -ENOMEM;
+	}
+	/*
+	 *  Initialize the struct se_session pointer
+	 */
+	tv_nexus->tvn_se_sess = transport_init_session(TARGET_PROT_NORMAL);
+	if (IS_ERR(tv_nexus->tvn_se_sess)) {
+		mutex_unlock(&tpg->tv_tpg_mutex);
+		kfree(tv_nexus);
+		return -ENOMEM;
+	}
+	se_sess = tv_nexus->tvn_se_sess;
+	/*
+	 * Since we are running in 'demo mode' this call with generate a
+	 * struct se_node_acl for the scsiback struct se_portal_group with
+	 * the SCSI Initiator port name of the passed configfs group 'name'.
+	 */
+	tv_nexus->tvn_se_sess->se_node_acl = core_tpg_check_initiator_node_acl(
+				se_tpg, (unsigned char *)name);
+	if (!tv_nexus->tvn_se_sess->se_node_acl) {
+		mutex_unlock(&tpg->tv_tpg_mutex);
+		pr_debug("core_tpg_check_initiator_node_acl() failed for %s\n",
+			 name);
+		goto out;
+	}
+	/*
+	 * Now register the TCM pvscsi virtual I_T Nexus as active with the
+	 * call to __transport_register_session()
+	 */
+	__transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl,
+			tv_nexus->tvn_se_sess, tv_nexus);
+	tpg->tpg_nexus = tv_nexus;
+
+	mutex_unlock(&tpg->tv_tpg_mutex);
+	return 0;
+
+out:
+	transport_free_session(se_sess);
+	kfree(tv_nexus);
+	return -ENOMEM;
+}
+
+static int scsiback_drop_nexus(struct scsiback_tpg *tpg)
+{
+	struct se_session *se_sess;
+	struct scsiback_nexus *tv_nexus;
+
+	mutex_lock(&tpg->tv_tpg_mutex);
+	tv_nexus = tpg->tpg_nexus;
+	if (!tv_nexus) {
+		mutex_unlock(&tpg->tv_tpg_mutex);
+		return -ENODEV;
+	}
+
+	se_sess = tv_nexus->tvn_se_sess;
+	if (!se_sess) {
+		mutex_unlock(&tpg->tv_tpg_mutex);
+		return -ENODEV;
+	}
+
+	if (tpg->tv_tpg_port_count != 0) {
+		mutex_unlock(&tpg->tv_tpg_mutex);
+		pr_err("Unable to remove xen-pvscsi I_T Nexus with active TPG port count: %d\n",
+			tpg->tv_tpg_port_count);
+		return -EBUSY;
+	}
+
+	if (tpg->tv_tpg_fe_count != 0) {
+		mutex_unlock(&tpg->tv_tpg_mutex);
+		pr_err("Unable to remove xen-pvscsi I_T Nexus with active TPG frontend count: %d\n",
+			tpg->tv_tpg_fe_count);
+		return -EBUSY;
+	}
+
+	pr_debug("xen-pvscsi: Removing I_T Nexus to emulated %s Initiator Port: %s\n",
+		scsiback_dump_proto_id(tpg->tport),
+		tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
+
+	/*
+	 * Release the SCSI I_T Nexus to the emulated xen-pvscsi Target Port
+	 */
+	transport_deregister_session(tv_nexus->tvn_se_sess);
+	tpg->tpg_nexus = NULL;
+	mutex_unlock(&tpg->tv_tpg_mutex);
+
+	kfree(tv_nexus);
+	return 0;
+}
+
+static ssize_t scsiback_tpg_show_nexus(struct se_portal_group *se_tpg,
+					char *page)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg,
+				struct scsiback_tpg, se_tpg);
+	struct scsiback_nexus *tv_nexus;
+	ssize_t ret;
+
+	mutex_lock(&tpg->tv_tpg_mutex);
+	tv_nexus = tpg->tpg_nexus;
+	if (!tv_nexus) {
+		mutex_unlock(&tpg->tv_tpg_mutex);
+		return -ENODEV;
+	}
+	ret = snprintf(page, PAGE_SIZE, "%s\n",
+			tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
+	mutex_unlock(&tpg->tv_tpg_mutex);
+
+	return ret;
+}
+
+static ssize_t scsiback_tpg_store_nexus(struct se_portal_group *se_tpg,
+					 const char *page,
+					 size_t count)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg,
+				struct scsiback_tpg, se_tpg);
+	struct scsiback_tport *tport_wwn = tpg->tport;
+	unsigned char i_port[VSCSI_NAMELEN], *ptr, *port_ptr;
+	int ret;
+	/*
+	 * Shutdown the active I_T nexus if 'NULL' is passed..
+	 */
+	if (!strncmp(page, "NULL", 4)) {
+		ret = scsiback_drop_nexus(tpg);
+		return (!ret) ? count : ret;
+	}
+	/*
+	 * Otherwise make sure the passed virtual Initiator port WWN matches
+	 * the fabric protocol_id set in scsiback_make_tport(), and call
+	 * scsiback_make_nexus().
+	 */
+	if (strlen(page) >= VSCSI_NAMELEN) {
+		pr_err("Emulated NAA Sas Address: %s, exceeds max: %d\n",
+			page, VSCSI_NAMELEN);
+		return -EINVAL;
+	}
+	snprintf(&i_port[0], VSCSI_NAMELEN, "%s", page);
+
+	ptr = strstr(i_port, "naa.");
+	if (ptr) {
+		if (tport_wwn->tport_proto_id != SCSI_PROTOCOL_SAS) {
+			pr_err("Passed SAS Initiator Port %s does not match target port protoid: %s\n",
+				i_port, scsiback_dump_proto_id(tport_wwn));
+			return -EINVAL;
+		}
+		port_ptr = &i_port[0];
+		goto check_newline;
+	}
+	ptr = strstr(i_port, "fc.");
+	if (ptr) {
+		if (tport_wwn->tport_proto_id != SCSI_PROTOCOL_FCP) {
+			pr_err("Passed FCP Initiator Port %s does not match target port protoid: %s\n",
+				i_port, scsiback_dump_proto_id(tport_wwn));
+			return -EINVAL;
+		}
+		port_ptr = &i_port[3]; /* Skip over "fc." */
+		goto check_newline;
+	}
+	ptr = strstr(i_port, "iqn.");
+	if (ptr) {
+		if (tport_wwn->tport_proto_id != SCSI_PROTOCOL_ISCSI) {
+			pr_err("Passed iSCSI Initiator Port %s does not match target port protoid: %s\n",
+				i_port, scsiback_dump_proto_id(tport_wwn));
+			return -EINVAL;
+		}
+		port_ptr = &i_port[0];
+		goto check_newline;
+	}
+	pr_err("Unable to locate prefix for emulated Initiator Port: %s\n",
+		i_port);
+	return -EINVAL;
+	/*
+	 * Clear any trailing newline for the NAA WWN
+	 */
+check_newline:
+	if (i_port[strlen(i_port) - 1] == '\n')
+		i_port[strlen(i_port) - 1] = '\0';
+
+	ret = scsiback_make_nexus(tpg, port_ptr);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+
+TF_TPG_BASE_ATTR(scsiback, nexus, S_IRUGO | S_IWUSR);
+
+static struct configfs_attribute *scsiback_tpg_attrs[] = {
+	&scsiback_tpg_nexus.attr,
+	NULL,
+};
+
+static ssize_t
+scsiback_wwn_show_attr_version(struct target_fabric_configfs *tf,
+				char *page)
+{
+	return sprintf(page, "xen-pvscsi fabric module %s on %s/%s on "
+		UTS_RELEASE"\n",
+		VSCSI_VERSION, utsname()->sysname, utsname()->machine);
+}
+
+TF_WWN_ATTR_RO(scsiback, version);
+
+static struct configfs_attribute *scsiback_wwn_attrs[] = {
+	&scsiback_wwn_version.attr,
+	NULL,
+};
+
+static char *scsiback_get_fabric_name(void)
+{
+	return "xen-pvscsi";
+}
+
+static int scsiback_port_link(struct se_portal_group *se_tpg,
+			       struct se_lun *lun)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg,
+				struct scsiback_tpg, se_tpg);
+
+	mutex_lock(&tpg->tv_tpg_mutex);
+	tpg->tv_tpg_port_count++;
+	mutex_unlock(&tpg->tv_tpg_mutex);
+
+	return 0;
+}
+
+static void scsiback_port_unlink(struct se_portal_group *se_tpg,
+				  struct se_lun *lun)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg,
+				struct scsiback_tpg, se_tpg);
+
+	mutex_lock(&tpg->tv_tpg_mutex);
+	tpg->tv_tpg_port_count--;
+	mutex_unlock(&tpg->tv_tpg_mutex);
+}
+
+static struct se_portal_group *
+scsiback_make_tpg(struct se_wwn *wwn,
+		   struct config_group *group,
+		   const char *name)
+{
+	struct scsiback_tport *tport = container_of(wwn,
+			struct scsiback_tport, tport_wwn);
+
+	struct scsiback_tpg *tpg;
+	u16 tpgt;
+	int ret;
+
+	if (strstr(name, "tpgt_") != name)
+		return ERR_PTR(-EINVAL);
+	ret = kstrtou16(name + 5, 10, &tpgt);
+	if (ret)
+		return ERR_PTR(ret);
+
+	tpg = kzalloc(sizeof(struct scsiback_tpg), GFP_KERNEL);
+	if (!tpg)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&tpg->tv_tpg_mutex);
+	INIT_LIST_HEAD(&tpg->tv_tpg_list);
+	INIT_LIST_HEAD(&tpg->info_list);
+	tpg->tport = tport;
+	tpg->tport_tpgt = tpgt;
+
+	ret = core_tpg_register(&scsiback_fabric_configfs->tf_ops, wwn,
+				&tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL);
+	if (ret < 0) {
+		kfree(tpg);
+		return NULL;
+	}
+	mutex_lock(&scsiback_mutex);
+	list_add_tail(&tpg->tv_tpg_list, &scsiback_list);
+	mutex_unlock(&scsiback_mutex);
+
+	return &tpg->se_tpg;
+}
+
+static void scsiback_drop_tpg(struct se_portal_group *se_tpg)
+{
+	struct scsiback_tpg *tpg = container_of(se_tpg,
+				struct scsiback_tpg, se_tpg);
+
+	mutex_lock(&scsiback_mutex);
+	list_del(&tpg->tv_tpg_list);
+	mutex_unlock(&scsiback_mutex);
+	/*
+	 * Release the virtual I_T Nexus for this xen-pvscsi TPG
+	 */
+	scsiback_drop_nexus(tpg);
+	/*
+	 * Deregister the se_tpg from TCM..
+	 */
+	core_tpg_deregister(se_tpg);
+	kfree(tpg);
+}
+
+static int scsiback_check_true(struct se_portal_group *se_tpg)
+{
+	return 1;
+}
+
+static int scsiback_check_false(struct se_portal_group *se_tpg)
+{
+	return 0;
+}
+
+static struct target_core_fabric_ops scsiback_ops = {
+	.get_fabric_name		= scsiback_get_fabric_name,
+	.get_fabric_proto_ident		= scsiback_get_fabric_proto_ident,
+	.tpg_get_wwn			= scsiback_get_fabric_wwn,
+	.tpg_get_tag			= scsiback_get_tag,
+	.tpg_get_default_depth		= scsiback_get_default_depth,
+	.tpg_get_pr_transport_id	= scsiback_get_pr_transport_id,
+	.tpg_get_pr_transport_id_len	= scsiback_get_pr_transport_id_len,
+	.tpg_parse_pr_out_transport_id	= scsiback_parse_pr_out_transport_id,
+	.tpg_check_demo_mode		= scsiback_check_true,
+	.tpg_check_demo_mode_cache	= scsiback_check_true,
+	.tpg_check_demo_mode_write_protect = scsiback_check_false,
+	.tpg_check_prod_mode_write_protect = scsiback_check_false,
+	.tpg_alloc_fabric_acl		= scsiback_alloc_fabric_acl,
+	.tpg_release_fabric_acl		= scsiback_release_fabric_acl,
+	.tpg_get_inst_index		= scsiback_tpg_get_inst_index,
+	.check_stop_free		= scsiback_check_stop_free,
+	.release_cmd			= scsiback_release_cmd,
+	.put_session			= NULL,
+	.shutdown_session		= scsiback_shutdown_session,
+	.close_session			= scsiback_close_session,
+	.sess_get_index			= scsiback_sess_get_index,
+	.sess_get_initiator_sid		= NULL,
+	.write_pending			= scsiback_write_pending,
+	.write_pending_status		= scsiback_write_pending_status,
+	.set_default_node_attributes	= scsiback_set_default_node_attrs,
+	.get_task_tag			= scsiback_get_task_tag,
+	.get_cmd_state			= scsiback_get_cmd_state,
+	.queue_data_in			= scsiback_queue_data_in,
+	.queue_status			= scsiback_queue_status,
+	.queue_tm_rsp			= scsiback_queue_tm_rsp,
+	.aborted_task			= scsiback_aborted_task,
+	/*
+	 * Setup callers for generic logic in target_core_fabric_configfs.c
+	 */
+	.fabric_make_wwn		= scsiback_make_tport,
+	.fabric_drop_wwn		= scsiback_drop_tport,
+	.fabric_make_tpg		= scsiback_make_tpg,
+	.fabric_drop_tpg		= scsiback_drop_tpg,
+	.fabric_post_link		= scsiback_port_link,
+	.fabric_pre_unlink		= scsiback_port_unlink,
+	.fabric_make_np			= NULL,
+	.fabric_drop_np			= NULL,
+#if 0
+	.fabric_make_nodeacl		= scsiback_make_nodeacl,
+	.fabric_drop_nodeacl		= scsiback_drop_nodeacl,
+#endif
+};
+
+static int scsiback_register_configfs(void)
+{
+	struct target_fabric_configfs *fabric;
+	int ret;
+
+	pr_debug("xen-pvscsi: fabric module %s on %s/%s on "UTS_RELEASE"\n",
+		 VSCSI_VERSION, utsname()->sysname, utsname()->machine);
+	/*
+	 * Register the top level struct config_item_type with TCM core
+	 */
+	fabric = target_fabric_configfs_init(THIS_MODULE, "xen-pvscsi");
+	if (IS_ERR(fabric))
+		return PTR_ERR(fabric);
+
+	/*
+	 * Setup fabric->tf_ops from our local scsiback_ops
+	 */
+	fabric->tf_ops = scsiback_ops;
+	/*
+	 * Setup default attribute lists for various fabric->tf_cit_tmpl
+	 */
+	fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = scsiback_wwn_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = scsiback_tpg_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = scsiback_param_attrs;
+	fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_base_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_attrib_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_auth_cit.ct_attrs = NULL;
+	fabric->tf_cit_tmpl.tfc_tpg_nacl_param_cit.ct_attrs = NULL;
+	/*
+	 * Register the fabric for use within TCM
+	 */
+	ret = target_fabric_configfs_register(fabric);
+	if (ret < 0) {
+		target_fabric_configfs_free(fabric);
+		return ret;
+	}
+	/*
+	 * Setup our local pointer to *fabric
+	 */
+	scsiback_fabric_configfs = fabric;
+	pr_debug("xen-pvscsi: Set fabric -> scsiback_fabric_configfs\n");
+	return 0;
+};
+
+static void scsiback_deregister_configfs(void)
+{
+	if (!scsiback_fabric_configfs)
+		return;
+
+	target_fabric_configfs_deregister(scsiback_fabric_configfs);
+	scsiback_fabric_configfs = NULL;
+	pr_debug("xen-pvscsi: Cleared scsiback_fabric_configfs\n");
+};
+
+static const struct xenbus_device_id scsiback_ids[] = {
+	{ "vscsi" },
+	{ "" }
+};
+
+static struct xenbus_driver scsiback_driver = {
+	.ids			= scsiback_ids,
+	.probe			= scsiback_probe,
+	.remove			= scsiback_remove,
+	.otherend_changed	= scsiback_frontend_changed
+};
+
+static void scsiback_init_pend(void *p)
+{
+	struct vscsibk_pend *pend = p;
+	int i;
+
+	memset(pend, 0, sizeof(*pend));
+	for (i = 0; i < VSCSI_MAX_GRANTS; i++)
+		pend->grant_handles[i] = SCSIBACK_INVALID_HANDLE;
+}
+
+static int __init scsiback_init(void)
+{
+	int ret;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	scsiback_cachep = kmem_cache_create("vscsiif_cache",
+		sizeof(struct vscsibk_pend), 0, 0, scsiback_init_pend);
+	if (!scsiback_cachep)
+		return -ENOMEM;
+
+	ret = xenbus_register_backend(&scsiback_driver);
+	if (ret)
+		goto out_cache_destroy;
+
+	ret = scsiback_register_configfs();
+	if (ret)
+		goto out_unregister_xenbus;
+
+	return 0;
+
+out_unregister_xenbus:
+	xenbus_unregister_driver(&scsiback_driver);
+out_cache_destroy:
+	kmem_cache_destroy(scsiback_cachep);
+	pr_err("xen-pvscsi: %s: error %d\n", __func__, ret);
+	return ret;
+}
+
+static void __exit scsiback_exit(void)
+{
+	struct page *page;
+
+	while (free_pages_num) {
+		if (get_free_page(&page))
+			BUG();
+		free_xenballooned_pages(1, &page);
+	}
+	scsiback_deregister_configfs();
+	xenbus_unregister_driver(&scsiback_driver);
+	kmem_cache_destroy(scsiback_cachep);
+}
+
+module_init(scsiback_init);
+module_exit(scsiback_exit);
+
+MODULE_DESCRIPTION("Xen SCSI backend driver");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_ALIAS("xen-backend:vscsi");
+MODULE_AUTHOR("Juergen Gross <jgross@suse.com>");
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 439c9dca9eee..ca744102b666 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -259,7 +259,6 @@ static char *error_path(struct xenbus_device *dev)
 static void xenbus_va_dev_error(struct xenbus_device *dev, int err,
 				const char *fmt, va_list ap)
 {
-	int ret;
 	unsigned int len;
 	char *printf_buffer = NULL;
 	char *path_buffer = NULL;
@@ -270,9 +269,7 @@ static void xenbus_va_dev_error(struct xenbus_device *dev, int err,
 		goto fail;
 
 	len = sprintf(printf_buffer, "%i ", -err);
-	ret = vsnprintf(printf_buffer+len, PRINTF_BUFFER_SIZE-len, fmt, ap);
-
-	BUG_ON(len + ret > PRINTF_BUFFER_SIZE-1);
+	vsnprintf(printf_buffer+len, PRINTF_BUFFER_SIZE-len, fmt, ap);
 
 	dev_err(&dev->dev, "%s\n", printf_buffer);
 
@@ -361,8 +358,8 @@ static void xenbus_switch_fatal(struct xenbus_device *dev, int depth, int err,
  * @ring_mfn: mfn of ring to grant
 
  * Grant access to the given @ring_mfn to the peer of the given device.  Return
- * 0 on success, or -errno on error.  On error, the device will switch to
- * XenbusStateClosing, and the error will be saved in the store.
+ * a grant reference on success, or -errno on error. On error, the device will
+ * switch to XenbusStateClosing, and the error will be saved in the store.
  */
 int xenbus_grant_ring(struct xenbus_device *dev, unsigned long ring_mfn)
 {
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 3c0a74b3e9b1..564b31584860 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -297,9 +297,13 @@ void xenbus_dev_shutdown(struct device *_dev)
 EXPORT_SYMBOL_GPL(xenbus_dev_shutdown);
 
 int xenbus_register_driver_common(struct xenbus_driver *drv,
-				  struct xen_bus_type *bus)
+				  struct xen_bus_type *bus,
+				  struct module *owner, const char *mod_name)
 {
+	drv->driver.name = drv->name ? drv->name : drv->ids[0].devicetype;
 	drv->driver.bus = &bus->bus;
+	drv->driver.owner = owner;
+	drv->driver.mod_name = mod_name;
 
 	return driver_register(&drv->driver);
 }
diff --git a/drivers/xen/xenbus/xenbus_probe.h b/drivers/xen/xenbus/xenbus_probe.h
index 1085ec294a19..c9ec7ca1f7ab 100644
--- a/drivers/xen/xenbus/xenbus_probe.h
+++ b/drivers/xen/xenbus/xenbus_probe.h
@@ -60,7 +60,9 @@ extern int xenbus_match(struct device *_dev, struct device_driver *_drv);
 extern int xenbus_dev_probe(struct device *_dev);
 extern int xenbus_dev_remove(struct device *_dev);
 extern int xenbus_register_driver_common(struct xenbus_driver *drv,
-					 struct xen_bus_type *bus);
+					 struct xen_bus_type *bus,
+					 struct module *owner,
+					 const char *mod_name);
 extern int xenbus_probe_node(struct xen_bus_type *bus,
 			     const char *type,
 			     const char *nodename);
diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c
index 5125dce11a60..04f7f85a5edf 100644
--- a/drivers/xen/xenbus/xenbus_probe_backend.c
+++ b/drivers/xen/xenbus/xenbus_probe_backend.c
@@ -234,13 +234,15 @@ int xenbus_dev_is_online(struct xenbus_device *dev)
 }
 EXPORT_SYMBOL_GPL(xenbus_dev_is_online);
 
-int xenbus_register_backend(struct xenbus_driver *drv)
+int __xenbus_register_backend(struct xenbus_driver *drv, struct module *owner,
+			      const char *mod_name)
 {
 	drv->read_otherend_details = read_frontend_details;
 
-	return xenbus_register_driver_common(drv, &xenbus_backend);
+	return xenbus_register_driver_common(drv, &xenbus_backend,
+					     owner, mod_name);
 }
-EXPORT_SYMBOL_GPL(xenbus_register_backend);
+EXPORT_SYMBOL_GPL(__xenbus_register_backend);
 
 static int backend_probe_and_watch(struct notifier_block *notifier,
 				   unsigned long event,
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index cb385c10d2b1..bcb53bdc469c 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -317,13 +317,15 @@ static void wait_for_devices(struct xenbus_driver *xendrv)
 			 print_device_status);
 }
 
-int xenbus_register_frontend(struct xenbus_driver *drv)
+int __xenbus_register_frontend(struct xenbus_driver *drv, struct module *owner,
+			       const char *mod_name)
 {
 	int ret;
 
 	drv->read_otherend_details = read_backend_details;
 
-	ret = xenbus_register_driver_common(drv, &xenbus_frontend);
+	ret = xenbus_register_driver_common(drv, &xenbus_frontend,
+					    owner, mod_name);
 	if (ret)
 		return ret;
 
@@ -332,7 +334,7 @@ int xenbus_register_frontend(struct xenbus_driver *drv)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(xenbus_register_frontend);
+EXPORT_SYMBOL_GPL(__xenbus_register_frontend);
 
 static DECLARE_WAIT_QUEUE_HEAD(backend_state_wq);
 static int backend_state;
diff --git a/firmware/Makefile b/firmware/Makefile
index 0862d34cf7d1..e297e1b52636 100644
--- a/firmware/Makefile
+++ b/firmware/Makefile
@@ -232,6 +232,6 @@ targets := $(fw-shipped-) $(patsubst $(obj)/%,%, \
 
 # Without this, built-in.o won't be created when it's empty, and the
 # final vmlinux link will fail.
-obj-n := dummy
+obj- := dummy
 
 hostprogs-y := ihex2fw
diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index d51ec9fafcc8..47db55aee7f2 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -65,8 +65,8 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
 {
 	struct p9_fid *fid, *ret;
 
-	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p) uid %d any %d\n",
-		 dentry->d_name.name, dentry, from_kuid(&init_user_ns, uid),
+	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p) uid %d any %d\n",
+		 dentry, dentry, from_kuid(&init_user_ns, uid),
 		 any);
 	ret = NULL;
 	/* we'll recheck under lock if there's anything to look in */
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index cc1cfae726b3..eb14e055ea83 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -266,8 +266,8 @@ v9fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 	 * Now that we do caching with cache mode enabled, We need
 	 * to support direct IO
 	 */
-	p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%s) off/no(%lld/%lu) EINVAL\n",
-		 iocb->ki_filp->f_path.dentry->d_name.name,
+	p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%pD) off/no(%lld/%lu) EINVAL\n",
+		 iocb->ki_filp,
 		 (long long)pos, iter->nr_segs);
 
 	return -EINVAL;
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index b03dd23feda8..a345b2d659cc 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -49,8 +49,8 @@
  */
 static int v9fs_cached_dentry_delete(const struct dentry *dentry)
 {
-	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n",
-		 dentry->d_name.name, dentry);
+	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
+		 dentry, dentry);
 
 	/* Don't cache negative dentries */
 	if (!dentry->d_inode)
@@ -67,8 +67,8 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry)
 static void v9fs_dentry_release(struct dentry *dentry)
 {
 	struct hlist_node *p, *n;
-	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n",
-		 dentry->d_name.name, dentry);
+	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
+		 dentry, dentry);
 	hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata)
 		p9_client_clunk(hlist_entry(p, struct p9_fid, dlist));
 	dentry->d_fsdata = NULL;
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index 0b3bfa303dda..4f1151088ebe 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -116,7 +116,7 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
 	int reclen = 0;
 	struct p9_rdir *rdir;
 
-	p9_debug(P9_DEBUG_VFS, "name %s\n", file->f_path.dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "name %pD\n", file);
 	fid = file->private_data;
 
 	buflen = fid->clnt->msize - P9_IOHDRSZ;
@@ -172,7 +172,7 @@ static int v9fs_dir_readdir_dotl(struct file *file, struct dir_context *ctx)
 	struct p9_rdir *rdir;
 	struct p9_dirent curdirent;
 
-	p9_debug(P9_DEBUG_VFS, "name %s\n", file->f_path.dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "name %pD\n", file);
 	fid = file->private_data;
 
 	buflen = fid->clnt->msize - P9_READDIRHDRSZ;
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 520c11c2dcca..5594505e6e73 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -301,8 +301,8 @@ static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl)
 	struct inode *inode = file_inode(filp);
 	int ret = -ENOLCK;
 
-	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n",
-		 filp, cmd, fl, filp->f_path.dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
+		 filp, cmd, fl, filp);
 
 	/* No mandatory locks */
 	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
@@ -337,8 +337,8 @@ static int v9fs_file_flock_dotl(struct file *filp, int cmd,
 	struct inode *inode = file_inode(filp);
 	int ret = -ENOLCK;
 
-	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n",
-		 filp, cmd, fl, filp->f_path.dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
+		 filp, cmd, fl, filp);
 
 	/* No mandatory locks */
 	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 7fa4f7a7653d..296482fc77a9 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -648,7 +648,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 	struct p9_fid *dfid, *ofid, *fid;
 	struct inode *inode;
 
-	p9_debug(P9_DEBUG_VFS, "name %s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
 
 	err = 0;
 	ofid = NULL;
@@ -755,7 +755,7 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 	struct p9_fid *fid;
 	struct v9fs_session_info *v9ses;
 
-	p9_debug(P9_DEBUG_VFS, "name %s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
 	err = 0;
 	v9ses = v9fs_inode2v9ses(dir);
 	perm = unixmode2p9mode(v9ses, mode | S_IFDIR);
@@ -791,8 +791,8 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	char *name;
 
-	p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p flags: %x\n",
-		 dir, dentry->d_name.name, dentry, flags);
+	p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%pd) %p flags: %x\n",
+		 dir, dentry, dentry, flags);
 
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -1239,7 +1239,7 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 	struct p9_fid *fid;
 	struct p9_wstat *st;
 
-	p9_debug(P9_DEBUG_VFS, " %s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, " %pd\n", dentry);
 	retval = -EPERM;
 	v9ses = v9fs_dentry2v9ses(dentry);
 	fid = v9fs_fid_lookup(dentry);
@@ -1262,8 +1262,8 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 	retval = min(strlen(st->extension)+1, (size_t)buflen);
 	memcpy(buffer, st->extension, retval);
 
-	p9_debug(P9_DEBUG_VFS, "%s -> %s (%.*s)\n",
-		 dentry->d_name.name, st->extension, buflen, buffer);
+	p9_debug(P9_DEBUG_VFS, "%pd -> %s (%.*s)\n",
+		 dentry, st->extension, buflen, buffer);
 
 done:
 	p9stat_free(st);
@@ -1283,7 +1283,7 @@ static void *v9fs_vfs_follow_link(struct dentry *dentry, struct nameidata *nd)
 	int len = 0;
 	char *link = __getname();
 
-	p9_debug(P9_DEBUG_VFS, "%s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
 
 	if (!link)
 		link = ERR_PTR(-ENOMEM);
@@ -1314,8 +1314,8 @@ v9fs_vfs_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
 {
 	char *s = nd_get_link(nd);
 
-	p9_debug(P9_DEBUG_VFS, " %s %s\n",
-		 dentry->d_name.name, IS_ERR(s) ? "<error>" : s);
+	p9_debug(P9_DEBUG_VFS, " %pd %s\n",
+		 dentry, IS_ERR(s) ? "<error>" : s);
 	if (!IS_ERR(s))
 		__putname(s);
 }
@@ -1364,8 +1364,8 @@ static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry,
 static int
 v9fs_vfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 {
-	p9_debug(P9_DEBUG_VFS, " %lu,%s,%s\n",
-		 dir->i_ino, dentry->d_name.name, symname);
+	p9_debug(P9_DEBUG_VFS, " %lu,%pd,%s\n",
+		 dir->i_ino, dentry, symname);
 
 	return v9fs_vfs_mkspecial(dir, dentry, P9_DMSYMLINK, symname);
 }
@@ -1386,8 +1386,8 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir,
 	char *name;
 	struct p9_fid *oldfid;
 
-	p9_debug(P9_DEBUG_VFS, " %lu,%s,%s\n",
-		 dir->i_ino, dentry->d_name.name, old_dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, " %lu,%pd,%pd\n",
+		 dir->i_ino, dentry, old_dentry);
 
 	oldfid = v9fs_fid_clone(old_dentry);
 	if (IS_ERR(oldfid))
@@ -1428,8 +1428,8 @@ v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rde
 	char *name;
 	u32 perm;
 
-	p9_debug(P9_DEBUG_VFS, " %lu,%s mode: %hx MAJOR: %u MINOR: %u\n",
-		 dir->i_ino, dentry->d_name.name, mode,
+	p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n",
+		 dir->i_ino, dentry, mode,
 		 MAJOR(rdev), MINOR(rdev));
 
 	if (!new_valid_dev(rdev))
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 1fa85aae24df..02b64f4e576a 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -393,7 +393,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
 	struct dentry *dir_dentry;
 	struct posix_acl *dacl = NULL, *pacl = NULL;
 
-	p9_debug(P9_DEBUG_VFS, "name %s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
 	err = 0;
 	v9ses = v9fs_inode2v9ses(dir);
 
@@ -767,8 +767,8 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
 	struct p9_fid *dfid, *oldfid;
 	struct v9fs_session_info *v9ses;
 
-	p9_debug(P9_DEBUG_VFS, "dir ino: %lu, old_name: %s, new_name: %s\n",
-		 dir->i_ino, old_dentry->d_name.name, dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "dir ino: %lu, old_name: %pd, new_name: %pd\n",
+		 dir->i_ino, old_dentry, dentry);
 
 	v9ses = v9fs_inode2v9ses(dir);
 	dir_dentry = dentry->d_parent;
@@ -917,7 +917,7 @@ v9fs_vfs_follow_link_dotl(struct dentry *dentry, struct nameidata *nd)
 	char *link = __getname();
 	char *target;
 
-	p9_debug(P9_DEBUG_VFS, "%s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
 
 	if (!link) {
 		link = ERR_PTR(-ENOMEM);
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 406b29836b19..abc853968fed 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -10,8 +10,6 @@
 
 #include "affs.h"
 
-extern struct timezone sys_tz;
-
 static char ErrorBuffer[256];
 
 /*
diff --git a/fs/affs/file.c b/fs/affs/file.c
index a7fe57d2cd9a..1ed590aafecf 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -584,11 +584,14 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
 		bh->b_state &= ~(1UL << BH_New);
 		mark_buffer_dirty_inode(bh, inode);
 		if (prev_bh) {
-			u32 tmp = be32_to_cpu(AFFS_DATA_HEAD(prev_bh)->next);
-			if (tmp)
-				affs_warning(sb, "extent_file_ofs", "next block already set for %d (%d)", bidx, tmp);
+			u32 tmp_next = be32_to_cpu(AFFS_DATA_HEAD(prev_bh)->next);
+
+			if (tmp_next)
+				affs_warning(sb, "extent_file_ofs",
+					     "next block already set for %d (%d)",
+					     bidx, tmp_next);
 			AFFS_DATA_HEAD(prev_bh)->next = cpu_to_be32(bh->b_blocknr);
-			affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp);
+			affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp_next);
 			mark_buffer_dirty_inode(prev_bh, inode);
 			affs_brelse(prev_bh);
 		}
@@ -727,11 +730,14 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 			AFFS_DATA_HEAD(bh)->next = 0;
 			bh->b_state &= ~(1UL << BH_New);
 			if (prev_bh) {
-				u32 tmp = be32_to_cpu(AFFS_DATA_HEAD(prev_bh)->next);
-				if (tmp)
-					affs_warning(sb, "commit_write_ofs", "next block already set for %d (%d)", bidx, tmp);
+				u32 tmp_next = be32_to_cpu(AFFS_DATA_HEAD(prev_bh)->next);
+
+				if (tmp_next)
+					affs_warning(sb, "commit_write_ofs",
+						     "next block already set for %d (%d)",
+						     bidx, tmp_next);
 				AFFS_DATA_HEAD(prev_bh)->next = cpu_to_be32(bh->b_blocknr);
-				affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp);
+				affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp_next);
 				mark_buffer_dirty_inode(prev_bh, inode);
 			}
 		}
@@ -758,11 +764,14 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 			AFFS_DATA_HEAD(bh)->next = 0;
 			bh->b_state &= ~(1UL << BH_New);
 			if (prev_bh) {
-				u32 tmp = be32_to_cpu(AFFS_DATA_HEAD(prev_bh)->next);
-				if (tmp)
-					affs_warning(sb, "commit_write_ofs", "next block already set for %d (%d)", bidx, tmp);
+				u32 tmp_next = be32_to_cpu(AFFS_DATA_HEAD(prev_bh)->next);
+
+				if (tmp_next)
+					affs_warning(sb, "commit_write_ofs",
+						     "next block already set for %d (%d)",
+						     bidx, tmp_next);
 				AFFS_DATA_HEAD(prev_bh)->next = cpu_to_be32(bh->b_blocknr);
-				affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp);
+				affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp_next);
 				mark_buffer_dirty_inode(prev_bh, inode);
 			}
 		} else if (be32_to_cpu(AFFS_DATA_HEAD(bh)->size) < tmp)
@@ -842,12 +851,12 @@ affs_truncate(struct inode *inode)
 		struct address_space *mapping = inode->i_mapping;
 		struct page *page;
 		void *fsdata;
-		loff_t size = inode->i_size;
+		loff_t isize = inode->i_size;
 		int res;
 
-		res = mapping->a_ops->write_begin(NULL, mapping, size, 0, 0, &page, &fsdata);
+		res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, 0, &page, &fsdata);
 		if (!res)
-			res = mapping->a_ops->write_end(NULL, mapping, size, 0, 0, page, fsdata);
+			res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, page, fsdata);
 		else
 			inode->i_size = AFFS_I(inode)->mmu_private;
 		mark_inode_dirty(inode);
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index bec2d1a0c91c..e217c511459b 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -14,13 +14,11 @@
 #include "affs.h"
 
 extern const struct inode_operations affs_symlink_inode_operations;
-extern struct timezone sys_tz;
 
 struct inode *affs_iget(struct super_block *sb, unsigned long ino)
 {
 	struct affs_sb_info	*sbi = AFFS_SB(sb);
 	struct buffer_head	*bh;
-	struct affs_head	*head;
 	struct affs_tail	*tail;
 	struct inode		*inode;
 	u32			 block;
@@ -49,7 +47,6 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
 		goto bad_inode;
 	}
 
-	head = AFFS_HEAD(bh);
 	tail = AFFS_TAIL(sb, bh);
 	prot = be32_to_cpu(tail->protect);
 
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 51f1a95bff73..f754ab68a840 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -20,8 +20,6 @@
 #include <linux/writeback.h>
 #include "affs.h"
 
-extern struct timezone sys_tz;
-
 static int affs_statfs(struct dentry *dentry, struct kstatfs *buf);
 static int affs_remount (struct super_block *sb, int *flags, char *data);
 
@@ -308,7 +306,6 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
 	u32			 chksum;
 	int			 num_bm;
 	int			 i, j;
-	s32			 key;
 	kuid_t			 uid;
 	kgid_t			 gid;
 	int			 reserved;
@@ -367,7 +364,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
 		i = j = blocksize;
 		size = size / (blocksize / 512);
 	}
-	for (blocksize = i, key = 0; blocksize <= j; blocksize <<= 1, size >>= 1) {
+	for (blocksize = i; blocksize <= j; blocksize <<= 1, size >>= 1) {
 		sbi->s_root_block = root_block;
 		if (root_block < 0)
 			sbi->s_root_block = (reserved + size - 1) / 2;
@@ -399,7 +396,6 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
 			    be32_to_cpu(AFFS_ROOT_TAIL(sb, root_bh)->stype) == ST_ROOT) {
 				sbi->s_hashsize    = blocksize / 4 - 56;
 				sbi->s_root_block += num_bm;
-				key                        = 1;
 				goto got_root;
 			}
 			affs_brelse(root_bh);
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 529300327f45..a1645b88fe8a 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -669,7 +669,6 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 
 out_valid:
 	dentry->d_fsdata = dir_version;
-out_skip:
 	dput(parent);
 	key_put(key);
 	_leave(" = 1 [valid]");
@@ -682,10 +681,6 @@ not_found:
 	spin_unlock(&dentry->d_lock);
 
 out_bad:
-	/* don't unhash if we have submounts */
-	if (check_submounts_and_drop(dentry) != 0)
-		goto out_skip;
-
 	_debug("dropping dentry %s/%s",
 	       parent->d_name.name, dentry->d_name.name);
 	dput(parent);
diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c
index b6df2e83809f..52976785a32c 100644
--- a/fs/afs/vlocation.c
+++ b/fs/afs/vlocation.c
@@ -130,7 +130,6 @@ static int afs_vlocation_access_vl_by_id(struct afs_vlocation *vl,
 					/* second+ BUSY - sleep a little bit */
 					set_current_state(TASK_UNINTERRUPTIBLE);
 					schedule_timeout(1);
-					__set_current_state(TASK_RUNNING);
 				}
 				continue;
 			}
diff --git a/fs/aio.c b/fs/aio.c
index 733750096b71..84a751005f5b 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -661,10 +661,10 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 
 	INIT_LIST_HEAD(&ctx->active_reqs);
 
-	if (percpu_ref_init(&ctx->users, free_ioctx_users))
+	if (percpu_ref_init(&ctx->users, free_ioctx_users, 0, GFP_KERNEL))
 		goto err;
 
-	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs))
+	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs, 0, GFP_KERNEL))
 		goto err;
 
 	ctx->cpu = alloc_percpu(struct kioctx_cpu);
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 9e359fb20c0a..8e98cf954bab 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -79,6 +79,10 @@ struct autofs_info {
 };
 
 #define AUTOFS_INF_EXPIRING	(1<<0) /* dentry is in the process of expiring */
+#define AUTOFS_INF_NO_RCU	(1<<1) /* the dentry is being considered
+					* for expiry, so RCU_walk is
+					* not permitted
+					*/
 #define AUTOFS_INF_PENDING	(1<<2) /* dentry pending mount */
 
 struct autofs_wait_queue {
@@ -148,7 +152,7 @@ void autofs4_free_ino(struct autofs_info *);
 
 /* Expiration */
 int is_autofs4_dentry(struct dentry *);
-int autofs4_expire_wait(struct dentry *dentry);
+int autofs4_expire_wait(struct dentry *dentry, int rcu_walk);
 int autofs4_expire_run(struct super_block *, struct vfsmount *,
 			struct autofs_sb_info *,
 			struct autofs_packet_expire __user *);
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 5b570b6efa28..aaf96cb25452 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -450,7 +450,7 @@ static int autofs_dev_ioctl_requester(struct file *fp,
 	ino = autofs4_dentry_ino(path.dentry);
 	if (ino) {
 		err = 0;
-		autofs4_expire_wait(path.dentry);
+		autofs4_expire_wait(path.dentry, 0);
 		spin_lock(&sbi->fs_lock);
 		param->requester.uid = from_kuid_munged(current_user_ns(), ino->uid);
 		param->requester.gid = from_kgid_munged(current_user_ns(), ino->gid);
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index a7be57e39be7..683a5b9ce22a 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -30,12 +30,6 @@ static inline int autofs4_can_expire(struct dentry *dentry,
 		/* Too young to die */
 		if (!timeout || time_after(ino->last_used + timeout, now))
 			return 0;
-
-		/* update last_used here :-
-		   - obviously makes sense if it is in use now
-		   - less obviously, prevents rapid-fire expire
-		     attempts if expire fails the first time */
-		ino->last_used = now;
 	}
 	return 1;
 }
@@ -255,12 +249,6 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
 			struct autofs_info *ino = autofs4_dentry_ino(p);
 			unsigned int ino_count = atomic_read(&ino->count);
 
-			/*
-			 * Clean stale dentries below that have not been
-			 * invalidated after a mount fail during lookup
-			 */
-			d_invalidate(p);
-
 			/* allow for dget above and top is already dgot */
 			if (p == top)
 				ino_count += 2;
@@ -333,10 +321,19 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
 	if (ino->flags & AUTOFS_INF_PENDING)
 		goto out;
 	if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
-		ino->flags |= AUTOFS_INF_EXPIRING;
-		init_completion(&ino->expire_complete);
+		ino->flags |= AUTOFS_INF_NO_RCU;
 		spin_unlock(&sbi->fs_lock);
-		return root;
+		synchronize_rcu();
+		spin_lock(&sbi->fs_lock);
+		if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
+			ino->flags |= AUTOFS_INF_EXPIRING;
+			smp_mb();
+			ino->flags &= ~AUTOFS_INF_NO_RCU;
+			init_completion(&ino->expire_complete);
+			spin_unlock(&sbi->fs_lock);
+			return root;
+		}
+		ino->flags &= ~AUTOFS_INF_NO_RCU;
 	}
 out:
 	spin_unlock(&sbi->fs_lock);
@@ -345,6 +342,89 @@ out:
 	return NULL;
 }
 
+/* Check if 'dentry' should expire, or return a nearby
+ * dentry that is suitable.
+ * If returned dentry is different from arg dentry,
+ * then a dget() reference was taken, else not.
+ */
+static struct dentry *should_expire(struct dentry *dentry,
+				    struct vfsmount *mnt,
+				    unsigned long timeout,
+				    int how)
+{
+	int do_now = how & AUTOFS_EXP_IMMEDIATE;
+	int exp_leaves = how & AUTOFS_EXP_LEAVES;
+	struct autofs_info *ino = autofs4_dentry_ino(dentry);
+	unsigned int ino_count;
+
+	/* No point expiring a pending mount */
+	if (ino->flags & AUTOFS_INF_PENDING)
+		return NULL;
+
+	/*
+	 * Case 1: (i) indirect mount or top level pseudo direct mount
+	 *	   (autofs-4.1).
+	 *	   (ii) indirect mount with offset mount, check the "/"
+	 *	   offset (autofs-5.0+).
+	 */
+	if (d_mountpoint(dentry)) {
+		DPRINTK("checking mountpoint %p %.*s",
+			dentry, (int)dentry->d_name.len, dentry->d_name.name);
+
+		/* Can we umount this guy */
+		if (autofs4_mount_busy(mnt, dentry))
+			return NULL;
+
+		/* Can we expire this guy */
+		if (autofs4_can_expire(dentry, timeout, do_now))
+			return dentry;
+		return NULL;
+	}
+
+	if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)) {
+		DPRINTK("checking symlink %p %.*s",
+			dentry, (int)dentry->d_name.len, dentry->d_name.name);
+		/*
+		 * A symlink can't be "busy" in the usual sense so
+		 * just check last used for expire timeout.
+		 */
+		if (autofs4_can_expire(dentry, timeout, do_now))
+			return dentry;
+		return NULL;
+	}
+
+	if (simple_empty(dentry))
+		return NULL;
+
+	/* Case 2: tree mount, expire iff entire tree is not busy */
+	if (!exp_leaves) {
+		/* Path walk currently on this dentry? */
+		ino_count = atomic_read(&ino->count) + 1;
+		if (d_count(dentry) > ino_count)
+			return NULL;
+
+		if (!autofs4_tree_busy(mnt, dentry, timeout, do_now))
+			return dentry;
+	/*
+	 * Case 3: pseudo direct mount, expire individual leaves
+	 *	   (autofs-4.1).
+	 */
+	} else {
+		/* Path walk currently on this dentry? */
+		struct dentry *expired;
+		ino_count = atomic_read(&ino->count) + 1;
+		if (d_count(dentry) > ino_count)
+			return NULL;
+
+		expired = autofs4_check_leaves(mnt, dentry, timeout, do_now);
+		if (expired) {
+			if (expired == dentry)
+				dput(dentry);
+			return expired;
+		}
+	}
+	return NULL;
+}
 /*
  * Find an eligible tree to time-out
  * A tree is eligible if :-
@@ -359,11 +439,8 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	unsigned long timeout;
 	struct dentry *root = sb->s_root;
 	struct dentry *dentry;
-	struct dentry *expired = NULL;
-	int do_now = how & AUTOFS_EXP_IMMEDIATE;
-	int exp_leaves = how & AUTOFS_EXP_LEAVES;
+	struct dentry *expired;
 	struct autofs_info *ino;
-	unsigned int ino_count;
 
 	if (!root)
 		return NULL;
@@ -375,77 +452,28 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	while ((dentry = get_next_positive_subdir(dentry, root))) {
 		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(dentry);
-		/* No point expiring a pending mount */
-		if (ino->flags & AUTOFS_INF_PENDING)
-			goto next;
-
-		/*
-		 * Case 1: (i) indirect mount or top level pseudo direct mount
-		 *	   (autofs-4.1).
-		 *	   (ii) indirect mount with offset mount, check the "/"
-		 *	   offset (autofs-5.0+).
-		 */
-		if (d_mountpoint(dentry)) {
-			DPRINTK("checking mountpoint %p %.*s",
-				dentry, (int)dentry->d_name.len, dentry->d_name.name);
-
-			/* Can we umount this guy */
-			if (autofs4_mount_busy(mnt, dentry))
-				goto next;
-
-			/* Can we expire this guy */
-			if (autofs4_can_expire(dentry, timeout, do_now)) {
-				expired = dentry;
-				goto found;
-			}
-			goto next;
-		}
-
-		if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)) {
-			DPRINTK("checking symlink %p %.*s",
-				dentry, (int)dentry->d_name.len, dentry->d_name.name);
-			/*
-			 * A symlink can't be "busy" in the usual sense so
-			 * just check last used for expire timeout.
-			 */
-			if (autofs4_can_expire(dentry, timeout, do_now)) {
-				expired = dentry;
-				goto found;
-			}
-			goto next;
+		if (ino->flags & AUTOFS_INF_NO_RCU)
+			expired = NULL;
+		else
+			expired = should_expire(dentry, mnt, timeout, how);
+		if (!expired) {
+			spin_unlock(&sbi->fs_lock);
+			continue;
 		}
-
-		if (simple_empty(dentry))
-			goto next;
-
-		/* Case 2: tree mount, expire iff entire tree is not busy */
-		if (!exp_leaves) {
-			/* Path walk currently on this dentry? */
-			ino_count = atomic_read(&ino->count) + 1;
-			if (d_count(dentry) > ino_count)
-				goto next;
-
-			if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) {
-				expired = dentry;
-				goto found;
-			}
-		/*
-		 * Case 3: pseudo direct mount, expire individual leaves
-		 *	   (autofs-4.1).
-		 */
-		} else {
-			/* Path walk currently on this dentry? */
-			ino_count = atomic_read(&ino->count) + 1;
-			if (d_count(dentry) > ino_count)
-				goto next;
-
-			expired = autofs4_check_leaves(mnt, dentry, timeout, do_now);
-			if (expired) {
+		ino = autofs4_dentry_ino(expired);
+		ino->flags |= AUTOFS_INF_NO_RCU;
+		spin_unlock(&sbi->fs_lock);
+		synchronize_rcu();
+		spin_lock(&sbi->fs_lock);
+		if (should_expire(expired, mnt, timeout, how)) {
+			if (expired != dentry)
 				dput(dentry);
-				goto found;
-			}
+			goto found;
 		}
-next:
+
+		ino->flags &= ~AUTOFS_INF_NO_RCU;
+		if (expired != dentry)
+			dput(expired);
 		spin_unlock(&sbi->fs_lock);
 	}
 	return NULL;
@@ -453,8 +481,9 @@ next:
 found:
 	DPRINTK("returning %p %.*s",
 		expired, (int)expired->d_name.len, expired->d_name.name);
-	ino = autofs4_dentry_ino(expired);
 	ino->flags |= AUTOFS_INF_EXPIRING;
+	smp_mb();
+	ino->flags &= ~AUTOFS_INF_NO_RCU;
 	init_completion(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
 	spin_lock(&sbi->lookup_lock);
@@ -467,13 +496,18 @@ found:
 	return expired;
 }
 
-int autofs4_expire_wait(struct dentry *dentry)
+int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status;
 
 	/* Block on any pending expire */
+	if (!(ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU)))
+		return 0;
+	if (rcu_walk)
+		return -ECHILD;
+
 	spin_lock(&sbi->fs_lock);
 	if (ino->flags & AUTOFS_INF_EXPIRING) {
 		spin_unlock(&sbi->fs_lock);
@@ -525,6 +559,8 @@ int autofs4_expire_run(struct super_block *sb,
 
 	spin_lock(&sbi->fs_lock);
 	ino = autofs4_dentry_ino(dentry);
+	/* avoid rapid-fire expire attempts if expiry fails */
+	ino->last_used = now;
 	ino->flags &= ~AUTOFS_INF_EXPIRING;
 	complete_all(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
@@ -551,6 +587,8 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 		ret = autofs4_wait(sbi, dentry, NFY_EXPIRE);
 
 		spin_lock(&sbi->fs_lock);
+		/* avoid rapid-fire expire attempts if expiry fails */
+		ino->last_used = now;
 		ino->flags &= ~AUTOFS_INF_EXPIRING;
 		complete_all(&ino->expire_complete);
 		spin_unlock(&sbi->fs_lock);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index cdb25ebccc4c..d76d083f2f06 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -210,7 +210,8 @@ next:
 	return NULL;
 }
 
-static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
+static struct dentry *autofs4_lookup_expiring(struct dentry *dentry,
+					      bool rcu_walk)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct dentry *parent = dentry->d_parent;
@@ -229,6 +230,11 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
 		struct dentry *expiring;
 		struct qstr *qstr;
 
+		if (rcu_walk) {
+			spin_unlock(&sbi->lookup_lock);
+			return ERR_PTR(-ECHILD);
+		}
+
 		ino = list_entry(p, struct autofs_info, expiring);
 		expiring = ino->dentry;
 
@@ -264,13 +270,15 @@ next:
 	return NULL;
 }
 
-static int autofs4_mount_wait(struct dentry *dentry)
+static int autofs4_mount_wait(struct dentry *dentry, bool rcu_walk)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status = 0;
 
 	if (ino->flags & AUTOFS_INF_PENDING) {
+		if (rcu_walk)
+			return -ECHILD;
 		DPRINTK("waiting for mount name=%.*s",
 			dentry->d_name.len, dentry->d_name.name);
 		status = autofs4_wait(sbi, dentry, NFY_MOUNT);
@@ -280,20 +288,22 @@ static int autofs4_mount_wait(struct dentry *dentry)
 	return status;
 }
 
-static int do_expire_wait(struct dentry *dentry)
+static int do_expire_wait(struct dentry *dentry, bool rcu_walk)
 {
 	struct dentry *expiring;
 
-	expiring = autofs4_lookup_expiring(dentry);
+	expiring = autofs4_lookup_expiring(dentry, rcu_walk);
+	if (IS_ERR(expiring))
+		return PTR_ERR(expiring);
 	if (!expiring)
-		return autofs4_expire_wait(dentry);
+		return autofs4_expire_wait(dentry, rcu_walk);
 	else {
 		/*
 		 * If we are racing with expire the request might not
 		 * be quite complete, but the directory has been removed
 		 * so it must have been successful, just wait for it.
 		 */
-		autofs4_expire_wait(expiring);
+		autofs4_expire_wait(expiring, 0);
 		autofs4_del_expiring(expiring);
 		dput(expiring);
 	}
@@ -345,7 +355,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 	 * and the directory was removed, so just go ahead and try
 	 * the mount.
 	 */
-	status = do_expire_wait(dentry);
+	status = do_expire_wait(dentry, 0);
 	if (status && status != -EAGAIN)
 		return NULL;
 
@@ -353,7 +363,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 	spin_lock(&sbi->fs_lock);
 	if (ino->flags & AUTOFS_INF_PENDING) {
 		spin_unlock(&sbi->fs_lock);
-		status = autofs4_mount_wait(dentry);
+		status = autofs4_mount_wait(dentry, 0);
 		if (status)
 			return ERR_PTR(status);
 		goto done;
@@ -394,7 +404,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 		}
 		ino->flags |= AUTOFS_INF_PENDING;
 		spin_unlock(&sbi->fs_lock);
-		status = autofs4_mount_wait(dentry);
+		status = autofs4_mount_wait(dentry, 0);
 		spin_lock(&sbi->fs_lock);
 		ino->flags &= ~AUTOFS_INF_PENDING;
 		if (status) {
@@ -423,28 +433,46 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 
 	/* The daemon never waits. */
 	if (autofs4_oz_mode(sbi)) {
-		if (rcu_walk)
-			return 0;
 		if (!d_mountpoint(dentry))
 			return -EISDIR;
 		return 0;
 	}
 
-	/* We need to sleep, so we need pathwalk to be in ref-mode */
-	if (rcu_walk)
-		return -ECHILD;
-
 	/* Wait for pending expires */
-	do_expire_wait(dentry);
+	if (do_expire_wait(dentry, rcu_walk) == -ECHILD)
+		return -ECHILD;
 
 	/*
 	 * This dentry may be under construction so wait on mount
 	 * completion.
 	 */
-	status = autofs4_mount_wait(dentry);
+	status = autofs4_mount_wait(dentry, rcu_walk);
 	if (status)
 		return status;
 
+	if (rcu_walk) {
+		/* We don't need fs_lock in rcu_walk mode,
+		 * just testing 'AUTOFS_INFO_NO_RCU' is enough.
+		 * simple_empty() takes a spinlock, so leave it
+		 * to last.
+		 * We only return -EISDIR when certain this isn't
+		 * a mount-trap.
+		 */
+		struct inode *inode;
+		if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))
+			return 0;
+		if (d_mountpoint(dentry))
+			return 0;
+		inode = ACCESS_ONCE(dentry->d_inode);
+		if (inode && S_ISLNK(inode->i_mode))
+			return -EISDIR;
+		if (list_empty(&dentry->d_subdirs))
+			return 0;
+		if (!simple_empty(dentry))
+			return -EISDIR;
+		return 0;
+	}
+
 	spin_lock(&sbi->fs_lock);
 	/*
 	 * If the dentry has been selected for expire while we slept
diff --git a/fs/befs/btree.c b/fs/befs/btree.c
index 9c7faa8a9288..0826e91dacda 100644
--- a/fs/befs/btree.c
+++ b/fs/befs/btree.c
@@ -78,11 +78,11 @@
 /*
  * In memory structure of each btree node
  */
-typedef struct {
+struct befs_btree_node {
 	befs_host_btree_nodehead head;	/* head of node converted to cpu byteorder */
 	struct buffer_head *bh;
 	befs_btree_nodehead *od_node;	/* on disk node */
-} befs_btree_node;
+};
 
 /* local constants */
 static const befs_off_t befs_bt_inval = 0xffffffffffffffffULL;
@@ -90,27 +90,30 @@ static const befs_off_t befs_bt_inval = 0xffffffffffffffffULL;
 /* local functions */
 static int befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds,
 			       befs_btree_super * bt_super,
-			       befs_btree_node * this_node,
+			       struct befs_btree_node *this_node,
 			       befs_off_t * node_off);
 
 static int befs_bt_read_super(struct super_block *sb, befs_data_stream * ds,
 			      befs_btree_super * sup);
 
 static int befs_bt_read_node(struct super_block *sb, befs_data_stream * ds,
-			     befs_btree_node * node, befs_off_t node_off);
+			     struct befs_btree_node *node,
+			     befs_off_t node_off);
 
-static int befs_leafnode(befs_btree_node * node);
+static int befs_leafnode(struct befs_btree_node *node);
 
-static fs16 *befs_bt_keylen_index(befs_btree_node * node);
+static fs16 *befs_bt_keylen_index(struct befs_btree_node *node);
 
-static fs64 *befs_bt_valarray(befs_btree_node * node);
+static fs64 *befs_bt_valarray(struct befs_btree_node *node);
 
-static char *befs_bt_keydata(befs_btree_node * node);
+static char *befs_bt_keydata(struct befs_btree_node *node);
 
-static int befs_find_key(struct super_block *sb, befs_btree_node * node,
+static int befs_find_key(struct super_block *sb,
+			 struct befs_btree_node *node,
 			 const char *findkey, befs_off_t * value);
 
-static char *befs_bt_get_key(struct super_block *sb, befs_btree_node * node,
+static char *befs_bt_get_key(struct super_block *sb,
+			     struct befs_btree_node *node,
 			     int index, u16 * keylen);
 
 static int befs_compare_strings(const void *key1, int keylen1,
@@ -191,7 +194,7 @@ befs_bt_read_super(struct super_block *sb, befs_data_stream * ds,
 
 static int
 befs_bt_read_node(struct super_block *sb, befs_data_stream * ds,
-		  befs_btree_node * node, befs_off_t node_off)
+		  struct befs_btree_node *node, befs_off_t node_off)
 {
 	uint off = 0;
 
@@ -247,7 +250,7 @@ int
 befs_btree_find(struct super_block *sb, befs_data_stream * ds,
 		const char *key, befs_off_t * value)
 {
-	befs_btree_node *this_node = NULL;
+	struct befs_btree_node *this_node = NULL;
 	befs_btree_super bt_super;
 	befs_off_t node_off;
 	int res;
@@ -260,11 +263,11 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
 		goto error;
 	}
 
-	this_node = kmalloc(sizeof (befs_btree_node),
+	this_node = kmalloc(sizeof(struct befs_btree_node),
 						GFP_NOFS);
 	if (!this_node) {
 		befs_error(sb, "befs_btree_find() failed to allocate %zu "
-			   "bytes of memory", sizeof (befs_btree_node));
+			   "bytes of memory", sizeof(struct befs_btree_node));
 		goto error;
 	}
 
@@ -333,7 +336,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds,
  * Use binary search instead of a linear.
  */
 static int
-befs_find_key(struct super_block *sb, befs_btree_node * node,
+befs_find_key(struct super_block *sb, struct befs_btree_node *node,
 	      const char *findkey, befs_off_t * value)
 {
 	int first, last, mid;
@@ -417,7 +420,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
 		loff_t key_no, size_t bufsize, char *keybuf, size_t * keysize,
 		befs_off_t * value)
 {
-	befs_btree_node *this_node;
+	struct befs_btree_node *this_node;
 	befs_btree_super bt_super;
 	befs_off_t node_off = 0;
 	int cur_key;
@@ -436,9 +439,10 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
 		goto error;
 	}
 
-	if ((this_node = kmalloc(sizeof (befs_btree_node), GFP_NOFS)) == NULL) {
+	this_node = kmalloc(sizeof(struct befs_btree_node), GFP_NOFS);
+	if (this_node == NULL) {
 		befs_error(sb, "befs_btree_read() failed to allocate %zu "
-			   "bytes of memory", sizeof (befs_btree_node));
+			   "bytes of memory", sizeof(struct befs_btree_node));
 		goto error;
 	}
 
@@ -545,7 +549,8 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
  */
 static int
 befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds,
-		    befs_btree_super * bt_super, befs_btree_node * this_node,
+		    befs_btree_super *bt_super,
+		    struct befs_btree_node *this_node,
 		    befs_off_t * node_off)
 {
 
@@ -600,7 +605,7 @@ befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds,
  * Return 1 if leaf, 0 if interior
  */
 static int
-befs_leafnode(befs_btree_node * node)
+befs_leafnode(struct befs_btree_node *node)
 {
 	/* all interior nodes (and only interior nodes) have an overflow node */
 	if (node->head.overflow == befs_bt_inval)
@@ -623,7 +628,7 @@ befs_leafnode(befs_btree_node * node)
  * Except that rounding up to 8 works, and rounding up to 4 doesn't.
  */
 static fs16 *
-befs_bt_keylen_index(befs_btree_node * node)
+befs_bt_keylen_index(struct befs_btree_node *node)
 {
 	const int keylen_align = 8;
 	unsigned long int off =
@@ -644,7 +649,7 @@ befs_bt_keylen_index(befs_btree_node * node)
  * of the node pointed to by the node header
  */
 static fs64 *
-befs_bt_valarray(befs_btree_node * node)
+befs_bt_valarray(struct befs_btree_node *node)
 {
 	void *keylen_index_start = (void *) befs_bt_keylen_index(node);
 	size_t keylen_index_size = node->head.all_key_count * sizeof (fs16);
@@ -660,7 +665,7 @@ befs_bt_valarray(befs_btree_node * node)
  * of the node pointed to by the node header 
  */
 static char *
-befs_bt_keydata(befs_btree_node * node)
+befs_bt_keydata(struct befs_btree_node *node)
 {
 	return (char *) ((void *) node->od_node + sizeof (befs_btree_nodehead));
 }
@@ -676,7 +681,7 @@ befs_bt_keydata(befs_btree_node * node)
  * Returns NULL on failure (bad input) and sets *@keylen = 0
  */
 static char *
-befs_bt_get_key(struct super_block *sb, befs_btree_node * node,
+befs_bt_get_key(struct super_block *sb, struct befs_btree_node *node,
 		int index, u16 * keylen)
 {
 	int prev_key_end;
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index ca0ba15a7306..929dec08c348 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -256,11 +256,8 @@ static int load_aout_binary(struct linux_binprm * bprm)
 		(current->mm->start_brk = N_BSSADDR(ex));
 
 	retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
-	if (retval < 0) {
-		/* Someone check-me: is this error path enough? */
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		return retval;
-	}
 
 	install_exec_creds(bprm);
 
@@ -278,17 +275,13 @@ static int load_aout_binary(struct linux_binprm * bprm)
 		map_size = ex.a_text+ex.a_data;
 #endif
 		error = vm_brk(text_addr & PAGE_MASK, map_size);
-		if (error != (text_addr & PAGE_MASK)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != (text_addr & PAGE_MASK))
 			return error;
-		}
 
 		error = read_code(bprm->file, text_addr, pos,
 				  ex.a_text+ex.a_data);
-		if ((signed long)error < 0) {
-			send_sig(SIGKILL, current, 0);
+		if ((signed long)error < 0)
 			return error;
-		}
 	} else {
 		if ((ex.a_text & 0xfff || ex.a_data & 0xfff) &&
 		    (N_MAGIC(ex) != NMAGIC) && printk_ratelimit())
@@ -315,28 +308,22 @@ static int load_aout_binary(struct linux_binprm * bprm)
 			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
 			fd_offset);
 
-		if (error != N_TXTADDR(ex)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != N_TXTADDR(ex))
 			return error;
-		}
 
 		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
 				PROT_READ | PROT_WRITE | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
 				fd_offset + ex.a_text);
-		if (error != N_DATADDR(ex)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != N_DATADDR(ex))
 			return error;
-		}
 	}
 beyond_if:
 	set_binfmt(&aout_format);
 
 	retval = set_brk(current->mm->start_brk, current->mm->brk);
-	if (retval < 0) {
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		return retval;
-	}
 
 	current->mm->start_stack =
 		(unsigned long) create_aout_tables((char __user *) bprm->p, bprm);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 3892c1a23241..d8fc0605b9d2 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -738,10 +738,8 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	   change some of these later */
 	retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP),
 				 executable_stack);
-	if (retval < 0) {
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		goto out_free_dentry;
-	}
 	
 	current->mm->start_stack = bprm->p;
 
@@ -763,10 +761,8 @@ static int load_elf_binary(struct linux_binprm *bprm)
 			   and clear the area.  */
 			retval = set_brk(elf_bss + load_bias,
 					 elf_brk + load_bias);
-			if (retval) {
-				send_sig(SIGKILL, current, 0);
+			if (retval)
 				goto out_free_dentry;
-			}
 			nbyte = ELF_PAGEOFFSET(elf_bss);
 			if (nbyte) {
 				nbyte = ELF_MIN_ALIGN - nbyte;
@@ -820,7 +816,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt,
 				elf_prot, elf_flags, 0);
 		if (BAD_ADDR(error)) {
-			send_sig(SIGKILL, current, 0);
 			retval = IS_ERR((void *)error) ?
 				PTR_ERR((void*)error) : -EINVAL;
 			goto out_free_dentry;
@@ -851,7 +846,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		    elf_ppnt->p_memsz > TASK_SIZE ||
 		    TASK_SIZE - elf_ppnt->p_memsz < k) {
 			/* set_brk can never work. Avoid overflows. */
-			send_sig(SIGKILL, current, 0);
 			retval = -EINVAL;
 			goto out_free_dentry;
 		}
@@ -883,12 +877,9 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	 * up getting placed where the bss needs to go.
 	 */
 	retval = set_brk(elf_bss, elf_brk);
-	if (retval) {
-		send_sig(SIGKILL, current, 0);
+	if (retval)
 		goto out_free_dentry;
-	}
 	if (likely(elf_bss != elf_brk) && unlikely(padzero(elf_bss))) {
-		send_sig(SIGSEGV, current, 0);
 		retval = -EFAULT; /* Nobody gets to see this, but.. */
 		goto out_free_dentry;
 	}
@@ -909,7 +900,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 			elf_entry += loc->interp_elf_ex.e_entry;
 		}
 		if (BAD_ADDR(elf_entry)) {
-			force_sig(SIGSEGV, current);
 			retval = IS_ERR((void *)elf_entry) ?
 					(int)elf_entry : -EINVAL;
 			goto out_free_dentry;
@@ -922,7 +912,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	} else {
 		elf_entry = loc->elf_ex.e_entry;
 		if (BAD_ADDR(elf_entry)) {
-			force_sig(SIGSEGV, current);
 			retval = -EINVAL;
 			goto out_free_dentry;
 		}
@@ -934,19 +923,15 @@ static int load_elf_binary(struct linux_binprm *bprm)
 
 #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
 	retval = arch_setup_additional_pages(bprm, !!elf_interpreter);
-	if (retval < 0) {
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		goto out;
-	}
 #endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
 
 	install_exec_creds(bprm);
 	retval = create_elf_tables(bprm, &loc->elf_ex,
 			  load_addr, interp_load_addr);
-	if (retval < 0) {
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		goto out;
-	}
 	/* N.B. passed_fileno might not be initialized? */
 	current->mm->end_code = end_code;
 	current->mm->start_code = start_code;
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index fe2a643ee005..d3634bfb7fe1 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -317,8 +317,8 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 		goto error;
 
 	/* there's now no turning back... the old userspace image is dead,
-	 * defunct, deceased, etc. after this point we have to exit via
-	 * error_kill */
+	 * defunct, deceased, etc.
+	 */
 	set_personality(PER_LINUX_FDPIC);
 	if (elf_read_implies_exec(&exec_params.hdr, executable_stack))
 		current->personality |= READ_IMPLIES_EXEC;
@@ -343,24 +343,22 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 
 	retval = setup_arg_pages(bprm, current->mm->start_stack,
 				 executable_stack);
-	if (retval < 0) {
-		send_sig(SIGKILL, current, 0);
-		goto error_kill;
-	}
+	if (retval < 0)
+		goto error;
 #endif
 
 	/* load the executable and interpreter into memory */
 	retval = elf_fdpic_map_file(&exec_params, bprm->file, current->mm,
 				    "executable");
 	if (retval < 0)
-		goto error_kill;
+		goto error;
 
 	if (interpreter_name) {
 		retval = elf_fdpic_map_file(&interp_params, interpreter,
 					    current->mm, "interpreter");
 		if (retval < 0) {
 			printk(KERN_ERR "Unable to load interpreter\n");
-			goto error_kill;
+			goto error;
 		}
 
 		allow_write_access(interpreter);
@@ -397,7 +395,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 	if (IS_ERR_VALUE(current->mm->start_brk)) {
 		retval = current->mm->start_brk;
 		current->mm->start_brk = 0;
-		goto error_kill;
+		goto error;
 	}
 
 	current->mm->brk = current->mm->start_brk;
@@ -410,7 +408,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 	install_exec_creds(bprm);
 	if (create_elf_fdpic_tables(bprm, current->mm,
 				    &exec_params, &interp_params) < 0)
-		goto error_kill;
+		goto error;
 
 	kdebug("- start_code  %lx", current->mm->start_code);
 	kdebug("- end_code    %lx", current->mm->end_code);
@@ -449,12 +447,6 @@ error:
 	kfree(interp_params.phdrs);
 	kfree(interp_params.loadmap);
 	return retval;
-
-	/* unrecoverable error - kill the process */
-error_kill:
-	send_sig(SIGSEGV, current, 0);
-	goto error;
-
 }
 
 /*****************************************************************************/
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index b60500300dd7..fd8beb9657a2 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -62,7 +62,22 @@ static struct file_system_type bm_fs_type;
 static struct vfsmount *bm_mnt;
 static int entry_count;
 
-/* 
+/*
+ * Max length of the register string.  Determined by:
+ *  - 7 delimiters
+ *  - name:   ~50 bytes
+ *  - type:   1 byte
+ *  - offset: 3 bytes (has to be smaller than BINPRM_BUF_SIZE)
+ *  - magic:  128 bytes (512 in escaped form)
+ *  - mask:   128 bytes (512 in escaped form)
+ *  - interp: ~50 bytes
+ *  - flags:  5 bytes
+ * Round that up a bit, and then back off to hold the internal data
+ * (like struct Node).
+ */
+#define MAX_REGISTER_LENGTH 1920
+
+/*
  * Check if we support the binfmt
  * if we do, return the node, else NULL
  * locking is done in load_misc_binary
@@ -279,7 +294,7 @@ static Node *create_entry(const char __user *buffer, size_t count)
 
 	/* some sanity checks */
 	err = -EINVAL;
-	if ((count < 11) || (count > 256))
+	if ((count < 11) || (count > MAX_REGISTER_LENGTH))
 		goto out;
 
 	err = -ENOMEM;
@@ -396,12 +411,12 @@ static int parse_command(const char __user *buffer, size_t count)
 {
 	char s[4];
 
-	if (!count)
-		return 0;
 	if (count > 3)
 		return -EINVAL;
 	if (copy_from_user(s, buffer, count))
 		return -EFAULT;
+	if (!count)
+		return 0;
 	if (s[count-1] == '\n')
 		count--;
 	if (count == 1 && s[0] == '0')
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 6d7274619bf9..cc9d4114cda0 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -50,32 +50,22 @@ inline struct block_device *I_BDEV(struct inode *inode)
 EXPORT_SYMBOL(I_BDEV);
 
 /*
- * Move the inode from its current bdi to a new bdi. If the inode is dirty we
- * need to move it onto the dirty list of @dst so that the inode is always on
- * the right list.
+ * Move the inode from its current bdi to a new bdi.  Make sure the inode
+ * is clean before moving so that it doesn't linger on the old bdi.
  */
 static void bdev_inode_switch_bdi(struct inode *inode,
 			struct backing_dev_info *dst)
 {
-	struct backing_dev_info *old = inode->i_data.backing_dev_info;
-	bool wakeup_bdi = false;
-
-	if (unlikely(dst == old))		/* deadlock avoidance */
-		return;
-	bdi_lock_two(&old->wb, &dst->wb);
-	spin_lock(&inode->i_lock);
-	inode->i_data.backing_dev_info = dst;
-	if (inode->i_state & I_DIRTY) {
-		if (bdi_cap_writeback_dirty(dst) && !wb_has_dirty_io(&dst->wb))
-			wakeup_bdi = true;
-		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
+	while (true) {
+		spin_lock(&inode->i_lock);
+		if (!(inode->i_state & I_DIRTY)) {
+			inode->i_data.backing_dev_info = dst;
+			spin_unlock(&inode->i_lock);
+			return;
+		}
+		spin_unlock(&inode->i_lock);
+		WARN_ON_ONCE(write_inode_now(inode, true));
 	}
-	spin_unlock(&inode->i_lock);
-	spin_unlock(&old->wb.list_lock);
-	spin_unlock(&dst->wb.list_lock);
-
-	if (wakeup_bdi)
-		bdi_wakeup_thread_delayed(dst);
 }
 
 /* Kill _all_ buffers and pagecache , dirty or not.. */
@@ -304,6 +294,12 @@ static int blkdev_readpage(struct file * file, struct page * page)
 	return block_read_full_page(page, blkdev_get_block);
 }
 
+static int blkdev_readpages(struct file *file, struct address_space *mapping,
+			struct list_head *pages, unsigned nr_pages)
+{
+	return mpage_readpages(mapping, pages, nr_pages, blkdev_get_block);
+}
+
 static int blkdev_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -1173,8 +1169,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (!ret) {
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
 				bdi = blk_get_backing_dev_info(bdev);
-				if (bdi == NULL)
-					bdi = &default_backing_dev_info;
 				bdev_inode_switch_bdi(bdev->bd_inode, bdi);
 			}
 
@@ -1622,6 +1616,7 @@ static int blkdev_releasepage(struct page *page, gfp_t wait)
 
 static const struct address_space_operations def_blk_aops = {
 	.readpage	= blkdev_readpage,
+	.readpages	= blkdev_readpages,
 	.writepage	= blkdev_writepage,
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index fbd76ded9a34..4dabeb893b7c 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -74,6 +74,7 @@ BTRFS_WORK_HELPER(endio_helper);
 BTRFS_WORK_HELPER(endio_meta_helper);
 BTRFS_WORK_HELPER(endio_meta_write_helper);
 BTRFS_WORK_HELPER(endio_raid56_helper);
+BTRFS_WORK_HELPER(endio_repair_helper);
 BTRFS_WORK_HELPER(rmw_helper);
 BTRFS_WORK_HELPER(endio_write_helper);
 BTRFS_WORK_HELPER(freespace_write_helper);
@@ -91,7 +92,7 @@ __btrfs_alloc_workqueue(const char *name, int flags, int max_active,
 {
 	struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
 
-	if (unlikely(!ret))
+	if (!ret)
 		return NULL;
 
 	ret->max_active = max_active;
@@ -115,7 +116,7 @@ __btrfs_alloc_workqueue(const char *name, int flags, int max_active,
 		ret->normal_wq = alloc_workqueue("%s-%s", flags,
 						 ret->max_active, "btrfs",
 						 name);
-	if (unlikely(!ret->normal_wq)) {
+	if (!ret->normal_wq) {
 		kfree(ret);
 		return NULL;
 	}
@@ -137,12 +138,12 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name,
 {
 	struct btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
 
-	if (unlikely(!ret))
+	if (!ret)
 		return NULL;
 
 	ret->normal = __btrfs_alloc_workqueue(name, flags & ~WQ_HIGHPRI,
 					      max_active, thresh);
-	if (unlikely(!ret->normal)) {
+	if (!ret->normal) {
 		kfree(ret);
 		return NULL;
 	}
@@ -150,7 +151,7 @@ struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name,
 	if (flags & WQ_HIGHPRI) {
 		ret->high = __btrfs_alloc_workqueue(name, flags, max_active,
 						    thresh);
-		if (unlikely(!ret->high)) {
+		if (!ret->high) {
 			__btrfs_destroy_workqueue(ret->normal);
 			kfree(ret);
 			return NULL;
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index e9e31c94758f..e386c29ef1f6 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -53,6 +53,7 @@ BTRFS_WORK_HELPER_PROTO(endio_helper);
 BTRFS_WORK_HELPER_PROTO(endio_meta_helper);
 BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper);
 BTRFS_WORK_HELPER_PROTO(endio_raid56_helper);
+BTRFS_WORK_HELPER_PROTO(endio_repair_helper);
 BTRFS_WORK_HELPER_PROTO(rmw_helper);
 BTRFS_WORK_HELPER_PROTO(endio_write_helper);
 BTRFS_WORK_HELPER_PROTO(freespace_write_helper);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 54a201dac7f9..2d3e32ebfd15 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -25,6 +25,9 @@
 #include "delayed-ref.h"
 #include "locking.h"
 
+/* Just an arbitrary number so we can be sure this happened */
+#define BACKREF_FOUND_SHARED 6
+
 struct extent_inode_elem {
 	u64 inum;
 	u64 offset;
@@ -377,7 +380,8 @@ out:
 static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info,
 				   struct btrfs_path *path, u64 time_seq,
 				   struct list_head *head,
-				   const u64 *extent_item_pos, u64 total_refs)
+				   const u64 *extent_item_pos, u64 total_refs,
+				   u64 root_objectid)
 {
 	int err;
 	int ret = 0;
@@ -402,6 +406,10 @@ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info,
 			continue;
 		if (ref->count == 0)
 			continue;
+		if (root_objectid && ref->root_id != root_objectid) {
+			ret = BACKREF_FOUND_SHARED;
+			goto out;
+		}
 		err = __resolve_indirect_ref(fs_info, path, time_seq, ref,
 					     parents, extent_item_pos,
 					     total_refs);
@@ -482,7 +490,7 @@ static int __add_missing_keys(struct btrfs_fs_info *fs_info,
 			continue;
 		BUG_ON(!ref->wanted_disk_byte);
 		eb = read_tree_block(fs_info->tree_root, ref->wanted_disk_byte,
-				     fs_info->tree_root->leafsize, 0);
+				     0);
 		if (!eb || !extent_buffer_uptodate(eb)) {
 			free_extent_buffer(eb);
 			return -EIO;
@@ -561,7 +569,8 @@ static void __merge_refs(struct list_head *head, int mode)
  * smaller or equal that seq to the list
  */
 static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
-			      struct list_head *prefs, u64 *total_refs)
+			      struct list_head *prefs, u64 *total_refs,
+			      u64 inum)
 {
 	struct btrfs_delayed_extent_op *extent_op = head->extent_op;
 	struct rb_node *n = &head->node.rb_node;
@@ -625,6 +634,16 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
 			key.objectid = ref->objectid;
 			key.type = BTRFS_EXTENT_DATA_KEY;
 			key.offset = ref->offset;
+
+			/*
+			 * Found a inum that doesn't match our known inum, we
+			 * know it's shared.
+			 */
+			if (inum && ref->objectid != inum) {
+				ret = BACKREF_FOUND_SHARED;
+				break;
+			}
+
 			ret = __add_prelim_ref(prefs, ref->root, &key, 0, 0,
 					       node->bytenr,
 					       node->ref_mod * sgn, GFP_ATOMIC);
@@ -659,7 +678,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
 static int __add_inline_refs(struct btrfs_fs_info *fs_info,
 			     struct btrfs_path *path, u64 bytenr,
 			     int *info_level, struct list_head *prefs,
-			     u64 *total_refs)
+			     u64 *total_refs, u64 inum)
 {
 	int ret = 0;
 	int slot;
@@ -744,6 +763,12 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info,
 								      dref);
 			key.type = BTRFS_EXTENT_DATA_KEY;
 			key.offset = btrfs_extent_data_ref_offset(leaf, dref);
+
+			if (inum && key.objectid != inum) {
+				ret = BACKREF_FOUND_SHARED;
+				break;
+			}
+
 			root = btrfs_extent_data_ref_root(leaf, dref);
 			ret = __add_prelim_ref(prefs, root, &key, 0, 0,
 					       bytenr, count, GFP_NOFS);
@@ -765,7 +790,7 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info,
  */
 static int __add_keyed_refs(struct btrfs_fs_info *fs_info,
 			    struct btrfs_path *path, u64 bytenr,
-			    int info_level, struct list_head *prefs)
+			    int info_level, struct list_head *prefs, u64 inum)
 {
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	int ret;
@@ -827,6 +852,12 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info,
 								      dref);
 			key.type = BTRFS_EXTENT_DATA_KEY;
 			key.offset = btrfs_extent_data_ref_offset(leaf, dref);
+
+			if (inum && key.objectid != inum) {
+				ret = BACKREF_FOUND_SHARED;
+				break;
+			}
+
 			root = btrfs_extent_data_ref_root(leaf, dref);
 			ret = __add_prelim_ref(prefs, root, &key, 0, 0,
 					       bytenr, count, GFP_NOFS);
@@ -854,7 +885,8 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info,
 static int find_parent_nodes(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info, u64 bytenr,
 			     u64 time_seq, struct ulist *refs,
-			     struct ulist *roots, const u64 *extent_item_pos)
+			     struct ulist *roots, const u64 *extent_item_pos,
+			     u64 root_objectid, u64 inum)
 {
 	struct btrfs_key key;
 	struct btrfs_path *path;
@@ -929,7 +961,8 @@ again:
 			}
 			spin_unlock(&delayed_refs->lock);
 			ret = __add_delayed_refs(head, time_seq,
-						 &prefs_delayed, &total_refs);
+						 &prefs_delayed, &total_refs,
+						 inum);
 			mutex_unlock(&head->mutex);
 			if (ret)
 				goto out;
@@ -951,11 +984,11 @@ again:
 		     key.type == BTRFS_METADATA_ITEM_KEY)) {
 			ret = __add_inline_refs(fs_info, path, bytenr,
 						&info_level, &prefs,
-						&total_refs);
+						&total_refs, inum);
 			if (ret)
 				goto out;
 			ret = __add_keyed_refs(fs_info, path, bytenr,
-					       info_level, &prefs);
+					       info_level, &prefs, inum);
 			if (ret)
 				goto out;
 		}
@@ -971,7 +1004,8 @@ again:
 	__merge_refs(&prefs, 1);
 
 	ret = __resolve_indirect_refs(fs_info, path, time_seq, &prefs,
-				      extent_item_pos, total_refs);
+				      extent_item_pos, total_refs,
+				      root_objectid);
 	if (ret)
 		goto out;
 
@@ -981,6 +1015,11 @@ again:
 		ref = list_first_entry(&prefs, struct __prelim_ref, list);
 		WARN_ON(ref->count < 0);
 		if (roots && ref->count && ref->root_id && ref->parent == 0) {
+			if (root_objectid && ref->root_id != root_objectid) {
+				ret = BACKREF_FOUND_SHARED;
+				goto out;
+			}
+
 			/* no parent == root of tree */
 			ret = ulist_add(roots, ref->root_id, 0, GFP_NOFS);
 			if (ret < 0)
@@ -989,12 +1028,10 @@ again:
 		if (ref->count && ref->parent) {
 			if (extent_item_pos && !ref->inode_list &&
 			    ref->level == 0) {
-				u32 bsz;
 				struct extent_buffer *eb;
-				bsz = btrfs_level_size(fs_info->extent_root,
-							ref->level);
+
 				eb = read_tree_block(fs_info->extent_root,
-							   ref->parent, bsz, 0);
+							   ref->parent, 0);
 				if (!eb || !extent_buffer_uptodate(eb)) {
 					free_extent_buffer(eb);
 					ret = -EIO;
@@ -1087,7 +1124,7 @@ static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	ret = find_parent_nodes(trans, fs_info, bytenr,
-				time_seq, *leafs, NULL, extent_item_pos);
+				time_seq, *leafs, NULL, extent_item_pos, 0, 0);
 	if (ret < 0 && ret != -ENOENT) {
 		free_leaf_list(*leafs);
 		return ret;
@@ -1130,7 +1167,7 @@ static int __btrfs_find_all_roots(struct btrfs_trans_handle *trans,
 	ULIST_ITER_INIT(&uiter);
 	while (1) {
 		ret = find_parent_nodes(trans, fs_info, bytenr,
-					time_seq, tmp, *roots, NULL);
+					time_seq, tmp, *roots, NULL, 0, 0);
 		if (ret < 0 && ret != -ENOENT) {
 			ulist_free(tmp);
 			ulist_free(*roots);
@@ -1161,6 +1198,54 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+int btrfs_check_shared(struct btrfs_trans_handle *trans,
+		       struct btrfs_fs_info *fs_info, u64 root_objectid,
+		       u64 inum, u64 bytenr)
+{
+	struct ulist *tmp = NULL;
+	struct ulist *roots = NULL;
+	struct ulist_iterator uiter;
+	struct ulist_node *node;
+	struct seq_list elem = {};
+	int ret = 0;
+
+	tmp = ulist_alloc(GFP_NOFS);
+	roots = ulist_alloc(GFP_NOFS);
+	if (!tmp || !roots) {
+		ulist_free(tmp);
+		ulist_free(roots);
+		return -ENOMEM;
+	}
+
+	if (trans)
+		btrfs_get_tree_mod_seq(fs_info, &elem);
+	else
+		down_read(&fs_info->commit_root_sem);
+	ULIST_ITER_INIT(&uiter);
+	while (1) {
+		ret = find_parent_nodes(trans, fs_info, bytenr, elem.seq, tmp,
+					roots, NULL, root_objectid, inum);
+		if (ret == BACKREF_FOUND_SHARED) {
+			ret = 1;
+			break;
+		}
+		if (ret < 0 && ret != -ENOENT)
+			break;
+		node = ulist_next(tmp, &uiter);
+		if (!node)
+			break;
+		bytenr = node->val;
+		cond_resched();
+	}
+	if (trans)
+		btrfs_put_tree_mod_seq(fs_info, &elem);
+	else
+		up_read(&fs_info->commit_root_sem);
+	ulist_free(tmp);
+	ulist_free(roots);
+	return ret;
+}
+
 /*
  * this makes the path point to (inum INODE_ITEM ioff)
  */
@@ -1193,7 +1278,7 @@ int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid,
 	unsigned long ptr;
 
 	key.objectid = inode_objectid;
-	btrfs_set_key_type(&key, BTRFS_INODE_EXTREF_KEY);
+	key.type = BTRFS_INODE_EXTREF_KEY;
 	key.offset = start_off;
 
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
@@ -1233,7 +1318,7 @@ int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid,
 		ret = -ENOENT;
 		if (found_key.objectid != inode_objectid)
 			break;
-		if (btrfs_key_type(&found_key) != BTRFS_INODE_EXTREF_KEY)
+		if (found_key.type != BTRFS_INODE_EXTREF_KEY)
 			break;
 
 		ret = 0;
@@ -1366,7 +1451,7 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 	}
 	btrfs_item_key_to_cpu(path->nodes[0], found_key, path->slots[0]);
 	if (found_key->type == BTRFS_METADATA_ITEM_KEY)
-		size = fs_info->extent_root->leafsize;
+		size = fs_info->extent_root->nodesize;
 	else if (found_key->type == BTRFS_EXTENT_ITEM_KEY)
 		size = found_key->offset;
 
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index 86fc20fec282..2a1ac6bfc724 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -71,6 +71,9 @@ int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid,
 			  u64 start_off, struct btrfs_path *path,
 			  struct btrfs_inode_extref **ret_extref,
 			  u64 *found_off);
+int btrfs_check_shared(struct btrfs_trans_handle *trans,
+		       struct btrfs_fs_info *fs_info, u64 root_objectid,
+		       u64 inum, u64 bytenr);
 
 int __init btrfs_prelim_ref_init(void);
 void btrfs_prelim_ref_exit(void);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 56b8522d5767..4aadadcfab20 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -44,6 +44,17 @@
 #define BTRFS_INODE_IN_DELALLOC_LIST		9
 #define BTRFS_INODE_READDIO_NEED_LOCK		10
 #define BTRFS_INODE_HAS_PROPS		        11
+/*
+ * The following 3 bits are meant only for the btree inode.
+ * When any of them is set, it means an error happened while writing an
+ * extent buffer belonging to:
+ * 1) a non-log btree
+ * 2) a log btree and first log sub-transaction
+ * 3) a log btree and second log sub-transaction
+ */
+#define BTRFS_INODE_BTREE_ERR		        12
+#define BTRFS_INODE_BTREE_LOG1_ERR		13
+#define BTRFS_INODE_BTREE_LOG2_ERR		14
 
 /* in memory btrfs inode */
 struct btrfs_inode {
@@ -121,6 +132,12 @@ struct btrfs_inode {
 	u64 delalloc_bytes;
 
 	/*
+	 * total number of bytes pending defrag, used by stat to check whether
+	 * it needs COW.
+	 */
+	u64 defrag_bytes;
+
+	/*
 	 * the size of the file stored in the metadata on disk.  data=ordered
 	 * means the in-memory i_size might be larger than the size on disk
 	 * because not all the blocks are written yet.
@@ -248,8 +265,11 @@ static inline int btrfs_inode_in_log(struct inode *inode, u64 generation)
 	return 0;
 }
 
+#define BTRFS_DIO_ORIG_BIO_SUBMITTED	0x1
+
 struct btrfs_dio_private {
 	struct inode *inode;
+	unsigned long flags;
 	u64 logical_offset;
 	u64 disk_bytenr;
 	u64 bytes;
@@ -266,7 +286,12 @@ struct btrfs_dio_private {
 
 	/* dio_bio came from fs/direct-io.c */
 	struct bio *dio_bio;
-	u8 csum[0];
+
+	/*
+	 * The original bio may be splited to several sub-bios, this is
+	 * done during endio of sub-bios
+	 */
+	int (*subio_endio)(struct inode *, struct btrfs_io_bio *, int);
 };
 
 /*
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index ce92ae30250f..cb7f3fe9c9f6 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -807,7 +807,7 @@ static int btrfsic_process_superblock_dev_mirror(
 
 	/* super block bytenr is always the unmapped device bytenr */
 	dev_bytenr = btrfs_sb_offset(superblock_mirror_num);
-	if (dev_bytenr + BTRFS_SUPER_INFO_SIZE > device->total_bytes)
+	if (dev_bytenr + BTRFS_SUPER_INFO_SIZE > device->commit_total_bytes)
 		return -1;
 	bh = __bread(superblock_bdev, dev_bytenr / 4096,
 		     BTRFS_SUPER_INFO_SIZE);
@@ -820,7 +820,6 @@ static int btrfsic_process_superblock_dev_mirror(
 	    btrfs_super_magic(super_tmp) != BTRFS_MAGIC ||
 	    memcmp(device->uuid, super_tmp->dev_item.uuid, BTRFS_UUID_SIZE) ||
 	    btrfs_super_nodesize(super_tmp) != state->metablock_size ||
-	    btrfs_super_leafsize(super_tmp) != state->metablock_size ||
 	    btrfs_super_sectorsize(super_tmp) != state->datablock_size) {
 		brelse(bh);
 		return 0;
@@ -1252,8 +1251,7 @@ static void btrfsic_read_from_block_data(
 
 	while (len > 0) {
 		cur = min(len, ((size_t)PAGE_CACHE_SIZE - offset_in_page));
-		BUG_ON(i >= (block_ctx->len + PAGE_CACHE_SIZE - 1) >>
-			    PAGE_CACHE_SHIFT);
+		BUG_ON(i >= DIV_ROUND_UP(block_ctx->len, PAGE_CACHE_SIZE));
 		kaddr = block_ctx->datav[i];
 		memcpy(dst, kaddr + offset_in_page, cur);
 
@@ -3120,24 +3118,12 @@ int btrfsic_mount(struct btrfs_root *root,
 	struct list_head *dev_head = &fs_devices->devices;
 	struct btrfs_device *device;
 
-	if (root->nodesize != root->leafsize) {
-		printk(KERN_INFO
-		       "btrfsic: cannot handle nodesize %d != leafsize %d!\n",
-		       root->nodesize, root->leafsize);
-		return -1;
-	}
 	if (root->nodesize & ((u64)PAGE_CACHE_SIZE - 1)) {
 		printk(KERN_INFO
 		       "btrfsic: cannot handle nodesize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n",
 		       root->nodesize, PAGE_CACHE_SIZE);
 		return -1;
 	}
-	if (root->leafsize & ((u64)PAGE_CACHE_SIZE - 1)) {
-		printk(KERN_INFO
-		       "btrfsic: cannot handle leafsize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n",
-		       root->leafsize, PAGE_CACHE_SIZE);
-		return -1;
-	}
 	if (root->sectorsize & ((u64)PAGE_CACHE_SIZE - 1)) {
 		printk(KERN_INFO
 		       "btrfsic: cannot handle sectorsize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n",
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 1daea0b47187..d3220d31d3cb 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -91,8 +91,7 @@ static inline int compressed_bio_size(struct btrfs_root *root,
 	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
 
 	return sizeof(struct compressed_bio) +
-		((disk_size + root->sectorsize - 1) / root->sectorsize) *
-		csum_size;
+		(DIV_ROUND_UP(disk_size, root->sectorsize)) * csum_size;
 }
 
 static struct bio *compressed_bio_alloc(struct block_device *bdev,
@@ -389,7 +388,8 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 			 * freed before we're done setting it up
 			 */
 			atomic_inc(&cb->pending_bios);
-			ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
+			ret = btrfs_bio_wq_end_io(root->fs_info, bio,
+					BTRFS_WQ_ENDIO_DATA);
 			BUG_ON(ret); /* -ENOMEM */
 
 			if (!skip_sum) {
@@ -420,7 +420,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	}
 	bio_get(bio);
 
-	ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
+	ret = btrfs_bio_wq_end_io(root->fs_info, bio, BTRFS_WQ_ENDIO_DATA);
 	BUG_ON(ret); /* -ENOMEM */
 
 	if (!skip_sum) {
@@ -615,8 +615,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	cb->compress_type = extent_compress_type(bio_flags);
 	cb->orig_bio = bio;
 
-	nr_pages = (compressed_len + PAGE_CACHE_SIZE - 1) /
-				 PAGE_CACHE_SIZE;
+	nr_pages = DIV_ROUND_UP(compressed_len, PAGE_CACHE_SIZE);
 	cb->compressed_pages = kzalloc(sizeof(struct page *) * nr_pages,
 				       GFP_NOFS);
 	if (!cb->compressed_pages)
@@ -670,7 +669,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		    PAGE_CACHE_SIZE) {
 			bio_get(comp_bio);
 
-			ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio, 0);
+			ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio,
+					BTRFS_WQ_ENDIO_DATA);
 			BUG_ON(ret); /* -ENOMEM */
 
 			/*
@@ -686,8 +686,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 							comp_bio, sums);
 				BUG_ON(ret); /* -ENOMEM */
 			}
-			sums += (comp_bio->bi_iter.bi_size +
-				 root->sectorsize - 1) / root->sectorsize;
+			sums += DIV_ROUND_UP(comp_bio->bi_iter.bi_size,
+					     root->sectorsize);
 
 			ret = btrfs_map_bio(root, READ, comp_bio,
 					    mirror_num, 0);
@@ -708,7 +708,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	}
 	bio_get(comp_bio);
 
-	ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio, 0);
+	ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio,
+			BTRFS_WQ_ENDIO_DATA);
 	BUG_ON(ret); /* -ENOMEM */
 
 	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 44ee5d2e52a4..19bc6162fb8e 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -258,9 +258,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 	else
 		btrfs_node_key(buf, &disk_key, 0);
 
-	cow = btrfs_alloc_free_block(trans, root, buf->len, 0,
-				     new_root_objectid, &disk_key, level,
-				     buf->start, 0);
+	cow = btrfs_alloc_tree_block(trans, root, 0, new_root_objectid,
+			&disk_key, level, buf->start, 0);
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
 
@@ -1133,9 +1132,9 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 	} else
 		parent_start = 0;
 
-	cow = btrfs_alloc_free_block(trans, root, buf->len, parent_start,
-				     root->root_key.objectid, &disk_key,
-				     level, search_start, empty_size);
+	cow = btrfs_alloc_tree_block(trans, root, parent_start,
+			root->root_key.objectid, &disk_key, level,
+			search_start, empty_size);
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
 
@@ -1425,7 +1424,6 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 	struct tree_mod_root *old_root = NULL;
 	u64 old_generation = 0;
 	u64 logical;
-	u32 blocksize;
 
 	eb_root = btrfs_read_lock_root_node(root);
 	tm = __tree_mod_log_oldest_root(root->fs_info, eb_root, time_seq);
@@ -1444,8 +1442,7 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 	if (old_root && tm && tm->op != MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
 		btrfs_tree_read_unlock(eb_root);
 		free_extent_buffer(eb_root);
-		blocksize = btrfs_level_size(root, old_root->level);
-		old = read_tree_block(root, logical, blocksize, 0);
+		old = read_tree_block(root, logical, 0);
 		if (WARN_ON(!old || !extent_buffer_uptodate(old))) {
 			free_extent_buffer(old);
 			btrfs_warn(root->fs_info,
@@ -1506,10 +1503,9 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root,
 				   struct extent_buffer *buf)
 {
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+	if (btrfs_test_is_dummy_root(root))
 		return 0;
-#endif
+
 	/* ensure we can see the force_cow */
 	smp_rmb();
 
@@ -1651,7 +1647,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 	WARN_ON(trans->transid != root->fs_info->generation);
 
 	parent_nritems = btrfs_header_nritems(parent);
-	blocksize = btrfs_level_size(root, parent_level - 1);
+	blocksize = root->nodesize;
 	end_slot = parent_nritems;
 
 	if (parent_nritems == 1)
@@ -1685,15 +1681,14 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 			continue;
 		}
 
-		cur = btrfs_find_tree_block(root, blocknr, blocksize);
+		cur = btrfs_find_tree_block(root, blocknr);
 		if (cur)
 			uptodate = btrfs_buffer_uptodate(cur, gen, 0);
 		else
 			uptodate = 0;
 		if (!cur || !uptodate) {
 			if (!cur) {
-				cur = read_tree_block(root, blocknr,
-							 blocksize, gen);
+				cur = read_tree_block(root, blocknr, gen);
 				if (!cur || !extent_buffer_uptodate(cur)) {
 					free_extent_buffer(cur);
 					return -EIO;
@@ -1872,7 +1867,6 @@ static noinline struct extent_buffer *read_node_slot(struct btrfs_root *root,
 	BUG_ON(level == 0);
 
 	eb = read_tree_block(root, btrfs_node_blockptr(parent, slot),
-			     btrfs_level_size(root, level - 1),
 			     btrfs_node_ptr_generation(parent, slot));
 	if (eb && !extent_buffer_uptodate(eb)) {
 		free_extent_buffer(eb);
@@ -2267,8 +2261,8 @@ static void reada_for_search(struct btrfs_root *root,
 	node = path->nodes[level];
 
 	search = btrfs_node_blockptr(node, slot);
-	blocksize = btrfs_level_size(root, level - 1);
-	eb = btrfs_find_tree_block(root, search, blocksize);
+	blocksize = root->nodesize;
+	eb = btrfs_find_tree_block(root, search);
 	if (eb) {
 		free_extent_buffer(eb);
 		return;
@@ -2298,7 +2292,7 @@ static void reada_for_search(struct btrfs_root *root,
 		if ((search <= target && target - search <= 65536) ||
 		    (search > target && search - target <= 65536)) {
 			gen = btrfs_node_ptr_generation(node, nr);
-			readahead_tree_block(root, search, blocksize, gen);
+			readahead_tree_block(root, search, blocksize);
 			nread += blocksize;
 		}
 		nscan++;
@@ -2325,12 +2319,12 @@ static noinline void reada_for_balance(struct btrfs_root *root,
 
 	nritems = btrfs_header_nritems(parent);
 	slot = path->slots[level + 1];
-	blocksize = btrfs_level_size(root, level);
+	blocksize = root->nodesize;
 
 	if (slot > 0) {
 		block1 = btrfs_node_blockptr(parent, slot - 1);
 		gen = btrfs_node_ptr_generation(parent, slot - 1);
-		eb = btrfs_find_tree_block(root, block1, blocksize);
+		eb = btrfs_find_tree_block(root, block1);
 		/*
 		 * if we get -eagain from btrfs_buffer_uptodate, we
 		 * don't want to return eagain here.  That will loop
@@ -2343,16 +2337,16 @@ static noinline void reada_for_balance(struct btrfs_root *root,
 	if (slot + 1 < nritems) {
 		block2 = btrfs_node_blockptr(parent, slot + 1);
 		gen = btrfs_node_ptr_generation(parent, slot + 1);
-		eb = btrfs_find_tree_block(root, block2, blocksize);
+		eb = btrfs_find_tree_block(root, block2);
 		if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0)
 			block2 = 0;
 		free_extent_buffer(eb);
 	}
 
 	if (block1)
-		readahead_tree_block(root, block1, blocksize, 0);
+		readahead_tree_block(root, block1, blocksize);
 	if (block2)
-		readahead_tree_block(root, block2, blocksize, 0);
+		readahead_tree_block(root, block2, blocksize);
 }
 
 
@@ -2454,16 +2448,14 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 {
 	u64 blocknr;
 	u64 gen;
-	u32 blocksize;
 	struct extent_buffer *b = *eb_ret;
 	struct extent_buffer *tmp;
 	int ret;
 
 	blocknr = btrfs_node_blockptr(b, slot);
 	gen = btrfs_node_ptr_generation(b, slot);
-	blocksize = btrfs_level_size(root, level - 1);
 
-	tmp = btrfs_find_tree_block(root, blocknr, blocksize);
+	tmp = btrfs_find_tree_block(root, blocknr);
 	if (tmp) {
 		/* first we do an atomic uptodate check */
 		if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) {
@@ -2507,7 +2499,7 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 	btrfs_release_path(p);
 
 	ret = -EAGAIN;
-	tmp = read_tree_block(root, blocknr, blocksize, 0);
+	tmp = read_tree_block(root, blocknr, 0);
 	if (tmp) {
 		/*
 		 * If the read above didn't mark this buffer up to date,
@@ -2792,8 +2784,6 @@ again:
 			if (!should_cow_block(trans, root, b))
 				goto cow_done;
 
-			btrfs_set_path_blocking(p);
-
 			/*
 			 * must have write locks on this node and the
 			 * parent
@@ -2807,6 +2797,7 @@ again:
 				goto again;
 			}
 
+			btrfs_set_path_blocking(p);
 			err = btrfs_cow_block(trans, root, b,
 					      p->nodes[level + 1],
 					      p->slots[level + 1], &b);
@@ -3362,9 +3353,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 	else
 		btrfs_node_key(lower, &lower_key, 0);
 
-	c = btrfs_alloc_free_block(trans, root, root->nodesize, 0,
-				   root->root_key.objectid, &lower_key,
-				   level, root->node->start, 0);
+	c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+				   &lower_key, level, root->node->start, 0);
 	if (IS_ERR(c))
 		return PTR_ERR(c);
 
@@ -3502,9 +3492,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 	mid = (c_nritems + 1) / 2;
 	btrfs_node_key(c, &disk_key, mid);
 
-	split = btrfs_alloc_free_block(trans, root, root->nodesize, 0,
-					root->root_key.objectid,
-					&disk_key, level, c->start, 0);
+	split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+			&disk_key, level, c->start, 0);
 	if (IS_ERR(split))
 		return PTR_ERR(split);
 
@@ -4282,13 +4271,12 @@ again:
 	else
 		btrfs_item_key(l, &disk_key, mid);
 
-	right = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
-					root->root_key.objectid,
-					&disk_key, 0, l->start, 0);
+	right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+			&disk_key, 0, l->start, 0);
 	if (IS_ERR(right))
 		return PTR_ERR(right);
 
-	root_add_used(root, root->leafsize);
+	root_add_used(root, root->nodesize);
 
 	memset_extent_buffer(right, 0, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_bytenr(right, right->start);
@@ -4626,8 +4614,7 @@ void btrfs_truncate_item(struct btrfs_root *root, struct btrfs_path *path,
 				ptr = btrfs_item_ptr_offset(leaf, slot);
 				memmove_extent_buffer(leaf, ptr,
 				      (unsigned long)fi,
-				      offsetof(struct btrfs_file_extent_item,
-						 disk_bytenr));
+				      BTRFS_FILE_EXTENT_INLINE_DATA_START);
 			}
 		}
 
@@ -4738,6 +4725,12 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
 	int slot;
 	struct btrfs_map_token token;
 
+	if (path->slots[0] == 0) {
+		btrfs_cpu_key_to_disk(&disk_key, cpu_key);
+		fixup_low_keys(root, path, &disk_key, 1);
+	}
+	btrfs_unlock_up_safe(path, 1);
+
 	btrfs_init_map_token(&token);
 
 	leaf = path->nodes[0];
@@ -4798,12 +4791,6 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
 	}
 
 	btrfs_set_header_nritems(leaf, nritems + nr);
-
-	if (slot == 0) {
-		btrfs_cpu_key_to_disk(&disk_key, cpu_key);
-		fixup_low_keys(root, path, &disk_key, 1);
-	}
-	btrfs_unlock_up_safe(path, 1);
 	btrfs_mark_buffer_dirty(leaf);
 
 	if (btrfs_leaf_free_space(root, leaf) < 0) {
@@ -5145,8 +5132,9 @@ int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key,
 	u32 nritems;
 	int level;
 	int ret = 1;
+	int keep_locks = path->keep_locks;
 
-	WARN_ON(!path->keep_locks);
+	path->keep_locks = 1;
 again:
 	cur = btrfs_read_lock_root_node(root);
 	level = btrfs_header_level(cur);
@@ -5210,7 +5198,6 @@ find_next_key:
 		path->slots[level] = slot;
 		if (level == path->lowest_level) {
 			ret = 0;
-			unlock_up(path, level, 1, 0, NULL);
 			goto out;
 		}
 		btrfs_set_path_blocking(path);
@@ -5225,9 +5212,12 @@ find_next_key:
 		btrfs_clear_path_blocking(path, NULL, 0);
 	}
 out:
-	if (ret == 0)
+	path->keep_locks = keep_locks;
+	if (ret == 0) {
+		btrfs_unlock_up_safe(path, path->lowest_level + 1);
+		btrfs_set_path_blocking(path);
 		memcpy(min_key, &found_key, sizeof(found_key));
-	btrfs_set_path_blocking(path);
+	}
 	return ret;
 }
 
@@ -5375,7 +5365,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 		goto out;
 	}
 
-	tmp_buf = kmalloc(left_root->leafsize, GFP_NOFS);
+	tmp_buf = kmalloc(left_root->nodesize, GFP_NOFS);
 	if (!tmp_buf) {
 		ret = -ENOMEM;
 		goto out;
@@ -5520,18 +5510,18 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 					goto out;
 				advance_right = ADVANCE;
 			} else {
-				enum btrfs_compare_tree_result cmp;
+				enum btrfs_compare_tree_result result;
 
 				WARN_ON(!extent_buffer_uptodate(left_path->nodes[0]));
 				ret = tree_compare_item(left_root, left_path,
 						right_path, tmp_buf);
 				if (ret)
-					cmp = BTRFS_COMPARE_TREE_CHANGED;
+					result = BTRFS_COMPARE_TREE_CHANGED;
 				else
-					cmp = BTRFS_COMPARE_TREE_SAME;
+					result = BTRFS_COMPARE_TREE_SAME;
 				ret = changed_cb(left_root, right_root,
 						 left_path, right_path,
-						 &left_key, cmp, ctx);
+						 &left_key, result, ctx);
 				if (ret < 0)
 					goto out;
 				advance_left = ADVANCE;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8e29b614fe93..d557264ee974 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -34,6 +34,7 @@
 #include <linux/pagemap.h>
 #include <linux/btrfs.h>
 #include <linux/workqueue.h>
+#include <linux/security.h>
 #include "extent_io.h"
 #include "extent_map.h"
 #include "async-thread.h"
@@ -62,13 +63,6 @@ struct btrfs_ordered_sum;
 
 #define BTRFS_COMPAT_EXTENT_TREE_V0
 
-/*
- * files bigger than this get some pre-flushing when they are added
- * to the ordered operations list.  That way we limit the total
- * work done by the commit
- */
-#define BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT (8 * 1024 * 1024)
-
 /* holds pointers to all of the tree roots */
 #define BTRFS_ROOT_TREE_OBJECTID 1ULL
 
@@ -391,10 +385,12 @@ struct btrfs_header {
 				      sizeof(struct btrfs_header)) / \
 				     sizeof(struct btrfs_key_ptr))
 #define __BTRFS_LEAF_DATA_SIZE(bs) ((bs) - sizeof(struct btrfs_header))
-#define BTRFS_LEAF_DATA_SIZE(r) (__BTRFS_LEAF_DATA_SIZE(r->leafsize))
+#define BTRFS_LEAF_DATA_SIZE(r) (__BTRFS_LEAF_DATA_SIZE(r->nodesize))
+#define BTRFS_FILE_EXTENT_INLINE_DATA_START		\
+		(offsetof(struct btrfs_file_extent_item, disk_bytenr))
 #define BTRFS_MAX_INLINE_DATA_SIZE(r) (BTRFS_LEAF_DATA_SIZE(r) - \
 					sizeof(struct btrfs_item) - \
-					sizeof(struct btrfs_file_extent_item))
+					BTRFS_FILE_EXTENT_INLINE_DATA_START)
 #define BTRFS_MAX_XATTR_SIZE(r)	(BTRFS_LEAF_DATA_SIZE(r) - \
 				 sizeof(struct btrfs_item) -\
 				 sizeof(struct btrfs_dir_item))
@@ -474,7 +470,7 @@ struct btrfs_super_block {
 	__le64 num_devices;
 	__le32 sectorsize;
 	__le32 nodesize;
-	__le32 leafsize;
+	__le32 __unused_leafsize;
 	__le32 stripesize;
 	__le32 sys_chunk_array_size;
 	__le64 chunk_root_generation;
@@ -903,6 +899,8 @@ struct btrfs_file_extent_item {
 	/*
 	 * disk space consumed by the extent, checksum blocks are included
 	 * in these numbers
+	 *
+	 * At this offset in the structure, the inline extent data start.
 	 */
 	__le64 disk_bytenr;
 	__le64 disk_num_bytes;
@@ -1305,8 +1303,8 @@ struct btrfs_block_group_cache {
 	 */
 	struct list_head cluster_list;
 
-	/* For delayed block group creation */
-	struct list_head new_bg_list;
+	/* For delayed block group creation or deletion of empty block groups */
+	struct list_head bg_list;
 };
 
 /* delayed seq elem */
@@ -1545,6 +1543,7 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *endio_workers;
 	struct btrfs_workqueue *endio_meta_workers;
 	struct btrfs_workqueue *endio_raid56_workers;
+	struct btrfs_workqueue *endio_repair_workers;
 	struct btrfs_workqueue *rmw_workers;
 	struct btrfs_workqueue *endio_meta_write_workers;
 	struct btrfs_workqueue *endio_write_workers;
@@ -1574,6 +1573,7 @@ struct btrfs_fs_info {
 	int do_barriers;
 	int closing;
 	int log_root_recovering;
+	int open;
 
 	u64 total_pinned;
 
@@ -1723,6 +1723,12 @@ struct btrfs_fs_info {
 
 	/* Used to reclaim the metadata space in the background. */
 	struct work_struct async_reclaim_work;
+
+	spinlock_t unused_bgs_lock;
+	struct list_head unused_bgs;
+
+	/* For btrfs to record security options */
+	struct security_mnt_opts security_opts;
 };
 
 struct btrfs_subvolume_writers {
@@ -1776,12 +1782,12 @@ struct btrfs_root {
 
 	/* free ino cache stuff */
 	struct btrfs_free_space_ctl *free_ino_ctl;
-	enum btrfs_caching_type cached;
-	spinlock_t cache_lock;
-	wait_queue_head_t cache_wait;
+	enum btrfs_caching_type ino_cache_state;
+	spinlock_t ino_cache_lock;
+	wait_queue_head_t ino_cache_wait;
 	struct btrfs_free_space_ctl *free_ino_pinned;
-	u64 cache_progress;
-	struct inode *cache_inode;
+	u64 ino_cache_progress;
+	struct inode *ino_cache_inode;
 
 	struct mutex log_mutex;
 	wait_queue_head_t log_writer_wait;
@@ -1806,18 +1812,14 @@ struct btrfs_root {
 	/* node allocations are done in nodesize units */
 	u32 nodesize;
 
-	/* leaf allocations are done in leafsize units */
-	u32 leafsize;
-
 	u32 stripesize;
 
 	u32 type;
 
 	u64 highest_objectid;
 
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	/* only used with CONFIG_BTRFS_FS_RUN_SANITY_TESTS is enabled */
 	u64 alloc_bytenr;
-#endif
 
 	u64 defrag_trans_start;
 	struct btrfs_key defrag_progress;
@@ -2094,6 +2096,7 @@ struct btrfs_ioctl_defrag_range_args {
 #define	BTRFS_MOUNT_CHANGE_INODE_CACHE	(1 << 24)
 
 #define BTRFS_DEFAULT_COMMIT_INTERVAL	(30)
+#define BTRFS_DEFAULT_MAX_INLINE	(8192)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
@@ -2995,8 +2998,6 @@ BTRFS_SETGET_STACK_FUNCS(super_sectorsize, struct btrfs_super_block,
 			 sectorsize, 32);
 BTRFS_SETGET_STACK_FUNCS(super_nodesize, struct btrfs_super_block,
 			 nodesize, 32);
-BTRFS_SETGET_STACK_FUNCS(super_leafsize, struct btrfs_super_block,
-			 leafsize, 32);
 BTRFS_SETGET_STACK_FUNCS(super_stripesize, struct btrfs_super_block,
 			 stripesize, 32);
 BTRFS_SETGET_STACK_FUNCS(super_root_dir, struct btrfs_super_block,
@@ -3049,14 +3050,12 @@ BTRFS_SETGET_STACK_FUNCS(stack_file_extent_compression,
 static inline unsigned long
 btrfs_file_extent_inline_start(struct btrfs_file_extent_item *e)
 {
-	unsigned long offset = (unsigned long)e;
-	offset += offsetof(struct btrfs_file_extent_item, disk_bytenr);
-	return offset;
+	return (unsigned long)e + BTRFS_FILE_EXTENT_INLINE_DATA_START;
 }
 
 static inline u32 btrfs_file_extent_calc_inline_size(u32 datasize)
 {
-	return offsetof(struct btrfs_file_extent_item, disk_bytenr) + datasize;
+	return BTRFS_FILE_EXTENT_INLINE_DATA_START + datasize;
 }
 
 BTRFS_SETGET_FUNCS(file_extent_disk_bytenr, struct btrfs_file_extent_item,
@@ -3086,9 +3085,7 @@ BTRFS_SETGET_FUNCS(file_extent_other_encoding, struct btrfs_file_extent_item,
 static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb,
 						    struct btrfs_item *e)
 {
-	unsigned long offset;
-	offset = offsetof(struct btrfs_file_extent_item, disk_bytenr);
-	return btrfs_item_size(eb, e) - offset;
+	return btrfs_item_size(eb, e) - BTRFS_FILE_EXTENT_INLINE_DATA_START;
 }
 
 /* this returns the number of file bytes represented by the inline item.
@@ -3232,13 +3229,6 @@ static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
-static inline u32 btrfs_level_size(struct btrfs_root *root, int level)
-{
-	if (level == 0)
-		return root->leafsize;
-	return root->nodesize;
-}
-
 /* helper function to cast into the data area of the leaf. */
 #define btrfs_item_ptr(leaf, slot, type) \
 	((type *)(btrfs_leaf_data(leaf) + \
@@ -3263,7 +3253,7 @@ static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
 static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root,
 						 unsigned num_items)
 {
-	return (root->leafsize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) *
+	return (root->nodesize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) *
 		2 * num_items;
 }
 
@@ -3274,8 +3264,7 @@ static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root,
 static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_root *root,
 						 unsigned num_items)
 {
-	return (root->leafsize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) *
-		num_items;
+	return root->nodesize * BTRFS_MAX_LEVEL * num_items;
 }
 
 int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
@@ -3305,9 +3294,9 @@ struct btrfs_block_group_cache *btrfs_lookup_block_group(
 						 u64 bytenr);
 void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int get_block_group_index(struct btrfs_block_group_cache *cache);
-struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root, u32 blocksize,
-					u64 parent, u64 root_objectid,
+struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
+					struct btrfs_root *root, u64 parent,
+					u64 root_objectid,
 					struct btrfs_disk_key *key, int level,
 					u64 hint, u64 empty_size);
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
@@ -3363,6 +3352,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 			   u64 size);
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 group_start);
+void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
 void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
 				       struct btrfs_root *root);
 u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data);
@@ -3604,6 +3594,7 @@ static inline void free_fs_info(struct btrfs_fs_info *fs_info)
 	kfree(fs_info->uuid_root);
 	kfree(fs_info->super_copy);
 	kfree(fs_info->super_for_commit);
+	security_free_mnt_opts(&fs_info->security_opts);
 	kfree(fs_info);
 }
 
@@ -3739,8 +3730,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode,
 			  struct bio *bio, u32 *dst);
 int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode,
-			      struct btrfs_dio_private *dip, struct bio *bio,
-			      u64 logical_offset);
+			      struct bio *bio, u64 logical_offset);
 int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
 			     u64 objectid, u64 pos,
@@ -4141,8 +4131,15 @@ static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info)
 /* Sanity test specific functions */
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 void btrfs_test_destroy_inode(struct inode *inode);
-int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
-			       u64 rfer, u64 excl);
 #endif
 
+static inline int btrfs_test_is_dummy_root(struct btrfs_root *root)
+{
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+		return 1;
+#endif
+	return 0;
+}
+
 #endif
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index a2e90f855d7d..054577bddaf2 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1042,7 +1042,7 @@ static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
 	int ret;
 
 	key.objectid = node->inode_id;
-	btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
+	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
 	if (test_bit(BTRFS_DELAYED_NODE_DEL_IREF, &node->flags))
@@ -1099,7 +1099,7 @@ err_out:
 search:
 	btrfs_release_path(path);
 
-	btrfs_set_key_type(&key, BTRFS_INODE_EXTREF_KEY);
+	key.type = BTRFS_INODE_EXTREF_KEY;
 	key.offset = -1;
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret < 0)
@@ -1473,7 +1473,7 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 	}
 
 	delayed_item->key.objectid = btrfs_ino(dir);
-	btrfs_set_key_type(&delayed_item->key, BTRFS_DIR_INDEX_KEY);
+	delayed_item->key.type = BTRFS_DIR_INDEX_KEY;
 	delayed_item->key.offset = index;
 
 	dir_item = (struct btrfs_dir_item *)delayed_item->data;
@@ -1542,7 +1542,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 		return PTR_ERR(node);
 
 	item_key.objectid = btrfs_ino(dir);
-	btrfs_set_key_type(&item_key, BTRFS_DIR_INDEX_KEY);
+	item_key.type = BTRFS_DIR_INDEX_KEY;
 	item_key.offset = index;
 
 	ret = btrfs_delete_delayed_insertion_item(root, node, &item_key);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index eea26e1b2fda..6f662b34ba0e 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -168,8 +168,12 @@ no_valid_dev_replace_entry_found:
 					dev_replace->srcdev->total_bytes;
 				dev_replace->tgtdev->disk_total_bytes =
 					dev_replace->srcdev->disk_total_bytes;
+				dev_replace->tgtdev->commit_total_bytes =
+					dev_replace->srcdev->commit_total_bytes;
 				dev_replace->tgtdev->bytes_used =
 					dev_replace->srcdev->bytes_used;
+				dev_replace->tgtdev->commit_bytes_used =
+					dev_replace->srcdev->commit_bytes_used;
 			}
 			dev_replace->tgtdev->is_tgtdev_for_dev_replace = 1;
 			btrfs_init_dev_replace_tgtdev_for_resume(fs_info,
@@ -329,30 +333,34 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	    args->start.tgtdev_name[0] == '\0')
 		return -EINVAL;
 
-	mutex_lock(&fs_info->volume_mutex);
-	ret = btrfs_init_dev_replace_tgtdev(root, args->start.tgtdev_name,
-					    &tgt_device);
-	if (ret) {
-		btrfs_err(fs_info, "target device %s is invalid!",
-		       args->start.tgtdev_name);
-		mutex_unlock(&fs_info->volume_mutex);
-		return -EINVAL;
+	/*
+	 * Here we commit the transaction to make sure commit_total_bytes
+	 * of all the devices are updated.
+	 */
+	trans = btrfs_attach_transaction(root);
+	if (!IS_ERR(trans)) {
+		ret = btrfs_commit_transaction(trans, root);
+		if (ret)
+			return ret;
+	} else if (PTR_ERR(trans) != -ENOENT) {
+		return PTR_ERR(trans);
 	}
 
+	/* the disk copy procedure reuses the scrub code */
+	mutex_lock(&fs_info->volume_mutex);
 	ret = btrfs_dev_replace_find_srcdev(root, args->start.srcdevid,
 					    args->start.srcdev_name,
 					    &src_device);
-	mutex_unlock(&fs_info->volume_mutex);
 	if (ret) {
-		ret = -EINVAL;
-		goto leave_no_lock;
+		mutex_unlock(&fs_info->volume_mutex);
+		return ret;
 	}
 
-	if (tgt_device->total_bytes < src_device->total_bytes) {
-		btrfs_err(fs_info, "target device is smaller than source device!");
-		ret = -EINVAL;
-		goto leave_no_lock;
-	}
+	ret = btrfs_init_dev_replace_tgtdev(root, args->start.tgtdev_name,
+					    src_device, &tgt_device);
+	mutex_unlock(&fs_info->volume_mutex);
+	if (ret)
+		return ret;
 
 	btrfs_dev_replace_lock(dev_replace);
 	switch (dev_replace->replace_state) {
@@ -380,10 +388,6 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 		      src_device->devid,
 		      rcu_str_deref(tgt_device->name));
 
-	tgt_device->total_bytes = src_device->total_bytes;
-	tgt_device->disk_total_bytes = src_device->disk_total_bytes;
-	tgt_device->bytes_used = src_device->bytes_used;
-
 	/*
 	 * from now on, the writes to the srcdev are all duplicated to
 	 * go to the tgtdev as well (refer to btrfs_map_block()).
@@ -414,7 +418,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 
 	/* the disk copy procedure reuses the scrub code */
 	ret = btrfs_scrub_dev(fs_info, src_device->devid, 0,
-			      src_device->total_bytes,
+			      btrfs_device_get_total_bytes(src_device),
 			      &dev_replace->scrub_progress, 0, 1);
 
 	ret = btrfs_dev_replace_finishing(root->fs_info, ret);
@@ -426,9 +430,7 @@ leave:
 	dev_replace->srcdev = NULL;
 	dev_replace->tgtdev = NULL;
 	btrfs_dev_replace_unlock(dev_replace);
-leave_no_lock:
-	if (tgt_device)
-		btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+	btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
 	return ret;
 }
 
@@ -507,9 +509,10 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	ret = btrfs_commit_transaction(trans, root);
 	WARN_ON(ret);
 
+	mutex_lock(&uuid_mutex);
 	/* keep away write_all_supers() during the finishing procedure */
-	mutex_lock(&root->fs_info->chunk_mutex);
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&root->fs_info->chunk_mutex);
 	btrfs_dev_replace_lock(dev_replace);
 	dev_replace->replace_state =
 		scrub_ret ? BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED
@@ -532,8 +535,9 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 			      src_device->devid,
 			      rcu_str_deref(tgt_device->name), scrub_ret);
 		btrfs_dev_replace_unlock(dev_replace);
-		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 		mutex_unlock(&root->fs_info->chunk_mutex);
+		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+		mutex_unlock(&uuid_mutex);
 		if (tgt_device)
 			btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
@@ -542,7 +546,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	}
 
 	printk_in_rcu(KERN_INFO
-		      "BTRFS: dev_replace from %s (devid %llu) to %s) finished\n",
+		      "BTRFS: dev_replace from %s (devid %llu) to %s finished\n",
 		      src_device->missing ? "<missing disk>" :
 		        rcu_str_deref(src_device->name),
 		      src_device->devid,
@@ -550,23 +554,29 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	tgt_device->is_tgtdev_for_dev_replace = 0;
 	tgt_device->devid = src_device->devid;
 	src_device->devid = BTRFS_DEV_REPLACE_DEVID;
-	tgt_device->bytes_used = src_device->bytes_used;
 	memcpy(uuid_tmp, tgt_device->uuid, sizeof(uuid_tmp));
 	memcpy(tgt_device->uuid, src_device->uuid, sizeof(tgt_device->uuid));
 	memcpy(src_device->uuid, uuid_tmp, sizeof(src_device->uuid));
-	tgt_device->total_bytes = src_device->total_bytes;
-	tgt_device->disk_total_bytes = src_device->disk_total_bytes;
-	tgt_device->bytes_used = src_device->bytes_used;
+	btrfs_device_set_total_bytes(tgt_device, src_device->total_bytes);
+	btrfs_device_set_disk_total_bytes(tgt_device,
+					  src_device->disk_total_bytes);
+	btrfs_device_set_bytes_used(tgt_device, src_device->bytes_used);
+	ASSERT(list_empty(&src_device->resized_list));
+	tgt_device->commit_total_bytes = src_device->commit_total_bytes;
+	tgt_device->commit_bytes_used = src_device->bytes_used;
 	if (fs_info->sb->s_bdev == src_device->bdev)
 		fs_info->sb->s_bdev = tgt_device->bdev;
 	if (fs_info->fs_devices->latest_bdev == src_device->bdev)
 		fs_info->fs_devices->latest_bdev = tgt_device->bdev;
 	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
+	fs_info->fs_devices->rw_devices++;
 
 	/* replace the sysfs entry */
 	btrfs_kobj_rm_device(fs_info, src_device);
 	btrfs_kobj_add_device(fs_info, tgt_device);
 
+	btrfs_dev_replace_unlock(dev_replace);
+
 	btrfs_rm_dev_replace_blocked(fs_info);
 
 	btrfs_rm_dev_replace_srcdev(fs_info, src_device);
@@ -580,9 +590,9 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	 * superblock is scratched out so that it is no longer marked to
 	 * belong to this filesystem.
 	 */
-	btrfs_dev_replace_unlock(dev_replace);
-	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 	mutex_unlock(&root->fs_info->chunk_mutex);
+	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&uuid_mutex);
 
 	/* write back the superblocks */
 	trans = btrfs_start_transaction(root, 0);
@@ -643,6 +653,7 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 			      struct btrfs_ioctl_dev_replace_args *args)
 {
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
+	struct btrfs_device *srcdev;
 
 	btrfs_dev_replace_lock(dev_replace);
 	/* even if !dev_replace_is_valid, the values are good enough for
@@ -665,8 +676,9 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 		break;
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
+		srcdev = dev_replace->srcdev;
 		args->status.progress_1000 = div64_u64(dev_replace->cursor_left,
-			div64_u64(dev_replace->srcdev->total_bytes, 1000));
+			div64_u64(btrfs_device_get_total_bytes(srcdev), 1000));
 		break;
 	}
 	btrfs_dev_replace_unlock(dev_replace);
@@ -825,7 +837,7 @@ static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info)
 
 	ret = btrfs_scrub_dev(fs_info, dev_replace->srcdev->devid,
 			      dev_replace->committed_cursor_left,
-			      dev_replace->srcdev->total_bytes,
+			      btrfs_device_get_total_bytes(dev_replace->srcdev),
 			      &dev_replace->scrub_progress, 0, 1);
 	ret = btrfs_dev_replace_finishing(fs_info, ret);
 	WARN_ON(ret);
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index a0691df5dcea..fc8df866e919 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -86,7 +86,7 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans,
 	BUG_ON(name_len + data_len > BTRFS_MAX_XATTR_SIZE(root));
 
 	key.objectid = objectid;
-	btrfs_set_key_type(&key, BTRFS_XATTR_ITEM_KEY);
+	key.type = BTRFS_XATTR_ITEM_KEY;
 	key.offset = btrfs_name_hash(name, name_len);
 
 	data_size = sizeof(*dir_item) + name_len + data_len;
@@ -137,7 +137,7 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
 	u32 data_size;
 
 	key.objectid = btrfs_ino(dir);
-	btrfs_set_key_type(&key, BTRFS_DIR_ITEM_KEY);
+	key.type = BTRFS_DIR_ITEM_KEY;
 	key.offset = btrfs_name_hash(name, name_len);
 
 	path = btrfs_alloc_path();
@@ -204,7 +204,7 @@ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans,
 	int cow = mod != 0;
 
 	key.objectid = dir;
-	btrfs_set_key_type(&key, BTRFS_DIR_ITEM_KEY);
+	key.type = BTRFS_DIR_ITEM_KEY;
 
 	key.offset = btrfs_name_hash(name, name_len);
 
@@ -234,7 +234,7 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
 		return -ENOMEM;
 
 	key.objectid = dir;
-	btrfs_set_key_type(&key, BTRFS_DIR_ITEM_KEY);
+	key.type = BTRFS_DIR_ITEM_KEY;
 	key.offset = btrfs_name_hash(name, name_len);
 
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
@@ -297,7 +297,7 @@ btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans,
 	int cow = mod != 0;
 
 	key.objectid = dir;
-	btrfs_set_key_type(&key, BTRFS_DIR_INDEX_KEY);
+	key.type = BTRFS_DIR_INDEX_KEY;
 	key.offset = objectid;
 
 	ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow);
@@ -367,7 +367,7 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
 	int cow = mod != 0;
 
 	key.objectid = dir;
-	btrfs_set_key_type(&key, BTRFS_XATTR_ITEM_KEY);
+	key.type = BTRFS_XATTR_ITEM_KEY;
 	key.offset = btrfs_name_hash(name, name_len);
 	ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow);
 	if (ret < 0)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a1d36e62179c..1ad0f47ac850 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -72,21 +72,41 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root);
 static void btrfs_error_commit_super(struct btrfs_root *root);
 
 /*
- * end_io_wq structs are used to do processing in task context when an IO is
- * complete.  This is used during reads to verify checksums, and it is used
+ * btrfs_end_io_wq structs are used to do processing in task context when an IO
+ * is complete.  This is used during reads to verify checksums, and it is used
  * by writes to insert metadata for new file extents after IO is complete.
  */
-struct end_io_wq {
+struct btrfs_end_io_wq {
 	struct bio *bio;
 	bio_end_io_t *end_io;
 	void *private;
 	struct btrfs_fs_info *info;
 	int error;
-	int metadata;
+	enum btrfs_wq_endio_type metadata;
 	struct list_head list;
 	struct btrfs_work work;
 };
 
+static struct kmem_cache *btrfs_end_io_wq_cache;
+
+int __init btrfs_end_io_wq_init(void)
+{
+	btrfs_end_io_wq_cache = kmem_cache_create("btrfs_end_io_wq",
+					sizeof(struct btrfs_end_io_wq),
+					0,
+					SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+					NULL);
+	if (!btrfs_end_io_wq_cache)
+		return -ENOMEM;
+	return 0;
+}
+
+void btrfs_end_io_wq_exit(void)
+{
+	if (btrfs_end_io_wq_cache)
+		kmem_cache_destroy(btrfs_end_io_wq_cache);
+}
+
 /*
  * async submit bios are used to offload expensive checksumming
  * onto the worker threads.  They checksum file and metadata bios
@@ -327,8 +347,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 {
 	struct extent_state *cached_state = NULL;
 	int ret;
-	bool need_lock = (current->journal_info ==
-			  (void *)BTRFS_SEND_TRANS_STUB);
+	bool need_lock = (current->journal_info == BTRFS_SEND_TRANS_STUB);
 
 	if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
 		return 0;
@@ -348,9 +367,9 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 		ret = 0;
 		goto out;
 	}
-	printk_ratelimited("parent transid verify failed on %llu wanted %llu "
-		       "found %llu\n",
-		       eb->start, parent_transid, btrfs_header_generation(eb));
+	printk_ratelimited(KERN_INFO "BTRFS (device %s): parent transid verify failed on %llu wanted %llu found %llu\n",
+			eb->fs_info->sb->s_id, eb->start,
+			parent_transid, btrfs_header_generation(eb));
 	ret = 1;
 
 	/*
@@ -607,22 +626,22 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 		goto err;
 
 	eb->read_mirror = mirror;
-	if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
+	if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
 		ret = -EIO;
 		goto err;
 	}
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != eb->start) {
-		printk_ratelimited(KERN_INFO "BTRFS: bad tree block start "
+		printk_ratelimited(KERN_INFO "BTRFS (device %s): bad tree block start "
 			       "%llu %llu\n",
-			       found_start, eb->start);
+			       eb->fs_info->sb->s_id, found_start, eb->start);
 		ret = -EIO;
 		goto err;
 	}
 	if (check_tree_block_fsid(root, eb)) {
-		printk_ratelimited(KERN_INFO "BTRFS: bad fsid on block %llu\n",
-			       eb->start);
+		printk_ratelimited(KERN_INFO "BTRFS (device %s): bad fsid on block %llu\n",
+			       eb->fs_info->sb->s_id, eb->start);
 		ret = -EIO;
 		goto err;
 	}
@@ -680,7 +699,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror)
 	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
 
 	eb = (struct extent_buffer *)page->private;
-	set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+	set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = failed_mirror;
 	atomic_dec(&eb->io_pages);
 	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
@@ -690,7 +709,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror)
 
 static void end_workqueue_bio(struct bio *bio, int err)
 {
-	struct end_io_wq *end_io_wq = bio->bi_private;
+	struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_workqueue *wq;
 	btrfs_work_func_t func;
@@ -713,7 +732,11 @@ static void end_workqueue_bio(struct bio *bio, int err)
 			func = btrfs_endio_write_helper;
 		}
 	} else {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+		if (unlikely(end_io_wq->metadata ==
+			     BTRFS_WQ_ENDIO_DIO_REPAIR)) {
+			wq = fs_info->endio_repair_workers;
+			func = btrfs_endio_repair_helper;
+		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
 			wq = fs_info->endio_raid56_workers;
 			func = btrfs_endio_raid56_helper;
 		} else if (end_io_wq->metadata) {
@@ -729,19 +752,12 @@ static void end_workqueue_bio(struct bio *bio, int err)
 	btrfs_queue_work(wq, &end_io_wq->work);
 }
 
-/*
- * For the metadata arg you want
- *
- * 0 - if data
- * 1 - if normal metadta
- * 2 - if writing to the free space cache area
- * 3 - raid parity work
- */
 int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
-			int metadata)
+			enum btrfs_wq_endio_type metadata)
 {
-	struct end_io_wq *end_io_wq;
-	end_io_wq = kmalloc(sizeof(*end_io_wq), GFP_NOFS);
+	struct btrfs_end_io_wq *end_io_wq;
+
+	end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS);
 	if (!end_io_wq)
 		return -ENOMEM;
 
@@ -925,7 +941,7 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 		 * can happen in the async kernel threads
 		 */
 		ret = btrfs_bio_wq_end_io(BTRFS_I(inode)->root->fs_info,
-					  bio, 1);
+					  bio, BTRFS_WQ_ENDIO_METADATA);
 		if (ret)
 			goto out_w_error;
 		ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
@@ -1057,20 +1073,17 @@ static const struct address_space_operations btree_aops = {
 	.set_page_dirty = btree_set_page_dirty,
 };
 
-int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize,
-			 u64 parent_transid)
+void readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize)
 {
 	struct extent_buffer *buf = NULL;
 	struct inode *btree_inode = root->fs_info->btree_inode;
-	int ret = 0;
 
 	buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
 	if (!buf)
-		return 0;
+		return;
 	read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
 				 buf, 0, WAIT_NONE, btree_get_extent, 0);
 	free_extent_buffer(buf);
-	return ret;
 }
 
 int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
@@ -1106,7 +1119,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
 }
 
 struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
-					    u64 bytenr, u32 blocksize)
+					    u64 bytenr)
 {
 	return find_extent_buffer(root->fs_info, bytenr);
 }
@@ -1114,11 +1127,9 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
 struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						 u64 bytenr, u32 blocksize)
 {
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+	if (btrfs_test_is_dummy_root(root))
 		return alloc_test_extent_buffer(root->fs_info, bytenr,
 						blocksize);
-#endif
 	return alloc_extent_buffer(root->fs_info, bytenr, blocksize);
 }
 
@@ -1136,12 +1147,12 @@ int btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
 }
 
 struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
-				      u32 blocksize, u64 parent_transid)
+				      u64 parent_transid)
 {
 	struct extent_buffer *buf = NULL;
 	int ret;
 
-	buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
+	buf = btrfs_find_create_tree_block(root, bytenr, root->nodesize);
 	if (!buf)
 		return NULL;
 
@@ -1183,7 +1194,7 @@ static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void)
 	if (!writers)
 		return ERR_PTR(-ENOMEM);
 
-	ret = percpu_counter_init(&writers->counter, 0);
+	ret = percpu_counter_init(&writers->counter, 0, GFP_KERNEL);
 	if (ret < 0) {
 		kfree(writers);
 		return ERR_PTR(ret);
@@ -1200,16 +1211,14 @@ btrfs_free_subvolume_writers(struct btrfs_subvolume_writers *writers)
 	kfree(writers);
 }
 
-static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
-			 u32 stripesize, struct btrfs_root *root,
-			 struct btrfs_fs_info *fs_info,
+static void __setup_root(u32 nodesize, u32 sectorsize, u32 stripesize,
+			 struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 			 u64 objectid)
 {
 	root->node = NULL;
 	root->commit_root = NULL;
 	root->sectorsize = sectorsize;
 	root->nodesize = nodesize;
-	root->leafsize = leafsize;
 	root->stripesize = stripesize;
 	root->state = 0;
 	root->orphan_cleanup_state = 0;
@@ -1295,7 +1304,7 @@ struct btrfs_root *btrfs_alloc_dummy_root(void)
 	root = btrfs_alloc_root(NULL);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
-	__setup_root(4096, 4096, 4096, 4096, root, NULL, 1);
+	__setup_root(4096, 4096, 4096, root, NULL, 1);
 	set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state);
 	root->alloc_bytenr = 0;
 
@@ -1318,15 +1327,13 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 
-	__setup_root(tree_root->nodesize, tree_root->leafsize,
-		     tree_root->sectorsize, tree_root->stripesize,
-		     root, fs_info, objectid);
+	__setup_root(tree_root->nodesize, tree_root->sectorsize,
+		tree_root->stripesize, root, fs_info, objectid);
 	root->root_key.objectid = objectid;
 	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
 	root->root_key.offset = 0;
 
-	leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
-				      0, objectid, NULL, 0, 0, 0);
+	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
 		leaf = NULL;
@@ -1396,9 +1403,9 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 
-	__setup_root(tree_root->nodesize, tree_root->leafsize,
-		     tree_root->sectorsize, tree_root->stripesize,
-		     root, fs_info, BTRFS_TREE_LOG_OBJECTID);
+	__setup_root(tree_root->nodesize, tree_root->sectorsize,
+		     tree_root->stripesize, root, fs_info,
+		     BTRFS_TREE_LOG_OBJECTID);
 
 	root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID;
 	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
@@ -1413,9 +1420,8 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	 * updated (along with back refs to the log tree).
 	 */
 
-	leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
-				      BTRFS_TREE_LOG_OBJECTID, NULL,
-				      0, 0, 0);
+	leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
+			NULL, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		kfree(root);
 		return ERR_CAST(leaf);
@@ -1465,7 +1471,7 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 	btrfs_set_stack_inode_generation(inode_item, 1);
 	btrfs_set_stack_inode_size(inode_item, 3);
 	btrfs_set_stack_inode_nlink(inode_item, 1);
-	btrfs_set_stack_inode_nbytes(inode_item, root->leafsize);
+	btrfs_set_stack_inode_nbytes(inode_item, root->nodesize);
 	btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
 
 	btrfs_set_root_node(&log_root->root_item, log_root->node);
@@ -1485,7 +1491,6 @@ static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
 	struct btrfs_fs_info *fs_info = tree_root->fs_info;
 	struct btrfs_path *path;
 	u64 generation;
-	u32 blocksize;
 	int ret;
 
 	path = btrfs_alloc_path();
@@ -1498,9 +1503,8 @@ static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
 		goto alloc_fail;
 	}
 
-	__setup_root(tree_root->nodesize, tree_root->leafsize,
-		     tree_root->sectorsize, tree_root->stripesize,
-		     root, fs_info, key->objectid);
+	__setup_root(tree_root->nodesize, tree_root->sectorsize,
+		tree_root->stripesize, root, fs_info, key->objectid);
 
 	ret = btrfs_find_root(tree_root, key, path,
 			      &root->root_item, &root->root_key);
@@ -1511,9 +1515,8 @@ static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
 	}
 
 	generation = btrfs_root_generation(&root->root_item);
-	blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
 	root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
-				     blocksize, generation);
+				     generation);
 	if (!root->node) {
 		ret = -ENOMEM;
 		goto find_fail;
@@ -1573,8 +1576,8 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 	root->subv_writers = writers;
 
 	btrfs_init_free_ino_ctl(root);
-	spin_lock_init(&root->cache_lock);
-	init_waitqueue_head(&root->cache_wait);
+	spin_lock_init(&root->ino_cache_lock);
+	init_waitqueue_head(&root->ino_cache_wait);
 
 	ret = get_anon_bdev(&root->anon_dev);
 	if (ret)
@@ -1699,7 +1702,7 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 		if (!device->bdev)
 			continue;
 		bdi = blk_get_backing_dev_info(device->bdev);
-		if (bdi && bdi_congested(bdi, bdi_bits)) {
+		if (bdi_congested(bdi, bdi_bits)) {
 			ret = 1;
 			break;
 		}
@@ -1708,10 +1711,6 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 	return ret;
 }
 
-/*
- * If this fails, caller must call bdi_destroy() to get rid of the
- * bdi again.
- */
 static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 {
 	int err;
@@ -1734,16 +1733,16 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 static void end_workqueue_fn(struct btrfs_work *work)
 {
 	struct bio *bio;
-	struct end_io_wq *end_io_wq;
+	struct btrfs_end_io_wq *end_io_wq;
 	int error;
 
-	end_io_wq = container_of(work, struct end_io_wq, work);
+	end_io_wq = container_of(work, struct btrfs_end_io_wq, work);
 	bio = end_io_wq->bio;
 
 	error = end_io_wq->error;
 	bio->bi_private = end_io_wq->private;
 	bio->bi_end_io = end_io_wq->end_io;
-	kfree(end_io_wq);
+	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
 	bio_endio_nodec(bio, error);
 }
 
@@ -1772,6 +1771,7 @@ static int cleaner_kthread(void *arg)
 		}
 
 		btrfs_run_delayed_iputs(root);
+		btrfs_delete_unused_bgs(root->fs_info);
 		again = btrfs_clean_one_deleted_snapshot(root);
 		mutex_unlock(&root->fs_info->cleaner_mutex);
 
@@ -2063,6 +2063,7 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->endio_workers);
 	btrfs_destroy_workqueue(fs_info->endio_meta_workers);
 	btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
+	btrfs_destroy_workqueue(fs_info->endio_repair_workers);
 	btrfs_destroy_workqueue(fs_info->rmw_workers);
 	btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
 	btrfs_destroy_workqueue(fs_info->endio_write_workers);
@@ -2143,8 +2144,6 @@ int open_ctree(struct super_block *sb,
 {
 	u32 sectorsize;
 	u32 nodesize;
-	u32 leafsize;
-	u32 blocksize;
 	u32 stripesize;
 	u64 generation;
 	u64 features;
@@ -2188,7 +2187,7 @@ int open_ctree(struct super_block *sb,
 		goto fail_srcu;
 	}
 
-	ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0);
+	ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
 	if (ret) {
 		err = ret;
 		goto fail_bdi;
@@ -2196,13 +2195,13 @@ int open_ctree(struct super_block *sb,
 	fs_info->dirty_metadata_batch = PAGE_CACHE_SIZE *
 					(1 + ilog2(nr_cpu_ids));
 
-	ret = percpu_counter_init(&fs_info->delalloc_bytes, 0);
+	ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL);
 	if (ret) {
 		err = ret;
 		goto fail_dirty_metadata_bytes;
 	}
 
-	ret = percpu_counter_init(&fs_info->bio_counter, 0);
+	ret = percpu_counter_init(&fs_info->bio_counter, 0, GFP_KERNEL);
 	if (ret) {
 		err = ret;
 		goto fail_delalloc_bytes;
@@ -2233,6 +2232,7 @@ int open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->qgroup_op_lock);
 	spin_lock_init(&fs_info->buffer_lock);
+	spin_lock_init(&fs_info->unused_bgs_lock);
 	rwlock_init(&fs_info->tree_mod_log_lock);
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
@@ -2242,6 +2242,7 @@ int open_ctree(struct super_block *sb,
 	INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
 	INIT_LIST_HEAD(&fs_info->space_info);
 	INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
+	INIT_LIST_HEAD(&fs_info->unused_bgs);
 	btrfs_mapping_init(&fs_info->mapping_tree);
 	btrfs_init_block_rsv(&fs_info->global_block_rsv,
 			     BTRFS_BLOCK_RSV_GLOBAL);
@@ -2260,7 +2261,7 @@ int open_ctree(struct super_block *sb,
 	atomic_set(&fs_info->qgroup_op_seq, 0);
 	atomic64_set(&fs_info->tree_mod_seq, 0);
 	fs_info->sb = sb;
-	fs_info->max_inline = 8192 * 1024;
+	fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
 	fs_info->metadata_ratio = 0;
 	fs_info->defrag_inodes = RB_ROOT;
 	fs_info->free_chunk_space = 0;
@@ -2389,7 +2390,7 @@ int open_ctree(struct super_block *sb,
 		goto fail_alloc;
 	}
 
-	__setup_root(4096, 4096, 4096, 4096, tree_root,
+	__setup_root(4096, 4096, 4096, tree_root,
 		     fs_info, BTRFS_ROOT_TREE_OBJECTID);
 
 	invalidate_bdev(fs_devices->latest_bdev);
@@ -2469,19 +2470,22 @@ int open_ctree(struct super_block *sb,
 		goto fail_alloc;
 	}
 
-	if (btrfs_super_leafsize(disk_super) !=
+	/*
+	 * Leafsize and nodesize were always equal, this is only a sanity check.
+	 */
+	if (le32_to_cpu(disk_super->__unused_leafsize) !=
 	    btrfs_super_nodesize(disk_super)) {
 		printk(KERN_ERR "BTRFS: couldn't mount because metadata "
 		       "blocksizes don't match.  node %d leaf %d\n",
 		       btrfs_super_nodesize(disk_super),
-		       btrfs_super_leafsize(disk_super));
+		       le32_to_cpu(disk_super->__unused_leafsize));
 		err = -EINVAL;
 		goto fail_alloc;
 	}
-	if (btrfs_super_leafsize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) {
+	if (btrfs_super_nodesize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) {
 		printk(KERN_ERR "BTRFS: couldn't mount because metadata "
 		       "blocksize (%d) was too large\n",
-		       btrfs_super_leafsize(disk_super));
+		       btrfs_super_nodesize(disk_super));
 		err = -EINVAL;
 		goto fail_alloc;
 	}
@@ -2498,17 +2502,16 @@ int open_ctree(struct super_block *sb,
 	 * flag our filesystem as having big metadata blocks if
 	 * they are bigger than the page size
 	 */
-	if (btrfs_super_leafsize(disk_super) > PAGE_CACHE_SIZE) {
+	if (btrfs_super_nodesize(disk_super) > PAGE_CACHE_SIZE) {
 		if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
 			printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n");
 		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
 	}
 
 	nodesize = btrfs_super_nodesize(disk_super);
-	leafsize = btrfs_super_leafsize(disk_super);
 	sectorsize = btrfs_super_sectorsize(disk_super);
 	stripesize = btrfs_super_stripesize(disk_super);
-	fs_info->dirty_metadata_batch = leafsize * (1 + ilog2(nr_cpu_ids));
+	fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
 	fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
 
 	/*
@@ -2516,7 +2519,7 @@ int open_ctree(struct super_block *sb,
 	 * extent buffers for the same range.  It leads to corruptions
 	 */
 	if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
-	    (sectorsize != leafsize)) {
+	    (sectorsize != nodesize)) {
 		printk(KERN_WARNING "BTRFS: unequal leaf/node/sector sizes "
 				"are not allowed for mixed block groups on %s\n",
 				sb->s_id);
@@ -2579,6 +2582,8 @@ int open_ctree(struct super_block *sb,
 		btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2);
 	fs_info->endio_raid56_workers =
 		btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4);
+	fs_info->endio_repair_workers =
+		btrfs_alloc_workqueue("endio-repair", flags, 1, 0);
 	fs_info->rmw_workers =
 		btrfs_alloc_workqueue("rmw", flags, max_active, 2);
 	fs_info->endio_write_workers =
@@ -2600,11 +2605,12 @@ int open_ctree(struct super_block *sb,
 	      fs_info->submit_workers && fs_info->flush_workers &&
 	      fs_info->endio_workers && fs_info->endio_meta_workers &&
 	      fs_info->endio_meta_write_workers &&
+	      fs_info->endio_repair_workers &&
 	      fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
 	      fs_info->endio_freespace_worker && fs_info->rmw_workers &&
 	      fs_info->caching_workers && fs_info->readahead_workers &&
 	      fs_info->fixup_workers && fs_info->delayed_workers &&
-	      fs_info->fixup_workers && fs_info->extent_workers &&
+	      fs_info->extent_workers &&
 	      fs_info->qgroup_rescan_workers)) {
 		err = -ENOMEM;
 		goto fail_sb_buffer;
@@ -2615,7 +2621,6 @@ int open_ctree(struct super_block *sb,
 				    4 * 1024 * 1024 / PAGE_CACHE_SIZE);
 
 	tree_root->nodesize = nodesize;
-	tree_root->leafsize = leafsize;
 	tree_root->sectorsize = sectorsize;
 	tree_root->stripesize = stripesize;
 
@@ -2642,16 +2647,14 @@ int open_ctree(struct super_block *sb,
 		goto fail_sb_buffer;
 	}
 
-	blocksize = btrfs_level_size(tree_root,
-				     btrfs_super_chunk_root_level(disk_super));
 	generation = btrfs_super_chunk_root_generation(disk_super);
 
-	__setup_root(nodesize, leafsize, sectorsize, stripesize,
-		     chunk_root, fs_info, BTRFS_CHUNK_TREE_OBJECTID);
+	__setup_root(nodesize, sectorsize, stripesize, chunk_root,
+		     fs_info, BTRFS_CHUNK_TREE_OBJECTID);
 
 	chunk_root->node = read_tree_block(chunk_root,
 					   btrfs_super_chunk_root(disk_super),
-					   blocksize, generation);
+					   generation);
 	if (!chunk_root->node ||
 	    !test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) {
 		printk(KERN_WARNING "BTRFS: failed to read chunk root on %s\n",
@@ -2684,13 +2687,11 @@ int open_ctree(struct super_block *sb,
 	}
 
 retry_root_backup:
-	blocksize = btrfs_level_size(tree_root,
-				     btrfs_super_root_level(disk_super));
 	generation = btrfs_super_generation(disk_super);
 
 	tree_root->node = read_tree_block(tree_root,
 					  btrfs_super_root(disk_super),
-					  blocksize, generation);
+					  generation);
 	if (!tree_root->node ||
 	    !test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) {
 		printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
@@ -2859,9 +2860,6 @@ retry_root_backup:
 			err = -EIO;
 			goto fail_qgroup;
 		}
-		blocksize =
-		     btrfs_level_size(tree_root,
-				      btrfs_super_log_root_level(disk_super));
 
 		log_tree_root = btrfs_alloc_root(fs_info);
 		if (!log_tree_root) {
@@ -2869,11 +2867,10 @@ retry_root_backup:
 			goto fail_qgroup;
 		}
 
-		__setup_root(nodesize, leafsize, sectorsize, stripesize,
+		__setup_root(nodesize, sectorsize, stripesize,
 			     log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID);
 
 		log_tree_root->node = read_tree_block(tree_root, bytenr,
-						      blocksize,
 						      generation + 1);
 		if (!log_tree_root->node ||
 		    !extent_buffer_uptodate(log_tree_root->node)) {
@@ -2980,6 +2977,8 @@ retry_root_backup:
 		fs_info->update_uuid_tree_gen = 1;
 	}
 
+	fs_info->open = 1;
+
 	return 0;
 
 fail_qgroup:
@@ -3139,7 +3138,8 @@ static int write_dev_supers(struct btrfs_device *device,
 
 	for (i = 0; i < max_mirrors; i++) {
 		bytenr = btrfs_sb_offset(i);
-		if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->total_bytes)
+		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
+		    device->commit_total_bytes)
 			break;
 
 		if (wait) {
@@ -3456,8 +3456,9 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
 		btrfs_set_stack_device_type(dev_item, dev->type);
 		btrfs_set_stack_device_id(dev_item, dev->devid);
 		btrfs_set_stack_device_total_bytes(dev_item,
-						   dev->disk_total_bytes);
-		btrfs_set_stack_device_bytes_used(dev_item, dev->bytes_used);
+						   dev->commit_total_bytes);
+		btrfs_set_stack_device_bytes_used(dev_item,
+						  dev->commit_bytes_used);
 		btrfs_set_stack_device_io_align(dev_item, dev->io_align);
 		btrfs_set_stack_device_io_width(dev_item, dev->io_width);
 		btrfs_set_stack_device_sector_size(dev_item, dev->sector_size);
@@ -3532,7 +3533,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 
 static void free_fs_root(struct btrfs_root *root)
 {
-	iput(root->cache_inode);
+	iput(root->ino_cache_inode);
 	WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
 	btrfs_free_block_rsv(root, root->orphan_block_rsv);
 	root->orphan_block_rsv = NULL;
@@ -3623,7 +3624,7 @@ int btrfs_commit_super(struct btrfs_root *root)
 	return btrfs_commit_transaction(trans, root);
 }
 
-int close_ctree(struct btrfs_root *root)
+void close_ctree(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
@@ -3689,6 +3690,7 @@ int close_ctree(struct btrfs_root *root)
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
+	fs_info->open = 0;
 	free_root_pointers(fs_info, 1);
 
 	iput(fs_info->btree_inode);
@@ -3711,8 +3713,6 @@ int close_ctree(struct btrfs_root *root)
 
 	btrfs_free_block_rsv(root, root->orphan_block_rsv);
 	root->orphan_block_rsv = NULL;
-
-	return 0;
 }
 
 int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
@@ -3814,10 +3814,73 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid)
 static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 			      int read_only)
 {
+	struct btrfs_super_block *sb = fs_info->super_copy;
+	int ret = 0;
+
+	if (sb->root_level > BTRFS_MAX_LEVEL) {
+		printk(KERN_ERR "BTRFS: tree_root level too big: %d > %d\n",
+				sb->root_level, BTRFS_MAX_LEVEL);
+		ret = -EINVAL;
+	}
+	if (sb->chunk_root_level > BTRFS_MAX_LEVEL) {
+		printk(KERN_ERR "BTRFS: chunk_root level too big: %d > %d\n",
+				sb->chunk_root_level, BTRFS_MAX_LEVEL);
+		ret = -EINVAL;
+	}
+	if (sb->log_root_level > BTRFS_MAX_LEVEL) {
+		printk(KERN_ERR "BTRFS: log_root level too big: %d > %d\n",
+				sb->log_root_level, BTRFS_MAX_LEVEL);
+		ret = -EINVAL;
+	}
+
 	/*
-	 * Placeholder for checks
+	 * The common minimum, we don't know if we can trust the nodesize/sectorsize
+	 * items yet, they'll be verified later. Issue just a warning.
 	 */
-	return 0;
+	if (!IS_ALIGNED(sb->root, 4096))
+		printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
+				sb->root);
+	if (!IS_ALIGNED(sb->chunk_root, 4096))
+		printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
+				sb->chunk_root);
+	if (!IS_ALIGNED(sb->log_root, 4096))
+		printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
+				sb->log_root);
+
+	if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) {
+		printk(KERN_ERR "BTRFS: dev_item UUID does not match fsid: %pU != %pU\n",
+				fs_info->fsid, sb->dev_item.fsid);
+		ret = -EINVAL;
+	}
+
+	/*
+	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
+	 * done later
+	 */
+	if (sb->num_devices > (1UL << 31))
+		printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
+				sb->num_devices);
+
+	if (sb->bytenr != BTRFS_SUPER_INFO_OFFSET) {
+		printk(KERN_ERR "BTRFS: super offset mismatch %llu != %u\n",
+				sb->bytenr, BTRFS_SUPER_INFO_OFFSET);
+		ret = -EINVAL;
+	}
+
+	/*
+	 * The generation is a global counter, we'll trust it more than the others
+	 * but it's still possible that it's the one that's wrong.
+	 */
+	if (sb->generation < sb->chunk_root_generation)
+		printk(KERN_WARNING
+			"BTRFS: suspicious: generation < chunk_root_generation: %llu < %llu\n",
+			sb->generation, sb->chunk_root_generation);
+	if (sb->generation < sb->cache_generation && sb->cache_generation != (u64)-1)
+		printk(KERN_WARNING
+			"BTRFS: suspicious: generation < cache_generation: %llu < %llu\n",
+			sb->generation, sb->cache_generation);
+
+	return ret;
 }
 
 static void btrfs_error_commit_super(struct btrfs_root *root)
@@ -4009,9 +4072,8 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root,
 
 		clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS);
 		while (start <= end) {
-			eb = btrfs_find_tree_block(root, start,
-						   root->leafsize);
-			start += root->leafsize;
+			eb = btrfs_find_tree_block(root, start);
+			start += root->nodesize;
 			if (!eb)
 				continue;
 			wait_on_extent_buffer_writeback(eb);
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 23ce3ceba0a9..414651821fb3 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -25,11 +25,12 @@
 #define BTRFS_SUPER_MIRROR_MAX	 3
 #define BTRFS_SUPER_MIRROR_SHIFT 12
 
-enum {
+enum btrfs_wq_endio_type {
 	BTRFS_WQ_ENDIO_DATA = 0,
 	BTRFS_WQ_ENDIO_METADATA = 1,
 	BTRFS_WQ_ENDIO_FREE_SPACE = 2,
 	BTRFS_WQ_ENDIO_RAID56 = 3,
+	BTRFS_WQ_ENDIO_DIO_REPAIR = 4,
 };
 
 static inline u64 btrfs_sb_offset(int mirror)
@@ -44,9 +45,8 @@ struct btrfs_device;
 struct btrfs_fs_devices;
 
 struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
-				      u32 blocksize, u64 parent_transid);
-int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize,
-			 u64 parent_transid);
+				      u64 parent_transid);
+void readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize);
 int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
 			 int mirror_num, struct extent_buffer **eb);
 struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
@@ -56,13 +56,13 @@ void clean_tree_block(struct btrfs_trans_handle *trans,
 int open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options);
-int close_ctree(struct btrfs_root *root);
+void close_ctree(struct btrfs_root *root);
 int write_ctree_super(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root, int max_mirrors);
 struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
 int btrfs_commit_super(struct btrfs_root *root);
 struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
-					    u64 bytenr, u32 blocksize);
+					    u64 bytenr);
 struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
 				      struct btrfs_key *location);
 int btrfs_init_fs_root(struct btrfs_root *root);
@@ -119,7 +119,7 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid);
 u32 btrfs_csum_data(char *data, u32 seed, size_t len);
 void btrfs_csum_final(u32 crc, char *result);
 int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
-			int metadata);
+			enum btrfs_wq_endio_type metadata);
 int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
 			int rw, struct bio *bio, int mirror_num,
 			unsigned long bio_flags, u64 bio_offset,
@@ -141,6 +141,8 @@ int btree_lock_page_hook(struct page *page, void *data,
 				void (*flush_fn)(void *));
 int btrfs_calc_num_tolerated_disk_barrier_failures(
 	struct btrfs_fs_info *fs_info);
+int __init btrfs_end_io_wq_init(void);
+void btrfs_end_io_wq_exit(void);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 void btrfs_init_lockdep(void);
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 41422a3de8ed..37d164540c3a 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -70,7 +70,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
 		return ERR_PTR(-ESTALE);
 
 	key.objectid = root_objectid;
-	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
+	key.type = BTRFS_ROOT_ITEM_KEY;
 	key.offset = (u64)-1;
 
 	index = srcu_read_lock(&fs_info->subvol_srcu);
@@ -82,7 +82,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
 	}
 
 	key.objectid = objectid;
-	btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
+	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
 	inode = btrfs_iget(sb, &key, root, NULL);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3efe1c3877bf..d56589571012 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -491,7 +491,7 @@ next:
 							  key.objectid);
 			if (key.type == BTRFS_METADATA_ITEM_KEY)
 				last = key.objectid +
-					fs_info->tree_root->leafsize;
+					fs_info->tree_root->nodesize;
 			else
 				last = key.objectid + key.offset;
 
@@ -765,7 +765,7 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 	 * different
 	 */
 	if (metadata && !btrfs_fs_incompat(root->fs_info, SKINNY_METADATA)) {
-		offset = root->leafsize;
+		offset = root->nodesize;
 		metadata = 0;
 	}
 
@@ -799,13 +799,13 @@ again:
 					      path->slots[0]);
 			if (key.objectid == bytenr &&
 			    key.type == BTRFS_EXTENT_ITEM_KEY &&
-			    key.offset == root->leafsize)
+			    key.offset == root->nodesize)
 				ret = 0;
 		}
 		if (ret) {
 			key.objectid = bytenr;
 			key.type = BTRFS_EXTENT_ITEM_KEY;
-			key.offset = root->leafsize;
+			key.offset = root->nodesize;
 			btrfs_release_path(path);
 			goto again;
 		}
@@ -2651,7 +2651,7 @@ int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
 	num_bytes = btrfs_calc_trans_metadata_size(root, 1);
 	num_heads = heads_to_leaves(root, num_heads);
 	if (num_heads > 1)
-		num_bytes += (num_heads - 1) * root->leafsize;
+		num_bytes += (num_heads - 1) * root->nodesize;
 	num_bytes <<= 1;
 	global_rsv = &root->fs_info->global_block_rsv;
 
@@ -3073,10 +3073,10 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 	int (*process_func)(struct btrfs_trans_handle *, struct btrfs_root *,
 			    u64, u64, u64, u64, u64, u64, int);
 
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+
+	if (btrfs_test_is_dummy_root(root))
 		return 0;
-#endif
+
 	ref_root = btrfs_header_owner(buf);
 	nritems = btrfs_header_nritems(buf);
 	level = btrfs_header_level(buf);
@@ -3097,7 +3097,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 	for (i = 0; i < nritems; i++) {
 		if (level == 0) {
 			btrfs_item_key_to_cpu(buf, &key, i);
-			if (btrfs_key_type(&key) != BTRFS_EXTENT_DATA_KEY)
+			if (key.type != BTRFS_EXTENT_DATA_KEY)
 				continue;
 			fi = btrfs_item_ptr(buf, i,
 					    struct btrfs_file_extent_item);
@@ -3117,7 +3117,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 				goto fail;
 		} else {
 			bytenr = btrfs_node_blockptr(buf, i);
-			num_bytes = btrfs_level_size(root, level - 1);
+			num_bytes = root->nodesize;
 			ret = process_func(trans, root, bytenr, num_bytes,
 					   parent, ref_root, level - 1, 0,
 					   1);
@@ -3494,7 +3494,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 	if (!found)
 		return -ENOMEM;
 
-	ret = percpu_counter_init(&found->total_bytes_pinned, 0);
+	ret = percpu_counter_init(&found->total_bytes_pinned, 0, GFP_KERNEL);
 	if (ret) {
 		kfree(found);
 		return ret;
@@ -4343,11 +4343,21 @@ static inline int need_do_async_reclaim(struct btrfs_space_info *space_info,
 }
 
 static int btrfs_need_do_async_reclaim(struct btrfs_space_info *space_info,
-				       struct btrfs_fs_info *fs_info)
+				       struct btrfs_fs_info *fs_info,
+				       int flush_state)
 {
 	u64 used;
 
 	spin_lock(&space_info->lock);
+	/*
+	 * We run out of space and have not got any free space via flush_space,
+	 * so don't bother doing async reclaim.
+	 */
+	if (flush_state > COMMIT_TRANS && space_info->full) {
+		spin_unlock(&space_info->lock);
+		return 0;
+	}
+
 	used = space_info->bytes_used + space_info->bytes_reserved +
 	       space_info->bytes_pinned + space_info->bytes_readonly +
 	       space_info->bytes_may_use;
@@ -4380,11 +4390,12 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
 		flush_space(fs_info->fs_root, space_info, to_reclaim,
 			    to_reclaim, flush_state);
 		flush_state++;
-		if (!btrfs_need_do_async_reclaim(space_info, fs_info))
+		if (!btrfs_need_do_async_reclaim(space_info, fs_info,
+						 flush_state))
 			return;
 	} while (flush_state <= COMMIT_TRANS);
 
-	if (btrfs_need_do_async_reclaim(space_info, fs_info))
+	if (btrfs_need_do_async_reclaim(space_info, fs_info, flush_state))
 		queue_work(system_unbound_wq, work);
 }
 
@@ -4502,7 +4513,13 @@ again:
 		space_info->flush = 1;
 	} else if (!ret && space_info->flags & BTRFS_BLOCK_GROUP_METADATA) {
 		used += orig_bytes;
-		if (need_do_async_reclaim(space_info, root->fs_info, used) &&
+		/*
+		 * We will do the space reservation dance during log replay,
+		 * which means we won't have fs_info->fs_root set, so don't do
+		 * the async reclaim as we will panic.
+		 */
+		if (!root->fs_info->log_root_recovering &&
+		    need_do_async_reclaim(space_info, root->fs_info, used) &&
 		    !work_busy(&root->fs_info->async_reclaim_work))
 			queue_work(system_unbound_wq,
 				   &root->fs_info->async_reclaim_work);
@@ -4839,7 +4856,7 @@ static u64 calc_global_metadata_size(struct btrfs_fs_info *fs_info)
 	if (num_bytes * 3 > meta_used)
 		num_bytes = div64_u64(meta_used, 3);
 
-	return ALIGN(num_bytes, fs_info->extent_root->leafsize << 10);
+	return ALIGN(num_bytes, fs_info->extent_root->nodesize << 10);
 }
 
 static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
@@ -4988,7 +5005,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 
 	if (root->fs_info->quota_enabled) {
 		/* One for parent inode, two for dir entries */
-		num_bytes = 3 * root->leafsize;
+		num_bytes = 3 * root->nodesize;
 		ret = btrfs_qgroup_reserve(root, num_bytes);
 		if (ret)
 			return ret;
@@ -5176,7 +5193,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 
 	if (root->fs_info->quota_enabled) {
 		ret = btrfs_qgroup_reserve(root, num_bytes +
-					   nr_extents * root->leafsize);
+					   nr_extents * root->nodesize);
 		if (ret)
 			goto out_fail;
 	}
@@ -5185,7 +5202,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	if (unlikely(ret)) {
 		if (root->fs_info->quota_enabled)
 			btrfs_qgroup_free(root, num_bytes +
-						nr_extents * root->leafsize);
+						nr_extents * root->nodesize);
 		goto out_fail;
 	}
 
@@ -5301,7 +5318,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
 				      btrfs_ino(inode), to_free, 0);
 	if (root->fs_info->quota_enabled) {
 		btrfs_qgroup_free(root, num_bytes +
-					dropped * root->leafsize);
+					dropped * root->nodesize);
 	}
 
 	btrfs_block_rsv_release(root, &root->fs_info->delalloc_block_rsv,
@@ -5422,6 +5439,20 @@ static int update_block_group(struct btrfs_root *root,
 			spin_unlock(&cache->space_info->lock);
 		} else {
 			old_val -= num_bytes;
+
+			/*
+			 * No longer have used bytes in this block group, queue
+			 * it for deletion.
+			 */
+			if (old_val == 0) {
+				spin_lock(&info->unused_bgs_lock);
+				if (list_empty(&cache->bg_list)) {
+					btrfs_get_block_group(cache);
+					list_add_tail(&cache->bg_list,
+						      &info->unused_bgs);
+				}
+				spin_unlock(&info->unused_bgs_lock);
+			}
 			btrfs_set_block_group_used(&cache->item, old_val);
 			cache->pinned += num_bytes;
 			cache->space_info->bytes_pinned += num_bytes;
@@ -6233,10 +6264,9 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	int ret;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+	if (btrfs_test_is_dummy_root(root))
 		return 0;
-#endif
+
 	add_pinned_bytes(root->fs_info, num_bytes, owner, root_objectid);
 
 	/*
@@ -6263,14 +6293,6 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	return ret;
 }
 
-static u64 stripe_align(struct btrfs_root *root,
-			struct btrfs_block_group_cache *cache,
-			u64 val, u64 num_bytes)
-{
-	u64 ret = ALIGN(val, root->stripesize);
-	return ret;
-}
-
 /*
  * when we wait for progress in the block group caching, its because
  * our allocation attempt failed at least once.  So, we must sleep
@@ -6464,7 +6486,7 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
 	bool have_caching_bg = false;
 
 	WARN_ON(num_bytes < root->sectorsize);
-	btrfs_set_key_type(ins, BTRFS_EXTENT_ITEM_KEY);
+	ins->type = BTRFS_EXTENT_ITEM_KEY;
 	ins->objectid = 0;
 	ins->offset = 0;
 
@@ -6751,8 +6773,7 @@ unclustered_alloc:
 			goto loop;
 		}
 checks:
-		search_start = stripe_align(root, block_group,
-					    offset, num_bytes);
+		search_start = ALIGN(offset, root->stripesize);
 
 		/* move on to the next group */
 		if (search_start + num_bytes >
@@ -7077,7 +7098,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path) {
 		btrfs_free_and_pin_reserved_extent(root, ins->objectid,
-						   root->leafsize);
+						   root->nodesize);
 		return -ENOMEM;
 	}
 
@@ -7086,7 +7107,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 				      ins, size);
 	if (ret) {
 		btrfs_free_and_pin_reserved_extent(root, ins->objectid,
-						   root->leafsize);
+						   root->nodesize);
 		btrfs_free_path(path);
 		return ret;
 	}
@@ -7101,7 +7122,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 
 	if (skinny_metadata) {
 		iref = (struct btrfs_extent_inline_ref *)(extent_item + 1);
-		num_bytes = root->leafsize;
+		num_bytes = root->nodesize;
 	} else {
 		block_info = (struct btrfs_tree_block_info *)(extent_item + 1);
 		btrfs_set_tree_block_key(leaf, block_info, key);
@@ -7131,14 +7152,14 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 			return ret;
 	}
 
-	ret = update_block_group(root, ins->objectid, root->leafsize, 1);
+	ret = update_block_group(root, ins->objectid, root->nodesize, 1);
 	if (ret) { /* -ENOENT, logic error */
 		btrfs_err(fs_info, "update block group failed for %llu %llu",
 			ins->objectid, ins->offset);
 		BUG();
 	}
 
-	trace_btrfs_reserved_extent_alloc(root, ins->objectid, root->leafsize);
+	trace_btrfs_reserved_extent_alloc(root, ins->objectid, root->nodesize);
 	return ret;
 }
 
@@ -7213,17 +7234,19 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	btrfs_set_buffer_uptodate(buf);
 
 	if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
+		buf->log_index = root->log_transid % 2;
 		/*
 		 * we allow two log transactions at a time, use different
 		 * EXENT bit to differentiate dirty pages.
 		 */
-		if (root->log_transid % 2 == 0)
+		if (buf->log_index == 0)
 			set_extent_dirty(&root->dirty_log_pages, buf->start,
 					buf->start + buf->len - 1, GFP_NOFS);
 		else
 			set_extent_new(&root->dirty_log_pages, buf->start,
 					buf->start + buf->len - 1, GFP_NOFS);
 	} else {
+		buf->log_index = -1;
 		set_extent_dirty(&trans->transaction->dirty_pages, buf->start,
 			 buf->start + buf->len - 1, GFP_NOFS);
 	}
@@ -7300,8 +7323,8 @@ static void unuse_block_rsv(struct btrfs_fs_info *fs_info,
  *
  * returns the tree buffer or NULL.
  */
-struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root, u32 blocksize,
+struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
+					struct btrfs_root *root,
 					u64 parent, u64 root_objectid,
 					struct btrfs_disk_key *key, int level,
 					u64 hint, u64 empty_size)
@@ -7311,18 +7334,18 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 	struct extent_buffer *buf;
 	u64 flags = 0;
 	int ret;
+	u32 blocksize = root->nodesize;
 	bool skinny_metadata = btrfs_fs_incompat(root->fs_info,
 						 SKINNY_METADATA);
 
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state))) {
+	if (btrfs_test_is_dummy_root(root)) {
 		buf = btrfs_init_new_buffer(trans, root, root->alloc_bytenr,
 					    blocksize, level);
 		if (!IS_ERR(buf))
 			root->alloc_bytenr += blocksize;
 		return buf;
 	}
-#endif
+
 	block_rsv = use_block_rsv(trans, root, blocksize);
 	if (IS_ERR(block_rsv))
 		return ERR_CAST(block_rsv);
@@ -7417,7 +7440,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
 
 	eb = path->nodes[wc->level];
 	nritems = btrfs_header_nritems(eb);
-	blocksize = btrfs_level_size(root, wc->level - 1);
+	blocksize = root->nodesize;
 
 	for (slot = path->slots[wc->level]; slot < nritems; slot++) {
 		if (nread >= wc->reada_count)
@@ -7464,10 +7487,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
 				continue;
 		}
 reada:
-		ret = readahead_tree_block(root, bytenr, blocksize,
-					   generation);
-		if (ret)
-			break;
+		readahead_tree_block(root, bytenr, blocksize);
 		nread++;
 	}
 	wc->reada_slot = slot;
@@ -7626,7 +7646,6 @@ walk_down:
 	level = root_level;
 	while (level >= 0) {
 		if (path->nodes[level] == NULL) {
-			int child_bsize = root->nodesize;
 			int parent_slot;
 			u64 child_gen;
 			u64 child_bytenr;
@@ -7638,8 +7657,7 @@ walk_down:
 			child_bytenr = btrfs_node_blockptr(eb, parent_slot);
 			child_gen = btrfs_node_ptr_generation(eb, parent_slot);
 
-			eb = read_tree_block(root, child_bytenr, child_bsize,
-					     child_gen);
+			eb = read_tree_block(root, child_bytenr, child_gen);
 			if (!eb || !extent_buffer_uptodate(eb)) {
 				ret = -EIO;
 				goto out;
@@ -7655,7 +7673,7 @@ walk_down:
 			ret = btrfs_qgroup_record_ref(trans, root->fs_info,
 						root->objectid,
 						child_bytenr,
-						child_bsize,
+						root->nodesize,
 						BTRFS_QGROUP_OPER_SUB_SUBTREE,
 						0);
 			if (ret)
@@ -7806,9 +7824,9 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	}
 
 	bytenr = btrfs_node_blockptr(path->nodes[level], path->slots[level]);
-	blocksize = btrfs_level_size(root, level - 1);
+	blocksize = root->nodesize;
 
-	next = btrfs_find_tree_block(root, bytenr, blocksize);
+	next = btrfs_find_tree_block(root, bytenr);
 	if (!next) {
 		next = btrfs_find_create_tree_block(root, bytenr, blocksize);
 		if (!next)
@@ -7870,7 +7888,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	if (!next) {
 		if (reada && level == 1)
 			reada_walk_down(trans, root, wc, path);
-		next = read_tree_block(root, bytenr, blocksize, generation);
+		next = read_tree_block(root, bytenr, generation);
 		if (!next || !extent_buffer_uptodate(next)) {
 			free_extent_buffer(next);
 			return -EIO;
@@ -8853,6 +8871,16 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 	}
 	up_write(&info->commit_root_sem);
 
+	spin_lock(&info->unused_bgs_lock);
+	while (!list_empty(&info->unused_bgs)) {
+		block_group = list_first_entry(&info->unused_bgs,
+					       struct btrfs_block_group_cache,
+					       bg_list);
+		list_del_init(&block_group->bg_list);
+		btrfs_put_block_group(block_group);
+	}
+	spin_unlock(&info->unused_bgs_lock);
+
 	spin_lock(&info->block_group_cache_lock);
 	while ((n = rb_last(&info->block_group_cache_tree)) != NULL) {
 		block_group = rb_entry(n, struct btrfs_block_group_cache,
@@ -8987,7 +9015,7 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size)
 	init_rwsem(&cache->data_rwsem);
 	INIT_LIST_HEAD(&cache->list);
 	INIT_LIST_HEAD(&cache->cluster_list);
-	INIT_LIST_HEAD(&cache->new_bg_list);
+	INIT_LIST_HEAD(&cache->bg_list);
 	btrfs_init_free_space_ctl(cache);
 
 	return cache;
@@ -9009,7 +9037,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 	root = info->extent_root;
 	key.objectid = 0;
 	key.offset = 0;
-	btrfs_set_key_type(&key, BTRFS_BLOCK_GROUP_ITEM_KEY);
+	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -9128,8 +9156,18 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 		__link_block_group(space_info, cache);
 
 		set_avail_alloc_bits(root->fs_info, cache->flags);
-		if (btrfs_chunk_readonly(root, cache->key.objectid))
+		if (btrfs_chunk_readonly(root, cache->key.objectid)) {
 			set_block_group_ro(cache, 1);
+		} else if (btrfs_block_group_used(&cache->item) == 0) {
+			spin_lock(&info->unused_bgs_lock);
+			/* Should always be true but just in case. */
+			if (list_empty(&cache->bg_list)) {
+				btrfs_get_block_group(cache);
+				list_add_tail(&cache->bg_list,
+					      &info->unused_bgs);
+			}
+			spin_unlock(&info->unused_bgs_lock);
+		}
 	}
 
 	list_for_each_entry_rcu(space_info, &root->fs_info->space_info, list) {
@@ -9170,10 +9208,8 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	int ret = 0;
 
-	list_for_each_entry_safe(block_group, tmp, &trans->new_bgs,
-				 new_bg_list) {
-		list_del_init(&block_group->new_bg_list);
-
+	list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
+		list_del_init(&block_group->bg_list);
 		if (ret)
 			continue;
 
@@ -9259,7 +9295,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 
 	__link_block_group(cache->space_info, cache);
 
-	list_add_tail(&cache->new_bg_list, &trans->new_bgs);
+	list_add_tail(&cache->bg_list, &trans->new_bgs);
 
 	set_avail_alloc_bits(extent_root->fs_info, type);
 
@@ -9413,8 +9449,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	memcpy(&key, &block_group->key, sizeof(key));
 
-	btrfs_clear_space_info_full(root->fs_info);
-
 	btrfs_put_block_group(block_group);
 	btrfs_put_block_group(block_group);
 
@@ -9430,6 +9464,101 @@ out:
 	return ret;
 }
 
+/*
+ * Process the unused_bgs list and remove any that don't have any allocated
+ * space inside of them.
+ */
+void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_block_group_cache *block_group;
+	struct btrfs_space_info *space_info;
+	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_trans_handle *trans;
+	int ret = 0;
+
+	if (!fs_info->open)
+		return;
+
+	spin_lock(&fs_info->unused_bgs_lock);
+	while (!list_empty(&fs_info->unused_bgs)) {
+		u64 start, end;
+
+		block_group = list_first_entry(&fs_info->unused_bgs,
+					       struct btrfs_block_group_cache,
+					       bg_list);
+		space_info = block_group->space_info;
+		list_del_init(&block_group->bg_list);
+		if (ret || btrfs_mixed_space_info(space_info)) {
+			btrfs_put_block_group(block_group);
+			continue;
+		}
+		spin_unlock(&fs_info->unused_bgs_lock);
+
+		/* Don't want to race with allocators so take the groups_sem */
+		down_write(&space_info->groups_sem);
+		spin_lock(&block_group->lock);
+		if (block_group->reserved ||
+		    btrfs_block_group_used(&block_group->item) ||
+		    block_group->ro) {
+			/*
+			 * We want to bail if we made new allocations or have
+			 * outstanding allocations in this block group.  We do
+			 * the ro check in case balance is currently acting on
+			 * this block group.
+			 */
+			spin_unlock(&block_group->lock);
+			up_write(&space_info->groups_sem);
+			goto next;
+		}
+		spin_unlock(&block_group->lock);
+
+		/* We don't want to force the issue, only flip if it's ok. */
+		ret = set_block_group_ro(block_group, 0);
+		up_write(&space_info->groups_sem);
+		if (ret < 0) {
+			ret = 0;
+			goto next;
+		}
+
+		/*
+		 * Want to do this before we do anything else so we can recover
+		 * properly if we fail to join the transaction.
+		 */
+		trans = btrfs_join_transaction(root);
+		if (IS_ERR(trans)) {
+			btrfs_set_block_group_rw(root, block_group);
+			ret = PTR_ERR(trans);
+			goto next;
+		}
+
+		/*
+		 * We could have pending pinned extents for this block group,
+		 * just delete them, we don't care about them anymore.
+		 */
+		start = block_group->key.objectid;
+		end = start + block_group->key.offset - 1;
+		clear_extent_bits(&fs_info->freed_extents[0], start, end,
+				  EXTENT_DIRTY, GFP_NOFS);
+		clear_extent_bits(&fs_info->freed_extents[1], start, end,
+				  EXTENT_DIRTY, GFP_NOFS);
+
+		/* Reset pinned so btrfs_put_block_group doesn't complain */
+		block_group->pinned = 0;
+
+		/*
+		 * Btrfs_remove_chunk will abort the transaction if things go
+		 * horribly wrong.
+		 */
+		ret = btrfs_remove_chunk(trans, root,
+					 block_group->key.objectid);
+		btrfs_end_transaction(trans, root);
+next:
+		btrfs_put_block_group(block_group);
+		spin_lock(&fs_info->unused_bgs_lock);
+	}
+	spin_unlock(&fs_info->unused_bgs_lock);
+}
+
 int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_space_info *space_info;
@@ -9561,7 +9690,7 @@ void btrfs_end_nocow_write(struct btrfs_root *root)
 
 int btrfs_start_nocow_write(struct btrfs_root *root)
 {
-	if (unlikely(atomic_read(&root->will_be_snapshoted)))
+	if (atomic_read(&root->will_be_snapshoted))
 		return 0;
 
 	percpu_counter_inc(&root->subv_writers->counter);
@@ -9569,7 +9698,7 @@ int btrfs_start_nocow_write(struct btrfs_root *root)
 	 * Make sure counter is updated before we check for snapshot creation.
 	 */
 	smp_mb();
-	if (unlikely(atomic_read(&root->will_be_snapshoted))) {
+	if (atomic_read(&root->will_be_snapshoted)) {
 		btrfs_end_nocow_write(root);
 		return 0;
 	}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index af0359dcf337..bf3f424e0013 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -25,6 +25,11 @@ static struct kmem_cache *extent_state_cache;
 static struct kmem_cache *extent_buffer_cache;
 static struct bio_set *btrfs_bioset;
 
+static inline bool extent_state_in_tree(const struct extent_state *state)
+{
+	return !RB_EMPTY_NODE(&state->rb_node);
+}
+
 #ifdef CONFIG_BTRFS_DEBUG
 static LIST_HEAD(buffers);
 static LIST_HEAD(states);
@@ -59,9 +64,9 @@ void btrfs_leak_debug_check(void)
 
 	while (!list_empty(&states)) {
 		state = list_entry(states.next, struct extent_state, leak_list);
-		printk(KERN_ERR "BTRFS: state leak: start %llu end %llu "
-		       "state %lu in tree %p refs %d\n",
-		       state->start, state->end, state->state, state->tree,
+		pr_err("BTRFS: state leak: start %llu end %llu state %lu in tree %d refs %d\n",
+		       state->start, state->end, state->state,
+		       extent_state_in_tree(state),
 		       atomic_read(&state->refs));
 		list_del(&state->leak_list);
 		kmem_cache_free(extent_state_cache, state);
@@ -209,7 +214,7 @@ static struct extent_state *alloc_extent_state(gfp_t mask)
 		return state;
 	state->state = 0;
 	state->private = 0;
-	state->tree = NULL;
+	RB_CLEAR_NODE(&state->rb_node);
 	btrfs_leak_debug_add(&state->leak_list, &states);
 	atomic_set(&state->refs, 1);
 	init_waitqueue_head(&state->wq);
@@ -222,7 +227,7 @@ void free_extent_state(struct extent_state *state)
 	if (!state)
 		return;
 	if (atomic_dec_and_test(&state->refs)) {
-		WARN_ON(state->tree);
+		WARN_ON(extent_state_in_tree(state));
 		btrfs_leak_debug_del(&state->leak_list);
 		trace_free_extent_state(state, _RET_IP_);
 		kmem_cache_free(extent_state_cache, state);
@@ -371,8 +376,8 @@ static void merge_state(struct extent_io_tree *tree,
 		    other->state == state->state) {
 			merge_cb(tree, state, other);
 			state->start = other->start;
-			other->tree = NULL;
 			rb_erase(&other->rb_node, &tree->state);
+			RB_CLEAR_NODE(&other->rb_node);
 			free_extent_state(other);
 		}
 	}
@@ -383,8 +388,8 @@ static void merge_state(struct extent_io_tree *tree,
 		    other->state == state->state) {
 			merge_cb(tree, state, other);
 			state->end = other->end;
-			other->tree = NULL;
 			rb_erase(&other->rb_node, &tree->state);
+			RB_CLEAR_NODE(&other->rb_node);
 			free_extent_state(other);
 		}
 	}
@@ -442,7 +447,6 @@ static int insert_state(struct extent_io_tree *tree,
 		       found->start, found->end, start, end);
 		return -EEXIST;
 	}
-	state->tree = tree;
 	merge_state(tree, state);
 	return 0;
 }
@@ -486,7 +490,6 @@ static int split_state(struct extent_io_tree *tree, struct extent_state *orig,
 		free_extent_state(prealloc);
 		return -EEXIST;
 	}
-	prealloc->tree = tree;
 	return 0;
 }
 
@@ -524,9 +527,9 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
 		wake_up(&state->wq);
 	if (state->state == 0) {
 		next = next_state(state);
-		if (state->tree) {
+		if (extent_state_in_tree(state)) {
 			rb_erase(&state->rb_node, &tree->state);
-			state->tree = NULL;
+			RB_CLEAR_NODE(&state->rb_node);
 			free_extent_state(state);
 		} else {
 			WARN_ON(1);
@@ -606,8 +609,8 @@ again:
 			cached_state = NULL;
 		}
 
-		if (cached && cached->tree && cached->start <= start &&
-		    cached->end > start) {
+		if (cached && extent_state_in_tree(cached) &&
+		    cached->start <= start && cached->end > start) {
 			if (clear)
 				atomic_dec(&cached->refs);
 			state = cached;
@@ -843,7 +846,7 @@ again:
 	if (cached_state && *cached_state) {
 		state = *cached_state;
 		if (state->start <= start && state->end > start &&
-		    state->tree) {
+		    extent_state_in_tree(state)) {
 			node = &state->rb_node;
 			goto hit_next;
 		}
@@ -1069,7 +1072,7 @@ again:
 	if (cached_state && *cached_state) {
 		state = *cached_state;
 		if (state->start <= start && state->end > start &&
-		    state->tree) {
+		    extent_state_in_tree(state)) {
 			node = &state->rb_node;
 			goto hit_next;
 		}
@@ -1459,7 +1462,7 @@ int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
 	spin_lock(&tree->lock);
 	if (cached_state && *cached_state) {
 		state = *cached_state;
-		if (state->end == start - 1 && state->tree) {
+		if (state->end == start - 1 && extent_state_in_tree(state)) {
 			n = rb_next(&state->rb_node);
 			while (n) {
 				state = rb_entry(n, struct extent_state,
@@ -1905,7 +1908,7 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	int bitset = 0;
 
 	spin_lock(&tree->lock);
-	if (cached && cached->tree && cached->start <= start &&
+	if (cached && extent_state_in_tree(cached) && cached->start <= start &&
 	    cached->end > start)
 		node = &cached->rb_node;
 	else
@@ -1959,27 +1962,7 @@ static void check_page_uptodate(struct extent_io_tree *tree, struct page *page)
 		SetPageUptodate(page);
 }
 
-/*
- * When IO fails, either with EIO or csum verification fails, we
- * try other mirrors that might have a good copy of the data.  This
- * io_failure_record is used to record state as we go through all the
- * mirrors.  If another mirror has good data, the page is set up to date
- * and things continue.  If a good mirror can't be found, the original
- * bio end_io callback is called to indicate things have failed.
- */
-struct io_failure_record {
-	struct page *page;
-	u64 start;
-	u64 len;
-	u64 logical;
-	unsigned long bio_flags;
-	int this_mirror;
-	int failed_mirror;
-	int in_validation;
-};
-
-static int free_io_failure(struct inode *inode, struct io_failure_record *rec,
-				int did_repair)
+int free_io_failure(struct inode *inode, struct io_failure_record *rec)
 {
 	int ret;
 	int err = 0;
@@ -2012,10 +1995,10 @@ static int free_io_failure(struct inode *inode, struct io_failure_record *rec,
  * currently, there can be no more than two copies of every data bit. thus,
  * exactly one rewrite is required.
  */
-int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
-			u64 length, u64 logical, struct page *page,
-			int mirror_num)
+int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
+		      struct page *page, unsigned int pg_offset, int mirror_num)
 {
+	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	struct bio *bio;
 	struct btrfs_device *dev;
 	u64 map_length = 0;
@@ -2053,7 +2036,7 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
 		return -EIO;
 	}
 	bio->bi_bdev = dev->bdev;
-	bio_add_page(bio, page, length, start - page_offset(page));
+	bio_add_page(bio, page, length, pg_offset);
 
 	if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) {
 		/* try to remap that extent elsewhere? */
@@ -2063,10 +2046,9 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
 	}
 
 	printk_ratelimited_in_rcu(KERN_INFO
-			"BTRFS: read error corrected: ino %lu off %llu "
-		    "(dev %s sector %llu)\n", page->mapping->host->i_ino,
-		    start, rcu_str_deref(dev->name), sector);
-
+				  "BTRFS: read error corrected: ino %llu off %llu (dev %s sector %llu)\n",
+				  btrfs_ino(inode), start,
+				  rcu_str_deref(dev->name), sector);
 	bio_put(bio);
 	return 0;
 }
@@ -2082,9 +2064,11 @@ int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
 		return -EROFS;
 
 	for (i = 0; i < num_pages; i++) {
-		struct page *p = extent_buffer_page(eb, i);
-		ret = repair_io_failure(root->fs_info, start, PAGE_CACHE_SIZE,
-					start, p, mirror_num);
+		struct page *p = eb->pages[i];
+
+		ret = repair_io_failure(root->fs_info->btree_inode, start,
+					PAGE_CACHE_SIZE, start, p,
+					start - page_offset(p), mirror_num);
 		if (ret)
 			break;
 		start += PAGE_CACHE_SIZE;
@@ -2097,16 +2081,15 @@ int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
  * each time an IO finishes, we do a fast check in the IO failure tree
  * to see if we need to process or clean up an io_failure_record
  */
-static int clean_io_failure(u64 start, struct page *page)
+int clean_io_failure(struct inode *inode, u64 start, struct page *page,
+		     unsigned int pg_offset)
 {
 	u64 private;
 	u64 private_failure;
 	struct io_failure_record *failrec;
-	struct inode *inode = page->mapping->host;
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	struct extent_state *state;
 	int num_copies;
-	int did_repair = 0;
 	int ret;
 
 	private = 0;
@@ -2127,7 +2110,6 @@ static int clean_io_failure(u64 start, struct page *page)
 		/* there was no real error, just free the record */
 		pr_debug("clean_io_failure: freeing dummy error at %llu\n",
 			 failrec->start);
-		did_repair = 1;
 		goto out;
 	}
 	if (fs_info->sb->s_flags & MS_RDONLY)
@@ -2144,55 +2126,70 @@ static int clean_io_failure(u64 start, struct page *page)
 		num_copies = btrfs_num_copies(fs_info, failrec->logical,
 					      failrec->len);
 		if (num_copies > 1)  {
-			ret = repair_io_failure(fs_info, start, failrec->len,
-						failrec->logical, page,
-						failrec->failed_mirror);
-			did_repair = !ret;
+			repair_io_failure(inode, start, failrec->len,
+					  failrec->logical, page,
+					  pg_offset, failrec->failed_mirror);
 		}
-		ret = 0;
 	}
 
 out:
-	if (!ret)
-		ret = free_io_failure(inode, failrec, did_repair);
+	free_io_failure(inode, failrec);
 
-	return ret;
+	return 0;
 }
 
 /*
- * this is a generic handler for readpage errors (default
- * readpage_io_failed_hook). if other copies exist, read those and write back
- * good data to the failed position. does not investigate in remapping the
- * failed extent elsewhere, hoping the device will be smart enough to do this as
- * needed
+ * Can be called when
+ * - hold extent lock
+ * - under ordered extent
+ * - the inode is freeing
  */
+void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end)
+{
+	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
+	struct io_failure_record *failrec;
+	struct extent_state *state, *next;
 
-static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
-			      struct page *page, u64 start, u64 end,
-			      int failed_mirror)
+	if (RB_EMPTY_ROOT(&failure_tree->state))
+		return;
+
+	spin_lock(&failure_tree->lock);
+	state = find_first_extent_bit_state(failure_tree, start, EXTENT_DIRTY);
+	while (state) {
+		if (state->start > end)
+			break;
+
+		ASSERT(state->end <= end);
+
+		next = next_state(state);
+
+		failrec = (struct io_failure_record *)state->private;
+		free_extent_state(state);
+		kfree(failrec);
+
+		state = next;
+	}
+	spin_unlock(&failure_tree->lock);
+}
+
+int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
+				struct io_failure_record **failrec_ret)
 {
-	struct io_failure_record *failrec = NULL;
+	struct io_failure_record *failrec;
 	u64 private;
 	struct extent_map *em;
-	struct inode *inode = page->mapping->host;
 	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
-	struct bio *bio;
-	struct btrfs_io_bio *btrfs_failed_bio;
-	struct btrfs_io_bio *btrfs_bio;
-	int num_copies;
 	int ret;
-	int read_mode;
 	u64 logical;
 
-	BUG_ON(failed_bio->bi_rw & REQ_WRITE);
-
 	ret = get_state_private(failure_tree, start, &private);
 	if (ret) {
 		failrec = kzalloc(sizeof(*failrec), GFP_NOFS);
 		if (!failrec)
 			return -ENOMEM;
+
 		failrec->start = start;
 		failrec->len = end - start + 1;
 		failrec->this_mirror = 0;
@@ -2212,11 +2209,11 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 			em = NULL;
 		}
 		read_unlock(&em_tree->lock);
-
 		if (!em) {
 			kfree(failrec);
 			return -EIO;
 		}
+
 		logical = start - em->start;
 		logical = em->block_start + logical;
 		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
@@ -2225,8 +2222,10 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 			extent_set_compress_type(&failrec->bio_flags,
 						 em->compress_type);
 		}
-		pr_debug("bio_readpage_error: (new) logical=%llu, start=%llu, "
-			 "len=%llu\n", logical, start, failrec->len);
+
+		pr_debug("Get IO Failure Record: (new) logical=%llu, start=%llu, len=%llu\n",
+			 logical, start, failrec->len);
+
 		failrec->logical = logical;
 		free_extent_map(em);
 
@@ -2246,8 +2245,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 		}
 	} else {
 		failrec = (struct io_failure_record *)(unsigned long)private;
-		pr_debug("bio_readpage_error: (found) logical=%llu, "
-			 "start=%llu, len=%llu, validation=%d\n",
+		pr_debug("Get IO Failure Record: (found) logical=%llu, start=%llu, len=%llu, validation=%d\n",
 			 failrec->logical, failrec->start, failrec->len,
 			 failrec->in_validation);
 		/*
@@ -2256,6 +2254,17 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 		 * clean_io_failure() clean all those errors at once.
 		 */
 	}
+
+	*failrec_ret = failrec;
+
+	return 0;
+}
+
+int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
+			   struct io_failure_record *failrec, int failed_mirror)
+{
+	int num_copies;
+
 	num_copies = btrfs_num_copies(BTRFS_I(inode)->root->fs_info,
 				      failrec->logical, failrec->len);
 	if (num_copies == 1) {
@@ -2264,10 +2273,9 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 		 * all the retry and error correction code that follows. no
 		 * matter what the error is, it is very likely to persist.
 		 */
-		pr_debug("bio_readpage_error: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d\n",
+		pr_debug("Check Repairable: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d\n",
 			 num_copies, failrec->this_mirror, failed_mirror);
-		free_io_failure(inode, failrec, 0);
-		return -EIO;
+		return 0;
 	}
 
 	/*
@@ -2287,7 +2295,6 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 		BUG_ON(failrec->in_validation);
 		failrec->in_validation = 1;
 		failrec->this_mirror = failed_mirror;
-		read_mode = READ_SYNC | REQ_FAILFAST_DEV;
 	} else {
 		/*
 		 * we're ready to fulfill a) and b) alongside. get a good copy
@@ -2303,25 +2310,36 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 		failrec->this_mirror++;
 		if (failrec->this_mirror == failed_mirror)
 			failrec->this_mirror++;
-		read_mode = READ_SYNC;
 	}
 
 	if (failrec->this_mirror > num_copies) {
-		pr_debug("bio_readpage_error: (fail) num_copies=%d, next_mirror %d, failed_mirror %d\n",
+		pr_debug("Check Repairable: (fail) num_copies=%d, next_mirror %d, failed_mirror %d\n",
 			 num_copies, failrec->this_mirror, failed_mirror);
-		free_io_failure(inode, failrec, 0);
-		return -EIO;
+		return 0;
 	}
 
+	return 1;
+}
+
+
+struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
+				    struct io_failure_record *failrec,
+				    struct page *page, int pg_offset, int icsum,
+				    bio_end_io_t *endio_func, void *data)
+{
+	struct bio *bio;
+	struct btrfs_io_bio *btrfs_failed_bio;
+	struct btrfs_io_bio *btrfs_bio;
+
 	bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
-	if (!bio) {
-		free_io_failure(inode, failrec, 0);
-		return -EIO;
-	}
-	bio->bi_end_io = failed_bio->bi_end_io;
+	if (!bio)
+		return NULL;
+
+	bio->bi_end_io = endio_func;
 	bio->bi_iter.bi_sector = failrec->logical >> 9;
 	bio->bi_bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
 	bio->bi_iter.bi_size = 0;
+	bio->bi_private = data;
 
 	btrfs_failed_bio = btrfs_io_bio(failed_bio);
 	if (btrfs_failed_bio->csum) {
@@ -2330,21 +2348,73 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 
 		btrfs_bio = btrfs_io_bio(bio);
 		btrfs_bio->csum = btrfs_bio->csum_inline;
-		phy_offset >>= inode->i_sb->s_blocksize_bits;
-		phy_offset *= csum_size;
-		memcpy(btrfs_bio->csum, btrfs_failed_bio->csum + phy_offset,
+		icsum *= csum_size;
+		memcpy(btrfs_bio->csum, btrfs_failed_bio->csum + icsum,
 		       csum_size);
 	}
 
-	bio_add_page(bio, page, failrec->len, start - page_offset(page));
+	bio_add_page(bio, page, failrec->len, pg_offset);
+
+	return bio;
+}
+
+/*
+ * this is a generic handler for readpage errors (default
+ * readpage_io_failed_hook). if other copies exist, read those and write back
+ * good data to the failed position. does not investigate in remapping the
+ * failed extent elsewhere, hoping the device will be smart enough to do this as
+ * needed
+ */
+
+static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
+			      struct page *page, u64 start, u64 end,
+			      int failed_mirror)
+{
+	struct io_failure_record *failrec;
+	struct inode *inode = page->mapping->host;
+	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
+	struct bio *bio;
+	int read_mode;
+	int ret;
+
+	BUG_ON(failed_bio->bi_rw & REQ_WRITE);
+
+	ret = btrfs_get_io_failure_record(inode, start, end, &failrec);
+	if (ret)
+		return ret;
+
+	ret = btrfs_check_repairable(inode, failed_bio, failrec, failed_mirror);
+	if (!ret) {
+		free_io_failure(inode, failrec);
+		return -EIO;
+	}
+
+	if (failed_bio->bi_vcnt > 1)
+		read_mode = READ_SYNC | REQ_FAILFAST_DEV;
+	else
+		read_mode = READ_SYNC;
+
+	phy_offset >>= inode->i_sb->s_blocksize_bits;
+	bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
+				      start - page_offset(page),
+				      (int)phy_offset, failed_bio->bi_end_io,
+				      NULL);
+	if (!bio) {
+		free_io_failure(inode, failrec);
+		return -EIO;
+	}
 
-	pr_debug("bio_readpage_error: submitting new read[%#x] to "
-		 "this_mirror=%d, num_copies=%d, in_validation=%d\n", read_mode,
-		 failrec->this_mirror, num_copies, failrec->in_validation);
+	pr_debug("Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d\n",
+		 read_mode, failrec->this_mirror, failrec->in_validation);
 
 	ret = tree->ops->submit_bio_hook(inode, read_mode, bio,
 					 failrec->this_mirror,
 					 failrec->bio_flags, 0);
+	if (ret) {
+		free_io_failure(inode, failrec);
+		bio_put(bio);
+	}
+
 	return ret;
 }
 
@@ -2469,7 +2539,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 		struct inode *inode = page->mapping->host;
 
 		pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
-			 "mirror=%lu\n", (u64)bio->bi_iter.bi_sector, err,
+			 "mirror=%u\n", (u64)bio->bi_iter.bi_sector, err,
 			 io_bio->mirror_num);
 		tree = &BTRFS_I(inode)->io_tree;
 
@@ -2503,7 +2573,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 			if (ret)
 				uptodate = 0;
 			else
-				clean_io_failure(start, page);
+				clean_io_failure(inode, start, page, 0);
 		}
 
 		if (likely(uptodate))
@@ -2540,12 +2610,12 @@ readpage_ok:
 		if (likely(uptodate)) {
 			loff_t i_size = i_size_read(inode);
 			pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
-			unsigned offset;
+			unsigned off;
 
 			/* Zero out the end if this page straddles i_size */
-			offset = i_size & (PAGE_CACHE_SIZE-1);
-			if (page->index == end_index && offset)
-				zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+			off = i_size & (PAGE_CACHE_SIZE-1);
+			if (page->index == end_index && off)
+				zero_user_segment(page, off, PAGE_CACHE_SIZE);
 			SetPageUptodate(page);
 		} else {
 			ClearPageUptodate(page);
@@ -2618,9 +2688,18 @@ btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
 
 struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask)
 {
-	return bio_clone_bioset(bio, gfp_mask, btrfs_bioset);
-}
+	struct btrfs_io_bio *btrfs_bio;
+	struct bio *new;
 
+	new = bio_clone_bioset(bio, gfp_mask, btrfs_bioset);
+	if (new) {
+		btrfs_bio = btrfs_io_bio(new);
+		btrfs_bio->csum = NULL;
+		btrfs_bio->csum_allocated = NULL;
+		btrfs_bio->end_io = NULL;
+	}
+	return new;
+}
 
 /* this also allocates from the btrfs_bioset */
 struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
@@ -3501,7 +3580,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
 
 	num_pages = num_extent_pages(eb->start, eb->len);
 	for (i = 0; i < num_pages; i++) {
-		struct page *p = extent_buffer_page(eb, i);
+		struct page *p = eb->pages[i];
 
 		if (!trylock_page(p)) {
 			if (!flush) {
@@ -3522,6 +3601,68 @@ static void end_extent_buffer_writeback(struct extent_buffer *eb)
 	wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
 }
 
+static void set_btree_ioerr(struct page *page)
+{
+	struct extent_buffer *eb = (struct extent_buffer *)page->private;
+	struct btrfs_inode *btree_ino = BTRFS_I(eb->fs_info->btree_inode);
+
+	SetPageError(page);
+	if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))
+		return;
+
+	/*
+	 * If writeback for a btree extent that doesn't belong to a log tree
+	 * failed, increment the counter transaction->eb_write_errors.
+	 * We do this because while the transaction is running and before it's
+	 * committing (when we call filemap_fdata[write|wait]_range against
+	 * the btree inode), we might have
+	 * btree_inode->i_mapping->a_ops->writepages() called by the VM - if it
+	 * returns an error or an error happens during writeback, when we're
+	 * committing the transaction we wouldn't know about it, since the pages
+	 * can be no longer dirty nor marked anymore for writeback (if a
+	 * subsequent modification to the extent buffer didn't happen before the
+	 * transaction commit), which makes filemap_fdata[write|wait]_range not
+	 * able to find the pages tagged with SetPageError at transaction
+	 * commit time. So if this happens we must abort the transaction,
+	 * otherwise we commit a super block with btree roots that point to
+	 * btree nodes/leafs whose content on disk is invalid - either garbage
+	 * or the content of some node/leaf from a past generation that got
+	 * cowed or deleted and is no longer valid.
+	 *
+	 * Note: setting AS_EIO/AS_ENOSPC in the btree inode's i_mapping would
+	 * not be enough - we need to distinguish between log tree extents vs
+	 * non-log tree extents, and the next filemap_fdatawait_range() call
+	 * will catch and clear such errors in the mapping - and that call might
+	 * be from a log sync and not from a transaction commit. Also, checking
+	 * for the eb flag EXTENT_BUFFER_WRITE_ERR at transaction commit time is
+	 * not done and would not be reliable - the eb might have been released
+	 * from memory and reading it back again means that flag would not be
+	 * set (since it's a runtime flag, not persisted on disk).
+	 *
+	 * Using the flags below in the btree inode also makes us achieve the
+	 * goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
+	 * writeback for all dirty pages and before filemap_fdatawait_range()
+	 * is called, the writeback for all dirty pages had already finished
+	 * with errors - because we were not using AS_EIO/AS_ENOSPC,
+	 * filemap_fdatawait_range() would return success, as it could not know
+	 * that writeback errors happened (the pages were no longer tagged for
+	 * writeback).
+	 */
+	switch (eb->log_index) {
+	case -1:
+		set_bit(BTRFS_INODE_BTREE_ERR, &btree_ino->runtime_flags);
+		break;
+	case 0:
+		set_bit(BTRFS_INODE_BTREE_LOG1_ERR, &btree_ino->runtime_flags);
+		break;
+	case 1:
+		set_bit(BTRFS_INODE_BTREE_LOG2_ERR, &btree_ino->runtime_flags);
+		break;
+	default:
+		BUG(); /* unexpected, logic error */
+	}
+}
+
 static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
 {
 	struct bio_vec *bvec;
@@ -3535,10 +3676,9 @@ static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
 		BUG_ON(!eb);
 		done = atomic_dec_and_test(&eb->io_pages);
 
-		if (err || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
-			set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+		if (err || test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
 			ClearPageUptodate(page);
-			SetPageError(page);
+			set_btree_ioerr(page);
 		}
 
 		end_page_writeback(page);
@@ -3565,14 +3705,14 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META;
 	int ret = 0;
 
-	clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+	clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
 	num_pages = num_extent_pages(eb->start, eb->len);
 	atomic_set(&eb->io_pages, num_pages);
 	if (btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID)
 		bio_flags = EXTENT_BIO_TREE_LOG;
 
 	for (i = 0; i < num_pages; i++) {
-		struct page *p = extent_buffer_page(eb, i);
+		struct page *p = eb->pages[i];
 
 		clear_page_dirty_for_io(p);
 		set_page_writeback(p);
@@ -3582,8 +3722,8 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 					 0, epd->bio_flags, bio_flags);
 		epd->bio_flags = bio_flags;
 		if (ret) {
-			set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
-			SetPageError(p);
+			set_btree_ioerr(p);
+			end_page_writeback(p);
 			if (atomic_sub_and_test(num_pages - i, &eb->io_pages))
 				end_extent_buffer_writeback(eb);
 			ret = -EIO;
@@ -3596,7 +3736,8 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 
 	if (unlikely(ret)) {
 		for (; i < num_pages; i++) {
-			struct page *p = extent_buffer_page(eb, i);
+			struct page *p = eb->pages[i];
+			clear_page_dirty_for_io(p);
 			unlock_page(p);
 		}
 	}
@@ -4166,19 +4307,6 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode,
 	return NULL;
 }
 
-static noinline int count_ext_ref(u64 inum, u64 offset, u64 root_id, void *ctx)
-{
-	unsigned long cnt = *((unsigned long *)ctx);
-
-	cnt++;
-	*((unsigned long *)ctx) = cnt;
-
-	/* Now we're sure that the extent is shared. */
-	if (cnt > 1)
-		return 1;
-	return 0;
-}
-
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len, get_extent_t *get_extent)
 {
@@ -4195,6 +4323,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	struct extent_map *em = NULL;
 	struct extent_state *cached_state = NULL;
 	struct btrfs_path *path;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int end = 0;
 	u64 em_start = 0;
 	u64 em_len = 0;
@@ -4215,8 +4344,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	 * lookup the last file extent.  We're not using i_size here
 	 * because there might be preallocation past i_size
 	 */
-	ret = btrfs_lookup_file_extent(NULL, BTRFS_I(inode)->root,
-				       path, btrfs_ino(inode), -1, 0);
+	ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(inode), -1,
+				       0);
 	if (ret < 0) {
 		btrfs_free_path(path);
 		return ret;
@@ -4224,7 +4353,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	WARN_ON(!ret);
 	path->slots[0]--;
 	btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
-	found_type = btrfs_key_type(&found_key);
+	found_type = found_key.type;
 
 	/* No extents, but there might be delalloc bits */
 	if (found_key.objectid != btrfs_ino(inode) ||
@@ -4309,25 +4438,27 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		} else if (em->block_start == EXTENT_MAP_DELALLOC) {
 			flags |= (FIEMAP_EXTENT_DELALLOC |
 				  FIEMAP_EXTENT_UNKNOWN);
-		} else {
-			unsigned long ref_cnt = 0;
+		} else if (fieinfo->fi_extents_max) {
+			u64 bytenr = em->block_start -
+				(em->start - em->orig_start);
 
 			disko = em->block_start + offset_in_extent;
 
 			/*
 			 * As btrfs supports shared space, this information
 			 * can be exported to userspace tools via
-			 * flag FIEMAP_EXTENT_SHARED.
+			 * flag FIEMAP_EXTENT_SHARED.  If fi_extents_max == 0
+			 * then we're just getting a count and we can skip the
+			 * lookup stuff.
 			 */
-			ret = iterate_inodes_from_logical(
-					em->block_start,
-					BTRFS_I(inode)->root->fs_info,
-					path, count_ext_ref, &ref_cnt);
-			if (ret < 0 && ret != -ENOENT)
+			ret = btrfs_check_shared(NULL, root->fs_info,
+						 root->objectid,
+						 btrfs_ino(inode), bytenr);
+			if (ret < 0)
 				goto out_free;
-
-			if (ref_cnt > 1)
+			if (ret)
 				flags |= FIEMAP_EXTENT_SHARED;
+			ret = 0;
 		}
 		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
 			flags |= FIEMAP_EXTENT_ENCODED;
@@ -4381,24 +4512,21 @@ int extent_buffer_under_io(struct extent_buffer *eb)
 /*
  * Helper for releasing extent buffer page.
  */
-static void btrfs_release_extent_buffer_page(struct extent_buffer *eb,
-						unsigned long start_idx)
+static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
 {
 	unsigned long index;
-	unsigned long num_pages;
 	struct page *page;
 	int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
 
 	BUG_ON(extent_buffer_under_io(eb));
 
-	num_pages = num_extent_pages(eb->start, eb->len);
-	index = start_idx + num_pages;
-	if (start_idx >= index)
+	index = num_extent_pages(eb->start, eb->len);
+	if (index == 0)
 		return;
 
 	do {
 		index--;
-		page = extent_buffer_page(eb, index);
+		page = eb->pages[index];
 		if (page && mapped) {
 			spin_lock(&page->mapping->private_lock);
 			/*
@@ -4429,7 +4557,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb,
 			/* One for when we alloced the page */
 			page_cache_release(page);
 		}
-	} while (index != start_idx);
+	} while (index != 0);
 }
 
 /*
@@ -4437,7 +4565,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb,
  */
 static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
 {
-	btrfs_release_extent_buffer_page(eb, 0);
+	btrfs_release_extent_buffer_page(eb);
 	__free_extent_buffer(eb);
 }
 
@@ -4580,7 +4708,8 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb,
 
 	num_pages = num_extent_pages(eb->start, eb->len);
 	for (i = 0; i < num_pages; i++) {
-		struct page *p = extent_buffer_page(eb, i);
+		struct page *p = eb->pages[i];
+
 		if (p != accessed)
 			mark_page_accessed(p);
 	}
@@ -4749,7 +4878,7 @@ again:
 	 */
 	SetPageChecked(eb->pages[0]);
 	for (i = 1; i < num_pages; i++) {
-		p = extent_buffer_page(eb, i);
+		p = eb->pages[i];
 		ClearPageChecked(p);
 		unlock_page(p);
 	}
@@ -4794,7 +4923,7 @@ static int release_extent_buffer(struct extent_buffer *eb)
 		}
 
 		/* Should be safe to release our pages at this point */
-		btrfs_release_extent_buffer_page(eb, 0);
+		btrfs_release_extent_buffer_page(eb);
 		call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
 		return 1;
 	}
@@ -4860,7 +4989,7 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
 	num_pages = num_extent_pages(eb->start, eb->len);
 
 	for (i = 0; i < num_pages; i++) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 		if (!PageDirty(page))
 			continue;
 
@@ -4896,7 +5025,7 @@ int set_extent_buffer_dirty(struct extent_buffer *eb)
 	WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
 
 	for (i = 0; i < num_pages; i++)
-		set_page_dirty(extent_buffer_page(eb, i));
+		set_page_dirty(eb->pages[i]);
 	return was_dirty;
 }
 
@@ -4909,7 +5038,7 @@ int clear_extent_buffer_uptodate(struct extent_buffer *eb)
 	clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 	num_pages = num_extent_pages(eb->start, eb->len);
 	for (i = 0; i < num_pages; i++) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 		if (page)
 			ClearPageUptodate(page);
 	}
@@ -4925,7 +5054,7 @@ int set_extent_buffer_uptodate(struct extent_buffer *eb)
 	set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 	num_pages = num_extent_pages(eb->start, eb->len);
 	for (i = 0; i < num_pages; i++) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 		SetPageUptodate(page);
 	}
 	return 0;
@@ -4965,7 +5094,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 
 	num_pages = num_extent_pages(eb->start, eb->len);
 	for (i = start_i; i < num_pages; i++) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 		if (wait == WAIT_NONE) {
 			if (!trylock_page(page))
 				goto unlock_exit;
@@ -4984,11 +5113,11 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 		goto unlock_exit;
 	}
 
-	clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+	clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = 0;
 	atomic_set(&eb->io_pages, num_reads);
 	for (i = start_i; i < num_pages; i++) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 		if (!PageUptodate(page)) {
 			ClearPageError(page);
 			err = __extent_read_full_page(tree, page,
@@ -5013,7 +5142,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 		return ret;
 
 	for (i = start_i; i < num_pages; i++) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 		wait_on_page_locked(page);
 		if (!PageUptodate(page))
 			ret = -EIO;
@@ -5024,7 +5153,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 unlock_exit:
 	i = start_i;
 	while (locked_pages > 0) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 		i++;
 		unlock_page(page);
 		locked_pages--;
@@ -5050,7 +5179,7 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv,
 	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
 
 	while (len > 0) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 
 		cur = min(len, (PAGE_CACHE_SIZE - offset));
 		kaddr = page_address(page);
@@ -5082,7 +5211,7 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
 	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
 
 	while (len > 0) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 
 		cur = min(len, (PAGE_CACHE_SIZE - offset));
 		kaddr = page_address(page);
@@ -5131,7 +5260,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 		return -EINVAL;
 	}
 
-	p = extent_buffer_page(eb, i);
+	p = eb->pages[i];
 	kaddr = page_address(p);
 	*map = kaddr + offset;
 	*map_len = PAGE_CACHE_SIZE - offset;
@@ -5157,7 +5286,7 @@ int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv,
 	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
 
 	while (len > 0) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 
 		cur = min(len, (PAGE_CACHE_SIZE - offset));
 
@@ -5191,7 +5320,7 @@ void write_extent_buffer(struct extent_buffer *eb, const void *srcv,
 	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
 
 	while (len > 0) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 		WARN_ON(!PageUptodate(page));
 
 		cur = min(len, PAGE_CACHE_SIZE - offset);
@@ -5221,7 +5350,7 @@ void memset_extent_buffer(struct extent_buffer *eb, char c,
 	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
 
 	while (len > 0) {
-		page = extent_buffer_page(eb, i);
+		page = eb->pages[i];
 		WARN_ON(!PageUptodate(page));
 
 		cur = min(len, PAGE_CACHE_SIZE - offset);
@@ -5252,7 +5381,7 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
 		(PAGE_CACHE_SIZE - 1);
 
 	while (len > 0) {
-		page = extent_buffer_page(dst, i);
+		page = dst->pages[i];
 		WARN_ON(!PageUptodate(page));
 
 		cur = min(len, (unsigned long)(PAGE_CACHE_SIZE - offset));
@@ -5330,8 +5459,7 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 		cur = min_t(unsigned long, cur,
 			(unsigned long)(PAGE_CACHE_SIZE - dst_off_in_page));
 
-		copy_pages(extent_buffer_page(dst, dst_i),
-			   extent_buffer_page(dst, src_i),
+		copy_pages(dst->pages[dst_i], dst->pages[src_i],
 			   dst_off_in_page, src_off_in_page, cur);
 
 		src_offset += cur;
@@ -5377,8 +5505,7 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 
 		cur = min_t(unsigned long, len, src_off_in_page + 1);
 		cur = min(cur, dst_off_in_page + 1);
-		copy_pages(extent_buffer_page(dst, dst_i),
-			   extent_buffer_page(dst, src_i),
+		copy_pages(dst->pages[dst_i], dst->pages[src_i],
 			   dst_off_in_page - cur + 1,
 			   src_off_in_page - cur + 1, cur);
 
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index ccc264e7bde1..6d4b938be986 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -11,8 +11,6 @@
 #define EXTENT_NEW (1 << 4)
 #define EXTENT_DELALLOC (1 << 5)
 #define EXTENT_DEFRAG (1 << 6)
-#define EXTENT_DEFRAG_DONE (1 << 7)
-#define EXTENT_BUFFER_FILLED (1 << 8)
 #define EXTENT_BOUNDARY (1 << 9)
 #define EXTENT_NODATASUM (1 << 10)
 #define EXTENT_DO_ACCOUNTING (1 << 11)
@@ -34,16 +32,16 @@
 
 /* these are bit numbers for test/set bit */
 #define EXTENT_BUFFER_UPTODATE 0
-#define EXTENT_BUFFER_BLOCKING 1
 #define EXTENT_BUFFER_DIRTY 2
 #define EXTENT_BUFFER_CORRUPT 3
 #define EXTENT_BUFFER_READAHEAD 4	/* this got triggered by readahead */
 #define EXTENT_BUFFER_TREE_REF 5
 #define EXTENT_BUFFER_STALE 6
 #define EXTENT_BUFFER_WRITEBACK 7
-#define EXTENT_BUFFER_IOERR 8
+#define EXTENT_BUFFER_READ_ERR 8        /* read IO error */
 #define EXTENT_BUFFER_DUMMY 9
 #define EXTENT_BUFFER_IN_TREE 10
+#define EXTENT_BUFFER_WRITE_ERR 11    /* write IO error */
 
 /* these are flags for extent_clear_unlock_delalloc */
 #define PAGE_UNLOCK		(1 << 0)
@@ -57,7 +55,6 @@
  * map has page->private set to one.
  */
 #define EXTENT_PAGE_PRIVATE 1
-#define EXTENT_PAGE_PRIVATE_FIRST_PAGE 3
 
 struct extent_state;
 struct btrfs_root;
@@ -108,7 +105,6 @@ struct extent_state {
 	struct rb_node rb_node;
 
 	/* ADD NEW ELEMENTS AFTER THIS */
-	struct extent_io_tree *tree;
 	wait_queue_head_t wq;
 	atomic_t refs;
 	unsigned long state;
@@ -126,8 +122,6 @@ struct extent_state {
 struct extent_buffer {
 	u64 start;
 	unsigned long len;
-	unsigned long map_start;
-	unsigned long map_len;
 	unsigned long bflags;
 	struct btrfs_fs_info *fs_info;
 	spinlock_t refs_lock;
@@ -144,7 +138,9 @@ struct extent_buffer {
 	atomic_t blocking_readers;
 	atomic_t spinning_readers;
 	atomic_t spinning_writers;
-	int lock_nested;
+	short lock_nested;
+	/* >= 0 if eb belongs to a log tree, -1 otherwise */
+	short log_index;
 
 	/* protects write locks */
 	rwlock_t lock;
@@ -286,12 +282,6 @@ static inline unsigned long num_extent_pages(u64 start, u64 len)
 		(start >> PAGE_CACHE_SHIFT);
 }
 
-static inline struct page *extent_buffer_page(struct extent_buffer *eb,
-					      unsigned long i)
-{
-	return eb->pages[i];
-}
-
 static inline void extent_buffer_get(struct extent_buffer *eb)
 {
 	atomic_inc(&eb->refs);
@@ -341,18 +331,50 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask);
 
 struct btrfs_fs_info;
 
-int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
-			u64 length, u64 logical, struct page *page,
-			int mirror_num);
+int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
+		      struct page *page, unsigned int pg_offset,
+		      int mirror_num);
+int clean_io_failure(struct inode *inode, u64 start, struct page *page,
+		     unsigned int pg_offset);
 int end_extent_writepage(struct page *page, int err, u64 start, u64 end);
 int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
 			 int mirror_num);
+
+/*
+ * When IO fails, either with EIO or csum verification fails, we
+ * try other mirrors that might have a good copy of the data.  This
+ * io_failure_record is used to record state as we go through all the
+ * mirrors.  If another mirror has good data, the page is set up to date
+ * and things continue.  If a good mirror can't be found, the original
+ * bio end_io callback is called to indicate things have failed.
+ */
+struct io_failure_record {
+	struct page *page;
+	u64 start;
+	u64 len;
+	u64 logical;
+	unsigned long bio_flags;
+	int this_mirror;
+	int failed_mirror;
+	int in_validation;
+};
+
+void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end);
+int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
+				struct io_failure_record **failrec_ret);
+int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
+			   struct io_failure_record *failrec, int fail_mirror);
+struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
+				    struct io_failure_record *failrec,
+				    struct page *page, int pg_offset, int icsum,
+				    bio_end_io_t *endio_func, void *data);
+int free_io_failure(struct inode *inode, struct io_failure_record *rec);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 noinline u64 find_lock_delalloc_range(struct inode *inode,
 				      struct extent_io_tree *tree,
 				      struct page *locked_page, u64 *start,
 				      u64 *end, u64 max_bytes);
+#endif
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
 					       u64 start, unsigned long len);
 #endif
-#endif
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 54c84daec9b5..783a94355efd 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -55,7 +55,7 @@ int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 	file_key.objectid = objectid;
 	file_key.offset = pos;
-	btrfs_set_key_type(&file_key, BTRFS_EXTENT_DATA_KEY);
+	file_key.type = BTRFS_EXTENT_DATA_KEY;
 
 	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(trans, root, path, &file_key,
@@ -100,7 +100,7 @@ btrfs_lookup_csum(struct btrfs_trans_handle *trans,
 
 	file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
 	file_key.offset = bytenr;
-	btrfs_set_key_type(&file_key, BTRFS_EXTENT_CSUM_KEY);
+	file_key.type = BTRFS_EXTENT_CSUM_KEY;
 	ret = btrfs_search_slot(trans, root, &file_key, path, 0, cow);
 	if (ret < 0)
 		goto fail;
@@ -111,7 +111,7 @@ btrfs_lookup_csum(struct btrfs_trans_handle *trans,
 			goto fail;
 		path->slots[0]--;
 		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-		if (btrfs_key_type(&found_key) != BTRFS_EXTENT_CSUM_KEY)
+		if (found_key.type != BTRFS_EXTENT_CSUM_KEY)
 			goto fail;
 
 		csum_offset = (bytenr - found_key.offset) >>
@@ -148,7 +148,7 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans,
 
 	file_key.objectid = objectid;
 	file_key.offset = offset;
-	btrfs_set_key_type(&file_key, BTRFS_EXTENT_DATA_KEY);
+	file_key.type = BTRFS_EXTENT_DATA_KEY;
 	ret = btrfs_search_slot(trans, root, &file_key, path, ins_len, cow);
 	return ret;
 }
@@ -299,19 +299,9 @@ int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode,
 }
 
 int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode,
-			      struct btrfs_dio_private *dip, struct bio *bio,
-			      u64 offset)
+			      struct bio *bio, u64 offset)
 {
-	int len = (bio->bi_iter.bi_sector << 9) - dip->disk_bytenr;
-	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
-	int ret;
-
-	len >>= inode->i_sb->s_blocksize_bits;
-	len *= csum_size;
-
-	ret = __btrfs_lookup_bio_sums(root, inode, bio, offset,
-				      (u32 *)(dip->csum + len), 1);
-	return ret;
+	return __btrfs_lookup_bio_sums(root, inode, bio, offset, NULL, 1);
 }
 
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
@@ -329,8 +319,8 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 	u64 csum_end;
 	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
 
-	ASSERT(start == ALIGN(start, root->sectorsize) &&
-	       (end + 1) == ALIGN(end + 1, root->sectorsize));
+	ASSERT(IS_ALIGNED(start, root->sectorsize) &&
+	       IS_ALIGNED(end + 1, root->sectorsize));
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -720,7 +710,7 @@ again:
 	bytenr = sums->bytenr + total_bytes;
 	file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
 	file_key.offset = bytenr;
-	btrfs_set_key_type(&file_key, BTRFS_EXTENT_CSUM_KEY);
+	file_key.type = BTRFS_EXTENT_CSUM_KEY;
 
 	item = btrfs_lookup_csum(trans, root, path, bytenr, 1);
 	if (!IS_ERR(item)) {
@@ -790,7 +780,7 @@ again:
 	csum_offset = (bytenr - found_key.offset) >>
 			root->fs_info->sb->s_blocksize_bits;
 
-	if (btrfs_key_type(&found_key) != BTRFS_EXTENT_CSUM_KEY ||
+	if (found_key.type != BTRFS_EXTENT_CSUM_KEY ||
 	    found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
 	    csum_offset >= MAX_CSUM_ITEMS(root, csum_size)) {
 		goto insert;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index ff1cc0399b9a..a18ceabd99a8 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -299,7 +299,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 
 	/* get the inode */
 	key.objectid = defrag->root;
-	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
+	key.type = BTRFS_ROOT_ITEM_KEY;
 	key.offset = (u64)-1;
 
 	index = srcu_read_lock(&fs_info->subvol_srcu);
@@ -311,7 +311,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 	}
 
 	key.objectid = defrag->ino;
-	btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
+	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 	inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
 	if (IS_ERR(inode)) {
@@ -452,7 +452,7 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
 		if (unlikely(copied == 0))
 			break;
 
-		if (unlikely(copied < PAGE_CACHE_SIZE - offset)) {
+		if (copied < PAGE_CACHE_SIZE - offset) {
 			offset += copied;
 		} else {
 			pg++;
@@ -1481,9 +1481,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 	bool force_page_uptodate = false;
 	bool need_unlock;
 
-	nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) /
-		     PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
-		     (sizeof(struct page *)));
+	nrptrs = min(DIV_ROUND_UP(iov_iter_count(i), PAGE_CACHE_SIZE),
+			PAGE_CACHE_SIZE / (sizeof(struct page *)));
 	nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied);
 	nrptrs = max(nrptrs, 8);
 	pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
@@ -1497,8 +1496,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		size_t write_bytes = min(iov_iter_count(i),
 					 nrptrs * (size_t)PAGE_CACHE_SIZE -
 					 offset);
-		size_t num_pages = (write_bytes + offset +
-				    PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+		size_t num_pages = DIV_ROUND_UP(write_bytes + offset,
+						PAGE_CACHE_SIZE);
 		size_t reserve_bytes;
 		size_t dirty_pages;
 		size_t copied;
@@ -1526,9 +1525,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 				 * our prealloc extent may be smaller than
 				 * write_bytes, so scale down.
 				 */
-				num_pages = (write_bytes + offset +
-					     PAGE_CACHE_SIZE - 1) >>
-					PAGE_CACHE_SHIFT;
+				num_pages = DIV_ROUND_UP(write_bytes + offset,
+							 PAGE_CACHE_SIZE);
 				reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
 				ret = 0;
 			} else {
@@ -1590,9 +1588,8 @@ again:
 			dirty_pages = 0;
 		} else {
 			force_page_uptodate = false;
-			dirty_pages = (copied + offset +
-				       PAGE_CACHE_SIZE - 1) >>
-				       PAGE_CACHE_SHIFT;
+			dirty_pages = DIV_ROUND_UP(copied + offset,
+						   PAGE_CACHE_SIZE);
 		}
 
 		/*
@@ -1653,7 +1650,7 @@ again:
 		cond_resched();
 
 		balance_dirty_pages_ratelimited(inode->i_mapping);
-		if (dirty_pages < (root->leafsize >> PAGE_CACHE_SHIFT) + 1)
+		if (dirty_pages < (root->nodesize >> PAGE_CACHE_SHIFT) + 1)
 			btrfs_btree_balance_dirty(root);
 
 		pos += copied;
@@ -1795,7 +1792,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	if (sync)
 		atomic_inc(&BTRFS_I(inode)->sync_writers);
 
-	if (unlikely(file->f_flags & O_DIRECT)) {
+	if (file->f_flags & O_DIRECT) {
 		num_written = __btrfs_direct_write(iocb, from, pos);
 	} else {
 		num_written = __btrfs_buffered_write(file, from, pos);
@@ -1852,6 +1849,20 @@ int btrfs_release_file(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
+{
+	int ret;
+
+	atomic_inc(&BTRFS_I(inode)->sync_writers);
+	ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
+	if (!ret && test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+			     &BTRFS_I(inode)->runtime_flags))
+		ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
+	atomic_dec(&BTRFS_I(inode)->sync_writers);
+
+	return ret;
+}
+
 /*
  * fsync call for both files and directories.  This logs the inode into
  * the tree log instead of forcing full commits whenever possible.
@@ -1881,30 +1892,64 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 * multi-task, and make the performance up.  See
 	 * btrfs_wait_ordered_range for an explanation of the ASYNC check.
 	 */
-	atomic_inc(&BTRFS_I(inode)->sync_writers);
-	ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
-	if (!ret && test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
-			     &BTRFS_I(inode)->runtime_flags))
-		ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
-	atomic_dec(&BTRFS_I(inode)->sync_writers);
+	ret = start_ordered_ops(inode, start, end);
 	if (ret)
 		return ret;
 
 	mutex_lock(&inode->i_mutex);
-
-	/*
-	 * We flush the dirty pages again to avoid some dirty pages in the
-	 * range being left.
-	 */
 	atomic_inc(&root->log_batch);
 	full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 			     &BTRFS_I(inode)->runtime_flags);
+	/*
+	 * We might have have had more pages made dirty after calling
+	 * start_ordered_ops and before acquiring the inode's i_mutex.
+	 */
 	if (full_sync) {
+		/*
+		 * For a full sync, we need to make sure any ordered operations
+		 * start and finish before we start logging the inode, so that
+		 * all extents are persisted and the respective file extent
+		 * items are in the fs/subvol btree.
+		 */
 		ret = btrfs_wait_ordered_range(inode, start, end - start + 1);
-		if (ret) {
-			mutex_unlock(&inode->i_mutex);
-			goto out;
-		}
+	} else {
+		/*
+		 * Start any new ordered operations before starting to log the
+		 * inode. We will wait for them to finish in btrfs_sync_log().
+		 *
+		 * Right before acquiring the inode's mutex, we might have new
+		 * writes dirtying pages, which won't immediately start the
+		 * respective ordered operations - that is done through the
+		 * fill_delalloc callbacks invoked from the writepage and
+		 * writepages address space operations. So make sure we start
+		 * all ordered operations before starting to log our inode. Not
+		 * doing this means that while logging the inode, writeback
+		 * could start and invoke writepage/writepages, which would call
+		 * the fill_delalloc callbacks (cow_file_range,
+		 * submit_compressed_extents). These callbacks add first an
+		 * extent map to the modified list of extents and then create
+		 * the respective ordered operation, which means in
+		 * tree-log.c:btrfs_log_inode() we might capture all existing
+		 * ordered operations (with btrfs_get_logged_extents()) before
+		 * the fill_delalloc callback adds its ordered operation, and by
+		 * the time we visit the modified list of extent maps (with
+		 * btrfs_log_changed_extents()), we see and process the extent
+		 * map they created. We then use the extent map to construct a
+		 * file extent item for logging without waiting for the
+		 * respective ordered operation to finish - this file extent
+		 * item points to a disk location that might not have yet been
+		 * written to, containing random data - so after a crash a log
+		 * replay will make our inode have file extent items that point
+		 * to disk locations containing invalid data, as we returned
+		 * success to userspace without waiting for the respective
+		 * ordered operation to finish, because it wasn't captured by
+		 * btrfs_get_logged_extents().
+		 */
+		ret = start_ordered_ops(inode, start, end);
+	}
+	if (ret) {
+		mutex_unlock(&inode->i_mutex);
+		goto out;
 	}
 	atomic_inc(&root->log_batch);
 
@@ -1984,6 +2029,25 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 */
 	mutex_unlock(&inode->i_mutex);
 
+	/*
+	 * If any of the ordered extents had an error, just return it to user
+	 * space, so that the application knows some writes didn't succeed and
+	 * can take proper action (retry for e.g.). Blindly committing the
+	 * transaction in this case, would fool userspace that everything was
+	 * successful. And we also want to make sure our log doesn't contain
+	 * file extent items pointing to extents that weren't fully written to -
+	 * just like in the non fast fsync path, where we check for the ordered
+	 * operation's error flag before writing to the log tree and return -EIO
+	 * if any of them had this flag set (btrfs_wait_ordered_range) -
+	 * therefore we need to check for errors in the ordered operations,
+	 * which are indicated by ctx.io_err.
+	 */
+	if (ctx.io_err) {
+		btrfs_end_transaction(trans, root);
+		ret = ctx.io_err;
+		goto out;
+	}
+
 	if (ret != BTRFS_NO_LOG_SYNC) {
 		if (!ret) {
 			ret = btrfs_sync_log(trans, root, &ctx);
@@ -2621,23 +2685,28 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct extent_map *em = NULL;
 	struct extent_state *cached_state = NULL;
-	u64 lockstart = *offset;
-	u64 lockend = i_size_read(inode);
-	u64 start = *offset;
-	u64 len = i_size_read(inode);
+	u64 lockstart;
+	u64 lockend;
+	u64 start;
+	u64 len;
 	int ret = 0;
 
-	lockend = max_t(u64, root->sectorsize, lockend);
+	if (inode->i_size == 0)
+		return -ENXIO;
+
+	/*
+	 * *offset can be negative, in this case we start finding DATA/HOLE from
+	 * the very start of the file.
+	 */
+	start = max_t(loff_t, 0, *offset);
+
+	lockstart = round_down(start, root->sectorsize);
+	lockend = round_up(i_size_read(inode), root->sectorsize);
 	if (lockend <= lockstart)
 		lockend = lockstart + root->sectorsize;
-
 	lockend--;
 	len = lockend - lockstart + 1;
 
-	len = max_t(u64, len, root->sectorsize);
-	if (inode->i_size == 0)
-		return -ENXIO;
-
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, 0,
 			 &cached_state);
 
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 2b0a627cb5f9..33848196550e 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -279,8 +279,7 @@ static int io_ctl_init(struct io_ctl *io_ctl, struct inode *inode,
 	int num_pages;
 	int check_crcs = 0;
 
-	num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
-		    PAGE_CACHE_SHIFT;
+	num_pages = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
 
 	if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID)
 		check_crcs = 1;
@@ -1998,6 +1997,128 @@ static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl,
 	return merged;
 }
 
+static bool steal_from_bitmap_to_end(struct btrfs_free_space_ctl *ctl,
+				     struct btrfs_free_space *info,
+				     bool update_stat)
+{
+	struct btrfs_free_space *bitmap;
+	unsigned long i;
+	unsigned long j;
+	const u64 end = info->offset + info->bytes;
+	const u64 bitmap_offset = offset_to_bitmap(ctl, end);
+	u64 bytes;
+
+	bitmap = tree_search_offset(ctl, bitmap_offset, 1, 0);
+	if (!bitmap)
+		return false;
+
+	i = offset_to_bit(bitmap->offset, ctl->unit, end);
+	j = find_next_zero_bit(bitmap->bitmap, BITS_PER_BITMAP, i);
+	if (j == i)
+		return false;
+	bytes = (j - i) * ctl->unit;
+	info->bytes += bytes;
+
+	if (update_stat)
+		bitmap_clear_bits(ctl, bitmap, end, bytes);
+	else
+		__bitmap_clear_bits(ctl, bitmap, end, bytes);
+
+	if (!bitmap->bytes)
+		free_bitmap(ctl, bitmap);
+
+	return true;
+}
+
+static bool steal_from_bitmap_to_front(struct btrfs_free_space_ctl *ctl,
+				       struct btrfs_free_space *info,
+				       bool update_stat)
+{
+	struct btrfs_free_space *bitmap;
+	u64 bitmap_offset;
+	unsigned long i;
+	unsigned long j;
+	unsigned long prev_j;
+	u64 bytes;
+
+	bitmap_offset = offset_to_bitmap(ctl, info->offset);
+	/* If we're on a boundary, try the previous logical bitmap. */
+	if (bitmap_offset == info->offset) {
+		if (info->offset == 0)
+			return false;
+		bitmap_offset = offset_to_bitmap(ctl, info->offset - 1);
+	}
+
+	bitmap = tree_search_offset(ctl, bitmap_offset, 1, 0);
+	if (!bitmap)
+		return false;
+
+	i = offset_to_bit(bitmap->offset, ctl->unit, info->offset) - 1;
+	j = 0;
+	prev_j = (unsigned long)-1;
+	for_each_clear_bit_from(j, bitmap->bitmap, BITS_PER_BITMAP) {
+		if (j > i)
+			break;
+		prev_j = j;
+	}
+	if (prev_j == i)
+		return false;
+
+	if (prev_j == (unsigned long)-1)
+		bytes = (i + 1) * ctl->unit;
+	else
+		bytes = (i - prev_j) * ctl->unit;
+
+	info->offset -= bytes;
+	info->bytes += bytes;
+
+	if (update_stat)
+		bitmap_clear_bits(ctl, bitmap, info->offset, bytes);
+	else
+		__bitmap_clear_bits(ctl, bitmap, info->offset, bytes);
+
+	if (!bitmap->bytes)
+		free_bitmap(ctl, bitmap);
+
+	return true;
+}
+
+/*
+ * We prefer always to allocate from extent entries, both for clustered and
+ * non-clustered allocation requests. So when attempting to add a new extent
+ * entry, try to see if there's adjacent free space in bitmap entries, and if
+ * there is, migrate that space from the bitmaps to the extent.
+ * Like this we get better chances of satisfying space allocation requests
+ * because we attempt to satisfy them based on a single cache entry, and never
+ * on 2 or more entries - even if the entries represent a contiguous free space
+ * region (e.g. 1 extent entry + 1 bitmap entry starting where the extent entry
+ * ends).
+ */
+static void steal_from_bitmap(struct btrfs_free_space_ctl *ctl,
+			      struct btrfs_free_space *info,
+			      bool update_stat)
+{
+	/*
+	 * Only work with disconnected entries, as we can change their offset,
+	 * and must be extent entries.
+	 */
+	ASSERT(!info->bitmap);
+	ASSERT(RB_EMPTY_NODE(&info->offset_index));
+
+	if (ctl->total_bitmaps > 0) {
+		bool stole_end;
+		bool stole_front = false;
+
+		stole_end = steal_from_bitmap_to_end(ctl, info, update_stat);
+		if (ctl->total_bitmaps > 0)
+			stole_front = steal_from_bitmap_to_front(ctl, info,
+								 update_stat);
+
+		if (stole_end || stole_front)
+			try_merge_free_space(ctl, info, update_stat);
+	}
+}
+
 int __btrfs_add_free_space(struct btrfs_free_space_ctl *ctl,
 			   u64 offset, u64 bytes)
 {
@@ -2010,6 +2131,7 @@ int __btrfs_add_free_space(struct btrfs_free_space_ctl *ctl,
 
 	info->offset = offset;
 	info->bytes = bytes;
+	RB_CLEAR_NODE(&info->offset_index);
 
 	spin_lock(&ctl->tree_lock);
 
@@ -2029,6 +2151,14 @@ int __btrfs_add_free_space(struct btrfs_free_space_ctl *ctl,
 		goto out;
 	}
 link:
+	/*
+	 * Only steal free space from adjacent bitmaps if we're sure we're not
+	 * going to add the new free space to existing bitmap entries - because
+	 * that would mean unnecessary work that would be reverted. Therefore
+	 * attempt to steal space from bitmaps if we're adding an extent entry.
+	 */
+	steal_from_bitmap(ctl, info, true);
+
 	ret = link_free_space(ctl, info);
 	if (ret)
 		kmem_cache_free(btrfs_free_space_cachep, info);
@@ -2205,10 +2335,13 @@ __btrfs_return_cluster_to_free_space(
 		entry = rb_entry(node, struct btrfs_free_space, offset_index);
 		node = rb_next(&entry->offset_index);
 		rb_erase(&entry->offset_index, &cluster->root);
+		RB_CLEAR_NODE(&entry->offset_index);
 
 		bitmap = (entry->bitmap != NULL);
-		if (!bitmap)
+		if (!bitmap) {
 			try_merge_free_space(ctl, entry, false);
+			steal_from_bitmap(ctl, entry, false);
+		}
 		tree_insert_offset(&ctl->free_space_offset,
 				   entry->offset, &entry->offset_index, bitmap);
 	}
@@ -3033,10 +3166,10 @@ struct inode *lookup_free_ino_inode(struct btrfs_root *root,
 {
 	struct inode *inode = NULL;
 
-	spin_lock(&root->cache_lock);
-	if (root->cache_inode)
-		inode = igrab(root->cache_inode);
-	spin_unlock(&root->cache_lock);
+	spin_lock(&root->ino_cache_lock);
+	if (root->ino_cache_inode)
+		inode = igrab(root->ino_cache_inode);
+	spin_unlock(&root->ino_cache_lock);
 	if (inode)
 		return inode;
 
@@ -3044,10 +3177,10 @@ struct inode *lookup_free_ino_inode(struct btrfs_root *root,
 	if (IS_ERR(inode))
 		return inode;
 
-	spin_lock(&root->cache_lock);
+	spin_lock(&root->ino_cache_lock);
 	if (!btrfs_fs_closing(root->fs_info))
-		root->cache_inode = igrab(inode);
-	spin_unlock(&root->cache_lock);
+		root->ino_cache_inode = igrab(inode);
+	spin_unlock(&root->ino_cache_lock);
 
 	return inode;
 }
@@ -3176,6 +3309,7 @@ again:
 		map = NULL;
 		add_new_bitmap(ctl, info, offset);
 		bitmap_info = info;
+		info = NULL;
 	}
 
 	bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes);
@@ -3186,6 +3320,8 @@ again:
 	if (bytes)
 		goto again;
 
+	if (info)
+		kmem_cache_free(btrfs_free_space_cachep, info);
 	if (map)
 		kfree(map);
 	return 0;
@@ -3260,6 +3396,7 @@ have_info:
 			goto have_info;
 		}
 
+		ret = 0;
 		goto out;
 	}
 
diff --git a/fs/btrfs/hash.c b/fs/btrfs/hash.c
index 85889aa82c62..aae520b2aee5 100644
--- a/fs/btrfs/hash.c
+++ b/fs/btrfs/hash.c
@@ -20,10 +20,8 @@ static struct crypto_shash *tfm;
 int __init btrfs_hash_init(void)
 {
 	tfm = crypto_alloc_shash("crc32c", 0, 0);
-	if (IS_ERR(tfm))
-		return PTR_ERR(tfm);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(tfm);
 }
 
 void btrfs_hash_exit(void)
@@ -33,18 +31,16 @@ void btrfs_hash_exit(void)
 
 u32 btrfs_crc32c(u32 crc, const void *address, unsigned int length)
 {
-	struct {
-		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(tfm)];
-	} desc;
+	SHASH_DESC_ON_STACK(shash, tfm);
+	u32 *ctx = (u32 *)shash_desc_ctx(shash);
 	int err;
 
-	desc.shash.tfm = tfm;
-	desc.shash.flags = 0;
-	*(u32 *)desc.ctx = crc;
+	shash->tfm = tfm;
+	shash->flags = 0;
+	*ctx = crc;
 
-	err = crypto_shash_update(&desc.shash, address, length);
+	err = crypto_shash_update(shash, address, length);
 	BUG_ON(err);
 
-	return *(u32 *)desc.ctx;
+	return *ctx;
 }
diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index 2be38df703c9..8ffa4783cbf4 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -135,7 +135,7 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans,
 	u32 item_size;
 
 	key.objectid = inode_objectid;
-	btrfs_set_key_type(&key, BTRFS_INODE_EXTREF_KEY);
+	key.type = BTRFS_INODE_EXTREF_KEY;
 	key.offset = btrfs_extref_hash(ref_objectid, name, name_len);
 
 	path = btrfs_alloc_path();
@@ -209,7 +209,7 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
 
 	key.objectid = inode_objectid;
 	key.offset = ref_objectid;
-	btrfs_set_key_type(&key, BTRFS_INODE_REF_KEY);
+	key.type = BTRFS_INODE_REF_KEY;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -337,7 +337,7 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 
 	key.objectid = inode_objectid;
 	key.offset = ref_objectid;
-	btrfs_set_key_type(&key, BTRFS_INODE_REF_KEY);
+	key.type = BTRFS_INODE_REF_KEY;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -400,7 +400,7 @@ int btrfs_insert_empty_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	int ret;
 	key.objectid = objectid;
-	btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
+	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
 	ret = btrfs_insert_empty_item(trans, root, path, &key,
@@ -420,13 +420,13 @@ int btrfs_lookup_inode(struct btrfs_trans_handle *trans, struct btrfs_root
 	struct btrfs_key found_key;
 
 	ret = btrfs_search_slot(trans, root, location, path, ins_len, cow);
-	if (ret > 0 && btrfs_key_type(location) == BTRFS_ROOT_ITEM_KEY &&
+	if (ret > 0 && location->type == BTRFS_ROOT_ITEM_KEY &&
 	    location->offset == (u64)-1 && path->slots[0] != 0) {
 		slot = path->slots[0] - 1;
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 		if (found_key.objectid == location->objectid &&
-		    btrfs_key_type(&found_key) == btrfs_key_type(location)) {
+		    found_key.type == location->type) {
 			path->slots[0]--;
 			return 0;
 		}
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 888fbe19079f..83d646bd2e4b 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -87,7 +87,7 @@ again:
 				 */
 				btrfs_item_key_to_cpu(leaf, &key, 0);
 				btrfs_release_path(path);
-				root->cache_progress = last;
+				root->ino_cache_progress = last;
 				up_read(&fs_info->commit_root_sem);
 				schedule_timeout(1);
 				goto again;
@@ -106,7 +106,7 @@ again:
 		if (last != (u64)-1 && last + 1 != key.objectid) {
 			__btrfs_add_free_space(ctl, last + 1,
 					       key.objectid - last - 1);
-			wake_up(&root->cache_wait);
+			wake_up(&root->ino_cache_wait);
 		}
 
 		last = key.objectid;
@@ -119,14 +119,14 @@ next:
 				       root->highest_objectid - last - 1);
 	}
 
-	spin_lock(&root->cache_lock);
-	root->cached = BTRFS_CACHE_FINISHED;
-	spin_unlock(&root->cache_lock);
+	spin_lock(&root->ino_cache_lock);
+	root->ino_cache_state = BTRFS_CACHE_FINISHED;
+	spin_unlock(&root->ino_cache_lock);
 
-	root->cache_progress = (u64)-1;
+	root->ino_cache_progress = (u64)-1;
 	btrfs_unpin_free_ino(root);
 out:
-	wake_up(&root->cache_wait);
+	wake_up(&root->ino_cache_wait);
 	up_read(&fs_info->commit_root_sem);
 
 	btrfs_free_path(path);
@@ -144,20 +144,20 @@ static void start_caching(struct btrfs_root *root)
 	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
 		return;
 
-	spin_lock(&root->cache_lock);
-	if (root->cached != BTRFS_CACHE_NO) {
-		spin_unlock(&root->cache_lock);
+	spin_lock(&root->ino_cache_lock);
+	if (root->ino_cache_state != BTRFS_CACHE_NO) {
+		spin_unlock(&root->ino_cache_lock);
 		return;
 	}
 
-	root->cached = BTRFS_CACHE_STARTED;
-	spin_unlock(&root->cache_lock);
+	root->ino_cache_state = BTRFS_CACHE_STARTED;
+	spin_unlock(&root->ino_cache_lock);
 
 	ret = load_free_ino_cache(root->fs_info, root);
 	if (ret == 1) {
-		spin_lock(&root->cache_lock);
-		root->cached = BTRFS_CACHE_FINISHED;
-		spin_unlock(&root->cache_lock);
+		spin_lock(&root->ino_cache_lock);
+		root->ino_cache_state = BTRFS_CACHE_FINISHED;
+		spin_unlock(&root->ino_cache_lock);
 		return;
 	}
 
@@ -196,11 +196,11 @@ again:
 
 	start_caching(root);
 
-	wait_event(root->cache_wait,
-		   root->cached == BTRFS_CACHE_FINISHED ||
+	wait_event(root->ino_cache_wait,
+		   root->ino_cache_state == BTRFS_CACHE_FINISHED ||
 		   root->free_ino_ctl->free_space > 0);
 
-	if (root->cached == BTRFS_CACHE_FINISHED &&
+	if (root->ino_cache_state == BTRFS_CACHE_FINISHED &&
 	    root->free_ino_ctl->free_space == 0)
 		return -ENOSPC;
 	else
@@ -214,17 +214,17 @@ void btrfs_return_ino(struct btrfs_root *root, u64 objectid)
 	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
 		return;
 again:
-	if (root->cached == BTRFS_CACHE_FINISHED) {
+	if (root->ino_cache_state == BTRFS_CACHE_FINISHED) {
 		__btrfs_add_free_space(pinned, objectid, 1);
 	} else {
 		down_write(&root->fs_info->commit_root_sem);
-		spin_lock(&root->cache_lock);
-		if (root->cached == BTRFS_CACHE_FINISHED) {
-			spin_unlock(&root->cache_lock);
+		spin_lock(&root->ino_cache_lock);
+		if (root->ino_cache_state == BTRFS_CACHE_FINISHED) {
+			spin_unlock(&root->ino_cache_lock);
 			up_write(&root->fs_info->commit_root_sem);
 			goto again;
 		}
-		spin_unlock(&root->cache_lock);
+		spin_unlock(&root->ino_cache_lock);
 
 		start_caching(root);
 
@@ -235,10 +235,10 @@ again:
 }
 
 /*
- * When a transaction is committed, we'll move those inode numbers which
- * are smaller than root->cache_progress from pinned tree to free_ino tree,
- * and others will just be dropped, because the commit root we were
- * searching has changed.
+ * When a transaction is committed, we'll move those inode numbers which are
+ * smaller than root->ino_cache_progress from pinned tree to free_ino tree, and
+ * others will just be dropped, because the commit root we were searching has
+ * changed.
  *
  * Must be called with root->fs_info->commit_root_sem held
  */
@@ -261,10 +261,10 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
 		info = rb_entry(n, struct btrfs_free_space, offset_index);
 		BUG_ON(info->bitmap); /* Logic error */
 
-		if (info->offset > root->cache_progress)
+		if (info->offset > root->ino_cache_progress)
 			goto free;
-		else if (info->offset + info->bytes > root->cache_progress)
-			count = root->cache_progress - info->offset + 1;
+		else if (info->offset + info->bytes > root->ino_cache_progress)
+			count = root->ino_cache_progress - info->offset + 1;
 		else
 			count = info->bytes;
 
@@ -462,13 +462,13 @@ again:
 		}
 	}
 
-	spin_lock(&root->cache_lock);
-	if (root->cached != BTRFS_CACHE_FINISHED) {
+	spin_lock(&root->ino_cache_lock);
+	if (root->ino_cache_state != BTRFS_CACHE_FINISHED) {
 		ret = -1;
-		spin_unlock(&root->cache_lock);
+		spin_unlock(&root->ino_cache_lock);
 		goto out_put;
 	}
-	spin_unlock(&root->cache_lock);
+	spin_unlock(&root->ino_cache_lock);
 
 	spin_lock(&ctl->tree_lock);
 	prealloc = sizeof(struct btrfs_free_space) * ctl->free_extents;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 016c403bfe7e..d23362f4464e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -153,7 +153,7 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 
 		key.objectid = btrfs_ino(inode);
 		key.offset = start;
-		btrfs_set_key_type(&key, BTRFS_EXTENT_DATA_KEY);
+		key.type = BTRFS_EXTENT_DATA_KEY;
 
 		datasize = btrfs_file_extent_calc_inline_size(cur_size);
 		path->leave_spinning = 1;
@@ -249,8 +249,8 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
 		data_len = compressed_size;
 
 	if (start > 0 ||
-	    actual_end >= PAGE_CACHE_SIZE ||
-	    data_len >= BTRFS_MAX_INLINE_DATA_SIZE(root) ||
+	    actual_end > PAGE_CACHE_SIZE ||
+	    data_len > BTRFS_MAX_INLINE_DATA_SIZE(root) ||
 	    (!compressed_size &&
 	    (actual_end & (root->sectorsize - 1)) == 0) ||
 	    end + 1 < isize ||
@@ -348,6 +348,23 @@ static noinline int add_async_extent(struct async_cow *cow,
 	return 0;
 }
 
+static inline int inode_need_compress(struct inode *inode)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+
+	/* force compress */
+	if (btrfs_test_opt(root, FORCE_COMPRESS))
+		return 1;
+	/* bad compression ratios */
+	if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS)
+		return 0;
+	if (btrfs_test_opt(root, COMPRESS) ||
+	    BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS ||
+	    BTRFS_I(inode)->force_compress)
+		return 1;
+	return 0;
+}
+
 /*
  * we create compressed extents in two phases.  The first
  * phase compresses a range of pages that have already been
@@ -444,10 +461,7 @@ again:
 	 * inode has not been flagged as nocompress.  This flag can
 	 * change at any time if we discover bad compression ratios.
 	 */
-	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS) &&
-	    (btrfs_test_opt(root, COMPRESS) ||
-	     (BTRFS_I(inode)->force_compress) ||
-	     (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS))) {
+	if (inode_need_compress(inode)) {
 		WARN_ON(pages);
 		pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
 		if (!pages) {
@@ -1094,7 +1108,8 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 		async_cow->locked_page = locked_page;
 		async_cow->start = start;
 
-		if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS)
+		if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS &&
+		    !btrfs_test_opt(root, FORCE_COMPRESS))
 			cur_end = end;
 		else
 			cur_end = min(end, start + 512 * 1024 - 1);
@@ -1445,6 +1460,26 @@ error:
 	return ret;
 }
 
+static inline int need_force_cow(struct inode *inode, u64 start, u64 end)
+{
+
+	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
+	    !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC))
+		return 0;
+
+	/*
+	 * @defrag_bytes is a hint value, no spinlock held here,
+	 * if is not zero, it means the file is defragging.
+	 * Force cow if given extent needs to be defragged.
+	 */
+	if (BTRFS_I(inode)->defrag_bytes &&
+	    test_range_bit(&BTRFS_I(inode)->io_tree, start, end,
+			   EXTENT_DEFRAG, 0, NULL))
+		return 1;
+
+	return 0;
+}
+
 /*
  * extent_io.c call back to do delayed allocation processing
  */
@@ -1453,17 +1488,15 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page,
 			      unsigned long *nr_written)
 {
 	int ret;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	int force_cow = need_force_cow(inode, start, end);
 
-	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) {
+	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) {
 		ret = run_delalloc_nocow(inode, locked_page, start, end,
 					 page_started, 1, nr_written);
-	} else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC) {
+	} else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC && !force_cow) {
 		ret = run_delalloc_nocow(inode, locked_page, start, end,
 					 page_started, 0, nr_written);
-	} else if (!btrfs_test_opt(root, COMPRESS) &&
-		   !(BTRFS_I(inode)->force_compress) &&
-		   !(BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS)) {
+	} else if (!inode_need_compress(inode)) {
 		ret = cow_file_range(inode, locked_page, start, end,
 				      page_started, nr_written, 1);
 	} else {
@@ -1555,6 +1588,8 @@ static void btrfs_set_bit_hook(struct inode *inode,
 			       struct extent_state *state, unsigned long *bits)
 {
 
+	if ((*bits & EXTENT_DEFRAG) && !(*bits & EXTENT_DELALLOC))
+		WARN_ON(1);
 	/*
 	 * set_bit and clear bit hooks normally require _irqsave/restore
 	 * but in this case, we are only testing for the DELALLOC
@@ -1577,6 +1612,8 @@ static void btrfs_set_bit_hook(struct inode *inode,
 				     root->fs_info->delalloc_batch);
 		spin_lock(&BTRFS_I(inode)->lock);
 		BTRFS_I(inode)->delalloc_bytes += len;
+		if (*bits & EXTENT_DEFRAG)
+			BTRFS_I(inode)->defrag_bytes += len;
 		if (do_list && !test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
 					 &BTRFS_I(inode)->runtime_flags))
 			btrfs_add_delalloc_inodes(root, inode);
@@ -1591,6 +1628,13 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 				 struct extent_state *state,
 				 unsigned long *bits)
 {
+	u64 len = state->end + 1 - state->start;
+
+	spin_lock(&BTRFS_I(inode)->lock);
+	if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG))
+		BTRFS_I(inode)->defrag_bytes -= len;
+	spin_unlock(&BTRFS_I(inode)->lock);
+
 	/*
 	 * set_bit and clear bit hooks normally require _irqsave/restore
 	 * but in this case, we are only testing for the DELALLOC
@@ -1598,7 +1642,6 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 	 */
 	if ((state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = BTRFS_I(inode)->root;
-		u64 len = state->end + 1 - state->start;
 		bool do_list = !btrfs_is_free_space_inode(inode);
 
 		if (*bits & EXTENT_FIRST_DELALLOC) {
@@ -2660,6 +2703,10 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		goto out;
 	}
 
+	btrfs_free_io_failure_record(inode, ordered_extent->file_offset,
+				     ordered_extent->file_offset +
+				     ordered_extent->len - 1);
+
 	if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) {
 		truncated = true;
 		logical_len = ordered_extent->truncated_len;
@@ -2856,6 +2903,40 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 	return 0;
 }
 
+static int __readpage_endio_check(struct inode *inode,
+				  struct btrfs_io_bio *io_bio,
+				  int icsum, struct page *page,
+				  int pgoff, u64 start, size_t len)
+{
+	char *kaddr;
+	u32 csum_expected;
+	u32 csum = ~(u32)0;
+	static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
+				      DEFAULT_RATELIMIT_BURST);
+
+	csum_expected = *(((u32 *)io_bio->csum) + icsum);
+
+	kaddr = kmap_atomic(page);
+	csum = btrfs_csum_data(kaddr + pgoff, csum,  len);
+	btrfs_csum_final(csum, (char *)&csum);
+	if (csum != csum_expected)
+		goto zeroit;
+
+	kunmap_atomic(kaddr);
+	return 0;
+zeroit:
+	if (__ratelimit(&_rs))
+		btrfs_info(BTRFS_I(inode)->root->fs_info,
+			   "csum failed ino %llu off %llu csum %u expected csum %u",
+			   btrfs_ino(inode), start, csum, csum_expected);
+	memset(kaddr + pgoff, 1, len);
+	flush_dcache_page(page);
+	kunmap_atomic(kaddr);
+	if (csum_expected == 0)
+		return 0;
+	return -EIO;
+}
+
 /*
  * when reads are done, we need to check csums to verify the data is correct
  * if there's a match, we allow the bio to finish.  If not, the code in
@@ -2868,20 +2949,15 @@ static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	size_t offset = start - page_offset(page);
 	struct inode *inode = page->mapping->host;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
-	char *kaddr;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	u32 csum_expected;
-	u32 csum = ~(u32)0;
-	static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
-	                              DEFAULT_RATELIMIT_BURST);
 
 	if (PageChecked(page)) {
 		ClearPageChecked(page);
-		goto good;
+		return 0;
 	}
 
 	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
-		goto good;
+		return 0;
 
 	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID &&
 	    test_range_bit(io_tree, start, end, EXTENT_NODATASUM, 1, NULL)) {
@@ -2891,28 +2967,8 @@ static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	}
 
 	phy_offset >>= inode->i_sb->s_blocksize_bits;
-	csum_expected = *(((u32 *)io_bio->csum) + phy_offset);
-
-	kaddr = kmap_atomic(page);
-	csum = btrfs_csum_data(kaddr + offset, csum,  end - start + 1);
-	btrfs_csum_final(csum, (char *)&csum);
-	if (csum != csum_expected)
-		goto zeroit;
-
-	kunmap_atomic(kaddr);
-good:
-	return 0;
-
-zeroit:
-	if (__ratelimit(&_rs))
-		btrfs_info(root->fs_info, "csum failed ino %llu off %llu csum %u expected csum %u",
-			btrfs_ino(page->mapping->host), start, csum, csum_expected);
-	memset(kaddr + offset, 1, end - start + 1);
-	flush_dcache_page(page);
-	kunmap_atomic(kaddr);
-	if (csum_expected == 0)
-		return 0;
-	return -EIO;
+	return __readpage_endio_check(inode, io_bio, phy_offset, page, offset,
+				      start, (size_t)(end - start + 1));
 }
 
 struct delayed_iput {
@@ -3159,7 +3215,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 	path->reada = -1;
 
 	key.objectid = BTRFS_ORPHAN_OBJECTID;
-	btrfs_set_key_type(&key, BTRFS_ORPHAN_ITEM_KEY);
+	key.type = BTRFS_ORPHAN_ITEM_KEY;
 	key.offset = (u64)-1;
 
 	while (1) {
@@ -3186,7 +3242,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 		/* make sure the item matches what we want */
 		if (found_key.objectid != BTRFS_ORPHAN_OBJECTID)
 			break;
-		if (btrfs_key_type(&found_key) != BTRFS_ORPHAN_ITEM_KEY)
+		if (found_key.type != BTRFS_ORPHAN_ITEM_KEY)
 			break;
 
 		/* release the path since we're done with it */
@@ -3662,7 +3718,8 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
 	 * without delay
 	 */
 	if (!btrfs_is_free_space_inode(inode)
-	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) {
+	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
+	    && !root->fs_info->log_root_recovering) {
 		btrfs_update_root_times(trans, root);
 
 		ret = btrfs_delayed_update_inode(trans, root, inode);
@@ -4085,7 +4142,7 @@ search_again:
 		fi = NULL;
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-		found_type = btrfs_key_type(&found_key);
+		found_type = found_key.type;
 
 		if (found_key.objectid != ino)
 			break;
@@ -4747,6 +4804,8 @@ void btrfs_evict_inode(struct inode *inode)
 	/* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */
 	btrfs_wait_ordered_range(inode, 0, (u64)-1);
 
+	btrfs_free_io_failure_record(inode, 0, (u64)-1);
+
 	if (root->fs_info->log_root_recovering) {
 		BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
 				 &BTRFS_I(inode)->runtime_flags));
@@ -5202,42 +5261,6 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 			iput(inode);
 			inode = ERR_PTR(ret);
 		}
-		/*
-		 * If orphan cleanup did remove any orphans, it means the tree
-		 * was modified and therefore the commit root is not the same as
-		 * the current root anymore. This is a problem, because send
-		 * uses the commit root and therefore can see inode items that
-		 * don't exist in the current root anymore, and for example make
-		 * calls to btrfs_iget, which will do tree lookups based on the
-		 * current root and not on the commit root. Those lookups will
-		 * fail, returning a -ESTALE error, and making send fail with
-		 * that error. So make sure a send does not see any orphans we
-		 * have just removed, and that it will see the same inodes
-		 * regardless of whether a transaction commit happened before
-		 * it started (meaning that the commit root will be the same as
-		 * the current root) or not.
-		 */
-		if (sub_root->node != sub_root->commit_root) {
-			u64 sub_flags = btrfs_root_flags(&sub_root->root_item);
-
-			if (sub_flags & BTRFS_ROOT_SUBVOL_RDONLY) {
-				struct extent_buffer *eb;
-
-				/*
-				 * Assert we can't have races between dentry
-				 * lookup called through the snapshot creation
-				 * ioctl and the VFS.
-				 */
-				ASSERT(mutex_is_locked(&dir->i_mutex));
-
-				down_write(&root->fs_info->commit_root_sem);
-				eb = sub_root->commit_root;
-				sub_root->commit_root =
-					btrfs_root_node(sub_root);
-				up_write(&root->fs_info->commit_root_sem);
-				free_extent_buffer(eb);
-			}
-		}
 	}
 
 	return inode;
@@ -5331,7 +5354,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 		btrfs_get_delayed_items(inode, &ins_list, &del_list);
 	}
 
-	btrfs_set_key_type(&key, key_type);
+	key.type = key_type;
 	key.offset = ctx->pos;
 	key.objectid = btrfs_ino(inode);
 
@@ -5356,7 +5379,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 
 		if (found_key.objectid != key.objectid)
 			break;
-		if (btrfs_key_type(&found_key) != key_type)
+		if (found_key.type != key_type)
 			break;
 		if (found_key.offset < ctx->pos)
 			goto next;
@@ -5568,7 +5591,7 @@ static int btrfs_set_inode_index_count(struct inode *inode)
 	int ret;
 
 	key.objectid = btrfs_ino(inode);
-	btrfs_set_key_type(&key, BTRFS_DIR_INDEX_KEY);
+	key.type = BTRFS_DIR_INDEX_KEY;
 	key.offset = (u64)-1;
 
 	path = btrfs_alloc_path();
@@ -5600,7 +5623,7 @@ static int btrfs_set_inode_index_count(struct inode *inode)
 	btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
 
 	if (found_key.objectid != btrfs_ino(inode) ||
-	    btrfs_key_type(&found_key) != BTRFS_DIR_INDEX_KEY) {
+	    found_key.type != BTRFS_DIR_INDEX_KEY) {
 		BTRFS_I(inode)->index_cnt = 2;
 		goto out;
 	}
@@ -5718,7 +5741,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
 
 	key[0].objectid = objectid;
-	btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
+	key[0].type = BTRFS_INODE_ITEM_KEY;
 	key[0].offset = 0;
 
 	sizes[0] = sizeof(struct btrfs_inode_item);
@@ -5731,7 +5754,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 		 * add more hard links than can fit in the ref item.
 		 */
 		key[1].objectid = objectid;
-		btrfs_set_key_type(&key[1], BTRFS_INODE_REF_KEY);
+		key[1].type = BTRFS_INODE_REF_KEY;
 		key[1].offset = ref_objectid;
 
 		sizes[1] = name_len + sizeof(*ref);
@@ -5740,7 +5763,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	location = &BTRFS_I(inode)->location;
 	location->objectid = objectid;
 	location->offset = 0;
-	btrfs_set_key_type(location, BTRFS_INODE_ITEM_KEY);
+	location->type = BTRFS_INODE_ITEM_KEY;
 
 	ret = btrfs_insert_inode_locked(inode);
 	if (ret < 0)
@@ -5832,7 +5855,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 		memcpy(&key, &BTRFS_I(inode)->root->root_key, sizeof(key));
 	} else {
 		key.objectid = ino;
-		btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
+		key.type = BTRFS_INODE_ITEM_KEY;
 		key.offset = 0;
 	}
 
@@ -6191,21 +6214,60 @@ out_fail_inode:
 	goto out_fail;
 }
 
+/* Find next extent map of a given extent map, caller needs to ensure locks */
+static struct extent_map *next_extent_map(struct extent_map *em)
+{
+	struct rb_node *next;
+
+	next = rb_next(&em->rb_node);
+	if (!next)
+		return NULL;
+	return container_of(next, struct extent_map, rb_node);
+}
+
+static struct extent_map *prev_extent_map(struct extent_map *em)
+{
+	struct rb_node *prev;
+
+	prev = rb_prev(&em->rb_node);
+	if (!prev)
+		return NULL;
+	return container_of(prev, struct extent_map, rb_node);
+}
+
 /* helper for btfs_get_extent.  Given an existing extent in the tree,
+ * the existing extent is the nearest extent to map_start,
  * and an extent that you want to insert, deal with overlap and insert
- * the new extent into the tree.
+ * the best fitted new extent into the tree.
  */
 static int merge_extent_mapping(struct extent_map_tree *em_tree,
 				struct extent_map *existing,
 				struct extent_map *em,
 				u64 map_start)
 {
+	struct extent_map *prev;
+	struct extent_map *next;
+	u64 start;
+	u64 end;
 	u64 start_diff;
 
 	BUG_ON(map_start < em->start || map_start >= extent_map_end(em));
-	start_diff = map_start - em->start;
-	em->start = map_start;
-	em->len = existing->start - em->start;
+
+	if (existing->start > map_start) {
+		next = existing;
+		prev = prev_extent_map(next);
+	} else {
+		prev = existing;
+		next = next_extent_map(prev);
+	}
+
+	start = prev ? extent_map_end(prev) : em->start;
+	start = max_t(u64, start, em->start);
+	end = next ? next->start : extent_map_end(em);
+	end = min_t(u64, end, extent_map_end(em));
+	start_diff = start - em->start;
+	em->start = start;
+	em->len = end - start;
 	if (em->block_start < EXTENT_MAP_LAST_BYTE &&
 	    !test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
 		em->block_start += start_diff;
@@ -6333,7 +6395,7 @@ again:
 			      struct btrfs_file_extent_item);
 	/* are we inside the extent that was found? */
 	btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-	found_type = btrfs_key_type(&found_key);
+	found_type = found_key.type;
 	if (found_key.objectid != objectid ||
 	    found_type != BTRFS_EXTENT_DATA_KEY) {
 		/*
@@ -6482,25 +6544,21 @@ insert:
 
 		ret = 0;
 
-		existing = lookup_extent_mapping(em_tree, start, len);
-		if (existing && (existing->start > start ||
-		    existing->start + existing->len <= start)) {
+		existing = search_extent_mapping(em_tree, start, len);
+		/*
+		 * existing will always be non-NULL, since there must be
+		 * extent causing the -EEXIST.
+		 */
+		if (start >= extent_map_end(existing) ||
+		    start <= existing->start) {
+			/*
+			 * The existing extent map is the one nearest to
+			 * the [start, start + len) range which overlaps
+			 */
+			err = merge_extent_mapping(em_tree, existing,
+						   em, start);
 			free_extent_map(existing);
-			existing = NULL;
-		}
-		if (!existing) {
-			existing = lookup_extent_mapping(em_tree, em->start,
-							 em->len);
-			if (existing) {
-				err = merge_extent_mapping(em_tree, existing,
-							   em, start);
-				free_extent_map(existing);
-				if (err) {
-					free_extent_map(em);
-					em = NULL;
-				}
-			} else {
-				err = -EIO;
+			if (err) {
 				free_extent_map(em);
 				em = NULL;
 			}
@@ -7112,8 +7170,10 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 						       block_start, len,
 						       orig_block_len,
 						       ram_bytes, type);
-				if (IS_ERR(em))
+				if (IS_ERR(em)) {
+					ret = PTR_ERR(em);
 					goto unlock_err;
+				}
 			}
 
 			ret = btrfs_add_ordered_extent_dio(inode, start,
@@ -7188,45 +7248,277 @@ unlock_err:
 	return ret;
 }
 
-static void btrfs_endio_direct_read(struct bio *bio, int err)
+static inline int submit_dio_repair_bio(struct inode *inode, struct bio *bio,
+					int rw, int mirror_num)
 {
-	struct btrfs_dio_private *dip = bio->bi_private;
-	struct bio_vec *bvec;
-	struct inode *inode = dip->inode;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct bio *dio_bio;
-	u32 *csums = (u32 *)dip->csum;
+	int ret;
+
+	BUG_ON(rw & REQ_WRITE);
+
+	bio_get(bio);
+
+	ret = btrfs_bio_wq_end_io(root->fs_info, bio,
+				  BTRFS_WQ_ENDIO_DIO_REPAIR);
+	if (ret)
+		goto err;
+
+	ret = btrfs_map_bio(root, rw, bio, mirror_num, 0);
+err:
+	bio_put(bio);
+	return ret;
+}
+
+static int btrfs_check_dio_repairable(struct inode *inode,
+				      struct bio *failed_bio,
+				      struct io_failure_record *failrec,
+				      int failed_mirror)
+{
+	int num_copies;
+
+	num_copies = btrfs_num_copies(BTRFS_I(inode)->root->fs_info,
+				      failrec->logical, failrec->len);
+	if (num_copies == 1) {
+		/*
+		 * we only have a single copy of the data, so don't bother with
+		 * all the retry and error correction code that follows. no
+		 * matter what the error is, it is very likely to persist.
+		 */
+		pr_debug("Check DIO Repairable: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d\n",
+			 num_copies, failrec->this_mirror, failed_mirror);
+		return 0;
+	}
+
+	failrec->failed_mirror = failed_mirror;
+	failrec->this_mirror++;
+	if (failrec->this_mirror == failed_mirror)
+		failrec->this_mirror++;
+
+	if (failrec->this_mirror > num_copies) {
+		pr_debug("Check DIO Repairable: (fail) num_copies=%d, next_mirror %d, failed_mirror %d\n",
+			 num_copies, failrec->this_mirror, failed_mirror);
+		return 0;
+	}
+
+	return 1;
+}
+
+static int dio_read_error(struct inode *inode, struct bio *failed_bio,
+			  struct page *page, u64 start, u64 end,
+			  int failed_mirror, bio_end_io_t *repair_endio,
+			  void *repair_arg)
+{
+	struct io_failure_record *failrec;
+	struct bio *bio;
+	int isector;
+	int read_mode;
+	int ret;
+
+	BUG_ON(failed_bio->bi_rw & REQ_WRITE);
+
+	ret = btrfs_get_io_failure_record(inode, start, end, &failrec);
+	if (ret)
+		return ret;
+
+	ret = btrfs_check_dio_repairable(inode, failed_bio, failrec,
+					 failed_mirror);
+	if (!ret) {
+		free_io_failure(inode, failrec);
+		return -EIO;
+	}
+
+	if (failed_bio->bi_vcnt > 1)
+		read_mode = READ_SYNC | REQ_FAILFAST_DEV;
+	else
+		read_mode = READ_SYNC;
+
+	isector = start - btrfs_io_bio(failed_bio)->logical;
+	isector >>= inode->i_sb->s_blocksize_bits;
+	bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
+				      0, isector, repair_endio, repair_arg);
+	if (!bio) {
+		free_io_failure(inode, failrec);
+		return -EIO;
+	}
+
+	btrfs_debug(BTRFS_I(inode)->root->fs_info,
+		    "Repair DIO Read Error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d\n",
+		    read_mode, failrec->this_mirror, failrec->in_validation);
+
+	ret = submit_dio_repair_bio(inode, bio, read_mode,
+				    failrec->this_mirror);
+	if (ret) {
+		free_io_failure(inode, failrec);
+		bio_put(bio);
+	}
+
+	return ret;
+}
+
+struct btrfs_retry_complete {
+	struct completion done;
+	struct inode *inode;
+	u64 start;
+	int uptodate;
+};
+
+static void btrfs_retry_endio_nocsum(struct bio *bio, int err)
+{
+	struct btrfs_retry_complete *done = bio->bi_private;
+	struct bio_vec *bvec;
+	int i;
+
+	if (err)
+		goto end;
+
+	done->uptodate = 1;
+	bio_for_each_segment_all(bvec, bio, i)
+		clean_io_failure(done->inode, done->start, bvec->bv_page, 0);
+end:
+	complete(&done->done);
+	bio_put(bio);
+}
+
+static int __btrfs_correct_data_nocsum(struct inode *inode,
+				       struct btrfs_io_bio *io_bio)
+{
+	struct bio_vec *bvec;
+	struct btrfs_retry_complete done;
 	u64 start;
 	int i;
+	int ret;
+
+	start = io_bio->logical;
+	done.inode = inode;
+
+	bio_for_each_segment_all(bvec, &io_bio->bio, i) {
+try_again:
+		done.uptodate = 0;
+		done.start = start;
+		init_completion(&done.done);
+
+		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start,
+				     start + bvec->bv_len - 1,
+				     io_bio->mirror_num,
+				     btrfs_retry_endio_nocsum, &done);
+		if (ret)
+			return ret;
+
+		wait_for_completion(&done.done);
+
+		if (!done.uptodate) {
+			/* We might have another mirror, so try again */
+			goto try_again;
+		}
+
+		start += bvec->bv_len;
+	}
 
-	start = dip->logical_offset;
+	return 0;
+}
+
+static void btrfs_retry_endio(struct bio *bio, int err)
+{
+	struct btrfs_retry_complete *done = bio->bi_private;
+	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+	struct bio_vec *bvec;
+	int uptodate;
+	int ret;
+	int i;
+
+	if (err)
+		goto end;
+
+	uptodate = 1;
 	bio_for_each_segment_all(bvec, bio, i) {
-		if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
-			struct page *page = bvec->bv_page;
-			char *kaddr;
-			u32 csum = ~(u32)0;
-			unsigned long flags;
-
-			local_irq_save(flags);
-			kaddr = kmap_atomic(page);
-			csum = btrfs_csum_data(kaddr + bvec->bv_offset,
-					       csum, bvec->bv_len);
-			btrfs_csum_final(csum, (char *)&csum);
-			kunmap_atomic(kaddr);
-			local_irq_restore(flags);
-
-			flush_dcache_page(bvec->bv_page);
-			if (csum != csums[i]) {
-				btrfs_err(root->fs_info, "csum failed ino %llu off %llu csum %u expected csum %u",
-					  btrfs_ino(inode), start, csum,
-					  csums[i]);
-				err = -EIO;
-			}
+		ret = __readpage_endio_check(done->inode, io_bio, i,
+					     bvec->bv_page, 0,
+					     done->start, bvec->bv_len);
+		if (!ret)
+			clean_io_failure(done->inode, done->start,
+					 bvec->bv_page, 0);
+		else
+			uptodate = 0;
+	}
+
+	done->uptodate = uptodate;
+end:
+	complete(&done->done);
+	bio_put(bio);
+}
+
+static int __btrfs_subio_endio_read(struct inode *inode,
+				    struct btrfs_io_bio *io_bio, int err)
+{
+	struct bio_vec *bvec;
+	struct btrfs_retry_complete done;
+	u64 start;
+	u64 offset = 0;
+	int i;
+	int ret;
+
+	err = 0;
+	start = io_bio->logical;
+	done.inode = inode;
+
+	bio_for_each_segment_all(bvec, &io_bio->bio, i) {
+		ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page,
+					     0, start, bvec->bv_len);
+		if (likely(!ret))
+			goto next;
+try_again:
+		done.uptodate = 0;
+		done.start = start;
+		init_completion(&done.done);
+
+		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start,
+				     start + bvec->bv_len - 1,
+				     io_bio->mirror_num,
+				     btrfs_retry_endio, &done);
+		if (ret) {
+			err = ret;
+			goto next;
 		}
 
+		wait_for_completion(&done.done);
+
+		if (!done.uptodate) {
+			/* We might have another mirror, so try again */
+			goto try_again;
+		}
+next:
+		offset += bvec->bv_len;
 		start += bvec->bv_len;
 	}
 
+	return err;
+}
+
+static int btrfs_subio_endio_read(struct inode *inode,
+				  struct btrfs_io_bio *io_bio, int err)
+{
+	bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
+
+	if (skip_csum) {
+		if (unlikely(err))
+			return __btrfs_correct_data_nocsum(inode, io_bio);
+		else
+			return 0;
+	} else {
+		return __btrfs_subio_endio_read(inode, io_bio, err);
+	}
+}
+
+static void btrfs_endio_direct_read(struct bio *bio, int err)
+{
+	struct btrfs_dio_private *dip = bio->bi_private;
+	struct inode *inode = dip->inode;
+	struct bio *dio_bio;
+	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+
+	if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
+		err = btrfs_subio_endio_read(inode, io_bio, err);
+
 	unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
 		      dip->logical_offset + dip->bytes - 1);
 	dio_bio = dip->dio_bio;
@@ -7237,6 +7529,9 @@ static void btrfs_endio_direct_read(struct bio *bio, int err)
 	if (err)
 		clear_bit(BIO_UPTODATE, &dio_bio->bi_flags);
 	dio_end_io(dio_bio, err);
+
+	if (io_bio->end_io)
+		io_bio->end_io(io_bio, err);
 	bio_put(bio);
 }
 
@@ -7302,12 +7597,17 @@ static void btrfs_end_dio_bio(struct bio *bio, int err)
 {
 	struct btrfs_dio_private *dip = bio->bi_private;
 
+	if (err)
+		btrfs_warn(BTRFS_I(dip->inode)->root->fs_info,
+			   "direct IO failed ino %llu rw %lu sector %#Lx len %u err no %d",
+			   btrfs_ino(dip->inode), bio->bi_rw,
+			   (unsigned long long)bio->bi_iter.bi_sector,
+			   bio->bi_iter.bi_size, err);
+
+	if (dip->subio_endio)
+		err = dip->subio_endio(dip->inode, btrfs_io_bio(bio), err);
+
 	if (err) {
-		btrfs_err(BTRFS_I(dip->inode)->root->fs_info,
-			  "direct IO failed ino %llu rw %lu sector %#Lx len %u err no %d",
-		      btrfs_ino(dip->inode), bio->bi_rw,
-		      (unsigned long long)bio->bi_iter.bi_sector,
-		      bio->bi_iter.bi_size, err);
 		dip->errors = 1;
 
 		/*
@@ -7338,6 +7638,38 @@ static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
 	return btrfs_bio_alloc(bdev, first_sector, nr_vecs, gfp_flags);
 }
 
+static inline int btrfs_lookup_and_bind_dio_csum(struct btrfs_root *root,
+						 struct inode *inode,
+						 struct btrfs_dio_private *dip,
+						 struct bio *bio,
+						 u64 file_offset)
+{
+	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+	struct btrfs_io_bio *orig_io_bio = btrfs_io_bio(dip->orig_bio);
+	int ret;
+
+	/*
+	 * We load all the csum data we need when we submit
+	 * the first bio to reduce the csum tree search and
+	 * contention.
+	 */
+	if (dip->logical_offset == file_offset) {
+		ret = btrfs_lookup_bio_sums_dio(root, inode, dip->orig_bio,
+						file_offset);
+		if (ret)
+			return ret;
+	}
+
+	if (bio == dip->orig_bio)
+		return 0;
+
+	file_offset -= dip->logical_offset;
+	file_offset >>= inode->i_sb->s_blocksize_bits;
+	io_bio->csum = (u8 *)(((u32 *)orig_io_bio->csum) + file_offset);
+
+	return 0;
+}
+
 static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 					 int rw, u64 file_offset, int skip_sum,
 					 int async_submit)
@@ -7353,7 +7685,8 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 	bio_get(bio);
 
 	if (!write) {
-		ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
+		ret = btrfs_bio_wq_end_io(root->fs_info, bio,
+				BTRFS_WQ_ENDIO_DATA);
 		if (ret)
 			goto err;
 	}
@@ -7376,13 +7709,12 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 		ret = btrfs_csum_one_bio(root, inode, bio, file_offset, 1);
 		if (ret)
 			goto err;
-	} else if (!skip_sum) {
-		ret = btrfs_lookup_bio_sums_dio(root, inode, dip, bio,
-						file_offset);
+	} else {
+		ret = btrfs_lookup_and_bind_dio_csum(root, inode, dip, bio,
+						     file_offset);
 		if (ret)
 			goto err;
 	}
-
 map:
 	ret = btrfs_map_bio(root, rw, bio, 0, async_submit);
 err:
@@ -7403,7 +7735,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	u64 submit_len = 0;
 	u64 map_length;
 	int nr_pages = 0;
-	int ret = 0;
+	int ret;
 	int async_submit = 0;
 
 	map_length = orig_bio->bi_iter.bi_size;
@@ -7414,6 +7746,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 
 	if (map_length >= orig_bio->bi_iter.bi_size) {
 		bio = orig_bio;
+		dip->flags |= BTRFS_DIO_ORIG_BIO_SUBMITTED;
 		goto submit;
 	}
 
@@ -7430,12 +7763,13 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 
 	bio->bi_private = dip;
 	bio->bi_end_io = btrfs_end_dio_bio;
+	btrfs_io_bio(bio)->logical = file_offset;
 	atomic_inc(&dip->pending_bios);
 
 	while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
-		if (unlikely(map_length < submit_len + bvec->bv_len ||
+		if (map_length < submit_len + bvec->bv_len ||
 		    bio_add_page(bio, bvec->bv_page, bvec->bv_len,
-				 bvec->bv_offset) < bvec->bv_len)) {
+				 bvec->bv_offset) < bvec->bv_len) {
 			/*
 			 * inc the count before we submit the bio so
 			 * we know the end IO handler won't happen before
@@ -7464,6 +7798,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 				goto out_err;
 			bio->bi_private = dip;
 			bio->bi_end_io = btrfs_end_dio_bio;
+			btrfs_io_bio(bio)->logical = file_offset;
 
 			map_length = orig_bio->bi_iter.bi_size;
 			ret = btrfs_map_block(root->fs_info, rw,
@@ -7507,11 +7842,10 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_dio_private *dip;
 	struct bio *io_bio;
+	struct btrfs_io_bio *btrfs_bio;
 	int skip_sum;
-	int sum_len;
 	int write = rw & REQ_WRITE;
 	int ret = 0;
-	u16 csum_size;
 
 	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
@@ -7521,16 +7855,7 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
 		goto free_ordered;
 	}
 
-	if (!skip_sum && !write) {
-		csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
-		sum_len = dio_bio->bi_iter.bi_size >>
-			inode->i_sb->s_blocksize_bits;
-		sum_len *= csum_size;
-	} else {
-		sum_len = 0;
-	}
-
-	dip = kmalloc(sizeof(*dip) + sum_len, GFP_NOFS);
+	dip = kzalloc(sizeof(*dip), GFP_NOFS);
 	if (!dip) {
 		ret = -ENOMEM;
 		goto free_io_bio;
@@ -7542,20 +7867,25 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
 	dip->bytes = dio_bio->bi_iter.bi_size;
 	dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
 	io_bio->bi_private = dip;
-	dip->errors = 0;
 	dip->orig_bio = io_bio;
 	dip->dio_bio = dio_bio;
 	atomic_set(&dip->pending_bios, 0);
+	btrfs_bio = btrfs_io_bio(io_bio);
+	btrfs_bio->logical = file_offset;
 
-	if (write)
+	if (write) {
 		io_bio->bi_end_io = btrfs_endio_direct_write;
-	else
+	} else {
 		io_bio->bi_end_io = btrfs_endio_direct_read;
+		dip->subio_endio = btrfs_subio_endio_read;
+	}
 
 	ret = btrfs_submit_direct_hook(rw, dip, skip_sum);
 	if (!ret)
 		return;
 
+	if (btrfs_bio->end_io)
+		btrfs_bio->end_io(btrfs_bio, ret);
 free_io_bio:
 	bio_put(io_bio);
 
@@ -7652,8 +7982,8 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 		ret = btrfs_delalloc_reserve_space(inode, count);
 		if (ret)
 			goto out;
-	} else if (unlikely(test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
-				     &BTRFS_I(inode)->runtime_flags))) {
+	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
+				     &BTRFS_I(inode)->runtime_flags)) {
 		inode_dio_done(inode);
 		flags = DIO_LOCKING | DIO_SKIP_HOLES;
 		wakeup = false;
@@ -8173,6 +8503,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->last_sub_trans = 0;
 	ei->logged_trans = 0;
 	ei->delalloc_bytes = 0;
+	ei->defrag_bytes = 0;
 	ei->disk_i_size = 0;
 	ei->flags = 0;
 	ei->csum_bytes = 0;
@@ -8231,6 +8562,7 @@ void btrfs_destroy_inode(struct inode *inode)
 	WARN_ON(BTRFS_I(inode)->reserved_extents);
 	WARN_ON(BTRFS_I(inode)->delalloc_bytes);
 	WARN_ON(BTRFS_I(inode)->csum_bytes);
+	WARN_ON(BTRFS_I(inode)->defrag_bytes);
 
 	/*
 	 * This can happen where we create an inode, but somebody else also
@@ -8646,7 +8978,7 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput,
 		spin_unlock(&root->delalloc_lock);
 
 		work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
-		if (unlikely(!work)) {
+		if (!work) {
 			if (delay_iput)
 				btrfs_add_delayed_iput(inode);
 			else
@@ -8832,7 +9164,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	}
 	key.objectid = btrfs_ino(inode);
 	key.offset = 0;
-	btrfs_set_key_type(&key, BTRFS_EXTENT_DATA_KEY);
+	key.type = BTRFS_EXTENT_DATA_KEY;
 	datasize = btrfs_file_extent_calc_inline_size(name_len);
 	err = btrfs_insert_empty_item(trans, root, path, &key,
 				      datasize);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 8a8e29878c34..8d2b76e29d3b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -332,6 +332,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 			goto out_drop;
 
 	} else {
+		ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
+		if (ret && ret != -ENODATA)
+			goto out_drop;
 		ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
 	}
 
@@ -477,8 +480,7 @@ static noinline int create_subvol(struct inode *dir,
 	if (ret)
 		goto fail;
 
-	leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
-				      0, objectid, NULL, 0, 0, 0);
+	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
 		goto fail;
@@ -503,7 +505,7 @@ static noinline int create_subvol(struct inode *dir,
 	btrfs_set_stack_inode_generation(inode_item, 1);
 	btrfs_set_stack_inode_size(inode_item, 3);
 	btrfs_set_stack_inode_nlink(inode_item, 1);
-	btrfs_set_stack_inode_nbytes(inode_item, root->leafsize);
+	btrfs_set_stack_inode_nbytes(inode_item, root->nodesize);
 	btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
 
 	btrfs_set_root_flags(&root_item, 0);
@@ -535,7 +537,7 @@ static noinline int create_subvol(struct inode *dir,
 
 	key.objectid = objectid;
 	key.offset = 0;
-	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
+	key.type = BTRFS_ROOT_ITEM_KEY;
 	ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
 				&root_item);
 	if (ret)
@@ -711,6 +713,39 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	if (ret)
 		goto fail;
 
+	ret = btrfs_orphan_cleanup(pending_snapshot->snap);
+	if (ret)
+		goto fail;
+
+	/*
+	 * If orphan cleanup did remove any orphans, it means the tree was
+	 * modified and therefore the commit root is not the same as the
+	 * current root anymore. This is a problem, because send uses the
+	 * commit root and therefore can see inode items that don't exist
+	 * in the current root anymore, and for example make calls to
+	 * btrfs_iget, which will do tree lookups based on the current root
+	 * and not on the commit root. Those lookups will fail, returning a
+	 * -ESTALE error, and making send fail with that error. So make sure
+	 * a send does not see any orphans we have just removed, and that it
+	 * will see the same inodes regardless of whether a transaction
+	 * commit happened before it started (meaning that the commit root
+	 * will be the same as the current root) or not.
+	 */
+	if (readonly && pending_snapshot->snap->node !=
+	    pending_snapshot->snap->commit_root) {
+		trans = btrfs_join_transaction(pending_snapshot->snap);
+		if (IS_ERR(trans) && PTR_ERR(trans) != -ENOENT) {
+			ret = PTR_ERR(trans);
+			goto fail;
+		}
+		if (!IS_ERR(trans)) {
+			ret = btrfs_commit_transaction(trans,
+						       pending_snapshot->snap);
+			if (ret)
+				goto fail;
+		}
+	}
+
 	inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
@@ -882,7 +917,7 @@ out_unlock:
  * file you want to defrag, we return 0 to let you know to skip this
  * part of the file
  */
-static int check_defrag_in_cache(struct inode *inode, u64 offset, int thresh)
+static int check_defrag_in_cache(struct inode *inode, u64 offset, u32 thresh)
 {
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct extent_map *em = NULL;
@@ -917,7 +952,7 @@ static int check_defrag_in_cache(struct inode *inode, u64 offset, int thresh)
  */
 static int find_new_extents(struct btrfs_root *root,
 			    struct inode *inode, u64 newer_than,
-			    u64 *off, int thresh)
+			    u64 *off, u32 thresh)
 {
 	struct btrfs_path *path;
 	struct btrfs_key min_key;
@@ -936,12 +971,9 @@ static int find_new_extents(struct btrfs_root *root,
 	min_key.offset = *off;
 
 	while (1) {
-		path->keep_locks = 1;
 		ret = btrfs_search_forward(root, &min_key, path, newer_than);
 		if (ret != 0)
 			goto none;
-		path->keep_locks = 0;
-		btrfs_unlock_up_safe(path, 1);
 process_slot:
 		if (min_key.objectid != ino)
 			goto none;
@@ -1029,7 +1061,7 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em)
 	return ret;
 }
 
-static int should_defrag_range(struct inode *inode, u64 start, int thresh,
+static int should_defrag_range(struct inode *inode, u64 start, u32 thresh,
 			       u64 *last_len, u64 *skip, u64 *defrag_end,
 			       int compress)
 {
@@ -1259,7 +1291,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 	int ret;
 	int defrag_count = 0;
 	int compress_type = BTRFS_COMPRESS_ZLIB;
-	int extent_thresh = range->extent_thresh;
+	u32 extent_thresh = range->extent_thresh;
 	unsigned long max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
 	unsigned long cluster = max_cluster;
 	u64 new_align = ~((u64)128 * 1024 - 1);
@@ -1335,8 +1367,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 		inode->i_mapping->writeback_index = i;
 
 	while (i <= last_index && defrag_count < max_to_defrag &&
-	       (i < (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
-		PAGE_CACHE_SHIFT)) {
+	       (i < DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE))) {
 		/*
 		 * make sure we stop running if someone unmounts
 		 * the FS
@@ -1359,7 +1390,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
 			 * the should_defrag function tells us how much to skip
 			 * bump our counter by the suggested amount
 			 */
-			next = (skip + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+			next = DIV_ROUND_UP(skip, PAGE_CACHE_SIZE);
 			i = max(i + 1, next);
 			continue;
 		}
@@ -1554,7 +1585,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		goto out_free;
 	}
 
-	old_size = device->total_bytes;
+	old_size = btrfs_device_get_total_bytes(device);
 
 	if (mod < 0) {
 		if (new_size > old_size) {
@@ -2089,8 +2120,6 @@ static noinline int search_ioctl(struct inode *inode,
 	key.type = sk->min_type;
 	key.offset = sk->min_offset;
 
-	path->keep_locks = 1;
-
 	while (1) {
 		ret = btrfs_search_forward(root, &key, path, sk->min_transid);
 		if (ret != 0) {
@@ -2423,9 +2452,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		goto out_dput;
 	}
 
-	err = d_invalidate(dentry);
-	if (err)
-		goto out_unlock;
+	d_invalidate(dentry);
 
 	down_write(&root->fs_info->subvol_sem);
 
@@ -2510,7 +2537,6 @@ out_release:
 	btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
 out_up_write:
 	up_write(&root->fs_info->subvol_sem);
-out_unlock:
 	if (err) {
 		spin_lock(&dest->root_item_lock);
 		root_flags = btrfs_root_flags(&dest->root_item);
@@ -2526,9 +2552,9 @@ out_unlock:
 		ASSERT(dest->send_in_progress == 0);
 
 		/* the last ref */
-		if (dest->cache_inode) {
-			iput(dest->cache_inode);
-			dest->cache_inode = NULL;
+		if (dest->ino_cache_inode) {
+			iput(dest->ino_cache_inode);
+			dest->ino_cache_inode = NULL;
 		}
 	}
 out_dput:
@@ -2634,6 +2660,9 @@ static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg)
 	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
 	ret = btrfs_init_new_device(root, vol_args->name);
 
+	if (!ret)
+		btrfs_info(root->fs_info, "disk added %s",vol_args->name);
+
 	kfree(vol_args);
 out:
 	mutex_unlock(&root->fs_info->volume_mutex);
@@ -2673,6 +2702,9 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	mutex_unlock(&root->fs_info->volume_mutex);
 	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
 
+	if (!ret)
+		btrfs_info(root->fs_info, "disk deleted %s",vol_args->name);
+
 out:
 	kfree(vol_args);
 err_drop:
@@ -2737,8 +2769,8 @@ static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg)
 	}
 
 	di_args->devid = dev->devid;
-	di_args->bytes_used = dev->bytes_used;
-	di_args->total_bytes = dev->total_bytes;
+	di_args->bytes_used = btrfs_device_get_bytes_used(dev);
+	di_args->total_bytes = btrfs_device_get_total_bytes(dev);
 	memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid));
 	if (dev->name) {
 		struct rcu_string *name;
@@ -3164,7 +3196,7 @@ static void clone_update_extent_map(struct inode *inode,
 					em->start + em->len - 1, 0);
 	}
 
-	if (unlikely(ret))
+	if (ret)
 		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 			&BTRFS_I(inode)->runtime_flags);
 }
@@ -3199,7 +3231,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 	u64 last_dest_end = destoff;
 
 	ret = -ENOMEM;
-	buf = vmalloc(btrfs_level_size(root, 0));
+	buf = vmalloc(root->nodesize);
 	if (!buf)
 		return ret;
 
@@ -3252,11 +3284,11 @@ process_slot:
 		slot = path->slots[0];
 
 		btrfs_item_key_to_cpu(leaf, &key, slot);
-		if (btrfs_key_type(&key) > BTRFS_EXTENT_DATA_KEY ||
+		if (key.type > BTRFS_EXTENT_DATA_KEY ||
 		    key.objectid != btrfs_ino(src))
 			break;
 
-		if (btrfs_key_type(&key) == BTRFS_EXTENT_DATA_KEY) {
+		if (key.type == BTRFS_EXTENT_DATA_KEY) {
 			struct btrfs_file_extent_item *extent;
 			int type;
 			u32 size;
@@ -5283,6 +5315,12 @@ long btrfs_ioctl(struct file *file, unsigned int
 		if (ret)
 			return ret;
 		ret = btrfs_sync_fs(file->f_dentry->d_sb, 1);
+		/*
+		 * The transaction thread may want to do more work,
+		 * namely it pokes the cleaner ktread that will start
+		 * processing uncleaned subvols.
+		 */
+		wake_up_process(root->fs_info->transaction_kthread);
 		return ret;
 	}
 	case BTRFS_IOC_START_SYNC:
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index dfad8514f0da..78285f30909e 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -266,8 +266,7 @@ static int lzo_decompress_biovec(struct list_head *ws,
 	char *data_in;
 	unsigned long page_in_index = 0;
 	unsigned long page_out_index = 0;
-	unsigned long total_pages_in = (srclen + PAGE_CACHE_SIZE - 1) /
-					PAGE_CACHE_SIZE;
+	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_CACHE_SIZE);
 	unsigned long buf_start;
 	unsigned long buf_offset = 0;
 	unsigned long bytes;
diff --git a/fs/btrfs/orphan.c b/fs/btrfs/orphan.c
index 65793edb38ca..47767d5b8f0b 100644
--- a/fs/btrfs/orphan.c
+++ b/fs/btrfs/orphan.c
@@ -27,7 +27,7 @@ int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
 	int ret = 0;
 
 	key.objectid = BTRFS_ORPHAN_OBJECTID;
-	btrfs_set_key_type(&key, BTRFS_ORPHAN_ITEM_KEY);
+	key.type = BTRFS_ORPHAN_ITEM_KEY;
 	key.offset = offset;
 
 	path = btrfs_alloc_path();
@@ -48,7 +48,7 @@ int btrfs_del_orphan_item(struct btrfs_trans_handle *trans,
 	int ret = 0;
 
 	key.objectid = BTRFS_ORPHAN_OBJECTID;
-	btrfs_set_key_type(&key, BTRFS_ORPHAN_ITEM_KEY);
+	key.type = BTRFS_ORPHAN_ITEM_KEY;
 	key.offset = offset;
 
 	path = btrfs_alloc_path();
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 9626b4ad3b9a..647ab12fdf5d 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -195,7 +195,7 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 	for (i = 0 ; i < nr ; i++) {
 		item = btrfs_item_nr(i);
 		btrfs_item_key_to_cpu(l, &key, i);
-		type = btrfs_key_type(&key);
+		type = key.type;
 		printk(KERN_INFO "\titem %d key (%llu %u %llu) itemoff %d "
 		       "itemsize %d\n",
 			i, key.objectid, type, key.offset,
@@ -336,7 +336,6 @@ void btrfs_print_tree(struct btrfs_root *root, struct extent_buffer *c)
 	for (i = 0; i < nr; i++) {
 		struct extent_buffer *next = read_tree_block(root,
 					btrfs_node_blockptr(c, i),
-					btrfs_level_size(root, level - 1),
 					btrfs_node_ptr_generation(c, i));
 		if (btrfs_is_leaf(next) &&
 		   level != 1)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index ded5c601d916..48b60dbf807f 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -539,10 +539,9 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 	struct btrfs_key key;
 
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &quota_root->state)))
+	if (btrfs_test_is_dummy_root(quota_root))
 		return 0;
-#endif
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -551,9 +550,15 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_QGROUP_INFO_KEY;
 	key.offset = qgroupid;
 
+	/*
+	 * Avoid a transaction abort by catching -EEXIST here. In that
+	 * case, we proceed by re-initializing the existing structure
+	 * on disk.
+	 */
+
 	ret = btrfs_insert_empty_item(trans, quota_root, path, &key,
 				      sizeof(*qgroup_info));
-	if (ret)
+	if (ret && ret != -EEXIST)
 		goto out;
 
 	leaf = path->nodes[0];
@@ -572,7 +577,7 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_QGROUP_LIMIT_KEY;
 	ret = btrfs_insert_empty_item(trans, quota_root, path, &key,
 				      sizeof(*qgroup_limit));
-	if (ret)
+	if (ret && ret != -EEXIST)
 		goto out;
 
 	leaf = path->nodes[0];
@@ -692,10 +697,9 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
 	int ret;
 	int slot;
 
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+	if (btrfs_test_is_dummy_root(root))
 		return 0;
-#endif
+
 	key.objectid = 0;
 	key.type = BTRFS_QGROUP_INFO_KEY;
 	key.offset = qgroup->qgroupid;
@@ -1335,6 +1339,8 @@ int btrfs_qgroup_record_ref(struct btrfs_trans_handle *trans,
 	INIT_LIST_HEAD(&oper->elem.list);
 	oper->elem.seq = 0;
 
+	trace_btrfs_qgroup_record_ref(oper);
+
 	if (type == BTRFS_QGROUP_OPER_SUB_SUBTREE) {
 		/*
 		 * If any operation for this bytenr/ref_root combo
@@ -2077,6 +2083,8 @@ static int btrfs_qgroup_account(struct btrfs_trans_handle *trans,
 
 	ASSERT(is_fstree(oper->ref_root));
 
+	trace_btrfs_qgroup_account(oper);
+
 	switch (oper->type) {
 	case BTRFS_QGROUP_OPER_ADD_EXCL:
 	case BTRFS_QGROUP_OPER_SUB_EXCL:
@@ -2237,7 +2245,6 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 	if (srcid) {
 		struct btrfs_root *srcroot;
 		struct btrfs_key srckey;
-		int srcroot_level;
 
 		srckey.objectid = srcid;
 		srckey.type = BTRFS_ROOT_ITEM_KEY;
@@ -2249,8 +2256,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		}
 
 		rcu_read_lock();
-		srcroot_level = btrfs_header_level(srcroot->node);
-		level_size = btrfs_level_size(srcroot, srcroot_level);
+		level_size = srcroot->nodesize;
 		rcu_read_unlock();
 	}
 
@@ -2566,7 +2572,7 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 		    found.type != BTRFS_METADATA_ITEM_KEY)
 			continue;
 		if (found.type == BTRFS_METADATA_ITEM_KEY)
-			num_bytes = fs_info->extent_root->leafsize;
+			num_bytes = fs_info->extent_root->nodesize;
 		else
 			num_bytes = found.offset;
 
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 0a6b6e4bcbb9..6a41631cb959 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -912,7 +912,7 @@ static struct page *page_in_rbio(struct btrfs_raid_bio *rbio,
 static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes)
 {
 	unsigned long nr = stripe_len * nr_stripes;
-	return (nr + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	return DIV_ROUND_UP(nr, PAGE_CACHE_SIZE);
 }
 
 /*
@@ -1442,7 +1442,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 	struct btrfs_bio *bbio = rbio->bbio;
 	struct bio_list bio_list;
 	int ret;
-	int nr_pages = (rbio->stripe_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
 	int pagenr;
 	int stripe;
 	struct bio *bio;
@@ -1725,7 +1725,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 	int pagenr, stripe;
 	void **pointers;
 	int faila = -1, failb = -1;
-	int nr_pages = (rbio->stripe_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
 	struct page *page;
 	int err;
 	int i;
@@ -1940,7 +1940,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 	struct btrfs_bio *bbio = rbio->bbio;
 	struct bio_list bio_list;
 	int ret;
-	int nr_pages = (rbio->stripe_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
 	int pagenr;
 	int stripe;
 	struct bio *bio;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 20408c6b665a..b63ae20618fb 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -347,7 +347,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	if (!re)
 		return NULL;
 
-	blocksize = btrfs_level_size(root, level);
+	blocksize = root->nodesize;
 	re->logical = logical;
 	re->blocksize = blocksize;
 	re->top = *top;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 65245a07275b..74257d6436ad 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -736,7 +736,8 @@ again:
 		err = ret;
 		goto out;
 	}
-	BUG_ON(!ret || !path1->slots[0]);
+	ASSERT(ret);
+	ASSERT(path1->slots[0]);
 
 	path1->slots[0]--;
 
@@ -746,10 +747,10 @@ again:
 		 * the backref was added previously when processing
 		 * backref of type BTRFS_TREE_BLOCK_REF_KEY
 		 */
-		BUG_ON(!list_is_singular(&cur->upper));
+		ASSERT(list_is_singular(&cur->upper));
 		edge = list_entry(cur->upper.next, struct backref_edge,
 				  list[LOWER]);
-		BUG_ON(!list_empty(&edge->list[UPPER]));
+		ASSERT(list_empty(&edge->list[UPPER]));
 		exist = edge->node[UPPER];
 		/*
 		 * add the upper level block to pending list if we need
@@ -831,7 +832,7 @@ again:
 					cur->cowonly = 1;
 			}
 #else
-		BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
+		ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY);
 		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) {
 #endif
 			if (key.objectid == key.offset) {
@@ -840,7 +841,7 @@ again:
 				 * backref of this type.
 				 */
 				root = find_reloc_root(rc, cur->bytenr);
-				BUG_ON(!root);
+				ASSERT(root);
 				cur->root = root;
 				break;
 			}
@@ -868,7 +869,7 @@ again:
 			} else {
 				upper = rb_entry(rb_node, struct backref_node,
 						 rb_node);
-				BUG_ON(!upper->checked);
+				ASSERT(upper->checked);
 				INIT_LIST_HEAD(&edge->list[UPPER]);
 			}
 			list_add_tail(&edge->list[LOWER], &cur->upper);
@@ -892,7 +893,7 @@ again:
 
 		if (btrfs_root_level(&root->root_item) == cur->level) {
 			/* tree root */
-			BUG_ON(btrfs_root_bytenr(&root->root_item) !=
+			ASSERT(btrfs_root_bytenr(&root->root_item) ==
 			       cur->bytenr);
 			if (should_ignore_root(root))
 				list_add(&cur->list, &useless);
@@ -927,7 +928,7 @@ again:
 		need_check = true;
 		for (; level < BTRFS_MAX_LEVEL; level++) {
 			if (!path2->nodes[level]) {
-				BUG_ON(btrfs_root_bytenr(&root->root_item) !=
+				ASSERT(btrfs_root_bytenr(&root->root_item) ==
 				       lower->bytenr);
 				if (should_ignore_root(root))
 					list_add(&lower->list, &useless);
@@ -977,12 +978,15 @@ again:
 					need_check = false;
 					list_add_tail(&edge->list[UPPER],
 						      &list);
-				} else
+				} else {
+					if (upper->checked)
+						need_check = true;
 					INIT_LIST_HEAD(&edge->list[UPPER]);
+				}
 			} else {
 				upper = rb_entry(rb_node, struct backref_node,
 						 rb_node);
-				BUG_ON(!upper->checked);
+				ASSERT(upper->checked);
 				INIT_LIST_HEAD(&edge->list[UPPER]);
 				if (!upper->owner)
 					upper->owner = btrfs_header_owner(eb);
@@ -1026,7 +1030,7 @@ next:
 	 * everything goes well, connect backref nodes and insert backref nodes
 	 * into the cache.
 	 */
-	BUG_ON(!node->checked);
+	ASSERT(node->checked);
 	cowonly = node->cowonly;
 	if (!cowonly) {
 		rb_node = tree_insert(&cache->rb_root, node->bytenr,
@@ -1062,8 +1066,21 @@ next:
 			continue;
 		}
 
-		BUG_ON(!upper->checked);
-		BUG_ON(cowonly != upper->cowonly);
+		if (!upper->checked) {
+			/*
+			 * Still want to blow up for developers since this is a
+			 * logic bug.
+			 */
+			ASSERT(0);
+			err = -EINVAL;
+			goto out;
+		}
+		if (cowonly != upper->cowonly) {
+			ASSERT(0);
+			err = -EINVAL;
+			goto out;
+		}
+
 		if (!cowonly) {
 			rb_node = tree_insert(&cache->rb_root, upper->bytenr,
 					      &upper->rb_node);
@@ -1086,7 +1103,7 @@ next:
 	while (!list_empty(&useless)) {
 		upper = list_entry(useless.next, struct backref_node, list);
 		list_del_init(&upper->list);
-		BUG_ON(!list_empty(&upper->upper));
+		ASSERT(list_empty(&upper->upper));
 		if (upper == node)
 			node = NULL;
 		if (upper->lowest) {
@@ -1119,29 +1136,45 @@ out:
 	if (err) {
 		while (!list_empty(&useless)) {
 			lower = list_entry(useless.next,
-					   struct backref_node, upper);
-			list_del_init(&lower->upper);
+					   struct backref_node, list);
+			list_del_init(&lower->list);
 		}
-		upper = node;
-		INIT_LIST_HEAD(&list);
-		while (upper) {
-			if (RB_EMPTY_NODE(&upper->rb_node)) {
-				list_splice_tail(&upper->upper, &list);
-				free_backref_node(cache, upper);
-			}
-
-			if (list_empty(&list))
-				break;
-
-			edge = list_entry(list.next, struct backref_edge,
-					  list[LOWER]);
+		while (!list_empty(&list)) {
+			edge = list_first_entry(&list, struct backref_edge,
+						list[UPPER]);
+			list_del(&edge->list[UPPER]);
 			list_del(&edge->list[LOWER]);
+			lower = edge->node[LOWER];
 			upper = edge->node[UPPER];
 			free_backref_edge(cache, edge);
+
+			/*
+			 * Lower is no longer linked to any upper backref nodes
+			 * and isn't in the cache, we can free it ourselves.
+			 */
+			if (list_empty(&lower->upper) &&
+			    RB_EMPTY_NODE(&lower->rb_node))
+				list_add(&lower->list, &useless);
+
+			if (!RB_EMPTY_NODE(&upper->rb_node))
+				continue;
+
+			/* Add this guy's upper edges to the list to proces */
+			list_for_each_entry(edge, &upper->upper, list[LOWER])
+				list_add_tail(&edge->list[UPPER], &list);
+			if (list_empty(&upper->upper))
+				list_add(&upper->list, &useless);
+		}
+
+		while (!list_empty(&useless)) {
+			lower = list_entry(useless.next,
+					   struct backref_node, list);
+			list_del_init(&lower->list);
+			free_backref_node(cache, lower);
 		}
 		return ERR_PTR(err);
 	}
-	BUG_ON(node && node->detached);
+	ASSERT(!node || !node->detached);
 	return node;
 }
 
@@ -1787,7 +1820,7 @@ again:
 			btrfs_node_key_to_cpu(parent, next_key, slot + 1);
 
 		old_bytenr = btrfs_node_blockptr(parent, slot);
-		blocksize = btrfs_level_size(dest, level - 1);
+		blocksize = dest->nodesize;
 		old_ptr_gen = btrfs_node_ptr_generation(parent, slot);
 
 		if (level <= max_level) {
@@ -1813,8 +1846,7 @@ again:
 				break;
 			}
 
-			eb = read_tree_block(dest, old_bytenr, blocksize,
-					     old_ptr_gen);
+			eb = read_tree_block(dest, old_bytenr, old_ptr_gen);
 			if (!eb || !extent_buffer_uptodate(eb)) {
 				ret = (!eb) ? -ENOMEM : -EIO;
 				free_extent_buffer(eb);
@@ -1944,7 +1976,6 @@ int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path,
 	u64 bytenr;
 	u64 ptr_gen = 0;
 	u64 last_snapshot;
-	u32 blocksize;
 	u32 nritems;
 
 	last_snapshot = btrfs_root_last_snapshot(&root->root_item);
@@ -1970,8 +2001,7 @@ int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path,
 		}
 
 		bytenr = btrfs_node_blockptr(eb, path->slots[i]);
-		blocksize = btrfs_level_size(root, i - 1);
-		eb = read_tree_block(root, bytenr, blocksize, ptr_gen);
+		eb = read_tree_block(root, bytenr, ptr_gen);
 		if (!eb || !extent_buffer_uptodate(eb)) {
 			free_extent_buffer(eb);
 			return -EIO;
@@ -2316,7 +2346,7 @@ void free_reloc_roots(struct list_head *list)
 }
 
 static noinline_for_stack
-int merge_reloc_roots(struct reloc_control *rc)
+void merge_reloc_roots(struct reloc_control *rc)
 {
 	struct btrfs_root *root;
 	struct btrfs_root *reloc_root;
@@ -2397,7 +2427,6 @@ out:
 	}
 
 	BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root));
-	return ret;
 }
 
 static void free_block_list(struct rb_root *blocks)
@@ -2544,8 +2573,7 @@ u64 calcu_metadata_size(struct reloc_control *rc,
 			if (next->processed && (reserve || next != node))
 				break;
 
-			num_bytes += btrfs_level_size(rc->extent_root,
-						      next->level);
+			num_bytes += rc->extent_root->nodesize;
 
 			if (list_empty(&next->upper))
 				break;
@@ -2679,9 +2707,9 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 				goto next;
 		}
 
-		blocksize = btrfs_level_size(root, node->level);
+		blocksize = root->nodesize;
 		generation = btrfs_node_ptr_generation(upper->eb, slot);
-		eb = read_tree_block(root, bytenr, blocksize, generation);
+		eb = read_tree_block(root, bytenr, generation);
 		if (!eb || !extent_buffer_uptodate(eb)) {
 			free_extent_buffer(eb);
 			err = -EIO;
@@ -2789,7 +2817,7 @@ static void __mark_block_processed(struct reloc_control *rc,
 	u32 blocksize;
 	if (node->level == 0 ||
 	    in_block_group(node->bytenr, rc->block_group)) {
-		blocksize = btrfs_level_size(rc->extent_root, node->level);
+		blocksize = rc->extent_root->nodesize;
 		mark_block_processed(rc, node->bytenr, blocksize);
 	}
 	node->processed = 1;
@@ -2843,7 +2871,7 @@ static int get_tree_block_key(struct reloc_control *rc,
 
 	BUG_ON(block->key_ready);
 	eb = read_tree_block(rc->extent_root, block->bytenr,
-			     block->key.objectid, block->key.offset);
+			     block->key.offset);
 	if (!eb || !extent_buffer_uptodate(eb)) {
 		free_extent_buffer(eb);
 		return -EIO;
@@ -2858,20 +2886,6 @@ static int get_tree_block_key(struct reloc_control *rc,
 	return 0;
 }
 
-static int reada_tree_block(struct reloc_control *rc,
-			    struct tree_block *block)
-{
-	BUG_ON(block->key_ready);
-	if (block->key.type == BTRFS_METADATA_ITEM_KEY)
-		readahead_tree_block(rc->extent_root, block->bytenr,
-				     block->key.objectid,
-				     rc->extent_root->leafsize);
-	else
-		readahead_tree_block(rc->extent_root, block->bytenr,
-				     block->key.objectid, block->key.offset);
-	return 0;
-}
-
 /*
  * helper function to relocate a tree block
  */
@@ -2951,7 +2965,8 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 	while (rb_node) {
 		block = rb_entry(rb_node, struct tree_block, rb_node);
 		if (!block->key_ready)
-			reada_tree_block(rc, block);
+			readahead_tree_block(rc->extent_root, block->bytenr,
+					block->key.objectid);
 		rb_node = rb_next(rb_node);
 	}
 
@@ -3313,7 +3328,7 @@ static int add_tree_block(struct reloc_control *rc,
 		return -ENOMEM;
 
 	block->bytenr = extent_key->objectid;
-	block->key.objectid = rc->extent_root->leafsize;
+	block->key.objectid = rc->extent_root->nodesize;
 	block->key.offset = generation;
 	block->level = level;
 	block->key_ready = 0;
@@ -3640,7 +3655,7 @@ int add_data_references(struct reloc_control *rc,
 	struct btrfs_extent_inline_ref *iref;
 	unsigned long ptr;
 	unsigned long end;
-	u32 blocksize = btrfs_level_size(rc->extent_root, 0);
+	u32 blocksize = rc->extent_root->nodesize;
 	int ret = 0;
 	int err = 0;
 
@@ -3783,7 +3798,7 @@ next:
 		}
 
 		if (key.type == BTRFS_METADATA_ITEM_KEY &&
-		    key.objectid + rc->extent_root->leafsize <=
+		    key.objectid + rc->extent_root->nodesize <=
 		    rc->search_start) {
 			path->slots[0]++;
 			goto next;
@@ -3801,7 +3816,7 @@ next:
 				rc->search_start = key.objectid + key.offset;
 			else
 				rc->search_start = key.objectid +
-					rc->extent_root->leafsize;
+					rc->extent_root->nodesize;
 			memcpy(extent_key, &key, sizeof(key));
 			return 0;
 		}
@@ -4096,7 +4111,6 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans,
 	btrfs_set_inode_flags(leaf, item, BTRFS_INODE_NOCOMPRESS |
 					  BTRFS_INODE_PREALLOC);
 	btrfs_mark_buffer_dirty(leaf);
-	btrfs_release_path(path);
 out:
 	btrfs_free_path(path);
 	return ret;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index f4a41f37be22..efa083113827 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -137,7 +137,6 @@ struct scrub_ctx {
 	int			pages_per_rd_bio;
 	u32			sectorsize;
 	u32			nodesize;
-	u32			leafsize;
 
 	int			is_dev_replace;
 	struct scrub_wr_ctx	wr_ctx;
@@ -178,17 +177,12 @@ struct scrub_copy_nocow_ctx {
 struct scrub_warning {
 	struct btrfs_path	*path;
 	u64			extent_item_size;
-	char			*scratch_buf;
-	char			*msg_buf;
 	const char		*errstr;
 	sector_t		sector;
 	u64			logical;
 	struct btrfs_device	*dev;
-	int			msg_bufsize;
-	int			scratch_bufsize;
 };
 
-
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx);
 static void scrub_pending_bio_dec(struct scrub_ctx *sctx);
 static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx);
@@ -438,7 +432,6 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 	}
 	sctx->first_free = 0;
 	sctx->nodesize = dev->dev_root->nodesize;
-	sctx->leafsize = dev->dev_root->leafsize;
 	sctx->sectorsize = dev->dev_root->sectorsize;
 	atomic_set(&sctx->bios_in_flight, 0);
 	atomic_set(&sctx->workers_pending, 0);
@@ -553,7 +546,6 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 	u64 ref_root;
 	u32 item_size;
 	u8 ref_level;
-	const int bufsize = 4096;
 	int ret;
 
 	WARN_ON(sblock->page_count < 1);
@@ -561,18 +553,13 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 	fs_info = sblock->sctx->dev_root->fs_info;
 
 	path = btrfs_alloc_path();
+	if (!path)
+		return;
 
-	swarn.scratch_buf = kmalloc(bufsize, GFP_NOFS);
-	swarn.msg_buf = kmalloc(bufsize, GFP_NOFS);
 	swarn.sector = (sblock->pagev[0]->physical) >> 9;
 	swarn.logical = sblock->pagev[0]->logical;
 	swarn.errstr = errstr;
 	swarn.dev = NULL;
-	swarn.msg_bufsize = bufsize;
-	swarn.scratch_bufsize = bufsize;
-
-	if (!path || !swarn.scratch_buf || !swarn.msg_buf)
-		goto out;
 
 	ret = extent_from_logical(fs_info, swarn.logical, path, &found_key,
 				  &flags);
@@ -613,8 +600,6 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 
 out:
 	btrfs_free_path(path);
-	kfree(swarn.scratch_buf);
-	kfree(swarn.msg_buf);
 }
 
 static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
@@ -681,9 +666,9 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
 			ret = -EIO;
 			goto out;
 		}
-		fs_info = BTRFS_I(inode)->root->fs_info;
-		ret = repair_io_failure(fs_info, offset, PAGE_SIZE,
+		ret = repair_io_failure(inode, offset, PAGE_SIZE,
 					fixup->logical, page,
+					offset - page_offset(page),
 					fixup->mirror_num);
 		unlock_page(page);
 		corrected = !ret;
@@ -1361,6 +1346,16 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
 	return;
 }
 
+static inline int scrub_check_fsid(u8 fsid[],
+				   struct scrub_page *spage)
+{
+	struct btrfs_fs_devices *fs_devices = spage->dev->fs_devices;
+	int ret;
+
+	ret = memcmp(fsid, fs_devices->fsid, BTRFS_UUID_SIZE);
+	return !ret;
+}
+
 static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
 					 struct scrub_block *sblock,
 					 int is_metadata, int have_csum,
@@ -1380,7 +1375,7 @@ static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
 		h = (struct btrfs_header *)mapped_buffer;
 
 		if (sblock->pagev[0]->logical != btrfs_stack_header_bytenr(h) ||
-		    memcmp(h->fsid, fs_info->fsid, BTRFS_UUID_SIZE) ||
+		    !scrub_check_fsid(h->fsid, sblock->pagev[0]) ||
 		    memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid,
 			   BTRFS_UUID_SIZE)) {
 			sblock->header_error = 1;
@@ -1751,14 +1746,13 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
 	if (sblock->pagev[0]->generation != btrfs_stack_header_generation(h))
 		++fail;
 
-	if (memcmp(h->fsid, fs_info->fsid, BTRFS_UUID_SIZE))
+	if (!scrub_check_fsid(h->fsid, sblock->pagev[0]))
 		++fail;
 
 	if (memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid,
 		   BTRFS_UUID_SIZE))
 		++fail;
 
-	WARN_ON(sctx->nodesize != sctx->leafsize);
 	len = sctx->nodesize - BTRFS_CSUM_SIZE;
 	mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE;
 	p = ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE;
@@ -1791,8 +1785,6 @@ static int scrub_checksum_super(struct scrub_block *sblock)
 {
 	struct btrfs_super_block *s;
 	struct scrub_ctx *sctx = sblock->sctx;
-	struct btrfs_root *root = sctx->dev_root;
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	u8 calculated_csum[BTRFS_CSUM_SIZE];
 	u8 on_disk_csum[BTRFS_CSUM_SIZE];
 	struct page *page;
@@ -1817,7 +1809,7 @@ static int scrub_checksum_super(struct scrub_block *sblock)
 	if (sblock->pagev[0]->generation != btrfs_super_generation(s))
 		++fail_gen;
 
-	if (memcmp(s->fsid, fs_info->fsid, BTRFS_UUID_SIZE))
+	if (!scrub_check_fsid(s->fsid, sblock->pagev[0]))
 		++fail_cor;
 
 	len = BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE;
@@ -2196,7 +2188,6 @@ static int scrub_extent(struct scrub_ctx *sctx, u64 logical, u64 len,
 		sctx->stat.data_bytes_scrubbed += len;
 		spin_unlock(&sctx->stat_lock);
 	} else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
-		WARN_ON(sctx->nodesize != sctx->leafsize);
 		blocksize = sctx->nodesize;
 		spin_lock(&sctx->stat_lock);
 		sctx->stat.tree_extents_scrubbed++;
@@ -2487,7 +2478,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 			btrfs_item_key_to_cpu(l, &key, slot);
 
 			if (key.type == BTRFS_METADATA_ITEM_KEY)
-				bytes = root->leafsize;
+				bytes = root->nodesize;
 			else
 				bytes = key.offset;
 
@@ -2714,7 +2705,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		if (found_key.objectid != scrub_dev->devid)
 			break;
 
-		if (btrfs_key_type(&found_key) != BTRFS_DEV_EXTENT_KEY)
+		if (found_key.type != BTRFS_DEV_EXTENT_KEY)
 			break;
 
 		if (found_key.offset >= end)
@@ -2828,11 +2819,16 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx,
 	if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
 		return -EIO;
 
-	gen = root->fs_info->last_trans_committed;
+	/* Seed devices of a new filesystem has their own generation. */
+	if (scrub_dev->fs_devices != root->fs_info->fs_devices)
+		gen = scrub_dev->generation;
+	else
+		gen = root->fs_info->last_trans_committed;
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
 		bytenr = btrfs_sb_offset(i);
-		if (bytenr + BTRFS_SUPER_INFO_SIZE > scrub_dev->total_bytes)
+		if (bytenr + BTRFS_SUPER_INFO_SIZE >
+		    scrub_dev->commit_total_bytes)
 			break;
 
 		ret = scrub_pages(sctx, bytenr, BTRFS_SUPER_INFO_SIZE, bytenr,
@@ -2910,17 +2906,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	if (btrfs_fs_closing(fs_info))
 		return -EINVAL;
 
-	/*
-	 * check some assumptions
-	 */
-	if (fs_info->chunk_root->nodesize != fs_info->chunk_root->leafsize) {
-		btrfs_err(fs_info,
-			   "scrub: size assumption nodesize == leafsize (%d == %d) fails",
-		       fs_info->chunk_root->nodesize,
-		       fs_info->chunk_root->leafsize);
-		return -EINVAL;
-	}
-
 	if (fs_info->chunk_root->nodesize > BTRFS_STRIPE_LEN) {
 		/*
 		 * in this case scrub is unable to calculate the checksum
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 6528aa662181..874828dd0a86 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -515,7 +515,8 @@ static int write_buf(struct file *filp, const void *buf, u32 len, loff_t *off)
 	set_fs(KERNEL_DS);
 
 	while (pos < len) {
-		ret = vfs_write(filp, (char *)buf + pos, len - pos, off);
+		ret = vfs_write(filp, (__force const char __user *)buf + pos,
+				len - pos, off);
 		/* TODO handle that correctly */
 		/*if (ret == -ERESTARTSYS) {
 			continue;
@@ -985,11 +986,13 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 	int num;
 	u8 type;
 
-	if (found_key->type == BTRFS_XATTR_ITEM_KEY)
-		buf_len = BTRFS_MAX_XATTR_SIZE(root);
-	else
-		buf_len = PATH_MAX;
-
+	/*
+	 * Start with a small buffer (1 page). If later we end up needing more
+	 * space, which can happen for xattrs on a fs with a leaf size greater
+	 * then the page size, attempt to increase the buffer. Typically xattr
+	 * values are small.
+	 */
+	buf_len = PATH_MAX;
 	buf = kmalloc(buf_len, GFP_NOFS);
 	if (!buf) {
 		ret = -ENOMEM;
@@ -1016,7 +1019,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 				ret = -ENAMETOOLONG;
 				goto out;
 			}
-			if (name_len + data_len > buf_len) {
+			if (name_len + data_len > BTRFS_MAX_XATTR_SIZE(root)) {
 				ret = -E2BIG;
 				goto out;
 			}
@@ -1024,12 +1027,34 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 			/*
 			 * Path too long
 			 */
-			if (name_len + data_len > buf_len) {
+			if (name_len + data_len > PATH_MAX) {
 				ret = -ENAMETOOLONG;
 				goto out;
 			}
 		}
 
+		if (name_len + data_len > buf_len) {
+			buf_len = name_len + data_len;
+			if (is_vmalloc_addr(buf)) {
+				vfree(buf);
+				buf = NULL;
+			} else {
+				char *tmp = krealloc(buf, buf_len,
+						     GFP_NOFS | __GFP_NOWARN);
+
+				if (!tmp)
+					kfree(buf);
+				buf = tmp;
+			}
+			if (!buf) {
+				buf = vmalloc(buf_len);
+				if (!buf) {
+					ret = -ENOMEM;
+					goto out;
+				}
+			}
+		}
+
 		read_extent_buffer(eb, buf, (unsigned long)(di + 1),
 				name_len + data_len);
 
@@ -1050,7 +1075,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 	}
 
 out:
-	kfree(buf);
+	kvfree(buf);
 	return ret;
 }
 
@@ -3302,7 +3327,7 @@ static int wait_for_parent_move(struct send_ctx *sctx,
 		if (ret < 0 && ret != -ENOENT) {
 			goto out;
 		} else if (ret == -ENOENT) {
-			ret = 1;
+			ret = 0;
 			break;
 		}
 
@@ -5703,7 +5728,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 			NULL);
 	sort_clone_roots = 1;
 
-	current->journal_info = (void *)BTRFS_SEND_TRANS_STUB;
+	current->journal_info = BTRFS_SEND_TRANS_STUB;
 	ret = send_subvol(sctx);
 	current->journal_info = NULL;
 	if (ret < 0)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index c4124de4435b..a2b97ef10317 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -60,6 +60,7 @@
 #include "backref.h"
 #include "tests/btrfs-tests.h"
 
+#include "qgroup.h"
 #define CREATE_TRACE_POINTS
 #include <trace/events/btrfs.h>
 
@@ -307,13 +308,7 @@ void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
 
 static void btrfs_put_super(struct super_block *sb)
 {
-	(void)close_ctree(btrfs_sb(sb)->tree_root);
-	/* FIXME: need to fix VFS to return error? */
-	/* AV: return it _where_?  ->put_super() can be triggered by any number
-	 * of async events, up to and including delivery of SIGKILL to the
-	 * last process that kept it busy.  Or segfault in the aforementioned
-	 * process...  Whom would you report that to?
-	 */
+	close_ctree(btrfs_sb(sb)->tree_root);
 }
 
 enum {
@@ -400,7 +395,6 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 	int ret = 0;
 	char *compress_type;
 	bool compress_force = false;
-	bool compress = false;
 
 	cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy);
 	if (cache_gen)
@@ -478,7 +472,6 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			/* Fallthrough */
 		case Opt_compress:
 		case Opt_compress_type:
-			compress = true;
 			if (token == Opt_compress ||
 			    token == Opt_compress_force ||
 			    strcmp(args[0].from, "zlib") == 0) {
@@ -508,11 +501,18 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				btrfs_set_and_info(root, FORCE_COMPRESS,
 						   "force %s compression",
 						   compress_type);
-			} else if (compress) {
+			} else {
 				if (!btrfs_test_opt(root, COMPRESS))
 					btrfs_info(root->fs_info,
 						   "btrfs: use %s compression",
 						   compress_type);
+				/*
+				 * If we remount from compress-force=xxx to
+				 * compress=xxx, we need clear FORCE_COMPRESS
+				 * flag, otherwise, there is no way for users
+				 * to disable forcible compression separately.
+				 */
+				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
 			}
 			break;
 		case Opt_ssd:
@@ -1014,7 +1014,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",nodatacow");
 	if (btrfs_test_opt(root, NOBARRIER))
 		seq_puts(seq, ",nobarrier");
-	if (info->max_inline != 8192 * 1024)
+	if (info->max_inline != BTRFS_DEFAULT_MAX_INLINE)
 		seq_printf(seq, ",max_inline=%llu", info->max_inline);
 	if (info->alloc_start != 0)
 		seq_printf(seq, ",alloc_start=%llu", info->alloc_start);
@@ -1215,6 +1215,56 @@ static struct dentry *mount_subvol(const char *subvol_name, int flags,
 	return root;
 }
 
+static int parse_security_options(char *orig_opts,
+				  struct security_mnt_opts *sec_opts)
+{
+	char *secdata = NULL;
+	int ret = 0;
+
+	secdata = alloc_secdata();
+	if (!secdata)
+		return -ENOMEM;
+	ret = security_sb_copy_data(orig_opts, secdata);
+	if (ret) {
+		free_secdata(secdata);
+		return ret;
+	}
+	ret = security_sb_parse_opts_str(secdata, sec_opts);
+	free_secdata(secdata);
+	return ret;
+}
+
+static int setup_security_options(struct btrfs_fs_info *fs_info,
+				  struct super_block *sb,
+				  struct security_mnt_opts *sec_opts)
+{
+	int ret = 0;
+
+	/*
+	 * Call security_sb_set_mnt_opts() to check whether new sec_opts
+	 * is valid.
+	 */
+	ret = security_sb_set_mnt_opts(sb, sec_opts, 0, NULL);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_SECURITY
+	if (!fs_info->security_opts.num_mnt_opts) {
+		/* first time security setup, copy sec_opts to fs_info */
+		memcpy(&fs_info->security_opts, sec_opts, sizeof(*sec_opts));
+	} else {
+		/*
+		 * Since SELinux(the only one supports security_mnt_opts) does
+		 * NOT support changing context during remount/mount same sb,
+		 * This must be the same or part of the same security options,
+		 * just free it.
+		 */
+		security_free_mnt_opts(sec_opts);
+	}
+#endif
+	return ret;
+}
+
 /*
  * Find a superblock for the given device / mount point.
  *
@@ -1229,6 +1279,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	struct dentry *root;
 	struct btrfs_fs_devices *fs_devices = NULL;
 	struct btrfs_fs_info *fs_info = NULL;
+	struct security_mnt_opts new_sec_opts;
 	fmode_t mode = FMODE_READ;
 	char *subvol_name = NULL;
 	u64 subvol_objectid = 0;
@@ -1251,9 +1302,16 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 		return root;
 	}
 
+	security_init_mnt_opts(&new_sec_opts);
+	if (data) {
+		error = parse_security_options(data, &new_sec_opts);
+		if (error)
+			return ERR_PTR(error);
+	}
+
 	error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
 	if (error)
-		return ERR_PTR(error);
+		goto error_sec_opts;
 
 	/*
 	 * Setup a dummy root and fs_info for test/set super.  This is because
@@ -1262,13 +1320,16 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	 * then open_ctree will properly initialize everything later.
 	 */
 	fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_NOFS);
-	if (!fs_info)
-		return ERR_PTR(-ENOMEM);
+	if (!fs_info) {
+		error = -ENOMEM;
+		goto error_sec_opts;
+	}
 
 	fs_info->fs_devices = fs_devices;
 
 	fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
 	fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
+	security_init_mnt_opts(&fs_info->security_opts);
 	if (!fs_info->super_copy || !fs_info->super_for_commit) {
 		error = -ENOMEM;
 		goto error_fs_info;
@@ -1306,8 +1367,19 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	}
 
 	root = !error ? get_default_root(s, subvol_objectid) : ERR_PTR(error);
-	if (IS_ERR(root))
+	if (IS_ERR(root)) {
+		deactivate_locked_super(s);
+		error = PTR_ERR(root);
+		goto error_sec_opts;
+	}
+
+	fs_info = btrfs_sb(s);
+	error = setup_security_options(fs_info, s, &new_sec_opts);
+	if (error) {
+		dput(root);
 		deactivate_locked_super(s);
+		goto error_sec_opts;
+	}
 
 	return root;
 
@@ -1315,6 +1387,8 @@ error_close_devices:
 	btrfs_close_devices(fs_devices);
 error_fs_info:
 	free_fs_info(fs_info);
+error_sec_opts:
+	security_free_mnt_opts(&new_sec_opts);
 	return ERR_PTR(error);
 }
 
@@ -1396,6 +1470,21 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 	sync_filesystem(sb);
 	btrfs_remount_prepare(fs_info);
 
+	if (data) {
+		struct security_mnt_opts new_sec_opts;
+
+		security_init_mnt_opts(&new_sec_opts);
+		ret = parse_security_options(data, &new_sec_opts);
+		if (ret)
+			goto restore;
+		ret = setup_security_options(fs_info, sb,
+					     &new_sec_opts);
+		if (ret) {
+			security_free_mnt_opts(&new_sec_opts);
+			goto restore;
+		}
+	}
+
 	ret = btrfs_parse_options(root, data);
 	if (ret) {
 		ret = -EINVAL;
@@ -1694,7 +1783,11 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
 	int ret;
 
-	/* holding chunk_muext to avoid allocating new chunks */
+	/*
+	 * holding chunk_muext to avoid allocating new chunks, holding
+	 * device_list_mutex to avoid the device being removed
+	 */
+	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	mutex_lock(&fs_info->chunk_mutex);
 	rcu_read_lock();
 	list_for_each_entry_rcu(found, head, list) {
@@ -1735,11 +1828,13 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	ret = btrfs_calc_avail_data_space(fs_info->tree_root, &total_free_data);
 	if (ret) {
 		mutex_unlock(&fs_info->chunk_mutex);
+		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		return ret;
 	}
 	buf->f_bavail += div_u64(total_free_data, factor);
 	buf->f_bavail = buf->f_bavail >> bits;
 	mutex_unlock(&fs_info->chunk_mutex);
+	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 
 	buf->f_type = BTRFS_SUPER_MAGIC;
 	buf->f_bsize = dentry->d_sb->s_blocksize;
@@ -1769,7 +1864,7 @@ static struct file_system_type btrfs_fs_type = {
 	.name		= "btrfs",
 	.mount		= btrfs_mount,
 	.kill_sb	= btrfs_kill_super,
-	.fs_flags	= FS_REQUIRES_DEV,
+	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA,
 };
 MODULE_ALIAS_FS("btrfs");
 
@@ -1993,11 +2088,15 @@ static int __init init_btrfs_fs(void)
 
 	err = btrfs_prelim_ref_init();
 	if (err)
+		goto free_delayed_ref;
+
+	err = btrfs_end_io_wq_init();
+	if (err)
 		goto free_prelim_ref;
 
 	err = btrfs_interface_init();
 	if (err)
-		goto free_delayed_ref;
+		goto free_end_io_wq;
 
 	btrfs_init_lockdep();
 
@@ -2015,6 +2114,8 @@ static int __init init_btrfs_fs(void)
 
 unregister_ioctl:
 	btrfs_interface_exit();
+free_end_io_wq:
+	btrfs_end_io_wq_exit();
 free_prelim_ref:
 	btrfs_prelim_ref_exit();
 free_delayed_ref:
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 12e53556e214..b2e7bb4393f6 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -242,7 +242,7 @@ static ssize_t global_rsv_size_show(struct kobject *kobj,
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
 	return btrfs_show_u64(&block_rsv->size, &block_rsv->lock, buf);
 }
-BTRFS_ATTR(global_rsv_size, 0444, global_rsv_size_show);
+BTRFS_ATTR(global_rsv_size, global_rsv_size_show);
 
 static ssize_t global_rsv_reserved_show(struct kobject *kobj,
 					struct kobj_attribute *a, char *buf)
@@ -251,7 +251,7 @@ static ssize_t global_rsv_reserved_show(struct kobject *kobj,
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
 	return btrfs_show_u64(&block_rsv->reserved, &block_rsv->lock, buf);
 }
-BTRFS_ATTR(global_rsv_reserved, 0444, global_rsv_reserved_show);
+BTRFS_ATTR(global_rsv_reserved, global_rsv_reserved_show);
 
 #define to_space_info(_kobj) container_of(_kobj, struct btrfs_space_info, kobj)
 #define to_raid_kobj(_kobj) container_of(_kobj, struct raid_kobject, kobj)
@@ -306,7 +306,7 @@ static ssize_t btrfs_space_info_show_##field(struct kobject *kobj,	\
 	struct btrfs_space_info *sinfo = to_space_info(kobj);		\
 	return btrfs_show_u64(&sinfo->field, &sinfo->lock, buf);	\
 }									\
-BTRFS_ATTR(field, 0444, btrfs_space_info_show_##field)
+BTRFS_ATTR(field, btrfs_space_info_show_##field)
 
 static ssize_t btrfs_space_info_show_total_bytes_pinned(struct kobject *kobj,
 						       struct kobj_attribute *a,
@@ -325,7 +325,7 @@ SPACE_INFO_ATTR(bytes_reserved);
 SPACE_INFO_ATTR(bytes_may_use);
 SPACE_INFO_ATTR(disk_used);
 SPACE_INFO_ATTR(disk_total);
-BTRFS_ATTR(total_bytes_pinned, 0444, btrfs_space_info_show_total_bytes_pinned);
+BTRFS_ATTR(total_bytes_pinned, btrfs_space_info_show_total_bytes_pinned);
 
 static struct attribute *space_info_attrs[] = {
 	BTRFS_ATTR_PTR(flags),
@@ -363,7 +363,8 @@ static ssize_t btrfs_label_show(struct kobject *kobj,
 				struct kobj_attribute *a, char *buf)
 {
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
-	return snprintf(buf, PAGE_SIZE, "%s\n", fs_info->super_copy->label);
+	char *label = fs_info->super_copy->label;
+	return snprintf(buf, PAGE_SIZE, label[0] ? "%s\n" : "%s", label);
 }
 
 static ssize_t btrfs_label_store(struct kobject *kobj,
@@ -374,8 +375,18 @@ static ssize_t btrfs_label_store(struct kobject *kobj,
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = fs_info->fs_root;
 	int ret;
+	size_t p_len;
 
-	if (len >= BTRFS_LABEL_SIZE)
+	if (fs_info->sb->s_flags & MS_RDONLY)
+		return -EROFS;
+
+	/*
+	 * p_len is the len until the first occurrence of either
+	 * '\n' or '\0'
+	 */
+	p_len = strcspn(buf, "\n");
+
+	if (p_len >= BTRFS_LABEL_SIZE)
 		return -EINVAL;
 
 	trans = btrfs_start_transaction(root, 0);
@@ -383,7 +394,8 @@ static ssize_t btrfs_label_store(struct kobject *kobj,
 		return PTR_ERR(trans);
 
 	spin_lock(&root->fs_info->super_lock);
-	strcpy(fs_info->super_copy->label, buf);
+	memset(fs_info->super_copy->label, 0, BTRFS_LABEL_SIZE);
+	memcpy(fs_info->super_copy->label, buf, p_len);
 	spin_unlock(&root->fs_info->super_lock);
 	ret = btrfs_commit_transaction(trans, root);
 
@@ -392,14 +404,7 @@ static ssize_t btrfs_label_store(struct kobject *kobj,
 
 	return ret;
 }
-BTRFS_ATTR_RW(label, 0644, btrfs_label_show, btrfs_label_store);
-
-static ssize_t btrfs_no_store(struct kobject *kobj,
-				 struct kobj_attribute *a,
-				 const char *buf, size_t len)
-{
-	return -EPERM;
-}
+BTRFS_ATTR_RW(label, btrfs_label_show, btrfs_label_store);
 
 static ssize_t btrfs_nodesize_show(struct kobject *kobj,
 				struct kobj_attribute *a, char *buf)
@@ -409,7 +414,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj,
 	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize);
 }
 
-BTRFS_ATTR_RW(nodesize, 0444, btrfs_nodesize_show, btrfs_no_store);
+BTRFS_ATTR(nodesize, btrfs_nodesize_show);
 
 static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
 				struct kobj_attribute *a, char *buf)
@@ -419,7 +424,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
 	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->sectorsize);
 }
 
-BTRFS_ATTR_RW(sectorsize, 0444, btrfs_sectorsize_show, btrfs_no_store);
+BTRFS_ATTR(sectorsize, btrfs_sectorsize_show);
 
 static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
 				struct kobj_attribute *a, char *buf)
@@ -429,7 +434,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
 	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->sectorsize);
 }
 
-BTRFS_ATTR_RW(clone_alignment, 0444, btrfs_clone_alignment_show, btrfs_no_store);
+BTRFS_ATTR(clone_alignment, btrfs_clone_alignment_show);
 
 static struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(label),
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index ac46df37504c..f7dd298b3cf6 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -20,16 +20,20 @@ enum btrfs_feature_set {
 	.store	= _store,						\
 }
 
-#define BTRFS_ATTR_RW(_name, _mode, _show, _store)			\
-static struct kobj_attribute btrfs_attr_##_name =			\
-			__INIT_KOBJ_ATTR(_name, _mode, _show, _store)
-#define BTRFS_ATTR(_name, _mode, _show)					\
-	BTRFS_ATTR_RW(_name, _mode, _show, NULL)
+#define BTRFS_ATTR_RW(_name, _show, _store)			\
+	static struct kobj_attribute btrfs_attr_##_name =		\
+			__INIT_KOBJ_ATTR(_name, 0644, _show, _store)
+
+#define BTRFS_ATTR(_name, _show)					\
+	static struct kobj_attribute btrfs_attr_##_name =		\
+			__INIT_KOBJ_ATTR(_name, 0444, _show, NULL)
+
 #define BTRFS_ATTR_PTR(_name)    (&btrfs_attr_##_name.attr)
 
 #define BTRFS_RAID_ATTR(_name, _show)					\
-static struct kobj_attribute btrfs_raid_attr_##_name =			\
+	static struct kobj_attribute btrfs_raid_attr_##_name =		\
 			__INIT_KOBJ_ATTR(_name, 0444, _show, NULL)
+
 #define BTRFS_RAID_ATTR_PTR(_name)    (&btrfs_raid_attr_##_name.attr)
 
 
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index c8d9ddf84c69..2299bfde39ee 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -40,11 +40,12 @@ static struct btrfs_block_group_cache *init_test_block_group(void)
 	cache->key.offset = 1024 * 1024 * 1024;
 	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
 	cache->sectorsize = 4096;
+	cache->full_stripe_len = 4096;
 
 	spin_lock_init(&cache->lock);
 	INIT_LIST_HEAD(&cache->list);
 	INIT_LIST_HEAD(&cache->cluster_list);
-	INIT_LIST_HEAD(&cache->new_bg_list);
+	INIT_LIST_HEAD(&cache->bg_list);
 
 	btrfs_init_free_space_ctl(cache);
 
@@ -364,6 +365,517 @@ static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache)
 	return 0;
 }
 
+/* Used by test_steal_space_from_bitmap_to_extent(). */
+static bool test_use_bitmap(struct btrfs_free_space_ctl *ctl,
+			    struct btrfs_free_space *info)
+{
+	return ctl->free_extents > 0;
+}
+
+/* Used by test_steal_space_from_bitmap_to_extent(). */
+static int
+check_num_extents_and_bitmaps(const struct btrfs_block_group_cache *cache,
+			      const int num_extents,
+			      const int num_bitmaps)
+{
+	if (cache->free_space_ctl->free_extents != num_extents) {
+		test_msg("Incorrect # of extent entries in the cache: %d, expected %d\n",
+			 cache->free_space_ctl->free_extents, num_extents);
+		return -EINVAL;
+	}
+	if (cache->free_space_ctl->total_bitmaps != num_bitmaps) {
+		test_msg("Incorrect # of extent entries in the cache: %d, expected %d\n",
+			 cache->free_space_ctl->total_bitmaps, num_bitmaps);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Used by test_steal_space_from_bitmap_to_extent(). */
+static int check_cache_empty(struct btrfs_block_group_cache *cache)
+{
+	u64 offset;
+	u64 max_extent_size;
+
+	/*
+	 * Now lets confirm that there's absolutely no free space left to
+	 * allocate.
+	 */
+	if (cache->free_space_ctl->free_space != 0) {
+		test_msg("Cache free space is not 0\n");
+		return -EINVAL;
+	}
+
+	/* And any allocation request, no matter how small, should fail now. */
+	offset = btrfs_find_space_for_alloc(cache, 0, 4096, 0,
+					    &max_extent_size);
+	if (offset != 0) {
+		test_msg("Space allocation did not fail, returned offset: %llu",
+			 offset);
+		return -EINVAL;
+	}
+
+	/* And no extent nor bitmap entries in the cache anymore. */
+	return check_num_extents_and_bitmaps(cache, 0, 0);
+}
+
+/*
+ * Before we were able to steal free space from a bitmap entry to an extent
+ * entry, we could end up with 2 entries representing a contiguous free space.
+ * One would be an extent entry and the other a bitmap entry. Since in order
+ * to allocate space to a caller we use only 1 entry, we couldn't return that
+ * whole range to the caller if it was requested. This forced the caller to
+ * either assume ENOSPC or perform several smaller space allocations, which
+ * wasn't optimal as they could be spread all over the block group while under
+ * concurrency (extra overhead and fragmentation).
+ *
+ * This stealing approach is benefical, since we always prefer to allocate from
+ * extent entries, both for clustered and non-clustered allocation requests.
+ */
+static int
+test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
+{
+	int ret;
+	u64 offset;
+	u64 max_extent_size;
+
+	bool (*use_bitmap_op)(struct btrfs_free_space_ctl *,
+			      struct btrfs_free_space *);
+
+	test_msg("Running space stealing from bitmap to extent\n");
+
+	/*
+	 * For this test, we want to ensure we end up with an extent entry
+	 * immediately adjacent to a bitmap entry, where the bitmap starts
+	 * at an offset where the extent entry ends. We keep adding and
+	 * removing free space to reach into this state, but to get there
+	 * we need to reach a point where marking new free space doesn't
+	 * result in adding new extent entries or merging the new space
+	 * with existing extent entries - the space ends up being marked
+	 * in an existing bitmap that covers the new free space range.
+	 *
+	 * To get there, we need to reach the threshold defined set at
+	 * cache->free_space_ctl->extents_thresh, which currently is
+	 * 256 extents on a x86_64 system at least, and a few other
+	 * conditions (check free_space_cache.c). Instead of making the
+	 * test much longer and complicated, use a "use_bitmap" operation
+	 * that forces use of bitmaps as soon as we have at least 1
+	 * extent entry.
+	 */
+	use_bitmap_op = cache->free_space_ctl->op->use_bitmap;
+	cache->free_space_ctl->op->use_bitmap = test_use_bitmap;
+
+	/*
+	 * Extent entry covering free space range [128Mb - 256Kb, 128Mb - 128Kb[
+	 */
+	ret = test_add_free_space_entry(cache, 128 * 1024 * 1024 - 256 * 1024,
+					128 * 1024, 0);
+	if (ret) {
+		test_msg("Couldn't add extent entry %d\n", ret);
+		return ret;
+	}
+
+	/* Bitmap entry covering free space range [128Mb + 512Kb, 256Mb[ */
+	ret = test_add_free_space_entry(cache, 128 * 1024 * 1024 + 512 * 1024,
+					128 * 1024 * 1024 - 512 * 1024, 1);
+	if (ret) {
+		test_msg("Couldn't add bitmap entry %d\n", ret);
+		return ret;
+	}
+
+	ret = check_num_extents_and_bitmaps(cache, 2, 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Now make only the first 256Kb of the bitmap marked as free, so that
+	 * we end up with only the following ranges marked as free space:
+	 *
+	 * [128Mb - 256Kb, 128Mb - 128Kb[
+	 * [128Mb + 512Kb, 128Mb + 768Kb[
+	 */
+	ret = btrfs_remove_free_space(cache,
+				      128 * 1024 * 1024 + 768 * 1024,
+				      128 * 1024 * 1024 - 768 * 1024);
+	if (ret) {
+		test_msg("Failed to free part of bitmap space %d\n", ret);
+		return ret;
+	}
+
+	/* Confirm that only those 2 ranges are marked as free. */
+	if (!test_check_exists(cache, 128 * 1024 * 1024 - 256 * 1024,
+			       128 * 1024)) {
+		test_msg("Free space range missing\n");
+		return -ENOENT;
+	}
+	if (!test_check_exists(cache, 128 * 1024 * 1024 + 512 * 1024,
+			       256 * 1024)) {
+		test_msg("Free space range missing\n");
+		return -ENOENT;
+	}
+
+	/*
+	 * Confirm that the bitmap range [128Mb + 768Kb, 256Mb[ isn't marked
+	 * as free anymore.
+	 */
+	if (test_check_exists(cache, 128 * 1024 * 1024 + 768 * 1024,
+			      128 * 1024 * 1024 - 768 * 1024)) {
+		test_msg("Bitmap region not removed from space cache\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Confirm that the region [128Mb + 256Kb, 128Mb + 512Kb[, which is
+	 * covered by the bitmap, isn't marked as free.
+	 */
+	if (test_check_exists(cache, 128 * 1024 * 1024 + 256 * 1024,
+			      256 * 1024)) {
+		test_msg("Invalid bitmap region marked as free\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Confirm that the region [128Mb, 128Mb + 256Kb[, which is covered
+	 * by the bitmap too, isn't marked as free either.
+	 */
+	if (test_check_exists(cache, 128 * 1024 * 1024,
+			      256 * 1024)) {
+		test_msg("Invalid bitmap region marked as free\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Now lets mark the region [128Mb, 128Mb + 512Kb[ as free too. But,
+	 * lets make sure the free space cache marks it as free in the bitmap,
+	 * and doesn't insert a new extent entry to represent this region.
+	 */
+	ret = btrfs_add_free_space(cache, 128 * 1024 * 1024, 512 * 1024);
+	if (ret) {
+		test_msg("Error adding free space: %d\n", ret);
+		return ret;
+	}
+	/* Confirm the region is marked as free. */
+	if (!test_check_exists(cache, 128 * 1024 * 1024, 512 * 1024)) {
+		test_msg("Bitmap region not marked as free\n");
+		return -ENOENT;
+	}
+
+	/*
+	 * Confirm that no new extent entries or bitmap entries were added to
+	 * the cache after adding that free space region.
+	 */
+	ret = check_num_extents_and_bitmaps(cache, 2, 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Now lets add a small free space region to the right of the previous
+	 * one, which is not contiguous with it and is part of the bitmap too.
+	 * The goal is to test that the bitmap entry space stealing doesn't
+	 * steal this space region.
+	 */
+	ret = btrfs_add_free_space(cache, 128 * 1024 * 1024 + 16 * 1024 * 1024,
+				   4096);
+	if (ret) {
+		test_msg("Error adding free space: %d\n", ret);
+		return ret;
+	}
+
+	/*
+	 * Confirm that no new extent entries or bitmap entries were added to
+	 * the cache after adding that free space region.
+	 */
+	ret = check_num_extents_and_bitmaps(cache, 2, 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Now mark the region [128Mb - 128Kb, 128Mb[ as free too. This will
+	 * expand the range covered by the existing extent entry that represents
+	 * the free space [128Mb - 256Kb, 128Mb - 128Kb[.
+	 */
+	ret = btrfs_add_free_space(cache, 128 * 1024 * 1024 - 128 * 1024,
+				   128 * 1024);
+	if (ret) {
+		test_msg("Error adding free space: %d\n", ret);
+		return ret;
+	}
+	/* Confirm the region is marked as free. */
+	if (!test_check_exists(cache, 128 * 1024 * 1024 - 128 * 1024,
+			       128 * 1024)) {
+		test_msg("Extent region not marked as free\n");
+		return -ENOENT;
+	}
+
+	/*
+	 * Confirm that our extent entry didn't stole all free space from the
+	 * bitmap, because of the small 4Kb free space region.
+	 */
+	ret = check_num_extents_and_bitmaps(cache, 2, 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * So now we have the range [128Mb - 256Kb, 128Mb + 768Kb[ as free
+	 * space. Without stealing bitmap free space into extent entry space,
+	 * we would have all this free space represented by 2 entries in the
+	 * cache:
+	 *
+	 * extent entry covering range: [128Mb - 256Kb, 128Mb[
+	 * bitmap entry covering range: [128Mb, 128Mb + 768Kb[
+	 *
+	 * Attempting to allocate the whole free space (1Mb) would fail, because
+	 * we can't allocate from multiple entries.
+	 * With the bitmap free space stealing, we get a single extent entry
+	 * that represents the 1Mb free space, and therefore we're able to
+	 * allocate the whole free space at once.
+	 */
+	if (!test_check_exists(cache, 128 * 1024 * 1024 - 256 * 1024,
+			       1 * 1024 * 1024)) {
+		test_msg("Expected region not marked as free\n");
+		return -ENOENT;
+	}
+
+	if (cache->free_space_ctl->free_space != (1 * 1024 * 1024 + 4096)) {
+		test_msg("Cache free space is not 1Mb + 4Kb\n");
+		return -EINVAL;
+	}
+
+	offset = btrfs_find_space_for_alloc(cache,
+					    0, 1 * 1024 * 1024, 0,
+					    &max_extent_size);
+	if (offset != (128 * 1024 * 1024 - 256 * 1024)) {
+		test_msg("Failed to allocate 1Mb from space cache, returned offset is: %llu\n",
+			 offset);
+		return -EINVAL;
+	}
+
+	/* All that remains is a 4Kb free space region in a bitmap. Confirm. */
+	ret = check_num_extents_and_bitmaps(cache, 1, 1);
+	if (ret)
+		return ret;
+
+	if (cache->free_space_ctl->free_space != 4096) {
+		test_msg("Cache free space is not 4Kb\n");
+		return -EINVAL;
+	}
+
+	offset = btrfs_find_space_for_alloc(cache,
+					    0, 4096, 0,
+					    &max_extent_size);
+	if (offset != (128 * 1024 * 1024 + 16 * 1024 * 1024)) {
+		test_msg("Failed to allocate 4Kb from space cache, returned offset is: %llu\n",
+			 offset);
+		return -EINVAL;
+	}
+
+	ret = check_cache_empty(cache);
+	if (ret)
+		return ret;
+
+	__btrfs_remove_free_space_cache(cache->free_space_ctl);
+
+	/*
+	 * Now test a similar scenario, but where our extent entry is located
+	 * to the right of the bitmap entry, so that we can check that stealing
+	 * space from a bitmap to the front of an extent entry works.
+	 */
+
+	/*
+	 * Extent entry covering free space range [128Mb + 128Kb, 128Mb + 256Kb[
+	 */
+	ret = test_add_free_space_entry(cache, 128 * 1024 * 1024 + 128 * 1024,
+					128 * 1024, 0);
+	if (ret) {
+		test_msg("Couldn't add extent entry %d\n", ret);
+		return ret;
+	}
+
+	/* Bitmap entry covering free space range [0, 128Mb - 512Kb[ */
+	ret = test_add_free_space_entry(cache, 0,
+					128 * 1024 * 1024 - 512 * 1024, 1);
+	if (ret) {
+		test_msg("Couldn't add bitmap entry %d\n", ret);
+		return ret;
+	}
+
+	ret = check_num_extents_and_bitmaps(cache, 2, 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Now make only the last 256Kb of the bitmap marked as free, so that
+	 * we end up with only the following ranges marked as free space:
+	 *
+	 * [128Mb + 128b, 128Mb + 256Kb[
+	 * [128Mb - 768Kb, 128Mb - 512Kb[
+	 */
+	ret = btrfs_remove_free_space(cache,
+				      0,
+				      128 * 1024 * 1024 - 768 * 1024);
+	if (ret) {
+		test_msg("Failed to free part of bitmap space %d\n", ret);
+		return ret;
+	}
+
+	/* Confirm that only those 2 ranges are marked as free. */
+	if (!test_check_exists(cache, 128 * 1024 * 1024 + 128 * 1024,
+			       128 * 1024)) {
+		test_msg("Free space range missing\n");
+		return -ENOENT;
+	}
+	if (!test_check_exists(cache, 128 * 1024 * 1024 - 768 * 1024,
+			       256 * 1024)) {
+		test_msg("Free space range missing\n");
+		return -ENOENT;
+	}
+
+	/*
+	 * Confirm that the bitmap range [0, 128Mb - 768Kb[ isn't marked
+	 * as free anymore.
+	 */
+	if (test_check_exists(cache, 0,
+			      128 * 1024 * 1024 - 768 * 1024)) {
+		test_msg("Bitmap region not removed from space cache\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Confirm that the region [128Mb - 512Kb, 128Mb[, which is
+	 * covered by the bitmap, isn't marked as free.
+	 */
+	if (test_check_exists(cache, 128 * 1024 * 1024 - 512 * 1024,
+			      512 * 1024)) {
+		test_msg("Invalid bitmap region marked as free\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Now lets mark the region [128Mb - 512Kb, 128Mb[ as free too. But,
+	 * lets make sure the free space cache marks it as free in the bitmap,
+	 * and doesn't insert a new extent entry to represent this region.
+	 */
+	ret = btrfs_add_free_space(cache, 128 * 1024 * 1024 - 512 * 1024,
+				   512 * 1024);
+	if (ret) {
+		test_msg("Error adding free space: %d\n", ret);
+		return ret;
+	}
+	/* Confirm the region is marked as free. */
+	if (!test_check_exists(cache, 128 * 1024 * 1024 - 512 * 1024,
+			       512 * 1024)) {
+		test_msg("Bitmap region not marked as free\n");
+		return -ENOENT;
+	}
+
+	/*
+	 * Confirm that no new extent entries or bitmap entries were added to
+	 * the cache after adding that free space region.
+	 */
+	ret = check_num_extents_and_bitmaps(cache, 2, 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Now lets add a small free space region to the left of the previous
+	 * one, which is not contiguous with it and is part of the bitmap too.
+	 * The goal is to test that the bitmap entry space stealing doesn't
+	 * steal this space region.
+	 */
+	ret = btrfs_add_free_space(cache, 32 * 1024 * 1024, 8192);
+	if (ret) {
+		test_msg("Error adding free space: %d\n", ret);
+		return ret;
+	}
+
+	/*
+	 * Now mark the region [128Mb, 128Mb + 128Kb[ as free too. This will
+	 * expand the range covered by the existing extent entry that represents
+	 * the free space [128Mb + 128Kb, 128Mb + 256Kb[.
+	 */
+	ret = btrfs_add_free_space(cache, 128 * 1024 * 1024, 128 * 1024);
+	if (ret) {
+		test_msg("Error adding free space: %d\n", ret);
+		return ret;
+	}
+	/* Confirm the region is marked as free. */
+	if (!test_check_exists(cache, 128 * 1024 * 1024, 128 * 1024)) {
+		test_msg("Extent region not marked as free\n");
+		return -ENOENT;
+	}
+
+	/*
+	 * Confirm that our extent entry didn't stole all free space from the
+	 * bitmap, because of the small 8Kb free space region.
+	 */
+	ret = check_num_extents_and_bitmaps(cache, 2, 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * So now we have the range [128Mb - 768Kb, 128Mb + 256Kb[ as free
+	 * space. Without stealing bitmap free space into extent entry space,
+	 * we would have all this free space represented by 2 entries in the
+	 * cache:
+	 *
+	 * extent entry covering range: [128Mb, 128Mb + 256Kb[
+	 * bitmap entry covering range: [128Mb - 768Kb, 128Mb[
+	 *
+	 * Attempting to allocate the whole free space (1Mb) would fail, because
+	 * we can't allocate from multiple entries.
+	 * With the bitmap free space stealing, we get a single extent entry
+	 * that represents the 1Mb free space, and therefore we're able to
+	 * allocate the whole free space at once.
+	 */
+	if (!test_check_exists(cache, 128 * 1024 * 1024 - 768 * 1024,
+			       1 * 1024 * 1024)) {
+		test_msg("Expected region not marked as free\n");
+		return -ENOENT;
+	}
+
+	if (cache->free_space_ctl->free_space != (1 * 1024 * 1024 + 8192)) {
+		test_msg("Cache free space is not 1Mb + 8Kb\n");
+		return -EINVAL;
+	}
+
+	offset = btrfs_find_space_for_alloc(cache,
+					    0, 1 * 1024 * 1024, 0,
+					    &max_extent_size);
+	if (offset != (128 * 1024 * 1024 - 768 * 1024)) {
+		test_msg("Failed to allocate 1Mb from space cache, returned offset is: %llu\n",
+			 offset);
+		return -EINVAL;
+	}
+
+	/* All that remains is a 8Kb free space region in a bitmap. Confirm. */
+	ret = check_num_extents_and_bitmaps(cache, 1, 1);
+	if (ret)
+		return ret;
+
+	if (cache->free_space_ctl->free_space != 8192) {
+		test_msg("Cache free space is not 8Kb\n");
+		return -EINVAL;
+	}
+
+	offset = btrfs_find_space_for_alloc(cache,
+					    0, 8192, 0,
+					    &max_extent_size);
+	if (offset != (32 * 1024 * 1024)) {
+		test_msg("Failed to allocate 8Kb from space cache, returned offset is: %llu\n",
+			 offset);
+		return -EINVAL;
+	}
+
+	ret = check_cache_empty(cache);
+	if (ret)
+		return ret;
+
+	cache->free_space_ctl->op->use_bitmap = use_bitmap_op;
+	__btrfs_remove_free_space_cache(cache->free_space_ctl);
+
+	return 0;
+}
+
 int btrfs_test_free_space_cache(void)
 {
 	struct btrfs_block_group_cache *cache;
@@ -386,6 +898,8 @@ int btrfs_test_free_space_cache(void)
 	ret = test_bitmaps_and_extents(cache);
 	if (ret)
 		goto out;
+
+	ret = test_steal_space_from_bitmap_to_extent(cache);
 out:
 	__btrfs_remove_free_space_cache(cache->free_space_ctl);
 	kfree(cache->free_space_ctl);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index d89c6d3542ca..dcaae3616728 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -386,7 +386,7 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type,
 	int ret;
 
 	/* Send isn't supposed to start transactions. */
-	ASSERT(current->journal_info != (void *)BTRFS_SEND_TRANS_STUB);
+	ASSERT(current->journal_info != BTRFS_SEND_TRANS_STUB);
 
 	if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
 		return ERR_PTR(-EROFS);
@@ -408,7 +408,7 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type,
 	if (num_items > 0 && root != root->fs_info->chunk_root) {
 		if (root->fs_info->quota_enabled &&
 		    is_fstree(root->root_key.objectid)) {
-			qgroup_reserved = num_items * root->leafsize;
+			qgroup_reserved = num_items * root->nodesize;
 			ret = btrfs_qgroup_reserve(root, qgroup_reserved);
 			if (ret)
 				return ERR_PTR(ret);
@@ -418,7 +418,7 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type,
 		/*
 		 * Do the reservation for the relocation root creation
 		 */
-		if (unlikely(need_reserve_reloc_root(root))) {
+		if (need_reserve_reloc_root(root)) {
 			num_bytes += root->nodesize;
 			reloc_reserved = true;
 		}
@@ -609,7 +609,6 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
 		if (transid <= root->fs_info->last_trans_committed)
 			goto out;
 
-		ret = -EINVAL;
 		/* find specified transaction */
 		spin_lock(&root->fs_info->trans_lock);
 		list_for_each_entry(t, &root->fs_info->trans_list, list) {
@@ -625,9 +624,16 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
 			}
 		}
 		spin_unlock(&root->fs_info->trans_lock);
-		/* The specified transaction doesn't exist */
-		if (!cur_trans)
+
+		/*
+		 * The specified transaction doesn't exist, or we
+		 * raced with btrfs_commit_transaction
+		 */
+		if (!cur_trans) {
+			if (transid > root->fs_info->last_trans_committed)
+				ret = -EINVAL;
 			goto out;
+		}
 	} else {
 		/* find newest transaction that is committing | committed */
 		spin_lock(&root->fs_info->trans_lock);
@@ -851,6 +857,8 @@ int btrfs_wait_marked_extents(struct btrfs_root *root,
 	struct extent_state *cached_state = NULL;
 	u64 start = 0;
 	u64 end;
+	struct btrfs_inode *btree_ino = BTRFS_I(root->fs_info->btree_inode);
+	bool errors = false;
 
 	while (!find_first_extent_bit(dirty_pages, start, &start, &end,
 				      EXTENT_NEED_WAIT, &cached_state)) {
@@ -864,6 +872,26 @@ int btrfs_wait_marked_extents(struct btrfs_root *root,
 	}
 	if (err)
 		werr = err;
+
+	if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
+		if ((mark & EXTENT_DIRTY) &&
+		    test_and_clear_bit(BTRFS_INODE_BTREE_LOG1_ERR,
+				       &btree_ino->runtime_flags))
+			errors = true;
+
+		if ((mark & EXTENT_NEW) &&
+		    test_and_clear_bit(BTRFS_INODE_BTREE_LOG2_ERR,
+				       &btree_ino->runtime_flags))
+			errors = true;
+	} else {
+		if (test_and_clear_bit(BTRFS_INODE_BTREE_ERR,
+				       &btree_ino->runtime_flags))
+			errors = true;
+	}
+
+	if (errors && !werr)
+		werr = -EIO;
+
 	return werr;
 }
 
@@ -1629,6 +1657,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_transaction *prev_trans = NULL;
+	struct btrfs_inode *btree_ino = BTRFS_I(root->fs_info->btree_inode);
 	int ret;
 
 	/* Stop the commit early if ->aborted is set */
@@ -1868,6 +1897,12 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	memcpy(root->fs_info->super_for_commit, root->fs_info->super_copy,
 	       sizeof(*root->fs_info->super_copy));
 
+	btrfs_update_commit_device_size(root->fs_info);
+	btrfs_update_commit_device_bytes_used(root, cur_trans);
+
+	clear_bit(BTRFS_INODE_BTREE_LOG1_ERR, &btree_ino->runtime_flags);
+	clear_bit(BTRFS_INODE_BTREE_LOG2_ERR, &btree_ino->runtime_flags);
+
 	spin_lock(&root->fs_info->trans_lock);
 	cur_trans->state = TRANS_STATE_UNBLOCKED;
 	root->fs_info->running_transaction = NULL;
@@ -1981,9 +2016,6 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root)
 		ret = btrfs_drop_snapshot(root, NULL, 0, 0);
 	else
 		ret = btrfs_drop_snapshot(root, NULL, 1, 0);
-	/*
-	 * If we encounter a transaction abort during snapshot cleaning, we
-	 * don't want to crash here
-	 */
+
 	return (ret < 0) ? 0 : 1;
 }
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 579be51b27e5..d8f40e1a5d2d 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -79,7 +79,7 @@ struct btrfs_transaction {
 #define TRANS_EXTWRITERS	(__TRANS_USERSPACE | __TRANS_START |	\
 				 __TRANS_ATTACH)
 
-#define BTRFS_SEND_TRANS_STUB	1
+#define BTRFS_SEND_TRANS_STUB	((void *)1)
 
 struct btrfs_trans_handle {
 	u64 transid;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d0262ceb85e1..1475979e5718 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -97,7 +97,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, struct inode *inode,
 			   int inode_only,
 			   const loff_t start,
-			   const loff_t end);
+			   const loff_t end,
+			   struct btrfs_log_ctx *ctx);
 static int link_to_fixup_dir(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
 			     struct btrfs_path *path, u64 objectid);
@@ -1498,7 +1499,7 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
 		return -EIO;
 
 	key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID;
-	btrfs_set_key_type(&key, BTRFS_ORPHAN_ITEM_KEY);
+	key.type = BTRFS_ORPHAN_ITEM_KEY;
 	key.offset = objectid;
 
 	ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
@@ -1637,6 +1638,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 	    found_key.type == log_key.type &&
 	    found_key.offset == log_key.offset &&
 	    btrfs_dir_type(path->nodes[0], dst_di) == log_type) {
+		update_size = false;
 		goto out;
 	}
 
@@ -2157,7 +2159,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 
 		bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
 		ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
-		blocksize = btrfs_level_size(root, *level - 1);
+		blocksize = root->nodesize;
 
 		parent = path->nodes[*level];
 		root_owner = btrfs_header_owner(parent);
@@ -2983,8 +2985,6 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	min_key.type = key_type;
 	min_key.offset = min_offset;
 
-	path->keep_locks = 1;
-
 	ret = btrfs_search_forward(root, &min_key, path, trans->transid);
 
 	/*
@@ -3364,7 +3364,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 		 * or deletes of this inode don't have to relog the inode
 		 * again
 		 */
-		if (btrfs_key_type(ins_keys + i) == BTRFS_EXTENT_DATA_KEY &&
+		if (ins_keys[i].type == BTRFS_EXTENT_DATA_KEY &&
 		    !skip_csum) {
 			int found_type;
 			extent = btrfs_item_ptr(src, start_slot + i,
@@ -3573,107 +3573,33 @@ static int extent_cmp(void *priv, struct list_head *a, struct list_head *b)
 	return 0;
 }
 
-static int log_one_extent(struct btrfs_trans_handle *trans,
-			  struct inode *inode, struct btrfs_root *root,
-			  struct extent_map *em, struct btrfs_path *path,
-			  struct list_head *logged_list)
+static int wait_ordered_extents(struct btrfs_trans_handle *trans,
+				struct inode *inode,
+				struct btrfs_root *root,
+				const struct extent_map *em,
+				const struct list_head *logged_list,
+				bool *ordered_io_error)
 {
-	struct btrfs_root *log = root->log_root;
-	struct btrfs_file_extent_item *fi;
-	struct extent_buffer *leaf;
 	struct btrfs_ordered_extent *ordered;
-	struct list_head ordered_sums;
-	struct btrfs_map_token token;
-	struct btrfs_key key;
+	struct btrfs_root *log = root->log_root;
 	u64 mod_start = em->mod_start;
 	u64 mod_len = em->mod_len;
+	const bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 	u64 csum_offset;
 	u64 csum_len;
-	u64 extent_offset = em->start - em->orig_start;
-	u64 block_len;
-	int ret;
-	bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
-	int extent_inserted = 0;
-
-	INIT_LIST_HEAD(&ordered_sums);
-	btrfs_init_map_token(&token);
-
-	ret = __btrfs_drop_extents(trans, log, inode, path, em->start,
-				   em->start + em->len, NULL, 0, 1,
-				   sizeof(*fi), &extent_inserted);
-	if (ret)
-		return ret;
-
-	if (!extent_inserted) {
-		key.objectid = btrfs_ino(inode);
-		key.type = BTRFS_EXTENT_DATA_KEY;
-		key.offset = em->start;
-
-		ret = btrfs_insert_empty_item(trans, log, path, &key,
-					      sizeof(*fi));
-		if (ret)
-			return ret;
-	}
-	leaf = path->nodes[0];
-	fi = btrfs_item_ptr(leaf, path->slots[0],
-			    struct btrfs_file_extent_item);
-
-	btrfs_set_token_file_extent_generation(leaf, fi, em->generation,
-					       &token);
-	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
-		skip_csum = true;
-		btrfs_set_token_file_extent_type(leaf, fi,
-						 BTRFS_FILE_EXTENT_PREALLOC,
-						 &token);
-	} else {
-		btrfs_set_token_file_extent_type(leaf, fi,
-						 BTRFS_FILE_EXTENT_REG,
-						 &token);
-		if (em->block_start == EXTENT_MAP_HOLE)
-			skip_csum = true;
-	}
-
-	block_len = max(em->block_len, em->orig_block_len);
-	if (em->compress_type != BTRFS_COMPRESS_NONE) {
-		btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
-							em->block_start,
-							&token);
-		btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
-							   &token);
-	} else if (em->block_start < EXTENT_MAP_LAST_BYTE) {
-		btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
-							em->block_start -
-							extent_offset, &token);
-		btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
-							   &token);
-	} else {
-		btrfs_set_token_file_extent_disk_bytenr(leaf, fi, 0, &token);
-		btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, 0,
-							   &token);
-	}
-
-	btrfs_set_token_file_extent_offset(leaf, fi,
-					   em->start - em->orig_start,
-					   &token);
-	btrfs_set_token_file_extent_num_bytes(leaf, fi, em->len, &token);
-	btrfs_set_token_file_extent_ram_bytes(leaf, fi, em->ram_bytes, &token);
-	btrfs_set_token_file_extent_compression(leaf, fi, em->compress_type,
-						&token);
-	btrfs_set_token_file_extent_encryption(leaf, fi, 0, &token);
-	btrfs_set_token_file_extent_other_encoding(leaf, fi, 0, &token);
-	btrfs_mark_buffer_dirty(leaf);
+	LIST_HEAD(ordered_sums);
+	int ret = 0;
 
-	btrfs_release_path(path);
-	if (ret) {
-		return ret;
-	}
+	*ordered_io_error = false;
 
-	if (skip_csum)
+	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+	    em->block_start == EXTENT_MAP_HOLE)
 		return 0;
 
 	/*
-	 * First check and see if our csums are on our outstanding ordered
-	 * extents.
+	 * Wait far any ordered extent that covers our extent map. If it
+	 * finishes without an error, first check and see if our csums are on
+	 * our outstanding ordered extents.
 	 */
 	list_for_each_entry(ordered, logged_list, log_list) {
 		struct btrfs_ordered_sum *sum;
@@ -3685,6 +3611,24 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 		    mod_start + mod_len <= ordered->file_offset)
 			continue;
 
+		if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
+		    !test_bit(BTRFS_ORDERED_IOERR, &ordered->flags) &&
+		    !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
+			const u64 start = ordered->file_offset;
+			const u64 end = ordered->file_offset + ordered->len - 1;
+
+			WARN_ON(ordered->inode != inode);
+			filemap_fdatawrite_range(inode->i_mapping, start, end);
+		}
+
+		wait_event(ordered->wait,
+			   (test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) ||
+			    test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)));
+
+		if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) {
+			*ordered_io_error = true;
+			break;
+		}
 		/*
 		 * We are going to copy all the csums on this ordered extent, so
 		 * go ahead and adjust mod_start and mod_len in case this
@@ -3716,6 +3660,9 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 			}
 		}
 
+		if (skip_csum)
+			continue;
+
 		/*
 		 * To keep us from looping for the above case of an ordered
 		 * extent that falls inside of the logged extent.
@@ -3733,18 +3680,16 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 		list_for_each_entry(sum, &ordered->list, list) {
 			ret = btrfs_csum_file_blocks(trans, log, sum);
 			if (ret)
-				goto unlocked;
+				break;
 		}
-
 	}
-unlocked:
 
-	if (!mod_len || ret)
+	if (*ordered_io_error || !mod_len || ret || skip_csum)
 		return ret;
 
 	if (em->compress_type) {
 		csum_offset = 0;
-		csum_len = block_len;
+		csum_len = max(em->block_len, em->orig_block_len);
 	} else {
 		csum_offset = mod_start - em->start;
 		csum_len = mod_len;
@@ -3771,11 +3716,106 @@ unlocked:
 	return ret;
 }
 
+static int log_one_extent(struct btrfs_trans_handle *trans,
+			  struct inode *inode, struct btrfs_root *root,
+			  const struct extent_map *em,
+			  struct btrfs_path *path,
+			  const struct list_head *logged_list,
+			  struct btrfs_log_ctx *ctx)
+{
+	struct btrfs_root *log = root->log_root;
+	struct btrfs_file_extent_item *fi;
+	struct extent_buffer *leaf;
+	struct btrfs_map_token token;
+	struct btrfs_key key;
+	u64 extent_offset = em->start - em->orig_start;
+	u64 block_len;
+	int ret;
+	int extent_inserted = 0;
+	bool ordered_io_err = false;
+
+	ret = wait_ordered_extents(trans, inode, root, em, logged_list,
+				   &ordered_io_err);
+	if (ret)
+		return ret;
+
+	if (ordered_io_err) {
+		ctx->io_err = -EIO;
+		return 0;
+	}
+
+	btrfs_init_map_token(&token);
+
+	ret = __btrfs_drop_extents(trans, log, inode, path, em->start,
+				   em->start + em->len, NULL, 0, 1,
+				   sizeof(*fi), &extent_inserted);
+	if (ret)
+		return ret;
+
+	if (!extent_inserted) {
+		key.objectid = btrfs_ino(inode);
+		key.type = BTRFS_EXTENT_DATA_KEY;
+		key.offset = em->start;
+
+		ret = btrfs_insert_empty_item(trans, log, path, &key,
+					      sizeof(*fi));
+		if (ret)
+			return ret;
+	}
+	leaf = path->nodes[0];
+	fi = btrfs_item_ptr(leaf, path->slots[0],
+			    struct btrfs_file_extent_item);
+
+	btrfs_set_token_file_extent_generation(leaf, fi, em->generation,
+					       &token);
+	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		btrfs_set_token_file_extent_type(leaf, fi,
+						 BTRFS_FILE_EXTENT_PREALLOC,
+						 &token);
+	else
+		btrfs_set_token_file_extent_type(leaf, fi,
+						 BTRFS_FILE_EXTENT_REG,
+						 &token);
+
+	block_len = max(em->block_len, em->orig_block_len);
+	if (em->compress_type != BTRFS_COMPRESS_NONE) {
+		btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
+							em->block_start,
+							&token);
+		btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
+							   &token);
+	} else if (em->block_start < EXTENT_MAP_LAST_BYTE) {
+		btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
+							em->block_start -
+							extent_offset, &token);
+		btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
+							   &token);
+	} else {
+		btrfs_set_token_file_extent_disk_bytenr(leaf, fi, 0, &token);
+		btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, 0,
+							   &token);
+	}
+
+	btrfs_set_token_file_extent_offset(leaf, fi, extent_offset, &token);
+	btrfs_set_token_file_extent_num_bytes(leaf, fi, em->len, &token);
+	btrfs_set_token_file_extent_ram_bytes(leaf, fi, em->ram_bytes, &token);
+	btrfs_set_token_file_extent_compression(leaf, fi, em->compress_type,
+						&token);
+	btrfs_set_token_file_extent_encryption(leaf, fi, 0, &token);
+	btrfs_set_token_file_extent_other_encoding(leaf, fi, 0, &token);
+	btrfs_mark_buffer_dirty(leaf);
+
+	btrfs_release_path(path);
+
+	return ret;
+}
+
 static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root,
 				     struct inode *inode,
 				     struct btrfs_path *path,
-				     struct list_head *logged_list)
+				     struct list_head *logged_list,
+				     struct btrfs_log_ctx *ctx)
 {
 	struct extent_map *em, *n;
 	struct list_head extents;
@@ -3833,7 +3873,8 @@ process:
 
 		write_unlock(&tree->lock);
 
-		ret = log_one_extent(trans, inode, root, em, path, logged_list);
+		ret = log_one_extent(trans, inode, root, em, path, logged_list,
+				     ctx);
 		write_lock(&tree->lock);
 		clear_em_logging(tree, em);
 		free_extent_map(em);
@@ -3863,7 +3904,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, struct inode *inode,
 			   int inode_only,
 			   const loff_t start,
-			   const loff_t end)
+			   const loff_t end,
+			   struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_path *path;
 	struct btrfs_path *dst_path;
@@ -3964,7 +4006,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		err = ret;
 		goto out_unlock;
 	}
-	path->keep_locks = 1;
 
 	while (1) {
 		ins_nr = 0;
@@ -4049,7 +4090,7 @@ log_extents:
 	btrfs_release_path(dst_path);
 	if (fast_search) {
 		ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
-						&logged_list);
+						&logged_list, ctx);
 		if (ret) {
 			err = ret;
 			goto out_unlock;
@@ -4239,7 +4280,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto end_no_trans;
 
-	ret = btrfs_log_inode(trans, root, inode, inode_only, start, end);
+	ret = btrfs_log_inode(trans, root, inode, inode_only, start, end, ctx);
 	if (ret)
 		goto end_trans;
 
@@ -4268,7 +4309,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		if (BTRFS_I(inode)->generation >
 		    root->fs_info->last_trans_committed) {
 			ret = btrfs_log_inode(trans, root, inode, inode_only,
-					      0, LLONG_MAX);
+					      0, LLONG_MAX, ctx);
 			if (ret)
 				goto end_trans;
 		}
@@ -4360,7 +4401,7 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)
 again:
 	key.objectid = BTRFS_TREE_LOG_OBJECTID;
 	key.offset = (u64)-1;
-	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
+	key.type = BTRFS_ROOT_ITEM_KEY;
 
 	while (1) {
 		ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0);
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index e2e798ae7cd7..154990c26dcb 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -28,6 +28,7 @@
 struct btrfs_log_ctx {
 	int log_ret;
 	int log_transid;
+	int io_err;
 	struct list_head list;
 };
 
@@ -35,6 +36,7 @@ static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx)
 {
 	ctx->log_ret = 0;
 	ctx->log_transid = 0;
+	ctx->io_err = 0;
 	INIT_LIST_HEAD(&ctx->list);
 }
 
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index f6a4c03ee7d8..778282944530 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -279,7 +279,6 @@ int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info,
 	key.offset = 0;
 
 again_search_slot:
-	path->keep_locks = 1;
 	ret = btrfs_search_forward(root, &key, path, 0);
 	if (ret) {
 		if (ret > 0)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 2c2d6d1d8eee..d47289c715c8 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -50,7 +50,7 @@ static void __btrfs_reset_dev_stats(struct btrfs_device *dev);
 static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev);
 static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
 
-static DEFINE_MUTEX(uuid_mutex);
+DEFINE_MUTEX(uuid_mutex);
 static LIST_HEAD(fs_uuids);
 
 static void lock_chunks(struct btrfs_root *root)
@@ -74,6 +74,7 @@ static struct btrfs_fs_devices *__alloc_fs_devices(void)
 	mutex_init(&fs_devs->device_list_mutex);
 
 	INIT_LIST_HEAD(&fs_devs->devices);
+	INIT_LIST_HEAD(&fs_devs->resized_devices);
 	INIT_LIST_HEAD(&fs_devs->alloc_list);
 	INIT_LIST_HEAD(&fs_devs->list);
 
@@ -154,11 +155,13 @@ static struct btrfs_device *__alloc_device(void)
 
 	INIT_LIST_HEAD(&dev->dev_list);
 	INIT_LIST_HEAD(&dev->dev_alloc_list);
+	INIT_LIST_HEAD(&dev->resized_list);
 
 	spin_lock_init(&dev->io_lock);
 
 	spin_lock_init(&dev->reada_lock);
 	atomic_set(&dev->reada_in_flight, 0);
+	atomic_set(&dev->dev_stats_ccnt, 0);
 	INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT);
 	INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT);
 
@@ -474,14 +477,13 @@ static noinline int device_list_add(const char *path,
 			return PTR_ERR(fs_devices);
 
 		list_add(&fs_devices->list, &fs_uuids);
-		fs_devices->latest_devid = devid;
-		fs_devices->latest_trans = found_transid;
 
 		device = NULL;
 	} else {
 		device = __find_device(&fs_devices->devices, devid,
 				       disk_super->dev_item.uuid);
 	}
+
 	if (!device) {
 		if (fs_devices->opened)
 			return -EBUSY;
@@ -565,10 +567,6 @@ static noinline int device_list_add(const char *path,
 	if (!fs_devices->opened)
 		device->generation = found_transid;
 
-	if (found_transid > fs_devices->latest_trans) {
-		fs_devices->latest_devid = devid;
-		fs_devices->latest_trans = found_transid;
-	}
 	*fs_devices_ret = fs_devices;
 
 	return ret;
@@ -584,8 +582,7 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 	if (IS_ERR(fs_devices))
 		return fs_devices;
 
-	fs_devices->latest_devid = orig->latest_devid;
-	fs_devices->latest_trans = orig->latest_trans;
+	mutex_lock(&orig->device_list_mutex);
 	fs_devices->total_devices = orig->total_devices;
 
 	/* We have held the volume lock, it is safe to get the devices. */
@@ -614,8 +611,10 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 		device->fs_devices = fs_devices;
 		fs_devices->num_devices++;
 	}
+	mutex_unlock(&orig->device_list_mutex);
 	return fs_devices;
 error:
+	mutex_unlock(&orig->device_list_mutex);
 	free_fs_devices(fs_devices);
 	return ERR_PTR(-ENOMEM);
 }
@@ -624,10 +623,7 @@ void btrfs_close_extra_devices(struct btrfs_fs_info *fs_info,
 			       struct btrfs_fs_devices *fs_devices, int step)
 {
 	struct btrfs_device *device, *next;
-
-	struct block_device *latest_bdev = NULL;
-	u64 latest_devid = 0;
-	u64 latest_transid = 0;
+	struct btrfs_device *latest_dev = NULL;
 
 	mutex_lock(&uuid_mutex);
 again:
@@ -635,11 +631,9 @@ again:
 	list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
 		if (device->in_fs_metadata) {
 			if (!device->is_tgtdev_for_dev_replace &&
-			    (!latest_transid ||
-			     device->generation > latest_transid)) {
-				latest_devid = device->devid;
-				latest_transid = device->generation;
-				latest_bdev = device->bdev;
+			    (!latest_dev ||
+			     device->generation > latest_dev->generation)) {
+				latest_dev = device;
 			}
 			continue;
 		}
@@ -681,9 +675,7 @@ again:
 		goto again;
 	}
 
-	fs_devices->latest_bdev = latest_bdev;
-	fs_devices->latest_devid = latest_devid;
-	fs_devices->latest_trans = latest_transid;
+	fs_devices->latest_bdev = latest_dev->bdev;
 
 	mutex_unlock(&uuid_mutex);
 }
@@ -732,8 +724,6 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 			fs_devices->rw_devices--;
 		}
 
-		if (device->can_discard)
-			fs_devices->num_can_discard--;
 		if (device->missing)
 			fs_devices->missing_devices--;
 
@@ -798,11 +788,9 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 	struct block_device *bdev;
 	struct list_head *head = &fs_devices->devices;
 	struct btrfs_device *device;
-	struct block_device *latest_bdev = NULL;
+	struct btrfs_device *latest_dev = NULL;
 	struct buffer_head *bh;
 	struct btrfs_super_block *disk_super;
-	u64 latest_devid = 0;
-	u64 latest_transid = 0;
 	u64 devid;
 	int seeding = 1;
 	int ret = 0;
@@ -830,11 +818,9 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 			goto error_brelse;
 
 		device->generation = btrfs_super_generation(disk_super);
-		if (!latest_transid || device->generation > latest_transid) {
-			latest_devid = devid;
-			latest_transid = device->generation;
-			latest_bdev = bdev;
-		}
+		if (!latest_dev ||
+		    device->generation > latest_dev->generation)
+			latest_dev = device;
 
 		if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING) {
 			device->writeable = 0;
@@ -844,10 +830,8 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		}
 
 		q = bdev_get_queue(bdev);
-		if (blk_queue_discard(q)) {
+		if (blk_queue_discard(q))
 			device->can_discard = 1;
-			fs_devices->num_can_discard++;
-		}
 
 		device->bdev = bdev;
 		device->in_fs_metadata = 0;
@@ -877,9 +861,7 @@ error_brelse:
 	}
 	fs_devices->seeding = seeding;
 	fs_devices->opened = 1;
-	fs_devices->latest_bdev = latest_bdev;
-	fs_devices->latest_devid = latest_devid;
-	fs_devices->latest_trans = latest_transid;
+	fs_devices->latest_bdev = latest_dev->bdev;
 	fs_devices->total_rw_bytes = 0;
 out:
 	return ret;
@@ -1053,7 +1035,7 @@ int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
 		if (key.objectid > device->devid)
 			break;
 
-		if (btrfs_key_type(&key) != BTRFS_DEV_EXTENT_KEY)
+		if (key.type != BTRFS_DEV_EXTENT_KEY)
 			goto next;
 
 		dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
@@ -1205,7 +1187,7 @@ again:
 		if (key.objectid > device->devid)
 			break;
 
-		if (btrfs_key_type(&key) != BTRFS_DEV_EXTENT_KEY)
+		if (key.type != BTRFS_DEV_EXTENT_KEY)
 			goto next;
 
 		if (key.offset > search_start) {
@@ -1284,7 +1266,7 @@ out:
 
 static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
 			  struct btrfs_device *device,
-			  u64 start)
+			  u64 start, u64 *dev_extent_len)
 {
 	int ret;
 	struct btrfs_path *path;
@@ -1326,13 +1308,8 @@ again:
 		goto out;
 	}
 
-	if (device->bytes_used > 0) {
-		u64 len = btrfs_dev_extent_length(leaf, extent);
-		device->bytes_used -= len;
-		spin_lock(&root->fs_info->free_chunk_lock);
-		root->fs_info->free_chunk_space += len;
-		spin_unlock(&root->fs_info->free_chunk_lock);
-	}
+	*dev_extent_len = btrfs_dev_extent_length(leaf, extent);
+
 	ret = btrfs_del_item(trans, root, path);
 	if (ret) {
 		btrfs_error(root->fs_info, ret,
@@ -1482,8 +1459,10 @@ static int btrfs_add_device(struct btrfs_trans_handle *trans,
 	btrfs_set_device_io_align(leaf, dev_item, device->io_align);
 	btrfs_set_device_io_width(leaf, dev_item, device->io_width);
 	btrfs_set_device_sector_size(leaf, dev_item, device->sector_size);
-	btrfs_set_device_total_bytes(leaf, dev_item, device->disk_total_bytes);
-	btrfs_set_device_bytes_used(leaf, dev_item, device->bytes_used);
+	btrfs_set_device_total_bytes(leaf, dev_item,
+				     btrfs_device_get_disk_total_bytes(device));
+	btrfs_set_device_bytes_used(leaf, dev_item,
+				    btrfs_device_get_bytes_used(device));
 	btrfs_set_device_group(leaf, dev_item, 0);
 	btrfs_set_device_seek_speed(leaf, dev_item, 0);
 	btrfs_set_device_bandwidth(leaf, dev_item, 0);
@@ -1539,7 +1518,6 @@ static int btrfs_rm_dev_item(struct btrfs_root *root,
 	key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
 	key.type = BTRFS_DEV_ITEM_KEY;
 	key.offset = device->devid;
-	lock_chunks(root);
 
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret < 0)
@@ -1555,7 +1533,6 @@ static int btrfs_rm_dev_item(struct btrfs_root *root,
 		goto out;
 out:
 	btrfs_free_path(path);
-	unlock_chunks(root);
 	btrfs_commit_transaction(trans, root);
 	return ret;
 }
@@ -1671,8 +1648,8 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	if (device->writeable) {
 		lock_chunks(root);
 		list_del_init(&device->dev_alloc_list);
+		device->fs_devices->rw_devices--;
 		unlock_chunks(root);
-		root->fs_info->fs_devices->rw_devices--;
 		clear_super = true;
 	}
 
@@ -1691,11 +1668,6 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	if (ret)
 		goto error_undo;
 
-	spin_lock(&root->fs_info->free_chunk_lock);
-	root->fs_info->free_chunk_space = device->total_bytes -
-		device->bytes_used;
-	spin_unlock(&root->fs_info->free_chunk_lock);
-
 	device->in_fs_metadata = 0;
 	btrfs_scrub_cancel_dev(root->fs_info, device);
 
@@ -1749,9 +1721,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 			fs_devices = fs_devices->seed;
 		}
 		cur_devices->seed = NULL;
-		lock_chunks(root);
 		__btrfs_close_devices(cur_devices);
-		unlock_chunks(root);
 		free_fs_devices(cur_devices);
 	}
 
@@ -1824,8 +1794,8 @@ error_undo:
 		lock_chunks(root);
 		list_add(&device->dev_alloc_list,
 			 &root->fs_info->fs_devices->alloc_list);
+		device->fs_devices->rw_devices++;
 		unlock_chunks(root);
-		root->fs_info->fs_devices->rw_devices++;
 	}
 	goto error_brelse;
 }
@@ -1833,29 +1803,57 @@ error_undo:
 void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info,
 				 struct btrfs_device *srcdev)
 {
+	struct btrfs_fs_devices *fs_devices;
+
 	WARN_ON(!mutex_is_locked(&fs_info->fs_devices->device_list_mutex));
 
+	/*
+	 * in case of fs with no seed, srcdev->fs_devices will point
+	 * to fs_devices of fs_info. However when the dev being replaced is
+	 * a seed dev it will point to the seed's local fs_devices. In short
+	 * srcdev will have its correct fs_devices in both the cases.
+	 */
+	fs_devices = srcdev->fs_devices;
+
 	list_del_rcu(&srcdev->dev_list);
 	list_del_rcu(&srcdev->dev_alloc_list);
-	fs_info->fs_devices->num_devices--;
-	if (srcdev->missing) {
-		fs_info->fs_devices->missing_devices--;
-		fs_info->fs_devices->rw_devices++;
-	}
-	if (srcdev->can_discard)
-		fs_info->fs_devices->num_can_discard--;
-	if (srcdev->bdev) {
-		fs_info->fs_devices->open_devices--;
+	fs_devices->num_devices--;
+	if (srcdev->missing)
+		fs_devices->missing_devices--;
 
-		/*
-		 * zero out the old super if it is not writable
-		 * (e.g. seed device)
-		 */
-		if (srcdev->writeable)
-			btrfs_scratch_superblock(srcdev);
+	if (srcdev->writeable) {
+		fs_devices->rw_devices--;
+		/* zero out the old super if it is writable */
+		btrfs_scratch_superblock(srcdev);
 	}
 
+	if (srcdev->bdev)
+		fs_devices->open_devices--;
+
 	call_rcu(&srcdev->rcu, free_device);
+
+	/*
+	 * unless fs_devices is seed fs, num_devices shouldn't go
+	 * zero
+	 */
+	BUG_ON(!fs_devices->num_devices && !fs_devices->seeding);
+
+	/* if this is no devs we rather delete the fs_devices */
+	if (!fs_devices->num_devices) {
+		struct btrfs_fs_devices *tmp_fs_devices;
+
+		tmp_fs_devices = fs_info->fs_devices;
+		while (tmp_fs_devices) {
+			if (tmp_fs_devices->seed == fs_devices) {
+				tmp_fs_devices->seed = fs_devices->seed;
+				break;
+			}
+			tmp_fs_devices = tmp_fs_devices->seed;
+		}
+		fs_devices->seed = NULL;
+		__btrfs_close_devices(fs_devices);
+		free_fs_devices(fs_devices);
+	}
 }
 
 void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
@@ -1863,6 +1861,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_device *next_device;
 
+	mutex_lock(&uuid_mutex);
 	WARN_ON(!tgtdev);
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	if (tgtdev->bdev) {
@@ -1870,8 +1869,6 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		fs_info->fs_devices->open_devices--;
 	}
 	fs_info->fs_devices->num_devices--;
-	if (tgtdev->can_discard)
-		fs_info->fs_devices->num_can_discard++;
 
 	next_device = list_entry(fs_info->fs_devices->devices.next,
 				 struct btrfs_device, dev_list);
@@ -1884,6 +1881,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	call_rcu(&tgtdev->rcu, free_device);
 
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&uuid_mutex);
 }
 
 static int btrfs_find_device_by_path(struct btrfs_root *root, char *device_path,
@@ -1982,17 +1980,17 @@ static int btrfs_prepare_sprout(struct btrfs_root *root)
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 	list_splice_init_rcu(&fs_devices->devices, &seed_devices->devices,
 			      synchronize_rcu);
+	list_for_each_entry(device, &seed_devices->devices, dev_list)
+		device->fs_devices = seed_devices;
 
+	lock_chunks(root);
 	list_splice_init(&fs_devices->alloc_list, &seed_devices->alloc_list);
-	list_for_each_entry(device, &seed_devices->devices, dev_list) {
-		device->fs_devices = seed_devices;
-	}
+	unlock_chunks(root);
 
 	fs_devices->seeding = 0;
 	fs_devices->num_devices = 0;
 	fs_devices->open_devices = 0;
 	fs_devices->missing_devices = 0;
-	fs_devices->num_can_discard = 0;
 	fs_devices->rotating = 0;
 	fs_devices->seed = seed_devices;
 
@@ -2092,7 +2090,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	struct list_head *devices;
 	struct super_block *sb = root->fs_info->sb;
 	struct rcu_string *name;
-	u64 total_bytes;
+	u64 tmp;
 	int seeding_dev = 0;
 	int ret = 0;
 
@@ -2148,8 +2146,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 		goto error;
 	}
 
-	lock_chunks(root);
-
 	q = bdev_get_queue(bdev);
 	if (blk_queue_discard(q))
 		device->can_discard = 1;
@@ -2160,6 +2156,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	device->sector_size = root->sectorsize;
 	device->total_bytes = i_size_read(bdev->bd_inode);
 	device->disk_total_bytes = device->total_bytes;
+	device->commit_total_bytes = device->total_bytes;
 	device->dev_root = root->fs_info->dev_root;
 	device->bdev = bdev;
 	device->in_fs_metadata = 1;
@@ -2177,6 +2174,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	device->fs_devices = root->fs_info->fs_devices;
 
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
+	lock_chunks(root);
 	list_add_rcu(&device->dev_list, &root->fs_info->fs_devices->devices);
 	list_add(&device->dev_alloc_list,
 		 &root->fs_info->fs_devices->alloc_list);
@@ -2184,8 +2182,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	root->fs_info->fs_devices->open_devices++;
 	root->fs_info->fs_devices->rw_devices++;
 	root->fs_info->fs_devices->total_devices++;
-	if (device->can_discard)
-		root->fs_info->fs_devices->num_can_discard++;
 	root->fs_info->fs_devices->total_rw_bytes += device->total_bytes;
 
 	spin_lock(&root->fs_info->free_chunk_lock);
@@ -2195,26 +2191,45 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	if (!blk_queue_nonrot(bdev_get_queue(bdev)))
 		root->fs_info->fs_devices->rotating = 1;
 
-	total_bytes = btrfs_super_total_bytes(root->fs_info->super_copy);
+	tmp = btrfs_super_total_bytes(root->fs_info->super_copy);
 	btrfs_set_super_total_bytes(root->fs_info->super_copy,
-				    total_bytes + device->total_bytes);
+				    tmp + device->total_bytes);
 
-	total_bytes = btrfs_super_num_devices(root->fs_info->super_copy);
+	tmp = btrfs_super_num_devices(root->fs_info->super_copy);
 	btrfs_set_super_num_devices(root->fs_info->super_copy,
-				    total_bytes + 1);
+				    tmp + 1);
 
 	/* add sysfs device entry */
 	btrfs_kobj_add_device(root->fs_info, device);
 
+	/*
+	 * we've got more storage, clear any full flags on the space
+	 * infos
+	 */
+	btrfs_clear_space_info_full(root->fs_info);
+
+	unlock_chunks(root);
 	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 
 	if (seeding_dev) {
-		char fsid_buf[BTRFS_UUID_UNPARSED_SIZE];
+		lock_chunks(root);
 		ret = init_first_rw_device(trans, root, device);
+		unlock_chunks(root);
 		if (ret) {
 			btrfs_abort_transaction(trans, root, ret);
 			goto error_trans;
 		}
+	}
+
+	ret = btrfs_add_device(trans, root, device);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto error_trans;
+	}
+
+	if (seeding_dev) {
+		char fsid_buf[BTRFS_UUID_UNPARSED_SIZE];
+
 		ret = btrfs_finish_sprout(trans, root);
 		if (ret) {
 			btrfs_abort_transaction(trans, root, ret);
@@ -2228,21 +2243,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 						root->fs_info->fsid);
 		if (kobject_rename(&root->fs_info->super_kobj, fsid_buf))
 			goto error_trans;
-	} else {
-		ret = btrfs_add_device(trans, root, device);
-		if (ret) {
-			btrfs_abort_transaction(trans, root, ret);
-			goto error_trans;
-		}
 	}
 
-	/*
-	 * we've got more storage, clear any full flags on the space
-	 * infos
-	 */
-	btrfs_clear_space_info_full(root->fs_info);
-
-	unlock_chunks(root);
 	root->fs_info->num_tolerated_disk_barrier_failures =
 		btrfs_calc_num_tolerated_disk_barrier_failures(root->fs_info);
 	ret = btrfs_commit_transaction(trans, root);
@@ -2274,7 +2276,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	return ret;
 
 error_trans:
-	unlock_chunks(root);
 	btrfs_end_transaction(trans, root);
 	rcu_string_free(device->name);
 	btrfs_kobj_rm_device(root->fs_info, device);
@@ -2289,6 +2290,7 @@ error:
 }
 
 int btrfs_init_dev_replace_tgtdev(struct btrfs_root *root, char *device_path,
+				  struct btrfs_device *srcdev,
 				  struct btrfs_device **device_out)
 {
 	struct request_queue *q;
@@ -2301,24 +2303,38 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_root *root, char *device_path,
 	int ret = 0;
 
 	*device_out = NULL;
-	if (fs_info->fs_devices->seeding)
+	if (fs_info->fs_devices->seeding) {
+		btrfs_err(fs_info, "the filesystem is a seed filesystem!");
 		return -EINVAL;
+	}
 
 	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
 				  fs_info->bdev_holder);
-	if (IS_ERR(bdev))
+	if (IS_ERR(bdev)) {
+		btrfs_err(fs_info, "target device %s is invalid!", device_path);
 		return PTR_ERR(bdev);
+	}
 
 	filemap_write_and_wait(bdev->bd_inode->i_mapping);
 
 	devices = &fs_info->fs_devices->devices;
 	list_for_each_entry(device, devices, dev_list) {
 		if (device->bdev == bdev) {
+			btrfs_err(fs_info, "target device is in the filesystem!");
 			ret = -EEXIST;
 			goto error;
 		}
 	}
 
+
+	if (i_size_read(bdev->bd_inode) <
+	    btrfs_device_get_total_bytes(srcdev)) {
+		btrfs_err(fs_info, "target device is smaller than source device!");
+		ret = -EINVAL;
+		goto error;
+	}
+
+
 	device = btrfs_alloc_device(NULL, &devid, NULL);
 	if (IS_ERR(device)) {
 		ret = PTR_ERR(device);
@@ -2342,8 +2358,12 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_root *root, char *device_path,
 	device->io_width = root->sectorsize;
 	device->io_align = root->sectorsize;
 	device->sector_size = root->sectorsize;
-	device->total_bytes = i_size_read(bdev->bd_inode);
-	device->disk_total_bytes = device->total_bytes;
+	device->total_bytes = btrfs_device_get_total_bytes(srcdev);
+	device->disk_total_bytes = btrfs_device_get_disk_total_bytes(srcdev);
+	device->bytes_used = btrfs_device_get_bytes_used(srcdev);
+	ASSERT(list_empty(&srcdev->resized_list));
+	device->commit_total_bytes = srcdev->commit_total_bytes;
+	device->commit_bytes_used = device->bytes_used;
 	device->dev_root = fs_info->dev_root;
 	device->bdev = bdev;
 	device->in_fs_metadata = 1;
@@ -2355,8 +2375,6 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_root *root, char *device_path,
 	list_add(&device->dev_list, &fs_info->fs_devices->devices);
 	fs_info->fs_devices->num_devices++;
 	fs_info->fs_devices->open_devices++;
-	if (device->can_discard)
-		fs_info->fs_devices->num_can_discard++;
 	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 
 	*device_out = device;
@@ -2415,8 +2433,10 @@ static noinline int btrfs_update_device(struct btrfs_trans_handle *trans,
 	btrfs_set_device_io_align(leaf, dev_item, device->io_align);
 	btrfs_set_device_io_width(leaf, dev_item, device->io_width);
 	btrfs_set_device_sector_size(leaf, dev_item, device->sector_size);
-	btrfs_set_device_total_bytes(leaf, dev_item, device->disk_total_bytes);
-	btrfs_set_device_bytes_used(leaf, dev_item, device->bytes_used);
+	btrfs_set_device_total_bytes(leaf, dev_item,
+				     btrfs_device_get_disk_total_bytes(device));
+	btrfs_set_device_bytes_used(leaf, dev_item,
+				    btrfs_device_get_bytes_used(device));
 	btrfs_mark_buffer_dirty(leaf);
 
 out:
@@ -2424,40 +2444,44 @@ out:
 	return ret;
 }
 
-static int __btrfs_grow_device(struct btrfs_trans_handle *trans,
+int btrfs_grow_device(struct btrfs_trans_handle *trans,
 		      struct btrfs_device *device, u64 new_size)
 {
 	struct btrfs_super_block *super_copy =
 		device->dev_root->fs_info->super_copy;
-	u64 old_total = btrfs_super_total_bytes(super_copy);
-	u64 diff = new_size - device->total_bytes;
+	struct btrfs_fs_devices *fs_devices;
+	u64 old_total;
+	u64 diff;
 
 	if (!device->writeable)
 		return -EACCES;
+
+	lock_chunks(device->dev_root);
+	old_total = btrfs_super_total_bytes(super_copy);
+	diff = new_size - device->total_bytes;
+
 	if (new_size <= device->total_bytes ||
-	    device->is_tgtdev_for_dev_replace)
+	    device->is_tgtdev_for_dev_replace) {
+		unlock_chunks(device->dev_root);
 		return -EINVAL;
+	}
+
+	fs_devices = device->dev_root->fs_info->fs_devices;
 
 	btrfs_set_super_total_bytes(super_copy, old_total + diff);
 	device->fs_devices->total_rw_bytes += diff;
 
-	device->total_bytes = new_size;
-	device->disk_total_bytes = new_size;
+	btrfs_device_set_total_bytes(device, new_size);
+	btrfs_device_set_disk_total_bytes(device, new_size);
 	btrfs_clear_space_info_full(device->dev_root->fs_info);
+	if (list_empty(&device->resized_list))
+		list_add_tail(&device->resized_list,
+			      &fs_devices->resized_devices);
+	unlock_chunks(device->dev_root);
 
 	return btrfs_update_device(trans, device);
 }
 
-int btrfs_grow_device(struct btrfs_trans_handle *trans,
-		      struct btrfs_device *device, u64 new_size)
-{
-	int ret;
-	lock_chunks(device->dev_root);
-	ret = __btrfs_grow_device(trans, device, new_size);
-	unlock_chunks(device->dev_root);
-	return ret;
-}
-
 static int btrfs_free_chunk(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root,
 			    u64 chunk_tree, u64 chunk_objectid,
@@ -2509,6 +2533,7 @@ static int btrfs_del_sys_chunk(struct btrfs_root *root, u64 chunk_objectid, u64
 	u32 cur;
 	struct btrfs_key key;
 
+	lock_chunks(root);
 	array_size = btrfs_super_sys_array_size(super_copy);
 
 	ptr = super_copy->sys_chunk_array;
@@ -2538,79 +2563,95 @@ static int btrfs_del_sys_chunk(struct btrfs_root *root, u64 chunk_objectid, u64
 			cur += len;
 		}
 	}
+	unlock_chunks(root);
 	return ret;
 }
 
-static int btrfs_relocate_chunk(struct btrfs_root *root,
-			 u64 chunk_tree, u64 chunk_objectid,
-			 u64 chunk_offset)
+int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
+		       struct btrfs_root *root, u64 chunk_offset)
 {
 	struct extent_map_tree *em_tree;
-	struct btrfs_root *extent_root;
-	struct btrfs_trans_handle *trans;
 	struct extent_map *em;
+	struct btrfs_root *extent_root = root->fs_info->extent_root;
 	struct map_lookup *map;
-	int ret;
-	int i;
+	u64 dev_extent_len = 0;
+	u64 chunk_objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
+	u64 chunk_tree = root->fs_info->chunk_root->objectid;
+	int i, ret = 0;
 
+	/* Just in case */
 	root = root->fs_info->chunk_root;
-	extent_root = root->fs_info->extent_root;
 	em_tree = &root->fs_info->mapping_tree.map_tree;
 
-	ret = btrfs_can_relocate(extent_root, chunk_offset);
-	if (ret)
-		return -ENOSPC;
-
-	/* step one, relocate all the extents inside this chunk */
-	ret = btrfs_relocate_block_group(extent_root, chunk_offset);
-	if (ret)
-		return ret;
-
-	trans = btrfs_start_transaction(root, 0);
-	if (IS_ERR(trans)) {
-		ret = PTR_ERR(trans);
-		btrfs_std_error(root->fs_info, ret);
-		return ret;
-	}
-
-	lock_chunks(root);
-
-	/*
-	 * step two, delete the device extents and the
-	 * chunk tree entries
-	 */
 	read_lock(&em_tree->lock);
 	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
 	read_unlock(&em_tree->lock);
 
-	BUG_ON(!em || em->start > chunk_offset ||
-	       em->start + em->len < chunk_offset);
+	if (!em || em->start > chunk_offset ||
+	    em->start + em->len < chunk_offset) {
+		/*
+		 * This is a logic error, but we don't want to just rely on the
+		 * user having built with ASSERT enabled, so if ASSERT doens't
+		 * do anything we still error out.
+		 */
+		ASSERT(0);
+		if (em)
+			free_extent_map(em);
+		return -EINVAL;
+	}
 	map = (struct map_lookup *)em->bdev;
 
 	for (i = 0; i < map->num_stripes; i++) {
-		ret = btrfs_free_dev_extent(trans, map->stripes[i].dev,
-					    map->stripes[i].physical);
-		BUG_ON(ret);
+		struct btrfs_device *device = map->stripes[i].dev;
+		ret = btrfs_free_dev_extent(trans, device,
+					    map->stripes[i].physical,
+					    &dev_extent_len);
+		if (ret) {
+			btrfs_abort_transaction(trans, root, ret);
+			goto out;
+		}
+
+		if (device->bytes_used > 0) {
+			lock_chunks(root);
+			btrfs_device_set_bytes_used(device,
+					device->bytes_used - dev_extent_len);
+			spin_lock(&root->fs_info->free_chunk_lock);
+			root->fs_info->free_chunk_space += dev_extent_len;
+			spin_unlock(&root->fs_info->free_chunk_lock);
+			btrfs_clear_space_info_full(root->fs_info);
+			unlock_chunks(root);
+		}
 
 		if (map->stripes[i].dev) {
 			ret = btrfs_update_device(trans, map->stripes[i].dev);
-			BUG_ON(ret);
+			if (ret) {
+				btrfs_abort_transaction(trans, root, ret);
+				goto out;
+			}
 		}
 	}
 	ret = btrfs_free_chunk(trans, root, chunk_tree, chunk_objectid,
 			       chunk_offset);
-
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto out;
+	}
 
 	trace_btrfs_chunk_free(root, map, chunk_offset, em->len);
 
 	if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
 		ret = btrfs_del_sys_chunk(root, chunk_objectid, chunk_offset);
-		BUG_ON(ret);
+		if (ret) {
+			btrfs_abort_transaction(trans, root, ret);
+			goto out;
+		}
 	}
 
 	ret = btrfs_remove_block_group(trans, extent_root, chunk_offset);
-	BUG_ON(ret);
+	if (ret) {
+		btrfs_abort_transaction(trans, extent_root, ret);
+		goto out;
+	}
 
 	write_lock(&em_tree->lock);
 	remove_extent_mapping(em_tree, em);
@@ -2618,12 +2659,46 @@ static int btrfs_relocate_chunk(struct btrfs_root *root,
 
 	/* once for the tree */
 	free_extent_map(em);
+out:
 	/* once for us */
 	free_extent_map(em);
+	return ret;
+}
 
-	unlock_chunks(root);
+static int btrfs_relocate_chunk(struct btrfs_root *root,
+			 u64 chunk_tree, u64 chunk_objectid,
+			 u64 chunk_offset)
+{
+	struct btrfs_root *extent_root;
+	struct btrfs_trans_handle *trans;
+	int ret;
+
+	root = root->fs_info->chunk_root;
+	extent_root = root->fs_info->extent_root;
+
+	ret = btrfs_can_relocate(extent_root, chunk_offset);
+	if (ret)
+		return -ENOSPC;
+
+	/* step one, relocate all the extents inside this chunk */
+	ret = btrfs_relocate_block_group(extent_root, chunk_offset);
+	if (ret)
+		return ret;
+
+	trans = btrfs_start_transaction(root, 0);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		btrfs_std_error(root->fs_info, ret);
+		return ret;
+	}
+
+	/*
+	 * step two, delete the device extents and the
+	 * chunk tree entries
+	 */
+	ret = btrfs_remove_chunk(trans, root, chunk_offset);
 	btrfs_end_transaction(trans, root);
-	return 0;
+	return ret;
 }
 
 static int btrfs_relocate_sys_chunks(struct btrfs_root *root)
@@ -2676,8 +2751,8 @@ again:
 						   found_key.offset);
 			if (ret == -ENOSPC)
 				failed++;
-			else if (ret)
-				BUG();
+			else
+				BUG_ON(ret);
 		}
 
 		if (found_key.offset == 0)
@@ -3084,11 +3159,12 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 	/* step one make some room on all the devices */
 	devices = &fs_info->fs_devices->devices;
 	list_for_each_entry(device, devices, dev_list) {
-		old_size = device->total_bytes;
+		old_size = btrfs_device_get_total_bytes(device);
 		size_to_free = div_factor(old_size, 1);
 		size_to_free = min(size_to_free, (u64)1 * 1024 * 1024);
 		if (!device->writeable ||
-		    device->total_bytes - device->bytes_used > size_to_free ||
+		    btrfs_device_get_total_bytes(device) -
+		    btrfs_device_get_bytes_used(device) > size_to_free ||
 		    device->is_tgtdev_for_dev_replace)
 			continue;
 
@@ -3643,8 +3719,6 @@ static int btrfs_uuid_scan_kthread(void *data)
 	max_key.type = BTRFS_ROOT_ITEM_KEY;
 	max_key.offset = (u64)-1;
 
-	path->keep_locks = 1;
-
 	while (1) {
 		ret = btrfs_search_forward(root, &key, path, 0);
 		if (ret) {
@@ -3896,8 +3970,8 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size)
 	struct btrfs_key key;
 	struct btrfs_super_block *super_copy = root->fs_info->super_copy;
 	u64 old_total = btrfs_super_total_bytes(super_copy);
-	u64 old_size = device->total_bytes;
-	u64 diff = device->total_bytes - new_size;
+	u64 old_size = btrfs_device_get_total_bytes(device);
+	u64 diff = old_size - new_size;
 
 	if (device->is_tgtdev_for_dev_replace)
 		return -EINVAL;
@@ -3910,7 +3984,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size)
 
 	lock_chunks(root);
 
-	device->total_bytes = new_size;
+	btrfs_device_set_total_bytes(device, new_size);
 	if (device->writeable) {
 		device->fs_devices->total_rw_bytes -= diff;
 		spin_lock(&root->fs_info->free_chunk_lock);
@@ -3976,7 +4050,7 @@ again:
 		ret = -ENOSPC;
 		lock_chunks(root);
 
-		device->total_bytes = old_size;
+		btrfs_device_set_total_bytes(device, old_size);
 		if (device->writeable)
 			device->fs_devices->total_rw_bytes += diff;
 		spin_lock(&root->fs_info->free_chunk_lock);
@@ -3994,18 +4068,17 @@ again:
 	}
 
 	lock_chunks(root);
+	btrfs_device_set_disk_total_bytes(device, new_size);
+	if (list_empty(&device->resized_list))
+		list_add_tail(&device->resized_list,
+			      &root->fs_info->fs_devices->resized_devices);
 
-	device->disk_total_bytes = new_size;
-	/* Now btrfs_update_device() will change the on-disk size. */
-	ret = btrfs_update_device(trans, device);
-	if (ret) {
-		unlock_chunks(root);
-		btrfs_end_transaction(trans, root);
-		goto done;
-	}
 	WARN_ON(diff > old_total);
 	btrfs_set_super_total_bytes(super_copy, old_total - diff);
 	unlock_chunks(root);
+
+	/* Now btrfs_update_device() will change the on-disk size. */
+	ret = btrfs_update_device(trans, device);
 	btrfs_end_transaction(trans, root);
 done:
 	btrfs_free_path(path);
@@ -4021,10 +4094,13 @@ static int btrfs_add_system_chunk(struct btrfs_root *root,
 	u32 array_size;
 	u8 *ptr;
 
+	lock_chunks(root);
 	array_size = btrfs_super_sys_array_size(super_copy);
 	if (array_size + item_size + sizeof(disk_key)
-			> BTRFS_SYSTEM_CHUNK_ARRAY_SIZE)
+			> BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
+		unlock_chunks(root);
 		return -EFBIG;
+	}
 
 	ptr = super_copy->sys_chunk_array + array_size;
 	btrfs_cpu_key_to_disk(&disk_key, key);
@@ -4033,6 +4109,8 @@ static int btrfs_add_system_chunk(struct btrfs_root *root,
 	memcpy(ptr, chunk, item_size);
 	item_size += sizeof(disk_key);
 	btrfs_set_super_sys_array_size(super_copy, array_size + item_size);
+	unlock_chunks(root);
+
 	return 0;
 }
 
@@ -4402,6 +4480,16 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto error_del_extent;
 
+	for (i = 0; i < map->num_stripes; i++) {
+		num_bytes = map->stripes[i].dev->bytes_used + stripe_size;
+		btrfs_device_set_bytes_used(map->stripes[i].dev, num_bytes);
+	}
+
+	spin_lock(&extent_root->fs_info->free_chunk_lock);
+	extent_root->fs_info->free_chunk_space -= (stripe_size *
+						   map->num_stripes);
+	spin_unlock(&extent_root->fs_info->free_chunk_lock);
+
 	free_extent_map(em);
 	check_raid56_incompat_flag(extent_root->fs_info, type);
 
@@ -4473,7 +4561,6 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 		device = map->stripes[i].dev;
 		dev_offset = map->stripes[i].physical;
 
-		device->bytes_used += stripe_size;
 		ret = btrfs_update_device(trans, device);
 		if (ret)
 			goto out;
@@ -4486,11 +4573,6 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 			goto out;
 	}
 
-	spin_lock(&extent_root->fs_info->free_chunk_lock);
-	extent_root->fs_info->free_chunk_space -= (stripe_size *
-						   map->num_stripes);
-	spin_unlock(&extent_root->fs_info->free_chunk_lock);
-
 	stripe = &chunk->stripe;
 	for (i = 0; i < map->num_stripes; i++) {
 		device = map->stripes[i].dev;
@@ -4570,16 +4652,25 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans,
 	alloc_profile = btrfs_get_alloc_profile(fs_info->chunk_root, 0);
 	ret = __btrfs_alloc_chunk(trans, extent_root, sys_chunk_offset,
 				  alloc_profile);
-	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
-		goto out;
+	return ret;
+}
+
+static inline int btrfs_chunk_max_errors(struct map_lookup *map)
+{
+	int max_errors;
+
+	if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
+			 BTRFS_BLOCK_GROUP_RAID10 |
+			 BTRFS_BLOCK_GROUP_RAID5 |
+			 BTRFS_BLOCK_GROUP_DUP)) {
+		max_errors = 1;
+	} else if (map->type & BTRFS_BLOCK_GROUP_RAID6) {
+		max_errors = 2;
+	} else {
+		max_errors = 0;
 	}
 
-	ret = btrfs_add_device(trans, fs_info->chunk_root, device);
-	if (ret)
-		btrfs_abort_transaction(trans, root, ret);
-out:
-	return ret;
+	return max_errors;
 }
 
 int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
@@ -4588,6 +4679,7 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
 	struct map_lookup *map;
 	struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
 	int readonly = 0;
+	int miss_ndevs = 0;
 	int i;
 
 	read_lock(&map_tree->map_tree.lock);
@@ -4596,18 +4688,27 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
 	if (!em)
 		return 1;
 
-	if (btrfs_test_opt(root, DEGRADED)) {
-		free_extent_map(em);
-		return 0;
-	}
-
 	map = (struct map_lookup *)em->bdev;
 	for (i = 0; i < map->num_stripes; i++) {
+		if (map->stripes[i].dev->missing) {
+			miss_ndevs++;
+			continue;
+		}
+
 		if (!map->stripes[i].dev->writeable) {
 			readonly = 1;
-			break;
+			goto end;
 		}
 	}
+
+	/*
+	 * If the number of missing devices is larger than max errors,
+	 * we can not write the data into that chunk successfully, so
+	 * set it readonly.
+	 */
+	if (miss_ndevs > btrfs_chunk_max_errors(map))
+		readonly = 1;
+end:
 	free_extent_map(em);
 	return readonly;
 }
@@ -5008,6 +5109,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 			num_stripes = min_t(u64, map->num_stripes,
 					    stripe_nr_end - stripe_nr_orig);
 		stripe_index = do_div(stripe_nr, map->num_stripes);
+		if (!(rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS)))
+			mirror_num = 1;
 	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
 		if (rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS))
 			num_stripes = map->num_stripes;
@@ -5111,6 +5214,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 			/* We distribute the parity blocks across stripes */
 			tmp = stripe_nr + stripe_index;
 			stripe_index = do_div(tmp, map->num_stripes);
+			if (!(rw & (REQ_WRITE | REQ_DISCARD |
+				    REQ_GET_READ_MIRRORS)) && mirror_num <= 1)
+				mirror_num = 1;
 		}
 	} else {
 		/*
@@ -5218,16 +5324,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 		}
 	}
 
-	if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) {
-		if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
-				 BTRFS_BLOCK_GROUP_RAID10 |
-				 BTRFS_BLOCK_GROUP_RAID5 |
-				 BTRFS_BLOCK_GROUP_DUP)) {
-			max_errors = 1;
-		} else if (map->type & BTRFS_BLOCK_GROUP_RAID6) {
-			max_errors = 2;
-		}
-	}
+	if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS))
+		max_errors = btrfs_chunk_max_errors(map);
 
 	if (dev_replace_is_ongoing && (rw & (REQ_WRITE | REQ_DISCARD)) &&
 	    dev_replace->tgtdev != NULL) {
@@ -5610,8 +5708,8 @@ static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
 		name = rcu_dereference(dev->name);
 		pr_debug("btrfs_map_bio: rw %d, sector=%llu, dev=%lu "
 			 "(%s id %llu), size=%u\n", rw,
-			 (u64)bio->bi_sector, (u_long)dev->bdev->bd_dev,
-			 name->str, dev->devid, bio->bi_size);
+			 (u64)bio->bi_iter.bi_sector, (u_long)dev->bdev->bd_dev,
+			 name->str, dev->devid, bio->bi_iter.bi_size);
 		rcu_read_unlock();
 	}
 #endif
@@ -5789,10 +5887,10 @@ struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid,
 }
 
 static struct btrfs_device *add_missing_dev(struct btrfs_root *root,
+					    struct btrfs_fs_devices *fs_devices,
 					    u64 devid, u8 *dev_uuid)
 {
 	struct btrfs_device *device;
-	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
 
 	device = btrfs_alloc_device(NULL, &devid, dev_uuid);
 	if (IS_ERR(device))
@@ -5929,7 +6027,8 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 		}
 		if (!map->stripes[i].dev) {
 			map->stripes[i].dev =
-				add_missing_dev(root, devid, uuid);
+				add_missing_dev(root, root->fs_info->fs_devices,
+						devid, uuid);
 			if (!map->stripes[i].dev) {
 				free_extent_map(em);
 				return -EIO;
@@ -5956,7 +6055,9 @@ static void fill_device_from_item(struct extent_buffer *leaf,
 	device->devid = btrfs_device_id(leaf, dev_item);
 	device->disk_total_bytes = btrfs_device_total_bytes(leaf, dev_item);
 	device->total_bytes = device->disk_total_bytes;
+	device->commit_total_bytes = device->disk_total_bytes;
 	device->bytes_used = btrfs_device_bytes_used(leaf, dev_item);
+	device->commit_bytes_used = device->bytes_used;
 	device->type = btrfs_device_type(leaf, dev_item);
 	device->io_align = btrfs_device_io_align(leaf, dev_item);
 	device->io_width = btrfs_device_io_width(leaf, dev_item);
@@ -5968,7 +6069,8 @@ static void fill_device_from_item(struct extent_buffer *leaf,
 	read_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE);
 }
 
-static int open_seed_devices(struct btrfs_root *root, u8 *fsid)
+static struct btrfs_fs_devices *open_seed_devices(struct btrfs_root *root,
+						  u8 *fsid)
 {
 	struct btrfs_fs_devices *fs_devices;
 	int ret;
@@ -5977,49 +6079,56 @@ static int open_seed_devices(struct btrfs_root *root, u8 *fsid)
 
 	fs_devices = root->fs_info->fs_devices->seed;
 	while (fs_devices) {
-		if (!memcmp(fs_devices->fsid, fsid, BTRFS_UUID_SIZE)) {
-			ret = 0;
-			goto out;
-		}
+		if (!memcmp(fs_devices->fsid, fsid, BTRFS_UUID_SIZE))
+			return fs_devices;
+
 		fs_devices = fs_devices->seed;
 	}
 
 	fs_devices = find_fsid(fsid);
 	if (!fs_devices) {
-		ret = -ENOENT;
-		goto out;
+		if (!btrfs_test_opt(root, DEGRADED))
+			return ERR_PTR(-ENOENT);
+
+		fs_devices = alloc_fs_devices(fsid);
+		if (IS_ERR(fs_devices))
+			return fs_devices;
+
+		fs_devices->seeding = 1;
+		fs_devices->opened = 1;
+		return fs_devices;
 	}
 
 	fs_devices = clone_fs_devices(fs_devices);
-	if (IS_ERR(fs_devices)) {
-		ret = PTR_ERR(fs_devices);
-		goto out;
-	}
+	if (IS_ERR(fs_devices))
+		return fs_devices;
 
 	ret = __btrfs_open_devices(fs_devices, FMODE_READ,
 				   root->fs_info->bdev_holder);
 	if (ret) {
 		free_fs_devices(fs_devices);
+		fs_devices = ERR_PTR(ret);
 		goto out;
 	}
 
 	if (!fs_devices->seeding) {
 		__btrfs_close_devices(fs_devices);
 		free_fs_devices(fs_devices);
-		ret = -EINVAL;
+		fs_devices = ERR_PTR(-EINVAL);
 		goto out;
 	}
 
 	fs_devices->seed = root->fs_info->fs_devices->seed;
 	root->fs_info->fs_devices->seed = fs_devices;
 out:
-	return ret;
+	return fs_devices;
 }
 
 static int read_one_dev(struct btrfs_root *root,
 			struct extent_buffer *leaf,
 			struct btrfs_dev_item *dev_item)
 {
+	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
 	struct btrfs_device *device;
 	u64 devid;
 	int ret;
@@ -6033,31 +6142,48 @@ static int read_one_dev(struct btrfs_root *root,
 			   BTRFS_UUID_SIZE);
 
 	if (memcmp(fs_uuid, root->fs_info->fsid, BTRFS_UUID_SIZE)) {
-		ret = open_seed_devices(root, fs_uuid);
-		if (ret && !btrfs_test_opt(root, DEGRADED))
-			return ret;
+		fs_devices = open_seed_devices(root, fs_uuid);
+		if (IS_ERR(fs_devices))
+			return PTR_ERR(fs_devices);
 	}
 
 	device = btrfs_find_device(root->fs_info, devid, dev_uuid, fs_uuid);
-	if (!device || !device->bdev) {
+	if (!device) {
 		if (!btrfs_test_opt(root, DEGRADED))
 			return -EIO;
 
-		if (!device) {
-			btrfs_warn(root->fs_info, "devid %llu missing", devid);
-			device = add_missing_dev(root, devid, dev_uuid);
-			if (!device)
-				return -ENOMEM;
-		} else if (!device->missing) {
+		btrfs_warn(root->fs_info, "devid %llu missing", devid);
+		device = add_missing_dev(root, fs_devices, devid, dev_uuid);
+		if (!device)
+			return -ENOMEM;
+	} else {
+		if (!device->bdev && !btrfs_test_opt(root, DEGRADED))
+			return -EIO;
+
+		if(!device->bdev && !device->missing) {
 			/*
 			 * this happens when a device that was properly setup
 			 * in the device info lists suddenly goes bad.
 			 * device->bdev is NULL, and so we have to set
 			 * device->missing to one here
 			 */
-			root->fs_info->fs_devices->missing_devices++;
+			device->fs_devices->missing_devices++;
 			device->missing = 1;
 		}
+
+		/* Move the device to its own fs_devices */
+		if (device->fs_devices != fs_devices) {
+			ASSERT(device->missing);
+
+			list_move(&device->dev_list, &fs_devices->devices);
+			device->fs_devices->num_devices--;
+			fs_devices->num_devices++;
+
+			device->fs_devices->missing_devices--;
+			fs_devices->missing_devices++;
+
+			device->fs_devices = fs_devices;
+		}
 	}
 
 	if (device->fs_devices != root->fs_info->fs_devices) {
@@ -6373,16 +6499,18 @@ int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
 	struct btrfs_root *dev_root = fs_info->dev_root;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *device;
+	int stats_cnt;
 	int ret = 0;
 
 	mutex_lock(&fs_devices->device_list_mutex);
 	list_for_each_entry(device, &fs_devices->devices, dev_list) {
-		if (!device->dev_stats_valid || !device->dev_stats_dirty)
+		if (!device->dev_stats_valid || !btrfs_dev_stats_dirty(device))
 			continue;
 
+		stats_cnt = atomic_read(&device->dev_stats_ccnt);
 		ret = update_dev_stat_item(trans, dev_root, device);
 		if (!ret)
-			device->dev_stats_dirty = 0;
+			atomic_sub(stats_cnt, &device->dev_stats_ccnt);
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 
@@ -6481,3 +6609,51 @@ int btrfs_scratch_superblock(struct btrfs_device *device)
 
 	return 0;
 }
+
+/*
+ * Update the size of all devices, which is used for writing out the
+ * super blocks.
+ */
+void btrfs_update_commit_device_size(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct btrfs_device *curr, *next;
+
+	if (list_empty(&fs_devices->resized_devices))
+		return;
+
+	mutex_lock(&fs_devices->device_list_mutex);
+	lock_chunks(fs_info->dev_root);
+	list_for_each_entry_safe(curr, next, &fs_devices->resized_devices,
+				 resized_list) {
+		list_del_init(&curr->resized_list);
+		curr->commit_total_bytes = curr->disk_total_bytes;
+	}
+	unlock_chunks(fs_info->dev_root);
+	mutex_unlock(&fs_devices->device_list_mutex);
+}
+
+/* Must be invoked during the transaction commit */
+void btrfs_update_commit_device_bytes_used(struct btrfs_root *root,
+					struct btrfs_transaction *transaction)
+{
+	struct extent_map *em;
+	struct map_lookup *map;
+	struct btrfs_device *dev;
+	int i;
+
+	if (list_empty(&transaction->pending_chunks))
+		return;
+
+	/* In order to kick the device replace finish process */
+	lock_chunks(root);
+	list_for_each_entry(em, &transaction->pending_chunks, list) {
+		map = (struct map_lookup *)em->bdev;
+
+		for (i = 0; i < map->num_stripes; i++) {
+			dev = map->stripes[i].dev;
+			dev->commit_bytes_used = dev->bytes_used;
+		}
+	}
+	unlock_chunks(root);
+}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 2aaa00c47816..08980fa23039 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -24,6 +24,8 @@
 #include <linux/btrfs.h>
 #include "async-thread.h"
 
+extern struct mutex uuid_mutex;
+
 #define BTRFS_STRIPE_LEN	(64 * 1024)
 
 struct buffer_head;
@@ -32,41 +34,59 @@ struct btrfs_pending_bios {
 	struct bio *tail;
 };
 
+/*
+ * Use sequence counter to get consistent device stat data on
+ * 32-bit processors.
+ */
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+#include <linux/seqlock.h>
+#define __BTRFS_NEED_DEVICE_DATA_ORDERED
+#define btrfs_device_data_ordered_init(device)	\
+	seqcount_init(&device->data_seqcount)
+#else
+#define btrfs_device_data_ordered_init(device) do { } while (0)
+#endif
+
 struct btrfs_device {
 	struct list_head dev_list;
 	struct list_head dev_alloc_list;
 	struct btrfs_fs_devices *fs_devices;
+
 	struct btrfs_root *dev_root;
 
+	struct rcu_string *name;
+
+	u64 generation;
+
+	spinlock_t io_lock ____cacheline_aligned;
+	int running_pending;
 	/* regular prio bios */
 	struct btrfs_pending_bios pending_bios;
 	/* WRITE_SYNC bios */
 	struct btrfs_pending_bios pending_sync_bios;
 
-	u64 generation;
-	int running_pending;
+	struct block_device *bdev;
+
+	/* the mode sent to blkdev_get */
+	fmode_t mode;
+
 	int writeable;
 	int in_fs_metadata;
 	int missing;
 	int can_discard;
 	int is_tgtdev_for_dev_replace;
 
-	spinlock_t io_lock;
-	/* the mode sent to blkdev_get */
-	fmode_t mode;
-
-	struct block_device *bdev;
-
-
-	struct rcu_string *name;
+#ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
+	seqcount_t data_seqcount;
+#endif
 
 	/* the internal btrfs device id */
 	u64 devid;
 
-	/* size of the device */
+	/* size of the device in memory */
 	u64 total_bytes;
 
-	/* size of the disk */
+	/* size of the device on disk */
 	u64 disk_total_bytes;
 
 	/* bytes used */
@@ -83,10 +103,26 @@ struct btrfs_device {
 	/* minimal io size for this device */
 	u32 sector_size;
 
-
 	/* physical drive uuid (or lvm uuid) */
 	u8 uuid[BTRFS_UUID_SIZE];
 
+	/*
+	 * size of the device on the current transaction
+	 *
+	 * This variant is update when committing the transaction,
+	 * and protected by device_list_mutex
+	 */
+	u64 commit_total_bytes;
+
+	/* bytes used on the current transaction */
+	u64 commit_bytes_used;
+	/*
+	 * used to manage the device which is resized
+	 *
+	 * It is protected by chunk_lock.
+	 */
+	struct list_head resized_list;
+
 	/* for sending down flush barriers */
 	int nobarriers;
 	struct bio *flush_bio;
@@ -107,26 +143,90 @@ struct btrfs_device {
 	struct radix_tree_root reada_zones;
 	struct radix_tree_root reada_extents;
 
-
 	/* disk I/O failure stats. For detailed description refer to
 	 * enum btrfs_dev_stat_values in ioctl.h */
 	int dev_stats_valid;
-	int dev_stats_dirty; /* counters need to be written to disk */
+
+	/* Counter to record the change of device stats */
+	atomic_t dev_stats_ccnt;
 	atomic_t dev_stat_values[BTRFS_DEV_STAT_VALUES_MAX];
 };
 
+/*
+ * If we read those variants at the context of their own lock, we needn't
+ * use the following helpers, reading them directly is safe.
+ */
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+#define BTRFS_DEVICE_GETSET_FUNCS(name)					\
+static inline u64							\
+btrfs_device_get_##name(const struct btrfs_device *dev)			\
+{									\
+	u64 size;							\
+	unsigned int seq;						\
+									\
+	do {								\
+		seq = read_seqcount_begin(&dev->data_seqcount);		\
+		size = dev->name;					\
+	} while (read_seqcount_retry(&dev->data_seqcount, seq));	\
+	return size;							\
+}									\
+									\
+static inline void							\
+btrfs_device_set_##name(struct btrfs_device *dev, u64 size)		\
+{									\
+	preempt_disable();						\
+	write_seqcount_begin(&dev->data_seqcount);			\
+	dev->name = size;						\
+	write_seqcount_end(&dev->data_seqcount);			\
+	preempt_enable();						\
+}
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#define BTRFS_DEVICE_GETSET_FUNCS(name)					\
+static inline u64							\
+btrfs_device_get_##name(const struct btrfs_device *dev)			\
+{									\
+	u64 size;							\
+									\
+	preempt_disable();						\
+	size = dev->name;						\
+	preempt_enable();						\
+	return size;							\
+}									\
+									\
+static inline void							\
+btrfs_device_set_##name(struct btrfs_device *dev, u64 size)		\
+{									\
+	preempt_disable();						\
+	dev->name = size;						\
+	preempt_enable();						\
+}
+#else
+#define BTRFS_DEVICE_GETSET_FUNCS(name)					\
+static inline u64							\
+btrfs_device_get_##name(const struct btrfs_device *dev)			\
+{									\
+	return dev->name;						\
+}									\
+									\
+static inline void							\
+btrfs_device_set_##name(struct btrfs_device *dev, u64 size)		\
+{									\
+	dev->name = size;						\
+}
+#endif
+
+BTRFS_DEVICE_GETSET_FUNCS(total_bytes);
+BTRFS_DEVICE_GETSET_FUNCS(disk_total_bytes);
+BTRFS_DEVICE_GETSET_FUNCS(bytes_used);
+
 struct btrfs_fs_devices {
 	u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
 
-	/* the device with this id has the most recent copy of the super */
-	u64 latest_devid;
-	u64 latest_trans;
 	u64 num_devices;
 	u64 open_devices;
 	u64 rw_devices;
 	u64 missing_devices;
 	u64 total_rw_bytes;
-	u64 num_can_discard;
 	u64 total_devices;
 	struct block_device *latest_bdev;
 
@@ -139,6 +239,7 @@ struct btrfs_fs_devices {
 	struct mutex device_list_mutex;
 	struct list_head devices;
 
+	struct list_head resized_devices;
 	/* devices not currently being allocated */
 	struct list_head alloc_list;
 	struct list_head list;
@@ -167,8 +268,9 @@ struct btrfs_fs_devices {
  */
 typedef void (btrfs_io_bio_end_io_t) (struct btrfs_io_bio *bio, int err);
 struct btrfs_io_bio {
-	unsigned long mirror_num;
-	unsigned long stripe_index;
+	unsigned int mirror_num;
+	unsigned int stripe_index;
+	u64 logical;
 	u8 *csum;
 	u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
 	u8 *csum_allocated;
@@ -325,6 +427,7 @@ struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid,
 int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
 int btrfs_init_new_device(struct btrfs_root *root, char *path);
 int btrfs_init_dev_replace_tgtdev(struct btrfs_root *root, char *device_path,
+				  struct btrfs_device *srcdev,
 				  struct btrfs_device **device_out);
 int btrfs_balance(struct btrfs_balance_control *bctl,
 		  struct btrfs_ioctl_balance_args *bargs);
@@ -360,11 +463,20 @@ unsigned long btrfs_full_stripe_len(struct btrfs_root *root,
 int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 				struct btrfs_root *extent_root,
 				u64 chunk_offset, u64 chunk_size);
+int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
+		       struct btrfs_root *root, u64 chunk_offset);
+
+static inline int btrfs_dev_stats_dirty(struct btrfs_device *dev)
+{
+	return atomic_read(&dev->dev_stats_ccnt);
+}
+
 static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
 				      int index)
 {
 	atomic_inc(dev->dev_stat_values + index);
-	dev->dev_stats_dirty = 1;
+	smp_mb__before_atomic();
+	atomic_inc(&dev->dev_stats_ccnt);
 }
 
 static inline int btrfs_dev_stat_read(struct btrfs_device *dev,
@@ -379,7 +491,8 @@ static inline int btrfs_dev_stat_read_and_reset(struct btrfs_device *dev,
 	int ret;
 
 	ret = atomic_xchg(dev->dev_stat_values + index, 0);
-	dev->dev_stats_dirty = 1;
+	smp_mb__before_atomic();
+	atomic_inc(&dev->dev_stats_ccnt);
 	return ret;
 }
 
@@ -387,7 +500,8 @@ static inline void btrfs_dev_stat_set(struct btrfs_device *dev,
 				      int index, unsigned long val)
 {
 	atomic_set(dev->dev_stat_values + index, val);
-	dev->dev_stats_dirty = 1;
+	smp_mb__before_atomic();
+	atomic_inc(&dev->dev_stats_ccnt);
 }
 
 static inline void btrfs_dev_stat_reset(struct btrfs_device *dev,
@@ -395,4 +509,8 @@ static inline void btrfs_dev_stat_reset(struct btrfs_device *dev,
 {
 	btrfs_dev_stat_set(dev, index, 0);
 }
+
+void btrfs_update_commit_device_size(struct btrfs_fs_info *fs_info);
+void btrfs_update_commit_device_bytes_used(struct btrfs_root *root,
+					struct btrfs_transaction *transaction);
 #endif
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index ad8328d797ea..dcf20131fbe4 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -237,7 +237,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 	 * first xattr that we find and walk forward
 	 */
 	key.objectid = btrfs_ino(inode);
-	btrfs_set_key_type(&key, BTRFS_XATTR_ITEM_KEY);
+	key.type = BTRFS_XATTR_ITEM_KEY;
 	key.offset = 0;
 
 	path = btrfs_alloc_path();
@@ -273,7 +273,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 		/* check to make sure this item is what we want */
 		if (found_key.objectid != key.objectid)
 			break;
-		if (btrfs_key_type(&found_key) != BTRFS_XATTR_ITEM_KEY)
+		if (found_key.type != BTRFS_XATTR_ITEM_KEY)
 			break;
 
 		di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index b67d8fc81277..759fa4e2de8f 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -33,8 +33,7 @@
 #include "compression.h"
 
 struct workspace {
-	z_stream inf_strm;
-	z_stream def_strm;
+	z_stream strm;
 	char *buf;
 	struct list_head list;
 };
@@ -43,8 +42,7 @@ static void zlib_free_workspace(struct list_head *ws)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
-	vfree(workspace->def_strm.workspace);
-	vfree(workspace->inf_strm.workspace);
+	vfree(workspace->strm.workspace);
 	kfree(workspace->buf);
 	kfree(workspace);
 }
@@ -52,17 +50,17 @@ static void zlib_free_workspace(struct list_head *ws)
 static struct list_head *zlib_alloc_workspace(void)
 {
 	struct workspace *workspace;
+	int workspacesize;
 
 	workspace = kzalloc(sizeof(*workspace), GFP_NOFS);
 	if (!workspace)
 		return ERR_PTR(-ENOMEM);
 
-	workspace->def_strm.workspace = vmalloc(zlib_deflate_workspacesize(
-						MAX_WBITS, MAX_MEM_LEVEL));
-	workspace->inf_strm.workspace = vmalloc(zlib_inflate_workspacesize());
+	workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL),
+			zlib_inflate_workspacesize());
+	workspace->strm.workspace = vmalloc(workspacesize);
 	workspace->buf = kmalloc(PAGE_CACHE_SIZE, GFP_NOFS);
-	if (!workspace->def_strm.workspace ||
-	    !workspace->inf_strm.workspace || !workspace->buf)
+	if (!workspace->strm.workspace || !workspace->buf)
 		goto fail;
 
 	INIT_LIST_HEAD(&workspace->list);
@@ -96,14 +94,14 @@ static int zlib_compress_pages(struct list_head *ws,
 	*total_out = 0;
 	*total_in = 0;
 
-	if (Z_OK != zlib_deflateInit(&workspace->def_strm, 3)) {
+	if (Z_OK != zlib_deflateInit(&workspace->strm, 3)) {
 		printk(KERN_WARNING "BTRFS: deflateInit failed\n");
 		ret = -EIO;
 		goto out;
 	}
 
-	workspace->def_strm.total_in = 0;
-	workspace->def_strm.total_out = 0;
+	workspace->strm.total_in = 0;
+	workspace->strm.total_out = 0;
 
 	in_page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT);
 	data_in = kmap(in_page);
@@ -117,25 +115,25 @@ static int zlib_compress_pages(struct list_head *ws,
 	pages[0] = out_page;
 	nr_pages = 1;
 
-	workspace->def_strm.next_in = data_in;
-	workspace->def_strm.next_out = cpage_out;
-	workspace->def_strm.avail_out = PAGE_CACHE_SIZE;
-	workspace->def_strm.avail_in = min(len, PAGE_CACHE_SIZE);
+	workspace->strm.next_in = data_in;
+	workspace->strm.next_out = cpage_out;
+	workspace->strm.avail_out = PAGE_CACHE_SIZE;
+	workspace->strm.avail_in = min(len, PAGE_CACHE_SIZE);
 
-	while (workspace->def_strm.total_in < len) {
-		ret = zlib_deflate(&workspace->def_strm, Z_SYNC_FLUSH);
+	while (workspace->strm.total_in < len) {
+		ret = zlib_deflate(&workspace->strm, Z_SYNC_FLUSH);
 		if (ret != Z_OK) {
 			printk(KERN_DEBUG "BTRFS: deflate in loop returned %d\n",
 			       ret);
-			zlib_deflateEnd(&workspace->def_strm);
+			zlib_deflateEnd(&workspace->strm);
 			ret = -EIO;
 			goto out;
 		}
 
 		/* we're making it bigger, give up */
-		if (workspace->def_strm.total_in > 8192 &&
-		    workspace->def_strm.total_in <
-		    workspace->def_strm.total_out) {
+		if (workspace->strm.total_in > 8192 &&
+		    workspace->strm.total_in <
+		    workspace->strm.total_out) {
 			ret = -E2BIG;
 			goto out;
 		}
@@ -143,7 +141,7 @@ static int zlib_compress_pages(struct list_head *ws,
 		 * before the total_in so we will pull in a new page for
 		 * the stream end if required
 		 */
-		if (workspace->def_strm.avail_out == 0) {
+		if (workspace->strm.avail_out == 0) {
 			kunmap(out_page);
 			if (nr_pages == nr_dest_pages) {
 				out_page = NULL;
@@ -158,19 +156,19 @@ static int zlib_compress_pages(struct list_head *ws,
 			cpage_out = kmap(out_page);
 			pages[nr_pages] = out_page;
 			nr_pages++;
-			workspace->def_strm.avail_out = PAGE_CACHE_SIZE;
-			workspace->def_strm.next_out = cpage_out;
+			workspace->strm.avail_out = PAGE_CACHE_SIZE;
+			workspace->strm.next_out = cpage_out;
 		}
 		/* we're all done */
-		if (workspace->def_strm.total_in >= len)
+		if (workspace->strm.total_in >= len)
 			break;
 
 		/* we've read in a full page, get a new one */
-		if (workspace->def_strm.avail_in == 0) {
-			if (workspace->def_strm.total_out > max_out)
+		if (workspace->strm.avail_in == 0) {
+			if (workspace->strm.total_out > max_out)
 				break;
 
-			bytes_left = len - workspace->def_strm.total_in;
+			bytes_left = len - workspace->strm.total_in;
 			kunmap(in_page);
 			page_cache_release(in_page);
 
@@ -178,28 +176,28 @@ static int zlib_compress_pages(struct list_head *ws,
 			in_page = find_get_page(mapping,
 						start >> PAGE_CACHE_SHIFT);
 			data_in = kmap(in_page);
-			workspace->def_strm.avail_in = min(bytes_left,
+			workspace->strm.avail_in = min(bytes_left,
 							   PAGE_CACHE_SIZE);
-			workspace->def_strm.next_in = data_in;
+			workspace->strm.next_in = data_in;
 		}
 	}
-	workspace->def_strm.avail_in = 0;
-	ret = zlib_deflate(&workspace->def_strm, Z_FINISH);
-	zlib_deflateEnd(&workspace->def_strm);
+	workspace->strm.avail_in = 0;
+	ret = zlib_deflate(&workspace->strm, Z_FINISH);
+	zlib_deflateEnd(&workspace->strm);
 
 	if (ret != Z_STREAM_END) {
 		ret = -EIO;
 		goto out;
 	}
 
-	if (workspace->def_strm.total_out >= workspace->def_strm.total_in) {
+	if (workspace->strm.total_out >= workspace->strm.total_in) {
 		ret = -E2BIG;
 		goto out;
 	}
 
 	ret = 0;
-	*total_out = workspace->def_strm.total_out;
-	*total_in = workspace->def_strm.total_in;
+	*total_out = workspace->strm.total_out;
+	*total_in = workspace->strm.total_in;
 out:
 	*out_pages = nr_pages;
 	if (out_page)
@@ -225,19 +223,18 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 	size_t total_out = 0;
 	unsigned long page_in_index = 0;
 	unsigned long page_out_index = 0;
-	unsigned long total_pages_in = (srclen + PAGE_CACHE_SIZE - 1) /
-					PAGE_CACHE_SIZE;
+	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_CACHE_SIZE);
 	unsigned long buf_start;
 	unsigned long pg_offset;
 
 	data_in = kmap(pages_in[page_in_index]);
-	workspace->inf_strm.next_in = data_in;
-	workspace->inf_strm.avail_in = min_t(size_t, srclen, PAGE_CACHE_SIZE);
-	workspace->inf_strm.total_in = 0;
+	workspace->strm.next_in = data_in;
+	workspace->strm.avail_in = min_t(size_t, srclen, PAGE_CACHE_SIZE);
+	workspace->strm.total_in = 0;
 
-	workspace->inf_strm.total_out = 0;
-	workspace->inf_strm.next_out = workspace->buf;
-	workspace->inf_strm.avail_out = PAGE_CACHE_SIZE;
+	workspace->strm.total_out = 0;
+	workspace->strm.next_out = workspace->buf;
+	workspace->strm.avail_out = PAGE_CACHE_SIZE;
 	pg_offset = 0;
 
 	/* If it's deflate, and it's got no preset dictionary, then
@@ -247,21 +244,21 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 	    !(((data_in[0]<<8) + data_in[1]) % 31)) {
 
 		wbits = -((data_in[0] >> 4) + 8);
-		workspace->inf_strm.next_in += 2;
-		workspace->inf_strm.avail_in -= 2;
+		workspace->strm.next_in += 2;
+		workspace->strm.avail_in -= 2;
 	}
 
-	if (Z_OK != zlib_inflateInit2(&workspace->inf_strm, wbits)) {
+	if (Z_OK != zlib_inflateInit2(&workspace->strm, wbits)) {
 		printk(KERN_WARNING "BTRFS: inflateInit failed\n");
 		return -EIO;
 	}
-	while (workspace->inf_strm.total_in < srclen) {
-		ret = zlib_inflate(&workspace->inf_strm, Z_NO_FLUSH);
+	while (workspace->strm.total_in < srclen) {
+		ret = zlib_inflate(&workspace->strm, Z_NO_FLUSH);
 		if (ret != Z_OK && ret != Z_STREAM_END)
 			break;
 
 		buf_start = total_out;
-		total_out = workspace->inf_strm.total_out;
+		total_out = workspace->strm.total_out;
 
 		/* we didn't make progress in this inflate call, we're done */
 		if (buf_start == total_out)
@@ -276,10 +273,10 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 			goto done;
 		}
 
-		workspace->inf_strm.next_out = workspace->buf;
-		workspace->inf_strm.avail_out = PAGE_CACHE_SIZE;
+		workspace->strm.next_out = workspace->buf;
+		workspace->strm.avail_out = PAGE_CACHE_SIZE;
 
-		if (workspace->inf_strm.avail_in == 0) {
+		if (workspace->strm.avail_in == 0) {
 			unsigned long tmp;
 			kunmap(pages_in[page_in_index]);
 			page_in_index++;
@@ -288,9 +285,9 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 				break;
 			}
 			data_in = kmap(pages_in[page_in_index]);
-			workspace->inf_strm.next_in = data_in;
-			tmp = srclen - workspace->inf_strm.total_in;
-			workspace->inf_strm.avail_in = min(tmp,
+			workspace->strm.next_in = data_in;
+			tmp = srclen - workspace->strm.total_in;
+			workspace->strm.avail_in = min(tmp,
 							   PAGE_CACHE_SIZE);
 		}
 	}
@@ -299,7 +296,7 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 	else
 		ret = 0;
 done:
-	zlib_inflateEnd(&workspace->inf_strm);
+	zlib_inflateEnd(&workspace->strm);
 	if (data_in)
 		kunmap(pages_in[page_in_index]);
 	return ret;
@@ -317,13 +314,13 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 	unsigned long total_out = 0;
 	char *kaddr;
 
-	workspace->inf_strm.next_in = data_in;
-	workspace->inf_strm.avail_in = srclen;
-	workspace->inf_strm.total_in = 0;
+	workspace->strm.next_in = data_in;
+	workspace->strm.avail_in = srclen;
+	workspace->strm.total_in = 0;
 
-	workspace->inf_strm.next_out = workspace->buf;
-	workspace->inf_strm.avail_out = PAGE_CACHE_SIZE;
-	workspace->inf_strm.total_out = 0;
+	workspace->strm.next_out = workspace->buf;
+	workspace->strm.avail_out = PAGE_CACHE_SIZE;
+	workspace->strm.total_out = 0;
 	/* If it's deflate, and it's got no preset dictionary, then
 	   we can tell zlib to skip the adler32 check. */
 	if (srclen > 2 && !(data_in[1] & PRESET_DICT) &&
@@ -331,11 +328,11 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 	    !(((data_in[0]<<8) + data_in[1]) % 31)) {
 
 		wbits = -((data_in[0] >> 4) + 8);
-		workspace->inf_strm.next_in += 2;
-		workspace->inf_strm.avail_in -= 2;
+		workspace->strm.next_in += 2;
+		workspace->strm.avail_in -= 2;
 	}
 
-	if (Z_OK != zlib_inflateInit2(&workspace->inf_strm, wbits)) {
+	if (Z_OK != zlib_inflateInit2(&workspace->strm, wbits)) {
 		printk(KERN_WARNING "BTRFS: inflateInit failed\n");
 		return -EIO;
 	}
@@ -346,12 +343,12 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 		unsigned long bytes;
 		unsigned long pg_offset = 0;
 
-		ret = zlib_inflate(&workspace->inf_strm, Z_NO_FLUSH);
+		ret = zlib_inflate(&workspace->strm, Z_NO_FLUSH);
 		if (ret != Z_OK && ret != Z_STREAM_END)
 			break;
 
 		buf_start = total_out;
-		total_out = workspace->inf_strm.total_out;
+		total_out = workspace->strm.total_out;
 
 		if (total_out == buf_start) {
 			ret = -EIO;
@@ -377,8 +374,8 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 		pg_offset += bytes;
 		bytes_left -= bytes;
 next:
-		workspace->inf_strm.next_out = workspace->buf;
-		workspace->inf_strm.avail_out = PAGE_CACHE_SIZE;
+		workspace->strm.next_out = workspace->buf;
+		workspace->strm.avail_out = PAGE_CACHE_SIZE;
 	}
 
 	if (ret != Z_STREAM_END && bytes_left != 0)
@@ -386,7 +383,7 @@ next:
 	else
 		ret = 0;
 
-	zlib_inflateEnd(&workspace->inf_strm);
+	zlib_inflateEnd(&workspace->strm);
 	return ret;
 }
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 3588a80854b2..9614adc7e754 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1253,7 +1253,7 @@ static struct buffer_head *__bread_slow(struct buffer_head *bh)
  * a local interrupt disable for that.
  */
 
-#define BH_LRU_SIZE	8
+#define BH_LRU_SIZE	16
 
 struct bh_lru {
 	struct buffer_head *bhs[BH_LRU_SIZE];
@@ -1331,8 +1331,8 @@ lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
 	for (i = 0; i < BH_LRU_SIZE; i++) {
 		struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]);
 
-		if (bh && bh->b_bdev == bdev &&
-				bh->b_blocknr == block && bh->b_size == size) {
+		if (bh && bh->b_blocknr == block && bh->b_bdev == bdev &&
+		    bh->b_size == size) {
 			if (i) {
 				while (i) {
 					__this_cpu_write(bh_lrus.bhs[i],
@@ -2318,6 +2318,11 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		err = 0;
 
 		balance_dirty_pages_ratelimited(mapping);
+
+		if (unlikely(fatal_signal_pending(current))) {
+			err = -EINTR;
+			goto out;
+		}
 	}
 
 	/* page covers the boundary, find the boundary offset */
@@ -2956,7 +2961,7 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
 
 /*
  * This allows us to do IO even on the odd last sectors
- * of a device, even if the bh block size is some multiple
+ * of a device, even if the block size is some multiple
  * of the physical sector size.
  *
  * We'll just truncate the bio to the size of the device,
@@ -2966,10 +2971,11 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
  * errors, this only handles the "we need to be able to
  * do IO at the final sector" case.
  */
-static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
+void guard_bio_eod(int rw, struct bio *bio)
 {
 	sector_t maxsector;
-	unsigned bytes;
+	struct bio_vec *bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
+	unsigned truncated_bytes;
 
 	maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
 	if (!maxsector)
@@ -2984,23 +2990,20 @@ static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
 		return;
 
 	maxsector -= bio->bi_iter.bi_sector;
-	bytes = bio->bi_iter.bi_size;
-	if (likely((bytes >> 9) <= maxsector))
+	if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
 		return;
 
-	/* Uhhuh. We've got a bh that straddles the device size! */
-	bytes = maxsector << 9;
+	/* Uhhuh. We've got a bio that straddles the device size! */
+	truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
 
 	/* Truncate the bio.. */
-	bio->bi_iter.bi_size = bytes;
-	bio->bi_io_vec[0].bv_len = bytes;
+	bio->bi_iter.bi_size -= truncated_bytes;
+	bvec->bv_len -= truncated_bytes;
 
 	/* ..and clear the end of the buffer for reads */
 	if ((rw & RW_MASK) == READ) {
-		void *kaddr = kmap_atomic(bh->b_page);
-		memset(kaddr + bh_offset(bh) + bytes, 0, bh->b_size - bytes);
-		kunmap_atomic(kaddr);
-		flush_dcache_page(bh->b_page);
+		zero_user(bvec->bv_page, bvec->bv_offset + bvec->bv_len,
+				truncated_bytes);
 	}
 }
 
@@ -3041,7 +3044,7 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
 	bio->bi_flags |= bio_flags;
 
 	/* Take care of bh's that straddle the end of the device */
-	guard_bh_eod(rw, bio, bh);
+	guard_bio_eod(rw, bio);
 
 	if (buffer_meta(bh))
 		rw |= REQ_META;
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 584743d456c3..1c7293c3a93a 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -268,20 +268,27 @@ static void cachefiles_drop_object(struct fscache_object *_object)
 	ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000);
 #endif
 
-	/* delete retired objects */
-	if (test_bit(FSCACHE_OBJECT_RETIRED, &object->fscache.flags) &&
-	    _object != cache->cache.fsdef
-	    ) {
-		_debug("- retire object OBJ%x", object->fscache.debug_id);
-		cachefiles_begin_secure(cache, &saved_cred);
-		cachefiles_delete_object(cache, object);
-		cachefiles_end_secure(cache, saved_cred);
-	}
+	/* We need to tidy the object up if we did in fact manage to open it.
+	 * It's possible for us to get here before the object is fully
+	 * initialised if the parent goes away or the object gets retired
+	 * before we set it up.
+	 */
+	if (object->dentry) {
+		/* delete retired objects */
+		if (test_bit(FSCACHE_OBJECT_RETIRED, &object->fscache.flags) &&
+		    _object != cache->cache.fsdef
+		    ) {
+			_debug("- retire object OBJ%x", object->fscache.debug_id);
+			cachefiles_begin_secure(cache, &saved_cred);
+			cachefiles_delete_object(cache, object);
+			cachefiles_end_secure(cache, saved_cred);
+		}
 
-	/* close the filesystem stuff attached to the object */
-	if (object->backer != object->dentry)
-		dput(object->backer);
-	object->backer = NULL;
+		/* close the filesystem stuff attached to the object */
+		if (object->backer != object->dentry)
+			dput(object->backer);
+		object->backer = NULL;
+	}
 
 	/* note that the object is now inactive */
 	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index dad7d9542a24..e12f189d539b 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -189,7 +189,7 @@ try_again:
 	/* an old object from a previous incarnation is hogging the slot - we
 	 * need to wait for it to be destroyed */
 wait_for_old_object:
-	if (fscache_object_is_live(&object->fscache)) {
+	if (fscache_object_is_live(&xobject->fscache)) {
 		pr_err("\n");
 		pr_err("Error: Unexpected object collision\n");
 		cachefiles_printk_object(object, xobject);
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 25e745b8eb1b..616db0e77b44 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -880,7 +880,6 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 {
 	struct cachefiles_object *object;
 	struct cachefiles_cache *cache;
-	mm_segment_t old_fs;
 	struct file *file;
 	struct path path;
 	loff_t pos, eof;
@@ -914,36 +913,27 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	if (IS_ERR(file)) {
 		ret = PTR_ERR(file);
 	} else {
-		ret = -EIO;
-		if (file->f_op->write) {
-			pos = (loff_t) page->index << PAGE_SHIFT;
-
-			/* we mustn't write more data than we have, so we have
-			 * to beware of a partial page at EOF */
-			eof = object->fscache.store_limit_l;
-			len = PAGE_SIZE;
-			if (eof & ~PAGE_MASK) {
-				ASSERTCMP(pos, <, eof);
-				if (eof - pos < PAGE_SIZE) {
-					_debug("cut short %llx to %llx",
-					       pos, eof);
-					len = eof - pos;
-					ASSERTCMP(pos + len, ==, eof);
-				}
+		pos = (loff_t) page->index << PAGE_SHIFT;
+
+		/* we mustn't write more data than we have, so we have
+		 * to beware of a partial page at EOF */
+		eof = object->fscache.store_limit_l;
+		len = PAGE_SIZE;
+		if (eof & ~PAGE_MASK) {
+			ASSERTCMP(pos, <, eof);
+			if (eof - pos < PAGE_SIZE) {
+				_debug("cut short %llx to %llx",
+				       pos, eof);
+				len = eof - pos;
+				ASSERTCMP(pos + len, ==, eof);
 			}
-
-			data = kmap(page);
-			file_start_write(file);
-			old_fs = get_fs();
-			set_fs(KERNEL_DS);
-			ret = file->f_op->write(
-				file, (const void __user *) data, len, &pos);
-			set_fs(old_fs);
-			kunmap(page);
-			file_end_write(file);
-			if (ret != len)
-				ret = -EIO;
 		}
+
+		data = kmap(page);
+		ret = __kernel_write(file, data, len, &pos);
+		kunmap(page);
+		if (ret != len)
+			ret = -EIO;
 		fput(file);
 	}
 
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index cebf2ebefb55..5bd853ba44ff 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -169,36 +169,109 @@ out:
 	return ret;
 }
 
-int ceph_init_acl(struct dentry *dentry, struct inode *inode, struct inode *dir)
+int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
+		       struct ceph_acls_info *info)
 {
-	struct posix_acl *default_acl, *acl;
-	umode_t new_mode = inode->i_mode;
-	int error;
-
-	error = posix_acl_create(dir, &new_mode, &default_acl, &acl);
-	if (error)
-		return error;
-
-	if (!default_acl && !acl) {
-		cache_no_acl(inode);
-		if (new_mode != inode->i_mode) {
-			struct iattr newattrs = {
-				.ia_mode = new_mode,
-				.ia_valid = ATTR_MODE,
-			};
-			error = ceph_setattr(dentry, &newattrs);
+	struct posix_acl *acl, *default_acl;
+	size_t val_size1 = 0, val_size2 = 0;
+	struct ceph_pagelist *pagelist = NULL;
+	void *tmp_buf = NULL;
+	int err;
+
+	err = posix_acl_create(dir, mode, &default_acl, &acl);
+	if (err)
+		return err;
+
+	if (acl) {
+		int ret = posix_acl_equiv_mode(acl, mode);
+		if (ret < 0)
+			goto out_err;
+		if (ret == 0) {
+			posix_acl_release(acl);
+			acl = NULL;
 		}
-		return error;
 	}
 
-	if (default_acl) {
-		error = ceph_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
-		posix_acl_release(default_acl);
-	}
+	if (!default_acl && !acl)
+		return 0;
+
+	if (acl)
+		val_size1 = posix_acl_xattr_size(acl->a_count);
+	if (default_acl)
+		val_size2 = posix_acl_xattr_size(default_acl->a_count);
+
+	err = -ENOMEM;
+	tmp_buf = kmalloc(max(val_size1, val_size2), GFP_NOFS);
+	if (!tmp_buf)
+		goto out_err;
+	pagelist = kmalloc(sizeof(struct ceph_pagelist), GFP_NOFS);
+	if (!pagelist)
+		goto out_err;
+	ceph_pagelist_init(pagelist);
+
+	err = ceph_pagelist_reserve(pagelist, PAGE_SIZE);
+	if (err)
+		goto out_err;
+
+	ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1);
+
 	if (acl) {
-		if (!error)
-			error = ceph_set_acl(inode, acl, ACL_TYPE_ACCESS);
-		posix_acl_release(acl);
+		size_t len = strlen(POSIX_ACL_XATTR_ACCESS);
+		err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8);
+		if (err)
+			goto out_err;
+		ceph_pagelist_encode_string(pagelist, POSIX_ACL_XATTR_ACCESS,
+					    len);
+		err = posix_acl_to_xattr(&init_user_ns, acl,
+					 tmp_buf, val_size1);
+		if (err < 0)
+			goto out_err;
+		ceph_pagelist_encode_32(pagelist, val_size1);
+		ceph_pagelist_append(pagelist, tmp_buf, val_size1);
 	}
-	return error;
+	if (default_acl) {
+		size_t len = strlen(POSIX_ACL_XATTR_DEFAULT);
+		err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
+		if (err)
+			goto out_err;
+		err = ceph_pagelist_encode_string(pagelist,
+						  POSIX_ACL_XATTR_DEFAULT, len);
+		err = posix_acl_to_xattr(&init_user_ns, default_acl,
+					 tmp_buf, val_size2);
+		if (err < 0)
+			goto out_err;
+		ceph_pagelist_encode_32(pagelist, val_size2);
+		ceph_pagelist_append(pagelist, tmp_buf, val_size2);
+	}
+
+	kfree(tmp_buf);
+
+	info->acl = acl;
+	info->default_acl = default_acl;
+	info->pagelist = pagelist;
+	return 0;
+
+out_err:
+	posix_acl_release(acl);
+	posix_acl_release(default_acl);
+	kfree(tmp_buf);
+	if (pagelist)
+		ceph_pagelist_release(pagelist);
+	return err;
+}
+
+void ceph_init_inode_acls(struct inode* inode, struct ceph_acls_info *info)
+{
+	if (!inode)
+		return;
+	ceph_set_cached_acl(inode, ACL_TYPE_ACCESS, info->acl);
+	ceph_set_cached_acl(inode, ACL_TYPE_DEFAULT, info->default_acl);
+}
+
+void ceph_release_acls_info(struct ceph_acls_info *info)
+{
+	posix_acl_release(info->acl);
+	posix_acl_release(info->default_acl);
+	if (info->pagelist)
+		ceph_pagelist_release(info->pagelist);
 }
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 90b3954d48ed..18c06bbaf136 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1076,12 +1076,6 @@ retry_locked:
 	/* past end of file? */
 	i_size = inode->i_size;   /* caller holds i_mutex */
 
-	if (i_size + len > inode->i_sb->s_maxbytes) {
-		/* file is too big */
-		r = -EINVAL;
-		goto fail;
-	}
-
 	if (page_off >= i_size ||
 	    (pos_in_page == 0 && (pos+len) >= i_size &&
 	     end_in_page - pos_in_page != PAGE_CACHE_SIZE)) {
@@ -1099,9 +1093,6 @@ retry_locked:
 	if (r < 0)
 		goto fail_nosnap;
 	goto retry_locked;
-
-fail:
-	up_read(&mdsc->snap_rwsem);
 fail_nosnap:
 	unlock_page(page);
 	return r;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 6d1cd45dca89..659f2ea9e6f7 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2397,12 +2397,12 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	u64 max_size = le64_to_cpu(grant->max_size);
 	struct timespec mtime, atime, ctime;
 	int check_caps = 0;
-	bool wake = 0;
-	bool writeback = 0;
-	bool queue_trunc = 0;
-	bool queue_invalidate = 0;
-	bool queue_revalidate = 0;
-	bool deleted_inode = 0;
+	bool wake = false;
+	bool writeback = false;
+	bool queue_trunc = false;
+	bool queue_invalidate = false;
+	bool queue_revalidate = false;
+	bool deleted_inode = false;
 
 	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
 	     inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2437,7 +2437,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 			/* there were locked pages.. invalidate later
 			   in a separate thread. */
 			if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
-				queue_invalidate = 1;
+				queue_invalidate = true;
 				ci->i_rdcache_revoking = ci->i_rdcache_gen;
 			}
 		}
@@ -2466,7 +2466,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 		set_nlink(inode, le32_to_cpu(grant->nlink));
 		if (inode->i_nlink == 0 &&
 		    (newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL)))
-			deleted_inode = 1;
+			deleted_inode = true;
 	}
 
 	if ((issued & CEPH_CAP_XATTR_EXCL) == 0 && grant->xattr_len) {
@@ -2487,7 +2487,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	/* Do we need to revalidate our fscache cookie. Don't bother on the
 	 * first cache cap as we already validate at cookie creation time. */
 	if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
-		queue_revalidate = 1;
+		queue_revalidate = true;
 
 	if (newcaps & CEPH_CAP_ANY_RD) {
 		/* ctime/mtime/atime? */
@@ -2516,7 +2516,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 				ci->i_wanted_max_size = 0;  /* reset */
 				ci->i_requested_max_size = 0;
 			}
-			wake = 1;
+			wake = true;
 		}
 	}
 
@@ -2546,7 +2546,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 		     ceph_cap_string(newcaps),
 		     ceph_cap_string(revoking));
 		if (revoking & used & CEPH_CAP_FILE_BUFFER)
-			writeback = 1;  /* initiate writeback; will delay ack */
+			writeback = true;  /* initiate writeback; will delay ack */
 		else if (revoking == CEPH_CAP_FILE_CACHE &&
 			 (newcaps & CEPH_CAP_FILE_LAZYIO) == 0 &&
 			 queue_invalidate)
@@ -2572,7 +2572,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 		cap->implemented |= newcaps; /* add bits only, to
 					      * avoid stepping on a
 					      * pending revocation */
-		wake = 1;
+		wake = true;
 	}
 	BUG_ON(cap->issued & ~cap->implemented);
 
@@ -2586,7 +2586,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 		kick_flushing_inode_caps(mdsc, session, inode);
 		up_read(&mdsc->snap_rwsem);
 		if (newcaps & ~issued)
-			wake = 1;
+			wake = true;
 	}
 
 	if (queue_trunc) {
@@ -3045,6 +3045,12 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		}
 	}
 
+	/* lookup ino */
+	inode = ceph_find_inode(sb, vino);
+	ci = ceph_inode(inode);
+	dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
+	     vino.snap, inode);
+
 	mutex_lock(&session->s_mutex);
 	session->s_seq++;
 	dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
@@ -3053,11 +3059,6 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	if (op == CEPH_CAP_OP_IMPORT)
 		ceph_add_cap_releases(mdsc, session);
 
-	/* lookup ino */
-	inode = ceph_find_inode(sb, vino);
-	ci = ceph_inode(inode);
-	dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
-	     vino.snap, inode);
 	if (!inode) {
 		dout(" i don't have ino %llx\n", vino.ino);
 
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 5a743ac141ab..5d5a4c8c8496 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -158,10 +158,47 @@ static int dentry_lru_show(struct seq_file *s, void *ptr)
 	return 0;
 }
 
+static int mds_sessions_show(struct seq_file *s, void *ptr)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_auth_client *ac = fsc->client->monc.auth;
+	struct ceph_options *opt = fsc->client->options;
+	int mds = -1;
+
+	mutex_lock(&mdsc->mutex);
+
+	/* The 'num' portion of an 'entity name' */
+	seq_printf(s, "global_id %llu\n", ac->global_id);
+
+	/* The -o name mount argument */
+	seq_printf(s, "name \"%s\"\n", opt->name ? opt->name : "");
+
+	/* The list of MDS session rank+state */
+	for (mds = 0; mds < mdsc->max_sessions; mds++) {
+		struct ceph_mds_session *session =
+			__ceph_lookup_mds_session(mdsc, mds);
+		if (!session) {
+			continue;
+		}
+		mutex_unlock(&mdsc->mutex);
+		seq_printf(s, "mds.%d %s\n",
+				session->s_mds,
+				ceph_session_state_name(session->s_state));
+
+		ceph_put_mds_session(session);
+		mutex_lock(&mdsc->mutex);
+	}
+	mutex_unlock(&mdsc->mutex);
+
+	return 0;
+}
+
 CEPH_DEFINE_SHOW_FUNC(mdsmap_show)
 CEPH_DEFINE_SHOW_FUNC(mdsc_show)
 CEPH_DEFINE_SHOW_FUNC(caps_show)
 CEPH_DEFINE_SHOW_FUNC(dentry_lru_show)
+CEPH_DEFINE_SHOW_FUNC(mds_sessions_show)
 
 
 /*
@@ -193,6 +230,7 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 	debugfs_remove(fsc->debugfs_bdi);
 	debugfs_remove(fsc->debugfs_congestion_kb);
 	debugfs_remove(fsc->debugfs_mdsmap);
+	debugfs_remove(fsc->debugfs_mds_sessions);
 	debugfs_remove(fsc->debugfs_caps);
 	debugfs_remove(fsc->debugfs_mdsc);
 	debugfs_remove(fsc->debugfs_dentry_lru);
@@ -231,6 +269,14 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 	if (!fsc->debugfs_mdsmap)
 		goto out;
 
+	fsc->debugfs_mds_sessions = debugfs_create_file("mds_sessions",
+					0600,
+					fsc->client->debugfs_dir,
+					fsc,
+					&mds_sessions_show_fops);
+	if (!fsc->debugfs_mds_sessions)
+		goto out;
+
 	fsc->debugfs_mdsc = debugfs_create_file("mdsc",
 						0600,
 						fsc->client->debugfs_dir,
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index c29d6ae68874..e6d63f8f98c0 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -682,17 +682,22 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
+	struct ceph_acls_info acls = {};
 	int err;
 
 	if (ceph_snap(dir) != CEPH_NOSNAP)
 		return -EROFS;
 
+	err = ceph_pre_init_acls(dir, &mode, &acls);
+	if (err < 0)
+		return err;
+
 	dout("mknod in dir %p dentry %p mode 0%ho rdev %d\n",
 	     dir, dentry, mode, rdev);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_MKNOD, USE_AUTH_MDS);
 	if (IS_ERR(req)) {
-		d_drop(dentry);
-		return PTR_ERR(req);
+		err = PTR_ERR(req);
+		goto out;
 	}
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
@@ -701,15 +706,20 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
 	req->r_args.mknod.rdev = cpu_to_le32(rdev);
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
+	if (acls.pagelist) {
+		req->r_pagelist = acls.pagelist;
+		acls.pagelist = NULL;
+	}
 	err = ceph_mdsc_do_request(mdsc, dir, req);
 	if (!err && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
 	ceph_mdsc_put_request(req);
-
+out:
 	if (!err)
-		ceph_init_acl(dentry, dentry->d_inode, dir);
+		ceph_init_inode_acls(dentry->d_inode, &acls);
 	else
 		d_drop(dentry);
+	ceph_release_acls_info(&acls);
 	return err;
 }
 
@@ -733,8 +743,8 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
 	dout("symlink in dir %p dentry %p to '%s'\n", dir, dentry, dest);
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SYMLINK, USE_AUTH_MDS);
 	if (IS_ERR(req)) {
-		d_drop(dentry);
-		return PTR_ERR(req);
+		err = PTR_ERR(req);
+		goto out;
 	}
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
@@ -746,9 +756,8 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
 	if (!err && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
 	ceph_mdsc_put_request(req);
-	if (!err)
-		ceph_init_acl(dentry, dentry->d_inode, dir);
-	else
+out:
+	if (err)
 		d_drop(dentry);
 	return err;
 }
@@ -758,6 +767,7 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
+	struct ceph_acls_info acls = {};
 	int err = -EROFS;
 	int op;
 
@@ -772,6 +782,12 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	} else {
 		goto out;
 	}
+
+	mode |= S_IFDIR;
+	err = ceph_pre_init_acls(dir, &mode, &acls);
+	if (err < 0)
+		goto out;
+
 	req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
@@ -784,15 +800,20 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	req->r_args.mkdir.mode = cpu_to_le32(mode);
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
+	if (acls.pagelist) {
+		req->r_pagelist = acls.pagelist;
+		acls.pagelist = NULL;
+	}
 	err = ceph_mdsc_do_request(mdsc, dir, req);
 	if (!err && !req->r_reply_info.head->is_dentry)
 		err = ceph_handle_notrace_create(dir, dentry);
 	ceph_mdsc_put_request(req);
 out:
 	if (!err)
-		ceph_init_acl(dentry, dentry->d_inode, dir);
+		ceph_init_inode_acls(dentry->d_inode, &acls);
 	else
 		d_drop(dentry);
+	ceph_release_acls_info(&acls);
 	return err;
 }
 
@@ -1069,7 +1090,6 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		ceph_dentry_lru_touch(dentry);
 	} else {
 		ceph_dir_clear_complete(dir);
-		d_drop(dentry);
 	}
 	iput(dir);
 	return valid;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 2eb02f80a0ab..d7e0da8366e6 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -235,6 +235,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	struct dentry *dn;
+	struct ceph_acls_info acls = {};
 	int err;
 
 	dout("atomic_open %p dentry %p '%.*s' %s flags %d mode 0%o\n",
@@ -248,22 +249,34 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (err < 0)
 		return err;
 
+	if (flags & O_CREAT) {
+		err = ceph_pre_init_acls(dir, &mode, &acls);
+		if (err < 0)
+			return err;
+	}
+
 	/* do the open */
 	req = prepare_open_request(dir->i_sb, flags, mode);
-	if (IS_ERR(req))
-		return PTR_ERR(req);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto out_acl;
+	}
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
 	if (flags & O_CREAT) {
 		req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
 		req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
+		if (acls.pagelist) {
+			req->r_pagelist = acls.pagelist;
+			acls.pagelist = NULL;
+		}
 	}
 	req->r_locked_dir = dir;           /* caller holds dir->i_mutex */
 	err = ceph_mdsc_do_request(mdsc,
 				   (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
 				   req);
 	if (err)
-		goto out_err;
+		goto out_req;
 
 	err = ceph_handle_snapdir(req, dentry, err);
 	if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
@@ -278,7 +291,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 		dn = NULL;
 	}
 	if (err)
-		goto out_err;
+		goto out_req;
 	if (dn || dentry->d_inode == NULL || S_ISLNK(dentry->d_inode->i_mode)) {
 		/* make vfs retry on splice, ENOENT, or symlink */
 		dout("atomic_open finish_no_open on dn %p\n", dn);
@@ -286,15 +299,17 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	} else {
 		dout("atomic_open finish_open on dn %p\n", dn);
 		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
-			ceph_init_acl(dentry, dentry->d_inode, dir);
+			ceph_init_inode_acls(dentry->d_inode, &acls);
 			*opened |= FILE_CREATED;
 		}
 		err = finish_open(file, dentry, ceph_open, opened);
 	}
-out_err:
+out_req:
 	if (!req->r_err && req->r_target_inode)
 		ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode);
 	ceph_mdsc_put_request(req);
+out_acl:
+	ceph_release_acls_info(&acls);
 	dout("atomic_open result=%d\n", err);
 	return err;
 }
@@ -826,8 +841,7 @@ again:
 	ceph_put_cap_refs(ci, got);
 
 	if (checkeof && ret >= 0) {
-		int statret = ceph_do_getattr(inode,
-					      CEPH_STAT_CAP_SIZE);
+		int statret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
 
 		/* hit EOF or hole? */
 		if (statret == 0 && iocb->ki_pos < inode->i_size &&
@@ -836,7 +850,6 @@ again:
 			     ", reading more\n", iocb->ki_pos,
 			     inode->i_size);
 
-			iov_iter_advance(to, ret);
 			read += ret;
 			len -= ret;
 			checkeof = 0;
@@ -995,7 +1008,7 @@ static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
 	mutex_lock(&inode->i_mutex);
 
 	if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
-		ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
+		ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
 		if (ret < 0) {
 			offset = ret;
 			goto out;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 04c89c266cec..7b6139004401 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -766,7 +766,7 @@ static int fill_inode(struct inode *inode,
 
 	/* xattrs */
 	/* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */
-	if ((issued & CEPH_CAP_XATTR_EXCL) == 0 &&
+	if ((ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))  &&
 	    le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) {
 		if (ci->i_xattrs.blob)
 			ceph_buffer_put(ci->i_xattrs.blob);
@@ -1813,10 +1813,6 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	if (ia_valid & ATTR_SIZE) {
 		dout("setattr %p size %lld -> %lld\n", inode,
 		     inode->i_size, attr->ia_size);
-		if (attr->ia_size > inode->i_sb->s_maxbytes) {
-			err = -EINVAL;
-			goto out;
-		}
 		if ((issued & CEPH_CAP_FILE_EXCL) &&
 		    attr->ia_size > inode->i_size) {
 			inode->i_size = attr->ia_size;
@@ -1896,8 +1892,6 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	if (mask & CEPH_SETATTR_SIZE)
 		__ceph_do_pending_vmtruncate(inode);
 	return err;
-out:
-	spin_unlock(&ci->i_ceph_lock);
 out_put:
 	ceph_mdsc_put_request(req);
 	return err;
@@ -1907,7 +1901,7 @@ out_put:
  * Verify that we have a lease on the given mask.  If not,
  * do a getattr against an mds.
  */
-int ceph_do_getattr(struct inode *inode, int mask)
+int ceph_do_getattr(struct inode *inode, int mask, bool force)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -1920,7 +1914,7 @@ int ceph_do_getattr(struct inode *inode, int mask)
 	}
 
 	dout("do_getattr inode %p mask %s mode 0%o\n", inode, ceph_cap_string(mask), inode->i_mode);
-	if (ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
+	if (!force && ceph_caps_issued_mask(ceph_inode(inode), mask, 1))
 		return 0;
 
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS);
@@ -1948,7 +1942,7 @@ int ceph_permission(struct inode *inode, int mask)
 	if (mask & MAY_NOT_BLOCK)
 		return -ECHILD;
 
-	err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED);
+	err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED, false);
 
 	if (!err)
 		err = generic_permission(inode, mask);
@@ -1966,7 +1960,7 @@ int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int err;
 
-	err = ceph_do_getattr(inode, CEPH_STAT_CAP_INODE_ALL);
+	err = ceph_do_getattr(inode, CEPH_STAT_CAP_INODE_ALL, false);
 	if (!err) {
 		generic_fillattr(inode, stat);
 		stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino);
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index a822a6e58290..f851d8d70158 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -19,7 +19,7 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
 	struct ceph_ioctl_layout l;
 	int err;
 
-	err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT);
+	err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT, false);
 	if (!err) {
 		l.stripe_unit = ceph_file_layout_su(ci->i_layout);
 		l.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
@@ -41,7 +41,7 @@ static long __validate_layout(struct ceph_mds_client *mdsc,
 	/* validate striping parameters */
 	if ((l->object_size & ~PAGE_MASK) ||
 	    (l->stripe_unit & ~PAGE_MASK) ||
-	    (l->stripe_unit != 0 &&
+	    ((unsigned)l->stripe_unit != 0 &&
 	     ((unsigned)l->object_size % (unsigned)l->stripe_unit)))
 		return -EINVAL;
 
@@ -74,7 +74,7 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 		return -EFAULT;
 
 	/* validate changed params against current layout */
-	err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT);
+	err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT, false);
 	if (err)
 		return err;
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index bad07c09f91e..a92d3f5c6c12 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -7,6 +7,7 @@
 #include <linux/sched.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/utsname.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -334,7 +335,7 @@ static void destroy_reply_info(struct ceph_mds_reply_info_parsed *info)
 /*
  * sessions
  */
-static const char *session_state_name(int s)
+const char *ceph_session_state_name(int s)
 {
 	switch (s) {
 	case CEPH_MDS_SESSION_NEW: return "new";
@@ -542,6 +543,8 @@ void ceph_mdsc_release_request(struct kref *kref)
 	}
 	kfree(req->r_path1);
 	kfree(req->r_path2);
+	if (req->r_pagelist)
+		ceph_pagelist_release(req->r_pagelist);
 	put_request_session(req);
 	ceph_unreserve_caps(req->r_mdsc, &req->r_caps_reservation);
 	kfree(req);
@@ -812,6 +815,74 @@ static struct ceph_msg *create_session_msg(u32 op, u64 seq)
 	h = msg->front.iov_base;
 	h->op = cpu_to_le32(op);
 	h->seq = cpu_to_le64(seq);
+
+	return msg;
+}
+
+/*
+ * session message, specialization for CEPH_SESSION_REQUEST_OPEN
+ * to include additional client metadata fields.
+ */
+static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u64 seq)
+{
+	struct ceph_msg *msg;
+	struct ceph_mds_session_head *h;
+	int i = -1;
+	int metadata_bytes = 0;
+	int metadata_key_count = 0;
+	struct ceph_options *opt = mdsc->fsc->client->options;
+	void *p;
+
+	const char* metadata[3][2] = {
+		{"hostname", utsname()->nodename},
+		{"entity_id", opt->name ? opt->name : ""},
+		{NULL, NULL}
+	};
+
+	/* Calculate serialized length of metadata */
+	metadata_bytes = 4;  /* map length */
+	for (i = 0; metadata[i][0] != NULL; ++i) {
+		metadata_bytes += 8 + strlen(metadata[i][0]) +
+			strlen(metadata[i][1]);
+		metadata_key_count++;
+	}
+
+	/* Allocate the message */
+	msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + metadata_bytes,
+			   GFP_NOFS, false);
+	if (!msg) {
+		pr_err("create_session_msg ENOMEM creating msg\n");
+		return NULL;
+	}
+	h = msg->front.iov_base;
+	h->op = cpu_to_le32(CEPH_SESSION_REQUEST_OPEN);
+	h->seq = cpu_to_le64(seq);
+
+	/*
+	 * Serialize client metadata into waiting buffer space, using
+	 * the format that userspace expects for map<string, string>
+	 */
+	msg->hdr.version = 2;  /* ClientSession messages with metadata are v2 */
+
+	/* The write pointer, following the session_head structure */
+	p = msg->front.iov_base + sizeof(*h);
+
+	/* Number of entries in the map */
+	ceph_encode_32(&p, metadata_key_count);
+
+	/* Two length-prefixed strings for each entry in the map */
+	for (i = 0; metadata[i][0] != NULL; ++i) {
+		size_t const key_len = strlen(metadata[i][0]);
+		size_t const val_len = strlen(metadata[i][1]);
+
+		ceph_encode_32(&p, key_len);
+		memcpy(p, metadata[i][0], key_len);
+		p += key_len;
+		ceph_encode_32(&p, val_len);
+		memcpy(p, metadata[i][1], val_len);
+		p += val_len;
+	}
+
 	return msg;
 }
 
@@ -835,7 +906,7 @@ static int __open_session(struct ceph_mds_client *mdsc,
 	session->s_renew_requested = jiffies;
 
 	/* send connect message */
-	msg = create_session_msg(CEPH_SESSION_REQUEST_OPEN, session->s_seq);
+	msg = create_session_open_msg(mdsc, session->s_seq);
 	if (!msg)
 		return -ENOMEM;
 	ceph_con_send(&session->s_con, msg);
@@ -1164,7 +1235,7 @@ static int send_flushmsg_ack(struct ceph_mds_client *mdsc,
 	struct ceph_msg *msg;
 
 	dout("send_flushmsg_ack to mds%d (%s)s seq %lld\n",
-	     session->s_mds, session_state_name(session->s_state), seq);
+	     session->s_mds, ceph_session_state_name(session->s_state), seq);
 	msg = create_session_msg(CEPH_SESSION_FLUSHMSG_ACK, seq);
 	if (!msg)
 		return -ENOMEM;
@@ -1216,7 +1287,7 @@ static int request_close_session(struct ceph_mds_client *mdsc,
 	struct ceph_msg *msg;
 
 	dout("request_close_session mds%d state %s seq %lld\n",
-	     session->s_mds, session_state_name(session->s_state),
+	     session->s_mds, ceph_session_state_name(session->s_state),
 	     session->s_seq);
 	msg = create_session_msg(CEPH_SESSION_REQUEST_CLOSE, session->s_seq);
 	if (!msg)
@@ -1847,13 +1918,15 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 
-	if (req->r_data_len) {
-		/* outbound data set only by ceph_sync_setxattr() */
-		BUG_ON(!req->r_pages);
-		ceph_msg_data_add_pages(msg, req->r_pages, req->r_data_len, 0);
+	if (req->r_pagelist) {
+		struct ceph_pagelist *pagelist = req->r_pagelist;
+		atomic_inc(&pagelist->refcnt);
+		ceph_msg_data_add_pagelist(msg, pagelist);
+		msg->hdr.data_len = cpu_to_le32(pagelist->length);
+	} else {
+		msg->hdr.data_len = 0;
 	}
 
-	msg->hdr.data_len = cpu_to_le32(req->r_data_len);
 	msg->hdr.data_off = cpu_to_le16(0);
 
 out_free2:
@@ -2007,7 +2080,7 @@ static int __do_request(struct ceph_mds_client *mdsc,
 	req->r_session = get_session(session);
 
 	dout("do_request mds%d session %p state %s\n", mds, session,
-	     session_state_name(session->s_state));
+	     ceph_session_state_name(session->s_state));
 	if (session->s_state != CEPH_MDS_SESSION_OPEN &&
 	    session->s_state != CEPH_MDS_SESSION_HUNG) {
 		if (session->s_state == CEPH_MDS_SESSION_NEW ||
@@ -2078,6 +2151,7 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds)
 		if (req->r_session &&
 		    req->r_session->s_mds == mds) {
 			dout(" kicking tid %llu\n", req->r_tid);
+			list_del_init(&req->r_wait);
 			__do_request(mdsc, req);
 		}
 	}
@@ -2444,7 +2518,7 @@ static void handle_session(struct ceph_mds_session *session,
 
 	dout("handle_session mds%d %s %p state %s seq %llu\n",
 	     mds, ceph_session_op_name(op), session,
-	     session_state_name(session->s_state), seq);
+	     ceph_session_state_name(session->s_state), seq);
 
 	if (session->s_state == CEPH_MDS_SESSION_HUNG) {
 		session->s_state = CEPH_MDS_SESSION_OPEN;
@@ -2471,9 +2545,8 @@ static void handle_session(struct ceph_mds_session *session,
 		if (session->s_state == CEPH_MDS_SESSION_RECONNECTING)
 			pr_info("mds%d reconnect denied\n", session->s_mds);
 		remove_session_caps(session);
-		wake = 1; /* for good measure */
+		wake = 2; /* for good measure */
 		wake_up_all(&mdsc->session_close_wq);
-		kick_requests(mdsc, mds);
 		break;
 
 	case CEPH_SESSION_STALE:
@@ -2503,6 +2576,8 @@ static void handle_session(struct ceph_mds_session *session,
 	if (wake) {
 		mutex_lock(&mdsc->mutex);
 		__wake_requests(mdsc, &session->s_waiting);
+		if (wake == 2)
+			kick_requests(mdsc, mds);
 		mutex_unlock(&mdsc->mutex);
 	}
 	return;
@@ -2695,18 +2770,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	session->s_state = CEPH_MDS_SESSION_RECONNECTING;
 	session->s_seq = 0;
 
-	ceph_con_close(&session->s_con);
-	ceph_con_open(&session->s_con,
-		      CEPH_ENTITY_TYPE_MDS, mds,
-		      ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
-
-	/* replay unsafe requests */
-	replay_unsafe_requests(mdsc, session);
-
-	down_read(&mdsc->snap_rwsem);
-
 	dout("session %p state %s\n", session,
-	     session_state_name(session->s_state));
+	     ceph_session_state_name(session->s_state));
 
 	spin_lock(&session->s_gen_ttl_lock);
 	session->s_cap_gen++;
@@ -2723,6 +2788,19 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	discard_cap_releases(mdsc, session);
 	spin_unlock(&session->s_cap_lock);
 
+	/* trim unused caps to reduce MDS's cache rejoin time */
+	shrink_dcache_parent(mdsc->fsc->sb->s_root);
+
+	ceph_con_close(&session->s_con);
+	ceph_con_open(&session->s_con,
+		      CEPH_ENTITY_TYPE_MDS, mds,
+		      ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
+
+	/* replay unsafe requests */
+	replay_unsafe_requests(mdsc, session);
+
+	down_read(&mdsc->snap_rwsem);
+
 	/* traverse this session's caps */
 	s_nr_caps = session->s_nr_caps;
 	err = ceph_pagelist_encode_32(pagelist, s_nr_caps);
@@ -2791,7 +2869,6 @@ fail:
 	mutex_unlock(&session->s_mutex);
 fail_nomsg:
 	ceph_pagelist_release(pagelist);
-	kfree(pagelist);
 fail_nopagelist:
 	pr_err("error %d preparing reconnect for mds%d\n", err, mds);
 	return;
@@ -2827,7 +2904,7 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		     ceph_mdsmap_is_laggy(oldmap, i) ? " (laggy)" : "",
 		     ceph_mds_state_name(newstate),
 		     ceph_mdsmap_is_laggy(newmap, i) ? " (laggy)" : "",
-		     session_state_name(s->s_state));
+		     ceph_session_state_name(s->s_state));
 
 		if (i >= newmap->m_max_mds ||
 		    memcmp(ceph_mdsmap_get_addr(oldmap, i),
@@ -2939,14 +3016,15 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 	if (dname.len != get_unaligned_le32(h+1))
 		goto bad;
 
-	mutex_lock(&session->s_mutex);
-	session->s_seq++;
-
 	/* lookup inode */
 	inode = ceph_find_inode(sb, vino);
 	dout("handle_lease %s, ino %llx %p %.*s\n",
 	     ceph_lease_op_name(h->action), vino.ino, inode,
 	     dname.len, dname.name);
+
+	mutex_lock(&session->s_mutex);
+	session->s_seq++;
+
 	if (inode == NULL) {
 		dout("handle_lease no inode %llx\n", vino.ino);
 		goto release;
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index e00737cf523c..3288359353e9 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -202,9 +202,7 @@ struct ceph_mds_request {
 	bool r_direct_is_hash;  /* true if r_direct_hash is valid */
 
 	/* data payload is used for xattr ops */
-	struct page **r_pages;
-	int r_num_pages;
-	int r_data_len;
+	struct ceph_pagelist *r_pagelist;
 
 	/* what caps shall we drop? */
 	int r_inode_drop, r_inode_unless;
@@ -332,6 +330,8 @@ ceph_get_mds_session(struct ceph_mds_session *s)
 	return s;
 }
 
+extern const char *ceph_session_state_name(int s);
+
 extern void ceph_put_mds_session(struct ceph_mds_session *s);
 
 extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 12b20744e386..b82f507979b8 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -95,6 +95,7 @@ struct ceph_fs_client {
 	struct dentry *debugfs_congestion_kb;
 	struct dentry *debugfs_bdi;
 	struct dentry *debugfs_mdsc, *debugfs_mdsmap;
+	struct dentry *debugfs_mds_sessions;
 #endif
 
 #ifdef CONFIG_CEPH_FSCACHE
@@ -714,7 +715,7 @@ extern void ceph_queue_vmtruncate(struct inode *inode);
 extern void ceph_queue_invalidate(struct inode *inode);
 extern void ceph_queue_writeback(struct inode *inode);
 
-extern int ceph_do_getattr(struct inode *inode, int mask);
+extern int ceph_do_getattr(struct inode *inode, int mask, bool force);
 extern int ceph_permission(struct inode *inode, int mask);
 extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
 extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
@@ -733,15 +734,23 @@ extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
 extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
 extern void __init ceph_xattr_init(void);
 extern void ceph_xattr_exit(void);
+extern const struct xattr_handler *ceph_xattr_handlers[];
 
 /* acl.c */
-extern const struct xattr_handler *ceph_xattr_handlers[];
+struct ceph_acls_info {
+	void *default_acl;
+	void *acl;
+	struct ceph_pagelist *pagelist;
+};
 
 #ifdef CONFIG_CEPH_FS_POSIX_ACL
 
 struct posix_acl *ceph_get_acl(struct inode *, int);
 int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type);
-int ceph_init_acl(struct dentry *, struct inode *, struct inode *);
+int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
+		       struct ceph_acls_info *info);
+void ceph_init_inode_acls(struct inode *inode, struct ceph_acls_info *info);
+void ceph_release_acls_info(struct ceph_acls_info *info);
 
 static inline void ceph_forget_all_cached_acls(struct inode *inode)
 {
@@ -753,12 +762,18 @@ static inline void ceph_forget_all_cached_acls(struct inode *inode)
 #define ceph_get_acl NULL
 #define ceph_set_acl NULL
 
-static inline int ceph_init_acl(struct dentry *dentry, struct inode *inode,
-				struct inode *dir)
+static inline int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
+				     struct ceph_acls_info *info)
 {
 	return 0;
 }
-
+static inline void ceph_init_inode_acls(struct inode *inode,
+					struct ceph_acls_info *info)
+{
+}
+static inline void ceph_release_acls_info(struct ceph_acls_info *info)
+{
+}
 static inline int ceph_acl_chmod(struct dentry *dentry, struct inode *inode)
 {
 	return 0;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 12f58d22e017..678b0d2bbbc4 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -1,4 +1,5 @@
 #include <linux/ceph/ceph_debug.h>
+#include <linux/ceph/pagelist.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -284,8 +285,7 @@ static size_t ceph_vxattrs_name_size(struct ceph_vxattr *vxattrs)
 		return ceph_dir_vxattrs_name_size;
 	if (vxattrs == ceph_file_vxattrs)
 		return ceph_file_vxattrs_name_size;
-	BUG();
-
+	BUG_ON(vxattrs);
 	return 0;
 }
 
@@ -736,24 +736,20 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
 	dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
 	     ci->i_xattrs.version, ci->i_xattrs.index_version);
 
-	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1) &&
-	    (ci->i_xattrs.index_version >= ci->i_xattrs.version)) {
-		goto get_xattr;
-	} else {
+	if (ci->i_xattrs.version == 0 ||
+	    !__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1)) {
 		spin_unlock(&ci->i_ceph_lock);
 		/* get xattrs from mds (if we don't already have them) */
-		err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR);
+		err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR, true);
 		if (err)
 			return err;
+		spin_lock(&ci->i_ceph_lock);
 	}
 
-	spin_lock(&ci->i_ceph_lock);
-
 	err = __build_xattrs(inode);
 	if (err < 0)
 		goto out;
 
-get_xattr:
 	err = -ENODATA;  /* == ENOATTR */
 	xattr = __get_xattr(ci, name);
 	if (!xattr)
@@ -798,23 +794,18 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
 	dout("listxattr %p ver=%lld index_ver=%lld\n", inode,
 	     ci->i_xattrs.version, ci->i_xattrs.index_version);
 
-	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1) &&
-	    (ci->i_xattrs.index_version >= ci->i_xattrs.version)) {
-		goto list_xattr;
-	} else {
+	if (ci->i_xattrs.version == 0 ||
+	    !__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1)) {
 		spin_unlock(&ci->i_ceph_lock);
-		err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR);
+		err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR, true);
 		if (err)
 			return err;
+		spin_lock(&ci->i_ceph_lock);
 	}
 
-	spin_lock(&ci->i_ceph_lock);
-
 	err = __build_xattrs(inode);
 	if (err < 0)
 		goto out;
-
-list_xattr:
 	/*
 	 * Start with virtual dir xattr names (if any) (including
 	 * terminating '\0' characters for each).
@@ -860,35 +851,25 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_request *req;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_pagelist *pagelist = NULL;
 	int err;
-	int i, nr_pages;
-	struct page **pages = NULL;
-	void *kaddr;
-
-	/* copy value into some pages */
-	nr_pages = calc_pages_for(0, size);
-	if (nr_pages) {
-		pages = kmalloc(sizeof(pages[0])*nr_pages, GFP_NOFS);
-		if (!pages)
+
+	if (value) {
+		/* copy value into pagelist */
+		pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS);
+		if (!pagelist)
 			return -ENOMEM;
-		err = -ENOMEM;
-		for (i = 0; i < nr_pages; i++) {
-			pages[i] = __page_cache_alloc(GFP_NOFS);
-			if (!pages[i]) {
-				nr_pages = i;
-				goto out;
-			}
-			kaddr = kmap(pages[i]);
-			memcpy(kaddr, value + i*PAGE_CACHE_SIZE,
-			       min(PAGE_CACHE_SIZE, size-i*PAGE_CACHE_SIZE));
-		}
+
+		ceph_pagelist_init(pagelist);
+		err = ceph_pagelist_append(pagelist, value, size);
+		if (err)
+			goto out;
+	} else {
+		flags |= CEPH_XATTR_REMOVE;
 	}
 
 	dout("setxattr value=%.*s\n", (int)size, value);
 
-	if (!value)
-		flags |= CEPH_XATTR_REMOVE;
-
 	/* do request */
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR,
 				       USE_AUTH_MDS);
@@ -903,9 +884,8 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
 	req->r_args.setxattr.flags = cpu_to_le32(flags);
 	req->r_path2 = kstrdup(name, GFP_NOFS);
 
-	req->r_pages = pages;
-	req->r_num_pages = nr_pages;
-	req->r_data_len = size;
+	req->r_pagelist = pagelist;
+	pagelist = NULL;
 
 	dout("xattr.ver (before): %lld\n", ci->i_xattrs.version);
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
@@ -913,11 +893,8 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
 	dout("xattr.ver (after): %lld\n", ci->i_xattrs.version);
 
 out:
-	if (pages) {
-		for (i = 0; i < nr_pages; i++)
-			__free_page(pages[i]);
-		kfree(pages);
-	}
+	if (pagelist)
+		ceph_pagelist_release(pagelist);
 	return err;
 }
 
@@ -968,7 +945,7 @@ int __ceph_setxattr(struct dentry *dentry, const char *name,
 retry:
 	issued = __ceph_caps_issued(ci, NULL);
 	dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued));
-	if (!(issued & CEPH_CAP_XATTR_EXCL))
+	if (ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))
 		goto do_sync;
 	__build_xattrs(inode);
 
@@ -1077,7 +1054,7 @@ retry:
 	issued = __ceph_caps_issued(ci, NULL);
 	dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
 
-	if (!(issued & CEPH_CAP_XATTR_EXCL))
+	if (ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))
 		goto do_sync;
 	__build_xattrs(inode);
 
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 58df174deb10..b8602f199815 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -195,15 +195,15 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 		else
 			noff = tkn_e - (sb_mountdata + off) + 1;
 
-		if (strnicmp(sb_mountdata + off, "unc=", 4) == 0) {
+		if (strncasecmp(sb_mountdata + off, "unc=", 4) == 0) {
 			off += noff;
 			continue;
 		}
-		if (strnicmp(sb_mountdata + off, "ip=", 3) == 0) {
+		if (strncasecmp(sb_mountdata + off, "ip=", 3) == 0) {
 			off += noff;
 			continue;
 		}
-		if (strnicmp(sb_mountdata + off, "prefixpath=", 11) == 0) {
+		if (strncasecmp(sb_mountdata + off, "prefixpath=", 11) == 0) {
 			off += noff;
 			continue;
 		}
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index 9409fa10bd5c..3182273a3407 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -45,6 +45,7 @@
 #define CIFS_MOUNT_POSIXACL	0x100000 /* mirror of MS_POSIXACL in mnt_cifs_flags */
 #define CIFS_MOUNT_CIFS_BACKUPUID 0x200000 /* backup intent bit for a user */
 #define CIFS_MOUNT_CIFS_BACKUPGID 0x400000 /* backup intent bit for a group */
+#define CIFS_MOUNT_MAP_SFM_CHR	0x800000 /* SFM/MAC mapping for illegal chars */
 
 struct cifs_sb_info {
 	struct rb_root tlink_tree;
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index a3e932547617..f4cf200b3c76 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -62,7 +62,6 @@ cifs_spnego_key_destroy(struct key *key)
 struct key_type cifs_spnego_key_type = {
 	.name		= "cifs.spnego",
 	.instantiate	= cifs_spnego_key_instantiate,
-	.match		= user_match,
 	.destroy	= cifs_spnego_key_destroy,
 	.describe	= user_describe,
 };
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 15e9505aa35f..0303c6793d90 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -20,6 +20,7 @@
  */
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include "cifs_fs_sb.h"
 #include "cifs_unicode.h"
 #include "cifs_uniupr.h"
 #include "cifspdu.h"
@@ -61,26 +62,24 @@ cifs_utf16_bytes(const __le16 *from, int maxbytes,
 	return outlen;
 }
 
-/*
- * cifs_mapchar - convert a host-endian char to proper char in codepage
- * @target - where converted character should be copied
- * @src_char - 2 byte host-endian source character
- * @cp - codepage to which character should be converted
- * @mapchar - should character be mapped according to mapchars mount option?
- *
- * This function handles the conversion of a single character. It is the
- * responsibility of the caller to ensure that the target buffer is large
- * enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
- */
-static int
-cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp,
-	     bool mapchar)
+int cifs_remap(struct cifs_sb_info *cifs_sb)
 {
-	int len = 1;
+	int map_type;
+
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
+		map_type = SFM_MAP_UNI_RSVD;
+	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
+		map_type = SFU_MAP_UNI_RSVD;
+	else
+		map_type = NO_MAP_UNI_RSVD;
 
-	if (!mapchar)
-		goto cp_convert;
+	return map_type;
+}
 
+/* Convert character using the SFU - "Services for Unix" remapping range */
+static bool
+convert_sfu_char(const __u16 src_char, char *target)
+{
 	/*
 	 * BB: Cannot handle remapping UNI_SLASH until all the calls to
 	 *     build_path_from_dentry are modified, as they use slash as
@@ -106,19 +105,74 @@ cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp,
 		*target = '<';
 		break;
 	default:
-		goto cp_convert;
+		return false;
 	}
+	return true;
+}
+
+/* Convert character using the SFM - "Services for Mac" remapping range */
+static bool
+convert_sfm_char(const __u16 src_char, char *target)
+{
+	switch (src_char) {
+	case SFM_COLON:
+		*target = ':';
+		break;
+	case SFM_ASTERISK:
+		*target = '*';
+		break;
+	case SFM_QUESTION:
+		*target = '?';
+		break;
+	case SFM_PIPE:
+		*target = '|';
+		break;
+	case SFM_GRTRTHAN:
+		*target = '>';
+		break;
+	case SFM_LESSTHAN:
+		*target = '<';
+		break;
+	case SFM_SLASH:
+		*target = '\\';
+		break;
+	default:
+		return false;
+	}
+	return true;
+}
 
-out:
-	return len;
 
-cp_convert:
+/*
+ * cifs_mapchar - convert a host-endian char to proper char in codepage
+ * @target - where converted character should be copied
+ * @src_char - 2 byte host-endian source character
+ * @cp - codepage to which character should be converted
+ * @map_type - How should the 7 NTFS/SMB reserved characters be mapped to UCS2?
+ *
+ * This function handles the conversion of a single character. It is the
+ * responsibility of the caller to ensure that the target buffer is large
+ * enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
+ */
+static int
+cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp,
+	     int maptype)
+{
+	int len = 1;
+
+	if ((maptype == SFM_MAP_UNI_RSVD) && convert_sfm_char(src_char, target))
+		return len;
+	else if ((maptype == SFU_MAP_UNI_RSVD) &&
+		  convert_sfu_char(src_char, target))
+		return len;
+
+	/* if character not one of seven in special remap set */
 	len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE);
 	if (len <= 0) {
 		*target = '?';
 		len = 1;
 	}
-	goto out;
+	return len;
 }
 
 /*
@@ -145,7 +199,7 @@ cp_convert:
  */
 int
 cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
-		 const struct nls_table *codepage, bool mapchar)
+		const struct nls_table *codepage, int map_type)
 {
 	int i, charlen, safelen;
 	int outlen = 0;
@@ -172,13 +226,13 @@ cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
 		 * conversion bleed into the null terminator
 		 */
 		if (outlen >= safelen) {
-			charlen = cifs_mapchar(tmp, ftmp, codepage, mapchar);
+			charlen = cifs_mapchar(tmp, ftmp, codepage, map_type);
 			if ((outlen + charlen) > (tolen - nullsize))
 				break;
 		}
 
 		/* put converted char into 'to' buffer */
-		charlen = cifs_mapchar(&to[outlen], ftmp, codepage, mapchar);
+		charlen = cifs_mapchar(&to[outlen], ftmp, codepage, map_type);
 		outlen += charlen;
 	}
 
@@ -267,7 +321,7 @@ cifs_strndup_from_utf16(const char *src, const int maxlen,
 		if (!dst)
 			return NULL;
 		cifs_from_utf16(dst, (__le16 *) src, len, maxlen, codepage,
-			       false);
+			       NO_MAP_UNI_RSVD);
 	} else {
 		len = strnlen(src, maxlen);
 		len++;
@@ -280,6 +334,66 @@ cifs_strndup_from_utf16(const char *src, const int maxlen,
 	return dst;
 }
 
+static __le16 convert_to_sfu_char(char src_char)
+{
+	__le16 dest_char;
+
+	switch (src_char) {
+	case ':':
+		dest_char = cpu_to_le16(UNI_COLON);
+		break;
+	case '*':
+		dest_char = cpu_to_le16(UNI_ASTERISK);
+		break;
+	case '?':
+		dest_char = cpu_to_le16(UNI_QUESTION);
+		break;
+	case '<':
+		dest_char = cpu_to_le16(UNI_LESSTHAN);
+		break;
+	case '>':
+		dest_char = cpu_to_le16(UNI_GRTRTHAN);
+		break;
+	case '|':
+		dest_char = cpu_to_le16(UNI_PIPE);
+		break;
+	default:
+		dest_char = 0;
+	}
+
+	return dest_char;
+}
+
+static __le16 convert_to_sfm_char(char src_char)
+{
+	__le16 dest_char;
+
+	switch (src_char) {
+	case ':':
+		dest_char = cpu_to_le16(SFM_COLON);
+		break;
+	case '*':
+		dest_char = cpu_to_le16(SFM_ASTERISK);
+		break;
+	case '?':
+		dest_char = cpu_to_le16(SFM_QUESTION);
+		break;
+	case '<':
+		dest_char = cpu_to_le16(SFM_LESSTHAN);
+		break;
+	case '>':
+		dest_char = cpu_to_le16(SFM_GRTRTHAN);
+		break;
+	case '|':
+		dest_char = cpu_to_le16(SFM_PIPE);
+		break;
+	default:
+		dest_char = 0;
+	}
+
+	return dest_char;
+}
+
 /*
  * Convert 16 bit Unicode pathname to wire format from string in current code
  * page. Conversion may involve remapping up the six characters that are
@@ -288,7 +402,7 @@ cifs_strndup_from_utf16(const char *src, const int maxlen,
  */
 int
 cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
-		 const struct nls_table *cp, int mapChars)
+		 const struct nls_table *cp, int map_chars)
 {
 	int i, charlen;
 	int j = 0;
@@ -296,39 +410,30 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 	__le16 dst_char;
 	wchar_t tmp;
 
-	if (!mapChars)
+	if (map_chars == NO_MAP_UNI_RSVD)
 		return cifs_strtoUTF16(target, source, PATH_MAX, cp);
 
 	for (i = 0; i < srclen; j++) {
 		src_char = source[i];
 		charlen = 1;
-		switch (src_char) {
-		case 0:
+
+		/* check if end of string */
+		if (src_char == 0)
 			goto ctoUTF16_out;
-		case ':':
-			dst_char = cpu_to_le16(UNI_COLON);
-			break;
-		case '*':
-			dst_char = cpu_to_le16(UNI_ASTERISK);
-			break;
-		case '?':
-			dst_char = cpu_to_le16(UNI_QUESTION);
-			break;
-		case '<':
-			dst_char = cpu_to_le16(UNI_LESSTHAN);
-			break;
-		case '>':
-			dst_char = cpu_to_le16(UNI_GRTRTHAN);
-			break;
-		case '|':
-			dst_char = cpu_to_le16(UNI_PIPE);
-			break;
+
+		/* see if we must remap this char */
+		if (map_chars == SFU_MAP_UNI_RSVD)
+			dst_char = convert_to_sfu_char(src_char);
+		else if (map_chars == SFM_MAP_UNI_RSVD)
+			dst_char = convert_to_sfm_char(src_char);
+		else
+			dst_char = 0;
 		/*
 		 * FIXME: We can not handle remapping backslash (UNI_SLASH)
 		 * until all the calls to build_path_from_dentry are modified,
 		 * as they use backslash as separator.
 		 */
-		default:
+		if (dst_char == 0) {
 			charlen = cp->char2uni(source + i, srclen - i, &tmp);
 			dst_char = cpu_to_le16(tmp);
 
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index d8eac3b6cefb..bdc52cb9a676 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -52,6 +52,34 @@
 #define UNI_PIPE        (__u16) ('|' + 0xF000)
 #define UNI_SLASH       (__u16) ('\\' + 0xF000)
 
+/*
+ * Macs use an older "SFM" mapping of the symbols above. Fortunately it does
+ * not conflict (although almost does) with the mapping above.
+ */
+
+#define SFM_ASTERISK    ((__u16) 0xF021)
+#define SFM_QUESTION    ((__u16) 0xF025)
+#define SFM_COLON       ((__u16) 0xF022)
+#define SFM_GRTRTHAN    ((__u16) 0xF024)
+#define SFM_LESSTHAN    ((__u16) 0xF023)
+#define SFM_PIPE        ((__u16) 0xF027)
+#define SFM_SLASH       ((__u16) 0xF026)
+
+/*
+ * Mapping mechanism to use when one of the seven reserved characters is
+ * encountered.  We can only map using one of the mechanisms at a time
+ * since otherwise readdir could return directory entries which we would
+ * not be able to open
+ *
+ * NO_MAP_UNI_RSVD  = do not perform any remapping of the character
+ * SFM_MAP_UNI_RSVD = map reserved characters using SFM scheme (MAC compatible)
+ * SFU_MAP_UNI_RSVD = map reserved characters ala SFU ("mapchars" option)
+ *
+ */
+#define NO_MAP_UNI_RSVD		0
+#define SFM_MAP_UNI_RSVD	1
+#define SFU_MAP_UNI_RSVD	2
+
 /* Just define what we want from uniupr.h.  We don't want to define the tables
  * in each source file.
  */
@@ -75,7 +103,7 @@ extern const struct UniCaseRange CifsUniLowerRange[];
 
 #ifdef __KERNEL__
 int cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
-		    const struct nls_table *codepage, bool mapchar);
+		    const struct nls_table *cp, int map_type);
 int cifs_utf16_bytes(const __le16 *from, int maxbytes,
 		     const struct nls_table *codepage);
 int cifs_strtoUTF16(__le16 *, const char *, int, const struct nls_table *);
@@ -84,6 +112,7 @@ char *cifs_strndup_from_utf16(const char *src, const int maxlen,
 			      const struct nls_table *codepage);
 extern int cifsConvertToUTF16(__le16 *target, const char *source, int maxlen,
 			      const struct nls_table *cp, int mapChars);
+extern int cifs_remap(struct cifs_sb_info *cifs_sb);
 #ifdef CONFIG_CIFS_SMB2
 extern __le16 *cifs_strndup_to_utf16(const char *src, const int maxlen,
 				     int *utf16_len, const struct nls_table *cp,
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 7ff866dbb89e..6d00c419cbae 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -84,7 +84,6 @@ static struct key_type cifs_idmap_key_type = {
 	.instantiate = cifs_idmap_key_instantiate,
 	.destroy     = cifs_idmap_key_destroy,
 	.describe    = user_describe,
-	.match       = user_match,
 };
 
 static char *
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 4934347321d3..4ac7445e6ec7 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -431,7 +431,7 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp)
 						return -ENOMEM;
 				cifs_from_utf16(ses->domainName,
 					(__le16 *)blobptr, attrsize, attrsize,
-					nls_cp, false);
+					nls_cp, NO_MAP_UNI_RSVD);
 				break;
 			}
 		}
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 889b98455750..9d7996e8e793 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -813,7 +813,8 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int whence)
 	return generic_file_llseek(file, offset, whence);
 }
 
-static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
+static int
+cifs_setlease(struct file *file, long arg, struct file_lock **lease, void **priv)
 {
 	/*
 	 * Note that this is called by vfs setlease with i_lock held to
@@ -829,7 +830,7 @@ static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
 	if (arg == F_UNLCK ||
 	    ((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) ||
 	    ((arg == F_WRLCK) && CIFS_CACHE_WRITE(CIFS_I(inode))))
-		return generic_setlease(file, arg, lease);
+		return generic_setlease(file, arg, lease, priv);
 	else if (tlink_tcon(cfile->tlink)->local_lease &&
 		 !CIFS_CACHE_READ(CIFS_I(inode)))
 		/*
@@ -840,7 +841,7 @@ static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)
 		 * knows that the file won't be changed on the server by anyone
 		 * else.
 		 */
-		return generic_setlease(file, arg, lease);
+		return generic_setlease(file, arg, lease, priv);
 	else
 		return -EAGAIN;
 }
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 25b8392bfdd2..02a33e529904 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -323,11 +323,11 @@ struct smb_version_operations {
 	int (*async_writev)(struct cifs_writedata *,
 			    void (*release)(struct kref *));
 	/* sync read from the server */
-	int (*sync_read)(const unsigned int, struct cifsFileInfo *,
+	int (*sync_read)(const unsigned int, struct cifs_fid *,
 			 struct cifs_io_parms *, unsigned int *, char **,
 			 int *);
 	/* sync write to the server */
-	int (*sync_write)(const unsigned int, struct cifsFileInfo *,
+	int (*sync_write)(const unsigned int, struct cifs_fid *,
 			  struct cifs_io_parms *, unsigned int *, struct kvec *,
 			  unsigned long);
 	/* open dir, start readdir */
@@ -466,6 +466,7 @@ struct smb_vol {
 	bool direct_io:1;
 	bool strict_io:1; /* strict cache behavior */
 	bool remap:1;      /* set to remap seven reserved chars in filenames */
+	bool sfu_remap:1;  /* remap seven reserved chars ala SFU */
 	bool posix_paths:1; /* unset to not ask for posix pathnames. */
 	bool no_linux_ext:1;
 	bool sfu_emul:1;
@@ -499,6 +500,7 @@ struct smb_vol {
 #define CIFS_MOUNT_MASK (CIFS_MOUNT_NO_PERM | CIFS_MOUNT_SET_UID | \
 			 CIFS_MOUNT_SERVER_INUM | CIFS_MOUNT_DIRECT_IO | \
 			 CIFS_MOUNT_NO_XATTR | CIFS_MOUNT_MAP_SPECIAL_CHR | \
+			 CIFS_MOUNT_MAP_SFM_CHR | \
 			 CIFS_MOUNT_UNX_EMUL | CIFS_MOUNT_NO_BRL | \
 			 CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_OVERR_UID | \
 			 CIFS_MOUNT_OVERR_GID | CIFS_MOUNT_DYNPERM | \
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 66f65001a6d8..61d00a6e398f 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -867,7 +867,7 @@ CIFSSMBDelFile(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	int rc = 0;
 	int bytes_returned;
 	int name_len;
-	int remap = cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR;
+	int remap = cifs_remap(cifs_sb);
 
 DelFileRetry:
 	rc = smb_init(SMB_COM_DELETE, 1, tcon, (void **) &pSMB,
@@ -913,7 +913,7 @@ CIFSSMBRmDir(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	int rc = 0;
 	int bytes_returned;
 	int name_len;
-	int remap = cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR;
+	int remap = cifs_remap(cifs_sb);
 
 	cifs_dbg(FYI, "In CIFSSMBRmDir\n");
 RmDirRetry:
@@ -958,7 +958,7 @@ CIFSSMBMkDir(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	CREATE_DIRECTORY_RSP *pSMBr = NULL;
 	int bytes_returned;
 	int name_len;
-	int remap = cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR;
+	int remap = cifs_remap(cifs_sb);
 
 	cifs_dbg(FYI, "In CIFSSMBMkDir\n");
 MkDirRetry:
@@ -1280,7 +1280,7 @@ CIFS_open(const unsigned int xid, struct cifs_open_parms *oparms, int *oplock,
 	__u16 count;
 	struct cifs_sb_info *cifs_sb = oparms->cifs_sb;
 	struct cifs_tcon *tcon = oparms->tcon;
-	int remap = cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR;
+	int remap = cifs_remap(cifs_sb);
 	const struct nls_table *nls = cifs_sb->local_nls;
 	int create_options = oparms->create_options;
 	int desired_access = oparms->desired_access;
@@ -2572,7 +2572,7 @@ CIFSSMBRename(const unsigned int xid, struct cifs_tcon *tcon,
 	int bytes_returned;
 	int name_len, name_len2;
 	__u16 count;
-	int remap = cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR;
+	int remap = cifs_remap(cifs_sb);
 
 	cifs_dbg(FYI, "In CIFSSMBRename\n");
 renameRetry:
@@ -2968,7 +2968,7 @@ CIFSCreateHardLink(const unsigned int xid, struct cifs_tcon *tcon,
 	int bytes_returned;
 	int name_len, name_len2;
 	__u16 count;
-	int remap = cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR;
+	int remap = cifs_remap(cifs_sb);
 
 	cifs_dbg(FYI, "In CIFSCreateHardLink\n");
 winCreateHardLinkRetry:
@@ -4367,7 +4367,7 @@ findFirstRetry:
 		return rc;
 
 	nls_codepage = cifs_sb->local_nls;
-	remap = cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR;
+	remap = cifs_remap(cifs_sb);
 
 	if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
 		name_len =
@@ -5527,7 +5527,7 @@ CIFSSMBSetEOF(const unsigned int xid, struct cifs_tcon *tcon,
 	int name_len;
 	int rc = 0;
 	int bytes_returned = 0;
-	int remap = cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR;
+	int remap = cifs_remap(cifs_sb);
 
 	__u16 params, byte_count, data_count, param_offset, offset;
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 36ca2045009b..24fa08d261fb 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -70,6 +70,7 @@ enum {
 	Opt_forcegid, Opt_noforcegid,
 	Opt_noblocksend, Opt_noautotune,
 	Opt_hard, Opt_soft, Opt_perm, Opt_noperm,
+	Opt_mapposix, Opt_nomapposix,
 	Opt_mapchars, Opt_nomapchars, Opt_sfu,
 	Opt_nosfu, Opt_nodfs, Opt_posixpaths,
 	Opt_noposixpaths, Opt_nounix,
@@ -124,8 +125,10 @@ static const match_table_t cifs_mount_option_tokens = {
 	{ Opt_soft, "soft" },
 	{ Opt_perm, "perm" },
 	{ Opt_noperm, "noperm" },
-	{ Opt_mapchars, "mapchars" },
+	{ Opt_mapchars, "mapchars" }, /* SFU style */
 	{ Opt_nomapchars, "nomapchars" },
+	{ Opt_mapposix, "mapposix" }, /* SFM style */
+	{ Opt_nomapposix, "nomapposix" },
 	{ Opt_sfu, "sfu" },
 	{ Opt_nosfu, "nosfu" },
 	{ Opt_nodfs, "nodfs" },
@@ -1231,6 +1234,14 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 	vol->linux_uid = current_uid();
 	vol->linux_gid = current_gid();
 
+	/*
+	 * default to SFM style remapping of seven reserved characters
+	 * unless user overrides it or we negotiate CIFS POSIX where
+	 * it is unnecessary.  Can not simultaneously use more than one mapping
+	 * since then readdir could list files that open could not open
+	 */
+	vol->remap = true;
+
 	/* default to only allowing write access to owner of the mount */
 	vol->dir_mode = vol->file_mode = S_IRUGO | S_IXUGO | S_IWUSR;
 
@@ -1338,10 +1349,18 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			vol->noperm = 1;
 			break;
 		case Opt_mapchars:
-			vol->remap = 1;
+			vol->sfu_remap = true;
+			vol->remap = false; /* disable SFM mapping */
 			break;
 		case Opt_nomapchars:
-			vol->remap = 0;
+			vol->sfu_remap = false;
+			break;
+		case Opt_mapposix:
+			vol->remap = true;
+			vol->sfu_remap = false; /* disable SFU mapping */
+			break;
+		case Opt_nomapposix:
+			vol->remap = false;
 			break;
 		case Opt_sfu:
 			vol->sfu_emul = 1;
@@ -1718,7 +1737,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 				goto cifs_parse_mount_err;
 			}
 
-			 if (strnicmp(string, "default", 7) != 0) {
+			 if (strncasecmp(string, "default", 7) != 0) {
 				vol->iocharset = kstrdup(string,
 							 GFP_KERNEL);
 				if (!vol->iocharset) {
@@ -1790,7 +1809,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			if (string == NULL)
 				goto out_nomem;
 
-			if (strnicmp(string, "1", 1) == 0) {
+			if (strncasecmp(string, "1", 1) == 0) {
 				/* This is the default */
 				break;
 			}
@@ -3197,6 +3216,8 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 	if (pvolume_info->server_ino)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SERVER_INUM;
 	if (pvolume_info->remap)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SFM_CHR;
+	if (pvolume_info->sfu_remap)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SPECIAL_CHR;
 	if (pvolume_info->no_xattr)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_XATTR;
@@ -3239,10 +3260,20 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 	}
 	if (pvolume_info->mfsymlinks) {
 		if (pvolume_info->sfu_emul) {
-			cifs_dbg(VFS, "mount option mfsymlinks ignored if sfu mount option is used\n");
-		} else {
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MF_SYMLINKS;
+			/*
+			 * Our SFU ("Services for Unix" emulation does not allow
+			 * creating symlinks but does allow reading existing SFU
+			 * symlinks (it does allow both creating and reading SFU
+			 * style mknod and FIFOs though). When "mfsymlinks" and
+			 * "sfu" are both enabled at the same time, it allows
+			 * reading both types of symlinks, but will only create
+			 * them with mfsymlinks format. This allows better
+			 * Apple compatibility (probably better for Samba too)
+			 * while still recognizing old Windows style symlinks.
+			 */
+			cifs_dbg(VFS, "mount options mfsymlinks and sfu both enabled\n");
 		}
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MF_SYMLINKS;
 	}
 
 	if ((pvolume_info->cifs_acl) && (pvolume_info->dynperm))
@@ -3330,8 +3361,7 @@ expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses,
 	ref_path = check_prefix ? full_path + 1 : volume_info->UNC + 1;
 
 	rc = get_dfs_path(xid, ses, ref_path, cifs_sb->local_nls,
-			  &num_referrals, &referrals,
-			  cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+			  &num_referrals, &referrals, cifs_remap(cifs_sb));
 
 	if (!rc && num_referrals > 0) {
 		char *fake_devname = NULL;
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 6cbd9c688cfe..b72bc29cba23 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -461,8 +461,8 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 
 	xid = get_xid();
 
-	cifs_dbg(FYI, "parent inode = 0x%p name is: %s and dentry = 0x%p\n",
-		 inode, direntry->d_name.name, direntry);
+	cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
+		 inode, direntry, direntry);
 
 	tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
 	if (IS_ERR(tlink)) {
@@ -540,8 +540,8 @@ int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
 	struct cifs_fid fid;
 	__u32 oplock;
 
-	cifs_dbg(FYI, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p\n",
-		 inode, direntry->d_name.name, direntry);
+	cifs_dbg(FYI, "cifs_create parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
+		 inode, direntry, direntry);
 
 	tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
 	rc = PTR_ERR(tlink);
@@ -577,12 +577,13 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
 	struct cifs_io_parms io_parms;
 	char *full_path = NULL;
 	struct inode *newinode = NULL;
-	int oplock = 0;
+	__u32 oplock = 0;
 	struct cifs_fid fid;
 	struct cifs_open_parms oparms;
 	FILE_ALL_INFO *buf = NULL;
 	unsigned int bytes_written;
 	struct win_dev *pdev;
+	struct kvec iov[2];
 
 	if (!old_valid_dev(device_number))
 		return -EINVAL;
@@ -658,7 +659,11 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
 	oparms.fid = &fid;
 	oparms.reconnect = false;
 
-	rc = CIFS_open(xid, &oparms, &oplock, buf);
+	if (tcon->ses->server->oplocks)
+		oplock = REQ_OPLOCK;
+	else
+		oplock = 0;
+	rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, buf);
 	if (rc)
 		goto mknod_out;
 
@@ -668,25 +673,26 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
 	 */
 
 	pdev = (struct win_dev *)buf;
-	io_parms.netfid = fid.netfid;
 	io_parms.pid = current->tgid;
 	io_parms.tcon = tcon;
 	io_parms.offset = 0;
 	io_parms.length = sizeof(struct win_dev);
+	iov[1].iov_base = buf;
+	iov[1].iov_len = sizeof(struct win_dev);
 	if (S_ISCHR(mode)) {
 		memcpy(pdev->type, "IntxCHR", 8);
 		pdev->major = cpu_to_le64(MAJOR(device_number));
 		pdev->minor = cpu_to_le64(MINOR(device_number));
-		rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, (char *)pdev,
-				  NULL, 0);
+		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
+							&bytes_written, iov, 1);
 	} else if (S_ISBLK(mode)) {
 		memcpy(pdev->type, "IntxBLK", 8);
 		pdev->major = cpu_to_le64(MAJOR(device_number));
 		pdev->minor = cpu_to_le64(MINOR(device_number));
-		rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, (char *)pdev,
-				  NULL, 0);
+		rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms,
+							&bytes_written, iov, 1);
 	} /* else if (S_ISFIFO) */
-	CIFSSMBClose(xid, tcon, fid.netfid);
+	tcon->ses->server->ops->close(xid, tcon, &fid);
 	d_drop(direntry);
 
 	/* FIXME: add code here to set EAs */
@@ -713,8 +719,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 
 	xid = get_xid();
 
-	cifs_dbg(FYI, "parent inode = 0x%p name is: %s and dentry = 0x%p\n",
-		 parent_dir_inode, direntry->d_name.name, direntry);
+	cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
+		 parent_dir_inode, direntry, direntry);
 
 	/* check whether path exists */
 
@@ -833,7 +839,7 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
 {
 	int rc = 0;
 
-	cifs_dbg(FYI, "In cifs d_delete, name = %s\n", direntry->d_name.name);
+	cifs_dbg(FYI, "In cifs d_delete, name = %pd\n", direntry);
 
 	return rc;
 }     */
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 5f29354b072a..3e4d00a06c44 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1650,8 +1650,8 @@ cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data,
 
 	cifs_sb = CIFS_SB(dentry->d_sb);
 
-	cifs_dbg(FYI, "write %zd bytes to offset %lld of %s\n",
-		 write_size, *offset, dentry->d_name.name);
+	cifs_dbg(FYI, "write %zd bytes to offset %lld of %pd\n",
+		 write_size, *offset, dentry);
 
 	tcon = tlink_tcon(open_file->tlink);
 	server = tcon->ses->server;
@@ -1687,8 +1687,8 @@ cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data,
 			io_parms.tcon = tcon;
 			io_parms.offset = *offset;
 			io_parms.length = len;
-			rc = server->ops->sync_write(xid, open_file, &io_parms,
-						     &bytes_written, iov, 1);
+			rc = server->ops->sync_write(xid, &open_file->fid,
+					&io_parms, &bytes_written, iov, 1);
 		}
 		if (rc || (bytes_written == 0)) {
 			if (total_written)
@@ -2273,8 +2273,8 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 
 	xid = get_xid();
 
-	cifs_dbg(FYI, "Sync file - name: %s datasync: 0x%x\n",
-		 file->f_path.dentry->d_name.name, datasync);
+	cifs_dbg(FYI, "Sync file - name: %pD datasync: 0x%x\n",
+		 file, datasync);
 
 	if (!CIFS_CACHE_READ(CIFS_I(inode))) {
 		rc = cifs_zap_mapping(inode);
@@ -2315,8 +2315,8 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 	xid = get_xid();
 
-	cifs_dbg(FYI, "Sync file - name: %s datasync: 0x%x\n",
-		 file->f_path.dentry->d_name.name, datasync);
+	cifs_dbg(FYI, "Sync file - name: %pD datasync: 0x%x\n",
+		 file, datasync);
 
 	tcon = tlink_tcon(smbfile->tlink);
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
@@ -3206,7 +3206,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
 			io_parms.tcon = tcon;
 			io_parms.offset = *offset;
 			io_parms.length = current_read_size;
-			rc = server->ops->sync_read(xid, open_file, &io_parms,
+			rc = server->ops->sync_read(xid, &open_file->fid, &io_parms,
 						    &bytes_read, &cur_offset,
 						    &buf_type);
 		} while (rc == -EAGAIN);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 7899a40465b3..197cb503d528 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -30,6 +30,7 @@
 #include "cifsproto.h"
 #include "cifs_debug.h"
 #include "cifs_fs_sb.h"
+#include "cifs_unicode.h"
 #include "fscache.h"
 
 
@@ -412,7 +413,7 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path,
 	      struct cifs_sb_info *cifs_sb, unsigned int xid)
 {
 	int rc;
-	int oplock = 0;
+	__u32 oplock;
 	struct tcon_link *tlink;
 	struct cifs_tcon *tcon;
 	struct cifs_fid fid;
@@ -451,8 +452,13 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path,
 	oparms.fid = &fid;
 	oparms.reconnect = false;
 
-	rc = CIFS_open(xid, &oparms, &oplock, NULL);
+	if (tcon->ses->server->oplocks)
+		oplock = REQ_OPLOCK;
+	else
+		oplock = 0;
+	rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, NULL);
 	if (rc) {
+		cifs_dbg(FYI, "check sfu type of %s, open rc = %d\n", path, rc);
 		cifs_put_tlink(tlink);
 		return rc;
 	}
@@ -464,7 +470,8 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path,
 	io_parms.offset = 0;
 	io_parms.length = 24;
 
-	rc = CIFSSMBRead(xid, &io_parms, &bytes_read, &pbuf, &buf_type);
+	rc = tcon->ses->server->ops->sync_read(xid, &fid, &io_parms,
+					&bytes_read, &pbuf, &buf_type);
 	if ((rc == 0) && (bytes_read >= 8)) {
 		if (memcmp("IntxBLK", pbuf, 8) == 0) {
 			cifs_dbg(FYI, "Block device\n");
@@ -504,7 +511,8 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path,
 		fattr->cf_dtype = DT_REG;
 		rc = -EOPNOTSUPP; /* or some unknown SFU type */
 	}
-	CIFSSMBClose(xid, tcon, fid.netfid);
+
+	tcon->ses->server->ops->close(xid, tcon, &fid);
 	cifs_put_tlink(tlink);
 	return rc;
 }
@@ -539,7 +547,7 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path,
 	rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path,
 			"SETFILEBITS", ea_value, 4 /* size of buf */,
 			cifs_sb->local_nls,
-			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+			cifs_remap(cifs_sb));
 	cifs_put_tlink(tlink);
 	if (rc < 0)
 		return (int)rc;
@@ -952,11 +960,18 @@ struct inode *cifs_root_iget(struct super_block *sb)
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 
 	xid = get_xid();
-	if (tcon->unix_ext)
+	if (tcon->unix_ext) {
 		rc = cifs_get_inode_info_unix(&inode, "", sb, xid);
-	else
-		rc = cifs_get_inode_info(&inode, "", NULL, sb, xid, NULL);
+		/* some servers mistakenly claim POSIX support */
+		if (rc != -EOPNOTSUPP)
+			goto iget_no_retry;
+		cifs_dbg(VFS, "server does not support POSIX extensions");
+		tcon->unix_ext = false;
+	}
+
+	rc = cifs_get_inode_info(&inode, "", NULL, sb, xid, NULL);
 
+iget_no_retry:
 	if (!inode) {
 		inode = ERR_PTR(rc);
 		goto out;
@@ -1117,8 +1132,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
 	/* rename the file */
 	rc = CIFSSMBRenameOpenFile(xid, tcon, fid.netfid, NULL,
 				   cifs_sb->local_nls,
-				   cifs_sb->mnt_cifs_flags &
-					    CIFS_MOUNT_MAP_SPECIAL_CHR);
+				   cifs_remap(cifs_sb));
 	if (rc != 0) {
 		rc = -EBUSY;
 		goto undo_setattr;
@@ -1159,8 +1173,7 @@ out:
 	 */
 undo_rename:
 	CIFSSMBRenameOpenFile(xid, tcon, fid.netfid, dentry->d_name.name,
-				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-					    CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_sb->local_nls, cifs_remap(cifs_sb));
 undo_setattr:
 	if (dosattr != origattr) {
 		info_buf->Attributes = cpu_to_le32(origattr);
@@ -1226,7 +1239,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry)
 				le64_to_cpu(tcon->fsUnixInfo.Capability))) {
 		rc = CIFSPOSIXDelFile(xid, tcon, full_path,
 			SMB_POSIX_UNLINK_FILE_TARGET, cifs_sb->local_nls,
-			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+			cifs_remap(cifs_sb));
 		cifs_dbg(FYI, "posix del rc %d\n", rc);
 		if ((rc == 0) || (rc == -ENOENT))
 			goto psx_del_no_retry;
@@ -1349,8 +1362,7 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
 		}
 		CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args,
 				       cifs_sb->local_nls,
-				       cifs_sb->mnt_cifs_flags &
-				       CIFS_MOUNT_MAP_SPECIAL_CHR);
+				       cifs_remap(cifs_sb));
 	} else {
 		struct TCP_Server_Info *server = tcon->ses->server;
 		if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) &&
@@ -1392,8 +1404,7 @@ cifs_posix_mkdir(struct inode *inode, struct dentry *dentry, umode_t mode,
 	mode &= ~current_umask();
 	rc = CIFSPOSIXCreate(xid, tcon, SMB_O_DIRECTORY | SMB_O_CREAT, mode,
 			     NULL /* netfid */, info, &oplock, full_path,
-			     cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-			     CIFS_MOUNT_MAP_SPECIAL_CHR);
+			     cifs_sb->local_nls, cifs_remap(cifs_sb));
 	if (rc == -EOPNOTSUPP)
 		goto posix_mkdir_out;
 	else if (rc) {
@@ -1419,8 +1430,8 @@ cifs_posix_mkdir(struct inode *inode, struct dentry *dentry, umode_t mode,
 	d_instantiate(dentry, newinode);
 
 #ifdef CONFIG_CIFS_DEBUG2
-	cifs_dbg(FYI, "instantiated dentry %p %s to inode %p\n",
-		 dentry, dentry->d_name.name, newinode);
+	cifs_dbg(FYI, "instantiated dentry %p %pd to inode %p\n",
+		 dentry, dentry, newinode);
 
 	if (newinode->i_nlink != 2)
 		cifs_dbg(FYI, "unexpected number of links %d\n",
@@ -1617,8 +1628,7 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
 	if (rc == 0) {
 		rc = CIFSSMBRenameOpenFile(xid, tcon, fid.netfid,
 				(const char *) to_dentry->d_name.name,
-				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_sb->local_nls, cifs_remap(cifs_sb));
 		CIFSSMBClose(xid, tcon, fid.netfid);
 	}
 do_rename_exit:
@@ -1694,16 +1704,14 @@ cifs_rename2(struct inode *source_dir, struct dentry *source_dentry,
 		tmprc = CIFSSMBUnixQPathInfo(xid, tcon, from_name,
 					     info_buf_source,
 					     cifs_sb->local_nls,
-					     cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+					     cifs_remap(cifs_sb));
 		if (tmprc != 0)
 			goto unlink_target;
 
 		tmprc = CIFSSMBUnixQPathInfo(xid, tcon, to_name,
 					     info_buf_target,
 					     cifs_sb->local_nls,
-					     cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+					     cifs_remap(cifs_sb));
 
 		if (tmprc == 0 && (info_buf_source->UniqueId ==
 				   info_buf_target->UniqueId)) {
@@ -2068,8 +2076,7 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 		rc = SMBLegacyOpen(xid, tcon, full_path, FILE_OPEN,
 				   GENERIC_WRITE, CREATE_NOT_DIR, &netfid,
 				   &oplock, NULL, cifs_sb->local_nls,
-				   cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+				   cifs_remap(cifs_sb));
 		if (rc == 0) {
 			unsigned int bytes_written;
 
@@ -2111,8 +2118,8 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 	struct cifs_unix_set_info_args *args = NULL;
 	struct cifsFileInfo *open_file;
 
-	cifs_dbg(FYI, "setattr_unix on file %s attrs->ia_valid=0x%x\n",
-		 direntry->d_name.name, attrs->ia_valid);
+	cifs_dbg(FYI, "setattr_unix on file %pd attrs->ia_valid=0x%x\n",
+		 direntry, attrs->ia_valid);
 
 	xid = get_xid();
 
@@ -2254,8 +2261,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 
 	xid = get_xid();
 
-	cifs_dbg(FYI, "setattr on file %s attrs->iavalid 0x%x\n",
-		 direntry->d_name.name, attrs->ia_valid);
+	cifs_dbg(FYI, "setattr on file %pd attrs->iavalid 0x%x\n",
+		 direntry, attrs->ia_valid);
 
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
 		attrs->ia_valid |= ATTR_FORCE;
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 5657416d3483..2ec6037f61c7 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -28,6 +28,10 @@
 #include "cifsproto.h"
 #include "cifs_debug.h"
 #include "cifs_fs_sb.h"
+#include "cifs_unicode.h"
+#ifdef CONFIG_CIFS_SMB2
+#include "smb2proto.h"
+#endif
 
 /*
  * M-F Symlink Functions - Begin
@@ -401,6 +405,134 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 }
 
 /*
+ * SMB 2.1/SMB3 Protocol specific functions
+ */
+#ifdef CONFIG_CIFS_SMB2
+int
+smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
+		      struct cifs_sb_info *cifs_sb, const unsigned char *path,
+		      char *pbuf, unsigned int *pbytes_read)
+{
+	int rc;
+	struct cifs_fid fid;
+	struct cifs_open_parms oparms;
+	struct cifs_io_parms io_parms;
+	int buf_type = CIFS_NO_BUFFER;
+	__le16 *utf16_path;
+	__u8 oplock = SMB2_OPLOCK_LEVEL_II;
+	struct smb2_file_all_info *pfile_info = NULL;
+
+	oparms.tcon = tcon;
+	oparms.cifs_sb = cifs_sb;
+	oparms.desired_access = GENERIC_READ;
+	oparms.create_options = CREATE_NOT_DIR;
+	if (backup_cred(cifs_sb))
+		oparms.create_options |= CREATE_OPEN_BACKUP_INTENT;
+	oparms.disposition = FILE_OPEN;
+	oparms.fid = &fid;
+	oparms.reconnect = false;
+
+	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
+	if (utf16_path == NULL)
+		return -ENOMEM;
+
+	pfile_info = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
+			     GFP_KERNEL);
+
+	if (pfile_info == NULL) {
+		kfree(utf16_path);
+		return  -ENOMEM;
+	}
+
+	rc = SMB2_open(xid, &oparms, utf16_path, &oplock, pfile_info, NULL);
+	if (rc)
+		goto qmf_out_open_fail;
+
+	if (pfile_info->EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) {
+		/* it's not a symlink */
+		rc = -ENOENT; /* Is there a better rc to return? */
+		goto qmf_out;
+	}
+
+	io_parms.netfid = fid.netfid;
+	io_parms.pid = current->tgid;
+	io_parms.tcon = tcon;
+	io_parms.offset = 0;
+	io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
+	io_parms.persistent_fid = fid.persistent_fid;
+	io_parms.volatile_fid = fid.volatile_fid;
+	rc = SMB2_read(xid, &io_parms, pbytes_read, &pbuf, &buf_type);
+qmf_out:
+	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+qmf_out_open_fail:
+	kfree(utf16_path);
+	kfree(pfile_info);
+	return rc;
+}
+
+int
+smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
+		       struct cifs_sb_info *cifs_sb, const unsigned char *path,
+		       char *pbuf, unsigned int *pbytes_written)
+{
+	int rc;
+	struct cifs_fid fid;
+	struct cifs_open_parms oparms;
+	struct cifs_io_parms io_parms;
+	int create_options = CREATE_NOT_DIR;
+	__le16 *utf16_path;
+	__u8 oplock = SMB2_OPLOCK_LEVEL_EXCLUSIVE;
+	struct kvec iov[2];
+
+	if (backup_cred(cifs_sb))
+		create_options |= CREATE_OPEN_BACKUP_INTENT;
+
+	cifs_dbg(FYI, "%s: path: %s\n", __func__, path);
+
+	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
+	if (!utf16_path)
+		return -ENOMEM;
+
+	oparms.tcon = tcon;
+	oparms.cifs_sb = cifs_sb;
+	oparms.desired_access = GENERIC_WRITE;
+	oparms.create_options = create_options;
+	oparms.disposition = FILE_CREATE;
+	oparms.fid = &fid;
+	oparms.reconnect = false;
+
+	rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
+	if (rc) {
+		kfree(utf16_path);
+		return rc;
+	}
+
+	io_parms.netfid = fid.netfid;
+	io_parms.pid = current->tgid;
+	io_parms.tcon = tcon;
+	io_parms.offset = 0;
+	io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
+	io_parms.persistent_fid = fid.persistent_fid;
+	io_parms.volatile_fid = fid.volatile_fid;
+
+	/* iov[0] is reserved for smb header */
+	iov[1].iov_base = pbuf;
+	iov[1].iov_len = CIFS_MF_SYMLINK_FILE_SIZE;
+
+	rc = SMB2_write(xid, &io_parms, pbytes_written, iov, 1);
+
+	/* Make sure we wrote all of the symlink data */
+	if ((rc == 0) && (*pbytes_written != CIFS_MF_SYMLINK_FILE_SIZE))
+		rc = -EIO;
+
+	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+
+	kfree(utf16_path);
+	return rc;
+}
+#endif /* CONFIG_CIFS_SMB2 */
+
+/*
  * M-F Symlink Functions - End
  */
 
@@ -435,8 +567,7 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
 	if (tcon->unix_ext)
 		rc = CIFSUnixCreateHardLink(xid, tcon, from_name, to_name,
 					    cifs_sb->local_nls,
-					    cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+					    cifs_remap(cifs_sb));
 	else {
 		server = tcon->ses->server;
 		if (!server->ops->create_hardlink) {
@@ -461,11 +592,7 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
 			spin_lock(&old_file->d_inode->i_lock);
 			inc_nlink(old_file->d_inode);
 			spin_unlock(&old_file->d_inode->i_lock);
-			/*
-			 * BB should we make this contingent on superblock flag
-			 * NOATIME?
-			 */
-			/* old_file->d_inode->i_ctime = CURRENT_TIME; */
+
 			/*
 			 * parent dir timestamps will update from srv within a
 			 * second, would it really be worth it to set the parent
@@ -475,7 +602,9 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
 		}
 		/*
 		 * if not oplocked will force revalidate to get info on source
-		 * file from srv
+		 * file from srv.  Note Samba server prior to 4.2 has bug -
+		 * not updating src file ctime on hardlinks but Windows servers
+		 * handle it properly
 		 */
 		cifsInode->time = 0;
 
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index b334a89d6a66..8fd2a95860ba 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -87,8 +87,6 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
 		return;
 
 	if (dentry) {
-		int err;
-
 		inode = dentry->d_inode;
 		if (inode) {
 			/*
@@ -105,10 +103,8 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
 				goto out;
 			}
 		}
-		err = d_invalidate(dentry);
+		d_invalidate(dentry);
 		dput(dentry);
-		if (err)
-			return;
 	}
 
 	/*
@@ -243,7 +239,7 @@ int get_symlink_reparse_path(char *full_path, struct cifs_sb_info *cifs_sb,
 	rc = CIFSSMBOpen(xid, ptcon, full_path, FILE_OPEN, GENERIC_READ,
 			OPEN_REPARSE_POINT, &fid, &oplock, NULL,
 			cifs_sb->local_nls,
-			cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+			cifs_remap(cifs_sb);
 	if (!rc) {
 		tmpbuffer = kmalloc(maxpath);
 		rc = CIFSSMBQueryReparseLinkInfo(xid, ptcon, full_path,
@@ -708,15 +704,15 @@ static int cifs_filldir(char *find_entry, struct file *file,
 
 	if (file_info->srch_inf.unicode) {
 		struct nls_table *nlt = cifs_sb->local_nls;
+		int map_type;
 
+		map_type = cifs_remap(cifs_sb);
 		name.name = scratch_buf;
 		name.len =
 			cifs_from_utf16((char *)name.name, (__le16 *)de.name,
 					UNICODE_NAME_MAX,
 					min_t(size_t, de.namelen,
-					      (size_t)max_len), nlt,
-					cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+					      (size_t)max_len), nlt, map_type);
 		name.len -= nls_nullsize(nlt);
 	} else {
 		name.name = de.name;
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 52131d8cb4d5..d2979036a4c7 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -23,6 +23,7 @@
 #include "cifsproto.h"
 #include "cifs_debug.h"
 #include "cifspdu.h"
+#include "cifs_unicode.h"
 
 /*
  * An NT cancel request header looks just like the original request except:
@@ -530,13 +531,11 @@ cifs_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = CIFSSMBQPathInfo(xid, tcon, full_path, file_info,
 			      0 /* not legacy */, cifs_sb->local_nls,
-			      cifs_sb->mnt_cifs_flags &
-				CIFS_MOUNT_MAP_SPECIAL_CHR);
+			      cifs_remap(cifs_sb));
 
 	if (rc == -EOPNOTSUPP || rc == -EINVAL)
 		rc = SMBQueryInformation(xid, tcon, full_path, file_info,
-				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-				  CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_sb->local_nls, cifs_remap(cifs_sb));
 	kfree(file_info);
 	return rc;
 }
@@ -552,8 +551,7 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	/* could do find first instead but this returns more info */
 	rc = CIFSSMBQPathInfo(xid, tcon, full_path, data, 0 /* not legacy */,
-			      cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+			      cifs_sb->local_nls, cifs_remap(cifs_sb));
 	/*
 	 * BB optimize code so we do not make the above call when server claims
 	 * no NT SMB support and the above call failed at least once - set flag
@@ -562,8 +560,7 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
 	if ((rc == -EOPNOTSUPP) || (rc == -EINVAL)) {
 		rc = SMBQueryInformation(xid, tcon, full_path, data,
 					 cifs_sb->local_nls,
-					 cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+					 cifs_remap(cifs_sb));
 		*adjustTZ = true;
 	}
 
@@ -611,8 +608,7 @@ cifs_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon,
 	 */
 	return CIFSGetSrvInodeNumber(xid, tcon, full_path, uniqueid,
 				     cifs_sb->local_nls,
-				     cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+				     cifs_remap(cifs_sb));
 }
 
 static int
@@ -703,8 +699,7 @@ cifs_mkdir_setinfo(struct inode *inode, const char *full_path,
 	dosattrs = cifsInode->cifsAttrs|ATTR_READONLY;
 	info.Attributes = cpu_to_le32(dosattrs);
 	rc = CIFSSMBSetPathInfo(xid, tcon, full_path, &info, cifs_sb->local_nls,
-				cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_remap(cifs_sb));
 	if (rc == 0)
 		cifsInode->cifsAttrs = dosattrs;
 }
@@ -720,8 +715,7 @@ cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 				     oparms->create_options,
 				     &oparms->fid->netfid, oplock, buf,
 				     oparms->cifs_sb->local_nls,
-				     oparms->cifs_sb->mnt_cifs_flags
-						& CIFS_MOUNT_MAP_SPECIAL_CHR);
+				     cifs_remap(oparms->cifs_sb));
 	return CIFS_open(xid, oparms, oplock, buf);
 }
 
@@ -749,21 +743,21 @@ cifs_flush_file(const unsigned int xid, struct cifs_tcon *tcon,
 }
 
 static int
-cifs_sync_read(const unsigned int xid, struct cifsFileInfo *cfile,
+cifs_sync_read(const unsigned int xid, struct cifs_fid *pfid,
 	       struct cifs_io_parms *parms, unsigned int *bytes_read,
 	       char **buf, int *buf_type)
 {
-	parms->netfid = cfile->fid.netfid;
+	parms->netfid = pfid->netfid;
 	return CIFSSMBRead(xid, parms, bytes_read, buf, buf_type);
 }
 
 static int
-cifs_sync_write(const unsigned int xid, struct cifsFileInfo *cfile,
+cifs_sync_write(const unsigned int xid, struct cifs_fid *pfid,
 		struct cifs_io_parms *parms, unsigned int *written,
 		struct kvec *iov, unsigned long nr_segs)
 {
 
-	parms->netfid = cfile->fid.netfid;
+	parms->netfid = pfid->netfid;
 	return CIFSSMBWrite2(xid, parms, written, iov, nr_segs);
 }
 
@@ -800,8 +794,7 @@ smb_set_file_info(struct inode *inode, const char *full_path,
 	tcon = tlink_tcon(tlink);
 
 	rc = CIFSSMBSetPathInfo(xid, tcon, full_path, buf, cifs_sb->local_nls,
-					cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_remap(cifs_sb));
 	if (rc == 0) {
 		cinode->cifsAttrs = le32_to_cpu(buf->Attributes);
 		goto out;
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 4aa7a0f07d6e..1a08a34838fc 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -379,6 +379,14 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)
 	int len;
 	const char *start_of_path;
 	__le16 *to;
+	int map_type;
+
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
+		map_type = SFM_MAP_UNI_RSVD;
+	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
+		map_type = SFU_MAP_UNI_RSVD;
+	else
+		map_type = NO_MAP_UNI_RSVD;
 
 	/* Windows doesn't allow paths beginning with \ */
 	if (from[0] == '\\')
@@ -386,9 +394,7 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)
 	else
 		start_of_path = from;
 	to = cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len,
-				   cifs_sb->local_nls,
-				   cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
+				   cifs_sb->local_nls, map_type);
 	return to;
 }
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index f522193b7184..c5f521bcdee2 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -265,15 +265,18 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
 			FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */,
 			NULL /* no data input */, 0 /* no data input */,
 			(char **)&out_buf, &ret_data_len);
-
-	if ((rc == 0)  && (ret_data_len > 0)) {
+	if (rc != 0)
+		cifs_dbg(VFS, "error %d on ioctl to get interface list\n", rc);
+	else if (ret_data_len < sizeof(struct network_interface_info_ioctl_rsp)) {
+		cifs_dbg(VFS, "server returned bad net interface info buf\n");
+		rc = -EINVAL;
+	} else {
 		/* Dump info on first interface */
 		cifs_dbg(FYI, "Adapter Capability 0x%x\t",
 			le32_to_cpu(out_buf->Capability));
 		cifs_dbg(FYI, "Link Speed %lld\n",
 			le64_to_cpu(out_buf->LinkSpeed));
-	} else
-		cifs_dbg(VFS, "error %d on ioctl to get interface list\n", rc);
+	}
 
 	return rc;
 }
@@ -711,23 +714,23 @@ smb2_read_data_length(char *buf)
 
 
 static int
-smb2_sync_read(const unsigned int xid, struct cifsFileInfo *cfile,
+smb2_sync_read(const unsigned int xid, struct cifs_fid *pfid,
 	       struct cifs_io_parms *parms, unsigned int *bytes_read,
 	       char **buf, int *buf_type)
 {
-	parms->persistent_fid = cfile->fid.persistent_fid;
-	parms->volatile_fid = cfile->fid.volatile_fid;
+	parms->persistent_fid = pfid->persistent_fid;
+	parms->volatile_fid = pfid->volatile_fid;
 	return SMB2_read(xid, parms, bytes_read, buf, buf_type);
 }
 
 static int
-smb2_sync_write(const unsigned int xid, struct cifsFileInfo *cfile,
+smb2_sync_write(const unsigned int xid, struct cifs_fid *pfid,
 		struct cifs_io_parms *parms, unsigned int *written,
 		struct kvec *iov, unsigned long nr_segs)
 {
 
-	parms->persistent_fid = cfile->fid.persistent_fid;
-	parms->volatile_fid = cfile->fid.volatile_fid;
+	parms->persistent_fid = pfid->persistent_fid;
+	parms->volatile_fid = pfid->volatile_fid;
 	return SMB2_write(xid, parms, written, iov, nr_segs);
 }
 
@@ -1452,6 +1455,8 @@ struct smb_version_operations smb21_operations = {
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
 	.query_symlink = smb2_query_symlink,
+	.query_mf_symlink = smb3_query_mf_symlink,
+	.create_mf_symlink = smb3_create_mf_symlink,
 	.open = smb2_open_file,
 	.set_fid = smb2_set_fid,
 	.close = smb2_close_file,
@@ -1531,6 +1536,8 @@ struct smb_version_operations smb30_operations = {
 	.rename = smb2_rename_path,
 	.create_hardlink = smb2_create_hardlink,
 	.query_symlink = smb2_query_symlink,
+	.query_mf_symlink = smb3_query_mf_symlink,
+	.create_mf_symlink = smb3_create_mf_symlink,
 	.open = smb2_open_file,
 	.set_fid = smb2_set_fid,
 	.close = smb2_close_file,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 74b3a6684383..8f1672bb82d5 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1098,6 +1098,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 
 	if (oparms->create_options & CREATE_OPTION_READONLY)
 		file_attributes |= ATTR_READONLY;
+	if (oparms->create_options & CREATE_OPTION_SPECIAL)
+		file_attributes |= ATTR_SYSTEM;
 
 	req->ImpersonationLevel = IL_IMPERSONATION;
 	req->DesiredAccess = cpu_to_le32(oparms->desired_access);
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index fbe486c285a9..e3188abdafd0 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -352,6 +352,8 @@ struct smb2_tree_disconnect_rsp {
 #define FILE_ATTRIBUTE_OFFLINE			0x00001000
 #define FILE_ATTRIBUTE_NOT_CONTENT_INDEXED	0x00002000
 #define FILE_ATTRIBUTE_ENCRYPTED		0x00004000
+#define FILE_ATTRIBUTE_INTEGRITY_STREAM		0x00008000
+#define FILE_ATTRIBUTE_NO_SCRUB_DATA		0x00020000
 
 /* Oplock levels */
 #define SMB2_OPLOCK_LEVEL_NONE		0x00
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 67e8ce8055de..79dc650c18b2 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -82,7 +82,13 @@ extern int smb2_rename_path(const unsigned int xid, struct cifs_tcon *tcon,
 extern int smb2_create_hardlink(const unsigned int xid, struct cifs_tcon *tcon,
 				const char *from_name, const char *to_name,
 				struct cifs_sb_info *cifs_sb);
-
+extern int smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
+			struct cifs_sb_info *cifs_sb, const unsigned char *path,
+			char *pbuf, unsigned int *pbytes_written);
+extern int smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
+			  struct cifs_sb_info *cifs_sb,
+			  const unsigned char *path, char *pbuf,
+			  unsigned int *pbytes_read);
 extern int smb2_open_file(const unsigned int xid,
 			  struct cifs_open_parms *oparms,
 			  __u32 *oplock, FILE_ALL_INFO *buf);
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index 43eb1367b103..6c1566366a66 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -29,6 +29,7 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/random.h>
+#include "cifs_fs_sb.h"
 #include "cifs_unicode.h"
 #include "cifspdu.h"
 #include "cifsglob.h"
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 5ac836a86b18..72a4d10653d6 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -28,6 +28,8 @@
 #include "cifsglob.h"
 #include "cifsproto.h"
 #include "cifs_debug.h"
+#include "cifs_fs_sb.h"
+#include "cifs_unicode.h"
 
 #define MAX_EA_VALUE_SIZE 65535
 #define CIFS_XATTR_DOS_ATTRIB "user.DosAttrib"
@@ -85,8 +87,7 @@ int cifs_removexattr(struct dentry *direntry, const char *ea_name)
 		if (pTcon->ses->server->ops->set_EA)
 			rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
 				full_path, ea_name, NULL, (__u16)0,
-				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_sb->local_nls, cifs_remap(cifs_sb));
 	}
 remove_ea_exit:
 	kfree(full_path);
@@ -154,8 +155,7 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
 		if (pTcon->ses->server->ops->set_EA)
 			rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
 				full_path, ea_name, ea_value, (__u16)value_size,
-				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_sb->local_nls, cifs_remap(cifs_sb));
 	} else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN)
 		   == 0) {
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
@@ -165,8 +165,7 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
 		if (pTcon->ses->server->ops->set_EA)
 			rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
 				full_path, ea_name, ea_value, (__u16)value_size,
-				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_sb->local_nls, cifs_remap(cifs_sb));
 	} else if (strncmp(ea_name, CIFS_XATTR_CIFS_ACL,
 			strlen(CIFS_XATTR_CIFS_ACL)) == 0) {
 #ifdef CONFIG_CIFS_ACL
@@ -199,8 +198,7 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
 				rc = CIFSSMBSetPosixACL(xid, pTcon, full_path,
 					ea_value, (const int)value_size,
 					ACL_TYPE_ACCESS, cifs_sb->local_nls,
-					cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+					cifs_remap(cifs_sb));
 			cifs_dbg(FYI, "set POSIX ACL rc %d\n", rc);
 #else
 			cifs_dbg(FYI, "set POSIX ACL not supported\n");
@@ -212,8 +210,7 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
 				rc = CIFSSMBSetPosixACL(xid, pTcon, full_path,
 					ea_value, (const int)value_size,
 					ACL_TYPE_DEFAULT, cifs_sb->local_nls,
-					cifs_sb->mnt_cifs_flags &
-						CIFS_MOUNT_MAP_SPECIAL_CHR);
+					cifs_remap(cifs_sb));
 			cifs_dbg(FYI, "set POSIX default ACL rc %d\n", rc);
 #else
 			cifs_dbg(FYI, "set default POSIX ACL not supported\n");
@@ -285,8 +282,7 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
 		if (pTcon->ses->server->ops->query_all_EAs)
 			rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
 				full_path, ea_name, ea_value, buf_size,
-				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_sb->local_nls, cifs_remap(cifs_sb));
 	} else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) == 0) {
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
 			goto get_ea_exit;
@@ -295,8 +291,7 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
 		if (pTcon->ses->server->ops->query_all_EAs)
 			rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
 				full_path, ea_name, ea_value, buf_size,
-				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_sb->local_nls, cifs_remap(cifs_sb));
 	} else if (strncmp(ea_name, POSIX_ACL_XATTR_ACCESS,
 			  strlen(POSIX_ACL_XATTR_ACCESS)) == 0) {
 #ifdef CONFIG_CIFS_POSIX
@@ -304,8 +299,7 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
 			rc = CIFSSMBGetPosixACL(xid, pTcon, full_path,
 				ea_value, buf_size, ACL_TYPE_ACCESS,
 				cifs_sb->local_nls,
-				cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_remap(cifs_sb));
 #else
 		cifs_dbg(FYI, "Query POSIX ACL not supported yet\n");
 #endif /* CONFIG_CIFS_POSIX */
@@ -316,8 +310,7 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
 			rc = CIFSSMBGetPosixACL(xid, pTcon, full_path,
 				ea_value, buf_size, ACL_TYPE_DEFAULT,
 				cifs_sb->local_nls,
-				cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_remap(cifs_sb));
 #else
 		cifs_dbg(FYI, "Query POSIX default ACL not supported yet\n");
 #endif /* CONFIG_CIFS_POSIX */
@@ -421,8 +414,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
 	if (pTcon->ses->server->ops->query_all_EAs)
 		rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
 				full_path, NULL, data, buf_size,
-				cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
-					CIFS_MOUNT_MAP_SPECIAL_CHR);
+				cifs_sb->local_nls, cifs_remap(cifs_sb));
 list_ea_exit:
 	kfree(full_path);
 	free_xid(xid);
diff --git a/fs/compat.c b/fs/compat.c
index 66d3d3c6b4b2..b13df99f3534 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -794,25 +794,21 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
 	char *kernel_type;
 	unsigned long data_page;
 	char *kernel_dev;
-	struct filename *dir;
 	int retval;
 
-	retval = copy_mount_string(type, &kernel_type);
-	if (retval < 0)
+	kernel_type = copy_mount_string(type);
+	retval = PTR_ERR(kernel_type);
+	if (IS_ERR(kernel_type))
 		goto out;
 
-	dir = getname(dir_name);
-	retval = PTR_ERR(dir);
-	if (IS_ERR(dir))
+	kernel_dev = copy_mount_string(dev_name);
+	retval = PTR_ERR(kernel_dev);
+	if (IS_ERR(kernel_dev))
 		goto out1;
 
-	retval = copy_mount_string(dev_name, &kernel_dev);
-	if (retval < 0)
-		goto out2;
-
 	retval = copy_mount_options(data, &data_page);
 	if (retval < 0)
-		goto out3;
+		goto out2;
 
 	retval = -EINVAL;
 
@@ -821,19 +817,17 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
 			do_ncp_super_data_conv((void *)data_page);
 		} else if (!strcmp(kernel_type, NFS4_NAME)) {
 			if (do_nfs4_super_data_conv((void *) data_page))
-				goto out4;
+				goto out3;
 		}
 	}
 
-	retval = do_mount(kernel_dev, dir->name, kernel_type,
+	retval = do_mount(kernel_dev, dir_name, kernel_type,
 			flags, (void*)data_page);
 
- out4:
-	free_page(data_page);
  out3:
-	kfree(kernel_dev);
+	free_page(data_page);
  out2:
-	putname(dir);
+	kfree(kernel_dev);
  out1:
 	kfree(kernel_type);
  out:
diff --git a/fs/coredump.c b/fs/coredump.c
index a93f7e6ea4cf..b5c86ffd5033 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -199,6 +199,14 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm)
 				err = cn_printf(cn, "%d",
 					      task_tgid_nr(current));
 				break;
+			case 'i':
+				err = cn_printf(cn, "%d",
+					      task_pid_vnr(current));
+				break;
+			case 'I':
+				err = cn_printf(cn, "%d",
+					      task_pid_nr(current));
+				break;
 			/* uid */
 			case 'u':
 				err = cn_printf(cn, "%d", cred->uid);
diff --git a/fs/dcache.c b/fs/dcache.c
index cb25a1a5e307..d5a23fd0da90 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -235,18 +235,49 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
 	return dentry_string_cmp(cs, ct, tcount);
 }
 
+struct external_name {
+	union {
+		atomic_t count;
+		struct rcu_head head;
+	} u;
+	unsigned char name[];
+};
+
+static inline struct external_name *external_name(struct dentry *dentry)
+{
+	return container_of(dentry->d_name.name, struct external_name, name[0]);
+}
+
 static void __d_free(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
 
 	WARN_ON(!hlist_unhashed(&dentry->d_alias));
-	if (dname_external(dentry))
-		kfree(dentry->d_name.name);
 	kmem_cache_free(dentry_cache, dentry); 
 }
 
+static void __d_free_external(struct rcu_head *head)
+{
+	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
+	WARN_ON(!hlist_unhashed(&dentry->d_alias));
+	kfree(external_name(dentry));
+	kmem_cache_free(dentry_cache, dentry); 
+}
+
+static inline int dname_external(const struct dentry *dentry)
+{
+	return dentry->d_name.name != dentry->d_iname;
+}
+
 static void dentry_free(struct dentry *dentry)
 {
+	if (unlikely(dname_external(dentry))) {
+		struct external_name *p = external_name(dentry);
+		if (likely(atomic_dec_and_test(&p->u.count))) {
+			call_rcu(&dentry->d_u.d_rcu, __d_free_external);
+			return;
+		}
+	}
 	/* if dentry was never visible to RCU, immediate free is OK */
 	if (!(dentry->d_flags & DCACHE_RCUACCESS))
 		__d_free(&dentry->d_u.d_rcu);
@@ -456,7 +487,7 @@ static void __dentry_kill(struct dentry *dentry)
 	 * inform the fs via d_prune that this dentry is about to be
 	 * unhashed and destroyed.
 	 */
-	if ((dentry->d_flags & DCACHE_OP_PRUNE) && !d_unhashed(dentry))
+	if (dentry->d_flags & DCACHE_OP_PRUNE)
 		dentry->d_op->d_prune(dentry);
 
 	if (dentry->d_flags & DCACHE_LRU_LIST) {
@@ -619,62 +650,6 @@ kill_it:
 }
 EXPORT_SYMBOL(dput);
 
-/**
- * d_invalidate - invalidate a dentry
- * @dentry: dentry to invalidate
- *
- * Try to invalidate the dentry if it turns out to be
- * possible. If there are other dentries that can be
- * reached through this one we can't delete it and we
- * return -EBUSY. On success we return 0.
- *
- * no dcache lock.
- */
- 
-int d_invalidate(struct dentry * dentry)
-{
-	/*
-	 * If it's already been dropped, return OK.
-	 */
-	spin_lock(&dentry->d_lock);
-	if (d_unhashed(dentry)) {
-		spin_unlock(&dentry->d_lock);
-		return 0;
-	}
-	/*
-	 * Check whether to do a partial shrink_dcache
-	 * to get rid of unused child entries.
-	 */
-	if (!list_empty(&dentry->d_subdirs)) {
-		spin_unlock(&dentry->d_lock);
-		shrink_dcache_parent(dentry);
-		spin_lock(&dentry->d_lock);
-	}
-
-	/*
-	 * Somebody else still using it?
-	 *
-	 * If it's a directory, we can't drop it
-	 * for fear of somebody re-populating it
-	 * with children (even though dropping it
-	 * would make it unreachable from the root,
-	 * we might still populate it if it was a
-	 * working directory or similar).
-	 * We also need to leave mountpoints alone,
-	 * directory or not.
-	 */
-	if (dentry->d_lockref.count > 1 && dentry->d_inode) {
-		if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) {
-			spin_unlock(&dentry->d_lock);
-			return -EBUSY;
-		}
-	}
-
-	__d_drop(dentry);
-	spin_unlock(&dentry->d_lock);
-	return 0;
-}
-EXPORT_SYMBOL(d_invalidate);
 
 /* This must be called with d_lock held */
 static inline void __dget_dlock(struct dentry *dentry)
@@ -735,7 +710,8 @@ EXPORT_SYMBOL(dget_parent);
  * acquire the reference to alias and return it. Otherwise return NULL.
  * Notice that if inode is a directory there can be only one alias and
  * it can be unhashed only if it has no children, or if it is the root
- * of a filesystem.
+ * of a filesystem, or if the directory was renamed and d_revalidate
+ * was the first vfs operation to notice.
  *
  * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
  * any other hashed alias over that one.
@@ -799,20 +775,13 @@ restart:
 	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (!dentry->d_lockref.count) {
-			/*
-			 * inform the fs via d_prune that this dentry
-			 * is about to be unhashed and destroyed.
-			 */
-			if ((dentry->d_flags & DCACHE_OP_PRUNE) &&
-			    !d_unhashed(dentry))
-				dentry->d_op->d_prune(dentry);
-
-			__dget_dlock(dentry);
-			__d_drop(dentry);
-			spin_unlock(&dentry->d_lock);
-			spin_unlock(&inode->i_lock);
-			dput(dentry);
-			goto restart;
+			struct dentry *parent = lock_parent(dentry);
+			if (likely(!dentry->d_lockref.count)) {
+				__dentry_kill(dentry);
+				goto restart;
+			}
+			if (parent)
+				spin_unlock(&parent->d_lock);
 		}
 		spin_unlock(&dentry->d_lock);
 	}
@@ -1193,7 +1162,7 @@ EXPORT_SYMBOL(have_submounts);
  * reachable (e.g. NFS can unhash a directory dentry and then the complete
  * subtree can become unreachable).
  *
- * Only one of check_submounts_and_drop() and d_set_mounted() must succeed.  For
+ * Only one of d_invalidate() and d_set_mounted() must succeed.  For
  * this reason take rename_lock and d_lock on dentry and ancestors.
  */
 int d_set_mounted(struct dentry *dentry)
@@ -1202,7 +1171,7 @@ int d_set_mounted(struct dentry *dentry)
 	int ret = -ENOENT;
 	write_seqlock(&rename_lock);
 	for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) {
-		/* Need exclusion wrt. check_submounts_and_drop() */
+		/* Need exclusion wrt. d_invalidate() */
 		spin_lock(&p->d_lock);
 		if (unlikely(d_unhashed(p))) {
 			spin_unlock(&p->d_lock);
@@ -1346,70 +1315,84 @@ void shrink_dcache_for_umount(struct super_block *sb)
 	}
 }
 
-static enum d_walk_ret check_and_collect(void *_data, struct dentry *dentry)
+struct detach_data {
+	struct select_data select;
+	struct dentry *mountpoint;
+};
+static enum d_walk_ret detach_and_collect(void *_data, struct dentry *dentry)
 {
-	struct select_data *data = _data;
+	struct detach_data *data = _data;
 
 	if (d_mountpoint(dentry)) {
-		data->found = -EBUSY;
+		__dget_dlock(dentry);
+		data->mountpoint = dentry;
 		return D_WALK_QUIT;
 	}
 
-	return select_collect(_data, dentry);
+	return select_collect(&data->select, dentry);
 }
 
 static void check_and_drop(void *_data)
 {
-	struct select_data *data = _data;
+	struct detach_data *data = _data;
 
-	if (d_mountpoint(data->start))
-		data->found = -EBUSY;
-	if (!data->found)
-		__d_drop(data->start);
+	if (!data->mountpoint && !data->select.found)
+		__d_drop(data->select.start);
 }
 
 /**
- * check_submounts_and_drop - prune dcache, check for submounts and drop
+ * d_invalidate - detach submounts, prune dcache, and drop
+ * @dentry: dentry to invalidate (aka detach, prune and drop)
  *
- * All done as a single atomic operation relative to has_unlinked_ancestor().
- * Returns 0 if successfully unhashed @parent.  If there were submounts then
- * return -EBUSY.
+ * no dcache lock.
  *
- * @dentry: dentry to prune and drop
+ * The final d_drop is done as an atomic operation relative to
+ * rename_lock ensuring there are no races with d_set_mounted.  This
+ * ensures there are no unhashed dentries on the path to a mountpoint.
  */
-int check_submounts_and_drop(struct dentry *dentry)
+void d_invalidate(struct dentry *dentry)
 {
-	int ret = 0;
+	/*
+	 * If it's already been dropped, return OK.
+	 */
+	spin_lock(&dentry->d_lock);
+	if (d_unhashed(dentry)) {
+		spin_unlock(&dentry->d_lock);
+		return;
+	}
+	spin_unlock(&dentry->d_lock);
 
 	/* Negative dentries can be dropped without further checks */
 	if (!dentry->d_inode) {
 		d_drop(dentry);
-		goto out;
+		return;
 	}
 
 	for (;;) {
-		struct select_data data;
+		struct detach_data data;
 
-		INIT_LIST_HEAD(&data.dispose);
-		data.start = dentry;
-		data.found = 0;
+		data.mountpoint = NULL;
+		INIT_LIST_HEAD(&data.select.dispose);
+		data.select.start = dentry;
+		data.select.found = 0;
+
+		d_walk(dentry, &data, detach_and_collect, check_and_drop);
 
-		d_walk(dentry, &data, check_and_collect, check_and_drop);
-		ret = data.found;
+		if (data.select.found)
+			shrink_dentry_list(&data.select.dispose);
 
-		if (!list_empty(&data.dispose))
-			shrink_dentry_list(&data.dispose);
+		if (data.mountpoint) {
+			detach_mounts(data.mountpoint);
+			dput(data.mountpoint);
+		}
 
-		if (ret <= 0)
+		if (!data.mountpoint && !data.select.found)
 			break;
 
 		cond_resched();
 	}
-
-out:
-	return ret;
 }
-EXPORT_SYMBOL(check_submounts_and_drop);
+EXPORT_SYMBOL(d_invalidate);
 
 /**
  * __d_alloc	-	allocate a dcache entry
@@ -1438,11 +1421,14 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	 */
 	dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
 	if (name->len > DNAME_INLINE_LEN-1) {
-		dname = kmalloc(name->len + 1, GFP_KERNEL);
-		if (!dname) {
+		size_t size = offsetof(struct external_name, name[1]);
+		struct external_name *p = kmalloc(size + name->len, GFP_KERNEL);
+		if (!p) {
 			kmem_cache_free(dentry_cache, dentry); 
 			return NULL;
 		}
+		atomic_set(&p->u.count, 1);
+		dname = p->name;
 	} else  {
 		dname = dentry->d_iname;
 	}	
@@ -2112,10 +2098,10 @@ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name)
 	struct dentry *dentry;
 	unsigned seq;
 
-        do {
-                seq = read_seqbegin(&rename_lock);
-                dentry = __d_lookup(parent, name);
-                if (dentry)
+	do {
+		seq = read_seqbegin(&rename_lock);
+		dentry = __d_lookup(parent, name);
+		if (dentry)
 			break;
 	} while (read_seqretry(&rename_lock, seq));
 	return dentry;
@@ -2372,11 +2358,10 @@ void dentry_update_name_case(struct dentry *dentry, struct qstr *name)
 }
 EXPORT_SYMBOL(dentry_update_name_case);
 
-static void switch_names(struct dentry *dentry, struct dentry *target,
-			 bool exchange)
+static void swap_names(struct dentry *dentry, struct dentry *target)
 {
-	if (dname_external(target)) {
-		if (dname_external(dentry)) {
+	if (unlikely(dname_external(target))) {
+		if (unlikely(dname_external(dentry))) {
 			/*
 			 * Both external: swap the pointers
 			 */
@@ -2392,7 +2377,7 @@ static void switch_names(struct dentry *dentry, struct dentry *target,
 			target->d_name.name = target->d_iname;
 		}
 	} else {
-		if (dname_external(dentry)) {
+		if (unlikely(dname_external(dentry))) {
 			/*
 			 * dentry:external, target:internal.  Give dentry's
 			 * storage to target and make dentry internal
@@ -2407,12 +2392,6 @@ static void switch_names(struct dentry *dentry, struct dentry *target,
 			 */
 			unsigned int i;
 			BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
-			if (!exchange) {
-				memcpy(dentry->d_iname, target->d_name.name,
-						target->d_name.len + 1);
-				dentry->d_name.hash_len = target->d_name.hash_len;
-				return;
-			}
 			for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
 				swap(((long *) &dentry->d_iname)[i],
 				     ((long *) &target->d_iname)[i]);
@@ -2422,6 +2401,24 @@ static void switch_names(struct dentry *dentry, struct dentry *target,
 	swap(dentry->d_name.hash_len, target->d_name.hash_len);
 }
 
+static void copy_name(struct dentry *dentry, struct dentry *target)
+{
+	struct external_name *old_name = NULL;
+	if (unlikely(dname_external(dentry)))
+		old_name = external_name(dentry);
+	if (unlikely(dname_external(target))) {
+		atomic_inc(&external_name(target)->u.count);
+		dentry->d_name = target->d_name;
+	} else {
+		memcpy(dentry->d_iname, target->d_name.name,
+				target->d_name.len + 1);
+		dentry->d_name.name = dentry->d_iname;
+		dentry->d_name.hash_len = target->d_name.hash_len;
+	}
+	if (old_name && likely(atomic_dec_and_test(&old_name->u.count)))
+		kfree_rcu(old_name, u.head);
+}
+
 static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target)
 {
 	/*
@@ -2518,7 +2515,10 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	}
 
 	/* Switch the names.. */
-	switch_names(dentry, target, exchange);
+	if (exchange)
+		swap_names(dentry, target);
+	else
+		copy_name(dentry, target);
 
 	/* ... and switch them in the tree */
 	if (IS_ROOT(dentry)) {
@@ -2625,10 +2625,8 @@ static struct dentry *__d_unalias(struct inode *inode,
 		goto out_err;
 	m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
-	if (likely(!d_mountpoint(alias))) {
-		__d_move(alias, dentry, false);
-		ret = alias;
-	}
+	__d_move(alias, dentry, false);
+	ret = alias;
 out_err:
 	spin_unlock(&inode->i_lock);
 	if (m2)
@@ -2810,6 +2808,9 @@ static int prepend(char **buffer, int *buflen, const char *str, int namelen)
  * the beginning of the name. The sequence number check at the caller will
  * retry it again when a d_move() does happen. So any garbage in the buffer
  * due to mismatched pointer and length will be discarded.
+ *
+ * Data dependency barrier is needed to make sure that we see that terminating
+ * NUL.  Alpha strikes again, film at 11...
  */
 static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 {
@@ -2817,6 +2818,8 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 	u32 dlen = ACCESS_ONCE(name->len);
 	char *p;
 
+	smp_read_barrier_depends();
+
 	*buflen -= dlen + 1;
 	if (*buflen < 0)
 		return -ENAMETOOLONG;
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index f704458ea5f5..e0ab3a93eeff 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -30,7 +30,7 @@ struct plock_op {
 
 struct plock_xop {
 	struct plock_op xop;
-	void *callback;
+	int (*callback)(struct file_lock *fl, int result);
 	void *fl;
 	void *file;
 	struct file_lock flc;
@@ -190,7 +190,7 @@ static int dlm_plock_callback(struct plock_op *op)
 	struct file *file;
 	struct file_lock *fl;
 	struct file_lock *flc;
-	int (*notify)(void *, void *, int) = NULL;
+	int (*notify)(struct file_lock *fl, int result) = NULL;
 	struct plock_xop *xop = (struct plock_xop *)op;
 	int rv = 0;
 
@@ -209,7 +209,7 @@ static int dlm_plock_callback(struct plock_op *op)
 	notify = xop->callback;
 
 	if (op->info.rv) {
-		notify(fl, NULL, op->info.rv);
+		notify(fl, op->info.rv);
 		goto out;
 	}
 
@@ -228,7 +228,7 @@ static int dlm_plock_callback(struct plock_op *op)
 			  (unsigned long long)op->info.number, file, fl);
 	}
 
-	rv = notify(fl, NULL, 0);
+	rv = notify(fl, 0);
 	if (rv) {
 		/* XXX: We need to cancel the fs lock here: */
 		log_print("dlm_plock_callback: lock granted after lock request "
diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c
index 9d61947d473a..f3f5e72a29ba 100644
--- a/fs/dlm/rcom.c
+++ b/fs/dlm/rcom.c
@@ -206,7 +206,7 @@ static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in)
 
 	rs = (struct rcom_status *)rc_in->rc_buf;
 
-	if (!(rs->rs_flags & DLM_RSF_NEED_SLOTS)) {
+	if (!(le32_to_cpu(rs->rs_flags) & DLM_RSF_NEED_SLOTS)) {
 		status = dlm_recover_status(ls);
 		goto do_create;
 	}
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index db0fad3269c0..f5bce9096555 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -229,8 +229,8 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to initialize "
 			"the lower file for the dentry with name "
-			"[%s]; rc = [%d]\n", __func__,
-			ecryptfs_dentry->d_name.name, rc);
+			"[%pd]; rc = [%d]\n", __func__,
+			ecryptfs_dentry, rc);
 		goto out_free;
 	}
 	if ((ecryptfs_inode_to_private(inode)->lower_file->f_flags & O_ACCMODE)
@@ -327,7 +327,7 @@ ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct file *lower_file = ecryptfs_file_to_lower(file);
 	long rc = -ENOIOCTLCMD;
 
-	if (lower_file->f_op && lower_file->f_op->compat_ioctl)
+	if (lower_file->f_op->compat_ioctl)
 		rc = lower_file->f_op->compat_ioctl(lower_file, cmd, arg);
 	return rc;
 }
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index d4a9431ec73c..1686dc2da9fd 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -53,9 +53,7 @@ static void unlock_dir(struct dentry *dir)
 
 static int ecryptfs_inode_test(struct inode *inode, void *lower_inode)
 {
-	if (ecryptfs_inode_to_lower(inode) == (struct inode *)lower_inode)
-		return 1;
-	return 0;
+	return ecryptfs_inode_to_lower(inode) == lower_inode;
 }
 
 static int ecryptfs_inode_set(struct inode *inode, void *opaque)
@@ -192,12 +190,6 @@ ecryptfs_do_create(struct inode *directory_inode,
 
 	lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
-	if (IS_ERR(lower_dir_dentry)) {
-		ecryptfs_printk(KERN_ERR, "Error locking directory of "
-				"dentry\n");
-		inode = ERR_CAST(lower_dir_dentry);
-		goto out;
-	}
 	rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, true);
 	if (rc) {
 		printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
@@ -215,7 +207,6 @@ ecryptfs_do_create(struct inode *directory_inode,
 	fsstack_copy_inode_size(directory_inode, lower_dir_dentry->d_inode);
 out_lock:
 	unlock_dir(lower_dir_dentry);
-out:
 	return inode;
 }
 
@@ -250,8 +241,8 @@ int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry,
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to initialize "
 			"the lower file for the dentry with name "
-			"[%s]; rc = [%d]\n", __func__,
-			ecryptfs_dentry->d_name.name, rc);
+			"[%pd]; rc = [%d]\n", __func__,
+			ecryptfs_dentry, rc);
 		goto out;
 	}
 	rc = ecryptfs_write_metadata(ecryptfs_dentry, ecryptfs_inode);
@@ -313,8 +304,8 @@ static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode)
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to initialize "
 			"the lower file for the dentry with name "
-			"[%s]; rc = [%d]\n", __func__,
-			dentry->d_name.name, rc);
+			"[%pd]; rc = [%d]\n", __func__,
+			dentry, rc);
 		return rc;
 	}
 
@@ -418,8 +409,8 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 	if (IS_ERR(lower_dentry)) {
 		rc = PTR_ERR(lower_dentry);
 		ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
-				"[%d] on lower_dentry = [%s]\n", __func__, rc,
-				ecryptfs_dentry->d_name.name);
+				"[%d] on lower_dentry = [%pd]\n", __func__, rc,
+				ecryptfs_dentry);
 		goto out;
 	}
 	if (lower_dentry->d_inode)
@@ -1039,7 +1030,7 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 	}
 
 	rc = vfs_setxattr(lower_dentry, name, value, size, flags);
-	if (!rc)
+	if (!rc && dentry->d_inode)
 		fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode);
 out:
 	return rc;
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 4725a07f003c..635e8e16a5b7 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -26,7 +26,6 @@
  */
 
 #include <linux/string.h>
-#include <linux/syscalls.h>
 #include <linux/pagemap.h>
 #include <linux/key.h>
 #include <linux/random.h>
@@ -1846,7 +1845,6 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat,
 					"(Tag 11 not allowed by itself)\n");
 			rc = -EIO;
 			goto out_wipe_list;
-			break;
 		default:
 			ecryptfs_printk(KERN_DEBUG, "No packet at offset [%zd] "
 					"of the file header; hex value of "
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index e57380e5f6bd..286f10b0363b 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -434,8 +434,7 @@ void ecryptfs_release_messaging(void)
 		mutex_lock(&ecryptfs_msg_ctx_lists_mux);
 		for (i = 0; i < ecryptfs_message_buf_len; i++) {
 			mutex_lock(&ecryptfs_msg_ctx_arr[i].mux);
-			if (ecryptfs_msg_ctx_arr[i].msg)
-				kfree(ecryptfs_msg_ctx_arr[i].msg);
+			kfree(ecryptfs_msg_ctx_arr[i].msg);
 			mutex_unlock(&ecryptfs_msg_ctx_arr[i].mux);
 		}
 		kfree(ecryptfs_msg_ctx_arr);
diff --git a/fs/exec.c b/fs/exec.c
index a2b42a98c743..7302b75a9820 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1372,18 +1372,23 @@ int search_binary_handler(struct linux_binprm *bprm)
 		read_unlock(&binfmt_lock);
 		bprm->recursion_depth++;
 		retval = fmt->load_binary(bprm);
+		read_lock(&binfmt_lock);
+		put_binfmt(fmt);
 		bprm->recursion_depth--;
-		if (retval >= 0 || retval != -ENOEXEC ||
-		    bprm->mm == NULL || bprm->file == NULL) {
-			put_binfmt(fmt);
+		if (retval < 0 && !bprm->mm) {
+			/* we got to flush_old_exec() and failed after it */
+			read_unlock(&binfmt_lock);
+			force_sigsegv(SIGSEGV, current);
+			return retval;
+		}
+		if (retval != -ENOEXEC || !bprm->file) {
+			read_unlock(&binfmt_lock);
 			return retval;
 		}
-		read_lock(&binfmt_lock);
-		put_binfmt(fmt);
 	}
 	read_unlock(&binfmt_lock);
 
-	if (need_retry && retval == -ENOEXEC) {
+	if (need_retry) {
 		if (printable(bprm->buf[0]) && printable(bprm->buf[1]) &&
 		    printable(bprm->buf[2]) && printable(bprm->buf[3]))
 			return retval;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index b88edc05c230..170dc41e8bf4 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1067,14 +1067,14 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	ext2_rsv_window_add(sb, &sbi->s_rsv_window_head);
 
 	err = percpu_counter_init(&sbi->s_freeblocks_counter,
-				ext2_count_free_blocks(sb));
+				ext2_count_free_blocks(sb), GFP_KERNEL);
 	if (!err) {
 		err = percpu_counter_init(&sbi->s_freeinodes_counter,
-				ext2_count_free_inodes(sb));
+				ext2_count_free_inodes(sb), GFP_KERNEL);
 	}
 	if (!err) {
 		err = percpu_counter_init(&sbi->s_dirs_counter,
-				ext2_count_dirs(sb));
+				ext2_count_dirs(sb), GFP_KERNEL);
 	}
 	if (err) {
 		ext2_msg(sb, KERN_ERR, "error: insufficient memory");
diff --git a/fs/ext3/ext3.h b/fs/ext3/ext3.h
index e85ff15a060e..fc3cdcf24aed 100644
--- a/fs/ext3/ext3.h
+++ b/fs/ext3/ext3.h
@@ -237,6 +237,8 @@ struct ext3_new_group_data {
 #define EXT3_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
 #define EXT3_IOC32_SETVERSION_OLD	FS_IOC32_SETVERSION
 
+/* Number of supported quota types */
+#define EXT3_MAXQUOTAS 2
 
 /*
  *  Mount options
@@ -248,7 +250,7 @@ struct ext3_mount_options {
 	unsigned long s_commit_interval;
 #ifdef CONFIG_QUOTA
 	int s_jquota_fmt;
-	char *s_qf_names[MAXQUOTAS];
+	char *s_qf_names[EXT3_MAXQUOTAS];
 #endif
 };
 
@@ -669,7 +671,7 @@ struct ext3_sb_info {
 	unsigned long s_commit_interval;
 	struct block_device *journal_bdev;
 #ifdef CONFIG_QUOTA
-	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
+	char *s_qf_names[EXT3_MAXQUOTAS];	/* Names of quota files with journalled quota */
 	int s_jquota_fmt;			/* Format of quota to use */
 #endif
 };
@@ -1183,9 +1185,9 @@ extern const struct inode_operations ext3_fast_symlink_inode_operations;
 #define EXT3_QUOTA_INIT_BLOCKS(sb) 0
 #define EXT3_QUOTA_DEL_BLOCKS(sb) 0
 #endif
-#define EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_TRANS_BLOCKS(sb))
-#define EXT3_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_INIT_BLOCKS(sb))
-#define EXT3_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_DEL_BLOCKS(sb))
+#define EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT3_MAXQUOTAS*EXT3_QUOTA_TRANS_BLOCKS(sb))
+#define EXT3_MAXQUOTAS_INIT_BLOCKS(sb) (EXT3_MAXQUOTAS*EXT3_QUOTA_INIT_BLOCKS(sb))
+#define EXT3_MAXQUOTAS_DEL_BLOCKS(sb) (EXT3_MAXQUOTAS*EXT3_QUOTA_DEL_BLOCKS(sb))
 
 int
 ext3_mark_iloc_dirty(handle_t *handle,
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 622e88249024..7015db0bafd1 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -441,7 +441,7 @@ static void ext3_put_super (struct super_block * sb)
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	brelse(sbi->s_sbh);
 #ifdef CONFIG_QUOTA
-	for (i = 0; i < MAXQUOTAS; i++)
+	for (i = 0; i < EXT3_MAXQUOTAS; i++)
 		kfree(sbi->s_qf_names[i]);
 #endif
 
@@ -1555,7 +1555,7 @@ static void ext3_orphan_cleanup (struct super_block * sb,
 	/* Needed for iput() to work correctly and not trash data */
 	sb->s_flags |= MS_ACTIVE;
 	/* Turn on quotas so that they are updated correctly */
-	for (i = 0; i < MAXQUOTAS; i++) {
+	for (i = 0; i < EXT3_MAXQUOTAS; i++) {
 		if (EXT3_SB(sb)->s_qf_names[i]) {
 			int ret = ext3_quota_on_mount(sb, i);
 			if (ret < 0)
@@ -1606,7 +1606,7 @@ static void ext3_orphan_cleanup (struct super_block * sb,
 		       PLURAL(nr_truncates));
 #ifdef CONFIG_QUOTA
 	/* Turn quotas off */
-	for (i = 0; i < MAXQUOTAS; i++) {
+	for (i = 0; i < EXT3_MAXQUOTAS; i++) {
 		if (sb_dqopt(sb)->files[i])
 			dquot_quota_off(sb, i);
 	}
@@ -2039,14 +2039,14 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
 		goto failed_mount2;
 	}
 	err = percpu_counter_init(&sbi->s_freeblocks_counter,
-			ext3_count_free_blocks(sb));
+			ext3_count_free_blocks(sb), GFP_KERNEL);
 	if (!err) {
 		err = percpu_counter_init(&sbi->s_freeinodes_counter,
-				ext3_count_free_inodes(sb));
+				ext3_count_free_inodes(sb), GFP_KERNEL);
 	}
 	if (!err) {
 		err = percpu_counter_init(&sbi->s_dirs_counter,
-				ext3_count_dirs(sb));
+				ext3_count_dirs(sb), GFP_KERNEL);
 	}
 	if (err) {
 		ext3_msg(sb, KERN_ERR, "error: insufficient memory");
@@ -2139,7 +2139,7 @@ failed_mount2:
 	kfree(sbi->s_group_desc);
 failed_mount:
 #ifdef CONFIG_QUOTA
-	for (i = 0; i < MAXQUOTAS; i++)
+	for (i = 0; i < EXT3_MAXQUOTAS; i++)
 		kfree(sbi->s_qf_names[i]);
 #endif
 	ext3_blkdev_remove(sbi);
@@ -2659,7 +2659,7 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
 	old_opts.s_commit_interval = sbi->s_commit_interval;
 #ifdef CONFIG_QUOTA
 	old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
-	for (i = 0; i < MAXQUOTAS; i++)
+	for (i = 0; i < EXT3_MAXQUOTAS; i++)
 		if (sbi->s_qf_names[i]) {
 			old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i],
 							 GFP_KERNEL);
@@ -2763,7 +2763,7 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
 	}
 #ifdef CONFIG_QUOTA
 	/* Release old quota file names */
-	for (i = 0; i < MAXQUOTAS; i++)
+	for (i = 0; i < EXT3_MAXQUOTAS; i++)
 		kfree(old_opts.s_qf_names[i]);
 #endif
 	if (enable_quota)
@@ -2777,7 +2777,7 @@ restore_opts:
 	sbi->s_commit_interval = old_opts.s_commit_interval;
 #ifdef CONFIG_QUOTA
 	sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
-	for (i = 0; i < MAXQUOTAS; i++) {
+	for (i = 0; i < EXT3_MAXQUOTAS; i++) {
 		kfree(sbi->s_qf_names[i]);
 		sbi->s_qf_names[i] = old_opts.s_qf_names[i];
 	}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 8b0f9ef517d6..748c9136a60a 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4134,7 +4134,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	 * per cpu locality group is to reduce the contention between block
 	 * request from multiple CPUs.
 	 */
-	ac->ac_lg = __this_cpu_ptr(sbi->s_locality_groups);
+	ac->ac_lg = raw_cpu_ptr(sbi->s_locality_groups);
 
 	/* we're going to use group allocation */
 	ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0b28b36e7915..05c159218bc2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3892,7 +3892,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	/* Register extent status tree shrinker */
 	ext4_es_register_shrinker(sbi);
 
-	if ((err = percpu_counter_init(&sbi->s_extent_cache_cnt, 0)) != 0) {
+	err = percpu_counter_init(&sbi->s_extent_cache_cnt, 0, GFP_KERNEL);
+	if (err) {
 		ext4_msg(sb, KERN_ERR, "insufficient memory");
 		goto failed_mount3;
 	}
@@ -4106,17 +4107,20 @@ no_journal:
 	block = ext4_count_free_clusters(sb);
 	ext4_free_blocks_count_set(sbi->s_es, 
 				   EXT4_C2B(sbi, block));
-	err = percpu_counter_init(&sbi->s_freeclusters_counter, block);
+	err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
+				  GFP_KERNEL);
 	if (!err) {
 		unsigned long freei = ext4_count_free_inodes(sb);
 		sbi->s_es->s_free_inodes_count = cpu_to_le32(freei);
-		err = percpu_counter_init(&sbi->s_freeinodes_counter, freei);
+		err = percpu_counter_init(&sbi->s_freeinodes_counter, freei,
+					  GFP_KERNEL);
 	}
 	if (!err)
 		err = percpu_counter_init(&sbi->s_dirs_counter,
-					  ext4_count_dirs(sb));
+					  ext4_count_dirs(sb), GFP_KERNEL);
 	if (!err)
-		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
+		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
+					  GFP_KERNEL);
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "insufficient memory");
 		goto failed_mount6;
diff --git a/fs/fat/misc.c b/fs/fat/misc.c
index 628e22a5a543..d8da2d2e30ae 100644
--- a/fs/fat/misc.c
+++ b/fs/fat/misc.c
@@ -164,8 +164,6 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster)
 	return 0;
 }
 
-extern struct timezone sys_tz;
-
 /*
  * The epoch of FAT timestamp is 1980.
  *     :  bits :     value
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 22d1c3df61ac..99d440a4a6ba 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -98,26 +98,19 @@ static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
 	write_unlock_irq(&filp->f_owner.lock);
 }
 
-int __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
+void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
 		int force)
 {
-	int err;
-
-	err = security_file_set_fowner(filp);
-	if (err)
-		return err;
-
+	security_file_set_fowner(filp);
 	f_modown(filp, pid, type, force);
-	return 0;
 }
 EXPORT_SYMBOL(__f_setown);
 
-int f_setown(struct file *filp, unsigned long arg, int force)
+void f_setown(struct file *filp, unsigned long arg, int force)
 {
 	enum pid_type type;
 	struct pid *pid;
 	int who = arg;
-	int result;
 	type = PIDTYPE_PID;
 	if (who < 0) {
 		type = PIDTYPE_PGID;
@@ -125,9 +118,8 @@ int f_setown(struct file *filp, unsigned long arg, int force)
 	}
 	rcu_read_lock();
 	pid = find_vpid(who);
-	result = __f_setown(filp, pid, type, force);
+	__f_setown(filp, pid, type, force);
 	rcu_read_unlock();
-	return result;
 }
 EXPORT_SYMBOL(f_setown);
 
@@ -181,7 +173,7 @@ static int f_setown_ex(struct file *filp, unsigned long arg)
 	if (owner.pid && !pid)
 		ret = -ESRCH;
 	else
-		ret = __f_setown(filp, pid, type, 1);
+		 __f_setown(filp, pid, type, 1);
 	rcu_read_unlock();
 
 	return ret;
@@ -302,7 +294,8 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		force_successful_syscall_return();
 		break;
 	case F_SETOWN:
-		err = f_setown(filp, arg, 1);
+		f_setown(filp, arg, 1);
+		err = 0;
 		break;
 	case F_GETOWN_EX:
 		err = f_getown_ex(filp, arg);
diff --git a/fs/file.c b/fs/file.c
index 66923fe3176e..ab3eb6a88239 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -367,7 +367,7 @@ static struct fdtable *close_files(struct files_struct * files)
 				struct file * file = xchg(&fdt->fd[i], NULL);
 				if (file) {
 					filp_close(file, files);
-					cond_resched();
+					cond_resched_rcu_qs();
 				}
 			}
 			i++;
@@ -750,6 +750,7 @@ bool get_close_on_exec(unsigned int fd)
 
 static int do_dup2(struct files_struct *files,
 	struct file *file, unsigned fd, unsigned flags)
+__releases(&files->file_lock)
 {
 	struct file *tofree;
 	struct fdtable *fdt;
diff --git a/fs/file_table.c b/fs/file_table.c
index 385bfd31512a..3f85411b03ce 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -150,18 +150,10 @@ over:
 
 /**
  * alloc_file - allocate and initialize a 'struct file'
- * @mnt: the vfsmount on which the file will reside
- * @dentry: the dentry representing the new file
+ *
+ * @path: the (dentry, vfsmount) pair for the new file
  * @mode: the mode with which the new file will be opened
  * @fop: the 'struct file_operations' for the new file
- *
- * Use this instead of get_empty_filp() to get a new
- * 'struct file'.  Do so because of the same initialization
- * pitfalls reasons listed for init_file().  This is a
- * preferred interface to using init_file().
- *
- * If all the callers of init_file() are eliminated, its
- * code should be moved into this function.
  */
 struct file *alloc_file(struct path *path, fmode_t mode,
 		const struct file_operations *fop)
@@ -331,5 +323,5 @@ void __init files_init(unsigned long mempages)
 
 	n = (mempages * (PAGE_SIZE / 1024)) / 10;
 	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
-	percpu_counter_init(&nr_files, 0);
+	percpu_counter_init(&nr_files, 0, GFP_KERNEL);
 } 
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index b8179ca6bf9d..51dde817e1f2 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -380,26 +380,14 @@ no_config:
 static int fscache_objlist_open(struct inode *inode, struct file *file)
 {
 	struct fscache_objlist_data *data;
-	struct seq_file *m;
-	int ret;
 
-	ret = seq_open(file, &fscache_objlist_ops);
-	if (ret < 0)
-		return ret;
-
-	m = file->private_data;
-
-	/* buffer for key extraction */
-	data = kmalloc(sizeof(struct fscache_objlist_data), GFP_KERNEL);
-	if (!data) {
-		seq_release(inode, file);
+	data = __seq_open_private(file, &fscache_objlist_ops, sizeof(*data));
+	if (!data)
 		return -ENOMEM;
-	}
 
 	/* get the configuration key */
 	fscache_objlist_config(data);
 
-	m->private = data;
 	return 0;
 }
 
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index de1d84af9f7c..dbab798f5caf 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -274,9 +274,6 @@ out:
 
 invalid:
 	ret = 0;
-
-	if (!(flags & LOOKUP_RCU) && check_submounts_and_drop(entry) != 0)
-		ret = 1;
 	goto out;
 }
 
@@ -1289,9 +1286,7 @@ static int fuse_direntplus_link(struct file *file,
 			d_drop(dentry);
 		} else if (get_node_id(inode) != o->nodeid ||
 			   ((o->attr.mode ^ inode->i_mode) & S_IFMT)) {
-			err = d_invalidate(dentry);
-			if (err)
-				goto out;
+			d_invalidate(dentry);
 		} else if (is_bad_inode(inode)) {
 			err = -EIO;
 			goto out;
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index d3a5d4e29ba5..589f4ea9381c 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -93,9 +93,6 @@ invalid_gunlock:
 	if (!had_lock)
 		gfs2_glock_dq_uninit(&d_gh);
 invalid:
-	if (check_submounts_and_drop(dentry) != 0)
-		goto valid;
-
 	dput(parent);
 	return 0;
 
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 1a349f9a9685..5d4261ff5d23 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -2100,8 +2100,13 @@ int gfs2_diradd_alloc_required(struct inode *inode, const struct qstr *name,
 	}
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
-	da->bh = bh;
-	da->dent = dent;
+
+	if (da->save_loc) {
+		da->bh = bh;
+		da->dent = dent;
+	} else {
+		brelse(bh);
+	}
 	return 0;
 }
 
diff --git a/fs/gfs2/dir.h b/fs/gfs2/dir.h
index 126c65dda028..e1b309c24dab 100644
--- a/fs/gfs2/dir.h
+++ b/fs/gfs2/dir.h
@@ -23,6 +23,7 @@ struct gfs2_diradd {
 	unsigned nr_blocks;
 	struct gfs2_dirent *dent;
 	struct buffer_head *bh;
+	int save_loc;
 };
 
 extern struct inode *gfs2_dir_search(struct inode *dir,
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 7f4ed3daa38c..80dd44dca028 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -914,26 +914,6 @@ out_uninit:
 #ifdef CONFIG_GFS2_FS_LOCKING_DLM
 
 /**
- * gfs2_setlease - acquire/release a file lease
- * @file: the file pointer
- * @arg: lease type
- * @fl: file lock
- *
- * We don't currently have a way to enforce a lease across the whole
- * cluster; until we do, disable leases (by just returning -EINVAL),
- * unless the administrator has requested purely local locking.
- *
- * Locking: called under i_lock
- *
- * Returns: errno
- */
-
-static int gfs2_setlease(struct file *file, long arg, struct file_lock **fl)
-{
-	return -EINVAL;
-}
-
-/**
  * gfs2_lock - acquire/release a posix lock on a file
  * @file: the file pointer
  * @cmd: either modify or retrieve lock state, possibly wait
@@ -1078,7 +1058,7 @@ const struct file_operations gfs2_file_fops = {
 	.flock		= gfs2_flock,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
-	.setlease	= gfs2_setlease,
+	.setlease	= simple_nosetlease,
 	.fallocate	= gfs2_fallocate,
 };
 
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 7f513b1ceb2c..8f0c19d1d943 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -811,7 +811,7 @@ void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
 {
 	INIT_LIST_HEAD(&gh->gh_list);
 	gh->gh_gl = gl;
-	gh->gh_ip = (unsigned long)__builtin_return_address(0);
+	gh->gh_ip = _RET_IP_;
 	gh->gh_owner_pid = get_pid(task_pid(current));
 	gh->gh_state = state;
 	gh->gh_flags = flags;
@@ -835,7 +835,7 @@ void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *
 	gh->gh_state = state;
 	gh->gh_flags = flags;
 	gh->gh_iflags = 0;
-	gh->gh_ip = (unsigned long)__builtin_return_address(0);
+	gh->gh_ip = _RET_IP_;
 	if (gh->gh_owner_pid)
 		put_pid(gh->gh_owner_pid);
 	gh->gh_owner_pid = get_pid(task_pid(current));
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 2ffc67dce87f..1cc0bba6313f 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -93,7 +93,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
          * tr->alloced is not set since the transaction structure is
          * on the stack */
 	tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64));
-	tr.tr_ip = (unsigned long)__builtin_return_address(0);
+	tr.tr_ip = _RET_IP_;
 	sb_start_intwrite(sdp->sd_vfs);
 	if (gfs2_log_reserve(sdp, tr.tr_reserved) < 0) {
 		sb_end_intwrite(sdp->sd_vfs);
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index fc8ac2ee0667..c4ed823d150e 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -600,7 +600,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	int error, free_vfs_inode = 0;
 	u32 aflags = 0;
 	unsigned blocks = 1;
-	struct gfs2_diradd da = { .bh = NULL, };
+	struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, };
 
 	if (!name->len || name->len > GFS2_FNAMESIZE)
 		return -ENAMETOOLONG;
@@ -672,6 +672,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	gfs2_set_inode_blocks(inode, 1);
 	munge_mode_uid_gid(dip, inode);
+	check_and_update_goal(dip);
 	ip->i_goal = dip->i_goal;
 	ip->i_diskflags = 0;
 	ip->i_eattr = 0;
@@ -899,7 +900,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder ghs[2];
 	struct buffer_head *dibh;
-	struct gfs2_diradd da = { .bh = NULL, };
+	struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, };
 	int error;
 
 	if (S_ISDIR(inode->i_mode))
@@ -1244,6 +1245,9 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct dentry *d;
 	bool excl = !!(flags & O_EXCL);
 
+	if (!d_unhashed(dentry))
+		goto skip_lookup;
+
 	d = __gfs2_lookup(dir, dentry, file, opened);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
@@ -1260,6 +1264,8 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 	}
 
 	BUG_ON(d != NULL);
+
+skip_lookup:
 	if (!(flags & O_CREAT))
 		return -ENOENT;
 
@@ -1337,7 +1343,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 	struct gfs2_rgrpd *nrgd;
 	unsigned int num_gh;
 	int dir_rename = 0;
-	struct gfs2_diradd da = { .nr_blocks = 0, };
+	struct gfs2_diradd da = { .nr_blocks = 0, .save_loc = 0, };
 	unsigned int x;
 	int error;
 
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index f4cb9c0d6bbd..7474c413ffd1 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -577,6 +577,13 @@ struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd)
 	return rgd;
 }
 
+void check_and_update_goal(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	if (!ip->i_goal || gfs2_blk2rgrpd(sdp, ip->i_goal, 1) == NULL)
+		ip->i_goal = ip->i_no_addr;
+}
+
 void gfs2_free_clones(struct gfs2_rgrpd *rgd)
 {
 	int x;
@@ -1910,6 +1917,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, const struct gfs2_alloc_parms *a
 	} else if (ip->i_rgd && rgrp_contains_block(ip->i_rgd, ip->i_goal)) {
 		rs->rs_rbm.rgd = begin = ip->i_rgd;
 	} else {
+		check_and_update_goal(ip);
 		rs->rs_rbm.rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal, 1);
 	}
 	if (S_ISDIR(ip->i_inode.i_mode) && (ap->aflags & GFS2_AF_ORLOV))
@@ -2089,7 +2097,7 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart,
 				     u32 blen, unsigned char new_state)
 {
 	struct gfs2_rbm rbm;
-	struct gfs2_bitmap *bi;
+	struct gfs2_bitmap *bi, *bi_prev = NULL;
 
 	rbm.rgd = gfs2_blk2rgrpd(sdp, bstart, 1);
 	if (!rbm.rgd) {
@@ -2098,18 +2106,22 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart,
 		return NULL;
 	}
 
+	gfs2_rbm_from_block(&rbm, bstart);
 	while (blen--) {
-		gfs2_rbm_from_block(&rbm, bstart);
 		bi = rbm_bi(&rbm);
-		bstart++;
-		if (!bi->bi_clone) {
-			bi->bi_clone = kmalloc(bi->bi_bh->b_size,
-					       GFP_NOFS | __GFP_NOFAIL);
-			memcpy(bi->bi_clone + bi->bi_offset,
-			       bi->bi_bh->b_data + bi->bi_offset, bi->bi_len);
+		if (bi != bi_prev) {
+			if (!bi->bi_clone) {
+				bi->bi_clone = kmalloc(bi->bi_bh->b_size,
+						      GFP_NOFS | __GFP_NOFAIL);
+				memcpy(bi->bi_clone + bi->bi_offset,
+				       bi->bi_bh->b_data + bi->bi_offset,
+				       bi->bi_len);
+			}
+			gfs2_trans_add_meta(rbm.rgd->rd_gl, bi->bi_bh);
+			bi_prev = bi;
 		}
-		gfs2_trans_add_meta(rbm.rgd->rd_gl, bi->bi_bh);
 		gfs2_setbit(&rbm, false, new_state);
+		gfs2_rbm_incr(&rbm);
 	}
 
 	return rbm.rgd;
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index 463ab2e95d1c..5d8f085f7ade 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -80,4 +80,5 @@ static inline bool gfs2_rs_active(struct gfs2_blkreserv *rs)
 	return rs && !RB_EMPTY_NODE(&rs->rs_node);
 }
 
+extern void check_and_update_goal(struct gfs2_inode *ip);
 #endif /* __RGRP_DOT_H__ */
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 0546ab4e28e8..42bfd3361979 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -44,7 +44,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 	if (!tr)
 		return -ENOMEM;
 
-	tr->tr_ip = (unsigned long)__builtin_return_address(0);
+	tr->tr_ip = _RET_IP_;
 	tr->tr_blocks = blocks;
 	tr->tr_revokes = revokes;
 	tr->tr_reserved = 1;
diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index 0524cda47a6e..95d255219b1e 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -242,8 +242,6 @@ extern int hfs_mac2asc(struct super_block *, char *, const struct hfs_name *);
 /* super.c */
 extern void hfs_mark_mdb_dirty(struct super_block *sb);
 
-extern struct timezone sys_tz;
-
 /*
  * There are two time systems.  Both are based on seconds since
  * a particular time/date.
diff --git a/fs/internal.h b/fs/internal.h
index e325b4f9c799..9477f8f6aefc 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -35,6 +35,11 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait)
 #endif
 
 /*
+ * buffer.c
+ */
+extern void guard_bio_eod(int rw, struct bio *bio);
+
+/*
  * char_dev.c
  */
 extern void __init chrdev_init(void);
@@ -51,7 +56,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
  * namespace.c
  */
 extern int copy_mount_options(const void __user *, unsigned long *);
-extern int copy_mount_string(const void __user *, char **);
+extern char *copy_mount_string(const void __user *);
 
 extern struct vfsmount *lookup_mnt(struct path *);
 extern int finish_automount(struct vfsmount *, struct path *);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 5ddaf8625d3b..881b3bd0143f 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -247,7 +247,7 @@ static int isofs_dentry_cmp_common(
 	}
 	if (alen == blen) {
 		if (ci) {
-			if (strnicmp(name->name, str, alen) == 0)
+			if (strncasecmp(name->name, str, alen) == 0)
 				return 0;
 		} else {
 			if (strncmp(name->name, str, alen) == 0)
diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h
index 413ef89c2d1b..046fee8b6e9b 100644
--- a/fs/jffs2/jffs2_fs_sb.h
+++ b/fs/jffs2/jffs2_fs_sb.h
@@ -134,8 +134,6 @@ struct jffs2_sb_info {
 	struct rw_semaphore wbuf_sem;	/* Protects the write buffer */
 
 	struct delayed_work wbuf_dwork; /* write-buffer write-out work */
-	int wbuf_queued;                /* non-zero delayed work is queued */
-	spinlock_t wbuf_dwork_lock;     /* protects wbuf_dwork and and wbuf_queued */
 
 	unsigned char *oobbuf;
 	int oobavail; /* How many bytes are available for JFFS2 in OOB */
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index a6597d60d76d..09ed55190ee2 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -1162,10 +1162,6 @@ static void delayed_wbuf_sync(struct work_struct *work)
 	struct jffs2_sb_info *c = work_to_sb(work);
 	struct super_block *sb = OFNI_BS_2SFFJ(c);
 
-	spin_lock(&c->wbuf_dwork_lock);
-	c->wbuf_queued = 0;
-	spin_unlock(&c->wbuf_dwork_lock);
-
 	if (!(sb->s_flags & MS_RDONLY)) {
 		jffs2_dbg(1, "%s()\n", __func__);
 		jffs2_flush_wbuf_gc(c, 0);
@@ -1180,14 +1176,9 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c)
 	if (sb->s_flags & MS_RDONLY)
 		return;
 
-	spin_lock(&c->wbuf_dwork_lock);
-	if (!c->wbuf_queued) {
+	delay = msecs_to_jiffies(dirty_writeback_interval * 10);
+	if (queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay))
 		jffs2_dbg(1, "%s()\n", __func__);
-		delay = msecs_to_jiffies(dirty_writeback_interval * 10);
-		queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay);
-		c->wbuf_queued = 1;
-	}
-	spin_unlock(&c->wbuf_dwork_lock);
 }
 
 int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
@@ -1211,7 +1202,6 @@ int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
 
 	/* Initialise write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 	c->wbuf_pagesize = c->mtd->writesize;
 	c->wbuf_ofs = 0xFFFFFFFF;
@@ -1251,7 +1241,6 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) {
 
 	/* Initialize write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 	c->wbuf_pagesize =  c->mtd->erasesize;
 
@@ -1311,7 +1300,6 @@ int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c) {
 
 	/* Initialize write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 
 	c->wbuf_pagesize = c->mtd->writesize;
@@ -1346,7 +1334,6 @@ int jffs2_ubivol_setup(struct jffs2_sb_info *c) {
 		return 0;
 
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 
 	c->wbuf_pagesize =  c->mtd->writesize;
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 0acddf60af55..bc462dcd7a40 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1585,7 +1585,6 @@ void jfs_flush_journal(struct jfs_log *log, int wait)
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		LOGGC_UNLOCK(log);
 		schedule();
-		__set_current_state(TASK_RUNNING);
 		LOGGC_LOCK(log);
 		remove_wait_queue(&target->gcwait, &__wait);
 	}
@@ -2359,7 +2358,6 @@ int jfsIOWait(void *arg)
 			set_current_state(TASK_INTERRUPTIBLE);
 			spin_unlock_irq(&log_redrive_lock);
 			schedule();
-			__set_current_state(TASK_RUNNING);
 		}
 	} while (!kthread_should_stop());
 
diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c
index 564c4f279ac6..d595856453b2 100644
--- a/fs/jfs/jfs_txnmgr.c
+++ b/fs/jfs/jfs_txnmgr.c
@@ -136,7 +136,6 @@ static inline void TXN_SLEEP_DROP_LOCK(wait_queue_head_t * event)
 	set_current_state(TASK_UNINTERRUPTIBLE);
 	TXN_UNLOCK();
 	io_schedule();
-	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(event, &wait);
 }
 
@@ -2808,7 +2807,6 @@ int jfs_lazycommit(void *arg)
 			set_current_state(TASK_INTERRUPTIBLE);
 			LAZY_UNLOCK(flags);
 			schedule();
-			__set_current_state(TASK_RUNNING);
 			remove_wait_queue(&jfs_commit_thread_wait, &wq);
 		}
 	} while (!kthread_should_stop());
@@ -2996,7 +2994,6 @@ int jfs_sync(void *arg)
 			set_current_state(TASK_INTERRUPTIBLE);
 			TXN_UNLOCK();
 			schedule();
-			__set_current_state(TASK_RUNNING);
 		}
 	} while (!kthread_should_stop());
 
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index adf8cb045b9e..93e897e588a8 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -550,7 +550,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 	inode->i_ino = 0;
 	inode->i_size = sb->s_bdev->bd_inode->i_size;
 	inode->i_mapping->a_ops = &jfs_metapage_aops;
-	insert_inode_hash(inode);
+	hlist_add_fake(&inode->i_hash);
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 
 	sbi->direct_inode = inode;
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index a693f5b01ae6..1c771931bb60 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -463,21 +463,10 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 		goto out_bad;
 
 	mutex_unlock(&kernfs_mutex);
-out_valid:
 	return 1;
 out_bad:
 	mutex_unlock(&kernfs_mutex);
 out_bad_unlocked:
-	/*
-	 * @dentry doesn't match the underlying kernfs node, drop the
-	 * dentry and force lookup.  If we have submounts we must allow the
-	 * vfs caches to lie about the state of the filesystem to prevent
-	 * leaks and other nasty things, so use check_submounts_and_drop()
-	 * instead of d_drop().
-	 */
-	if (check_submounts_and_drop(dentry) != 0)
-		goto out_valid;
-
 	return 0;
 }
 
diff --git a/fs/libfs.c b/fs/libfs.c
index 88e3e00e2eca..171d2846f2a3 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1075,3 +1075,21 @@ struct inode *alloc_anon_inode(struct super_block *s)
 	return inode;
 }
 EXPORT_SYMBOL(alloc_anon_inode);
+
+/**
+ * simple_nosetlease - generic helper for prohibiting leases
+ * @filp: file pointer
+ * @arg: type of lease to obtain
+ * @flp: new lease supplied for insertion
+ * @priv: private data for lm_setup operation
+ *
+ * Generic helper for filesystems that do not wish to allow leases to be set.
+ * All arguments are ignored and it just returns -EINVAL.
+ */
+int
+simple_nosetlease(struct file *filp, long arg, struct file_lock **flp,
+		  void **priv)
+{
+	return -EINVAL;
+}
+EXPORT_SYMBOL(simple_nosetlease);
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index ab798a88ec1d..13db95f54176 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -245,7 +245,6 @@ nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_host *host,
 	block->b_daemon = rqstp->rq_server;
 	block->b_host   = host;
 	block->b_file   = file;
-	block->b_fl = NULL;
 	file->f_count++;
 
 	/* Add to file's list of blocks */
@@ -295,7 +294,6 @@ static void nlmsvc_free_block(struct kref *kref)
 	nlmsvc_freegrantargs(block->b_call);
 	nlmsvc_release_call(block->b_call);
 	nlm_release_file(block->b_file);
-	kfree(block->b_fl);
 	kfree(block);
 }
 
@@ -508,7 +506,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 		struct nlm_host *host, struct nlm_lock *lock,
 		struct nlm_lock *conflock, struct nlm_cookie *cookie)
 {
-	struct nlm_block 	*block = NULL;
 	int			error;
 	__be32			ret;
 
@@ -519,63 +516,26 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
 
-	/* Get existing block (in case client is busy-waiting) */
-	block = nlmsvc_lookup_block(file, lock);
-
-	if (block == NULL) {
-		struct file_lock *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
-
-		if (conf == NULL)
-			return nlm_granted;
-		block = nlmsvc_create_block(rqstp, host, file, lock, cookie);
-		if (block == NULL) {
-			kfree(conf);
-			return nlm_granted;
-		}
-		block->b_fl = conf;
-	}
-	if (block->b_flags & B_QUEUED) {
-		dprintk("lockd: nlmsvc_testlock deferred block %p flags %d fl %p\n",
-			block, block->b_flags, block->b_fl);
-		if (block->b_flags & B_TIMED_OUT) {
-			nlmsvc_unlink_block(block);
-			ret = nlm_lck_denied;
-			goto out;
-		}
-		if (block->b_flags & B_GOT_CALLBACK) {
-			nlmsvc_unlink_block(block);
-			if (block->b_fl != NULL
-					&& block->b_fl->fl_type != F_UNLCK) {
-				lock->fl = *block->b_fl;
-				goto conf_lock;
-			} else {
-				ret = nlm_granted;
-				goto out;
-			}
-		}
-		ret = nlm_drop_reply;
-		goto out;
-	}
-
 	if (locks_in_grace(SVC_NET(rqstp))) {
 		ret = nlm_lck_denied_grace_period;
 		goto out;
 	}
+
 	error = vfs_test_lock(file->f_file, &lock->fl);
-	if (error == FILE_LOCK_DEFERRED) {
-		ret = nlmsvc_defer_lock_rqst(rqstp, block);
-		goto out;
-	}
 	if (error) {
+		/* We can't currently deal with deferred test requests */
+		if (error == FILE_LOCK_DEFERRED)
+			WARN_ON_ONCE(1);
+
 		ret = nlm_lck_denied_nolocks;
 		goto out;
 	}
+
 	if (lock->fl.fl_type == F_UNLCK) {
 		ret = nlm_granted;
 		goto out;
 	}
 
-conf_lock:
 	dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
 		lock->fl.fl_type, (long long)lock->fl.fl_start,
 		(long long)lock->fl.fl_end);
@@ -586,10 +546,9 @@ conf_lock:
 	conflock->fl.fl_type = lock->fl.fl_type;
 	conflock->fl.fl_start = lock->fl.fl_start;
 	conflock->fl.fl_end = lock->fl.fl_end;
+	locks_release_private(&lock->fl);
 	ret = nlm_lck_denied;
 out:
-	if (block)
-		nlmsvc_release_block(block);
 	return ret;
 }
 
@@ -660,29 +619,22 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l
  * This is a callback from the filesystem for VFS file lock requests.
  * It will be used if lm_grant is defined and the filesystem can not
  * respond to the request immediately.
- * For GETLK request it will copy the reply to the nlm_block.
  * For SETLK or SETLKW request it will get the local posix lock.
  * In all cases it will move the block to the head of nlm_blocked q where
  * nlmsvc_retry_blocked() can send back a reply for SETLKW or revisit the
  * deferred rpc for GETLK and SETLK.
  */
 static void
-nlmsvc_update_deferred_block(struct nlm_block *block, struct file_lock *conf,
-			     int result)
+nlmsvc_update_deferred_block(struct nlm_block *block, int result)
 {
 	block->b_flags |= B_GOT_CALLBACK;
 	if (result == 0)
 		block->b_granted = 1;
 	else
 		block->b_flags |= B_TIMED_OUT;
-	if (conf) {
-		if (block->b_fl)
-			__locks_copy_lock(block->b_fl, conf);
-	}
 }
 
-static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
-					int result)
+static int nlmsvc_grant_deferred(struct file_lock *fl, int result)
 {
 	struct nlm_block *block;
 	int rc = -ENOENT;
@@ -697,7 +649,7 @@ static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
 					rc = -ENOLCK;
 					break;
 				}
-				nlmsvc_update_deferred_block(block, conf, result);
+				nlmsvc_update_deferred_block(block, result);
 			} else if (result == 0)
 				block->b_granted = 1;
 
diff --git a/fs/locks.c b/fs/locks.c
index bb08857f90b5..735b8d3fa78c 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -230,8 +230,12 @@ void locks_release_private(struct file_lock *fl)
 			fl->fl_ops->fl_release_private(fl);
 		fl->fl_ops = NULL;
 	}
-	fl->fl_lmops = NULL;
 
+	if (fl->fl_lmops) {
+		if (fl->fl_lmops->lm_put_owner)
+			fl->fl_lmops->lm_put_owner(fl);
+		fl->fl_lmops = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(locks_release_private);
 
@@ -267,21 +271,10 @@ void locks_init_lock(struct file_lock *fl)
 
 EXPORT_SYMBOL(locks_init_lock);
 
-static void locks_copy_private(struct file_lock *new, struct file_lock *fl)
-{
-	if (fl->fl_ops) {
-		if (fl->fl_ops->fl_copy_lock)
-			fl->fl_ops->fl_copy_lock(new, fl);
-		new->fl_ops = fl->fl_ops;
-	}
-	if (fl->fl_lmops)
-		new->fl_lmops = fl->fl_lmops;
-}
-
 /*
  * Initialize a new lock from an existing file_lock structure.
  */
-void __locks_copy_lock(struct file_lock *new, const struct file_lock *fl)
+void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
 	new->fl_owner = fl->fl_owner;
 	new->fl_pid = fl->fl_pid;
@@ -290,22 +283,30 @@ void __locks_copy_lock(struct file_lock *new, const struct file_lock *fl)
 	new->fl_type = fl->fl_type;
 	new->fl_start = fl->fl_start;
 	new->fl_end = fl->fl_end;
+	new->fl_lmops = fl->fl_lmops;
 	new->fl_ops = NULL;
-	new->fl_lmops = NULL;
+
+	if (fl->fl_lmops) {
+		if (fl->fl_lmops->lm_get_owner)
+			fl->fl_lmops->lm_get_owner(new, fl);
+	}
 }
-EXPORT_SYMBOL(__locks_copy_lock);
+EXPORT_SYMBOL(locks_copy_conflock);
 
 void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
 {
 	/* "new" must be a freshly-initialized lock */
 	WARN_ON_ONCE(new->fl_ops);
 
-	__locks_copy_lock(new, fl);
+	locks_copy_conflock(new, fl);
+
 	new->fl_file = fl->fl_file;
 	new->fl_ops = fl->fl_ops;
-	new->fl_lmops = fl->fl_lmops;
 
-	locks_copy_private(new, fl);
+	if (fl->fl_ops) {
+		if (fl->fl_ops->fl_copy_lock)
+			fl->fl_ops->fl_copy_lock(new, fl);
+	}
 }
 
 EXPORT_SYMBOL(locks_copy_lock);
@@ -325,17 +326,18 @@ static inline int flock_translate_cmd(int cmd) {
 }
 
 /* Fill in a file_lock structure with an appropriate FLOCK lock. */
-static int flock_make_lock(struct file *filp, struct file_lock **lock,
-		unsigned int cmd)
+static struct file_lock *
+flock_make_lock(struct file *filp, unsigned int cmd)
 {
 	struct file_lock *fl;
 	int type = flock_translate_cmd(cmd);
+
 	if (type < 0)
-		return type;
+		return ERR_PTR(type);
 	
 	fl = locks_alloc_lock();
 	if (fl == NULL)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	fl->fl_file = filp;
 	fl->fl_owner = filp;
@@ -344,8 +346,7 @@ static int flock_make_lock(struct file *filp, struct file_lock **lock,
 	fl->fl_type = type;
 	fl->fl_end = OFFSET_MAX;
 	
-	*lock = fl;
-	return 0;
+	return fl;
 }
 
 static int assign_type(struct file_lock *fl, long type)
@@ -426,14 +427,34 @@ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl,
 }
 
 /* default lease lock manager operations */
-static void lease_break_callback(struct file_lock *fl)
+static bool
+lease_break_callback(struct file_lock *fl)
 {
 	kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG);
+	return false;
+}
+
+static void
+lease_setup(struct file_lock *fl, void **priv)
+{
+	struct file *filp = fl->fl_file;
+	struct fasync_struct *fa = *priv;
+
+	/*
+	 * fasync_insert_entry() returns the old entry if any. If there was no
+	 * old entry, then it used "priv" and inserted it into the fasync list.
+	 * Clear the pointer to indicate that it shouldn't be freed.
+	 */
+	if (!fasync_insert_entry(fa->fa_fd, filp, &fl->fl_fasync, fa))
+		*priv = NULL;
+
+	__f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
 }
 
 static const struct lock_manager_operations lease_manager_ops = {
 	.lm_break = lease_break_callback,
 	.lm_change = lease_modify,
+	.lm_setup = lease_setup,
 };
 
 /*
@@ -444,7 +465,7 @@ static int lease_init(struct file *filp, long type, struct file_lock *fl)
 	if (assign_type(fl, type) != 0)
 		return -EINVAL;
 
-	fl->fl_owner = current->files;
+	fl->fl_owner = filp;
 	fl->fl_pid = current->tgid;
 
 	fl->fl_file = filp;
@@ -735,7 +756,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 			break;
 	}
 	if (cfl) {
-		__locks_copy_lock(fl, cfl);
+		locks_copy_conflock(fl, cfl);
 		if (cfl->fl_nspid)
 			fl->fl_pid = pid_vnr(cfl->fl_nspid);
 	} else
@@ -941,7 +962,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			if (!posix_locks_conflict(request, fl))
 				continue;
 			if (conflock)
-				__locks_copy_lock(conflock, fl);
+				locks_copy_conflock(conflock, fl);
 			error = -EAGAIN;
 			if (!(request->fl_flags & FL_SLEEP))
 				goto out;
@@ -1273,7 +1294,7 @@ static void lease_clear_pending(struct file_lock *fl, int arg)
 }
 
 /* We already had a lease on this file; just change its type */
-int lease_modify(struct file_lock **before, int arg)
+int lease_modify(struct file_lock **before, int arg, struct list_head *dispose)
 {
 	struct file_lock *fl = *before;
 	int error = assign_type(fl, arg);
@@ -1292,11 +1313,10 @@ int lease_modify(struct file_lock **before, int arg)
 			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
 			fl->fl_fasync = NULL;
 		}
-		locks_delete_lock(before, NULL);
+		locks_delete_lock(before, dispose);
 	}
 	return 0;
 }
-
 EXPORT_SYMBOL(lease_modify);
 
 static bool past_time(unsigned long then)
@@ -1307,18 +1327,20 @@ static bool past_time(unsigned long then)
 	return time_after(jiffies, then);
 }
 
-static void time_out_leases(struct inode *inode)
+static void time_out_leases(struct inode *inode, struct list_head *dispose)
 {
 	struct file_lock **before;
 	struct file_lock *fl;
 
+	lockdep_assert_held(&inode->i_lock);
+
 	before = &inode->i_flock;
 	while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) {
 		trace_time_out_leases(inode, fl);
 		if (past_time(fl->fl_downgrade_time))
-			lease_modify(before, F_RDLCK);
+			lease_modify(before, F_RDLCK, dispose);
 		if (past_time(fl->fl_break_time))
-			lease_modify(before, F_UNLCK);
+			lease_modify(before, F_UNLCK, dispose);
 		if (fl == *before)	/* lease_modify may have freed fl */
 			before = &fl->fl_next;
 	}
@@ -1331,6 +1353,20 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
 	return locks_conflict(breaker, lease);
 }
 
+static bool
+any_leases_conflict(struct inode *inode, struct file_lock *breaker)
+{
+	struct file_lock *fl;
+
+	lockdep_assert_held(&inode->i_lock);
+
+	for (fl = inode->i_flock ; fl && IS_LEASE(fl); fl = fl->fl_next) {
+		if (leases_conflict(fl, breaker))
+			return true;
+	}
+	return false;
+}
+
 /**
  *	__break_lease	-	revoke all outstanding leases on file
  *	@inode: the inode of the file to return
@@ -1347,12 +1383,11 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
 int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
-	struct file_lock *new_fl, *flock;
-	struct file_lock *fl;
+	struct file_lock *new_fl;
+	struct file_lock *fl, **before;
 	unsigned long break_time;
-	int i_have_this_lease = 0;
-	bool lease_conflict = false;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
+	LIST_HEAD(dispose);
 
 	new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK);
 	if (IS_ERR(new_fl))
@@ -1361,20 +1396,9 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 
 	spin_lock(&inode->i_lock);
 
-	time_out_leases(inode);
-
-	flock = inode->i_flock;
-	if ((flock == NULL) || !IS_LEASE(flock))
-		goto out;
+	time_out_leases(inode, &dispose);
 
-	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
-		if (leases_conflict(fl, new_fl)) {
-			lease_conflict = true;
-			if (fl->fl_owner == current->files)
-				i_have_this_lease = 1;
-		}
-	}
-	if (!lease_conflict)
+	if (!any_leases_conflict(inode, new_fl))
 		goto out;
 
 	break_time = 0;
@@ -1384,7 +1408,9 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			break_time++;	/* so that 0 means no break time */
 	}
 
-	for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
+	for (before = &inode->i_flock;
+			((fl = *before) != NULL) && IS_LEASE(fl);
+			before = &fl->fl_next) {
 		if (!leases_conflict(fl, new_fl))
 			continue;
 		if (want_write) {
@@ -1393,51 +1419,56 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			fl->fl_flags |= FL_UNLOCK_PENDING;
 			fl->fl_break_time = break_time;
 		} else {
-			if (lease_breaking(flock))
+			if (lease_breaking(inode->i_flock))
 				continue;
 			fl->fl_flags |= FL_DOWNGRADE_PENDING;
 			fl->fl_downgrade_time = break_time;
 		}
-		fl->fl_lmops->lm_break(fl);
+		if (fl->fl_lmops->lm_break(fl))
+			locks_delete_lock(before, &dispose);
 	}
 
-	if (i_have_this_lease || (mode & O_NONBLOCK)) {
+	fl = inode->i_flock;
+	if (!fl || !IS_LEASE(fl))
+		goto out;
+
+	if (mode & O_NONBLOCK) {
 		trace_break_lease_noblock(inode, new_fl);
 		error = -EWOULDBLOCK;
 		goto out;
 	}
 
 restart:
-	break_time = flock->fl_break_time;
+	break_time = inode->i_flock->fl_break_time;
 	if (break_time != 0)
 		break_time -= jiffies;
 	if (break_time == 0)
 		break_time++;
-	locks_insert_block(flock, new_fl);
+	locks_insert_block(inode->i_flock, new_fl);
 	trace_break_lease_block(inode, new_fl);
 	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
 						!new_fl->fl_next, break_time);
 	spin_lock(&inode->i_lock);
 	trace_break_lease_unblock(inode, new_fl);
 	locks_delete_block(new_fl);
 	if (error >= 0) {
-		if (error == 0)
-			time_out_leases(inode);
 		/*
 		 * Wait for the next conflicting lease that has not been
 		 * broken yet
 		 */
-		for (flock = inode->i_flock; flock && IS_LEASE(flock);
-				flock = flock->fl_next) {
-			if (leases_conflict(new_fl, flock))
-				goto restart;
-		}
+		if (error == 0)
+			time_out_leases(inode, &dispose);
+		if (any_leases_conflict(inode, new_fl))
+			goto restart;
+
 		error = 0;
 	}
 
 out:
 	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	locks_free_lock(new_fl);
 	return error;
 }
@@ -1455,8 +1486,18 @@ EXPORT_SYMBOL(__break_lease);
  */
 void lease_get_mtime(struct inode *inode, struct timespec *time)
 {
-	struct file_lock *flock = inode->i_flock;
-	if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK))
+	bool has_lease = false;
+	struct file_lock *flock;
+
+	if (inode->i_flock) {
+		spin_lock(&inode->i_lock);
+		flock = inode->i_flock;
+		if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK))
+			has_lease = true;
+		spin_unlock(&inode->i_lock);
+	}
+
+	if (has_lease)
 		*time = current_fs_time(inode->i_sb);
 	else
 		*time = inode->i_mtime;
@@ -1492,9 +1533,10 @@ int fcntl_getlease(struct file *filp)
 	struct file_lock *fl;
 	struct inode *inode = file_inode(filp);
 	int type = F_UNLCK;
+	LIST_HEAD(dispose);
 
 	spin_lock(&inode->i_lock);
-	time_out_leases(file_inode(filp));
+	time_out_leases(file_inode(filp), &dispose);
 	for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl);
 			fl = fl->fl_next) {
 		if (fl->fl_file == filp) {
@@ -1503,6 +1545,7 @@ int fcntl_getlease(struct file *filp)
 		}
 	}
 	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	return type;
 }
 
@@ -1532,13 +1575,15 @@ check_conflicting_open(const struct dentry *dentry, const long arg)
 	return ret;
 }
 
-static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp)
+static int
+generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv)
 {
 	struct file_lock *fl, **before, **my_before = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
+	LIST_HEAD(dispose);
 
 	lease = *flp;
 	trace_generic_add_lease(inode, lease);
@@ -1561,6 +1606,8 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 		return -EINVAL;
 	}
 
+	spin_lock(&inode->i_lock);
+	time_out_leases(inode, &dispose);
 	error = check_conflicting_open(dentry, arg);
 	if (error)
 		goto out;
@@ -1596,10 +1643,11 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 	}
 
 	if (my_before != NULL) {
-		error = lease->fl_lmops->lm_change(my_before, arg);
-		if (!error)
-			*flp = *my_before;
-		goto out;
+		lease = *my_before;
+		error = lease->fl_lmops->lm_change(my_before, arg, &dispose);
+		if (error)
+			goto out;
+		goto out_setup;
 	}
 
 	error = -EINVAL;
@@ -1619,43 +1667,61 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 	smp_mb();
 	error = check_conflicting_open(dentry, arg);
 	if (error)
-		locks_unlink_lock(before);
+		goto out_unlink;
+
+out_setup:
+	if (lease->fl_lmops->lm_setup)
+		lease->fl_lmops->lm_setup(lease, priv);
 out:
+	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
 	if (is_deleg)
 		mutex_unlock(&inode->i_mutex);
+	if (!error && !my_before)
+		*flp = NULL;
 	return error;
+out_unlink:
+	locks_unlink_lock(before);
+	goto out;
 }
 
-static int generic_delete_lease(struct file *filp, struct file_lock **flp)
+static int generic_delete_lease(struct file *filp)
 {
+	int error = -EAGAIN;
 	struct file_lock *fl, **before;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	LIST_HEAD(dispose);
 
-	trace_generic_delete_lease(inode, *flp);
-
+	spin_lock(&inode->i_lock);
+	time_out_leases(inode, &dispose);
 	for (before = &inode->i_flock;
 			((fl = *before) != NULL) && IS_LEASE(fl);
 			before = &fl->fl_next) {
-		if (fl->fl_file != filp)
-			continue;
-		return (*flp)->fl_lmops->lm_change(before, F_UNLCK);
+		if (fl->fl_file == filp)
+			break;
 	}
-	return -EAGAIN;
+	trace_generic_delete_lease(inode, fl);
+	if (fl)
+		error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose);
+	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
+	return error;
 }
 
 /**
  *	generic_setlease	-	sets a lease on an open file
- *	@filp: file pointer
- *	@arg: type of lease to obtain
- *	@flp: input - file_lock to use, output - file_lock inserted
+ *	@filp:	file pointer
+ *	@arg:	type of lease to obtain
+ *	@flp:	input - file_lock to use, output - file_lock inserted
+ *	@priv:	private data for lm_setup (may be NULL if lm_setup
+ *		doesn't require it)
  *
  *	The (input) flp->fl_lmops->lm_break function is required
  *	by break_lease().
- *
- *	Called with inode->i_lock held.
  */
-int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
+int generic_setlease(struct file *filp, long arg, struct file_lock **flp,
+			void **priv)
 {
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
@@ -1669,83 +1735,52 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
 	if (error)
 		return error;
 
-	time_out_leases(inode);
-
-	BUG_ON(!(*flp)->fl_lmops->lm_break);
-
 	switch (arg) {
 	case F_UNLCK:
-		return generic_delete_lease(filp, flp);
+		return generic_delete_lease(filp);
 	case F_RDLCK:
 	case F_WRLCK:
-		return generic_add_lease(filp, arg, flp);
+		if (!(*flp)->fl_lmops->lm_break) {
+			WARN_ON_ONCE(1);
+			return -ENOLCK;
+		}
+		return generic_add_lease(filp, arg, flp, priv);
 	default:
 		return -EINVAL;
 	}
 }
 EXPORT_SYMBOL(generic_setlease);
 
-static int __vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
-{
-	if (filp->f_op->setlease)
-		return filp->f_op->setlease(filp, arg, lease);
-	else
-		return generic_setlease(filp, arg, lease);
-}
-
 /**
- *	vfs_setlease        -       sets a lease on an open file
- *	@filp: file pointer
- *	@arg: type of lease to obtain
- *	@lease: file_lock to use
- *
- *	Call this to establish a lease on the file.
- *	The (*lease)->fl_lmops->lm_break operation must be set; if not,
- *	break_lease will oops!
- *
- *	This will call the filesystem's setlease file method, if
- *	defined.  Note that there is no getlease method; instead, the
- *	filesystem setlease method should call back to setlease() to
- *	add a lease to the inode's lease list, where fcntl_getlease() can
- *	find it.  Since fcntl_getlease() only reports whether the current
- *	task holds a lease, a cluster filesystem need only do this for
- *	leases held by processes on this node.
- *
- *	There is also no break_lease method; filesystems that
- *	handle their own leases should break leases themselves from the
- *	filesystem's open, create, and (on truncate) setattr methods.
- *
- *	Warning: the only current setlease methods exist only to disable
- *	leases in certain cases.  More vfs changes may be required to
- *	allow a full filesystem lease implementation.
+ * vfs_setlease        -       sets a lease on an open file
+ * @filp:	file pointer
+ * @arg:	type of lease to obtain
+ * @lease:	file_lock to use when adding a lease
+ * @priv:	private info for lm_setup when adding a lease (may be
+ * 		NULL if lm_setup doesn't require it)
+ *
+ * Call this to establish a lease on the file. The "lease" argument is not
+ * used for F_UNLCK requests and may be NULL. For commands that set or alter
+ * an existing lease, the (*lease)->fl_lmops->lm_break operation must be set;
+ * if not, this function will return -ENOLCK (and generate a scary-looking
+ * stack trace).
+ *
+ * The "priv" pointer is passed directly to the lm_setup function as-is. It
+ * may be NULL if the lm_setup operation doesn't require it.
  */
-
-int vfs_setlease(struct file *filp, long arg, struct file_lock **lease)
+int
+vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv)
 {
-	struct inode *inode = file_inode(filp);
-	int error;
-
-	spin_lock(&inode->i_lock);
-	error = __vfs_setlease(filp, arg, lease);
-	spin_unlock(&inode->i_lock);
-
-	return error;
+	if (filp->f_op->setlease)
+		return filp->f_op->setlease(filp, arg, lease, priv);
+	else
+		return generic_setlease(filp, arg, lease, priv);
 }
 EXPORT_SYMBOL_GPL(vfs_setlease);
 
-static int do_fcntl_delete_lease(struct file *filp)
-{
-	struct file_lock fl, *flp = &fl;
-
-	lease_init(filp, F_UNLCK, flp);
-
-	return vfs_setlease(filp, F_UNLCK, &flp);
-}
-
 static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 {
-	struct file_lock *fl, *ret;
-	struct inode *inode = file_inode(filp);
+	struct file_lock *fl;
 	struct fasync_struct *new;
 	int error;
 
@@ -1758,26 +1793,9 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg)
 		locks_free_lock(fl);
 		return -ENOMEM;
 	}
-	ret = fl;
-	spin_lock(&inode->i_lock);
-	error = __vfs_setlease(filp, arg, &ret);
-	if (error)
-		goto out_unlock;
-	if (ret == fl)
-		fl = NULL;
-
-	/*
-	 * fasync_insert_entry() returns the old entry if any.
-	 * If there was no old entry, then it used 'new' and
-	 * inserted it into the fasync list. Clear new so that
-	 * we don't release it here.
-	 */
-	if (!fasync_insert_entry(fd, filp, &ret->fl_fasync, new))
-		new = NULL;
+	new->fa_fd = fd;
 
-	error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
-out_unlock:
-	spin_unlock(&inode->i_lock);
+	error = vfs_setlease(filp, arg, &fl, (void **)&new);
 	if (fl)
 		locks_free_lock(fl);
 	if (new)
@@ -1798,7 +1816,7 @@ out_unlock:
 int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
 	if (arg == F_UNLCK)
-		return do_fcntl_delete_lease(filp);
+		return vfs_setlease(filp, F_UNLCK, NULL, NULL);
 	return do_fcntl_add_lease(fd, filp, arg);
 }
 
@@ -1867,9 +1885,12 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
 	    !(f.file->f_mode & (FMODE_READ|FMODE_WRITE)))
 		goto out_putf;
 
-	error = flock_make_lock(f.file, &lock, cmd);
-	if (error)
+	lock = flock_make_lock(f.file, cmd);
+	if (IS_ERR(lock)) {
+		error = PTR_ERR(lock);
 		goto out_putf;
+	}
+
 	if (can_sleep)
 		lock->fl_flags |= FL_SLEEP;
 
@@ -1981,11 +2002,13 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l)
 	if (file_lock.fl_type != F_UNLCK) {
 		error = posix_lock_to_flock(&flock, &file_lock);
 		if (error)
-			goto out;
+			goto rel_priv;
 	}
 	error = -EFAULT;
 	if (!copy_to_user(l, &flock, sizeof(flock)))
 		error = 0;
+rel_priv:
+	locks_release_private(&file_lock);
 out:
 	return error;
 }
@@ -2206,7 +2229,8 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l)
 	error = -EFAULT;
 	if (!copy_to_user(l, &flock, sizeof(flock)))
 		error = 0;
-  
+
+	locks_release_private(&file_lock);
 out:
 	return error;
 }
@@ -2369,7 +2393,7 @@ void locks_remove_file(struct file *filp)
 	while ((fl = *before) != NULL) {
 		if (fl->fl_file == filp) {
 			if (IS_LEASE(fl)) {
-				lease_modify(before, F_UNLCK);
+				lease_modify(before, F_UNLCK, &dispose);
 				continue;
 			}
 
@@ -2593,86 +2617,6 @@ static int __init proc_locks_init(void)
 module_init(proc_locks_init);
 #endif
 
-/**
- *	lock_may_read - checks that the region is free of locks
- *	@inode: the inode that is being read
- *	@start: the first byte to read
- *	@len: the number of bytes to read
- *
- *	Emulates Windows locking requirements.  Whole-file
- *	mandatory locks (share modes) can prohibit a read and
- *	byte-range POSIX locks can prohibit a read if they overlap.
- *
- *	N.B. this function is only ever called
- *	from knfsd and ownership of locks is never checked.
- */
-int lock_may_read(struct inode *inode, loff_t start, unsigned long len)
-{
-	struct file_lock *fl;
-	int result = 1;
-
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (IS_POSIX(fl)) {
-			if (fl->fl_type == F_RDLCK)
-				continue;
-			if ((fl->fl_end < start) || (fl->fl_start > (start + len)))
-				continue;
-		} else if (IS_FLOCK(fl)) {
-			if (!(fl->fl_type & LOCK_MAND))
-				continue;
-			if (fl->fl_type & LOCK_READ)
-				continue;
-		} else
-			continue;
-		result = 0;
-		break;
-	}
-	spin_unlock(&inode->i_lock);
-	return result;
-}
-
-EXPORT_SYMBOL(lock_may_read);
-
-/**
- *	lock_may_write - checks that the region is free of locks
- *	@inode: the inode that is being written
- *	@start: the first byte to write
- *	@len: the number of bytes to write
- *
- *	Emulates Windows locking requirements.  Whole-file
- *	mandatory locks (share modes) can prohibit a write and
- *	byte-range POSIX locks can prohibit a write if they overlap.
- *
- *	N.B. this function is only ever called
- *	from knfsd and ownership of locks is never checked.
- */
-int lock_may_write(struct inode *inode, loff_t start, unsigned long len)
-{
-	struct file_lock *fl;
-	int result = 1;
-
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (IS_POSIX(fl)) {
-			if ((fl->fl_end < start) || (fl->fl_start > (start + len)))
-				continue;
-		} else if (IS_FLOCK(fl)) {
-			if (!(fl->fl_type & LOCK_MAND))
-				continue;
-			if (fl->fl_type & LOCK_WRITE)
-				continue;
-		} else
-			continue;
-		result = 0;
-		break;
-	}
-	spin_unlock(&inode->i_lock);
-	return result;
-}
-
-EXPORT_SYMBOL(lock_may_write);
-
 static int __init filelock_init(void)
 {
 	int i;
diff --git a/fs/mount.h b/fs/mount.h
index 6740a6215529..f82c62840905 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -21,6 +21,7 @@ struct mnt_pcp {
 struct mountpoint {
 	struct hlist_node m_hash;
 	struct dentry *m_dentry;
+	struct hlist_head m_list;
 	int m_count;
 };
 
@@ -29,7 +30,10 @@ struct mount {
 	struct mount *mnt_parent;
 	struct dentry *mnt_mountpoint;
 	struct vfsmount mnt;
-	struct rcu_head mnt_rcu;
+	union {
+		struct rcu_head mnt_rcu;
+		struct llist_node mnt_llist;
+	};
 #ifdef CONFIG_SMP
 	struct mnt_pcp __percpu *mnt_pcp;
 #else
@@ -48,6 +52,7 @@ struct mount {
 	struct mount *mnt_master;	/* slave is on master->mnt_slave_list */
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
+	struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
 #ifdef CONFIG_FSNOTIFY
 	struct hlist_head mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
@@ -82,6 +87,15 @@ extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *);
 
 extern bool legitimize_mnt(struct vfsmount *, unsigned);
 
+extern void __detach_mounts(struct dentry *dentry);
+
+static inline void detach_mounts(struct dentry *dentry)
+{
+	if (!d_mountpoint(dentry))
+		return;
+	__detach_mounts(dentry);
+}
+
 static inline void get_mnt_ns(struct mnt_namespace *ns)
 {
 	atomic_inc(&ns->count);
@@ -112,3 +126,12 @@ struct proc_mounts {
 #define proc_mounts(p) (container_of((p), struct proc_mounts, m))
 
 extern const struct seq_operations mounts_op;
+
+extern bool __is_local_mountpoint(struct dentry *dentry);
+static inline bool is_local_mountpoint(struct dentry *dentry)
+{
+	if (!d_mountpoint(dentry))
+		return false;
+
+	return __is_local_mountpoint(dentry);
+}
diff --git a/fs/mpage.c b/fs/mpage.c
index 5f9ed622274f..3e79220babac 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -28,6 +28,7 @@
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
 #include <linux/cleancache.h>
+#include "internal.h"
 
 /*
  * I/O completion handler for multipage BIOs.
@@ -57,6 +58,7 @@ static void mpage_end_io(struct bio *bio, int err)
 static struct bio *mpage_bio_submit(int rw, struct bio *bio)
 {
 	bio->bi_end_io = mpage_end_io;
+	guard_bio_eod(rw, bio);
 	submit_bio(rw, bio);
 	return NULL;
 }
diff --git a/fs/namei.c b/fs/namei.c
index a7b05bf82d31..43927d14db67 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1306,7 +1306,8 @@ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
 				if (error < 0) {
 					dput(dentry);
 					return ERR_PTR(error);
-				} else if (!d_invalidate(dentry)) {
+				} else {
+					d_invalidate(dentry);
 					dput(dentry);
 					dentry = NULL;
 				}
@@ -1435,10 +1436,9 @@ unlazy:
 			dput(dentry);
 			return status;
 		}
-		if (!d_invalidate(dentry)) {
-			dput(dentry);
-			goto need_lookup;
-		}
+		d_invalidate(dentry);
+		dput(dentry);
+		goto need_lookup;
 	}
 
 	path->mnt = mnt;
@@ -1950,7 +1950,7 @@ static int path_lookupat(int dfd, const char *name,
 	err = path_init(dfd, name, flags | LOOKUP_PARENT, nd, &base);
 
 	if (unlikely(err))
-		return err;
+		goto out;
 
 	current->total_link_count = 0;
 	err = link_path_walk(name, nd);
@@ -1982,6 +1982,7 @@ static int path_lookupat(int dfd, const char *name,
 		}
 	}
 
+out:
 	if (base)
 		fput(base);
 
@@ -2301,7 +2302,7 @@ path_mountpoint(int dfd, const char *name, struct path *path, unsigned int flags
 
 	err = path_init(dfd, name, flags | LOOKUP_PARENT, &nd, &base);
 	if (unlikely(err))
-		return err;
+		goto out;
 
 	current->total_link_count = 0;
 	err = link_path_walk(name, &nd);
@@ -3074,7 +3075,7 @@ opened:
 	error = open_check_o_direct(file);
 	if (error)
 		goto exit_fput;
-	error = ima_file_check(file, op->acc_mode);
+	error = ima_file_check(file, op->acc_mode, *opened);
 	if (error)
 		goto exit_fput;
 
@@ -3565,7 +3566,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 	mutex_lock(&dentry->d_inode->i_mutex);
 
 	error = -EBUSY;
-	if (d_mountpoint(dentry))
+	if (is_local_mountpoint(dentry))
 		goto out;
 
 	error = security_inode_rmdir(dir, dentry);
@@ -3579,6 +3580,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 
 	dentry->d_inode->i_flags |= S_DEAD;
 	dont_mount(dentry);
+	detach_mounts(dentry);
 
 out:
 	mutex_unlock(&dentry->d_inode->i_mutex);
@@ -3681,7 +3683,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate
 		return -EPERM;
 
 	mutex_lock(&target->i_mutex);
-	if (d_mountpoint(dentry))
+	if (is_local_mountpoint(dentry))
 		error = -EBUSY;
 	else {
 		error = security_inode_unlink(dir, dentry);
@@ -3690,8 +3692,10 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate
 			if (error)
 				goto out;
 			error = dir->i_op->unlink(dir, dentry);
-			if (!error)
+			if (!error) {
 				dont_mount(dentry);
+				detach_mounts(dentry);
+			}
 		}
 	}
 out:
@@ -4126,7 +4130,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		mutex_lock(&target->i_mutex);
 
 	error = -EBUSY;
-	if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
+	if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry))
 		goto out;
 
 	if (max_links && new_dir != old_dir) {
@@ -4164,6 +4168,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (is_dir)
 			target->i_flags |= S_DEAD;
 		dont_mount(new_dentry);
+		detach_mounts(new_dentry);
 	}
 	if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) {
 		if (!(flags & RENAME_EXCHANGE))
diff --git a/fs/namespace.c b/fs/namespace.c
index ef42d9bee212..fbba8b17330d 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -23,6 +23,7 @@
 #include <linux/proc_ns.h>
 #include <linux/magic.h>
 #include <linux/bootmem.h>
+#include <linux/task_work.h>
 #include "pnode.h"
 #include "internal.h"
 
@@ -224,6 +225,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_share);
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
+		INIT_HLIST_NODE(&mnt->mnt_mp_list);
 #ifdef CONFIG_FSNOTIFY
 		INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
 #endif
@@ -666,11 +668,45 @@ struct vfsmount *lookup_mnt(struct path *path)
 	return m;
 }
 
-static struct mountpoint *new_mountpoint(struct dentry *dentry)
+/*
+ * __is_local_mountpoint - Test to see if dentry is a mountpoint in the
+ *                         current mount namespace.
+ *
+ * The common case is dentries are not mountpoints at all and that
+ * test is handled inline.  For the slow case when we are actually
+ * dealing with a mountpoint of some kind, walk through all of the
+ * mounts in the current mount namespace and test to see if the dentry
+ * is a mountpoint.
+ *
+ * The mount_hashtable is not usable in the context because we
+ * need to identify all mounts that may be in the current mount
+ * namespace not just a mount that happens to have some specified
+ * parent mount.
+ */
+bool __is_local_mountpoint(struct dentry *dentry)
+{
+	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+	struct mount *mnt;
+	bool is_covered = false;
+
+	if (!d_mountpoint(dentry))
+		goto out;
+
+	down_read(&namespace_sem);
+	list_for_each_entry(mnt, &ns->list, mnt_list) {
+		is_covered = (mnt->mnt_mountpoint == dentry);
+		if (is_covered)
+			break;
+	}
+	up_read(&namespace_sem);
+out:
+	return is_covered;
+}
+
+static struct mountpoint *lookup_mountpoint(struct dentry *dentry)
 {
 	struct hlist_head *chain = mp_hash(dentry);
 	struct mountpoint *mp;
-	int ret;
 
 	hlist_for_each_entry(mp, chain, m_hash) {
 		if (mp->m_dentry == dentry) {
@@ -681,6 +717,14 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry)
 			return mp;
 		}
 	}
+	return NULL;
+}
+
+static struct mountpoint *new_mountpoint(struct dentry *dentry)
+{
+	struct hlist_head *chain = mp_hash(dentry);
+	struct mountpoint *mp;
+	int ret;
 
 	mp = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
 	if (!mp)
@@ -695,6 +739,7 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry)
 	mp->m_dentry = dentry;
 	mp->m_count = 1;
 	hlist_add_head(&mp->m_hash, chain);
+	INIT_HLIST_HEAD(&mp->m_list);
 	return mp;
 }
 
@@ -702,6 +747,7 @@ static void put_mountpoint(struct mountpoint *mp)
 {
 	if (!--mp->m_count) {
 		struct dentry *dentry = mp->m_dentry;
+		BUG_ON(!hlist_empty(&mp->m_list));
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags &= ~DCACHE_MOUNTED;
 		spin_unlock(&dentry->d_lock);
@@ -748,6 +794,7 @@ static void detach_mnt(struct mount *mnt, struct path *old_path)
 	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
 	list_del_init(&mnt->mnt_child);
 	hlist_del_init_rcu(&mnt->mnt_hash);
+	hlist_del_init(&mnt->mnt_mp_list);
 	put_mountpoint(mnt->mnt_mp);
 	mnt->mnt_mp = NULL;
 }
@@ -764,6 +811,7 @@ void mnt_set_mountpoint(struct mount *mnt,
 	child_mnt->mnt_mountpoint = dget(mp->m_dentry);
 	child_mnt->mnt_parent = mnt;
 	child_mnt->mnt_mp = mp;
+	hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
 }
 
 /*
@@ -957,6 +1005,46 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	return ERR_PTR(err);
 }
 
+static void cleanup_mnt(struct mount *mnt)
+{
+	/*
+	 * This probably indicates that somebody messed
+	 * up a mnt_want/drop_write() pair.  If this
+	 * happens, the filesystem was probably unable
+	 * to make r/w->r/o transitions.
+	 */
+	/*
+	 * The locking used to deal with mnt_count decrement provides barriers,
+	 * so mnt_get_writers() below is safe.
+	 */
+	WARN_ON(mnt_get_writers(mnt));
+	if (unlikely(mnt->mnt_pins.first))
+		mnt_pin_kill(mnt);
+	fsnotify_vfsmount_delete(&mnt->mnt);
+	dput(mnt->mnt.mnt_root);
+	deactivate_super(mnt->mnt.mnt_sb);
+	mnt_free_id(mnt);
+	call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt);
+}
+
+static void __cleanup_mnt(struct rcu_head *head)
+{
+	cleanup_mnt(container_of(head, struct mount, mnt_rcu));
+}
+
+static LLIST_HEAD(delayed_mntput_list);
+static void delayed_mntput(struct work_struct *unused)
+{
+	struct llist_node *node = llist_del_all(&delayed_mntput_list);
+	struct llist_node *next;
+
+	for (; node; node = next) {
+		next = llist_next(node);
+		cleanup_mnt(llist_entry(node, struct mount, mnt_llist));
+	}
+}
+static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
+
 static void mntput_no_expire(struct mount *mnt)
 {
 	rcu_read_lock();
@@ -982,24 +1070,18 @@ static void mntput_no_expire(struct mount *mnt)
 	list_del(&mnt->mnt_instance);
 	unlock_mount_hash();
 
-	/*
-	 * This probably indicates that somebody messed
-	 * up a mnt_want/drop_write() pair.  If this
-	 * happens, the filesystem was probably unable
-	 * to make r/w->r/o transitions.
-	 */
-	/*
-	 * The locking used to deal with mnt_count decrement provides barriers,
-	 * so mnt_get_writers() below is safe.
-	 */
-	WARN_ON(mnt_get_writers(mnt));
-	if (unlikely(mnt->mnt_pins.first))
-		mnt_pin_kill(mnt);
-	fsnotify_vfsmount_delete(&mnt->mnt);
-	dput(mnt->mnt.mnt_root);
-	deactivate_super(mnt->mnt.mnt_sb);
-	mnt_free_id(mnt);
-	call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt);
+	if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) {
+		struct task_struct *task = current;
+		if (likely(!(task->flags & PF_KTHREAD))) {
+			init_task_work(&mnt->mnt_rcu, __cleanup_mnt);
+			if (!task_work_add(task, &mnt->mnt_rcu, true))
+				return;
+		}
+		if (llist_add(&mnt->mnt_llist, &delayed_mntput_list))
+			schedule_delayed_work(&delayed_mntput_work, 1);
+		return;
+	}
+	cleanup_mnt(mnt);
 }
 
 void mntput(struct vfsmount *mnt)
@@ -1272,6 +1354,7 @@ void umount_tree(struct mount *mnt, int how)
 		if (how < 2)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
 		if (mnt_has_parent(p)) {
+			hlist_del_init(&p->mnt_mp_list);
 			put_mountpoint(p->mnt_mp);
 			mnt_add_count(p->mnt_parent, -1);
 			/* move the reference to mountpoint into ->mnt_ex_mountpoint */
@@ -1356,6 +1439,8 @@ static int do_umount(struct mount *mnt, int flags)
 		 * Special case for "unmounting" root ...
 		 * we just try to remount it readonly.
 		 */
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
 		down_write(&sb->s_umount);
 		if (!(sb->s_flags & MS_RDONLY))
 			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
@@ -1385,6 +1470,37 @@ static int do_umount(struct mount *mnt, int flags)
 	return retval;
 }
 
+/*
+ * __detach_mounts - lazily unmount all mounts on the specified dentry
+ *
+ * During unlink, rmdir, and d_drop it is possible to loose the path
+ * to an existing mountpoint, and wind up leaking the mount.
+ * detach_mounts allows lazily unmounting those mounts instead of
+ * leaking them.
+ *
+ * The caller may hold dentry->d_inode->i_mutex.
+ */
+void __detach_mounts(struct dentry *dentry)
+{
+	struct mountpoint *mp;
+	struct mount *mnt;
+
+	namespace_lock();
+	mp = lookup_mountpoint(dentry);
+	if (!mp)
+		goto out_unlock;
+
+	lock_mount_hash();
+	while (!hlist_empty(&mp->m_list)) {
+		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
+		umount_tree(mnt, 2);
+	}
+	unlock_mount_hash();
+	put_mountpoint(mp);
+out_unlock:
+	namespace_unlock();
+}
+
 /* 
  * Is the caller allowed to modify his namespace?
  */
@@ -1742,7 +1858,9 @@ retry:
 	namespace_lock();
 	mnt = lookup_mnt(path);
 	if (likely(!mnt)) {
-		struct mountpoint *mp = new_mountpoint(dentry);
+		struct mountpoint *mp = lookup_mountpoint(dentry);
+		if (!mp)
+			mp = new_mountpoint(dentry);
 		if (IS_ERR(mp)) {
 			namespace_unlock();
 			mutex_unlock(&dentry->d_inode->i_mutex);
@@ -2398,21 +2516,9 @@ int copy_mount_options(const void __user * data, unsigned long *where)
 	return 0;
 }
 
-int copy_mount_string(const void __user *data, char **where)
+char *copy_mount_string(const void __user *data)
 {
-	char *tmp;
-
-	if (!data) {
-		*where = NULL;
-		return 0;
-	}
-
-	tmp = strndup_user(data, PAGE_SIZE);
-	if (IS_ERR(tmp))
-		return PTR_ERR(tmp);
-
-	*where = tmp;
-	return 0;
+	return data ? strndup_user(data, PAGE_SIZE) : NULL;
 }
 
 /*
@@ -2429,7 +2535,7 @@ int copy_mount_string(const void __user *data, char **where)
  * Therefore, if this magic number is present, it carries no information
  * and must be discarded.
  */
-long do_mount(const char *dev_name, const char *dir_name,
+long do_mount(const char *dev_name, const char __user *dir_name,
 		const char *type_page, unsigned long flags, void *data_page)
 {
 	struct path path;
@@ -2441,15 +2547,11 @@ long do_mount(const char *dev_name, const char *dir_name,
 		flags &= ~MS_MGC_MSK;
 
 	/* Basic sanity checks */
-
-	if (!dir_name || !*dir_name || !memchr(dir_name, 0, PAGE_SIZE))
-		return -EINVAL;
-
 	if (data_page)
 		((char *)data_page)[PAGE_SIZE - 1] = 0;
 
 	/* ... and get the mountpoint */
-	retval = kern_path(dir_name, LOOKUP_FOLLOW, &path);
+	retval = user_path(dir_name, &path);
 	if (retval)
 		return retval;
 
@@ -2674,37 +2776,30 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 {
 	int ret;
 	char *kernel_type;
-	struct filename *kernel_dir;
 	char *kernel_dev;
 	unsigned long data_page;
 
-	ret = copy_mount_string(type, &kernel_type);
-	if (ret < 0)
+	kernel_type = copy_mount_string(type);
+	ret = PTR_ERR(kernel_type);
+	if (IS_ERR(kernel_type))
 		goto out_type;
 
-	kernel_dir = getname(dir_name);
-	if (IS_ERR(kernel_dir)) {
-		ret = PTR_ERR(kernel_dir);
-		goto out_dir;
-	}
-
-	ret = copy_mount_string(dev_name, &kernel_dev);
-	if (ret < 0)
+	kernel_dev = copy_mount_string(dev_name);
+	ret = PTR_ERR(kernel_dev);
+	if (IS_ERR(kernel_dev))
 		goto out_dev;
 
 	ret = copy_mount_options(data, &data_page);
 	if (ret < 0)
 		goto out_data;
 
-	ret = do_mount(kernel_dev, kernel_dir->name, kernel_type, flags,
+	ret = do_mount(kernel_dev, dir_name, kernel_type, flags,
 		(void *) data_page);
 
 	free_page(data_page);
 out_data:
 	kfree(kernel_dev);
 out_dev:
-	putname(kernel_dir);
-out_dir:
 	kfree(kernel_type);
 out_type:
 	return ret;
@@ -2820,6 +2915,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	/* make sure we can reach put_old from new_root */
 	if (!is_path_reachable(old_mnt, old.dentry, &new))
 		goto out4;
+	/* make certain new is below the root */
+	if (!is_path_reachable(new_mnt, new.dentry, &root))
+		goto out4;
 	root_mp->m_count++; /* pin it so it won't go away */
 	lock_mount_hash();
 	detach_mnt(new_mnt, &parent_path);
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 08b8ea8c353e..7cb751dfbeef 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -388,7 +388,6 @@ static struct dentry *
 ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos)
 {
 	struct dentry *dent = dentry;
-	struct list_head *next;
 
 	if (d_validate(dent, parent)) {
 		if (dent->d_name.len <= NCP_MAXPATHLEN &&
@@ -404,9 +403,7 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos)
 
 	/* If a pointer is invalid, we search the dentry. */
 	spin_lock(&parent->d_lock);
-	next = parent->d_subdirs.next;
-	while (next != &parent->d_subdirs) {
-		dent = list_entry(next, struct dentry, d_u.d_child);
+	list_for_each_entry(dent, &parent->d_subdirs, d_u.d_child) {
 		if ((unsigned long)dent->d_fsdata == fpos) {
 			if (dent->d_inode)
 				dget(dent);
@@ -415,7 +412,6 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos)
 			spin_unlock(&parent->d_lock);
 			goto out;
 		}
-		next = next->next;
 	}
 	spin_unlock(&parent->d_lock);
 	return NULL;
@@ -1182,9 +1178,6 @@ static int day_n[] =
 {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 0, 0, 0, 0};
 /* Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec */
 
-
-extern struct timezone sys_tz;
-
 static int utc2local(int time)
 {
 	return time - sys_tz.tz_minuteswest * 60;
diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h
index 32c06587351a..52cb19d66ecb 100644
--- a/fs/ncpfs/ncplib_kernel.h
+++ b/fs/ncpfs/ncplib_kernel.h
@@ -188,20 +188,14 @@ static inline void
 ncp_renew_dentries(struct dentry *parent)
 {
 	struct ncp_server *server = NCP_SERVER(parent->d_inode);
-	struct list_head *next;
 	struct dentry *dentry;
 
 	spin_lock(&parent->d_lock);
-	next = parent->d_subdirs.next;
-	while (next != &parent->d_subdirs) {
-		dentry = list_entry(next, struct dentry, d_u.d_child);
-
+	list_for_each_entry(dentry, &parent->d_subdirs, d_u.d_child) {
 		if (dentry->d_fsdata == NULL)
 			ncp_age_dentry(server, dentry);
 		else
 			ncp_new_dentry(dentry);
-
-		next = next->next;
 	}
 	spin_unlock(&parent->d_lock);
 }
@@ -210,16 +204,12 @@ static inline void
 ncp_invalidate_dircache_entries(struct dentry *parent)
 {
 	struct ncp_server *server = NCP_SERVER(parent->d_inode);
-	struct list_head *next;
 	struct dentry *dentry;
 
 	spin_lock(&parent->d_lock);
-	next = parent->d_subdirs.next;
-	while (next != &parent->d_subdirs) {
-		dentry = list_entry(next, struct dentry, d_u.d_child);
+	list_for_each_entry(dentry, &parent->d_subdirs, d_u.d_child) {
 		dentry->d_fsdata = NULL;
 		ncp_age_dentry(server, dentry);
-		next = next->next;
 	}
 	spin_unlock(&parent->d_lock);
 }
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 4782e0840dcc..04cb830fa09f 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -28,6 +28,7 @@ nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o
 nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
 nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
 nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
+nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
 obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index 8d04bda2bd2e..e966c023b1b7 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -92,7 +92,6 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
 
 	set_current_state(TASK_UNINTERRUPTIBLE);
 	schedule();
-	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(&nn->bl_wq, &wq);
 
 	if (reply->status != BL_DEVICE_REQUEST_PROC) {
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 36d921f0c602..06e8cfcbb670 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -486,8 +486,7 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 				nfs_setsecurity(dentry->d_inode, entry->fattr, entry->label);
 			goto out;
 		} else {
-			if (d_invalidate(dentry) != 0)
-				goto out;
+			d_invalidate(dentry);
 			dput(dentry);
 		}
 	}
@@ -1211,10 +1210,6 @@ out_zap_parent:
 		if (IS_ROOT(dentry))
 			goto out_valid;
 	}
-	/* If we have submounts, don't unhash ! */
-	if (check_submounts_and_drop(dentry) != 0)
-		goto out_valid;
-
 	dput(parent);
 	dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n",
 			__func__, dentry);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index dda4b8667c02..20cffc830468 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -220,11 +220,9 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t
 #else
 	VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
 
-	if (rw == READ || rw == KERNEL_READ)
-		return nfs_file_direct_read(iocb, iter, pos,
-				rw == READ ? true : false);
-	return nfs_file_direct_write(iocb, iter, pos,
-				rw == WRITE ? true : false);
+	if (rw == READ)
+		return nfs_file_direct_read(iocb, iter, pos);
+	return nfs_file_direct_write(iocb, iter, pos);
 #endif /* CONFIG_NFS_SWAP */
 }
 
@@ -510,7 +508,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
  * cache.
  */
 ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
-				loff_t pos, bool uio)
+				loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
@@ -879,7 +877,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
  * is no atomic O_APPEND write facility in the NFS protocol.
  */
 ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
-				loff_t pos, bool uio)
+				loff_t pos)
 {
 	ssize_t result = -EINVAL;
 	struct file *file = iocb->ki_filp;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 6920127c5eb7..2ab6f00dba5b 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -172,7 +172,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 	ssize_t result;
 
 	if (iocb->ki_filp->f_flags & O_DIRECT)
-		return nfs_file_direct_read(iocb, to, iocb->ki_pos, true);
+		return nfs_file_direct_read(iocb, to, iocb->ki_pos);
 
 	dprintk("NFS: read(%pD2, %zu@%lu)\n",
 		iocb->ki_filp,
@@ -676,7 +676,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 		return result;
 
 	if (file->f_flags & O_DIRECT)
-		return nfs_file_direct_write(iocb, from, pos, true);
+		return nfs_file_direct_write(iocb, from, pos);
 
 	dprintk("NFS: write(%pD2, %zu@%Ld)\n",
 		file, count, (long long) pos);
@@ -919,17 +919,6 @@ int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 }
 EXPORT_SYMBOL_GPL(nfs_flock);
 
-/*
- * There is no protocol support for leases, so we have no way to implement
- * them correctly in the face of opens by other clients.
- */
-int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
-{
-	dprintk("NFS: setlease(%pD2, arg=%ld)\n", file, arg);
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(nfs_setlease);
-
 const struct file_operations nfs_file_operations = {
 	.llseek		= nfs_file_llseek,
 	.read		= new_sync_read,
@@ -946,6 +935,6 @@ const struct file_operations nfs_file_operations = {
 	.splice_read	= nfs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
-	.setlease	= nfs_setlease,
+	.setlease	= simple_nosetlease,
 };
 EXPORT_SYMBOL_GPL(nfs_file_operations);
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index abc5056999d6..46fab1cb455a 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -1031,7 +1031,7 @@ filelayout_clear_request_commit(struct nfs_page *req,
 	}
 out:
 	nfs_request_remove_commit_list(req, cinfo);
-	pnfs_put_lseg_async(freeme);
+	pnfs_put_lseg_locked(freeme);
 }
 
 static void
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index 7dd55b745c4d..2f5db844c172 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -177,7 +177,6 @@ static struct key_type key_type_id_resolver = {
 	.preparse	= user_preparse,
 	.free_preparse	= user_free_preparse,
 	.instantiate	= generic_key_instantiate,
-	.match		= user_match,
 	.revoke		= user_revoke,
 	.destroy	= user_destroy,
 	.describe	= user_describe,
@@ -401,7 +400,6 @@ static struct key_type key_type_id_resolver_legacy = {
 	.preparse	= user_preparse,
 	.free_preparse	= user_free_preparse,
 	.instantiate	= generic_key_instantiate,
-	.match		= user_match,
 	.revoke		= user_revoke,
 	.destroy	= user_destroy,
 	.describe	= user_describe,
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 141c9f4a40de..6388a59f2add 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -718,6 +718,7 @@ struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx)
 	kfree(new);
 	return res;
 }
+EXPORT_SYMBOL_GPL(nfs_get_lock_context);
 
 void nfs_put_lock_context(struct nfs_lock_context *l_ctx)
 {
@@ -730,6 +731,7 @@ void nfs_put_lock_context(struct nfs_lock_context *l_ctx)
 	spin_unlock(&inode->i_lock);
 	kfree(l_ctx);
 }
+EXPORT_SYMBOL_GPL(nfs_put_lock_context);
 
 /**
  * nfs_close_context - Common close_context() routine NFSv2/v3
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 14ae6f20a172..efaa31c70fbe 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -339,7 +339,6 @@ int nfs_file_release(struct inode *, struct file *);
 int nfs_lock(struct file *, int, struct file_lock *);
 int nfs_flock(struct file *, int, struct file_lock *);
 int nfs_check_flags(int);
-int nfs_setlease(struct file *, long, struct file_lock **);
 
 /* inode.c */
 extern struct workqueue_struct *nfsiod_workqueue;
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
new file mode 100644
index 000000000000..d10333a197bf
--- /dev/null
+++ b/fs/nfs/nfs42.h
@@ -0,0 +1,14 @@
+/*
+ * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com>
+ */
+
+#ifndef __LINUX_FS_NFS_NFS4_2_H
+#define __LINUX_FS_NFS_NFS4_2_H
+
+/* nfs4.2proc.c */
+loff_t nfs42_proc_llseek(struct file *, loff_t, int);
+
+/* nfs4.2xdr.h */
+extern struct rpc_procinfo nfs4_2_procedures[];
+
+#endif /* __LINUX_FS_NFS_NFS4_2_H */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
new file mode 100644
index 000000000000..0886f1db5917
--- /dev/null
+++ b/fs/nfs/nfs42proc.c
@@ -0,0 +1,69 @@
+/*
+ * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com>
+ */
+#include <linux/fs.h>
+#include <linux/sunrpc/sched.h>
+#include <linux/nfs.h>
+#include <linux/nfs3.h>
+#include <linux/nfs4.h>
+#include <linux/nfs_xdr.h>
+#include <linux/nfs_fs.h>
+#include "nfs4_fs.h"
+#include "nfs42.h"
+
+static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file,
+				fmode_t fmode)
+{
+	struct nfs_open_context *open;
+	struct nfs_lock_context *lock;
+	int ret;
+
+	open = get_nfs_open_context(nfs_file_open_context(file));
+	lock = nfs_get_lock_context(open);
+	if (IS_ERR(lock)) {
+		put_nfs_open_context(open);
+		return PTR_ERR(lock);
+	}
+
+	ret = nfs4_set_rw_stateid(dst, open, lock, fmode);
+
+	nfs_put_lock_context(lock);
+	put_nfs_open_context(open);
+	return ret;
+}
+
+loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+{
+	struct inode *inode = file_inode(filep);
+	struct nfs42_seek_args args = {
+		.sa_fh		= NFS_FH(inode),
+		.sa_offset	= offset,
+		.sa_what	= (whence == SEEK_HOLE) ?
+					NFS4_CONTENT_HOLE : NFS4_CONTENT_DATA,
+	};
+	struct nfs42_seek_res res;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SEEK],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	struct nfs_server *server = NFS_SERVER(inode);
+	int status;
+
+	if (!(server->caps & NFS_CAP_SEEK))
+		return -ENOTSUPP;
+
+	status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ);
+	if (status)
+		return status;
+
+	nfs_wb_all(inode);
+	status = nfs4_call_sync(server->client, server, &msg,
+				&args.seq_args, &res.seq_res, 0);
+	if (status == -ENOTSUPP)
+		server->caps &= ~NFS_CAP_SEEK;
+	if (status)
+		return status;
+
+	return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
+}
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
new file mode 100644
index 000000000000..c90469b604b8
--- /dev/null
+++ b/fs/nfs/nfs42xdr.c
@@ -0,0 +1,98 @@
+/*
+ * Copyright (c) 2014 Anna Schumaker <Anna.Schumaker@Netapp.com>
+ */
+#ifndef __LINUX_FS_NFS_NFS4_2XDR_H
+#define __LINUX_FS_NFS_NFS4_2XDR_H
+
+#define encode_seek_maxsz		(op_encode_hdr_maxsz + \
+					 encode_stateid_maxsz + \
+					 2 /* offset */ + \
+					 1 /* whence */)
+#define decode_seek_maxsz		(op_decode_hdr_maxsz + \
+					 1 /* eof */ + \
+					 1 /* whence */ + \
+					 2 /* offset */ + \
+					 2 /* length */)
+
+#define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_seek_maxsz)
+#define NFS4_dec_seek_sz		(compound_decode_hdr_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_seek_maxsz)
+
+
+static void encode_seek(struct xdr_stream *xdr,
+			struct nfs42_seek_args *args,
+			struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_SEEK, decode_seek_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->sa_stateid);
+	encode_uint64(xdr, args->sa_offset);
+	encode_uint32(xdr, args->sa_what);
+}
+
+/*
+ * Encode SEEK request
+ */
+static void nfs4_xdr_enc_seek(struct rpc_rqst *req,
+			      struct xdr_stream *xdr,
+			      struct nfs42_seek_args *args)
+{
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->sa_fh, &hdr);
+	encode_seek(xdr, args, &hdr);
+	encode_nops(&hdr);
+}
+
+static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res)
+{
+	int status;
+	__be32 *p;
+
+	status = decode_op_hdr(xdr, OP_SEEK);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4 + 8);
+	if (unlikely(!p))
+		goto out_overflow;
+
+	res->sr_eof = be32_to_cpup(p++);
+	p = xdr_decode_hyper(p, &res->sr_offset);
+	return 0;
+
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
+/*
+ * Decode SEEK request
+ */
+static int nfs4_xdr_dec_seek(struct rpc_rqst *rqstp,
+			     struct xdr_stream *xdr,
+			     struct nfs42_seek_res *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_seek(xdr, res);
+out:
+	return status;
+}
+#endif /* __LINUX_FS_NFS_NFS4_2XDR_H */
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index a8b855ab4e22..be6cac37ea10 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -226,6 +226,9 @@ int nfs4_replace_transport(struct nfs_server *server,
 				const struct nfs4_fs_locations *locations);
 
 /* nfs4proc.c */
+extern int nfs4_call_sync(struct rpc_clnt *, struct nfs_server *,
+			  struct rpc_message *, struct nfs4_sequence_args *,
+			  struct nfs4_sequence_res *, int);
 extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *);
 extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *);
 extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *, bool);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index a816f0627a6c..c51fb4db9bfe 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -8,6 +8,10 @@
 #include "fscache.h"
 #include "pnfs.h"
 
+#ifdef CONFIG_NFS_V4_2
+#include "nfs42.h"
+#endif
+
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
 static int
@@ -115,8 +119,29 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	return ret;
 }
 
+#ifdef CONFIG_NFS_V4_2
+static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
+{
+	loff_t ret;
+
+	switch (whence) {
+	case SEEK_HOLE:
+	case SEEK_DATA:
+		ret = nfs42_proc_llseek(filep, offset, whence);
+		if (ret != -ENOTSUPP)
+			return ret;
+	default:
+		return nfs_file_llseek(filep, offset, whence);
+	}
+}
+#endif /* CONFIG_NFS_V4_2 */
+
 const struct file_operations nfs4_file_operations = {
+#ifdef CONFIG_NFS_V4_2
+	.llseek		= nfs4_file_llseek,
+#else
 	.llseek		= nfs_file_llseek,
+#endif
 	.read		= new_sync_read,
 	.write		= new_sync_write,
 	.read_iter	= nfs_file_read,
@@ -131,5 +156,5 @@ const struct file_operations nfs4_file_operations = {
 	.splice_read	= nfs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
-	.setlease	= nfs_setlease,
+	.setlease	= simple_nosetlease,
 };
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 5aa55c132aa2..405bd95c1f58 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -885,7 +885,6 @@ static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
 	return ret;
 }
 
-static
 int nfs4_call_sync(struct rpc_clnt *clnt,
 		   struct nfs_server *server,
 		   struct rpc_message *msg,
@@ -8409,7 +8408,8 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
-		| NFS_CAP_ATOMIC_OPEN_V1,
+		| NFS_CAP_ATOMIC_OPEN_V1
+		| NFS_CAP_SEEK,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 005d03c5d274..206c08a60c7f 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7321,6 +7321,10 @@ nfs4_stat_to_errno(int stat)
 	return -stat;
 }
 
+#ifdef CONFIG_NFS_V4_2
+#include "nfs42xdr.c"
+#endif /* CONFIG_NFS_V4_2 */
+
 #define PROC(proc, argtype, restype)				\
 [NFSPROC4_CLNT_##proc] = {					\
 	.p_proc   = NFSPROC4_COMPOUND,				\
@@ -7388,6 +7392,9 @@ struct rpc_procinfo	nfs4_procedures[] = {
 			enc_bind_conn_to_session, dec_bind_conn_to_session),
 	PROC(DESTROY_CLIENTID,	enc_destroy_clientid,	dec_destroy_clientid),
 #endif /* CONFIG_NFS_V4_1 */
+#ifdef CONFIG_NFS_V4_2
+	PROC(SEEK,		enc_seek,		dec_seek),
+#endif /* CONFIG_NFS_V4_2 */
 };
 
 const struct rpc_version nfs_version4 = {
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 94e16ec88312..ed0db61f8543 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -526,7 +526,8 @@ EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
  */
 void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr)
 {
-	put_nfs_open_context(hdr->args.context);
+	if (hdr->args.context)
+		put_nfs_open_context(hdr->args.context);
 	if (hdr->page_array.pagevec != hdr->page_array.page_array)
 		kfree(hdr->page_array.pagevec);
 }
@@ -751,12 +752,11 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 		nfs_list_remove_request(req);
 		nfs_list_add_request(req, &hdr->pages);
 
-		if (WARN_ON_ONCE(pageused >= pagecount))
-			return nfs_pgio_error(desc, hdr);
-
 		if (!last_page || last_page != req->wb_page) {
-			*pages++ = last_page = req->wb_page;
 			pageused++;
+			if (pageused > pagecount)
+				break;
+			*pages++ = last_page = req->wb_page;
 		}
 	}
 	if (WARN_ON_ONCE(pageused != pagecount))
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 76de7f568119..0a5dda4d85c2 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -361,22 +361,43 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 }
 EXPORT_SYMBOL_GPL(pnfs_put_lseg);
 
-static void pnfs_put_lseg_async_work(struct work_struct *work)
+static void pnfs_free_lseg_async_work(struct work_struct *work)
 {
 	struct pnfs_layout_segment *lseg;
+	struct pnfs_layout_hdr *lo;
 
 	lseg = container_of(work, struct pnfs_layout_segment, pls_work);
+	lo = lseg->pls_layout;
 
-	pnfs_put_lseg(lseg);
+	pnfs_free_lseg(lseg);
+	pnfs_put_layout_hdr(lo);
 }
 
-void
-pnfs_put_lseg_async(struct pnfs_layout_segment *lseg)
+static void pnfs_free_lseg_async(struct pnfs_layout_segment *lseg)
 {
-	INIT_WORK(&lseg->pls_work, pnfs_put_lseg_async_work);
+	INIT_WORK(&lseg->pls_work, pnfs_free_lseg_async_work);
 	schedule_work(&lseg->pls_work);
 }
-EXPORT_SYMBOL_GPL(pnfs_put_lseg_async);
+
+void
+pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg)
+{
+	if (!lseg)
+		return;
+
+	assert_spin_locked(&lseg->pls_layout->plh_inode->i_lock);
+
+	dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg,
+		atomic_read(&lseg->pls_refcount),
+		test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
+	if (atomic_dec_and_test(&lseg->pls_refcount)) {
+		struct pnfs_layout_hdr *lo = lseg->pls_layout;
+		pnfs_get_layout_hdr(lo);
+		pnfs_layout_remove_lseg(lo, lseg);
+		pnfs_free_lseg_async(lseg);
+	}
+}
+EXPORT_SYMBOL_GPL(pnfs_put_lseg_locked);
 
 static u64
 end_offset(u64 start, u64 len)
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 693ce42ec683..9ae5b765b073 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -190,7 +190,7 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 /* pnfs.c */
 void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo);
 void pnfs_put_lseg(struct pnfs_layout_segment *lseg);
-void pnfs_put_lseg_async(struct pnfs_layout_segment *lseg);
+void pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg);
 
 void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
 void unset_pnfs_layoutdriver(struct nfs_server *);
@@ -270,7 +270,6 @@ nfs4_find_get_deviceid(struct nfs_server *server,
 void nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
 void nfs4_init_deviceid_node(struct nfs4_deviceid_node *, struct nfs_server *,
 			     const struct nfs4_deviceid *);
-struct nfs4_deviceid_node *nfs4_insert_deviceid_node(struct nfs4_deviceid_node *);
 bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
 void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node);
 bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node);
@@ -446,10 +445,6 @@ static inline void pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 {
 }
 
-static inline void pnfs_put_lseg_async(struct pnfs_layout_segment *lseg)
-{
-}
-
 static inline int pnfs_return_layout(struct inode *ino)
 {
 	return 0;
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index ea95a2bc21b5..a25490ae6c62 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -675,7 +675,6 @@ __cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg)
 	}
 
 	schedule();
-	set_current_state(TASK_RUNNING);
 
 	if (msg.errno < 0)
 		ret = msg.errno;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 5c0cac173068..e9c3afe4b5d3 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -218,6 +218,13 @@ static void nfsd4_put_session(struct nfsd4_session *ses)
 	spin_unlock(&nn->client_lock);
 }
 
+static inline struct nfs4_stateowner *
+nfs4_get_stateowner(struct nfs4_stateowner *sop)
+{
+	atomic_inc(&sop->so_count);
+	return sop;
+}
+
 static int
 same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner)
 {
@@ -237,10 +244,8 @@ find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open,
 			    so_strhash) {
 		if (!so->so_is_open_owner)
 			continue;
-		if (same_owner_str(so, &open->op_owner)) {
-			atomic_inc(&so->so_count);
-			return openowner(so);
-		}
+		if (same_owner_str(so, &open->op_owner))
+			return openowner(nfs4_get_stateowner(so));
 	}
 	return NULL;
 }
@@ -678,18 +683,14 @@ nfs4_put_stid(struct nfs4_stid *s)
 static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 {
 	struct file *filp = NULL;
-	struct file_lock *fl;
 
 	spin_lock(&fp->fi_lock);
-	if (fp->fi_lease && atomic_dec_and_test(&fp->fi_delegees)) {
+	if (fp->fi_deleg_file && atomic_dec_and_test(&fp->fi_delegees))
 		swap(filp, fp->fi_deleg_file);
-		fl = fp->fi_lease;
-		fp->fi_lease = NULL;
-	}
 	spin_unlock(&fp->fi_lock);
 
 	if (filp) {
-		vfs_setlease(filp, F_UNLCK, &fl);
+		vfs_setlease(filp, F_UNLCK, NULL, NULL);
 		fput(filp);
 	}
 }
@@ -1655,7 +1656,7 @@ __destroy_client(struct nfs4_client *clp)
 	}
 	while (!list_empty(&clp->cl_openowners)) {
 		oo = list_entry(clp->cl_openowners.next, struct nfs4_openowner, oo_perclient);
-		atomic_inc(&oo->oo_owner.so_count);
+		nfs4_get_stateowner(&oo->oo_owner);
 		release_openowner(oo);
 	}
 	nfsd4_shutdown_callback(clp);
@@ -3067,8 +3068,8 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct knfsd_fh *fh)
 	INIT_LIST_HEAD(&fp->fi_stateids);
 	INIT_LIST_HEAD(&fp->fi_delegations);
 	fh_copy_shallow(&fp->fi_fhandle, fh);
+	fp->fi_deleg_file = NULL;
 	fp->fi_had_conflict = false;
-	fp->fi_lease = NULL;
 	fp->fi_share_deny = 0;
 	memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
 	memset(fp->fi_access, 0, sizeof(fp->fi_access));
@@ -3136,8 +3137,7 @@ static void nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate,
 {
 	if (!nfsd4_has_session(cstate)) {
 		mutex_lock(&so->so_replay.rp_mutex);
-		cstate->replay_owner = so;
-		atomic_inc(&so->so_count);
+		cstate->replay_owner = nfs4_get_stateowner(so);
 	}
 }
 
@@ -3236,8 +3236,7 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
 	atomic_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_OPEN_STID;
 	INIT_LIST_HEAD(&stp->st_locks);
-	stp->st_stateowner = &oo->oo_owner;
-	atomic_inc(&stp->st_stateowner->so_count);
+	stp->st_stateowner = nfs4_get_stateowner(&oo->oo_owner);
 	get_nfs4_file(fp);
 	stp->st_stid.sc_file = fp;
 	stp->st_access_bmap = 0;
@@ -3434,18 +3433,20 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 }
 
 /* Called from break_lease() with i_lock held. */
-static void nfsd_break_deleg_cb(struct file_lock *fl)
+static bool
+nfsd_break_deleg_cb(struct file_lock *fl)
 {
+	bool ret = false;
 	struct nfs4_file *fp = (struct nfs4_file *)fl->fl_owner;
 	struct nfs4_delegation *dp;
 
 	if (!fp) {
 		WARN(1, "(%p)->fl_owner NULL\n", fl);
-		return;
+		return ret;
 	}
 	if (fp->fi_had_conflict) {
 		WARN(1, "duplicate break on %p\n", fp);
-		return;
+		return ret;
 	}
 	/*
 	 * We don't want the locks code to timeout the lease for us;
@@ -3457,24 +3458,23 @@ static void nfsd_break_deleg_cb(struct file_lock *fl)
 	spin_lock(&fp->fi_lock);
 	fp->fi_had_conflict = true;
 	/*
-	 * If there are no delegations on the list, then we can't count on this
-	 * lease ever being cleaned up. Set the fl_break_time to jiffies so that
-	 * time_out_leases will do it ASAP. The fact that fi_had_conflict is now
-	 * true should keep any new delegations from being hashed.
+	 * If there are no delegations on the list, then return true
+	 * so that the lease code will go ahead and delete it.
 	 */
 	if (list_empty(&fp->fi_delegations))
-		fl->fl_break_time = jiffies;
+		ret = true;
 	else
 		list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
 			nfsd_break_one_deleg(dp);
 	spin_unlock(&fp->fi_lock);
+	return ret;
 }
 
-static
-int nfsd_change_deleg_cb(struct file_lock **onlist, int arg)
+static int
+nfsd_change_deleg_cb(struct file_lock **onlist, int arg, struct list_head *dispose)
 {
 	if (arg & F_UNLCK)
-		return lease_modify(onlist, arg);
+		return lease_modify(onlist, arg, dispose);
 	else
 		return -EAGAIN;
 }
@@ -3820,7 +3820,7 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_file *fp, int flag)
 static int nfs4_setlease(struct nfs4_delegation *dp)
 {
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
-	struct file_lock *fl;
+	struct file_lock *fl, *ret;
 	struct file *filp;
 	int status = 0;
 
@@ -3834,11 +3834,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 		return -EBADF;
 	}
 	fl->fl_file = filp;
-	status = vfs_setlease(filp, fl->fl_type, &fl);
-	if (status) {
+	ret = fl;
+	status = vfs_setlease(filp, fl->fl_type, &fl, NULL);
+	if (fl)
 		locks_free_lock(fl);
+	if (status)
 		goto out_fput;
-	}
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
 	/* Did the lease get broken before we took the lock? */
@@ -3846,13 +3847,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 	if (fp->fi_had_conflict)
 		goto out_unlock;
 	/* Race breaker */
-	if (fp->fi_lease) {
+	if (fp->fi_deleg_file) {
 		status = 0;
 		atomic_inc(&fp->fi_delegees);
 		hash_delegation_locked(dp, fp);
 		goto out_unlock;
 	}
-	fp->fi_lease = fl;
 	fp->fi_deleg_file = filp;
 	atomic_set(&fp->fi_delegees, 1);
 	hash_delegation_locked(dp, fp);
@@ -3885,7 +3885,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
 	dp->dl_stid.sc_file = fp;
-	if (!fp->fi_lease) {
+	if (!fp->fi_deleg_file) {
 		spin_unlock(&fp->fi_lock);
 		spin_unlock(&state_lock);
 		status = nfs4_setlease(dp);
@@ -4929,9 +4929,25 @@ nfs4_transform_lock_offset(struct file_lock *lock)
 		lock->fl_end = OFFSET_MAX;
 }
 
-/* Hack!: For now, we're defining this just so we can use a pointer to it
- * as a unique cookie to identify our (NFSv4's) posix locks. */
+static void nfsd4_fl_get_owner(struct file_lock *dst, struct file_lock *src)
+{
+	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)src->fl_owner;
+	dst->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lo->lo_owner));
+}
+
+static void nfsd4_fl_put_owner(struct file_lock *fl)
+{
+	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)fl->fl_owner;
+
+	if (lo) {
+		nfs4_put_stateowner(&lo->lo_owner);
+		fl->fl_owner = NULL;
+	}
+}
+
 static const struct lock_manager_operations nfsd_posix_mng_ops  = {
+	.lm_get_owner = nfsd4_fl_get_owner,
+	.lm_put_owner = nfsd4_fl_put_owner,
 };
 
 static inline void
@@ -4977,10 +4993,8 @@ find_lockowner_str_locked(clientid_t *clid, struct xdr_netobj *owner,
 			    so_strhash) {
 		if (so->so_is_open_owner)
 			continue;
-		if (!same_owner_str(so, owner))
-			continue;
-		atomic_inc(&so->so_count);
-		return lockowner(so);
+		if (same_owner_str(so, owner))
+			return lockowner(nfs4_get_stateowner(so));
 	}
 	return NULL;
 }
@@ -5059,8 +5073,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 
 	atomic_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_LOCK_STID;
-	stp->st_stateowner = &lo->lo_owner;
-	atomic_inc(&lo->lo_owner.so_count);
+	stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner);
 	get_nfs4_file(fp);
 	stp->st_stid.sc_file = fp;
 	stp->st_stid.sc_free = nfs4_free_lock_stateid;
@@ -5299,7 +5312,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfserr_openmode;
 		goto out;
 	}
-	file_lock->fl_owner = (fl_owner_t)lock_sop;
+
+	file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner));
 	file_lock->fl_pid = current->tgid;
 	file_lock->fl_file = filp;
 	file_lock->fl_flags = FL_POSIX;
@@ -5495,7 +5509,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	}
 
 	file_lock->fl_type = F_UNLCK;
-	file_lock->fl_owner = (fl_owner_t)lockowner(stp->st_stateowner);
+	file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner));
 	file_lock->fl_pid = current->tgid;
 	file_lock->fl_file = filp;
 	file_lock->fl_flags = FL_POSIX;
@@ -5602,7 +5616,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 			}
 		}
 
-		atomic_inc(&sop->so_count);
+		nfs4_get_stateowner(sop);
 		break;
 	}
 	spin_unlock(&clp->cl_lock);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 0a47c6a6b301..2712042a66b1 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -486,7 +486,6 @@ struct nfs4_file {
 	atomic_t		fi_access[2];
 	u32			fi_share_deny;
 	struct file		*fi_deleg_file;
-	struct file_lock	*fi_lease;
 	atomic_t		fi_delegees;
 	struct knfsd_fh		fi_fhandle;
 	bool			fi_had_conflict;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 965cffd17a0c..989129e2d6ea 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -721,7 +721,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 		goto out_nfserr;
 	}
 
-	host_err = ima_file_check(file, may_flags);
+	host_err = ima_file_check(file, may_flags, 0);
 	if (host_err) {
 		nfsd_close(file);
 		goto out_nfserr;
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 24978153c0c4..e9e3325f29f3 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -56,11 +56,9 @@ int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	mutex_unlock(&inode->i_mutex);
 
 	nilfs = inode->i_sb->s_fs_info;
-	if (!err && nilfs_test_opt(nilfs, BARRIER)) {
-		err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
-		if (err != -EIO)
-			err = 0;
-	}
+	if (!err)
+		err = nilfs_flush_device(nilfs);
+
 	return err;
 }
 
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index d071e7f23de2..e1fa69b341b9 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -126,7 +126,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
 			nilfs_transaction_abort(inode->i_sb);
 			goto out;
 		}
-		nilfs_mark_inode_dirty(inode);
+		nilfs_mark_inode_dirty_sync(inode);
 		nilfs_transaction_commit(inode->i_sb); /* never fails */
 		/* Error handling should be detailed */
 		set_buffer_new(bh_result);
@@ -672,7 +672,7 @@ void nilfs_write_inode_common(struct inode *inode,
 	   for substitutions of appended fields */
 }
 
-void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh)
+void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh, int flags)
 {
 	ino_t ino = inode->i_ino;
 	struct nilfs_inode_info *ii = NILFS_I(inode);
@@ -683,7 +683,8 @@ void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh)
 
 	if (test_and_clear_bit(NILFS_I_NEW, &ii->i_state))
 		memset(raw_inode, 0, NILFS_MDT(ifile)->mi_entry_size);
-	set_bit(NILFS_I_INODE_DIRTY, &ii->i_state);
+	if (flags & I_DIRTY_DATASYNC)
+		set_bit(NILFS_I_INODE_SYNC, &ii->i_state);
 
 	nilfs_write_inode_common(inode, raw_inode, 0);
 		/* XXX: call with has_bmap = 0 is a workaround to avoid
@@ -939,7 +940,7 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty)
 	return 0;
 }
 
-int nilfs_mark_inode_dirty(struct inode *inode)
+int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
 {
 	struct buffer_head *ibh;
 	int err;
@@ -950,7 +951,7 @@ int nilfs_mark_inode_dirty(struct inode *inode)
 			      "failed to reget inode block.\n");
 		return err;
 	}
-	nilfs_update_inode(inode, ibh);
+	nilfs_update_inode(inode, ibh, flags);
 	mark_buffer_dirty(ibh);
 	nilfs_mdt_mark_dirty(NILFS_I(inode)->i_root->ifile);
 	brelse(ibh);
@@ -983,7 +984,7 @@ void nilfs_dirty_inode(struct inode *inode, int flags)
 		return;
 	}
 	nilfs_transaction_begin(inode->i_sb, &ti, 0);
-	nilfs_mark_inode_dirty(inode);
+	__nilfs_mark_inode_dirty(inode, flags);
 	nilfs_transaction_commit(inode->i_sb); /* never fails */
 }
 
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 422fb54b7377..9a20e513d7eb 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1022,11 +1022,9 @@ static int nilfs_ioctl_sync(struct inode *inode, struct file *filp,
 		return ret;
 
 	nilfs = inode->i_sb->s_fs_info;
-	if (nilfs_test_opt(nilfs, BARRIER)) {
-		ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
-		if (ret == -EIO)
-			return ret;
-	}
+	ret = nilfs_flush_device(nilfs);
+	if (ret < 0)
+		return ret;
 
 	if (argp != NULL) {
 		down_read(&nilfs->ns_segctor_sem);
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 0696161bf59d..91093cd74f0d 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -104,7 +104,7 @@ enum {
 					   constructor */
 	NILFS_I_COLLECTED,		/* All dirty blocks are collected */
 	NILFS_I_UPDATED,		/* The file has been written back */
-	NILFS_I_INODE_DIRTY,		/* write_inode is requested */
+	NILFS_I_INODE_SYNC,		/* dsync is not allowed for inode */
 	NILFS_I_BMAP,			/* has bmap and btnode_cache */
 	NILFS_I_GCINODE,		/* inode for GC, on memory only */
 };
@@ -273,7 +273,7 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root,
 			 unsigned long ino);
 extern struct inode *nilfs_iget_for_gc(struct super_block *sb,
 				       unsigned long ino, __u64 cno);
-extern void nilfs_update_inode(struct inode *, struct buffer_head *);
+extern void nilfs_update_inode(struct inode *, struct buffer_head *, int);
 extern void nilfs_truncate(struct inode *);
 extern void nilfs_evict_inode(struct inode *);
 extern int nilfs_setattr(struct dentry *, struct iattr *);
@@ -282,10 +282,18 @@ int nilfs_permission(struct inode *inode, int mask);
 int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh);
 extern int nilfs_inode_dirty(struct inode *);
 int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty);
-extern int nilfs_mark_inode_dirty(struct inode *);
+extern int __nilfs_mark_inode_dirty(struct inode *, int);
 extern void nilfs_dirty_inode(struct inode *, int flags);
 int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		 __u64 start, __u64 len);
+static inline int nilfs_mark_inode_dirty(struct inode *inode)
+{
+	return __nilfs_mark_inode_dirty(inode, I_DIRTY);
+}
+static inline int nilfs_mark_inode_dirty_sync(struct inode *inode)
+{
+	return __nilfs_mark_inode_dirty(inode, I_DIRTY_SYNC);
+}
 
 /* super.c */
 extern struct inode *nilfs_alloc_inode(struct super_block *);
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index a1a191634abc..7ef18fc656c2 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -930,7 +930,7 @@ static void nilfs_drop_collected_inodes(struct list_head *head)
 		if (!test_and_clear_bit(NILFS_I_COLLECTED, &ii->i_state))
 			continue;
 
-		clear_bit(NILFS_I_INODE_DIRTY, &ii->i_state);
+		clear_bit(NILFS_I_INODE_SYNC, &ii->i_state);
 		set_bit(NILFS_I_UPDATED, &ii->i_state);
 	}
 }
@@ -1833,6 +1833,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 	nilfs_set_next_segment(nilfs, segbuf);
 
 	if (update_sr) {
+		nilfs->ns_flushed_device = 0;
 		nilfs_set_last_segment(nilfs, segbuf->sb_pseg_start,
 				       segbuf->sb_sum.seg_seq, nilfs->ns_cno++);
 
@@ -2194,7 +2195,7 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
 	nilfs_transaction_lock(sb, &ti, 0);
 
 	ii = NILFS_I(inode);
-	if (test_bit(NILFS_I_INODE_DIRTY, &ii->i_state) ||
+	if (test_bit(NILFS_I_INODE_SYNC, &ii->i_state) ||
 	    nilfs_test_opt(nilfs, STRICT_ORDER) ||
 	    test_bit(NILFS_SC_UNCLOSED, &sci->sc_flags) ||
 	    nilfs_discontinued(nilfs)) {
@@ -2216,6 +2217,8 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
 	sci->sc_dsync_end = end;
 
 	err = nilfs_segctor_do_construct(sci, SC_LSEG_DSYNC);
+	if (!err)
+		nilfs->ns_flushed_device = 0;
 
 	nilfs_transaction_unlock(sb);
 	return err;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 228f5bdf0772..2e5b3ec85b8f 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -310,6 +310,9 @@ int nilfs_commit_super(struct super_block *sb, int flag)
 					    nilfs->ns_sbsize));
 	}
 	clear_nilfs_sb_dirty(nilfs);
+	nilfs->ns_flushed_device = 1;
+	/* make sure store to ns_flushed_device cannot be reordered */
+	smp_wmb();
 	return nilfs_sync_super(sb, flag);
 }
 
@@ -514,6 +517,9 @@ static int nilfs_sync_fs(struct super_block *sb, int wait)
 	}
 	up_write(&nilfs->ns_sem);
 
+	if (!err)
+		err = nilfs_flush_device(nilfs);
+
 	return err;
 }
 
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index d01ead1bea9a..23778d385836 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -46,6 +46,7 @@ enum {
 /**
  * struct the_nilfs - struct to supervise multiple nilfs mount points
  * @ns_flags: flags
+ * @ns_flushed_device: flag indicating if all volatile data was flushed
  * @ns_bdev: block device
  * @ns_sem: semaphore for shared states
  * @ns_snapshot_mount_mutex: mutex to protect snapshot mounts
@@ -103,6 +104,7 @@ enum {
  */
 struct the_nilfs {
 	unsigned long		ns_flags;
+	int			ns_flushed_device;
 
 	struct block_device    *ns_bdev;
 	struct rw_semaphore	ns_sem;
@@ -371,4 +373,24 @@ static inline int nilfs_segment_is_active(struct the_nilfs *nilfs, __u64 n)
 	return n == nilfs->ns_segnum || n == nilfs->ns_nextnum;
 }
 
+static inline int nilfs_flush_device(struct the_nilfs *nilfs)
+{
+	int err;
+
+	if (!nilfs_test_opt(nilfs, BARRIER) || nilfs->ns_flushed_device)
+		return 0;
+
+	nilfs->ns_flushed_device = 1;
+	/*
+	 * the store to ns_flushed_device must not be reordered after
+	 * blkdev_issue_flush().
+	 */
+	smp_wmb();
+
+	err = blkdev_issue_flush(nilfs->ns_bdev, GFP_KERNEL, NULL);
+	if (err != -EIO)
+		err = 0;
+	return err;
+}
+
 #endif /* _THE_NILFS_H */
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index abc8cbcfe90e..caaaf9dfe353 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -346,13 +346,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
 		goto out;
 	}
 
-	error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
-	if (error) {
-		/* if we added, we must shoot */
-		if (dn_mark == new_dn_mark)
-			destroy = 1;
-		goto out;
-	}
+	__f_setown(filp, task_pid(current), PIDTYPE_PID, 0);
 
 	error = attach_dn(dn, dn_mark, id, fd, filp, mask);
 	/* !error means that we attached the dn to the dn_mark, so don't free it */
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index b13992a41bd9..c991616acca9 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -78,7 +78,7 @@ static int create_fd(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	client_fd = get_unused_fd();
+	client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
 	if (client_fd < 0)
 		return client_fd;
 
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 85e7d2b431d9..9c0898c4cfe1 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -23,9 +23,6 @@ extern int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 				      struct fsnotify_group *group, struct vfsmount *mnt,
 				      int allow_dups);
 
-/* final kfree of a group */
-extern void fsnotify_final_destroy_group(struct fsnotify_group *group);
-
 /* vfsmount specific destruction of a mark */
 extern void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark);
 /* inode specific destruction of a mark */
diff --git a/fs/notify/group.c b/fs/notify/group.c
index ad1995980456..d16b62cb2854 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -31,7 +31,7 @@
 /*
  * Final freeing of a group
  */
-void fsnotify_final_destroy_group(struct fsnotify_group *group)
+static void fsnotify_final_destroy_group(struct fsnotify_group *group)
 {
 	if (group->ops->free_group_priv)
 		group->ops->free_group_priv(group);
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 0f88bc0b4e6c..7d888d77d59a 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -165,8 +165,10 @@ static void inotify_free_group_priv(struct fsnotify_group *group)
 	/* ideally the idr is empty and we won't hit the BUG in the callback */
 	idr_for_each(&group->inotify_data.idr, idr_callback, group);
 	idr_destroy(&group->inotify_data.idr);
-	atomic_dec(&group->inotify_data.user->inotify_devs);
-	free_uid(group->inotify_data.user);
+	if (group->inotify_data.user) {
+		atomic_dec(&group->inotify_data.user->inotify_devs);
+		free_uid(group->inotify_data.user);
+	}
 }
 
 static void inotify_free_event(struct fsnotify_event *fsn_event)
diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile
index 30206b238433..36ae529511c4 100644
--- a/fs/ntfs/Makefile
+++ b/fs/ntfs/Makefile
@@ -8,7 +8,7 @@ ntfs-y := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
 
 ntfs-$(CONFIG_NTFS_RW) += bitmap.o lcnalloc.o logfile.o quota.o usnjrnl.o
 
-ccflags-y := -DNTFS_VERSION=\"2.1.30\"
+ccflags-y := -DNTFS_VERSION=\"2.1.31\"
 ccflags-$(CONFIG_NTFS_DEBUG)	+= -DDEBUG
 ccflags-$(CONFIG_NTFS_RW)	+= -DNTFS_RW
 
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index d267ea6aa1a0..7521e11db728 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -1,8 +1,7 @@
 /**
  * aops.c - NTFS kernel address space operations and page cache handling.
- *	    Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2007 Anton Altaparmakov
+ * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
  * Copyright (c) 2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -1539,16 +1538,157 @@ err_out:
 #endif	/* NTFS_RW */
 
 /**
- * ntfs_aops - general address space operations for inodes and attributes
+ * ntfs_bmap - map logical file block to physical device block
+ * @mapping:	address space mapping to which the block to be mapped belongs
+ * @block:	logical block to map to its physical device block
+ *
+ * For regular, non-resident files (i.e. not compressed and not encrypted), map
+ * the logical @block belonging to the file described by the address space
+ * mapping @mapping to its physical device block.
+ *
+ * The size of the block is equal to the @s_blocksize field of the super block
+ * of the mounted file system which is guaranteed to be smaller than or equal
+ * to the cluster size thus the block is guaranteed to fit entirely inside the
+ * cluster which means we do not need to care how many contiguous bytes are
+ * available after the beginning of the block.
+ *
+ * Return the physical device block if the mapping succeeded or 0 if the block
+ * is sparse or there was an error.
+ *
+ * Note: This is a problem if someone tries to run bmap() on $Boot system file
+ * as that really is in block zero but there is nothing we can do.  bmap() is
+ * just broken in that respect (just like it cannot distinguish sparse from
+ * not available or error).
  */
-const struct address_space_operations ntfs_aops = {
-	.readpage	= ntfs_readpage,	/* Fill page with data. */
+static sector_t ntfs_bmap(struct address_space *mapping, sector_t block)
+{
+	s64 ofs, size;
+	loff_t i_size;
+	LCN lcn;
+	unsigned long blocksize, flags;
+	ntfs_inode *ni = NTFS_I(mapping->host);
+	ntfs_volume *vol = ni->vol;
+	unsigned delta;
+	unsigned char blocksize_bits, cluster_size_shift;
+
+	ntfs_debug("Entering for mft_no 0x%lx, logical block 0x%llx.",
+			ni->mft_no, (unsigned long long)block);
+	if (ni->type != AT_DATA || !NInoNonResident(ni) || NInoEncrypted(ni)) {
+		ntfs_error(vol->sb, "BMAP does not make sense for %s "
+				"attributes, returning 0.",
+				(ni->type != AT_DATA) ? "non-data" :
+				(!NInoNonResident(ni) ? "resident" :
+				"encrypted"));
+		return 0;
+	}
+	/* None of these can happen. */
+	BUG_ON(NInoCompressed(ni));
+	BUG_ON(NInoMstProtected(ni));
+	blocksize = vol->sb->s_blocksize;
+	blocksize_bits = vol->sb->s_blocksize_bits;
+	ofs = (s64)block << blocksize_bits;
+	read_lock_irqsave(&ni->size_lock, flags);
+	size = ni->initialized_size;
+	i_size = i_size_read(VFS_I(ni));
+	read_unlock_irqrestore(&ni->size_lock, flags);
+	/*
+	 * If the offset is outside the initialized size or the block straddles
+	 * the initialized size then pretend it is a hole unless the
+	 * initialized size equals the file size.
+	 */
+	if (unlikely(ofs >= size || (ofs + blocksize > size && size < i_size)))
+		goto hole;
+	cluster_size_shift = vol->cluster_size_bits;
+	down_read(&ni->runlist.lock);
+	lcn = ntfs_attr_vcn_to_lcn_nolock(ni, ofs >> cluster_size_shift, false);
+	up_read(&ni->runlist.lock);
+	if (unlikely(lcn < LCN_HOLE)) {
+		/*
+		 * Step down to an integer to avoid gcc doing a long long
+		 * comparision in the switch when we know @lcn is between
+		 * LCN_HOLE and LCN_EIO (i.e. -1 to -5).
+		 *
+		 * Otherwise older gcc (at least on some architectures) will
+		 * try to use __cmpdi2() which is of course not available in
+		 * the kernel.
+		 */
+		switch ((int)lcn) {
+		case LCN_ENOENT:
+			/*
+			 * If the offset is out of bounds then pretend it is a
+			 * hole.
+			 */
+			goto hole;
+		case LCN_ENOMEM:
+			ntfs_error(vol->sb, "Not enough memory to complete "
+					"mapping for inode 0x%lx.  "
+					"Returning 0.", ni->mft_no);
+			break;
+		default:
+			ntfs_error(vol->sb, "Failed to complete mapping for "
+					"inode 0x%lx.  Run chkdsk.  "
+					"Returning 0.", ni->mft_no);
+			break;
+		}
+		return 0;
+	}
+	if (lcn < 0) {
+		/* It is a hole. */
+hole:
+		ntfs_debug("Done (returning hole).");
+		return 0;
+	}
+	/*
+	 * The block is really allocated and fullfils all our criteria.
+	 * Convert the cluster to units of block size and return the result.
+	 */
+	delta = ofs & vol->cluster_size_mask;
+	if (unlikely(sizeof(block) < sizeof(lcn))) {
+		block = lcn = ((lcn << cluster_size_shift) + delta) >>
+				blocksize_bits;
+		/* If the block number was truncated return 0. */
+		if (unlikely(block != lcn)) {
+			ntfs_error(vol->sb, "Physical block 0x%llx is too "
+					"large to be returned, returning 0.",
+					(long long)lcn);
+			return 0;
+		}
+	} else
+		block = ((lcn << cluster_size_shift) + delta) >>
+				blocksize_bits;
+	ntfs_debug("Done (returning block 0x%llx).", (unsigned long long)lcn);
+	return block;
+}
+
+/**
+ * ntfs_normal_aops - address space operations for normal inodes and attributes
+ *
+ * Note these are not used for compressed or mst protected inodes and
+ * attributes.
+ */
+const struct address_space_operations ntfs_normal_aops = {
+	.readpage	= ntfs_readpage,
 #ifdef NTFS_RW
-	.writepage	= ntfs_writepage,	/* Write dirty page to disk. */
+	.writepage	= ntfs_writepage,
+	.set_page_dirty	= __set_page_dirty_buffers,
+#endif /* NTFS_RW */
+	.bmap		= ntfs_bmap,
+	.migratepage	= buffer_migrate_page,
+	.is_partially_uptodate = block_is_partially_uptodate,
+	.error_remove_page = generic_error_remove_page,
+};
+
+/**
+ * ntfs_compressed_aops - address space operations for compressed inodes
+ */
+const struct address_space_operations ntfs_compressed_aops = {
+	.readpage	= ntfs_readpage,
+#ifdef NTFS_RW
+	.writepage	= ntfs_writepage,
+	.set_page_dirty	= __set_page_dirty_buffers,
 #endif /* NTFS_RW */
-	.migratepage	= buffer_migrate_page,	/* Move a page cache page from
-						   one physical page to an
-						   other. */
+	.migratepage	= buffer_migrate_page,
+	.is_partially_uptodate = block_is_partially_uptodate,
 	.error_remove_page = generic_error_remove_page,
 };
 
@@ -1564,9 +1704,8 @@ const struct address_space_operations ntfs_mst_aops = {
 						   without touching the buffers
 						   belonging to the page. */
 #endif /* NTFS_RW */
-	.migratepage	= buffer_migrate_page,	/* Move a page cache page from
-						   one physical page to an
-						   other. */
+	.migratepage	= buffer_migrate_page,
+	.is_partially_uptodate	= block_is_partially_uptodate,
 	.error_remove_page = generic_error_remove_page,
 };
 
diff --git a/fs/ntfs/debug.c b/fs/ntfs/debug.c
index dd6103cc93c1..825a54e8f490 100644
--- a/fs/ntfs/debug.c
+++ b/fs/ntfs/debug.c
@@ -112,7 +112,7 @@ void __ntfs_error(const char *function, const struct super_block *sb,
 /* If 1, output debug messages, and if 0, don't. */
 int debug_msgs = 0;
 
-void __ntfs_debug (const char *file, int line, const char *function,
+void __ntfs_debug(const char *file, int line, const char *function,
 		const char *fmt, ...)
 {
 	struct va_format vaf;
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index f5ec1ce7a532..643faa44f22b 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1,7 +1,7 @@
 /*
  * file.c - NTFS kernel file operations.  Part of the Linux-NTFS project.
  *
- * Copyright (c) 2001-2011 Anton Altaparmakov and Tuxera Inc.
+ * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
  *
  * This program/include file is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as published
@@ -410,7 +410,8 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
 	BUG_ON(!nr_pages);
 	err = nr = 0;
 	do {
-		pages[nr] = find_lock_page(mapping, index);
+		pages[nr] = find_get_page_flags(mapping, index, FGP_LOCK |
+				FGP_ACCESSED);
 		if (!pages[nr]) {
 			if (!*cached_page) {
 				*cached_page = page_cache_alloc(mapping);
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index f47af5e6e230..898b9949d363 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -1,7 +1,7 @@
 /**
- * inode.c - NTFS kernel inode handling. Part of the Linux-NTFS project.
+ * inode.c - NTFS kernel inode handling.
  *
- * Copyright (c) 2001-2007 Anton Altaparmakov
+ * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
  *
  * This program/include file is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as published
@@ -1012,6 +1012,7 @@ skip_large_dir_stuff:
 		/* Setup the operations for this inode. */
 		vi->i_op = &ntfs_dir_inode_ops;
 		vi->i_fop = &ntfs_dir_ops;
+		vi->i_mapping->a_ops = &ntfs_mst_aops;
 	} else {
 		/* It is a file. */
 		ntfs_attr_reinit_search_ctx(ctx);
@@ -1160,11 +1161,12 @@ no_data_attr_special_case:
 		/* Setup the operations for this inode. */
 		vi->i_op = &ntfs_file_inode_ops;
 		vi->i_fop = &ntfs_file_ops;
+		vi->i_mapping->a_ops = &ntfs_normal_aops;
+		if (NInoMstProtected(ni))
+			vi->i_mapping->a_ops = &ntfs_mst_aops;
+		else if (NInoCompressed(ni))
+			vi->i_mapping->a_ops = &ntfs_compressed_aops;
 	}
-	if (NInoMstProtected(ni))
-		vi->i_mapping->a_ops = &ntfs_mst_aops;
-	else
-		vi->i_mapping->a_ops = &ntfs_aops;
 	/*
 	 * The number of 512-byte blocks used on disk (for stat). This is in so
 	 * far inaccurate as it doesn't account for any named streams or other
@@ -1414,10 +1416,11 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi)
 		ni->allocated_size = sle64_to_cpu(
 				a->data.non_resident.allocated_size);
 	}
+	vi->i_mapping->a_ops = &ntfs_normal_aops;
 	if (NInoMstProtected(ni))
 		vi->i_mapping->a_ops = &ntfs_mst_aops;
-	else
-		vi->i_mapping->a_ops = &ntfs_aops;
+	else if (NInoCompressed(ni))
+		vi->i_mapping->a_ops = &ntfs_compressed_aops;
 	if ((NInoCompressed(ni) || NInoSparse(ni)) && ni->type != AT_INDEX_ROOT)
 		vi->i_blocks = ni->itype.compressed.size >> 9;
 	else
diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h
index d6a340bf80fc..c581e26a350d 100644
--- a/fs/ntfs/ntfs.h
+++ b/fs/ntfs/ntfs.h
@@ -1,8 +1,7 @@
 /*
- * ntfs.h - Defines for NTFS Linux kernel driver. Part of the Linux-NTFS
- *	    project.
+ * ntfs.h - Defines for NTFS Linux kernel driver.
  *
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.
  * Copyright (C) 2002 Richard Russon
  *
  * This program/include file is free software; you can redistribute it and/or
@@ -57,7 +56,8 @@ extern struct kmem_cache *ntfs_attr_ctx_cache;
 extern struct kmem_cache *ntfs_index_ctx_cache;
 
 /* The various operations structs defined throughout the driver files. */
-extern const struct address_space_operations ntfs_aops;
+extern const struct address_space_operations ntfs_normal_aops;
+extern const struct address_space_operations ntfs_compressed_aops;
 extern const struct address_space_operations ntfs_mst_aops;
 
 extern const struct  file_operations ntfs_file_ops;
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 6c3296e546c3..9e1e112074fb 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -3208,7 +3208,7 @@ static void __exit exit_ntfs_fs(void)
 }
 
 MODULE_AUTHOR("Anton Altaparmakov <anton@tuxera.com>");
-MODULE_DESCRIPTION("NTFS 1.2/3.x driver - Copyright (c) 2001-2011 Anton Altaparmakov and Tuxera Inc.");
+MODULE_DESCRIPTION("NTFS 1.2/3.x driver - Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc.");
 MODULE_VERSION(NTFS_VERSION);
 MODULE_LICENSE("GPL");
 #ifdef DEBUG
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 4a231a166cf8..1ef547e49373 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1481,8 +1481,16 @@ static int ocfs2_write_begin_inline(struct address_space *mapping,
 	handle_t *handle;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
 
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out;
+	}
+
 	page = find_or_create_page(mapping, 0, GFP_NOFS);
 	if (!page) {
+		ocfs2_commit_trans(osb, handle);
 		ret = -ENOMEM;
 		mlog_errno(ret);
 		goto out;
@@ -1494,13 +1502,6 @@ static int ocfs2_write_begin_inline(struct address_space *mapping,
 	wc->w_pages[0] = wc->w_target_page = page;
 	wc->w_num_pages = 1;
 
-	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
-	if (IS_ERR(handle)) {
-		ret = PTR_ERR(handle);
-		mlog_errno(ret);
-		goto out;
-	}
-
 	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
 				      OCFS2_JOURNAL_ACCESS_WRITE);
 	if (ret) {
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 73039295d0d1..eb9d48746ab4 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -2244,7 +2244,7 @@ ssize_t o2hb_heartbeat_group_mode_store(struct o2hb_heartbeat_group *group,
 		return -EINVAL;
 
 	for (i = 0; i < O2HB_HEARTBEAT_NUM_MODES; ++i) {
-		if (strnicmp(page, o2hb_heartbeat_mode_desc[i], len))
+		if (strncasecmp(page, o2hb_heartbeat_mode_desc[i], len))
 			continue;
 
 		ret = o2hb_global_heartbeat_mode_set(i);
@@ -2572,6 +2572,25 @@ int o2hb_check_node_heartbeating(u8 node_num)
 }
 EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating);
 
+int o2hb_check_node_heartbeating_no_sem(u8 node_num)
+{
+	unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	unsigned long flags;
+
+	spin_lock_irqsave(&o2hb_live_lock, flags);
+	o2hb_fill_node_map_from_callback(testing_map, sizeof(testing_map));
+	spin_unlock_irqrestore(&o2hb_live_lock, flags);
+	if (!test_bit(node_num, testing_map)) {
+		mlog(ML_HEARTBEAT,
+		     "node (%u) does not have heartbeating enabled.\n",
+		     node_num);
+		return 0;
+	}
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating_no_sem);
+
 int o2hb_check_node_heartbeating_from_callback(u8 node_num)
 {
 	unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h
index 00ad8e8fea51..3ef5137dc362 100644
--- a/fs/ocfs2/cluster/heartbeat.h
+++ b/fs/ocfs2/cluster/heartbeat.h
@@ -80,6 +80,7 @@ void o2hb_fill_node_map(unsigned long *map,
 void o2hb_exit(void);
 int o2hb_init(void);
 int o2hb_check_node_heartbeating(u8 node_num);
+int o2hb_check_node_heartbeating_no_sem(u8 node_num);
 int o2hb_check_node_heartbeating_from_callback(u8 node_num);
 int o2hb_check_local_node_heartbeating(void);
 void o2hb_stop_all_regions(void);
diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c
index 07ac24fd9252..af7598bff1b5 100644
--- a/fs/ocfs2/cluster/masklog.c
+++ b/fs/ocfs2/cluster/masklog.c
@@ -49,13 +49,13 @@ static ssize_t mlog_mask_show(u64 mask, char *buf)
 
 static ssize_t mlog_mask_store(u64 mask, const char *buf, size_t count)
 {
-	if (!strnicmp(buf, "allow", 5)) {
+	if (!strncasecmp(buf, "allow", 5)) {
 		__mlog_set_u64(mask, mlog_and_bits);
 		__mlog_clear_u64(mask, mlog_not_bits);
-	} else if (!strnicmp(buf, "deny", 4)) {
+	} else if (!strncasecmp(buf, "deny", 4)) {
 		__mlog_set_u64(mask, mlog_not_bits);
 		__mlog_clear_u64(mask, mlog_and_bits);
-	} else if (!strnicmp(buf, "off", 3)) {
+	} else if (!strncasecmp(buf, "off", 3)) {
 		__mlog_clear_u64(mask, mlog_not_bits);
 		__mlog_clear_u64(mask, mlog_and_bits);
 	} else
diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
index 73ba81928bce..27d1242c8383 100644
--- a/fs/ocfs2/cluster/netdebug.c
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -185,29 +185,13 @@ static const struct seq_operations nst_seq_ops = {
 static int nst_fop_open(struct inode *inode, struct file *file)
 {
 	struct o2net_send_tracking *dummy_nst;
-	struct seq_file *seq;
-	int ret;
 
-	dummy_nst = kmalloc(sizeof(struct o2net_send_tracking), GFP_KERNEL);
-	if (dummy_nst == NULL) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	dummy_nst->st_task = NULL;
-
-	ret = seq_open(file, &nst_seq_ops);
-	if (ret)
-		goto out;
-
-	seq = file->private_data;
-	seq->private = dummy_nst;
+	dummy_nst = __seq_open_private(file, &nst_seq_ops, sizeof(*dummy_nst));
+	if (!dummy_nst)
+		return -ENOMEM;
 	o2net_debug_add_nst(dummy_nst);
 
-	dummy_nst = NULL;
-
-out:
-	kfree(dummy_nst);
-	return ret;
+	return 0;
 }
 
 static int nst_fop_release(struct inode *inode, struct file *file)
@@ -412,33 +396,27 @@ static const struct seq_operations sc_seq_ops = {
 	.show = sc_seq_show,
 };
 
-static int sc_common_open(struct file *file, struct o2net_sock_debug *sd)
+static int sc_common_open(struct file *file, int ctxt)
 {
+	struct o2net_sock_debug *sd;
 	struct o2net_sock_container *dummy_sc;
-	struct seq_file *seq;
-	int ret;
 
-	dummy_sc = kmalloc(sizeof(struct o2net_sock_container), GFP_KERNEL);
-	if (dummy_sc == NULL) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	dummy_sc->sc_page = NULL;
+	dummy_sc = kzalloc(sizeof(*dummy_sc), GFP_KERNEL);
+	if (!dummy_sc)
+		return -ENOMEM;
 
-	ret = seq_open(file, &sc_seq_ops);
-	if (ret)
-		goto out;
+	sd = __seq_open_private(file, &sc_seq_ops, sizeof(*sd));
+	if (!sd) {
+		kfree(dummy_sc);
+		return -ENOMEM;
+	}
 
-	seq = file->private_data;
-	seq->private = sd;
+	sd->dbg_ctxt = ctxt;
 	sd->dbg_sock = dummy_sc;
-	o2net_debug_add_sc(dummy_sc);
 
-	dummy_sc = NULL;
+	o2net_debug_add_sc(dummy_sc);
 
-out:
-	kfree(dummy_sc);
-	return ret;
+	return 0;
 }
 
 static int sc_fop_release(struct inode *inode, struct file *file)
@@ -453,16 +431,7 @@ static int sc_fop_release(struct inode *inode, struct file *file)
 
 static int stats_fop_open(struct inode *inode, struct file *file)
 {
-	struct o2net_sock_debug *sd;
-
-	sd = kmalloc(sizeof(struct o2net_sock_debug), GFP_KERNEL);
-	if (sd == NULL)
-		return -ENOMEM;
-
-	sd->dbg_ctxt = SHOW_SOCK_STATS;
-	sd->dbg_sock = NULL;
-
-	return sc_common_open(file, sd);
+	return sc_common_open(file, SHOW_SOCK_STATS);
 }
 
 static const struct file_operations stats_seq_fops = {
@@ -474,16 +443,7 @@ static const struct file_operations stats_seq_fops = {
 
 static int sc_fop_open(struct inode *inode, struct file *file)
 {
-	struct o2net_sock_debug *sd;
-
-	sd = kmalloc(sizeof(struct o2net_sock_debug), GFP_KERNEL);
-	if (sd == NULL)
-		return -ENOMEM;
-
-	sd->dbg_ctxt = SHOW_SOCK_CONTAINERS;
-	sd->dbg_sock = NULL;
-
-	return sc_common_open(file, sd);
+	return sc_common_open(file, SHOW_SOCK_CONTAINERS);
 }
 
 static const struct file_operations sc_seq_fops = {
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index ea34952f9496..97de0fbd9f78 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -536,7 +536,7 @@ static void o2net_set_nn_state(struct o2net_node *nn,
 	if (nn->nn_persistent_error || nn->nn_sc_valid)
 		wake_up(&nn->nn_sc_wq);
 
-	if (!was_err && nn->nn_persistent_error) {
+	if (was_valid && !was_err && nn->nn_persistent_error) {
 		o2quo_conn_err(o2net_num_from_nn(nn));
 		queue_delayed_work(o2net_wq, &nn->nn_still_up,
 				   msecs_to_jiffies(O2NET_QUORUM_DELAY_MS));
@@ -1601,7 +1601,15 @@ static void o2net_start_connect(struct work_struct *work)
 	struct sockaddr_in myaddr = {0, }, remoteaddr = {0, };
 	int ret = 0, stop;
 	unsigned int timeout;
+	unsigned int noio_flag;
 
+	/*
+	 * sock_create allocates the sock with GFP_KERNEL. We must set
+	 * per-process flag PF_MEMALLOC_NOIO so that all allocations done
+	 * by this process are done as if GFP_NOIO was specified. So we
+	 * are not reentering filesystem while doing memory reclaim.
+	 */
+	noio_flag = memalloc_noio_save();
 	/* if we're greater we initiate tx, otherwise we accept */
 	if (o2nm_this_node() <= o2net_num_from_nn(nn))
 		goto out;
@@ -1710,6 +1718,7 @@ out:
 	if (mynode)
 		o2nm_node_put(mynode);
 
+	memalloc_noio_restore(noio_flag);
 	return;
 }
 
@@ -1721,7 +1730,8 @@ static void o2net_connect_expired(struct work_struct *work)
 	spin_lock(&nn->nn_lock);
 	if (!nn->nn_sc_valid) {
 		printk(KERN_NOTICE "o2net: No connection established with "
-		       "node %u after %u.%u seconds, giving up.\n",
+		       "node %u after %u.%u seconds, check network and"
+		       " cluster configuration.\n",
 		     o2net_num_from_nn(nn),
 		     o2net_idle_timeout() / 1000,
 		     o2net_idle_timeout() % 1000);
@@ -1835,6 +1845,15 @@ static int o2net_accept_one(struct socket *sock, int *more)
 	struct o2nm_node *local_node = NULL;
 	struct o2net_sock_container *sc = NULL;
 	struct o2net_node *nn;
+	unsigned int noio_flag;
+
+	/*
+	 * sock_create_lite allocates the sock with GFP_KERNEL. We must set
+	 * per-process flag PF_MEMALLOC_NOIO so that all allocations done
+	 * by this process are done as if GFP_NOIO was specified. So we
+	 * are not reentering filesystem while doing memory reclaim.
+	 */
+	noio_flag = memalloc_noio_save();
 
 	BUG_ON(sock == NULL);
 	*more = 0;
@@ -1951,6 +1970,8 @@ out:
 		o2nm_node_put(local_node);
 	if (sc)
 		sc_put(sc);
+
+	memalloc_noio_restore(noio_flag);
 	return ret;
 }
 
@@ -2146,17 +2167,13 @@ int o2net_init(void)
 	o2quo_init();
 
 	if (o2net_debugfs_init())
-		return -ENOMEM;
+		goto out;
 
 	o2net_hand = kzalloc(sizeof(struct o2net_handshake), GFP_KERNEL);
 	o2net_keep_req = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
 	o2net_keep_resp = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
-	if (!o2net_hand || !o2net_keep_req || !o2net_keep_resp) {
-		kfree(o2net_hand);
-		kfree(o2net_keep_req);
-		kfree(o2net_keep_resp);
-		return -ENOMEM;
-	}
+	if (!o2net_hand || !o2net_keep_req || !o2net_keep_resp)
+		goto out;
 
 	o2net_hand->protocol_version = cpu_to_be64(O2NET_PROTOCOL_VERSION);
 	o2net_hand->connector_id = cpu_to_be64(1);
@@ -2181,6 +2198,14 @@ int o2net_init(void)
 	}
 
 	return 0;
+
+out:
+	kfree(o2net_hand);
+	kfree(o2net_keep_req);
+	kfree(o2net_keep_resp);
+
+	o2quo_exit();
+	return -ENOMEM;
 }
 
 void o2net_exit(void)
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 18f13c2e4a10..149eb556b8c6 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -647,41 +647,30 @@ static const struct seq_operations debug_lockres_ops = {
 static int debug_lockres_open(struct inode *inode, struct file *file)
 {
 	struct dlm_ctxt *dlm = inode->i_private;
-	int ret = -ENOMEM;
-	struct seq_file *seq;
-	struct debug_lockres *dl = NULL;
+	struct debug_lockres *dl;
+	void *buf;
 
-	dl = kzalloc(sizeof(struct debug_lockres), GFP_KERNEL);
-	if (!dl) {
-		mlog_errno(ret);
+	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!buf)
 		goto bail;
-	}
 
-	dl->dl_len = PAGE_SIZE;
-	dl->dl_buf = kmalloc(dl->dl_len, GFP_KERNEL);
-	if (!dl->dl_buf) {
-		mlog_errno(ret);
-		goto bail;
-	}
+	dl = __seq_open_private(file, &debug_lockres_ops, sizeof(*dl));
+	if (!dl)
+		goto bailfree;
 
-	ret = seq_open(file, &debug_lockres_ops);
-	if (ret) {
-		mlog_errno(ret);
-		goto bail;
-	}
-
-	seq = file->private_data;
-	seq->private = dl;
+	dl->dl_len = PAGE_SIZE;
+	dl->dl_buf = buf;
 
 	dlm_grab(dlm);
 	dl->dl_ctxt = dlm;
 
 	return 0;
+
+bailfree:
+	kfree(buf);
 bail:
-	if (dl)
-		kfree(dl->dl_buf);
-	kfree(dl);
-	return ret;
+	mlog_errno(-ENOMEM);
+	return -ENOMEM;
 }
 
 static int debug_lockres_release(struct inode *inode, struct file *file)
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 3fcf205ee900..02d315fef432 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -839,7 +839,7 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data,
 	 * to back off and try again.  This gives heartbeat a chance
 	 * to catch up.
 	 */
-	if (!o2hb_check_node_heartbeating(query->node_idx)) {
+	if (!o2hb_check_node_heartbeating_no_sem(query->node_idx)) {
 		mlog(0, "node %u is not in our live map yet\n",
 		     query->node_idx);
 
@@ -1975,24 +1975,22 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 
 	dlm = kzalloc(sizeof(*dlm), GFP_KERNEL);
 	if (!dlm) {
-		mlog_errno(-ENOMEM);
+		ret = -ENOMEM;
+		mlog_errno(ret);
 		goto leave;
 	}
 
 	dlm->name = kstrdup(domain, GFP_KERNEL);
 	if (dlm->name == NULL) {
-		mlog_errno(-ENOMEM);
-		kfree(dlm);
-		dlm = NULL;
+		ret = -ENOMEM;
+		mlog_errno(ret);
 		goto leave;
 	}
 
 	dlm->lockres_hash = (struct hlist_head **)dlm_alloc_pagevec(DLM_HASH_PAGES);
 	if (!dlm->lockres_hash) {
-		mlog_errno(-ENOMEM);
-		kfree(dlm->name);
-		kfree(dlm);
-		dlm = NULL;
+		ret = -ENOMEM;
+		mlog_errno(ret);
 		goto leave;
 	}
 
@@ -2002,11 +2000,8 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 	dlm->master_hash = (struct hlist_head **)
 				dlm_alloc_pagevec(DLM_HASH_PAGES);
 	if (!dlm->master_hash) {
-		mlog_errno(-ENOMEM);
-		dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES);
-		kfree(dlm->name);
-		kfree(dlm);
-		dlm = NULL;
+		ret = -ENOMEM;
+		mlog_errno(ret);
 		goto leave;
 	}
 
@@ -2017,14 +2012,8 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 	dlm->node_num = o2nm_this_node();
 
 	ret = dlm_create_debugfs_subroot(dlm);
-	if (ret < 0) {
-		dlm_free_pagevec((void **)dlm->master_hash, DLM_HASH_PAGES);
-		dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES);
-		kfree(dlm->name);
-		kfree(dlm);
-		dlm = NULL;
+	if (ret < 0)
 		goto leave;
-	}
 
 	spin_lock_init(&dlm->spinlock);
 	spin_lock_init(&dlm->master_lock);
@@ -2085,6 +2074,19 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 		  atomic_read(&dlm->dlm_refs.refcount));
 
 leave:
+	if (ret < 0 && dlm) {
+		if (dlm->master_hash)
+			dlm_free_pagevec((void **)dlm->master_hash,
+					DLM_HASH_PAGES);
+
+		if (dlm->lockres_hash)
+			dlm_free_pagevec((void **)dlm->lockres_hash,
+					DLM_HASH_PAGES);
+
+		kfree(dlm->name);
+		kfree(dlm);
+		dlm = NULL;
+	}
 	return dlm;
 }
 
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 12ba682fc53c..215e41abf101 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -625,9 +625,6 @@ struct dlm_lock_resource *dlm_new_lockres(struct dlm_ctxt *dlm,
 	return res;
 
 error:
-	if (res && res->lockname.name)
-		kmem_cache_free(dlm_lockname_cache, (void *)res->lockname.name);
-
 	if (res)
 		kmem_cache_free(dlm_lockres_cache, res);
 	return NULL;
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 45067faf5695..3365839d2971 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1710,9 +1710,12 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 				BUG();
 			} else
 				__dlm_lockres_grab_inflight_worker(dlm, res);
-		} else /* put.. incase we are not the master */
+			spin_unlock(&res->spinlock);
+		} else {
+			/* put.. incase we are not the master */
+			spin_unlock(&res->spinlock);
 			dlm_lockres_put(res);
-		spin_unlock(&res->spinlock);
+		}
 	}
 	spin_unlock(&dlm->spinlock);
 
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 52cfe99ae056..21262f2b1654 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2892,37 +2892,24 @@ static int ocfs2_dlm_debug_release(struct inode *inode, struct file *file)
 
 static int ocfs2_dlm_debug_open(struct inode *inode, struct file *file)
 {
-	int ret;
 	struct ocfs2_dlm_seq_priv *priv;
-	struct seq_file *seq;
 	struct ocfs2_super *osb;
 
-	priv = kzalloc(sizeof(struct ocfs2_dlm_seq_priv), GFP_KERNEL);
+	priv = __seq_open_private(file, &ocfs2_dlm_seq_ops, sizeof(*priv));
 	if (!priv) {
-		ret = -ENOMEM;
-		mlog_errno(ret);
-		goto out;
+		mlog_errno(-ENOMEM);
+		return -ENOMEM;
 	}
+
 	osb = inode->i_private;
 	ocfs2_get_dlm_debug(osb->osb_dlm_debug);
 	priv->p_dlm_debug = osb->osb_dlm_debug;
 	INIT_LIST_HEAD(&priv->p_iter_res.l_debug_list);
 
-	ret = seq_open(file, &ocfs2_dlm_seq_ops);
-	if (ret) {
-		kfree(priv);
-		mlog_errno(ret);
-		goto out;
-	}
-
-	seq = file->private_data;
-	seq->private = priv;
-
 	ocfs2_add_lockres_tracking(&priv->p_iter_res,
 				   priv->p_dlm_debug);
 
-out:
-	return ret;
+	return 0;
 }
 
 static const struct file_operations ocfs2_dlm_debug_fops = {
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 2930e231f3f9..324dc93ac896 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -760,7 +760,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
 	unsigned long index = abs_from >> PAGE_CACHE_SHIFT;
-	handle_t *handle = NULL;
+	handle_t *handle;
 	int ret = 0;
 	unsigned zero_from, zero_to, block_start, block_end;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
@@ -769,11 +769,17 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 	BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT));
 	BUG_ON(abs_from & (inode->i_blkbits - 1));
 
+	handle = ocfs2_zero_start_ordered_transaction(inode, di_bh);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+
 	page = find_or_create_page(mapping, index, GFP_NOFS);
 	if (!page) {
 		ret = -ENOMEM;
 		mlog_errno(ret);
-		goto out;
+		goto out_commit_trans;
 	}
 
 	/* Get the offsets within the page that we want to zero */
@@ -805,15 +811,6 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 			goto out_unlock;
 		}
 
-		if (!handle) {
-			handle = ocfs2_zero_start_ordered_transaction(inode,
-								      di_bh);
-			if (IS_ERR(handle)) {
-				ret = PTR_ERR(handle);
-				handle = NULL;
-				break;
-			}
-		}
 
 		/* must not update i_size! */
 		ret = block_commit_write(page, block_start + 1,
@@ -824,27 +821,29 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 			ret = 0;
 	}
 
+	/*
+	 * fs-writeback will release the dirty pages without page lock
+	 * whose offset are over inode size, the release happens at
+	 * block_write_full_page().
+	 */
+	i_size_write(inode, abs_to);
+	inode->i_blocks = ocfs2_inode_sector_count(inode);
+	di->i_size = cpu_to_le64((u64)i_size_read(inode));
+	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+	di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+	di->i_mtime_nsec = di->i_ctime_nsec;
 	if (handle) {
-		/*
-		 * fs-writeback will release the dirty pages without page lock
-		 * whose offset are over inode size, the release happens at
-		 * block_write_full_page().
-		 */
-		i_size_write(inode, abs_to);
-		inode->i_blocks = ocfs2_inode_sector_count(inode);
-		di->i_size = cpu_to_le64((u64)i_size_read(inode));
-		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
-		di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
-		di->i_mtime_nsec = di->i_ctime_nsec;
 		ocfs2_journal_dirty(handle, di_bh);
 		ocfs2_update_inode_fsync_trans(handle, inode, 1);
-		ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
 	}
 
 out_unlock:
 	unlock_page(page);
 	page_cache_release(page);
+out_commit_trans:
+	if (handle)
+		ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
 out:
 	return ret;
 }
@@ -1253,7 +1252,7 @@ bail:
 	brelse(bh);
 
 	/* Release quota pointers in case we acquired them */
-	for (qtype = 0; qtype < MAXQUOTAS; qtype++)
+	for (qtype = 0; qtype < OCFS2_MAXQUOTAS; qtype++)
 		dqput(transfer_to[qtype]);
 
 	if (!status && attr->ia_valid & ATTR_MODE) {
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index a6c991c0fc98..a9b76de46047 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -162,7 +162,7 @@ static inline blkcnt_t ocfs2_inode_sector_count(struct inode *inode)
 {
 	int c_to_s_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits - 9;
 
-	return (blkcnt_t)(OCFS2_I(inode)->ip_clusters << c_to_s_bits);
+	return (blkcnt_t)OCFS2_I(inode)->ip_clusters << c_to_s_bits;
 }
 
 /* Validate that a bh contains a valid inode */
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 6219aaadeb08..74caffeeee1d 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -404,7 +404,7 @@ static int ocfs2_find_victim_alloc_group(struct inode *inode,
 	 * 'vict_blkno' was out of the valid range.
 	 */
 	if ((vict_blkno < le64_to_cpu(rec->c_blkno)) ||
-	    (vict_blkno >= (le32_to_cpu(ac_dinode->id1.bitmap1.i_total) <<
+	    (vict_blkno >= ((u64)le32_to_cpu(ac_dinode->id1.bitmap1.i_total) <<
 				bits_per_unit))) {
 		ret = -EINVAL;
 		goto out;
diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h
index f266d67df3c6..1eae330193a6 100644
--- a/fs/ocfs2/quota.h
+++ b/fs/ocfs2/quota.h
@@ -17,6 +17,9 @@
 
 #include "ocfs2.h"
 
+/* Number of quota types we support */
+#define OCFS2_MAXQUOTAS 2
+
 /*
  * In-memory structures
  */
@@ -39,7 +42,7 @@ struct ocfs2_recovery_chunk {
 };
 
 struct ocfs2_quota_recovery {
-	struct list_head r_list[MAXQUOTAS];	/* List of chunks to recover */
+	struct list_head r_list[OCFS2_MAXQUOTAS];	/* List of chunks to recover */
 };
 
 /* In-memory structure with quota header information */
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index b990a62cff50..c93d67220887 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -336,8 +336,8 @@ void ocfs2_unlock_global_qf(struct ocfs2_mem_dqinfo *oinfo, int ex)
 int ocfs2_global_read_info(struct super_block *sb, int type)
 {
 	struct inode *gqinode = NULL;
-	unsigned int ino[MAXQUOTAS] = { USER_QUOTA_SYSTEM_INODE,
-					GROUP_QUOTA_SYSTEM_INODE };
+	unsigned int ino[OCFS2_MAXQUOTAS] = { USER_QUOTA_SYSTEM_INODE,
+					      GROUP_QUOTA_SYSTEM_INODE };
 	struct ocfs2_global_disk_dqinfo dinfo;
 	struct mem_dqinfo *info = sb_dqinfo(sb, type);
 	struct ocfs2_mem_dqinfo *oinfo = info->dqi_priv;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2001862bf2b1..10b653930ee2 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -166,12 +166,12 @@ static int ocfs2_read_quota_block(struct inode *inode, u64 v_block,
 /* Check whether we understand format of quota files */
 static int ocfs2_local_check_quota_file(struct super_block *sb, int type)
 {
-	unsigned int lmagics[MAXQUOTAS] = OCFS2_LOCAL_QMAGICS;
-	unsigned int lversions[MAXQUOTAS] = OCFS2_LOCAL_QVERSIONS;
-	unsigned int gmagics[MAXQUOTAS] = OCFS2_GLOBAL_QMAGICS;
-	unsigned int gversions[MAXQUOTAS] = OCFS2_GLOBAL_QVERSIONS;
-	unsigned int ino[MAXQUOTAS] = { USER_QUOTA_SYSTEM_INODE,
-					GROUP_QUOTA_SYSTEM_INODE };
+	unsigned int lmagics[OCFS2_MAXQUOTAS] = OCFS2_LOCAL_QMAGICS;
+	unsigned int lversions[OCFS2_MAXQUOTAS] = OCFS2_LOCAL_QVERSIONS;
+	unsigned int gmagics[OCFS2_MAXQUOTAS] = OCFS2_GLOBAL_QMAGICS;
+	unsigned int gversions[OCFS2_MAXQUOTAS] = OCFS2_GLOBAL_QVERSIONS;
+	unsigned int ino[OCFS2_MAXQUOTAS] = { USER_QUOTA_SYSTEM_INODE,
+					      GROUP_QUOTA_SYSTEM_INODE };
 	struct buffer_head *bh = NULL;
 	struct inode *linode = sb_dqopt(sb)->files[type];
 	struct inode *ginode = NULL;
@@ -336,7 +336,7 @@ void ocfs2_free_quota_recovery(struct ocfs2_quota_recovery *rec)
 {
 	int type;
 
-	for (type = 0; type < MAXQUOTAS; type++)
+	for (type = 0; type < OCFS2_MAXQUOTAS; type++)
 		free_recovery_list(&(rec->r_list[type]));
 	kfree(rec);
 }
@@ -382,7 +382,7 @@ static struct ocfs2_quota_recovery *ocfs2_alloc_quota_recovery(void)
 	rec = kmalloc(sizeof(struct ocfs2_quota_recovery), GFP_NOFS);
 	if (!rec)
 		return NULL;
-	for (type = 0; type < MAXQUOTAS; type++)
+	for (type = 0; type < OCFS2_MAXQUOTAS; type++)
 		INIT_LIST_HEAD(&(rec->r_list[type]));
 	return rec;
 }
@@ -392,10 +392,11 @@ struct ocfs2_quota_recovery *ocfs2_begin_quota_recovery(
 						struct ocfs2_super *osb,
 						int slot_num)
 {
-	unsigned int feature[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
-					    OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
-	unsigned int ino[MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
-					LOCAL_GROUP_QUOTA_SYSTEM_INODE };
+	unsigned int feature[OCFS2_MAXQUOTAS] = {
+					OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
+					OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
+	unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
+					      LOCAL_GROUP_QUOTA_SYSTEM_INODE };
 	struct super_block *sb = osb->sb;
 	struct ocfs2_local_disk_dqinfo *ldinfo;
 	struct inode *lqinode;
@@ -412,7 +413,7 @@ struct ocfs2_quota_recovery *ocfs2_begin_quota_recovery(
 		return ERR_PTR(-ENOMEM);
 	/* First init... */
 
-	for (type = 0; type < MAXQUOTAS; type++) {
+	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type]))
 			continue;
 		/* At this point, journal of the slot is already replayed so
@@ -589,8 +590,8 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 				struct ocfs2_quota_recovery *rec,
 				int slot_num)
 {
-	unsigned int ino[MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
-					LOCAL_GROUP_QUOTA_SYSTEM_INODE };
+	unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
+					      LOCAL_GROUP_QUOTA_SYSTEM_INODE };
 	struct super_block *sb = osb->sb;
 	struct ocfs2_local_disk_dqinfo *ldinfo;
 	struct buffer_head *bh;
@@ -604,7 +605,7 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 	       "slot %u\n", osb->dev_str, slot_num);
 
 	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
-	for (type = 0; type < MAXQUOTAS; type++) {
+	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (list_empty(&(rec->r_list[type])))
 			continue;
 		trace_ocfs2_finish_quota_recovery(slot_num);
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 13a8537d8e8b..720aa389e0ea 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -591,7 +591,7 @@ static int ocfs2_control_release(struct inode *inode, struct file *file)
 		 */
 		ocfs2_control_this_node = -1;
 		running_proto.pv_major = 0;
-		running_proto.pv_major = 0;
+		running_proto.pv_minor = 0;
 	}
 
 out:
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 4142546aedae..93c85bc745e1 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -899,11 +899,12 @@ static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend)
 {
 	int type;
 	struct super_block *sb = osb->sb;
-	unsigned int feature[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
-					     OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
+	unsigned int feature[OCFS2_MAXQUOTAS] = {
+					OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
+					OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
 	int status = 0;
 
-	for (type = 0; type < MAXQUOTAS; type++) {
+	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type]))
 			continue;
 		if (unsuspend)
@@ -927,17 +928,19 @@ static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend)
 
 static int ocfs2_enable_quotas(struct ocfs2_super *osb)
 {
-	struct inode *inode[MAXQUOTAS] = { NULL, NULL };
+	struct inode *inode[OCFS2_MAXQUOTAS] = { NULL, NULL };
 	struct super_block *sb = osb->sb;
-	unsigned int feature[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
-					     OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
-	unsigned int ino[MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
+	unsigned int feature[OCFS2_MAXQUOTAS] = {
+					OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
+					OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
+	unsigned int ino[OCFS2_MAXQUOTAS] = {
+					LOCAL_USER_QUOTA_SYSTEM_INODE,
 					LOCAL_GROUP_QUOTA_SYSTEM_INODE };
 	int status;
 	int type;
 
 	sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NEGATIVE_USAGE;
-	for (type = 0; type < MAXQUOTAS; type++) {
+	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type]))
 			continue;
 		inode[type] = ocfs2_get_system_file_inode(osb, ino[type],
@@ -952,12 +955,12 @@ static int ocfs2_enable_quotas(struct ocfs2_super *osb)
 			goto out_quota_off;
 	}
 
-	for (type = 0; type < MAXQUOTAS; type++)
+	for (type = 0; type < OCFS2_MAXQUOTAS; type++)
 		iput(inode[type]);
 	return 0;
 out_quota_off:
 	ocfs2_disable_quotas(osb);
-	for (type = 0; type < MAXQUOTAS; type++)
+	for (type = 0; type < OCFS2_MAXQUOTAS; type++)
 		iput(inode[type]);
 	mlog_errno(status);
 	return status;
@@ -972,7 +975,7 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb)
 
 	/* We mostly ignore errors in this function because there's not much
 	 * we can do when we see them */
-	for (type = 0; type < MAXQUOTAS; type++) {
+	for (type = 0; type < OCFS2_MAXQUOTAS; type++) {
 		if (!sb_has_quota_loaded(sb, type))
 			continue;
 		/* Cancel periodic syncing before we grab dqonoff_mutex */
@@ -993,8 +996,9 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb)
 /* Handle quota on quotactl */
 static int ocfs2_quota_on(struct super_block *sb, int type, int format_id)
 {
-	unsigned int feature[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
-					     OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
+	unsigned int feature[OCFS2_MAXQUOTAS] = {
+					OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
+					OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
 
 	if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type]))
 		return -EINVAL;
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index ba8819702c56..138321b0c6c2 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -306,9 +306,7 @@ static const struct super_operations omfs_sops = {
  */
 static int omfs_get_imap(struct super_block *sb)
 {
-	int bitmap_size;
-	int array_size;
-	int count;
+	unsigned int bitmap_size, count, array_size;
 	struct omfs_sb_info *sbi = OMFS_SB(sb);
 	struct buffer_head *bh;
 	unsigned long **ptr;
@@ -473,6 +471,12 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_sys_blocksize = be32_to_cpu(omfs_sb->s_sys_blocksize);
 	mutex_init(&sbi->s_bitmap_lock);
 
+	if (sbi->s_num_blocks > OMFS_MAX_BLOCKS) {
+		printk(KERN_ERR "omfs: sysblock number (%llx) is out of range\n",
+		       (unsigned long long)sbi->s_num_blocks);
+		goto out_brelse_bh;
+	}
+
 	if (sbi->s_sys_blocksize > PAGE_SIZE) {
 		printk(KERN_ERR "omfs: sysblock size (%d) is out of range\n",
 			sbi->s_sys_blocksize);
diff --git a/fs/omfs/omfs_fs.h b/fs/omfs/omfs_fs.h
index ee5e4327de92..83a98330ed66 100644
--- a/fs/omfs/omfs_fs.h
+++ b/fs/omfs/omfs_fs.h
@@ -18,6 +18,7 @@
 #define OMFS_XOR_COUNT 19
 #define OMFS_MAX_BLOCK_SIZE 8192
 #define OMFS_MAX_CLUSTER_SIZE 8
+#define OMFS_MAX_BLOCKS (1ul << 31)
 
 struct omfs_super_block {
 	char s_fill1[256];
diff --git a/fs/proc/base.c b/fs/proc/base.c
index baf852b648ad..772efa45a452 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -376,37 +376,6 @@ static const struct file_operations proc_lstats_operations = {
 
 #endif
 
-#ifdef CONFIG_CGROUPS
-static int cgroup_open(struct inode *inode, struct file *file)
-{
-	struct pid *pid = PROC_I(inode)->pid;
-	return single_open(file, proc_cgroup_show, pid);
-}
-
-static const struct file_operations proc_cgroup_operations = {
-	.open		= cgroup_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif
-
-#ifdef CONFIG_PROC_PID_CPUSET
-
-static int cpuset_open(struct inode *inode, struct file *file)
-{
-	struct pid *pid = PROC_I(inode)->pid;
-	return single_open(file, proc_cpuset_show, pid);
-}
-
-static const struct file_operations proc_cpuset_operations = {
-	.open		= cpuset_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif
-
 static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
 			  struct pid *pid, struct task_struct *task)
 {
@@ -632,29 +601,35 @@ static const struct file_operations proc_single_file_operations = {
 	.release	= single_release,
 };
 
-static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
+
+struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
 {
-	struct task_struct *task = get_proc_task(file_inode(file));
-	struct mm_struct *mm;
+	struct task_struct *task = get_proc_task(inode);
+	struct mm_struct *mm = ERR_PTR(-ESRCH);
 
-	if (!task)
-		return -ESRCH;
+	if (task) {
+		mm = mm_access(task, mode);
+		put_task_struct(task);
 
-	mm = mm_access(task, mode);
-	put_task_struct(task);
+		if (!IS_ERR_OR_NULL(mm)) {
+			/* ensure this mm_struct can't be freed */
+			atomic_inc(&mm->mm_count);
+			/* but do not pin its memory */
+			mmput(mm);
+		}
+	}
+
+	return mm;
+}
+
+static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
+{
+	struct mm_struct *mm = proc_mem_open(inode, mode);
 
 	if (IS_ERR(mm))
 		return PTR_ERR(mm);
 
-	if (mm) {
-		/* ensure this mm_struct can't be freed */
-		atomic_inc(&mm->mm_count);
-		/* but do not pin its memory */
-		mmput(mm);
-	}
-
 	file->private_data = mm;
-
 	return 0;
 }
 
@@ -1590,7 +1565,6 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags)
 		put_task_struct(task);
 		return 1;
 	}
-	d_drop(dentry);
 	return 0;
 }
 
@@ -1727,9 +1701,6 @@ out:
 	put_task_struct(task);
 
 out_notask:
-	if (status <= 0)
-		d_drop(dentry);
-
 	return status;
 }
 
@@ -2573,10 +2544,10 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("latency",  S_IRUGO, proc_lstats_operations),
 #endif
 #ifdef CONFIG_PROC_PID_CPUSET
-	REG("cpuset",     S_IRUGO, proc_cpuset_operations),
+	ONE("cpuset",     S_IRUGO, proc_cpuset_show),
 #endif
 #ifdef CONFIG_CGROUPS
-	REG("cgroup",  S_IRUGO, proc_cgroup_operations),
+	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
 #endif
 	ONE("oom_score",  S_IRUGO, proc_oom_score),
 	REG("oom_adj",    S_IRUGO|S_IWUSR, proc_oom_adj_operations),
@@ -2643,8 +2614,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
 	/* no ->d_hash() rejects on procfs */
 	dentry = d_hash_and_lookup(mnt->mnt_root, &name);
 	if (dentry) {
-		shrink_dcache_parent(dentry);
-		d_drop(dentry);
+		d_invalidate(dentry);
 		dput(dentry);
 	}
 
@@ -2664,8 +2634,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
 	name.len = snprintf(buf, sizeof(buf), "%d", pid);
 	dentry = d_hash_and_lookup(dir, &name);
 	if (dentry) {
-		shrink_dcache_parent(dentry);
-		d_drop(dentry);
+		d_invalidate(dentry);
 		dput(dentry);
 	}
 
@@ -2919,10 +2888,10 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("latency",  S_IRUGO, proc_lstats_operations),
 #endif
 #ifdef CONFIG_PROC_PID_CPUSET
-	REG("cpuset",    S_IRUGO, proc_cpuset_operations),
+	ONE("cpuset",    S_IRUGO, proc_cpuset_show),
 #endif
 #ifdef CONFIG_CGROUPS
-	REG("cgroup",  S_IRUGO, proc_cgroup_operations),
+	ONE("cgroup",  S_IRUGO, proc_cgroup_show),
 #endif
 	ONE("oom_score", S_IRUGO, proc_oom_score),
 	REG("oom_adj",   S_IRUGO|S_IWUSR, proc_oom_adj_operations),
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 955bb55fab8c..e11d7c590bb0 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -129,8 +129,6 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
 		}
 		put_task_struct(task);
 	}
-
-	d_drop(dentry);
 	return 0;
 }
 
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 7da13e49128a..aa7a0ee182e1 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -268,8 +268,9 @@ extern int proc_remount(struct super_block *, int *, char *);
  * task_[no]mmu.c
  */
 struct proc_maps_private {
-	struct pid *pid;
+	struct inode *inode;
 	struct task_struct *task;
+	struct mm_struct *mm;
 #ifdef CONFIG_MMU
 	struct vm_area_struct *tail_vma;
 #endif
@@ -278,6 +279,8 @@ struct proc_maps_private {
 #endif
 };
 
+struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode);
+
 extern const struct file_operations proc_pid_maps_operations;
 extern const struct file_operations proc_tid_maps_operations;
 extern const struct file_operations proc_pid_numa_maps_operations;
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 6df8d0722c97..91a4e6426321 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -610,8 +610,10 @@ static void __init proc_kcore_text_init(void)
 struct kcore_list kcore_modules;
 static void __init add_modules_range(void)
 {
-	kclist_add(&kcore_modules, (void *)MODULES_VADDR,
+	if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) {
+		kclist_add(&kcore_modules, (void *)MODULES_VADDR,
 			MODULES_END - MODULES_VADDR, KCORE_VMALLOC);
+	}
 }
 #else
 static void __init add_modules_range(void)
diff --git a/fs/proc/page.c b/fs/proc/page.c
index e647c55275d9..1e3187da1fed 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -133,6 +133,9 @@ u64 stable_page_flags(struct page *page)
 	if (PageBuddy(page))
 		u |= 1 << KPF_BUDDY;
 
+	if (PageBalloon(page))
+		u |= 1 << KPF_BALLOON;
+
 	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
 
 	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index c34156888d70..4e0388cffe3d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -87,32 +87,14 @@ unsigned long task_statm(struct mm_struct *mm,
 
 #ifdef CONFIG_NUMA
 /*
- * These functions are for numa_maps but called in generic **maps seq_file
- * ->start(), ->stop() ops.
- *
- * numa_maps scans all vmas under mmap_sem and checks their mempolicy.
- * Each mempolicy object is controlled by reference counting. The problem here
- * is how to avoid accessing dead mempolicy object.
- *
- * Because we're holding mmap_sem while reading seq_file, it's safe to access
- * each vma's mempolicy, no vma objects will never drop refs to mempolicy.
- *
- * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy
- * is set and replaced under mmap_sem but unrefed and cleared under task_lock().
- * So, without task_lock(), we cannot trust get_vma_policy() because we cannot
- * gurantee the task never exits under us. But taking task_lock() around
- * get_vma_plicy() causes lock order problem.
- *
- * To access task->mempolicy without lock, we hold a reference count of an
- * object pointed by task->mempolicy and remember it. This will guarantee
- * that task->mempolicy points to an alive object or NULL in numa_maps accesses.
+ * Save get_task_policy() for show_numa_map().
  */
 static void hold_task_mempolicy(struct proc_maps_private *priv)
 {
 	struct task_struct *task = priv->task;
 
 	task_lock(task);
-	priv->task_mempolicy = task->mempolicy;
+	priv->task_mempolicy = get_task_policy(task);
 	mpol_get(priv->task_mempolicy);
 	task_unlock(task);
 }
@@ -129,124 +111,154 @@ static void release_task_mempolicy(struct proc_maps_private *priv)
 }
 #endif
 
-static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
+static void vma_stop(struct proc_maps_private *priv)
 {
-	if (vma && vma != priv->tail_vma) {
-		struct mm_struct *mm = vma->vm_mm;
-		release_task_mempolicy(priv);
-		up_read(&mm->mmap_sem);
-		mmput(mm);
-	}
+	struct mm_struct *mm = priv->mm;
+
+	release_task_mempolicy(priv);
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+}
+
+static struct vm_area_struct *
+m_next_vma(struct proc_maps_private *priv, struct vm_area_struct *vma)
+{
+	if (vma == priv->tail_vma)
+		return NULL;
+	return vma->vm_next ?: priv->tail_vma;
 }
 
-static void *m_start(struct seq_file *m, loff_t *pos)
+static void m_cache_vma(struct seq_file *m, struct vm_area_struct *vma)
+{
+	if (m->count < m->size)	/* vma is copied successfully */
+		m->version = m_next_vma(m->private, vma) ? vma->vm_start : -1UL;
+}
+
+static void *m_start(struct seq_file *m, loff_t *ppos)
 {
 	struct proc_maps_private *priv = m->private;
 	unsigned long last_addr = m->version;
 	struct mm_struct *mm;
-	struct vm_area_struct *vma, *tail_vma = NULL;
-	loff_t l = *pos;
-
-	/* Clear the per syscall fields in priv */
-	priv->task = NULL;
-	priv->tail_vma = NULL;
-
-	/*
-	 * We remember last_addr rather than next_addr to hit with
-	 * vmacache most of the time. We have zero last_addr at
-	 * the beginning and also after lseek. We will have -1 last_addr
-	 * after the end of the vmas.
-	 */
+	struct vm_area_struct *vma;
+	unsigned int pos = *ppos;
 
+	/* See m_cache_vma(). Zero at the start or after lseek. */
 	if (last_addr == -1UL)
 		return NULL;
 
-	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
+	priv->task = get_proc_task(priv->inode);
 	if (!priv->task)
 		return ERR_PTR(-ESRCH);
 
-	mm = mm_access(priv->task, PTRACE_MODE_READ);
-	if (!mm || IS_ERR(mm))
-		return mm;
-	down_read(&mm->mmap_sem);
+	mm = priv->mm;
+	if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+		return NULL;
 
-	tail_vma = get_gate_vma(priv->task->mm);
-	priv->tail_vma = tail_vma;
+	down_read(&mm->mmap_sem);
 	hold_task_mempolicy(priv);
-	/* Start with last addr hint */
-	vma = find_vma(mm, last_addr);
-	if (last_addr && vma) {
-		vma = vma->vm_next;
-		goto out;
+	priv->tail_vma = get_gate_vma(mm);
+
+	if (last_addr) {
+		vma = find_vma(mm, last_addr);
+		if (vma && (vma = m_next_vma(priv, vma)))
+			return vma;
 	}
 
-	/*
-	 * Check the vma index is within the range and do
-	 * sequential scan until m_index.
-	 */
-	vma = NULL;
-	if ((unsigned long)l < mm->map_count) {
-		vma = mm->mmap;
-		while (l-- && vma)
+	m->version = 0;
+	if (pos < mm->map_count) {
+		for (vma = mm->mmap; pos; pos--) {
+			m->version = vma->vm_start;
 			vma = vma->vm_next;
-		goto out;
+		}
+		return vma;
 	}
 
-	if (l != mm->map_count)
-		tail_vma = NULL; /* After gate vma */
+	/* we do not bother to update m->version in this case */
+	if (pos == mm->map_count && priv->tail_vma)
+		return priv->tail_vma;
 
-out:
-	if (vma)
-		return vma;
-
-	release_task_mempolicy(priv);
-	/* End of vmas has been reached */
-	m->version = (tail_vma != NULL)? 0: -1UL;
-	up_read(&mm->mmap_sem);
-	mmput(mm);
-	return tail_vma;
+	vma_stop(priv);
+	return NULL;
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct proc_maps_private *priv = m->private;
-	struct vm_area_struct *vma = v;
-	struct vm_area_struct *tail_vma = priv->tail_vma;
+	struct vm_area_struct *next;
 
 	(*pos)++;
-	if (vma && (vma != tail_vma) && vma->vm_next)
-		return vma->vm_next;
-	vma_stop(priv, vma);
-	return (vma != tail_vma)? tail_vma: NULL;
+	next = m_next_vma(priv, v);
+	if (!next)
+		vma_stop(priv);
+	return next;
 }
 
 static void m_stop(struct seq_file *m, void *v)
 {
 	struct proc_maps_private *priv = m->private;
-	struct vm_area_struct *vma = v;
 
-	if (!IS_ERR(vma))
-		vma_stop(priv, vma);
-	if (priv->task)
+	if (!IS_ERR_OR_NULL(v))
+		vma_stop(priv);
+	if (priv->task) {
 		put_task_struct(priv->task);
+		priv->task = NULL;
+	}
+}
+
+static int proc_maps_open(struct inode *inode, struct file *file,
+			const struct seq_operations *ops, int psize)
+{
+	struct proc_maps_private *priv = __seq_open_private(file, ops, psize);
+
+	if (!priv)
+		return -ENOMEM;
+
+	priv->inode = inode;
+	priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
+	if (IS_ERR(priv->mm)) {
+		int err = PTR_ERR(priv->mm);
+
+		seq_release_private(inode, file);
+		return err;
+	}
+
+	return 0;
+}
+
+static int proc_map_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct proc_maps_private *priv = seq->private;
+
+	if (priv->mm)
+		mmdrop(priv->mm);
+
+	return seq_release_private(inode, file);
 }
 
 static int do_maps_open(struct inode *inode, struct file *file,
 			const struct seq_operations *ops)
 {
-	struct proc_maps_private *priv;
-	int ret = -ENOMEM;
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (priv) {
-		priv->pid = proc_pid(inode);
-		ret = seq_open(file, ops);
-		if (!ret) {
-			struct seq_file *m = file->private_data;
-			m->private = priv;
-		} else {
-			kfree(priv);
-		}
+	return proc_maps_open(inode, file, ops,
+				sizeof(struct proc_maps_private));
+}
+
+static pid_t pid_of_stack(struct proc_maps_private *priv,
+				struct vm_area_struct *vma, bool is_pid)
+{
+	struct inode *inode = priv->inode;
+	struct task_struct *task;
+	pid_t ret = 0;
+
+	rcu_read_lock();
+	task = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (task) {
+		task = task_of_stack(task, vma, is_pid);
+		if (task)
+			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
 	}
+	rcu_read_unlock();
+
 	return ret;
 }
 
@@ -256,7 +268,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
 	struct proc_maps_private *priv = m->private;
-	struct task_struct *task = priv->task;
 	vm_flags_t flags = vma->vm_flags;
 	unsigned long ino = 0;
 	unsigned long long pgoff = 0;
@@ -321,8 +332,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 			goto done;
 		}
 
-		tid = vm_is_stack(task, vma, is_pid);
-
+		tid = pid_of_stack(priv, vma, is_pid);
 		if (tid != 0) {
 			/*
 			 * Thread stack in /proc/PID/task/TID/maps or
@@ -349,15 +359,8 @@ done:
 
 static int show_map(struct seq_file *m, void *v, int is_pid)
 {
-	struct vm_area_struct *vma = v;
-	struct proc_maps_private *priv = m->private;
-	struct task_struct *task = priv->task;
-
-	show_map_vma(m, vma, is_pid);
-
-	if (m->count < m->size)  /* vma is copied successfully */
-		m->version = (vma != get_gate_vma(task->mm))
-			? vma->vm_start : 0;
+	show_map_vma(m, v, is_pid);
+	m_cache_vma(m, v);
 	return 0;
 }
 
@@ -399,14 +402,14 @@ const struct file_operations proc_pid_maps_operations = {
 	.open		= pid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 
 const struct file_operations proc_tid_maps_operations = {
 	.open		= tid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 
 /*
@@ -583,8 +586,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 
 static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
-	struct proc_maps_private *priv = m->private;
-	struct task_struct *task = priv->task;
 	struct vm_area_struct *vma = v;
 	struct mem_size_stats mss;
 	struct mm_walk smaps_walk = {
@@ -637,10 +638,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 				mss.nonlinear >> 10);
 
 	show_smap_vma_flags(m, vma);
-
-	if (m->count < m->size)  /* vma is copied successfully */
-		m->version = (vma != get_gate_vma(task->mm))
-			? vma->vm_start : 0;
+	m_cache_vma(m, vma);
 	return 0;
 }
 
@@ -682,14 +680,14 @@ const struct file_operations proc_pid_smaps_operations = {
 	.open		= pid_smaps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 
 const struct file_operations proc_tid_smaps_operations = {
 	.open		= tid_smaps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 
 /*
@@ -829,8 +827,21 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			.private = &cp,
 		};
 		down_read(&mm->mmap_sem);
-		if (type == CLEAR_REFS_SOFT_DIRTY)
+		if (type == CLEAR_REFS_SOFT_DIRTY) {
+			for (vma = mm->mmap; vma; vma = vma->vm_next) {
+				if (!(vma->vm_flags & VM_SOFTDIRTY))
+					continue;
+				up_read(&mm->mmap_sem);
+				down_write(&mm->mmap_sem);
+				for (vma = mm->mmap; vma; vma = vma->vm_next) {
+					vma->vm_flags &= ~VM_SOFTDIRTY;
+					vma_set_page_prot(vma);
+				}
+				downgrade_write(&mm->mmap_sem);
+				break;
+			}
 			mmu_notifier_invalidate_range_start(mm, 0, -1);
+		}
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
 			cp.vma = vma;
 			if (is_vm_hugetlb_page(vma))
@@ -850,10 +861,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				continue;
 			if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
 				continue;
-			if (type == CLEAR_REFS_SOFT_DIRTY) {
-				if (vma->vm_flags & VM_SOFTDIRTY)
-					vma->vm_flags &= ~VM_SOFTDIRTY;
-			}
 			walk_page_range(vma->vm_start, vma->vm_end,
 					&clear_refs_walk);
 		}
@@ -1029,7 +1036,6 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	spinlock_t *ptl;
 	pte_t *pte;
 	int err = 0;
-	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
@@ -1043,6 +1049,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 
 		for (; addr != end; addr += PAGE_SIZE) {
 			unsigned long offset;
+			pagemap_entry_t pme;
 
 			offset = (addr & ~PAGEMAP_WALK_MASK) >>
 					PAGE_SHIFT;
@@ -1057,32 +1064,51 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 
 	if (pmd_trans_unstable(pmd))
 		return 0;
-	for (; addr != end; addr += PAGE_SIZE) {
-		int flags2;
-
-		/* check to see if we've left 'vma' behind
-		 * and need a new, higher one */
-		if (vma && (addr >= vma->vm_end)) {
-			vma = find_vma(walk->mm, addr);
-			if (vma && (vma->vm_flags & VM_SOFTDIRTY))
-				flags2 = __PM_SOFT_DIRTY;
-			else
-				flags2 = 0;
-			pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
+
+	while (1) {
+		/* End of address space hole, which we mark as non-present. */
+		unsigned long hole_end;
+
+		if (vma)
+			hole_end = min(end, vma->vm_start);
+		else
+			hole_end = end;
+
+		for (; addr < hole_end; addr += PAGE_SIZE) {
+			pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				return err;
 		}
 
-		/* check that 'vma' actually covers this address,
-		 * and that it isn't a huge page vma */
-		if (vma && (vma->vm_start <= addr) &&
-		    !is_vm_hugetlb_page(vma)) {
+		if (!vma || vma->vm_start >= end)
+			break;
+		/*
+		 * We can't possibly be in a hugetlb VMA. In general,
+		 * for a mm_walk with a pmd_entry and a hugetlb_entry,
+		 * the pmd_entry can only be called on addresses in a
+		 * hugetlb if the walk starts in a non-hugetlb VMA and
+		 * spans a hugepage VMA. Since pagemap_read walks are
+		 * PMD-sized and PMD-aligned, this will never be true.
+		 */
+		BUG_ON(is_vm_hugetlb_page(vma));
+
+		/* Addresses in the VMA. */
+		for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
+			pagemap_entry_t pme;
 			pte = pte_offset_map(pmd, addr);
 			pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
-			/* unmap before userspace copy */
 			pte_unmap(pte);
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				return err;
 		}
-		err = add_to_pagemap(addr, &pme, pm);
-		if (err)
-			return err;
+
+		if (addr == end)
+			break;
+
+		vma = find_vma(walk->mm, addr);
 	}
 
 	cond_resched();
@@ -1415,7 +1441,6 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	struct vm_area_struct *vma = v;
 	struct numa_maps *md = &numa_priv->md;
 	struct file *file = vma->vm_file;
-	struct task_struct *task = proc_priv->task;
 	struct mm_struct *mm = vma->vm_mm;
 	struct mm_walk walk = {};
 	struct mempolicy *pol;
@@ -1435,9 +1460,13 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	walk.private = md;
 	walk.mm = mm;
 
-	pol = get_vma_policy(task, vma, vma->vm_start);
-	mpol_to_str(buffer, sizeof(buffer), pol);
-	mpol_cond_put(pol);
+	pol = __get_vma_policy(vma, vma->vm_start);
+	if (pol) {
+		mpol_to_str(buffer, sizeof(buffer), pol);
+		mpol_cond_put(pol);
+	} else {
+		mpol_to_str(buffer, sizeof(buffer), proc_priv->task_mempolicy);
+	}
 
 	seq_printf(m, "%08lx %s", vma->vm_start, buffer);
 
@@ -1447,7 +1476,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_puts(m, " heap");
 	} else {
-		pid_t tid = vm_is_stack(task, vma, is_pid);
+		pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
 		if (tid != 0) {
 			/*
 			 * Thread stack in /proc/PID/task/TID/maps or
@@ -1495,9 +1524,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 			seq_printf(m, " N%d=%lu", nid, md->node[nid]);
 out:
 	seq_putc(m, '\n');
-
-	if (m->count < m->size)
-		m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0;
+	m_cache_vma(m, vma);
 	return 0;
 }
 
@@ -1528,20 +1555,8 @@ static const struct seq_operations proc_tid_numa_maps_op = {
 static int numa_maps_open(struct inode *inode, struct file *file,
 			  const struct seq_operations *ops)
 {
-	struct numa_maps_private *priv;
-	int ret = -ENOMEM;
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (priv) {
-		priv->proc_maps.pid = proc_pid(inode);
-		ret = seq_open(file, ops);
-		if (!ret) {
-			struct seq_file *m = file->private_data;
-			m->private = priv;
-		} else {
-			kfree(priv);
-		}
-	}
-	return ret;
+	return proc_maps_open(inode, file, ops,
+				sizeof(struct numa_maps_private));
 }
 
 static int pid_numa_maps_open(struct inode *inode, struct file *file)
@@ -1558,13 +1573,13 @@ const struct file_operations proc_pid_numa_maps_operations = {
 	.open		= pid_numa_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 
 const struct file_operations proc_tid_numa_maps_operations = {
 	.open		= tid_numa_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= proc_map_release,
 };
 #endif /* CONFIG_NUMA */
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 678455d2d683..599ec2e20104 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -123,6 +123,25 @@ unsigned long task_statm(struct mm_struct *mm,
 	return size;
 }
 
+static pid_t pid_of_stack(struct proc_maps_private *priv,
+				struct vm_area_struct *vma, bool is_pid)
+{
+	struct inode *inode = priv->inode;
+	struct task_struct *task;
+	pid_t ret = 0;
+
+	rcu_read_lock();
+	task = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (task) {
+		task = task_of_stack(task, vma, is_pid);
+		if (task)
+			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 /*
  * display a single VMA to a sequenced file
  */
@@ -163,7 +182,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
 		seq_pad(m, ' ');
 		seq_path(m, &file->f_path, "");
 	} else if (mm) {
-		pid_t tid = vm_is_stack(priv->task, vma, is_pid);
+		pid_t tid = pid_of_stack(priv, vma, is_pid);
 
 		if (tid != 0) {
 			seq_pad(m, ' ');
@@ -212,22 +231,22 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 	loff_t n = *pos;
 
 	/* pin the task and mm whilst we play with them */
-	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
+	priv->task = get_proc_task(priv->inode);
 	if (!priv->task)
 		return ERR_PTR(-ESRCH);
 
-	mm = mm_access(priv->task, PTRACE_MODE_READ);
-	if (!mm || IS_ERR(mm)) {
-		put_task_struct(priv->task);
-		priv->task = NULL;
-		return mm;
-	}
-	down_read(&mm->mmap_sem);
+	mm = priv->mm;
+	if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+		return NULL;
 
+	down_read(&mm->mmap_sem);
 	/* start from the Nth VMA */
 	for (p = rb_first(&mm->mm_rb); p; p = rb_next(p))
 		if (n-- == 0)
 			return p;
+
+	up_read(&mm->mmap_sem);
+	mmput(mm);
 	return NULL;
 }
 
@@ -235,11 +254,13 @@ static void m_stop(struct seq_file *m, void *_vml)
 {
 	struct proc_maps_private *priv = m->private;
 
+	if (!IS_ERR_OR_NULL(_vml)) {
+		up_read(&priv->mm->mmap_sem);
+		mmput(priv->mm);
+	}
 	if (priv->task) {
-		struct mm_struct *mm = priv->task->mm;
-		up_read(&mm->mmap_sem);
-		mmput(mm);
 		put_task_struct(priv->task);
+		priv->task = NULL;
 	}
 }
 
@@ -269,20 +290,33 @@ static int maps_open(struct inode *inode, struct file *file,
 		     const struct seq_operations *ops)
 {
 	struct proc_maps_private *priv;
-	int ret = -ENOMEM;
-
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (priv) {
-		priv->pid = proc_pid(inode);
-		ret = seq_open(file, ops);
-		if (!ret) {
-			struct seq_file *m = file->private_data;
-			m->private = priv;
-		} else {
-			kfree(priv);
-		}
+
+	priv = __seq_open_private(file, ops, sizeof(*priv));
+	if (!priv)
+		return -ENOMEM;
+
+	priv->inode = inode;
+	priv->mm = proc_mem_open(inode, PTRACE_MODE_READ);
+	if (IS_ERR(priv->mm)) {
+		int err = PTR_ERR(priv->mm);
+
+		seq_release_private(inode, file);
+		return err;
 	}
-	return ret;
+
+	return 0;
+}
+
+
+static int map_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct proc_maps_private *priv = seq->private;
+
+	if (priv->mm)
+		mmdrop(priv->mm);
+
+	return seq_release_private(inode, file);
 }
 
 static int pid_maps_open(struct inode *inode, struct file *file)
@@ -299,13 +333,13 @@ const struct file_operations proc_pid_maps_operations = {
 	.open		= pid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= map_release,
 };
 
 const struct file_operations proc_tid_maps_operations = {
 	.open		= tid_maps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release_private,
+	.release	= map_release,
 };
 
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 192297b0090d..fafb7a02a5d6 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -320,10 +320,10 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 						compressed ? ".enc.z" : "");
 		break;
 	case PSTORE_TYPE_CONSOLE:
-		sprintf(name, "console-%s", psname);
+		sprintf(name, "console-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_FTRACE:
-		sprintf(name, "ftrace-%s", psname);
+		sprintf(name, "ftrace-%s-%lld", psname, id);
 		break;
 	case PSTORE_TYPE_MCE:
 		sprintf(name, "mce-%s-%lld", psname, id);
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index f2d0eee9d1f1..8b663b2d9562 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2725,7 +2725,7 @@ static int __init dquot_init(void)
 		panic("Cannot create dquot hash table");
 
 	for (i = 0; i < _DQST_DQSTAT_LAST; i++) {
-		ret = percpu_counter_init(&dqstats.counter[i], 0);
+		ret = percpu_counter_init(&dqstats.counter[i], 0, GFP_KERNEL);
 		if (ret)
 			panic("Cannot create dquot stat counters");
 	}
diff --git a/fs/read_write.c b/fs/read_write.c
index 009d8542a889..7d9318c3d43c 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -513,6 +513,8 @@ ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t
 	return ret;
 }
 
+EXPORT_SYMBOL(__kernel_write);
+
 ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
 {
 	ssize_t ret;
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index a88b1b3e7db3..d571e173a990 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -699,11 +699,13 @@ static int add_to_chunk(struct buffer_chunk *chunk, struct buffer_head *bh,
 	chunk->bh[chunk->nr++] = bh;
 	if (chunk->nr >= CHUNK_SIZE) {
 		ret = 1;
-		if (lock)
+		if (lock) {
 			spin_unlock(lock);
-		fn(chunk);
-		if (lock)
+			fn(chunk);
 			spin_lock(lock);
+		} else {
+			fn(chunk);
+		}
 	}
 	return ret;
 }
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 735c2c2b4536..1894d96ccb7c 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -506,6 +506,9 @@ typedef struct reiserfs_proc_info_data {
 } reiserfs_proc_info_data_t;
 #endif
 
+/* Number of quota types we support */
+#define REISERFS_MAXQUOTAS 2
+
 /* reiserfs union of in-core super block data */
 struct reiserfs_sb_info {
 	/* Buffer containing the super block */
@@ -615,7 +618,7 @@ struct reiserfs_sb_info {
 	spinlock_t old_work_lock;     /* protects old_work and work_queued */
 
 #ifdef CONFIG_QUOTA
-	char *s_qf_names[MAXQUOTAS];
+	char *s_qf_names[REISERFS_MAXQUOTAS];
 	int s_jquota_fmt;
 #endif
 	char *s_jdev;		/* Stored jdev for mount option showing */
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index d46e88a33b02..f1376c92cf74 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -206,7 +206,7 @@ static int finish_unfinished(struct super_block *s)
 #ifdef CONFIG_QUOTA
 	int i;
 	int ms_active_set;
-	int quota_enabled[MAXQUOTAS];
+	int quota_enabled[REISERFS_MAXQUOTAS];
 #endif
 
 	/* compose key to look for "save" links */
@@ -227,7 +227,7 @@ static int finish_unfinished(struct super_block *s)
 		s->s_flags |= MS_ACTIVE;
 	}
 	/* Turn on quotas so that they are updated correctly */
-	for (i = 0; i < MAXQUOTAS; i++) {
+	for (i = 0; i < REISERFS_MAXQUOTAS; i++) {
 		quota_enabled[i] = 1;
 		if (REISERFS_SB(s)->s_qf_names[i]) {
 			int ret;
@@ -370,7 +370,7 @@ static int finish_unfinished(struct super_block *s)
 #ifdef CONFIG_QUOTA
 	/* Turn quotas off */
 	reiserfs_write_unlock(s);
-	for (i = 0; i < MAXQUOTAS; i++) {
+	for (i = 0; i < REISERFS_MAXQUOTAS; i++) {
 		if (sb_dqopt(s)->files[i] && quota_enabled[i])
 			dquot_quota_off(s, i);
 	}
@@ -1360,7 +1360,7 @@ static void handle_quota_files(struct super_block *s, char **qf_names,
 {
 	int i;
 
-	for (i = 0; i < MAXQUOTAS; i++) {
+	for (i = 0; i < REISERFS_MAXQUOTAS; i++) {
 		if (qf_names[i] != REISERFS_SB(s)->s_qf_names[i])
 			kfree(REISERFS_SB(s)->s_qf_names[i]);
 		REISERFS_SB(s)->s_qf_names[i] = qf_names[i];
@@ -1381,7 +1381,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	struct reiserfs_journal *journal = SB_JOURNAL(s);
 	char *new_opts = kstrdup(arg, GFP_KERNEL);
 	int err;
-	char *qf_names[MAXQUOTAS];
+	char *qf_names[REISERFS_MAXQUOTAS];
 	unsigned int qfmt = 0;
 #ifdef CONFIG_QUOTA
 	int i;
@@ -1400,7 +1400,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	    (s, arg, &mount_options, &blocks, NULL, &commit_max_age,
 	    qf_names, &qfmt)) {
 #ifdef CONFIG_QUOTA
-		for (i = 0; i < MAXQUOTAS; i++)
+		for (i = 0; i < REISERFS_MAXQUOTAS; i++)
 			if (qf_names[i] != REISERFS_SB(s)->s_qf_names[i])
 				kfree(qf_names[i]);
 #endif
@@ -1844,7 +1844,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	char *jdev_name;
 	struct reiserfs_sb_info *sbi;
 	int errval = -EINVAL;
-	char *qf_names[MAXQUOTAS] = {};
+	char *qf_names[REISERFS_MAXQUOTAS] = {};
 	unsigned int qfmt = 0;
 
 	save_mount_options(s, data);
@@ -2169,7 +2169,7 @@ error_unlocked:
 #ifdef CONFIG_QUOTA
 	{
 		int j;
-		for (j = 0; j < MAXQUOTAS; j++)
+		for (j = 0; j < REISERFS_MAXQUOTAS; j++)
 			kfree(qf_names[j]);
 	}
 #endif
diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h
index 857ec7e3016f..f620e9678dd5 100644
--- a/fs/reiserfs/xattr.h
+++ b/fs/reiserfs/xattr.h
@@ -7,7 +7,6 @@ struct inode;
 struct dentry;
 struct iattr;
 struct super_block;
-struct nameidata;
 
 int reiserfs_xattr_register_handlers(void) __init;
 void reiserfs_xattr_unregister_handlers(void);
diff --git a/fs/super.c b/fs/super.c
index b9a214d2fe98..eae088f6aaae 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -80,6 +80,8 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
 	inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
 	dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
 	total_objects = dentries + inodes + fs_objects + 1;
+	if (!total_objects)
+		total_objects = 1;
 
 	/* proportion the scan between the caches */
 	dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
@@ -175,7 +177,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 		goto fail;
 
 	for (i = 0; i < SB_FREEZE_LEVELS; i++) {
-		if (percpu_counter_init(&s->s_writers.counter[i], 0) < 0)
+		if (percpu_counter_init(&s->s_writers.counter[i], 0,
+					GFP_KERNEL) < 0)
 			goto fail;
 		lockdep_init_map(&s->s_writers.lock_map[i], sb_writers_name[i],
 				 &type->s_writers_key[i], 0);
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 80c350216ea8..b46ffa94372a 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -333,8 +333,7 @@ static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg
 		spin_lock_irq(&ctx->wqh.lock);
 		if (!timerfd_canceled(ctx)) {
 			ctx->ticks = ticks;
-			if (ticks)
-				wake_up_locked(&ctx->wqh);
+			wake_up_locked(&ctx->wqh);
 		} else
 			ret = -ECANCELED;
 		spin_unlock_irq(&ctx->wqh.lock);
diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c
index aa13ad053b14..26b69b2d4a45 100644
--- a/fs/ubifs/commit.c
+++ b/fs/ubifs/commit.c
@@ -166,10 +166,6 @@ static int do_commit(struct ubifs_info *c)
 	err = ubifs_orphan_end_commit(c);
 	if (err)
 		goto out;
-	old_ltail_lnum = c->ltail_lnum;
-	err = ubifs_log_end_commit(c, new_ltail_lnum);
-	if (err)
-		goto out;
 	err = dbg_check_old_index(c, &zroot);
 	if (err)
 		goto out;
@@ -202,7 +198,9 @@ static int do_commit(struct ubifs_info *c)
 		c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
 	else
 		c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_NO_ORPHS);
-	err = ubifs_write_master(c);
+
+	old_ltail_lnum = c->ltail_lnum;
+	err = ubifs_log_end_commit(c, new_ltail_lnum);
 	if (err)
 		goto out;
 
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 177b0152fef4..7ed13e1e216a 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -334,9 +334,9 @@ void ubifs_dump_node(const struct ubifs_info *c, const void *node)
 		pr_err("\tkey_fmt        %d (%s)\n",
 		       (int)sup->key_fmt, get_key_fmt(sup->key_fmt));
 		pr_err("\tflags          %#x\n", sup_flags);
-		pr_err("\t  big_lpt      %u\n",
+		pr_err("\tbig_lpt        %u\n",
 		       !!(sup_flags & UBIFS_FLG_BIGLPT));
-		pr_err("\t  space_fixup  %u\n",
+		pr_err("\tspace_fixup    %u\n",
 		       !!(sup_flags & UBIFS_FLG_SPACE_FIXUP));
 		pr_err("\tmin_io_size    %u\n", le32_to_cpu(sup->min_io_size));
 		pr_err("\tleb_size       %u\n", le32_to_cpu(sup->leb_size));
@@ -2462,7 +2462,7 @@ static int power_cut_emulated(struct ubifs_info *c, int lnum, int write)
 
 			if (chance(1, 2)) {
 				d->pc_delay = 1;
-				/* Fail withing 1 minute */
+				/* Fail within 1 minute */
 				delay = prandom_u32() % 60000;
 				d->pc_timeout = jiffies;
 				d->pc_timeout += msecs_to_jiffies(delay);
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 0e045e75abd8..fb166e204441 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -546,15 +546,14 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 	int aligned_dlen, aligned_ilen, sync = IS_DIRSYNC(dir);
 	int last_reference = !!(deletion && inode->i_nlink == 0);
 	struct ubifs_inode *ui = ubifs_inode(inode);
-	struct ubifs_inode *dir_ui = ubifs_inode(dir);
+	struct ubifs_inode *host_ui = ubifs_inode(dir);
 	struct ubifs_dent_node *dent;
 	struct ubifs_ino_node *ino;
 	union ubifs_key dent_key, ino_key;
 
 	dbg_jnl("ino %lu, dent '%.*s', data len %d in dir ino %lu",
 		inode->i_ino, nm->len, nm->name, ui->data_len, dir->i_ino);
-	ubifs_assert(dir_ui->data_len == 0);
-	ubifs_assert(mutex_is_locked(&dir_ui->ui_mutex));
+	ubifs_assert(mutex_is_locked(&host_ui->ui_mutex));
 
 	dlen = UBIFS_DENT_NODE_SZ + nm->len + 1;
 	ilen = UBIFS_INO_NODE_SZ;
@@ -658,7 +657,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 	ui->synced_i_size = ui->ui_size;
 	spin_unlock(&ui->ui_lock);
 	mark_inode_clean(c, ui);
-	mark_inode_clean(c, dir_ui);
+	mark_inode_clean(c, host_ui);
 	return 0;
 
 out_finish:
diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c
index a47ddfc9be6b..c14628fbeee2 100644
--- a/fs/ubifs/log.c
+++ b/fs/ubifs/log.c
@@ -106,10 +106,14 @@ static inline long long empty_log_bytes(const struct ubifs_info *c)
 	h = (long long)c->lhead_lnum * c->leb_size + c->lhead_offs;
 	t = (long long)c->ltail_lnum * c->leb_size;
 
-	if (h >= t)
+	if (h > t)
 		return c->log_bytes - h + t;
-	else
+	else if (h != t)
 		return t - h;
+	else if (c->lhead_lnum != c->ltail_lnum)
+		return 0;
+	else
+		return c->log_bytes;
 }
 
 /**
@@ -447,9 +451,9 @@ out:
  * @ltail_lnum: new log tail LEB number
  *
  * This function is called on when the commit operation was finished. It
- * moves log tail to new position and unmaps LEBs which contain obsolete data.
- * Returns zero in case of success and a negative error code in case of
- * failure.
+ * moves log tail to new position and updates the master node so that it stores
+ * the new log tail LEB number. Returns zero in case of success and a negative
+ * error code in case of failure.
  */
 int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum)
 {
@@ -477,7 +481,12 @@ int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum)
 	spin_unlock(&c->buds_lock);
 
 	err = dbg_check_bud_bytes(c);
+	if (err)
+		goto out;
 
+	err = ubifs_write_master(c);
+
+out:
 	mutex_unlock(&c->log_mutex);
 	return err;
 }
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 86c6743ec1fe..bb15771b92ae 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -223,11 +223,18 @@ out:
 
 static int udf_release_file(struct inode *inode, struct file *filp)
 {
-	if (filp->f_mode & FMODE_WRITE) {
+	if (filp->f_mode & FMODE_WRITE &&
+	    atomic_read(&inode->i_writecount) > 1) {
+		/*
+		 * Grab i_mutex to avoid races with writes changing i_size
+		 * while we are running.
+		 */
+		mutex_lock(&inode->i_mutex);
 		down_write(&UDF_I(inode)->i_data_sem);
 		udf_discard_prealloc(inode);
 		udf_truncate_tail_extent(inode);
 		up_write(&UDF_I(inode)->i_data_sem);
+		mutex_unlock(&inode->i_mutex);
 	}
 	return 0;
 }
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 08598843288f..c9b4df5810d5 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1277,7 +1277,7 @@ update_time:
  */
 #define UDF_MAX_ICB_NESTING 1024
 
-static int udf_read_inode(struct inode *inode)
+static int udf_read_inode(struct inode *inode, bool hidden_inode)
 {
 	struct buffer_head *bh = NULL;
 	struct fileEntry *fe;
@@ -1436,8 +1436,11 @@ reread:
 
 	link_count = le16_to_cpu(fe->fileLinkCount);
 	if (!link_count) {
-		ret = -ESTALE;
-		goto out;
+		if (!hidden_inode) {
+			ret = -ESTALE;
+			goto out;
+		}
+		link_count = 1;
 	}
 	set_nlink(inode, link_count);
 
@@ -1826,7 +1829,8 @@ out:
 	return err;
 }
 
-struct inode *udf_iget(struct super_block *sb, struct kernel_lb_addr *ino)
+struct inode *__udf_iget(struct super_block *sb, struct kernel_lb_addr *ino,
+			 bool hidden_inode)
 {
 	unsigned long block = udf_get_lb_pblock(sb, ino, 0);
 	struct inode *inode = iget_locked(sb, block);
@@ -1839,7 +1843,7 @@ struct inode *udf_iget(struct super_block *sb, struct kernel_lb_addr *ino)
 		return inode;
 
 	memcpy(&UDF_I(inode)->i_location, ino, sizeof(struct kernel_lb_addr));
-	err = udf_read_inode(inode);
+	err = udf_read_inode(inode, hidden_inode);
 	if (err < 0) {
 		iget_failed(inode);
 		return ERR_PTR(err);
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 5401fc33f5cc..e229315bbf7a 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -959,7 +959,7 @@ struct inode *udf_find_metadata_inode_efe(struct super_block *sb,
 	addr.logicalBlockNum = meta_file_loc;
 	addr.partitionReferenceNum = partition_num;
 
-	metadata_fe = udf_iget(sb, &addr);
+	metadata_fe = udf_iget_special(sb, &addr);
 
 	if (IS_ERR(metadata_fe)) {
 		udf_warn(sb, "metadata inode efe not found\n");
@@ -1020,7 +1020,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
 		udf_debug("Bitmap file location: block = %d part = %d\n",
 			  addr.logicalBlockNum, addr.partitionReferenceNum);
 
-		fe = udf_iget(sb, &addr);
+		fe = udf_iget_special(sb, &addr);
 		if (IS_ERR(fe)) {
 			if (sb->s_flags & MS_RDONLY)
 				udf_warn(sb, "bitmap inode efe not found but it's ok since the disc is mounted read-only\n");
@@ -1119,7 +1119,7 @@ static int udf_fill_partdesc_info(struct super_block *sb,
 		};
 		struct inode *inode;
 
-		inode = udf_iget(sb, &loc);
+		inode = udf_iget_special(sb, &loc);
 		if (IS_ERR(inode)) {
 			udf_debug("cannot load unallocSpaceTable (part %d)\n",
 				  p_index);
@@ -1154,7 +1154,7 @@ static int udf_fill_partdesc_info(struct super_block *sb,
 		};
 		struct inode *inode;
 
-		inode = udf_iget(sb, &loc);
+		inode = udf_iget_special(sb, &loc);
 		if (IS_ERR(inode)) {
 			udf_debug("cannot load freedSpaceTable (part %d)\n",
 				  p_index);
@@ -1198,7 +1198,7 @@ static void udf_find_vat_block(struct super_block *sb, int p_index,
 	     vat_block >= map->s_partition_root &&
 	     vat_block >= start_block - 3; vat_block--) {
 		ino.logicalBlockNum = vat_block - map->s_partition_root;
-		inode = udf_iget(sb, &ino);
+		inode = udf_iget_special(sb, &ino);
 		if (!IS_ERR(inode)) {
 			sbi->s_vat_inode = inode;
 			break;
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 742557be9936..1cc3c993ebd0 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -138,7 +138,18 @@ extern int udf_write_fi(struct inode *inode, struct fileIdentDesc *,
 /* file.c */
 extern long udf_ioctl(struct file *, unsigned int, unsigned long);
 /* inode.c */
-extern struct inode *udf_iget(struct super_block *, struct kernel_lb_addr *);
+extern struct inode *__udf_iget(struct super_block *, struct kernel_lb_addr *,
+				bool hidden_inode);
+static inline struct inode *udf_iget_special(struct super_block *sb,
+					     struct kernel_lb_addr *ino)
+{
+	return __udf_iget(sb, ino, true);
+}
+static inline struct inode *udf_iget(struct super_block *sb,
+				     struct kernel_lb_addr *ino)
+{
+	return __udf_iget(sb, ino, false);
+}
 extern int udf_expand_file_adinicb(struct inode *);
 extern struct buffer_head *udf_expand_dir_adinicb(struct inode *, int *, int *);
 extern struct buffer_head *udf_bread(struct inode *, int, int, int *);
diff --git a/fs/udf/udftime.c b/fs/udf/udftime.c
index 1f11483eba6a..77c331f1a770 100644
--- a/fs/udf/udftime.c
+++ b/fs/udf/udftime.c
@@ -81,8 +81,6 @@ static time_t year_seconds[MAX_YEAR_SECONDS] = {
 /*2038*/ SPY(68, 17, 0)
 };
 
-extern struct timezone sys_tz;
-
 #define SECS_PER_HOUR	(60 * 60)
 #define SECS_PER_DAY	(SECS_PER_HOUR * 24)
 
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index 7bc20809c99e..2c1036080d52 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -784,7 +784,6 @@ static u64 ufs_bitmap_search(struct super_block *sb,
 		0x0, 0x2, 0x6, 0xe, 0x1e, 0x3e, 0x7e, 0xfe, 0x1fe
 	};
 	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
-	struct ufs_cylinder_group *ucg;
 	unsigned start, length, loc;
 	unsigned pos, want, blockmap, mask, end;
 	u64 result;
@@ -792,8 +791,6 @@ static u64 ufs_bitmap_search(struct super_block *sb,
 	UFSD("ENTER, cg %u, goal %llu, count %u\n", ucpi->c_cgx,
 	     (unsigned long long)goal, count);
 
-	ucg = ubh_get_ucg(UCPI_UBH(ucpi));
-
 	if (goal)
 		start = ufs_dtogd(uspi, goal) >> 3;
 	else
diff --git a/fs/xattr.c b/fs/xattr.c
index c69e6d43a0d2..64e83efb742d 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -364,13 +364,12 @@ out:
 	return error;
 }
 
-SYSCALL_DEFINE5(setxattr, const char __user *, pathname,
-		const char __user *, name, const void __user *, value,
-		size_t, size, int, flags)
+static int path_setxattr(const char __user *pathname,
+			 const char __user *name, const void __user *value,
+			 size_t size, int flags, unsigned int lookup_flags)
 {
 	struct path path;
 	int error;
-	unsigned int lookup_flags = LOOKUP_FOLLOW;
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
@@ -388,28 +387,18 @@ retry:
 	return error;
 }
 
+SYSCALL_DEFINE5(setxattr, const char __user *, pathname,
+		const char __user *, name, const void __user *, value,
+		size_t, size, int, flags)
+{
+	return path_setxattr(pathname, name, value, size, flags, LOOKUP_FOLLOW);
+}
+
 SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
 		const char __user *, name, const void __user *, value,
 		size_t, size, int, flags)
 {
-	struct path path;
-	int error;
-	unsigned int lookup_flags = 0;
-retry:
-	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
-	if (error)
-		return error;
-	error = mnt_want_write(path.mnt);
-	if (!error) {
-		error = setxattr(path.dentry, name, value, size, flags);
-		mnt_drop_write(path.mnt);
-	}
-	path_put(&path);
-	if (retry_estale(error, lookup_flags)) {
-		lookup_flags |= LOOKUP_REVAL;
-		goto retry;
-	}
-	return error;
+	return path_setxattr(pathname, name, value, size, flags, 0);
 }
 
 SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
@@ -481,12 +470,12 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 	return error;
 }
 
-SYSCALL_DEFINE4(getxattr, const char __user *, pathname,
-		const char __user *, name, void __user *, value, size_t, size)
+static ssize_t path_getxattr(const char __user *pathname,
+			     const char __user *name, void __user *value,
+			     size_t size, unsigned int lookup_flags)
 {
 	struct path path;
 	ssize_t error;
-	unsigned int lookup_flags = LOOKUP_FOLLOW;
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
@@ -500,23 +489,16 @@ retry:
 	return error;
 }
 
+SYSCALL_DEFINE4(getxattr, const char __user *, pathname,
+		const char __user *, name, void __user *, value, size_t, size)
+{
+	return path_getxattr(pathname, name, value, size, LOOKUP_FOLLOW);
+}
+
 SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname,
 		const char __user *, name, void __user *, value, size_t, size)
 {
-	struct path path;
-	ssize_t error;
-	unsigned int lookup_flags = 0;
-retry:
-	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
-	if (error)
-		return error;
-	error = getxattr(path.dentry, name, value, size);
-	path_put(&path);
-	if (retry_estale(error, lookup_flags)) {
-		lookup_flags |= LOOKUP_REVAL;
-		goto retry;
-	}
-	return error;
+	return path_getxattr(pathname, name, value, size, 0);
 }
 
 SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name,
@@ -571,12 +553,11 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 	return error;
 }
 
-SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list,
-		size_t, size)
+static ssize_t path_listxattr(const char __user *pathname, char __user *list,
+			      size_t size, unsigned int lookup_flags)
 {
 	struct path path;
 	ssize_t error;
-	unsigned int lookup_flags = LOOKUP_FOLLOW;
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
@@ -590,23 +571,16 @@ retry:
 	return error;
 }
 
+SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list,
+		size_t, size)
+{
+	return path_listxattr(pathname, list, size, LOOKUP_FOLLOW);
+}
+
 SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list,
 		size_t, size)
 {
-	struct path path;
-	ssize_t error;
-	unsigned int lookup_flags = 0;
-retry:
-	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
-	if (error)
-		return error;
-	error = listxattr(path.dentry, list, size);
-	path_put(&path);
-	if (retry_estale(error, lookup_flags)) {
-		lookup_flags |= LOOKUP_REVAL;
-		goto retry;
-	}
-	return error;
+	return path_listxattr(pathname, list, size, 0);
 }
 
 SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
@@ -640,12 +614,11 @@ removexattr(struct dentry *d, const char __user *name)
 	return vfs_removexattr(d, kname);
 }
 
-SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
-		const char __user *, name)
+static int path_removexattr(const char __user *pathname,
+			    const char __user *name, unsigned int lookup_flags)
 {
 	struct path path;
 	int error;
-	unsigned int lookup_flags = LOOKUP_FOLLOW;
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
@@ -663,27 +636,16 @@ retry:
 	return error;
 }
 
+SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
+		const char __user *, name)
+{
+	return path_removexattr(pathname, name, LOOKUP_FOLLOW);
+}
+
 SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
 		const char __user *, name)
 {
-	struct path path;
-	int error;
-	unsigned int lookup_flags = 0;
-retry:
-	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
-	if (error)
-		return error;
-	error = mnt_want_write(path.mnt);
-	if (!error) {
-		error = removexattr(path.dentry, name);
-		mnt_drop_write(path.mnt);
-	}
-	path_put(&path);
-	if (retry_estale(error, lookup_flags)) {
-		lookup_flags |= LOOKUP_REVAL;
-		goto retry;
-	}
-	return error;
+	return path_removexattr(pathname, name, 0);
 }
 
 SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 844e288b9576..53e95b2a1369 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -21,7 +21,6 @@
 #include <linux/swap.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
-#include "time.h"
 #include "kmem.h"
 #include "xfs_message.h"
 
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 4bffffe038a1..eff34218f405 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2209,6 +2209,10 @@ xfs_agf_verify(
 	      be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp)))
 		return false;
 
+	if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > XFS_BTREE_MAXLEVELS ||
+	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) > XFS_BTREE_MAXLEVELS)
+		return false;
+
 	/*
 	 * during growfs operations, the perag is not fully initialised,
 	 * so we can't use it for any useful checking. growfs ensures we can't
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 86df952d3e24..79c981984dca 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5404,22 +5404,223 @@ error0:
 }
 
 /*
+ * Determine whether an extent shift can be accomplished by a merge with the
+ * extent that precedes the target hole of the shift.
+ */
+STATIC bool
+xfs_bmse_can_merge(
+	struct xfs_bmbt_irec	*left,	/* preceding extent */
+	struct xfs_bmbt_irec	*got,	/* current extent to shift */
+	xfs_fileoff_t		shift)	/* shift fsb */
+{
+	xfs_fileoff_t		startoff;
+
+	startoff = got->br_startoff - shift;
+
+	/*
+	 * The extent, once shifted, must be adjacent in-file and on-disk with
+	 * the preceding extent.
+	 */
+	if ((left->br_startoff + left->br_blockcount != startoff) ||
+	    (left->br_startblock + left->br_blockcount != got->br_startblock) ||
+	    (left->br_state != got->br_state) ||
+	    (left->br_blockcount + got->br_blockcount > MAXEXTLEN))
+		return false;
+
+	return true;
+}
+
+/*
+ * A bmap extent shift adjusts the file offset of an extent to fill a preceding
+ * hole in the file. If an extent shift would result in the extent being fully
+ * adjacent to the extent that currently precedes the hole, we can merge with
+ * the preceding extent rather than do the shift.
+ *
+ * This function assumes the caller has verified a shift-by-merge is possible
+ * with the provided extents via xfs_bmse_can_merge().
+ */
+STATIC int
+xfs_bmse_merge(
+	struct xfs_inode		*ip,
+	int				whichfork,
+	xfs_fileoff_t			shift,		/* shift fsb */
+	int				current_ext,	/* idx of gotp */
+	struct xfs_bmbt_rec_host	*gotp,		/* extent to shift */
+	struct xfs_bmbt_rec_host	*leftp,		/* preceding extent */
+	struct xfs_btree_cur		*cur,
+	int				*logflags)	/* output */
+{
+	struct xfs_ifork		*ifp;
+	struct xfs_bmbt_irec		got;
+	struct xfs_bmbt_irec		left;
+	xfs_filblks_t			blockcount;
+	int				error, i;
+
+	ifp = XFS_IFORK_PTR(ip, whichfork);
+	xfs_bmbt_get_all(gotp, &got);
+	xfs_bmbt_get_all(leftp, &left);
+	blockcount = left.br_blockcount + got.br_blockcount;
+
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT(xfs_bmse_can_merge(&left, &got, shift));
+
+	/*
+	 * Merge the in-core extents. Note that the host record pointers and
+	 * current_ext index are invalid once the extent has been removed via
+	 * xfs_iext_remove().
+	 */
+	xfs_bmbt_set_blockcount(leftp, blockcount);
+	xfs_iext_remove(ip, current_ext, 1, 0);
+
+	/*
+	 * Update the on-disk extent count, the btree if necessary and log the
+	 * inode.
+	 */
+	XFS_IFORK_NEXT_SET(ip, whichfork,
+			   XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
+	*logflags |= XFS_ILOG_CORE;
+	if (!cur) {
+		*logflags |= XFS_ILOG_DEXT;
+		return 0;
+	}
+
+	/* lookup and remove the extent to merge */
+	error = xfs_bmbt_lookup_eq(cur, got.br_startoff, got.br_startblock,
+				   got.br_blockcount, &i);
+	if (error)
+		goto out_error;
+	XFS_WANT_CORRUPTED_GOTO(i == 1, out_error);
+
+	error = xfs_btree_delete(cur, &i);
+	if (error)
+		goto out_error;
+	XFS_WANT_CORRUPTED_GOTO(i == 1, out_error);
+
+	/* lookup and update size of the previous extent */
+	error = xfs_bmbt_lookup_eq(cur, left.br_startoff, left.br_startblock,
+				   left.br_blockcount, &i);
+	if (error)
+		goto out_error;
+	XFS_WANT_CORRUPTED_GOTO(i == 1, out_error);
+
+	left.br_blockcount = blockcount;
+
+	error = xfs_bmbt_update(cur, left.br_startoff, left.br_startblock,
+				left.br_blockcount, left.br_state);
+	if (error)
+		goto out_error;
+
+	return 0;
+
+out_error:
+	return error;
+}
+
+/*
+ * Shift a single extent.
+ */
+STATIC int
+xfs_bmse_shift_one(
+	struct xfs_inode		*ip,
+	int				whichfork,
+	xfs_fileoff_t			offset_shift_fsb,
+	int				*current_ext,
+	struct xfs_bmbt_rec_host	*gotp,
+	struct xfs_btree_cur		*cur,
+	int				*logflags)
+{
+	struct xfs_ifork		*ifp;
+	xfs_fileoff_t			startoff;
+	struct xfs_bmbt_rec_host	*leftp;
+	struct xfs_bmbt_irec		got;
+	struct xfs_bmbt_irec		left;
+	int				error;
+	int				i;
+
+	ifp = XFS_IFORK_PTR(ip, whichfork);
+
+	xfs_bmbt_get_all(gotp, &got);
+	startoff = got.br_startoff - offset_shift_fsb;
+
+	/* delalloc extents should be prevented by caller */
+	XFS_WANT_CORRUPTED_GOTO(!isnullstartblock(got.br_startblock),
+				out_error);
+
+	/*
+	 * If this is the first extent in the file, make sure there's enough
+	 * room at the start of the file and jump right to the shift as there's
+	 * no left extent to merge.
+	 */
+	if (*current_ext == 0) {
+		if (got.br_startoff < offset_shift_fsb)
+			return -EINVAL;
+		goto shift_extent;
+	}
+
+	/* grab the left extent and check for a large enough hole */
+	leftp = xfs_iext_get_ext(ifp, *current_ext - 1);
+	xfs_bmbt_get_all(leftp, &left);
+
+	if (startoff < left.br_startoff + left.br_blockcount)
+		return -EINVAL;
+
+	/* check whether to merge the extent or shift it down */
+	if (!xfs_bmse_can_merge(&left, &got, offset_shift_fsb))
+		goto shift_extent;
+
+	return xfs_bmse_merge(ip, whichfork, offset_shift_fsb, *current_ext,
+			      gotp, leftp, cur, logflags);
+
+shift_extent:
+	/*
+	 * Increment the extent index for the next iteration, update the start
+	 * offset of the in-core extent and update the btree if applicable.
+	 */
+	(*current_ext)++;
+	xfs_bmbt_set_startoff(gotp, startoff);
+	*logflags |= XFS_ILOG_CORE;
+	if (!cur) {
+		*logflags |= XFS_ILOG_DEXT;
+		return 0;
+	}
+
+	error = xfs_bmbt_lookup_eq(cur, got.br_startoff, got.br_startblock,
+				   got.br_blockcount, &i);
+	if (error)
+		return error;
+	XFS_WANT_CORRUPTED_GOTO(i == 1, out_error);
+
+	got.br_startoff = startoff;
+	error = xfs_bmbt_update(cur, got.br_startoff, got.br_startblock,
+				got.br_blockcount, got.br_state);
+	if (error)
+		return error;
+
+	return 0;
+
+out_error:
+	return error;
+}
+
+/*
  * Shift extent records to the left to cover a hole.
  *
- * The maximum number of extents to be shifted in a single operation
- * is @num_exts, and @current_ext keeps track of the current extent
- * index we have shifted. @offset_shift_fsb is the length by which each
- * extent is shifted. If there is no hole to shift the extents
- * into, this will be considered invalid operation and we abort immediately.
+ * The maximum number of extents to be shifted in a single operation is
+ * @num_exts. @start_fsb specifies the file offset to start the shift and the
+ * file offset where we've left off is returned in @next_fsb. @offset_shift_fsb
+ * is the length by which each extent is shifted. If there is no hole to shift
+ * the extents into, this will be considered invalid operation and we abort
+ * immediately.
  */
 int
 xfs_bmap_shift_extents(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
-	int			*done,
 	xfs_fileoff_t		start_fsb,
 	xfs_fileoff_t		offset_shift_fsb,
-	xfs_extnum_t		*current_ext,
+	int			*done,
+	xfs_fileoff_t		*next_fsb,
 	xfs_fsblock_t		*firstblock,
 	struct xfs_bmap_free	*flist,
 	int			num_exts)
@@ -5427,16 +5628,13 @@ xfs_bmap_shift_extents(
 	struct xfs_btree_cur		*cur = NULL;
 	struct xfs_bmbt_rec_host	*gotp;
 	struct xfs_bmbt_irec            got;
-	struct xfs_bmbt_irec		left;
 	struct xfs_mount		*mp = ip->i_mount;
 	struct xfs_ifork		*ifp;
 	xfs_extnum_t			nexts = 0;
-	xfs_fileoff_t			startoff;
+	xfs_extnum_t			current_ext;
 	int				error = 0;
-	int				i;
 	int				whichfork = XFS_DATA_FORK;
 	int				logflags = 0;
-	xfs_filblks_t			blockcount = 0;
 	int				total_extents;
 
 	if (unlikely(XFS_TEST_ERROR(
@@ -5451,7 +5649,8 @@ xfs_bmap_shift_extents(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	ASSERT(current_ext != NULL);
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
@@ -5461,23 +5660,6 @@ xfs_bmap_shift_extents(
 			return error;
 	}
 
-	/*
-	 * If *current_ext is 0, we would need to lookup the extent
-	 * from where we would start shifting and store it in gotp.
-	 */
-	if (!*current_ext) {
-		gotp = xfs_iext_bno_to_ext(ifp, start_fsb, current_ext);
-		/*
-		 * gotp can be null in 2 cases: 1) if there are no extents
-		 * or 2) start_fsb lies in a hole beyond which there are
-		 * no extents. Either way, we are done.
-		 */
-		if (!gotp) {
-			*done = 1;
-			return 0;
-		}
-	}
-
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstblock;
@@ -5486,112 +5668,46 @@ xfs_bmap_shift_extents(
 	}
 
 	/*
+	 * Look up the extent index for the fsb where we start shifting. We can
+	 * henceforth iterate with current_ext as extent list changes are locked
+	 * out via ilock.
+	 *
+	 * gotp can be null in 2 cases: 1) if there are no extents or 2)
+	 * start_fsb lies in a hole beyond which there are no extents. Either
+	 * way, we are done.
+	 */
+	gotp = xfs_iext_bno_to_ext(ifp, start_fsb, &current_ext);
+	if (!gotp) {
+		*done = 1;
+		goto del_cursor;
+	}
+
+	/*
 	 * There may be delalloc extents in the data fork before the range we
-	 * are collapsing out, so we cannot
-	 * use the count of real extents here. Instead we have to calculate it
-	 * from the incore fork.
+	 * are collapsing out, so we cannot use the count of real extents here.
+	 * Instead we have to calculate it from the incore fork.
 	 */
 	total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
-	while (nexts++ < num_exts && *current_ext < total_extents) {
-
-		gotp = xfs_iext_get_ext(ifp, *current_ext);
-		xfs_bmbt_get_all(gotp, &got);
-		startoff = got.br_startoff - offset_shift_fsb;
-
-		/*
-		 * Before shifting extent into hole, make sure that the hole
-		 * is large enough to accomodate the shift.
-		 */
-		if (*current_ext) {
-			xfs_bmbt_get_all(xfs_iext_get_ext(ifp,
-						*current_ext - 1), &left);
-
-			if (startoff < left.br_startoff + left.br_blockcount)
-				error = -EINVAL;
-		} else if (offset_shift_fsb > got.br_startoff) {
-			/*
-			 * When first extent is shifted, offset_shift_fsb
-			 * should be less than the stating offset of
-			 * the first extent.
-			 */
-			error = -EINVAL;
-		}
-
+	while (nexts++ < num_exts && current_ext < total_extents) {
+		error = xfs_bmse_shift_one(ip, whichfork, offset_shift_fsb,
+					&current_ext, gotp, cur, &logflags);
 		if (error)
 			goto del_cursor;
 
-		if (cur) {
-			error = xfs_bmbt_lookup_eq(cur, got.br_startoff,
-						   got.br_startblock,
-						   got.br_blockcount,
-						   &i);
-			if (error)
-				goto del_cursor;
-			XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor);
-		}
-
-		/* Check if we can merge 2 adjacent extents */
-		if (*current_ext &&
-		    left.br_startoff + left.br_blockcount == startoff &&
-		    left.br_startblock + left.br_blockcount ==
-				got.br_startblock &&
-		    left.br_state == got.br_state &&
-		    left.br_blockcount + got.br_blockcount <= MAXEXTLEN) {
-			blockcount = left.br_blockcount +
-				got.br_blockcount;
-			xfs_iext_remove(ip, *current_ext, 1, 0);
-			logflags |= XFS_ILOG_CORE;
-			if (cur) {
-				error = xfs_btree_delete(cur, &i);
-				if (error)
-					goto del_cursor;
-				XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor);
-			} else {
-				logflags |= XFS_ILOG_DEXT;
-			}
-			XFS_IFORK_NEXT_SET(ip, whichfork,
-				XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
-			gotp = xfs_iext_get_ext(ifp, --*current_ext);
-			xfs_bmbt_get_all(gotp, &got);
-
-			/* Make cursor point to the extent we will update */
-			if (cur) {
-				error = xfs_bmbt_lookup_eq(cur, got.br_startoff,
-							   got.br_startblock,
-							   got.br_blockcount,
-							   &i);
-				if (error)
-					goto del_cursor;
-				XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor);
-			}
-
-			xfs_bmbt_set_blockcount(gotp, blockcount);
-			got.br_blockcount = blockcount;
-		} else {
-			/* We have to update the startoff */
-			xfs_bmbt_set_startoff(gotp, startoff);
-			got.br_startoff = startoff;
-		}
-
-		logflags |= XFS_ILOG_CORE;
-		if (cur) {
-			error = xfs_bmbt_update(cur, got.br_startoff,
-						got.br_startblock,
-						got.br_blockcount,
-						got.br_state);
-			if (error)
-				goto del_cursor;
-		} else {
-			logflags |= XFS_ILOG_DEXT;
-		}
-
-		(*current_ext)++;
+		/* update total extent count and grab the next record */
 		total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
+		if (current_ext >= total_extents)
+			break;
+		gotp = xfs_iext_get_ext(ifp, current_ext);
 	}
 
 	/* Check if we are done */
-	if (*current_ext == total_extents)
+	if (current_ext == total_extents) {
 		*done = 1;
+	} else if (next_fsb) {
+		xfs_bmbt_get_all(gotp, &got);
+		*next_fsb = got.br_startoff;
+	}
 
 del_cursor:
 	if (cur)
@@ -5600,5 +5716,6 @@ del_cursor:
 
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
+
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index b879ca56a64c..44db6db86402 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -178,9 +178,8 @@ int	xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
 		xfs_extnum_t num);
 uint	xfs_default_attroffset(struct xfs_inode *ip);
 int	xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip,
-		int *done, xfs_fileoff_t start_fsb,
-		xfs_fileoff_t offset_shift_fsb, xfs_extnum_t *current_ext,
-		xfs_fsblock_t *firstblock, struct xfs_bmap_free	*flist,
-		int num_exts);
+		xfs_fileoff_t start_fsb, xfs_fileoff_t offset_shift_fsb,
+		int *done, xfs_fileoff_t *next_fsb, xfs_fsblock_t *firstblock,
+		struct xfs_bmap_free *flist, int num_exts);
 
 #endif	/* __XFS_BMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 2c42ae28d027..fd827530afec 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2563,7 +2563,8 @@ xfs_da_get_buf(
 				    mapp, nmap, 0);
 	error = bp ? bp->b_error : -EIO;
 	if (error) {
-		xfs_trans_brelse(trans, bp);
+		if (bp)
+			xfs_trans_brelse(trans, bp);
 		goto out_free;
 	}
 
diff --git a/fs/xfs/libxfs/xfs_da_format.c b/fs/xfs/libxfs/xfs_da_format.c
index c9aee52a37e2..7e42fdfd2f1d 100644
--- a/fs/xfs/libxfs/xfs_da_format.c
+++ b/fs/xfs/libxfs/xfs_da_format.c
@@ -270,7 +270,6 @@ xfs_dir3_data_get_ftype(
 {
 	__uint8_t	ftype = dep->name[dep->namelen];
 
-	ASSERT(ftype < XFS_DIR3_FT_MAX);
 	if (ftype >= XFS_DIR3_FT_MAX)
 		return XFS_DIR3_FT_UNKNOWN;
 	return ftype;
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 6cef22152fd6..7075aaf131f4 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -237,7 +237,8 @@ xfs_dir_init(
 }
 
 /*
-  Enter a name in a directory.
+ * Enter a name in a directory, or check for available space.
+ * If inum is 0, only the available space test is performed.
  */
 int
 xfs_dir_createname(
@@ -254,10 +255,12 @@ xfs_dir_createname(
 	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(dp->i_d.di_mode));
-	rval = xfs_dir_ino_validate(tp->t_mountp, inum);
-	if (rval)
-		return rval;
-	XFS_STATS_INC(xs_dir_create);
+	if (inum) {
+		rval = xfs_dir_ino_validate(tp->t_mountp, inum);
+		if (rval)
+			return rval;
+		XFS_STATS_INC(xs_dir_create);
+	}
 
 	args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
 	if (!args)
@@ -276,6 +279,8 @@ xfs_dir_createname(
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
 	args->op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
+	if (!inum)
+		args->op_flags |= XFS_DA_OP_JUSTCHECK;
 
 	if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
 		rval = xfs_dir2_sf_addname(args);
@@ -535,62 +540,14 @@ out_free:
 
 /*
  * See if this entry can be added to the directory without allocating space.
- * First checks that the caller couldn't reserve enough space (resblks = 0).
  */
 int
 xfs_dir_canenter(
 	xfs_trans_t	*tp,
 	xfs_inode_t	*dp,
-	struct xfs_name	*name,		/* name of entry to add */
-	uint		resblks)
+	struct xfs_name	*name)		/* name of entry to add */
 {
-	struct xfs_da_args *args;
-	int		rval;
-	int		v;		/* type-checking value */
-
-	if (resblks)
-		return 0;
-
-	ASSERT(S_ISDIR(dp->i_d.di_mode));
-
-	args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
-	if (!args)
-		return -ENOMEM;
-
-	args->geo = dp->i_mount->m_dir_geo;
-	args->name = name->name;
-	args->namelen = name->len;
-	args->filetype = name->type;
-	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
-	args->dp = dp;
-	args->whichfork = XFS_DATA_FORK;
-	args->trans = tp;
-	args->op_flags = XFS_DA_OP_JUSTCHECK | XFS_DA_OP_ADDNAME |
-							XFS_DA_OP_OKNOENT;
-
-	if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
-		rval = xfs_dir2_sf_addname(args);
-		goto out_free;
-	}
-
-	rval = xfs_dir2_isblock(args, &v);
-	if (rval)
-		goto out_free;
-	if (v) {
-		rval = xfs_dir2_block_addname(args);
-		goto out_free;
-	}
-
-	rval = xfs_dir2_isleaf(args, &v);
-	if (rval)
-		goto out_free;
-	if (v)
-		rval = xfs_dir2_leaf_addname(args);
-	else
-		rval = xfs_dir2_node_addname(args);
-out_free:
-	kmem_free(args);
-	return rval;
+	return xfs_dir_createname(tp, dp, name, 0, NULL, NULL, 0);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index c8e86b0b5e99..4dff261e6ed5 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -136,7 +136,7 @@ extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp,
 				xfs_fsblock_t *first,
 				struct xfs_bmap_free *flist, xfs_extlen_t tot);
 extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
-				struct xfs_name *name, uint resblks);
+				struct xfs_name *name);
 
 /*
  * Direct call from the bmap code, bypassing the generic directory layer.
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index b62771f1f4b5..23dcb72fc5e6 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1076,8 +1076,8 @@ xfs_dialloc_ag_finobt_newino(
 	int i;
 
 	if (agi->agi_newino != cpu_to_be32(NULLAGINO)) {
-		error = xfs_inobt_lookup(cur, agi->agi_newino, XFS_LOOKUP_EQ,
-					 &i);
+		error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino),
+					 XFS_LOOKUP_EQ, &i);
 		if (error)
 			return error;
 		if (i == 1) {
@@ -1085,7 +1085,6 @@ xfs_dialloc_ag_finobt_newino(
 			if (error)
 				return error;
 			XFS_WANT_CORRUPTED_RETURN(i == 1);
-
 			return 0;
 		}
 	}
@@ -2051,6 +2050,8 @@ xfs_agi_verify(
 	if (!XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum)))
 		return false;
 
+	if (be32_to_cpu(agi->agi_level) > XFS_BTREE_MAXLEVELS)
+		return false;
 	/*
 	 * during growfs operations, the perag is not fully initialised,
 	 * so we can't use it for any useful checking. growfs ensures we can't
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index f4dd697cac08..7c818f1e4484 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -424,20 +424,24 @@ xfs_rtfind_forw(
 }
 
 /*
- * Read and modify the summary information for a given extent size,
+ * Read and/or modify the summary information for a given extent size,
  * bitmap block combination.
  * Keeps track of a current summary block, so we don't keep reading
  * it from the buffer cache.
+ *
+ * Summary information is returned in *sum if specified.
+ * If no delta is specified, returns summary only.
  */
 int
-xfs_rtmodify_summary(
-	xfs_mount_t	*mp,		/* file system mount point */
+xfs_rtmodify_summary_int(
+	xfs_mount_t	*mp,		/* file system mount structure */
 	xfs_trans_t	*tp,		/* transaction pointer */
 	int		log,		/* log2 of extent size */
 	xfs_rtblock_t	bbno,		/* bitmap block number */
 	int		delta,		/* change to make to summary info */
 	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
-	xfs_fsblock_t	*rsb)		/* in/out: summary block number */
+	xfs_fsblock_t	*rsb,		/* in/out: summary block number */
+	xfs_suminfo_t	*sum)		/* out: summary info for this block */
 {
 	xfs_buf_t	*bp;		/* buffer for the summary block */
 	int		error;		/* error value */
@@ -456,7 +460,7 @@ xfs_rtmodify_summary(
 	/*
 	 * If we have an old buffer, and the block number matches, use that.
 	 */
-	if (rbpp && *rbpp && *rsb == sb)
+	if (*rbpp && *rsb == sb)
 		bp = *rbpp;
 	/*
 	 * Otherwise we have to get the buffer.
@@ -465,7 +469,7 @@ xfs_rtmodify_summary(
 		/*
 		 * If there was an old one, get rid of it first.
 		 */
-		if (rbpp && *rbpp)
+		if (*rbpp)
 			xfs_trans_brelse(tp, *rbpp);
 		error = xfs_rtbuf_get(mp, tp, sb, 1, &bp);
 		if (error) {
@@ -474,21 +478,38 @@ xfs_rtmodify_summary(
 		/*
 		 * Remember this buffer and block for the next call.
 		 */
-		if (rbpp) {
-			*rbpp = bp;
-			*rsb = sb;
-		}
+		*rbpp = bp;
+		*rsb = sb;
 	}
 	/*
-	 * Point to the summary information, modify and log it.
+	 * Point to the summary information, modify/log it, and/or copy it out.
 	 */
 	sp = XFS_SUMPTR(mp, bp, so);
-	*sp += delta;
-	xfs_trans_log_buf(tp, bp, (uint)((char *)sp - (char *)bp->b_addr),
-		(uint)((char *)sp - (char *)bp->b_addr + sizeof(*sp) - 1));
+	if (delta) {
+		uint first = (uint)((char *)sp - (char *)bp->b_addr);
+
+		*sp += delta;
+		xfs_trans_log_buf(tp, bp, first, first + sizeof(*sp) - 1);
+	}
+	if (sum)
+		*sum = *sp;
 	return 0;
 }
 
+int
+xfs_rtmodify_summary(
+	xfs_mount_t	*mp,		/* file system mount structure */
+	xfs_trans_t	*tp,		/* transaction pointer */
+	int		log,		/* log2 of extent size */
+	xfs_rtblock_t	bbno,		/* bitmap block number */
+	int		delta,		/* change to make to summary info */
+	xfs_buf_t	**rbpp,		/* in/out: summary block buffer */
+	xfs_fsblock_t	*rsb)		/* in/out: summary block number */
+{
+	return xfs_rtmodify_summary_int(mp, tp, log, bbno,
+					delta, rbpp, rsb, NULL);
+}
+
 /*
  * Set the given range of bitmap bits to the given value.
  * Do whatever I/O and logging is required.
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index ad525a5623a4..5f902fa7913f 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -279,11 +279,13 @@ xfs_mount_validate_sb(
 	    sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG			||
 	    sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG			||
 	    sbp->sb_blocksize != (1 << sbp->sb_blocklog)		||
+	    sbp->sb_dirblklog > XFS_MAX_BLOCKSIZE_LOG			||
 	    sbp->sb_inodesize < XFS_DINODE_MIN_SIZE			||
 	    sbp->sb_inodesize > XFS_DINODE_MAX_SIZE			||
 	    sbp->sb_inodelog < XFS_DINODE_MIN_LOG			||
 	    sbp->sb_inodelog > XFS_DINODE_MAX_LOG			||
 	    sbp->sb_inodesize != (1 << sbp->sb_inodelog)		||
+	    sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE			||
 	    sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) ||
 	    (sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog)	||
 	    (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE)	||
@@ -443,6 +445,8 @@ __xfs_sb_from_disk(
 	to->sb_features_incompat = be32_to_cpu(from->sb_features_incompat);
 	to->sb_features_log_incompat =
 				be32_to_cpu(from->sb_features_log_incompat);
+	/* crc is only used on disk, not in memory; just init to 0 here. */
+	to->sb_crc = 0;
 	to->sb_pad = 0;
 	to->sb_pquotino = be64_to_cpu(from->sb_pquotino);
 	to->sb_lsn = be64_to_cpu(from->sb_lsn);
@@ -548,6 +552,9 @@ xfs_sb_to_disk(
 	if (!fields)
 		return;
 
+	/* We should never write the crc here, it's updated in the IO path */
+	fields &= ~XFS_SB_CRC;
+
 	xfs_sb_quota_to_disk(to, from, &fields);
 	while (fields) {
 		f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields);
diff --git a/fs/xfs/time.h b/fs/xfs/time.h
deleted file mode 100644
index 387e695a184c..000000000000
--- a/fs/xfs/time.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_SUPPORT_TIME_H__
-#define __XFS_SUPPORT_TIME_H__
-
-#include <linux/sched.h>
-#include <linux/time.h>
-
-typedef struct timespec timespec_t;
-
-static inline void delay(long ticks)
-{
-	schedule_timeout_uninterruptible(ticks);
-}
-
-static inline void nanotime(struct timespec *tvp)
-{
-	*tvp = CURRENT_TIME;
-}
-
-#endif /* __XFS_SUPPORT_TIME_H__ */
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index b984647c24db..f5b2453a43b2 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -434,10 +434,22 @@ xfs_start_page_writeback(
 {
 	ASSERT(PageLocked(page));
 	ASSERT(!PageWriteback(page));
-	if (clear_dirty)
+
+	/*
+	 * if the page was not fully cleaned, we need to ensure that the higher
+	 * layers come back to it correctly. That means we need to keep the page
+	 * dirty, and for WB_SYNC_ALL writeback we need to ensure the
+	 * PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to
+	 * write this page in this writeback sweep will be made.
+	 */
+	if (clear_dirty) {
 		clear_page_dirty_for_io(page);
-	set_page_writeback(page);
+		set_page_writeback(page);
+	} else
+		set_page_writeback_keepwrite(page);
+
 	unlock_page(page);
+
 	/* If no buffers on the page are to be written, finish it here */
 	if (!buffers)
 		end_page_writeback(page);
@@ -548,6 +560,13 @@ xfs_cancel_ioend(
 		do {
 			next_bh = bh->b_private;
 			clear_buffer_async_write(bh);
+			/*
+			 * The unwritten flag is cleared when added to the
+			 * ioend. We're not submitting for I/O so mark the
+			 * buffer unwritten again for next time around.
+			 */
+			if (ioend->io_type == XFS_IO_UNWRITTEN)
+				set_buffer_unwritten(bh);
 			unlock_buffer(bh);
 		} while ((bh = next_bh) != NULL);
 
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 1707980f9a4b..92e8f99a5857 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1122,14 +1122,6 @@ xfs_zero_remaining_bytes(
 	if (endoff > XFS_ISIZE(ip))
 		endoff = XFS_ISIZE(ip);
 
-	bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
-					mp->m_rtdev_targp : mp->m_ddev_targp,
-				  BTOBB(mp->m_sb.sb_blocksize), 0);
-	if (!bp)
-		return -ENOMEM;
-
-	xfs_buf_unlock(bp);
-
 	for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
 		uint lock_mode;
 
@@ -1152,42 +1144,24 @@ xfs_zero_remaining_bytes(
 		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
 		if (imap.br_state == XFS_EXT_UNWRITTEN)
 			continue;
-		XFS_BUF_UNDONE(bp);
-		XFS_BUF_UNWRITE(bp);
-		XFS_BUF_READ(bp);
-		XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
 
-		if (XFS_FORCED_SHUTDOWN(mp)) {
-			error = -EIO;
-			break;
-		}
-		xfs_buf_iorequest(bp);
-		error = xfs_buf_iowait(bp);
-		if (error) {
-			xfs_buf_ioerror_alert(bp,
-					"xfs_zero_remaining_bytes(read)");
-			break;
-		}
+		error = xfs_buf_read_uncached(XFS_IS_REALTIME_INODE(ip) ?
+				mp->m_rtdev_targp : mp->m_ddev_targp,
+				xfs_fsb_to_db(ip, imap.br_startblock),
+				BTOBB(mp->m_sb.sb_blocksize),
+				0, &bp, NULL);
+		if (error)
+			return error;
+
 		memset(bp->b_addr +
-			(offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
-		      0, lastoffset - offset + 1);
-		XFS_BUF_UNDONE(bp);
-		XFS_BUF_UNREAD(bp);
-		XFS_BUF_WRITE(bp);
-
-		if (XFS_FORCED_SHUTDOWN(mp)) {
-			error = -EIO;
-			break;
-		}
-		xfs_buf_iorequest(bp);
-		error = xfs_buf_iowait(bp);
-		if (error) {
-			xfs_buf_ioerror_alert(bp,
-					"xfs_zero_remaining_bytes(write)");
-			break;
-		}
+				(offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
+		       0, lastoffset - offset + 1);
+
+		error = xfs_bwrite(bp);
+		xfs_buf_relse(bp);
+		if (error)
+			return error;
 	}
-	xfs_buf_free(bp);
 	return error;
 }
 
@@ -1205,6 +1179,7 @@ xfs_free_file_space(
 	xfs_bmap_free_t		free_list;
 	xfs_bmbt_irec_t		imap;
 	xfs_off_t		ioffset;
+	xfs_off_t		iendoffset;
 	xfs_extlen_t		mod=0;
 	xfs_mount_t		*mp;
 	int			nimap;
@@ -1233,12 +1208,13 @@ xfs_free_file_space(
 	inode_dio_wait(VFS_I(ip));
 
 	rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
-	ioffset = offset & ~(rounding - 1);
-	error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
-					      ioffset, -1);
+	ioffset = round_down(offset, rounding);
+	iendoffset = round_up(offset + len, rounding) - 1;
+	error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, ioffset,
+					     iendoffset);
 	if (error)
 		goto out;
-	truncate_pagecache_range(VFS_I(ip), ioffset, -1);
+	truncate_pagecache_range(VFS_I(ip), ioffset, iendoffset);
 
 	/*
 	 * Need to zero the stuff we're not freeing, on disk.
@@ -1392,14 +1368,14 @@ xfs_zero_file_space(
 
 	if (start_boundary < end_boundary - 1) {
 		/*
-		 * punch out delayed allocation blocks and the page cache over
-		 * the conversion range
+		 * Writeback the range to ensure any inode size updates due to
+		 * appending writes make it to disk (otherwise we could just
+		 * punch out the delalloc blocks).
 		 */
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		error = xfs_bmap_punch_delalloc_range(ip,
-				XFS_B_TO_FSBT(mp, start_boundary),
-				XFS_B_TO_FSB(mp, end_boundary - start_boundary));
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+				start_boundary, end_boundary - 1);
+		if (error)
+			goto out;
 		truncate_pagecache_range(VFS_I(ip), start_boundary,
 					 end_boundary - 1);
 
@@ -1456,41 +1432,47 @@ xfs_collapse_file_space(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
-	xfs_extnum_t		current_ext = 0;
 	struct xfs_bmap_free	free_list;
 	xfs_fsblock_t		first_block;
 	int			committed;
 	xfs_fileoff_t		start_fsb;
+	xfs_fileoff_t		next_fsb;
 	xfs_fileoff_t		shift_fsb;
 
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 
 	trace_xfs_collapse_file_space(ip);
 
-	start_fsb = XFS_B_TO_FSB(mp, offset + len);
+	next_fsb = XFS_B_TO_FSB(mp, offset + len);
 	shift_fsb = XFS_B_TO_FSB(mp, len);
 
-	/*
-	 * Writeback the entire file and force remove any post-eof blocks. The
-	 * writeback prevents changes to the extent list via concurrent
-	 * writeback and the eofblocks trim prevents the extent shift algorithm
-	 * from running into a post-eof delalloc extent.
-	 *
-	 * XXX: This is a temporary fix until the extent shift loop below is
-	 * converted to use offsets and lookups within the ILOCK rather than
-	 * carrying around the index into the extent list for the next
-	 * iteration.
-	 */
-	error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
+	error = xfs_free_file_space(ip, offset, len);
 	if (error)
 		return error;
+
+	/*
+	 * Trim eofblocks to avoid shifting uninitialized post-eof preallocation
+	 * into the accessible region of the file.
+	 */
 	if (xfs_can_free_eofblocks(ip, true)) {
 		error = xfs_free_eofblocks(mp, ip, false);
 		if (error)
 			return error;
 	}
 
-	error = xfs_free_file_space(ip, offset, len);
+	/*
+	 * Writeback and invalidate cache for the remainder of the file as we're
+	 * about to shift down every extent from the collapse range to EOF. The
+	 * free of the collapse range above might have already done some of
+	 * this, but we shouldn't rely on it to do anything outside of the range
+	 * that was freed.
+	 */
+	error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+					     offset + len, -1);
+	if (error)
+		return error;
+	error = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
+					(offset + len) >> PAGE_CACHE_SHIFT, -1);
 	if (error)
 		return error;
 
@@ -1525,10 +1507,10 @@ xfs_collapse_file_space(
 		 * We are using the write transaction in which max 2 bmbt
 		 * updates are allowed
 		 */
-		error = xfs_bmap_shift_extents(tp, ip, &done, start_fsb,
-					       shift_fsb, &current_ext,
-					       &first_block, &free_list,
-					       XFS_BMAP_MAX_SHIFT_EXTENTS);
+		start_fsb = next_fsb;
+		error = xfs_bmap_shift_extents(tp, ip, start_fsb, shift_fsb,
+				&done, &next_fsb, &first_block, &free_list,
+				XFS_BMAP_MAX_SHIFT_EXTENTS);
 		if (error)
 			goto out;
 
@@ -1638,7 +1620,7 @@ xfs_swap_extents_check_format(
 	return 0;
 }
 
-int
+static int
 xfs_swap_extent_flush(
 	struct xfs_inode	*ip)
 {
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index cd7b8ca9b064..24b4ebea0d4d 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -623,10 +623,11 @@ _xfs_buf_read(
 	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
 
-	xfs_buf_iorequest(bp);
-	if (flags & XBF_ASYNC)
+	if (flags & XBF_ASYNC) {
+		xfs_buf_submit(bp);
 		return 0;
-	return xfs_buf_iowait(bp);
+	}
+	return xfs_buf_submit_wait(bp);
 }
 
 xfs_buf_t *
@@ -687,34 +688,39 @@ xfs_buf_readahead_map(
  * Read an uncached buffer from disk. Allocates and returns a locked
  * buffer containing the disk contents or nothing.
  */
-struct xfs_buf *
+int
 xfs_buf_read_uncached(
 	struct xfs_buftarg	*target,
 	xfs_daddr_t		daddr,
 	size_t			numblks,
 	int			flags,
+	struct xfs_buf		**bpp,
 	const struct xfs_buf_ops *ops)
 {
 	struct xfs_buf		*bp;
 
+	*bpp = NULL;
+
 	bp = xfs_buf_get_uncached(target, numblks, flags);
 	if (!bp)
-		return NULL;
+		return -ENOMEM;
 
 	/* set up the buffer for a read IO */
 	ASSERT(bp->b_map_count == 1);
-	bp->b_bn = daddr;
+	bp->b_bn = XFS_BUF_DADDR_NULL;  /* always null for uncached buffers */
 	bp->b_maps[0].bm_bn = daddr;
 	bp->b_flags |= XBF_READ;
 	bp->b_ops = ops;
 
-	if (XFS_FORCED_SHUTDOWN(target->bt_mount)) {
+	xfs_buf_submit_wait(bp);
+	if (bp->b_error) {
+		int	error = bp->b_error;
 		xfs_buf_relse(bp);
-		return NULL;
+		return error;
 	}
-	xfs_buf_iorequest(bp);
-	xfs_buf_iowait(bp);
-	return bp;
+
+	*bpp = bp;
+	return 0;
 }
 
 /*
@@ -998,53 +1004,56 @@ xfs_buf_wait_unpin(
  *	Buffer Utility Routines
  */
 
-STATIC void
-xfs_buf_iodone_work(
-	struct work_struct	*work)
+void
+xfs_buf_ioend(
+	struct xfs_buf	*bp)
 {
-	struct xfs_buf		*bp =
-		container_of(work, xfs_buf_t, b_iodone_work);
-	bool			read = !!(bp->b_flags & XBF_READ);
+	bool		read = bp->b_flags & XBF_READ;
+
+	trace_xfs_buf_iodone(bp, _RET_IP_);
 
 	bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
 
-	/* only validate buffers that were read without errors */
-	if (read && bp->b_ops && !bp->b_error && (bp->b_flags & XBF_DONE))
+	/*
+	 * Pull in IO completion errors now. We are guaranteed to be running
+	 * single threaded, so we don't need the lock to read b_io_error.
+	 */
+	if (!bp->b_error && bp->b_io_error)
+		xfs_buf_ioerror(bp, bp->b_io_error);
+
+	/* Only validate buffers that were read without errors */
+	if (read && !bp->b_error && bp->b_ops) {
+		ASSERT(!bp->b_iodone);
 		bp->b_ops->verify_read(bp);
+	}
+
+	if (!bp->b_error)
+		bp->b_flags |= XBF_DONE;
 
 	if (bp->b_iodone)
 		(*(bp->b_iodone))(bp);
 	else if (bp->b_flags & XBF_ASYNC)
 		xfs_buf_relse(bp);
-	else {
-		ASSERT(read && bp->b_ops);
+	else
 		complete(&bp->b_iowait);
-	}
 }
 
-void
-xfs_buf_ioend(
-	struct xfs_buf	*bp,
-	int		schedule)
+static void
+xfs_buf_ioend_work(
+	struct work_struct	*work)
 {
-	bool		read = !!(bp->b_flags & XBF_READ);
-
-	trace_xfs_buf_iodone(bp, _RET_IP_);
+	struct xfs_buf		*bp =
+		container_of(work, xfs_buf_t, b_iodone_work);
 
-	if (bp->b_error == 0)
-		bp->b_flags |= XBF_DONE;
+	xfs_buf_ioend(bp);
+}
 
-	if (bp->b_iodone || (read && bp->b_ops) || (bp->b_flags & XBF_ASYNC)) {
-		if (schedule) {
-			INIT_WORK(&bp->b_iodone_work, xfs_buf_iodone_work);
-			queue_work(xfslogd_workqueue, &bp->b_iodone_work);
-		} else {
-			xfs_buf_iodone_work(&bp->b_iodone_work);
-		}
-	} else {
-		bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
-		complete(&bp->b_iowait);
-	}
+void
+xfs_buf_ioend_async(
+	struct xfs_buf	*bp)
+{
+	INIT_WORK(&bp->b_iodone_work, xfs_buf_ioend_work);
+	queue_work(xfslogd_workqueue, &bp->b_iodone_work);
 }
 
 void
@@ -1067,96 +1076,6 @@ xfs_buf_ioerror_alert(
 		(__uint64_t)XFS_BUF_ADDR(bp), func, -bp->b_error, bp->b_length);
 }
 
-/*
- * Called when we want to stop a buffer from getting written or read.
- * We attach the EIO error, muck with its flags, and call xfs_buf_ioend
- * so that the proper iodone callbacks get called.
- */
-STATIC int
-xfs_bioerror(
-	xfs_buf_t *bp)
-{
-#ifdef XFSERRORDEBUG
-	ASSERT(XFS_BUF_ISREAD(bp) || bp->b_iodone);
-#endif
-
-	/*
-	 * No need to wait until the buffer is unpinned, we aren't flushing it.
-	 */
-	xfs_buf_ioerror(bp, -EIO);
-
-	/*
-	 * We're calling xfs_buf_ioend, so delete XBF_DONE flag.
-	 */
-	XFS_BUF_UNREAD(bp);
-	XFS_BUF_UNDONE(bp);
-	xfs_buf_stale(bp);
-
-	xfs_buf_ioend(bp, 0);
-
-	return -EIO;
-}
-
-/*
- * Same as xfs_bioerror, except that we are releasing the buffer
- * here ourselves, and avoiding the xfs_buf_ioend call.
- * This is meant for userdata errors; metadata bufs come with
- * iodone functions attached, so that we can track down errors.
- */
-int
-xfs_bioerror_relse(
-	struct xfs_buf	*bp)
-{
-	int64_t		fl = bp->b_flags;
-	/*
-	 * No need to wait until the buffer is unpinned.
-	 * We aren't flushing it.
-	 *
-	 * chunkhold expects B_DONE to be set, whether
-	 * we actually finish the I/O or not. We don't want to
-	 * change that interface.
-	 */
-	XFS_BUF_UNREAD(bp);
-	XFS_BUF_DONE(bp);
-	xfs_buf_stale(bp);
-	bp->b_iodone = NULL;
-	if (!(fl & XBF_ASYNC)) {
-		/*
-		 * Mark b_error and B_ERROR _both_.
-		 * Lot's of chunkcache code assumes that.
-		 * There's no reason to mark error for
-		 * ASYNC buffers.
-		 */
-		xfs_buf_ioerror(bp, -EIO);
-		complete(&bp->b_iowait);
-	} else {
-		xfs_buf_relse(bp);
-	}
-
-	return -EIO;
-}
-
-STATIC int
-xfs_bdstrat_cb(
-	struct xfs_buf	*bp)
-{
-	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
-		trace_xfs_bdstrat_shut(bp, _RET_IP_);
-		/*
-		 * Metadata write that didn't get logged but
-		 * written delayed anyway. These aren't associated
-		 * with a transaction, and can be ignored.
-		 */
-		if (!bp->b_iodone && !XFS_BUF_ISREAD(bp))
-			return xfs_bioerror_relse(bp);
-		else
-			return xfs_bioerror(bp);
-	}
-
-	xfs_buf_iorequest(bp);
-	return 0;
-}
-
 int
 xfs_bwrite(
 	struct xfs_buf		*bp)
@@ -1166,11 +1085,10 @@ xfs_bwrite(
 	ASSERT(xfs_buf_islocked(bp));
 
 	bp->b_flags |= XBF_WRITE;
-	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL);
-
-	xfs_bdstrat_cb(bp);
+	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q |
+			 XBF_WRITE_FAIL | XBF_DONE);
 
-	error = xfs_buf_iowait(bp);
+	error = xfs_buf_submit_wait(bp);
 	if (error) {
 		xfs_force_shutdown(bp->b_target->bt_mount,
 				   SHUTDOWN_META_IO_ERROR);
@@ -1179,15 +1097,6 @@ xfs_bwrite(
 }
 
 STATIC void
-_xfs_buf_ioend(
-	xfs_buf_t		*bp,
-	int			schedule)
-{
-	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
-		xfs_buf_ioend(bp, schedule);
-}
-
-STATIC void
 xfs_buf_bio_end_io(
 	struct bio		*bio,
 	int			error)
@@ -1198,13 +1107,18 @@ xfs_buf_bio_end_io(
 	 * don't overwrite existing errors - otherwise we can lose errors on
 	 * buffers that require multiple bios to complete.
 	 */
-	if (!bp->b_error)
-		xfs_buf_ioerror(bp, error);
+	if (error) {
+		spin_lock(&bp->b_lock);
+		if (!bp->b_io_error)
+			bp->b_io_error = error;
+		spin_unlock(&bp->b_lock);
+	}
 
 	if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
 		invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
 
-	_xfs_buf_ioend(bp, 1);
+	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
+		xfs_buf_ioend_async(bp);
 	bio_put(bio);
 }
 
@@ -1283,7 +1197,7 @@ next_chunk:
 	} else {
 		/*
 		 * This is guaranteed not to be the last io reference count
-		 * because the caller (xfs_buf_iorequest) holds a count itself.
+		 * because the caller (xfs_buf_submit) holds a count itself.
 		 */
 		atomic_dec(&bp->b_io_remaining);
 		xfs_buf_ioerror(bp, -EIO);
@@ -1373,53 +1287,131 @@ _xfs_buf_ioapply(
 	blk_finish_plug(&plug);
 }
 
+/*
+ * Asynchronous IO submission path. This transfers the buffer lock ownership and
+ * the current reference to the IO. It is not safe to reference the buffer after
+ * a call to this function unless the caller holds an additional reference
+ * itself.
+ */
 void
-xfs_buf_iorequest(
-	xfs_buf_t		*bp)
+xfs_buf_submit(
+	struct xfs_buf	*bp)
 {
-	trace_xfs_buf_iorequest(bp, _RET_IP_);
+	trace_xfs_buf_submit(bp, _RET_IP_);
 
 	ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
+	ASSERT(bp->b_flags & XBF_ASYNC);
+
+	/* on shutdown we stale and complete the buffer immediately */
+	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
+		xfs_buf_ioerror(bp, -EIO);
+		bp->b_flags &= ~XBF_DONE;
+		xfs_buf_stale(bp);
+		xfs_buf_ioend(bp);
+		return;
+	}
 
 	if (bp->b_flags & XBF_WRITE)
 		xfs_buf_wait_unpin(bp);
+
+	/* clear the internal error state to avoid spurious errors */
+	bp->b_io_error = 0;
+
+	/*
+	 * The caller's reference is released during I/O completion.
+	 * This occurs some time after the last b_io_remaining reference is
+	 * released, so after we drop our Io reference we have to have some
+	 * other reference to ensure the buffer doesn't go away from underneath
+	 * us. Take a direct reference to ensure we have safe access to the
+	 * buffer until we are finished with it.
+	 */
 	xfs_buf_hold(bp);
 
 	/*
-	 * Set the count to 1 initially, this will stop an I/O
-	 * completion callout which happens before we have started
-	 * all the I/O from calling xfs_buf_ioend too early.
+	 * Set the count to 1 initially, this will stop an I/O completion
+	 * callout which happens before we have started all the I/O from calling
+	 * xfs_buf_ioend too early.
 	 */
 	atomic_set(&bp->b_io_remaining, 1);
 	_xfs_buf_ioapply(bp);
+
 	/*
-	 * If _xfs_buf_ioapply failed, we'll get back here with
-	 * only the reference we took above.  _xfs_buf_ioend will
-	 * drop it to zero, so we'd better not queue it for later,
-	 * or we'll free it before it's done.
+	 * If _xfs_buf_ioapply failed, we can get back here with only the IO
+	 * reference we took above. If we drop it to zero, run completion so
+	 * that we don't return to the caller with completion still pending.
 	 */
-	_xfs_buf_ioend(bp, bp->b_error ? 0 : 1);
+	if (atomic_dec_and_test(&bp->b_io_remaining) == 1) {
+		if (bp->b_error)
+			xfs_buf_ioend(bp);
+		else
+			xfs_buf_ioend_async(bp);
+	}
 
 	xfs_buf_rele(bp);
+	/* Note: it is not safe to reference bp now we've dropped our ref */
 }
 
 /*
- * Waits for I/O to complete on the buffer supplied.  It returns immediately if
- * no I/O is pending or there is already a pending error on the buffer, in which
- * case nothing will ever complete.  It returns the I/O error code, if any, or
- * 0 if there was no error.
+ * Synchronous buffer IO submission path, read or write.
  */
 int
-xfs_buf_iowait(
-	xfs_buf_t		*bp)
+xfs_buf_submit_wait(
+	struct xfs_buf	*bp)
 {
-	trace_xfs_buf_iowait(bp, _RET_IP_);
+	int		error;
 
-	if (!bp->b_error)
-		wait_for_completion(&bp->b_iowait);
+	trace_xfs_buf_submit_wait(bp, _RET_IP_);
+
+	ASSERT(!(bp->b_flags & (_XBF_DELWRI_Q | XBF_ASYNC)));
+
+	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
+		xfs_buf_ioerror(bp, -EIO);
+		xfs_buf_stale(bp);
+		bp->b_flags &= ~XBF_DONE;
+		return -EIO;
+	}
+
+	if (bp->b_flags & XBF_WRITE)
+		xfs_buf_wait_unpin(bp);
+
+	/* clear the internal error state to avoid spurious errors */
+	bp->b_io_error = 0;
+
+	/*
+	 * For synchronous IO, the IO does not inherit the submitters reference
+	 * count, nor the buffer lock. Hence we cannot release the reference we
+	 * are about to take until we've waited for all IO completion to occur,
+	 * including any xfs_buf_ioend_async() work that may be pending.
+	 */
+	xfs_buf_hold(bp);
+
+	/*
+	 * Set the count to 1 initially, this will stop an I/O completion
+	 * callout which happens before we have started all the I/O from calling
+	 * xfs_buf_ioend too early.
+	 */
+	atomic_set(&bp->b_io_remaining, 1);
+	_xfs_buf_ioapply(bp);
+
+	/*
+	 * make sure we run completion synchronously if it raced with us and is
+	 * already complete.
+	 */
+	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
+		xfs_buf_ioend(bp);
 
+	/* wait for completion before gathering the error from the buffer */
+	trace_xfs_buf_iowait(bp, _RET_IP_);
+	wait_for_completion(&bp->b_iowait);
 	trace_xfs_buf_iowait_done(bp, _RET_IP_);
-	return bp->b_error;
+	error = bp->b_error;
+
+	/*
+	 * all done now, we can release the hold that keeps the buffer
+	 * referenced for the entire IO.
+	 */
+	xfs_buf_rele(bp);
+	return error;
 }
 
 xfs_caddr_t
@@ -1678,8 +1670,6 @@ xfs_alloc_buftarg(
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
 	btp->bt_bdi = blk_get_backing_dev_info(bdev);
-	if (!btp->bt_bdi)
-		goto error;
 
 	if (xfs_setsize_buftarg_early(btp, bdev))
 		goto error;
@@ -1813,13 +1803,19 @@ __xfs_buf_delwri_submit(
 	blk_start_plug(&plug);
 	list_for_each_entry_safe(bp, n, io_list, b_list) {
 		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL);
-		bp->b_flags |= XBF_WRITE;
+		bp->b_flags |= XBF_WRITE | XBF_ASYNC;
 
-		if (!wait) {
-			bp->b_flags |= XBF_ASYNC;
+		/*
+		 * we do all Io submission async. This means if we need to wait
+		 * for IO completion we need to take an extra reference so the
+		 * buffer is still valid on the other side.
+		 */
+		if (wait)
+			xfs_buf_hold(bp);
+		else
 			list_del_init(&bp->b_list);
-		}
-		xfs_bdstrat_cb(bp);
+
+		xfs_buf_submit(bp);
 	}
 	blk_finish_plug(&plug);
 
@@ -1866,7 +1862,10 @@ xfs_buf_delwri_submit(
 		bp = list_first_entry(&io_list, struct xfs_buf, b_list);
 
 		list_del_init(&bp->b_list);
-		error2 = xfs_buf_iowait(bp);
+
+		/* locking the buffer will wait for async IO completion. */
+		xfs_buf_lock(bp);
+		error2 = bp->b_error;
 		xfs_buf_relse(bp);
 		if (!error)
 			error = error2;
@@ -1884,7 +1883,7 @@ xfs_buf_init(void)
 		goto out;
 
 	xfslogd_workqueue = alloc_workqueue("xfslogd",
-					WQ_MEM_RECLAIM | WQ_HIGHPRI, 1);
+				WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_FREEZABLE, 1);
 	if (!xfslogd_workqueue)
 		goto out_free_buf_zone;
 
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index c753183900b3..82002c00af90 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -158,6 +158,7 @@ typedef struct xfs_buf {
 	struct list_head	b_lru;		/* lru list */
 	spinlock_t		b_lock;		/* internal state lock */
 	unsigned int		b_state;	/* internal state flags */
+	int			b_io_error;	/* internal IO error state */
 	wait_queue_head_t	b_waiters;	/* unpin waiters */
 	struct list_head	b_list;
 	struct xfs_perag	*b_pag;		/* contains rbtree root */
@@ -268,9 +269,9 @@ int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length);
 
 struct xfs_buf *xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks,
 				int flags);
-struct xfs_buf *xfs_buf_read_uncached(struct xfs_buftarg *target,
-				xfs_daddr_t daddr, size_t numblks, int flags,
-				const struct xfs_buf_ops *ops);
+int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr,
+			  size_t numblks, int flags, struct xfs_buf **bpp,
+			  const struct xfs_buf_ops *ops);
 void xfs_buf_hold(struct xfs_buf *bp);
 
 /* Releasing Buffers */
@@ -286,18 +287,16 @@ extern void xfs_buf_unlock(xfs_buf_t *);
 
 /* Buffer Read and Write Routines */
 extern int xfs_bwrite(struct xfs_buf *bp);
-extern void xfs_buf_ioend(xfs_buf_t *,	int);
+extern void xfs_buf_ioend(struct xfs_buf *bp);
 extern void xfs_buf_ioerror(xfs_buf_t *, int);
 extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
-extern void xfs_buf_iorequest(xfs_buf_t *);
-extern int xfs_buf_iowait(xfs_buf_t *);
+extern void xfs_buf_submit(struct xfs_buf *bp);
+extern int xfs_buf_submit_wait(struct xfs_buf *bp);
 extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 				xfs_buf_rw_t);
 #define xfs_buf_zero(bp, off, len) \
 	    xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
 
-extern int xfs_bioerror_relse(struct xfs_buf *);
-
 /* Buffer Utility Routines */
 extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
 
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 76007deed31f..f15969543326 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -491,7 +491,7 @@ xfs_buf_item_unpin(
 		xfs_buf_ioerror(bp, -EIO);
 		XFS_BUF_UNDONE(bp);
 		xfs_buf_stale(bp);
-		xfs_buf_ioend(bp, 0);
+		xfs_buf_ioend(bp);
 	}
 }
 
@@ -501,7 +501,7 @@ xfs_buf_item_unpin(
  * buffer being bad..
  */
 
-DEFINE_RATELIMIT_STATE(xfs_buf_write_fail_rl_state, 30 * HZ, 10);
+static DEFINE_RATELIMIT_STATE(xfs_buf_write_fail_rl_state, 30 * HZ, 10);
 
 STATIC uint
 xfs_buf_item_push(
@@ -1081,7 +1081,7 @@ xfs_buf_iodone_callbacks(
 	 * a way to shut the filesystem down if the writes keep failing.
 	 *
 	 * In practice we'll shut the filesystem down soon as non-transient
-	 * erorrs tend to affect the whole device and a failing log write
+	 * errors tend to affect the whole device and a failing log write
 	 * will make us give up.  But we really ought to do better here.
 	 */
 	if (XFS_BUF_ISASYNC(bp)) {
@@ -1094,7 +1094,7 @@ xfs_buf_iodone_callbacks(
 		if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) {
 			bp->b_flags |= XBF_WRITE | XBF_ASYNC |
 				       XBF_DONE | XBF_WRITE_FAIL;
-			xfs_buf_iorequest(bp);
+			xfs_buf_submit(bp);
 		} else {
 			xfs_buf_relse(bp);
 		}
@@ -1115,7 +1115,7 @@ do_callbacks:
 	xfs_buf_do_callbacks(bp);
 	bp->b_fspriv = NULL;
 	bp->b_iodone = NULL;
-	xfs_buf_ioend(bp, 0);
+	xfs_buf_ioend(bp);
 }
 
 /*
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index de5368c803f9..eb596b419942 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -983,7 +983,7 @@ xfs_vm_page_mkwrite(
 
 /*
  * This type is designed to indicate the type of offset we would like
- * to search from page cache for either xfs_seek_data() or xfs_seek_hole().
+ * to search from page cache for xfs_seek_hole_data().
  */
 enum {
 	HOLE_OFF = 0,
@@ -1040,7 +1040,7 @@ xfs_lookup_buffer_offset(
 /*
  * This routine is called to find out and return a data or hole offset
  * from the page cache for unwritten extents according to the desired
- * type for xfs_seek_data() or xfs_seek_hole().
+ * type for xfs_seek_hole_data().
  *
  * The argument offset is used to tell where we start to search from the
  * page cache.  Map is used to figure out the end points of the range to
@@ -1200,9 +1200,10 @@ out:
 }
 
 STATIC loff_t
-xfs_seek_data(
+xfs_seek_hole_data(
 	struct file		*file,
-	loff_t			start)
+	loff_t			start,
+	int			whence)
 {
 	struct inode		*inode = file->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
@@ -1214,6 +1215,9 @@ xfs_seek_data(
 	uint			lock;
 	int			error;
 
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
+
 	lock = xfs_ilock_data_map_shared(ip);
 
 	isize = i_size_read(inode);
@@ -1228,6 +1232,7 @@ xfs_seek_data(
 	 */
 	fsbno = XFS_B_TO_FSBT(mp, start);
 	end = XFS_B_TO_FSB(mp, isize);
+
 	for (;;) {
 		struct xfs_bmbt_irec	map[2];
 		int			nmap = 2;
@@ -1248,29 +1253,48 @@ xfs_seek_data(
 			offset = max_t(loff_t, start,
 				       XFS_FSB_TO_B(mp, map[i].br_startoff));
 
-			/* Landed in a data extent */
-			if (map[i].br_startblock == DELAYSTARTBLOCK ||
-			    (map[i].br_state == XFS_EXT_NORM &&
-			     !isnullstartblock(map[i].br_startblock)))
+			/* Landed in the hole we wanted? */
+			if (whence == SEEK_HOLE &&
+			    map[i].br_startblock == HOLESTARTBLOCK)
+				goto out;
+
+			/* Landed in the data extent we wanted? */
+			if (whence == SEEK_DATA &&
+			    (map[i].br_startblock == DELAYSTARTBLOCK ||
+			     (map[i].br_state == XFS_EXT_NORM &&
+			      !isnullstartblock(map[i].br_startblock))))
 				goto out;
 
 			/*
-			 * Landed in an unwritten extent, try to search data
-			 * from page cache.
+			 * Landed in an unwritten extent, try to search
+			 * for hole or data from page cache.
 			 */
 			if (map[i].br_state == XFS_EXT_UNWRITTEN) {
 				if (xfs_find_get_desired_pgoff(inode, &map[i],
-							DATA_OFF, &offset))
+				      whence == SEEK_HOLE ? HOLE_OFF : DATA_OFF,
+							&offset))
 					goto out;
 			}
 		}
 
 		/*
-		 * map[0] is hole or its an unwritten extent but
-		 * without data in page cache.  Probably means that
-		 * we are reading after EOF if nothing in map[1].
+		 * We only received one extent out of the two requested. This
+		 * means we've hit EOF and didn't find what we are looking for.
 		 */
 		if (nmap == 1) {
+			/*
+			 * If we were looking for a hole, set offset to
+			 * the end of the file (i.e., there is an implicit
+			 * hole at the end of any file).
+		 	 */
+			if (whence == SEEK_HOLE) {
+				offset = isize;
+				break;
+			}
+			/*
+			 * If we were looking for data, it's nowhere to be found
+			 */
+			ASSERT(whence == SEEK_DATA);
 			error = -ENXIO;
 			goto out_unlock;
 		}
@@ -1279,125 +1303,30 @@ xfs_seek_data(
 
 		/*
 		 * Nothing was found, proceed to the next round of search
-		 * if reading offset not beyond or hit EOF.
+		 * if the next reading offset is not at or beyond EOF.
 		 */
 		fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
 		start = XFS_FSB_TO_B(mp, fsbno);
 		if (start >= isize) {
+			if (whence == SEEK_HOLE) {
+				offset = isize;
+				break;
+			}
+			ASSERT(whence == SEEK_DATA);
 			error = -ENXIO;
 			goto out_unlock;
 		}
 	}
 
 out:
-	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
-
-out_unlock:
-	xfs_iunlock(ip, lock);
-
-	if (error)
-		return error;
-	return offset;
-}
-
-STATIC loff_t
-xfs_seek_hole(
-	struct file		*file,
-	loff_t			start)
-{
-	struct inode		*inode = file->f_mapping->host;
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	loff_t			uninitialized_var(offset);
-	xfs_fsize_t		isize;
-	xfs_fileoff_t		fsbno;
-	xfs_filblks_t		end;
-	uint			lock;
-	int			error;
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-	lock = xfs_ilock_data_map_shared(ip);
-
-	isize = i_size_read(inode);
-	if (start >= isize) {
-		error = -ENXIO;
-		goto out_unlock;
-	}
-
-	fsbno = XFS_B_TO_FSBT(mp, start);
-	end = XFS_B_TO_FSB(mp, isize);
-
-	for (;;) {
-		struct xfs_bmbt_irec	map[2];
-		int			nmap = 2;
-		unsigned int		i;
-
-		error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
-				       XFS_BMAPI_ENTIRE);
-		if (error)
-			goto out_unlock;
-
-		/* No extents at given offset, must be beyond EOF */
-		if (nmap == 0) {
-			error = -ENXIO;
-			goto out_unlock;
-		}
-
-		for (i = 0; i < nmap; i++) {
-			offset = max_t(loff_t, start,
-				       XFS_FSB_TO_B(mp, map[i].br_startoff));
-
-			/* Landed in a hole */
-			if (map[i].br_startblock == HOLESTARTBLOCK)
-				goto out;
-
-			/*
-			 * Landed in an unwritten extent, try to search hole
-			 * from page cache.
-			 */
-			if (map[i].br_state == XFS_EXT_UNWRITTEN) {
-				if (xfs_find_get_desired_pgoff(inode, &map[i],
-							HOLE_OFF, &offset))
-					goto out;
-			}
-		}
-
-		/*
-		 * map[0] contains data or its unwritten but contains
-		 * data in page cache, probably means that we are
-		 * reading after EOF.  We should fix offset to point
-		 * to the end of the file(i.e., there is an implicit
-		 * hole at the end of any file).
-		 */
-		if (nmap == 1) {
-			offset = isize;
-			break;
-		}
-
-		ASSERT(i > 1);
-
-		/*
-		 * Both mappings contains data, proceed to the next round of
-		 * search if the current reading offset not beyond or hit EOF.
-		 */
-		fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
-		start = XFS_FSB_TO_B(mp, fsbno);
-		if (start >= isize) {
-			offset = isize;
-			break;
-		}
-	}
-
-out:
 	/*
-	 * At this point, we must have found a hole.  However, the returned
+	 * If at this point we have found the hole we wanted, the returned
 	 * offset may be bigger than the file size as it may be aligned to
-	 * page boundary for unwritten extents, we need to deal with this
+	 * page boundary for unwritten extents.  We need to deal with this
 	 * situation in particular.
 	 */
-	offset = min_t(loff_t, offset, isize);
+	if (whence == SEEK_HOLE)
+		offset = min_t(loff_t, offset, isize);
 	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 
 out_unlock:
@@ -1412,17 +1341,16 @@ STATIC loff_t
 xfs_file_llseek(
 	struct file	*file,
 	loff_t		offset,
-	int		origin)
+	int		whence)
 {
-	switch (origin) {
+	switch (whence) {
 	case SEEK_END:
 	case SEEK_CUR:
 	case SEEK_SET:
-		return generic_file_llseek(file, offset, origin);
-	case SEEK_DATA:
-		return xfs_seek_data(file, offset);
+		return generic_file_llseek(file, offset, whence);
 	case SEEK_HOLE:
-		return xfs_seek_hole(file, offset);
+	case SEEK_DATA:
+		return xfs_seek_hole_data(file, offset, whence);
 	default:
 		return -EINVAL;
 	}
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index f91de1ef05e1..c05ac8b70fa9 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -172,16 +172,11 @@ xfs_growfs_data_private(
 	if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
 		return error;
 	dpct = pct - mp->m_sb.sb_imax_pct;
-	bp = xfs_buf_read_uncached(mp->m_ddev_targp,
+	error = xfs_buf_read_uncached(mp->m_ddev_targp,
 				XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
-				XFS_FSS_TO_BB(mp, 1), 0, NULL);
-	if (!bp)
-		return -EIO;
-	if (bp->b_error) {
-		error = bp->b_error;
-		xfs_buf_relse(bp);
+				XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
+	if (error)
 		return error;
-	}
 	xfs_buf_relse(bp);
 
 	new = nb;	/* use new as a temporary here */
diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c
index 5399ef222dd7..4d41b241298f 100644
--- a/fs/xfs/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
@@ -43,3 +43,7 @@ xfs_param_t xfs_params = {
 	.fstrm_timer	= {	1,		30*100,		3600*100},
 	.eofb_timer	= {	1,		300,		3600*24},
 };
+
+struct xfs_globals xfs_globals = {
+	.log_recovery_delay	=	0,	/* no delay by default */
+};
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 981b2cf51985..b45f7b27b5df 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -33,7 +33,6 @@
 #include "xfs_trace.h"
 #include "xfs_icache.h"
 #include "xfs_bmap_util.h"
-#include "xfs_quota.h"
 #include "xfs_dquot_item.h"
 #include "xfs_dquot.h"
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index fea3c92fb3f0..8ed049d1e332 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -654,7 +654,7 @@ xfs_ialloc(
 	xfs_inode_t	*ip;
 	uint		flags;
 	int		error;
-	timespec_t	tv;
+	struct timespec	tv;
 
 	/*
 	 * Call the space management code to pick
@@ -720,7 +720,7 @@ xfs_ialloc(
 	ip->i_d.di_nextents = 0;
 	ASSERT(ip->i_d.di_nblocks == 0);
 
-	nanotime(&tv);
+	tv = current_fs_time(mp->m_super);
 	ip->i_d.di_mtime.t_sec = (__int32_t)tv.tv_sec;
 	ip->i_d.di_mtime.t_nsec = (__int32_t)tv.tv_nsec;
 	ip->i_d.di_atime = ip->i_d.di_mtime;
@@ -769,6 +769,8 @@ xfs_ialloc(
 					di_flags |= XFS_DIFLAG_EXTSZINHERIT;
 					ip->i_d.di_extsize = pip->i_d.di_extsize;
 				}
+				if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
+					di_flags |= XFS_DIFLAG_PROJINHERIT;
 			} else if (S_ISREG(mode)) {
 				if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
 					di_flags |= XFS_DIFLAG_REALTIME;
@@ -789,8 +791,6 @@ xfs_ialloc(
 			if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
 			    xfs_inherit_nosymlinks)
 				di_flags |= XFS_DIFLAG_NOSYMLINKS;
-			if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
-				di_flags |= XFS_DIFLAG_PROJINHERIT;
 			if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
 			    xfs_inherit_nodefrag)
 				di_flags |= XFS_DIFLAG_NODEFRAG;
@@ -1153,9 +1153,11 @@ xfs_create(
 	if (error)
 		goto out_trans_cancel;
 
-	error = xfs_dir_canenter(tp, dp, name, resblks);
-	if (error)
-		goto out_trans_cancel;
+	if (!resblks) {
+		error = xfs_dir_canenter(tp, dp, name);
+		if (error)
+			goto out_trans_cancel;
+	}
 
 	/*
 	 * A newly created regular or special file just has one directory
@@ -1421,9 +1423,11 @@ xfs_link(
 		goto error_return;
 	}
 
-	error = xfs_dir_canenter(tp, tdp, target_name, resblks);
-	if (error)
-		goto error_return;
+	if (!resblks) {
+		error = xfs_dir_canenter(tp, tdp, target_name);
+		if (error)
+			goto error_return;
+	}
 
 	xfs_bmap_init(&free_list, &first_block);
 
@@ -2759,9 +2763,11 @@ xfs_rename(
 		 * If there's no space reservation, check the entry will
 		 * fit before actually inserting it.
 		 */
-		error = xfs_dir_canenter(tp, target_dp, target_name, spaceres);
-		if (error)
-			goto error_return;
+		if (!spaceres) {
+			error = xfs_dir_canenter(tp, target_dp, target_name);
+			if (error)
+				goto error_return;
+		}
 		/*
 		 * If target does not exist and the rename crosses
 		 * directories, adjust the target directory link count
@@ -3056,7 +3062,7 @@ cluster_corrupt_out:
 			XFS_BUF_UNDONE(bp);
 			xfs_buf_stale(bp);
 			xfs_buf_ioerror(bp, -EIO);
-			xfs_buf_ioend(bp, 0);
+			xfs_buf_ioend(bp);
 		} else {
 			xfs_buf_stale(bp);
 			xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index c10e3fadd9af..9af2882e1f4c 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -102,7 +102,7 @@ xfs_new_eof(struct xfs_inode *ip, xfs_fsize_t new_size)
 {
 	xfs_fsize_t i_size = i_size_read(VFS_I(ip));
 
-	if (new_size > i_size)
+	if (new_size > i_size || new_size < 0)
 		new_size = i_size;
 	return new_size > ip->i_d.di_size ? new_size : 0;
 }
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index de5a7be36e60..63de0b0acc32 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -615,7 +615,7 @@ xfs_iflush_done(
 	blip = bp->b_fspriv;
 	prev = NULL;
 	while (blip != NULL) {
-		if (lip->li_cb != xfs_iflush_done) {
+		if (blip->li_cb != xfs_iflush_done) {
 			prev = blip;
 			blip = blip->li_bio_list;
 			continue;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 3799695b9249..24c926b6fe85 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -968,8 +968,6 @@ xfs_set_diflags(
 		di_flags |= XFS_DIFLAG_NOATIME;
 	if (xflags & XFS_XFLAG_NODUMP)
 		di_flags |= XFS_DIFLAG_NODUMP;
-	if (xflags & XFS_XFLAG_PROJINHERIT)
-		di_flags |= XFS_DIFLAG_PROJINHERIT;
 	if (xflags & XFS_XFLAG_NODEFRAG)
 		di_flags |= XFS_DIFLAG_NODEFRAG;
 	if (xflags & XFS_XFLAG_FILESTREAM)
@@ -981,6 +979,8 @@ xfs_set_diflags(
 			di_flags |= XFS_DIFLAG_NOSYMLINKS;
 		if (xflags & XFS_XFLAG_EXTSZINHERIT)
 			di_flags |= XFS_DIFLAG_EXTSZINHERIT;
+		if (xflags & XFS_XFLAG_PROJINHERIT)
+			di_flags |= XFS_DIFLAG_PROJINHERIT;
 	} else if (S_ISREG(ip->i_d.di_mode)) {
 		if (xflags & XFS_XFLAG_REALTIME)
 			di_flags |= XFS_DIFLAG_REALTIME;
@@ -1231,13 +1231,25 @@ xfs_ioctl_setattr(
 
 	}
 
-	if (mask & FSX_EXTSIZE)
-		ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
 	if (mask & FSX_XFLAGS) {
 		xfs_set_diflags(ip, fa->fsx_xflags);
 		xfs_diflags_to_linux(ip);
 	}
 
+	/*
+	 * Only set the extent size hint if we've already determined that the
+	 * extent size hint should be set on the inode. If no extent size flags
+	 * are set on the inode then unconditionally clear the extent size hint.
+	 */
+	if (mask & FSX_EXTSIZE) {
+		int	extsize = 0;
+
+		if (ip->i_d.di_flags &
+				(XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT))
+			extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
+		ip->i_d.di_extsize = extsize;
+	}
+
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
@@ -1349,7 +1361,7 @@ xfs_ioc_setxflags(
 STATIC int
 xfs_getbmap_format(void **ap, struct getbmapx *bmv, int *full)
 {
-	struct getbmap __user	*base = *ap;
+	struct getbmap __user	*base = (struct getbmap __user *)*ap;
 
 	/* copy only getbmap portion (not getbmapx) */
 	if (copy_to_user(base, bmv, sizeof(struct getbmap)))
@@ -1380,7 +1392,7 @@ xfs_ioc_getbmap(
 		bmx.bmv_iflags |= BMV_IF_NO_DMAPI_READ;
 
 	error = xfs_getbmap(ip, &bmx, xfs_getbmap_format,
-			    (struct getbmap *)arg+1);
+			    (__force struct getbmap *)arg+1);
 	if (error)
 		return error;
 
@@ -1393,7 +1405,7 @@ xfs_ioc_getbmap(
 STATIC int
 xfs_getbmapx_format(void **ap, struct getbmapx *bmv, int *full)
 {
-	struct getbmapx __user	*base = *ap;
+	struct getbmapx __user	*base = (struct getbmapx __user *)*ap;
 
 	if (copy_to_user(base, bmv, sizeof(struct getbmapx)))
 		return -EFAULT;
@@ -1420,7 +1432,7 @@ xfs_ioc_getbmapx(
 		return -EINVAL;
 
 	error = xfs_getbmap(ip, &bmx, xfs_getbmapx_format,
-			    (struct getbmapx *)arg+1);
+			    (__force struct getbmapx *)arg+1);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index a554646ff141..94ce027e28e3 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -160,6 +160,7 @@ xfs_ioctl32_bstat_copyin(
 	    get_user(bstat->bs_gen,	&bstat32->bs_gen)	||
 	    get_user(bstat->bs_projid_lo, &bstat32->bs_projid_lo) ||
 	    get_user(bstat->bs_projid_hi, &bstat32->bs_projid_hi) ||
+	    get_user(bstat->bs_forkoff,	&bstat32->bs_forkoff)	||
 	    get_user(bstat->bs_dmevmask, &bstat32->bs_dmevmask)	||
 	    get_user(bstat->bs_dmstate,	&bstat32->bs_dmstate)	||
 	    get_user(bstat->bs_aextents, &bstat32->bs_aextents))
@@ -214,6 +215,7 @@ xfs_bulkstat_one_fmt_compat(
 	    put_user(buffer->bs_gen,	  &p32->bs_gen)		||
 	    put_user(buffer->bs_projid,	  &p32->bs_projid)	||
 	    put_user(buffer->bs_projid_hi,	&p32->bs_projid_hi)	||
+	    put_user(buffer->bs_forkoff,  &p32->bs_forkoff)	||
 	    put_user(buffer->bs_dmevmask, &p32->bs_dmevmask)	||
 	    put_user(buffer->bs_dmstate,  &p32->bs_dmstate)	||
 	    put_user(buffer->bs_aextents, &p32->bs_aextents))
diff --git a/fs/xfs/xfs_ioctl32.h b/fs/xfs/xfs_ioctl32.h
index 80f4060e8970..b1bb45444df8 100644
--- a/fs/xfs/xfs_ioctl32.h
+++ b/fs/xfs/xfs_ioctl32.h
@@ -67,8 +67,9 @@ typedef struct compat_xfs_bstat {
 	__u32		bs_gen;		/* generation count		*/
 	__u16		bs_projid_lo;	/* lower part of project id	*/
 #define	bs_projid	bs_projid_lo	/* (previously just bs_projid)	*/
+	__u16		bs_forkoff;	/* inode fork offset in bytes	*/
 	__u16		bs_projid_hi;	/* high part of project id	*/
-	unsigned char	bs_pad[12];	/* pad space, unused		*/
+	unsigned char	bs_pad[10];	/* pad space, unused		*/
 	__u32		bs_dmevmask;	/* DMIG event mask		*/
 	__u16		bs_dmstate;	/* DMIG state info		*/
 	__u16		bs_aextents;	/* attribute number of extents	*/
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index e9c47b6f5e5a..afcf3c926565 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -404,8 +404,8 @@ xfs_quota_calc_throttle(
 	int shift = 0;
 	struct xfs_dquot *dq = xfs_inode_dquot(ip, type);
 
-	/* over hi wmark, squash the prealloc completely */
-	if (dq->q_res_bcount >= dq->q_prealloc_hi_wmark) {
+	/* no dq, or over hi wmark, squash the prealloc completely */
+	if (!dq || dq->q_res_bcount >= dq->q_prealloc_hi_wmark) {
 		*qblocks = 0;
 		*qfreesp = 0;
 		return;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 72129493e9d3..ec6dcdc181ee 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -849,6 +849,36 @@ xfs_setattr_size(
 		return error;
 	truncate_setsize(inode, newsize);
 
+	/*
+	 * The "we can't serialise against page faults" pain gets worse.
+	 *
+	 * If the file is mapped then we have to clean the page at the old EOF
+	 * when extending the file. Extending the file can expose changes the
+	 * underlying page mapping (e.g. from beyond EOF to a hole or
+	 * unwritten), and so on the next attempt to write to that page we need
+	 * to remap it for write. i.e. we need .page_mkwrite() to be called.
+	 * Hence we need to clean the page to clean the pte and so a new write
+	 * fault will be triggered appropriately.
+	 *
+	 * If we do it before we change the inode size, then we can race with a
+	 * page fault that maps the page with exactly the same problem. If we do
+	 * it after we change the file size, then a new page fault can come in
+	 * and allocate space before we've run the rest of the truncate
+	 * transaction. That's kinda grotesque, but it's better than have data
+	 * over a hole, and so that's the lesser evil that has been chosen here.
+	 *
+	 * The real solution, however, is to have some mechanism for locking out
+	 * page faults while a truncate is in progress.
+	 */
+	if (newsize > oldsize && mapping_mapped(VFS_I(ip)->i_mapping)) {
+		error = filemap_write_and_wait_range(
+				VFS_I(ip)->i_mapping,
+				round_down(oldsize, PAGE_CACHE_SIZE),
+				round_up(oldsize, PAGE_CACHE_SIZE) - 1);
+		if (error)
+			return error;
+	}
+
 	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
 	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
 	if (error)
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index f71be9c68017..f1deb961a296 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -639,7 +639,8 @@ next_ag:
 		xfs_buf_relse(agbp);
 		agbp = NULL;
 		agino = 0;
-	} while (++agno < mp->m_sb.sb_agcount);
+		agno++;
+	} while (agno < mp->m_sb.sb_agcount);
 
 	if (!error) {
 		if (bufidx) {
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index d10dc8f397c9..6a51619d8690 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -56,7 +56,6 @@ typedef __uint64_t __psunsigned_t;
 
 #include "kmem.h"
 #include "mrlock.h"
-#include "time.h"
 #include "uuid.h"
 
 #include <linux/semaphore.h>
@@ -179,6 +178,11 @@ typedef __uint64_t __psunsigned_t;
 #define MAX(a,b)	(max(a,b))
 #define howmany(x, y)	(((x)+((y)-1))/(y))
 
+static inline void delay(long ticks)
+{
+	schedule_timeout_uninterruptible(ticks);
+}
+
 /*
  * XFS wrapper structure for sysfs support. It depends on external data
  * structures and is embedded in various internal data structures to implement
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index ca4fd5bd8522..fe88ef67f93a 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1678,7 +1678,7 @@ xlog_bdstrat(
 	if (iclog->ic_state & XLOG_STATE_IOERROR) {
 		xfs_buf_ioerror(bp, -EIO);
 		xfs_buf_stale(bp);
-		xfs_buf_ioend(bp, 0);
+		xfs_buf_ioend(bp);
 		/*
 		 * It would seem logical to return EIO here, but we rely on
 		 * the log state machine to propagate I/O errors instead of
@@ -1688,7 +1688,7 @@ xlog_bdstrat(
 		return 0;
 	}
 
-	xfs_buf_iorequest(bp);
+	xfs_buf_submit(bp);
 	return 0;
 }
 
@@ -3867,18 +3867,17 @@ xlog_state_ioerror(
  * This is called from xfs_force_shutdown, when we're forcibly
  * shutting down the filesystem, typically because of an IO error.
  * Our main objectives here are to make sure that:
- *	a. the filesystem gets marked 'SHUTDOWN' for all interested
+ *	a. if !logerror, flush the logs to disk. Anything modified
+ *	   after this is ignored.
+ *	b. the filesystem gets marked 'SHUTDOWN' for all interested
  *	   parties to find out, 'atomically'.
- *	b. those who're sleeping on log reservations, pinned objects and
+ *	c. those who're sleeping on log reservations, pinned objects and
  *	    other resources get woken up, and be told the bad news.
- *	c. nothing new gets queued up after (a) and (b) are done.
- *	d. if !logerror, flush the iclogs to disk, then seal them off
- *	   for business.
+ *	d. nothing new gets queued up after (b) and (c) are done.
  *
- * Note: for delayed logging the !logerror case needs to flush the regions
- * held in memory out to the iclogs before flushing them to disk. This needs
- * to be done before the log is marked as shutdown, otherwise the flush to the
- * iclogs will fail.
+ * Note: for the !logerror case we need to flush the regions held in memory out
+ * to disk first. This needs to be done before the log is marked as shutdown,
+ * otherwise the iclog writes will fail.
  */
 int
 xfs_log_force_umount(
@@ -3910,16 +3909,16 @@ xfs_log_force_umount(
 		ASSERT(XLOG_FORCED_SHUTDOWN(log));
 		return 1;
 	}
-	retval = 0;
 
 	/*
-	 * Flush the in memory commit item list before marking the log as
-	 * being shut down. We need to do it in this order to ensure all the
-	 * completed transactions are flushed to disk with the xfs_log_force()
-	 * call below.
+	 * Flush all the completed transactions to disk before marking the log
+	 * being shut down. We need to do it in this order to ensure that
+	 * completed operations are safely on disk before we shut down, and that
+	 * we don't have to issue any buffer IO after the shutdown flags are set
+	 * to guarantee this.
 	 */
 	if (!logerror)
-		xlog_cil_force(log);
+		_xfs_log_force(mp, XFS_LOG_SYNC, NULL);
 
 	/*
 	 * mark the filesystem and the as in a shutdown state and wake
@@ -3931,18 +3930,11 @@ xfs_log_force_umount(
 		XFS_BUF_DONE(mp->m_sb_bp);
 
 	/*
-	 * This flag is sort of redundant because of the mount flag, but
-	 * it's good to maintain the separation between the log and the rest
-	 * of XFS.
+	 * Mark the log and the iclogs with IO error flags to prevent any
+	 * further log IO from being issued or completed.
 	 */
 	log->l_flags |= XLOG_IO_ERROR;
-
-	/*
-	 * If we hit a log error, we want to mark all the iclogs IOERROR
-	 * while we're still holding the loglock.
-	 */
-	if (logerror)
-		retval = xlog_state_ioerror(log);
+	retval = xlog_state_ioerror(log);
 	spin_unlock(&log->l_icloglock);
 
 	/*
@@ -3955,19 +3947,6 @@ xfs_log_force_umount(
 	xlog_grant_head_wake_all(&log->l_reserve_head);
 	xlog_grant_head_wake_all(&log->l_write_head);
 
-	if (!(log->l_iclog->ic_state & XLOG_STATE_IOERROR)) {
-		ASSERT(!logerror);
-		/*
-		 * Force the incore logs to disk before shutting the
-		 * log down completely.
-		 */
-		_xfs_log_force(mp, XFS_LOG_SYNC, NULL);
-
-		spin_lock(&log->l_icloglock);
-		retval = xlog_state_ioerror(log);
-		spin_unlock(&log->l_icloglock);
-	}
-
 	/*
 	 * Wake up everybody waiting on xfs_log_force. Wake the CIL push first
 	 * as if the log writes were completed. The abort handling in the log
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index f6b79e5325dd..f506c457011e 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -463,12 +463,40 @@ xlog_cil_push(
 		spin_unlock(&cil->xc_push_lock);
 		goto out_skip;
 	}
-	spin_unlock(&cil->xc_push_lock);
 
 
 	/* check for a previously pushed seqeunce */
-	if (push_seq < cil->xc_ctx->sequence)
+	if (push_seq < cil->xc_ctx->sequence) {
+		spin_unlock(&cil->xc_push_lock);
 		goto out_skip;
+	}
+
+	/*
+	 * We are now going to push this context, so add it to the committing
+	 * list before we do anything else. This ensures that anyone waiting on
+	 * this push can easily detect the difference between a "push in
+	 * progress" and "CIL is empty, nothing to do".
+	 *
+	 * IOWs, a wait loop can now check for:
+	 *	the current sequence not being found on the committing list;
+	 *	an empty CIL; and
+	 *	an unchanged sequence number
+	 * to detect a push that had nothing to do and therefore does not need
+	 * waiting on. If the CIL is not empty, we get put on the committing
+	 * list before emptying the CIL and bumping the sequence number. Hence
+	 * an empty CIL and an unchanged sequence number means we jumped out
+	 * above after doing nothing.
+	 *
+	 * Hence the waiter will either find the commit sequence on the
+	 * committing list or the sequence number will be unchanged and the CIL
+	 * still dirty. In that latter case, the push has not yet started, and
+	 * so the waiter will have to continue trying to check the CIL
+	 * committing list until it is found. In extreme cases of delay, the
+	 * sequence may fully commit between the attempts the wait makes to wait
+	 * on the commit sequence.
+	 */
+	list_add(&ctx->committing, &cil->xc_committing);
+	spin_unlock(&cil->xc_push_lock);
 
 	/*
 	 * pull all the log vectors off the items in the CIL, and
@@ -532,7 +560,6 @@ xlog_cil_push(
 	 */
 	spin_lock(&cil->xc_push_lock);
 	cil->xc_current_sequence = new_ctx->sequence;
-	list_add(&ctx->committing, &cil->xc_committing);
 	spin_unlock(&cil->xc_push_lock);
 	up_write(&cil->xc_ctx_lock);
 
@@ -855,13 +882,15 @@ restart:
 	 * Hence by the time we have got here it our sequence may not have been
 	 * pushed yet. This is true if the current sequence still matches the
 	 * push sequence after the above wait loop and the CIL still contains
-	 * dirty objects.
+	 * dirty objects. This is guaranteed by the push code first adding the
+	 * context to the committing list before emptying the CIL.
 	 *
-	 * When the push occurs, it will empty the CIL and atomically increment
-	 * the currect sequence past the push sequence and move it into the
-	 * committing list. Of course, if the CIL is clean at the time of the
-	 * push, it won't have pushed the CIL at all, so in that case we should
-	 * try the push for this sequence again from the start just in case.
+	 * Hence if we don't find the context in the committing list and the
+	 * current sequence number is unchanged then the CIL contents are
+	 * significant.  If the CIL is empty, if means there was nothing to push
+	 * and that means there is nothing to wait for. If the CIL is not empty,
+	 * it means we haven't yet started the push, because if it had started
+	 * we would have found the context on the committing list.
 	 */
 	if (sequence == cil->xc_current_sequence &&
 	    !list_empty(&cil->xc_cil)) {
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 1fd5787add99..00cd7f3a8f59 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -193,12 +193,8 @@ xlog_bread_noalign(
 	bp->b_io_length = nbblks;
 	bp->b_error = 0;
 
-	if (XFS_FORCED_SHUTDOWN(log->l_mp))
-		return -EIO;
-
-	xfs_buf_iorequest(bp);
-	error = xfs_buf_iowait(bp);
-	if (error)
+	error = xfs_buf_submit_wait(bp);
+	if (error && !XFS_FORCED_SHUTDOWN(log->l_mp))
 		xfs_buf_ioerror_alert(bp, __func__);
 	return error;
 }
@@ -378,12 +374,14 @@ xlog_recover_iodone(
 		 * We're not going to bother about retrying
 		 * this during recovery. One strike!
 		 */
-		xfs_buf_ioerror_alert(bp, __func__);
-		xfs_force_shutdown(bp->b_target->bt_mount,
-					SHUTDOWN_META_IO_ERROR);
+		if (!XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
+			xfs_buf_ioerror_alert(bp, __func__);
+			xfs_force_shutdown(bp->b_target->bt_mount,
+						SHUTDOWN_META_IO_ERROR);
+		}
 	}
 	bp->b_iodone = NULL;
-	xfs_buf_ioend(bp, 0);
+	xfs_buf_ioend(bp);
 }
 
 /*
@@ -1445,160 +1443,6 @@ xlog_clear_stale_blocks(
  ******************************************************************************
  */
 
-STATIC xlog_recover_t *
-xlog_recover_find_tid(
-	struct hlist_head	*head,
-	xlog_tid_t		tid)
-{
-	xlog_recover_t		*trans;
-
-	hlist_for_each_entry(trans, head, r_list) {
-		if (trans->r_log_tid == tid)
-			return trans;
-	}
-	return NULL;
-}
-
-STATIC void
-xlog_recover_new_tid(
-	struct hlist_head	*head,
-	xlog_tid_t		tid,
-	xfs_lsn_t		lsn)
-{
-	xlog_recover_t		*trans;
-
-	trans = kmem_zalloc(sizeof(xlog_recover_t), KM_SLEEP);
-	trans->r_log_tid   = tid;
-	trans->r_lsn	   = lsn;
-	INIT_LIST_HEAD(&trans->r_itemq);
-
-	INIT_HLIST_NODE(&trans->r_list);
-	hlist_add_head(&trans->r_list, head);
-}
-
-STATIC void
-xlog_recover_add_item(
-	struct list_head	*head)
-{
-	xlog_recover_item_t	*item;
-
-	item = kmem_zalloc(sizeof(xlog_recover_item_t), KM_SLEEP);
-	INIT_LIST_HEAD(&item->ri_list);
-	list_add_tail(&item->ri_list, head);
-}
-
-STATIC int
-xlog_recover_add_to_cont_trans(
-	struct xlog		*log,
-	struct xlog_recover	*trans,
-	xfs_caddr_t		dp,
-	int			len)
-{
-	xlog_recover_item_t	*item;
-	xfs_caddr_t		ptr, old_ptr;
-	int			old_len;
-
-	if (list_empty(&trans->r_itemq)) {
-		/* finish copying rest of trans header */
-		xlog_recover_add_item(&trans->r_itemq);
-		ptr = (xfs_caddr_t) &trans->r_theader +
-				sizeof(xfs_trans_header_t) - len;
-		memcpy(ptr, dp, len); /* d, s, l */
-		return 0;
-	}
-	/* take the tail entry */
-	item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list);
-
-	old_ptr = item->ri_buf[item->ri_cnt-1].i_addr;
-	old_len = item->ri_buf[item->ri_cnt-1].i_len;
-
-	ptr = kmem_realloc(old_ptr, len+old_len, old_len, KM_SLEEP);
-	memcpy(&ptr[old_len], dp, len); /* d, s, l */
-	item->ri_buf[item->ri_cnt-1].i_len += len;
-	item->ri_buf[item->ri_cnt-1].i_addr = ptr;
-	trace_xfs_log_recover_item_add_cont(log, trans, item, 0);
-	return 0;
-}
-
-/*
- * The next region to add is the start of a new region.  It could be
- * a whole region or it could be the first part of a new region.  Because
- * of this, the assumption here is that the type and size fields of all
- * format structures fit into the first 32 bits of the structure.
- *
- * This works because all regions must be 32 bit aligned.  Therefore, we
- * either have both fields or we have neither field.  In the case we have
- * neither field, the data part of the region is zero length.  We only have
- * a log_op_header and can throw away the header since a new one will appear
- * later.  If we have at least 4 bytes, then we can determine how many regions
- * will appear in the current log item.
- */
-STATIC int
-xlog_recover_add_to_trans(
-	struct xlog		*log,
-	struct xlog_recover	*trans,
-	xfs_caddr_t		dp,
-	int			len)
-{
-	xfs_inode_log_format_t	*in_f;			/* any will do */
-	xlog_recover_item_t	*item;
-	xfs_caddr_t		ptr;
-
-	if (!len)
-		return 0;
-	if (list_empty(&trans->r_itemq)) {
-		/* we need to catch log corruptions here */
-		if (*(uint *)dp != XFS_TRANS_HEADER_MAGIC) {
-			xfs_warn(log->l_mp, "%s: bad header magic number",
-				__func__);
-			ASSERT(0);
-			return -EIO;
-		}
-		if (len == sizeof(xfs_trans_header_t))
-			xlog_recover_add_item(&trans->r_itemq);
-		memcpy(&trans->r_theader, dp, len); /* d, s, l */
-		return 0;
-	}
-
-	ptr = kmem_alloc(len, KM_SLEEP);
-	memcpy(ptr, dp, len);
-	in_f = (xfs_inode_log_format_t *)ptr;
-
-	/* take the tail entry */
-	item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list);
-	if (item->ri_total != 0 &&
-	     item->ri_total == item->ri_cnt) {
-		/* tail item is in use, get a new one */
-		xlog_recover_add_item(&trans->r_itemq);
-		item = list_entry(trans->r_itemq.prev,
-					xlog_recover_item_t, ri_list);
-	}
-
-	if (item->ri_total == 0) {		/* first region to be added */
-		if (in_f->ilf_size == 0 ||
-		    in_f->ilf_size > XLOG_MAX_REGIONS_IN_ITEM) {
-			xfs_warn(log->l_mp,
-		"bad number of regions (%d) in inode log format",
-				  in_f->ilf_size);
-			ASSERT(0);
-			kmem_free(ptr);
-			return -EIO;
-		}
-
-		item->ri_total = in_f->ilf_size;
-		item->ri_buf =
-			kmem_zalloc(item->ri_total * sizeof(xfs_log_iovec_t),
-				    KM_SLEEP);
-	}
-	ASSERT(item->ri_total > item->ri_cnt);
-	/* Description region is ri_buf[0] */
-	item->ri_buf[item->ri_cnt].i_addr = ptr;
-	item->ri_buf[item->ri_cnt].i_len  = len;
-	item->ri_cnt++;
-	trace_xfs_log_recover_item_add(log, trans, item, 0);
-	return 0;
-}
-
 /*
  * Sort the log items in the transaction.
  *
@@ -3254,31 +3098,6 @@ xlog_recover_do_icreate_pass2(
 	return 0;
 }
 
-/*
- * Free up any resources allocated by the transaction
- *
- * Remember that EFIs, EFDs, and IUNLINKs are handled later.
- */
-STATIC void
-xlog_recover_free_trans(
-	struct xlog_recover	*trans)
-{
-	xlog_recover_item_t	*item, *n;
-	int			i;
-
-	list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) {
-		/* Free the regions in the item. */
-		list_del(&item->ri_list);
-		for (i = 0; i < item->ri_cnt; i++)
-			kmem_free(item->ri_buf[i].i_addr);
-		/* Free the item itself */
-		kmem_free(item->ri_buf);
-		kmem_free(item);
-	}
-	/* Free the transaction recover structure */
-	kmem_free(trans);
-}
-
 STATIC void
 xlog_recover_buffer_ra_pass2(
 	struct xlog                     *log,
@@ -3528,22 +3347,309 @@ out:
 	if (!list_empty(&done_list))
 		list_splice_init(&done_list, &trans->r_itemq);
 
-	xlog_recover_free_trans(trans);
-
 	error2 = xfs_buf_delwri_submit(&buffer_list);
 	return error ? error : error2;
 }
 
+STATIC void
+xlog_recover_add_item(
+	struct list_head	*head)
+{
+	xlog_recover_item_t	*item;
+
+	item = kmem_zalloc(sizeof(xlog_recover_item_t), KM_SLEEP);
+	INIT_LIST_HEAD(&item->ri_list);
+	list_add_tail(&item->ri_list, head);
+}
+
 STATIC int
-xlog_recover_unmount_trans(
-	struct xlog		*log)
+xlog_recover_add_to_cont_trans(
+	struct xlog		*log,
+	struct xlog_recover	*trans,
+	xfs_caddr_t		dp,
+	int			len)
 {
-	/* Do nothing now */
-	xfs_warn(log->l_mp, "%s: Unmount LR", __func__);
+	xlog_recover_item_t	*item;
+	xfs_caddr_t		ptr, old_ptr;
+	int			old_len;
+
+	if (list_empty(&trans->r_itemq)) {
+		/* finish copying rest of trans header */
+		xlog_recover_add_item(&trans->r_itemq);
+		ptr = (xfs_caddr_t) &trans->r_theader +
+				sizeof(xfs_trans_header_t) - len;
+		memcpy(ptr, dp, len);
+		return 0;
+	}
+	/* take the tail entry */
+	item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list);
+
+	old_ptr = item->ri_buf[item->ri_cnt-1].i_addr;
+	old_len = item->ri_buf[item->ri_cnt-1].i_len;
+
+	ptr = kmem_realloc(old_ptr, len+old_len, old_len, KM_SLEEP);
+	memcpy(&ptr[old_len], dp, len);
+	item->ri_buf[item->ri_cnt-1].i_len += len;
+	item->ri_buf[item->ri_cnt-1].i_addr = ptr;
+	trace_xfs_log_recover_item_add_cont(log, trans, item, 0);
+	return 0;
+}
+
+/*
+ * The next region to add is the start of a new region.  It could be
+ * a whole region or it could be the first part of a new region.  Because
+ * of this, the assumption here is that the type and size fields of all
+ * format structures fit into the first 32 bits of the structure.
+ *
+ * This works because all regions must be 32 bit aligned.  Therefore, we
+ * either have both fields or we have neither field.  In the case we have
+ * neither field, the data part of the region is zero length.  We only have
+ * a log_op_header and can throw away the header since a new one will appear
+ * later.  If we have at least 4 bytes, then we can determine how many regions
+ * will appear in the current log item.
+ */
+STATIC int
+xlog_recover_add_to_trans(
+	struct xlog		*log,
+	struct xlog_recover	*trans,
+	xfs_caddr_t		dp,
+	int			len)
+{
+	xfs_inode_log_format_t	*in_f;			/* any will do */
+	xlog_recover_item_t	*item;
+	xfs_caddr_t		ptr;
+
+	if (!len)
+		return 0;
+	if (list_empty(&trans->r_itemq)) {
+		/* we need to catch log corruptions here */
+		if (*(uint *)dp != XFS_TRANS_HEADER_MAGIC) {
+			xfs_warn(log->l_mp, "%s: bad header magic number",
+				__func__);
+			ASSERT(0);
+			return -EIO;
+		}
+		if (len == sizeof(xfs_trans_header_t))
+			xlog_recover_add_item(&trans->r_itemq);
+		memcpy(&trans->r_theader, dp, len);
+		return 0;
+	}
+
+	ptr = kmem_alloc(len, KM_SLEEP);
+	memcpy(ptr, dp, len);
+	in_f = (xfs_inode_log_format_t *)ptr;
+
+	/* take the tail entry */
+	item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list);
+	if (item->ri_total != 0 &&
+	     item->ri_total == item->ri_cnt) {
+		/* tail item is in use, get a new one */
+		xlog_recover_add_item(&trans->r_itemq);
+		item = list_entry(trans->r_itemq.prev,
+					xlog_recover_item_t, ri_list);
+	}
+
+	if (item->ri_total == 0) {		/* first region to be added */
+		if (in_f->ilf_size == 0 ||
+		    in_f->ilf_size > XLOG_MAX_REGIONS_IN_ITEM) {
+			xfs_warn(log->l_mp,
+		"bad number of regions (%d) in inode log format",
+				  in_f->ilf_size);
+			ASSERT(0);
+			kmem_free(ptr);
+			return -EIO;
+		}
+
+		item->ri_total = in_f->ilf_size;
+		item->ri_buf =
+			kmem_zalloc(item->ri_total * sizeof(xfs_log_iovec_t),
+				    KM_SLEEP);
+	}
+	ASSERT(item->ri_total > item->ri_cnt);
+	/* Description region is ri_buf[0] */
+	item->ri_buf[item->ri_cnt].i_addr = ptr;
+	item->ri_buf[item->ri_cnt].i_len  = len;
+	item->ri_cnt++;
+	trace_xfs_log_recover_item_add(log, trans, item, 0);
 	return 0;
 }
 
 /*
+ * Free up any resources allocated by the transaction
+ *
+ * Remember that EFIs, EFDs, and IUNLINKs are handled later.
+ */
+STATIC void
+xlog_recover_free_trans(
+	struct xlog_recover	*trans)
+{
+	xlog_recover_item_t	*item, *n;
+	int			i;
+
+	list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) {
+		/* Free the regions in the item. */
+		list_del(&item->ri_list);
+		for (i = 0; i < item->ri_cnt; i++)
+			kmem_free(item->ri_buf[i].i_addr);
+		/* Free the item itself */
+		kmem_free(item->ri_buf);
+		kmem_free(item);
+	}
+	/* Free the transaction recover structure */
+	kmem_free(trans);
+}
+
+/*
+ * On error or completion, trans is freed.
+ */
+STATIC int
+xlog_recovery_process_trans(
+	struct xlog		*log,
+	struct xlog_recover	*trans,
+	xfs_caddr_t		dp,
+	unsigned int		len,
+	unsigned int		flags,
+	int			pass)
+{
+	int			error = 0;
+	bool			freeit = false;
+
+	/* mask off ophdr transaction container flags */
+	flags &= ~XLOG_END_TRANS;
+	if (flags & XLOG_WAS_CONT_TRANS)
+		flags &= ~XLOG_CONTINUE_TRANS;
+
+	/*
+	 * Callees must not free the trans structure. We'll decide if we need to
+	 * free it or not based on the operation being done and it's result.
+	 */
+	switch (flags) {
+	/* expected flag values */
+	case 0:
+	case XLOG_CONTINUE_TRANS:
+		error = xlog_recover_add_to_trans(log, trans, dp, len);
+		break;
+	case XLOG_WAS_CONT_TRANS:
+		error = xlog_recover_add_to_cont_trans(log, trans, dp, len);
+		break;
+	case XLOG_COMMIT_TRANS:
+		error = xlog_recover_commit_trans(log, trans, pass);
+		/* success or fail, we are now done with this transaction. */
+		freeit = true;
+		break;
+
+	/* unexpected flag values */
+	case XLOG_UNMOUNT_TRANS:
+		/* just skip trans */
+		xfs_warn(log->l_mp, "%s: Unmount LR", __func__);
+		freeit = true;
+		break;
+	case XLOG_START_TRANS:
+	default:
+		xfs_warn(log->l_mp, "%s: bad flag 0x%x", __func__, flags);
+		ASSERT(0);
+		error = -EIO;
+		break;
+	}
+	if (error || freeit)
+		xlog_recover_free_trans(trans);
+	return error;
+}
+
+/*
+ * Lookup the transaction recovery structure associated with the ID in the
+ * current ophdr. If the transaction doesn't exist and the start flag is set in
+ * the ophdr, then allocate a new transaction for future ID matches to find.
+ * Either way, return what we found during the lookup - an existing transaction
+ * or nothing.
+ */
+STATIC struct xlog_recover *
+xlog_recover_ophdr_to_trans(
+	struct hlist_head	rhash[],
+	struct xlog_rec_header	*rhead,
+	struct xlog_op_header	*ohead)
+{
+	struct xlog_recover	*trans;
+	xlog_tid_t		tid;
+	struct hlist_head	*rhp;
+
+	tid = be32_to_cpu(ohead->oh_tid);
+	rhp = &rhash[XLOG_RHASH(tid)];
+	hlist_for_each_entry(trans, rhp, r_list) {
+		if (trans->r_log_tid == tid)
+			return trans;
+	}
+
+	/*
+	 * skip over non-start transaction headers - we could be
+	 * processing slack space before the next transaction starts
+	 */
+	if (!(ohead->oh_flags & XLOG_START_TRANS))
+		return NULL;
+
+	ASSERT(be32_to_cpu(ohead->oh_len) == 0);
+
+	/*
+	 * This is a new transaction so allocate a new recovery container to
+	 * hold the recovery ops that will follow.
+	 */
+	trans = kmem_zalloc(sizeof(struct xlog_recover), KM_SLEEP);
+	trans->r_log_tid = tid;
+	trans->r_lsn = be64_to_cpu(rhead->h_lsn);
+	INIT_LIST_HEAD(&trans->r_itemq);
+	INIT_HLIST_NODE(&trans->r_list);
+	hlist_add_head(&trans->r_list, rhp);
+
+	/*
+	 * Nothing more to do for this ophdr. Items to be added to this new
+	 * transaction will be in subsequent ophdr containers.
+	 */
+	return NULL;
+}
+
+STATIC int
+xlog_recover_process_ophdr(
+	struct xlog		*log,
+	struct hlist_head	rhash[],
+	struct xlog_rec_header	*rhead,
+	struct xlog_op_header	*ohead,
+	xfs_caddr_t		dp,
+	xfs_caddr_t		end,
+	int			pass)
+{
+	struct xlog_recover	*trans;
+	unsigned int		len;
+
+	/* Do we understand who wrote this op? */
+	if (ohead->oh_clientid != XFS_TRANSACTION &&
+	    ohead->oh_clientid != XFS_LOG) {
+		xfs_warn(log->l_mp, "%s: bad clientid 0x%x",
+			__func__, ohead->oh_clientid);
+		ASSERT(0);
+		return -EIO;
+	}
+
+	/*
+	 * Check the ophdr contains all the data it is supposed to contain.
+	 */
+	len = be32_to_cpu(ohead->oh_len);
+	if (dp + len > end) {
+		xfs_warn(log->l_mp, "%s: bad length 0x%x", __func__, len);
+		WARN_ON(1);
+		return -EIO;
+	}
+
+	trans = xlog_recover_ophdr_to_trans(rhash, rhead, ohead);
+	if (!trans) {
+		/* nothing to do, so skip over this ophdr */
+		return 0;
+	}
+
+	return xlog_recovery_process_trans(log, trans, dp, len,
+					   ohead->oh_flags, pass);
+}
+
+/*
  * There are two valid states of the r_state field.  0 indicates that the
  * transaction structure is in a normal state.  We have either seen the
  * start of the transaction or the last operation we added was not a partial
@@ -3560,86 +3666,30 @@ xlog_recover_process_data(
 	xfs_caddr_t		dp,
 	int			pass)
 {
-	xfs_caddr_t		lp;
+	struct xlog_op_header	*ohead;
+	xfs_caddr_t		end;
 	int			num_logops;
-	xlog_op_header_t	*ohead;
-	xlog_recover_t		*trans;
-	xlog_tid_t		tid;
 	int			error;
-	unsigned long		hash;
-	uint			flags;
 
-	lp = dp + be32_to_cpu(rhead->h_len);
+	end = dp + be32_to_cpu(rhead->h_len);
 	num_logops = be32_to_cpu(rhead->h_num_logops);
 
 	/* check the log format matches our own - else we can't recover */
 	if (xlog_header_check_recover(log->l_mp, rhead))
 		return -EIO;
 
-	while ((dp < lp) && num_logops) {
-		ASSERT(dp + sizeof(xlog_op_header_t) <= lp);
-		ohead = (xlog_op_header_t *)dp;
-		dp += sizeof(xlog_op_header_t);
-		if (ohead->oh_clientid != XFS_TRANSACTION &&
-		    ohead->oh_clientid != XFS_LOG) {
-			xfs_warn(log->l_mp, "%s: bad clientid 0x%x",
-					__func__, ohead->oh_clientid);
-			ASSERT(0);
-			return -EIO;
-		}
-		tid = be32_to_cpu(ohead->oh_tid);
-		hash = XLOG_RHASH(tid);
-		trans = xlog_recover_find_tid(&rhash[hash], tid);
-		if (trans == NULL) {		   /* not found; add new tid */
-			if (ohead->oh_flags & XLOG_START_TRANS)
-				xlog_recover_new_tid(&rhash[hash], tid,
-					be64_to_cpu(rhead->h_lsn));
-		} else {
-			if (dp + be32_to_cpu(ohead->oh_len) > lp) {
-				xfs_warn(log->l_mp, "%s: bad length 0x%x",
-					__func__, be32_to_cpu(ohead->oh_len));
-				WARN_ON(1);
-				return -EIO;
-			}
-			flags = ohead->oh_flags & ~XLOG_END_TRANS;
-			if (flags & XLOG_WAS_CONT_TRANS)
-				flags &= ~XLOG_CONTINUE_TRANS;
-			switch (flags) {
-			case XLOG_COMMIT_TRANS:
-				error = xlog_recover_commit_trans(log,
-								trans, pass);
-				break;
-			case XLOG_UNMOUNT_TRANS:
-				error = xlog_recover_unmount_trans(log);
-				break;
-			case XLOG_WAS_CONT_TRANS:
-				error = xlog_recover_add_to_cont_trans(log,
-						trans, dp,
-						be32_to_cpu(ohead->oh_len));
-				break;
-			case XLOG_START_TRANS:
-				xfs_warn(log->l_mp, "%s: bad transaction",
-					__func__);
-				ASSERT(0);
-				error = -EIO;
-				break;
-			case 0:
-			case XLOG_CONTINUE_TRANS:
-				error = xlog_recover_add_to_trans(log, trans,
-						dp, be32_to_cpu(ohead->oh_len));
-				break;
-			default:
-				xfs_warn(log->l_mp, "%s: bad flag 0x%x",
-					__func__, flags);
-				ASSERT(0);
-				error = -EIO;
-				break;
-			}
-			if (error) {
-				xlog_recover_free_trans(trans);
-				return error;
-			}
-		}
+	while ((dp < end) && num_logops) {
+
+		ohead = (struct xlog_op_header *)dp;
+		dp += sizeof(*ohead);
+		ASSERT(dp <= end);
+
+		/* errors will abort recovery */
+		error = xlog_recover_process_ophdr(log, rhash, rhead, ohead,
+						    dp, end, pass);
+		if (error)
+			return error;
+
 		dp += be32_to_cpu(ohead->oh_len);
 		num_logops--;
 	}
@@ -4132,41 +4182,13 @@ xlog_do_recovery_pass(
 	}
 
 	memset(rhash, 0, sizeof(rhash));
-	if (tail_blk <= head_blk) {
-		for (blk_no = tail_blk; blk_no < head_blk; ) {
-			error = xlog_bread(log, blk_no, hblks, hbp, &offset);
-			if (error)
-				goto bread_err2;
-
-			rhead = (xlog_rec_header_t *)offset;
-			error = xlog_valid_rec_header(log, rhead, blk_no);
-			if (error)
-				goto bread_err2;
-
-			/* blocks in data section */
-			bblks = (int)BTOBB(be32_to_cpu(rhead->h_len));
-			error = xlog_bread(log, blk_no + hblks, bblks, dbp,
-					   &offset);
-			if (error)
-				goto bread_err2;
-
-			error = xlog_unpack_data(rhead, offset, log);
-			if (error)
-				goto bread_err2;
-
-			error = xlog_recover_process_data(log,
-						rhash, rhead, offset, pass);
-			if (error)
-				goto bread_err2;
-			blk_no += bblks + hblks;
-		}
-	} else {
+	blk_no = tail_blk;
+	if (tail_blk > head_blk) {
 		/*
 		 * Perform recovery around the end of the physical log.
 		 * When the head is not on the same cycle number as the tail,
-		 * we can't do a sequential recovery as above.
+		 * we can't do a sequential recovery.
 		 */
-		blk_no = tail_blk;
 		while (blk_no < log->l_logBBsize) {
 			/*
 			 * Check for header wrapping around physical end-of-log
@@ -4280,34 +4302,35 @@ xlog_do_recovery_pass(
 
 		ASSERT(blk_no >= log->l_logBBsize);
 		blk_no -= log->l_logBBsize;
+	}
 
-		/* read first part of physical log */
-		while (blk_no < head_blk) {
-			error = xlog_bread(log, blk_no, hblks, hbp, &offset);
-			if (error)
-				goto bread_err2;
+	/* read first part of physical log */
+	while (blk_no < head_blk) {
+		error = xlog_bread(log, blk_no, hblks, hbp, &offset);
+		if (error)
+			goto bread_err2;
 
-			rhead = (xlog_rec_header_t *)offset;
-			error = xlog_valid_rec_header(log, rhead, blk_no);
-			if (error)
-				goto bread_err2;
+		rhead = (xlog_rec_header_t *)offset;
+		error = xlog_valid_rec_header(log, rhead, blk_no);
+		if (error)
+			goto bread_err2;
 
-			bblks = (int)BTOBB(be32_to_cpu(rhead->h_len));
-			error = xlog_bread(log, blk_no+hblks, bblks, dbp,
-					   &offset);
-			if (error)
-				goto bread_err2;
+		/* blocks in data section */
+		bblks = (int)BTOBB(be32_to_cpu(rhead->h_len));
+		error = xlog_bread(log, blk_no+hblks, bblks, dbp,
+				   &offset);
+		if (error)
+			goto bread_err2;
 
-			error = xlog_unpack_data(rhead, offset, log);
-			if (error)
-				goto bread_err2;
+		error = xlog_unpack_data(rhead, offset, log);
+		if (error)
+			goto bread_err2;
 
-			error = xlog_recover_process_data(log, rhash,
-							rhead, offset, pass);
-			if (error)
-				goto bread_err2;
-			blk_no += bblks + hblks;
-		}
+		error = xlog_recover_process_data(log, rhash,
+						rhead, offset, pass);
+		if (error)
+			goto bread_err2;
+		blk_no += bblks + hblks;
 	}
 
  bread_err2:
@@ -4427,16 +4450,12 @@ xlog_do_recover(
 	XFS_BUF_UNASYNC(bp);
 	bp->b_ops = &xfs_sb_buf_ops;
 
-	if (XFS_FORCED_SHUTDOWN(log->l_mp)) {
-		xfs_buf_relse(bp);
-		return -EIO;
-	}
-
-	xfs_buf_iorequest(bp);
-	error = xfs_buf_iowait(bp);
+	error = xfs_buf_submit_wait(bp);
 	if (error) {
-		xfs_buf_ioerror_alert(bp, __func__);
-		ASSERT(0);
+		if (!XFS_FORCED_SHUTDOWN(log->l_mp)) {
+			xfs_buf_ioerror_alert(bp, __func__);
+			ASSERT(0);
+		}
 		xfs_buf_relse(bp);
 		return error;
 	}
@@ -4509,6 +4528,18 @@ xlog_recover(
 			return -EINVAL;
 		}
 
+		/*
+		 * Delay log recovery if the debug hook is set. This is debug
+		 * instrumention to coordinate simulation of I/O failures with
+		 * log recovery.
+		 */
+		if (xfs_globals.log_recovery_delay) {
+			xfs_notice(log->l_mp,
+				"Delaying log recovery for %d seconds.",
+				xfs_globals.log_recovery_delay);
+			msleep(xfs_globals.log_recovery_delay * 1000);
+		}
+
 		xfs_notice(log->l_mp, "Starting recovery (logdev: %s)",
 				log->l_mp->m_logname ? log->l_mp->m_logname
 						     : "internal");
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index fbf0384a466f..51435dbce9c4 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -61,8 +61,6 @@ static DEFINE_MUTEX(xfs_uuid_table_mutex);
 static int xfs_uuid_table_size;
 static uuid_t *xfs_uuid_table;
 
-extern struct kset *xfs_kset;
-
 /*
  * See if the UUID is unique among mounted XFS filesystems.
  * Mount fails if UUID is nil or a FS with the same UUID is already mounted.
@@ -302,21 +300,15 @@ xfs_readsb(
 	 * access to the superblock.
 	 */
 reread:
-	bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
-				   BTOBB(sector_size), 0, buf_ops);
-	if (!bp) {
-		if (loud)
-			xfs_warn(mp, "SB buffer read failed");
-		return -EIO;
-	}
-	if (bp->b_error) {
-		error = bp->b_error;
+	error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
+				   BTOBB(sector_size), 0, &bp, buf_ops);
+	if (error) {
 		if (loud)
 			xfs_warn(mp, "SB validate failed with error %d.", error);
 		/* bad CRC means corrupted metadata */
 		if (error == -EFSBADCRC)
 			error = -EFSCORRUPTED;
-		goto release_buf;
+		return error;
 	}
 
 	/*
@@ -546,40 +538,43 @@ xfs_set_inoalignment(xfs_mount_t *mp)
  * Check that the data (and log if separate) is an ok size.
  */
 STATIC int
-xfs_check_sizes(xfs_mount_t *mp)
+xfs_check_sizes(
+	struct xfs_mount *mp)
 {
-	xfs_buf_t	*bp;
+	struct xfs_buf	*bp;
 	xfs_daddr_t	d;
+	int		error;
 
 	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
 	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) {
 		xfs_warn(mp, "filesystem size mismatch detected");
 		return -EFBIG;
 	}
-	bp = xfs_buf_read_uncached(mp->m_ddev_targp,
+	error = xfs_buf_read_uncached(mp->m_ddev_targp,
 					d - XFS_FSS_TO_BB(mp, 1),
-					XFS_FSS_TO_BB(mp, 1), 0, NULL);
-	if (!bp) {
+					XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
+	if (error) {
 		xfs_warn(mp, "last sector read failed");
-		return -EIO;
+		return error;
 	}
 	xfs_buf_relse(bp);
 
-	if (mp->m_logdev_targp != mp->m_ddev_targp) {
-		d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
-		if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
-			xfs_warn(mp, "log size mismatch detected");
-			return -EFBIG;
-		}
-		bp = xfs_buf_read_uncached(mp->m_logdev_targp,
+	if (mp->m_logdev_targp == mp->m_ddev_targp)
+		return 0;
+
+	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
+	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
+		xfs_warn(mp, "log size mismatch detected");
+		return -EFBIG;
+	}
+	error = xfs_buf_read_uncached(mp->m_logdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_BB(mp, 1), 0, NULL);
-		if (!bp) {
-			xfs_warn(mp, "log device read failed");
-			return -EIO;
-		}
-		xfs_buf_relse(bp);
+					XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
+	if (error) {
+		xfs_warn(mp, "log device read failed");
+		return error;
 	}
+	xfs_buf_relse(bp);
 	return 0;
 }
 
@@ -729,7 +724,6 @@ xfs_mountfs(
 
 	xfs_set_maxicount(mp);
 
-	mp->m_kobj.kobject.kset = xfs_kset;
 	error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, NULL, mp->m_fsname);
 	if (error)
 		goto out;
diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index 1eb6f3df698c..30ecca3037e3 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -304,7 +304,8 @@ _xfs_mru_cache_reap(
 int
 xfs_mru_cache_init(void)
 {
-	xfs_mru_reap_wq = alloc_workqueue("xfs_mru_cache", WQ_MEM_RECLAIM, 1);
+	xfs_mru_reap_wq = alloc_workqueue("xfs_mru_cache",
+				WQ_MEM_RECLAIM|WQ_FREEZABLE, 1);
 	if (!xfs_mru_reap_wq)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 10232102b4a6..d68f23021af3 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -434,6 +434,7 @@ xfs_qm_dquot_isolate(
 	struct list_head	*item,
 	spinlock_t		*lru_lock,
 	void			*arg)
+		__releases(lru_lock) __acquires(lru_lock)
 {
 	struct xfs_dquot	*dqp = container_of(item,
 						struct xfs_dquot, q_lru);
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 909e143b87ae..e1175ea9b551 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -46,7 +46,7 @@
  * Keeps track of a current summary block, so we don't keep reading
  * it from the buffer cache.
  */
-STATIC int				/* error */
+static int
 xfs_rtget_summary(
 	xfs_mount_t	*mp,		/* file system mount structure */
 	xfs_trans_t	*tp,		/* transaction pointer */
@@ -56,60 +56,9 @@ xfs_rtget_summary(
 	xfs_fsblock_t	*rsb,		/* in/out: summary block number */
 	xfs_suminfo_t	*sum)		/* out: summary info for this block */
 {
-	xfs_buf_t	*bp;		/* buffer for summary block */
-	int		error;		/* error value */
-	xfs_fsblock_t	sb;		/* summary fsblock */
-	int		so;		/* index into the summary file */
-	xfs_suminfo_t	*sp;		/* pointer to returned data */
-
-	/*
-	 * Compute entry number in the summary file.
-	 */
-	so = XFS_SUMOFFS(mp, log, bbno);
-	/*
-	 * Compute the block number in the summary file.
-	 */
-	sb = XFS_SUMOFFSTOBLOCK(mp, so);
-	/*
-	 * If we have an old buffer, and the block number matches, use that.
-	 */
-	if (rbpp && *rbpp && *rsb == sb)
-		bp = *rbpp;
-	/*
-	 * Otherwise we have to get the buffer.
-	 */
-	else {
-		/*
-		 * If there was an old one, get rid of it first.
-		 */
-		if (rbpp && *rbpp)
-			xfs_trans_brelse(tp, *rbpp);
-		error = xfs_rtbuf_get(mp, tp, sb, 1, &bp);
-		if (error) {
-			return error;
-		}
-		/*
-		 * Remember this buffer and block for the next call.
-		 */
-		if (rbpp) {
-			*rbpp = bp;
-			*rsb = sb;
-		}
-	}
-	/*
-	 * Point to the summary information & copy it out.
-	 */
-	sp = XFS_SUMPTR(mp, bp, so);
-	*sum = *sp;
-	/*
-	 * Drop the buffer if we're not asked to remember it.
-	 */
-	if (!rbpp)
-		xfs_trans_brelse(tp, bp);
-	return 0;
+	return xfs_rtmodify_summary_int(mp, tp, log, bbno, 0, rbpp, rsb, sum);
 }
 
-
 /*
  * Return whether there are any free extents in the size range given
  * by low and high, for the bitmap block bbno.
@@ -972,16 +921,11 @@ xfs_growfs_rt(
 	/*
 	 * Read in the last block of the device, make sure it exists.
 	 */
-	bp = xfs_buf_read_uncached(mp->m_rtdev_targp,
+	error = xfs_buf_read_uncached(mp->m_rtdev_targp,
 				XFS_FSB_TO_BB(mp, nrblocks - 1),
-				XFS_FSB_TO_BB(mp, 1), 0, NULL);
-	if (!bp)
-		return -EIO;
-	if (bp->b_error) {
-		error = bp->b_error;
-		xfs_buf_relse(bp);
+				XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
+	if (error)
 		return error;
-	}
 	xfs_buf_relse(bp);
 
 	/*
@@ -1235,11 +1179,12 @@ xfs_rtallocate_extent(
  */
 int				/* error */
 xfs_rtmount_init(
-	xfs_mount_t	*mp)	/* file system mount structure */
+	struct xfs_mount	*mp)	/* file system mount structure */
 {
-	xfs_buf_t	*bp;	/* buffer for last block of subvolume */
-	xfs_daddr_t	d;	/* address of last block of subvolume */
-	xfs_sb_t	*sbp;	/* filesystem superblock copy in mount */
+	struct xfs_buf		*bp;	/* buffer for last block of subvolume */
+	struct xfs_sb		*sbp;	/* filesystem superblock copy in mount */
+	xfs_daddr_t		d;	/* address of last block of subvolume */
+	int			error;
 
 	sbp = &mp->m_sb;
 	if (sbp->sb_rblocks == 0)
@@ -1265,14 +1210,12 @@ xfs_rtmount_init(
 			(unsigned long long) mp->m_sb.sb_rblocks);
 		return -EFBIG;
 	}
-	bp = xfs_buf_read_uncached(mp->m_rtdev_targp,
+	error = xfs_buf_read_uncached(mp->m_rtdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_BB(mp, 1), 0, NULL);
-	if (!bp || bp->b_error) {
+					XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
+	if (error) {
 		xfs_warn(mp, "realtime device size check failed");
-		if (bp)
-			xfs_buf_relse(bp);
-		return -EIO;
+		return error;
 	}
 	xfs_buf_relse(bp);
 	return 0;
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index c642795324af..76c0a4a9bb17 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -111,6 +111,10 @@ int xfs_rtfind_forw(struct xfs_mount *mp, struct xfs_trans *tp,
 		    xfs_rtblock_t *rtblock);
 int xfs_rtmodify_range(struct xfs_mount *mp, struct xfs_trans *tp,
 		       xfs_rtblock_t start, xfs_extlen_t len, int val);
+int xfs_rtmodify_summary_int(struct xfs_mount *mp, struct xfs_trans *tp,
+			     int log, xfs_rtblock_t bbno, int delta,
+			     xfs_buf_t **rbpp, xfs_fsblock_t *rsb,
+			     xfs_suminfo_t *sum);
 int xfs_rtmodify_summary(struct xfs_mount *mp, struct xfs_trans *tp, int log,
 			 xfs_rtblock_t bbno, int delta, xfs_buf_t **rbpp,
 			 xfs_fsblock_t *rsb);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index b194652033cd..9f622feda6a4 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -47,6 +47,7 @@
 #include "xfs_dinode.h"
 #include "xfs_filestream.h"
 #include "xfs_quota.h"
+#include "xfs_sysfs.h"
 
 #include <linux/namei.h>
 #include <linux/init.h>
@@ -61,7 +62,11 @@
 static const struct super_operations xfs_super_operations;
 static kmem_zone_t *xfs_ioend_zone;
 mempool_t *xfs_ioend_pool;
-struct kset *xfs_kset;
+
+static struct kset *xfs_kset;		/* top-level xfs sysfs dir */
+#ifdef DEBUG
+static struct xfs_kobj xfs_dbg_kobj;	/* global debug sysfs attrs */
+#endif
 
 #define MNTOPT_LOGBUFS	"logbufs"	/* number of XFS log buffers */
 #define MNTOPT_LOGBSIZE	"logbsize"	/* size of XFS log buffers */
@@ -838,32 +843,32 @@ xfs_init_mount_workqueues(
 	struct xfs_mount	*mp)
 {
 	mp->m_data_workqueue = alloc_workqueue("xfs-data/%s",
-			WQ_MEM_RECLAIM, 0, mp->m_fsname);
+			WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
 	if (!mp->m_data_workqueue)
 		goto out;
 
 	mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s",
-			WQ_MEM_RECLAIM, 0, mp->m_fsname);
+			WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
 	if (!mp->m_unwritten_workqueue)
 		goto out_destroy_data_iodone_queue;
 
 	mp->m_cil_workqueue = alloc_workqueue("xfs-cil/%s",
-			WQ_MEM_RECLAIM, 0, mp->m_fsname);
+			WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
 	if (!mp->m_cil_workqueue)
 		goto out_destroy_unwritten;
 
 	mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s",
-			0, 0, mp->m_fsname);
+			WQ_FREEZABLE, 0, mp->m_fsname);
 	if (!mp->m_reclaim_workqueue)
 		goto out_destroy_cil;
 
 	mp->m_log_workqueue = alloc_workqueue("xfs-log/%s",
-			0, 0, mp->m_fsname);
+			WQ_FREEZABLE, 0, mp->m_fsname);
 	if (!mp->m_log_workqueue)
 		goto out_destroy_reclaim;
 
 	mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s",
-			0, 0, mp->m_fsname);
+			WQ_FREEZABLE, 0, mp->m_fsname);
 	if (!mp->m_eofblocks_workqueue)
 		goto out_destroy_log;
 
@@ -1406,6 +1411,7 @@ xfs_fs_fill_super(
 	atomic_set(&mp->m_active_trans, 0);
 	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
 	INIT_DELAYED_WORK(&mp->m_eofblocks_work, xfs_eofblocks_worker);
+	mp->m_kobj.kobject.kset = xfs_kset;
 
 	mp->m_super = sb;
 	sb->s_fs_info = mp;
@@ -1715,7 +1721,8 @@ xfs_init_workqueues(void)
 	 * AGs in all the filesystems mounted. Hence use the default large
 	 * max_active value for this workqueue.
 	 */
-	xfs_alloc_wq = alloc_workqueue("xfsalloc", WQ_MEM_RECLAIM, 0);
+	xfs_alloc_wq = alloc_workqueue("xfsalloc",
+			WQ_MEM_RECLAIM|WQ_FREEZABLE, 0);
 	if (!xfs_alloc_wq)
 		return -ENOMEM;
 
@@ -1768,9 +1775,16 @@ init_xfs_fs(void)
 		goto out_sysctl_unregister;;
 	}
 
-	error = xfs_qm_init();
+#ifdef DEBUG
+	xfs_dbg_kobj.kobject.kset = xfs_kset;
+	error = xfs_sysfs_init(&xfs_dbg_kobj, &xfs_dbg_ktype, NULL, "debug");
 	if (error)
 		goto out_kset_unregister;
+#endif
+
+	error = xfs_qm_init();
+	if (error)
+		goto out_remove_kobj;
 
 	error = register_filesystem(&xfs_fs_type);
 	if (error)
@@ -1779,7 +1793,11 @@ init_xfs_fs(void)
 
  out_qm_exit:
 	xfs_qm_exit();
+ out_remove_kobj:
+#ifdef DEBUG
+	xfs_sysfs_del(&xfs_dbg_kobj);
  out_kset_unregister:
+#endif
 	kset_unregister(xfs_kset);
  out_sysctl_unregister:
 	xfs_sysctl_unregister();
@@ -1802,6 +1820,9 @@ exit_xfs_fs(void)
 {
 	xfs_qm_exit();
 	unregister_filesystem(&xfs_fs_type);
+#ifdef DEBUG
+	xfs_sysfs_del(&xfs_dbg_kobj);
+#endif
 	kset_unregister(xfs_kset);
 	xfs_sysctl_unregister();
 	xfs_cleanup_procfs();
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 6a944a2cd36f..02ae62a998e0 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -269,9 +269,11 @@ xfs_symlink(
 	/*
 	 * Check for ability to enter directory entry, if no space reserved.
 	 */
-	error = xfs_dir_canenter(tp, dp, link_name, resblks);
-	if (error)
-		goto error_return;
+	if (!resblks) {
+		error = xfs_dir_canenter(tp, dp, link_name);
+		if (error)
+			goto error_return;
+	}
 	/*
 	 * Initialize the bmap freelist prior to calling either
 	 * bmapi or the directory create code.
diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h
index bd8e157c20ef..ffef45375754 100644
--- a/fs/xfs/xfs_sysctl.h
+++ b/fs/xfs/xfs_sysctl.h
@@ -92,6 +92,11 @@ enum {
 
 extern xfs_param_t	xfs_params;
 
+struct xfs_globals {
+	int	log_recovery_delay;	/* log recovery delay (secs) */
+};
+extern struct xfs_globals	xfs_globals;
+
 #ifdef CONFIG_SYSCTL
 extern int xfs_sysctl_register(void);
 extern void xfs_sysctl_unregister(void);
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 9835139ce1ec..aa03670851d8 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -51,6 +51,80 @@ struct kobj_type xfs_mp_ktype = {
 	.release = xfs_sysfs_release,
 };
 
+#ifdef DEBUG
+/* debug */
+
+STATIC ssize_t
+log_recovery_delay_store(
+	const char	*buf,
+	size_t		count,
+	void		*data)
+{
+	int		ret;
+	int		val;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val < 0 || val > 60)
+		return -EINVAL;
+
+	xfs_globals.log_recovery_delay = val;
+
+	return count;
+}
+
+STATIC ssize_t
+log_recovery_delay_show(
+	char	*buf,
+	void	*data)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.log_recovery_delay);
+}
+XFS_SYSFS_ATTR_RW(log_recovery_delay);
+
+static struct attribute *xfs_dbg_attrs[] = {
+	ATTR_LIST(log_recovery_delay),
+	NULL,
+};
+
+STATIC ssize_t
+xfs_dbg_show(
+	struct kobject		*kobject,
+	struct attribute	*attr,
+	char			*buf)
+{
+	struct xfs_sysfs_attr *xfs_attr = to_attr(attr);
+
+	return xfs_attr->show ? xfs_attr->show(buf, NULL) : 0;
+}
+
+STATIC ssize_t
+xfs_dbg_store(
+	struct kobject		*kobject,
+	struct attribute	*attr,
+	const char		*buf,
+	size_t			count)
+{
+	struct xfs_sysfs_attr *xfs_attr = to_attr(attr);
+
+	return xfs_attr->store ? xfs_attr->store(buf, count, NULL) : 0;
+}
+
+static struct sysfs_ops xfs_dbg_ops = {
+	.show = xfs_dbg_show,
+	.store = xfs_dbg_store,
+};
+
+struct kobj_type xfs_dbg_ktype = {
+	.release = xfs_sysfs_release,
+	.sysfs_ops = &xfs_dbg_ops,
+	.default_attrs = xfs_dbg_attrs,
+};
+
+#endif /* DEBUG */
+
 /* xlog */
 
 STATIC ssize_t
diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h
index 54a2091183c0..240eee35f342 100644
--- a/fs/xfs/xfs_sysfs.h
+++ b/fs/xfs/xfs_sysfs.h
@@ -20,6 +20,7 @@
 #define __XFS_SYSFS_H__
 
 extern struct kobj_type xfs_mp_ktype;	/* xfs_mount */
+extern struct kobj_type xfs_dbg_ktype;	/* debug */
 extern struct kobj_type xfs_log_ktype;	/* xlog */
 
 static inline struct xfs_kobj *
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 152f82782630..51372e34d988 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -349,7 +349,8 @@ DEFINE_BUF_EVENT(xfs_buf_free);
 DEFINE_BUF_EVENT(xfs_buf_hold);
 DEFINE_BUF_EVENT(xfs_buf_rele);
 DEFINE_BUF_EVENT(xfs_buf_iodone);
-DEFINE_BUF_EVENT(xfs_buf_iorequest);
+DEFINE_BUF_EVENT(xfs_buf_submit);
+DEFINE_BUF_EVENT(xfs_buf_submit_wait);
 DEFINE_BUF_EVENT(xfs_buf_bawrite);
 DEFINE_BUF_EVENT(xfs_buf_lock);
 DEFINE_BUF_EVENT(xfs_buf_lock_done);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 96c898e7ac9a..e2b2216b1635 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -318,20 +318,10 @@ xfs_trans_read_buf_map(
 			XFS_BUF_READ(bp);
 			bp->b_ops = ops;
 
-			/*
-			 * XXX(hch): clean up the error handling here to be less
-			 * of a mess..
-			 */
-			if (XFS_FORCED_SHUTDOWN(mp)) {
-				trace_xfs_bdstrat_shut(bp, _RET_IP_);
-				xfs_bioerror_relse(bp);
-			} else {
-				xfs_buf_iorequest(bp);
-			}
-
-			error = xfs_buf_iowait(bp);
+			error = xfs_buf_submit_wait(bp);
 			if (error) {
-				xfs_buf_ioerror_alert(bp, __func__);
+				if (!XFS_FORCED_SHUTDOWN(mp))
+					xfs_buf_ioerror_alert(bp, __func__);
 				xfs_buf_relse(bp);
 				/*
 				 * We can gracefully recover from most read
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index 50c3f5614288..cdb4d86520e1 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -70,7 +70,7 @@ xfs_trans_ichgtime(
 	int			flags)
 {
 	struct inode		*inode = VFS_I(ip);
-	timespec_t		tv;
+	struct timespec		tv;
 
 	ASSERT(tp);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h
index c728113374f5..f97804bdf1ff 100644
--- a/include/acpi/acnames.h
+++ b/include/acpi/acnames.h
@@ -59,6 +59,10 @@
 #define METHOD_NAME__PRS        "_PRS"
 #define METHOD_NAME__PRT        "_PRT"
 #define METHOD_NAME__PRW        "_PRW"
+#define METHOD_NAME__PS0        "_PS0"
+#define METHOD_NAME__PS1        "_PS1"
+#define METHOD_NAME__PS2        "_PS2"
+#define METHOD_NAME__PS3        "_PS3"
 #define METHOD_NAME__REG        "_REG"
 #define METHOD_NAME__SB_        "_SB_"
 #define METHOD_NAME__SEG        "_SEG"
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index b7c89d47efbe..9fc1d71c82bc 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -46,7 +46,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20140724
+#define ACPI_CA_VERSION                 0x20140828
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
@@ -692,6 +692,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 						     *event_status))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void))
 
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_get_gpe_device(u32 gpe_index,
diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h
index 7626bfeac2cb..29e79370641d 100644
--- a/include/acpi/actbl1.h
+++ b/include/acpi/actbl1.h
@@ -952,7 +952,8 @@ enum acpi_srat_type {
 	ACPI_SRAT_TYPE_CPU_AFFINITY = 0,
 	ACPI_SRAT_TYPE_MEMORY_AFFINITY = 1,
 	ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY = 2,
-	ACPI_SRAT_TYPE_RESERVED = 3	/* 3 and greater are reserved */
+	ACPI_SRAT_TYPE_GICC_AFFINITY = 3,
+	ACPI_SRAT_TYPE_RESERVED = 4	/* 4 and greater are reserved */
 };
 
 /*
@@ -968,7 +969,7 @@ struct acpi_srat_cpu_affinity {
 	u32 flags;
 	u8 local_sapic_eid;
 	u8 proximity_domain_hi[3];
-	u32 reserved;		/* Reserved, must be zero */
+	u32 clock_domain;
 };
 
 /* Flags */
@@ -1010,6 +1011,20 @@ struct acpi_srat_x2apic_cpu_affinity {
 
 #define ACPI_SRAT_CPU_ENABLED       (1)	/* 00: Use affinity structure */
 
+/* 3: GICC Affinity (ACPI 5.1) */
+
+struct acpi_srat_gicc_affinity {
+	struct acpi_subtable_header header;
+	u32 proximity_domain;
+	u32 acpi_processor_uid;
+	u32 flags;
+	u32 clock_domain;
+};
+
+/* Flags for struct acpi_srat_gicc_affinity */
+
+#define ACPI_SRAT_GICC_ENABLED     (1)	/* 00: Use affinity structure */
+
 /* Reset to default packing */
 
 #pragma pack()
diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h
index 787bcc814463..5480cb2236bf 100644
--- a/include/acpi/actbl3.h
+++ b/include/acpi/actbl3.h
@@ -310,10 +310,15 @@ struct acpi_gtdt_timer_entry {
 	u32 common_flags;
 };
 
+/* Flag Definitions: timer_flags and virtual_timer_flags above */
+
+#define ACPI_GTDT_GT_IRQ_MODE               (1)
+#define ACPI_GTDT_GT_IRQ_POLARITY           (1<<1)
+
 /* Flag Definitions: common_flags above */
 
-#define ACPI_GTDT_GT_IS_SECURE_TIMER    (1)
-#define ACPI_GTDT_GT_ALWAYS_ON          (1<<1)
+#define ACPI_GTDT_GT_IS_SECURE_TIMER        (1)
+#define ACPI_GTDT_GT_ALWAYS_ON              (1<<1)
 
 /* 1: SBSA Generic Watchdog Structure */
 
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 9c79e7603459..1973ad2b13f4 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -18,14 +18,100 @@
 #include <asm/cmpxchg.h>
 #include <asm/barrier.h>
 
+/*
+ * atomic_$op() - $op integer to atomic variable
+ * @i: integer value to $op
+ * @v: pointer to the atomic variable
+ *
+ * Atomically $ops @i to @v. Does not strictly guarantee a memory-barrier, use
+ * smp_mb__{before,after}_atomic().
+ */
+
+/*
+ * atomic_$op_return() - $op interer to atomic variable and returns the result
+ * @i: integer value to $op
+ * @v: pointer to the atomic variable
+ *
+ * Atomically $ops @i to @v. Does imply a full memory barrier.
+ */
+
 #ifdef CONFIG_SMP
-/* Force people to define core atomics */
-# if !defined(atomic_add_return) || !defined(atomic_sub_return) || \
-     !defined(atomic_clear_mask) || !defined(atomic_set_mask)
-#  error "SMP requires a little arch-specific magic"
-# endif
+
+/* we can build all atomic primitives from cmpxchg */
+
+#define ATOMIC_OP(op, c_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = cmpxchg(&v->counter, c, c c_op i)) != c)		\
+		c = old;						\
+}
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	int c, old;							\
+									\
+	c = v->counter;							\
+	while ((old = cmpxchg(&v->counter, c, c c_op i)) != c)		\
+		c = old;						\
+									\
+	return c c_op i;						\
+}
+
+#else
+
+#include <linux/irqflags.h>
+
+#define ATOMIC_OP(op, c_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	raw_local_irq_save(flags);					\
+	v->counter = v->counter c_op i;					\
+	raw_local_irq_restore(flags);					\
+}
+
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int ret;							\
+									\
+	raw_local_irq_save(flags);					\
+	ret = (v->counter = v->counter c_op i);				\
+	raw_local_irq_restore(flags);					\
+									\
+	return ret;							\
+}
+
+#endif /* CONFIG_SMP */
+
+#ifndef atomic_add_return
+ATOMIC_OP_RETURN(add, +)
+#endif
+
+#ifndef atomic_sub_return
+ATOMIC_OP_RETURN(sub, -)
+#endif
+
+#ifndef atomic_clear_mask
+ATOMIC_OP(and, &)
+#define atomic_clear_mask(i, v) atomic_and(~(i), (v))
 #endif
 
+#ifndef atomic_set_mask
+#define CONFIG_ARCH_HAS_ATOMIC_OR
+ATOMIC_OP(or, |)
+#define atomic_set_mask(i, v)	atomic_or((i), (v))
+#endif
+
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
 /*
  * Atomic operations that C can't guarantee us.  Useful for
  * resource counting etc..
@@ -33,8 +119,6 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#ifdef __KERNEL__
-
 /**
  * atomic_read - read atomic variable
  * @v: pointer of type atomic_t
@@ -42,7 +126,7 @@
  * Atomically reads the value of @v.
  */
 #ifndef atomic_read
-#define atomic_read(v)	(*(volatile int *)&(v)->counter)
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
 #endif
 
 /**
@@ -56,52 +140,6 @@
 
 #include <linux/irqflags.h>
 
-/**
- * atomic_add_return - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and returns the result
- */
-#ifndef atomic_add_return
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	int temp;
-
-	raw_local_irq_save(flags); /* Don't trace it in an irqsoff handler */
-	temp = v->counter;
-	temp += i;
-	v->counter = temp;
-	raw_local_irq_restore(flags);
-
-	return temp;
-}
-#endif
-
-/**
- * atomic_sub_return - subtract integer from atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns the result
- */
-#ifndef atomic_sub_return
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	int temp;
-
-	raw_local_irq_save(flags); /* Don't trace it in an irqsoff handler */
-	temp = v->counter;
-	temp -= i;
-	v->counter = temp;
-	raw_local_irq_restore(flags);
-
-	return temp;
-}
-#endif
-
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
 	return atomic_add_return(i, v) < 0;
@@ -139,49 +177,11 @@ static inline void atomic_dec(atomic_t *v)
 
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
-  int c, old;
-  c = atomic_read(v);
-  while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
-    c = old;
-  return c;
-}
-
-/**
- * atomic_clear_mask - Atomically clear bits in atomic variable
- * @mask: Mask of the bits to be cleared
- * @v: pointer of type atomic_t
- *
- * Atomically clears the bits set in @mask from @v
- */
-#ifndef atomic_clear_mask
-static inline void atomic_clear_mask(unsigned long mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	mask = ~mask;
-	raw_local_irq_save(flags); /* Don't trace it in a irqsoff handler */
-	v->counter &= mask;
-	raw_local_irq_restore(flags);
+	int c, old;
+	c = atomic_read(v);
+	while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
+		c = old;
+	return c;
 }
-#endif
-
-/**
- * atomic_set_mask - Atomically set bits in atomic variable
- * @mask: Mask of the bits to be set
- * @v: pointer of type atomic_t
- *
- * Atomically sets the bits set in @mask in @v
- */
-#ifndef atomic_set_mask
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	unsigned long flags;
-
-	raw_local_irq_save(flags); /* Don't trace it in a irqsoff handler */
-	v->counter |= mask;
-	raw_local_irq_restore(flags);
-}
-#endif
 
-#endif /* __KERNEL__ */
 #endif /* __ASM_GENERIC_ATOMIC_H */
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index b18ce4f9ee3d..30ad9c86cebb 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -20,10 +20,22 @@ typedef struct {
 
 extern long long atomic64_read(const atomic64_t *v);
 extern void	 atomic64_set(atomic64_t *v, long long i);
-extern void	 atomic64_add(long long a, atomic64_t *v);
-extern long long atomic64_add_return(long long a, atomic64_t *v);
-extern void	 atomic64_sub(long long a, atomic64_t *v);
-extern long long atomic64_sub_return(long long a, atomic64_t *v);
+
+#define ATOMIC64_OP(op)							\
+extern void	 atomic64_##op(long long a, atomic64_t *v);
+
+#define ATOMIC64_OP_RETURN(op)						\
+extern long long atomic64_##op##_return(long long a, atomic64_t *v);
+
+#define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op)
+
+ATOMIC64_OPS(add)
+ATOMIC64_OPS(sub)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+
 extern long long atomic64_dec_if_positive(atomic64_t *v);
 extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
 extern long long atomic64_xchg(atomic64_t *v, long long new);
diff --git a/include/asm-generic/clkdev.h b/include/asm-generic/clkdev.h
index 90a32a61dd21..4ff334749ed5 100644
--- a/include/asm-generic/clkdev.h
+++ b/include/asm-generic/clkdev.h
@@ -15,10 +15,12 @@
 
 #include <linux/slab.h>
 
+#ifndef CONFIG_COMMON_CLK
 struct clk;
 
 static inline int __clk_get(struct clk *clk) { return 1; }
 static inline void __clk_put(struct clk *clk) { }
+#endif
 
 static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size)
 {
diff --git a/include/asm-generic/cputime_jiffies.h b/include/asm-generic/cputime_jiffies.h
index d5cb78f53986..fe386fc6e85e 100644
--- a/include/asm-generic/cputime_jiffies.h
+++ b/include/asm-generic/cputime_jiffies.h
@@ -3,6 +3,8 @@
 
 typedef unsigned long __nocast cputime_t;
 
+#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
+
 #define cputime_one_jiffy		jiffies_to_cputime(1)
 #define cputime_to_jiffies(__ct)	(__force unsigned long)(__ct)
 #define cputime_to_scaled(__ct)		(__ct)
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
index 4e817606c549..0419485891f2 100644
--- a/include/asm-generic/cputime_nsecs.h
+++ b/include/asm-generic/cputime_nsecs.h
@@ -21,6 +21,8 @@
 typedef u64 __nocast cputime_t;
 typedef u64 __nocast cputime64_t;
 
+#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
+
 #define cputime_one_jiffy		jiffies_to_cputime(1)
 
 #define cputime_div(__ct, divisor)  div_u64((__force u64)__ct, divisor)
diff --git a/arch/x86/include/asm/dma-contiguous.h b/include/asm-generic/dma-contiguous.h
index b4b38bacb404..292c571750f0 100644
--- a/arch/x86/include/asm/dma-contiguous.h
+++ b/include/asm-generic/dma-contiguous.h
@@ -1,7 +1,5 @@
-#ifndef ASMX86_DMA_CONTIGUOUS_H
-#define ASMX86_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
+#ifndef _ASM_GENERIC_DMA_CONTIGUOUS_H
+#define _ASM_GENERIC_DMA_CONTIGUOUS_H
 
 #include <linux/types.h>
 
@@ -9,4 +7,3 @@ static inline void
 dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
 
 #endif
-#endif
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index de8bf89940f8..3378dcf4c31e 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -179,6 +179,15 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
 
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller);
+
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller);
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags);
+
 /**
  * dma_mmap_attrs - map a coherent DMA allocation into user space
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
@@ -205,14 +214,6 @@ dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr,
 
 #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, NULL)
 
-static inline int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
-		      void *cpu_addr, dma_addr_t dma_addr, size_t size)
-{
-	DEFINE_DMA_ATTRS(attrs);
-	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
-	return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs);
-}
-
 int
 dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
 		       void *cpu_addr, dma_addr_t dma_addr, size_t size);
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index c1d4105e1c1d..383ade1a211b 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -27,7 +27,7 @@
  */
 
 #ifndef ARCH_NR_GPIOS
-#define ARCH_NR_GPIOS		256
+#define ARCH_NR_GPIOS		512
 #endif
 
 /*
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 975e1cc75edb..b8fdc57a7335 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -331,7 +331,7 @@ static inline void iounmap(void __iomem *addr)
 #ifndef CONFIG_GENERIC_IOMAP
 static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
-	return (void __iomem *) port;
+	return PCI_IOBASE + (port & IO_SPACE_LIMIT);
 }
 
 static inline void ioport_unmap(void __iomem *p)
diff --git a/include/asm-generic/irq_work.h b/include/asm-generic/irq_work.h
new file mode 100644
index 000000000000..a44f452c6590
--- /dev/null
+++ b/include/asm-generic/irq_work.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_IRQ_WORK_H
+#define __ASM_IRQ_WORK_H
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+	return false;
+}
+
+#endif /* __ASM_IRQ_WORK_H */
+
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 53b2acc38213..752e30d63904 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -249,6 +249,24 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #define pgprot_writecombine pgprot_noncached
 #endif
 
+#ifndef pgprot_device
+#define pgprot_device pgprot_noncached
+#endif
+
+#ifndef pgprot_modify
+#define pgprot_modify pgprot_modify
+static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
+{
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot)))
+		newprot = pgprot_noncached(newprot);
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot)))
+		newprot = pgprot_writecombine(newprot);
+	if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot)))
+		newprot = pgprot_device(newprot);
+	return newprot;
+}
+#endif
+
 /*
  * When walking page tables, get the address of the next boundary,
  * or the end address of the range if that comes earlier.  Although no
@@ -660,11 +678,12 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 }
 
 #ifdef CONFIG_NUMA_BALANCING
-#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
 /*
- * _PAGE_NUMA works identical to _PAGE_PROTNONE (it's actually the
- * same bit too). It's set only when _PAGE_PRESET is not set and it's
- * never set if _PAGE_PRESENT is set.
+ * _PAGE_NUMA distinguishes between an unmapped page table entry, an entry that
+ * is protected for PROT_NONE and a NUMA hinting fault entry. If the
+ * architecture defines __PAGE_PROTNONE then it should take that into account
+ * but those that do not can rely on the fact that the NUMA hinting scanner
+ * skips inaccessible VMAs.
  *
  * pte/pmd_present() returns true if pte/pmd_numa returns true. Page
  * fault triggers on those regions if pte/pmd_numa returns true
@@ -673,16 +692,14 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 #ifndef pte_numa
 static inline int pte_numa(pte_t pte)
 {
-	return (pte_flags(pte) &
-		(_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA;
+	return ptenuma_flags(pte) == _PAGE_NUMA;
 }
 #endif
 
 #ifndef pmd_numa
 static inline int pmd_numa(pmd_t pmd)
 {
-	return (pmd_flags(pmd) &
-		(_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA;
+	return pmdnuma_flags(pmd) == _PAGE_NUMA;
 }
 #endif
 
@@ -722,6 +739,8 @@ static inline pte_t pte_mknuma(pte_t pte)
 {
 	pteval_t val = pte_val(pte);
 
+	VM_BUG_ON(!(val & _PAGE_PRESENT));
+
 	val &= ~_PAGE_PRESENT;
 	val |= _PAGE_NUMA;
 
@@ -765,16 +784,6 @@ static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
 }
 #endif
 #else
-extern int pte_numa(pte_t pte);
-extern int pmd_numa(pmd_t pmd);
-extern pte_t pte_mknonnuma(pte_t pte);
-extern pmd_t pmd_mknonnuma(pmd_t pmd);
-extern pte_t pte_mknuma(pte_t pte);
-extern pmd_t pmd_mknuma(pmd_t pmd);
-extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
-extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp);
-#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
-#else
 static inline int pmd_numa(pmd_t pmd)
 {
 	return 0;
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index f1a24b5c3b90..b58fd667f87b 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -3,6 +3,8 @@
 
 /* References to section boundaries */
 
+#include <linux/compiler.h>
+
 /*
  * Usage guidelines:
  * _text, _data: architecture specific, don't use them in arch-independent code
@@ -37,6 +39,8 @@ extern char __start_rodata[], __end_rodata[];
 /* Start and end of .ctors section - used for constructor calls. */
 extern char __ctors_start[], __ctors_end[];
 
+extern __visible const void __nosave_begin, __nosave_end;
+
 /* function descriptor handling (if any).  Override
  * in asm/sections.h */
 #ifndef dereference_function_descriptor
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index a39195539601..74b13ec1ebd4 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -58,6 +58,11 @@ struct shash_desc {
 	void *__ctx[] CRYPTO_MINALIGN_ATTR;
 };
 
+#define SHASH_DESC_ON_STACK(shash, ctx)				  \
+	char __##shash##_desc[sizeof(struct shash_desc) +	  \
+		crypto_shash_descsize(ctx)] CRYPTO_MINALIGN_ATTR; \
+	struct shash_desc *shash = (struct shash_desc *)__##shash##_desc
+
 struct shash_alg {
 	int (*init)(struct shash_desc *desc);
 	int (*update)(struct shash_desc *desc, const u8 *data,
diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h
index 0d164c6af539..54add2069901 100644
--- a/include/crypto/public_key.h
+++ b/include/crypto/public_key.h
@@ -15,6 +15,7 @@
 #define _LINUX_PUBLIC_KEY_H
 
 #include <linux/mpi.h>
+#include <keys/asymmetric-type.h>
 #include <crypto/hash_info.h>
 
 enum pkey_algo {
@@ -98,8 +99,9 @@ struct key;
 extern int verify_signature(const struct key *key,
 			    const struct public_key_signature *sig);
 
+struct asymmetric_key_id;
 extern struct key *x509_request_asymmetric_key(struct key *keyring,
-					       const char *issuer,
-					       const char *key_id);
+					       const struct asymmetric_key_id *kid,
+					       bool partial);
 
 #endif /* _LINUX_PUBLIC_KEY_H */
diff --git a/include/drm/ati_pcigart.h b/include/drm/ati_pcigart.h
new file mode 100644
index 000000000000..5765648b5ef7
--- /dev/null
+++ b/include/drm/ati_pcigart.h
@@ -0,0 +1,30 @@
+#ifndef DRM_ATI_PCIGART_H
+#define DRM_ATI_PCIGART_H
+
+#include <drm/drm_legacy.h>
+
+/* location of GART table */
+#define DRM_ATI_GART_MAIN 1
+#define DRM_ATI_GART_FB   2
+
+#define DRM_ATI_GART_PCI 1
+#define DRM_ATI_GART_PCIE 2
+#define DRM_ATI_GART_IGP 3
+
+struct drm_ati_pcigart_info {
+	int gart_table_location;
+	int gart_reg_if;
+	void *addr;
+	dma_addr_t bus_addr;
+	dma_addr_t table_mask;
+	struct drm_dma_handle *table_handle;
+	struct drm_local_map mapping;
+	int table_size;
+};
+
+extern int drm_ati_pcigart_init(struct drm_device *dev,
+				struct drm_ati_pcigart_info * gart_info);
+extern int drm_ati_pcigart_cleanup(struct drm_device *dev,
+				   struct drm_ati_pcigart_info * gart_info);
+
+#endif
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 196890735367..53ed87698a74 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1,17 +1,14 @@
-/**
- * \file drmP.h
- * Private header for Direct Rendering Manager
- *
- * \author Rickard E. (Rik) Faith <faith@valinux.com>
- * \author Gareth Hughes <gareth@valinux.com>
- */
-
 /*
+ * Internal Header for the Direct Rendering Manager
+ *
  * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
  * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
  * Copyright (c) 2009-2010, Code Aurora Forum.
  * All rights reserved.
  *
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
+ * Author: Gareth Hughes <gareth@valinux.com>
+ *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
  * to deal in the Software without restriction, including without limitation
@@ -35,59 +32,62 @@
 #ifndef _DRM_P_H_
 #define _DRM_P_H_
 
-#ifdef __KERNEL__
-#ifdef __alpha__
-/* add include of current.h so that "current" is defined
- * before static inline funcs in wait.h. Doing this so we
- * can build the DRM (part of PI DRI). 4/21/2000 S + B */
-#include <asm/current.h>
-#endif				/* __alpha__ */
-#include <linux/kernel.h>
-#include <linux/kref.h>
-#include <linux/miscdevice.h>
+#include <linux/agp_backend.h>
+#include <linux/cdev.h>
+#include <linux/dma-mapping.h>
+#include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/highmem.h>
+#include <linux/idr.h>
 #include <linux/init.h>
-#include <linux/file.h>
-#include <linux/platform_device.h>
-#include <linux/pci.h>
+#include <linux/io.h>
 #include <linux/jiffies.h>
-#include <linux/dma-mapping.h>
+#include <linux/kernel.h>
+#include <linux/kref.h>
+#include <linux/miscdevice.h>
 #include <linux/mm.h>
-#include <linux/cdev.h>
 #include <linux/mutex.h>
-#include <linux/io.h>
-#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/poll.h>
 #include <linux/ratelimit.h>
-#if defined(__alpha__) || defined(__powerpc__)
-#include <asm/pgtable.h>	/* For pte_wrprotect */
-#endif
-#include <asm/mman.h>
-#include <asm/uaccess.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/types.h>
-#include <linux/agp_backend.h>
+#include <linux/vmalloc.h>
 #include <linux/workqueue.h>
-#include <linux/poll.h>
+
+#include <asm/mman.h>
 #include <asm/pgalloc.h>
-#include <drm/drm.h>
-#include <drm/drm_sarea.h>
-#include <drm/drm_vma_manager.h>
+#include <asm/uaccess.h>
 
-#include <linux/idr.h>
+#include <uapi/drm/drm.h>
+#include <uapi/drm/drm_mode.h>
 
-#define __OS_HAS_AGP (defined(CONFIG_AGP) || (defined(CONFIG_AGP_MODULE) && defined(MODULE)))
+#include <drm/drm_agpsupport.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_global.h>
+#include <drm/drm_hashtab.h>
+#include <drm/drm_mem_util.h>
+#include <drm/drm_mm.h>
+#include <drm/drm_os_linux.h>
+#include <drm/drm_sarea.h>
+#include <drm/drm_vma_manager.h>
 
 struct module;
 
 struct drm_file;
 struct drm_device;
+struct drm_agp_head;
+struct drm_local_map;
+struct drm_device_dma;
+struct drm_dma_handle;
+struct drm_gem_object;
 
 struct device_node;
 struct videomode;
 struct reservation_object;
-
-#include <drm/drm_os_linux.h>
-#include <drm/drm_hashtab.h>
-#include <drm/drm_mm.h>
+struct dma_buf_attachment;
 
 /*
  * 4 debug categories are defined:
@@ -126,7 +126,7 @@ extern __printf(2, 3)
 void drm_ut_debug_printk(const char *function_name,
 			 const char *format, ...);
 extern __printf(2, 3)
-int drm_err(const char *func, const char *format, ...);
+void drm_err(const char *func, const char *format, ...);
 
 /***********************************************************************/
 /** \name DRM template customization defaults */
@@ -145,19 +145,6 @@ int drm_err(const char *func, const char *format, ...);
 #define DRIVER_RENDER      0x8000
 
 /***********************************************************************/
-/** \name Begin the DRM... */
-/*@{*/
-
-#define DRM_DEBUG_CODE 2	  /**< Include debugging code if > 1, then
-				     also include looping detection. */
-
-#define DRM_MAGIC_HASH_ORDER  4  /**< Size of key hash table. Must be power of 2. */
-
-#define DRM_MAP_HASH_OFFSET 0x10000000
-
-/*@}*/
-
-/***********************************************************************/
 /** \name Macros to make printk easier */
 /*@{*/
 
@@ -198,7 +185,6 @@ int drm_err(const char *func, const char *format, ...);
  * \param fmt printf() like format string.
  * \param arg arguments
  */
-#if DRM_DEBUG_CODE
 #define DRM_DEBUG(fmt, args...)						\
 	do {								\
 		if (unlikely(drm_debug & DRM_UT_CORE))			\
@@ -220,12 +206,6 @@ int drm_err(const char *func, const char *format, ...);
 		if (unlikely(drm_debug & DRM_UT_PRIME))			\
 			drm_ut_debug_printk(__func__, fmt, ##args);	\
 	} while (0)
-#else
-#define DRM_DEBUG_DRIVER(fmt, args...) do { } while (0)
-#define DRM_DEBUG_KMS(fmt, args...)	do { } while (0)
-#define DRM_DEBUG_PRIME(fmt, args...)	do { } while (0)
-#define DRM_DEBUG(fmt, arg...)		 do { } while (0)
-#endif
 
 /*@}*/
 
@@ -236,23 +216,6 @@ int drm_err(const char *func, const char *format, ...);
 #define DRM_IF_VERSION(maj, min) (maj << 16 | min)
 
 /**
- * Test that the hardware lock is held by the caller, returning otherwise.
- *
- * \param dev DRM device.
- * \param filp file pointer of the caller.
- */
-#define LOCK_TEST_WITH_RETURN( dev, _file_priv )				\
-do {										\
-	if (!_DRM_LOCK_IS_HELD(_file_priv->master->lock.hw_lock->lock) ||	\
-	    _file_priv->master->lock.file_priv != _file_priv)	{		\
-		DRM_ERROR( "%s called without lock held, held  %d owner %p %p\n",\
-			   __func__, _DRM_LOCK_IS_HELD(_file_priv->master->lock.hw_lock->lock),\
-			   _file_priv->master->lock.file_priv, _file_priv);	\
-		return -EINVAL;							\
-	}									\
-} while (0)
-
-/**
  * Ioctl function type.
  *
  * \param inode device inode.
@@ -292,80 +255,6 @@ struct drm_ioctl_desc {
 #define DRM_IOCTL_DEF_DRV(ioctl, _func, _flags)			\
 	[DRM_IOCTL_NR(DRM_##ioctl)] = {.cmd = DRM_##ioctl, .func = _func, .flags = _flags, .cmd_drv = DRM_IOCTL_##ioctl, .name = #ioctl}
 
-struct drm_magic_entry {
-	struct list_head head;
-	struct drm_hash_item hash_item;
-	struct drm_file *priv;
-};
-
-struct drm_vma_entry {
-	struct list_head head;
-	struct vm_area_struct *vma;
-	pid_t pid;
-};
-
-/**
- * DMA buffer.
- */
-struct drm_buf {
-	int idx;		       /**< Index into master buflist */
-	int total;		       /**< Buffer size */
-	int order;		       /**< log-base-2(total) */
-	int used;		       /**< Amount of buffer in use (for DMA) */
-	unsigned long offset;	       /**< Byte offset (used internally) */
-	void *address;		       /**< Address of buffer */
-	unsigned long bus_address;     /**< Bus address of buffer */
-	struct drm_buf *next;	       /**< Kernel-only: used for free list */
-	__volatile__ int waiting;      /**< On kernel DMA queue */
-	__volatile__ int pending;      /**< On hardware DMA queue */
-	struct drm_file *file_priv;    /**< Private of holding file descr */
-	int context;		       /**< Kernel queue for this buffer */
-	int while_locked;	       /**< Dispatch this buffer while locked */
-	enum {
-		DRM_LIST_NONE = 0,
-		DRM_LIST_FREE = 1,
-		DRM_LIST_WAIT = 2,
-		DRM_LIST_PEND = 3,
-		DRM_LIST_PRIO = 4,
-		DRM_LIST_RECLAIM = 5
-	} list;			       /**< Which list we're on */
-
-	int dev_priv_size;		 /**< Size of buffer private storage */
-	void *dev_private;		 /**< Per-buffer private storage */
-};
-
-/** bufs is one longer than it has to be */
-struct drm_waitlist {
-	int count;			/**< Number of possible buffers */
-	struct drm_buf **bufs;		/**< List of pointers to buffers */
-	struct drm_buf **rp;			/**< Read pointer */
-	struct drm_buf **wp;			/**< Write pointer */
-	struct drm_buf **end;		/**< End pointer */
-	spinlock_t read_lock;
-	spinlock_t write_lock;
-};
-
-typedef struct drm_dma_handle {
-	dma_addr_t busaddr;
-	void *vaddr;
-	size_t size;
-} drm_dma_handle_t;
-
-/**
- * Buffer entry.  There is one of this for each buffer size order.
- */
-struct drm_buf_entry {
-	int buf_size;			/**< size */
-	int buf_count;			/**< number of buffers */
-	struct drm_buf *buflist;		/**< buffer list */
-	int seg_count;
-	int page_order;
-	struct drm_dma_handle **seglist;
-
-	int low_mark;			/**< Low water mark */
-	int high_mark;			/**< High water mark */
-};
-
 /* Event queued up for userspace to read */
 struct drm_pending_event {
 	struct drm_event *event;
@@ -444,214 +333,12 @@ struct drm_lock_data {
 };
 
 /**
- * DMA data.
- */
-struct drm_device_dma {
-
-	struct drm_buf_entry bufs[DRM_MAX_ORDER + 1];	/**< buffers, grouped by their size order */
-	int buf_count;			/**< total number of buffers */
-	struct drm_buf **buflist;		/**< Vector of pointers into drm_device_dma::bufs */
-	int seg_count;
-	int page_count;			/**< number of pages */
-	unsigned long *pagelist;	/**< page list */
-	unsigned long byte_count;
-	enum {
-		_DRM_DMA_USE_AGP = 0x01,
-		_DRM_DMA_USE_SG = 0x02,
-		_DRM_DMA_USE_FB = 0x04,
-		_DRM_DMA_USE_PCI_RO = 0x08
-	} flags;
-
-};
-
-/**
- * AGP memory entry.  Stored as a doubly linked list.
- */
-struct drm_agp_mem {
-	unsigned long handle;		/**< handle */
-	struct agp_memory *memory;
-	unsigned long bound;		/**< address */
-	int pages;
-	struct list_head head;
-};
-
-/**
- * AGP data.
- *
- * \sa drm_agp_init() and drm_device::agp.
- */
-struct drm_agp_head {
-	struct agp_kern_info agp_info;		/**< AGP device information */
-	struct list_head memory;
-	unsigned long mode;		/**< AGP mode */
-	struct agp_bridge_data *bridge;
-	int enabled;			/**< whether the AGP bus as been enabled */
-	int acquired;			/**< whether the AGP device has been acquired */
-	unsigned long base;
-	int agp_mtrr;
-	int cant_use_aperture;
-	unsigned long page_mask;
-};
-
-/**
- * Scatter-gather memory.
- */
-struct drm_sg_mem {
-	unsigned long handle;
-	void *virtual;
-	int pages;
-	struct page **pagelist;
-	dma_addr_t *busaddr;
-};
-
-struct drm_sigdata {
-	int context;
-	struct drm_hw_lock *lock;
-};
-
-
-/**
- * Kernel side of a mapping
- */
-struct drm_local_map {
-	resource_size_t offset;	 /**< Requested physical address (0 for SAREA)*/
-	unsigned long size;	 /**< Requested physical size (bytes) */
-	enum drm_map_type type;	 /**< Type of memory to map */
-	enum drm_map_flags flags;	 /**< Flags */
-	void *handle;		 /**< User-space: "Handle" to pass to mmap() */
-				 /**< Kernel-space: kernel-virtual address */
-	int mtrr;		 /**< MTRR slot used */
-};
-
-typedef struct drm_local_map drm_local_map_t;
-
-/**
- * Mappings list
- */
-struct drm_map_list {
-	struct list_head head;		/**< list head */
-	struct drm_hash_item hash;
-	struct drm_local_map *map;	/**< mapping */
-	uint64_t user_token;
-	struct drm_master *master;
-};
-
-/* location of GART table */
-#define DRM_ATI_GART_MAIN 1
-#define DRM_ATI_GART_FB   2
-
-#define DRM_ATI_GART_PCI 1
-#define DRM_ATI_GART_PCIE 2
-#define DRM_ATI_GART_IGP 3
-
-struct drm_ati_pcigart_info {
-	int gart_table_location;
-	int gart_reg_if;
-	void *addr;
-	dma_addr_t bus_addr;
-	dma_addr_t table_mask;
-	struct drm_dma_handle *table_handle;
-	struct drm_local_map mapping;
-	int table_size;
-};
-
-/**
- * This structure defines the drm_mm memory object, which will be used by the
- * DRM for its buffer objects.
- */
-struct drm_gem_object {
-	/** Reference count of this object */
-	struct kref refcount;
-
-	/**
-	 * handle_count - gem file_priv handle count of this object
-	 *
-	 * Each handle also holds a reference. Note that when the handle_count
-	 * drops to 0 any global names (e.g. the id in the flink namespace) will
-	 * be cleared.
-	 *
-	 * Protected by dev->object_name_lock.
-	 * */
-	unsigned handle_count;
-
-	/** Related drm device */
-	struct drm_device *dev;
-
-	/** File representing the shmem storage */
-	struct file *filp;
-
-	/* Mapping info for this object */
-	struct drm_vma_offset_node vma_node;
-
-	/**
-	 * Size of the object, in bytes.  Immutable over the object's
-	 * lifetime.
-	 */
-	size_t size;
-
-	/**
-	 * Global name for this object, starts at 1. 0 means unnamed.
-	 * Access is covered by the object_name_lock in the related drm_device
-	 */
-	int name;
-
-	/**
-	 * Memory domains. These monitor which caches contain read/write data
-	 * related to the object. When transitioning from one set of domains
-	 * to another, the driver is called to ensure that caches are suitably
-	 * flushed and invalidated
-	 */
-	uint32_t read_domains;
-	uint32_t write_domain;
-
-	/**
-	 * While validating an exec operation, the
-	 * new read/write domain values are computed here.
-	 * They will be transferred to the above values
-	 * at the point that any cache flushing occurs
-	 */
-	uint32_t pending_read_domains;
-	uint32_t pending_write_domain;
-
-	/**
-	 * dma_buf - dma buf associated with this GEM object
-	 *
-	 * Pointer to the dma-buf associated with this gem object (either
-	 * through importing or exporting). We break the resulting reference
-	 * loop when the last gem handle for this object is released.
-	 *
-	 * Protected by obj->object_name_lock
-	 */
-	struct dma_buf *dma_buf;
-
-	/**
-	 * import_attach - dma buf attachment backing this object
-	 *
-	 * Any foreign dma_buf imported as a gem object has this set to the
-	 * attachment point for the device. This is invariant over the lifetime
-	 * of a gem object.
-	 *
-	 * The driver's ->gem_free_object callback is responsible for cleaning
-	 * up the dma_buf attachment and references acquired at import time.
-	 *
-	 * Note that the drm gem/prime core does not depend upon drivers setting
-	 * this field any more. So for drivers where this doesn't make sense
-	 * (e.g. virtual devices or a displaylink behind an usb bus) they can
-	 * simply leave it as NULL.
-	 */
-	struct dma_buf_attachment *import_attach;
-};
-
-#include <drm/drm_crtc.h>
-
-/**
  * struct drm_master - drm master structure
  *
  * @refcount: Refcount for this master object.
  * @minor: Link back to minor char device we are master for. Immutable.
  * @unique: Unique identifier: e.g. busid. Protected by drm_global_mutex.
  * @unique_len: Length of unique field. Protected by drm_global_mutex.
- * @unique_size: Amount allocated. Protected by drm_global_mutex.
  * @magiclist: Hash of used authentication tokens. Protected by struct_mutex.
  * @magicfree: List of used authentication tokens. Protected by struct_mutex.
  * @lock: DRI lock information.
@@ -662,7 +349,6 @@ struct drm_master {
 	struct drm_minor *minor;
 	char *unique;
 	int unique_len;
-	int unique_size;
 	struct drm_open_hash magiclist;
 	struct list_head magicfree;
 	struct drm_lock_data lock;
@@ -677,17 +363,13 @@ struct drm_master {
 /* Flags and return codes for get_vblank_timestamp() driver function. */
 #define DRM_CALLED_FROM_VBLIRQ 1
 #define DRM_VBLANKTIME_SCANOUTPOS_METHOD (1 << 0)
-#define DRM_VBLANKTIME_INVBL             (1 << 1)
+#define DRM_VBLANKTIME_IN_VBLANK         (1 << 1)
 
 /* get_scanout_position() return flags */
 #define DRM_SCANOUTPOS_VALID        (1 << 0)
-#define DRM_SCANOUTPOS_INVBL        (1 << 1)
+#define DRM_SCANOUTPOS_IN_VBLANK    (1 << 1)
 #define DRM_SCANOUTPOS_ACCURATE     (1 << 2)
 
-struct drm_bus {
-	int (*set_busid)(struct drm_device *dev, struct drm_master *master);
-};
-
 /**
  * DRM driver structure. This structure represent the common code for
  * a family of cards. There will one drm_device for each card present
@@ -706,6 +388,7 @@ struct drm_driver {
 	int (*dma_ioctl) (struct drm_device *dev, void *data, struct drm_file *file_priv);
 	int (*dma_quiescent) (struct drm_device *);
 	int (*context_dtor) (struct drm_device *dev, int context);
+	int (*set_busid)(struct drm_device *dev, struct drm_master *master);
 
 	/**
 	 * get_vblank_counter - get raw hardware vblank counter
@@ -888,7 +571,8 @@ struct drm_driver {
 				struct drm_gem_object *obj);
 	struct sg_table *(*gem_prime_get_sg_table)(struct drm_gem_object *obj);
 	struct drm_gem_object *(*gem_prime_import_sg_table)(
-				struct drm_device *dev, size_t size,
+				struct drm_device *dev,
+				struct dma_buf_attachment *attach,
 				struct sg_table *sgt);
 	void *(*gem_prime_vmap)(struct drm_gem_object *obj);
 	void (*gem_prime_vunmap)(struct drm_gem_object *obj, void *vaddr);
@@ -924,7 +608,6 @@ struct drm_driver {
 	const struct drm_ioctl_desc *ioctls;
 	int num_ioctls;
 	const struct file_operations *fops;
-	struct drm_bus *bus;
 
 	/* List of devices hanging off this driver with stealth attach. */
 	struct list_head legacy_dev_list;
@@ -1079,6 +762,16 @@ struct drm_device {
 	 */
 	bool vblank_disable_allowed;
 
+	/*
+	 * If true, vblank interrupt will be disabled immediately when the
+	 * refcount drops to zero, as opposed to via the vblank disable
+	 * timer.
+	 * This can be set to true it the hardware has a working vblank
+	 * counter and the driver uses drm_vblank_on() and drm_vblank_off()
+	 * appropriately.
+	 */
+	bool vblank_disable_immediate;
+
 	/* array of size num_crtcs */
 	struct drm_vblank_crtc *vblank;
 
@@ -1103,13 +796,16 @@ struct drm_device {
 #endif
 
 	struct platform_device *platformdev; /**< Platform device struture */
-	struct usb_device *usbdev;
 
 	struct drm_sg_mem *sg;	/**< Scatter gather memory */
 	unsigned int num_crtcs;                  /**< Number of CRTCs on this device */
-	struct drm_sigdata sigdata;	   /**< For block_all_signals */
 	sigset_t sigmask;
 
+	struct {
+		int context;
+		struct drm_hw_lock *lock;
+	} sigdata;
+
 	struct drm_local_map *agp_buffer_map;
 	unsigned int agp_buffer_token;
 
@@ -1172,112 +868,32 @@ extern long drm_ioctl(struct file *filp,
 		      unsigned int cmd, unsigned long arg);
 extern long drm_compat_ioctl(struct file *filp,
 			     unsigned int cmd, unsigned long arg);
-extern int drm_lastclose(struct drm_device *dev);
 extern bool drm_ioctl_flags(unsigned int nr, unsigned int *flags);
 
 				/* Device support (drm_fops.h) */
-extern struct mutex drm_global_mutex;
 extern int drm_open(struct inode *inode, struct file *filp);
 extern ssize_t drm_read(struct file *filp, char __user *buffer,
 			size_t count, loff_t *offset);
 extern int drm_release(struct inode *inode, struct file *filp);
 
 				/* Mapping support (drm_vm.h) */
-extern int drm_mmap(struct file *filp, struct vm_area_struct *vma);
-extern int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma);
-extern void drm_vm_open_locked(struct drm_device *dev, struct vm_area_struct *vma);
-extern void drm_vm_close_locked(struct drm_device *dev, struct vm_area_struct *vma);
 extern unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait);
 
-				/* Memory management support (drm_memory.h) */
-#include <drm/drm_memory.h>
-
-
-				/* Misc. IOCTL support (drm_ioctl.h) */
-extern int drm_irq_by_busid(struct drm_device *dev, void *data,
-			    struct drm_file *file_priv);
-extern int drm_getunique(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
-extern int drm_setunique(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
-extern int drm_getmap(struct drm_device *dev, void *data,
-		      struct drm_file *file_priv);
-extern int drm_getclient(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
-extern int drm_getstats(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_getcap(struct drm_device *dev, void *data,
-		      struct drm_file *file_priv);
-extern int drm_setclientcap(struct drm_device *dev, void *data,
-			    struct drm_file *file_priv);
-extern int drm_setversion(struct drm_device *dev, void *data,
-			  struct drm_file *file_priv);
-extern int drm_noop(struct drm_device *dev, void *data,
-		    struct drm_file *file_priv);
-
-				/* Authentication IOCTL support (drm_auth.h) */
-extern int drm_getmagic(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_authmagic(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
-extern int drm_remove_magic(struct drm_master *master, drm_magic_t magic);
+/* Misc. IOCTL support (drm_ioctl.c) */
+int drm_noop(struct drm_device *dev, void *data,
+	     struct drm_file *file_priv);
 
 /* Cache management (drm_cache.c) */
 void drm_clflush_pages(struct page *pages[], unsigned long num_pages);
 void drm_clflush_sg(struct sg_table *st);
 void drm_clflush_virt_range(void *addr, unsigned long length);
 
-				/* Locking IOCTL support (drm_lock.h) */
-extern int drm_lock(struct drm_device *dev, void *data,
-		    struct drm_file *file_priv);
-extern int drm_unlock(struct drm_device *dev, void *data,
-		      struct drm_file *file_priv);
-extern int drm_lock_free(struct drm_lock_data *lock_data, unsigned int context);
-extern void drm_idlelock_take(struct drm_lock_data *lock_data);
-extern void drm_idlelock_release(struct drm_lock_data *lock_data);
-
 /*
  * These are exported to drivers so that they can implement fencing using
  * DMA quiscent + idle. DMA quiescent usually requires the hardware lock.
  */
 
-extern int drm_i_have_hw_lock(struct drm_device *dev, struct drm_file *file_priv);
-
-				/* Buffer management support (drm_bufs.h) */
-extern int drm_addbufs_agp(struct drm_device *dev, struct drm_buf_desc * request);
-extern int drm_addbufs_pci(struct drm_device *dev, struct drm_buf_desc * request);
-extern int drm_addmap(struct drm_device *dev, resource_size_t offset,
-		      unsigned int size, enum drm_map_type type,
-		      enum drm_map_flags flags, struct drm_local_map **map_ptr);
-extern int drm_addmap_ioctl(struct drm_device *dev, void *data,
-			    struct drm_file *file_priv);
-extern int drm_rmmap(struct drm_device *dev, struct drm_local_map *map);
-extern int drm_rmmap_locked(struct drm_device *dev, struct drm_local_map *map);
-extern int drm_rmmap_ioctl(struct drm_device *dev, void *data,
-			   struct drm_file *file_priv);
-extern int drm_addbufs(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv);
-extern int drm_infobufs(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_markbufs(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_freebufs(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_mapbufs(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv);
-extern int drm_dma_ioctl(struct drm_device *dev, void *data,
-			 struct drm_file *file_priv);
-
-				/* DMA support (drm_dma.h) */
-extern int drm_legacy_dma_setup(struct drm_device *dev);
-extern void drm_legacy_dma_takedown(struct drm_device *dev);
-extern void drm_free_buffer(struct drm_device *dev, struct drm_buf * buf);
-extern void drm_core_reclaim_buffers(struct drm_device *dev,
-				     struct drm_file *filp);
-
 				/* IRQ support (drm_irq.h) */
-extern int drm_control(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv);
 extern int drm_irq_install(struct drm_device *dev, int irq);
 extern int drm_irq_uninstall(struct drm_device *dev);
 
@@ -1294,14 +910,14 @@ extern int drm_vblank_get(struct drm_device *dev, int crtc);
 extern void drm_vblank_put(struct drm_device *dev, int crtc);
 extern int drm_crtc_vblank_get(struct drm_crtc *crtc);
 extern void drm_crtc_vblank_put(struct drm_crtc *crtc);
+extern void drm_wait_one_vblank(struct drm_device *dev, int crtc);
+extern void drm_crtc_wait_one_vblank(struct drm_crtc *crtc);
 extern void drm_vblank_off(struct drm_device *dev, int crtc);
 extern void drm_vblank_on(struct drm_device *dev, int crtc);
 extern void drm_crtc_vblank_off(struct drm_crtc *crtc);
 extern void drm_crtc_vblank_on(struct drm_crtc *crtc);
 extern void drm_vblank_cleanup(struct drm_device *dev);
 
-extern u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
-				     struct timeval *tvblank, unsigned flags);
 extern int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev,
 						 int crtc, int *max_error,
 						 struct timeval *vblank_time,
@@ -1311,23 +927,23 @@ extern int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev,
 extern void drm_calc_timestamping_constants(struct drm_crtc *crtc,
 					    const struct drm_display_mode *mode);
 
+/**
+ * drm_crtc_vblank_waitqueue - get vblank waitqueue for the CRTC
+ * @crtc: which CRTC's vblank waitqueue to retrieve
+ *
+ * This function returns a pointer to the vblank waitqueue for the CRTC.
+ * Drivers can use this to implement vblank waits using wait_event() & co.
+ */
+static inline wait_queue_head_t *drm_crtc_vblank_waitqueue(struct drm_crtc *crtc)
+{
+	return &crtc->dev->vblank[drm_crtc_index(crtc)].queue;
+}
 
 /* Modesetting support */
 extern void drm_vblank_pre_modeset(struct drm_device *dev, int crtc);
 extern void drm_vblank_post_modeset(struct drm_device *dev, int crtc);
-extern int drm_modeset_ctl(struct drm_device *dev, void *data,
-			   struct drm_file *file_priv);
-
-				/* AGP/GART support (drm_agpsupport.h) */
-
-#include <drm/drm_agpsupport.h>
 
 				/* Stub support (drm_stub.h) */
-extern int drm_setmaster_ioctl(struct drm_device *dev, void *data,
-			       struct drm_file *file_priv);
-extern int drm_dropmaster_ioctl(struct drm_device *dev, void *data,
-				struct drm_file *file_priv);
-struct drm_master *drm_master_create(struct drm_minor *minor);
 extern struct drm_master *drm_master_get(struct drm_master *master);
 extern void drm_master_put(struct drm_master **master);
 
@@ -1335,33 +951,14 @@ extern void drm_put_dev(struct drm_device *dev);
 extern void drm_unplug_dev(struct drm_device *dev);
 extern unsigned int drm_debug;
 
-extern unsigned int drm_vblank_offdelay;
-extern unsigned int drm_timestamp_precision;
-extern unsigned int drm_timestamp_monotonic;
-
-extern struct class *drm_class;
-
-extern struct drm_local_map *drm_getsarea(struct drm_device *dev);
-
 				/* Debugfs support */
 #if defined(CONFIG_DEBUG_FS)
-extern int drm_debugfs_init(struct drm_minor *minor, int minor_id,
-			    struct dentry *root);
 extern int drm_debugfs_create_files(const struct drm_info_list *files,
 				    int count, struct dentry *root,
 				    struct drm_minor *minor);
 extern int drm_debugfs_remove_files(const struct drm_info_list *files,
 				    int count, struct drm_minor *minor);
-extern int drm_debugfs_cleanup(struct drm_minor *minor);
-extern int drm_debugfs_connector_add(struct drm_connector *connector);
-extern void drm_debugfs_connector_remove(struct drm_connector *connector);
 #else
-static inline int drm_debugfs_init(struct drm_minor *minor, int minor_id,
-				   struct dentry *root)
-{
-	return 0;
-}
-
 static inline int drm_debugfs_create_files(const struct drm_info_list *files,
 					   int count, struct dentry *root,
 					   struct drm_minor *minor)
@@ -1374,31 +971,8 @@ static inline int drm_debugfs_remove_files(const struct drm_info_list *files,
 {
 	return 0;
 }
-
-static inline int drm_debugfs_cleanup(struct drm_minor *minor)
-{
-	return 0;
-}
-
-static inline int drm_debugfs_connector_add(struct drm_connector *connector)
-{
-	return 0;
-}
-static inline void drm_debugfs_connector_remove(struct drm_connector *connector)
-{
-}
-
 #endif
 
-				/* Info file support */
-extern int drm_name_info(struct seq_file *m, void *data);
-extern int drm_vm_info(struct seq_file *m, void *data);
-extern int drm_bufs_info(struct seq_file *m, void *data);
-extern int drm_vblank_info(struct seq_file *m, void *data);
-extern int drm_clients_info(struct seq_file *m, void* data);
-extern int drm_gem_name_info(struct seq_file *m, void *data);
-
-
 extern struct dma_buf *drm_gem_prime_export(struct drm_device *dev,
 		struct drm_gem_object *obj, int flags);
 extern int drm_gem_prime_handle_to_fd(struct drm_device *dev,
@@ -1410,150 +984,20 @@ extern int drm_gem_prime_fd_to_handle(struct drm_device *dev,
 		struct drm_file *file_priv, int prime_fd, uint32_t *handle);
 extern void drm_gem_dmabuf_release(struct dma_buf *dma_buf);
 
-extern int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
-					struct drm_file *file_priv);
-extern int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
-					struct drm_file *file_priv);
-
 extern int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages,
 					    dma_addr_t *addrs, int max_pages);
 extern struct sg_table *drm_prime_pages_to_sg(struct page **pages, int nr_pages);
 extern void drm_prime_gem_destroy(struct drm_gem_object *obj, struct sg_table *sg);
 
-int drm_gem_dumb_destroy(struct drm_file *file,
-			 struct drm_device *dev,
-			 uint32_t handle);
-
-void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv);
-void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv);
-void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv, struct dma_buf *dma_buf);
-
-#if DRM_DEBUG_CODE
-extern int drm_vma_info(struct seq_file *m, void *data);
-#endif
 
-				/* Scatter Gather Support (drm_scatter.h) */
-extern void drm_legacy_sg_cleanup(struct drm_device *dev);
-extern int drm_sg_alloc(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-extern int drm_sg_free(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv);
-
-			       /* ATI PCIGART support (ati_pcigart.h) */
-extern int drm_ati_pcigart_init(struct drm_device *dev,
-				struct drm_ati_pcigart_info * gart_info);
-extern int drm_ati_pcigart_cleanup(struct drm_device *dev,
-				   struct drm_ati_pcigart_info * gart_info);
-
-extern drm_dma_handle_t *drm_pci_alloc(struct drm_device *dev, size_t size,
-				       size_t align);
-extern void __drm_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
-extern void drm_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
-extern int drm_pci_set_unique(struct drm_device *dev,
-			      struct drm_master *master,
-			      struct drm_unique *u);
+extern struct drm_dma_handle *drm_pci_alloc(struct drm_device *dev, size_t size,
+					    size_t align);
+extern void drm_pci_free(struct drm_device *dev, struct drm_dma_handle * dmah);
 
 			       /* sysfs support (drm_sysfs.c) */
-struct drm_sysfs_class;
-extern struct class *drm_sysfs_create(struct module *owner, char *name);
-extern void drm_sysfs_destroy(void);
-extern struct device *drm_sysfs_minor_alloc(struct drm_minor *minor);
 extern void drm_sysfs_hotplug_event(struct drm_device *dev);
-extern int drm_sysfs_connector_add(struct drm_connector *connector);
-extern void drm_sysfs_connector_remove(struct drm_connector *connector);
-
-/* Graphics Execution Manager library functions (drm_gem.c) */
-int drm_gem_init(struct drm_device *dev);
-void drm_gem_destroy(struct drm_device *dev);
-void drm_gem_object_release(struct drm_gem_object *obj);
-void drm_gem_object_free(struct kref *kref);
-int drm_gem_object_init(struct drm_device *dev,
-			struct drm_gem_object *obj, size_t size);
-void drm_gem_private_object_init(struct drm_device *dev,
-				 struct drm_gem_object *obj, size_t size);
-void drm_gem_vm_open(struct vm_area_struct *vma);
-void drm_gem_vm_close(struct vm_area_struct *vma);
-int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size,
-		     struct vm_area_struct *vma);
-int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
-
-#include <drm/drm_global.h>
-
-static inline void
-drm_gem_object_reference(struct drm_gem_object *obj)
-{
-	kref_get(&obj->refcount);
-}
-
-static inline void
-drm_gem_object_unreference(struct drm_gem_object *obj)
-{
-	if (obj != NULL)
-		kref_put(&obj->refcount, drm_gem_object_free);
-}
-
-static inline void
-drm_gem_object_unreference_unlocked(struct drm_gem_object *obj)
-{
-	if (obj && !atomic_add_unless(&obj->refcount.refcount, -1, 1)) {
-		struct drm_device *dev = obj->dev;
-
-		mutex_lock(&dev->struct_mutex);
-		if (likely(atomic_dec_and_test(&obj->refcount.refcount)))
-			drm_gem_object_free(&obj->refcount);
-		mutex_unlock(&dev->struct_mutex);
-	}
-}
-
-int drm_gem_handle_create_tail(struct drm_file *file_priv,
-			       struct drm_gem_object *obj,
-			       u32 *handlep);
-int drm_gem_handle_create(struct drm_file *file_priv,
-			  struct drm_gem_object *obj,
-			  u32 *handlep);
-int drm_gem_handle_delete(struct drm_file *filp, u32 handle);
 
 
-void drm_gem_free_mmap_offset(struct drm_gem_object *obj);
-int drm_gem_create_mmap_offset(struct drm_gem_object *obj);
-int drm_gem_create_mmap_offset_size(struct drm_gem_object *obj, size_t size);
-
-struct page **drm_gem_get_pages(struct drm_gem_object *obj);
-void drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages,
-		bool dirty, bool accessed);
-
-struct drm_gem_object *drm_gem_object_lookup(struct drm_device *dev,
-					     struct drm_file *filp,
-					     u32 handle);
-int drm_gem_close_ioctl(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-int drm_gem_flink_ioctl(struct drm_device *dev, void *data,
-			struct drm_file *file_priv);
-int drm_gem_open_ioctl(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv);
-void drm_gem_open(struct drm_device *dev, struct drm_file *file_private);
-void drm_gem_release(struct drm_device *dev, struct drm_file *file_private);
-
-extern void drm_core_ioremap(struct drm_local_map *map, struct drm_device *dev);
-extern void drm_core_ioremap_wc(struct drm_local_map *map, struct drm_device *dev);
-extern void drm_core_ioremapfree(struct drm_local_map *map, struct drm_device *dev);
-
-static __inline__ struct drm_local_map *drm_core_findmap(struct drm_device *dev,
-							 unsigned int token)
-{
-	struct drm_map_list *_entry;
-	list_for_each_entry(_entry, &dev->maplist, head)
-	    if (_entry->user_token == token)
-		return _entry->map;
-	return NULL;
-}
-
-static __inline__ void drm_core_dropmap(struct drm_local_map *map)
-{
-}
-
-#include <drm/drm_mem_util.h>
-
 struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 				 struct device *parent);
 void drm_dev_ref(struct drm_device *dev);
@@ -1587,6 +1031,7 @@ extern void drm_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver);
 extern int drm_get_pci_dev(struct pci_dev *pdev,
 			   const struct pci_device_id *ent,
 			   struct drm_driver *driver);
+extern int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master);
 
 #define DRM_PCIE_SPEED_25 1
 #define DRM_PCIE_SPEED_50 2
@@ -1596,6 +1041,7 @@ extern int drm_pcie_get_speed_cap_mask(struct drm_device *dev, u32 *speed_mask);
 
 /* platform section */
 extern int drm_platform_init(struct drm_driver *driver, struct platform_device *platform_device);
+extern int drm_platform_set_busid(struct drm_device *d, struct drm_master *m);
 
 /* returns true if currently okay to sleep */
 static __inline__ bool drm_can_sleep(void)
@@ -1605,5 +1051,4 @@ static __inline__ bool drm_can_sleep(void)
 	return true;
 }
 
-#endif				/* __KERNEL__ */
 #endif
diff --git a/include/drm/drm_agpsupport.h b/include/drm/drm_agpsupport.h
index 86a02188074b..055dc058d147 100644
--- a/include/drm/drm_agpsupport.h
+++ b/include/drm/drm_agpsupport.h
@@ -1,12 +1,32 @@
 #ifndef _DRM_AGPSUPPORT_H_
 #define _DRM_AGPSUPPORT_H_
 
+#include <linux/agp_backend.h>
 #include <linux/kernel.h>
+#include <linux/list.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/types.h>
-#include <linux/agp_backend.h>
-#include <drm/drmP.h>
+#include <uapi/drm/drm.h>
+
+struct drm_device;
+struct drm_file;
+
+#define __OS_HAS_AGP (defined(CONFIG_AGP) || (defined(CONFIG_AGP_MODULE) && \
+					      defined(MODULE)))
+
+struct drm_agp_head {
+	struct agp_kern_info agp_info;
+	struct list_head memory;
+	unsigned long mode;
+	struct agp_bridge_data *bridge;
+	int enabled;
+	int acquired;
+	unsigned long base;
+	int agp_mtrr;
+	int cant_use_aperture;
+	unsigned long page_mask;
+};
 
 #if __OS_HAS_AGP
 
@@ -45,6 +65,7 @@ int drm_agp_unbind_ioctl(struct drm_device *dev, void *data,
 int drm_agp_bind(struct drm_device *dev, struct drm_agp_binding *request);
 int drm_agp_bind_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
+
 #else /* __OS_HAS_AGP */
 
 static inline void drm_free_agp(struct agp_memory * handle, int pages)
@@ -172,6 +193,7 @@ static inline int drm_agp_bind_ioctl(struct drm_device *dev, void *data,
 {
 	return -ENODEV;
 }
+
 #endif /* __OS_HAS_AGP */
 
 #endif /* _DRM_AGPSUPPORT_H_ */
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index f1105d0da059..c40070a92d6b 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -31,8 +31,8 @@
 #include <linux/idr.h>
 #include <linux/fb.h>
 #include <linux/hdmi.h>
-#include <drm/drm_mode.h>
-#include <drm/drm_fourcc.h>
+#include <uapi/drm/drm_mode.h>
+#include <uapi/drm/drm_fourcc.h>
 #include <drm/drm_modeset_lock.h>
 
 struct drm_device;
@@ -218,10 +218,6 @@ struct drm_property {
 	struct list_head enum_blob_list;
 };
 
-void drm_modeset_lock_all(struct drm_device *dev);
-void drm_modeset_unlock_all(struct drm_device *dev);
-void drm_warn_on_modeset_not_all_locked(struct drm_device *dev);
-
 struct drm_crtc;
 struct drm_connector;
 struct drm_encoder;
@@ -345,10 +341,6 @@ struct drm_crtc {
 	int cursor_x;
 	int cursor_y;
 
-	/* Temporary tracking of the old fb while a modeset is ongoing. Used
-	 * by drm_mode_set_config_internal to implement correct refcounting. */
-	struct drm_framebuffer *old_fb;
-
 	bool enabled;
 
 	/* Requested mode from modesetting. */
@@ -375,6 +367,12 @@ struct drm_crtc {
 	void *helper_private;
 
 	struct drm_object_properties properties;
+
+	/*
+	 * For legacy crtc ioctls so that atomic drivers can get at the locking
+	 * acquire context.
+	 */
+	struct drm_modeset_acquire_ctx *acquire_ctx;
 };
 
 
@@ -548,6 +546,7 @@ struct drm_connector {
 	void *helper_private;
 
 	/* forced on connector */
+	struct drm_cmdline_mode cmdline_mode;
 	enum drm_connector_force force;
 	bool override_edid;
 	uint32_t encoder_ids[DRM_CONNECTOR_MAX_ENCODER];
@@ -582,6 +581,7 @@ struct drm_plane_funcs {
 			    uint32_t src_w, uint32_t src_h);
 	int (*disable_plane)(struct drm_plane *plane);
 	void (*destroy)(struct drm_plane *plane);
+	void (*reset)(struct drm_plane *plane);
 
 	int (*set_property)(struct drm_plane *plane,
 			    struct drm_property *property, uint64_t val);
@@ -620,6 +620,10 @@ struct drm_plane {
 	struct drm_crtc *crtc;
 	struct drm_framebuffer *fb;
 
+	/* Temporary tracking of the old fb while a modeset is ongoing. Used
+	 * by drm_mode_set_config_internal to implement correct refcounting. */
+	struct drm_framebuffer *old_fb;
+
 	const struct drm_plane_funcs *funcs;
 
 	struct drm_object_properties properties;
@@ -821,6 +825,7 @@ struct drm_mode_config {
 	struct drm_property *dpms_property;
 	struct drm_property *path_property;
 	struct drm_property *plane_type_property;
+	struct drm_property *rotation_property;
 
 	/* DVI-I properties */
 	struct drm_property *dvi_i_subconnector_property;
@@ -903,6 +908,7 @@ int drm_connector_register(struct drm_connector *connector);
 void drm_connector_unregister(struct drm_connector *connector);
 
 extern void drm_connector_cleanup(struct drm_connector *connector);
+extern unsigned int drm_connector_index(struct drm_connector *connector);
 /* helper to unplug all connectors from sysfs for device */
 extern void drm_connector_unplug_all(struct drm_device *dev);
 
@@ -942,6 +948,7 @@ extern int drm_plane_init(struct drm_device *dev,
 			  const uint32_t *formats, uint32_t format_count,
 			  bool is_primary);
 extern void drm_plane_cleanup(struct drm_plane *plane);
+extern unsigned int drm_plane_index(struct drm_plane *plane);
 extern void drm_plane_force_disable(struct drm_plane *plane);
 extern int drm_crtc_check_viewport(const struct drm_crtc *crtc,
 				   int x, int y,
@@ -1120,6 +1127,9 @@ extern int drm_mode_obj_get_properties_ioctl(struct drm_device *dev, void *data,
 					     struct drm_file *file_priv);
 extern int drm_mode_obj_set_property_ioctl(struct drm_device *dev, void *data,
 					   struct drm_file *file_priv);
+extern int drm_mode_plane_set_obj_prop(struct drm_plane *plane,
+				       struct drm_property *property,
+				       uint64_t value);
 
 extern void drm_fb_get_bpp_depth(uint32_t format, unsigned int *depth,
 				 int *bpp);
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index a21568bf1514..9305c718d789 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -190,16 +190,16 @@
 # define DP_TRAIN_VOLTAGE_SWING_MASK	    0x3
 # define DP_TRAIN_VOLTAGE_SWING_SHIFT	    0
 # define DP_TRAIN_MAX_SWING_REACHED	    (1 << 2)
-# define DP_TRAIN_VOLTAGE_SWING_400	    (0 << 0)
-# define DP_TRAIN_VOLTAGE_SWING_600	    (1 << 0)
-# define DP_TRAIN_VOLTAGE_SWING_800	    (2 << 0)
-# define DP_TRAIN_VOLTAGE_SWING_1200	    (3 << 0)
+# define DP_TRAIN_VOLTAGE_SWING_LEVEL_0 (0 << 0)
+# define DP_TRAIN_VOLTAGE_SWING_LEVEL_1 (1 << 0)
+# define DP_TRAIN_VOLTAGE_SWING_LEVEL_2 (2 << 0)
+# define DP_TRAIN_VOLTAGE_SWING_LEVEL_3 (3 << 0)
 
 # define DP_TRAIN_PRE_EMPHASIS_MASK	    (3 << 3)
-# define DP_TRAIN_PRE_EMPHASIS_0	    (0 << 3)
-# define DP_TRAIN_PRE_EMPHASIS_3_5	    (1 << 3)
-# define DP_TRAIN_PRE_EMPHASIS_6	    (2 << 3)
-# define DP_TRAIN_PRE_EMPHASIS_9_5	    (3 << 3)
+# define DP_TRAIN_PRE_EMPH_LEVEL_0		(0 << 3)
+# define DP_TRAIN_PRE_EMPH_LEVEL_1		(1 << 3)
+# define DP_TRAIN_PRE_EMPH_LEVEL_2		(2 << 3)
+# define DP_TRAIN_PRE_EMPH_LEVEL_3		(3 << 3)
 
 # define DP_TRAIN_PRE_EMPHASIS_SHIFT	    3
 # define DP_TRAIN_MAX_PRE_EMPHASIS_REACHED  (1 << 5)
diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index 9b446ada2532..338fc1053835 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -388,6 +388,7 @@ struct drm_dp_payload {
 	int payload_state;
 	int start_slot;
 	int num_slots;
+	int vcpi;
 };
 
 /**
@@ -454,6 +455,7 @@ struct drm_dp_mst_topology_mgr {
 	struct drm_dp_vcpi **proposed_vcpis;
 	struct drm_dp_payload *payloads;
 	unsigned long payload_mask;
+	unsigned long vcpi_mask;
 
 	wait_queue_head_t tx_waitq;
 	struct work_struct work;
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index bfd329d613c4..f4ad254e3488 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -77,7 +77,6 @@ struct drm_fb_helper_funcs {
 
 struct drm_fb_helper_connector {
 	struct drm_connector *connector;
-	struct drm_cmdline_mode cmdline_mode;
 };
 
 struct drm_fb_helper {
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
new file mode 100644
index 000000000000..1e6ae1458f7a
--- /dev/null
+++ b/include/drm/drm_gem.h
@@ -0,0 +1,183 @@
+#ifndef __DRM_GEM_H__
+#define __DRM_GEM_H__
+
+/*
+ * GEM Graphics Execution Manager Driver Interfaces
+ *
+ * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
+ * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
+ * Copyright (c) 2009-2010, Code Aurora Forum.
+ * All rights reserved.
+ * Copyright © 2014 Intel Corporation
+ *   Daniel Vetter <daniel.vetter@ffwll.ch>
+ *
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
+ * Author: Gareth Hughes <gareth@valinux.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/**
+ * This structure defines the drm_mm memory object, which will be used by the
+ * DRM for its buffer objects.
+ */
+struct drm_gem_object {
+	/** Reference count of this object */
+	struct kref refcount;
+
+	/**
+	 * handle_count - gem file_priv handle count of this object
+	 *
+	 * Each handle also holds a reference. Note that when the handle_count
+	 * drops to 0 any global names (e.g. the id in the flink namespace) will
+	 * be cleared.
+	 *
+	 * Protected by dev->object_name_lock.
+	 * */
+	unsigned handle_count;
+
+	/** Related drm device */
+	struct drm_device *dev;
+
+	/** File representing the shmem storage */
+	struct file *filp;
+
+	/* Mapping info for this object */
+	struct drm_vma_offset_node vma_node;
+
+	/**
+	 * Size of the object, in bytes.  Immutable over the object's
+	 * lifetime.
+	 */
+	size_t size;
+
+	/**
+	 * Global name for this object, starts at 1. 0 means unnamed.
+	 * Access is covered by the object_name_lock in the related drm_device
+	 */
+	int name;
+
+	/**
+	 * Memory domains. These monitor which caches contain read/write data
+	 * related to the object. When transitioning from one set of domains
+	 * to another, the driver is called to ensure that caches are suitably
+	 * flushed and invalidated
+	 */
+	uint32_t read_domains;
+	uint32_t write_domain;
+
+	/**
+	 * While validating an exec operation, the
+	 * new read/write domain values are computed here.
+	 * They will be transferred to the above values
+	 * at the point that any cache flushing occurs
+	 */
+	uint32_t pending_read_domains;
+	uint32_t pending_write_domain;
+
+	/**
+	 * dma_buf - dma buf associated with this GEM object
+	 *
+	 * Pointer to the dma-buf associated with this gem object (either
+	 * through importing or exporting). We break the resulting reference
+	 * loop when the last gem handle for this object is released.
+	 *
+	 * Protected by obj->object_name_lock
+	 */
+	struct dma_buf *dma_buf;
+
+	/**
+	 * import_attach - dma buf attachment backing this object
+	 *
+	 * Any foreign dma_buf imported as a gem object has this set to the
+	 * attachment point for the device. This is invariant over the lifetime
+	 * of a gem object.
+	 *
+	 * The driver's ->gem_free_object callback is responsible for cleaning
+	 * up the dma_buf attachment and references acquired at import time.
+	 *
+	 * Note that the drm gem/prime core does not depend upon drivers setting
+	 * this field any more. So for drivers where this doesn't make sense
+	 * (e.g. virtual devices or a displaylink behind an usb bus) they can
+	 * simply leave it as NULL.
+	 */
+	struct dma_buf_attachment *import_attach;
+};
+
+void drm_gem_object_release(struct drm_gem_object *obj);
+void drm_gem_object_free(struct kref *kref);
+int drm_gem_object_init(struct drm_device *dev,
+			struct drm_gem_object *obj, size_t size);
+void drm_gem_private_object_init(struct drm_device *dev,
+				 struct drm_gem_object *obj, size_t size);
+void drm_gem_vm_open(struct vm_area_struct *vma);
+void drm_gem_vm_close(struct vm_area_struct *vma);
+int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size,
+		     struct vm_area_struct *vma);
+int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
+
+static inline void
+drm_gem_object_reference(struct drm_gem_object *obj)
+{
+	kref_get(&obj->refcount);
+}
+
+static inline void
+drm_gem_object_unreference(struct drm_gem_object *obj)
+{
+	if (obj != NULL)
+		kref_put(&obj->refcount, drm_gem_object_free);
+}
+
+static inline void
+drm_gem_object_unreference_unlocked(struct drm_gem_object *obj)
+{
+	if (obj && !atomic_add_unless(&obj->refcount.refcount, -1, 1)) {
+		struct drm_device *dev = obj->dev;
+
+		mutex_lock(&dev->struct_mutex);
+		if (likely(atomic_dec_and_test(&obj->refcount.refcount)))
+			drm_gem_object_free(&obj->refcount);
+		mutex_unlock(&dev->struct_mutex);
+	}
+}
+
+int drm_gem_handle_create(struct drm_file *file_priv,
+			  struct drm_gem_object *obj,
+			  u32 *handlep);
+int drm_gem_handle_delete(struct drm_file *filp, u32 handle);
+
+
+void drm_gem_free_mmap_offset(struct drm_gem_object *obj);
+int drm_gem_create_mmap_offset(struct drm_gem_object *obj);
+int drm_gem_create_mmap_offset_size(struct drm_gem_object *obj, size_t size);
+
+struct page **drm_gem_get_pages(struct drm_gem_object *obj);
+void drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages,
+		bool dirty, bool accessed);
+
+struct drm_gem_object *drm_gem_object_lookup(struct drm_device *dev,
+					     struct drm_file *filp,
+					     u32 handle);
+int drm_gem_dumb_destroy(struct drm_file *file,
+			 struct drm_device *dev,
+			 uint32_t handle);
+
+#endif /* __DRM_GEM_H__ */
diff --git a/include/drm/drm_gem_cma_helper.h b/include/drm/drm_gem_cma_helper.h
index 2a3cea91606d..2ff35f3de9c5 100644
--- a/include/drm/drm_gem_cma_helper.h
+++ b/include/drm/drm_gem_cma_helper.h
@@ -2,6 +2,7 @@
 #define __DRM_GEM_CMA_HELPER_H__
 
 #include <drm/drmP.h>
+#include <drm/drm_gem.h>
 
 struct drm_gem_cma_object {
 	struct drm_gem_object base;
@@ -44,7 +45,8 @@ void drm_gem_cma_describe(struct drm_gem_cma_object *obj, struct seq_file *m);
 
 struct sg_table *drm_gem_cma_prime_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *
-drm_gem_cma_prime_import_sg_table(struct drm_device *dev, size_t size,
+drm_gem_cma_prime_import_sg_table(struct drm_device *dev,
+				  struct dma_buf_attachment *attach,
 				  struct sg_table *sgt);
 int drm_gem_cma_prime_mmap(struct drm_gem_object *obj,
 			   struct vm_area_struct *vma);
diff --git a/include/drm/drm_legacy.h b/include/drm/drm_legacy.h
new file mode 100644
index 000000000000..3e698038dc7b
--- /dev/null
+++ b/include/drm/drm_legacy.h
@@ -0,0 +1,203 @@
+#ifndef __DRM_DRM_LEGACY_H__
+#define __DRM_DRM_LEGACY_H__
+
+/*
+ * Legacy driver interfaces for the Direct Rendering Manager
+ *
+ * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
+ * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
+ * Copyright (c) 2009-2010, Code Aurora Forum.
+ * All rights reserved.
+ * Copyright © 2014 Intel Corporation
+ *   Daniel Vetter <daniel.vetter@ffwll.ch>
+ *
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
+ * Author: Gareth Hughes <gareth@valinux.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+
+/*
+ * Legacy Support for palateontologic DRM drivers
+ *
+ * If you add a new driver and it uses any of these functions or structures,
+ * you're doing it terribly wrong.
+ */
+
+/**
+ * DMA buffer.
+ */
+struct drm_buf {
+	int idx;		       /**< Index into master buflist */
+	int total;		       /**< Buffer size */
+	int order;		       /**< log-base-2(total) */
+	int used;		       /**< Amount of buffer in use (for DMA) */
+	unsigned long offset;	       /**< Byte offset (used internally) */
+	void *address;		       /**< Address of buffer */
+	unsigned long bus_address;     /**< Bus address of buffer */
+	struct drm_buf *next;	       /**< Kernel-only: used for free list */
+	__volatile__ int waiting;      /**< On kernel DMA queue */
+	__volatile__ int pending;      /**< On hardware DMA queue */
+	struct drm_file *file_priv;    /**< Private of holding file descr */
+	int context;		       /**< Kernel queue for this buffer */
+	int while_locked;	       /**< Dispatch this buffer while locked */
+	enum {
+		DRM_LIST_NONE = 0,
+		DRM_LIST_FREE = 1,
+		DRM_LIST_WAIT = 2,
+		DRM_LIST_PEND = 3,
+		DRM_LIST_PRIO = 4,
+		DRM_LIST_RECLAIM = 5
+	} list;			       /**< Which list we're on */
+
+	int dev_priv_size;		 /**< Size of buffer private storage */
+	void *dev_private;		 /**< Per-buffer private storage */
+};
+
+typedef struct drm_dma_handle {
+	dma_addr_t busaddr;
+	void *vaddr;
+	size_t size;
+} drm_dma_handle_t;
+
+/**
+ * Buffer entry.  There is one of this for each buffer size order.
+ */
+struct drm_buf_entry {
+	int buf_size;			/**< size */
+	int buf_count;			/**< number of buffers */
+	struct drm_buf *buflist;		/**< buffer list */
+	int seg_count;
+	int page_order;
+	struct drm_dma_handle **seglist;
+
+	int low_mark;			/**< Low water mark */
+	int high_mark;			/**< High water mark */
+};
+
+/**
+ * DMA data.
+ */
+struct drm_device_dma {
+
+	struct drm_buf_entry bufs[DRM_MAX_ORDER + 1];	/**< buffers, grouped by their size order */
+	int buf_count;			/**< total number of buffers */
+	struct drm_buf **buflist;		/**< Vector of pointers into drm_device_dma::bufs */
+	int seg_count;
+	int page_count;			/**< number of pages */
+	unsigned long *pagelist;	/**< page list */
+	unsigned long byte_count;
+	enum {
+		_DRM_DMA_USE_AGP = 0x01,
+		_DRM_DMA_USE_SG = 0x02,
+		_DRM_DMA_USE_FB = 0x04,
+		_DRM_DMA_USE_PCI_RO = 0x08
+	} flags;
+
+};
+
+/**
+ * Scatter-gather memory.
+ */
+struct drm_sg_mem {
+	unsigned long handle;
+	void *virtual;
+	int pages;
+	struct page **pagelist;
+	dma_addr_t *busaddr;
+};
+
+/**
+ * Kernel side of a mapping
+ */
+struct drm_local_map {
+	resource_size_t offset;	 /**< Requested physical address (0 for SAREA)*/
+	unsigned long size;	 /**< Requested physical size (bytes) */
+	enum drm_map_type type;	 /**< Type of memory to map */
+	enum drm_map_flags flags;	 /**< Flags */
+	void *handle;		 /**< User-space: "Handle" to pass to mmap() */
+				 /**< Kernel-space: kernel-virtual address */
+	int mtrr;		 /**< MTRR slot used */
+};
+
+typedef struct drm_local_map drm_local_map_t;
+
+/**
+ * Mappings list
+ */
+struct drm_map_list {
+	struct list_head head;		/**< list head */
+	struct drm_hash_item hash;
+	struct drm_local_map *map;	/**< mapping */
+	uint64_t user_token;
+	struct drm_master *master;
+};
+
+int drm_legacy_addmap(struct drm_device *d, resource_size_t offset,
+		      unsigned int size, enum drm_map_type type,
+		      enum drm_map_flags flags, struct drm_local_map **map_p);
+int drm_legacy_rmmap(struct drm_device *d, struct drm_local_map *map);
+int drm_legacy_rmmap_locked(struct drm_device *d, struct drm_local_map *map);
+struct drm_local_map *drm_legacy_getsarea(struct drm_device *dev);
+int drm_legacy_mmap(struct file *filp, struct vm_area_struct *vma);
+
+int drm_legacy_addbufs_agp(struct drm_device *d, struct drm_buf_desc *req);
+int drm_legacy_addbufs_pci(struct drm_device *d, struct drm_buf_desc *req);
+
+/**
+ * Test that the hardware lock is held by the caller, returning otherwise.
+ *
+ * \param dev DRM device.
+ * \param filp file pointer of the caller.
+ */
+#define LOCK_TEST_WITH_RETURN( dev, _file_priv )				\
+do {										\
+	if (!_DRM_LOCK_IS_HELD(_file_priv->master->lock.hw_lock->lock) ||	\
+	    _file_priv->master->lock.file_priv != _file_priv)	{		\
+		DRM_ERROR( "%s called without lock held, held  %d owner %p %p\n",\
+			   __func__, _DRM_LOCK_IS_HELD(_file_priv->master->lock.hw_lock->lock),\
+			   _file_priv->master->lock.file_priv, _file_priv);	\
+		return -EINVAL;							\
+	}									\
+} while (0)
+
+void drm_legacy_idlelock_take(struct drm_lock_data *lock);
+void drm_legacy_idlelock_release(struct drm_lock_data *lock);
+
+/* drm_pci.c dma alloc wrappers */
+void __drm_legacy_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
+
+/* drm_memory.c */
+void drm_legacy_ioremap(struct drm_local_map *map, struct drm_device *dev);
+void drm_legacy_ioremap_wc(struct drm_local_map *map, struct drm_device *dev);
+void drm_legacy_ioremapfree(struct drm_local_map *map, struct drm_device *dev);
+
+static __inline__ struct drm_local_map *drm_legacy_findmap(struct drm_device *dev,
+							   unsigned int token)
+{
+	struct drm_map_list *_entry;
+	list_for_each_entry(_entry, &dev->maplist, head)
+	    if (_entry->user_token == token)
+		return _entry->map;
+	return NULL;
+}
+
+#endif /* __DRM_DRM_LEGACY_H__ */
diff --git a/include/drm/drm_memory.h b/include/drm/drm_memory.h
deleted file mode 100644
index 4baf57a207e7..000000000000
--- a/include/drm/drm_memory.h
+++ /dev/null
@@ -1,59 +0,0 @@
-/**
- * \file drm_memory.h
- * Memory management wrappers for DRM
- *
- * \author Rickard E. (Rik) Faith <faith@valinux.com>
- * \author Gareth Hughes <gareth@valinux.com>
- */
-
-/*
- * Created: Thu Feb  4 14:00:34 1999 by faith@valinux.com
- *
- * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
- * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
- * All Rights Reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- */
-
-#include <linux/highmem.h>
-#include <linux/vmalloc.h>
-#include <drm/drmP.h>
-
-/**
- * Cut down version of drm_memory_debug.h, which used to be called
- * drm_memory.h.
- */
-
-#if __OS_HAS_AGP
-
-#ifdef HAVE_PAGE_AGP
-#include <asm/agp.h>
-#else
-# ifdef __powerpc__
-#  define PAGE_AGP	__pgprot(_PAGE_KERNEL | _PAGE_NO_CACHE)
-# else
-#  define PAGE_AGP	PAGE_KERNEL
-# endif
-#endif
-
-#else				/* __OS_HAS_AGP */
-
-#endif
diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h
index 2bb55b8b9031..8569dc5a1026 100644
--- a/include/drm/drm_mipi_dsi.h
+++ b/include/drm/drm_mipi_dsi.h
@@ -96,6 +96,8 @@ void mipi_dsi_host_unregister(struct mipi_dsi_host *host);
 #define MIPI_DSI_MODE_EOT_PACKET	BIT(9)
 /* device supports non-continuous clock behavior (DSI spec 5.6.1) */
 #define MIPI_DSI_CLOCK_NON_CONTINUOUS	BIT(10)
+/* transmit data in low power */
+#define MIPI_DSI_MODE_LPM		BIT(11)
 
 enum mipi_dsi_pixel_format {
 	MIPI_DSI_FMT_RGB888,
diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h
index 402aa7a6a058..75a5c45e21c7 100644
--- a/include/drm/drm_modeset_lock.h
+++ b/include/drm/drm_modeset_lock.h
@@ -29,7 +29,7 @@
 struct drm_modeset_lock;
 
 /**
- * drm_modeset_acquire_ctx - locking context (see ww_acquire_ctx)
+ * struct drm_modeset_acquire_ctx - locking context (see ww_acquire_ctx)
  * @ww_ctx: base acquire ctx
  * @contended: used internally for -EDEADLK handling
  * @locked: list of held locks
@@ -53,10 +53,15 @@ struct drm_modeset_acquire_ctx {
 	 * list of held locks (drm_modeset_lock)
 	 */
 	struct list_head locked;
+
+	/**
+	 * Trylock mode, use only for panic handlers!
+	 */
+	bool trylock_only;
 };
 
 /**
- * drm_modeset_lock - used for locking modeset resources.
+ * struct drm_modeset_lock - used for locking modeset resources.
  * @mutex: resource locking
  * @head: used to hold it's place on state->locked list when
  *    part of an atomic update
@@ -120,6 +125,17 @@ int drm_modeset_lock_interruptible(struct drm_modeset_lock *lock,
 void drm_modeset_unlock(struct drm_modeset_lock *lock);
 
 struct drm_device;
+struct drm_crtc;
+
+void drm_modeset_lock_all(struct drm_device *dev);
+int __drm_modeset_lock_all(struct drm_device *dev, bool trylock);
+void drm_modeset_unlock_all(struct drm_device *dev);
+void drm_modeset_lock_crtc(struct drm_crtc *crtc);
+void drm_modeset_unlock_crtc(struct drm_crtc *crtc);
+void drm_warn_on_modeset_not_all_locked(struct drm_device *dev);
+struct drm_modeset_acquire_ctx *
+drm_modeset_legacy_acquire_ctx(struct drm_crtc *crtc);
+
 int drm_modeset_lock_all_crtcs(struct drm_device *dev,
 		struct drm_modeset_acquire_ctx *ctx);
 
diff --git a/include/drm/drm_usb.h b/include/drm/drm_usb.h
deleted file mode 100644
index 33506c11da8b..000000000000
--- a/include/drm/drm_usb.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef DRM_USB_H
-#define DRM_USB_H
-
-#include <drmP.h>
-
-#include <linux/usb.h>
-
-extern int drm_usb_init(struct drm_driver *driver, struct usb_driver *udriver);
-extern void drm_usb_exit(struct drm_driver *driver, struct usb_driver *udriver);
-
-int drm_get_usb_dev(struct usb_interface *interface,
-		    const struct usb_device_id *id,
-		    struct drm_driver *driver);
-
-#endif
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 7526c5bf5610..0ccf7f267ff9 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -45,12 +45,24 @@ struct ttm_bo_device;
 
 struct drm_mm_node;
 
+/**
+ * struct ttm_place
+ *
+ * @fpfn:	first valid page frame number to put the object
+ * @lpfn:	last valid page frame number to put the object
+ * @flags:	memory domain and caching flags for the object
+ *
+ * Structure indicating a possible place to put an object.
+ */
+struct ttm_place {
+	unsigned	fpfn;
+	unsigned	lpfn;
+	uint32_t	flags;
+};
 
 /**
  * struct ttm_placement
  *
- * @fpfn:		first valid page frame number to put the object
- * @lpfn:		last valid page frame number to put the object
  * @num_placement:	number of preferred placements
  * @placement:		preferred placements
  * @num_busy_placement:	number of preferred placements when need to evict buffer
@@ -59,12 +71,10 @@ struct drm_mm_node;
  * Structure indicating the placement you request for an object.
  */
 struct ttm_placement {
-	unsigned	fpfn;
-	unsigned	lpfn;
-	unsigned	num_placement;
-	const uint32_t	*placement;
-	unsigned	num_busy_placement;
-	const uint32_t	*busy_placement;
+	unsigned		num_placement;
+	const struct ttm_place	*placement;
+	unsigned		num_busy_placement;
+	const struct ttm_place	*busy_placement;
 };
 
 /**
@@ -163,7 +173,6 @@ struct ttm_tt;
  * @lru: List head for the lru list.
  * @ddestroy: List head for the delayed destroy list.
  * @swap: List head for swap LRU list.
- * @sync_obj: Pointer to a synchronization object.
  * @priv_flags: Flags describing buffer object internal state.
  * @vma_node: Address space manager node.
  * @offset: The current GPU offset, which can have different meanings
@@ -227,13 +236,9 @@ struct ttm_buffer_object {
 	struct list_head io_reserve_lru;
 
 	/**
-	 * Members protected by struct buffer_object_device::fence_lock
-	 * In addition, setting sync_obj to anything else
-	 * than NULL requires bo::reserved to be held. This allows for
-	 * checking NULL while reserved but not holding the mentioned lock.
+	 * Members protected by a bo reservation.
 	 */
 
-	void *sync_obj;
 	unsigned long priv_flags;
 
 	struct drm_vma_offset_node vma_node;
@@ -455,6 +460,7 @@ size_t ttm_bo_dma_acc_size(struct ttm_bo_device *bdev,
  * point to the shmem object backing a GEM object if TTM is used to back a
  * GEM user interface.
  * @acc_size: Accounted size for this object.
+ * @resv: Pointer to a reservation_object, or NULL to let ttm allocate one.
  * @destroy: Destroy function. Use NULL for kfree().
  *
  * This function initializes a pre-allocated struct ttm_buffer_object.
@@ -482,6 +488,7 @@ extern int ttm_bo_init(struct ttm_bo_device *bdev,
 			struct file *persistent_swap_storage,
 			size_t acc_size,
 			struct sg_table *sg,
+			struct reservation_object *resv,
 			void (*destroy) (struct ttm_buffer_object *));
 
 /**
@@ -519,20 +526,6 @@ extern int ttm_bo_create(struct ttm_bo_device *bdev,
 				struct ttm_buffer_object **p_bo);
 
 /**
- * ttm_bo_check_placement
- *
- * @bo:		the buffer object.
- * @placement:	placements
- *
- * Performs minimal validity checking on an intended change of
- * placement flags.
- * Returns
- * -EINVAL: Intended change is invalid or not allowed.
- */
-extern int ttm_bo_check_placement(struct ttm_buffer_object *bo,
-					struct ttm_placement *placement);
-
-/**
  * ttm_bo_init_mm
  *
  * @bdev: Pointer to a ttm_bo_device struct.
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 1d9f0f1ff52d..142d752fc450 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -208,8 +208,7 @@ struct ttm_mem_type_manager_func {
 	 */
 	int  (*get_node)(struct ttm_mem_type_manager *man,
 			 struct ttm_buffer_object *bo,
-			 struct ttm_placement *placement,
-			 uint32_t flags,
+			 const struct ttm_place *place,
 			 struct ttm_mem_reg *mem);
 
 	/**
@@ -313,11 +312,6 @@ struct ttm_mem_type_manager {
  * @move: Callback for a driver to hook in accelerated functions to
  * move a buffer.
  * If set to NULL, a potentially slow memcpy() move is used.
- * @sync_obj_signaled: See ttm_fence_api.h
- * @sync_obj_wait: See ttm_fence_api.h
- * @sync_obj_flush: See ttm_fence_api.h
- * @sync_obj_unref: See ttm_fence_api.h
- * @sync_obj_ref: See ttm_fence_api.h
  */
 
 struct ttm_bo_driver {
@@ -419,23 +413,6 @@ struct ttm_bo_driver {
 	int (*verify_access) (struct ttm_buffer_object *bo,
 			      struct file *filp);
 
-	/**
-	 * In case a driver writer dislikes the TTM fence objects,
-	 * the driver writer can replace those with sync objects of
-	 * his / her own. If it turns out that no driver writer is
-	 * using these. I suggest we remove these hooks and plug in
-	 * fences directly. The bo driver needs the following functionality:
-	 * See the corresponding functions in the fence object API
-	 * documentation.
-	 */
-
-	bool (*sync_obj_signaled) (void *sync_obj);
-	int (*sync_obj_wait) (void *sync_obj,
-			      bool lazy, bool interruptible);
-	int (*sync_obj_flush) (void *sync_obj);
-	void (*sync_obj_unref) (void **sync_obj);
-	void *(*sync_obj_ref) (void *sync_obj);
-
 	/* hook to notify driver about a driver move so it
 	 * can do tiling things */
 	void (*move_notify)(struct ttm_buffer_object *bo,
@@ -522,8 +499,6 @@ struct ttm_bo_global {
  *
  * @driver: Pointer to a struct ttm_bo_driver struct setup by the driver.
  * @man: An array of mem_type_managers.
- * @fence_lock: Protects the synchronizing members on *all* bos belonging
- * to this device.
  * @vma_manager: Address space manager
  * lru_lock: Spinlock that protects the buffer+device lru lists and
  * ddestroy lists.
@@ -543,7 +518,6 @@ struct ttm_bo_device {
 	struct ttm_bo_global *glob;
 	struct ttm_bo_driver *driver;
 	struct ttm_mem_type_manager man[TTM_NUM_MEM_TYPES];
-	spinlock_t fence_lock;
 
 	/*
 	 * Protected by internal locks.
@@ -1026,7 +1000,7 @@ extern void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  * ttm_bo_move_accel_cleanup.
  *
  * @bo: A pointer to a struct ttm_buffer_object.
- * @sync_obj: A sync object that signals when moving is complete.
+ * @fence: A fence object that signals when moving is complete.
  * @evict: This is an evict move. Don't return until the buffer is idle.
  * @no_wait_gpu: Return immediately if the GPU is busy.
  * @new_mem: struct ttm_mem_reg indicating where to move.
@@ -1040,7 +1014,7 @@ extern void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  */
 
 extern int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
-				     void *sync_obj,
+				     struct fence *fence,
 				     bool evict, bool no_wait_gpu,
 				     struct ttm_mem_reg *new_mem);
 /**
diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h
index 16db7d01a336..460441714413 100644
--- a/include/drm/ttm/ttm_execbuf_util.h
+++ b/include/drm/ttm/ttm_execbuf_util.h
@@ -39,19 +39,13 @@
  *
  * @head:           list head for thread-private list.
  * @bo:             refcounted buffer object pointer.
- * @reserved:       Indicates whether @bo has been reserved for validation.
- * @removed:        Indicates whether @bo has been removed from lru lists.
- * @put_count:      Number of outstanding references on bo::list_kref.
- * @old_sync_obj:   Pointer to a sync object about to be unreferenced
+ * @shared:         should the fence be added shared?
  */
 
 struct ttm_validate_buffer {
 	struct list_head head;
 	struct ttm_buffer_object *bo;
-	bool reserved;
-	bool removed;
-	int put_count;
-	void *old_sync_obj;
+	bool shared;
 };
 
 /**
@@ -73,6 +67,7 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
  * @ticket:  [out] ww_acquire_ctx filled in by call, or NULL if only
  *           non-blocking reserves should be tried.
  * @list:    thread private list of ttm_validate_buffer structs.
+ * @intr:    should the wait be interruptible
  *
  * Tries to reserve bos pointed to by the list entries for validation.
  * If the function returns 0, all buffers are marked as "unfenced",
@@ -84,9 +79,9 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
  * CPU write reservations to be cleared, and for other threads to
  * unreserve their buffers.
  *
- * This function may return -ERESTART or -EAGAIN if the calling process
- * receives a signal while waiting. In that case, no buffers on the list
- * will be reserved upon return.
+ * If intr is set to true, this function may return -ERESTARTSYS if the
+ * calling process receives a signal while waiting. In that case, no
+ * buffers on the list will be reserved upon return.
  *
  * Buffers reserved by this function should be unreserved by
  * a call to either ttm_eu_backoff_reservation() or
@@ -95,14 +90,14 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
  */
 
 extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
-				  struct list_head *list);
+				  struct list_head *list, bool intr);
 
 /**
  * function ttm_eu_fence_buffer_objects.
  *
  * @ticket:      ww_acquire_ctx from reserve call
  * @list:        thread private list of ttm_validate_buffer structs.
- * @sync_obj:    The new sync object for the buffers.
+ * @fence:       The new exclusive fence for the buffers.
  *
  * This function should be called when command submission is complete, and
  * it will add a new sync object to bos pointed to by entries on @list.
@@ -111,6 +106,7 @@ extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
  */
 
 extern void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
-					struct list_head *list, void *sync_obj);
+					struct list_head *list,
+					struct fence *fence);
 
 #endif
diff --git a/include/dt-bindings/clock/exynos3250.h b/include/dt-bindings/clock/exynos3250.h
index b535e9da7de6..961b9c130ea9 100644
--- a/include/dt-bindings/clock/exynos3250.h
+++ b/include/dt-bindings/clock/exynos3250.h
@@ -255,4 +255,31 @@
  */
 #define CLK_NR_CLKS			248
 
+/*
+ * CMU DMC
+ */
+
+#define CLK_FOUT_BPLL			1
+#define CLK_FOUT_EPLL			2
+
+/* Muxes */
+#define CLK_MOUT_MPLL_MIF		8
+#define CLK_MOUT_BPLL			9
+#define CLK_MOUT_DPHY			10
+#define CLK_MOUT_DMC_BUS		11
+#define CLK_MOUT_EPLL			12
+
+/* Dividers */
+#define CLK_DIV_DMC			16
+#define CLK_DIV_DPHY			17
+#define CLK_DIV_DMC_PRE			18
+#define CLK_DIV_DMCP			19
+#define CLK_DIV_DMCD			20
+
+/*
+ * Total number of clocks of main CMU.
+ * NOTE: Must be equal to last clock ID increased by one.
+ */
+#define NR_CLKS_DMC			21
+
 #endif /* _DT_BINDINGS_CLOCK_SAMSUNG_EXYNOS3250_CLOCK_H */
diff --git a/include/dt-bindings/clock/exynos4.h b/include/dt-bindings/clock/exynos4.h
index 459bd2bd411f..34fe28c622d0 100644
--- a/include/dt-bindings/clock/exynos4.h
+++ b/include/dt-bindings/clock/exynos4.h
@@ -115,11 +115,11 @@
 #define CLK_SMMU_MFCR		275
 #define CLK_G3D			276
 #define CLK_G2D			277
-#define CLK_ROTATOR		278 /* Exynos4210 only */
-#define CLK_MDMA		279 /* Exynos4210 only */
-#define CLK_SMMU_G2D		280 /* Exynos4210 only */
-#define CLK_SMMU_ROTATOR	281 /* Exynos4210 only */
-#define CLK_SMMU_MDMA		282 /* Exynos4210 only */
+#define CLK_ROTATOR		278
+#define CLK_MDMA		279
+#define CLK_SMMU_G2D		280
+#define CLK_SMMU_ROTATOR	281
+#define CLK_SMMU_MDMA		282
 #define CLK_FIMD0		283
 #define CLK_MIE0		284
 #define CLK_MDNIE0		285 /* Exynos4412 only */
@@ -234,6 +234,8 @@
 #define CLK_MOUT_G3D1		393
 #define CLK_MOUT_G3D		394
 #define CLK_ACLK400_MCUISP	395 /* Exynos4x12 only */
+#define CLK_MOUT_HDMI		396
+#define CLK_MOUT_MIXER		397
 
 /* gate clocks - ppmu */
 #define CLK_PPMULEFT		400
diff --git a/include/dt-bindings/clock/hix5hd2-clock.h b/include/dt-bindings/clock/hix5hd2-clock.h
index aad579a75802..fd29c174ba63 100644
--- a/include/dt-bindings/clock/hix5hd2-clock.h
+++ b/include/dt-bindings/clock/hix5hd2-clock.h
@@ -46,6 +46,7 @@
 #define HIX5HD2_SFC_MUX			64
 #define HIX5HD2_MMC_MUX			65
 #define HIX5HD2_FEPHY_MUX		66
+#define HIX5HD2_SD_MUX			67
 
 /* gate clocks */
 #define HIX5HD2_SFC_RST			128
@@ -53,6 +54,32 @@
 #define HIX5HD2_MMC_CIU_CLK		130
 #define HIX5HD2_MMC_BIU_CLK		131
 #define HIX5HD2_MMC_CIU_RST		132
+#define HIX5HD2_FWD_BUS_CLK		133
+#define HIX5HD2_FWD_SYS_CLK		134
+#define HIX5HD2_MAC0_PHY_CLK		135
+#define HIX5HD2_SD_CIU_CLK		136
+#define HIX5HD2_SD_BIU_CLK		137
+#define HIX5HD2_SD_CIU_RST		138
+#define HIX5HD2_WDG0_CLK		139
+#define HIX5HD2_WDG0_RST		140
+#define HIX5HD2_I2C0_CLK		141
+#define HIX5HD2_I2C0_RST		142
+#define HIX5HD2_I2C1_CLK		143
+#define HIX5HD2_I2C1_RST		144
+#define HIX5HD2_I2C2_CLK		145
+#define HIX5HD2_I2C2_RST		146
+#define HIX5HD2_I2C3_CLK		147
+#define HIX5HD2_I2C3_RST		148
+#define HIX5HD2_I2C4_CLK		149
+#define HIX5HD2_I2C4_RST		150
+#define HIX5HD2_I2C5_CLK		151
+#define HIX5HD2_I2C5_RST		152
+
+/* complex */
+#define HIX5HD2_MAC0_CLK		192
+#define HIX5HD2_MAC1_CLK		193
+#define HIX5HD2_SATA_CLK		194
+#define HIX5HD2_USB_CLK			195
 
 #define HIX5HD2_NR_CLKS			256
 #endif	/* __DTS_HIX5HD2_CLOCK_H */
diff --git a/include/dt-bindings/clock/maxim,max77686.h b/include/dt-bindings/clock/maxim,max77686.h
new file mode 100644
index 000000000000..7b28b0905869
--- /dev/null
+++ b/include/dt-bindings/clock/maxim,max77686.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2014 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Device Tree binding constants clocks for the Maxim 77686 PMIC.
+ */
+
+#ifndef _DT_BINDINGS_CLOCK_MAXIM_MAX77686_CLOCK_H
+#define _DT_BINDINGS_CLOCK_MAXIM_MAX77686_CLOCK_H
+
+/* Fixed rate clocks. */
+
+#define MAX77686_CLK_AP		0
+#define MAX77686_CLK_CP		1
+#define MAX77686_CLK_PMIC	2
+
+/* Total number of clocks. */
+#define MAX77686_CLKS_NUM		(MAX77686_CLK_PMIC + 1)
+
+#endif /* _DT_BINDINGS_CLOCK_MAXIM_MAX77686_CLOCK_H */
diff --git a/include/dt-bindings/clock/maxim,max77802.h b/include/dt-bindings/clock/maxim,max77802.h
new file mode 100644
index 000000000000..997312edcbb5
--- /dev/null
+++ b/include/dt-bindings/clock/maxim,max77802.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2014 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Device Tree binding constants clocks for the Maxim 77802 PMIC.
+ */
+
+#ifndef _DT_BINDINGS_CLOCK_MAXIM_MAX77802_CLOCK_H
+#define _DT_BINDINGS_CLOCK_MAXIM_MAX77802_CLOCK_H
+
+/* Fixed rate clocks. */
+
+#define MAX77802_CLK_32K_AP		0
+#define MAX77802_CLK_32K_CP		1
+
+/* Total number of clocks. */
+#define MAX77802_CLKS_NUM		(MAX77802_CLK_32K_CP + 1)
+
+#endif /* _DT_BINDINGS_CLOCK_MAXIM_MAX77802_CLOCK_H */
diff --git a/include/dt-bindings/clock/pxa-clock.h b/include/dt-bindings/clock/pxa-clock.h
new file mode 100644
index 000000000000..e65803b1dc7e
--- /dev/null
+++ b/include/dt-bindings/clock/pxa-clock.h
@@ -0,0 +1,77 @@
+/*
+ * Inspired by original work from pxa2xx-regs.h by Nicolas Pitre
+ * Copyright (C) 2014 Robert Jarzmik
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_PXA2XX_H__
+#define __DT_BINDINGS_CLOCK_PXA2XX_H__
+
+#define CLK_NONE 0
+#define CLK_1WIRE 1
+#define CLK_AC97 2
+#define CLK_AC97CONF 3
+#define CLK_ASSP 4
+#define CLK_BOOT 5
+#define CLK_BTUART 6
+#define CLK_CAMERA 7
+#define CLK_CIR 8
+#define CLK_CORE 9
+#define CLK_DMC 10
+#define CLK_FFUART 11
+#define CLK_FICP 12
+#define CLK_GPIO 13
+#define CLK_HSIO2 14
+#define CLK_HWUART 15
+#define CLK_I2C 16
+#define CLK_I2S 17
+#define CLK_IM 18
+#define CLK_INC 19
+#define CLK_ISC 20
+#define CLK_KEYPAD 21
+#define CLK_LCD 22
+#define CLK_MEMC 23
+#define CLK_MEMSTK 24
+#define CLK_MINI_IM 25
+#define CLK_MINI_LCD 26
+#define CLK_MMC 27
+#define CLK_MMC1 28
+#define CLK_MMC2 29
+#define CLK_MMC3 30
+#define CLK_MSL 31
+#define CLK_MSL0 32
+#define CLK_MVED 33
+#define CLK_NAND 34
+#define CLK_NSSP 35
+#define CLK_OSTIMER 36
+#define CLK_PWM0 37
+#define CLK_PWM1 38
+#define CLK_PWM2 39
+#define CLK_PWM3 40
+#define CLK_PWRI2C 41
+#define CLK_PXA300_GCU 42
+#define CLK_PXA320_GCU 43
+#define CLK_SMC 44
+#define CLK_SSP 45
+#define CLK_SSP1 46
+#define CLK_SSP2 47
+#define CLK_SSP3 48
+#define CLK_SSP4 49
+#define CLK_STUART 50
+#define CLK_TOUCH 51
+#define CLK_TPM 52
+#define CLK_UDC 53
+#define CLK_USB 54
+#define CLK_USB2 55
+#define CLK_USBH 56
+#define CLK_USBHOST 57
+#define CLK_USIM 58
+#define CLK_USIM1 59
+#define CLK_USMI0 60
+#define CLK_MAX 61
+
+#endif
diff --git a/include/dt-bindings/clock/rk3188-cru-common.h b/include/dt-bindings/clock/rk3188-cru-common.h
index 750ee60e75fb..6a370503c954 100644
--- a/include/dt-bindings/clock/rk3188-cru-common.h
+++ b/include/dt-bindings/clock/rk3188-cru-common.h
@@ -20,6 +20,7 @@
 #define PLL_GPLL		4
 #define CORE_PERI		5
 #define CORE_L2C		6
+#define ARMCLK			7
 
 /* sclk gates (special clocks) */
 #define SCLK_UART0		64
diff --git a/include/dt-bindings/clock/rk3288-cru.h b/include/dt-bindings/clock/rk3288-cru.h
index ebcb460ea4ad..100a08c47692 100644
--- a/include/dt-bindings/clock/rk3288-cru.h
+++ b/include/dt-bindings/clock/rk3288-cru.h
@@ -19,6 +19,7 @@
 #define PLL_CPLL		3
 #define PLL_GPLL		4
 #define PLL_NPLL		5
+#define ARMCLK			6
 
 /* sclk gates (special clocks) */
 #define SCLK_GPU		64
@@ -61,6 +62,15 @@
 #define SCLK_LCDC_PWM1		101
 #define SCLK_MAC_RX		102
 #define SCLK_MAC_TX		103
+#define SCLK_EDP_24M		104
+#define SCLK_EDP		105
+#define SCLK_RGA		106
+#define SCLK_ISP		107
+#define SCLK_ISP_JPE		108
+#define SCLK_HDMI_HDCP		109
+#define SCLK_HDMI_CEC		110
+#define SCLK_HEVC_CABAC		111
+#define SCLK_HEVC_CORE		112
 
 #define DCLK_VOP0		190
 #define DCLK_VOP1		191
@@ -75,6 +85,16 @@
 #define ACLK_VOP1		198
 #define ACLK_CRYPTO		199
 #define ACLK_RGA		200
+#define ACLK_RGA_NIU		201
+#define ACLK_IEP		202
+#define ACLK_VIO0_NIU		203
+#define ACLK_VIP		204
+#define ACLK_ISP		205
+#define ACLK_VIO1_NIU		206
+#define ACLK_HEVC		207
+#define ACLK_VCODEC		208
+#define ACLK_CPU		209
+#define ACLK_PERI		210
 
 /* pclk gates */
 #define PCLK_GPIO0		320
@@ -112,6 +132,15 @@
 #define PCLK_PS2C		352
 #define PCLK_TIMER		353
 #define PCLK_TZPC		354
+#define PCLK_EDP_CTRL		355
+#define PCLK_MIPI_DSI0		356
+#define PCLK_MIPI_DSI1		357
+#define PCLK_MIPI_CSI		358
+#define PCLK_LVDS_PHY		359
+#define PCLK_HDMI_CTRL		360
+#define PCLK_VIO2_H2P		361
+#define PCLK_CPU		362
+#define PCLK_PERI		363
 
 /* hclk gates */
 #define HCLK_GPS		448
@@ -137,8 +166,16 @@
 #define HCLK_IEP		468
 #define HCLK_ISP		469
 #define HCLK_RGA		470
+#define HCLK_VIO_AHB_ARBI	471
+#define HCLK_VIO_NIU		472
+#define HCLK_VIP		473
+#define HCLK_VIO2_H2P		474
+#define HCLK_HEVC		475
+#define HCLK_VCODEC		476
+#define HCLK_CPU		477
+#define HCLK_PERI		478
 
-#define CLK_NR_CLKS		(HCLK_RGA + 1)
+#define CLK_NR_CLKS		(HCLK_PERI + 1)
 
 /* soft-reset indices */
 #define SRST_CORE0		0
@@ -276,3 +313,46 @@
 #define SRST_USBHOST1_CON	140
 #define SRST_USB_ADP		141
 #define SRST_ACC_EFUSE		142
+
+#define SRST_CORESIGHT		144
+#define SRST_PD_CORE_AHB_NOC	145
+#define SRST_PD_CORE_APB_NOC	146
+#define SRST_PD_CORE_MP_AXI	147
+#define SRST_GIC		148
+#define SRST_LCDC_PWM0		149
+#define SRST_LCDC_PWM1		150
+#define SRST_VIO0_H2P_BRG	151
+#define SRST_VIO1_H2P_BRG	152
+#define SRST_RGA_H2P_BRG	153
+#define SRST_HEVC		154
+#define SRST_TSADC		159
+
+#define SRST_DDRPHY0		160
+#define SRST_DDRPHY0_APB	161
+#define SRST_DDRCTRL0		162
+#define SRST_DDRCTRL0_APB	163
+#define SRST_DDRPHY0_CTRL	164
+#define SRST_DDRPHY1		165
+#define SRST_DDRPHY1_APB	166
+#define SRST_DDRCTRL1		167
+#define SRST_DDRCTRL1_APB	168
+#define SRST_DDRPHY1_CTRL	169
+#define SRST_DDRMSCH0		170
+#define SRST_DDRMSCH1		171
+#define SRST_CRYPTO		174
+#define SRST_C2C_HOST		175
+
+#define SRST_LCDC1_AXI		176
+#define SRST_LCDC1_AHB		177
+#define SRST_LCDC1_DCLK		178
+#define SRST_UART0		179
+#define SRST_UART1		180
+#define SRST_UART2		181
+#define SRST_UART3		182
+#define SRST_UART4		183
+#define SRST_SIMC		186
+#define SRST_PS2C		187
+#define SRST_TSP		188
+#define SRST_TSP_CLKIN0		189
+#define SRST_TSP_CLKIN1		190
+#define SRST_TSP_27M		191
diff --git a/include/dt-bindings/clock/rockchip,rk808.h b/include/dt-bindings/clock/rockchip,rk808.h
new file mode 100644
index 000000000000..1a873432f965
--- /dev/null
+++ b/include/dt-bindings/clock/rockchip,rk808.h
@@ -0,0 +1,11 @@
+/*
+ * This header provides constants clk index RK808 pmic clkout
+ */
+#ifndef _CLK_ROCKCHIP_RK808
+#define _CLK_ROCKCHIP_RK808
+
+/* CLOCKOUT index */
+#define RK808_CLKOUT0		0
+#define RK808_CLKOUT1		1
+
+#endif
diff --git a/include/dt-bindings/clock/tegra124-car.h b/include/dt-bindings/clock/tegra124-car.h
index 8a4c5892890f..6bac637fd635 100644
--- a/include/dt-bindings/clock/tegra124-car.h
+++ b/include/dt-bindings/clock/tegra124-car.h
@@ -337,6 +337,10 @@
 #define TEGRA124_CLK_DSIB_MUX 310
 #define TEGRA124_CLK_SOR0_LVDS 311
 #define TEGRA124_CLK_XUSB_SS_DIV2 312
-#define TEGRA124_CLK_CLK_MAX 313
+
+#define TEGRA124_CLK_PLL_M_UD 313
+#define TEGRA124_CLK_PLL_C_UD 314
+
+#define TEGRA124_CLK_CLK_MAX 315
 
 #endif	/* _DT_BINDINGS_CLOCK_TEGRA124_CAR_H */
diff --git a/include/dt-bindings/sound/cs35l32.h b/include/dt-bindings/sound/cs35l32.h
new file mode 100644
index 000000000000..0c6d6a3c15a2
--- /dev/null
+++ b/include/dt-bindings/sound/cs35l32.h
@@ -0,0 +1,26 @@
+#ifndef __DT_CS35L32_H
+#define __DT_CS35L32_H
+
+#define CS35L32_BOOST_MGR_AUTO		0
+#define CS35L32_BOOST_MGR_AUTO_AUDIO	1
+#define CS35L32_BOOST_MGR_BYPASS	2
+#define CS35L32_BOOST_MGR_FIXED		3
+
+#define CS35L32_DATA_CFG_LR_VP		0
+#define CS35L32_DATA_CFG_LR_STAT	1
+#define CS35L32_DATA_CFG_LR		2
+#define CS35L32_DATA_CFG_LR_VPSTAT	3
+
+#define CS35L32_BATT_THRESH_3_1V	0
+#define CS35L32_BATT_THRESH_3_2V	1
+#define CS35L32_BATT_THRESH_3_3V	2
+#define CS35L32_BATT_THRESH_3_4V	3
+
+#define CS35L32_BATT_RECOV_3_1V		0
+#define CS35L32_BATT_RECOV_3_2V		1
+#define CS35L32_BATT_RECOV_3_3V		2
+#define CS35L32_BATT_RECOV_3_4V		3
+#define CS35L32_BATT_RECOV_3_5V		4
+#define CS35L32_BATT_RECOV_3_6V		5
+
+#endif /* __DT_CS35L32_H */
diff --git a/include/keys/asymmetric-type.h b/include/keys/asymmetric-type.h
index 7dd473496180..c0754abb2f56 100644
--- a/include/keys/asymmetric-type.h
+++ b/include/keys/asymmetric-type.h
@@ -19,6 +19,47 @@
 extern struct key_type key_type_asymmetric;
 
 /*
+ * Identifiers for an asymmetric key ID.  We have three ways of looking up a
+ * key derived from an X.509 certificate:
+ *
+ * (1) Serial Number & Issuer.  Non-optional.  This is the only valid way to
+ *     map a PKCS#7 signature to an X.509 certificate.
+ *
+ * (2) Issuer & Subject Unique IDs.  Optional.  These were the original way to
+ *     match X.509 certificates, but have fallen into disuse in favour of (3).
+ *
+ * (3) Auth & Subject Key Identifiers.  Optional.  SKIDs are only provided on
+ *     CA keys that are intended to sign other keys, so don't appear in end
+ *     user certificates unless forced.
+ *
+ * We could also support an PGP key identifier, which is just a SHA1 sum of the
+ * public key and certain parameters, but since we don't support PGP keys at
+ * the moment, we shall ignore those.
+ *
+ * What we actually do is provide a place where binary identifiers can be
+ * stashed and then compare against them when checking for an id match.
+ */
+struct asymmetric_key_id {
+	unsigned short	len;
+	unsigned char	data[];
+};
+
+struct asymmetric_key_ids {
+	void		*id[2];
+};
+
+extern bool asymmetric_key_id_same(const struct asymmetric_key_id *kid1,
+				   const struct asymmetric_key_id *kid2);
+
+extern bool asymmetric_key_id_partial(const struct asymmetric_key_id *kid1,
+				      const struct asymmetric_key_id *kid2);
+
+extern struct asymmetric_key_id *asymmetric_key_generate_id(const void *val_1,
+							    size_t len_1,
+							    const void *val_2,
+							    size_t len_2);
+
+/*
  * The payload is at the discretion of the subtype.
  */
 
diff --git a/include/keys/user-type.h b/include/keys/user-type.h
index 3ab1873a4bfa..cebefb069c44 100644
--- a/include/keys/user-type.h
+++ b/include/keys/user-type.h
@@ -40,7 +40,6 @@ struct key_preparsed_payload;
 extern int user_preparse(struct key_preparsed_payload *prep);
 extern void user_free_preparse(struct key_preparsed_payload *prep);
 extern int user_update(struct key *key, struct key_preparsed_payload *prep);
-extern int user_match(const struct key *key, const void *criterion);
 extern void user_revoke(struct key *key);
 extern void user_destroy(struct key *key);
 extern void user_describe(const struct key *user, struct seq_file *m);
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 2f2aac8448a4..206dcc3b3f7a 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -219,8 +219,8 @@ struct vgic_v2_cpu_if {
 	u32		vgic_hcr;
 	u32		vgic_vmcr;
 	u32		vgic_misr;	/* Saved only */
-	u32		vgic_eisr[2];	/* Saved only */
-	u32		vgic_elrsr[2];	/* Saved only */
+	u64		vgic_eisr;	/* Saved only */
+	u64		vgic_elrsr;	/* Saved only */
 	u32		vgic_apr;
 	u32		vgic_lr[VGIC_V2_MAX_LRS];
 };
@@ -331,6 +331,14 @@ static inline int kvm_vgic_create(struct kvm *kvm)
 	return 0;
 }
 
+static inline void kvm_vgic_destroy(struct kvm *kvm)
+{
+}
+
+static inline void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+}
+
 static inline int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	return 0;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 807cbc46d73e..b7926bb9b444 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -587,7 +587,6 @@ static inline int acpi_subsys_freeze(struct device *dev) { return 0; }
 #if defined(CONFIG_ACPI) && defined(CONFIG_PM)
 struct acpi_device *acpi_dev_pm_get_node(struct device *dev);
 int acpi_dev_pm_attach(struct device *dev, bool power_on);
-void acpi_dev_pm_detach(struct device *dev, bool power_off);
 #else
 static inline struct acpi_device *acpi_dev_pm_get_node(struct device *dev)
 {
@@ -597,7 +596,6 @@ static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
 {
 	return -ENODEV;
 }
-static inline void acpi_dev_pm_detach(struct device *dev, bool power_off) {}
 #endif
 
 #ifdef CONFIG_ACPI
diff --git a/include/linux/aer.h b/include/linux/aer.h
index c826d1c28f9c..4fef65e57023 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -7,6 +7,8 @@
 #ifndef _AER_H_
 #define _AER_H_
 
+#include <linux/types.h>
+
 #define AER_NONFATAL			0
 #define AER_FATAL			1
 #define AER_CORRECTABLE			2
diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h
index 09a947e8bc87..642d6ae4030c 100644
--- a/include/linux/ahci_platform.h
+++ b/include/linux/ahci_platform.h
@@ -22,19 +22,6 @@ struct ata_port_info;
 struct ahci_host_priv;
 struct platform_device;
 
-/*
- * Note ahci_platform_data is deprecated, it is only kept around for use
- * by the old da850 and spear13xx ahci code.
- * New drivers should instead declare their own platform_driver struct, and
- * use ahci_platform* functions in their own probe, suspend and resume methods.
- */
-struct ahci_platform_data {
-	int (*init)(struct device *dev, void __iomem *addr);
-	void (*exit)(struct device *dev);
-	int (*suspend)(struct device *dev);
-	int (*resume)(struct device *dev);
-};
-
 int ahci_platform_enable_clks(struct ahci_host_priv *hpriv);
 void ahci_platform_disable_clks(struct ahci_host_priv *hpriv);
 int ahci_platform_enable_resources(struct ahci_host_priv *hpriv);
diff --git a/include/linux/ata_platform.h b/include/linux/ata_platform.h
index b9fde17f767c..5c618a084225 100644
--- a/include/linux/ata_platform.h
+++ b/include/linux/ata_platform.h
@@ -8,11 +8,6 @@ struct pata_platform_info {
 	 * spacing used by ata_std_ports().
 	 */
 	unsigned int ioport_shift;
-	/* 
-	 * Indicate platform specific irq types and initial
-	 * IRQ flags when call request_irq()
-	 */
-	unsigned int irq_flags;
 };
 
 extern int __pata_platform_probe(struct device *dev,
diff --git a/include/linux/atmel-mci.h b/include/linux/atmel-mci.h
index 4c7a4b2104bf..91b77f8d495d 100644
--- a/include/linux/atmel-mci.h
+++ b/include/linux/atmel-mci.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_ATMEL_MCI_H
 #define __LINUX_ATMEL_MCI_H
 
+#include <linux/types.h>
+
 #define ATMCI_MAX_NR_SLOTS	2
 
 /**
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index fef3a809e7cf..5b08a8540ecf 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -3,42 +3,6 @@
 #define _LINUX_ATOMIC_H
 #include <asm/atomic.h>
 
-/*
- * Provide __deprecated wrappers for the new interface, avoid flag day changes.
- * We need the ugly external functions to break header recursion hell.
- */
-#ifndef smp_mb__before_atomic_inc
-static inline void __deprecated smp_mb__before_atomic_inc(void)
-{
-	extern void __smp_mb__before_atomic(void);
-	__smp_mb__before_atomic();
-}
-#endif
-
-#ifndef smp_mb__after_atomic_inc
-static inline void __deprecated smp_mb__after_atomic_inc(void)
-{
-	extern void __smp_mb__after_atomic(void);
-	__smp_mb__after_atomic();
-}
-#endif
-
-#ifndef smp_mb__before_atomic_dec
-static inline void __deprecated smp_mb__before_atomic_dec(void)
-{
-	extern void __smp_mb__before_atomic(void);
-	__smp_mb__before_atomic();
-}
-#endif
-
-#ifndef smp_mb__after_atomic_dec
-static inline void __deprecated smp_mb__after_atomic_dec(void)
-{
-	extern void __smp_mb__after_atomic(void);
-	__smp_mb__after_atomic();
-}
-#endif
-
 /**
  * atomic_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index e488e9459a93..5da6012b7a14 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -28,12 +28,10 @@ struct dentry;
  * Bits in backing_dev_info.state
  */
 enum bdi_state {
-	BDI_wb_alloc,		/* Default embedded wb allocated */
 	BDI_async_congested,	/* The async (write) queue is getting full */
 	BDI_sync_congested,	/* The sync queue is getting full */
 	BDI_registered,		/* bdi_register() was done */
 	BDI_writeback_running,	/* Writeback is in progress */
-	BDI_unused,		/* Available bits start here */
 };
 
 typedef int (congested_fn)(void *, int);
@@ -50,7 +48,6 @@ enum bdi_stat_item {
 
 struct bdi_writeback {
 	struct backing_dev_info *bdi;	/* our parent bdi */
-	unsigned int nr;
 
 	unsigned long last_old_flush;	/* last old data flush */
 
@@ -124,7 +121,6 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi);
 void bdi_writeback_workfn(struct work_struct *work);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
 void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
-void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2);
 
 extern spinlock_t bdi_lock;
 extern struct list_head bdi_list;
diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index 089743ade734..9b0a15d06a4f 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -27,10 +27,13 @@
  *      counter raised only while it is under our special handling;
  *
  * iii. after the lockless scan step have selected a potential balloon page for
- *      isolation, re-test the page->mapping flags and the page ref counter
+ *      isolation, re-test the PageBalloon mark and the PagePrivate flag
  *      under the proper page lock, to ensure isolating a valid balloon page
  *      (not yet isolated, nor under release procedure)
  *
+ *  iv. isolation or dequeueing procedure must clear PagePrivate flag under
+ *      page lock together with removing page from balloon device page list.
+ *
  * The functions provided by this interface are placed to help on coping with
  * the aforementioned balloon page corner case, as well as to ensure the simple
  * set of exposed rules are satisfied while we are dealing with balloon pages
@@ -54,43 +57,22 @@
  * balloon driver as a page book-keeper for its registered balloon devices.
  */
 struct balloon_dev_info {
-	void *balloon_device;		/* balloon device descriptor */
-	struct address_space *mapping;	/* balloon special page->mapping */
 	unsigned long isolated_pages;	/* # of isolated pages for migration */
 	spinlock_t pages_lock;		/* Protection to pages list */
 	struct list_head pages;		/* Pages enqueued & handled to Host */
+	int (*migratepage)(struct balloon_dev_info *, struct page *newpage,
+			struct page *page, enum migrate_mode mode);
 };
 
 extern struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info);
 extern struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info);
-extern struct balloon_dev_info *balloon_devinfo_alloc(
-						void *balloon_dev_descriptor);
 
-static inline void balloon_devinfo_free(struct balloon_dev_info *b_dev_info)
-{
-	kfree(b_dev_info);
-}
-
-/*
- * balloon_page_free - release a balloon page back to the page free lists
- * @page: ballooned page to be set free
- *
- * This function must be used to properly set free an isolated/dequeued balloon
- * page at the end of a sucessful page migration, or at the balloon driver's
- * page release procedure.
- */
-static inline void balloon_page_free(struct page *page)
+static inline void balloon_devinfo_init(struct balloon_dev_info *balloon)
 {
-	/*
-	 * Balloon pages always get an extra refcount before being isolated
-	 * and before being dequeued to help on sorting out fortuite colisions
-	 * between a thread attempting to isolate and another thread attempting
-	 * to release the very same balloon page.
-	 *
-	 * Before we handle the page back to Buddy, lets drop its extra refcnt.
-	 */
-	put_page(page);
-	__free_page(page);
+	balloon->isolated_pages = 0;
+	spin_lock_init(&balloon->pages_lock);
+	INIT_LIST_HEAD(&balloon->pages);
+	balloon->migratepage = NULL;
 }
 
 #ifdef CONFIG_BALLOON_COMPACTION
@@ -98,107 +80,58 @@ extern bool balloon_page_isolate(struct page *page);
 extern void balloon_page_putback(struct page *page);
 extern int balloon_page_migrate(struct page *newpage,
 				struct page *page, enum migrate_mode mode);
-extern struct address_space
-*balloon_mapping_alloc(struct balloon_dev_info *b_dev_info,
-			const struct address_space_operations *a_ops);
-
-static inline void balloon_mapping_free(struct address_space *balloon_mapping)
-{
-	kfree(balloon_mapping);
-}
 
 /*
- * page_flags_cleared - helper to perform balloon @page ->flags tests.
- *
- * As balloon pages are obtained from buddy and we do not play with page->flags
- * at driver level (exception made when we get the page lock for compaction),
- * we can safely identify a ballooned page by checking if the
- * PAGE_FLAGS_CHECK_AT_PREP page->flags are all cleared.  This approach also
- * helps us skip ballooned pages that are locked for compaction or release, thus
- * mitigating their racy check at balloon_page_movable()
- */
-static inline bool page_flags_cleared(struct page *page)
-{
-	return !(page->flags & PAGE_FLAGS_CHECK_AT_PREP);
-}
-
-/*
- * __is_movable_balloon_page - helper to perform @page mapping->flags tests
+ * __is_movable_balloon_page - helper to perform @page PageBalloon tests
  */
 static inline bool __is_movable_balloon_page(struct page *page)
 {
-	struct address_space *mapping = page->mapping;
-	return mapping_balloon(mapping);
+	return PageBalloon(page);
 }
 
 /*
- * balloon_page_movable - test page->mapping->flags to identify balloon pages
- *			  that can be moved by compaction/migration.
- *
- * This function is used at core compaction's page isolation scheme, therefore
- * most pages exposed to it are not enlisted as balloon pages and so, to avoid
- * undesired side effects like racing against __free_pages(), we cannot afford
- * holding the page locked while testing page->mapping->flags here.
+ * balloon_page_movable - test PageBalloon to identify balloon pages
+ *			  and PagePrivate to check that the page is not
+ *			  isolated and can be moved by compaction/migration.
  *
  * As we might return false positives in the case of a balloon page being just
- * released under us, the page->mapping->flags need to be re-tested later,
- * under the proper page lock, at the functions that will be coping with the
- * balloon page case.
+ * released under us, this need to be re-tested later, under the page lock.
  */
 static inline bool balloon_page_movable(struct page *page)
 {
-	/*
-	 * Before dereferencing and testing mapping->flags, let's make sure
-	 * this is not a page that uses ->mapping in a different way
-	 */
-	if (page_flags_cleared(page) && !page_mapped(page) &&
-	    page_count(page) == 1)
-		return __is_movable_balloon_page(page);
-
-	return false;
+	return PageBalloon(page) && PagePrivate(page);
 }
 
 /*
  * isolated_balloon_page - identify an isolated balloon page on private
  *			   compaction/migration page lists.
- *
- * After a compaction thread isolates a balloon page for migration, it raises
- * the page refcount to prevent concurrent compaction threads from re-isolating
- * the same page. For that reason putback_movable_pages(), or other routines
- * that need to identify isolated balloon pages on private pagelists, cannot
- * rely on balloon_page_movable() to accomplish the task.
  */
 static inline bool isolated_balloon_page(struct page *page)
 {
-	/* Already isolated balloon pages, by default, have a raised refcount */
-	if (page_flags_cleared(page) && !page_mapped(page) &&
-	    page_count(page) >= 2)
-		return __is_movable_balloon_page(page);
-
-	return false;
+	return PageBalloon(page);
 }
 
 /*
  * balloon_page_insert - insert a page into the balloon's page list and make
- *		         the page->mapping assignment accordingly.
+ *			 the page->private assignment accordingly.
+ * @balloon : pointer to balloon device
  * @page    : page to be assigned as a 'balloon page'
- * @mapping : allocated special 'balloon_mapping'
- * @head    : balloon's device page list head
  *
  * Caller must ensure the page is locked and the spin_lock protecting balloon
  * pages list is held before inserting a page into the balloon device.
  */
-static inline void balloon_page_insert(struct page *page,
-				       struct address_space *mapping,
-				       struct list_head *head)
+static inline void balloon_page_insert(struct balloon_dev_info *balloon,
+				       struct page *page)
 {
-	page->mapping = mapping;
-	list_add(&page->lru, head);
+	__SetPageBalloon(page);
+	SetPagePrivate(page);
+	set_page_private(page, (unsigned long)balloon);
+	list_add(&page->lru, &balloon->pages);
 }
 
 /*
  * balloon_page_delete - delete a page from balloon's page list and clear
- *			 the page->mapping assignement accordingly.
+ *			 the page->private assignement accordingly.
  * @page    : page to be released from balloon's page list
  *
  * Caller must ensure the page is locked and the spin_lock protecting balloon
@@ -206,8 +139,12 @@ static inline void balloon_page_insert(struct page *page,
  */
 static inline void balloon_page_delete(struct page *page)
 {
-	page->mapping = NULL;
-	list_del(&page->lru);
+	__ClearPageBalloon(page);
+	set_page_private(page, 0);
+	if (PagePrivate(page)) {
+		ClearPagePrivate(page);
+		list_del(&page->lru);
+	}
 }
 
 /*
@@ -216,11 +153,7 @@ static inline void balloon_page_delete(struct page *page)
  */
 static inline struct balloon_dev_info *balloon_page_device(struct page *page)
 {
-	struct address_space *mapping = page->mapping;
-	if (likely(mapping))
-		return mapping->private_data;
-
-	return NULL;
+	return (struct balloon_dev_info *)page_private(page);
 }
 
 static inline gfp_t balloon_mapping_gfp_mask(void)
@@ -228,34 +161,24 @@ static inline gfp_t balloon_mapping_gfp_mask(void)
 	return GFP_HIGHUSER_MOVABLE;
 }
 
-static inline bool balloon_compaction_check(void)
-{
-	return true;
-}
-
 #else /* !CONFIG_BALLOON_COMPACTION */
 
-static inline void *balloon_mapping_alloc(void *balloon_device,
-				const struct address_space_operations *a_ops)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
-static inline void balloon_mapping_free(struct address_space *balloon_mapping)
+static inline void balloon_page_insert(struct balloon_dev_info *balloon,
+				       struct page *page)
 {
-	return;
+	__SetPageBalloon(page);
+	list_add(&page->lru, &balloon->pages);
 }
 
-static inline void balloon_page_insert(struct page *page,
-				       struct address_space *mapping,
-				       struct list_head *head)
+static inline void balloon_page_delete(struct page *page)
 {
-	list_add(&page->lru, head);
+	__ClearPageBalloon(page);
+	list_del(&page->lru);
 }
 
-static inline void balloon_page_delete(struct page *page)
+static inline bool __is_movable_balloon_page(struct page *page)
 {
-	list_del(&page->lru);
+	return false;
 }
 
 static inline bool balloon_page_movable(struct page *page)
@@ -289,9 +212,5 @@ static inline gfp_t balloon_mapping_gfp_mask(void)
 	return GFP_HIGHUSER;
 }
 
-static inline bool balloon_compaction_check(void)
-{
-	return false;
-}
 #endif /* CONFIG_BALLOON_COMPACTION */
 #endif /* _LINUX_BALLOON_COMPACTION_H */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b39e5000ff58..7347f486ceca 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -292,7 +292,24 @@ static inline unsigned bio_segments(struct bio *bio)
  */
 #define bio_get(bio)	atomic_inc(&(bio)->bi_cnt)
 
+enum bip_flags {
+	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
+	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
+	BIP_CTRL_NOCHECK	= 1 << 2, /* disable HBA integrity checking */
+	BIP_DISK_NOCHECK	= 1 << 3, /* disable disk integrity checking */
+	BIP_IP_CHECKSUM		= 1 << 4, /* IP checksum */
+};
+
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
+
+static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
+{
+	if (bio->bi_rw & REQ_INTEGRITY)
+		return bio->bi_integrity;
+
+	return NULL;
+}
+
 /*
  * bio integrity payload
  */
@@ -301,21 +318,40 @@ struct bio_integrity_payload {
 
 	struct bvec_iter	bip_iter;
 
-	/* kill - should just use bip_vec */
-	void			*bip_buf;	/* generated integrity data */
-
 	bio_end_io_t		*bip_end_io;	/* saved I/O completion fn */
 
 	unsigned short		bip_slab;	/* slab the bip came from */
 	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
 	unsigned short		bip_max_vcnt;	/* integrity bio_vec slots */
-	unsigned		bip_owns_buf:1;	/* should free bip_buf */
+	unsigned short		bip_flags;	/* control flags */
 
 	struct work_struct	bip_work;	/* I/O completion */
 
 	struct bio_vec		*bip_vec;
 	struct bio_vec		bip_inline_vecs[0];/* embedded bvec array */
 };
+
+static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
+{
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+
+	if (bip)
+		return bip->bip_flags & flag;
+
+	return false;
+}
+
+static inline sector_t bip_get_seed(struct bio_integrity_payload *bip)
+{
+	return bip->bip_iter.bi_sector;
+}
+
+static inline void bip_set_seed(struct bio_integrity_payload *bip,
+				sector_t seed)
+{
+	bip->bip_iter.bi_sector = seed;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 extern void bio_trim(struct bio *bio, int offset, int size);
@@ -342,6 +378,7 @@ static inline struct bio *bio_next_split(struct bio *bio, int sectors,
 }
 
 extern struct bio_set *bioset_create(unsigned int, unsigned int);
+extern struct bio_set *bioset_create_nobvec(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
 extern mempool_t *biovec_create_pool(int pool_entries);
 
@@ -353,7 +390,6 @@ extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
 extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
 
 extern struct bio_set *fs_bio_set;
-unsigned int bio_integrity_tag_size(struct bio *bio);
 
 static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 {
@@ -661,14 +697,10 @@ struct biovec_slab {
 	for_each_bio(_bio)						\
 		bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
 
-#define bio_integrity(bio) (bio->bi_integrity != NULL)
-
 extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
 extern void bio_integrity_free(struct bio *);
 extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
-extern int bio_integrity_enabled(struct bio *bio);
-extern int bio_integrity_set_tag(struct bio *, void *, unsigned int);
-extern int bio_integrity_get_tag(struct bio *, void *, unsigned int);
+extern bool bio_integrity_enabled(struct bio *bio);
 extern int bio_integrity_prep(struct bio *);
 extern void bio_integrity_endio(struct bio *, int);
 extern void bio_integrity_advance(struct bio *, unsigned int);
@@ -680,14 +712,14 @@ extern void bio_integrity_init(void);
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
-static inline int bio_integrity(struct bio *bio)
+static inline void *bio_integrity(struct bio *bio)
 {
-	return 0;
+	return NULL;
 }
 
-static inline int bio_integrity_enabled(struct bio *bio)
+static inline bool bio_integrity_enabled(struct bio *bio)
 {
-	return 0;
+	return false;
 }
 
 static inline int bioset_integrity_create(struct bio_set *bs, int pool_size)
@@ -733,6 +765,11 @@ static inline void bio_integrity_init(void)
 	return;
 }
 
+static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
+{
+	return false;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 #endif /* CONFIG_BLOCK */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index cbc5833fb221..be5fd38bd5a0 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -32,26 +32,6 @@ extern unsigned long __sw_hweight64(__u64 w);
  */
 #include <asm/bitops.h>
 
-/*
- * Provide __deprecated wrappers for the new interface, avoid flag day changes.
- * We need the ugly external functions to break header recursion hell.
- */
-#ifndef smp_mb__before_clear_bit
-static inline void __deprecated smp_mb__before_clear_bit(void)
-{
-	extern void __smp_mb__before_atomic(void);
-	__smp_mb__before_atomic();
-}
-#endif
-
-#ifndef smp_mb__after_clear_bit
-static inline void __deprecated smp_mb__after_clear_bit(void)
-{
-	extern void __smp_mb__after_atomic(void);
-	__smp_mb__after_atomic();
-}
-#endif
-
 #define for_each_set_bit(bit, addr, size) \
 	for ((bit) = find_first_bit((addr), (size));		\
 	     (bit) < (size);					\
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index a1e31f274fcd..c9be1589415a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -4,6 +4,7 @@
 #include <linux/blkdev.h>
 
 struct blk_mq_tags;
+struct blk_flush_queue;
 
 struct blk_mq_cpu_notifier {
 	struct list_head list;
@@ -34,6 +35,7 @@ struct blk_mq_hw_ctx {
 
 	struct request_queue	*queue;
 	unsigned int		queue_num;
+	struct blk_flush_queue	*fq;
 
 	void			*driver_data;
 
@@ -77,8 +79,9 @@ struct blk_mq_tag_set {
 	struct list_head	tag_list;
 };
 
-typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, struct request *);
+typedef int (queue_rq_fn)(struct blk_mq_hw_ctx *, struct request *, bool);
 typedef struct blk_mq_hw_ctx *(map_queue_fn)(struct request_queue *, const int);
+typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
 typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
 typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
 typedef int (init_request_fn)(void *, struct request *, unsigned int,
@@ -86,6 +89,9 @@ typedef int (init_request_fn)(void *, struct request *, unsigned int,
 typedef void (exit_request_fn)(void *, struct request *, unsigned int,
 		unsigned int);
 
+typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
+		bool);
+
 struct blk_mq_ops {
 	/*
 	 * Queue request
@@ -100,7 +106,7 @@ struct blk_mq_ops {
 	/*
 	 * Called on request timeout
 	 */
-	rq_timed_out_fn		*timeout;
+	timeout_fn		*timeout;
 
 	softirq_done_fn		*complete;
 
@@ -115,6 +121,10 @@ struct blk_mq_ops {
 	/*
 	 * Called for every command allocated by the block layer to allow
 	 * the driver to set up driver specific data.
+	 *
+	 * Tag greater than or equal to queue_depth is for setting up
+	 * flush request.
+	 *
 	 * Ditto for exit/teardown.
 	 */
 	init_request_fn		*init_request;
@@ -140,6 +150,7 @@ enum {
 };
 
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
+void blk_mq_finish_init(struct request_queue *q);
 int blk_mq_register_disk(struct gendisk *);
 void blk_mq_unregister_disk(struct gendisk *);
 
@@ -159,8 +170,9 @@ struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
 struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
 
-void blk_mq_end_io(struct request *rq, int error);
-void __blk_mq_end_io(struct request *rq, int error);
+void blk_mq_start_request(struct request *rq);
+void blk_mq_end_request(struct request *rq, int error);
+void __blk_mq_end_request(struct request *rq, int error);
 
 void blk_mq_requeue_request(struct request *rq);
 void blk_mq_add_to_requeue_list(struct request *rq, bool at_head);
@@ -173,7 +185,8 @@ void blk_mq_stop_hw_queues(struct request_queue *q);
 void blk_mq_start_hw_queues(struct request_queue *q);
 void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
-void blk_mq_tag_busy_iter(struct blk_mq_tags *tags, void (*fn)(void *data, unsigned long *), void *data);
+void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
+		void *priv);
 
 /*
  * Driver command data is immediately after the request. So subtract request
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 66c2167f04a9..445d59231bc4 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -78,9 +78,11 @@ struct bio {
 	struct io_context	*bi_ioc;
 	struct cgroup_subsys_state *bi_css;
 #endif
+	union {
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
-	struct bio_integrity_payload *bi_integrity;  /* data integrity */
+		struct bio_integrity_payload *bi_integrity; /* data integrity */
 #endif
+	};
 
 	unsigned short		bi_vcnt;	/* how many bio_vec's */
 
@@ -118,10 +120,8 @@ struct bio {
 #define BIO_USER_MAPPED 6	/* contains user pages */
 #define BIO_EOPNOTSUPP	7	/* not supported */
 #define BIO_NULL_MAPPED 8	/* contains invalid user pages */
-#define BIO_FS_INTEGRITY 9	/* fs owns integrity data, not block layer */
-#define BIO_QUIET	10	/* Make BIO Quiet */
-#define BIO_MAPPED_INTEGRITY 11/* integrity metadata has been remapped */
-#define BIO_SNAP_STABLE	12	/* bio data must be snapshotted during write */
+#define BIO_QUIET	9	/* Make BIO Quiet */
+#define BIO_SNAP_STABLE	10	/* bio data must be snapshotted during write */
 
 /*
  * Flags starting here get preserved by bio_reset() - this includes
@@ -162,6 +162,7 @@ enum rq_flag_bits {
 	__REQ_WRITE_SAME,	/* write same block many times */
 
 	__REQ_NOIDLE,		/* don't anticipate more IO after this one */
+	__REQ_INTEGRITY,	/* I/O includes block integrity payload */
 	__REQ_FUA,		/* forced unit access */
 	__REQ_FLUSH,		/* request for cache flush */
 
@@ -186,9 +187,7 @@ enum rq_flag_bits {
 	__REQ_FLUSH_SEQ,	/* request for flush sequence */
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
-	__REQ_KERNEL, 		/* direct IO to kernel pages */
 	__REQ_PM,		/* runtime pm request */
-	__REQ_END,		/* last of chain of requests */
 	__REQ_HASHED,		/* on IO scheduler merge hash */
 	__REQ_MQ_INFLIGHT,	/* track inflight for MQ */
 	__REQ_NR_BITS,		/* stops here */
@@ -204,13 +203,14 @@ enum rq_flag_bits {
 #define REQ_DISCARD		(1ULL << __REQ_DISCARD)
 #define REQ_WRITE_SAME		(1ULL << __REQ_WRITE_SAME)
 #define REQ_NOIDLE		(1ULL << __REQ_NOIDLE)
+#define REQ_INTEGRITY		(1ULL << __REQ_INTEGRITY)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
 	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \
 	 REQ_DISCARD | REQ_WRITE_SAME | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | \
-	 REQ_SECURE)
+	 REQ_SECURE | REQ_INTEGRITY)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
 
 #define BIO_NO_ADVANCE_ITER_MASK	(REQ_DISCARD|REQ_WRITE_SAME)
@@ -240,9 +240,7 @@ enum rq_flag_bits {
 #define REQ_IO_STAT		(1ULL << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE		(1ULL << __REQ_MIXED_MERGE)
 #define REQ_SECURE		(1ULL << __REQ_SECURE)
-#define REQ_KERNEL		(1ULL << __REQ_KERNEL)
 #define REQ_PM			(1ULL << __REQ_PM)
-#define REQ_END			(1ULL << __REQ_END)
 #define REQ_HASHED		(1ULL << __REQ_HASHED)
 #define REQ_MQ_INFLIGHT		(1ULL << __REQ_MQ_INFLIGHT)
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 518b46555b80..0207a78a8d82 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -36,6 +36,7 @@ struct request;
 struct sg_io_hdr;
 struct bsg_job;
 struct blkcg_gq;
+struct blk_flush_queue;
 
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
@@ -455,14 +456,7 @@ struct request_queue {
 	 */
 	unsigned int		flush_flags;
 	unsigned int		flush_not_queueable:1;
-	unsigned int		flush_queue_delayed:1;
-	unsigned int		flush_pending_idx:1;
-	unsigned int		flush_running_idx:1;
-	unsigned long		flush_pending_since;
-	struct list_head	flush_queue[2];
-	struct list_head	flush_data_in_flight;
-	struct request		*flush_rq;
-	spinlock_t		mq_flush_lock;
+	struct blk_flush_queue	*fq;
 
 	struct list_head	requeue_list;
 	spinlock_t		requeue_lock;
@@ -865,7 +859,7 @@ extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 {
-	return bdev->bd_disk->queue;
+	return bdev->bd_disk->queue;	/* this is never NULL */
 }
 
 /*
@@ -1285,10 +1279,9 @@ static inline int queue_alignment_offset(struct request_queue *q)
 static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
 {
 	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
-	unsigned int alignment = (sector << 9) & (granularity - 1);
+	unsigned int alignment = sector_div(sector, granularity >> 9) << 9;
 
-	return (granularity + lim->alignment_offset - alignment)
-		& (granularity - 1);
+	return (granularity + lim->alignment_offset - alignment) % granularity;
 }
 
 static inline int bdev_alignment_offset(struct block_device *bdev)
@@ -1464,32 +1457,31 @@ static inline uint64_t rq_io_start_time_ns(struct request *req)
 
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
-#define INTEGRITY_FLAG_READ	2	/* verify data integrity on read */
-#define INTEGRITY_FLAG_WRITE	4	/* generate data integrity on write */
+enum blk_integrity_flags {
+	BLK_INTEGRITY_VERIFY		= 1 << 0,
+	BLK_INTEGRITY_GENERATE		= 1 << 1,
+	BLK_INTEGRITY_DEVICE_CAPABLE	= 1 << 2,
+	BLK_INTEGRITY_IP_CHECKSUM	= 1 << 3,
+};
 
-struct blk_integrity_exchg {
+struct blk_integrity_iter {
 	void			*prot_buf;
 	void			*data_buf;
-	sector_t		sector;
+	sector_t		seed;
 	unsigned int		data_size;
-	unsigned short		sector_size;
+	unsigned short		interval;
 	const char		*disk_name;
 };
 
-typedef void (integrity_gen_fn) (struct blk_integrity_exchg *);
-typedef int (integrity_vrfy_fn) (struct blk_integrity_exchg *);
-typedef void (integrity_set_tag_fn) (void *, void *, unsigned int);
-typedef void (integrity_get_tag_fn) (void *, void *, unsigned int);
+typedef int (integrity_processing_fn) (struct blk_integrity_iter *);
 
 struct blk_integrity {
-	integrity_gen_fn	*generate_fn;
-	integrity_vrfy_fn	*verify_fn;
-	integrity_set_tag_fn	*set_tag_fn;
-	integrity_get_tag_fn	*get_tag_fn;
+	integrity_processing_fn	*generate_fn;
+	integrity_processing_fn	*verify_fn;
 
 	unsigned short		flags;
 	unsigned short		tuple_size;
-	unsigned short		sector_size;
+	unsigned short		interval;
 	unsigned short		tag_size;
 
 	const char		*name;
@@ -1504,10 +1496,10 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
 extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
 				   struct scatterlist *);
 extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
-extern int blk_integrity_merge_rq(struct request_queue *, struct request *,
-				  struct request *);
-extern int blk_integrity_merge_bio(struct request_queue *, struct request *,
-				   struct bio *);
+extern bool blk_integrity_merge_rq(struct request_queue *, struct request *,
+				   struct request *);
+extern bool blk_integrity_merge_bio(struct request_queue *, struct request *,
+				    struct bio *);
 
 static inline
 struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
@@ -1520,12 +1512,9 @@ static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 	return disk->integrity;
 }
 
-static inline int blk_integrity_rq(struct request *rq)
+static inline bool blk_integrity_rq(struct request *rq)
 {
-	if (rq->bio == NULL)
-		return 0;
-
-	return bio_integrity(rq->bio);
+	return rq->cmd_flags & REQ_INTEGRITY;
 }
 
 static inline void blk_queue_max_integrity_segments(struct request_queue *q,
@@ -1564,7 +1553,7 @@ static inline int blk_rq_map_integrity_sg(struct request_queue *q,
 }
 static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
 {
-	return 0;
+	return NULL;
 }
 static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 {
@@ -1590,15 +1579,15 @@ static inline unsigned short queue_max_integrity_segments(struct request_queue *
 {
 	return 0;
 }
-static inline int blk_integrity_merge_rq(struct request_queue *rq,
-					 struct request *r1,
-					 struct request *r2)
+static inline bool blk_integrity_merge_rq(struct request_queue *rq,
+					  struct request *r1,
+					  struct request *r2)
 {
 	return 0;
 }
-static inline int blk_integrity_merge_bio(struct request_queue *rq,
-					  struct request *r,
-					  struct bio *b)
+static inline bool blk_integrity_merge_bio(struct request_queue *rq,
+					   struct request *r,
+					   struct bio *b)
 {
 	return 0;
 }
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 279b0afac1c1..07bc359b88ac 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -211,7 +211,6 @@ extern struct page **ceph_get_direct_page_vector(const void __user *data,
 						 bool write_page);
 extern void ceph_put_page_vector(struct page **pages, int num_pages,
 				 bool dirty);
-extern void ceph_release_page_vector(struct page **pages, int num_pages);
 extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
 extern int ceph_copy_user_to_page_vector(struct page **pages,
 					 const void __user *data,
diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h
index 9660d6b0a35d..5f871d84ddce 100644
--- a/include/linux/ceph/pagelist.h
+++ b/include/linux/ceph/pagelist.h
@@ -2,6 +2,7 @@
 #define __FS_CEPH_PAGELIST_H
 
 #include <linux/list.h>
+#include <linux/atomic.h>
 
 struct ceph_pagelist {
 	struct list_head head;
@@ -10,6 +11,7 @@ struct ceph_pagelist {
 	size_t room;
 	struct list_head free_list;
 	size_t num_pages_free;
+	atomic_t refcnt;
 };
 
 struct ceph_pagelist_cursor {
@@ -26,9 +28,10 @@ static inline void ceph_pagelist_init(struct ceph_pagelist *pl)
 	pl->room = 0;
 	INIT_LIST_HEAD(&pl->free_list);
 	pl->num_pages_free = 0;
+	atomic_set(&pl->refcnt, 1);
 }
 
-extern int ceph_pagelist_release(struct ceph_pagelist *pl);
+extern void ceph_pagelist_release(struct ceph_pagelist *pl);
 
 extern int ceph_pagelist_append(struct ceph_pagelist *pl, const void *d, size_t l);
 
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index f20e0d8a2155..2f822dca1046 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -172,6 +172,7 @@ extern const char *ceph_osd_state_name(int s);
 #define CEPH_OSD_OP_MODE_WR    0x2000
 #define CEPH_OSD_OP_MODE_RMW   0x3000
 #define CEPH_OSD_OP_MODE_SUB   0x4000
+#define CEPH_OSD_OP_MODE_CACHE 0x8000
 
 #define CEPH_OSD_OP_TYPE       0x0f00
 #define CEPH_OSD_OP_TYPE_LOCK  0x0100
@@ -181,103 +182,135 @@ extern const char *ceph_osd_state_name(int s);
 #define CEPH_OSD_OP_TYPE_PG    0x0500
 #define CEPH_OSD_OP_TYPE_MULTI 0x0600 /* multiobject */
 
+#define __CEPH_OSD_OP1(mode, nr) \
+	(CEPH_OSD_OP_MODE_##mode | (nr))
+
+#define __CEPH_OSD_OP(mode, type, nr) \
+	(CEPH_OSD_OP_MODE_##mode | CEPH_OSD_OP_TYPE_##type | (nr))
+
+#define __CEPH_FORALL_OSD_OPS(f)					    \
+	/** data **/							    \
+	/* read */							    \
+	f(READ,		__CEPH_OSD_OP(RD, DATA, 1),	"read")		    \
+	f(STAT,		__CEPH_OSD_OP(RD, DATA, 2),	"stat")		    \
+	f(MAPEXT,	__CEPH_OSD_OP(RD, DATA, 3),	"mapext")	    \
+									    \
+	/* fancy read */						    \
+	f(MASKTRUNC,	__CEPH_OSD_OP(RD, DATA, 4),	"masktrunc")	    \
+	f(SPARSE_READ,	__CEPH_OSD_OP(RD, DATA, 5),	"sparse-read")	    \
+									    \
+	f(NOTIFY,	__CEPH_OSD_OP(RD, DATA, 6),	"notify")	    \
+	f(NOTIFY_ACK,	__CEPH_OSD_OP(RD, DATA, 7),	"notify-ack")	    \
+									    \
+	/* versioning */						    \
+	f(ASSERT_VER,	__CEPH_OSD_OP(RD, DATA, 8),	"assert-version")   \
+									    \
+	f(LIST_WATCHERS, __CEPH_OSD_OP(RD, DATA, 9),	"list-watchers")    \
+									    \
+	f(LIST_SNAPS,	__CEPH_OSD_OP(RD, DATA, 10),	"list-snaps")	    \
+									    \
+	/* sync */							    \
+	f(SYNC_READ,	__CEPH_OSD_OP(RD, DATA, 11),	"sync_read")	    \
+									    \
+	/* write */							    \
+	f(WRITE,	__CEPH_OSD_OP(WR, DATA, 1),	"write")	    \
+	f(WRITEFULL,	__CEPH_OSD_OP(WR, DATA, 2),	"writefull")	    \
+	f(TRUNCATE,	__CEPH_OSD_OP(WR, DATA, 3),	"truncate")	    \
+	f(ZERO,		__CEPH_OSD_OP(WR, DATA, 4),	"zero")		    \
+	f(DELETE,	__CEPH_OSD_OP(WR, DATA, 5),	"delete")	    \
+									    \
+	/* fancy write */						    \
+	f(APPEND,	__CEPH_OSD_OP(WR, DATA, 6),	"append")	    \
+	f(STARTSYNC,	__CEPH_OSD_OP(WR, DATA, 7),	"startsync")	    \
+	f(SETTRUNC,	__CEPH_OSD_OP(WR, DATA, 8),	"settrunc")	    \
+	f(TRIMTRUNC,	__CEPH_OSD_OP(WR, DATA, 9),	"trimtrunc")	    \
+									    \
+	f(TMAPUP,	__CEPH_OSD_OP(RMW, DATA, 10),	"tmapup")	    \
+	f(TMAPPUT,	__CEPH_OSD_OP(WR, DATA, 11),	"tmapput")	    \
+	f(TMAPGET,	__CEPH_OSD_OP(RD, DATA, 12),	"tmapget")	    \
+									    \
+	f(CREATE,	__CEPH_OSD_OP(WR, DATA, 13),	"create")	    \
+	f(ROLLBACK,	__CEPH_OSD_OP(WR, DATA, 14),	"rollback")	    \
+									    \
+	f(WATCH,	__CEPH_OSD_OP(WR, DATA, 15),	"watch")	    \
+									    \
+	/* omap */							    \
+	f(OMAPGETKEYS,	__CEPH_OSD_OP(RD, DATA, 17),	"omap-get-keys")    \
+	f(OMAPGETVALS,	__CEPH_OSD_OP(RD, DATA, 18),	"omap-get-vals")    \
+	f(OMAPGETHEADER, __CEPH_OSD_OP(RD, DATA, 19),	"omap-get-header")  \
+	f(OMAPGETVALSBYKEYS, __CEPH_OSD_OP(RD, DATA, 20), "omap-get-vals-by-keys") \
+	f(OMAPSETVALS,	__CEPH_OSD_OP(WR, DATA, 21),	"omap-set-vals")    \
+	f(OMAPSETHEADER, __CEPH_OSD_OP(WR, DATA, 22),	"omap-set-header")  \
+	f(OMAPCLEAR,	__CEPH_OSD_OP(WR, DATA, 23),	"omap-clear")	    \
+	f(OMAPRMKEYS,	__CEPH_OSD_OP(WR, DATA, 24),	"omap-rm-keys")	    \
+	f(OMAP_CMP,	__CEPH_OSD_OP(RD, DATA, 25),	"omap-cmp")	    \
+									    \
+	/* tiering */							    \
+	f(COPY_FROM,	__CEPH_OSD_OP(WR, DATA, 26),	"copy-from")	    \
+	f(COPY_GET_CLASSIC, __CEPH_OSD_OP(RD, DATA, 27), "copy-get-classic") \
+	f(UNDIRTY,	__CEPH_OSD_OP(WR, DATA, 28),	"undirty")	    \
+	f(ISDIRTY,	__CEPH_OSD_OP(RD, DATA, 29),	"isdirty")	    \
+	f(COPY_GET,	__CEPH_OSD_OP(RD, DATA, 30),	"copy-get")	    \
+	f(CACHE_FLUSH,	__CEPH_OSD_OP(CACHE, DATA, 31),	"cache-flush")	    \
+	f(CACHE_EVICT,	__CEPH_OSD_OP(CACHE, DATA, 32),	"cache-evict")	    \
+	f(CACHE_TRY_FLUSH, __CEPH_OSD_OP(CACHE, DATA, 33), "cache-try-flush") \
+									    \
+	/* convert tmap to omap */					    \
+	f(TMAP2OMAP,	__CEPH_OSD_OP(RMW, DATA, 34),	"tmap2omap")	    \
+									    \
+	/* hints */							    \
+	f(SETALLOCHINT,	__CEPH_OSD_OP(WR, DATA, 35),	"set-alloc-hint")   \
+									    \
+	/** multi **/							    \
+	f(CLONERANGE,	__CEPH_OSD_OP(WR, MULTI, 1),	"clonerange")	    \
+	f(ASSERT_SRC_VERSION, __CEPH_OSD_OP(RD, MULTI, 2), "assert-src-version") \
+	f(SRC_CMPXATTR,	__CEPH_OSD_OP(RD, MULTI, 3),	"src-cmpxattr")	    \
+									    \
+	/** attrs **/							    \
+	/* read */							    \
+	f(GETXATTR,	__CEPH_OSD_OP(RD, ATTR, 1),	"getxattr")	    \
+	f(GETXATTRS,	__CEPH_OSD_OP(RD, ATTR, 2),	"getxattrs")	    \
+	f(CMPXATTR,	__CEPH_OSD_OP(RD, ATTR, 3),	"cmpxattr")	    \
+									    \
+	/* write */							    \
+	f(SETXATTR,	__CEPH_OSD_OP(WR, ATTR, 1),	"setxattr")	    \
+	f(SETXATTRS,	__CEPH_OSD_OP(WR, ATTR, 2),	"setxattrs")	    \
+	f(RESETXATTRS,	__CEPH_OSD_OP(WR, ATTR, 3),	"resetxattrs")	    \
+	f(RMXATTR,	__CEPH_OSD_OP(WR, ATTR, 4),	"rmxattr")	    \
+									    \
+	/** subop **/							    \
+	f(PULL,		__CEPH_OSD_OP1(SUB, 1),		"pull")		    \
+	f(PUSH,		__CEPH_OSD_OP1(SUB, 2),		"push")		    \
+	f(BALANCEREADS,	__CEPH_OSD_OP1(SUB, 3),		"balance-reads")    \
+	f(UNBALANCEREADS, __CEPH_OSD_OP1(SUB, 4),	"unbalance-reads")  \
+	f(SCRUB,	__CEPH_OSD_OP1(SUB, 5),		"scrub")	    \
+	f(SCRUB_RESERVE, __CEPH_OSD_OP1(SUB, 6),	"scrub-reserve")    \
+	f(SCRUB_UNRESERVE, __CEPH_OSD_OP1(SUB, 7),	"scrub-unreserve")  \
+	f(SCRUB_STOP,	__CEPH_OSD_OP1(SUB, 8),		"scrub-stop")	    \
+	f(SCRUB_MAP,	__CEPH_OSD_OP1(SUB, 9),		"scrub-map")	    \
+									    \
+	/** lock **/							    \
+	f(WRLOCK,	__CEPH_OSD_OP(WR, LOCK, 1),	"wrlock")	    \
+	f(WRUNLOCK,	__CEPH_OSD_OP(WR, LOCK, 2),	"wrunlock")	    \
+	f(RDLOCK,	__CEPH_OSD_OP(WR, LOCK, 3),	"rdlock")	    \
+	f(RDUNLOCK,	__CEPH_OSD_OP(WR, LOCK, 4),	"rdunlock")	    \
+	f(UPLOCK,	__CEPH_OSD_OP(WR, LOCK, 5),	"uplock")	    \
+	f(DNLOCK,	__CEPH_OSD_OP(WR, LOCK, 6),	"dnlock")	    \
+									    \
+	/** exec **/							    \
+	/* note: the RD bit here is wrong; see special-case below in helper */ \
+	f(CALL,		__CEPH_OSD_OP(RD, EXEC, 1),	"call")		    \
+									    \
+	/** pg **/							    \
+	f(PGLS,		__CEPH_OSD_OP(RD, PG, 1),	"pgls")		    \
+	f(PGLS_FILTER,	__CEPH_OSD_OP(RD, PG, 2),	"pgls-filter")	    \
+	f(PG_HITSET_LS,	__CEPH_OSD_OP(RD, PG, 3),	"pg-hitset-ls")	    \
+	f(PG_HITSET_GET, __CEPH_OSD_OP(RD, PG, 4),	"pg-hitset-get")
+
 enum {
-	/** data **/
-	/* read */
-	CEPH_OSD_OP_READ      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 1,
-	CEPH_OSD_OP_STAT      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 2,
-	CEPH_OSD_OP_MAPEXT    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 3,
-
-	/* fancy read */
-	CEPH_OSD_OP_MASKTRUNC   = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 4,
-	CEPH_OSD_OP_SPARSE_READ = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 5,
-
-	CEPH_OSD_OP_NOTIFY    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 6,
-	CEPH_OSD_OP_NOTIFY_ACK = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 7,
-
-	/* versioning */
-	CEPH_OSD_OP_ASSERT_VER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 8,
-
-	/* write */
-	CEPH_OSD_OP_WRITE     = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 1,
-	CEPH_OSD_OP_WRITEFULL = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 2,
-	CEPH_OSD_OP_TRUNCATE  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 3,
-	CEPH_OSD_OP_ZERO      = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 4,
-	CEPH_OSD_OP_DELETE    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 5,
-
-	/* fancy write */
-	CEPH_OSD_OP_APPEND    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 6,
-	CEPH_OSD_OP_STARTSYNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 7,
-	CEPH_OSD_OP_SETTRUNC  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 8,
-	CEPH_OSD_OP_TRIMTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 9,
-
-	CEPH_OSD_OP_TMAPUP  = CEPH_OSD_OP_MODE_RMW | CEPH_OSD_OP_TYPE_DATA | 10,
-	CEPH_OSD_OP_TMAPPUT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 11,
-	CEPH_OSD_OP_TMAPGET = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 12,
-
-	CEPH_OSD_OP_CREATE  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 13,
-	CEPH_OSD_OP_ROLLBACK= CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 14,
-
-	CEPH_OSD_OP_WATCH   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 15,
-
-	/* omap */
-	CEPH_OSD_OP_OMAPGETKEYS   = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 17,
-	CEPH_OSD_OP_OMAPGETVALS   = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 18,
-	CEPH_OSD_OP_OMAPGETHEADER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 19,
-	CEPH_OSD_OP_OMAPGETVALSBYKEYS  =
-	  CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 20,
-	CEPH_OSD_OP_OMAPSETVALS   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 21,
-	CEPH_OSD_OP_OMAPSETHEADER = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 22,
-	CEPH_OSD_OP_OMAPCLEAR     = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 23,
-	CEPH_OSD_OP_OMAPRMKEYS    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 24,
-	CEPH_OSD_OP_OMAP_CMP      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 25,
-
-	/* hints */
-	CEPH_OSD_OP_SETALLOCHINT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 35,
-
-	/** multi **/
-	CEPH_OSD_OP_CLONERANGE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_MULTI | 1,
-	CEPH_OSD_OP_ASSERT_SRC_VERSION = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 2,
-	CEPH_OSD_OP_SRC_CMPXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 3,
-
-	/** attrs **/
-	/* read */
-	CEPH_OSD_OP_GETXATTR  = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1,
-	CEPH_OSD_OP_GETXATTRS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 2,
-	CEPH_OSD_OP_CMPXATTR  = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 3,
-
-	/* write */
-	CEPH_OSD_OP_SETXATTR  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 1,
-	CEPH_OSD_OP_SETXATTRS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 2,
-	CEPH_OSD_OP_RESETXATTRS = CEPH_OSD_OP_MODE_WR|CEPH_OSD_OP_TYPE_ATTR | 3,
-	CEPH_OSD_OP_RMXATTR   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 4,
-
-	/** subop **/
-	CEPH_OSD_OP_PULL            = CEPH_OSD_OP_MODE_SUB | 1,
-	CEPH_OSD_OP_PUSH            = CEPH_OSD_OP_MODE_SUB | 2,
-	CEPH_OSD_OP_BALANCEREADS    = CEPH_OSD_OP_MODE_SUB | 3,
-	CEPH_OSD_OP_UNBALANCEREADS  = CEPH_OSD_OP_MODE_SUB | 4,
-	CEPH_OSD_OP_SCRUB           = CEPH_OSD_OP_MODE_SUB | 5,
-	CEPH_OSD_OP_SCRUB_RESERVE   = CEPH_OSD_OP_MODE_SUB | 6,
-	CEPH_OSD_OP_SCRUB_UNRESERVE = CEPH_OSD_OP_MODE_SUB | 7,
-	CEPH_OSD_OP_SCRUB_STOP      = CEPH_OSD_OP_MODE_SUB | 8,
-	CEPH_OSD_OP_SCRUB_MAP     = CEPH_OSD_OP_MODE_SUB | 9,
-
-	/** lock **/
-	CEPH_OSD_OP_WRLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1,
-	CEPH_OSD_OP_WRUNLOCK  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 2,
-	CEPH_OSD_OP_RDLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 3,
-	CEPH_OSD_OP_RDUNLOCK  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 4,
-	CEPH_OSD_OP_UPLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 5,
-	CEPH_OSD_OP_DNLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6,
-
-	/** exec **/
-	/* note: the RD bit here is wrong; see special-case below in helper */
-	CEPH_OSD_OP_CALL    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1,
-
-	/** pg **/
-	CEPH_OSD_OP_PGLS      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1,
-	CEPH_OSD_OP_PGLS_FILTER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 2,
+#define GENERATE_ENUM_ENTRY(op, opcode, str)	CEPH_OSD_OP_##op = (opcode),
+__CEPH_FORALL_OSD_OPS(GENERATE_ENUM_ENTRY)
+#undef GENERATE_ENUM_ENTRY
 };
 
 static inline int ceph_osd_op_type_lock(int op)
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index b5223c570eba..1d5196889048 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -27,7 +27,6 @@
 
 struct cgroup_root;
 struct cgroup_subsys;
-struct inode;
 struct cgroup;
 
 extern int cgroup_init_early(void);
@@ -38,7 +37,8 @@ extern void cgroup_exit(struct task_struct *p);
 extern int cgroupstats_build(struct cgroupstats *stats,
 				struct dentry *dentry);
 
-extern int proc_cgroup_show(struct seq_file *, void *);
+extern int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
+			    struct pid *pid, struct task_struct *tsk);
 
 /* define the enumeration of all cgroup subsystems */
 #define SUBSYS(_x) _x ## _cgrp_id,
@@ -161,11 +161,6 @@ static inline void css_put(struct cgroup_subsys_state *css)
 
 /* bits in struct cgroup flags field */
 enum {
-	/*
-	 * Control Group has previously had a child cgroup or a task,
-	 * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set)
-	 */
-	CGRP_RELEASABLE,
 	/* Control Group requires release notifications to userspace */
 	CGRP_NOTIFY_ON_RELEASE,
 	/*
@@ -235,13 +230,6 @@ struct cgroup {
 	struct list_head e_csets[CGROUP_SUBSYS_COUNT];
 
 	/*
-	 * Linked list running through all cgroups that can
-	 * potentially be reaped by the release agent. Protected by
-	 * release_list_lock
-	 */
-	struct list_head release_list;
-
-	/*
 	 * list of pidlists, up to two for each namespace (one for procs, one
 	 * for tasks); created on demand.
 	 */
@@ -250,6 +238,9 @@ struct cgroup {
 
 	/* used to wait for offlining of csses */
 	wait_queue_head_t offline_waitq;
+
+	/* used to schedule release agent */
+	struct work_struct release_agent_work;
 };
 
 #define MAX_CGROUP_ROOT_NAMELEN 64
@@ -536,13 +527,10 @@ static inline bool cgroup_has_tasks(struct cgroup *cgrp)
 	return !list_empty(&cgrp->cset_links);
 }
 
-/* returns ino associated with a cgroup, 0 indicates unmounted root */
+/* returns ino associated with a cgroup */
 static inline ino_t cgroup_ino(struct cgroup *cgrp)
 {
-	if (cgrp->kn)
-		return cgrp->kn->ino;
-	else
-		return 0;
+	return cgrp->kn->ino;
 }
 
 /* cft/css accessors for cftype->write() operation */
diff --git a/include/linux/clk-private.h b/include/linux/clk-private.h
index efbf70b9fd84..0ca5f6046920 100644
--- a/include/linux/clk-private.h
+++ b/include/linux/clk-private.h
@@ -46,8 +46,10 @@ struct clk {
 	unsigned int		enable_count;
 	unsigned int		prepare_count;
 	unsigned long		accuracy;
+	int			phase;
 	struct hlist_head	children;
 	struct hlist_node	child_node;
+	struct hlist_node	debug_node;
 	unsigned int		notifier_count;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry		*dentry;
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 411dd7eb2653..be21af149f11 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -13,6 +13,7 @@
 
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/of.h>
 
 #ifdef CONFIG_COMMON_CLK
 
@@ -129,6 +130,14 @@ struct dentry;
  *		set then clock accuracy will be initialized to parent accuracy
  *		or 0 (perfect clock) if clock has no parent.
  *
+ * @get_phase:	Queries the hardware to get the current phase of a clock.
+ *		Returned values are 0-359 degrees on success, negative
+ *		error codes on failure.
+ *
+ * @set_phase:	Shift the phase this clock signal in degrees specified
+ *		by the second argument. Valid values for degrees are
+ *		0-359. Return 0 on success, otherwise -EERROR.
+ *
  * @init:	Perform platform-specific initialization magic.
  *		This is not not used by any of the basic clock types.
  *		Please consider other ways of solving initialization problems
@@ -177,6 +186,8 @@ struct clk_ops {
 				    unsigned long parent_rate, u8 index);
 	unsigned long	(*recalc_accuracy)(struct clk_hw *hw,
 					   unsigned long parent_accuracy);
+	int		(*get_phase)(struct clk_hw *hw);
+	int		(*set_phase)(struct clk_hw *hw, int degrees);
 	void		(*init)(struct clk_hw *hw);
 	int		(*debug_init)(struct clk_hw *hw, struct dentry *dentry);
 };
@@ -488,6 +499,28 @@ struct clk *clk_register_composite(struct device *dev, const char *name,
 		struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
 		unsigned long flags);
 
+/***
+ * struct clk_gpio_gate - gpio gated clock
+ *
+ * @hw:		handle between common and hardware-specific interfaces
+ * @gpiod:	gpio descriptor
+ *
+ * Clock with a gpio control for enabling and disabling the parent clock.
+ * Implements .enable, .disable and .is_enabled
+ */
+
+struct clk_gpio {
+	struct clk_hw	hw;
+	struct gpio_desc *gpiod;
+};
+
+extern const struct clk_ops clk_gpio_gate_ops;
+struct clk *clk_register_gpio_gate(struct device *dev, const char *name,
+		const char *parent_name, struct gpio_desc *gpio,
+		unsigned long flags);
+
+void of_gpio_clk_gate_setup(struct device_node *node);
+
 /**
  * clk_register - allocate a new clock, register it and return an opaque cookie
  * @dev: device that is registering this clock
diff --git a/include/linux/clk.h b/include/linux/clk.h
index afb44bfaf8d1..c7f258a81761 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -106,6 +106,25 @@ int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb);
  */
 long clk_get_accuracy(struct clk *clk);
 
+/**
+ * clk_set_phase - adjust the phase shift of a clock signal
+ * @clk: clock signal source
+ * @degrees: number of degrees the signal is shifted
+ *
+ * Shifts the phase of a clock signal by the specified degrees. Returns 0 on
+ * success, -EERROR otherwise.
+ */
+int clk_set_phase(struct clk *clk, int degrees);
+
+/**
+ * clk_get_phase - return the phase shift of a clock signal
+ * @clk: clock signal source
+ *
+ * Returns the phase shift of a clock node in degrees, otherwise returns
+ * -EERROR.
+ */
+int clk_get_phase(struct clk *clk);
+
 #else
 
 static inline long clk_get_accuracy(struct clk *clk)
@@ -113,6 +132,16 @@ static inline long clk_get_accuracy(struct clk *clk)
 	return -ENOTSUPP;
 }
 
+static inline long clk_set_phase(struct clk *clk, int phase)
+{
+	return -ENOTSUPP;
+}
+
+static inline long clk_get_phase(struct clk *clk)
+{
+	return -ENOTSUPP;
+}
+
 #endif
 
 /**
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index e8d8a35034a5..f75acbf70e96 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -292,6 +292,7 @@ void omap2xxx_clkt_vps_init(void);
 void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index);
 void ti_dt_clocks_register(struct ti_dt_clk *oclks);
 void ti_dt_clk_init_provider(struct device_node *np, int index);
+void ti_dt_clk_init_retry_clks(void);
 void ti_dt_clockdomains_setup(void);
 int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw,
 		      ti_of_clk_init_cb_t func);
diff --git a/include/linux/cma.h b/include/linux/cma.h
index 371b93042520..0430ed05d3b9 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -22,6 +22,9 @@ extern int __init cma_declare_contiguous(phys_addr_t size,
 			phys_addr_t base, phys_addr_t limit,
 			phys_addr_t alignment, unsigned int order_per_bit,
 			bool fixed, struct cma **res_cma);
+extern int cma_init_reserved_mem(phys_addr_t size,
+					phys_addr_t base, int order_per_bit,
+					struct cma **res_cma);
 extern struct page *cma_alloc(struct cma *cma, int count, unsigned int align);
 extern bool cma_release(struct cma *cma, struct page *pages, int count);
 #endif
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 01e3132820da..60bdf8dc02a3 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -2,14 +2,24 @@
 #define _LINUX_COMPACTION_H
 
 /* Return values for compact_zone() and try_to_compact_pages() */
+/* compaction didn't start as it was deferred due to past failures */
+#define COMPACT_DEFERRED	0
 /* compaction didn't start as it was not possible or direct reclaim was more suitable */
-#define COMPACT_SKIPPED		0
+#define COMPACT_SKIPPED		1
 /* compaction should continue to another pageblock */
-#define COMPACT_CONTINUE	1
+#define COMPACT_CONTINUE	2
 /* direct compaction partially compacted a zone and there are suitable pages */
-#define COMPACT_PARTIAL		2
+#define COMPACT_PARTIAL		3
 /* The full zone was compacted */
-#define COMPACT_COMPLETE	3
+#define COMPACT_COMPLETE	4
+
+/* Used to signal whether compaction detected need_sched() or lock contention */
+/* No contention detected */
+#define COMPACT_CONTENDED_NONE	0
+/* Either need_sched() was true or fatal signal pending */
+#define COMPACT_CONTENDED_SCHED	1
+/* Zone lock or lru_lock was contended in async compaction */
+#define COMPACT_CONTENDED_LOCK	2
 
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
@@ -22,7 +32,8 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
-			enum migrate_mode mode, bool *contended);
+			enum migrate_mode mode, int *contended,
+			struct zone **candidate_zone);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
@@ -91,7 +102,8 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			enum migrate_mode mode, bool *contended)
+			enum migrate_mode mode, int *contended,
+			struct zone **candidate_zone)
 {
 	return COMPACT_CONTINUE;
 }
diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h
new file mode 100644
index 000000000000..cdd1cc202d51
--- /dev/null
+++ b/include/linux/compiler-gcc5.h
@@ -0,0 +1,66 @@
+#ifndef __LINUX_COMPILER_H
+#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead."
+#endif
+
+#define __used				__attribute__((__used__))
+#define __must_check			__attribute__((warn_unused_result))
+#define __compiler_offsetof(a, b)	__builtin_offsetof(a, b)
+
+/* Mark functions as cold. gcc will assume any path leading to a call
+   to them will be unlikely.  This means a lot of manual unlikely()s
+   are unnecessary now for any paths leading to the usual suspects
+   like BUG(), printk(), panic() etc. [but let's keep them for now for
+   older compilers]
+
+   Early snapshots of gcc 4.3 don't support this and we can't detect this
+   in the preprocessor, but we can live with this because they're unreleased.
+   Maketime probing would be overkill here.
+
+   gcc also has a __attribute__((__hot__)) to move hot functions into
+   a special section, but I don't see any sense in this right now in
+   the kernel context */
+#define __cold			__attribute__((__cold__))
+
+#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+
+#ifndef __CHECKER__
+# define __compiletime_warning(message) __attribute__((warning(message)))
+# define __compiletime_error(message) __attribute__((error(message)))
+#endif /* __CHECKER__ */
+
+/*
+ * Mark a position in code as unreachable.  This can be used to
+ * suppress control flow warnings after asm blocks that transfer
+ * control elsewhere.
+ *
+ * Early snapshots of gcc 4.5 don't support this and we can't detect
+ * this in the preprocessor, but we can live with this because they're
+ * unreleased.  Really, we need to have autoconf for the kernel.
+ */
+#define unreachable() __builtin_unreachable()
+
+/* Mark a function definition as prohibited from being cloned. */
+#define __noclone	__attribute__((__noclone__))
+
+/*
+ * Tell the optimizer that something else uses this function or variable.
+ */
+#define __visible __attribute__((externally_visible))
+
+/*
+ * GCC 'asm goto' miscompiles certain code sequences:
+ *
+ *   http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
+ * Fixed in GCC 4.8.2 and later versions.
+ *
+ * (asm goto is automatically volatile - the naming reflects this.)
+ */
+#define asm_volatile_goto(x...)	do { asm goto(x); asm (""); } while (0)
+
+#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
+#define __HAVE_BUILTIN_BSWAP32__
+#define __HAVE_BUILTIN_BSWAP64__
+#define __HAVE_BUILTIN_BSWAP16__
+#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 95978ad7fcdd..b2d9a43012b2 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -213,6 +213,7 @@ extern struct bus_type cpu_subsys;
 extern void cpu_hotplug_begin(void);
 extern void cpu_hotplug_done(void);
 extern void get_online_cpus(void);
+extern bool try_get_online_cpus(void);
 extern void put_online_cpus(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
@@ -230,6 +231,7 @@ int cpu_down(unsigned int cpu);
 static inline void cpu_hotplug_begin(void) {}
 static inline void cpu_hotplug_done(void) {}
 #define get_online_cpus()	do { } while (0)
+#define try_get_online_cpus()	true
 #define put_online_cpus()	do { } while (0)
 #define cpu_hotplug_disable()	do { } while (0)
 #define cpu_hotplug_enable()	do { } while (0)
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 7d1955afa62c..138336b6bb04 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -112,6 +112,9 @@ struct cpufreq_policy {
 	spinlock_t		transition_lock;
 	wait_queue_head_t	transition_wait;
 	struct task_struct	*transition_task; /* Task which is doing the transition */
+
+	/* For cpufreq driver's internal use */
+	void			*driver_data;
 };
 
 /* Only for ACPI */
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 2997af6d2ccd..0a9a6da21e74 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -666,10 +666,19 @@ static inline size_t cpumask_size(void)
  *
  * This code makes NR_CPUS length memcopy and brings to a memory corruption.
  * cpumask_copy() provide safe copy functionality.
+ *
+ * Note that there is another evil here: If you define a cpumask_var_t
+ * as a percpu variable then the way to obtain the address of the cpumask
+ * structure differently influences what this_cpu_* operation needs to be
+ * used. Please use this_cpu_cpumask_var_t in those cases. The direct use
+ * of this_cpu_ptr() or this_cpu_read() will lead to failures when the
+ * other type of cpumask_var_t implementation is configured.
  */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 typedef struct cpumask *cpumask_var_t;
 
+#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x)
+
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
 bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
@@ -681,6 +690,8 @@ void free_bootmem_cpumask_var(cpumask_var_t mask);
 #else
 typedef struct cpumask cpumask_var_t[1];
 
+#define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x)
+
 static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return true;
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 6e39c9bb0dae..2f073db7392e 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -86,7 +86,8 @@ extern void __cpuset_memory_pressure_bump(void);
 
 extern void cpuset_task_status_allowed(struct seq_file *m,
 					struct task_struct *task);
-extern int proc_cpuset_show(struct seq_file *, void *);
+extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
+			    struct pid *pid, struct task_struct *tsk);
 
 extern int cpuset_mem_spread_node(void);
 extern int cpuset_slab_spread_node(void);
diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h
index b3cb71f0d3b0..cf53d0773ce3 100644
--- a/include/linux/crc-t10dif.h
+++ b/include/linux/crc-t10dif.h
@@ -6,7 +6,8 @@
 #define CRC_T10DIF_DIGEST_SIZE 2
 #define CRC_T10DIF_BLOCK_SIZE 1
 
-__u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len);
-__u16 crc_t10dif(unsigned char const *, size_t);
+extern __u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer,
+				size_t len);
+extern __u16 crc_t10dif(unsigned char const *, size_t);
 
 #endif
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 75a227cc7ce2..b2a2a08523bf 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -11,7 +11,6 @@
 #include <linux/rcupdate.h>
 #include <linux/lockref.h>
 
-struct nameidata;
 struct path;
 struct vfsmount;
 
@@ -226,11 +225,6 @@ struct dentry_operations {
 
 extern seqlock_t rename_lock;
 
-static inline int dname_external(const struct dentry *dentry)
-{
-	return dentry->d_name.name != dentry->d_iname;
-}
-
 /*
  * These are the low-level FS interfaces to the dcache..
  */
@@ -254,7 +248,7 @@ extern struct dentry * d_obtain_root(struct inode *);
 extern void shrink_dcache_sb(struct super_block *);
 extern void shrink_dcache_parent(struct dentry *);
 extern void shrink_dcache_for_umount(struct super_block *);
-extern int d_invalidate(struct dentry *);
+extern void d_invalidate(struct dentry *);
 
 /* only used at mount-time */
 extern struct dentry * d_make_root(struct inode *);
@@ -269,7 +263,6 @@ extern void d_prune_aliases(struct inode *);
 
 /* test whether we have any submounts in a subdir tree */
 extern int have_submounts(struct dentry *);
-extern int check_submounts_and_drop(struct dentry *);
 
 /*
  * This adds the entry to the hash queues.
diff --git a/include/linux/device.h b/include/linux/device.h
index a608e237f0a8..ce1f21608b16 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -181,13 +181,14 @@ extern int bus_unregister_notifier(struct bus_type *bus,
  * with the device lock held in the core, so be careful.
  */
 #define BUS_NOTIFY_ADD_DEVICE		0x00000001 /* device added */
-#define BUS_NOTIFY_DEL_DEVICE		0x00000002 /* device removed */
-#define BUS_NOTIFY_BIND_DRIVER		0x00000003 /* driver about to be
+#define BUS_NOTIFY_DEL_DEVICE		0x00000002 /* device to be removed */
+#define BUS_NOTIFY_REMOVED_DEVICE	0x00000003 /* device removed */
+#define BUS_NOTIFY_BIND_DRIVER		0x00000004 /* driver about to be
 						      bound */
-#define BUS_NOTIFY_BOUND_DRIVER		0x00000004 /* driver bound to device */
-#define BUS_NOTIFY_UNBIND_DRIVER	0x00000005 /* driver about to be
+#define BUS_NOTIFY_BOUND_DRIVER		0x00000005 /* driver bound to device */
+#define BUS_NOTIFY_UNBIND_DRIVER	0x00000006 /* driver about to be
 						      unbound */
-#define BUS_NOTIFY_UNBOUND_DRIVER	0x00000006 /* driver is unbound
+#define BUS_NOTIFY_UNBOUND_DRIVER	0x00000007 /* driver is unbound
 						      from the device */
 
 extern struct kset *bus_get_kset(struct bus_type *bus);
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 931b70986272..d5d388160f42 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -263,6 +263,32 @@ struct dma_attrs;
 #define dma_unmap_sg_attrs(dev, sgl, nents, dir, attrs) \
 	dma_unmap_sg(dev, sgl, nents, dir)
 
+#else
+static inline void *dma_alloc_writecombine(struct device *dev, size_t size,
+					   dma_addr_t *dma_addr, gfp_t gfp)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_alloc_attrs(dev, size, dma_addr, gfp, &attrs);
+}
+
+static inline void dma_free_writecombine(struct device *dev, size_t size,
+					 void *cpu_addr, dma_addr_t dma_addr)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_free_attrs(dev, size, cpu_addr, dma_addr, &attrs);
+}
+
+static inline int dma_mmap_writecombine(struct device *dev,
+					struct vm_area_struct *vma,
+					void *cpu_addr, dma_addr_t dma_addr,
+					size_t size)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs);
+}
 #endif /* CONFIG_HAVE_DMA_ATTRS */
 
 #ifdef CONFIG_NEED_DMA_MAP_STATE
diff --git a/include/linux/dma/dw.h b/include/linux/dma/dw.h
new file mode 100644
index 000000000000..71456442ebe3
--- /dev/null
+++ b/include/linux/dma/dw.h
@@ -0,0 +1,64 @@
+/*
+ * Driver for the Synopsys DesignWare DMA Controller
+ *
+ * Copyright (C) 2007 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
+ * Copyright (C) 2014 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _DMA_DW_H
+#define _DMA_DW_H
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+
+#include <linux/platform_data/dma-dw.h>
+
+struct dw_dma;
+
+/**
+ * struct dw_dma_chip - representation of DesignWare DMA controller hardware
+ * @dev:		struct device of the DMA controller
+ * @irq:		irq line
+ * @regs:		memory mapped I/O space
+ * @clk:		hclk clock
+ * @dw:			struct dw_dma that is filed by dw_dma_probe()
+ */
+struct dw_dma_chip {
+	struct device	*dev;
+	int		irq;
+	void __iomem	*regs;
+	struct clk	*clk;
+	struct dw_dma	*dw;
+};
+
+/* Export to the platform drivers */
+int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata);
+int dw_dma_remove(struct dw_dma_chip *chip);
+
+/* DMA API extensions */
+struct dw_desc;
+
+struct dw_cyclic_desc {
+	struct dw_desc	**desc;
+	unsigned long	periods;
+	void		(*period_callback)(void *param);
+	void		*period_callback_param;
+};
+
+struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
+		dma_addr_t buf_addr, size_t buf_len, size_t period_len,
+		enum dma_transfer_direction direction);
+void dw_dma_cyclic_free(struct dma_chan *chan);
+int dw_dma_cyclic_start(struct dma_chan *chan);
+void dw_dma_cyclic_stop(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan);
+
+#endif /* _DMA_DW_H */
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 212c5b9ac106..653a1fd07ae8 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -199,15 +199,12 @@ enum dma_ctrl_flags {
  * configuration data in statically from the platform). An additional
  * argument of struct dma_slave_config must be passed in with this
  * command.
- * @FSLDMA_EXTERNAL_START: this command will put the Freescale DMA controller
- * into external start mode.
  */
 enum dma_ctrl_cmd {
 	DMA_TERMINATE_ALL,
 	DMA_PAUSE,
 	DMA_RESUME,
 	DMA_SLAVE_CONFIG,
-	FSLDMA_EXTERNAL_START,
 };
 
 /**
@@ -307,7 +304,9 @@ enum dma_slave_buswidth {
  * struct dma_slave_config - dma slave channel runtime config
  * @direction: whether the data shall go in or out on this slave
  * channel, right now. DMA_MEM_TO_DEV and DMA_DEV_TO_MEM are
- * legal values.
+ * legal values. DEPRECATED, drivers should use the direction argument
+ * to the device_prep_slave_sg and device_prep_dma_cyclic functions or
+ * the dir field in the dma_interleaved_template structure.
  * @src_addr: this is the physical address where DMA slave data
  * should be read (RX), if the source is memory this argument is
  * ignored.
@@ -755,6 +754,16 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma(
 	return chan->device->device_prep_interleaved_dma(chan, xt, flags);
 }
 
+static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg(
+		struct dma_chan *chan,
+		struct scatterlist *dst_sg, unsigned int dst_nents,
+		struct scatterlist *src_sg, unsigned int src_nents,
+		unsigned long flags)
+{
+	return chan->device->device_prep_dma_sg(chan, dst_sg, dst_nents,
+			src_sg, src_nents, flags);
+}
+
 static inline int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 {
 	if (!chan || !caps)
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 1deece46a0ca..593fff99e6bf 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -56,13 +56,19 @@ struct dmar_drhd_unit {
 	struct intel_iommu *iommu;
 };
 
+struct dmar_pci_path {
+	u8 bus;
+	u8 device;
+	u8 function;
+};
+
 struct dmar_pci_notify_info {
 	struct pci_dev			*dev;
 	unsigned long			event;
 	int				bus;
 	u16				seg;
 	u16				level;
-	struct acpi_dmar_pci_path	path[];
+	struct dmar_pci_path		path[];
 }  __attribute__((packed));
 
 extern struct rw_semaphore dmar_global_lock;
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
deleted file mode 100644
index 68b4024184de..000000000000
--- a/include/linux/dw_dmac.h
+++ /dev/null
@@ -1,111 +0,0 @@
-/*
- * Driver for the Synopsys DesignWare DMA Controller
- *
- * Copyright (C) 2007 Atmel Corporation
- * Copyright (C) 2010-2011 ST Microelectronics
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef DW_DMAC_H
-#define DW_DMAC_H
-
-#include <linux/dmaengine.h>
-
-/**
- * struct dw_dma_slave - Controller-specific information about a slave
- *
- * @dma_dev: required DMA master device. Depricated.
- * @bus_id: name of this device channel, not just a device name since
- *          devices may have more than one channel e.g. "foo_tx"
- * @cfg_hi: Platform-specific initializer for the CFG_HI register
- * @cfg_lo: Platform-specific initializer for the CFG_LO register
- * @src_master: src master for transfers on allocated channel.
- * @dst_master: dest master for transfers on allocated channel.
- */
-struct dw_dma_slave {
-	struct device		*dma_dev;
-	u32			cfg_hi;
-	u32			cfg_lo;
-	u8			src_master;
-	u8			dst_master;
-};
-
-/**
- * struct dw_dma_platform_data - Controller configuration parameters
- * @nr_channels: Number of channels supported by hardware (max 8)
- * @is_private: The device channels should be marked as private and not for
- *	by the general purpose DMA channel allocator.
- * @chan_allocation_order: Allocate channels starting from 0 or 7
- * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0.
- * @block_size: Maximum block size supported by the controller
- * @nr_masters: Number of AHB masters supported by the controller
- * @data_width: Maximum data width supported by hardware per AHB master
- *		(0 - 8bits, 1 - 16bits, ..., 5 - 256bits)
- */
-struct dw_dma_platform_data {
-	unsigned int	nr_channels;
-	bool		is_private;
-#define CHAN_ALLOCATION_ASCENDING	0	/* zero to seven */
-#define CHAN_ALLOCATION_DESCENDING	1	/* seven to zero */
-	unsigned char	chan_allocation_order;
-#define CHAN_PRIORITY_ASCENDING		0	/* chan0 highest */
-#define CHAN_PRIORITY_DESCENDING	1	/* chan7 highest */
-	unsigned char	chan_priority;
-	unsigned short	block_size;
-	unsigned char	nr_masters;
-	unsigned char	data_width[4];
-};
-
-/* bursts size */
-enum dw_dma_msize {
-	DW_DMA_MSIZE_1,
-	DW_DMA_MSIZE_4,
-	DW_DMA_MSIZE_8,
-	DW_DMA_MSIZE_16,
-	DW_DMA_MSIZE_32,
-	DW_DMA_MSIZE_64,
-	DW_DMA_MSIZE_128,
-	DW_DMA_MSIZE_256,
-};
-
-/* Platform-configurable bits in CFG_HI */
-#define DWC_CFGH_FCMODE		(1 << 0)
-#define DWC_CFGH_FIFO_MODE	(1 << 1)
-#define DWC_CFGH_PROTCTL(x)	((x) << 2)
-#define DWC_CFGH_SRC_PER(x)	((x) << 7)
-#define DWC_CFGH_DST_PER(x)	((x) << 11)
-
-/* Platform-configurable bits in CFG_LO */
-#define DWC_CFGL_LOCK_CH_XFER	(0 << 12)	/* scope of LOCK_CH */
-#define DWC_CFGL_LOCK_CH_BLOCK	(1 << 12)
-#define DWC_CFGL_LOCK_CH_XACT	(2 << 12)
-#define DWC_CFGL_LOCK_BUS_XFER	(0 << 14)	/* scope of LOCK_BUS */
-#define DWC_CFGL_LOCK_BUS_BLOCK	(1 << 14)
-#define DWC_CFGL_LOCK_BUS_XACT	(2 << 14)
-#define DWC_CFGL_LOCK_CH	(1 << 15)	/* channel lockout */
-#define DWC_CFGL_LOCK_BUS	(1 << 16)	/* busmaster lockout */
-#define DWC_CFGL_HS_DST_POL	(1 << 18)	/* dst handshake active low */
-#define DWC_CFGL_HS_SRC_POL	(1 << 19)	/* src handshake active low */
-
-/* DMA API extensions */
-struct dw_cyclic_desc {
-	struct dw_desc	**desc;
-	unsigned long	periods;
-	void		(*period_callback)(void *param);
-	void		*period_callback_param;
-};
-
-struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
-		dma_addr_t buf_addr, size_t buf_len, size_t period_len,
-		enum dma_transfer_direction direction);
-void dw_dma_cyclic_free(struct dma_chan *chan);
-int dw_dma_cyclic_start(struct dma_chan *chan);
-void dw_dma_cyclic_stop(struct dma_chan *chan);
-
-dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan);
-
-dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan);
-
-#endif /* DW_DMAC_H */
diff --git a/include/linux/flex_proportions.h b/include/linux/flex_proportions.h
index 4ebc49fae391..0d348e011a6e 100644
--- a/include/linux/flex_proportions.h
+++ b/include/linux/flex_proportions.h
@@ -10,6 +10,7 @@
 #include <linux/percpu_counter.h>
 #include <linux/spinlock.h>
 #include <linux/seqlock.h>
+#include <linux/gfp.h>
 
 /*
  * When maximum proportion of some event type is specified, this is the
@@ -32,7 +33,7 @@ struct fprop_global {
 	seqcount_t sequence;
 };
 
-int fprop_global_init(struct fprop_global *p);
+int fprop_global_init(struct fprop_global *p, gfp_t gfp);
 void fprop_global_destroy(struct fprop_global *p);
 bool fprop_new_period(struct fprop_global *p, int periods);
 
@@ -79,7 +80,7 @@ struct fprop_local_percpu {
 	raw_spinlock_t lock;	/* Protect period and numerator */
 };
 
-int fprop_local_init_percpu(struct fprop_local_percpu *pl);
+int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp);
 void fprop_local_destroy_percpu(struct fprop_local_percpu *pl);
 void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl);
 void __fprop_inc_percpu_max(struct fprop_global *p, struct fprop_local_percpu *pl,
diff --git a/include/linux/font.h b/include/linux/font.h
index 40a24ab41b36..d6821769dd1e 100644
--- a/include/linux/font.h
+++ b/include/linux/font.h
@@ -31,6 +31,7 @@ struct font_desc {
 #define SUN12x22_IDX	7
 #define ACORN8x8_IDX	8
 #define	MINI4x6_IDX	9
+#define FONT6x10_IDX	10
 
 extern const struct font_desc	font_vga_8x8,
 			font_vga_8x16,
@@ -41,7 +42,8 @@ extern const struct font_desc	font_vga_8x8,
 			font_sun_8x16,
 			font_sun_12x22,
 			font_acorn_8x8,
-			font_mini_4x6;
+			font_mini_4x6,
+			font_6x10;
 
 /* Find a font with a specific name */
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 94187721ad41..a957d4366c24 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -192,8 +192,6 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define READ			0
 #define WRITE			RW_MASK
 #define READA			RWA_MASK
-#define KERNEL_READ		(READ|REQ_KERNEL)
-#define KERNEL_WRITE		(WRITE|REQ_KERNEL)
 
 #define READ_SYNC		(READ | REQ_SYNC)
 #define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
@@ -851,13 +849,7 @@ static inline struct file *get_file(struct file *f)
  */
 #define FILE_LOCK_DEFERRED 1
 
-/*
- * The POSIX file lock owner is determined by
- * the "struct files_struct" in the thread group
- * (or NULL for no owner - BSD locks).
- *
- * Lockd stuffs a "host" pointer into this.
- */
+/* legacy typedef, should eventually be removed */
 typedef void *fl_owner_t;
 
 struct file_lock_operations {
@@ -868,10 +860,13 @@ struct file_lock_operations {
 struct lock_manager_operations {
 	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
 	unsigned long (*lm_owner_key)(struct file_lock *);
+	void (*lm_get_owner)(struct file_lock *, struct file_lock *);
+	void (*lm_put_owner)(struct file_lock *);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
-	int (*lm_grant)(struct file_lock *, struct file_lock *, int);
-	void (*lm_break)(struct file_lock *);
-	int (*lm_change)(struct file_lock **, int);
+	int (*lm_grant)(struct file_lock *, int);
+	bool (*lm_break)(struct file_lock *);
+	int (*lm_change)(struct file_lock **, int, struct list_head *);
+	void (*lm_setup)(struct file_lock *, void **);
 };
 
 struct lock_manager {
@@ -966,7 +961,7 @@ void locks_free_lock(struct file_lock *fl);
 extern void locks_init_lock(struct file_lock *);
 extern struct file_lock * locks_alloc_lock(void);
 extern void locks_copy_lock(struct file_lock *, struct file_lock *);
-extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
+extern void locks_copy_conflock(struct file_lock *, struct file_lock *);
 extern void locks_remove_posix(struct file *, fl_owner_t);
 extern void locks_remove_file(struct file *);
 extern void locks_release_private(struct file_lock *);
@@ -980,11 +975,9 @@ extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
 extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
 extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
 extern void lease_get_mtime(struct inode *, struct timespec *time);
-extern int generic_setlease(struct file *, long, struct file_lock **);
-extern int vfs_setlease(struct file *, long, struct file_lock **);
-extern int lease_modify(struct file_lock **, int);
-extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
-extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
+extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
+extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
+extern int lease_modify(struct file_lock **, int, struct list_head *);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, unsigned int cmd,
 			      struct flock __user *user)
@@ -1013,12 +1006,12 @@ static inline int fcntl_setlk64(unsigned int fd, struct file *file,
 #endif
 static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
-	return 0;
+	return -EINVAL;
 }
 
 static inline int fcntl_getlease(struct file *filp)
 {
-	return 0;
+	return F_UNLCK;
 }
 
 static inline void locks_init_lock(struct file_lock *fl)
@@ -1026,7 +1019,7 @@ static inline void locks_init_lock(struct file_lock *fl)
 	return;
 }
 
-static inline void __locks_copy_lock(struct file_lock *new, struct file_lock *fl)
+static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
 	return;
 }
@@ -1100,33 +1093,22 @@ static inline void lease_get_mtime(struct inode *inode, struct timespec *time)
 }
 
 static inline int generic_setlease(struct file *filp, long arg,
-				    struct file_lock **flp)
+				    struct file_lock **flp, void **priv)
 {
 	return -EINVAL;
 }
 
 static inline int vfs_setlease(struct file *filp, long arg,
-			       struct file_lock **lease)
+			       struct file_lock **lease, void **priv)
 {
 	return -EINVAL;
 }
 
-static inline int lease_modify(struct file_lock **before, int arg)
+static inline int lease_modify(struct file_lock **before, int arg,
+			       struct list_head *dispose)
 {
 	return -EINVAL;
 }
-
-static inline int lock_may_read(struct inode *inode, loff_t start,
-				unsigned long len)
-{
-	return 1;
-}
-
-static inline int lock_may_write(struct inode *inode, loff_t start,
-				 unsigned long len)
-{
-	return 1;
-}
 #endif /* !CONFIG_FILE_LOCKING */
 
 
@@ -1151,8 +1133,8 @@ extern void fasync_free(struct fasync_struct *);
 /* can be called from interrupts */
 extern void kill_fasync(struct fasync_struct **, int, int);
 
-extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
-extern int f_setown(struct file *filp, unsigned long arg, int force);
+extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
+extern void f_setown(struct file *filp, unsigned long arg, int force);
 extern void f_delown(struct file *filp);
 extern pid_t f_getown(struct file *filp);
 extern int send_sigurg(struct fown_struct *fown);
@@ -1506,7 +1488,7 @@ struct file_operations {
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
-	int (*setlease)(struct file *, long, struct file_lock **);
+	int (*setlease)(struct file *, long, struct file_lock **, void **);
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
 	int (*show_fdinfo)(struct seq_file *m, struct file *f);
@@ -1855,7 +1837,8 @@ extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
 extern void kern_unmount(struct vfsmount *mnt);
 extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
-extern long do_mount(const char *, const char *, const char *, unsigned long, void *);
+extern long do_mount(const char *, const char __user *,
+		     const char *, unsigned long, void *);
 extern struct vfsmount *collect_mounts(struct path *);
 extern void drop_collected_mounts(struct vfsmount *);
 extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
@@ -1874,7 +1857,7 @@ extern int current_umask(void);
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
 
-static inline struct inode *file_inode(struct file *f)
+static inline struct inode *file_inode(const struct file *f)
 {
 	return f->f_inode;
 }
@@ -2611,6 +2594,7 @@ extern int simple_write_end(struct file *file, struct address_space *mapping,
 			struct page *page, void *fsdata);
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
+extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
 extern const struct dentry_operations simple_dentry_operations;
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h
index f49ddb1b2273..84d60cb841b1 100644
--- a/include/linux/fsl_ifc.h
+++ b/include/linux/fsl_ifc.h
@@ -781,13 +781,13 @@ struct fsl_ifc_regs {
 		__be32 amask;
 		u32 res4[0x2];
 	} amask_cs[FSL_IFC_BANK_COUNT];
-	u32 res5[0x17];
+	u32 res5[0x18];
 	struct {
-		__be32 csor_ext;
 		__be32 csor;
+		__be32 csor_ext;
 		u32 res6;
 	} csor_cs[FSL_IFC_BANK_COUNT];
-	u32 res7[0x19];
+	u32 res7[0x18];
 	struct {
 		__be32 ftim[4];
 		u32 res8[0x8];
diff --git a/include/linux/fsldma.h b/include/linux/fsldma.h
new file mode 100644
index 000000000000..b213c02963c9
--- /dev/null
+++ b/include/linux/fsldma.h
@@ -0,0 +1,13 @@
+/*
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef FSL_DMA_H
+#define FSL_DMA_H
+/* fsl dma API for enxternal start */
+int fsl_dma_external_start(struct dma_chan *dchan, int enable);
+
+#endif
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index f0b0edbf55a9..662697babd48 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -56,6 +56,8 @@ struct ftrace_ops;
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
 			      struct ftrace_ops *op, struct pt_regs *regs);
 
+ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
+
 /*
  * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
  * set in the flags member.
@@ -89,6 +91,9 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
  * INITIALIZED - The ftrace_ops has already been initialized (first use time
  *            register_ftrace_function() is called, it will initialized the ops)
  * DELETED - The ops are being deleted, do not let them be registered again.
+ * ADDING  - The ops is in the process of being added.
+ * REMOVING - The ops is in the process of being removed.
+ * MODIFYING - The ops is in the process of changing its filter functions.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
@@ -100,6 +105,9 @@ enum {
 	FTRACE_OPS_FL_STUB			= 1 << 6,
 	FTRACE_OPS_FL_INITIALIZED		= 1 << 7,
 	FTRACE_OPS_FL_DELETED			= 1 << 8,
+	FTRACE_OPS_FL_ADDING			= 1 << 9,
+	FTRACE_OPS_FL_REMOVING			= 1 << 10,
+	FTRACE_OPS_FL_MODIFYING			= 1 << 11,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -132,7 +140,7 @@ struct ftrace_ops {
 	int				nr_trampolines;
 	struct ftrace_ops_hash		local_hash;
 	struct ftrace_ops_hash		*func_hash;
-	struct ftrace_hash		*tramp_hash;
+	struct ftrace_ops_hash		old_hash;
 	unsigned long			trampoline;
 #endif
 };
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 1c2fdaa2ffc3..1ccaab44abcc 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -110,6 +110,10 @@ extern void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo,
 extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data);
 
+extern unsigned long gen_pool_first_fit_order_align(unsigned long *map,
+		unsigned long size, unsigned long start, unsigned int nr,
+		void *data);
+
 extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data);
 
@@ -117,6 +121,9 @@ extern struct gen_pool *devm_gen_pool_create(struct device *dev,
 		int min_alloc_order, int nid);
 extern struct gen_pool *dev_get_gen_pool(struct device *dev);
 
+bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
+			size_t size);
+
 #ifdef CONFIG_OF
 extern struct gen_pool *of_get_named_gen_pool(struct device_node *np,
 	const char *propname, int index);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 5e7219dc0fae..41b30fd4d041 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -156,7 +156,7 @@ struct vm_area_struct;
 #define GFP_DMA32	__GFP_DMA32
 
 /* Convert GFP flags to their corresponding migrate type */
-static inline int allocflags_to_migratetype(gfp_t gfp_flags)
+static inline int gfpflags_to_migratetype(const gfp_t gfp_flags)
 {
 	WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
 
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index c5e41da20112..249db3057e4d 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -56,6 +56,8 @@ struct seq_file;
  *	as the chip access may sleep when e.g. reading out the IRQ status
  *	registers.
  * @exported: flags if the gpiochip is exported for use from sysfs. Private.
+ * @irq_not_threaded: flag must be set if @can_sleep is set but the
+ *	IRQs don't need to be threaded
  *
  * A gpio_chip can help platforms abstract various sources of GPIOs so
  * they can all be accessed through a common programing interface.
@@ -101,6 +103,7 @@ struct gpio_chip {
 	struct gpio_desc	*desc;
 	const char		*const *names;
 	bool			can_sleep;
+	bool			irq_not_threaded;
 	bool			exported;
 
 #ifdef CONFIG_GPIOLIB_IRQCHIP
@@ -141,7 +144,7 @@ extern const char *gpiochip_is_requested(struct gpio_chip *chip,
 
 /* add/remove chips */
 extern int gpiochip_add(struct gpio_chip *chip);
-extern int gpiochip_remove(struct gpio_chip *chip);
+extern void gpiochip_remove(struct gpio_chip *chip);
 extern struct gpio_chip *gpiochip_find(void *data,
 			      int (*match)(struct gpio_chip *chip, void *data));
 
@@ -166,7 +169,8 @@ int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
 
 #endif /* CONFIG_GPIOLIB_IRQCHIP */
 
-int gpiochip_request_own_desc(struct gpio_desc *desc, const char *label);
+struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *chip, u16 hwnum,
+					    const char *label);
 void gpiochip_free_own_desc(struct gpio_desc *desc);
 
 #else /* CONFIG_GPIOLIB */
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 63579cb8d3dc..ad9051bab267 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -132,7 +132,7 @@ extern int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 		spinlock_t **ptl)
 {
-	VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
+	VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
 	if (pmd_trans_huge(*pmd))
 		return __pmd_trans_huge_lock(pmd, vma, ptl);
 	else
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 7cf5e9b32550..120ccc53fcb7 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -15,7 +15,7 @@ struct linux_binprm;
 
 #ifdef CONFIG_IMA
 extern int ima_bprm_check(struct linux_binprm *bprm);
-extern int ima_file_check(struct file *file, int mask);
+extern int ima_file_check(struct file *file, int mask, int opened);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
 extern int ima_module_check(struct file *file);
@@ -27,7 +27,7 @@ static inline int ima_bprm_check(struct linux_binprm *bprm)
 	return 0;
 }
 
-static inline int ima_file_check(struct file *file, int mask)
+static inline int ima_file_check(struct file *file, int mask, int opened)
 {
 	return 0;
 }
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 2bb4c4f3531a..77fc43f8fb72 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -111,12 +111,21 @@ extern struct group_info init_groups;
 #ifdef CONFIG_PREEMPT_RCU
 #define INIT_TASK_RCU_PREEMPT(tsk)					\
 	.rcu_read_lock_nesting = 0,					\
-	.rcu_read_unlock_special = 0,					\
+	.rcu_read_unlock_special.s = 0,					\
 	.rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),		\
 	INIT_TASK_RCU_TREE_PREEMPT()
 #else
 #define INIT_TASK_RCU_PREEMPT(tsk)
 #endif
+#ifdef CONFIG_TASKS_RCU
+#define INIT_TASK_RCU_TASKS(tsk)					\
+	.rcu_tasks_holdout = false,					\
+	.rcu_tasks_holdout_list =					\
+		LIST_HEAD_INIT(tsk.rcu_tasks_holdout_list),		\
+	.rcu_tasks_idle_cpu = -1,
+#else
+#define INIT_TASK_RCU_TASKS(tsk)
+#endif
 
 extern struct cred init_cred;
 
@@ -224,6 +233,7 @@ extern struct task_group root_task_group;
 	INIT_FTRACE_GRAPH						\
 	INIT_TRACE_RECURSION						\
 	INIT_TASK_RCU_PREEMPT(tsk)					\
+	INIT_TASK_RCU_TASKS(tsk)					\
 	INIT_CPUSET_SEQ(tsk)						\
 	INIT_RT_MUTEXES(tsk)						\
 	INIT_VTIME(tsk)							\
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 698ad053d064..69517a24bc50 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -193,11 +193,6 @@ extern void irq_wake_thread(unsigned int irq, void *dev_id);
 /* The following three functions are for the core kernel use only. */
 extern void suspend_device_irqs(void);
 extern void resume_device_irqs(void);
-#ifdef CONFIG_PM_SLEEP
-extern int check_wakeup_irqs(void);
-#else
-static inline int check_wakeup_irqs(void) { return 0; }
-#endif
 
 /**
  * struct irq_affinity_notify - context for notification of IRQ affinity changes
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 20f9a527922a..e6a7c9ff72f2 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -57,8 +57,11 @@ struct iommu_domain {
 	struct iommu_domain_geometry geometry;
 };
 
-#define IOMMU_CAP_CACHE_COHERENCY	0x1
-#define IOMMU_CAP_INTR_REMAP		0x2	/* isolates device intrs */
+enum iommu_cap {
+	IOMMU_CAP_CACHE_COHERENCY,	/* IOMMU can enforce cache coherent DMA
+					   transactions */
+	IOMMU_CAP_INTR_REMAP,		/* IOMMU supports interrupt isolation */
+};
 
 /*
  * Following constraints are specifc to FSL_PAMUV1:
@@ -80,6 +83,7 @@ enum iommu_attr {
 	DOMAIN_ATTR_FSL_PAMU_STASH,
 	DOMAIN_ATTR_FSL_PAMU_ENABLE,
 	DOMAIN_ATTR_FSL_PAMUV1,
+	DOMAIN_ATTR_NESTING,	/* two stages of translation */
 	DOMAIN_ATTR_MAX,
 };
 
@@ -94,7 +98,6 @@ enum iommu_attr {
  * @map: map a physically contiguous memory region to an iommu domain
  * @unmap: unmap a physically contiguous memory region from an iommu domain
  * @iova_to_phys: translate iova to physical address
- * @domain_has_cap: domain capabilities query
  * @add_device: add device to iommu grouping
  * @remove_device: remove device from iommu grouping
  * @domain_get_attr: Query domain attributes
@@ -102,6 +105,7 @@ enum iommu_attr {
  * @pgsize_bitmap: bitmap of supported page sizes
  */
 struct iommu_ops {
+	bool (*capable)(enum iommu_cap);
 	int (*domain_init)(struct iommu_domain *domain);
 	void (*domain_destroy)(struct iommu_domain *domain);
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
@@ -111,8 +115,6 @@ struct iommu_ops {
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size);
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova);
-	int (*domain_has_cap)(struct iommu_domain *domain,
-			      unsigned long cap);
 	int (*add_device)(struct device *dev);
 	void (*remove_device)(struct device *dev);
 	int (*device_group)(struct device *dev, unsigned int *groupid);
@@ -142,6 +144,7 @@ struct iommu_ops {
 
 extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops);
 extern bool iommu_present(struct bus_type *bus);
+extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap);
 extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus);
 extern struct iommu_group *iommu_group_get_by_id(int id);
 extern void iommu_domain_free(struct iommu_domain *domain);
@@ -154,8 +157,6 @@ extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 		       size_t size);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
-extern int iommu_domain_has_cap(struct iommu_domain *domain,
-				unsigned long cap);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
 
@@ -250,6 +251,11 @@ static inline bool iommu_present(struct bus_type *bus)
 	return false;
 }
 
+static inline bool iommu_capable(struct bus_type *bus, enum iommu_cap cap)
+{
+	return false;
+}
+
 static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
 {
 	return NULL;
@@ -304,12 +310,6 @@ static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_ad
 	return 0;
 }
 
-static inline int iommu_domain_has_cap(struct iommu_domain *domain,
-				       unsigned long cap)
-{
-	return 0;
-}
-
 static inline void iommu_set_fault_handler(struct iommu_domain *domain,
 				iommu_fault_handler_t handler, void *token)
 {
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 142ec544167c..2c5250222278 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -215,6 +215,11 @@ static inline int __deprecated check_region(resource_size_t s,
 
 /* Wrappers for managed devices */
 struct device;
+
+extern int devm_request_resource(struct device *dev, struct resource *root,
+				 struct resource *new);
+extern void devm_release_resource(struct device *dev, struct resource *new);
+
 #define devm_request_region(dev,start,n,name) \
 	__devm_request_region(dev, &ioport_resource, (start), (n), (name))
 #define devm_request_mem_region(dev,start,n,name) \
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 62af59242ddc..03f48d936f66 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -173,6 +173,7 @@ struct irq_data {
  * IRQD_IRQ_DISABLED		- Disabled state of the interrupt
  * IRQD_IRQ_MASKED		- Masked state of the interrupt
  * IRQD_IRQ_INPROGRESS		- In progress state of the interrupt
+ * IRQD_WAKEUP_ARMED		- Wakeup mode armed
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
@@ -186,6 +187,7 @@ enum {
 	IRQD_IRQ_DISABLED		= (1 << 16),
 	IRQD_IRQ_MASKED			= (1 << 17),
 	IRQD_IRQ_INPROGRESS		= (1 << 18),
+	IRQD_WAKEUP_ARMED		= (1 << 19),
 };
 
 static inline bool irqd_is_setaffinity_pending(struct irq_data *d)
@@ -257,6 +259,12 @@ static inline bool irqd_irq_inprogress(struct irq_data *d)
 	return d->state_use_accessors & IRQD_IRQ_INPROGRESS;
 }
 
+static inline bool irqd_is_wakeup_armed(struct irq_data *d)
+{
+	return d->state_use_accessors & IRQD_WAKEUP_ARMED;
+}
+
+
 /*
  * Functions for chained handlers which can be enabled/disabled by the
  * standard disable_irq/enable_irq calls. Must be called with
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index bf9422c3aefe..bf3fe719c7ce 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -39,9 +39,12 @@ bool irq_work_queue_on(struct irq_work *work, int cpu);
 #endif
 
 void irq_work_run(void);
+void irq_work_tick(void);
 void irq_work_sync(struct irq_work *work);
 
 #ifdef CONFIG_IRQ_WORK
+#include <asm/irq_work.h>
+
 bool irq_work_needs_cpu(void);
 #else
 static inline bool irq_work_needs_cpu(void) { return false; }
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 45e2d8c15bd2..13eed92c7d24 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -21,7 +21,11 @@
 #define GIC_CPU_ACTIVEPRIO		0xd0
 #define GIC_CPU_IDENT			0xfc
 
+#define GICC_ENABLE			0x1
+#define GICC_INT_PRI_THRESHOLD		0xf0
 #define GICC_IAR_INT_ID_MASK		0x3ff
+#define GICC_INT_SPURIOUS		1023
+#define GICC_DIS_BYPASS_MASK		0x1e0
 
 #define GIC_DIST_CTRL			0x000
 #define GIC_DIST_CTR			0x004
@@ -39,6 +43,18 @@
 #define GIC_DIST_SGI_PENDING_CLEAR	0xf10
 #define GIC_DIST_SGI_PENDING_SET	0xf20
 
+#define GICD_ENABLE			0x1
+#define GICD_DISABLE			0x0
+#define GICD_INT_ACTLOW_LVLTRIG		0x0
+#define GICD_INT_EN_CLR_X32		0xffffffff
+#define GICD_INT_EN_SET_SGI		0x0000ffff
+#define GICD_INT_EN_CLR_PPI		0xffff0000
+#define GICD_INT_DEF_PRI		0xa0
+#define GICD_INT_DEF_PRI_X4		((GICD_INT_DEF_PRI << 24) |\
+					(GICD_INT_DEF_PRI << 16) |\
+					(GICD_INT_DEF_PRI << 8) |\
+					GICD_INT_DEF_PRI)
+
 #define GICH_HCR			0x0
 #define GICH_VTR			0x4
 #define GICH_VMCR			0x8
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 472c021a2d4f..faf433af425e 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -12,6 +12,8 @@ struct irq_affinity_notify;
 struct proc_dir_entry;
 struct module;
 struct irq_desc;
+struct irq_domain;
+struct pt_regs;
 
 /**
  * struct irq_desc - interrupt descriptor
@@ -36,6 +38,11 @@ struct irq_desc;
  * @threads_oneshot:	bitfield to handle shared oneshot threads
  * @threads_active:	number of irqaction threads currently running
  * @wait_for_threads:	wait queue for sync_irq to wait for threaded handlers
+ * @nr_actions:		number of installed actions on this descriptor
+ * @no_suspend_depth:	number of irqactions on a irq descriptor with
+ *			IRQF_NO_SUSPEND set
+ * @force_resume_depth:	number of irqactions on a irq descriptor with
+ *			IRQF_FORCE_RESUME set
  * @dir:		/proc/irq/ procfs entry
  * @name:		flow handler name for /proc/interrupts output
  */
@@ -68,6 +75,11 @@ struct irq_desc {
 	unsigned long		threads_oneshot;
 	atomic_t		threads_active;
 	wait_queue_head_t       wait_for_threads;
+#ifdef CONFIG_PM_SLEEP
+	unsigned int		nr_actions;
+	unsigned int		no_suspend_depth;
+	unsigned int		force_resume_depth;
+#endif
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry	*dir;
 #endif
@@ -118,6 +130,23 @@ static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *de
 
 int generic_handle_irq(unsigned int irq);
 
+#ifdef CONFIG_HANDLE_DOMAIN_IRQ
+/*
+ * Convert a HW interrupt number to a logical one using a IRQ domain,
+ * and handle the result interrupt number. Return -EINVAL if
+ * conversion failed. Providing a NULL domain indicates that the
+ * conversion has already been done.
+ */
+int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq,
+			bool lookup, struct pt_regs *regs);
+
+static inline int handle_domain_irq(struct irq_domain *domain,
+				    unsigned int hwirq, struct pt_regs *regs)
+{
+	return __handle_domain_irq(domain, hwirq, true, regs);
+}
+#endif
+
 /* Test to see if a driver has successfully requested an irq */
 static inline int irq_has_action(unsigned int irq)
 {
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 784304b222b3..98f923b6a0ea 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -8,28 +8,28 @@
  * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com>
  *
  * Jump labels provide an interface to generate dynamic branches using
- * self-modifying code. Assuming toolchain and architecture support the result
- * of a "if (static_key_false(&key))" statement is a unconditional branch (which
+ * self-modifying code. Assuming toolchain and architecture support, the result
+ * of a "if (static_key_false(&key))" statement is an unconditional branch (which
  * defaults to false - and the true block is placed out of line).
  *
  * However at runtime we can change the branch target using
  * static_key_slow_{inc,dec}(). These function as a 'reference' count on the key
- * object and for as long as there are references all branches referring to
+ * object, and for as long as there are references all branches referring to
  * that particular key will point to the (out of line) true block.
  *
- * Since this relies on modifying code the static_key_slow_{inc,dec}() functions
+ * Since this relies on modifying code, the static_key_slow_{inc,dec}() functions
  * must be considered absolute slow paths (machine wide synchronization etc.).
- * OTOH, since the affected branches are unconditional their runtime overhead
+ * OTOH, since the affected branches are unconditional, their runtime overhead
  * will be absolutely minimal, esp. in the default (off) case where the total
  * effect is a single NOP of appropriate size. The on case will patch in a jump
  * to the out-of-line block.
  *
- * When the control is directly exposed to userspace it is prudent to delay the
+ * When the control is directly exposed to userspace, it is prudent to delay the
  * decrement to avoid high frequency code modifications which can (and do)
  * cause significant performance degradation. Struct static_key_deferred and
  * static_key_slow_dec_deferred() provide for this.
  *
- * Lacking toolchain and or architecture support, it falls back to a simple
+ * Lacking toolchain and or architecture support, jump labels fall back to a simple
  * conditional branch.
  *
  * struct static_key my_key = STATIC_KEY_INIT_TRUE;
@@ -43,8 +43,7 @@
  *
  * Not initializing the key (static data is initialized to 0s anyway) is the
  * same as using STATIC_KEY_INIT_FALSE.
- *
-*/
+ */
 
 #include <linux/types.h>
 #include <linux/compiler.h>
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 95624bed87ef..40728cf1c452 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -376,10 +376,6 @@ extern unsigned long simple_strtoul(const char *,char **,unsigned int);
 extern long simple_strtol(const char *,char **,unsigned int);
 extern unsigned long long simple_strtoull(const char *,char **,unsigned int);
 extern long long simple_strtoll(const char *,char **,unsigned int);
-#define strict_strtoul	kstrtoul
-#define strict_strtol	kstrtol
-#define strict_strtoull	kstrtoull
-#define strict_strtoll	kstrtoll
 
 extern int num_to_str(char *buf, int size, unsigned long long num);
 
@@ -496,6 +492,7 @@ static inline char *hex_byte_pack_upper(char *buf, u8 byte)
 
 extern int hex_to_bin(char ch);
 extern int __must_check hex2bin(u8 *dst, const char *src, size_t count);
+extern char *bin2hex(char *dst, const void *src, size_t count);
 
 bool mac_pton(const char *s, u8 *mac);
 
@@ -715,23 +712,8 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 	(void) (&_max1 == &_max2);		\
 	_max1 > _max2 ? _max1 : _max2; })
 
-#define min3(x, y, z) ({			\
-	typeof(x) _min1 = (x);			\
-	typeof(y) _min2 = (y);			\
-	typeof(z) _min3 = (z);			\
-	(void) (&_min1 == &_min2);		\
-	(void) (&_min1 == &_min3);		\
-	_min1 < _min2 ? (_min1 < _min3 ? _min1 : _min3) : \
-		(_min2 < _min3 ? _min2 : _min3); })
-
-#define max3(x, y, z) ({			\
-	typeof(x) _max1 = (x);			\
-	typeof(y) _max2 = (y);			\
-	typeof(z) _max3 = (z);			\
-	(void) (&_max1 == &_max2);		\
-	(void) (&_max1 == &_max3);		\
-	_max1 > _max2 ? (_max1 > _max3 ? _max1 : _max3) : \
-		(_max2 > _max3 ? _max2 : _max3); })
+#define min3(x, y, z) min((typeof(x))min(x, y), z)
+#define max3(x, y, z) max((typeof(x))max(x, y), z)
 
 /**
  * min_not_zero - return the minimum that is _not_ zero, unless both are zero
@@ -746,20 +728,13 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 /**
  * clamp - return a value clamped to a given range with strict typechecking
  * @val: current value
- * @min: minimum allowable value
- * @max: maximum allowable value
+ * @lo: lowest allowable value
+ * @hi: highest allowable value
  *
- * This macro does strict typechecking of min/max to make sure they are of the
+ * This macro does strict typechecking of lo/hi to make sure they are of the
  * same type as val.  See the unnecessary pointer comparisons.
  */
-#define clamp(val, min, max) ({			\
-	typeof(val) __val = (val);		\
-	typeof(min) __min = (min);		\
-	typeof(max) __max = (max);		\
-	(void) (&__val == &__min);		\
-	(void) (&__val == &__max);		\
-	__val = __val < __min ? __min: __val;	\
-	__val > __max ? __max: __val; })
+#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
 
 /*
  * ..and if you can't take the strict
@@ -781,36 +756,26 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
  * clamp_t - return a value clamped to a given range using a given type
  * @type: the type of variable to use
  * @val: current value
- * @min: minimum allowable value
- * @max: maximum allowable value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
  *
  * This macro does no typechecking and uses temporary variables of type
  * 'type' to make all the comparisons.
  */
-#define clamp_t(type, val, min, max) ({		\
-	type __val = (val);			\
-	type __min = (min);			\
-	type __max = (max);			\
-	__val = __val < __min ? __min: __val;	\
-	__val > __max ? __max: __val; })
+#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
 
 /**
  * clamp_val - return a value clamped to a given range using val's type
  * @val: current value
- * @min: minimum allowable value
- * @max: maximum allowable value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
  *
  * This macro does no typechecking and uses temporary variables of whatever
  * type the input argument 'val' is.  This is useful when val is an unsigned
  * type and min and max are literals that will otherwise be assigned a signed
  * integer type.
  */
-#define clamp_val(val, min, max) ({		\
-	typeof(val) __val = (val);		\
-	typeof(val) __min = (min);		\
-	typeof(val) __max = (max);		\
-	__val = __val < __min ? __min: __val;	\
-	__val > __max ? __max: __val; })
+#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
 
 
 /*
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index ecbc52f9ff77..8422b4ed6882 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -44,8 +44,8 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 DECLARE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
 
 /* Must have preemption disabled for this to be meaningful. */
-#define kstat_this_cpu (&__get_cpu_var(kstat))
-#define kcpustat_this_cpu (&__get_cpu_var(kernel_cpustat))
+#define kstat_this_cpu this_cpu_ptr(&kstat)
+#define kcpustat_this_cpu this_cpu_ptr(&kernel_cpustat)
 #define kstat_cpu(cpu) per_cpu(kstat, cpu)
 #define kcpustat_cpu(cpu) per_cpu(kernel_cpustat, cpu)
 
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 4b2a0e11cc5b..9d957b7ae095 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -178,6 +178,7 @@ struct kexec_buf {
 	struct kimage *image;
 	char *buffer;
 	unsigned long bufsz;
+	unsigned long mem;
 	unsigned long memsz;
 	unsigned long buf_align;
 	unsigned long buf_min;
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 44792ee649de..ff9f1d394235 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -53,6 +53,24 @@ typedef int (*request_key_actor_t)(struct key_construction *key,
 				   const char *op, void *aux);
 
 /*
+ * Preparsed matching criterion.
+ */
+struct key_match_data {
+	/* Comparison function, defaults to exact description match, but can be
+	 * overridden by type->match_preparse().  Should return true if a match
+	 * is found and false if not.
+	 */
+	bool (*cmp)(const struct key *key,
+		    const struct key_match_data *match_data);
+
+	const void	*raw_data;	/* Raw match data */
+	void		*preparsed;	/* For ->match_preparse() to stash stuff */
+	unsigned	lookup_type;	/* Type of lookup for this search. */
+#define KEYRING_SEARCH_LOOKUP_DIRECT	0x0000	/* Direct lookup by description. */
+#define KEYRING_SEARCH_LOOKUP_ITERATE	0x0001	/* Iterative search. */
+};
+
+/*
  * kernel managed key type definition
  */
 struct key_type {
@@ -65,11 +83,6 @@ struct key_type {
 	 */
 	size_t def_datalen;
 
-	/* Default key search algorithm. */
-	unsigned def_lookup_type;
-#define KEYRING_SEARCH_LOOKUP_DIRECT	0x0000	/* Direct lookup by description. */
-#define KEYRING_SEARCH_LOOKUP_ITERATE	0x0001	/* Iterative search. */
-
 	/* vet a description */
 	int (*vet_description)(const char *description);
 
@@ -96,8 +109,15 @@ struct key_type {
 	 */
 	int (*update)(struct key *key, struct key_preparsed_payload *prep);
 
-	/* match a key against a description */
-	int (*match)(const struct key *key, const void *desc);
+	/* Preparse the data supplied to ->match() (optional).  The
+	 * data to be preparsed can be found in match_data->raw_data.
+	 * The lookup type can also be set by this function.
+	 */
+	int (*match_preparse)(struct key_match_data *match_data);
+
+	/* Free preparsed match data (optional).  This should be supplied it
+	 * ->match_preparse() is supplied. */
+	void (*match_free)(struct key_match_data *match_data);
 
 	/* clear some of the data from a key on revokation (optional)
 	 * - the key's semaphore will be write-locked by the caller
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 92abb497ab14..bd5fefeaf548 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1404,14 +1404,14 @@ static inline int sata_srst_pmp(struct ata_link *link)
  * printk helpers
  */
 __printf(3, 4)
-int ata_port_printk(const struct ata_port *ap, const char *level,
-		    const char *fmt, ...);
+void ata_port_printk(const struct ata_port *ap, const char *level,
+		     const char *fmt, ...);
 __printf(3, 4)
-int ata_link_printk(const struct ata_link *link, const char *level,
-		    const char *fmt, ...);
+void ata_link_printk(const struct ata_link *link, const char *level,
+		     const char *fmt, ...);
 __printf(3, 4)
-int ata_dev_printk(const struct ata_device *dev, const char *level,
-		   const char *fmt, ...);
+void ata_dev_printk(const struct ata_device *dev, const char *level,
+		    const char *fmt, ...);
 
 #define ata_port_err(ap, fmt, ...)				\
 	ata_port_printk(ap, KERN_ERR, fmt, ##__VA_ARGS__)
diff --git a/include/linux/list.h b/include/linux/list.h
index cbbb96fcead9..f33f831eb3c8 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -5,6 +5,7 @@
 #include <linux/stddef.h>
 #include <linux/poison.h>
 #include <linux/const.h>
+#include <linux/kernel.h>
 
 /*
  * Simple doubly linked list implementation.
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 219d79627c05..ff82a32871b5 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -178,7 +178,6 @@ struct nlm_block {
 	unsigned char		b_granted;	/* VFS granted lock */
 	struct nlm_file *	b_file;		/* file in question */
 	struct cache_req *	b_cache_req;	/* deferred request handling */
-	struct file_lock *	b_fl;		/* set for GETLK */
 	struct cache_deferred_req * b_deferred_req;
 	unsigned int		b_flags;	/* block flags */
 #define B_QUEUED		1	/* lock queued */
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 64c7425afbce..74ab23176e9b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -4,7 +4,7 @@
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
  *
- * see Documentation/lockdep-design.txt for more details.
+ * see Documentation/locking/lockdep-design.txt for more details.
  */
 #ifndef __LINUX_LOCKDEP_H
 #define __LINUX_LOCKDEP_H
@@ -510,6 +510,7 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 
 #define lock_map_acquire(l)			lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_)
 #define lock_map_acquire_read(l)		lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_)
+#define lock_map_acquire_tryread(l)		lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_)
 #define lock_map_release(l)			lock_release(l, 1, _THIS_IP_)
 
 #ifdef CONFIG_PROVE_LOCKING
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e0752d204d9e..19df5d857411 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -440,11 +440,6 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
 int memcg_cache_id(struct mem_cgroup *memcg);
 
-int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s,
-			     struct kmem_cache *root_cache);
-void memcg_free_cache_params(struct kmem_cache *s);
-
-int memcg_update_cache_size(struct kmem_cache *s, int num_groups);
 void memcg_update_array_size(int num_groups);
 
 struct kmem_cache *
@@ -574,16 +569,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return -1;
 }
 
-static inline int memcg_alloc_cache_params(struct mem_cgroup *memcg,
-		struct kmem_cache *s, struct kmem_cache *root_cache)
-{
-	return 0;
-}
-
-static inline void memcg_free_cache_params(struct kmem_cache *s)
-{
-}
-
 static inline struct kmem_cache *
 memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index d9524c49d767..8f1a41951df9 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -84,6 +84,7 @@ extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
 /* VM interface that may be used by firmware interface */
 extern int online_pages(unsigned long, unsigned long, int);
+extern int test_pages_in_a_zone(unsigned long, unsigned long);
 extern void __offline_isolated_pages(unsigned long, unsigned long);
 
 typedef void (*online_page_callback_t)(struct page *page);
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index f230a978e6ba..3d385c81c153 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -134,9 +134,10 @@ void mpol_free_shared_policy(struct shared_policy *p);
 struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
 					    unsigned long idx);
 
-struct mempolicy *get_vma_policy(struct task_struct *tsk,
-		struct vm_area_struct *vma, unsigned long addr);
-bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma);
+struct mempolicy *get_task_policy(struct task_struct *p);
+struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
+		unsigned long addr);
+bool vma_policy_mof(struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);
 extern void numa_policy_init(void);
diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index dbd23c36de21..c0b075f6bc35 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -27,6 +27,7 @@
 #define ARIZONA_WRITE_SEQUENCER_CTRL_0           0x16
 #define ARIZONA_WRITE_SEQUENCER_CTRL_1           0x17
 #define ARIZONA_WRITE_SEQUENCER_CTRL_2           0x18
+#define ARIZONA_WRITE_SEQUENCER_CTRL_3           0x19
 #define ARIZONA_WRITE_SEQUENCER_PROM             0x1A
 #define ARIZONA_TONE_GENERATOR_1                 0x20
 #define ARIZONA_TONE_GENERATOR_2                 0x21
@@ -70,7 +71,9 @@
 #define ARIZONA_SAMPLE_RATE_3_STATUS             0x10C
 #define ARIZONA_ASYNC_CLOCK_1                    0x112
 #define ARIZONA_ASYNC_SAMPLE_RATE_1              0x113
+#define ARIZONA_ASYNC_SAMPLE_RATE_2              0x114
 #define ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS       0x11B
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS       0x11C
 #define ARIZONA_OUTPUT_SYSTEM_CLOCK              0x149
 #define ARIZONA_OUTPUT_ASYNC_CLOCK               0x14A
 #define ARIZONA_RATE_ESTIMATOR_1                 0x152
@@ -1664,16 +1667,30 @@
 /*
  * R275 (0x113) - Async sample rate 1
  */
-#define ARIZONA_ASYNC_SAMPLE_RATE_MASK           0x001F  /* ASYNC_SAMPLE_RATE - [4:0] */
-#define ARIZONA_ASYNC_SAMPLE_RATE_SHIFT               0  /* ASYNC_SAMPLE_RATE - [4:0] */
-#define ARIZONA_ASYNC_SAMPLE_RATE_WIDTH               5  /* ASYNC_SAMPLE_RATE - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_MASK         0x001F  /* ASYNC_SAMPLE_RATE_1 - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_SHIFT             0  /* ASYNC_SAMPLE_RATE_1 - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_WIDTH             5  /* ASYNC_SAMPLE_RATE_1 - [4:0] */
+
+/*
+ * R276 (0x114) - Async sample rate 2
+ */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_MASK         0x001F  /* ASYNC_SAMPLE_RATE_2 - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_SHIFT             0  /* ASYNC_SAMPLE_RATE_2 - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_WIDTH             5  /* ASYNC_SAMPLE_RATE_2 - [4:0] */
 
 /*
  * R283 (0x11B) - Async sample rate 1 status
  */
-#define ARIZONA_ASYNC_SAMPLE_RATE_STS_MASK       0x001F  /* ASYNC_SAMPLE_RATE_STS - [4:0] */
-#define ARIZONA_ASYNC_SAMPLE_RATE_STS_SHIFT           0  /* ASYNC_SAMPLE_RATE_STS - [4:0] */
-#define ARIZONA_ASYNC_SAMPLE_RATE_STS_WIDTH           5  /* ASYNC_SAMPLE_RATE_STS - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_STS_MASK     0x001F  /* ASYNC_SAMPLE_RATE_1_STS - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_STS_SHIFT         0  /* ASYNC_SAMPLE_RATE_1_STS - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_1_STS_WIDTH         5  /* ASYNC_SAMPLE_RATE_1_STS - [4:0] */
+
+/*
+ * R284 (0x11C) - Async sample rate 2 status
+ */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_STS_MASK     0x001F  /* ASYNC_SAMPLE_RATE_2_STS - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_STS_SHIFT         0  /* ASYNC_SAMPLE_RATE_2_STS - [4:0] */
+#define ARIZONA_ASYNC_SAMPLE_RATE_2_STS_WIDTH         5  /* ASYNC_SAMPLE_RATE_2_STS - [4:0] */
 
 /*
  * R329 (0x149) - Output system clock
diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h
index f543de91ce19..73e1709d4c09 100644
--- a/include/linux/mfd/core.h
+++ b/include/linux/mfd/core.h
@@ -44,6 +44,9 @@ struct mfd_cell {
 	 */
 	const char		*of_compatible;
 
+	/* Matches ACPI PNP id, either _HID or _CID */
+	const char		*acpi_pnpid;
+
 	/*
 	 * These resources can be specified relative to the parent device.
 	 * For accessing hardware you should use resources from the platform dev
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
index fcbe9d129a9d..0e166b92f5b4 100644
--- a/include/linux/mfd/cros_ec.h
+++ b/include/linux/mfd/cros_ec.h
@@ -62,10 +62,6 @@ struct cros_ec_command {
  * @dev: Device pointer
  * @was_wake_device: true if this device was set to wake the system from
  * sleep at the last suspend
- * @cmd_xfer: send command to EC and get response
- *     Returns the number of bytes received if the communication succeeded, but
- *     that doesn't mean the EC was happy with the command. The caller
- *     should check msg.result for the EC's result code.
  *
  * @priv: Private data
  * @irq: Interrupt to use
@@ -82,6 +78,10 @@ struct cros_ec_command {
  * @dout_size: size of dout buffer to allocate (zero to use static dout)
  * @parent: pointer to parent device (e.g. i2c or spi device)
  * @wake_enabled: true if this device can wake the system from sleep
+ * @cmd_xfer: send command to EC and get response
+ *     Returns the number of bytes received if the communication succeeded, but
+ *     that doesn't mean the EC was happy with the command. The caller
+ *     should check msg.result for the EC's result code.
  * @lock: one transaction at a time
  */
 struct cros_ec_device {
@@ -92,8 +92,6 @@ struct cros_ec_device {
 	struct device *dev;
 	bool was_wake_device;
 	struct class *cros_class;
-	int (*cmd_xfer)(struct cros_ec_device *ec,
-			struct cros_ec_command *msg);
 
 	/* These are used to implement the platform-specific interface */
 	void *priv;
@@ -104,6 +102,8 @@ struct cros_ec_device {
 	int dout_size;
 	struct device *parent;
 	bool wake_enabled;
+	int (*cmd_xfer)(struct cros_ec_device *ec,
+			struct cros_ec_command *msg);
 	struct mutex lock;
 };
 
@@ -153,6 +153,18 @@ int cros_ec_check_result(struct cros_ec_device *ec_dev,
 			 struct cros_ec_command *msg);
 
 /**
+ * cros_ec_cmd_xfer - Send a command to the ChromeOS EC
+ *
+ * Call this to send a command to the ChromeOS EC.  This should be used
+ * instead of calling the EC's cmd_xfer() callback directly.
+ *
+ * @ec_dev: EC device
+ * @msg: Message to write
+ */
+int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
+		     struct cros_ec_command *msg);
+
+/**
  * cros_ec_remove - Remove a ChromeOS EC
  *
  * Call this to deregister a ChromeOS EC, then clean up any private data.
diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h
index bba65f51a0b5..c18a4c19d6fc 100644
--- a/include/linux/mfd/da9052/da9052.h
+++ b/include/linux/mfd/da9052/da9052.h
@@ -211,7 +211,7 @@ static inline int da9052_reg_update(struct da9052 *da9052, unsigned char reg,
 int da9052_device_init(struct da9052 *da9052, u8 chip_id);
 void da9052_device_exit(struct da9052 *da9052);
 
-extern struct regmap_config da9052_regmap_config;
+extern const struct regmap_config da9052_regmap_config;
 
 int da9052_irq_init(struct da9052 *da9052);
 int da9052_irq_exit(struct da9052 *da9052);
diff --git a/include/linux/mfd/davinci_voicecodec.h b/include/linux/mfd/davinci_voicecodec.h
index 5166935ce66d..cb01496bfa49 100644
--- a/include/linux/mfd/davinci_voicecodec.h
+++ b/include/linux/mfd/davinci_voicecodec.h
@@ -21,7 +21,7 @@
  */
 
 #ifndef __LINUX_MFD_DAVINCI_VOICECODEC_H_
-#define __LINUX_MFD_DAVINIC_VOICECODEC_H_
+#define __LINUX_MFD_DAVINCI_VOICECODEC_H_
 
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
diff --git a/include/linux/mfd/hi6421-pmic.h b/include/linux/mfd/hi6421-pmic.h
new file mode 100644
index 000000000000..587273e35acf
--- /dev/null
+++ b/include/linux/mfd/hi6421-pmic.h
@@ -0,0 +1,41 @@
+/*
+ * Header file for device driver Hi6421 PMIC
+ *
+ * Copyright (c) <2011-2014> HiSilicon Technologies Co., Ltd.
+ *              http://www.hisilicon.com
+ * Copyright (c) <2013-2014> Linaro Ltd.
+ *              http://www.linaro.org
+ *
+ * Author: Guodong Xu <guodong.xu@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef	__HI6421_PMIC_H
+#define	__HI6421_PMIC_H
+
+/* Hi6421 registers are mapped to memory bus in 4 bytes stride */
+#define HI6421_REG_TO_BUS_ADDR(x)	(x << 2)
+
+/* Hi6421 maximum register number */
+#define HI6421_REG_MAX			0xFF
+
+/* Hi6421 OCP (over current protection) and DEB (debounce) control register */
+#define	HI6421_OCP_DEB_CTRL_REG		HI6421_REG_TO_BUS_ADDR(0x51)
+#define	HI6421_OCP_DEB_SEL_MASK		0x0C
+#define HI6421_OCP_DEB_SEL_8MS		0x00
+#define HI6421_OCP_DEB_SEL_16MS		0x04
+#define HI6421_OCP_DEB_SEL_32MS		0x08
+#define HI6421_OCP_DEB_SEL_64MS		0x0C
+#define HI6421_OCP_EN_DEBOUNCE_MASK	0x02
+#define HI6421_OCP_EN_DEBOUNCE_ENABLE	0x02
+#define HI6421_OCP_AUTO_STOP_MASK	0x01
+#define HI6421_OCP_AUTO_STOP_ENABLE	0x01
+
+struct hi6421_pmic {
+	struct regmap		*regmap;
+};
+
+#endif		/* __HI6421_PMIC_H */
diff --git a/include/linux/mfd/max14577-private.h b/include/linux/mfd/max14577-private.h
index 499253604026..f01c1fae4d84 100644
--- a/include/linux/mfd/max14577-private.h
+++ b/include/linux/mfd/max14577-private.h
@@ -72,15 +72,33 @@ enum max14577_muic_reg {
 	MAX14577_MUIC_REG_END,
 };
 
+/*
+ * Combined charger types for max14577 and max77836.
+ *
+ * On max14577 three lower bits map to STATUS2/CHGTYP field.
+ * However the max77836 has different two last values of STATUS2/CHGTYP.
+ * To indicate the difference enum has two additional values for max77836.
+ * These values are just a register value bitwise OR with 0x8.
+ */
 enum max14577_muic_charger_type {
-	MAX14577_CHARGER_TYPE_NONE = 0,
-	MAX14577_CHARGER_TYPE_USB,
-	MAX14577_CHARGER_TYPE_DOWNSTREAM_PORT,
-	MAX14577_CHARGER_TYPE_DEDICATED_CHG,
-	MAX14577_CHARGER_TYPE_SPECIAL_500MA,
-	MAX14577_CHARGER_TYPE_SPECIAL_1A,
-	MAX14577_CHARGER_TYPE_RESERVED,
-	MAX14577_CHARGER_TYPE_DEAD_BATTERY = 7,
+	MAX14577_CHARGER_TYPE_NONE		= 0x0,
+	MAX14577_CHARGER_TYPE_USB		= 0x1,
+	MAX14577_CHARGER_TYPE_DOWNSTREAM_PORT	= 0x2,
+	MAX14577_CHARGER_TYPE_DEDICATED_CHG	= 0x3,
+	MAX14577_CHARGER_TYPE_SPECIAL_500MA	= 0x4,
+	/* Special 1A or 2A charger */
+	MAX14577_CHARGER_TYPE_SPECIAL_1A	= 0x5,
+	/* max14577: reserved, used on max77836 */
+	MAX14577_CHARGER_TYPE_RESERVED		= 0x6,
+	/* max14577: dead-battery charing with maximum current 100mA */
+	MAX14577_CHARGER_TYPE_DEAD_BATTERY	= 0x7,
+	/*
+	 * max77836: special charger (bias on D+/D-),
+	 * matches register value of 0x6
+	 */
+	MAX77836_CHARGER_TYPE_SPECIAL_BIAS	= 0xe,
+	/* max77836: reserved, register value 0x7 */
+	MAX77836_CHARGER_TYPE_RESERVED		= 0xf,
 };
 
 /* MAX14577 interrupts */
@@ -121,13 +139,15 @@ enum max14577_muic_charger_type {
 #define STATUS2_CHGTYP_SHIFT		0
 #define STATUS2_CHGDETRUN_SHIFT		3
 #define STATUS2_DCDTMR_SHIFT		4
-#define STATUS2_DBCHG_SHIFT		5
+#define MAX14577_STATUS2_DBCHG_SHIFT	5
+#define MAX77836_STATUS2_DXOVP_SHIFT	5
 #define STATUS2_VBVOLT_SHIFT		6
 #define MAX77836_STATUS2_VIDRM_SHIFT	7
 #define STATUS2_CHGTYP_MASK		(0x7 << STATUS2_CHGTYP_SHIFT)
 #define STATUS2_CHGDETRUN_MASK		BIT(STATUS2_CHGDETRUN_SHIFT)
 #define STATUS2_DCDTMR_MASK		BIT(STATUS2_DCDTMR_SHIFT)
-#define STATUS2_DBCHG_MASK		BIT(STATUS2_DBCHG_SHIFT)
+#define MAX14577_STATUS2_DBCHG_MASK	BIT(MAX14577_STATUS2_DBCHG_SHIFT)
+#define MAX77836_STATUS2_DXOVP_MASK	BIT(MAX77836_STATUS2_DXOVP_SHIFT)
 #define STATUS2_VBVOLT_MASK		BIT(STATUS2_VBVOLT_SHIFT)
 #define MAX77836_STATUS2_VIDRM_MASK	BIT(MAX77836_STATUS2_VIDRM_SHIFT)
 
@@ -177,9 +197,11 @@ enum max14577_muic_charger_type {
 #define CTRL3_JIGSET_SHIFT		0
 #define CTRL3_BOOTSET_SHIFT		2
 #define CTRL3_ADCDBSET_SHIFT		4
+#define CTRL3_WBTH_SHIFT		6
 #define CTRL3_JIGSET_MASK		(0x3 << CTRL3_JIGSET_SHIFT)
 #define CTRL3_BOOTSET_MASK		(0x3 << CTRL3_BOOTSET_SHIFT)
 #define CTRL3_ADCDBSET_MASK		(0x3 << CTRL3_ADCDBSET_SHIFT)
+#define CTRL3_WBTH_MASK			(0x3 << CTRL3_WBTH_SHIFT)
 
 /* Slave addr = 0x4A: Charger */
 enum max14577_charger_reg {
@@ -210,16 +232,20 @@ enum max14577_charger_reg {
 #define CDETCTRL1_CHGTYPMAN_SHIFT	1
 #define CDETCTRL1_DCDEN_SHIFT		2
 #define CDETCTRL1_DCD2SCT_SHIFT		3
-#define CDETCTRL1_DCHKTM_SHIFT		4
-#define CDETCTRL1_DBEXIT_SHIFT		5
+#define MAX14577_CDETCTRL1_DCHKTM_SHIFT	4
+#define MAX77836_CDETCTRL1_CDLY_SHIFT	4
+#define MAX14577_CDETCTRL1_DBEXIT_SHIFT	5
+#define MAX77836_CDETCTRL1_DCDCPL_SHIFT	5
 #define CDETCTRL1_DBIDLE_SHIFT		6
 #define CDETCTRL1_CDPDET_SHIFT		7
 #define CDETCTRL1_CHGDETEN_MASK		BIT(CDETCTRL1_CHGDETEN_SHIFT)
 #define CDETCTRL1_CHGTYPMAN_MASK	BIT(CDETCTRL1_CHGTYPMAN_SHIFT)
 #define CDETCTRL1_DCDEN_MASK		BIT(CDETCTRL1_DCDEN_SHIFT)
 #define CDETCTRL1_DCD2SCT_MASK		BIT(CDETCTRL1_DCD2SCT_SHIFT)
-#define CDETCTRL1_DCHKTM_MASK		BIT(CDETCTRL1_DCHKTM_SHIFT)
-#define CDETCTRL1_DBEXIT_MASK		BIT(CDETCTRL1_DBEXIT_SHIFT)
+#define MAX14577_CDETCTRL1_DCHKTM_MASK	BIT(MAX14577_CDETCTRL1_DCHKTM_SHIFT)
+#define MAX77836_CDETCTRL1_CDDLY_MASK	BIT(MAX77836_CDETCTRL1_CDDLY_SHIFT)
+#define MAX14577_CDETCTRL1_DBEXIT_MASK	BIT(MAX14577_CDETCTRL1_DBEXIT_SHIFT)
+#define MAX77836_CDETCTRL1_DCDCPL_MASK	BIT(MAX77836_CDETCTRL1_DCDCPL_SHIFT)
 #define CDETCTRL1_DBIDLE_MASK		BIT(CDETCTRL1_DBIDLE_SHIFT)
 #define CDETCTRL1_CDPDET_MASK		BIT(CDETCTRL1_CDPDET_SHIFT)
 
@@ -255,17 +281,36 @@ enum max14577_charger_reg {
 #define CHGCTRL7_OTPCGHCVS_SHIFT	0
 #define CHGCTRL7_OTPCGHCVS_MASK		(0x3 << CHGCTRL7_OTPCGHCVS_SHIFT)
 
-/* MAX14577 regulator current limits (as in CHGCTRL4 register), uA */
-#define MAX14577_REGULATOR_CURRENT_LIMIT_MIN		 90000
-#define MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_START	200000
-#define MAX14577_REGULATOR_CURRENT_LIMIT_HIGH_STEP	 50000
-#define MAX14577_REGULATOR_CURRENT_LIMIT_MAX		950000
-
-/* MAX77836 regulator current limits (as in CHGCTRL4 register), uA */
-#define MAX77836_REGULATOR_CURRENT_LIMIT_MIN		 45000
-#define MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_START	100000
-#define MAX77836_REGULATOR_CURRENT_LIMIT_HIGH_STEP	 25000
-#define MAX77836_REGULATOR_CURRENT_LIMIT_MAX		475000
+/* MAX14577 charger current limits (as in CHGCTRL4 register), uA */
+#define MAX14577_CHARGER_CURRENT_LIMIT_MIN		 90000U
+#define MAX14577_CHARGER_CURRENT_LIMIT_HIGH_START	200000U
+#define MAX14577_CHARGER_CURRENT_LIMIT_HIGH_STEP	 50000U
+#define MAX14577_CHARGER_CURRENT_LIMIT_MAX		950000U
+
+/* MAX77836 charger current limits (as in CHGCTRL4 register), uA */
+#define MAX77836_CHARGER_CURRENT_LIMIT_MIN		 45000U
+#define MAX77836_CHARGER_CURRENT_LIMIT_HIGH_START	100000U
+#define MAX77836_CHARGER_CURRENT_LIMIT_HIGH_STEP	 25000U
+#define MAX77836_CHARGER_CURRENT_LIMIT_MAX		475000U
+
+/*
+ * MAX14577 charger End-Of-Charge current limits
+ * (as in CHGCTRL5 register), uA
+ */
+#define MAX14577_CHARGER_EOC_CURRENT_LIMIT_MIN		50000U
+#define MAX14577_CHARGER_EOC_CURRENT_LIMIT_STEP		10000U
+#define MAX14577_CHARGER_EOC_CURRENT_LIMIT_MAX		200000U
+
+/*
+ * MAX14577/MAX77836 Battery Constant Voltage
+ * (as in CHGCTRL3 register), uV
+ */
+#define MAXIM_CHARGER_CONSTANT_VOLTAGE_MIN		4000000U
+#define MAXIM_CHARGER_CONSTANT_VOLTAGE_STEP		20000U
+#define MAXIM_CHARGER_CONSTANT_VOLTAGE_MAX		4350000U
+
+/* Default value for fast charge timer, in hours */
+#define MAXIM_CHARGER_FAST_CHARGE_TIMER_DEFAULT		5
 
 /* MAX14577 regulator SFOUT LDO voltage, fixed, uV */
 #define MAX14577_REGULATOR_SAFEOUT_VOLTAGE		4900000
diff --git a/include/linux/mfd/max14577.h b/include/linux/mfd/max14577.h
index c83fbed1c7b6..ccfaf952c31b 100644
--- a/include/linux/mfd/max14577.h
+++ b/include/linux/mfd/max14577.h
@@ -54,6 +54,13 @@ struct max14577_regulator_platform_data {
 	struct device_node *of_node;
 };
 
+struct max14577_charger_platform_data {
+	u32 constant_uvolt;
+	u32 fast_charge_uamp;
+	u32 eoc_uamp;
+	u32 ovp_uvolt;
+};
+
 /*
  * MAX14577 MFD platform data
  */
@@ -74,4 +81,27 @@ struct max14577_platform_data {
 	struct max14577_regulator_platform_data *regulators;
 };
 
+/*
+ * Valid limits of current for max14577 and max77836 chargers.
+ * They must correspond to MBCICHWRCL and MBCICHWRCH fields in CHGCTRL4
+ * register for given chipset.
+ */
+struct maxim_charger_current {
+	/* Minimal current, set in CHGCTRL4/MBCICHWRCL, uA */
+	unsigned int min;
+	/*
+	 * Minimal current when high setting is active,
+	 * set in CHGCTRL4/MBCICHWRCH, uA
+	 */
+	unsigned int high_start;
+	/* Value of one step in high setting, uA */
+	unsigned int high_step;
+	/* Maximum current of high setting, uA */
+	unsigned int max;
+};
+
+extern const struct maxim_charger_current maxim_charger_currents[];
+extern int maxim_charger_calc_reg_current(const struct maxim_charger_current *limits,
+		unsigned int min_ua, unsigned int max_ua, u8 *dst);
+
 #endif /* __MAX14577_H__ */
diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index d0e578fd7053..fc17d56581b2 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -46,7 +46,7 @@ enum max77693_pmic_reg {
 	MAX77693_LED_REG_VOUT_FLASH2			= 0x0C,
 	MAX77693_LED_REG_FLASH_INT			= 0x0E,
 	MAX77693_LED_REG_FLASH_INT_MASK			= 0x0F,
-	MAX77693_LED_REG_FLASH_INT_STATUS		= 0x10,
+	MAX77693_LED_REG_FLASH_STATUS			= 0x10,
 
 	MAX77693_PMIC_REG_PMIC_ID1			= 0x20,
 	MAX77693_PMIC_REG_PMIC_ID2			= 0x21,
@@ -85,6 +85,65 @@ enum max77693_pmic_reg {
 	MAX77693_PMIC_REG_END,
 };
 
+/* MAX77693 ITORCH register */
+#define TORCH_IOUT1_SHIFT	0
+#define TORCH_IOUT2_SHIFT	4
+#define TORCH_IOUT_MIN		15625
+#define TORCH_IOUT_MAX		250000
+#define TORCH_IOUT_STEP		15625
+
+/* MAX77693 IFLASH1 and IFLASH2 registers */
+#define FLASH_IOUT_MIN		15625
+#define FLASH_IOUT_MAX_1LED	1000000
+#define FLASH_IOUT_MAX_2LEDS	625000
+#define FLASH_IOUT_STEP		15625
+
+/* MAX77693 TORCH_TIMER register */
+#define TORCH_TMR_NO_TIMER	0x40
+#define TORCH_TIMEOUT_MIN	262000
+#define TORCH_TIMEOUT_MAX	15728000
+
+/* MAX77693 FLASH_TIMER register */
+#define FLASH_TMR_LEVEL		0x80
+#define FLASH_TIMEOUT_MIN	62500
+#define FLASH_TIMEOUT_MAX	1000000
+#define FLASH_TIMEOUT_STEP	62500
+
+/* MAX77693 FLASH_EN register */
+#define FLASH_EN_OFF		0x0
+#define FLASH_EN_FLASH		0x1
+#define FLASH_EN_TORCH		0x2
+#define FLASH_EN_ON		0x3
+#define FLASH_EN_SHIFT(x)	(6 - ((x) - 1) * 2)
+#define TORCH_EN_SHIFT(x)	(2 - ((x) - 1) * 2)
+
+/* MAX77693 MAX_FLASH1 register */
+#define MAX_FLASH1_MAX_FL_EN	0x80
+#define MAX_FLASH1_VSYS_MIN	2400
+#define MAX_FLASH1_VSYS_MAX	3400
+#define MAX_FLASH1_VSYS_STEP	33
+
+/* MAX77693 VOUT_CNTL register */
+#define FLASH_BOOST_FIXED	0x04
+#define FLASH_BOOST_LEDNUM_2	0x80
+
+/* MAX77693 VOUT_FLASH1 register */
+#define FLASH_VOUT_MIN		3300
+#define FLASH_VOUT_MAX		5500
+#define FLASH_VOUT_STEP		25
+#define FLASH_VOUT_RMIN		0x0c
+
+/* MAX77693 FLASH_STATUS register */
+#define FLASH_STATUS_FLASH_ON	BIT(3)
+#define FLASH_STATUS_TORCH_ON	BIT(2)
+
+/* MAX77693 FLASH_INT register */
+#define FLASH_INT_FLED2_OPEN	BIT(0)
+#define FLASH_INT_FLED2_SHORT	BIT(1)
+#define FLASH_INT_FLED1_OPEN	BIT(2)
+#define FLASH_INT_FLED1_SHORT	BIT(3)
+#define FLASH_INT_OVER_CURRENT	BIT(4)
+
 /* MAX77693 CHG_CNFG_00 register */
 #define CHG_CNFG_00_CHG_MASK		0x1
 #define CHG_CNFG_00_BUCK_MASK		0x4
diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h
index 3f3dc45f93ee..f0b6585cd874 100644
--- a/include/linux/mfd/max77693.h
+++ b/include/linux/mfd/max77693.h
@@ -63,6 +63,45 @@ struct max77693_muic_platform_data {
 	int path_uart;
 };
 
+/* MAX77693 led flash */
+
+/* triggers */
+enum max77693_led_trigger {
+	MAX77693_LED_TRIG_OFF,
+	MAX77693_LED_TRIG_FLASH,
+	MAX77693_LED_TRIG_TORCH,
+	MAX77693_LED_TRIG_EXT,
+	MAX77693_LED_TRIG_SOFT,
+};
+
+/* trigger types */
+enum max77693_led_trigger_type {
+	MAX77693_LED_TRIG_TYPE_EDGE,
+	MAX77693_LED_TRIG_TYPE_LEVEL,
+};
+
+/* boost modes */
+enum max77693_led_boost_mode {
+	MAX77693_LED_BOOST_NONE,
+	MAX77693_LED_BOOST_ADAPTIVE,
+	MAX77693_LED_BOOST_FIXED,
+};
+
+struct max77693_led_platform_data {
+	u32 fleds[2];
+	u32 iout_torch[2];
+	u32 iout_flash[2];
+	u32 trigger[2];
+	u32 trigger_type[2];
+	u32 num_leds;
+	u32 boost_mode;
+	u32 flash_timeout;
+	u32 boost_vout;
+	u32 low_vsys;
+};
+
+/* MAX77693 */
+
 struct max77693_platform_data {
 	/* regulator data */
 	struct max77693_regulator_data *regulators;
@@ -70,5 +109,6 @@ struct max77693_platform_data {
 
 	/* muic data */
 	struct max77693_muic_platform_data *muic_data;
+	struct max77693_led_platform_data *led_data;
 };
 #endif	/* __LINUX_MFD_MAX77693_H */
diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h
new file mode 100644
index 000000000000..fb09312d854b
--- /dev/null
+++ b/include/linux/mfd/rk808.h
@@ -0,0 +1,196 @@
+/*
+ * rk808.h for Rockchip RK808
+ *
+ * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd
+ *
+ * Author: Chris Zhong <zyw@rock-chips.com>
+ * Author: Zhang Qing <zhangqing@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __LINUX_REGULATOR_rk808_H
+#define __LINUX_REGULATOR_rk808_H
+
+#include <linux/regulator/machine.h>
+#include <linux/regmap.h>
+
+/*
+ * rk808 Global Register Map.
+ */
+
+#define RK808_DCDC1	0 /* (0+RK808_START) */
+#define RK808_LDO1	4 /* (4+RK808_START) */
+#define RK808_NUM_REGULATORS   14
+
+enum rk808_reg {
+	RK808_ID_DCDC1,
+	RK808_ID_DCDC2,
+	RK808_ID_DCDC3,
+	RK808_ID_DCDC4,
+	RK808_ID_LDO1,
+	RK808_ID_LDO2,
+	RK808_ID_LDO3,
+	RK808_ID_LDO4,
+	RK808_ID_LDO5,
+	RK808_ID_LDO6,
+	RK808_ID_LDO7,
+	RK808_ID_LDO8,
+	RK808_ID_SWITCH1,
+	RK808_ID_SWITCH2,
+};
+
+#define RK808_SECONDS_REG	0x00
+#define RK808_MINUTES_REG	0x01
+#define RK808_HOURS_REG		0x02
+#define RK808_DAYS_REG		0x03
+#define RK808_MONTHS_REG	0x04
+#define RK808_YEARS_REG		0x05
+#define RK808_WEEKS_REG		0x06
+#define RK808_ALARM_SECONDS_REG	0x08
+#define RK808_ALARM_MINUTES_REG	0x09
+#define RK808_ALARM_HOURS_REG	0x0a
+#define RK808_ALARM_DAYS_REG	0x0b
+#define RK808_ALARM_MONTHS_REG	0x0c
+#define RK808_ALARM_YEARS_REG	0x0d
+#define RK808_RTC_CTRL_REG	0x10
+#define RK808_RTC_STATUS_REG	0x11
+#define RK808_RTC_INT_REG	0x12
+#define RK808_RTC_COMP_LSB_REG	0x13
+#define RK808_RTC_COMP_MSB_REG	0x14
+#define RK808_CLK32OUT_REG	0x20
+#define RK808_VB_MON_REG	0x21
+#define RK808_THERMAL_REG	0x22
+#define RK808_DCDC_EN_REG	0x23
+#define RK808_LDO_EN_REG	0x24
+#define RK808_SLEEP_SET_OFF_REG1	0x25
+#define RK808_SLEEP_SET_OFF_REG2	0x26
+#define RK808_DCDC_UV_STS_REG	0x27
+#define RK808_DCDC_UV_ACT_REG	0x28
+#define RK808_LDO_UV_STS_REG	0x29
+#define RK808_LDO_UV_ACT_REG	0x2a
+#define RK808_DCDC_PG_REG	0x2b
+#define RK808_LDO_PG_REG	0x2c
+#define RK808_VOUT_MON_TDB_REG	0x2d
+#define RK808_BUCK1_CONFIG_REG		0x2e
+#define RK808_BUCK1_ON_VSEL_REG		0x2f
+#define RK808_BUCK1_SLP_VSEL_REG	0x30
+#define RK808_BUCK1_DVS_VSEL_REG	0x31
+#define RK808_BUCK2_CONFIG_REG		0x32
+#define RK808_BUCK2_ON_VSEL_REG		0x33
+#define RK808_BUCK2_SLP_VSEL_REG	0x34
+#define RK808_BUCK2_DVS_VSEL_REG	0x35
+#define RK808_BUCK3_CONFIG_REG		0x36
+#define RK808_BUCK4_CONFIG_REG		0x37
+#define RK808_BUCK4_ON_VSEL_REG		0x38
+#define RK808_BUCK4_SLP_VSEL_REG	0x39
+#define RK808_BOOST_CONFIG_REG		0x3a
+#define RK808_LDO1_ON_VSEL_REG		0x3b
+#define RK808_LDO1_SLP_VSEL_REG		0x3c
+#define RK808_LDO2_ON_VSEL_REG		0x3d
+#define RK808_LDO2_SLP_VSEL_REG		0x3e
+#define RK808_LDO3_ON_VSEL_REG		0x3f
+#define RK808_LDO3_SLP_VSEL_REG		0x40
+#define RK808_LDO4_ON_VSEL_REG		0x41
+#define RK808_LDO4_SLP_VSEL_REG		0x42
+#define RK808_LDO5_ON_VSEL_REG		0x43
+#define RK808_LDO5_SLP_VSEL_REG		0x44
+#define RK808_LDO6_ON_VSEL_REG		0x45
+#define RK808_LDO6_SLP_VSEL_REG		0x46
+#define RK808_LDO7_ON_VSEL_REG		0x47
+#define RK808_LDO7_SLP_VSEL_REG		0x48
+#define RK808_LDO8_ON_VSEL_REG		0x49
+#define RK808_LDO8_SLP_VSEL_REG		0x4a
+#define RK808_DEVCTRL_REG	0x4b
+#define RK808_INT_STS_REG1	0x4c
+#define RK808_INT_STS_MSK_REG1	0x4d
+#define RK808_INT_STS_REG2	0x4e
+#define RK808_INT_STS_MSK_REG2	0x4f
+#define RK808_IO_POL_REG	0x50
+
+/* IRQ Definitions */
+#define RK808_IRQ_VOUT_LO	0
+#define RK808_IRQ_VB_LO		1
+#define RK808_IRQ_PWRON		2
+#define RK808_IRQ_PWRON_LP	3
+#define RK808_IRQ_HOTDIE	4
+#define RK808_IRQ_RTC_ALARM	5
+#define RK808_IRQ_RTC_PERIOD	6
+#define RK808_IRQ_PLUG_IN_INT	7
+#define RK808_IRQ_PLUG_OUT_INT	8
+#define RK808_NUM_IRQ		9
+
+#define RK808_IRQ_VOUT_LO_MSK		BIT(0)
+#define RK808_IRQ_VB_LO_MSK		BIT(1)
+#define RK808_IRQ_PWRON_MSK		BIT(2)
+#define RK808_IRQ_PWRON_LP_MSK		BIT(3)
+#define RK808_IRQ_HOTDIE_MSK		BIT(4)
+#define RK808_IRQ_RTC_ALARM_MSK		BIT(5)
+#define RK808_IRQ_RTC_PERIOD_MSK	BIT(6)
+#define RK808_IRQ_PLUG_IN_INT_MSK	BIT(0)
+#define RK808_IRQ_PLUG_OUT_INT_MSK	BIT(1)
+
+#define RK808_VBAT_LOW_2V8	0x00
+#define RK808_VBAT_LOW_2V9	0x01
+#define RK808_VBAT_LOW_3V0	0x02
+#define RK808_VBAT_LOW_3V1	0x03
+#define RK808_VBAT_LOW_3V2	0x04
+#define RK808_VBAT_LOW_3V3	0x05
+#define RK808_VBAT_LOW_3V4	0x06
+#define RK808_VBAT_LOW_3V5	0x07
+#define VBAT_LOW_VOL_MASK	(0x07 << 0)
+#define EN_VABT_LOW_SHUT_DOWN	(0x00 << 4)
+#define EN_VBAT_LOW_IRQ		(0x1 << 4)
+#define VBAT_LOW_ACT_MASK	(0x1 << 4)
+
+#define BUCK_ILMIN_MASK		(7 << 0)
+#define BOOST_ILMIN_MASK	(7 << 0)
+#define BUCK1_RATE_MASK		(3 << 3)
+#define BUCK2_RATE_MASK		(3 << 3)
+#define MASK_ALL	0xff
+
+#define SWITCH2_EN	BIT(6)
+#define SWITCH1_EN	BIT(5)
+#define DEV_OFF_RST	BIT(3)
+
+#define VB_LO_ACT		BIT(4)
+#define VB_LO_SEL_3500MV	(7 << 0)
+
+#define VOUT_LO_INT	BIT(0)
+#define CLK32KOUT2_EN	BIT(0)
+
+enum {
+	BUCK_ILMIN_50MA,
+	BUCK_ILMIN_100MA,
+	BUCK_ILMIN_150MA,
+	BUCK_ILMIN_200MA,
+	BUCK_ILMIN_250MA,
+	BUCK_ILMIN_300MA,
+	BUCK_ILMIN_350MA,
+	BUCK_ILMIN_400MA,
+};
+
+enum {
+	BOOST_ILMIN_75MA,
+	BOOST_ILMIN_100MA,
+	BOOST_ILMIN_125MA,
+	BOOST_ILMIN_150MA,
+	BOOST_ILMIN_175MA,
+	BOOST_ILMIN_200MA,
+	BOOST_ILMIN_225MA,
+	BOOST_ILMIN_250MA,
+};
+
+struct rk808 {
+	struct i2c_client *i2c;
+	struct regmap_irq_chip_data *irq_data;
+	struct regmap *regmap;
+};
+#endif /* __LINUX_REGULATOR_rk808_H */
diff --git a/include/linux/mfd/rn5t618.h b/include/linux/mfd/rn5t618.h
new file mode 100644
index 000000000000..c72d5344f3b3
--- /dev/null
+++ b/include/linux/mfd/rn5t618.h
@@ -0,0 +1,228 @@
+/*
+ * MFD core driver for Ricoh RN5T618 PMIC
+ *
+ * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __LINUX_MFD_RN5T618_H
+#define __LINUX_MFD_RN5T618_H
+
+#include <linux/regmap.h>
+
+#define RN5T618_LSIVER			0x00
+#define RN5T618_OTPVER			0x01
+#define RN5T618_IODAC			0x02
+#define RN5T618_VINDAC			0x03
+#define RN5T618_CPUCNT			0x06
+#define RN5T618_PSWR			0x07
+#define RN5T618_PONHIS			0x09
+#define RN5T618_POFFHIS			0x0a
+#define RN5T618_WATCHDOG		0x0b
+#define RN5T618_WATCHDOGCNT		0x0c
+#define RN5T618_PWRFUNC			0x0d
+#define RN5T618_SLPCNT			0x0e
+#define RN5T618_REPCNT			0x0f
+#define RN5T618_PWRONTIMSET		0x10
+#define RN5T618_NOETIMSETCNT		0x11
+#define RN5T618_PWRIREN			0x12
+#define RN5T618_PWRIRQ			0x13
+#define RN5T618_PWRMON			0x14
+#define RN5T618_PWRIRSEL		0x15
+#define RN5T618_DC1_SLOT		0x16
+#define RN5T618_DC2_SLOT		0x17
+#define RN5T618_DC3_SLOT		0x18
+#define RN5T618_LDO1_SLOT		0x1b
+#define RN5T618_LDO2_SLOT		0x1c
+#define RN5T618_LDO3_SLOT		0x1d
+#define RN5T618_LDO4_SLOT		0x1e
+#define RN5T618_LDO5_SLOT		0x1f
+#define RN5T618_PSO0_SLOT		0x25
+#define RN5T618_PSO1_SLOT		0x26
+#define RN5T618_PSO2_SLOT		0x27
+#define RN5T618_PSO3_SLOT		0x28
+#define RN5T618_LDORTC1_SLOT		0x2a
+#define RN5T618_DC1CTL			0x2c
+#define RN5T618_DC1CTL2			0x2d
+#define RN5T618_DC2CTL			0x2e
+#define RN5T618_DC2CTL2			0x2f
+#define RN5T618_DC3CTL			0x30
+#define RN5T618_DC3CTL2			0x31
+#define RN5T618_DC1DAC			0x36
+#define RN5T618_DC2DAC			0x37
+#define RN5T618_DC3DAC			0x38
+#define RN5T618_DC1DAC_SLP		0x3b
+#define RN5T618_DC2DAC_SLP		0x3c
+#define RN5T618_DC3DAC_SLP		0x3d
+#define RN5T618_DCIREN			0x40
+#define RN5T618_DCIRQ			0x41
+#define RN5T618_DCIRMON			0x42
+#define RN5T618_LDOEN1			0x44
+#define RN5T618_LDOEN2			0x45
+#define RN5T618_LDODIS			0x46
+#define RN5T618_LDO1DAC			0x4c
+#define RN5T618_LDO2DAC			0x4d
+#define RN5T618_LDO3DAC			0x4e
+#define RN5T618_LDO4DAC			0x4f
+#define RN5T618_LDO5DAC			0x50
+#define RN5T618_LDORTCDAC		0x56
+#define RN5T618_LDORTC2DAC		0x57
+#define RN5T618_LDO1DAC_SLP		0x58
+#define RN5T618_LDO2DAC_SLP		0x59
+#define RN5T618_LDO3DAC_SLP		0x5a
+#define RN5T618_LDO4DAC_SLP		0x5b
+#define RN5T618_LDO5DAC_SLP		0x5c
+#define RN5T618_ADCCNT1			0x64
+#define RN5T618_ADCCNT2			0x65
+#define RN5T618_ADCCNT3			0x66
+#define RN5T618_ILIMDATAH		0x68
+#define RN5T618_ILIMDATAL		0x69
+#define RN5T618_VBATDATAH		0x6a
+#define RN5T618_VBATDATAL		0x6b
+#define RN5T618_VADPDATAH		0x6c
+#define RN5T618_VADPDATAL		0x6d
+#define RN5T618_VUSBDATAH		0x6e
+#define RN5T618_VUSBDATAL		0x6f
+#define RN5T618_VSYSDATAH		0x70
+#define RN5T618_VSYSDATAL		0x71
+#define RN5T618_VTHMDATAH		0x72
+#define RN5T618_VTHMDATAL		0x73
+#define RN5T618_AIN1DATAH		0x74
+#define RN5T618_AIN1DATAL		0x75
+#define RN5T618_AIN0DATAH		0x76
+#define RN5T618_AIN0DATAL		0x77
+#define RN5T618_ILIMTHL			0x78
+#define RN5T618_ILIMTHH			0x79
+#define RN5T618_VBATTHL			0x7a
+#define RN5T618_VBATTHH			0x7b
+#define RN5T618_VADPTHL			0x7c
+#define RN5T618_VADPTHH			0x7d
+#define RN5T618_VUSBTHL			0x7e
+#define RN5T618_VUSBTHH			0x7f
+#define RN5T618_VSYSTHL			0x80
+#define RN5T618_VSYSTHH			0x81
+#define RN5T618_VTHMTHL			0x82
+#define RN5T618_VTHMTHH			0x83
+#define RN5T618_AIN1THL			0x84
+#define RN5T618_AIN1THH			0x85
+#define RN5T618_AIN0THL			0x86
+#define RN5T618_AIN0THH			0x87
+#define RN5T618_EN_ADCIR1		0x88
+#define RN5T618_EN_ADCIR2		0x89
+#define RN5T618_EN_ADCIR3		0x8a
+#define RN5T618_IR_ADC1			0x8c
+#define RN5T618_IR_ADC2			0x8d
+#define RN5T618_IR_ADC3			0x8e
+#define RN5T618_IOSEL			0x90
+#define RN5T618_IOOUT			0x91
+#define RN5T618_GPEDGE1			0x92
+#define RN5T618_GPEDGE2			0x93
+#define RN5T618_EN_GPIR			0x94
+#define RN5T618_IR_GPR			0x95
+#define RN5T618_IR_GPF			0x96
+#define RN5T618_MON_IOIN		0x97
+#define RN5T618_GPLED_FUNC		0x98
+#define RN5T618_INTPOL			0x9c
+#define RN5T618_INTEN			0x9d
+#define RN5T618_INTMON			0x9e
+#define RN5T618_PREVINDAC		0xb0
+#define RN5T618_BATDAC			0xb1
+#define RN5T618_CHGCTL1			0xb3
+#define RN5T618_CHGCTL2			0xb4
+#define RN5T618_VSYSSET			0xb5
+#define RN5T618_REGISET1		0xb6
+#define RN5T618_REGISET2		0xb7
+#define RN5T618_CHGISET			0xb8
+#define RN5T618_TIMSET			0xb9
+#define RN5T618_BATSET1			0xba
+#define RN5T618_BATSET2			0xbb
+#define RN5T618_DIESET			0xbc
+#define RN5T618_CHGSTATE		0xbd
+#define RN5T618_CHGCTRL_IRFMASK		0xbe
+#define RN5T618_CHGSTAT_IRFMASK1	0xbf
+#define RN5T618_CHGSTAT_IRFMASK2	0xc0
+#define RN5T618_CHGERR_IRFMASK		0xc1
+#define RN5T618_CHGCTRL_IRR		0xc2
+#define RN5T618_CHGSTAT_IRR1		0xc3
+#define RN5T618_CHGSTAT_IRR2		0xc4
+#define RN5T618_CHGERR_IRR		0xc5
+#define RN5T618_CHGCTRL_MONI		0xc6
+#define RN5T618_CHGSTAT_MONI1		0xc7
+#define RN5T618_CHGSTAT_MONI2		0xc8
+#define RN5T618_CHGERR_MONI		0xc9
+#define RN5T618_CHGCTRL_DETMOD1		0xca
+#define RN5T618_CHGCTRL_DETMOD2		0xcb
+#define RN5T618_CHGSTAT_DETMOD1		0xcc
+#define RN5T618_CHGSTAT_DETMOD2		0xcd
+#define RN5T618_CHGSTAT_DETMOD3		0xce
+#define RN5T618_CHGERR_DETMOD1		0xcf
+#define RN5T618_CHGERR_DETMOD2		0xd0
+#define RN5T618_CHGOSCCTL		0xd4
+#define RN5T618_CHGOSCSCORESET1		0xd5
+#define RN5T618_CHGOSCSCORESET2		0xd6
+#define RN5T618_CHGOSCSCORESET3		0xd7
+#define RN5T618_CHGOSCFREQSET1		0xd8
+#define RN5T618_CHGOSCFREQSET2		0xd9
+#define RN5T618_CONTROL			0xe0
+#define RN5T618_SOC			0xe1
+#define RN5T618_RE_CAP_H		0xe2
+#define RN5T618_RE_CAP_L		0xe3
+#define RN5T618_FA_CAP_H		0xe4
+#define RN5T618_FA_CAP_L		0xe5
+#define RN5T618_AGE			0xe6
+#define RN5T618_TT_EMPTY_H		0xe7
+#define RN5T618_TT_EMPTY_L		0xe8
+#define RN5T618_TT_FULL_H		0xe9
+#define RN5T618_TT_FULL_L		0xea
+#define RN5T618_VOLTAGE_1		0xeb
+#define RN5T618_VOLTAGE_0		0xec
+#define RN5T618_TEMP_1			0xed
+#define RN5T618_TEMP_0			0xee
+#define RN5T618_CC_CTRL			0xef
+#define RN5T618_CC_COUNT2		0xf0
+#define RN5T618_CC_COUNT1		0xf1
+#define RN5T618_CC_COUNT0		0xf2
+#define RN5T618_CC_SUMREG3		0xf3
+#define RN5T618_CC_SUMREG2		0xf4
+#define RN5T618_CC_SUMREG1		0xf5
+#define RN5T618_CC_SUMREG0		0xf6
+#define RN5T618_CC_OFFREG1		0xf7
+#define RN5T618_CC_OFFREG0		0xf8
+#define RN5T618_CC_GAINREG1		0xf9
+#define RN5T618_CC_GAINREG0		0xfa
+#define RN5T618_CC_AVEREG1		0xfb
+#define RN5T618_CC_AVEREG0		0xfc
+#define RN5T618_MAX_REG			0xfc
+
+#define RN5T618_REPCNT_REPWRON		BIT(0)
+#define RN5T618_SLPCNT_SWPWROFF		BIT(0)
+#define RN5T618_WATCHDOG_WDOGEN		BIT(2)
+#define RN5T618_WATCHDOG_WDOGTIM_M	(BIT(0) | BIT(1))
+#define RN5T618_WATCHDOG_WDOGTIM_S	0
+#define RN5T618_PWRIRQ_IR_WDOG		BIT(6)
+
+enum {
+	RN5T618_DCDC1,
+	RN5T618_DCDC2,
+	RN5T618_DCDC3,
+	RN5T618_LDO1,
+	RN5T618_LDO2,
+	RN5T618_LDO3,
+	RN5T618_LDO4,
+	RN5T618_LDO5,
+	RN5T618_LDORTC1,
+	RN5T618_LDORTC2,
+	RN5T618_REG_NUM,
+};
+
+struct rn5t618 {
+	struct regmap *regmap;
+};
+
+#endif /* __LINUX_MFD_RN5T618_H */
diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
index fb96c84dada5..e2e70053470e 100644
--- a/include/linux/mfd/ti_am335x_tscadc.h
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -155,6 +155,7 @@ struct ti_tscadc_dev {
 	void __iomem *tscadc_base;
 	int irq;
 	int used_cells;	/* 1-2 */
+	int tsc_wires;
 	int tsc_cell;	/* -1 if not used */
 	int adc_cell;	/* -1 if not used */
 	struct mfd_cell cells[TSCADC_CELLS];
diff --git a/include/linux/mfd/ti_ssp.h b/include/linux/mfd/ti_ssp.h
deleted file mode 100644
index dbb4b43bd20e..000000000000
--- a/include/linux/mfd/ti_ssp.h
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * Sequencer Serial Port (SSP) driver for Texas Instruments' SoCs
- *
- * Copyright (C) 2010 Texas Instruments Inc
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-#ifndef __TI_SSP_H__
-#define __TI_SSP_H__
-
-struct ti_ssp_dev_data {
-	const char	*dev_name;
-	void		*pdata;
-	size_t		pdata_size;
-};
-
-struct ti_ssp_data {
-	unsigned long		out_clock;
-	struct ti_ssp_dev_data	dev_data[2];
-};
-
-struct ti_ssp_spi_data {
-	unsigned long	iosel;
-	int		num_cs;
-	void		(*select)(int cs);
-};
-
-/*
- * Sequencer port IO pin configuration bits.  These do not correlate 1-1 with
- * the hardware.  The iosel field in the port data combines iosel1 and iosel2,
- * and is therefore not a direct map to register space.  It is best to use the
- * macros below to construct iosel values.
- *
- * least significant 16 bits --> iosel1
- * most significant 16 bits  --> iosel2
- */
-
-#define SSP_IN			0x0000
-#define SSP_DATA		0x0001
-#define SSP_CLOCK		0x0002
-#define SSP_CHIPSEL		0x0003
-#define SSP_OUT			0x0004
-#define SSP_PIN_SEL(pin, v)	((v) << ((pin) * 3))
-#define SSP_PIN_MASK(pin)	SSP_PIN_SEL(pin, 0x7)
-#define SSP_INPUT_SEL(pin)	((pin) << 16)
-
-/* Sequencer port config bits */
-#define SSP_EARLY_DIN		BIT(8)
-#define SSP_DELAY_DOUT		BIT(9)
-
-/* Sequence map definitions */
-#define SSP_CLK_HIGH		BIT(0)
-#define SSP_CLK_LOW		0
-#define SSP_DATA_HIGH		BIT(1)
-#define SSP_DATA_LOW		0
-#define SSP_CS_HIGH		BIT(2)
-#define SSP_CS_LOW		0
-#define SSP_OUT_MODE		BIT(3)
-#define SSP_IN_MODE		0
-#define SSP_DATA_REG		BIT(4)
-#define SSP_ADDR_REG		0
-
-#define SSP_OPCODE_DIRECT	((0x0) << 5)
-#define SSP_OPCODE_TOGGLE	((0x1) << 5)
-#define SSP_OPCODE_SHIFT	((0x2) << 5)
-#define SSP_OPCODE_BRANCH0	((0x4) << 5)
-#define SSP_OPCODE_BRANCH1	((0x5) << 5)
-#define SSP_OPCODE_BRANCH	((0x6) << 5)
-#define SSP_OPCODE_STOP		((0x7) << 5)
-#define SSP_BRANCH(addr)	((addr) << 8)
-#define SSP_COUNT(cycles)	((cycles) << 8)
-
-int ti_ssp_raw_read(struct device *dev);
-int ti_ssp_raw_write(struct device *dev, u32 val);
-int ti_ssp_load(struct device *dev, int offs, u32* prog, int len);
-int ti_ssp_run(struct device *dev, u32 pc, u32 input, u32 *output);
-int ti_ssp_set_mode(struct device *dev, int mode);
-int ti_ssp_set_iosel(struct device *dev, u32 iosel);
-
-#endif /* __TI_SSP_H__ */
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 8f6f2e91e7ae..57388171610d 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -5,6 +5,7 @@
 #include <linux/fb.h>
 #include <linux/io.h>
 #include <linux/jiffies.h>
+#include <linux/mmc/card.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 
@@ -83,6 +84,27 @@
  */
 #define TMIO_MMC_HAVE_HIGH_REG		(1 << 6)
 
+/*
+ * Some controllers have CMD12 automatically
+ * issue/non-issue register
+ */
+#define TMIO_MMC_HAVE_CMD12_CTRL	(1 << 7)
+
+/*
+ * Some controllers needs to set 1 on SDIO status reserved bits
+ */
+#define TMIO_MMC_SDIO_STATUS_QUIRK	(1 << 8)
+
+/*
+ * Some controllers have DMA enable/disable register
+ */
+#define TMIO_MMC_HAVE_CTL_DMA_REG	(1 << 9)
+
+/*
+ * Some controllers allows to set SDx actual clock
+ */
+#define TMIO_MMC_CLK_ACTUAL		(1 << 10)
+
 int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base);
 int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base);
 void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state);
@@ -96,6 +118,7 @@ struct tmio_mmc_dma {
 	int slave_id_tx;
 	int slave_id_rx;
 	int alignment_shift;
+	dma_addr_t dma_rx_offset;
 	bool (*filter)(struct dma_chan *chan, void *arg);
 };
 
@@ -120,6 +143,8 @@ struct tmio_mmc_data {
 	/* clock management callbacks */
 	int (*clk_enable)(struct platform_device *pdev, unsigned int *f);
 	void (*clk_disable)(struct platform_device *pdev);
+	int (*multi_io_quirk)(struct mmc_card *card,
+			      unsigned int direction, int blk_size);
 };
 
 /*
diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h
index 95d6938737fd..ac7fba44d7e4 100644
--- a/include/linux/mfd/tps65217.h
+++ b/include/linux/mfd/tps65217.h
@@ -60,6 +60,8 @@
 #define TPS65217_REG_SEQ5		0X1D
 #define TPS65217_REG_SEQ6		0X1E
 
+#define TPS65217_REG_MAX		TPS65217_REG_SEQ6
+
 /* Register field definitions */
 #define TPS65217_CHIPID_CHIP_MASK	0xF0
 #define TPS65217_CHIPID_REV_MASK	0x0F
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index a2901c414664..01aad3ed89ec 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -13,18 +13,9 @@ typedef void free_page_t(struct page *page, unsigned long private);
  * Return values from addresss_space_operations.migratepage():
  * - negative errno on page migration failure;
  * - zero on page migration success;
- *
- * The balloon page migration introduces this special case where a 'distinct'
- * return code is used to flag a successful page migration to unmap_and_move().
- * This approach is necessary because page migration can race against balloon
- * deflation procedure, and for such case we could introduce a nasty page leak
- * if a successfully migrated balloon page gets released concurrently with
- * migration's unmap_and_move() wrap-up steps.
  */
 #define MIGRATEPAGE_SUCCESS		0
-#define MIGRATEPAGE_BALLOON_SUCCESS	1 /* special ret code for balloon page
-					   * sucessful migration case.
-					   */
+
 enum migrate_reason {
 	MR_COMPACTION,
 	MR_MEMORY_FAILURE,
@@ -82,9 +73,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 	return -ENOSYS;
 }
 
-/* Possible settings for the migrate_page() method in address_operations */
-#define migrate_page NULL
-
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_NUMA_BALANCING
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0f4196a0bc20..02d11ee7f19d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -18,6 +18,7 @@
 #include <linux/pfn.h>
 #include <linux/bit_spinlock.h>
 #include <linux/shrinker.h>
+#include <linux/resource.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -346,6 +347,7 @@ static inline int put_page_unless_one(struct page *page)
 }
 
 extern int page_is_ram(unsigned long pfn);
+extern int region_is_ram(resource_size_t phys_addr, unsigned long size);
 
 /* Support for virtually mapped pages */
 struct page *vmalloc_to_page(const void *addr);
@@ -553,6 +555,25 @@ static inline void __ClearPageBuddy(struct page *page)
 	atomic_set(&page->_mapcount, -1);
 }
 
+#define PAGE_BALLOON_MAPCOUNT_VALUE (-256)
+
+static inline int PageBalloon(struct page *page)
+{
+	return atomic_read(&page->_mapcount) == PAGE_BALLOON_MAPCOUNT_VALUE;
+}
+
+static inline void __SetPageBalloon(struct page *page)
+{
+	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
+	atomic_set(&page->_mapcount, PAGE_BALLOON_MAPCOUNT_VALUE);
+}
+
+static inline void __ClearPageBalloon(struct page *page)
+{
+	VM_BUG_ON_PAGE(!PageBalloon(page), page);
+	atomic_set(&page->_mapcount, -1);
+}
+
 void put_page(struct page *page);
 void put_pages_list(struct list_head *pages);
 
@@ -1247,8 +1268,8 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma,
 		!vma_growsup(vma->vm_next, addr);
 }
 
-extern pid_t
-vm_is_stack(struct task_struct *task, struct vm_area_struct *vma, int in_group);
+extern struct task_struct *task_of_stack(struct task_struct *task,
+				struct vm_area_struct *vma, bool in_group);
 
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
@@ -1780,6 +1801,20 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
 	bool *need_rmap_locks);
 extern void exit_mmap(struct mm_struct *);
 
+static inline int check_data_rlimit(unsigned long rlim,
+				    unsigned long new,
+				    unsigned long start,
+				    unsigned long end_data,
+				    unsigned long start_data)
+{
+	if (rlim < RLIM_INFINITY) {
+		if (((new - start) + (end_data - start_data)) > rlim)
+			return -ENOSPC;
+	}
+
+	return 0;
+}
+
 extern int mm_take_all_locks(struct mm_struct *mm);
 extern void mm_drop_all_locks(struct mm_struct *mm);
 
@@ -1939,11 +1974,16 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
 
 #ifdef CONFIG_MMU
 pgprot_t vm_get_page_prot(unsigned long vm_flags);
+void vma_set_page_prot(struct vm_area_struct *vma);
 #else
 static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
 {
 	return __pgprot(0);
 }
+static inline void vma_set_page_prot(struct vm_area_struct *vma)
+{
+	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+}
 #endif
 
 #ifdef CONFIG_NUMA_BALANCING
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index d424b9de3aff..b0692d28f8e6 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -42,7 +42,8 @@ struct mmc_csd {
 	unsigned int		read_partial:1,
 				read_misalign:1,
 				write_partial:1,
-				write_misalign:1;
+				write_misalign:1,
+				dsr_imp:1;
 };
 
 struct mmc_ext_csd {
@@ -74,7 +75,7 @@ struct mmc_ext_csd {
 	unsigned int		sec_trim_mult;	/* Secure trim multiplier  */
 	unsigned int		sec_erase_mult;	/* Secure erase multiplier */
 	unsigned int		trim_timeout;		/* In milliseconds */
-	bool			enhanced_area_en;	/* enable bit */
+	bool			partition_setting_completed;	/* enable bit */
 	unsigned long long	enhanced_area_offset;	/* Units: Byte */
 	unsigned int		enhanced_area_size;	/* Units: KB */
 	unsigned int		cache_size;		/* Units: KB */
@@ -214,11 +215,12 @@ enum mmc_blk_status {
 };
 
 /* The number of MMC physical partitions.  These consist of:
- * boot partitions (2), general purpose partitions (4) in MMC v4.4.
+ * boot partitions (2), general purpose partitions (4) and
+ * RPMB partition (1) in MMC v4.4.
  */
 #define MMC_NUM_BOOT_PARTITION	2
 #define MMC_NUM_GP_PARTITION	4
-#define MMC_NUM_PHY_PARTITION	6
+#define MMC_NUM_PHY_PARTITION	7
 #define MAX_MMC_PART_NAME_LEN	20
 
 /*
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 29ce014ab421..001366927cf4 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -26,6 +26,8 @@ enum dw_mci_state {
 	STATE_DATA_BUSY,
 	STATE_SENDING_STOP,
 	STATE_DATA_ERROR,
+	STATE_SENDING_CMD11,
+	STATE_WAITING_CMD11_DONE,
 };
 
 enum {
@@ -188,7 +190,7 @@ struct dw_mci {
 	/* Workaround flags */
 	u32			quirks;
 
-	struct regulator	*vmmc;	/* Power regulator */
+	bool			vqmmc_enabled;
 	unsigned long		irq_flags; /* IRQ flags */
 	int			irq;
 };
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 7960424d0bc0..df0c15396bbf 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -42,6 +42,7 @@ struct mmc_ios {
 #define MMC_POWER_OFF		0
 #define MMC_POWER_UP		1
 #define MMC_POWER_ON		2
+#define MMC_POWER_UNDEFINED	3
 
 	unsigned char	bus_width;		/* data bus width */
 
@@ -139,6 +140,13 @@ struct mmc_host_ops {
 	int	(*select_drive_strength)(unsigned int max_dtr, int host_drv, int card_drv);
 	void	(*hw_reset)(struct mmc_host *host);
 	void	(*card_event)(struct mmc_host *host);
+
+	/*
+	 * Optional callback to support controllers with HW issues for multiple
+	 * I/O. Returns the number of supported blocks for the request.
+	 */
+	int	(*multi_io_quirk)(struct mmc_card *card,
+				  unsigned int direction, int blk_size);
 };
 
 struct mmc_card;
@@ -265,7 +273,6 @@ struct mmc_host {
 
 #define MMC_CAP2_BOOTPART_NOACC	(1 << 0)	/* Boot partition no access */
 #define MMC_CAP2_FULL_PWR_CYCLE	(1 << 2)	/* Can do full power cycle */
-#define MMC_CAP2_NO_MULTI_READ	(1 << 3)	/* Multiblock reads don't work */
 #define MMC_CAP2_HS200_1_8V_SDR	(1 << 5)        /* can support */
 #define MMC_CAP2_HS200_1_2V_SDR	(1 << 6)        /* can support */
 #define MMC_CAP2_HS200		(MMC_CAP2_HS200_1_8V_SDR | \
@@ -365,6 +372,9 @@ struct mmc_host {
 
 	unsigned int		slotno;	/* used for sdio acpi binding */
 
+	int			dsr_req;	/* DSR value is valid */
+	u32			dsr;	/* optional driver stage (DSR) value */
+
 	unsigned long		private[0] ____cacheline_aligned;
 };
 
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 64ec963ed347..1cd00b3a75b9 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -53,6 +53,11 @@
 #define MMC_SEND_TUNING_BLOCK    19   /* adtc                    R1  */
 #define MMC_SEND_TUNING_BLOCK_HS200	21	/* adtc R1  */
 
+#define MMC_TUNING_BLK_PATTERN_4BIT_SIZE	 64
+#define MMC_TUNING_BLK_PATTERN_8BIT_SIZE	128
+extern const u8 tuning_blk_pattern_4bit[MMC_TUNING_BLK_PATTERN_4BIT_SIZE];
+extern const u8 tuning_blk_pattern_8bit[MMC_TUNING_BLK_PATTERN_8BIT_SIZE];
+
   /* class 3 */
 #define MMC_WRITE_DAT_UNTIL_STOP 20   /* adtc [31:0] data addr   R1  */
 
@@ -281,6 +286,7 @@ struct _mmc_csd {
 #define EXT_CSD_EXP_EVENTS_CTRL		56	/* R/W, 2 bytes */
 #define EXT_CSD_DATA_SECTOR_SIZE	61	/* R */
 #define EXT_CSD_GP_SIZE_MULT		143	/* R/W */
+#define EXT_CSD_PARTITION_SETTING_COMPLETED 155	/* R/W */
 #define EXT_CSD_PARTITION_ATTRIBUTE	156	/* R/W */
 #define EXT_CSD_PARTITION_SUPPORT	160	/* RO */
 #define EXT_CSD_HPI_MGMT		161	/* R/W */
@@ -349,6 +355,7 @@ struct _mmc_csd {
 #define EXT_CSD_PART_CONFIG_ACC_RPMB	(0x3)
 #define EXT_CSD_PART_CONFIG_ACC_GP0	(0x4)
 
+#define EXT_CSD_PART_SETTING_COMPLETED	(0x1)
 #define EXT_CSD_PART_SUPPORT_PART_EN	(0x1)
 
 #define EXT_CSD_CMD_SET_NORMAL		(1<<0)
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index 09ebe57d5ce9..dba793e3a331 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -98,6 +98,8 @@ struct sdhci_host {
 #define SDHCI_QUIRK2_BROKEN_HS200			(1<<6)
 /* Controller does not support DDR50 */
 #define SDHCI_QUIRK2_BROKEN_DDR50			(1<<7)
+/* Stop command (CMD12) can set Transfer Complete when not using MMC_RSP_BUSY */
+#define SDHCI_QUIRK2_STOP_WITH_TC			(1<<8)
 
 	int irq;		/* Device IRQ */
 	void __iomem *ioaddr;	/* Mapped address */
@@ -146,6 +148,7 @@ struct sdhci_host {
 	struct mmc_command *cmd;	/* Current command */
 	struct mmc_data *data;	/* Current data request */
 	unsigned int data_early:1;	/* Data finished before cmd */
+	unsigned int busy_handle:1;	/* Handling the order of Busy-end */
 
 	struct sg_mapping_iter sg_miter;	/* SG state for PIO */
 	unsigned int blocks;	/* remaining PIO blocks */
diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h
index d2433381e828..e56fa24c9322 100644
--- a/include/linux/mmc/slot-gpio.h
+++ b/include/linux/mmc/slot-gpio.h
@@ -24,7 +24,10 @@ void mmc_gpio_free_cd(struct mmc_host *host);
 
 int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
-			 unsigned int debounce);
+			 unsigned int debounce, bool *gpio_invert);
+int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
+			 unsigned int idx, bool override_active_level,
+			 unsigned int debounce, bool *gpio_invert);
 void mmc_gpiod_free_cd(struct mmc_host *host);
 void mmc_gpiod_request_cd_irq(struct mmc_host *host);
 
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 2f348d02f640..877ef226f90f 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -4,10 +4,14 @@
 #include <linux/stringify.h>
 
 struct page;
+struct vm_area_struct;
+struct mm_struct;
 
 extern void dump_page(struct page *page, const char *reason);
 extern void dump_page_badflags(struct page *page, const char *reason,
 			       unsigned long badflags);
+void dump_vma(const struct vm_area_struct *vma);
+void dump_mm(const struct mm_struct *mm);
 
 #ifdef CONFIG_DEBUG_VM
 #define VM_BUG_ON(cond) BUG_ON(cond)
@@ -18,12 +22,28 @@ extern void dump_page_badflags(struct page *page, const char *reason,
 			BUG();						\
 		}							\
 	} while (0)
+#define VM_BUG_ON_VMA(cond, vma)					\
+	do {								\
+		if (unlikely(cond)) {					\
+			dump_vma(vma);					\
+			BUG();						\
+		}							\
+	} while (0)
+#define VM_BUG_ON_MM(cond, mm)						\
+	do {								\
+		if (unlikely(cond)) {					\
+			dump_mm(mm);					\
+			BUG();						\
+		}							\
+	} while (0)
 #define VM_WARN_ON(cond) WARN_ON(cond)
 #define VM_WARN_ON_ONCE(cond) WARN_ON_ONCE(cond)
 #define VM_WARN_ONCE(cond, format...) WARN_ONCE(cond, format)
 #else
 #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond)
+#define VM_BUG_ON_VMA(cond, vma) VM_BUG_ON(cond)
+#define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond)
 #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 318df7051850..48bf12ef6620 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -521,13 +521,13 @@ struct zone {
 	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
 } ____cacheline_internodealigned_in_smp;
 
-typedef enum {
+enum zone_flags {
 	ZONE_RECLAIM_LOCKED,		/* prevents concurrent reclaim */
 	ZONE_OOM_LOCKED,		/* zone is in OOM killer zonelist */
 	ZONE_CONGESTED,			/* zone has many dirty pages backed by
 					 * a congested BDI
 					 */
-	ZONE_TAIL_LRU_DIRTY,		/* reclaim scanning has recently found
+	ZONE_DIRTY,			/* reclaim scanning has recently found
 					 * many dirty file pages at the tail
 					 * of the LRU.
 					 */
@@ -535,52 +535,7 @@ typedef enum {
 					 * many pages under writeback
 					 */
 	ZONE_FAIR_DEPLETED,		/* fair zone policy batch depleted */
-} zone_flags_t;
-
-static inline void zone_set_flag(struct zone *zone, zone_flags_t flag)
-{
-	set_bit(flag, &zone->flags);
-}
-
-static inline int zone_test_and_set_flag(struct zone *zone, zone_flags_t flag)
-{
-	return test_and_set_bit(flag, &zone->flags);
-}
-
-static inline void zone_clear_flag(struct zone *zone, zone_flags_t flag)
-{
-	clear_bit(flag, &zone->flags);
-}
-
-static inline int zone_is_reclaim_congested(const struct zone *zone)
-{
-	return test_bit(ZONE_CONGESTED, &zone->flags);
-}
-
-static inline int zone_is_reclaim_dirty(const struct zone *zone)
-{
-	return test_bit(ZONE_TAIL_LRU_DIRTY, &zone->flags);
-}
-
-static inline int zone_is_reclaim_writeback(const struct zone *zone)
-{
-	return test_bit(ZONE_WRITEBACK, &zone->flags);
-}
-
-static inline int zone_is_reclaim_locked(const struct zone *zone)
-{
-	return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags);
-}
-
-static inline int zone_is_fair_depleted(const struct zone *zone)
-{
-	return test_bit(ZONE_FAIR_DEPLETED, &zone->flags);
-}
-
-static inline int zone_is_oom_locked(const struct zone *zone)
-{
-	return test_bit(ZONE_OOM_LOCKED, &zone->flags);
-}
+};
 
 static inline unsigned long zone_end_pfn(const struct zone *zone)
 {
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index b43f4752304e..1c9effa25e26 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -78,6 +78,8 @@ struct kernel_param {
 	};
 };
 
+extern const struct kernel_param __start___param[], __stop___param[];
+
 /* Special one for strings we want to copy into */
 struct kparam_string {
 	unsigned int maxlen;
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 8103f32f6d87..44f4746d033b 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -29,7 +29,6 @@ struct msi_desc {
 		__u8	multi_cap : 3;	/* log2 num of messages supported */
 		__u8	maskbit	: 1;	/* mask-pending bit supported ? */
 		__u8	is_64	: 1;	/* Address size: 0=32bit 1=64bit */
-		__u8	pos;		/* Location of the msi capability */
 		__u16	entry_nr;	/* specific enabled entry */
 		unsigned default_irq;	/* default pre-assigned irq */
 	} msi_attrib;
@@ -47,8 +46,6 @@ struct msi_desc {
 
 	/* Last set MSI message */
 	struct msi_msg msg;
-
-	struct kobject kobj;
 };
 
 /*
@@ -60,7 +57,6 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc);
 void arch_teardown_msi_irq(unsigned int irq);
 int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
 void arch_teardown_msi_irqs(struct pci_dev *dev);
-int arch_msi_check_device(struct pci_dev* dev, int nvec, int type);
 void arch_restore_msi_irqs(struct pci_dev *dev);
 
 void default_teardown_msi_irqs(struct pci_dev *dev);
@@ -77,8 +73,6 @@ struct msi_chip {
 	int (*setup_irq)(struct msi_chip *chip, struct pci_dev *dev,
 			 struct msi_desc *desc);
 	void (*teardown_irq)(struct msi_chip *chip, unsigned int irq);
-	int (*check_device)(struct msi_chip *chip, struct pci_dev *dev,
-			    int nvec, int type);
 };
 
 #endif /* LINUX_MSI_H */
diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h
index 37ef6b194089..299d7d31fe53 100644
--- a/include/linux/mtd/cfi.h
+++ b/include/linux/mtd/cfi.h
@@ -153,7 +153,7 @@ struct cfi_ident {
 	uint16_t MaxBufWriteSize;
 	uint8_t  NumEraseRegions;
 	uint32_t EraseRegionInfo[0]; /* Not host ordered */
-} __attribute__((packed));
+} __packed;
 
 /* Extended Query Structure for both PRI and ALT */
 
@@ -161,7 +161,7 @@ struct cfi_extquery {
 	uint8_t  pri[3];
 	uint8_t  MajorVersion;
 	uint8_t  MinorVersion;
-} __attribute__((packed));
+} __packed;
 
 /* Vendor-Specific PRI for Intel/Sharp Extended Command Set (0x0001) */
 
@@ -180,7 +180,7 @@ struct cfi_pri_intelext {
 	uint8_t  FactProtRegSize;
 	uint8_t  UserProtRegSize;
 	uint8_t  extra[0];
-} __attribute__((packed));
+} __packed;
 
 struct cfi_intelext_otpinfo {
 	uint32_t ProtRegAddr;
@@ -188,7 +188,7 @@ struct cfi_intelext_otpinfo {
 	uint8_t  FactProtRegSize;
 	uint16_t UserGroups;
 	uint8_t  UserProtRegSize;
-} __attribute__((packed));
+} __packed;
 
 struct cfi_intelext_blockinfo {
 	uint16_t NumIdentBlocks;
@@ -196,7 +196,7 @@ struct cfi_intelext_blockinfo {
 	uint16_t MinBlockEraseCycles;
 	uint8_t  BitsPerCell;
 	uint8_t  BlockCap;
-} __attribute__((packed));
+} __packed;
 
 struct cfi_intelext_regioninfo {
 	uint16_t NumIdentPartitions;
@@ -205,7 +205,7 @@ struct cfi_intelext_regioninfo {
 	uint8_t  NumOpAllowedSimEraMode;
 	uint8_t  NumBlockTypes;
 	struct cfi_intelext_blockinfo BlockTypes[1];
-} __attribute__((packed));
+} __packed;
 
 struct cfi_intelext_programming_regioninfo {
 	uint8_t  ProgRegShift;
@@ -214,7 +214,7 @@ struct cfi_intelext_programming_regioninfo {
 	uint8_t  Reserved2;
 	uint8_t  ControlInvalid;
 	uint8_t  Reserved3;
-} __attribute__((packed));
+} __packed;
 
 /* Vendor-Specific PRI for AMD/Fujitsu Extended Command Set (0x0002) */
 
@@ -233,7 +233,7 @@ struct cfi_pri_amdstd {
 	uint8_t  VppMin;
 	uint8_t  VppMax;
 	uint8_t  TopBottom;
-} __attribute__((packed));
+} __packed;
 
 /* Vendor-Specific PRI for Atmel chips (command set 0x0002) */
 
@@ -245,18 +245,18 @@ struct cfi_pri_atmel {
 	uint8_t BottomBoot;
 	uint8_t BurstMode;
 	uint8_t PageMode;
-} __attribute__((packed));
+} __packed;
 
 struct cfi_pri_query {
 	uint8_t  NumFields;
 	uint32_t ProtField[1]; /* Not host ordered */
-} __attribute__((packed));
+} __packed;
 
 struct cfi_bri_query {
 	uint8_t  PageModeReadCap;
 	uint8_t  NumFields;
 	uint32_t ConfField[1]; /* Not host ordered */
-} __attribute__((packed));
+} __packed;
 
 #define P_ID_NONE               0x0000
 #define P_ID_INTEL_EXT          0x0001
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index c300db3ae285..e4d451e4600b 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -587,6 +587,11 @@ struct nand_buffers {
  * @ecc_step_ds:	[INTERN] ECC step required by the @ecc_strength_ds,
  *                      also from the datasheet. It is the recommended ECC step
  *			size, if known; if unknown, set to zero.
+ * @onfi_timing_mode_default: [INTERN] default ONFI timing mode. This field is
+ *			      either deduced from the datasheet if the NAND
+ *			      chip is not ONFI compliant or set to 0 if it is
+ *			      (an ONFI chip is always configured in mode 0
+ *			      after a NAND reset)
  * @numchips:		[INTERN] number of physical chips
  * @chipsize:		[INTERN] the size of one chip for multichip arrays
  * @pagemask:		[INTERN] page number mask = number of (pages / chip) - 1
@@ -671,6 +676,7 @@ struct nand_chip {
 	uint8_t bits_per_cell;
 	uint16_t ecc_strength_ds;
 	uint16_t ecc_step_ds;
+	int onfi_timing_mode_default;
 	int badblockpos;
 	int badblockbits;
 
@@ -766,12 +772,17 @@ struct nand_chip {
  * @options: stores various chip bit options
  * @id_len: The valid length of the @id.
  * @oobsize: OOB size
+ * @ecc: ECC correctability and step information from the datasheet.
  * @ecc.strength_ds: The ECC correctability from the datasheet, same as the
  *                   @ecc_strength_ds in nand_chip{}.
  * @ecc.step_ds: The ECC step required by the @ecc.strength_ds, same as the
  *               @ecc_step_ds in nand_chip{}, also from the datasheet.
  *               For example, the "4bit ECC for each 512Byte" can be set with
  *               NAND_ECC_INFO(4, 512).
+ * @onfi_timing_mode_default: the default ONFI timing mode entered after a NAND
+ *			      reset. Should be deduced from timings described
+ *			      in the datasheet.
+ *
  */
 struct nand_flash_dev {
 	char *name;
@@ -792,6 +803,7 @@ struct nand_flash_dev {
 		uint16_t strength_ds;
 		uint16_t step_ds;
 	} ecc;
+	int onfi_timing_mode_default;
 };
 
 /**
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 8d5535c58cc2..cc31498fc526 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -52,7 +52,7 @@ struct mutex {
 	atomic_t		count;
 	spinlock_t		wait_lock;
 	struct list_head	wait_list;
-#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP)
+#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
 	struct task_struct	*owner;
 #endif
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
@@ -133,7 +133,7 @@ static inline int mutex_is_locked(struct mutex *lock)
 
 /*
  * See kernel/locking/mutex.c for detailed documentation of these APIs.
- * Also see Documentation/mutex-design.txt.
+ * Also see Documentation/locking/mutex-design.txt.
  */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 026b0c042c40..356acc2846fd 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -487,6 +487,9 @@ enum {
 	NFSPROC4_CLNT_GETDEVICELIST,
 	NFSPROC4_CLNT_BIND_CONN_TO_SESSION,
 	NFSPROC4_CLNT_DESTROY_CLIENTID,
+
+	/* nfs42 */
+	NFSPROC4_CLNT_SEEK,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 28d649054d5f..c72d1ad41ad4 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -448,10 +448,10 @@ static inline struct rpc_cred *nfs_file_cred(struct file *file)
 extern ssize_t nfs_direct_IO(int, struct kiocb *, struct iov_iter *, loff_t);
 extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
 			struct iov_iter *iter,
-			loff_t pos, bool uio);
+			loff_t pos);
 extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
 			struct iov_iter *iter,
-			loff_t pos, bool uio);
+			loff_t pos);
 
 /*
  * linux/fs/nfs/dir.c
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 922be2e050f5..a32ba0d7a98f 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -230,5 +230,6 @@ struct nfs_server {
 #define NFS_CAP_STATEID_NFSV41	(1U << 16)
 #define NFS_CAP_ATOMIC_OPEN_V1	(1U << 17)
 #define NFS_CAP_SECURITY_LABEL	(1U << 18)
+#define NFS_CAP_SEEK		(1U << 19)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 6951c7d9097d..983876f24aed 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1231,6 +1231,25 @@ struct pnfs_ds_commit_info {
 
 #endif /* CONFIG_NFS_V4_1 */
 
+#ifdef CONFIG_NFS_V4_2
+struct nfs42_seek_args {
+	struct nfs4_sequence_args	seq_args;
+
+	struct nfs_fh			*sa_fh;
+	nfs4_stateid			sa_stateid;
+	u64				sa_offset;
+	u32				sa_what;
+};
+
+struct nfs42_seek_res {
+	struct nfs4_sequence_res	seq_res;
+	unsigned int			status;
+
+	u32	sr_eof;
+	u64	sr_offset;
+};
+#endif
+
 struct nfs_page;
 
 #define NFS_PAGEVEC_SIZE	(8U)
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 1d2a6ab6b8bb..9b2022ab4d85 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -24,6 +24,19 @@ static inline void touch_nmi_watchdog(void)
 }
 #endif
 
+#if defined(CONFIG_HARDLOCKUP_DETECTOR)
+extern void watchdog_enable_hardlockup_detector(bool val);
+extern bool watchdog_hardlockup_detector_is_enabled(void);
+#else
+static inline void watchdog_enable_hardlockup_detector(bool val)
+{
+}
+static inline bool watchdog_hardlockup_detector_is_enabled(void)
+{
+	return true;
+}
+#endif
+
 /*
  * Create trigger_all_cpu_backtrace() out of the arch-provided
  * base function. Return whether such support was available,
diff --git a/include/linux/of.h b/include/linux/of.h
index 6c4363b8ddc3..6545e7aec7bb 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -863,4 +863,7 @@ static inline int of_changeset_update_property(struct of_changeset *ocs,
 }
 #endif
 
+/* CONFIG_OF_RESOLVE api */
+extern int of_resolve_phandles(struct device_node *tree);
+
 #endif /* _LINUX_OF_H */
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index fb7b7221e063..8cb14eb393d6 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -23,17 +23,6 @@ struct of_pci_range {
 #define for_each_of_pci_range(parser, range) \
 	for (; of_pci_range_parser_one(parser, range);)
 
-static inline void of_pci_range_to_resource(struct of_pci_range *range,
-					    struct device_node *np,
-					    struct resource *res)
-{
-	res->flags = range->flags;
-	res->start = range->cpu_addr;
-	res->end = range->cpu_addr + range->size - 1;
-	res->parent = res->child = res->sibling = NULL;
-	res->name = np->full_name;
-}
-
 /* Translate a DMA address from device space to CPU space */
 extern u64 of_translate_dma_address(struct device_node *dev,
 				    const __be32 *in_addr);
@@ -55,7 +44,9 @@ extern void __iomem *of_iomap(struct device_node *device, int index);
 extern const __be32 *of_get_address(struct device_node *dev, int index,
 			   u64 *size, unsigned int *flags);
 
+extern int pci_register_io_range(phys_addr_t addr, resource_size_t size);
 extern unsigned long pci_address_to_pio(phys_addr_t addr);
+extern phys_addr_t pci_pio_to_address(unsigned long pio);
 
 extern int of_pci_range_parser_init(struct of_pci_range_parser *parser,
 			struct device_node *node);
@@ -80,6 +71,11 @@ static inline const __be32 *of_get_address(struct device_node *dev, int index,
 	return NULL;
 }
 
+static inline phys_addr_t pci_pio_to_address(unsigned long pio)
+{
+	return 0;
+}
+
 static inline int of_pci_range_parser_init(struct of_pci_range_parser *parser,
 			struct device_node *node)
 {
@@ -138,6 +134,9 @@ extern const __be32 *of_get_pci_address(struct device_node *dev, int bar_no,
 			       u64 *size, unsigned int *flags);
 extern int of_pci_address_to_resource(struct device_node *dev, int bar,
 				      struct resource *r);
+extern int of_pci_range_to_resource(struct of_pci_range *range,
+				    struct device_node *np,
+				    struct resource *res);
 #else /* CONFIG_OF_ADDRESS && CONFIG_PCI */
 static inline int of_pci_address_to_resource(struct device_node *dev, int bar,
 				             struct resource *r)
@@ -150,6 +149,12 @@ static inline const __be32 *of_get_pci_address(struct device_node *dev,
 {
 	return NULL;
 }
+static inline int of_pci_range_to_resource(struct of_pci_range *range,
+					   struct device_node *np,
+					   struct resource *res)
+{
+	return -ENOSYS;
+}
 #endif /* CONFIG_OF_ADDRESS && CONFIG_PCI */
 
 #endif /* __OF_ADDRESS_H */
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index dde3a4a0fa5d..1fd207e7a847 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -15,6 +15,7 @@ struct device_node *of_pci_find_child_device(struct device_node *parent,
 int of_pci_get_devfn(struct device_node *np);
 int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin);
 int of_pci_parse_bus_range(struct device_node *node, struct resource *res);
+int of_get_pci_domain_nr(struct device_node *node);
 #else
 static inline int of_irq_parse_pci(const struct pci_dev *pdev, struct of_phandle_args *out_irq)
 {
@@ -43,6 +44,18 @@ of_pci_parse_bus_range(struct device_node *node, struct resource *res)
 {
 	return -EINVAL;
 }
+
+static inline int
+of_get_pci_domain_nr(struct device_node *node)
+{
+	return -1;
+}
+#endif
+
+#if defined(CONFIG_OF_ADDRESS)
+int of_pci_get_host_bridge_resources(struct device_node *dev,
+			unsigned char busno, unsigned char bus_max,
+			struct list_head *resources, resource_size_t *io_base);
 #endif
 
 #if defined(CONFIG_OF) && defined(CONFIG_PCI_MSI)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 19191d39c4f3..7ea069cd3257 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -24,8 +24,7 @@ enum mapping_flags {
 	AS_ENOSPC	= __GFP_BITS_SHIFT + 1,	/* ENOSPC on async write */
 	AS_MM_ALL_LOCKS	= __GFP_BITS_SHIFT + 2,	/* under mm_take_all_locks() */
 	AS_UNEVICTABLE	= __GFP_BITS_SHIFT + 3,	/* e.g., ramdisk, SHM_LOCK */
-	AS_BALLOON_MAP  = __GFP_BITS_SHIFT + 4, /* balloon page special map */
-	AS_EXITING	= __GFP_BITS_SHIFT + 5, /* final truncate in progress */
+	AS_EXITING	= __GFP_BITS_SHIFT + 4, /* final truncate in progress */
 };
 
 static inline void mapping_set_error(struct address_space *mapping, int error)
@@ -55,21 +54,6 @@ static inline int mapping_unevictable(struct address_space *mapping)
 	return !!mapping;
 }
 
-static inline void mapping_set_balloon(struct address_space *mapping)
-{
-	set_bit(AS_BALLOON_MAP, &mapping->flags);
-}
-
-static inline void mapping_clear_balloon(struct address_space *mapping)
-{
-	clear_bit(AS_BALLOON_MAP, &mapping->flags);
-}
-
-static inline int mapping_balloon(struct address_space *mapping)
-{
-	return mapping && test_bit(AS_BALLOON_MAP, &mapping->flags);
-}
-
 static inline void mapping_set_exiting(struct address_space *mapping)
 {
 	set_bit(AS_EXITING, &mapping->flags);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 96453f9bc8ba..5be8db45e368 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -45,7 +45,7 @@
  * In the interest of not exposing interfaces to user-space unnecessarily,
  * the following kernel-only defines are being added here.
  */
-#define PCI_DEVID(bus, devfn)  ((((u16)bus) << 8) | devfn)
+#define PCI_DEVID(bus, devfn)  ((((u16)(bus)) << 8) | (devfn))
 /* return bus from PCI devid = ((u16)bus_number) << 8) | devfn */
 #define PCI_BUS_NUM(x) (((x) >> 8) & 0xff)
 
@@ -457,6 +457,9 @@ struct pci_bus {
 	unsigned char	primary;	/* number of primary bridge */
 	unsigned char	max_bus_speed;	/* enum pci_bus_speed */
 	unsigned char	cur_bus_speed;	/* enum pci_bus_speed */
+#ifdef CONFIG_PCI_DOMAINS_GENERIC
+	int		domain_nr;
+#endif
 
 	char		name[48];
 
@@ -1103,6 +1106,9 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus,
 						  resource_size_t),
 			void *alignf_data);
 
+
+int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr);
+
 static inline dma_addr_t pci_bus_address(struct pci_dev *pdev, int bar)
 {
 	struct pci_bus_region region;
@@ -1288,12 +1294,32 @@ void pci_cfg_access_unlock(struct pci_dev *dev);
  */
 #ifdef CONFIG_PCI_DOMAINS
 extern int pci_domains_supported;
+int pci_get_new_domain_nr(void);
 #else
 enum { pci_domains_supported = 0 };
 static inline int pci_domain_nr(struct pci_bus *bus) { return 0; }
 static inline int pci_proc_domain(struct pci_bus *bus) { return 0; }
+static inline int pci_get_new_domain_nr(void) { return -ENOSYS; }
 #endif /* CONFIG_PCI_DOMAINS */
 
+/*
+ * Generic implementation for PCI domain support. If your
+ * architecture does not need custom management of PCI
+ * domains then this implementation will be used
+ */
+#ifdef CONFIG_PCI_DOMAINS_GENERIC
+static inline int pci_domain_nr(struct pci_bus *bus)
+{
+	return bus->domain_nr;
+}
+void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent);
+#else
+static inline void pci_bus_assign_domain_nr(struct pci_bus *bus,
+					struct device *parent)
+{
+}
+#endif
+
 /* some architectures require additional setup to direct VGA traffic */
 typedef int (*arch_set_vga_state_t)(struct pci_dev *pdev, bool decode,
 		      unsigned int command_bits, u32 flags);
@@ -1402,6 +1428,7 @@ static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus,
 
 static inline int pci_domain_nr(struct pci_bus *bus) { return 0; }
 static inline struct pci_dev *pci_dev_get(struct pci_dev *dev) { return NULL; }
+static inline int pci_get_new_domain_nr(void) { return -ENOSYS; }
 
 #define dev_is_pci(d) (false)
 #define dev_is_pf(d) (false)
@@ -1563,16 +1590,11 @@ enum pci_fixup_pass {
 
 #ifdef CONFIG_PCI_QUIRKS
 void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev);
-struct pci_dev *pci_get_dma_source(struct pci_dev *dev);
 int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
 void pci_dev_specific_enable_acs(struct pci_dev *dev);
 #else
 static inline void pci_fixup_device(enum pci_fixup_pass pass,
 				    struct pci_dev *dev) { }
-static inline struct pci_dev *pci_get_dma_source(struct pci_dev *dev)
-{
-	return pci_dev_get(dev);
-}
 static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
 					       u16 acs_flags)
 {
@@ -1707,7 +1729,7 @@ bool pci_acs_path_enabled(struct pci_dev *start,
 			  struct pci_dev *end, u16 acs_flags);
 
 #define PCI_VPD_LRDT			0x80	/* Large Resource Data Type */
-#define PCI_VPD_LRDT_ID(x)		(x | PCI_VPD_LRDT)
+#define PCI_VPD_LRDT_ID(x)		((x) | PCI_VPD_LRDT)
 
 /* Large Resource Data Type Tag Item Names */
 #define PCI_VPD_LTIN_ID_STRING		0x02	/* Identifier String */
@@ -1834,15 +1856,17 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
 			   int (*fn)(struct pci_dev *pdev,
 				     u16 alias, void *data), void *data);
 
-/**
- * pci_find_upstream_pcie_bridge - find upstream PCIe-to-PCI bridge of a device
- * @pdev: the PCI device
- *
- * if the device is PCIE, return NULL
- * if the device isn't connected to a PCIe bridge (that is its parent is a
- * legacy PCI bridge and the bridge is directly connected to bus 0), return its
- * parent
- */
-struct pci_dev *pci_find_upstream_pcie_bridge(struct pci_dev *pdev);
-
+/* helper functions for operation of device flag */
+static inline void pci_set_dev_assigned(struct pci_dev *pdev)
+{
+	pdev->dev_flags |= PCI_DEV_FLAGS_ASSIGNED;
+}
+static inline void pci_clear_dev_assigned(struct pci_dev *pdev)
+{
+	pdev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
+}
+static inline bool pci_is_dev_assigned(struct pci_dev *pdev)
+{
+	return (pdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) == PCI_DEV_FLAGS_ASSIGNED;
+}
 #endif /* LINUX_PCI_H */
diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h
index 5f2e559af6b0..2706ee9a4327 100644
--- a/include/linux/pci_hotplug.h
+++ b/include/linux/pci_hotplug.h
@@ -187,6 +187,4 @@ static inline int pci_get_hp_params(struct pci_dev *dev,
 	return -ENODEV;
 }
 #endif
-
-void pci_configure_slot(struct pci_dev *dev);
 #endif
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 6ed0bb73a864..1fa99a301817 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2245,6 +2245,8 @@
 #define PCI_VENDOR_ID_MORETON		0x15aa
 #define PCI_DEVICE_ID_RASTEL_2PORT	0x2000
 
+#define PCI_VENDOR_ID_VMWARE		0x15ad
+
 #define PCI_VENDOR_ID_ZOLTRIX		0x15b0
 #define PCI_DEVICE_ID_ZOLTRIX_2BD0	0x2bd0
 
@@ -2536,6 +2538,7 @@
 #define PCI_DEVICE_ID_INTEL_EESSC	0x0008
 #define PCI_DEVICE_ID_INTEL_SNB_IMC	0x0100
 #define PCI_DEVICE_ID_INTEL_IVB_IMC	0x0154
+#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC	0x0150
 #define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_PXHD_0	0x0320
 #define PCI_DEVICE_ID_INTEL_PXHD_1	0x0321
@@ -2557,6 +2560,7 @@
 #define PCI_DEVICE_ID_INTEL_MFD_EMMC0	0x0823
 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1	0x0824
 #define PCI_DEVICE_ID_INTEL_MRST_SD2	0x084F
+#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB	0x095E
 #define PCI_DEVICE_ID_INTEL_I960	0x0960
 #define PCI_DEVICE_ID_INTEL_I960RM	0x0962
 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB	0x0c60
@@ -2818,7 +2822,22 @@
 #define PCI_DEVICE_ID_INTEL_UNC_R2PCIE	0x3c43
 #define PCI_DEVICE_ID_INTEL_UNC_R3QPI0	0x3c44
 #define PCI_DEVICE_ID_INTEL_UNC_R3QPI1	0x3c45
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_RAS	0x3c71	/* 15.1 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR0	0x3c72	/* 16.2 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR1	0x3c73	/* 16.3 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR2	0x3c76	/* 16.6 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_ERR3	0x3c77	/* 16.7 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_HA0	0x3ca0	/* 14.0 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA	0x3ca8	/* 15.0 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD0	0x3caa	/* 15.2 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD1	0x3cab	/* 15.3 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD2	0x3cac	/* 15.4 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TAD3	0x3cad	/* 15.5 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_DDRIO	0x3cb8	/* 17.0 */
 #define PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX	0x3ce0
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD0	0x3cf4	/* 12.6 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_BR		0x3cf5	/* 13.6 */
+#define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1	0x3cf6	/* 12.7 */
 #define PCI_DEVICE_ID_INTEL_IOAT_SNB	0x402f
 #define PCI_DEVICE_ID_INTEL_5100_16	0x65f0
 #define PCI_DEVICE_ID_INTEL_5100_19	0x65f3
@@ -2860,6 +2879,7 @@
 #define PCI_DEVICE_ID_INTEL_82372FB_1	0x7601
 #define PCI_DEVICE_ID_INTEL_SCH_LPC	0x8119
 #define PCI_DEVICE_ID_INTEL_SCH_IDE	0x811a
+#define PCI_DEVICE_ID_INTEL_E6XX_CU	0x8183
 #define PCI_DEVICE_ID_INTEL_ITC_LPC	0x8186
 #define PCI_DEVICE_ID_INTEL_82454GX	0x84c4
 #define PCI_DEVICE_ID_INTEL_82450GX	0x84c5
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index cfd56046ecec..420032d41d27 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -257,9 +257,6 @@ do {									\
 #define __raw_get_cpu_var(var)	(*raw_cpu_ptr(&(var)))
 #define __get_cpu_var(var)	(*this_cpu_ptr(&(var)))
 
-/* keep until we have removed all uses of __this_cpu_ptr */
-#define __this_cpu_ptr(ptr)	raw_cpu_ptr(ptr)
-
 /*
  * Must be an lvalue. Since @var must be a simple identifier,
  * we force a syntax error here if it isn't.
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 68a64f11ce02..d5c89e0dd0e6 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -13,7 +13,7 @@
  *
  * The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less
  * than an atomic_t - this is because of the way shutdown works, see
- * percpu_ref_kill()/PCPU_COUNT_BIAS.
+ * percpu_ref_kill()/PERCPU_COUNT_BIAS.
  *
  * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the
  * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill()
@@ -49,29 +49,60 @@
 #include <linux/kernel.h>
 #include <linux/percpu.h>
 #include <linux/rcupdate.h>
+#include <linux/gfp.h>
 
 struct percpu_ref;
 typedef void (percpu_ref_func_t)(struct percpu_ref *);
 
+/* flags set in the lower bits of percpu_ref->percpu_count_ptr */
+enum {
+	__PERCPU_REF_ATOMIC	= 1LU << 0,	/* operating in atomic mode */
+	__PERCPU_REF_DEAD	= 1LU << 1,	/* (being) killed */
+	__PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD,
+
+	__PERCPU_REF_FLAG_BITS	= 2,
+};
+
+/* @flags for percpu_ref_init() */
+enum {
+	/*
+	 * Start w/ ref == 1 in atomic mode.  Can be switched to percpu
+	 * operation using percpu_ref_switch_to_percpu().  If initialized
+	 * with this flag, the ref will stay in atomic mode until
+	 * percpu_ref_switch_to_percpu() is invoked on it.
+	 */
+	PERCPU_REF_INIT_ATOMIC	= 1 << 0,
+
+	/*
+	 * Start dead w/ ref == 0 in atomic mode.  Must be revived with
+	 * percpu_ref_reinit() before used.  Implies INIT_ATOMIC.
+	 */
+	PERCPU_REF_INIT_DEAD	= 1 << 1,
+};
+
 struct percpu_ref {
-	atomic_t		count;
+	atomic_long_t		count;
 	/*
 	 * The low bit of the pointer indicates whether the ref is in percpu
 	 * mode; if set, then get/put will manipulate the atomic_t.
 	 */
-	unsigned long		pcpu_count_ptr;
+	unsigned long		percpu_count_ptr;
 	percpu_ref_func_t	*release;
-	percpu_ref_func_t	*confirm_kill;
+	percpu_ref_func_t	*confirm_switch;
+	bool			force_atomic:1;
 	struct rcu_head		rcu;
 };
 
 int __must_check percpu_ref_init(struct percpu_ref *ref,
-				 percpu_ref_func_t *release);
-void percpu_ref_reinit(struct percpu_ref *ref);
+				 percpu_ref_func_t *release, unsigned int flags,
+				 gfp_t gfp);
 void percpu_ref_exit(struct percpu_ref *ref);
+void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
+				 percpu_ref_func_t *confirm_switch);
+void percpu_ref_switch_to_percpu(struct percpu_ref *ref);
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill);
-void __percpu_ref_kill_expedited(struct percpu_ref *ref);
+void percpu_ref_reinit(struct percpu_ref *ref);
 
 /**
  * percpu_ref_kill - drop the initial ref
@@ -88,26 +119,24 @@ static inline void percpu_ref_kill(struct percpu_ref *ref)
 	return percpu_ref_kill_and_confirm(ref, NULL);
 }
 
-#define PCPU_REF_DEAD		1
-
 /*
  * Internal helper.  Don't use outside percpu-refcount proper.  The
  * function doesn't return the pointer and let the caller test it for NULL
  * because doing so forces the compiler to generate two conditional
- * branches as it can't assume that @ref->pcpu_count is not NULL.
+ * branches as it can't assume that @ref->percpu_count is not NULL.
  */
-static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
-				    unsigned __percpu **pcpu_countp)
+static inline bool __ref_is_percpu(struct percpu_ref *ref,
+					  unsigned long __percpu **percpu_countp)
 {
-	unsigned long pcpu_ptr = ACCESS_ONCE(ref->pcpu_count_ptr);
+	unsigned long percpu_ptr = ACCESS_ONCE(ref->percpu_count_ptr);
 
 	/* paired with smp_store_release() in percpu_ref_reinit() */
 	smp_read_barrier_depends();
 
-	if (unlikely(pcpu_ptr & PCPU_REF_DEAD))
+	if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC))
 		return false;
 
-	*pcpu_countp = (unsigned __percpu *)pcpu_ptr;
+	*percpu_countp = (unsigned long __percpu *)percpu_ptr;
 	return true;
 }
 
@@ -115,18 +144,20 @@ static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
  * percpu_ref_get - increment a percpu refcount
  * @ref: percpu_ref to get
  *
- * Analagous to atomic_inc().
-  */
+ * Analagous to atomic_long_inc().
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
 static inline void percpu_ref_get(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
-	if (__pcpu_ref_alive(ref, &pcpu_count))
-		this_cpu_inc(*pcpu_count);
+	if (__ref_is_percpu(ref, &percpu_count))
+		this_cpu_inc(*percpu_count);
 	else
-		atomic_inc(&ref->count);
+		atomic_long_inc(&ref->count);
 
 	rcu_read_unlock_sched();
 }
@@ -138,20 +169,20 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
  * Increment a percpu refcount unless its count already reached zero.
  * Returns %true on success; %false on failure.
  *
- * The caller is responsible for ensuring that @ref stays accessible.
+ * This function is safe to call as long as @ref is between init and exit.
  */
 static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
-	int ret = false;
+	unsigned long __percpu *percpu_count;
+	int ret;
 
 	rcu_read_lock_sched();
 
-	if (__pcpu_ref_alive(ref, &pcpu_count)) {
-		this_cpu_inc(*pcpu_count);
+	if (__ref_is_percpu(ref, &percpu_count)) {
+		this_cpu_inc(*percpu_count);
 		ret = true;
 	} else {
-		ret = atomic_inc_not_zero(&ref->count);
+		ret = atomic_long_inc_not_zero(&ref->count);
 	}
 
 	rcu_read_unlock_sched();
@@ -166,23 +197,26 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
  * Increment a percpu refcount unless it has already been killed.  Returns
  * %true on success; %false on failure.
  *
- * Completion of percpu_ref_kill() in itself doesn't guarantee that tryget
- * will fail.  For such guarantee, percpu_ref_kill_and_confirm() should be
- * used.  After the confirm_kill callback is invoked, it's guaranteed that
- * no new reference will be given out by percpu_ref_tryget().
+ * Completion of percpu_ref_kill() in itself doesn't guarantee that this
+ * function will fail.  For such guarantee, percpu_ref_kill_and_confirm()
+ * should be used.  After the confirm_kill callback is invoked, it's
+ * guaranteed that no new reference will be given out by
+ * percpu_ref_tryget_live().
  *
- * The caller is responsible for ensuring that @ref stays accessible.
+ * This function is safe to call as long as @ref is between init and exit.
  */
 static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *percpu_count;
 	int ret = false;
 
 	rcu_read_lock_sched();
 
-	if (__pcpu_ref_alive(ref, &pcpu_count)) {
-		this_cpu_inc(*pcpu_count);
+	if (__ref_is_percpu(ref, &percpu_count)) {
+		this_cpu_inc(*percpu_count);
 		ret = true;
+	} else if (!(ACCESS_ONCE(ref->percpu_count_ptr) & __PERCPU_REF_DEAD)) {
+		ret = atomic_long_inc_not_zero(&ref->count);
 	}
 
 	rcu_read_unlock_sched();
@@ -196,16 +230,18 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
  *
  * Decrement the refcount, and if 0, call the release function (which was passed
  * to percpu_ref_init())
+ *
+ * This function is safe to call as long as @ref is between init and exit.
  */
 static inline void percpu_ref_put(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
-	if (__pcpu_ref_alive(ref, &pcpu_count))
-		this_cpu_dec(*pcpu_count);
-	else if (unlikely(atomic_dec_and_test(&ref->count)))
+	if (__ref_is_percpu(ref, &percpu_count))
+		this_cpu_dec(*percpu_count);
+	else if (unlikely(atomic_long_dec_and_test(&ref->count)))
 		ref->release(ref);
 
 	rcu_read_unlock_sched();
@@ -216,14 +252,16 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
  * @ref: percpu_ref to test
  *
  * Returns %true if @ref reached zero.
+ *
+ * This function is safe to call as long as @ref is between init and exit.
  */
 static inline bool percpu_ref_is_zero(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count;
+	unsigned long __percpu *percpu_count;
 
-	if (__pcpu_ref_alive(ref, &pcpu_count))
+	if (__ref_is_percpu(ref, &percpu_count))
 		return false;
-	return !atomic_read(&ref->count);
+	return !atomic_long_read(&ref->count);
 }
 
 #endif
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 6f61b61b7996..a3aa63e47637 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -48,9 +48,9 @@
  * intelligent way to determine this would be nice.
  */
 #if BITS_PER_LONG > 32
-#define PERCPU_DYNAMIC_RESERVE		(20 << 10)
+#define PERCPU_DYNAMIC_RESERVE		(28 << 10)
 #else
-#define PERCPU_DYNAMIC_RESERVE		(12 << 10)
+#define PERCPU_DYNAMIC_RESERVE		(20 << 10)
 #endif
 
 extern void *pcpu_base_addr;
@@ -122,11 +122,16 @@ extern void __init setup_per_cpu_areas(void);
 #endif
 extern void __init percpu_init_late(void);
 
+extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp);
 extern void __percpu *__alloc_percpu(size_t size, size_t align);
 extern void free_percpu(void __percpu *__pdata);
 extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
 
-#define alloc_percpu(type)	\
-	(typeof(type) __percpu *)__alloc_percpu(sizeof(type), __alignof__(type))
+#define alloc_percpu_gfp(type, gfp)					\
+	(typeof(type) __percpu *)__alloc_percpu_gfp(sizeof(type),	\
+						__alignof__(type), gfp)
+#define alloc_percpu(type)						\
+	(typeof(type) __percpu *)__alloc_percpu(sizeof(type),		\
+						__alignof__(type))
 
 #endif /* __LINUX_PERCPU_H */
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index d5dd4657c8d6..50e50095c8d1 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -12,6 +12,7 @@
 #include <linux/threads.h>
 #include <linux/percpu.h>
 #include <linux/types.h>
+#include <linux/gfp.h>
 
 #ifdef CONFIG_SMP
 
@@ -26,14 +27,14 @@ struct percpu_counter {
 
 extern int percpu_counter_batch;
 
-int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
+int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp,
 			  struct lock_class_key *key);
 
-#define percpu_counter_init(fbc, value)					\
+#define percpu_counter_init(fbc, value, gfp)				\
 	({								\
 		static struct lock_class_key __key;			\
 									\
-		__percpu_counter_init(fbc, value, &__key);		\
+		__percpu_counter_init(fbc, value, gfp, &__key);		\
 	})
 
 void percpu_counter_destroy(struct percpu_counter *fbc);
@@ -89,7 +90,8 @@ struct percpu_counter {
 	s64 count;
 };
 
-static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount)
+static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount,
+				      gfp_t gfp)
 {
 	fbc->count = amount;
 	return 0;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 707617a8c0f6..893a0d07986f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -52,6 +52,7 @@ struct perf_guest_info_callbacks {
 #include <linux/atomic.h>
 #include <linux/sysfs.h>
 #include <linux/perf_regs.h>
+#include <linux/workqueue.h>
 #include <asm/local.h>
 
 struct perf_callchain_entry {
@@ -268,6 +269,7 @@ struct pmu {
  * enum perf_event_active_state - the states of a event
  */
 enum perf_event_active_state {
+	PERF_EVENT_STATE_EXIT		= -3,
 	PERF_EVENT_STATE_ERROR		= -2,
 	PERF_EVENT_STATE_OFF		= -1,
 	PERF_EVENT_STATE_INACTIVE	=  0,
@@ -507,6 +509,9 @@ struct perf_event_context {
 	int				nr_cgroups;	 /* cgroup evts */
 	int				nr_branch_stack; /* branch_stack evt */
 	struct rcu_head			rcu_head;
+
+	struct delayed_work		orphans_remove;
+	bool				orphans_remove_sched;
 };
 
 /*
@@ -604,6 +609,13 @@ struct perf_sample_data {
 	u64				txn;
 };
 
+/* default value for data source */
+#define PERF_MEM_NA (PERF_MEM_S(OP, NA)   |\
+		    PERF_MEM_S(LVL, NA)   |\
+		    PERF_MEM_S(SNOOP, NA) |\
+		    PERF_MEM_S(LOCK, NA)  |\
+		    PERF_MEM_S(TLB, NA))
+
 static inline void perf_sample_data_init(struct perf_sample_data *data,
 					 u64 addr, u64 period)
 {
@@ -616,7 +628,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->regs_user.regs = NULL;
 	data->stack_user_size = 0;
 	data->weight = 0;
-	data->data_src.val = 0;
+	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
 }
 
diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h
new file mode 100644
index 000000000000..d8155c005242
--- /dev/null
+++ b/include/linux/platform_data/dma-dw.h
@@ -0,0 +1,59 @@
+/*
+ * Driver for the Synopsys DesignWare DMA Controller
+ *
+ * Copyright (C) 2007 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef _PLATFORM_DATA_DMA_DW_H
+#define _PLATFORM_DATA_DMA_DW_H
+
+#include <linux/device.h>
+
+/**
+ * struct dw_dma_slave - Controller-specific information about a slave
+ *
+ * @dma_dev: required DMA master device. Depricated.
+ * @src_id:	src request line
+ * @dst_id:	dst request line
+ * @src_master: src master for transfers on allocated channel.
+ * @dst_master: dest master for transfers on allocated channel.
+ */
+struct dw_dma_slave {
+	struct device		*dma_dev;
+	u8			src_id;
+	u8			dst_id;
+	u8			src_master;
+	u8			dst_master;
+};
+
+/**
+ * struct dw_dma_platform_data - Controller configuration parameters
+ * @nr_channels: Number of channels supported by hardware (max 8)
+ * @is_private: The device channels should be marked as private and not for
+ *	by the general purpose DMA channel allocator.
+ * @chan_allocation_order: Allocate channels starting from 0 or 7
+ * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0.
+ * @block_size: Maximum block size supported by the controller
+ * @nr_masters: Number of AHB masters supported by the controller
+ * @data_width: Maximum data width supported by hardware per AHB master
+ *		(0 - 8bits, 1 - 16bits, ..., 5 - 256bits)
+ */
+struct dw_dma_platform_data {
+	unsigned int	nr_channels;
+	bool		is_private;
+#define CHAN_ALLOCATION_ASCENDING	0	/* zero to seven */
+#define CHAN_ALLOCATION_DESCENDING	1	/* seven to zero */
+	unsigned char	chan_allocation_order;
+#define CHAN_PRIORITY_ASCENDING		0	/* chan0 highest */
+#define CHAN_PRIORITY_DESCENDING	1	/* chan7 highest */
+	unsigned char	chan_priority;
+	unsigned short	block_size;
+	unsigned char	nr_masters;
+	unsigned char	data_width[4];
+};
+
+#endif /* _PLATFORM_DATA_DMA_DW_H */
diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h
index 780d1e97f620..b8686c00f15f 100644
--- a/include/linux/platform_data/elm.h
+++ b/include/linux/platform_data/elm.h
@@ -42,8 +42,24 @@ struct elm_errorvec {
 	int error_loc[16];
 };
 
+#if IS_ENABLED(CONFIG_MTD_NAND_OMAP_BCH)
 void elm_decode_bch_error_page(struct device *dev, u8 *ecc_calc,
 		struct elm_errorvec *err_vec);
 int elm_config(struct device *dev, enum bch_ecc bch_type,
 	int ecc_steps, int ecc_step_size, int ecc_syndrome_size);
+#else
+static inline void
+elm_decode_bch_error_page(struct device *dev, u8 *ecc_calc,
+			  struct elm_errorvec *err_vec)
+{
+}
+
+static inline int elm_config(struct device *dev, enum bch_ecc bch_type,
+			     int ecc_steps, int ecc_step_size,
+			     int ecc_syndrome_size)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_MTD_NAND_ECC_BCH */
+
 #endif /* __ELM_H */
diff --git a/include/linux/platform_data/gpio-dwapb.h b/include/linux/platform_data/gpio-dwapb.h
new file mode 100644
index 000000000000..28702c849af1
--- /dev/null
+++ b/include/linux/platform_data/gpio-dwapb.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef GPIO_DW_APB_H
+#define GPIO_DW_APB_H
+
+struct dwapb_port_property {
+	struct device_node *node;
+	const char	*name;
+	unsigned int	idx;
+	unsigned int	ngpio;
+	unsigned int	gpio_base;
+	unsigned int	irq;
+	bool		irq_shared;
+};
+
+struct dwapb_platform_data {
+	struct dwapb_port_property *properties;
+	unsigned int nports;
+};
+
+#endif
diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h
index 16ec262dfcc8..090bbab0130a 100644
--- a/include/linux/platform_data/mtd-nand-omap2.h
+++ b/include/linux/platform_data/mtd-nand-omap2.h
@@ -71,6 +71,7 @@ struct omap_nand_platform_data {
 	struct mtd_partition	*parts;
 	int			nr_parts;
 	bool			dev_ready;
+	bool			flash_bbt;
 	enum nand_io		xfer_type;
 	int			devsize;
 	enum omap_ecc           ecc_opt;
diff --git a/include/linux/platform_data/rcar-du.h b/include/linux/platform_data/rcar-du.h
index 1a2e9901a22e..a5f045e1d8fe 100644
--- a/include/linux/platform_data/rcar-du.h
+++ b/include/linux/platform_data/rcar-du.h
@@ -14,7 +14,7 @@
 #ifndef __RCAR_DU_H__
 #define __RCAR_DU_H__
 
-#include <drm/drm_mode.h>
+#include <video/videomode.h>
 
 enum rcar_du_output {
 	RCAR_DU_OUTPUT_DPAD0,
@@ -35,7 +35,7 @@ enum rcar_du_encoder_type {
 struct rcar_du_panel_data {
 	unsigned int width_mm;		/* Panel width in mm */
 	unsigned int height_mm;		/* Panel height in mm */
-	struct drm_mode_modeinfo mode;
+	struct videomode mode;
 };
 
 struct rcar_du_connector_lvds_data {
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 72c0fe098a27..383fd68aaee1 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -619,6 +619,7 @@ extern int dev_pm_put_subsys_data(struct device *dev);
  */
 struct dev_pm_domain {
 	struct dev_pm_ops	ops;
+	void (*detach)(struct device *dev, bool power_off);
 };
 
 /*
@@ -679,12 +680,16 @@ struct dev_pm_domain {
 extern void device_pm_lock(void);
 extern void dpm_resume_start(pm_message_t state);
 extern void dpm_resume_end(pm_message_t state);
+extern void dpm_resume_noirq(pm_message_t state);
+extern void dpm_resume_early(pm_message_t state);
 extern void dpm_resume(pm_message_t state);
 extern void dpm_complete(pm_message_t state);
 
 extern void device_pm_unlock(void);
 extern int dpm_suspend_end(pm_message_t state);
 extern int dpm_suspend_start(pm_message_t state);
+extern int dpm_suspend_noirq(pm_message_t state);
+extern int dpm_suspend_late(pm_message_t state);
 extern int dpm_suspend(pm_message_t state);
 extern int dpm_prepare(pm_message_t state);
 
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index ebc4c76ffb73..73e938b7e937 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -35,18 +35,10 @@ struct gpd_dev_ops {
 	int (*stop)(struct device *dev);
 	int (*save_state)(struct device *dev);
 	int (*restore_state)(struct device *dev);
-	int (*suspend)(struct device *dev);
-	int (*suspend_late)(struct device *dev);
-	int (*resume_early)(struct device *dev);
-	int (*resume)(struct device *dev);
-	int (*freeze)(struct device *dev);
-	int (*freeze_late)(struct device *dev);
-	int (*thaw_early)(struct device *dev);
-	int (*thaw)(struct device *dev);
 	bool (*active_wakeup)(struct device *dev);
 };
 
-struct gpd_cpu_data {
+struct gpd_cpuidle_data {
 	unsigned int saved_exit_latency;
 	struct cpuidle_state *idle_state;
 };
@@ -71,7 +63,6 @@ struct generic_pm_domain {
 	unsigned int suspended_count;	/* System suspend device counter */
 	unsigned int prepared_count;	/* Suspend counter of prepared devices */
 	bool suspend_power_off;	/* Power status before system suspend */
-	bool dev_irq_safe;	/* Device callbacks are IRQ-safe */
 	int (*power_off)(struct generic_pm_domain *domain);
 	s64 power_off_latency_ns;
 	int (*power_on)(struct generic_pm_domain *domain);
@@ -80,8 +71,9 @@ struct generic_pm_domain {
 	s64 max_off_time_ns;	/* Maximum allowed "suspended" time. */
 	bool max_off_time_changed;
 	bool cached_power_down_ok;
-	struct device_node *of_node; /* Node in device tree */
-	struct gpd_cpu_data *cpu_data;
+	struct gpd_cpuidle_data *cpuidle_data;
+	void (*attach_dev)(struct device *dev);
+	void (*detach_dev)(struct device *dev);
 };
 
 static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd)
@@ -108,7 +100,6 @@ struct gpd_timing_data {
 
 struct generic_pm_domain_data {
 	struct pm_domain_data base;
-	struct gpd_dev_ops ops;
 	struct gpd_timing_data td;
 	struct notifier_block nb;
 	struct mutex lock;
@@ -127,17 +118,11 @@ static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev)
 	return to_gpd_data(dev->power.subsys_data->domain_data);
 }
 
-extern struct dev_power_governor simple_qos_governor;
-
 extern struct generic_pm_domain *dev_to_genpd(struct device *dev);
 extern int __pm_genpd_add_device(struct generic_pm_domain *genpd,
 				 struct device *dev,
 				 struct gpd_timing_data *td);
 
-extern int __pm_genpd_of_add_device(struct device_node *genpd_node,
-				    struct device *dev,
-				    struct gpd_timing_data *td);
-
 extern int __pm_genpd_name_add_device(const char *domain_name,
 				      struct device *dev,
 				      struct gpd_timing_data *td);
@@ -151,10 +136,6 @@ extern int pm_genpd_add_subdomain_names(const char *master_name,
 					const char *subdomain_name);
 extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 				     struct generic_pm_domain *target);
-extern int pm_genpd_add_callbacks(struct device *dev,
-				  struct gpd_dev_ops *ops,
-				  struct gpd_timing_data *td);
-extern int __pm_genpd_remove_callbacks(struct device *dev, bool clear_td);
 extern int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state);
 extern int pm_genpd_name_attach_cpuidle(const char *name, int state);
 extern int pm_genpd_detach_cpuidle(struct generic_pm_domain *genpd);
@@ -165,8 +146,7 @@ extern void pm_genpd_init(struct generic_pm_domain *genpd,
 extern int pm_genpd_poweron(struct generic_pm_domain *genpd);
 extern int pm_genpd_name_poweron(const char *domain_name);
 
-extern bool default_stop_ok(struct device *dev);
-
+extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
 #else
 
@@ -184,12 +164,6 @@ static inline int __pm_genpd_add_device(struct generic_pm_domain *genpd,
 {
 	return -ENOSYS;
 }
-static inline int __pm_genpd_of_add_device(struct device_node *genpd_node,
-					   struct device *dev,
-					   struct gpd_timing_data *td)
-{
-	return -ENOSYS;
-}
 static inline int __pm_genpd_name_add_device(const char *domain_name,
 					     struct device *dev,
 					     struct gpd_timing_data *td)
@@ -217,16 +191,6 @@ static inline int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 {
 	return -ENOSYS;
 }
-static inline int pm_genpd_add_callbacks(struct device *dev,
-					 struct gpd_dev_ops *ops,
-					 struct gpd_timing_data *td)
-{
-	return -ENOSYS;
-}
-static inline int __pm_genpd_remove_callbacks(struct device *dev, bool clear_td)
-{
-	return -ENOSYS;
-}
 static inline int pm_genpd_attach_cpuidle(struct generic_pm_domain *genpd, int st)
 {
 	return -ENOSYS;
@@ -255,10 +219,6 @@ static inline int pm_genpd_name_poweron(const char *domain_name)
 {
 	return -ENOSYS;
 }
-static inline bool default_stop_ok(struct device *dev)
-{
-	return false;
-}
 #define simple_qos_governor NULL
 #define pm_domain_always_on_gov NULL
 #endif
@@ -269,45 +229,87 @@ static inline int pm_genpd_add_device(struct generic_pm_domain *genpd,
 	return __pm_genpd_add_device(genpd, dev, NULL);
 }
 
-static inline int pm_genpd_of_add_device(struct device_node *genpd_node,
-					 struct device *dev)
-{
-	return __pm_genpd_of_add_device(genpd_node, dev, NULL);
-}
-
 static inline int pm_genpd_name_add_device(const char *domain_name,
 					   struct device *dev)
 {
 	return __pm_genpd_name_add_device(domain_name, dev, NULL);
 }
 
-static inline int pm_genpd_remove_callbacks(struct device *dev)
-{
-	return __pm_genpd_remove_callbacks(dev, true);
-}
-
 #ifdef CONFIG_PM_GENERIC_DOMAINS_RUNTIME
-extern void genpd_queue_power_off_work(struct generic_pm_domain *genpd);
 extern void pm_genpd_poweroff_unused(void);
 #else
-static inline void genpd_queue_power_off_work(struct generic_pm_domain *gpd) {}
 static inline void pm_genpd_poweroff_unused(void) {}
 #endif
 
 #ifdef CONFIG_PM_GENERIC_DOMAINS_SLEEP
-extern void pm_genpd_syscore_switch(struct device *dev, bool suspend);
+extern void pm_genpd_syscore_poweroff(struct device *dev);
+extern void pm_genpd_syscore_poweron(struct device *dev);
 #else
-static inline void pm_genpd_syscore_switch(struct device *dev, bool suspend) {}
+static inline void pm_genpd_syscore_poweroff(struct device *dev) {}
+static inline void pm_genpd_syscore_poweron(struct device *dev) {}
 #endif
 
-static inline void pm_genpd_syscore_poweroff(struct device *dev)
+/* OF PM domain providers */
+struct of_device_id;
+
+struct genpd_onecell_data {
+	struct generic_pm_domain **domains;
+	unsigned int num_domains;
+};
+
+typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args,
+						void *data);
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+			void *data);
+void of_genpd_del_provider(struct device_node *np);
+
+struct generic_pm_domain *__of_genpd_xlate_simple(
+					struct of_phandle_args *genpdspec,
+					void *data);
+struct generic_pm_domain *__of_genpd_xlate_onecell(
+					struct of_phandle_args *genpdspec,
+					void *data);
+
+int genpd_dev_pm_attach(struct device *dev);
+#else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
+static inline int __of_genpd_add_provider(struct device_node *np,
+					genpd_xlate_t xlate, void *data)
+{
+	return 0;
+}
+static inline void of_genpd_del_provider(struct device_node *np) {}
+
+#define __of_genpd_xlate_simple		NULL
+#define __of_genpd_xlate_onecell	NULL
+
+static inline int genpd_dev_pm_attach(struct device *dev)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
+
+static inline int of_genpd_add_provider_simple(struct device_node *np,
+					struct generic_pm_domain *genpd)
+{
+	return __of_genpd_add_provider(np, __of_genpd_xlate_simple, genpd);
+}
+static inline int of_genpd_add_provider_onecell(struct device_node *np,
+					struct genpd_onecell_data *data)
 {
-	pm_genpd_syscore_switch(dev, true);
+	return __of_genpd_add_provider(np, __of_genpd_xlate_onecell, data);
 }
 
-static inline void pm_genpd_syscore_poweron(struct device *dev)
+#ifdef CONFIG_PM
+extern int dev_pm_domain_attach(struct device *dev, bool power_on);
+extern void dev_pm_domain_detach(struct device *dev, bool power_off);
+#else
+static inline int dev_pm_domain_attach(struct device *dev, bool power_on)
 {
-	pm_genpd_syscore_switch(dev, false);
+	return -ENODEV;
 }
+static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {}
+#endif
 
 #endif /* _LINUX_PM_DOMAIN_H */
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index f3dea41dbcd2..3ed049673022 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -18,8 +18,6 @@
 #include <linux/spinlock.h>
 #include <linux/notifier.h>
 
-struct device;
-
 /*
  * All voltages, currents, charges, energies, time and temperatures in uV,
  * µA, µAh, µWh, seconds and tenths of degree Celsius unless otherwise
@@ -102,9 +100,11 @@ enum power_supply_property {
 	POWER_SUPPLY_PROP_VOLTAGE_NOW,
 	POWER_SUPPLY_PROP_VOLTAGE_AVG,
 	POWER_SUPPLY_PROP_VOLTAGE_OCV,
+	POWER_SUPPLY_PROP_VOLTAGE_BOOT,
 	POWER_SUPPLY_PROP_CURRENT_MAX,
 	POWER_SUPPLY_PROP_CURRENT_NOW,
 	POWER_SUPPLY_PROP_CURRENT_AVG,
+	POWER_SUPPLY_PROP_CURRENT_BOOT,
 	POWER_SUPPLY_PROP_POWER_NOW,
 	POWER_SUPPLY_PROP_POWER_AVG,
 	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
@@ -146,6 +146,7 @@ enum power_supply_property {
 	POWER_SUPPLY_PROP_TYPE, /* use power_supply.type instead */
 	POWER_SUPPLY_PROP_SCOPE,
 	POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT,
+	POWER_SUPPLY_PROP_CALIBRATE,
 	/* Properties of type `const char *' */
 	POWER_SUPPLY_PROP_MODEL_NAME,
 	POWER_SUPPLY_PROP_MANUFACTURER,
@@ -172,6 +173,7 @@ union power_supply_propval {
 	const char *strval;
 };
 
+struct device;
 struct device_node;
 
 struct power_supply {
@@ -291,6 +293,7 @@ static inline bool power_supply_is_amp_property(enum power_supply_property psp)
 	case POWER_SUPPLY_PROP_CURRENT_MAX:
 	case POWER_SUPPLY_PROP_CURRENT_NOW:
 	case POWER_SUPPLY_PROP_CURRENT_AVG:
+	case POWER_SUPPLY_PROP_CURRENT_BOOT:
 		return 1;
 	default:
 		break;
@@ -315,6 +318,7 @@ static inline bool power_supply_is_watt_property(enum power_supply_property psp)
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
 	case POWER_SUPPLY_PROP_VOLTAGE_AVG:
 	case POWER_SUPPLY_PROP_VOLTAGE_OCV:
+	case POWER_SUPPLY_PROP_VOLTAGE_BOOT:
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE:
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
 	case POWER_SUPPLY_PROP_POWER_NOW:
diff --git a/include/linux/prio_heap.h b/include/linux/prio_heap.h
deleted file mode 100644
index 08094350f26a..000000000000
--- a/include/linux/prio_heap.h
+++ /dev/null
@@ -1,58 +0,0 @@
-#ifndef _LINUX_PRIO_HEAP_H
-#define _LINUX_PRIO_HEAP_H
-
-/*
- * Simple insertion-only static-sized priority heap containing
- * pointers, based on CLR, chapter 7
- */
-
-#include <linux/gfp.h>
-
-/**
- * struct ptr_heap - simple static-sized priority heap
- * @ptrs - pointer to data area
- * @max - max number of elements that can be stored in @ptrs
- * @size - current number of valid elements in @ptrs (in the range 0..@size-1
- * @gt: comparison operator, which should implement "greater than"
- */
-struct ptr_heap {
-	void **ptrs;
-	int max;
-	int size;
-	int (*gt)(void *, void *);
-};
-
-/**
- * heap_init - initialize an empty heap with a given memory size
- * @heap: the heap structure to be initialized
- * @size: amount of memory to use in bytes
- * @gfp_mask: mask to pass to kmalloc()
- * @gt: comparison operator, which should implement "greater than"
- */
-extern int heap_init(struct ptr_heap *heap, size_t size, gfp_t gfp_mask,
-		     int (*gt)(void *, void *));
-
-/**
- * heap_free - release a heap's storage
- * @heap: the heap structure whose data should be released
- */
-void heap_free(struct ptr_heap *heap);
-
-/**
- * heap_insert - insert a value into the heap and return any overflowed value
- * @heap: the heap to be operated on
- * @p: the pointer to be inserted
- *
- * Attempts to insert the given value into the priority heap. If the
- * heap is full prior to the insertion, then the resulting heap will
- * consist of the smallest @max elements of the original heap and the
- * new element; the greatest element will be removed from the heap and
- * returned. Note that the returned element will be the new element
- * (i.e. no change to the heap) if the new element is greater than all
- * elements currently in the heap.
- */
-extern void *heap_insert(struct ptr_heap *heap, void *p);
-
-
-
-#endif /* _LINUX_PRIO_HEAP_H */
diff --git a/include/linux/proportions.h b/include/linux/proportions.h
index 26a8a4ed9b07..00e8e8fa7358 100644
--- a/include/linux/proportions.h
+++ b/include/linux/proportions.h
@@ -12,6 +12,7 @@
 #include <linux/percpu_counter.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
+#include <linux/gfp.h>
 
 struct prop_global {
 	/*
@@ -40,7 +41,7 @@ struct prop_descriptor {
 	struct mutex mutex;		/* serialize the prop_global switch */
 };
 
-int prop_descriptor_init(struct prop_descriptor *pd, int shift);
+int prop_descriptor_init(struct prop_descriptor *pd, int shift, gfp_t gfp);
 void prop_change_shift(struct prop_descriptor *pd, int new_shift);
 
 /*
@@ -61,7 +62,7 @@ struct prop_local_percpu {
 	raw_spinlock_t lock;		/* protect the snapshot state */
 };
 
-int prop_local_init_percpu(struct prop_local_percpu *pl);
+int prop_local_init_percpu(struct prop_local_percpu *pl, gfp_t gfp);
 void prop_local_destroy_percpu(struct prop_local_percpu *pl);
 void __prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl);
 void prop_fraction_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl,
diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index fea49b5da12a..378c5ee75f78 100644
--- a/include/linux/rbtree_augmented.h
+++ b/include/linux/rbtree_augmented.h
@@ -43,6 +43,16 @@ struct rb_augment_callbacks {
 
 extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+/*
+ * Fixup the rbtree and update the augmented information when rebalancing.
+ *
+ * On insertion, the user must update the augmented information on the path
+ * leading to the inserted node, then call rb_link_node() as usual and
+ * rb_augment_inserted() instead of the usual rb_insert_color() call.
+ * If rb_augment_inserted() rebalances the rbtree, it will callback into
+ * a user provided function to update the augmented information on the
+ * affected subtrees.
+ */
 static inline void
 rb_insert_augmented(struct rb_node *node, struct rb_root *root,
 		    const struct rb_augment_callbacks *augment)
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index d231aa17b1d7..a4a819ffb2d1 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -47,14 +47,12 @@
 #include <asm/barrier.h>
 
 extern int rcu_expedited; /* for sysctl */
-#ifdef CONFIG_RCU_TORTURE_TEST
-extern int rcutorture_runnable; /* for sysctl */
-#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 enum rcutorture_type {
 	RCU_FLAVOR,
 	RCU_BH_FLAVOR,
 	RCU_SCHED_FLAVOR,
+	RCU_TASKS_FLAVOR,
 	SRCU_FLAVOR,
 	INVALID_RCU_FLAVOR
 };
@@ -197,6 +195,28 @@ void call_rcu_sched(struct rcu_head *head,
 
 void synchronize_sched(void);
 
+/**
+ * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks() assumes
+ * that the read-side critical sections end at a voluntary context
+ * switch (not a preemption!), entry into idle, or transition to usermode
+ * execution.  As such, there are no read-side primitives analogous to
+ * rcu_read_lock() and rcu_read_unlock() because this primitive is intended
+ * to determine that all tasks have passed through a safe state, not so
+ * much for data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks(struct rcu_head *head, void (*func)(struct rcu_head *head));
+void synchronize_rcu_tasks(void);
+void rcu_barrier_tasks(void);
+
 #ifdef CONFIG_PREEMPT_RCU
 
 void __rcu_read_lock(void);
@@ -238,8 +258,8 @@ static inline int rcu_preempt_depth(void)
 
 /* Internal to kernel */
 void rcu_init(void);
-void rcu_sched_qs(int cpu);
-void rcu_bh_qs(int cpu);
+void rcu_sched_qs(void);
+void rcu_bh_qs(void);
 void rcu_check_callbacks(int cpu, int user);
 struct notifier_block;
 void rcu_idle_enter(void);
@@ -269,6 +289,14 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 					 struct task_struct *next) { }
 #endif /* CONFIG_RCU_USER_QS */
 
+#ifdef CONFIG_RCU_NOCB_CPU
+void rcu_init_nohz(void);
+#else /* #ifdef CONFIG_RCU_NOCB_CPU */
+static inline void rcu_init_nohz(void)
+{
+}
+#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
+
 /**
  * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers
  * @a: Code that RCU needs to pay attention to.
@@ -294,6 +322,36 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 		rcu_irq_exit(); \
 	} while (0)
 
+/*
+ * Note a voluntary context switch for RCU-tasks benefit.  This is a
+ * macro rather than an inline function to avoid #include hell.
+ */
+#ifdef CONFIG_TASKS_RCU
+#define TASKS_RCU(x) x
+extern struct srcu_struct tasks_rcu_exit_srcu;
+#define rcu_note_voluntary_context_switch(t) \
+	do { \
+		if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
+			ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
+	} while (0)
+#else /* #ifdef CONFIG_TASKS_RCU */
+#define TASKS_RCU(x) do { } while (0)
+#define rcu_note_voluntary_context_switch(t)	do { } while (0)
+#endif /* #else #ifdef CONFIG_TASKS_RCU */
+
+/**
+ * cond_resched_rcu_qs - Report potential quiescent states to RCU
+ *
+ * This macro resembles cond_resched(), except that it is defined to
+ * report potential quiescent states to RCU-tasks even if the cond_resched()
+ * machinery were to be shut off, as some advocate for PREEMPT kernels.
+ */
+#define cond_resched_rcu_qs() \
+do { \
+	rcu_note_voluntary_context_switch(current); \
+	cond_resched(); \
+} while (0)
+
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
 bool __rcu_is_watching(void);
 #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
@@ -349,7 +407,7 @@ bool rcu_lockdep_current_cpu_online(void);
 #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
 static inline bool rcu_lockdep_current_cpu_online(void)
 {
-	return 1;
+	return true;
 }
 #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */
 
@@ -371,41 +429,7 @@ extern struct lockdep_map rcu_sched_lock_map;
 extern struct lockdep_map rcu_callback_map;
 int debug_lockdep_rcu_enabled(void);
 
-/**
- * rcu_read_lock_held() - might we be in RCU read-side critical section?
- *
- * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
- * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
- * this assumes we are in an RCU read-side critical section unless it can
- * prove otherwise.  This is useful for debug checks in functions that
- * require that they be called within an RCU read-side critical section.
- *
- * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
- * and while lockdep is disabled.
- *
- * Note that rcu_read_lock() and the matching rcu_read_unlock() must
- * occur in the same context, for example, it is illegal to invoke
- * rcu_read_unlock() in process context if the matching rcu_read_lock()
- * was invoked from within an irq handler.
- *
- * Note that rcu_read_lock() is disallowed if the CPU is either idle or
- * offline from an RCU perspective, so check for those as well.
- */
-static inline int rcu_read_lock_held(void)
-{
-	if (!debug_lockdep_rcu_enabled())
-		return 1;
-	if (!rcu_is_watching())
-		return 0;
-	if (!rcu_lockdep_current_cpu_online())
-		return 0;
-	return lock_is_held(&rcu_lock_map);
-}
-
-/*
- * rcu_read_lock_bh_held() is defined out of line to avoid #include-file
- * hell.
- */
+int rcu_read_lock_held(void);
 int rcu_read_lock_bh_held(void);
 
 /**
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index d40a6a451330..38cc5b1e252d 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -80,7 +80,7 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 
 static inline void rcu_note_context_switch(int cpu)
 {
-	rcu_sched_qs(cpu);
+	rcu_sched_qs();
 }
 
 /*
diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index 48bf152761c7..67fc8fcdc4b0 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -38,6 +38,9 @@ extern int reboot_force;
 extern int register_reboot_notifier(struct notifier_block *);
 extern int unregister_reboot_notifier(struct notifier_block *);
 
+extern int register_restart_handler(struct notifier_block *);
+extern int unregister_restart_handler(struct notifier_block *);
+extern void do_kernel_restart(char *cmd);
 
 /*
  * Architecture-specific implementations of sys_reboot commands.
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index be574506e6a9..c0c2bce6b0b7 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -150,7 +150,7 @@ int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
 static inline void anon_vma_merge(struct vm_area_struct *vma,
 				  struct vm_area_struct *next)
 {
-	VM_BUG_ON(vma->anon_vma != next->anon_vma);
+	VM_BUG_ON_VMA(vma->anon_vma != next->anon_vma, vma);
 	unlink_anon_vmas(next);
 }
 
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 035d3c57fc8a..8f498cdde280 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -149,7 +149,7 @@ extern void downgrade_write(struct rw_semaphore *sem);
  * static then another method for expressing nested locking is
  * the explicit definition of lock class keys and the use of
  * lockdep_set_class() at lock initialization time.
- * See Documentation/lockdep-design.txt for more details.)
+ * See Documentation/locking/lockdep-design.txt for more details.)
  */
 extern void down_read_nested(struct rw_semaphore *sem, int subclass);
 extern void down_write_nested(struct rw_semaphore *sem, int subclass);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9c6353d9e63a..5e344bbe63ec 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -57,6 +57,7 @@ struct sched_param {
 #include <linux/llist.h>
 #include <linux/uidgid.h>
 #include <linux/gfp.h>
+#include <linux/magic.h>
 
 #include <asm/processor.h>
 
@@ -646,6 +647,7 @@ struct signal_struct {
 	 * Live threads maintain their own counters and add to these
 	 * in __exit_signal, except for the group leader.
 	 */
+	seqlock_t stats_lock;
 	cputime_t utime, stime, cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
@@ -1024,6 +1026,7 @@ struct sched_domain_topology_level {
 extern struct sched_domain_topology_level *sched_domain_topology;
 
 extern void set_sched_topology(struct sched_domain_topology_level *tl);
+extern void wake_up_if_idle(int cpu);
 
 #ifdef CONFIG_SCHED_DEBUG
 # define SD_INIT_NAME(type)		.name = #type
@@ -1213,6 +1216,13 @@ struct sched_dl_entity {
 	struct hrtimer dl_timer;
 };
 
+union rcu_special {
+	struct {
+		bool blocked;
+		bool need_qs;
+	} b;
+	short s;
+};
 struct rcu_node;
 
 enum perf_event_task_context {
@@ -1265,12 +1275,18 @@ struct task_struct {
 
 #ifdef CONFIG_PREEMPT_RCU
 	int rcu_read_lock_nesting;
-	char rcu_read_unlock_special;
+	union rcu_special rcu_read_unlock_special;
 	struct list_head rcu_node_entry;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 #ifdef CONFIG_TREE_PREEMPT_RCU
 	struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+#ifdef CONFIG_TASKS_RCU
+	unsigned long rcu_tasks_nvcsw;
+	bool rcu_tasks_holdout;
+	struct list_head rcu_tasks_holdout_list;
+	int rcu_tasks_idle_cpu;
+#endif /* #ifdef CONFIG_TASKS_RCU */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	struct sched_info sched_info;
@@ -1935,11 +1951,13 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
-/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags
+ * __GFP_FS is also cleared as it implies __GFP_IO.
+ */
 static inline gfp_t memalloc_noio_flags(gfp_t flags)
 {
 	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
-		flags &= ~__GFP_IO;
+		flags &= ~(__GFP_IO | __GFP_FS);
 	return flags;
 }
 
@@ -2012,29 +2030,21 @@ extern void task_clear_jobctl_trapping(struct task_struct *task);
 extern void task_clear_jobctl_pending(struct task_struct *task,
 				      unsigned int mask);
 
-#ifdef CONFIG_PREEMPT_RCU
-
-#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
-#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
-
 static inline void rcu_copy_process(struct task_struct *p)
 {
+#ifdef CONFIG_PREEMPT_RCU
 	p->rcu_read_lock_nesting = 0;
-	p->rcu_read_unlock_special = 0;
-#ifdef CONFIG_TREE_PREEMPT_RCU
+	p->rcu_read_unlock_special.s = 0;
 	p->rcu_blocked_node = NULL;
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 	INIT_LIST_HEAD(&p->rcu_node_entry);
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+#ifdef CONFIG_TASKS_RCU
+	p->rcu_tasks_holdout = false;
+	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
+	p->rcu_tasks_idle_cpu = -1;
+#endif /* #ifdef CONFIG_TASKS_RCU */
 }
 
-#else
-
-static inline void rcu_copy_process(struct task_struct *p)
-{
-}
-
-#endif
-
 static inline void tsk_restore_flags(struct task_struct *task,
 				unsigned long orig_flags, unsigned long flags)
 {
@@ -2640,6 +2650,8 @@ static inline unsigned long *end_of_stack(struct task_struct *p)
 }
 
 #endif
+#define task_stack_end_corrupted(task) \
+		(*(end_of_stack(task)) != STACK_END_MAGIC)
 
 static inline int object_is_on_stack(void *obj)
 {
@@ -2662,6 +2674,7 @@ static inline unsigned long stack_not_used(struct task_struct *p)
 	return (unsigned long)n - (unsigned long)end_of_stack(p);
 }
 #endif
+extern void set_task_stack_end_magic(struct task_struct *tsk);
 
 /* set thread flags in other task's structures
  * - see asm/thread_info.h for TIF_xxxx flags available
diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h
index 005bf3e38db5..f0f8bad54be9 100644
--- a/include/linux/screen_info.h
+++ b/include/linux/screen_info.h
@@ -5,12 +5,4 @@
 
 extern struct screen_info screen_info;
 
-#define ORIG_X			(screen_info.orig_x)
-#define ORIG_Y			(screen_info.orig_y)
-#define ORIG_VIDEO_MODE		(screen_info.orig_video_mode)
-#define ORIG_VIDEO_COLS 	(screen_info.orig_video_cols)
-#define ORIG_VIDEO_EGA_BX	(screen_info.orig_video_ega_bx)
-#define ORIG_VIDEO_LINES	(screen_info.orig_video_lines)
-#define ORIG_VIDEO_ISVGA	(screen_info.orig_video_isVGA)
-#define ORIG_VIDEO_POINTS       (screen_info.orig_video_points)
 #endif /* _SCREEN_INFO_H */
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 5d586a45a319..a19ddacdac30 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -27,19 +27,23 @@ struct seccomp {
 	struct seccomp_filter *filter;
 };
 
-extern int __secure_computing(int);
-static inline int secure_computing(int this_syscall)
+#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
+extern int __secure_computing(void);
+static inline int secure_computing(void)
 {
 	if (unlikely(test_thread_flag(TIF_SECCOMP)))
-		return  __secure_computing(this_syscall);
+		return  __secure_computing();
 	return 0;
 }
 
-/* A wrapper for architectures supporting only SECCOMP_MODE_STRICT. */
-static inline void secure_computing_strict(int this_syscall)
-{
-	BUG_ON(secure_computing(this_syscall) != 0);
-}
+#define SECCOMP_PHASE1_OK	0
+#define SECCOMP_PHASE1_SKIP	1
+
+extern u32 seccomp_phase1(struct seccomp_data *sd);
+int seccomp_phase2(u32 phase1_result);
+#else
+extern void secure_computing_strict(int this_syscall);
+#endif
 
 extern long prctl_get_seccomp(void);
 extern long prctl_set_seccomp(unsigned long, char __user *);
@@ -56,8 +60,11 @@ static inline int seccomp_mode(struct seccomp *s)
 struct seccomp { };
 struct seccomp_filter { };
 
-static inline int secure_computing(int this_syscall) { return 0; }
+#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
+static inline int secure_computing(void) { return 0; }
+#else
 static inline void secure_computing_strict(int this_syscall) { return; }
+#endif
 
 static inline long prctl_get_seccomp(void)
 {
diff --git a/include/linux/security.h b/include/linux/security.h
index 623f90e5f38d..ba96471c11ba 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1559,7 +1559,7 @@ struct security_operations {
 	int (*file_lock) (struct file *file, unsigned int cmd);
 	int (*file_fcntl) (struct file *file, unsigned int cmd,
 			   unsigned long arg);
-	int (*file_set_fowner) (struct file *file);
+	void (*file_set_fowner) (struct file *file);
 	int (*file_send_sigiotask) (struct task_struct *tsk,
 				    struct fown_struct *fown, int sig);
 	int (*file_receive) (struct file *file);
@@ -1834,7 +1834,7 @@ int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
 			   unsigned long prot);
 int security_file_lock(struct file *file, unsigned int cmd);
 int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
-int security_file_set_fowner(struct file *file);
+void security_file_set_fowner(struct file *file);
 int security_file_send_sigiotask(struct task_struct *tsk,
 				 struct fown_struct *fown, int sig);
 int security_file_receive(struct file *file);
@@ -2108,7 +2108,7 @@ static inline int security_dentry_init_security(struct dentry *dentry,
 static inline int security_inode_init_security(struct inode *inode,
 						struct inode *dir,
 						const struct qstr *qstr,
-						const initxattrs initxattrs,
+						const initxattrs xattrs,
 						void *fs_data)
 {
 	return 0;
@@ -2312,9 +2312,9 @@ static inline int security_file_fcntl(struct file *file, unsigned int cmd,
 	return 0;
 }
 
-static inline int security_file_set_fowner(struct file *file)
+static inline void security_file_set_fowner(struct file *file)
 {
-	return 0;
+	return;
 }
 
 static inline int security_file_send_sigiotask(struct task_struct *tsk,
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index cc359636cfa3..f5df8f687b4d 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -456,4 +456,23 @@ read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags)
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
+static inline unsigned long
+read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq)
+{
+	unsigned long flags = 0;
+
+	if (!(*seq & 1))	/* Even */
+		*seq = read_seqbegin(lock);
+	else			/* Odd */
+		read_seqlock_excl_irqsave(lock, flags);
+
+	return flags;
+}
+
+static inline void
+done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags)
+{
+	if (seq & 1)
+		read_sequnlock_excl_irqrestore(lock, flags);
+}
 #endif /* __LINUX_SEQLOCK_H */
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 750196fcc0a5..ab1e0392b5ac 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -2,6 +2,7 @@
 #define _LINUX_SIGNAL_H
 
 #include <linux/list.h>
+#include <linux/bug.h>
 #include <uapi/linux/signal.h>
 
 struct task_struct;
@@ -67,7 +68,6 @@ static inline int sigismember(sigset_t *set, int _sig)
 
 static inline int sigisemptyset(sigset_t *set)
 {
-	extern void _NSIG_WORDS_is_unsupported_size(void);
 	switch (_NSIG_WORDS) {
 	case 4:
 		return (set->sig[3] | set->sig[2] |
@@ -77,7 +77,7 @@ static inline int sigisemptyset(sigset_t *set)
 	case 1:
 		return set->sig[0] == 0;
 	default:
-		_NSIG_WORDS_is_unsupported_size();
+		BUILD_BUG();
 		return 0;
 	}
 }
@@ -90,24 +90,23 @@ static inline int sigisemptyset(sigset_t *set)
 #define _SIG_SET_BINOP(name, op)					\
 static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \
 {									\
-	extern void _NSIG_WORDS_is_unsupported_size(void);		\
 	unsigned long a0, a1, a2, a3, b0, b1, b2, b3;			\
 									\
 	switch (_NSIG_WORDS) {						\
-	    case 4:							\
+	case 4:								\
 		a3 = a->sig[3]; a2 = a->sig[2];				\
 		b3 = b->sig[3]; b2 = b->sig[2];				\
 		r->sig[3] = op(a3, b3);					\
 		r->sig[2] = op(a2, b2);					\
-	    case 2:							\
+	case 2:								\
 		a1 = a->sig[1]; b1 = b->sig[1];				\
 		r->sig[1] = op(a1, b1);					\
-	    case 1:							\
+	case 1:								\
 		a0 = a->sig[0]; b0 = b->sig[0];				\
 		r->sig[0] = op(a0, b0);					\
 		break;							\
-	    default:							\
-		_NSIG_WORDS_is_unsupported_size();			\
+	default:							\
+		BUILD_BUG();						\
 	}								\
 }
 
@@ -128,16 +127,14 @@ _SIG_SET_BINOP(sigandnsets, _sig_andn)
 #define _SIG_SET_OP(name, op)						\
 static inline void name(sigset_t *set)					\
 {									\
-	extern void _NSIG_WORDS_is_unsupported_size(void);		\
-									\
 	switch (_NSIG_WORDS) {						\
-	    case 4: set->sig[3] = op(set->sig[3]);			\
-		    set->sig[2] = op(set->sig[2]);			\
-	    case 2: set->sig[1] = op(set->sig[1]);			\
-	    case 1: set->sig[0] = op(set->sig[0]);			\
+	case 4:	set->sig[3] = op(set->sig[3]);				\
+		set->sig[2] = op(set->sig[2]);				\
+	case 2:	set->sig[1] = op(set->sig[1]);				\
+	case 1:	set->sig[0] = op(set->sig[0]);				\
 		    break;						\
-	    default:							\
-		_NSIG_WORDS_is_unsupported_size();			\
+	default:							\
+		BUILD_BUG();						\
 	}								\
 }
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 1d9abb7d22a0..c265bec6a57d 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -158,31 +158,6 @@ size_t ksize(const void *);
 #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
 #endif
 
-#ifdef CONFIG_SLOB
-/*
- * Common fields provided in kmem_cache by all slab allocators
- * This struct is either used directly by the allocator (SLOB)
- * or the allocator must include definitions for all fields
- * provided in kmem_cache_common in their definition of kmem_cache.
- *
- * Once we can do anonymous structs (C11 standard) we could put a
- * anonymous struct definition in these allocators so that the
- * separate allocations in the kmem_cache structure of SLAB and
- * SLUB is no longer needed.
- */
-struct kmem_cache {
-	unsigned int object_size;/* The original size of the object */
-	unsigned int size;	/* The aligned/padded/added on size  */
-	unsigned int align;	/* Alignment as calculated */
-	unsigned long flags;	/* Active flags on the slab */
-	const char *name;	/* Slab name for sysfs */
-	int refcount;		/* Use counter */
-	void (*ctor)(void *);	/* Called on object slot creation */
-	struct list_head list;	/* List of all slab caches on the system */
-};
-
-#endif /* CONFIG_SLOB */
-
 /*
  * Kmalloc array related definitions
  */
@@ -363,14 +338,6 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s,
 }
 #endif /* CONFIG_TRACING */
 
-#ifdef CONFIG_SLAB
-#include <linux/slab_def.h>
-#endif
-
-#ifdef CONFIG_SLUB
-#include <linux/slub_def.h>
-#endif
-
 extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order);
 
 #ifdef CONFIG_TRACING
@@ -582,37 +549,15 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
  * allocator where we care about the real place the memory allocation
  * request comes from.
  */
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \
-	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING)) || \
-	(defined(CONFIG_SLOB) && defined(CONFIG_TRACING))
 extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
 #define kmalloc_track_caller(size, flags) \
 	__kmalloc_track_caller(size, flags, _RET_IP_)
-#else
-#define kmalloc_track_caller(size, flags) \
-	__kmalloc(size, flags)
-#endif /* DEBUG_SLAB */
 
 #ifdef CONFIG_NUMA
-/*
- * kmalloc_node_track_caller is a special version of kmalloc_node that
- * records the calling function of the routine calling it for slab leak
- * tracking instead of just the calling function (confusing, eh?).
- * It's useful when the call to kmalloc_node comes from a widely-used
- * standard allocator where we care about the real place the memory
- * allocation request comes from.
- */
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \
-	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING)) || \
-	(defined(CONFIG_SLOB) && defined(CONFIG_TRACING))
 extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long);
 #define kmalloc_node_track_caller(size, flags, node) \
 	__kmalloc_node_track_caller(size, flags, node, \
 			_RET_IP_)
-#else
-#define kmalloc_node_track_caller(size, flags, node) \
-	__kmalloc_node(size, flags, node)
-#endif
 
 #else /* CONFIG_NUMA */
 
@@ -650,14 +595,7 @@ static inline void *kzalloc_node(size_t size, gfp_t flags, int node)
 	return kmalloc_node(size, flags | __GFP_ZERO, node);
 }
 
-/*
- * Determine the size of a slab object
- */
-static inline unsigned int kmem_cache_size(struct kmem_cache *s)
-{
-	return s->object_size;
-}
-
+unsigned int kmem_cache_size(struct kmem_cache *s);
 void __init kmem_cache_init_late(void);
 
 #endif	/* _LINUX_SLAB_H */
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 8235dfbb3b05..b869d1662ba3 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -8,6 +8,8 @@
  */
 
 struct kmem_cache {
+	struct array_cache __percpu *cpu_cache;
+
 /* 1) Cache tunables. Protected by slab_mutex */
 	unsigned int batchcount;
 	unsigned int limit;
@@ -71,23 +73,7 @@ struct kmem_cache {
 	struct memcg_cache_params *memcg_params;
 #endif
 
-/* 6) per-cpu/per-node data, touched during every alloc/free */
-	/*
-	 * We put array[] at the end of kmem_cache, because we want to size
-	 * this array to nr_cpu_ids slots instead of NR_CPUS
-	 * (see kmem_cache_init())
-	 * We still use [NR_CPUS] and not [1] or [0] because cache_cache
-	 * is statically defined, so we reserve the max number of cpus.
-	 *
-	 * We also need to guarantee that the list is able to accomodate a
-	 * pointer for each node since "nodelists" uses the remainder of
-	 * available pointers.
-	 */
-	struct kmem_cache_node **node;
-	struct array_cache *array[NR_CPUS + MAX_NUMNODES];
-	/*
-	 * Do not add fields after array[]
-	 */
+	struct kmem_cache_node *node[MAX_NUMNODES];
 };
 
 #endif	/* _LINUX_SLAB_DEF_H */
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 34347f26be9b..93dff5fff524 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -100,6 +100,7 @@ int smp_call_function_any(const struct cpumask *mask,
 			  smp_call_func_t func, void *info, int wait);
 
 void kick_all_cpus_sync(void);
+void wake_up_all_idle_cpus(void);
 
 /*
  * Generic and arch helpers
@@ -148,6 +149,7 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
 }
 
 static inline void kick_all_cpus_sync(void) {  }
+static inline void wake_up_all_idle_cpus(void) {  }
 
 #endif /* !SMP */
 
diff --git a/include/linux/spi/mcp23s08.h b/include/linux/spi/mcp23s08.h
index 2d676d5aaa89..aa07d7b32568 100644
--- a/include/linux/spi/mcp23s08.h
+++ b/include/linux/spi/mcp23s08.h
@@ -22,4 +22,22 @@ struct mcp23s08_platform_data {
 	 * base to base+15 (or base+31 for s17 variant).
 	 */
 	unsigned	base;
+	/* Marks the device as a interrupt controller.
+	 * NOTE: The interrupt functionality is only supported for i2c
+	 * versions of the chips. The spi chips can also do the interrupts,
+	 * but this is not supported by the linux driver yet.
+	 */
+	bool		irq_controller;
+
+	/* Sets the mirror flag in the IOCON register. Devices
+	 * with two interrupt outputs (these are the devices ending with 17 and
+	 * those that have 16 IOs) have two IO banks: IO 0-7 form bank 1 and
+	 * IO 8-15 are bank 2. These chips have two different interrupt outputs:
+	 * One for bank 1 and another for bank 2. If irq-mirror is set, both
+	 * interrupts are generated regardless of the bank that an input change
+	 * occurred on. If it is not set, the interrupt are only generated for
+	 * the bank they belong to.
+	 * On devices with only one interrupt output this property is useless.
+	 */
+	bool		mirror;
 };
diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h
index 82d5111cd0c2..d5a316550177 100644
--- a/include/linux/spi/pxa2xx_spi.h
+++ b/include/linux/spi/pxa2xx_spi.h
@@ -23,6 +23,8 @@
 #define PXA2XX_CS_ASSERT (0x01)
 #define PXA2XX_CS_DEASSERT (0x02)
 
+struct dma_chan;
+
 /* device.platform_data for SSP controller devices */
 struct pxa2xx_spi_master {
 	u32 clock_enable;
@@ -30,10 +32,9 @@ struct pxa2xx_spi_master {
 	u8 enable_dma;
 
 	/* DMA engine specific config */
-	int rx_chan_id;
-	int tx_chan_id;
-	int rx_slave_id;
-	int tx_slave_id;
+	bool (*dma_filter)(struct dma_chan *chan, void *param);
+	void *tx_param;
+	void *rx_param;
 
 	/* For non-PXA arches */
 	struct ssp_device ssp;
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 3f2867ff0ced..262ba4ef9a8e 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -197,7 +197,13 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 		 _raw_spin_lock_nest_lock(lock, &(nest_lock)->dep_map);	\
 	 } while (0)
 #else
-# define raw_spin_lock_nested(lock, subclass)		_raw_spin_lock(lock)
+/*
+ * Always evaluate the 'subclass' argument to avoid that the compiler
+ * warns about set-but-not-used variables when building with
+ * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1.
+ */
+# define raw_spin_lock_nested(lock, subclass)		\
+	_raw_spin_lock(((void)(subclass), (lock)))
 # define raw_spin_lock_nest_lock(lock, nest_lock)	_raw_spin_lock(lock)
 #endif
 
diff --git a/include/linux/string.h b/include/linux/string.h
index d36977e029af..e6edfe51575a 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -41,7 +41,7 @@ extern int strcmp(const char *,const char *);
 extern int strncmp(const char *,const char *,__kernel_size_t);
 #endif
 #ifndef __HAVE_ARCH_STRNICMP
-extern int strnicmp(const char *, const char *, __kernel_size_t);
+#define strnicmp strncasecmp
 #endif
 #ifndef __HAVE_ARCH_STRCASECMP
 extern int strcasecmp(const char *s1, const char *s2);
diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h
index 3eeee9672a4a..6eb567ac56bc 100644
--- a/include/linux/string_helpers.h
+++ b/include/linux/string_helpers.h
@@ -20,40 +20,6 @@ int string_get_size(u64 size, enum string_size_units units,
 #define UNESCAPE_ANY		\
 	(UNESCAPE_SPACE | UNESCAPE_OCTAL | UNESCAPE_HEX | UNESCAPE_SPECIAL)
 
-/**
- * string_unescape - unquote characters in the given string
- * @src:	source buffer (escaped)
- * @dst:	destination buffer (unescaped)
- * @size:	size of the destination buffer (0 to unlimit)
- * @flags:	combination of the flags (bitwise OR):
- *	%UNESCAPE_SPACE:
- *		'\f' - form feed
- *		'\n' - new line
- *		'\r' - carriage return
- *		'\t' - horizontal tab
- *		'\v' - vertical tab
- *	%UNESCAPE_OCTAL:
- *		'\NNN' - byte with octal value NNN (1 to 3 digits)
- *	%UNESCAPE_HEX:
- *		'\xHH' - byte with hexadecimal value HH (1 to 2 digits)
- *	%UNESCAPE_SPECIAL:
- *		'\"' - double quote
- *		'\\' - backslash
- *		'\a' - alert (BEL)
- *		'\e' - escape
- *	%UNESCAPE_ANY:
- *		all previous together
- *
- * Returns amount of characters processed to the destination buffer excluding
- * trailing '\0'.
- *
- * Because the size of the output will be the same as or less than the size of
- * the input, the transformation may be performed in place.
- *
- * Caller must provide valid source and destination pointers. Be aware that
- * destination buffer will always be NULL-terminated. Source string must be
- * NULL-terminated as well.
- */
 int string_unescape(char *src, char *dst, size_t size, unsigned int flags);
 
 static inline int string_unescape_inplace(char *buf, unsigned int flags)
@@ -71,4 +37,35 @@ static inline int string_unescape_any_inplace(char *buf)
 	return string_unescape_any(buf, buf, 0);
 }
 
+#define ESCAPE_SPACE		0x01
+#define ESCAPE_SPECIAL		0x02
+#define ESCAPE_NULL		0x04
+#define ESCAPE_OCTAL		0x08
+#define ESCAPE_ANY		\
+	(ESCAPE_SPACE | ESCAPE_OCTAL | ESCAPE_SPECIAL | ESCAPE_NULL)
+#define ESCAPE_NP		0x10
+#define ESCAPE_ANY_NP		(ESCAPE_ANY | ESCAPE_NP)
+#define ESCAPE_HEX		0x20
+
+int string_escape_mem(const char *src, size_t isz, char **dst, size_t osz,
+		unsigned int flags, const char *esc);
+
+static inline int string_escape_mem_any_np(const char *src, size_t isz,
+		char **dst, size_t osz, const char *esc)
+{
+	return string_escape_mem(src, isz, dst, osz, ESCAPE_ANY_NP, esc);
+}
+
+static inline int string_escape_str(const char *src, char **dst, size_t sz,
+		unsigned int flags, const char *esc)
+{
+	return string_escape_mem(src, strlen(src), dst, sz, flags, esc);
+}
+
+static inline int string_escape_str_any_np(const char *src, char **dst,
+		size_t sz, const char *esc)
+{
+	return string_escape_str(src, dst, sz, ESCAPE_ANY_NP, esc);
+}
+
 #endif
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 519064e0c943..3388c1b6f7d8 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -189,6 +189,8 @@ struct platform_suspend_ops {
 
 struct platform_freeze_ops {
 	int (*begin)(void);
+	int (*prepare)(void);
+	void (*restore)(void);
 	void (*end)(void);
 };
 
@@ -371,6 +373,8 @@ extern int unregister_pm_notifier(struct notifier_block *nb);
 extern bool events_check_enabled;
 
 extern bool pm_wakeup_pending(void);
+extern void pm_system_wakeup(void);
+extern void pm_wakeup_clear(void);
 extern bool pm_get_wakeup_count(unsigned int *count, bool block);
 extern bool pm_save_wakeup_count(unsigned int count);
 extern void pm_wakep_autosleep_enabled(bool set);
@@ -418,6 +422,8 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)
 
 static inline bool pm_wakeup_pending(void) { return false; }
+static inline void pm_system_wakeup(void) {}
+static inline void pm_wakeup_clear(void) {}
 
 static inline void lock_system_sleep(void) {}
 static inline void unlock_system_sleep(void) {}
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 1b72060f093a..37a585beef5c 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -327,8 +327,10 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
 extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
-extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
-						  gfp_t gfp_mask, bool noswap);
+extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
+						  unsigned long nr_pages,
+						  gfp_t gfp_mask,
+						  bool may_swap);
 extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 						gfp_t gfp_mask, bool noswap,
 						struct zone *zone,
@@ -354,22 +356,6 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
 extern int page_evictable(struct page *page);
 extern void check_move_unevictable_pages(struct page **, int nr_pages);
 
-extern unsigned long scan_unevictable_pages;
-extern int scan_unevictable_handler(struct ctl_table *, int,
-					void __user *, size_t *, loff_t *);
-#ifdef CONFIG_NUMA
-extern int scan_unevictable_register_node(struct node *node);
-extern void scan_unevictable_unregister_node(struct node *node);
-#else
-static inline int scan_unevictable_register_node(struct node *node)
-{
-	return 0;
-}
-static inline void scan_unevictable_unregister_node(struct node *node)
-{
-}
-#endif
-
 extern int kswapd_run(int nid);
 extern void kswapd_stop(int nid);
 #ifdef CONFIG_MEMCG
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
new file mode 100644
index 000000000000..6a8b9942632d
--- /dev/null
+++ b/include/linux/t10-pi.h
@@ -0,0 +1,22 @@
+#ifndef _LINUX_T10_PI_H
+#define _LINUX_T10_PI_H
+
+#include <linux/types.h>
+#include <linux/blkdev.h>
+
+/*
+ * T10 Protection Information tuple.
+ */
+struct t10_pi_tuple {
+	__be16 guard_tag;	/* Checksum */
+	__be16 app_tag;		/* Opaque storage */
+	__be32 ref_tag;		/* Target LBA or indirect LBA */
+};
+
+
+extern struct blk_integrity t10_pi_type1_crc;
+extern struct blk_integrity t10_pi_type1_ip;
+extern struct blk_integrity t10_pi_type3_crc;
+extern struct blk_integrity t10_pi_type3_ip;
+
+#endif
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 9a82c7dc3fdd..eda850ca757a 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -108,7 +108,7 @@ extern struct tick_sched *tick_get_tick_sched(int cpu);
 extern void tick_irq_enter(void);
 extern int tick_oneshot_mode_active(void);
 #  ifndef arch_needs_cpu
-#   define arch_needs_cpu(cpu) (0)
+#   define arch_needs_cpu() (0)
 #  endif
 # else
 static inline void tick_clock_notify(void) { }
@@ -181,14 +181,12 @@ static inline bool tick_nohz_full_cpu(int cpu)
 	return cpumask_test_cpu(cpu, tick_nohz_full_mask);
 }
 
-extern void tick_nohz_init(void);
 extern void __tick_nohz_full_check(void);
 extern void tick_nohz_full_kick(void);
 extern void tick_nohz_full_kick_cpu(int cpu);
 extern void tick_nohz_full_kick_all(void);
 extern void __tick_nohz_task_switch(struct task_struct *tsk);
 #else
-static inline void tick_nohz_init(void) { }
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void __tick_nohz_full_check(void) { }
diff --git a/include/linux/topology.h b/include/linux/topology.h
index dda6ee521e74..909b6e43b694 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -119,11 +119,20 @@ static inline int numa_node_id(void)
  * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem().
  */
 DECLARE_PER_CPU(int, _numa_mem_);
+extern int _node_numa_mem_[MAX_NUMNODES];
 
 #ifndef set_numa_mem
 static inline void set_numa_mem(int node)
 {
 	this_cpu_write(_numa_mem_, node);
+	_node_numa_mem_[numa_node_id()] = node;
+}
+#endif
+
+#ifndef node_to_mem_node
+static inline int node_to_mem_node(int node)
+{
+	return _node_numa_mem_[node];
 }
 #endif
 
@@ -146,6 +155,7 @@ static inline int cpu_to_mem(int cpu)
 static inline void set_cpu_numa_mem(int cpu, int node)
 {
 	per_cpu(_numa_mem_, cpu) = node;
+	_node_numa_mem_[cpu_to_node(cpu)] = node;
 }
 #endif
 
@@ -159,6 +169,13 @@ static inline int numa_mem_id(void)
 }
 #endif
 
+#ifndef node_to_mem_node
+static inline int node_to_mem_node(int node)
+{
+	return node;
+}
+#endif
+
 #ifndef cpu_to_mem
 static inline int cpu_to_mem(int cpu)
 {
diff --git a/include/linux/torture.h b/include/linux/torture.h
index 5ca58fcbaf1b..7759fc3c622d 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -51,7 +51,7 @@
 
 /* Definitions for online/offline exerciser. */
 int torture_onoff_init(long ooholdoff, long oointerval);
-char *torture_onoff_stats(char *page);
+void torture_onoff_stats(void);
 bool torture_onoff_failures(void);
 
 /* Low-rider random number generator. */
@@ -77,7 +77,8 @@ int torture_stutter_init(int s);
 /* Initialization and cleanup. */
 bool torture_init_begin(char *ttype, bool v, int *runnable);
 void torture_init_end(void);
-bool torture_cleanup(void);
+bool torture_cleanup_begin(void);
+void torture_cleanup_end(void);
 bool torture_must_stop(void);
 bool torture_must_stop_irq(void);
 void torture_kthread_stopping(char *title);
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index b1293f15f592..e08e21e5f601 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -157,6 +157,12 @@ extern void syscall_unregfunc(void);
  * Make sure the alignment of the structure in the __tracepoints section will
  * not add unwanted padding between the beginning of the section and the
  * structure. Force alignment to the same alignment as the section start.
+ *
+ * When lockdep is enabled, we make sure to always do the RCU portions of
+ * the tracepoint code, regardless of whether tracing is on or we match the
+ * condition.  This lets us find RCU issues triggered with tracepoints even
+ * when this tracepoint is off.  This code has no purpose other than poking
+ * RCU a bit.
  */
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
 	extern struct tracepoint __tracepoint_##name;			\
@@ -167,6 +173,11 @@ extern void syscall_unregfunc(void);
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond),,);			\
+		if (IS_ENABLED(CONFIG_LOCKDEP)) {			\
+			rcu_read_lock_sched_notrace();			\
+			rcu_dereference_sched(__tracepoint_##name.funcs);\
+			rcu_read_unlock_sched_notrace();		\
+		}							\
 	}								\
 	__DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args),		\
 		PARAMS(cond), PARAMS(data_proto), PARAMS(data_args))	\
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 290fbf0b6b8a..9b1581414cd4 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -80,6 +80,9 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
 size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
+size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i);
+size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
+size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov,
 			unsigned long nr_segs, size_t count);
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index b46671e28de2..65261a7244fc 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -78,6 +78,10 @@ bool virtqueue_is_broken(struct virtqueue *vq);
 /**
  * virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
+ * @failed: saved value for CONFIG_S_FAILED bit (for restore)
+ * @config_enabled: configuration change reporting enabled
+ * @config_change_pending: configuration change reported while disabled
+ * @config_lock: protects configuration change reporting
  * @dev: underlying device.
  * @id: the device type identification (used to match it with a driver).
  * @config: the configuration ops for this device.
@@ -88,6 +92,10 @@ bool virtqueue_is_broken(struct virtqueue *vq);
  */
 struct virtio_device {
 	int index;
+	bool failed;
+	bool config_enabled;
+	bool config_change_pending;
+	spinlock_t config_lock;
 	struct device dev;
 	struct virtio_device_id id;
 	const struct virtio_config_ops *config;
@@ -108,6 +116,12 @@ void unregister_virtio_device(struct virtio_device *dev);
 
 void virtio_break_device(struct virtio_device *dev);
 
+void virtio_config_changed(struct virtio_device *dev);
+#ifdef CONFIG_PM_SLEEP
+int virtio_device_freeze(struct virtio_device *dev);
+int virtio_device_restore(struct virtio_device *dev);
+#endif
+
 /**
  * virtio_driver - operations for a virtio I/O driver
  * @driver: underlying device driver (populate name and owner).
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index e8f8f71e843c..7f4ef66873ef 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -109,6 +109,23 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev,
 	return vq;
 }
 
+/**
+ * virtio_device_ready - enable vq use in probe function
+ * @vdev: the device
+ *
+ * Driver must call this to use vqs in the probe function.
+ *
+ * Note: vqs are enabled automatically after probe returns.
+ */
+static inline
+void virtio_device_ready(struct virtio_device *dev)
+{
+	unsigned status = dev->config->get_status(dev);
+
+	BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK);
+	dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK);
+}
+
 static inline
 const char *virtio_bus_name(struct virtio_device *vdev)
 {
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index ced92345c963..730334cdf037 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -72,6 +72,13 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 #endif
+#ifdef CONFIG_MEMORY_BALLOON
+		BALLOON_INFLATE,
+		BALLOON_DEFLATE,
+#ifdef CONFIG_BALLOON_COMPACTION
+		BALLOON_MIGRATE,
+#endif
+#endif
 #ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 		NR_TLB_REMOTE_FLUSH,	/* cpu tried to flush others' tlbs */
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 80115bf88671..e4a8eb9312ea 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -281,9 +281,11 @@ do {									\
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
  *
- * The function returns 0 if the @timeout elapsed, or the remaining
- * jiffies (at least 1) if the @condition evaluated to %true before
- * the @timeout elapsed.
+ * Returns:
+ * 0 if the @condition evaluated to %false after the @timeout elapsed,
+ * 1 if the @condition evaluated to %true after the @timeout elapsed,
+ * or the remaining jiffies (at least 1) if the @condition evaluated
+ * to %true before the @timeout elapsed.
  */
 #define wait_event_timeout(wq, condition, timeout)			\
 ({									\
@@ -364,9 +366,11 @@ do {									\
  * change the result of the wait condition.
  *
  * Returns:
- * 0 if the @timeout elapsed, -%ERESTARTSYS if it was interrupted by
- * a signal, or the remaining jiffies (at least 1) if the @condition
- * evaluated to %true before the @timeout elapsed.
+ * 0 if the @condition evaluated to %false after the @timeout elapsed,
+ * 1 if the @condition evaluated to %true after the @timeout elapsed,
+ * the remaining jiffies (at least 1) if the @condition evaluated
+ * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was
+ * interrupted by a signal.
  */
 #define wait_event_interruptible_timeout(wq, condition, timeout)	\
 ({									\
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index e44d634e7fb7..05c214760977 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -46,6 +46,6 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 			enum zs_mapmode mm);
 void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
 
-u64 zs_get_total_size_bytes(struct zs_pool *pool);
+unsigned long zs_get_total_pages(struct zs_pool *pool);
 
 #endif
diff --git a/include/media/davinci/dm644x_ccdc.h b/include/media/davinci/dm644x_ccdc.h
index 852e96c4bb46..984fb79031de 100644
--- a/include/media/davinci/dm644x_ccdc.h
+++ b/include/media/davinci/dm644x_ccdc.h
@@ -114,7 +114,7 @@ struct ccdc_fault_pixel {
 	/* Number of fault pixel */
 	unsigned short fp_num;
 	/* Address of fault pixel table */
-	unsigned int fpc_table_addr;
+	unsigned long fpc_table_addr;
 };
 
 /* Structure for CCDC configuration parameters for raw capture mode passed
diff --git a/include/media/omap3isp.h b/include/media/omap3isp.h
index c9d06d9f7e6e..398279dd1922 100644
--- a/include/media/omap3isp.h
+++ b/include/media/omap3isp.h
@@ -57,6 +57,8 @@ enum {
  *		0 - Active high, 1 - Active low
  * @vs_pol: Vertical synchronization polarity
  *		0 - Active high, 1 - Active low
+ * @fld_pol: Field signal polarity
+ *		0 - Positive, 1 - Negative
  * @data_pol: Data polarity
  *		0 - Normal, 1 - One's complement
  */
@@ -65,6 +67,7 @@ struct isp_parallel_platform_data {
 	unsigned int clk_pol:1;
 	unsigned int hs_pol:1;
 	unsigned int vs_pol:1;
+	unsigned int fld_pol:1;
 	unsigned int data_pol:1;
 };
 
diff --git a/include/media/rc-map.h b/include/media/rc-map.h
index 80f951890b4c..e7a1514075ec 100644
--- a/include/media/rc-map.h
+++ b/include/media/rc-map.h
@@ -135,6 +135,7 @@ void rc_map_init(void);
 #define RC_MAP_DM1105_NEC                "rc-dm1105-nec"
 #define RC_MAP_DNTV_LIVE_DVBT_PRO        "rc-dntv-live-dvbt-pro"
 #define RC_MAP_DNTV_LIVE_DVB_T           "rc-dntv-live-dvb-t"
+#define RC_MAP_DVBSKY                    "rc-dvbsky"
 #define RC_MAP_EMPTY                     "rc-empty"
 #define RC_MAP_EM_TERRATEC               "rc-em-terratec"
 #define RC_MAP_ENCORE_ENLTV2             "rc-encore-enltv2"
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 2fefcf491aa8..6ef2d01197da 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -356,8 +356,8 @@ struct v4l2_fh;
  * @buf_struct_size: size of the driver-specific buffer structure;
  *		"0" indicates the driver doesn't want to use a custom buffer
  *		structure type, so sizeof(struct vb2_buffer) will is used
- * @timestamp_flags: Timestamp flags; V4L2_BUF_FLAGS_TIMESTAMP_* and
- *		V4L2_BUF_FLAGS_TSTAMP_SRC_*
+ * @timestamp_flags: Timestamp flags; V4L2_BUF_FLAG_TIMESTAMP_* and
+ *		V4L2_BUF_FLAG_TSTAMP_SRC_*
  * @gfp_flags:	additional gfp flags used when allocating the buffers.
  *		Typically this is 0, but it may be e.g. GFP_DMA or __GFP_DMA32
  *		to force the buffer allocation to a specific memory zone.
@@ -366,6 +366,7 @@ struct v4l2_fh;
  *		cannot be started unless at least this number of buffers
  *		have been queued into the driver.
  *
+ * @mmap_lock:	private mutex used when buffers are allocated/freed/mmapped
  * @memory:	current memory type used
  * @bufs:	videobuf buffer structures
  * @num_buffers: number of allocated/used buffers
@@ -402,6 +403,7 @@ struct vb2_queue {
 	u32				min_buffers_needed;
 
 /* private: internal use only */
+	struct mutex			mmap_lock;
 	enum v4l2_memory		memory;
 	struct vb2_buffer		*bufs[VIDEO_MAX_FRAME];
 	unsigned int			num_buffers;
@@ -592,6 +594,15 @@ vb2_plane_size(struct vb2_buffer *vb, unsigned int plane_no)
 	return 0;
 }
 
+/**
+ * vb2_start_streaming_called() - return streaming status of driver
+ * @q:		videobuf queue
+ */
+static inline bool vb2_start_streaming_called(struct vb2_queue *q)
+{
+	return q->start_streaming_called;
+}
+
 /*
  * The following functions are not part of the vb2 core API, but are simple
  * helper functions that you can use in your struct v4l2_file_operations,
diff --git a/include/misc/cxl.h b/include/misc/cxl.h
new file mode 100644
index 000000000000..975cc7861f18
--- /dev/null
+++ b/include/misc/cxl.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _MISC_CXL_H
+#define _MISC_CXL_H
+
+#ifdef CONFIG_CXL_BASE
+
+#define CXL_IRQ_RANGES 4
+
+struct cxl_irq_ranges {
+	irq_hw_number_t offset[CXL_IRQ_RANGES];
+	irq_hw_number_t range[CXL_IRQ_RANGES];
+};
+
+extern atomic_t cxl_use_count;
+
+static inline bool cxl_ctx_in_use(void)
+{
+       return (atomic_read(&cxl_use_count) != 0);
+}
+
+static inline void cxl_ctx_get(void)
+{
+       atomic_inc(&cxl_use_count);
+}
+
+static inline void cxl_ctx_put(void)
+{
+       atomic_dec(&cxl_use_count);
+}
+
+void cxl_slbia(struct mm_struct *mm);
+
+#else /* CONFIG_CXL_BASE */
+
+static inline bool cxl_ctx_in_use(void) { return false; }
+static inline void cxl_slbia(struct mm_struct *mm) {}
+
+#endif /* CONFIG_CXL_BASE */
+
+#endif
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 2f26dfb8450e..1f99a1de0e4f 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -63,7 +63,7 @@ static inline void dst_entries_add(struct dst_ops *dst, int val)
 
 static inline int dst_entries_init(struct dst_ops *dst)
 {
-	return percpu_counter_init(&dst->pcpuc_entries, 0);
+	return percpu_counter_init(&dst->pcpuc_entries, 0, GFP_KERNEL);
 }
 
 static inline void dst_entries_destroy(struct dst_ops *dst)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 65a8855e99fe..8d1765577acc 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -151,7 +151,7 @@ static inline void add_frag_mem_limit(struct inet_frag_queue *q, int i)
 
 static inline void init_frag_mem_limit(struct netns_frags *nf)
 {
-	percpu_counter_init(&nf->mem, 0);
+	percpu_counter_init(&nf->mem, 0, GFP_KERNEL);
 }
 
 static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)
diff --git a/include/net/lib80211.h b/include/net/lib80211.h
index be95b9262801..aab0f427edb5 100644
--- a/include/net/lib80211.h
+++ b/include/net/lib80211.h
@@ -32,11 +32,6 @@
 #include <linux/timer.h>
 #include <linux/seq_file.h>
 
-/* print_ssid() is intended to be used in debug (and possibly error)
- * messages. It should never be used for passing ssid to user space. */
-const char *print_ssid(char *buf, const char *ssid, u8 ssid_len);
-#define DECLARE_SSID_BUF(var) char var[IEEE80211_MAX_SSID_LEN * 4 + 1] __maybe_unused
-
 #define NUM_WEP_KEYS	4
 
 enum {
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 37252f71a380..c8a7db605e03 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -242,7 +242,7 @@ extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct,
 DECLARE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
 static inline struct nf_conn *nf_ct_untracked_get(void)
 {
-	return &__raw_get_cpu_var(nf_conntrack_untracked);
+	return raw_cpu_ptr(&nf_conntrack_untracked);
 }
 void nf_ct_untracked_status_or(unsigned long bits);
 
diff --git a/include/net/snmp.h b/include/net/snmp.h
index 8fd2f498782e..35512ac6dcfb 100644
--- a/include/net/snmp.h
+++ b/include/net/snmp.h
@@ -164,7 +164,7 @@ struct linux_xfrm_mib {
 
 #define SNMP_ADD_STATS64_BH(mib, field, addend) 			\
 	do {								\
-		__typeof__(*mib) *ptr = __this_cpu_ptr(mib);		\
+		__typeof__(*mib) *ptr = raw_cpu_ptr(mib);		\
 		u64_stats_update_begin(&ptr->syncp);			\
 		ptr->mibs[field] += addend;				\
 		u64_stats_update_end(&ptr->syncp);			\
@@ -185,8 +185,8 @@ struct linux_xfrm_mib {
 #define SNMP_INC_STATS64(mib, field) SNMP_ADD_STATS64(mib, field, 1)
 #define SNMP_UPD_PO_STATS64_BH(mib, basefield, addend)			\
 	do {								\
-		__typeof__(*mib) *ptr;					\
-		ptr = __this_cpu_ptr(mib);				\
+		__typeof__(*mib) *ptr;				\
+		ptr = raw_cpu_ptr((mib));				\
 		u64_stats_update_begin(&ptr->syncp);			\
 		ptr->mibs[basefield##PKTS]++;				\
 		ptr->mibs[basefield##OCTETS] += addend;			\
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 47da53c27ffa..79abb9c71772 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -8,6 +8,7 @@
 #include <linux/tracepoint.h>
 #include <linux/edac.h>
 #include <linux/ktime.h>
+#include <linux/pci.h>
 #include <linux/aer.h>
 #include <linux/cper.h>
 
@@ -173,25 +174,34 @@ TRACE_EVENT(mc_event,
  * u8 severity -	error severity 0:NONFATAL 1:FATAL 2:CORRECTED
  */
 
-#define aer_correctable_errors		\
-	{BIT(0),	"Receiver Error"},		\
-	{BIT(6),	"Bad TLP"},			\
-	{BIT(7),	"Bad DLLP"},			\
-	{BIT(8),	"RELAY_NUM Rollover"},		\
-	{BIT(12),	"Replay Timer Timeout"},	\
-	{BIT(13),	"Advisory Non-Fatal"}
-
-#define aer_uncorrectable_errors		\
-	{BIT(4),	"Data Link Protocol"},		\
-	{BIT(12),	"Poisoned TLP"},		\
-	{BIT(13),	"Flow Control Protocol"},	\
-	{BIT(14),	"Completion Timeout"},		\
-	{BIT(15),	"Completer Abort"},		\
-	{BIT(16),	"Unexpected Completion"},	\
-	{BIT(17),	"Receiver Overflow"},		\
-	{BIT(18),	"Malformed TLP"},		\
-	{BIT(19),	"ECRC"},			\
-	{BIT(20),	"Unsupported Request"}
+#define aer_correctable_errors					\
+	{PCI_ERR_COR_RCVR,	"Receiver Error"},		\
+	{PCI_ERR_COR_BAD_TLP,	"Bad TLP"},			\
+	{PCI_ERR_COR_BAD_DLLP,	"Bad DLLP"},			\
+	{PCI_ERR_COR_REP_ROLL,	"RELAY_NUM Rollover"},		\
+	{PCI_ERR_COR_REP_TIMER,	"Replay Timer Timeout"},	\
+	{PCI_ERR_COR_ADV_NFAT,	"Advisory Non-Fatal Error"},	\
+	{PCI_ERR_COR_INTERNAL,	"Corrected Internal Error"},	\
+	{PCI_ERR_COR_LOG_OVER,	"Header Log Overflow"}
+
+#define aer_uncorrectable_errors				\
+	{PCI_ERR_UNC_UND,	"Undefined"},			\
+	{PCI_ERR_UNC_DLP,	"Data Link Protocol Error"},	\
+	{PCI_ERR_UNC_SURPDN,	"Surprise Down Error"},		\
+	{PCI_ERR_UNC_POISON_TLP,"Poisoned TLP"},		\
+	{PCI_ERR_UNC_FCP,	"Flow Control Protocol Error"},	\
+	{PCI_ERR_UNC_COMP_TIME,	"Completion Timeout"},		\
+	{PCI_ERR_UNC_COMP_ABORT,"Completer Abort"},		\
+	{PCI_ERR_UNC_UNX_COMP,	"Unexpected Completion"},	\
+	{PCI_ERR_UNC_RX_OVER,	"Receiver Overflow"},		\
+	{PCI_ERR_UNC_MALF_TLP,	"Malformed TLP"},		\
+	{PCI_ERR_UNC_ECRC,	"ECRC Error"},			\
+	{PCI_ERR_UNC_UNSUP,	"Unsupported Request Error"},	\
+	{PCI_ERR_UNC_ACSV,	"ACS Violation"},		\
+	{PCI_ERR_UNC_INTN,	"Uncorrectable Internal Error"},\
+	{PCI_ERR_UNC_MCBTLP,	"MC Blocked TLP"},		\
+	{PCI_ERR_UNC_ATOMEG,	"AtomicOp Egress Blocked"},	\
+	{PCI_ERR_UNC_TLPPRE,	"TLP Prefix Blocked Error"}
 
 TRACE_EVENT(aer_event,
 	TP_PROTO(const char *dev_name,
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 73f349044941..522a5f27f553 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -10,9 +10,10 @@
 #include <scsi/scsi_device.h>
 
 struct Scsi_Host;
-struct scsi_device;
 struct scsi_driver;
 
+#include <scsi/scsi_device.h>
+
 /*
  * MAX_COMMAND_SIZE is:
  * The longest fixed-length SCSI CDB as per the SCSI standard.
@@ -81,6 +82,7 @@ struct scsi_cmnd {
 
 	unsigned char prot_op;
 	unsigned char prot_type;
+	unsigned char prot_flags;
 
 	unsigned short cmd_len;
 	enum dma_data_direction sc_data_direction;
@@ -252,6 +254,14 @@ static inline unsigned char scsi_get_prot_op(struct scsi_cmnd *scmd)
 	return scmd->prot_op;
 }
 
+enum scsi_prot_flags {
+	SCSI_PROT_TRANSFER_PI		= 1 << 0,
+	SCSI_PROT_GUARD_CHECK		= 1 << 1,
+	SCSI_PROT_REF_CHECK		= 1 << 2,
+	SCSI_PROT_REF_INCREMENT		= 1 << 3,
+	SCSI_PROT_IP_CHECKSUM		= 1 << 4,
+};
+
 /*
  * The controller usually does not know anything about the target it
  * is communicating with.  However, when DIX is enabled the controller
@@ -280,6 +290,17 @@ static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd)
 	return blk_rq_pos(scmd->request);
 }
 
+static inline unsigned int scsi_prot_interval(struct scsi_cmnd *scmd)
+{
+	return scmd->device->sector_size;
+}
+
+static inline u32 scsi_prot_ref_tag(struct scsi_cmnd *scmd)
+{
+	return blk_rq_pos(scmd->request) >>
+		(ilog2(scsi_prot_interval(scmd)) - 9) & 0xffffffff;
+}
+
 static inline unsigned scsi_prot_sg_count(struct scsi_cmnd *cmd)
 {
 	return cmd->prot_sdb ? cmd->prot_sdb->table.nents : 0;
@@ -316,17 +337,12 @@ static inline void set_driver_byte(struct scsi_cmnd *cmd, char status)
 static inline unsigned scsi_transfer_length(struct scsi_cmnd *scmd)
 {
 	unsigned int xfer_len = scsi_out(scmd)->length;
-	unsigned int prot_op = scsi_get_prot_op(scmd);
-	unsigned int sector_size = scmd->device->sector_size;
+	unsigned int prot_interval = scsi_prot_interval(scmd);
 
-	switch (prot_op) {
-	case SCSI_PROT_NORMAL:
-	case SCSI_PROT_WRITE_STRIP:
-	case SCSI_PROT_READ_INSERT:
-		return xfer_len;
-	}
+	if (scmd->prot_flags & SCSI_PROT_TRANSFER_PI)
+		xfer_len += (xfer_len >> ilog2(prot_interval)) * 8;
 
-	return xfer_len + (xfer_len >> ilog2(sector_size)) * 8;
+	return xfer_len;
 }
 
 #endif /* _SCSI_SCSI_CMND_H */
diff --git a/include/sound/atmel-abdac.h b/include/sound/atmel-abdac.h
index edff6a8ba1b5..a8f735d677fa 100644
--- a/include/sound/atmel-abdac.h
+++ b/include/sound/atmel-abdac.h
@@ -10,7 +10,7 @@
 #ifndef __INCLUDE_SOUND_ATMEL_ABDAC_H
 #define __INCLUDE_SOUND_ATMEL_ABDAC_H
 
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 
 /**
  * struct atmel_abdac_pdata - board specific ABDAC configuration
diff --git a/include/sound/atmel-ac97c.h b/include/sound/atmel-ac97c.h
index 00e6c289a936..f2a1cdc37661 100644
--- a/include/sound/atmel-ac97c.h
+++ b/include/sound/atmel-ac97c.h
@@ -10,7 +10,7 @@
 #ifndef __INCLUDE_SOUND_ATMEL_AC97C_H
 #define __INCLUDE_SOUND_ATMEL_AC97C_H
 
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
 
 #define AC97C_CAPTURE	0x01
 #define AC97C_PLAYBACK	0x02
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 6f3e10ca0e32..e862497f7556 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -183,6 +183,7 @@ struct snd_pcm_ops {
 #define SNDRV_PCM_FMTBIT_G723_40_1B	_SNDRV_PCM_FMTBIT(G723_40_1B)
 #define SNDRV_PCM_FMTBIT_DSD_U8		_SNDRV_PCM_FMTBIT(DSD_U8)
 #define SNDRV_PCM_FMTBIT_DSD_U16_LE	_SNDRV_PCM_FMTBIT(DSD_U16_LE)
+#define SNDRV_PCM_FMTBIT_DSD_U32_LE	_SNDRV_PCM_FMTBIT(DSD_U32_LE)
 
 #ifdef SNDRV_LITTLE_ENDIAN
 #define SNDRV_PCM_FMTBIT_S16		SNDRV_PCM_FMTBIT_S16_LE
@@ -365,6 +366,7 @@ struct snd_pcm_runtime {
 
 struct snd_pcm_group {		/* keep linked substreams */
 	spinlock_t lock;
+	struct mutex mutex;
 	struct list_head substreams;
 	int count;
 };
@@ -460,6 +462,7 @@ struct snd_pcm {
 	void (*private_free) (struct snd_pcm *pcm);
 	struct device *dev; /* actual hw device this belongs to */
 	bool internal; /* pcm is for internal use only */
+	bool nonatomic; /* whole PCM operations are in non-atomic context */
 #if defined(CONFIG_SND_PCM_OSS) || defined(CONFIG_SND_PCM_OSS_MODULE)
 	struct snd_pcm_oss oss;
 #endif
@@ -492,8 +495,6 @@ int snd_pcm_notify(struct snd_pcm_notify *notify, int nfree);
  *  Native I/O
  */
 
-extern rwlock_t snd_pcm_link_rwlock;
-
 int snd_pcm_info(struct snd_pcm_substream *substream, struct snd_pcm_info *info);
 int snd_pcm_info_user(struct snd_pcm_substream *substream,
 		      struct snd_pcm_info __user *info);
@@ -537,41 +538,18 @@ static inline int snd_pcm_stream_linked(struct snd_pcm_substream *substream)
 	return substream->group != &substream->self_group;
 }
 
-static inline void snd_pcm_stream_lock(struct snd_pcm_substream *substream)
-{
-	read_lock(&snd_pcm_link_rwlock);
-	spin_lock(&substream->self_group.lock);
-}
-
-static inline void snd_pcm_stream_unlock(struct snd_pcm_substream *substream)
-{
-	spin_unlock(&substream->self_group.lock);
-	read_unlock(&snd_pcm_link_rwlock);
-}
-
-static inline void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream)
-{
-	read_lock_irq(&snd_pcm_link_rwlock);
-	spin_lock(&substream->self_group.lock);
-}
-
-static inline void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream)
-{
-	spin_unlock(&substream->self_group.lock);
-	read_unlock_irq(&snd_pcm_link_rwlock);
-}
-
-#define snd_pcm_stream_lock_irqsave(substream, flags) \
-do { \
-	read_lock_irqsave(&snd_pcm_link_rwlock, (flags)); \
-	spin_lock(&substream->self_group.lock); \
-} while (0)
-
-#define snd_pcm_stream_unlock_irqrestore(substream, flags) \
-do { \
-	spin_unlock(&substream->self_group.lock); \
-	read_unlock_irqrestore(&snd_pcm_link_rwlock, (flags)); \
-} while (0)
+void snd_pcm_stream_lock(struct snd_pcm_substream *substream);
+void snd_pcm_stream_unlock(struct snd_pcm_substream *substream);
+void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream);
+void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream);
+unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream);
+#define snd_pcm_stream_lock_irqsave(substream, flags)		 \
+	do {							 \
+		typecheck(unsigned long, flags);		 \
+		flags = _snd_pcm_stream_lock_irqsave(substream); \
+	} while (0)
+void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream,
+				      unsigned long flags);
 
 #define snd_pcm_group_for_each_entry(s, substream) \
 	list_for_each_entry(s, &substream->group->substreams, link_list)
diff --git a/include/sound/rt5645.h b/include/sound/rt5645.h
index 1de744c242f6..a5352712194b 100644
--- a/include/sound/rt5645.h
+++ b/include/sound/rt5645.h
@@ -20,6 +20,9 @@ struct rt5645_platform_data {
 	/* 0 = IN2N; 1 = GPIO5; 2 = GPIO11 */
 	unsigned int dmic2_data_pin;
 	/* 0 = IN2P; 1 = GPIO6; 2 = GPIO10; 3 = GPIO12 */
+
+	unsigned int hp_det_gpio;
+	bool gpio_hp_det_active_high;
 };
 
 #endif
diff --git a/include/sound/rt5677.h b/include/sound/rt5677.h
index 3da14313bcfc..082670e3a353 100644
--- a/include/sound/rt5677.h
+++ b/include/sound/rt5677.h
@@ -12,10 +12,21 @@
 #ifndef __LINUX_SND_RT5677_H
 #define __LINUX_SND_RT5677_H
 
+enum rt5677_dmic2_clk {
+	RT5677_DMIC_CLK1 = 0,
+	RT5677_DMIC_CLK2 = 1,
+};
+
+
 struct rt5677_platform_data {
-	/* IN1 IN2 can optionally be differential */
+	/* IN1/IN2/LOUT1/LOUT2/LOUT3 can optionally be differential */
 	bool in1_diff;
 	bool in2_diff;
+	bool lout1_diff;
+	bool lout2_diff;
+	bool lout3_diff;
+	/* DMIC2 clock source selection */
+	enum rt5677_dmic2_clk dmic2_clk_pin;
 };
 
 #endif
diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index aac04ff84eea..3a4d7da67b8d 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -432,6 +432,7 @@ int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
 int snd_soc_dapm_ignore_suspend(struct snd_soc_dapm_context *dapm,
 				const char *pin);
 void snd_soc_dapm_auto_nc_pins(struct snd_soc_card *card);
+unsigned int dapm_kcontrol_get_value(const struct snd_kcontrol *kcontrol);
 
 /* Mostly internal - should not normally be used */
 void dapm_mark_io_dirty(struct snd_soc_dapm_context *dapm);
@@ -587,13 +588,13 @@ struct snd_soc_dapm_context {
 	enum snd_soc_bias_level suspend_bias_level;
 	struct delayed_work delayed_work;
 	unsigned int idle_bias_off:1; /* Use BIAS_OFF instead of STANDBY */
-
+	/* Go to BIAS_OFF in suspend if the DAPM context is idle */
+	unsigned int suspend_bias_off:1;
 	void (*seq_notifier)(struct snd_soc_dapm_context *,
 			     enum snd_soc_dapm_type, int);
 
 	struct device *dev; /* from parent - for debug */
 	struct snd_soc_component *component; /* parent component */
-	struct snd_soc_codec *codec; /* parent codec */
 	struct snd_soc_card *card; /* parent card */
 
 	/* used during DAPM updates */
diff --git a/include/sound/soc.h b/include/sound/soc.h
index c83a334dd00f..7ba7130037a0 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -690,6 +690,17 @@ struct snd_soc_compr_ops {
 struct snd_soc_component_driver {
 	const char *name;
 
+	/* Default control and setup, added after probe() is run */
+	const struct snd_kcontrol_new *controls;
+	unsigned int num_controls;
+	const struct snd_soc_dapm_widget *dapm_widgets;
+	unsigned int num_dapm_widgets;
+	const struct snd_soc_dapm_route *dapm_routes;
+	unsigned int num_dapm_routes;
+
+	int (*probe)(struct snd_soc_component *);
+	void (*remove)(struct snd_soc_component *);
+
 	/* DT */
 	int (*of_xlate_dai_name)(struct snd_soc_component *component,
 				 struct of_phandle_args *args,
@@ -697,6 +708,10 @@ struct snd_soc_component_driver {
 	void (*seq_notifier)(struct snd_soc_component *, enum snd_soc_dapm_type,
 		int subseq);
 	int (*stream_event)(struct snd_soc_component *, int event);
+
+	/* probe ordering - for components with runtime dependencies */
+	int probe_order;
+	int remove_order;
 };
 
 struct snd_soc_component {
@@ -710,6 +725,7 @@ struct snd_soc_component {
 
 	unsigned int ignore_pmdown_time:1; /* pmdown_time is ignored at stop */
 	unsigned int registered_as_component:1;
+	unsigned int probed:1;
 
 	struct list_head list;
 
@@ -728,9 +744,35 @@ struct snd_soc_component {
 
 	struct mutex io_mutex;
 
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *debugfs_root;
+#endif
+
+	/*
+	* DO NOT use any of the fields below in drivers, they are temporary and
+	* are going to be removed again soon. If you use them in driver code the
+	* driver will be marked as BROKEN when these fields are removed.
+	*/
+
 	/* Don't use these, use snd_soc_component_get_dapm() */
 	struct snd_soc_dapm_context dapm;
 	struct snd_soc_dapm_context *dapm_ptr;
+
+	const struct snd_kcontrol_new *controls;
+	unsigned int num_controls;
+	const struct snd_soc_dapm_widget *dapm_widgets;
+	unsigned int num_dapm_widgets;
+	const struct snd_soc_dapm_route *dapm_routes;
+	unsigned int num_dapm_routes;
+	struct snd_soc_codec *codec;
+
+	int (*probe)(struct snd_soc_component *);
+	void (*remove)(struct snd_soc_component *);
+
+#ifdef CONFIG_DEBUG_FS
+	void (*init_debugfs)(struct snd_soc_component *component);
+	const char *debugfs_prefix;
+#endif
 };
 
 /* SoC Audio Codec device */
@@ -746,11 +788,9 @@ struct snd_soc_codec {
 	struct snd_ac97 *ac97;  /* for ad-hoc ac97 devices */
 	unsigned int cache_bypass:1; /* Suppress access to the cache */
 	unsigned int suspended:1; /* Codec is in suspend PM state */
-	unsigned int probed:1; /* Codec has been probed */
 	unsigned int ac97_registered:1; /* Codec has been AC97 registered */
 	unsigned int ac97_created:1; /* Codec has been created by SoC */
 	unsigned int cache_init:1; /* codec cache has been initialized */
-	u32 cache_only;  /* Suppress writes to hardware */
 	u32 cache_sync; /* Cache needs to be synced to hardware */
 
 	/* codec IO */
@@ -766,7 +806,6 @@ struct snd_soc_codec {
 	struct snd_soc_dapm_context dapm;
 
 #ifdef CONFIG_DEBUG_FS
-	struct dentry *debugfs_codec_root;
 	struct dentry *debugfs_reg;
 #endif
 };
@@ -808,15 +847,12 @@ struct snd_soc_codec_driver {
 	int (*set_bias_level)(struct snd_soc_codec *,
 			      enum snd_soc_bias_level level);
 	bool idle_bias_off;
+	bool suspend_bias_off;
 
 	void (*seq_notifier)(struct snd_soc_dapm_context *,
 			     enum snd_soc_dapm_type, int);
 
 	bool ignore_pmdown_time;  /* Doesn't benefit from pmdown delay */
-
-	/* probe ordering - for components with runtime dependencies */
-	int probe_order;
-	int remove_order;
 };
 
 /* SoC platform interface */
@@ -832,14 +868,6 @@ struct snd_soc_platform_driver {
 	int (*pcm_new)(struct snd_soc_pcm_runtime *);
 	void (*pcm_free)(struct snd_pcm *);
 
-	/* Default control and setup, added after probe() is run */
-	const struct snd_kcontrol_new *controls;
-	int num_controls;
-	const struct snd_soc_dapm_widget *dapm_widgets;
-	int num_dapm_widgets;
-	const struct snd_soc_dapm_route *dapm_routes;
-	int num_dapm_routes;
-
 	/*
 	 * For platform caused delay reporting.
 	 * Optional.
@@ -853,13 +881,6 @@ struct snd_soc_platform_driver {
 	/* platform stream compress ops */
 	const struct snd_compr_ops *compr_ops;
 
-	/* probe ordering - for components with runtime dependencies */
-	int probe_order;
-	int remove_order;
-
-	/* platform IO - used for platform DAPM */
-	unsigned int (*read)(struct snd_soc_platform *, unsigned int);
-	int (*write)(struct snd_soc_platform *, unsigned int, unsigned int);
 	int (*bespoke_trigger)(struct snd_pcm_substream *, int);
 };
 
@@ -874,15 +895,10 @@ struct snd_soc_platform {
 	const struct snd_soc_platform_driver *driver;
 
 	unsigned int suspended:1; /* platform is suspended */
-	unsigned int probed:1;
 
 	struct list_head list;
 
 	struct snd_soc_component component;
-
-#ifdef CONFIG_DEBUG_FS
-	struct dentry *debugfs_platform_root;
-#endif
 };
 
 struct snd_soc_dai_link {
@@ -897,7 +913,7 @@ struct snd_soc_dai_link {
 	 * only for codec to codec links, or systems using device tree.
 	 */
 	const char *cpu_name;
-	const struct device_node *cpu_of_node;
+	struct device_node *cpu_of_node;
 	/*
 	 * You MAY specify the DAI name of the CPU DAI. If this information is
 	 * omitted, the CPU-side DAI is matched using .cpu_name/.cpu_of_node
@@ -909,7 +925,7 @@ struct snd_soc_dai_link {
 	 * DT/OF node, but not both.
 	 */
 	const char *codec_name;
-	const struct device_node *codec_of_node;
+	struct device_node *codec_of_node;
 	/* You MUST specify the DAI name within the codec */
 	const char *codec_dai_name;
 
@@ -922,7 +938,7 @@ struct snd_soc_dai_link {
 	 * do not need a platform.
 	 */
 	const char *platform_name;
-	const struct device_node *platform_of_node;
+	struct device_node *platform_of_node;
 	int be_id;	/* optional ID for machine driver BE identification */
 
 	const struct snd_soc_pcm_stream *params;
@@ -994,7 +1010,7 @@ struct snd_soc_aux_dev {
 	const struct device_node *codec_of_node;
 
 	/* codec/machine specific init - e.g. add machine controls */
-	int (*init)(struct snd_soc_dapm_context *dapm);
+	int (*init)(struct snd_soc_component *component);
 };
 
 /* SoC card */
@@ -1112,6 +1128,7 @@ struct snd_soc_pcm_runtime {
 	struct snd_soc_platform *platform;
 	struct snd_soc_dai *codec_dai;
 	struct snd_soc_dai *cpu_dai;
+	struct snd_soc_component *component; /* Only valid for AUX dev rtds */
 
 	struct snd_soc_dai **codec_dais;
 	unsigned int num_codecs;
@@ -1260,9 +1277,6 @@ void snd_soc_component_async_complete(struct snd_soc_component *component);
 int snd_soc_component_test_bits(struct snd_soc_component *component,
 	unsigned int reg, unsigned int mask, unsigned int value);
 
-int snd_soc_component_init_io(struct snd_soc_component *component,
-	struct regmap *regmap);
-
 /* device driver data */
 
 static inline void snd_soc_card_set_drvdata(struct snd_soc_card *card,
@@ -1276,26 +1290,37 @@ static inline void *snd_soc_card_get_drvdata(struct snd_soc_card *card)
 	return card->drvdata;
 }
 
+static inline void snd_soc_component_set_drvdata(struct snd_soc_component *c,
+		void *data)
+{
+	dev_set_drvdata(c->dev, data);
+}
+
+static inline void *snd_soc_component_get_drvdata(struct snd_soc_component *c)
+{
+	return dev_get_drvdata(c->dev);
+}
+
 static inline void snd_soc_codec_set_drvdata(struct snd_soc_codec *codec,
 		void *data)
 {
-	dev_set_drvdata(codec->dev, data);
+	snd_soc_component_set_drvdata(&codec->component, data);
 }
 
 static inline void *snd_soc_codec_get_drvdata(struct snd_soc_codec *codec)
 {
-	return dev_get_drvdata(codec->dev);
+	return snd_soc_component_get_drvdata(&codec->component);
 }
 
 static inline void snd_soc_platform_set_drvdata(struct snd_soc_platform *platform,
 		void *data)
 {
-	dev_set_drvdata(platform->dev, data);
+	snd_soc_component_set_drvdata(&platform->component, data);
 }
 
 static inline void *snd_soc_platform_get_drvdata(struct snd_soc_platform *platform)
 {
-	return dev_get_drvdata(platform->dev);
+	return snd_soc_component_get_drvdata(&platform->component);
 }
 
 static inline void snd_soc_pcm_set_drvdata(struct snd_soc_pcm_runtime *rtd,
diff --git a/include/sound/vx_core.h b/include/sound/vx_core.h
index f634f8f85db5..cae9c9d4ef22 100644
--- a/include/sound/vx_core.h
+++ b/include/sound/vx_core.h
@@ -80,8 +80,6 @@ struct vx_pipe {
 
 	unsigned int references;     /* an output pipe may be used for monitoring and/or playback */
 	struct vx_pipe *monitoring_pipe;  /* pointer to the monitoring pipe (capture pipe only)*/
-
-	struct tasklet_struct start_tq;
 };
 
 struct vx_core;
@@ -165,9 +163,7 @@ struct vx_core {
 	struct snd_vx_hardware *hw;
 	struct snd_vx_ops *ops;
 
-	spinlock_t lock;
-	spinlock_t irq_lock;
-	struct tasklet_struct tq;
+	struct mutex lock;
 
 	unsigned int chip_status;
 	unsigned int pcm_running;
@@ -223,6 +219,7 @@ void snd_vx_free_firmware(struct vx_core *chip);
  * interrupt handler; exported for pcmcia
  */
 irqreturn_t snd_vx_irq_handler(int irq, void *dev);
+irqreturn_t snd_vx_threaded_irq_handler(int irq, void *dev);
 
 /*
  * lowlevel functions
diff --git a/include/trace/events/asoc.h b/include/trace/events/asoc.h
index 0194a641e4e2..b04ee7e5a466 100644
--- a/include/trace/events/asoc.h
+++ b/include/trace/events/asoc.h
@@ -175,7 +175,7 @@ TRACE_EVENT(snd_soc_dapm_output_path,
 		__entry->path_sink = (long)path->sink;
 	),
 
-	TP_printk("%c%s -> %s -> %s\n",
+	TP_printk("%c%s -> %s -> %s",
 		(int) __entry->path_sink &&
 		(int) __entry->path_connect ? '*' : ' ',
 		__get_str(wname), __get_str(pname), __get_str(psname))
@@ -204,7 +204,7 @@ TRACE_EVENT(snd_soc_dapm_input_path,
 		__entry->path_source = (long)path->source;
 	),
 
-	TP_printk("%c%s <- %s <- %s\n",
+	TP_printk("%c%s <- %s <- %s",
 		(int) __entry->path_source &&
 		(int) __entry->path_connect ? '*' : ' ',
 		__get_str(wname), __get_str(pname), __get_str(psname))
@@ -226,7 +226,7 @@ TRACE_EVENT(snd_soc_dapm_connected,
 		__entry->stream = stream;
 	),
 
-	TP_printk("%s: found %d paths\n",
+	TP_printk("%s: found %d paths",
 		__entry->stream ? "capture" : "playback", __entry->paths)
 );
 
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 4ee4e30d26d9..1faecea101f3 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -23,6 +23,7 @@ struct map_lookup;
 struct extent_buffer;
 struct btrfs_work;
 struct __btrfs_workqueue;
+struct btrfs_qgroup_operation;
 
 #define show_ref_type(type)						\
 	__print_symbolic(type,						\
@@ -157,12 +158,13 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
 
 #define show_map_flags(flag)						\
 	__print_flags(flag, "|",					\
-		{ EXTENT_FLAG_PINNED, 		"PINNED" 	},	\
-		{ EXTENT_FLAG_COMPRESSED, 	"COMPRESSED" 	},	\
-		{ EXTENT_FLAG_VACANCY, 		"VACANCY" 	},	\
-		{ EXTENT_FLAG_PREALLOC, 	"PREALLOC" 	},	\
-		{ EXTENT_FLAG_LOGGING,	 	"LOGGING" 	},	\
-		{ EXTENT_FLAG_FILLING,	 	"FILLING" 	})
+		{ (1 << EXTENT_FLAG_PINNED), 		"PINNED" 	},\
+		{ (1 << EXTENT_FLAG_COMPRESSED), 	"COMPRESSED" 	},\
+		{ (1 << EXTENT_FLAG_VACANCY), 		"VACANCY" 	},\
+		{ (1 << EXTENT_FLAG_PREALLOC), 		"PREALLOC" 	},\
+		{ (1 << EXTENT_FLAG_LOGGING),	 	"LOGGING" 	},\
+		{ (1 << EXTENT_FLAG_FILLING),	 	"FILLING" 	},\
+		{ (1 << EXTENT_FLAG_FS_MAPPING),	"FS_MAPPING"	})
 
 TRACE_EVENT_CONDITION(btrfs_get_extent,
 
@@ -996,6 +998,7 @@ DECLARE_EVENT_CLASS(btrfs__work,
 		__field(	void *,	func			)
 		__field(	void *,	ordered_func		)
 		__field(	void *,	ordered_free		)
+		__field(	void *,	normal_work		)
 	),
 
 	TP_fast_assign(
@@ -1004,11 +1007,13 @@ DECLARE_EVENT_CLASS(btrfs__work,
 		__entry->func		= work->func;
 		__entry->ordered_func	= work->ordered_func;
 		__entry->ordered_free	= work->ordered_free;
+		__entry->normal_work	= &work->normal_work;
 	),
 
-	TP_printk("work=%p, wq=%p, func=%p, ordered_func=%p, ordered_free=%p",
-		  __entry->work, __entry->wq, __entry->func,
-		  __entry->ordered_func, __entry->ordered_free)
+	TP_printk("work=%p (normal_work=%p), wq=%p, func=%pf, ordered_func=%p,"
+		  " ordered_free=%p",
+		  __entry->work, __entry->normal_work, __entry->wq,
+		   __entry->func, __entry->ordered_func, __entry->ordered_free)
 );
 
 /* For situiations that the work is freed */
@@ -1043,13 +1048,6 @@ DEFINE_EVENT(btrfs__work, btrfs_work_sched,
 	TP_ARGS(work)
 );
 
-DEFINE_EVENT(btrfs__work, btrfs_normal_work_done,
-
-	TP_PROTO(struct btrfs_work *work),
-
-	TP_ARGS(work)
-);
-
 DEFINE_EVENT(btrfs__work__done, btrfs_all_work_done,
 
 	TP_PROTO(struct btrfs_work *work),
@@ -1119,6 +1117,61 @@ DEFINE_EVENT(btrfs__workqueue_done, btrfs_workqueue_destroy,
 	TP_ARGS(wq)
 );
 
+#define show_oper_type(type)						\
+	__print_symbolic(type,						\
+		{ BTRFS_QGROUP_OPER_ADD_EXCL, 	"OPER_ADD_EXCL" },	\
+		{ BTRFS_QGROUP_OPER_ADD_SHARED, "OPER_ADD_SHARED" },	\
+		{ BTRFS_QGROUP_OPER_SUB_EXCL, 	"OPER_SUB_EXCL" },	\
+		{ BTRFS_QGROUP_OPER_SUB_SHARED,	"OPER_SUB_SHARED" })
+
+DECLARE_EVENT_CLASS(btrfs_qgroup_oper,
+
+	TP_PROTO(struct btrfs_qgroup_operation *oper),
+
+	TP_ARGS(oper),
+
+	TP_STRUCT__entry(
+		__field(	u64,  ref_root		)
+		__field(	u64,  bytenr		)
+		__field(	u64,  num_bytes		)
+		__field(	u64,  seq		)
+		__field(	int,  type		)
+		__field(	u64,  elem_seq		)
+	),
+
+	TP_fast_assign(
+		__entry->ref_root	= oper->ref_root;
+		__entry->bytenr		= oper->bytenr,
+		__entry->num_bytes	= oper->num_bytes;
+		__entry->seq 		= oper->seq;
+		__entry->type		= oper->type;
+		__entry->elem_seq	= oper->elem.seq;
+	),
+
+	TP_printk("ref_root = %llu, bytenr = %llu, num_bytes = %llu, "
+		  "seq = %llu, elem.seq = %llu, type = %s",
+		  (unsigned long long)__entry->ref_root,
+		  (unsigned long long)__entry->bytenr,
+		  (unsigned long long)__entry->num_bytes,
+		  (unsigned long long)__entry->seq,
+		  (unsigned long long)__entry->elem_seq,
+		  show_oper_type(__entry->type))
+);
+
+DEFINE_EVENT(btrfs_qgroup_oper, btrfs_qgroup_account,
+
+	TP_PROTO(struct btrfs_qgroup_operation *oper),
+
+	TP_ARGS(oper)
+);
+
+DEFINE_EVENT(btrfs_qgroup_oper, btrfs_qgroup_record_ref,
+
+	TP_PROTO(struct btrfs_qgroup_operation *oper),
+
+	TP_ARGS(oper)
+);
+
 #endif /* _TRACE_BTRFS_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index 59d11c22f076..a0d008070962 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -53,15 +53,15 @@ DECLARE_EVENT_CLASS(filelock_lease,
 	),
 
 	TP_fast_assign(
-		__entry->fl = fl;
+		__entry->fl = fl ? fl : NULL;
 		__entry->s_dev = inode->i_sb->s_dev;
 		__entry->i_ino = inode->i_ino;
-		__entry->fl_next = fl->fl_next;
-		__entry->fl_owner = fl->fl_owner;
-		__entry->fl_flags = fl->fl_flags;
-		__entry->fl_type = fl->fl_type;
-		__entry->fl_break_time = fl->fl_break_time;
-		__entry->fl_downgrade_time = fl->fl_downgrade_time;
+		__entry->fl_next = fl ? fl->fl_next : NULL;
+		__entry->fl_owner = fl ? fl->fl_owner : NULL;
+		__entry->fl_flags = fl ? fl->fl_flags : 0;
+		__entry->fl_type = fl ? fl->fl_type : 0;
+		__entry->fl_break_time = fl ? fl->fl_break_time : 0;
+		__entry->fl_downgrade_time = fl ? fl->fl_downgrade_time : 0;
 	),
 
 	TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_next=0x%p fl_owner=0x%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu",
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index aca382266411..9b56f37148cf 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -180,9 +180,12 @@ TRACE_EVENT(rcu_grace_period_init,
  * argument is a string as follows:
  *
  *	"WakeEmpty": Wake rcuo kthread, first CB to empty list.
+ *	"WakeEmptyIsDeferred": Wake rcuo kthread later, first CB to empty list.
  *	"WakeOvf": Wake rcuo kthread, CB list is huge.
+ *	"WakeOvfIsDeferred": Wake rcuo kthread later, CB list is huge.
  *	"WakeNot": Don't wake rcuo kthread.
  *	"WakeNotPoll": Don't wake rcuo kthread because it is polling.
+ *	"DeferredWake": Carried out the "IsDeferred" wakeup.
  *	"Poll": Start of new polling cycle for rcu_nocb_poll.
  *	"Sleep": Sleep waiting for CBs for !rcu_nocb_poll.
  *	"WokeEmpty": rcuo kthread woke to find empty list.
diff --git a/include/uapi/Kbuild b/include/uapi/Kbuild
index 81d2106287fe..245aa6e05e6a 100644
--- a/include/uapi/Kbuild
+++ b/include/uapi/Kbuild
@@ -12,3 +12,4 @@ header-y += video/
 header-y += drm/
 header-y += xen/
 header-y += scsi/
+header-y += misc/
diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h
index d5844122ff32..5575ed1598bd 100644
--- a/include/uapi/drm/exynos_drm.h
+++ b/include/uapi/drm/exynos_drm.h
@@ -33,38 +33,6 @@ struct drm_exynos_gem_create {
 };
 
 /**
- * A structure for getting buffer offset.
- *
- * @handle: a pointer to gem object created.
- * @pad: just padding to be 64-bit aligned.
- * @offset: relatived offset value of the memory region allocated.
- *	- this value should be set by user.
- */
-struct drm_exynos_gem_map_off {
-	unsigned int handle;
-	unsigned int pad;
-	uint64_t offset;
-};
-
-/**
- * A structure for mapping buffer.
- *
- * @handle: a handle to gem object created.
- * @pad: just padding to be 64-bit aligned.
- * @size: memory size to be mapped.
- * @mapped: having user virtual address mmaped.
- *	- this variable would be filled by exynos gem module
- *	of kernel side with user virtual address which is allocated
- *	by do_mmap().
- */
-struct drm_exynos_gem_mmap {
-	unsigned int handle;
-	unsigned int pad;
-	uint64_t size;
-	uint64_t mapped;
-};
-
-/**
  * A structure to gem information.
  *
  * @handle: a handle to gem object created.
@@ -316,8 +284,6 @@ struct drm_exynos_ipp_cmd_ctrl {
 };
 
 #define DRM_EXYNOS_GEM_CREATE		0x00
-#define DRM_EXYNOS_GEM_MAP_OFFSET	0x01
-#define DRM_EXYNOS_GEM_MMAP		0x02
 /* Reserved 0x03 ~ 0x05 for exynos specific gem ioctl */
 #define DRM_EXYNOS_GEM_GET		0x04
 #define DRM_EXYNOS_VIDI_CONNECTION	0x07
@@ -336,12 +302,6 @@ struct drm_exynos_ipp_cmd_ctrl {
 #define DRM_IOCTL_EXYNOS_GEM_CREATE		DRM_IOWR(DRM_COMMAND_BASE + \
 		DRM_EXYNOS_GEM_CREATE, struct drm_exynos_gem_create)
 
-#define DRM_IOCTL_EXYNOS_GEM_MAP_OFFSET	DRM_IOWR(DRM_COMMAND_BASE + \
-		DRM_EXYNOS_GEM_MAP_OFFSET, struct drm_exynos_gem_map_off)
-
-#define DRM_IOCTL_EXYNOS_GEM_MMAP	DRM_IOWR(DRM_COMMAND_BASE + \
-		DRM_EXYNOS_GEM_MMAP, struct drm_exynos_gem_mmap)
-
 #define DRM_IOCTL_EXYNOS_GEM_GET	DRM_IOWR(DRM_COMMAND_BASE + \
 		DRM_EXYNOS_GEM_GET,	struct drm_exynos_gem_info)
 
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index fea6099608ef..50d0fb41a3bf 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -511,6 +511,7 @@ typedef struct {
 #define DRM_RADEON_GEM_BUSY		0x2a
 #define DRM_RADEON_GEM_VA		0x2b
 #define DRM_RADEON_GEM_OP		0x2c
+#define DRM_RADEON_GEM_USERPTR		0x2d
 
 #define DRM_IOCTL_RADEON_CP_INIT    DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_CP_INIT, drm_radeon_init_t)
 #define DRM_IOCTL_RADEON_CP_START   DRM_IO(  DRM_COMMAND_BASE + DRM_RADEON_CP_START)
@@ -554,6 +555,7 @@ typedef struct {
 #define DRM_IOCTL_RADEON_GEM_BUSY	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_BUSY, struct drm_radeon_gem_busy)
 #define DRM_IOCTL_RADEON_GEM_VA		DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_VA, struct drm_radeon_gem_va)
 #define DRM_IOCTL_RADEON_GEM_OP		DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_OP, struct drm_radeon_gem_op)
+#define DRM_IOCTL_RADEON_GEM_USERPTR	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_USERPTR, struct drm_radeon_gem_userptr)
 
 typedef struct drm_radeon_init {
 	enum {
@@ -799,6 +801,10 @@ struct drm_radeon_gem_info {
 #define RADEON_GEM_NO_BACKING_STORE	(1 << 0)
 #define RADEON_GEM_GTT_UC		(1 << 1)
 #define RADEON_GEM_GTT_WC		(1 << 2)
+/* BO is expected to be accessed by the CPU */
+#define RADEON_GEM_CPU_ACCESS		(1 << 3)
+/* CPU access is not expected to work for this BO */
+#define RADEON_GEM_NO_CPU_ACCESS	(1 << 4)
 
 struct drm_radeon_gem_create {
 	uint64_t	size;
@@ -808,6 +814,23 @@ struct drm_radeon_gem_create {
 	uint32_t	flags;
 };
 
+/*
+ * This is not a reliable API and you should expect it to fail for any
+ * number of reasons and have fallback path that do not use userptr to
+ * perform any operation.
+ */
+#define RADEON_GEM_USERPTR_READONLY	(1 << 0)
+#define RADEON_GEM_USERPTR_ANONONLY	(1 << 1)
+#define RADEON_GEM_USERPTR_VALIDATE	(1 << 2)
+#define RADEON_GEM_USERPTR_REGISTER	(1 << 3)
+
+struct drm_radeon_gem_userptr {
+	uint64_t		addr;
+	uint64_t		size;
+	uint32_t		flags;
+	uint32_t		handle;
+};
+
 #define RADEON_TILING_MACRO				0x1
 #define RADEON_TILING_MICRO				0x2
 #define RADEON_TILING_SWAP_16BIT			0x4
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 4fc66f6b12ce..c472bedbe38e 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -29,7 +29,7 @@
 #define __VMWGFX_DRM_H__
 
 #ifndef __KERNEL__
-#include <drm.h>
+#include <drm/drm.h>
 #endif
 
 #define DRM_VMW_MAX_SURFACE_FACES 6
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 1115d68b150f..6cad97485bad 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -356,6 +356,7 @@ header-y += serio.h
 header-y += shm.h
 header-y += signal.h
 header-y += signalfd.h
+header-y += smiapp.h
 header-y += snmp.h
 header-y += sock_diag.h
 header-y += socket.h
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index c8a4302093a3..3315ab21f728 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	27
+#define DM_VERSION_MINOR	28
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2013-10-30)"
+#define DM_VERSION_EXTRA	"-ioctl (2014-09-17)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index ef6103bf1f9b..ea9bf2561b9e 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -391,6 +391,8 @@ typedef struct elf64_shdr {
 #define NT_S390_LAST_BREAK	0x306	/* s390 breaking event address */
 #define NT_S390_SYSTEM_CALL	0x307	/* s390 system call restart data */
 #define NT_S390_TDB	0x308		/* s390 transaction diagnostic block */
+#define NT_S390_VXRS_LOW	0x309	/* s390 vector registers 0-15 upper half */
+#define NT_S390_VXRS_HIGH	0x30a	/* s390 vector registers 16-31 */
 #define NT_ARM_VFP	0x400		/* ARM VFP/NEON registers */
 #define NT_ARM_TLS	0x401		/* ARM TLS register */
 #define NT_ARM_HW_BREAK	0x402		/* ARM hardware breakpoint registers */
diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h
index 5116a0e48172..2f96d233c980 100644
--- a/include/uapi/linux/kernel-page-flags.h
+++ b/include/uapi/linux/kernel-page-flags.h
@@ -31,6 +31,7 @@
 
 #define KPF_KSM			21
 #define KPF_THP			22
+#define KPF_BALLOON		23
 
 
 #endif /* _UAPILINUX_KERNEL_PAGE_FLAGS_H */
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 30db069bce62..4a1d0cc38ff2 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -552,6 +552,7 @@
 #define  PCI_EXP_RTCTL_PMEIE	0x0008	/* PME Interrupt Enable */
 #define  PCI_EXP_RTCTL_CRSSVE	0x0010	/* CRS Software Visibility Enable */
 #define PCI_EXP_RTCAP		30	/* Root Capabilities */
+#define  PCI_EXP_RTCAP_CRSVIS	0x0001	/* CRS Software Visibility capability */
 #define PCI_EXP_RTSTA		32	/* Root Status */
 #define PCI_EXP_RTSTA_PME	0x00010000 /* PME status */
 #define PCI_EXP_RTSTA_PENDING	0x00020000 /* PME pending */
@@ -630,7 +631,7 @@
 
 /* Advanced Error Reporting */
 #define PCI_ERR_UNCOR_STATUS	4	/* Uncorrectable Error Status */
-#define  PCI_ERR_UNC_TRAIN	0x00000001	/* Training */
+#define  PCI_ERR_UNC_UND	0x00000001	/* Undefined */
 #define  PCI_ERR_UNC_DLP	0x00000010	/* Data Link Protocol */
 #define  PCI_ERR_UNC_SURPDN	0x00000020	/* Surprise Down */
 #define  PCI_ERR_UNC_POISON_TLP	0x00001000	/* Poisoned TLP */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 58afc04c107e..513df75d0fc9 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_PRCTL_H
 #define _LINUX_PRCTL_H
 
+#include <linux/types.h>
+
 /* Values to pass as first argument to prctl() */
 
 #define PR_SET_PDEATHSIG  1  /* Second arg is a signal */
@@ -119,6 +121,31 @@
 # define PR_SET_MM_ENV_END		11
 # define PR_SET_MM_AUXV			12
 # define PR_SET_MM_EXE_FILE		13
+# define PR_SET_MM_MAP			14
+# define PR_SET_MM_MAP_SIZE		15
+
+/*
+ * This structure provides new memory descriptor
+ * map which mostly modifies /proc/pid/stat[m]
+ * output for a task. This mostly done in a
+ * sake of checkpoint/restore functionality.
+ */
+struct prctl_mm_map {
+	__u64	start_code;		/* code section bounds */
+	__u64	end_code;
+	__u64	start_data;		/* data section bounds */
+	__u64	end_data;
+	__u64	start_brk;		/* heap for brk() syscall */
+	__u64	brk;
+	__u64	start_stack;		/* stack starts at */
+	__u64	arg_start;		/* command line arguments bounds */
+	__u64	arg_end;
+	__u64	env_start;		/* environment variables bounds */
+	__u64	env_end;
+	__u64	*auxv;			/* auxiliary vector */
+	__u32	auxv_size;		/* vector size */
+	__u32	exe_fd;			/* /proc/$pid/exe link file */
+};
 
 /*
  * Set specific pid that is allowed to ptrace the current task.
diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h
index 4133e744e4e6..74e7c60c4716 100644
--- a/include/uapi/linux/raid/md_u.h
+++ b/include/uapi/linux/raid/md_u.h
@@ -39,7 +39,6 @@
 #define RAID_VERSION		_IOR (MD_MAJOR, 0x10, mdu_version_t)
 #define GET_ARRAY_INFO		_IOR (MD_MAJOR, 0x11, mdu_array_info_t)
 #define GET_DISK_INFO		_IOR (MD_MAJOR, 0x12, mdu_disk_info_t)
-#define PRINT_RAID_DEBUG	_IO (MD_MAJOR, 0x13)
 #define RAID_AUTORUN		_IO (MD_MAJOR, 0x14)
 #define GET_BITMAP_FILE		_IOR (MD_MAJOR, 0x15, mdu_bitmap_file_t)
 
diff --git a/include/uapi/linux/smiapp.h b/include/uapi/linux/smiapp.h
new file mode 100644
index 000000000000..53938f4412ee
--- /dev/null
+++ b/include/uapi/linux/smiapp.h
@@ -0,0 +1,29 @@
+/*
+ * include/uapi/linux/smiapp.h
+ *
+ * Generic driver for SMIA/SMIA++ compliant camera modules
+ *
+ * Copyright (C) 2014 Intel Corporation
+ * Contact: Sakari Ailus <sakari.ailus@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ */
+
+#ifndef __UAPI_LINUX_SMIAPP_H_
+#define __UAPI_LINUX_SMIAPP_H_
+
+#define V4L2_SMIAPP_TEST_PATTERN_MODE_DISABLED			0
+#define V4L2_SMIAPP_TEST_PATTERN_MODE_SOLID_COLOUR		1
+#define V4L2_SMIAPP_TEST_PATTERN_MODE_COLOUR_BARS		2
+#define V4L2_SMIAPP_TEST_PATTERN_MODE_COLOUR_BARS_GREY		3
+#define V4L2_SMIAPP_TEST_PATTERN_MODE_PN9			4
+
+#endif /* __UAPI_LINUX_SMIAPP_H_ */
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index e946e43fb8d5..661f119a51b8 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -746,6 +746,8 @@ enum v4l2_auto_focus_range {
 	V4L2_AUTO_FOCUS_RANGE_INFINITY		= 3,
 };
 
+#define V4L2_CID_PAN_SPEED			(V4L2_CID_CAMERA_CLASS_BASE+32)
+#define V4L2_CID_TILT_SPEED			(V4L2_CID_CAMERA_CLASS_BASE+33)
 
 /* FM Modulator class control IDs */
 
@@ -865,6 +867,10 @@ enum v4l2_jpeg_chroma_subsampling {
 #define V4L2_CID_VBLANK				(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 1)
 #define V4L2_CID_HBLANK				(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 2)
 #define V4L2_CID_ANALOGUE_GAIN			(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 3)
+#define V4L2_CID_TEST_PATTERN_RED		(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 4)
+#define V4L2_CID_TEST_PATTERN_GREENR		(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 5)
+#define V4L2_CID_TEST_PATTERN_BLUE		(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 6)
+#define V4L2_CID_TEST_PATTERN_GREENB		(V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 7)
 
 
 /* Image processing controls */
diff --git a/include/uapi/linux/v4l2-dv-timings.h b/include/uapi/linux/v4l2-dv-timings.h
index 6c8f159e416e..6a0764c89fcb 100644
--- a/include/uapi/linux/v4l2-dv-timings.h
+++ b/include/uapi/linux/v4l2-dv-timings.h
@@ -21,17 +21,8 @@
 #ifndef _V4L2_DV_TIMINGS_H
 #define _V4L2_DV_TIMINGS_H
 
-#if __GNUC__ < 4 || (__GNUC__ == 4 && (__GNUC_MINOR__ < 6))
-/* Sadly gcc versions older than 4.6 have a bug in how they initialize
-   anonymous unions where they require additional curly brackets.
-   This violates the C1x standard. This workaround adds the curly brackets
-   if needed. */
 #define V4L2_INIT_BT_TIMINGS(_width, args...) \
 	{ .bt = { _width , ## args } }
-#else
-#define V4L2_INIT_BT_TIMINGS(_width, args...) \
-	.bt = { _width , ## args }
-#endif
 
 /* CEA-861-E timings (i.e. standard HDTV timings) */
 
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 6612974c64bf..29715d27548f 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -33,6 +33,9 @@
 /* Check if EEH is supported */
 #define VFIO_EEH			5
 
+/* Two-stage IOMMU */
+#define VFIO_TYPE1_NESTING_IOMMU	6	/* Implies v2 */
+
 /*
  * The IOCTL interface is designed for extensibility by embedding the
  * structure length (argsz) and flags into structures passed between
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 778a3298fb34..1c2f84fd4d99 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -79,6 +79,7 @@
 /*  Four-character-code (FOURCC) */
 #define v4l2_fourcc(a, b, c, d)\
 	((__u32)(a) | ((__u32)(b) << 8) | ((__u32)(c) << 16) | ((__u32)(d) << 24))
+#define v4l2_fourcc_be(a, b, c, d)	(v4l2_fourcc(a, b, c, d) | (1 << 31))
 
 /*
  *	E N U M S
@@ -307,6 +308,8 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_XRGB555 v4l2_fourcc('X', 'R', '1', '5') /* 16  XRGB-1-5-5-5  */
 #define V4L2_PIX_FMT_RGB565  v4l2_fourcc('R', 'G', 'B', 'P') /* 16  RGB-5-6-5     */
 #define V4L2_PIX_FMT_RGB555X v4l2_fourcc('R', 'G', 'B', 'Q') /* 16  RGB-5-5-5 BE  */
+#define V4L2_PIX_FMT_ARGB555X v4l2_fourcc_be('A', 'R', '1', '5') /* 16  ARGB-5-5-5 BE */
+#define V4L2_PIX_FMT_XRGB555X v4l2_fourcc_be('X', 'R', '1', '5') /* 16  XRGB-5-5-5 BE */
 #define V4L2_PIX_FMT_RGB565X v4l2_fourcc('R', 'G', 'B', 'R') /* 16  RGB-5-6-5 BE  */
 #define V4L2_PIX_FMT_BGR666  v4l2_fourcc('B', 'G', 'R', 'H') /* 18  BGR-6-6-6	  */
 #define V4L2_PIX_FMT_BGR24   v4l2_fourcc('B', 'G', 'R', '3') /* 24  BGR-8-8-8     */
@@ -1285,11 +1288,11 @@ struct v4l2_ext_control {
 	union {
 		__s32 value;
 		__s64 value64;
-		char *string;
-		__u8 *p_u8;
-		__u16 *p_u16;
-		__u32 *p_u32;
-		void *ptr;
+		char __user *string;
+		__u8 __user *p_u8;
+		__u16 __user *p_u16;
+		__u32 __user *p_u32;
+		void __user *ptr;
 	};
 } __attribute__ ((packed));
 
diff --git a/include/uapi/misc/Kbuild b/include/uapi/misc/Kbuild
new file mode 100644
index 000000000000..e96cae7d58c9
--- /dev/null
+++ b/include/uapi/misc/Kbuild
@@ -0,0 +1,2 @@
+# misc Header export list
+header-y += cxl.h
diff --git a/include/uapi/misc/cxl.h b/include/uapi/misc/cxl.h
new file mode 100644
index 000000000000..cd6d789b73ec
--- /dev/null
+++ b/include/uapi/misc/cxl.h
@@ -0,0 +1,88 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_MISC_CXL_H
+#define _UAPI_MISC_CXL_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+
+struct cxl_ioctl_start_work {
+	__u64 flags;
+	__u64 work_element_descriptor;
+	__u64 amr;
+	__s16 num_interrupts;
+	__s16 reserved1;
+	__s32 reserved2;
+	__u64 reserved3;
+	__u64 reserved4;
+	__u64 reserved5;
+	__u64 reserved6;
+};
+
+#define CXL_START_WORK_AMR		0x0000000000000001ULL
+#define CXL_START_WORK_NUM_IRQS		0x0000000000000002ULL
+#define CXL_START_WORK_ALL		(CXL_START_WORK_AMR |\
+					 CXL_START_WORK_NUM_IRQS)
+
+/* ioctl numbers */
+#define CXL_MAGIC 0xCA
+#define CXL_IOCTL_START_WORK		_IOW(CXL_MAGIC, 0x00, struct cxl_ioctl_start_work)
+#define CXL_IOCTL_GET_PROCESS_ELEMENT	_IOR(CXL_MAGIC, 0x01, __u32)
+
+#define CXL_READ_MIN_SIZE 0x1000 /* 4K */
+
+/* Events from read() */
+enum cxl_event_type {
+	CXL_EVENT_RESERVED      = 0,
+	CXL_EVENT_AFU_INTERRUPT = 1,
+	CXL_EVENT_DATA_STORAGE  = 2,
+	CXL_EVENT_AFU_ERROR     = 3,
+};
+
+struct cxl_event_header {
+	__u16 type;
+	__u16 size;
+	__u16 process_element;
+	__u16 reserved1;
+};
+
+struct cxl_event_afu_interrupt {
+	__u16 flags;
+	__u16 irq; /* Raised AFU interrupt number */
+	__u32 reserved1;
+};
+
+struct cxl_event_data_storage {
+	__u16 flags;
+	__u16 reserved1;
+	__u32 reserved2;
+	__u64 addr;
+	__u64 dsisr;
+	__u64 reserved3;
+};
+
+struct cxl_event_afu_error {
+	__u16 flags;
+	__u16 reserved1;
+	__u32 reserved2;
+	__u64 error;
+};
+
+struct cxl_event {
+	struct cxl_event_header header;
+	union {
+		struct cxl_event_afu_interrupt irq;
+		struct cxl_event_data_storage fault;
+		struct cxl_event_afu_error afu_error;
+	};
+};
+
+#endif /* _UAPI_MISC_CXL_H */
diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index 32168f7ffce3..6ee586728df9 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -219,7 +219,8 @@ typedef int __bitwise snd_pcm_format_t;
 #define	SNDRV_PCM_FORMAT_G723_40_1B	((__force snd_pcm_format_t) 47) /* 1 sample in 1 byte */
 #define	SNDRV_PCM_FORMAT_DSD_U8		((__force snd_pcm_format_t) 48) /* DSD, 1-byte samples DSD (x8) */
 #define	SNDRV_PCM_FORMAT_DSD_U16_LE	((__force snd_pcm_format_t) 49) /* DSD, 2-byte samples DSD (x16), little endian */
-#define	SNDRV_PCM_FORMAT_LAST		SNDRV_PCM_FORMAT_DSD_U16_LE
+#define	SNDRV_PCM_FORMAT_DSD_U32_LE	((__force snd_pcm_format_t) 50) /* DSD, 4-byte samples DSD (x32), little endian */
+#define	SNDRV_PCM_FORMAT_LAST		SNDRV_PCM_FORMAT_DSD_U32_LE
 
 #ifdef SNDRV_LITTLE_ENDIAN
 #define	SNDRV_PCM_FORMAT_S16		SNDRV_PCM_FORMAT_S16_LE
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index ef64b66b18df..c74bf4a0520e 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -16,6 +16,7 @@
 #include <linux/videodev2.h>
 #include <linux/bitmap.h>
 #include <linux/fb.h>
+#include <media/v4l2-mediabus.h>
 
 struct ipu_soc;
 
@@ -61,6 +62,29 @@ struct ipu_di_signal_cfg {
 	u8 vsync_pin;
 };
 
+/*
+ * Enumeration of CSI destinations
+ */
+enum ipu_csi_dest {
+	IPU_CSI_DEST_IDMAC, /* to memory via SMFC */
+	IPU_CSI_DEST_IC,	/* to Image Converter */
+	IPU_CSI_DEST_VDIC,  /* to VDIC */
+};
+
+/*
+ * Enumeration of IPU rotation modes
+ */
+enum ipu_rotate_mode {
+	IPU_ROTATE_NONE = 0,
+	IPU_ROTATE_VERT_FLIP,
+	IPU_ROTATE_HORIZ_FLIP,
+	IPU_ROTATE_180,
+	IPU_ROTATE_90_RIGHT,
+	IPU_ROTATE_90_RIGHT_VFLIP,
+	IPU_ROTATE_90_RIGHT_HFLIP,
+	IPU_ROTATE_90_LEFT,
+};
+
 enum ipu_color_space {
 	IPUV3_COLORSPACE_RGB,
 	IPUV3_COLORSPACE_YUV,
@@ -76,6 +100,36 @@ enum ipu_channel_irq {
 	IPU_IRQ_EOS = 192,
 };
 
+/*
+ * Enumeration of IDMAC channels
+ */
+#define IPUV3_CHANNEL_CSI0			 0
+#define IPUV3_CHANNEL_CSI1			 1
+#define IPUV3_CHANNEL_CSI2			 2
+#define IPUV3_CHANNEL_CSI3			 3
+#define IPUV3_CHANNEL_VDI_MEM_IC_VF		 5
+#define IPUV3_CHANNEL_MEM_IC_PP			11
+#define IPUV3_CHANNEL_MEM_IC_PRP_VF		12
+#define IPUV3_CHANNEL_G_MEM_IC_PRP_VF		14
+#define IPUV3_CHANNEL_G_MEM_IC_PP		15
+#define IPUV3_CHANNEL_IC_PRP_ENC_MEM		20
+#define IPUV3_CHANNEL_IC_PRP_VF_MEM		21
+#define IPUV3_CHANNEL_IC_PP_MEM			22
+#define IPUV3_CHANNEL_MEM_BG_SYNC		23
+#define IPUV3_CHANNEL_MEM_BG_ASYNC		24
+#define IPUV3_CHANNEL_MEM_FG_SYNC		27
+#define IPUV3_CHANNEL_MEM_DC_SYNC		28
+#define IPUV3_CHANNEL_MEM_FG_ASYNC		29
+#define IPUV3_CHANNEL_MEM_FG_SYNC_ALPHA		31
+#define IPUV3_CHANNEL_MEM_DC_ASYNC		41
+#define IPUV3_CHANNEL_MEM_ROT_ENC		45
+#define IPUV3_CHANNEL_MEM_ROT_VF		46
+#define IPUV3_CHANNEL_MEM_ROT_PP		47
+#define IPUV3_CHANNEL_ROT_ENC_MEM		48
+#define IPUV3_CHANNEL_ROT_VF_MEM		49
+#define IPUV3_CHANNEL_ROT_PP_MEM		50
+#define IPUV3_CHANNEL_MEM_BG_SYNC_ALPHA		51
+
 int ipu_map_irq(struct ipu_soc *ipu, int irq);
 int ipu_idmac_channel_irq(struct ipu_soc *ipu, struct ipuv3_channel *channel,
 		enum ipu_channel_irq irq);
@@ -93,6 +147,13 @@ int ipu_idmac_channel_irq(struct ipu_soc *ipu, struct ipuv3_channel *channel,
 #define IPU_IRQ_VSYNC_PRE_1		(448 + 15)
 
 /*
+ * IPU Common functions
+ */
+void ipu_set_csi_src_mux(struct ipu_soc *ipu, int csi_id, bool mipi_csi2);
+void ipu_set_ic_src_mux(struct ipu_soc *ipu, int csi_id, bool vdi);
+void ipu_dump(struct ipu_soc *ipu);
+
+/*
  * IPU Image DMA Controller (idmac) functions
  */
 struct ipuv3_channel *ipu_idmac_get(struct ipu_soc *ipu, unsigned channel);
@@ -100,12 +161,16 @@ void ipu_idmac_put(struct ipuv3_channel *);
 
 int ipu_idmac_enable_channel(struct ipuv3_channel *channel);
 int ipu_idmac_disable_channel(struct ipuv3_channel *channel);
+void ipu_idmac_enable_watermark(struct ipuv3_channel *channel, bool enable);
+int ipu_idmac_lock_enable(struct ipuv3_channel *channel, int num_bursts);
 int ipu_idmac_wait_busy(struct ipuv3_channel *channel, int ms);
 
 void ipu_idmac_set_double_buffer(struct ipuv3_channel *channel,
 		bool doublebuffer);
 int ipu_idmac_get_current_buffer(struct ipuv3_channel *channel);
+bool ipu_idmac_buffer_is_ready(struct ipuv3_channel *channel, u32 buf_num);
 void ipu_idmac_select_buffer(struct ipuv3_channel *channel, u32 buf_num);
+void ipu_idmac_clear_buffer(struct ipuv3_channel *channel, u32 buf_num);
 
 /*
  * IPU Channel Parameter Memory (cpmem) functions
@@ -121,7 +186,8 @@ struct ipu_rgb {
 struct ipu_image {
 	struct v4l2_pix_format pix;
 	struct v4l2_rect rect;
-	dma_addr_t phys;
+	dma_addr_t phys0;
+	dma_addr_t phys1;
 };
 
 void ipu_cpmem_zero(struct ipuv3_channel *ch);
@@ -130,7 +196,11 @@ void ipu_cpmem_set_stride(struct ipuv3_channel *ch, int stride);
 void ipu_cpmem_set_high_priority(struct ipuv3_channel *ch);
 void ipu_cpmem_set_buffer(struct ipuv3_channel *ch, int bufnum, dma_addr_t buf);
 void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride);
+void ipu_cpmem_set_axi_id(struct ipuv3_channel *ch, u32 id);
 void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize);
+void ipu_cpmem_set_block_mode(struct ipuv3_channel *ch);
+void ipu_cpmem_set_rotation(struct ipuv3_channel *ch,
+			    enum ipu_rotate_mode rot);
 int ipu_cpmem_set_format_rgb(struct ipuv3_channel *ch,
 			     const struct ipu_rgb *rgb);
 int ipu_cpmem_set_format_passthrough(struct ipuv3_channel *ch, int width);
@@ -142,6 +212,7 @@ void ipu_cpmem_set_yuv_planar(struct ipuv3_channel *ch,
 			      u32 pixel_format, int stride, int height);
 int ipu_cpmem_set_fmt(struct ipuv3_channel *ch, u32 drm_fourcc);
 int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image);
+void ipu_cpmem_dump(struct ipuv3_channel *ch);
 
 /*
  * IPU Display Controller (dc) functions
@@ -205,19 +276,78 @@ int ipu_dp_set_global_alpha(struct ipu_dp *dp, bool enable, u8 alpha,
 /*
  * IPU CMOS Sensor Interface (csi) functions
  */
-int ipu_csi_enable(struct ipu_soc *ipu, int csi);
-int ipu_csi_disable(struct ipu_soc *ipu, int csi);
+struct ipu_csi;
+int ipu_csi_init_interface(struct ipu_csi *csi,
+			   struct v4l2_mbus_config *mbus_cfg,
+			   struct v4l2_mbus_framefmt *mbus_fmt);
+bool ipu_csi_is_interlaced(struct ipu_csi *csi);
+void ipu_csi_get_window(struct ipu_csi *csi, struct v4l2_rect *w);
+void ipu_csi_set_window(struct ipu_csi *csi, struct v4l2_rect *w);
+void ipu_csi_set_test_generator(struct ipu_csi *csi, bool active,
+				u32 r_value, u32 g_value, u32 b_value,
+				u32 pix_clk);
+int ipu_csi_set_mipi_datatype(struct ipu_csi *csi, u32 vc,
+			      struct v4l2_mbus_framefmt *mbus_fmt);
+int ipu_csi_set_skip_smfc(struct ipu_csi *csi, u32 skip,
+			  u32 max_ratio, u32 id);
+int ipu_csi_set_dest(struct ipu_csi *csi, enum ipu_csi_dest csi_dest);
+int ipu_csi_enable(struct ipu_csi *csi);
+int ipu_csi_disable(struct ipu_csi *csi);
+struct ipu_csi *ipu_csi_get(struct ipu_soc *ipu, int id);
+void ipu_csi_put(struct ipu_csi *csi);
+void ipu_csi_dump(struct ipu_csi *csi);
+
+/*
+ * IPU Image Converter (ic) functions
+ */
+enum ipu_ic_task {
+	IC_TASK_ENCODER,
+	IC_TASK_VIEWFINDER,
+	IC_TASK_POST_PROCESSOR,
+	IC_NUM_TASKS,
+};
+
+struct ipu_ic;
+int ipu_ic_task_init(struct ipu_ic *ic,
+		     int in_width, int in_height,
+		     int out_width, int out_height,
+		     enum ipu_color_space in_cs,
+		     enum ipu_color_space out_cs);
+int ipu_ic_task_graphics_init(struct ipu_ic *ic,
+			      enum ipu_color_space in_g_cs,
+			      bool galpha_en, u32 galpha,
+			      bool colorkey_en, u32 colorkey);
+void ipu_ic_task_enable(struct ipu_ic *ic);
+void ipu_ic_task_disable(struct ipu_ic *ic);
+int ipu_ic_task_idma_init(struct ipu_ic *ic, struct ipuv3_channel *channel,
+			  u32 width, u32 height, int burst_size,
+			  enum ipu_rotate_mode rot);
+int ipu_ic_enable(struct ipu_ic *ic);
+int ipu_ic_disable(struct ipu_ic *ic);
+struct ipu_ic *ipu_ic_get(struct ipu_soc *ipu, enum ipu_ic_task task);
+void ipu_ic_put(struct ipu_ic *ic);
+void ipu_ic_dump(struct ipu_ic *ic);
 
 /*
  * IPU Sensor Multiple FIFO Controller (SMFC) functions
  */
-int ipu_smfc_enable(struct ipu_soc *ipu);
-int ipu_smfc_disable(struct ipu_soc *ipu);
-int ipu_smfc_map_channel(struct ipu_soc *ipu, int channel, int csi_id, int mipi_id);
-int ipu_smfc_set_burstsize(struct ipu_soc *ipu, int channel, int burstsize);
+struct ipu_smfc *ipu_smfc_get(struct ipu_soc *ipu, unsigned int chno);
+void ipu_smfc_put(struct ipu_smfc *smfc);
+int ipu_smfc_enable(struct ipu_smfc *smfc);
+int ipu_smfc_disable(struct ipu_smfc *smfc);
+int ipu_smfc_map_channel(struct ipu_smfc *smfc, int csi_id, int mipi_id);
+int ipu_smfc_set_burstsize(struct ipu_smfc *smfc, int burstsize);
+int ipu_smfc_set_watermark(struct ipu_smfc *smfc, u32 set_level, u32 clr_level);
 
 enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc);
 enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat);
+enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code);
+int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat);
+bool ipu_pixelformat_is_planar(u32 pixelformat);
+int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
+			    bool hflip, bool vflip);
+int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode,
+			    bool hflip, bool vflip);
 
 struct ipu_client_platformdata {
 	int csi;
diff --git a/include/video/of_display_timing.h b/include/video/of_display_timing.h
index 79e6697af6cf..ea755b5616d8 100644
--- a/include/video/of_display_timing.h
+++ b/include/video/of_display_timing.h
@@ -15,9 +15,25 @@ struct display_timings;
 
 #define OF_USE_NATIVE_MODE -1
 
+#ifdef CONFIG_OF
 int of_get_display_timing(struct device_node *np, const char *name,
 		struct display_timing *dt);
 struct display_timings *of_get_display_timings(struct device_node *np);
 int of_display_timings_exist(struct device_node *np);
+#else
+static inline int of_get_display_timing(struct device_node *np, const char *name,
+		struct display_timing *dt)
+{
+	return -ENOSYS;
+}
+static inline struct display_timings *of_get_display_timings(struct device_node *np)
+{
+	return NULL;
+}
+static inline int of_display_timings_exist(struct device_node *np)
+{
+	return -ENOSYS;
+}
+#endif
 
 #endif
diff --git a/include/xen/events.h b/include/xen/events.h
index 8bee7a75e850..5321cd9636e6 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -28,6 +28,8 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
 			   unsigned long irqflags,
 			   const char *devname,
 			   void *dev_id);
+int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
+				   unsigned int remote_port);
 int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
 					  unsigned int remote_port,
 					  irq_handler_t handler,
diff --git a/include/xen/interface/elfnote.h b/include/xen/interface/elfnote.h
index 6f4eae328ca7..f90b03454659 100644
--- a/include/xen/interface/elfnote.h
+++ b/include/xen/interface/elfnote.h
@@ -3,6 +3,24 @@
  *
  * Definitions used for the Xen ELF notes.
  *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
  * Copyright (c) 2006, Ian Campbell, XenSource Ltd.
  */
 
@@ -18,12 +36,13 @@
  *
  * LEGACY indicated the fields in the legacy __xen_guest string which
  * this a note type replaces.
+ *
+ * String values (for non-legacy) are NULL terminated ASCII, also known
+ * as ASCIZ type.
  */
 
 /*
  * NAME=VALUE pair (string).
- *
- * LEGACY: FEATURES and PAE
  */
 #define XEN_ELFNOTE_INFO           0
 
@@ -137,10 +156,30 @@
 
 /*
  * Whether or not the guest supports cooperative suspend cancellation.
+ * This is a numeric value.
+ *
+ * Default is 0
  */
 #define XEN_ELFNOTE_SUSPEND_CANCEL 14
 
 /*
+ * The (non-default) location the initial phys-to-machine map should be
+ * placed at by the hypervisor (Dom0) or the tools (DomU).
+ * The kernel must be prepared for this mapping to be established using
+ * large pages, despite such otherwise not being available to guests.
+ * The kernel must also be able to handle the page table pages used for
+ * this mapping not being accessible through the initial mapping.
+ * (Only x86-64 supports this at present.)
+ */
+#define XEN_ELFNOTE_INIT_P2M      15
+
+/*
+ * Whether or not the guest can deal with being passed an initrd not
+ * mapped through its initial page tables.
+ */
+#define XEN_ELFNOTE_MOD_START_PFN 16
+
+/*
  * The features supported by this kernel (numeric).
  *
  * Other than XEN_ELFNOTE_FEATURES on pre-4.2 Xen, this note allows a
@@ -153,6 +192,11 @@
  */
 #define XEN_ELFNOTE_SUPPORTED_FEATURES 17
 
+/*
+ * The number of the highest elfnote defined.
+ */
+#define XEN_ELFNOTE_MAX XEN_ELFNOTE_SUPPORTED_FEATURES
+
 #endif /* __XEN_PUBLIC_ELFNOTE_H__ */
 
 /*
diff --git a/include/xen/interface/io/vscsiif.h b/include/xen/interface/io/vscsiif.h
new file mode 100644
index 000000000000..d07d7aca8d1c
--- /dev/null
+++ b/include/xen/interface/io/vscsiif.h
@@ -0,0 +1,229 @@
+/******************************************************************************
+ * vscsiif.h
+ *
+ * Based on the blkif.h code.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Copyright(c) FUJITSU Limited 2008.
+ */
+
+#ifndef __XEN__PUBLIC_IO_SCSI_H__
+#define __XEN__PUBLIC_IO_SCSI_H__
+
+#include "ring.h"
+#include "../grant_table.h"
+
+/*
+ * Feature and Parameter Negotiation
+ * =================================
+ * The two halves of a Xen pvSCSI driver utilize nodes within the XenStore to
+ * communicate capabilities and to negotiate operating parameters.  This
+ * section enumerates these nodes which reside in the respective front and
+ * backend portions of the XenStore, following the XenBus convention.
+ *
+ * Any specified default value is in effect if the corresponding XenBus node
+ * is not present in the XenStore.
+ *
+ * XenStore nodes in sections marked "PRIVATE" are solely for use by the
+ * driver side whose XenBus tree contains them.
+ *
+ *****************************************************************************
+ *                            Backend XenBus Nodes
+ *****************************************************************************
+ *
+ *------------------ Backend Device Identification (PRIVATE) ------------------
+ *
+ * p-devname
+ *      Values:         string
+ *
+ *      A free string used to identify the physical device (e.g. a disk name).
+ *
+ * p-dev
+ *      Values:         string
+ *
+ *      A string specifying the backend device: either a 4-tuple "h:c:t:l"
+ *      (host, controller, target, lun, all integers), or a WWN (e.g.
+ *      "naa.60014054ac780582").
+ *
+ * v-dev
+ *      Values:         string
+ *
+ *      A string specifying the frontend device in form of a 4-tuple "h:c:t:l"
+ *      (host, controller, target, lun, all integers).
+ *
+ *--------------------------------- Features ---------------------------------
+ *
+ * feature-sg-grant
+ *      Values:         unsigned [VSCSIIF_SG_TABLESIZE...65535]
+ *      Default Value:  0
+ *
+ *      Specifies the maximum number of scatter/gather elements in grant pages
+ *      supported. If not set, the backend supports up to VSCSIIF_SG_TABLESIZE
+ *      SG elements specified directly in the request.
+ *
+ *****************************************************************************
+ *                            Frontend XenBus Nodes
+ *****************************************************************************
+ *
+ *----------------------- Request Transport Parameters -----------------------
+ *
+ * event-channel
+ *      Values:         unsigned
+ *
+ *      The identifier of the Xen event channel used to signal activity
+ *      in the ring buffer.
+ *
+ * ring-ref
+ *      Values:         unsigned
+ *
+ *      The Xen grant reference granting permission for the backend to map
+ *      the sole page in a single page sized ring buffer.
+ *
+ * protocol
+ *      Values:         string (XEN_IO_PROTO_ABI_*)
+ *      Default Value:  XEN_IO_PROTO_ABI_NATIVE
+ *
+ *      The machine ABI rules governing the format of all ring request and
+ *      response structures.
+ */
+
+/* Requests from the frontend to the backend */
+
+/*
+ * Request a SCSI operation specified via a CDB in vscsiif_request.cmnd.
+ * The target is specified via channel, id and lun.
+ *
+ * The operation to be performed is specified via a CDB in cmnd[], the length
+ * of the CDB is in cmd_len. sc_data_direction specifies the direction of data
+ * (to the device, from the device, or none at all).
+ *
+ * If data is to be transferred to or from the device the buffer(s) in the
+ * guest memory is/are specified via one or multiple scsiif_request_segment
+ * descriptors each specifying a memory page via a grant_ref_t, a offset into
+ * the page and the length of the area in that page. All scsiif_request_segment
+ * areas concatenated form the resulting data buffer used by the operation.
+ * If the number of scsiif_request_segment areas is not too large (less than
+ * or equal VSCSIIF_SG_TABLESIZE) the areas can be specified directly in the
+ * seg[] array and the number of valid scsiif_request_segment elements is to be
+ * set in nr_segments.
+ *
+ * If "feature-sg-grant" in the Xenstore is set it is possible to specify more
+ * than VSCSIIF_SG_TABLESIZE scsiif_request_segment elements via indirection.
+ * The maximum number of allowed scsiif_request_segment elements is the value
+ * of the "feature-sg-grant" entry from Xenstore. When using indirection the
+ * seg[] array doesn't contain specifications of the data buffers, but
+ * references to scsiif_request_segment arrays, which in turn reference the
+ * data buffers. While nr_segments holds the number of populated seg[] entries
+ * (plus the set VSCSIIF_SG_GRANT bit), the number of scsiif_request_segment
+ * elements referencing the target data buffers is calculated from the lengths
+ * of the seg[] elements (the sum of all valid seg[].length divided by the
+ * size of one scsiif_request_segment structure).
+ */
+#define VSCSIIF_ACT_SCSI_CDB		1
+
+/*
+ * Request abort of a running operation for the specified target given by
+ * channel, id, lun and the operation's rqid in ref_rqid.
+ */
+#define VSCSIIF_ACT_SCSI_ABORT		2
+
+/*
+ * Request a device reset of the specified target (channel and id).
+ */
+#define VSCSIIF_ACT_SCSI_RESET		3
+
+/*
+ * Preset scatter/gather elements for a following request. Deprecated.
+ * Keeping the define only to avoid usage of the value "4" for other actions.
+ */
+#define VSCSIIF_ACT_SCSI_SG_PRESET	4
+
+/*
+ * Maximum scatter/gather segments per request.
+ *
+ * Considering balance between allocating at least 16 "vscsiif_request"
+ * structures on one page (4096 bytes) and the number of scatter/gather
+ * elements needed, we decided to use 26 as a magic number.
+ *
+ * If "feature-sg-grant" is set, more scatter/gather elements can be specified
+ * by placing them in one or more (up to VSCSIIF_SG_TABLESIZE) granted pages.
+ * In this case the vscsiif_request seg elements don't contain references to
+ * the user data, but to the SG elements referencing the user data.
+ */
+#define VSCSIIF_SG_TABLESIZE		26
+
+/*
+ * based on Linux kernel 2.6.18, still valid
+ * Changing these values requires support of multiple protocols via the rings
+ * as "old clients" will blindly use these values and the resulting structure
+ * sizes.
+ */
+#define VSCSIIF_MAX_COMMAND_SIZE	16
+#define VSCSIIF_SENSE_BUFFERSIZE	96
+
+struct scsiif_request_segment {
+	grant_ref_t gref;
+	uint16_t offset;
+	uint16_t length;
+};
+
+#define VSCSIIF_SG_PER_PAGE (PAGE_SIZE / sizeof(struct scsiif_request_segment))
+
+/* Size of one request is 252 bytes */
+struct vscsiif_request {
+	uint16_t rqid;		/* private guest value, echoed in resp  */
+	uint8_t act;		/* command between backend and frontend */
+	uint8_t cmd_len;	/* valid CDB bytes */
+
+	uint8_t cmnd[VSCSIIF_MAX_COMMAND_SIZE];	/* the CDB */
+	uint16_t timeout_per_command;	/* deprecated */
+	uint16_t channel, id, lun;	/* (virtual) device specification */
+	uint16_t ref_rqid;		/* command abort reference */
+	uint8_t sc_data_direction;	/* for DMA_TO_DEVICE(1)
+					   DMA_FROM_DEVICE(2)
+					   DMA_NONE(3) requests */
+	uint8_t nr_segments;		/* Number of pieces of scatter-gather */
+/*
+ * flag in nr_segments: SG elements via grant page
+ *
+ * If VSCSIIF_SG_GRANT is set, the low 7 bits of nr_segments specify the number
+ * of grant pages containing SG elements. Usable if "feature-sg-grant" set.
+ */
+#define VSCSIIF_SG_GRANT	0x80
+
+	struct scsiif_request_segment seg[VSCSIIF_SG_TABLESIZE];
+	uint32_t reserved[3];
+};
+
+/* Size of one response is 252 bytes */
+struct vscsiif_response {
+	uint16_t rqid;		/* identifies request */
+	uint8_t padding;
+	uint8_t sense_len;
+	uint8_t sense_buffer[VSCSIIF_SENSE_BUFFERSIZE];
+	int32_t rslt;
+	uint32_t residual_len;	/* request bufflen -
+				   return the value from physical device */
+	uint32_t reserved[36];
+};
+
+DEFINE_RING_TYPES(vscsiif, struct vscsiif_request, struct vscsiif_response);
+
+#endif /*__XEN__PUBLIC_IO_SCSI_H__*/
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index de082130ba4b..f68719f405af 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -3,6 +3,24 @@
  *
  * Guest OS interface to Xen.
  *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
  * Copyright (c) 2004, K A Fraser
  */
 
@@ -73,13 +91,23 @@
  * VIRTUAL INTERRUPTS
  *
  * Virtual interrupts that a guest OS may receive from Xen.
+ * In the side comments, 'V.' denotes a per-VCPU VIRQ while 'G.' denotes a
+ * global VIRQ. The former can be bound once per VCPU and cannot be re-bound.
+ * The latter can be allocated only once per guest: they must initially be
+ * allocated to VCPU0 but can subsequently be re-bound.
  */
-#define VIRQ_TIMER      0  /* Timebase update, and/or requested timeout.  */
-#define VIRQ_DEBUG      1  /* Request guest to dump debug info.           */
-#define VIRQ_CONSOLE    2  /* (DOM0) Bytes received on emergency console. */
-#define VIRQ_DOM_EXC    3  /* (DOM0) Exceptional event for some domain.   */
-#define VIRQ_DEBUGGER   6  /* (DOM0) A domain has paused for debugging.   */
-#define VIRQ_PCPU_STATE 9  /* (DOM0) PCPU state changed                   */
+#define VIRQ_TIMER      0  /* V. Timebase update, and/or requested timeout.  */
+#define VIRQ_DEBUG      1  /* V. Request guest to dump debug info.           */
+#define VIRQ_CONSOLE    2  /* G. (DOM0) Bytes received on emergency console. */
+#define VIRQ_DOM_EXC    3  /* G. (DOM0) Exceptional event for some domain.   */
+#define VIRQ_TBUF       4  /* G. (DOM0) Trace buffer has records available.  */
+#define VIRQ_DEBUGGER   6  /* G. (DOM0) A domain has paused for debugging.   */
+#define VIRQ_XENOPROF   7  /* V. XenOprofile interrupt: new sample available */
+#define VIRQ_CON_RING   8  /* G. (DOM0) Bytes received on console            */
+#define VIRQ_PCPU_STATE 9  /* G. (DOM0) PCPU state changed                   */
+#define VIRQ_MEM_EVENT  10 /* G. (DOM0) A memory event has occured           */
+#define VIRQ_XC_RESERVED 11 /* G. Reserved for XenClient                     */
+#define VIRQ_ENOMEM     12 /* G. (DOM0) Low on heap memory       */
 
 /* Architecture-specific VIRQ definitions. */
 #define VIRQ_ARCH_0    16
@@ -92,24 +120,68 @@
 #define VIRQ_ARCH_7    23
 
 #define NR_VIRQS       24
+
 /*
- * MMU-UPDATE REQUESTS
- *
- * HYPERVISOR_mmu_update() accepts a list of (ptr, val) pairs.
- * A foreigndom (FD) can be specified (or DOMID_SELF for none).
- * Where the FD has some effect, it is described below.
- * ptr[1:0] specifies the appropriate MMU_* command.
+ * enum neg_errnoval HYPERVISOR_mmu_update(const struct mmu_update reqs[],
+ *                                         unsigned count, unsigned *done_out,
+ *                                         unsigned foreigndom)
+ * @reqs is an array of mmu_update_t structures ((ptr, val) pairs).
+ * @count is the length of the above array.
+ * @pdone is an output parameter indicating number of completed operations
+ * @foreigndom[15:0]: FD, the expected owner of data pages referenced in this
+ *                    hypercall invocation. Can be DOMID_SELF.
+ * @foreigndom[31:16]: PFD, the expected owner of pagetable pages referenced
+ *                     in this hypercall invocation. The value of this field
+ *                     (x) encodes the PFD as follows:
+ *                     x == 0 => PFD == DOMID_SELF
+ *                     x != 0 => PFD == x - 1
  *
+ * Sub-commands: ptr[1:0] specifies the appropriate MMU_* command.
+ * -------------
  * ptr[1:0] == MMU_NORMAL_PT_UPDATE:
- * Updates an entry in a page table. If updating an L1 table, and the new
- * table entry is valid/present, the mapped frame must belong to the FD, if
- * an FD has been specified. If attempting to map an I/O page then the
- * caller assumes the privilege of the FD.
+ * Updates an entry in a page table belonging to PFD. If updating an L1 table,
+ * and the new table entry is valid/present, the mapped frame must belong to
+ * FD. If attempting to map an I/O page then the caller assumes the privilege
+ * of the FD.
  * FD == DOMID_IO: Permit /only/ I/O mappings, at the priv level of the caller.
  * FD == DOMID_XEN: Map restricted areas of Xen's heap space.
  * ptr[:2]  -- Machine address of the page-table entry to modify.
  * val      -- Value to write.
  *
+ * There also certain implicit requirements when using this hypercall. The
+ * pages that make up a pagetable must be mapped read-only in the guest.
+ * This prevents uncontrolled guest updates to the pagetable. Xen strictly
+ * enforces this, and will disallow any pagetable update which will end up
+ * mapping pagetable page RW, and will disallow using any writable page as a
+ * pagetable. In practice it means that when constructing a page table for a
+ * process, thread, etc, we MUST be very dilligient in following these rules:
+ *  1). Start with top-level page (PGD or in Xen language: L4). Fill out
+ *      the entries.
+ *  2). Keep on going, filling out the upper (PUD or L3), and middle (PMD
+ *      or L2).
+ *  3). Start filling out the PTE table (L1) with the PTE entries. Once
+ *      done, make sure to set each of those entries to RO (so writeable bit
+ *      is unset). Once that has been completed, set the PMD (L2) for this
+ *      PTE table as RO.
+ *  4). When completed with all of the PMD (L2) entries, and all of them have
+ *      been set to RO, make sure to set RO the PUD (L3). Do the same
+ *      operation on PGD (L4) pagetable entries that have a PUD (L3) entry.
+ *  5). Now before you can use those pages (so setting the cr3), you MUST also
+ *      pin them so that the hypervisor can verify the entries. This is done
+ *      via the HYPERVISOR_mmuext_op(MMUEXT_PIN_L4_TABLE, guest physical frame
+ *      number of the PGD (L4)). And this point the HYPERVISOR_mmuext_op(
+ *      MMUEXT_NEW_BASEPTR, guest physical frame number of the PGD (L4)) can be
+ *      issued.
+ * For 32-bit guests, the L4 is not used (as there is less pagetables), so
+ * instead use L3.
+ * At this point the pagetables can be modified using the MMU_NORMAL_PT_UPDATE
+ * hypercall. Also if so desired the OS can also try to write to the PTE
+ * and be trapped by the hypervisor (as the PTE entry is RO).
+ *
+ * To deallocate the pages, the operations are the reverse of the steps
+ * mentioned above. The argument is MMUEXT_UNPIN_TABLE for all levels and the
+ * pagetable MUST not be in use (meaning that the cr3 is not set to it).
+ *
  * ptr[1:0] == MMU_MACHPHYS_UPDATE:
  * Updates an entry in the machine->pseudo-physical mapping table.
  * ptr[:2]  -- Machine address within the frame whose mapping to modify.
@@ -119,6 +191,72 @@
  * ptr[1:0] == MMU_PT_UPDATE_PRESERVE_AD:
  * As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed
  * with those in @val.
+ *
+ * @val is usually the machine frame number along with some attributes.
+ * The attributes by default follow the architecture defined bits. Meaning that
+ * if this is a X86_64 machine and four page table layout is used, the layout
+ * of val is:
+ *  - 63 if set means No execute (NX)
+ *  - 46-13 the machine frame number
+ *  - 12 available for guest
+ *  - 11 available for guest
+ *  - 10 available for guest
+ *  - 9 available for guest
+ *  - 8 global
+ *  - 7 PAT (PSE is disabled, must use hypercall to make 4MB or 2MB pages)
+ *  - 6 dirty
+ *  - 5 accessed
+ *  - 4 page cached disabled
+ *  - 3 page write through
+ *  - 2 userspace accessible
+ *  - 1 writeable
+ *  - 0 present
+ *
+ *  The one bits that does not fit with the default layout is the PAGE_PSE
+ *  also called PAGE_PAT). The MMUEXT_[UN]MARK_SUPER arguments to the
+ *  HYPERVISOR_mmuext_op serve as mechanism to set a pagetable to be 4MB
+ *  (or 2MB) instead of using the PAGE_PSE bit.
+ *
+ *  The reason that the PAGE_PSE (bit 7) is not being utilized is due to Xen
+ *  using it as the Page Attribute Table (PAT) bit - for details on it please
+ *  refer to Intel SDM 10.12. The PAT allows to set the caching attributes of
+ *  pages instead of using MTRRs.
+ *
+ *  The PAT MSR is as follows (it is a 64-bit value, each entry is 8 bits):
+ *                    PAT4                 PAT0
+ *  +-----+-----+----+----+----+-----+----+----+
+ *  | UC  | UC- | WC | WB | UC | UC- | WC | WB |  <= Linux
+ *  +-----+-----+----+----+----+-----+----+----+
+ *  | UC  | UC- | WT | WB | UC | UC- | WT | WB |  <= BIOS (default when machine boots)
+ *  +-----+-----+----+----+----+-----+----+----+
+ *  | rsv | rsv | WP | WC | UC | UC- | WT | WB |  <= Xen
+ *  +-----+-----+----+----+----+-----+----+----+
+ *
+ *  The lookup of this index table translates to looking up
+ *  Bit 7, Bit 4, and Bit 3 of val entry:
+ *
+ *  PAT/PSE (bit 7) ... PCD (bit 4) .. PWT (bit 3).
+ *
+ *  If all bits are off, then we are using PAT0. If bit 3 turned on,
+ *  then we are using PAT1, if bit 3 and bit 4, then PAT2..
+ *
+ *  As you can see, the Linux PAT1 translates to PAT4 under Xen. Which means
+ *  that if a guest that follows Linux's PAT setup and would like to set Write
+ *  Combined on pages it MUST use PAT4 entry. Meaning that Bit 7 (PAGE_PAT) is
+ *  set. For example, under Linux it only uses PAT0, PAT1, and PAT2 for the
+ *  caching as:
+ *
+ *   WB = none (so PAT0)
+ *   WC = PWT (bit 3 on)
+ *   UC = PWT | PCD (bit 3 and 4 are on).
+ *
+ * To make it work with Xen, it needs to translate the WC bit as so:
+ *
+ *  PWT (so bit 3 on) --> PAT (so bit 7 is on) and clear bit 3
+ *
+ * And to translate back it would:
+ *
+ * PAT (bit 7 on) --> PWT (bit 3 on) and clear bit 7.
  */
 #define MMU_NORMAL_PT_UPDATE      0 /* checked '*ptr = val'. ptr is MA.       */
 #define MMU_MACHPHYS_UPDATE       1 /* ptr = MA of frame to modify entry for  */
@@ -127,7 +265,12 @@
 /*
  * MMU EXTENDED OPERATIONS
  *
- * HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures.
+ * enum neg_errnoval HYPERVISOR_mmuext_op(mmuext_op_t uops[],
+ *                                        unsigned int count,
+ *                                        unsigned int *pdone,
+ *                                        unsigned int foreigndom)
+ */
+/* HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures.
  * A foreigndom (FD) can be specified (or DOMID_SELF for none).
  * Where the FD has some effect, it is described below.
  *
@@ -164,9 +307,23 @@
  * cmd: MMUEXT_FLUSH_CACHE
  * No additional arguments. Writes back and flushes cache contents.
  *
+ * cmd: MMUEXT_FLUSH_CACHE_GLOBAL
+ * No additional arguments. Writes back and flushes cache contents
+ * on all CPUs in the system.
+ *
  * cmd: MMUEXT_SET_LDT
  * linear_addr: Linear address of LDT base (NB. must be page-aligned).
  * nr_ents: Number of entries in LDT.
+ *
+ * cmd: MMUEXT_CLEAR_PAGE
+ * mfn: Machine frame number to be cleared.
+ *
+ * cmd: MMUEXT_COPY_PAGE
+ * mfn: Machine frame number of the destination page.
+ * src_mfn: Machine frame number of the source page.
+ *
+ * cmd: MMUEXT_[UN]MARK_SUPER
+ * mfn: Machine frame number of head of superpage to be [un]marked.
  */
 #define MMUEXT_PIN_L1_TABLE      0
 #define MMUEXT_PIN_L2_TABLE      1
@@ -183,12 +340,18 @@
 #define MMUEXT_FLUSH_CACHE      12
 #define MMUEXT_SET_LDT          13
 #define MMUEXT_NEW_USER_BASEPTR 15
+#define MMUEXT_CLEAR_PAGE       16
+#define MMUEXT_COPY_PAGE        17
+#define MMUEXT_FLUSH_CACHE_GLOBAL 18
+#define MMUEXT_MARK_SUPER       19
+#define MMUEXT_UNMARK_SUPER     20
 
 #ifndef __ASSEMBLY__
 struct mmuext_op {
 	unsigned int cmd;
 	union {
-		/* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR */
+		/* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR
+		 * CLEAR_PAGE, COPY_PAGE, [UN]MARK_SUPER */
 		xen_pfn_t mfn;
 		/* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */
 		unsigned long linear_addr;
@@ -198,6 +361,8 @@ struct mmuext_op {
 		unsigned int nr_ents;
 		/* TLB_FLUSH_MULTI, INVLPG_MULTI */
 		void *vcpumask;
+		/* COPY_PAGE */
+		xen_pfn_t src_mfn;
 	} arg2;
 };
 DEFINE_GUEST_HANDLE_STRUCT(mmuext_op);
@@ -225,10 +390,23 @@ DEFINE_GUEST_HANDLE_STRUCT(mmuext_op);
  */
 #define VMASST_CMD_enable                0
 #define VMASST_CMD_disable               1
+
+/* x86/32 guests: simulate full 4GB segment limits. */
 #define VMASST_TYPE_4gb_segments         0
+
+/* x86/32 guests: trap (vector 15) whenever above vmassist is used. */
 #define VMASST_TYPE_4gb_segments_notify  1
+
+/*
+ * x86 guests: support writes to bottom-level PTEs.
+ * NB1. Page-directory entries cannot be written.
+ * NB2. Guest must continue to remove all writable mappings of PTEs.
+ */
 #define VMASST_TYPE_writable_pagetables  2
+
+/* x86/PAE guests: support PDPTs above 4GB. */
 #define VMASST_TYPE_pae_extended_cr3     3
+
 #define MAX_VMASST_TYPE 3
 
 #ifndef __ASSEMBLY__
@@ -260,6 +438,15 @@ typedef uint16_t domid_t;
  */
 #define DOMID_XEN  (0x7FF2U)
 
+/* DOMID_COW is used as the owner of sharable pages */
+#define DOMID_COW  (0x7FF3U)
+
+/* DOMID_INVALID is used to identify pages with unknown owner. */
+#define DOMID_INVALID (0x7FF4U)
+
+/* Idle domain. */
+#define DOMID_IDLE (0x7FFFU)
+
 /*
  * Send an array of these to HYPERVISOR_mmu_update().
  * NB. The fields are natural pointer/address size for this architecture.
@@ -272,7 +459,9 @@ DEFINE_GUEST_HANDLE_STRUCT(mmu_update);
 
 /*
  * Send an array of these to HYPERVISOR_multicall().
- * NB. The fields are natural register size for this architecture.
+ * NB. The fields are logically the natural register size for this
+ * architecture. In cases where xen_ulong_t is larger than this then
+ * any unused bits in the upper portion must be zero.
  */
 struct multicall_entry {
     xen_ulong_t op;
@@ -442,8 +631,48 @@ struct start_info {
 	unsigned long mod_start;    /* VIRTUAL address of pre-loaded module.  */
 	unsigned long mod_len;      /* Size (bytes) of pre-loaded module.     */
 	int8_t cmd_line[MAX_GUEST_CMDLINE];
+	/* The pfn range here covers both page table and p->m table frames.   */
+	unsigned long first_p2m_pfn;/* 1st pfn forming initial P->M table.    */
+	unsigned long nr_p2m_frames;/* # of pfns forming initial P->M table.  */
 };
 
+/* These flags are passed in the 'flags' field of start_info_t. */
+#define SIF_PRIVILEGED    (1<<0)  /* Is the domain privileged? */
+#define SIF_INITDOMAIN    (1<<1)  /* Is this the initial control domain? */
+#define SIF_MULTIBOOT_MOD (1<<2)  /* Is mod_start a multiboot module? */
+#define SIF_MOD_START_PFN (1<<3)  /* Is mod_start a PFN? */
+#define SIF_PM_MASK       (0xFF<<8) /* reserve 1 byte for xen-pm options */
+
+/*
+ * A multiboot module is a package containing modules very similar to a
+ * multiboot module array. The only differences are:
+ * - the array of module descriptors is by convention simply at the beginning
+ *   of the multiboot module,
+ * - addresses in the module descriptors are based on the beginning of the
+ *   multiboot module,
+ * - the number of modules is determined by a termination descriptor that has
+ *   mod_start == 0.
+ *
+ * This permits to both build it statically and reference it in a configuration
+ * file, and let the PV guest easily rebase the addresses to virtual addresses
+ * and at the same time count the number of modules.
+ */
+struct xen_multiboot_mod_list {
+	/* Address of first byte of the module */
+	uint32_t mod_start;
+	/* Address of last byte of the module (inclusive) */
+	uint32_t mod_end;
+	/* Address of zero-terminated command line */
+	uint32_t cmdline;
+	/* Unused, must be zero */
+	uint32_t pad;
+};
+/*
+ * The console structure in start_info.console.dom0
+ *
+ * This structure includes a variety of information required to
+ * have a working VGA/VESA console.
+ */
 struct dom0_vga_console_info {
 	uint8_t video_type;
 #define XEN_VGATYPE_TEXT_MODE_3 0x03
@@ -484,11 +713,6 @@ struct dom0_vga_console_info {
 	} u;
 };
 
-/* These flags are passed in the 'flags' field of start_info_t. */
-#define SIF_PRIVILEGED    (1<<0)  /* Is the domain privileged? */
-#define SIF_INITDOMAIN    (1<<1)  /* Is this the initial control domain? */
-#define SIF_PM_MASK       (0xFF<<8) /* reserve 1 byte for xen-pm options */
-
 typedef uint64_t cpumap_t;
 
 typedef uint8_t xen_domain_handle_t[16];
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index 0324c6d340c1..b78f21caf55a 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -86,6 +86,7 @@ struct xenbus_device_id
 
 /* A xenbus driver. */
 struct xenbus_driver {
+	const char *name;       /* defaults to ids[0].devicetype */
 	const struct xenbus_device_id *ids;
 	int (*probe)(struct xenbus_device *dev,
 		     const struct xenbus_device_id *id);
@@ -100,20 +101,22 @@ struct xenbus_driver {
 	int (*is_ready)(struct xenbus_device *dev);
 };
 
-#define DEFINE_XENBUS_DRIVER(var, drvname, methods...)		\
-struct xenbus_driver var ## _driver = {				\
-	.driver.name = drvname + 0 ?: var ## _ids->devicetype,	\
-	.driver.owner = THIS_MODULE,				\
-	.ids = var ## _ids, ## methods				\
-}
-
 static inline struct xenbus_driver *to_xenbus_driver(struct device_driver *drv)
 {
 	return container_of(drv, struct xenbus_driver, driver);
 }
 
-int __must_check xenbus_register_frontend(struct xenbus_driver *);
-int __must_check xenbus_register_backend(struct xenbus_driver *);
+int __must_check __xenbus_register_frontend(struct xenbus_driver *drv,
+					    struct module *owner,
+					    const char *mod_name);
+int __must_check __xenbus_register_backend(struct xenbus_driver *drv,
+					   struct module *owner,
+					   const char *mod_name);
+
+#define xenbus_register_frontend(drv) \
+	__xenbus_register_frontend(drv, THIS_MODULE, KBUILD_MODNAME);
+#define xenbus_register_backend(drv) \
+	__xenbus_register_backend(drv, THIS_MODULE, KBUILD_MODNAME);
 
 void xenbus_unregister_driver(struct xenbus_driver *drv);
 
diff --git a/init/Kconfig b/init/Kconfig
index e25a82a291a6..3ee28ae02cc8 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -507,6 +507,16 @@ config PREEMPT_RCU
 	  This option enables preemptible-RCU code that is common between
 	  TREE_PREEMPT_RCU and, in the old days, TINY_PREEMPT_RCU.
 
+config TASKS_RCU
+	bool "Task_based RCU implementation using voluntary context switch"
+	default n
+	help
+	  This option enables a task-based RCU implementation that uses
+	  only voluntary context switch (not preemption!), idle, and
+	  user-mode execution as quiescent states.
+
+	  If unsure, say N.
+
 config RCU_STALL_COMMON
 	def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE )
 	help
@@ -737,7 +747,7 @@ choice
 
 config RCU_NOCB_CPU_NONE
 	bool "No build_forced no-CBs CPUs"
-	depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL
+	depends on RCU_NOCB_CPU
 	help
 	  This option does not force any of the CPUs to be no-CBs CPUs.
 	  Only CPUs designated by the rcu_nocbs= boot parameter will be
@@ -751,7 +761,7 @@ config RCU_NOCB_CPU_NONE
 
 config RCU_NOCB_CPU_ZERO
 	bool "CPU 0 is a build_forced no-CBs CPU"
-	depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL
+	depends on RCU_NOCB_CPU
 	help
 	  This option forces CPU 0 to be a no-CBs CPU, so that its RCU
 	  callbacks are invoked by a per-CPU kthread whose name begins
@@ -828,6 +838,7 @@ config LOG_BUF_SHIFT
 
 config LOG_CPU_MAX_BUF_SHIFT
 	int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)"
+	depends on SMP
 	range 0 21
 	default 12 if !BASE_SMALL
 	default 0 if BASE_SMALL
@@ -889,17 +900,6 @@ config ARCH_SUPPORTS_INT128
 config ARCH_WANT_NUMA_VARIABLE_LOCALITY
 	bool
 
-#
-# For architectures that are willing to define _PAGE_NUMA as _PAGE_PROTNONE
-config ARCH_WANTS_PROT_NUMA_PROT_NONE
-	bool
-
-config ARCH_USES_NUMA_PROT_NONE
-	bool
-	default y
-	depends on ARCH_WANTS_PROT_NUMA_PROT_NONE
-	depends on NUMA_BALANCING
-
 config NUMA_BALANCING_DEFAULT_ENABLED
 	bool "Automatically enable NUMA aware memory/task placement"
 	default y
diff --git a/init/initramfs.c b/init/initramfs.c
index bece48c3461e..ad1bd7787bbb 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -197,14 +197,14 @@ static __initdata enum state {
 } state, next_state;
 
 static __initdata char *victim;
-static unsigned long count __initdata;
+static unsigned long byte_count __initdata;
 static __initdata loff_t this_header, next_header;
 
 static inline void __init eat(unsigned n)
 {
 	victim += n;
 	this_header += n;
-	count -= n;
+	byte_count -= n;
 }
 
 static __initdata char *vcollected;
@@ -214,7 +214,7 @@ static __initdata char *collect;
 
 static void __init read_into(char *buf, unsigned size, enum state next)
 {
-	if (count >= size) {
+	if (byte_count >= size) {
 		collected = victim;
 		eat(size);
 		state = next;
@@ -237,8 +237,8 @@ static int __init do_start(void)
 static int __init do_collect(void)
 {
 	unsigned long n = remains;
-	if (count < n)
-		n = count;
+	if (byte_count < n)
+		n = byte_count;
 	memcpy(collect, victim, n);
 	eat(n);
 	collect += n;
@@ -280,8 +280,8 @@ static int __init do_header(void)
 
 static int __init do_skip(void)
 {
-	if (this_header + count < next_header) {
-		eat(count);
+	if (this_header + byte_count < next_header) {
+		eat(byte_count);
 		return 1;
 	} else {
 		eat(next_header - this_header);
@@ -292,9 +292,9 @@ static int __init do_skip(void)
 
 static int __init do_reset(void)
 {
-	while(count && *victim == '\0')
+	while (byte_count && *victim == '\0')
 		eat(1);
-	if (count && (this_header & 3))
+	if (byte_count && (this_header & 3))
 		error("broken padding");
 	return 1;
 }
@@ -309,11 +309,11 @@ static int __init maybe_link(void)
 	return 0;
 }
 
-static void __init clean_path(char *path, umode_t mode)
+static void __init clean_path(char *path, umode_t fmode)
 {
 	struct stat st;
 
-	if (!sys_newlstat(path, &st) && (st.st_mode^mode) & S_IFMT) {
+	if (!sys_newlstat(path, &st) && (st.st_mode ^ fmode) & S_IFMT) {
 		if (S_ISDIR(st.st_mode))
 			sys_rmdir(path);
 		else
@@ -368,7 +368,7 @@ static int __init do_name(void)
 
 static int __init do_copy(void)
 {
-	if (count >= body_len) {
+	if (byte_count >= body_len) {
 		if (xwrite(wfd, victim, body_len) != body_len)
 			error("write error");
 		sys_close(wfd);
@@ -378,10 +378,10 @@ static int __init do_copy(void)
 		state = SkipIt;
 		return 0;
 	} else {
-		if (xwrite(wfd, victim, count) != count)
+		if (xwrite(wfd, victim, byte_count) != byte_count)
 			error("write error");
-		body_len -= count;
-		eat(count);
+		body_len -= byte_count;
+		eat(byte_count);
 		return 1;
 	}
 }
@@ -411,12 +411,12 @@ static __initdata int (*actions[])(void) = {
 
 static long __init write_buffer(char *buf, unsigned long len)
 {
-	count = len;
+	byte_count = len;
 	victim = buf;
 
 	while (!actions[state]())
 		;
-	return len - count;
+	return len - byte_count;
 }
 
 static long __init flush_buffer(void *bufv, unsigned long len)
diff --git a/init/main.c b/init/main.c
index bb1aed928f21..800a0daede7e 100644
--- a/init/main.c
+++ b/init/main.c
@@ -501,13 +501,13 @@ asmlinkage __visible void __init start_kernel(void)
 {
 	char *command_line;
 	char *after_dashes;
-	extern const struct kernel_param __start___param[], __stop___param[];
 
 	/*
 	 * Need to run as early as possible, to initialize the
 	 * lockdep hash:
 	 */
 	lockdep_init();
+	set_task_stack_end_magic(&init_task);
 	smp_setup_processor_id();
 	debug_objects_early_init();
 
@@ -577,13 +577,13 @@ asmlinkage __visible void __init start_kernel(void)
 		local_irq_disable();
 	idr_init_cache();
 	rcu_init();
-	tick_nohz_init();
 	context_tracking_init();
 	radix_tree_init();
 	/* init some links before init_ISA_irqs() */
 	early_irq_init();
 	init_IRQ();
 	tick_init();
+	rcu_init_nohz();
 	init_timers();
 	hrtimers_init();
 	softirq_init();
@@ -843,7 +843,6 @@ static char *initcall_level_names[] __initdata = {
 
 static void __init do_initcall_level(int level)
 {
-	extern const struct kernel_param __start___param[], __stop___param[];
 	initcall_t *fn;
 
 	strcpy(initcall_command_line, saved_command_line);
diff --git a/ipc/compat.c b/ipc/compat.c
index b5ef4f7946dc..9b3c85f8a538 100644
--- a/ipc/compat.c
+++ b/ipc/compat.c
@@ -171,32 +171,32 @@ static inline int __put_compat_ipc64_perm(struct ipc64_perm *p64,
 }
 
 static inline int __put_compat_ipc_perm(struct ipc64_perm *p,
-					struct compat_ipc_perm __user *up)
+					struct compat_ipc_perm __user *uip)
 {
 	int err;
 	__compat_uid_t u;
 	__compat_gid_t g;
 
-	err  = __put_user(p->key, &up->key);
+	err  = __put_user(p->key, &uip->key);
 	SET_UID(u, p->uid);
-	err |= __put_user(u, &up->uid);
+	err |= __put_user(u, &uip->uid);
 	SET_GID(g, p->gid);
-	err |= __put_user(g, &up->gid);
+	err |= __put_user(g, &uip->gid);
 	SET_UID(u, p->cuid);
-	err |= __put_user(u, &up->cuid);
+	err |= __put_user(u, &uip->cuid);
 	SET_GID(g, p->cgid);
-	err |= __put_user(g, &up->cgid);
-	err |= __put_user(p->mode, &up->mode);
-	err |= __put_user(p->seq, &up->seq);
+	err |= __put_user(g, &uip->cgid);
+	err |= __put_user(p->mode, &uip->mode);
+	err |= __put_user(p->seq, &uip->seq);
 	return err;
 }
 
-static inline int get_compat_semid64_ds(struct semid64_ds *s64,
+static inline int get_compat_semid64_ds(struct semid64_ds *sem64,
 					struct compat_semid64_ds __user *up64)
 {
 	if (!access_ok(VERIFY_READ, up64, sizeof(*up64)))
 		return -EFAULT;
-	return __get_compat_ipc64_perm(&s64->sem_perm, &up64->sem_perm);
+	return __get_compat_ipc64_perm(&sem64->sem_perm, &up64->sem_perm);
 }
 
 static inline int get_compat_semid_ds(struct semid64_ds *s,
@@ -207,17 +207,17 @@ static inline int get_compat_semid_ds(struct semid64_ds *s,
 	return __get_compat_ipc_perm(&s->sem_perm, &up->sem_perm);
 }
 
-static inline int put_compat_semid64_ds(struct semid64_ds *s64,
+static inline int put_compat_semid64_ds(struct semid64_ds *sem64,
 					struct compat_semid64_ds __user *up64)
 {
 	int err;
 
 	if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64)))
 		return -EFAULT;
-	err  = __put_compat_ipc64_perm(&s64->sem_perm, &up64->sem_perm);
-	err |= __put_user(s64->sem_otime, &up64->sem_otime);
-	err |= __put_user(s64->sem_ctime, &up64->sem_ctime);
-	err |= __put_user(s64->sem_nsems, &up64->sem_nsems);
+	err  = __put_compat_ipc64_perm(&sem64->sem_perm, &up64->sem_perm);
+	err |= __put_user(sem64->sem_otime, &up64->sem_otime);
+	err |= __put_user(sem64->sem_ctime, &up64->sem_ctime);
+	err |= __put_user(sem64->sem_nsems, &up64->sem_nsems);
 	return err;
 }
 
@@ -239,11 +239,11 @@ static long do_compat_semctl(int first, int second, int third, u32 pad)
 {
 	unsigned long fourth;
 	int err, err2;
-	struct semid64_ds s64;
+	struct semid64_ds sem64;
 	struct semid64_ds __user *up64;
 	int version = compat_ipc_parse_version(&third);
 
-	memset(&s64, 0, sizeof(s64));
+	memset(&sem64, 0, sizeof(sem64));
 
 	if ((third & (~IPC_64)) == SETVAL)
 #ifdef __BIG_ENDIAN
@@ -269,29 +269,29 @@ static long do_compat_semctl(int first, int second, int third, u32 pad)
 
 	case IPC_STAT:
 	case SEM_STAT:
-		up64 = compat_alloc_user_space(sizeof(s64));
+		up64 = compat_alloc_user_space(sizeof(sem64));
 		fourth = (unsigned long)up64;
 		err = sys_semctl(first, second, third, fourth);
 		if (err < 0)
 			break;
-		if (copy_from_user(&s64, up64, sizeof(s64)))
+		if (copy_from_user(&sem64, up64, sizeof(sem64)))
 			err2 = -EFAULT;
 		else if (version == IPC_64)
-			err2 = put_compat_semid64_ds(&s64, compat_ptr(pad));
+			err2 = put_compat_semid64_ds(&sem64, compat_ptr(pad));
 		else
-			err2 = put_compat_semid_ds(&s64, compat_ptr(pad));
+			err2 = put_compat_semid_ds(&sem64, compat_ptr(pad));
 		if (err2)
 			err = -EFAULT;
 		break;
 
 	case IPC_SET:
 		if (version == IPC_64)
-			err = get_compat_semid64_ds(&s64, compat_ptr(pad));
+			err = get_compat_semid64_ds(&sem64, compat_ptr(pad));
 		else
-			err = get_compat_semid_ds(&s64, compat_ptr(pad));
+			err = get_compat_semid_ds(&sem64, compat_ptr(pad));
 
-		up64 = compat_alloc_user_space(sizeof(s64));
-		if (copy_to_user(up64, &s64, sizeof(s64)))
+		up64 = compat_alloc_user_space(sizeof(sem64));
+		if (copy_to_user(up64, &sem64, sizeof(sem64)))
 			err = -EFAULT;
 		if (err)
 			break;
@@ -561,12 +561,12 @@ COMPAT_SYSCALL_DEFINE3(shmat, int, shmid, compat_uptr_t, shmaddr, int, shmflg)
 	return (long)ret;
 }
 
-static inline int get_compat_shmid64_ds(struct shmid64_ds *s64,
+static inline int get_compat_shmid64_ds(struct shmid64_ds *sem64,
 					struct compat_shmid64_ds __user *up64)
 {
 	if (!access_ok(VERIFY_READ, up64, sizeof(*up64)))
 		return -EFAULT;
-	return __get_compat_ipc64_perm(&s64->shm_perm, &up64->shm_perm);
+	return __get_compat_ipc64_perm(&sem64->shm_perm, &up64->shm_perm);
 }
 
 static inline int get_compat_shmid_ds(struct shmid64_ds *s,
@@ -577,21 +577,21 @@ static inline int get_compat_shmid_ds(struct shmid64_ds *s,
 	return __get_compat_ipc_perm(&s->shm_perm, &up->shm_perm);
 }
 
-static inline int put_compat_shmid64_ds(struct shmid64_ds *s64,
+static inline int put_compat_shmid64_ds(struct shmid64_ds *sem64,
 					struct compat_shmid64_ds __user *up64)
 {
 	int err;
 
 	if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64)))
 		return -EFAULT;
-	err  = __put_compat_ipc64_perm(&s64->shm_perm, &up64->shm_perm);
-	err |= __put_user(s64->shm_atime, &up64->shm_atime);
-	err |= __put_user(s64->shm_dtime, &up64->shm_dtime);
-	err |= __put_user(s64->shm_ctime, &up64->shm_ctime);
-	err |= __put_user(s64->shm_segsz, &up64->shm_segsz);
-	err |= __put_user(s64->shm_nattch, &up64->shm_nattch);
-	err |= __put_user(s64->shm_cpid, &up64->shm_cpid);
-	err |= __put_user(s64->shm_lpid, &up64->shm_lpid);
+	err  = __put_compat_ipc64_perm(&sem64->shm_perm, &up64->shm_perm);
+	err |= __put_user(sem64->shm_atime, &up64->shm_atime);
+	err |= __put_user(sem64->shm_dtime, &up64->shm_dtime);
+	err |= __put_user(sem64->shm_ctime, &up64->shm_ctime);
+	err |= __put_user(sem64->shm_segsz, &up64->shm_segsz);
+	err |= __put_user(sem64->shm_nattch, &up64->shm_nattch);
+	err |= __put_user(sem64->shm_cpid, &up64->shm_cpid);
+	err |= __put_user(sem64->shm_lpid, &up64->shm_lpid);
 	return err;
 }
 
@@ -668,12 +668,12 @@ static inline int put_compat_shm_info(struct shm_info __user *ip,
 COMPAT_SYSCALL_DEFINE3(shmctl, int, first, int, second, void __user *, uptr)
 {
 	void __user *p;
-	struct shmid64_ds s64;
+	struct shmid64_ds sem64;
 	struct shminfo64 smi;
 	int err, err2;
 	int version = compat_ipc_parse_version(&second);
 
-	memset(&s64, 0, sizeof(s64));
+	memset(&sem64, 0, sizeof(sem64));
 
 	switch (second & (~IPC_64)) {
 	case IPC_RMID:
@@ -700,14 +700,14 @@ COMPAT_SYSCALL_DEFINE3(shmctl, int, first, int, second, void __user *, uptr)
 
 	case IPC_SET:
 		if (version == IPC_64)
-			err = get_compat_shmid64_ds(&s64, uptr);
+			err = get_compat_shmid64_ds(&sem64, uptr);
 		else
-			err = get_compat_shmid_ds(&s64, uptr);
+			err = get_compat_shmid_ds(&sem64, uptr);
 
 		if (err)
 			break;
-		p = compat_alloc_user_space(sizeof(s64));
-		if (copy_to_user(p, &s64, sizeof(s64)))
+		p = compat_alloc_user_space(sizeof(sem64));
+		if (copy_to_user(p, &sem64, sizeof(sem64)))
 			err = -EFAULT;
 		else
 			err = sys_shmctl(first, second, p);
@@ -715,16 +715,16 @@ COMPAT_SYSCALL_DEFINE3(shmctl, int, first, int, second, void __user *, uptr)
 
 	case IPC_STAT:
 	case SHM_STAT:
-		p = compat_alloc_user_space(sizeof(s64));
+		p = compat_alloc_user_space(sizeof(sem64));
 		err = sys_shmctl(first, second, p);
 		if (err < 0)
 			break;
-		if (copy_from_user(&s64, p, sizeof(s64)))
+		if (copy_from_user(&sem64, p, sizeof(sem64)))
 			err2 = -EFAULT;
 		else if (version == IPC_64)
-			err2 = put_compat_shmid64_ds(&s64, uptr);
+			err2 = put_compat_shmid64_ds(&sem64, uptr);
 		else
-			err2 = put_compat_shmid_ds(&s64, uptr);
+			err2 = put_compat_shmid_ds(&sem64, uptr);
 		if (err2)
 			err = -EFAULT;
 		break;
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index c3f0326e98db..e8075b247497 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -123,7 +123,6 @@ static int proc_ipcauto_dointvec_minmax(struct ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table ipc_table;
-	size_t lenp_bef = *lenp;
 	int oldval;
 	int rc;
 
@@ -133,7 +132,7 @@ static int proc_ipcauto_dointvec_minmax(struct ctl_table *table, int write,
 
 	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 
-	if (write && !rc && lenp_bef == *lenp) {
+	if (write && !rc) {
 		int newval = *((int *)(ipc_table.data));
 		/*
 		 * The file "auto_msgmni" has correctly been set.
diff --git a/ipc/shm.c b/ipc/shm.c
index 7fc9f9f3a26b..01454796ba3c 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1172,13 +1172,6 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
 
 		if (find_vma_intersection(current->mm, addr, addr + size))
 			goto invalid;
-		/*
-		 * If shm segment goes below stack, make sure there is some
-		 * space left for the stack to grow (at least 4 pages).
-		 */
-		if (addr < current->mm->start_stack &&
-		    addr > current->mm->start_stack - size - PAGE_SIZE * 5)
-			goto invalid;
 	}
 
 	addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate);
diff --git a/ipc/util.c b/ipc/util.c
index d73b7af581e2..88adc329888c 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -892,28 +892,16 @@ static const struct seq_operations sysvipc_proc_seqops = {
 
 static int sysvipc_proc_open(struct inode *inode, struct file *file)
 {
-	int ret;
-	struct seq_file *seq;
 	struct ipc_proc_iter *iter;
 
-	ret = -ENOMEM;
-	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+	iter = __seq_open_private(file, &sysvipc_proc_seqops, sizeof(*iter));
 	if (!iter)
-		goto out;
-
-	ret = seq_open(file, &sysvipc_proc_seqops);
-	if (ret) {
-		kfree(iter);
-		goto out;
-	}
-
-	seq = file->private_data;
-	seq->private = iter;
+		return -ENOMEM;
 
 	iter->iface = PDE_DATA(inode);
 	iter->ns    = get_ipc_ns(current->nsproxy->ipc_ns);
-out:
-	return ret;
+
+	return 0;
 }
 
 static int sysvipc_proc_release(struct inode *inode, struct file *file)
diff --git a/kernel/acct.c b/kernel/acct.c
index b4c667d22e79..33738ef972f3 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -472,7 +472,6 @@ static void do_acct_process(struct bsd_acct_struct *acct)
 	acct_t ac;
 	unsigned long flim;
 	const struct cred *orig_cred;
-	struct pid_namespace *ns = acct->ns;
 	struct file *file = acct->file;
 
 	/*
@@ -500,10 +499,15 @@ static void do_acct_process(struct bsd_acct_struct *acct)
 	ac.ac_gid16 = ac.ac_gid;
 #endif
 #if ACCT_VERSION == 3
-	ac.ac_pid = task_tgid_nr_ns(current, ns);
-	rcu_read_lock();
-	ac.ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), ns);
-	rcu_read_unlock();
+	{
+		struct pid_namespace *ns = acct->ns;
+
+		ac.ac_pid = task_tgid_nr_ns(current, ns);
+		rcu_read_lock();
+		ac.ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent),
+					     ns);
+		rcu_read_unlock();
+	}
 #endif
 	/*
 	 * Get freeze protection. If the fs is frozen, just skip the write
diff --git a/kernel/async.c b/kernel/async.c
index 61f023ce0228..4c3773c0bf63 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -115,7 +115,7 @@ static void async_run_entry_fn(struct work_struct *work)
 
 	/* 1) run (and print duration) */
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
-		printk(KERN_DEBUG "calling  %lli_%pF @ %i\n",
+		pr_debug("calling  %lli_%pF @ %i\n",
 			(long long)entry->cookie,
 			entry->func, task_pid_nr(current));
 		calltime = ktime_get();
@@ -124,7 +124,7 @@ static void async_run_entry_fn(struct work_struct *work)
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
 		rettime = ktime_get();
 		delta = ktime_sub(rettime, calltime);
-		printk(KERN_DEBUG "initcall %lli_%pF returned 0 after %lld usecs\n",
+		pr_debug("initcall %lli_%pF returned 0 after %lld usecs\n",
 			(long long)entry->cookie,
 			entry->func,
 			(long long)ktime_to_ns(delta) >> 10);
@@ -285,7 +285,7 @@ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain
 	ktime_t uninitialized_var(starttime), delta, endtime;
 
 	if (initcall_debug && system_state == SYSTEM_BOOTING) {
-		printk(KERN_DEBUG "async_waiting @ %i\n", task_pid_nr(current));
+		pr_debug("async_waiting @ %i\n", task_pid_nr(current));
 		starttime = ktime_get();
 	}
 
@@ -295,7 +295,7 @@ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain
 		endtime = ktime_get();
 		delta = ktime_sub(endtime, starttime);
 
-		printk(KERN_DEBUG "async_continuing @ %i after %lli usec\n",
+		pr_debug("async_continuing @ %i after %lli usec\n",
 			task_pid_nr(current),
 			(long long)ktime_to_ns(delta) >> 10);
 	}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 3a73f995a81e..136eceadeed1 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -185,7 +185,6 @@ static int need_forkexit_callback __read_mostly;
 static struct cftype cgroup_dfl_base_files[];
 static struct cftype cgroup_legacy_base_files[];
 
-static void cgroup_put(struct cgroup *cgrp);
 static int rebind_subsystems(struct cgroup_root *dst_root,
 			     unsigned int ss_mask);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
@@ -195,7 +194,6 @@ static void css_release(struct percpu_ref *ref);
 static void kill_css(struct cgroup_subsys_state *css);
 static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
 			      bool is_add);
-static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
 
 /* IDR wrappers which synchronize using cgroup_idr_lock */
 static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end,
@@ -331,14 +329,6 @@ bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor)
 	return false;
 }
 
-static int cgroup_is_releasable(const struct cgroup *cgrp)
-{
-	const int bits =
-		(1 << CGRP_RELEASABLE) |
-		(1 << CGRP_NOTIFY_ON_RELEASE);
-	return (cgrp->flags & bits) == bits;
-}
-
 static int notify_on_release(const struct cgroup *cgrp)
 {
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -394,12 +384,7 @@ static int notify_on_release(const struct cgroup *cgrp)
 			;						\
 		else
 
-/* the list of cgroups eligible for automatic release. Protected by
- * release_list_lock */
-static LIST_HEAD(release_list);
-static DEFINE_RAW_SPINLOCK(release_list_lock);
 static void cgroup_release_agent(struct work_struct *work);
-static DECLARE_WORK(release_agent_work, cgroup_release_agent);
 static void check_for_release(struct cgroup *cgrp);
 
 /*
@@ -498,7 +483,7 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
 	return key;
 }
 
-static void put_css_set_locked(struct css_set *cset, bool taskexit)
+static void put_css_set_locked(struct css_set *cset)
 {
 	struct cgrp_cset_link *link, *tmp_link;
 	struct cgroup_subsys *ss;
@@ -524,11 +509,7 @@ static void put_css_set_locked(struct css_set *cset, bool taskexit)
 		/* @cgrp can't go away while we're holding css_set_rwsem */
 		if (list_empty(&cgrp->cset_links)) {
 			cgroup_update_populated(cgrp, false);
-			if (notify_on_release(cgrp)) {
-				if (taskexit)
-					set_bit(CGRP_RELEASABLE, &cgrp->flags);
-				check_for_release(cgrp);
-			}
+			check_for_release(cgrp);
 		}
 
 		kfree(link);
@@ -537,7 +518,7 @@ static void put_css_set_locked(struct css_set *cset, bool taskexit)
 	kfree_rcu(cset, rcu_head);
 }
 
-static void put_css_set(struct css_set *cset, bool taskexit)
+static void put_css_set(struct css_set *cset)
 {
 	/*
 	 * Ensure that the refcount doesn't hit zero while any readers
@@ -548,7 +529,7 @@ static void put_css_set(struct css_set *cset, bool taskexit)
 		return;
 
 	down_write(&css_set_rwsem);
-	put_css_set_locked(cset, taskexit);
+	put_css_set_locked(cset);
 	up_write(&css_set_rwsem);
 }
 
@@ -969,14 +950,6 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  * knows that the cgroup won't be removed, as cgroup_rmdir()
  * needs that mutex.
  *
- * The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't
- * (usually) take cgroup_mutex.  These are the two most performance
- * critical pieces of code here.  The exception occurs on cgroup_exit(),
- * when a task in a notify_on_release cgroup exits.  Then cgroup_mutex
- * is taken, and if the cgroup count is zero, a usermode call made
- * to the release agent with the name of the cgroup (path relative to
- * the root of cgroup file system) as the argument.
- *
  * A cgroup can only be deleted if both its 'count' of using tasks
  * is zero, and its list of 'children' cgroups is empty.  Since all
  * tasks in the system use _some_ cgroup, and since there is always at
@@ -1587,7 +1560,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_LIST_HEAD(&cgrp->self.sibling);
 	INIT_LIST_HEAD(&cgrp->self.children);
 	INIT_LIST_HEAD(&cgrp->cset_links);
-	INIT_LIST_HEAD(&cgrp->release_list);
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
 	cgrp->self.cgroup = cgrp;
@@ -1597,6 +1569,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 		INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
 
 	init_waitqueue_head(&cgrp->offline_waitq);
+	INIT_WORK(&cgrp->release_agent_work, cgroup_release_agent);
 }
 
 static void init_cgroup_root(struct cgroup_root *root,
@@ -1634,7 +1607,8 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned int ss_mask)
 		goto out;
 	root_cgrp->id = ret;
 
-	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release);
+	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0,
+			      GFP_KERNEL);
 	if (ret)
 		goto out;
 
@@ -2052,8 +2026,7 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
 	 * task. As trading it for new_cset is protected by cgroup_mutex,
 	 * we're safe to drop it here; it will be freed under RCU.
 	 */
-	set_bit(CGRP_RELEASABLE, &old_cgrp->flags);
-	put_css_set_locked(old_cset, false);
+	put_css_set_locked(old_cset);
 }
 
 /**
@@ -2074,7 +2047,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
 		cset->mg_src_cgrp = NULL;
 		cset->mg_dst_cset = NULL;
 		list_del_init(&cset->mg_preload_node);
-		put_css_set_locked(cset, false);
+		put_css_set_locked(cset);
 	}
 	up_write(&css_set_rwsem);
 }
@@ -2168,8 +2141,8 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp,
 		if (src_cset == dst_cset) {
 			src_cset->mg_src_cgrp = NULL;
 			list_del_init(&src_cset->mg_preload_node);
-			put_css_set(src_cset, false);
-			put_css_set(dst_cset, false);
+			put_css_set(src_cset);
+			put_css_set(dst_cset);
 			continue;
 		}
 
@@ -2178,7 +2151,7 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp,
 		if (list_empty(&dst_cset->mg_preload_node))
 			list_add(&dst_cset->mg_preload_node, &csets);
 		else
-			put_css_set(dst_cset, false);
+			put_css_set(dst_cset);
 	}
 
 	list_splice_tail(&csets, preloaded_csets);
@@ -4173,7 +4146,6 @@ static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
 static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
 					  struct cftype *cft, u64 val)
 {
-	clear_bit(CGRP_RELEASABLE, &css->cgroup->flags);
 	if (val)
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags);
 	else
@@ -4351,6 +4323,7 @@ static void css_free_work_fn(struct work_struct *work)
 		/* cgroup free path */
 		atomic_dec(&cgrp->root->nr_cgrps);
 		cgroup_pidlist_destroy_all(cgrp);
+		cancel_work_sync(&cgrp->release_agent_work);
 
 		if (cgroup_parent(cgrp)) {
 			/*
@@ -4510,7 +4483,7 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
 
 	init_and_link_css(css, ss, cgrp);
 
-	err = percpu_ref_init(&css->refcnt, css_release);
+	err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL);
 	if (err)
 		goto err_free_css;
 
@@ -4583,7 +4556,7 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 		goto out_unlock;
 	}
 
-	ret = percpu_ref_init(&cgrp->self.refcnt, css_release);
+	ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL);
 	if (ret)
 		goto out_free_cgrp;
 
@@ -4813,19 +4786,12 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	for_each_css(css, ssid, cgrp)
 		kill_css(css);
 
-	/* CSS_ONLINE is clear, remove from ->release_list for the last time */
-	raw_spin_lock(&release_list_lock);
-	if (!list_empty(&cgrp->release_list))
-		list_del_init(&cgrp->release_list);
-	raw_spin_unlock(&release_list_lock);
-
 	/*
 	 * Remove @cgrp directory along with the base files.  @cgrp has an
 	 * extra ref on its kn.
 	 */
 	kernfs_remove(cgrp->kn);
 
-	set_bit(CGRP_RELEASABLE, &cgroup_parent(cgrp)->flags);
 	check_for_release(cgroup_parent(cgrp));
 
 	/* put the base reference */
@@ -4842,13 +4808,10 @@ static int cgroup_rmdir(struct kernfs_node *kn)
 	cgrp = cgroup_kn_lock_live(kn);
 	if (!cgrp)
 		return 0;
-	cgroup_get(cgrp);	/* for @kn->priv clearing */
 
 	ret = cgroup_destroy_locked(cgrp);
 
 	cgroup_kn_unlock(kn);
-
-	cgroup_put(cgrp);
 	return ret;
 }
 
@@ -5052,12 +5015,9 @@ core_initcall(cgroup_wq_init);
  *  - Print task's cgroup paths into seq_file, one line for each hierarchy
  *  - Used for /proc/<pid>/cgroup.
  */
-
-/* TODO: Use a proper seq_file iterator */
-int proc_cgroup_show(struct seq_file *m, void *v)
+int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
+		     struct pid *pid, struct task_struct *tsk)
 {
-	struct pid *pid;
-	struct task_struct *tsk;
 	char *buf, *path;
 	int retval;
 	struct cgroup_root *root;
@@ -5067,14 +5027,6 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 	if (!buf)
 		goto out;
 
-	retval = -ESRCH;
-	pid = m->private;
-	tsk = get_pid_task(pid, PIDTYPE_PID);
-	if (!tsk)
-		goto out_free;
-
-	retval = 0;
-
 	mutex_lock(&cgroup_mutex);
 	down_read(&css_set_rwsem);
 
@@ -5104,11 +5056,10 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 		seq_putc(m, '\n');
 	}
 
+	retval = 0;
 out_unlock:
 	up_read(&css_set_rwsem);
 	mutex_unlock(&cgroup_mutex);
-	put_task_struct(tsk);
-out_free:
 	kfree(buf);
 out:
 	return retval;
@@ -5179,7 +5130,7 @@ void cgroup_post_fork(struct task_struct *child)
 	int i;
 
 	/*
-	 * This may race against cgroup_enable_task_cg_links().  As that
+	 * This may race against cgroup_enable_task_cg_lists().  As that
 	 * function sets use_task_css_set_links before grabbing
 	 * tasklist_lock and we just went through tasklist_lock to add
 	 * @child, it's guaranteed that either we see the set
@@ -5194,7 +5145,7 @@ void cgroup_post_fork(struct task_struct *child)
 	 * when implementing operations which need to migrate all tasks of
 	 * a cgroup to another.
 	 *
-	 * Note that if we lose to cgroup_enable_task_cg_links(), @child
+	 * Note that if we lose to cgroup_enable_task_cg_lists(), @child
 	 * will remain in init_css_set.  This is safe because all tasks are
 	 * in the init_css_set before cg_links is enabled and there's no
 	 * operation which transfers all tasks out of init_css_set.
@@ -5278,30 +5229,14 @@ void cgroup_exit(struct task_struct *tsk)
 	}
 
 	if (put_cset)
-		put_css_set(cset, true);
+		put_css_set(cset);
 }
 
 static void check_for_release(struct cgroup *cgrp)
 {
-	if (cgroup_is_releasable(cgrp) && list_empty(&cgrp->cset_links) &&
-	    !css_has_online_children(&cgrp->self)) {
-		/*
-		 * Control Group is currently removeable. If it's not
-		 * already queued for a userspace notification, queue
-		 * it now
-		 */
-		int need_schedule_work = 0;
-
-		raw_spin_lock(&release_list_lock);
-		if (!cgroup_is_dead(cgrp) &&
-		    list_empty(&cgrp->release_list)) {
-			list_add(&cgrp->release_list, &release_list);
-			need_schedule_work = 1;
-		}
-		raw_spin_unlock(&release_list_lock);
-		if (need_schedule_work)
-			schedule_work(&release_agent_work);
-	}
+	if (notify_on_release(cgrp) && !cgroup_has_tasks(cgrp) &&
+	    !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp))
+		schedule_work(&cgrp->release_agent_work);
 }
 
 /*
@@ -5329,52 +5264,39 @@ static void check_for_release(struct cgroup *cgrp)
  */
 static void cgroup_release_agent(struct work_struct *work)
 {
-	BUG_ON(work != &release_agent_work);
+	struct cgroup *cgrp =
+		container_of(work, struct cgroup, release_agent_work);
+	char *pathbuf = NULL, *agentbuf = NULL, *path;
+	char *argv[3], *envp[3];
+
 	mutex_lock(&cgroup_mutex);
-	raw_spin_lock(&release_list_lock);
-	while (!list_empty(&release_list)) {
-		char *argv[3], *envp[3];
-		int i;
-		char *pathbuf = NULL, *agentbuf = NULL, *path;
-		struct cgroup *cgrp = list_entry(release_list.next,
-						    struct cgroup,
-						    release_list);
-		list_del_init(&cgrp->release_list);
-		raw_spin_unlock(&release_list_lock);
-		pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
-		if (!pathbuf)
-			goto continue_free;
-		path = cgroup_path(cgrp, pathbuf, PATH_MAX);
-		if (!path)
-			goto continue_free;
-		agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
-		if (!agentbuf)
-			goto continue_free;
-
-		i = 0;
-		argv[i++] = agentbuf;
-		argv[i++] = path;
-		argv[i] = NULL;
-
-		i = 0;
-		/* minimal command environment */
-		envp[i++] = "HOME=/";
-		envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
-		envp[i] = NULL;
-
-		/* Drop the lock while we invoke the usermode helper,
-		 * since the exec could involve hitting disk and hence
-		 * be a slow process */
-		mutex_unlock(&cgroup_mutex);
-		call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
-		mutex_lock(&cgroup_mutex);
- continue_free:
-		kfree(pathbuf);
-		kfree(agentbuf);
-		raw_spin_lock(&release_list_lock);
-	}
-	raw_spin_unlock(&release_list_lock);
+
+	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
+	agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
+	if (!pathbuf || !agentbuf)
+		goto out;
+
+	path = cgroup_path(cgrp, pathbuf, PATH_MAX);
+	if (!path)
+		goto out;
+
+	argv[0] = agentbuf;
+	argv[1] = path;
+	argv[2] = NULL;
+
+	/* minimal command environment */
+	envp[0] = "HOME=/";
+	envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
+	envp[2] = NULL;
+
+	mutex_unlock(&cgroup_mutex);
+	call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+	goto out_free;
+out:
 	mutex_unlock(&cgroup_mutex);
+out_free:
+	kfree(agentbuf);
+	kfree(pathbuf);
 }
 
 static int __init cgroup_disable(char *str)
@@ -5562,7 +5484,8 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
 
 static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft)
 {
-	return test_bit(CGRP_RELEASABLE, &css->cgroup->flags);
+	return (!cgroup_has_tasks(css->cgroup) &&
+		!css_has_online_children(&css->cgroup->self));
 }
 
 static struct cftype debug_files[] =  {
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 81e2a388a0f6..356450f09c1f 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -79,6 +79,8 @@ static struct {
 
 /* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */
 #define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map)
+#define cpuhp_lock_acquire_tryread() \
+				  lock_map_acquire_tryread(&cpu_hotplug.dep_map)
 #define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
 #define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)
 
@@ -91,10 +93,22 @@ void get_online_cpus(void)
 	mutex_lock(&cpu_hotplug.lock);
 	cpu_hotplug.refcount++;
 	mutex_unlock(&cpu_hotplug.lock);
-
 }
 EXPORT_SYMBOL_GPL(get_online_cpus);
 
+bool try_get_online_cpus(void)
+{
+	if (cpu_hotplug.active_writer == current)
+		return true;
+	if (!mutex_trylock(&cpu_hotplug.lock))
+		return false;
+	cpuhp_lock_acquire_tryread();
+	cpu_hotplug.refcount++;
+	mutex_unlock(&cpu_hotplug.lock);
+	return true;
+}
+EXPORT_SYMBOL_GPL(try_get_online_cpus);
+
 void put_online_cpus(void)
 {
 	if (cpu_hotplug.active_writer == current)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 52cb04c993b7..1f107c74087b 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2730,10 +2730,9 @@ void __cpuset_memory_pressure_bump(void)
  *    and we take cpuset_mutex, keeping cpuset_attach() from changing it
  *    anyway.
  */
-int proc_cpuset_show(struct seq_file *m, void *unused_v)
+int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
+		     struct pid *pid, struct task_struct *tsk)
 {
-	struct pid *pid;
-	struct task_struct *tsk;
 	char *buf, *p;
 	struct cgroup_subsys_state *css;
 	int retval;
@@ -2743,24 +2742,16 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v)
 	if (!buf)
 		goto out;
 
-	retval = -ESRCH;
-	pid = m->private;
-	tsk = get_pid_task(pid, PIDTYPE_PID);
-	if (!tsk)
-		goto out_free;
-
 	retval = -ENAMETOOLONG;
 	rcu_read_lock();
 	css = task_css(tsk, cpuset_cgrp_id);
 	p = cgroup_path(css->cgroup, buf, PATH_MAX);
 	rcu_read_unlock();
 	if (!p)
-		goto out_put_task;
+		goto out_free;
 	seq_puts(m, p);
 	seq_putc(m, '\n');
 	retval = 0;
-out_put_task:
-	put_task_struct(tsk);
 out_free:
 	kfree(buf);
 out:
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index 70a504601dc3..b20d544f20c2 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -52,11 +52,11 @@ static int kdb_parsebp(int argc, const char **argv, int *nextargp, kdb_bp_t *bp)
 
 	bp->bph_length = 1;
 	if ((argc + 1) != nextarg) {
-		if (strnicmp(argv[nextarg], "datar", sizeof("datar")) == 0)
+		if (strncasecmp(argv[nextarg], "datar", sizeof("datar")) == 0)
 			bp->bp_type = BP_ACCESS_WATCHPOINT;
-		else if (strnicmp(argv[nextarg], "dataw", sizeof("dataw")) == 0)
+		else if (strncasecmp(argv[nextarg], "dataw", sizeof("dataw")) == 0)
 			bp->bp_type = BP_WRITE_WATCHPOINT;
-		else if (strnicmp(argv[nextarg], "inst", sizeof("inst")) == 0)
+		else if (strncasecmp(argv[nextarg], "inst", sizeof("inst")) == 0)
 			bp->bp_type = BP_HARDWARE_BREAKPOINT;
 		else
 			return KDB_ARGCOUNT;
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 97b67df8fbfe..d659487254d5 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -52,7 +52,7 @@ static void release_callchain_buffers(void)
 	struct callchain_cpus_entries *entries;
 
 	entries = callchain_cpus_entries;
-	rcu_assign_pointer(callchain_cpus_entries, NULL);
+	RCU_INIT_POINTER(callchain_cpus_entries, NULL);
 	call_rcu(&entries->rcu_head, release_callchain_buffers_rcu);
 }
 
@@ -137,7 +137,7 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
 	int cpu;
 	struct callchain_cpus_entries *entries;
 
-	*rctx = get_recursion_context(__get_cpu_var(callchain_recursion));
+	*rctx = get_recursion_context(this_cpu_ptr(callchain_recursion));
 	if (*rctx == -1)
 		return NULL;
 
@@ -153,7 +153,7 @@ static struct perf_callchain_entry *get_callchain_entry(int *rctx)
 static void
 put_callchain_entry(int rctx)
 {
-	put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
+	put_recursion_context(this_cpu_ptr(callchain_recursion), rctx);
 }
 
 struct perf_callchain_entry *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 963bf139e2b2..1425d07018de 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -47,6 +47,8 @@
 
 #include <asm/irq_regs.h>
 
+static struct workqueue_struct *perf_wq;
+
 struct remote_function_call {
 	struct task_struct	*p;
 	int			(*func)(void *info);
@@ -120,6 +122,13 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
 	return data.ret;
 }
 
+#define EVENT_OWNER_KERNEL ((void *) -1)
+
+static bool is_kernel_event(struct perf_event *event)
+{
+	return event->owner == EVENT_OWNER_KERNEL;
+}
+
 #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
 		       PERF_FLAG_FD_OUTPUT  |\
 		       PERF_FLAG_PID_CGROUP |\
@@ -240,7 +249,7 @@ static void perf_duration_warn(struct irq_work *w)
 	u64 avg_local_sample_len;
 	u64 local_samples_len;
 
-	local_samples_len = __get_cpu_var(running_sample_length);
+	local_samples_len = __this_cpu_read(running_sample_length);
 	avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
 
 	printk_ratelimited(KERN_WARNING
@@ -262,10 +271,10 @@ void perf_sample_event_took(u64 sample_len_ns)
 		return;
 
 	/* decay the counter by 1 average sample */
-	local_samples_len = __get_cpu_var(running_sample_length);
+	local_samples_len = __this_cpu_read(running_sample_length);
 	local_samples_len -= local_samples_len/NR_ACCUMULATED_SAMPLES;
 	local_samples_len += sample_len_ns;
-	__get_cpu_var(running_sample_length) = local_samples_len;
+	__this_cpu_write(running_sample_length, local_samples_len);
 
 	/*
 	 * note: this will be biased artifically low until we have
@@ -392,14 +401,9 @@ perf_cgroup_match(struct perf_event *event)
 				    event->cgrp->css.cgroup);
 }
 
-static inline void perf_put_cgroup(struct perf_event *event)
-{
-	css_put(&event->cgrp->css);
-}
-
 static inline void perf_detach_cgroup(struct perf_event *event)
 {
-	perf_put_cgroup(event);
+	css_put(&event->cgrp->css);
 	event->cgrp = NULL;
 }
 
@@ -878,7 +882,7 @@ static DEFINE_PER_CPU(struct list_head, rotation_list);
 static void perf_pmu_rotate_start(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-	struct list_head *head = &__get_cpu_var(rotation_list);
+	struct list_head *head = this_cpu_ptr(&rotation_list);
 
 	WARN_ON(!irqs_disabled());
 
@@ -902,13 +906,23 @@ static void put_ctx(struct perf_event_context *ctx)
 	}
 }
 
-static void unclone_ctx(struct perf_event_context *ctx)
+/*
+ * This must be done under the ctx->lock, such as to serialize against
+ * context_equiv(), therefore we cannot call put_ctx() since that might end up
+ * calling scheduler related locks and ctx->lock nests inside those.
+ */
+static __must_check struct perf_event_context *
+unclone_ctx(struct perf_event_context *ctx)
 {
-	if (ctx->parent_ctx) {
-		put_ctx(ctx->parent_ctx);
+	struct perf_event_context *parent_ctx = ctx->parent_ctx;
+
+	lockdep_assert_held(&ctx->lock);
+
+	if (parent_ctx)
 		ctx->parent_ctx = NULL;
-	}
 	ctx->generation++;
+
+	return parent_ctx;
 }
 
 static u32 perf_event_pid(struct perf_event *event, struct task_struct *p)
@@ -1375,6 +1389,45 @@ out:
 		perf_event__header_size(tmp);
 }
 
+/*
+ * User event without the task.
+ */
+static bool is_orphaned_event(struct perf_event *event)
+{
+	return event && !is_kernel_event(event) && !event->owner;
+}
+
+/*
+ * Event has a parent but parent's task finished and it's
+ * alive only because of children holding refference.
+ */
+static bool is_orphaned_child(struct perf_event *event)
+{
+	return is_orphaned_event(event->parent);
+}
+
+static void orphans_remove_work(struct work_struct *work);
+
+static void schedule_orphans_remove(struct perf_event_context *ctx)
+{
+	if (!ctx->task || ctx->orphans_remove_sched || !perf_wq)
+		return;
+
+	if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) {
+		get_ctx(ctx);
+		ctx->orphans_remove_sched = true;
+	}
+}
+
+static int __init perf_workqueue_init(void)
+{
+	perf_wq = create_singlethread_workqueue("perf");
+	WARN(!perf_wq, "failed to create perf workqueue\n");
+	return perf_wq ? 0 : -1;
+}
+
+core_initcall(perf_workqueue_init);
+
 static inline int
 event_filter_match(struct perf_event *event)
 {
@@ -1424,6 +1477,9 @@ event_sched_out(struct perf_event *event,
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
 		cpuctx->exclusive = 0;
 
+	if (is_orphaned_child(event))
+		schedule_orphans_remove(ctx);
+
 	perf_pmu_enable(event->pmu);
 }
 
@@ -1731,6 +1787,9 @@ event_sched_in(struct perf_event *event,
 	if (event->attr.exclusive)
 		cpuctx->exclusive = 1;
 
+	if (is_orphaned_child(event))
+		schedule_orphans_remove(ctx);
+
 out:
 	perf_pmu_enable(event->pmu);
 
@@ -2210,6 +2269,9 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 static int context_equiv(struct perf_event_context *ctx1,
 			 struct perf_event_context *ctx2)
 {
+	lockdep_assert_held(&ctx1->lock);
+	lockdep_assert_held(&ctx2->lock);
+
 	/* Pinning disables the swap optimization */
 	if (ctx1->pin_count || ctx2->pin_count)
 		return 0;
@@ -2331,7 +2393,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 	next_parent = rcu_dereference(next_ctx->parent_ctx);
 
 	/* If neither context have a parent context; they cannot be clones. */
-	if (!parent || !next_parent)
+	if (!parent && !next_parent)
 		goto unlock;
 
 	if (next_parent == ctx || next_ctx == parent || next_parent == parent) {
@@ -2400,7 +2462,7 @@ void __perf_event_task_sched_out(struct task_struct *task,
 	 * to check if we have to switch out PMU state.
 	 * cgroup event are system-wide mode only
 	 */
-	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
 		perf_cgroup_sched_out(task, next);
 }
 
@@ -2643,11 +2705,11 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	 * to check if we have to switch in PMU state.
 	 * cgroup event are system-wide mode only
 	 */
-	if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
+	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
 		perf_cgroup_sched_in(prev, task);
 
 	/* check for system-wide branch_stack events */
-	if (atomic_read(&__get_cpu_var(perf_branch_stack_events)))
+	if (atomic_read(this_cpu_ptr(&perf_branch_stack_events)))
 		perf_branch_stack_sched_in(prev, task);
 }
 
@@ -2902,7 +2964,7 @@ bool perf_event_can_stop_tick(void)
 
 void perf_event_task_tick(void)
 {
-	struct list_head *head = &__get_cpu_var(rotation_list);
+	struct list_head *head = this_cpu_ptr(&rotation_list);
 	struct perf_cpu_context *cpuctx, *tmp;
 	struct perf_event_context *ctx;
 	int throttled;
@@ -2943,6 +3005,7 @@ static int event_enable_on_exec(struct perf_event *event,
  */
 static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 {
+	struct perf_event_context *clone_ctx = NULL;
 	struct perf_event *event;
 	unsigned long flags;
 	int enabled = 0;
@@ -2974,7 +3037,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 	 * Unclone this context if we enabled any event.
 	 */
 	if (enabled)
-		unclone_ctx(ctx);
+		clone_ctx = unclone_ctx(ctx);
 
 	raw_spin_unlock(&ctx->lock);
 
@@ -2984,6 +3047,9 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 	perf_event_context_sched_in(ctx, ctx->task);
 out:
 	local_irq_restore(flags);
+
+	if (clone_ctx)
+		put_ctx(clone_ctx);
 }
 
 void perf_event_exec(void)
@@ -3078,6 +3144,7 @@ static void __perf_event_init_context(struct perf_event_context *ctx)
 	INIT_LIST_HEAD(&ctx->flexible_groups);
 	INIT_LIST_HEAD(&ctx->event_list);
 	atomic_set(&ctx->refcount, 1);
+	INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work);
 }
 
 static struct perf_event_context *
@@ -3135,7 +3202,7 @@ errout:
 static struct perf_event_context *
 find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 {
-	struct perf_event_context *ctx;
+	struct perf_event_context *ctx, *clone_ctx = NULL;
 	struct perf_cpu_context *cpuctx;
 	unsigned long flags;
 	int ctxn, err;
@@ -3169,9 +3236,12 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu)
 retry:
 	ctx = perf_lock_task_context(task, ctxn, &flags);
 	if (ctx) {
-		unclone_ctx(ctx);
+		clone_ctx = unclone_ctx(ctx);
 		++ctx->pin_count;
 		raw_spin_unlock_irqrestore(&ctx->lock, flags);
+
+		if (clone_ctx)
+			put_ctx(clone_ctx);
 	} else {
 		ctx = alloc_perf_context(pmu, task);
 		err = -ENOMEM;
@@ -3323,16 +3393,12 @@ static void free_event(struct perf_event *event)
 }
 
 /*
- * Called when the last reference to the file is gone.
+ * Remove user event from the owner task.
  */
-static void put_event(struct perf_event *event)
+static void perf_remove_from_owner(struct perf_event *event)
 {
-	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *owner;
 
-	if (!atomic_long_dec_and_test(&event->refcount))
-		return;
-
 	rcu_read_lock();
 	owner = ACCESS_ONCE(event->owner);
 	/*
@@ -3365,6 +3431,20 @@ static void put_event(struct perf_event *event)
 		mutex_unlock(&owner->perf_event_mutex);
 		put_task_struct(owner);
 	}
+}
+
+/*
+ * Called when the last reference to the file is gone.
+ */
+static void put_event(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+
+	if (!atomic_long_dec_and_test(&event->refcount))
+		return;
+
+	if (!is_kernel_event(event))
+		perf_remove_from_owner(event);
 
 	WARN_ON_ONCE(ctx->parent_ctx);
 	/*
@@ -3399,6 +3479,42 @@ static int perf_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+/*
+ * Remove all orphanes events from the context.
+ */
+static void orphans_remove_work(struct work_struct *work)
+{
+	struct perf_event_context *ctx;
+	struct perf_event *event, *tmp;
+
+	ctx = container_of(work, struct perf_event_context,
+			   orphans_remove.work);
+
+	mutex_lock(&ctx->mutex);
+	list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) {
+		struct perf_event *parent_event = event->parent;
+
+		if (!is_orphaned_child(event))
+			continue;
+
+		perf_remove_from_context(event, true);
+
+		mutex_lock(&parent_event->child_mutex);
+		list_del_init(&event->child_list);
+		mutex_unlock(&parent_event->child_mutex);
+
+		free_event(event);
+		put_event(parent_event);
+	}
+
+	raw_spin_lock_irq(&ctx->lock);
+	ctx->orphans_remove_sched = false;
+	raw_spin_unlock_irq(&ctx->lock);
+	mutex_unlock(&ctx->mutex);
+
+	put_ctx(ctx);
+}
+
 u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
 {
 	struct perf_event *child;
@@ -3496,6 +3612,19 @@ static int perf_event_read_one(struct perf_event *event,
 	return n * sizeof(u64);
 }
 
+static bool is_event_hup(struct perf_event *event)
+{
+	bool no_children;
+
+	if (event->state != PERF_EVENT_STATE_EXIT)
+		return false;
+
+	mutex_lock(&event->child_mutex);
+	no_children = list_empty(&event->child_list);
+	mutex_unlock(&event->child_mutex);
+	return no_children;
+}
+
 /*
  * Read the performance event - simple non blocking version for now
  */
@@ -3537,7 +3666,12 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 {
 	struct perf_event *event = file->private_data;
 	struct ring_buffer *rb;
-	unsigned int events = POLL_HUP;
+	unsigned int events = POLLHUP;
+
+	poll_wait(file, &event->waitq, wait);
+
+	if (is_event_hup(event))
+		return events;
 
 	/*
 	 * Pin the event->rb by taking event->mmap_mutex; otherwise
@@ -3548,9 +3682,6 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	if (rb)
 		events = atomic_xchg(&rb->poll, 0);
 	mutex_unlock(&event->mmap_mutex);
-
-	poll_wait(file, &event->waitq, wait);
-
 	return events;
 }
 
@@ -5702,7 +5833,7 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id,
 				    struct perf_sample_data *data,
 				    struct pt_regs *regs)
 {
-	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
 	struct perf_event *event;
 	struct hlist_head *head;
 
@@ -5721,7 +5852,7 @@ end:
 
 int perf_swevent_get_recursion_context(void)
 {
-	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
 
 	return get_recursion_context(swhash->recursion);
 }
@@ -5729,7 +5860,7 @@ EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
 
 inline void perf_swevent_put_recursion_context(int rctx)
 {
-	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
 
 	put_recursion_context(swhash->recursion, rctx);
 }
@@ -5758,7 +5889,7 @@ static void perf_swevent_read(struct perf_event *event)
 
 static int perf_swevent_add(struct perf_event *event, int flags)
 {
-	struct swevent_htable *swhash = &__get_cpu_var(swevent_htable);
+	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
 	struct hw_perf_event *hwc = &event->hw;
 	struct hlist_head *head;
 
@@ -5814,7 +5945,7 @@ static void swevent_hlist_release(struct swevent_htable *swhash)
 	if (!hlist)
 		return;
 
-	rcu_assign_pointer(swhash->swevent_hlist, NULL);
+	RCU_INIT_POINTER(swhash->swevent_hlist, NULL);
 	kfree_rcu(hlist, rcu_head);
 }
 
@@ -7397,6 +7528,9 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 		goto err;
 	}
 
+	/* Mark owner so we could distinguish it from user events. */
+	event->owner = EVENT_OWNER_KERNEL;
+
 	account_event(event);
 
 	ctx = find_get_context(event->pmu, task, cpu);
@@ -7484,6 +7618,12 @@ static void sync_child_event(struct perf_event *child_event,
 	mutex_unlock(&parent_event->child_mutex);
 
 	/*
+	 * Make sure user/parent get notified, that we just
+	 * lost one event.
+	 */
+	perf_event_wakeup(parent_event);
+
+	/*
 	 * Release the parent event, if this was the last
 	 * reference to it.
 	 */
@@ -7517,13 +7657,16 @@ __perf_event_exit_task(struct perf_event *child_event,
 	if (child_event->parent) {
 		sync_child_event(child_event, child);
 		free_event(child_event);
+	} else {
+		child_event->state = PERF_EVENT_STATE_EXIT;
+		perf_event_wakeup(child_event);
 	}
 }
 
 static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 {
 	struct perf_event *child_event, *next;
-	struct perf_event_context *child_ctx, *parent_ctx;
+	struct perf_event_context *child_ctx, *clone_ctx = NULL;
 	unsigned long flags;
 
 	if (likely(!child->perf_event_ctxp[ctxn])) {
@@ -7550,28 +7693,16 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	child->perf_event_ctxp[ctxn] = NULL;
 
 	/*
-	 * In order to avoid freeing: child_ctx->parent_ctx->task
-	 * under perf_event_context::lock, grab another reference.
-	 */
-	parent_ctx = child_ctx->parent_ctx;
-	if (parent_ctx)
-		get_ctx(parent_ctx);
-
-	/*
 	 * If this context is a clone; unclone it so it can't get
 	 * swapped to another process while we're removing all
 	 * the events from it.
 	 */
-	unclone_ctx(child_ctx);
+	clone_ctx = unclone_ctx(child_ctx);
 	update_context_time(child_ctx);
 	raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
 
-	/*
-	 * Now that we no longer hold perf_event_context::lock, drop
-	 * our extra child_ctx->parent_ctx reference.
-	 */
-	if (parent_ctx)
-		put_ctx(parent_ctx);
+	if (clone_ctx)
+		put_ctx(clone_ctx);
 
 	/*
 	 * Report the task dead after unscheduling the events so that we
@@ -7700,6 +7831,7 @@ inherit_event(struct perf_event *parent_event,
 	      struct perf_event *group_leader,
 	      struct perf_event_context *child_ctx)
 {
+	enum perf_event_active_state parent_state = parent_event->state;
 	struct perf_event *child_event;
 	unsigned long flags;
 
@@ -7720,7 +7852,8 @@ inherit_event(struct perf_event *parent_event,
 	if (IS_ERR(child_event))
 		return child_event;
 
-	if (!atomic_long_inc_not_zero(&parent_event->refcount)) {
+	if (is_orphaned_event(parent_event) ||
+	    !atomic_long_inc_not_zero(&parent_event->refcount)) {
 		free_event(child_event);
 		return NULL;
 	}
@@ -7732,7 +7865,7 @@ inherit_event(struct perf_event *parent_event,
 	 * not its attr.disabled bit.  We hold the parent's mutex,
 	 * so we won't race with perf_event_{en, dis}able_family.
 	 */
-	if (parent_event->state >= PERF_EVENT_STATE_INACTIVE)
+	if (parent_state >= PERF_EVENT_STATE_INACTIVE)
 		child_event->state = PERF_EVENT_STATE_INACTIVE;
 	else
 		child_event->state = PERF_EVENT_STATE_OFF;
diff --git a/kernel/exit.c b/kernel/exit.c
index 32c58f7433a3..5d30019ff953 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -115,32 +115,33 @@ static void __exit_signal(struct task_struct *tsk)
 
 		if (tsk == sig->curr_target)
 			sig->curr_target = next_thread(tsk);
-		/*
-		 * Accumulate here the counters for all threads but the
-		 * group leader as they die, so they can be added into
-		 * the process-wide totals when those are taken.
-		 * The group leader stays around as a zombie as long
-		 * as there are other threads.  When it gets reaped,
-		 * the exit.c code will add its counts into these totals.
-		 * We won't ever get here for the group leader, since it
-		 * will have been the last reference on the signal_struct.
-		 */
-		task_cputime(tsk, &utime, &stime);
-		sig->utime += utime;
-		sig->stime += stime;
-		sig->gtime += task_gtime(tsk);
-		sig->min_flt += tsk->min_flt;
-		sig->maj_flt += tsk->maj_flt;
-		sig->nvcsw += tsk->nvcsw;
-		sig->nivcsw += tsk->nivcsw;
-		sig->inblock += task_io_get_inblock(tsk);
-		sig->oublock += task_io_get_oublock(tsk);
-		task_io_accounting_add(&sig->ioac, &tsk->ioac);
-		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
 	}
 
+	/*
+	 * Accumulate here the counters for all threads but the group leader
+	 * as they die, so they can be added into the process-wide totals
+	 * when those are taken.  The group leader stays around as a zombie as
+	 * long as there are other threads.  When it gets reaped, the exit.c
+	 * code will add its counts into these totals.  We won't ever get here
+	 * for the group leader, since it will have been the last reference on
+	 * the signal_struct.
+	 */
+	task_cputime(tsk, &utime, &stime);
+	write_seqlock(&sig->stats_lock);
+	sig->utime += utime;
+	sig->stime += stime;
+	sig->gtime += task_gtime(tsk);
+	sig->min_flt += tsk->min_flt;
+	sig->maj_flt += tsk->maj_flt;
+	sig->nvcsw += tsk->nvcsw;
+	sig->nivcsw += tsk->nivcsw;
+	sig->inblock += task_io_get_inblock(tsk);
+	sig->oublock += task_io_get_oublock(tsk);
+	task_io_accounting_add(&sig->ioac, &tsk->ioac);
+	sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
 	sig->nr_threads--;
 	__unhash_process(tsk, group_dead);
+	write_sequnlock(&sig->stats_lock);
 
 	/*
 	 * Do this under ->siglock, we can race with another thread
@@ -667,6 +668,7 @@ void do_exit(long code)
 {
 	struct task_struct *tsk = current;
 	int group_dead;
+	TASKS_RCU(int tasks_rcu_i);
 
 	profile_task_exit(tsk);
 
@@ -775,6 +777,7 @@ void do_exit(long code)
 	 */
 	flush_ptrace_hw_breakpoint(tsk);
 
+	TASKS_RCU(tasks_rcu_i = __srcu_read_lock(&tasks_rcu_exit_srcu));
 	exit_notify(tsk, group_dead);
 	proc_exit_connector(tsk);
 #ifdef CONFIG_NUMA
@@ -814,6 +817,7 @@ void do_exit(long code)
 	if (tsk->nr_dirtied)
 		__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
 	exit_rcu();
+	TASKS_RCU(__srcu_read_unlock(&tasks_rcu_exit_srcu, tasks_rcu_i));
 
 	/*
 	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
@@ -1043,6 +1047,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		spin_lock_irq(&p->real_parent->sighand->siglock);
 		psig = p->real_parent->signal;
 		sig = p->signal;
+		write_seqlock(&psig->stats_lock);
 		psig->cutime += tgutime + sig->cutime;
 		psig->cstime += tgstime + sig->cstime;
 		psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime;
@@ -1065,6 +1070,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 			psig->cmaxrss = maxrss;
 		task_io_accounting_add(&psig->ioac, &p->ioac);
 		task_io_accounting_add(&psig->ioac, &sig->ioac);
+		write_sequnlock(&psig->stats_lock);
 		spin_unlock_irq(&p->real_parent->sighand->siglock);
 	}
 
diff --git a/kernel/fork.c b/kernel/fork.c
index a91e47d86de2..9b7d746d6d62 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -294,11 +294,18 @@ int __weak arch_dup_task_struct(struct task_struct *dst,
 	return 0;
 }
 
+void set_task_stack_end_magic(struct task_struct *tsk)
+{
+	unsigned long *stackend;
+
+	stackend = end_of_stack(tsk);
+	*stackend = STACK_END_MAGIC;	/* for overflow detection */
+}
+
 static struct task_struct *dup_task_struct(struct task_struct *orig)
 {
 	struct task_struct *tsk;
 	struct thread_info *ti;
-	unsigned long *stackend;
 	int node = tsk_fork_get_node(orig);
 	int err;
 
@@ -328,8 +335,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	setup_thread_stack(tsk, orig);
 	clear_user_return_notifier(tsk);
 	clear_tsk_need_resched(tsk);
-	stackend = end_of_stack(tsk);
-	*stackend = STACK_END_MAGIC;	/* for overflow detection */
+	set_task_stack_end_magic(tsk);
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 	tsk->stack_canary = get_random_int();
@@ -601,9 +607,8 @@ static void check_mm(struct mm_struct *mm)
 			printk(KERN_ALERT "BUG: Bad rss-counter state "
 					  "mm:%p idx:%d val:%ld\n", mm, i, x);
 	}
-
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
-	VM_BUG_ON(mm->pmd_huge_pte);
+	VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
 #endif
 }
 
@@ -1068,6 +1073,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
 	INIT_LIST_HEAD(&sig->posix_timers);
+	seqlock_init(&sig->stats_lock);
 
 	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	sig->real_timer.function = it_real_fn;
diff --git a/kernel/futex.c b/kernel/futex.c
index 815d7af2ffe8..f3a3a071283c 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -343,6 +343,8 @@ static void get_futex_key_refs(union futex_key *key)
 	case FUT_OFF_MMSHARED:
 		futex_get_mm(key); /* implies MB (B) */
 		break;
+	default:
+		smp_mb(); /* explicit MB (B) */
 	}
 }
 
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index d269cecdfbf0..225086b2652e 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -55,6 +55,9 @@ config GENERIC_IRQ_CHIP
 config IRQ_DOMAIN
 	bool
 
+config HANDLE_DOMAIN_IRQ
+	bool
+
 config IRQ_DOMAIN_DEBUG
 	bool "Expose hardware/virtual IRQ mapping via debugfs"
 	depends on IRQ_DOMAIN && DEBUG_FS
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 6223fab9a9d2..e5202f00cabc 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -342,6 +342,31 @@ static bool irq_check_poll(struct irq_desc *desc)
 	return irq_wait_for_poll(desc);
 }
 
+static bool irq_may_run(struct irq_desc *desc)
+{
+	unsigned int mask = IRQD_IRQ_INPROGRESS | IRQD_WAKEUP_ARMED;
+
+	/*
+	 * If the interrupt is not in progress and is not an armed
+	 * wakeup interrupt, proceed.
+	 */
+	if (!irqd_has_set(&desc->irq_data, mask))
+		return true;
+
+	/*
+	 * If the interrupt is an armed wakeup source, mark it pending
+	 * and suspended, disable it and notify the pm core about the
+	 * event.
+	 */
+	if (irq_pm_check_wakeup(desc))
+		return false;
+
+	/*
+	 * Handle a potential concurrent poll on a different core.
+	 */
+	return irq_check_poll(desc);
+}
+
 /**
  *	handle_simple_irq - Simple and software-decoded IRQs.
  *	@irq:	the interrupt number
@@ -359,9 +384,8 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 {
 	raw_spin_lock(&desc->lock);
 
-	if (unlikely(irqd_irq_inprogress(&desc->irq_data)))
-		if (!irq_check_poll(desc))
-			goto out_unlock;
+	if (!irq_may_run(desc))
+		goto out_unlock;
 
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
@@ -412,9 +436,8 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	raw_spin_lock(&desc->lock);
 	mask_ack_irq(desc);
 
-	if (unlikely(irqd_irq_inprogress(&desc->irq_data)))
-		if (!irq_check_poll(desc))
-			goto out_unlock;
+	if (!irq_may_run(desc))
+		goto out_unlock;
 
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
@@ -485,9 +508,8 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 
 	raw_spin_lock(&desc->lock);
 
-	if (unlikely(irqd_irq_inprogress(&desc->irq_data)))
-		if (!irq_check_poll(desc))
-			goto out;
+	if (!irq_may_run(desc))
+		goto out;
 
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
@@ -541,19 +563,23 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 	raw_spin_lock(&desc->lock);
 
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
+
+	if (!irq_may_run(desc)) {
+		desc->istate |= IRQS_PENDING;
+		mask_ack_irq(desc);
+		goto out_unlock;
+	}
+
 	/*
-	 * If we're currently running this IRQ, or its disabled,
-	 * we shouldn't process the IRQ. Mark it pending, handle
-	 * the necessary masking and go out
+	 * If its disabled or no action available then mask it and get
+	 * out of here.
 	 */
-	if (unlikely(irqd_irq_disabled(&desc->irq_data) ||
-		     irqd_irq_inprogress(&desc->irq_data) || !desc->action)) {
-		if (!irq_check_poll(desc)) {
-			desc->istate |= IRQS_PENDING;
-			mask_ack_irq(desc);
-			goto out_unlock;
-		}
+	if (irqd_irq_disabled(&desc->irq_data) || !desc->action) {
+		desc->istate |= IRQS_PENDING;
+		mask_ack_irq(desc);
+		goto out_unlock;
 	}
+
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/* Start handling the irq */
@@ -602,18 +628,21 @@ void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc)
 	raw_spin_lock(&desc->lock);
 
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
+
+	if (!irq_may_run(desc)) {
+		desc->istate |= IRQS_PENDING;
+		goto out_eoi;
+	}
+
 	/*
-	 * If we're currently running this IRQ, or its disabled,
-	 * we shouldn't process the IRQ. Mark it pending, handle
-	 * the necessary masking and go out
+	 * If its disabled or no action available then mask it and get
+	 * out of here.
 	 */
-	if (unlikely(irqd_irq_disabled(&desc->irq_data) ||
-		     irqd_irq_inprogress(&desc->irq_data) || !desc->action)) {
-		if (!irq_check_poll(desc)) {
-			desc->istate |= IRQS_PENDING;
-			goto out_eoi;
-		}
+	if (irqd_irq_disabled(&desc->irq_data) || !desc->action) {
+		desc->istate |= IRQS_PENDING;
+		goto out_eoi;
 	}
+
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	do {
@@ -670,7 +699,7 @@ void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct irqaction *action = desc->action;
-	void *dev_id = __this_cpu_ptr(action->percpu_dev_id);
+	void *dev_id = raw_cpu_ptr(action->percpu_dev_id);
 	irqreturn_t res;
 
 	kstat_incr_irqs_this_cpu(irq, desc);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 099ea2e0eb88..4332d766619d 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -63,8 +63,8 @@ enum {
 
 extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		unsigned long flags);
-extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
-extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
+extern void __disable_irq(struct irq_desc *desc, unsigned int irq);
+extern void __enable_irq(struct irq_desc *desc, unsigned int irq);
 
 extern int irq_startup(struct irq_desc *desc, bool resend);
 extern void irq_shutdown(struct irq_desc *desc);
@@ -194,3 +194,15 @@ static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *d
 	__this_cpu_inc(*desc->kstat_irqs);
 	__this_cpu_inc(kstat.irqs_sum);
 }
+
+#ifdef CONFIG_PM_SLEEP
+bool irq_pm_check_wakeup(struct irq_desc *desc);
+void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action);
+void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action);
+#else
+static inline bool irq_pm_check_wakeup(struct irq_desc *desc) { return false; }
+static inline void
+irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { }
+static inline void
+irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { }
+#endif
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 1487a123db5c..a1782f88f0af 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -14,6 +14,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/radix-tree.h>
 #include <linux/bitmap.h>
+#include <linux/irqdomain.h>
 
 #include "internals.h"
 
@@ -336,6 +337,47 @@ int generic_handle_irq(unsigned int irq)
 }
 EXPORT_SYMBOL_GPL(generic_handle_irq);
 
+#ifdef CONFIG_HANDLE_DOMAIN_IRQ
+/**
+ * __handle_domain_irq - Invoke the handler for a HW irq belonging to a domain
+ * @domain:	The domain where to perform the lookup
+ * @hwirq:	The HW irq number to convert to a logical one
+ * @lookup:	Whether to perform the domain lookup or not
+ * @regs:	Register file coming from the low-level handling code
+ *
+ * Returns:	0 on success, or -EINVAL if conversion has failed
+ */
+int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq,
+			bool lookup, struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	unsigned int irq = hwirq;
+	int ret = 0;
+
+	irq_enter();
+
+#ifdef CONFIG_IRQ_DOMAIN
+	if (lookup)
+		irq = irq_find_mapping(domain, hwirq);
+#endif
+
+	/*
+	 * Some hardware gives randomly wrong interrupts.  Rather
+	 * than crashing, do something sensible.
+	 */
+	if (unlikely(!irq || irq >= nr_irqs)) {
+		ack_bad_irq(irq);
+		ret = -EINVAL;
+	} else {
+		generic_handle_irq(irq);
+	}
+
+	irq_exit();
+	set_irq_regs(old_regs);
+	return ret;
+}
+#endif
+
 /* Dynamic interrupt handling */
 
 /**
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 3dc6a61bf06a..0a9104b4608b 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -382,14 +382,8 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 }
 #endif
 
-void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
+void __disable_irq(struct irq_desc *desc, unsigned int irq)
 {
-	if (suspend) {
-		if (!desc->action || (desc->action->flags & IRQF_NO_SUSPEND))
-			return;
-		desc->istate |= IRQS_SUSPENDED;
-	}
-
 	if (!desc->depth++)
 		irq_disable(desc);
 }
@@ -401,7 +395,7 @@ static int __disable_irq_nosync(unsigned int irq)
 
 	if (!desc)
 		return -EINVAL;
-	__disable_irq(desc, irq, false);
+	__disable_irq(desc, irq);
 	irq_put_desc_busunlock(desc, flags);
 	return 0;
 }
@@ -442,20 +436,8 @@ void disable_irq(unsigned int irq)
 }
 EXPORT_SYMBOL(disable_irq);
 
-void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
+void __enable_irq(struct irq_desc *desc, unsigned int irq)
 {
-	if (resume) {
-		if (!(desc->istate & IRQS_SUSPENDED)) {
-			if (!desc->action)
-				return;
-			if (!(desc->action->flags & IRQF_FORCE_RESUME))
-				return;
-			/* Pretend that it got disabled ! */
-			desc->depth++;
-		}
-		desc->istate &= ~IRQS_SUSPENDED;
-	}
-
 	switch (desc->depth) {
 	case 0:
  err_out:
@@ -497,7 +479,7 @@ void enable_irq(unsigned int irq)
 		 KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
 		goto out;
 
-	__enable_irq(desc, irq, false);
+	__enable_irq(desc, irq);
 out:
 	irq_put_desc_busunlock(desc, flags);
 }
@@ -1218,6 +1200,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	new->irq = irq;
 	*old_ptr = new;
 
+	irq_pm_install_action(desc, new);
+
 	/* Reset broken irq detection when installing new handler */
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
@@ -1228,7 +1212,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	 */
 	if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) {
 		desc->istate &= ~IRQS_SPURIOUS_DISABLED;
-		__enable_irq(desc, irq, false);
+		__enable_irq(desc, irq);
 	}
 
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -1336,6 +1320,8 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 	/* Found it - now remove it from the list of entries: */
 	*action_ptr = action->next;
 
+	irq_pm_remove_action(desc, action);
+
 	/* If this was the last handler, shut down the IRQ line: */
 	if (!desc->action) {
 		irq_shutdown(desc);
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index abcd6ca86cb7..3ca532592704 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -9,17 +9,105 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
+#include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 
 #include "internals.h"
 
+bool irq_pm_check_wakeup(struct irq_desc *desc)
+{
+	if (irqd_is_wakeup_armed(&desc->irq_data)) {
+		irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED);
+		desc->istate |= IRQS_SUSPENDED | IRQS_PENDING;
+		desc->depth++;
+		irq_disable(desc);
+		pm_system_wakeup();
+		return true;
+	}
+	return false;
+}
+
+/*
+ * Called from __setup_irq() with desc->lock held after @action has
+ * been installed in the action chain.
+ */
+void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action)
+{
+	desc->nr_actions++;
+
+	if (action->flags & IRQF_FORCE_RESUME)
+		desc->force_resume_depth++;
+
+	WARN_ON_ONCE(desc->force_resume_depth &&
+		     desc->force_resume_depth != desc->nr_actions);
+
+	if (action->flags & IRQF_NO_SUSPEND)
+		desc->no_suspend_depth++;
+
+	WARN_ON_ONCE(desc->no_suspend_depth &&
+		     desc->no_suspend_depth != desc->nr_actions);
+}
+
+/*
+ * Called from __free_irq() with desc->lock held after @action has
+ * been removed from the action chain.
+ */
+void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action)
+{
+	desc->nr_actions--;
+
+	if (action->flags & IRQF_FORCE_RESUME)
+		desc->force_resume_depth--;
+
+	if (action->flags & IRQF_NO_SUSPEND)
+		desc->no_suspend_depth--;
+}
+
+static bool suspend_device_irq(struct irq_desc *desc, int irq)
+{
+	if (!desc->action || desc->no_suspend_depth)
+		return false;
+
+	if (irqd_is_wakeup_set(&desc->irq_data)) {
+		irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED);
+		/*
+		 * We return true here to force the caller to issue
+		 * synchronize_irq(). We need to make sure that the
+		 * IRQD_WAKEUP_ARMED is visible before we return from
+		 * suspend_device_irqs().
+		 */
+		return true;
+	}
+
+	desc->istate |= IRQS_SUSPENDED;
+	__disable_irq(desc, irq);
+
+	/*
+	 * Hardware which has no wakeup source configuration facility
+	 * requires that the non wakeup interrupts are masked at the
+	 * chip level. The chip implementation indicates that with
+	 * IRQCHIP_MASK_ON_SUSPEND.
+	 */
+	if (irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND)
+		mask_irq(desc);
+	return true;
+}
+
 /**
  * suspend_device_irqs - disable all currently enabled interrupt lines
  *
- * During system-wide suspend or hibernation device drivers need to be prevented
- * from receiving interrupts and this function is provided for this purpose.
- * It marks all interrupt lines in use, except for the timer ones, as disabled
- * and sets the IRQS_SUSPENDED flag for each of them.
+ * During system-wide suspend or hibernation device drivers need to be
+ * prevented from receiving interrupts and this function is provided
+ * for this purpose.
+ *
+ * So we disable all interrupts and mark them IRQS_SUSPENDED except
+ * for those which are unused, those which are marked as not
+ * suspendable via an interrupt request with the flag IRQF_NO_SUSPEND
+ * set and those which are marked as active wakeup sources.
+ *
+ * The active wakeup sources are handled by the flow handler entry
+ * code which checks for the IRQD_WAKEUP_ARMED flag, suspends the
+ * interrupt and notifies the pm core about the wakeup.
  */
 void suspend_device_irqs(void)
 {
@@ -28,18 +116,36 @@ void suspend_device_irqs(void)
 
 	for_each_irq_desc(irq, desc) {
 		unsigned long flags;
+		bool sync;
 
 		raw_spin_lock_irqsave(&desc->lock, flags);
-		__disable_irq(desc, irq, true);
+		sync = suspend_device_irq(desc, irq);
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
-	}
 
-	for_each_irq_desc(irq, desc)
-		if (desc->istate & IRQS_SUSPENDED)
+		if (sync)
 			synchronize_irq(irq);
+	}
 }
 EXPORT_SYMBOL_GPL(suspend_device_irqs);
 
+static void resume_irq(struct irq_desc *desc, int irq)
+{
+	irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED);
+
+	if (desc->istate & IRQS_SUSPENDED)
+		goto resume;
+
+	/* Force resume the interrupt? */
+	if (!desc->force_resume_depth)
+		return;
+
+	/* Pretend that it got disabled ! */
+	desc->depth++;
+resume:
+	desc->istate &= ~IRQS_SUSPENDED;
+	__enable_irq(desc, irq);
+}
+
 static void resume_irqs(bool want_early)
 {
 	struct irq_desc *desc;
@@ -54,7 +160,7 @@ static void resume_irqs(bool want_early)
 			continue;
 
 		raw_spin_lock_irqsave(&desc->lock, flags);
-		__enable_irq(desc, irq, true);
+		resume_irq(desc, irq);
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
 }
@@ -93,38 +199,3 @@ void resume_device_irqs(void)
 	resume_irqs(false);
 }
 EXPORT_SYMBOL_GPL(resume_device_irqs);
-
-/**
- * check_wakeup_irqs - check if any wake-up interrupts are pending
- */
-int check_wakeup_irqs(void)
-{
-	struct irq_desc *desc;
-	int irq;
-
-	for_each_irq_desc(irq, desc) {
-		/*
-		 * Only interrupts which are marked as wakeup source
-		 * and have not been disabled before the suspend check
-		 * can abort suspend.
-		 */
-		if (irqd_is_wakeup_set(&desc->irq_data)) {
-			if (desc->depth == 1 && desc->istate & IRQS_PENDING)
-				return -EBUSY;
-			continue;
-		}
-		/*
-		 * Check the non wakeup interrupts whether they need
-		 * to be masked before finally going into suspend
-		 * state. That's for hardware which has no wakeup
-		 * source configuration facility. The chip
-		 * implementation indicates that with
-		 * IRQCHIP_MASK_ON_SUSPEND.
-		 */
-		if (desc->istate & IRQS_SUSPENDED &&
-		    irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND)
-			mask_irq(desc);
-	}
-
-	return 0;
-}
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index e6bcbe756663..3ab9048483fa 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -95,11 +95,11 @@ bool irq_work_queue(struct irq_work *work)
 
 	/* If the work is "lazy", handle it from next tick if any */
 	if (work->flags & IRQ_WORK_LAZY) {
-		if (llist_add(&work->llnode, &__get_cpu_var(lazy_list)) &&
+		if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
 		    tick_nohz_tick_stopped())
 			arch_irq_work_raise();
 	} else {
-		if (llist_add(&work->llnode, &__get_cpu_var(raised_list)))
+		if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
 			arch_irq_work_raise();
 	}
 
@@ -113,10 +113,12 @@ bool irq_work_needs_cpu(void)
 {
 	struct llist_head *raised, *lazy;
 
-	raised = &__get_cpu_var(raised_list);
-	lazy = &__get_cpu_var(lazy_list);
-	if (llist_empty(raised) && llist_empty(lazy))
-		return false;
+	raised = this_cpu_ptr(&raised_list);
+	lazy = this_cpu_ptr(&lazy_list);
+
+	if (llist_empty(raised) || arch_irq_work_has_interrupt())
+		if (llist_empty(lazy))
+			return false;
 
 	/* All work should have been flushed before going offline */
 	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
@@ -166,11 +168,20 @@ static void irq_work_run_list(struct llist_head *list)
  */
 void irq_work_run(void)
 {
-	irq_work_run_list(&__get_cpu_var(raised_list));
-	irq_work_run_list(&__get_cpu_var(lazy_list));
+	irq_work_run_list(this_cpu_ptr(&raised_list));
+	irq_work_run_list(this_cpu_ptr(&lazy_list));
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
+void irq_work_tick(void)
+{
+	struct llist_head *raised = &__get_cpu_var(raised_list);
+
+	if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
+		irq_work_run_list(raised);
+	irq_work_run_list(&__get_cpu_var(lazy_list));
+}
+
 /*
  * Synchronize against the irq_work @entry, ensures the entry is not
  * currently in use.
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index ae5167087845..5c5987f10819 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -565,19 +565,12 @@ static int kallsyms_open(struct inode *inode, struct file *file)
 	 * using get_symbol_offset for every symbol.
 	 */
 	struct kallsym_iter *iter;
-	int ret;
-
-	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+	iter = __seq_open_private(file, &kallsyms_op, sizeof(*iter));
 	if (!iter)
 		return -ENOMEM;
 	reset_iter(iter, 0);
 
-	ret = seq_open(file, &kallsyms_op);
-	if (ret == 0)
-		((struct seq_file *)file->private_data)->private = iter;
-	else
-		kfree(iter);
-	return ret;
+	return 0;
 }
 
 #ifdef	CONFIG_KGDB_KDB
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 2bee072268d9..2abf9f6e9a61 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1759,7 +1759,6 @@ static __initdata char *suffix_tbl[] = {
  */
 static int __init parse_crashkernel_suffix(char *cmdline,
 					   unsigned long long	*crash_size,
-					   unsigned long long	*crash_base,
 					   const char *suffix)
 {
 	char *cur = cmdline;
@@ -1848,7 +1847,7 @@ static int __init __parse_crashkernel(char *cmdline,
 
 	if (suffix)
 		return parse_crashkernel_suffix(ck_cmdline, crash_size,
-				crash_base, suffix);
+				suffix);
 	/*
 	 * if the commandline contains a ':', then that's the extended
 	 * syntax -- if not, it must be the classic syntax
@@ -2016,22 +2015,6 @@ static int __init crash_save_vmcoreinfo_init(void)
 subsys_initcall(crash_save_vmcoreinfo_init);
 
 #ifdef CONFIG_KEXEC_FILE
-static int __kexec_add_segment(struct kimage *image, char *buf,
-			       unsigned long bufsz, unsigned long mem,
-			       unsigned long memsz)
-{
-	struct kexec_segment *ksegment;
-
-	ksegment = &image->segment[image->nr_segments];
-	ksegment->kbuf = buf;
-	ksegment->bufsz = bufsz;
-	ksegment->mem = mem;
-	ksegment->memsz = memsz;
-	image->nr_segments++;
-
-	return 0;
-}
-
 static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
 				    struct kexec_buf *kbuf)
 {
@@ -2064,8 +2047,7 @@ static int locate_mem_hole_top_down(unsigned long start, unsigned long end,
 	} while (1);
 
 	/* If we are here, we found a suitable memory range */
-	__kexec_add_segment(image, kbuf->buffer, kbuf->bufsz, temp_start,
-			    kbuf->memsz);
+	kbuf->mem = temp_start;
 
 	/* Success, stop navigating through remaining System RAM ranges */
 	return 1;
@@ -2099,8 +2081,7 @@ static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end,
 	} while (1);
 
 	/* If we are here, we found a suitable memory range */
-	__kexec_add_segment(image, kbuf->buffer, kbuf->bufsz, temp_start,
-			    kbuf->memsz);
+	kbuf->mem = temp_start;
 
 	/* Success, stop navigating through remaining System RAM ranges */
 	return 1;
@@ -2187,7 +2168,12 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 	}
 
 	/* Found a suitable memory range */
-	ksegment = &image->segment[image->nr_segments - 1];
+	ksegment = &image->segment[image->nr_segments];
+	ksegment->kbuf = kbuf->buffer;
+	ksegment->bufsz = kbuf->bufsz;
+	ksegment->mem = kbuf->mem;
+	ksegment->memsz = kbuf->memsz;
+	image->nr_segments++;
 	*load_addr = ksegment->mem;
 	return 0;
 }
diff --git a/kernel/kthread.c b/kernel/kthread.c
index ef483220e855..10e489c448fe 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -369,7 +369,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 {
 	struct task_struct *p;
 
-	p = kthread_create_on_node(threadfn, data, cpu_to_mem(cpu), namefmt,
+	p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
 				   cpu);
 	if (IS_ERR(p))
 		return p;
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 0955b885d0dc..ec8cce259779 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -20,30 +20,20 @@
  * Author: Paul E. McKenney <paulmck@us.ibm.com>
  *	Based on kernel/rcu/torture.c.
  */
-#include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
-#include <linux/err.h>
 #include <linux/spinlock.h>
+#include <linux/rwlock.h>
+#include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/atomic.h>
-#include <linux/bitops.h>
-#include <linux/completion.h>
 #include <linux/moduleparam.h>
-#include <linux/percpu.h>
-#include <linux/notifier.h>
-#include <linux/reboot.h>
-#include <linux/freezer.h>
-#include <linux/cpu.h>
 #include <linux/delay.h>
-#include <linux/stat.h>
 #include <linux/slab.h>
-#include <linux/trace_clock.h>
-#include <asm/byteorder.h>
 #include <linux/torture.h>
 
 MODULE_LICENSE("GPL");
@@ -51,6 +41,8 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
 
 torture_param(int, nwriters_stress, -1,
 	     "Number of write-locking stress-test threads");
+torture_param(int, nreaders_stress, -1,
+	     "Number of read-locking stress-test threads");
 torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
 torture_param(int, onoff_interval, 0,
 	     "Time between CPU hotplugs (s), 0=disable");
@@ -66,30 +58,28 @@ torture_param(bool, verbose, true,
 static char *torture_type = "spin_lock";
 module_param(torture_type, charp, 0444);
 MODULE_PARM_DESC(torture_type,
-		 "Type of lock to torture (spin_lock, spin_lock_irq, ...)");
-
-static atomic_t n_lock_torture_errors;
+		 "Type of lock to torture (spin_lock, spin_lock_irq, mutex_lock, ...)");
 
 static struct task_struct *stats_task;
 static struct task_struct **writer_tasks;
+static struct task_struct **reader_tasks;
 
-static int nrealwriters_stress;
 static bool lock_is_write_held;
+static bool lock_is_read_held;
 
-struct lock_writer_stress_stats {
-	long n_write_lock_fail;
-	long n_write_lock_acquired;
+struct lock_stress_stats {
+	long n_lock_fail;
+	long n_lock_acquired;
 };
-static struct lock_writer_stress_stats *lwsa;
 
 #if defined(MODULE)
 #define LOCKTORTURE_RUNNABLE_INIT 1
 #else
 #define LOCKTORTURE_RUNNABLE_INIT 0
 #endif
-int locktorture_runnable = LOCKTORTURE_RUNNABLE_INIT;
-module_param(locktorture_runnable, int, 0444);
-MODULE_PARM_DESC(locktorture_runnable, "Start locktorture at module init");
+int torture_runnable = LOCKTORTURE_RUNNABLE_INIT;
+module_param(torture_runnable, int, 0444);
+MODULE_PARM_DESC(torture_runnable, "Start locktorture at module init");
 
 /* Forward reference. */
 static void lock_torture_cleanup(void);
@@ -102,12 +92,25 @@ struct lock_torture_ops {
 	int (*writelock)(void);
 	void (*write_delay)(struct torture_random_state *trsp);
 	void (*writeunlock)(void);
+	int (*readlock)(void);
+	void (*read_delay)(struct torture_random_state *trsp);
+	void (*readunlock)(void);
 	unsigned long flags;
 	const char *name;
 };
 
-static struct lock_torture_ops *cur_ops;
-
+struct lock_torture_cxt {
+	int nrealwriters_stress;
+	int nrealreaders_stress;
+	bool debug_lock;
+	atomic_t n_lock_torture_errors;
+	struct lock_torture_ops *cur_ops;
+	struct lock_stress_stats *lwsa; /* writer statistics */
+	struct lock_stress_stats *lrsa; /* reader statistics */
+};
+static struct lock_torture_cxt cxt = { 0, 0, false,
+				       ATOMIC_INIT(0),
+				       NULL, NULL};
 /*
  * Definitions for lock torture testing.
  */
@@ -123,10 +126,10 @@ static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
 
 	/* We want a long delay occasionally to force massive contention.  */
 	if (!(torture_random(trsp) %
-	      (nrealwriters_stress * 2000 * longdelay_us)))
+	      (cxt.nrealwriters_stress * 2000 * longdelay_us)))
 		mdelay(longdelay_us);
 #ifdef CONFIG_PREEMPT
-	if (!(torture_random(trsp) % (nrealwriters_stress * 20000)))
+	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
 		preempt_schedule();  /* Allow test to be preempted. */
 #endif
 }
@@ -140,6 +143,9 @@ static struct lock_torture_ops lock_busted_ops = {
 	.writelock	= torture_lock_busted_write_lock,
 	.write_delay	= torture_lock_busted_write_delay,
 	.writeunlock	= torture_lock_busted_write_unlock,
+	.readlock       = NULL,
+	.read_delay     = NULL,
+	.readunlock     = NULL,
 	.name		= "lock_busted"
 };
 
@@ -160,13 +166,13 @@ static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
 	 * we want a long delay occasionally to force massive contention.
 	 */
 	if (!(torture_random(trsp) %
-	      (nrealwriters_stress * 2000 * longdelay_us)))
+	      (cxt.nrealwriters_stress * 2000 * longdelay_us)))
 		mdelay(longdelay_us);
 	if (!(torture_random(trsp) %
-	      (nrealwriters_stress * 2 * shortdelay_us)))
+	      (cxt.nrealwriters_stress * 2 * shortdelay_us)))
 		udelay(shortdelay_us);
 #ifdef CONFIG_PREEMPT
-	if (!(torture_random(trsp) % (nrealwriters_stress * 20000)))
+	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
 		preempt_schedule();  /* Allow test to be preempted. */
 #endif
 }
@@ -180,39 +186,253 @@ static struct lock_torture_ops spin_lock_ops = {
 	.writelock	= torture_spin_lock_write_lock,
 	.write_delay	= torture_spin_lock_write_delay,
 	.writeunlock	= torture_spin_lock_write_unlock,
+	.readlock       = NULL,
+	.read_delay     = NULL,
+	.readunlock     = NULL,
 	.name		= "spin_lock"
 };
 
 static int torture_spin_lock_write_lock_irq(void)
-__acquires(torture_spinlock_irq)
+__acquires(torture_spinlock)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&torture_spinlock, flags);
-	cur_ops->flags = flags;
+	cxt.cur_ops->flags = flags;
 	return 0;
 }
 
 static void torture_lock_spin_write_unlock_irq(void)
 __releases(torture_spinlock)
 {
-	spin_unlock_irqrestore(&torture_spinlock, cur_ops->flags);
+	spin_unlock_irqrestore(&torture_spinlock, cxt.cur_ops->flags);
 }
 
 static struct lock_torture_ops spin_lock_irq_ops = {
 	.writelock	= torture_spin_lock_write_lock_irq,
 	.write_delay	= torture_spin_lock_write_delay,
 	.writeunlock	= torture_lock_spin_write_unlock_irq,
+	.readlock       = NULL,
+	.read_delay     = NULL,
+	.readunlock     = NULL,
 	.name		= "spin_lock_irq"
 };
 
+static DEFINE_RWLOCK(torture_rwlock);
+
+static int torture_rwlock_write_lock(void) __acquires(torture_rwlock)
+{
+	write_lock(&torture_rwlock);
+	return 0;
+}
+
+static void torture_rwlock_write_delay(struct torture_random_state *trsp)
+{
+	const unsigned long shortdelay_us = 2;
+	const unsigned long longdelay_ms = 100;
+
+	/* We want a short delay mostly to emulate likely code, and
+	 * we want a long delay occasionally to force massive contention.
+	 */
+	if (!(torture_random(trsp) %
+	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms);
+	else
+		udelay(shortdelay_us);
+}
+
+static void torture_rwlock_write_unlock(void) __releases(torture_rwlock)
+{
+	write_unlock(&torture_rwlock);
+}
+
+static int torture_rwlock_read_lock(void) __acquires(torture_rwlock)
+{
+	read_lock(&torture_rwlock);
+	return 0;
+}
+
+static void torture_rwlock_read_delay(struct torture_random_state *trsp)
+{
+	const unsigned long shortdelay_us = 10;
+	const unsigned long longdelay_ms = 100;
+
+	/* We want a short delay mostly to emulate likely code, and
+	 * we want a long delay occasionally to force massive contention.
+	 */
+	if (!(torture_random(trsp) %
+	      (cxt.nrealreaders_stress * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms);
+	else
+		udelay(shortdelay_us);
+}
+
+static void torture_rwlock_read_unlock(void) __releases(torture_rwlock)
+{
+	read_unlock(&torture_rwlock);
+}
+
+static struct lock_torture_ops rw_lock_ops = {
+	.writelock	= torture_rwlock_write_lock,
+	.write_delay	= torture_rwlock_write_delay,
+	.writeunlock	= torture_rwlock_write_unlock,
+	.readlock       = torture_rwlock_read_lock,
+	.read_delay     = torture_rwlock_read_delay,
+	.readunlock     = torture_rwlock_read_unlock,
+	.name		= "rw_lock"
+};
+
+static int torture_rwlock_write_lock_irq(void) __acquires(torture_rwlock)
+{
+	unsigned long flags;
+
+	write_lock_irqsave(&torture_rwlock, flags);
+	cxt.cur_ops->flags = flags;
+	return 0;
+}
+
+static void torture_rwlock_write_unlock_irq(void)
+__releases(torture_rwlock)
+{
+	write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
+}
+
+static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock)
+{
+	unsigned long flags;
+
+	read_lock_irqsave(&torture_rwlock, flags);
+	cxt.cur_ops->flags = flags;
+	return 0;
+}
+
+static void torture_rwlock_read_unlock_irq(void)
+__releases(torture_rwlock)
+{
+	write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
+}
+
+static struct lock_torture_ops rw_lock_irq_ops = {
+	.writelock	= torture_rwlock_write_lock_irq,
+	.write_delay	= torture_rwlock_write_delay,
+	.writeunlock	= torture_rwlock_write_unlock_irq,
+	.readlock       = torture_rwlock_read_lock_irq,
+	.read_delay     = torture_rwlock_read_delay,
+	.readunlock     = torture_rwlock_read_unlock_irq,
+	.name		= "rw_lock_irq"
+};
+
+static DEFINE_MUTEX(torture_mutex);
+
+static int torture_mutex_lock(void) __acquires(torture_mutex)
+{
+	mutex_lock(&torture_mutex);
+	return 0;
+}
+
+static void torture_mutex_delay(struct torture_random_state *trsp)
+{
+	const unsigned long longdelay_ms = 100;
+
+	/* We want a long delay occasionally to force massive contention.  */
+	if (!(torture_random(trsp) %
+	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms * 5);
+	else
+		mdelay(longdelay_ms / 5);
+#ifdef CONFIG_PREEMPT
+	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
+		preempt_schedule();  /* Allow test to be preempted. */
+#endif
+}
+
+static void torture_mutex_unlock(void) __releases(torture_mutex)
+{
+	mutex_unlock(&torture_mutex);
+}
+
+static struct lock_torture_ops mutex_lock_ops = {
+	.writelock	= torture_mutex_lock,
+	.write_delay	= torture_mutex_delay,
+	.writeunlock	= torture_mutex_unlock,
+	.readlock       = NULL,
+	.read_delay     = NULL,
+	.readunlock     = NULL,
+	.name		= "mutex_lock"
+};
+
+static DECLARE_RWSEM(torture_rwsem);
+static int torture_rwsem_down_write(void) __acquires(torture_rwsem)
+{
+	down_write(&torture_rwsem);
+	return 0;
+}
+
+static void torture_rwsem_write_delay(struct torture_random_state *trsp)
+{
+	const unsigned long longdelay_ms = 100;
+
+	/* We want a long delay occasionally to force massive contention.  */
+	if (!(torture_random(trsp) %
+	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms * 10);
+	else
+		mdelay(longdelay_ms / 10);
+#ifdef CONFIG_PREEMPT
+	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
+		preempt_schedule();  /* Allow test to be preempted. */
+#endif
+}
+
+static void torture_rwsem_up_write(void) __releases(torture_rwsem)
+{
+	up_write(&torture_rwsem);
+}
+
+static int torture_rwsem_down_read(void) __acquires(torture_rwsem)
+{
+	down_read(&torture_rwsem);
+	return 0;
+}
+
+static void torture_rwsem_read_delay(struct torture_random_state *trsp)
+{
+	const unsigned long longdelay_ms = 100;
+
+	/* We want a long delay occasionally to force massive contention.  */
+	if (!(torture_random(trsp) %
+	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms * 2);
+	else
+		mdelay(longdelay_ms / 2);
+#ifdef CONFIG_PREEMPT
+	if (!(torture_random(trsp) % (cxt.nrealreaders_stress * 20000)))
+		preempt_schedule();  /* Allow test to be preempted. */
+#endif
+}
+
+static void torture_rwsem_up_read(void) __releases(torture_rwsem)
+{
+	up_read(&torture_rwsem);
+}
+
+static struct lock_torture_ops rwsem_lock_ops = {
+	.writelock	= torture_rwsem_down_write,
+	.write_delay	= torture_rwsem_write_delay,
+	.writeunlock	= torture_rwsem_up_write,
+	.readlock       = torture_rwsem_down_read,
+	.read_delay     = torture_rwsem_read_delay,
+	.readunlock     = torture_rwsem_up_read,
+	.name		= "rwsem_lock"
+};
+
 /*
  * Lock torture writer kthread.  Repeatedly acquires and releases
  * the lock, checking for duplicate acquisitions.
  */
 static int lock_torture_writer(void *arg)
 {
-	struct lock_writer_stress_stats *lwsp = arg;
+	struct lock_stress_stats *lwsp = arg;
 	static DEFINE_TORTURE_RANDOM(rand);
 
 	VERBOSE_TOROUT_STRING("lock_torture_writer task started");
@@ -221,14 +441,19 @@ static int lock_torture_writer(void *arg)
 	do {
 		if ((torture_random(&rand) & 0xfffff) == 0)
 			schedule_timeout_uninterruptible(1);
-		cur_ops->writelock();
+
+		cxt.cur_ops->writelock();
 		if (WARN_ON_ONCE(lock_is_write_held))
-			lwsp->n_write_lock_fail++;
+			lwsp->n_lock_fail++;
 		lock_is_write_held = 1;
-		lwsp->n_write_lock_acquired++;
-		cur_ops->write_delay(&rand);
+		if (WARN_ON_ONCE(lock_is_read_held))
+			lwsp->n_lock_fail++; /* rare, but... */
+
+		lwsp->n_lock_acquired++;
+		cxt.cur_ops->write_delay(&rand);
 		lock_is_write_held = 0;
-		cur_ops->writeunlock();
+		cxt.cur_ops->writeunlock();
+
 		stutter_wait("lock_torture_writer");
 	} while (!torture_must_stop());
 	torture_kthread_stopping("lock_torture_writer");
@@ -236,32 +461,66 @@ static int lock_torture_writer(void *arg)
 }
 
 /*
+ * Lock torture reader kthread.  Repeatedly acquires and releases
+ * the reader lock.
+ */
+static int lock_torture_reader(void *arg)
+{
+	struct lock_stress_stats *lrsp = arg;
+	static DEFINE_TORTURE_RANDOM(rand);
+
+	VERBOSE_TOROUT_STRING("lock_torture_reader task started");
+	set_user_nice(current, MAX_NICE);
+
+	do {
+		if ((torture_random(&rand) & 0xfffff) == 0)
+			schedule_timeout_uninterruptible(1);
+
+		cxt.cur_ops->readlock();
+		lock_is_read_held = 1;
+		if (WARN_ON_ONCE(lock_is_write_held))
+			lrsp->n_lock_fail++; /* rare, but... */
+
+		lrsp->n_lock_acquired++;
+		cxt.cur_ops->read_delay(&rand);
+		lock_is_read_held = 0;
+		cxt.cur_ops->readunlock();
+
+		stutter_wait("lock_torture_reader");
+	} while (!torture_must_stop());
+	torture_kthread_stopping("lock_torture_reader");
+	return 0;
+}
+
+/*
  * Create an lock-torture-statistics message in the specified buffer.
  */
-static void lock_torture_printk(char *page)
+static void __torture_print_stats(char *page,
+				  struct lock_stress_stats *statp, bool write)
 {
 	bool fail = 0;
-	int i;
+	int i, n_stress;
 	long max = 0;
-	long min = lwsa[0].n_write_lock_acquired;
+	long min = statp[0].n_lock_acquired;
 	long long sum = 0;
 
-	for (i = 0; i < nrealwriters_stress; i++) {
-		if (lwsa[i].n_write_lock_fail)
+	n_stress = write ? cxt.nrealwriters_stress : cxt.nrealreaders_stress;
+	for (i = 0; i < n_stress; i++) {
+		if (statp[i].n_lock_fail)
 			fail = true;
-		sum += lwsa[i].n_write_lock_acquired;
-		if (max < lwsa[i].n_write_lock_fail)
-			max = lwsa[i].n_write_lock_fail;
-		if (min > lwsa[i].n_write_lock_fail)
-			min = lwsa[i].n_write_lock_fail;
+		sum += statp[i].n_lock_acquired;
+		if (max < statp[i].n_lock_fail)
+			max = statp[i].n_lock_fail;
+		if (min > statp[i].n_lock_fail)
+			min = statp[i].n_lock_fail;
 	}
-	page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
 	page += sprintf(page,
-			"Writes:  Total: %lld  Max/Min: %ld/%ld %s  Fail: %d %s\n",
+			"%s:  Total: %lld  Max/Min: %ld/%ld %s  Fail: %d %s\n",
+			write ? "Writes" : "Reads ",
 			sum, max, min, max / 2 > min ? "???" : "",
 			fail, fail ? "!!!" : "");
 	if (fail)
-		atomic_inc(&n_lock_torture_errors);
+		atomic_inc(&cxt.n_lock_torture_errors);
 }
 
 /*
@@ -274,18 +533,35 @@ static void lock_torture_printk(char *page)
  */
 static void lock_torture_stats_print(void)
 {
-	int size = nrealwriters_stress * 200 + 8192;
+	int size = cxt.nrealwriters_stress * 200 + 8192;
 	char *buf;
 
+	if (cxt.cur_ops->readlock)
+		size += cxt.nrealreaders_stress * 200 + 8192;
+
 	buf = kmalloc(size, GFP_KERNEL);
 	if (!buf) {
 		pr_err("lock_torture_stats_print: Out of memory, need: %d",
 		       size);
 		return;
 	}
-	lock_torture_printk(buf);
+
+	__torture_print_stats(buf, cxt.lwsa, true);
 	pr_alert("%s", buf);
 	kfree(buf);
+
+	if (cxt.cur_ops->readlock) {
+		buf = kmalloc(size, GFP_KERNEL);
+		if (!buf) {
+			pr_err("lock_torture_stats_print: Out of memory, need: %d",
+			       size);
+			return;
+		}
+
+		__torture_print_stats(buf, cxt.lrsa, false);
+		pr_alert("%s", buf);
+		kfree(buf);
+	}
 }
 
 /*
@@ -312,9 +588,10 @@ lock_torture_print_module_parms(struct lock_torture_ops *cur_ops,
 				const char *tag)
 {
 	pr_alert("%s" TORTURE_FLAG
-		 "--- %s: nwriters_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
-		 torture_type, tag, nrealwriters_stress, stat_interval, verbose,
-		 shuffle_interval, stutter, shutdown_secs,
+		 "--- %s%s: nwriters_stress=%d nreaders_stress=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
+		 torture_type, tag, cxt.debug_lock ? " [debug]": "",
+		 cxt.nrealwriters_stress, cxt.nrealreaders_stress, stat_interval,
+		 verbose, shuffle_interval, stutter, shutdown_secs,
 		 onoff_interval, onoff_holdoff);
 }
 
@@ -322,46 +599,59 @@ static void lock_torture_cleanup(void)
 {
 	int i;
 
-	if (torture_cleanup())
+	if (torture_cleanup_begin())
 		return;
 
 	if (writer_tasks) {
-		for (i = 0; i < nrealwriters_stress; i++)
+		for (i = 0; i < cxt.nrealwriters_stress; i++)
 			torture_stop_kthread(lock_torture_writer,
 					     writer_tasks[i]);
 		kfree(writer_tasks);
 		writer_tasks = NULL;
 	}
 
+	if (reader_tasks) {
+		for (i = 0; i < cxt.nrealreaders_stress; i++)
+			torture_stop_kthread(lock_torture_reader,
+					     reader_tasks[i]);
+		kfree(reader_tasks);
+		reader_tasks = NULL;
+	}
+
 	torture_stop_kthread(lock_torture_stats, stats_task);
 	lock_torture_stats_print();  /* -After- the stats thread is stopped! */
 
-	if (atomic_read(&n_lock_torture_errors))
-		lock_torture_print_module_parms(cur_ops,
+	if (atomic_read(&cxt.n_lock_torture_errors))
+		lock_torture_print_module_parms(cxt.cur_ops,
 						"End of test: FAILURE");
 	else if (torture_onoff_failures())
-		lock_torture_print_module_parms(cur_ops,
+		lock_torture_print_module_parms(cxt.cur_ops,
 						"End of test: LOCK_HOTPLUG");
 	else
-		lock_torture_print_module_parms(cur_ops,
+		lock_torture_print_module_parms(cxt.cur_ops,
 						"End of test: SUCCESS");
+	torture_cleanup_end();
 }
 
 static int __init lock_torture_init(void)
 {
-	int i;
+	int i, j;
 	int firsterr = 0;
 	static struct lock_torture_ops *torture_ops[] = {
-		&lock_busted_ops, &spin_lock_ops, &spin_lock_irq_ops,
+		&lock_busted_ops,
+		&spin_lock_ops, &spin_lock_irq_ops,
+		&rw_lock_ops, &rw_lock_irq_ops,
+		&mutex_lock_ops,
+		&rwsem_lock_ops,
 	};
 
-	if (!torture_init_begin(torture_type, verbose, &locktorture_runnable))
+	if (!torture_init_begin(torture_type, verbose, &torture_runnable))
 		return -EBUSY;
 
 	/* Process args and tell the world that the torturer is on the job. */
 	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
-		cur_ops = torture_ops[i];
-		if (strcmp(torture_type, cur_ops->name) == 0)
+		cxt.cur_ops = torture_ops[i];
+		if (strcmp(torture_type, cxt.cur_ops->name) == 0)
 			break;
 	}
 	if (i == ARRAY_SIZE(torture_ops)) {
@@ -374,31 +664,69 @@ static int __init lock_torture_init(void)
 		torture_init_end();
 		return -EINVAL;
 	}
-	if (cur_ops->init)
-		cur_ops->init(); /* no "goto unwind" prior to this point!!! */
+	if (cxt.cur_ops->init)
+		cxt.cur_ops->init(); /* no "goto unwind" prior to this point!!! */
 
 	if (nwriters_stress >= 0)
-		nrealwriters_stress = nwriters_stress;
+		cxt.nrealwriters_stress = nwriters_stress;
 	else
-		nrealwriters_stress = 2 * num_online_cpus();
-	lock_torture_print_module_parms(cur_ops, "Start of test");
+		cxt.nrealwriters_stress = 2 * num_online_cpus();
+
+#ifdef CONFIG_DEBUG_MUTEXES
+	if (strncmp(torture_type, "mutex", 5) == 0)
+		cxt.debug_lock = true;
+#endif
+#ifdef CONFIG_DEBUG_SPINLOCK
+	if ((strncmp(torture_type, "spin", 4) == 0) ||
+	    (strncmp(torture_type, "rw_lock", 7) == 0))
+		cxt.debug_lock = true;
+#endif
 
 	/* Initialize the statistics so that each run gets its own numbers. */
 
 	lock_is_write_held = 0;
-	lwsa = kmalloc(sizeof(*lwsa) * nrealwriters_stress, GFP_KERNEL);
-	if (lwsa == NULL) {
-		VERBOSE_TOROUT_STRING("lwsa: Out of memory");
+	cxt.lwsa = kmalloc(sizeof(*cxt.lwsa) * cxt.nrealwriters_stress, GFP_KERNEL);
+	if (cxt.lwsa == NULL) {
+		VERBOSE_TOROUT_STRING("cxt.lwsa: Out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
-	for (i = 0; i < nrealwriters_stress; i++) {
-		lwsa[i].n_write_lock_fail = 0;
-		lwsa[i].n_write_lock_acquired = 0;
+	for (i = 0; i < cxt.nrealwriters_stress; i++) {
+		cxt.lwsa[i].n_lock_fail = 0;
+		cxt.lwsa[i].n_lock_acquired = 0;
 	}
 
-	/* Start up the kthreads. */
+	if (cxt.cur_ops->readlock) {
+		if (nreaders_stress >= 0)
+			cxt.nrealreaders_stress = nreaders_stress;
+		else {
+			/*
+			 * By default distribute evenly the number of
+			 * readers and writers. We still run the same number
+			 * of threads as the writer-only locks default.
+			 */
+			if (nwriters_stress < 0) /* user doesn't care */
+				cxt.nrealwriters_stress = num_online_cpus();
+			cxt.nrealreaders_stress = cxt.nrealwriters_stress;
+		}
+
+		lock_is_read_held = 0;
+		cxt.lrsa = kmalloc(sizeof(*cxt.lrsa) * cxt.nrealreaders_stress, GFP_KERNEL);
+		if (cxt.lrsa == NULL) {
+			VERBOSE_TOROUT_STRING("cxt.lrsa: Out of memory");
+			firsterr = -ENOMEM;
+			kfree(cxt.lwsa);
+			goto unwind;
+		}
+
+		for (i = 0; i < cxt.nrealreaders_stress; i++) {
+			cxt.lrsa[i].n_lock_fail = 0;
+			cxt.lrsa[i].n_lock_acquired = 0;
+		}
+	}
+	lock_torture_print_module_parms(cxt.cur_ops, "Start of test");
 
+	/* Prepare torture context. */
 	if (onoff_interval > 0) {
 		firsterr = torture_onoff_init(onoff_holdoff * HZ,
 					      onoff_interval * HZ);
@@ -422,18 +750,51 @@ static int __init lock_torture_init(void)
 			goto unwind;
 	}
 
-	writer_tasks = kzalloc(nrealwriters_stress * sizeof(writer_tasks[0]),
+	writer_tasks = kzalloc(cxt.nrealwriters_stress * sizeof(writer_tasks[0]),
 			       GFP_KERNEL);
 	if (writer_tasks == NULL) {
 		VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
-	for (i = 0; i < nrealwriters_stress; i++) {
-		firsterr = torture_create_kthread(lock_torture_writer, &lwsa[i],
+
+	if (cxt.cur_ops->readlock) {
+		reader_tasks = kzalloc(cxt.nrealreaders_stress * sizeof(reader_tasks[0]),
+				       GFP_KERNEL);
+		if (reader_tasks == NULL) {
+			VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
+			firsterr = -ENOMEM;
+			goto unwind;
+		}
+	}
+
+	/*
+	 * Create the kthreads and start torturing (oh, those poor little locks).
+	 *
+	 * TODO: Note that we interleave writers with readers, giving writers a
+	 * slight advantage, by creating its kthread first. This can be modified
+	 * for very specific needs, or even let the user choose the policy, if
+	 * ever wanted.
+	 */
+	for (i = 0, j = 0; i < cxt.nrealwriters_stress ||
+		    j < cxt.nrealreaders_stress; i++, j++) {
+		if (i >= cxt.nrealwriters_stress)
+			goto create_reader;
+
+		/* Create writer. */
+		firsterr = torture_create_kthread(lock_torture_writer, &cxt.lwsa[i],
 						  writer_tasks[i]);
 		if (firsterr)
 			goto unwind;
+
+	create_reader:
+		if (cxt.cur_ops->readlock == NULL || (j >= cxt.nrealreaders_stress))
+			continue;
+		/* Create reader. */
+		firsterr = torture_create_kthread(lock_torture_reader, &cxt.lrsa[j],
+						  reader_tasks[j]);
+		if (firsterr)
+			goto unwind;
 	}
 	if (stat_interval > 0) {
 		firsterr = torture_create_kthread(lock_torture_stats, NULL,
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index 23e89c5930e9..4d60986fcbee 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -56,9 +56,6 @@ do {									\
  * If the lock has already been acquired, then this will proceed to spin
  * on this node->locked until the previous lock holder sets the node->locked
  * in mcs_spin_unlock().
- *
- * We don't inline mcs_spin_lock() so that perf can correctly account for the
- * time spent in this lock function.
  */
 static inline
 void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index ae712b25e492..dadbf88c22c4 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -15,7 +15,7 @@
  *    by Steven Rostedt, based on work by Gregory Haskins, Peter Morreale
  *    and Sven Dietrich.
  *
- * Also see Documentation/mutex-design.txt.
+ * Also see Documentation/locking/mutex-design.txt.
  */
 #include <linux/mutex.h>
 #include <linux/ww_mutex.h>
@@ -106,6 +106,92 @@ void __sched mutex_lock(struct mutex *lock)
 EXPORT_SYMBOL(mutex_lock);
 #endif
 
+static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
+						   struct ww_acquire_ctx *ww_ctx)
+{
+#ifdef CONFIG_DEBUG_MUTEXES
+	/*
+	 * If this WARN_ON triggers, you used ww_mutex_lock to acquire,
+	 * but released with a normal mutex_unlock in this call.
+	 *
+	 * This should never happen, always use ww_mutex_unlock.
+	 */
+	DEBUG_LOCKS_WARN_ON(ww->ctx);
+
+	/*
+	 * Not quite done after calling ww_acquire_done() ?
+	 */
+	DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire);
+
+	if (ww_ctx->contending_lock) {
+		/*
+		 * After -EDEADLK you tried to
+		 * acquire a different ww_mutex? Bad!
+		 */
+		DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww);
+
+		/*
+		 * You called ww_mutex_lock after receiving -EDEADLK,
+		 * but 'forgot' to unlock everything else first?
+		 */
+		DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0);
+		ww_ctx->contending_lock = NULL;
+	}
+
+	/*
+	 * Naughty, using a different class will lead to undefined behavior!
+	 */
+	DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
+#endif
+	ww_ctx->acquired++;
+}
+
+/*
+ * after acquiring lock with fastpath or when we lost out in contested
+ * slowpath, set ctx and wake up any waiters so they can recheck.
+ *
+ * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set,
+ * as the fastpath and opportunistic spinning are disabled in that case.
+ */
+static __always_inline void
+ww_mutex_set_context_fastpath(struct ww_mutex *lock,
+			       struct ww_acquire_ctx *ctx)
+{
+	unsigned long flags;
+	struct mutex_waiter *cur;
+
+	ww_mutex_lock_acquired(lock, ctx);
+
+	lock->ctx = ctx;
+
+	/*
+	 * The lock->ctx update should be visible on all cores before
+	 * the atomic read is done, otherwise contended waiters might be
+	 * missed. The contended waiters will either see ww_ctx == NULL
+	 * and keep spinning, or it will acquire wait_lock, add itself
+	 * to waiter list and sleep.
+	 */
+	smp_mb(); /* ^^^ */
+
+	/*
+	 * Check if lock is contended, if not there is nobody to wake up
+	 */
+	if (likely(atomic_read(&lock->base.count) == 0))
+		return;
+
+	/*
+	 * Uh oh, we raced in fastpath, wake up everyone in this case,
+	 * so they can see the new lock->ctx.
+	 */
+	spin_lock_mutex(&lock->base.wait_lock, flags);
+	list_for_each_entry(cur, &lock->base.wait_list, list) {
+		debug_mutex_wake_waiter(&lock->base, cur);
+		wake_up_process(cur->task);
+	}
+	spin_unlock_mutex(&lock->base.wait_lock, flags);
+}
+
+
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 /*
  * In order to avoid a stampede of mutex spinners from acquiring the mutex
@@ -180,6 +266,129 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
 	 */
 	return retval;
 }
+
+/*
+ * Atomically try to take the lock when it is available
+ */
+static inline bool mutex_try_to_acquire(struct mutex *lock)
+{
+	return !mutex_is_locked(lock) &&
+		(atomic_cmpxchg(&lock->count, 1, 0) == 1);
+}
+
+/*
+ * Optimistic spinning.
+ *
+ * We try to spin for acquisition when we find that the lock owner
+ * is currently running on a (different) CPU and while we don't
+ * need to reschedule. The rationale is that if the lock owner is
+ * running, it is likely to release the lock soon.
+ *
+ * Since this needs the lock owner, and this mutex implementation
+ * doesn't track the owner atomically in the lock field, we need to
+ * track it non-atomically.
+ *
+ * We can't do this for DEBUG_MUTEXES because that relies on wait_lock
+ * to serialize everything.
+ *
+ * The mutex spinners are queued up using MCS lock so that only one
+ * spinner can compete for the mutex. However, if mutex spinning isn't
+ * going to happen, there is no point in going through the lock/unlock
+ * overhead.
+ *
+ * Returns true when the lock was taken, otherwise false, indicating
+ * that we need to jump to the slowpath and sleep.
+ */
+static bool mutex_optimistic_spin(struct mutex *lock,
+				  struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
+{
+	struct task_struct *task = current;
+
+	if (!mutex_can_spin_on_owner(lock))
+		goto done;
+
+	if (!osq_lock(&lock->osq))
+		goto done;
+
+	while (true) {
+		struct task_struct *owner;
+
+		if (use_ww_ctx && ww_ctx->acquired > 0) {
+			struct ww_mutex *ww;
+
+			ww = container_of(lock, struct ww_mutex, base);
+			/*
+			 * If ww->ctx is set the contents are undefined, only
+			 * by acquiring wait_lock there is a guarantee that
+			 * they are not invalid when reading.
+			 *
+			 * As such, when deadlock detection needs to be
+			 * performed the optimistic spinning cannot be done.
+			 */
+			if (ACCESS_ONCE(ww->ctx))
+				break;
+		}
+
+		/*
+		 * If there's an owner, wait for it to either
+		 * release the lock or go to sleep.
+		 */
+		owner = ACCESS_ONCE(lock->owner);
+		if (owner && !mutex_spin_on_owner(lock, owner))
+			break;
+
+		/* Try to acquire the mutex if it is unlocked. */
+		if (mutex_try_to_acquire(lock)) {
+			lock_acquired(&lock->dep_map, ip);
+
+			if (use_ww_ctx) {
+				struct ww_mutex *ww;
+				ww = container_of(lock, struct ww_mutex, base);
+
+				ww_mutex_set_context_fastpath(ww, ww_ctx);
+			}
+
+			mutex_set_owner(lock);
+			osq_unlock(&lock->osq);
+			return true;
+		}
+
+		/*
+		 * When there's no owner, we might have preempted between the
+		 * owner acquiring the lock and setting the owner field. If
+		 * we're an RT task that will live-lock because we won't let
+		 * the owner complete.
+		 */
+		if (!owner && (need_resched() || rt_task(task)))
+			break;
+
+		/*
+		 * The cpu_relax() call is a compiler barrier which forces
+		 * everything in this loop to be re-loaded. We don't need
+		 * memory barriers as we'll eventually observe the right
+		 * values at the cost of a few extra spins.
+		 */
+		cpu_relax_lowlatency();
+	}
+
+	osq_unlock(&lock->osq);
+done:
+	/*
+	 * If we fell out of the spin path because of need_resched(),
+	 * reschedule now, before we try-lock the mutex. This avoids getting
+	 * scheduled out right after we obtained the mutex.
+	 */
+	if (need_resched())
+		schedule_preempt_disabled();
+
+	return false;
+}
+#else
+static bool mutex_optimistic_spin(struct mutex *lock,
+				  struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
+{
+	return false;
+}
 #endif
 
 __visible __used noinline
@@ -277,91 +486,6 @@ __mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx)
 	return 0;
 }
 
-static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
-						   struct ww_acquire_ctx *ww_ctx)
-{
-#ifdef CONFIG_DEBUG_MUTEXES
-	/*
-	 * If this WARN_ON triggers, you used ww_mutex_lock to acquire,
-	 * but released with a normal mutex_unlock in this call.
-	 *
-	 * This should never happen, always use ww_mutex_unlock.
-	 */
-	DEBUG_LOCKS_WARN_ON(ww->ctx);
-
-	/*
-	 * Not quite done after calling ww_acquire_done() ?
-	 */
-	DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire);
-
-	if (ww_ctx->contending_lock) {
-		/*
-		 * After -EDEADLK you tried to
-		 * acquire a different ww_mutex? Bad!
-		 */
-		DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww);
-
-		/*
-		 * You called ww_mutex_lock after receiving -EDEADLK,
-		 * but 'forgot' to unlock everything else first?
-		 */
-		DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0);
-		ww_ctx->contending_lock = NULL;
-	}
-
-	/*
-	 * Naughty, using a different class will lead to undefined behavior!
-	 */
-	DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
-#endif
-	ww_ctx->acquired++;
-}
-
-/*
- * after acquiring lock with fastpath or when we lost out in contested
- * slowpath, set ctx and wake up any waiters so they can recheck.
- *
- * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set,
- * as the fastpath and opportunistic spinning are disabled in that case.
- */
-static __always_inline void
-ww_mutex_set_context_fastpath(struct ww_mutex *lock,
-			       struct ww_acquire_ctx *ctx)
-{
-	unsigned long flags;
-	struct mutex_waiter *cur;
-
-	ww_mutex_lock_acquired(lock, ctx);
-
-	lock->ctx = ctx;
-
-	/*
-	 * The lock->ctx update should be visible on all cores before
-	 * the atomic read is done, otherwise contended waiters might be
-	 * missed. The contended waiters will either see ww_ctx == NULL
-	 * and keep spinning, or it will acquire wait_lock, add itself
-	 * to waiter list and sleep.
-	 */
-	smp_mb(); /* ^^^ */
-
-	/*
-	 * Check if lock is contended, if not there is nobody to wake up
-	 */
-	if (likely(atomic_read(&lock->base.count) == 0))
-		return;
-
-	/*
-	 * Uh oh, we raced in fastpath, wake up everyone in this case,
-	 * so they can see the new lock->ctx.
-	 */
-	spin_lock_mutex(&lock->base.wait_lock, flags);
-	list_for_each_entry(cur, &lock->base.wait_list, list) {
-		debug_mutex_wake_waiter(&lock->base, cur);
-		wake_up_process(cur->task);
-	}
-	spin_unlock_mutex(&lock->base.wait_lock, flags);
-}
-
 /*
  * Lock a mutex (possibly interruptible), slowpath:
  */
@@ -378,104 +502,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	preempt_disable();
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
-#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-	/*
-	 * Optimistic spinning.
-	 *
-	 * We try to spin for acquisition when we find that the lock owner
-	 * is currently running on a (different) CPU and while we don't
-	 * need to reschedule. The rationale is that if the lock owner is
-	 * running, it is likely to release the lock soon.
-	 *
-	 * Since this needs the lock owner, and this mutex implementation
-	 * doesn't track the owner atomically in the lock field, we need to
-	 * track it non-atomically.
-	 *
-	 * We can't do this for DEBUG_MUTEXES because that relies on wait_lock
-	 * to serialize everything.
-	 *
-	 * The mutex spinners are queued up using MCS lock so that only one
-	 * spinner can compete for the mutex. However, if mutex spinning isn't
-	 * going to happen, there is no point in going through the lock/unlock
-	 * overhead.
-	 */
-	if (!mutex_can_spin_on_owner(lock))
-		goto slowpath;
-
-	if (!osq_lock(&lock->osq))
-		goto slowpath;
-
-	for (;;) {
-		struct task_struct *owner;
-
-		if (use_ww_ctx && ww_ctx->acquired > 0) {
-			struct ww_mutex *ww;
-
-			ww = container_of(lock, struct ww_mutex, base);
-			/*
-			 * If ww->ctx is set the contents are undefined, only
-			 * by acquiring wait_lock there is a guarantee that
-			 * they are not invalid when reading.
-			 *
-			 * As such, when deadlock detection needs to be
-			 * performed the optimistic spinning cannot be done.
-			 */
-			if (ACCESS_ONCE(ww->ctx))
-				break;
-		}
-
-		/*
-		 * If there's an owner, wait for it to either
-		 * release the lock or go to sleep.
-		 */
-		owner = ACCESS_ONCE(lock->owner);
-		if (owner && !mutex_spin_on_owner(lock, owner))
-			break;
-
-		/* Try to acquire the mutex if it is unlocked. */
-		if (!mutex_is_locked(lock) &&
-		    (atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
-			lock_acquired(&lock->dep_map, ip);
-			if (use_ww_ctx) {
-				struct ww_mutex *ww;
-				ww = container_of(lock, struct ww_mutex, base);
-
-				ww_mutex_set_context_fastpath(ww, ww_ctx);
-			}
-
-			mutex_set_owner(lock);
-			osq_unlock(&lock->osq);
-			preempt_enable();
-			return 0;
-		}
-
-		/*
-		 * When there's no owner, we might have preempted between the
-		 * owner acquiring the lock and setting the owner field. If
-		 * we're an RT task that will live-lock because we won't let
-		 * the owner complete.
-		 */
-		if (!owner && (need_resched() || rt_task(task)))
-			break;
-
-		/*
-		 * The cpu_relax() call is a compiler barrier which forces
-		 * everything in this loop to be re-loaded. We don't need
-		 * memory barriers as we'll eventually observe the right
-		 * values at the cost of a few extra spins.
-		 */
-		cpu_relax_lowlatency();
+	if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) {
+		/* got the lock, yay! */
+		preempt_enable();
+		return 0;
 	}
-	osq_unlock(&lock->osq);
-slowpath:
-	/*
-	 * If we fell out of the spin path because of need_resched(),
-	 * reschedule now, before we try-lock the mutex. This avoids getting
-	 * scheduled out right after we obtained the mutex.
-	 */
-	if (need_resched())
-		schedule_preempt_disabled();
-#endif
+
 	spin_lock_mutex(&lock->wait_lock, flags);
 
 	/*
@@ -679,15 +711,21 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
  * Release the lock, slowpath:
  */
 static inline void
-__mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
+__mutex_unlock_common_slowpath(struct mutex *lock, int nested)
 {
-	struct mutex *lock = container_of(lock_count, struct mutex, count);
 	unsigned long flags;
 
 	/*
-	 * some architectures leave the lock unlocked in the fastpath failure
+	 * As a performance measurement, release the lock before doing other
+	 * wakeup related duties to follow. This allows other tasks to acquire
+	 * the lock sooner, while still handling cleanups in past unlock calls.
+	 * This can be done as we do not enforce strict equivalence between the
+	 * mutex counter and wait_list.
+	 *
+	 *
+	 * Some architectures leave the lock unlocked in the fastpath failure
 	 * case, others need to leave it locked. In the later case we have to
-	 * unlock it here
+	 * unlock it here - as the lock counter is currently 0 or negative.
 	 */
 	if (__mutex_slowpath_needs_to_unlock())
 		atomic_set(&lock->count, 1);
@@ -716,7 +754,9 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
 __visible void
 __mutex_unlock_slowpath(atomic_t *lock_count)
 {
-	__mutex_unlock_common_slowpath(lock_count, 1);
+	struct mutex *lock = container_of(lock_count, struct mutex, count);
+
+	__mutex_unlock_common_slowpath(lock, 1);
 }
 
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 4115fbf83b12..5cda397607f2 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -16,7 +16,7 @@
 #define mutex_remove_waiter(lock, waiter, ti) \
 		__list_del((waiter)->list.prev, (waiter)->list.next)
 
-#ifdef CONFIG_SMP
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 static inline void mutex_set_owner(struct mutex *lock)
 {
 	lock->owner = current;
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index a0ea2a141b3b..7c98873a3077 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -8,7 +8,7 @@
  *  Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
  *  Copyright (C) 2006 Esben Nielsen
  *
- *  See Documentation/rt-mutex-design.txt for details.
+ *  See Documentation/locking/rt-mutex-design.txt for details.
  */
 #include <linux/spinlock.h>
 #include <linux/export.h>
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index d6203faf2eb1..7628c3fc37ca 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -246,19 +246,22 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 
 	return sem;
 }
+EXPORT_SYMBOL(rwsem_down_read_failed);
 
 static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
 {
-	if (!(count & RWSEM_ACTIVE_MASK)) {
-		/* try acquiring the write lock */
-		if (sem->count == RWSEM_WAITING_BIAS &&
-		    cmpxchg(&sem->count, RWSEM_WAITING_BIAS,
-			    RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) {
-			if (!list_is_singular(&sem->wait_list))
-				rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
-			return true;
-		}
+	/*
+	 * Try acquiring the write lock. Check count first in order
+	 * to reduce unnecessary expensive cmpxchg() operations.
+	 */
+	if (count == RWSEM_WAITING_BIAS &&
+	    cmpxchg(&sem->count, RWSEM_WAITING_BIAS,
+		    RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) {
+		if (!list_is_singular(&sem->wait_list))
+			rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
+		return true;
 	}
+
 	return false;
 }
 
@@ -465,6 +468,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
 
 	return sem;
 }
+EXPORT_SYMBOL(rwsem_down_write_failed);
 
 /*
  * handle waking up a waiter on the semaphore
@@ -485,6 +489,7 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 
 	return sem;
 }
+EXPORT_SYMBOL(rwsem_wake);
 
 /*
  * downgrade a write lock into a read lock
@@ -506,8 +511,4 @@ struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 
 	return sem;
 }
-
-EXPORT_SYMBOL(rwsem_down_read_failed);
-EXPORT_SYMBOL(rwsem_down_write_failed);
-EXPORT_SYMBOL(rwsem_wake);
 EXPORT_SYMBOL(rwsem_downgrade_wake);
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index 6815171a4fff..b8120abe594b 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -36,7 +36,7 @@
 static noinline void __down(struct semaphore *sem);
 static noinline int __down_interruptible(struct semaphore *sem);
 static noinline int __down_killable(struct semaphore *sem);
-static noinline int __down_timeout(struct semaphore *sem, long jiffies);
+static noinline int __down_timeout(struct semaphore *sem, long timeout);
 static noinline void __up(struct semaphore *sem);
 
 /**
@@ -145,14 +145,14 @@ EXPORT_SYMBOL(down_trylock);
 /**
  * down_timeout - acquire the semaphore within a specified time
  * @sem: the semaphore to be acquired
- * @jiffies: how long to wait before failing
+ * @timeout: how long to wait before failing
  *
  * Attempts to acquire the semaphore.  If no more tasks are allowed to
  * acquire the semaphore, calling this function will put the task to sleep.
  * If the semaphore is not released within the specified number of jiffies,
  * this function returns -ETIME.  It returns 0 if the semaphore was acquired.
  */
-int down_timeout(struct semaphore *sem, long jiffies)
+int down_timeout(struct semaphore *sem, long timeout)
 {
 	unsigned long flags;
 	int result = 0;
@@ -161,7 +161,7 @@ int down_timeout(struct semaphore *sem, long jiffies)
 	if (likely(sem->count > 0))
 		sem->count--;
 	else
-		result = __down_timeout(sem, jiffies);
+		result = __down_timeout(sem, timeout);
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
 
 	return result;
@@ -248,9 +248,9 @@ static noinline int __sched __down_killable(struct semaphore *sem)
 	return __down_common(sem, TASK_KILLABLE, MAX_SCHEDULE_TIMEOUT);
 }
 
-static noinline int __sched __down_timeout(struct semaphore *sem, long jiffies)
+static noinline int __sched __down_timeout(struct semaphore *sem, long timeout)
 {
-	return __down_common(sem, TASK_UNINTERRUPTIBLE, jiffies);
+	return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout);
 }
 
 static noinline void __sched __up(struct semaphore *sem)
diff --git a/kernel/module.c b/kernel/module.c
index 65586ffa0c98..88cec1ddb1e3 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1842,7 +1842,9 @@ static void free_module(struct module *mod)
 
 	/* We leave it in list to prevent duplicate loads, but make sure
 	 * that noone uses it while it's being deconstructed. */
+	mutex_lock(&module_mutex);
 	mod->state = MODULE_STATE_UNFORMED;
+	mutex_unlock(&module_mutex);
 
 	/* Remove dynamic debug info */
 	ddebug_remove_module(mod->name);
diff --git a/kernel/params.c b/kernel/params.c
index 041b5899d5e2..db97b791390f 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -19,6 +19,7 @@
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/module.h>
+#include <linux/moduleparam.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/slab.h>
@@ -513,8 +514,6 @@ EXPORT_SYMBOL(param_ops_string);
 #define to_module_attr(n) container_of(n, struct module_attribute, attr)
 #define to_module_kobject(n) container_of(n, struct module_kobject, kobj)
 
-extern struct kernel_param __start___param[], __stop___param[];
-
 struct param_attribute
 {
 	struct module_attribute mattr;
@@ -774,7 +773,7 @@ static struct module_kobject * __init locate_module_kobject(const char *name)
 }
 
 static void __init kernel_add_sysfs_param(const char *name,
-					  struct kernel_param *kparam,
+					  const struct kernel_param *kparam,
 					  unsigned int name_skip)
 {
 	struct module_kobject *mk;
@@ -809,7 +808,7 @@ static void __init kernel_add_sysfs_param(const char *name,
  */
 static void __init param_sysfs_builtin(void)
 {
-	struct kernel_param *kp;
+	const struct kernel_param *kp;
 	unsigned int name_len;
 	char modname[MODULE_NAME_LEN];
 
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index e4e4121fa327..bbef57f5bdfd 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -302,6 +302,10 @@ config PM_GENERIC_DOMAINS_RUNTIME
 	def_bool y
 	depends on PM_RUNTIME && PM_GENERIC_DOMAINS
 
+config PM_GENERIC_DOMAINS_OF
+	def_bool y
+	depends on PM_GENERIC_DOMAINS && OF
+
 config CPU_PM
 	bool
 	depends on SUSPEND || CPU_IDLE
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 4ee194eb524b..7b323221b9ee 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -129,6 +129,7 @@ int freeze_processes(void)
 	if (!pm_freezing)
 		atomic_inc(&system_freezing_cnt);
 
+	pm_wakeup_clear();
 	printk("Freezing user space processes ... ");
 	pm_freezing = true;
 	error = try_to_freeze_tasks(true);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index f1604d8cf489..791a61892bb5 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -725,6 +725,14 @@ static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn)
 	clear_bit(bit, addr);
 }
 
+static void memory_bm_clear_current(struct memory_bitmap *bm)
+{
+	int bit;
+
+	bit = max(bm->cur.node_bit - 1, 0);
+	clear_bit(bit, bm->cur.node->data);
+}
+
 static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
 	void *addr;
@@ -1333,23 +1341,39 @@ static struct memory_bitmap copy_bm;
 
 void swsusp_free(void)
 {
-	struct zone *zone;
-	unsigned long pfn, max_zone_pfn;
+	unsigned long fb_pfn, fr_pfn;
 
-	for_each_populated_zone(zone) {
-		max_zone_pfn = zone_end_pfn(zone);
-		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
-			if (pfn_valid(pfn)) {
-				struct page *page = pfn_to_page(pfn);
-
-				if (swsusp_page_is_forbidden(page) &&
-				    swsusp_page_is_free(page)) {
-					swsusp_unset_page_forbidden(page);
-					swsusp_unset_page_free(page);
-					__free_page(page);
-				}
-			}
+	if (!forbidden_pages_map || !free_pages_map)
+		goto out;
+
+	memory_bm_position_reset(forbidden_pages_map);
+	memory_bm_position_reset(free_pages_map);
+
+loop:
+	fr_pfn = memory_bm_next_pfn(free_pages_map);
+	fb_pfn = memory_bm_next_pfn(forbidden_pages_map);
+
+	/*
+	 * Find the next bit set in both bitmaps. This is guaranteed to
+	 * terminate when fb_pfn == fr_pfn == BM_END_OF_MAP.
+	 */
+	do {
+		if (fb_pfn < fr_pfn)
+			fb_pfn = memory_bm_next_pfn(forbidden_pages_map);
+		if (fr_pfn < fb_pfn)
+			fr_pfn = memory_bm_next_pfn(free_pages_map);
+	} while (fb_pfn != fr_pfn);
+
+	if (fr_pfn != BM_END_OF_MAP && pfn_valid(fr_pfn)) {
+		struct page *page = pfn_to_page(fr_pfn);
+
+		memory_bm_clear_current(forbidden_pages_map);
+		memory_bm_clear_current(free_pages_map);
+		__free_page(page);
+		goto loop;
 	}
+
+out:
 	nr_copy_pages = 0;
 	nr_meta_pages = 0;
 	restore_pblist = NULL;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 18c62195660f..4ca9a33ff620 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -146,17 +146,29 @@ static int platform_suspend_prepare(suspend_state_t state)
 
 static int platform_suspend_prepare_late(suspend_state_t state)
 {
+	return state == PM_SUSPEND_FREEZE && freeze_ops->prepare ?
+		freeze_ops->prepare() : 0;
+}
+
+static int platform_suspend_prepare_noirq(suspend_state_t state)
+{
 	return state != PM_SUSPEND_FREEZE && suspend_ops->prepare_late ?
 		suspend_ops->prepare_late() : 0;
 }
 
-static void platform_suspend_wake(suspend_state_t state)
+static void platform_resume_noirq(suspend_state_t state)
 {
 	if (state != PM_SUSPEND_FREEZE && suspend_ops->wake)
 		suspend_ops->wake();
 }
 
-static void platform_suspend_finish(suspend_state_t state)
+static void platform_resume_early(suspend_state_t state)
+{
+	if (state == PM_SUSPEND_FREEZE && freeze_ops->restore)
+		freeze_ops->restore();
+}
+
+static void platform_resume_finish(suspend_state_t state)
 {
 	if (state != PM_SUSPEND_FREEZE && suspend_ops->finish)
 		suspend_ops->finish();
@@ -172,7 +184,7 @@ static int platform_suspend_begin(suspend_state_t state)
 		return 0;
 }
 
-static void platform_suspend_end(suspend_state_t state)
+static void platform_resume_end(suspend_state_t state)
 {
 	if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->end)
 		freeze_ops->end();
@@ -180,7 +192,7 @@ static void platform_suspend_end(suspend_state_t state)
 		suspend_ops->end();
 }
 
-static void platform_suspend_recover(suspend_state_t state)
+static void platform_recover(suspend_state_t state)
 {
 	if (state != PM_SUSPEND_FREEZE && suspend_ops->recover)
 		suspend_ops->recover();
@@ -265,13 +277,22 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	if (error)
 		goto Platform_finish;
 
-	error = dpm_suspend_end(PMSG_SUSPEND);
+	error = dpm_suspend_late(PMSG_SUSPEND);
 	if (error) {
-		printk(KERN_ERR "PM: Some devices failed to power down\n");
+		printk(KERN_ERR "PM: late suspend of devices failed\n");
 		goto Platform_finish;
 	}
 	error = platform_suspend_prepare_late(state);
 	if (error)
+		goto Devices_early_resume;
+
+	error = dpm_suspend_noirq(PMSG_SUSPEND);
+	if (error) {
+		printk(KERN_ERR "PM: noirq suspend of devices failed\n");
+		goto Platform_early_resume;
+	}
+	error = platform_suspend_prepare_noirq(state);
+	if (error)
 		goto Platform_wake;
 
 	if (suspend_test(TEST_PLATFORM))
@@ -318,11 +339,17 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	enable_nonboot_cpus();
 
  Platform_wake:
-	platform_suspend_wake(state);
-	dpm_resume_start(PMSG_RESUME);
+	platform_resume_noirq(state);
+	dpm_resume_noirq(PMSG_RESUME);
+
+ Platform_early_resume:
+	platform_resume_early(state);
+
+ Devices_early_resume:
+	dpm_resume_early(PMSG_RESUME);
 
  Platform_finish:
-	platform_suspend_finish(state);
+	platform_resume_finish(state);
 	return error;
 }
 
@@ -361,14 +388,16 @@ int suspend_devices_and_enter(suspend_state_t state)
 	suspend_test_start();
 	dpm_resume_end(PMSG_RESUME);
 	suspend_test_finish("resume devices");
+	trace_suspend_resume(TPS("resume_console"), state, true);
 	resume_console();
+	trace_suspend_resume(TPS("resume_console"), state, false);
 
  Close:
-	platform_suspend_end(state);
+	platform_resume_end(state);
 	return error;
 
  Recover_platform:
-	platform_suspend_recover(state);
+	platform_recover(state);
 	goto Resume_devices;
 }
 
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index bd91bc177c93..084452e34a12 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -22,6 +22,8 @@
 #define TEST_SUSPEND_SECONDS	10
 
 static unsigned long suspend_test_start_time;
+static u32 test_repeat_count_max = 1;
+static u32 test_repeat_count_current;
 
 void suspend_test_start(void)
 {
@@ -74,6 +76,7 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
 	int			status;
 
 	/* this may fail if the RTC hasn't been initialized */
+repeat:
 	status = rtc_read_time(rtc, &alm.time);
 	if (status < 0) {
 		printk(err_readtime, dev_name(&rtc->dev), status);
@@ -100,10 +103,21 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
 	if (state == PM_SUSPEND_STANDBY) {
 		printk(info_test, pm_states[state]);
 		status = pm_suspend(state);
+		if (status < 0)
+			state = PM_SUSPEND_FREEZE;
 	}
+	if (state == PM_SUSPEND_FREEZE) {
+		printk(info_test, pm_states[state]);
+		status = pm_suspend(state);
+	}
+
 	if (status < 0)
 		printk(err_suspend, status);
 
+	test_repeat_count_current++;
+	if (test_repeat_count_current < test_repeat_count_max)
+		goto repeat;
+
 	/* Some platforms can't detect that the alarm triggered the
 	 * wakeup, or (accordingly) disable it after it afterwards.
 	 * It's supposed to give oneshot behavior; cope.
@@ -137,16 +151,28 @@ static char warn_bad_state[] __initdata =
 static int __init setup_test_suspend(char *value)
 {
 	int i;
+	char *repeat;
+	char *suspend_type;
 
-	/* "=mem" ==> "mem" */
+	/* example : "=mem[,N]" ==> "mem[,N]" */
 	value++;
+	suspend_type = strsep(&value, ",");
+	if (!suspend_type)
+		return 0;
+
+	repeat = strsep(&value, ",");
+	if (repeat) {
+		if (kstrtou32(repeat, 0, &test_repeat_count_max))
+			return 0;
+	}
+
 	for (i = 0; pm_labels[i]; i++)
-		if (!strcmp(pm_labels[i], value)) {
+		if (!strcmp(pm_labels[i], suspend_type)) {
 			test_state_label = pm_labels[i];
 			return 0;
 		}
 
-	printk(warn_bad_state, value);
+	printk(warn_bad_state, suspend_type);
 	return 0;
 }
 __setup("test_suspend", setup_test_suspend);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 1ce770687ea8..ced2b84b1cb7 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -267,7 +267,6 @@ static u32 clear_idx;
 #define LOG_ALIGN __alignof__(struct printk_log)
 #endif
 #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
-#define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT)
 static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
 static char *log_buf = __log_buf;
 static u32 log_buf_len = __LOG_BUF_LEN;
@@ -519,14 +518,13 @@ struct devkmsg_user {
 	char buf[8192];
 };
 
-static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv,
-			      unsigned long count, loff_t pos)
+static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	char *buf, *line;
 	int i;
 	int level = default_message_loglevel;
 	int facility = 1;	/* LOG_USER */
-	size_t len = iov_length(iv, count);
+	size_t len = iocb->ki_nbytes;
 	ssize_t ret = len;
 
 	if (len > LOG_LINE_MAX)
@@ -535,13 +533,10 @@ static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv,
 	if (buf == NULL)
 		return -ENOMEM;
 
-	line = buf;
-	for (i = 0; i < count; i++) {
-		if (copy_from_user(line, iv[i].iov_base, iv[i].iov_len)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		line += iv[i].iov_len;
+	buf[len] = '\0';
+	if (copy_from_iter(buf, len, from) != len) {
+		kfree(buf);
+		return -EFAULT;
 	}
 
 	/*
@@ -567,10 +562,8 @@ static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv,
 			line = endp;
 		}
 	}
-	line[len] = '\0';
 
 	printk_emit(facility, level, NULL, 0, "%s", line);
-out:
 	kfree(buf);
 	return ret;
 }
@@ -802,7 +795,7 @@ static int devkmsg_release(struct inode *inode, struct file *file)
 const struct file_operations kmsg_fops = {
 	.open = devkmsg_open,
 	.read = devkmsg_read,
-	.aio_write = devkmsg_writev,
+	.write_iter = devkmsg_write,
 	.llseek = devkmsg_llseek,
 	.poll = devkmsg_poll,
 	.release = devkmsg_release,
@@ -858,6 +851,9 @@ static int __init log_buf_len_setup(char *str)
 }
 early_param("log_buf_len", log_buf_len_setup);
 
+#ifdef CONFIG_SMP
+#define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT)
+
 static void __init log_buf_add_cpu(void)
 {
 	unsigned int cpu_extra;
@@ -884,6 +880,9 @@ static void __init log_buf_add_cpu(void)
 
 	log_buf_len_update(cpu_extra + __LOG_BUF_LEN);
 }
+#else /* !CONFIG_SMP */
+static inline void log_buf_add_cpu(void) {}
+#endif /* CONFIG_SMP */
 
 void __init setup_log_buf(int early)
 {
@@ -1680,12 +1679,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 	 * The printf needs to come first; we need the syslog
 	 * prefix which might be passed-in as a parameter.
 	 */
-	if (in_sched)
-		text_len = scnprintf(text, sizeof(textbuf),
-				     KERN_WARNING "[sched_delayed] ");
-
-	text_len += vscnprintf(text + text_len,
-			       sizeof(textbuf) - text_len, fmt, args);
+	text_len = vscnprintf(text, sizeof(textbuf), fmt, args);
 
 	/* mark and strip a trailing newline */
 	if (text_len && text[text_len-1] == '\n') {
@@ -2628,7 +2622,7 @@ void wake_up_klogd(void)
 	preempt_disable();
 	if (waitqueue_active(&log_wait)) {
 		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
-		irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
+		irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
 	}
 	preempt_enable();
 }
@@ -2644,7 +2638,7 @@ int printk_deferred(const char *fmt, ...)
 	va_end(args);
 
 	__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
-	irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
+	irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
 	preempt_enable();
 
 	return r;
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 948a7693748e..240fa9094f83 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -49,11 +49,19 @@
 #include <linux/trace_clock.h>
 #include <asm/byteorder.h>
 #include <linux/torture.h>
+#include <linux/vmalloc.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
 
 
+torture_param(int, cbflood_inter_holdoff, HZ,
+	      "Holdoff between floods (jiffies)");
+torture_param(int, cbflood_intra_holdoff, 1,
+	      "Holdoff between bursts (jiffies)");
+torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable");
+torture_param(int, cbflood_n_per_burst, 20000,
+	      "# callbacks per burst in flood");
 torture_param(int, fqs_duration, 0,
 	      "Duration of fqs bursts (us), 0 to disable");
 torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
@@ -96,10 +104,12 @@ module_param(torture_type, charp, 0444);
 MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)");
 
 static int nrealreaders;
+static int ncbflooders;
 static struct task_struct *writer_task;
 static struct task_struct **fakewriter_tasks;
 static struct task_struct **reader_tasks;
 static struct task_struct *stats_task;
+static struct task_struct **cbflood_task;
 static struct task_struct *fqs_task;
 static struct task_struct *boost_tasks[NR_CPUS];
 static struct task_struct *stall_task;
@@ -138,6 +148,7 @@ static long n_rcu_torture_boosts;
 static long n_rcu_torture_timers;
 static long n_barrier_attempts;
 static long n_barrier_successes;
+static atomic_long_t n_cbfloods;
 static struct list_head rcu_torture_removed;
 
 static int rcu_torture_writer_state;
@@ -157,9 +168,9 @@ static int rcu_torture_writer_state;
 #else
 #define RCUTORTURE_RUNNABLE_INIT 0
 #endif
-int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
-module_param(rcutorture_runnable, int, 0444);
-MODULE_PARM_DESC(rcutorture_runnable, "Start rcutorture at boot");
+static int torture_runnable = RCUTORTURE_RUNNABLE_INIT;
+module_param(torture_runnable, int, 0444);
+MODULE_PARM_DESC(torture_runnable, "Start rcutorture at boot");
 
 #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU)
 #define rcu_can_boost() 1
@@ -182,7 +193,7 @@ static u64 notrace rcu_trace_clock_local(void)
 #endif /* #else #ifdef CONFIG_RCU_TRACE */
 
 static unsigned long boost_starttime;	/* jiffies of next boost test start. */
-DEFINE_MUTEX(boost_mutex);		/* protect setting boost_starttime */
+static DEFINE_MUTEX(boost_mutex);	/* protect setting boost_starttime */
 					/*  and boost task create/destroy. */
 static atomic_t barrier_cbs_count;	/* Barrier callbacks registered. */
 static bool barrier_phase;		/* Test phase. */
@@ -242,7 +253,7 @@ struct rcu_torture_ops {
 	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
-	void (*stats)(char *page);
+	void (*stats)(void);
 	int irq_capable;
 	int can_boost;
 	const char *name;
@@ -525,21 +536,21 @@ static void srcu_torture_barrier(void)
 	srcu_barrier(&srcu_ctl);
 }
 
-static void srcu_torture_stats(char *page)
+static void srcu_torture_stats(void)
 {
 	int cpu;
 	int idx = srcu_ctl.completed & 0x1;
 
-	page += sprintf(page, "%s%s per-CPU(idx=%d):",
-		       torture_type, TORTURE_FLAG, idx);
+	pr_alert("%s%s per-CPU(idx=%d):",
+		 torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
 		long c0, c1;
 
 		c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx];
 		c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx];
-		page += sprintf(page, " %d(%ld,%ld)", cpu, c0, c1);
+		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
 	}
-	sprintf(page, "\n");
+	pr_cont("\n");
 }
 
 static void srcu_torture_synchronize_expedited(void)
@@ -601,6 +612,52 @@ static struct rcu_torture_ops sched_ops = {
 	.name		= "sched"
 };
 
+#ifdef CONFIG_TASKS_RCU
+
+/*
+ * Definitions for RCU-tasks torture testing.
+ */
+
+static int tasks_torture_read_lock(void)
+{
+	return 0;
+}
+
+static void tasks_torture_read_unlock(int idx)
+{
+}
+
+static void rcu_tasks_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_tasks(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops tasks_ops = {
+	.ttype		= RCU_TASKS_FLAVOR,
+	.init		= rcu_sync_torture_init,
+	.readlock	= tasks_torture_read_lock,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= tasks_torture_read_unlock,
+	.completed	= rcu_no_completed,
+	.deferred_free	= rcu_tasks_torture_deferred_free,
+	.sync		= synchronize_rcu_tasks,
+	.exp_sync	= synchronize_rcu_tasks,
+	.call		= call_rcu_tasks,
+	.cb_barrier	= rcu_barrier_tasks,
+	.fqs		= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "tasks"
+};
+
+#define RCUTORTURE_TASKS_OPS &tasks_ops,
+
+#else /* #ifdef CONFIG_TASKS_RCU */
+
+#define RCUTORTURE_TASKS_OPS
+
+#endif /* #else #ifdef CONFIG_TASKS_RCU */
+
 /*
  * RCU torture priority-boost testing.  Runs one real-time thread per
  * CPU for moderate bursts, repeatedly registering RCU callbacks and
@@ -667,7 +724,7 @@ static int rcu_torture_boost(void *arg)
 				}
 				call_rcu_time = jiffies;
 			}
-			cond_resched();
+			cond_resched_rcu_qs();
 			stutter_wait("rcu_torture_boost");
 			if (torture_must_stop())
 				goto checkwait;
@@ -707,6 +764,58 @@ checkwait:	stutter_wait("rcu_torture_boost");
 	return 0;
 }
 
+static void rcu_torture_cbflood_cb(struct rcu_head *rhp)
+{
+}
+
+/*
+ * RCU torture callback-flood kthread.  Repeatedly induces bursts of calls
+ * to call_rcu() or analogous, increasing the probability of occurrence
+ * of callback-overflow corner cases.
+ */
+static int
+rcu_torture_cbflood(void *arg)
+{
+	int err = 1;
+	int i;
+	int j;
+	struct rcu_head *rhp;
+
+	if (cbflood_n_per_burst > 0 &&
+	    cbflood_inter_holdoff > 0 &&
+	    cbflood_intra_holdoff > 0 &&
+	    cur_ops->call &&
+	    cur_ops->cb_barrier) {
+		rhp = vmalloc(sizeof(*rhp) *
+			      cbflood_n_burst * cbflood_n_per_burst);
+		err = !rhp;
+	}
+	if (err) {
+		VERBOSE_TOROUT_STRING("rcu_torture_cbflood disabled: Bad args or OOM");
+		while (!torture_must_stop())
+			schedule_timeout_interruptible(HZ);
+		return 0;
+	}
+	VERBOSE_TOROUT_STRING("rcu_torture_cbflood task started");
+	do {
+		schedule_timeout_interruptible(cbflood_inter_holdoff);
+		atomic_long_inc(&n_cbfloods);
+		WARN_ON(signal_pending(current));
+		for (i = 0; i < cbflood_n_burst; i++) {
+			for (j = 0; j < cbflood_n_per_burst; j++) {
+				cur_ops->call(&rhp[i * cbflood_n_per_burst + j],
+					      rcu_torture_cbflood_cb);
+			}
+			schedule_timeout_interruptible(cbflood_intra_holdoff);
+			WARN_ON(signal_pending(current));
+		}
+		cur_ops->cb_barrier();
+		stutter_wait("rcu_torture_cbflood");
+	} while (!torture_must_stop());
+	torture_kthread_stopping("rcu_torture_cbflood");
+	return 0;
+}
+
 /*
  * RCU torture force-quiescent-state kthread.  Repeatedly induces
  * bursts of calls to force_quiescent_state(), increasing the probability
@@ -1019,7 +1128,7 @@ rcu_torture_reader(void *arg)
 		__this_cpu_inc(rcu_torture_batch[completed]);
 		preempt_enable();
 		cur_ops->readunlock(idx);
-		cond_resched();
+		cond_resched_rcu_qs();
 		stutter_wait("rcu_torture_reader");
 	} while (!torture_must_stop());
 	if (irqreader && cur_ops->irq_capable) {
@@ -1031,10 +1140,15 @@ rcu_torture_reader(void *arg)
 }
 
 /*
- * Create an RCU-torture statistics message in the specified buffer.
+ * Print torture statistics.  Caller must ensure that there is only
+ * one call to this function at a given time!!!  This is normally
+ * accomplished by relying on the module system to only have one copy
+ * of the module loaded, and then by giving the rcu_torture_stats
+ * kthread full control (or the init/cleanup functions when rcu_torture_stats
+ * thread is not running).
  */
 static void
-rcu_torture_printk(char *page)
+rcu_torture_stats_print(void)
 {
 	int cpu;
 	int i;
@@ -1052,55 +1166,61 @@ rcu_torture_printk(char *page)
 		if (pipesummary[i] != 0)
 			break;
 	}
-	page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
-	page += sprintf(page,
-		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
-		       rcu_torture_current,
-		       rcu_torture_current_version,
-		       list_empty(&rcu_torture_freelist),
-		       atomic_read(&n_rcu_torture_alloc),
-		       atomic_read(&n_rcu_torture_alloc_fail),
-		       atomic_read(&n_rcu_torture_free));
-	page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ",
-		       atomic_read(&n_rcu_torture_mberror),
-		       n_rcu_torture_boost_ktrerror,
-		       n_rcu_torture_boost_rterror);
-	page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ",
-		       n_rcu_torture_boost_failure,
-		       n_rcu_torture_boosts,
-		       n_rcu_torture_timers);
-	page = torture_onoff_stats(page);
-	page += sprintf(page, "barrier: %ld/%ld:%ld",
-		       n_barrier_successes,
-		       n_barrier_attempts,
-		       n_rcu_torture_barrier_error);
-	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+
+	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
+	pr_cont("rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
+		rcu_torture_current,
+		rcu_torture_current_version,
+		list_empty(&rcu_torture_freelist),
+		atomic_read(&n_rcu_torture_alloc),
+		atomic_read(&n_rcu_torture_alloc_fail),
+		atomic_read(&n_rcu_torture_free));
+	pr_cont("rtmbe: %d rtbke: %ld rtbre: %ld ",
+		atomic_read(&n_rcu_torture_mberror),
+		n_rcu_torture_boost_ktrerror,
+		n_rcu_torture_boost_rterror);
+	pr_cont("rtbf: %ld rtb: %ld nt: %ld ",
+		n_rcu_torture_boost_failure,
+		n_rcu_torture_boosts,
+		n_rcu_torture_timers);
+	torture_onoff_stats();
+	pr_cont("barrier: %ld/%ld:%ld ",
+		n_barrier_successes,
+		n_barrier_attempts,
+		n_rcu_torture_barrier_error);
+	pr_cont("cbflood: %ld\n", atomic_long_read(&n_cbfloods));
+
+	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
 	    n_rcu_torture_barrier_error != 0 ||
 	    n_rcu_torture_boost_ktrerror != 0 ||
 	    n_rcu_torture_boost_rterror != 0 ||
 	    n_rcu_torture_boost_failure != 0 ||
 	    i > 1) {
-		page += sprintf(page, "!!! ");
+		pr_cont("%s", "!!! ");
 		atomic_inc(&n_rcu_torture_error);
 		WARN_ON_ONCE(1);
 	}
-	page += sprintf(page, "Reader Pipe: ");
+	pr_cont("Reader Pipe: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		page += sprintf(page, " %ld", pipesummary[i]);
-	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
-	page += sprintf(page, "Reader Batch: ");
+		pr_cont(" %ld", pipesummary[i]);
+	pr_cont("\n");
+
+	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
+	pr_cont("Reader Batch: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		page += sprintf(page, " %ld", batchsummary[i]);
-	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
-	page += sprintf(page, "Free-Block Circulation: ");
+		pr_cont(" %ld", batchsummary[i]);
+	pr_cont("\n");
+
+	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
+	pr_cont("Free-Block Circulation: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
-		page += sprintf(page, " %d",
-			       atomic_read(&rcu_torture_wcount[i]));
+		pr_cont(" %d", atomic_read(&rcu_torture_wcount[i]));
 	}
-	page += sprintf(page, "\n");
+	pr_cont("\n");
+
 	if (cur_ops->stats)
-		cur_ops->stats(page);
+		cur_ops->stats();
 	if (rtcv_snap == rcu_torture_current_version &&
 	    rcu_torture_current != NULL) {
 		int __maybe_unused flags;
@@ -1109,10 +1229,9 @@ rcu_torture_printk(char *page)
 
 		rcutorture_get_gp_data(cur_ops->ttype,
 				       &flags, &gpnum, &completed);
-		page += sprintf(page,
-				"??? Writer stall state %d g%lu c%lu f%#x\n",
-				rcu_torture_writer_state,
-				gpnum, completed, flags);
+		pr_alert("??? Writer stall state %d g%lu c%lu f%#x\n",
+			 rcu_torture_writer_state,
+			 gpnum, completed, flags);
 		show_rcu_gp_kthreads();
 		rcutorture_trace_dump();
 	}
@@ -1120,30 +1239,6 @@ rcu_torture_printk(char *page)
 }
 
 /*
- * Print torture statistics.  Caller must ensure that there is only
- * one call to this function at a given time!!!  This is normally
- * accomplished by relying on the module system to only have one copy
- * of the module loaded, and then by giving the rcu_torture_stats
- * kthread full control (or the init/cleanup functions when rcu_torture_stats
- * thread is not running).
- */
-static void
-rcu_torture_stats_print(void)
-{
-	int size = nr_cpu_ids * 200 + 8192;
-	char *buf;
-
-	buf = kmalloc(size, GFP_KERNEL);
-	if (!buf) {
-		pr_err("rcu-torture: Out of memory, need: %d", size);
-		return;
-	}
-	rcu_torture_printk(buf);
-	pr_alert("%s", buf);
-	kfree(buf);
-}
-
-/*
  * Periodically prints torture statistics, if periodic statistics printing
  * was specified via the stat_interval module parameter.
  */
@@ -1295,7 +1390,8 @@ static int rcu_torture_barrier_cbs(void *arg)
 		if (atomic_dec_and_test(&barrier_cbs_count))
 			wake_up(&barrier_wq);
 	} while (!torture_must_stop());
-	cur_ops->cb_barrier();
+	if (cur_ops->cb_barrier != NULL)
+		cur_ops->cb_barrier();
 	destroy_rcu_head_on_stack(&rcu);
 	torture_kthread_stopping("rcu_torture_barrier_cbs");
 	return 0;
@@ -1418,7 +1514,7 @@ rcu_torture_cleanup(void)
 	int i;
 
 	rcutorture_record_test_transition();
-	if (torture_cleanup()) {
+	if (torture_cleanup_begin()) {
 		if (cur_ops->cb_barrier != NULL)
 			cur_ops->cb_barrier();
 		return;
@@ -1447,6 +1543,8 @@ rcu_torture_cleanup(void)
 
 	torture_stop_kthread(rcu_torture_stats, stats_task);
 	torture_stop_kthread(rcu_torture_fqs, fqs_task);
+	for (i = 0; i < ncbflooders; i++)
+		torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]);
 	if ((test_boost == 1 && cur_ops->can_boost) ||
 	    test_boost == 2) {
 		unregister_cpu_notifier(&rcutorture_cpu_nb);
@@ -1468,6 +1566,7 @@ rcu_torture_cleanup(void)
 					       "End of test: RCU_HOTPLUG");
 	else
 		rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS");
+	torture_cleanup_end();
 }
 
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
@@ -1534,9 +1633,10 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
 		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
+		RCUTORTURE_TASKS_OPS
 	};
 
-	if (!torture_init_begin(torture_type, verbose, &rcutorture_runnable))
+	if (!torture_init_begin(torture_type, verbose, &torture_runnable))
 		return -EBUSY;
 
 	/* Process args and tell the world that the torturer is on the job. */
@@ -1693,6 +1793,24 @@ rcu_torture_init(void)
 		goto unwind;
 	if (object_debug)
 		rcu_test_debug_objects();
+	if (cbflood_n_burst > 0) {
+		/* Create the cbflood threads */
+		ncbflooders = (num_online_cpus() + 3) / 4;
+		cbflood_task = kcalloc(ncbflooders, sizeof(*cbflood_task),
+				       GFP_KERNEL);
+		if (!cbflood_task) {
+			VERBOSE_TOROUT_ERRSTRING("out of memory");
+			firsterr = -ENOMEM;
+			goto unwind;
+		}
+		for (i = 0; i < ncbflooders; i++) {
+			firsterr = torture_create_kthread(rcu_torture_cbflood,
+							  NULL,
+							  cbflood_task[i]);
+			if (firsterr)
+				goto unwind;
+		}
+	}
 	rcutorture_record_test_transition();
 	torture_init_end();
 	return 0;
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index d9efcc13008c..c0623fc47125 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -51,7 +51,7 @@ static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 
 #include "tiny_plugin.h"
 
-/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */
+/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcu/tree.c. */
 static void rcu_idle_enter_common(long long newval)
 {
 	if (newval) {
@@ -62,7 +62,7 @@ static void rcu_idle_enter_common(long long newval)
 	}
 	RCU_TRACE(trace_rcu_dyntick(TPS("Start"),
 				    rcu_dynticks_nesting, newval));
-	if (!is_idle_task(current)) {
+	if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
 
 		RCU_TRACE(trace_rcu_dyntick(TPS("Entry error: not idle task"),
@@ -72,7 +72,7 @@ static void rcu_idle_enter_common(long long newval)
 			  current->pid, current->comm,
 			  idle->pid, idle->comm); /* must be idle task! */
 	}
-	rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+	rcu_sched_qs(); /* implies rcu_bh_inc() */
 	barrier();
 	rcu_dynticks_nesting = newval;
 }
@@ -114,7 +114,7 @@ void rcu_irq_exit(void)
 }
 EXPORT_SYMBOL_GPL(rcu_irq_exit);
 
-/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcutree.c. */
+/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcu/tree.c. */
 static void rcu_idle_exit_common(long long oldval)
 {
 	if (oldval) {
@@ -123,7 +123,7 @@ static void rcu_idle_exit_common(long long oldval)
 		return;
 	}
 	RCU_TRACE(trace_rcu_dyntick(TPS("End"), oldval, rcu_dynticks_nesting));
-	if (!is_idle_task(current)) {
+	if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
 
 		RCU_TRACE(trace_rcu_dyntick(TPS("Exit error: not idle task"),
@@ -217,7 +217,7 @@ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
  * are at it, given that any rcu quiescent state is also an rcu_bh
  * quiescent state.  Use "+" instead of "||" to defeat short circuiting.
  */
-void rcu_sched_qs(int cpu)
+void rcu_sched_qs(void)
 {
 	unsigned long flags;
 
@@ -231,7 +231,7 @@ void rcu_sched_qs(int cpu)
 /*
  * Record an rcu_bh quiescent state.
  */
-void rcu_bh_qs(int cpu)
+void rcu_bh_qs(void)
 {
 	unsigned long flags;
 
@@ -251,9 +251,11 @@ void rcu_check_callbacks(int cpu, int user)
 {
 	RCU_TRACE(check_cpu_stalls());
 	if (user || rcu_is_cpu_rrupt_from_idle())
-		rcu_sched_qs(cpu);
+		rcu_sched_qs();
 	else if (!in_softirq())
-		rcu_bh_qs(cpu);
+		rcu_bh_qs();
+	if (user)
+		rcu_note_voluntary_context_switch(current);
 }
 
 /*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1b70cb6fbe3c..133e47223095 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -79,9 +79,18 @@ static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
  * the tracing userspace tools to be able to decipher the string
  * address to the matching string.
  */
-#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
+#ifdef CONFIG_TRACING
+# define DEFINE_RCU_TPS(sname) \
 static char sname##_varname[] = #sname; \
-static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname; \
+static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname;
+# define RCU_STATE_NAME(sname) sname##_varname
+#else
+# define DEFINE_RCU_TPS(sname)
+# define RCU_STATE_NAME(sname) __stringify(sname)
+#endif
+
+#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
+DEFINE_RCU_TPS(sname) \
 struct rcu_state sname##_state = { \
 	.level = { &sname##_state.node[0] }, \
 	.call = cr, \
@@ -93,7 +102,7 @@ struct rcu_state sname##_state = { \
 	.orphan_donetail = &sname##_state.orphan_donelist, \
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
 	.onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \
-	.name = sname##_varname, \
+	.name = RCU_STATE_NAME(sname), \
 	.abbr = sabbr, \
 }; \
 DEFINE_PER_CPU(struct rcu_data, sname##_data)
@@ -188,22 +197,24 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
  * one since the start of the grace period, this just sets a flag.
  * The caller must have disabled preemption.
  */
-void rcu_sched_qs(int cpu)
+void rcu_sched_qs(void)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);
-
-	if (rdp->passed_quiesce == 0)
-		trace_rcu_grace_period(TPS("rcu_sched"), rdp->gpnum, TPS("cpuqs"));
-	rdp->passed_quiesce = 1;
+	if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) {
+		trace_rcu_grace_period(TPS("rcu_sched"),
+				       __this_cpu_read(rcu_sched_data.gpnum),
+				       TPS("cpuqs"));
+		__this_cpu_write(rcu_sched_data.passed_quiesce, 1);
+	}
 }
 
-void rcu_bh_qs(int cpu)
+void rcu_bh_qs(void)
 {
-	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
-
-	if (rdp->passed_quiesce == 0)
-		trace_rcu_grace_period(TPS("rcu_bh"), rdp->gpnum, TPS("cpuqs"));
-	rdp->passed_quiesce = 1;
+	if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) {
+		trace_rcu_grace_period(TPS("rcu_bh"),
+				       __this_cpu_read(rcu_bh_data.gpnum),
+				       TPS("cpuqs"));
+		__this_cpu_write(rcu_bh_data.passed_quiesce, 1);
+	}
 }
 
 static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
@@ -278,7 +289,7 @@ static void rcu_momentary_dyntick_idle(void)
 void rcu_note_context_switch(int cpu)
 {
 	trace_rcu_utilization(TPS("Start context switch"));
-	rcu_sched_qs(cpu);
+	rcu_sched_qs();
 	rcu_preempt_note_context_switch(cpu);
 	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
 		rcu_momentary_dyntick_idle();
@@ -526,6 +537,7 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 	atomic_inc(&rdtp->dynticks);
 	smp_mb__after_atomic();  /* Force ordering with next sojourn. */
 	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+	rcu_dynticks_task_enter();
 
 	/*
 	 * It is illegal to enter an extended quiescent state while
@@ -642,6 +654,7 @@ void rcu_irq_exit(void)
 static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
 			       int user)
 {
+	rcu_dynticks_task_exit();
 	smp_mb__before_atomic();  /* Force ordering w/previous sojourn. */
 	atomic_inc(&rdtp->dynticks);
 	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
@@ -819,7 +832,7 @@ bool notrace __rcu_is_watching(void)
  */
 bool notrace rcu_is_watching(void)
 {
-	int ret;
+	bool ret;
 
 	preempt_disable();
 	ret = __rcu_is_watching();
@@ -1647,7 +1660,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
-		cond_resched();
+		cond_resched_rcu_qs();
 	}
 
 	mutex_unlock(&rsp->onoff_mutex);
@@ -1668,7 +1681,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 	if (fqs_state == RCU_SAVE_DYNTICK) {
 		/* Collect dyntick-idle snapshots. */
 		if (is_sysidle_rcu_state(rsp)) {
-			isidle = 1;
+			isidle = true;
 			maxj = jiffies - ULONG_MAX / 4;
 		}
 		force_qs_rnp(rsp, dyntick_save_progress_counter,
@@ -1677,14 +1690,15 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 		fqs_state = RCU_FORCE_QS;
 	} else {
 		/* Handle dyntick-idle and offline CPUs. */
-		isidle = 0;
+		isidle = false;
 		force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj);
 	}
 	/* Clear flag to prevent immediate re-entry. */
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
-		ACCESS_ONCE(rsp->gp_flags) &= ~RCU_GP_FLAG_FQS;
+		ACCESS_ONCE(rsp->gp_flags) =
+			ACCESS_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS;
 		raw_spin_unlock_irq(&rnp->lock);
 	}
 	return fqs_state;
@@ -1736,7 +1750,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		/* smp_mb() provided by prior unlock-lock pair. */
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
-		cond_resched();
+		cond_resched_rcu_qs();
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
@@ -1785,8 +1799,8 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
 				break;
-			cond_resched();
-			flush_signals(current);
+			cond_resched_rcu_qs();
+			WARN_ON(signal_pending(current));
 			trace_rcu_grace_period(rsp->name,
 					       ACCESS_ONCE(rsp->gpnum),
 					       TPS("reqwaitsig"));
@@ -1828,11 +1842,11 @@ static int __noreturn rcu_gp_kthread(void *arg)
 				trace_rcu_grace_period(rsp->name,
 						       ACCESS_ONCE(rsp->gpnum),
 						       TPS("fqsend"));
-				cond_resched();
+				cond_resched_rcu_qs();
 			} else {
 				/* Deal with stray signal. */
-				cond_resched();
-				flush_signals(current);
+				cond_resched_rcu_qs();
+				WARN_ON(signal_pending(current));
 				trace_rcu_grace_period(rsp->name,
 						       ACCESS_ONCE(rsp->gpnum),
 						       TPS("fqswaitsig"));
@@ -1928,7 +1942,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 {
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
 	raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
-	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
+	rcu_gp_kthread_wake(rsp);
 }
 
 /*
@@ -2210,8 +2224,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 	/* Adjust any no-longer-needed kthreads. */
 	rcu_boost_kthread_setaffinity(rnp, -1);
 
-	/* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */
-
 	/* Exclude any attempts to start a new grace period. */
 	mutex_lock(&rsp->onoff_mutex);
 	raw_spin_lock_irqsave(&rsp->orphan_lock, flags);
@@ -2393,8 +2405,8 @@ void rcu_check_callbacks(int cpu, int user)
 		 * at least not while the corresponding CPU is online.
 		 */
 
-		rcu_sched_qs(cpu);
-		rcu_bh_qs(cpu);
+		rcu_sched_qs();
+		rcu_bh_qs();
 
 	} else if (!in_softirq()) {
 
@@ -2405,11 +2417,13 @@ void rcu_check_callbacks(int cpu, int user)
 		 * critical section, so note it.
 		 */
 
-		rcu_bh_qs(cpu);
+		rcu_bh_qs();
 	}
 	rcu_preempt_check_callbacks(cpu);
 	if (rcu_pending(cpu))
 		invoke_rcu_core();
+	if (user)
+		rcu_note_voluntary_context_switch(current);
 	trace_rcu_utilization(TPS("End scheduler-tick"));
 }
 
@@ -2432,7 +2446,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 	struct rcu_node *rnp;
 
 	rcu_for_each_leaf_node(rsp, rnp) {
-		cond_resched();
+		cond_resched_rcu_qs();
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
@@ -2449,7 +2463,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
 			if ((rnp->qsmask & bit) != 0) {
 				if ((rnp->qsmaskinit & bit) != 0)
-					*isidle = 0;
+					*isidle = false;
 				if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
 					mask |= bit;
 			}
@@ -2505,9 +2519,10 @@ static void force_quiescent_state(struct rcu_state *rsp)
 		raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
 		return;  /* Someone beat us to it. */
 	}
-	ACCESS_ONCE(rsp->gp_flags) |= RCU_GP_FLAG_FQS;
+	ACCESS_ONCE(rsp->gp_flags) =
+		ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS;
 	raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
-	wake_up(&rsp->gp_wq);  /* Memory barrier implied by wake_up() path. */
+	rcu_gp_kthread_wake(rsp);
 }
 
 /*
@@ -2925,11 +2940,6 @@ static int synchronize_sched_expedited_cpu_stop(void *data)
  * restructure your code to batch your updates, and then use a single
  * synchronize_sched() instead.
  *
- * Note that it is illegal to call this function while holding any lock
- * that is acquired by a CPU-hotplug notifier.  And yes, it is also illegal
- * to call this function from a CPU-hotplug notifier.  Failing to observe
- * these restriction will result in deadlock.
- *
  * This implementation can be thought of as an application of ticket
  * locking to RCU, with sync_sched_expedited_started and
  * sync_sched_expedited_done taking on the roles of the halves
@@ -2979,7 +2989,12 @@ void synchronize_sched_expedited(void)
 	 */
 	snap = atomic_long_inc_return(&rsp->expedited_start);
 	firstsnap = snap;
-	get_online_cpus();
+	if (!try_get_online_cpus()) {
+		/* CPU hotplug operation in flight, fall back to normal GP. */
+		wait_rcu_gp(call_rcu_sched);
+		atomic_long_inc(&rsp->expedited_normal);
+		return;
+	}
 	WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));
 
 	/*
@@ -3026,7 +3041,12 @@ void synchronize_sched_expedited(void)
 		 * and they started after our first try, so their grace
 		 * period works for us.
 		 */
-		get_online_cpus();
+		if (!try_get_online_cpus()) {
+			/* CPU hotplug operation in flight, use normal GP. */
+			wait_rcu_gp(call_rcu_sched);
+			atomic_long_inc(&rsp->expedited_normal);
+			return;
+		}
 		snap = atomic_long_read(&rsp->expedited_start);
 		smp_mb(); /* ensure read is before try_stop_cpus(). */
 	}
@@ -3442,6 +3462,7 @@ static int rcu_cpu_notify(struct notifier_block *self,
 	case CPU_UP_PREPARE_FROZEN:
 		rcu_prepare_cpu(cpu);
 		rcu_prepare_kthreads(cpu);
+		rcu_spawn_all_nocb_kthreads(cpu);
 		break;
 	case CPU_ONLINE:
 	case CPU_DOWN_FAILED:
@@ -3489,7 +3510,7 @@ static int rcu_pm_notify(struct notifier_block *self,
 }
 
 /*
- * Spawn the kthread that handles this RCU flavor's grace periods.
+ * Spawn the kthreads that handle each RCU flavor's grace periods.
  */
 static int __init rcu_spawn_gp_kthread(void)
 {
@@ -3498,6 +3519,7 @@ static int __init rcu_spawn_gp_kthread(void)
 	struct rcu_state *rsp;
 	struct task_struct *t;
 
+	rcu_scheduler_fully_active = 1;
 	for_each_rcu_flavor(rsp) {
 		t = kthread_run(rcu_gp_kthread, rsp, "%s", rsp->name);
 		BUG_ON(IS_ERR(t));
@@ -3505,8 +3527,9 @@ static int __init rcu_spawn_gp_kthread(void)
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rsp->gp_kthread = t;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		rcu_spawn_nocb_kthreads(rsp);
 	}
+	rcu_spawn_nocb_kthreads();
+	rcu_spawn_boost_kthreads();
 	return 0;
 }
 early_initcall(rcu_spawn_gp_kthread);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 6a86eb7bac45..d03764652d91 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -350,7 +350,7 @@ struct rcu_data {
 	int nocb_p_count_lazy;		/*  (approximate). */
 	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
-	bool nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
+	int nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
 
 	/* The following fields are used by the leader, hence own cacheline. */
 	struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp;
@@ -383,6 +383,11 @@ struct rcu_data {
 #define RCU_FORCE_QS		3	/* Need to force quiescent state. */
 #define RCU_SIGNAL_INIT		RCU_SAVE_DYNTICK
 
+/* Values for nocb_defer_wakeup field in struct rcu_data. */
+#define RCU_NOGP_WAKE_NOT	0
+#define RCU_NOGP_WAKE		1
+#define RCU_NOGP_WAKE_FORCE	2
+
 #define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
 					/* For jiffies_till_first_fqs and */
 					/*  and jiffies_till_next_fqs. */
@@ -572,6 +577,7 @@ static void rcu_preempt_do_callbacks(void);
 static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 						 struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_RCU_BOOST */
+static void __init rcu_spawn_boost_kthreads(void);
 static void rcu_prepare_kthreads(int cpu);
 static void rcu_cleanup_after_idle(int cpu);
 static void rcu_prepare_for_idle(int cpu);
@@ -589,10 +595,14 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 				      struct rcu_data *rdp,
 				      unsigned long flags);
-static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
+static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
 static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
-static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
+static void rcu_spawn_all_nocb_kthreads(int cpu);
+static void __init rcu_spawn_nocb_kthreads(void);
+#ifdef CONFIG_RCU_NOCB_CPU
+static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp);
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
 static bool init_nocb_callback_list(struct rcu_data *rdp);
 static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq);
@@ -605,6 +615,8 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
 static void rcu_bind_gp_kthread(void);
 static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
 static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
+static void rcu_dynticks_task_enter(void);
+static void rcu_dynticks_task_exit(void);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index a7997e272564..387dd4599344 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -85,33 +85,6 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
-#ifdef CONFIG_RCU_NOCB_CPU
-#ifndef CONFIG_RCU_NOCB_CPU_NONE
-	if (!have_rcu_nocb_mask) {
-		zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL);
-		have_rcu_nocb_mask = true;
-	}
-#ifdef CONFIG_RCU_NOCB_CPU_ZERO
-	pr_info("\tOffload RCU callbacks from CPU 0\n");
-	cpumask_set_cpu(0, rcu_nocb_mask);
-#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
-#ifdef CONFIG_RCU_NOCB_CPU_ALL
-	pr_info("\tOffload RCU callbacks from all CPUs\n");
-	cpumask_copy(rcu_nocb_mask, cpu_possible_mask);
-#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
-	if (have_rcu_nocb_mask) {
-		if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
-			pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
-			cpumask_and(rcu_nocb_mask, cpu_possible_mask,
-				    rcu_nocb_mask);
-		}
-		cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
-		pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
-		if (rcu_nocb_poll)
-			pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
-	}
-#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 }
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
@@ -134,7 +107,7 @@ static void __init rcu_bootup_announce(void)
  * Return the number of RCU-preempt batches processed thus far
  * for debug and statistics.
  */
-long rcu_batches_completed_preempt(void)
+static long rcu_batches_completed_preempt(void)
 {
 	return rcu_preempt_state.completed;
 }
@@ -155,18 +128,19 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed);
  * not in a quiescent state.  There might be any number of tasks blocked
  * while in an RCU read-side critical section.
  *
- * Unlike the other rcu_*_qs() functions, callers to this function
- * must disable irqs in order to protect the assignment to
- * ->rcu_read_unlock_special.
- */
-static void rcu_preempt_qs(int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu);
-
-	if (rdp->passed_quiesce == 0)
-		trace_rcu_grace_period(TPS("rcu_preempt"), rdp->gpnum, TPS("cpuqs"));
-	rdp->passed_quiesce = 1;
-	current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+ * As with the other rcu_*_qs() functions, callers to this function
+ * must disable preemption.
+ */
+static void rcu_preempt_qs(void)
+{
+	if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) {
+		trace_rcu_grace_period(TPS("rcu_preempt"),
+				       __this_cpu_read(rcu_preempt_data.gpnum),
+				       TPS("cpuqs"));
+		__this_cpu_write(rcu_preempt_data.passed_quiesce, 1);
+		barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
+		current->rcu_read_unlock_special.b.need_qs = false;
+	}
 }
 
 /*
@@ -190,14 +164,14 @@ static void rcu_preempt_note_context_switch(int cpu)
 	struct rcu_node *rnp;
 
 	if (t->rcu_read_lock_nesting > 0 &&
-	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
+	    !t->rcu_read_unlock_special.b.blocked) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
 		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
-		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
+		t->rcu_read_unlock_special.b.blocked = true;
 		t->rcu_blocked_node = rnp;
 
 		/*
@@ -239,7 +213,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 				       : rnp->gpnum + 1);
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	} else if (t->rcu_read_lock_nesting < 0 &&
-		   t->rcu_read_unlock_special) {
+		   t->rcu_read_unlock_special.s) {
 
 		/*
 		 * Complete exit from RCU read-side critical section on
@@ -257,9 +231,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 	 * grace period, then the fact that the task has been enqueued
 	 * means that we continue to block the current grace period.
 	 */
-	local_irq_save(flags);
-	rcu_preempt_qs(cpu);
-	local_irq_restore(flags);
+	rcu_preempt_qs();
 }
 
 /*
@@ -340,7 +312,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 	bool drop_boost_mutex = false;
 #endif /* #ifdef CONFIG_RCU_BOOST */
 	struct rcu_node *rnp;
-	int special;
+	union rcu_special special;
 
 	/* NMI handlers cannot block and cannot safely manipulate state. */
 	if (in_nmi())
@@ -350,12 +322,13 @@ void rcu_read_unlock_special(struct task_struct *t)
 
 	/*
 	 * If RCU core is waiting for this CPU to exit critical section,
-	 * let it know that we have done so.
+	 * let it know that we have done so.  Because irqs are disabled,
+	 * t->rcu_read_unlock_special cannot change.
 	 */
 	special = t->rcu_read_unlock_special;
-	if (special & RCU_READ_UNLOCK_NEED_QS) {
-		rcu_preempt_qs(smp_processor_id());
-		if (!t->rcu_read_unlock_special) {
+	if (special.b.need_qs) {
+		rcu_preempt_qs();
+		if (!t->rcu_read_unlock_special.s) {
 			local_irq_restore(flags);
 			return;
 		}
@@ -368,8 +341,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 	}
 
 	/* Clean up if blocked during RCU read-side critical section. */
-	if (special & RCU_READ_UNLOCK_BLOCKED) {
-		t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;
+	if (special.b.blocked) {
+		t->rcu_read_unlock_special.b.blocked = false;
 
 		/*
 		 * Remove this task from the list it blocked on.  The
@@ -653,12 +626,13 @@ static void rcu_preempt_check_callbacks(int cpu)
 	struct task_struct *t = current;
 
 	if (t->rcu_read_lock_nesting == 0) {
-		rcu_preempt_qs(cpu);
+		rcu_preempt_qs();
 		return;
 	}
 	if (t->rcu_read_lock_nesting > 0 &&
-	    per_cpu(rcu_preempt_data, cpu).qs_pending)
-		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
+	    per_cpu(rcu_preempt_data, cpu).qs_pending &&
+	    !per_cpu(rcu_preempt_data, cpu).passed_quiesce)
+		t->rcu_read_unlock_special.b.need_qs = true;
 }
 
 #ifdef CONFIG_RCU_BOOST
@@ -819,11 +793,6 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
  * In fact, if you are using synchronize_rcu_expedited() in a loop,
  * please restructure your code to batch your updates, and then Use a
  * single synchronize_rcu() instead.
- *
- * Note that it is illegal to call this function while holding any lock
- * that is acquired by a CPU-hotplug notifier.  And yes, it is also illegal
- * to call this function from a CPU-hotplug notifier.  Failing to observe
- * these restriction will result in deadlock.
  */
 void synchronize_rcu_expedited(void)
 {
@@ -845,7 +814,11 @@ void synchronize_rcu_expedited(void)
 	 * being boosted.  This simplifies the process of moving tasks
 	 * from leaf to root rcu_node structures.
 	 */
-	get_online_cpus();
+	if (!try_get_online_cpus()) {
+		/* CPU-hotplug operation in flight, fall back to normal GP. */
+		wait_rcu_gp(call_rcu);
+		return;
+	}
 
 	/*
 	 * Acquire lock, falling back to synchronize_rcu() if too many
@@ -897,7 +870,8 @@ void synchronize_rcu_expedited(void)
 
 	/* Clean up and exit. */
 	smp_mb(); /* ensure expedited GP seen before counter increment. */
-	ACCESS_ONCE(sync_rcu_preempt_exp_count)++;
+	ACCESS_ONCE(sync_rcu_preempt_exp_count) =
+					sync_rcu_preempt_exp_count + 1;
 unlock_mb_ret:
 	mutex_unlock(&sync_rcu_preempt_exp_mutex);
 mb_ret:
@@ -941,7 +915,7 @@ void exit_rcu(void)
 		return;
 	t->rcu_read_lock_nesting = 1;
 	barrier();
-	t->rcu_read_unlock_special = RCU_READ_UNLOCK_BLOCKED;
+	t->rcu_read_unlock_special.b.blocked = true;
 	__rcu_read_unlock();
 }
 
@@ -1462,14 +1436,13 @@ static struct smp_hotplug_thread rcu_cpu_thread_spec = {
 };
 
 /*
- * Spawn all kthreads -- called as soon as the scheduler is running.
+ * Spawn boost kthreads -- called as soon as the scheduler is running.
  */
-static int __init rcu_spawn_kthreads(void)
+static void __init rcu_spawn_boost_kthreads(void)
 {
 	struct rcu_node *rnp;
 	int cpu;
 
-	rcu_scheduler_fully_active = 1;
 	for_each_possible_cpu(cpu)
 		per_cpu(rcu_cpu_has_work, cpu) = 0;
 	BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
@@ -1479,9 +1452,7 @@ static int __init rcu_spawn_kthreads(void)
 		rcu_for_each_leaf_node(rcu_state_p, rnp)
 			(void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp);
 	}
-	return 0;
 }
-early_initcall(rcu_spawn_kthreads);
 
 static void rcu_prepare_kthreads(int cpu)
 {
@@ -1519,12 +1490,9 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 {
 }
 
-static int __init rcu_scheduler_really_started(void)
+static void __init rcu_spawn_boost_kthreads(void)
 {
-	rcu_scheduler_fully_active = 1;
-	return 0;
 }
-early_initcall(rcu_scheduler_really_started);
 
 static void rcu_prepare_kthreads(int cpu)
 {
@@ -1625,7 +1593,7 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
 
 	/* Exit early if we advanced recently. */
 	if (jiffies == rdtp->last_advance_all)
-		return 0;
+		return false;
 	rdtp->last_advance_all = jiffies;
 
 	for_each_rcu_flavor(rsp) {
@@ -1848,7 +1816,7 @@ static int rcu_oom_notify(struct notifier_block *self,
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1);
-		cond_resched();
+		cond_resched_rcu_qs();
 	}
 	put_online_cpus();
 
@@ -2075,7 +2043,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
 	if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
 		return;
 	if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) {
-		/* Prior xchg orders against prior callback enqueue. */
+		/* Prior smp_mb__after_atomic() orders against prior enqueue. */
 		ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false;
 		wake_up(&rdp_leader->nocb_wq);
 	}
@@ -2104,6 +2072,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 	ACCESS_ONCE(*old_rhpp) = rhp;
 	atomic_long_add(rhcount, &rdp->nocb_q_count);
 	atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy);
+	smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */
 
 	/* If we are not being polled and there is a kthread, awaken it ... */
 	t = ACCESS_ONCE(rdp->nocb_kthread);
@@ -2120,16 +2089,23 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("WakeEmpty"));
 		} else {
-			rdp->nocb_defer_wakeup = true;
+			rdp->nocb_defer_wakeup = RCU_NOGP_WAKE;
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("WakeEmptyIsDeferred"));
 		}
 		rdp->qlen_last_fqs_check = 0;
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
 		/* ... or if many callbacks queued. */
-		wake_nocb_leader(rdp, true);
+		if (!irqs_disabled_flags(flags)) {
+			wake_nocb_leader(rdp, true);
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeOvf"));
+		} else {
+			rdp->nocb_defer_wakeup = RCU_NOGP_WAKE_FORCE;
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeOvfIsDeferred"));
+		}
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
-		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf"));
 	} else {
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeNot"));
 	}
@@ -2150,7 +2126,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 {
 
 	if (!rcu_is_nocb_cpu(rdp->cpu))
-		return 0;
+		return false;
 	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags);
 	if (__is_kfree_rcu_offset((unsigned long)rhp->func))
 		trace_rcu_kfree_callback(rdp->rsp->name, rhp,
@@ -2161,7 +2137,18 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 		trace_rcu_callback(rdp->rsp->name, rhp,
 				   -atomic_long_read(&rdp->nocb_q_count_lazy),
 				   -atomic_long_read(&rdp->nocb_q_count));
-	return 1;
+
+	/*
+	 * If called from an extended quiescent state with interrupts
+	 * disabled, invoke the RCU core in order to allow the idle-entry
+	 * deferred-wakeup check to function.
+	 */
+	if (irqs_disabled_flags(flags) &&
+	    !rcu_is_watching() &&
+	    cpu_online(smp_processor_id()))
+		invoke_rcu_core();
+
+	return true;
 }
 
 /*
@@ -2177,7 +2164,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 
 	/* If this is not a no-CBs CPU, tell the caller to do it the old way. */
 	if (!rcu_is_nocb_cpu(smp_processor_id()))
-		return 0;
+		return false;
 	rsp->qlen = 0;
 	rsp->qlen_lazy = 0;
 
@@ -2196,7 +2183,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 		rsp->orphan_nxtlist = NULL;
 		rsp->orphan_nxttail = &rsp->orphan_nxtlist;
 	}
-	return 1;
+	return true;
 }
 
 /*
@@ -2229,7 +2216,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 			(d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c)));
 		if (likely(d))
 			break;
-		flush_signals(current);
+		WARN_ON(signal_pending(current));
 		trace_rcu_future_gp(rnp, rdp, c, TPS("ResumeWait"));
 	}
 	trace_rcu_future_gp(rnp, rdp, c, TPS("EndWait"));
@@ -2288,7 +2275,7 @@ wait_again:
 		if (!rcu_nocb_poll)
 			trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu,
 					    "WokeEmpty");
-		flush_signals(current);
+		WARN_ON(signal_pending(current));
 		schedule_timeout_interruptible(1);
 
 		/* Rescan in case we were a victim of memory ordering. */
@@ -2327,6 +2314,7 @@ wait_again:
 		atomic_long_add(rdp->nocb_gp_count, &rdp->nocb_follower_count);
 		atomic_long_add(rdp->nocb_gp_count_lazy,
 				&rdp->nocb_follower_count_lazy);
+		smp_mb__after_atomic(); /* Store *tail before wakeup. */
 		if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
 			/*
 			 * List was empty, wake up the follower.
@@ -2367,7 +2355,7 @@ static void nocb_follower_wait(struct rcu_data *rdp)
 		if (!rcu_nocb_poll)
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    "WokeEmpty");
-		flush_signals(current);
+		WARN_ON(signal_pending(current));
 		schedule_timeout_interruptible(1);
 	}
 }
@@ -2428,15 +2416,16 @@ static int rcu_nocb_kthread(void *arg)
 			list = next;
 		}
 		trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1);
-		ACCESS_ONCE(rdp->nocb_p_count) -= c;
-		ACCESS_ONCE(rdp->nocb_p_count_lazy) -= cl;
+		ACCESS_ONCE(rdp->nocb_p_count) = rdp->nocb_p_count - c;
+		ACCESS_ONCE(rdp->nocb_p_count_lazy) =
+						rdp->nocb_p_count_lazy - cl;
 		rdp->n_nocbs_invoked += c;
 	}
 	return 0;
 }
 
 /* Is a deferred wakeup of rcu_nocb_kthread() required? */
-static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
 {
 	return ACCESS_ONCE(rdp->nocb_defer_wakeup);
 }
@@ -2444,11 +2433,79 @@ static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
 /* Do a deferred wakeup of rcu_nocb_kthread(). */
 static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
 {
+	int ndw;
+
 	if (!rcu_nocb_need_deferred_wakeup(rdp))
 		return;
-	ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
-	wake_nocb_leader(rdp, false);
-	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
+	ndw = ACCESS_ONCE(rdp->nocb_defer_wakeup);
+	ACCESS_ONCE(rdp->nocb_defer_wakeup) = RCU_NOGP_WAKE_NOT;
+	wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE);
+	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake"));
+}
+
+void __init rcu_init_nohz(void)
+{
+	int cpu;
+	bool need_rcu_nocb_mask = true;
+	struct rcu_state *rsp;
+
+#ifdef CONFIG_RCU_NOCB_CPU_NONE
+	need_rcu_nocb_mask = false;
+#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
+
+#if defined(CONFIG_NO_HZ_FULL)
+	if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask))
+		need_rcu_nocb_mask = true;
+#endif /* #if defined(CONFIG_NO_HZ_FULL) */
+
+	if (!have_rcu_nocb_mask && need_rcu_nocb_mask) {
+		if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) {
+			pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n");
+			return;
+		}
+		have_rcu_nocb_mask = true;
+	}
+	if (!have_rcu_nocb_mask)
+		return;
+
+#ifdef CONFIG_RCU_NOCB_CPU_ZERO
+	pr_info("\tOffload RCU callbacks from CPU 0\n");
+	cpumask_set_cpu(0, rcu_nocb_mask);
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
+#ifdef CONFIG_RCU_NOCB_CPU_ALL
+	pr_info("\tOffload RCU callbacks from all CPUs\n");
+	cpumask_copy(rcu_nocb_mask, cpu_possible_mask);
+#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
+#if defined(CONFIG_NO_HZ_FULL)
+	if (tick_nohz_full_running)
+		cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
+#endif /* #if defined(CONFIG_NO_HZ_FULL) */
+
+	if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
+		pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
+		cpumask_and(rcu_nocb_mask, cpu_possible_mask,
+			    rcu_nocb_mask);
+	}
+	cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
+	pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
+	if (rcu_nocb_poll)
+		pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
+
+	for_each_rcu_flavor(rsp) {
+		for_each_cpu(cpu, rcu_nocb_mask) {
+			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+
+			/*
+			 * If there are early callbacks, they will need
+			 * to be moved to the nocb lists.
+			 */
+			WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] !=
+				     &rdp->nxtlist &&
+				     rdp->nxttail[RCU_NEXT_TAIL] != NULL);
+			init_nocb_callback_list(rdp);
+		}
+		rcu_organize_nocb_kthreads(rsp);
+	}
 }
 
 /* Initialize per-rcu_data variables for no-CBs CPUs. */
@@ -2459,15 +2516,85 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 	rdp->nocb_follower_tail = &rdp->nocb_follower_head;
 }
 
+/*
+ * If the specified CPU is a no-CBs CPU that does not already have its
+ * rcuo kthread for the specified RCU flavor, spawn it.  If the CPUs are
+ * brought online out of order, this can require re-organizing the
+ * leader-follower relationships.
+ */
+static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu)
+{
+	struct rcu_data *rdp;
+	struct rcu_data *rdp_last;
+	struct rcu_data *rdp_old_leader;
+	struct rcu_data *rdp_spawn = per_cpu_ptr(rsp->rda, cpu);
+	struct task_struct *t;
+
+	/*
+	 * If this isn't a no-CBs CPU or if it already has an rcuo kthread,
+	 * then nothing to do.
+	 */
+	if (!rcu_is_nocb_cpu(cpu) || rdp_spawn->nocb_kthread)
+		return;
+
+	/* If we didn't spawn the leader first, reorganize! */
+	rdp_old_leader = rdp_spawn->nocb_leader;
+	if (rdp_old_leader != rdp_spawn && !rdp_old_leader->nocb_kthread) {
+		rdp_last = NULL;
+		rdp = rdp_old_leader;
+		do {
+			rdp->nocb_leader = rdp_spawn;
+			if (rdp_last && rdp != rdp_spawn)
+				rdp_last->nocb_next_follower = rdp;
+			rdp_last = rdp;
+			rdp = rdp->nocb_next_follower;
+			rdp_last->nocb_next_follower = NULL;
+		} while (rdp);
+		rdp_spawn->nocb_next_follower = rdp_old_leader;
+	}
+
+	/* Spawn the kthread for this CPU and RCU flavor. */
+	t = kthread_run(rcu_nocb_kthread, rdp_spawn,
+			"rcuo%c/%d", rsp->abbr, cpu);
+	BUG_ON(IS_ERR(t));
+	ACCESS_ONCE(rdp_spawn->nocb_kthread) = t;
+}
+
+/*
+ * If the specified CPU is a no-CBs CPU that does not already have its
+ * rcuo kthreads, spawn them.
+ */
+static void rcu_spawn_all_nocb_kthreads(int cpu)
+{
+	struct rcu_state *rsp;
+
+	if (rcu_scheduler_fully_active)
+		for_each_rcu_flavor(rsp)
+			rcu_spawn_one_nocb_kthread(rsp, cpu);
+}
+
+/*
+ * Once the scheduler is running, spawn rcuo kthreads for all online
+ * no-CBs CPUs.  This assumes that the early_initcall()s happen before
+ * non-boot CPUs come online -- if this changes, we will need to add
+ * some mutual exclusion.
+ */
+static void __init rcu_spawn_nocb_kthreads(void)
+{
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		rcu_spawn_all_nocb_kthreads(cpu);
+}
+
 /* How many follower CPU IDs per leader?  Default of -1 for sqrt(nr_cpu_ids). */
 static int rcu_nocb_leader_stride = -1;
 module_param(rcu_nocb_leader_stride, int, 0444);
 
 /*
- * Create a kthread for each RCU flavor for each no-CBs CPU.
- * Also initialize leader-follower relationships.
+ * Initialize leader-follower relationships for all no-CBs CPU.
  */
-static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
+static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp)
 {
 	int cpu;
 	int ls = rcu_nocb_leader_stride;
@@ -2475,14 +2602,9 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 	struct rcu_data *rdp;
 	struct rcu_data *rdp_leader = NULL;  /* Suppress misguided gcc warn. */
 	struct rcu_data *rdp_prev = NULL;
-	struct task_struct *t;
 
-	if (rcu_nocb_mask == NULL)
+	if (!have_rcu_nocb_mask)
 		return;
-#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL)
-	if (tick_nohz_full_running)
-		cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
-#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */
 	if (ls == -1) {
 		ls = int_sqrt(nr_cpu_ids);
 		rcu_nocb_leader_stride = ls;
@@ -2505,21 +2627,15 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 			rdp_prev->nocb_next_follower = rdp;
 		}
 		rdp_prev = rdp;
-
-		/* Spawn the kthread for this CPU. */
-		t = kthread_run(rcu_nocb_kthread, rdp,
-				"rcuo%c/%d", rsp->abbr, cpu);
-		BUG_ON(IS_ERR(t));
-		ACCESS_ONCE(rdp->nocb_kthread) = t;
 	}
 }
 
 /* Prevent __call_rcu() from enqueuing callbacks on no-CBs CPUs */
 static bool init_nocb_callback_list(struct rcu_data *rdp)
 {
-	if (rcu_nocb_mask == NULL ||
-	    !cpumask_test_cpu(rdp->cpu, rcu_nocb_mask))
+	if (!rcu_is_nocb_cpu(rdp->cpu))
 		return false;
+
 	rdp->nxttail[RCU_NEXT_TAIL] = NULL;
 	return true;
 }
@@ -2541,21 +2657,21 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 			    bool lazy, unsigned long flags)
 {
-	return 0;
+	return false;
 }
 
 static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 						     struct rcu_data *rdp,
 						     unsigned long flags)
 {
-	return 0;
+	return false;
 }
 
 static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
 }
 
-static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
 {
 	return false;
 }
@@ -2564,7 +2680,11 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
 {
 }
 
-static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
+static void rcu_spawn_all_nocb_kthreads(int cpu)
+{
+}
+
+static void __init rcu_spawn_nocb_kthreads(void)
 {
 }
 
@@ -2595,16 +2715,6 @@ static void __maybe_unused rcu_kick_nohz_cpu(int cpu)
 
 #ifdef CONFIG_NO_HZ_FULL_SYSIDLE
 
-/*
- * Define RCU flavor that holds sysidle state.  This needs to be the
- * most active flavor of RCU.
- */
-#ifdef CONFIG_PREEMPT_RCU
-static struct rcu_state *rcu_sysidle_state = &rcu_preempt_state;
-#else /* #ifdef CONFIG_PREEMPT_RCU */
-static struct rcu_state *rcu_sysidle_state = &rcu_sched_state;
-#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
-
 static int full_sysidle_state;		/* Current system-idle state. */
 #define RCU_SYSIDLE_NOT		0	/* Some CPU is not idle. */
 #define RCU_SYSIDLE_SHORT	1	/* All CPUs idle for brief period. */
@@ -2622,6 +2732,10 @@ static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq)
 {
 	unsigned long j;
 
+	/* If there are no nohz_full= CPUs, no need to track this. */
+	if (!tick_nohz_full_enabled())
+		return;
+
 	/* Adjust nesting, check for fully idle. */
 	if (irq) {
 		rdtp->dynticks_idle_nesting--;
@@ -2687,6 +2801,10 @@ void rcu_sysidle_force_exit(void)
  */
 static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq)
 {
+	/* If there are no nohz_full= CPUs, no need to track this. */
+	if (!tick_nohz_full_enabled())
+		return;
+
 	/* Adjust nesting, check for already non-idle. */
 	if (irq) {
 		rdtp->dynticks_idle_nesting++;
@@ -2741,12 +2859,16 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
 	unsigned long j;
 	struct rcu_dynticks *rdtp = rdp->dynticks;
 
+	/* If there are no nohz_full= CPUs, don't check system-wide idleness. */
+	if (!tick_nohz_full_enabled())
+		return;
+
 	/*
 	 * If some other CPU has already reported non-idle, if this is
 	 * not the flavor of RCU that tracks sysidle state, or if this
 	 * is an offline or the timekeeping CPU, nothing to do.
 	 */
-	if (!*isidle || rdp->rsp != rcu_sysidle_state ||
+	if (!*isidle || rdp->rsp != rcu_state_p ||
 	    cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu)
 		return;
 	if (rcu_gp_in_progress(rdp->rsp))
@@ -2772,7 +2894,7 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
  */
 static bool is_sysidle_rcu_state(struct rcu_state *rsp)
 {
-	return rsp == rcu_sysidle_state;
+	return rsp == rcu_state_p;
 }
 
 /*
@@ -2850,7 +2972,7 @@ static void rcu_sysidle_cancel(void)
 static void rcu_sysidle_report(struct rcu_state *rsp, int isidle,
 			       unsigned long maxj, bool gpkt)
 {
-	if (rsp != rcu_sysidle_state)
+	if (rsp != rcu_state_p)
 		return;  /* Wrong flavor, ignore. */
 	if (gpkt && nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL)
 		return;  /* Running state machine from timekeeping CPU. */
@@ -2867,6 +2989,10 @@ static void rcu_sysidle_report(struct rcu_state *rsp, int isidle,
 static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
 				  unsigned long maxj)
 {
+	/* If there are no nohz_full= CPUs, no need to track this. */
+	if (!tick_nohz_full_enabled())
+		return;
+
 	rcu_sysidle_report(rsp, isidle, maxj, true);
 }
 
@@ -2893,7 +3019,8 @@ static void rcu_sysidle_cb(struct rcu_head *rhp)
 
 /*
  * Check to see if the system is fully idle, other than the timekeeping CPU.
- * The caller must have disabled interrupts.
+ * The caller must have disabled interrupts.  This is not intended to be
+ * called unless tick_nohz_full_enabled().
  */
 bool rcu_sys_is_idle(void)
 {
@@ -2919,13 +3046,12 @@ bool rcu_sys_is_idle(void)
 
 			/* Scan all the CPUs looking for nonidle CPUs. */
 			for_each_possible_cpu(cpu) {
-				rdp = per_cpu_ptr(rcu_sysidle_state->rda, cpu);
+				rdp = per_cpu_ptr(rcu_state_p->rda, cpu);
 				rcu_sysidle_check_cpu(rdp, &isidle, &maxj);
 				if (!isidle)
 					break;
 			}
-			rcu_sysidle_report(rcu_sysidle_state,
-					   isidle, maxj, false);
+			rcu_sysidle_report(rcu_state_p, isidle, maxj, false);
 			oldrss = rss;
 			rss = ACCESS_ONCE(full_sysidle_state);
 		}
@@ -2952,7 +3078,7 @@ bool rcu_sys_is_idle(void)
 	 * provided by the memory allocator.
 	 */
 	if (nr_cpu_ids > CONFIG_NO_HZ_FULL_SYSIDLE_SMALL &&
-	    !rcu_gp_in_progress(rcu_sysidle_state) &&
+	    !rcu_gp_in_progress(rcu_state_p) &&
 	    !rsh.inuse && xchg(&rsh.inuse, 1) == 0)
 		call_rcu(&rsh.rh, rcu_sysidle_cb);
 	return false;
@@ -3036,3 +3162,19 @@ static void rcu_bind_gp_kthread(void)
 		housekeeping_affine(current);
 #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 }
+
+/* Record the current task on dyntick-idle entry. */
+static void rcu_dynticks_task_enter(void)
+{
+#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
+	ACCESS_ONCE(current->rcu_tasks_idle_cpu) = smp_processor_id();
+#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
+}
+
+/* Record no current task on dyntick-idle exit. */
+static void rcu_dynticks_task_exit(void)
+{
+#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
+	ACCESS_ONCE(current->rcu_tasks_idle_cpu) = -1;
+#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
+}
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 4056d7992a6c..3ef8ba58694e 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -47,6 +47,8 @@
 #include <linux/hardirq.h>
 #include <linux/delay.h>
 #include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/tick.h>
 
 #define CREATE_TRACE_POINTS
 
@@ -91,7 +93,7 @@ void __rcu_read_unlock(void)
 		barrier();  /* critical section before exit code. */
 		t->rcu_read_lock_nesting = INT_MIN;
 		barrier();  /* assign before ->rcu_read_unlock_special load */
-		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special.s)))
 			rcu_read_unlock_special(t);
 		barrier();  /* ->rcu_read_unlock_special load before assign */
 		t->rcu_read_lock_nesting = 0;
@@ -137,6 +139,38 @@ int notrace debug_lockdep_rcu_enabled(void)
 EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
 
 /**
+ * rcu_read_lock_held() - might we be in RCU read-side critical section?
+ *
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
+ * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
+ * this assumes we are in an RCU read-side critical section unless it can
+ * prove otherwise.  This is useful for debug checks in functions that
+ * require that they be called within an RCU read-side critical section.
+ *
+ * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
+ *
+ * Note that rcu_read_lock() and the matching rcu_read_unlock() must
+ * occur in the same context, for example, it is illegal to invoke
+ * rcu_read_unlock() in process context if the matching rcu_read_lock()
+ * was invoked from within an irq handler.
+ *
+ * Note that rcu_read_lock() is disallowed if the CPU is either idle or
+ * offline from an RCU perspective, so check for those as well.
+ */
+int rcu_read_lock_held(void)
+{
+	if (!debug_lockdep_rcu_enabled())
+		return 1;
+	if (!rcu_is_watching())
+		return 0;
+	if (!rcu_lockdep_current_cpu_online())
+		return 0;
+	return lock_is_held(&rcu_lock_map);
+}
+EXPORT_SYMBOL_GPL(rcu_read_lock_held);
+
+/**
  * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
  *
  * Check for bottom half being disabled, which covers both the
@@ -347,3 +381,312 @@ static int __init check_cpu_stall_init(void)
 early_initcall(check_cpu_stall_init);
 
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
+
+#ifdef CONFIG_TASKS_RCU
+
+/*
+ * Simple variant of RCU whose quiescent states are voluntary context switch,
+ * user-space execution, and idle.  As such, grace periods can take one good
+ * long time.  There are no read-side primitives similar to rcu_read_lock()
+ * and rcu_read_unlock() because this implementation is intended to get
+ * the system into a safe state for some of the manipulations involved in
+ * tracing and the like.  Finally, this implementation does not support
+ * high call_rcu_tasks() rates from multiple CPUs.  If this is required,
+ * per-CPU callback lists will be needed.
+ */
+
+/* Global list of callbacks and associated lock. */
+static struct rcu_head *rcu_tasks_cbs_head;
+static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
+static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq);
+static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock);
+
+/* Track exiting tasks in order to allow them to be waited for. */
+DEFINE_SRCU(tasks_rcu_exit_srcu);
+
+/* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
+static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 10;
+module_param(rcu_task_stall_timeout, int, 0644);
+
+static void rcu_spawn_tasks_kthread(void);
+
+/*
+ * Post an RCU-tasks callback.  First call must be from process context
+ * after the scheduler if fully operational.
+ */
+void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp))
+{
+	unsigned long flags;
+	bool needwake;
+
+	rhp->next = NULL;
+	rhp->func = func;
+	raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
+	needwake = !rcu_tasks_cbs_head;
+	*rcu_tasks_cbs_tail = rhp;
+	rcu_tasks_cbs_tail = &rhp->next;
+	raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
+	if (needwake) {
+		rcu_spawn_tasks_kthread();
+		wake_up(&rcu_tasks_cbs_wq);
+	}
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks);
+
+/**
+ * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu-tasks
+ * grace period has elapsed, in other words after all currently
+ * executing rcu-tasks read-side critical sections have elapsed.  These
+ * read-side critical sections are delimited by calls to schedule(),
+ * cond_resched_rcu_qs(), idle execution, userspace execution, calls
+ * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function
+ * preambles and profiling hooks.  The synchronize_rcu_tasks() function
+ * is not (yet) intended for heavy use from multiple CPUs.
+ *
+ * Note that this guarantee implies further memory-ordering guarantees.
+ * On systems with more than one CPU, when synchronize_rcu_tasks() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since the
+ * end of its last RCU-tasks read-side critical section whose beginning
+ * preceded the call to synchronize_rcu_tasks().  In addition, each CPU
+ * having an RCU-tasks read-side critical section that extends beyond
+ * the return from synchronize_rcu_tasks() is guaranteed to have executed
+ * a full memory barrier after the beginning of synchronize_rcu_tasks()
+ * and before the beginning of that RCU-tasks read-side critical section.
+ * Note that these guarantees include CPUs that are offline, idle, or
+ * executing in user mode, as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_rcu_tasks(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_rcu_tasks() -- even if CPU A and CPU B are the same CPU
+ * (but again only if the system has more than one CPU).
+ */
+void synchronize_rcu_tasks(void)
+{
+	/* Complain if the scheduler has not started.  */
+	rcu_lockdep_assert(!rcu_scheduler_active,
+			   "synchronize_rcu_tasks called too soon");
+
+	/* Wait for the grace period. */
+	wait_rcu_gp(call_rcu_tasks);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
+
+/**
+ * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks(void)
+{
+	/* There is only one callback queue, so this is easy.  ;-) */
+	synchronize_rcu_tasks();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
+
+/* See if tasks are still holding out, complain if so. */
+static void check_holdout_task(struct task_struct *t,
+			       bool needreport, bool *firstreport)
+{
+	int cpu;
+
+	if (!ACCESS_ONCE(t->rcu_tasks_holdout) ||
+	    t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) ||
+	    !ACCESS_ONCE(t->on_rq) ||
+	    (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
+	     !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
+		ACCESS_ONCE(t->rcu_tasks_holdout) = false;
+		list_del_init(&t->rcu_tasks_holdout_list);
+		put_task_struct(t);
+		return;
+	}
+	if (!needreport)
+		return;
+	if (*firstreport) {
+		pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
+		*firstreport = false;
+	}
+	cpu = task_cpu(t);
+	pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
+		 t, ".I"[is_idle_task(t)],
+		 "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
+		 t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
+		 t->rcu_tasks_idle_cpu, cpu);
+	sched_show_task(t);
+}
+
+/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
+static int __noreturn rcu_tasks_kthread(void *arg)
+{
+	unsigned long flags;
+	struct task_struct *g, *t;
+	unsigned long lastreport;
+	struct rcu_head *list;
+	struct rcu_head *next;
+	LIST_HEAD(rcu_tasks_holdouts);
+
+	/* FIXME: Add housekeeping affinity. */
+
+	/*
+	 * Each pass through the following loop makes one check for
+	 * newly arrived callbacks, and, if there are some, waits for
+	 * one RCU-tasks grace period and then invokes the callbacks.
+	 * This loop is terminated by the system going down.  ;-)
+	 */
+	for (;;) {
+
+		/* Pick up any new callbacks. */
+		raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
+		list = rcu_tasks_cbs_head;
+		rcu_tasks_cbs_head = NULL;
+		rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
+		raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
+
+		/* If there were none, wait a bit and start over. */
+		if (!list) {
+			wait_event_interruptible(rcu_tasks_cbs_wq,
+						 rcu_tasks_cbs_head);
+			if (!rcu_tasks_cbs_head) {
+				WARN_ON(signal_pending(current));
+				schedule_timeout_interruptible(HZ/10);
+			}
+			continue;
+		}
+
+		/*
+		 * Wait for all pre-existing t->on_rq and t->nvcsw
+		 * transitions to complete.  Invoking synchronize_sched()
+		 * suffices because all these transitions occur with
+		 * interrupts disabled.  Without this synchronize_sched(),
+		 * a read-side critical section that started before the
+		 * grace period might be incorrectly seen as having started
+		 * after the grace period.
+		 *
+		 * This synchronize_sched() also dispenses with the
+		 * need for a memory barrier on the first store to
+		 * ->rcu_tasks_holdout, as it forces the store to happen
+		 * after the beginning of the grace period.
+		 */
+		synchronize_sched();
+
+		/*
+		 * There were callbacks, so we need to wait for an
+		 * RCU-tasks grace period.  Start off by scanning
+		 * the task list for tasks that are not already
+		 * voluntarily blocked.  Mark these tasks and make
+		 * a list of them in rcu_tasks_holdouts.
+		 */
+		rcu_read_lock();
+		for_each_process_thread(g, t) {
+			if (t != current && ACCESS_ONCE(t->on_rq) &&
+			    !is_idle_task(t)) {
+				get_task_struct(t);
+				t->rcu_tasks_nvcsw = ACCESS_ONCE(t->nvcsw);
+				ACCESS_ONCE(t->rcu_tasks_holdout) = true;
+				list_add(&t->rcu_tasks_holdout_list,
+					 &rcu_tasks_holdouts);
+			}
+		}
+		rcu_read_unlock();
+
+		/*
+		 * Wait for tasks that are in the process of exiting.
+		 * This does only part of the job, ensuring that all
+		 * tasks that were previously exiting reach the point
+		 * where they have disabled preemption, allowing the
+		 * later synchronize_sched() to finish the job.
+		 */
+		synchronize_srcu(&tasks_rcu_exit_srcu);
+
+		/*
+		 * Each pass through the following loop scans the list
+		 * of holdout tasks, removing any that are no longer
+		 * holdouts.  When the list is empty, we are done.
+		 */
+		lastreport = jiffies;
+		while (!list_empty(&rcu_tasks_holdouts)) {
+			bool firstreport;
+			bool needreport;
+			int rtst;
+			struct task_struct *t1;
+
+			schedule_timeout_interruptible(HZ);
+			rtst = ACCESS_ONCE(rcu_task_stall_timeout);
+			needreport = rtst > 0 &&
+				     time_after(jiffies, lastreport + rtst);
+			if (needreport)
+				lastreport = jiffies;
+			firstreport = true;
+			WARN_ON(signal_pending(current));
+			list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts,
+						rcu_tasks_holdout_list) {
+				check_holdout_task(t, needreport, &firstreport);
+				cond_resched();
+			}
+		}
+
+		/*
+		 * Because ->on_rq and ->nvcsw are not guaranteed
+		 * to have a full memory barriers prior to them in the
+		 * schedule() path, memory reordering on other CPUs could
+		 * cause their RCU-tasks read-side critical sections to
+		 * extend past the end of the grace period.  However,
+		 * because these ->nvcsw updates are carried out with
+		 * interrupts disabled, we can use synchronize_sched()
+		 * to force the needed ordering on all such CPUs.
+		 *
+		 * This synchronize_sched() also confines all
+		 * ->rcu_tasks_holdout accesses to be within the grace
+		 * period, avoiding the need for memory barriers for
+		 * ->rcu_tasks_holdout accesses.
+		 *
+		 * In addition, this synchronize_sched() waits for exiting
+		 * tasks to complete their final preempt_disable() region
+		 * of execution, cleaning up after the synchronize_srcu()
+		 * above.
+		 */
+		synchronize_sched();
+
+		/* Invoke the callbacks. */
+		while (list) {
+			next = list->next;
+			local_bh_disable();
+			list->func(list);
+			local_bh_enable();
+			list = next;
+			cond_resched();
+		}
+		schedule_timeout_uninterruptible(HZ/10);
+	}
+}
+
+/* Spawn rcu_tasks_kthread() at first call to call_rcu_tasks(). */
+static void rcu_spawn_tasks_kthread(void)
+{
+	static DEFINE_MUTEX(rcu_tasks_kthread_mutex);
+	static struct task_struct *rcu_tasks_kthread_ptr;
+	struct task_struct *t;
+
+	if (ACCESS_ONCE(rcu_tasks_kthread_ptr)) {
+		smp_mb(); /* Ensure caller sees full kthread. */
+		return;
+	}
+	mutex_lock(&rcu_tasks_kthread_mutex);
+	if (rcu_tasks_kthread_ptr) {
+		mutex_unlock(&rcu_tasks_kthread_mutex);
+		return;
+	}
+	t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
+	BUG_ON(IS_ERR(t));
+	smp_mb(); /* Ensure others see full kthread. */
+	ACCESS_ONCE(rcu_tasks_kthread_ptr) = t;
+	mutex_unlock(&rcu_tasks_kthread_mutex);
+}
+
+#endif /* #ifdef CONFIG_TASKS_RCU */
diff --git a/kernel/reboot.c b/kernel/reboot.c
index a3a9e240fcdb..5925f5ae8dff 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -104,6 +104,87 @@ int unregister_reboot_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_reboot_notifier);
 
+/*
+ *	Notifier list for kernel code which wants to be called
+ *	to restart the system.
+ */
+static ATOMIC_NOTIFIER_HEAD(restart_handler_list);
+
+/**
+ *	register_restart_handler - Register function to be called to reset
+ *				   the system
+ *	@nb: Info about handler function to be called
+ *	@nb->priority:	Handler priority. Handlers should follow the
+ *			following guidelines for setting priorities.
+ *			0:	Restart handler of last resort,
+ *				with limited restart capabilities
+ *			128:	Default restart handler; use if no other
+ *				restart handler is expected to be available,
+ *				and/or if restart functionality is
+ *				sufficient to restart the entire system
+ *			255:	Highest priority restart handler, will
+ *				preempt all other restart handlers
+ *
+ *	Registers a function with code to be called to restart the
+ *	system.
+ *
+ *	Registered functions will be called from machine_restart as last
+ *	step of the restart sequence (if the architecture specific
+ *	machine_restart function calls do_kernel_restart - see below
+ *	for details).
+ *	Registered functions are expected to restart the system immediately.
+ *	If more than one function is registered, the restart handler priority
+ *	selects which function will be called first.
+ *
+ *	Restart handlers are expected to be registered from non-architecture
+ *	code, typically from drivers. A typical use case would be a system
+ *	where restart functionality is provided through a watchdog. Multiple
+ *	restart handlers may exist; for example, one restart handler might
+ *	restart the entire system, while another only restarts the CPU.
+ *	In such cases, the restart handler which only restarts part of the
+ *	hardware is expected to register with low priority to ensure that
+ *	it only runs if no other means to restart the system is available.
+ *
+ *	Currently always returns zero, as atomic_notifier_chain_register()
+ *	always returns zero.
+ */
+int register_restart_handler(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_register(&restart_handler_list, nb);
+}
+EXPORT_SYMBOL(register_restart_handler);
+
+/**
+ *	unregister_restart_handler - Unregister previously registered
+ *				     restart handler
+ *	@nb: Hook to be unregistered
+ *
+ *	Unregisters a previously registered restart handler function.
+ *
+ *	Returns zero on success, or %-ENOENT on failure.
+ */
+int unregister_restart_handler(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&restart_handler_list, nb);
+}
+EXPORT_SYMBOL(unregister_restart_handler);
+
+/**
+ *	do_kernel_restart - Execute kernel restart handler call chain
+ *
+ *	Calls functions registered with register_restart_handler.
+ *
+ *	Expected to be called from machine_restart as last step of the restart
+ *	sequence.
+ *
+ *	Restarts the system immediately if a restart handler function has been
+ *	registered. Otherwise does nothing.
+ */
+void do_kernel_restart(char *cmd)
+{
+	atomic_notifier_call_chain(&restart_handler_list, reboot_mode, cmd);
+}
+
 void migrate_to_reboot_cpu(void)
 {
 	/* The boot cpu is always logical cpu 0 */
diff --git a/kernel/resource.c b/kernel/resource.c
index 60c5a3856ab7..0bcebffc4e77 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -491,6 +491,42 @@ int __weak page_is_ram(unsigned long pfn)
 }
 EXPORT_SYMBOL_GPL(page_is_ram);
 
+/*
+ * Search for a resouce entry that fully contains the specified region.
+ * If found, return 1 if it is RAM, 0 if not.
+ * If not found, or region is not fully contained, return -1
+ *
+ * Used by the ioremap functions to ensure the user is not remapping RAM and is
+ * a vast speed up over walking through the resource table page by page.
+ */
+int region_is_ram(resource_size_t start, unsigned long size)
+{
+	struct resource *p;
+	resource_size_t end = start + size - 1;
+	int flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	const char *name = "System RAM";
+	int ret = -1;
+
+	read_lock(&resource_lock);
+	for (p = iomem_resource.child; p ; p = p->sibling) {
+		if (end < p->start)
+			continue;
+
+		if (p->start <= start && end <= p->end) {
+			/* resource fully contains region */
+			if ((p->flags != flags) || strcmp(p->name, name))
+				ret = 0;
+			else
+				ret = 1;
+			break;
+		}
+		if (p->end < start)
+			break;	/* not found */
+	}
+	read_unlock(&resource_lock);
+	return ret;
+}
+
 void __weak arch_remove_reservations(struct resource *avail)
 {
 }
@@ -1245,6 +1281,76 @@ int release_mem_region_adjustable(struct resource *parent,
 /*
  * Managed region resource
  */
+static void devm_resource_release(struct device *dev, void *ptr)
+{
+	struct resource **r = ptr;
+
+	release_resource(*r);
+}
+
+/**
+ * devm_request_resource() - request and reserve an I/O or memory resource
+ * @dev: device for which to request the resource
+ * @root: root of the resource tree from which to request the resource
+ * @new: descriptor of the resource to request
+ *
+ * This is a device-managed version of request_resource(). There is usually
+ * no need to release resources requested by this function explicitly since
+ * that will be taken care of when the device is unbound from its driver.
+ * If for some reason the resource needs to be released explicitly, because
+ * of ordering issues for example, drivers must call devm_release_resource()
+ * rather than the regular release_resource().
+ *
+ * When a conflict is detected between any existing resources and the newly
+ * requested resource, an error message will be printed.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+int devm_request_resource(struct device *dev, struct resource *root,
+			  struct resource *new)
+{
+	struct resource *conflict, **ptr;
+
+	ptr = devres_alloc(devm_resource_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	*ptr = new;
+
+	conflict = request_resource_conflict(root, new);
+	if (conflict) {
+		dev_err(dev, "resource collision: %pR conflicts with %s %pR\n",
+			new, conflict->name, conflict);
+		devres_free(ptr);
+		return -EBUSY;
+	}
+
+	devres_add(dev, ptr);
+	return 0;
+}
+EXPORT_SYMBOL(devm_request_resource);
+
+static int devm_resource_match(struct device *dev, void *res, void *data)
+{
+	struct resource **ptr = res;
+
+	return *ptr == data;
+}
+
+/**
+ * devm_release_resource() - release a previously requested resource
+ * @dev: device for which to release the resource
+ * @new: descriptor of the resource to release
+ *
+ * Releases a resource previously requested using devm_request_resource().
+ */
+void devm_release_resource(struct device *dev, struct resource *new)
+{
+	WARN_ON(devres_release(dev, devm_resource_release, devm_resource_match,
+			       new));
+}
+EXPORT_SYMBOL(devm_release_resource);
+
 struct region_devres {
 	struct resource *parent;
 	resource_size_t start;
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index e73efba98301..8a2e230fb86a 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -148,11 +148,8 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 	if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
 		goto out;
 
-	t = p;
-	do {
+	for_each_thread(p, t)
 		sched_move_task(t);
-	} while_each_thread(p, t);
-
 out:
 	unlock_task_sighand(p, &flags);
 	autogroup_kref_put(prev);
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 3ef6451e972e..c27e4f8f4879 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -134,7 +134,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
 
 static inline struct sched_clock_data *this_scd(void)
 {
-	return &__get_cpu_var(sched_clock_data);
+	return this_cpu_ptr(&sched_clock_data);
 }
 
 static inline struct sched_clock_data *cpu_sdc(int cpu)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 59965ec0b7de..44999505e1bf 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -90,22 +90,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
-#ifdef smp_mb__before_atomic
-void __smp_mb__before_atomic(void)
-{
-	smp_mb__before_atomic();
-}
-EXPORT_SYMBOL(__smp_mb__before_atomic);
-#endif
-
-#ifdef smp_mb__after_atomic
-void __smp_mb__after_atomic(void)
-{
-	smp_mb__after_atomic();
-}
-EXPORT_SYMBOL(__smp_mb__after_atomic);
-#endif
-
 void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
 {
 	unsigned long delta;
@@ -333,9 +317,12 @@ static inline struct rq *__task_rq_lock(struct task_struct *p)
 	for (;;) {
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p)))
+		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
 			return rq;
 		raw_spin_unlock(&rq->lock);
+
+		while (unlikely(task_on_rq_migrating(p)))
+			cpu_relax();
 	}
 }
 
@@ -352,10 +339,13 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
 		raw_spin_lock_irqsave(&p->pi_lock, *flags);
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p)))
+		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
 			return rq;
 		raw_spin_unlock(&rq->lock);
 		raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
+
+		while (unlikely(task_on_rq_migrating(p)))
+			cpu_relax();
 	}
 }
 
@@ -449,7 +439,15 @@ static void __hrtick_start(void *arg)
 void hrtick_start(struct rq *rq, u64 delay)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
-	ktime_t time = ktime_add_ns(timer->base->get_time(), delay);
+	ktime_t time;
+	s64 delta;
+
+	/*
+	 * Don't schedule slices shorter than 10000ns, that just
+	 * doesn't make sense and can cause timer DoS.
+	 */
+	delta = max_t(s64, delay, 10000LL);
+	time = ktime_add_ns(timer->base->get_time(), delta);
 
 	hrtimer_set_expires(timer, time);
 
@@ -1043,7 +1041,7 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 	 * A queue event has occurred, and we're going to schedule.  In
 	 * this case, we can save a useless back to back clock update.
 	 */
-	if (rq->curr->on_rq && test_tsk_need_resched(rq->curr))
+	if (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr))
 		rq->skip_clock_update = 1;
 }
 
@@ -1088,7 +1086,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
-	if (p->on_rq) {
+	if (task_on_rq_queued(p)) {
 		struct rq *src_rq, *dst_rq;
 
 		src_rq = task_rq(p);
@@ -1214,7 +1212,7 @@ static int migration_cpu_stop(void *data);
 unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 {
 	unsigned long flags;
-	int running, on_rq;
+	int running, queued;
 	unsigned long ncsw;
 	struct rq *rq;
 
@@ -1252,7 +1250,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		rq = task_rq_lock(p, &flags);
 		trace_sched_wait_task(p);
 		running = task_running(rq, p);
-		on_rq = p->on_rq;
+		queued = task_on_rq_queued(p);
 		ncsw = 0;
 		if (!match_state || p->state == match_state)
 			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
@@ -1284,7 +1282,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * running right now), it's preempted, and we should
 		 * yield - it could be a while.
 		 */
-		if (unlikely(on_rq)) {
+		if (unlikely(queued)) {
 			ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ);
 
 			set_current_state(TASK_UNINTERRUPTIBLE);
@@ -1478,7 +1476,7 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
 {
 	activate_task(rq, p, en_flags);
-	p->on_rq = 1;
+	p->on_rq = TASK_ON_RQ_QUEUED;
 
 	/* if a worker is waking up, notify workqueue */
 	if (p->flags & PF_WQ_WORKER)
@@ -1537,7 +1535,7 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 	int ret = 0;
 
 	rq = __task_rq_lock(p);
-	if (p->on_rq) {
+	if (task_on_rq_queued(p)) {
 		/* check_preempt_curr() may use rq clock */
 		update_rq_clock(rq);
 		ttwu_do_wakeup(rq, p, wake_flags);
@@ -1620,6 +1618,25 @@ static void ttwu_queue_remote(struct task_struct *p, int cpu)
 	}
 }
 
+void wake_up_if_idle(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long flags;
+
+	if (!is_idle_task(rq->curr))
+		return;
+
+	if (set_nr_if_polling(rq->idle)) {
+		trace_sched_wake_idle_without_ipi(cpu);
+	} else {
+		raw_spin_lock_irqsave(&rq->lock, flags);
+		if (is_idle_task(rq->curr))
+			smp_send_reschedule(cpu);
+		/* Else cpu is not in idle, do nothing here */
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
+	}
+}
+
 bool cpus_share_cache(int this_cpu, int that_cpu)
 {
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
@@ -1742,7 +1759,7 @@ static void try_to_wake_up_local(struct task_struct *p)
 	if (!(p->state & TASK_NORMAL))
 		goto out;
 
-	if (!p->on_rq)
+	if (!task_on_rq_queued(p))
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
 
 	ttwu_do_wakeup(rq, p, 0);
@@ -1776,6 +1793,20 @@ int wake_up_state(struct task_struct *p, unsigned int state)
 }
 
 /*
+ * This function clears the sched_dl_entity static params.
+ */
+void __dl_clear_params(struct task_struct *p)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	dl_se->dl_runtime = 0;
+	dl_se->dl_deadline = 0;
+	dl_se->dl_period = 0;
+	dl_se->flags = 0;
+	dl_se->dl_bw = 0;
+}
+
+/*
  * Perform scheduler related setup for a newly forked process p.
  * p is forked by current.
  *
@@ -1799,10 +1830,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 	RB_CLEAR_NODE(&p->dl.rb_node);
 	hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	p->dl.dl_runtime = p->dl.runtime = 0;
-	p->dl.dl_deadline = p->dl.deadline = 0;
-	p->dl.dl_period = 0;
-	p->dl.flags = 0;
+	__dl_clear_params(p);
 
 	INIT_LIST_HEAD(&p->rt.run_list);
 
@@ -1977,6 +2005,8 @@ unsigned long to_ratio(u64 period, u64 runtime)
 #ifdef CONFIG_SMP
 inline struct dl_bw *dl_bw_of(int i)
 {
+	rcu_lockdep_assert(rcu_read_lock_sched_held(),
+			   "sched RCU must be held");
 	return &cpu_rq(i)->rd->dl_bw;
 }
 
@@ -1985,6 +2015,8 @@ static inline int dl_bw_cpus(int i)
 	struct root_domain *rd = cpu_rq(i)->rd;
 	int cpus = 0;
 
+	rcu_lockdep_assert(rcu_read_lock_sched_held(),
+			   "sched RCU must be held");
 	for_each_cpu_and(i, rd->span, cpu_active_mask)
 		cpus++;
 
@@ -2095,7 +2127,7 @@ void wake_up_new_task(struct task_struct *p)
 	init_task_runnable_average(p);
 	rq = __task_rq_lock(p);
 	activate_task(rq, p, 0);
-	p->on_rq = 1;
+	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p, true);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
@@ -2287,10 +2319,6 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	 */
 	post_schedule(rq);
 
-#ifdef __ARCH_WANT_UNLOCKED_CTXSW
-	/* In this case, finish_task_switch does not reenable preemption */
-	preempt_enable();
-#endif
 	if (current->set_child_tid)
 		put_user(task_pid_vnr(current), current->set_child_tid);
 }
@@ -2333,9 +2361,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	 * of the scheduler it's an obvious special-case), so we
 	 * do an early lockdep release here:
 	 */
-#ifndef __ARCH_WANT_UNLOCKED_CTXSW
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
-#endif
 
 	context_tracking_task_switch(prev, next);
 	/* Here we just switch the register state and the stack. */
@@ -2463,7 +2489,7 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
 	 * project cycles that may never be accounted to this
 	 * thread, breaking clock_gettime().
 	 */
-	if (task_current(rq, p) && p->on_rq) {
+	if (task_current(rq, p) && task_on_rq_queued(p)) {
 		update_rq_clock(rq);
 		ns = rq_clock_task(rq) - p->se.exec_start;
 		if ((s64)ns < 0)
@@ -2509,7 +2535,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	 * If we see ->on_cpu without ->on_rq, the task is leaving, and has
 	 * been accounted, so we're correct here as well.
 	 */
-	if (!p->on_cpu || !p->on_rq)
+	if (!p->on_cpu || !task_on_rq_queued(p))
 		return p->se.sum_exec_runtime;
 #endif
 
@@ -2672,6 +2698,9 @@ static noinline void __schedule_bug(struct task_struct *prev)
  */
 static inline void schedule_debug(struct task_struct *prev)
 {
+#ifdef CONFIG_SCHED_STACK_END_CHECK
+	BUG_ON(unlikely(task_stack_end_corrupted(prev)));
+#endif
 	/*
 	 * Test if we are atomic. Since do_exit() needs to call into
 	 * schedule() atomically, we ignore that path. Otherwise whine
@@ -2813,7 +2842,7 @@ need_resched:
 		switch_count = &prev->nvcsw;
 	}
 
-	if (prev->on_rq || rq->skip_clock_update < 0)
+	if (task_on_rq_queued(prev) || rq->skip_clock_update < 0)
 		update_rq_clock(rq);
 
 	next = pick_next_task(rq, prev);
@@ -2978,7 +3007,7 @@ EXPORT_SYMBOL(default_wake_function);
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
-	int oldprio, on_rq, running, enqueue_flag = 0;
+	int oldprio, queued, running, enqueue_flag = 0;
 	struct rq *rq;
 	const struct sched_class *prev_class;
 
@@ -3007,12 +3036,12 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	trace_sched_pi_setprio(p, prio);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
-	on_rq = p->on_rq;
+	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
-	if (on_rq)
+	if (queued)
 		dequeue_task(rq, p, 0);
 	if (running)
-		p->sched_class->put_prev_task(rq, p);
+		put_prev_task(rq, p);
 
 	/*
 	 * Boosting condition are:
@@ -3049,7 +3078,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq)
+	if (queued)
 		enqueue_task(rq, p, enqueue_flag);
 
 	check_class_changed(rq, p, prev_class, oldprio);
@@ -3060,7 +3089,7 @@ out_unlock:
 
 void set_user_nice(struct task_struct *p, long nice)
 {
-	int old_prio, delta, on_rq;
+	int old_prio, delta, queued;
 	unsigned long flags;
 	struct rq *rq;
 
@@ -3081,8 +3110,8 @@ void set_user_nice(struct task_struct *p, long nice)
 		p->static_prio = NICE_TO_PRIO(nice);
 		goto out_unlock;
 	}
-	on_rq = p->on_rq;
-	if (on_rq)
+	queued = task_on_rq_queued(p);
+	if (queued)
 		dequeue_task(rq, p, 0);
 
 	p->static_prio = NICE_TO_PRIO(nice);
@@ -3091,7 +3120,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	p->prio = effective_prio(p);
 	delta = p->prio - old_prio;
 
-	if (on_rq) {
+	if (queued) {
 		enqueue_task(rq, p, 0);
 		/*
 		 * If the task increased its priority or is running and
@@ -3363,7 +3392,7 @@ static int __sched_setscheduler(struct task_struct *p,
 {
 	int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
 		      MAX_RT_PRIO - 1 - attr->sched_priority;
-	int retval, oldprio, oldpolicy = -1, on_rq, running;
+	int retval, oldprio, oldpolicy = -1, queued, running;
 	int policy = attr->sched_policy;
 	unsigned long flags;
 	const struct sched_class *prev_class;
@@ -3560,19 +3589,19 @@ change:
 		return 0;
 	}
 
-	on_rq = p->on_rq;
+	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
-	if (on_rq)
+	if (queued)
 		dequeue_task(rq, p, 0);
 	if (running)
-		p->sched_class->put_prev_task(rq, p);
+		put_prev_task(rq, p);
 
 	prev_class = p->sched_class;
 	__setscheduler(rq, p, attr);
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq) {
+	if (queued) {
 		/*
 		 * We enqueue to tail when the priority of a task is
 		 * increased (user space view).
@@ -3996,14 +4025,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 		rcu_read_lock();
 		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
 			rcu_read_unlock();
-			goto out_unlock;
+			goto out_free_new_mask;
 		}
 		rcu_read_unlock();
 	}
 
 	retval = security_task_setscheduler(p);
 	if (retval)
-		goto out_unlock;
+		goto out_free_new_mask;
 
 
 	cpuset_cpus_allowed(p, cpus_allowed);
@@ -4016,13 +4045,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	 * root_domain.
 	 */
 #ifdef CONFIG_SMP
-	if (task_has_dl_policy(p)) {
-		const struct cpumask *span = task_rq(p)->rd->span;
-
-		if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) {
+	if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
+		rcu_read_lock();
+		if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) {
 			retval = -EBUSY;
-			goto out_unlock;
+			rcu_read_unlock();
+			goto out_free_new_mask;
 		}
+		rcu_read_unlock();
 	}
 #endif
 again:
@@ -4040,7 +4070,7 @@ again:
 			goto again;
 		}
 	}
-out_unlock:
+out_free_new_mask:
 	free_cpumask_var(new_mask);
 out_free_cpus_allowed:
 	free_cpumask_var(cpus_allowed);
@@ -4524,7 +4554,7 @@ void show_state_filter(unsigned long state_filter)
 		"  task                        PC stack   pid father\n");
 #endif
 	rcu_read_lock();
-	do_each_thread(g, p) {
+	for_each_process_thread(g, p) {
 		/*
 		 * reset the NMI-timeout, listing all files on a slow
 		 * console might take a lot of time:
@@ -4532,7 +4562,7 @@ void show_state_filter(unsigned long state_filter)
 		touch_nmi_watchdog();
 		if (!state_filter || (p->state & state_filter))
 			sched_show_task(p);
-	} while_each_thread(g, p);
+	}
 
 	touch_all_softlockup_watchdogs();
 
@@ -4587,7 +4617,7 @@ void init_idle(struct task_struct *idle, int cpu)
 	rcu_read_unlock();
 
 	rq->curr = rq->idle = idle;
-	idle->on_rq = 1;
+	idle->on_rq = TASK_ON_RQ_QUEUED;
 #if defined(CONFIG_SMP)
 	idle->on_cpu = 1;
 #endif
@@ -4608,6 +4638,33 @@ void init_idle(struct task_struct *idle, int cpu)
 }
 
 #ifdef CONFIG_SMP
+/*
+ * move_queued_task - move a queued task to new rq.
+ *
+ * Returns (locked) new rq. Old rq's lock is released.
+ */
+static struct rq *move_queued_task(struct task_struct *p, int new_cpu)
+{
+	struct rq *rq = task_rq(p);
+
+	lockdep_assert_held(&rq->lock);
+
+	dequeue_task(rq, p, 0);
+	p->on_rq = TASK_ON_RQ_MIGRATING;
+	set_task_cpu(p, new_cpu);
+	raw_spin_unlock(&rq->lock);
+
+	rq = cpu_rq(new_cpu);
+
+	raw_spin_lock(&rq->lock);
+	BUG_ON(task_cpu(p) != new_cpu);
+	p->on_rq = TASK_ON_RQ_QUEUED;
+	enqueue_task(rq, p, 0);
+	check_preempt_curr(rq, p, 0);
+
+	return rq;
+}
+
 void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
 	if (p->sched_class && p->sched_class->set_cpus_allowed)
@@ -4664,14 +4721,15 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 		goto out;
 
 	dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
-	if (p->on_rq) {
+	if (task_running(rq, p) || p->state == TASK_WAKING) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
 		task_rq_unlock(rq, p, &flags);
 		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
 		tlb_migrate_finish(p->mm);
 		return 0;
-	}
+	} else if (task_on_rq_queued(p))
+		rq = move_queued_task(p, dest_cpu);
 out:
 	task_rq_unlock(rq, p, &flags);
 
@@ -4692,20 +4750,20 @@ EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
  */
 static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 {
-	struct rq *rq_dest, *rq_src;
+	struct rq *rq;
 	int ret = 0;
 
 	if (unlikely(!cpu_active(dest_cpu)))
 		return ret;
 
-	rq_src = cpu_rq(src_cpu);
-	rq_dest = cpu_rq(dest_cpu);
+	rq = cpu_rq(src_cpu);
 
 	raw_spin_lock(&p->pi_lock);
-	double_rq_lock(rq_src, rq_dest);
+	raw_spin_lock(&rq->lock);
 	/* Already moved. */
 	if (task_cpu(p) != src_cpu)
 		goto done;
+
 	/* Affinity changed (again). */
 	if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
 		goto fail;
@@ -4714,16 +4772,12 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 	 * If we're not on a rq, the next wake-up will ensure we're
 	 * placed properly.
 	 */
-	if (p->on_rq) {
-		dequeue_task(rq_src, p, 0);
-		set_task_cpu(p, dest_cpu);
-		enqueue_task(rq_dest, p, 0);
-		check_preempt_curr(rq_dest, p, 0);
-	}
+	if (task_on_rq_queued(p))
+		rq = move_queued_task(p, dest_cpu);
 done:
 	ret = 1;
 fail:
-	double_rq_unlock(rq_src, rq_dest);
+	raw_spin_unlock(&rq->lock);
 	raw_spin_unlock(&p->pi_lock);
 	return ret;
 }
@@ -4755,22 +4809,22 @@ void sched_setnuma(struct task_struct *p, int nid)
 {
 	struct rq *rq;
 	unsigned long flags;
-	bool on_rq, running;
+	bool queued, running;
 
 	rq = task_rq_lock(p, &flags);
-	on_rq = p->on_rq;
+	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 
-	if (on_rq)
+	if (queued)
 		dequeue_task(rq, p, 0);
 	if (running)
-		p->sched_class->put_prev_task(rq, p);
+		put_prev_task(rq, p);
 
 	p->numa_preferred_nid = nid;
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq)
+	if (queued)
 		enqueue_task(rq, p, 0);
 	task_rq_unlock(rq, p, &flags);
 }
@@ -4790,6 +4844,12 @@ static int migration_cpu_stop(void *data)
 	 * be on another cpu but it doesn't matter.
 	 */
 	local_irq_disable();
+	/*
+	 * We need to explicitly wake pending tasks before running
+	 * __migrate_task() such that we will not miss enforcing cpus_allowed
+	 * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
+	 */
+	sched_ttwu_pending();
 	__migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu);
 	local_irq_enable();
 	return 0;
@@ -5200,6 +5260,7 @@ static int sched_cpu_inactive(struct notifier_block *nfb,
 {
 	unsigned long flags;
 	long cpu = (long)hcpu;
+	struct dl_bw *dl_b;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_DOWN_PREPARE:
@@ -5207,15 +5268,19 @@ static int sched_cpu_inactive(struct notifier_block *nfb,
 
 		/* explicitly allow suspend */
 		if (!(action & CPU_TASKS_FROZEN)) {
-			struct dl_bw *dl_b = dl_bw_of(cpu);
 			bool overflow;
 			int cpus;
 
+			rcu_read_lock_sched();
+			dl_b = dl_bw_of(cpu);
+
 			raw_spin_lock_irqsave(&dl_b->lock, flags);
 			cpus = dl_bw_cpus(cpu);
 			overflow = __dl_overflow(dl_b, cpus, 0, 0);
 			raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
+			rcu_read_unlock_sched();
+
 			if (overflow)
 				return notifier_from_errno(-EBUSY);
 		}
@@ -5758,7 +5823,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 	const struct cpumask *span = sched_domain_span(sd);
 	struct cpumask *covered = sched_domains_tmpmask;
 	struct sd_data *sdd = sd->private;
-	struct sched_domain *child;
+	struct sched_domain *sibling;
 	int i;
 
 	cpumask_clear(covered);
@@ -5769,10 +5834,10 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		if (cpumask_test_cpu(i, covered))
 			continue;
 
-		child = *per_cpu_ptr(sdd->sd, i);
+		sibling = *per_cpu_ptr(sdd->sd, i);
 
 		/* See the comment near build_group_mask(). */
-		if (!cpumask_test_cpu(i, sched_domain_span(child)))
+		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
 			continue;
 
 		sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
@@ -5782,10 +5847,9 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 			goto fail;
 
 		sg_span = sched_group_cpus(sg);
-		if (child->child) {
-			child = child->child;
-			cpumask_copy(sg_span, sched_domain_span(child));
-		} else
+		if (sibling->child)
+			cpumask_copy(sg_span, sched_domain_span(sibling->child));
+		else
 			cpumask_set_cpu(i, sg_span);
 
 		cpumask_or(covered, covered, sg_span);
@@ -7136,13 +7200,13 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 		.sched_policy = SCHED_NORMAL,
 	};
 	int old_prio = p->prio;
-	int on_rq;
+	int queued;
 
-	on_rq = p->on_rq;
-	if (on_rq)
+	queued = task_on_rq_queued(p);
+	if (queued)
 		dequeue_task(rq, p, 0);
 	__setscheduler(rq, p, &attr);
-	if (on_rq) {
+	if (queued) {
 		enqueue_task(rq, p, 0);
 		resched_curr(rq);
 	}
@@ -7156,12 +7220,12 @@ void normalize_rt_tasks(void)
 	unsigned long flags;
 	struct rq *rq;
 
-	read_lock_irqsave(&tasklist_lock, flags);
-	do_each_thread(g, p) {
+	read_lock(&tasklist_lock);
+	for_each_process_thread(g, p) {
 		/*
 		 * Only normalize user tasks:
 		 */
-		if (!p->mm)
+		if (p->flags & PF_KTHREAD)
 			continue;
 
 		p->se.exec_start		= 0;
@@ -7176,21 +7240,16 @@ void normalize_rt_tasks(void)
 			 * Renice negative nice level userspace
 			 * tasks back to 0:
 			 */
-			if (task_nice(p) < 0 && p->mm)
+			if (task_nice(p) < 0)
 				set_user_nice(p, 0);
 			continue;
 		}
 
-		raw_spin_lock(&p->pi_lock);
-		rq = __task_rq_lock(p);
-
+		rq = task_rq_lock(p, &flags);
 		normalize_task(rq, p);
-
-		__task_rq_unlock(rq);
-		raw_spin_unlock(&p->pi_lock);
-	} while_each_thread(g, p);
-
-	read_unlock_irqrestore(&tasklist_lock, flags);
+		task_rq_unlock(rq, p, &flags);
+	}
+	read_unlock(&tasklist_lock);
 }
 
 #endif /* CONFIG_MAGIC_SYSRQ */
@@ -7330,19 +7389,19 @@ void sched_offline_group(struct task_group *tg)
 void sched_move_task(struct task_struct *tsk)
 {
 	struct task_group *tg;
-	int on_rq, running;
+	int queued, running;
 	unsigned long flags;
 	struct rq *rq;
 
 	rq = task_rq_lock(tsk, &flags);
 
 	running = task_current(rq, tsk);
-	on_rq = tsk->on_rq;
+	queued = task_on_rq_queued(tsk);
 
-	if (on_rq)
+	if (queued)
 		dequeue_task(rq, tsk, 0);
 	if (unlikely(running))
-		tsk->sched_class->put_prev_task(rq, tsk);
+		put_prev_task(rq, tsk);
 
 	tg = container_of(task_css_check(tsk, cpu_cgrp_id,
 				lockdep_is_held(&tsk->sighand->siglock)),
@@ -7352,14 +7411,14 @@ void sched_move_task(struct task_struct *tsk)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	if (tsk->sched_class->task_move_group)
-		tsk->sched_class->task_move_group(tsk, on_rq);
+		tsk->sched_class->task_move_group(tsk, queued);
 	else
 #endif
 		set_task_rq(tsk, task_cpu(tsk));
 
 	if (unlikely(running))
 		tsk->sched_class->set_curr_task(rq);
-	if (on_rq)
+	if (queued)
 		enqueue_task(rq, tsk, 0);
 
 	task_rq_unlock(rq, tsk, &flags);
@@ -7377,10 +7436,10 @@ static inline int tg_has_rt_tasks(struct task_group *tg)
 {
 	struct task_struct *g, *p;
 
-	do_each_thread(g, p) {
-		if (rt_task(p) && task_rq(p)->rt.tg == tg)
+	for_each_process_thread(g, p) {
+		if (rt_task(p) && task_group(p) == tg)
 			return 1;
-	} while_each_thread(g, p);
+	}
 
 	return 0;
 }
@@ -7589,6 +7648,7 @@ static int sched_dl_global_constraints(void)
 	u64 runtime = global_rt_runtime();
 	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
+	struct dl_bw *dl_b;
 	int cpu, ret = 0;
 	unsigned long flags;
 
@@ -7602,13 +7662,16 @@ static int sched_dl_global_constraints(void)
 	 * solutions is welcome!
 	 */
 	for_each_possible_cpu(cpu) {
-		struct dl_bw *dl_b = dl_bw_of(cpu);
+		rcu_read_lock_sched();
+		dl_b = dl_bw_of(cpu);
 
 		raw_spin_lock_irqsave(&dl_b->lock, flags);
 		if (new_bw < dl_b->total_bw)
 			ret = -EBUSY;
 		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
+		rcu_read_unlock_sched();
+
 		if (ret)
 			break;
 	}
@@ -7619,6 +7682,7 @@ static int sched_dl_global_constraints(void)
 static void sched_dl_do_global(void)
 {
 	u64 new_bw = -1;
+	struct dl_bw *dl_b;
 	int cpu;
 	unsigned long flags;
 
@@ -7632,11 +7696,14 @@ static void sched_dl_do_global(void)
 	 * FIXME: As above...
 	 */
 	for_each_possible_cpu(cpu) {
-		struct dl_bw *dl_b = dl_bw_of(cpu);
+		rcu_read_lock_sched();
+		dl_b = dl_bw_of(cpu);
 
 		raw_spin_lock_irqsave(&dl_b->lock, flags);
 		dl_b->bw = new_bw;
 		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+		rcu_read_unlock_sched();
 	}
 }
 
@@ -8017,7 +8084,7 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
 		struct cfs_bandwidth *parent_b = &tg->parent->cfs_bandwidth;
 
 		quota = normalize_cfs_quota(tg, d);
-		parent_quota = parent_b->hierarchal_quota;
+		parent_quota = parent_b->hierarchical_quota;
 
 		/*
 		 * ensure max(child_quota) <= parent_quota, inherit when no
@@ -8028,7 +8095,7 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
 		else if (parent_quota != RUNTIME_INF && quota > parent_quota)
 			return -EINVAL;
 	}
-	cfs_b->hierarchal_quota = quota;
+	cfs_b->hierarchical_quota = quota;
 
 	return 0;
 }
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index bd95963dae80..539ca3ce071b 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -107,9 +107,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	int best_cpu = -1;
 	const struct sched_dl_entity *dl_se = &p->dl;
 
-	if (later_mask && cpumask_and(later_mask, cp->free_cpus,
-			&p->cpus_allowed) && cpumask_and(later_mask,
-			later_mask, cpu_active_mask)) {
+	if (later_mask && cpumask_and(later_mask, later_mask, cp->free_cpus)) {
 		best_cpu = cpumask_any(later_mask);
 		goto out;
 	} else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 72fdf06ef865..8394b1ee600c 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -288,24 +288,29 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 	struct signal_struct *sig = tsk->signal;
 	cputime_t utime, stime;
 	struct task_struct *t;
-
-	times->utime = sig->utime;
-	times->stime = sig->stime;
-	times->sum_exec_runtime = sig->sum_sched_runtime;
+	unsigned int seq, nextseq;
+	unsigned long flags;
 
 	rcu_read_lock();
-	/* make sure we can trust tsk->thread_group list */
-	if (!likely(pid_alive(tsk)))
-		goto out;
-
-	t = tsk;
+	/* Attempt a lockless read on the first round. */
+	nextseq = 0;
 	do {
-		task_cputime(t, &utime, &stime);
-		times->utime += utime;
-		times->stime += stime;
-		times->sum_exec_runtime += task_sched_runtime(t);
-	} while_each_thread(tsk, t);
-out:
+		seq = nextseq;
+		flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
+		times->utime = sig->utime;
+		times->stime = sig->stime;
+		times->sum_exec_runtime = sig->sum_sched_runtime;
+
+		for_each_thread(tsk, t) {
+			task_cputime(t, &utime, &stime);
+			times->utime += utime;
+			times->stime += stime;
+			times->sum_exec_runtime += task_sched_runtime(t);
+		}
+		/* If lockless access failed, take the lock. */
+		nextseq = 1;
+	} while (need_seqretry(&sig->stats_lock, seq));
+	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
 	rcu_read_unlock();
 }
 
@@ -550,6 +555,23 @@ drop_precision:
 }
 
 /*
+ * Atomically advance counter to the new value. Interrupts, vcpu
+ * scheduling, and scaling inaccuracies can cause cputime_advance
+ * to be occasionally called with a new value smaller than counter.
+ * Let's enforce atomicity.
+ *
+ * Normally a caller will only go through this loop once, or not
+ * at all in case a previous caller updated counter the same jiffy.
+ */
+static void cputime_advance(cputime_t *counter, cputime_t new)
+{
+	cputime_t old;
+
+	while (new > (old = ACCESS_ONCE(*counter)))
+		cmpxchg_cputime(counter, old, new);
+}
+
+/*
  * Adjust tick based cputime random precision against scheduler
  * runtime accounting.
  */
@@ -594,13 +616,8 @@ static void cputime_adjust(struct task_cputime *curr,
 		utime = rtime - stime;
 	}
 
-	/*
-	 * If the tick based count grows faster than the scheduler one,
-	 * the result of the scaling may go backward.
-	 * Let's enforce monotonicity.
-	 */
-	prev->stime = max(prev->stime, stime);
-	prev->utime = max(prev->utime, utime);
+	cputime_advance(&prev->stime, stime);
+	cputime_advance(&prev->utime, utime);
 
 out:
 	*ut = prev->utime;
@@ -617,9 +634,6 @@ void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 
-/*
- * Must be called with siglock held.
- */
 void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 {
 	struct task_cputime cputime;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 255ce138b652..256e577faf1b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -530,7 +530,7 @@ again:
 	update_rq_clock(rq);
 	dl_se->dl_throttled = 0;
 	dl_se->dl_yielded = 0;
-	if (p->on_rq) {
+	if (task_on_rq_queued(p)) {
 		enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
 		if (task_has_dl_policy(rq->curr))
 			check_preempt_curr_dl(rq, p, 0);
@@ -997,10 +997,7 @@ static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
 #ifdef CONFIG_SCHED_HRTICK
 static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
 {
-	s64 delta = p->dl.dl_runtime - p->dl.runtime;
-
-	if (delta > 10000)
-		hrtick_start(rq, p->dl.runtime);
+	hrtick_start(rq, p->dl.runtime);
 }
 #endif
 
@@ -1030,7 +1027,7 @@ struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
 		 * means a stop task can slip in, in which case we need to
 		 * re-start task selection.
 		 */
-		if (rq->stop && rq->stop->on_rq)
+		if (rq->stop && task_on_rq_queued(rq->stop))
 			return RETRY_TASK;
 	}
 
@@ -1124,10 +1121,8 @@ static void set_curr_task_dl(struct rq *rq)
 static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) &&
-	    (p->nr_cpus_allowed > 1))
+	    cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
 		return 1;
-
 	return 0;
 }
 
@@ -1158,7 +1153,7 @@ static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
 static int find_later_rq(struct task_struct *task)
 {
 	struct sched_domain *sd;
-	struct cpumask *later_mask = __get_cpu_var(local_cpu_mask_dl);
+	struct cpumask *later_mask = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
 	int this_cpu = smp_processor_id();
 	int best_cpu, cpu = task_cpu(task);
 
@@ -1169,6 +1164,13 @@ static int find_later_rq(struct task_struct *task)
 	if (task->nr_cpus_allowed == 1)
 		return -1;
 
+	/*
+	 * We have to consider system topology and task affinity
+	 * first, then we can look for a suitable cpu.
+	 */
+	cpumask_copy(later_mask, task_rq(task)->rd->span);
+	cpumask_and(later_mask, later_mask, cpu_active_mask);
+	cpumask_and(later_mask, later_mask, &task->cpus_allowed);
 	best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
 			task, later_mask);
 	if (best_cpu == -1)
@@ -1257,7 +1259,8 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 			if (unlikely(task_rq(task) != rq ||
 				     !cpumask_test_cpu(later_rq->cpu,
 				                       &task->cpus_allowed) ||
-				     task_running(rq, task) || !task->on_rq)) {
+				     task_running(rq, task) ||
+				     !task_on_rq_queued(task))) {
 				double_unlock_balance(rq, later_rq);
 				later_rq = NULL;
 				break;
@@ -1296,7 +1299,7 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
 	BUG_ON(task_current(rq, p));
 	BUG_ON(p->nr_cpus_allowed <= 1);
 
-	BUG_ON(!p->on_rq);
+	BUG_ON(!task_on_rq_queued(p));
 	BUG_ON(!dl_task(p));
 
 	return p;
@@ -1443,7 +1446,7 @@ static int pull_dl_task(struct rq *this_rq)
 		     dl_time_before(p->dl.deadline,
 				    this_rq->dl.earliest_dl.curr))) {
 			WARN_ON(p == src_rq->curr);
-			WARN_ON(!p->on_rq);
+			WARN_ON(!task_on_rq_queued(p));
 
 			/*
 			 * Then we pull iff p has actually an earlier
@@ -1569,6 +1572,8 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
 	if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy))
 		hrtimer_try_to_cancel(&p->dl.dl_timer);
 
+	__dl_clear_params(p);
+
 #ifdef CONFIG_SMP
 	/*
 	 * Since this might be the only -deadline task on the rq,
@@ -1596,7 +1601,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 	if (unlikely(p->dl.dl_throttled))
 		return;
 
-	if (p->on_rq && rq->curr != p) {
+	if (task_on_rq_queued(p) && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
 			/* Only reschedule if pushing failed */
@@ -1614,7 +1619,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 			    int oldprio)
 {
-	if (p->on_rq || rq->curr == p) {
+	if (task_on_rq_queued(p) || rq->curr == p) {
 #ifdef CONFIG_SMP
 		/*
 		 * This might be too much, but unfortunately
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 627b3c34b821..ce33780d8f20 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -150,7 +150,6 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 {
 	struct task_struct *g, *p;
-	unsigned long flags;
 
 	SEQ_printf(m,
 	"\nrunnable tasks:\n"
@@ -159,16 +158,14 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 	"------------------------------------------------------"
 	"----------------------------------------------------\n");
 
-	read_lock_irqsave(&tasklist_lock, flags);
-
-	do_each_thread(g, p) {
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
 		if (task_cpu(p) != rq_cpu)
 			continue;
 
 		print_task(m, rq, p);
-	} while_each_thread(g, p);
-
-	read_unlock_irqrestore(&tasklist_lock, flags);
+	}
+	rcu_read_unlock();
 }
 
 void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
@@ -333,9 +330,7 @@ do {									\
 	print_cfs_stats(m, cpu);
 	print_rt_stats(m, cpu);
 
-	rcu_read_lock();
 	print_rq(m, rq, cpu);
-	rcu_read_unlock();
 	spin_unlock_irqrestore(&sched_debug_lock, flags);
 	SEQ_printf(m, "\n");
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bfa3c86d0d68..0b069bf3e708 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -23,6 +23,7 @@
 #include <linux/latencytop.h>
 #include <linux/sched.h>
 #include <linux/cpumask.h>
+#include <linux/cpuidle.h>
 #include <linux/slab.h>
 #include <linux/profile.h>
 #include <linux/interrupt.h>
@@ -665,6 +666,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 #ifdef CONFIG_SMP
+static int select_idle_sibling(struct task_struct *p, int cpu);
 static unsigned long task_h_load(struct task_struct *p);
 
 static inline void __update_task_entity_contrib(struct sched_entity *se);
@@ -1038,7 +1040,8 @@ struct numa_stats {
  */
 static void update_numa_stats(struct numa_stats *ns, int nid)
 {
-	int cpu, cpus = 0;
+	int smt, cpu, cpus = 0;
+	unsigned long capacity;
 
 	memset(ns, 0, sizeof(*ns));
 	for_each_cpu(cpu, cpumask_of_node(nid)) {
@@ -1062,8 +1065,12 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 	if (!cpus)
 		return;
 
-	ns->task_capacity =
-		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE);
+	/* smt := ceil(cpus / capacity), assumes: 1 < smt_power < 2 */
+	smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
+	capacity = cpus / smt; /* cores */
+
+	ns->task_capacity = min_t(unsigned, capacity,
+		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
 	ns->has_free_capacity = (ns->nr_running < ns->task_capacity);
 }
 
@@ -1206,7 +1213,7 @@ static void task_numa_compare(struct task_numa_env *env,
 
 	if (!cur) {
 		/* Is there capacity at our destination? */
-		if (env->src_stats.has_free_capacity &&
+		if (env->src_stats.nr_running <= env->src_stats.task_capacity &&
 		    !env->dst_stats.has_free_capacity)
 			goto unlock;
 
@@ -1252,6 +1259,13 @@ balance:
 	if (load_too_imbalanced(src_load, dst_load, env))
 		goto unlock;
 
+	/*
+	 * One idle CPU per node is evaluated for a task numa move.
+	 * Call select_idle_sibling to maybe find a better one.
+	 */
+	if (!cur)
+		env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
+
 assign:
 	task_numa_assign(env, cur, imp);
 unlock:
@@ -1775,7 +1789,7 @@ void task_numa_free(struct task_struct *p)
 		list_del(&p->numa_entry);
 		grp->nr_tasks--;
 		spin_unlock_irqrestore(&grp->lock, flags);
-		rcu_assign_pointer(p->numa_group, NULL);
+		RCU_INIT_POINTER(p->numa_group, NULL);
 		put_numa_group(grp);
 	}
 
@@ -1804,10 +1818,6 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 	if (!p->mm)
 		return;
 
-	/* Do not worry about placement if exiting */
-	if (p->state == TASK_DEAD)
-		return;
-
 	/* Allocate buffer to track faults on a per-node basis */
 	if (unlikely(!p->numa_faults_memory)) {
 		int size = sizeof(*p->numa_faults_memory) *
@@ -1946,7 +1956,7 @@ void task_numa_work(struct callback_head *work)
 		vma = mm->mmap;
 	}
 	for (; vma; vma = vma->vm_next) {
-		if (!vma_migratable(vma) || !vma_policy_mof(p, vma))
+		if (!vma_migratable(vma) || !vma_policy_mof(vma))
 			continue;
 
 		/*
@@ -2211,8 +2221,8 @@ static __always_inline u64 decay_load(u64 val, u64 n)
 
 	/*
 	 * As y^PERIOD = 1/2, we can combine
-	 *    y^n = 1/2^(n/PERIOD) * k^(n%PERIOD)
-	 * With a look-up table which covers k^n (n<PERIOD)
+	 *    y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
+	 * With a look-up table which covers y^n (n<PERIOD)
 	 *
 	 * To achieve constant time decay_load.
 	 */
@@ -2377,6 +2387,9 @@ static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
 	tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg;
 	tg_contrib -= cfs_rq->tg_load_contrib;
 
+	if (!tg_contrib)
+		return;
+
 	if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) {
 		atomic_long_add(tg_contrib, &tg->load_avg);
 		cfs_rq->tg_load_contrib += tg_contrib;
@@ -3892,14 +3905,6 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 				resched_curr(rq);
 			return;
 		}
-
-		/*
-		 * Don't schedule slices shorter than 10000ns, that just
-		 * doesn't make sense. Rely on vruntime for fairness.
-		 */
-		if (rq->curr != p)
-			delta = max_t(s64, 10000LL, delta);
-
 		hrtick_start(rq, delta);
 	}
 }
@@ -4087,7 +4092,7 @@ static unsigned long capacity_of(int cpu)
 static unsigned long cpu_avg_load_per_task(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	unsigned long nr_running = ACCESS_ONCE(rq->nr_running);
+	unsigned long nr_running = ACCESS_ONCE(rq->cfs.h_nr_running);
 	unsigned long load_avg = rq->cfs.runnable_load_avg;
 
 	if (nr_running)
@@ -4276,8 +4281,8 @@ static int wake_wide(struct task_struct *p)
 static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 {
 	s64 this_load, load;
+	s64 this_eff_load, prev_eff_load;
 	int idx, this_cpu, prev_cpu;
-	unsigned long tl_per_task;
 	struct task_group *tg;
 	unsigned long weight;
 	int balanced;
@@ -4320,47 +4325,30 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	 * Otherwise check if either cpus are near enough in load to allow this
 	 * task to be woken on this_cpu.
 	 */
-	if (this_load > 0) {
-		s64 this_eff_load, prev_eff_load;
+	this_eff_load = 100;
+	this_eff_load *= capacity_of(prev_cpu);
 
-		this_eff_load = 100;
-		this_eff_load *= capacity_of(prev_cpu);
+	prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
+	prev_eff_load *= capacity_of(this_cpu);
+
+	if (this_load > 0) {
 		this_eff_load *= this_load +
 			effective_load(tg, this_cpu, weight, weight);
 
-		prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
-		prev_eff_load *= capacity_of(this_cpu);
 		prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight);
+	}
 
-		balanced = this_eff_load <= prev_eff_load;
-	} else
-		balanced = true;
-
-	/*
-	 * If the currently running task will sleep within
-	 * a reasonable amount of time then attract this newly
-	 * woken task:
-	 */
-	if (sync && balanced)
-		return 1;
+	balanced = this_eff_load <= prev_eff_load;
 
 	schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts);
-	tl_per_task = cpu_avg_load_per_task(this_cpu);
 
-	if (balanced ||
-	    (this_load <= load &&
-	     this_load + target_load(prev_cpu, idx) <= tl_per_task)) {
-		/*
-		 * This domain has SD_WAKE_AFFINE and
-		 * p is cache cold in this domain, and
-		 * there is no bad imbalance.
-		 */
-		schedstat_inc(sd, ttwu_move_affine);
-		schedstat_inc(p, se.statistics.nr_wakeups_affine);
+	if (!balanced)
+		return 0;
 
-		return 1;
-	}
-	return 0;
+	schedstat_inc(sd, ttwu_move_affine);
+	schedstat_inc(p, se.statistics.nr_wakeups_affine);
+
+	return 1;
 }
 
 /*
@@ -4428,20 +4416,46 @@ static int
 find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 {
 	unsigned long load, min_load = ULONG_MAX;
-	int idlest = -1;
+	unsigned int min_exit_latency = UINT_MAX;
+	u64 latest_idle_timestamp = 0;
+	int least_loaded_cpu = this_cpu;
+	int shallowest_idle_cpu = -1;
 	int i;
 
 	/* Traverse only the allowed CPUs */
 	for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) {
-		load = weighted_cpuload(i);
-
-		if (load < min_load || (load == min_load && i == this_cpu)) {
-			min_load = load;
-			idlest = i;
+		if (idle_cpu(i)) {
+			struct rq *rq = cpu_rq(i);
+			struct cpuidle_state *idle = idle_get_state(rq);
+			if (idle && idle->exit_latency < min_exit_latency) {
+				/*
+				 * We give priority to a CPU whose idle state
+				 * has the smallest exit latency irrespective
+				 * of any idle timestamp.
+				 */
+				min_exit_latency = idle->exit_latency;
+				latest_idle_timestamp = rq->idle_stamp;
+				shallowest_idle_cpu = i;
+			} else if ((!idle || idle->exit_latency == min_exit_latency) &&
+				   rq->idle_stamp > latest_idle_timestamp) {
+				/*
+				 * If equal or no active idle state, then
+				 * the most recently idled CPU might have
+				 * a warmer cache.
+				 */
+				latest_idle_timestamp = rq->idle_stamp;
+				shallowest_idle_cpu = i;
+			}
+		} else {
+			load = weighted_cpuload(i);
+			if (load < min_load || (load == min_load && i == this_cpu)) {
+				min_load = load;
+				least_loaded_cpu = i;
+			}
 		}
 	}
 
-	return idlest;
+	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
 
 /*
@@ -4513,11 +4527,8 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	if (p->nr_cpus_allowed == 1)
 		return prev_cpu;
 
-	if (sd_flag & SD_BALANCE_WAKE) {
-		if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
-			want_affine = 1;
-		new_cpu = prev_cpu;
-	}
+	if (sd_flag & SD_BALANCE_WAKE)
+		want_affine = cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
 
 	rcu_read_lock();
 	for_each_domain(cpu, tmp) {
@@ -4704,7 +4715,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 		return;
 
 	/*
-	 * This is possible from callers such as move_task(), in which we
+	 * This is possible from callers such as attach_tasks(), in which we
 	 * unconditionally check_prempt_curr() after an enqueue (which may have
 	 * lead to a throttle).  This both saves work and prevents false
 	 * next-buddy nomination below.
@@ -5112,27 +5123,18 @@ struct lb_env {
 	unsigned int		loop_max;
 
 	enum fbq_type		fbq_type;
+	struct list_head	tasks;
 };
 
 /*
- * move_task - move a task from one runqueue to another runqueue.
- * Both runqueues must be locked.
- */
-static void move_task(struct task_struct *p, struct lb_env *env)
-{
-	deactivate_task(env->src_rq, p, 0);
-	set_task_cpu(p, env->dst_cpu);
-	activate_task(env->dst_rq, p, 0);
-	check_preempt_curr(env->dst_rq, p, 0);
-}
-
-/*
  * Is this task likely cache-hot:
  */
 static int task_hot(struct task_struct *p, struct lb_env *env)
 {
 	s64 delta;
 
+	lockdep_assert_held(&env->src_rq->lock);
+
 	if (p->sched_class != &fair_sched_class)
 		return 0;
 
@@ -5252,6 +5254,9 @@ static
 int can_migrate_task(struct task_struct *p, struct lb_env *env)
 {
 	int tsk_cache_hot = 0;
+
+	lockdep_assert_held(&env->src_rq->lock);
+
 	/*
 	 * We do not migrate tasks that are:
 	 * 1) throttled_lb_pair, or
@@ -5310,24 +5315,12 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	if (!tsk_cache_hot)
 		tsk_cache_hot = migrate_degrades_locality(p, env);
 
-	if (migrate_improves_locality(p, env)) {
-#ifdef CONFIG_SCHEDSTATS
+	if (migrate_improves_locality(p, env) || !tsk_cache_hot ||
+	    env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
 		if (tsk_cache_hot) {
 			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
 			schedstat_inc(p, se.statistics.nr_forced_migrations);
 		}
-#endif
-		return 1;
-	}
-
-	if (!tsk_cache_hot ||
-		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
-
-		if (tsk_cache_hot) {
-			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
-			schedstat_inc(p, se.statistics.nr_forced_migrations);
-		}
-
 		return 1;
 	}
 
@@ -5336,47 +5329,63 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 }
 
 /*
- * move_one_task tries to move exactly one task from busiest to this_rq, as
+ * detach_task() -- detach the task for the migration specified in env
+ */
+static void detach_task(struct task_struct *p, struct lb_env *env)
+{
+	lockdep_assert_held(&env->src_rq->lock);
+
+	deactivate_task(env->src_rq, p, 0);
+	p->on_rq = TASK_ON_RQ_MIGRATING;
+	set_task_cpu(p, env->dst_cpu);
+}
+
+/*
+ * detach_one_task() -- tries to dequeue exactly one task from env->src_rq, as
  * part of active balancing operations within "domain".
- * Returns 1 if successful and 0 otherwise.
  *
- * Called with both runqueues locked.
+ * Returns a task if successful and NULL otherwise.
  */
-static int move_one_task(struct lb_env *env)
+static struct task_struct *detach_one_task(struct lb_env *env)
 {
 	struct task_struct *p, *n;
 
+	lockdep_assert_held(&env->src_rq->lock);
+
 	list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
 		if (!can_migrate_task(p, env))
 			continue;
 
-		move_task(p, env);
+		detach_task(p, env);
+
 		/*
-		 * Right now, this is only the second place move_task()
-		 * is called, so we can safely collect move_task()
-		 * stats here rather than inside move_task().
+		 * Right now, this is only the second place where
+		 * lb_gained[env->idle] is updated (other is detach_tasks)
+		 * so we can safely collect stats here rather than
+		 * inside detach_tasks().
 		 */
 		schedstat_inc(env->sd, lb_gained[env->idle]);
-		return 1;
+		return p;
 	}
-	return 0;
+	return NULL;
 }
 
 static const unsigned int sched_nr_migrate_break = 32;
 
 /*
- * move_tasks tries to move up to imbalance weighted load from busiest to
- * this_rq, as part of a balancing operation within domain "sd".
- * Returns 1 if successful and 0 otherwise.
+ * detach_tasks() -- tries to detach up to imbalance weighted load from
+ * busiest_rq, as part of a balancing operation within domain "sd".
  *
- * Called with both runqueues locked.
+ * Returns number of detached tasks if successful and 0 otherwise.
  */
-static int move_tasks(struct lb_env *env)
+static int detach_tasks(struct lb_env *env)
 {
 	struct list_head *tasks = &env->src_rq->cfs_tasks;
 	struct task_struct *p;
 	unsigned long load;
-	int pulled = 0;
+	int detached = 0;
+
+	lockdep_assert_held(&env->src_rq->lock);
 
 	if (env->imbalance <= 0)
 		return 0;
@@ -5407,14 +5416,16 @@ static int move_tasks(struct lb_env *env)
 		if ((load / 2) > env->imbalance)
 			goto next;
 
-		move_task(p, env);
-		pulled++;
+		detach_task(p, env);
+		list_add(&p->se.group_node, &env->tasks);
+
+		detached++;
 		env->imbalance -= load;
 
 #ifdef CONFIG_PREEMPT
 		/*
 		 * NEWIDLE balancing is a source of latency, so preemptible
-		 * kernels will stop after the first task is pulled to minimize
+		 * kernels will stop after the first task is detached to minimize
 		 * the critical section.
 		 */
 		if (env->idle == CPU_NEWLY_IDLE)
@@ -5434,13 +5445,58 @@ next:
 	}
 
 	/*
-	 * Right now, this is one of only two places move_task() is called,
-	 * so we can safely collect move_task() stats here rather than
-	 * inside move_task().
+	 * Right now, this is one of only two places we collect this stat
+	 * so we can safely collect detach_one_task() stats here rather
+	 * than inside detach_one_task().
 	 */
-	schedstat_add(env->sd, lb_gained[env->idle], pulled);
+	schedstat_add(env->sd, lb_gained[env->idle], detached);
+
+	return detached;
+}
+
+/*
+ * attach_task() -- attach the task detached by detach_task() to its new rq.
+ */
+static void attach_task(struct rq *rq, struct task_struct *p)
+{
+	lockdep_assert_held(&rq->lock);
+
+	BUG_ON(task_rq(p) != rq);
+	p->on_rq = TASK_ON_RQ_QUEUED;
+	activate_task(rq, p, 0);
+	check_preempt_curr(rq, p, 0);
+}
+
+/*
+ * attach_one_task() -- attaches the task returned from detach_one_task() to
+ * its new rq.
+ */
+static void attach_one_task(struct rq *rq, struct task_struct *p)
+{
+	raw_spin_lock(&rq->lock);
+	attach_task(rq, p);
+	raw_spin_unlock(&rq->lock);
+}
+
+/*
+ * attach_tasks() -- attaches all tasks detached by detach_tasks() to their
+ * new rq.
+ */
+static void attach_tasks(struct lb_env *env)
+{
+	struct list_head *tasks = &env->tasks;
+	struct task_struct *p;
+
+	raw_spin_lock(&env->dst_rq->lock);
+
+	while (!list_empty(tasks)) {
+		p = list_first_entry(tasks, struct task_struct, se.group_node);
+		list_del_init(&p->se.group_node);
 
-	return pulled;
+		attach_task(env->dst_rq, p);
+	}
+
+	raw_spin_unlock(&env->dst_rq->lock);
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -5559,6 +5615,13 @@ static unsigned long task_h_load(struct task_struct *p)
 #endif
 
 /********** Helpers for find_busiest_group ************************/
+
+enum group_type {
+	group_other = 0,
+	group_imbalanced,
+	group_overloaded,
+};
+
 /*
  * sg_lb_stats - stats of a sched_group required for load_balancing
  */
@@ -5572,7 +5635,7 @@ struct sg_lb_stats {
 	unsigned int group_capacity_factor;
 	unsigned int idle_cpus;
 	unsigned int group_weight;
-	int group_imb; /* Is there an imbalance in the group ? */
+	enum group_type group_type;
 	int group_has_free_capacity;
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int nr_numa_running;
@@ -5610,6 +5673,8 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
 		.total_capacity = 0UL,
 		.busiest_stat = {
 			.avg_load = 0UL,
+			.sum_nr_running = 0,
+			.group_type = group_other,
 		},
 	};
 }
@@ -5652,19 +5717,17 @@ unsigned long __weak arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
 	return default_scale_capacity(sd, cpu);
 }
 
-static unsigned long default_scale_smt_capacity(struct sched_domain *sd, int cpu)
+static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long weight = sd->span_weight;
-	unsigned long smt_gain = sd->smt_gain;
+	if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
+		return sd->smt_gain / sd->span_weight;
 
-	smt_gain /= weight;
-
-	return smt_gain;
+	return SCHED_CAPACITY_SCALE;
 }
 
-unsigned long __weak arch_scale_smt_capacity(struct sched_domain *sd, int cpu)
+unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	return default_scale_smt_capacity(sd, cpu);
+	return default_scale_cpu_capacity(sd, cpu);
 }
 
 static unsigned long scale_rt_capacity(int cpu)
@@ -5703,18 +5766,15 @@ static unsigned long scale_rt_capacity(int cpu)
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long weight = sd->span_weight;
 	unsigned long capacity = SCHED_CAPACITY_SCALE;
 	struct sched_group *sdg = sd->groups;
 
-	if ((sd->flags & SD_SHARE_CPUCAPACITY) && weight > 1) {
-		if (sched_feat(ARCH_CAPACITY))
-			capacity *= arch_scale_smt_capacity(sd, cpu);
-		else
-			capacity *= default_scale_smt_capacity(sd, cpu);
+	if (sched_feat(ARCH_CAPACITY))
+		capacity *= arch_scale_cpu_capacity(sd, cpu);
+	else
+		capacity *= default_scale_cpu_capacity(sd, cpu);
 
-		capacity >>= SCHED_CAPACITY_SHIFT;
-	}
+	capacity >>= SCHED_CAPACITY_SHIFT;
 
 	sdg->sgc->capacity_orig = capacity;
 
@@ -5891,6 +5951,18 @@ static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *gro
 	return capacity_factor;
 }
 
+static enum group_type
+group_classify(struct sched_group *group, struct sg_lb_stats *sgs)
+{
+	if (sgs->sum_nr_running > sgs->group_capacity_factor)
+		return group_overloaded;
+
+	if (sg_imbalanced(group))
+		return group_imbalanced;
+
+	return group_other;
+}
+
 /**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
  * @env: The load balancing environment.
@@ -5920,7 +5992,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			load = source_load(i, load_idx);
 
 		sgs->group_load += load;
-		sgs->sum_nr_running += rq->nr_running;
+		sgs->sum_nr_running += rq->cfs.h_nr_running;
 
 		if (rq->nr_running > 1)
 			*overload = true;
@@ -5942,9 +6014,8 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
 	sgs->group_weight = group->group_weight;
-
-	sgs->group_imb = sg_imbalanced(group);
 	sgs->group_capacity_factor = sg_capacity_factor(env, group);
+	sgs->group_type = group_classify(group, sgs);
 
 	if (sgs->group_capacity_factor > sgs->sum_nr_running)
 		sgs->group_has_free_capacity = 1;
@@ -5968,13 +6039,19 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 				   struct sched_group *sg,
 				   struct sg_lb_stats *sgs)
 {
-	if (sgs->avg_load <= sds->busiest_stat.avg_load)
-		return false;
+	struct sg_lb_stats *busiest = &sds->busiest_stat;
 
-	if (sgs->sum_nr_running > sgs->group_capacity_factor)
+	if (sgs->group_type > busiest->group_type)
 		return true;
 
-	if (sgs->group_imb)
+	if (sgs->group_type < busiest->group_type)
+		return false;
+
+	if (sgs->avg_load <= busiest->avg_load)
+		return false;
+
+	/* This is the busiest node in its class. */
+	if (!(env->sd->flags & SD_ASYM_PACKING))
 		return true;
 
 	/*
@@ -5982,8 +6059,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	 * numbered CPUs in the group, therefore mark all groups
 	 * higher than ourself as busy.
 	 */
-	if ((env->sd->flags & SD_ASYM_PACKING) && sgs->sum_nr_running &&
-	    env->dst_cpu < group_first_cpu(sg)) {
+	if (sgs->sum_nr_running && env->dst_cpu < group_first_cpu(sg)) {
 		if (!sds->busiest)
 			return true;
 
@@ -6228,7 +6304,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	local = &sds->local_stat;
 	busiest = &sds->busiest_stat;
 
-	if (busiest->group_imb) {
+	if (busiest->group_type == group_imbalanced) {
 		/*
 		 * In the group_imb case we cannot rely on group-wide averages
 		 * to ensure cpu-load equilibrium, look at wider averages. XXX
@@ -6248,12 +6324,11 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 		return fix_small_imbalance(env, sds);
 	}
 
-	if (!busiest->group_imb) {
-		/*
-		 * Don't want to pull so many tasks that a group would go idle.
-		 * Except of course for the group_imb case, since then we might
-		 * have to drop below capacity to reach cpu-load equilibrium.
-		 */
+	/*
+	 * If there aren't any idle cpus, avoid creating some.
+	 */
+	if (busiest->group_type == group_overloaded &&
+	    local->group_type   == group_overloaded) {
 		load_above_capacity =
 			(busiest->sum_nr_running - busiest->group_capacity_factor);
 
@@ -6337,7 +6412,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 	 * work because they assume all things are equal, which typically
 	 * isn't true due to cpus_allowed constraints and the like.
 	 */
-	if (busiest->group_imb)
+	if (busiest->group_type == group_imbalanced)
 		goto force_balance;
 
 	/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
@@ -6346,7 +6421,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 		goto force_balance;
 
 	/*
-	 * If the local group is more busy than the selected busiest group
+	 * If the local group is busier than the selected busiest group
 	 * don't try and pull any tasks.
 	 */
 	if (local->avg_load >= busiest->avg_load)
@@ -6361,13 +6436,14 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 
 	if (env->idle == CPU_IDLE) {
 		/*
-		 * This cpu is idle. If the busiest group load doesn't
-		 * have more tasks than the number of available cpu's and
-		 * there is no imbalance between this and busiest group
-		 * wrt to idle cpu's, it is balanced.
+		 * This cpu is idle. If the busiest group is not overloaded
+		 * and there is no imbalance between this and busiest group
+		 * wrt idle cpus, it is balanced. The imbalance becomes
+		 * significant if the diff is greater than 1 otherwise we
+		 * might end up to just move the imbalance on another group
 		 */
-		if ((local->idle_cpus < busiest->idle_cpus) &&
-		    busiest->sum_nr_running <= busiest->group_weight)
+		if ((busiest->group_type != group_overloaded) &&
+				(local->idle_cpus <= (busiest->idle_cpus + 1)))
 			goto out_balanced;
 	} else {
 		/*
@@ -6539,7 +6615,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 	struct sched_group *group;
 	struct rq *busiest;
 	unsigned long flags;
-	struct cpumask *cpus = __get_cpu_var(load_balance_mask);
+	struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask);
 
 	struct lb_env env = {
 		.sd		= sd,
@@ -6550,6 +6626,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.loop_break	= sched_nr_migrate_break,
 		.cpus		= cpus,
 		.fbq_type	= all,
+		.tasks		= LIST_HEAD_INIT(env.tasks),
 	};
 
 	/*
@@ -6599,23 +6676,30 @@ redo:
 		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
-		local_irq_save(flags);
-		double_rq_lock(env.dst_rq, busiest);
+		raw_spin_lock_irqsave(&busiest->lock, flags);
 
 		/*
 		 * cur_ld_moved - load moved in current iteration
 		 * ld_moved     - cumulative load moved across iterations
 		 */
-		cur_ld_moved = move_tasks(&env);
-		ld_moved += cur_ld_moved;
-		double_rq_unlock(env.dst_rq, busiest);
-		local_irq_restore(flags);
+		cur_ld_moved = detach_tasks(&env);
 
 		/*
-		 * some other cpu did the load balance for us.
+		 * We've detached some tasks from busiest_rq. Every
+		 * task is masked "TASK_ON_RQ_MIGRATING", so we can safely
+		 * unlock busiest->lock, and we are able to be sure
+		 * that nobody can manipulate the tasks in parallel.
+		 * See task_rq_lock() family for the details.
 		 */
-		if (cur_ld_moved && env.dst_cpu != smp_processor_id())
-			resched_cpu(env.dst_cpu);
+
+		raw_spin_unlock(&busiest->lock);
+
+		if (cur_ld_moved) {
+			attach_tasks(&env);
+			ld_moved += cur_ld_moved;
+		}
+
+		local_irq_restore(flags);
 
 		if (env.flags & LBF_NEED_BREAK) {
 			env.flags &= ~LBF_NEED_BREAK;
@@ -6665,10 +6749,8 @@ more_balance:
 		if (sd_parent) {
 			int *group_imbalance = &sd_parent->groups->sgc->imbalance;
 
-			if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) {
+			if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0)
 				*group_imbalance = 1;
-			} else if (*group_imbalance)
-				*group_imbalance = 0;
 		}
 
 		/* All tasks on this runqueue were pinned by CPU affinity */
@@ -6679,7 +6761,7 @@ more_balance:
 				env.loop_break = sched_nr_migrate_break;
 				goto redo;
 			}
-			goto out_balanced;
+			goto out_all_pinned;
 		}
 	}
 
@@ -6744,7 +6826,7 @@ more_balance:
 		 * If we've begun active balancing, start to back off. This
 		 * case may not be covered by the all_pinned logic if there
 		 * is only 1 task on the busy runqueue (because we don't call
-		 * move_tasks).
+		 * detach_tasks).
 		 */
 		if (sd->balance_interval < sd->max_interval)
 			sd->balance_interval *= 2;
@@ -6753,6 +6835,23 @@ more_balance:
 	goto out;
 
 out_balanced:
+	/*
+	 * We reach balance although we may have faced some affinity
+	 * constraints. Clear the imbalance flag if it was set.
+	 */
+	if (sd_parent) {
+		int *group_imbalance = &sd_parent->groups->sgc->imbalance;
+
+		if (*group_imbalance)
+			*group_imbalance = 0;
+	}
+
+out_all_pinned:
+	/*
+	 * We reach balance because all tasks are pinned at this level so
+	 * we can't migrate them. Let the imbalance flag set so parent level
+	 * can try to migrate them.
+	 */
 	schedstat_inc(sd, lb_balanced[idle]);
 
 	sd->nr_balance_failed = 0;
@@ -6914,6 +7013,7 @@ static int active_load_balance_cpu_stop(void *data)
 	int target_cpu = busiest_rq->push_cpu;
 	struct rq *target_rq = cpu_rq(target_cpu);
 	struct sched_domain *sd;
+	struct task_struct *p = NULL;
 
 	raw_spin_lock_irq(&busiest_rq->lock);
 
@@ -6933,9 +7033,6 @@ static int active_load_balance_cpu_stop(void *data)
 	 */
 	BUG_ON(busiest_rq == target_rq);
 
-	/* move a task from busiest_rq to target_rq */
-	double_lock_balance(busiest_rq, target_rq);
-
 	/* Search for an sd spanning us and the target CPU. */
 	rcu_read_lock();
 	for_each_domain(target_cpu, sd) {
@@ -6956,16 +7053,22 @@ static int active_load_balance_cpu_stop(void *data)
 
 		schedstat_inc(sd, alb_count);
 
-		if (move_one_task(&env))
+		p = detach_one_task(&env);
+		if (p)
 			schedstat_inc(sd, alb_pushed);
 		else
 			schedstat_inc(sd, alb_failed);
 	}
 	rcu_read_unlock();
-	double_unlock_balance(busiest_rq, target_rq);
 out_unlock:
 	busiest_rq->active_balance = 0;
-	raw_spin_unlock_irq(&busiest_rq->lock);
+	raw_spin_unlock(&busiest_rq->lock);
+
+	if (p)
+		attach_one_task(target_rq, p);
+
+	local_irq_enable();
+
 	return 0;
 }
 
@@ -7465,7 +7568,7 @@ static void task_fork_fair(struct task_struct *p)
 static void
 prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 {
-	if (!p->se.on_rq)
+	if (!task_on_rq_queued(p))
 		return;
 
 	/*
@@ -7490,11 +7593,11 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
 	 * switched back to the fair class the enqueue_entity(.flags=0) will
 	 * do the right thing.
 	 *
-	 * If it's on_rq, then the dequeue_entity(.flags=0) will already
-	 * have normalized the vruntime, if it's !on_rq, then only when
+	 * If it's queued, then the dequeue_entity(.flags=0) will already
+	 * have normalized the vruntime, if it's !queued, then only when
 	 * the task is sleeping will it still have non-normalized vruntime.
 	 */
-	if (!p->on_rq && p->state != TASK_RUNNING) {
+	if (!task_on_rq_queued(p) && p->state != TASK_RUNNING) {
 		/*
 		 * Fix up our vruntime so that the current sleep doesn't
 		 * cause 'unlimited' sleep bonus.
@@ -7521,15 +7624,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
  */
 static void switched_to_fair(struct rq *rq, struct task_struct *p)
 {
-	struct sched_entity *se = &p->se;
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	struct sched_entity *se = &p->se;
 	/*
 	 * Since the real-depth could have been changed (only FAIR
 	 * class maintain depth value), reset depth properly.
 	 */
 	se->depth = se->parent ? se->parent->depth + 1 : 0;
 #endif
-	if (!se->on_rq)
+	if (!task_on_rq_queued(p))
 		return;
 
 	/*
@@ -7575,7 +7678,7 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static void task_move_group_fair(struct task_struct *p, int on_rq)
+static void task_move_group_fair(struct task_struct *p, int queued)
 {
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq;
@@ -7594,7 +7697,7 @@ static void task_move_group_fair(struct task_struct *p, int on_rq)
 	 * fair sleeper stuff for the first placement, but who cares.
 	 */
 	/*
-	 * When !on_rq, vruntime of the task has usually NOT been normalized.
+	 * When !queued, vruntime of the task has usually NOT been normalized.
 	 * But there are some cases where it has already been normalized:
 	 *
 	 * - Moving a forked child which is waiting for being woken up by
@@ -7605,14 +7708,14 @@ static void task_move_group_fair(struct task_struct *p, int on_rq)
 	 * To prevent boost or penalty in the new cfs_rq caused by delta
 	 * min_vruntime between the two cfs_rqs, we skip vruntime adjustment.
 	 */
-	if (!on_rq && (!se->sum_exec_runtime || p->state == TASK_WAKING))
-		on_rq = 1;
+	if (!queued && (!se->sum_exec_runtime || p->state == TASK_WAKING))
+		queued = 1;
 
-	if (!on_rq)
+	if (!queued)
 		se->vruntime -= cfs_rq_of(se)->min_vruntime;
 	set_task_rq(p, task_cpu(p));
 	se->depth = se->parent ? se->parent->depth + 1 : 0;
-	if (!on_rq) {
+	if (!queued) {
 		cfs_rq = cfs_rq_of(se);
 		se->vruntime += cfs_rq->min_vruntime;
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 11e7bc434f43..c47fce75e666 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -147,6 +147,9 @@ use_default:
 	    clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
 		goto use_default;
 
+	/* Take note of the planned idle state. */
+	idle_set_state(this_rq(), &drv->states[next_state]);
+
 	/*
 	 * Enter the idle state previously returned by the governor decision.
 	 * This function will block until an interrupt occurs and will take
@@ -154,6 +157,9 @@ use_default:
 	 */
 	entered_state = cpuidle_enter(drv, dev, next_state);
 
+	/* The cpu is no longer idle or about to enter idle. */
+	idle_set_state(this_rq(), NULL);
+
 	if (broadcast)
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 5f6edca4fafd..d024e6ce30ba 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1448,7 +1448,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev)
 		 * means a dl or stop task can slip in, in which case we need
 		 * to re-start task selection.
 		 */
-		if (unlikely((rq->stop && rq->stop->on_rq) ||
+		if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) ||
 			     rq->dl.dl_nr_running))
 			return RETRY_TASK;
 	}
@@ -1468,8 +1468,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev)
 	p = _pick_next_task_rt(rq);
 
 	/* The running task is never eligible for pushing */
-	if (p)
-		dequeue_pushable_task(rq, p);
+	dequeue_pushable_task(rq, p);
 
 	set_post_schedule(rq);
 
@@ -1526,7 +1525,7 @@ static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 static int find_lowest_rq(struct task_struct *task)
 {
 	struct sched_domain *sd;
-	struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
+	struct cpumask *lowest_mask = this_cpu_cpumask_var_ptr(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
 
@@ -1624,7 +1623,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 				     !cpumask_test_cpu(lowest_rq->cpu,
 						       tsk_cpus_allowed(task)) ||
 				     task_running(rq, task) ||
-				     !task->on_rq)) {
+				     !task_on_rq_queued(task))) {
 
 				double_unlock_balance(rq, lowest_rq);
 				lowest_rq = NULL;
@@ -1658,7 +1657,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
 	BUG_ON(task_current(rq, p));
 	BUG_ON(p->nr_cpus_allowed <= 1);
 
-	BUG_ON(!p->on_rq);
+	BUG_ON(!task_on_rq_queued(p));
 	BUG_ON(!rt_task(p));
 
 	return p;
@@ -1809,7 +1808,7 @@ static int pull_rt_task(struct rq *this_rq)
 		 */
 		if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
 			WARN_ON(p == src_rq->curr);
-			WARN_ON(!p->on_rq);
+			WARN_ON(!task_on_rq_queued(p));
 
 			/*
 			 * There's a chance that p is higher in priority
@@ -1870,7 +1869,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 
 	BUG_ON(!rt_task(p));
 
-	if (!p->on_rq)
+	if (!task_on_rq_queued(p))
 		return;
 
 	weight = cpumask_weight(new_mask);
@@ -1936,7 +1935,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
 	 * we may need to handle the pulling of RT tasks
 	 * now.
 	 */
-	if (!p->on_rq || rq->rt.rt_nr_running)
+	if (!task_on_rq_queued(p) || rq->rt.rt_nr_running)
 		return;
 
 	if (pull_rt_task(rq))
@@ -1970,7 +1969,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 	 * If that current running task is also an RT task
 	 * then see if we can move to another run queue.
 	 */
-	if (p->on_rq && rq->curr != p) {
+	if (task_on_rq_queued(p) && rq->curr != p) {
 #ifdef CONFIG_SMP
 		if (p->nr_cpus_allowed > 1 && rq->rt.overloaded &&
 		    /* Don't resched if we changed runqueues */
@@ -1989,7 +1988,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 static void
 prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 {
-	if (!p->on_rq)
+	if (!task_on_rq_queued(p))
 		return;
 
 	if (rq->curr == p) {
@@ -2073,7 +2072,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	for_each_sched_rt_entity(rt_se) {
 		if (rt_se->run_list.prev != rt_se->run_list.next) {
 			requeue_task_rt(rq, p, 0);
-			set_tsk_need_resched(p);
+			resched_curr(rq);
 			return;
 		}
 	}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 579712f4e9d5..24156c8434d1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -14,6 +14,11 @@
 #include "cpuacct.h"
 
 struct rq;
+struct cpuidle_state;
+
+/* task_struct::on_rq states: */
+#define TASK_ON_RQ_QUEUED	1
+#define TASK_ON_RQ_MIGRATING	2
 
 extern __read_mostly int scheduler_running;
 
@@ -126,6 +131,9 @@ struct rt_bandwidth {
 	u64			rt_runtime;
 	struct hrtimer		rt_period_timer;
 };
+
+void __dl_clear_params(struct task_struct *p);
+
 /*
  * To keep the bandwidth of -deadline tasks and groups under control
  * we need some place where:
@@ -184,7 +192,7 @@ struct cfs_bandwidth {
 	raw_spinlock_t lock;
 	ktime_t period;
 	u64 quota, runtime;
-	s64 hierarchal_quota;
+	s64 hierarchical_quota;
 	u64 runtime_expires;
 
 	int idle, timer_active;
@@ -636,6 +644,11 @@ struct rq {
 #ifdef CONFIG_SMP
 	struct llist_head wake_list;
 #endif
+
+#ifdef CONFIG_CPU_IDLE
+	/* Must be inspected within a rcu lock section */
+	struct cpuidle_state *idle_state;
+#endif
 };
 
 static inline int cpu_of(struct rq *rq)
@@ -647,13 +660,13 @@ static inline int cpu_of(struct rq *rq)
 #endif
 }
 
-DECLARE_PER_CPU(struct rq, runqueues);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
 #define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
-#define this_rq()		(&__get_cpu_var(runqueues))
+#define this_rq()		this_cpu_ptr(&runqueues)
 #define task_rq(p)		cpu_rq(task_cpu(p))
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
-#define raw_rq()		(&__raw_get_cpu_var(runqueues))
+#define raw_rq()		raw_cpu_ptr(&runqueues)
 
 static inline u64 rq_clock(struct rq *rq)
 {
@@ -942,6 +955,15 @@ static inline int task_running(struct rq *rq, struct task_struct *p)
 #endif
 }
 
+static inline int task_on_rq_queued(struct task_struct *p)
+{
+	return p->on_rq == TASK_ON_RQ_QUEUED;
+}
+
+static inline int task_on_rq_migrating(struct task_struct *p)
+{
+	return p->on_rq == TASK_ON_RQ_MIGRATING;
+}
 
 #ifndef prepare_arch_switch
 # define prepare_arch_switch(next)	do { } while (0)
@@ -953,7 +975,6 @@ static inline int task_running(struct rq *rq, struct task_struct *p)
 # define finish_arch_post_lock_switch()	do { } while (0)
 #endif
 
-#ifndef __ARCH_WANT_UNLOCKED_CTXSW
 static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
 {
 #ifdef CONFIG_SMP
@@ -991,35 +1012,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	raw_spin_unlock_irq(&rq->lock);
 }
 
-#else /* __ARCH_WANT_UNLOCKED_CTXSW */
-static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
-{
-#ifdef CONFIG_SMP
-	/*
-	 * We can optimise this out completely for !SMP, because the
-	 * SMP rebalancing from interrupt is the only thing that cares
-	 * here.
-	 */
-	next->on_cpu = 1;
-#endif
-	raw_spin_unlock(&rq->lock);
-}
-
-static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
-{
-#ifdef CONFIG_SMP
-	/*
-	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
-	 * We must ensure this doesn't happen until the switch is completely
-	 * finished.
-	 */
-	smp_wmb();
-	prev->on_cpu = 0;
-#endif
-	local_irq_enable();
-}
-#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
-
 /*
  * wake flags
  */
@@ -1180,6 +1172,30 @@ static inline void idle_exit_fair(struct rq *rq) { }
 
 #endif
 
+#ifdef CONFIG_CPU_IDLE
+static inline void idle_set_state(struct rq *rq,
+				  struct cpuidle_state *idle_state)
+{
+	rq->idle_state = idle_state;
+}
+
+static inline struct cpuidle_state *idle_get_state(struct rq *rq)
+{
+	WARN_ON(!rcu_read_lock_held());
+	return rq->idle_state;
+}
+#else
+static inline void idle_set_state(struct rq *rq,
+				  struct cpuidle_state *idle_state)
+{
+}
+
+static inline struct cpuidle_state *idle_get_state(struct rq *rq)
+{
+	return NULL;
+}
+#endif
+
 extern void sysrq_sched_debug_show(void);
 extern void sched_init_granularity(void);
 extern void update_max_interval(void);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index bfe0edadbfbb..67426e529f59 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -28,7 +28,7 @@ pick_next_task_stop(struct rq *rq, struct task_struct *prev)
 {
 	struct task_struct *stop = rq->stop;
 
-	if (!stop || !stop->on_rq)
+	if (!stop || !task_on_rq_queued(stop))
 		return NULL;
 
 	put_prev_task(rq, prev);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 84922befea84..4ef9687ac115 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -21,10 +21,11 @@
 #include <linux/slab.h>
 #include <linux/syscalls.h>
 
-/* #define SECCOMP_DEBUG 1 */
+#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
+#include <asm/syscall.h>
+#endif
 
 #ifdef CONFIG_SECCOMP_FILTER
-#include <asm/syscall.h>
 #include <linux/filter.h>
 #include <linux/pid.h>
 #include <linux/ptrace.h>
@@ -172,10 +173,10 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
  *
  * Returns valid seccomp BPF response codes.
  */
-static u32 seccomp_run_filters(int syscall)
+static u32 seccomp_run_filters(struct seccomp_data *sd)
 {
 	struct seccomp_filter *f = ACCESS_ONCE(current->seccomp.filter);
-	struct seccomp_data sd;
+	struct seccomp_data sd_local;
 	u32 ret = SECCOMP_RET_ALLOW;
 
 	/* Ensure unexpected behavior doesn't result in failing open. */
@@ -185,14 +186,17 @@ static u32 seccomp_run_filters(int syscall)
 	/* Make sure cross-thread synced filter points somewhere sane. */
 	smp_read_barrier_depends();
 
-	populate_seccomp_data(&sd);
+	if (!sd) {
+		populate_seccomp_data(&sd_local);
+		sd = &sd_local;
+	}
 
 	/*
 	 * All filters in the list are evaluated and the lowest BPF return
 	 * value always takes priority (ignoring the DATA).
 	 */
 	for (; f; f = f->prev) {
-		u32 cur_ret = BPF_PROG_RUN(f->prog, (void *)&sd);
+		u32 cur_ret = BPF_PROG_RUN(f->prog, (void *)sd);
 
 		if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
 			ret = cur_ret;
@@ -563,11 +567,55 @@ static int mode1_syscalls_32[] = {
 };
 #endif
 
-int __secure_computing(int this_syscall)
+static void __secure_computing_strict(int this_syscall)
+{
+	int *syscall_whitelist = mode1_syscalls;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task())
+		syscall_whitelist = mode1_syscalls_32;
+#endif
+	do {
+		if (*syscall_whitelist == this_syscall)
+			return;
+	} while (*++syscall_whitelist);
+
+#ifdef SECCOMP_DEBUG
+	dump_stack();
+#endif
+	audit_seccomp(this_syscall, SIGKILL, SECCOMP_RET_KILL);
+	do_exit(SIGKILL);
+}
+
+#ifndef CONFIG_HAVE_ARCH_SECCOMP_FILTER
+void secure_computing_strict(int this_syscall)
+{
+	int mode = current->seccomp.mode;
+
+	if (mode == 0)
+		return;
+	else if (mode == SECCOMP_MODE_STRICT)
+		__secure_computing_strict(this_syscall);
+	else
+		BUG();
+}
+#else
+int __secure_computing(void)
 {
-	int exit_sig = 0;
-	int *syscall;
-	u32 ret;
+	u32 phase1_result = seccomp_phase1(NULL);
+
+	if (likely(phase1_result == SECCOMP_PHASE1_OK))
+		return 0;
+	else if (likely(phase1_result == SECCOMP_PHASE1_SKIP))
+		return -1;
+	else
+		return seccomp_phase2(phase1_result);
+}
+
+#ifdef CONFIG_SECCOMP_FILTER
+static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
+{
+	u32 filter_ret, action;
+	int data;
 
 	/*
 	 * Make sure that any changes to mode from another thread have
@@ -575,85 +623,127 @@ int __secure_computing(int this_syscall)
 	 */
 	rmb();
 
-	switch (current->seccomp.mode) {
-	case SECCOMP_MODE_STRICT:
-		syscall = mode1_syscalls;
-#ifdef CONFIG_COMPAT
-		if (is_compat_task())
-			syscall = mode1_syscalls_32;
+	filter_ret = seccomp_run_filters(sd);
+	data = filter_ret & SECCOMP_RET_DATA;
+	action = filter_ret & SECCOMP_RET_ACTION;
+
+	switch (action) {
+	case SECCOMP_RET_ERRNO:
+		/* Set the low-order 16-bits as a errno. */
+		syscall_set_return_value(current, task_pt_regs(current),
+					 -data, 0);
+		goto skip;
+
+	case SECCOMP_RET_TRAP:
+		/* Show the handler the original registers. */
+		syscall_rollback(current, task_pt_regs(current));
+		/* Let the filter pass back 16 bits of data. */
+		seccomp_send_sigsys(this_syscall, data);
+		goto skip;
+
+	case SECCOMP_RET_TRACE:
+		return filter_ret;  /* Save the rest for phase 2. */
+
+	case SECCOMP_RET_ALLOW:
+		return SECCOMP_PHASE1_OK;
+
+	case SECCOMP_RET_KILL:
+	default:
+		audit_seccomp(this_syscall, SIGSYS, action);
+		do_exit(SIGSYS);
+	}
+
+	unreachable();
+
+skip:
+	audit_seccomp(this_syscall, 0, action);
+	return SECCOMP_PHASE1_SKIP;
+}
 #endif
-		do {
-			if (*syscall == this_syscall)
-				return 0;
-		} while (*++syscall);
-		exit_sig = SIGKILL;
-		ret = SECCOMP_RET_KILL;
-		break;
+
+/**
+ * seccomp_phase1() - run fast path seccomp checks on the current syscall
+ * @arg sd: The seccomp_data or NULL
+ *
+ * This only reads pt_regs via the syscall_xyz helpers.  The only change
+ * it will make to pt_regs is via syscall_set_return_value, and it will
+ * only do that if it returns SECCOMP_PHASE1_SKIP.
+ *
+ * If sd is provided, it will not read pt_regs at all.
+ *
+ * It may also call do_exit or force a signal; these actions must be
+ * safe.
+ *
+ * If it returns SECCOMP_PHASE1_OK, the syscall passes checks and should
+ * be processed normally.
+ *
+ * If it returns SECCOMP_PHASE1_SKIP, then the syscall should not be
+ * invoked.  In this case, seccomp_phase1 will have set the return value
+ * using syscall_set_return_value.
+ *
+ * If it returns anything else, then the return value should be passed
+ * to seccomp_phase2 from a context in which ptrace hooks are safe.
+ */
+u32 seccomp_phase1(struct seccomp_data *sd)
+{
+	int mode = current->seccomp.mode;
+	int this_syscall = sd ? sd->nr :
+		syscall_get_nr(current, task_pt_regs(current));
+
+	switch (mode) {
+	case SECCOMP_MODE_STRICT:
+		__secure_computing_strict(this_syscall);  /* may call do_exit */
+		return SECCOMP_PHASE1_OK;
 #ifdef CONFIG_SECCOMP_FILTER
-	case SECCOMP_MODE_FILTER: {
-		int data;
-		struct pt_regs *regs = task_pt_regs(current);
-		ret = seccomp_run_filters(this_syscall);
-		data = ret & SECCOMP_RET_DATA;
-		ret &= SECCOMP_RET_ACTION;
-		switch (ret) {
-		case SECCOMP_RET_ERRNO:
-			/* Set the low-order 16-bits as a errno. */
-			syscall_set_return_value(current, regs,
-						 -data, 0);
-			goto skip;
-		case SECCOMP_RET_TRAP:
-			/* Show the handler the original registers. */
-			syscall_rollback(current, regs);
-			/* Let the filter pass back 16 bits of data. */
-			seccomp_send_sigsys(this_syscall, data);
-			goto skip;
-		case SECCOMP_RET_TRACE:
-			/* Skip these calls if there is no tracer. */
-			if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
-				syscall_set_return_value(current, regs,
-							 -ENOSYS, 0);
-				goto skip;
-			}
-			/* Allow the BPF to provide the event message */
-			ptrace_event(PTRACE_EVENT_SECCOMP, data);
-			/*
-			 * The delivery of a fatal signal during event
-			 * notification may silently skip tracer notification.
-			 * Terminating the task now avoids executing a system
-			 * call that may not be intended.
-			 */
-			if (fatal_signal_pending(current))
-				break;
-			if (syscall_get_nr(current, regs) < 0)
-				goto skip;  /* Explicit request to skip. */
-
-			return 0;
-		case SECCOMP_RET_ALLOW:
-			return 0;
-		case SECCOMP_RET_KILL:
-		default:
-			break;
-		}
-		exit_sig = SIGSYS;
-		break;
-	}
+	case SECCOMP_MODE_FILTER:
+		return __seccomp_phase1_filter(this_syscall, sd);
 #endif
 	default:
 		BUG();
 	}
+}
 
-#ifdef SECCOMP_DEBUG
-	dump_stack();
-#endif
-	audit_seccomp(this_syscall, exit_sig, ret);
-	do_exit(exit_sig);
-#ifdef CONFIG_SECCOMP_FILTER
-skip:
-	audit_seccomp(this_syscall, exit_sig, ret);
-#endif
-	return -1;
+/**
+ * seccomp_phase2() - finish slow path seccomp work for the current syscall
+ * @phase1_result: The return value from seccomp_phase1()
+ *
+ * This must be called from a context in which ptrace hooks can be used.
+ *
+ * Returns 0 if the syscall should be processed or -1 to skip the syscall.
+ */
+int seccomp_phase2(u32 phase1_result)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	u32 action = phase1_result & SECCOMP_RET_ACTION;
+	int data = phase1_result & SECCOMP_RET_DATA;
+
+	BUG_ON(action != SECCOMP_RET_TRACE);
+
+	audit_seccomp(syscall_get_nr(current, regs), 0, action);
+
+	/* Skip these calls if there is no tracer. */
+	if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
+		syscall_set_return_value(current, regs,
+					 -ENOSYS, 0);
+		return -1;
+	}
+
+	/* Allow the BPF to provide the event message */
+	ptrace_event(PTRACE_EVENT_SECCOMP, data);
+	/*
+	 * The delivery of a fatal signal during event
+	 * notification may silently skip tracer notification.
+	 * Terminating the task now avoids executing a system
+	 * call that may not be intended.
+	 */
+	if (fatal_signal_pending(current))
+		do_exit(SIGSYS);
+	if (syscall_get_nr(current, regs) < 0)
+		return -1;  /* Explicit request to skip. */
+
+	return 0;
 }
+#endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */
 
 long prctl_get_seccomp(void)
 {
diff --git a/kernel/smp.c b/kernel/smp.c
index aff8aa14f547..f38a1e692259 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -13,6 +13,7 @@
 #include <linux/gfp.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
+#include <linux/sched.h>
 
 #include "smpboot.h"
 
@@ -164,7 +165,7 @@ static int generic_exec_single(int cpu, struct call_single_data *csd,
 	if (!csd) {
 		csd = &csd_stack;
 		if (!wait)
-			csd = &__get_cpu_var(csd_data);
+			csd = this_cpu_ptr(&csd_data);
 	}
 
 	csd_lock(csd);
@@ -229,7 +230,7 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 
 	WARN_ON(!irqs_disabled());
 
-	head = &__get_cpu_var(call_single_queue);
+	head = this_cpu_ptr(&call_single_queue);
 	entry = llist_del_all(head);
 	entry = llist_reverse_order(entry);
 
@@ -419,7 +420,7 @@ void smp_call_function_many(const struct cpumask *mask,
 		return;
 	}
 
-	cfd = &__get_cpu_var(cfd_data);
+	cfd = this_cpu_ptr(&cfd_data);
 
 	cpumask_and(cfd->cpumask, mask, cpu_online_mask);
 	cpumask_clear_cpu(this_cpu, cfd->cpumask);
@@ -699,3 +700,24 @@ void kick_all_cpus_sync(void)
 	smp_call_function(do_nothing, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(kick_all_cpus_sync);
+
+/**
+ * wake_up_all_idle_cpus - break all cpus out of idle
+ * wake_up_all_idle_cpus try to break all cpus which is in idle state even
+ * including idle polling cpus, for non-idle cpus, we will do nothing
+ * for them.
+ */
+void wake_up_all_idle_cpus(void)
+{
+	int cpu;
+
+	preempt_disable();
+	for_each_online_cpu(cpu) {
+		if (cpu == smp_processor_id())
+			continue;
+
+		wake_up_if_idle(cpu);
+	}
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 5918d227730f..0699add19164 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -278,7 +278,7 @@ restart:
 		pending >>= softirq_bit;
 	}
 
-	rcu_bh_qs(smp_processor_id());
+	rcu_bh_qs();
 	local_irq_disable();
 
 	pending = local_softirq_pending();
@@ -485,7 +485,7 @@ static void tasklet_action(struct softirq_action *a)
 	local_irq_disable();
 	list = __this_cpu_read(tasklet_vec.head);
 	__this_cpu_write(tasklet_vec.head, NULL);
-	__this_cpu_write(tasklet_vec.tail, &__get_cpu_var(tasklet_vec).head);
+	__this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head));
 	local_irq_enable();
 
 	while (list) {
@@ -521,7 +521,7 @@ static void tasklet_hi_action(struct softirq_action *a)
 	local_irq_disable();
 	list = __this_cpu_read(tasklet_hi_vec.head);
 	__this_cpu_write(tasklet_hi_vec.head, NULL);
-	__this_cpu_write(tasklet_hi_vec.tail, &__get_cpu_var(tasklet_hi_vec).head);
+	__this_cpu_write(tasklet_hi_vec.tail, this_cpu_ptr(&tasklet_hi_vec.head));
 	local_irq_enable();
 
 	while (list) {
diff --git a/kernel/sys.c b/kernel/sys.c
index ce8129192a26..1eaa2f0b0246 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -62,28 +62,28 @@
 #include <asm/unistd.h>
 
 #ifndef SET_UNALIGN_CTL
-# define SET_UNALIGN_CTL(a,b)	(-EINVAL)
+# define SET_UNALIGN_CTL(a, b)	(-EINVAL)
 #endif
 #ifndef GET_UNALIGN_CTL
-# define GET_UNALIGN_CTL(a,b)	(-EINVAL)
+# define GET_UNALIGN_CTL(a, b)	(-EINVAL)
 #endif
 #ifndef SET_FPEMU_CTL
-# define SET_FPEMU_CTL(a,b)	(-EINVAL)
+# define SET_FPEMU_CTL(a, b)	(-EINVAL)
 #endif
 #ifndef GET_FPEMU_CTL
-# define GET_FPEMU_CTL(a,b)	(-EINVAL)
+# define GET_FPEMU_CTL(a, b)	(-EINVAL)
 #endif
 #ifndef SET_FPEXC_CTL
-# define SET_FPEXC_CTL(a,b)	(-EINVAL)
+# define SET_FPEXC_CTL(a, b)	(-EINVAL)
 #endif
 #ifndef GET_FPEXC_CTL
-# define GET_FPEXC_CTL(a,b)	(-EINVAL)
+# define GET_FPEXC_CTL(a, b)	(-EINVAL)
 #endif
 #ifndef GET_ENDIAN
-# define GET_ENDIAN(a,b)	(-EINVAL)
+# define GET_ENDIAN(a, b)	(-EINVAL)
 #endif
 #ifndef SET_ENDIAN
-# define SET_ENDIAN(a,b)	(-EINVAL)
+# define SET_ENDIAN(a, b)	(-EINVAL)
 #endif
 #ifndef GET_TSC_CTL
 # define GET_TSC_CTL(a)		(-EINVAL)
@@ -182,39 +182,40 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
 	rcu_read_lock();
 	read_lock(&tasklist_lock);
 	switch (which) {
-		case PRIO_PROCESS:
-			if (who)
-				p = find_task_by_vpid(who);
-			else
-				p = current;
-			if (p)
-				error = set_one_prio(p, niceval, error);
-			break;
-		case PRIO_PGRP:
-			if (who)
-				pgrp = find_vpid(who);
-			else
-				pgrp = task_pgrp(current);
-			do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
-				error = set_one_prio(p, niceval, error);
-			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
-			break;
-		case PRIO_USER:
-			uid = make_kuid(cred->user_ns, who);
-			user = cred->user;
-			if (!who)
-				uid = cred->uid;
-			else if (!uid_eq(uid, cred->uid) &&
-				 !(user = find_user(uid)))
+	case PRIO_PROCESS:
+		if (who)
+			p = find_task_by_vpid(who);
+		else
+			p = current;
+		if (p)
+			error = set_one_prio(p, niceval, error);
+		break;
+	case PRIO_PGRP:
+		if (who)
+			pgrp = find_vpid(who);
+		else
+			pgrp = task_pgrp(current);
+		do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
+			error = set_one_prio(p, niceval, error);
+		} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+		break;
+	case PRIO_USER:
+		uid = make_kuid(cred->user_ns, who);
+		user = cred->user;
+		if (!who)
+			uid = cred->uid;
+		else if (!uid_eq(uid, cred->uid)) {
+			user = find_user(uid);
+			if (!user)
 				goto out_unlock;	/* No processes for this user */
-
-			do_each_thread(g, p) {
-				if (uid_eq(task_uid(p), uid))
-					error = set_one_prio(p, niceval, error);
-			} while_each_thread(g, p);
-			if (!uid_eq(uid, cred->uid))
-				free_uid(user);		/* For find_user() */
-			break;
+		}
+		do_each_thread(g, p) {
+			if (uid_eq(task_uid(p), uid))
+				error = set_one_prio(p, niceval, error);
+		} while_each_thread(g, p);
+		if (!uid_eq(uid, cred->uid))
+			free_uid(user);		/* For find_user() */
+		break;
 	}
 out_unlock:
 	read_unlock(&tasklist_lock);
@@ -244,47 +245,48 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
 	rcu_read_lock();
 	read_lock(&tasklist_lock);
 	switch (which) {
-		case PRIO_PROCESS:
-			if (who)
-				p = find_task_by_vpid(who);
-			else
-				p = current;
-			if (p) {
+	case PRIO_PROCESS:
+		if (who)
+			p = find_task_by_vpid(who);
+		else
+			p = current;
+		if (p) {
+			niceval = nice_to_rlimit(task_nice(p));
+			if (niceval > retval)
+				retval = niceval;
+		}
+		break;
+	case PRIO_PGRP:
+		if (who)
+			pgrp = find_vpid(who);
+		else
+			pgrp = task_pgrp(current);
+		do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
+			niceval = nice_to_rlimit(task_nice(p));
+			if (niceval > retval)
+				retval = niceval;
+		} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+		break;
+	case PRIO_USER:
+		uid = make_kuid(cred->user_ns, who);
+		user = cred->user;
+		if (!who)
+			uid = cred->uid;
+		else if (!uid_eq(uid, cred->uid)) {
+			user = find_user(uid);
+			if (!user)
+				goto out_unlock;	/* No processes for this user */
+		}
+		do_each_thread(g, p) {
+			if (uid_eq(task_uid(p), uid)) {
 				niceval = nice_to_rlimit(task_nice(p));
 				if (niceval > retval)
 					retval = niceval;
 			}
-			break;
-		case PRIO_PGRP:
-			if (who)
-				pgrp = find_vpid(who);
-			else
-				pgrp = task_pgrp(current);
-			do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
-				niceval = nice_to_rlimit(task_nice(p));
-				if (niceval > retval)
-					retval = niceval;
-			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
-			break;
-		case PRIO_USER:
-			uid = make_kuid(cred->user_ns, who);
-			user = cred->user;
-			if (!who)
-				uid = cred->uid;
-			else if (!uid_eq(uid, cred->uid) &&
-				 !(user = find_user(uid)))
-				goto out_unlock;	/* No processes for this user */
-
-			do_each_thread(g, p) {
-				if (uid_eq(task_uid(p), uid)) {
-					niceval = nice_to_rlimit(task_nice(p));
-					if (niceval > retval)
-						retval = niceval;
-				}
-			} while_each_thread(g, p);
-			if (!uid_eq(uid, cred->uid))
-				free_uid(user);		/* for find_user() */
-			break;
+		} while_each_thread(g, p);
+		if (!uid_eq(uid, cred->uid))
+			free_uid(user);		/* for find_user() */
+		break;
 	}
 out_unlock:
 	read_unlock(&tasklist_lock);
@@ -306,7 +308,7 @@ out_unlock:
  *
  * The general idea is that a program which uses just setregid() will be
  * 100% compatible with BSD.  A program which uses just setgid() will be
- * 100% compatible with POSIX with saved IDs. 
+ * 100% compatible with POSIX with saved IDs.
  *
  * SMP: There are not races, the GIDs are checked only by filesystem
  *      operations (as far as semantic preservation is concerned).
@@ -364,7 +366,7 @@ error:
 }
 
 /*
- * setgid() is implemented like SysV w/ SAVED_IDS 
+ * setgid() is implemented like SysV w/ SAVED_IDS
  *
  * SMP: Same implicit races as above.
  */
@@ -442,7 +444,7 @@ static int set_user(struct cred *new)
  *
  * The general idea is that a program which uses just setreuid() will be
  * 100% compatible with BSD.  A program which uses just setuid() will be
- * 100% compatible with POSIX with saved IDs. 
+ * 100% compatible with POSIX with saved IDs.
  */
 SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
 {
@@ -503,17 +505,17 @@ error:
 	abort_creds(new);
 	return retval;
 }
-		
+
 /*
- * setuid() is implemented like SysV with SAVED_IDS 
- * 
+ * setuid() is implemented like SysV with SAVED_IDS
+ *
  * Note that SAVED_ID's is deficient in that a setuid root program
- * like sendmail, for example, cannot set its uid to be a normal 
+ * like sendmail, for example, cannot set its uid to be a normal
  * user and then switch back, because if you're root, setuid() sets
  * the saved uid too.  If you don't like this, blame the bright people
  * in the POSIX committee and/or USG.  Note that the BSD-style setreuid()
  * will allow a root program to temporarily drop privileges and be able to
- * regain them by swapping the real and effective uid.  
+ * regain them by swapping the real and effective uid.
  */
 SYSCALL_DEFINE1(setuid, uid_t, uid)
 {
@@ -637,10 +639,12 @@ SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t _
 	euid = from_kuid_munged(cred->user_ns, cred->euid);
 	suid = from_kuid_munged(cred->user_ns, cred->suid);
 
-	if (!(retval   = put_user(ruid, ruidp)) &&
-	    !(retval   = put_user(euid, euidp)))
-		retval = put_user(suid, suidp);
-
+	retval = put_user(ruid, ruidp);
+	if (!retval) {
+		retval = put_user(euid, euidp);
+		if (!retval)
+			return put_user(suid, suidp);
+	}
 	return retval;
 }
 
@@ -709,9 +713,12 @@ SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t _
 	egid = from_kgid_munged(cred->user_ns, cred->egid);
 	sgid = from_kgid_munged(cred->user_ns, cred->sgid);
 
-	if (!(retval   = put_user(rgid, rgidp)) &&
-	    !(retval   = put_user(egid, egidp)))
-		retval = put_user(sgid, sgidp);
+	retval = put_user(rgid, rgidp);
+	if (!retval) {
+		retval = put_user(egid, egidp);
+		if (!retval)
+			retval = put_user(sgid, sgidp);
+	}
 
 	return retval;
 }
@@ -862,11 +869,9 @@ void do_sys_times(struct tms *tms)
 {
 	cputime_t tgutime, tgstime, cutime, cstime;
 
-	spin_lock_irq(&current->sighand->siglock);
 	thread_group_cputime_adjusted(current, &tgutime, &tgstime);
 	cutime = current->signal->cutime;
 	cstime = current->signal->cstime;
-	spin_unlock_irq(&current->sighand->siglock);
 	tms->tms_utime = cputime_to_clock_t(tgutime);
 	tms->tms_stime = cputime_to_clock_t(tgstime);
 	tms->tms_cutime = cputime_to_clock_t(cutime);
@@ -1284,7 +1289,6 @@ SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim)
 /*
  *	Back compatibility for getrlimit. Needed for some apps.
  */
- 
 SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
 		struct rlimit __user *, rlim)
 {
@@ -1299,7 +1303,7 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
 		x.rlim_cur = 0x7FFFFFFF;
 	if (x.rlim_max > 0x7FFFFFFF)
 		x.rlim_max = 0x7FFFFFFF;
-	return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0;
+	return copy_to_user(rlim, &x, sizeof(x)) ? -EFAULT : 0;
 }
 
 #endif
@@ -1527,7 +1531,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 	cputime_t tgutime, tgstime, utime, stime;
 	unsigned long maxrss = 0;
 
-	memset((char *) r, 0, sizeof *r);
+	memset((char *)r, 0, sizeof (*r));
 	utime = stime = 0;
 
 	if (who == RUSAGE_THREAD) {
@@ -1541,41 +1545,41 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 		return;
 
 	switch (who) {
-		case RUSAGE_BOTH:
-		case RUSAGE_CHILDREN:
-			utime = p->signal->cutime;
-			stime = p->signal->cstime;
-			r->ru_nvcsw = p->signal->cnvcsw;
-			r->ru_nivcsw = p->signal->cnivcsw;
-			r->ru_minflt = p->signal->cmin_flt;
-			r->ru_majflt = p->signal->cmaj_flt;
-			r->ru_inblock = p->signal->cinblock;
-			r->ru_oublock = p->signal->coublock;
-			maxrss = p->signal->cmaxrss;
-
-			if (who == RUSAGE_CHILDREN)
-				break;
-
-		case RUSAGE_SELF:
-			thread_group_cputime_adjusted(p, &tgutime, &tgstime);
-			utime += tgutime;
-			stime += tgstime;
-			r->ru_nvcsw += p->signal->nvcsw;
-			r->ru_nivcsw += p->signal->nivcsw;
-			r->ru_minflt += p->signal->min_flt;
-			r->ru_majflt += p->signal->maj_flt;
-			r->ru_inblock += p->signal->inblock;
-			r->ru_oublock += p->signal->oublock;
-			if (maxrss < p->signal->maxrss)
-				maxrss = p->signal->maxrss;
-			t = p;
-			do {
-				accumulate_thread_rusage(t, r);
-			} while_each_thread(p, t);
+	case RUSAGE_BOTH:
+	case RUSAGE_CHILDREN:
+		utime = p->signal->cutime;
+		stime = p->signal->cstime;
+		r->ru_nvcsw = p->signal->cnvcsw;
+		r->ru_nivcsw = p->signal->cnivcsw;
+		r->ru_minflt = p->signal->cmin_flt;
+		r->ru_majflt = p->signal->cmaj_flt;
+		r->ru_inblock = p->signal->cinblock;
+		r->ru_oublock = p->signal->coublock;
+		maxrss = p->signal->cmaxrss;
+
+		if (who == RUSAGE_CHILDREN)
 			break;
 
-		default:
-			BUG();
+	case RUSAGE_SELF:
+		thread_group_cputime_adjusted(p, &tgutime, &tgstime);
+		utime += tgutime;
+		stime += tgstime;
+		r->ru_nvcsw += p->signal->nvcsw;
+		r->ru_nivcsw += p->signal->nivcsw;
+		r->ru_minflt += p->signal->min_flt;
+		r->ru_majflt += p->signal->maj_flt;
+		r->ru_inblock += p->signal->inblock;
+		r->ru_oublock += p->signal->oublock;
+		if (maxrss < p->signal->maxrss)
+			maxrss = p->signal->maxrss;
+		t = p;
+		do {
+			accumulate_thread_rusage(t, r);
+		} while_each_thread(p, t);
+		break;
+
+	default:
+		BUG();
 	}
 	unlock_task_sighand(p, &flags);
 
@@ -1585,6 +1589,7 @@ out:
 
 	if (who != RUSAGE_CHILDREN) {
 		struct mm_struct *mm = get_task_mm(p);
+
 		if (mm) {
 			setmax_mm_hiwater_rss(&maxrss, mm);
 			mmput(mm);
@@ -1596,6 +1601,7 @@ out:
 int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
 {
 	struct rusage r;
+
 	k_getrusage(p, who, &r);
 	return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
 }
@@ -1628,12 +1634,14 @@ SYSCALL_DEFINE1(umask, int, mask)
 	return mask;
 }
 
-static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
+static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd)
 {
 	struct fd exe;
 	struct inode *inode;
 	int err;
 
+	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
+
 	exe = fdget(fd);
 	if (!exe.file)
 		return -EBADF;
@@ -1654,8 +1662,6 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	if (err)
 		goto exit;
 
-	down_write(&mm->mmap_sem);
-
 	/*
 	 * Forbid mm->exe_file change if old file still mapped.
 	 */
@@ -1667,7 +1673,7 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 			if (vma->vm_file &&
 			    path_equal(&vma->vm_file->f_path,
 				       &mm->exe_file->f_path))
-				goto exit_unlock;
+				goto exit;
 	}
 
 	/*
@@ -1678,34 +1684,222 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	 */
 	err = -EPERM;
 	if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags))
-		goto exit_unlock;
+		goto exit;
 
 	err = 0;
 	set_mm_exe_file(mm, exe.file);	/* this grabs a reference to exe.file */
-exit_unlock:
-	up_write(&mm->mmap_sem);
-
 exit:
 	fdput(exe);
 	return err;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+/*
+ * WARNING: we don't require any capability here so be very careful
+ * in what is allowed for modification from userspace.
+ */
+static int validate_prctl_map(struct prctl_mm_map *prctl_map)
+{
+	unsigned long mmap_max_addr = TASK_SIZE;
+	struct mm_struct *mm = current->mm;
+	int error = -EINVAL, i;
+
+	static const unsigned char offsets[] = {
+		offsetof(struct prctl_mm_map, start_code),
+		offsetof(struct prctl_mm_map, end_code),
+		offsetof(struct prctl_mm_map, start_data),
+		offsetof(struct prctl_mm_map, end_data),
+		offsetof(struct prctl_mm_map, start_brk),
+		offsetof(struct prctl_mm_map, brk),
+		offsetof(struct prctl_mm_map, start_stack),
+		offsetof(struct prctl_mm_map, arg_start),
+		offsetof(struct prctl_mm_map, arg_end),
+		offsetof(struct prctl_mm_map, env_start),
+		offsetof(struct prctl_mm_map, env_end),
+	};
+
+	/*
+	 * Make sure the members are not somewhere outside
+	 * of allowed address space.
+	 */
+	for (i = 0; i < ARRAY_SIZE(offsets); i++) {
+		u64 val = *(u64 *)((char *)prctl_map + offsets[i]);
+
+		if ((unsigned long)val >= mmap_max_addr ||
+		    (unsigned long)val < mmap_min_addr)
+			goto out;
+	}
+
+	/*
+	 * Make sure the pairs are ordered.
+	 */
+#define __prctl_check_order(__m1, __op, __m2)				\
+	((unsigned long)prctl_map->__m1 __op				\
+	 (unsigned long)prctl_map->__m2) ? 0 : -EINVAL
+	error  = __prctl_check_order(start_code, <, end_code);
+	error |= __prctl_check_order(start_data, <, end_data);
+	error |= __prctl_check_order(start_brk, <=, brk);
+	error |= __prctl_check_order(arg_start, <=, arg_end);
+	error |= __prctl_check_order(env_start, <=, env_end);
+	if (error)
+		goto out;
+#undef __prctl_check_order
+
+	error = -EINVAL;
+
+	/*
+	 * @brk should be after @end_data in traditional maps.
+	 */
+	if (prctl_map->start_brk <= prctl_map->end_data ||
+	    prctl_map->brk <= prctl_map->end_data)
+		goto out;
+
+	/*
+	 * Neither we should allow to override limits if they set.
+	 */
+	if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk,
+			      prctl_map->start_brk, prctl_map->end_data,
+			      prctl_map->start_data))
+			goto out;
+
+	/*
+	 * Someone is trying to cheat the auxv vector.
+	 */
+	if (prctl_map->auxv_size) {
+		if (!prctl_map->auxv || prctl_map->auxv_size > sizeof(mm->saved_auxv))
+			goto out;
+	}
+
+	/*
+	 * Finally, make sure the caller has the rights to
+	 * change /proc/pid/exe link: only local root should
+	 * be allowed to.
+	 */
+	if (prctl_map->exe_fd != (u32)-1) {
+		struct user_namespace *ns = current_user_ns();
+		const struct cred *cred = current_cred();
+
+		if (!uid_eq(cred->uid, make_kuid(ns, 0)) ||
+		    !gid_eq(cred->gid, make_kgid(ns, 0)))
+			goto out;
+	}
+
+	error = 0;
+out:
+	return error;
+}
+
+static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size)
+{
+	struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, };
+	unsigned long user_auxv[AT_VECTOR_SIZE];
+	struct mm_struct *mm = current->mm;
+	int error;
+
+	BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv));
+	BUILD_BUG_ON(sizeof(struct prctl_mm_map) > 256);
+
+	if (opt == PR_SET_MM_MAP_SIZE)
+		return put_user((unsigned int)sizeof(prctl_map),
+				(unsigned int __user *)addr);
+
+	if (data_size != sizeof(prctl_map))
+		return -EINVAL;
+
+	if (copy_from_user(&prctl_map, addr, sizeof(prctl_map)))
+		return -EFAULT;
+
+	error = validate_prctl_map(&prctl_map);
+	if (error)
+		return error;
+
+	if (prctl_map.auxv_size) {
+		memset(user_auxv, 0, sizeof(user_auxv));
+		if (copy_from_user(user_auxv,
+				   (const void __user *)prctl_map.auxv,
+				   prctl_map.auxv_size))
+			return -EFAULT;
+
+		/* Last entry must be AT_NULL as specification requires */
+		user_auxv[AT_VECTOR_SIZE - 2] = AT_NULL;
+		user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL;
+	}
+
+	down_write(&mm->mmap_sem);
+	if (prctl_map.exe_fd != (u32)-1)
+		error = prctl_set_mm_exe_file_locked(mm, prctl_map.exe_fd);
+	downgrade_write(&mm->mmap_sem);
+	if (error)
+		goto out;
+
+	/*
+	 * We don't validate if these members are pointing to
+	 * real present VMAs because application may have correspond
+	 * VMAs already unmapped and kernel uses these members for statistics
+	 * output in procfs mostly, except
+	 *
+	 *  - @start_brk/@brk which are used in do_brk but kernel lookups
+	 *    for VMAs when updating these memvers so anything wrong written
+	 *    here cause kernel to swear at userspace program but won't lead
+	 *    to any problem in kernel itself
+	 */
+
+	mm->start_code	= prctl_map.start_code;
+	mm->end_code	= prctl_map.end_code;
+	mm->start_data	= prctl_map.start_data;
+	mm->end_data	= prctl_map.end_data;
+	mm->start_brk	= prctl_map.start_brk;
+	mm->brk		= prctl_map.brk;
+	mm->start_stack	= prctl_map.start_stack;
+	mm->arg_start	= prctl_map.arg_start;
+	mm->arg_end	= prctl_map.arg_end;
+	mm->env_start	= prctl_map.env_start;
+	mm->env_end	= prctl_map.env_end;
+
+	/*
+	 * Note this update of @saved_auxv is lockless thus
+	 * if someone reads this member in procfs while we're
+	 * updating -- it may get partly updated results. It's
+	 * known and acceptable trade off: we leave it as is to
+	 * not introduce additional locks here making the kernel
+	 * more complex.
+	 */
+	if (prctl_map.auxv_size)
+		memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv));
+
+	error = 0;
+out:
+	up_read(&mm->mmap_sem);
+	return error;
+}
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+
 static int prctl_set_mm(int opt, unsigned long addr,
 			unsigned long arg4, unsigned long arg5)
 {
-	unsigned long rlim = rlimit(RLIMIT_DATA);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	int error;
 
-	if (arg5 || (arg4 && opt != PR_SET_MM_AUXV))
+	if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV &&
+			      opt != PR_SET_MM_MAP &&
+			      opt != PR_SET_MM_MAP_SIZE)))
 		return -EINVAL;
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	if (opt == PR_SET_MM_MAP || opt == PR_SET_MM_MAP_SIZE)
+		return prctl_set_mm_map(opt, (const void __user *)addr, arg4);
+#endif
+
 	if (!capable(CAP_SYS_RESOURCE))
 		return -EPERM;
 
-	if (opt == PR_SET_MM_EXE_FILE)
-		return prctl_set_mm_exe_file(mm, (unsigned int)addr);
+	if (opt == PR_SET_MM_EXE_FILE) {
+		down_write(&mm->mmap_sem);
+		error = prctl_set_mm_exe_file_locked(mm, (unsigned int)addr);
+		up_write(&mm->mmap_sem);
+		return error;
+	}
 
 	if (addr >= TASK_SIZE || addr < mmap_min_addr)
 		return -EINVAL;
@@ -1733,9 +1927,8 @@ static int prctl_set_mm(int opt, unsigned long addr,
 		if (addr <= mm->end_data)
 			goto out;
 
-		if (rlim < RLIM_INFINITY &&
-		    (mm->brk - addr) +
-		    (mm->end_data - mm->start_data) > rlim)
+		if (check_data_rlimit(rlimit(RLIMIT_DATA), mm->brk, addr,
+				      mm->end_data, mm->start_data))
 			goto out;
 
 		mm->start_brk = addr;
@@ -1745,9 +1938,8 @@ static int prctl_set_mm(int opt, unsigned long addr,
 		if (addr <= mm->end_data)
 			goto out;
 
-		if (rlim < RLIM_INFINITY &&
-		    (addr - mm->start_brk) +
-		    (mm->end_data - mm->start_data) > rlim)
+		if (check_data_rlimit(rlimit(RLIMIT_DATA), addr, mm->start_brk,
+				      mm->end_data, mm->start_data))
 			goto out;
 
 		mm->brk = addr;
@@ -2023,6 +2215,7 @@ SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep,
 {
 	int err = 0;
 	int cpu = raw_smp_processor_id();
+
 	if (cpup)
 		err |= put_user(cpu, cpup);
 	if (nodep)
@@ -2135,7 +2328,7 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
 	/* Check to see if any memory value is too large for 32-bit and scale
 	 *  down if needed
 	 */
-	if ((s.totalram >> 32) || (s.totalswap >> 32)) {
+	if (upper_32_bits(s.totalram) || upper_32_bits(s.totalswap)) {
 		int bitcount = 0;
 
 		while (s.mem_unit < PAGE_SIZE) {
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 75875a741b5e..4aada6d9fe74 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1055,15 +1055,6 @@ static struct ctl_table kern_table[] = {
 		.child		= key_sysctls,
 	},
 #endif
-#ifdef CONFIG_RCU_TORTURE_TEST
-	{
-		.procname       = "rcutorture_runnable",
-		.data           = &rcutorture_runnable,
-		.maxlen         = sizeof(int),
-		.mode           = 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
 #ifdef CONFIG_PERF_EVENTS
 	/*
 	 * User-space scripts rely on the existence of this file
@@ -1460,13 +1451,6 @@ static struct ctl_table vm_table[] = {
 		.extra2		= &one,
 	},
 #endif
-	{
-		.procname	= "scan_unevictable_pages",
-		.data		= &scan_unevictable_pages,
-		.maxlen		= sizeof(scan_unevictable_pages),
-		.mode		= 0644,
-		.proc_handler	= scan_unevictable_handler,
-	},
 #ifdef CONFIG_MEMORY_FAILURE
 	{
 		.procname	= "memory_failure_early_kill",
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 13d2f7cd65db..b312fcc73024 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -638,7 +638,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
 		fill_tgid_exit(tsk);
 	}
 
-	listeners = __this_cpu_ptr(&listener_array);
+	listeners = raw_cpu_ptr(&listener_array);
 	if (list_empty(&listeners->list))
 		return;
 
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 1c2fe7de2842..37e50aadd471 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -558,7 +558,7 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 static int hrtimer_reprogram(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base)
 {
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
 	int res;
 
@@ -629,7 +629,7 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
  */
 static void retrigger_next_event(void *arg)
 {
-	struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
 	if (!hrtimer_hres_active())
 		return;
@@ -903,7 +903,7 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 		 */
 		debug_deactivate(timer);
 		timer_stats_hrtimer_clear_start_info(timer);
-		reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
+		reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
 		/*
 		 * We must preserve the CALLBACK state flag here,
 		 * otherwise we could move the timer base in
@@ -963,7 +963,7 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 		 * on dynticks target.
 		 */
 		wake_up_nohz_cpu(new_base->cpu_base->cpu);
-	} else if (new_base->cpu_base == &__get_cpu_var(hrtimer_bases) &&
+	} else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases) &&
 			hrtimer_reprogram(timer, new_base)) {
 		/*
 		 * Only allow reprogramming if the new base is on this CPU.
@@ -1103,7 +1103,7 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
  */
 ktime_t hrtimer_get_next_event(void)
 {
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	struct hrtimer_clock_base *base = cpu_base->clock_base;
 	ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
 	unsigned long flags;
@@ -1144,7 +1144,7 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 
 	memset(timer, 0, sizeof(struct hrtimer));
 
-	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
+	cpu_base = raw_cpu_ptr(&hrtimer_bases);
 
 	if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
 		clock_id = CLOCK_MONOTONIC;
@@ -1187,7 +1187,7 @@ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 	struct hrtimer_cpu_base *cpu_base;
 	int base = hrtimer_clockid_to_base(which_clock);
 
-	cpu_base = &__raw_get_cpu_var(hrtimer_bases);
+	cpu_base = raw_cpu_ptr(&hrtimer_bases);
 	*tp = ktime_to_timespec(cpu_base->clock_base[base].resolution);
 
 	return 0;
@@ -1242,7 +1242,7 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
  */
 void hrtimer_interrupt(struct clock_event_device *dev)
 {
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	ktime_t expires_next, now, entry_time, delta;
 	int i, retries = 0;
 
@@ -1376,7 +1376,7 @@ static void __hrtimer_peek_ahead_timers(void)
 	if (!hrtimer_hres_active())
 		return;
 
-	td = &__get_cpu_var(tick_cpu_device);
+	td = this_cpu_ptr(&tick_cpu_device);
 	if (td && td->evtdev)
 		hrtimer_interrupt(td->evtdev);
 }
@@ -1440,7 +1440,7 @@ void hrtimer_run_pending(void)
 void hrtimer_run_queues(void)
 {
 	struct timerqueue_node *node;
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
 	struct hrtimer_clock_base *base;
 	int index, gettime = 1;
 
@@ -1679,7 +1679,7 @@ static void migrate_hrtimers(int scpu)
 
 	local_irq_disable();
 	old_base = &per_cpu(hrtimer_bases, scpu);
-	new_base = &__get_cpu_var(hrtimer_bases);
+	new_base = this_cpu_ptr(&hrtimer_bases);
 	/*
 	 * The caller is globally serialized and nobody else
 	 * takes two locks at once, deadlock is not possible.
@@ -1776,7 +1776,6 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
 	 */
 	if (!expires) {
 		schedule();
-		__set_current_state(TASK_RUNNING);
 		return -EINTR;
 	}
 
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 3b8946416a5f..492b986195d5 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -272,22 +272,8 @@ static int posix_cpu_clock_get_task(struct task_struct *tsk,
 		if (same_thread_group(tsk, current))
 			err = cpu_clock_sample(which_clock, tsk, &rtn);
 	} else {
-		unsigned long flags;
-		struct sighand_struct *sighand;
-
-		/*
-		 * while_each_thread() is not yet entirely RCU safe,
-		 * keep locking the group while sampling process
-		 * clock for now.
-		 */
-		sighand = lock_task_sighand(tsk, &flags);
-		if (!sighand)
-			return err;
-
 		if (tsk == current || thread_group_leader(tsk))
 			err = cpu_clock_sample_group(which_clock, tsk, &rtn);
-
-		unlock_task_sighand(tsk, &flags);
 	}
 
 	if (!err)
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 64c5990fd500..066f0ec05e48 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -554,7 +554,7 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 void tick_check_oneshot_broadcast_this_cpu(void)
 {
 	if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) {
-		struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+		struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 
 		/*
 		 * We might be in the middle of switching over from
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 0a0608edeb26..7efeedf53ebd 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -224,7 +224,7 @@ static void tick_setup_device(struct tick_device *td,
 
 void tick_install_replacement(struct clock_event_device *newdev)
 {
-	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	int cpu = smp_processor_id();
 
 	clockevents_exchange_device(td->evtdev, newdev);
@@ -374,14 +374,14 @@ void tick_shutdown(unsigned int *cpup)
 
 void tick_suspend(void)
 {
-	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 
 	clockevents_shutdown(td->evtdev);
 }
 
 void tick_resume(void)
 {
-	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	int broadcast = tick_resume_broadcast();
 
 	clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME);
@@ -400,4 +400,5 @@ void tick_resume(void)
 void __init tick_init(void)
 {
 	tick_broadcast_init();
+	tick_nohz_init();
 }
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index c19c1d84b6f3..366aeb4f2c66 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -99,6 +99,13 @@ static inline int tick_broadcast_oneshot_active(void) { return 0; }
 static inline bool tick_broadcast_oneshot_available(void) { return false; }
 #endif /* !TICK_ONESHOT */
 
+/* NO_HZ_FULL internal */
+#ifdef CONFIG_NO_HZ_FULL
+extern void tick_nohz_init(void);
+# else
+static inline void tick_nohz_init(void) { }
+#endif
+
 /*
  * Broadcasting support
  */
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 824109060a33..7ce740e78e1b 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -59,7 +59,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev,
  */
 int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
 {
-	struct tick_device *td = &__get_cpu_var(tick_cpu_device);
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
 	struct clock_event_device *dev = td->evtdev;
 
 	if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) ||
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f654a8a298fa..7b5741fc4110 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -205,7 +205,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now);
  */
 void __tick_nohz_full_check(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	if (tick_nohz_full_cpu(smp_processor_id())) {
 		if (ts->tick_stopped && !is_idle_task(current)) {
@@ -295,22 +295,12 @@ out:
 /* Parse the boot-time nohz CPU list from the kernel parameters. */
 static int __init tick_nohz_full_setup(char *str)
 {
-	int cpu;
-
 	alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
-	alloc_bootmem_cpumask_var(&housekeeping_mask);
 	if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
 		pr_warning("NOHZ: Incorrect nohz_full cpumask\n");
+		free_bootmem_cpumask_var(tick_nohz_full_mask);
 		return 1;
 	}
-
-	cpu = smp_processor_id();
-	if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
-		pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
-		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
-	}
-	cpumask_andnot(housekeeping_mask,
-		       cpu_possible_mask, tick_nohz_full_mask);
 	tick_nohz_full_running = true;
 
 	return 1;
@@ -349,18 +339,11 @@ static int tick_nohz_init_all(void)
 
 #ifdef CONFIG_NO_HZ_FULL_ALL
 	if (!alloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL)) {
-		pr_err("NO_HZ: Can't allocate full dynticks cpumask\n");
-		return err;
-	}
-	if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) {
-		pr_err("NO_HZ: Can't allocate not-full dynticks cpumask\n");
+		WARN(1, "NO_HZ: Can't allocate full dynticks cpumask\n");
 		return err;
 	}
 	err = 0;
 	cpumask_setall(tick_nohz_full_mask);
-	cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask);
-	cpumask_clear(housekeeping_mask);
-	cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
 	tick_nohz_full_running = true;
 #endif
 	return err;
@@ -375,6 +358,37 @@ void __init tick_nohz_init(void)
 			return;
 	}
 
+	if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) {
+		WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n");
+		cpumask_clear(tick_nohz_full_mask);
+		tick_nohz_full_running = false;
+		return;
+	}
+
+	/*
+	 * Full dynticks uses irq work to drive the tick rescheduling on safe
+	 * locking contexts. But then we need irq work to raise its own
+	 * interrupts to avoid circular dependency on the tick
+	 */
+	if (!arch_irq_work_has_interrupt()) {
+		pr_warning("NO_HZ: Can't run full dynticks because arch doesn't "
+			   "support irq work self-IPIs\n");
+		cpumask_clear(tick_nohz_full_mask);
+		cpumask_copy(housekeeping_mask, cpu_possible_mask);
+		tick_nohz_full_running = false;
+		return;
+	}
+
+	cpu = smp_processor_id();
+
+	if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
+		pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
+		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+	}
+
+	cpumask_andnot(housekeeping_mask,
+		       cpu_possible_mask, tick_nohz_full_mask);
+
 	for_each_cpu(cpu, tick_nohz_full_mask)
 		context_tracking_cpu_set(cpu);
 
@@ -559,7 +573,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
 	ktime_t last_update, expires, ret = { .tv64 = 0 };
 	unsigned long rcu_delta_jiffies;
-	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 	u64 time_delta;
 
 	time_delta = timekeeping_max_deferment();
@@ -572,7 +586,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	} while (read_seqretry(&jiffies_lock, seq));
 
 	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) ||
-	    arch_needs_cpu(cpu) || irq_work_needs_cpu()) {
+	    arch_needs_cpu() || irq_work_needs_cpu()) {
 		next_jiffies = last_jiffies + 1;
 		delta_jiffies = 1;
 	} else {
@@ -827,7 +841,7 @@ void tick_nohz_idle_enter(void)
 
 	local_irq_disable();
 
-	ts = &__get_cpu_var(tick_cpu_sched);
+	ts = this_cpu_ptr(&tick_cpu_sched);
 	ts->inidle = 1;
 	__tick_nohz_idle_enter(ts);
 
@@ -845,7 +859,7 @@ EXPORT_SYMBOL_GPL(tick_nohz_idle_enter);
  */
 void tick_nohz_irq_exit(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	if (ts->inidle)
 		__tick_nohz_idle_enter(ts);
@@ -860,7 +874,7 @@ void tick_nohz_irq_exit(void)
  */
 ktime_t tick_nohz_get_sleep_length(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	return ts->sleep_length;
 }
@@ -938,7 +952,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
  */
 void tick_nohz_idle_exit(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	ktime_t now;
 
 	local_irq_disable();
@@ -973,7 +987,7 @@ static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now)
  */
 static void tick_nohz_handler(struct clock_event_device *dev)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	struct pt_regs *regs = get_irq_regs();
 	ktime_t now = ktime_get();
 
@@ -982,6 +996,10 @@ static void tick_nohz_handler(struct clock_event_device *dev)
 	tick_sched_do_timer(now);
 	tick_sched_handle(ts, regs);
 
+	/* No need to reprogram if we are running tickless  */
+	if (unlikely(ts->tick_stopped))
+		return;
+
 	while (tick_nohz_reprogram(ts, now)) {
 		now = ktime_get();
 		tick_do_update_jiffies64(now);
@@ -993,7 +1011,7 @@ static void tick_nohz_handler(struct clock_event_device *dev)
  */
 static void tick_nohz_switch_to_nohz(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	ktime_t next;
 
 	if (!tick_nohz_enabled)
@@ -1055,7 +1073,7 @@ static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now)
 
 static inline void tick_nohz_irq_enter(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	ktime_t now;
 
 	if (!ts->idle_active && !ts->tick_stopped)
@@ -1109,6 +1127,10 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
 	if (regs)
 		tick_sched_handle(ts, regs);
 
+	/* No need to reprogram if we are in idle or full dynticks mode */
+	if (unlikely(ts->tick_stopped))
+		return HRTIMER_NORESTART;
+
 	hrtimer_forward(timer, now, tick_period);
 
 	return HRTIMER_RESTART;
@@ -1129,7 +1151,7 @@ early_param("skew_tick", skew_tick);
  */
 void tick_setup_sched_timer(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 	ktime_t now = ktime_get();
 
 	/*
@@ -1198,7 +1220,7 @@ void tick_clock_notify(void)
  */
 void tick_oneshot_notify(void)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	set_bit(0, &ts->check_clocks);
 }
@@ -1213,7 +1235,7 @@ void tick_oneshot_notify(void)
  */
 int tick_check_oneshot_change(int allow_nohz)
 {
-	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	if (!test_and_clear_bit(0, &ts->check_clocks))
 		return 0;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index aca5dfe2fa3d..3260ffdb368f 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -655,7 +655,7 @@ static inline void debug_assert_init(struct timer_list *timer)
 static void do_init_timer(struct timer_list *timer, unsigned int flags,
 			  const char *name, struct lock_class_key *key)
 {
-	struct tvec_base *base = __raw_get_cpu_var(tvec_bases);
+	struct tvec_base *base = raw_cpu_read(tvec_bases);
 
 	timer->entry.next = NULL;
 	timer->base = (void *)((unsigned long)base | flags);
@@ -1385,7 +1385,7 @@ void update_process_times(int user_tick)
 	rcu_check_callbacks(cpu, user_tick);
 #ifdef CONFIG_IRQ_WORK
 	if (in_irq())
-		irq_work_run();
+		irq_work_tick();
 #endif
 	scheduler_tick();
 	run_posix_cpu_timers(p);
diff --git a/kernel/torture.c b/kernel/torture.c
index d600af21f022..dd70993c266c 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -211,18 +211,16 @@ EXPORT_SYMBOL_GPL(torture_onoff_cleanup);
 /*
  * Print online/offline testing statistics.
  */
-char *torture_onoff_stats(char *page)
+void torture_onoff_stats(void)
 {
 #ifdef CONFIG_HOTPLUG_CPU
-	page += sprintf(page,
-		       "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
-		       n_online_successes, n_online_attempts,
-		       n_offline_successes, n_offline_attempts,
-		       min_online, max_online,
-		       min_offline, max_offline,
-		       sum_online, sum_offline, HZ);
+	pr_cont("onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
+		n_online_successes, n_online_attempts,
+		n_offline_successes, n_offline_attempts,
+		min_online, max_online,
+		min_offline, max_offline,
+		sum_online, sum_offline, HZ);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
-	return page;
 }
 EXPORT_SYMBOL_GPL(torture_onoff_stats);
 
@@ -635,8 +633,13 @@ EXPORT_SYMBOL_GPL(torture_init_end);
  *
  * This must be called before the caller starts shutting down its own
  * kthreads.
+ *
+ * Both torture_cleanup_begin() and torture_cleanup_end() must be paired,
+ * in order to correctly perform the cleanup. They are separated because
+ * threads can still need to reference the torture_type type, thus nullify
+ * only after completing all other relevant calls.
  */
-bool torture_cleanup(void)
+bool torture_cleanup_begin(void)
 {
 	mutex_lock(&fullstop_mutex);
 	if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
@@ -651,12 +654,17 @@ bool torture_cleanup(void)
 	torture_shuffle_cleanup();
 	torture_stutter_cleanup();
 	torture_onoff_cleanup();
+	return false;
+}
+EXPORT_SYMBOL_GPL(torture_cleanup_begin);
+
+void torture_cleanup_end(void)
+{
 	mutex_lock(&fullstop_mutex);
 	torture_type = NULL;
 	mutex_unlock(&fullstop_mutex);
-	return false;
 }
-EXPORT_SYMBOL_GPL(torture_cleanup);
+EXPORT_SYMBOL_GPL(torture_cleanup_end);
 
 /*
  * Is it time for the current torture test to stop?
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 5916a8e59e87..fb186b9ddf51 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -113,6 +113,9 @@ ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
 static struct ftrace_ops control_ops;
 
+static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip,
+				   struct ftrace_ops *op, struct pt_regs *regs);
+
 #if ARCH_SUPPORTS_FTRACE_OPS
 static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 				 struct ftrace_ops *op, struct pt_regs *regs);
@@ -251,18 +254,24 @@ static void update_ftrace_function(void)
 	ftrace_func_t func;
 
 	/*
+	 * Prepare the ftrace_ops that the arch callback will use.
+	 * If there's only one ftrace_ops registered, the ftrace_ops_list
+	 * will point to the ops we want.
+	 */
+	set_function_trace_op = ftrace_ops_list;
+
+	/* If there's no ftrace_ops registered, just call the stub function */
+	if (ftrace_ops_list == &ftrace_list_end) {
+		func = ftrace_stub;
+
+	/*
 	 * If we are at the end of the list and this ops is
 	 * recursion safe and not dynamic and the arch supports passing ops,
 	 * then have the mcount trampoline call the function directly.
 	 */
-	if (ftrace_ops_list == &ftrace_list_end ||
-	    (ftrace_ops_list->next == &ftrace_list_end &&
-	     !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) &&
-	     (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) &&
-	     !FTRACE_FORCE_LIST_FUNC)) {
-		/* Set the ftrace_ops that the arch callback uses */
-		set_function_trace_op = ftrace_ops_list;
-		func = ftrace_ops_list->func;
+	} else if (ftrace_ops_list->next == &ftrace_list_end) {
+		func = ftrace_ops_get_func(ftrace_ops_list);
+
 	} else {
 		/* Just use the default ftrace_ops */
 		set_function_trace_op = &ftrace_list_end;
@@ -1048,6 +1057,12 @@ static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
 static struct ftrace_ops *removed_ops;
 
+/*
+ * Set when doing a global update, like enabling all recs or disabling them.
+ * It is not set when just updating a single ftrace_ops.
+ */
+static bool update_all_ops;
+
 #ifndef CONFIG_FTRACE_MCOUNT_RECORD
 # error Dynamic ftrace depends on MCOUNT_RECORD
 #endif
@@ -1307,7 +1322,6 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	struct ftrace_func_entry *entry;
 	struct hlist_node *tn;
 	struct hlist_head *hhd;
-	struct ftrace_hash *old_hash;
 	struct ftrace_hash *new_hash;
 	int size = src->count;
 	int bits = 0;
@@ -1352,15 +1366,28 @@ update:
 	 */
 	ftrace_hash_rec_disable_modify(ops, enable);
 
-	old_hash = *dst;
 	rcu_assign_pointer(*dst, new_hash);
-	free_ftrace_hash_rcu(old_hash);
 
 	ftrace_hash_rec_enable_modify(ops, enable);
 
 	return 0;
 }
 
+static bool hash_contains_ip(unsigned long ip,
+			     struct ftrace_ops_hash *hash)
+{
+	/*
+	 * The function record is a match if it exists in the filter
+	 * hash and not in the notrace hash. Note, an emty hash is
+	 * considered a match for the filter hash, but an empty
+	 * notrace hash is considered not in the notrace hash.
+	 */
+	return (ftrace_hash_empty(hash->filter_hash) ||
+		ftrace_lookup_ip(hash->filter_hash, ip)) &&
+		(ftrace_hash_empty(hash->notrace_hash) ||
+		 !ftrace_lookup_ip(hash->notrace_hash, ip));
+}
+
 /*
  * Test the hashes for this ops to see if we want to call
  * the ops->func or not.
@@ -1376,8 +1403,7 @@ update:
 static int
 ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 {
-	struct ftrace_hash *filter_hash;
-	struct ftrace_hash *notrace_hash;
+	struct ftrace_ops_hash hash;
 	int ret;
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
@@ -1390,13 +1416,10 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 		return 0;
 #endif
 
-	filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash);
-	notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash);
+	hash.filter_hash = rcu_dereference_raw_notrace(ops->func_hash->filter_hash);
+	hash.notrace_hash = rcu_dereference_raw_notrace(ops->func_hash->notrace_hash);
 
-	if ((ftrace_hash_empty(filter_hash) ||
-	     ftrace_lookup_ip(filter_hash, ip)) &&
-	    (ftrace_hash_empty(notrace_hash) ||
-	     !ftrace_lookup_ip(notrace_hash, ip)))
+	if (hash_contains_ip(ip, &hash))
 		ret = 1;
 	else
 		ret = 0;
@@ -1508,46 +1531,6 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec)
 	return  keep_regs;
 }
 
-static void ftrace_remove_tramp(struct ftrace_ops *ops,
-				struct dyn_ftrace *rec)
-{
-	/* If TRAMP is not set, no ops should have a trampoline for this */
-	if (!(rec->flags & FTRACE_FL_TRAMP))
-		return;
-
-	rec->flags &= ~FTRACE_FL_TRAMP;
-
-	if ((!ftrace_hash_empty(ops->func_hash->filter_hash) &&
-	     !ftrace_lookup_ip(ops->func_hash->filter_hash, rec->ip)) ||
-	    ftrace_lookup_ip(ops->func_hash->notrace_hash, rec->ip))
-		return;
-	/*
-	 * The tramp_hash entry will be removed at time
-	 * of update.
-	 */
-	ops->nr_trampolines--;
-}
-
-static void ftrace_clear_tramps(struct dyn_ftrace *rec, struct ftrace_ops *ops)
-{
-	struct ftrace_ops *op;
-
-	/* If TRAMP is not set, no ops should have a trampoline for this */
-	if (!(rec->flags & FTRACE_FL_TRAMP))
-		return;
-
-	do_for_each_ftrace_op(op, ftrace_ops_list) {
-		/*
-		 * This function is called to clear other tramps
-		 * not the one that is being updated.
-		 */
-		if (op == ops)
-			continue;
-		if (op->nr_trampolines)
-			ftrace_remove_tramp(op, rec);
-	} while_for_each_ftrace_op(op);
-}
-
 static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				     int filter_hash,
 				     bool inc)
@@ -1636,18 +1619,16 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			 * function, and the ops has a trampoline registered
 			 * for it, then we can call it directly.
 			 */
-			if (ftrace_rec_count(rec) == 1 && ops->trampoline) {
+			if (ftrace_rec_count(rec) == 1 && ops->trampoline)
 				rec->flags |= FTRACE_FL_TRAMP;
-				ops->nr_trampolines++;
-			} else {
+			else
 				/*
 				 * If we are adding another function callback
 				 * to this function, and the previous had a
 				 * custom trampoline in use, then we need to go
 				 * back to the default trampoline.
 				 */
-				ftrace_clear_tramps(rec, ops);
-			}
+				rec->flags &= ~FTRACE_FL_TRAMP;
 
 			/*
 			 * If any ops wants regs saved for this function
@@ -1660,9 +1641,6 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				return;
 			rec->flags--;
 
-			if (ops->trampoline && !ftrace_rec_count(rec))
-				ftrace_remove_tramp(ops, rec);
-
 			/*
 			 * If the rec had REGS enabled and the ops that is
 			 * being removed had REGS set, then see if there is
@@ -1677,6 +1655,17 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			}
 
 			/*
+			 * If the rec had TRAMP enabled, then it needs to
+			 * be cleared. As TRAMP can only be enabled iff
+			 * there is only a single ops attached to it.
+			 * In otherwords, always disable it on decrementing.
+			 * In the future, we may set it if rec count is
+			 * decremented to one, and the ops that is left
+			 * has a trampoline.
+			 */
+			rec->flags &= ~FTRACE_FL_TRAMP;
+
+			/*
 			 * flags will be cleared in ftrace_check_record()
 			 * if rec count is zero.
 			 */
@@ -1895,21 +1884,72 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable)
 }
 
 static struct ftrace_ops *
+ftrace_find_tramp_ops_any(struct dyn_ftrace *rec)
+{
+	struct ftrace_ops *op;
+	unsigned long ip = rec->ip;
+
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+
+		if (!op->trampoline)
+			continue;
+
+		if (hash_contains_ip(ip, op->func_hash))
+			return op;
+	} while_for_each_ftrace_op(op);
+
+	return NULL;
+}
+
+static struct ftrace_ops *
 ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec)
 {
 	struct ftrace_ops *op;
+	unsigned long ip = rec->ip;
 
-	/* Removed ops need to be tested first */
-	if (removed_ops && removed_ops->tramp_hash) {
-		if (ftrace_lookup_ip(removed_ops->tramp_hash, rec->ip))
+	/*
+	 * Need to check removed ops first.
+	 * If they are being removed, and this rec has a tramp,
+	 * and this rec is in the ops list, then it would be the
+	 * one with the tramp.
+	 */
+	if (removed_ops) {
+		if (hash_contains_ip(ip, &removed_ops->old_hash))
 			return removed_ops;
 	}
 
+	/*
+	 * Need to find the current trampoline for a rec.
+	 * Now, a trampoline is only attached to a rec if there
+	 * was a single 'ops' attached to it. But this can be called
+	 * when we are adding another op to the rec or removing the
+	 * current one. Thus, if the op is being added, we can
+	 * ignore it because it hasn't attached itself to the rec
+	 * yet. That means we just need to find the op that has a
+	 * trampoline and is not beeing added.
+	 */
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
-		if (!op->tramp_hash)
+
+		if (!op->trampoline)
 			continue;
 
-		if (ftrace_lookup_ip(op->tramp_hash, rec->ip))
+		/*
+		 * If the ops is being added, it hasn't gotten to
+		 * the point to be removed from this tree yet.
+		 */
+		if (op->flags & FTRACE_OPS_FL_ADDING)
+			continue;
+
+		/*
+		 * If the ops is not being added and has a trampoline,
+		 * then it must be the one that we want!
+		 */
+		if (hash_contains_ip(ip, op->func_hash))
+			return op;
+
+		/* If the ops is being modified, it may be in the old hash. */
+		if ((op->flags & FTRACE_OPS_FL_MODIFYING) &&
+		    hash_contains_ip(ip, &op->old_hash))
 			return op;
 
 	} while_for_each_ftrace_op(op);
@@ -1921,10 +1961,11 @@ static struct ftrace_ops *
 ftrace_find_tramp_ops_new(struct dyn_ftrace *rec)
 {
 	struct ftrace_ops *op;
+	unsigned long ip = rec->ip;
 
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
 		/* pass rec in as regs to have non-NULL val */
-		if (ftrace_ops_test(op, rec->ip, rec))
+		if (hash_contains_ip(ip, op->func_hash))
 			return op;
 	} while_for_each_ftrace_op(op);
 
@@ -2231,92 +2272,6 @@ void __weak arch_ftrace_update_code(int command)
 	ftrace_run_stop_machine(command);
 }
 
-static int ftrace_save_ops_tramp_hash(struct ftrace_ops *ops)
-{
-	struct ftrace_page *pg;
-	struct dyn_ftrace *rec;
-	int size, bits;
-	int ret;
-
-	size = ops->nr_trampolines;
-	bits = 0;
-	/*
-	 * Make the hash size about 1/2 the # found
-	 */
-	for (size /= 2; size; size >>= 1)
-		bits++;
-
-	ops->tramp_hash = alloc_ftrace_hash(bits);
-	/*
-	 * TODO: a failed allocation is going to screw up
-	 * the accounting of what needs to be modified
-	 * and not. For now, we kill ftrace if we fail
-	 * to allocate here. But there are ways around this,
-	 * but that will take a little more work.
-	 */
-	if (!ops->tramp_hash)
-		return -ENOMEM;
-
-	do_for_each_ftrace_rec(pg, rec) {
-		if (ftrace_rec_count(rec) == 1 &&
-		    ftrace_ops_test(ops, rec->ip, rec)) {
-
-			/*
-			 * If another ops adds to a rec, the rec will
-			 * lose its trampoline and never get it back
-			 * until all ops are off of it.
-			 */
-			if (!(rec->flags & FTRACE_FL_TRAMP))
-				continue;
-
-			/* This record had better have a trampoline */
-			if (FTRACE_WARN_ON(!(rec->flags & FTRACE_FL_TRAMP_EN)))
-				return -1;
-
-			ret = add_hash_entry(ops->tramp_hash, rec->ip);
-			if (ret < 0)
-				return ret;
-		}
-	} while_for_each_ftrace_rec();
-
-	/* The number of recs in the hash must match nr_trampolines */
-	if (FTRACE_WARN_ON(ops->tramp_hash->count != ops->nr_trampolines))
-		pr_warn("count=%ld trampolines=%d\n",
-			ops->tramp_hash->count,
-			ops->nr_trampolines);
-
-	return 0;
-}
-
-static int ftrace_save_tramp_hashes(void)
-{
-	struct ftrace_ops *op;
-	int ret;
-
-	/*
-	 * Now that any trampoline is being used, we need to save the
-	 * hashes for the ops that have them. This allows the mapping
-	 * back from the record to the ops that has the trampoline to
-	 * know what code is being replaced. Modifying code must always
-	 * verify what it is changing.
-	 */
-	do_for_each_ftrace_op(op, ftrace_ops_list) {
-
-		/* The tramp_hash is recreated each time. */
-		free_ftrace_hash(op->tramp_hash);
-		op->tramp_hash = NULL;
-
-		if (op->nr_trampolines) {
-			ret = ftrace_save_ops_tramp_hash(op);
-			if (ret)
-				return ret;
-		}
-
-	} while_for_each_ftrace_op(op);
-
-	return 0;
-}
-
 static void ftrace_run_update_code(int command)
 {
 	int ret;
@@ -2336,9 +2291,13 @@ static void ftrace_run_update_code(int command)
 
 	ret = ftrace_arch_code_modify_post_process();
 	FTRACE_WARN_ON(ret);
+}
 
-	ret = ftrace_save_tramp_hashes();
-	FTRACE_WARN_ON(ret);
+static void ftrace_run_modify_code(struct ftrace_ops *ops, int command)
+{
+	ops->flags |= FTRACE_OPS_FL_MODIFYING;
+	ftrace_run_update_code(command);
+	ops->flags &= ~FTRACE_OPS_FL_MODIFYING;
 }
 
 static ftrace_func_t saved_ftrace_func;
@@ -2362,6 +2321,13 @@ static void ftrace_startup_enable(int command)
 	ftrace_run_update_code(command);
 }
 
+static void ftrace_startup_all(int command)
+{
+	update_all_ops = true;
+	ftrace_startup_enable(command);
+	update_all_ops = false;
+}
+
 static int ftrace_startup(struct ftrace_ops *ops, int command)
 {
 	int ret;
@@ -2376,12 +2342,22 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 	ftrace_start_up++;
 	command |= FTRACE_UPDATE_CALLS;
 
-	ops->flags |= FTRACE_OPS_FL_ENABLED;
+	/*
+	 * Note that ftrace probes uses this to start up
+	 * and modify functions it will probe. But we still
+	 * set the ADDING flag for modification, as probes
+	 * do not have trampolines. If they add them in the
+	 * future, then the probes will need to distinguish
+	 * between adding and updating probes.
+	 */
+	ops->flags |= FTRACE_OPS_FL_ENABLED | FTRACE_OPS_FL_ADDING;
 
 	ftrace_hash_rec_enable(ops, 1);
 
 	ftrace_startup_enable(command);
 
+	ops->flags &= ~FTRACE_OPS_FL_ADDING;
+
 	return 0;
 }
 
@@ -2431,11 +2407,35 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	 * If the ops uses a trampoline, then it needs to be
 	 * tested first on update.
 	 */
+	ops->flags |= FTRACE_OPS_FL_REMOVING;
 	removed_ops = ops;
 
+	/* The trampoline logic checks the old hashes */
+	ops->old_hash.filter_hash = ops->func_hash->filter_hash;
+	ops->old_hash.notrace_hash = ops->func_hash->notrace_hash;
+
 	ftrace_run_update_code(command);
 
+	/*
+	 * If there's no more ops registered with ftrace, run a
+	 * sanity check to make sure all rec flags are cleared.
+	 */
+	if (ftrace_ops_list == &ftrace_list_end) {
+		struct ftrace_page *pg;
+		struct dyn_ftrace *rec;
+
+		do_for_each_ftrace_rec(pg, rec) {
+			if (FTRACE_WARN_ON_ONCE(rec->flags))
+				pr_warn("  %pS flags:%lx\n",
+					(void *)rec->ip, rec->flags);
+		} while_for_each_ftrace_rec();
+	}
+
+	ops->old_hash.filter_hash = NULL;
+	ops->old_hash.notrace_hash = NULL;
+
 	removed_ops = NULL;
+	ops->flags &= ~FTRACE_OPS_FL_REMOVING;
 
 	/*
 	 * Dynamic ops may be freed, we must make sure that all
@@ -2960,8 +2960,8 @@ static int t_show(struct seq_file *m, void *v)
 		if (rec->flags & FTRACE_FL_TRAMP_EN) {
 			struct ftrace_ops *ops;
 
-			ops = ftrace_find_tramp_ops_curr(rec);
-			if (ops && ops->trampoline)
+			ops = ftrace_find_tramp_ops_any(rec);
+			if (ops)
 				seq_printf(m, "\ttramp: %pS",
 					   (void *)ops->trampoline);
 			else
@@ -3348,7 +3348,7 @@ static void __enable_ftrace_function_probe(void)
 	if (ftrace_probe_registered) {
 		/* still need to update the function call sites */
 		if (ftrace_enabled)
-			ftrace_run_update_code(FTRACE_UPDATE_CALLS);
+			ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS);
 		return;
 	}
 
@@ -3399,6 +3399,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 {
 	struct ftrace_func_probe *entry;
 	struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
+	struct ftrace_hash *old_hash = *orig_hash;
 	struct ftrace_hash *hash;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
@@ -3417,7 +3418,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	mutex_lock(&trace_probe_ops.func_hash->regex_lock);
 
-	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash);
 	if (!hash) {
 		count = -ENOMEM;
 		goto out;
@@ -3476,7 +3477,9 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	} while_for_each_ftrace_rec();
 
 	ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
-	if (ret < 0)
+	if (!ret)
+		free_ftrace_hash_rcu(old_hash);
+	else
 		count = ret;
 
 	__enable_ftrace_function_probe();
@@ -3503,6 +3506,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	struct ftrace_func_probe *entry;
 	struct ftrace_func_probe *p;
 	struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
+	struct ftrace_hash *old_hash = *orig_hash;
 	struct list_head free_list;
 	struct ftrace_hash *hash;
 	struct hlist_node *tmp;
@@ -3510,6 +3514,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	int type = MATCH_FULL;
 	int i, len = 0;
 	char *search;
+	int ret;
 
 	if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
 		glob = NULL;
@@ -3568,8 +3573,11 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	 * Remove after the disable is called. Otherwise, if the last
 	 * probe is removed, a null hash means *all enabled*.
 	 */
-	ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+	ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
 	synchronize_sched();
+	if (!ret)
+		free_ftrace_hash_rcu(old_hash);
+
 	list_for_each_entry_safe(entry, p, &free_list, free_list) {
 		list_del(&entry->free_list);
 		ftrace_free_entry(entry);
@@ -3759,7 +3767,7 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 static void ftrace_ops_update_code(struct ftrace_ops *ops)
 {
 	if (ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled)
-		ftrace_run_update_code(FTRACE_UPDATE_CALLS);
+		ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS);
 }
 
 static int
@@ -3767,6 +3775,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 		unsigned long ip, int remove, int reset, int enable)
 {
 	struct ftrace_hash **orig_hash;
+	struct ftrace_hash *old_hash;
 	struct ftrace_hash *hash;
 	int ret;
 
@@ -3801,10 +3810,12 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 	}
 
 	mutex_lock(&ftrace_lock);
+	old_hash = *orig_hash;
 	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
-	if (!ret)
+	if (!ret) {
 		ftrace_ops_update_code(ops);
-
+		free_ftrace_hash_rcu(old_hash);
+	}
 	mutex_unlock(&ftrace_lock);
 
  out_regex_unlock:
@@ -4013,6 +4024,7 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 	struct seq_file *m = (struct seq_file *)file->private_data;
 	struct ftrace_iterator *iter;
 	struct ftrace_hash **orig_hash;
+	struct ftrace_hash *old_hash;
 	struct trace_parser *parser;
 	int filter_hash;
 	int ret;
@@ -4042,11 +4054,13 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 			orig_hash = &iter->ops->func_hash->notrace_hash;
 
 		mutex_lock(&ftrace_lock);
+		old_hash = *orig_hash;
 		ret = ftrace_hash_move(iter->ops, filter_hash,
 				       orig_hash, iter->hash);
-		if (!ret)
+		if (!ret) {
 			ftrace_ops_update_code(iter->ops);
-
+			free_ftrace_hash_rcu(old_hash);
+		}
 		mutex_unlock(&ftrace_lock);
 	}
 
@@ -4678,6 +4692,7 @@ core_initcall(ftrace_nodyn_init);
 
 static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
 static inline void ftrace_startup_enable(int command) { }
+static inline void ftrace_startup_all(int command) { }
 /* Keep as macros so we do not need to define the commands */
 # define ftrace_startup(ops, command)					\
 	({								\
@@ -4827,6 +4842,56 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
 }
 #endif
 
+/*
+ * If there's only one function registered but it does not support
+ * recursion, this function will be called by the mcount trampoline.
+ * This function will handle recursion protection.
+ */
+static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip,
+				   struct ftrace_ops *op, struct pt_regs *regs)
+{
+	int bit;
+
+	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
+	if (bit < 0)
+		return;
+
+	op->func(ip, parent_ip, op, regs);
+
+	trace_clear_recursion(bit);
+}
+
+/**
+ * ftrace_ops_get_func - get the function a trampoline should call
+ * @ops: the ops to get the function for
+ *
+ * Normally the mcount trampoline will call the ops->func, but there
+ * are times that it should not. For example, if the ops does not
+ * have its own recursion protection, then it should call the
+ * ftrace_ops_recurs_func() instead.
+ *
+ * Returns the function that the trampoline should call for @ops.
+ */
+ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
+{
+	/*
+	 * If this is a dynamic ops or we force list func,
+	 * then it needs to call the list anyway.
+	 */
+	if (ops->flags & FTRACE_OPS_FL_DYNAMIC || FTRACE_FORCE_LIST_FUNC)
+		return ftrace_ops_list_func;
+
+	/*
+	 * If the func handles its own recursion, call it directly.
+	 * Otherwise call the recursion protected function that
+	 * will call the ftrace ops function.
+	 */
+	if (!(ops->flags & FTRACE_OPS_FL_RECURSION_SAFE))
+		return ftrace_ops_recurs_func;
+
+	return ops->func;
+}
+
 static void clear_ftrace_swapper(void)
 {
 	struct task_struct *p;
@@ -4927,7 +4992,8 @@ static int ftrace_pid_add(int p)
 	set_ftrace_pid_task(pid);
 
 	ftrace_update_pid_func();
-	ftrace_startup_enable(0);
+
+	ftrace_startup_all(0);
 
 	mutex_unlock(&ftrace_lock);
 	return 0;
@@ -4956,7 +5022,7 @@ static void ftrace_pid_reset(void)
 	}
 
 	ftrace_update_pid_func();
-	ftrace_startup_enable(0);
+	ftrace_startup_all(0);
 
 	mutex_unlock(&ftrace_lock);
 }
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 0434ff1b808e..3f9e328c30b5 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -205,7 +205,6 @@ static void ring_buffer_consumer(void)
 			break;
 
 		schedule();
-		__set_current_state(TASK_RUNNING);
 	}
 	reader_finish = 0;
 	complete(&read_done);
@@ -379,7 +378,6 @@ static int ring_buffer_consumer_thread(void *arg)
 			break;
 
 		schedule();
-		__set_current_state(TASK_RUNNING);
 	}
 	__set_current_state(TASK_RUNNING);
 
@@ -407,7 +405,6 @@ static int ring_buffer_producer_thread(void *arg)
 		trace_printk("Sleeping for 10 secs\n");
 		set_current_state(TASK_INTERRUPTIBLE);
 		schedule_timeout(HZ * SLEEP_TIME);
-		__set_current_state(TASK_RUNNING);
 	}
 
 	if (kill_test)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index ef06ce7e9cf8..0cc51edde3a8 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2513,8 +2513,11 @@ static __init int event_test_thread(void *unused)
 	kfree(test_malloc);
 
 	set_current_state(TASK_INTERRUPTIBLE);
-	while (!kthread_should_stop())
+	while (!kthread_should_stop()) {
 		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__set_current_state(TASK_RUNNING);
 
 	return 0;
 }
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 5ef60499dc8e..b0f86ea77881 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -382,6 +382,8 @@ static int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 
 	/* check the trace buffer */
 	ret = trace_test_buffer(&tr->trace_buffer, &count);
+
+	ftrace_enabled = 1;
 	tracing_start();
 
 	/* we should only have one item */
@@ -679,6 +681,8 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 
 	/* check the trace buffer */
 	ret = trace_test_buffer(&tr->trace_buffer, &count);
+
+	ftrace_enabled = 1;
 	trace->reset(tr);
 	tracing_start();
 
@@ -1025,6 +1029,12 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
 #endif
 
 #ifdef CONFIG_SCHED_TRACER
+
+struct wakeup_test_data {
+	struct completion	is_ready;
+	int			go;
+};
+
 static int trace_wakeup_test_thread(void *data)
 {
 	/* Make this a -deadline thread */
@@ -1034,51 +1044,56 @@ static int trace_wakeup_test_thread(void *data)
 		.sched_deadline = 10000000ULL,
 		.sched_period = 10000000ULL
 	};
-	struct completion *x = data;
+	struct wakeup_test_data *x = data;
 
 	sched_setattr(current, &attr);
 
 	/* Make it know we have a new prio */
-	complete(x);
+	complete(&x->is_ready);
 
 	/* now go to sleep and let the test wake us up */
 	set_current_state(TASK_INTERRUPTIBLE);
-	schedule();
+	while (!x->go) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
 
-	complete(x);
+	complete(&x->is_ready);
+
+	set_current_state(TASK_INTERRUPTIBLE);
 
 	/* we are awake, now wait to disappear */
 	while (!kthread_should_stop()) {
-		/*
-		 * This will likely be the system top priority
-		 * task, do short sleeps to let others run.
-		 */
-		msleep(100);
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
 	}
 
+	__set_current_state(TASK_RUNNING);
+
 	return 0;
 }
-
 int
 trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 {
 	unsigned long save_max = tr->max_latency;
 	struct task_struct *p;
-	struct completion is_ready;
+	struct wakeup_test_data data;
 	unsigned long count;
 	int ret;
 
-	init_completion(&is_ready);
+	memset(&data, 0, sizeof(data));
+
+	init_completion(&data.is_ready);
 
 	/* create a -deadline thread */
-	p = kthread_run(trace_wakeup_test_thread, &is_ready, "ftrace-test");
+	p = kthread_run(trace_wakeup_test_thread, &data, "ftrace-test");
 	if (IS_ERR(p)) {
 		printk(KERN_CONT "Failed to create ftrace wakeup test thread ");
 		return -1;
 	}
 
 	/* make sure the thread is running at -deadline policy */
-	wait_for_completion(&is_ready);
+	wait_for_completion(&data.is_ready);
 
 	/* start the tracing */
 	ret = tracer_init(trace, tr);
@@ -1099,18 +1114,20 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 		msleep(100);
 	}
 
-	init_completion(&is_ready);
+	init_completion(&data.is_ready);
+
+	data.go = 1;
+	/* memory barrier is in the wake_up_process() */
 
 	wake_up_process(p);
 
 	/* Wait for the task to wake up */
-	wait_for_completion(&is_ready);
+	wait_for_completion(&data.is_ready);
 
 	/* stop the tracing. */
 	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(&tr->trace_buffer, NULL);
-	printk("ret = %d\n", ret);
 	if (!ret)
 		ret = trace_test_buffer(&tr->max_buffer, &count);
 
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 8a4e5cb66a4c..16eddb308c33 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -13,7 +13,6 @@
 #include <linux/sysctl.h>
 #include <linux/init.h>
 #include <linux/fs.h>
-#include <linux/magic.h>
 
 #include <asm/setup.h>
 
@@ -171,8 +170,7 @@ check_stack(unsigned long ip, unsigned long *stack)
 			i++;
 	}
 
-	if ((current != &init_task &&
-		*(end_of_stack(current)) != STACK_END_MAGIC)) {
+	if (task_stack_end_corrupted(current)) {
 		print_max_stack();
 		BUG();
 	}
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 759d5e004517..4dc8b79c5f75 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -425,7 +425,7 @@ static void unreg_event_syscall_enter(struct ftrace_event_file *file,
 		return;
 	mutex_lock(&syscall_trace_lock);
 	tr->sys_refcount_enter--;
-	rcu_assign_pointer(tr->enter_syscall_files[num], NULL);
+	RCU_INIT_POINTER(tr->enter_syscall_files[num], NULL);
 	if (!tr->sys_refcount_enter)
 		unregister_trace_sys_enter(ftrace_syscall_enter, tr);
 	mutex_unlock(&syscall_trace_lock);
@@ -463,7 +463,7 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file,
 		return;
 	mutex_lock(&syscall_trace_lock);
 	tr->sys_refcount_exit--;
-	rcu_assign_pointer(tr->exit_syscall_files[num], NULL);
+	RCU_INIT_POINTER(tr->exit_syscall_files[num], NULL);
 	if (!tr->sys_refcount_exit)
 		unregister_trace_sys_exit(ftrace_syscall_exit, tr);
 	mutex_unlock(&syscall_trace_lock);
diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c
index 394f70b17162..9586b670a5b2 100644
--- a/kernel/user-return-notifier.c
+++ b/kernel/user-return-notifier.c
@@ -14,7 +14,7 @@ static DEFINE_PER_CPU(struct hlist_head, return_notifier_list);
 void user_return_notifier_register(struct user_return_notifier *urn)
 {
 	set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
-	hlist_add_head(&urn->link, &__get_cpu_var(return_notifier_list));
+	hlist_add_head(&urn->link, this_cpu_ptr(&return_notifier_list));
 }
 EXPORT_SYMBOL_GPL(user_return_notifier_register);
 
@@ -25,7 +25,7 @@ EXPORT_SYMBOL_GPL(user_return_notifier_register);
 void user_return_notifier_unregister(struct user_return_notifier *urn)
 {
 	hlist_del(&urn->link);
-	if (hlist_empty(&__get_cpu_var(return_notifier_list)))
+	if (hlist_empty(this_cpu_ptr(&return_notifier_list)))
 		clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
 }
 EXPORT_SYMBOL_GPL(user_return_notifier_unregister);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index a8d6914030fe..70bf11815f84 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -15,11 +15,6 @@
 #include <linux/cpu.h>
 #include <linux/nmi.h>
 #include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/freezer.h>
-#include <linux/kthread.h>
-#include <linux/lockdep.h>
-#include <linux/notifier.h>
 #include <linux/module.h>
 #include <linux/sysctl.h>
 #include <linux/smpboot.h>
@@ -47,6 +42,7 @@ static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
 static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
+static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
@@ -63,6 +59,25 @@ static unsigned long soft_lockup_nmi_warn;
 static int hardlockup_panic =
 			CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
 
+static bool hardlockup_detector_enabled = true;
+/*
+ * We may not want to enable hard lockup detection by default in all cases,
+ * for example when running the kernel as a guest on a hypervisor. In these
+ * cases this function can be called to disable hard lockup detection. This
+ * function should only be executed once by the boot processor before the
+ * kernel command line parameters are parsed, because otherwise it is not
+ * possible to override this in hardlockup_panic_setup().
+ */
+void watchdog_enable_hardlockup_detector(bool val)
+{
+	hardlockup_detector_enabled = val;
+}
+
+bool watchdog_hardlockup_detector_is_enabled(void)
+{
+	return hardlockup_detector_enabled;
+}
+
 static int __init hardlockup_panic_setup(char *str)
 {
 	if (!strncmp(str, "panic", 5))
@@ -71,6 +86,14 @@ static int __init hardlockup_panic_setup(char *str)
 		hardlockup_panic = 0;
 	else if (!strncmp(str, "0", 1))
 		watchdog_user_enabled = 0;
+	else if (!strncmp(str, "1", 1) || !strncmp(str, "2", 1)) {
+		/*
+		 * Setting 'nmi_watchdog=1' or 'nmi_watchdog=2' (legacy option)
+		 * has the same effect.
+		 */
+		watchdog_user_enabled = 1;
+		watchdog_enable_hardlockup_detector(true);
+	}
 	return 1;
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
@@ -185,7 +208,7 @@ void touch_nmi_watchdog(void)
 	 * case we shouldn't have to worry about the watchdog
 	 * going off.
 	 */
-	__raw_get_cpu_var(watchdog_nmi_touch) = true;
+	raw_cpu_write(watchdog_nmi_touch, true);
 	touch_softlockup_watchdog();
 }
 EXPORT_SYMBOL(touch_nmi_watchdog);
@@ -194,8 +217,8 @@ EXPORT_SYMBOL(touch_nmi_watchdog);
 
 void touch_softlockup_watchdog_sync(void)
 {
-	__raw_get_cpu_var(softlockup_touch_sync) = true;
-	__raw_get_cpu_var(watchdog_touch_ts) = 0;
+	__this_cpu_write(softlockup_touch_sync, true);
+	__this_cpu_write(watchdog_touch_ts, 0);
 }
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
@@ -333,8 +356,22 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 			return HRTIMER_RESTART;
 
 		/* only warn once */
-		if (__this_cpu_read(soft_watchdog_warn) == true)
+		if (__this_cpu_read(soft_watchdog_warn) == true) {
+			/*
+			 * When multiple processes are causing softlockups the
+			 * softlockup detector only warns on the first one
+			 * because the code relies on a full quiet cycle to
+			 * re-arm.  The second process prevents the quiet cycle
+			 * and never gets reported.  Use task pointers to detect
+			 * this.
+			 */
+			if (__this_cpu_read(softlockup_task_ptr_saved) !=
+			    current) {
+				__this_cpu_write(soft_watchdog_warn, false);
+				__touch_watchdog();
+			}
 			return HRTIMER_RESTART;
+		}
 
 		if (softlockup_all_cpu_backtrace) {
 			/* Prevent multiple soft-lockup reports if one cpu is already
@@ -350,6 +387,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
+		__this_cpu_write(softlockup_task_ptr_saved, current);
 		print_modules();
 		print_irqtrace_events(current);
 		if (regs)
@@ -387,7 +425,7 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio)
 
 static void watchdog_enable(unsigned int cpu)
 {
-	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+	struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
 
 	/* kick off the timer for the hardlockup detector */
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
@@ -407,7 +445,7 @@ static void watchdog_enable(unsigned int cpu)
 
 static void watchdog_disable(unsigned int cpu)
 {
-	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+	struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
 
 	watchdog_set_prio(SCHED_NORMAL, 0);
 	hrtimer_cancel(hrtimer);
@@ -454,6 +492,15 @@ static int watchdog_nmi_enable(unsigned int cpu)
 	struct perf_event_attr *wd_attr;
 	struct perf_event *event = per_cpu(watchdog_ev, cpu);
 
+	/*
+	 * Some kernels need to default hard lockup detection to
+	 * 'disabled', for example a guest on a hypervisor.
+	 */
+	if (!watchdog_hardlockup_detector_is_enabled()) {
+		event = ERR_PTR(-ENOENT);
+		goto handle_err;
+	}
+
 	/* is it already setup and enabled? */
 	if (event && event->state > PERF_EVENT_STATE_OFF)
 		goto out;
@@ -468,6 +515,7 @@ static int watchdog_nmi_enable(unsigned int cpu)
 	/* Try to register using hardware perf events */
 	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
 
+handle_err:
 	/* save cpu0 error for future comparision */
 	if (cpu == 0 && IS_ERR(event))
 		cpu0_err = PTR_ERR(event);
@@ -514,7 +562,10 @@ static void watchdog_nmi_disable(unsigned int cpu)
 		/* should be in cleanup, but blocks oprofile */
 		perf_event_release_kernel(event);
 	}
-	return;
+	if (cpu == 0) {
+		/* watchdog_nmi_enable() expects this to be zero initially. */
+		cpu0_err = 0;
+	}
 }
 #else
 static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
@@ -534,7 +585,7 @@ static struct smp_hotplug_thread watchdog_threads = {
 
 static void restart_watchdog_hrtimer(void *info)
 {
-	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
+	struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
 	int ret;
 
 	/*
@@ -610,11 +661,13 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 		    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int err, old_thresh, old_enabled;
+	bool old_hardlockup;
 	static DEFINE_MUTEX(watchdog_proc_mutex);
 
 	mutex_lock(&watchdog_proc_mutex);
 	old_thresh = ACCESS_ONCE(watchdog_thresh);
 	old_enabled = ACCESS_ONCE(watchdog_user_enabled);
+	old_hardlockup = watchdog_hardlockup_detector_is_enabled();
 
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (err || !write)
@@ -626,15 +679,22 @@ int proc_dowatchdog(struct ctl_table *table, int write,
 	 * disabled. The 'watchdog_running' variable check in
 	 * watchdog_*_all_cpus() function takes care of this.
 	 */
-	if (watchdog_user_enabled && watchdog_thresh)
+	if (watchdog_user_enabled && watchdog_thresh) {
+		/*
+		 * Prevent a change in watchdog_thresh accidentally overriding
+		 * the enablement of the hardlockup detector.
+		 */
+		if (watchdog_user_enabled != old_enabled)
+			watchdog_enable_hardlockup_detector(true);
 		err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh);
-	else
+	} else
 		watchdog_disable_all_cpus();
 
 	/* Restore old values on failure */
 	if (err) {
 		watchdog_thresh = old_thresh;
 		watchdog_user_enabled = old_enabled;
+		watchdog_enable_hardlockup_detector(old_hardlockup);
 	}
 out:
 	mutex_unlock(&watchdog_proc_mutex);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 5dbe22aa3efd..09b685daee3d 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2043,9 +2043,10 @@ __acquires(&pool->lock)
 	 * kernels, where a requeueing work item waiting for something to
 	 * happen could deadlock with stop_machine as such work item could
 	 * indefinitely requeue itself while all other CPUs are trapped in
-	 * stop_machine.
+	 * stop_machine. At the same time, report a quiescent RCU state so
+	 * the same condition doesn't freeze RCU.
 	 */
-	cond_resched();
+	cond_resched_rcu_qs();
 
 	spin_lock_irq(&pool->lock);
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 3ac43f34437b..4e35a5d767ed 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -824,6 +824,18 @@ config SCHEDSTATS
 	  application, you can say N to avoid the very slight overhead
 	  this adds.
 
+config SCHED_STACK_END_CHECK
+	bool "Detect stack corruption on calls to schedule()"
+	depends on DEBUG_KERNEL
+	default n
+	help
+	  This option checks for a stack overrun on calls to schedule().
+	  If the stack end location is found to be over written always panic as
+	  the content of the corrupted region can no longer be trusted.
+	  This is to ensure no erroneous behaviour occurs which could result in
+	  data corruption or a sporadic crash at a later stage once the region
+	  is examined. The runtime overhead introduced is minimal.
+
 config TIMER_STATS
 	bool "Collect kernel timers statistics"
 	depends on DEBUG_KERNEL && PROC_FS
@@ -952,7 +964,7 @@ config PROVE_LOCKING
 	 the proof of observed correctness is also maintained for an
 	 arbitrary combination of these separate locking variants.
 
-	 For more details, see Documentation/lockdep-design.txt.
+	 For more details, see Documentation/locking/lockdep-design.txt.
 
 config LOCKDEP
 	bool
@@ -973,7 +985,7 @@ config LOCK_STAT
 	help
 	 This feature enables tracking lock contention points
 
-	 For more details, see Documentation/lockstat.txt
+	 For more details, see Documentation/locking/lockstat.txt
 
 	 This also enables lock events required by "perf lock",
 	 subcommand of perf.
@@ -1636,7 +1648,7 @@ config DMA_API_DEBUG
 
 	  If unsure, say N.
 
-config TEST_MODULE
+config TEST_LKM
 	tristate "Test module loading with 'hello world' module"
 	default n
 	depends on m
diff --git a/lib/Makefile b/lib/Makefile
index d6b4bc496408..7512dc978f18 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -11,7 +11,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o timerqueue.o\
 	 idr.o int_sqrt.o extable.o \
 	 sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
-	 proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
+	 proportions.o flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o
 
@@ -31,7 +31,7 @@ obj-y += string_helpers.o
 obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
 obj-y += kstrtox.o
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
-obj-$(CONFIG_TEST_MODULE) += test_module.o
+obj-$(CONFIG_TEST_LKM) += test_module.o
 obj-$(CONFIG_TEST_USER_COPY) += test_user_copy.o
 obj-$(CONFIG_TEST_BPF) += test_bpf.o
 obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 08a4f068e61e..1298c05ef528 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -70,53 +70,42 @@ void atomic64_set(atomic64_t *v, long long i)
 }
 EXPORT_SYMBOL(atomic64_set);
 
-void atomic64_add(long long a, atomic64_t *v)
-{
-	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
-
-	raw_spin_lock_irqsave(lock, flags);
-	v->counter += a;
-	raw_spin_unlock_irqrestore(lock, flags);
-}
-EXPORT_SYMBOL(atomic64_add);
-
-long long atomic64_add_return(long long a, atomic64_t *v)
-{
-	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
-
-	raw_spin_lock_irqsave(lock, flags);
-	val = v->counter += a;
-	raw_spin_unlock_irqrestore(lock, flags);
-	return val;
-}
-EXPORT_SYMBOL(atomic64_add_return);
-
-void atomic64_sub(long long a, atomic64_t *v)
-{
-	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
-
-	raw_spin_lock_irqsave(lock, flags);
-	v->counter -= a;
-	raw_spin_unlock_irqrestore(lock, flags);
-}
-EXPORT_SYMBOL(atomic64_sub);
-
-long long atomic64_sub_return(long long a, atomic64_t *v)
-{
-	unsigned long flags;
-	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
-
-	raw_spin_lock_irqsave(lock, flags);
-	val = v->counter -= a;
-	raw_spin_unlock_irqrestore(lock, flags);
-	return val;
-}
-EXPORT_SYMBOL(atomic64_sub_return);
+#define ATOMIC64_OP(op, c_op)						\
+void atomic64_##op(long long a, atomic64_t *v)				\
+{									\
+	unsigned long flags;						\
+	raw_spinlock_t *lock = lock_addr(v);				\
+									\
+	raw_spin_lock_irqsave(lock, flags);				\
+	v->counter c_op a;						\
+	raw_spin_unlock_irqrestore(lock, flags);			\
+}									\
+EXPORT_SYMBOL(atomic64_##op);
+
+#define ATOMIC64_OP_RETURN(op, c_op)					\
+long long atomic64_##op##_return(long long a, atomic64_t *v)		\
+{									\
+	unsigned long flags;						\
+	raw_spinlock_t *lock = lock_addr(v);				\
+	long long val;							\
+									\
+	raw_spin_lock_irqsave(lock, flags);				\
+	val = (v->counter c_op a);					\
+	raw_spin_unlock_irqrestore(lock, flags);			\
+	return val;							\
+}									\
+EXPORT_SYMBOL(atomic64_##op##_return);
+
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_OP_RETURN(op, c_op)
+
+ATOMIC64_OPS(add, +=)
+ATOMIC64_OPS(sub, -=)
+
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
 
 long long atomic64_dec_if_positive(atomic64_t *v)
 {
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 31fe79e31ab8..dfba05521748 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -819,22 +819,9 @@ static const struct seq_operations ddebug_proc_seqops = {
  */
 static int ddebug_proc_open(struct inode *inode, struct file *file)
 {
-	struct ddebug_iter *iter;
-	int err;
-
 	vpr_info("called\n");
-
-	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-	if (iter == NULL)
-		return -ENOMEM;
-
-	err = seq_open(file, &ddebug_proc_seqops);
-	if (err) {
-		kfree(iter);
-		return err;
-	}
-	((struct seq_file *)file->private_data)->private = iter;
-	return 0;
+	return seq_open_private(file, &ddebug_proc_seqops,
+				sizeof(struct ddebug_iter));
 }
 
 static const struct file_operations ddebug_proc_fops = {
diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c
index ebf3bac460b0..8f25652f40d4 100644
--- a/lib/flex_proportions.c
+++ b/lib/flex_proportions.c
@@ -34,13 +34,13 @@
  */
 #include <linux/flex_proportions.h>
 
-int fprop_global_init(struct fprop_global *p)
+int fprop_global_init(struct fprop_global *p, gfp_t gfp)
 {
 	int err;
 
 	p->period = 0;
 	/* Use 1 to avoid dealing with periods with 0 events... */
-	err = percpu_counter_init(&p->events, 1);
+	err = percpu_counter_init(&p->events, 1, gfp);
 	if (err)
 		return err;
 	seqcount_init(&p->sequence);
@@ -168,11 +168,11 @@ void fprop_fraction_single(struct fprop_global *p,
  */
 #define PROP_BATCH (8*(1+ilog2(nr_cpu_ids)))
 
-int fprop_local_init_percpu(struct fprop_local_percpu *pl)
+int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp)
 {
 	int err;
 
-	err = percpu_counter_init(&pl->events, 0);
+	err = percpu_counter_init(&pl->events, 0, gfp);
 	if (err)
 		return err;
 	pl->period = 0;
diff --git a/lib/fonts/Kconfig b/lib/fonts/Kconfig
index 34fd931b54b5..e77dfe00de36 100644
--- a/lib/fonts/Kconfig
+++ b/lib/fonts/Kconfig
@@ -79,6 +79,14 @@ config FONT_MINI_4x6
 	bool "Mini 4x6 font"
 	depends on !SPARC && FONTS
 
+config FONT_6x10
+	bool "Medium-size 6x10 font"
+	depends on !SPARC && FONTS
+	help
+	  Medium-size console font. Suitable for framebuffer consoles on
+	  embedded devices with a 320x240 screen, to get a reasonable number
+	  of characters (53x24) that are still at a readable size.
+
 config FONT_SUN8x16
 	bool "Sparc console 8x16 font"
 	depends on FRAMEBUFFER_CONSOLE && (!SPARC && FONTS || SPARC)
@@ -109,6 +117,7 @@ config FONT_AUTOSELECT
 	depends on !FONT_PEARL_8x8
 	depends on !FONT_ACORN_8x8
 	depends on !FONT_MINI_4x6
+	depends on !FONT_6x10
 	depends on !FONT_SUN8x16
 	depends on !FONT_SUN12x22
 	depends on !FONT_10x18
diff --git a/lib/fonts/Makefile b/lib/fonts/Makefile
index 2761560f3f15..e04d010cfbf5 100644
--- a/lib/fonts/Makefile
+++ b/lib/fonts/Makefile
@@ -12,6 +12,7 @@ font-objs-$(CONFIG_FONT_10x18)     += font_10x18.o
 font-objs-$(CONFIG_FONT_PEARL_8x8) += font_pearl_8x8.o
 font-objs-$(CONFIG_FONT_ACORN_8x8) += font_acorn_8x8.o
 font-objs-$(CONFIG_FONT_MINI_4x6)  += font_mini_4x6.o
+font-objs-$(CONFIG_FONT_6x10)      += font_6x10.o
 
 font-objs += $(font-objs-y)
 
diff --git a/lib/fonts/font_6x10.c b/lib/fonts/font_6x10.c
new file mode 100644
index 000000000000..b20620904d31
--- /dev/null
+++ b/lib/fonts/font_6x10.c
@@ -0,0 +1,3086 @@
+#include <linux/font.h>
+
+static const unsigned char fontdata_6x10[] = {
+
+	/* 0 0x00 '^@' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 1 0x01 '^A' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x84, /* 10000100 */
+	0xCC, /* 11001100 */
+	0x84, /* 10000100 */
+	0xCC, /* 11001100 */
+	0xB4, /* 10110100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 2 0x02 '^B' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0xFC, /* 11111100 */
+	0xB4, /* 10110100 */
+	0xFC, /* 11111100 */
+	0xB4, /* 10110100 */
+	0xCC, /* 11001100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 3 0x03 '^C' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x7C, /* 01111100 */
+	0x7C, /* 01111100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 4 0x04 '^D' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x7C, /* 01111100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 5 0x05 '^E' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x6C, /* 01101100 */
+	0x6C, /* 01101100 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 6 0x06 '^F' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x7C, /* 01111100 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 7 0x07 '^G' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x78, /* 01111000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 8 0x08 '^H' */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xCC, /* 11001100 */
+	0x84, /* 10000100 */
+	0xCC, /* 11001100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+
+	/* 9 0x09 '^I' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x48, /* 01001000 */
+	0x84, /* 10000100 */
+	0x48, /* 01001000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 10 0x0A '^J' */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xCC, /* 11001100 */
+	0xB4, /* 10110100 */
+	0x78, /* 01111000 */
+	0xB4, /* 10110100 */
+	0xCC, /* 11001100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+
+	/* 11 0x0B '^K' */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x14, /* 00010100 */
+	0x20, /* 00100000 */
+	0x78, /* 01111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 12 0x0C '^L' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 13 0x0D '^M' */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x14, /* 00010100 */
+	0x14, /* 00010100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x70, /* 01110000 */
+	0x60, /* 01100000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 14 0x0E '^N' */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x24, /* 00100100 */
+	0x3C, /* 00111100 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x6C, /* 01101100 */
+	0x6C, /* 01101100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 15 0x0F '^O' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x6C, /* 01101100 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 16 0x10 '^P' */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x60, /* 01100000 */
+	0x70, /* 01110000 */
+	0x78, /* 01111000 */
+	0x70, /* 01110000 */
+	0x60, /* 01100000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 17 0x11 '^Q' */
+	0x00, /* 00000000 */
+	0x04, /* 00000100 */
+	0x0C, /* 00001100 */
+	0x1C, /* 00011100 */
+	0x3C, /* 00111100 */
+	0x1C, /* 00011100 */
+	0x0C, /* 00001100 */
+	0x04, /* 00000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 18 0x12 '^R' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x10, /* 00010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 19 0x13 '^S' */
+	0x00, /* 00000000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x00, /* 00000000 */
+	0x48, /* 01001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 20 0x14 '^T' */
+	0x3C, /* 00111100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x3C, /* 00111100 */
+	0x14, /* 00010100 */
+	0x14, /* 00010100 */
+	0x14, /* 00010100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 21 0x15 '^U' */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x20, /* 00100000 */
+	0x50, /* 01010000 */
+	0x48, /* 01001000 */
+	0x24, /* 00100100 */
+	0x14, /* 00010100 */
+	0x08, /* 00001000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+
+	/* 22 0x16 '^V' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xF8, /* 11111000 */
+	0xF8, /* 11111000 */
+	0xF8, /* 11111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 23 0x17 '^W' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x10, /* 00010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+
+	/* 24 0x18 '^X' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 25 0x19 '^Y' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 26 0x1A '^Z' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x7C, /* 01111100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 27 0x1B '^[' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x7C, /* 01111100 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 28 0x1C '^\' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 29 0x1D '^]' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x48, /* 01001000 */
+	0x84, /* 10000100 */
+	0xFC, /* 11111100 */
+	0x84, /* 10000100 */
+	0x48, /* 01001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 30 0x1E '^^' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x7C, /* 01111100 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 31 0x1F '^_' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x7C, /* 01111100 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 32 0x20 ' ' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 33 0x21 '!' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 34 0x22 '"' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 35 0x23 '#' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x7C, /* 01111100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x7C, /* 01111100 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 36 0x24 '$' */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x50, /* 01010000 */
+	0x38, /* 00111000 */
+	0x14, /* 00010100 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+
+	/* 37 0x25 '%' */
+	0x00, /* 00000000 */
+	0x64, /* 01100100 */
+	0x64, /* 01100100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x4C, /* 01001100 */
+	0x4C, /* 01001100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 38 0x26 '&' */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x48, /* 01001000 */
+	0x50, /* 01010000 */
+	0x20, /* 00100000 */
+	0x54, /* 01010100 */
+	0x48, /* 01001000 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 39 0x27 ''' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 40 0x28 '(' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+
+	/* 41 0x29 ')' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x00, /* 00000000 */
+
+	/* 42 0x2A '*' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 43 0x2B '+' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 44 0x2C ',' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+
+	/* 45 0x2D '-' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 46 0x2E '.' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x18, /* 00011000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 47 0x2F '/' */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+
+	/* 48 0x30 '0' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x54, /* 01010100 */
+	0x64, /* 01100100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 49 0x31 '1' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x30, /* 00110000 */
+	0x50, /* 01010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 50 0x32 '2' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 51 0x33 '3' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x04, /* 00000100 */
+	0x18, /* 00011000 */
+	0x04, /* 00000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 52 0x34 '4' */
+	0x00, /* 00000000 */
+	0x08, /* 00001000 */
+	0x18, /* 00011000 */
+	0x28, /* 00101000 */
+	0x48, /* 01001000 */
+	0x7C, /* 01111100 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 53 0x35 '5' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 54 0x36 '6' */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x20, /* 00100000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 55 0x37 '7' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 56 0x38 '8' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 57 0x39 '9' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 58 0x3A ':' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x18, /* 00011000 */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x18, /* 00011000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 59 0x3B ';' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+
+	/* 60 0x3C '<' */
+	0x00, /* 00000000 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x04, /* 00000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 61 0x3D '=' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 62 0x3E '>' */
+	0x00, /* 00000000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 63 0x3F '?' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 64 0x40 '@' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x5C, /* 01011100 */
+	0x54, /* 01010100 */
+	0x5C, /* 01011100 */
+	0x40, /* 01000000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 65 0x41 'A' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 66 0x42 'B' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x38, /* 00111000 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 67 0x43 'C' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 68 0x44 'D' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 69 0x45 'E' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 70 0x46 'F' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 71 0x47 'G' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x5C, /* 01011100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 72 0x48 'H' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 73 0x49 'I' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 74 0x4A 'J' */
+	0x00, /* 00000000 */
+	0x1C, /* 00011100 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 75 0x4B 'K' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x48, /* 01001000 */
+	0x50, /* 01010000 */
+	0x60, /* 01100000 */
+	0x50, /* 01010000 */
+	0x48, /* 01001000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 76 0x4C 'L' */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 77 0x4D 'M' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x6C, /* 01101100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 78 0x4E 'N' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x64, /* 01100100 */
+	0x54, /* 01010100 */
+	0x4C, /* 01001100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 79 0x4F 'O' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 80 0x50 'P' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x78, /* 01111000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 81 0x51 'Q' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x54, /* 01010100 */
+	0x48, /* 01001000 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 82 0x52 'R' */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x78, /* 01111000 */
+	0x50, /* 01010000 */
+	0x48, /* 01001000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 83 0x53 'S' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 84 0x54 'T' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 85 0x55 'U' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 86 0x56 'V' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 87 0x57 'W' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x6C, /* 01101100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 88 0x58 'X' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 89 0x59 'Y' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 90 0x5A 'Z' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x40, /* 01000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 91 0x5B '[' */
+	0x18, /* 00011000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x18, /* 00011000 */
+	0x00, /* 00000000 */
+
+	/* 92 0x5C '\' */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+
+	/* 93 0x5D ']' */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+
+	/* 94 0x5E '^' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 95 0x5F '_' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+
+	/* 96 0x60 '`' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 97 0x61 'a' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 98 0x62 'b' */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x58, /* 01011000 */
+	0x64, /* 01100100 */
+	0x44, /* 01000100 */
+	0x64, /* 01100100 */
+	0x58, /* 01011000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 99 0x63 'c' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 100 0x64 'd' */
+	0x00, /* 00000000 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+	0x34, /* 00110100 */
+	0x4C, /* 01001100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 101 0x65 'e' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 102 0x66 'f' */
+	0x00, /* 00000000 */
+	0x0C, /* 00001100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 103 0x67 'g' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x34, /* 00110100 */
+	0x4C, /* 01001100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x04, /* 00000100 */
+	0x38, /* 00111000 */
+
+	/* 104 0x68 'h' */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 105 0x69 'i' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 106 0x6A 'j' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x60, /* 01100000 */
+
+	/* 107 0x6B 'k' */
+	0x00, /* 00000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x48, /* 01001000 */
+	0x50, /* 01010000 */
+	0x70, /* 01110000 */
+	0x48, /* 01001000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 108 0x6C 'l' */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 109 0x6D 'm' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x68, /* 01101000 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 110 0x6E 'n' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x58, /* 01011000 */
+	0x64, /* 01100100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 111 0x6F 'o' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 112 0x70 'p' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x58, /* 01011000 */
+	0x64, /* 01100100 */
+	0x44, /* 01000100 */
+	0x64, /* 01100100 */
+	0x58, /* 01011000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+
+	/* 113 0x71 'q' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x34, /* 00110100 */
+	0x4C, /* 01001100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+
+	/* 114 0x72 'r' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x58, /* 01011000 */
+	0x64, /* 01100100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 115 0x73 's' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x40, /* 01000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 116 0x74 't' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x0C, /* 00001100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 117 0x75 'u' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 118 0x76 'v' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 119 0x77 'w' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 120 0x78 'x' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 121 0x79 'y' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x04, /* 00000100 */
+	0x38, /* 00111000 */
+
+	/* 122 0x7A 'z' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 123 0x7B '{' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+
+	/* 124 0x7C '|' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+
+	/* 125 0x7D '}' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x00, /* 00000000 */
+
+	/* 126 0x7E '~' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x20, /* 00100000 */
+	0x54, /* 01010100 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 127 0x7F '' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 128 0x80 '\200' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+
+	/* 129 0x81 '\201' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 130 0x82 '\202' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 131 0x83 '\203' */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 132 0x84 '\204' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 133 0x85 '\205' */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 134 0x86 '\206' */
+	0x18, /* 00011000 */
+	0x24, /* 00100100 */
+	0x18, /* 00011000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 135 0x87 '\207' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+
+	/* 136 0x88 '\210' */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 137 0x89 '\211' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 138 0x8A '\212' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 139 0x8B '\213' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 140 0x8C '\214' */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 141 0x8D '\215' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 142 0x8E '\216' */
+	0x44, /* 01000100 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 143 0x8F '\217' */
+	0x30, /* 00110000 */
+	0x48, /* 01001000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 144 0x90 '\220' */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x78, /* 01111000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 145 0x91 '\221' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x78, /* 01111000 */
+	0x14, /* 00010100 */
+	0x7C, /* 01111100 */
+	0x50, /* 01010000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 146 0x92 '\222' */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x50, /* 01010000 */
+	0x50, /* 01010000 */
+	0x78, /* 01111000 */
+	0x50, /* 01010000 */
+	0x50, /* 01010000 */
+	0x5C, /* 01011100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 147 0x93 '\223' */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 148 0x94 '\224' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 149 0x95 '\225' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 150 0x96 '\226' */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 151 0x97 '\227' */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 152 0x98 '\230' */
+	0x00, /* 00000000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x04, /* 00000100 */
+	0x38, /* 00111000 */
+
+	/* 153 0x99 '\231' */
+	0x84, /* 10000100 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 154 0x9A '\232' */
+	0x88, /* 10001000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 155 0x9B '\233' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x50, /* 01010000 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+
+	/* 156 0x9C '\234' */
+	0x30, /* 00110000 */
+	0x48, /* 01001000 */
+	0x40, /* 01000000 */
+	0x70, /* 01110000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x78, /* 01111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 157 0x9D '\235' */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 158 0x9E '\236' */
+	0x00, /* 00000000 */
+	0x70, /* 01110000 */
+	0x48, /* 01001000 */
+	0x70, /* 01110000 */
+	0x48, /* 01001000 */
+	0x5C, /* 01011100 */
+	0x48, /* 01001000 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 159 0x9F '\237' */
+	0x00, /* 00000000 */
+	0x0C, /* 00001100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x60, /* 01100000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 160 0xA0 '\240' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 161 0xA1 '\241' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x30, /* 00110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 162 0xA2 '\242' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 163 0xA3 '\243' */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x4C, /* 01001100 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 164 0xA4 '\244' */
+	0x34, /* 00110100 */
+	0x58, /* 01011000 */
+	0x00, /* 00000000 */
+	0x58, /* 01011000 */
+	0x64, /* 01100100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 165 0xA5 '\245' */
+	0x58, /* 01011000 */
+	0x44, /* 01000100 */
+	0x64, /* 01100100 */
+	0x54, /* 01010100 */
+	0x4C, /* 01001100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 166 0xA6 '\246' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x04, /* 00000100 */
+	0x3C, /* 00111100 */
+	0x44, /* 01000100 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 167 0xA7 '\247' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 168 0xA8 '\250' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x40, /* 01000000 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 169 0xA9 '\251' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 170 0xAA '\252' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x04, /* 00000100 */
+	0x04, /* 00000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 171 0xAB '\253' */
+	0x20, /* 00100000 */
+	0x60, /* 01100000 */
+	0x24, /* 00100100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x44, /* 01000100 */
+	0x08, /* 00001000 */
+	0x1C, /* 00011100 */
+	0x00, /* 00000000 */
+
+	/* 172 0xAC '\254' */
+	0x20, /* 00100000 */
+	0x60, /* 01100000 */
+	0x24, /* 00100100 */
+	0x28, /* 00101000 */
+	0x10, /* 00010000 */
+	0x28, /* 00101000 */
+	0x58, /* 01011000 */
+	0x3C, /* 00111100 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+
+	/* 173 0xAD '\255' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 174 0xAE '\256' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x24, /* 00100100 */
+	0x48, /* 01001000 */
+	0x90, /* 10010000 */
+	0x48, /* 01001000 */
+	0x24, /* 00100100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 175 0xAF '\257' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x90, /* 10010000 */
+	0x48, /* 01001000 */
+	0x24, /* 00100100 */
+	0x48, /* 01001000 */
+	0x90, /* 10010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 176 0xB0 '\260' */
+	0x10, /* 00010000 */
+	0x44, /* 01000100 */
+	0x10, /* 00010000 */
+	0x44, /* 01000100 */
+	0x10, /* 00010000 */
+	0x44, /* 01000100 */
+	0x10, /* 00010000 */
+	0x44, /* 01000100 */
+	0x10, /* 00010000 */
+	0x44, /* 01000100 */
+
+	/* 177 0xB1 '\261' */
+	0xA8, /* 10101000 */
+	0x54, /* 01010100 */
+	0xA8, /* 10101000 */
+	0x54, /* 01010100 */
+	0xA8, /* 10101000 */
+	0x54, /* 01010100 */
+	0xA8, /* 10101000 */
+	0x54, /* 01010100 */
+	0xA8, /* 10101000 */
+	0x54, /* 01010100 */
+
+	/* 178 0xB2 '\262' */
+	0xDC, /* 11011100 */
+	0x74, /* 01110100 */
+	0xDC, /* 11011100 */
+	0x74, /* 01110100 */
+	0xDC, /* 11011100 */
+	0x74, /* 01110100 */
+	0xDC, /* 11011100 */
+	0x74, /* 01110100 */
+	0xDC, /* 11011100 */
+	0x74, /* 01110100 */
+
+	/* 179 0xB3 '\263' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 180 0xB4 '\264' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 181 0xB5 '\265' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 182 0xB6 '\266' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xE8, /* 11101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 183 0xB7 '\267' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xF8, /* 11111000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 184 0xB8 '\270' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 185 0xB9 '\271' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xE8, /* 11101000 */
+	0x08, /* 00001000 */
+	0xE8, /* 11101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 186 0xBA '\272' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 187 0xBB '\273' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xF8, /* 11111000 */
+	0x08, /* 00001000 */
+	0xE8, /* 11101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 188 0xBC '\274' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xE8, /* 11101000 */
+	0x08, /* 00001000 */
+	0xF8, /* 11111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 189 0xBD '\275' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xF8, /* 11111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 190 0xBE '\276' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 191 0xBF '\277' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xF0, /* 11110000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 192 0xC0 '\300' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 193 0xC1 '\301' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 194 0xC2 '\302' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 195 0xC3 '\303' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 196 0xC4 '\304' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 197 0xC5 '\305' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xFC, /* 11111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 198 0xC6 '\306' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 199 0xC7 '\307' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x2C, /* 00101100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 200 0xC8 '\310' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x2C, /* 00101100 */
+	0x20, /* 00100000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 201 0xC9 '\311' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x20, /* 00100000 */
+	0x2C, /* 00101100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 202 0xCA '\312' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xEC, /* 11101100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 203 0xCB '\313' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xEC, /* 11101100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 204 0xCC '\314' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x2C, /* 00101100 */
+	0x20, /* 00100000 */
+	0x2C, /* 00101100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 205 0xCD '\315' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 206 0xCE '\316' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xEC, /* 11101100 */
+	0x00, /* 00000000 */
+	0xEC, /* 11101100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 207 0xCF '\317' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 208 0xD0 '\320' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 209 0xD1 '\321' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 210 0xD2 '\322' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 211 0xD3 '\323' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 212 0xD4 '\324' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 213 0xD5 '\325' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 214 0xD6 '\326' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 215 0xD7 '\327' */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0xFC, /* 11111100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+
+	/* 216 0xD8 '\330' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xFC, /* 11111100 */
+	0x10, /* 00010000 */
+	0xFC, /* 11111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 217 0xD9 '\331' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0xF0, /* 11110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 218 0xDA '\332' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x1C, /* 00011100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 219 0xDB '\333' */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+
+	/* 220 0xDC '\334' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+
+	/* 221 0xDD '\335' */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+	0xE0, /* 11100000 */
+
+	/* 222 0xDE '\336' */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+	0x1C, /* 00011100 */
+
+	/* 223 0xDF '\337' */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 224 0xE0 '\340' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x34, /* 00110100 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x34, /* 00110100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 225 0xE1 '\341' */
+	0x18, /* 00011000 */
+	0x24, /* 00100100 */
+	0x44, /* 01000100 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x58, /* 01011000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+
+	/* 226 0xE2 '\342' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 227 0xE3 '\343' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x28, /* 00101000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 228 0xE4 '\344' */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x24, /* 00100100 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x24, /* 00100100 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 229 0xE5 '\345' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 230 0xE6 '\346' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x74, /* 01110100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+
+	/* 231 0xE7 '\347' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x0C, /* 00001100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 232 0xE8 '\350' */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 233 0xE9 '\351' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x7C, /* 01111100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 234 0xEA '\352' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x28, /* 00101000 */
+	0x6C, /* 01101100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 235 0xEB '\353' */
+	0x00, /* 00000000 */
+	0x18, /* 00011000 */
+	0x20, /* 00100000 */
+	0x18, /* 00011000 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x24, /* 00100100 */
+	0x18, /* 00011000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 236 0xEC '\354' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 237 0xED '\355' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x04, /* 00000100 */
+	0x38, /* 00111000 */
+	0x54, /* 01010100 */
+	0x54, /* 01010100 */
+	0x38, /* 00111000 */
+	0x40, /* 01000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 238 0xEE '\356' */
+	0x00, /* 00000000 */
+	0x3C, /* 00111100 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x38, /* 00111000 */
+	0x40, /* 01000000 */
+	0x40, /* 01000000 */
+	0x3C, /* 00111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 239 0xEF '\357' */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x44, /* 01000100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 240 0xF0 '\360' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0xFC, /* 11111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 241 0xF1 '\361' */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x7C, /* 01111100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 242 0xF2 '\362' */
+	0x00, /* 00000000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 243 0xF3 '\363' */
+	0x00, /* 00000000 */
+	0x08, /* 00001000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x10, /* 00010000 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 244 0xF4 '\364' */
+	0x00, /* 00000000 */
+	0x0C, /* 00001100 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+
+	/* 245 0xF5 '\365' */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x10, /* 00010000 */
+	0x60, /* 01100000 */
+	0x00, /* 00000000 */
+
+	/* 246 0xF6 '\366' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x7C, /* 01111100 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 247 0xF7 '\367' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x20, /* 00100000 */
+	0x54, /* 01010100 */
+	0x08, /* 00001000 */
+	0x20, /* 00100000 */
+	0x54, /* 01010100 */
+	0x08, /* 00001000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 248 0xF8 '\370' */
+	0x30, /* 00110000 */
+	0x48, /* 01001000 */
+	0x48, /* 01001000 */
+	0x30, /* 00110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 249 0xF9 '\371' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x38, /* 00111000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 250 0xFA '\372' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x10, /* 00010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 251 0xFB '\373' */
+	0x00, /* 00000000 */
+	0x04, /* 00000100 */
+	0x08, /* 00001000 */
+	0x08, /* 00001000 */
+	0x50, /* 01010000 */
+	0x50, /* 01010000 */
+	0x20, /* 00100000 */
+	0x20, /* 00100000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 252 0xFC '\374' */
+	0x60, /* 01100000 */
+	0x50, /* 01010000 */
+	0x50, /* 01010000 */
+	0x50, /* 01010000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 253 0xFD '\375' */
+	0x60, /* 01100000 */
+	0x10, /* 00010000 */
+	0x20, /* 00100000 */
+	0x70, /* 01110000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 254 0xFE '\376' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x38, /* 00111000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+	/* 255 0xFF '\377' */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+	0x00, /* 00000000 */
+
+};
+
+const struct font_desc font_6x10 = {
+	.idx	= FONT6x10_IDX,
+	.name	= "6x10",
+	.width	= 6,
+	.height	= 10,
+	.data	= fontdata_6x10,
+	.pref	= 0,
+};
diff --git a/lib/fonts/fonts.c b/lib/fonts/fonts.c
index f947189efe6d..823376ca0a8b 100644
--- a/lib/fonts/fonts.c
+++ b/lib/fonts/fonts.c
@@ -63,6 +63,10 @@ static const struct font_desc *fonts[] = {
 #undef NO_FONTS
     &font_mini_4x6,
 #endif
+#ifdef CONFIG_FONT_6x10
+#undef NO_FONTS
+    &font_6x10,
+#endif
 };
 
 #define num_fonts ARRAY_SIZE(fonts)
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 38d2db82228c..cce4dd68c40d 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -403,6 +403,35 @@ void gen_pool_for_each_chunk(struct gen_pool *pool,
 EXPORT_SYMBOL(gen_pool_for_each_chunk);
 
 /**
+ * addr_in_gen_pool - checks if an address falls within the range of a pool
+ * @pool:	the generic memory pool
+ * @start:	start address
+ * @size:	size of the region
+ *
+ * Check if the range of addresses falls within the specified pool. Returns
+ * true if the entire range is contained in the pool and false otherwise.
+ */
+bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
+			size_t size)
+{
+	bool found = false;
+	unsigned long end = start + size;
+	struct gen_pool_chunk *chunk;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk) {
+		if (start >= chunk->start_addr && start <= chunk->end_addr) {
+			if (end <= chunk->end_addr) {
+				found = true;
+				break;
+			}
+		}
+	}
+	rcu_read_unlock();
+	return found;
+}
+
+/**
  * gen_pool_avail - get available free space of the pool
  * @pool: pool to get available free space
  *
@@ -481,6 +510,26 @@ unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
 EXPORT_SYMBOL(gen_pool_first_fit);
 
 /**
+ * gen_pool_first_fit_order_align - find the first available region
+ * of memory matching the size requirement. The region will be aligned
+ * to the order of the size specified.
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @data: additional data - unused
+ */
+unsigned long gen_pool_first_fit_order_align(unsigned long *map,
+		unsigned long size, unsigned long start,
+		unsigned int nr, void *data)
+{
+	unsigned long align_mask = roundup_pow_of_two(nr) - 1;
+
+	return bitmap_find_next_zero_area(map, size, start, nr, align_mask);
+}
+EXPORT_SYMBOL(gen_pool_first_fit_order_align);
+
+/**
  * gen_pool_best_fit - find the best fitting region of memory
  * macthing the size requirement (no alignment constraint)
  * @map: The address to base the search on
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 8499c810909a..270773b91923 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -59,6 +59,22 @@ int hex2bin(u8 *dst, const char *src, size_t count)
 EXPORT_SYMBOL(hex2bin);
 
 /**
+ * bin2hex - convert binary data to an ascii hexadecimal string
+ * @dst: ascii hexadecimal result
+ * @src: binary data
+ * @count: binary data length
+ */
+char *bin2hex(char *dst, const void *src, size_t count)
+{
+	const unsigned char *_src = src;
+
+	while (count--)
+		dst = hex_byte_pack(dst, *_src++);
+	return dst;
+}
+EXPORT_SYMBOL(bin2hex);
+
+/**
  * hex_dump_to_buffer - convert a blob of data to "hex ASCII" in memory
  * @buf: data blob to dump
  * @len: number of bytes in the @buf
diff --git a/lib/libcrc32c.c b/lib/libcrc32c.c
index b3131f5cf8a2..6a08ce7d6adc 100644
--- a/lib/libcrc32c.c
+++ b/lib/libcrc32c.c
@@ -41,20 +41,18 @@ static struct crypto_shash *tfm;
 
 u32 crc32c(u32 crc, const void *address, unsigned int length)
 {
-	struct {
-		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(tfm)];
-	} desc;
+	SHASH_DESC_ON_STACK(shash, tfm);
+	u32 *ctx = (u32 *)shash_desc_ctx(shash);
 	int err;
 
-	desc.shash.tfm = tfm;
-	desc.shash.flags = 0;
-	*(u32 *)desc.ctx = crc;
+	shash->tfm = tfm;
+	shash->flags = 0;
+	*ctx = crc;
 
-	err = crypto_shash_update(&desc.shash, address, length);
+	err = crypto_shash_update(shash, address, length);
 	BUG_ON(err);
 
-	return *(u32 *)desc.ctx;
+	return *ctx;
 }
 
 EXPORT_SYMBOL(crc32c);
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index a89cf09a8268..6111bcb28376 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -1,6 +1,8 @@
 #define pr_fmt(fmt) "%s: " fmt "\n", __func__
 
 #include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
 #include <linux/percpu-refcount.h>
 
 /*
@@ -11,8 +13,8 @@
  * percpu counters will all sum to the correct value
  *
  * (More precisely: because moduler arithmatic is commutative the sum of all the
- * pcpu_count vars will be equal to what it would have been if all the gets and
- * puts were done to a single integer, even if some of the percpu integers
+ * percpu_count vars will be equal to what it would have been if all the gets
+ * and puts were done to a single integer, even if some of the percpu integers
  * overflow or underflow).
  *
  * The real trick to implementing percpu refcounts is shutdown. We can't detect
@@ -25,75 +27,64 @@
  * works.
  *
  * Converting to non percpu mode is done with some RCUish stuff in
- * percpu_ref_kill. Additionally, we need a bias value so that the atomic_t
- * can't hit 0 before we've added up all the percpu refs.
+ * percpu_ref_kill. Additionally, we need a bias value so that the
+ * atomic_long_t can't hit 0 before we've added up all the percpu refs.
  */
 
-#define PCPU_COUNT_BIAS		(1U << 31)
+#define PERCPU_COUNT_BIAS	(1LU << (BITS_PER_LONG - 1))
 
-static unsigned __percpu *pcpu_count_ptr(struct percpu_ref *ref)
+static DECLARE_WAIT_QUEUE_HEAD(percpu_ref_switch_waitq);
+
+static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref)
 {
-	return (unsigned __percpu *)(ref->pcpu_count_ptr & ~PCPU_REF_DEAD);
+	return (unsigned long __percpu *)
+		(ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC_DEAD);
 }
 
 /**
  * percpu_ref_init - initialize a percpu refcount
  * @ref: percpu_ref to initialize
  * @release: function which will be called when refcount hits 0
+ * @flags: PERCPU_REF_INIT_* flags
+ * @gfp: allocation mask to use
  *
- * Initializes the refcount in single atomic counter mode with a refcount of 1;
- * analagous to atomic_set(ref, 1).
+ * Initializes @ref.  If @flags is zero, @ref starts in percpu mode with a
+ * refcount of 1; analagous to atomic_long_set(ref, 1).  See the
+ * definitions of PERCPU_REF_INIT_* flags for flag behaviors.
  *
  * Note that @release must not sleep - it may potentially be called from RCU
  * callback context by percpu_ref_kill().
  */
-int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release)
+int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
+		    unsigned int flags, gfp_t gfp)
 {
-	atomic_set(&ref->count, 1 + PCPU_COUNT_BIAS);
+	size_t align = max_t(size_t, 1 << __PERCPU_REF_FLAG_BITS,
+			     __alignof__(unsigned long));
+	unsigned long start_count = 0;
 
-	ref->pcpu_count_ptr = (unsigned long)alloc_percpu(unsigned);
-	if (!ref->pcpu_count_ptr)
+	ref->percpu_count_ptr = (unsigned long)
+		__alloc_percpu_gfp(sizeof(unsigned long), align, gfp);
+	if (!ref->percpu_count_ptr)
 		return -ENOMEM;
 
-	ref->release = release;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(percpu_ref_init);
-
-/**
- * percpu_ref_reinit - re-initialize a percpu refcount
- * @ref: perpcu_ref to re-initialize
- *
- * Re-initialize @ref so that it's in the same state as when it finished
- * percpu_ref_init().  @ref must have been initialized successfully, killed
- * and reached 0 but not exited.
- *
- * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while
- * this function is in progress.
- */
-void percpu_ref_reinit(struct percpu_ref *ref)
-{
-	unsigned __percpu *pcpu_count = pcpu_count_ptr(ref);
-	int cpu;
+	ref->force_atomic = flags & PERCPU_REF_INIT_ATOMIC;
 
-	BUG_ON(!pcpu_count);
-	WARN_ON(!percpu_ref_is_zero(ref));
+	if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD))
+		ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
+	else
+		start_count += PERCPU_COUNT_BIAS;
 
-	atomic_set(&ref->count, 1 + PCPU_COUNT_BIAS);
+	if (flags & PERCPU_REF_INIT_DEAD)
+		ref->percpu_count_ptr |= __PERCPU_REF_DEAD;
+	else
+		start_count++;
 
-	/*
-	 * Restore per-cpu operation.  smp_store_release() is paired with
-	 * smp_read_barrier_depends() in __pcpu_ref_alive() and guarantees
-	 * that the zeroing is visible to all percpu accesses which can see
-	 * the following PCPU_REF_DEAD clearing.
-	 */
-	for_each_possible_cpu(cpu)
-		*per_cpu_ptr(pcpu_count, cpu) = 0;
+	atomic_long_set(&ref->count, start_count);
 
-	smp_store_release(&ref->pcpu_count_ptr,
-			  ref->pcpu_count_ptr & ~PCPU_REF_DEAD);
+	ref->release = release;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(percpu_ref_reinit);
+EXPORT_SYMBOL_GPL(percpu_ref_init);
 
 /**
  * percpu_ref_exit - undo percpu_ref_init()
@@ -107,26 +98,39 @@ EXPORT_SYMBOL_GPL(percpu_ref_reinit);
  */
 void percpu_ref_exit(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count = pcpu_count_ptr(ref);
+	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
 
-	if (pcpu_count) {
-		free_percpu(pcpu_count);
-		ref->pcpu_count_ptr = PCPU_REF_DEAD;
+	if (percpu_count) {
+		free_percpu(percpu_count);
+		ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD;
 	}
 }
 EXPORT_SYMBOL_GPL(percpu_ref_exit);
 
-static void percpu_ref_kill_rcu(struct rcu_head *rcu)
+static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu)
+{
+	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
+
+	ref->confirm_switch(ref);
+	ref->confirm_switch = NULL;
+	wake_up_all(&percpu_ref_switch_waitq);
+
+	/* drop ref from percpu_ref_switch_to_atomic() */
+	percpu_ref_put(ref);
+}
+
+static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
 {
 	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
-	unsigned __percpu *pcpu_count = pcpu_count_ptr(ref);
-	unsigned count = 0;
+	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
+	unsigned long count = 0;
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		count += *per_cpu_ptr(pcpu_count, cpu);
+		count += *per_cpu_ptr(percpu_count, cpu);
 
-	pr_debug("global %i pcpu %i", atomic_read(&ref->count), (int) count);
+	pr_debug("global %ld percpu %ld",
+		 atomic_long_read(&ref->count), (long)count);
 
 	/*
 	 * It's crucial that we sum the percpu counters _before_ adding the sum
@@ -140,21 +144,137 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 	 * reaching 0 before we add the percpu counts. But doing it at the same
 	 * time is equivalent and saves us atomic operations:
 	 */
+	atomic_long_add((long)count - PERCPU_COUNT_BIAS, &ref->count);
+
+	WARN_ONCE(atomic_long_read(&ref->count) <= 0,
+		  "percpu ref (%pf) <= 0 (%ld) after switching to atomic",
+		  ref->release, atomic_long_read(&ref->count));
+
+	/* @ref is viewed as dead on all CPUs, send out switch confirmation */
+	percpu_ref_call_confirm_rcu(rcu);
+}
+
+static void percpu_ref_noop_confirm_switch(struct percpu_ref *ref)
+{
+}
+
+static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref,
+					  percpu_ref_func_t *confirm_switch)
+{
+	if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC)) {
+		/* switching from percpu to atomic */
+		ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
+
+		/*
+		 * Non-NULL ->confirm_switch is used to indicate that
+		 * switching is in progress.  Use noop one if unspecified.
+		 */
+		WARN_ON_ONCE(ref->confirm_switch);
+		ref->confirm_switch =
+			confirm_switch ?: percpu_ref_noop_confirm_switch;
+
+		percpu_ref_get(ref);	/* put after confirmation */
+		call_rcu_sched(&ref->rcu, percpu_ref_switch_to_atomic_rcu);
+	} else if (confirm_switch) {
+		/*
+		 * Somebody already set ATOMIC.  Switching may still be in
+		 * progress.  @confirm_switch must be invoked after the
+		 * switching is complete and a full sched RCU grace period
+		 * has passed.  Wait synchronously for the previous
+		 * switching and schedule @confirm_switch invocation.
+		 */
+		wait_event(percpu_ref_switch_waitq, !ref->confirm_switch);
+		ref->confirm_switch = confirm_switch;
 
-	atomic_add((int) count - PCPU_COUNT_BIAS, &ref->count);
+		percpu_ref_get(ref);	/* put after confirmation */
+		call_rcu_sched(&ref->rcu, percpu_ref_call_confirm_rcu);
+	}
+}
+
+/**
+ * percpu_ref_switch_to_atomic - switch a percpu_ref to atomic mode
+ * @ref: percpu_ref to switch to atomic mode
+ * @confirm_switch: optional confirmation callback
+ *
+ * There's no reason to use this function for the usual reference counting.
+ * Use percpu_ref_kill[_and_confirm]().
+ *
+ * Schedule switching of @ref to atomic mode.  All its percpu counts will
+ * be collected to the main atomic counter.  On completion, when all CPUs
+ * are guaraneed to be in atomic mode, @confirm_switch, which may not
+ * block, is invoked.  This function may be invoked concurrently with all
+ * the get/put operations and can safely be mixed with kill and reinit
+ * operations.  Note that @ref will stay in atomic mode across kill/reinit
+ * cycles until percpu_ref_switch_to_percpu() is called.
+ *
+ * This function normally doesn't block and can be called from any context
+ * but it may block if @confirm_kill is specified and @ref is already in
+ * the process of switching to atomic mode.  In such cases, @confirm_switch
+ * will be invoked after the switching is complete.
+ *
+ * Due to the way percpu_ref is implemented, @confirm_switch will be called
+ * after at least one full sched RCU grace period has passed but this is an
+ * implementation detail and must not be depended upon.
+ */
+void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
+				 percpu_ref_func_t *confirm_switch)
+{
+	ref->force_atomic = true;
+	__percpu_ref_switch_to_atomic(ref, confirm_switch);
+}
 
-	WARN_ONCE(atomic_read(&ref->count) <= 0, "percpu ref <= 0 (%i)",
-		  atomic_read(&ref->count));
+static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
+{
+	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
+	int cpu;
+
+	BUG_ON(!percpu_count);
 
-	/* @ref is viewed as dead on all CPUs, send out kill confirmation */
-	if (ref->confirm_kill)
-		ref->confirm_kill(ref);
+	if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC))
+		return;
+
+	wait_event(percpu_ref_switch_waitq, !ref->confirm_switch);
+
+	atomic_long_add(PERCPU_COUNT_BIAS, &ref->count);
 
 	/*
-	 * Now we're in single atomic_t mode with a consistent refcount, so it's
-	 * safe to drop our initial ref:
+	 * Restore per-cpu operation.  smp_store_release() is paired with
+	 * smp_read_barrier_depends() in __ref_is_percpu() and guarantees
+	 * that the zeroing is visible to all percpu accesses which can see
+	 * the following __PERCPU_REF_ATOMIC clearing.
 	 */
-	percpu_ref_put(ref);
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(percpu_count, cpu) = 0;
+
+	smp_store_release(&ref->percpu_count_ptr,
+			  ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC);
+}
+
+/**
+ * percpu_ref_switch_to_percpu - switch a percpu_ref to percpu mode
+ * @ref: percpu_ref to switch to percpu mode
+ *
+ * There's no reason to use this function for the usual reference counting.
+ * To re-use an expired ref, use percpu_ref_reinit().
+ *
+ * Switch @ref to percpu mode.  This function may be invoked concurrently
+ * with all the get/put operations and can safely be mixed with kill and
+ * reinit operations.  This function reverses the sticky atomic state set
+ * by PERCPU_REF_INIT_ATOMIC or percpu_ref_switch_to_atomic().  If @ref is
+ * dying or dead, the actual switching takes place on the following
+ * percpu_ref_reinit().
+ *
+ * This function normally doesn't block and can be called from any context
+ * but it may block if @ref is in the process of switching to atomic mode
+ * by percpu_ref_switch_atomic().
+ */
+void percpu_ref_switch_to_percpu(struct percpu_ref *ref)
+{
+	ref->force_atomic = false;
+
+	/* a dying or dead ref can't be switched to percpu mode w/o reinit */
+	if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD))
+		__percpu_ref_switch_to_percpu(ref);
 }
 
 /**
@@ -164,39 +284,48 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
  *
  * Equivalent to percpu_ref_kill() but also schedules kill confirmation if
  * @confirm_kill is not NULL.  @confirm_kill, which may not block, will be
- * called after @ref is seen as dead from all CPUs - all further
- * invocations of percpu_ref_tryget() will fail.  See percpu_ref_tryget()
- * for more details.
+ * called after @ref is seen as dead from all CPUs at which point all
+ * further invocations of percpu_ref_tryget_live() will fail.  See
+ * percpu_ref_tryget_live() for details.
+ *
+ * This function normally doesn't block and can be called from any context
+ * but it may block if @confirm_kill is specified and @ref is in the
+ * process of switching to atomic mode by percpu_ref_switch_atomic().
  *
- * Due to the way percpu_ref is implemented, @confirm_kill will be called
- * after at least one full RCU grace period has passed but this is an
- * implementation detail and callers must not depend on it.
+ * Due to the way percpu_ref is implemented, @confirm_switch will be called
+ * after at least one full sched RCU grace period has passed but this is an
+ * implementation detail and must not be depended upon.
  */
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill)
 {
-	WARN_ONCE(ref->pcpu_count_ptr & PCPU_REF_DEAD,
-		  "percpu_ref_kill() called more than once!\n");
+	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD,
+		  "%s called more than once on %pf!", __func__, ref->release);
 
-	ref->pcpu_count_ptr |= PCPU_REF_DEAD;
-	ref->confirm_kill = confirm_kill;
-
-	call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
+	ref->percpu_count_ptr |= __PERCPU_REF_DEAD;
+	__percpu_ref_switch_to_atomic(ref, confirm_kill);
+	percpu_ref_put(ref);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
 
-/*
- * XXX: Temporary kludge to work around SCSI blk-mq stall.  Used only by
- * block/blk-mq.c::blk_mq_freeze_queue().  Will be removed during v3.18
- * devel cycle.  Do not use anywhere else.
+/**
+ * percpu_ref_reinit - re-initialize a percpu refcount
+ * @ref: perpcu_ref to re-initialize
+ *
+ * Re-initialize @ref so that it's in the same state as when it finished
+ * percpu_ref_init() ignoring %PERCPU_REF_INIT_DEAD.  @ref must have been
+ * initialized successfully and reached 0 but not exited.
+ *
+ * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while
+ * this function is in progress.
  */
-void __percpu_ref_kill_expedited(struct percpu_ref *ref)
+void percpu_ref_reinit(struct percpu_ref *ref)
 {
-	WARN_ONCE(ref->pcpu_count_ptr & PCPU_REF_DEAD,
-		  "percpu_ref_kill() called more than once on %pf!",
-		  ref->release);
+	WARN_ON_ONCE(!percpu_ref_is_zero(ref));
 
-	ref->pcpu_count_ptr |= PCPU_REF_DEAD;
-	synchronize_sched_expedited();
-	percpu_ref_kill_rcu(&ref->rcu);
+	ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD;
+	percpu_ref_get(ref);
+	if (!ref->force_atomic)
+		__percpu_ref_switch_to_percpu(ref);
 }
+EXPORT_SYMBOL_GPL(percpu_ref_reinit);
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 7dd33577b905..48144cdae819 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -112,13 +112,15 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
 }
 EXPORT_SYMBOL(__percpu_counter_sum);
 
-int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
+int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp,
 			  struct lock_class_key *key)
 {
+	unsigned long flags __maybe_unused;
+
 	raw_spin_lock_init(&fbc->lock);
 	lockdep_set_class(&fbc->lock, key);
 	fbc->count = amount;
-	fbc->counters = alloc_percpu(s32);
+	fbc->counters = alloc_percpu_gfp(s32, gfp);
 	if (!fbc->counters)
 		return -ENOMEM;
 
@@ -126,9 +128,9 @@ int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
 
 #ifdef CONFIG_HOTPLUG_CPU
 	INIT_LIST_HEAD(&fbc->list);
-	spin_lock(&percpu_counters_lock);
+	spin_lock_irqsave(&percpu_counters_lock, flags);
 	list_add(&fbc->list, &percpu_counters);
-	spin_unlock(&percpu_counters_lock);
+	spin_unlock_irqrestore(&percpu_counters_lock, flags);
 #endif
 	return 0;
 }
@@ -136,15 +138,17 @@ EXPORT_SYMBOL(__percpu_counter_init);
 
 void percpu_counter_destroy(struct percpu_counter *fbc)
 {
+	unsigned long flags __maybe_unused;
+
 	if (!fbc->counters)
 		return;
 
 	debug_percpu_counter_deactivate(fbc);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	spin_lock(&percpu_counters_lock);
+	spin_lock_irqsave(&percpu_counters_lock, flags);
 	list_del(&fbc->list);
-	spin_unlock(&percpu_counters_lock);
+	spin_unlock_irqrestore(&percpu_counters_lock, flags);
 #endif
 	free_percpu(fbc->counters);
 	fbc->counters = NULL;
@@ -173,7 +177,7 @@ static int percpu_counter_hotcpu_callback(struct notifier_block *nb,
 		return NOTIFY_OK;
 
 	cpu = (unsigned long)hcpu;
-	spin_lock(&percpu_counters_lock);
+	spin_lock_irq(&percpu_counters_lock);
 	list_for_each_entry(fbc, &percpu_counters, list) {
 		s32 *pcount;
 		unsigned long flags;
@@ -184,7 +188,7 @@ static int percpu_counter_hotcpu_callback(struct notifier_block *nb,
 		*pcount = 0;
 		raw_spin_unlock_irqrestore(&fbc->lock, flags);
 	}
-	spin_unlock(&percpu_counters_lock);
+	spin_unlock_irq(&percpu_counters_lock);
 #endif
 	return NOTIFY_OK;
 }
diff --git a/lib/prio_heap.c b/lib/prio_heap.c
deleted file mode 100644
index a7af6f85eca8..000000000000
--- a/lib/prio_heap.c
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * Simple insertion-only static-sized priority heap containing
- * pointers, based on CLR, chapter 7
- */
-
-#include <linux/slab.h>
-#include <linux/prio_heap.h>
-
-int heap_init(struct ptr_heap *heap, size_t size, gfp_t gfp_mask,
-	      int (*gt)(void *, void *))
-{
-	heap->ptrs = kmalloc(size, gfp_mask);
-	if (!heap->ptrs)
-		return -ENOMEM;
-	heap->size = 0;
-	heap->max = size / sizeof(void *);
-	heap->gt = gt;
-	return 0;
-}
-
-void heap_free(struct ptr_heap *heap)
-{
-	kfree(heap->ptrs);
-}
-
-void *heap_insert(struct ptr_heap *heap, void *p)
-{
-	void *res;
-	void **ptrs = heap->ptrs;
-	int pos;
-
-	if (heap->size < heap->max) {
-		/* Heap insertion */
-		pos = heap->size++;
-		while (pos > 0 && heap->gt(p, ptrs[(pos-1)/2])) {
-			ptrs[pos] = ptrs[(pos-1)/2];
-			pos = (pos-1)/2;
-		}
-		ptrs[pos] = p;
-		return NULL;
-	}
-
-	/* The heap is full, so something will have to be dropped */
-
-	/* If the new pointer is greater than the current max, drop it */
-	if (heap->gt(p, ptrs[0]))
-		return p;
-
-	/* Replace the current max and heapify */
-	res = ptrs[0];
-	ptrs[0] = p;
-	pos = 0;
-
-	while (1) {
-		int left = 2 * pos + 1;
-		int right = 2 * pos + 2;
-		int largest = pos;
-		if (left < heap->size && heap->gt(ptrs[left], p))
-			largest = left;
-		if (right < heap->size && heap->gt(ptrs[right], ptrs[largest]))
-			largest = right;
-		if (largest == pos)
-			break;
-		/* Push p down the heap one level and bump one up */
-		ptrs[pos] = ptrs[largest];
-		ptrs[largest] = p;
-		pos = largest;
-	}
-	return res;
-}
diff --git a/lib/proportions.c b/lib/proportions.c
index 05df84801b56..6f724298f67a 100644
--- a/lib/proportions.c
+++ b/lib/proportions.c
@@ -73,7 +73,7 @@
 #include <linux/proportions.h>
 #include <linux/rcupdate.h>
 
-int prop_descriptor_init(struct prop_descriptor *pd, int shift)
+int prop_descriptor_init(struct prop_descriptor *pd, int shift, gfp_t gfp)
 {
 	int err;
 
@@ -83,11 +83,11 @@ int prop_descriptor_init(struct prop_descriptor *pd, int shift)
 	pd->index = 0;
 	pd->pg[0].shift = shift;
 	mutex_init(&pd->mutex);
-	err = percpu_counter_init(&pd->pg[0].events, 0);
+	err = percpu_counter_init(&pd->pg[0].events, 0, gfp);
 	if (err)
 		goto out;
 
-	err = percpu_counter_init(&pd->pg[1].events, 0);
+	err = percpu_counter_init(&pd->pg[1].events, 0, gfp);
 	if (err)
 		percpu_counter_destroy(&pd->pg[0].events);
 
@@ -188,12 +188,12 @@ prop_adjust_shift(int *pl_shift, unsigned long *pl_period, int new_shift)
 
 #define PROP_BATCH (8*(1+ilog2(nr_cpu_ids)))
 
-int prop_local_init_percpu(struct prop_local_percpu *pl)
+int prop_local_init_percpu(struct prop_local_percpu *pl, gfp_t gfp)
 {
 	raw_spin_lock_init(&pl->lock);
 	pl->shift = 0;
 	pl->period = 0;
-	return percpu_counter_init(&pl->events, 0);
+	return percpu_counter_init(&pl->events, 0, gfp);
 }
 
 void prop_local_destroy_percpu(struct prop_local_percpu *pl)
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index f0b1aa3586d1..7d0e5cd7b570 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -121,9 +121,9 @@ static inline const struct raid6_recov_calls *raid6_choose_recov(void)
 		raid6_2data_recov = best->data2;
 		raid6_datap_recov = best->datap;
 
-		printk("raid6: using %s recovery algorithm\n", best->name);
+		pr_info("raid6: using %s recovery algorithm\n", best->name);
 	} else
-		printk("raid6: Yikes! No recovery algorithm found!\n");
+		pr_err("raid6: Yikes! No recovery algorithm found!\n");
 
 	return best;
 }
@@ -157,18 +157,18 @@ static inline const struct raid6_calls *raid6_choose_gen(
 				bestperf = perf;
 				best = *algo;
 			}
-			printk("raid6: %-8s %5ld MB/s\n", (*algo)->name,
+			pr_info("raid6: %-8s %5ld MB/s\n", (*algo)->name,
 			       (perf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2));
 		}
 	}
 
 	if (best) {
-		printk("raid6: using algorithm %s (%ld MB/s)\n",
+		pr_info("raid6: using algorithm %s (%ld MB/s)\n",
 		       best->name,
 		       (bestperf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2));
 		raid6_call = *best;
 	} else
-		printk("raid6: Yikes!  No algorithm found!\n");
+		pr_err("raid6: Yikes!  No algorithm found!\n");
 
 	return best;
 }
@@ -194,7 +194,7 @@ int __init raid6_select_algo(void)
 	syndromes = (void *) __get_free_pages(GFP_KERNEL, 1);
 
 	if (!syndromes) {
-		printk("raid6: Yikes!  No memory available.\n");
+		pr_err("raid6: Yikes!  No memory available.\n");
 		return -ENOMEM;
 	}
 
diff --git a/lib/string.c b/lib/string.c
index f3c6ff596414..2fc20aa06f84 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -27,14 +27,14 @@
 #include <linux/bug.h>
 #include <linux/errno.h>
 
-#ifndef __HAVE_ARCH_STRNICMP
+#ifndef __HAVE_ARCH_STRNCASECMP
 /**
- * strnicmp - Case insensitive, length-limited string comparison
+ * strncasecmp - Case insensitive, length-limited string comparison
  * @s1: One string
  * @s2: The other string
  * @len: the maximum number of characters to compare
  */
-int strnicmp(const char *s1, const char *s2, size_t len)
+int strncasecmp(const char *s1, const char *s2, size_t len)
 {
 	/* Yes, Virginia, it had better be unsigned */
 	unsigned char c1, c2;
@@ -56,6 +56,14 @@ int strnicmp(const char *s1, const char *s2, size_t len)
 	} while (--len);
 	return (int)c1 - (int)c2;
 }
+EXPORT_SYMBOL(strncasecmp);
+#endif
+#ifndef __HAVE_ARCH_STRNICMP
+#undef strnicmp
+int strnicmp(const char *s1, const char *s2, size_t len)
+{
+	return strncasecmp(s1, s2, len);
+}
 EXPORT_SYMBOL(strnicmp);
 #endif
 
@@ -73,20 +81,6 @@ int strcasecmp(const char *s1, const char *s2)
 EXPORT_SYMBOL(strcasecmp);
 #endif
 
-#ifndef __HAVE_ARCH_STRNCASECMP
-int strncasecmp(const char *s1, const char *s2, size_t n)
-{
-	int c1, c2;
-
-	do {
-		c1 = tolower(*s1++);
-		c2 = tolower(*s2++);
-	} while ((--n > 0) && c1 == c2 && c1 != 0);
-	return c1 - c2;
-}
-EXPORT_SYMBOL(strncasecmp);
-#endif
-
 #ifndef __HAVE_ARCH_STRCPY
 /**
  * strcpy - Copy a %NUL terminated string
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index 29033f319aea..58b78ba57439 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -8,6 +8,8 @@
 #include <linux/math64.h>
 #include <linux/export.h>
 #include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/string.h>
 #include <linux/string_helpers.h>
 
 /**
@@ -168,6 +170,44 @@ static bool unescape_special(char **src, char **dst)
 	return true;
 }
 
+/**
+ * string_unescape - unquote characters in the given string
+ * @src:	source buffer (escaped)
+ * @dst:	destination buffer (unescaped)
+ * @size:	size of the destination buffer (0 to unlimit)
+ * @flags:	combination of the flags (bitwise OR):
+ *	%UNESCAPE_SPACE:
+ *		'\f' - form feed
+ *		'\n' - new line
+ *		'\r' - carriage return
+ *		'\t' - horizontal tab
+ *		'\v' - vertical tab
+ *	%UNESCAPE_OCTAL:
+ *		'\NNN' - byte with octal value NNN (1 to 3 digits)
+ *	%UNESCAPE_HEX:
+ *		'\xHH' - byte with hexadecimal value HH (1 to 2 digits)
+ *	%UNESCAPE_SPECIAL:
+ *		'\"' - double quote
+ *		'\\' - backslash
+ *		'\a' - alert (BEL)
+ *		'\e' - escape
+ *	%UNESCAPE_ANY:
+ *		all previous together
+ *
+ * Description:
+ * The function unquotes characters in the given string.
+ *
+ * Because the size of the output will be the same as or less than the size of
+ * the input, the transformation may be performed in place.
+ *
+ * Caller must provide valid source and destination pointers. Be aware that
+ * destination buffer will always be NULL-terminated. Source string must be
+ * NULL-terminated as well.
+ *
+ * Return:
+ * The amount of the characters processed to the destination buffer excluding
+ * trailing '\0' is returned.
+ */
 int string_unescape(char *src, char *dst, size_t size, unsigned int flags)
 {
 	char *out = dst;
@@ -202,3 +242,275 @@ int string_unescape(char *src, char *dst, size_t size, unsigned int flags)
 	return out - dst;
 }
 EXPORT_SYMBOL(string_unescape);
+
+static int escape_passthrough(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+
+	if (*osz < 1)
+		return -ENOMEM;
+
+	*out++ = c;
+
+	*dst = out;
+	*osz -= 1;
+
+	return 1;
+}
+
+static int escape_space(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+	unsigned char to;
+
+	if (*osz < 2)
+		return -ENOMEM;
+
+	switch (c) {
+	case '\n':
+		to = 'n';
+		break;
+	case '\r':
+		to = 'r';
+		break;
+	case '\t':
+		to = 't';
+		break;
+	case '\v':
+		to = 'v';
+		break;
+	case '\f':
+		to = 'f';
+		break;
+	default:
+		return 0;
+	}
+
+	*out++ = '\\';
+	*out++ = to;
+
+	*dst = out;
+	*osz -= 2;
+
+	return 1;
+}
+
+static int escape_special(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+	unsigned char to;
+
+	if (*osz < 2)
+		return -ENOMEM;
+
+	switch (c) {
+	case '\\':
+		to = '\\';
+		break;
+	case '\a':
+		to = 'a';
+		break;
+	case '\e':
+		to = 'e';
+		break;
+	default:
+		return 0;
+	}
+
+	*out++ = '\\';
+	*out++ = to;
+
+	*dst = out;
+	*osz -= 2;
+
+	return 1;
+}
+
+static int escape_null(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+
+	if (*osz < 2)
+		return -ENOMEM;
+
+	if (c)
+		return 0;
+
+	*out++ = '\\';
+	*out++ = '0';
+
+	*dst = out;
+	*osz -= 2;
+
+	return 1;
+}
+
+static int escape_octal(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+
+	if (*osz < 4)
+		return -ENOMEM;
+
+	*out++ = '\\';
+	*out++ = ((c >> 6) & 0x07) + '0';
+	*out++ = ((c >> 3) & 0x07) + '0';
+	*out++ = ((c >> 0) & 0x07) + '0';
+
+	*dst = out;
+	*osz -= 4;
+
+	return 1;
+}
+
+static int escape_hex(unsigned char c, char **dst, size_t *osz)
+{
+	char *out = *dst;
+
+	if (*osz < 4)
+		return -ENOMEM;
+
+	*out++ = '\\';
+	*out++ = 'x';
+	*out++ = hex_asc_hi(c);
+	*out++ = hex_asc_lo(c);
+
+	*dst = out;
+	*osz -= 4;
+
+	return 1;
+}
+
+/**
+ * string_escape_mem - quote characters in the given memory buffer
+ * @src:	source buffer (unescaped)
+ * @isz:	source buffer size
+ * @dst:	destination buffer (escaped)
+ * @osz:	destination buffer size
+ * @flags:	combination of the flags (bitwise OR):
+ *	%ESCAPE_SPACE:
+ *		'\f' - form feed
+ *		'\n' - new line
+ *		'\r' - carriage return
+ *		'\t' - horizontal tab
+ *		'\v' - vertical tab
+ *	%ESCAPE_SPECIAL:
+ *		'\\' - backslash
+ *		'\a' - alert (BEL)
+ *		'\e' - escape
+ *	%ESCAPE_NULL:
+ *		'\0' - null
+ *	%ESCAPE_OCTAL:
+ *		'\NNN' - byte with octal value NNN (3 digits)
+ *	%ESCAPE_ANY:
+ *		all previous together
+ *	%ESCAPE_NP:
+ *		escape only non-printable characters (checked by isprint)
+ *	%ESCAPE_ANY_NP:
+ *		all previous together
+ *	%ESCAPE_HEX:
+ *		'\xHH' - byte with hexadecimal value HH (2 digits)
+ * @esc:	NULL-terminated string of characters any of which, if found in
+ *		the source, has to be escaped
+ *
+ * Description:
+ * The process of escaping byte buffer includes several parts. They are applied
+ * in the following sequence.
+ *	1. The character is matched to the printable class, if asked, and in
+ *	   case of match it passes through to the output.
+ *	2. The character is not matched to the one from @esc string and thus
+ *	   must go as is to the output.
+ *	3. The character is checked if it falls into the class given by @flags.
+ *	   %ESCAPE_OCTAL and %ESCAPE_HEX are going last since they cover any
+ *	   character. Note that they actually can't go together, otherwise
+ *	   %ESCAPE_HEX will be ignored.
+ *
+ * Caller must provide valid source and destination pointers. Be aware that
+ * destination buffer will not be NULL-terminated, thus caller have to append
+ * it if needs.
+ *
+ * Return:
+ * The amount of the characters processed to the destination buffer, or
+ * %-ENOMEM if the size of buffer is not enough to put an escaped character is
+ * returned.
+ *
+ * Even in the case of error @dst pointer will be updated to point to the byte
+ * after the last processed character.
+ */
+int string_escape_mem(const char *src, size_t isz, char **dst, size_t osz,
+		      unsigned int flags, const char *esc)
+{
+	char *out = *dst, *p = out;
+	bool is_dict = esc && *esc;
+	int ret = 0;
+
+	while (isz--) {
+		unsigned char c = *src++;
+
+		/*
+		 * Apply rules in the following sequence:
+		 *	- the character is printable, when @flags has
+		 *	  %ESCAPE_NP bit set
+		 *	- the @esc string is supplied and does not contain a
+		 *	  character under question
+		 *	- the character doesn't fall into a class of symbols
+		 *	  defined by given @flags
+		 * In these cases we just pass through a character to the
+		 * output buffer.
+		 */
+		if ((flags & ESCAPE_NP && isprint(c)) ||
+		    (is_dict && !strchr(esc, c))) {
+			/* do nothing */
+		} else {
+			if (flags & ESCAPE_SPACE) {
+				ret = escape_space(c, &p, &osz);
+				if (ret < 0)
+					break;
+				if (ret > 0)
+					continue;
+			}
+
+			if (flags & ESCAPE_SPECIAL) {
+				ret = escape_special(c, &p, &osz);
+				if (ret < 0)
+					break;
+				if (ret > 0)
+					continue;
+			}
+
+			if (flags & ESCAPE_NULL) {
+				ret = escape_null(c, &p, &osz);
+				if (ret < 0)
+					break;
+				if (ret > 0)
+					continue;
+			}
+
+			/* ESCAPE_OCTAL and ESCAPE_HEX always go last */
+			if (flags & ESCAPE_OCTAL) {
+				ret = escape_octal(c, &p, &osz);
+				if (ret < 0)
+					break;
+				continue;
+			}
+			if (flags & ESCAPE_HEX) {
+				ret = escape_hex(c, &p, &osz);
+				if (ret < 0)
+					break;
+				continue;
+			}
+		}
+
+		ret = escape_passthrough(c, &p, &osz);
+		if (ret < 0)
+			break;
+	}
+
+	*dst = p;
+
+	if (ret < 0)
+		return ret;
+
+	return p - out;
+}
+EXPORT_SYMBOL(string_escape_mem);
diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c
index 6ac48de04c0e..ab0d30e1e18f 100644
--- a/lib/test-string_helpers.c
+++ b/lib/test-string_helpers.c
@@ -5,11 +5,32 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/string.h>
 #include <linux/string_helpers.h>
 
+static __init bool test_string_check_buf(const char *name, unsigned int flags,
+					 char *in, size_t p,
+					 char *out_real, size_t q_real,
+					 char *out_test, size_t q_test)
+{
+	if (q_real == q_test && !memcmp(out_test, out_real, q_test))
+		return true;
+
+	pr_warn("Test '%s' failed: flags = %u\n", name, flags);
+
+	print_hex_dump(KERN_WARNING, "Input: ", DUMP_PREFIX_NONE, 16, 1,
+		       in, p, true);
+	print_hex_dump(KERN_WARNING, "Expected: ", DUMP_PREFIX_NONE, 16, 1,
+		       out_test, q_test, true);
+	print_hex_dump(KERN_WARNING, "Got: ", DUMP_PREFIX_NONE, 16, 1,
+		       out_real, q_real, true);
+
+	return false;
+}
+
 struct test_string {
 	const char *in;
 	const char *out;
@@ -39,12 +60,17 @@ static const struct test_string strings[] __initconst = {
 	},
 };
 
-static void __init test_string_unescape(unsigned int flags, bool inplace)
+static void __init test_string_unescape(const char *name, unsigned int flags,
+					bool inplace)
 {
-	char in[256];
-	char out_test[256];
-	char out_real[256];
-	int i, p = 0, q_test = 0, q_real = sizeof(out_real);
+	int q_real = 256;
+	char *in = kmalloc(q_real, GFP_KERNEL);
+	char *out_test = kmalloc(q_real, GFP_KERNEL);
+	char *out_real = kmalloc(q_real, GFP_KERNEL);
+	int i, p = 0, q_test = 0;
+
+	if (!in || !out_test || !out_real)
+		goto out;
 
 	for (i = 0; i < ARRAY_SIZE(strings); i++) {
 		const char *s = strings[i].in;
@@ -77,15 +103,225 @@ static void __init test_string_unescape(unsigned int flags, bool inplace)
 		q_real = string_unescape(in, out_real, q_real, flags);
 	}
 
-	if (q_real != q_test || memcmp(out_test, out_real, q_test)) {
-		pr_warn("Test failed: flags = %u\n", flags);
-		print_hex_dump(KERN_WARNING, "Input: ",
-			       DUMP_PREFIX_NONE, 16, 1, in, p - 1, true);
-		print_hex_dump(KERN_WARNING, "Expected: ",
-			       DUMP_PREFIX_NONE, 16, 1, out_test, q_test, true);
-		print_hex_dump(KERN_WARNING, "Got: ",
-			       DUMP_PREFIX_NONE, 16, 1, out_real, q_real, true);
+	test_string_check_buf(name, flags, in, p - 1, out_real, q_real,
+			      out_test, q_test);
+out:
+	kfree(out_real);
+	kfree(out_test);
+	kfree(in);
+}
+
+struct test_string_1 {
+	const char *out;
+	unsigned int flags;
+};
+
+#define	TEST_STRING_2_MAX_S1		32
+struct test_string_2 {
+	const char *in;
+	struct test_string_1 s1[TEST_STRING_2_MAX_S1];
+};
+
+#define	TEST_STRING_2_DICT_0		NULL
+static const struct test_string_2 escape0[] __initconst = {{
+	.in = "\f\\ \n\r\t\v",
+	.s1 = {{
+		.out = "\\f\\ \\n\\r\\t\\v",
+		.flags = ESCAPE_SPACE,
+	},{
+		.out = "\\f\\134\\040\\n\\r\\t\\v",
+		.flags = ESCAPE_SPACE | ESCAPE_OCTAL,
+	},{
+		.out = "\\f\\x5c\\x20\\n\\r\\t\\v",
+		.flags = ESCAPE_SPACE | ESCAPE_HEX,
+	},{
+		/* terminator */
+	}},
+},{
+	.in = "\\h\\\"\a\e\\",
+	.s1 = {{
+		.out = "\\\\h\\\\\"\\a\\e\\\\",
+		.flags = ESCAPE_SPECIAL,
+	},{
+		.out = "\\\\\\150\\\\\\042\\a\\e\\\\",
+		.flags = ESCAPE_SPECIAL | ESCAPE_OCTAL,
+	},{
+		.out = "\\\\\\x68\\\\\\x22\\a\\e\\\\",
+		.flags = ESCAPE_SPECIAL | ESCAPE_HEX,
+	},{
+		/* terminator */
+	}},
+},{
+	.in = "\eb \\C\007\"\x90\r]",
+	.s1 = {{
+		.out = "\eb \\C\007\"\x90\\r]",
+		.flags = ESCAPE_SPACE,
+	},{
+		.out = "\\eb \\\\C\\a\"\x90\r]",
+		.flags = ESCAPE_SPECIAL,
+	},{
+		.out = "\\eb \\\\C\\a\"\x90\\r]",
+		.flags = ESCAPE_SPACE | ESCAPE_SPECIAL,
+	},{
+		.out = "\\033\\142\\040\\134\\103\\007\\042\\220\\015\\135",
+		.flags = ESCAPE_OCTAL,
+	},{
+		.out = "\\033\\142\\040\\134\\103\\007\\042\\220\\r\\135",
+		.flags = ESCAPE_SPACE | ESCAPE_OCTAL,
+	},{
+		.out = "\\e\\142\\040\\\\\\103\\a\\042\\220\\015\\135",
+		.flags = ESCAPE_SPECIAL | ESCAPE_OCTAL,
+	},{
+		.out = "\\e\\142\\040\\\\\\103\\a\\042\\220\\r\\135",
+		.flags = ESCAPE_SPACE | ESCAPE_SPECIAL | ESCAPE_OCTAL,
+	},{
+		.out = "\eb \\C\007\"\x90\r]",
+		.flags = ESCAPE_NP,
+	},{
+		.out = "\eb \\C\007\"\x90\\r]",
+		.flags = ESCAPE_SPACE | ESCAPE_NP,
+	},{
+		.out = "\\eb \\C\\a\"\x90\r]",
+		.flags = ESCAPE_SPECIAL | ESCAPE_NP,
+	},{
+		.out = "\\eb \\C\\a\"\x90\\r]",
+		.flags = ESCAPE_SPACE | ESCAPE_SPECIAL | ESCAPE_NP,
+	},{
+		.out = "\\033b \\C\\007\"\\220\\015]",
+		.flags = ESCAPE_OCTAL | ESCAPE_NP,
+	},{
+		.out = "\\033b \\C\\007\"\\220\\r]",
+		.flags = ESCAPE_SPACE | ESCAPE_OCTAL | ESCAPE_NP,
+	},{
+		.out = "\\eb \\C\\a\"\\220\\r]",
+		.flags = ESCAPE_SPECIAL | ESCAPE_SPACE | ESCAPE_OCTAL |
+			 ESCAPE_NP,
+	},{
+		.out = "\\x1bb \\C\\x07\"\\x90\\x0d]",
+		.flags = ESCAPE_NP | ESCAPE_HEX,
+	},{
+		/* terminator */
+	}},
+},{
+	/* terminator */
+}};
+
+#define	TEST_STRING_2_DICT_1		"b\\ \t\r"
+static const struct test_string_2 escape1[] __initconst = {{
+	.in = "\f\\ \n\r\t\v",
+	.s1 = {{
+		.out = "\f\\134\\040\n\\015\\011\v",
+		.flags = ESCAPE_OCTAL,
+	},{
+		.out = "\f\\x5c\\x20\n\\x0d\\x09\v",
+		.flags = ESCAPE_HEX,
+	},{
+		/* terminator */
+	}},
+},{
+	.in = "\\h\\\"\a\e\\",
+	.s1 = {{
+		.out = "\\134h\\134\"\a\e\\134",
+		.flags = ESCAPE_OCTAL,
+	},{
+		/* terminator */
+	}},
+},{
+	.in = "\eb \\C\007\"\x90\r]",
+	.s1 = {{
+		.out = "\e\\142\\040\\134C\007\"\x90\\015]",
+		.flags = ESCAPE_OCTAL,
+	},{
+		/* terminator */
+	}},
+},{
+	/* terminator */
+}};
+
+static __init const char *test_string_find_match(const struct test_string_2 *s2,
+						 unsigned int flags)
+{
+	const struct test_string_1 *s1 = s2->s1;
+	unsigned int i;
+
+	if (!flags)
+		return s2->in;
+
+	/* Test cases are NULL-aware */
+	flags &= ~ESCAPE_NULL;
+
+	/* ESCAPE_OCTAL has a higher priority */
+	if (flags & ESCAPE_OCTAL)
+		flags &= ~ESCAPE_HEX;
+
+	for (i = 0; i < TEST_STRING_2_MAX_S1 && s1->out; i++, s1++)
+		if (s1->flags == flags)
+			return s1->out;
+	return NULL;
+}
+
+static __init void test_string_escape(const char *name,
+				      const struct test_string_2 *s2,
+				      unsigned int flags, const char *esc)
+{
+	int q_real = 512;
+	char *out_test = kmalloc(q_real, GFP_KERNEL);
+	char *out_real = kmalloc(q_real, GFP_KERNEL);
+	char *in = kmalloc(256, GFP_KERNEL);
+	char *buf = out_real;
+	int p = 0, q_test = 0;
+
+	if (!out_test || !out_real || !in)
+		goto out;
+
+	for (; s2->in; s2++) {
+		const char *out;
+		int len;
+
+		/* NULL injection */
+		if (flags & ESCAPE_NULL) {
+			in[p++] = '\0';
+			out_test[q_test++] = '\\';
+			out_test[q_test++] = '0';
+		}
+
+		/* Don't try strings that have no output */
+		out = test_string_find_match(s2, flags);
+		if (!out)
+			continue;
+
+		/* Copy string to in buffer */
+		len = strlen(s2->in);
+		memcpy(&in[p], s2->in, len);
+		p += len;
+
+		/* Copy expected result for given flags */
+		len = strlen(out);
+		memcpy(&out_test[q_test], out, len);
+		q_test += len;
 	}
+
+	q_real = string_escape_mem(in, p, &buf, q_real, flags, esc);
+
+	test_string_check_buf(name, flags, in, p, out_real, q_real, out_test,
+			      q_test);
+out:
+	kfree(in);
+	kfree(out_real);
+	kfree(out_test);
+}
+
+static __init void test_string_escape_nomem(void)
+{
+	char *in = "\eb \\C\007\"\x90\r]";
+	char out[64], *buf = out;
+	int rc = -ENOMEM, ret;
+
+	ret = string_escape_str_any_np(in, &buf, strlen(in), NULL);
+	if (ret == rc)
+		return;
+
+	pr_err("Test 'escape nomem' failed: got %d instead of %d\n", ret, rc);
 }
 
 static int __init test_string_helpers_init(void)
@@ -94,8 +330,19 @@ static int __init test_string_helpers_init(void)
 
 	pr_info("Running tests...\n");
 	for (i = 0; i < UNESCAPE_ANY + 1; i++)
-		test_string_unescape(i, false);
-	test_string_unescape(get_random_int() % (UNESCAPE_ANY + 1), true);
+		test_string_unescape("unescape", i, false);
+	test_string_unescape("unescape inplace",
+			     get_random_int() % (UNESCAPE_ANY + 1), true);
+
+	/* Without dictionary */
+	for (i = 0; i < (ESCAPE_ANY_NP | ESCAPE_HEX) + 1; i++)
+		test_string_escape("escape 0", escape0, i, TEST_STRING_2_DICT_0);
+
+	/* With dictionary */
+	for (i = 0; i < (ESCAPE_ANY_NP | ESCAPE_HEX) + 1; i++)
+		test_string_escape("escape 1", escape1, i, TEST_STRING_2_DICT_1);
+
+	test_string_escape_nomem();
 
 	return -EINVAL;
 }
diff --git a/lib/textsearch.c b/lib/textsearch.c
index 0c7e9ab2d88f..0b79908dfe89 100644
--- a/lib/textsearch.c
+++ b/lib/textsearch.c
@@ -249,9 +249,7 @@ EXPORT_SYMBOL(textsearch_find_continuous);
  * @flags: search flags
  *
  * Looks up the search algorithm module and creates a new textsearch
- * configuration for the specified pattern. Upon completion all
- * necessary refcnts are held and the configuration must be put back
- * using textsearch_put() after usage.
+ * configuration for the specified pattern.
  *
  * Note: The format of the pattern may not be compatible between
  *       the various search algorithms.
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index ba3cd0a35640..ec337f64f52d 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -33,6 +33,7 @@
 #include <asm/page.h>		/* for PAGE_SIZE */
 #include <asm/sections.h>	/* for dereference_function_descriptor() */
 
+#include <linux/string_helpers.h>
 #include "kstrtox.h"
 
 /**
@@ -1101,6 +1102,62 @@ char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa,
 }
 
 static noinline_for_stack
+char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec,
+		     const char *fmt)
+{
+	bool found = true;
+	int count = 1;
+	unsigned int flags = 0;
+	int len;
+
+	if (spec.field_width == 0)
+		return buf;				/* nothing to print */
+
+	if (ZERO_OR_NULL_PTR(addr))
+		return string(buf, end, NULL, spec);	/* NULL pointer */
+
+
+	do {
+		switch (fmt[count++]) {
+		case 'a':
+			flags |= ESCAPE_ANY;
+			break;
+		case 'c':
+			flags |= ESCAPE_SPECIAL;
+			break;
+		case 'h':
+			flags |= ESCAPE_HEX;
+			break;
+		case 'n':
+			flags |= ESCAPE_NULL;
+			break;
+		case 'o':
+			flags |= ESCAPE_OCTAL;
+			break;
+		case 'p':
+			flags |= ESCAPE_NP;
+			break;
+		case 's':
+			flags |= ESCAPE_SPACE;
+			break;
+		default:
+			found = false;
+			break;
+		}
+	} while (found);
+
+	if (!flags)
+		flags = ESCAPE_ANY_NP;
+
+	len = spec.field_width < 0 ? 1 : spec.field_width;
+
+	/* Ignore the error. We print as many characters as we can */
+	string_escape_mem(addr, len, &buf, end - buf, flags, NULL);
+
+	return buf;
+}
+
+static noinline_for_stack
 char *uuid_string(char *buf, char *end, const u8 *addr,
 		  struct printf_spec spec, const char *fmt)
 {
@@ -1221,6 +1278,17 @@ int kptr_restrict __read_mostly;
  * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order
  * - 'I[6S]c' for IPv6 addresses printed as specified by
  *       http://tools.ietf.org/html/rfc5952
+ * - 'E[achnops]' For an escaped buffer, where rules are defined by combination
+ *                of the following flags (see string_escape_mem() for the
+ *                details):
+ *                  a - ESCAPE_ANY
+ *                  c - ESCAPE_SPECIAL
+ *                  h - ESCAPE_HEX
+ *                  n - ESCAPE_NULL
+ *                  o - ESCAPE_OCTAL
+ *                  p - ESCAPE_NP
+ *                  s - ESCAPE_SPACE
+ *                By default ESCAPE_ANY_NP is used.
  * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form
  *       "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
  *       Options for %pU are:
@@ -1321,6 +1389,8 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 			}}
 		}
 		break;
+	case 'E':
+		return escaped_string(buf, end, ptr, spec, fmt);
 	case 'U':
 		return uuid_string(buf, end, ptr, spec, fmt);
 	case 'V':
@@ -1633,6 +1703,7 @@ qualifier:
  * %piS depending on sa_family of 'struct sockaddr *' print IPv4/IPv6 address
  * %pU[bBlL] print a UUID/GUID in big or little endian using lower or upper
  *   case.
+ * %*pE[achnops] print an escaped buffer
  * %*ph[CDN] a variable-length hex string with a separator (supports up to 64
  *           bytes of the input)
  * %n is ignored
diff --git a/mm/Kconfig b/mm/Kconfig
index 886db2158538..1d1ae6b078fd 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -137,6 +137,9 @@ config HAVE_MEMBLOCK_NODE_MAP
 config HAVE_MEMBLOCK_PHYS_MAP
 	boolean
 
+config HAVE_GENERIC_RCU_GUP
+	boolean
+
 config ARCH_DISCARD_MEMBLOCK
 	boolean
 
@@ -228,11 +231,16 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 	boolean
 
 #
+# support for memory balloon
+config MEMORY_BALLOON
+	boolean
+
+#
 # support for memory balloon compaction
 config BALLOON_COMPACTION
 	bool "Allow for balloon memory compaction/migration"
 	def_bool y
-	depends on COMPACTION && VIRTIO_BALLOON
+	depends on COMPACTION && MEMORY_BALLOON
 	help
 	  Memory fragmentation introduced by ballooning might reduce
 	  significantly the number of 2MB contiguous memory blocks that can be
diff --git a/mm/Makefile b/mm/Makefile
index fe7a053c0f45..8405eb0023a9 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -16,9 +16,9 @@ obj-y			:= filemap.o mempool.o oom_kill.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
-			   compaction.o balloon_compaction.o vmacache.o \
+			   compaction.o vmacache.o \
 			   interval_tree.o list_lru.o workingset.o \
-			   iov_iter.o $(mmu-y)
+			   iov_iter.o debug.o $(mmu-y)
 
 obj-y += init-mm.o
 
@@ -28,8 +28,9 @@ else
 	obj-y		+= bootmem.o
 endif
 
+obj-$(CONFIG_ADVISE_SYSCALLS)	+= fadvise.o
 ifdef CONFIG_MMU
-	obj-$(CONFIG_ADVISE_SYSCALLS)	+= fadvise.o madvise.o
+	obj-$(CONFIG_ADVISE_SYSCALLS)	+= madvise.o
 endif
 obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
 
@@ -67,3 +68,4 @@ obj-$(CONFIG_ZBUD)	+= zbud.o
 obj-$(CONFIG_ZSMALLOC)	+= zsmalloc.o
 obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o
 obj-$(CONFIG_CMA)	+= cma.o
+obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1706cbbdf5f0..0ae0df55000b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -40,7 +40,7 @@ LIST_HEAD(bdi_list);
 /* bdi_wq serves all asynchronous writeback tasks */
 struct workqueue_struct *bdi_wq;
 
-void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+static void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
 {
 	if (wb1 < wb2) {
 		spin_lock(&wb1->list_lock);
@@ -376,13 +376,7 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
 	flush_delayed_work(&bdi->wb.dwork);
 	WARN_ON(!list_empty(&bdi->work_list));
-
-	/*
-	 * This shouldn't be necessary unless @bdi for some reason has
-	 * unflushed dirty IO after work_list is drained.  Do it anyway
-	 * just in case.
-	 */
-	cancel_delayed_work_sync(&bdi->wb.dwork);
+	WARN_ON(delayed_work_pending(&bdi->wb.dwork));
 }
 
 /*
@@ -402,21 +396,15 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 
 void bdi_unregister(struct backing_dev_info *bdi)
 {
-	struct device *dev = bdi->dev;
-
-	if (dev) {
+	if (bdi->dev) {
 		bdi_set_min_ratio(bdi, 0);
 		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
 
 		bdi_wb_shutdown(bdi);
 		bdi_debug_unregister(bdi);
-
-		spin_lock_bh(&bdi->wb_lock);
+		device_unregister(bdi->dev);
 		bdi->dev = NULL;
-		spin_unlock_bh(&bdi->wb_lock);
-
-		device_unregister(dev);
 	}
 }
 EXPORT_SYMBOL(bdi_unregister);
@@ -455,7 +443,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi_wb_init(&bdi->wb, bdi);
 
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
-		err = percpu_counter_init(&bdi->bdi_stat[i], 0);
+		err = percpu_counter_init(&bdi->bdi_stat[i], 0, GFP_KERNEL);
 		if (err)
 			goto err;
 	}
@@ -470,7 +458,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi->write_bandwidth = INIT_BW;
 	bdi->avg_write_bandwidth = INIT_BW;
 
-	err = fprop_local_init_percpu(&bdi->completions);
+	err = fprop_local_init_percpu(&bdi->completions, GFP_KERNEL);
 
 	if (err) {
 err:
@@ -487,8 +475,17 @@ void bdi_destroy(struct backing_dev_info *bdi)
 	int i;
 
 	/*
-	 * Splice our entries to the default_backing_dev_info, if this
-	 * bdi disappears
+	 * Splice our entries to the default_backing_dev_info.  This
+	 * condition shouldn't happen.  @wb must be empty at this point and
+	 * dirty inodes on it might cause other issues.  This workaround is
+	 * added by ce5f8e779519 ("writeback: splice dirty inode entries to
+	 * default bdi on bdi_destroy()") without root-causing the issue.
+	 *
+	 * http://lkml.kernel.org/g/1253038617-30204-11-git-send-email-jens.axboe@oracle.com
+	 * http://thread.gmane.org/gmane.linux.file-systems/35341/focus=35350
+	 *
+	 * We should probably add WARN_ON() to find out whether it still
+	 * happens and track it down if so.
 	 */
 	if (bdi_has_dirty_io(bdi)) {
 		struct bdi_writeback *dst = &default_backing_dev_info.wb;
@@ -503,12 +500,7 @@ void bdi_destroy(struct backing_dev_info *bdi)
 
 	bdi_unregister(bdi);
 
-	/*
-	 * If bdi_unregister() had already been called earlier, the dwork
-	 * could still be pending because bdi_prune_sb() can race with the
-	 * bdi_wakeup_thread_delayed() calls from __mark_inode_dirty().
-	 */
-	cancel_delayed_work_sync(&bdi->wb.dwork);
+	WARN_ON(delayed_work_pending(&bdi->wb.dwork));
 
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
 		percpu_counter_destroy(&bdi->bdi_stat[i]);
@@ -631,7 +623,7 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout)
 	 * of sleeping on the congestion queue
 	 */
 	if (atomic_read(&nr_bdi_congested[sync]) == 0 ||
-			!zone_is_reclaim_congested(zone)) {
+	    !test_bit(ZONE_CONGESTED, &zone->flags)) {
 		cond_resched();
 
 		/* In case we scheduled, work out time remaining */
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index 6e45a5074bf0..b3cbe19f71b5 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -11,32 +11,6 @@
 #include <linux/balloon_compaction.h>
 
 /*
- * balloon_devinfo_alloc - allocates a balloon device information descriptor.
- * @balloon_dev_descriptor: pointer to reference the balloon device which
- *                          this struct balloon_dev_info will be servicing.
- *
- * Driver must call it to properly allocate and initialize an instance of
- * struct balloon_dev_info which will be used to reference a balloon device
- * as well as to keep track of the balloon device page list.
- */
-struct balloon_dev_info *balloon_devinfo_alloc(void *balloon_dev_descriptor)
-{
-	struct balloon_dev_info *b_dev_info;
-	b_dev_info = kmalloc(sizeof(*b_dev_info), GFP_KERNEL);
-	if (!b_dev_info)
-		return ERR_PTR(-ENOMEM);
-
-	b_dev_info->balloon_device = balloon_dev_descriptor;
-	b_dev_info->mapping = NULL;
-	b_dev_info->isolated_pages = 0;
-	spin_lock_init(&b_dev_info->pages_lock);
-	INIT_LIST_HEAD(&b_dev_info->pages);
-
-	return b_dev_info;
-}
-EXPORT_SYMBOL_GPL(balloon_devinfo_alloc);
-
-/*
  * balloon_page_enqueue - allocates a new page and inserts it into the balloon
  *			  page list.
  * @b_dev_info: balloon device decriptor where we will insert a new page to
@@ -61,7 +35,8 @@ struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
 	 */
 	BUG_ON(!trylock_page(page));
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
-	balloon_page_insert(page, b_dev_info->mapping, &b_dev_info->pages);
+	balloon_page_insert(b_dev_info, page);
+	__count_vm_event(BALLOON_INFLATE);
 	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 	unlock_page(page);
 	return page;
@@ -93,18 +68,14 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
 		 * to be released by the balloon driver.
 		 */
 		if (trylock_page(page)) {
+			if (!PagePrivate(page)) {
+				/* raced with isolation */
+				unlock_page(page);
+				continue;
+			}
 			spin_lock_irqsave(&b_dev_info->pages_lock, flags);
-			/*
-			 * Raise the page refcount here to prevent any wrong
-			 * attempt to isolate this page, in case of coliding
-			 * with balloon_page_isolate() just after we release
-			 * the page lock.
-			 *
-			 * balloon_page_free() will take care of dropping
-			 * this extra refcount later.
-			 */
-			get_page(page);
 			balloon_page_delete(page);
+			__count_vm_event(BALLOON_DEFLATE);
 			spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 			unlock_page(page);
 			dequeued_page = true;
@@ -132,62 +103,14 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
 EXPORT_SYMBOL_GPL(balloon_page_dequeue);
 
 #ifdef CONFIG_BALLOON_COMPACTION
-/*
- * balloon_mapping_alloc - allocates a special ->mapping for ballooned pages.
- * @b_dev_info: holds the balloon device information descriptor.
- * @a_ops: balloon_mapping address_space_operations descriptor.
- *
- * Driver must call it to properly allocate and initialize an instance of
- * struct address_space which will be used as the special page->mapping for
- * balloon device enlisted page instances.
- */
-struct address_space *balloon_mapping_alloc(struct balloon_dev_info *b_dev_info,
-				const struct address_space_operations *a_ops)
-{
-	struct address_space *mapping;
-
-	mapping = kmalloc(sizeof(*mapping), GFP_KERNEL);
-	if (!mapping)
-		return ERR_PTR(-ENOMEM);
-
-	/*
-	 * Give a clean 'zeroed' status to all elements of this special
-	 * balloon page->mapping struct address_space instance.
-	 */
-	address_space_init_once(mapping);
-
-	/*
-	 * Set mapping->flags appropriately, to allow balloon pages
-	 * ->mapping identification.
-	 */
-	mapping_set_balloon(mapping);
-	mapping_set_gfp_mask(mapping, balloon_mapping_gfp_mask());
-
-	/* balloon's page->mapping->a_ops callback descriptor */
-	mapping->a_ops = a_ops;
-
-	/*
-	 * Establish a pointer reference back to the balloon device descriptor
-	 * this particular page->mapping will be servicing.
-	 * This is used by compaction / migration procedures to identify and
-	 * access the balloon device pageset while isolating / migrating pages.
-	 *
-	 * As some balloon drivers can register multiple balloon devices
-	 * for a single guest, this also helps compaction / migration to
-	 * properly deal with multiple balloon pagesets, when required.
-	 */
-	mapping->private_data = b_dev_info;
-	b_dev_info->mapping = mapping;
-
-	return mapping;
-}
-EXPORT_SYMBOL_GPL(balloon_mapping_alloc);
 
 static inline void __isolate_balloon_page(struct page *page)
 {
-	struct balloon_dev_info *b_dev_info = page->mapping->private_data;
+	struct balloon_dev_info *b_dev_info = balloon_page_device(page);
 	unsigned long flags;
+
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	ClearPagePrivate(page);
 	list_del(&page->lru);
 	b_dev_info->isolated_pages++;
 	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
@@ -195,20 +118,16 @@ static inline void __isolate_balloon_page(struct page *page)
 
 static inline void __putback_balloon_page(struct page *page)
 {
-	struct balloon_dev_info *b_dev_info = page->mapping->private_data;
+	struct balloon_dev_info *b_dev_info = balloon_page_device(page);
 	unsigned long flags;
+
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	SetPagePrivate(page);
 	list_add(&page->lru, &b_dev_info->pages);
 	b_dev_info->isolated_pages--;
 	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 }
 
-static inline int __migrate_balloon_page(struct address_space *mapping,
-		struct page *newpage, struct page *page, enum migrate_mode mode)
-{
-	return page->mapping->a_ops->migratepage(mapping, newpage, page, mode);
-}
-
 /* __isolate_lru_page() counterpart for a ballooned page */
 bool balloon_page_isolate(struct page *page)
 {
@@ -235,12 +154,11 @@ bool balloon_page_isolate(struct page *page)
 		 */
 		if (likely(trylock_page(page))) {
 			/*
-			 * A ballooned page, by default, has just one refcount.
+			 * A ballooned page, by default, has PagePrivate set.
 			 * Prevent concurrent compaction threads from isolating
-			 * an already isolated balloon page by refcount check.
+			 * an already isolated balloon page by clearing it.
 			 */
-			if (__is_movable_balloon_page(page) &&
-			    page_count(page) == 2) {
+			if (balloon_page_movable(page)) {
 				__isolate_balloon_page(page);
 				unlock_page(page);
 				return true;
@@ -276,7 +194,7 @@ void balloon_page_putback(struct page *page)
 int balloon_page_migrate(struct page *newpage,
 			 struct page *page, enum migrate_mode mode)
 {
-	struct address_space *mapping;
+	struct balloon_dev_info *balloon = balloon_page_device(page);
 	int rc = -EAGAIN;
 
 	/*
@@ -292,9 +210,8 @@ int balloon_page_migrate(struct page *newpage,
 		return rc;
 	}
 
-	mapping = page->mapping;
-	if (mapping)
-		rc = __migrate_balloon_page(mapping, newpage, page, mode);
+	if (balloon && balloon->migratepage)
+		rc = balloon->migratepage(balloon, newpage, page, mode);
 
 	unlock_page(newpage);
 	return rc;
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 90bd3507b413..8a000cebb0d7 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -16,9 +16,9 @@
 #include <linux/kmemleak.h>
 #include <linux/range.h>
 #include <linux/memblock.h>
+#include <linux/bug.h>
+#include <linux/io.h>
 
-#include <asm/bug.h>
-#include <asm/io.h>
 #include <asm/processor.h>
 
 #include "internal.h"
diff --git a/mm/cma.c b/mm/cma.c
index c17751c0dcaf..963bc4add9af 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -32,6 +32,7 @@
 #include <linux/slab.h>
 #include <linux/log2.h>
 #include <linux/cma.h>
+#include <linux/highmem.h>
 
 struct cma {
 	unsigned long	base_pfn;
@@ -57,7 +58,9 @@ unsigned long cma_get_size(struct cma *cma)
 
 static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order)
 {
-	return (1UL << (align_order >> cma->order_per_bit)) - 1;
+	if (align_order <= cma->order_per_bit)
+		return 0;
+	return (1UL << (align_order - cma->order_per_bit)) - 1;
 }
 
 static unsigned long cma_bitmap_maxno(struct cma *cma)
@@ -140,6 +143,54 @@ static int __init cma_init_reserved_areas(void)
 core_initcall(cma_init_reserved_areas);
 
 /**
+ * cma_init_reserved_mem() - create custom contiguous area from reserved memory
+ * @base: Base address of the reserved area
+ * @size: Size of the reserved area (in bytes),
+ * @order_per_bit: Order of pages represented by one bit on bitmap.
+ * @res_cma: Pointer to store the created cma region.
+ *
+ * This function creates custom contiguous area from already reserved memory.
+ */
+int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
+				 int order_per_bit, struct cma **res_cma)
+{
+	struct cma *cma;
+	phys_addr_t alignment;
+
+	/* Sanity checks */
+	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
+		pr_err("Not enough slots for CMA reserved regions!\n");
+		return -ENOSPC;
+	}
+
+	if (!size || !memblock_is_region_reserved(base, size))
+		return -EINVAL;
+
+	/* ensure minimal alignment requied by mm core */
+	alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+
+	/* alignment should be aligned with order_per_bit */
+	if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit))
+		return -EINVAL;
+
+	if (ALIGN(base, alignment) != base || ALIGN(size, alignment) != size)
+		return -EINVAL;
+
+	/*
+	 * Each reserved area must be initialised later, when more kernel
+	 * subsystems (like slab allocator) are available.
+	 */
+	cma = &cma_areas[cma_area_count];
+	cma->base_pfn = PFN_DOWN(base);
+	cma->count = size >> PAGE_SHIFT;
+	cma->order_per_bit = order_per_bit;
+	*res_cma = cma;
+	cma_area_count++;
+
+	return 0;
+}
+
+/**
  * cma_declare_contiguous() - reserve custom contiguous area
  * @base: Base address of the reserved area optional, use 0 for any
  * @size: Size of the reserved area (in bytes),
@@ -162,7 +213,8 @@ int __init cma_declare_contiguous(phys_addr_t base,
 			phys_addr_t alignment, unsigned int order_per_bit,
 			bool fixed, struct cma **res_cma)
 {
-	struct cma *cma;
+	phys_addr_t memblock_end = memblock_end_of_DRAM();
+	phys_addr_t highmem_start = __pa(high_memory);
 	int ret = 0;
 
 	pr_debug("%s(size %lx, base %08lx, limit %08lx alignment %08lx)\n",
@@ -196,6 +248,24 @@ int __init cma_declare_contiguous(phys_addr_t base,
 	if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit))
 		return -EINVAL;
 
+	/*
+	 * adjust limit to avoid crossing low/high memory boundary for
+	 * automatically allocated regions
+	 */
+	if (((limit == 0 || limit > memblock_end) &&
+	     (memblock_end - size < highmem_start &&
+	      memblock_end > highmem_start)) ||
+	    (!fixed && limit > highmem_start && limit - size < highmem_start)) {
+		limit = highmem_start;
+	}
+
+	if (fixed && base < highmem_start && base+size > highmem_start) {
+		ret = -EINVAL;
+		pr_err("Region at %08lx defined on low/high memory boundary (%08lx)\n",
+			(unsigned long)base, (unsigned long)highmem_start);
+		goto err;
+	}
+
 	/* Reserve memory */
 	if (base && fixed) {
 		if (memblock_is_region_reserved(base, size) ||
@@ -214,16 +284,9 @@ int __init cma_declare_contiguous(phys_addr_t base,
 		}
 	}
 
-	/*
-	 * Each reserved area must be initialised later, when more kernel
-	 * subsystems (like slab allocator) are available.
-	 */
-	cma = &cma_areas[cma_area_count];
-	cma->base_pfn = PFN_DOWN(base);
-	cma->count = size >> PAGE_SHIFT;
-	cma->order_per_bit = order_per_bit;
-	*res_cma = cma;
-	cma_area_count++;
+	ret = cma_init_reserved_mem(base, size, order_per_bit, res_cma);
+	if (ret)
+		goto err;
 
 	pr_info("Reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
 		(unsigned long)base);
diff --git a/mm/compaction.c b/mm/compaction.c
index 21bf292b642a..edba18aed173 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -67,6 +67,49 @@ static inline bool migrate_async_suitable(int migratetype)
 	return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE;
 }
 
+/*
+ * Check that the whole (or subset of) a pageblock given by the interval of
+ * [start_pfn, end_pfn) is valid and within the same zone, before scanning it
+ * with the migration of free compaction scanner. The scanners then need to
+ * use only pfn_valid_within() check for arches that allow holes within
+ * pageblocks.
+ *
+ * Return struct page pointer of start_pfn, or NULL if checks were not passed.
+ *
+ * It's possible on some configurations to have a setup like node0 node1 node0
+ * i.e. it's possible that all pages within a zones range of pages do not
+ * belong to a single zone. We assume that a border between node0 and node1
+ * can occur within a single pageblock, but not a node0 node1 node0
+ * interleaving within a single pageblock. It is therefore sufficient to check
+ * the first and last page of a pageblock and avoid checking each individual
+ * page in a pageblock.
+ */
+static struct page *pageblock_pfn_to_page(unsigned long start_pfn,
+				unsigned long end_pfn, struct zone *zone)
+{
+	struct page *start_page;
+	struct page *end_page;
+
+	/* end_pfn is one past the range we are checking */
+	end_pfn--;
+
+	if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
+		return NULL;
+
+	start_page = pfn_to_page(start_pfn);
+
+	if (page_zone(start_page) != zone)
+		return NULL;
+
+	end_page = pfn_to_page(end_pfn);
+
+	/* This gives a shorter code than deriving page_zone(end_page) */
+	if (page_zone_id(start_page) != page_zone_id(end_page))
+		return NULL;
+
+	return start_page;
+}
+
 #ifdef CONFIG_COMPACTION
 /* Returns true if the pageblock should be scanned for pages to isolate. */
 static inline bool isolation_suitable(struct compact_control *cc,
@@ -132,7 +175,7 @@ void reset_isolation_suitable(pg_data_t *pgdat)
  */
 static void update_pageblock_skip(struct compact_control *cc,
 			struct page *page, unsigned long nr_isolated,
-			bool set_unsuitable, bool migrate_scanner)
+			bool migrate_scanner)
 {
 	struct zone *zone = cc->zone;
 	unsigned long pfn;
@@ -146,12 +189,7 @@ static void update_pageblock_skip(struct compact_control *cc,
 	if (nr_isolated)
 		return;
 
-	/*
-	 * Only skip pageblocks when all forms of compaction will be known to
-	 * fail in the near future.
-	 */
-	if (set_unsuitable)
-		set_pageblock_skip(page);
+	set_pageblock_skip(page);
 
 	pfn = page_to_pfn(page);
 
@@ -180,52 +218,77 @@ static inline bool isolation_suitable(struct compact_control *cc,
 
 static void update_pageblock_skip(struct compact_control *cc,
 			struct page *page, unsigned long nr_isolated,
-			bool set_unsuitable, bool migrate_scanner)
+			bool migrate_scanner)
 {
 }
 #endif /* CONFIG_COMPACTION */
 
-static inline bool should_release_lock(spinlock_t *lock)
+/*
+ * Compaction requires the taking of some coarse locks that are potentially
+ * very heavily contended. For async compaction, back out if the lock cannot
+ * be taken immediately. For sync compaction, spin on the lock if needed.
+ *
+ * Returns true if the lock is held
+ * Returns false if the lock is not held and compaction should abort
+ */
+static bool compact_trylock_irqsave(spinlock_t *lock, unsigned long *flags,
+						struct compact_control *cc)
 {
-	return need_resched() || spin_is_contended(lock);
+	if (cc->mode == MIGRATE_ASYNC) {
+		if (!spin_trylock_irqsave(lock, *flags)) {
+			cc->contended = COMPACT_CONTENDED_LOCK;
+			return false;
+		}
+	} else {
+		spin_lock_irqsave(lock, *flags);
+	}
+
+	return true;
 }
 
 /*
  * Compaction requires the taking of some coarse locks that are potentially
- * very heavily contended. Check if the process needs to be scheduled or
- * if the lock is contended. For async compaction, back out in the event
- * if contention is severe. For sync compaction, schedule.
+ * very heavily contended. The lock should be periodically unlocked to avoid
+ * having disabled IRQs for a long time, even when there is nobody waiting on
+ * the lock. It might also be that allowing the IRQs will result in
+ * need_resched() becoming true. If scheduling is needed, async compaction
+ * aborts. Sync compaction schedules.
+ * Either compaction type will also abort if a fatal signal is pending.
+ * In either case if the lock was locked, it is dropped and not regained.
  *
- * Returns true if the lock is held.
- * Returns false if the lock is released and compaction should abort
+ * Returns true if compaction should abort due to fatal signal pending, or
+ *		async compaction due to need_resched()
+ * Returns false when compaction can continue (sync compaction might have
+ *		scheduled)
  */
-static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
-				      bool locked, struct compact_control *cc)
+static bool compact_unlock_should_abort(spinlock_t *lock,
+		unsigned long flags, bool *locked, struct compact_control *cc)
 {
-	if (should_release_lock(lock)) {
-		if (locked) {
-			spin_unlock_irqrestore(lock, *flags);
-			locked = false;
-		}
+	if (*locked) {
+		spin_unlock_irqrestore(lock, flags);
+		*locked = false;
+	}
+
+	if (fatal_signal_pending(current)) {
+		cc->contended = COMPACT_CONTENDED_SCHED;
+		return true;
+	}
 
-		/* async aborts if taking too long or contended */
+	if (need_resched()) {
 		if (cc->mode == MIGRATE_ASYNC) {
-			cc->contended = true;
-			return false;
+			cc->contended = COMPACT_CONTENDED_SCHED;
+			return true;
 		}
-
 		cond_resched();
 	}
 
-	if (!locked)
-		spin_lock_irqsave(lock, *flags);
-	return true;
+	return false;
 }
 
 /*
  * Aside from avoiding lock contention, compaction also periodically checks
  * need_resched() and either schedules in sync compaction or aborts async
- * compaction. This is similar to what compact_checklock_irqsave() does, but
+ * compaction. This is similar to what compact_unlock_should_abort() does, but
  * is used where no lock is concerned.
  *
  * Returns false when no scheduling was needed, or sync compaction scheduled.
@@ -236,7 +299,7 @@ static inline bool compact_should_abort(struct compact_control *cc)
 	/* async compaction aborts if contended */
 	if (need_resched()) {
 		if (cc->mode == MIGRATE_ASYNC) {
-			cc->contended = true;
+			cc->contended = COMPACT_CONTENDED_SCHED;
 			return true;
 		}
 
@@ -250,8 +313,15 @@ static inline bool compact_should_abort(struct compact_control *cc)
 static bool suitable_migration_target(struct page *page)
 {
 	/* If the page is a large free page, then disallow migration */
-	if (PageBuddy(page) && page_order(page) >= pageblock_order)
-		return false;
+	if (PageBuddy(page)) {
+		/*
+		 * We are checking page_order without zone->lock taken. But
+		 * the only small danger is that we skip a potentially suitable
+		 * pageblock, so it's not worth to check order for valid range.
+		 */
+		if (page_order_unsafe(page) >= pageblock_order)
+			return false;
+	}
 
 	/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
 	if (migrate_async_suitable(get_pageblock_migratetype(page)))
@@ -267,16 +337,16 @@ static bool suitable_migration_target(struct page *page)
  * (even though it may still end up isolating some pages).
  */
 static unsigned long isolate_freepages_block(struct compact_control *cc,
-				unsigned long blockpfn,
+				unsigned long *start_pfn,
 				unsigned long end_pfn,
 				struct list_head *freelist,
 				bool strict)
 {
 	int nr_scanned = 0, total_isolated = 0;
 	struct page *cursor, *valid_page = NULL;
-	unsigned long flags;
+	unsigned long flags = 0;
 	bool locked = false;
-	bool checked_pageblock = false;
+	unsigned long blockpfn = *start_pfn;
 
 	cursor = pfn_to_page(blockpfn);
 
@@ -285,6 +355,16 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 		int isolated, i;
 		struct page *page = cursor;
 
+		/*
+		 * Periodically drop the lock (if held) regardless of its
+		 * contention, to give chance to IRQs. Abort if fatal signal
+		 * pending or async compaction detects need_resched()
+		 */
+		if (!(blockpfn % SWAP_CLUSTER_MAX)
+		    && compact_unlock_should_abort(&cc->zone->lock, flags,
+								&locked, cc))
+			break;
+
 		nr_scanned++;
 		if (!pfn_valid_within(blockpfn))
 			goto isolate_fail;
@@ -295,33 +375,30 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 			goto isolate_fail;
 
 		/*
-		 * The zone lock must be held to isolate freepages.
-		 * Unfortunately this is a very coarse lock and can be
-		 * heavily contended if there are parallel allocations
-		 * or parallel compactions. For async compaction do not
-		 * spin on the lock and we acquire the lock as late as
-		 * possible.
+		 * If we already hold the lock, we can skip some rechecking.
+		 * Note that if we hold the lock now, checked_pageblock was
+		 * already set in some previous iteration (or strict is true),
+		 * so it is correct to skip the suitable migration target
+		 * recheck as well.
 		 */
-		locked = compact_checklock_irqsave(&cc->zone->lock, &flags,
-								locked, cc);
-		if (!locked)
-			break;
-
-		/* Recheck this is a suitable migration target under lock */
-		if (!strict && !checked_pageblock) {
+		if (!locked) {
 			/*
-			 * We need to check suitability of pageblock only once
-			 * and this isolate_freepages_block() is called with
-			 * pageblock range, so just check once is sufficient.
+			 * The zone lock must be held to isolate freepages.
+			 * Unfortunately this is a very coarse lock and can be
+			 * heavily contended if there are parallel allocations
+			 * or parallel compactions. For async compaction do not
+			 * spin on the lock and we acquire the lock as late as
+			 * possible.
 			 */
-			checked_pageblock = true;
-			if (!suitable_migration_target(page))
+			locked = compact_trylock_irqsave(&cc->zone->lock,
+								&flags, cc);
+			if (!locked)
 				break;
-		}
 
-		/* Recheck this is a buddy page under lock */
-		if (!PageBuddy(page))
-			goto isolate_fail;
+			/* Recheck this is a buddy page under lock */
+			if (!PageBuddy(page))
+				goto isolate_fail;
+		}
 
 		/* Found a free page, break it into order-0 pages */
 		isolated = split_free_page(page);
@@ -346,6 +423,9 @@ isolate_fail:
 
 	}
 
+	/* Record how far we have got within the block */
+	*start_pfn = blockpfn;
+
 	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
 
 	/*
@@ -361,8 +441,7 @@ isolate_fail:
 
 	/* Update the pageblock-skip if the whole pageblock was scanned */
 	if (blockpfn == end_pfn)
-		update_pageblock_skip(cc, valid_page, total_isolated, true,
-				      false);
+		update_pageblock_skip(cc, valid_page, total_isolated, false);
 
 	count_compact_events(COMPACTFREE_SCANNED, nr_scanned);
 	if (total_isolated)
@@ -390,19 +469,21 @@ isolate_freepages_range(struct compact_control *cc,
 	unsigned long isolated, pfn, block_end_pfn;
 	LIST_HEAD(freelist);
 
-	for (pfn = start_pfn; pfn < end_pfn; pfn += isolated) {
-		if (!pfn_valid(pfn) || cc->zone != page_zone(pfn_to_page(pfn)))
-			break;
+	pfn = start_pfn;
+	block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
+
+	for (; pfn < end_pfn; pfn += isolated,
+				block_end_pfn += pageblock_nr_pages) {
+		/* Protect pfn from changing by isolate_freepages_block */
+		unsigned long isolate_start_pfn = pfn;
 
-		/*
-		 * On subsequent iterations ALIGN() is actually not needed,
-		 * but we keep it that we not to complicate the code.
-		 */
-		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 		block_end_pfn = min(block_end_pfn, end_pfn);
 
-		isolated = isolate_freepages_block(cc, pfn, block_end_pfn,
-						   &freelist, true);
+		if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone))
+			break;
+
+		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
+						block_end_pfn, &freelist, true);
 
 		/*
 		 * In strict mode, isolate_freepages_block() returns 0 if
@@ -433,22 +514,19 @@ isolate_freepages_range(struct compact_control *cc,
 }
 
 /* Update the number of anon and file isolated pages in the zone */
-static void acct_isolated(struct zone *zone, bool locked, struct compact_control *cc)
+static void acct_isolated(struct zone *zone, struct compact_control *cc)
 {
 	struct page *page;
 	unsigned int count[2] = { 0, };
 
+	if (list_empty(&cc->migratepages))
+		return;
+
 	list_for_each_entry(page, &cc->migratepages, lru)
 		count[!!page_is_file_cache(page)]++;
 
-	/* If locked we can use the interrupt unsafe versions */
-	if (locked) {
-		__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
-		__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
-	} else {
-		mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
-		mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
-	}
+	mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
+	mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
 }
 
 /* Similar to reclaim, but different enough that they don't share logic */
@@ -467,40 +545,34 @@ static bool too_many_isolated(struct zone *zone)
 }
 
 /**
- * isolate_migratepages_range() - isolate all migrate-able pages in range.
- * @zone:	Zone pages are in.
+ * isolate_migratepages_block() - isolate all migrate-able pages within
+ *				  a single pageblock
  * @cc:		Compaction control structure.
- * @low_pfn:	The first PFN of the range.
- * @end_pfn:	The one-past-the-last PFN of the range.
- * @unevictable: true if it allows to isolate unevictable pages
+ * @low_pfn:	The first PFN to isolate
+ * @end_pfn:	The one-past-the-last PFN to isolate, within same pageblock
+ * @isolate_mode: Isolation mode to be used.
  *
  * Isolate all pages that can be migrated from the range specified by
- * [low_pfn, end_pfn).  Returns zero if there is a fatal signal
- * pending), otherwise PFN of the first page that was not scanned
- * (which may be both less, equal to or more then end_pfn).
+ * [low_pfn, end_pfn). The range is expected to be within same pageblock.
+ * Returns zero if there is a fatal signal pending, otherwise PFN of the
+ * first page that was not scanned (which may be both less, equal to or more
+ * than end_pfn).
  *
- * Assumes that cc->migratepages is empty and cc->nr_migratepages is
- * zero.
- *
- * Apart from cc->migratepages and cc->nr_migratetypes this function
- * does not modify any cc's fields, in particular it does not modify
- * (or read for that matter) cc->migrate_pfn.
+ * The pages are isolated on cc->migratepages list (not required to be empty),
+ * and cc->nr_migratepages is updated accordingly. The cc->migrate_pfn field
+ * is neither read nor updated.
  */
-unsigned long
-isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
-		unsigned long low_pfn, unsigned long end_pfn, bool unevictable)
+static unsigned long
+isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
+			unsigned long end_pfn, isolate_mode_t isolate_mode)
 {
-	unsigned long last_pageblock_nr = 0, pageblock_nr;
+	struct zone *zone = cc->zone;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct list_head *migratelist = &cc->migratepages;
 	struct lruvec *lruvec;
-	unsigned long flags;
+	unsigned long flags = 0;
 	bool locked = false;
 	struct page *page = NULL, *valid_page = NULL;
-	bool set_unsuitable = true;
-	const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ?
-					ISOLATE_ASYNC_MIGRATE : 0) |
-				    (unevictable ? ISOLATE_UNEVICTABLE : 0);
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
@@ -523,72 +595,43 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 
 	/* Time to isolate some pages for migration */
 	for (; low_pfn < end_pfn; low_pfn++) {
-		/* give a chance to irqs before checking need_resched() */
-		if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) {
-			if (should_release_lock(&zone->lru_lock)) {
-				spin_unlock_irqrestore(&zone->lru_lock, flags);
-				locked = false;
-			}
-		}
-
 		/*
-		 * migrate_pfn does not necessarily start aligned to a
-		 * pageblock. Ensure that pfn_valid is called when moving
-		 * into a new MAX_ORDER_NR_PAGES range in case of large
-		 * memory holes within the zone
+		 * Periodically drop the lock (if held) regardless of its
+		 * contention, to give chance to IRQs. Abort async compaction
+		 * if contended.
 		 */
-		if ((low_pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
-			if (!pfn_valid(low_pfn)) {
-				low_pfn += MAX_ORDER_NR_PAGES - 1;
-				continue;
-			}
-		}
+		if (!(low_pfn % SWAP_CLUSTER_MAX)
+		    && compact_unlock_should_abort(&zone->lru_lock, flags,
+								&locked, cc))
+			break;
 
 		if (!pfn_valid_within(low_pfn))
 			continue;
 		nr_scanned++;
 
-		/*
-		 * Get the page and ensure the page is within the same zone.
-		 * See the comment in isolate_freepages about overlapping
-		 * nodes. It is deliberate that the new zone lock is not taken
-		 * as memory compaction should not move pages between nodes.
-		 */
 		page = pfn_to_page(low_pfn);
-		if (page_zone(page) != zone)
-			continue;
 
 		if (!valid_page)
 			valid_page = page;
 
-		/* If isolation recently failed, do not retry */
-		pageblock_nr = low_pfn >> pageblock_order;
-		if (last_pageblock_nr != pageblock_nr) {
-			int mt;
-
-			last_pageblock_nr = pageblock_nr;
-			if (!isolation_suitable(cc, page))
-				goto next_pageblock;
+		/*
+		 * Skip if free. We read page order here without zone lock
+		 * which is generally unsafe, but the race window is small and
+		 * the worst thing that can happen is that we skip some
+		 * potential isolation targets.
+		 */
+		if (PageBuddy(page)) {
+			unsigned long freepage_order = page_order_unsafe(page);
 
 			/*
-			 * For async migration, also only scan in MOVABLE
-			 * blocks. Async migration is optimistic to see if
-			 * the minimum amount of work satisfies the allocation
+			 * Without lock, we cannot be sure that what we got is
+			 * a valid page order. Consider only values in the
+			 * valid order range to prevent low_pfn overflow.
 			 */
-			mt = get_pageblock_migratetype(page);
-			if (cc->mode == MIGRATE_ASYNC &&
-			    !migrate_async_suitable(mt)) {
-				set_unsuitable = false;
-				goto next_pageblock;
-			}
-		}
-
-		/*
-		 * Skip if free. page_order cannot be used without zone->lock
-		 * as nothing prevents parallel allocations or buddy merging.
-		 */
-		if (PageBuddy(page))
+			if (freepage_order > 0 && freepage_order < MAX_ORDER)
+				low_pfn += (1UL << freepage_order) - 1;
 			continue;
+		}
 
 		/*
 		 * Check may be lockless but that's ok as we recheck later.
@@ -597,7 +640,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		 */
 		if (!PageLRU(page)) {
 			if (unlikely(balloon_page_movable(page))) {
-				if (locked && balloon_page_isolate(page)) {
+				if (balloon_page_isolate(page)) {
 					/* Successfully isolated */
 					goto isolate_success;
 				}
@@ -617,8 +660,11 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		 */
 		if (PageTransHuge(page)) {
 			if (!locked)
-				goto next_pageblock;
-			low_pfn += (1 << compound_order(page)) - 1;
+				low_pfn = ALIGN(low_pfn + 1,
+						pageblock_nr_pages) - 1;
+			else
+				low_pfn += (1 << compound_order(page)) - 1;
+
 			continue;
 		}
 
@@ -631,24 +677,26 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		    page_count(page) > page_mapcount(page))
 			continue;
 
-		/* Check if it is ok to still hold the lock */
-		locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
-								locked, cc);
-		if (!locked || fatal_signal_pending(current))
-			break;
+		/* If we already hold the lock, we can skip some rechecking */
+		if (!locked) {
+			locked = compact_trylock_irqsave(&zone->lru_lock,
+								&flags, cc);
+			if (!locked)
+				break;
 
-		/* Recheck PageLRU and PageTransHuge under lock */
-		if (!PageLRU(page))
-			continue;
-		if (PageTransHuge(page)) {
-			low_pfn += (1 << compound_order(page)) - 1;
-			continue;
+			/* Recheck PageLRU and PageTransHuge under lock */
+			if (!PageLRU(page))
+				continue;
+			if (PageTransHuge(page)) {
+				low_pfn += (1 << compound_order(page)) - 1;
+				continue;
+			}
 		}
 
 		lruvec = mem_cgroup_page_lruvec(page, zone);
 
 		/* Try isolate the page */
-		if (__isolate_lru_page(page, mode) != 0)
+		if (__isolate_lru_page(page, isolate_mode) != 0)
 			continue;
 
 		VM_BUG_ON_PAGE(PageTransCompound(page), page);
@@ -667,14 +715,14 @@ isolate_success:
 			++low_pfn;
 			break;
 		}
-
-		continue;
-
-next_pageblock:
-		low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
 	}
 
-	acct_isolated(zone, locked, cc);
+	/*
+	 * The PageBuddy() check could have potentially brought us outside
+	 * the range to be scanned.
+	 */
+	if (unlikely(low_pfn > end_pfn))
+		low_pfn = end_pfn;
 
 	if (locked)
 		spin_unlock_irqrestore(&zone->lru_lock, flags);
@@ -684,8 +732,7 @@ next_pageblock:
 	 * if the whole pageblock was scanned without isolating any page.
 	 */
 	if (low_pfn == end_pfn)
-		update_pageblock_skip(cc, valid_page, nr_isolated,
-				      set_unsuitable, true);
+		update_pageblock_skip(cc, valid_page, nr_isolated, true);
 
 	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
 
@@ -696,17 +743,65 @@ next_pageblock:
 	return low_pfn;
 }
 
+/**
+ * isolate_migratepages_range() - isolate migrate-able pages in a PFN range
+ * @cc:        Compaction control structure.
+ * @start_pfn: The first PFN to start isolating.
+ * @end_pfn:   The one-past-last PFN.
+ *
+ * Returns zero if isolation fails fatally due to e.g. pending signal.
+ * Otherwise, function returns one-past-the-last PFN of isolated page
+ * (which may be greater than end_pfn if end fell in a middle of a THP page).
+ */
+unsigned long
+isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
+							unsigned long end_pfn)
+{
+	unsigned long pfn, block_end_pfn;
+
+	/* Scan block by block. First and last block may be incomplete */
+	pfn = start_pfn;
+	block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
+
+	for (; pfn < end_pfn; pfn = block_end_pfn,
+				block_end_pfn += pageblock_nr_pages) {
+
+		block_end_pfn = min(block_end_pfn, end_pfn);
+
+		if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone))
+			continue;
+
+		pfn = isolate_migratepages_block(cc, pfn, block_end_pfn,
+							ISOLATE_UNEVICTABLE);
+
+		/*
+		 * In case of fatal failure, release everything that might
+		 * have been isolated in the previous iteration, and signal
+		 * the failure back to caller.
+		 */
+		if (!pfn) {
+			putback_movable_pages(&cc->migratepages);
+			cc->nr_migratepages = 0;
+			break;
+		}
+	}
+	acct_isolated(cc->zone, cc);
+
+	return pfn;
+}
+
 #endif /* CONFIG_COMPACTION || CONFIG_CMA */
 #ifdef CONFIG_COMPACTION
 /*
  * Based on information in the current compact_control, find blocks
  * suitable for isolating free pages from and then isolate them.
  */
-static void isolate_freepages(struct zone *zone,
-				struct compact_control *cc)
+static void isolate_freepages(struct compact_control *cc)
 {
+	struct zone *zone = cc->zone;
 	struct page *page;
 	unsigned long block_start_pfn;	/* start of current pageblock */
+	unsigned long isolate_start_pfn; /* exact pfn we start at */
 	unsigned long block_end_pfn;	/* end of current pageblock */
 	unsigned long low_pfn;	     /* lowest pfn scanner is able to scan */
 	int nr_freepages = cc->nr_freepages;
@@ -715,14 +810,15 @@ static void isolate_freepages(struct zone *zone,
 	/*
 	 * Initialise the free scanner. The starting point is where we last
 	 * successfully isolated from, zone-cached value, or the end of the
-	 * zone when isolating for the first time. We need this aligned to
-	 * the pageblock boundary, because we do
+	 * zone when isolating for the first time. For looping we also need
+	 * this pfn aligned down to the pageblock boundary, because we do
 	 * block_start_pfn -= pageblock_nr_pages in the for loop.
 	 * For ending point, take care when isolating in last pageblock of a
 	 * a zone which ends in the middle of a pageblock.
 	 * The low boundary is the end of the pageblock the migration scanner
 	 * is using.
 	 */
+	isolate_start_pfn = cc->free_pfn;
 	block_start_pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
 	block_end_pfn = min(block_start_pfn + pageblock_nr_pages,
 						zone_end_pfn(zone));
@@ -735,7 +831,8 @@ static void isolate_freepages(struct zone *zone,
 	 */
 	for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
 				block_end_pfn = block_start_pfn,
-				block_start_pfn -= pageblock_nr_pages) {
+				block_start_pfn -= pageblock_nr_pages,
+				isolate_start_pfn = block_start_pfn) {
 		unsigned long isolated;
 
 		/*
@@ -747,18 +844,9 @@ static void isolate_freepages(struct zone *zone,
 						&& compact_should_abort(cc))
 			break;
 
-		if (!pfn_valid(block_start_pfn))
-			continue;
-
-		/*
-		 * Check for overlapping nodes/zones. It's possible on some
-		 * configurations to have a setup like
-		 * node0 node1 node0
-		 * i.e. it's possible that all pages within a zones range of
-		 * pages do not belong to a single zone.
-		 */
-		page = pfn_to_page(block_start_pfn);
-		if (page_zone(page) != zone)
+		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
+									zone);
+		if (!page)
 			continue;
 
 		/* Check the block is suitable for migration */
@@ -769,13 +857,25 @@ static void isolate_freepages(struct zone *zone,
 		if (!isolation_suitable(cc, page))
 			continue;
 
-		/* Found a block suitable for isolating free pages from */
-		cc->free_pfn = block_start_pfn;
-		isolated = isolate_freepages_block(cc, block_start_pfn,
+		/* Found a block suitable for isolating free pages from. */
+		isolated = isolate_freepages_block(cc, &isolate_start_pfn,
 					block_end_pfn, freelist, false);
 		nr_freepages += isolated;
 
 		/*
+		 * Remember where the free scanner should restart next time,
+		 * which is where isolate_freepages_block() left off.
+		 * But if it scanned the whole pageblock, isolate_start_pfn
+		 * now points at block_end_pfn, which is the start of the next
+		 * pageblock.
+		 * In that case we will however want to restart at the start
+		 * of the previous pageblock.
+		 */
+		cc->free_pfn = (isolate_start_pfn < block_end_pfn) ?
+				isolate_start_pfn :
+				block_start_pfn - pageblock_nr_pages;
+
+		/*
 		 * Set a flag that we successfully isolated in this pageblock.
 		 * In the next loop iteration, zone->compact_cached_free_pfn
 		 * will not be updated and thus it will effectively contain the
@@ -822,7 +922,7 @@ static struct page *compaction_alloc(struct page *migratepage,
 	 */
 	if (list_empty(&cc->freepages)) {
 		if (!cc->contended)
-			isolate_freepages(cc->zone, cc);
+			isolate_freepages(cc);
 
 		if (list_empty(&cc->freepages))
 			return NULL;
@@ -856,38 +956,84 @@ typedef enum {
 } isolate_migrate_t;
 
 /*
- * Isolate all pages that can be migrated from the block pointed to by
- * the migrate scanner within compact_control.
+ * Isolate all pages that can be migrated from the first suitable block,
+ * starting at the block pointed to by the migrate scanner pfn within
+ * compact_control.
  */
 static isolate_migrate_t isolate_migratepages(struct zone *zone,
 					struct compact_control *cc)
 {
 	unsigned long low_pfn, end_pfn;
+	struct page *page;
+	const isolate_mode_t isolate_mode =
+		(cc->mode == MIGRATE_ASYNC ? ISOLATE_ASYNC_MIGRATE : 0);
 
-	/* Do not scan outside zone boundaries */
-	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);
+	/*
+	 * Start at where we last stopped, or beginning of the zone as
+	 * initialized by compact_zone()
+	 */
+	low_pfn = cc->migrate_pfn;
 
 	/* Only scan within a pageblock boundary */
 	end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);
 
-	/* Do not cross the free scanner or scan within a memory hole */
-	if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) {
-		cc->migrate_pfn = end_pfn;
-		return ISOLATE_NONE;
-	}
+	/*
+	 * Iterate over whole pageblocks until we find the first suitable.
+	 * Do not cross the free scanner.
+	 */
+	for (; end_pfn <= cc->free_pfn;
+			low_pfn = end_pfn, end_pfn += pageblock_nr_pages) {
 
-	/* Perform the isolation */
-	low_pfn = isolate_migratepages_range(zone, cc, low_pfn, end_pfn, false);
-	if (!low_pfn || cc->contended)
-		return ISOLATE_ABORT;
+		/*
+		 * This can potentially iterate a massively long zone with
+		 * many pageblocks unsuitable, so periodically check if we
+		 * need to schedule, or even abort async compaction.
+		 */
+		if (!(low_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
+						&& compact_should_abort(cc))
+			break;
+
+		page = pageblock_pfn_to_page(low_pfn, end_pfn, zone);
+		if (!page)
+			continue;
+
+		/* If isolation recently failed, do not retry */
+		if (!isolation_suitable(cc, page))
+			continue;
+
+		/*
+		 * For async compaction, also only scan in MOVABLE blocks.
+		 * Async compaction is optimistic to see if the minimum amount
+		 * of work satisfies the allocation.
+		 */
+		if (cc->mode == MIGRATE_ASYNC &&
+		    !migrate_async_suitable(get_pageblock_migratetype(page)))
+			continue;
+
+		/* Perform the isolation */
+		low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn,
+								isolate_mode);
 
+		if (!low_pfn || cc->contended)
+			return ISOLATE_ABORT;
+
+		/*
+		 * Either we isolated something and proceed with migration. Or
+		 * we failed and compact_zone should decide if we should
+		 * continue or not.
+		 */
+		break;
+	}
+
+	acct_isolated(zone, cc);
+	/* Record where migration scanner will be restarted */
 	cc->migrate_pfn = low_pfn;
 
-	return ISOLATE_SUCCESS;
+	return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
 }
 
-static int compact_finished(struct zone *zone,
-			    struct compact_control *cc)
+static int compact_finished(struct zone *zone, struct compact_control *cc,
+			    const int migratetype)
 {
 	unsigned int order;
 	unsigned long watermark;
@@ -933,7 +1079,7 @@ static int compact_finished(struct zone *zone,
 		struct free_area *area = &zone->free_area[order];
 
 		/* Job done if page is free of the right migratetype */
-		if (!list_empty(&area->free_list[cc->migratetype]))
+		if (!list_empty(&area->free_list[migratetype]))
 			return COMPACT_PARTIAL;
 
 		/* Job done if allocation would set block type */
@@ -999,6 +1145,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	int ret;
 	unsigned long start_pfn = zone->zone_start_pfn;
 	unsigned long end_pfn = zone_end_pfn(zone);
+	const int migratetype = gfpflags_to_migratetype(cc->gfp_mask);
 	const bool sync = cc->mode != MIGRATE_ASYNC;
 
 	ret = compaction_suitable(zone, cc->order);
@@ -1041,7 +1188,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
 	migrate_prep_local();
 
-	while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
+	while ((ret = compact_finished(zone, cc, migratetype)) ==
+						COMPACT_CONTINUE) {
 		int err;
 
 		switch (isolate_migratepages(zone, cc)) {
@@ -1056,9 +1204,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 			;
 		}
 
-		if (!cc->nr_migratepages)
-			continue;
-
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
 				compaction_free, (unsigned long)cc, cc->mode,
 				MR_COMPACTION);
@@ -1092,14 +1237,14 @@ out:
 }
 
 static unsigned long compact_zone_order(struct zone *zone, int order,
-		gfp_t gfp_mask, enum migrate_mode mode, bool *contended)
+		gfp_t gfp_mask, enum migrate_mode mode, int *contended)
 {
 	unsigned long ret;
 	struct compact_control cc = {
 		.nr_freepages = 0,
 		.nr_migratepages = 0,
 		.order = order,
-		.migratetype = allocflags_to_migratetype(gfp_mask),
+		.gfp_mask = gfp_mask,
 		.zone = zone,
 		.mode = mode,
 	};
@@ -1124,48 +1269,117 @@ int sysctl_extfrag_threshold = 500;
  * @gfp_mask: The GFP mask of the current allocation
  * @nodemask: The allowed nodes to allocate from
  * @mode: The migration mode for async, sync light, or sync migration
- * @contended: Return value that is true if compaction was aborted due to lock contention
- * @page: Optionally capture a free page of the requested order during compaction
+ * @contended: Return value that determines if compaction was aborted due to
+ *	       need_resched() or lock contention
+ * @candidate_zone: Return the zone where we think allocation should succeed
  *
  * This is the main entry point for direct page compaction.
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			enum migrate_mode mode, bool *contended)
+			enum migrate_mode mode, int *contended,
+			struct zone **candidate_zone)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
 	int may_perform_io = gfp_mask & __GFP_IO;
 	struct zoneref *z;
 	struct zone *zone;
-	int rc = COMPACT_SKIPPED;
+	int rc = COMPACT_DEFERRED;
 	int alloc_flags = 0;
+	int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */
+
+	*contended = COMPACT_CONTENDED_NONE;
 
 	/* Check if the GFP flags allow compaction */
 	if (!order || !may_enter_fs || !may_perform_io)
-		return rc;
-
-	count_compact_event(COMPACTSTALL);
+		return COMPACT_SKIPPED;
 
 #ifdef CONFIG_CMA
-	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 #endif
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 								nodemask) {
 		int status;
+		int zone_contended;
+
+		if (compaction_deferred(zone, order))
+			continue;
 
 		status = compact_zone_order(zone, order, gfp_mask, mode,
-						contended);
+							&zone_contended);
 		rc = max(status, rc);
+		/*
+		 * It takes at least one zone that wasn't lock contended
+		 * to clear all_zones_contended.
+		 */
+		all_zones_contended &= zone_contended;
 
 		/* If a normal allocation would succeed, stop compacting */
 		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0,
-				      alloc_flags))
-			break;
+				      alloc_flags)) {
+			*candidate_zone = zone;
+			/*
+			 * We think the allocation will succeed in this zone,
+			 * but it is not certain, hence the false. The caller
+			 * will repeat this with true if allocation indeed
+			 * succeeds in this zone.
+			 */
+			compaction_defer_reset(zone, order, false);
+			/*
+			 * It is possible that async compaction aborted due to
+			 * need_resched() and the watermarks were ok thanks to
+			 * somebody else freeing memory. The allocation can
+			 * however still fail so we better signal the
+			 * need_resched() contention anyway (this will not
+			 * prevent the allocation attempt).
+			 */
+			if (zone_contended == COMPACT_CONTENDED_SCHED)
+				*contended = COMPACT_CONTENDED_SCHED;
+
+			goto break_loop;
+		}
+
+		if (mode != MIGRATE_ASYNC) {
+			/*
+			 * We think that allocation won't succeed in this zone
+			 * so we defer compaction there. If it ends up
+			 * succeeding after all, it will be reset.
+			 */
+			defer_compaction(zone, order);
+		}
+
+		/*
+		 * We might have stopped compacting due to need_resched() in
+		 * async compaction, or due to a fatal signal detected. In that
+		 * case do not try further zones and signal need_resched()
+		 * contention.
+		 */
+		if ((zone_contended == COMPACT_CONTENDED_SCHED)
+					|| fatal_signal_pending(current)) {
+			*contended = COMPACT_CONTENDED_SCHED;
+			goto break_loop;
+		}
+
+		continue;
+break_loop:
+		/*
+		 * We might not have tried all the zones, so  be conservative
+		 * and assume they are not all lock contended.
+		 */
+		all_zones_contended = 0;
+		break;
 	}
 
+	/*
+	 * If at least one zone wasn't deferred or skipped, we report if all
+	 * zones that were tried were lock contended.
+	 */
+	if (rc > COMPACT_SKIPPED && all_zones_contended)
+		*contended = COMPACT_CONTENDED_LOCK;
+
 	return rc;
 }
 
diff --git a/mm/debug.c b/mm/debug.c
new file mode 100644
index 000000000000..5ce45c9a29b5
--- /dev/null
+++ b/mm/debug.c
@@ -0,0 +1,237 @@
+/*
+ * mm/debug.c
+ *
+ * mm/ specific debug routines.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/ftrace_event.h>
+#include <linux/memcontrol.h>
+
+static const struct trace_print_flags pageflag_names[] = {
+	{1UL << PG_locked,		"locked"	},
+	{1UL << PG_error,		"error"		},
+	{1UL << PG_referenced,		"referenced"	},
+	{1UL << PG_uptodate,		"uptodate"	},
+	{1UL << PG_dirty,		"dirty"		},
+	{1UL << PG_lru,			"lru"		},
+	{1UL << PG_active,		"active"	},
+	{1UL << PG_slab,		"slab"		},
+	{1UL << PG_owner_priv_1,	"owner_priv_1"	},
+	{1UL << PG_arch_1,		"arch_1"	},
+	{1UL << PG_reserved,		"reserved"	},
+	{1UL << PG_private,		"private"	},
+	{1UL << PG_private_2,		"private_2"	},
+	{1UL << PG_writeback,		"writeback"	},
+#ifdef CONFIG_PAGEFLAGS_EXTENDED
+	{1UL << PG_head,		"head"		},
+	{1UL << PG_tail,		"tail"		},
+#else
+	{1UL << PG_compound,		"compound"	},
+#endif
+	{1UL << PG_swapcache,		"swapcache"	},
+	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
+	{1UL << PG_reclaim,		"reclaim"	},
+	{1UL << PG_swapbacked,		"swapbacked"	},
+	{1UL << PG_unevictable,		"unevictable"	},
+#ifdef CONFIG_MMU
+	{1UL << PG_mlocked,		"mlocked"	},
+#endif
+#ifdef CONFIG_ARCH_USES_PG_UNCACHED
+	{1UL << PG_uncached,		"uncached"	},
+#endif
+#ifdef CONFIG_MEMORY_FAILURE
+	{1UL << PG_hwpoison,		"hwpoison"	},
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	{1UL << PG_compound_lock,	"compound_lock"	},
+#endif
+};
+
+static void dump_flags(unsigned long flags,
+			const struct trace_print_flags *names, int count)
+{
+	const char *delim = "";
+	unsigned long mask;
+	int i;
+
+	pr_emerg("flags: %#lx(", flags);
+
+	/* remove zone id */
+	flags &= (1UL << NR_PAGEFLAGS) - 1;
+
+	for (i = 0; i < count && flags; i++) {
+
+		mask = names[i].mask;
+		if ((flags & mask) != mask)
+			continue;
+
+		flags &= ~mask;
+		pr_cont("%s%s", delim, names[i].name);
+		delim = "|";
+	}
+
+	/* check for left over flags */
+	if (flags)
+		pr_cont("%s%#lx", delim, flags);
+
+	pr_cont(")\n");
+}
+
+void dump_page_badflags(struct page *page, const char *reason,
+		unsigned long badflags)
+{
+	pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
+		  page, atomic_read(&page->_count), page_mapcount(page),
+		  page->mapping, page->index);
+	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
+	dump_flags(page->flags, pageflag_names, ARRAY_SIZE(pageflag_names));
+	if (reason)
+		pr_alert("page dumped because: %s\n", reason);
+	if (page->flags & badflags) {
+		pr_alert("bad because of flags:\n");
+		dump_flags(page->flags & badflags,
+				pageflag_names, ARRAY_SIZE(pageflag_names));
+	}
+	mem_cgroup_print_bad_page(page);
+}
+
+void dump_page(struct page *page, const char *reason)
+{
+	dump_page_badflags(page, reason, 0);
+}
+EXPORT_SYMBOL(dump_page);
+
+#ifdef CONFIG_DEBUG_VM
+
+static const struct trace_print_flags vmaflags_names[] = {
+	{VM_READ,			"read"		},
+	{VM_WRITE,			"write"		},
+	{VM_EXEC,			"exec"		},
+	{VM_SHARED,			"shared"	},
+	{VM_MAYREAD,			"mayread"	},
+	{VM_MAYWRITE,			"maywrite"	},
+	{VM_MAYEXEC,			"mayexec"	},
+	{VM_MAYSHARE,			"mayshare"	},
+	{VM_GROWSDOWN,			"growsdown"	},
+	{VM_PFNMAP,			"pfnmap"	},
+	{VM_DENYWRITE,			"denywrite"	},
+	{VM_LOCKED,			"locked"	},
+	{VM_IO,				"io"		},
+	{VM_SEQ_READ,			"seqread"	},
+	{VM_RAND_READ,			"randread"	},
+	{VM_DONTCOPY,			"dontcopy"	},
+	{VM_DONTEXPAND,			"dontexpand"	},
+	{VM_ACCOUNT,			"account"	},
+	{VM_NORESERVE,			"noreserve"	},
+	{VM_HUGETLB,			"hugetlb"	},
+	{VM_NONLINEAR,			"nonlinear"	},
+#if defined(CONFIG_X86)
+	{VM_PAT,			"pat"		},
+#elif defined(CONFIG_PPC)
+	{VM_SAO,			"sao"		},
+#elif defined(CONFIG_PARISC) || defined(CONFIG_METAG) || defined(CONFIG_IA64)
+	{VM_GROWSUP,			"growsup"	},
+#elif !defined(CONFIG_MMU)
+	{VM_MAPPED_COPY,		"mappedcopy"	},
+#else
+	{VM_ARCH_1,			"arch_1"	},
+#endif
+	{VM_DONTDUMP,			"dontdump"	},
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	{VM_SOFTDIRTY,			"softdirty"	},
+#endif
+	{VM_MIXEDMAP,			"mixedmap"	},
+	{VM_HUGEPAGE,			"hugepage"	},
+	{VM_NOHUGEPAGE,			"nohugepage"	},
+	{VM_MERGEABLE,			"mergeable"	},
+};
+
+void dump_vma(const struct vm_area_struct *vma)
+{
+	pr_emerg("vma %p start %p end %p\n"
+		"next %p prev %p mm %p\n"
+		"prot %lx anon_vma %p vm_ops %p\n"
+		"pgoff %lx file %p private_data %p\n",
+		vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
+		vma->vm_prev, vma->vm_mm,
+		(unsigned long)pgprot_val(vma->vm_page_prot),
+		vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
+		vma->vm_file, vma->vm_private_data);
+	dump_flags(vma->vm_flags, vmaflags_names, ARRAY_SIZE(vmaflags_names));
+}
+EXPORT_SYMBOL(dump_vma);
+
+void dump_mm(const struct mm_struct *mm)
+{
+	pr_emerg("mm %p mmap %p seqnum %d task_size %lu\n"
+#ifdef CONFIG_MMU
+		"get_unmapped_area %p\n"
+#endif
+		"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
+		"pgd %p mm_users %d mm_count %d nr_ptes %lu map_count %d\n"
+		"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
+		"pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n"
+		"start_code %lx end_code %lx start_data %lx end_data %lx\n"
+		"start_brk %lx brk %lx start_stack %lx\n"
+		"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
+		"binfmt %p flags %lx core_state %p\n"
+#ifdef CONFIG_AIO
+		"ioctx_table %p\n"
+#endif
+#ifdef CONFIG_MEMCG
+		"owner %p "
+#endif
+		"exe_file %p\n"
+#ifdef CONFIG_MMU_NOTIFIER
+		"mmu_notifier_mm %p\n"
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+		"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
+#endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+		"tlb_flush_pending %d\n"
+#endif
+		"%s",	/* This is here to hold the comma */
+
+		mm, mm->mmap, mm->vmacache_seqnum, mm->task_size,
+#ifdef CONFIG_MMU
+		mm->get_unmapped_area,
+#endif
+		mm->mmap_base, mm->mmap_legacy_base, mm->highest_vm_end,
+		mm->pgd, atomic_read(&mm->mm_users),
+		atomic_read(&mm->mm_count),
+		atomic_long_read((atomic_long_t *)&mm->nr_ptes),
+		mm->map_count,
+		mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
+		mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm,
+		mm->start_code, mm->end_code, mm->start_data, mm->end_data,
+		mm->start_brk, mm->brk, mm->start_stack,
+		mm->arg_start, mm->arg_end, mm->env_start, mm->env_end,
+		mm->binfmt, mm->flags, mm->core_state,
+#ifdef CONFIG_AIO
+		mm->ioctx_table,
+#endif
+#ifdef CONFIG_MEMCG
+		mm->owner,
+#endif
+		mm->exe_file,
+#ifdef CONFIG_MMU_NOTIFIER
+		mm->mmu_notifier_mm,
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+		mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
+#endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+		mm->tlb_flush_pending,
+#endif
+		""		/* This is here to not have a comma! */
+		);
+
+		dump_flags(mm->def_flags, vmaflags_names,
+				ARRAY_SIZE(vmaflags_names));
+}
+
+#endif		/* CONFIG_DEBUG_VM */
diff --git a/mm/dmapool.c b/mm/dmapool.c
index ba8019b063e1..fd5fe4342e93 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -62,6 +62,7 @@ struct dma_page {		/* cacheable header for 'allocation' bytes */
 };
 
 static DEFINE_MUTEX(pools_lock);
+static DEFINE_MUTEX(pools_reg_lock);
 
 static ssize_t
 show_pools(struct device *dev, struct device_attribute *attr, char *buf)
@@ -132,29 +133,27 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev,
 {
 	struct dma_pool *retval;
 	size_t allocation;
+	bool empty = false;
 
-	if (align == 0) {
+	if (align == 0)
 		align = 1;
-	} else if (align & (align - 1)) {
+	else if (align & (align - 1))
 		return NULL;
-	}
 
-	if (size == 0) {
+	if (size == 0)
 		return NULL;
-	} else if (size < 4) {
+	else if (size < 4)
 		size = 4;
-	}
 
 	if ((size % align) != 0)
 		size = ALIGN(size, align);
 
 	allocation = max_t(size_t, size, PAGE_SIZE);
 
-	if (!boundary) {
+	if (!boundary)
 		boundary = allocation;
-	} else if ((boundary < size) || (boundary & (boundary - 1))) {
+	else if ((boundary < size) || (boundary & (boundary - 1)))
 		return NULL;
-	}
 
 	retval = kmalloc_node(sizeof(*retval), GFP_KERNEL, dev_to_node(dev));
 	if (!retval)
@@ -172,15 +171,34 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev,
 
 	INIT_LIST_HEAD(&retval->pools);
 
+	/*
+	 * pools_lock ensures that the ->dma_pools list does not get corrupted.
+	 * pools_reg_lock ensures that there is not a race between
+	 * dma_pool_create() and dma_pool_destroy() or within dma_pool_create()
+	 * when the first invocation of dma_pool_create() failed on
+	 * device_create_file() and the second assumes that it has been done (I
+	 * know it is a short window).
+	 */
+	mutex_lock(&pools_reg_lock);
 	mutex_lock(&pools_lock);
-	if (list_empty(&dev->dma_pools) &&
-	    device_create_file(dev, &dev_attr_pools)) {
-		kfree(retval);
-		retval = NULL;
-	} else
-		list_add(&retval->pools, &dev->dma_pools);
+	if (list_empty(&dev->dma_pools))
+		empty = true;
+	list_add(&retval->pools, &dev->dma_pools);
 	mutex_unlock(&pools_lock);
-
+	if (empty) {
+		int err;
+
+		err = device_create_file(dev, &dev_attr_pools);
+		if (err) {
+			mutex_lock(&pools_lock);
+			list_del(&retval->pools);
+			mutex_unlock(&pools_lock);
+			mutex_unlock(&pools_reg_lock);
+			kfree(retval);
+			return NULL;
+		}
+	}
+	mutex_unlock(&pools_reg_lock);
 	return retval;
 }
 EXPORT_SYMBOL(dma_pool_create);
@@ -251,11 +269,17 @@ static void pool_free_page(struct dma_pool *pool, struct dma_page *page)
  */
 void dma_pool_destroy(struct dma_pool *pool)
 {
+	bool empty = false;
+
+	mutex_lock(&pools_reg_lock);
 	mutex_lock(&pools_lock);
 	list_del(&pool->pools);
 	if (pool->dev && list_empty(&pool->dev->dma_pools))
-		device_remove_file(pool->dev, &dev_attr_pools);
+		empty = true;
 	mutex_unlock(&pools_lock);
+	if (empty)
+		device_remove_file(pool->dev, &dev_attr_pools);
+	mutex_unlock(&pools_reg_lock);
 
 	while (!list_empty(&pool->page_list)) {
 		struct dma_page *page;
diff --git a/mm/filemap.c b/mm/filemap.c
index 0ab0a3ea5721..14b4642279f1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1753,7 +1753,7 @@ EXPORT_SYMBOL(generic_file_read_iter);
 static int page_cache_read(struct file *file, pgoff_t offset)
 {
 	struct address_space *mapping = file->f_mapping;
-	struct page *page; 
+	struct page *page;
 	int ret;
 
 	do {
@@ -1770,7 +1770,7 @@ static int page_cache_read(struct file *file, pgoff_t offset)
 		page_cache_release(page);
 
 	} while (ret == AOP_TRUNCATED_PAGE);
-		
+
 	return ret;
 }
 
diff --git a/mm/gup.c b/mm/gup.c
index af7ea3e0826b..cd62c8c90d4a 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -10,6 +10,10 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 
+#include <linux/sched.h>
+#include <linux/rwsem.h>
+#include <asm/pgtable.h>
+
 #include "internal.h"
 
 static struct page *no_page_table(struct vm_area_struct *vma,
@@ -676,3 +680,353 @@ struct page *get_dump_page(unsigned long addr)
 	return page;
 }
 #endif /* CONFIG_ELF_CORE */
+
+/*
+ * Generic RCU Fast GUP
+ *
+ * get_user_pages_fast attempts to pin user pages by walking the page
+ * tables directly and avoids taking locks. Thus the walker needs to be
+ * protected from page table pages being freed from under it, and should
+ * block any THP splits.
+ *
+ * One way to achieve this is to have the walker disable interrupts, and
+ * rely on IPIs from the TLB flushing code blocking before the page table
+ * pages are freed. This is unsuitable for architectures that do not need
+ * to broadcast an IPI when invalidating TLBs.
+ *
+ * Another way to achieve this is to batch up page table containing pages
+ * belonging to more than one mm_user, then rcu_sched a callback to free those
+ * pages. Disabling interrupts will allow the fast_gup walker to both block
+ * the rcu_sched callback, and an IPI that we broadcast for splitting THPs
+ * (which is a relatively rare event). The code below adopts this strategy.
+ *
+ * Before activating this code, please be aware that the following assumptions
+ * are currently made:
+ *
+ *  *) HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table is used to free
+ *      pages containing page tables.
+ *
+ *  *) THP splits will broadcast an IPI, this can be achieved by overriding
+ *      pmdp_splitting_flush.
+ *
+ *  *) ptes can be read atomically by the architecture.
+ *
+ *  *) access_ok is sufficient to validate userspace address ranges.
+ *
+ * The last two assumptions can be relaxed by the addition of helper functions.
+ *
+ * This code is based heavily on the PowerPC implementation by Nick Piggin.
+ */
+#ifdef CONFIG_HAVE_GENERIC_RCU_GUP
+
+#ifdef __HAVE_ARCH_PTE_SPECIAL
+static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
+			 int write, struct page **pages, int *nr)
+{
+	pte_t *ptep, *ptem;
+	int ret = 0;
+
+	ptem = ptep = pte_offset_map(&pmd, addr);
+	do {
+		/*
+		 * In the line below we are assuming that the pte can be read
+		 * atomically. If this is not the case for your architecture,
+		 * please wrap this in a helper function!
+		 *
+		 * for an example see gup_get_pte in arch/x86/mm/gup.c
+		 */
+		pte_t pte = ACCESS_ONCE(*ptep);
+		struct page *page;
+
+		/*
+		 * Similar to the PMD case below, NUMA hinting must take slow
+		 * path
+		 */
+		if (!pte_present(pte) || pte_special(pte) ||
+			pte_numa(pte) || (write && !pte_write(pte)))
+			goto pte_unmap;
+
+		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+		page = pte_page(pte);
+
+		if (!page_cache_get_speculative(page))
+			goto pte_unmap;
+
+		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+			put_page(page);
+			goto pte_unmap;
+		}
+
+		pages[*nr] = page;
+		(*nr)++;
+
+	} while (ptep++, addr += PAGE_SIZE, addr != end);
+
+	ret = 1;
+
+pte_unmap:
+	pte_unmap(ptem);
+	return ret;
+}
+#else
+
+/*
+ * If we can't determine whether or not a pte is special, then fail immediately
+ * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not
+ * to be special.
+ *
+ * For a futex to be placed on a THP tail page, get_futex_key requires a
+ * __get_user_pages_fast implementation that can pin pages. Thus it's still
+ * useful to have gup_huge_pmd even if we can't operate on ptes.
+ */
+static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
+			 int write, struct page **pages, int *nr)
+{
+	return 0;
+}
+#endif /* __HAVE_ARCH_PTE_SPECIAL */
+
+static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	struct page *head, *page, *tail;
+	int refs;
+
+	if (write && !pmd_write(orig))
+		return 0;
+
+	refs = 0;
+	head = pmd_page(orig);
+	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	tail = page;
+	do {
+		VM_BUG_ON_PAGE(compound_head(page) != head, page);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	/*
+	 * Any tail pages need their mapcount reference taken before we
+	 * return. (This allows the THP code to bump their ref count when
+	 * they are split into base pages).
+	 */
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
+	}
+
+	return 1;
+}
+
+static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	struct page *head, *page, *tail;
+	int refs;
+
+	if (write && !pud_write(orig))
+		return 0;
+
+	refs = 0;
+	head = pud_page(orig);
+	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	tail = page;
+	do {
+		VM_BUG_ON_PAGE(compound_head(page) != head, page);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
+	}
+
+	return 1;
+}
+
+static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
+		int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	pmd_t *pmdp;
+
+	pmdp = pmd_offset(&pud, addr);
+	do {
+		pmd_t pmd = ACCESS_ONCE(*pmdp);
+
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
+			return 0;
+
+		if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) {
+			/*
+			 * NUMA hinting faults need to be handled in the GUP
+			 * slowpath for accounting purposes and so that they
+			 * can be serialised against THP migration.
+			 */
+			if (pmd_numa(pmd))
+				return 0;
+
+			if (!gup_huge_pmd(pmd, pmdp, addr, next, write,
+				pages, nr))
+				return 0;
+
+		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
+				return 0;
+	} while (pmdp++, addr = next, addr != end);
+
+	return 1;
+}
+
+static int gup_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end,
+		int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	pud_t *pudp;
+
+	pudp = pud_offset(pgdp, addr);
+	do {
+		pud_t pud = ACCESS_ONCE(*pudp);
+
+		next = pud_addr_end(addr, end);
+		if (pud_none(pud))
+			return 0;
+		if (pud_huge(pud)) {
+			if (!gup_huge_pud(pud, pudp, addr, next, write,
+					pages, nr))
+				return 0;
+		} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
+			return 0;
+	} while (pudp++, addr = next, addr != end);
+
+	return 1;
+}
+
+/*
+ * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
+ * the regular GUP. It will only return non-negative values.
+ */
+int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			  struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr, len, end;
+	unsigned long next, flags;
+	pgd_t *pgdp;
+	int nr = 0;
+
+	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+
+	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
+					start, len)))
+		return 0;
+
+	/*
+	 * Disable interrupts.  We use the nested form as we can already have
+	 * interrupts disabled by get_futex_key.
+	 *
+	 * With interrupts disabled, we block page table pages from being
+	 * freed from under us. See mmu_gather_tlb in asm-generic/tlb.h
+	 * for more details.
+	 *
+	 * We do not adopt an rcu_read_lock(.) here as we also want to
+	 * block IPIs that come from THPs splitting.
+	 */
+
+	local_irq_save(flags);
+	pgdp = pgd_offset(mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(*pgdp))
+			break;
+		else if (!gup_pud_range(pgdp, addr, next, write, pages, &nr))
+			break;
+	} while (pgdp++, addr = next, addr != end);
+	local_irq_restore(flags);
+
+	return nr;
+}
+
+/**
+ * get_user_pages_fast() - pin user pages in memory
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @write:	whether pages will be written to
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long.
+ *
+ * Attempt to pin user pages in memory without taking mm->mmap_sem.
+ * If not successful, it will fall back to taking the lock and
+ * calling get_user_pages().
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno.
+ */
+int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	int nr, ret;
+
+	start &= PAGE_MASK;
+	nr = __get_user_pages_fast(start, nr_pages, write, pages);
+	ret = nr;
+
+	if (nr < nr_pages) {
+		/* Try to get the remaining pages with get_user_pages */
+		start += nr << PAGE_SHIFT;
+		pages += nr;
+
+		down_read(&mm->mmap_sem);
+		ret = get_user_pages(current, mm, start,
+				     nr_pages - nr, write, 0, pages, NULL);
+		up_read(&mm->mmap_sem);
+
+		/* Have to be a bit careful with return values */
+		if (nr > 0) {
+			if (ret < 0)
+				ret = nr;
+			else
+				ret += nr;
+		}
+	}
+
+	return ret;
+}
+
+#endif /* CONFIG_HAVE_GENERIC_RCU_GUP */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f8ffd9412ec5..74c78aa8bc2f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1096,7 +1096,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long mmun_end;		/* For mmu_notifiers */
 
 	ptl = pmd_lockptr(mm, pmd);
-	VM_BUG_ON(!vma->anon_vma);
+	VM_BUG_ON_VMA(!vma->anon_vma, vma);
 	haddr = address & HPAGE_PMD_MASK;
 	if (is_huge_zero_pmd(orig_pmd))
 		goto alloc;
@@ -2048,7 +2048,7 @@ int __khugepaged_enter(struct mm_struct *mm)
 		return -ENOMEM;
 
 	/* __khugepaged_exit() must not run from under us */
-	VM_BUG_ON(khugepaged_test_exit(mm));
+	VM_BUG_ON_MM(khugepaged_test_exit(mm), mm);
 	if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) {
 		free_mm_slot(mm_slot);
 		return 0;
@@ -2083,7 +2083,7 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
 	if (vma->vm_ops)
 		/* khugepaged not yet working on file or special mappings */
 		return 0;
-	VM_BUG_ON(vma->vm_flags & VM_NO_THP);
+	VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
@@ -2322,23 +2322,17 @@ static struct page
 		       int node)
 {
 	VM_BUG_ON_PAGE(*hpage, *hpage);
+
 	/*
-	 * Allocate the page while the vma is still valid and under
-	 * the mmap_sem read mode so there is no memory allocation
-	 * later when we take the mmap_sem in write mode. This is more
-	 * friendly behavior (OTOH it may actually hide bugs) to
-	 * filesystems in userland with daemons allocating memory in
-	 * the userland I/O paths.  Allocating memory with the
-	 * mmap_sem in read mode is good idea also to allow greater
-	 * scalability.
+	 * Before allocating the hugepage, release the mmap_sem read lock.
+	 * The allocation can take potentially a long time if it involves
+	 * sync compaction, and we do not need to hold the mmap_sem during
+	 * that. We will recheck the vma after taking it again in write mode.
 	 */
+	up_read(&mm->mmap_sem);
+
 	*hpage = alloc_pages_exact_node(node, alloc_hugepage_gfpmask(
 		khugepaged_defrag(), __GFP_OTHER_NODE), HPAGE_PMD_ORDER);
-	/*
-	 * After allocating the hugepage, release the mmap_sem read lock in
-	 * preparation for taking it in write mode.
-	 */
-	up_read(&mm->mmap_sem);
 	if (unlikely(!*hpage)) {
 		count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
 		*hpage = ERR_PTR(-ENOMEM);
@@ -2412,7 +2406,7 @@ static bool hugepage_vma_check(struct vm_area_struct *vma)
 		return false;
 	if (is_vma_temporary_stack(vma))
 		return false;
-	VM_BUG_ON(vma->vm_flags & VM_NO_THP);
+	VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
 	return true;
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index eeceeeb09019..9fd722769927 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -434,7 +434,7 @@ static inline struct resv_map *inode_resv_map(struct inode *inode)
 
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
 {
-	VM_BUG_ON(!is_vm_hugetlb_page(vma));
+	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
 	if (vma->vm_flags & VM_MAYSHARE) {
 		struct address_space *mapping = vma->vm_file->f_mapping;
 		struct inode *inode = mapping->host;
@@ -449,8 +449,8 @@ static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
 
 static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
 {
-	VM_BUG_ON(!is_vm_hugetlb_page(vma));
-	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);
+	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
+	VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma);
 
 	set_vma_private_data(vma, (get_vma_private_data(vma) &
 				HPAGE_RESV_MASK) | (unsigned long)map);
@@ -458,15 +458,15 @@ static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
 
 static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
 {
-	VM_BUG_ON(!is_vm_hugetlb_page(vma));
-	VM_BUG_ON(vma->vm_flags & VM_MAYSHARE);
+	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
+	VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma);
 
 	set_vma_private_data(vma, get_vma_private_data(vma) | flags);
 }
 
 static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 {
-	VM_BUG_ON(!is_vm_hugetlb_page(vma));
+	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
 
 	return (get_vma_private_data(vma) & flag) != 0;
 }
@@ -474,7 +474,7 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 /* Reset counters to 0 and clear all HPAGE_RESV_* flags */
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 {
-	VM_BUG_ON(!is_vm_hugetlb_page(vma));
+	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
 	if (!(vma->vm_flags & VM_MAYSHARE))
 		vma->vm_private_data = (void *)0;
 }
diff --git a/mm/internal.h b/mm/internal.h
index a1b651b11c5f..829304090b90 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -142,10 +142,10 @@ struct compact_control {
 	bool finished_update_migrate;
 
 	int order;			/* order a direct compactor needs */
-	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
+	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
 	struct zone *zone;
-	bool contended;			/* True if a lock was contended, or
-					 * need_resched() true during async
+	int contended;			/* Signal need_sched() or lock
+					 * contention detected during
 					 * compaction
 					 */
 };
@@ -154,8 +154,8 @@ unsigned long
 isolate_freepages_range(struct compact_control *cc,
 			unsigned long start_pfn, unsigned long end_pfn);
 unsigned long
-isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
-	unsigned long low_pfn, unsigned long end_pfn, bool unevictable);
+isolate_migratepages_range(struct compact_control *cc,
+			   unsigned long low_pfn, unsigned long end_pfn);
 
 #endif
 
@@ -164,7 +164,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
  * general, page_zone(page)->lock must be held by the caller to prevent the
  * page from being allocated in parallel and returning garbage as the order.
  * If a caller does not hold page_zone(page)->lock, it must guarantee that the
- * page cannot be allocated or merged in parallel.
+ * page cannot be allocated or merged in parallel. Alternatively, it must
+ * handle invalid values gracefully, and use page_order_unsafe() below.
  */
 static inline unsigned long page_order(struct page *page)
 {
@@ -172,6 +173,19 @@ static inline unsigned long page_order(struct page *page)
 	return page_private(page);
 }
 
+/*
+ * Like page_order(), but for callers who cannot afford to hold the zone lock.
+ * PageBuddy() should be checked first by the caller to minimize race window,
+ * and invalid values must be handled gracefully.
+ *
+ * ACCESS_ONCE is used so that if the caller assigns the result into a local
+ * variable and e.g. tests it for valid range before using, the compiler cannot
+ * decide to remove the variable and inline the page_private(page) multiple
+ * times, potentially observing different values in the tests and the actual
+ * use of the result.
+ */
+#define page_order_unsafe(page)		ACCESS_ONCE(page_private(page))
+
 static inline bool is_cow_mapping(vm_flags_t flags)
 {
 	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
diff --git a/mm/interval_tree.c b/mm/interval_tree.c
index 4a5822a586e6..8da581fa9060 100644
--- a/mm/interval_tree.c
+++ b/mm/interval_tree.c
@@ -34,7 +34,7 @@ void vma_interval_tree_insert_after(struct vm_area_struct *node,
 	struct vm_area_struct *parent;
 	unsigned long last = vma_last_pgoff(node);
 
-	VM_BUG_ON(vma_start_pgoff(node) != vma_start_pgoff(prev));
+	VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node);
 
 	if (!prev->shared.linear.rb.rb_right) {
 		parent = prev;
diff --git a/mm/iov_iter.c b/mm/iov_iter.c
index 9a09f2034fcc..eafcf60f6b83 100644
--- a/mm/iov_iter.c
+++ b/mm/iov_iter.c
@@ -4,6 +4,96 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
+static size_t copy_to_iter_iovec(void *from, size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __copy_to_user(buf, from, copy);
+	copy -= left;
+	skip += copy;
+	from += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_to_user(buf, from, copy);
+		copy -= left;
+		skip = copy;
+		from += copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t copy_from_iter_iovec(void *to, size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __copy_from_user(to, buf, copy);
+	copy -= left;
+	skip += copy;
+	to += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_from_user(to, buf, copy);
+		copy -= left;
+		skip = copy;
+		to += copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
 static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i)
 {
@@ -166,6 +256,50 @@ done:
 	return wanted - bytes;
 }
 
+static size_t zero_iovec(size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __clear_user(buf, copy);
+	copy -= left;
+	skip += copy;
+	bytes -= copy;
+
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __clear_user(buf, copy);
+		copy -= left;
+		skip = copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
 static size_t __iovec_copy_from_user_inatomic(char *vaddr,
 			const struct iovec *iov, size_t base, size_t bytes)
 {
@@ -414,12 +548,17 @@ static void memcpy_to_page(struct page *page, size_t offset, char *from, size_t
 	kunmap_atomic(to);
 }
 
-static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t bytes,
-			 struct iov_iter *i)
+static void memzero_page(struct page *page, size_t offset, size_t len)
+{
+	char *addr = kmap_atomic(page);
+	memset(addr + offset, 0, len);
+	kunmap_atomic(addr);
+}
+
+static size_t copy_to_iter_bvec(void *from, size_t bytes, struct iov_iter *i)
 {
 	size_t skip, copy, wanted;
 	const struct bio_vec *bvec;
-	void *kaddr, *from;
 
 	if (unlikely(bytes > i->count))
 		bytes = i->count;
@@ -432,8 +571,6 @@ static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t by
 	skip = i->iov_offset;
 	copy = min_t(size_t, bytes, bvec->bv_len - skip);
 
-	kaddr = kmap_atomic(page);
-	from = kaddr + offset;
 	memcpy_to_page(bvec->bv_page, skip + bvec->bv_offset, from, copy);
 	skip += copy;
 	from += copy;
@@ -446,7 +583,6 @@ static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t by
 		from += copy;
 		bytes -= copy;
 	}
-	kunmap_atomic(kaddr);
 	if (skip == bvec->bv_len) {
 		bvec++;
 		skip = 0;
@@ -458,12 +594,10 @@ static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t by
 	return wanted - bytes;
 }
 
-static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t bytes,
-			 struct iov_iter *i)
+static size_t copy_from_iter_bvec(void *to, size_t bytes, struct iov_iter *i)
 {
 	size_t skip, copy, wanted;
 	const struct bio_vec *bvec;
-	void *kaddr, *to;
 
 	if (unlikely(bytes > i->count))
 		bytes = i->count;
@@ -475,10 +609,6 @@ static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t
 	bvec = i->bvec;
 	skip = i->iov_offset;
 
-	kaddr = kmap_atomic(page);
-
-	to = kaddr + offset;
-
 	copy = min(bytes, bvec->bv_len - skip);
 
 	memcpy_from_page(to, bvec->bv_page, bvec->bv_offset + skip, copy);
@@ -495,7 +625,6 @@ static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t
 		to += copy;
 		bytes -= copy;
 	}
-	kunmap_atomic(kaddr);
 	if (skip == bvec->bv_len) {
 		bvec++;
 		skip = 0;
@@ -507,6 +636,61 @@ static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t
 	return wanted;
 }
 
+static size_t copy_page_to_iter_bvec(struct page *page, size_t offset,
+					size_t bytes, struct iov_iter *i)
+{
+	void *kaddr = kmap_atomic(page);
+	size_t wanted = copy_to_iter_bvec(kaddr + offset, bytes, i);
+	kunmap_atomic(kaddr);
+	return wanted;
+}
+
+static size_t copy_page_from_iter_bvec(struct page *page, size_t offset,
+					size_t bytes, struct iov_iter *i)
+{
+	void *kaddr = kmap_atomic(page);
+	size_t wanted = copy_from_iter_bvec(kaddr + offset, bytes, i);
+	kunmap_atomic(kaddr);
+	return wanted;
+}
+
+static size_t zero_bvec(size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, wanted;
+	const struct bio_vec *bvec;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	bvec = i->bvec;
+	skip = i->iov_offset;
+	copy = min_t(size_t, bytes, bvec->bv_len - skip);
+
+	memzero_page(bvec->bv_page, skip + bvec->bv_offset, copy);
+	skip += copy;
+	bytes -= copy;
+	while (bytes) {
+		bvec++;
+		copy = min(bytes, (size_t)bvec->bv_len);
+		memzero_page(bvec->bv_page, bvec->bv_offset, copy);
+		skip = copy;
+		bytes -= copy;
+	}
+	if (skip == bvec->bv_len) {
+		bvec++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= bvec - i->bvec;
+	i->bvec = bvec;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
 static size_t copy_from_user_bvec(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes)
 {
@@ -672,6 +856,34 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 }
 EXPORT_SYMBOL(copy_page_from_iter);
 
+size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_to_iter_bvec(addr, bytes, i);
+	else
+		return copy_to_iter_iovec(addr, bytes, i);
+}
+EXPORT_SYMBOL(copy_to_iter);
+
+size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_from_iter_bvec(addr, bytes, i);
+	else
+		return copy_from_iter_iovec(addr, bytes, i);
+}
+EXPORT_SYMBOL(copy_from_iter);
+
+size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC) {
+		return zero_bvec(bytes, i);
+	} else {
+		return zero_iovec(bytes, i);
+	}
+}
+EXPORT_SYMBOL(iov_iter_zero);
+
 size_t iov_iter_copy_from_user_atomic(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes)
 {
diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c
index fd814fd61319..cab58bb592d8 100644
--- a/mm/kmemcheck.c
+++ b/mm/kmemcheck.c
@@ -2,6 +2,7 @@
 #include <linux/mm_types.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include "slab.h"
 #include <linux/kmemcheck.h>
 
 void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node)
diff --git a/mm/ksm.c b/mm/ksm.c
index fb7590222706..6b2e337bc03c 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2310,7 +2310,7 @@ static int __init ksm_init(void)
 
 	ksm_thread = kthread_run(ksm_scan_thread, NULL, "ksmd");
 	if (IS_ERR(ksm_thread)) {
-		printk(KERN_ERR "ksm: creating kthread failed\n");
+		pr_err("ksm: creating kthread failed\n");
 		err = PTR_ERR(ksm_thread);
 		goto out_free;
 	}
@@ -2318,7 +2318,7 @@ static int __init ksm_init(void)
 #ifdef CONFIG_SYSFS
 	err = sysfs_create_group(mm_kobj, &ksm_attr_group);
 	if (err) {
-		printk(KERN_ERR "ksm: register sysfs failed\n");
+		pr_err("ksm: register sysfs failed\n");
 		kthread_stop(ksm_thread);
 		goto out_free;
 	}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 28928ce9b07f..23976fd885fd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -318,9 +318,6 @@ struct mem_cgroup {
 	/* OOM-Killer disable */
 	int		oom_kill_disable;
 
-	/* set when res.limit == memsw.limit */
-	bool		memsw_is_minimum;
-
 	/* protect arrays of thresholds */
 	struct mutex thresholds_lock;
 
@@ -484,14 +481,6 @@ enum res_type {
 #define OOM_CONTROL		(0)
 
 /*
- * Reclaim flags for mem_cgroup_hierarchical_reclaim
- */
-#define MEM_CGROUP_RECLAIM_NOSWAP_BIT	0x0
-#define MEM_CGROUP_RECLAIM_NOSWAP	(1 << MEM_CGROUP_RECLAIM_NOSWAP_BIT)
-#define MEM_CGROUP_RECLAIM_SHRINK_BIT	0x1
-#define MEM_CGROUP_RECLAIM_SHRINK	(1 << MEM_CGROUP_RECLAIM_SHRINK_BIT)
-
-/*
  * The memcg_create_mutex will be held whenever a new cgroup is created.
  * As a consequence, any change that needs to protect against new child cgroups
  * appearing has to hold it as well.
@@ -649,11 +638,13 @@ int memcg_limited_groups_array_size;
 struct static_key memcg_kmem_enabled_key;
 EXPORT_SYMBOL(memcg_kmem_enabled_key);
 
+static void memcg_free_cache_id(int id);
+
 static void disarm_kmem_keys(struct mem_cgroup *memcg)
 {
 	if (memcg_kmem_is_active(memcg)) {
 		static_key_slow_dec(&memcg_kmem_enabled_key);
-		ida_simple_remove(&kmem_limited_groups, memcg->kmemcg_id);
+		memcg_free_cache_id(memcg->kmemcg_id);
 	}
 	/*
 	 * This check can't live in kmem destruction function,
@@ -1806,42 +1797,6 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 			 NULL, "Memory cgroup out of memory");
 }
 
-static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
-					gfp_t gfp_mask,
-					unsigned long flags)
-{
-	unsigned long total = 0;
-	bool noswap = false;
-	int loop;
-
-	if (flags & MEM_CGROUP_RECLAIM_NOSWAP)
-		noswap = true;
-	if (!(flags & MEM_CGROUP_RECLAIM_SHRINK) && memcg->memsw_is_minimum)
-		noswap = true;
-
-	for (loop = 0; loop < MEM_CGROUP_MAX_RECLAIM_LOOPS; loop++) {
-		if (loop)
-			drain_all_stock_async(memcg);
-		total += try_to_free_mem_cgroup_pages(memcg, gfp_mask, noswap);
-		/*
-		 * Allow limit shrinkers, which are triggered directly
-		 * by userspace, to catch signals and stop reclaim
-		 * after minimal progress, regardless of the margin.
-		 */
-		if (total && (flags & MEM_CGROUP_RECLAIM_SHRINK))
-			break;
-		if (mem_cgroup_margin(memcg))
-			break;
-		/*
-		 * If nothing was reclaimed after two attempts, there
-		 * may be no reclaimable pages in this hierarchy.
-		 */
-		if (loop && !total)
-			break;
-	}
-	return total;
-}
-
 /**
  * test_mem_cgroup_node_reclaimable
  * @memcg: the target memcg
@@ -2544,8 +2499,9 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	struct mem_cgroup *mem_over_limit;
 	struct res_counter *fail_res;
 	unsigned long nr_reclaimed;
-	unsigned long flags = 0;
 	unsigned long long size;
+	bool may_swap = true;
+	bool drained = false;
 	int ret = 0;
 
 	if (mem_cgroup_is_root(memcg))
@@ -2555,16 +2511,17 @@ retry:
 		goto done;
 
 	size = batch * PAGE_SIZE;
-	if (!res_counter_charge(&memcg->res, size, &fail_res)) {
-		if (!do_swap_account)
-			goto done_restock;
-		if (!res_counter_charge(&memcg->memsw, size, &fail_res))
+	if (!do_swap_account ||
+	    !res_counter_charge(&memcg->memsw, size, &fail_res)) {
+		if (!res_counter_charge(&memcg->res, size, &fail_res))
 			goto done_restock;
-		res_counter_uncharge(&memcg->res, size);
-		mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
-		flags |= MEM_CGROUP_RECLAIM_NOSWAP;
-	} else
+		if (do_swap_account)
+			res_counter_uncharge(&memcg->memsw, size);
 		mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
+	} else {
+		mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
+		may_swap = false;
+	}
 
 	if (batch > nr_pages) {
 		batch = nr_pages;
@@ -2588,11 +2545,18 @@ retry:
 	if (!(gfp_mask & __GFP_WAIT))
 		goto nomem;
 
-	nr_reclaimed = mem_cgroup_reclaim(mem_over_limit, gfp_mask, flags);
+	nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
+						    gfp_mask, may_swap);
 
 	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
 		goto retry;
 
+	if (!drained) {
+		drain_all_stock_async(mem_over_limit);
+		drained = true;
+		goto retry;
+	}
+
 	if (gfp_mask & __GFP_NORETRY)
 		goto nomem;
 	/*
@@ -2798,12 +2762,6 @@ static DEFINE_MUTEX(memcg_slab_mutex);
 
 static DEFINE_MUTEX(activate_kmem_mutex);
 
-static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg)
-{
-	return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg) &&
-		memcg_kmem_is_active(memcg);
-}
-
 /*
  * This is a bit cumbersome, but it is rarely used and avoids a backpointer
  * in the memcg_cache_params struct.
@@ -2823,7 +2781,7 @@ static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v)
 	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
 	struct memcg_cache_params *params;
 
-	if (!memcg_can_account_kmem(memcg))
+	if (!memcg_kmem_is_active(memcg))
 		return -EIO;
 
 	print_slabinfo_header(m);
@@ -2906,19 +2864,44 @@ int memcg_cache_id(struct mem_cgroup *memcg)
 	return memcg ? memcg->kmemcg_id : -1;
 }
 
-static size_t memcg_caches_array_size(int num_groups)
+static int memcg_alloc_cache_id(void)
 {
-	ssize_t size;
-	if (num_groups <= 0)
-		return 0;
+	int id, size;
+	int err;
+
+	id = ida_simple_get(&kmem_limited_groups,
+			    0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
+	if (id < 0)
+		return id;
+
+	if (id < memcg_limited_groups_array_size)
+		return id;
+
+	/*
+	 * There's no space for the new id in memcg_caches arrays,
+	 * so we have to grow them.
+	 */
 
-	size = 2 * num_groups;
+	size = 2 * (id + 1);
 	if (size < MEMCG_CACHES_MIN_SIZE)
 		size = MEMCG_CACHES_MIN_SIZE;
 	else if (size > MEMCG_CACHES_MAX_SIZE)
 		size = MEMCG_CACHES_MAX_SIZE;
 
-	return size;
+	mutex_lock(&memcg_slab_mutex);
+	err = memcg_update_all_caches(size);
+	mutex_unlock(&memcg_slab_mutex);
+
+	if (err) {
+		ida_simple_remove(&kmem_limited_groups, id);
+		return err;
+	}
+	return id;
+}
+
+static void memcg_free_cache_id(int id)
+{
+	ida_simple_remove(&kmem_limited_groups, id);
 }
 
 /*
@@ -2928,97 +2911,7 @@ static size_t memcg_caches_array_size(int num_groups)
  */
 void memcg_update_array_size(int num)
 {
-	if (num > memcg_limited_groups_array_size)
-		memcg_limited_groups_array_size = memcg_caches_array_size(num);
-}
-
-int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
-{
-	struct memcg_cache_params *cur_params = s->memcg_params;
-
-	VM_BUG_ON(!is_root_cache(s));
-
-	if (num_groups > memcg_limited_groups_array_size) {
-		int i;
-		struct memcg_cache_params *new_params;
-		ssize_t size = memcg_caches_array_size(num_groups);
-
-		size *= sizeof(void *);
-		size += offsetof(struct memcg_cache_params, memcg_caches);
-
-		new_params = kzalloc(size, GFP_KERNEL);
-		if (!new_params)
-			return -ENOMEM;
-
-		new_params->is_root_cache = true;
-
-		/*
-		 * There is the chance it will be bigger than
-		 * memcg_limited_groups_array_size, if we failed an allocation
-		 * in a cache, in which case all caches updated before it, will
-		 * have a bigger array.
-		 *
-		 * But if that is the case, the data after
-		 * memcg_limited_groups_array_size is certainly unused
-		 */
-		for (i = 0; i < memcg_limited_groups_array_size; i++) {
-			if (!cur_params->memcg_caches[i])
-				continue;
-			new_params->memcg_caches[i] =
-						cur_params->memcg_caches[i];
-		}
-
-		/*
-		 * Ideally, we would wait until all caches succeed, and only
-		 * then free the old one. But this is not worth the extra
-		 * pointer per-cache we'd have to have for this.
-		 *
-		 * It is not a big deal if some caches are left with a size
-		 * bigger than the others. And all updates will reset this
-		 * anyway.
-		 */
-		rcu_assign_pointer(s->memcg_params, new_params);
-		if (cur_params)
-			kfree_rcu(cur_params, rcu_head);
-	}
-	return 0;
-}
-
-int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s,
-			     struct kmem_cache *root_cache)
-{
-	size_t size;
-
-	if (!memcg_kmem_enabled())
-		return 0;
-
-	if (!memcg) {
-		size = offsetof(struct memcg_cache_params, memcg_caches);
-		size += memcg_limited_groups_array_size * sizeof(void *);
-	} else
-		size = sizeof(struct memcg_cache_params);
-
-	s->memcg_params = kzalloc(size, GFP_KERNEL);
-	if (!s->memcg_params)
-		return -ENOMEM;
-
-	if (memcg) {
-		s->memcg_params->memcg = memcg;
-		s->memcg_params->root_cache = root_cache;
-		css_get(&memcg->css);
-	} else
-		s->memcg_params->is_root_cache = true;
-
-	return 0;
-}
-
-void memcg_free_cache_params(struct kmem_cache *s)
-{
-	if (!s->memcg_params)
-		return;
-	if (!s->memcg_params->is_root_cache)
-		css_put(&s->memcg_params->memcg->css);
-	kfree(s->memcg_params);
+	memcg_limited_groups_array_size = num;
 }
 
 static void memcg_register_cache(struct mem_cgroup *memcg,
@@ -3051,6 +2944,7 @@ static void memcg_register_cache(struct mem_cgroup *memcg,
 	if (!cachep)
 		return;
 
+	css_get(&memcg->css);
 	list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches);
 
 	/*
@@ -3084,6 +2978,9 @@ static void memcg_unregister_cache(struct kmem_cache *cachep)
 	list_del(&cachep->memcg_params->list);
 
 	kmem_cache_destroy(cachep);
+
+	/* drop the reference taken in memcg_register_cache */
+	css_put(&memcg->css);
 }
 
 /*
@@ -3261,7 +3158,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep,
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference(current->mm->owner));
 
-	if (!memcg_can_account_kmem(memcg))
+	if (!memcg_kmem_is_active(memcg))
 		goto out;
 
 	memcg_cachep = cache_from_memcg_idx(cachep, memcg_cache_id(memcg));
@@ -3346,7 +3243,7 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
 
 	memcg = get_mem_cgroup_from_mm(current->mm);
 
-	if (!memcg_can_account_kmem(memcg)) {
+	if (!memcg_kmem_is_active(memcg)) {
 		css_put(&memcg->css);
 		return true;
 	}
@@ -3688,7 +3585,6 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 				unsigned long long val)
 {
 	int retry_count;
-	u64 memswlimit, memlimit;
 	int ret = 0;
 	int children = mem_cgroup_count_children(memcg);
 	u64 curusage, oldusage;
@@ -3715,31 +3611,23 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
 		 */
 		mutex_lock(&set_limit_mutex);
-		memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
-		if (memswlimit < val) {
+		if (res_counter_read_u64(&memcg->memsw, RES_LIMIT) < val) {
 			ret = -EINVAL;
 			mutex_unlock(&set_limit_mutex);
 			break;
 		}
 
-		memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
-		if (memlimit < val)
+		if (res_counter_read_u64(&memcg->res, RES_LIMIT) < val)
 			enlarge = 1;
 
 		ret = res_counter_set_limit(&memcg->res, val);
-		if (!ret) {
-			if (memswlimit == val)
-				memcg->memsw_is_minimum = true;
-			else
-				memcg->memsw_is_minimum = false;
-		}
 		mutex_unlock(&set_limit_mutex);
 
 		if (!ret)
 			break;
 
-		mem_cgroup_reclaim(memcg, GFP_KERNEL,
-				   MEM_CGROUP_RECLAIM_SHRINK);
+		try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, true);
+
 		curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)
@@ -3757,7 +3645,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 					unsigned long long val)
 {
 	int retry_count;
-	u64 memlimit, memswlimit, oldusage, curusage;
+	u64 oldusage, curusage;
 	int children = mem_cgroup_count_children(memcg);
 	int ret = -EBUSY;
 	int enlarge = 0;
@@ -3776,30 +3664,21 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
 		 */
 		mutex_lock(&set_limit_mutex);
-		memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
-		if (memlimit > val) {
+		if (res_counter_read_u64(&memcg->res, RES_LIMIT) > val) {
 			ret = -EINVAL;
 			mutex_unlock(&set_limit_mutex);
 			break;
 		}
-		memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
-		if (memswlimit < val)
+		if (res_counter_read_u64(&memcg->memsw, RES_LIMIT) < val)
 			enlarge = 1;
 		ret = res_counter_set_limit(&memcg->memsw, val);
-		if (!ret) {
-			if (memlimit == val)
-				memcg->memsw_is_minimum = true;
-			else
-				memcg->memsw_is_minimum = false;
-		}
 		mutex_unlock(&set_limit_mutex);
 
 		if (!ret)
 			break;
 
-		mem_cgroup_reclaim(memcg, GFP_KERNEL,
-				   MEM_CGROUP_RECLAIM_NOSWAP |
-				   MEM_CGROUP_RECLAIM_SHRINK);
+		try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, false);
+
 		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)
@@ -4048,8 +3927,8 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 		if (signal_pending(current))
 			return -EINTR;
 
-		progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL,
-						false);
+		progress = try_to_free_mem_cgroup_pages(memcg, 1,
+							GFP_KERNEL, true);
 		if (!progress) {
 			nr_retries--;
 			/* maybe some writeback is necessary */
@@ -4214,23 +4093,12 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg,
 	if (err)
 		goto out;
 
-	memcg_id = ida_simple_get(&kmem_limited_groups,
-				  0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
+	memcg_id = memcg_alloc_cache_id();
 	if (memcg_id < 0) {
 		err = memcg_id;
 		goto out;
 	}
 
-	/*
-	 * Make sure we have enough space for this cgroup in each root cache's
-	 * memcg_params.
-	 */
-	mutex_lock(&memcg_slab_mutex);
-	err = memcg_update_all_caches(memcg_id + 1);
-	mutex_unlock(&memcg_slab_mutex);
-	if (err)
-		goto out_rmid;
-
 	memcg->kmemcg_id = memcg_id;
 	INIT_LIST_HEAD(&memcg->memcg_slab_caches);
 
@@ -4251,10 +4119,6 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg,
 out:
 	memcg_resume_kmem_account();
 	return err;
-
-out_rmid:
-	ida_simple_remove(&kmem_limited_groups, memcg_id);
-	goto out;
 }
 
 static int memcg_activate_kmem(struct mem_cgroup *memcg,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 44c6bd201d3a..8639f6b28746 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -148,7 +148,7 @@ static int hwpoison_filter_task(struct page *p)
 	ino = cgroup_ino(css->cgroup);
 	css_put(css);
 
-	if (!ino || ino != hwpoison_filter_memcg)
+	if (ino != hwpoison_filter_memcg)
 		return -EINVAL;
 
 	return 0;
diff --git a/mm/memory.c b/mm/memory.c
index e229970e4223..1cc6bfbd872e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2053,7 +2053,8 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	old_page = vm_normal_page(vma, address, orig_pte);
 	if (!old_page) {
 		/*
-		 * VM_MIXEDMAP !pfn_valid() case
+		 * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a
+		 * VM_PFNMAP VMA.
 		 *
 		 * We should not cow pages in a shared writeable mapping.
 		 * Just mark the pages writable as we can't do any dirty
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 2ff8c2325e96..29d8693d0c61 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1307,7 +1307,7 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
 /*
  * Confirm all pages in a range [start, end) is belongs to the same zone.
  */
-static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
+int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long pfn;
 	struct zone *zone = NULL;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 8f5330d74f47..e58725aff7e9 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -123,25 +123,23 @@ static struct mempolicy default_policy = {
 
 static struct mempolicy preferred_node_policy[MAX_NUMNODES];
 
-static struct mempolicy *get_task_policy(struct task_struct *p)
+struct mempolicy *get_task_policy(struct task_struct *p)
 {
 	struct mempolicy *pol = p->mempolicy;
+	int node;
 
-	if (!pol) {
-		int node = numa_node_id();
+	if (pol)
+		return pol;
 
-		if (node != NUMA_NO_NODE) {
-			pol = &preferred_node_policy[node];
-			/*
-			 * preferred_node_policy is not initialised early in
-			 * boot
-			 */
-			if (!pol->mode)
-				pol = NULL;
-		}
+	node = numa_node_id();
+	if (node != NUMA_NO_NODE) {
+		pol = &preferred_node_policy[node];
+		/* preferred_node_policy is not initialised early in boot */
+		if (pol->mode)
+			return pol;
 	}
 
-	return pol;
+	return &default_policy;
 }
 
 static const struct mempolicy_operations {
@@ -683,7 +681,9 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 		}
 
 		if (flags & MPOL_MF_LAZY) {
-			change_prot_numa(vma, start, endvma);
+			/* Similar to task_numa_work, skip inaccessible VMAs */
+			if (vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))
+				change_prot_numa(vma, start, endvma);
 			goto next;
 		}
 
@@ -804,7 +804,6 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 			     nodemask_t *nodes)
 {
 	struct mempolicy *new, *old;
-	struct mm_struct *mm = current->mm;
 	NODEMASK_SCRATCH(scratch);
 	int ret;
 
@@ -816,20 +815,11 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 		ret = PTR_ERR(new);
 		goto out;
 	}
-	/*
-	 * prevent changing our mempolicy while show_numa_maps()
-	 * is using it.
-	 * Note:  do_set_mempolicy() can be called at init time
-	 * with no 'mm'.
-	 */
-	if (mm)
-		down_write(&mm->mmap_sem);
+
 	task_lock(current);
 	ret = mpol_set_nodemask(new, nodes, scratch);
 	if (ret) {
 		task_unlock(current);
-		if (mm)
-			up_write(&mm->mmap_sem);
 		mpol_put(new);
 		goto out;
 	}
@@ -839,9 +829,6 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 	    nodes_weight(new->v.nodes))
 		current->il_next = first_node(new->v.nodes);
 	task_unlock(current);
-	if (mm)
-		up_write(&mm->mmap_sem);
-
 	mpol_put(old);
 	ret = 0;
 out:
@@ -1605,32 +1592,14 @@ COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len,
 
 #endif
 
-/*
- * get_vma_policy(@task, @vma, @addr)
- * @task: task for fallback if vma policy == default
- * @vma: virtual memory area whose policy is sought
- * @addr: address in @vma for shared policy lookup
- *
- * Returns effective policy for a VMA at specified address.
- * Falls back to @task or system default policy, as necessary.
- * Current or other task's task mempolicy and non-shared vma policies must be
- * protected by task_lock(task) by the caller.
- * Shared policies [those marked as MPOL_F_SHARED] require an extra reference
- * count--added by the get_policy() vm_op, as appropriate--to protect against
- * freeing by another task.  It is the caller's responsibility to free the
- * extra reference for shared policies.
- */
-struct mempolicy *get_vma_policy(struct task_struct *task,
-		struct vm_area_struct *vma, unsigned long addr)
+struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
+						unsigned long addr)
 {
-	struct mempolicy *pol = get_task_policy(task);
+	struct mempolicy *pol = NULL;
 
 	if (vma) {
 		if (vma->vm_ops && vma->vm_ops->get_policy) {
-			struct mempolicy *vpol = vma->vm_ops->get_policy(vma,
-									addr);
-			if (vpol)
-				pol = vpol;
+			pol = vma->vm_ops->get_policy(vma, addr);
 		} else if (vma->vm_policy) {
 			pol = vma->vm_policy;
 
@@ -1644,31 +1613,51 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
 				mpol_get(pol);
 		}
 	}
+
+	return pol;
+}
+
+/*
+ * get_vma_policy(@vma, @addr)
+ * @vma: virtual memory area whose policy is sought
+ * @addr: address in @vma for shared policy lookup
+ *
+ * Returns effective policy for a VMA at specified address.
+ * Falls back to current->mempolicy or system default policy, as necessary.
+ * Shared policies [those marked as MPOL_F_SHARED] require an extra reference
+ * count--added by the get_policy() vm_op, as appropriate--to protect against
+ * freeing by another task.  It is the caller's responsibility to free the
+ * extra reference for shared policies.
+ */
+static struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+						unsigned long addr)
+{
+	struct mempolicy *pol = __get_vma_policy(vma, addr);
+
 	if (!pol)
-		pol = &default_policy;
+		pol = get_task_policy(current);
+
 	return pol;
 }
 
-bool vma_policy_mof(struct task_struct *task, struct vm_area_struct *vma)
+bool vma_policy_mof(struct vm_area_struct *vma)
 {
-	struct mempolicy *pol = get_task_policy(task);
-	if (vma) {
-		if (vma->vm_ops && vma->vm_ops->get_policy) {
-			bool ret = false;
+	struct mempolicy *pol;
 
-			pol = vma->vm_ops->get_policy(vma, vma->vm_start);
-			if (pol && (pol->flags & MPOL_F_MOF))
-				ret = true;
-			mpol_cond_put(pol);
+	if (vma->vm_ops && vma->vm_ops->get_policy) {
+		bool ret = false;
 
-			return ret;
-		} else if (vma->vm_policy) {
-			pol = vma->vm_policy;
-		}
+		pol = vma->vm_ops->get_policy(vma, vma->vm_start);
+		if (pol && (pol->flags & MPOL_F_MOF))
+			ret = true;
+		mpol_cond_put(pol);
+
+		return ret;
 	}
 
+	pol = vma->vm_policy;
 	if (!pol)
-		return default_policy.flags & MPOL_F_MOF;
+		pol = get_task_policy(current);
 
 	return pol->flags & MPOL_F_MOF;
 }
@@ -1874,7 +1863,7 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
 {
 	struct zonelist *zl;
 
-	*mpol = get_vma_policy(current, vma, addr);
+	*mpol = get_vma_policy(vma, addr);
 	*nodemask = NULL;	/* assume !MPOL_BIND */
 
 	if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
@@ -2029,7 +2018,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 	unsigned int cpuset_mems_cookie;
 
 retry_cpuset:
-	pol = get_vma_policy(current, vma, addr);
+	pol = get_vma_policy(vma, addr);
 	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
@@ -2046,8 +2035,7 @@ retry_cpuset:
 	page = __alloc_pages_nodemask(gfp, order,
 				      policy_zonelist(gfp, pol, node),
 				      policy_nodemask(gfp, pol));
-	if (unlikely(mpol_needs_cond_ref(pol)))
-		__mpol_put(pol);
+	mpol_cond_put(pol);
 	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return page;
@@ -2074,12 +2062,12 @@ retry_cpuset:
  */
 struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
-	struct mempolicy *pol = get_task_policy(current);
+	struct mempolicy *pol = &default_policy;
 	struct page *page;
 	unsigned int cpuset_mems_cookie;
 
-	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
-		pol = &default_policy;
+	if (!in_interrupt() && !(gfp & __GFP_THISNODE))
+		pol = get_task_policy(current);
 
 retry_cpuset:
 	cpuset_mems_cookie = read_mems_allowed_begin();
@@ -2296,7 +2284,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 
 	BUG_ON(!vma);
 
-	pol = get_vma_policy(current, vma, addr);
+	pol = get_vma_policy(vma, addr);
 	if (!(pol->flags & MPOL_F_MOF))
 		goto out;
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 2740360cd216..01439953abf5 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -876,7 +876,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		}
 	}
 
-	if (unlikely(balloon_page_movable(page))) {
+	if (unlikely(isolated_balloon_page(page))) {
 		/*
 		 * A ballooned page does not need any special attention from
 		 * physical to virtual reverse mapping procedures.
@@ -955,17 +955,6 @@ static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page,
 
 	rc = __unmap_and_move(page, newpage, force, mode);
 
-	if (unlikely(rc == MIGRATEPAGE_BALLOON_SUCCESS)) {
-		/*
-		 * A ballooned page has been migrated already.
-		 * Now, it's the time to wrap-up counters,
-		 * handle the page back to Buddy and return.
-		 */
-		dec_zone_page_state(page, NR_ISOLATED_ANON +
-				    page_is_file_cache(page));
-		balloon_page_free(page);
-		return MIGRATEPAGE_SUCCESS;
-	}
 out:
 	if (rc != -EAGAIN) {
 		/*
@@ -988,6 +977,9 @@ out:
 	if (rc != MIGRATEPAGE_SUCCESS && put_new_page) {
 		ClearPageSwapBacked(newpage);
 		put_new_page(newpage, private);
+	} else if (unlikely(__is_movable_balloon_page(newpage))) {
+		/* drop our reference, page already in the balloon */
+		put_page(newpage);
 	} else
 		putback_lru_page(newpage);
 
diff --git a/mm/mlock.c b/mm/mlock.c
index ce84cb0b83ef..73cf0987088c 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -233,9 +233,9 @@ long __mlock_vma_pages_range(struct vm_area_struct *vma,
 
 	VM_BUG_ON(start & ~PAGE_MASK);
 	VM_BUG_ON(end   & ~PAGE_MASK);
-	VM_BUG_ON(start < vma->vm_start);
-	VM_BUG_ON(end   > vma->vm_end);
-	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
+	VM_BUG_ON_VMA(start < vma->vm_start, vma);
+	VM_BUG_ON_VMA(end   > vma->vm_end, vma);
+	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
 
 	gup_flags = FOLL_TOUCH | FOLL_MLOCK;
 	/*
@@ -789,7 +789,7 @@ static int do_mlockall(int flags)
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
-		cond_resched();
+		cond_resched_rcu_qs();
 	}
 out:
 	return 0;
diff --git a/mm/mmap.c b/mm/mmap.c
index c0a3637cdb64..7f855206e7fb 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -70,7 +70,7 @@ static void unmap_region(struct mm_struct *mm,
  * MAP_SHARED	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
  *		w: (no) no	w: (no) no	w: (yes) yes	w: (no) no
  *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
- *		
+ *
  * MAP_PRIVATE	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
  *		w: (no) no	w: (no) no	w: (copy) copy	w: (no) no
  *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
@@ -89,6 +89,25 @@ pgprot_t vm_get_page_prot(unsigned long vm_flags)
 }
 EXPORT_SYMBOL(vm_get_page_prot);
 
+static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
+{
+	return pgprot_modify(oldprot, vm_get_page_prot(vm_flags));
+}
+
+/* Update vma->vm_page_prot to reflect vma->vm_flags. */
+void vma_set_page_prot(struct vm_area_struct *vma)
+{
+	unsigned long vm_flags = vma->vm_flags;
+
+	vma->vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags);
+	if (vma_wants_writenotify(vma)) {
+		vm_flags &= ~VM_SHARED;
+		vma->vm_page_prot = vm_pgprot_modify(vma->vm_page_prot,
+						     vm_flags);
+	}
+}
+
+
 int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;  /* heuristic overcommit */
 int sysctl_overcommit_ratio __read_mostly = 50;	/* default is 50% */
 unsigned long sysctl_overcommit_kbytes __read_mostly;
@@ -268,7 +287,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len);
 
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
-	unsigned long rlim, retval;
+	unsigned long retval;
 	unsigned long newbrk, oldbrk;
 	struct mm_struct *mm = current->mm;
 	unsigned long min_brk;
@@ -298,9 +317,8 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	 * segment grow beyond its set limit the in case where the limit is
 	 * not page aligned -Ram Gupta
 	 */
-	rlim = rlimit(RLIMIT_DATA);
-	if (rlim < RLIM_INFINITY && (brk - mm->start_brk) +
-			(mm->end_data - mm->start_data) > rlim)
+	if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk,
+			      mm->end_data, mm->start_data))
 		goto out;
 
 	newbrk = PAGE_ALIGN(brk);
@@ -369,16 +387,18 @@ static int browse_rb(struct rb_root *root)
 		struct vm_area_struct *vma;
 		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
 		if (vma->vm_start < prev) {
-			pr_emerg("vm_start %lx prev %lx\n", vma->vm_start, prev);
+			pr_emerg("vm_start %lx < prev %lx\n",
+				  vma->vm_start, prev);
 			bug = 1;
 		}
 		if (vma->vm_start < pend) {
-			pr_emerg("vm_start %lx pend %lx\n", vma->vm_start, pend);
+			pr_emerg("vm_start %lx < pend %lx\n",
+				  vma->vm_start, pend);
 			bug = 1;
 		}
 		if (vma->vm_start > vma->vm_end) {
-			pr_emerg("vm_end %lx < vm_start %lx\n",
-				vma->vm_end, vma->vm_start);
+			pr_emerg("vm_start %lx > vm_end %lx\n",
+				  vma->vm_start, vma->vm_end);
 			bug = 1;
 		}
 		if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) {
@@ -409,8 +429,9 @@ static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore)
 	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
 		struct vm_area_struct *vma;
 		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
-		BUG_ON(vma != ignore &&
-		       vma->rb_subtree_gap != vma_compute_subtree_gap(vma));
+		VM_BUG_ON_VMA(vma != ignore &&
+			vma->rb_subtree_gap != vma_compute_subtree_gap(vma),
+			vma);
 	}
 }
 
@@ -420,8 +441,10 @@ static void validate_mm(struct mm_struct *mm)
 	int i = 0;
 	unsigned long highest_address = 0;
 	struct vm_area_struct *vma = mm->mmap;
+
 	while (vma) {
 		struct anon_vma_chain *avc;
+
 		vma_lock_anon_vma(vma);
 		list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
 			anon_vma_interval_tree_verify(avc);
@@ -436,15 +459,16 @@ static void validate_mm(struct mm_struct *mm)
 	}
 	if (highest_address != mm->highest_vm_end) {
 		pr_emerg("mm->highest_vm_end %lx, found %lx\n",
-		       mm->highest_vm_end, highest_address);
+			  mm->highest_vm_end, highest_address);
 		bug = 1;
 	}
 	i = browse_rb(&mm->mm_rb);
 	if (i != mm->map_count) {
-		pr_emerg("map_count %d rb %d\n", mm->map_count, i);
+		if (i != -1)
+			pr_emerg("map_count %d rb %d\n", mm->map_count, i);
 		bug = 1;
 	}
-	BUG_ON(bug);
+	VM_BUG_ON_MM(bug, mm);
 }
 #else
 #define validate_mm_rb(root, ignore) do { } while (0)
@@ -741,7 +765,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 			 * split_vma inserting another: so it must be
 			 * mprotect case 4 shifting the boundary down.
 			 */
-			adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT);
+			adjust_next = -((vma->vm_end - end) >> PAGE_SHIFT);
 			exporter = vma;
 			importer = next;
 		}
@@ -787,8 +811,8 @@ again:			remove_next = 1 + (end > next->vm_end);
 	if (!anon_vma && adjust_next)
 		anon_vma = next->anon_vma;
 	if (anon_vma) {
-		VM_BUG_ON(adjust_next && next->anon_vma &&
-			  anon_vma != next->anon_vma);
+		VM_BUG_ON_VMA(adjust_next && next->anon_vma &&
+			  anon_vma != next->anon_vma, next);
 		anon_vma_lock_write(anon_vma);
 		anon_vma_interval_tree_pre_update_vma(vma);
 		if (adjust_next)
@@ -1010,7 +1034,7 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
 struct vm_area_struct *vma_merge(struct mm_struct *mm,
 			struct vm_area_struct *prev, unsigned long addr,
 			unsigned long end, unsigned long vm_flags,
-		     	struct anon_vma *anon_vma, struct file *file,
+			struct anon_vma *anon_vma, struct file *file,
 			pgoff_t pgoff, struct mempolicy *policy)
 {
 	pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
@@ -1036,7 +1060,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 	 * Can it merge with the predecessor?
 	 */
 	if (prev && prev->vm_end == addr &&
-  			mpol_equal(vma_policy(prev), policy) &&
+			mpol_equal(vma_policy(prev), policy) &&
 			can_vma_merge_after(prev, vm_flags,
 						anon_vma, file, pgoff)) {
 		/*
@@ -1064,7 +1088,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 	 * Can this new request be merged in front of next?
 	 */
 	if (next && end == next->vm_start &&
- 			mpol_equal(policy, vma_policy(next)) &&
+			mpol_equal(policy, vma_policy(next)) &&
 			can_vma_merge_before(next, vm_flags,
 					anon_vma, file, pgoff+pglen)) {
 		if (prev && addr < prev->vm_end)	/* case 4 */
@@ -1235,7 +1259,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			unsigned long flags, unsigned long pgoff,
 			unsigned long *populate)
 {
-	struct mm_struct * mm = current->mm;
+	struct mm_struct *mm = current->mm;
 	vm_flags_t vm_flags;
 
 	*populate = 0;
@@ -1263,7 +1287,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 
 	/* offset overflow? */
 	if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
-               return -EOVERFLOW;
+		return -EOVERFLOW;
 
 	/* Too many mappings? */
 	if (mm->map_count > sysctl_max_map_count)
@@ -1470,11 +1494,16 @@ int vma_wants_writenotify(struct vm_area_struct *vma)
 	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
 		return 1;
 
-	/* The open routine did something to the protections already? */
+	/* The open routine did something to the protections that pgprot_modify
+	 * won't preserve? */
 	if (pgprot_val(vma->vm_page_prot) !=
-	    pgprot_val(vm_get_page_prot(vm_flags)))
+	    pgprot_val(vm_pgprot_modify(vma->vm_page_prot, vm_flags)))
 		return 0;
 
+	/* Do we need to track softdirty? */
+	if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY))
+		return 1;
+
 	/* Specialty mapping? */
 	if (vm_flags & VM_PFNMAP)
 		return 0;
@@ -1610,21 +1639,6 @@ munmap_back:
 			goto free_vma;
 	}
 
-	if (vma_wants_writenotify(vma)) {
-		pgprot_t pprot = vma->vm_page_prot;
-
-		/* Can vma->vm_page_prot have changed??
-		 *
-		 * Answer: Yes, drivers may have changed it in their
-		 *         f_op->mmap method.
-		 *
-		 * Ensures that vmas marked as uncached stay that way.
-		 */
-		vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
-		if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot)))
-			vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	}
-
 	vma_link(mm, vma, prev, rb_link, rb_parent);
 	/* Once vma denies write, undo our temporary denial count */
 	if (file) {
@@ -1658,6 +1672,8 @@ out:
 	 */
 	vma->vm_flags |= VM_SOFTDIRTY;
 
+	vma_set_page_prot(vma);
+
 	return addr;
 
 unmap_and_free_vma:
@@ -1921,7 +1937,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.align_mask = 0;
 	return vm_unmapped_area(&info);
 }
-#endif	
+#endif
 
 /*
  * This mmap-allocator allocates new areas top-down from below the
@@ -2321,13 +2337,13 @@ int expand_stack(struct vm_area_struct *vma, unsigned long address)
 }
 
 struct vm_area_struct *
-find_extend_vma(struct mm_struct * mm, unsigned long addr)
+find_extend_vma(struct mm_struct *mm, unsigned long addr)
 {
-	struct vm_area_struct * vma;
+	struct vm_area_struct *vma;
 	unsigned long start;
 
 	addr &= PAGE_MASK;
-	vma = find_vma(mm,addr);
+	vma = find_vma(mm, addr);
 	if (!vma)
 		return NULL;
 	if (vma->vm_start <= addr)
@@ -2376,7 +2392,7 @@ static void unmap_region(struct mm_struct *mm,
 		struct vm_area_struct *vma, struct vm_area_struct *prev,
 		unsigned long start, unsigned long end)
 {
-	struct vm_area_struct *next = prev? prev->vm_next: mm->mmap;
+	struct vm_area_struct *next = prev ? prev->vm_next : mm->mmap;
 	struct mmu_gather tlb;
 
 	lru_add_drain();
@@ -2423,7 +2439,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
  * __split_vma() bypasses sysctl_max_map_count checking.  We use this on the
  * munmap path where it doesn't make sense to fail.
  */
-static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
+static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	      unsigned long addr, int new_below)
 {
 	struct vm_area_struct *new;
@@ -2512,7 +2528,8 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	if ((start & ~PAGE_MASK) || start > TASK_SIZE || len > TASK_SIZE-start)
 		return -EINVAL;
 
-	if ((len = PAGE_ALIGN(len)) == 0)
+	len = PAGE_ALIGN(len);
+	if (len == 0)
 		return -EINVAL;
 
 	/* Find the first overlapping VMA */
@@ -2558,7 +2575,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 		if (error)
 			return error;
 	}
-	vma = prev? prev->vm_next: mm->mmap;
+	vma = prev ? prev->vm_next : mm->mmap;
 
 	/*
 	 * unlock any mlock()ed ranges before detaching vmas
@@ -2621,10 +2638,10 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  */
 static unsigned long do_brk(unsigned long addr, unsigned long len)
 {
-	struct mm_struct * mm = current->mm;
-	struct vm_area_struct * vma, * prev;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma, *prev;
 	unsigned long flags;
-	struct rb_node ** rb_link, * rb_parent;
+	struct rb_node **rb_link, *rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
 
@@ -2848,7 +2865,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 			 * safe. It is only safe to keep the vm_pgoff
 			 * linear if there are no pages mapped yet.
 			 */
-			VM_BUG_ON(faulted_in_anon_vma);
+			VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma);
 			*vmap = vma = new_vma;
 		}
 		*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
@@ -3196,7 +3213,7 @@ void __init mmap_init(void)
 {
 	int ret;
 
-	ret = percpu_counter_init(&vm_committed_as, 0);
+	ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL);
 	VM_BUG_ON(ret);
 }
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index c43d557941f8..ace93454ce8e 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -29,13 +29,6 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
-#ifndef pgprot_modify
-static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
-{
-	return newprot;
-}
-#endif
-
 /*
  * For a prot_numa update we only hold mmap_sem for read so there is a
  * potential race with faulting where a pmd was temporarily none. This
@@ -93,7 +86,9 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				 * Avoid taking write faults for pages we
 				 * know to be dirty.
 				 */
-				if (dirty_accountable && pte_dirty(ptent))
+				if (dirty_accountable && pte_dirty(ptent) &&
+				    (pte_soft_dirty(ptent) ||
+				     !(vma->vm_flags & VM_SOFTDIRTY)))
 					ptent = pte_mkwrite(ptent);
 				ptep_modify_prot_commit(mm, addr, pte, ptent);
 				updated = true;
@@ -320,13 +315,8 @@ success:
 	 * held in write mode.
 	 */
 	vma->vm_flags = newflags;
-	vma->vm_page_prot = pgprot_modify(vma->vm_page_prot,
-					  vm_get_page_prot(newflags));
-
-	if (vma_wants_writenotify(vma)) {
-		vma->vm_page_prot = vm_get_page_prot(newflags & ~VM_SHARED);
-		dirty_accountable = 1;
-	}
+	dirty_accountable = vma_wants_writenotify(vma);
+	vma_set_page_prot(vma);
 
 	change_protection(vma, start, end, vma->vm_page_prot,
 			  dirty_accountable, 0);
diff --git a/mm/mremap.c b/mm/mremap.c
index 05f1180e9f21..b147f66f4c40 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -21,8 +21,8 @@
 #include <linux/syscalls.h>
 #include <linux/mmu_notifier.h>
 #include <linux/sched/sysctl.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
@@ -195,7 +195,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 		if (pmd_trans_huge(*old_pmd)) {
 			int err = 0;
 			if (extent == HPAGE_PMD_SIZE) {
-				VM_BUG_ON(vma->vm_file || !vma->anon_vma);
+				VM_BUG_ON_VMA(vma->vm_file || !vma->anon_vma,
+					      vma);
 				/* See comment in move_ptes() */
 				if (need_rmap_locks)
 					anon_vma_lock_write(vma->anon_vma);
diff --git a/mm/nommu.c b/mm/nommu.c
index a881d9673c6b..bd1808e194a7 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -539,7 +539,7 @@ void __init mmap_init(void)
 {
 	int ret;
 
-	ret = percpu_counter_init(&vm_committed_as, 0);
+	ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL);
 	VM_BUG_ON(ret);
 	vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC);
 }
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 1e11df8fa7ec..bbf405a3a18f 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -565,7 +565,7 @@ bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_mask)
 
 	spin_lock(&zone_scan_lock);
 	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
-		if (zone_is_oom_locked(zone)) {
+		if (test_bit(ZONE_OOM_LOCKED, &zone->flags)) {
 			ret = false;
 			goto out;
 		}
@@ -575,7 +575,7 @@ bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_mask)
 	 * call to oom_zonelist_trylock() doesn't succeed when it shouldn't.
 	 */
 	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
-		zone_set_flag(zone, ZONE_OOM_LOCKED);
+		set_bit(ZONE_OOM_LOCKED, &zone->flags);
 
 out:
 	spin_unlock(&zone_scan_lock);
@@ -594,7 +594,7 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask)
 
 	spin_lock(&zone_scan_lock);
 	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask))
-		zone_clear_flag(zone, ZONE_OOM_LOCKED);
+		clear_bit(ZONE_OOM_LOCKED, &zone->flags);
 	spin_unlock(&zone_scan_lock);
 }
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 91d73ef1744d..ff24c9d83112 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1075,13 +1075,13 @@ static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi,
 	}
 
 	if (dirty < setpoint) {
-		x = min(bdi->balanced_dirty_ratelimit,
-			 min(balanced_dirty_ratelimit, task_ratelimit));
+		x = min3(bdi->balanced_dirty_ratelimit,
+			 balanced_dirty_ratelimit, task_ratelimit);
 		if (dirty_ratelimit < x)
 			step = x - dirty_ratelimit;
 	} else {
-		x = max(bdi->balanced_dirty_ratelimit,
-			 max(balanced_dirty_ratelimit, task_ratelimit));
+		x = max3(bdi->balanced_dirty_ratelimit,
+			 balanced_dirty_ratelimit, task_ratelimit);
 		if (dirty_ratelimit > x)
 			step = dirty_ratelimit - x;
 	}
@@ -1777,7 +1777,7 @@ void __init page_writeback_init(void)
 	writeback_set_ratelimit();
 	register_cpu_notifier(&ratelimit_nb);
 
-	fprop_global_init(&writeout_completions);
+	fprop_global_init(&writeout_completions, GFP_KERNEL);
 }
 
 /**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eee961958021..736d8e1b6381 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -53,8 +53,6 @@
 #include <linux/kmemleak.h>
 #include <linux/compaction.h>
 #include <trace/events/kmem.h>
-#include <linux/ftrace_event.h>
-#include <linux/memcontrol.h>
 #include <linux/prefetch.h>
 #include <linux/mm_inline.h>
 #include <linux/migrate.h>
@@ -85,6 +83,7 @@ EXPORT_PER_CPU_SYMBOL(numa_node);
  */
 DEFINE_PER_CPU(int, _numa_mem_);		/* Kernel "local memory" node */
 EXPORT_PER_CPU_SYMBOL(_numa_mem_);
+int _node_numa_mem_[MAX_NUMNODES];
 #endif
 
 /*
@@ -1014,7 +1013,7 @@ int move_freepages(struct zone *zone,
 	 * Remove at a later date when no bug reports exist related to
 	 * grouping pages by mobility
 	 */
-	BUG_ON(page_zone(start_page) != page_zone(end_page));
+	VM_BUG_ON(page_zone(start_page) != page_zone(end_page));
 #endif
 
 	for (page = start_page; page <= end_page;) {
@@ -1613,8 +1612,8 @@ again:
 
 	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
 	if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 &&
-	    !zone_is_fair_depleted(zone))
-		zone_set_flag(zone, ZONE_FAIR_DEPLETED);
+	    !test_bit(ZONE_FAIR_DEPLETED, &zone->flags))
+		set_bit(ZONE_FAIR_DEPLETED, &zone->flags);
 
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
@@ -1934,7 +1933,7 @@ static void reset_alloc_batches(struct zone *preferred_zone)
 		mod_zone_page_state(zone, NR_ALLOC_BATCH,
 			high_wmark_pages(zone) - low_wmark_pages(zone) -
 			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
-		zone_clear_flag(zone, ZONE_FAIR_DEPLETED);
+		clear_bit(ZONE_FAIR_DEPLETED, &zone->flags);
 	} while (zone++ != preferred_zone);
 }
 
@@ -1985,7 +1984,7 @@ zonelist_scan:
 		if (alloc_flags & ALLOC_FAIR) {
 			if (!zone_local(preferred_zone, zone))
 				break;
-			if (zone_is_fair_depleted(zone)) {
+			if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) {
 				nr_fair_skipped++;
 				continue;
 			}
@@ -2296,58 +2295,72 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
 	int classzone_idx, int migratetype, enum migrate_mode mode,
-	bool *contended_compaction, bool *deferred_compaction,
-	unsigned long *did_some_progress)
+	int *contended_compaction, bool *deferred_compaction)
 {
-	if (!order)
-		return NULL;
+	struct zone *last_compact_zone = NULL;
+	unsigned long compact_result;
+	struct page *page;
 
-	if (compaction_deferred(preferred_zone, order)) {
-		*deferred_compaction = true;
+	if (!order)
 		return NULL;
-	}
 
 	current->flags |= PF_MEMALLOC;
-	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
+	compact_result = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, mode,
-						contended_compaction);
+						contended_compaction,
+						&last_compact_zone);
 	current->flags &= ~PF_MEMALLOC;
 
-	if (*did_some_progress != COMPACT_SKIPPED) {
-		struct page *page;
+	switch (compact_result) {
+	case COMPACT_DEFERRED:
+		*deferred_compaction = true;
+		/* fall-through */
+	case COMPACT_SKIPPED:
+		return NULL;
+	default:
+		break;
+	}
 
-		/* Page migration frees to the PCP lists but we want merging */
-		drain_pages(get_cpu());
-		put_cpu();
+	/*
+	 * At least in one zone compaction wasn't deferred or skipped, so let's
+	 * count a compaction stall
+	 */
+	count_vm_event(COMPACTSTALL);
 
-		page = get_page_from_freelist(gfp_mask, nodemask,
-				order, zonelist, high_zoneidx,
-				alloc_flags & ~ALLOC_NO_WATERMARKS,
-				preferred_zone, classzone_idx, migratetype);
-		if (page) {
-			preferred_zone->compact_blockskip_flush = false;
-			compaction_defer_reset(preferred_zone, order, true);
-			count_vm_event(COMPACTSUCCESS);
-			return page;
-		}
+	/* Page migration frees to the PCP lists but we want merging */
+	drain_pages(get_cpu());
+	put_cpu();
 
-		/*
-		 * It's bad if compaction run occurs and fails.
-		 * The most likely reason is that pages exist,
-		 * but not enough to satisfy watermarks.
-		 */
-		count_vm_event(COMPACTFAIL);
+	page = get_page_from_freelist(gfp_mask, nodemask,
+			order, zonelist, high_zoneidx,
+			alloc_flags & ~ALLOC_NO_WATERMARKS,
+			preferred_zone, classzone_idx, migratetype);
 
-		/*
-		 * As async compaction considers a subset of pageblocks, only
-		 * defer if the failure was a sync compaction failure.
-		 */
-		if (mode != MIGRATE_ASYNC)
-			defer_compaction(preferred_zone, order);
+	if (page) {
+		struct zone *zone = page_zone(page);
 
-		cond_resched();
+		zone->compact_blockskip_flush = false;
+		compaction_defer_reset(zone, order, true);
+		count_vm_event(COMPACTSUCCESS);
+		return page;
 	}
 
+	/*
+	 * last_compact_zone is where try_to_compact_pages thought allocation
+	 * should succeed, so it did not defer compaction. But here we know
+	 * that it didn't succeed, so we do the defer.
+	 */
+	if (last_compact_zone && mode != MIGRATE_ASYNC)
+		defer_compaction(last_compact_zone, order);
+
+	/*
+	 * It's bad if compaction run occurs and fails. The most likely reason
+	 * is that pages exist, but not enough to satisfy watermarks.
+	 */
+	count_vm_event(COMPACTFAIL);
+
+	cond_resched();
+
 	return NULL;
 }
 #else
@@ -2355,9 +2368,8 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int classzone_idx, int migratetype,
-	enum migrate_mode mode, bool *contended_compaction,
-	bool *deferred_compaction, unsigned long *did_some_progress)
+	int classzone_idx, int migratetype, enum migrate_mode mode,
+	int *contended_compaction, bool *deferred_compaction)
 {
 	return NULL;
 }
@@ -2457,12 +2469,14 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
 static void wake_all_kswapds(unsigned int order,
 			     struct zonelist *zonelist,
 			     enum zone_type high_zoneidx,
-			     struct zone *preferred_zone)
+			     struct zone *preferred_zone,
+			     nodemask_t *nodemask)
 {
 	struct zoneref *z;
 	struct zone *zone;
 
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+						high_zoneidx, nodemask)
 		wakeup_kswapd(zone, order, zone_idx(preferred_zone));
 }
 
@@ -2509,7 +2523,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 			alloc_flags |= ALLOC_NO_WATERMARKS;
 	}
 #ifdef CONFIG_CMA
-	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 #endif
 	return alloc_flags;
@@ -2533,7 +2547,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned long did_some_progress;
 	enum migrate_mode migration_mode = MIGRATE_ASYNC;
 	bool deferred_compaction = false;
-	bool contended_compaction = false;
+	int contended_compaction = COMPACT_CONTENDED_NONE;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -2560,7 +2574,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 
 restart:
 	if (!(gfp_mask & __GFP_NO_KSWAPD))
-		wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone);
+		wake_all_kswapds(order, zonelist, high_zoneidx,
+				preferred_zone, nodemask);
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
@@ -2633,20 +2648,40 @@ rebalance:
 					preferred_zone,
 					classzone_idx, migratetype,
 					migration_mode, &contended_compaction,
-					&deferred_compaction,
-					&did_some_progress);
+					&deferred_compaction);
 	if (page)
 		goto got_pg;
 
-	/*
-	 * If compaction is deferred for high-order allocations, it is because
-	 * sync compaction recently failed. In this is the case and the caller
-	 * requested a movable allocation that does not heavily disrupt the
-	 * system then fail the allocation instead of entering direct reclaim.
-	 */
-	if ((deferred_compaction || contended_compaction) &&
-						(gfp_mask & __GFP_NO_KSWAPD))
-		goto nopage;
+	/* Checks for THP-specific high-order allocations */
+	if ((gfp_mask & GFP_TRANSHUGE) == GFP_TRANSHUGE) {
+		/*
+		 * If compaction is deferred for high-order allocations, it is
+		 * because sync compaction recently failed. If this is the case
+		 * and the caller requested a THP allocation, we do not want
+		 * to heavily disrupt the system, so we fail the allocation
+		 * instead of entering direct reclaim.
+		 */
+		if (deferred_compaction)
+			goto nopage;
+
+		/*
+		 * In all zones where compaction was attempted (and not
+		 * deferred or skipped), lock contention has been detected.
+		 * For THP allocation we do not want to disrupt the others
+		 * so we fallback to base pages instead.
+		 */
+		if (contended_compaction == COMPACT_CONTENDED_LOCK)
+			goto nopage;
+
+		/*
+		 * If compaction was aborted due to need_resched(), we do not
+		 * want to further increase allocation latency, unless it is
+		 * khugepaged trying to collapse.
+		 */
+		if (contended_compaction == COMPACT_CONTENDED_SCHED
+			&& !(current->flags & PF_KTHREAD))
+			goto nopage;
+	}
 
 	/*
 	 * It can become very expensive to allocate transparent hugepages at
@@ -2726,8 +2761,7 @@ rebalance:
 					preferred_zone,
 					classzone_idx, migratetype,
 					migration_mode, &contended_compaction,
-					&deferred_compaction,
-					&did_some_progress);
+					&deferred_compaction);
 		if (page)
 			goto got_pg;
 	}
@@ -2753,7 +2787,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	struct zone *preferred_zone;
 	struct zoneref *preferred_zoneref;
 	struct page *page = NULL;
-	int migratetype = allocflags_to_migratetype(gfp_mask);
+	int migratetype = gfpflags_to_migratetype(gfp_mask);
 	unsigned int cpuset_mems_cookie;
 	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
 	int classzone_idx;
@@ -2775,6 +2809,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!zonelist->_zonerefs->zone))
 		return NULL;
 
+	if (IS_ENABLED(CONFIG_CMA) && migratetype == MIGRATE_MOVABLE)
+		alloc_flags |= ALLOC_CMA;
+
 retry_cpuset:
 	cpuset_mems_cookie = read_mems_allowed_begin();
 
@@ -2786,10 +2823,6 @@ retry_cpuset:
 		goto out;
 	classzone_idx = zonelist_zone_idx(preferred_zoneref);
 
-#ifdef CONFIG_CMA
-	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
-		alloc_flags |= ALLOC_CMA;
-#endif
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
 			zonelist, high_zoneidx, alloc_flags,
@@ -3579,68 +3612,30 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
 	zonelist->_zonerefs[pos].zone_idx = 0;
 }
 
+#if defined(CONFIG_64BIT)
+/*
+ * Devices that require DMA32/DMA are relatively rare and do not justify a
+ * penalty to every machine in case the specialised case applies. Default
+ * to Node-ordering on 64-bit NUMA machines
+ */
+static int default_zonelist_order(void)
+{
+	return ZONELIST_ORDER_NODE;
+}
+#else
+/*
+ * On 32-bit, the Normal zone needs to be preserved for allocations accessible
+ * by the kernel. If processes running on node 0 deplete the low memory zone
+ * then reclaim will occur more frequency increasing stalls and potentially
+ * be easier to OOM if a large percentage of the zone is under writeback or
+ * dirty. The problem is significantly worse if CONFIG_HIGHPTE is not set.
+ * Hence, default to zone ordering on 32-bit.
+ */
 static int default_zonelist_order(void)
 {
-	int nid, zone_type;
-	unsigned long low_kmem_size, total_size;
-	struct zone *z;
-	int average_size;
-	/*
-	 * ZONE_DMA and ZONE_DMA32 can be very small area in the system.
-	 * If they are really small and used heavily, the system can fall
-	 * into OOM very easily.
-	 * This function detect ZONE_DMA/DMA32 size and configures zone order.
-	 */
-	/* Is there ZONE_NORMAL ? (ex. ppc has only DMA zone..) */
-	low_kmem_size = 0;
-	total_size = 0;
-	for_each_online_node(nid) {
-		for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
-			z = &NODE_DATA(nid)->node_zones[zone_type];
-			if (populated_zone(z)) {
-				if (zone_type < ZONE_NORMAL)
-					low_kmem_size += z->managed_pages;
-				total_size += z->managed_pages;
-			} else if (zone_type == ZONE_NORMAL) {
-				/*
-				 * If any node has only lowmem, then node order
-				 * is preferred to allow kernel allocations
-				 * locally; otherwise, they can easily infringe
-				 * on other nodes when there is an abundance of
-				 * lowmem available to allocate from.
-				 */
-				return ZONELIST_ORDER_NODE;
-			}
-		}
-	}
-	if (!low_kmem_size ||  /* there are no DMA area. */
-	    low_kmem_size > total_size/2) /* DMA/DMA32 is big. */
-		return ZONELIST_ORDER_NODE;
-	/*
-	 * look into each node's config.
-	 * If there is a node whose DMA/DMA32 memory is very big area on
-	 * local memory, NODE_ORDER may be suitable.
-	 */
-	average_size = total_size /
-				(nodes_weight(node_states[N_MEMORY]) + 1);
-	for_each_online_node(nid) {
-		low_kmem_size = 0;
-		total_size = 0;
-		for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
-			z = &NODE_DATA(nid)->node_zones[zone_type];
-			if (populated_zone(z)) {
-				if (zone_type < ZONE_NORMAL)
-					low_kmem_size += z->present_pages;
-				total_size += z->present_pages;
-			}
-		}
-		if (low_kmem_size &&
-		    total_size > average_size && /* ignore small node */
-		    low_kmem_size > total_size * 70/100)
-			return ZONELIST_ORDER_NODE;
-	}
 	return ZONELIST_ORDER_ZONE;
 }
+#endif /* CONFIG_64BIT */
 
 static void set_zonelist_order(void)
 {
@@ -4976,6 +4971,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	pgdat->node_start_pfn = node_start_pfn;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+	printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid,
+			(u64) start_pfn << PAGE_SHIFT, (u64) (end_pfn << PAGE_SHIFT) - 1);
 #endif
 	calculate_node_totalpages(pgdat, start_pfn, end_pfn,
 				  zones_size, zholes_size);
@@ -6277,8 +6274,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 
 		if (list_empty(&cc->migratepages)) {
 			cc->nr_migratepages = 0;
-			pfn = isolate_migratepages_range(cc->zone, cc,
-							 pfn, end, true);
+			pfn = isolate_migratepages_range(cc, pfn, end);
 			if (!pfn) {
 				ret = -EINTR;
 				break;
@@ -6554,97 +6550,3 @@ bool is_free_buddy_page(struct page *page)
 	return order < MAX_ORDER;
 }
 #endif
-
-static const struct trace_print_flags pageflag_names[] = {
-	{1UL << PG_locked,		"locked"	},
-	{1UL << PG_error,		"error"		},
-	{1UL << PG_referenced,		"referenced"	},
-	{1UL << PG_uptodate,		"uptodate"	},
-	{1UL << PG_dirty,		"dirty"		},
-	{1UL << PG_lru,			"lru"		},
-	{1UL << PG_active,		"active"	},
-	{1UL << PG_slab,		"slab"		},
-	{1UL << PG_owner_priv_1,	"owner_priv_1"	},
-	{1UL << PG_arch_1,		"arch_1"	},
-	{1UL << PG_reserved,		"reserved"	},
-	{1UL << PG_private,		"private"	},
-	{1UL << PG_private_2,		"private_2"	},
-	{1UL << PG_writeback,		"writeback"	},
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
-	{1UL << PG_head,		"head"		},
-	{1UL << PG_tail,		"tail"		},
-#else
-	{1UL << PG_compound,		"compound"	},
-#endif
-	{1UL << PG_swapcache,		"swapcache"	},
-	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
-	{1UL << PG_reclaim,		"reclaim"	},
-	{1UL << PG_swapbacked,		"swapbacked"	},
-	{1UL << PG_unevictable,		"unevictable"	},
-#ifdef CONFIG_MMU
-	{1UL << PG_mlocked,		"mlocked"	},
-#endif
-#ifdef CONFIG_ARCH_USES_PG_UNCACHED
-	{1UL << PG_uncached,		"uncached"	},
-#endif
-#ifdef CONFIG_MEMORY_FAILURE
-	{1UL << PG_hwpoison,		"hwpoison"	},
-#endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	{1UL << PG_compound_lock,	"compound_lock"	},
-#endif
-};
-
-static void dump_page_flags(unsigned long flags)
-{
-	const char *delim = "";
-	unsigned long mask;
-	int i;
-
-	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
-
-	printk(KERN_ALERT "page flags: %#lx(", flags);
-
-	/* remove zone id */
-	flags &= (1UL << NR_PAGEFLAGS) - 1;
-
-	for (i = 0; i < ARRAY_SIZE(pageflag_names) && flags; i++) {
-
-		mask = pageflag_names[i].mask;
-		if ((flags & mask) != mask)
-			continue;
-
-		flags &= ~mask;
-		printk("%s%s", delim, pageflag_names[i].name);
-		delim = "|";
-	}
-
-	/* check for left over flags */
-	if (flags)
-		printk("%s%#lx", delim, flags);
-
-	printk(")\n");
-}
-
-void dump_page_badflags(struct page *page, const char *reason,
-		unsigned long badflags)
-{
-	printk(KERN_ALERT
-	       "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
-		page, atomic_read(&page->_count), page_mapcount(page),
-		page->mapping, page->index);
-	dump_page_flags(page->flags);
-	if (reason)
-		pr_alert("page dumped because: %s\n", reason);
-	if (page->flags & badflags) {
-		pr_alert("bad because of flags:\n");
-		dump_page_flags(page->flags & badflags);
-	}
-	mem_cgroup_print_bad_page(page);
-}
-
-void dump_page(struct page *page, const char *reason)
-{
-	dump_page_badflags(page, reason, 0);
-}
-EXPORT_SYMBOL(dump_page);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 2beeabf502c5..ad83195521f2 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -177,7 +177,7 @@ int walk_page_range(unsigned long addr, unsigned long end,
 	if (!walk->mm)
 		return -EINVAL;
 
-	VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem));
+	VM_BUG_ON_MM(!rwsem_is_locked(&walk->mm->mmap_sem), walk->mm);
 
 	pgd = pgd_offset(walk->mm, addr);
 	do {
diff --git a/mm/percpu-km.c b/mm/percpu-km.c
index 89633fefc6a2..10e3d0b8a86d 100644
--- a/mm/percpu-km.c
+++ b/mm/percpu-km.c
@@ -33,17 +33,14 @@
 
 #include <linux/log2.h>
 
-static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
+			       int page_start, int page_end)
 {
-	unsigned int cpu;
-
-	for_each_possible_cpu(cpu)
-		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
-
 	return 0;
 }
 
-static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size)
+static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
+				  int page_start, int page_end)
 {
 	/* nada */
 }
@@ -70,6 +67,11 @@ static struct pcpu_chunk *pcpu_create_chunk(void)
 
 	chunk->data = pages;
 	chunk->base_addr = page_address(pages) - pcpu_group_offsets[0];
+
+	spin_lock_irq(&pcpu_lock);
+	pcpu_chunk_populated(chunk, 0, nr_pages);
+	spin_unlock_irq(&pcpu_lock);
+
 	return chunk;
 }
 
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 51108165f829..538998a137d2 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -20,46 +20,25 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
 }
 
 /**
- * pcpu_get_pages_and_bitmap - get temp pages array and bitmap
+ * pcpu_get_pages - get temp pages array
  * @chunk: chunk of interest
- * @bitmapp: output parameter for bitmap
- * @may_alloc: may allocate the array
  *
- * Returns pointer to array of pointers to struct page and bitmap,
- * both of which can be indexed with pcpu_page_idx().  The returned
- * array is cleared to zero and *@bitmapp is copied from
- * @chunk->populated.  Note that there is only one array and bitmap
- * and access exclusion is the caller's responsibility.
- *
- * CONTEXT:
- * pcpu_alloc_mutex and does GFP_KERNEL allocation if @may_alloc.
- * Otherwise, don't care.
+ * Returns pointer to array of pointers to struct page which can be indexed
+ * with pcpu_page_idx().  Note that there is only one array and accesses
+ * should be serialized by pcpu_alloc_mutex.
  *
  * RETURNS:
- * Pointer to temp pages array on success, NULL on failure.
+ * Pointer to temp pages array on success.
  */
-static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
-					       unsigned long **bitmapp,
-					       bool may_alloc)
+static struct page **pcpu_get_pages(struct pcpu_chunk *chunk_alloc)
 {
 	static struct page **pages;
-	static unsigned long *bitmap;
 	size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);
-	size_t bitmap_size = BITS_TO_LONGS(pcpu_unit_pages) *
-			     sizeof(unsigned long);
-
-	if (!pages || !bitmap) {
-		if (may_alloc && !pages)
-			pages = pcpu_mem_zalloc(pages_size);
-		if (may_alloc && !bitmap)
-			bitmap = pcpu_mem_zalloc(bitmap_size);
-		if (!pages || !bitmap)
-			return NULL;
-	}
 
-	bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages);
+	lockdep_assert_held(&pcpu_alloc_mutex);
 
-	*bitmapp = bitmap;
+	if (!pages)
+		pages = pcpu_mem_zalloc(pages_size);
 	return pages;
 }
 
@@ -67,7 +46,6 @@ static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
  * pcpu_free_pages - free pages which were allocated for @chunk
  * @chunk: chunk pages were allocated for
  * @pages: array of pages to be freed, indexed by pcpu_page_idx()
- * @populated: populated bitmap
  * @page_start: page index of the first page to be freed
  * @page_end: page index of the last page to be freed + 1
  *
@@ -75,8 +53,7 @@ static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
  * The pages were allocated for @chunk.
  */
 static void pcpu_free_pages(struct pcpu_chunk *chunk,
-			    struct page **pages, unsigned long *populated,
-			    int page_start, int page_end)
+			    struct page **pages, int page_start, int page_end)
 {
 	unsigned int cpu;
 	int i;
@@ -95,7 +72,6 @@ static void pcpu_free_pages(struct pcpu_chunk *chunk,
  * pcpu_alloc_pages - allocates pages for @chunk
  * @chunk: target chunk
  * @pages: array to put the allocated pages into, indexed by pcpu_page_idx()
- * @populated: populated bitmap
  * @page_start: page index of the first page to be allocated
  * @page_end: page index of the last page to be allocated + 1
  *
@@ -104,8 +80,7 @@ static void pcpu_free_pages(struct pcpu_chunk *chunk,
  * content of @pages and will pass it verbatim to pcpu_map_pages().
  */
 static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
-			    struct page **pages, unsigned long *populated,
-			    int page_start, int page_end)
+			    struct page **pages, int page_start, int page_end)
 {
 	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
 	unsigned int cpu, tcpu;
@@ -164,7 +139,6 @@ static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
  * pcpu_unmap_pages - unmap pages out of a pcpu_chunk
  * @chunk: chunk of interest
  * @pages: pages array which can be used to pass information to free
- * @populated: populated bitmap
  * @page_start: page index of the first page to unmap
  * @page_end: page index of the last page to unmap + 1
  *
@@ -175,8 +149,7 @@ static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
  * proper pre/post flush functions.
  */
 static void pcpu_unmap_pages(struct pcpu_chunk *chunk,
-			     struct page **pages, unsigned long *populated,
-			     int page_start, int page_end)
+			     struct page **pages, int page_start, int page_end)
 {
 	unsigned int cpu;
 	int i;
@@ -192,8 +165,6 @@ static void pcpu_unmap_pages(struct pcpu_chunk *chunk,
 		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start),
 				   page_end - page_start);
 	}
-
-	bitmap_clear(populated, page_start, page_end - page_start);
 }
 
 /**
@@ -228,7 +199,6 @@ static int __pcpu_map_pages(unsigned long addr, struct page **pages,
  * pcpu_map_pages - map pages into a pcpu_chunk
  * @chunk: chunk of interest
  * @pages: pages array containing pages to be mapped
- * @populated: populated bitmap
  * @page_start: page index of the first page to map
  * @page_end: page index of the last page to map + 1
  *
@@ -236,13 +206,11 @@ static int __pcpu_map_pages(unsigned long addr, struct page **pages,
  * caller is responsible for calling pcpu_post_map_flush() after all
  * mappings are complete.
  *
- * This function is responsible for setting corresponding bits in
- * @chunk->populated bitmap and whatever is necessary for reverse
- * lookup (addr -> chunk).
+ * This function is responsible for setting up whatever is necessary for
+ * reverse lookup (addr -> chunk).
  */
 static int pcpu_map_pages(struct pcpu_chunk *chunk,
-			  struct page **pages, unsigned long *populated,
-			  int page_start, int page_end)
+			  struct page **pages, int page_start, int page_end)
 {
 	unsigned int cpu, tcpu;
 	int i, err;
@@ -253,18 +221,12 @@ static int pcpu_map_pages(struct pcpu_chunk *chunk,
 				       page_end - page_start);
 		if (err < 0)
 			goto err;
-	}
 
-	/* mapping successful, link chunk and mark populated */
-	for (i = page_start; i < page_end; i++) {
-		for_each_possible_cpu(cpu)
+		for (i = page_start; i < page_end; i++)
 			pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)],
 					    chunk);
-		__set_bit(i, populated);
 	}
-
 	return 0;
-
 err:
 	for_each_possible_cpu(tcpu) {
 		if (tcpu == cpu)
@@ -299,123 +261,69 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
 /**
  * pcpu_populate_chunk - populate and map an area of a pcpu_chunk
  * @chunk: chunk of interest
- * @off: offset to the area to populate
- * @size: size of the area to populate in bytes
+ * @page_start: the start page
+ * @page_end: the end page
  *
  * For each cpu, populate and map pages [@page_start,@page_end) into
- * @chunk.  The area is cleared on return.
+ * @chunk.
  *
  * CONTEXT:
  * pcpu_alloc_mutex, does GFP_KERNEL allocation.
  */
-static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
+			       int page_start, int page_end)
 {
-	int page_start = PFN_DOWN(off);
-	int page_end = PFN_UP(off + size);
-	int free_end = page_start, unmap_end = page_start;
 	struct page **pages;
-	unsigned long *populated;
-	unsigned int cpu;
-	int rs, re, rc;
-
-	/* quick path, check whether all pages are already there */
-	rs = page_start;
-	pcpu_next_pop(chunk, &rs, &re, page_end);
-	if (rs == page_start && re == page_end)
-		goto clear;
 
-	/* need to allocate and map pages, this chunk can't be immutable */
-	WARN_ON(chunk->immutable);
-
-	pages = pcpu_get_pages_and_bitmap(chunk, &populated, true);
+	pages = pcpu_get_pages(chunk);
 	if (!pages)
 		return -ENOMEM;
 
-	/* alloc and map */
-	pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
-		rc = pcpu_alloc_pages(chunk, pages, populated, rs, re);
-		if (rc)
-			goto err_free;
-		free_end = re;
-	}
+	if (pcpu_alloc_pages(chunk, pages, page_start, page_end))
+		return -ENOMEM;
 
-	pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
-		rc = pcpu_map_pages(chunk, pages, populated, rs, re);
-		if (rc)
-			goto err_unmap;
-		unmap_end = re;
+	if (pcpu_map_pages(chunk, pages, page_start, page_end)) {
+		pcpu_free_pages(chunk, pages, page_start, page_end);
+		return -ENOMEM;
 	}
 	pcpu_post_map_flush(chunk, page_start, page_end);
 
-	/* commit new bitmap */
-	bitmap_copy(chunk->populated, populated, pcpu_unit_pages);
-clear:
-	for_each_possible_cpu(cpu)
-		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
 	return 0;
-
-err_unmap:
-	pcpu_pre_unmap_flush(chunk, page_start, unmap_end);
-	pcpu_for_each_unpop_region(chunk, rs, re, page_start, unmap_end)
-		pcpu_unmap_pages(chunk, pages, populated, rs, re);
-	pcpu_post_unmap_tlb_flush(chunk, page_start, unmap_end);
-err_free:
-	pcpu_for_each_unpop_region(chunk, rs, re, page_start, free_end)
-		pcpu_free_pages(chunk, pages, populated, rs, re);
-	return rc;
 }
 
 /**
  * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk
  * @chunk: chunk to depopulate
- * @off: offset to the area to depopulate
- * @size: size of the area to depopulate in bytes
+ * @page_start: the start page
+ * @page_end: the end page
  *
  * For each cpu, depopulate and unmap pages [@page_start,@page_end)
- * from @chunk.  If @flush is true, vcache is flushed before unmapping
- * and tlb after.
+ * from @chunk.
  *
  * CONTEXT:
  * pcpu_alloc_mutex.
  */
-static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size)
+static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
+				  int page_start, int page_end)
 {
-	int page_start = PFN_DOWN(off);
-	int page_end = PFN_UP(off + size);
 	struct page **pages;
-	unsigned long *populated;
-	int rs, re;
-
-	/* quick path, check whether it's empty already */
-	rs = page_start;
-	pcpu_next_unpop(chunk, &rs, &re, page_end);
-	if (rs == page_start && re == page_end)
-		return;
-
-	/* immutable chunks can't be depopulated */
-	WARN_ON(chunk->immutable);
 
 	/*
 	 * If control reaches here, there must have been at least one
 	 * successful population attempt so the temp pages array must
 	 * be available now.
 	 */
-	pages = pcpu_get_pages_and_bitmap(chunk, &populated, false);
+	pages = pcpu_get_pages(chunk);
 	BUG_ON(!pages);
 
 	/* unmap and free */
 	pcpu_pre_unmap_flush(chunk, page_start, page_end);
 
-	pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
-		pcpu_unmap_pages(chunk, pages, populated, rs, re);
+	pcpu_unmap_pages(chunk, pages, page_start, page_end);
 
 	/* no need to flush tlb, vmalloc will handle it lazily */
 
-	pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
-		pcpu_free_pages(chunk, pages, populated, rs, re);
-
-	/* commit new bitmap */
-	bitmap_copy(chunk->populated, populated, pcpu_unit_pages);
+	pcpu_free_pages(chunk, pages, page_start, page_end);
 }
 
 static struct pcpu_chunk *pcpu_create_chunk(void)
diff --git a/mm/percpu.c b/mm/percpu.c
index da997f9800bd..014bab65e0ff 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -76,6 +76,10 @@
 
 #define PCPU_SLOT_BASE_SHIFT		5	/* 1-31 shares the same slot */
 #define PCPU_DFL_MAP_ALLOC		16	/* start a map with 16 ents */
+#define PCPU_ATOMIC_MAP_MARGIN_LOW	32
+#define PCPU_ATOMIC_MAP_MARGIN_HIGH	64
+#define PCPU_EMPTY_POP_PAGES_LOW	2
+#define PCPU_EMPTY_POP_PAGES_HIGH	4
 
 #ifdef CONFIG_SMP
 /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
@@ -102,12 +106,16 @@ struct pcpu_chunk {
 	int			free_size;	/* free bytes in the chunk */
 	int			contig_hint;	/* max contiguous size hint */
 	void			*base_addr;	/* base address of this chunk */
+
 	int			map_used;	/* # of map entries used before the sentry */
 	int			map_alloc;	/* # of map entries allocated */
 	int			*map;		/* allocation map */
+	struct work_struct	map_extend_work;/* async ->map[] extension */
+
 	void			*data;		/* chunk data */
 	int			first_free;	/* no free below this */
 	bool			immutable;	/* no [de]population allowed */
+	int			nr_populated;	/* # of populated pages */
 	unsigned long		populated[];	/* populated bitmap */
 };
 
@@ -151,38 +159,33 @@ static struct pcpu_chunk *pcpu_first_chunk;
 static struct pcpu_chunk *pcpu_reserved_chunk;
 static int pcpu_reserved_chunk_limit;
 
+static DEFINE_SPINLOCK(pcpu_lock);	/* all internal data structures */
+static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop */
+
+static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
+
 /*
- * Synchronization rules.
- *
- * There are two locks - pcpu_alloc_mutex and pcpu_lock.  The former
- * protects allocation/reclaim paths, chunks, populated bitmap and
- * vmalloc mapping.  The latter is a spinlock and protects the index
- * data structures - chunk slots, chunks and area maps in chunks.
- *
- * During allocation, pcpu_alloc_mutex is kept locked all the time and
- * pcpu_lock is grabbed and released as necessary.  All actual memory
- * allocations are done using GFP_KERNEL with pcpu_lock released.  In
- * general, percpu memory can't be allocated with irq off but
- * irqsave/restore are still used in alloc path so that it can be used
- * from early init path - sched_init() specifically.
- *
- * Free path accesses and alters only the index data structures, so it
- * can be safely called from atomic context.  When memory needs to be
- * returned to the system, free path schedules reclaim_work which
- * grabs both pcpu_alloc_mutex and pcpu_lock, unlinks chunks to be
- * reclaimed, release both locks and frees the chunks.  Note that it's
- * necessary to grab both locks to remove a chunk from circulation as
- * allocation path might be referencing the chunk with only
- * pcpu_alloc_mutex locked.
+ * The number of empty populated pages, protected by pcpu_lock.  The
+ * reserved chunk doesn't contribute to the count.
  */
-static DEFINE_MUTEX(pcpu_alloc_mutex);	/* protects whole alloc and reclaim */
-static DEFINE_SPINLOCK(pcpu_lock);	/* protects index data structures */
+static int pcpu_nr_empty_pop_pages;
 
-static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
+/*
+ * Balance work is used to populate or destroy chunks asynchronously.  We
+ * try to keep the number of populated free pages between
+ * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one
+ * empty chunk.
+ */
+static void pcpu_balance_workfn(struct work_struct *work);
+static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn);
+static bool pcpu_async_enabled __read_mostly;
+static bool pcpu_atomic_alloc_failed;
 
-/* reclaim work to release fully free chunks, scheduled from free path */
-static void pcpu_reclaim(struct work_struct *work);
-static DECLARE_WORK(pcpu_reclaim_work, pcpu_reclaim);
+static void pcpu_schedule_balance_work(void)
+{
+	if (pcpu_async_enabled)
+		schedule_work(&pcpu_balance_work);
+}
 
 static bool pcpu_addr_in_first_chunk(void *addr)
 {
@@ -315,6 +318,38 @@ static void pcpu_mem_free(void *ptr, size_t size)
 }
 
 /**
+ * pcpu_count_occupied_pages - count the number of pages an area occupies
+ * @chunk: chunk of interest
+ * @i: index of the area in question
+ *
+ * Count the number of pages chunk's @i'th area occupies.  When the area's
+ * start and/or end address isn't aligned to page boundary, the straddled
+ * page is included in the count iff the rest of the page is free.
+ */
+static int pcpu_count_occupied_pages(struct pcpu_chunk *chunk, int i)
+{
+	int off = chunk->map[i] & ~1;
+	int end = chunk->map[i + 1] & ~1;
+
+	if (!PAGE_ALIGNED(off) && i > 0) {
+		int prev = chunk->map[i - 1];
+
+		if (!(prev & 1) && prev <= round_down(off, PAGE_SIZE))
+			off = round_down(off, PAGE_SIZE);
+	}
+
+	if (!PAGE_ALIGNED(end) && i + 1 < chunk->map_used) {
+		int next = chunk->map[i + 1];
+		int nend = chunk->map[i + 2] & ~1;
+
+		if (!(next & 1) && nend >= round_up(end, PAGE_SIZE))
+			end = round_up(end, PAGE_SIZE);
+	}
+
+	return max_t(int, PFN_DOWN(end) - PFN_UP(off), 0);
+}
+
+/**
  * pcpu_chunk_relocate - put chunk in the appropriate chunk slot
  * @chunk: chunk of interest
  * @oslot: the previous slot it was on
@@ -342,9 +377,14 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
 /**
  * pcpu_need_to_extend - determine whether chunk area map needs to be extended
  * @chunk: chunk of interest
+ * @is_atomic: the allocation context
  *
- * Determine whether area map of @chunk needs to be extended to
- * accommodate a new allocation.
+ * Determine whether area map of @chunk needs to be extended.  If
+ * @is_atomic, only the amount necessary for a new allocation is
+ * considered; however, async extension is scheduled if the left amount is
+ * low.  If !@is_atomic, it aims for more empty space.  Combined, this
+ * ensures that the map is likely to have enough available space to
+ * accomodate atomic allocations which can't extend maps directly.
  *
  * CONTEXT:
  * pcpu_lock.
@@ -353,15 +393,26 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
  * New target map allocation length if extension is necessary, 0
  * otherwise.
  */
-static int pcpu_need_to_extend(struct pcpu_chunk *chunk)
+static int pcpu_need_to_extend(struct pcpu_chunk *chunk, bool is_atomic)
 {
-	int new_alloc;
+	int margin, new_alloc;
+
+	if (is_atomic) {
+		margin = 3;
+
+		if (chunk->map_alloc <
+		    chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW &&
+		    pcpu_async_enabled)
+			schedule_work(&chunk->map_extend_work);
+	} else {
+		margin = PCPU_ATOMIC_MAP_MARGIN_HIGH;
+	}
 
-	if (chunk->map_alloc >= chunk->map_used + 3)
+	if (chunk->map_alloc >= chunk->map_used + margin)
 		return 0;
 
 	new_alloc = PCPU_DFL_MAP_ALLOC;
-	while (new_alloc < chunk->map_used + 3)
+	while (new_alloc < chunk->map_used + margin)
 		new_alloc *= 2;
 
 	return new_alloc;
@@ -418,11 +469,76 @@ out_unlock:
 	return 0;
 }
 
+static void pcpu_map_extend_workfn(struct work_struct *work)
+{
+	struct pcpu_chunk *chunk = container_of(work, struct pcpu_chunk,
+						map_extend_work);
+	int new_alloc;
+
+	spin_lock_irq(&pcpu_lock);
+	new_alloc = pcpu_need_to_extend(chunk, false);
+	spin_unlock_irq(&pcpu_lock);
+
+	if (new_alloc)
+		pcpu_extend_area_map(chunk, new_alloc);
+}
+
+/**
+ * pcpu_fit_in_area - try to fit the requested allocation in a candidate area
+ * @chunk: chunk the candidate area belongs to
+ * @off: the offset to the start of the candidate area
+ * @this_size: the size of the candidate area
+ * @size: the size of the target allocation
+ * @align: the alignment of the target allocation
+ * @pop_only: only allocate from already populated region
+ *
+ * We're trying to allocate @size bytes aligned at @align.  @chunk's area
+ * at @off sized @this_size is a candidate.  This function determines
+ * whether the target allocation fits in the candidate area and returns the
+ * number of bytes to pad after @off.  If the target area doesn't fit, -1
+ * is returned.
+ *
+ * If @pop_only is %true, this function only considers the already
+ * populated part of the candidate area.
+ */
+static int pcpu_fit_in_area(struct pcpu_chunk *chunk, int off, int this_size,
+			    int size, int align, bool pop_only)
+{
+	int cand_off = off;
+
+	while (true) {
+		int head = ALIGN(cand_off, align) - off;
+		int page_start, page_end, rs, re;
+
+		if (this_size < head + size)
+			return -1;
+
+		if (!pop_only)
+			return head;
+
+		/*
+		 * If the first unpopulated page is beyond the end of the
+		 * allocation, the whole allocation is populated;
+		 * otherwise, retry from the end of the unpopulated area.
+		 */
+		page_start = PFN_DOWN(head + off);
+		page_end = PFN_UP(head + off + size);
+
+		rs = page_start;
+		pcpu_next_unpop(chunk, &rs, &re, PFN_UP(off + this_size));
+		if (rs >= page_end)
+			return head;
+		cand_off = re * PAGE_SIZE;
+	}
+}
+
 /**
  * pcpu_alloc_area - allocate area from a pcpu_chunk
  * @chunk: chunk of interest
  * @size: wanted size in bytes
  * @align: wanted align
+ * @pop_only: allocate only from the populated area
+ * @occ_pages_p: out param for the number of pages the area occupies
  *
  * Try to allocate @size bytes area aligned at @align from @chunk.
  * Note that this function only allocates the offset.  It doesn't
@@ -437,7 +553,8 @@ out_unlock:
  * Allocated offset in @chunk on success, -1 if no matching area is
  * found.
  */
-static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
+static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align,
+			   bool pop_only, int *occ_pages_p)
 {
 	int oslot = pcpu_chunk_slot(chunk);
 	int max_contig = 0;
@@ -453,11 +570,11 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
 		if (off & 1)
 			continue;
 
-		/* extra for alignment requirement */
-		head = ALIGN(off, align) - off;
-
 		this_size = (p[1] & ~1) - off;
-		if (this_size < head + size) {
+
+		head = pcpu_fit_in_area(chunk, off, this_size, size, align,
+					pop_only);
+		if (head < 0) {
 			if (!seen_free) {
 				chunk->first_free = i;
 				seen_free = true;
@@ -526,6 +643,7 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
 		chunk->free_size -= size;
 		*p |= 1;
 
+		*occ_pages_p = pcpu_count_occupied_pages(chunk, i);
 		pcpu_chunk_relocate(chunk, oslot);
 		return off;
 	}
@@ -541,6 +659,7 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
  * pcpu_free_area - free area to a pcpu_chunk
  * @chunk: chunk of interest
  * @freeme: offset of area to free
+ * @occ_pages_p: out param for the number of pages the area occupies
  *
  * Free area starting from @freeme to @chunk.  Note that this function
  * only modifies the allocation map.  It doesn't depopulate or unmap
@@ -549,7 +668,8 @@ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
  * CONTEXT:
  * pcpu_lock.
  */
-static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme)
+static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme,
+			   int *occ_pages_p)
 {
 	int oslot = pcpu_chunk_slot(chunk);
 	int off = 0;
@@ -580,6 +700,8 @@ static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme)
 	*p = off &= ~1;
 	chunk->free_size += (p[1] & ~1) - off;
 
+	*occ_pages_p = pcpu_count_occupied_pages(chunk, i);
+
 	/* merge with next? */
 	if (!(p[1] & 1))
 		to_free++;
@@ -620,6 +742,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	chunk->map_used = 1;
 
 	INIT_LIST_HEAD(&chunk->list);
+	INIT_WORK(&chunk->map_extend_work, pcpu_map_extend_workfn);
 	chunk->free_size = pcpu_unit_size;
 	chunk->contig_hint = pcpu_unit_size;
 
@@ -634,6 +757,50 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk)
 	pcpu_mem_free(chunk, pcpu_chunk_struct_size);
 }
 
+/**
+ * pcpu_chunk_populated - post-population bookkeeping
+ * @chunk: pcpu_chunk which got populated
+ * @page_start: the start page
+ * @page_end: the end page
+ *
+ * Pages in [@page_start,@page_end) have been populated to @chunk.  Update
+ * the bookkeeping information accordingly.  Must be called after each
+ * successful population.
+ */
+static void pcpu_chunk_populated(struct pcpu_chunk *chunk,
+				 int page_start, int page_end)
+{
+	int nr = page_end - page_start;
+
+	lockdep_assert_held(&pcpu_lock);
+
+	bitmap_set(chunk->populated, page_start, nr);
+	chunk->nr_populated += nr;
+	pcpu_nr_empty_pop_pages += nr;
+}
+
+/**
+ * pcpu_chunk_depopulated - post-depopulation bookkeeping
+ * @chunk: pcpu_chunk which got depopulated
+ * @page_start: the start page
+ * @page_end: the end page
+ *
+ * Pages in [@page_start,@page_end) have been depopulated from @chunk.
+ * Update the bookkeeping information accordingly.  Must be called after
+ * each successful depopulation.
+ */
+static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk,
+				   int page_start, int page_end)
+{
+	int nr = page_end - page_start;
+
+	lockdep_assert_held(&pcpu_lock);
+
+	bitmap_clear(chunk->populated, page_start, nr);
+	chunk->nr_populated -= nr;
+	pcpu_nr_empty_pop_pages -= nr;
+}
+
 /*
  * Chunk management implementation.
  *
@@ -695,21 +862,23 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
  * @reserved: allocate from the reserved chunk if available
+ * @gfp: allocation flags
  *
- * Allocate percpu area of @size bytes aligned at @align.
- *
- * CONTEXT:
- * Does GFP_KERNEL allocation.
+ * Allocate percpu area of @size bytes aligned at @align.  If @gfp doesn't
+ * contain %GFP_KERNEL, the allocation is atomic.
  *
  * RETURNS:
  * Percpu pointer to the allocated area on success, NULL on failure.
  */
-static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved)
+static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
+				 gfp_t gfp)
 {
 	static int warn_limit = 10;
 	struct pcpu_chunk *chunk;
 	const char *err;
-	int slot, off, new_alloc;
+	bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
+	int occ_pages = 0;
+	int slot, off, new_alloc, cpu, ret;
 	unsigned long flags;
 	void __percpu *ptr;
 
@@ -728,7 +897,6 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved)
 		return NULL;
 	}
 
-	mutex_lock(&pcpu_alloc_mutex);
 	spin_lock_irqsave(&pcpu_lock, flags);
 
 	/* serve reserved allocations from the reserved chunk if available */
@@ -740,16 +908,18 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved)
 			goto fail_unlock;
 		}
 
-		while ((new_alloc = pcpu_need_to_extend(chunk))) {
+		while ((new_alloc = pcpu_need_to_extend(chunk, is_atomic))) {
 			spin_unlock_irqrestore(&pcpu_lock, flags);
-			if (pcpu_extend_area_map(chunk, new_alloc) < 0) {
+			if (is_atomic ||
+			    pcpu_extend_area_map(chunk, new_alloc) < 0) {
 				err = "failed to extend area map of reserved chunk";
-				goto fail_unlock_mutex;
+				goto fail;
 			}
 			spin_lock_irqsave(&pcpu_lock, flags);
 		}
 
-		off = pcpu_alloc_area(chunk, size, align);
+		off = pcpu_alloc_area(chunk, size, align, is_atomic,
+				      &occ_pages);
 		if (off >= 0)
 			goto area_found;
 
@@ -764,13 +934,15 @@ restart:
 			if (size > chunk->contig_hint)
 				continue;
 
-			new_alloc = pcpu_need_to_extend(chunk);
+			new_alloc = pcpu_need_to_extend(chunk, is_atomic);
 			if (new_alloc) {
+				if (is_atomic)
+					continue;
 				spin_unlock_irqrestore(&pcpu_lock, flags);
 				if (pcpu_extend_area_map(chunk,
 							 new_alloc) < 0) {
 					err = "failed to extend area map";
-					goto fail_unlock_mutex;
+					goto fail;
 				}
 				spin_lock_irqsave(&pcpu_lock, flags);
 				/*
@@ -780,74 +952,134 @@ restart:
 				goto restart;
 			}
 
-			off = pcpu_alloc_area(chunk, size, align);
+			off = pcpu_alloc_area(chunk, size, align, is_atomic,
+					      &occ_pages);
 			if (off >= 0)
 				goto area_found;
 		}
 	}
 
-	/* hmmm... no space left, create a new chunk */
 	spin_unlock_irqrestore(&pcpu_lock, flags);
 
-	chunk = pcpu_create_chunk();
-	if (!chunk) {
-		err = "failed to allocate new chunk";
-		goto fail_unlock_mutex;
+	/*
+	 * No space left.  Create a new chunk.  We don't want multiple
+	 * tasks to create chunks simultaneously.  Serialize and create iff
+	 * there's still no empty chunk after grabbing the mutex.
+	 */
+	if (is_atomic)
+		goto fail;
+
+	mutex_lock(&pcpu_alloc_mutex);
+
+	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
+		chunk = pcpu_create_chunk();
+		if (!chunk) {
+			mutex_unlock(&pcpu_alloc_mutex);
+			err = "failed to allocate new chunk";
+			goto fail;
+		}
+
+		spin_lock_irqsave(&pcpu_lock, flags);
+		pcpu_chunk_relocate(chunk, -1);
+	} else {
+		spin_lock_irqsave(&pcpu_lock, flags);
 	}
 
-	spin_lock_irqsave(&pcpu_lock, flags);
-	pcpu_chunk_relocate(chunk, -1);
+	mutex_unlock(&pcpu_alloc_mutex);
 	goto restart;
 
 area_found:
 	spin_unlock_irqrestore(&pcpu_lock, flags);
 
-	/* populate, map and clear the area */
-	if (pcpu_populate_chunk(chunk, off, size)) {
-		spin_lock_irqsave(&pcpu_lock, flags);
-		pcpu_free_area(chunk, off);
-		err = "failed to populate";
-		goto fail_unlock;
+	/* populate if not all pages are already there */
+	if (!is_atomic) {
+		int page_start, page_end, rs, re;
+
+		mutex_lock(&pcpu_alloc_mutex);
+
+		page_start = PFN_DOWN(off);
+		page_end = PFN_UP(off + size);
+
+		pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
+			WARN_ON(chunk->immutable);
+
+			ret = pcpu_populate_chunk(chunk, rs, re);
+
+			spin_lock_irqsave(&pcpu_lock, flags);
+			if (ret) {
+				mutex_unlock(&pcpu_alloc_mutex);
+				pcpu_free_area(chunk, off, &occ_pages);
+				err = "failed to populate";
+				goto fail_unlock;
+			}
+			pcpu_chunk_populated(chunk, rs, re);
+			spin_unlock_irqrestore(&pcpu_lock, flags);
+		}
+
+		mutex_unlock(&pcpu_alloc_mutex);
 	}
 
-	mutex_unlock(&pcpu_alloc_mutex);
+	if (chunk != pcpu_reserved_chunk)
+		pcpu_nr_empty_pop_pages -= occ_pages;
+
+	if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
+		pcpu_schedule_balance_work();
+
+	/* clear the areas and return address relative to base address */
+	for_each_possible_cpu(cpu)
+		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
 
-	/* return address relative to base address */
 	ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
 	kmemleak_alloc_percpu(ptr, size);
 	return ptr;
 
 fail_unlock:
 	spin_unlock_irqrestore(&pcpu_lock, flags);
-fail_unlock_mutex:
-	mutex_unlock(&pcpu_alloc_mutex);
-	if (warn_limit) {
-		pr_warning("PERCPU: allocation failed, size=%zu align=%zu, "
-			   "%s\n", size, align, err);
+fail:
+	if (!is_atomic && warn_limit) {
+		pr_warning("PERCPU: allocation failed, size=%zu align=%zu atomic=%d, %s\n",
+			   size, align, is_atomic, err);
 		dump_stack();
 		if (!--warn_limit)
 			pr_info("PERCPU: limit reached, disable warning\n");
 	}
+	if (is_atomic) {
+		/* see the flag handling in pcpu_blance_workfn() */
+		pcpu_atomic_alloc_failed = true;
+		pcpu_schedule_balance_work();
+	}
 	return NULL;
 }
 
 /**
- * __alloc_percpu - allocate dynamic percpu area
+ * __alloc_percpu_gfp - allocate dynamic percpu area
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
+ * @gfp: allocation flags
  *
- * Allocate zero-filled percpu area of @size bytes aligned at @align.
- * Might sleep.  Might trigger writeouts.
- *
- * CONTEXT:
- * Does GFP_KERNEL allocation.
+ * Allocate zero-filled percpu area of @size bytes aligned at @align.  If
+ * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can
+ * be called from any context but is a lot more likely to fail.
  *
  * RETURNS:
  * Percpu pointer to the allocated area on success, NULL on failure.
  */
+void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp)
+{
+	return pcpu_alloc(size, align, false, gfp);
+}
+EXPORT_SYMBOL_GPL(__alloc_percpu_gfp);
+
+/**
+ * __alloc_percpu - allocate dynamic percpu area
+ * @size: size of area to allocate in bytes
+ * @align: alignment of area (max PAGE_SIZE)
+ *
+ * Equivalent to __alloc_percpu_gfp(size, align, %GFP_KERNEL).
+ */
 void __percpu *__alloc_percpu(size_t size, size_t align)
 {
-	return pcpu_alloc(size, align, false);
+	return pcpu_alloc(size, align, false, GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(__alloc_percpu);
 
@@ -869,44 +1101,121 @@ EXPORT_SYMBOL_GPL(__alloc_percpu);
  */
 void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
 {
-	return pcpu_alloc(size, align, true);
+	return pcpu_alloc(size, align, true, GFP_KERNEL);
 }
 
 /**
- * pcpu_reclaim - reclaim fully free chunks, workqueue function
+ * pcpu_balance_workfn - manage the amount of free chunks and populated pages
  * @work: unused
  *
  * Reclaim all fully free chunks except for the first one.
- *
- * CONTEXT:
- * workqueue context.
  */
-static void pcpu_reclaim(struct work_struct *work)
+static void pcpu_balance_workfn(struct work_struct *work)
 {
-	LIST_HEAD(todo);
-	struct list_head *head = &pcpu_slot[pcpu_nr_slots - 1];
+	LIST_HEAD(to_free);
+	struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
 	struct pcpu_chunk *chunk, *next;
+	int slot, nr_to_pop, ret;
 
+	/*
+	 * There's no reason to keep around multiple unused chunks and VM
+	 * areas can be scarce.  Destroy all free chunks except for one.
+	 */
 	mutex_lock(&pcpu_alloc_mutex);
 	spin_lock_irq(&pcpu_lock);
 
-	list_for_each_entry_safe(chunk, next, head, list) {
+	list_for_each_entry_safe(chunk, next, free_head, list) {
 		WARN_ON(chunk->immutable);
 
 		/* spare the first one */
-		if (chunk == list_first_entry(head, struct pcpu_chunk, list))
+		if (chunk == list_first_entry(free_head, struct pcpu_chunk, list))
 			continue;
 
-		list_move(&chunk->list, &todo);
+		list_move(&chunk->list, &to_free);
 	}
 
 	spin_unlock_irq(&pcpu_lock);
 
-	list_for_each_entry_safe(chunk, next, &todo, list) {
-		pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size);
+	list_for_each_entry_safe(chunk, next, &to_free, list) {
+		int rs, re;
+
+		pcpu_for_each_pop_region(chunk, rs, re, 0, pcpu_unit_pages) {
+			pcpu_depopulate_chunk(chunk, rs, re);
+			spin_lock_irq(&pcpu_lock);
+			pcpu_chunk_depopulated(chunk, rs, re);
+			spin_unlock_irq(&pcpu_lock);
+		}
 		pcpu_destroy_chunk(chunk);
 	}
 
+	/*
+	 * Ensure there are certain number of free populated pages for
+	 * atomic allocs.  Fill up from the most packed so that atomic
+	 * allocs don't increase fragmentation.  If atomic allocation
+	 * failed previously, always populate the maximum amount.  This
+	 * should prevent atomic allocs larger than PAGE_SIZE from keeping
+	 * failing indefinitely; however, large atomic allocs are not
+	 * something we support properly and can be highly unreliable and
+	 * inefficient.
+	 */
+retry_pop:
+	if (pcpu_atomic_alloc_failed) {
+		nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH;
+		/* best effort anyway, don't worry about synchronization */
+		pcpu_atomic_alloc_failed = false;
+	} else {
+		nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
+				  pcpu_nr_empty_pop_pages,
+				  0, PCPU_EMPTY_POP_PAGES_HIGH);
+	}
+
+	for (slot = pcpu_size_to_slot(PAGE_SIZE); slot < pcpu_nr_slots; slot++) {
+		int nr_unpop = 0, rs, re;
+
+		if (!nr_to_pop)
+			break;
+
+		spin_lock_irq(&pcpu_lock);
+		list_for_each_entry(chunk, &pcpu_slot[slot], list) {
+			nr_unpop = pcpu_unit_pages - chunk->nr_populated;
+			if (nr_unpop)
+				break;
+		}
+		spin_unlock_irq(&pcpu_lock);
+
+		if (!nr_unpop)
+			continue;
+
+		/* @chunk can't go away while pcpu_alloc_mutex is held */
+		pcpu_for_each_unpop_region(chunk, rs, re, 0, pcpu_unit_pages) {
+			int nr = min(re - rs, nr_to_pop);
+
+			ret = pcpu_populate_chunk(chunk, rs, rs + nr);
+			if (!ret) {
+				nr_to_pop -= nr;
+				spin_lock_irq(&pcpu_lock);
+				pcpu_chunk_populated(chunk, rs, rs + nr);
+				spin_unlock_irq(&pcpu_lock);
+			} else {
+				nr_to_pop = 0;
+			}
+
+			if (!nr_to_pop)
+				break;
+		}
+	}
+
+	if (nr_to_pop) {
+		/* ran out of chunks to populate, create a new one and retry */
+		chunk = pcpu_create_chunk();
+		if (chunk) {
+			spin_lock_irq(&pcpu_lock);
+			pcpu_chunk_relocate(chunk, -1);
+			spin_unlock_irq(&pcpu_lock);
+			goto retry_pop;
+		}
+	}
+
 	mutex_unlock(&pcpu_alloc_mutex);
 }
 
@@ -924,7 +1233,7 @@ void free_percpu(void __percpu *ptr)
 	void *addr;
 	struct pcpu_chunk *chunk;
 	unsigned long flags;
-	int off;
+	int off, occ_pages;
 
 	if (!ptr)
 		return;
@@ -938,7 +1247,10 @@ void free_percpu(void __percpu *ptr)
 	chunk = pcpu_chunk_addr_search(addr);
 	off = addr - chunk->base_addr;
 
-	pcpu_free_area(chunk, off);
+	pcpu_free_area(chunk, off, &occ_pages);
+
+	if (chunk != pcpu_reserved_chunk)
+		pcpu_nr_empty_pop_pages += occ_pages;
 
 	/* if there are more than one fully free chunks, wake up grim reaper */
 	if (chunk->free_size == pcpu_unit_size) {
@@ -946,7 +1258,7 @@ void free_percpu(void __percpu *ptr)
 
 		list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list)
 			if (pos != chunk) {
-				schedule_work(&pcpu_reclaim_work);
+				pcpu_schedule_balance_work();
 				break;
 			}
 	}
@@ -1336,11 +1648,13 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	 */
 	schunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 	INIT_LIST_HEAD(&schunk->list);
+	INIT_WORK(&schunk->map_extend_work, pcpu_map_extend_workfn);
 	schunk->base_addr = base_addr;
 	schunk->map = smap;
 	schunk->map_alloc = ARRAY_SIZE(smap);
 	schunk->immutable = true;
 	bitmap_fill(schunk->populated, pcpu_unit_pages);
+	schunk->nr_populated = pcpu_unit_pages;
 
 	if (ai->reserved_size) {
 		schunk->free_size = ai->reserved_size;
@@ -1364,11 +1678,13 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	if (dyn_size) {
 		dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
 		INIT_LIST_HEAD(&dchunk->list);
+		INIT_WORK(&dchunk->map_extend_work, pcpu_map_extend_workfn);
 		dchunk->base_addr = base_addr;
 		dchunk->map = dmap;
 		dchunk->map_alloc = ARRAY_SIZE(dmap);
 		dchunk->immutable = true;
 		bitmap_fill(dchunk->populated, pcpu_unit_pages);
+		dchunk->nr_populated = pcpu_unit_pages;
 
 		dchunk->contig_hint = dchunk->free_size = dyn_size;
 		dchunk->map[0] = 1;
@@ -1379,6 +1695,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 	/* link the first chunk in */
 	pcpu_first_chunk = dchunk ?: schunk;
+	pcpu_nr_empty_pop_pages +=
+		pcpu_count_occupied_pages(pcpu_first_chunk, 1);
 	pcpu_chunk_relocate(pcpu_first_chunk, -1);
 
 	/* we're done */
@@ -1932,8 +2250,6 @@ void __init setup_per_cpu_areas(void)
 
 	if (pcpu_setup_first_chunk(ai, fc) < 0)
 		panic("Failed to initialize percpu areas.");
-
-	pcpu_free_alloc_info(ai);
 }
 
 #endif	/* CONFIG_SMP */
@@ -1967,3 +2283,15 @@ void __init percpu_init_late(void)
 		spin_unlock_irqrestore(&pcpu_lock, flags);
 	}
 }
+
+/*
+ * Percpu allocator is initialized early during boot when neither slab or
+ * workqueue is available.  Plug async management until everything is up
+ * and running.
+ */
+static int __init percpu_enable_async(void)
+{
+	pcpu_async_enabled = true;
+	return 0;
+}
+subsys_initcall(percpu_enable_async);
diff --git a/mm/rmap.c b/mm/rmap.c
index bc74e0012809..116a5053415b 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -527,7 +527,7 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 	unsigned long address = __vma_address(page, vma);
 
 	/* page should be within @vma mapping range */
-	VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
 
 	return address;
 }
@@ -897,7 +897,7 @@ void page_move_anon_rmap(struct page *page,
 	struct anon_vma *anon_vma = vma->anon_vma;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	VM_BUG_ON(!anon_vma);
+	VM_BUG_ON_VMA(!anon_vma, vma);
 	VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page);
 
 	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
@@ -1024,7 +1024,7 @@ void do_page_add_anon_rmap(struct page *page,
 void page_add_new_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address)
 {
-	VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
 	SetPageSwapBacked(page);
 	atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
 	if (PageTransHuge(page))
@@ -1670,7 +1670,7 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 	 * structure at mapping cannot be freed and reused yet,
 	 * so we can safely take mapping->i_mmap_mutex.
 	 */
-	VM_BUG_ON(!PageLocked(page));
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	if (!mapping)
 		return ret;
diff --git a/mm/shmem.c b/mm/shmem.c
index 469f90d56051..cd6fc7590e54 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2995,7 +2995,7 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent)
 #endif
 
 	spin_lock_init(&sbinfo->stat_lock);
-	if (percpu_counter_init(&sbinfo->used_blocks, 0))
+	if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL))
 		goto failed;
 	sbinfo->free_inodes = sbinfo->max_inodes;
 
@@ -3077,7 +3077,9 @@ static const struct address_space_operations shmem_aops = {
 	.write_begin	= shmem_write_begin,
 	.write_end	= shmem_write_end,
 #endif
+#ifdef CONFIG_MIGRATION
 	.migratepage	= migrate_page,
+#endif
 	.error_remove_page = generic_error_remove_page,
 };
 
diff --git a/mm/slab.c b/mm/slab.c
index 7c52b3890d25..eb2b2ea30130 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -237,11 +237,10 @@ struct arraycache_init {
 /*
  * Need this for bootstrapping a per node allocator.
  */
-#define NUM_INIT_LISTS (3 * MAX_NUMNODES)
+#define NUM_INIT_LISTS (2 * MAX_NUMNODES)
 static struct kmem_cache_node __initdata init_kmem_cache_node[NUM_INIT_LISTS];
 #define	CACHE_CACHE 0
-#define	SIZE_AC MAX_NUMNODES
-#define	SIZE_NODE (2 * MAX_NUMNODES)
+#define	SIZE_NODE (MAX_NUMNODES)
 
 static int drain_freelist(struct kmem_cache *cache,
 			struct kmem_cache_node *n, int tofree);
@@ -253,7 +252,6 @@ static void cache_reap(struct work_struct *unused);
 
 static int slab_early_init = 1;
 
-#define INDEX_AC kmalloc_index(sizeof(struct arraycache_init))
 #define INDEX_NODE kmalloc_index(sizeof(struct kmem_cache_node))
 
 static void kmem_cache_node_init(struct kmem_cache_node *parent)
@@ -458,9 +456,6 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache,
 	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
 }
 
-static struct arraycache_init initarray_generic =
-    { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
-
 /* internal cache of cache description objs */
 static struct kmem_cache kmem_cache_boot = {
 	.batchcount = 1,
@@ -476,7 +471,7 @@ static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
 
 static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 {
-	return cachep->array[smp_processor_id()];
+	return this_cpu_ptr(cachep->cpu_cache);
 }
 
 static size_t calculate_freelist_size(int nr_objs, size_t align)
@@ -785,8 +780,8 @@ static inline void *ac_get_obj(struct kmem_cache *cachep,
 	return objp;
 }
 
-static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
-								void *objp)
+static noinline void *__ac_put_obj(struct kmem_cache *cachep,
+			struct array_cache *ac, void *objp)
 {
 	if (unlikely(pfmemalloc_active)) {
 		/* Some pfmemalloc slabs exist, check if this is one */
@@ -984,46 +979,50 @@ static void drain_alien_cache(struct kmem_cache *cachep,
 	}
 }
 
-static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
+static int __cache_free_alien(struct kmem_cache *cachep, void *objp,
+				int node, int page_node)
 {
-	int nodeid = page_to_nid(virt_to_page(objp));
 	struct kmem_cache_node *n;
 	struct alien_cache *alien = NULL;
 	struct array_cache *ac;
-	int node;
 	LIST_HEAD(list);
 
-	node = numa_mem_id();
-
-	/*
-	 * Make sure we are not freeing a object from another node to the array
-	 * cache on this cpu.
-	 */
-	if (likely(nodeid == node))
-		return 0;
-
 	n = get_node(cachep, node);
 	STATS_INC_NODEFREES(cachep);
-	if (n->alien && n->alien[nodeid]) {
-		alien = n->alien[nodeid];
+	if (n->alien && n->alien[page_node]) {
+		alien = n->alien[page_node];
 		ac = &alien->ac;
 		spin_lock(&alien->lock);
 		if (unlikely(ac->avail == ac->limit)) {
 			STATS_INC_ACOVERFLOW(cachep);
-			__drain_alien_cache(cachep, ac, nodeid, &list);
+			__drain_alien_cache(cachep, ac, page_node, &list);
 		}
 		ac_put_obj(cachep, ac, objp);
 		spin_unlock(&alien->lock);
 		slabs_destroy(cachep, &list);
 	} else {
-		n = get_node(cachep, nodeid);
+		n = get_node(cachep, page_node);
 		spin_lock(&n->list_lock);
-		free_block(cachep, &objp, 1, nodeid, &list);
+		free_block(cachep, &objp, 1, page_node, &list);
 		spin_unlock(&n->list_lock);
 		slabs_destroy(cachep, &list);
 	}
 	return 1;
 }
+
+static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
+{
+	int page_node = page_to_nid(virt_to_page(objp));
+	int node = numa_mem_id();
+	/*
+	 * Make sure we are not freeing a object from another node to the array
+	 * cache on this cpu.
+	 */
+	if (likely(node == page_node))
+		return 0;
+
+	return __cache_free_alien(cachep, objp, node, page_node);
+}
 #endif
 
 /*
@@ -1092,24 +1091,25 @@ static void cpuup_canceled(long cpu)
 		struct alien_cache **alien;
 		LIST_HEAD(list);
 
-		/* cpu is dead; no one can alloc from it. */
-		nc = cachep->array[cpu];
-		cachep->array[cpu] = NULL;
 		n = get_node(cachep, node);
-
 		if (!n)
-			goto free_array_cache;
+			continue;
 
 		spin_lock_irq(&n->list_lock);
 
 		/* Free limit for this kmem_cache_node */
 		n->free_limit -= cachep->batchcount;
-		if (nc)
+
+		/* cpu is dead; no one can alloc from it. */
+		nc = per_cpu_ptr(cachep->cpu_cache, cpu);
+		if (nc) {
 			free_block(cachep, nc->entry, nc->avail, node, &list);
+			nc->avail = 0;
+		}
 
 		if (!cpumask_empty(mask)) {
 			spin_unlock_irq(&n->list_lock);
-			goto free_array_cache;
+			goto free_slab;
 		}
 
 		shared = n->shared;
@@ -1129,9 +1129,9 @@ static void cpuup_canceled(long cpu)
 			drain_alien_cache(cachep, alien);
 			free_alien_cache(alien);
 		}
-free_array_cache:
+
+free_slab:
 		slabs_destroy(cachep, &list);
-		kfree(nc);
 	}
 	/*
 	 * In the previous loop, all the objects were freed to
@@ -1168,32 +1168,23 @@ static int cpuup_prepare(long cpu)
 	 * array caches
 	 */
 	list_for_each_entry(cachep, &slab_caches, list) {
-		struct array_cache *nc;
 		struct array_cache *shared = NULL;
 		struct alien_cache **alien = NULL;
 
-		nc = alloc_arraycache(node, cachep->limit,
-					cachep->batchcount, GFP_KERNEL);
-		if (!nc)
-			goto bad;
 		if (cachep->shared) {
 			shared = alloc_arraycache(node,
 				cachep->shared * cachep->batchcount,
 				0xbaadf00d, GFP_KERNEL);
-			if (!shared) {
-				kfree(nc);
+			if (!shared)
 				goto bad;
-			}
 		}
 		if (use_alien_caches) {
 			alien = alloc_alien_cache(node, cachep->limit, GFP_KERNEL);
 			if (!alien) {
 				kfree(shared);
-				kfree(nc);
 				goto bad;
 			}
 		}
-		cachep->array[cpu] = nc;
 		n = get_node(cachep, node);
 		BUG_ON(!n);
 
@@ -1385,15 +1376,6 @@ static void __init set_up_node(struct kmem_cache *cachep, int index)
 }
 
 /*
- * The memory after the last cpu cache pointer is used for the
- * the node pointer.
- */
-static void setup_node_pointer(struct kmem_cache *cachep)
-{
-	cachep->node = (struct kmem_cache_node **)&cachep->array[nr_cpu_ids];
-}
-
-/*
  * Initialisation.  Called after the page allocator have been initialised and
  * before smp_init().
  */
@@ -1404,7 +1386,6 @@ void __init kmem_cache_init(void)
 	BUILD_BUG_ON(sizeof(((struct page *)NULL)->lru) <
 					sizeof(struct rcu_head));
 	kmem_cache = &kmem_cache_boot;
-	setup_node_pointer(kmem_cache);
 
 	if (num_possible_nodes() == 1)
 		use_alien_caches = 0;
@@ -1412,8 +1393,6 @@ void __init kmem_cache_init(void)
 	for (i = 0; i < NUM_INIT_LISTS; i++)
 		kmem_cache_node_init(&init_kmem_cache_node[i]);
 
-	set_up_node(kmem_cache, CACHE_CACHE);
-
 	/*
 	 * Fragmentation resistance on low memory - only use bigger
 	 * page orders on machines with more than 32MB of memory if
@@ -1448,49 +1427,22 @@ void __init kmem_cache_init(void)
 	 * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids
 	 */
 	create_boot_cache(kmem_cache, "kmem_cache",
-		offsetof(struct kmem_cache, array[nr_cpu_ids]) +
+		offsetof(struct kmem_cache, node) +
 				  nr_node_ids * sizeof(struct kmem_cache_node *),
 				  SLAB_HWCACHE_ALIGN);
 	list_add(&kmem_cache->list, &slab_caches);
-
-	/* 2+3) create the kmalloc caches */
+	slab_state = PARTIAL;
 
 	/*
-	 * Initialize the caches that provide memory for the array cache and the
-	 * kmem_cache_node structures first.  Without this, further allocations will
-	 * bug.
+	 * Initialize the caches that provide memory for the  kmem_cache_node
+	 * structures first.  Without this, further allocations will bug.
 	 */
-
-	kmalloc_caches[INDEX_AC] = create_kmalloc_cache("kmalloc-ac",
-					kmalloc_size(INDEX_AC), ARCH_KMALLOC_FLAGS);
-
-	if (INDEX_AC != INDEX_NODE)
-		kmalloc_caches[INDEX_NODE] =
-			create_kmalloc_cache("kmalloc-node",
+	kmalloc_caches[INDEX_NODE] = create_kmalloc_cache("kmalloc-node",
 				kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS);
+	slab_state = PARTIAL_NODE;
 
 	slab_early_init = 0;
 
-	/* 4) Replace the bootstrap head arrays */
-	{
-		struct array_cache *ptr;
-
-		ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
-
-		memcpy(ptr, cpu_cache_get(kmem_cache),
-		       sizeof(struct arraycache_init));
-
-		kmem_cache->array[smp_processor_id()] = ptr;
-
-		ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
-
-		BUG_ON(cpu_cache_get(kmalloc_caches[INDEX_AC])
-		       != &initarray_generic.cache);
-		memcpy(ptr, cpu_cache_get(kmalloc_caches[INDEX_AC]),
-		       sizeof(struct arraycache_init));
-
-		kmalloc_caches[INDEX_AC]->array[smp_processor_id()] = ptr;
-	}
 	/* 5) Replace the bootstrap kmem_cache_node */
 	{
 		int nid;
@@ -1498,13 +1450,8 @@ void __init kmem_cache_init(void)
 		for_each_online_node(nid) {
 			init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid);
 
-			init_list(kmalloc_caches[INDEX_AC],
-				  &init_kmem_cache_node[SIZE_AC + nid], nid);
-
-			if (INDEX_AC != INDEX_NODE) {
-				init_list(kmalloc_caches[INDEX_NODE],
+			init_list(kmalloc_caches[INDEX_NODE],
 					  &init_kmem_cache_node[SIZE_NODE + nid], nid);
-			}
 		}
 	}
 
@@ -2037,56 +1984,53 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 	return left_over;
 }
 
+static struct array_cache __percpu *alloc_kmem_cache_cpus(
+		struct kmem_cache *cachep, int entries, int batchcount)
+{
+	int cpu;
+	size_t size;
+	struct array_cache __percpu *cpu_cache;
+
+	size = sizeof(void *) * entries + sizeof(struct array_cache);
+	cpu_cache = __alloc_percpu(size, sizeof(void *));
+
+	if (!cpu_cache)
+		return NULL;
+
+	for_each_possible_cpu(cpu) {
+		init_arraycache(per_cpu_ptr(cpu_cache, cpu),
+				entries, batchcount);
+	}
+
+	return cpu_cache;
+}
+
 static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	if (slab_state >= FULL)
 		return enable_cpucache(cachep, gfp);
 
+	cachep->cpu_cache = alloc_kmem_cache_cpus(cachep, 1, 1);
+	if (!cachep->cpu_cache)
+		return 1;
+
 	if (slab_state == DOWN) {
-		/*
-		 * Note: Creation of first cache (kmem_cache).
-		 * The setup_node is taken care
-		 * of by the caller of __kmem_cache_create
-		 */
-		cachep->array[smp_processor_id()] = &initarray_generic.cache;
-		slab_state = PARTIAL;
+		/* Creation of first cache (kmem_cache). */
+		set_up_node(kmem_cache, CACHE_CACHE);
 	} else if (slab_state == PARTIAL) {
-		/*
-		 * Note: the second kmem_cache_create must create the cache
-		 * that's used by kmalloc(24), otherwise the creation of
-		 * further caches will BUG().
-		 */
-		cachep->array[smp_processor_id()] = &initarray_generic.cache;
-
-		/*
-		 * If the cache that's used by kmalloc(sizeof(kmem_cache_node)) is
-		 * the second cache, then we need to set up all its node/,
-		 * otherwise the creation of further caches will BUG().
-		 */
-		set_up_node(cachep, SIZE_AC);
-		if (INDEX_AC == INDEX_NODE)
-			slab_state = PARTIAL_NODE;
-		else
-			slab_state = PARTIAL_ARRAYCACHE;
+		/* For kmem_cache_node */
+		set_up_node(cachep, SIZE_NODE);
 	} else {
-		/* Remaining boot caches */
-		cachep->array[smp_processor_id()] =
-			kmalloc(sizeof(struct arraycache_init), gfp);
+		int node;
 
-		if (slab_state == PARTIAL_ARRAYCACHE) {
-			set_up_node(cachep, SIZE_NODE);
-			slab_state = PARTIAL_NODE;
-		} else {
-			int node;
-			for_each_online_node(node) {
-				cachep->node[node] =
-				    kmalloc_node(sizeof(struct kmem_cache_node),
-						gfp, node);
-				BUG_ON(!cachep->node[node]);
-				kmem_cache_node_init(cachep->node[node]);
-			}
+		for_each_online_node(node) {
+			cachep->node[node] = kmalloc_node(
+				sizeof(struct kmem_cache_node), gfp, node);
+			BUG_ON(!cachep->node[node]);
+			kmem_cache_node_init(cachep->node[node]);
 		}
 	}
+
 	cachep->node[numa_mem_id()]->next_reap =
 			jiffies + REAPTIMEOUT_NODE +
 			((unsigned long)cachep) % REAPTIMEOUT_NODE;
@@ -2100,6 +2044,32 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 	return 0;
 }
 
+unsigned long kmem_cache_flags(unsigned long object_size,
+	unsigned long flags, const char *name,
+	void (*ctor)(void *))
+{
+	return flags;
+}
+
+struct kmem_cache *
+__kmem_cache_alias(const char *name, size_t size, size_t align,
+		   unsigned long flags, void (*ctor)(void *))
+{
+	struct kmem_cache *cachep;
+
+	cachep = find_mergeable(size, align, flags, name, ctor);
+	if (cachep) {
+		cachep->refcount++;
+
+		/*
+		 * Adjust the object sizes so that we clear
+		 * the complete object on kzalloc.
+		 */
+		cachep->object_size = max_t(int, cachep->object_size, size);
+	}
+	return cachep;
+}
+
 /**
  * __kmem_cache_create - Create a cache.
  * @cachep: cache management descriptor
@@ -2183,7 +2153,6 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	else
 		gfp = GFP_NOWAIT;
 
-	setup_node_pointer(cachep);
 #if DEBUG
 
 	/*
@@ -2440,8 +2409,7 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep)
 	if (rc)
 		return rc;
 
-	for_each_online_cpu(i)
-	    kfree(cachep->array[i]);
+	free_percpu(cachep->cpu_cache);
 
 	/* NUMA: free the node structures */
 	for_each_kmem_cache_node(cachep, i, n) {
@@ -3399,7 +3367,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp,
 	if (nr_online_nodes > 1 && cache_free_alien(cachep, objp))
 		return;
 
-	if (likely(ac->avail < ac->limit)) {
+	if (ac->avail < ac->limit) {
 		STATS_INC_FREEHIT(cachep);
 	} else {
 		STATS_INC_FREEMISS(cachep);
@@ -3496,7 +3464,6 @@ __do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller)
 	return kmem_cache_alloc_node_trace(cachep, flags, node, size);
 }
 
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING)
 void *__kmalloc_node(size_t size, gfp_t flags, int node)
 {
 	return __do_kmalloc_node(size, flags, node, _RET_IP_);
@@ -3509,13 +3476,6 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
 	return __do_kmalloc_node(size, flags, node, caller);
 }
 EXPORT_SYMBOL(__kmalloc_node_track_caller);
-#else
-void *__kmalloc_node(size_t size, gfp_t flags, int node)
-{
-	return __do_kmalloc_node(size, flags, node, 0);
-}
-EXPORT_SYMBOL(__kmalloc_node);
-#endif /* CONFIG_DEBUG_SLAB || CONFIG_TRACING */
 #endif /* CONFIG_NUMA */
 
 /**
@@ -3541,8 +3501,6 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 	return ret;
 }
 
-
-#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING)
 void *__kmalloc(size_t size, gfp_t flags)
 {
 	return __do_kmalloc(size, flags, _RET_IP_);
@@ -3555,14 +3513,6 @@ void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller)
 }
 EXPORT_SYMBOL(__kmalloc_track_caller);
 
-#else
-void *__kmalloc(size_t size, gfp_t flags)
-{
-	return __do_kmalloc(size, flags, 0);
-}
-EXPORT_SYMBOL(__kmalloc);
-#endif
-
 /**
  * kmem_cache_free - Deallocate an object
  * @cachep: The cache the allocation was from.
@@ -3707,72 +3657,45 @@ fail:
 	return -ENOMEM;
 }
 
-struct ccupdate_struct {
-	struct kmem_cache *cachep;
-	struct array_cache *new[0];
-};
-
-static void do_ccupdate_local(void *info)
-{
-	struct ccupdate_struct *new = info;
-	struct array_cache *old;
-
-	check_irq_off();
-	old = cpu_cache_get(new->cachep);
-
-	new->cachep->array[smp_processor_id()] = new->new[smp_processor_id()];
-	new->new[smp_processor_id()] = old;
-}
-
 /* Always called with the slab_mutex held */
 static int __do_tune_cpucache(struct kmem_cache *cachep, int limit,
 				int batchcount, int shared, gfp_t gfp)
 {
-	struct ccupdate_struct *new;
-	int i;
+	struct array_cache __percpu *cpu_cache, *prev;
+	int cpu;
 
-	new = kzalloc(sizeof(*new) + nr_cpu_ids * sizeof(struct array_cache *),
-		      gfp);
-	if (!new)
+	cpu_cache = alloc_kmem_cache_cpus(cachep, limit, batchcount);
+	if (!cpu_cache)
 		return -ENOMEM;
 
-	for_each_online_cpu(i) {
-		new->new[i] = alloc_arraycache(cpu_to_mem(i), limit,
-						batchcount, gfp);
-		if (!new->new[i]) {
-			for (i--; i >= 0; i--)
-				kfree(new->new[i]);
-			kfree(new);
-			return -ENOMEM;
-		}
-	}
-	new->cachep = cachep;
-
-	on_each_cpu(do_ccupdate_local, (void *)new, 1);
+	prev = cachep->cpu_cache;
+	cachep->cpu_cache = cpu_cache;
+	kick_all_cpus_sync();
 
 	check_irq_on();
 	cachep->batchcount = batchcount;
 	cachep->limit = limit;
 	cachep->shared = shared;
 
-	for_each_online_cpu(i) {
+	if (!prev)
+		goto alloc_node;
+
+	for_each_online_cpu(cpu) {
 		LIST_HEAD(list);
-		struct array_cache *ccold = new->new[i];
 		int node;
 		struct kmem_cache_node *n;
+		struct array_cache *ac = per_cpu_ptr(prev, cpu);
 
-		if (!ccold)
-			continue;
-
-		node = cpu_to_mem(i);
+		node = cpu_to_mem(cpu);
 		n = get_node(cachep, node);
 		spin_lock_irq(&n->list_lock);
-		free_block(cachep, ccold->entry, ccold->avail, node, &list);
+		free_block(cachep, ac->entry, ac->avail, node, &list);
 		spin_unlock_irq(&n->list_lock);
 		slabs_destroy(cachep, &list);
-		kfree(ccold);
 	}
-	kfree(new);
+	free_percpu(prev);
+
+alloc_node:
 	return alloc_kmem_cache_node(cachep, gfp);
 }
 
@@ -4255,19 +4178,15 @@ static const struct seq_operations slabstats_op = {
 
 static int slabstats_open(struct inode *inode, struct file *file)
 {
-	unsigned long *n = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	int ret = -ENOMEM;
-	if (n) {
-		ret = seq_open(file, &slabstats_op);
-		if (!ret) {
-			struct seq_file *m = file->private_data;
-			*n = PAGE_SIZE / (2 * sizeof(unsigned long));
-			m->private = n;
-			n = NULL;
-		}
-		kfree(n);
-	}
-	return ret;
+	unsigned long *n;
+
+	n = __seq_open_private(file, &slabstats_op, PAGE_SIZE);
+	if (!n)
+		return -ENOMEM;
+
+	*n = PAGE_SIZE / (2 * sizeof(unsigned long));
+
+	return 0;
 }
 
 static const struct file_operations proc_slabstats_operations = {
diff --git a/mm/slab.h b/mm/slab.h
index 0e0fdd365840..ab019e63e3c2 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -4,6 +4,41 @@
  * Internal slab definitions
  */
 
+#ifdef CONFIG_SLOB
+/*
+ * Common fields provided in kmem_cache by all slab allocators
+ * This struct is either used directly by the allocator (SLOB)
+ * or the allocator must include definitions for all fields
+ * provided in kmem_cache_common in their definition of kmem_cache.
+ *
+ * Once we can do anonymous structs (C11 standard) we could put a
+ * anonymous struct definition in these allocators so that the
+ * separate allocations in the kmem_cache structure of SLAB and
+ * SLUB is no longer needed.
+ */
+struct kmem_cache {
+	unsigned int object_size;/* The original size of the object */
+	unsigned int size;	/* The aligned/padded/added on size  */
+	unsigned int align;	/* Alignment as calculated */
+	unsigned long flags;	/* Active flags on the slab */
+	const char *name;	/* Slab name for sysfs */
+	int refcount;		/* Use counter */
+	void (*ctor)(void *);	/* Called on object slot creation */
+	struct list_head list;	/* List of all slab caches on the system */
+};
+
+#endif /* CONFIG_SLOB */
+
+#ifdef CONFIG_SLAB
+#include <linux/slab_def.h>
+#endif
+
+#ifdef CONFIG_SLUB
+#include <linux/slub_def.h>
+#endif
+
+#include <linux/memcontrol.h>
+
 /*
  * State of the slab allocator.
  *
@@ -15,7 +50,6 @@
 enum slab_state {
 	DOWN,			/* No slab functionality yet */
 	PARTIAL,		/* SLUB: kmem_cache_node available */
-	PARTIAL_ARRAYCACHE,	/* SLAB: kmalloc size for arraycache available */
 	PARTIAL_NODE,		/* SLAB: kmalloc size for node struct available */
 	UP,			/* Slab caches usable but not all extras yet */
 	FULL			/* Everything is working */
@@ -53,15 +87,30 @@ extern void create_boot_cache(struct kmem_cache *, const char *name,
 			size_t size, unsigned long flags);
 
 struct mem_cgroup;
-#ifdef CONFIG_SLUB
+
+int slab_unmergeable(struct kmem_cache *s);
+struct kmem_cache *find_mergeable(size_t size, size_t align,
+		unsigned long flags, const char *name, void (*ctor)(void *));
+#ifndef CONFIG_SLOB
 struct kmem_cache *
 __kmem_cache_alias(const char *name, size_t size, size_t align,
 		   unsigned long flags, void (*ctor)(void *));
+
+unsigned long kmem_cache_flags(unsigned long object_size,
+	unsigned long flags, const char *name,
+	void (*ctor)(void *));
 #else
 static inline struct kmem_cache *
 __kmem_cache_alias(const char *name, size_t size, size_t align,
 		   unsigned long flags, void (*ctor)(void *))
 { return NULL; }
+
+static inline unsigned long kmem_cache_flags(unsigned long object_size,
+	unsigned long flags, const char *name,
+	void (*ctor)(void *))
+{
+	return flags;
+}
 #endif
 
 
@@ -303,8 +352,8 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
  * a kmem_cache_node structure allocated (which is true for all online nodes)
  */
 #define for_each_kmem_cache_node(__s, __node, __n) \
-	for (__node = 0; __n = get_node(__s, __node), __node < nr_node_ids; __node++) \
-		 if (__n)
+	for (__node = 0; __node < nr_node_ids; __node++) \
+		 if ((__n = get_node(__s, __node)))
 
 #endif
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index d319502b2403..3a6e0cfdf03a 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -30,6 +30,43 @@ LIST_HEAD(slab_caches);
 DEFINE_MUTEX(slab_mutex);
 struct kmem_cache *kmem_cache;
 
+/*
+ * Set of flags that will prevent slab merging
+ */
+#define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
+		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
+		SLAB_FAILSLAB)
+
+#define SLAB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
+		SLAB_CACHE_DMA | SLAB_NOTRACK)
+
+/*
+ * Merge control. If this is set then no merging of slab caches will occur.
+ * (Could be removed. This was introduced to pacify the merge skeptics.)
+ */
+static int slab_nomerge;
+
+static int __init setup_slab_nomerge(char *str)
+{
+	slab_nomerge = 1;
+	return 1;
+}
+
+#ifdef CONFIG_SLUB
+__setup_param("slub_nomerge", slub_nomerge, setup_slab_nomerge, 0);
+#endif
+
+__setup("slab_nomerge", setup_slab_nomerge);
+
+/*
+ * Determine the size of a slab object
+ */
+unsigned int kmem_cache_size(struct kmem_cache *s)
+{
+	return s->object_size;
+}
+EXPORT_SYMBOL(kmem_cache_size);
+
 #ifdef CONFIG_DEBUG_VM
 static int kmem_cache_sanity_check(const char *name, size_t size)
 {
@@ -79,6 +116,65 @@ static inline int kmem_cache_sanity_check(const char *name, size_t size)
 #endif
 
 #ifdef CONFIG_MEMCG_KMEM
+static int memcg_alloc_cache_params(struct mem_cgroup *memcg,
+		struct kmem_cache *s, struct kmem_cache *root_cache)
+{
+	size_t size;
+
+	if (!memcg_kmem_enabled())
+		return 0;
+
+	if (!memcg) {
+		size = offsetof(struct memcg_cache_params, memcg_caches);
+		size += memcg_limited_groups_array_size * sizeof(void *);
+	} else
+		size = sizeof(struct memcg_cache_params);
+
+	s->memcg_params = kzalloc(size, GFP_KERNEL);
+	if (!s->memcg_params)
+		return -ENOMEM;
+
+	if (memcg) {
+		s->memcg_params->memcg = memcg;
+		s->memcg_params->root_cache = root_cache;
+	} else
+		s->memcg_params->is_root_cache = true;
+
+	return 0;
+}
+
+static void memcg_free_cache_params(struct kmem_cache *s)
+{
+	kfree(s->memcg_params);
+}
+
+static int memcg_update_cache_params(struct kmem_cache *s, int num_memcgs)
+{
+	int size;
+	struct memcg_cache_params *new_params, *cur_params;
+
+	BUG_ON(!is_root_cache(s));
+
+	size = offsetof(struct memcg_cache_params, memcg_caches);
+	size += num_memcgs * sizeof(void *);
+
+	new_params = kzalloc(size, GFP_KERNEL);
+	if (!new_params)
+		return -ENOMEM;
+
+	cur_params = s->memcg_params;
+	memcpy(new_params->memcg_caches, cur_params->memcg_caches,
+	       memcg_limited_groups_array_size * sizeof(void *));
+
+	new_params->is_root_cache = true;
+
+	rcu_assign_pointer(s->memcg_params, new_params);
+	if (cur_params)
+		kfree_rcu(cur_params, rcu_head);
+
+	return 0;
+}
+
 int memcg_update_all_caches(int num_memcgs)
 {
 	struct kmem_cache *s;
@@ -89,9 +185,8 @@ int memcg_update_all_caches(int num_memcgs)
 		if (!is_root_cache(s))
 			continue;
 
-		ret = memcg_update_cache_size(s, num_memcgs);
+		ret = memcg_update_cache_params(s, num_memcgs);
 		/*
-		 * See comment in memcontrol.c, memcg_update_cache_size:
 		 * Instead of freeing the memory, we'll just leave the caches
 		 * up to this point in an updated state.
 		 */
@@ -104,7 +199,80 @@ out:
 	mutex_unlock(&slab_mutex);
 	return ret;
 }
-#endif
+#else
+static inline int memcg_alloc_cache_params(struct mem_cgroup *memcg,
+		struct kmem_cache *s, struct kmem_cache *root_cache)
+{
+	return 0;
+}
+
+static inline void memcg_free_cache_params(struct kmem_cache *s)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+/*
+ * Find a mergeable slab cache
+ */
+int slab_unmergeable(struct kmem_cache *s)
+{
+	if (slab_nomerge || (s->flags & SLAB_NEVER_MERGE))
+		return 1;
+
+	if (!is_root_cache(s))
+		return 1;
+
+	if (s->ctor)
+		return 1;
+
+	/*
+	 * We may have set a slab to be unmergeable during bootstrap.
+	 */
+	if (s->refcount < 0)
+		return 1;
+
+	return 0;
+}
+
+struct kmem_cache *find_mergeable(size_t size, size_t align,
+		unsigned long flags, const char *name, void (*ctor)(void *))
+{
+	struct kmem_cache *s;
+
+	if (slab_nomerge || (flags & SLAB_NEVER_MERGE))
+		return NULL;
+
+	if (ctor)
+		return NULL;
+
+	size = ALIGN(size, sizeof(void *));
+	align = calculate_alignment(flags, align, size);
+	size = ALIGN(size, align);
+	flags = kmem_cache_flags(size, flags, name, NULL);
+
+	list_for_each_entry(s, &slab_caches, list) {
+		if (slab_unmergeable(s))
+			continue;
+
+		if (size > s->size)
+			continue;
+
+		if ((flags & SLAB_MERGE_SAME) != (s->flags & SLAB_MERGE_SAME))
+			continue;
+		/*
+		 * Check if alignment is compatible.
+		 * Courtesy of Adrian Drzewiecki
+		 */
+		if ((s->size & ~(align - 1)) != s->size)
+			continue;
+
+		if (s->size - size >= sizeof(void *))
+			continue;
+
+		return s;
+	}
+	return NULL;
+}
 
 /*
  * Figure out what the alignment of the objects will be given a set of
@@ -211,8 +379,10 @@ kmem_cache_create(const char *name, size_t size, size_t align,
 	mutex_lock(&slab_mutex);
 
 	err = kmem_cache_sanity_check(name, size);
-	if (err)
+	if (err) {
+		s = NULL;	/* suppress uninit var warning */
 		goto out_unlock;
+	}
 
 	/*
 	 * Some allocators will constraint the set of valid flags to a subset
diff --git a/mm/slob.c b/mm/slob.c
index 21980e0f39a8..96a86206a26b 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -468,7 +468,6 @@ void *__kmalloc(size_t size, gfp_t gfp)
 }
 EXPORT_SYMBOL(__kmalloc);
 
-#ifdef CONFIG_TRACING
 void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller)
 {
 	return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, caller);
@@ -481,7 +480,6 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfp,
 	return __do_kmalloc_node(size, gfp, node, caller);
 }
 #endif
-#endif
 
 void kfree(const void *block)
 {
diff --git a/mm/slub.c b/mm/slub.c
index 3e8afcc07a76..ae7b9f1ad394 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -169,16 +169,6 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
  */
 #define DEBUG_METADATA_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
 
-/*
- * Set of flags that will prevent slab merging
- */
-#define SLUB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
-		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
-		SLAB_FAILSLAB)
-
-#define SLUB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
-		SLAB_CACHE_DMA | SLAB_NOTRACK)
-
 #define OO_SHIFT	16
 #define OO_MASK		((1 << OO_SHIFT) - 1)
 #define MAX_OBJS_PER_PAGE	32767 /* since page.objects is u15 */
@@ -1176,7 +1166,7 @@ out:
 
 __setup("slub_debug", setup_slub_debug);
 
-static unsigned long kmem_cache_flags(unsigned long object_size,
+unsigned long kmem_cache_flags(unsigned long object_size,
 	unsigned long flags, const char *name,
 	void (*ctor)(void *))
 {
@@ -1208,7 +1198,7 @@ static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
 					struct page *page) {}
 static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
 					struct page *page) {}
-static inline unsigned long kmem_cache_flags(unsigned long object_size,
+unsigned long kmem_cache_flags(unsigned long object_size,
 	unsigned long flags, const char *name,
 	void (*ctor)(void *))
 {
@@ -1699,7 +1689,12 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
 		struct kmem_cache_cpu *c)
 {
 	void *object;
-	int searchnode = (node == NUMA_NO_NODE) ? numa_mem_id() : node;
+	int searchnode = node;
+
+	if (node == NUMA_NO_NODE)
+		searchnode = numa_mem_id();
+	else if (!node_present_pages(node))
+		searchnode = node_to_mem_node(node);
 
 	object = get_partial_node(s, get_node(s, searchnode), c, flags);
 	if (object || node != NUMA_NO_NODE)
@@ -2280,11 +2275,18 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 redo:
 
 	if (unlikely(!node_match(page, node))) {
-		stat(s, ALLOC_NODE_MISMATCH);
-		deactivate_slab(s, page, c->freelist);
-		c->page = NULL;
-		c->freelist = NULL;
-		goto new_slab;
+		int searchnode = node;
+
+		if (node != NUMA_NO_NODE && !node_present_pages(node))
+			searchnode = node_to_mem_node(node);
+
+		if (unlikely(!node_match(page, searchnode))) {
+			stat(s, ALLOC_NODE_MISMATCH);
+			deactivate_slab(s, page, c->freelist);
+			c->page = NULL;
+			c->freelist = NULL;
+			goto new_slab;
+		}
 	}
 
 	/*
@@ -2707,12 +2709,6 @@ static int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
 static int slub_min_objects;
 
 /*
- * Merge control. If this is set then no merging of slab caches will occur.
- * (Could be removed. This was introduced to pacify the merge skeptics.)
- */
-static int slub_nomerge;
-
-/*
  * Calculate the order of allocation given an slab object size.
  *
  * The order of allocation has significant impact on performance and other
@@ -3240,14 +3236,6 @@ static int __init setup_slub_min_objects(char *str)
 
 __setup("slub_min_objects=", setup_slub_min_objects);
 
-static int __init setup_slub_nomerge(char *str)
-{
-	slub_nomerge = 1;
-	return 1;
-}
-
-__setup("slub_nomerge", setup_slub_nomerge);
-
 void *__kmalloc(size_t size, gfp_t flags)
 {
 	struct kmem_cache *s;
@@ -3625,69 +3613,6 @@ void __init kmem_cache_init_late(void)
 {
 }
 
-/*
- * Find a mergeable slab cache
- */
-static int slab_unmergeable(struct kmem_cache *s)
-{
-	if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE))
-		return 1;
-
-	if (!is_root_cache(s))
-		return 1;
-
-	if (s->ctor)
-		return 1;
-
-	/*
-	 * We may have set a slab to be unmergeable during bootstrap.
-	 */
-	if (s->refcount < 0)
-		return 1;
-
-	return 0;
-}
-
-static struct kmem_cache *find_mergeable(size_t size, size_t align,
-		unsigned long flags, const char *name, void (*ctor)(void *))
-{
-	struct kmem_cache *s;
-
-	if (slub_nomerge || (flags & SLUB_NEVER_MERGE))
-		return NULL;
-
-	if (ctor)
-		return NULL;
-
-	size = ALIGN(size, sizeof(void *));
-	align = calculate_alignment(flags, align, size);
-	size = ALIGN(size, align);
-	flags = kmem_cache_flags(size, flags, name, NULL);
-
-	list_for_each_entry(s, &slab_caches, list) {
-		if (slab_unmergeable(s))
-			continue;
-
-		if (size > s->size)
-			continue;
-
-		if ((flags & SLUB_MERGE_SAME) != (s->flags & SLUB_MERGE_SAME))
-			continue;
-		/*
-		 * Check if alignment is compatible.
-		 * Courtesy of Adrian Drzewiecki
-		 */
-		if ((s->size & ~(align - 1)) != s->size)
-			continue;
-
-		if (s->size - size >= sizeof(void *))
-			continue;
-
-		return s;
-	}
-	return NULL;
-}
-
 struct kmem_cache *
 __kmem_cache_alias(const char *name, size_t size, size_t align,
 		   unsigned long flags, void (*ctor)(void *))
@@ -4604,6 +4529,14 @@ static ssize_t trace_show(struct kmem_cache *s, char *buf)
 static ssize_t trace_store(struct kmem_cache *s, const char *buf,
 							size_t length)
 {
+	/*
+	 * Tracing a merged cache is going to give confusing results
+	 * as well as cause other issues like converting a mergeable
+	 * cache into an umergeable one.
+	 */
+	if (s->refcount > 1)
+		return -EINVAL;
+
 	s->flags &= ~SLAB_TRACE;
 	if (buf[0] == '1') {
 		s->flags &= ~__CMPXCHG_DOUBLE;
@@ -4721,6 +4654,9 @@ static ssize_t failslab_show(struct kmem_cache *s, char *buf)
 static ssize_t failslab_store(struct kmem_cache *s, const char *buf,
 							size_t length)
 {
+	if (s->refcount > 1)
+		return -EINVAL;
+
 	s->flags &= ~SLAB_FAILSLAB;
 	if (buf[0] == '1')
 		s->flags |= SLAB_FAILSLAB;
diff --git a/mm/swap.c b/mm/swap.c
index 6b2dc3897cd5..8a12b33936b4 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -887,18 +887,14 @@ void lru_add_drain_all(void)
 	mutex_unlock(&lock);
 }
 
-/*
- * Batched page_cache_release().  Decrement the reference count on all the
- * passed pages.  If it fell to zero then remove the page from the LRU and
- * free it.
- *
- * Avoid taking zone->lru_lock if possible, but if it is taken, retain it
- * for the remainder of the operation.
+/**
+ * release_pages - batched page_cache_release()
+ * @pages: array of pages to release
+ * @nr: number of pages
+ * @cold: whether the pages are cache cold
  *
- * The locking in this function is against shrink_inactive_list(): we recheck
- * the page count inside the lock to see whether shrink_inactive_list()
- * grabbed the page via the LRU.  If it did, give up: shrink_inactive_list()
- * will free it.
+ * Decrement the reference count on all the pages in @pages.  If it
+ * fell to zero, remove the page from the LRU and free it.
  */
 void release_pages(struct page **pages, int nr, bool cold)
 {
@@ -907,6 +903,7 @@ void release_pages(struct page **pages, int nr, bool cold)
 	struct zone *zone = NULL;
 	struct lruvec *lruvec;
 	unsigned long uninitialized_var(flags);
+	unsigned int uninitialized_var(lock_batch);
 
 	for (i = 0; i < nr; i++) {
 		struct page *page = pages[i];
@@ -920,6 +917,16 @@ void release_pages(struct page **pages, int nr, bool cold)
 			continue;
 		}
 
+		/*
+		 * Make sure the IRQ-safe lock-holding time does not get
+		 * excessive with a continuous string of pages from the
+		 * same zone. The lock is held only if zone != NULL.
+		 */
+		if (zone && ++lock_batch == SWAP_CLUSTER_MAX) {
+			spin_unlock_irqrestore(&zone->lru_lock, flags);
+			zone = NULL;
+		}
+
 		if (!put_page_testzero(page))
 			continue;
 
@@ -930,6 +937,7 @@ void release_pages(struct page **pages, int nr, bool cold)
 				if (zone)
 					spin_unlock_irqrestore(&zone->lru_lock,
 									flags);
+				lock_batch = 0;
 				zone = pagezone;
 				spin_lock_irqsave(&zone->lru_lock, flags);
 			}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 3e0ec83d000c..154444918685 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -28,7 +28,9 @@
 static const struct address_space_operations swap_aops = {
 	.writepage	= swap_writepage,
 	.set_page_dirty	= swap_set_page_dirty,
+#ifdef CONFIG_MIGRATION
 	.migratepage	= migrate_page,
+#endif
 };
 
 static struct backing_dev_info swap_backing_dev_info = {
@@ -263,18 +265,12 @@ void free_page_and_swap_cache(struct page *page)
 void free_pages_and_swap_cache(struct page **pages, int nr)
 {
 	struct page **pagep = pages;
+	int i;
 
 	lru_add_drain();
-	while (nr) {
-		int todo = min(nr, PAGEVEC_SIZE);
-		int i;
-
-		for (i = 0; i < todo; i++)
-			free_swap_cache(pagep[i]);
-		release_pages(pagep, todo, false);
-		pagep += todo;
-		nr -= todo;
-	}
+	for (i = 0; i < nr; i++)
+		free_swap_cache(pagep[i]);
+	release_pages(pagep, nr, false);
 }
 
 /*
diff --git a/mm/util.c b/mm/util.c
index 093c973f1697..fec39d4509a9 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -170,32 +170,25 @@ static int vm_is_stack_for_task(struct task_struct *t,
 /*
  * Check if the vma is being used as a stack.
  * If is_group is non-zero, check in the entire thread group or else
- * just check in the current task. Returns the pid of the task that
- * the vma is stack for.
+ * just check in the current task. Returns the task_struct of the task
+ * that the vma is stack for. Must be called under rcu_read_lock().
  */
-pid_t vm_is_stack(struct task_struct *task,
-		  struct vm_area_struct *vma, int in_group)
+struct task_struct *task_of_stack(struct task_struct *task,
+				struct vm_area_struct *vma, bool in_group)
 {
-	pid_t ret = 0;
-
 	if (vm_is_stack_for_task(task, vma))
-		return task->pid;
+		return task;
 
 	if (in_group) {
 		struct task_struct *t;
 
-		rcu_read_lock();
 		for_each_thread(task, t) {
-			if (vm_is_stack_for_task(t, vma)) {
-				ret = t->pid;
-				goto done;
-			}
+			if (vm_is_stack_for_task(t, vma))
+				return t;
 		}
-done:
-		rcu_read_unlock();
 	}
 
-	return ret;
+	return NULL;
 }
 
 #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 2b0aa5486092..90520af7f186 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2646,21 +2646,11 @@ static const struct seq_operations vmalloc_op = {
 
 static int vmalloc_open(struct inode *inode, struct file *file)
 {
-	unsigned int *ptr = NULL;
-	int ret;
-
-	if (IS_ENABLED(CONFIG_NUMA)) {
-		ptr = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
-		if (ptr == NULL)
-			return -ENOMEM;
-	}
-	ret = seq_open(file, &vmalloc_op);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-		m->private = ptr;
-	} else
-		kfree(ptr);
-	return ret;
+	if (IS_ENABLED(CONFIG_NUMA))
+		return seq_open_private(file, &vmalloc_op,
+					nr_node_ids * sizeof(unsigned int));
+	else
+		return seq_open(file, &vmalloc_op);
 }
 
 static const struct file_operations proc_vmalloc_operations = {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2836b5373b2e..dcb47074ae03 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -920,7 +920,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			/* Case 1 above */
 			if (current_is_kswapd() &&
 			    PageReclaim(page) &&
-			    zone_is_reclaim_writeback(zone)) {
+			    test_bit(ZONE_WRITEBACK, &zone->flags)) {
 				nr_immediate++;
 				goto keep_locked;
 
@@ -1002,7 +1002,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			 */
 			if (page_is_file_cache(page) &&
 					(!current_is_kswapd() ||
-					 !zone_is_reclaim_dirty(zone))) {
+					 !test_bit(ZONE_DIRTY, &zone->flags))) {
 				/*
 				 * Immediately reclaim when written back.
 				 * Similar in principal to deactivate_page()
@@ -1563,7 +1563,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	 * are encountered in the nr_immediate check below.
 	 */
 	if (nr_writeback && nr_writeback == nr_taken)
-		zone_set_flag(zone, ZONE_WRITEBACK);
+		set_bit(ZONE_WRITEBACK, &zone->flags);
 
 	/*
 	 * memcg will stall in page writeback so only consider forcibly
@@ -1575,16 +1575,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		 * backed by a congested BDI and wait_iff_congested will stall.
 		 */
 		if (nr_dirty && nr_dirty == nr_congested)
-			zone_set_flag(zone, ZONE_CONGESTED);
+			set_bit(ZONE_CONGESTED, &zone->flags);
 
 		/*
 		 * If dirty pages are scanned that are not queued for IO, it
 		 * implies that flushers are not keeping up. In this case, flag
-		 * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing
-		 * pages from reclaim context.
+		 * the zone ZONE_DIRTY and kswapd will start writing pages from
+		 * reclaim context.
 		 */
 		if (nr_unqueued_dirty == nr_taken)
-			zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
+			set_bit(ZONE_DIRTY, &zone->flags);
 
 		/*
 		 * If kswapd scans pages marked marked for immediate
@@ -2315,7 +2315,10 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc)
 	return reclaimable;
 }
 
-/* Returns true if compaction should go ahead for a high-order request */
+/*
+ * Returns true if compaction should go ahead for a high-order request, or
+ * the high-order allocation would succeed without compaction.
+ */
 static inline bool compaction_ready(struct zone *zone, int order)
 {
 	unsigned long balance_gap, watermark;
@@ -2339,8 +2342,11 @@ static inline bool compaction_ready(struct zone *zone, int order)
 	if (compaction_deferred(zone, order))
 		return watermark_ok;
 
-	/* If compaction is not ready to start, keep reclaiming */
-	if (!compaction_suitable(zone, order))
+	/*
+	 * If compaction is not ready to start and allocation is not likely
+	 * to succeed without it, then keep reclaiming.
+	 */
+	if (compaction_suitable(zone, order) == COMPACT_SKIPPED)
 		return false;
 
 	return watermark_ok;
@@ -2753,21 +2759,22 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 }
 
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
+					   unsigned long nr_pages,
 					   gfp_t gfp_mask,
-					   bool noswap)
+					   bool may_swap)
 {
 	struct zonelist *zonelist;
 	unsigned long nr_reclaimed;
 	int nid;
 	struct scan_control sc = {
-		.nr_to_reclaim = SWAP_CLUSTER_MAX,
+		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
 		.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 				(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
 		.target_mem_cgroup = memcg,
 		.priority = DEF_PRIORITY,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
-		.may_swap = !noswap,
+		.may_swap = may_swap,
 	};
 
 	/*
@@ -2818,7 +2825,7 @@ static bool zone_balanced(struct zone *zone, int order,
 		return false;
 
 	if (IS_ENABLED(CONFIG_COMPACTION) && order &&
-	    !compaction_suitable(zone, order))
+	    compaction_suitable(zone, order) == COMPACT_SKIPPED)
 		return false;
 
 	return true;
@@ -2978,7 +2985,7 @@ static bool kswapd_shrink_zone(struct zone *zone,
 	/* Account for the number of pages attempted to reclaim */
 	*nr_attempted += sc->nr_to_reclaim;
 
-	zone_clear_flag(zone, ZONE_WRITEBACK);
+	clear_bit(ZONE_WRITEBACK, &zone->flags);
 
 	/*
 	 * If a zone reaches its high watermark, consider it to be no longer
@@ -2988,8 +2995,8 @@ static bool kswapd_shrink_zone(struct zone *zone,
 	 */
 	if (zone_reclaimable(zone) &&
 	    zone_balanced(zone, testorder, 0, classzone_idx)) {
-		zone_clear_flag(zone, ZONE_CONGESTED);
-		zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
+		clear_bit(ZONE_CONGESTED, &zone->flags);
+		clear_bit(ZONE_DIRTY, &zone->flags);
 	}
 
 	return sc->nr_scanned >= sc->nr_to_reclaim;
@@ -3080,8 +3087,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 				 * If balanced, clear the dirty and congested
 				 * flags
 				 */
-				zone_clear_flag(zone, ZONE_CONGESTED);
-				zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
+				clear_bit(ZONE_CONGESTED, &zone->flags);
+				clear_bit(ZONE_DIRTY, &zone->flags);
 			}
 		}
 
@@ -3708,11 +3715,11 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	if (node_state(node_id, N_CPU) && node_id != numa_node_id())
 		return ZONE_RECLAIM_NOSCAN;
 
-	if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
+	if (test_and_set_bit(ZONE_RECLAIM_LOCKED, &zone->flags))
 		return ZONE_RECLAIM_NOSCAN;
 
 	ret = __zone_reclaim(zone, gfp_mask, order);
-	zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);
+	clear_bit(ZONE_RECLAIM_LOCKED, &zone->flags);
 
 	if (!ret)
 		count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
@@ -3791,66 +3798,3 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages)
 	}
 }
 #endif /* CONFIG_SHMEM */
-
-static void warn_scan_unevictable_pages(void)
-{
-	printk_once(KERN_WARNING
-		    "%s: The scan_unevictable_pages sysctl/node-interface has been "
-		    "disabled for lack of a legitimate use case.  If you have "
-		    "one, please send an email to linux-mm@kvack.org.\n",
-		    current->comm);
-}
-
-/*
- * scan_unevictable_pages [vm] sysctl handler.  On demand re-scan of
- * all nodes' unevictable lists for evictable pages
- */
-unsigned long scan_unevictable_pages;
-
-int scan_unevictable_handler(struct ctl_table *table, int write,
-			   void __user *buffer,
-			   size_t *length, loff_t *ppos)
-{
-	warn_scan_unevictable_pages();
-	proc_doulongvec_minmax(table, write, buffer, length, ppos);
-	scan_unevictable_pages = 0;
-	return 0;
-}
-
-#ifdef CONFIG_NUMA
-/*
- * per node 'scan_unevictable_pages' attribute.  On demand re-scan of
- * a specified node's per zone unevictable lists for evictable pages.
- */
-
-static ssize_t read_scan_unevictable_node(struct device *dev,
-					  struct device_attribute *attr,
-					  char *buf)
-{
-	warn_scan_unevictable_pages();
-	return sprintf(buf, "0\n");	/* always zero; should fit... */
-}
-
-static ssize_t write_scan_unevictable_node(struct device *dev,
-					   struct device_attribute *attr,
-					const char *buf, size_t count)
-{
-	warn_scan_unevictable_pages();
-	return 1;
-}
-
-
-static DEVICE_ATTR(scan_unevictable_pages, S_IRUGO | S_IWUSR,
-			read_scan_unevictable_node,
-			write_scan_unevictable_node);
-
-int scan_unevictable_register_node(struct node *node)
-{
-	return device_create_file(&node->dev, &dev_attr_scan_unevictable_pages);
-}
-
-void scan_unevictable_unregister_node(struct node *node)
-{
-	device_remove_file(&node->dev, &dev_attr_scan_unevictable_pages);
-}
-#endif
diff --git a/mm/vmstat.c b/mm/vmstat.c
index e9ab104b956f..1b12d390dc68 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -7,6 +7,7 @@
  *  zoned VM statistics
  *  Copyright (C) 2006 Silicon Graphics, Inc.,
  *		Christoph Lameter <christoph@lameter.com>
+ *  Copyright (C) 2008-2014 Christoph Lameter
  */
 #include <linux/fs.h>
 #include <linux/mm.h>
@@ -14,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/cpumask.h>
 #include <linux/vmstat.h>
 #include <linux/sched.h>
 #include <linux/math64.h>
@@ -419,13 +421,22 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item)
 EXPORT_SYMBOL(dec_zone_page_state);
 #endif
 
-static inline void fold_diff(int *diff)
+
+/*
+ * Fold a differential into the global counters.
+ * Returns the number of counters updated.
+ */
+static int fold_diff(int *diff)
 {
 	int i;
+	int changes = 0;
 
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-		if (diff[i])
+		if (diff[i]) {
 			atomic_long_add(diff[i], &vm_stat[i]);
+			changes++;
+	}
+	return changes;
 }
 
 /*
@@ -441,12 +452,15 @@ static inline void fold_diff(int *diff)
  * statistics in the remote zone struct as well as the global cachelines
  * with the global counters. These could cause remote node cache line
  * bouncing and will have to be only done when necessary.
+ *
+ * The function returns the number of global counters updated.
  */
-static void refresh_cpu_vm_stats(void)
+static int refresh_cpu_vm_stats(void)
 {
 	struct zone *zone;
 	int i;
 	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+	int changes = 0;
 
 	for_each_populated_zone(zone) {
 		struct per_cpu_pageset __percpu *p = zone->pageset;
@@ -486,15 +500,17 @@ static void refresh_cpu_vm_stats(void)
 			continue;
 		}
 
-
 		if (__this_cpu_dec_return(p->expire))
 			continue;
 
-		if (__this_cpu_read(p->pcp.count))
+		if (__this_cpu_read(p->pcp.count)) {
 			drain_zone_pages(zone, this_cpu_ptr(&p->pcp));
+			changes++;
+		}
 #endif
 	}
-	fold_diff(global_diff);
+	changes += fold_diff(global_diff);
+	return changes;
 }
 
 /*
@@ -735,7 +751,7 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
 					TEXT_FOR_HIGHMEM(xx) xx "_movable",
 
 const char * const vmstat_text[] = {
-	/* Zoned VM counters */
+	/* enum zone_stat_item countes */
 	"nr_free_pages",
 	"nr_alloc_batch",
 	"nr_inactive_anon",
@@ -778,10 +794,13 @@ const char * const vmstat_text[] = {
 	"workingset_nodereclaim",
 	"nr_anon_transparent_hugepages",
 	"nr_free_cma",
+
+	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
 	"nr_dirty_background_threshold",
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
+	/* enum vm_event_item counters */
 	"pgpgin",
 	"pgpgout",
 	"pswpin",
@@ -860,6 +879,13 @@ const char * const vmstat_text[] = {
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif
+#ifdef CONFIG_MEMORY_BALLOON
+	"balloon_inflate",
+	"balloon_deflate",
+#ifdef CONFIG_BALLOON_COMPACTION
+	"balloon_migrate",
+#endif
+#endif /* CONFIG_MEMORY_BALLOON */
 #ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
@@ -1229,20 +1255,108 @@ static const struct file_operations proc_vmstat_file_operations = {
 #ifdef CONFIG_SMP
 static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
 int sysctl_stat_interval __read_mostly = HZ;
+static cpumask_var_t cpu_stat_off;
 
 static void vmstat_update(struct work_struct *w)
 {
-	refresh_cpu_vm_stats();
-	schedule_delayed_work(this_cpu_ptr(&vmstat_work),
+	if (refresh_cpu_vm_stats())
+		/*
+		 * Counters were updated so we expect more updates
+		 * to occur in the future. Keep on running the
+		 * update worker thread.
+		 */
+		schedule_delayed_work(this_cpu_ptr(&vmstat_work),
+			round_jiffies_relative(sysctl_stat_interval));
+	else {
+		/*
+		 * We did not update any counters so the app may be in
+		 * a mode where it does not cause counter updates.
+		 * We may be uselessly running vmstat_update.
+		 * Defer the checking for differentials to the
+		 * shepherd thread on a different processor.
+		 */
+		int r;
+		/*
+		 * Shepherd work thread does not race since it never
+		 * changes the bit if its zero but the cpu
+		 * online / off line code may race if
+		 * worker threads are still allowed during
+		 * shutdown / startup.
+		 */
+		r = cpumask_test_and_set_cpu(smp_processor_id(),
+			cpu_stat_off);
+		VM_BUG_ON(r);
+	}
+}
+
+/*
+ * Check if the diffs for a certain cpu indicate that
+ * an update is needed.
+ */
+static bool need_update(int cpu)
+{
+	struct zone *zone;
+
+	for_each_populated_zone(zone) {
+		struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu);
+
+		BUILD_BUG_ON(sizeof(p->vm_stat_diff[0]) != 1);
+		/*
+		 * The fast way of checking if there are any vmstat diffs.
+		 * This works because the diffs are byte sized items.
+		 */
+		if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS))
+			return true;
+
+	}
+	return false;
+}
+
+
+/*
+ * Shepherd worker thread that checks the
+ * differentials of processors that have their worker
+ * threads for vm statistics updates disabled because of
+ * inactivity.
+ */
+static void vmstat_shepherd(struct work_struct *w);
+
+static DECLARE_DELAYED_WORK(shepherd, vmstat_shepherd);
+
+static void vmstat_shepherd(struct work_struct *w)
+{
+	int cpu;
+
+	get_online_cpus();
+	/* Check processors whose vmstat worker threads have been disabled */
+	for_each_cpu(cpu, cpu_stat_off)
+		if (need_update(cpu) &&
+			cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
+
+			schedule_delayed_work_on(cpu, &per_cpu(vmstat_work, cpu),
+				__round_jiffies_relative(sysctl_stat_interval, cpu));
+
+	put_online_cpus();
+
+	schedule_delayed_work(&shepherd,
 		round_jiffies_relative(sysctl_stat_interval));
+
 }
 
-static void start_cpu_timer(int cpu)
+static void __init start_shepherd_timer(void)
 {
-	struct delayed_work *work = &per_cpu(vmstat_work, cpu);
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
+			vmstat_update);
+
+	if (!alloc_cpumask_var(&cpu_stat_off, GFP_KERNEL))
+		BUG();
+	cpumask_copy(cpu_stat_off, cpu_online_mask);
 
-	INIT_DEFERRABLE_WORK(work, vmstat_update);
-	schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
+	schedule_delayed_work(&shepherd,
+		round_jiffies_relative(sysctl_stat_interval));
 }
 
 static void vmstat_cpu_dead(int node)
@@ -1273,17 +1387,17 @@ static int vmstat_cpuup_callback(struct notifier_block *nfb,
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
 		refresh_zone_stat_thresholds();
-		start_cpu_timer(cpu);
 		node_set_state(cpu_to_node(cpu), N_CPU);
+		cpumask_set_cpu(cpu, cpu_stat_off);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
 		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
-		per_cpu(vmstat_work, cpu).work.func = NULL;
+		cpumask_clear_cpu(cpu, cpu_stat_off);
 		break;
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
-		start_cpu_timer(cpu);
+		cpumask_set_cpu(cpu, cpu_stat_off);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
@@ -1303,15 +1417,10 @@ static struct notifier_block vmstat_notifier =
 static int __init setup_vmstat(void)
 {
 #ifdef CONFIG_SMP
-	int cpu;
-
 	cpu_notifier_register_begin();
 	__register_cpu_notifier(&vmstat_notifier);
 
-	for_each_online_cpu(cpu) {
-		start_cpu_timer(cpu);
-		node_set_state(cpu_to_node(cpu), N_CPU);
-	}
+	start_shepherd_timer();
 	cpu_notifier_register_done();
 #endif
 #ifdef CONFIG_PROC_FS
diff --git a/mm/zbud.c b/mm/zbud.c
index f26e7fcc7fa2..ecf1dbef6983 100644
--- a/mm/zbud.c
+++ b/mm/zbud.c
@@ -60,15 +60,17 @@
  * NCHUNKS_ORDER determines the internal allocation granularity, effectively
  * adjusting internal fragmentation.  It also determines the number of
  * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the
- * allocation granularity will be in chunks of size PAGE_SIZE/64, and there
- * will be 64 freelists per pool.
+ * allocation granularity will be in chunks of size PAGE_SIZE/64. As one chunk
+ * in allocated page is occupied by zbud header, NCHUNKS will be calculated to
+ * 63 which shows the max number of free chunks in zbud page, also there will be
+ * 63 freelists per pool.
  */
 #define NCHUNKS_ORDER	6
 
 #define CHUNK_SHIFT	(PAGE_SHIFT - NCHUNKS_ORDER)
 #define CHUNK_SIZE	(1 << CHUNK_SHIFT)
-#define NCHUNKS		(PAGE_SIZE >> CHUNK_SHIFT)
 #define ZHDR_SIZE_ALIGNED CHUNK_SIZE
+#define NCHUNKS		((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT)
 
 /**
  * struct zbud_pool - stores metadata for each zbud pool
@@ -268,10 +270,9 @@ static int num_free_chunks(struct zbud_header *zhdr)
 {
 	/*
 	 * Rather than branch for different situations, just use the fact that
-	 * free buddies have a length of zero to simplify everything. -1 at the
-	 * end for the zbud header.
+	 * free buddies have a length of zero to simplify everything.
 	 */
-	return NCHUNKS - zhdr->first_chunks - zhdr->last_chunks - 1;
+	return NCHUNKS - zhdr->first_chunks - zhdr->last_chunks;
 }
 
 /*****************
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 94f38fac5e81..839a48c3ca27 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -175,7 +175,7 @@ enum fullness_group {
  *	n <= N / f, where
  * n = number of allocated objects
  * N = total number of objects zspage can store
- * f = 1/fullness_threshold_frac
+ * f = fullness_threshold_frac
  *
  * Similarly, we assign zspage to:
  *	ZS_ALMOST_FULL	when n > N / f
@@ -199,9 +199,6 @@ struct size_class {
 
 	spinlock_t lock;
 
-	/* stats */
-	u64 pages_allocated;
-
 	struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS];
 };
 
@@ -220,6 +217,7 @@ struct zs_pool {
 	struct size_class size_class[ZS_SIZE_CLASSES];
 
 	gfp_t flags;	/* allocation flags used when growing pool */
+	atomic_long_t pages_allocated;
 };
 
 /*
@@ -299,7 +297,7 @@ static void zs_zpool_unmap(void *pool, unsigned long handle)
 
 static u64 zs_zpool_total_size(void *pool)
 {
-	return zs_get_total_size_bytes(pool);
+	return zs_get_total_pages(pool) << PAGE_SHIFT;
 }
 
 static struct zpool_driver zs_zpool_driver = {
@@ -630,7 +628,7 @@ static void init_zspage(struct page *first_page, struct size_class *class)
 	while (page) {
 		struct page *next_page;
 		struct link_free *link;
-		unsigned int i, objs_on_page;
+		unsigned int i = 1;
 
 		/*
 		 * page->index stores offset of first object starting
@@ -643,14 +641,10 @@ static void init_zspage(struct page *first_page, struct size_class *class)
 
 		link = (struct link_free *)kmap_atomic(page) +
 						off / sizeof(*link);
-		objs_on_page = (PAGE_SIZE - off) / class->size;
 
-		for (i = 1; i <= objs_on_page; i++) {
-			off += class->size;
-			if (off < PAGE_SIZE) {
-				link->next = obj_location_to_handle(page, i);
-				link += class->size / sizeof(*link);
-			}
+		while ((off += class->size) < PAGE_SIZE) {
+			link->next = obj_location_to_handle(page, i++);
+			link += class->size / sizeof(*link);
 		}
 
 		/*
@@ -662,7 +656,7 @@ static void init_zspage(struct page *first_page, struct size_class *class)
 		link->next = obj_location_to_handle(next_page, 0);
 		kunmap_atomic(link);
 		page = next_page;
-		off = (off + class->size) % PAGE_SIZE;
+		off %= PAGE_SIZE;
 	}
 }
 
@@ -1028,8 +1022,9 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
 			return 0;
 
 		set_zspage_mapping(first_page, class->index, ZS_EMPTY);
+		atomic_long_add(class->pages_per_zspage,
+					&pool->pages_allocated);
 		spin_lock(&class->lock);
-		class->pages_allocated += class->pages_per_zspage;
 	}
 
 	obj = (unsigned long)first_page->freelist;
@@ -1082,14 +1077,13 @@ void zs_free(struct zs_pool *pool, unsigned long obj)
 
 	first_page->inuse--;
 	fullness = fix_fullness_group(pool, first_page);
-
-	if (fullness == ZS_EMPTY)
-		class->pages_allocated -= class->pages_per_zspage;
-
 	spin_unlock(&class->lock);
 
-	if (fullness == ZS_EMPTY)
+	if (fullness == ZS_EMPTY) {
+		atomic_long_sub(class->pages_per_zspage,
+				&pool->pages_allocated);
 		free_zspage(first_page);
+	}
 }
 EXPORT_SYMBOL_GPL(zs_free);
 
@@ -1183,17 +1177,11 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 }
 EXPORT_SYMBOL_GPL(zs_unmap_object);
 
-u64 zs_get_total_size_bytes(struct zs_pool *pool)
+unsigned long zs_get_total_pages(struct zs_pool *pool)
 {
-	int i;
-	u64 npages = 0;
-
-	for (i = 0; i < ZS_SIZE_CLASSES; i++)
-		npages += pool->size_class[i].pages_allocated;
-
-	return npages << PAGE_SHIFT;
+	return atomic_long_read(&pool->pages_allocated);
 }
-EXPORT_SYMBOL_GPL(zs_get_total_size_bytes);
+EXPORT_SYMBOL_GPL(zs_get_total_pages);
 
 module_init(zs_init);
 module_exit(zs_exit);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 6940d8fe8971..daa749c8b3fb 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -575,6 +575,8 @@ static int p9_virtio_probe(struct virtio_device *vdev)
 	/* Ceiling limit to avoid denial of service attacks */
 	chan->p9_max_pages = nr_free_buffer_pages()/4;
 
+	virtio_device_ready(vdev);
+
 	mutex_lock(&virtio_9p_lock);
 	list_add_tail(&chan->chan_list, &virtio_chan_list);
 	mutex_unlock(&virtio_9p_lock);
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index 6f5e621f220a..88a1bc3804d1 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -44,10 +44,10 @@ static bool batadv_parse_gw_bandwidth(struct net_device *net_dev, char *buff,
 	if (strlen(buff) > 4) {
 		tmp_ptr = buff + strlen(buff) - 4;
 
-		if (strnicmp(tmp_ptr, "mbit", 4) == 0)
+		if (strncasecmp(tmp_ptr, "mbit", 4) == 0)
 			bw_unit_type = BATADV_BW_UNIT_MBIT;
 
-		if ((strnicmp(tmp_ptr, "kbit", 4) == 0) ||
+		if ((strncasecmp(tmp_ptr, "kbit", 4) == 0) ||
 		    (bw_unit_type == BATADV_BW_UNIT_MBIT))
 			*tmp_ptr = '\0';
 	}
@@ -77,10 +77,10 @@ static bool batadv_parse_gw_bandwidth(struct net_device *net_dev, char *buff,
 		if (strlen(slash_ptr + 1) > 4) {
 			tmp_ptr = slash_ptr + 1 - 4 + strlen(slash_ptr + 1);
 
-			if (strnicmp(tmp_ptr, "mbit", 4) == 0)
+			if (strncasecmp(tmp_ptr, "mbit", 4) == 0)
 				bw_unit_type = BATADV_BW_UNIT_MBIT;
 
-			if ((strnicmp(tmp_ptr, "kbit", 4) == 0) ||
+			if ((strncasecmp(tmp_ptr, "kbit", 4) == 0) ||
 			    (bw_unit_type == BATADV_BW_UNIT_MBIT))
 				*tmp_ptr = '\0';
 		}
diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig
index e50cc69ae8ca..f8cceb99e732 100644
--- a/net/ceph/Kconfig
+++ b/net/ceph/Kconfig
@@ -3,6 +3,7 @@ config CEPH_LIB
 	depends on INET
 	select LIBCRC32C
 	select CRYPTO_AES
+	select CRYPTO_CBC
 	select CRYPTO
 	select KEYS
 	default n
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 1675021d8c12..58fbfe134f93 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -293,17 +293,20 @@ static int get_secret(struct ceph_crypto_key *dst, const char *name) {
 		key_err = PTR_ERR(ukey);
 		switch (key_err) {
 		case -ENOKEY:
-			pr_warning("ceph: Mount failed due to key not found: %s\n", name);
+			pr_warn("ceph: Mount failed due to key not found: %s\n",
+				name);
 			break;
 		case -EKEYEXPIRED:
-			pr_warning("ceph: Mount failed due to expired key: %s\n", name);
+			pr_warn("ceph: Mount failed due to expired key: %s\n",
+				name);
 			break;
 		case -EKEYREVOKED:
-			pr_warning("ceph: Mount failed due to revoked key: %s\n", name);
+			pr_warn("ceph: Mount failed due to revoked key: %s\n",
+				name);
 			break;
 		default:
-			pr_warning("ceph: Mount failed due to unknown key error"
-			       " %d: %s\n", key_err, name);
+			pr_warn("ceph: Mount failed due to unknown key error %d: %s\n",
+				key_err, name);
 		}
 		err = -EPERM;
 		goto out;
@@ -433,7 +436,7 @@ ceph_parse_options(char *options, const char *dev_name,
 
 			/* misc */
 		case Opt_osdtimeout:
-			pr_warning("ignoring deprecated osdtimeout option\n");
+			pr_warn("ignoring deprecated osdtimeout option\n");
 			break;
 		case Opt_osdkeepalivetimeout:
 			opt->osd_keepalive_timeout = intval;
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
index 1348df96fe15..30560202f57b 100644
--- a/net/ceph/ceph_strings.c
+++ b/net/ceph/ceph_strings.c
@@ -19,77 +19,12 @@ const char *ceph_entity_type_name(int type)
 const char *ceph_osd_op_name(int op)
 {
 	switch (op) {
-	case CEPH_OSD_OP_READ: return "read";
-	case CEPH_OSD_OP_STAT: return "stat";
-	case CEPH_OSD_OP_MAPEXT: return "mapext";
-	case CEPH_OSD_OP_SPARSE_READ: return "sparse-read";
-	case CEPH_OSD_OP_NOTIFY: return "notify";
-	case CEPH_OSD_OP_NOTIFY_ACK: return "notify-ack";
-	case CEPH_OSD_OP_ASSERT_VER: return "assert-version";
-
-	case CEPH_OSD_OP_MASKTRUNC: return "masktrunc";
-
-	case CEPH_OSD_OP_CREATE: return "create";
-	case CEPH_OSD_OP_WRITE: return "write";
-	case CEPH_OSD_OP_DELETE: return "delete";
-	case CEPH_OSD_OP_TRUNCATE: return "truncate";
-	case CEPH_OSD_OP_ZERO: return "zero";
-	case CEPH_OSD_OP_WRITEFULL: return "writefull";
-	case CEPH_OSD_OP_ROLLBACK: return "rollback";
-
-	case CEPH_OSD_OP_APPEND: return "append";
-	case CEPH_OSD_OP_STARTSYNC: return "startsync";
-	case CEPH_OSD_OP_SETTRUNC: return "settrunc";
-	case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc";
-
-	case CEPH_OSD_OP_TMAPUP: return "tmapup";
-	case CEPH_OSD_OP_TMAPGET: return "tmapget";
-	case CEPH_OSD_OP_TMAPPUT: return "tmapput";
-	case CEPH_OSD_OP_WATCH: return "watch";
-
-	case CEPH_OSD_OP_CLONERANGE: return "clonerange";
-	case CEPH_OSD_OP_ASSERT_SRC_VERSION: return "assert-src-version";
-	case CEPH_OSD_OP_SRC_CMPXATTR: return "src-cmpxattr";
-
-	case CEPH_OSD_OP_GETXATTR: return "getxattr";
-	case CEPH_OSD_OP_GETXATTRS: return "getxattrs";
-	case CEPH_OSD_OP_SETXATTR: return "setxattr";
-	case CEPH_OSD_OP_SETXATTRS: return "setxattrs";
-	case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs";
-	case CEPH_OSD_OP_RMXATTR: return "rmxattr";
-	case CEPH_OSD_OP_CMPXATTR: return "cmpxattr";
-
-	case CEPH_OSD_OP_PULL: return "pull";
-	case CEPH_OSD_OP_PUSH: return "push";
-	case CEPH_OSD_OP_BALANCEREADS: return "balance-reads";
-	case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads";
-	case CEPH_OSD_OP_SCRUB: return "scrub";
-	case CEPH_OSD_OP_SCRUB_RESERVE: return "scrub-reserve";
-	case CEPH_OSD_OP_SCRUB_UNRESERVE: return "scrub-unreserve";
-	case CEPH_OSD_OP_SCRUB_STOP: return "scrub-stop";
-	case CEPH_OSD_OP_SCRUB_MAP: return "scrub-map";
-
-	case CEPH_OSD_OP_WRLOCK: return "wrlock";
-	case CEPH_OSD_OP_WRUNLOCK: return "wrunlock";
-	case CEPH_OSD_OP_RDLOCK: return "rdlock";
-	case CEPH_OSD_OP_RDUNLOCK: return "rdunlock";
-	case CEPH_OSD_OP_UPLOCK: return "uplock";
-	case CEPH_OSD_OP_DNLOCK: return "dnlock";
-
-	case CEPH_OSD_OP_CALL: return "call";
-
-	case CEPH_OSD_OP_PGLS: return "pgls";
-	case CEPH_OSD_OP_PGLS_FILTER: return "pgls-filter";
-	case CEPH_OSD_OP_OMAPGETKEYS: return "omap-get-keys";
-	case CEPH_OSD_OP_OMAPGETVALS: return "omap-get-vals";
-	case CEPH_OSD_OP_OMAPGETHEADER: return "omap-get-header";
-	case CEPH_OSD_OP_OMAPGETVALSBYKEYS: return "omap-get-vals-by-keys";
-	case CEPH_OSD_OP_OMAPSETVALS: return "omap-set-vals";
-	case CEPH_OSD_OP_OMAPSETHEADER: return "omap-set-header";
-	case CEPH_OSD_OP_OMAPCLEAR: return "omap-clear";
-	case CEPH_OSD_OP_OMAPRMKEYS: return "omap-rm-keys";
+#define GENERATE_CASE(op, opcode, str)	case CEPH_OSD_OP_##op: return (str);
+__CEPH_FORALL_OSD_OPS(GENERATE_CASE)
+#undef GENERATE_CASE
+	default:
+		return "???";
 	}
-	return "???";
 }
 
 const char *ceph_osd_state_name(int s)
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index ffeba8f9dda9..62fc5e7a9acf 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -476,7 +476,6 @@ struct key_type key_type_ceph = {
 	.preparse	= ceph_key_preparse,
 	.free_preparse	= ceph_key_free_preparse,
 	.instantiate	= generic_key_instantiate,
-	.match		= user_match,
 	.destroy	= ceph_key_destroy,
 };
 
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index d1a62c69a9f4..d2d525529f87 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -169,7 +169,8 @@ static int osdc_show(struct seq_file *s, void *pp)
 
 		for (i = 0; i < req->r_num_ops; i++) {
 			opcode = req->r_ops[i].op;
-			seq_printf(s, "\t%s", ceph_osd_op_name(opcode));
+			seq_printf(s, "%s%s", (i == 0 ? "\t" : ","),
+				   ceph_osd_op_name(opcode));
 		}
 
 		seq_printf(s, "\n");
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index b2f571dd933d..559c9f619c20 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -292,7 +292,11 @@ int ceph_msgr_init(void)
 	if (ceph_msgr_slab_init())
 		return -ENOMEM;
 
-	ceph_msgr_wq = alloc_workqueue("ceph-msgr", 0, 0);
+	/*
+	 * The number of active work items is limited by the number of
+	 * connections, so leave @max_active at default.
+	 */
+	ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_MEM_RECLAIM, 0);
 	if (ceph_msgr_wq)
 		return 0;
 
@@ -1937,11 +1941,11 @@ static int process_banner(struct ceph_connection *con)
 		   sizeof(con->peer_addr)) != 0 &&
 	    !(addr_is_blank(&con->actual_peer_addr.in_addr) &&
 	      con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
-		pr_warning("wrong peer, want %s/%d, got %s/%d\n",
-			   ceph_pr_addr(&con->peer_addr.in_addr),
-			   (int)le32_to_cpu(con->peer_addr.nonce),
-			   ceph_pr_addr(&con->actual_peer_addr.in_addr),
-			   (int)le32_to_cpu(con->actual_peer_addr.nonce));
+		pr_warn("wrong peer, want %s/%d, got %s/%d\n",
+			ceph_pr_addr(&con->peer_addr.in_addr),
+			(int)le32_to_cpu(con->peer_addr.nonce),
+			ceph_pr_addr(&con->actual_peer_addr.in_addr),
+			(int)le32_to_cpu(con->actual_peer_addr.nonce));
 		con->error_msg = "wrong peer at address";
 		return -1;
 	}
@@ -2302,7 +2306,7 @@ static int read_partial_message(struct ceph_connection *con)
 
 		BUG_ON(!con->in_msg ^ skip);
 		if (con->in_msg && data_len > con->in_msg->data_length) {
-			pr_warning("%s skipping long message (%u > %zd)\n",
+			pr_warn("%s skipping long message (%u > %zd)\n",
 				__func__, data_len, con->in_msg->data_length);
 			ceph_msg_put(con->in_msg);
 			con->in_msg = NULL;
@@ -2712,7 +2716,7 @@ static bool con_sock_closed(struct ceph_connection *con)
 	CASE(OPEN);
 	CASE(STANDBY);
 	default:
-		pr_warning("%s con %p unrecognized state %lu\n",
+		pr_warn("%s con %p unrecognized state %lu\n",
 			__func__, con, con->state);
 		con->error_msg = "unrecognized con state";
 		BUG();
@@ -2828,8 +2832,8 @@ static void con_work(struct work_struct *work)
  */
 static void con_fault(struct ceph_connection *con)
 {
-	pr_warning("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
-	       ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
+	pr_warn("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
+		ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
 	dout("fault %p state %lu to peer %s\n",
 	     con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));
 
@@ -3071,10 +3075,8 @@ static void ceph_msg_data_destroy(struct ceph_msg_data *data)
 		return;
 
 	WARN_ON(!list_empty(&data->links));
-	if (data->type == CEPH_MSG_DATA_PAGELIST) {
+	if (data->type == CEPH_MSG_DATA_PAGELIST)
 		ceph_pagelist_release(data->pagelist);
-		kfree(data->pagelist);
-	}
 	kmem_cache_free(ceph_msg_data_cache, data);
 }
 
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 61fcfc304f68..a83062ceeec9 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -1182,10 +1182,10 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 		pr_info("alloc_msg unknown type %d\n", type);
 		*skip = 1;
 	} else if (front_len > m->front_alloc_len) {
-		pr_warning("mon_alloc_msg front %d > prealloc %d (%u#%llu)\n",
-			   front_len, m->front_alloc_len,
-			   (unsigned int)con->peer_name.type,
-			   le64_to_cpu(con->peer_name.num));
+		pr_warn("mon_alloc_msg front %d > prealloc %d (%u#%llu)\n",
+			front_len, m->front_alloc_len,
+			(unsigned int)con->peer_name.type,
+			le64_to_cpu(con->peer_name.num));
 		ceph_msg_put(m);
 		m = ceph_msg_new(type, front_len, GFP_NOFS, false);
 	}
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 30f6faf3584f..f3fc54eac09d 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -30,8 +30,11 @@ static void __send_queued(struct ceph_osd_client *osdc);
 static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd);
 static void __register_request(struct ceph_osd_client *osdc,
 			       struct ceph_osd_request *req);
+static void __unregister_request(struct ceph_osd_client *osdc,
+				 struct ceph_osd_request *req);
 static void __unregister_linger_request(struct ceph_osd_client *osdc,
 					struct ceph_osd_request *req);
+static void __enqueue_request(struct ceph_osd_request *req);
 static void __send_request(struct ceph_osd_client *osdc,
 			   struct ceph_osd_request *req);
 
@@ -428,68 +431,9 @@ EXPORT_SYMBOL(ceph_osdc_alloc_request);
 static bool osd_req_opcode_valid(u16 opcode)
 {
 	switch (opcode) {
-	case CEPH_OSD_OP_READ:
-	case CEPH_OSD_OP_STAT:
-	case CEPH_OSD_OP_MAPEXT:
-	case CEPH_OSD_OP_MASKTRUNC:
-	case CEPH_OSD_OP_SPARSE_READ:
-	case CEPH_OSD_OP_NOTIFY:
-	case CEPH_OSD_OP_NOTIFY_ACK:
-	case CEPH_OSD_OP_ASSERT_VER:
-	case CEPH_OSD_OP_WRITE:
-	case CEPH_OSD_OP_WRITEFULL:
-	case CEPH_OSD_OP_TRUNCATE:
-	case CEPH_OSD_OP_ZERO:
-	case CEPH_OSD_OP_DELETE:
-	case CEPH_OSD_OP_APPEND:
-	case CEPH_OSD_OP_STARTSYNC:
-	case CEPH_OSD_OP_SETTRUNC:
-	case CEPH_OSD_OP_TRIMTRUNC:
-	case CEPH_OSD_OP_TMAPUP:
-	case CEPH_OSD_OP_TMAPPUT:
-	case CEPH_OSD_OP_TMAPGET:
-	case CEPH_OSD_OP_CREATE:
-	case CEPH_OSD_OP_ROLLBACK:
-	case CEPH_OSD_OP_WATCH:
-	case CEPH_OSD_OP_OMAPGETKEYS:
-	case CEPH_OSD_OP_OMAPGETVALS:
-	case CEPH_OSD_OP_OMAPGETHEADER:
-	case CEPH_OSD_OP_OMAPGETVALSBYKEYS:
-	case CEPH_OSD_OP_OMAPSETVALS:
-	case CEPH_OSD_OP_OMAPSETHEADER:
-	case CEPH_OSD_OP_OMAPCLEAR:
-	case CEPH_OSD_OP_OMAPRMKEYS:
-	case CEPH_OSD_OP_OMAP_CMP:
-	case CEPH_OSD_OP_SETALLOCHINT:
-	case CEPH_OSD_OP_CLONERANGE:
-	case CEPH_OSD_OP_ASSERT_SRC_VERSION:
-	case CEPH_OSD_OP_SRC_CMPXATTR:
-	case CEPH_OSD_OP_GETXATTR:
-	case CEPH_OSD_OP_GETXATTRS:
-	case CEPH_OSD_OP_CMPXATTR:
-	case CEPH_OSD_OP_SETXATTR:
-	case CEPH_OSD_OP_SETXATTRS:
-	case CEPH_OSD_OP_RESETXATTRS:
-	case CEPH_OSD_OP_RMXATTR:
-	case CEPH_OSD_OP_PULL:
-	case CEPH_OSD_OP_PUSH:
-	case CEPH_OSD_OP_BALANCEREADS:
-	case CEPH_OSD_OP_UNBALANCEREADS:
-	case CEPH_OSD_OP_SCRUB:
-	case CEPH_OSD_OP_SCRUB_RESERVE:
-	case CEPH_OSD_OP_SCRUB_UNRESERVE:
-	case CEPH_OSD_OP_SCRUB_STOP:
-	case CEPH_OSD_OP_SCRUB_MAP:
-	case CEPH_OSD_OP_WRLOCK:
-	case CEPH_OSD_OP_WRUNLOCK:
-	case CEPH_OSD_OP_RDLOCK:
-	case CEPH_OSD_OP_RDUNLOCK:
-	case CEPH_OSD_OP_UPLOCK:
-	case CEPH_OSD_OP_DNLOCK:
-	case CEPH_OSD_OP_CALL:
-	case CEPH_OSD_OP_PGLS:
-	case CEPH_OSD_OP_PGLS_FILTER:
-		return true;
+#define GENERATE_CASE(op, opcode, str)	case CEPH_OSD_OP_##op: return true;
+__CEPH_FORALL_OSD_OPS(GENERATE_CASE)
+#undef GENERATE_CASE
 	default:
 		return false;
 	}
@@ -892,6 +836,37 @@ __lookup_request_ge(struct ceph_osd_client *osdc,
 	return NULL;
 }
 
+static void __kick_linger_request(struct ceph_osd_request *req)
+{
+	struct ceph_osd_client *osdc = req->r_osdc;
+	struct ceph_osd *osd = req->r_osd;
+
+	/*
+	 * Linger requests need to be resent with a new tid to avoid
+	 * the dup op detection logic on the OSDs.  Achieve this with
+	 * a re-register dance instead of open-coding.
+	 */
+	ceph_osdc_get_request(req);
+	if (!list_empty(&req->r_linger_item))
+		__unregister_linger_request(osdc, req);
+	else
+		__unregister_request(osdc, req);
+	__register_request(osdc, req);
+	ceph_osdc_put_request(req);
+
+	/*
+	 * Unless request has been registered as both normal and
+	 * lingering, __unregister{,_linger}_request clears r_osd.
+	 * However, here we need to preserve r_osd to make sure we
+	 * requeue on the same OSD.
+	 */
+	WARN_ON(req->r_osd || !osd);
+	req->r_osd = osd;
+
+	dout("%s requeueing %p tid %llu\n", __func__, req, req->r_tid);
+	__enqueue_request(req);
+}
+
 /*
  * Resubmit requests pending on the given osd.
  */
@@ -900,12 +875,14 @@ static void __kick_osd_requests(struct ceph_osd_client *osdc,
 {
 	struct ceph_osd_request *req, *nreq;
 	LIST_HEAD(resend);
+	LIST_HEAD(resend_linger);
 	int err;
 
-	dout("__kick_osd_requests osd%d\n", osd->o_osd);
+	dout("%s osd%d\n", __func__, osd->o_osd);
 	err = __reset_osd(osdc, osd);
 	if (err)
 		return;
+
 	/*
 	 * Build up a list of requests to resend by traversing the
 	 * osd's list of requests.  Requests for a given object are
@@ -926,33 +903,32 @@ static void __kick_osd_requests(struct ceph_osd_client *osdc,
 	list_for_each_entry(req, &osd->o_requests, r_osd_item) {
 		if (!req->r_sent)
 			break;
-		list_move_tail(&req->r_req_lru_item, &resend);
-		dout("requeueing %p tid %llu osd%d\n", req, req->r_tid,
-		     osd->o_osd);
-		if (!req->r_linger)
+
+		if (!req->r_linger) {
+			dout("%s requeueing %p tid %llu\n", __func__, req,
+			     req->r_tid);
+			list_move_tail(&req->r_req_lru_item, &resend);
 			req->r_flags |= CEPH_OSD_FLAG_RETRY;
+		} else {
+			list_move_tail(&req->r_req_lru_item, &resend_linger);
+		}
 	}
 	list_splice(&resend, &osdc->req_unsent);
 
 	/*
-	 * Linger requests are re-registered before sending, which
-	 * sets up a new tid for each.  We add them to the unsent
-	 * list at the end to keep things in tid order.
+	 * Both registered and not yet registered linger requests are
+	 * enqueued with a new tid on the same OSD.  We add/move them
+	 * to req_unsent/o_requests at the end to keep things in tid
+	 * order.
 	 */
 	list_for_each_entry_safe(req, nreq, &osd->o_linger_requests,
 				 r_linger_osd_item) {
-		/*
-		 * reregister request prior to unregistering linger so
-		 * that r_osd is preserved.
-		 */
-		BUG_ON(!list_empty(&req->r_req_lru_item));
-		__register_request(osdc, req);
-		list_add_tail(&req->r_req_lru_item, &osdc->req_unsent);
-		list_add_tail(&req->r_osd_item, &req->r_osd->o_requests);
-		__unregister_linger_request(osdc, req);
-		dout("requeued lingering %p tid %llu osd%d\n", req, req->r_tid,
-		     osd->o_osd);
+		WARN_ON(!list_empty(&req->r_req_lru_item));
+		__kick_linger_request(req);
 	}
+
+	list_for_each_entry_safe(req, nreq, &resend_linger, r_req_lru_item)
+		__kick_linger_request(req);
 }
 
 /*
@@ -1346,6 +1322,22 @@ static int __calc_request_pg(struct ceph_osdmap *osdmap,
 				   &req->r_target_oid, pg_out);
 }
 
+static void __enqueue_request(struct ceph_osd_request *req)
+{
+	struct ceph_osd_client *osdc = req->r_osdc;
+
+	dout("%s %p tid %llu to osd%d\n", __func__, req, req->r_tid,
+	     req->r_osd ? req->r_osd->o_osd : -1);
+
+	if (req->r_osd) {
+		__remove_osd_from_lru(req->r_osd);
+		list_add_tail(&req->r_osd_item, &req->r_osd->o_requests);
+		list_move_tail(&req->r_req_lru_item, &osdc->req_unsent);
+	} else {
+		list_move_tail(&req->r_req_lru_item, &osdc->req_notarget);
+	}
+}
+
 /*
  * Pick an osd (the first 'up' osd in the pg), allocate the osd struct
  * (as needed), and set the request r_osd appropriately.  If there is
@@ -1423,13 +1415,7 @@ static int __map_request(struct ceph_osd_client *osdc,
 			      &osdc->osdmap->osd_addr[o]);
 	}
 
-	if (req->r_osd) {
-		__remove_osd_from_lru(req->r_osd);
-		list_add_tail(&req->r_osd_item, &req->r_osd->o_requests);
-		list_move_tail(&req->r_req_lru_item, &osdc->req_unsent);
-	} else {
-		list_move_tail(&req->r_req_lru_item, &osdc->req_notarget);
-	}
+	__enqueue_request(req);
 	err = 1;   /* osd or pg changed */
 
 out:
@@ -1774,8 +1760,8 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 	}
 	bytes = le32_to_cpu(msg->hdr.data_len);
 	if (payload_len != bytes) {
-		pr_warning("sum of op payload lens %d != data_len %d",
-			   payload_len, bytes);
+		pr_warn("sum of op payload lens %d != data_len %d\n",
+			payload_len, bytes);
 		goto bad_put;
 	}
 
@@ -2313,24 +2299,19 @@ static void handle_watch_notify(struct ceph_osd_client *osdc,
 	if (event) {
 		event_work = kmalloc(sizeof(*event_work), GFP_NOIO);
 		if (!event_work) {
-			dout("ERROR: could not allocate event_work\n");
-			goto done_err;
+			pr_err("couldn't allocate event_work\n");
+			ceph_osdc_put_event(event);
+			return;
 		}
 		INIT_WORK(&event_work->work, do_event_work);
 		event_work->event = event;
 		event_work->ver = ver;
 		event_work->notify_id = notify_id;
 		event_work->opcode = opcode;
-		if (!queue_work(osdc->notify_wq, &event_work->work)) {
-			dout("WARNING: failed to queue notify event work\n");
-			goto done_err;
-		}
-	}
 
-	return;
+		queue_work(osdc->notify_wq, &event_work->work);
+	}
 
-done_err:
-	ceph_osdc_put_event(event);
 	return;
 
 bad:
@@ -2797,10 +2778,10 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	ceph_msg_revoke_incoming(req->r_reply);
 
 	if (front_len > req->r_reply->front_alloc_len) {
-		pr_warning("get_reply front %d > preallocated %d (%u#%llu)\n",
-			   front_len, req->r_reply->front_alloc_len,
-			   (unsigned int)con->peer_name.type,
-			   le64_to_cpu(con->peer_name.num));
+		pr_warn("get_reply front %d > preallocated %d (%u#%llu)\n",
+			front_len, req->r_reply->front_alloc_len,
+			(unsigned int)con->peer_name.type,
+			le64_to_cpu(con->peer_name.num));
 		m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS,
 				 false);
 		if (!m)
@@ -2823,8 +2804,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 			if (osd_data->pages &&
 				unlikely(osd_data->length < data_len)) {
 
-				pr_warning("tid %lld reply has %d bytes "
-					"we had only %llu bytes ready\n",
+				pr_warn("tid %lld reply has %d bytes we had only %llu bytes ready\n",
 					tid, data_len, osd_data->length);
 				*skip = 1;
 				ceph_msg_put(m);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index c547e46084d3..b8c3fde5b04f 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -521,11 +521,11 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi)
 	ev = ceph_decode_8(p);  /* encoding version */
 	cv = ceph_decode_8(p); /* compat version */
 	if (ev < 5) {
-		pr_warning("got v %d < 5 cv %d of ceph_pg_pool\n", ev, cv);
+		pr_warn("got v %d < 5 cv %d of ceph_pg_pool\n", ev, cv);
 		return -EINVAL;
 	}
 	if (cv > 9) {
-		pr_warning("got v %d cv %d > 9 of ceph_pg_pool\n", ev, cv);
+		pr_warn("got v %d cv %d > 9 of ceph_pg_pool\n", ev, cv);
 		return -EINVAL;
 	}
 	len = ceph_decode_32(p);
@@ -671,26 +671,26 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
 	int i;
 
 	state = krealloc(map->osd_state, max*sizeof(*state), GFP_NOFS);
+	if (!state)
+		return -ENOMEM;
+	map->osd_state = state;
+
 	weight = krealloc(map->osd_weight, max*sizeof(*weight), GFP_NOFS);
-	addr = krealloc(map->osd_addr, max*sizeof(*addr), GFP_NOFS);
-	if (!state || !weight || !addr) {
-		kfree(state);
-		kfree(weight);
-		kfree(addr);
+	if (!weight)
+		return -ENOMEM;
+	map->osd_weight = weight;
 
+	addr = krealloc(map->osd_addr, max*sizeof(*addr), GFP_NOFS);
+	if (!addr)
 		return -ENOMEM;
-	}
+	map->osd_addr = addr;
 
 	for (i = map->max_osd; i < max; i++) {
-		state[i] = 0;
-		weight[i] = CEPH_OSD_OUT;
-		memset(addr + i, 0, sizeof(*addr));
+		map->osd_state[i] = 0;
+		map->osd_weight[i] = CEPH_OSD_OUT;
+		memset(map->osd_addr + i, 0, sizeof(*map->osd_addr));
 	}
 
-	map->osd_state = state;
-	map->osd_weight = weight;
-	map->osd_addr = addr;
-
 	if (map->osd_primary_affinity) {
 		u32 *affinity;
 
@@ -698,11 +698,11 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
 				    max*sizeof(*affinity), GFP_NOFS);
 		if (!affinity)
 			return -ENOMEM;
+		map->osd_primary_affinity = affinity;
 
 		for (i = map->max_osd; i < max; i++)
-			affinity[i] = CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
-
-		map->osd_primary_affinity = affinity;
+			map->osd_primary_affinity[i] =
+			    CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
 	}
 
 	map->max_osd = max;
@@ -729,9 +729,9 @@ static int get_osdmap_client_data_v(void **p, void *end,
 
 		ceph_decode_8_safe(p, end, struct_compat, e_inval);
 		if (struct_compat > OSDMAP_WRAPPER_COMPAT_VER) {
-			pr_warning("got v %d cv %d > %d of %s ceph_osdmap\n",
-				   struct_v, struct_compat,
-				   OSDMAP_WRAPPER_COMPAT_VER, prefix);
+			pr_warn("got v %d cv %d > %d of %s ceph_osdmap\n",
+				struct_v, struct_compat,
+				OSDMAP_WRAPPER_COMPAT_VER, prefix);
 			return -EINVAL;
 		}
 		*p += 4; /* ignore wrapper struct_len */
@@ -739,9 +739,9 @@ static int get_osdmap_client_data_v(void **p, void *end,
 		ceph_decode_8_safe(p, end, struct_v, e_inval);
 		ceph_decode_8_safe(p, end, struct_compat, e_inval);
 		if (struct_compat > OSDMAP_CLIENT_DATA_COMPAT_VER) {
-			pr_warning("got v %d cv %d > %d of %s ceph_osdmap client data\n",
-				   struct_v, struct_compat,
-				   OSDMAP_CLIENT_DATA_COMPAT_VER, prefix);
+			pr_warn("got v %d cv %d > %d of %s ceph_osdmap client data\n",
+				struct_v, struct_compat,
+				OSDMAP_CLIENT_DATA_COMPAT_VER, prefix);
 			return -EINVAL;
 		}
 		*p += 4; /* ignore client data struct_len */
@@ -751,8 +751,8 @@ static int get_osdmap_client_data_v(void **p, void *end,
 		*p -= 1;
 		ceph_decode_16_safe(p, end, version, e_inval);
 		if (version < 6) {
-			pr_warning("got v %d < 6 of %s ceph_osdmap\n", version,
-				   prefix);
+			pr_warn("got v %d < 6 of %s ceph_osdmap\n",
+				version, prefix);
 			return -EINVAL;
 		}
 
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
index 92866bebb65f..c7c220a736e5 100644
--- a/net/ceph/pagelist.c
+++ b/net/ceph/pagelist.c
@@ -1,5 +1,6 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 #include <linux/ceph/pagelist.h>
@@ -13,8 +14,10 @@ static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
 	}
 }
 
-int ceph_pagelist_release(struct ceph_pagelist *pl)
+void ceph_pagelist_release(struct ceph_pagelist *pl)
 {
+	if (!atomic_dec_and_test(&pl->refcnt))
+		return;
 	ceph_pagelist_unmap_tail(pl);
 	while (!list_empty(&pl->head)) {
 		struct page *page = list_first_entry(&pl->head, struct page,
@@ -23,7 +26,7 @@ int ceph_pagelist_release(struct ceph_pagelist *pl)
 		__free_page(page);
 	}
 	ceph_pagelist_free_reserve(pl);
-	return 0;
+	kfree(pl);
 }
 EXPORT_SYMBOL(ceph_pagelist_release);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 9f77a78c6b1c..b793e3521a36 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2153,7 +2153,7 @@ static inline void __netif_reschedule(struct Qdisc *q)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	sd = &__get_cpu_var(softnet_data);
+	sd = this_cpu_ptr(&softnet_data);
 	q->next_sched = NULL;
 	*sd->output_queue_tailp = q;
 	sd->output_queue_tailp = &q->next_sched;
@@ -3233,7 +3233,7 @@ static void rps_trigger_softirq(void *data)
 static int rps_ipi_queued(struct softnet_data *sd)
 {
 #ifdef CONFIG_RPS
-	struct softnet_data *mysd = &__get_cpu_var(softnet_data);
+	struct softnet_data *mysd = this_cpu_ptr(&softnet_data);
 
 	if (sd != mysd) {
 		sd->rps_ipi_next = mysd->rps_ipi_list;
@@ -3260,7 +3260,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
 	if (qlen < (netdev_max_backlog >> 1))
 		return false;
 
-	sd = &__get_cpu_var(softnet_data);
+	sd = this_cpu_ptr(&softnet_data);
 
 	rcu_read_lock();
 	fl = rcu_dereference(sd->flow_limit);
@@ -3407,7 +3407,7 @@ EXPORT_SYMBOL(netif_rx_ni);
 
 static void net_tx_action(struct softirq_action *h)
 {
-	struct softnet_data *sd = &__get_cpu_var(softnet_data);
+	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 
 	if (sd->completion_queue) {
 		struct sk_buff *clist;
@@ -3832,7 +3832,7 @@ EXPORT_SYMBOL(netif_receive_skb);
 static void flush_backlog(void *arg)
 {
 	struct net_device *dev = arg;
-	struct softnet_data *sd = &__get_cpu_var(softnet_data);
+	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 	struct sk_buff *skb, *tmp;
 
 	rps_lock(sd);
@@ -4379,7 +4379,7 @@ void __napi_schedule(struct napi_struct *n)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	____napi_schedule(&__get_cpu_var(softnet_data), n);
+	____napi_schedule(this_cpu_ptr(&softnet_data), n);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(__napi_schedule);
@@ -4500,7 +4500,7 @@ EXPORT_SYMBOL(netif_napi_del);
 
 static void net_rx_action(struct softirq_action *h)
 {
-	struct softnet_data *sd = &__get_cpu_var(softnet_data);
+	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 	unsigned long time_limit = jiffies + 2;
 	int budget = netdev_budget;
 	void *have;
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 50f9a9db5792..252e155c837b 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -146,7 +146,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	data = &__get_cpu_var(dm_cpu_data);
+	data = this_cpu_ptr(&dm_cpu_data);
 	spin_lock(&data->lock);
 	dskb = data->skb;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 829d013745ab..61059a05ec95 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -345,7 +345,7 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	nc = &__get_cpu_var(netdev_alloc_cache);
+	nc = this_cpu_ptr(&netdev_alloc_cache);
 	if (unlikely(!nc->frag.page)) {
 refill:
 		for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) {
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 97b0fcc79547..5ab6627cf370 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1115,7 +1115,7 @@ static int __init dccp_init(void)
 
 	BUILD_BUG_ON(sizeof(struct dccp_skb_cb) >
 		     FIELD_SIZEOF(struct sk_buff, cb));
-	rc = percpu_counter_init(&dccp_orphan_count, 0);
+	rc = percpu_counter_init(&dccp_orphan_count, 0, GFP_KERNEL);
 	if (rc)
 		goto out_fail;
 	rc = -ENOBUFS;
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index f380b2c58178..31cd4fd75486 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -176,11 +176,11 @@ static void dns_resolver_free_preparse(struct key_preparsed_payload *prep)
  * The domain name may be a simple name or an absolute domain name (which
  * should end with a period).  The domain name is case-independent.
  */
-static int
-dns_resolver_match(const struct key *key, const void *description)
+static bool dns_resolver_cmp(const struct key *key,
+			     const struct key_match_data *match_data)
 {
 	int slen, dlen, ret = 0;
-	const char *src = key->description, *dsp = description;
+	const char *src = key->description, *dsp = match_data->raw_data;
 
 	kenter("%s,%s", src, dsp);
 
@@ -209,6 +209,16 @@ no_match:
 }
 
 /*
+ * Preparse the match criterion.
+ */
+static int dns_resolver_match_preparse(struct key_match_data *match_data)
+{
+	match_data->lookup_type = KEYRING_SEARCH_LOOKUP_ITERATE;
+	match_data->cmp = dns_resolver_cmp;
+	return 0;
+}
+
+/*
  * Describe a DNS key
  */
 static void dns_resolver_describe(const struct key *key, struct seq_file *m)
@@ -242,7 +252,7 @@ struct key_type key_type_dns_resolver = {
 	.preparse	= dns_resolver_preparse,
 	.free_preparse	= dns_resolver_free_preparse,
 	.instantiate	= generic_key_instantiate,
-	.match		= dns_resolver_match,
+	.match_preparse	= dns_resolver_match_preparse,
 	.revoke		= user_revoke,
 	.destroy	= user_destroy,
 	.describe	= dns_resolver_describe,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 793c0bb8c4fd..2d4ae469b471 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1311,7 +1311,7 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 	if (rt_is_input_route(rt)) {
 		p = (struct rtable **)&nh->nh_rth_input;
 	} else {
-		p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output);
+		p = (struct rtable **)raw_cpu_ptr(nh->nh_pcpu_rth_output);
 	}
 	orig = *p;
 
@@ -1939,7 +1939,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 				do_cache = false;
 				goto add;
 			}
-			prth = __this_cpu_ptr(nh->nh_pcpu_rth_output);
+			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
 		rth = rcu_dereference(*prth);
 		if (rt_cache_valid(rth)) {
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index d346303fac77..32b98d0207b4 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -40,7 +40,7 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
 
 	net_get_random_once(syncookie_secret, sizeof(syncookie_secret));
 
-	tmp  = __get_cpu_var(ipv4_cookie_scratch);
+	tmp  = this_cpu_ptr(ipv4_cookie_scratch);
 	memcpy(tmp + 4, syncookie_secret[c], sizeof(syncookie_secret[c]));
 	tmp[0] = (__force u32)saddr;
 	tmp[1] = (__force u32)daddr;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 461003d258ba..1bec4e76d88c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2941,7 +2941,7 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
 	local_bh_disable();
 	p = ACCESS_ONCE(tcp_md5sig_pool);
 	if (p)
-		return __this_cpu_ptr(p);
+		return raw_cpu_ptr(p);
 
 	local_bh_enable();
 	return NULL;
@@ -3071,8 +3071,8 @@ void __init tcp_init(void)
 
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
 
-	percpu_counter_init(&tcp_sockets_allocated, 0);
-	percpu_counter_init(&tcp_orphan_count, 0);
+	percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
+	percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL);
 	tcp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("tcp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 3af522622fad..1d191357bf88 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -32,7 +32,7 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 		res_parent = &parent_cg->memory_allocated;
 
 	res_counter_init(&cg_proto->memory_allocated, res_parent);
-	percpu_counter_init(&cg_proto->sockets_allocated, 0);
+	percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL);
 
 	return 0;
 }
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e13d77857225..3af21296d967 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -863,7 +863,7 @@ void tcp_wfree(struct sk_buff *skb)
 
 		/* queue this socket to tasklet queue */
 		local_irq_save(flags);
-		tsq = &__get_cpu_var(tsq_tasklet);
+		tsq = this_cpu_ptr(&tsq_tasklet);
 		list_add(&tp->tsq_node, &tsq->head);
 		tasklet_schedule(&tsq->tasklet);
 		local_irq_restore(flags);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 2a86a0f00f2b..2f25cb6347ca 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -67,7 +67,7 @@ static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *dadd
 
 	net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret));
 
-	tmp  = __get_cpu_var(ipv6_cookie_scratch);
+	tmp  = this_cpu_ptr(ipv6_cookie_scratch);
 
 	/*
 	 * we have 320 bits of information to hash, copy in the remaining
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index a64fa15790e5..1d5341f3761d 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -96,13 +96,13 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit,
 
 	if (data_limit - data < plen) {
 		/* check if there is partial match */
-		if (strnicmp(data, pattern, data_limit - data) == 0)
+		if (strncasecmp(data, pattern, data_limit - data) == 0)
 			return -1;
 		else
 			return 0;
 	}
 
-	if (strnicmp(data, pattern, plen) != 0) {
+	if (strncasecmp(data, pattern, plen) != 0) {
 		return 0;
 	}
 	s = data + plen;
@@ -354,7 +354,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	data_limit = skb_tail_pointer(skb);
 
 	while (data <= data_limit - 6) {
-		if (strnicmp(data, "PASV\r\n", 6) == 0) {
+		if (strncasecmp(data, "PASV\r\n", 6) == 0) {
 			/* Passive mode on */
 			IP_VS_DBG(7, "got PASV at %td of %td\n",
 				  data - data_start,
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index b8a0924064ef..b666959f17c0 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -304,12 +304,12 @@ static int find_pattern(const char *data, size_t dlen,
 
 	if (dlen <= plen) {
 		/* Short packet: try for partial? */
-		if (strnicmp(data, pattern, dlen) == 0)
+		if (strncasecmp(data, pattern, dlen) == 0)
 			return -1;
 		else return 0;
 	}
 
-	if (strnicmp(data, pattern, plen) != 0) {
+	if (strncasecmp(data, pattern, plen) != 0) {
 #if 0
 		size_t i;
 
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 4c3ba1c8d682..885b4aba3695 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -247,7 +247,7 @@ int ct_sip_parse_request(const struct nf_conn *ct,
 	for (; dptr < limit - strlen("sip:"); dptr++) {
 		if (*dptr == '\r' || *dptr == '\n')
 			return -1;
-		if (strnicmp(dptr, "sip:", strlen("sip:")) == 0) {
+		if (strncasecmp(dptr, "sip:", strlen("sip:")) == 0) {
 			dptr += strlen("sip:");
 			break;
 		}
@@ -350,7 +350,7 @@ static const char *ct_sip_header_search(const char *dptr, const char *limit,
 			continue;
 		}
 
-		if (strnicmp(dptr, needle, len) == 0)
+		if (strncasecmp(dptr, needle, len) == 0)
 			return dptr;
 	}
 	return NULL;
@@ -383,10 +383,10 @@ int ct_sip_get_header(const struct nf_conn *ct, const char *dptr,
 		/* Find header. Compact headers must be followed by a
 		 * non-alphabetic character to avoid mismatches. */
 		if (limit - dptr >= hdr->len &&
-		    strnicmp(dptr, hdr->name, hdr->len) == 0)
+		    strncasecmp(dptr, hdr->name, hdr->len) == 0)
 			dptr += hdr->len;
 		else if (hdr->cname && limit - dptr >= hdr->clen + 1 &&
-			 strnicmp(dptr, hdr->cname, hdr->clen) == 0 &&
+			 strncasecmp(dptr, hdr->cname, hdr->clen) == 0 &&
 			 !isalpha(*(dptr + hdr->clen)))
 			dptr += hdr->clen;
 		else
@@ -620,9 +620,9 @@ static int ct_sip_parse_transport(struct nf_conn *ct, const char *dptr,
 
 	if (ct_sip_parse_param(ct, dptr, dataoff, datalen, "transport=",
 			       &matchoff, &matchlen)) {
-		if (!strnicmp(dptr + matchoff, "TCP", strlen("TCP")))
+		if (!strncasecmp(dptr + matchoff, "TCP", strlen("TCP")))
 			*proto = IPPROTO_TCP;
-		else if (!strnicmp(dptr + matchoff, "UDP", strlen("UDP")))
+		else if (!strncasecmp(dptr + matchoff, "UDP", strlen("UDP")))
 			*proto = IPPROTO_UDP;
 		else
 			return 0;
@@ -743,10 +743,10 @@ int ct_sip_get_sdp_header(const struct nf_conn *ct, const char *dptr,
 
 		if (term != SDP_HDR_UNSPEC &&
 		    limit - dptr >= thdr->len &&
-		    strnicmp(dptr, thdr->name, thdr->len) == 0)
+		    strncasecmp(dptr, thdr->name, thdr->len) == 0)
 			break;
 		else if (limit - dptr >= hdr->len &&
-			 strnicmp(dptr, hdr->name, hdr->len) == 0)
+			 strncasecmp(dptr, hdr->name, hdr->len) == 0)
 			dptr += hdr->len;
 		else
 			continue;
@@ -1394,7 +1394,7 @@ static int process_sip_response(struct sk_buff *skb, unsigned int protoff,
 		if (handler->response == NULL)
 			continue;
 		if (*datalen < matchend + handler->len ||
-		    strnicmp(*dptr + matchend, handler->method, handler->len))
+		    strncasecmp(*dptr + matchend, handler->method, handler->len))
 			continue;
 		return handler->response(skb, protoff, dataoff, dptr, datalen,
 					 cseq, code);
@@ -1435,7 +1435,7 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff,
 		if (handler->request == NULL)
 			continue;
 		if (*datalen < handler->len ||
-		    strnicmp(*dptr, handler->method, handler->len))
+		    strncasecmp(*dptr, handler->method, handler->len))
 			continue;
 
 		if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CSEQ,
@@ -1462,7 +1462,7 @@ static int process_sip_msg(struct sk_buff *skb, struct nf_conn *ct,
 	const struct nf_nat_sip_hooks *hooks;
 	int ret;
 
-	if (strnicmp(*dptr, "SIP/2.0 ", strlen("SIP/2.0 ")) != 0)
+	if (strncasecmp(*dptr, "SIP/2.0 ", strlen("SIP/2.0 ")) != 0)
 		ret = process_sip_request(skb, protoff, dataoff, dptr, datalen);
 	else
 		ret = process_sip_response(skb, protoff, dataoff, dptr, datalen);
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index daad6022c689..d7197649dba6 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -30,7 +30,7 @@ static struct nf_logger *__find_logger(int pf, const char *str_logger)
 
 		log = rcu_dereference_protected(loggers[pf][i],
 						lockdep_is_held(&nf_log_mutex));
-		if (!strnicmp(str_logger, log->name, strlen(log->name)))
+		if (!strncasecmp(str_logger, log->name, strlen(log->name)))
 			return log;
 	}
 
diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c
index b4d691db955e..791fac4fd745 100644
--- a/net/netfilter/nf_nat_sip.c
+++ b/net/netfilter/nf_nat_sip.c
@@ -155,7 +155,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff,
 	int request, in_header;
 
 	/* Basic rules: requests and responses. */
-	if (strnicmp(*dptr, "SIP/2.0", strlen("SIP/2.0")) != 0) {
+	if (strncasecmp(*dptr, "SIP/2.0", strlen("SIP/2.0")) != 0) {
 		if (ct_sip_parse_request(ct, *dptr, *datalen,
 					 &matchoff, &matchlen,
 					 &addr, &port) > 0 &&
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index c416725d28c4..7a186e74b1b3 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -715,7 +715,7 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 	 * after validation, the socket and the ring may only be used by a
 	 * single process, otherwise we fall back to copying.
 	 */
-	if (atomic_long_read(&sk->sk_socket->file->f_count) > 2 ||
+	if (atomic_long_read(&sk->sk_socket->file->f_count) > 1 ||
 	    atomic_read(&nlk->mapped) > 1)
 		excl = false;
 
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index e8fdb172adbb..273b8bff6ba4 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -267,7 +267,7 @@ static inline struct rds_ib_mr *rds_ib_reuse_fmr(struct rds_ib_mr_pool *pool)
 	unsigned long *flag;
 
 	preempt_disable();
-	flag = &__get_cpu_var(clean_list_grace);
+	flag = this_cpu_ptr(&clean_list_grace);
 	set_bit(CLEAN_LIST_BUSY_BIT, flag);
 	ret = llist_del_first(&pool->clean_list);
 	if (ret)
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index 1b24191167f1..db0f39f5ef96 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -44,7 +44,6 @@ struct key_type key_type_rxrpc = {
 	.preparse	= rxrpc_preparse,
 	.free_preparse	= rxrpc_free_preparse,
 	.instantiate	= generic_key_instantiate,
-	.match		= user_match,
 	.destroy	= rxrpc_destroy,
 	.describe	= rxrpc_describe,
 	.read		= rxrpc_read,
@@ -61,7 +60,6 @@ struct key_type key_type_rxrpc_s = {
 	.preparse	= rxrpc_preparse_s,
 	.free_preparse	= rxrpc_free_preparse_s,
 	.instantiate	= generic_key_instantiate,
-	.match		= user_match,
 	.destroy	= rxrpc_destroy_s,
 	.describe	= rxrpc_describe,
 };
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 9d2c6c9facb6..8f34b27d5775 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1341,7 +1341,7 @@ static __init int sctp_init(void)
 	if (!sctp_chunk_cachep)
 		goto err_chunk_cachep;
 
-	status = percpu_counter_init(&sctp_sockets_allocated, 0);
+	status = percpu_counter_init(&sctp_sockets_allocated, 0, GFP_KERNEL);
 	if (status)
 		goto err_percpu_counter_init;
 
diff --git a/net/socket.c b/net/socket.c
index ffd9cb46902b..fe20c319a0bb 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1065,7 +1065,8 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 			err = -EFAULT;
 			if (get_user(pid, (int __user *)argp))
 				break;
-			err = f_setown(sock->file, pid, 1);
+			f_setown(sock->file, pid, 1);
+			err = 0;
 			break;
 		case FIOGETOWN:
 		case SIOCGPGRP:
diff --git a/net/wireless/lib80211.c b/net/wireless/lib80211.c
index a55c27b75ee5..459611577d3d 100644
--- a/net/wireless/lib80211.c
+++ b/net/wireless/lib80211.c
@@ -46,38 +46,6 @@ static void lib80211_crypt_deinit_entries(struct lib80211_crypt_info *info,
 static void lib80211_crypt_quiescing(struct lib80211_crypt_info *info);
 static void lib80211_crypt_deinit_handler(unsigned long data);
 
-const char *print_ssid(char *buf, const char *ssid, u8 ssid_len)
-{
-	const char *s = ssid;
-	char *d = buf;
-
-	ssid_len = min_t(u8, ssid_len, IEEE80211_MAX_SSID_LEN);
-	while (ssid_len--) {
-		if (isprint(*s)) {
-			*d++ = *s++;
-			continue;
-		}
-
-		*d++ = '\\';
-		if (*s == '\0')
-			*d++ = '0';
-		else if (*s == '\n')
-			*d++ = 'n';
-		else if (*s == '\r')
-			*d++ = 'r';
-		else if (*s == '\t')
-			*d++ = 't';
-		else if (*s == '\\')
-			*d++ = '\\';
-		else
-			d += snprintf(d, 3, "%03o", *s);
-		s++;
-	}
-	*d = '\0';
-	return buf;
-}
-EXPORT_SYMBOL(print_ssid);
-
 int lib80211_crypt_info_init(struct lib80211_crypt_info *info, char *name,
 				spinlock_t *lock)
 {
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 8a9a4e1c7eab..65e7b08bb2cc 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -171,13 +171,13 @@ ld-ifversion = $(shell [ $(call ld-version) $(1) $(2) ] && echo $(3))
 # Shorthand for $(Q)$(MAKE) -f scripts/Makefile.build obj=
 # Usage:
 # $(Q)$(MAKE) $(build)=dir
-build := -f $(if $(KBUILD_SRC),$(srctree)/)scripts/Makefile.build obj
+build := -f $(srctree)/scripts/Makefile.build obj
 
 ###
 # Shorthand for $(Q)$(MAKE) -f scripts/Makefile.modbuiltin obj=
 # Usage:
 # $(Q)$(MAKE) $(modbuiltin)=dir
-modbuiltin := -f $(if $(KBUILD_SRC),$(srctree)/)scripts/Makefile.modbuiltin obj
+modbuiltin := -f $(srctree)/scripts/Makefile.modbuiltin obj
 
 # Prefix -I with $(srctree) if it is not an absolute path.
 # skip if -I has no parameter
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index bf3e6778cd71..649ce6844033 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -79,11 +79,11 @@ endif
 
 # ===========================================================================
 
-ifneq ($(strip $(lib-y) $(lib-m) $(lib-n) $(lib-)),)
+ifneq ($(strip $(lib-y) $(lib-m) $(lib-)),)
 lib-target := $(obj)/lib.a
 endif
 
-ifneq ($(strip $(obj-y) $(obj-m) $(obj-n) $(obj-) $(subdir-m) $(lib-target)),)
+ifneq ($(strip $(obj-y) $(obj-m) $(obj-) $(subdir-m) $(lib-target)),)
 builtin-target := $(obj)/built-in.o
 endif
 
@@ -382,16 +382,14 @@ cmd_link_multi-y = $(LD) $(ld_flags) -r -o $@ $(link_multi_deps) $(cmd_secanalys
 quiet_cmd_link_multi-m = LD [M]  $@
 cmd_link_multi-m = $(cmd_link_multi-y)
 
-# We would rather have a list of rules like
-# 	foo.o: $(foo-objs)
-# but that's not so easy, so we rather make all composite objects depend
-# on the set of all their parts
-$(multi-used-y) : %.o: $(multi-objs-y) FORCE
+$(multi-used-y): FORCE
 	$(call if_changed,link_multi-y)
+$(call multi_depend, $(multi-used-y), .o, -objs -y)
 
-$(multi-used-m) : %.o: $(multi-objs-m) FORCE
+$(multi-used-m): FORCE
 	$(call if_changed,link_multi-m)
 	@{ echo $(@:.o=.ko); echo $(link_multi_deps); } > $(MODVERDIR)/$(@F:.o=.mod)
+$(call multi_depend, $(multi-used-m), .o, -objs -y)
 
 targets += $(multi-used-y) $(multi-used-m)
 
diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean
index a651cee84f2a..b1c668dc6815 100644
--- a/scripts/Makefile.clean
+++ b/scripts/Makefile.clean
@@ -10,7 +10,7 @@ __clean:
 # Shorthand for $(Q)$(MAKE) scripts/Makefile.clean obj=dir
 # Usage:
 # $(Q)$(MAKE) $(clean)=dir
-clean := -f $(if $(KBUILD_SRC),$(srctree)/)scripts/Makefile.clean obj
+clean := -f $(srctree)/scripts/Makefile.clean obj
 
 # The filename Kbuild has precedence over Makefile
 kbuild-dir := $(if $(filter /%,$(src)),$(src),$(srctree)/$(src))
@@ -23,15 +23,13 @@ __subdir-y	:= $(patsubst %/,%,$(filter %/, $(obj-y)))
 subdir-y	+= $(__subdir-y)
 __subdir-m	:= $(patsubst %/,%,$(filter %/, $(obj-m)))
 subdir-m	+= $(__subdir-m)
-__subdir-n	:= $(patsubst %/,%,$(filter %/, $(obj-n)))
-subdir-n	+= $(__subdir-n)
 __subdir-	:= $(patsubst %/,%,$(filter %/, $(obj-)))
 subdir-		+= $(__subdir-)
 
 # Subdirectories we need to descend into
 
 subdir-ym	:= $(sort $(subdir-y) $(subdir-m))
-subdir-ymn      := $(sort $(subdir-ym) $(subdir-n) $(subdir-))
+subdir-ymn      := $(sort $(subdir-ym) $(subdir-))
 
 # Add subdir path
 
diff --git a/scripts/Makefile.fwinst b/scripts/Makefile.fwinst
index d8e335eed226..5b698add4f31 100644
--- a/scripts/Makefile.fwinst
+++ b/scripts/Makefile.fwinst
@@ -2,7 +2,7 @@
 # Installing firmware
 #
 # We don't include the .config, so all firmware files are in $(fw-shipped-)
-# rather than in $(fw-shipped-y) or $(fw-shipped-n).
+# rather than in $(fw-shipped-y) or $(fw-shipped-m).
 # ==========================================================================
 
 INSTALL := install
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index ab5980f91714..133edfae5b8a 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -96,8 +96,9 @@ quiet_cmd_host-cmulti	= HOSTLD  $@
       cmd_host-cmulti	= $(HOSTCC) $(HOSTLDFLAGS) -o $@ \
 			  $(addprefix $(obj)/,$($(@F)-objs)) \
 			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
-$(host-cmulti): $(obj)/%: $(host-cobjs) FORCE
+$(host-cmulti): FORCE
 	$(call if_changed,host-cmulti)
+$(call multi_depend, $(host-cmulti), , -objs)
 
 # Create .o file from a single .c file
 # host-cobjs -> .o
@@ -113,8 +114,9 @@ quiet_cmd_host-cxxmulti	= HOSTLD  $@
 			  $(foreach o,objs cxxobjs,\
 			  $(addprefix $(obj)/,$($(@F)-$(o)))) \
 			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
-$(host-cxxmulti): $(obj)/%: $(host-cobjs) $(host-cxxobjs) FORCE
+$(host-cxxmulti): FORCE
 	$(call if_changed,host-cxxmulti)
+$(call multi_depend, $(host-cxxmulti), , -objs -cxxobjs)
 
 # Create .o file from a single .cc (C++) file
 quiet_cmd_host-cxxobjs	= HOSTCXX $@
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 260bf8acfce9..54be19a0fa51 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -159,6 +159,15 @@ dtc_cpp_flags  = -Wp,-MD,$(depfile).pre.tmp -nostdinc                    \
 modname-multi = $(sort $(foreach m,$(multi-used),\
 		$(if $(filter $(subst $(obj)/,,$*.o), $($(m:.o=-objs)) $($(m:.o=-y))),$(m:.o=))))
 
+# Useful for describing the dependency of composite objects
+# Usage:
+#   $(call multi_depend, multi_used_targets, suffix_to_remove, suffix_to_add)
+define multi_depend
+$(foreach m, $(notdir $1), \
+	$(eval $(obj)/$m: \
+	$(addprefix $(obj)/, $(foreach s, $3, $($(m:%$(strip $2)=%$(s)))))))
+endef
+
 ifdef REGENERATE_PARSERS
 
 # GPERF
diff --git a/scripts/bootgraph.pl b/scripts/bootgraph.pl
index 9ca667bcaee9..9ca667bcaee9 100644..100755
--- a/scripts/bootgraph.pl
+++ b/scripts/bootgraph.pl
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 4d08b398411f..374abf443636 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -9,7 +9,8 @@ use strict;
 use POSIX;
 
 my $P = $0;
-$P =~ s@.*/@@g;
+$P =~ s@(.*)/@@g;
+my $D = $1;
 
 my $V = '0.32';
 
@@ -43,6 +44,8 @@ my $configuration_file = ".checkpatch.conf";
 my $max_line_length = 80;
 my $ignore_perl_version = 0;
 my $minimum_perl_version = 5.10.0;
+my $min_conf_desc_length = 4;
+my $spelling_file = "$D/spelling.txt";
 
 sub help {
 	my ($exitcode) = @_;
@@ -63,6 +66,7 @@ Options:
   --types TYPE(,TYPE2...)    show only these comma separated message types
   --ignore TYPE(,TYPE2...)   ignore various comma separated message types
   --max-line-length=n        set the maximum line length, if exceeded, warn
+  --min-conf-desc-length=n   set the min description length, if shorter, warn
   --show-types               show the message "types" in the output
   --root=PATH                PATH to the kernel tree root
   --no-summary               suppress the per-file summary
@@ -131,6 +135,7 @@ GetOptions(
 	'types=s'	=> \@use,
 	'show-types!'	=> \$show_types,
 	'max-line-length=i' => \$max_line_length,
+	'min-conf-desc-length=i' => \$min_conf_desc_length,
 	'root=s'	=> \$root,
 	'summary!'	=> \$summary,
 	'mailback!'	=> \$mailback,
@@ -425,10 +430,35 @@ foreach my $entry (@mode_permission_funcs) {
 
 our $allowed_asm_includes = qr{(?x:
 	irq|
-	memory
+	memory|
+	time|
+	reboot
 )};
 # memory.h: ARM has a custom one
 
+# Load common spelling mistakes and build regular expression list.
+my $misspellings;
+my @spelling_list;
+my %spelling_fix;
+open(my $spelling, '<', $spelling_file)
+    or die "$P: Can't open $spelling_file for reading: $!\n";
+while (<$spelling>) {
+	my $line = $_;
+
+	$line =~ s/\s*\n?$//g;
+	$line =~ s/^\s*//g;
+
+	next if ($line =~ m/^\s*#/);
+	next if ($line =~ m/^\s*$/);
+
+	my ($suspect, $fix) = split(/\|\|/, $line);
+
+	push(@spelling_list, $suspect);
+	$spelling_fix{$suspect} = $fix;
+}
+close($spelling);
+$misspellings = join("|", @spelling_list);
+
 sub build_types {
 	my $mods = "(?x:  \n" . join("|\n  ", @modifierList) . "\n)";
 	my $all = "(?x:  \n" . join("|\n  ", @typeList) . "\n)";
@@ -2215,6 +2245,23 @@ sub process {
 			    "8-bit UTF-8 used in possible commit log\n" . $herecurr);
 		}
 
+# Check for various typo / spelling mistakes
+		if ($in_commit_log || $line =~ /^\+/) {
+			while ($rawline =~ /(?:^|[^a-z@])($misspellings)(?:$|[^a-z@])/gi) {
+				my $typo = $1;
+				my $typo_fix = $spelling_fix{lc($typo)};
+				$typo_fix = ucfirst($typo_fix) if ($typo =~ /^[A-Z]/);
+				$typo_fix = uc($typo_fix) if ($typo =~ /^[A-Z]+$/);
+				my $msg_type = \&WARN;
+				$msg_type = \&CHK if ($file);
+				if (&{$msg_type}("TYPO_SPELLING",
+						 "'$typo' may be misspelled - perhaps '$typo_fix'?\n" . $herecurr) &&
+				    $fix) {
+					$fixed[$fixlinenr] =~ s/(^|[^A-Za-z@])($typo)($|[^A-Za-z@])/$1$typo_fix$3/;
+				}
+			}
+		}
+
 # ignore non-hunk lines and lines being removed
 		next if (!$hunk_line || $line =~ /^-/);
 
@@ -2283,8 +2330,10 @@ sub process {
 				}
 				$length++;
 			}
-			WARN("CONFIG_DESCRIPTION",
-			     "please write a paragraph that describes the config symbol fully\n" . $herecurr) if ($is_start && $is_end && $length < 4);
+			if ($is_start && $is_end && $length < $min_conf_desc_length) {
+				WARN("CONFIG_DESCRIPTION",
+				     "please write a paragraph that describes the config symbol fully\n" . $herecurr);
+			}
 			#print "is_start<$is_start> is_end<$is_end> length<$length>\n";
 		}
 
@@ -2341,7 +2390,7 @@ sub process {
 		}
 
 # check we are in a valid source file if not then ignore this hunk
-		next if ($realfile !~ /\.(h|c|s|S|pl|sh)$/);
+		next if ($realfile !~ /\.(h|c|s|S|pl|sh|dtsi|dts)$/);
 
 #line length limit
 		if ($line =~ /^\+/ && $prevrawline !~ /\/\*\*/ &&
@@ -2402,7 +2451,7 @@ sub process {
 		}
 
 # check we are in a valid source file C or perl if not then ignore this hunk
-		next if ($realfile !~ /\.(h|c|pl)$/);
+		next if ($realfile !~ /\.(h|c|pl|dtsi|dts)$/);
 
 # at the beginning of a line any tabs must come first and anything
 # more than 8 must use tabs.
@@ -2424,7 +2473,7 @@ sub process {
 				"please, no space before tabs\n" . $herevet) &&
 			    $fix) {
 				while ($fixed[$fixlinenr] =~
-					   s/(^\+.*) {8,8}+\t/$1\t\t/) {}
+					   s/(^\+.*) {8,8}\t/$1\t\t/) {}
 				while ($fixed[$fixlinenr] =~
 					   s/(^\+.*) +\t/$1\t/) {}
 			}
@@ -2592,10 +2641,14 @@ sub process {
 		next if ($realfile !~ /\.(h|c)$/);
 
 # check indentation of any line with a bare else
+# (but not if it is a multiple line "if (foo) return bar; else return baz;")
 # if the previous line is a break or return and is indented 1 tab more...
 		if ($sline =~ /^\+([\t]+)(?:}[ \t]*)?else(?:[ \t]*{)?\s*$/) {
 			my $tabs = length($1) + 1;
-			if ($prevline =~ /^\+\t{$tabs,$tabs}(?:break|return)\b/) {
+			if ($prevline =~ /^\+\t{$tabs,$tabs}break\b/ ||
+			    ($prevline =~ /^\+\t{$tabs,$tabs}return\b/ &&
+			     defined $lines[$linenr] &&
+			     $lines[$linenr] !~ /^[ \+]\t{$tabs,$tabs}return/)) {
 				WARN("UNNECESSARY_ELSE",
 				     "else is not generally useful after a break or return\n" . $hereprev);
 			}
@@ -3752,7 +3805,6 @@ sub process {
 			if (ERROR("SPACING",
 				  "space prohibited before that close parenthesis ')'\n" . $herecurr) &&
 			    $fix) {
-				print("fixlinenr: <$fixlinenr> fixed[fixlinenr]: <$fixed[$fixlinenr]>\n");
 				$fixed[$fixlinenr] =~
 				    s/\s+\)/\)/;
 			}
@@ -4060,12 +4112,17 @@ sub process {
 			my $cnt = $realcnt;
 			my ($off, $dstat, $dcond, $rest);
 			my $ctx = '';
+			my $has_flow_statement = 0;
+			my $has_arg_concat = 0;
 			($dstat, $dcond, $ln, $cnt, $off) =
 				ctx_statement_block($linenr, $realcnt, 0);
 			$ctx = $dstat;
 			#print "dstat<$dstat> dcond<$dcond> cnt<$cnt> off<$off>\n";
 			#print "LINE<$lines[$ln-1]> len<" . length($lines[$ln-1]) . "\n";
 
+			$has_flow_statement = 1 if ($ctx =~ /\b(goto|return)\b/);
+			$has_arg_concat = 1 if ($ctx =~ /\#\#/);
+
 			$dstat =~ s/^.\s*\#\s*define\s+$Ident(?:\([^\)]*\))?\s*//;
 			$dstat =~ s/$;//g;
 			$dstat =~ s/\\\n.//g;
@@ -4126,10 +4183,23 @@ sub process {
 					      "Macros with multiple statements should be enclosed in a do - while loop\n" . "$herectx");
 				} else {
 					ERROR("COMPLEX_MACRO",
-					      "Macros with complex values should be enclosed in parenthesis\n" . "$herectx");
+					      "Macros with complex values should be enclosed in parentheses\n" . "$herectx");
 				}
 			}
 
+# check for macros with flow control, but without ## concatenation
+# ## concatenation is commonly a macro that defines a function so ignore those
+			if ($has_flow_statement && !$has_arg_concat) {
+				my $herectx = $here . "\n";
+				my $cnt = statement_rawlines($ctx);
+
+				for (my $n = 0; $n < $cnt; $n++) {
+					$herectx .= raw_line($linenr, $n) . "\n";
+				}
+				WARN("MACRO_WITH_FLOW_CONTROL",
+				     "Macros with flow control statements should be avoided\n" . "$herectx");
+			}
+
 # check for line continuations outside of #defines, preprocessor #, and asm
 
 		} else {
@@ -4338,6 +4408,12 @@ sub process {
 			     "Use of volatile is usually wrong: see Documentation/volatile-considered-harmful.txt\n" . $herecurr);
 		}
 
+# concatenated string without spaces between elements
+		if ($line =~ /"X+"[A-Z_]+/ || $line =~ /[A-Z_]+"X+"/) {
+			CHK("CONCATENATED_STRING",
+			    "Concatenated strings should use spaces between elements\n" . $herecurr);
+		}
+
 # warn about #if 0
 		if ($line =~ /^.\s*\#\s*if\s+0\b/) {
 			CHK("REDUNDANT_CODE",
@@ -4371,6 +4447,17 @@ sub process {
 			}
 		}
 
+# check for logging functions with KERN_<LEVEL>
+		if ($line !~ /printk\s*\(/ &&
+		    $line =~ /\b$logFunctions\s*\(.*\b(KERN_[A-Z]+)\b/) {
+			my $level = $1;
+			if (WARN("UNNECESSARY_KERN_LEVEL",
+				 "Possible unnecessary $level\n" . $herecurr) &&
+			    $fix) {
+				$fixed[$fixlinenr] =~ s/\s*$level\s*//;
+			}
+		}
+
 # check for bad placement of section $InitAttribute (e.g.: __initdata)
 		if ($line =~ /(\b$InitAttribute\b)/) {
 			my $attr = $1;
diff --git a/scripts/coccinelle/misc/simple_return.cocci b/scripts/coccinelle/misc/simple_return.cocci
new file mode 100644
index 000000000000..47f7084b6360
--- /dev/null
+++ b/scripts/coccinelle/misc/simple_return.cocci
@@ -0,0 +1,180 @@
+/// Simplify a trivial if-return sequence.  Possibly combine with a
+/// preceding function call.
+//
+// Confidence: High
+// Copyright: (C) 2014 Julia Lawall, INRIA/LIP6.  GPLv2.
+// Copyright: (C) 2014 Gilles Muller, INRIA/LiP6.  GPLv2.
+// URL: http://coccinelle.lip6.fr/
+// Comments:
+// Options: --no-includes --include-headers
+
+virtual patch
+virtual context
+virtual org
+virtual report
+
+@r depends on patch@
+local idexpression e;
+identifier i,f,fn;
+@@
+
+fn(...) { <...
+- e@i =
++ return
+    f(...);
+-if (i != 0) return i;
+-return 0;
+...> }
+
+@depends on patch@
+identifier r.i;
+type t;
+@@
+
+-t i;
+ ... when != i
+
+@depends on patch@
+expression e;
+@@
+
+-if (e != 0)
+   return e;
+-return 0;
+
+// -----------------------------------------------------------------------
+
+@s1 depends on context || org || report@
+local idexpression e;
+identifier i,f,fn;
+position p,p1,p2;
+@@
+
+fn(...) { <...
+* e@i@p = f(...);
+  if (\(i@p1 != 0\|i@p2 < 0\))
+     return i;
+  return 0;
+...> }
+
+@s2 depends on context || org || report forall@
+identifier s1.i;
+type t;
+position q,s1.p;
+expression e,f;
+@@
+
+* t i@q;
+  ... when != i
+  e@p = f(...);
+
+@s3 depends on context || org || report@
+expression e;
+position p1!=s1.p1;
+position p2!=s1.p2;
+@@
+
+*if (\(e@p1 != 0\|e@p2 < 0\))
+   return e;
+ return 0;
+
+// -----------------------------------------------------------------------
+
+@script:python depends on org@
+p << s1.p;
+p1 << s1.p1;
+q << s2.q;
+@@
+
+cocci.print_main("decl",q)
+cocci.print_secs("use",p)
+cocci.include_match(False)
+
+@script:python depends on org@
+p << s1.p;
+p2 << s1.p2;
+q << s2.q;
+@@
+
+cocci.print_main("decl",q)
+cocci.print_secs("use with questionable test",p)
+cocci.include_match(False)
+
+@script:python depends on org@
+p << s1.p;
+p1 << s1.p1;
+@@
+
+cocci.print_main("use",p)
+
+@script:python depends on org@
+p << s1.p;
+p2 << s1.p2;
+@@
+
+cocci.print_main("use with questionable test",p)
+
+@script:python depends on org@
+p << s3.p1;
+@@
+
+cocci.print_main("test",p)
+
+@script:python depends on org@
+p << s3.p2;
+@@
+
+cocci.print_main("questionable test",p)
+
+// -----------------------------------------------------------------------
+
+@script:python depends on report@
+p << s1.p;
+p1 << s1.p1;
+q << s2.q;
+@@
+
+msg = "WARNING: end returns can be simpified and declaration on line %s can be dropped" % (q[0].line)
+coccilib.report.print_report(p[0],msg)
+cocci.include_match(False)
+
+@script:python depends on report@
+p << s1.p;
+p1 << s1.p1;
+q << s2.q
+;
+@@
+
+msg = "WARNING: end returns may be simpified if negative or 0 value and declaration on line %s can be dropped" % (q[0].line)
+coccilib.report.print_report(p[0],msg)
+cocci.include_match(False)
+
+@script:python depends on report@
+p << s1.p;
+p1 << s1.p1;
+@@
+
+msg = "WARNING: end returns can be simpified"
+coccilib.report.print_report(p[0],msg)
+
+@script:python depends on report@
+p << s1.p;
+p2 << s1.p2;
+@@
+
+msg = "WARNING: end returns can be simpified if negative or 0 value"
+coccilib.report.print_report(p[0],msg)
+
+@script:python depends on report@
+p << s3.p1;
+@@
+
+msg = "WARNING: end returns can be simpified"
+coccilib.report.print_report(p[0],msg)
+
+@script:python depends on report@
+p << s3.p2;
+@@
+
+msg = "WARNING: end returns can be simpified if tested value is negative or 0"
+coccilib.report.print_report(p[0],msg)
diff --git a/scripts/export_report.pl b/scripts/export_report.pl
index 8f79b701de87..8f79b701de87 100644..100755
--- a/scripts/export_report.pl
+++ b/scripts/export_report.pl
diff --git a/scripts/gcc-goto.sh b/scripts/gcc-goto.sh
index c9469d34ecc6..c9469d34ecc6 100644..100755
--- a/scripts/gcc-goto.sh
+++ b/scripts/gcc-goto.sh
diff --git a/scripts/gcc-ld b/scripts/gcc-ld
index cadab9a13ed7..cadab9a13ed7 100644..100755
--- a/scripts/gcc-ld
+++ b/scripts/gcc-ld
diff --git a/scripts/gcc-version.sh b/scripts/gcc-version.sh
index 7f2126df91f2..7f2126df91f2 100644..100755
--- a/scripts/gcc-version.sh
+++ b/scripts/gcc-version.sh
diff --git a/scripts/gcc-x86_32-has-stack-protector.sh b/scripts/gcc-x86_32-has-stack-protector.sh
index 12dbd0b11ea4..12dbd0b11ea4 100644..100755
--- a/scripts/gcc-x86_32-has-stack-protector.sh
+++ b/scripts/gcc-x86_32-has-stack-protector.sh
diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh
index 973e8c141567..973e8c141567 100644..100755
--- a/scripts/gcc-x86_64-has-stack-protector.sh
+++ b/scripts/gcc-x86_64-has-stack-protector.sh
diff --git a/scripts/gen_initramfs_list.sh b/scripts/gen_initramfs_list.sh
index 17fa901418ae..17fa901418ae 100644..100755
--- a/scripts/gen_initramfs_list.sh
+++ b/scripts/gen_initramfs_list.sh
diff --git a/scripts/headers_check.pl b/scripts/headers_check.pl
index 62320f93e903..62320f93e903 100644..100755
--- a/scripts/headers_check.pl
+++ b/scripts/headers_check.pl
diff --git a/scripts/headers_install.sh b/scripts/headers_install.sh
index 5de5660cb708..fdebd66f8fc1 100644..100755
--- a/scripts/headers_install.sh
+++ b/scripts/headers_install.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-if [ $# -lt 1 ]
+if [ $# -lt 2 ]
 then
-	echo "Usage: headers_install.sh OUTDIR SRCDIR [FILES...]
+	echo "Usage: headers_install.sh OUTDIR SRCDIR [FILES...]"
 	echo
 	echo "Prepares kernel header files for use by user space, by removing"
 	echo "all compiler.h definitions and #includes, removing any"
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index ebf40f6edb4d..9645c0739386 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -176,39 +176,10 @@ qconf-cxxobjs	:= qconf.o
 qconf-objs	:= zconf.tab.o
 gconf-objs	:= gconf.o zconf.tab.o
 
-hostprogs-y := conf
-
-ifeq ($(MAKECMDGOALS),nconfig)
-	hostprogs-y += nconf
-endif
-
-ifeq ($(MAKECMDGOALS),menuconfig)
-	hostprogs-y += mconf
-endif
-
-ifeq ($(MAKECMDGOALS),update-po-config)
-	hostprogs-y += kxgettext
-endif
-
-ifeq ($(MAKECMDGOALS),xconfig)
-	qconf-target := 1
-endif
-ifeq ($(MAKECMDGOALS),gconfig)
-	gconf-target := 1
-endif
-
-
-ifeq ($(qconf-target),1)
-	hostprogs-y += qconf
-endif
-
-ifeq ($(gconf-target),1)
-	hostprogs-y += gconf
-endif
+hostprogs-y := conf nconf mconf kxgettext qconf gconf
 
 clean-files	:= qconf.moc .tmp_qtcheck .tmp_gtkcheck
 clean-files	+= zconf.tab.c zconf.lex.c zconf.hash.c gconf.glade.h
-clean-files     += mconf qconf gconf nconf
 clean-files     += config.pot linux.pot
 
 # Check that we have the required ncurses stuff installed for lxdialog (menuconfig)
@@ -239,11 +210,12 @@ HOSTCFLAGS_gconf.o	= `pkg-config --cflags gtk+-2.0 gmodule-2.0 libglade-2.0` \
 HOSTLOADLIBES_mconf   = $(shell $(CONFIG_SHELL) $(check-lxdialog) -ldflags $(HOSTCC))
 
 HOSTLOADLIBES_nconf	= $(shell \
-				pkg-config --libs menu panel ncurses 2>/dev/null \
+				pkg-config --libs menuw panelw ncursesw 2>/dev/null \
+				|| pkg-config --libs menu panel ncurses 2>/dev/null \
 				|| echo "-lmenu -lpanel -lncurses"  )
 $(obj)/qconf.o: $(obj)/.tmp_qtcheck
 
-ifeq ($(qconf-target),1)
+ifeq ($(MAKECMDGOALS),xconfig)
 $(obj)/.tmp_qtcheck: $(src)/Makefile
 -include $(obj)/.tmp_qtcheck
 
@@ -300,7 +272,7 @@ endif
 
 $(obj)/gconf.o: $(obj)/.tmp_gtkcheck
 
-ifeq ($(gconf-target),1)
+ifeq ($(MAKECMDGOALS),gconfig)
 -include $(obj)/.tmp_gtkcheck
 
 # GTK needs some extra effort, too...
diff --git a/scripts/kconfig/lxdialog/check-lxdialog.sh b/scripts/kconfig/lxdialog/check-lxdialog.sh
index 9d2a4c585ee1..5075ebf2d3b9 100644..100755
--- a/scripts/kconfig/lxdialog/check-lxdialog.sh
+++ b/scripts/kconfig/lxdialog/check-lxdialog.sh
@@ -21,7 +21,11 @@ ldflags()
 # Where is ncurses.h?
 ccflags()
 {
-	if [ -f /usr/include/ncursesw/curses.h ]; then
+	if pkg-config --cflags ncursesw 2>/dev/null; then
+		echo '-DCURSES_LOC="<ncurses.h>" -DNCURSES_WIDECHAR=1'
+	elif pkg-config --cflags ncurses 2>/dev/null; then
+		echo '-DCURSES_LOC="<ncurses.h>"'
+	elif [ -f /usr/include/ncursesw/curses.h ]; then
 		echo '-I/usr/include/ncursesw -DCURSES_LOC="<curses.h>"'
 		echo ' -DNCURSES_WIDECHAR=1'
 	elif [ -f /usr/include/ncurses/ncurses.h ]; then
diff --git a/scripts/kconfig/lxdialog/dialog.h b/scripts/kconfig/lxdialog/dialog.h
index b4343d384926..fcffd5b41fb0 100644
--- a/scripts/kconfig/lxdialog/dialog.h
+++ b/scripts/kconfig/lxdialog/dialog.h
@@ -170,7 +170,7 @@ char item_tag(void);
 /* item list manipulation for lxdialog use */
 #define MAXITEMSTR 200
 struct dialog_item {
-	char str[MAXITEMSTR];	/* promtp displayed */
+	char str[MAXITEMSTR];	/* prompt displayed */
 	char tag;
 	void *data;	/* pointer to menu item - used by menubox+checklist */
 	int selected;	/* Set to 1 by dialog_*() function if selected. */
diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl
index 9cb8522d8d22..9cb8522d8d22 100644..100755
--- a/scripts/kconfig/streamline_config.pl
+++ b/scripts/kconfig/streamline_config.pl
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 86a4fe75f453..86a4fe75f453 100644..100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
diff --git a/scripts/markup_oops.pl b/scripts/markup_oops.pl
index c21d16328d3f..c21d16328d3f 100644..100755
--- a/scripts/markup_oops.pl
+++ b/scripts/markup_oops.pl
diff --git a/scripts/mkmakefile b/scripts/mkmakefile
index 84af27bf0f99..84af27bf0f99 100644..100755
--- a/scripts/mkmakefile
+++ b/scripts/mkmakefile
diff --git a/scripts/mksysmap b/scripts/mksysmap
index 7ada35a0f478..7ada35a0f478 100644..100755
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index 35d5a5877d04..59726243c2eb 100644..100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -37,7 +37,7 @@ create_package() {
 	s390*)
 		debarch=s390$(grep -q CONFIG_64BIT=y $KCONFIG_CONFIG && echo x || true) ;;
 	ppc*)
-		debarch=powerpc ;;
+		debarch=$(grep -q CPU_LITTLE_ENDIAN=y $KCONFIG_CONFIG && echo ppc64el || echo powerpc) ;;
 	parisc*)
 		debarch=hppa ;;
 	mips*)
@@ -64,7 +64,7 @@ create_package() {
 	fi
 
 	# Create the package
-	dpkg-gencontrol -isp $forcearch -Vkernel:debarch="${debarch:-$(dpkg --print-architecture)}" -p$pname -P"$pdir"
+	dpkg-gencontrol $forcearch -Vkernel:debarch="${debarch:-$(dpkg --print-architecture)}" -p$pname -P"$pdir"
 	dpkg --build "$pdir" ..
 }
 
@@ -152,18 +152,16 @@ if grep -q '^CONFIG_MODULES=y' $KCONFIG_CONFIG ; then
 		rmdir "$tmpdir/lib/modules/$version"
 	fi
 	if [ -n "$BUILD_DEBUG" ] ; then
-		(
-			cd $tmpdir
-			for module in $(find lib/modules/ -name *.ko); do
-				mkdir -p $(dirname $dbg_dir/usr/lib/debug/$module)
-				# only keep debug symbols in the debug file
-				$OBJCOPY --only-keep-debug $module $dbg_dir/usr/lib/debug/$module
-				# strip original module from debug symbols
-				$OBJCOPY --strip-debug $module
-				# then add a link to those
-				$OBJCOPY --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $module
-			done
-		)
+		for module in $(find $tmpdir/lib/modules/ -name *.ko -printf '%P\n'); do
+			module=lib/modules/$module
+			mkdir -p $(dirname $dbg_dir/usr/lib/debug/$module)
+			# only keep debug symbols in the debug file
+			$OBJCOPY --only-keep-debug $tmpdir/$module $dbg_dir/usr/lib/debug/$module
+			# strip original module from debug symbols
+			$OBJCOPY --strip-debug $tmpdir/$module
+			# then add a link to those
+			$OBJCOPY --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $tmpdir/$module
+		done
 	fi
 fi
 
diff --git a/scripts/package/buildtar b/scripts/package/buildtar
index e046bff33589..e046bff33589 100644..100755
--- a/scripts/package/buildtar
+++ b/scripts/package/buildtar
diff --git a/scripts/profile2linkerlist.pl b/scripts/profile2linkerlist.pl
index 6943fa7cc95b..6943fa7cc95b 100644..100755
--- a/scripts/profile2linkerlist.pl
+++ b/scripts/profile2linkerlist.pl
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 650ecc83d7d7..001facfa5b74 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -388,10 +388,6 @@ do_file(char const *const fname)
 				"unrecognized ET_REL file: %s\n", fname);
 			fail_file();
 		}
-		if (w2(ehdr->e_machine) == EM_S390) {
-			reltype = R_390_32;
-			mcount_adjust_32 = -4;
-		}
 		if (w2(ehdr->e_machine) == EM_MIPS) {
 			reltype = R_MIPS_32;
 			is_fake_mcount32 = MIPS32_is_fake_mcount;
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 397b6b84e8c5..d4b665610d67 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -241,13 +241,6 @@ if ($arch eq "x86_64") {
     $objcopy .= " -O elf32-i386";
     $cc .= " -m32";
 
-} elsif ($arch eq "s390" && $bits == 32) {
-    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_390_32\\s+_mcount\$";
-    $mcount_adjust = -4;
-    $alignment = 4;
-    $ld .= " -m elf_s390";
-    $cc .= " -m31";
-
 } elsif ($arch eq "s390" && $bits == 64) {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_390_(PC|PLT)32DBL\\s+_mcount\\+0x2\$";
     $mcount_adjust = -8;
diff --git a/scripts/rt-tester/rt-tester.py b/scripts/rt-tester/rt-tester.py
index 6d916c2a45a5..6d916c2a45a5 100644..100755
--- a/scripts/rt-tester/rt-tester.py
+++ b/scripts/rt-tester/rt-tester.py
diff --git a/scripts/selinux/install_policy.sh b/scripts/selinux/install_policy.sh
index f6a0ce71015f..f6a0ce71015f 100644..100755
--- a/scripts/selinux/install_policy.sh
+++ b/scripts/selinux/install_policy.sh
diff --git a/scripts/sortextable.h b/scripts/sortextable.h
index 8fac3fd697a6..ba8700428e21 100644
--- a/scripts/sortextable.h
+++ b/scripts/sortextable.h
@@ -103,7 +103,7 @@ do_func(Elf_Ehdr *ehdr, char const *const fname, table_sort_t custom_sort)
 	Elf_Sym *sort_needed_sym;
 	Elf_Shdr *sort_needed_sec;
 	Elf_Rel *relocs = NULL;
-	int relocs_size;
+	int relocs_size = 0;
 	uint32_t *sort_done_location;
 	const char *secstrtab;
 	const char *strtab;
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
new file mode 100644
index 000000000000..fc7fd52b5e03
--- /dev/null
+++ b/scripts/spelling.txt
@@ -0,0 +1,1042 @@
+# Originally from Debian's Lintian tool. Various false positives have been
+# removed, and various additions have been made as they've been discovered
+# in the kernel source.
+#
+# License: GPLv2
+#
+# The format of each line is:
+# mistake||correction
+#
+abandonning||abandoning
+abigious||ambiguous
+abitrate||arbitrate
+abov||above
+abreviated||abbreviated
+absense||absence
+absolut||absolute
+absoulte||absolute
+acccess||access
+acceleratoin||acceleration
+accelleration||acceleration
+accesing||accessing
+accesnt||accent
+accessable||accessible
+accesss||access
+accidentaly||accidentally
+accidentually||accidentally
+accoding||according
+accomodate||accommodate
+accomodates||accommodates
+accordign||according
+accoring||according
+accout||account
+accquire||acquire
+accquired||acquired
+acessable||accessible
+acess||access
+achitecture||architecture
+acient||ancient
+acitions||actions
+acitve||active
+acknowldegement||acknowldegement
+acknowledgement||acknowledgment
+ackowledge||acknowledge
+ackowledged||acknowledged
+acording||according
+activete||activate
+acumulating||accumulating
+adapater||adapter
+addional||additional
+additionaly||additionally
+addres||address
+addreses||addresses
+addresss||address
+aditional||additional
+aditionally||additionally
+aditionaly||additionally
+adminstrative||administrative
+adress||address
+adresses||addresses
+adviced||advised
+afecting||affecting
+agaist||against
+albumns||albums
+alegorical||allegorical
+algorith||algorithm
+algorithmical||algorithmically
+algoritm||algorithm
+algoritms||algorithms
+algorrithm||algorithm
+algorritm||algorithm
+allign||align
+allocatrd||allocated
+allocte||allocate
+allpication||application
+alocate||allocate
+alogirhtms||algorithms
+alogrithm||algorithm
+alot||a lot
+alow||allow
+alows||allows
+altough||although
+alue||value
+ambigious||ambiguous
+amoung||among
+amout||amount
+analysator||analyzer
+ang||and
+anniversery||anniversary
+annoucement||announcement
+anomolies||anomalies
+anomoly||anomaly
+anway||anyway
+aplication||application
+appearence||appearance
+applicaion||application
+appliction||application
+applictions||applications
+appplications||applications
+appropiate||appropriate
+appropriatly||appropriately
+approriate||appropriate
+approriately||appropriately
+aquainted||acquainted
+aquired||acquired
+arbitary||arbitrary
+architechture||architecture
+arguement||argument
+arguements||arguments
+aritmetic||arithmetic
+arne't||aren't
+arraival||arrival
+artifical||artificial
+artillary||artillery
+assiged||assigned
+assigment||assignment
+assigments||assignments
+assistent||assistant
+assocation||association
+associcated||associated
+assotiated||associated
+assum||assume
+assumtpion||assumption
+asuming||assuming
+asycronous||asynchronous
+asynchnous||asynchronous
+atomatically||automatically
+atomicly||atomically
+attachement||attachment
+attched||attached
+attemps||attempts
+attruibutes||attributes
+authentification||authentication
+automaticaly||automatically
+automaticly||automatically
+automatize||automate
+automatized||automated
+automatizes||automates
+autonymous||autonomous
+auxilliary||auxiliary
+avaiable||available
+avaible||available
+availabe||available
+availabled||available
+availablity||availability
+availale||available
+availavility||availability
+availble||available
+availiable||available
+avalable||available
+avaliable||available
+aysnc||async
+backgroud||background
+backword||backward
+backwords||backwards
+bahavior||behavior
+bakup||backup
+baloon||balloon
+baloons||balloons
+bandwith||bandwidth
+batery||battery
+beacuse||because
+becasue||because
+becomming||becoming
+becuase||because
+beeing||being
+befor||before
+begining||beginning
+beter||better
+betweeen||between
+bianries||binaries
+bitmast||bitmask
+boardcast||broadcast
+borad||board
+boundry||boundary
+brievely||briefly
+broadcat||broadcast
+cacluated||calculated
+caculation||calculation
+calender||calendar
+calle||called
+calucate||calculate
+calulate||calculate
+cancelation||cancellation
+capabilites||capabilities
+capabitilies||capabilities
+capatibilities||capabilities
+carefuly||carefully
+cariage||carriage
+catagory||category
+challange||challenge
+challanges||challenges
+chanell||channel
+changable||changeable
+channle||channel
+channnel||channel
+charachter||character
+charachters||characters
+charactor||character
+charater||character
+charaters||characters
+charcter||character
+checksuming||checksumming
+childern||children
+childs||children
+chiled||child
+chked||checked
+chnage||change
+chnages||changes
+chnnel||channel
+choosen||chosen
+chouse||chose
+circumvernt||circumvent
+claread||cleared
+clared||cleared
+closeing||closing
+clustred||clustered
+collapsable||collapsible
+colorfull||colorful
+comand||command
+comit||commit
+commerical||commercial
+comming||coming
+comminucation||communication
+commited||committed
+commiting||committing
+committ||commit
+commoditiy||commodity
+compability||compatibility
+compaibility||compatibility
+compatability||compatibility
+compatable||compatible
+compatibiliy||compatibility
+compatibilty||compatibility
+compilant||compliant
+compleatly||completely
+completly||completely
+complient||compliant
+componnents||components
+compres||compress
+compresion||compression
+comression||compression
+comunication||communication
+conbination||combination
+conditionaly||conditionally
+conected||connected
+configuratoin||configuration
+configuraton||configuration
+configuretion||configuration
+conider||consider
+conjuction||conjunction
+connectinos||connections
+connnection||connection
+connnections||connections
+consistancy||consistency
+consistant||consistent
+containes||contains
+containts||contains
+contaisn||contains
+contant||contact
+contence||contents
+continous||continuous
+continously||continuously
+continueing||continuing
+contraints||constraints
+controled||controlled
+controler||controller
+controll||control
+contruction||construction
+contry||country
+convertion||conversion
+convertor||converter
+convienient||convenient
+convinient||convenient
+corected||corrected
+correponding||corresponding
+correponds||corresponds
+correspoding||corresponding
+cotrol||control
+couter||counter
+coutner||counter
+cryptocraphic||cryptographic
+cunter||counter
+curently||currently
+dafault||default
+deafult||default
+deamon||daemon
+decompres||decompress
+decription||description
+defailt||default
+defferred||deferred
+definate||definite
+definately||definitely
+defintion||definition
+defualt||default
+defult||default
+deivce||device
+delared||declared
+delare||declare
+delares||declares
+delaring||declaring
+delemiter||delimiter
+dependancies||dependencies
+dependancy||dependency
+dependant||dependent
+depreacted||deprecated
+depreacte||deprecate
+desactivate||deactivate
+desciptors||descriptors
+descrition||description
+descritptor||descriptor
+desctiptor||descriptor
+desriptor||descriptor
+desriptors||descriptors
+destory||destroy
+destoryed||destroyed
+destorys||destroys
+destroied||destroyed
+detabase||database
+develope||develop
+developement||development
+developped||developed
+developpement||development
+developper||developer
+developpment||development
+deveolpment||development
+devided||divided
+deviece||device
+diable||disable
+dictionnary||dictionary
+diferent||different
+differrence||difference
+difinition||definition
+diplay||display
+direectly||directly
+disapear||disappear
+disapeared||disappeared
+disappared||disappeared
+disconnet||disconnect
+discontinous||discontinuous
+dispertion||dispersion
+dissapears||disappears
+distiction||distinction
+docuentation||documentation
+documantation||documentation
+documentaion||documentation
+documment||document
+dorp||drop
+dosen||doesn
+downlad||download
+downlads||downloads
+druing||during
+dynmaic||dynamic
+easilly||easily
+ecspecially||especially
+edditable||editable
+editting||editing
+efficently||efficiently
+ehther||ether
+eigth||eight
+eletronic||electronic
+enabledi||enabled
+enchanced||enhanced
+encorporating||incorporating
+encrupted||encrypted
+encrypiton||encryption
+endianess||endianness
+enhaced||enhanced
+enlightnment||enlightenment
+enocded||encoded
+enterily||entirely
+enviroiment||environment
+enviroment||environment
+environement||environment
+environent||environment
+eqivalent||equivalent
+equiped||equipped
+equivelant||equivalent
+equivilant||equivalent
+eror||error
+estbalishment||establishment
+etsablishment||establishment
+etsbalishment||establishment
+excecutable||executable
+exceded||exceeded
+excellant||excellent
+existance||existence
+existant||existent
+exixt||exist
+exlcude||exclude
+exlcusive||exclusive
+exmaple||example
+expecially||especially
+explicite||explicit
+explicitely||explicitly
+explict||explicit
+explictly||explicitly
+expresion||expression
+exprimental||experimental
+extened||extended
+extensability||extensibility
+extention||extension
+extracter||extractor
+faild||failed
+faill||fail
+failue||failure
+failuer||failure
+faireness||fairness
+faliure||failure
+familar||familiar
+fatser||faster
+feauture||feature
+feautures||features
+fetaure||feature
+fetaures||features
+fileystem||filesystem
+finanize||finalize
+findn||find
+finilizes||finalizes
+finsih||finish
+flusing||flushing
+folloing||following
+followign||following
+follwing||following
+forseeable||foreseeable
+forse||force
+fortan||fortran
+forwardig||forwarding
+framwork||framework
+frequncy||frequency
+frome||from
+fucntion||function
+fuction||function
+fuctions||functions
+funcion||function
+functionallity||functionality
+functionaly||functionally
+functionnality||functionality
+functonality||functionality
+funtion||function
+funtions||functions
+furthur||further
+futhermore||furthermore
+futrue||future
+gaurenteed||guaranteed
+generiously||generously
+genric||generic
+globel||global
+grabing||grabbing
+grahical||graphical
+grahpical||graphical
+grapic||graphic
+guage||gauge
+guarentee||guarantee
+halfs||halves
+hander||handler
+handfull||handful
+hanled||handled
+harware||hardware
+heirarchically||hierarchically
+helpfull||helpful
+hierachy||hierarchy
+hierarchie||hierarchy
+howver||however
+hsould||should
+hypter||hyper
+identidier||identifier
+imblance||imbalance
+immeadiately||immediately
+immedaite||immediate
+immediatelly||immediately
+immediatly||immediately
+immidiate||immediate
+impelentation||implementation
+impementated||implemented
+implemantation||implementation
+implemenation||implementation
+implementaiton||implementation
+implementated||implemented
+implemention||implementation
+implemetation||implementation
+implemntation||implementation
+implentation||implementation
+implmentation||implementation
+implmenting||implementing
+incomming||incoming
+incompatabilities||incompatibilities
+incompatable||incompatible
+inconsistant||inconsistent
+increas||increase
+incrment||increment
+indendation||indentation
+indended||intended
+independant||independent
+independantly||independently
+independed||independent
+indiate||indicate
+inexpect||inexpected
+infomation||information
+informatiom||information
+informations||information
+informtion||information
+infromation||information
+ingore||ignore
+inital||initial
+initalised||initialized
+initalise||initialize
+initalize||initialize
+initation||initiation
+initators||initiators
+initializiation||initialization
+initialzed||initialized
+initilization||initialization
+initilize||initialize
+inofficial||unofficial
+instal||install
+inteface||interface
+integreated||integrated
+integrety||integrity
+integrey||integrity
+intendet||intended
+intented||intended
+interanl||internal
+interchangable||interchangeable
+interferring||interfering
+interger||integer
+intermittant||intermittent
+internel||internal
+interoprability||interoperability
+interrface||interface
+interrrupt||interrupt
+interrup||interrupt
+interrups||interrupts
+interruptted||interrupted
+interupted||interrupted
+interupt||interrupt
+intial||initial
+intialized||initialized
+intialize||initialize
+intregral||integral
+intrrupt||interrupt
+intuative||intuitive
+invaid||invalid
+invalde||invald
+invalide||invalid
+invididual||individual
+invokation||invocation
+invokations||invocations
+irrelevent||irrelevant
+isssue||issue
+itslef||itself
+jave||java
+jeffies||jiffies
+juse||just
+jus||just
+kown||known
+langage||language
+langauage||language
+langauge||language
+langugage||language
+lauch||launch
+leightweight||lightweight
+lengh||length
+lenght||length
+lenth||length
+lesstiff||lesstif
+libaries||libraries
+libary||library
+librairies||libraries
+libraris||libraries
+licenceing||licencing
+loggging||logging
+loggin||login
+logile||logfile
+loosing||losing
+losted||lost
+machinary||machinery
+maintainance||maintenance
+maintainence||maintenance
+maintan||maintain
+makeing||making
+malplaced||misplaced
+malplace||misplace
+managable||manageable
+managment||management
+mangement||management
+manoeuvering||maneuvering
+mappping||mapping
+mathimatical||mathematical
+mathimatic||mathematic
+mathimatics||mathematics
+maxium||maximum
+mechamism||mechanism
+meetign||meeting
+ment||meant
+mergable||mergeable
+mesage||message
+messags||messages
+messgaes||messages
+messsage||message
+messsages||messages
+microprocesspr||microprocessor
+milliseonds||milliseconds
+minumum||minimum
+miscelleneous||miscellaneous
+misformed||malformed
+mispelled||misspelled
+mispelt||misspelt
+miximum||maximum
+mmnemonic||mnemonic
+mnay||many
+modeled||modelled
+modulues||modules
+monochorome||monochrome
+monochromo||monochrome
+monocrome||monochrome
+mopdule||module
+mroe||more
+mulitplied||multiplied
+multidimensionnal||multidimensional
+multple||multiple
+mumber||number
+muticast||multicast
+mutiple||multiple
+mutli||multi
+nams||names
+navagating||navigating
+nead||need
+neccecary||necessary
+neccesary||necessary
+neccessary||necessary
+necesary||necessary
+negaive||negative
+negoitation||negotiation
+negotation||negotiation
+nerver||never
+nescessary||necessary
+nessessary||necessary
+noticable||noticeable
+notications||notifications
+notifed||notified
+numebr||number
+numner||number
+obtaion||obtain
+occassionally||occasionally
+occationally||occasionally
+occurance||occurrence
+occurances||occurrences
+occured||occurred
+occurence||occurrence
+occure||occurred
+occuring||occurring
+offet||offset
+omitt||omit
+ommiting||omitting
+ommitted||omitted
+onself||oneself
+ony||only
+operatione||operation
+opertaions||operations
+optionnal||optional
+optmizations||optimizations
+orientatied||orientated
+orientied||oriented
+otherise||otherwise
+ouput||output
+overaall||overall
+overhread||overhead
+overlaping||overlapping
+overriden||overridden
+overun||overrun
+pacakge||package
+pachage||package
+packacge||package
+packege||package
+packge||package
+packtes||packets
+pakage||package
+pallette||palette
+paln||plan
+paramameters||parameters
+paramater||parameter
+parametes||parameters
+parametised||parametrised
+paramter||parameter
+paramters||parameters
+particuarly||particularly
+particularily||particularly
+pased||passed
+passin||passing
+pathes||paths
+pecularities||peculiarities
+peformance||performance
+peice||piece
+pendantic||pedantic
+peprocessor||preprocessor
+perfoming||performing
+permissons||permissions
+peroid||period
+persistance||persistence
+persistant||persistent
+platfrom||platform
+plattform||platform
+pleaes||please
+ploting||plotting
+plugable||pluggable
+poinnter||pointer
+poiter||pointer
+posible||possible
+positon||position
+possibilites||possibilities
+powerfull||powerful
+preceeded||preceded
+preceeding||preceding
+preceed||precede
+precendence||precedence
+precission||precision
+prefered||preferred
+prefferably||preferably
+premption||preemption
+prepaired||prepared
+pressre||pressure
+primative||primitive
+princliple||principle
+priorty||priority
+privilaged||privileged
+privilage||privilege
+priviledge||privilege
+priviledges||privileges
+probaly||probably
+procceed||proceed
+proccesors||processors
+procesed||processed
+proces||process
+processessing||processing
+processess||processes
+processpr||processor
+processsed||processed
+processsing||processing
+procteted||protected
+prodecure||procedure
+progams||programs
+progess||progress
+programers||programmers
+programm||program
+programms||programs
+progresss||progress
+promps||prompts
+pronnounced||pronounced
+prononciation||pronunciation
+pronouce||pronounce
+pronunce||pronounce
+propery||property
+propigate||propagate
+propigation||propagation
+propogate||propagate
+prosess||process
+protable||portable
+protcol||protocol
+protecion||protection
+protocoll||protocol
+psudo||pseudo
+psuedo||pseudo
+psychadelic||psychedelic
+pwoer||power
+quering||querying
+raoming||roaming
+reasearcher||researcher
+reasearchers||researchers
+reasearch||research
+recepient||recipient
+receving||receiving
+recieved||received
+recieve||receive
+reciever||receiver
+recieves||receives
+recogniced||recognised
+recognizeable||recognizable
+recommanded||recommended
+recyle||recycle
+redircet||redirect
+redirectrion||redirection
+refcounf||refcount
+refence||reference
+refered||referred
+referenace||reference
+refering||referring
+refernces||references
+refernnce||reference
+refrence||reference
+registerd||registered
+registeresd||registered
+registes||registers
+registraration||registration
+regster||register
+regualar||regular
+reguator||regulator
+regulamentations||regulations
+reigstration||registration
+releated||related
+relevent||relevant
+remoote||remote
+remore||remote
+removeable||removable
+repectively||respectively
+replacable||replaceable
+replacments||replacements
+replys||replies
+reponse||response
+representaion||representation
+reqeust||request
+requiere||require
+requirment||requirement
+requred||required
+requried||required
+requst||request
+reseting||resetting
+resizeable||resizable
+resouces||resources
+resoures||resources
+ressizes||resizes
+ressource||resource
+ressources||resources
+retransmited||retransmitted
+retreived||retrieved
+retreive||retrieve
+retrive||retrieve
+retuned||returned
+reuest||request
+reuqest||request
+reutnred||returned
+rmeoved||removed
+rmeove||remove
+rmeoves||removes
+rountine||routine
+routins||routines
+rquest||request
+runing||running
+runned||ran
+runnning||running
+runtine||runtime
+sacrifying||sacrificing
+safly||safely
+safty||safety
+savable||saveable
+scaned||scanned
+scaning||scanning
+scarch||search
+seach||search
+searchs||searches
+secquence||sequence
+secund||second
+segement||segment
+senarios||scenarios
+sentivite||sensitive
+separatly||separately
+sepcify||specify
+sepc||spec
+seperated||separated
+seperately||separately
+seperate||separate
+seperatly||separately
+seperator||separator
+sepperate||separate
+sequece||sequence
+sequencial||sequential
+serveral||several
+setts||sets
+settting||setting
+shotdown||shutdown
+shoud||should
+shoule||should
+shrinked||shrunk
+siginificantly||significantly
+signabl||signal
+similary||similarly
+similiar||similar
+simlar||similar
+simliar||similar
+simpified||simplified
+singaled||signaled
+singal||signal
+singed||signed
+sleeped||slept
+softwares||software
+speach||speech
+specfic||specific
+speciefied||specified
+specifc||specific
+specifed||specified
+specificatin||specification
+specificaton||specification
+specifing||specifying
+specifiying||specifying
+speficied||specified
+speicify||specify
+speling||spelling
+spinlcok||spinlock
+spinock||spinlock
+splitted||split
+spreaded||spread
+sructure||structure
+stablilization||stabilization
+staically||statically
+staion||station
+standardss||standards
+standartization||standardization
+standart||standard
+staticly||statically
+stoped||stopped
+stoppped||stopped
+straming||streaming
+struc||struct
+structres||structures
+stuct||struct
+sturcture||structure
+subdirectoires||subdirectories
+suble||subtle
+succesfully||successfully
+succesful||successful
+successfull||successful
+sucessfully||successfully
+sucess||success
+superflous||superfluous
+superseeded||superseded
+suplied||supplied
+suported||supported
+suport||support
+suppored||supported
+supportin||supporting
+suppoted||supported
+suppported||supported
+suppport||support
+supress||suppress
+surpresses||suppresses
+susbsystem||subsystem
+suspicously||suspiciously
+swaping||swapping
+switchs||switches
+symetric||symmetric
+synax||syntax
+synchonized||synchronized
+syncronize||synchronize
+syncronizing||synchronizing
+syncronus||synchronous
+syste||system
+sytem||system
+sythesis||synthesis
+taht||that
+targetted||targeted
+targetting||targeting
+teh||the
+temorary||temporary
+temproarily||temporarily
+thier||their
+threds||threads
+threshhold||threshold
+throught||through
+thses||these
+tiggered||triggered
+tipically||typically
+tmis||this
+torerable||tolerable
+tramsmitted||transmitted
+tramsmit||transmit
+tranfer||transfer
+transciever||transceiver
+transferd||transferrd
+transfered||transferred
+transfering||transferring
+transision||transition
+transmittd||transmitted
+transormed||transformed
+trasmission||transmission
+treshold||threshold
+trigerring||triggering
+trun||turn
+ture||true
+tyep||type
+udpate||update
+uesd||used
+unconditionaly||unconditionally
+underun||underrun
+unecessary||unnecessary
+unexecpted||unexpected
+unexpectd||unexpected
+unexpeted||unexpected
+unfortunatelly||unfortunately
+unifiy||unify
+unknonw||unknown
+unknow||unknown
+unkown||unknown
+unneedingly||unnecessarily
+unresgister||unregister
+unsinged||unsigned
+unstabel||unstable
+unsuccessfull||unsuccessful
+unsuported||unsupported
+untill||until
+unuseful||useless
+upate||update
+usefule||useful
+usefull||useful
+usege||usage
+usera||users
+usualy||usually
+utilites||utilities
+utillities||utilities
+utilties||utilities
+utiltity||utility
+utitity||utility
+utitlty||utility
+vaid||valid
+vaild||valid
+valide||valid
+variantions||variations
+varient||variant
+vaule||value
+verbse||verbose
+verisons||versions
+verison||version
+verson||version
+vicefersa||vice-versa
+virtal||virtual
+virtaul||virtual
+virtiual||virtual
+visiters||visitors
+vitual||virtual
+wating||waiting
+whataver||whatever
+whenver||whenever
+wheter||whether
+whe||when
+wierd||weird
+wiil||will
+wirte||write
+withing||within
+wnat||want
+workarould||workaround
+writeing||writing
+writting||writing
+zombe||zombie
+zomebie||zombie
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 293828bfd4ac..cdb491d84503 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -193,10 +193,6 @@ exuberant()
 	--regex-c++='/TESTCLEARFLAG_FALSE\(([^,)]*).*/TestClearPage\1/' \
 	--regex-c++='/__TESTCLEARFLAG_FALSE\(([^,)]*).*/__TestClearPage\1/' \
 	--regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/'		\
-	--regex-c++='/TESTPCGFLAG\(([^,)]*).*/PageCgroup\1/'		\
-	--regex-c++='/SETPCGFLAG\(([^,)]*).*/SetPageCgroup\1/'		\
-	--regex-c++='/CLEARPCGFLAG\(([^,)]*).*/ClearPageCgroup\1/'	\
-	--regex-c++='/TESTCLEARPCGFLAG\(([^,)]*).*/TestClearPageCgroup\1/' \
 	--regex-c++='/TASK_PFA_TEST\([^,]*,\s*([^)]*)\)/task_\1/'	\
 	--regex-c++='/TASK_PFA_SET\([^,]*,\s*([^)]*)\)/task_set_\1/'	\
 	--regex-c++='/TASK_PFA_CLEAR\([^,]*,\s*([^)]*)\)/task_clear_\1/'\
@@ -259,17 +255,13 @@ emacs()
 	--regex='/__CLEARPAGEFLAG_NOOP(\([^,)]*\).*/__ClearPage\1/' \
 	--regex='/TESTCLEARFLAG_FALSE(\([^,)]*\).*/TestClearPage\1/' \
 	--regex='/__TESTCLEARFLAG_FALSE(\([^,)]*\).*/__TestClearPage\1/' \
-	--regex='/TESTPCGFLAG\(([^,)]*).*/PageCgroup\1/'	\
-	--regex='/SETPCGFLAG\(([^,)]*).*/SetPageCgroup\1/'	\
-	--regex='/CLEARPCGFLAG\(([^,)]*).*/ClearPageCgroup\1/'	\
-	--regex='/TESTCLEARPCGFLAG\(([^,)]*).*/TestClearPageCgroup\1/' \
 	--regex='/TASK_PFA_TEST\([^,]*,\s*([^)]*)\)/task_\1/'		\
 	--regex='/TASK_PFA_SET\([^,]*,\s*([^)]*)\)/task_set_\1/'	\
 	--regex='/TASK_PFA_CLEAR\([^,]*,\s*([^)]*)\)/task_clear_\1/'	\
 	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'		\
 	--regex='/PCI_OP_READ(\([a-z]*[a-z]\).*[1-4])/pci_bus_read_config_\1/' \
 	--regex='/PCI_OP_WRITE(\([a-z]*[a-z]\).*[1-4])/pci_bus_write_config_\1/'\
-	--regex='/DEFINE_HASHTABLE\((\w*)/\1/v/'
+	--regex='/[^#]*DEFINE_HASHTABLE(\([^,)]*\)/\1/'
 
 	all_kconfigs | xargs $1 -a                              \
 	--regex='/^[ \t]*\(\(menu\)*config\)[ \t]+\([a-zA-Z0-9_]+\)/\3/'
diff --git a/scripts/tracing/draw_functrace.py b/scripts/tracing/draw_functrace.py
index db40fa04cd51..db40fa04cd51 100644..100755
--- a/scripts/tracing/draw_functrace.py
+++ b/scripts/tracing/draw_functrace.py
diff --git a/scripts/xz_wrap.sh b/scripts/xz_wrap.sh
index 7a2d372f4885..7a2d372f4885 100644..100755
--- a/scripts/xz_wrap.sh
+++ b/scripts/xz_wrap.sh
diff --git a/security/capability.c b/security/capability.c
index a74fde6a7468..d68c57a62bcf 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -343,9 +343,9 @@ static int cap_file_fcntl(struct file *file, unsigned int cmd,
 	return 0;
 }
 
-static int cap_file_set_fowner(struct file *file)
+static void cap_file_set_fowner(struct file *file)
 {
-	return 0;
+	return;
 }
 
 static int cap_file_send_sigiotask(struct task_struct *tsk,
diff --git a/security/integrity/Kconfig b/security/integrity/Kconfig
index 245c6d92065b..b76235ae4786 100644
--- a/security/integrity/Kconfig
+++ b/security/integrity/Kconfig
@@ -1,11 +1,23 @@
 #
 config INTEGRITY
-	def_bool y
-	depends on IMA || EVM
+	bool "Integrity subsystem"
+	depends on SECURITY
+	default y
+	help
+	  This option enables the integrity subsystem, which is comprised
+	  of a number of different components including the Integrity
+	  Measurement Architecture (IMA), Extended Verification Module
+	  (EVM), IMA-appraisal extension, digital signature verification
+	  extension and audit measurement log support.
+
+	  Each of these components can be enabled/disabled separately.
+	  Refer to the individual components for additional details.
+
+if INTEGRITY
 
 config INTEGRITY_SIGNATURE
 	boolean "Digital signature verification using multiple keyrings"
-	depends on INTEGRITY && KEYS
+	depends on KEYS
 	default n
 	select SIGNATURE
 	help
@@ -17,9 +29,21 @@ config INTEGRITY_SIGNATURE
 	  This is useful for evm and module keyrings, when keys are
 	  usually only added from initramfs.
 
+config INTEGRITY_ASYMMETRIC_KEYS
+	boolean "Enable asymmetric keys support"
+	depends on INTEGRITY_SIGNATURE
+	default n
+        select ASYMMETRIC_KEY_TYPE
+        select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
+        select PUBLIC_KEY_ALGO_RSA
+        select X509_CERTIFICATE_PARSER
+	help
+	  This option enables digital signature verification using
+	  asymmetric keys.
+
 config INTEGRITY_AUDIT
 	bool "Enables integrity auditing support "
-	depends on INTEGRITY && AUDIT
+	depends on AUDIT
 	default y
 	help
 	  In addition to enabling integrity auditing support, this
@@ -32,17 +56,7 @@ config INTEGRITY_AUDIT
 	  be enabled by specifying 'integrity_audit=1' on the kernel
 	  command line.
 
-config INTEGRITY_ASYMMETRIC_KEYS
-	boolean "Enable asymmetric keys support"
-	depends on INTEGRITY_SIGNATURE
-	default n
-        select ASYMMETRIC_KEY_TYPE
-        select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
-        select PUBLIC_KEY_ALGO_RSA
-        select X509_CERTIFICATE_PARSER
-	help
-	  This option enables digital signature verification using
-	  asymmetric keys.
-
 source security/integrity/ima/Kconfig
 source security/integrity/evm/Kconfig
+
+endif   # if INTEGRITY
diff --git a/security/integrity/Makefile b/security/integrity/Makefile
index 0793f4811cb7..8d1f4bf51087 100644
--- a/security/integrity/Makefile
+++ b/security/integrity/Makefile
@@ -3,11 +3,11 @@
 #
 
 obj-$(CONFIG_INTEGRITY) += integrity.o
-obj-$(CONFIG_INTEGRITY_AUDIT) += integrity_audit.o
-obj-$(CONFIG_INTEGRITY_SIGNATURE) += digsig.o
-obj-$(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) += digsig_asymmetric.o
 
 integrity-y := iint.o
+integrity-$(CONFIG_INTEGRITY_AUDIT) += integrity_audit.o
+integrity-$(CONFIG_INTEGRITY_SIGNATURE) += digsig.o
+integrity-$(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) += digsig_asymmetric.o
 
 subdir-$(CONFIG_IMA)			+= ima
 obj-$(CONFIG_IMA)			+= ima/
diff --git a/security/integrity/digsig_asymmetric.c b/security/integrity/digsig_asymmetric.c
index 9eae4809006b..4fec1816a2b3 100644
--- a/security/integrity/digsig_asymmetric.c
+++ b/security/integrity/digsig_asymmetric.c
@@ -13,6 +13,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/err.h>
+#include <linux/ratelimit.h>
 #include <linux/key-type.h>
 #include <crypto/public_key.h>
 #include <keys/asymmetric-type.h>
@@ -27,7 +28,7 @@ static struct key *request_asymmetric_key(struct key *keyring, uint32_t keyid)
 	struct key *key;
 	char name[12];
 
-	sprintf(name, "id:%x", keyid);
+	sprintf(name, "id:%08x", keyid);
 
 	pr_debug("key search: \"%s\"\n", name);
 
@@ -45,8 +46,8 @@ static struct key *request_asymmetric_key(struct key *keyring, uint32_t keyid)
 	}
 
 	if (IS_ERR(key)) {
-		pr_warn("Request for unknown key '%s' err %ld\n",
-			name, PTR_ERR(key));
+		pr_err_ratelimited("Request for unknown key '%s' err %ld\n",
+				   name, PTR_ERR(key));
 		switch (PTR_ERR(key)) {
 			/* Hide some search errors */
 		case -EACCES:
diff --git a/security/integrity/evm/Kconfig b/security/integrity/evm/Kconfig
index d606f3d12d6b..df586fa00ef1 100644
--- a/security/integrity/evm/Kconfig
+++ b/security/integrity/evm/Kconfig
@@ -1,6 +1,5 @@
 config EVM
 	boolean "EVM support"
-	depends on SECURITY
 	select KEYS
 	select ENCRYPTED_KEYS
 	select CRYPTO_HMAC
@@ -12,10 +11,6 @@ config EVM
 
 	  If you are unsure how to answer this question, answer N.
 
-if EVM
-
-menu "EVM options"
-
 config EVM_ATTR_FSUUID
 	bool "FSUUID (version 2)"
 	default y
@@ -47,6 +42,3 @@ config EVM_EXTRA_SMACK_XATTRS
 	  additional info to the calculation, requires existing EVM
 	  labeled file systems to be relabeled.
 
-endmenu
-
-endif
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 3bcb80df4d01..9685af330de5 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -126,14 +126,15 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry,
 	rc = vfs_getxattr_alloc(dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0,
 				GFP_NOFS);
 	if (rc <= 0) {
-		if (rc == 0)
-			evm_status = INTEGRITY_FAIL; /* empty */
-		else if (rc == -ENODATA) {
+		evm_status = INTEGRITY_FAIL;
+		if (rc == -ENODATA) {
 			rc = evm_find_protected_xattrs(dentry);
 			if (rc > 0)
 				evm_status = INTEGRITY_NOLABEL;
 			else if (rc == 0)
 				evm_status = INTEGRITY_NOXATTRS; /* new file */
+		} else if (rc == -EOPNOTSUPP) {
+			evm_status = INTEGRITY_UNKNOWN;
 		}
 		goto out;
 	}
@@ -284,6 +285,13 @@ static int evm_protect_xattr(struct dentry *dentry, const char *xattr_name,
 		goto out;
 	}
 	evm_status = evm_verify_current_integrity(dentry);
+	if (evm_status == INTEGRITY_NOXATTRS) {
+		struct integrity_iint_cache *iint;
+
+		iint = integrity_iint_find(dentry->d_inode);
+		if (iint && (iint->flags & IMA_NEW_FILE))
+			return 0;
+	}
 out:
 	if (evm_status != INTEGRITY_PASS)
 		integrity_audit_msg(AUDIT_INTEGRITY_METADATA, dentry->d_inode,
@@ -352,7 +360,6 @@ void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name,
 		return;
 
 	evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len);
-	return;
 }
 
 /**
@@ -372,7 +379,6 @@ void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name)
 	mutex_lock(&inode->i_mutex);
 	evm_update_evmxattr(dentry, xattr_name, NULL, 0);
 	mutex_unlock(&inode->i_mutex);
-	return;
 }
 
 /**
@@ -414,7 +420,6 @@ void evm_inode_post_setattr(struct dentry *dentry, int ia_valid)
 
 	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
 		evm_update_evmxattr(dentry, NULL, NULL, 0);
-	return;
 }
 
 /*
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index 08758fbd496f..e099875643c5 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -2,8 +2,6 @@
 #
 config IMA
 	bool "Integrity Measurement Architecture(IMA)"
-	depends on SECURITY
-	select INTEGRITY
 	select SECURITYFS
 	select CRYPTO
 	select CRYPTO_HMAC
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 57da4bd7ba0c..8ee997dff139 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -43,6 +43,9 @@ enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
 #define IMA_TEMPLATE_IMA_NAME "ima"
 #define IMA_TEMPLATE_IMA_FMT "d|n"
 
+/* current content of the policy */
+extern int ima_policy_flag;
+
 /* set during initialization */
 extern int ima_initialized;
 extern int ima_used_chip;
@@ -90,10 +93,7 @@ extern struct list_head ima_measurements;	/* list of all measurements */
 
 /* Internal IMA function definitions */
 int ima_init(void);
-void ima_cleanup(void);
 int ima_fs_init(void);
-void ima_fs_cleanup(void);
-int ima_inode_alloc(struct inode *inode);
 int ima_add_template_entry(struct ima_template_entry *entry, int violation,
 			   const char *op, struct inode *inode,
 			   const unsigned char *filename);
@@ -110,8 +110,6 @@ void ima_print_digest(struct seq_file *m, u8 *digest, int size);
 struct ima_template_desc *ima_template_desc_current(void);
 int ima_init_template(void);
 
-int ima_init_template(void);
-
 /*
  * used to protect h_table and sha_table
  */
@@ -151,12 +149,6 @@ int ima_store_template(struct ima_template_entry *entry, int violation,
 void ima_free_template_entry(struct ima_template_entry *entry);
 const char *ima_d_path(struct path *path, char **pathbuf);
 
-/* rbtree tree calls to lookup, insert, delete
- * integrity data associated with an inode.
- */
-struct integrity_iint_cache *integrity_iint_insert(struct inode *inode);
-struct integrity_iint_cache *integrity_iint_find(struct inode *inode);
-
 /* IMA policy related functions */
 enum ima_hooks { FILE_CHECK = 1, MMAP_CHECK, BPRM_CHECK, MODULE_CHECK, FIRMWARE_CHECK, POST_SETATTR };
 
@@ -164,20 +156,22 @@ int ima_match_policy(struct inode *inode, enum ima_hooks func, int mask,
 		     int flags);
 void ima_init_policy(void);
 void ima_update_policy(void);
+void ima_update_policy_flag(void);
 ssize_t ima_parse_add_rule(char *);
 void ima_delete_rules(void);
 
 /* Appraise integrity measurements */
 #define IMA_APPRAISE_ENFORCE	0x01
 #define IMA_APPRAISE_FIX	0x02
-#define IMA_APPRAISE_MODULES	0x04
-#define IMA_APPRAISE_FIRMWARE	0x08
+#define IMA_APPRAISE_LOG	0x04
+#define IMA_APPRAISE_MODULES	0x08
+#define IMA_APPRAISE_FIRMWARE	0x10
 
 #ifdef CONFIG_IMA_APPRAISE
 int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 			     struct file *file, const unsigned char *filename,
 			     struct evm_ima_xattr_data *xattr_value,
-			     int xattr_len);
+			     int xattr_len, int opened);
 int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func);
 void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file);
 enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
@@ -193,7 +187,7 @@ static inline int ima_appraise_measurement(int func,
 					   struct file *file,
 					   const unsigned char *filename,
 					   struct evm_ima_xattr_data *xattr_value,
-					   int xattr_len)
+					   int xattr_len, int opened)
 {
 	return INTEGRITY_UNKNOWN;
 }
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index d9cd5ce14d2b..86885979918c 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -179,11 +179,6 @@ int ima_get_action(struct inode *inode, int mask, int function)
 	return ima_match_policy(inode, function, mask, flags);
 }
 
-int ima_must_measure(struct inode *inode, int mask, int function)
-{
-	return ima_match_policy(inode, function, mask, IMA_MEASURE);
-}
-
 /*
  * ima_collect_measurement - collect file measurement
  *
@@ -330,10 +325,9 @@ const char *ima_d_path(struct path *path, char **pathbuf)
 {
 	char *pathname = NULL;
 
-	/* We will allow 11 spaces for ' (deleted)' to be appended */
-	*pathbuf = kmalloc(PATH_MAX + 11, GFP_KERNEL);
+	*pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (*pathbuf) {
-		pathname = d_path(path, *pathbuf, PATH_MAX + 11);
+		pathname = d_absolute_path(path, *pathbuf, PATH_MAX);
 		if (IS_ERR(pathname)) {
 			kfree(*pathbuf);
 			*pathbuf = NULL;
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 86bfd5c5df85..922685483bd3 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -23,6 +23,8 @@ static int __init default_appraise_setup(char *str)
 {
 	if (strncmp(str, "off", 3) == 0)
 		ima_appraise = 0;
+	else if (strncmp(str, "log", 3) == 0)
+		ima_appraise = IMA_APPRAISE_LOG;
 	else if (strncmp(str, "fix", 3) == 0)
 		ima_appraise = IMA_APPRAISE_FIX;
 	return 1;
@@ -183,7 +185,7 @@ int ima_read_xattr(struct dentry *dentry,
 int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 			     struct file *file, const unsigned char *filename,
 			     struct evm_ima_xattr_data *xattr_value,
-			     int xattr_len)
+			     int xattr_len, int opened)
 {
 	static const char op[] = "appraise_data";
 	char *cause = "unknown";
@@ -192,8 +194,6 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 	enum integrity_status status = INTEGRITY_UNKNOWN;
 	int rc = xattr_len, hash_start = 0;
 
-	if (!ima_appraise)
-		return 0;
 	if (!inode->i_op->getxattr)
 		return INTEGRITY_UNKNOWN;
 
@@ -202,8 +202,11 @@ int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
 			goto out;
 
 		cause = "missing-hash";
-		status =
-		    (inode->i_size == 0) ? INTEGRITY_PASS : INTEGRITY_NOLABEL;
+		status = INTEGRITY_NOLABEL;
+		if (opened & FILE_CREATED) {
+			iint->flags |= IMA_NEW_FILE;
+			status = INTEGRITY_PASS;
+		}
 		goto out;
 	}
 
@@ -315,7 +318,7 @@ void ima_inode_post_setattr(struct dentry *dentry)
 	struct integrity_iint_cache *iint;
 	int must_appraise, rc;
 
-	if (!ima_initialized || !ima_appraise || !S_ISREG(inode->i_mode)
+	if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode)
 	    || !inode->i_op->removexattr)
 		return;
 
@@ -353,7 +356,7 @@ static void ima_reset_appraise_flags(struct inode *inode, int digsig)
 {
 	struct integrity_iint_cache *iint;
 
-	if (!ima_initialized || !ima_appraise || !S_ISREG(inode->i_mode))
+	if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode))
 		return;
 
 	iint = integrity_iint_find(inode);
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 0bd732843fe7..78d66dae15f4 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -80,24 +80,24 @@ static int ima_kernel_read(struct file *file, loff_t offset,
 {
 	mm_segment_t old_fs;
 	char __user *buf = addr;
-	ssize_t ret;
+	ssize_t ret = -EINVAL;
 
 	if (!(file->f_mode & FMODE_READ))
 		return -EBADF;
-	if (!file->f_op->read && !file->f_op->aio_read)
-		return -EINVAL;
 
 	old_fs = get_fs();
 	set_fs(get_ds());
 	if (file->f_op->read)
 		ret = file->f_op->read(file, buf, count, &offset);
-	else
+	else if (file->f_op->aio_read)
 		ret = do_sync_read(file, buf, count, &offset);
+	else if (file->f_op->read_iter)
+		ret = new_sync_read(file, buf, count, &offset);
 	set_fs(old_fs);
 	return ret;
 }
 
-int ima_init_crypto(void)
+int __init ima_init_crypto(void)
 {
 	long rc;
 
@@ -116,7 +116,10 @@ static struct crypto_shash *ima_alloc_tfm(enum hash_algo algo)
 	struct crypto_shash *tfm = ima_shash_tfm;
 	int rc;
 
-	if (algo != ima_hash_algo && algo < HASH_ALGO__LAST) {
+	if (algo < 0 || algo >= HASH_ALGO__LAST)
+		algo = ima_hash_algo;
+
+	if (algo != ima_hash_algo) {
 		tfm = crypto_alloc_shash(hash_algo_name[algo], 0, 0);
 		if (IS_ERR(tfm)) {
 			rc = PTR_ERR(tfm);
@@ -200,7 +203,10 @@ static struct crypto_ahash *ima_alloc_atfm(enum hash_algo algo)
 	struct crypto_ahash *tfm = ima_ahash_tfm;
 	int rc;
 
-	if ((algo != ima_hash_algo && algo < HASH_ALGO__LAST) || !tfm) {
+	if (algo < 0 || algo >= HASH_ALGO__LAST)
+		algo = ima_hash_algo;
+
+	if (algo != ima_hash_algo || !tfm) {
 		tfm = crypto_alloc_ahash(hash_algo_name[algo], 0, 0);
 		if (!IS_ERR(tfm)) {
 			if (algo == ima_hash_algo)
@@ -380,17 +386,14 @@ static int ima_calc_file_hash_tfm(struct file *file,
 	loff_t i_size, offset = 0;
 	char *rbuf;
 	int rc, read = 0;
-	struct {
-		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(tfm)];
-	} desc;
+	SHASH_DESC_ON_STACK(shash, tfm);
 
-	desc.shash.tfm = tfm;
-	desc.shash.flags = 0;
+	shash->tfm = tfm;
+	shash->flags = 0;
 
 	hash->length = crypto_shash_digestsize(tfm);
 
-	rc = crypto_shash_init(&desc.shash);
+	rc = crypto_shash_init(shash);
 	if (rc != 0)
 		return rc;
 
@@ -420,7 +423,7 @@ static int ima_calc_file_hash_tfm(struct file *file,
 			break;
 		offset += rbuf_len;
 
-		rc = crypto_shash_update(&desc.shash, rbuf, rbuf_len);
+		rc = crypto_shash_update(shash, rbuf, rbuf_len);
 		if (rc)
 			break;
 	}
@@ -429,7 +432,7 @@ static int ima_calc_file_hash_tfm(struct file *file,
 	kfree(rbuf);
 out:
 	if (!rc)
-		rc = crypto_shash_final(&desc.shash, hash->digest);
+		rc = crypto_shash_final(shash, hash->digest);
 	return rc;
 }
 
@@ -487,18 +490,15 @@ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
 					 struct ima_digest_data *hash,
 					 struct crypto_shash *tfm)
 {
-	struct {
-		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(tfm)];
-	} desc;
+	SHASH_DESC_ON_STACK(shash, tfm);
 	int rc, i;
 
-	desc.shash.tfm = tfm;
-	desc.shash.flags = 0;
+	shash->tfm = tfm;
+	shash->flags = 0;
 
 	hash->length = crypto_shash_digestsize(tfm);
 
-	rc = crypto_shash_init(&desc.shash);
+	rc = crypto_shash_init(shash);
 	if (rc != 0)
 		return rc;
 
@@ -508,7 +508,7 @@ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
 		u32 datalen = field_data[i].len;
 
 		if (strcmp(td->name, IMA_TEMPLATE_IMA_NAME) != 0) {
-			rc = crypto_shash_update(&desc.shash,
+			rc = crypto_shash_update(shash,
 						(const u8 *) &field_data[i].len,
 						sizeof(field_data[i].len));
 			if (rc)
@@ -518,13 +518,13 @@ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
 			data_to_hash = buffer;
 			datalen = IMA_EVENT_NAME_LEN_MAX + 1;
 		}
-		rc = crypto_shash_update(&desc.shash, data_to_hash, datalen);
+		rc = crypto_shash_update(shash, data_to_hash, datalen);
 		if (rc)
 			break;
 	}
 
 	if (!rc)
-		rc = crypto_shash_final(&desc.shash, hash->digest);
+		rc = crypto_shash_final(shash, hash->digest);
 
 	return rc;
 }
@@ -565,15 +565,12 @@ static int __init ima_calc_boot_aggregate_tfm(char *digest,
 {
 	u8 pcr_i[TPM_DIGEST_SIZE];
 	int rc, i;
-	struct {
-		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(tfm)];
-	} desc;
+	SHASH_DESC_ON_STACK(shash, tfm);
 
-	desc.shash.tfm = tfm;
-	desc.shash.flags = 0;
+	shash->tfm = tfm;
+	shash->flags = 0;
 
-	rc = crypto_shash_init(&desc.shash);
+	rc = crypto_shash_init(shash);
 	if (rc != 0)
 		return rc;
 
@@ -581,10 +578,10 @@ static int __init ima_calc_boot_aggregate_tfm(char *digest,
 	for (i = TPM_PCR0; i < TPM_PCR8; i++) {
 		ima_pcrread(i, pcr_i);
 		/* now accumulate with current aggregate */
-		rc = crypto_shash_update(&desc.shash, pcr_i, TPM_DIGEST_SIZE);
+		rc = crypto_shash_update(shash, pcr_i, TPM_DIGEST_SIZE);
 	}
 	if (!rc)
-		crypto_shash_final(&desc.shash, digest);
+		crypto_shash_final(shash, digest);
 	return rc;
 }
 
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index e8f9d70a465d..9164fc8cac84 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -43,7 +43,7 @@ int ima_used_chip;
  * a different value.) Violations add a zero entry to the measurement
  * list and extend the aggregate PCR value with ff...ff's.
  */
-static void __init ima_add_boot_aggregate(void)
+static int __init ima_add_boot_aggregate(void)
 {
 	static const char op[] = "add_boot_aggregate";
 	const char *audit_cause = "ENOMEM";
@@ -72,17 +72,23 @@ static void __init ima_add_boot_aggregate(void)
 
 	result = ima_alloc_init_template(iint, NULL, boot_aggregate_name,
 					 NULL, 0, &entry);
-	if (result < 0)
-		return;
+	if (result < 0) {
+		audit_cause = "alloc_entry";
+		goto err_out;
+	}
 
 	result = ima_store_template(entry, violation, NULL,
 				    boot_aggregate_name);
-	if (result < 0)
+	if (result < 0) {
 		ima_free_template_entry(entry);
-	return;
+		audit_cause = "store_entry";
+		goto err_out;
+	}
+	return 0;
 err_out:
 	integrity_audit_msg(AUDIT_INTEGRITY_PCR, NULL, boot_aggregate_name, op,
 			    audit_cause, result, 0);
+	return result;
 }
 
 int __init ima_init(void)
@@ -98,6 +104,10 @@ int __init ima_init(void)
 	if (!ima_used_chip)
 		pr_info("No TPM chip found, activating TPM-bypass!\n");
 
+	rc = ima_init_keyring(INTEGRITY_KEYRING_IMA);
+	if (rc)
+		return rc;
+
 	rc = ima_init_crypto();
 	if (rc)
 		return rc;
@@ -105,7 +115,10 @@ int __init ima_init(void)
 	if (rc != 0)
 		return rc;
 
-	ima_add_boot_aggregate();	/* boot aggregate must be first entry */
+	rc = ima_add_boot_aggregate();	/* boot aggregate must be first entry */
+	if (rc != 0)
+		return rc;
+
 	ima_init_policy();
 
 	return ima_fs_init();
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 2917f980bf30..62f59eca32d3 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -77,42 +77,39 @@ __setup("ima_hash=", hash_setup);
  *	  could result in a file measurement error.
  *
  */
-static void ima_rdwr_violation_check(struct file *file)
+static void ima_rdwr_violation_check(struct file *file,
+				     struct integrity_iint_cache *iint,
+				     int must_measure,
+				     char **pathbuf,
+				     const char **pathname)
 {
 	struct inode *inode = file_inode(file);
 	fmode_t mode = file->f_mode;
 	bool send_tomtou = false, send_writers = false;
-	char *pathbuf = NULL;
-	const char *pathname;
-
-	if (!S_ISREG(inode->i_mode) || !ima_initialized)
-		return;
 
 	if (mode & FMODE_WRITE) {
 		if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) {
-			struct integrity_iint_cache *iint;
-			iint = integrity_iint_find(inode);
+			if (!iint)
+				iint = integrity_iint_find(inode);
 			/* IMA_MEASURE is set from reader side */
 			if (iint && (iint->flags & IMA_MEASURE))
 				send_tomtou = true;
 		}
 	} else {
-		if ((atomic_read(&inode->i_writecount) > 0) &&
-		    ima_must_measure(inode, MAY_READ, FILE_CHECK))
+		if ((atomic_read(&inode->i_writecount) > 0) && must_measure)
 			send_writers = true;
 	}
 
 	if (!send_tomtou && !send_writers)
 		return;
 
-	pathname = ima_d_path(&file->f_path, &pathbuf);
+	*pathname = ima_d_path(&file->f_path, pathbuf);
 
 	if (send_tomtou)
-		ima_add_violation(file, pathname, "invalid_pcr", "ToMToU");
+		ima_add_violation(file, *pathname, "invalid_pcr", "ToMToU");
 	if (send_writers)
-		ima_add_violation(file, pathname,
+		ima_add_violation(file, *pathname,
 				  "invalid_pcr", "open_writers");
-	kfree(pathbuf);
 }
 
 static void ima_check_last_writer(struct integrity_iint_cache *iint,
@@ -124,11 +121,13 @@ static void ima_check_last_writer(struct integrity_iint_cache *iint,
 		return;
 
 	mutex_lock(&inode->i_mutex);
-	if (atomic_read(&inode->i_writecount) == 1 &&
-	    iint->version != inode->i_version) {
-		iint->flags &= ~IMA_DONE_MASK;
-		if (iint->flags & IMA_APPRAISE)
-			ima_update_xattr(iint, file);
+	if (atomic_read(&inode->i_writecount) == 1) {
+		if ((iint->version != inode->i_version) ||
+		    (iint->flags & IMA_NEW_FILE)) {
+			iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE);
+			if (iint->flags & IMA_APPRAISE)
+				ima_update_xattr(iint, file);
+		}
 	}
 	mutex_unlock(&inode->i_mutex);
 }
@@ -154,19 +153,20 @@ void ima_file_free(struct file *file)
 	ima_check_last_writer(iint, inode, file);
 }
 
-static int process_measurement(struct file *file, const char *filename,
-			       int mask, int function)
+static int process_measurement(struct file *file, int mask, int function,
+			       int opened)
 {
 	struct inode *inode = file_inode(file);
-	struct integrity_iint_cache *iint;
+	struct integrity_iint_cache *iint = NULL;
 	struct ima_template_desc *template_desc;
 	char *pathbuf = NULL;
 	const char *pathname = NULL;
-	int rc = -ENOMEM, action, must_appraise, _func;
+	int rc = -ENOMEM, action, must_appraise;
 	struct evm_ima_xattr_data *xattr_value = NULL, **xattr_ptr = NULL;
 	int xattr_len = 0;
+	bool violation_check;
 
-	if (!ima_initialized || !S_ISREG(inode->i_mode))
+	if (!ima_policy_flag || !S_ISREG(inode->i_mode))
 		return 0;
 
 	/* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action
@@ -174,19 +174,33 @@ static int process_measurement(struct file *file, const char *filename,
 	 * Included is the appraise submask.
 	 */
 	action = ima_get_action(inode, mask, function);
-	if (!action)
+	violation_check = ((function == FILE_CHECK || function == MMAP_CHECK) &&
+			   (ima_policy_flag & IMA_MEASURE));
+	if (!action && !violation_check)
 		return 0;
 
 	must_appraise = action & IMA_APPRAISE;
 
 	/*  Is the appraise rule hook specific?  */
-	_func = (action & IMA_FILE_APPRAISE) ? FILE_CHECK : function;
+	if (action & IMA_FILE_APPRAISE)
+		function = FILE_CHECK;
 
 	mutex_lock(&inode->i_mutex);
 
-	iint = integrity_inode_get(inode);
-	if (!iint)
-		goto out;
+	if (action) {
+		iint = integrity_inode_get(inode);
+		if (!iint)
+			goto out;
+	}
+
+	if (violation_check) {
+		ima_rdwr_violation_check(file, iint, action & IMA_MEASURE,
+					 &pathbuf, &pathname);
+		if (!action) {
+			rc = 0;
+			goto out_free;
+		}
+	}
 
 	/* Determine if already appraised/measured based on bitmask
 	 * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED,
@@ -199,15 +213,13 @@ static int process_measurement(struct file *file, const char *filename,
 	/* Nothing to do, just return existing appraised status */
 	if (!action) {
 		if (must_appraise)
-			rc = ima_get_cache_status(iint, _func);
+			rc = ima_get_cache_status(iint, function);
 		goto out_digsig;
 	}
 
 	template_desc = ima_template_desc_current();
-	if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) {
-		if (action & IMA_APPRAISE_SUBMASK)
-			xattr_ptr = &xattr_value;
-	} else
+	if ((action & IMA_APPRAISE_SUBMASK) ||
+		    strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0)
 		xattr_ptr = &xattr_value;
 
 	rc = ima_collect_measurement(iint, file, xattr_ptr, &xattr_len);
@@ -217,23 +229,26 @@ static int process_measurement(struct file *file, const char *filename,
 		goto out_digsig;
 	}
 
-	pathname = filename ?: ima_d_path(&file->f_path, &pathbuf);
+	if (!pathname)	/* ima_rdwr_violation possibly pre-fetched */
+		pathname = ima_d_path(&file->f_path, &pathbuf);
 
 	if (action & IMA_MEASURE)
 		ima_store_measurement(iint, file, pathname,
 				      xattr_value, xattr_len);
 	if (action & IMA_APPRAISE_SUBMASK)
-		rc = ima_appraise_measurement(_func, iint, file, pathname,
-					      xattr_value, xattr_len);
+		rc = ima_appraise_measurement(function, iint, file, pathname,
+					      xattr_value, xattr_len, opened);
 	if (action & IMA_AUDIT)
 		ima_audit_measurement(iint, pathname);
-	kfree(pathbuf);
+
 out_digsig:
 	if ((mask & MAY_WRITE) && (iint->flags & IMA_DIGSIG))
 		rc = -EACCES;
+	kfree(xattr_value);
+out_free:
+	kfree(pathbuf);
 out:
 	mutex_unlock(&inode->i_mutex);
-	kfree(xattr_value);
 	if ((rc && must_appraise) && (ima_appraise & IMA_APPRAISE_ENFORCE))
 		return -EACCES;
 	return 0;
@@ -253,7 +268,7 @@ out:
 int ima_file_mmap(struct file *file, unsigned long prot)
 {
 	if (file && (prot & PROT_EXEC))
-		return process_measurement(file, NULL, MAY_EXEC, MMAP_CHECK);
+		return process_measurement(file, MAY_EXEC, MMAP_CHECK, 0);
 	return 0;
 }
 
@@ -272,10 +287,7 @@ int ima_file_mmap(struct file *file, unsigned long prot)
  */
 int ima_bprm_check(struct linux_binprm *bprm)
 {
-	return process_measurement(bprm->file,
-				   (strcmp(bprm->filename, bprm->interp) == 0) ?
-				   bprm->filename : bprm->interp,
-				   MAY_EXEC, BPRM_CHECK);
+	return process_measurement(bprm->file, MAY_EXEC, BPRM_CHECK, 0);
 }
 
 /**
@@ -288,12 +300,11 @@ int ima_bprm_check(struct linux_binprm *bprm)
  * On success return 0.  On integrity appraisal error, assuming the file
  * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
  */
-int ima_file_check(struct file *file, int mask)
+int ima_file_check(struct file *file, int mask, int opened)
 {
-	ima_rdwr_violation_check(file);
-	return process_measurement(file, NULL,
+	return process_measurement(file,
 				   mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
-				   FILE_CHECK);
+				   FILE_CHECK, opened);
 }
 EXPORT_SYMBOL_GPL(ima_file_check);
 
@@ -316,7 +327,7 @@ int ima_module_check(struct file *file)
 #endif
 		return 0;	/* We rely on module signature checking */
 	}
-	return process_measurement(file, NULL, MAY_EXEC, MODULE_CHECK);
+	return process_measurement(file, MAY_EXEC, MODULE_CHECK, 0);
 }
 
 int ima_fw_from_file(struct file *file, char *buf, size_t size)
@@ -327,7 +338,7 @@ int ima_fw_from_file(struct file *file, char *buf, size_t size)
 			return -EACCES;	/* INTEGRITY_UNKNOWN */
 		return 0;
 	}
-	return process_measurement(file, NULL, MAY_EXEC, FIRMWARE_CHECK);
+	return process_measurement(file, MAY_EXEC, FIRMWARE_CHECK, 0);
 }
 
 static int __init init_ima(void)
@@ -336,14 +347,10 @@ static int __init init_ima(void)
 
 	hash_setup(CONFIG_IMA_DEFAULT_HASH);
 	error = ima_init();
-	if (error)
-		goto out;
-
-	error = ima_init_keyring(INTEGRITY_KEYRING_IMA);
-	if (error)
-		goto out;
-	ima_initialized = 1;
-out:
+	if (!error) {
+		ima_initialized = 1;
+		ima_update_policy_flag();
+	}
 	return error;
 }
 
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 07099a8bc283..cdc620b2152f 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -35,6 +35,8 @@
 #define DONT_APPRAISE	0x0008
 #define AUDIT		0x0040
 
+int ima_policy_flag;
+
 #define MAX_LSM_RULES 6
 enum lsm_rule_types { LSM_OBJ_USER, LSM_OBJ_ROLE, LSM_OBJ_TYPE,
 	LSM_SUBJ_USER, LSM_SUBJ_ROLE, LSM_SUBJ_TYPE
@@ -295,6 +297,26 @@ int ima_match_policy(struct inode *inode, enum ima_hooks func, int mask,
 	return action;
 }
 
+/*
+ * Initialize the ima_policy_flag variable based on the currently
+ * loaded policy.  Based on this flag, the decision to short circuit
+ * out of a function or not call the function in the first place
+ * can be made earlier.
+ */
+void ima_update_policy_flag(void)
+{
+	struct ima_rule_entry *entry;
+
+	ima_policy_flag = 0;
+	list_for_each_entry(entry, ima_rules, list) {
+		if (entry->action & IMA_DO_MASK)
+			ima_policy_flag |= entry->action;
+	}
+
+	if (!ima_appraise)
+		ima_policy_flag &= ~IMA_APPRAISE;
+}
+
 /**
  * ima_init_policy - initialize the default measure rules.
  *
@@ -341,6 +363,7 @@ void ima_update_policy(void)
 
 	if (ima_rules == &ima_default_rules) {
 		ima_rules = &ima_policy_rules;
+		ima_update_policy_flag();
 		cause = "complete";
 		result = 0;
 	}
diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
index a076a967ec47..e854862c9337 100644
--- a/security/integrity/ima/ima_template.c
+++ b/security/integrity/ima/ima_template.c
@@ -152,24 +152,6 @@ out:
 	return result;
 }
 
-static int init_defined_templates(void)
-{
-	int i = 0;
-	int result = 0;
-
-	/* Init defined templates. */
-	for (i = 0; i < ARRAY_SIZE(defined_templates); i++) {
-		struct ima_template_desc *template = &defined_templates[i];
-
-		result = template_desc_init_fields(template->fmt,
-						   &(template->fields),
-						   &(template->num_fields));
-		if (result < 0)
-			return result;
-	}
-	return result;
-}
-
 struct ima_template_desc *ima_template_desc_current(void)
 {
 	if (!ima_template)
@@ -178,13 +160,11 @@ struct ima_template_desc *ima_template_desc_current(void)
 	return ima_template;
 }
 
-int ima_init_template(void)
+int __init ima_init_template(void)
 {
-	int result;
-
-	result = init_defined_templates();
-	if (result < 0)
-		return result;
+	struct ima_template_desc *template = ima_template_desc_current();
 
-	return 0;
+	return template_desc_init_fields(template->fmt,
+					 &(template->fields),
+					 &(template->num_fields));
 }
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index 19b8e314ca96..c0379d13dbe1 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -31,6 +31,7 @@
 #define IMA_DIGSIG		0x01000000
 #define IMA_DIGSIG_REQUIRED	0x02000000
 #define IMA_PERMIT_DIRECTIO	0x04000000
+#define IMA_NEW_FILE		0x08000000
 
 #define IMA_DO_MASK		(IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \
 				 IMA_APPRAISE_SUBMASK)
@@ -116,7 +117,6 @@ struct integrity_iint_cache {
 /* rbtree tree calls to lookup, insert, delete
  * integrity data associated with an inode.
  */
-struct integrity_iint_cache *integrity_iint_insert(struct inode *inode);
 struct integrity_iint_cache *integrity_iint_find(struct inode *inode);
 
 #define INTEGRITY_KEYRING_EVM		0
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index c2f91a0cf889..b6adb94f6d52 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -33,11 +33,9 @@ MODULE_LICENSE("GPL");
  */
 struct key_type key_type_big_key = {
 	.name			= "big_key",
-	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	.preparse		= big_key_preparse,
 	.free_preparse		= big_key_free_preparse,
 	.instantiate		= generic_key_instantiate,
-	.match			= user_match,
 	.revoke			= big_key_revoke,
 	.destroy		= big_key_destroy,
 	.describe		= big_key_describe,
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 5fe443d120af..db9675db1026 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -970,7 +970,6 @@ struct key_type key_type_encrypted = {
 	.name = "encrypted",
 	.instantiate = encrypted_instantiate,
 	.update = encrypted_update,
-	.match = user_match,
 	.destroy = encrypted_destroy,
 	.describe = user_describe,
 	.read = encrypted_read,
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 5f20da01fd8d..b8960c4959a5 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -107,20 +107,16 @@ extern int iterate_over_keyring(const struct key *keyring,
 				int (*func)(const struct key *key, void *data),
 				void *data);
 
-typedef int (*key_match_func_t)(const struct key *, const void *);
-
 struct keyring_search_context {
 	struct keyring_index_key index_key;
 	const struct cred	*cred;
-	key_match_func_t	match;
-	const void		*match_data;
+	struct key_match_data	match_data;
 	unsigned		flags;
-#define KEYRING_SEARCH_LOOKUP_TYPE	0x0001	/* [as type->def_lookup_type] */
-#define KEYRING_SEARCH_NO_STATE_CHECK	0x0002	/* Skip state checks */
-#define KEYRING_SEARCH_DO_STATE_CHECK	0x0004	/* Override NO_STATE_CHECK */
-#define KEYRING_SEARCH_NO_UPDATE_TIME	0x0008	/* Don't update times */
-#define KEYRING_SEARCH_NO_CHECK_PERM	0x0010	/* Don't check permissions */
-#define KEYRING_SEARCH_DETECT_TOO_DEEP	0x0020	/* Give an error on excessive depth */
+#define KEYRING_SEARCH_NO_STATE_CHECK	0x0001	/* Skip state checks */
+#define KEYRING_SEARCH_DO_STATE_CHECK	0x0002	/* Override NO_STATE_CHECK */
+#define KEYRING_SEARCH_NO_UPDATE_TIME	0x0004	/* Don't update times */
+#define KEYRING_SEARCH_NO_CHECK_PERM	0x0008	/* Don't check permissions */
+#define KEYRING_SEARCH_DETECT_TOO_DEEP	0x0010	/* Give an error on excessive depth */
 
 	int (*iterator)(const void *object, void *iterator_data);
 
@@ -131,6 +127,8 @@ struct keyring_search_context {
 	struct timespec		now;
 };
 
+extern bool key_default_cmp(const struct key *key,
+			    const struct key_match_data *match_data);
 extern key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 				    struct keyring_search_context *ctx);
 
@@ -152,7 +150,8 @@ extern struct key *request_key_and_link(struct key_type *type,
 					struct key *dest_keyring,
 					unsigned long flags);
 
-extern int lookup_user_key_possessed(const struct key *key, const void *target);
+extern bool lookup_user_key_possessed(const struct key *key,
+				      const struct key_match_data *match_data);
 extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags,
 				 key_perm_t perm);
 #define KEY_LOOKUP_CREATE	0x01
diff --git a/security/keys/key.c b/security/keys/key.c
index 6d0cad16f002..e17ba6aefdc0 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -799,7 +799,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 	}
 
 	key_ref = ERR_PTR(-EINVAL);
-	if (!index_key.type->match || !index_key.type->instantiate ||
+	if (!index_key.type->instantiate ||
 	    (!index_key.description && !index_key.type->preparse))
 		goto error_put_type;
 
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index e26f860e5f2e..eff88a5f5d40 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -37,6 +37,8 @@ static int key_get_type_from_user(char *type,
 		return ret;
 	if (ret == 0 || ret >= len)
 		return -EINVAL;
+	if (type[0] == '.')
+		return -EPERM;
 	type[len - 1] = '\0';
 	return 0;
 }
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 8314a7d2104d..8177010174f7 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -89,7 +89,6 @@ struct key_type key_type_keyring = {
 	.preparse	= keyring_preparse,
 	.free_preparse	= keyring_free_preparse,
 	.instantiate	= keyring_instantiate,
-	.match		= user_match,
 	.revoke		= keyring_revoke,
 	.destroy	= keyring_destroy,
 	.describe	= keyring_describe,
@@ -512,6 +511,15 @@ struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid,
 EXPORT_SYMBOL(keyring_alloc);
 
 /*
+ * By default, we keys found by getting an exact match on their descriptions.
+ */
+bool key_default_cmp(const struct key *key,
+		     const struct key_match_data *match_data)
+{
+	return strcmp(key->description, match_data->raw_data) == 0;
+}
+
+/*
  * Iteration function to consider each key found.
  */
 static int keyring_search_iterator(const void *object, void *iterator_data)
@@ -545,7 +553,7 @@ static int keyring_search_iterator(const void *object, void *iterator_data)
 	}
 
 	/* keys that don't match */
-	if (!ctx->match(key, ctx->match_data)) {
+	if (!ctx->match_data.cmp(key, &ctx->match_data)) {
 		kleave(" = 0 [!match]");
 		return 0;
 	}
@@ -585,8 +593,7 @@ skipped:
  */
 static int search_keyring(struct key *keyring, struct keyring_search_context *ctx)
 {
-	if ((ctx->flags & KEYRING_SEARCH_LOOKUP_TYPE) ==
-	    KEYRING_SEARCH_LOOKUP_DIRECT) {
+	if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_DIRECT) {
 		const void *object;
 
 		object = assoc_array_find(&keyring->keys,
@@ -627,7 +634,7 @@ static bool search_nested_keyrings(struct key *keyring,
 	/* Check to see if this top-level keyring is what we are looking for
 	 * and whether it is valid or not.
 	 */
-	if (ctx->flags & KEYRING_SEARCH_LOOKUP_ITERATE ||
+	if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_ITERATE ||
 	    keyring_compare_object(keyring, &ctx->index_key)) {
 		ctx->skipped_ret = 2;
 		ctx->flags |= KEYRING_SEARCH_DO_STATE_CHECK;
@@ -885,16 +892,25 @@ key_ref_t keyring_search(key_ref_t keyring,
 		.index_key.type		= type,
 		.index_key.description	= description,
 		.cred			= current_cred(),
-		.match			= type->match,
-		.match_data		= description,
-		.flags			= (type->def_lookup_type |
-					   KEYRING_SEARCH_DO_STATE_CHECK),
+		.match_data.cmp		= key_default_cmp,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= KEYRING_SEARCH_DO_STATE_CHECK,
 	};
+	key_ref_t key;
+	int ret;
 
-	if (!ctx.match)
-		return ERR_PTR(-ENOKEY);
+	if (type->match_preparse) {
+		ret = type->match_preparse(&ctx.match_data);
+		if (ret < 0)
+			return ERR_PTR(ret);
+	}
 
-	return keyring_search_aux(keyring, &ctx);
+	key = keyring_search_aux(keyring, &ctx);
+
+	if (type->match_free)
+		type->match_free(&ctx.match_data);
+	return key;
 }
 EXPORT_SYMBOL(keyring_search);
 
@@ -1014,7 +1030,7 @@ static int keyring_detect_cycle_iterator(const void *object,
 
 	/* We might get a keyring with matching index-key that is nonetheless a
 	 * different keyring. */
-	if (key != ctx->match_data)
+	if (key != ctx->match_data.raw_data)
 		return 0;
 
 	ctx->result = ERR_PTR(-EDEADLK);
@@ -1031,14 +1047,14 @@ static int keyring_detect_cycle_iterator(const void *object,
 static int keyring_detect_cycle(struct key *A, struct key *B)
 {
 	struct keyring_search_context ctx = {
-		.index_key	= A->index_key,
-		.match_data	= A,
-		.iterator	= keyring_detect_cycle_iterator,
-		.flags		= (KEYRING_SEARCH_LOOKUP_DIRECT |
-				   KEYRING_SEARCH_NO_STATE_CHECK |
-				   KEYRING_SEARCH_NO_UPDATE_TIME |
-				   KEYRING_SEARCH_NO_CHECK_PERM |
-				   KEYRING_SEARCH_DETECT_TOO_DEEP),
+		.index_key		= A->index_key,
+		.match_data.raw_data	= A,
+		.match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT,
+		.iterator		= keyring_detect_cycle_iterator,
+		.flags			= (KEYRING_SEARCH_NO_STATE_CHECK |
+					   KEYRING_SEARCH_NO_UPDATE_TIME |
+					   KEYRING_SEARCH_NO_CHECK_PERM |
+					   KEYRING_SEARCH_DETECT_TOO_DEEP),
 	};
 
 	rcu_read_lock();
diff --git a/security/keys/proc.c b/security/keys/proc.c
index d3f6f2fd21db..972eeb336b81 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -194,10 +194,10 @@ static int proc_keys_show(struct seq_file *m, void *v)
 		.index_key.type		= key->type,
 		.index_key.description	= key->description,
 		.cred			= current_cred(),
-		.match			= lookup_user_key_possessed,
-		.match_data		= key,
-		.flags			= (KEYRING_SEARCH_NO_STATE_CHECK |
-					   KEYRING_SEARCH_LOOKUP_DIRECT),
+		.match_data.cmp		= lookup_user_key_possessed,
+		.match_data.raw_data	= key,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= KEYRING_SEARCH_NO_STATE_CHECK,
 	};
 
 	key_ref = make_key_ref(key, 0);
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index 0cf8a130a267..bd536cb221e2 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -489,9 +489,10 @@ found:
 /*
  * See if the key we're looking at is the target key.
  */
-int lookup_user_key_possessed(const struct key *key, const void *target)
+bool lookup_user_key_possessed(const struct key *key,
+			       const struct key_match_data *match_data)
 {
-	return key == target;
+	return key == match_data->raw_data;
 }
 
 /*
@@ -516,9 +517,9 @@ key_ref_t lookup_user_key(key_serial_t id, unsigned long lflags,
 			  key_perm_t perm)
 {
 	struct keyring_search_context ctx = {
-		.match	= lookup_user_key_possessed,
-		.flags	= (KEYRING_SEARCH_NO_STATE_CHECK |
-			   KEYRING_SEARCH_LOOKUP_DIRECT),
+		.match_data.cmp		= lookup_user_key_possessed,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= KEYRING_SEARCH_NO_STATE_CHECK,
 	};
 	struct request_key_auth *rka;
 	struct key *key;
@@ -673,7 +674,7 @@ try_again:
 		ctx.index_key.type		= key->type;
 		ctx.index_key.description	= key->description;
 		ctx.index_key.desc_len		= strlen(key->description);
-		ctx.match_data			= key;
+		ctx.match_data.raw_data		= key;
 		kdebug("check possessed");
 		skey_ref = search_process_keyrings(&ctx);
 		kdebug("possessed=%p", skey_ref);
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 26a94f18af94..bb4337c7ae1b 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -513,9 +513,9 @@ struct key *request_key_and_link(struct key_type *type,
 		.index_key.type		= type,
 		.index_key.description	= description,
 		.cred			= current_cred(),
-		.match			= type->match,
-		.match_data		= description,
-		.flags			= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.match_data.cmp		= key_default_cmp,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	};
 	struct key *key;
 	key_ref_t key_ref;
@@ -525,6 +525,14 @@ struct key *request_key_and_link(struct key_type *type,
 	       ctx.index_key.type->name, ctx.index_key.description,
 	       callout_info, callout_len, aux, dest_keyring, flags);
 
+	if (type->match_preparse) {
+		ret = type->match_preparse(&ctx.match_data);
+		if (ret < 0) {
+			key = ERR_PTR(ret);
+			goto error;
+		}
+	}
+
 	/* search all the process keyrings for a key */
 	key_ref = search_process_keyrings(&ctx);
 
@@ -537,7 +545,7 @@ struct key *request_key_and_link(struct key_type *type,
 			if (ret < 0) {
 				key_put(key);
 				key = ERR_PTR(ret);
-				goto error;
+				goto error_free;
 			}
 		}
 	} else if (PTR_ERR(key_ref) != -EAGAIN) {
@@ -547,12 +555,15 @@ struct key *request_key_and_link(struct key_type *type,
 		 * should consult userspace if we can */
 		key = ERR_PTR(-ENOKEY);
 		if (!callout_info)
-			goto error;
+			goto error_free;
 
 		key = construct_key_and_link(&ctx, callout_info, callout_len,
 					     aux, dest_keyring, flags);
 	}
 
+error_free:
+	if (type->match_free)
+		type->match_free(&ctx.match_data);
 error:
 	kleave(" = %p", key);
 	return key;
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
index 842e6f410d50..6639e2cb8853 100644
--- a/security/keys/request_key_auth.c
+++ b/security/keys/request_key_auth.c
@@ -44,12 +44,12 @@ struct key_type key_type_request_key_auth = {
 	.read		= request_key_auth_read,
 };
 
-int request_key_auth_preparse(struct key_preparsed_payload *prep)
+static int request_key_auth_preparse(struct key_preparsed_payload *prep)
 {
 	return 0;
 }
 
-void request_key_auth_free_preparse(struct key_preparsed_payload *prep)
+static void request_key_auth_free_preparse(struct key_preparsed_payload *prep)
 {
 }
 
@@ -246,9 +246,9 @@ struct key *key_get_instantiation_authkey(key_serial_t target_id)
 		.index_key.type		= &key_type_request_key_auth,
 		.index_key.description	= description,
 		.cred			= current_cred(),
-		.match			= user_match,
-		.match_data		= description,
-		.flags			= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.match_data.cmp		= key_default_cmp,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	};
 	struct key *authkey;
 	key_ref_t authkey_ref;
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index 6b804aa4529a..c0594cb07ada 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -1096,7 +1096,6 @@ struct key_type key_type_trusted = {
 	.name = "trusted",
 	.instantiate = trusted_instantiate,
 	.update = trusted_update,
-	.match = user_match,
 	.destroy = trusted_destroy,
 	.describe = user_describe,
 	.read = trusted_read,
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index eee340011f2b..36b47bbd3d8c 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -26,12 +26,10 @@ static int logon_vet_description(const char *desc);
  */
 struct key_type key_type_user = {
 	.name			= "user",
-	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	.preparse		= user_preparse,
 	.free_preparse		= user_free_preparse,
 	.instantiate		= generic_key_instantiate,
 	.update			= user_update,
-	.match			= user_match,
 	.revoke			= user_revoke,
 	.destroy		= user_destroy,
 	.describe		= user_describe,
@@ -48,12 +46,10 @@ EXPORT_SYMBOL_GPL(key_type_user);
  */
 struct key_type key_type_logon = {
 	.name			= "logon",
-	.def_lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
 	.preparse		= user_preparse,
 	.free_preparse		= user_free_preparse,
 	.instantiate		= generic_key_instantiate,
 	.update			= user_update,
-	.match			= user_match,
 	.revoke			= user_revoke,
 	.destroy		= user_destroy,
 	.describe		= user_describe,
@@ -139,16 +135,6 @@ error:
 EXPORT_SYMBOL_GPL(user_update);
 
 /*
- * match users on their name
- */
-int user_match(const struct key *key, const void *description)
-{
-	return strcmp(key->description, description) == 0;
-}
-
-EXPORT_SYMBOL_GPL(user_match);
-
-/*
  * dispose of the links from a revoked keyring
  * - called with the key sem write-locked
  */
diff --git a/security/security.c b/security/security.c
index e41b1a8d7644..18b35c63fc0c 100644
--- a/security/security.c
+++ b/security/security.c
@@ -775,9 +775,9 @@ int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 	return security_ops->file_fcntl(file, cmd, arg);
 }
 
-int security_file_set_fowner(struct file *file)
+void security_file_set_fowner(struct file *file)
 {
-	return security_ops->file_set_fowner(file);
+	security_ops->file_set_fowner(file);
 }
 
 int security_file_send_sigiotask(struct task_struct *tsk,
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index b0e940497e23..e66314138b38 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -481,6 +481,7 @@ next_inode:
 				list_entry(sbsec->isec_head.next,
 					   struct inode_security_struct, list);
 		struct inode *inode = isec->inode;
+		list_del_init(&isec->list);
 		spin_unlock(&sbsec->isec_lock);
 		inode = igrab(inode);
 		if (inode) {
@@ -489,7 +490,6 @@ next_inode:
 			iput(inode);
 		}
 		spin_lock(&sbsec->isec_lock);
-		list_del_init(&isec->list);
 		goto next_inode;
 	}
 	spin_unlock(&sbsec->isec_lock);
@@ -2097,6 +2097,41 @@ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages)
 
 /* binprm security operations */
 
+static int check_nnp_nosuid(const struct linux_binprm *bprm,
+			    const struct task_security_struct *old_tsec,
+			    const struct task_security_struct *new_tsec)
+{
+	int nnp = (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS);
+	int nosuid = (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID);
+	int rc;
+
+	if (!nnp && !nosuid)
+		return 0; /* neither NNP nor nosuid */
+
+	if (new_tsec->sid == old_tsec->sid)
+		return 0; /* No change in credentials */
+
+	/*
+	 * The only transitions we permit under NNP or nosuid
+	 * are transitions to bounded SIDs, i.e. SIDs that are
+	 * guaranteed to only be allowed a subset of the permissions
+	 * of the current SID.
+	 */
+	rc = security_bounded_transition(old_tsec->sid, new_tsec->sid);
+	if (rc) {
+		/*
+		 * On failure, preserve the errno values for NNP vs nosuid.
+		 * NNP:  Operation not permitted for caller.
+		 * nosuid:  Permission denied to file.
+		 */
+		if (nnp)
+			return -EPERM;
+		else
+			return -EACCES;
+	}
+	return 0;
+}
+
 static int selinux_bprm_set_creds(struct linux_binprm *bprm)
 {
 	const struct task_security_struct *old_tsec;
@@ -2133,14 +2168,10 @@ static int selinux_bprm_set_creds(struct linux_binprm *bprm)
 		/* Reset exec SID on execve. */
 		new_tsec->exec_sid = 0;
 
-		/*
-		 * Minimize confusion: if no_new_privs or nosuid and a
-		 * transition is explicitly requested, then fail the exec.
-		 */
-		if (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)
-			return -EPERM;
-		if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
-			return -EACCES;
+		/* Fail on NNP or nosuid if not an allowed transition. */
+		rc = check_nnp_nosuid(bprm, old_tsec, new_tsec);
+		if (rc)
+			return rc;
 	} else {
 		/* Check for a default transition on this program. */
 		rc = security_transition_sid(old_tsec->sid, isec->sid,
@@ -2148,15 +2179,19 @@ static int selinux_bprm_set_creds(struct linux_binprm *bprm)
 					     &new_tsec->sid);
 		if (rc)
 			return rc;
+
+		/*
+		 * Fallback to old SID on NNP or nosuid if not an allowed
+		 * transition.
+		 */
+		rc = check_nnp_nosuid(bprm, old_tsec, new_tsec);
+		if (rc)
+			new_tsec->sid = old_tsec->sid;
 	}
 
 	ad.type = LSM_AUDIT_DATA_PATH;
 	ad.u.path = bprm->file->f_path;
 
-	if ((bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) ||
-	    (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS))
-		new_tsec->sid = old_tsec->sid;
-
 	if (new_tsec->sid == old_tsec->sid) {
 		rc = avc_has_perm(old_tsec->sid, isec->sid,
 				  SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad);
@@ -3346,14 +3381,12 @@ static int selinux_file_fcntl(struct file *file, unsigned int cmd,
 	return err;
 }
 
-static int selinux_file_set_fowner(struct file *file)
+static void selinux_file_set_fowner(struct file *file)
 {
 	struct file_security_struct *fsec;
 
 	fsec = file->f_security;
 	fsec->fown_sid = current_sid();
-
-	return 0;
 }
 
 static int selinux_file_send_sigiotask(struct task_struct *tsk,
@@ -4272,15 +4305,15 @@ static int selinux_socket_unix_may_send(struct socket *sock,
 			    &ad);
 }
 
-static int selinux_inet_sys_rcv_skb(int ifindex, char *addrp, u16 family,
-				    u32 peer_sid,
+static int selinux_inet_sys_rcv_skb(struct net *ns, int ifindex,
+				    char *addrp, u16 family, u32 peer_sid,
 				    struct common_audit_data *ad)
 {
 	int err;
 	u32 if_sid;
 	u32 node_sid;
 
-	err = sel_netif_sid(ifindex, &if_sid);
+	err = sel_netif_sid(ns, ifindex, &if_sid);
 	if (err)
 		return err;
 	err = avc_has_perm(peer_sid, if_sid,
@@ -4373,8 +4406,8 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		err = selinux_skb_peerlbl_sid(skb, family, &peer_sid);
 		if (err)
 			return err;
-		err = selinux_inet_sys_rcv_skb(skb->skb_iif, addrp, family,
-					       peer_sid, &ad);
+		err = selinux_inet_sys_rcv_skb(sock_net(sk), skb->skb_iif,
+					       addrp, family, peer_sid, &ad);
 		if (err) {
 			selinux_netlbl_err(skb, err, 0);
 			return err;
@@ -4692,10 +4725,9 @@ static int selinux_nlmsg_perm(struct sock *sk, struct sk_buff *skb)
 	err = selinux_nlmsg_lookup(sksec->sclass, nlh->nlmsg_type, &perm);
 	if (err) {
 		if (err == -EINVAL) {
-			audit_log(current->audit_context, GFP_KERNEL, AUDIT_SELINUX_ERR,
-				  "SELinux:  unrecognized netlink message"
-				  " type=%hu for sclass=%hu\n",
-				  nlh->nlmsg_type, sksec->sclass);
+			WARN_ONCE(1, "selinux_nlmsg_perm: unrecognized netlink message:"
+				  " protocol=%hu nlmsg_type=%hu sclass=%hu\n",
+				  sk->sk_protocol, nlh->nlmsg_type, sksec->sclass);
 			if (!selinux_enforcing || security_get_allow_unknown())
 				err = 0;
 		}
@@ -4713,7 +4745,8 @@ out:
 
 #ifdef CONFIG_NETFILTER
 
-static unsigned int selinux_ip_forward(struct sk_buff *skb, int ifindex,
+static unsigned int selinux_ip_forward(struct sk_buff *skb,
+				       const struct net_device *indev,
 				       u16 family)
 {
 	int err;
@@ -4739,14 +4772,14 @@ static unsigned int selinux_ip_forward(struct sk_buff *skb, int ifindex,
 
 	ad.type = LSM_AUDIT_DATA_NET;
 	ad.u.net = &net;
-	ad.u.net->netif = ifindex;
+	ad.u.net->netif = indev->ifindex;
 	ad.u.net->family = family;
 	if (selinux_parse_skb(skb, &ad, &addrp, 1, NULL) != 0)
 		return NF_DROP;
 
 	if (peerlbl_active) {
-		err = selinux_inet_sys_rcv_skb(ifindex, addrp, family,
-					       peer_sid, &ad);
+		err = selinux_inet_sys_rcv_skb(dev_net(indev), indev->ifindex,
+					       addrp, family, peer_sid, &ad);
 		if (err) {
 			selinux_netlbl_err(skb, err, 1);
 			return NF_DROP;
@@ -4775,7 +4808,7 @@ static unsigned int selinux_ipv4_forward(const struct nf_hook_ops *ops,
 					 const struct net_device *out,
 					 int (*okfn)(struct sk_buff *))
 {
-	return selinux_ip_forward(skb, in->ifindex, PF_INET);
+	return selinux_ip_forward(skb, in, PF_INET);
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
@@ -4785,7 +4818,7 @@ static unsigned int selinux_ipv6_forward(const struct nf_hook_ops *ops,
 					 const struct net_device *out,
 					 int (*okfn)(struct sk_buff *))
 {
-	return selinux_ip_forward(skb, in->ifindex, PF_INET6);
+	return selinux_ip_forward(skb, in, PF_INET6);
 }
 #endif	/* IPV6 */
 
@@ -4873,11 +4906,13 @@ static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb,
 	return NF_ACCEPT;
 }
 
-static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
+static unsigned int selinux_ip_postroute(struct sk_buff *skb,
+					 const struct net_device *outdev,
 					 u16 family)
 {
 	u32 secmark_perm;
 	u32 peer_sid;
+	int ifindex = outdev->ifindex;
 	struct sock *sk;
 	struct common_audit_data ad;
 	struct lsm_network_audit net = {0,};
@@ -4958,6 +4993,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 			case PF_INET6:
 				if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
 					return NF_ACCEPT;
+				break;
 			default:
 				return NF_DROP_ERR(-ECONNREFUSED);
 			}
@@ -4989,7 +5025,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex,
 		u32 if_sid;
 		u32 node_sid;
 
-		if (sel_netif_sid(ifindex, &if_sid))
+		if (sel_netif_sid(dev_net(outdev), ifindex, &if_sid))
 			return NF_DROP;
 		if (avc_has_perm(peer_sid, if_sid,
 				 SECCLASS_NETIF, NETIF__EGRESS, &ad))
@@ -5011,7 +5047,7 @@ static unsigned int selinux_ipv4_postroute(const struct nf_hook_ops *ops,
 					   const struct net_device *out,
 					   int (*okfn)(struct sk_buff *))
 {
-	return selinux_ip_postroute(skb, out->ifindex, PF_INET);
+	return selinux_ip_postroute(skb, out, PF_INET);
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
@@ -5021,7 +5057,7 @@ static unsigned int selinux_ipv6_postroute(const struct nf_hook_ops *ops,
 					   const struct net_device *out,
 					   int (*okfn)(struct sk_buff *))
 {
-	return selinux_ip_postroute(skb, out->ifindex, PF_INET6);
+	return selinux_ip_postroute(skb, out, PF_INET6);
 }
 #endif	/* IPV6 */
 
@@ -6035,7 +6071,7 @@ security_initcall(selinux_init);
 
 #if defined(CONFIG_NETFILTER)
 
-static struct nf_hook_ops selinux_ipv4_ops[] = {
+static struct nf_hook_ops selinux_nf_ops[] = {
 	{
 		.hook =		selinux_ipv4_postroute,
 		.owner =	THIS_MODULE,
@@ -6056,12 +6092,8 @@ static struct nf_hook_ops selinux_ipv4_ops[] = {
 		.pf =		NFPROTO_IPV4,
 		.hooknum =	NF_INET_LOCAL_OUT,
 		.priority =	NF_IP_PRI_SELINUX_FIRST,
-	}
-};
-
+	},
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-
-static struct nf_hook_ops selinux_ipv6_ops[] = {
 	{
 		.hook =		selinux_ipv6_postroute,
 		.owner =	THIS_MODULE,
@@ -6075,32 +6107,24 @@ static struct nf_hook_ops selinux_ipv6_ops[] = {
 		.pf =		NFPROTO_IPV6,
 		.hooknum =	NF_INET_FORWARD,
 		.priority =	NF_IP6_PRI_SELINUX_FIRST,
-	}
-};
-
+	},
 #endif	/* IPV6 */
+};
 
 static int __init selinux_nf_ip_init(void)
 {
-	int err = 0;
+	int err;
 
 	if (!selinux_enabled)
-		goto out;
+		return 0;
 
 	printk(KERN_DEBUG "SELinux:  Registering netfilter hooks\n");
 
-	err = nf_register_hooks(selinux_ipv4_ops, ARRAY_SIZE(selinux_ipv4_ops));
-	if (err)
-		panic("SELinux: nf_register_hooks for IPv4: error %d\n", err);
-
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-	err = nf_register_hooks(selinux_ipv6_ops, ARRAY_SIZE(selinux_ipv6_ops));
+	err = nf_register_hooks(selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops));
 	if (err)
-		panic("SELinux: nf_register_hooks for IPv6: error %d\n", err);
-#endif	/* IPV6 */
+		panic("SELinux: nf_register_hooks: error %d\n", err);
 
-out:
-	return err;
+	return 0;
 }
 
 __initcall(selinux_nf_ip_init);
@@ -6110,10 +6134,7 @@ static void selinux_nf_ip_exit(void)
 {
 	printk(KERN_DEBUG "SELinux:  Unregistering netfilter hooks\n");
 
-	nf_unregister_hooks(selinux_ipv4_ops, ARRAY_SIZE(selinux_ipv4_ops));
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-	nf_unregister_hooks(selinux_ipv6_ops, ARRAY_SIZE(selinux_ipv6_ops));
-#endif	/* IPV6 */
+	nf_unregister_hooks(selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops));
 }
 #endif
 
diff --git a/security/selinux/include/netif.h b/security/selinux/include/netif.h
index 57c6eae81eac..c72145444090 100644
--- a/security/selinux/include/netif.h
+++ b/security/selinux/include/netif.h
@@ -17,9 +17,11 @@
 #ifndef _SELINUX_NETIF_H_
 #define _SELINUX_NETIF_H_
 
+#include <net/net_namespace.h>
+
 void sel_netif_flush(void);
 
-int sel_netif_sid(int ifindex, u32 *sid);
+int sel_netif_sid(struct net *ns, int ifindex, u32 *sid);
 
 #endif	/* _SELINUX_NETIF_H_ */
 
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index 078e553f52f2..81fa718d5cb3 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -24,6 +24,7 @@
 #include <linux/binfmts.h>
 #include <linux/in.h>
 #include <linux/spinlock.h>
+#include <net/net_namespace.h>
 #include "flask.h"
 #include "avc.h"
 
@@ -78,6 +79,7 @@ struct ipc_security_struct {
 };
 
 struct netif_security_struct {
+	struct net *ns;			/* network namespace */
 	int ifindex;			/* device index */
 	u32 sid;			/* SID for this interface */
 };
diff --git a/security/selinux/netif.c b/security/selinux/netif.c
index 50ce177d71a0..e607b4473ef6 100644
--- a/security/selinux/netif.c
+++ b/security/selinux/netif.c
@@ -45,6 +45,7 @@ static struct list_head sel_netif_hash[SEL_NETIF_HASH_SIZE];
 
 /**
  * sel_netif_hashfn - Hashing function for the interface table
+ * @ns: the network namespace
  * @ifindex: the network interface
  *
  * Description:
@@ -52,13 +53,14 @@ static struct list_head sel_netif_hash[SEL_NETIF_HASH_SIZE];
  * bucket number for the given interface.
  *
  */
-static inline u32 sel_netif_hashfn(int ifindex)
+static inline u32 sel_netif_hashfn(const struct net *ns, int ifindex)
 {
-	return (ifindex & (SEL_NETIF_HASH_SIZE - 1));
+	return (((uintptr_t)ns + ifindex) & (SEL_NETIF_HASH_SIZE - 1));
 }
 
 /**
  * sel_netif_find - Search for an interface record
+ * @ns: the network namespace
  * @ifindex: the network interface
  *
  * Description:
@@ -66,15 +68,15 @@ static inline u32 sel_netif_hashfn(int ifindex)
  * If an entry can not be found in the table return NULL.
  *
  */
-static inline struct sel_netif *sel_netif_find(int ifindex)
+static inline struct sel_netif *sel_netif_find(const struct net *ns,
+					       int ifindex)
 {
-	int idx = sel_netif_hashfn(ifindex);
+	int idx = sel_netif_hashfn(ns, ifindex);
 	struct sel_netif *netif;
 
 	list_for_each_entry_rcu(netif, &sel_netif_hash[idx], list)
-		/* all of the devices should normally fit in the hash, so we
-		 * optimize for that case */
-		if (likely(netif->nsec.ifindex == ifindex))
+		if (net_eq(netif->nsec.ns, ns) &&
+		    netif->nsec.ifindex == ifindex)
 			return netif;
 
 	return NULL;
@@ -96,7 +98,7 @@ static int sel_netif_insert(struct sel_netif *netif)
 	if (sel_netif_total >= SEL_NETIF_HASH_MAX)
 		return -ENOSPC;
 
-	idx = sel_netif_hashfn(netif->nsec.ifindex);
+	idx = sel_netif_hashfn(netif->nsec.ns, netif->nsec.ifindex);
 	list_add_rcu(&netif->list, &sel_netif_hash[idx]);
 	sel_netif_total++;
 
@@ -120,6 +122,7 @@ static void sel_netif_destroy(struct sel_netif *netif)
 
 /**
  * sel_netif_sid_slow - Lookup the SID of a network interface using the policy
+ * @ns: the network namespace
  * @ifindex: the network interface
  * @sid: interface SID
  *
@@ -130,7 +133,7 @@ static void sel_netif_destroy(struct sel_netif *netif)
  * failure.
  *
  */
-static int sel_netif_sid_slow(int ifindex, u32 *sid)
+static int sel_netif_sid_slow(struct net *ns, int ifindex, u32 *sid)
 {
 	int ret;
 	struct sel_netif *netif;
@@ -140,7 +143,7 @@ static int sel_netif_sid_slow(int ifindex, u32 *sid)
 	/* NOTE: we always use init's network namespace since we don't
 	 * currently support containers */
 
-	dev = dev_get_by_index(&init_net, ifindex);
+	dev = dev_get_by_index(ns, ifindex);
 	if (unlikely(dev == NULL)) {
 		printk(KERN_WARNING
 		       "SELinux: failure in sel_netif_sid_slow(),"
@@ -149,7 +152,7 @@ static int sel_netif_sid_slow(int ifindex, u32 *sid)
 	}
 
 	spin_lock_bh(&sel_netif_lock);
-	netif = sel_netif_find(ifindex);
+	netif = sel_netif_find(ns, ifindex);
 	if (netif != NULL) {
 		*sid = netif->nsec.sid;
 		ret = 0;
@@ -163,6 +166,7 @@ static int sel_netif_sid_slow(int ifindex, u32 *sid)
 	ret = security_netif_sid(dev->name, &new->nsec.sid);
 	if (ret != 0)
 		goto out;
+	new->nsec.ns = ns;
 	new->nsec.ifindex = ifindex;
 	ret = sel_netif_insert(new);
 	if (ret != 0)
@@ -184,6 +188,7 @@ out:
 
 /**
  * sel_netif_sid - Lookup the SID of a network interface
+ * @ns: the network namespace
  * @ifindex: the network interface
  * @sid: interface SID
  *
@@ -195,12 +200,12 @@ out:
  * on failure.
  *
  */
-int sel_netif_sid(int ifindex, u32 *sid)
+int sel_netif_sid(struct net *ns, int ifindex, u32 *sid)
 {
 	struct sel_netif *netif;
 
 	rcu_read_lock();
-	netif = sel_netif_find(ifindex);
+	netif = sel_netif_find(ns, ifindex);
 	if (likely(netif != NULL)) {
 		*sid = netif->nsec.sid;
 		rcu_read_unlock();
@@ -208,11 +213,12 @@ int sel_netif_sid(int ifindex, u32 *sid)
 	}
 	rcu_read_unlock();
 
-	return sel_netif_sid_slow(ifindex, sid);
+	return sel_netif_sid_slow(ns, ifindex, sid);
 }
 
 /**
  * sel_netif_kill - Remove an entry from the network interface table
+ * @ns: the network namespace
  * @ifindex: the network interface
  *
  * Description:
@@ -220,13 +226,13 @@ int sel_netif_sid(int ifindex, u32 *sid)
  * table if it exists.
  *
  */
-static void sel_netif_kill(int ifindex)
+static void sel_netif_kill(const struct net *ns, int ifindex)
 {
 	struct sel_netif *netif;
 
 	rcu_read_lock();
 	spin_lock_bh(&sel_netif_lock);
-	netif = sel_netif_find(ifindex);
+	netif = sel_netif_find(ns, ifindex);
 	if (netif)
 		sel_netif_destroy(netif);
 	spin_unlock_bh(&sel_netif_lock);
@@ -257,11 +263,8 @@ static int sel_netif_netdev_notifier_handler(struct notifier_block *this,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (dev_net(dev) != &init_net)
-		return NOTIFY_DONE;
-
 	if (event == NETDEV_DOWN)
-		sel_netif_kill(dev->ifindex);
+		sel_netif_kill(dev_net(dev), dev->ifindex);
 
 	return NOTIFY_DONE;
 }
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 2aa9d172dc7e..a1d3944751b9 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -728,7 +728,7 @@ static int security_validtrans_handle_fail(struct context *ocontext,
 	if (context_struct_to_string(tcontext, &t, &tlen))
 		goto out;
 	audit_log(current->audit_context, GFP_ATOMIC, AUDIT_SELINUX_ERR,
-		  "security_validate_transition:  denied for"
+		  "op=security_validate_transition seresult=denied"
 		  " oldcontext=%s newcontext=%s taskcontext=%s tclass=%s",
 		  o, n, t, sym_name(&policydb, SYM_CLASSES, tclass-1));
 out:
@@ -877,7 +877,7 @@ int security_bounded_transition(u32 old_sid, u32 new_sid)
 			audit_log(current->audit_context,
 				  GFP_ATOMIC, AUDIT_SELINUX_ERR,
 				  "op=security_bounded_transition "
-				  "result=denied "
+				  "seresult=denied "
 				  "oldcontext=%s newcontext=%s",
 				  old_name, new_name);
 		}
@@ -1351,8 +1351,8 @@ static int compute_sid_handle_invalid_context(
 	if (context_struct_to_string(newcontext, &n, &nlen))
 		goto out;
 	audit_log(current->audit_context, GFP_ATOMIC, AUDIT_SELINUX_ERR,
-		  "security_compute_sid:  invalid context %s"
-		  " for scontext=%s"
+		  "op=security_compute_sid invalid_context=%s"
+		  " scontext=%s"
 		  " tcontext=%s"
 		  " tclass=%s",
 		  n, s, t, sym_name(&policydb, SYM_CLASSES, tclass-1));
@@ -2607,8 +2607,10 @@ int security_sid_mls_copy(u32 sid, u32 mls_sid, u32 *new_sid)
 		rc = convert_context_handle_invalid_context(&newcon);
 		if (rc) {
 			if (!context_struct_to_string(&newcon, &s, &len)) {
-				audit_log(current->audit_context, GFP_ATOMIC, AUDIT_SELINUX_ERR,
-					  "security_sid_mls_copy: invalid context %s", s);
+				audit_log(current->audit_context,
+					  GFP_ATOMIC, AUDIT_SELINUX_ERR,
+					  "op=security_sid_mls_copy "
+					  "invalid_context=%s", s);
 				kfree(s);
 			}
 			goto out_unlock;
diff --git a/security/smack/Kconfig b/security/smack/Kconfig
index e69de9c642b7..b065f9789418 100644
--- a/security/smack/Kconfig
+++ b/security/smack/Kconfig
@@ -12,3 +12,19 @@ config SECURITY_SMACK
 	  of other mandatory security schemes.
 	  If you are unsure how to answer this question, answer N.
 
+config SECURITY_SMACK_BRINGUP
+	bool "Reporting on access granted by Smack rules"
+	depends on SECURITY_SMACK
+	default n
+	help
+	  Enable the bring-up ("b") access mode in Smack rules.
+	  When access is granted by a rule with the "b" mode a
+	  message about the access requested is generated. The
+	  intention is that a process can be granted a wide set
+	  of access initially with the bringup mode set on the
+	  rules. The developer can use the information to
+	  identify which rules are necessary and what accesses
+	  may be inappropriate. The developer can reduce the
+	  access rule set once the behavior is well understood.
+	  This is a superior mechanism to the oft abused
+	  "permissive" mode of other systems.
diff --git a/security/smack/smack.h b/security/smack/smack.h
index 020307ef0972..b828a379377c 100644
--- a/security/smack/smack.h
+++ b/security/smack/smack.h
@@ -71,11 +71,11 @@ struct smack_known {
 #define SMK_CIPSOLEN	24
 
 struct superblock_smack {
-	char		*smk_root;
-	char		*smk_floor;
-	char		*smk_hat;
-	char		*smk_default;
-	int		smk_initialized;
+	struct smack_known	*smk_root;
+	struct smack_known	*smk_floor;
+	struct smack_known	*smk_hat;
+	struct smack_known	*smk_default;
+	int			smk_initialized;
 };
 
 struct socket_smack {
@@ -88,7 +88,7 @@ struct socket_smack {
  * Inode smack data
  */
 struct inode_smack {
-	char			*smk_inode;	/* label of the fso */
+	struct smack_known	*smk_inode;	/* label of the fso */
 	struct smack_known	*smk_task;	/* label of the task */
 	struct smack_known	*smk_mmap;	/* label of the mmap domain */
 	struct mutex		smk_lock;	/* initialization lock */
@@ -112,7 +112,7 @@ struct task_smack {
 struct smack_rule {
 	struct list_head	list;
 	struct smack_known	*smk_subject;
-	char			*smk_object;
+	struct smack_known	*smk_object;
 	int			smk_access;
 };
 
@@ -123,7 +123,7 @@ struct smk_netlbladdr {
 	struct list_head	list;
 	struct sockaddr_in	smk_host;	/* network address */
 	struct in_addr		smk_mask;	/* network mask */
-	char			*smk_label;	/* label */
+	struct smack_known	*smk_label;	/* label */
 };
 
 /*
@@ -191,6 +191,7 @@ struct smk_port_label {
  */
 #define MAY_TRANSMUTE	0x00001000	/* Controls directory labeling */
 #define MAY_LOCK	0x00002000	/* Locks should be writes, but ... */
+#define MAY_BRINGUP	0x00004000	/* Report use of this rule */
 
 /*
  * Just to make the common cases easier to deal with
@@ -200,9 +201,9 @@ struct smk_port_label {
 #define MAY_NOT		0
 
 /*
- * Number of access types used by Smack (rwxatl)
+ * Number of access types used by Smack (rwxatlb)
  */
-#define SMK_NUM_ACCESS_TYPE 6
+#define SMK_NUM_ACCESS_TYPE 7
 
 /* SMACK data */
 struct smack_audit_data {
@@ -226,23 +227,23 @@ struct smk_audit_info {
 /*
  * These functions are in smack_lsm.c
  */
-struct inode_smack *new_inode_smack(char *);
+struct inode_smack *new_inode_smack(struct smack_known *);
 
 /*
  * These functions are in smack_access.c
  */
 int smk_access_entry(char *, char *, struct list_head *);
-int smk_access(struct smack_known *, char *, int, struct smk_audit_info *);
-int smk_tskacc(struct task_smack *, char *, u32, struct smk_audit_info *);
-int smk_curacc(char *, u32, struct smk_audit_info *);
+int smk_access(struct smack_known *, struct smack_known *,
+	       int, struct smk_audit_info *);
+int smk_tskacc(struct task_smack *, struct smack_known *,
+	       u32, struct smk_audit_info *);
+int smk_curacc(struct smack_known *, u32, struct smk_audit_info *);
 struct smack_known *smack_from_secid(const u32);
 char *smk_parse_smack(const char *string, int len);
 int smk_netlbl_mls(int, char *, struct netlbl_lsm_secattr *, int);
-char *smk_import(const char *, int);
 struct smack_known *smk_import_entry(const char *, int);
 void smk_insert_entry(struct smack_known *skp);
 struct smack_known *smk_find_entry(const char *);
-u32 smack_to_secid(const char *);
 
 /*
  * Shared data.
@@ -252,7 +253,7 @@ extern int smack_cipso_mapped;
 extern struct smack_known *smack_net_ambient;
 extern struct smack_known *smack_onlycap;
 extern struct smack_known *smack_syslog_label;
-extern const char *smack_cipso_option;
+extern struct smack_known smack_cipso_option;
 extern int smack_ptrace_rule;
 
 extern struct smack_known smack_known_floor;
@@ -281,9 +282,9 @@ static inline int smk_inode_transmutable(const struct inode *isp)
 }
 
 /*
- * Present a pointer to the smack label in an inode blob.
+ * Present a pointer to the smack label entry in an inode blob.
  */
-static inline char *smk_of_inode(const struct inode *isp)
+static inline struct smack_known *smk_of_inode(const struct inode *isp)
 {
 	struct inode_smack *sip = isp->i_security;
 	return sip->smk_inode;
diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c
index f97d0842e621..5b970ffde024 100644
--- a/security/smack/smack_access.c
+++ b/security/smack/smack_access.c
@@ -94,7 +94,7 @@ int smk_access_entry(char *subject_label, char *object_label,
 	struct smack_rule *srp;
 
 	list_for_each_entry_rcu(srp, rule_list, list) {
-		if (srp->smk_object == object_label &&
+		if (srp->smk_object->smk_known == object_label &&
 		    srp->smk_subject->smk_known == subject_label) {
 			may = srp->smk_access;
 			break;
@@ -111,8 +111,8 @@ int smk_access_entry(char *subject_label, char *object_label,
 
 /**
  * smk_access - determine if a subject has a specific access to an object
- * @subject_known: a pointer to the subject's Smack label entry
- * @object_label: a pointer to the object's Smack label
+ * @subject: a pointer to the subject's Smack label entry
+ * @object: a pointer to the object's Smack label entry
  * @request: the access requested, in "MAY" format
  * @a : a pointer to the audit data
  *
@@ -122,8 +122,8 @@ int smk_access_entry(char *subject_label, char *object_label,
  *
  * Smack labels are shared on smack_list
  */
-int smk_access(struct smack_known *subject_known, char *object_label,
-		int request, struct smk_audit_info *a)
+int smk_access(struct smack_known *subject, struct smack_known *object,
+	       int request, struct smk_audit_info *a)
 {
 	int may = MAY_NOT;
 	int rc = 0;
@@ -133,7 +133,7 @@ int smk_access(struct smack_known *subject_known, char *object_label,
 	 *
 	 * A star subject can't access any object.
 	 */
-	if (subject_known == &smack_known_star) {
+	if (subject == &smack_known_star) {
 		rc = -EACCES;
 		goto out_audit;
 	}
@@ -142,28 +142,28 @@ int smk_access(struct smack_known *subject_known, char *object_label,
 	 * Tasks cannot be assigned the internet label.
 	 * An internet subject can access any object.
 	 */
-	if (object_label == smack_known_web.smk_known ||
-	    subject_known == &smack_known_web)
+	if (object == &smack_known_web ||
+	    subject == &smack_known_web)
 		goto out_audit;
 	/*
 	 * A star object can be accessed by any subject.
 	 */
-	if (object_label == smack_known_star.smk_known)
+	if (object == &smack_known_star)
 		goto out_audit;
 	/*
 	 * An object can be accessed in any way by a subject
 	 * with the same label.
 	 */
-	if (subject_known->smk_known == object_label)
+	if (subject->smk_known == object->smk_known)
 		goto out_audit;
 	/*
 	 * A hat subject can read any object.
 	 * A floor object can be read by any subject.
 	 */
 	if ((request & MAY_ANYREAD) == request) {
-		if (object_label == smack_known_floor.smk_known)
+		if (object == &smack_known_floor)
 			goto out_audit;
-		if (subject_known == &smack_known_hat)
+		if (subject == &smack_known_hat)
 			goto out_audit;
 	}
 	/*
@@ -174,27 +174,38 @@ int smk_access(struct smack_known *subject_known, char *object_label,
 	 * indicates there is no entry for this pair.
 	 */
 	rcu_read_lock();
-	may = smk_access_entry(subject_known->smk_known, object_label,
-				&subject_known->smk_rules);
+	may = smk_access_entry(subject->smk_known, object->smk_known,
+			       &subject->smk_rules);
 	rcu_read_unlock();
 
-	if (may > 0 && (request & may) == request)
+	if (may <= 0 || (request & may) != request) {
+		rc = -EACCES;
 		goto out_audit;
+	}
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+	/*
+	 * Return a positive value if using bringup mode.
+	 * This allows the hooks to identify checks that
+	 * succeed because of "b" rules.
+	 */
+	if (may & MAY_BRINGUP)
+		rc = MAY_BRINGUP;
+#endif
 
-	rc = -EACCES;
 out_audit:
 #ifdef CONFIG_AUDIT
 	if (a)
-		smack_log(subject_known->smk_known, object_label, request,
-				rc, a);
+		smack_log(subject->smk_known, object->smk_known,
+			  request, rc, a);
 #endif
+
 	return rc;
 }
 
 /**
  * smk_tskacc - determine if a task has a specific access to an object
- * @tsp: a pointer to the subject task
- * @obj_label: a pointer to the object's Smack label
+ * @tsp: a pointer to the subject's task
+ * @obj_known: a pointer to the object's label entry
  * @mode: the access requested, in "MAY" format
  * @a : common audit data
  *
@@ -203,24 +214,25 @@ out_audit:
  * non zero otherwise. It allows that the task may have the capability
  * to override the rules.
  */
-int smk_tskacc(struct task_smack *subject, char *obj_label,
+int smk_tskacc(struct task_smack *tsp, struct smack_known *obj_known,
 	       u32 mode, struct smk_audit_info *a)
 {
-	struct smack_known *skp = smk_of_task(subject);
+	struct smack_known *sbj_known = smk_of_task(tsp);
 	int may;
 	int rc;
 
 	/*
 	 * Check the global rule list
 	 */
-	rc = smk_access(skp, obj_label, mode, NULL);
-	if (rc == 0) {
+	rc = smk_access(sbj_known, obj_known, mode, NULL);
+	if (rc >= 0) {
 		/*
 		 * If there is an entry in the task's rule list
 		 * it can further restrict access.
 		 */
-		may = smk_access_entry(skp->smk_known, obj_label,
-					&subject->smk_rules);
+		may = smk_access_entry(sbj_known->smk_known,
+				       obj_known->smk_known,
+				       &tsp->smk_rules);
 		if (may < 0)
 			goto out_audit;
 		if ((mode & may) == mode)
@@ -237,14 +249,15 @@ int smk_tskacc(struct task_smack *subject, char *obj_label,
 out_audit:
 #ifdef CONFIG_AUDIT
 	if (a)
-		smack_log(skp->smk_known, obj_label, mode, rc, a);
+		smack_log(sbj_known->smk_known, obj_known->smk_known,
+			  mode, rc, a);
 #endif
 	return rc;
 }
 
 /**
  * smk_curacc - determine if current has a specific access to an object
- * @obj_label: a pointer to the object's Smack label
+ * @obj_known: a pointer to the object's Smack label entry
  * @mode: the access requested, in "MAY" format
  * @a : common audit data
  *
@@ -253,11 +266,12 @@ out_audit:
  * non zero otherwise. It allows that current may have the capability
  * to override the rules.
  */
-int smk_curacc(char *obj_label, u32 mode, struct smk_audit_info *a)
+int smk_curacc(struct smack_known *obj_known,
+	       u32 mode, struct smk_audit_info *a)
 {
 	struct task_smack *tsp = current_security();
 
-	return smk_tskacc(tsp, obj_label, mode, a);
+	return smk_tskacc(tsp, obj_known, mode, a);
 }
 
 #ifdef CONFIG_AUDIT
@@ -328,6 +342,13 @@ void smack_log(char *subject_label, char *object_label, int request,
 	struct smack_audit_data *sad;
 	struct common_audit_data *a = &ad->a;
 
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+	/*
+	 * The result may be positive in bringup mode.
+	 */
+	if (result > 0)
+		result = 0;
+#endif
 	/* check if we have to log the current event */
 	if (result != 0 && (log_policy & SMACK_AUDIT_DENIED) == 0)
 		return;
@@ -544,27 +565,6 @@ unlockout:
 }
 
 /**
- * smk_import - import a smack label
- * @string: a text string that might be a Smack label
- * @len: the maximum size, or zero if it is NULL terminated.
- *
- * Returns a pointer to the label in the label list that
- * matches the passed string, adding it if necessary.
- */
-char *smk_import(const char *string, int len)
-{
-	struct smack_known *skp;
-
-	/* labels cannot begin with a '-' */
-	if (string[0] == '-')
-		return NULL;
-	skp = smk_import_entry(string, len);
-	if (skp == NULL)
-		return NULL;
-	return skp->smk_known;
-}
-
-/**
  * smack_from_secid - find the Smack label associated with a secid
  * @secid: an integer that might be associated with a Smack label
  *
@@ -590,19 +590,3 @@ struct smack_known *smack_from_secid(const u32 secid)
 	rcu_read_unlock();
 	return &smack_known_invalid;
 }
-
-/**
- * smack_to_secid - find the secid associated with a Smack label
- * @smack: the Smack label
- *
- * Returns the appropriate secid if there is one,
- * otherwise 0
- */
-u32 smack_to_secid(const char *smack)
-{
-	struct smack_known *skp = smk_find_entry(smack);
-
-	if (skp == NULL)
-		return 0;
-	return skp->smk_secid;
-}
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index e6ab307ce86e..d515ec25ae9f 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -54,6 +54,151 @@
 
 LIST_HEAD(smk_ipv6_port_list);
 
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static void smk_bu_mode(int mode, char *s)
+{
+	int i = 0;
+
+	if (mode & MAY_READ)
+		s[i++] = 'r';
+	if (mode & MAY_WRITE)
+		s[i++] = 'w';
+	if (mode & MAY_EXEC)
+		s[i++] = 'x';
+	if (mode & MAY_APPEND)
+		s[i++] = 'a';
+	if (mode & MAY_TRANSMUTE)
+		s[i++] = 't';
+	if (mode & MAY_LOCK)
+		s[i++] = 'l';
+	if (i == 0)
+		s[i++] = '-';
+	s[i] = '\0';
+}
+#endif
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static int smk_bu_note(char *note, struct smack_known *sskp,
+		       struct smack_known *oskp, int mode, int rc)
+{
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+
+	if (rc <= 0)
+		return rc;
+
+	smk_bu_mode(mode, acc);
+	pr_info("Smack Bringup: (%s %s %s) %s\n",
+		sskp->smk_known, oskp->smk_known, acc, note);
+	return 0;
+}
+#else
+#define smk_bu_note(note, sskp, oskp, mode, RC) (RC)
+#endif
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static int smk_bu_current(char *note, struct smack_known *oskp,
+			  int mode, int rc)
+{
+	struct task_smack *tsp = current_security();
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+
+	if (rc <= 0)
+		return rc;
+
+	smk_bu_mode(mode, acc);
+	pr_info("Smack Bringup: (%s %s %s) %s %s\n",
+		tsp->smk_task->smk_known, oskp->smk_known,
+		acc, current->comm, note);
+	return 0;
+}
+#else
+#define smk_bu_current(note, oskp, mode, RC) (RC)
+#endif
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static int smk_bu_task(struct task_struct *otp, int mode, int rc)
+{
+	struct task_smack *tsp = current_security();
+	struct task_smack *otsp = task_security(otp);
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+
+	if (rc <= 0)
+		return rc;
+
+	smk_bu_mode(mode, acc);
+	pr_info("Smack Bringup: (%s %s %s) %s to %s\n",
+		tsp->smk_task->smk_known, otsp->smk_task->smk_known, acc,
+		current->comm, otp->comm);
+	return 0;
+}
+#else
+#define smk_bu_task(otp, mode, RC) (RC)
+#endif
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static int smk_bu_inode(struct inode *inode, int mode, int rc)
+{
+	struct task_smack *tsp = current_security();
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+
+	if (rc <= 0)
+		return rc;
+
+	smk_bu_mode(mode, acc);
+	pr_info("Smack Bringup: (%s %s %s) inode=(%s %ld) %s\n",
+		tsp->smk_task->smk_known, smk_of_inode(inode)->smk_known, acc,
+		inode->i_sb->s_id, inode->i_ino, current->comm);
+	return 0;
+}
+#else
+#define smk_bu_inode(inode, mode, RC) (RC)
+#endif
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static int smk_bu_file(struct file *file, int mode, int rc)
+{
+	struct task_smack *tsp = current_security();
+	struct smack_known *sskp = tsp->smk_task;
+	struct inode *inode = file->f_inode;
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+
+	if (rc <= 0)
+		return rc;
+
+	smk_bu_mode(mode, acc);
+	pr_info("Smack Bringup: (%s %s %s) file=(%s %ld %s) %s\n",
+		sskp->smk_known, (char *)file->f_security, acc,
+		inode->i_sb->s_id, inode->i_ino, file->f_dentry->d_name.name,
+		current->comm);
+	return 0;
+}
+#else
+#define smk_bu_file(file, mode, RC) (RC)
+#endif
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static int smk_bu_credfile(const struct cred *cred, struct file *file,
+				int mode, int rc)
+{
+	struct task_smack *tsp = cred->security;
+	struct smack_known *sskp = tsp->smk_task;
+	struct inode *inode = file->f_inode;
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+
+	if (rc <= 0)
+		return rc;
+
+	smk_bu_mode(mode, acc);
+	pr_info("Smack Bringup: (%s %s %s) file=(%s %ld %s) %s\n",
+		sskp->smk_known, smk_of_inode(inode)->smk_known, acc,
+		inode->i_sb->s_id, inode->i_ino, file->f_dentry->d_name.name,
+		current->comm);
+	return 0;
+}
+#else
+#define smk_bu_credfile(cred, file, mode, RC) (RC)
+#endif
+
 /**
  * smk_fetch - Fetch the smack label from a file.
  * @ip: a pointer to the inode
@@ -87,11 +232,11 @@ static struct smack_known *smk_fetch(const char *name, struct inode *ip,
 
 /**
  * new_inode_smack - allocate an inode security blob
- * @smack: a pointer to the Smack label to use in the blob
+ * @skp: a pointer to the Smack label entry to use in the blob
  *
  * Returns the new blob or NULL if there's no memory available
  */
-struct inode_smack *new_inode_smack(char *smack)
+struct inode_smack *new_inode_smack(struct smack_known *skp)
 {
 	struct inode_smack *isp;
 
@@ -99,7 +244,7 @@ struct inode_smack *new_inode_smack(char *smack)
 	if (isp == NULL)
 		return NULL;
 
-	isp->smk_inode = smack;
+	isp->smk_inode = skp;
 	isp->smk_flags = 0;
 	mutex_init(&isp->smk_lock);
 
@@ -178,20 +323,20 @@ static inline unsigned int smk_ptrace_mode(unsigned int mode)
 /**
  * smk_ptrace_rule_check - helper for ptrace access
  * @tracer: tracer process
- * @tracee_label: label of the process that's about to be traced,
- *                the pointer must originate from smack structures
+ * @tracee_known: label entry of the process that's about to be traced
  * @mode: ptrace attachment mode (PTRACE_MODE_*)
  * @func: name of the function that called us, used for audit
  *
  * Returns 0 on access granted, -error on error
  */
-static int smk_ptrace_rule_check(struct task_struct *tracer, char *tracee_label,
+static int smk_ptrace_rule_check(struct task_struct *tracer,
+				 struct smack_known *tracee_known,
 				 unsigned int mode, const char *func)
 {
 	int rc;
 	struct smk_audit_info ad, *saip = NULL;
 	struct task_smack *tsp;
-	struct smack_known *skp;
+	struct smack_known *tracer_known;
 
 	if ((mode & PTRACE_MODE_NOAUDIT) == 0) {
 		smk_ad_init(&ad, func, LSM_AUDIT_DATA_TASK);
@@ -200,12 +345,12 @@ static int smk_ptrace_rule_check(struct task_struct *tracer, char *tracee_label,
 	}
 
 	tsp = task_security(tracer);
-	skp = smk_of_task(tsp);
+	tracer_known = smk_of_task(tsp);
 
 	if ((mode & PTRACE_MODE_ATTACH) &&
 	    (smack_ptrace_rule == SMACK_PTRACE_EXACT ||
 	     smack_ptrace_rule == SMACK_PTRACE_DRACONIAN)) {
-		if (skp->smk_known == tracee_label)
+		if (tracer_known->smk_known == tracee_known->smk_known)
 			rc = 0;
 		else if (smack_ptrace_rule == SMACK_PTRACE_DRACONIAN)
 			rc = -EACCES;
@@ -215,13 +360,15 @@ static int smk_ptrace_rule_check(struct task_struct *tracer, char *tracee_label,
 			rc = -EACCES;
 
 		if (saip)
-			smack_log(skp->smk_known, tracee_label, 0, rc, saip);
+			smack_log(tracer_known->smk_known,
+				  tracee_known->smk_known,
+				  0, rc, saip);
 
 		return rc;
 	}
 
 	/* In case of rule==SMACK_PTRACE_DEFAULT or mode==PTRACE_MODE_READ */
-	rc = smk_tskacc(tsp, tracee_label, smk_ptrace_mode(mode), saip);
+	rc = smk_tskacc(tsp, tracee_known, smk_ptrace_mode(mode), saip);
 	return rc;
 }
 
@@ -250,7 +397,7 @@ static int smack_ptrace_access_check(struct task_struct *ctp, unsigned int mode)
 
 	skp = smk_of_task(task_security(ctp));
 
-	rc = smk_ptrace_rule_check(current, skp->smk_known, mode, __func__);
+	rc = smk_ptrace_rule_check(current, skp, mode, __func__);
 	return rc;
 }
 
@@ -273,8 +420,7 @@ static int smack_ptrace_traceme(struct task_struct *ptp)
 
 	skp = smk_of_task(current_security());
 
-	rc = smk_ptrace_rule_check(ptp, skp->smk_known,
-				   PTRACE_MODE_ATTACH, __func__);
+	rc = smk_ptrace_rule_check(ptp, skp, PTRACE_MODE_ATTACH, __func__);
 	return rc;
 }
 
@@ -318,10 +464,10 @@ static int smack_sb_alloc_security(struct super_block *sb)
 	if (sbsp == NULL)
 		return -ENOMEM;
 
-	sbsp->smk_root = smack_known_floor.smk_known;
-	sbsp->smk_default = smack_known_floor.smk_known;
-	sbsp->smk_floor = smack_known_floor.smk_known;
-	sbsp->smk_hat = smack_known_hat.smk_known;
+	sbsp->smk_root = &smack_known_floor;
+	sbsp->smk_default = &smack_known_floor;
+	sbsp->smk_floor = &smack_known_floor;
+	sbsp->smk_hat = &smack_known_hat;
 	/*
 	 * smk_initialized will be zero from kzalloc.
 	 */
@@ -405,7 +551,6 @@ static int smack_sb_kern_mount(struct super_block *sb, int flags, void *data)
 	struct smack_known *skp;
 	char *op;
 	char *commap;
-	char *nsp;
 	int transmute = 0;
 	int specified = 0;
 
@@ -421,38 +566,38 @@ static int smack_sb_kern_mount(struct super_block *sb, int flags, void *data)
 
 		if (strncmp(op, SMK_FSHAT, strlen(SMK_FSHAT)) == 0) {
 			op += strlen(SMK_FSHAT);
-			nsp = smk_import(op, 0);
-			if (nsp != NULL) {
-				sp->smk_hat = nsp;
+			skp = smk_import_entry(op, 0);
+			if (skp != NULL) {
+				sp->smk_hat = skp;
 				specified = 1;
 			}
 		} else if (strncmp(op, SMK_FSFLOOR, strlen(SMK_FSFLOOR)) == 0) {
 			op += strlen(SMK_FSFLOOR);
-			nsp = smk_import(op, 0);
-			if (nsp != NULL) {
-				sp->smk_floor = nsp;
+			skp = smk_import_entry(op, 0);
+			if (skp != NULL) {
+				sp->smk_floor = skp;
 				specified = 1;
 			}
 		} else if (strncmp(op, SMK_FSDEFAULT,
 				   strlen(SMK_FSDEFAULT)) == 0) {
 			op += strlen(SMK_FSDEFAULT);
-			nsp = smk_import(op, 0);
-			if (nsp != NULL) {
-				sp->smk_default = nsp;
+			skp = smk_import_entry(op, 0);
+			if (skp != NULL) {
+				sp->smk_default = skp;
 				specified = 1;
 			}
 		} else if (strncmp(op, SMK_FSROOT, strlen(SMK_FSROOT)) == 0) {
 			op += strlen(SMK_FSROOT);
-			nsp = smk_import(op, 0);
-			if (nsp != NULL) {
-				sp->smk_root = nsp;
+			skp = smk_import_entry(op, 0);
+			if (skp != NULL) {
+				sp->smk_root = skp;
 				specified = 1;
 			}
 		} else if (strncmp(op, SMK_FSTRANS, strlen(SMK_FSTRANS)) == 0) {
 			op += strlen(SMK_FSTRANS);
-			nsp = smk_import(op, 0);
-			if (nsp != NULL) {
-				sp->smk_root = nsp;
+			skp = smk_import_entry(op, 0);
+			if (skp != NULL) {
+				sp->smk_root = skp;
 				transmute = 1;
 				specified = 1;
 			}
@@ -469,8 +614,8 @@ static int smack_sb_kern_mount(struct super_block *sb, int flags, void *data)
 		 * Unprivileged mounts get root and default from the caller.
 		 */
 		skp = smk_of_current();
-		sp->smk_root = skp->smk_known;
-		sp->smk_default = skp->smk_known;
+		sp->smk_root = skp;
+		sp->smk_default = skp;
 	}
 	/*
 	 * Initialize the root inode.
@@ -507,6 +652,7 @@ static int smack_sb_statfs(struct dentry *dentry)
 	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
 
 	rc = smk_curacc(sbp->smk_floor, MAY_READ, &ad);
+	rc = smk_bu_current("statfs", sbp->smk_floor, MAY_READ, rc);
 	return rc;
 }
 
@@ -546,7 +692,7 @@ static int smack_bprm_set_creds(struct linux_binprm *bprm)
 		tracer = ptrace_parent(current);
 		if (likely(tracer != NULL))
 			rc = smk_ptrace_rule_check(tracer,
-						   isp->smk_task->smk_known,
+						   isp->smk_task,
 						   PTRACE_MODE_ATTACH,
 						   __func__);
 		rcu_read_unlock();
@@ -607,7 +753,7 @@ static int smack_inode_alloc_security(struct inode *inode)
 {
 	struct smack_known *skp = smk_of_current();
 
-	inode->i_security = new_inode_smack(skp->smk_known);
+	inode->i_security = new_inode_smack(skp);
 	if (inode->i_security == NULL)
 		return -ENOMEM;
 	return 0;
@@ -627,8 +773,8 @@ static void smack_inode_free_security(struct inode *inode)
 
 /**
  * smack_inode_init_security - copy out the smack from an inode
- * @inode: the inode
- * @dir: unused
+ * @inode: the newly created inode
+ * @dir: containing directory object
  * @qstr: unused
  * @name: where to put the attribute name
  * @value: where to put the attribute value
@@ -642,8 +788,8 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir,
 {
 	struct inode_smack *issp = inode->i_security;
 	struct smack_known *skp = smk_of_current();
-	char *isp = smk_of_inode(inode);
-	char *dsp = smk_of_inode(dir);
+	struct smack_known *isp = smk_of_inode(inode);
+	struct smack_known *dsp = smk_of_inode(dir);
 	int may;
 
 	if (name)
@@ -651,7 +797,8 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir,
 
 	if (value) {
 		rcu_read_lock();
-		may = smk_access_entry(skp->smk_known, dsp, &skp->smk_rules);
+		may = smk_access_entry(skp->smk_known, dsp->smk_known,
+				       &skp->smk_rules);
 		rcu_read_unlock();
 
 		/*
@@ -666,13 +813,13 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir,
 			issp->smk_flags |= SMK_INODE_CHANGED;
 		}
 
-		*value = kstrdup(isp, GFP_NOFS);
+		*value = kstrdup(isp->smk_known, GFP_NOFS);
 		if (*value == NULL)
 			return -ENOMEM;
 	}
 
 	if (len)
-		*len = strlen(isp) + 1;
+		*len = strlen(isp->smk_known);
 
 	return 0;
 }
@@ -688,7 +835,7 @@ static int smack_inode_init_security(struct inode *inode, struct inode *dir,
 static int smack_inode_link(struct dentry *old_dentry, struct inode *dir,
 			    struct dentry *new_dentry)
 {
-	char *isp;
+	struct smack_known *isp;
 	struct smk_audit_info ad;
 	int rc;
 
@@ -697,11 +844,13 @@ static int smack_inode_link(struct dentry *old_dentry, struct inode *dir,
 
 	isp = smk_of_inode(old_dentry->d_inode);
 	rc = smk_curacc(isp, MAY_WRITE, &ad);
+	rc = smk_bu_inode(old_dentry->d_inode, MAY_WRITE, rc);
 
 	if (rc == 0 && new_dentry->d_inode != NULL) {
 		isp = smk_of_inode(new_dentry->d_inode);
 		smk_ad_setfield_u_fs_path_dentry(&ad, new_dentry);
 		rc = smk_curacc(isp, MAY_WRITE, &ad);
+		rc = smk_bu_inode(new_dentry->d_inode, MAY_WRITE, rc);
 	}
 
 	return rc;
@@ -728,6 +877,7 @@ static int smack_inode_unlink(struct inode *dir, struct dentry *dentry)
 	 * You need write access to the thing you're unlinking
 	 */
 	rc = smk_curacc(smk_of_inode(ip), MAY_WRITE, &ad);
+	rc = smk_bu_inode(ip, MAY_WRITE, rc);
 	if (rc == 0) {
 		/*
 		 * You also need write access to the containing directory
@@ -735,6 +885,7 @@ static int smack_inode_unlink(struct inode *dir, struct dentry *dentry)
 		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_INODE);
 		smk_ad_setfield_u_fs_inode(&ad, dir);
 		rc = smk_curacc(smk_of_inode(dir), MAY_WRITE, &ad);
+		rc = smk_bu_inode(dir, MAY_WRITE, rc);
 	}
 	return rc;
 }
@@ -759,6 +910,7 @@ static int smack_inode_rmdir(struct inode *dir, struct dentry *dentry)
 	 * You need write access to the thing you're removing
 	 */
 	rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
+	rc = smk_bu_inode(dentry->d_inode, MAY_WRITE, rc);
 	if (rc == 0) {
 		/*
 		 * You also need write access to the containing directory
@@ -766,6 +918,7 @@ static int smack_inode_rmdir(struct inode *dir, struct dentry *dentry)
 		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_INODE);
 		smk_ad_setfield_u_fs_inode(&ad, dir);
 		rc = smk_curacc(smk_of_inode(dir), MAY_WRITE, &ad);
+		rc = smk_bu_inode(dir, MAY_WRITE, rc);
 	}
 
 	return rc;
@@ -773,10 +926,10 @@ static int smack_inode_rmdir(struct inode *dir, struct dentry *dentry)
 
 /**
  * smack_inode_rename - Smack check on rename
- * @old_inode: the old directory
- * @old_dentry: unused
- * @new_inode: the new directory
- * @new_dentry: unused
+ * @old_inode: unused
+ * @old_dentry: the old object
+ * @new_inode: unused
+ * @new_dentry: the new object
  *
  * Read and write access is required on both the old and
  * new directories.
@@ -789,7 +942,7 @@ static int smack_inode_rename(struct inode *old_inode,
 			      struct dentry *new_dentry)
 {
 	int rc;
-	char *isp;
+	struct smack_known *isp;
 	struct smk_audit_info ad;
 
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
@@ -797,11 +950,13 @@ static int smack_inode_rename(struct inode *old_inode,
 
 	isp = smk_of_inode(old_dentry->d_inode);
 	rc = smk_curacc(isp, MAY_READWRITE, &ad);
+	rc = smk_bu_inode(old_dentry->d_inode, MAY_READWRITE, rc);
 
 	if (rc == 0 && new_dentry->d_inode != NULL) {
 		isp = smk_of_inode(new_dentry->d_inode);
 		smk_ad_setfield_u_fs_path_dentry(&ad, new_dentry);
 		rc = smk_curacc(isp, MAY_READWRITE, &ad);
+		rc = smk_bu_inode(new_dentry->d_inode, MAY_READWRITE, rc);
 	}
 	return rc;
 }
@@ -819,6 +974,7 @@ static int smack_inode_permission(struct inode *inode, int mask)
 {
 	struct smk_audit_info ad;
 	int no_block = mask & MAY_NOT_BLOCK;
+	int rc;
 
 	mask &= (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND);
 	/*
@@ -832,7 +988,9 @@ static int smack_inode_permission(struct inode *inode, int mask)
 		return -ECHILD;
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_INODE);
 	smk_ad_setfield_u_fs_inode(&ad, inode);
-	return smk_curacc(smk_of_inode(inode), mask, &ad);
+	rc = smk_curacc(smk_of_inode(inode), mask, &ad);
+	rc = smk_bu_inode(inode, mask, rc);
+	return rc;
 }
 
 /**
@@ -845,6 +1003,8 @@ static int smack_inode_permission(struct inode *inode, int mask)
 static int smack_inode_setattr(struct dentry *dentry, struct iattr *iattr)
 {
 	struct smk_audit_info ad;
+	int rc;
+
 	/*
 	 * Need to allow for clearing the setuid bit.
 	 */
@@ -853,12 +1013,14 @@ static int smack_inode_setattr(struct dentry *dentry, struct iattr *iattr)
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
 	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
 
-	return smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
+	rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
+	rc = smk_bu_inode(dentry->d_inode, MAY_WRITE, rc);
+	return rc;
 }
 
 /**
  * smack_inode_getattr - Smack check for getting attributes
- * @mnt: unused
+ * @mnt: vfsmount of the object
  * @dentry: the object
  *
  * Returns 0 if access is permitted, an error code otherwise
@@ -867,21 +1029,24 @@ static int smack_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
 {
 	struct smk_audit_info ad;
 	struct path path;
+	int rc;
 
 	path.dentry = dentry;
 	path.mnt = mnt;
 
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
 	smk_ad_setfield_u_fs_path(&ad, path);
-	return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ, &ad);
+	rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ, &ad);
+	rc = smk_bu_inode(dentry->d_inode, MAY_READ, rc);
+	return rc;
 }
 
 /**
  * smack_inode_setxattr - Smack check for setting xattrs
  * @dentry: the object
  * @name: name of the attribute
- * @value: unused
- * @size: unused
+ * @value: value of the attribute
+ * @size: size of the value
  * @flags: unused
  *
  * This protects the Smack attribute explicitly.
@@ -923,7 +1088,7 @@ static int smack_inode_setxattr(struct dentry *dentry, const char *name,
 		rc = -EPERM;
 
 	if (rc == 0 && check_import) {
-		skp = smk_import_entry(value, size);
+		skp = size ? smk_import_entry(value, size) : NULL;
 		if (skp == NULL || (check_star &&
 		    (skp == &smack_known_star || skp == &smack_known_web)))
 			rc = -EINVAL;
@@ -932,8 +1097,10 @@ static int smack_inode_setxattr(struct dentry *dentry, const char *name,
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
 	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
 
-	if (rc == 0)
+	if (rc == 0) {
 		rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
+		rc = smk_bu_inode(dentry->d_inode, MAY_WRITE, rc);
+	}
 
 	return rc;
 }
@@ -963,9 +1130,9 @@ static void smack_inode_post_setxattr(struct dentry *dentry, const char *name,
 	if (strcmp(name, XATTR_NAME_SMACK) == 0) {
 		skp = smk_import_entry(value, size);
 		if (skp != NULL)
-			isp->smk_inode = skp->smk_known;
+			isp->smk_inode = skp;
 		else
-			isp->smk_inode = smack_known_invalid.smk_known;
+			isp->smk_inode = &smack_known_invalid;
 	} else if (strcmp(name, XATTR_NAME_SMACKEXEC) == 0) {
 		skp = smk_import_entry(value, size);
 		if (skp != NULL)
@@ -993,11 +1160,14 @@ static void smack_inode_post_setxattr(struct dentry *dentry, const char *name,
 static int smack_inode_getxattr(struct dentry *dentry, const char *name)
 {
 	struct smk_audit_info ad;
+	int rc;
 
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
 	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
 
-	return smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ, &ad);
+	rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_READ, &ad);
+	rc = smk_bu_inode(dentry->d_inode, MAY_READ, rc);
+	return rc;
 }
 
 /**
@@ -1033,6 +1203,7 @@ static int smack_inode_removexattr(struct dentry *dentry, const char *name)
 	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
 
 	rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
+	rc = smk_bu_inode(dentry->d_inode, MAY_WRITE, rc);
 	if (rc != 0)
 		return rc;
 
@@ -1070,14 +1241,14 @@ static int smack_inode_getsecurity(const struct inode *inode,
 	struct socket *sock;
 	struct super_block *sbp;
 	struct inode *ip = (struct inode *)inode;
-	char *isp;
+	struct smack_known *isp;
 	int ilen;
 	int rc = 0;
 
 	if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) {
 		isp = smk_of_inode(inode);
-		ilen = strlen(isp) + 1;
-		*buffer = isp;
+		ilen = strlen(isp->smk_known);
+		*buffer = isp->smk_known;
 		return ilen;
 	}
 
@@ -1095,15 +1266,15 @@ static int smack_inode_getsecurity(const struct inode *inode,
 	ssp = sock->sk->sk_security;
 
 	if (strcmp(name, XATTR_SMACK_IPIN) == 0)
-		isp = ssp->smk_in->smk_known;
+		isp = ssp->smk_in;
 	else if (strcmp(name, XATTR_SMACK_IPOUT) == 0)
-		isp = ssp->smk_out->smk_known;
+		isp = ssp->smk_out;
 	else
 		return -EOPNOTSUPP;
 
-	ilen = strlen(isp) + 1;
+	ilen = strlen(isp->smk_known);
 	if (rc == 0) {
-		*buffer = isp;
+		*buffer = isp->smk_known;
 		rc = ilen;
 	}
 
@@ -1122,13 +1293,12 @@ static int smack_inode_getsecurity(const struct inode *inode,
 static int smack_inode_listsecurity(struct inode *inode, char *buffer,
 				    size_t buffer_size)
 {
-	int len = strlen(XATTR_NAME_SMACK);
+	int len = sizeof(XATTR_NAME_SMACK);
 
-	if (buffer != NULL && len <= buffer_size) {
+	if (buffer != NULL && len <= buffer_size)
 		memcpy(buffer, XATTR_NAME_SMACK, len);
-		return len;
-	}
-	return -EINVAL;
+
+	return len;
 }
 
 /**
@@ -1140,7 +1310,7 @@ static void smack_inode_getsecid(const struct inode *inode, u32 *secid)
 {
 	struct inode_smack *isp = inode->i_security;
 
-	*secid = smack_to_secid(isp->smk_inode);
+	*secid = isp->smk_inode->smk_secid;
 }
 
 /*
@@ -1179,7 +1349,7 @@ static int smack_file_alloc_security(struct file *file)
 {
 	struct smack_known *skp = smk_of_current();
 
-	file->f_security = skp->smk_known;
+	file->f_security = skp;
 	return 0;
 }
 
@@ -1214,11 +1384,15 @@ static int smack_file_ioctl(struct file *file, unsigned int cmd,
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
 	smk_ad_setfield_u_fs_path(&ad, file->f_path);
 
-	if (_IOC_DIR(cmd) & _IOC_WRITE)
+	if (_IOC_DIR(cmd) & _IOC_WRITE) {
 		rc = smk_curacc(file->f_security, MAY_WRITE, &ad);
+		rc = smk_bu_file(file, MAY_WRITE, rc);
+	}
 
-	if (rc == 0 && (_IOC_DIR(cmd) & _IOC_READ))
+	if (rc == 0 && (_IOC_DIR(cmd) & _IOC_READ)) {
 		rc = smk_curacc(file->f_security, MAY_READ, &ad);
+		rc = smk_bu_file(file, MAY_READ, rc);
+	}
 
 	return rc;
 }
@@ -1233,10 +1407,13 @@ static int smack_file_ioctl(struct file *file, unsigned int cmd,
 static int smack_file_lock(struct file *file, unsigned int cmd)
 {
 	struct smk_audit_info ad;
+	int rc;
 
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
 	smk_ad_setfield_u_fs_path(&ad, file->f_path);
-	return smk_curacc(file->f_security, MAY_LOCK, &ad);
+	rc = smk_curacc(file->f_security, MAY_LOCK, &ad);
+	rc = smk_bu_file(file, MAY_LOCK, rc);
+	return rc;
 }
 
 /**
@@ -1266,12 +1443,14 @@ static int smack_file_fcntl(struct file *file, unsigned int cmd,
 		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
 		smk_ad_setfield_u_fs_path(&ad, file->f_path);
 		rc = smk_curacc(file->f_security, MAY_LOCK, &ad);
+		rc = smk_bu_file(file, MAY_LOCK, rc);
 		break;
 	case F_SETOWN:
 	case F_SETSIG:
 		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
 		smk_ad_setfield_u_fs_path(&ad, file->f_path);
 		rc = smk_curacc(file->f_security, MAY_WRITE, &ad);
+		rc = smk_bu_file(file, MAY_WRITE, rc);
 		break;
 	default:
 		break;
@@ -1298,7 +1477,7 @@ static int smack_mmap_file(struct file *file,
 	struct smack_known *mkp;
 	struct smack_rule *srp;
 	struct task_smack *tsp;
-	char *osmack;
+	struct smack_known *okp;
 	struct inode_smack *isp;
 	int may;
 	int mmay;
@@ -1324,18 +1503,19 @@ static int smack_mmap_file(struct file *file,
 	 * to that rule's object label.
 	 */
 	list_for_each_entry_rcu(srp, &skp->smk_rules, list) {
-		osmack = srp->smk_object;
+		okp = srp->smk_object;
 		/*
 		 * Matching labels always allows access.
 		 */
-		if (mkp->smk_known == osmack)
+		if (mkp->smk_known == okp->smk_known)
 			continue;
 		/*
 		 * If there is a matching local rule take
 		 * that into account as well.
 		 */
-		may = smk_access_entry(srp->smk_subject->smk_known, osmack,
-					&tsp->smk_rules);
+		may = smk_access_entry(srp->smk_subject->smk_known,
+				       okp->smk_known,
+				       &tsp->smk_rules);
 		if (may == -ENOENT)
 			may = srp->smk_access;
 		else
@@ -1352,8 +1532,8 @@ static int smack_mmap_file(struct file *file,
 		 * If there isn't one a SMACK64MMAP subject
 		 * can't have as much access as current.
 		 */
-		mmay = smk_access_entry(mkp->smk_known, osmack,
-						&mkp->smk_rules);
+		mmay = smk_access_entry(mkp->smk_known, okp->smk_known,
+					&mkp->smk_rules);
 		if (mmay == -ENOENT) {
 			rc = -EACCES;
 			break;
@@ -1362,8 +1542,8 @@ static int smack_mmap_file(struct file *file,
 		 * If there is a local entry it modifies the
 		 * potential access, too.
 		 */
-		tmay = smk_access_entry(mkp->smk_known, osmack,
-						&tsp->smk_rules);
+		tmay = smk_access_entry(mkp->smk_known, okp->smk_known,
+					&tsp->smk_rules);
 		if (tmay != -ENOENT)
 			mmay &= tmay;
 
@@ -1390,12 +1570,11 @@ static int smack_mmap_file(struct file *file,
  * Returns 0
  * Further research may be required on this one.
  */
-static int smack_file_set_fowner(struct file *file)
+static void smack_file_set_fowner(struct file *file)
 {
 	struct smack_known *skp = smk_of_current();
 
-	file->f_security = skp->smk_known;
-	return 0;
+	file->f_security = skp;
 }
 
 /**
@@ -1424,14 +1603,15 @@ static int smack_file_send_sigiotask(struct task_struct *tsk,
 	file = container_of(fown, struct file, f_owner);
 
 	/* we don't log here as rc can be overriden */
-	skp = smk_find_entry(file->f_security);
-	rc = smk_access(skp, tkp->smk_known, MAY_WRITE, NULL);
+	skp = file->f_security;
+	rc = smk_access(skp, tkp, MAY_WRITE, NULL);
+	rc = smk_bu_note("sigiotask", skp, tkp, MAY_WRITE, rc);
 	if (rc != 0 && has_capability(tsk, CAP_MAC_OVERRIDE))
 		rc = 0;
 
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
 	smk_ad_setfield_u_tsk(&ad, tsk);
-	smack_log(file->f_security, tkp->smk_known, MAY_WRITE, rc, &ad);
+	smack_log(skp->smk_known, tkp->smk_known, MAY_WRITE, rc, &ad);
 	return rc;
 }
 
@@ -1443,6 +1623,7 @@ static int smack_file_send_sigiotask(struct task_struct *tsk,
  */
 static int smack_file_receive(struct file *file)
 {
+	int rc;
 	int may = 0;
 	struct smk_audit_info ad;
 
@@ -1456,7 +1637,9 @@ static int smack_file_receive(struct file *file)
 	if (file->f_mode & FMODE_WRITE)
 		may |= MAY_WRITE;
 
-	return smk_curacc(file->f_security, may, &ad);
+	rc = smk_curacc(file->f_security, may, &ad);
+	rc = smk_bu_file(file, may, rc);
+	return rc;
 }
 
 /**
@@ -1478,12 +1661,15 @@ static int smack_file_open(struct file *file, const struct cred *cred)
 	struct smk_audit_info ad;
 	int rc;
 
-	if (smack_privileged(CAP_MAC_OVERRIDE))
+	if (smack_privileged(CAP_MAC_OVERRIDE)) {
+		file->f_security = isp->smk_inode;
 		return 0;
+	}
 
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
 	smk_ad_setfield_u_fs_path(&ad, file->f_path);
 	rc = smk_access(tsp->smk_task, isp->smk_inode, MAY_READ, &ad);
+	rc = smk_bu_credfile(cred, file, MAY_READ, rc);
 	if (rc == 0)
 		file->f_security = isp->smk_inode;
 
@@ -1622,7 +1808,7 @@ static int smack_kernel_create_files_as(struct cred *new,
 	struct inode_smack *isp = inode->i_security;
 	struct task_smack *tsp = new->security;
 
-	tsp->smk_forked = smk_find_entry(isp->smk_inode);
+	tsp->smk_forked = isp->smk_inode;
 	tsp->smk_task = tsp->smk_forked;
 	return 0;
 }
@@ -1640,10 +1826,13 @@ static int smk_curacc_on_task(struct task_struct *p, int access,
 {
 	struct smk_audit_info ad;
 	struct smack_known *skp = smk_of_task(task_security(p));
+	int rc;
 
 	smk_ad_init(&ad, caller, LSM_AUDIT_DATA_TASK);
 	smk_ad_setfield_u_tsk(&ad, p);
-	return smk_curacc(skp->smk_known, access, &ad);
+	rc = smk_curacc(skp, access, &ad);
+	rc = smk_bu_task(p, access, rc);
+	return rc;
 }
 
 /**
@@ -1797,6 +1986,7 @@ static int smack_task_kill(struct task_struct *p, struct siginfo *info,
 	struct smk_audit_info ad;
 	struct smack_known *skp;
 	struct smack_known *tkp = smk_of_task(task_security(p));
+	int rc;
 
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
 	smk_ad_setfield_u_tsk(&ad, p);
@@ -1804,15 +1994,20 @@ static int smack_task_kill(struct task_struct *p, struct siginfo *info,
 	 * Sending a signal requires that the sender
 	 * can write the receiver.
 	 */
-	if (secid == 0)
-		return smk_curacc(tkp->smk_known, MAY_WRITE, &ad);
+	if (secid == 0) {
+		rc = smk_curacc(tkp, MAY_WRITE, &ad);
+		rc = smk_bu_task(p, MAY_WRITE, rc);
+		return rc;
+	}
 	/*
 	 * If the secid isn't 0 we're dealing with some USB IO
 	 * specific behavior. This is not clean. For one thing
 	 * we can't take privilege into account.
 	 */
 	skp = smack_from_secid(secid);
-	return smk_access(skp, tkp->smk_known, MAY_WRITE, &ad);
+	rc = smk_access(skp, tkp, MAY_WRITE, &ad);
+	rc = smk_bu_note("USB signal", skp, tkp, MAY_WRITE, rc);
+	return rc;
 }
 
 /**
@@ -1846,7 +2041,7 @@ static void smack_task_to_inode(struct task_struct *p, struct inode *inode)
 	struct inode_smack *isp = inode->i_security;
 	struct smack_known *skp = smk_of_task(task_security(p));
 
-	isp->smk_inode = skp->smk_known;
+	isp->smk_inode = skp;
 }
 
 /*
@@ -1904,7 +2099,7 @@ static void smack_sk_free_security(struct sock *sk)
 *
 * Returns the label of the far end or NULL if it's not special.
 */
-static char *smack_host_label(struct sockaddr_in *sip)
+static struct smack_known *smack_host_label(struct sockaddr_in *sip)
 {
 	struct smk_netlbladdr *snp;
 	struct in_addr *siap = &sip->sin_addr;
@@ -1921,7 +2116,7 @@ static char *smack_host_label(struct sockaddr_in *sip)
 		if ((&snp->smk_host.sin_addr)->s_addr ==
 		    (siap->s_addr & (&snp->smk_mask)->s_addr)) {
 			/* we have found the special CIPSO option */
-			if (snp->smk_label == smack_cipso_option)
+			if (snp->smk_label == &smack_cipso_option)
 				return NULL;
 			return snp->smk_label;
 		}
@@ -1986,13 +2181,13 @@ static int smack_netlabel_send(struct sock *sk, struct sockaddr_in *sap)
 	struct smack_known *skp;
 	int rc;
 	int sk_lbl;
-	char *hostsp;
+	struct smack_known *hkp;
 	struct socket_smack *ssp = sk->sk_security;
 	struct smk_audit_info ad;
 
 	rcu_read_lock();
-	hostsp = smack_host_label(sap);
-	if (hostsp != NULL) {
+	hkp = smack_host_label(sap);
+	if (hkp != NULL) {
 #ifdef CONFIG_AUDIT
 		struct lsm_network_audit net;
 
@@ -2003,7 +2198,8 @@ static int smack_netlabel_send(struct sock *sk, struct sockaddr_in *sap)
 #endif
 		sk_lbl = SMACK_UNLABELED_SOCKET;
 		skp = ssp->smk_out;
-		rc = smk_access(skp, hostsp, MAY_WRITE, &ad);
+		rc = smk_access(skp, hkp, MAY_WRITE, &ad);
+		rc = smk_bu_note("IPv4 host check", skp, hkp, MAY_WRITE, rc);
 	} else {
 		sk_lbl = SMACK_CIPSO_SOCKET;
 		rc = 0;
@@ -2104,18 +2300,19 @@ static int smk_ipv6_port_check(struct sock *sk, struct sockaddr_in6 *address,
 	struct socket_smack *ssp = sk->sk_security;
 	struct smack_known *skp;
 	unsigned short port = 0;
-	char *object;
+	struct smack_known *object;
 	struct smk_audit_info ad;
+	int rc;
 #ifdef CONFIG_AUDIT
 	struct lsm_network_audit net;
 #endif
 
 	if (act == SMK_RECEIVING) {
 		skp = smack_net_ambient;
-		object = ssp->smk_in->smk_known;
+		object = ssp->smk_in;
 	} else {
 		skp = ssp->smk_out;
-		object = smack_net_ambient->smk_known;
+		object = smack_net_ambient;
 	}
 
 	/*
@@ -2142,7 +2339,7 @@ static int smk_ipv6_port_check(struct sock *sk, struct sockaddr_in6 *address,
 	list_for_each_entry(spp, &smk_ipv6_port_list, list) {
 		if (spp->smk_port != port)
 			continue;
-		object = spp->smk_in->smk_known;
+		object = spp->smk_in;
 		if (act == SMK_CONNECTING)
 			ssp->smk_packet = spp->smk_out;
 		break;
@@ -2159,7 +2356,9 @@ auditout:
 	else
 		ad.a.u.net->v6info.daddr = address->sin6_addr;
 #endif
-	return smk_access(skp, object, MAY_WRITE, &ad);
+	rc = smk_access(skp, object, MAY_WRITE, &ad);
+	rc = smk_bu_note("IPv6 port check", skp, object, MAY_WRITE, rc);
+	return rc;
 }
 
 /**
@@ -2191,7 +2390,7 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name,
 		return -EINVAL;
 
 	if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) {
-		nsp->smk_inode = skp->smk_known;
+		nsp->smk_inode = skp;
 		nsp->smk_flags |= SMK_INODE_INSTANT;
 		return 0;
 	}
@@ -2333,7 +2532,7 @@ static int smack_msg_msg_alloc_security(struct msg_msg *msg)
 {
 	struct smack_known *skp = smk_of_current();
 
-	msg->security = skp->smk_known;
+	msg->security = skp;
 	return 0;
 }
 
@@ -2354,9 +2553,9 @@ static void smack_msg_msg_free_security(struct msg_msg *msg)
  *
  * Returns a pointer to the smack value
  */
-static char *smack_of_shm(struct shmid_kernel *shp)
+static struct smack_known *smack_of_shm(struct shmid_kernel *shp)
 {
-	return (char *)shp->shm_perm.security;
+	return (struct smack_known *)shp->shm_perm.security;
 }
 
 /**
@@ -2370,7 +2569,7 @@ static int smack_shm_alloc_security(struct shmid_kernel *shp)
 	struct kern_ipc_perm *isp = &shp->shm_perm;
 	struct smack_known *skp = smk_of_current();
 
-	isp->security = skp->smk_known;
+	isp->security = skp;
 	return 0;
 }
 
@@ -2396,14 +2595,17 @@ static void smack_shm_free_security(struct shmid_kernel *shp)
  */
 static int smk_curacc_shm(struct shmid_kernel *shp, int access)
 {
-	char *ssp = smack_of_shm(shp);
+	struct smack_known *ssp = smack_of_shm(shp);
 	struct smk_audit_info ad;
+	int rc;
 
 #ifdef CONFIG_AUDIT
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
 	ad.a.u.ipc_id = shp->shm_perm.id;
 #endif
-	return smk_curacc(ssp, access, &ad);
+	rc = smk_curacc(ssp, access, &ad);
+	rc = smk_bu_current("shm", ssp, access, rc);
+	return rc;
 }
 
 /**
@@ -2478,9 +2680,9 @@ static int smack_shm_shmat(struct shmid_kernel *shp, char __user *shmaddr,
  *
  * Returns a pointer to the smack value
  */
-static char *smack_of_sem(struct sem_array *sma)
+static struct smack_known *smack_of_sem(struct sem_array *sma)
 {
-	return (char *)sma->sem_perm.security;
+	return (struct smack_known *)sma->sem_perm.security;
 }
 
 /**
@@ -2494,7 +2696,7 @@ static int smack_sem_alloc_security(struct sem_array *sma)
 	struct kern_ipc_perm *isp = &sma->sem_perm;
 	struct smack_known *skp = smk_of_current();
 
-	isp->security = skp->smk_known;
+	isp->security = skp;
 	return 0;
 }
 
@@ -2520,14 +2722,17 @@ static void smack_sem_free_security(struct sem_array *sma)
  */
 static int smk_curacc_sem(struct sem_array *sma, int access)
 {
-	char *ssp = smack_of_sem(sma);
+	struct smack_known *ssp = smack_of_sem(sma);
 	struct smk_audit_info ad;
+	int rc;
 
 #ifdef CONFIG_AUDIT
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
 	ad.a.u.ipc_id = sma->sem_perm.id;
 #endif
-	return smk_curacc(ssp, access, &ad);
+	rc = smk_curacc(ssp, access, &ad);
+	rc = smk_bu_current("sem", ssp, access, rc);
+	return rc;
 }
 
 /**
@@ -2613,7 +2818,7 @@ static int smack_msg_queue_alloc_security(struct msg_queue *msq)
 	struct kern_ipc_perm *kisp = &msq->q_perm;
 	struct smack_known *skp = smk_of_current();
 
-	kisp->security = skp->smk_known;
+	kisp->security = skp;
 	return 0;
 }
 
@@ -2634,11 +2839,11 @@ static void smack_msg_queue_free_security(struct msg_queue *msq)
  * smack_of_msq - the smack pointer for the msq
  * @msq: the object
  *
- * Returns a pointer to the smack value
+ * Returns a pointer to the smack label entry
  */
-static char *smack_of_msq(struct msg_queue *msq)
+static struct smack_known *smack_of_msq(struct msg_queue *msq)
 {
-	return (char *)msq->q_perm.security;
+	return (struct smack_known *)msq->q_perm.security;
 }
 
 /**
@@ -2650,14 +2855,17 @@ static char *smack_of_msq(struct msg_queue *msq)
  */
 static int smk_curacc_msq(struct msg_queue *msq, int access)
 {
-	char *msp = smack_of_msq(msq);
+	struct smack_known *msp = smack_of_msq(msq);
 	struct smk_audit_info ad;
+	int rc;
 
 #ifdef CONFIG_AUDIT
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
 	ad.a.u.ipc_id = msq->q_perm.id;
 #endif
-	return smk_curacc(msp, access, &ad);
+	rc = smk_curacc(msp, access, &ad);
+	rc = smk_bu_current("msq", msp, access, rc);
+	return rc;
 }
 
 /**
@@ -2750,15 +2958,18 @@ static int smack_msg_queue_msgrcv(struct msg_queue *msq, struct msg_msg *msg,
  */
 static int smack_ipc_permission(struct kern_ipc_perm *ipp, short flag)
 {
-	char *isp = ipp->security;
+	struct smack_known *iskp = ipp->security;
 	int may = smack_flags_to_may(flag);
 	struct smk_audit_info ad;
+	int rc;
 
 #ifdef CONFIG_AUDIT
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
 	ad.a.u.ipc_id = ipp->id;
 #endif
-	return smk_curacc(isp, may, &ad);
+	rc = smk_curacc(iskp, may, &ad);
+	rc = smk_bu_current("svipc", iskp, may, rc);
+	return rc;
 }
 
 /**
@@ -2768,9 +2979,9 @@ static int smack_ipc_permission(struct kern_ipc_perm *ipp, short flag)
  */
 static void smack_ipc_getsecid(struct kern_ipc_perm *ipp, u32 *secid)
 {
-	char *smack = ipp->security;
+	struct smack_known *iskp = ipp->security;
 
-	*secid = smack_to_secid(smack);
+	*secid = iskp->smk_secid;
 }
 
 /**
@@ -2787,7 +2998,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 	struct inode_smack *isp;
 	struct smack_known *skp;
 	struct smack_known *ckp = smk_of_current();
-	char *final;
+	struct smack_known *final;
 	char trattr[TRANS_TRUE_SIZE];
 	int transflag = 0;
 	int rc;
@@ -2827,8 +3038,8 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 			 * so there's no opportunity to set the mount
 			 * options.
 			 */
-			sbsp->smk_root = smack_known_star.smk_known;
-			sbsp->smk_default = smack_known_star.smk_known;
+			sbsp->smk_root = &smack_known_star;
+			sbsp->smk_default = &smack_known_star;
 		}
 		isp->smk_inode = sbsp->smk_root;
 		isp->smk_flags |= SMK_INODE_INSTANT;
@@ -2858,7 +3069,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 		 *
 		 * Cgroupfs is special
 		 */
-		final = smack_known_star.smk_known;
+		final = &smack_known_star;
 		break;
 	case DEVPTS_SUPER_MAGIC:
 		/*
@@ -2866,7 +3077,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 		 * Programs that change smack have to treat the
 		 * pty with respect.
 		 */
-		final = ckp->smk_known;
+		final = ckp;
 		break;
 	case PROC_SUPER_MAGIC:
 		/*
@@ -2880,7 +3091,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 		 * but watch out, because they're volitile,
 		 * getting recreated on every reboot.
 		 */
-		final = smack_known_star.smk_known;
+		final = &smack_known_star;
 		/*
 		 * No break.
 		 *
@@ -2899,7 +3110,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 		 * UNIX domain sockets use lower level socket data.
 		 */
 		if (S_ISSOCK(inode->i_mode)) {
-			final = smack_known_star.smk_known;
+			final = &smack_known_star;
 			break;
 		}
 		/*
@@ -2916,7 +3127,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 		dp = dget(opt_dentry);
 		skp = smk_fetch(XATTR_NAME_SMACK, inode, dp);
 		if (skp != NULL)
-			final = skp->smk_known;
+			final = skp;
 
 		/*
 		 * Transmuting directory
@@ -2965,7 +3176,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 	}
 
 	if (final == NULL)
-		isp->smk_inode = ckp->smk_known;
+		isp->smk_inode = ckp;
 	else
 		isp->smk_inode = final;
 
@@ -3090,9 +3301,13 @@ static int smack_unix_stream_connect(struct sock *sock,
 		smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
 		smk_ad_setfield_u_net_sk(&ad, other);
 #endif
-		rc = smk_access(skp, okp->smk_known, MAY_WRITE, &ad);
-		if (rc == 0)
-			rc = smk_access(okp, okp->smk_known, MAY_WRITE, NULL);
+		rc = smk_access(skp, okp, MAY_WRITE, &ad);
+		rc = smk_bu_note("UDS connect", skp, okp, MAY_WRITE, rc);
+		if (rc == 0) {
+			rc = smk_access(okp, skp, MAY_WRITE, NULL);
+			rc = smk_bu_note("UDS connect", okp, skp,
+						MAY_WRITE, rc);
+		}
 	}
 
 	/*
@@ -3118,8 +3333,8 @@ static int smack_unix_may_send(struct socket *sock, struct socket *other)
 {
 	struct socket_smack *ssp = sock->sk->sk_security;
 	struct socket_smack *osp = other->sk->sk_security;
-	struct smack_known *skp;
 	struct smk_audit_info ad;
+	int rc;
 
 #ifdef CONFIG_AUDIT
 	struct lsm_network_audit net;
@@ -3131,8 +3346,9 @@ static int smack_unix_may_send(struct socket *sock, struct socket *other)
 	if (smack_privileged(CAP_MAC_OVERRIDE))
 		return 0;
 
-	skp = ssp->smk_out;
-	return smk_access(skp, osp->smk_in->smk_known, MAY_WRITE, &ad);
+	rc = smk_access(ssp->smk_out, osp->smk_in, MAY_WRITE, &ad);
+	rc = smk_bu_note("UDS send", ssp->smk_out, osp->smk_in, MAY_WRITE, rc);
+	return rc;
 }
 
 /**
@@ -3346,7 +3562,9 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		 * This is the simplist possible security model
 		 * for networking.
 		 */
-		rc = smk_access(skp, ssp->smk_in->smk_known, MAY_WRITE, &ad);
+		rc = smk_access(skp, ssp->smk_in, MAY_WRITE, &ad);
+		rc = smk_bu_note("IPv4 delivery", skp, ssp->smk_in,
+					MAY_WRITE, rc);
 		if (rc != 0)
 			netlbl_skbuff_err(skb, rc, 0);
 		break;
@@ -3489,7 +3707,7 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 	struct netlbl_lsm_secattr secattr;
 	struct sockaddr_in addr;
 	struct iphdr *hdr;
-	char *hsp;
+	struct smack_known *hskp;
 	int rc;
 	struct smk_audit_info ad;
 #ifdef CONFIG_AUDIT
@@ -3526,7 +3744,8 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 	 * Receiving a packet requires that the other end be able to write
 	 * here. Read access is not required.
 	 */
-	rc = smk_access(skp, ssp->smk_in->smk_known, MAY_WRITE, &ad);
+	rc = smk_access(skp, ssp->smk_in, MAY_WRITE, &ad);
+	rc = smk_bu_note("IPv4 connect", skp, ssp->smk_in, MAY_WRITE, rc);
 	if (rc != 0)
 		return rc;
 
@@ -3544,10 +3763,10 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 	hdr = ip_hdr(skb);
 	addr.sin_addr.s_addr = hdr->saddr;
 	rcu_read_lock();
-	hsp = smack_host_label(&addr);
+	hskp = smack_host_label(&addr);
 	rcu_read_unlock();
 
-	if (hsp == NULL)
+	if (hskp == NULL)
 		rc = netlbl_req_setattr(req, &skp->smk_netlabel);
 	else
 		netlbl_req_delattr(req);
@@ -3599,7 +3818,7 @@ static int smack_key_alloc(struct key *key, const struct cred *cred,
 {
 	struct smack_known *skp = smk_of_task(cred->security);
 
-	key->security = skp->smk_known;
+	key->security = skp;
 	return 0;
 }
 
@@ -3630,6 +3849,7 @@ static int smack_key_permission(key_ref_t key_ref,
 	struct smk_audit_info ad;
 	struct smack_known *tkp = smk_of_task(cred->security);
 	int request = 0;
+	int rc;
 
 	keyp = key_ref_to_ptr(key_ref);
 	if (keyp == NULL)
@@ -3654,7 +3874,9 @@ static int smack_key_permission(key_ref_t key_ref,
 		request = MAY_READ;
 	if (perm & (KEY_NEED_WRITE | KEY_NEED_LINK | KEY_NEED_SETATTR))
 		request = MAY_WRITE;
-	return smk_access(tkp, keyp->security, request, &ad);
+	rc = smk_access(tkp, keyp->security, request, &ad);
+	rc = smk_bu_note("key access", tkp, keyp->security, request, rc);
+	return rc;
 }
 #endif /* CONFIG_KEYS */
 
@@ -3685,6 +3907,7 @@ static int smack_key_permission(key_ref_t key_ref,
  */
 static int smack_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule)
 {
+	struct smack_known *skp;
 	char **rule = (char **)vrule;
 	*rule = NULL;
 
@@ -3694,7 +3917,9 @@ static int smack_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule)
 	if (op != Audit_equal && op != Audit_not_equal)
 		return -EINVAL;
 
-	*rule = smk_import(rulestr, 0);
+	skp = smk_import_entry(rulestr, 0);
+	if (skp)
+		*rule = skp->smk_known;
 
 	return 0;
 }
@@ -3813,7 +4038,12 @@ static int smack_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
  */
 static int smack_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
 {
-	*secid = smack_to_secid(secdata);
+	struct smack_known *skp = smk_find_entry(secdata);
+
+	if (skp)
+		*secid = skp->smk_secid;
+	else
+		*secid = 0;
 	return 0;
 }
 
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index 3c720ff10591..bce4e8f1b267 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -131,14 +131,17 @@ LIST_HEAD(smack_rule_list);
 
 struct smack_parsed_rule {
 	struct smack_known	*smk_subject;
-	char			*smk_object;
+	struct smack_known	*smk_object;
 	int			smk_access1;
 	int			smk_access2;
 };
 
 static int smk_cipso_doi_value = SMACK_CIPSO_DOI_DEFAULT;
 
-const char *smack_cipso_option = SMACK_CIPSO_OPTION;
+struct smack_known smack_cipso_option = {
+	.smk_known	= SMACK_CIPSO_OPTION,
+	.smk_secid	= 0,
+};
 
 /*
  * Values for parsing cipso rules
@@ -304,6 +307,10 @@ static int smk_perm_from_str(const char *string)
 		case 'L':
 			perm |= MAY_LOCK;
 			break;
+		case 'b':
+		case 'B':
+			perm |= MAY_BRINGUP;
+			break;
 		default:
 			return perm;
 		}
@@ -335,7 +342,7 @@ static int smk_fill_rule(const char *subject, const char *object,
 		if (rule->smk_subject == NULL)
 			return -EINVAL;
 
-		rule->smk_object = smk_import(object, len);
+		rule->smk_object = smk_import_entry(object, len);
 		if (rule->smk_object == NULL)
 			return -EINVAL;
 	} else {
@@ -355,7 +362,7 @@ static int smk_fill_rule(const char *subject, const char *object,
 		kfree(cp);
 		if (skp == NULL)
 			return -ENOENT;
-		rule->smk_object = skp->smk_known;
+		rule->smk_object = skp;
 	}
 
 	rule->smk_access1 = smk_perm_from_str(access1);
@@ -594,13 +601,15 @@ static void smk_rule_show(struct seq_file *s, struct smack_rule *srp, int max)
 	 * anything you read back.
 	 */
 	if (strlen(srp->smk_subject->smk_known) >= max ||
-	    strlen(srp->smk_object) >= max)
+	    strlen(srp->smk_object->smk_known) >= max)
 		return;
 
 	if (srp->smk_access == 0)
 		return;
 
-	seq_printf(s, "%s %s", srp->smk_subject->smk_known, srp->smk_object);
+	seq_printf(s, "%s %s",
+		   srp->smk_subject->smk_known,
+		   srp->smk_object->smk_known);
 
 	seq_putc(s, ' ');
 
@@ -616,6 +625,8 @@ static void smk_rule_show(struct seq_file *s, struct smack_rule *srp, int max)
 		seq_putc(s, 't');
 	if (srp->smk_access & MAY_LOCK)
 		seq_putc(s, 'l');
+	if (srp->smk_access & MAY_BRINGUP)
+		seq_putc(s, 'b');
 
 	seq_putc(s, '\n');
 }
@@ -1067,7 +1078,7 @@ static int netlbladdr_seq_show(struct seq_file *s, void *v)
 	for (maskn = 0; temp_mask; temp_mask <<= 1, maskn++);
 
 	seq_printf(s, "%u.%u.%u.%u/%d %s\n",
-		hp[0], hp[1], hp[2], hp[3], maskn, skp->smk_label);
+		hp[0], hp[1], hp[2], hp[3], maskn, skp->smk_label->smk_known);
 
 	return 0;
 }
@@ -1147,10 +1158,10 @@ static void smk_netlbladdr_insert(struct smk_netlbladdr *new)
 static ssize_t smk_write_netlbladdr(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
-	struct smk_netlbladdr *skp;
+	struct smk_netlbladdr *snp;
 	struct sockaddr_in newname;
 	char *smack;
-	char *sp;
+	struct smack_known *skp;
 	char *data;
 	char *host = (char *)&newname.sin_addr.s_addr;
 	int rc;
@@ -1213,15 +1224,15 @@ static ssize_t smk_write_netlbladdr(struct file *file, const char __user *buf,
 	 * If smack begins with '-', it is an option, don't import it
 	 */
 	if (smack[0] != '-') {
-		sp = smk_import(smack, 0);
-		if (sp == NULL) {
+		skp = smk_import_entry(smack, 0);
+		if (skp == NULL) {
 			rc = -EINVAL;
 			goto free_out;
 		}
 	} else {
 		/* check known options */
-		if (strcmp(smack, smack_cipso_option) == 0)
-			sp = (char *)smack_cipso_option;
+		if (strcmp(smack, smack_cipso_option.smk_known) == 0)
+			skp = &smack_cipso_option;
 		else {
 			rc = -EINVAL;
 			goto free_out;
@@ -1244,9 +1255,9 @@ static ssize_t smk_write_netlbladdr(struct file *file, const char __user *buf,
 	nsa = newname.sin_addr.s_addr;
 	/* try to find if the prefix is already in the list */
 	found = 0;
-	list_for_each_entry_rcu(skp, &smk_netlbladdr_list, list) {
-		if (skp->smk_host.sin_addr.s_addr == nsa &&
-		    skp->smk_mask.s_addr == mask.s_addr) {
+	list_for_each_entry_rcu(snp, &smk_netlbladdr_list, list) {
+		if (snp->smk_host.sin_addr.s_addr == nsa &&
+		    snp->smk_mask.s_addr == mask.s_addr) {
 			found = 1;
 			break;
 		}
@@ -1254,26 +1265,26 @@ static ssize_t smk_write_netlbladdr(struct file *file, const char __user *buf,
 	smk_netlabel_audit_set(&audit_info);
 
 	if (found == 0) {
-		skp = kzalloc(sizeof(*skp), GFP_KERNEL);
-		if (skp == NULL)
+		snp = kzalloc(sizeof(*snp), GFP_KERNEL);
+		if (snp == NULL)
 			rc = -ENOMEM;
 		else {
 			rc = 0;
-			skp->smk_host.sin_addr.s_addr = newname.sin_addr.s_addr;
-			skp->smk_mask.s_addr = mask.s_addr;
-			skp->smk_label = sp;
-			smk_netlbladdr_insert(skp);
+			snp->smk_host.sin_addr.s_addr = newname.sin_addr.s_addr;
+			snp->smk_mask.s_addr = mask.s_addr;
+			snp->smk_label = skp;
+			smk_netlbladdr_insert(snp);
 		}
 	} else {
 		/* we delete the unlabeled entry, only if the previous label
 		 * wasn't the special CIPSO option */
-		if (skp->smk_label != smack_cipso_option)
+		if (snp->smk_label != &smack_cipso_option)
 			rc = netlbl_cfg_unlbl_static_del(&init_net, NULL,
-					&skp->smk_host.sin_addr, &skp->smk_mask,
+					&snp->smk_host.sin_addr, &snp->smk_mask,
 					PF_INET, &audit_info);
 		else
 			rc = 0;
-		skp->smk_label = sp;
+		snp->smk_label = skp;
 	}
 
 	/*
@@ -1281,10 +1292,10 @@ static ssize_t smk_write_netlbladdr(struct file *file, const char __user *buf,
 	 * this host so that incoming packets get labeled.
 	 * but only if we didn't get the special CIPSO option
 	 */
-	if (rc == 0 && sp != smack_cipso_option)
+	if (rc == 0 && skp != &smack_cipso_option)
 		rc = netlbl_cfg_unlbl_static_add(&init_net, NULL,
-			&skp->smk_host.sin_addr, &skp->smk_mask, PF_INET,
-			smack_to_secid(skp->smk_label), &audit_info);
+			&snp->smk_host.sin_addr, &snp->smk_mask, PF_INET,
+			snp->smk_label->smk_secid, &audit_info);
 
 	if (rc == 0)
 		rc = count;
@@ -1677,7 +1688,7 @@ static ssize_t smk_write_onlycap(struct file *file, const char __user *buf,
 	if (smack_onlycap != NULL && smack_onlycap != skp)
 		return -EPERM;
 
-	data = kzalloc(count, GFP_KERNEL);
+	data = kzalloc(count + 1, GFP_KERNEL);
 	if (data == NULL)
 		return -ENOMEM;
 
@@ -1880,7 +1891,10 @@ static ssize_t smk_user_access(struct file *file, const char __user *buf,
 	else if (res != -ENOENT)
 		return -EINVAL;
 
-	data[0] = res == 0 ? '1' : '0';
+	/*
+	 * smk_access() can return a value > 0 in the "bringup" case.
+	 */
+	data[0] = res >= 0 ? '1' : '0';
 	data[1] = '\0';
 
 	simple_transaction_set(file, 2);
@@ -2228,7 +2242,7 @@ static ssize_t smk_write_syslog(struct file *file, const char __user *buf,
 	if (!smack_privileged(CAP_MAC_ADMIN))
 		return -EPERM;
 
-	data = kzalloc(count, GFP_KERNEL);
+	data = kzalloc(count + 1, GFP_KERNEL);
 	if (data == NULL)
 		return -ENOMEM;
 
diff --git a/sound/atmel/abdac.c b/sound/atmel/abdac.c
index edf2ca72d518..31061e3521d4 100644
--- a/sound/atmel/abdac.c
+++ b/sound/atmel/abdac.c
@@ -9,7 +9,6 @@
  */
 #include <linux/clk.h>
 #include <linux/bitmap.h>
-#include <linux/dw_dmac.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/init.h>
@@ -25,6 +24,9 @@
 #include <sound/pcm_params.h>
 #include <sound/atmel-abdac.h>
 
+#include <linux/platform_data/dma-dw.h>
+#include <linux/dma/dw.h>
+
 /* DAC register offsets */
 #define DAC_DATA                                0x0000
 #define DAC_CTRL                                0x0008
diff --git a/sound/atmel/ac97c.c b/sound/atmel/ac97c.c
index a04d23174dc2..b59427d5a697 100644
--- a/sound/atmel/ac97c.c
+++ b/sound/atmel/ac97c.c
@@ -31,7 +31,8 @@
 #include <sound/atmel-ac97c.h>
 #include <sound/memalloc.h>
 
-#include <linux/dw_dmac.h>
+#include <linux/platform_data/dma-dw.h>
+#include <linux/dma/dw.h>
 
 #include <mach/cpu.h>
 
diff --git a/sound/core/misc.c b/sound/core/misc.c
index 30e027ecf4da..f2e8226c88fb 100644
--- a/sound/core/misc.c
+++ b/sound/core/misc.c
@@ -145,6 +145,8 @@ EXPORT_SYMBOL(snd_pci_quirk_lookup_id);
 const struct snd_pci_quirk *
 snd_pci_quirk_lookup(struct pci_dev *pci, const struct snd_pci_quirk *list)
 {
+	if (!pci)
+		return NULL;
 	return snd_pci_quirk_lookup_id(pci->subsystem_vendor,
 				       pci->subsystem_device,
 				       list);
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 43932e8dce66..42ded997b223 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -215,6 +215,7 @@ static char *snd_pcm_format_names[] = {
 	FORMAT(G723_40_1B),
 	FORMAT(DSD_U8),
 	FORMAT(DSD_U16_LE),
+	FORMAT(DSD_U32_LE),
 };
 
 const char *snd_pcm_format_name(snd_pcm_format_t format)
@@ -698,6 +699,7 @@ int snd_pcm_new_stream(struct snd_pcm *pcm, int stream, int substream_count)
 		}
 		substream->group = &substream->self_group;
 		spin_lock_init(&substream->self_group.lock);
+		mutex_init(&substream->self_group.mutex);
 		INIT_LIST_HEAD(&substream->self_group.substreams);
 		list_add_tail(&substream->link_list, &substream->self_group.substreams);
 		atomic_set(&substream->mmap_count, 0);
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 0032278567ad..dfc28542a007 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -1113,18 +1113,20 @@ int snd_interval_list(struct snd_interval *i, unsigned int count,
 
 EXPORT_SYMBOL(snd_interval_list);
 
-static int snd_interval_step(struct snd_interval *i, unsigned int min, unsigned int step)
+static int snd_interval_step(struct snd_interval *i, unsigned int step)
 {
 	unsigned int n;
 	int changed = 0;
-	n = (i->min - min) % step;
+	n = i->min % step;
 	if (n != 0 || i->openmin) {
 		i->min += step - n;
+		i->openmin = 0;
 		changed = 1;
 	}
-	n = (i->max - min) % step;
+	n = i->max % step;
 	if (n != 0 || i->openmax) {
 		i->max -= n;
+		i->openmax = 0;
 		changed = 1;
 	}
 	if (snd_interval_checkempty(i)) {
@@ -1427,7 +1429,7 @@ static int snd_pcm_hw_rule_step(struct snd_pcm_hw_params *params,
 				struct snd_pcm_hw_rule *rule)
 {
 	unsigned long step = (unsigned long) rule->private;
-	return snd_interval_step(hw_param_interval(params, rule->var), 0, step);
+	return snd_interval_step(hw_param_interval(params, rule->var), step);
 }
 
 /**
diff --git a/sound/core/pcm_misc.c b/sound/core/pcm_misc.c
index 2c6fd80e0bd1..ae7a0feb3b76 100644
--- a/sound/core/pcm_misc.c
+++ b/sound/core/pcm_misc.c
@@ -148,6 +148,10 @@ static struct pcm_format_data pcm_formats[(INT)SNDRV_PCM_FORMAT_LAST+1] = {
 		.width = 16, .phys = 16, .le = 1, .signd = 0,
 		.silence = { 0x69, 0x69 },
 	},
+	[SNDRV_PCM_FORMAT_DSD_U32_LE] = {
+		.width = 32, .phys = 32, .le = 1, .signd = 0,
+		.silence = { 0x69, 0x69, 0x69, 0x69 },
+	},
 	/* FIXME: the following three formats are not defined properly yet */
 	[SNDRV_PCM_FORMAT_MPEG] = {
 		.le = -1, .signd = -1,
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 8cd2f930ad0b..85fe1a216225 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -74,11 +74,68 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream);
  *
  */
 
-DEFINE_RWLOCK(snd_pcm_link_rwlock);
-EXPORT_SYMBOL(snd_pcm_link_rwlock);
-
+static DEFINE_RWLOCK(snd_pcm_link_rwlock);
 static DECLARE_RWSEM(snd_pcm_link_rwsem);
 
+void snd_pcm_stream_lock(struct snd_pcm_substream *substream)
+{
+	if (substream->pcm->nonatomic) {
+		down_read(&snd_pcm_link_rwsem);
+		mutex_lock(&substream->self_group.mutex);
+	} else {
+		read_lock(&snd_pcm_link_rwlock);
+		spin_lock(&substream->self_group.lock);
+	}
+}
+EXPORT_SYMBOL_GPL(snd_pcm_stream_lock);
+
+void snd_pcm_stream_unlock(struct snd_pcm_substream *substream)
+{
+	if (substream->pcm->nonatomic) {
+		mutex_unlock(&substream->self_group.mutex);
+		up_read(&snd_pcm_link_rwsem);
+	} else {
+		spin_unlock(&substream->self_group.lock);
+		read_unlock(&snd_pcm_link_rwlock);
+	}
+}
+EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock);
+
+void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream)
+{
+	if (!substream->pcm->nonatomic)
+		local_irq_disable();
+	snd_pcm_stream_lock(substream);
+}
+EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq);
+
+void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream)
+{
+	snd_pcm_stream_unlock(substream);
+	if (!substream->pcm->nonatomic)
+		local_irq_enable();
+}
+EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irq);
+
+unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream)
+{
+	unsigned long flags = 0;
+	if (!substream->pcm->nonatomic)
+		local_irq_save(flags);
+	snd_pcm_stream_lock(substream);
+	return flags;
+}
+EXPORT_SYMBOL_GPL(_snd_pcm_stream_lock_irqsave);
+
+void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream,
+				      unsigned long flags)
+{
+	snd_pcm_stream_unlock(substream);
+	if (!substream->pcm->nonatomic)
+		local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irqrestore);
+
 static inline mm_segment_t snd_enter_user(void)
 {
 	mm_segment_t fs = get_fs();
@@ -727,9 +784,14 @@ static int snd_pcm_action_group(struct action_ops *ops,
 	int res = 0;
 
 	snd_pcm_group_for_each_entry(s, substream) {
-		if (do_lock && s != substream)
-			spin_lock_nested(&s->self_group.lock,
-					 SINGLE_DEPTH_NESTING);
+		if (do_lock && s != substream) {
+			if (s->pcm->nonatomic)
+				mutex_lock_nested(&s->self_group.mutex,
+						  SINGLE_DEPTH_NESTING);
+			else
+				spin_lock_nested(&s->self_group.lock,
+						 SINGLE_DEPTH_NESTING);
+		}
 		res = ops->pre_action(s, state);
 		if (res < 0)
 			goto _unlock;
@@ -755,8 +817,12 @@ static int snd_pcm_action_group(struct action_ops *ops,
 	if (do_lock) {
 		/* unlock streams */
 		snd_pcm_group_for_each_entry(s1, substream) {
-			if (s1 != substream)
-				spin_unlock(&s1->self_group.lock);
+			if (s1 != substream) {
+				if (s->pcm->nonatomic)
+					mutex_unlock(&s1->self_group.mutex);
+				else
+					spin_unlock(&s1->self_group.lock);
+			}
 			if (s1 == s)	/* end */
 				break;
 		}
@@ -784,6 +850,27 @@ static int snd_pcm_action_single(struct action_ops *ops,
 	return res;
 }
 
+/* call in mutex-protected context */
+static int snd_pcm_action_mutex(struct action_ops *ops,
+				struct snd_pcm_substream *substream,
+				int state)
+{
+	int res;
+
+	if (snd_pcm_stream_linked(substream)) {
+		if (!mutex_trylock(&substream->group->mutex)) {
+			mutex_unlock(&substream->self_group.mutex);
+			mutex_lock(&substream->group->mutex);
+			mutex_lock(&substream->self_group.mutex);
+		}
+		res = snd_pcm_action_group(ops, substream, state, 1);
+		mutex_unlock(&substream->group->mutex);
+	} else {
+		res = snd_pcm_action_single(ops, substream, state);
+	}
+	return res;
+}
+
 /*
  *  Note: call with stream lock
  */
@@ -793,6 +880,9 @@ static int snd_pcm_action(struct action_ops *ops,
 {
 	int res;
 
+	if (substream->pcm->nonatomic)
+		return snd_pcm_action_mutex(ops, substream, state);
+
 	if (snd_pcm_stream_linked(substream)) {
 		if (!spin_trylock(&substream->group->lock)) {
 			spin_unlock(&substream->self_group.lock);
@@ -807,6 +897,29 @@ static int snd_pcm_action(struct action_ops *ops,
 	return res;
 }
 
+static int snd_pcm_action_lock_mutex(struct action_ops *ops,
+				     struct snd_pcm_substream *substream,
+				     int state)
+{
+	int res;
+
+	down_read(&snd_pcm_link_rwsem);
+	if (snd_pcm_stream_linked(substream)) {
+		mutex_lock(&substream->group->mutex);
+		mutex_lock_nested(&substream->self_group.mutex,
+				  SINGLE_DEPTH_NESTING);
+		res = snd_pcm_action_group(ops, substream, state, 1);
+		mutex_unlock(&substream->self_group.mutex);
+		mutex_unlock(&substream->group->mutex);
+	} else {
+		mutex_lock(&substream->self_group.mutex);
+		res = snd_pcm_action_single(ops, substream, state);
+		mutex_unlock(&substream->self_group.mutex);
+	}
+	up_read(&snd_pcm_link_rwsem);
+	return res;
+}
+
 /*
  *  Note: don't use any locks before
  */
@@ -816,6 +929,9 @@ static int snd_pcm_action_lock_irq(struct action_ops *ops,
 {
 	int res;
 
+	if (substream->pcm->nonatomic)
+		return snd_pcm_action_lock_mutex(ops, substream, state);
+
 	read_lock_irq(&snd_pcm_link_rwlock);
 	if (snd_pcm_stream_linked(substream)) {
 		spin_lock(&substream->group->lock);
@@ -1634,7 +1750,8 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd)
 	down_write(&snd_pcm_link_rwsem);
 	write_lock_irq(&snd_pcm_link_rwlock);
 	if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN ||
-	    substream->runtime->status->state != substream1->runtime->status->state) {
+	    substream->runtime->status->state != substream1->runtime->status->state ||
+	    substream->pcm->nonatomic != substream1->pcm->nonatomic) {
 		res = -EBADFD;
 		goto _end;
 	}
@@ -1646,6 +1763,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd)
 		substream->group = group;
 		group = NULL;
 		spin_lock_init(&substream->group->lock);
+		mutex_init(&substream->group->mutex);
 		INIT_LIST_HEAD(&substream->group->substreams);
 		list_add_tail(&substream->link_list, &substream->group->substreams);
 		substream->group->count = 1;
diff --git a/sound/drivers/vx/vx_core.c b/sound/drivers/vx/vx_core.c
index 83596891cde4..e8cc16993903 100644
--- a/sound/drivers/vx/vx_core.c
+++ b/sound/drivers/vx/vx_core.c
@@ -117,7 +117,7 @@ static int vx_reset_chk(struct vx_core *chip)
  *
  * returns 0 if successful, or a negative error code.
  * the error code can be VX-specific, retrieved via vx_get_error().
- * NB: call with spinlock held!
+ * NB: call with mutex held!
  */
 static int vx_transfer_end(struct vx_core *chip, int cmd)
 {
@@ -155,7 +155,7 @@ static int vx_transfer_end(struct vx_core *chip, int cmd)
  *
  * returns 0 if successful, or a negative error code.
  * the error code can be VX-specific, retrieved via vx_get_error().
- * NB: call with spinlock held!
+ * NB: call with mutex held!
  */
 static int vx_read_status(struct vx_core *chip, struct vx_rmh *rmh)
 {
@@ -236,7 +236,7 @@ static int vx_read_status(struct vx_core *chip, struct vx_rmh *rmh)
  * returns 0 if successful, or a negative error code.
  * the error code can be VX-specific, retrieved via vx_get_error().
  * 
- * this function doesn't call spinlock at all.
+ * this function doesn't call mutex lock at all.
  */
 int vx_send_msg_nolock(struct vx_core *chip, struct vx_rmh *rmh)
 {
@@ -337,7 +337,7 @@ int vx_send_msg_nolock(struct vx_core *chip, struct vx_rmh *rmh)
 
 
 /*
- * vx_send_msg - send a DSP message with spinlock
+ * vx_send_msg - send a DSP message with mutex
  * @rmh: the rmh record to send and receive
  *
  * returns 0 if successful, or a negative error code.
@@ -345,12 +345,11 @@ int vx_send_msg_nolock(struct vx_core *chip, struct vx_rmh *rmh)
  */
 int vx_send_msg(struct vx_core *chip, struct vx_rmh *rmh)
 {
-	unsigned long flags;
 	int err;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	err = vx_send_msg_nolock(chip, rmh);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 	return err;
 }
 
@@ -362,7 +361,7 @@ int vx_send_msg(struct vx_core *chip, struct vx_rmh *rmh)
  * returns 0 if successful, or a negative error code.
  * the error code can be VX-specific, retrieved via vx_get_error().
  *
- * this function doesn't call spinlock at all.
+ * this function doesn't call mutex at all.
  *
  * unlike RMH, no command is sent to DSP.
  */
@@ -398,19 +397,18 @@ int vx_send_rih_nolock(struct vx_core *chip, int cmd)
 
 
 /*
- * vx_send_rih - send an RIH with spinlock
+ * vx_send_rih - send an RIH with mutex
  * @cmd: the command to send
  *
  * see vx_send_rih_nolock().
  */
 int vx_send_rih(struct vx_core *chip, int cmd)
 {
-	unsigned long flags;
 	int err;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	err = vx_send_rih_nolock(chip, cmd);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 	return err;
 }
 
@@ -482,30 +480,30 @@ static int vx_test_irq_src(struct vx_core *chip, unsigned int *ret)
 	int err;
 
 	vx_init_rmh(&chip->irq_rmh, CMD_TEST_IT);
-	spin_lock(&chip->lock);
+	mutex_lock(&chip->lock);
 	err = vx_send_msg_nolock(chip, &chip->irq_rmh);
 	if (err < 0)
 		*ret = 0;
 	else
 		*ret = chip->irq_rmh.Stat[0];
-	spin_unlock(&chip->lock);
+	mutex_unlock(&chip->lock);
 	return err;
 }
 
 
 /*
- * vx_interrupt - soft irq handler
+ * snd_vx_threaded_irq_handler - threaded irq handler
  */
-static void vx_interrupt(unsigned long private_data)
+irqreturn_t snd_vx_threaded_irq_handler(int irq, void *dev)
 {
-	struct vx_core *chip = (struct vx_core *) private_data;
+	struct vx_core *chip = dev;
 	unsigned int events;
 		
 	if (chip->chip_status & VX_STAT_IS_STALE)
-		return;
+		return IRQ_HANDLED;
 
 	if (vx_test_irq_src(chip, &events) < 0)
-		return;
+		return IRQ_HANDLED;
     
 #if 0
 	if (events & 0x000800)
@@ -519,7 +517,7 @@ static void vx_interrupt(unsigned long private_data)
 	 */
 	if (events & FATAL_DSP_ERROR) {
 		snd_printk(KERN_ERR "vx_core: fatal DSP error!!\n");
-		return;
+		return IRQ_HANDLED;
 	}
 
 	/* The start on time code conditions are filled (ie the time code
@@ -534,8 +532,9 @@ static void vx_interrupt(unsigned long private_data)
 
 	/* update the pcm streams */
 	vx_pcm_update_intr(chip, events);
+	return IRQ_HANDLED;
 }
-
+EXPORT_SYMBOL(snd_vx_threaded_irq_handler);
 
 /**
  * snd_vx_irq_handler - interrupt handler
@@ -548,8 +547,8 @@ irqreturn_t snd_vx_irq_handler(int irq, void *dev)
 	    (chip->chip_status & VX_STAT_IS_STALE))
 		return IRQ_NONE;
 	if (! vx_test_and_ack(chip))
-		tasklet_schedule(&chip->tq);
-	return IRQ_HANDLED;
+		return IRQ_WAKE_THREAD;
+	return IRQ_NONE;
 }
 
 EXPORT_SYMBOL(snd_vx_irq_handler);
@@ -790,13 +789,11 @@ struct vx_core *snd_vx_create(struct snd_card *card, struct snd_vx_hardware *hw,
 		snd_printk(KERN_ERR "vx_core: no memory\n");
 		return NULL;
 	}
-	spin_lock_init(&chip->lock);
-	spin_lock_init(&chip->irq_lock);
+	mutex_init(&chip->lock);
 	chip->irq = -1;
 	chip->hw = hw;
 	chip->type = hw->type;
 	chip->ops = ops;
-	tasklet_init(&chip->tq, vx_interrupt, (unsigned long)chip);
 	mutex_init(&chip->mixer_mutex);
 
 	chip->card = card;
diff --git a/sound/drivers/vx/vx_mixer.c b/sound/drivers/vx/vx_mixer.c
index c71b8d148d7f..3b6823fc0606 100644
--- a/sound/drivers/vx/vx_mixer.c
+++ b/sound/drivers/vx/vx_mixer.c
@@ -32,17 +32,15 @@
  */
 static void vx_write_codec_reg(struct vx_core *chip, int codec, unsigned int data)
 {
-	unsigned long flags;
-
 	if (snd_BUG_ON(!chip->ops->write_codec))
 		return;
 
 	if (chip->chip_status & VX_STAT_IS_STALE)
 		return;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	chip->ops->write_codec(chip, codec, data);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 /*
@@ -178,14 +176,12 @@ void vx_reset_codec(struct vx_core *chip, int cold_reset)
  */
 static void vx_change_audio_source(struct vx_core *chip, int src)
 {
-	unsigned long flags;
-
 	if (chip->chip_status & VX_STAT_IS_STALE)
 		return;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	chip->ops->change_audio_source(chip, src);
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 
diff --git a/sound/drivers/vx/vx_pcm.c b/sound/drivers/vx/vx_pcm.c
index deed5efff33c..11467272089e 100644
--- a/sound/drivers/vx/vx_pcm.c
+++ b/sound/drivers/vx/vx_pcm.c
@@ -229,7 +229,7 @@ static int vx_get_pipe_state(struct vx_core *chip, struct vx_pipe *pipe, int *st
 
 	vx_init_rmh(&rmh, CMD_PIPE_STATE);
 	vx_set_pipe_cmd_params(&rmh, pipe->is_capture, pipe->number, 0);
-	err = vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	err = vx_send_msg(chip, &rmh);
 	if (! err)
 		*state = (rmh.Stat[0] & (1 << pipe->number)) ? 1 : 0;
 	return err;
@@ -280,7 +280,7 @@ static int vx_pipe_can_start(struct vx_core *chip, struct vx_pipe *pipe)
 	vx_set_pipe_cmd_params(&rmh, pipe->is_capture, pipe->number, 0);
 	rmh.Cmd[0] |= 1;
 
-	err = vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	err = vx_send_msg(chip, &rmh);
 	if (! err) {
 		if (rmh.Stat[0])
 			err = 1;
@@ -300,7 +300,7 @@ static int vx_conf_pipe(struct vx_core *chip, struct vx_pipe *pipe)
 	if (pipe->is_capture)
 		rmh.Cmd[0] |= COMMAND_RECORD_MASK;
 	rmh.Cmd[1] = 1 << pipe->number;
-	return vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */
+	return vx_send_msg(chip, &rmh);
 }
 
 /*
@@ -311,7 +311,7 @@ static int vx_send_irqa(struct vx_core *chip)
 	struct vx_rmh rmh;
 
 	vx_init_rmh(&rmh, CMD_SEND_IRQA);
-	return vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	return vx_send_msg(chip, &rmh);
 }
 
 
@@ -389,7 +389,7 @@ static int vx_stop_pipe(struct vx_core *chip, struct vx_pipe *pipe)
 	struct vx_rmh rmh;
 	vx_init_rmh(&rmh, CMD_STOP_PIPE);
 	vx_set_pipe_cmd_params(&rmh, pipe->is_capture, pipe->number, 0);
-	return vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	return vx_send_msg(chip, &rmh);
 }
 
 
@@ -477,7 +477,7 @@ static int vx_start_stream(struct vx_core *chip, struct vx_pipe *pipe)
 	vx_init_rmh(&rmh, CMD_START_ONE_STREAM);
 	vx_set_stream_cmd_params(&rmh, pipe->is_capture, pipe->number);
 	vx_set_differed_time(chip, &rmh, pipe);
-	return vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	return vx_send_msg(chip, &rmh);
 }
 
 
@@ -492,7 +492,7 @@ static int vx_stop_stream(struct vx_core *chip, struct vx_pipe *pipe)
 
 	vx_init_rmh(&rmh, CMD_STOP_STREAM);
 	vx_set_stream_cmd_params(&rmh, pipe->is_capture, pipe->number);
-	return vx_send_msg_nolock(chip, &rmh); /* no lock needed for trigger */ 
+	return vx_send_msg(chip, &rmh);
 }
 
 
@@ -520,8 +520,6 @@ static struct snd_pcm_hardware vx_pcm_playback_hw = {
 };
 
 
-static void vx_pcm_delayed_start(unsigned long arg);
-
 /*
  * vx_pcm_playback_open - open callback for playback
  */
@@ -553,7 +551,6 @@ static int vx_pcm_playback_open(struct snd_pcm_substream *subs)
 	pipe->references++;
 
 	pipe->substream = subs;
-	tasklet_init(&pipe->start_tq, vx_pcm_delayed_start, (unsigned long)subs);
 	chip->playback_pipes[audio] = pipe;
 
 	runtime->hw = vx_pcm_playback_hw;
@@ -646,12 +643,12 @@ static int vx_pcm_playback_transfer_chunk(struct vx_core *chip,
 	/* we don't need irqsave here, because this function
 	 * is called from either trigger callback or irq handler
 	 */
-	spin_lock(&chip->lock); 
+	mutex_lock(&chip->lock);
 	vx_pseudo_dma_write(chip, runtime, pipe, size);
 	err = vx_notify_end_of_buffer(chip, pipe);
 	/* disconnect the host, SIZE_HBUF command always switches to the stream mode */
 	vx_send_rih_nolock(chip, IRQ_CONNECT_STREAM_NEXT);
-	spin_unlock(&chip->lock);
+	mutex_unlock(&chip->lock);
 	return err;
 }
 
@@ -728,31 +725,6 @@ static void vx_pcm_playback_update(struct vx_core *chip,
 }
 
 /*
- * start the stream and pipe.
- * this function is called from tasklet, which is invoked by the trigger
- * START callback.
- */
-static void vx_pcm_delayed_start(unsigned long arg)
-{
-	struct snd_pcm_substream *subs = (struct snd_pcm_substream *)arg;
-	struct vx_core *chip = subs->pcm->private_data;
-	struct vx_pipe *pipe = subs->runtime->private_data;
-	int err;
-
-	/*  printk( KERN_DEBUG "DDDD tasklet delayed start jiffies = %ld\n", jiffies);*/
-
-	if ((err = vx_start_stream(chip, pipe)) < 0) {
-		snd_printk(KERN_ERR "vx: cannot start stream\n");
-		return;
-	}
-	if ((err = vx_toggle_pipe(chip, pipe, 1)) < 0) {
-		snd_printk(KERN_ERR "vx: cannot start pipe\n");
-		return;
-	}
-	/*   printk( KERN_DEBUG "dddd tasklet delayed start jiffies = %ld \n", jiffies);*/
-}
-
-/*
  * vx_pcm_playback_trigger - trigger callback for playback
  */
 static int vx_pcm_trigger(struct snd_pcm_substream *subs, int cmd)
@@ -769,11 +741,17 @@ static int vx_pcm_trigger(struct snd_pcm_substream *subs, int cmd)
 	case SNDRV_PCM_TRIGGER_RESUME:
 		if (! pipe->is_capture)
 			vx_pcm_playback_transfer(chip, subs, pipe, 2);
-		/* FIXME:
-		 * we trigger the pipe using tasklet, so that the interrupts are
-		 * issued surely after the trigger is completed.
-		 */ 
-		tasklet_schedule(&pipe->start_tq);
+		err = vx_start_stream(chip, pipe);
+		if (err < 0) {
+			pr_debug("vx: cannot start stream\n");
+			return err;
+		}
+		err = vx_toggle_pipe(chip, pipe, 1);
+		if (err < 0) {
+			pr_debug("vx: cannot start pipe\n");
+			vx_stop_stream(chip, pipe);
+			return err;
+		}
 		chip->pcm_running++;
 		pipe->running = 1;
 		break;
@@ -955,7 +933,6 @@ static int vx_pcm_capture_open(struct snd_pcm_substream *subs)
 	if (err < 0)
 		return err;
 	pipe->substream = subs;
-	tasklet_init(&pipe->start_tq, vx_pcm_delayed_start, (unsigned long)subs);
 	chip->capture_pipes[audio] = pipe;
 
 	/* check if monitoring is needed */
@@ -1082,7 +1059,7 @@ static void vx_pcm_capture_update(struct vx_core *chip, struct snd_pcm_substream
 		count -= 3;
 	}
 	/* disconnect the host, SIZE_HBUF command always switches to the stream mode */
-	vx_send_rih_nolock(chip, IRQ_CONNECT_STREAM_NEXT);
+	vx_send_rih(chip, IRQ_CONNECT_STREAM_NEXT);
 	/* read the last pending 6 bytes */
 	count = DMA_READ_ALIGN;
 	while (count > 0) {
@@ -1099,7 +1076,7 @@ static void vx_pcm_capture_update(struct vx_core *chip, struct snd_pcm_substream
 
  _error:
 	/* disconnect the host, SIZE_HBUF command always switches to the stream mode */
-	vx_send_rih_nolock(chip, IRQ_CONNECT_STREAM_NEXT);
+	vx_send_rih(chip, IRQ_CONNECT_STREAM_NEXT);
 	return;
 }
 
@@ -1275,6 +1252,7 @@ int snd_vx_pcm_new(struct vx_core *chip)
 		pcm->private_data = chip;
 		pcm->private_free = snd_vx_pcm_free;
 		pcm->info_flags = 0;
+		pcm->nonatomic = true;
 		strcpy(pcm->name, chip->card->shortname);
 		chip->pcm[i] = pcm;
 	}
diff --git a/sound/drivers/vx/vx_uer.c b/sound/drivers/vx/vx_uer.c
index b0560fec6bba..ef0b40c0a594 100644
--- a/sound/drivers/vx/vx_uer.c
+++ b/sound/drivers/vx/vx_uer.c
@@ -60,9 +60,9 @@ static int vx_modify_board_inputs(struct vx_core *chip)
  */
 static int vx_read_one_cbit(struct vx_core *chip, int index)
 {
-	unsigned long flags;
 	int val;
-	spin_lock_irqsave(&chip->lock, flags);
+
+	mutex_lock(&chip->lock);
 	if (chip->type >= VX_TYPE_VXPOCKET) {
 		vx_outb(chip, CSUER, 1); /* read */
 		vx_outb(chip, RUER, index & XX_UER_CBITS_OFFSET_MASK);
@@ -72,7 +72,7 @@ static int vx_read_one_cbit(struct vx_core *chip, int index)
 		vx_outl(chip, RUER, index & XX_UER_CBITS_OFFSET_MASK);
 		val = (vx_inl(chip, RUER) >> 7) & 0x01;
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 	return val;
 }
 
@@ -83,9 +83,8 @@ static int vx_read_one_cbit(struct vx_core *chip, int index)
  */
 static void vx_write_one_cbit(struct vx_core *chip, int index, int val)
 {
-	unsigned long flags;
 	val = !!val;	/* 0 or 1 */
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	if (vx_is_pcmcia(chip)) {
 		vx_outb(chip, CSUER, 0); /* write */
 		vx_outb(chip, RUER, (val << 7) | (index & XX_UER_CBITS_OFFSET_MASK));
@@ -93,7 +92,7 @@ static void vx_write_one_cbit(struct vx_core *chip, int index, int val)
 		vx_outl(chip, CSUER, 0); /* write */
 		vx_outl(chip, RUER, (val << 7) | (index & XX_UER_CBITS_OFFSET_MASK));
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 /*
@@ -190,14 +189,12 @@ static int vx_calc_clock_from_freq(struct vx_core *chip, int freq)
  */
 static void vx_change_clock_source(struct vx_core *chip, int source)
 {
-	unsigned long flags;
-
 	/* we mute DAC to prevent clicks */
 	vx_toggle_dac_mute(chip, 1);
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	chip->ops->set_clock_source(chip, source);
 	chip->clock_source = source;
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 	/* unmute */
 	vx_toggle_dac_mute(chip, 0);
 }
@@ -209,11 +206,11 @@ static void vx_change_clock_source(struct vx_core *chip, int source)
 void vx_set_internal_clock(struct vx_core *chip, unsigned int freq)
 {
 	int clock;
-	unsigned long flags;
+
 	/* Get real clock value */
 	clock = vx_calc_clock_from_freq(chip, freq);
 	snd_printdd(KERN_DEBUG "set internal clock to 0x%x from freq %d\n", clock, freq);
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	if (vx_is_pcmcia(chip)) {
 		vx_outb(chip, HIFREQ, (clock >> 8) & 0x0f);
 		vx_outb(chip, LOFREQ, clock & 0xff);
@@ -221,7 +218,7 @@ void vx_set_internal_clock(struct vx_core *chip, unsigned int freq)
 		vx_outl(chip, HIFREQ, (clock >> 8) & 0x0f);
 		vx_outl(chip, LOFREQ, clock & 0xff);
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 
diff --git a/sound/pci/au88x0/au88x0.c b/sound/pci/au88x0/au88x0.c
index afb1b44b741e..21ce31f636bc 100644
--- a/sound/pci/au88x0/au88x0.c
+++ b/sound/pci/au88x0/au88x0.c
@@ -48,10 +48,10 @@ static void vortex_fix_latency(struct pci_dev *vortex)
 {
 	int rc;
 	if (!(rc = pci_write_config_byte(vortex, 0x40, 0xff))) {
-			printk(KERN_INFO CARD_NAME
+			pr_info( CARD_NAME
 			       ": vortex latency is 0xff\n");
 	} else {
-		printk(KERN_WARNING CARD_NAME
+		pr_warn( CARD_NAME
 				": could not set vortex latency: pci error 0x%x\n", rc);
 	}
 }
@@ -70,10 +70,10 @@ static void vortex_fix_agp_bridge(struct pci_dev *via)
 	if (!(rc = pci_read_config_byte(via, 0x42, &value))
 			&& ((value & 0x10)
 				|| !(rc = pci_write_config_byte(via, 0x42, value | 0x10)))) {
-		printk(KERN_INFO CARD_NAME
+		pr_info( CARD_NAME
 				": bridge config is 0x%x\n", value | 0x10);
 	} else {
-		printk(KERN_WARNING CARD_NAME
+		pr_warn( CARD_NAME
 				": could not set vortex latency: pci error 0x%x\n", rc);
 	}
 }
@@ -97,7 +97,7 @@ static void snd_vortex_workaround(struct pci_dev *vortex, int fix)
 					PCI_DEVICE_ID_AMD_FE_GATE_7007, NULL);
 		}
 		if (via) {
-			printk(KERN_INFO CARD_NAME ": Activating latency workaround...\n");
+			pr_info( CARD_NAME ": Activating latency workaround...\n");
 			vortex_fix_latency(vortex);
 			vortex_fix_agp_bridge(via);
 		}
@@ -153,7 +153,7 @@ snd_vortex_create(struct snd_card *card, struct pci_dev *pci, vortex_t ** rchip)
 		return err;
 	if (pci_set_dma_mask(pci, DMA_BIT_MASK(32)) < 0 ||
 	    pci_set_consistent_dma_mask(pci, DMA_BIT_MASK(32)) < 0) {
-		printk(KERN_ERR "error to set DMA mask\n");
+		pr_err( "error to set DMA mask\n");
 		pci_disable_device(pci);
 		return -ENXIO;
 	}
@@ -182,7 +182,7 @@ snd_vortex_create(struct snd_card *card, struct pci_dev *pci, vortex_t ** rchip)
 
 	chip->mmio = pci_ioremap_bar(pci, 0);
 	if (!chip->mmio) {
-		printk(KERN_ERR "MMIO area remap failed.\n");
+		pr_err( "MMIO area remap failed.\n");
 		err = -ENOMEM;
 		goto ioremap_out;
 	}
@@ -191,14 +191,14 @@ snd_vortex_create(struct snd_card *card, struct pci_dev *pci, vortex_t ** rchip)
 	 * This must be done before we do request_irq otherwise we can get spurious
 	 * interrupts that we do not handle properly and make a mess of things */
 	if ((err = vortex_core_init(chip)) != 0) {
-		printk(KERN_ERR "hw core init failed\n");
+		pr_err( "hw core init failed\n");
 		goto core_out;
 	}
 
 	if ((err = request_irq(pci->irq, vortex_interrupt,
 			       IRQF_SHARED, KBUILD_MODNAME,
 	                       chip)) != 0) {
-		printk(KERN_ERR "cannot grab irq\n");
+		pr_err( "cannot grab irq\n");
 		goto irq_out;
 	}
 	chip->irq = pci->irq;
@@ -342,10 +342,10 @@ snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id)
 	chip->rev = pci->revision;
 #ifdef CHIP_AU8830
 	if ((chip->rev) != 0xfe && (chip->rev) != 0xfa) {
-		printk(KERN_ALERT
+		pr_alert(
 		       "vortex: The revision (%x) of your card has not been seen before.\n",
 		       chip->rev);
-		printk(KERN_ALERT
+		pr_alert(
 		       "vortex: Please email the results of 'lspci -vv' to openvortex-dev@nongnu.org.\n");
 		snd_card_free(card);
 		err = -ENODEV;
diff --git a/sound/pci/au88x0/au88x0_a3d.c b/sound/pci/au88x0/au88x0_a3d.c
index aad831acbb17..30f760e3d2c0 100644
--- a/sound/pci/au88x0/au88x0_a3d.c
+++ b/sound/pci/au88x0/au88x0_a3d.c
@@ -463,7 +463,7 @@ static void a3dsrc_ZeroSliceIO(a3dsrc_t * a)
 static void a3dsrc_ZeroState(a3dsrc_t * a)
 {
 	/*
-	printk(KERN_DEBUG "vortex: ZeroState slice: %d, source %d\n",
+	pr_debug( "vortex: ZeroState slice: %d, source %d\n",
 	       a->slice, a->source);
 	*/
 	a3dsrc_SetAtmosState(a, 0, 0, 0, 0);
@@ -489,7 +489,7 @@ static void a3dsrc_ZeroStateA3D(a3dsrc_t * a)
 	int i, var, var2;
 
 	if ((a->vortex) == NULL) {
-		printk(KERN_ERR "vortex: ZeroStateA3D: ERROR: a->vortex is NULL\n");
+		pr_err( "vortex: ZeroStateA3D: ERROR: a->vortex is NULL\n");
 		return;
 	}
 
@@ -628,14 +628,14 @@ static void vortex_Vort3D_connect(vortex_t * v, int en)
 	v->mixxtlk[0] =
 	    vortex_adb_checkinout(v, v->fixed_res, en, VORTEX_RESOURCE_MIXIN);
 	if (v->mixxtlk[0] < 0) {
-		printk
+		pr_warn
 		    ("vortex: vortex_Vort3D: ERROR: not enough free mixer resources.\n");
 		return;
 	}
 	v->mixxtlk[1] =
 	    vortex_adb_checkinout(v, v->fixed_res, en, VORTEX_RESOURCE_MIXIN);
 	if (v->mixxtlk[1] < 0) {
-		printk
+		pr_warn
 		    ("vortex: vortex_Vort3D: ERROR: not enough free mixer resources.\n");
 		return;
 	}
@@ -679,7 +679,7 @@ static void vortex_Vort3D_connect(vortex_t * v, int en)
 static void vortex_Vort3D_InitializeSource(a3dsrc_t * a, int en)
 {
 	if (a->vortex == NULL) {
-		printk
+		pr_warn
 		    ("vortex: Vort3D_InitializeSource: A3D source not initialized\n");
 		return;
 	}
diff --git a/sound/pci/au88x0/au88x0_core.c b/sound/pci/au88x0/au88x0_core.c
index ae59dbaa53d9..72e81286b70e 100644
--- a/sound/pci/au88x0/au88x0_core.c
+++ b/sound/pci/au88x0/au88x0_core.c
@@ -285,7 +285,7 @@ vortex_mixer_addWTD(vortex_t * vortex, unsigned char mix, unsigned char ch)
 		temp = hwread(vortex->mmio, prev);
 		//printk(KERN_INFO "vortex: mixAddWTD: while addr=%x, val=%x\n", prev, temp);
 		if ((++lifeboat) > 0xf) {
-			printk(KERN_ERR
+			pr_err(
 			       "vortex_mixer_addWTD: lifeboat overflow\n");
 			return 0;
 		}
@@ -303,7 +303,7 @@ vortex_mixer_delWTD(vortex_t * vortex, unsigned char mix, unsigned char ch)
 
 	eax = hwread(vortex->mmio, VORTEX_MIXER_SR);
 	if (((1 << ch) & eax) == 0) {
-		printk(KERN_ERR "mix ALARM %x\n", eax);
+		pr_err( "mix ALARM %x\n", eax);
 		return 0;
 	}
 	ebp = VORTEX_MIXER_CHNBASE + (ch << 2);
@@ -324,7 +324,7 @@ vortex_mixer_delWTD(vortex_t * vortex, unsigned char mix, unsigned char ch)
 			//printk(KERN_INFO "vortex: mixdelWTD: 1 addr=%x, val=%x, src=%x\n", ebx, edx, src);
 			while ((edx & 0xf) != mix) {
 				if ((esi) > 0xf) {
-					printk(KERN_ERR
+					pr_err(
 					       "vortex: mixdelWTD: error lifeboat overflow\n");
 					return 0;
 				}
@@ -492,7 +492,7 @@ vortex_src_persist_convratio(vortex_t * vortex, unsigned char src, int ratio)
 		hwwrite(vortex->mmio, VORTEX_SRC_CONVRATIO + (src << 2), ratio);
 		temp = hwread(vortex->mmio, VORTEX_SRC_CONVRATIO + (src << 2));
 		if ((++lifeboat) > 0x9) {
-			printk(KERN_ERR "Vortex: Src cvr fail\n");
+			pr_err( "Vortex: Src cvr fail\n");
 			break;
 		}
 	}
@@ -545,7 +545,7 @@ vortex_src_checkratio(vortex_t * vortex, unsigned char src,
 		hwwrite(vortex->mmio, VORTEX_SRC_CONVRATIO + (src << 2), desired_ratio);
 
 		if ((lifeboat++) > 15) {
-			printk(KERN_ERR "Vortex: could not set src-%d from %d to %d\n",
+			pr_err( "Vortex: could not set src-%d from %d to %d\n",
 			       src, hw_ratio, desired_ratio);
 			break;
 		}
@@ -684,7 +684,7 @@ vortex_src_addWTD(vortex_t * vortex, unsigned char src, unsigned char ch)
 		temp = hwread(vortex->mmio, prev);
 		//printk(KERN_INFO "vortex: srcAddWTD: while addr=%x, val=%x\n", prev, temp);
 		if ((++lifeboat) > 0xf) {
-			printk(KERN_ERR
+			pr_err(
 			       "vortex_src_addWTD: lifeboat overflow\n");
 			return 0;
 		}
@@ -703,7 +703,7 @@ vortex_src_delWTD(vortex_t * vortex, unsigned char src, unsigned char ch)
 
 	eax = hwread(vortex->mmio, VORTEX_SRCBLOCK_SR);
 	if (((1 << ch) & eax) == 0) {
-		printk(KERN_ERR "src alarm\n");
+		pr_err( "src alarm\n");
 		return 0;
 	}
 	ebp = VORTEX_SRC_CHNBASE + (ch << 2);
@@ -724,7 +724,7 @@ vortex_src_delWTD(vortex_t * vortex, unsigned char src, unsigned char ch)
 			//printk(KERN_INFO "vortex: srcdelWTD: 1 addr=%x, val=%x, src=%x\n", ebx, edx, src);
 			while ((edx & 0xf) != src) {
 				if ((esi) > 0xf) {
-					printk
+					pr_warn
 					    ("vortex: srcdelWTD: error, lifeboat overflow\n");
 					return 0;
 				}
@@ -819,7 +819,7 @@ vortex_fifo_setadbctrl(vortex_t * vortex, int fifo, int stereo, int priority,
 	do {
 		temp = hwread(vortex->mmio, VORTEX_FIFO_ADBCTRL + (fifo << 2));
 		if (lifeboat++ > 0xbb8) {
-			printk(KERN_ERR
+			pr_err(
 			       "Vortex: vortex_fifo_setadbctrl fail\n");
 			break;
 		}
@@ -915,7 +915,7 @@ vortex_fifo_setwtctrl(vortex_t * vortex, int fifo, int ctrl, int priority,
 	do {
 		temp = hwread(vortex->mmio, VORTEX_FIFO_WTCTRL + (fifo << 2));
 		if (lifeboat++ > 0xbb8) {
-			printk(KERN_ERR "Vortex: vortex_fifo_setwtctrl fail\n");
+			pr_err( "Vortex: vortex_fifo_setwtctrl fail\n");
 			break;
 		}
 	}
@@ -970,7 +970,7 @@ vortex_fifo_setwtctrl(vortex_t * vortex, int fifo, int ctrl, int priority,
     do {
 		temp = hwread(vortex->mmio, VORTEX_FIFO_WTCTRL + (fifo << 2));
 		if (lifeboat++ > 0xbb8) {
-			printk(KERN_ERR "Vortex: vortex_fifo_setwtctrl fail (hanging)\n");
+			pr_err( "Vortex: vortex_fifo_setwtctrl fail (hanging)\n");
 			break;
 		}
     } while ((temp & FIFO_RDONLY)&&(temp & FIFO_VALID)&&(temp != 0xFFFFFFFF));
@@ -1042,7 +1042,7 @@ static void vortex_fifo_init(vortex_t * vortex)
 	for (x = NR_ADB - 1; x >= 0; x--) {
 		hwwrite(vortex->mmio, addr, (FIFO_U0 | FIFO_U1));
 		if (hwread(vortex->mmio, addr) != (FIFO_U0 | FIFO_U1))
-			printk(KERN_ERR "bad adb fifo reset!");
+			pr_err( "bad adb fifo reset!");
 		vortex_fifo_clearadbdata(vortex, x, FIFO_SIZE);
 		addr -= 4;
 	}
@@ -1053,7 +1053,7 @@ static void vortex_fifo_init(vortex_t * vortex)
 	for (x = NR_WT - 1; x >= 0; x--) {
 		hwwrite(vortex->mmio, addr, FIFO_U0);
 		if (hwread(vortex->mmio, addr) != FIFO_U0)
-			printk(KERN_ERR
+			pr_err(
 			       "bad wt fifo reset (0x%08x, 0x%08x)!\n",
 			       addr, hwread(vortex->mmio, addr));
 		vortex_fifo_clearwtdata(vortex, x, FIFO_SIZE);
@@ -1136,7 +1136,7 @@ vortex_adbdma_setbuffers(vortex_t * vortex, int adbdma,
 		break;
 	}
 	/*
-	printk(KERN_DEBUG "vortex: cfg0 = 0x%x\nvortex: cfg1=0x%x\n",
+	pr_debug( "vortex: cfg0 = 0x%x\nvortex: cfg1=0x%x\n",
 	       dma->cfg0, dma->cfg1);
 	*/
 	hwwrite(vortex->mmio, VORTEX_ADBDMA_BUFCFG0 + (adbdma << 3), dma->cfg0);
@@ -1213,7 +1213,7 @@ static int vortex_adbdma_bufshift(vortex_t * vortex, int adbdma)
 	if (dma->period_virt >= dma->nr_periods)
 		dma->period_virt -= dma->nr_periods;
 	if (delta != 1)
-		printk(KERN_INFO "vortex: %d virt=%d, real=%d, delta=%d\n",
+		pr_info( "vortex: %d virt=%d, real=%d, delta=%d\n",
 		       adbdma, dma->period_virt, dma->period_real, delta);
 
 	return delta;
@@ -1482,7 +1482,7 @@ static int vortex_wtdma_bufshift(vortex_t * vortex, int wtdma)
 	dma->period_real = page;
 
 	if (delta != 1)
-		printk(KERN_WARNING "vortex: wt virt = %d, delta = %d\n",
+		pr_warn( "vortex: wt virt = %d, delta = %d\n",
 		       dma->period_virt, delta);
 
 	return delta;
@@ -1667,7 +1667,7 @@ vortex_adb_addroutes(vortex_t * vortex, unsigned char channel,
 		    hwread(vortex->mmio,
 			   VORTEX_ADB_RTBASE + (temp << 2)) & ADB_MASK;
 		if ((lifeboat++) > ADB_MASK) {
-			printk(KERN_ERR
+			pr_err(
 			       "vortex_adb_addroutes: unending route! 0x%x\n",
 			       *route);
 			return;
@@ -1703,7 +1703,7 @@ vortex_adb_delroutes(vortex_t * vortex, unsigned char channel,
 		    hwread(vortex->mmio,
 			   VORTEX_ADB_RTBASE + (prev << 2)) & ADB_MASK;
 		if (((lifeboat++) > ADB_MASK) || (temp == ADB_MASK)) {
-			printk(KERN_ERR
+			pr_err(
 			       "vortex_adb_delroutes: route not found! 0x%x\n",
 			       route0);
 			return;
@@ -1967,7 +1967,7 @@ vortex_connect_codecplay(vortex_t * vortex, int en, unsigned char mixers[])
 					  ADB_CODECOUT(0 + 4));
 		vortex_connection_mix_adb(vortex, en, 0x11, mixers[3],
 					  ADB_CODECOUT(1 + 4));
-		/* printk(KERN_DEBUG "SDAC detected "); */
+		/* pr_debug( "SDAC detected "); */
 	}
 #else
 	// Use plain direct output to codec.
@@ -2022,7 +2022,7 @@ vortex_adb_checkinout(vortex_t * vortex, int resmap[], int out, int restype)
 				else
 					vortex->dma_adb[i].resources[restype] |= (1 << i);
 				/*
-				printk(KERN_DEBUG
+				pr_debug(
 				       "vortex: ResManager: type %d out %d\n",
 				       restype, i);
 				*/
@@ -2037,7 +2037,7 @@ vortex_adb_checkinout(vortex_t * vortex, int resmap[], int out, int restype)
 			if (resmap[restype] & (1 << i)) {
 				resmap[restype] &= ~(1 << i);
 				/*
-				printk(KERN_DEBUG
+				pr_debug(
 				       "vortex: ResManager: type %d in %d\n",
 				       restype, i);
 				*/
@@ -2045,7 +2045,7 @@ vortex_adb_checkinout(vortex_t * vortex, int resmap[], int out, int restype)
 			}
 		}
 	}
-	printk(KERN_ERR "vortex: FATAL: ResManager: resource type %d exhausted.\n", restype);
+	pr_err( "vortex: FATAL: ResManager: resource type %d exhausted.\n", restype);
 	return -ENOMEM;
 }
 
@@ -2173,7 +2173,7 @@ vortex_adb_allocroute(vortex_t *vortex, int dma, int nr_ch, int dir,
 				memset(stream->resources, 0,
 				       sizeof(unsigned char) *
 				       VORTEX_RESOURCE_LAST);
-				printk(KERN_ERR "vortex: out of A3D sources. Sorry\n");
+				pr_err( "vortex: out of A3D sources. Sorry\n");
 				return -EBUSY;
 			}
 			/* (De)Initialize A3D hardware source. */
@@ -2421,7 +2421,7 @@ static irqreturn_t vortex_interrupt(int irq, void *dev_id)
 	hwread(vortex->mmio, VORTEX_IRQ_SOURCE);
 	// Is at least one IRQ flag set?
 	if (source == 0) {
-		printk(KERN_ERR "vortex: missing irq source\n");
+		pr_err( "vortex: missing irq source\n");
 		return IRQ_NONE;
 	}
 
@@ -2429,19 +2429,19 @@ static irqreturn_t vortex_interrupt(int irq, void *dev_id)
 	// Attend every interrupt source.
 	if (unlikely(source & IRQ_ERR_MASK)) {
 		if (source & IRQ_FATAL) {
-			printk(KERN_ERR "vortex: IRQ fatal error\n");
+			pr_err( "vortex: IRQ fatal error\n");
 		}
 		if (source & IRQ_PARITY) {
-			printk(KERN_ERR "vortex: IRQ parity error\n");
+			pr_err( "vortex: IRQ parity error\n");
 		}
 		if (source & IRQ_REG) {
-			printk(KERN_ERR "vortex: IRQ reg error\n");
+			pr_err( "vortex: IRQ reg error\n");
 		}
 		if (source & IRQ_FIFO) {
-			printk(KERN_ERR "vortex: IRQ fifo error\n");
+			pr_err( "vortex: IRQ fifo error\n");
 		}
 		if (source & IRQ_DMA) {
-			printk(KERN_ERR "vortex: IRQ dma error\n");
+			pr_err( "vortex: IRQ dma error\n");
 		}
 		handled = 1;
 	}
@@ -2489,7 +2489,7 @@ static irqreturn_t vortex_interrupt(int irq, void *dev_id)
 	}
 
 	if (!handled) {
-		printk(KERN_ERR "vortex: unknown irq source %x\n", source);
+		pr_err( "vortex: unknown irq source %x\n", source);
 	}
 	return IRQ_RETVAL(handled);
 }
@@ -2546,7 +2546,7 @@ vortex_codec_write(struct snd_ac97 * codec, unsigned short addr, unsigned short
 	while (!(hwread(card->mmio, VORTEX_CODEC_CTRL) & 0x100)) {
 		udelay(100);
 		if (lifeboat++ > POLL_COUNT) {
-			printk(KERN_ERR "vortex: ac97 codec stuck busy\n");
+			pr_err( "vortex: ac97 codec stuck busy\n");
 			return;
 		}
 	}
@@ -2572,7 +2572,7 @@ static unsigned short vortex_codec_read(struct snd_ac97 * codec, unsigned short
 	while (!(hwread(card->mmio, VORTEX_CODEC_CTRL) & 0x100)) {
 		udelay(100);
 		if (lifeboat++ > POLL_COUNT) {
-			printk(KERN_ERR "vortex: ac97 codec stuck busy\n");
+			pr_err( "vortex: ac97 codec stuck busy\n");
 			return 0xffff;
 		}
 	}
@@ -2586,7 +2586,7 @@ static unsigned short vortex_codec_read(struct snd_ac97 * codec, unsigned short
 		udelay(100);
 		data = hwread(card->mmio, VORTEX_CODEC_IO);
 		if (lifeboat++ > POLL_COUNT) {
-			printk(KERN_ERR "vortex: ac97 address never arrived\n");
+			pr_err( "vortex: ac97 address never arrived\n");
 			return 0xffff;
 		}
 	} while ((data & VORTEX_CODEC_ADDMASK) !=
@@ -2683,7 +2683,7 @@ static void vortex_spdif_init(vortex_t * vortex, int spdif_sr, int spdif_mode)
 static int vortex_core_init(vortex_t *vortex)
 {
 
-	printk(KERN_INFO "Vortex: init.... ");
+	pr_info( "Vortex: init.... ");
 	/* Hardware Init. */
 	hwwrite(vortex->mmio, VORTEX_CTRL, 0xffffffff);
 	msleep(5);
@@ -2728,7 +2728,7 @@ static int vortex_core_init(vortex_t *vortex)
 	//vortex_enable_timer_int(vortex);
 	//vortex_disable_timer_int(vortex);
 
-	printk(KERN_INFO "done.\n");
+	pr_info( "done.\n");
 	spin_lock_init(&vortex->lock);
 
 	return 0;
@@ -2737,7 +2737,7 @@ static int vortex_core_init(vortex_t *vortex)
 static int vortex_core_shutdown(vortex_t * vortex)
 {
 
-	printk(KERN_INFO "Vortex: shutdown...");
+	pr_info( "Vortex: shutdown...");
 #ifndef CHIP_AU8820
 	vortex_eq_free(vortex);
 	vortex_Vort3D_disable(vortex);
@@ -2759,7 +2759,7 @@ static int vortex_core_shutdown(vortex_t * vortex)
 	msleep(5);
 	hwwrite(vortex->mmio, VORTEX_IRQ_SOURCE, 0xffff);
 
-	printk(KERN_INFO "done.\n");
+	pr_info( "done.\n");
 	return 0;
 }
 
@@ -2793,7 +2793,7 @@ static int vortex_alsafmt_aspfmt(int alsafmt)
 		break;
 	default:
 		fmt = 0x8;
-		printk(KERN_ERR "vortex: format unsupported %d\n", alsafmt);
+		pr_err( "vortex: format unsupported %d\n", alsafmt);
 		break;
 	}
 	return fmt;
diff --git a/sound/pci/au88x0/au88x0_eq.c b/sound/pci/au88x0/au88x0_eq.c
index e7220533ecfc..9404ba73eaf6 100644
--- a/sound/pci/au88x0/au88x0_eq.c
+++ b/sound/pci/au88x0/au88x0_eq.c
@@ -845,7 +845,7 @@ snd_vortex_peaks_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *u
 
 	vortex_Eqlzr_GetAllPeaks(vortex, peaks, &count);
 	if (count != 20) {
-		printk(KERN_ERR "vortex: peak count error 20 != %d \n", count);
+		pr_err( "vortex: peak count error 20 != %d \n", count);
 		return -1;
 	}
 	for (i = 0; i < 20; i++)
diff --git a/sound/pci/au88x0/au88x0_game.c b/sound/pci/au88x0/au88x0_game.c
index 280f86de2230..72daf6cf8169 100644
--- a/sound/pci/au88x0/au88x0_game.c
+++ b/sound/pci/au88x0/au88x0_game.c
@@ -98,7 +98,7 @@ static int vortex_gameport_register(vortex_t *vortex)
 
 	vortex->gameport = gp = gameport_allocate_port();
 	if (!gp) {
-		printk(KERN_ERR "vortex: cannot allocate memory for gameport\n");
+		pr_err( "vortex: cannot allocate memory for gameport\n");
 		return -ENOMEM;
 	}
 
diff --git a/sound/pci/au88x0/au88x0_mpu401.c b/sound/pci/au88x0/au88x0_mpu401.c
index 29e5945eef60..328c1943c0c3 100644
--- a/sound/pci/au88x0/au88x0_mpu401.c
+++ b/sound/pci/au88x0/au88x0_mpu401.c
@@ -73,7 +73,7 @@ static int snd_vortex_midi(vortex_t *vortex)
 	/* Check if anything is OK. */
 	temp = hwread(vortex->mmio, VORTEX_MIDI_DATA);
 	if (temp != MPU401_ACK /*0xfe */ ) {
-		printk(KERN_ERR "midi port doesn't acknowledge!\n");
+		pr_err( "midi port doesn't acknowledge!\n");
 		return -ENODEV;
 	}
 	/* Enable MPU401 interrupts. */
diff --git a/sound/pci/au88x0/au88x0_pcm.c b/sound/pci/au88x0/au88x0_pcm.c
index 9fb03b4ea925..5adc6b92ffab 100644
--- a/sound/pci/au88x0/au88x0_pcm.c
+++ b/sound/pci/au88x0/au88x0_pcm.c
@@ -227,11 +227,11 @@ snd_vortex_pcm_hw_params(struct snd_pcm_substream *substream,
 	err =
 	    snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params));
 	if (err < 0) {
-		printk(KERN_ERR "Vortex: pcm page alloc failed!\n");
+		pr_err( "Vortex: pcm page alloc failed!\n");
 		return err;
 	}
 	/*
-	   printk(KERN_INFO "Vortex: periods %d, period_bytes %d, channels = %d\n", params_periods(hw_params),
+	   pr_info( "Vortex: periods %d, period_bytes %d, channels = %d\n", params_periods(hw_params),
 	   params_period_bytes(hw_params), params_channels(hw_params));
 	 */
 	spin_lock_irq(&chip->lock);
@@ -371,7 +371,7 @@ static int snd_vortex_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 		}
 #ifndef CHIP_AU8810
 		else {
-			printk(KERN_INFO "vortex: wt start %d\n", dma);
+			pr_info( "vortex: wt start %d\n", dma);
 			vortex_wtdma_startfifo(chip, dma);
 		}
 #endif
@@ -384,7 +384,7 @@ static int snd_vortex_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 			vortex_adbdma_stopfifo(chip, dma);
 #ifndef CHIP_AU8810
 		else {
-			printk(KERN_INFO "vortex: wt stop %d\n", dma);
+			pr_info( "vortex: wt stop %d\n", dma);
 			vortex_wtdma_stopfifo(chip, dma);
 		}
 #endif
diff --git a/sound/pci/au88x0/au88x0_synth.c b/sound/pci/au88x0/au88x0_synth.c
index 922a84bba2ef..f094bac24291 100644
--- a/sound/pci/au88x0/au88x0_synth.c
+++ b/sound/pci/au88x0/au88x0_synth.c
@@ -90,7 +90,7 @@ static int vortex_wt_allocroute(vortex_t * vortex, int wt, int nr_ch)
 	hwwrite(vortex->mmio, WT_PARM(wt, 2), 0);
 
 	temp = hwread(vortex->mmio, WT_PARM(wt, 3));
-	printk(KERN_DEBUG "vortex: WT PARM3: %x\n", temp);
+	pr_debug( "vortex: WT PARM3: %x\n", temp);
 	//hwwrite(vortex->mmio, WT_PARM(wt, 3), temp);
 
 	hwwrite(vortex->mmio, WT_DELAY(wt, 0), 0);
@@ -98,7 +98,7 @@ static int vortex_wt_allocroute(vortex_t * vortex, int wt, int nr_ch)
 	hwwrite(vortex->mmio, WT_DELAY(wt, 2), 0);
 	hwwrite(vortex->mmio, WT_DELAY(wt, 3), 0);
 
-	printk(KERN_DEBUG "vortex: WT GMODE: %x\n", hwread(vortex->mmio, WT_GMODE(wt)));
+	pr_debug( "vortex: WT GMODE: %x\n", hwread(vortex->mmio, WT_GMODE(wt)));
 
 	hwwrite(vortex->mmio, WT_PARM(wt, 2), 0xffffffff);
 	hwwrite(vortex->mmio, WT_PARM(wt, 3), 0xcff1c810);
@@ -106,7 +106,7 @@ static int vortex_wt_allocroute(vortex_t * vortex, int wt, int nr_ch)
 	voice->parm0 = voice->parm1 = 0xcfb23e2f;
 	hwwrite(vortex->mmio, WT_PARM(wt, 0), voice->parm0);
 	hwwrite(vortex->mmio, WT_PARM(wt, 1), voice->parm1);
-	printk(KERN_DEBUG "vortex: WT GMODE 2 : %x\n", hwread(vortex->mmio, WT_GMODE(wt)));
+	pr_debug( "vortex: WT GMODE 2 : %x\n", hwread(vortex->mmio, WT_GMODE(wt)));
 	return 0;
 }
 
@@ -196,14 +196,14 @@ vortex_wt_SetReg(vortex_t * vortex, unsigned char reg, int wt,
 
 	if ((reg == 5) || ((reg >= 7) && (reg <= 10)) || (reg == 0xc)) {
 		if (wt >= (NR_WT / NR_WT_PB)) {
-			printk
+			pr_warn
 			    ("vortex: WT SetReg: bank out of range. reg=0x%x, wt=%d\n",
 			     reg, wt);
 			return 0;
 		}
 	} else {
 		if (wt >= NR_WT) {
-			printk(KERN_ERR "vortex: WT SetReg: voice out of range\n");
+			pr_err( "vortex: WT SetReg: voice out of range\n");
 			return 0;
 		}
 	}
@@ -214,42 +214,42 @@ vortex_wt_SetReg(vortex_t * vortex, unsigned char reg, int wt,
 		/* Voice specific parameters */
 	case 0:		/* running */
 		/*
-		printk(KERN_DEBUG "vortex: WT SetReg(0x%x) = 0x%08x\n",
+		pr_debug( "vortex: WT SetReg(0x%x) = 0x%08x\n",
 		       WT_RUN(wt), (int)val);
 		*/
 		hwwrite(vortex->mmio, WT_RUN(wt), val);
 		return 0xc;
 	case 1:		/* param 0 */
 		/*
-		printk(KERN_DEBUG "vortex: WT SetReg(0x%x) = 0x%08x\n",
+		pr_debug( "vortex: WT SetReg(0x%x) = 0x%08x\n",
 		       WT_PARM(wt,0), (int)val);
 		*/
 		hwwrite(vortex->mmio, WT_PARM(wt, 0), val);
 		return 0xc;
 	case 2:		/* param 1 */
 		/*
-		printk(KERN_DEBUG "vortex: WT SetReg(0x%x) = 0x%08x\n",
+		pr_debug( "vortex: WT SetReg(0x%x) = 0x%08x\n",
 		       WT_PARM(wt,1), (int)val);
 		*/
 		hwwrite(vortex->mmio, WT_PARM(wt, 1), val);
 		return 0xc;
 	case 3:		/* param 2 */
 		/*
-		printk(KERN_DEBUG "vortex: WT SetReg(0x%x) = 0x%08x\n",
+		pr_debug( "vortex: WT SetReg(0x%x) = 0x%08x\n",
 		       WT_PARM(wt,2), (int)val);
 		*/
 		hwwrite(vortex->mmio, WT_PARM(wt, 2), val);
 		return 0xc;
 	case 4:		/* param 3 */
 		/*
-		printk(KERN_DEBUG "vortex: WT SetReg(0x%x) = 0x%08x\n",
+		pr_debug( "vortex: WT SetReg(0x%x) = 0x%08x\n",
 		       WT_PARM(wt,3), (int)val);
 		*/
 		hwwrite(vortex->mmio, WT_PARM(wt, 3), val);
 		return 0xc;
 	case 6:		/* mute */
 		/*
-		printk(KERN_DEBUG "vortex: WT SetReg(0x%x) = 0x%08x\n",
+		pr_debug( "vortex: WT SetReg(0x%x) = 0x%08x\n",
 		       WT_MUTE(wt), (int)val);
 		*/
 		hwwrite(vortex->mmio, WT_MUTE(wt), val);
@@ -257,7 +257,7 @@ vortex_wt_SetReg(vortex_t * vortex, unsigned char reg, int wt,
 	case 0xb:
 			/* delay */
 		/*
-		printk(KERN_DEBUG "vortex: WT SetReg(0x%x) = 0x%08x\n",
+		pr_debug( "vortex: WT SetReg(0x%x) = 0x%08x\n",
 		       WT_DELAY(wt,0), (int)val);
 		*/
 		hwwrite(vortex->mmio, WT_DELAY(wt, 3), val);
@@ -285,7 +285,7 @@ vortex_wt_SetReg(vortex_t * vortex, unsigned char reg, int wt,
 		return 0;
 	}
 	/*
-	printk(KERN_DEBUG "vortex: WT SetReg(0x%x) = 0x%08x\n", ecx, (int)val);
+	pr_debug( "vortex: WT SetReg(0x%x) = 0x%08x\n", ecx, (int)val);
 	*/
 	hwwrite(vortex->mmio, ecx, val);
 	return 1;
diff --git a/sound/pci/ctxfi/ctamixer.c b/sound/pci/ctxfi/ctamixer.c
index fee35cfc0c7f..c7dc38d41b7f 100644
--- a/sound/pci/ctxfi/ctamixer.c
+++ b/sound/pci/ctxfi/ctamixer.c
@@ -258,7 +258,8 @@ static int get_amixer_rsc(struct amixer_mgr *mgr,
 	}
 	spin_unlock_irqrestore(&mgr->mgr_lock, flags);
 	if (err) {
-		printk(KERN_ERR "ctxfi: Can't meet AMIXER resource request!\n");
+		dev_err(mgr->card->dev,
+			"Can't meet AMIXER resource request!\n");
 		goto error;
 	}
 
@@ -296,7 +297,7 @@ static int put_amixer_rsc(struct amixer_mgr *mgr, struct amixer *amixer)
 	return 0;
 }
 
-int amixer_mgr_create(void *hw, struct amixer_mgr **ramixer_mgr)
+int amixer_mgr_create(struct hw *hw, struct amixer_mgr **ramixer_mgr)
 {
 	int err;
 	struct amixer_mgr *amixer_mgr;
@@ -314,6 +315,7 @@ int amixer_mgr_create(void *hw, struct amixer_mgr **ramixer_mgr)
 
 	amixer_mgr->get_amixer = get_amixer_rsc;
 	amixer_mgr->put_amixer = put_amixer_rsc;
+	amixer_mgr->card = hw->card;
 
 	*ramixer_mgr = amixer_mgr;
 
@@ -411,7 +413,8 @@ static int get_sum_rsc(struct sum_mgr *mgr,
 	}
 	spin_unlock_irqrestore(&mgr->mgr_lock, flags);
 	if (err) {
-		printk(KERN_ERR "ctxfi: Can't meet SUM resource request!\n");
+		dev_err(mgr->card->dev,
+			"Can't meet SUM resource request!\n");
 		goto error;
 	}
 
@@ -449,7 +452,7 @@ static int put_sum_rsc(struct sum_mgr *mgr, struct sum *sum)
 	return 0;
 }
 
-int sum_mgr_create(void *hw, struct sum_mgr **rsum_mgr)
+int sum_mgr_create(struct hw *hw, struct sum_mgr **rsum_mgr)
 {
 	int err;
 	struct sum_mgr *sum_mgr;
@@ -467,6 +470,7 @@ int sum_mgr_create(void *hw, struct sum_mgr **rsum_mgr)
 
 	sum_mgr->get_sum = get_sum_rsc;
 	sum_mgr->put_sum = put_sum_rsc;
+	sum_mgr->card = hw->card;
 
 	*rsum_mgr = sum_mgr;
 
diff --git a/sound/pci/ctxfi/ctamixer.h b/sound/pci/ctxfi/ctamixer.h
index cc49e5ab4750..72f42f27434e 100644
--- a/sound/pci/ctxfi/ctamixer.h
+++ b/sound/pci/ctxfi/ctamixer.h
@@ -21,6 +21,7 @@
 
 #include "ctresource.h"
 #include <linux/spinlock.h>
+#include <sound/core.h>
 
 /* Define the descriptor of a summation node resource */
 struct sum {
@@ -35,6 +36,7 @@ struct sum_desc {
 
 struct sum_mgr {
 	struct rsc_mgr mgr;	/* Basic resource manager info */
+	struct snd_card *card;	/* pointer to this card */
 	spinlock_t mgr_lock;
 
 	 /* request one sum resource */
@@ -45,7 +47,7 @@ struct sum_mgr {
 };
 
 /* Constructor and destructor of daio resource manager */
-int sum_mgr_create(void *hw, struct sum_mgr **rsum_mgr);
+int sum_mgr_create(struct hw *hw, struct sum_mgr **rsum_mgr);
 int sum_mgr_destroy(struct sum_mgr *sum_mgr);
 
 /* Define the descriptor of a amixer resource */
@@ -79,6 +81,7 @@ struct amixer_desc {
 
 struct amixer_mgr {
 	struct rsc_mgr mgr;	/* Basic resource manager info */
+	struct snd_card *card;	/* pointer to this card */
 	spinlock_t mgr_lock;
 
 	 /* request one amixer resource */
@@ -90,7 +93,7 @@ struct amixer_mgr {
 };
 
 /* Constructor and destructor of amixer resource manager */
-int amixer_mgr_create(void *hw, struct amixer_mgr **ramixer_mgr);
+int amixer_mgr_create(struct hw *hw, struct amixer_mgr **ramixer_mgr);
 int amixer_mgr_destroy(struct amixer_mgr *amixer_mgr);
 
 #endif /* CTAMIXER_H */
diff --git a/sound/pci/ctxfi/ctatc.c b/sound/pci/ctxfi/ctatc.c
index af632bd08323..454659074390 100644
--- a/sound/pci/ctxfi/ctatc.c
+++ b/sound/pci/ctxfi/ctatc.c
@@ -106,11 +106,11 @@ static struct {
 			    .public_name = "Mixer"}
 };
 
-typedef int (*create_t)(void *, void **);
+typedef int (*create_t)(struct hw *, void **);
 typedef int (*destroy_t)(void *);
 
 static struct {
-	int (*create)(void *hw, void **rmgr);
+	int (*create)(struct hw *hw, void **rmgr);
 	int (*destroy)(void *mgr);
 } rsc_mgr_funcs[NUM_RSCTYP] = {
 	[SRC] 		= { .create 	= (create_t)src_mgr_create,
@@ -171,7 +171,8 @@ static unsigned long atc_get_ptp_phys(struct ct_atc *atc, int index)
 	return atc->vm->get_ptp_phys(atc->vm, index);
 }
 
-static unsigned int convert_format(snd_pcm_format_t snd_format)
+static unsigned int convert_format(snd_pcm_format_t snd_format,
+				   struct snd_card *card)
 {
 	switch (snd_format) {
 	case SNDRV_PCM_FORMAT_U8:
@@ -185,7 +186,7 @@ static unsigned int convert_format(snd_pcm_format_t snd_format)
 	case SNDRV_PCM_FORMAT_FLOAT_LE:
 		return SRC_SF_F32;
 	default:
-		printk(KERN_ERR "ctxfi: not recognized snd format is %d \n",
+		dev_err(card->dev, "not recognized snd format is %d\n",
 			snd_format);
 		return SRC_SF_S16;
 	}
@@ -268,7 +269,8 @@ static int atc_pcm_playback_prepare(struct ct_atc *atc, struct ct_atc_pcm *apcm)
 	src = apcm->src;
 	src->ops->set_pitch(src, pitch);
 	src->ops->set_rom(src, select_rom(pitch));
-	src->ops->set_sf(src, convert_format(apcm->substream->runtime->format));
+	src->ops->set_sf(src, convert_format(apcm->substream->runtime->format,
+					     atc->card));
 	src->ops->set_pm(src, (src->ops->next_interleave(src) != NULL));
 
 	/* Get AMIXER resource */
@@ -738,7 +740,8 @@ static int atc_pcm_capture_start(struct ct_atc *atc, struct ct_atc_pcm *apcm)
 
 	/*  Set up recording SRC */
 	src = apcm->src;
-	src->ops->set_sf(src, convert_format(apcm->substream->runtime->format));
+	src->ops->set_sf(src, convert_format(apcm->substream->runtime->format,
+					     atc->card));
 	src->ops->set_sa(src, apcm->vm_block->addr);
 	src->ops->set_la(src, apcm->vm_block->addr + apcm->vm_block->size);
 	src->ops->set_ca(src, apcm->vm_block->addr);
@@ -807,7 +810,8 @@ static int spdif_passthru_playback_get_resources(struct ct_atc *atc,
 	src = apcm->src;
 	src->ops->set_pitch(src, pitch);
 	src->ops->set_rom(src, select_rom(pitch));
-	src->ops->set_sf(src, convert_format(apcm->substream->runtime->format));
+	src->ops->set_sf(src, convert_format(apcm->substream->runtime->format,
+					     atc->card));
 	src->ops->set_pm(src, (src->ops->next_interleave(src) != NULL));
 	src->ops->set_bp(src, 1);
 
@@ -1235,7 +1239,7 @@ static int ct_atc_destroy(struct ct_atc *atc)
 	}
 
 	if (atc->hw)
-		destroy_hw_obj((struct hw *)atc->hw);
+		destroy_hw_obj(atc->hw);
 
 	/* Destroy device virtual memory manager object */
 	if (atc->vm) {
@@ -1282,9 +1286,9 @@ static int atc_identify_card(struct ct_atc *atc, unsigned int ssid)
 	p = snd_pci_quirk_lookup_id(vendor_id, device_id, list);
 	if (p) {
 		if (p->value < 0) {
-			printk(KERN_ERR "ctxfi: "
-			       "Device %04x:%04x is black-listed\n",
-			       vendor_id, device_id);
+			dev_err(atc->card->dev,
+				"Device %04x:%04x is black-listed\n",
+				vendor_id, device_id);
 			return -ENOENT;
 		}
 		atc->model = p->value;
@@ -1315,8 +1319,8 @@ int ct_atc_create_alsa_devs(struct ct_atc *atc)
 		err = alsa_dev_funcs[i].create(atc, i,
 				alsa_dev_funcs[i].public_name);
 		if (err) {
-			printk(KERN_ERR "ctxfi: "
-			       "Creating alsa device %d failed!\n", i);
+			dev_err(atc->card->dev,
+				"Creating alsa device %d failed!\n", i);
 			return err;
 		}
 	}
@@ -1332,9 +1336,10 @@ static int atc_create_hw_devs(struct ct_atc *atc)
 
 	err = create_hw_obj(atc->pci, atc->chip_type, atc->model, &hw);
 	if (err) {
-		printk(KERN_ERR "Failed to create hw obj!!!\n");
+		dev_err(atc->card->dev, "Failed to create hw obj!!!\n");
 		return err;
 	}
+	hw->card = atc->card;
 	atc->hw = hw;
 
 	/* Initialize card hardware. */
@@ -1351,8 +1356,8 @@ static int atc_create_hw_devs(struct ct_atc *atc)
 
 		err = rsc_mgr_funcs[i].create(atc->hw, &atc->rsc_mgrs[i]);
 		if (err) {
-			printk(KERN_ERR "ctxfi: "
-			       "Failed to create rsc_mgr %d!!!\n", i);
+			dev_err(atc->card->dev,
+				"Failed to create rsc_mgr %d!!!\n", i);
 			return err;
 		}
 	}
@@ -1399,8 +1404,9 @@ static int atc_get_resources(struct ct_atc *atc)
 		err = daio_mgr->get_daio(daio_mgr, &da_desc,
 					(struct daio **)&atc->daios[i]);
 		if (err) {
-			printk(KERN_ERR "ctxfi: Failed to get DAIO "
-					"resource %d!!!\n", i);
+			dev_err(atc->card->dev,
+				"Failed to get DAIO resource %d!!!\n",
+				i);
 			return err;
 		}
 		atc->n_daio++;
@@ -1603,8 +1609,8 @@ static int atc_resume(struct ct_atc *atc)
 	/* Do hardware resume. */
 	err = atc_hw_resume(atc);
 	if (err < 0) {
-		printk(KERN_ERR "ctxfi: pci_enable_device failed, "
-		       "disabling device\n");
+		dev_err(atc->card->dev,
+			"pci_enable_device failed, disabling device\n");
 		snd_card_disconnect(atc->card);
 		return err;
 	}
@@ -1701,7 +1707,7 @@ int ct_atc_create(struct snd_card *card, struct pci_dev *pci,
 	/* Find card model */
 	err = atc_identify_card(atc, ssid);
 	if (err < 0) {
-		printk(KERN_ERR "ctatc: Card not recognised\n");
+		dev_err(card->dev, "ctatc: Card not recognised\n");
 		goto error1;
 	}
 
@@ -1717,7 +1723,7 @@ int ct_atc_create(struct snd_card *card, struct pci_dev *pci,
 
 	err = ct_mixer_create(atc, (struct ct_mixer **)&atc->mixer);
 	if (err) {
-		printk(KERN_ERR "ctxfi: Failed to create mixer obj!!!\n");
+		dev_err(card->dev, "Failed to create mixer obj!!!\n");
 		goto error1;
 	}
 
@@ -1744,6 +1750,6 @@ int ct_atc_create(struct snd_card *card, struct pci_dev *pci,
 
 error1:
 	ct_atc_destroy(atc);
-	printk(KERN_ERR "ctxfi: Something wrong!!!\n");
+	dev_err(card->dev, "Something wrong!!!\n");
 	return err;
 }
diff --git a/sound/pci/ctxfi/ctatc.h b/sound/pci/ctxfi/ctatc.h
index 5f11ca22fcde..56413343a9e8 100644
--- a/sound/pci/ctxfi/ctatc.h
+++ b/sound/pci/ctxfi/ctatc.h
@@ -131,7 +131,7 @@ struct ct_atc {
 	/* Don't touch! Used for internal object. */
 	void *rsc_mgrs[NUM_RSCTYP]; /* chip resource managers */
 	void *mixer;		/* internal mixer object */
-	void *hw;		/* chip specific hardware access object */
+	struct hw *hw;		/* chip specific hardware access object */
 	void **daios;		/* digital audio io resources */
 	void **pcm;		/* SUMs for collecting all pcm stream */
 	void **srcs;		/* Sample Rate Converters for input signal */
diff --git a/sound/pci/ctxfi/ctdaio.c b/sound/pci/ctxfi/ctdaio.c
index 84f86bf63b8f..c1c3f8816fff 100644
--- a/sound/pci/ctxfi/ctdaio.c
+++ b/sound/pci/ctxfi/ctdaio.c
@@ -140,19 +140,19 @@ static int dao_rsc_reinit(struct dao *dao, const struct dao_desc *desc);
 
 static int dao_spdif_get_spos(struct dao *dao, unsigned int *spos)
 {
-	((struct hw *)dao->hw)->dao_get_spos(dao->ctrl_blk, spos);
+	dao->hw->dao_get_spos(dao->ctrl_blk, spos);
 	return 0;
 }
 
 static int dao_spdif_set_spos(struct dao *dao, unsigned int spos)
 {
-	((struct hw *)dao->hw)->dao_set_spos(dao->ctrl_blk, spos);
+	dao->hw->dao_set_spos(dao->ctrl_blk, spos);
 	return 0;
 }
 
 static int dao_commit_write(struct dao *dao)
 {
-	((struct hw *)dao->hw)->dao_commit_write(dao->hw,
+	dao->hw->dao_commit_write(dao->hw,
 		daio_device_index(dao->daio.type, dao->hw), dao->ctrl_blk);
 	return 0;
 }
@@ -277,16 +277,14 @@ static struct dao_rsc_ops dao_ops = {
 static int dai_set_srt_srcl(struct dai *dai, struct rsc *src)
 {
 	src->ops->master(src);
-	((struct hw *)dai->hw)->dai_srt_set_srcm(dai->ctrl_blk,
-						src->ops->index(src));
+	dai->hw->dai_srt_set_srcm(dai->ctrl_blk, src->ops->index(src));
 	return 0;
 }
 
 static int dai_set_srt_srcr(struct dai *dai, struct rsc *src)
 {
 	src->ops->master(src);
-	((struct hw *)dai->hw)->dai_srt_set_srco(dai->ctrl_blk,
-						src->ops->index(src));
+	dai->hw->dai_srt_set_srco(dai->ctrl_blk, src->ops->index(src));
 	return 0;
 }
 
@@ -297,25 +295,25 @@ static int dai_set_srt_msr(struct dai *dai, unsigned int msr)
 	for (rsr = 0; msr > 1; msr >>= 1)
 		rsr++;
 
-	((struct hw *)dai->hw)->dai_srt_set_rsr(dai->ctrl_blk, rsr);
+	dai->hw->dai_srt_set_rsr(dai->ctrl_blk, rsr);
 	return 0;
 }
 
 static int dai_set_enb_src(struct dai *dai, unsigned int enb)
 {
-	((struct hw *)dai->hw)->dai_srt_set_ec(dai->ctrl_blk, enb);
+	dai->hw->dai_srt_set_ec(dai->ctrl_blk, enb);
 	return 0;
 }
 
 static int dai_set_enb_srt(struct dai *dai, unsigned int enb)
 {
-	((struct hw *)dai->hw)->dai_srt_set_et(dai->ctrl_blk, enb);
+	dai->hw->dai_srt_set_et(dai->ctrl_blk, enb);
 	return 0;
 }
 
 static int dai_commit_write(struct dai *dai)
 {
-	((struct hw *)dai->hw)->dai_commit_write(dai->hw,
+	dai->hw->dai_commit_write(dai->hw,
 		daio_device_index(dai->daio.type, dai->hw), dai->ctrl_blk);
 	return 0;
 }
@@ -331,12 +329,12 @@ static struct dai_rsc_ops dai_ops = {
 
 static int daio_rsc_init(struct daio *daio,
 			 const struct daio_desc *desc,
-			 void *hw)
+			 struct hw *hw)
 {
 	int err;
 	unsigned int idx_l, idx_r;
 
-	switch (((struct hw *)hw)->chip_type) {
+	switch (hw->chip_type) {
 	case ATC20K1:
 		idx_l = idx_20k1[desc->type].left;
 		idx_r = idx_20k1[desc->type].right;
@@ -360,7 +358,7 @@ static int daio_rsc_init(struct daio *daio,
 	if (desc->type <= DAIO_OUT_MAX) {
 		daio->rscl.ops = daio->rscr.ops = &daio_out_rsc_ops;
 	} else {
-		switch (((struct hw *)hw)->chip_type) {
+		switch (hw->chip_type) {
 		case ATC20K1:
 			daio->rscl.ops = daio->rscr.ops = &daio_in_rsc_ops_20k1;
 			break;
@@ -445,7 +443,7 @@ static int dao_rsc_uninit(struct dao *dao)
 		kfree(dao->imappers);
 		dao->imappers = NULL;
 	}
-	((struct hw *)dao->hw)->dao_put_ctrl_blk(dao->ctrl_blk);
+	dao->hw->dao_put_ctrl_blk(dao->ctrl_blk);
 	dao->hw = dao->ctrl_blk = NULL;
 	daio_rsc_uninit(&dao->daio);
 
@@ -502,7 +500,7 @@ error1:
 
 static int dai_rsc_uninit(struct dai *dai)
 {
-	((struct hw *)dai->hw)->dai_put_ctrl_blk(dai->ctrl_blk);
+	dai->hw->dai_put_ctrl_blk(dai->ctrl_blk);
 	dai->hw = dai->ctrl_blk = NULL;
 	daio_rsc_uninit(&dai->daio);
 	return 0;
@@ -541,7 +539,8 @@ static int get_daio_rsc(struct daio_mgr *mgr,
 	err = daio_mgr_get_rsc(&mgr->mgr, desc->type);
 	spin_unlock_irqrestore(&mgr->mgr_lock, flags);
 	if (err) {
-		printk(KERN_ERR "Can't meet DAIO resource request!\n");
+		dev_err(mgr->card->dev,
+			"Can't meet DAIO resource request!\n");
 		return err;
 	}
 
@@ -692,7 +691,7 @@ static int daio_mgr_commit_write(struct daio_mgr *mgr)
 	return 0;
 }
 
-int daio_mgr_create(void *hw, struct daio_mgr **rdaio_mgr)
+int daio_mgr_create(struct hw *hw, struct daio_mgr **rdaio_mgr)
 {
 	int err, i;
 	struct daio_mgr *daio_mgr;
@@ -727,12 +726,13 @@ int daio_mgr_create(void *hw, struct daio_mgr **rdaio_mgr)
 	daio_mgr->imap_add = daio_imap_add;
 	daio_mgr->imap_delete = daio_imap_delete;
 	daio_mgr->commit_write = daio_mgr_commit_write;
+	daio_mgr->card = hw->card;
 
 	for (i = 0; i < 8; i++) {
-		((struct hw *)hw)->daio_mgr_dsb_dao(daio_mgr->mgr.ctrl_blk, i);
-		((struct hw *)hw)->daio_mgr_dsb_dai(daio_mgr->mgr.ctrl_blk, i);
+		hw->daio_mgr_dsb_dao(daio_mgr->mgr.ctrl_blk, i);
+		hw->daio_mgr_dsb_dai(daio_mgr->mgr.ctrl_blk, i);
 	}
-	((struct hw *)hw)->daio_mgr_commit_write(hw, daio_mgr->mgr.ctrl_blk);
+	hw->daio_mgr_commit_write(hw, daio_mgr->mgr.ctrl_blk);
 
 	*rdaio_mgr = daio_mgr;
 
diff --git a/sound/pci/ctxfi/ctdaio.h b/sound/pci/ctxfi/ctdaio.h
index 85ccb6ee1ab4..0ebbf350f51a 100644
--- a/sound/pci/ctxfi/ctdaio.h
+++ b/sound/pci/ctxfi/ctdaio.h
@@ -23,6 +23,7 @@
 #include "ctimap.h"
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <sound/core.h>
 
 /* Define the descriptor of a daio resource */
 enum DAIOTYP {
@@ -53,14 +54,14 @@ struct dao {
 	struct dao_rsc_ops *ops;	/* DAO specific operations */
 	struct imapper **imappers;
 	struct daio_mgr *mgr;
-	void *hw;
+	struct hw *hw;
 	void *ctrl_blk;
 };
 
 struct dai {
 	struct daio daio;
 	struct dai_rsc_ops *ops;	/* DAI specific operations */
-	void *hw;
+	struct hw *hw;
 	void *ctrl_blk;
 };
 
@@ -98,6 +99,7 @@ struct daio_desc {
 
 struct daio_mgr {
 	struct rsc_mgr mgr;	/* Basic resource manager info */
+	struct snd_card *card;	/* pointer to this card */
 	spinlock_t mgr_lock;
 	spinlock_t imap_lock;
 	struct list_head imappers;
@@ -117,7 +119,7 @@ struct daio_mgr {
 };
 
 /* Constructor and destructor of daio resource manager */
-int daio_mgr_create(void *hw, struct daio_mgr **rdaio_mgr);
+int daio_mgr_create(struct hw *hw, struct daio_mgr **rdaio_mgr);
 int daio_mgr_destroy(struct daio_mgr *daio_mgr);
 
 #endif /* CTDAIO_H */
diff --git a/sound/pci/ctxfi/cthardware.h b/sound/pci/ctxfi/cthardware.h
index 5977e9a24b5c..54cc9cb75f00 100644
--- a/sound/pci/ctxfi/cthardware.h
+++ b/sound/pci/ctxfi/cthardware.h
@@ -20,6 +20,7 @@
 
 #include <linux/types.h>
 #include <linux/pci.h>
+#include <sound/core.h>
 
 enum CHIPTYP {
 	ATC20K1,
@@ -184,9 +185,10 @@ struct hw {
 	void *irq_callback_data;
 
 	struct pci_dev *pci;	/* the pci kernel structure of this card */
+	struct snd_card *card;	/* pointer to this card */
 	int irq;
 	unsigned long io_base;
-	unsigned long mem_base;
+	void __iomem *mem_base;
 
 	enum CHIPTYP chip_type;
 	enum CTCARDS model;
diff --git a/sound/pci/ctxfi/cthw20k1.c b/sound/pci/ctxfi/cthw20k1.c
index 6ac40beb49da..b425aa8ee578 100644
--- a/sound/pci/ctxfi/cthw20k1.c
+++ b/sound/pci/ctxfi/cthw20k1.c
@@ -1268,7 +1268,8 @@ static int hw_trn_init(struct hw *hw, const struct trn_conf *info)
 
 	/* Set up device page table */
 	if ((~0UL) == info->vm_pgt_phys) {
-		printk(KERN_ERR "Wrong device page table page address!\n");
+		dev_err(hw->card->dev,
+			"Wrong device page table page address!\n");
 		return -1;
 	}
 
@@ -1327,7 +1328,7 @@ static int hw_pll_init(struct hw *hw, unsigned int rsr)
 		mdelay(40);
 	}
 	if (i >= 3) {
-		printk(KERN_ALERT "PLL initialization failed!!!\n");
+		dev_alert(hw->card->dev, "PLL initialization failed!!!\n");
 		return -EBUSY;
 	}
 
@@ -1351,7 +1352,7 @@ static int hw_auto_init(struct hw *hw)
 			break;
 	}
 	if (!get_field(gctl, GCTL_AID)) {
-		printk(KERN_ALERT "Card Auto-init failed!!!\n");
+		dev_alert(hw->card->dev, "Card Auto-init failed!!!\n");
 		return -EBUSY;
 	}
 
@@ -1802,7 +1803,7 @@ static int uaa_to_xfi(struct pci_dev *pci)
 	unsigned int is_uaa;
 	unsigned int data[4] = {0};
 	unsigned int io_base;
-	void *mem_base;
+	void __iomem *mem_base;
 	int i;
 	const u32 CTLX = CTLBITS('C', 'T', 'L', 'X');
 	const u32 CTL_ = CTLBITS('C', 'T', 'L', '-');
@@ -1911,9 +1912,9 @@ static int hw_card_start(struct hw *hw)
 	/* Set DMA transfer mask */
 	if (pci_set_dma_mask(pci, CT_XFI_DMA_MASK) < 0 ||
 	    pci_set_consistent_dma_mask(pci, CT_XFI_DMA_MASK) < 0) {
-		printk(KERN_ERR "architecture does not support PCI "
-				"busmaster DMA with mask 0x%llx\n",
-		       CT_XFI_DMA_MASK);
+		dev_err(hw->card->dev,
+			"architecture does not support PCI busmaster DMA with mask 0x%llx\n",
+			CT_XFI_DMA_MASK);
 		err = -ENXIO;
 		goto error1;
 	}
@@ -1942,7 +1943,8 @@ static int hw_card_start(struct hw *hw)
 		err = request_irq(pci->irq, ct_20k1_interrupt, IRQF_SHARED,
 				  KBUILD_MODNAME, hw);
 		if (err < 0) {
-			printk(KERN_ERR "XFi: Cannot get irq %d\n", pci->irq);
+			dev_err(hw->card->dev,
+				"XFi: Cannot get irq %d\n", pci->irq);
 			goto error2;
 		}
 		hw->irq = pci->irq;
@@ -1985,9 +1987,9 @@ static int hw_card_shutdown(struct hw *hw)
 	hw->irq	= -1;
 
 	if (hw->mem_base)
-		iounmap((void *)hw->mem_base);
+		iounmap(hw->mem_base);
 
-	hw->mem_base = (unsigned long)NULL;
+	hw->mem_base = NULL;
 
 	if (hw->io_base)
 		pci_release_regions(hw->pci);
diff --git a/sound/pci/ctxfi/cthw20k2.c b/sound/pci/ctxfi/cthw20k2.c
index b1438861d38a..253899d13790 100644
--- a/sound/pci/ctxfi/cthw20k2.c
+++ b/sound/pci/ctxfi/cthw20k2.c
@@ -1187,7 +1187,8 @@ static int hw_daio_init(struct hw *hw, const struct daio_conf *info)
 		hw_write_20kx(hw, AUDIO_IO_TX_BLRCLK, 0x21212121);
 		hw_write_20kx(hw, AUDIO_IO_RX_BLRCLK, 0);
 	} else {
-		printk(KERN_ALERT "ctxfi: ERROR!!! Invalid sampling rate!!!\n");
+		dev_alert(hw->card->dev,
+			  "ERROR!!! Invalid sampling rate!!!\n");
 		return -EINVAL;
 	}
 
@@ -1246,8 +1247,8 @@ static int hw_trn_init(struct hw *hw, const struct trn_conf *info)
 
 	/* Set up device page table */
 	if ((~0UL) == info->vm_pgt_phys) {
-		printk(KERN_ALERT "ctxfi: "
-		       "Wrong device page table page address!!!\n");
+		dev_alert(hw->card->dev,
+			  "Wrong device page table page address!!!\n");
 		return -1;
 	}
 
@@ -1352,7 +1353,8 @@ static int hw_pll_init(struct hw *hw, unsigned int rsr)
 		break;
 	}
 	if (i >= 1000) {
-		printk(KERN_ALERT "ctxfi: PLL initialization failed!!!\n");
+		dev_alert(hw->card->dev,
+			  "PLL initialization failed!!!\n");
 		return -EBUSY;
 	}
 
@@ -1376,7 +1378,7 @@ static int hw_auto_init(struct hw *hw)
 			break;
 	}
 	if (!get_field(gctl, GCTL_AID)) {
-		printk(KERN_ALERT "ctxfi: Card Auto-init failed!!!\n");
+		dev_alert(hw->card->dev, "Card Auto-init failed!!!\n");
 		return -EBUSY;
 	}
 
@@ -1847,7 +1849,7 @@ static int hw_adc_init(struct hw *hw, const struct adc_conf *info)
 	/* Initialize I2C */
 	err = hw20k2_i2c_init(hw, 0x1A, 1, 1);
 	if (err < 0) {
-		printk(KERN_ALERT "ctxfi: Failure to acquire I2C!!!\n");
+		dev_alert(hw->card->dev, "Failure to acquire I2C!!!\n");
 		goto error;
 	}
 
@@ -1890,8 +1892,9 @@ static int hw_adc_init(struct hw *hw, const struct adc_conf *info)
 		hw20k2_i2c_write(hw, MAKE_WM8775_ADDR(WM8775_MMC, 0x0A),
 						MAKE_WM8775_DATA(0x0A));
 	} else {
-		printk(KERN_ALERT "ctxfi: Invalid master sampling "
-				  "rate (msr %d)!!!\n", info->msr);
+		dev_alert(hw->card->dev,
+			  "Invalid master sampling rate (msr %d)!!!\n",
+			  info->msr);
 		err = -EINVAL;
 		goto error;
 	}
@@ -2034,8 +2037,9 @@ static int hw_card_start(struct hw *hw)
 	/* Set DMA transfer mask */
 	if (pci_set_dma_mask(pci, CT_XFI_DMA_MASK) < 0 ||
 	    pci_set_consistent_dma_mask(pci, CT_XFI_DMA_MASK) < 0) {
-		printk(KERN_ERR "ctxfi: architecture does not support PCI "
-		"busmaster DMA with mask 0x%llx\n", CT_XFI_DMA_MASK);
+		dev_err(hw->card->dev,
+			"architecture does not support PCI busmaster DMA with mask 0x%llx\n",
+			CT_XFI_DMA_MASK);
 		err = -ENXIO;
 		goto error1;
 	}
@@ -2046,8 +2050,8 @@ static int hw_card_start(struct hw *hw)
 			goto error1;
 
 		hw->io_base = pci_resource_start(hw->pci, 2);
-		hw->mem_base = (unsigned long)ioremap(hw->io_base,
-					pci_resource_len(hw->pci, 2));
+		hw->mem_base = ioremap(hw->io_base,
+				       pci_resource_len(hw->pci, 2));
 		if (!hw->mem_base) {
 			err = -ENOENT;
 			goto error2;
@@ -2063,7 +2067,8 @@ static int hw_card_start(struct hw *hw)
 		err = request_irq(pci->irq, ct_20k2_interrupt, IRQF_SHARED,
 				  KBUILD_MODNAME, hw);
 		if (err < 0) {
-			printk(KERN_ERR "XFi: Cannot get irq %d\n", pci->irq);
+			dev_err(hw->card->dev,
+				"XFi: Cannot get irq %d\n", pci->irq);
 			goto error2;
 		}
 		hw->irq = pci->irq;
@@ -2107,9 +2112,9 @@ static int hw_card_shutdown(struct hw *hw)
 	hw->irq	= -1;
 
 	if (hw->mem_base)
-		iounmap((void *)hw->mem_base);
+		iounmap(hw->mem_base);
 
-	hw->mem_base = (unsigned long)NULL;
+	hw->mem_base = NULL;
 
 	if (hw->io_base)
 		pci_release_regions(hw->pci);
@@ -2229,12 +2234,12 @@ static int hw_resume(struct hw *hw, struct card_conf *info)
 
 static u32 hw_read_20kx(struct hw *hw, u32 reg)
 {
-	return readl((void *)(hw->mem_base + reg));
+	return readl(hw->mem_base + reg);
 }
 
 static void hw_write_20kx(struct hw *hw, u32 reg, u32 data)
 {
-	writel(data, (void *)(hw->mem_base + reg));
+	writel(data, hw->mem_base + reg);
 }
 
 static struct hw ct20k2_preset = {
diff --git a/sound/pci/ctxfi/ctmixer.c b/sound/pci/ctxfi/ctmixer.c
index 48fe0e39c2be..4f4a2a5dedb8 100644
--- a/sound/pci/ctxfi/ctmixer.c
+++ b/sound/pci/ctxfi/ctmixer.c
@@ -854,8 +854,8 @@ static int ct_mixer_get_resources(struct ct_mixer *mixer)
 	for (i = 0; i < (NUM_CT_SUMS * CHN_NUM); i++) {
 		err = sum_mgr->get_sum(sum_mgr, &sum_desc, &sum);
 		if (err) {
-			printk(KERN_ERR "ctxfi:Failed to get sum resources for "
-					  "front output!\n");
+			dev_err(mixer->atc->card->dev,
+				"Failed to get sum resources for front output!\n");
 			break;
 		}
 		mixer->sums[i] = sum;
@@ -869,8 +869,8 @@ static int ct_mixer_get_resources(struct ct_mixer *mixer)
 	for (i = 0; i < (NUM_CT_AMIXERS * CHN_NUM); i++) {
 		err = amixer_mgr->get_amixer(amixer_mgr, &am_desc, &amixer);
 		if (err) {
-			printk(KERN_ERR "ctxfi:Failed to get amixer resources "
-			       "for mixer obj!\n");
+			dev_err(mixer->atc->card->dev,
+				"Failed to get amixer resources for mixer obj!\n");
 			break;
 		}
 		mixer->amixers[i] = amixer;
diff --git a/sound/pci/ctxfi/ctpcm.c b/sound/pci/ctxfi/ctpcm.c
index e8a4feb1ed86..d86c474ca5b6 100644
--- a/sound/pci/ctxfi/ctpcm.c
+++ b/sound/pci/ctxfi/ctpcm.c
@@ -217,7 +217,8 @@ static int ct_pcm_playback_prepare(struct snd_pcm_substream *substream)
 		err = atc->pcm_playback_prepare(atc, apcm);
 
 	if (err < 0) {
-		printk(KERN_ERR "ctxfi: Preparing pcm playback failed!!!\n");
+		dev_err(atc->card->dev,
+			"Preparing pcm playback failed!!!\n");
 		return err;
 	}
 
@@ -324,7 +325,8 @@ static int ct_pcm_capture_prepare(struct snd_pcm_substream *substream)
 
 	err = atc->pcm_capture_prepare(atc, apcm);
 	if (err < 0) {
-		printk(KERN_ERR "ctxfi: Preparing pcm capture failed!!!\n");
+		dev_err(atc->card->dev,
+			"Preparing pcm capture failed!!!\n");
 		return err;
 	}
 
@@ -435,7 +437,8 @@ int ct_alsa_pcm_create(struct ct_atc *atc,
 	err = snd_pcm_new(atc->card, "ctxfi", device,
 			  playback_count, capture_count, &pcm);
 	if (err < 0) {
-		printk(KERN_ERR "ctxfi: snd_pcm_new failed!! Err=%d\n", err);
+		dev_err(atc->card->dev, "snd_pcm_new failed!! Err=%d\n",
+			err);
 		return err;
 	}
 
diff --git a/sound/pci/ctxfi/ctresource.c b/sound/pci/ctxfi/ctresource.c
index 7dfaf67344d4..1a97e406d8ec 100644
--- a/sound/pci/ctxfi/ctresource.c
+++ b/sound/pci/ctxfi/ctresource.c
@@ -134,7 +134,8 @@ static struct rsc_ops rsc_generic_ops = {
 	.next_conj	= rsc_next_conj,
 };
 
-int rsc_init(struct rsc *rsc, u32 idx, enum RSCTYP type, u32 msr, void *hw)
+int
+rsc_init(struct rsc *rsc, u32 idx, enum RSCTYP type, u32 msr, struct hw *hw)
 {
 	int err = 0;
 
@@ -151,25 +152,24 @@ int rsc_init(struct rsc *rsc, u32 idx, enum RSCTYP type, u32 msr, void *hw)
 
 	switch (type) {
 	case SRC:
-		err = ((struct hw *)hw)->src_rsc_get_ctrl_blk(&rsc->ctrl_blk);
+		err = hw->src_rsc_get_ctrl_blk(&rsc->ctrl_blk);
 		break;
 	case AMIXER:
-		err = ((struct hw *)hw)->
-				amixer_rsc_get_ctrl_blk(&rsc->ctrl_blk);
+		err = hw->amixer_rsc_get_ctrl_blk(&rsc->ctrl_blk);
 		break;
 	case SRCIMP:
 	case SUM:
 	case DAIO:
 		break;
 	default:
-		printk(KERN_ERR
-		       "ctxfi: Invalid resource type value %d!\n", type);
+		dev_err(((struct hw *)hw)->card->dev,
+			"Invalid resource type value %d!\n", type);
 		return -EINVAL;
 	}
 
 	if (err) {
-		printk(KERN_ERR
-		       "ctxfi: Failed to get resource control block!\n");
+		dev_err(((struct hw *)hw)->card->dev,
+			"Failed to get resource control block!\n");
 		return err;
 	}
 
@@ -181,19 +181,18 @@ int rsc_uninit(struct rsc *rsc)
 	if ((NULL != rsc->hw) && (NULL != rsc->ctrl_blk)) {
 		switch (rsc->type) {
 		case SRC:
-			((struct hw *)rsc->hw)->
-				src_rsc_put_ctrl_blk(rsc->ctrl_blk);
+			rsc->hw->src_rsc_put_ctrl_blk(rsc->ctrl_blk);
 			break;
 		case AMIXER:
-			((struct hw *)rsc->hw)->
-				amixer_rsc_put_ctrl_blk(rsc->ctrl_blk);
+			rsc->hw->amixer_rsc_put_ctrl_blk(rsc->ctrl_blk);
 			break;
 		case SUM:
 		case DAIO:
 			break;
 		default:
-			printk(KERN_ERR "ctxfi: "
-			       "Invalid resource type value %d!\n", rsc->type);
+			dev_err(((struct hw *)rsc->hw)->card->dev,
+				"Invalid resource type value %d!\n",
+				rsc->type);
 			break;
 		}
 
@@ -208,10 +207,9 @@ int rsc_uninit(struct rsc *rsc)
 }
 
 int rsc_mgr_init(struct rsc_mgr *mgr, enum RSCTYP type,
-		 unsigned int amount, void *hw_obj)
+		 unsigned int amount, struct hw *hw)
 {
 	int err = 0;
-	struct hw *hw = hw_obj;
 
 	mgr->type = NUM_RSCTYP;
 
@@ -235,15 +233,15 @@ int rsc_mgr_init(struct rsc_mgr *mgr, enum RSCTYP type,
 	case SUM:
 		break;
 	default:
-		printk(KERN_ERR
-		       "ctxfi: Invalid resource type value %d!\n", type);
+		dev_err(hw->card->dev,
+			"Invalid resource type value %d!\n", type);
 		err = -EINVAL;
 		goto error;
 	}
 
 	if (err) {
-		printk(KERN_ERR
-		       "ctxfi: Failed to get manager control block!\n");
+		dev_err(hw->card->dev,
+			"Failed to get manager control block!\n");
 		goto error;
 	}
 
@@ -268,26 +266,23 @@ int rsc_mgr_uninit(struct rsc_mgr *mgr)
 	if ((NULL != mgr->hw) && (NULL != mgr->ctrl_blk)) {
 		switch (mgr->type) {
 		case SRC:
-			((struct hw *)mgr->hw)->
-				src_mgr_put_ctrl_blk(mgr->ctrl_blk);
+			mgr->hw->src_mgr_put_ctrl_blk(mgr->ctrl_blk);
 			break;
 		case SRCIMP:
-			((struct hw *)mgr->hw)->
-				srcimp_mgr_put_ctrl_blk(mgr->ctrl_blk);
+			mgr->hw->srcimp_mgr_put_ctrl_blk(mgr->ctrl_blk);
 			break;
 		case AMIXER:
-			((struct hw *)mgr->hw)->
-				amixer_mgr_put_ctrl_blk(mgr->ctrl_blk);
+			mgr->hw->amixer_mgr_put_ctrl_blk(mgr->ctrl_blk);
 			break;
 		case DAIO:
-			((struct hw *)mgr->hw)->
-				daio_mgr_put_ctrl_blk(mgr->ctrl_blk);
+			mgr->hw->daio_mgr_put_ctrl_blk(mgr->ctrl_blk);
 			break;
 		case SUM:
 			break;
 		default:
-			printk(KERN_ERR "ctxfi: "
-			       "Invalid resource type value %d!\n", mgr->type);
+			dev_err(((struct hw *)mgr->hw)->card->dev,
+				"Invalid resource type value %d!\n",
+				mgr->type);
 			break;
 		}
 
diff --git a/sound/pci/ctxfi/ctresource.h b/sound/pci/ctxfi/ctresource.h
index 0838c2e84f8b..9b746c3719e6 100644
--- a/sound/pci/ctxfi/ctresource.h
+++ b/sound/pci/ctxfi/ctresource.h
@@ -38,7 +38,7 @@ struct rsc {
 	u32 conj:12;	/* Current conjugate index */
 	u32 msr:4;	/* The Master Sample Rate a resource working on */
 	void *ctrl_blk;	/* Chip specific control info block for a resource */
-	void *hw;	/* Chip specific object for hardware access means */
+	struct hw *hw;	/* Chip specific object for hardware access means */
 	struct rsc_ops *ops;	/* Generic resource operations */
 };
 
@@ -50,7 +50,8 @@ struct rsc_ops {
 	int (*output_slot)(const struct rsc *rsc);
 };
 
-int rsc_init(struct rsc *rsc, u32 idx, enum RSCTYP type, u32 msr, void *hw);
+int
+rsc_init(struct rsc *rsc, u32 idx, enum RSCTYP type, u32 msr, struct hw *hw);
 int rsc_uninit(struct rsc *rsc);
 
 struct rsc_mgr {
@@ -59,12 +60,12 @@ struct rsc_mgr {
 	unsigned int avail; /* The amount of currently available resources */
 	unsigned char *rscs; /* The bit-map for resource allocation */
 	void *ctrl_blk; /* Chip specific control info block */
-	void *hw; /* Chip specific object for hardware access */
+	struct hw *hw; /* Chip specific object for hardware access */
 };
 
 /* Resource management is based on bit-map mechanism */
 int rsc_mgr_init(struct rsc_mgr *mgr, enum RSCTYP type,
-		 unsigned int amount, void *hw);
+		 unsigned int amount, struct hw *hw);
 int rsc_mgr_uninit(struct rsc_mgr *mgr);
 int mgr_get_resource(struct rsc_mgr *mgr, unsigned int n, unsigned int *ridx);
 int mgr_put_resource(struct rsc_mgr *mgr, unsigned int n, unsigned int idx);
diff --git a/sound/pci/ctxfi/ctsrc.c b/sound/pci/ctxfi/ctsrc.c
index 6e77e86307c2..ec1f08464d93 100644
--- a/sound/pci/ctxfi/ctsrc.c
+++ b/sound/pci/ctxfi/ctsrc.c
@@ -431,7 +431,8 @@ get_src_rsc(struct src_mgr *mgr, const struct src_desc *desc, struct src **rsrc)
 
 	spin_unlock_irqrestore(&mgr->mgr_lock, flags);
 	if (err) {
-		printk(KERN_ERR "ctxfi: Can't meet SRC resource request!\n");
+		dev_err(mgr->card->dev,
+			"Can't meet SRC resource request!\n");
 		return err;
 	}
 
@@ -543,7 +544,7 @@ static int src_mgr_commit_write(struct src_mgr *mgr)
 	return 0;
 }
 
-int src_mgr_create(void *hw, struct src_mgr **rsrc_mgr)
+int src_mgr_create(struct hw *hw, struct src_mgr **rsrc_mgr)
 {
 	int err, i;
 	struct src_mgr *src_mgr;
@@ -558,7 +559,7 @@ int src_mgr_create(void *hw, struct src_mgr **rsrc_mgr)
 		goto error1;
 
 	spin_lock_init(&src_mgr->mgr_lock);
-	conj_mask = ((struct hw *)hw)->src_dirty_conj_mask();
+	conj_mask = hw->src_dirty_conj_mask();
 
 	src_mgr->get_src = get_src_rsc;
 	src_mgr->put_src = put_src_rsc;
@@ -566,12 +567,13 @@ int src_mgr_create(void *hw, struct src_mgr **rsrc_mgr)
 	src_mgr->src_enable = src_enable;
 	src_mgr->src_disable = src_disable;
 	src_mgr->commit_write = src_mgr_commit_write;
+	src_mgr->card = hw->card;
 
 	/* Disable all SRC resources. */
 	for (i = 0; i < 256; i++)
-		((struct hw *)hw)->src_mgr_dsb_src(src_mgr->mgr.ctrl_blk, i);
+		hw->src_mgr_dsb_src(src_mgr->mgr.ctrl_blk, i);
 
-	((struct hw *)hw)->src_mgr_commit_write(hw, src_mgr->mgr.ctrl_blk);
+	hw->src_mgr_commit_write(hw, src_mgr->mgr.ctrl_blk);
 
 	*rsrc_mgr = src_mgr;
 
@@ -739,7 +741,8 @@ static int get_srcimp_rsc(struct srcimp_mgr *mgr,
 	}
 	spin_unlock_irqrestore(&mgr->mgr_lock, flags);
 	if (err) {
-		printk(KERN_ERR "ctxfi: Can't meet SRCIMP resource request!\n");
+		dev_err(mgr->card->dev,
+			"Can't meet SRCIMP resource request!\n");
 		goto error1;
 	}
 
@@ -825,7 +828,7 @@ static int srcimp_imap_delete(struct srcimp_mgr *mgr, struct imapper *entry)
 	return err;
 }
 
-int srcimp_mgr_create(void *hw, struct srcimp_mgr **rsrcimp_mgr)
+int srcimp_mgr_create(struct hw *hw, struct srcimp_mgr **rsrcimp_mgr)
 {
 	int err;
 	struct srcimp_mgr *srcimp_mgr;
@@ -857,6 +860,7 @@ int srcimp_mgr_create(void *hw, struct srcimp_mgr **rsrcimp_mgr)
 	srcimp_mgr->put_srcimp = put_srcimp_rsc;
 	srcimp_mgr->imap_add = srcimp_imap_add;
 	srcimp_mgr->imap_delete = srcimp_imap_delete;
+	srcimp_mgr->card = hw->card;
 
 	*rsrcimp_mgr = srcimp_mgr;
 
diff --git a/sound/pci/ctxfi/ctsrc.h b/sound/pci/ctxfi/ctsrc.h
index 259366aabcac..da7573c5db9b 100644
--- a/sound/pci/ctxfi/ctsrc.h
+++ b/sound/pci/ctxfi/ctsrc.h
@@ -23,6 +23,7 @@
 #include "ctimap.h"
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <sound/core.h>
 
 #define SRC_STATE_OFF	0x0
 #define SRC_STATE_INIT	0x4
@@ -85,6 +86,7 @@ struct src_desc {
 /* Define src manager object */
 struct src_mgr {
 	struct rsc_mgr mgr;	/* Basic resource manager info */
+	struct snd_card *card;	/* pointer to this card */
 	spinlock_t mgr_lock;
 
 	 /* request src resource */
@@ -123,6 +125,7 @@ struct srcimp_desc {
 
 struct srcimp_mgr {
 	struct rsc_mgr mgr;	/* Basic resource manager info */
+	struct snd_card *card;	/* pointer to this card */
 	spinlock_t mgr_lock;
 	spinlock_t imap_lock;
 	struct list_head imappers;
@@ -140,10 +143,10 @@ struct srcimp_mgr {
 };
 
 /* Constructor and destructor of SRC resource manager */
-int src_mgr_create(void *hw, struct src_mgr **rsrc_mgr);
+int src_mgr_create(struct hw *hw, struct src_mgr **rsrc_mgr);
 int src_mgr_destroy(struct src_mgr *src_mgr);
 /* Constructor and destructor of SRCIMP resource manager */
-int srcimp_mgr_create(void *hw, struct srcimp_mgr **rsrc_mgr);
+int srcimp_mgr_create(struct hw *hw, struct srcimp_mgr **rsrc_mgr);
 int srcimp_mgr_destroy(struct srcimp_mgr *srcimp_mgr);
 
 #endif /* CTSRC_H */
diff --git a/sound/pci/ctxfi/ctvmem.c b/sound/pci/ctxfi/ctvmem.c
index 6109490b83e8..419306ef825f 100644
--- a/sound/pci/ctxfi/ctvmem.c
+++ b/sound/pci/ctxfi/ctvmem.c
@@ -16,6 +16,7 @@
  */
 
 #include "ctvmem.h"
+#include "ctatc.h"
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/io.h>
@@ -29,15 +30,15 @@
  * @size must be page aligned.
  * */
 static struct ct_vm_block *
-get_vm_block(struct ct_vm *vm, unsigned int size)
+get_vm_block(struct ct_vm *vm, unsigned int size, struct ct_atc *atc)
 {
 	struct ct_vm_block *block = NULL, *entry;
 	struct list_head *pos;
 
 	size = CT_PAGE_ALIGN(size);
 	if (size > vm->size) {
-		printk(KERN_ERR "ctxfi: Fail! No sufficient device virtual "
-				  "memory space available!\n");
+		dev_err(atc->card->dev,
+			"Fail! No sufficient device virtual memory space available!\n");
 		return NULL;
 	}
 
@@ -129,11 +130,12 @@ ct_vm_map(struct ct_vm *vm, struct snd_pcm_substream *substream, int size)
 	unsigned int pte_start;
 	unsigned i, pages;
 	unsigned long *ptp;
+	struct ct_atc *atc = snd_pcm_substream_chip(substream);
 
-	block = get_vm_block(vm, size);
+	block = get_vm_block(vm, size, atc);
 	if (block == NULL) {
-		printk(KERN_ERR "ctxfi: No virtual memory block that is big "
-				  "enough to allocate!\n");
+		dev_err(atc->card->dev,
+			"No virtual memory block that is big enough to allocate!\n");
 		return NULL;
 	}
 
diff --git a/sound/pci/ctxfi/xfi.c b/sound/pci/ctxfi/xfi.c
index 8f8b566a1b35..f2f32779de98 100644
--- a/sound/pci/ctxfi/xfi.c
+++ b/sound/pci/ctxfi/xfi.c
@@ -76,17 +76,18 @@ ct_card_probe(struct pci_dev *pci, const struct pci_device_id *pci_id)
 	if (err)
 		return err;
 	if ((reference_rate != 48000) && (reference_rate != 44100)) {
-		printk(KERN_ERR "ctxfi: Invalid reference_rate value %u!!!\n",
-		       reference_rate);
-		printk(KERN_ERR "ctxfi: The valid values for reference_rate "
-		       "are 48000 and 44100, Value 48000 is assumed.\n");
+		dev_err(card->dev,
+			"Invalid reference_rate value %u!!!\n",
+			reference_rate);
+		dev_err(card->dev,
+			"The valid values for reference_rate are 48000 and 44100, Value 48000 is assumed.\n");
 		reference_rate = 48000;
 	}
 	if ((multiple != 1) && (multiple != 2) && (multiple != 4)) {
-		printk(KERN_ERR "ctxfi: Invalid multiple value %u!!!\n",
-		       multiple);
-		printk(KERN_ERR "ctxfi: The valid values for multiple are "
-		       "1, 2 and 4, Value 2 is assumed.\n");
+		dev_err(card->dev, "Invalid multiple value %u!!!\n",
+			multiple);
+		dev_err(card->dev,
+			"The valid values for multiple are 1, 2 and 4, Value 2 is assumed.\n");
 		multiple = 2;
 	}
 	err = ct_atc_create(card, pci, reference_rate, multiple,
diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c
index 51dea49aadd4..fcc5e478c9a1 100644
--- a/sound/pci/hda/hda_auto_parser.c
+++ b/sound/pci/hda/hda_auto_parser.c
@@ -57,12 +57,14 @@ static void sort_pins_by_sequence(hda_nid_t *pins, struct auto_out_pin *list,
 
 
 /* add the found input-pin to the cfg->inputs[] table */
-static void add_auto_cfg_input_pin(struct auto_pin_cfg *cfg, hda_nid_t nid,
-				   int type)
+static void add_auto_cfg_input_pin(struct hda_codec *codec, struct auto_pin_cfg *cfg,
+				   hda_nid_t nid, int type)
 {
 	if (cfg->num_inputs < AUTO_CFG_MAX_INS) {
 		cfg->inputs[cfg->num_inputs].pin = nid;
 		cfg->inputs[cfg->num_inputs].type = type;
+		cfg->inputs[cfg->num_inputs].has_boost_on_pin =
+			nid_has_volume(codec, nid, HDA_INPUT);
 		cfg->num_inputs++;
 	}
 }
@@ -71,7 +73,12 @@ static int compare_input_type(const void *ap, const void *bp)
 {
 	const struct auto_pin_cfg_item *a = ap;
 	const struct auto_pin_cfg_item *b = bp;
-	return (int)(a->type - b->type);
+	if (a->type != b->type)
+		return (int)(a->type - b->type);
+
+	/* In case one has boost and the other one has not,
+	   pick the one with boost first. */
+	return (int)(b->has_boost_on_pin - a->has_boost_on_pin);
 }
 
 /* Reorder the surround channels
@@ -268,16 +275,16 @@ int snd_hda_parse_pin_defcfg(struct hda_codec *codec,
 			cfg->hp_outs++;
 			break;
 		case AC_JACK_MIC_IN:
-			add_auto_cfg_input_pin(cfg, nid, AUTO_PIN_MIC);
+			add_auto_cfg_input_pin(codec, cfg, nid, AUTO_PIN_MIC);
 			break;
 		case AC_JACK_LINE_IN:
-			add_auto_cfg_input_pin(cfg, nid, AUTO_PIN_LINE_IN);
+			add_auto_cfg_input_pin(codec, cfg, nid, AUTO_PIN_LINE_IN);
 			break;
 		case AC_JACK_CD:
-			add_auto_cfg_input_pin(cfg, nid, AUTO_PIN_CD);
+			add_auto_cfg_input_pin(codec, cfg, nid, AUTO_PIN_CD);
 			break;
 		case AC_JACK_AUX:
-			add_auto_cfg_input_pin(cfg, nid, AUTO_PIN_AUX);
+			add_auto_cfg_input_pin(codec, cfg, nid, AUTO_PIN_AUX);
 			break;
 		case AC_JACK_SPDIF_OUT:
 		case AC_JACK_DIG_OTHER_OUT:
diff --git a/sound/pci/hda/hda_auto_parser.h b/sound/pci/hda/hda_auto_parser.h
index e941f604f5e5..2b8e29fd73e7 100644
--- a/sound/pci/hda/hda_auto_parser.h
+++ b/sound/pci/hda/hda_auto_parser.h
@@ -38,6 +38,7 @@ struct auto_pin_cfg_item {
 	int type;
 	unsigned int is_headset_mic:1;
 	unsigned int is_headphone_mic:1; /* Mic-only in headphone jack */
+	unsigned int has_boost_on_pin:1;
 };
 
 struct auto_pin_cfg;
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index ec6a7d0d1886..15e0089492f7 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -2002,6 +2002,26 @@ u32 query_amp_caps(struct hda_codec *codec, hda_nid_t nid, int direction)
 EXPORT_SYMBOL_GPL(query_amp_caps);
 
 /**
+ * snd_hda_check_amp_caps - query AMP capabilities
+ * @codec: the HD-audio codec
+ * @nid: the NID to query
+ * @dir: either #HDA_INPUT or #HDA_OUTPUT
+ *
+ * Check whether the widget has the given amp capability for the direction.
+ */
+bool snd_hda_check_amp_caps(struct hda_codec *codec, hda_nid_t nid,
+			   int dir, unsigned int bits)
+{
+	if (!nid)
+		return false;
+	if (get_wcaps(codec, nid) & (1 << (dir + 1)))
+		if (query_amp_caps(codec, nid, dir) & bits)
+			return true;
+	return false;
+}
+EXPORT_SYMBOL_GPL(snd_hda_check_amp_caps);
+
+/**
  * snd_hda_override_amp_caps - Override the AMP capabilities
  * @codec: the CODEC to clean up
  * @nid: the NID to clean up
@@ -4817,121 +4837,6 @@ int snd_hda_build_pcms(struct hda_bus *bus)
 EXPORT_SYMBOL_GPL(snd_hda_build_pcms);
 
 /**
- * snd_hda_check_board_config - compare the current codec with the config table
- * @codec: the HDA codec
- * @num_configs: number of config enums
- * @models: array of model name strings
- * @tbl: configuration table, terminated by null entries
- *
- * Compares the modelname or PCI subsystem id of the current codec with the
- * given configuration table.  If a matching entry is found, returns its
- * config value (supposed to be 0 or positive).
- *
- * If no entries are matching, the function returns a negative value.
- */
-int snd_hda_check_board_config(struct hda_codec *codec,
-			       int num_configs, const char * const *models,
-			       const struct snd_pci_quirk *tbl)
-{
-	if (codec->modelname && models) {
-		int i;
-		for (i = 0; i < num_configs; i++) {
-			if (models[i] &&
-			    !strcmp(codec->modelname, models[i])) {
-				codec_info(codec, "model '%s' is selected\n",
-					   models[i]);
-				return i;
-			}
-		}
-	}
-
-	if (!codec->bus->pci || !tbl)
-		return -1;
-
-	tbl = snd_pci_quirk_lookup(codec->bus->pci, tbl);
-	if (!tbl)
-		return -1;
-	if (tbl->value >= 0 && tbl->value < num_configs) {
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		char tmp[10];
-		const char *model = NULL;
-		if (models)
-			model = models[tbl->value];
-		if (!model) {
-			sprintf(tmp, "#%d", tbl->value);
-			model = tmp;
-		}
-		codec_info(codec, "model '%s' is selected for config %x:%x (%s)\n",
-			   model, tbl->subvendor, tbl->subdevice,
-			   (tbl->name ? tbl->name : "Unknown device"));
-#endif
-		return tbl->value;
-	}
-	return -1;
-}
-EXPORT_SYMBOL_GPL(snd_hda_check_board_config);
-
-/**
- * snd_hda_check_board_codec_sid_config - compare the current codec
-					subsystem ID with the
-					config table
-
-	   This is important for Gateway notebooks with SB450 HDA Audio
-	   where the vendor ID of the PCI device is:
-		ATI Technologies Inc SB450 HDA Audio [1002:437b]
-	   and the vendor/subvendor are found only at the codec.
-
- * @codec: the HDA codec
- * @num_configs: number of config enums
- * @models: array of model name strings
- * @tbl: configuration table, terminated by null entries
- *
- * Compares the modelname or PCI subsystem id of the current codec with the
- * given configuration table.  If a matching entry is found, returns its
- * config value (supposed to be 0 or positive).
- *
- * If no entries are matching, the function returns a negative value.
- */
-int snd_hda_check_board_codec_sid_config(struct hda_codec *codec,
-			       int num_configs, const char * const *models,
-			       const struct snd_pci_quirk *tbl)
-{
-	const struct snd_pci_quirk *q;
-
-	/* Search for codec ID */
-	for (q = tbl; q->subvendor; q++) {
-		unsigned int mask = 0xffff0000 | q->subdevice_mask;
-		unsigned int id = (q->subdevice | (q->subvendor << 16)) & mask;
-		if ((codec->subsystem_id & mask) == id)
-			break;
-	}
-
-	if (!q->subvendor)
-		return -1;
-
-	tbl = q;
-
-	if (tbl->value >= 0 && tbl->value < num_configs) {
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		char tmp[10];
-		const char *model = NULL;
-		if (models)
-			model = models[tbl->value];
-		if (!model) {
-			sprintf(tmp, "#%d", tbl->value);
-			model = tmp;
-		}
-		codec_info(codec, "model '%s' is selected for config %x:%x (%s)\n",
-			   model, tbl->subvendor, tbl->subdevice,
-			   (tbl->name ? tbl->name : "Unknown device"));
-#endif
-		return tbl->value;
-	}
-	return -1;
-}
-EXPORT_SYMBOL_GPL(snd_hda_check_board_codec_sid_config);
-
-/**
  * snd_hda_add_new_ctls - create controls from the array
  * @codec: the HDA codec
  * @knew: the array of struct snd_kcontrol_new
diff --git a/sound/pci/hda/hda_codec.h b/sound/pci/hda/hda_codec.h
index bbc5a1392c75..9c8820f21f94 100644
--- a/sound/pci/hda/hda_codec.h
+++ b/sound/pci/hda/hda_codec.h
@@ -687,6 +687,4 @@ snd_hda_codec_load_dsp_cleanup(struct hda_codec *codec,
 				struct snd_dma_buffer *dmab) {}
 #endif
 
-#define EXPORT_SYMBOL_HDA(sym) EXPORT_SYMBOL_GPL(sym)
-
 #endif /* __SOUND_HDA_CODEC_H */
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index b956449ddada..64220c08bd98 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -31,6 +31,7 @@
 #include <linux/module.h>
 #include <sound/core.h>
 #include <sound/jack.h>
+#include <sound/tlv.h>
 #include "hda_codec.h"
 #include "hda_local.h"
 #include "hda_auto_parser.h"
@@ -518,18 +519,6 @@ static unsigned int amp_val_replace_channels(unsigned int val, unsigned int chs)
 	return val;
 }
 
-/* check whether the widget has the given amp capability for the direction */
-static bool check_amp_caps(struct hda_codec *codec, hda_nid_t nid,
-			   int dir, unsigned int bits)
-{
-	if (!nid)
-		return false;
-	if (get_wcaps(codec, nid) & (1 << (dir + 1)))
-		if (query_amp_caps(codec, nid, dir) & bits)
-			return true;
-	return false;
-}
-
 static bool same_amp_caps(struct hda_codec *codec, hda_nid_t nid1,
 			  hda_nid_t nid2, int dir)
 {
@@ -539,11 +528,6 @@ static bool same_amp_caps(struct hda_codec *codec, hda_nid_t nid1,
 		query_amp_caps(codec, nid2, dir));
 }
 
-#define nid_has_mute(codec, nid, dir) \
-	check_amp_caps(codec, nid, dir, (AC_AMPCAP_MUTE | AC_AMPCAP_MIN_MUTE))
-#define nid_has_volume(codec, nid, dir) \
-	check_amp_caps(codec, nid, dir, AC_AMPCAP_NUM_STEPS)
-
 /* look for a widget suitable for assigning a mute switch in the path */
 static hda_nid_t look_for_out_mute_nid(struct hda_codec *codec,
 				       struct nid_path *path)
@@ -1105,6 +1089,7 @@ enum {
  */
 static int assign_out_path_ctls(struct hda_codec *codec, struct nid_path *path)
 {
+	struct hda_gen_spec *spec = codec->spec;
 	hda_nid_t nid;
 	unsigned int val;
 	int badness = 0;
@@ -1119,6 +1104,8 @@ static int assign_out_path_ctls(struct hda_codec *codec, struct nid_path *path)
 	nid = look_for_out_vol_nid(codec, path);
 	if (nid) {
 		val = HDA_COMPOSE_AMP_VAL(nid, 3, 0, HDA_OUTPUT);
+		if (spec->dac_min_mute)
+			val |= HDA_AMP_VAL_MIN_MUTE;
 		if (is_ctl_used(codec, val, NID_PATH_VOL_CTL))
 			badness += BAD_SHARED_VOL;
 		else
@@ -1880,9 +1867,12 @@ static int parse_output_paths(struct hda_codec *codec)
 		path = snd_hda_get_path_from_idx(codec, spec->out_paths[0]);
 		if (path)
 			spec->vmaster_nid = look_for_out_vol_nid(codec, path);
-		if (spec->vmaster_nid)
+		if (spec->vmaster_nid) {
 			snd_hda_set_vmaster_tlv(codec, spec->vmaster_nid,
 						HDA_OUTPUT, spec->vmaster_tlv);
+			if (spec->dac_min_mute)
+				spec->vmaster_tlv[3] |= TLV_DB_SCALE_MUTE;
+		}
 	}
 
 	/* set initial pinctl targets */
@@ -2025,7 +2015,8 @@ static int create_speaker_out_ctls(struct hda_codec *codec)
  * independent HP controls
  */
 
-static void call_hp_automute(struct hda_codec *codec, struct hda_jack_tbl *jack);
+static void call_hp_automute(struct hda_codec *codec,
+			     struct hda_jack_callback *jack);
 static int indep_hp_info(struct snd_kcontrol *kcontrol,
 			 struct snd_ctl_elem_info *uinfo)
 {
@@ -3941,7 +3932,8 @@ static void call_update_outputs(struct hda_codec *codec)
 }
 
 /* standard HP-automute helper */
-void snd_hda_gen_hp_automute(struct hda_codec *codec, struct hda_jack_tbl *jack)
+void snd_hda_gen_hp_automute(struct hda_codec *codec,
+			     struct hda_jack_callback *jack)
 {
 	struct hda_gen_spec *spec = codec->spec;
 	hda_nid_t *pins = spec->autocfg.hp_pins;
@@ -3961,7 +3953,8 @@ void snd_hda_gen_hp_automute(struct hda_codec *codec, struct hda_jack_tbl *jack)
 EXPORT_SYMBOL_GPL(snd_hda_gen_hp_automute);
 
 /* standard line-out-automute helper */
-void snd_hda_gen_line_automute(struct hda_codec *codec, struct hda_jack_tbl *jack)
+void snd_hda_gen_line_automute(struct hda_codec *codec,
+			       struct hda_jack_callback *jack)
 {
 	struct hda_gen_spec *spec = codec->spec;
 
@@ -3981,7 +3974,8 @@ void snd_hda_gen_line_automute(struct hda_codec *codec, struct hda_jack_tbl *jac
 EXPORT_SYMBOL_GPL(snd_hda_gen_line_automute);
 
 /* standard mic auto-switch helper */
-void snd_hda_gen_mic_autoswitch(struct hda_codec *codec, struct hda_jack_tbl *jack)
+void snd_hda_gen_mic_autoswitch(struct hda_codec *codec,
+				struct hda_jack_callback *jack)
 {
 	struct hda_gen_spec *spec = codec->spec;
 	int i;
@@ -4004,7 +3998,8 @@ void snd_hda_gen_mic_autoswitch(struct hda_codec *codec, struct hda_jack_tbl *ja
 EXPORT_SYMBOL_GPL(snd_hda_gen_mic_autoswitch);
 
 /* call appropriate hooks */
-static void call_hp_automute(struct hda_codec *codec, struct hda_jack_tbl *jack)
+static void call_hp_automute(struct hda_codec *codec,
+			     struct hda_jack_callback *jack)
 {
 	struct hda_gen_spec *spec = codec->spec;
 	if (spec->hp_automute_hook)
@@ -4014,7 +4009,7 @@ static void call_hp_automute(struct hda_codec *codec, struct hda_jack_tbl *jack)
 }
 
 static void call_line_automute(struct hda_codec *codec,
-			       struct hda_jack_tbl *jack)
+			       struct hda_jack_callback *jack)
 {
 	struct hda_gen_spec *spec = codec->spec;
 	if (spec->line_automute_hook)
@@ -4024,7 +4019,7 @@ static void call_line_automute(struct hda_codec *codec,
 }
 
 static void call_mic_autoswitch(struct hda_codec *codec,
-				struct hda_jack_tbl *jack)
+				struct hda_jack_callback *jack)
 {
 	struct hda_gen_spec *spec = codec->spec;
 	if (spec->mic_autoswitch_hook)
@@ -4173,7 +4168,7 @@ static int check_auto_mute_availability(struct hda_codec *codec)
 		if (!is_jack_detectable(codec, nid))
 			continue;
 		codec_dbg(codec, "Enable HP auto-muting on NID 0x%x\n", nid);
-		snd_hda_jack_detect_enable_callback(codec, nid, HDA_GEN_HP_EVENT,
+		snd_hda_jack_detect_enable_callback(codec, nid,
 						    call_hp_automute);
 		spec->detect_hp = 1;
 	}
@@ -4186,7 +4181,6 @@ static int check_auto_mute_availability(struct hda_codec *codec)
 					continue;
 				codec_dbg(codec, "Enable Line-Out auto-muting on NID 0x%x\n", nid);
 				snd_hda_jack_detect_enable_callback(codec, nid,
-								    HDA_GEN_FRONT_EVENT,
 								    call_line_automute);
 				spec->detect_lo = 1;
 			}
@@ -4228,7 +4222,6 @@ static bool auto_mic_check_imux(struct hda_codec *codec)
 	for (i = 1; i < spec->am_num_entries; i++)
 		snd_hda_jack_detect_enable_callback(codec,
 						    spec->am_entry[i].pin,
-						    HDA_GEN_MIC_EVENT,
 						    call_mic_autoswitch);
 	return true;
 }
diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h
index bb2dea743986..61dd5153f512 100644
--- a/sound/pci/hda/hda_generic.h
+++ b/sound/pci/hda/hda_generic.h
@@ -12,12 +12,6 @@
 #ifndef __SOUND_HDA_GENERIC_H
 #define __SOUND_HDA_GENERIC_H
 
-/* unsol event tags */
-enum {
-	HDA_GEN_HP_EVENT = 1, HDA_GEN_FRONT_EVENT, HDA_GEN_MIC_EVENT,
-	HDA_GEN_LAST_EVENT = HDA_GEN_MIC_EVENT
-};
-
 /* table entry for multi-io paths */
 struct hda_multi_io {
 	hda_nid_t pin;		/* multi-io widget pin NID */
@@ -231,6 +225,7 @@ struct hda_gen_spec {
 	unsigned int add_stereo_mix_input:1; /* add aamix as a capture src */
 	unsigned int add_jack_modes:1; /* add i/o jack mode enum ctls */
 	unsigned int power_down_unused:1; /* power down unused widgets */
+	unsigned int dac_min_mute:1; /* minimal = mute for DACs */
 
 	/* other internal flags */
 	unsigned int no_analog:1; /* digital I/O only */
@@ -289,11 +284,11 @@ struct hda_gen_spec {
 
 	/* automute / autoswitch hooks */
 	void (*hp_automute_hook)(struct hda_codec *codec,
-				 struct hda_jack_tbl *tbl);
+				 struct hda_jack_callback *cb);
 	void (*line_automute_hook)(struct hda_codec *codec,
-				   struct hda_jack_tbl *tbl);
+				   struct hda_jack_callback *cb);
 	void (*mic_autoswitch_hook)(struct hda_codec *codec,
-				    struct hda_jack_tbl *tbl);
+				    struct hda_jack_callback *cb);
 };
 
 int snd_hda_gen_spec_init(struct hda_gen_spec *spec);
@@ -325,11 +320,11 @@ int snd_hda_gen_build_pcms(struct hda_codec *codec);
 
 /* standard jack event callbacks */
 void snd_hda_gen_hp_automute(struct hda_codec *codec,
-			     struct hda_jack_tbl *jack);
+			     struct hda_jack_callback *jack);
 void snd_hda_gen_line_automute(struct hda_codec *codec,
-			       struct hda_jack_tbl *jack);
+			       struct hda_jack_callback *jack);
 void snd_hda_gen_mic_autoswitch(struct hda_codec *codec,
-				struct hda_jack_tbl *jack);
+				struct hda_jack_callback *jack);
 void snd_hda_gen_update_outputs(struct hda_codec *codec);
 
 #ifdef CONFIG_PM
diff --git a/sound/pci/hda/hda_jack.c b/sound/pci/hda/hda_jack.c
index 9746d73cec52..f56765ae73a7 100644
--- a/sound/pci/hda/hda_jack.c
+++ b/sound/pci/hda/hda_jack.c
@@ -94,7 +94,7 @@ EXPORT_SYMBOL_GPL(snd_hda_jack_tbl_get_from_tag);
 /**
  * snd_hda_jack_tbl_new - create a jack-table entry for the given NID
  */
-struct hda_jack_tbl *
+static struct hda_jack_tbl *
 snd_hda_jack_tbl_new(struct hda_codec *codec, hda_nid_t nid)
 {
 	struct hda_jack_tbl *jack = snd_hda_jack_tbl_get(codec, nid);
@@ -108,21 +108,24 @@ snd_hda_jack_tbl_new(struct hda_codec *codec, hda_nid_t nid)
 	jack->tag = codec->jacktbl.used;
 	return jack;
 }
-EXPORT_SYMBOL_GPL(snd_hda_jack_tbl_new);
 
 void snd_hda_jack_tbl_clear(struct hda_codec *codec)
 {
+	struct hda_jack_tbl *jack = codec->jacktbl.list;
+	int i;
+
+	for (i = 0; i < codec->jacktbl.used; i++, jack++) {
+		struct hda_jack_callback *cb, *next;
 #ifdef CONFIG_SND_HDA_INPUT_JACK
-	/* free jack instances manually when clearing/reconfiguring */
-	if (!codec->bus->shutdown && codec->jacktbl.list) {
-		struct hda_jack_tbl *jack = codec->jacktbl.list;
-		int i;
-		for (i = 0; i < codec->jacktbl.used; i++, jack++) {
-			if (jack->jack)
-				snd_device_free(codec->bus->card, jack->jack);
+		/* free jack instances manually when clearing/reconfiguring */
+		if (!codec->bus->shutdown && jack->jack)
+			snd_device_free(codec->bus->card, jack->jack);
+#endif
+		for (cb = jack->callback; cb; cb = next) {
+			next = cb->next;
+			kfree(cb);
 		}
 	}
-#endif
 	snd_array_free(&codec->jacktbl);
 }
 
@@ -215,33 +218,49 @@ EXPORT_SYMBOL_GPL(snd_hda_jack_detect_state);
 
 /**
  * snd_hda_jack_detect_enable - enable the jack-detection
+ *
+ * In the case of error, the return value will be a pointer embedded with
+ * errno.  Check and handle the return value appropriately with standard
+ * macros such as @IS_ERR() and @PTR_ERR().
  */
-int snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid,
-					unsigned char action,
-					hda_jack_callback cb)
+struct hda_jack_callback *
+snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid,
+				    hda_jack_callback_fn func)
 {
-	struct hda_jack_tbl *jack = snd_hda_jack_tbl_new(codec, nid);
+	struct hda_jack_tbl *jack;
+	struct hda_jack_callback *callback = NULL;
+	int err;
+
+	jack = snd_hda_jack_tbl_new(codec, nid);
 	if (!jack)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
+	if (func) {
+		callback = kzalloc(sizeof(*callback), GFP_KERNEL);
+		if (!callback)
+			return ERR_PTR(-ENOMEM);
+		callback->func = func;
+		callback->tbl = jack;
+		callback->next = jack->callback;
+		jack->callback = callback;
+	}
+
 	if (jack->jack_detect)
-		return 0; /* already registered */
+		return callback; /* already registered */
 	jack->jack_detect = 1;
-	if (action)
-		jack->action = action;
-	if (cb)
-		jack->callback = cb;
 	if (codec->jackpoll_interval > 0)
-		return 0; /* No unsol if we're polling instead */
-	return snd_hda_codec_write_cache(codec, nid, 0,
+		return callback; /* No unsol if we're polling instead */
+	err = snd_hda_codec_write_cache(codec, nid, 0,
 					 AC_VERB_SET_UNSOLICITED_ENABLE,
 					 AC_USRSP_EN | jack->tag);
+	if (err < 0)
+		return ERR_PTR(err);
+	return callback;
 }
 EXPORT_SYMBOL_GPL(snd_hda_jack_detect_enable_callback);
 
-int snd_hda_jack_detect_enable(struct hda_codec *codec, hda_nid_t nid,
-			       unsigned char action)
+int snd_hda_jack_detect_enable(struct hda_codec *codec, hda_nid_t nid)
 {
-	return snd_hda_jack_detect_enable_callback(codec, nid, action, NULL);
+	return PTR_ERR_OR_ZERO(snd_hda_jack_detect_enable_callback(codec, nid, NULL));
 }
 EXPORT_SYMBOL_GPL(snd_hda_jack_detect_enable);
 
@@ -431,7 +450,7 @@ static int add_jack_kctl(struct hda_codec *codec, hda_nid_t nid,
 		return err;
 
 	if (!phantom_jack)
-		return snd_hda_jack_detect_enable(codec, nid, 0);
+		return snd_hda_jack_detect_enable(codec, nid);
 	return 0;
 }
 
@@ -498,13 +517,17 @@ EXPORT_SYMBOL_GPL(snd_hda_jack_add_kctls);
 static void call_jack_callback(struct hda_codec *codec,
 			       struct hda_jack_tbl *jack)
 {
-	if (jack->callback)
-		jack->callback(codec, jack);
+	struct hda_jack_callback *cb;
+
+	for (cb = jack->callback; cb; cb = cb->next)
+		cb->func(codec, cb);
 	if (jack->gated_jack) {
 		struct hda_jack_tbl *gated =
 			snd_hda_jack_tbl_get(codec, jack->gated_jack);
-		if (gated && gated->callback)
-			gated->callback(codec, gated);
+		if (gated) {
+			for (cb = gated->callback; cb; cb = cb->next)
+				cb->func(codec, cb);
+		}
 	}
 }
 
diff --git a/sound/pci/hda/hda_jack.h b/sound/pci/hda/hda_jack.h
index 46e1ea83ce3c..13cb375454f6 100644
--- a/sound/pci/hda/hda_jack.h
+++ b/sound/pci/hda/hda_jack.h
@@ -12,17 +12,25 @@
 #ifndef __SOUND_HDA_JACK_H
 #define __SOUND_HDA_JACK_H
 
+#include <linux/err.h>
+
 struct auto_pin_cfg;
 struct hda_jack_tbl;
+struct hda_jack_callback;
+
+typedef void (*hda_jack_callback_fn) (struct hda_codec *, struct hda_jack_callback *);
 
-typedef void (*hda_jack_callback) (struct hda_codec *, struct hda_jack_tbl *);
+struct hda_jack_callback {
+	struct hda_jack_tbl *tbl;
+	hda_jack_callback_fn func;
+	unsigned int private_data;	/* arbitrary data */
+	struct hda_jack_callback *next;
+};
 
 struct hda_jack_tbl {
 	hda_nid_t nid;
-	unsigned char action;		/* event action (0 = none) */
 	unsigned char tag;		/* unsol event tag */
-	unsigned int private_data;	/* arbitrary data */
-	hda_jack_callback callback;
+	struct hda_jack_callback *callback;
 	/* jack-detection stuff */
 	unsigned int pin_sense;		/* cached pin-sense value */
 	unsigned int jack_detect:1;	/* capable of jack-detection? */
@@ -43,34 +51,14 @@ snd_hda_jack_tbl_get(struct hda_codec *codec, hda_nid_t nid);
 struct hda_jack_tbl *
 snd_hda_jack_tbl_get_from_tag(struct hda_codec *codec, unsigned char tag);
 
-struct hda_jack_tbl *
-snd_hda_jack_tbl_new(struct hda_codec *codec, hda_nid_t nid);
 void snd_hda_jack_tbl_clear(struct hda_codec *codec);
 
-/**
- * snd_hda_jack_get_action - get jack-tbl entry for the tag
- *
- * Call this from the unsol event handler to get the assigned action for the
- * event.  This will mark the dirty flag for the later reporting, too.
- */
-static inline unsigned char
-snd_hda_jack_get_action(struct hda_codec *codec, unsigned int tag)
-{
-	struct hda_jack_tbl *jack = snd_hda_jack_tbl_get_from_tag(codec, tag);
-	if (jack) {
-		jack->jack_dirty = 1;
-		return jack->action;
-	}
-	return 0;
-}
-
 void snd_hda_jack_set_dirty_all(struct hda_codec *codec);
 
-int snd_hda_jack_detect_enable(struct hda_codec *codec, hda_nid_t nid,
-			       unsigned char action);
-int snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid,
-					unsigned char action,
-					hda_jack_callback cb);
+int snd_hda_jack_detect_enable(struct hda_codec *codec, hda_nid_t nid);
+struct hda_jack_callback *
+snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid,
+				    hda_jack_callback_fn cb);
 
 int snd_hda_jack_set_gating_jack(struct hda_codec *codec, hda_nid_t gated_nid,
 				 hda_nid_t gating_nid);
diff --git a/sound/pci/hda/hda_local.h b/sound/pci/hda/hda_local.h
index 364bb413e02a..7eb44e78e141 100644
--- a/sound/pci/hda/hda_local.h
+++ b/sound/pci/hda/hda_local.h
@@ -371,12 +371,6 @@ void snd_print_pcm_bits(int pcm, char *buf, int buflen);
 /*
  * Misc
  */
-int snd_hda_check_board_config(struct hda_codec *codec, int num_configs,
-			       const char * const *modelnames,
-			       const struct snd_pci_quirk *pci_list);
-int snd_hda_check_board_codec_sid_config(struct hda_codec *codec,
-                               int num_configs, const char * const *models,
-                               const struct snd_pci_quirk *tbl);
 int snd_hda_add_new_ctls(struct hda_codec *codec,
 			 const struct snd_kcontrol_new *knew);
 
@@ -609,6 +603,14 @@ int snd_hda_override_amp_caps(struct hda_codec *codec, hda_nid_t nid, int dir,
 u32 snd_hda_query_pin_caps(struct hda_codec *codec, hda_nid_t nid);
 int snd_hda_override_pin_caps(struct hda_codec *codec, hda_nid_t nid,
 			      unsigned int caps);
+bool snd_hda_check_amp_caps(struct hda_codec *codec, hda_nid_t nid,
+			   int dir, unsigned int bits);
+
+#define nid_has_mute(codec, nid, dir) \
+	snd_hda_check_amp_caps(codec, nid, dir, (AC_AMPCAP_MUTE | AC_AMPCAP_MIN_MUTE))
+#define nid_has_volume(codec, nid, dir) \
+	snd_hda_check_amp_caps(codec, nid, dir, AC_AMPCAP_NUM_STEPS)
+
 
 /* flags for hda_nid_item */
 #define HDA_NID_ITEM_AMP	(1<<0)
diff --git a/sound/pci/hda/hda_sysfs.c b/sound/pci/hda/hda_sysfs.c
index e2079090ca6f..9b49f156a12e 100644
--- a/sound/pci/hda/hda_sysfs.c
+++ b/sound/pci/hda/hda_sysfs.c
@@ -514,7 +514,7 @@ enum {
 
 static inline int strmatch(const char *a, const char *b)
 {
-	return strnicmp(a, b, strlen(b)) == 0;
+	return strncasecmp(a, b, strlen(b)) == 0;
 }
 
 /* parse the contents after the line "[codec]"
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 5d8455e2dacd..4f7ffa8c4a0d 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -3224,8 +3224,14 @@ static void ca0132_unsol_hp_delayed(struct work_struct *work)
 {
 	struct ca0132_spec *spec = container_of(
 		to_delayed_work(work), struct ca0132_spec, unsol_hp_work);
+	struct hda_jack_tbl *jack;
+
 	ca0132_select_out(spec->codec);
-	snd_hda_jack_report_sync(spec->codec);
+	jack = snd_hda_jack_tbl_get(spec->codec, UNSOL_TAG_HP);
+	if (jack) {
+		jack->block_report = 0;
+		snd_hda_jack_report_sync(spec->codec);
+	}
 }
 
 static void ca0132_set_dmic(struct hda_codec *codec, int enable);
@@ -4114,12 +4120,6 @@ static void init_input(struct hda_codec *codec, hda_nid_t pin, hda_nid_t adc)
 	}
 }
 
-static void ca0132_init_unsol(struct hda_codec *codec)
-{
-	snd_hda_jack_detect_enable(codec, UNSOL_TAG_HP, UNSOL_TAG_HP);
-	snd_hda_jack_detect_enable(codec, UNSOL_TAG_AMIC1, UNSOL_TAG_AMIC1);
-}
-
 static void refresh_amp_caps(struct hda_codec *codec, hda_nid_t nid, int dir)
 {
 	unsigned int caps;
@@ -4390,7 +4390,8 @@ static void ca0132_download_dsp(struct hda_codec *codec)
 		ca0132_set_dsp_msr(codec, true);
 }
 
-static void ca0132_process_dsp_response(struct hda_codec *codec)
+static void ca0132_process_dsp_response(struct hda_codec *codec,
+					struct hda_jack_callback *callback)
 {
 	struct ca0132_spec *spec = codec->spec;
 
@@ -4403,36 +4404,31 @@ static void ca0132_process_dsp_response(struct hda_codec *codec)
 	dspio_clear_response_queue(codec);
 }
 
-static void ca0132_unsol_event(struct hda_codec *codec, unsigned int res)
+static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
 {
 	struct ca0132_spec *spec = codec->spec;
 
-	if (((res >> AC_UNSOL_RES_TAG_SHIFT) & 0x3f) == UNSOL_TAG_DSP) {
-		ca0132_process_dsp_response(codec);
-	} else {
-		res = snd_hda_jack_get_action(codec,
-				(res >> AC_UNSOL_RES_TAG_SHIFT) & 0x3f);
-
-		codec_dbg(codec, "snd_hda_jack_get_action: 0x%x\n", res);
-
-		switch (res) {
-		case UNSOL_TAG_HP:
-			/* Delay enabling the HP amp, to let the mic-detection
-			 * state machine run.
-			 */
-			cancel_delayed_work_sync(&spec->unsol_hp_work);
-			queue_delayed_work(codec->bus->workq,
-					   &spec->unsol_hp_work,
-					   msecs_to_jiffies(500));
-			break;
-		case UNSOL_TAG_AMIC1:
-			ca0132_select_mic(codec);
-			snd_hda_jack_report_sync(codec);
-			break;
-		default:
-			break;
-		}
-	}
+	/* Delay enabling the HP amp, to let the mic-detection
+	 * state machine run.
+	 */
+	cancel_delayed_work_sync(&spec->unsol_hp_work);
+	queue_delayed_work(codec->bus->workq, &spec->unsol_hp_work,
+			   msecs_to_jiffies(500));
+	cb->tbl->block_report = 1;
+}
+
+static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
+{
+	ca0132_select_mic(codec);
+}
+
+static void ca0132_init_unsol(struct hda_codec *codec)
+{
+	snd_hda_jack_detect_enable_callback(codec, UNSOL_TAG_HP, hp_callback);
+	snd_hda_jack_detect_enable_callback(codec, UNSOL_TAG_AMIC1,
+					    amic_callback);
+	snd_hda_jack_detect_enable_callback(codec, UNSOL_TAG_DSP,
+					    ca0132_process_dsp_response);
 }
 
 /*
@@ -4443,8 +4439,6 @@ static void ca0132_unsol_event(struct hda_codec *codec, unsigned int res)
 static struct hda_verb ca0132_base_init_verbs[] = {
 	/*enable ct extension*/
 	{0x15, VENDOR_CHIPIO_CT_EXTENSIONS_ENABLE, 0x1},
-	/*enable DSP node unsol, needed for DSP download*/
-	{0x16, AC_VERB_SET_UNSOLICITED_ENABLE, AC_USRSP_EN | UNSOL_TAG_DSP},
 	{}
 };
 
@@ -4561,6 +4555,8 @@ static int ca0132_init(struct hda_codec *codec)
 
 	snd_hda_power_up(codec);
 
+	ca0132_init_unsol(codec);
+
 	ca0132_init_params(codec);
 	ca0132_init_flags(codec);
 	snd_hda_sequence_write(codec, spec->base_init_verbs);
@@ -4583,8 +4579,6 @@ static int ca0132_init(struct hda_codec *codec)
 	for (i = 0; i < spec->num_init_verbs; i++)
 		snd_hda_sequence_write(codec, spec->init_verbs[i]);
 
-	ca0132_init_unsol(codec);
-
 	ca0132_select_out(codec);
 	ca0132_select_mic(codec);
 
@@ -4612,7 +4606,7 @@ static struct hda_codec_ops ca0132_patch_ops = {
 	.build_pcms = ca0132_build_pcms,
 	.init = ca0132_init,
 	.free = ca0132_free,
-	.unsol_event = ca0132_unsol_event,
+	.unsol_event = snd_hda_jack_unsol_event,
 };
 
 static void ca0132_config(struct hda_codec *codec)
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index 3db724eaa53c..1589c9bcce3e 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -135,8 +135,6 @@ enum {
 #define CS421X_IDX_DAC_CFG	0x03
 #define CS421X_IDX_SPK_CTL	0x04
 
-#define SPDIF_EVENT		0x04
-
 /* Cirrus Logic CS4213 is like CS4210 but does not have SPDIF input/output */
 #define CS4213_VENDOR_NID	0x09
 
@@ -984,7 +982,7 @@ static void cs4210_pinmux_init(struct hda_codec *codec)
 }
 
 static void cs4210_spdif_automute(struct hda_codec *codec,
-				  struct hda_jack_tbl *tbl)
+				  struct hda_jack_callback *tbl)
 {
 	struct cs_spec *spec = codec->spec;
 	bool spdif_present = false;
@@ -1019,7 +1017,6 @@ static void parse_cs421x_digital(struct hda_codec *codec)
 		if (get_wcaps(codec, nid) & AC_WCAP_UNSOL_CAP) {
 			spec->spdif_detect = 1;
 			snd_hda_jack_detect_enable_callback(codec, nid,
-							    SPDIF_EVENT,
 							    cs4210_spdif_automute);
 		}
 	}
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 47ccb8f44adb..71e4bad06345 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -26,7 +26,6 @@
 #include <linux/module.h>
 #include <sound/core.h>
 #include <sound/jack.h>
-#include <sound/tlv.h>
 
 #include "hda_codec.h"
 #include "hda_local.h"
@@ -394,7 +393,8 @@ static void olpc_xo_update_mic_pins(struct hda_codec *codec)
 }
 
 /* mic_autoswitch hook */
-static void olpc_xo_automic(struct hda_codec *codec, struct hda_jack_tbl *jack)
+static void olpc_xo_automic(struct hda_codec *codec,
+			    struct hda_jack_callback *jack)
 {
 	struct conexant_spec *spec = codec->spec;
 	int saved_cached_write = codec->cached_write;
@@ -752,6 +752,7 @@ static const struct hda_model_fixup cxt5051_fixup_models[] = {
 static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x1025, 0x0543, "Acer Aspire One 522", CXT_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC),
+	SND_PCI_QUIRK(0x1025, 0x054f, "Acer Aspire 4830T", CXT_FIXUP_ASPIRE_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
 	SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
@@ -787,6 +788,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = {
  */
 static void add_cx5051_fake_mutes(struct hda_codec *codec)
 {
+	struct conexant_spec *spec = codec->spec;
 	static hda_nid_t out_nids[] = {
 		0x10, 0x11, 0
 	};
@@ -796,6 +798,7 @@ static void add_cx5051_fake_mutes(struct hda_codec *codec)
 		snd_hda_override_amp_caps(codec, *p, HDA_OUTPUT,
 					  AC_AMPCAP_MIN_MUTE |
 					  query_amp_caps(codec, *p, HDA_OUTPUT));
+	spec->gen.dac_min_mute = true;
 }
 
 static int patch_conexant_auto(struct hda_codec *codec)
@@ -868,11 +871,6 @@ static int patch_conexant_auto(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (codec->vendor_id == 0x14f15051) {
-		/* minimum value is actually mute */
-		spec->gen.vmaster_tlv[3] |= TLV_DB_SCALE_MUTE;
-	}
-
 	codec->patch_ops = cx_auto_patch_ops;
 
 	/* Some laptops with Conexant chips show stalls in S3 resume,
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 99d7d7fecaad..39862e98551c 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1163,17 +1163,23 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec,
 
 static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll);
 
-static void jack_callback(struct hda_codec *codec, struct hda_jack_tbl *jack)
+static void check_presence_and_report(struct hda_codec *codec, hda_nid_t nid)
 {
 	struct hdmi_spec *spec = codec->spec;
-	int pin_idx = pin_nid_to_pin_index(codec, jack->nid);
+	int pin_idx = pin_nid_to_pin_index(codec, nid);
+
 	if (pin_idx < 0)
 		return;
-
 	if (hdmi_present_sense(get_pin(spec, pin_idx), 1))
 		snd_hda_jack_report_sync(codec);
 }
 
+static void jack_callback(struct hda_codec *codec,
+			  struct hda_jack_callback *jack)
+{
+	check_presence_and_report(codec, jack->tbl->nid);
+}
+
 static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res)
 {
 	int tag = res >> AC_UNSOL_RES_TAG_SHIFT;
@@ -1190,7 +1196,7 @@ static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res)
 		codec->addr, jack->nid, dev_entry, !!(res & AC_UNSOL_RES_IA),
 		!!(res & AC_UNSOL_RES_PD), !!(res & AC_UNSOL_RES_ELDV));
 
-	jack_callback(codec, jack);
+	check_presence_and_report(codec, jack->nid);
 }
 
 static void hdmi_non_intrinsic_event(struct hda_codec *codec, unsigned int res)
@@ -2165,7 +2171,7 @@ static int generic_hdmi_init(struct hda_codec *codec)
 		hda_nid_t pin_nid = per_pin->pin_nid;
 
 		hdmi_init_pin(codec, pin_nid);
-		snd_hda_jack_detect_enable_callback(codec, pin_nid, pin_nid,
+		snd_hda_jack_detect_enable_callback(codec, pin_nid,
 			codec->jackpoll_interval > 0 ? jack_callback : NULL);
 	}
 	return 0;
@@ -2428,7 +2434,7 @@ static int simple_playback_init(struct hda_codec *codec)
 	if (get_wcaps(codec, pin) & AC_WCAP_OUT_AMP)
 		snd_hda_codec_write(codec, pin, 0, AC_VERB_SET_AMP_GAIN_MUTE,
 				    AMP_OUT_UNMUTE);
-	snd_hda_jack_detect_enable(codec, pin, pin);
+	snd_hda_jack_detect_enable(codec, pin);
 	return 0;
 }
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 1ba22fb527c2..bc86c36b4bfa 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -40,9 +40,6 @@
 /* keep halting ALC5505 DSP, for power saving */
 #define HALT_REALTEK_ALC5505
 
-/* unsol event tags */
-#define ALC_DCVOL_EVENT		0x08
-
 /* for GPIO Poll */
 #define GPIO_MASK	0x03
 
@@ -93,11 +90,6 @@ struct alc_spec {
 	struct alc_customize_define cdefine;
 	unsigned int parse_flags; /* flag for snd_hda_parse_pin_defcfg() */
 
-	/* inverted dmic fix */
-	unsigned int inv_dmic_fixup:1; /* has inverted digital-mic workaround */
-	unsigned int inv_dmic_muted:1; /* R-ch of inv d-mic is muted? */
-	hda_nid_t inv_dmic_pin;
-
 	/* mute LED for HP laptops, see alc269_fixup_mic_mute_hook() */
 	int mute_led_polarity;
 	hda_nid_t mute_led_nid;
@@ -129,6 +121,83 @@ struct alc_spec {
 };
 
 /*
+ * COEF access helper functions
+ */
+
+static int alc_read_coefex_idx(struct hda_codec *codec, hda_nid_t nid,
+			       unsigned int coef_idx)
+{
+	unsigned int val;
+
+	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_COEF_INDEX, coef_idx);
+	val = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_PROC_COEF, 0);
+	return val;
+}
+
+#define alc_read_coef_idx(codec, coef_idx) \
+	alc_read_coefex_idx(codec, 0x20, coef_idx)
+
+static void alc_write_coefex_idx(struct hda_codec *codec, hda_nid_t nid,
+				 unsigned int coef_idx, unsigned int coef_val)
+{
+	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_COEF_INDEX, coef_idx);
+	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_PROC_COEF, coef_val);
+}
+
+#define alc_write_coef_idx(codec, coef_idx, coef_val) \
+	alc_write_coefex_idx(codec, 0x20, coef_idx, coef_val)
+
+static void alc_update_coefex_idx(struct hda_codec *codec, hda_nid_t nid,
+				  unsigned int coef_idx, unsigned int mask,
+				  unsigned int bits_set)
+{
+	unsigned int val = alc_read_coefex_idx(codec, nid, coef_idx);
+
+	if (val != -1)
+		alc_write_coefex_idx(codec, nid, coef_idx,
+				     (val & ~mask) | bits_set);
+}
+
+#define alc_update_coef_idx(codec, coef_idx, mask, bits_set)	\
+	alc_update_coefex_idx(codec, 0x20, coef_idx, mask, bits_set)
+
+/* a special bypass for COEF 0; read the cached value at the second time */
+static unsigned int alc_get_coef0(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (!spec->coef0)
+		spec->coef0 = alc_read_coef_idx(codec, 0);
+	return spec->coef0;
+}
+
+/* coef writes/updates batch */
+struct coef_fw {
+	unsigned char nid;
+	unsigned char idx;
+	unsigned short mask;
+	unsigned short val;
+};
+
+#define UPDATE_COEFEX(_nid, _idx, _mask, _val) \
+	{ .nid = (_nid), .idx = (_idx), .mask = (_mask), .val = (_val) }
+#define WRITE_COEFEX(_nid, _idx, _val) UPDATE_COEFEX(_nid, _idx, -1, _val)
+#define WRITE_COEF(_idx, _val) WRITE_COEFEX(0x20, _idx, _val)
+#define UPDATE_COEF(_idx, _mask, _val) UPDATE_COEFEX(0x20, _idx, _mask, _val)
+
+static void alc_process_coef_fw(struct hda_codec *codec,
+				const struct coef_fw *fw)
+{
+	for (; fw->nid; fw++) {
+		if (fw->mask == (unsigned short)-1)
+			alc_write_coefex_idx(codec, fw->nid, fw->idx, fw->val);
+		else
+			alc_update_coefex_idx(codec, fw->nid, fw->idx,
+					      fw->mask, fw->val);
+	}
+}
+
+/*
  * Append the given mixer and verb elements for the later use
  * The mixer array is referred in build_controls(), and init_verbs are
  * called in init().
@@ -173,20 +242,10 @@ static const struct hda_verb alc_gpio3_init_verbs[] = {
 static void alc_fix_pll(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
-	unsigned int val;
 
-	if (!spec->pll_nid)
-		return;
-	snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_COEF_INDEX,
-			    spec->pll_coef_idx);
-	val = snd_hda_codec_read(codec, spec->pll_nid, 0,
-				 AC_VERB_GET_PROC_COEF, 0);
-	if (val == -1)
-		return;
-	snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_COEF_INDEX,
-			    spec->pll_coef_idx);
-	snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_PROC_COEF,
-			    val & ~(1 << spec->pll_coef_bit));
+	if (spec->pll_nid)
+		alc_update_coefex_idx(codec, spec->pll_nid, spec->pll_coef_idx,
+				      1 << spec->pll_coef_bit, 0);
 }
 
 static void alc_fix_pll_init(struct hda_codec *codec, hda_nid_t nid,
@@ -200,7 +259,8 @@ static void alc_fix_pll_init(struct hda_codec *codec, hda_nid_t nid,
 }
 
 /* update the master volume per volume-knob's unsol event */
-static void alc_update_knob_master(struct hda_codec *codec, struct hda_jack_tbl *jack)
+static void alc_update_knob_master(struct hda_codec *codec,
+				   struct hda_jack_callback *jack)
 {
 	unsigned int val;
 	struct snd_kcontrol *kctl;
@@ -212,7 +272,7 @@ static void alc_update_knob_master(struct hda_codec *codec, struct hda_jack_tbl
 	uctl = kzalloc(sizeof(*uctl), GFP_KERNEL);
 	if (!uctl)
 		return;
-	val = snd_hda_codec_read(codec, jack->nid, 0,
+	val = snd_hda_codec_read(codec, jack->tbl->nid, 0,
 				 AC_VERB_GET_VOLUME_KNOB_CONTROL, 0);
 	val &= HDA_AMP_VOLMASK;
 	uctl->value.integer.value[0] = val;
@@ -231,30 +291,18 @@ static void alc880_unsol_event(struct hda_codec *codec, unsigned int res)
 /* additional initialization for ALC888 variants */
 static void alc888_coef_init(struct hda_codec *codec)
 {
-	unsigned int tmp;
-
-	snd_hda_codec_write(codec, 0x20, 0, AC_VERB_SET_COEF_INDEX, 0);
-	tmp = snd_hda_codec_read(codec, 0x20, 0, AC_VERB_GET_PROC_COEF, 0);
-	snd_hda_codec_write(codec, 0x20, 0, AC_VERB_SET_COEF_INDEX, 7);
-	if ((tmp & 0xf0) == 0x20)
+	if (alc_get_coef0(codec) == 0x20)
 		/* alc888S-VC */
-		snd_hda_codec_read(codec, 0x20, 0,
-				   AC_VERB_SET_PROC_COEF, 0x830);
+		alc_write_coef_idx(codec, 7, 0x830);
 	 else
 		 /* alc888-VB */
-		 snd_hda_codec_read(codec, 0x20, 0,
-				    AC_VERB_SET_PROC_COEF, 0x3030);
+		alc_write_coef_idx(codec, 7, 0x3030);
 }
 
 /* additional initialization for ALC889 variants */
 static void alc889_coef_init(struct hda_codec *codec)
 {
-	unsigned int tmp;
-
-	snd_hda_codec_write(codec, 0x20, 0, AC_VERB_SET_COEF_INDEX, 7);
-	tmp = snd_hda_codec_read(codec, 0x20, 0, AC_VERB_GET_PROC_COEF, 0);
-	snd_hda_codec_write(codec, 0x20, 0, AC_VERB_SET_COEF_INDEX, 7);
-	snd_hda_codec_write(codec, 0x20, 0, AC_VERB_SET_PROC_COEF, tmp|0x2010);
+	alc_update_coef_idx(codec, 7, 0, 0x2010);
 }
 
 /* turn on/off EAPD control (only if available) */
@@ -295,8 +343,6 @@ static void alc_eapd_shutup(struct hda_codec *codec)
 /* generic EAPD initialization */
 static void alc_auto_init_amp(struct hda_codec *codec, int type)
 {
-	unsigned int tmp;
-
 	alc_auto_setup_eapd(codec, true);
 	switch (type) {
 	case ALC_INIT_GPIO1:
@@ -311,15 +357,7 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type)
 	case ALC_INIT_DEFAULT:
 		switch (codec->vendor_id) {
 		case 0x10ec0260:
-			snd_hda_codec_write(codec, 0x1a, 0,
-					    AC_VERB_SET_COEF_INDEX, 7);
-			tmp = snd_hda_codec_read(codec, 0x1a, 0,
-						 AC_VERB_GET_PROC_COEF, 0);
-			snd_hda_codec_write(codec, 0x1a, 0,
-					    AC_VERB_SET_COEF_INDEX, 7);
-			snd_hda_codec_write(codec, 0x1a, 0,
-					    AC_VERB_SET_PROC_COEF,
-					    tmp | 0x2010);
+			alc_update_coefex_idx(codec, 0x1a, 7, 0, 0x2010);
 			break;
 		case 0x10ec0262:
 		case 0x10ec0880:
@@ -337,15 +375,7 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type)
 #if 0 /* XXX: This may cause the silent output on speaker on some machines */
 		case 0x10ec0267:
 		case 0x10ec0268:
-			snd_hda_codec_write(codec, 0x20, 0,
-					    AC_VERB_SET_COEF_INDEX, 7);
-			tmp = snd_hda_codec_read(codec, 0x20, 0,
-						 AC_VERB_GET_PROC_COEF, 0);
-			snd_hda_codec_write(codec, 0x20, 0,
-					    AC_VERB_SET_COEF_INDEX, 7);
-			snd_hda_codec_write(codec, 0x20, 0,
-					    AC_VERB_SET_PROC_COEF,
-					    tmp | 0x3000);
+			alc_update_coef_idx(codec, 7, 0, 0x3000);
 			break;
 #endif /* XXX */
 		}
@@ -588,190 +618,14 @@ static void alc_ssid_check(struct hda_codec *codec, const hda_nid_t *ports)
 }
 
 /*
- * COEF access helper functions
- */
-
-static int alc_read_coefex_idx(struct hda_codec *codec,
-					hda_nid_t nid,
-					unsigned int coef_idx)
-{
-	unsigned int val;
-	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_COEF_INDEX,
-		    		coef_idx);
-	val = snd_hda_codec_read(codec, nid, 0,
-			 	AC_VERB_GET_PROC_COEF, 0);
-	return val;
-}
-
-#define alc_read_coef_idx(codec, coef_idx) \
-	alc_read_coefex_idx(codec, 0x20, coef_idx)
-
-static void alc_write_coefex_idx(struct hda_codec *codec, hda_nid_t nid,
-							unsigned int coef_idx,
-							unsigned int coef_val)
-{
-	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_COEF_INDEX,
-			    coef_idx);
-	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_PROC_COEF,
-			    coef_val);
-}
-
-#define alc_write_coef_idx(codec, coef_idx, coef_val) \
-	alc_write_coefex_idx(codec, 0x20, coef_idx, coef_val)
-
-/* a special bypass for COEF 0; read the cached value at the second time */
-static unsigned int alc_get_coef0(struct hda_codec *codec)
-{
-	struct alc_spec *spec = codec->spec;
-	if (!spec->coef0)
-		spec->coef0 = alc_read_coef_idx(codec, 0);
-	return spec->coef0;
-}
-
-/*
  */
 
-static hda_nid_t get_adc_nid(struct hda_codec *codec, int adc_idx, int imux_idx)
-{
-	struct hda_gen_spec *spec = codec->spec;
-	if (spec->dyn_adc_switch)
-		adc_idx = spec->dyn_adc_idx[imux_idx];
-	return spec->adc_nids[adc_idx];
-}
-
-static void alc_inv_dmic_sync_adc(struct hda_codec *codec, int adc_idx)
-{
-	struct alc_spec *spec = codec->spec;
-	struct hda_input_mux *imux = &spec->gen.input_mux;
-	struct nid_path *path;
-	hda_nid_t nid;
-	int i, dir, parm;
-	unsigned int val;
-
-	for (i = 0; i < imux->num_items; i++) {
-		if (spec->gen.imux_pins[i] == spec->inv_dmic_pin)
-			break;
-	}
-	if (i >= imux->num_items)
-		return;
-
-	path = snd_hda_get_nid_path(codec, spec->inv_dmic_pin,
-				    get_adc_nid(codec, adc_idx, i));
-	val = path->ctls[NID_PATH_MUTE_CTL];
-	if (!val)
-		return;
-	nid = get_amp_nid_(val);
-	dir = get_amp_direction_(val);
-	parm = AC_AMP_SET_RIGHT |
-		(dir == HDA_OUTPUT ? AC_AMP_SET_OUTPUT : AC_AMP_SET_INPUT);
-
-	/* flush all cached amps at first */
-	snd_hda_codec_flush_cache(codec);
-
-	/* we care only right channel */
-	val = snd_hda_codec_amp_read(codec, nid, 1, dir, 0);
-	if (val & 0x80) /* if already muted, we don't need to touch */
-		return;
-	val |= 0x80;
-	snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_AMP_GAIN_MUTE,
-			    parm | val);
-}
-
-/*
- * Inverted digital-mic handling
- *
- * First off, it's a bit tricky.  The "Inverted Internal Mic Capture Switch"
- * gives the additional mute only to the right channel of the digital mic
- * capture stream.  This is a workaround for avoiding the almost silence
- * by summing the stereo stream from some (known to be ForteMedia)
- * digital mic unit.
- *
- * The logic is to call alc_inv_dmic_sync() after each action (possibly)
- * modifying ADC amp.  When the mute flag is set, it mutes the R-channel
- * without caching so that the cache can still keep the original value.
- * The cached value is then restored when the flag is set off or any other
- * than d-mic is used as the current input source.
- */
-static void alc_inv_dmic_sync(struct hda_codec *codec, bool force)
-{
-	struct alc_spec *spec = codec->spec;
-	int src, nums;
-
-	if (!spec->inv_dmic_fixup)
-		return;
-	if (!spec->inv_dmic_muted && !force)
-		return;
-	nums = spec->gen.dyn_adc_switch ? 1 : spec->gen.num_adc_nids;
-	for (src = 0; src < nums; src++) {
-		bool dmic_fixup = false;
-
-		if (spec->inv_dmic_muted &&
-		    spec->gen.imux_pins[spec->gen.cur_mux[src]] == spec->inv_dmic_pin)
-			dmic_fixup = true;
-		if (!dmic_fixup && !force)
-			continue;
-		alc_inv_dmic_sync_adc(codec, src);
-	}
-}
-
-static void alc_inv_dmic_hook(struct hda_codec *codec,
-			      struct snd_kcontrol *kcontrol,
-			      struct snd_ctl_elem_value *ucontrol)
-{
-	alc_inv_dmic_sync(codec, false);
-}
-
-static int alc_inv_dmic_sw_get(struct snd_kcontrol *kcontrol,
-			       struct snd_ctl_elem_value *ucontrol)
-{
-	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
-	struct alc_spec *spec = codec->spec;
-
-	ucontrol->value.integer.value[0] = !spec->inv_dmic_muted;
-	return 0;
-}
-
-static int alc_inv_dmic_sw_put(struct snd_kcontrol *kcontrol,
-			       struct snd_ctl_elem_value *ucontrol)
-{
-	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
-	struct alc_spec *spec = codec->spec;
-	unsigned int val = !ucontrol->value.integer.value[0];
-
-	if (val == spec->inv_dmic_muted)
-		return 0;
-	spec->inv_dmic_muted = val;
-	alc_inv_dmic_sync(codec, true);
-	return 0;
-}
-
-static const struct snd_kcontrol_new alc_inv_dmic_sw = {
-	.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
-	.name = "Inverted Internal Mic Capture Switch",
-	.info = snd_ctl_boolean_mono_info,
-	.get = alc_inv_dmic_sw_get,
-	.put = alc_inv_dmic_sw_put,
-};
-
-static int alc_add_inv_dmic_mixer(struct hda_codec *codec, hda_nid_t nid)
+static void alc_fixup_inv_dmic(struct hda_codec *codec,
+			       const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
 
-	if (!snd_hda_gen_add_kctl(&spec->gen, NULL, &alc_inv_dmic_sw))
-		return -ENOMEM;
-	spec->inv_dmic_fixup = 1;
-	spec->inv_dmic_muted = 0;
-	spec->inv_dmic_pin = nid;
-	spec->gen.cap_sync_hook = alc_inv_dmic_hook;
-	return 0;
-}
-
-/* typically the digital mic is put at node 0x12 */
-static void alc_fixup_inv_dmic_0x12(struct hda_codec *codec,
-				    const struct hda_fixup *fix, int action)
-{
-	if (action == HDA_FIXUP_ACT_PROBE)
-		alc_add_inv_dmic_mixer(codec, 0x12);
+	spec->gen.inv_dmic_split = 1;
 }
 
 
@@ -880,7 +734,6 @@ static int alc_resume(struct hda_codec *codec)
 	codec->patch_ops.init(codec);
 	snd_hda_codec_resume_amp(codec);
 	snd_hda_codec_resume_cache(codec);
-	alc_inv_dmic_sync(codec, true);
 	hda_call_check_power_status(codec, 0x01);
 	return 0;
 }
@@ -1134,7 +987,8 @@ static void alc880_fixup_vol_knob(struct hda_codec *codec,
 				  const struct hda_fixup *fix, int action)
 {
 	if (action == HDA_FIXUP_ACT_PROBE)
-		snd_hda_jack_detect_enable_callback(codec, 0x21, ALC_DCVOL_EVENT, alc_update_knob_master);
+		snd_hda_jack_detect_enable_callback(codec, 0x21,
+						    alc_update_knob_master);
 }
 
 static const struct hda_fixup alc880_fixups[] = {
@@ -1597,7 +1451,7 @@ static void alc260_fixup_gpio1_toggle(struct hda_codec *codec,
 		spec->gen.detect_hp = 1;
 		spec->gen.automute_speaker = 1;
 		spec->gen.autocfg.hp_pins[0] = 0x0f; /* copy it for automute */
-		snd_hda_jack_detect_enable_callback(codec, 0x0f, HDA_GEN_HP_EVENT,
+		snd_hda_jack_detect_enable_callback(codec, 0x0f,
 						    snd_hda_gen_hp_automute);
 		snd_hda_add_verbs(codec, alc_gpio1_init_verbs);
 	}
@@ -2222,7 +2076,7 @@ static const struct hda_fixup alc882_fixups[] = {
 	},
 	[ALC882_FIXUP_INV_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
-		.v.func = alc_fixup_inv_dmic_0x12,
+		.v.func = alc_fixup_inv_dmic,
 	},
 	[ALC882_FIXUP_NO_PRIMARY_HP] = {
 		.type = HDA_FIXUP_FUNC,
@@ -2473,7 +2327,7 @@ static const struct hda_fixup alc262_fixups[] = {
 	},
 	[ALC262_FIXUP_INV_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
-		.v.func = alc_fixup_inv_dmic_0x12,
+		.v.func = alc_fixup_inv_dmic,
 	},
 	[ALC262_FIXUP_INTEL_BAYLEYBAY] = {
 		.type = HDA_FIXUP_FUNC,
@@ -2517,13 +2371,7 @@ static int patch_alc262(struct hda_codec *codec)
 	/* pshou 07/11/05  set a zero PCM sample to DAC when FIFO is
 	 * under-run
 	 */
-	{
-	int tmp;
-	snd_hda_codec_write(codec, 0x1a, 0, AC_VERB_SET_COEF_INDEX, 7);
-	tmp = snd_hda_codec_read(codec, 0x20, 0, AC_VERB_GET_PROC_COEF, 0);
-	snd_hda_codec_write(codec, 0x1a, 0, AC_VERB_SET_COEF_INDEX, 7);
-	snd_hda_codec_write(codec, 0x1a, 0, AC_VERB_SET_PROC_COEF, tmp | 0x80);
-	}
+	alc_update_coefex_idx(codec, 0x1a, 7, 0, 0x80);
 #endif
 	alc_fix_pll_init(codec, 0x20, 0x0a, 10);
 
@@ -2592,7 +2440,7 @@ enum {
 static const struct hda_fixup alc268_fixups[] = {
 	[ALC268_FIXUP_INV_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
-		.v.func = alc_fixup_inv_dmic_0x12,
+		.v.func = alc_fixup_inv_dmic,
 	},
 	[ALC268_FIXUP_HP_EAPD] = {
 		.type = HDA_FIXUP_VERBS,
@@ -2809,14 +2657,7 @@ static void alc286_shutup(struct hda_codec *codec)
 
 static void alc269vb_toggle_power_output(struct hda_codec *codec, int power_up)
 {
-	int val = alc_read_coef_idx(codec, 0x04);
-	if (val == -1)
-		return;
-	if (power_up)
-		val |= 1 << 11;
-	else
-		val &= ~(1 << 11);
-	alc_write_coef_idx(codec, 0x04, val);
+	alc_update_coef_idx(codec, 0x04, 1 << 11, power_up ? (1 << 11) : 0);
 }
 
 static void alc269_shutup(struct hda_codec *codec)
@@ -2832,79 +2673,42 @@ static void alc269_shutup(struct hda_codec *codec)
 	snd_hda_shutup_pins(codec);
 }
 
+static struct coef_fw alc282_coefs[] = {
+	WRITE_COEF(0x03, 0x0002), /* Power Down Control */
+	WRITE_COEF(0x05, 0x0700), /* FIFO and filter clock */
+	WRITE_COEF(0x07, 0x0200), /* DMIC control */
+	UPDATE_COEF(0x06, 0x00f0, 0), /* Analog clock */
+	UPDATE_COEF(0x08, 0xfffc, 0x0c2c), /* JD */
+	WRITE_COEF(0x0a, 0xcccc), /* JD offset1 */
+	WRITE_COEF(0x0b, 0xcccc), /* JD offset2 */
+	WRITE_COEF(0x0e, 0x6e00), /* LDO1/2/3, DAC/ADC */
+	UPDATE_COEF(0x0f, 0xf800, 0x1000), /* JD */
+	UPDATE_COEF(0x10, 0xfc00, 0x0c00), /* Capless */
+	WRITE_COEF(0x6f, 0x0), /* Class D test 4 */
+	UPDATE_COEF(0x0c, 0xfe00, 0), /* IO power down directly */
+	WRITE_COEF(0x34, 0xa0c0), /* ANC */
+	UPDATE_COEF(0x16, 0x0008, 0), /* AGC MUX */
+	UPDATE_COEF(0x1d, 0x00e0, 0), /* DAC simple content protection */
+	UPDATE_COEF(0x1f, 0x00e0, 0), /* ADC simple content protection */
+	WRITE_COEF(0x21, 0x8804), /* DAC ADC Zero Detection */
+	WRITE_COEF(0x63, 0x2902), /* PLL */
+	WRITE_COEF(0x68, 0xa080), /* capless control 2 */
+	WRITE_COEF(0x69, 0x3400), /* capless control 3 */
+	WRITE_COEF(0x6a, 0x2f3e), /* capless control 4 */
+	WRITE_COEF(0x6b, 0x0), /* capless control 5 */
+	UPDATE_COEF(0x6d, 0x0fff, 0x0900), /* class D test 2 */
+	WRITE_COEF(0x6e, 0x110a), /* class D test 3 */
+	UPDATE_COEF(0x70, 0x00f8, 0x00d8), /* class D test 5 */
+	WRITE_COEF(0x71, 0x0014), /* class D test 6 */
+	WRITE_COEF(0x72, 0xc2ba), /* classD OCP */
+	UPDATE_COEF(0x77, 0x0f80, 0), /* classD pure DC test */
+	WRITE_COEF(0x6c, 0xfc06), /* Class D amp control */
+	{}
+};
+
 static void alc282_restore_default_value(struct hda_codec *codec)
 {
-	int val;
-
-	/* Power Down Control */
-	alc_write_coef_idx(codec, 0x03, 0x0002);
-	/* FIFO and filter clock */
-	alc_write_coef_idx(codec, 0x05, 0x0700);
-	/* DMIC control */
-	alc_write_coef_idx(codec, 0x07, 0x0200);
-	/* Analog clock */
-	val = alc_read_coef_idx(codec, 0x06);
-	alc_write_coef_idx(codec, 0x06, (val & ~0x00f0) | 0x0);
-	/* JD */
-	val = alc_read_coef_idx(codec, 0x08);
-	alc_write_coef_idx(codec, 0x08, (val & ~0xfffc) | 0x0c2c);
-	/* JD offset1 */
-	alc_write_coef_idx(codec, 0x0a, 0xcccc);
-	/* JD offset2 */
-	alc_write_coef_idx(codec, 0x0b, 0xcccc);
-	/* LDO1/2/3, DAC/ADC */
-	alc_write_coef_idx(codec, 0x0e, 0x6e00);
-	/* JD */
-	val = alc_read_coef_idx(codec, 0x0f);
-	alc_write_coef_idx(codec, 0x0f, (val & ~0xf800) | 0x1000);
-	/* Capless */
-	val = alc_read_coef_idx(codec, 0x10);
-	alc_write_coef_idx(codec, 0x10, (val & ~0xfc00) | 0x0c00);
-	/* Class D test 4 */
-	alc_write_coef_idx(codec, 0x6f, 0x0);
-	/* IO power down directly */
-	val = alc_read_coef_idx(codec, 0x0c);
-	alc_write_coef_idx(codec, 0x0c, (val & ~0xfe00) | 0x0);
-	/* ANC */
-	alc_write_coef_idx(codec, 0x34, 0xa0c0);
-	/* AGC MUX */
-	val = alc_read_coef_idx(codec, 0x16);
-	alc_write_coef_idx(codec, 0x16, (val & ~0x0008) | 0x0);
-	/* DAC simple content protection */
-	val = alc_read_coef_idx(codec, 0x1d);
-	alc_write_coef_idx(codec, 0x1d, (val & ~0x00e0) | 0x0);
-	/* ADC simple content protection */
-	val = alc_read_coef_idx(codec, 0x1f);
-	alc_write_coef_idx(codec, 0x1f, (val & ~0x00e0) | 0x0);
-	/* DAC ADC Zero Detection */
-	alc_write_coef_idx(codec, 0x21, 0x8804);
-	/* PLL */
-	alc_write_coef_idx(codec, 0x63, 0x2902);
-	/* capless control 2 */
-	alc_write_coef_idx(codec, 0x68, 0xa080);
-	/* capless control 3 */
-	alc_write_coef_idx(codec, 0x69, 0x3400);
-	/* capless control 4 */
-	alc_write_coef_idx(codec, 0x6a, 0x2f3e);
-	/* capless control 5 */
-	alc_write_coef_idx(codec, 0x6b, 0x0);
-	/* class D test 2 */
-	val = alc_read_coef_idx(codec, 0x6d);
-	alc_write_coef_idx(codec, 0x6d, (val & ~0x0fff) | 0x0900);
-	/* class D test 3 */
-	alc_write_coef_idx(codec, 0x6e, 0x110a);
-	/* class D test 5 */
-	val = alc_read_coef_idx(codec, 0x70);
-	alc_write_coef_idx(codec, 0x70, (val & ~0x00f8) | 0x00d8);
-	/* class D test 6 */
-	alc_write_coef_idx(codec, 0x71, 0x0014);
-	/* classD OCP */
-	alc_write_coef_idx(codec, 0x72, 0xc2ba);
-	/* classD pure DC test */
-	val = alc_read_coef_idx(codec, 0x77);
-	alc_write_coef_idx(codec, 0x77, (val & ~0x0f80) | 0x0);
-	/* Class D amp control */
-	alc_write_coef_idx(codec, 0x6c, 0xfc06);
+	alc_process_coef_fw(codec, alc282_coefs);
 }
 
 static void alc282_init(struct hda_codec *codec)
@@ -2980,87 +2784,45 @@ static void alc282_shutup(struct hda_codec *codec)
 	alc_write_coef_idx(codec, 0x78, coef78);
 }
 
+static struct coef_fw alc283_coefs[] = {
+	WRITE_COEF(0x03, 0x0002), /* Power Down Control */
+	WRITE_COEF(0x05, 0x0700), /* FIFO and filter clock */
+	WRITE_COEF(0x07, 0x0200), /* DMIC control */
+	UPDATE_COEF(0x06, 0x00f0, 0), /* Analog clock */
+	UPDATE_COEF(0x08, 0xfffc, 0x0c2c), /* JD */
+	WRITE_COEF(0x0a, 0xcccc), /* JD offset1 */
+	WRITE_COEF(0x0b, 0xcccc), /* JD offset2 */
+	WRITE_COEF(0x0e, 0x6fc0), /* LDO1/2/3, DAC/ADC */
+	UPDATE_COEF(0x0f, 0xf800, 0x1000), /* JD */
+	UPDATE_COEF(0x10, 0xfc00, 0x0c00), /* Capless */
+	WRITE_COEF(0x3a, 0x0), /* Class D test 4 */
+	UPDATE_COEF(0x0c, 0xfe00, 0x0), /* IO power down directly */
+	WRITE_COEF(0x22, 0xa0c0), /* ANC */
+	UPDATE_COEFEX(0x53, 0x01, 0x000f, 0x0008), /* AGC MUX */
+	UPDATE_COEF(0x1d, 0x00e0, 0), /* DAC simple content protection */
+	UPDATE_COEF(0x1f, 0x00e0, 0), /* ADC simple content protection */
+	WRITE_COEF(0x21, 0x8804), /* DAC ADC Zero Detection */
+	WRITE_COEF(0x2e, 0x2902), /* PLL */
+	WRITE_COEF(0x33, 0xa080), /* capless control 2 */
+	WRITE_COEF(0x34, 0x3400), /* capless control 3 */
+	WRITE_COEF(0x35, 0x2f3e), /* capless control 4 */
+	WRITE_COEF(0x36, 0x0), /* capless control 5 */
+	UPDATE_COEF(0x38, 0x0fff, 0x0900), /* class D test 2 */
+	WRITE_COEF(0x39, 0x110a), /* class D test 3 */
+	UPDATE_COEF(0x3b, 0x00f8, 0x00d8), /* class D test 5 */
+	WRITE_COEF(0x3c, 0x0014), /* class D test 6 */
+	WRITE_COEF(0x3d, 0xc2ba), /* classD OCP */
+	UPDATE_COEF(0x42, 0x0f80, 0x0), /* classD pure DC test */
+	WRITE_COEF(0x49, 0x0), /* test mode */
+	UPDATE_COEF(0x40, 0xf800, 0x9800), /* Class D DC enable */
+	UPDATE_COEF(0x42, 0xf000, 0x2000), /* DC offset */
+	WRITE_COEF(0x37, 0xfc06), /* Class D amp control */
+	{}
+};
+
 static void alc283_restore_default_value(struct hda_codec *codec)
 {
-	int val;
-
-	/* Power Down Control */
-	alc_write_coef_idx(codec, 0x03, 0x0002);
-	/* FIFO and filter clock */
-	alc_write_coef_idx(codec, 0x05, 0x0700);
-	/* DMIC control */
-	alc_write_coef_idx(codec, 0x07, 0x0200);
-	/* Analog clock */
-	val = alc_read_coef_idx(codec, 0x06);
-	alc_write_coef_idx(codec, 0x06, (val & ~0x00f0) | 0x0);
-	/* JD */
-	val = alc_read_coef_idx(codec, 0x08);
-	alc_write_coef_idx(codec, 0x08, (val & ~0xfffc) | 0x0c2c);
-	/* JD offset1 */
-	alc_write_coef_idx(codec, 0x0a, 0xcccc);
-	/* JD offset2 */
-	alc_write_coef_idx(codec, 0x0b, 0xcccc);
-	/* LDO1/2/3, DAC/ADC */
-	alc_write_coef_idx(codec, 0x0e, 0x6fc0);
-	/* JD */
-	val = alc_read_coef_idx(codec, 0x0f);
-	alc_write_coef_idx(codec, 0x0f, (val & ~0xf800) | 0x1000);
-	/* Capless */
-	val = alc_read_coef_idx(codec, 0x10);
-	alc_write_coef_idx(codec, 0x10, (val & ~0xfc00) | 0x0c00);
-	/* Class D test 4 */
-	alc_write_coef_idx(codec, 0x3a, 0x0);
-	/* IO power down directly */
-	val = alc_read_coef_idx(codec, 0x0c);
-	alc_write_coef_idx(codec, 0x0c, (val & ~0xfe00) | 0x0);
-	/* ANC */
-	alc_write_coef_idx(codec, 0x22, 0xa0c0);
-	/* AGC MUX */
-	val = alc_read_coefex_idx(codec, 0x53, 0x01);
-	alc_write_coefex_idx(codec, 0x53, 0x01, (val & ~0x000f) | 0x0008);
-	/* DAC simple content protection */
-	val = alc_read_coef_idx(codec, 0x1d);
-	alc_write_coef_idx(codec, 0x1d, (val & ~0x00e0) | 0x0);
-	/* ADC simple content protection */
-	val = alc_read_coef_idx(codec, 0x1f);
-	alc_write_coef_idx(codec, 0x1f, (val & ~0x00e0) | 0x0);
-	/* DAC ADC Zero Detection */
-	alc_write_coef_idx(codec, 0x21, 0x8804);
-	/* PLL */
-	alc_write_coef_idx(codec, 0x2e, 0x2902);
-	/* capless control 2 */
-	alc_write_coef_idx(codec, 0x33, 0xa080);
-	/* capless control 3 */
-	alc_write_coef_idx(codec, 0x34, 0x3400);
-	/* capless control 4 */
-	alc_write_coef_idx(codec, 0x35, 0x2f3e);
-	/* capless control 5 */
-	alc_write_coef_idx(codec, 0x36, 0x0);
-	/* class D test 2 */
-	val = alc_read_coef_idx(codec, 0x38);
-	alc_write_coef_idx(codec, 0x38, (val & ~0x0fff) | 0x0900);
-	/* class D test 3 */
-	alc_write_coef_idx(codec, 0x39, 0x110a);
-	/* class D test 5 */
-	val = alc_read_coef_idx(codec, 0x3b);
-	alc_write_coef_idx(codec, 0x3b, (val & ~0x00f8) | 0x00d8);
-	/* class D test 6 */
-	alc_write_coef_idx(codec, 0x3c, 0x0014);
-	/* classD OCP */
-	alc_write_coef_idx(codec, 0x3d, 0xc2ba);
-	/* classD pure DC test */
-	val = alc_read_coef_idx(codec, 0x42);
-	alc_write_coef_idx(codec, 0x42, (val & ~0x0f80) | 0x0);
-	/* test mode */
-	alc_write_coef_idx(codec, 0x49, 0x0);
-	/* Class D DC enable */
-	val = alc_read_coef_idx(codec, 0x40);
-	alc_write_coef_idx(codec, 0x40, (val & ~0xf800) | 0x9800);
-	/* DC offset */
-	val = alc_read_coef_idx(codec, 0x42);
-	alc_write_coef_idx(codec, 0x42, (val & ~0xf000) | 0x2000);
-	/* Class D amp control */
-	alc_write_coef_idx(codec, 0x37, 0xfc06);
+	alc_process_coef_fw(codec, alc283_coefs);
 }
 
 static void alc283_init(struct hda_codec *codec)
@@ -3068,7 +2830,6 @@ static void alc283_init(struct hda_codec *codec)
 	struct alc_spec *spec = codec->spec;
 	hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0];
 	bool hp_pin_sense;
-	int val;
 
 	if (!spec->gen.autocfg.hp_outs) {
 		if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT)
@@ -3098,8 +2859,7 @@ static void alc283_init(struct hda_codec *codec)
 		msleep(85);
 	/* Index 0x46 Combo jack auto switch control 2 */
 	/* 3k pull low control for Headset jack. */
-	val = alc_read_coef_idx(codec, 0x46);
-	alc_write_coef_idx(codec, 0x46, val & ~(3 << 12));
+	alc_update_coef_idx(codec, 0x46, 3 << 12, 0);
 	/* Headphone capless set to normal mode */
 	alc_write_coef_idx(codec, 0x43, 0x9614);
 }
@@ -3109,7 +2869,6 @@ static void alc283_shutup(struct hda_codec *codec)
 	struct alc_spec *spec = codec->spec;
 	hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0];
 	bool hp_pin_sense;
-	int val;
 
 	if (!spec->gen.autocfg.hp_outs) {
 		if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT)
@@ -3134,8 +2893,7 @@ static void alc283_shutup(struct hda_codec *codec)
 	snd_hda_codec_write(codec, hp_pin, 0,
 			    AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
 
-	val = alc_read_coef_idx(codec, 0x46);
-	alc_write_coef_idx(codec, 0x46, val | (3 << 12));
+	alc_update_coef_idx(codec, 0x46, 0, 3 << 12);
 
 	if (hp_pin_sense)
 		msleep(100);
@@ -3268,7 +3026,6 @@ static int alc269_resume(struct hda_codec *codec)
 
 	snd_hda_codec_resume_amp(codec);
 	snd_hda_codec_resume_cache(codec);
-	alc_inv_dmic_sync(codec, true);
 	hda_call_check_power_status(codec, 0x01);
 
 	/* on some machine, the BIOS will clear the codec gpio data when enter
@@ -3298,12 +3055,8 @@ static void alc269_fixup_pincfg_no_hp_to_lineout(struct hda_codec *codec,
 static void alc269_fixup_hweq(struct hda_codec *codec,
 			       const struct hda_fixup *fix, int action)
 {
-	int coef;
-
-	if (action != HDA_FIXUP_ACT_INIT)
-		return;
-	coef = alc_read_coef_idx(codec, 0x1e);
-	alc_write_coef_idx(codec, 0x1e, coef | 0x80);
+	if (action == HDA_FIXUP_ACT_INIT)
+		alc_update_coef_idx(codec, 0x1e, 0, 0x80);
 }
 
 static void alc269_fixup_headset_mic(struct hda_codec *codec,
@@ -3351,32 +3104,21 @@ static void alc269_fixup_pcm_44k(struct hda_codec *codec,
 static void alc269_fixup_stereo_dmic(struct hda_codec *codec,
 				     const struct hda_fixup *fix, int action)
 {
-	int coef;
-
-	if (action != HDA_FIXUP_ACT_INIT)
-		return;
 	/* The digital-mic unit sends PDM (differential signal) instead of
 	 * the standard PCM, thus you can't record a valid mono stream as is.
 	 * Below is a workaround specific to ALC269 to control the dmic
 	 * signal source as mono.
 	 */
-	coef = alc_read_coef_idx(codec, 0x07);
-	alc_write_coef_idx(codec, 0x07, coef | 0x80);
+	if (action == HDA_FIXUP_ACT_INIT)
+		alc_update_coef_idx(codec, 0x07, 0, 0x80);
 }
 
 static void alc269_quanta_automute(struct hda_codec *codec)
 {
 	snd_hda_gen_update_outputs(codec);
 
-	snd_hda_codec_write(codec, 0x20, 0,
-			AC_VERB_SET_COEF_INDEX, 0x0c);
-	snd_hda_codec_write(codec, 0x20, 0,
-			AC_VERB_SET_PROC_COEF, 0x680);
-
-	snd_hda_codec_write(codec, 0x20, 0,
-			AC_VERB_SET_COEF_INDEX, 0x0c);
-	snd_hda_codec_write(codec, 0x20, 0,
-			AC_VERB_SET_PROC_COEF, 0x480);
+	alc_write_coef_idx(codec, 0x0c, 0x680);
+	alc_write_coef_idx(codec, 0x0c, 0x480);
 }
 
 static void alc269_fixup_quanta_mute(struct hda_codec *codec,
@@ -3389,7 +3131,7 @@ static void alc269_fixup_quanta_mute(struct hda_codec *codec,
 }
 
 static void alc269_x101_hp_automute_hook(struct hda_codec *codec,
-					 struct hda_jack_tbl *jack)
+					 struct hda_jack_callback *jack)
 {
 	struct alc_spec *spec = codec->spec;
 	int vref;
@@ -3622,61 +3364,62 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 
 static void alc_headset_mode_unplugged(struct hda_codec *codec)
 {
-	int val;
+	static struct coef_fw coef0255[] = {
+		WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */
+		WRITE_COEF(0x45, 0xd089), /* UAJ function set to menual mode */
+		UPDATE_COEFEX(0x57, 0x05, 1<<14, 0), /* Direct Drive HP Amp control(Set to verb control)*/
+		WRITE_COEF(0x06, 0x6104), /* Set MIC2 Vref gate with HP */
+		WRITE_COEFEX(0x57, 0x03, 0x8aa6), /* Direct Drive HP Amp control */
+		{}
+	};
+	static struct coef_fw coef0233[] = {
+		WRITE_COEF(0x1b, 0x0c0b),
+		WRITE_COEF(0x45, 0xc429),
+		UPDATE_COEF(0x35, 0x4000, 0),
+		WRITE_COEF(0x06, 0x2104),
+		WRITE_COEF(0x1a, 0x0001),
+		WRITE_COEF(0x26, 0x0004),
+		WRITE_COEF(0x32, 0x42a3),
+		{}
+	};
+	static struct coef_fw coef0292[] = {
+		WRITE_COEF(0x76, 0x000e),
+		WRITE_COEF(0x6c, 0x2400),
+		WRITE_COEF(0x18, 0x7308),
+		WRITE_COEF(0x6b, 0xc429),
+		{}
+	};
+	static struct coef_fw coef0293[] = {
+		UPDATE_COEF(0x10, 7<<8, 6<<8), /* SET Line1 JD to 0 */
+		UPDATE_COEFEX(0x57, 0x05, 1<<15|1<<13, 0x0), /* SET charge pump by verb */
+		UPDATE_COEFEX(0x57, 0x03, 1<<10, 1<<10), /* SET EN_OSW to 1 */
+		UPDATE_COEF(0x1a, 1<<3, 1<<3), /* Combo JD gating with LINE1-VREFO */
+		WRITE_COEF(0x45, 0xc429), /* Set to TRS type */
+		UPDATE_COEF(0x4a, 0x000f, 0x000e), /* Combo Jack auto detect */
+		{}
+	};
+	static struct coef_fw coef0668[] = {
+		WRITE_COEF(0x15, 0x0d40),
+		WRITE_COEF(0xb7, 0x802b),
+		{}
+	};
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
-		/* LDO and MISC control */
-		alc_write_coef_idx(codec, 0x1b, 0x0c0b);
-		/* UAJ function set to menual mode */
-		alc_write_coef_idx(codec, 0x45, 0xd089);
-		/* Direct Drive HP Amp control(Set to verb control)*/
-		val = alc_read_coefex_idx(codec, 0x57, 0x05);
-		alc_write_coefex_idx(codec, 0x57, 0x05, val & ~(1<<14));
-		/* Set MIC2 Vref gate with HP */
-		alc_write_coef_idx(codec, 0x06, 0x6104);
-		/* Direct Drive HP Amp control */
-		alc_write_coefex_idx(codec, 0x57, 0x03, 0x8aa6);
+		alc_process_coef_fw(codec, coef0255);
 		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
-		alc_write_coef_idx(codec, 0x1b, 0x0c0b);
-		alc_write_coef_idx(codec, 0x45, 0xc429);
-		val = alc_read_coef_idx(codec, 0x35);
-		alc_write_coef_idx(codec, 0x35, val & 0xbfff);
-		alc_write_coef_idx(codec, 0x06, 0x2104);
-		alc_write_coef_idx(codec, 0x1a, 0x0001);
-		alc_write_coef_idx(codec, 0x26, 0x0004);
-		alc_write_coef_idx(codec, 0x32, 0x42a3);
+		alc_process_coef_fw(codec, coef0233);
 		break;
 	case 0x10ec0292:
-		alc_write_coef_idx(codec, 0x76, 0x000e);
-		alc_write_coef_idx(codec, 0x6c, 0x2400);
-		alc_write_coef_idx(codec, 0x18, 0x7308);
-		alc_write_coef_idx(codec, 0x6b, 0xc429);
+		alc_process_coef_fw(codec, coef0292);
 		break;
 	case 0x10ec0293:
-		/* SET Line1 JD to 0 */
-		val = alc_read_coef_idx(codec, 0x10);
-		alc_write_coef_idx(codec, 0x10, (val & ~(7<<8)) | 6<<8);
-		/* SET charge pump by verb */
-		val = alc_read_coefex_idx(codec, 0x57, 0x05);
-		alc_write_coefex_idx(codec, 0x57, 0x05, (val & ~(1<<15|1<<13)) | 0x0);
-		/* SET EN_OSW to 1 */
-		val = alc_read_coefex_idx(codec, 0x57, 0x03);
-		alc_write_coefex_idx(codec, 0x57, 0x03, (val & ~(1<<10)) | (1<<10) );
-		/* Combo JD gating with LINE1-VREFO */
-		val = alc_read_coef_idx(codec, 0x1a);
-		alc_write_coef_idx(codec, 0x1a, (val & ~(1<<3)) | (1<<3));
-		/* Set to TRS type */
-		alc_write_coef_idx(codec, 0x45, 0xc429);
-		/* Combo Jack auto detect */
-		val = alc_read_coef_idx(codec, 0x4a);
-		alc_write_coef_idx(codec, 0x4a, (val & 0xfff0) | 0x000e);
+		alc_process_coef_fw(codec, coef0293);
 		break;
 	case 0x10ec0668:
-		alc_write_coef_idx(codec, 0x15, 0x0d40);
-		alc_write_coef_idx(codec, 0xb7, 0x802b);
+		alc_process_coef_fw(codec, coef0668);
 		break;
 	}
 	codec_dbg(codec, "Headset jack set to unplugged mode.\n");
@@ -3686,55 +3429,65 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
 static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 				    hda_nid_t mic_pin)
 {
-	int val;
+	static struct coef_fw coef0255[] = {
+		WRITE_COEFEX(0x57, 0x03, 0x8aa6),
+		WRITE_COEF(0x06, 0x6100), /* Set MIC2 Vref gate to normal */
+		{}
+	};
+	static struct coef_fw coef0233[] = {
+		UPDATE_COEF(0x35, 0, 1<<14),
+		WRITE_COEF(0x06, 0x2100),
+		WRITE_COEF(0x1a, 0x0021),
+		WRITE_COEF(0x26, 0x008c),
+		{}
+	};
+	static struct coef_fw coef0292[] = {
+		WRITE_COEF(0x19, 0xa208),
+		WRITE_COEF(0x2e, 0xacf0),
+		{}
+	};
+	static struct coef_fw coef0293[] = {
+		UPDATE_COEFEX(0x57, 0x05, 0, 1<<15|1<<13), /* SET charge pump by verb */
+		UPDATE_COEFEX(0x57, 0x03, 1<<10, 0), /* SET EN_OSW to 0 */
+		UPDATE_COEF(0x1a, 1<<3, 0), /* Combo JD gating without LINE1-VREFO */
+		{}
+	};
+	static struct coef_fw coef0688[] = {
+		WRITE_COEF(0xb7, 0x802b),
+		WRITE_COEF(0xb5, 0x1040),
+		UPDATE_COEF(0xc3, 0, 1<<12),
+		{}
+	};
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
 		alc_write_coef_idx(codec, 0x45, 0xc489);
 		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
-		alc_write_coefex_idx(codec, 0x57, 0x03, 0x8aa6);
-		/* Set MIC2 Vref gate to normal */
-		alc_write_coef_idx(codec, 0x06, 0x6100);
+		alc_process_coef_fw(codec, coef0255);
 		snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
 		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
 		alc_write_coef_idx(codec, 0x45, 0xc429);
 		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
-		val = alc_read_coef_idx(codec, 0x35);
-		alc_write_coef_idx(codec, 0x35, val | 1<<14);
-		alc_write_coef_idx(codec, 0x06, 0x2100);
-		alc_write_coef_idx(codec, 0x1a, 0x0021);
-		alc_write_coef_idx(codec, 0x26, 0x008c);
+		alc_process_coef_fw(codec, coef0233);
 		snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
 		break;
 	case 0x10ec0292:
 		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
-		alc_write_coef_idx(codec, 0x19, 0xa208);
-		alc_write_coef_idx(codec, 0x2e, 0xacf0);
+		alc_process_coef_fw(codec, coef0292);
 		break;
 	case 0x10ec0293:
 		/* Set to TRS mode */
 		alc_write_coef_idx(codec, 0x45, 0xc429);
 		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
-		/* SET charge pump by verb */
-		val = alc_read_coefex_idx(codec, 0x57, 0x05);
-		alc_write_coefex_idx(codec, 0x57, 0x05, (val & ~(1<<15|1<<13)) | (1<<15|1<<13));
-		/* SET EN_OSW to 0 */
-		val = alc_read_coefex_idx(codec, 0x57, 0x03);
-		alc_write_coefex_idx(codec, 0x57, 0x03, (val & ~(1<<10)) | 0x0);
-		/* Combo JD gating without LINE1-VREFO */
-		val = alc_read_coef_idx(codec, 0x1a);
-		alc_write_coef_idx(codec, 0x1a, (val & ~(1<<3)) | 0x0);
+		alc_process_coef_fw(codec, coef0293);
 		snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
 		break;
 	case 0x10ec0668:
 		alc_write_coef_idx(codec, 0x11, 0x0001);
 		snd_hda_set_pin_ctl_cache(codec, hp_pin, 0);
-		alc_write_coef_idx(codec, 0xb7, 0x802b);
-		alc_write_coef_idx(codec, 0xb5, 0x1040);
-		val = alc_read_coef_idx(codec, 0xc3);
-		alc_write_coef_idx(codec, 0xc3, val | 1<<12);
+		alc_process_coef_fw(codec, coef0688);
 		snd_hda_set_pin_ctl_cache(codec, mic_pin, PIN_VREF50);
 		break;
 	}
@@ -3743,40 +3496,54 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin,
 
 static void alc_headset_mode_default(struct hda_codec *codec)
 {
-	int val;
+	static struct coef_fw coef0255[] = {
+		WRITE_COEF(0x45, 0xc089),
+		WRITE_COEF(0x45, 0xc489),
+		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
+		WRITE_COEF(0x49, 0x0049),
+		{}
+	};
+	static struct coef_fw coef0233[] = {
+		WRITE_COEF(0x06, 0x2100),
+		WRITE_COEF(0x32, 0x4ea3),
+		{}
+	};
+	static struct coef_fw coef0292[] = {
+		WRITE_COEF(0x76, 0x000e),
+		WRITE_COEF(0x6c, 0x2400),
+		WRITE_COEF(0x6b, 0xc429),
+		WRITE_COEF(0x18, 0x7308),
+		{}
+	};
+	static struct coef_fw coef0293[] = {
+		UPDATE_COEF(0x4a, 0x000f, 0x000e), /* Combo Jack auto detect */
+		WRITE_COEF(0x45, 0xC429), /* Set to TRS type */
+		UPDATE_COEF(0x1a, 1<<3, 0), /* Combo JD gating without LINE1-VREFO */
+		{}
+	};
+	static struct coef_fw coef0688[] = {
+		WRITE_COEF(0x11, 0x0041),
+		WRITE_COEF(0x15, 0x0d40),
+		WRITE_COEF(0xb7, 0x802b),
+		{}
+	};
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
-		alc_write_coef_idx(codec, 0x45, 0xc089);
-		alc_write_coef_idx(codec, 0x45, 0xc489);
-		alc_write_coefex_idx(codec, 0x57, 0x03, 0x8ea6);
-		alc_write_coef_idx(codec, 0x49, 0x0049);
+		alc_process_coef_fw(codec, coef0255);
 		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
-		alc_write_coef_idx(codec, 0x06, 0x2100);
-		alc_write_coef_idx(codec, 0x32, 0x4ea3);
+		alc_process_coef_fw(codec, coef0233);
 		break;
 	case 0x10ec0292:
-		alc_write_coef_idx(codec, 0x76, 0x000e);
-		alc_write_coef_idx(codec, 0x6c, 0x2400);
-		alc_write_coef_idx(codec, 0x6b, 0xc429);
-		alc_write_coef_idx(codec, 0x18, 0x7308);
+		alc_process_coef_fw(codec, coef0292);
 		break;
 	case 0x10ec0293:
-		/* Combo Jack auto detect */
-		val = alc_read_coef_idx(codec, 0x4a);
-		alc_write_coef_idx(codec, 0x4a, (val & 0xfff0) | 0x000e);
-		/* Set to TRS type */
-		alc_write_coef_idx(codec, 0x45, 0xC429);
-		/* Combo JD gating without LINE1-VREFO */
-		val = alc_read_coef_idx(codec, 0x1a);
-		alc_write_coef_idx(codec, 0x1a, (val & ~(1<<3)) | 0x0);
+		alc_process_coef_fw(codec, coef0293);
 		break;
 	case 0x10ec0668:
-		alc_write_coef_idx(codec, 0x11, 0x0041);
-		alc_write_coef_idx(codec, 0x15, 0x0d40);
-		alc_write_coef_idx(codec, 0xb7, 0x802b);
+		alc_process_coef_fw(codec, coef0688);
 		break;
 	}
 	codec_dbg(codec, "Headset jack set to headphone (default) mode.\n");
@@ -3785,37 +3552,52 @@ static void alc_headset_mode_default(struct hda_codec *codec)
 /* Iphone type */
 static void alc_headset_mode_ctia(struct hda_codec *codec)
 {
-	int val;
+	static struct coef_fw coef0255[] = {
+		WRITE_COEF(0x45, 0xd489), /* Set to CTIA type */
+		WRITE_COEF(0x1b, 0x0c2b),
+		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
+		{}
+	};
+	static struct coef_fw coef0233[] = {
+		WRITE_COEF(0x45, 0xd429),
+		WRITE_COEF(0x1b, 0x0c2b),
+		WRITE_COEF(0x32, 0x4ea3),
+		{}
+	};
+	static struct coef_fw coef0292[] = {
+		WRITE_COEF(0x6b, 0xd429),
+		WRITE_COEF(0x76, 0x0008),
+		WRITE_COEF(0x18, 0x7388),
+		{}
+	};
+	static struct coef_fw coef0293[] = {
+		WRITE_COEF(0x45, 0xd429), /* Set to ctia type */
+		UPDATE_COEF(0x10, 7<<8, 7<<8), /* SET Line1 JD to 1 */
+		{}
+	};
+	static struct coef_fw coef0688[] = {
+		WRITE_COEF(0x11, 0x0001),
+		WRITE_COEF(0x15, 0x0d60),
+		WRITE_COEF(0xc3, 0x0000),
+		{}
+	};
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
-		/* Set to CTIA type */
-		alc_write_coef_idx(codec, 0x45, 0xd489);
-		alc_write_coef_idx(codec, 0x1b, 0x0c2b);
-		alc_write_coefex_idx(codec, 0x57, 0x03, 0x8ea6);
+		alc_process_coef_fw(codec, coef0255);
 		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
-		alc_write_coef_idx(codec, 0x45, 0xd429);
-		alc_write_coef_idx(codec, 0x1b, 0x0c2b);
-		alc_write_coef_idx(codec, 0x32, 0x4ea3);
+		alc_process_coef_fw(codec, coef0233);
 		break;
 	case 0x10ec0292:
-		alc_write_coef_idx(codec, 0x6b, 0xd429);
-		alc_write_coef_idx(codec, 0x76, 0x0008);
-		alc_write_coef_idx(codec, 0x18, 0x7388);
+		alc_process_coef_fw(codec, coef0292);
 		break;
 	case 0x10ec0293:
-		/* Set to ctia type */
-		alc_write_coef_idx(codec, 0x45, 0xd429);
-		/* SET Line1 JD to 1 */
-		val = alc_read_coef_idx(codec, 0x10);
-		alc_write_coef_idx(codec, 0x10, (val & ~(7<<8)) | 7<<8);
+		alc_process_coef_fw(codec, coef0293);
 		break;
 	case 0x10ec0668:
-		alc_write_coef_idx(codec, 0x11, 0x0001);
-		alc_write_coef_idx(codec, 0x15, 0x0d60);
-		alc_write_coef_idx(codec, 0xc3, 0x0000);
+		alc_process_coef_fw(codec, coef0688);
 		break;
 	}
 	codec_dbg(codec, "Headset jack set to iPhone-style headset mode.\n");
@@ -3824,37 +3606,52 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
 /* Nokia type */
 static void alc_headset_mode_omtp(struct hda_codec *codec)
 {
-	int val;
+	static struct coef_fw coef0255[] = {
+		WRITE_COEF(0x45, 0xe489), /* Set to OMTP Type */
+		WRITE_COEF(0x1b, 0x0c2b),
+		WRITE_COEFEX(0x57, 0x03, 0x8ea6),
+		{}
+	};
+	static struct coef_fw coef0233[] = {
+		WRITE_COEF(0x45, 0xe429),
+		WRITE_COEF(0x1b, 0x0c2b),
+		WRITE_COEF(0x32, 0x4ea3),
+		{}
+	};
+	static struct coef_fw coef0292[] = {
+		WRITE_COEF(0x6b, 0xe429),
+		WRITE_COEF(0x76, 0x0008),
+		WRITE_COEF(0x18, 0x7388),
+		{}
+	};
+	static struct coef_fw coef0293[] = {
+		WRITE_COEF(0x45, 0xe429), /* Set to omtp type */
+		UPDATE_COEF(0x10, 7<<8, 7<<8), /* SET Line1 JD to 1 */
+		{}
+	};
+	static struct coef_fw coef0688[] = {
+		WRITE_COEF(0x11, 0x0001),
+		WRITE_COEF(0x15, 0x0d50),
+		WRITE_COEF(0xc3, 0x0000),
+		{}
+	};
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
-		/* Set to OMTP Type */
-		alc_write_coef_idx(codec, 0x45, 0xe489);
-		alc_write_coef_idx(codec, 0x1b, 0x0c2b);
-		alc_write_coefex_idx(codec, 0x57, 0x03, 0x8ea6);
+		alc_process_coef_fw(codec, coef0255);
 		break;
 	case 0x10ec0233:
 	case 0x10ec0283:
-		alc_write_coef_idx(codec, 0x45, 0xe429);
-		alc_write_coef_idx(codec, 0x1b, 0x0c2b);
-		alc_write_coef_idx(codec, 0x32, 0x4ea3);
+		alc_process_coef_fw(codec, coef0233);
 		break;
 	case 0x10ec0292:
-		alc_write_coef_idx(codec, 0x6b, 0xe429);
-		alc_write_coef_idx(codec, 0x76, 0x0008);
-		alc_write_coef_idx(codec, 0x18, 0x7388);
+		alc_process_coef_fw(codec, coef0292);
 		break;
 	case 0x10ec0293:
-		/* Set to omtp type */
-		alc_write_coef_idx(codec, 0x45, 0xe429);
-		/* SET Line1 JD to 1 */
-		val = alc_read_coef_idx(codec, 0x10);
-		alc_write_coef_idx(codec, 0x10, (val & ~(7<<8)) | 7<<8);
+		alc_process_coef_fw(codec, coef0293);
 		break;
 	case 0x10ec0668:
-		alc_write_coef_idx(codec, 0x11, 0x0001);
-		alc_write_coef_idx(codec, 0x15, 0x0d50);
-		alc_write_coef_idx(codec, 0xc3, 0x0000);
+		alc_process_coef_fw(codec, coef0688);
 		break;
 	}
 	codec_dbg(codec, "Headset jack set to Nokia-style headset mode.\n");
@@ -3865,13 +3662,28 @@ static void alc_determine_headset_type(struct hda_codec *codec)
 	int val;
 	bool is_ctia = false;
 	struct alc_spec *spec = codec->spec;
+	static struct coef_fw coef0255[] = {
+		WRITE_COEF(0x45, 0xd089), /* combo jack auto switch control(Check type)*/
+		WRITE_COEF(0x49, 0x0149), /* combo jack auto switch control(Vref
+ conteol) */
+		{}
+	};
+	static struct coef_fw coef0293[] = {
+		UPDATE_COEF(0x4a, 0x000f, 0x0008), /* Combo Jack auto detect */
+		WRITE_COEF(0x45, 0xD429), /* Set to ctia type */
+		{}
+	};
+	static struct coef_fw coef0688[] = {
+		WRITE_COEF(0x11, 0x0001),
+		WRITE_COEF(0xb7, 0x802b),
+		WRITE_COEF(0x15, 0x0d60),
+		WRITE_COEF(0xc3, 0x0c00),
+		{}
+	};
 
 	switch (codec->vendor_id) {
 	case 0x10ec0255:
-		/* combo jack auto switch control(Check type)*/
-		alc_write_coef_idx(codec, 0x45, 0xd089);
-		/* combo jack auto switch control(Vref conteol) */
-		alc_write_coef_idx(codec, 0x49, 0x0149);
+		alc_process_coef_fw(codec, coef0255);
 		msleep(300);
 		val = alc_read_coef_idx(codec, 0x46);
 		is_ctia = (val & 0x0070) == 0x0070;
@@ -3890,20 +3702,13 @@ static void alc_determine_headset_type(struct hda_codec *codec)
 		is_ctia = (val & 0x001c) == 0x001c;
 		break;
 	case 0x10ec0293:
-		/* Combo Jack auto detect */
-		val = alc_read_coef_idx(codec, 0x4a);
-		alc_write_coef_idx(codec, 0x4a, (val & 0xfff0) | 0x0008);
-		/* Set to ctia type */
-		alc_write_coef_idx(codec, 0x45, 0xD429);
+		alc_process_coef_fw(codec, coef0293);
 		msleep(300);
 		val = alc_read_coef_idx(codec, 0x46);
 		is_ctia = (val & 0x0070) == 0x0070;
 		break;
 	case 0x10ec0668:
-		alc_write_coef_idx(codec, 0x11, 0x0001);
-		alc_write_coef_idx(codec, 0xb7, 0x802b);
-		alc_write_coef_idx(codec, 0x15, 0x0d60);
-		alc_write_coef_idx(codec, 0xc3, 0x0c00);
+		alc_process_coef_fw(codec, coef0688);
 		msleep(300);
 		val = alc_read_coef_idx(codec, 0xbe);
 		is_ctia = (val & 0x1c02) == 0x1c02;
@@ -3980,7 +3785,8 @@ static void alc_update_headset_mode_hook(struct hda_codec *codec,
 	alc_update_headset_mode(codec);
 }
 
-static void alc_update_headset_jack_cb(struct hda_codec *codec, struct hda_jack_tbl *jack)
+static void alc_update_headset_jack_cb(struct hda_codec *codec,
+				       struct hda_jack_callback *jack)
 {
 	struct alc_spec *spec = codec->spec;
 	spec->current_headset_type = ALC_HEADSET_TYPE_UNKNOWN;
@@ -4039,11 +3845,15 @@ static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec,
 static void alc255_set_default_jack_type(struct hda_codec *codec)
 {
 	/* Set to iphone type */
-	alc_write_coef_idx(codec, 0x1b, 0x880b);
-	alc_write_coef_idx(codec, 0x45, 0xd089);
-	alc_write_coef_idx(codec, 0x1b, 0x080b);
-	alc_write_coef_idx(codec, 0x46, 0x0004);
-	alc_write_coef_idx(codec, 0x1b, 0x0c0b);
+	static struct coef_fw fw[] = {
+		WRITE_COEF(0x1b, 0x880b),
+		WRITE_COEF(0x45, 0xd089),
+		WRITE_COEF(0x1b, 0x080b),
+		WRITE_COEF(0x46, 0x0004),
+		WRITE_COEF(0x1b, 0x0c0b),
+		{}
+	};
+	alc_process_coef_fw(codec, fw);
 	msleep(30);
 }
 
@@ -4138,10 +3948,8 @@ static void alc_fixup_headset_mode_alc668(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		int val;
 		alc_write_coef_idx(codec, 0xc4, 0x8000);
-		val = alc_read_coef_idx(codec, 0xc2);
-		alc_write_coef_idx(codec, 0xc2, val & 0xfe);
+		alc_update_coef_idx(codec, 0xc2, ~0xfe, 0);
 		snd_hda_set_pin_ctl_cache(codec, 0x18, 0);
 	}
 	alc_fixup_headset_mode(codec, fix, action);
@@ -4218,7 +4026,7 @@ static void alc269_fixup_limit_int_mic_boost(struct hda_codec *codec,
 }
 
 static void alc283_hp_automute_hook(struct hda_codec *codec,
-				    struct hda_jack_tbl *jack)
+				    struct hda_jack_callback *jack)
 {
 	struct alc_spec *spec = codec->spec;
 	int vref;
@@ -4237,7 +4045,6 @@ static void alc283_fixup_chromebook(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	int val;
 
 	switch (action) {
 	case HDA_FIXUP_ACT_PRE_PROBE:
@@ -4248,11 +4055,9 @@ static void alc283_fixup_chromebook(struct hda_codec *codec,
 	case HDA_FIXUP_ACT_INIT:
 		/* MIC2-VREF control */
 		/* Set to manual mode */
-		val = alc_read_coef_idx(codec, 0x06);
-		alc_write_coef_idx(codec, 0x06, val & ~0x000c);
+		alc_update_coef_idx(codec, 0x06, 0x000c, 0);
 		/* Enable Line1 input control by verb */
-		val = alc_read_coef_idx(codec, 0x1a);
-		alc_write_coef_idx(codec, 0x1a, val | (1 << 4));
+		alc_update_coef_idx(codec, 0x1a, 0, 1 << 4);
 		break;
 	}
 }
@@ -4261,7 +4066,6 @@ static void alc283_fixup_sense_combo_jack(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	int val;
 
 	switch (action) {
 	case HDA_FIXUP_ACT_PRE_PROBE:
@@ -4270,8 +4074,7 @@ static void alc283_fixup_sense_combo_jack(struct hda_codec *codec,
 	case HDA_FIXUP_ACT_INIT:
 		/* MIC2-VREF control */
 		/* Set to manual mode */
-		val = alc_read_coef_idx(codec, 0x06);
-		alc_write_coef_idx(codec, 0x06, val & ~0x000c);
+		alc_update_coef_idx(codec, 0x06, 0x000c, 0);
 		break;
 	}
 }
@@ -4309,7 +4112,6 @@ static void alc282_fixup_asus_tx300(struct hda_codec *codec,
 		spec->gen.auto_mute_via_amp = 1;
 		spec->gen.automute_hook = asus_tx300_automute;
 		snd_hda_jack_detect_enable_callback(codec, 0x1b,
-						    HDA_GEN_HP_EVENT,
 						    snd_hda_gen_hp_automute);
 		break;
 	case HDA_FIXUP_ACT_BUILD:
@@ -4576,7 +4378,7 @@ static const struct hda_fixup alc269_fixups[] = {
 	},
 	[ALC269_FIXUP_INV_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
-		.v.func = alc_fixup_inv_dmic_0x12,
+		.v.func = alc_fixup_inv_dmic,
 	},
 	[ALC269_FIXUP_NO_SHUTUP] = {
 		.type = HDA_FIXUP_FUNC,
@@ -4887,122 +4689,45 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
 	SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
 	SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
-	SND_PCI_QUIRK(0x1028, 0x05bd, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05be, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05c4, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05c5, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05c6, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05c7, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05c8, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05c9, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05ca, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05cb, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05da, "Dell Vostro 5460", ALC290_FIXUP_SUBWOOFER),
-	SND_PCI_QUIRK(0x1028, 0x05de, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05e0, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05e9, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05ea, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05eb, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05ec, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05ed, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05ee, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05f3, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05f4, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05f5, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05f6, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05f8, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05f9, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x05fb, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0606, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0608, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0609, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0610, "Dell", ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED),
-	SND_PCI_QUIRK(0x1028, 0x0613, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0614, "Dell Inspiron 3135", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0615, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x061f, "Dell", ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED),
 	SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS_HSJACK),
-	SND_PCI_QUIRK(0x1028, 0x063f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x064b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0668, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0669, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0684, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x15cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x15cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
 	SND_PCI_QUIRK(0x103c, 0x18e6, "HP", ALC269_FIXUP_HP_GPIO_LED),
-	SND_PCI_QUIRK(0x103c, 0x1973, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED),
 	/* ALC282 */
-	SND_PCI_QUIRK(0x103c, 0x21f8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x21f9, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x220d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x220e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2210, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x2211, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x2212, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x2213, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2214, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x2234, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x2235, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2236, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2237, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2238, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2239, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x2246, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x2247, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x2248, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x2249, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x224a, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x224b, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x224c, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x224d, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x2266, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x2267, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2268, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x2269, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x226a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x226b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x226c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x226d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x226e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x226f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x227a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x227b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x229e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x22a0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22b2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22b7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22bf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x22c0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x22c1, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x22c2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x22cd, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x22ce, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22cf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x22d0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x22da, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x22db, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x22dc, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x22fb, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x8004, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	/* ALC290 */
 	SND_PCI_QUIRK(0x103c, 0x221b, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x221c, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x221d, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x2220, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2221, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x2222, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x2223, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x2224, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2225, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2246, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2247, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
@@ -5017,8 +4742,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x2259, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x225a, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2260, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x2261, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x2262, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2263, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2264, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2265, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -5026,23 +4749,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x2273, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2277, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x2278, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
-	SND_PCI_QUIRK(0x103c, 0x227d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x227e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x227f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x2280, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x2281, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2282, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x2289, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x228a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x228b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x228c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x228d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x228e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c5, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x22c6, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
-	SND_PCI_QUIRK(0x103c, 0x22c3, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c4, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2334, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -5070,6 +4783,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x104d, 0x9099, "Sony VAIO S13", ALC275_FIXUP_SONY_DISABLE_AAMIX),
 	SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK),
 	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
+	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_BXBT2807_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
@@ -5085,12 +4799,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x220c, "Thinkpad T440s", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x220e, "Thinkpad T440p", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2210, "Thinkpad T540p", ALC292_FIXUP_TPT440_DOCK),
-	SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad T440", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
 	SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC),
+	SND_PCI_QUIRK(0x17aa, 0x501e, "Thinkpad L440", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
@@ -5173,28 +4888,58 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{}
 };
 
+#define ALC255_STANDARD_PINS \
+	{0x18, 0x411111f0}, \
+	{0x19, 0x411111f0}, \
+	{0x1a, 0x411111f0}, \
+	{0x1b, 0x411111f0}, \
+	{0x1e, 0x411111f0}
+
+#define ALC282_STANDARD_PINS \
+	{0x14, 0x90170110}, \
+	{0x18, 0x411111f0}, \
+	{0x1a, 0x411111f0}, \
+	{0x1b, 0x411111f0}, \
+	{0x1e, 0x411111f0}
+
+#define ALC290_STANDARD_PINS \
+	{0x12, 0x99a30130}, \
+	{0x13, 0x40000000}, \
+	{0x16, 0x411111f0}, \
+	{0x17, 0x411111f0}, \
+	{0x19, 0x411111f0}, \
+	{0x1b, 0x411111f0}, \
+	{0x1e, 0x411111f0}
+
+#define ALC292_STANDARD_PINS \
+	{0x14, 0x90170110}, \
+	{0x15, 0x0221401f}, \
+	{0x1a, 0x411111f0}, \
+	{0x1b, 0x411111f0}, \
+	{0x1d, 0x40700001}, \
+	{0x1e, 0x411111f0}
+
 static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
+		ALC255_STANDARD_PINS,
+		{0x12, 0x40300000},
+		{0x14, 0x90170110},
+		{0x17, 0x411111f0},
+		{0x1d, 0x40538029},
+		{0x21, 0x02211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC255_STANDARD_PINS,
 		{0x12, 0x90a60140},
 		{0x14, 0x90170110},
 		{0x17, 0x40000000},
-		{0x18, 0x411111f0},
-		{0x19, 0x411111f0},
-		{0x1a, 0x411111f0},
-		{0x1b, 0x411111f0},
 		{0x1d, 0x40700001},
-		{0x1e, 0x411111f0},
 		{0x21, 0x02211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC255_STANDARD_PINS,
 		{0x12, 0x90a60160},
 		{0x14, 0x90170120},
 		{0x17, 0x40000000},
-		{0x18, 0x411111f0},
-		{0x19, 0x411111f0},
-		{0x1a, 0x411111f0},
-		{0x1b, 0x411111f0},
 		{0x1d, 0x40700001},
-		{0x1e, 0x411111f0},
 		{0x21, 0x02211030}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60160},
@@ -5208,70 +4953,101 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x1e, 0x411111f0},
 		{0x21, 0x0321102f}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC255_STANDARD_PINS,
 		{0x12, 0x90a60160},
 		{0x14, 0x90170130},
 		{0x17, 0x40000000},
-		{0x18, 0x411111f0},
-		{0x19, 0x411111f0},
-		{0x1a, 0x411111f0},
-		{0x1b, 0x411111f0},
 		{0x1d, 0x40700001},
-		{0x1e, 0x411111f0},
 		{0x21, 0x02211040}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC255_STANDARD_PINS,
 		{0x12, 0x90a60160},
 		{0x14, 0x90170140},
 		{0x17, 0x40000000},
-		{0x18, 0x411111f0},
-		{0x19, 0x411111f0},
-		{0x1a, 0x411111f0},
-		{0x1b, 0x411111f0},
 		{0x1d, 0x40700001},
-		{0x1e, 0x411111f0},
 		{0x21, 0x02211050}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC255_STANDARD_PINS,
 		{0x12, 0x90a60170},
 		{0x14, 0x90170120},
 		{0x17, 0x40000000},
-		{0x18, 0x411111f0},
-		{0x19, 0x411111f0},
-		{0x1a, 0x411111f0},
-		{0x1b, 0x411111f0},
 		{0x1d, 0x40700001},
-		{0x1e, 0x411111f0},
 		{0x21, 0x02211030}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC255_STANDARD_PINS,
 		{0x12, 0x90a60170},
 		{0x14, 0x90170130},
 		{0x17, 0x40000000},
-		{0x18, 0x411111f0},
-		{0x19, 0x411111f0},
-		{0x1a, 0x411111f0},
-		{0x1b, 0x411111f0},
 		{0x1d, 0x40700001},
-		{0x1e, 0x411111f0},
 		{0x21, 0x02211040}),
+	SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED,
+		{0x12, 0x90a60140},
+		{0x13, 0x40000000},
+		{0x14, 0x90170110},
+		{0x15, 0x0421101f},
+		{0x16, 0x411111f0},
+		{0x17, 0x411111f0},
+		{0x18, 0x02811030},
+		{0x19, 0x411111f0},
+		{0x1a, 0x04a1103f},
+		{0x1b, 0x02011020},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0282, 0x103c, "HP 15 Touchsmart", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC282_STANDARD_PINS,
 		{0x12, 0x99a30130},
-		{0x14, 0x90170110},
 		{0x17, 0x40000000},
-		{0x18, 0x411111f0},
 		{0x19, 0x03a11020},
-		{0x1a, 0x411111f0},
-		{0x1b, 0x411111f0},
 		{0x1d, 0x40f41905},
-		{0x1e, 0x411111f0},
 		{0x21, 0x0321101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0282, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC282_STANDARD_PINS,
+		{0x12, 0x99a30130},
+		{0x17, 0x40020008},
+		{0x19, 0x03a11020},
+		{0x1d, 0x40e00001},
+		{0x21, 0x03211040}),
+	SND_HDA_PIN_QUIRK(0x10ec0282, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC282_STANDARD_PINS,
+		{0x12, 0x99a30130},
+		{0x17, 0x40000000},
+		{0x19, 0x03a11030},
+		{0x1d, 0x40e00001},
+		{0x21, 0x03211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0282, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC282_STANDARD_PINS,
+		{0x12, 0x99a30130},
+		{0x17, 0x40000000},
+		{0x19, 0x03a11030},
+		{0x1d, 0x40f00001},
+		{0x21, 0x03211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0282, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC282_STANDARD_PINS,
+		{0x12, 0x99a30130},
+		{0x17, 0x40000000},
+		{0x19, 0x04a11020},
+		{0x1d, 0x40f00001},
+		{0x21, 0x0421101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0282, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC282_STANDARD_PINS,
+		{0x12, 0x99a30130},
+		{0x17, 0x40000000},
+		{0x19, 0x03a11030},
+		{0x1d, 0x40f00001},
+		{0x21, 0x04211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0282, 0x103c, "HP", ALC269_FIXUP_HP_LINE1_MIC1_LED,
+		ALC282_STANDARD_PINS,
+		{0x12, 0x90a60140},
+		{0x17, 0x40000000},
+		{0x19, 0x04a11030},
+		{0x1d, 0x40f00001},
+		{0x21, 0x04211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0283, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC282_STANDARD_PINS,
 		{0x12, 0x90a60130},
-		{0x14, 0x90170110},
 		{0x17, 0x40020008},
-		{0x18, 0x411111f0},
 		{0x19, 0x411111f0},
-		{0x1a, 0x411111f0},
-		{0x1b, 0x411111f0},
 		{0x1d, 0x40e00001},
-		{0x1e, 0x411111f0},
 		{0x21, 0x0321101f}),
 	SND_HDA_PIN_QUIRK(0x10ec0283, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60160},
@@ -5284,42 +5060,97 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x1d, 0x40700001},
 		{0x1e, 0x411111f0},
 		{0x21, 0x02211030}),
+	SND_HDA_PIN_QUIRK(0x10ec0283, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC282_STANDARD_PINS,
+		{0x12, 0x90a60130},
+		{0x17, 0x40020008},
+		{0x19, 0x03a11020},
+		{0x1d, 0x40e00001},
+		{0x21, 0x0321101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0290, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC290_STANDARD_PINS,
+		{0x14, 0x411111f0},
+		{0x15, 0x04211040},
+		{0x18, 0x90170112},
+		{0x1a, 0x04a11020},
+		{0x1d, 0x4075812d}),
+	SND_HDA_PIN_QUIRK(0x10ec0290, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC290_STANDARD_PINS,
+		{0x14, 0x411111f0},
+		{0x15, 0x04211040},
+		{0x18, 0x90170110},
+		{0x1a, 0x04a11020},
+		{0x1d, 0x4075812d}),
+	SND_HDA_PIN_QUIRK(0x10ec0290, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC290_STANDARD_PINS,
+		{0x14, 0x411111f0},
+		{0x15, 0x0421101f},
+		{0x18, 0x411111f0},
+		{0x1a, 0x04a11020},
+		{0x1d, 0x4075812d}),
+	SND_HDA_PIN_QUIRK(0x10ec0290, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC290_STANDARD_PINS,
+		{0x14, 0x411111f0},
+		{0x15, 0x04211020},
+		{0x18, 0x411111f0},
+		{0x1a, 0x04a11040},
+		{0x1d, 0x4076a12d}),
+	SND_HDA_PIN_QUIRK(0x10ec0290, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC290_STANDARD_PINS,
+		{0x14, 0x90170110},
+		{0x15, 0x04211020},
+		{0x18, 0x411111f0},
+		{0x1a, 0x04a11040},
+		{0x1d, 0x4076a12d}),
+	SND_HDA_PIN_QUIRK(0x10ec0290, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC290_STANDARD_PINS,
+		{0x14, 0x90170110},
+		{0x15, 0x04211020},
+		{0x18, 0x411111f0},
+		{0x1a, 0x04a11020},
+		{0x1d, 0x4076a12d}),
+	SND_HDA_PIN_QUIRK(0x10ec0290, 0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1,
+		ALC290_STANDARD_PINS,
+		{0x14, 0x90170110},
+		{0x15, 0x0421101f},
+		{0x18, 0x411111f0},
+		{0x1a, 0x04a11020},
+		{0x1d, 0x4075812d}),
+	SND_HDA_PIN_QUIRK(0x10ec0292, 0x1028, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE,
+		ALC292_STANDARD_PINS,
+		{0x12, 0x90a60140},
+		{0x13, 0x411111f0},
+		{0x16, 0x01014020},
+		{0x18, 0x411111f0},
+		{0x19, 0x01a19030}),
+	SND_HDA_PIN_QUIRK(0x10ec0292, 0x1028, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE,
+		ALC292_STANDARD_PINS,
+		{0x12, 0x90a60140},
+		{0x13, 0x411111f0},
+		{0x16, 0x01014020},
+		{0x18, 0x02a19031},
+		{0x19, 0x01a1903e}),
 	SND_HDA_PIN_QUIRK(0x10ec0292, 0x1028, "Dell", ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
+		ALC292_STANDARD_PINS,
 		{0x12, 0x90a60140},
 		{0x13, 0x411111f0},
-		{0x14, 0x90170110},
-		{0x15, 0x0221401f},
 		{0x16, 0x411111f0},
 		{0x18, 0x411111f0},
-		{0x19, 0x411111f0},
-		{0x1a, 0x411111f0},
-		{0x1b, 0x411111f0},
-		{0x1d, 0x40700001},
-		{0x1e, 0x411111f0}),
+		{0x19, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC292_STANDARD_PINS,
 		{0x12, 0x40000000},
 		{0x13, 0x90a60140},
-		{0x14, 0x90170110},
-		{0x15, 0x0221401f},
 		{0x16, 0x21014020},
 		{0x18, 0x411111f0},
-		{0x19, 0x21a19030},
-		{0x1a, 0x411111f0},
-		{0x1b, 0x411111f0},
-		{0x1d, 0x40700001},
-		{0x1e, 0x411111f0}),
+		{0x19, 0x21a19030}),
 	SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC292_STANDARD_PINS,
 		{0x12, 0x40000000},
 		{0x13, 0x90a60140},
-		{0x14, 0x90170110},
-		{0x15, 0x0221401f},
 		{0x16, 0x411111f0},
 		{0x18, 0x411111f0},
-		{0x19, 0x411111f0},
-		{0x1a, 0x411111f0},
-		{0x1b, 0x411111f0},
-		{0x1d, 0x40700001},
-		{0x1e, 0x411111f0}),
+		{0x19, 0x411111f0}),
 	{}
 };
 
@@ -5342,10 +5173,8 @@ static void alc269_fill_coef(struct hda_codec *codec)
 	}
 
 	if ((alc_get_coef0(codec) & 0x00ff) == 0x017) {
-		val = alc_read_coef_idx(codec, 0x04);
 		/* Power up output pin */
-		if (val != -1)
-			alc_write_coef_idx(codec, 0x04, val | (1<<11));
+		alc_update_coef_idx(codec, 0x04, 0, 1<<11);
 	}
 
 	if ((alc_get_coef0(codec) & 0x00ff) == 0x018) {
@@ -5361,13 +5190,11 @@ static void alc269_fill_coef(struct hda_codec *codec)
 		}
 	}
 
-	val = alc_read_coef_idx(codec, 0xd); /* Class D */
-	if (val != -1)
-		alc_write_coef_idx(codec, 0xd, val | (1<<14));
+	/* Class D */
+	alc_update_coef_idx(codec, 0xd, 0, 1<<14);
 
-	val = alc_read_coef_idx(codec, 0x4); /* HP */
-	if (val != -1)
-		alc_write_coef_idx(codec, 0x4, val | (1<<11));
+	/* HP */
+	alc_update_coef_idx(codec, 0x4, 0, 1<<11);
 }
 
 /*
@@ -6012,7 +5839,7 @@ static const struct hda_fixup alc662_fixups[] = {
 	},
 	[ALC662_FIXUP_INV_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
-		.v.func = alc_fixup_inv_dmic_0x12,
+		.v.func = alc_fixup_inv_dmic,
 	},
 	[ALC668_FIXUP_DELL_XPS13] = {
 		.type = HDA_FIXUP_FUNC,
@@ -6247,16 +6074,14 @@ static const struct snd_hda_pin_quirk alc662_pin_fixup_tbl[] = {
 
 static void alc662_fill_coef(struct hda_codec *codec)
 {
-	int val, coef;
+	int coef;
 
 	coef = alc_get_coef0(codec);
 
 	switch (codec->vendor_id) {
 	case 0x10ec0662:
-		if ((coef & 0x00f0) == 0x0030) {
-			val = alc_read_coef_idx(codec, 0x4); /* EAPD Ctrl */
-			alc_write_coef_idx(codec, 0x4, val & ~(1<<10));
-		}
+		if ((coef & 0x00f0) == 0x0030)
+			alc_update_coef_idx(codec, 0x4, 1<<10, 0); /* EAPD Ctrl */
 		break;
 	case 0x10ec0272:
 	case 0x10ec0273:
@@ -6265,8 +6090,7 @@ static void alc662_fill_coef(struct hda_codec *codec)
 	case 0x10ec0670:
 	case 0x10ec0671:
 	case 0x10ec0672:
-		val = alc_read_coef_idx(codec, 0xd); /* EAPD Ctrl */
-		alc_write_coef_idx(codec, 0xd, val | (1<<14));
+		alc_update_coef_idx(codec, 0xd, 0, 1<<14); /* EAPD Ctrl */
 		break;
 	}
 }
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 98cd1908c039..4f6413e01c13 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -32,7 +32,6 @@
 #include <linux/module.h>
 #include <sound/core.h>
 #include <sound/jack.h>
-#include <sound/tlv.h>
 #include "hda_codec.h"
 #include "hda_local.h"
 #include "hda_auto_parser.h"
@@ -41,11 +40,6 @@
 #include "hda_generic.h"
 
 enum {
-	STAC_VREF_EVENT	= 8,
-	STAC_PWR_EVENT,
-};
-
-enum {
 	STAC_REF,
 	STAC_9200_OQO,
 	STAC_9200_DELL_D21,
@@ -487,7 +481,7 @@ static void stac_toggle_power_map(struct hda_codec *codec, hda_nid_t nid,
 
 /* update power bit per jack plug/unplug */
 static void jack_update_power(struct hda_codec *codec,
-			      struct hda_jack_tbl *jack)
+			      struct hda_jack_callback *jack)
 {
 	struct sigmatel_spec *spec = codec->spec;
 	int i;
@@ -495,9 +489,9 @@ static void jack_update_power(struct hda_codec *codec,
 	if (!spec->num_pwrs)
 		return;
 
-	if (jack && jack->nid) {
-		stac_toggle_power_map(codec, jack->nid,
-				      snd_hda_jack_detect(codec, jack->nid),
+	if (jack && jack->tbl->nid) {
+		stac_toggle_power_map(codec, jack->tbl->nid,
+				      snd_hda_jack_detect(codec, jack->tbl->nid),
 				      true);
 		return;
 	}
@@ -505,42 +499,19 @@ static void jack_update_power(struct hda_codec *codec,
 	/* update all jacks */
 	for (i = 0; i < spec->num_pwrs; i++) {
 		hda_nid_t nid = spec->pwr_nids[i];
-		jack = snd_hda_jack_tbl_get(codec, nid);
-		if (!jack || !jack->action)
+		if (!snd_hda_jack_tbl_get(codec, nid))
 			continue;
-		if (jack->action == STAC_PWR_EVENT ||
-		    jack->action <= HDA_GEN_LAST_EVENT)
-			stac_toggle_power_map(codec, nid,
-					      snd_hda_jack_detect(codec, nid),
-					      false);
+		stac_toggle_power_map(codec, nid,
+				      snd_hda_jack_detect(codec, nid),
+				      false);
 	}
 
 	snd_hda_codec_write(codec, codec->afg, 0, AC_VERB_IDT_SET_POWER_MAP,
 			    spec->power_map_bits);
 }
 
-static void stac_hp_automute(struct hda_codec *codec,
-				 struct hda_jack_tbl *jack)
-{
-	snd_hda_gen_hp_automute(codec, jack);
-	jack_update_power(codec, jack);
-}
-
-static void stac_line_automute(struct hda_codec *codec,
-				   struct hda_jack_tbl *jack)
-{
-	snd_hda_gen_line_automute(codec, jack);
-	jack_update_power(codec, jack);
-}
-
-static void stac_mic_autoswitch(struct hda_codec *codec,
-				struct hda_jack_tbl *jack)
-{
-	snd_hda_gen_mic_autoswitch(codec, jack);
-	jack_update_power(codec, jack);
-}
-
-static void stac_vref_event(struct hda_codec *codec, struct hda_jack_tbl *event)
+static void stac_vref_event(struct hda_codec *codec,
+			    struct hda_jack_callback *event)
 {
 	unsigned int data;
 
@@ -563,13 +534,10 @@ static void stac_init_power_map(struct hda_codec *codec)
 		hda_nid_t nid = spec->pwr_nids[i];
 		unsigned int def_conf = snd_hda_codec_get_pincfg(codec, nid);
 		def_conf = get_defcfg_connect(def_conf);
-		if (snd_hda_jack_tbl_get(codec, nid))
-			continue;
 		if (def_conf == AC_JACK_PORT_COMPLEX &&
 		    spec->vref_mute_led_nid != nid &&
 		    is_jack_detectable(codec, nid)) {
 			snd_hda_jack_detect_enable_callback(codec, nid,
-							    STAC_PWR_EVENT,
 							    jack_update_power);
 		} else {
 			if (def_conf == AC_JACK_PORT_NONE)
@@ -3020,7 +2988,7 @@ static void stac92hd71bxx_fixup_hp_m4(struct hda_codec *codec,
 				      const struct hda_fixup *fix, int action)
 {
 	struct sigmatel_spec *spec = codec->spec;
-	struct hda_jack_tbl *jack;
+	struct hda_jack_callback *jack;
 
 	if (action != HDA_FIXUP_ACT_PRE_PROBE)
 		return;
@@ -3028,11 +2996,9 @@ static void stac92hd71bxx_fixup_hp_m4(struct hda_codec *codec,
 	/* Enable VREF power saving on GPIO1 detect */
 	snd_hda_codec_write_cache(codec, codec->afg, 0,
 				  AC_VERB_SET_GPIO_UNSOLICITED_RSP_MASK, 0x02);
-	snd_hda_jack_detect_enable_callback(codec, codec->afg,
-					    STAC_VREF_EVENT,
-					    stac_vref_event);
-	jack = snd_hda_jack_tbl_get(codec, codec->afg);
-	if (jack)
+	jack = snd_hda_jack_detect_enable_callback(codec, codec->afg,
+						   stac_vref_event);
+	if (!IS_ERR(jack))
 		jack->private_data = 0x02;
 
 	spec->gpio_mask |= 0x02;
@@ -4044,7 +4010,7 @@ static void stac9205_fixup_dell_m43(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
 	struct sigmatel_spec *spec = codec->spec;
-	struct hda_jack_tbl *jack;
+	struct hda_jack_callback *jack;
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		snd_hda_apply_pincfgs(codec, dell_9205_m43_pin_configs);
@@ -4052,11 +4018,9 @@ static void stac9205_fixup_dell_m43(struct hda_codec *codec,
 		/* Enable unsol response for GPIO4/Dock HP connection */
 		snd_hda_codec_write_cache(codec, codec->afg, 0,
 			AC_VERB_SET_GPIO_UNSOLICITED_RSP_MASK, 0x10);
-		snd_hda_jack_detect_enable_callback(codec, codec->afg,
-						    STAC_VREF_EVENT,
-						    stac_vref_event);
-		jack = snd_hda_jack_tbl_get(codec, codec->afg);
-		if (jack)
+		jack = snd_hda_jack_detect_enable_callback(codec, codec->afg,
+							   stac_vref_event);
+		if (!IS_ERR(jack))
 			jack->private_data = 0x01;
 
 		spec->gpio_dir = 0x0b;
@@ -4219,17 +4183,11 @@ static int stac_parse_auto_config(struct hda_codec *codec)
 	spec->gen.pcm_capture_hook = stac_capture_pcm_hook;
 
 	spec->gen.automute_hook = stac_update_outputs;
-	spec->gen.hp_automute_hook = stac_hp_automute;
-	spec->gen.line_automute_hook = stac_line_automute;
-	spec->gen.mic_autoswitch_hook = stac_mic_autoswitch;
 
 	err = snd_hda_gen_parse_auto_config(codec, &spec->gen.autocfg);
 	if (err < 0)
 		return err;
 
-	/* minimum value is actually mute */
-	spec->gen.vmaster_tlv[3] |= TLV_DB_SCALE_MUTE;
-
 	/* setup analog beep controls */
 	if (spec->anabeep_nid > 0) {
 		err = stac_auto_create_beep_ctls(codec,
@@ -4276,16 +4234,8 @@ static int stac_parse_auto_config(struct hda_codec *codec)
 			return err;
 	}
 
-	return 0;
-}
-
-static int stac_build_controls(struct hda_codec *codec)
-{
-	int err = snd_hda_gen_build_controls(codec);
-
-	if (err < 0)
-		return err;
 	stac_init_power_map(codec);
+
 	return 0;
 }
 
@@ -4399,7 +4349,7 @@ static int stac_suspend(struct hda_codec *codec)
 #endif /* CONFIG_PM */
 
 static const struct hda_codec_ops stac_patch_ops = {
-	.build_controls = stac_build_controls,
+	.build_controls = snd_hda_gen_build_controls,
 	.build_pcms = snd_hda_gen_build_pcms,
 	.init = stac_init,
 	.free = stac_free,
@@ -4420,6 +4370,7 @@ static int alloc_stac_spec(struct hda_codec *codec)
 	snd_hda_gen_spec_init(&spec->gen);
 	codec->spec = spec;
 	codec->no_trigger_sense = 1; /* seems common with STAC/IDT codecs */
+	spec->gen.dac_min_mute = true;
 	return 0;
 }
 
diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index 778166259b3e..6c206b6c8d65 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -118,7 +118,6 @@ static void via_playback_pcm_hook(struct hda_pcm_stream *hinfo,
 				  struct hda_codec *codec,
 				  struct snd_pcm_substream *substream,
 				  int action);
-static void via_hp_automute(struct hda_codec *codec, struct hda_jack_tbl *tbl);
 
 static struct via_spec *via_new_spec(struct hda_codec *codec)
 {
@@ -575,25 +574,12 @@ static const struct snd_kcontrol_new vt1708_jack_detect_ctl[] = {
 	{} /* terminator */
 };
 
-static void via_hp_automute(struct hda_codec *codec, struct hda_jack_tbl *tbl)
+static void via_jack_powerstate_event(struct hda_codec *codec,
+				      struct hda_jack_callback *tbl)
 {
 	set_widgets_power_state(codec);
-	snd_hda_gen_hp_automute(codec, tbl);
 }
 
-static void via_line_automute(struct hda_codec *codec, struct hda_jack_tbl *tbl)
-{
-	set_widgets_power_state(codec);
-	snd_hda_gen_line_automute(codec, tbl);
-}
-
-static void via_jack_powerstate_event(struct hda_codec *codec, struct hda_jack_tbl *tbl)
-{
-	set_widgets_power_state(codec);
-}
-
-#define VIA_JACK_EVENT	(HDA_GEN_LAST_EVENT + 1)
-
 static void via_set_jack_unsol_events(struct hda_codec *codec)
 {
 	struct via_spec *spec = codec->spec;
@@ -601,25 +587,17 @@ static void via_set_jack_unsol_events(struct hda_codec *codec)
 	hda_nid_t pin;
 	int i;
 
-	spec->gen.hp_automute_hook = via_hp_automute;
-	if (cfg->speaker_pins[0])
-		spec->gen.line_automute_hook = via_line_automute;
-
 	for (i = 0; i < cfg->line_outs; i++) {
 		pin = cfg->line_out_pins[i];
-		if (pin && !snd_hda_jack_tbl_get(codec, pin) &&
-		    is_jack_detectable(codec, pin))
+		if (pin && is_jack_detectable(codec, pin))
 			snd_hda_jack_detect_enable_callback(codec, pin,
-							    VIA_JACK_EVENT,
 							    via_jack_powerstate_event);
 	}
 
 	for (i = 0; i < cfg->num_inputs; i++) {
 		pin = cfg->line_out_pins[i];
-		if (pin && !snd_hda_jack_tbl_get(codec, pin) &&
-		    is_jack_detectable(codec, pin))
+		if (pin && is_jack_detectable(codec, pin))
 			snd_hda_jack_detect_enable_callback(codec, pin,
-							    VIA_JACK_EVENT,
 							    via_jack_powerstate_event);
 	}
 }
diff --git a/sound/pci/ice1712/ice1712.c b/sound/pci/ice1712/ice1712.c
index 87f7fc41d4f2..206ed2cbcef9 100644
--- a/sound/pci/ice1712/ice1712.c
+++ b/sound/pci/ice1712/ice1712.c
@@ -2528,7 +2528,7 @@ static int snd_ice1712_free(struct snd_ice1712 *ice)
 	if (!ice->port)
 		goto __hw_end;
 	/* mask all interrupts */
-	outb(0xc0, ICEMT(ice, IRQ));
+	outb(ICE1712_MULTI_CAPTURE | ICE1712_MULTI_PLAYBACK, ICEMT(ice, IRQ));
 	outb(0xff, ICEREG(ice, IRQMASK));
 	/* --- */
 __hw_end:
diff --git a/sound/pci/lx6464es/lx6464es.c b/sound/pci/lx6464es/lx6464es.c
index a671f0865f71..601315a1f58f 100644
--- a/sound/pci/lx6464es/lx6464es.c
+++ b/sound/pci/lx6464es/lx6464es.c
@@ -279,7 +279,6 @@ static snd_pcm_uframes_t lx_pcm_stream_pointer(struct snd_pcm_substream
 {
 	struct lx6464es *chip = snd_pcm_substream_chip(substream);
 	snd_pcm_uframes_t pos;
-	unsigned long flags;
 	int is_capture = (substream->stream == SNDRV_PCM_STREAM_CAPTURE);
 
 	struct lx_stream *lx_stream = is_capture ? &chip->capture_stream :
@@ -287,9 +286,9 @@ static snd_pcm_uframes_t lx_pcm_stream_pointer(struct snd_pcm_substream
 
 	dev_dbg(chip->card->dev, "->lx_pcm_stream_pointer\n");
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	pos = lx_stream->frame_pos * substream->runtime->period_size;
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 
 	dev_dbg(chip->card->dev, "stream_pointer at %ld\n", pos);
 	return pos;
@@ -485,8 +484,8 @@ static void lx_trigger_stop(struct lx6464es *chip, struct lx_stream *lx_stream)
 
 }
 
-static void lx_trigger_tasklet_dispatch_stream(struct lx6464es *chip,
-					       struct lx_stream *lx_stream)
+static void lx_trigger_dispatch_stream(struct lx6464es *chip,
+				       struct lx_stream *lx_stream)
 {
 	switch (lx_stream->status) {
 	case LX_STREAM_STATUS_SCHEDULE_RUN:
@@ -502,24 +501,12 @@ static void lx_trigger_tasklet_dispatch_stream(struct lx6464es *chip,
 	}
 }
 
-static void lx_trigger_tasklet(unsigned long data)
-{
-	struct lx6464es *chip = (struct lx6464es *)data;
-	unsigned long flags;
-
-	dev_dbg(chip->card->dev, "->lx_trigger_tasklet\n");
-
-	spin_lock_irqsave(&chip->lock, flags);
-	lx_trigger_tasklet_dispatch_stream(chip, &chip->capture_stream);
-	lx_trigger_tasklet_dispatch_stream(chip, &chip->playback_stream);
-	spin_unlock_irqrestore(&chip->lock, flags);
-}
-
 static int lx_pcm_trigger_dispatch(struct lx6464es *chip,
 				   struct lx_stream *lx_stream, int cmd)
 {
 	int err = 0;
 
+	mutex_lock(&chip->lock);
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 		lx_stream->status = LX_STREAM_STATUS_SCHEDULE_RUN;
@@ -533,9 +520,12 @@ static int lx_pcm_trigger_dispatch(struct lx6464es *chip,
 		err = -EINVAL;
 		goto exit;
 	}
-	tasklet_schedule(&chip->trigger_tasklet);
+
+	lx_trigger_dispatch_stream(chip, &chip->capture_stream);
+	lx_trigger_dispatch_stream(chip, &chip->playback_stream);
 
 exit:
+	mutex_unlock(&chip->lock);
 	return err;
 }
 
@@ -861,6 +851,7 @@ static int lx_pcm_create(struct lx6464es *chip)
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &lx_ops_capture);
 
 	pcm->info_flags = 0;
+	pcm->nonatomic = true;
 	strcpy(pcm->name, card_name);
 
 	err = snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
@@ -1009,15 +1000,9 @@ static int snd_lx6464es_create(struct snd_card *card,
 	chip->irq = -1;
 
 	/* initialize synchronization structs */
-	spin_lock_init(&chip->lock);
-	spin_lock_init(&chip->msg_lock);
+	mutex_init(&chip->lock);
+	mutex_init(&chip->msg_lock);
 	mutex_init(&chip->setup_mutex);
-	tasklet_init(&chip->trigger_tasklet, lx_trigger_tasklet,
-		     (unsigned long)chip);
-	tasklet_init(&chip->tasklet_capture, lx_tasklet_capture,
-		     (unsigned long)chip);
-	tasklet_init(&chip->tasklet_playback, lx_tasklet_playback,
-		     (unsigned long)chip);
 
 	/* request resources */
 	err = pci_request_regions(pci, card_name);
@@ -1032,8 +1017,8 @@ static int snd_lx6464es_create(struct snd_card *card,
 	/* dsp port */
 	chip->port_dsp_bar = pci_ioremap_bar(pci, 2);
 
-	err = request_irq(pci->irq, lx_interrupt, IRQF_SHARED,
-			  KBUILD_MODNAME, chip);
+	err = request_threaded_irq(pci->irq, lx_interrupt, lx_threaded_irq,
+				   IRQF_SHARED, KBUILD_MODNAME, chip);
 	if (err) {
 		dev_err(card->dev, "unable to grab IRQ %d\n", pci->irq);
 		goto request_irq_failed;
diff --git a/sound/pci/lx6464es/lx6464es.h b/sound/pci/lx6464es/lx6464es.h
index 6792eda9c9a5..1bec187d772f 100644
--- a/sound/pci/lx6464es/lx6464es.h
+++ b/sound/pci/lx6464es/lx6464es.h
@@ -71,14 +71,10 @@ struct lx6464es {
 
 	u8			mac_address[6];
 
-	spinlock_t		lock;        /* interrupt spinlock */
+	struct mutex		lock;        /* interrupt lock */
 	struct mutex            setup_mutex; /* mutex used in hw_params, open
 					      * and close */
 
-	struct tasklet_struct   trigger_tasklet; /* trigger tasklet */
-	struct tasklet_struct   tasklet_capture;
-	struct tasklet_struct   tasklet_playback;
-
 	/* ports */
 	unsigned long		port_plx;	   /* io port (size=256) */
 	void __iomem           *port_plx_remapped; /* remapped plx port */
@@ -87,8 +83,9 @@ struct lx6464es {
 						    * size=8K) */
 
 	/* messaging */
-	spinlock_t		msg_lock;          /* message spinlock */
+	struct mutex		msg_lock;          /* message lock */
 	struct lx_rmh           rmh;
+	u32			irqsrc;
 
 	/* configuration */
 	uint			freq_ratio : 2;
diff --git a/sound/pci/lx6464es/lx_core.c b/sound/pci/lx6464es/lx_core.c
index e8f38e5df10a..f3d62020ef66 100644
--- a/sound/pci/lx6464es/lx_core.c
+++ b/sound/pci/lx6464es/lx_core.c
@@ -332,27 +332,25 @@ polling_successful:
 int lx_dsp_get_version(struct lx6464es *chip, u32 *rdsp_version)
 {
 	u16 ret;
-	unsigned long flags;
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 
 	lx_message_init(&chip->rmh, CMD_01_GET_SYS_CFG);
 	ret = lx_message_send_atomic(chip, &chip->rmh);
 
 	*rdsp_version = chip->rmh.stat[1];
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return ret;
 }
 
 int lx_dsp_get_clock_frequency(struct lx6464es *chip, u32 *rfreq)
 {
 	u16 ret = 0;
-	unsigned long flags;
 	u32 freq_raw = 0;
 	u32 freq = 0;
 	u32 frequency = 0;
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 
 	lx_message_init(&chip->rmh, CMD_01_GET_SYS_CFG);
 	ret = lx_message_send_atomic(chip, &chip->rmh);
@@ -370,7 +368,7 @@ int lx_dsp_get_clock_frequency(struct lx6464es *chip, u32 *rfreq)
 			frequency = 48000;
 	}
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 
 	*rfreq = frequency * chip->freq_ratio;
 
@@ -398,25 +396,23 @@ int lx_dsp_get_mac(struct lx6464es *chip)
 
 int lx_dsp_set_granularity(struct lx6464es *chip, u32 gran)
 {
-	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 
 	lx_message_init(&chip->rmh, CMD_02_SET_GRANULARITY);
 	chip->rmh.cmd[0] |= gran;
 
 	ret = lx_message_send_atomic(chip, &chip->rmh);
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return ret;
 }
 
 int lx_dsp_read_async_events(struct lx6464es *chip, u32 *data)
 {
-	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 
 	lx_message_init(&chip->rmh, CMD_04_GET_EVENT);
 	chip->rmh.stat_len = 9;	/* we don't necessarily need the full length */
@@ -426,7 +422,7 @@ int lx_dsp_read_async_events(struct lx6464es *chip, u32 *data)
 	if (!ret)
 		memcpy(data, chip->rmh.stat, chip->rmh.stat_len * sizeof(u32));
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return ret;
 }
 
@@ -440,18 +436,16 @@ int lx_pipe_allocate(struct lx6464es *chip, u32 pipe, int is_capture,
 		     int channels)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_06_ALLOCATE_PIPE);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
 	chip->rmh.cmd[0] |= channels;
 
 	err = lx_message_send_atomic(chip, &chip->rmh);
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 
 	if (err != 0)
 		dev_err(chip->card->dev, "could not allocate pipe\n");
@@ -462,17 +456,15 @@ int lx_pipe_allocate(struct lx6464es *chip, u32 pipe, int is_capture,
 int lx_pipe_release(struct lx6464es *chip, u32 pipe, int is_capture)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_07_RELEASE_PIPE);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
 
 	err = lx_message_send_atomic(chip, &chip->rmh);
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 
 	return err;
 }
@@ -481,8 +473,6 @@ int lx_buffer_ask(struct lx6464es *chip, u32 pipe, int is_capture,
 		  u32 *r_needed, u32 *r_freed, u32 *size_array)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
 #ifdef CONFIG_SND_DEBUG
@@ -493,7 +483,7 @@ int lx_buffer_ask(struct lx6464es *chip, u32 pipe, int is_capture,
 	*r_needed = 0;
 	*r_freed = 0;
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_08_ASK_BUFFERS);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
@@ -527,7 +517,7 @@ int lx_buffer_ask(struct lx6464es *chip, u32 pipe, int is_capture,
 		}
 	}
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
@@ -535,36 +525,32 @@ int lx_buffer_ask(struct lx6464es *chip, u32 pipe, int is_capture,
 int lx_pipe_stop(struct lx6464es *chip, u32 pipe, int is_capture)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_09_STOP_PIPE);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
 
 	err = lx_message_send_atomic(chip, &chip->rmh);
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
 static int lx_pipe_toggle_state(struct lx6464es *chip, u32 pipe, int is_capture)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_0B_TOGGLE_PIPE_STATE);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
 
 	err = lx_message_send_atomic(chip, &chip->rmh);
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
@@ -600,11 +586,9 @@ int lx_pipe_sample_count(struct lx6464es *chip, u32 pipe, int is_capture,
 			 u64 *rsample_count)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_0A_GET_PIPE_SPL_COUNT);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
@@ -621,18 +605,16 @@ int lx_pipe_sample_count(struct lx6464es *chip, u32 pipe, int is_capture,
 			+ chip->rmh.stat[1]; /* lo part */
 	}
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
 int lx_pipe_state(struct lx6464es *chip, u32 pipe, int is_capture, u16 *rstate)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_0A_GET_PIPE_SPL_COUNT);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
@@ -644,7 +626,7 @@ int lx_pipe_state(struct lx6464es *chip, u32 pipe, int is_capture, u16 *rstate)
 	else
 		*rstate = (chip->rmh.stat[0] >> PSTATE_OFFSET) & 0x0F;
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
@@ -686,18 +668,16 @@ int lx_stream_set_state(struct lx6464es *chip, u32 pipe,
 			       int is_capture, enum stream_state_t state)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_13_SET_STREAM_STATE);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
 	chip->rmh.cmd[0] |= state;
 
 	err = lx_message_send_atomic(chip, &chip->rmh);
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 
 	return err;
 }
@@ -706,17 +686,14 @@ int lx_stream_set_format(struct lx6464es *chip, struct snd_pcm_runtime *runtime,
 			 u32 pipe, int is_capture)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
-
 	u32 channels = runtime->channels;
 
 	if (runtime->channels != channels)
 		dev_err(chip->card->dev, "channel count mismatch: %d vs %d",
 			   runtime->channels, channels);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_0C_DEF_STREAM);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
@@ -732,7 +709,7 @@ int lx_stream_set_format(struct lx6464es *chip, struct snd_pcm_runtime *runtime,
 	chip->rmh.cmd[0] |= channels-1;
 
 	err = lx_message_send_atomic(chip, &chip->rmh);
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 
 	return err;
 }
@@ -741,11 +718,9 @@ int lx_stream_state(struct lx6464es *chip, u32 pipe, int is_capture,
 		    int *rstate)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_0E_GET_STREAM_SPL_COUNT);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
@@ -754,7 +729,7 @@ int lx_stream_state(struct lx6464es *chip, u32 pipe, int is_capture,
 
 	*rstate = (chip->rmh.stat[0] & SF_START) ? START_STATE : PAUSE_STATE;
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
@@ -762,11 +737,9 @@ int lx_stream_sample_position(struct lx6464es *chip, u32 pipe, int is_capture,
 			      u64 *r_bytepos)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_0E_GET_STREAM_SPL_COUNT);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
@@ -777,7 +750,7 @@ int lx_stream_sample_position(struct lx6464es *chip, u32 pipe, int is_capture,
 		      << 32)	     /* hi part */
 		+ chip->rmh.stat[1]; /* lo part */
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
@@ -787,11 +760,9 @@ int lx_buffer_give(struct lx6464es *chip, u32 pipe, int is_capture,
 		   u32 *r_buffer_index)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_0F_UPDATE_BUFFER);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
@@ -828,7 +799,7 @@ int lx_buffer_give(struct lx6464es *chip, u32 pipe, int is_capture,
 			"lx_buffer_give EB_CMD_REFUSED\n");
 
  done:
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
@@ -836,11 +807,9 @@ int lx_buffer_free(struct lx6464es *chip, u32 pipe, int is_capture,
 		   u32 *r_buffer_size)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_11_CANCEL_BUFFER);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
@@ -852,7 +821,7 @@ int lx_buffer_free(struct lx6464es *chip, u32 pipe, int is_capture,
 	if (err == 0)
 		*r_buffer_size = chip->rmh.stat[0]  & MASK_DATA_SIZE;
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
@@ -860,11 +829,9 @@ int lx_buffer_cancel(struct lx6464es *chip, u32 pipe, int is_capture,
 		     u32 buffer_index)
 {
 	int err;
-	unsigned long flags;
-
 	u32 pipe_cmd = PIPE_INFO_TO_CMD(is_capture, pipe);
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_11_CANCEL_BUFFER);
 
 	chip->rmh.cmd[0] |= pipe_cmd;
@@ -872,7 +839,7 @@ int lx_buffer_cancel(struct lx6464es *chip, u32 pipe, int is_capture,
 
 	err = lx_message_send_atomic(chip, &chip->rmh);
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
@@ -885,12 +852,10 @@ int lx_buffer_cancel(struct lx6464es *chip, u32 pipe, int is_capture,
 int lx_level_unmute(struct lx6464es *chip, int is_capture, int unmute)
 {
 	int err;
-	unsigned long flags;
-
 	/* bit set to 1: channel muted */
 	u64 mute_mask = unmute ? 0 : 0xFFFFFFFFFFFFFFFFLLU;
 
-	spin_lock_irqsave(&chip->msg_lock, flags);
+	mutex_lock(&chip->msg_lock);
 	lx_message_init(&chip->rmh, CMD_0D_SET_MUTE);
 
 	chip->rmh.cmd[0] |= PIPE_INFO_TO_CMD(is_capture, 0);
@@ -904,7 +869,7 @@ int lx_level_unmute(struct lx6464es *chip, int is_capture, int unmute)
 
 	err = lx_message_send_atomic(chip, &chip->rmh);
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
@@ -931,10 +896,9 @@ int lx_level_peaks(struct lx6464es *chip, int is_capture, int channels,
 		   u32 *r_levels)
 {
 	int err = 0;
-	unsigned long flags;
 	int i;
-	spin_lock_irqsave(&chip->msg_lock, flags);
 
+	mutex_lock(&chip->msg_lock);
 	for (i = 0; i < channels; i += 4) {
 		u32 s0, s1, s2, s3;
 
@@ -959,7 +923,7 @@ int lx_level_peaks(struct lx6464es *chip, int is_capture, int channels,
 		r_levels += 4;
 	}
 
-	spin_unlock_irqrestore(&chip->msg_lock, flags);
+	mutex_unlock(&chip->msg_lock);
 	return err;
 }
 
@@ -1075,7 +1039,6 @@ static int lx_interrupt_request_new_buffer(struct lx6464es *chip,
 	struct snd_pcm_substream *substream = lx_stream->stream;
 	const unsigned int is_capture = lx_stream->is_capture;
 	int err;
-	unsigned long flags;
 
 	const u32 channels = substream->runtime->channels;
 	const u32 bytes_per_frame = channels * 3;
@@ -1095,7 +1058,7 @@ static int lx_interrupt_request_new_buffer(struct lx6464es *chip,
 
 	dev_dbg(chip->card->dev, "->lx_interrupt_request_new_buffer\n");
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 
 	err = lx_buffer_ask(chip, 0, is_capture, &needed, &freed, size_array);
 	dev_dbg(chip->card->dev,
@@ -1109,85 +1072,28 @@ static int lx_interrupt_request_new_buffer(struct lx6464es *chip,
 		    buffer_index, (unsigned long)buf, period_bytes);
 
 	lx_stream->frame_pos = next_pos;
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 
 	return err;
 }
 
-void lx_tasklet_playback(unsigned long data)
-{
-	struct lx6464es *chip = (struct lx6464es *)data;
-	struct lx_stream *lx_stream = &chip->playback_stream;
-	int err;
-
-	dev_dbg(chip->card->dev, "->lx_tasklet_playback\n");
-
-	err = lx_interrupt_request_new_buffer(chip, lx_stream);
-	if (err < 0)
-		dev_err(chip->card->dev,
-			   "cannot request new buffer for playback\n");
-
-	snd_pcm_period_elapsed(lx_stream->stream);
-}
-
-void lx_tasklet_capture(unsigned long data)
-{
-	struct lx6464es *chip = (struct lx6464es *)data;
-	struct lx_stream *lx_stream = &chip->capture_stream;
-	int err;
-
-	dev_dbg(chip->card->dev, "->lx_tasklet_capture\n");
-	err = lx_interrupt_request_new_buffer(chip, lx_stream);
-	if (err < 0)
-		dev_err(chip->card->dev,
-			   "cannot request new buffer for capture\n");
-
-	snd_pcm_period_elapsed(lx_stream->stream);
-}
-
-
-
-static int lx_interrupt_handle_audio_transfer(struct lx6464es *chip,
-					      u64 notified_in_pipe_mask,
-					      u64 notified_out_pipe_mask)
-{
-	int err = 0;
-
-	if (notified_in_pipe_mask) {
-		dev_dbg(chip->card->dev,
-			"requesting audio transfer for capture\n");
-		tasklet_hi_schedule(&chip->tasklet_capture);
-	}
-
-	if (notified_out_pipe_mask) {
-		dev_dbg(chip->card->dev,
-			"requesting audio transfer for playback\n");
-		tasklet_hi_schedule(&chip->tasklet_playback);
-	}
-
-	return err;
-}
-
-
 irqreturn_t lx_interrupt(int irq, void *dev_id)
 {
 	struct lx6464es *chip = dev_id;
 	int async_pending, async_escmd;
 	u32 irqsrc;
-
-	spin_lock(&chip->lock);
+	bool wake_thread = false;
 
 	dev_dbg(chip->card->dev,
 		"**************************************************\n");
 
 	if (!lx_interrupt_ack(chip, &irqsrc, &async_pending, &async_escmd)) {
-		spin_unlock(&chip->lock);
 		dev_dbg(chip->card->dev, "IRQ_NONE\n");
 		return IRQ_NONE; /* this device did not cause the interrupt */
 	}
 
 	if (irqsrc & MASK_SYS_STATUS_CMD_DONE)
-		goto exit;
+		return IRQ_HANDLED;
 
 	if (irqsrc & MASK_SYS_STATUS_EOBI)
 		dev_dbg(chip->card->dev, "interrupt: EOBI\n");
@@ -1202,27 +1108,8 @@ irqreturn_t lx_interrupt(int irq, void *dev_id)
 		dev_dbg(chip->card->dev, "interrupt: ORUN\n");
 
 	if (async_pending) {
-		u64 notified_in_pipe_mask = 0;
-		u64 notified_out_pipe_mask = 0;
-		int freq_changed;
-		int err;
-
-		/* handle async events */
-		err = lx_interrupt_handle_async_events(chip, irqsrc,
-						       &freq_changed,
-						       &notified_in_pipe_mask,
-						       &notified_out_pipe_mask);
-		if (err)
-			dev_err(chip->card->dev,
-				   "error handling async events\n");
-
-		err = lx_interrupt_handle_audio_transfer(chip,
-							 notified_in_pipe_mask,
-							 notified_out_pipe_mask
-			);
-		if (err)
-			dev_err(chip->card->dev,
-				   "error during audio transfer\n");
+		wake_thread = true;
+		chip->irqsrc = irqsrc;
 	}
 
 	if (async_escmd) {
@@ -1235,9 +1122,50 @@ irqreturn_t lx_interrupt(int irq, void *dev_id)
 		dev_dbg(chip->card->dev, "interrupt requests escmd handling\n");
 	}
 
-exit:
-	spin_unlock(&chip->lock);
-	return IRQ_HANDLED;	/* this device caused the interrupt */
+	return wake_thread ? IRQ_WAKE_THREAD : IRQ_HANDLED;
+}
+
+irqreturn_t lx_threaded_irq(int irq, void *dev_id)
+{
+	struct lx6464es *chip = dev_id;
+	u64 notified_in_pipe_mask = 0;
+	u64 notified_out_pipe_mask = 0;
+	int freq_changed;
+	int err;
+
+	/* handle async events */
+	err = lx_interrupt_handle_async_events(chip, chip->irqsrc,
+					       &freq_changed,
+					       &notified_in_pipe_mask,
+					       &notified_out_pipe_mask);
+	if (err)
+		dev_err(chip->card->dev, "error handling async events\n");
+
+	if (notified_in_pipe_mask) {
+		struct lx_stream *lx_stream = &chip->capture_stream;
+
+		dev_dbg(chip->card->dev,
+			"requesting audio transfer for capture\n");
+		err = lx_interrupt_request_new_buffer(chip, lx_stream);
+		if (err < 0)
+			dev_err(chip->card->dev,
+				"cannot request new buffer for capture\n");
+		snd_pcm_period_elapsed(lx_stream->stream);
+	}
+
+	if (notified_out_pipe_mask) {
+		struct lx_stream *lx_stream = &chip->playback_stream;
+
+		dev_dbg(chip->card->dev,
+			"requesting audio transfer for playback\n");
+		err = lx_interrupt_request_new_buffer(chip, lx_stream);
+		if (err < 0)
+			dev_err(chip->card->dev,
+				"cannot request new buffer for playback\n");
+		snd_pcm_period_elapsed(lx_stream->stream);
+	}
+
+	return IRQ_HANDLED;
 }
 
 
diff --git a/sound/pci/lx6464es/lx_core.h b/sound/pci/lx6464es/lx_core.h
index 5ec5e04da1a5..0cc140ca98e3 100644
--- a/sound/pci/lx6464es/lx_core.h
+++ b/sound/pci/lx6464es/lx_core.h
@@ -181,12 +181,10 @@ int lx_level_peaks(struct lx6464es *chip, int is_capture, int channels,
 
 /* interrupt handling */
 irqreturn_t lx_interrupt(int irq, void *dev_id);
+irqreturn_t lx_threaded_irq(int irq, void *dev_id);
 void lx_irq_enable(struct lx6464es *chip);
 void lx_irq_disable(struct lx6464es *chip);
 
-void lx_tasklet_capture(unsigned long data);
-void lx_tasklet_playback(unsigned long data);
-
 
 /* Stream Format Header Defines (for LIN and IEEE754) */
 #define HEADER_FMT_BASE		HEADER_FMT_BASE_LIN
diff --git a/sound/pci/mixart/mixart.c b/sound/pci/mixart/mixart.c
index 75fc342cff2a..1faf47e81570 100644
--- a/sound/pci/mixart/mixart.c
+++ b/sound/pci/mixart/mixart.c
@@ -986,6 +986,7 @@ static int snd_mixart_pcm_analog(struct snd_mixart *chip)
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_mixart_capture_ops);
 
 	pcm->info_flags = 0;
+	pcm->nonatomic = true;
 	strcpy(pcm->name, name);
 
 	preallocate_buffers(chip, pcm);
@@ -1018,6 +1019,7 @@ static int snd_mixart_pcm_digital(struct snd_mixart *chip)
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_mixart_capture_ops);
 
 	pcm->info_flags = 0;
+	pcm->nonatomic = true;
 	strcpy(pcm->name, name);
 
 	preallocate_buffers(chip, pcm);
@@ -1303,8 +1305,9 @@ static int snd_mixart_probe(struct pci_dev *pci,
 		}
 	}
 
-	if (request_irq(pci->irq, snd_mixart_interrupt, IRQF_SHARED,
-			KBUILD_MODNAME, mgr)) {
+	if (request_threaded_irq(pci->irq, snd_mixart_interrupt,
+				 snd_mixart_threaded_irq, IRQF_SHARED,
+				 KBUILD_MODNAME, mgr)) {
 		dev_err(&pci->dev, "unable to grab IRQ %d\n", pci->irq);
 		snd_mixart_free(mgr);
 		return -EBUSY;
@@ -1314,24 +1317,18 @@ static int snd_mixart_probe(struct pci_dev *pci,
 	sprintf(mgr->shortname, "Digigram miXart");
 	sprintf(mgr->longname, "%s at 0x%lx & 0x%lx, irq %i", mgr->shortname, mgr->mem[0].phys, mgr->mem[1].phys, mgr->irq);
 
-	/* ISR spinlock  */
-	spin_lock_init(&mgr->lock);
-
 	/* init mailbox  */
 	mgr->msg_fifo_readptr = 0;
 	mgr->msg_fifo_writeptr = 0;
 
-	spin_lock_init(&mgr->msg_lock);
-	mutex_init(&mgr->msg_mutex);
+	mutex_init(&mgr->lock);
+	mutex_init(&mgr->msg_lock);
 	init_waitqueue_head(&mgr->msg_sleep);
 	atomic_set(&mgr->msg_processed, 0);
 
 	/* init setup mutex*/
 	mutex_init(&mgr->setup_mutex);
 
-	/* init message taslket */
-	tasklet_init(&mgr->msg_taskq, snd_mixart_msg_tasklet, (unsigned long) mgr);
-
 	/* card assignment */
 	mgr->num_cards = MIXART_MAX_CARDS; /* 4  FIXME: configurable? */
 	for (i = 0; i < mgr->num_cards; i++) {
diff --git a/sound/pci/mixart/mixart.h b/sound/pci/mixart/mixart.h
index 561634d5c007..0cc17e0ea34a 100644
--- a/sound/pci/mixart/mixart.h
+++ b/sound/pci/mixart/mixart.h
@@ -78,22 +78,18 @@ struct mixart_mgr {
 	char shortname[32];         /* short name of this soundcard */
 	char longname[80];          /* name of this soundcard */
 
-	/* message tasklet */
-	struct tasklet_struct msg_taskq;
-
 	/* one and only blocking message or notification may be pending  */
 	u32 pending_event;
 	wait_queue_head_t msg_sleep;
 
-	/* messages stored for tasklet */
+	/* messages fifo */
 	u32 msg_fifo[MSG_FIFO_SIZE];
 	int msg_fifo_readptr;
 	int msg_fifo_writeptr;
 	atomic_t msg_processed;       /* number of messages to be processed in takslet */
 
-	spinlock_t lock;              /* interrupt spinlock */
-	spinlock_t msg_lock;          /* mailbox spinlock */
-	struct mutex msg_mutex;   /* mutex for blocking_requests */
+	struct mutex lock;              /* interrupt lock */
+	struct mutex msg_lock;		/* mailbox lock */
 
 	struct mutex setup_mutex; /* mutex used in hw_params, open and close */
 
diff --git a/sound/pci/mixart/mixart_core.c b/sound/pci/mixart/mixart_core.c
index 84f67450924e..fe80313674d9 100644
--- a/sound/pci/mixart/mixart_core.c
+++ b/sound/pci/mixart/mixart_core.c
@@ -76,7 +76,6 @@ static int retrieve_msg_frame(struct mixart_mgr *mgr, u32 *msg_frame)
 static int get_msg(struct mixart_mgr *mgr, struct mixart_msg *resp,
 		   u32 msg_frame_address )
 {
-	unsigned long flags;
 	u32  headptr;
 	u32  size;
 	int  err;
@@ -84,7 +83,7 @@ static int get_msg(struct mixart_mgr *mgr, struct mixart_msg *resp,
 	unsigned int i;
 #endif
 
-	spin_lock_irqsave(&mgr->msg_lock, flags);
+	mutex_lock(&mgr->msg_lock);
 	err = 0;
 
 	/* copy message descriptor from miXart to driver */
@@ -133,7 +132,7 @@ static int get_msg(struct mixart_mgr *mgr, struct mixart_msg *resp,
 	writel_be(headptr, MIXART_MEM(mgr, MSG_OUTBOUND_FREE_HEAD));
 
  _clean_exit:
-	spin_unlock_irqrestore(&mgr->msg_lock, flags);
+	mutex_unlock(&mgr->msg_lock);
 
 	return err;
 }
@@ -243,28 +242,24 @@ int snd_mixart_send_msg(struct mixart_mgr *mgr, struct mixart_msg *request, int
 	wait_queue_t wait;
 	long timeout;
 
-	mutex_lock(&mgr->msg_mutex);
-
 	init_waitqueue_entry(&wait, current);
 
-	spin_lock_irq(&mgr->msg_lock);
+	mutex_lock(&mgr->msg_lock);
 	/* send the message */
 	err = send_msg(mgr, request, max_resp_size, 1, &msg_frame);  /* send and mark the answer pending */
 	if (err) {
-		spin_unlock_irq(&mgr->msg_lock);
-		mutex_unlock(&mgr->msg_mutex);
+		mutex_unlock(&mgr->msg_lock);
 		return err;
 	}
 
 	set_current_state(TASK_UNINTERRUPTIBLE);
 	add_wait_queue(&mgr->msg_sleep, &wait);
-	spin_unlock_irq(&mgr->msg_lock);
+	mutex_unlock(&mgr->msg_lock);
 	timeout = schedule_timeout(MSG_TIMEOUT_JIFFIES);
 	remove_wait_queue(&mgr->msg_sleep, &wait);
 
 	if (! timeout) {
 		/* error - no ack */
-		mutex_unlock(&mgr->msg_mutex);
 		dev_err(&mgr->pci->dev,
 			"error: no response on msg %x\n", msg_frame);
 		return -EIO;
@@ -281,7 +276,6 @@ int snd_mixart_send_msg(struct mixart_mgr *mgr, struct mixart_msg *request, int
 	if( request->message_id != resp.message_id )
 		dev_err(&mgr->pci->dev, "RESPONSE ERROR!\n");
 
-	mutex_unlock(&mgr->msg_mutex);
 	return err;
 }
 
@@ -300,34 +294,29 @@ int snd_mixart_send_msg_wait_notif(struct mixart_mgr *mgr,
 	if (snd_BUG_ON(notif_event & MSG_CANCEL_NOTIFY_MASK))
 		return -EINVAL;
 
-	mutex_lock(&mgr->msg_mutex);
-
 	init_waitqueue_entry(&wait, current);
 
-	spin_lock_irq(&mgr->msg_lock);
+	mutex_lock(&mgr->msg_lock);
 	/* send the message */
 	err = send_msg(mgr, request, MSG_DEFAULT_SIZE, 1, &notif_event);  /* send and mark the notification event pending */
 	if(err) {
-		spin_unlock_irq(&mgr->msg_lock);
-		mutex_unlock(&mgr->msg_mutex);
+		mutex_unlock(&mgr->msg_lock);
 		return err;
 	}
 
 	set_current_state(TASK_UNINTERRUPTIBLE);
 	add_wait_queue(&mgr->msg_sleep, &wait);
-	spin_unlock_irq(&mgr->msg_lock);
+	mutex_unlock(&mgr->msg_lock);
 	timeout = schedule_timeout(MSG_TIMEOUT_JIFFIES);
 	remove_wait_queue(&mgr->msg_sleep, &wait);
 
 	if (! timeout) {
 		/* error - no ack */
-		mutex_unlock(&mgr->msg_mutex);
 		dev_err(&mgr->pci->dev,
 			"error: notification %x not received\n", notif_event);
 		return -EIO;
 	}
 
-	mutex_unlock(&mgr->msg_mutex);
 	return 0;
 }
 
@@ -335,13 +324,12 @@ int snd_mixart_send_msg_wait_notif(struct mixart_mgr *mgr,
 int snd_mixart_send_msg_nonblock(struct mixart_mgr *mgr, struct mixart_msg *request)
 {
 	u32 message_frame;
-	unsigned long flags;
 	int err;
 
 	/* just send the message (do not mark it as a pending one) */
-	spin_lock_irqsave(&mgr->msg_lock, flags);
+	mutex_lock(&mgr->msg_lock);
 	err = send_msg(mgr, request, MSG_DEFAULT_SIZE, 0, &message_frame);
-	spin_unlock_irqrestore(&mgr->msg_lock, flags);
+	mutex_unlock(&mgr->msg_lock);
 
 	/* the answer will be handled by snd_struct mixart_msgasklet()  */
 	atomic_inc(&mgr->msg_processed);
@@ -350,19 +338,16 @@ int snd_mixart_send_msg_nonblock(struct mixart_mgr *mgr, struct mixart_msg *requ
 }
 
 
-/* common buffer of tasklet and interrupt to send/receive messages */
+/* common buffer of interrupt to send/receive messages */
 static u32 mixart_msg_data[MSG_DEFAULT_SIZE / 4];
 
 
-void snd_mixart_msg_tasklet(unsigned long arg)
+static void snd_mixart_process_msg(struct mixart_mgr *mgr)
 {
-	struct mixart_mgr *mgr = ( struct mixart_mgr*)(arg);
 	struct mixart_msg resp;
 	u32 msg, addr, type;
 	int err;
 
-	spin_lock(&mgr->lock);
-
 	while (mgr->msg_fifo_readptr != mgr->msg_fifo_writeptr) {
 		msg = mgr->msg_fifo[mgr->msg_fifo_readptr];
 		mgr->msg_fifo_readptr++;
@@ -381,7 +366,7 @@ void snd_mixart_msg_tasklet(unsigned long arg)
 			err = get_msg(mgr, &resp, addr);
 			if( err < 0 ) {
 				dev_err(&mgr->pci->dev,
-					"tasklet: error(%d) reading mf %x\n",
+					"error(%d) reading mf %x\n",
 					err, msg);
 				break;
 			}
@@ -393,12 +378,12 @@ void snd_mixart_msg_tasklet(unsigned long arg)
 			case MSG_STREAM_STOP_OUTPUT_STAGE_PACKET:
 				if(mixart_msg_data[0])
 					dev_err(&mgr->pci->dev,
-						"tasklet : error MSG_STREAM_ST***_***PUT_STAGE_PACKET status=%x\n",
+						"error MSG_STREAM_ST***_***PUT_STAGE_PACKET status=%x\n",
 						mixart_msg_data[0]);
 				break;
 			default:
 				dev_dbg(&mgr->pci->dev,
-					"tasklet received mf(%x) : msg_id(%x) uid(%x, %x) size(%zd)\n",
+					"received mf(%x) : msg_id(%x) uid(%x, %x) size(%zd)\n",
 					   msg, resp.message_id, resp.uid.object_id, resp.uid.desc, resp.size);
 				break;
 			}
@@ -409,7 +394,7 @@ void snd_mixart_msg_tasklet(unsigned long arg)
 			/* get_msg() necessary */
 		default:
 			dev_err(&mgr->pci->dev,
-				"tasklet doesn't know what to do with message %x\n",
+				"doesn't know what to do with message %x\n",
 				msg);
 		} /* switch type */
 
@@ -417,26 +402,17 @@ void snd_mixart_msg_tasklet(unsigned long arg)
 		atomic_dec(&mgr->msg_processed);
 
 	} /* while there is a msg in fifo */
-
-	spin_unlock(&mgr->lock);
 }
 
 
 irqreturn_t snd_mixart_interrupt(int irq, void *dev_id)
 {
 	struct mixart_mgr *mgr = dev_id;
-	int err;
-	struct mixart_msg resp;
-
-	u32 msg;
 	u32 it_reg;
 
-	spin_lock(&mgr->lock);
-
 	it_reg = readl_le(MIXART_REG(mgr, MIXART_PCI_OMISR_OFFSET));
 	if( !(it_reg & MIXART_OIDI) ) {
 		/* this device did not cause the interrupt */
-		spin_unlock(&mgr->lock);
 		return IRQ_NONE;
 	}
 
@@ -450,6 +426,17 @@ irqreturn_t snd_mixart_interrupt(int irq, void *dev_id)
 	/* clear interrupt */
 	writel_le( MIXART_OIDI, MIXART_REG(mgr, MIXART_PCI_OMISR_OFFSET) );
 
+	return IRQ_WAKE_THREAD;
+}
+
+irqreturn_t snd_mixart_threaded_irq(int irq, void *dev_id)
+{
+	struct mixart_mgr *mgr = dev_id;
+	int err;
+	struct mixart_msg resp;
+	u32 msg;
+
+	mutex_lock(&mgr->lock);
 	/* process interrupt */
 	while (retrieve_msg_frame(mgr, &msg)) {
 
@@ -518,9 +505,9 @@ irqreturn_t snd_mixart_interrupt(int irq, void *dev_id)
 						stream->buf_period_frag = (u32)( sample_count - stream->abs_period_elapsed );
 
 						if(elapsed) {
-							spin_unlock(&mgr->lock);
+							mutex_unlock(&mgr->lock);
 							snd_pcm_period_elapsed(stream->substream);
-							spin_lock(&mgr->lock);
+							mutex_lock(&mgr->lock);
 						}
 					}
 				}
@@ -556,7 +543,7 @@ irqreturn_t snd_mixart_interrupt(int irq, void *dev_id)
 			/* no break, continue ! */
 		case MSG_TYPE_ANSWER:
 			/* answer or notification to a message we are waiting for*/
-			spin_lock(&mgr->msg_lock);
+			mutex_lock(&mgr->msg_lock);
 			if( (msg & ~MSG_TYPE_MASK) == mgr->pending_event ) {
 				wake_up(&mgr->msg_sleep);
 				mgr->pending_event = 0;
@@ -566,9 +553,9 @@ irqreturn_t snd_mixart_interrupt(int irq, void *dev_id)
 				mgr->msg_fifo[mgr->msg_fifo_writeptr] = msg;
 				mgr->msg_fifo_writeptr++;
 				mgr->msg_fifo_writeptr %= MSG_FIFO_SIZE;
-				tasklet_schedule(&mgr->msg_taskq);
+				snd_mixart_process_msg(mgr);
 			}
-			spin_unlock(&mgr->msg_lock);
+			mutex_unlock(&mgr->msg_lock);
 			break;
 		case MSG_TYPE_REQUEST:
 		default:
@@ -582,7 +569,7 @@ irqreturn_t snd_mixart_interrupt(int irq, void *dev_id)
 	/* allow interrupt again */
 	writel_le( MIXART_ALLOW_OUTBOUND_DOORBELL, MIXART_REG( mgr, MIXART_PCI_OMIMR_OFFSET));
 
-	spin_unlock(&mgr->lock);
+	mutex_unlock(&mgr->lock);
 
 	return IRQ_HANDLED;
 }
diff --git a/sound/pci/mixart/mixart_core.h b/sound/pci/mixart/mixart_core.h
index c919b734756f..d1722e575409 100644
--- a/sound/pci/mixart/mixart_core.h
+++ b/sound/pci/mixart/mixart_core.h
@@ -564,7 +564,7 @@ int  snd_mixart_send_msg_wait_notif(struct mixart_mgr *mgr, struct mixart_msg *r
 int  snd_mixart_send_msg_nonblock(struct mixart_mgr *mgr, struct mixart_msg *request);
 
 irqreturn_t snd_mixart_interrupt(int irq, void *dev_id);
-void snd_mixart_msg_tasklet(unsigned long arg);
+irqreturn_t snd_mixart_threaded_irq(int irq, void *dev_id);
 
 void snd_mixart_reset_board(struct mixart_mgr *mgr);
 
diff --git a/sound/pci/oxygen/oxygen_pcm.c b/sound/pci/oxygen/oxygen_pcm.c
index cc0bcd9f3350..02828240ba15 100644
--- a/sound/pci/oxygen/oxygen_pcm.c
+++ b/sound/pci/oxygen/oxygen_pcm.c
@@ -29,6 +29,9 @@
 /* the multichannel DMA channel has a 24-bit counter */
 #define BUFFER_BYTES_MAX_MULTICH	((1 << 24) * 4)
 
+#define FIFO_BYTES			256
+#define FIFO_BYTES_MULTICH		1024
+
 #define PERIOD_BYTES_MIN		64
 
 #define DEFAULT_BUFFER_BYTES		(BUFFER_BYTES_MAX / 2)
@@ -60,6 +63,7 @@ static const struct snd_pcm_hardware oxygen_stereo_hardware = {
 	.period_bytes_max = BUFFER_BYTES_MAX,
 	.periods_min = 1,
 	.periods_max = BUFFER_BYTES_MAX / PERIOD_BYTES_MIN,
+	.fifo_size = FIFO_BYTES,
 };
 static const struct snd_pcm_hardware oxygen_multichannel_hardware = {
 	.info = SNDRV_PCM_INFO_MMAP |
@@ -87,6 +91,7 @@ static const struct snd_pcm_hardware oxygen_multichannel_hardware = {
 	.period_bytes_max = BUFFER_BYTES_MAX_MULTICH,
 	.periods_min = 1,
 	.periods_max = BUFFER_BYTES_MAX_MULTICH / PERIOD_BYTES_MIN,
+	.fifo_size = FIFO_BYTES_MULTICH,
 };
 static const struct snd_pcm_hardware oxygen_ac97_hardware = {
 	.info = SNDRV_PCM_INFO_MMAP |
@@ -106,6 +111,7 @@ static const struct snd_pcm_hardware oxygen_ac97_hardware = {
 	.period_bytes_max = BUFFER_BYTES_MAX,
 	.periods_min = 1,
 	.periods_max = BUFFER_BYTES_MAX / PERIOD_BYTES_MIN,
+	.fifo_size = FIFO_BYTES,
 };
 
 static const struct snd_pcm_hardware *const oxygen_hardware[PCM_COUNT] = {
@@ -141,6 +147,10 @@ static int oxygen_open(struct snd_pcm_substream *substream,
 		runtime->hw.rates &= ~(SNDRV_PCM_RATE_32000 |
 				       SNDRV_PCM_RATE_64000);
 		runtime->hw.rate_min = 44100;
+		/* fall through */
+	case PCM_A:
+	case PCM_B:
+		runtime->hw.fifo_size = 0;
 		break;
 	case PCM_MULTICH:
 		runtime->hw.channels_max = chip->model.dac_channels_pcm;
diff --git a/sound/pci/oxygen/virtuoso.c b/sound/pci/oxygen/virtuoso.c
index 7b317a28a19c..83de6fb01021 100644
--- a/sound/pci/oxygen/virtuoso.c
+++ b/sound/pci/oxygen/virtuoso.c
@@ -52,6 +52,7 @@ static const struct pci_device_id xonar_ids[] = {
 	{ OXYGEN_PCI_SUBID(0x1043, 0x835d) },
 	{ OXYGEN_PCI_SUBID(0x1043, 0x835e) },
 	{ OXYGEN_PCI_SUBID(0x1043, 0x838e) },
+	{ OXYGEN_PCI_SUBID(0x1043, 0x8428) },
 	{ OXYGEN_PCI_SUBID(0x1043, 0x8522) },
 	{ OXYGEN_PCI_SUBID(0x1043, 0x85f4) },
 	{ OXYGEN_PCI_SUBID_BROKEN_EEPROM },
diff --git a/sound/pci/oxygen/xonar_pcm179x.c b/sound/pci/oxygen/xonar_pcm179x.c
index e02605931669..24109d37ca09 100644
--- a/sound/pci/oxygen/xonar_pcm179x.c
+++ b/sound/pci/oxygen/xonar_pcm179x.c
@@ -212,6 +212,9 @@
 #define GPIO_ST_MAGIC		0x0040
 #define GPIO_ST_HP		0x0080
 
+#define GPIO_XENSE_OUTPUT_ENABLE	(0x0001 | 0x0010 | 0x0020)
+#define GPIO_XENSE_SPEAKERS		0x0080
+
 #define I2C_DEVICE_PCM1796(i)	(0x98 + ((i) << 1))	/* 10011, ii, /W=0 */
 #define I2C_DEVICE_CS2000	0x9c			/* 100111, 0, /W=0 */
 
@@ -419,6 +422,7 @@ static void xonar_st_init_common(struct oxygen *chip)
 
 	data->generic.output_enable_bit = GPIO_ST_OUTPUT_ENABLE;
 	data->dacs = chip->model.dac_channels_mixer / 2;
+	data->h6 = chip->model.dac_channels_mixer > 2;
 	data->hp_gain_offset = 2*-18;
 
 	pcm1796_init(chip);
@@ -499,6 +503,51 @@ static void xonar_stx_init(struct oxygen *chip)
 	xonar_st_init_common(chip);
 }
 
+static void xonar_xense_init(struct oxygen *chip)
+{
+	struct xonar_pcm179x *data = chip->model_data;
+
+	data->generic.ext_power_reg = OXYGEN_GPI_DATA;
+	data->generic.ext_power_int_reg = OXYGEN_GPI_INTERRUPT_MASK;
+	data->generic.ext_power_bit = GPI_EXT_POWER;
+	xonar_init_ext_power(chip);
+
+	data->generic.anti_pop_delay = 100;
+	data->has_cs2000 = 1;
+	data->cs2000_regs[CS2000_FUN_CFG_1] = CS2000_REF_CLK_DIV_1;
+
+	oxygen_write16(chip, OXYGEN_I2S_A_FORMAT,
+		OXYGEN_RATE_48000 |
+		OXYGEN_I2S_FORMAT_I2S |
+		OXYGEN_I2S_MCLK(MCLK_512) |
+		OXYGEN_I2S_BITS_16 |
+		OXYGEN_I2S_MASTER |
+		OXYGEN_I2S_BCLK_64);
+
+	xonar_st_init_i2c(chip);
+	cs2000_registers_init(chip);
+
+	data->generic.output_enable_bit = GPIO_XENSE_OUTPUT_ENABLE;
+	data->dacs = 1;
+	data->hp_gain_offset = 2*-18;
+
+	pcm1796_init(chip);
+
+	oxygen_set_bits16(chip, OXYGEN_GPIO_CONTROL,
+		GPIO_INPUT_ROUTE | GPIO_ST_HP_REAR |
+		GPIO_ST_MAGIC | GPIO_XENSE_SPEAKERS);
+	oxygen_clear_bits16(chip, OXYGEN_GPIO_DATA,
+		GPIO_INPUT_ROUTE | GPIO_ST_HP_REAR |
+		GPIO_XENSE_SPEAKERS);
+
+	xonar_init_cs53x1(chip);
+	xonar_enable_output(chip);
+
+	snd_component_add(chip->card, "PCM1796");
+	snd_component_add(chip->card, "CS5381");
+	snd_component_add(chip->card, "CS2000");
+}
+
 static void xonar_d2_cleanup(struct oxygen *chip)
 {
 	xonar_disable_output(chip);
@@ -795,11 +844,11 @@ static int st_output_switch_put(struct snd_kcontrol *ctl,
 static int st_hp_volume_offset_info(struct snd_kcontrol *ctl,
 				    struct snd_ctl_elem_info *info)
 {
-	static const char *const names[3] = {
-		"< 64 ohms", "64-300 ohms", "300-600 ohms"
+	static const char *const names[4] = {
+		"< 32 ohms", "32-64 ohms", "64-300 ohms", "300-600 ohms"
 	};
 
-	return snd_ctl_enum_info(info, 1, 3, names);
+	return snd_ctl_enum_info(info, 1, 4, names);
 }
 
 static int st_hp_volume_offset_get(struct snd_kcontrol *ctl,
@@ -809,12 +858,14 @@ static int st_hp_volume_offset_get(struct snd_kcontrol *ctl,
 	struct xonar_pcm179x *data = chip->model_data;
 
 	mutex_lock(&chip->mutex);
-	if (data->hp_gain_offset < 2*-6)
+	if (data->hp_gain_offset < 2*-12)
 		value->value.enumerated.item[0] = 0;
-	else if (data->hp_gain_offset < 0)
+	else if (data->hp_gain_offset < 2*-6)
 		value->value.enumerated.item[0] = 1;
-	else
+	else if (data->hp_gain_offset < 0)
 		value->value.enumerated.item[0] = 2;
+	else
+		value->value.enumerated.item[0] = 3;
 	mutex_unlock(&chip->mutex);
 	return 0;
 }
@@ -823,13 +874,13 @@ static int st_hp_volume_offset_get(struct snd_kcontrol *ctl,
 static int st_hp_volume_offset_put(struct snd_kcontrol *ctl,
 				   struct snd_ctl_elem_value *value)
 {
-	static const s8 offsets[] = { 2*-18, 2*-6, 0 };
+	static const s8 offsets[] = { 2*-18, 2*-12, 2*-6, 0 };
 	struct oxygen *chip = ctl->private_data;
 	struct xonar_pcm179x *data = chip->model_data;
 	s8 offset;
 	int changed;
 
-	if (value->value.enumerated.item[0] > 2)
+	if (value->value.enumerated.item[0] > 3)
 		return -EINVAL;
 	offset = offsets[value->value.enumerated.item[0]];
 	mutex_lock(&chip->mutex);
@@ -859,6 +910,67 @@ static const struct snd_kcontrol_new st_controls[] = {
 	},
 };
 
+static int xense_output_switch_get(struct snd_kcontrol *ctl,
+				   struct snd_ctl_elem_value *value)
+{
+	struct oxygen *chip = ctl->private_data;
+	u16 gpio;
+
+	gpio = oxygen_read16(chip, OXYGEN_GPIO_DATA);
+	if (gpio & GPIO_XENSE_SPEAKERS)
+		value->value.enumerated.item[0] = 0;
+	else if (!(gpio & GPIO_XENSE_SPEAKERS) && (gpio & GPIO_ST_HP_REAR))
+		value->value.enumerated.item[0] = 1;
+	else
+		value->value.enumerated.item[0] = 2;
+	return 0;
+}
+
+static int xense_output_switch_put(struct snd_kcontrol *ctl,
+				   struct snd_ctl_elem_value *value)
+{
+	struct oxygen *chip = ctl->private_data;
+	struct xonar_pcm179x *data = chip->model_data;
+	u16 gpio_old, gpio;
+
+	mutex_lock(&chip->mutex);
+	gpio_old = oxygen_read16(chip, OXYGEN_GPIO_DATA);
+	gpio = gpio_old;
+	switch (value->value.enumerated.item[0]) {
+	case 0:
+		gpio |= GPIO_XENSE_SPEAKERS | GPIO_ST_HP_REAR;
+		break;
+	case 1:
+		gpio = (gpio | GPIO_ST_HP_REAR) & ~GPIO_XENSE_SPEAKERS;
+		break;
+	case 2:
+		gpio &= ~(GPIO_XENSE_SPEAKERS | GPIO_ST_HP_REAR);
+		break;
+	}
+	oxygen_write16(chip, OXYGEN_GPIO_DATA, gpio);
+	data->hp_active = !(gpio & GPIO_XENSE_SPEAKERS);
+	update_pcm1796_volume(chip);
+	mutex_unlock(&chip->mutex);
+	return gpio != gpio_old;
+}
+
+static const struct snd_kcontrol_new xense_controls[] = {
+	{
+		.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
+		.name = "Analog Output",
+		.info = st_output_switch_info,
+		.get = xense_output_switch_get,
+		.put = xense_output_switch_put,
+	},
+	{
+		.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
+		.name = "Headphones Impedance Playback Enum",
+		.info = st_hp_volume_offset_info,
+		.get = st_hp_volume_offset_get,
+		.put = st_hp_volume_offset_put,
+	},
+};
+
 static void xonar_line_mic_ac97_switch(struct oxygen *chip,
 				       unsigned int reg, unsigned int mute)
 {
@@ -946,6 +1058,23 @@ static int xonar_st_mixer_init(struct oxygen *chip)
 	return 0;
 }
 
+static int xonar_xense_mixer_init(struct oxygen *chip)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < ARRAY_SIZE(xense_controls); ++i) {
+		err = snd_ctl_add(chip->card,
+		snd_ctl_new1(&xense_controls[i], chip));
+		if (err < 0)
+			return err;
+	}
+	err = add_pcm1796_controls(chip);
+	if (err < 0)
+		return err;
+	return 0;
+}
+
 static void dump_pcm1796_registers(struct oxygen *chip,
 				   struct snd_info_buffer *buffer)
 {
@@ -1140,12 +1269,29 @@ int get_xonar_pcm179x_model(struct oxygen *chip,
 		break;
 	case 0x85f4:
 		chip->model = model_xonar_st;
-		/* TODO: daughterboard support */
-		chip->model.shortname = "Xonar STX II";
+		oxygen_clear_bits16(chip, OXYGEN_GPIO_CONTROL, GPIO_DB_MASK);
+		switch (oxygen_read16(chip, OXYGEN_GPIO_DATA) & GPIO_DB_MASK) {
+		default:
+			chip->model.shortname = "Xonar STX II";
+			break;
+		case GPIO_DB_H6:
+			chip->model.shortname = "Xonar STX II+H6";
+			chip->model.dac_channels_pcm = 8;
+			chip->model.dac_channels_mixer = 8;
+			chip->model.dac_mclks = OXYGEN_MCLKS(256, 128, 128);
+			break;
+		}
 		chip->model.init = xonar_stx_init;
 		chip->model.resume = xonar_stx_resume;
 		chip->model.set_dac_params = set_pcm1796_params;
 		break;
+	case 0x8428:
+		chip->model = model_xonar_st;
+		chip->model.shortname = "Xonar Xense";
+		chip->model.chip = "AV100";
+		chip->model.init = xonar_xense_init;
+		chip->model.mixer_init = xonar_xense_mixer_init;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/sound/pci/pcxhr/pcxhr.c b/sound/pci/pcxhr/pcxhr.c
index 68a37a7906c1..b854fc5e01f5 100644
--- a/sound/pci/pcxhr/pcxhr.c
+++ b/sound/pci/pcxhr/pcxhr.c
@@ -702,13 +702,11 @@ static inline int pcxhr_stream_scheduled_get_pipe(struct pcxhr_stream *stream,
 	return 0;
 }
 
-static void pcxhr_trigger_tasklet(unsigned long arg)
+static void pcxhr_start_linked_stream(struct pcxhr_mgr *mgr)
 {
-	unsigned long flags;
 	int i, j, err;
 	struct pcxhr_pipe *pipe;
 	struct snd_pcxhr *chip;
-	struct pcxhr_mgr *mgr = (struct pcxhr_mgr*)(arg);
 	int capture_mask = 0;
 	int playback_mask = 0;
 
@@ -736,11 +734,11 @@ static void pcxhr_trigger_tasklet(unsigned long arg)
 	}
 	if (capture_mask == 0 && playback_mask == 0) {
 		mutex_unlock(&mgr->setup_mutex);
-		dev_err(&mgr->pci->dev, "pcxhr_trigger_tasklet : no pipes\n");
+		dev_err(&mgr->pci->dev, "pcxhr_start_linked_stream : no pipes\n");
 		return;
 	}
 
-	dev_dbg(&mgr->pci->dev, "pcxhr_trigger_tasklet : "
+	dev_dbg(&mgr->pci->dev, "pcxhr_start_linked_stream : "
 		    "playback_mask=%x capture_mask=%x\n",
 		    playback_mask, capture_mask);
 
@@ -748,7 +746,7 @@ static void pcxhr_trigger_tasklet(unsigned long arg)
 	err = pcxhr_set_pipe_state(mgr,  playback_mask, capture_mask, 0);
 	if (err) {
 		mutex_unlock(&mgr->setup_mutex);
-		dev_err(&mgr->pci->dev, "pcxhr_trigger_tasklet : "
+		dev_err(&mgr->pci->dev, "pcxhr_start_linked_stream : "
 			   "error stop pipes (P%x C%x)\n",
 			   playback_mask, capture_mask);
 		return;
@@ -793,7 +791,7 @@ static void pcxhr_trigger_tasklet(unsigned long arg)
 	err = pcxhr_set_pipe_state(mgr, playback_mask, capture_mask, 1);
 	if (err) {
 		mutex_unlock(&mgr->setup_mutex);
-		dev_err(&mgr->pci->dev, "pcxhr_trigger_tasklet : "
+		dev_err(&mgr->pci->dev, "pcxhr_start_linked_stream : "
 			   "error start pipes (P%x C%x)\n",
 			   playback_mask, capture_mask);
 		return;
@@ -802,7 +800,7 @@ static void pcxhr_trigger_tasklet(unsigned long arg)
 	/* put the streams into the running state now
 	 * (increment pointer by interrupt)
 	 */
-	spin_lock_irqsave(&mgr->lock, flags);
+	mutex_lock(&mgr->lock);
 	for ( i =0; i < mgr->num_cards; i++) {
 		struct pcxhr_stream *stream;
 		chip = mgr->chip[i];
@@ -820,13 +818,13 @@ static void pcxhr_trigger_tasklet(unsigned long arg)
 			}
 		}
 	}
-	spin_unlock_irqrestore(&mgr->lock, flags);
+	mutex_unlock(&mgr->lock);
 
 	mutex_unlock(&mgr->setup_mutex);
 
 #ifdef CONFIG_SND_DEBUG_VERBOSE
 	do_gettimeofday(&my_tv2);
-	dev_dbg(&mgr->pci->dev, "***TRIGGER TASKLET*** TIME = %ld (err = %x)\n",
+	dev_dbg(&mgr->pci->dev, "***TRIGGER START*** TIME = %ld (err = %x)\n",
 		    (long)(my_tv2.tv_usec - my_tv1.tv_usec), err);
 #endif
 }
@@ -853,7 +851,7 @@ static int pcxhr_trigger(struct snd_pcm_substream *subs, int cmd)
 					PCXHR_STREAM_STATUS_SCHEDULE_RUN;
 				snd_pcm_trigger_done(s, subs);
 			}
-			tasklet_schedule(&chip->mgr->trigger_taskq);
+			pcxhr_start_linked_stream(chip->mgr);
 		} else {
 			stream = subs->runtime->private_data;
 			snd_printdd("Only one Substream %c %d\n",
@@ -1127,20 +1125,19 @@ static int pcxhr_close(struct snd_pcm_substream *subs)
 
 static snd_pcm_uframes_t pcxhr_stream_pointer(struct snd_pcm_substream *subs)
 {
-	unsigned long flags;
 	u_int32_t timer_period_frag;
 	int timer_buf_periods;
 	struct snd_pcxhr *chip = snd_pcm_substream_chip(subs);
 	struct snd_pcm_runtime *runtime = subs->runtime;
 	struct pcxhr_stream *stream  = runtime->private_data;
 
-	spin_lock_irqsave(&chip->mgr->lock, flags);
+	mutex_lock(&chip->mgr->lock);
 
 	/* get the period fragment and the nb of periods in the buffer */
 	timer_period_frag = stream->timer_period_frag;
 	timer_buf_periods = stream->timer_buf_periods;
 
-	spin_unlock_irqrestore(&chip->mgr->lock, flags);
+	mutex_unlock(&chip->mgr->lock);
 
 	return (snd_pcm_uframes_t)((timer_buf_periods * runtime->period_size) +
 				   timer_period_frag);
@@ -1181,6 +1178,7 @@ int pcxhr_create_pcm(struct snd_pcxhr *chip)
 		snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &pcxhr_ops);
 
 	pcm->info_flags = 0;
+	pcm->nonatomic = true;
 	strcpy(pcm->name, name);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
@@ -1588,8 +1586,9 @@ static int pcxhr_probe(struct pci_dev *pci,
 	mgr->pci = pci;
 	mgr->irq = -1;
 
-	if (request_irq(pci->irq, pcxhr_interrupt, IRQF_SHARED,
-			KBUILD_MODNAME, mgr)) {
+	if (request_threaded_irq(pci->irq, pcxhr_interrupt,
+				 pcxhr_threaded_irq, IRQF_SHARED,
+				 KBUILD_MODNAME, mgr)) {
 		dev_err(&pci->dev, "unable to grab IRQ %d\n", pci->irq);
 		pcxhr_free(mgr);
 		return -EBUSY;
@@ -1601,19 +1600,13 @@ static int pcxhr_probe(struct pci_dev *pci,
 		mgr->shortname,
 		mgr->port[0], mgr->port[1], mgr->port[2], mgr->irq);
 
-	/* ISR spinlock  */
-	spin_lock_init(&mgr->lock);
-	spin_lock_init(&mgr->msg_lock);
+	/* ISR lock  */
+	mutex_init(&mgr->lock);
+	mutex_init(&mgr->msg_lock);
 
 	/* init setup mutex*/
 	mutex_init(&mgr->setup_mutex);
 
-	/* init taslket */
-	tasklet_init(&mgr->msg_taskq, pcxhr_msg_tasklet,
-		     (unsigned long) mgr);
-	tasklet_init(&mgr->trigger_taskq, pcxhr_trigger_tasklet,
-		     (unsigned long) mgr);
-
 	mgr->prmh = kmalloc(sizeof(*mgr->prmh) + 
 			    sizeof(u32) * (PCXHR_SIZE_MAX_LONG_STATUS -
 					   PCXHR_SIZE_MAX_STATUS),
diff --git a/sound/pci/pcxhr/pcxhr.h b/sound/pci/pcxhr/pcxhr.h
index a4c602c45173..9e39e509a3ef 100644
--- a/sound/pci/pcxhr/pcxhr.h
+++ b/sound/pci/pcxhr/pcxhr.h
@@ -78,14 +78,10 @@ struct pcxhr_mgr {
 	char shortname[32];		/* short name of this soundcard */
 	char longname[96];		/* name of this soundcard */
 
-	/* message tasklet */
-	struct tasklet_struct msg_taskq;
 	struct pcxhr_rmh *prmh;
-	/* trigger tasklet */
-	struct tasklet_struct trigger_taskq;
 
-	spinlock_t lock;		/* interrupt spinlock */
-	spinlock_t msg_lock;		/* message spinlock */
+	struct mutex lock;		/* interrupt lock */
+	struct mutex msg_lock;		/* message lock */
 
 	struct mutex setup_mutex;	/* mutex used in hw_params, open and close */
 	struct mutex mixer_mutex;	/* mutex for mixer */
diff --git a/sound/pci/pcxhr/pcxhr_core.c b/sound/pci/pcxhr/pcxhr_core.c
index df9371918601..a584acb61c00 100644
--- a/sound/pci/pcxhr/pcxhr_core.c
+++ b/sound/pci/pcxhr/pcxhr_core.c
@@ -767,11 +767,11 @@ void pcxhr_set_pipe_cmd_params(struct pcxhr_rmh *rmh, int capture,
  */
 int pcxhr_send_msg(struct pcxhr_mgr *mgr, struct pcxhr_rmh *rmh)
 {
-	unsigned long flags;
 	int err;
-	spin_lock_irqsave(&mgr->msg_lock, flags);
+
+	mutex_lock(&mgr->msg_lock);
 	err = pcxhr_send_msg_nolock(mgr, rmh);
-	spin_unlock_irqrestore(&mgr->msg_lock, flags);
+	mutex_unlock(&mgr->msg_lock);
 	return err;
 }
 
@@ -971,17 +971,16 @@ int pcxhr_write_io_num_reg_cont(struct pcxhr_mgr *mgr, unsigned int mask,
 				unsigned int value, int *changed)
 {
 	struct pcxhr_rmh rmh;
-	unsigned long flags;
 	int err;
 
-	spin_lock_irqsave(&mgr->msg_lock, flags);
+	mutex_lock(&mgr->msg_lock);
 	if ((mgr->io_num_reg_cont & mask) == value) {
 		dev_dbg(&mgr->pci->dev,
 			"IO_NUM_REG_CONT mask %x already is set to %x\n",
 			    mask, value);
 		if (changed)
 			*changed = 0;
-		spin_unlock_irqrestore(&mgr->msg_lock, flags);
+		mutex_unlock(&mgr->msg_lock);
 		return 0;	/* already programmed */
 	}
 	pcxhr_init_rmh(&rmh, CMD_ACCESS_IO_WRITE);
@@ -996,7 +995,7 @@ int pcxhr_write_io_num_reg_cont(struct pcxhr_mgr *mgr, unsigned int mask,
 		if (changed)
 			*changed = 1;
 	}
-	spin_unlock_irqrestore(&mgr->msg_lock, flags);
+	mutex_unlock(&mgr->msg_lock);
 	return err;
 }
 
@@ -1043,22 +1042,21 @@ static int pcxhr_handle_async_err(struct pcxhr_mgr *mgr, u32 err,
 }
 
 
-void pcxhr_msg_tasklet(unsigned long arg)
+static void pcxhr_msg_thread(struct pcxhr_mgr *mgr)
 {
-	struct pcxhr_mgr *mgr = (struct pcxhr_mgr *)(arg);
 	struct pcxhr_rmh *prmh = mgr->prmh;
 	int err;
 	int i, j;
 
 	if (mgr->src_it_dsp & PCXHR_IRQ_FREQ_CHANGE)
 		dev_dbg(&mgr->pci->dev,
-			"TASKLET : PCXHR_IRQ_FREQ_CHANGE event occurred\n");
+			"PCXHR_IRQ_FREQ_CHANGE event occurred\n");
 	if (mgr->src_it_dsp & PCXHR_IRQ_TIME_CODE)
 		dev_dbg(&mgr->pci->dev,
-			"TASKLET : PCXHR_IRQ_TIME_CODE event occurred\n");
+			"PCXHR_IRQ_TIME_CODE event occurred\n");
 	if (mgr->src_it_dsp & PCXHR_IRQ_NOTIFY)
 		dev_dbg(&mgr->pci->dev,
-			"TASKLET : PCXHR_IRQ_NOTIFY event occurred\n");
+			"PCXHR_IRQ_NOTIFY event occurred\n");
 	if (mgr->src_it_dsp & (PCXHR_IRQ_FREQ_CHANGE | PCXHR_IRQ_TIME_CODE)) {
 		/* clear events FREQ_CHANGE and TIME_CODE */
 		pcxhr_init_rmh(prmh, CMD_TEST_IT);
@@ -1068,7 +1066,7 @@ void pcxhr_msg_tasklet(unsigned long arg)
 	}
 	if (mgr->src_it_dsp & PCXHR_IRQ_ASYNC) {
 		dev_dbg(&mgr->pci->dev,
-			"TASKLET : PCXHR_IRQ_ASYNC event occurred\n");
+			"PCXHR_IRQ_ASYNC event occurred\n");
 
 		pcxhr_init_rmh(prmh, CMD_ASYNC);
 		prmh->cmd[0] |= 1;	/* add SEL_ASYNC_EVENTS */
@@ -1076,7 +1074,7 @@ void pcxhr_msg_tasklet(unsigned long arg)
 		prmh->stat_len = PCXHR_SIZE_MAX_LONG_STATUS;
 		err = pcxhr_send_msg(mgr, prmh);
 		if (err)
-			dev_err(&mgr->pci->dev, "ERROR pcxhr_msg_tasklet=%x;\n",
+			dev_err(&mgr->pci->dev, "ERROR pcxhr_msg_thread=%x;\n",
 				   err);
 		i = 1;
 		while (i < prmh->stat_len) {
@@ -1220,9 +1218,9 @@ static void pcxhr_update_timer_pos(struct pcxhr_mgr *mgr,
 		}
 
 		if (elapsed) {
-			spin_unlock(&mgr->lock);
+			mutex_unlock(&mgr->lock);
 			snd_pcm_period_elapsed(stream->substream);
-			spin_lock(&mgr->lock);
+			mutex_lock(&mgr->lock);
 		}
 	}
 }
@@ -1231,14 +1229,10 @@ irqreturn_t pcxhr_interrupt(int irq, void *dev_id)
 {
 	struct pcxhr_mgr *mgr = dev_id;
 	unsigned int reg;
-	int i, j;
-	struct snd_pcxhr *chip;
-
-	spin_lock(&mgr->lock);
+	bool wake_thread = false;
 
 	reg = PCXHR_INPL(mgr, PCXHR_PLX_IRQCS);
 	if (! (reg & PCXHR_IRQCS_ACTIVE_PCIDB)) {
-		spin_unlock(&mgr->lock);
 		/* this device did not cause the interrupt */
 		return IRQ_NONE;
 	}
@@ -1250,6 +1244,44 @@ irqreturn_t pcxhr_interrupt(int irq, void *dev_id)
 	/* timer irq occurred */
 	if (reg & PCXHR_IRQ_TIMER) {
 		int timer_toggle = reg & PCXHR_IRQ_TIMER;
+		if (timer_toggle == mgr->timer_toggle) {
+			dev_dbg(&mgr->pci->dev, "ERROR TIMER TOGGLE\n");
+			mgr->dsp_time_err++;
+		}
+
+		mgr->timer_toggle = timer_toggle;
+		mgr->src_it_dsp = reg;
+		wake_thread = true;
+	}
+
+	/* other irq's handled in the thread */
+	if (reg & PCXHR_IRQ_MASK) {
+		if (reg & PCXHR_IRQ_ASYNC) {
+			/* as we didn't request any async notifications,
+			 * some kind of xrun error will probably occurred
+			 */
+			/* better resynchronize all streams next interrupt : */
+			mgr->dsp_time_last = PCXHR_DSP_TIME_INVALID;
+		}
+		mgr->src_it_dsp = reg;
+		wake_thread = true;
+	}
+#ifdef CONFIG_SND_DEBUG_VERBOSE
+	if (reg & PCXHR_FATAL_DSP_ERR)
+		dev_dbg(&mgr->pci->dev, "FATAL DSP ERROR : %x\n", reg);
+#endif
+
+	return wake_thread ? IRQ_WAKE_THREAD : IRQ_HANDLED;
+}
+
+irqreturn_t pcxhr_threaded_irq(int irq, void *dev_id)
+{
+	struct pcxhr_mgr *mgr = dev_id;
+	int i, j;
+	struct snd_pcxhr *chip;
+
+	mutex_lock(&mgr->lock);
+	if (mgr->src_it_dsp & PCXHR_IRQ_TIMER) {
 		/* is a 24 bit counter */
 		int dsp_time_new =
 			PCXHR_INPL(mgr, PCXHR_PLX_MBOX4) & PCXHR_DSP_TIME_MASK;
@@ -1290,13 +1322,6 @@ irqreturn_t pcxhr_interrupt(int irq, void *dev_id)
 #endif
 		mgr->dsp_time_last = dsp_time_new;
 
-		if (timer_toggle == mgr->timer_toggle) {
-			dev_dbg(&mgr->pci->dev, "ERROR TIMER TOGGLE\n");
-			mgr->dsp_time_err++;
-		}
-		mgr->timer_toggle = timer_toggle;
-
-		reg &= ~PCXHR_IRQ_TIMER;
 		for (i = 0; i < mgr->num_cards; i++) {
 			chip = mgr->chip[i];
 			for (j = 0; j < chip->nb_streams_capt; j++)
@@ -1312,22 +1337,7 @@ irqreturn_t pcxhr_interrupt(int irq, void *dev_id)
 						dsp_time_diff);
 		}
 	}
-	/* other irq's handled in the tasklet */
-	if (reg & PCXHR_IRQ_MASK) {
-		if (reg & PCXHR_IRQ_ASYNC) {
-			/* as we didn't request any async notifications,
-			 * some kind of xrun error will probably occurred
-			 */
-			/* better resynchronize all streams next interrupt : */
-			mgr->dsp_time_last = PCXHR_DSP_TIME_INVALID;
-		}
-		mgr->src_it_dsp = reg;
-		tasklet_schedule(&mgr->msg_taskq);
-	}
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-	if (reg & PCXHR_FATAL_DSP_ERR)
-		dev_dbg(&mgr->pci->dev, "FATAL DSP ERROR : %x\n", reg);
-#endif
-	spin_unlock(&mgr->lock);
-	return IRQ_HANDLED;	/* this device caused the interrupt */
+
+	pcxhr_msg_thread(mgr);
+	return IRQ_HANDLED;
 }
diff --git a/sound/pci/pcxhr/pcxhr_core.h b/sound/pci/pcxhr/pcxhr_core.h
index a81ab6b811e7..dc267e4c1074 100644
--- a/sound/pci/pcxhr/pcxhr_core.h
+++ b/sound/pci/pcxhr/pcxhr_core.h
@@ -200,6 +200,6 @@ int pcxhr_write_io_num_reg_cont(struct pcxhr_mgr *mgr, unsigned int mask,
 
 /* interrupt handling */
 irqreturn_t pcxhr_interrupt(int irq, void *dev_id);
-void pcxhr_msg_tasklet(unsigned long arg);
+irqreturn_t pcxhr_threaded_irq(int irq, void *dev_id);
 
 #endif /* __SOUND_PCXHR_CORE_H */
diff --git a/sound/pci/vx222/vx222.c b/sound/pci/vx222/vx222.c
index 3dc4732142ee..c5a25e39e3a8 100644
--- a/sound/pci/vx222/vx222.c
+++ b/sound/pci/vx222/vx222.c
@@ -168,8 +168,9 @@ static int snd_vx222_create(struct snd_card *card, struct pci_dev *pci,
 	for (i = 0; i < 2; i++)
 		vx->port[i] = pci_resource_start(pci, i + 1);
 
-	if (request_irq(pci->irq, snd_vx_irq_handler, IRQF_SHARED,
-			KBUILD_MODNAME, chip)) {
+	if (request_threaded_irq(pci->irq, snd_vx_irq_handler,
+				 snd_vx_threaded_irq_handler, IRQF_SHARED,
+				 KBUILD_MODNAME, chip)) {
 		dev_err(card->dev, "unable to grab IRQ %d\n", pci->irq);
 		snd_vx222_free(chip);
 		return -EBUSY;
diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf.c b/sound/pcmcia/pdaudiocf/pdaudiocf.c
index 56bda124cd4a..07f4b33db3af 100644
--- a/sound/pcmcia/pdaudiocf/pdaudiocf.c
+++ b/sound/pcmcia/pdaudiocf/pdaudiocf.c
@@ -61,6 +61,7 @@ static void snd_pdacf_detach(struct pcmcia_device *p_dev);
 
 static void pdacf_release(struct pcmcia_device *link)
 {
+	free_irq(link->irq, link->priv);
 	pcmcia_disable_device(link);
 }
 
@@ -220,11 +221,13 @@ static int pdacf_config(struct pcmcia_device *link)
 
 	ret = pcmcia_request_io(link);
 	if (ret)
-		goto failed;
+		goto failed_preirq;
 
-	ret = pcmcia_request_irq(link, pdacf_interrupt);
+	ret = request_threaded_irq(link->irq, pdacf_interrupt,
+				   pdacf_threaded_irq,
+				   IRQF_SHARED, link->devname, link->priv);
 	if (ret)
-		goto failed;
+		goto failed_preirq;
 
 	ret = pcmcia_enable_device(link);
 	if (ret)
@@ -236,7 +239,9 @@ static int pdacf_config(struct pcmcia_device *link)
 
 	return 0;
 
-failed:
+ failed:
+	free_irq(link->irq, link->priv);
+failed_preirq:
 	pcmcia_disable_device(link);
 	return -ENODEV;
 }
diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf.h b/sound/pcmcia/pdaudiocf/pdaudiocf.h
index ea41e57d7179..e9a7d3a784f7 100644
--- a/sound/pcmcia/pdaudiocf/pdaudiocf.h
+++ b/sound/pcmcia/pdaudiocf/pdaudiocf.h
@@ -88,10 +88,9 @@ struct snd_pdacf {
 	unsigned long port;
 	int irq;
 
-	spinlock_t reg_lock;
+	struct mutex reg_lock;
 	unsigned short regmap[8];
 	unsigned short suspend_reg_scr;
-	struct tasklet_struct tq;
 
 	spinlock_t ak4117_lock;
 	struct ak4117 *ak4117;
@@ -136,7 +135,7 @@ int snd_pdacf_resume(struct snd_pdacf *chip);
 #endif
 int snd_pdacf_pcm_new(struct snd_pdacf *chip);
 irqreturn_t pdacf_interrupt(int irq, void *dev);
-void pdacf_tasklet(unsigned long private_data);
+irqreturn_t pdacf_threaded_irq(int irq, void *dev);
 void pdacf_reinit(struct snd_pdacf *chip, int resume);
 
 #endif /* __PDAUDIOCF_H */
diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf_core.c b/sound/pcmcia/pdaudiocf/pdaudiocf_core.c
index ea0adfb984ad..d724ab0653cf 100644
--- a/sound/pcmcia/pdaudiocf/pdaudiocf_core.c
+++ b/sound/pcmcia/pdaudiocf/pdaudiocf_core.c
@@ -162,9 +162,8 @@ struct snd_pdacf *snd_pdacf_create(struct snd_card *card)
 	if (chip == NULL)
 		return NULL;
 	chip->card = card;
-	spin_lock_init(&chip->reg_lock);
+	mutex_init(&chip->reg_lock);
 	spin_lock_init(&chip->ak4117_lock);
-	tasklet_init(&chip->tq, pdacf_tasklet, (unsigned long)chip);
 	card->private_data = chip;
 
 	pdacf_proc_init(chip);
@@ -174,19 +173,18 @@ struct snd_pdacf *snd_pdacf_create(struct snd_card *card)
 static void snd_pdacf_ak4117_change(struct ak4117 *ak4117, unsigned char c0, unsigned char c1)
 {
 	struct snd_pdacf *chip = ak4117->change_callback_private;
-	unsigned long flags;
 	u16 val;
 
 	if (!(c0 & AK4117_UNLCK))
 		return;
-	spin_lock_irqsave(&chip->reg_lock, flags);
+	mutex_lock(&chip->reg_lock);
 	val = chip->regmap[PDAUDIOCF_REG_SCR>>1];
 	if (ak4117->rcs0 & AK4117_UNLCK)
 		val |= PDAUDIOCF_BLUE_LED_OFF;
 	else
 		val &= ~PDAUDIOCF_BLUE_LED_OFF;
 	pdacf_reg_write(chip, PDAUDIOCF_REG_SCR, val);
-	spin_unlock_irqrestore(&chip->reg_lock, flags);
+	mutex_unlock(&chip->reg_lock);
 }
 
 int snd_pdacf_ak4117_create(struct snd_pdacf *chip)
diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf_irq.c b/sound/pcmcia/pdaudiocf/pdaudiocf_irq.c
index dcd32201bc8c..ecf0fbd91794 100644
--- a/sound/pcmcia/pdaudiocf/pdaudiocf_irq.c
+++ b/sound/pcmcia/pdaudiocf/pdaudiocf_irq.c
@@ -30,6 +30,7 @@ irqreturn_t pdacf_interrupt(int irq, void *dev)
 {
 	struct snd_pdacf *chip = dev;
 	unsigned short stat;
+	bool wake_thread = false;
 
 	if ((chip->chip_status & (PDAUDIOCF_STAT_IS_STALE|
 				  PDAUDIOCF_STAT_IS_CONFIGURED|
@@ -41,13 +42,13 @@ irqreturn_t pdacf_interrupt(int irq, void *dev)
 		if (stat & PDAUDIOCF_IRQOVR)	/* should never happen */
 			snd_printk(KERN_ERR "PDAUDIOCF SRAM buffer overrun detected!\n");
 		if (chip->pcm_substream)
-			tasklet_schedule(&chip->tq);
+			wake_thread = true;
 		if (!(stat & PDAUDIOCF_IRQAKM))
 			stat |= PDAUDIOCF_IRQAKM;	/* check rate */
 	}
 	if (get_irq_regs() != NULL)
 		snd_ak4117_check_rate_and_errors(chip->ak4117, 0);
-	return IRQ_HANDLED;
+	return wake_thread ? IRQ_WAKE_THREAD : IRQ_HANDLED;
 }
 
 static inline void pdacf_transfer_mono16(u16 *dst, u16 xor, unsigned int size, unsigned long rdp_port)
@@ -256,16 +257,16 @@ static void pdacf_transfer(struct snd_pdacf *chip, unsigned int size, unsigned i
 	}
 }
 
-void pdacf_tasklet(unsigned long private_data)
+irqreturn_t pdacf_threaded_irq(int irq, void *dev)
 {
-	struct snd_pdacf *chip = (struct snd_pdacf *) private_data;
+	struct snd_pdacf *chip = dev;
 	int size, off, cont, rdp, wdp;
 
 	if ((chip->chip_status & (PDAUDIOCF_STAT_IS_STALE|PDAUDIOCF_STAT_IS_CONFIGURED)) != PDAUDIOCF_STAT_IS_CONFIGURED)
-		return;
+		return IRQ_HANDLED;
 	
 	if (chip->pcm_substream == NULL || chip->pcm_substream->runtime == NULL || !snd_pcm_running(chip->pcm_substream))
-		return;
+		return IRQ_HANDLED;
 
 	rdp = inw(chip->port + PDAUDIOCF_REG_RDP);
 	wdp = inw(chip->port + PDAUDIOCF_REG_WDP);
@@ -311,15 +312,15 @@ void pdacf_tasklet(unsigned long private_data)
 		size -= cont;
 	}
 #endif
-	spin_lock(&chip->reg_lock);
+	mutex_lock(&chip->reg_lock);
 	while (chip->pcm_tdone >= chip->pcm_period) {
 		chip->pcm_hwptr += chip->pcm_period;
 		chip->pcm_hwptr %= chip->pcm_size;
 		chip->pcm_tdone -= chip->pcm_period;
-		spin_unlock(&chip->reg_lock);
+		mutex_unlock(&chip->reg_lock);
 		snd_pcm_period_elapsed(chip->pcm_substream);
-		spin_lock(&chip->reg_lock);
+		mutex_lock(&chip->reg_lock);
 	}
-	spin_unlock(&chip->reg_lock);
-	/* printk(KERN_DEBUG "TASKLET: end\n"); */
+	mutex_unlock(&chip->reg_lock);
+	return IRQ_HANDLED;
 }
diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c b/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
index 43f995a3f960..b48aa0a78c19 100644
--- a/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
+++ b/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
@@ -77,7 +77,7 @@ static int pdacf_pcm_trigger(struct snd_pcm_substream *subs, int cmd)
 	default:
 		return -EINVAL;
 	}
-	spin_lock(&chip->reg_lock);
+	mutex_lock(&chip->reg_lock);
 	chip->pcm_running += inc;
 	tmp = pdacf_reg_read(chip, PDAUDIOCF_REG_SCR);
 	if (chip->pcm_running) {
@@ -91,7 +91,7 @@ static int pdacf_pcm_trigger(struct snd_pcm_substream *subs, int cmd)
 	tmp |= val;
 	pdacf_reg_write(chip, PDAUDIOCF_REG_SCR, tmp);
       __end:
-	spin_unlock(&chip->reg_lock);
+	mutex_unlock(&chip->reg_lock);
 	snd_ak4117_check_rate_and_errors(chip->ak4117, AK4117_CHECK_NO_RATE);
 	return ret;
 }
@@ -296,6 +296,7 @@ int snd_pdacf_pcm_new(struct snd_pdacf *chip)
 
 	pcm->private_data = chip;
 	pcm->info_flags = 0;
+	pcm->nonatomic = true;
 	strcpy(pcm->name, chip->card->shortname);
 	chip->pcm = pcm;
 	
diff --git a/sound/pcmcia/vx/vxp_ops.c b/sound/pcmcia/vx/vxp_ops.c
index fe33e122e372..281972913c32 100644
--- a/sound/pcmcia/vx/vxp_ops.c
+++ b/sound/pcmcia/vx/vxp_ops.c
@@ -468,12 +468,11 @@ static void vxp_write_codec_reg(struct vx_core *chip, int codec, unsigned int da
 void vx_set_mic_boost(struct vx_core *chip, int boost)
 {
 	struct snd_vxpocket *pchip = (struct snd_vxpocket *)chip;
-	unsigned long flags;
 
 	if (chip->chip_status & VX_STAT_IS_STALE)
 		return;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	if (pchip->regCDSP & P24_CDSP_MICS_SEL_MASK) {
 		if (boost) {
 			/* boost: 38 dB */
@@ -486,7 +485,7 @@ void vx_set_mic_boost(struct vx_core *chip, int boost)
                 }
 		vx_outb(chip, CDSP, pchip->regCDSP);
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 /*
@@ -511,17 +510,16 @@ static int vx_compute_mic_level(int level)
 void vx_set_mic_level(struct vx_core *chip, int level)
 {
 	struct snd_vxpocket *pchip = (struct snd_vxpocket *)chip;
-	unsigned long flags;
 
 	if (chip->chip_status & VX_STAT_IS_STALE)
 		return;
 
-	spin_lock_irqsave(&chip->lock, flags);
+	mutex_lock(&chip->lock);
 	if (pchip->regCDSP & VXP_CDSP_MIC_SEL_MASK) {
 		level = vx_compute_mic_level(level);
 		vx_outb(chip, MICRO, level);
 	}
-	spin_unlock_irqrestore(&chip->lock, flags);
+	mutex_unlock(&chip->lock);
 }
 
 
diff --git a/sound/pcmcia/vx/vxpocket.c b/sound/pcmcia/vx/vxpocket.c
index 786e7e139c9e..92ec11456e3a 100644
--- a/sound/pcmcia/vx/vxpocket.c
+++ b/sound/pcmcia/vx/vxpocket.c
@@ -62,6 +62,7 @@ static unsigned int card_alloc;
  */
 static void vxpocket_release(struct pcmcia_device *link)
 {
+	free_irq(link->irq, link->priv);
 	pcmcia_disable_device(link);
 }
 
@@ -227,11 +228,13 @@ static int vxpocket_config(struct pcmcia_device *link)
 
 	ret = pcmcia_request_io(link);
 	if (ret)
-		goto failed;
+		goto failed_preirq;
 
-	ret = pcmcia_request_irq(link, snd_vx_irq_handler);
+	ret = request_threaded_irq(link->irq, snd_vx_irq_handler,
+				   snd_vx_threaded_irq_handler,
+				   IRQF_SHARED, link->devname, link->priv);
 	if (ret)
-		goto failed;
+		goto failed_preirq;
 
 	ret = pcmcia_enable_device(link);
 	if (ret)
@@ -245,7 +248,9 @@ static int vxpocket_config(struct pcmcia_device *link)
 
 	return 0;
 
-failed:
+ failed:
+	free_irq(link->irq, link->priv);
+failed_preirq:
 	pcmcia_disable_device(link);
 	return -ENODEV;
 }
diff --git a/sound/soc/codecs/88pm860x-codec.c b/sound/soc/codecs/88pm860x-codec.c
index 922006dd0583..e88a6b67f781 100644
--- a/sound/soc/codecs/88pm860x-codec.c
+++ b/sound/soc/codecs/88pm860x-codec.c
@@ -146,7 +146,7 @@ struct pm860x_priv {
 	struct pm860x_det	det;
 
 	int			irq[4];
-	unsigned char		name[4][MAX_NAME_LEN];
+	unsigned char		name[4][MAX_NAME_LEN+1];
 };
 
 /* -9450dB to 0dB in 150dB steps ( mute instead of -9450dB) */
@@ -1337,8 +1337,6 @@ static int pm860x_probe(struct snd_soc_codec *codec)
 		}
 	}
 
-	pm860x_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
 	return 0;
 
 out:
@@ -1354,7 +1352,6 @@ static int pm860x_remove(struct snd_soc_codec *codec)
 
 	for (i = 3; i >= 0; i--)
 		free_irq(pm860x->irq[i], pm860x);
-	pm860x_set_bias_level(codec, SND_SOC_BIAS_OFF);
 	return 0;
 }
 
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 8838838e25ed..a68d1731a8fd 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -43,6 +43,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_ALC5623 if I2C
 	select SND_SOC_ALC5632 if I2C
 	select SND_SOC_CQ0093VC if MFD_DAVINCI_VOICECODEC
+	select SND_SOC_CS35L32 if I2C
 	select SND_SOC_CS42L51_I2C if I2C
 	select SND_SOC_CS42L52 if I2C && INPUT
 	select SND_SOC_CS42L56 if I2C && INPUT
@@ -56,7 +57,10 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_DA7213 if I2C
 	select SND_SOC_DA732X if I2C
 	select SND_SOC_DA9055 if I2C
+	select SND_SOC_DMIC
 	select SND_SOC_BT_SCO
+	select SND_SOC_ES8328_SPI if SPI_MASTER
+	select SND_SOC_ES8328_I2C if I2C
 	select SND_SOC_ISABELLE if I2C
 	select SND_SOC_JZ4740_CODEC
 	select SND_SOC_LM4857 if I2C
@@ -90,6 +94,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_SSM2518 if I2C
 	select SND_SOC_SSM2602_SPI if SPI_MASTER
 	select SND_SOC_SSM2602_I2C if I2C
+	select SND_SOC_SSM4567 if I2C
 	select SND_SOC_STA32X if I2C
 	select SND_SOC_STA350 if I2C
 	select SND_SOC_STA529 if I2C
@@ -323,6 +328,10 @@ config SND_SOC_ALC5632
 config SND_SOC_CQ0093VC
 	tristate
 
+config SND_SOC_CS35L32
+	tristate "Cirrus Logic CS35L32 CODEC"
+	depends on I2C
+
 config SND_SOC_CS42L51
 	tristate
 
@@ -405,6 +414,17 @@ config SND_SOC_DMIC
 config SND_SOC_HDMI_CODEC
        tristate "HDMI stub CODEC"
 
+config SND_SOC_ES8328
+	tristate "Everest Semi ES8328 CODEC"
+
+config SND_SOC_ES8328_I2C
+	tristate
+	select SND_SOC_ES8328
+
+config SND_SOC_ES8328_SPI
+	tristate
+	select SND_SOC_ES8328
+
 config SND_SOC_ISABELLE
         tristate
 
@@ -464,6 +484,7 @@ config SND_SOC_RL6231
 
 config SND_SOC_RT286
 	tristate
+	depends on I2C
 
 config SND_SOC_RT5631
 	tristate
@@ -520,12 +541,20 @@ config SND_SOC_SSM2602
 	tristate
 
 config SND_SOC_SSM2602_SPI
+	tristate "Analog Devices SSM2602 CODEC - SPI"
+	depends on SPI_MASTER
 	select SND_SOC_SSM2602
-	tristate
+	select REGMAP_SPI
 
 config SND_SOC_SSM2602_I2C
+	tristate "Analog Devices SSM2602 CODEC - I2C"
+	depends on I2C
 	select SND_SOC_SSM2602
-	tristate
+	select REGMAP_I2C
+
+config SND_SOC_SSM4567
+	tristate "Analog Devices ssm4567 amplifier driver support"
+	depends on I2C
 
 config SND_SOC_STA32X
 	tristate
@@ -712,7 +741,8 @@ config SND_SOC_WM8974
 	tristate
 
 config SND_SOC_WM8978
-	tristate
+	tristate "Wolfson Microelectronics WM8978 codec"
+	depends on I2C
 
 config SND_SOC_WM8983
 	tristate
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index 20afe0f0c5be..5dce451661e4 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -32,6 +32,7 @@ snd-soc-ak4671-objs := ak4671.o
 snd-soc-ak5386-objs := ak5386.o
 snd-soc-arizona-objs := arizona.o
 snd-soc-cq93vc-objs := cq93vc.o
+snd-soc-cs35l32-objs := cs35l32.o
 snd-soc-cs42l51-objs := cs42l51.o
 snd-soc-cs42l51-i2c-objs := cs42l51-i2c.o
 snd-soc-cs42l52-objs := cs42l52.o
@@ -49,6 +50,9 @@ snd-soc-da732x-objs := da732x.o
 snd-soc-da9055-objs := da9055.o
 snd-soc-bt-sco-objs := bt-sco.o
 snd-soc-dmic-objs := dmic.o
+snd-soc-es8328-objs := es8328.o
+snd-soc-es8328-i2c-objs := es8328-i2c.o
+snd-soc-es8328-spi-objs := es8328-spi.o
 snd-soc-isabelle-objs := isabelle.o
 snd-soc-jz4740-codec-objs := jz4740.o
 snd-soc-l3-objs := l3.o
@@ -91,6 +95,7 @@ snd-soc-ssm2518-objs := ssm2518.o
 snd-soc-ssm2602-objs := ssm2602.o
 snd-soc-ssm2602-spi-objs := ssm2602-spi.o
 snd-soc-ssm2602-i2c-objs := ssm2602-i2c.o
+snd-soc-ssm4567-objs := ssm4567.o
 snd-soc-sta32x-objs := sta32x.o
 snd-soc-sta350-objs := sta350.o
 snd-soc-sta529-objs := sta529.o
@@ -203,6 +208,7 @@ obj-$(CONFIG_SND_SOC_ALC5623)    += snd-soc-alc5623.o
 obj-$(CONFIG_SND_SOC_ALC5632)	+= snd-soc-alc5632.o
 obj-$(CONFIG_SND_SOC_ARIZONA)	+= snd-soc-arizona.o
 obj-$(CONFIG_SND_SOC_CQ0093VC) += snd-soc-cq93vc.o
+obj-$(CONFIG_SND_SOC_CS35L32)	+= snd-soc-cs35l32.o
 obj-$(CONFIG_SND_SOC_CS42L51)	+= snd-soc-cs42l51.o
 obj-$(CONFIG_SND_SOC_CS42L51_I2C)	+= snd-soc-cs42l51-i2c.o
 obj-$(CONFIG_SND_SOC_CS42L52)	+= snd-soc-cs42l52.o
@@ -220,6 +226,9 @@ obj-$(CONFIG_SND_SOC_DA732X)	+= snd-soc-da732x.o
 obj-$(CONFIG_SND_SOC_DA9055)	+= snd-soc-da9055.o
 obj-$(CONFIG_SND_SOC_BT_SCO)	+= snd-soc-bt-sco.o
 obj-$(CONFIG_SND_SOC_DMIC)	+= snd-soc-dmic.o
+obj-$(CONFIG_SND_SOC_ES8328)	+= snd-soc-es8328.o
+obj-$(CONFIG_SND_SOC_ES8328_I2C)+= snd-soc-es8328-i2c.o
+obj-$(CONFIG_SND_SOC_ES8328_SPI)+= snd-soc-es8328-spi.o
 obj-$(CONFIG_SND_SOC_ISABELLE)	+= snd-soc-isabelle.o
 obj-$(CONFIG_SND_SOC_JZ4740_CODEC)	+= snd-soc-jz4740-codec.o
 obj-$(CONFIG_SND_SOC_L3)	+= snd-soc-l3.o
@@ -258,6 +267,7 @@ obj-$(CONFIG_SND_SOC_SSM2518)	+= snd-soc-ssm2518.o
 obj-$(CONFIG_SND_SOC_SSM2602)	+= snd-soc-ssm2602.o
 obj-$(CONFIG_SND_SOC_SSM2602_SPI)	+= snd-soc-ssm2602-spi.o
 obj-$(CONFIG_SND_SOC_SSM2602_I2C)	+= snd-soc-ssm2602-i2c.o
+obj-$(CONFIG_SND_SOC_SSM4567)	+= snd-soc-ssm4567.o
 obj-$(CONFIG_SND_SOC_STA32X)   += snd-soc-sta32x.o
 obj-$(CONFIG_SND_SOC_STA350)   += snd-soc-sta350.o
 obj-$(CONFIG_SND_SOC_STA529)   += snd-soc-sta529.o
diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c
index 1fb4402bf72d..fd43827bb856 100644
--- a/sound/soc/codecs/ab8500-codec.c
+++ b/sound/soc/codecs/ab8500-codec.c
@@ -56,8 +56,7 @@
 #define GPIO31_DIR_OUTPUT			0x40
 
 /* Macrocell register definitions */
-#define AB8500_CTRL3_REG			0x0200
-#define AB8500_GPIO_DIR4_REG			0x1013
+#define AB8500_GPIO_DIR4_REG			0x13 /* Bank AB8500_MISC */
 
 /* Nr of FIR/IIR-coeff banks in ANC-block */
 #define AB8500_NR_OF_ANC_COEFF_BANKS		2
@@ -126,6 +125,8 @@ struct ab8500_codec_drvdata_dbg {
 
 /* Private data for AB8500 device-driver */
 struct ab8500_codec_drvdata {
+	struct regmap *regmap;
+
 	/* Sidetone */
 	long *sid_fir_values;
 	enum sid_state sid_status;
@@ -166,49 +167,35 @@ static inline const char *amic_type_str(enum amic_type type)
  */
 
 /* Read a register from the audio-bank of AB8500 */
-static unsigned int ab8500_codec_read_reg(struct snd_soc_codec *codec,
-					unsigned int reg)
+static int ab8500_codec_read_reg(void *context, unsigned int reg,
+				 unsigned int *value)
 {
+	struct device *dev = context;
 	int status;
-	unsigned int value = 0;
 
 	u8 value8;
-	status = abx500_get_register_interruptible(codec->dev, AB8500_AUDIO,
-						reg, &value8);
-	if (status < 0) {
-		dev_err(codec->dev,
-			"%s: ERROR: Register (0x%02x:0x%02x) read failed (%d).\n",
-			__func__, (u8)AB8500_AUDIO, (u8)reg, status);
-	} else {
-		dev_dbg(codec->dev,
-			"%s: Read 0x%02x from register 0x%02x:0x%02x\n",
-			__func__, value8, (u8)AB8500_AUDIO, (u8)reg);
-		value = (unsigned int)value8;
-	}
+	status = abx500_get_register_interruptible(dev, AB8500_AUDIO,
+						   reg, &value8);
+	*value = (unsigned int)value8;
 
-	return value;
+	return status;
 }
 
 /* Write to a register in the audio-bank of AB8500 */
-static int ab8500_codec_write_reg(struct snd_soc_codec *codec,
-				unsigned int reg, unsigned int value)
+static int ab8500_codec_write_reg(void *context, unsigned int reg,
+				  unsigned int value)
 {
-	int status;
-
-	status = abx500_set_register_interruptible(codec->dev, AB8500_AUDIO,
-						reg, value);
-	if (status < 0)
-		dev_err(codec->dev,
-			"%s: ERROR: Register (%02x:%02x) write failed (%d).\n",
-			__func__, (u8)AB8500_AUDIO, (u8)reg, status);
-	else
-		dev_dbg(codec->dev,
-			"%s: Wrote 0x%02x into register %02x:%02x\n",
-			__func__, (u8)value, (u8)AB8500_AUDIO, (u8)reg);
+	struct device *dev = context;
 
-	return status;
+	return abx500_set_register_interruptible(dev, AB8500_AUDIO,
+						 reg, value);
 }
 
+static const struct regmap_config ab8500_codec_regmap = {
+	.reg_read = ab8500_codec_read_reg,
+	.reg_write = ab8500_codec_write_reg,
+};
+
 /*
  * Controls - DAPM
  */
@@ -1968,16 +1955,16 @@ static int ab8500_audio_setup_mics(struct snd_soc_codec *codec,
 	dev_dbg(codec->dev, "%s: Enter.\n", __func__);
 
 	/* Set DMic-clocks to outputs */
-	status = abx500_get_register_interruptible(codec->dev, (u8)AB8500_MISC,
-						(u8)AB8500_GPIO_DIR4_REG,
+	status = abx500_get_register_interruptible(codec->dev, AB8500_MISC,
+						AB8500_GPIO_DIR4_REG,
 						&value8);
 	if (status < 0)
 		return status;
 	value = value8 | GPIO27_DIR_OUTPUT | GPIO29_DIR_OUTPUT |
 		GPIO31_DIR_OUTPUT;
 	status = abx500_set_register_interruptible(codec->dev,
-						(u8)AB8500_MISC,
-						(u8)AB8500_GPIO_DIR4_REG,
+						AB8500_MISC,
+						AB8500_GPIO_DIR4_REG,
 						value);
 	if (status < 0)
 		return status;
@@ -2565,9 +2552,6 @@ static int ab8500_codec_probe(struct snd_soc_codec *codec)
 
 static struct snd_soc_codec_driver ab8500_codec_driver = {
 	.probe =		ab8500_codec_probe,
-	.read =			ab8500_codec_read_reg,
-	.write =		ab8500_codec_write_reg,
-	.reg_word_size =	sizeof(u8),
 	.controls =		ab8500_ctrls,
 	.num_controls =		ARRAY_SIZE(ab8500_ctrls),
 	.dapm_widgets =		ab8500_dapm_widgets,
@@ -2592,6 +2576,15 @@ static int ab8500_codec_driver_probe(struct platform_device *pdev)
 	drvdata->anc_status = ANC_UNCONFIGURED;
 	dev_set_drvdata(&pdev->dev, drvdata);
 
+	drvdata->regmap = devm_regmap_init(&pdev->dev, NULL, &pdev->dev,
+					   &ab8500_codec_regmap);
+	if (IS_ERR(drvdata->regmap)) {
+		status = PTR_ERR(drvdata->regmap);
+		dev_err(&pdev->dev, "%s: Failed to allocate regmap: %d\n",
+			__func__, status);
+		return status;
+	}
+
 	dev_dbg(&pdev->dev, "%s: Register codec.\n", __func__);
 	status = snd_soc_register_codec(&pdev->dev, &ab8500_codec_driver,
 				ab8500_codec_dai,
diff --git a/sound/soc/codecs/ac97.c b/sound/soc/codecs/ac97.c
index e889e1b84192..bd9b1839c8b0 100644
--- a/sound/soc/codecs/ac97.c
+++ b/sound/soc/codecs/ac97.c
@@ -69,19 +69,6 @@ static struct snd_soc_dai_driver ac97_dai = {
 	.ops = &ac97_dai_ops,
 };
 
-static unsigned int ac97_read(struct snd_soc_codec *codec,
-	unsigned int reg)
-{
-	return soc_ac97_ops->read(codec->ac97, reg);
-}
-
-static int ac97_write(struct snd_soc_codec *codec, unsigned int reg,
-	unsigned int val)
-{
-	soc_ac97_ops->write(codec->ac97, reg, val);
-	return 0;
-}
-
 static int ac97_soc_probe(struct snd_soc_codec *codec)
 {
 	struct snd_ac97_bus *ac97_bus;
@@ -122,8 +109,6 @@ static int ac97_soc_resume(struct snd_soc_codec *codec)
 #endif
 
 static struct snd_soc_codec_driver soc_codec_dev_ac97 = {
-	.write =	ac97_write,
-	.read =		ac97_read,
 	.probe = 	ac97_soc_probe,
 	.suspend =	ac97_soc_suspend,
 	.resume =	ac97_soc_resume,
diff --git a/sound/soc/codecs/adau1373.c b/sound/soc/codecs/adau1373.c
index 1ff7d4d027e9..7c784ad3e8b2 100644
--- a/sound/soc/codecs/adau1373.c
+++ b/sound/soc/codecs/adau1373.c
@@ -1448,29 +1448,10 @@ static int adau1373_set_bias_level(struct snd_soc_codec *codec,
 	return 0;
 }
 
-static int adau1373_remove(struct snd_soc_codec *codec)
-{
-	adau1373_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	return 0;
-}
-
-static int adau1373_suspend(struct snd_soc_codec *codec)
-{
-	struct adau1373 *adau1373 = snd_soc_codec_get_drvdata(codec);
-	int ret;
-
-	ret = adau1373_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	regcache_cache_only(adau1373->regmap, true);
-
-	return ret;
-}
-
 static int adau1373_resume(struct snd_soc_codec *codec)
 {
 	struct adau1373 *adau1373 = snd_soc_codec_get_drvdata(codec);
 
-	regcache_cache_only(adau1373->regmap, false);
-	adau1373_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
 	regcache_sync(adau1373->regmap);
 
 	return 0;
@@ -1501,8 +1482,6 @@ static const struct regmap_config adau1373_regmap_config = {
 
 static struct snd_soc_codec_driver adau1373_codec_driver = {
 	.probe =	adau1373_probe,
-	.remove =	adau1373_remove,
-	.suspend =	adau1373_suspend,
 	.resume =	adau1373_resume,
 	.set_bias_level = adau1373_set_bias_level,
 	.idle_bias_off = true,
diff --git a/sound/soc/codecs/adau1761.c b/sound/soc/codecs/adau1761.c
index 848cab839553..5518ebd6947c 100644
--- a/sound/soc/codecs/adau1761.c
+++ b/sound/soc/codecs/adau1761.c
@@ -714,9 +714,9 @@ static int adau1761_codec_probe(struct snd_soc_codec *codec)
 
 static const struct snd_soc_codec_driver adau1761_codec_driver = {
 	.probe = adau1761_codec_probe,
-	.suspend = adau17x1_suspend,
 	.resume	= adau17x1_resume,
 	.set_bias_level	= adau1761_set_bias_level,
+	.suspend_bias_off = true,
 
 	.controls = adau1761_controls,
 	.num_controls = ARRAY_SIZE(adau1761_controls),
diff --git a/sound/soc/codecs/adau1781.c b/sound/soc/codecs/adau1781.c
index 045a61413840..e9fc00fb13dd 100644
--- a/sound/soc/codecs/adau1781.c
+++ b/sound/soc/codecs/adau1781.c
@@ -446,9 +446,9 @@ static int adau1781_codec_probe(struct snd_soc_codec *codec)
 
 static const struct snd_soc_codec_driver adau1781_codec_driver = {
 	.probe = adau1781_codec_probe,
-	.suspend = adau17x1_suspend,
 	.resume = adau17x1_resume,
 	.set_bias_level = adau1781_set_bias_level,
+	.suspend_bias_off = true,
 
 	.controls = adau1781_controls,
 	.num_controls = ARRAY_SIZE(adau1781_controls),
diff --git a/sound/soc/codecs/adau17x1.c b/sound/soc/codecs/adau17x1.c
index 0b659704e60c..3e16c1c64115 100644
--- a/sound/soc/codecs/adau17x1.c
+++ b/sound/soc/codecs/adau17x1.c
@@ -815,13 +815,6 @@ int adau17x1_add_routes(struct snd_soc_codec *codec)
 }
 EXPORT_SYMBOL_GPL(adau17x1_add_routes);
 
-int adau17x1_suspend(struct snd_soc_codec *codec)
-{
-	codec->driver->set_bias_level(codec, SND_SOC_BIAS_OFF);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(adau17x1_suspend);
-
 int adau17x1_resume(struct snd_soc_codec *codec)
 {
 	struct adau *adau = snd_soc_codec_get_drvdata(codec);
@@ -829,7 +822,6 @@ int adau17x1_resume(struct snd_soc_codec *codec)
 	if (adau->switch_mode)
 		adau->switch_mode(codec->dev);
 
-	codec->driver->set_bias_level(codec, SND_SOC_BIAS_STANDBY);
 	regcache_sync(adau->regmap);
 
 	return 0;
diff --git a/sound/soc/codecs/adau17x1.h b/sound/soc/codecs/adau17x1.h
index 3ffabaf4c7a8..e4a557fd7155 100644
--- a/sound/soc/codecs/adau17x1.h
+++ b/sound/soc/codecs/adau17x1.h
@@ -52,7 +52,6 @@ int adau17x1_set_micbias_voltage(struct snd_soc_codec *codec,
 	enum adau17x1_micbias_voltage micbias);
 bool adau17x1_readable_register(struct device *dev, unsigned int reg);
 bool adau17x1_volatile_register(struct device *dev, unsigned int reg);
-int adau17x1_suspend(struct snd_soc_codec *codec);
 int adau17x1_resume(struct snd_soc_codec *codec);
 
 extern const struct snd_soc_dai_ops adau17x1_dai_ops;
diff --git a/sound/soc/codecs/adav80x.c b/sound/soc/codecs/adav80x.c
index c43b93fdf0df..ce3cdca9fc62 100644
--- a/sound/soc/codecs/adav80x.c
+++ b/sound/soc/codecs/adav80x.c
@@ -812,42 +812,23 @@ static int adav80x_probe(struct snd_soc_codec *codec)
 	/* Disable DAC zero flag */
 	regmap_write(adav80x->regmap, ADAV80X_DAC_CTRL3, 0x6);
 
-	return adav80x_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-}
-
-static int adav80x_suspend(struct snd_soc_codec *codec)
-{
-	struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec);
-	int ret;
-
-	ret = adav80x_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	regcache_cache_only(adav80x->regmap, true);
-
-	return ret;
+	return 0;
 }
 
 static int adav80x_resume(struct snd_soc_codec *codec)
 {
 	struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec);
 
-	regcache_cache_only(adav80x->regmap, false);
-	adav80x_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
 	regcache_sync(adav80x->regmap);
 
 	return 0;
 }
 
-static int adav80x_remove(struct snd_soc_codec *codec)
-{
-	return adav80x_set_bias_level(codec, SND_SOC_BIAS_OFF);
-}
-
 static struct snd_soc_codec_driver adav80x_codec_driver = {
 	.probe = adav80x_probe,
-	.remove = adav80x_remove,
-	.suspend = adav80x_suspend,
 	.resume = adav80x_resume,
 	.set_bias_level = adav80x_set_bias_level,
+	.suspend_bias_off = true,
 
 	.set_pll = adav80x_set_pll,
 	.set_sysclk = adav80x_set_sysclk,
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 2c71f16bd661..0c05e7a7945f 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -1220,7 +1220,7 @@ static int arizona_hw_params_rate(struct snd_pcm_substream *substream,
 		break;
 	case ARIZONA_CLK_ASYNCCLK:
 		snd_soc_update_bits(codec, ARIZONA_ASYNC_SAMPLE_RATE_1,
-				    ARIZONA_ASYNC_SAMPLE_RATE_MASK, sr_val);
+				    ARIZONA_ASYNC_SAMPLE_RATE_1_MASK, sr_val);
 		if (base)
 			snd_soc_update_bits(codec, base + ARIZONA_AIF_RATE_CTRL,
 					    ARIZONA_AIF1_RATE_MASK,
diff --git a/sound/soc/codecs/cs35l32.c b/sound/soc/codecs/cs35l32.c
new file mode 100644
index 000000000000..c125925da92e
--- /dev/null
+++ b/sound/soc/codecs/cs35l32.c
@@ -0,0 +1,631 @@
+/*
+ * cs35l32.c -- CS35L32 ALSA SoC audio driver
+ *
+ * Copyright 2014 CirrusLogic, Inc.
+ *
+ * Author: Brian Austin <brian.austin@cirrus.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/version.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of_device.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/initval.h>
+#include <sound/tlv.h>
+#include <dt-bindings/sound/cs35l32.h>
+
+#include "cs35l32.h"
+
+#define CS35L32_NUM_SUPPLIES 2
+static const char *const cs35l32_supply_names[CS35L32_NUM_SUPPLIES] = {
+	"VA",
+	"VP",
+};
+
+struct  cs35l32_private {
+	struct regmap *regmap;
+	struct snd_soc_codec *codec;
+	struct regulator_bulk_data supplies[CS35L32_NUM_SUPPLIES];
+	struct cs35l32_platform_data pdata;
+	struct gpio_desc *reset_gpio;
+};
+
+static const struct reg_default cs35l32_reg_defaults[] = {
+
+	{ 0x06, 0x04 }, /* Power Ctl 1 */
+	{ 0x07, 0xE8 }, /* Power Ctl 2 */
+	{ 0x08, 0x40 }, /* Clock Ctl */
+	{ 0x09, 0x20 }, /* Low Battery Threshold */
+	{ 0x0A, 0x00 }, /* Voltage Monitor [RO] */
+	{ 0x0B, 0x40 }, /* Conv Peak Curr Protection CTL */
+	{ 0x0C, 0x07 }, /* IMON Scaling */
+	{ 0x0D, 0x03 }, /* Audio/LED Pwr Manager */
+	{ 0x0F, 0x20 }, /* Serial Port Control */
+	{ 0x10, 0x14 }, /* Class D Amp CTL */
+	{ 0x11, 0x00 }, /* Protection Release CTL */
+	{ 0x12, 0xFF }, /* Interrupt Mask 1 */
+	{ 0x13, 0xFF }, /* Interrupt Mask 2 */
+	{ 0x14, 0xFF }, /* Interrupt Mask 3 */
+	{ 0x19, 0x00 }, /* LED Flash Mode Current */
+	{ 0x1A, 0x00 }, /* LED Movie Mode Current */
+	{ 0x1B, 0x20 }, /* LED Flash Timer */
+	{ 0x1C, 0x00 }, /* LED Flash Inhibit Current */
+};
+
+static bool cs35l32_readable_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case CS35L32_DEVID_AB:
+	case CS35L32_DEVID_CD:
+	case CS35L32_DEVID_E:
+	case CS35L32_FAB_ID:
+	case CS35L32_REV_ID:
+	case CS35L32_PWRCTL1:
+	case CS35L32_PWRCTL2:
+	case CS35L32_CLK_CTL:
+	case CS35L32_BATT_THRESHOLD:
+	case CS35L32_VMON:
+	case CS35L32_BST_CPCP_CTL:
+	case CS35L32_IMON_SCALING:
+	case CS35L32_AUDIO_LED_MNGR:
+	case CS35L32_ADSP_CTL:
+	case CS35L32_CLASSD_CTL:
+	case CS35L32_PROTECT_CTL:
+	case CS35L32_INT_MASK_1:
+	case CS35L32_INT_MASK_2:
+	case CS35L32_INT_MASK_3:
+	case CS35L32_INT_STATUS_1:
+	case CS35L32_INT_STATUS_2:
+	case CS35L32_INT_STATUS_3:
+	case CS35L32_LED_STATUS:
+	case CS35L32_FLASH_MODE:
+	case CS35L32_MOVIE_MODE:
+	case CS35L32_FLASH_TIMER:
+	case CS35L32_FLASH_INHIBIT:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool cs35l32_volatile_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case CS35L32_DEVID_AB:
+	case CS35L32_DEVID_CD:
+	case CS35L32_DEVID_E:
+	case CS35L32_FAB_ID:
+	case CS35L32_REV_ID:
+	case CS35L32_INT_STATUS_1:
+	case CS35L32_INT_STATUS_2:
+	case CS35L32_INT_STATUS_3:
+	case CS35L32_LED_STATUS:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool cs35l32_precious_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case CS35L32_INT_STATUS_1:
+	case CS35L32_INT_STATUS_2:
+	case CS35L32_INT_STATUS_3:
+	case CS35L32_LED_STATUS:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static DECLARE_TLV_DB_SCALE(classd_ctl_tlv, 900, 300, 0);
+
+static const struct snd_kcontrol_new imon_ctl =
+	SOC_DAPM_SINGLE("Switch", CS35L32_PWRCTL2, 6, 1, 1);
+
+static const struct snd_kcontrol_new vmon_ctl =
+	SOC_DAPM_SINGLE("Switch", CS35L32_PWRCTL2, 7, 1, 1);
+
+static const struct snd_kcontrol_new vpmon_ctl =
+	SOC_DAPM_SINGLE("Switch", CS35L32_PWRCTL2, 5, 1, 1);
+
+static const struct snd_kcontrol_new cs35l32_snd_controls[] = {
+	SOC_SINGLE_TLV("Speaker Volume", CS35L32_CLASSD_CTL,
+		       3, 0x04, 1, classd_ctl_tlv),
+	SOC_SINGLE("Zero Cross Switch", CS35L32_CLASSD_CTL, 2, 1, 0),
+	SOC_SINGLE("Gain Manager Switch", CS35L32_AUDIO_LED_MNGR, 3, 1, 0),
+};
+
+static const struct snd_soc_dapm_widget cs35l32_dapm_widgets[] = {
+
+	SND_SOC_DAPM_SUPPLY("BOOST", CS35L32_PWRCTL1, 2, 1, NULL, 0),
+	SND_SOC_DAPM_OUT_DRV("Speaker", CS35L32_PWRCTL1, 7, 1, NULL, 0),
+
+	SND_SOC_DAPM_AIF_OUT("SDOUT", NULL, 0, CS35L32_PWRCTL2, 3, 1),
+
+	SND_SOC_DAPM_INPUT("VP"),
+	SND_SOC_DAPM_INPUT("ISENSE"),
+	SND_SOC_DAPM_INPUT("VSENSE"),
+
+	SND_SOC_DAPM_SWITCH("VMON ADC", CS35L32_PWRCTL2, 7, 1, &vmon_ctl),
+	SND_SOC_DAPM_SWITCH("IMON ADC", CS35L32_PWRCTL2, 6, 1, &imon_ctl),
+	SND_SOC_DAPM_SWITCH("VPMON ADC", CS35L32_PWRCTL2, 5, 1, &vpmon_ctl),
+};
+
+static const struct snd_soc_dapm_route cs35l32_audio_map[] = {
+
+	{"Speaker", NULL, "BOOST"},
+
+	{"VMON ADC", NULL, "VSENSE"},
+	{"IMON ADC", NULL, "ISENSE"},
+	{"VPMON ADC", NULL, "VP"},
+
+	{"SDOUT", "Switch", "VMON ADC"},
+	{"SDOUT",  "Switch", "IMON ADC"},
+	{"SDOUT", "Switch", "VPMON ADC"},
+
+	{"Capture", NULL, "SDOUT"},
+};
+
+static int cs35l32_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
+{
+	struct snd_soc_codec *codec = codec_dai->codec;
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		snd_soc_update_bits(codec, CS35L32_ADSP_CTL,
+				    CS35L32_ADSP_MASTER_MASK,
+				CS35L32_ADSP_MASTER_MASK);
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		snd_soc_update_bits(codec, CS35L32_ADSP_CTL,
+				    CS35L32_ADSP_MASTER_MASK, 0);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int cs35l32_set_tristate(struct snd_soc_dai *dai, int tristate)
+{
+	struct snd_soc_codec *codec = dai->codec;
+
+	return snd_soc_update_bits(codec, CS35L32_PWRCTL2,
+					CS35L32_SDOUT_3ST, tristate << 3);
+}
+
+static const struct snd_soc_dai_ops cs35l32_ops = {
+	.set_fmt = cs35l32_set_dai_fmt,
+	.set_tristate = cs35l32_set_tristate,
+};
+
+static struct snd_soc_dai_driver cs35l32_dai[] = {
+	{
+		.name = "cs35l32-monitor",
+		.id = 0,
+		.capture = {
+			.stream_name = "Capture",
+			.channels_min = 2,
+			.channels_max = 2,
+			.rates = CS35L32_RATES,
+			.formats = CS35L32_FORMATS,
+		},
+		.ops = &cs35l32_ops,
+		.symmetric_rates = 1,
+	}
+};
+
+static int cs35l32_codec_set_sysclk(struct snd_soc_codec *codec,
+			      int clk_id, int source, unsigned int freq, int dir)
+{
+	unsigned int val;
+
+	switch (freq) {
+	case 6000000:
+		val = CS35L32_MCLK_RATIO;
+		break;
+	case 12000000:
+		val = CS35L32_MCLK_DIV2_MASK | CS35L32_MCLK_RATIO;
+		break;
+	case 6144000:
+		val = 0;
+		break;
+	case 12288000:
+		val = CS35L32_MCLK_DIV2_MASK;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return snd_soc_update_bits(codec, CS35L32_CLK_CTL,
+			CS35L32_MCLK_DIV2_MASK | CS35L32_MCLK_RATIO_MASK, val);
+}
+
+static struct snd_soc_codec_driver soc_codec_dev_cs35l32 = {
+	.set_sysclk = cs35l32_codec_set_sysclk,
+
+	.dapm_widgets = cs35l32_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(cs35l32_dapm_widgets),
+	.dapm_routes = cs35l32_audio_map,
+	.num_dapm_routes = ARRAY_SIZE(cs35l32_audio_map),
+
+	.controls = cs35l32_snd_controls,
+	.num_controls = ARRAY_SIZE(cs35l32_snd_controls),
+};
+
+/* Current and threshold powerup sequence Pg37 in datasheet */
+static const struct reg_default cs35l32_monitor_patch[] = {
+
+	{ 0x00, 0x99 },
+	{ 0x48, 0x17 },
+	{ 0x49, 0x56 },
+	{ 0x43, 0x01 },
+	{ 0x3B, 0x62 },
+	{ 0x3C, 0x80 },
+	{ 0x00, 0x00 },
+};
+
+static struct regmap_config cs35l32_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = CS35L32_MAX_REGISTER,
+	.reg_defaults = cs35l32_reg_defaults,
+	.num_reg_defaults = ARRAY_SIZE(cs35l32_reg_defaults),
+	.volatile_reg = cs35l32_volatile_register,
+	.readable_reg = cs35l32_readable_register,
+	.precious_reg = cs35l32_precious_register,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static int cs35l32_handle_of_data(struct i2c_client *i2c_client,
+				    struct cs35l32_platform_data *pdata)
+{
+	struct device_node *np = i2c_client->dev.of_node;
+	unsigned int val;
+
+	if (of_property_read_u32(np, "cirrus,sdout-share", &val) >= 0)
+		pdata->sdout_share = val;
+
+	of_property_read_u32(np, "cirrus,boost-manager", &val);
+	switch (val) {
+	case CS35L32_BOOST_MGR_AUTO:
+	case CS35L32_BOOST_MGR_AUTO_AUDIO:
+	case CS35L32_BOOST_MGR_BYPASS:
+	case CS35L32_BOOST_MGR_FIXED:
+		pdata->boost_mng = val;
+		break;
+	default:
+		dev_err(&i2c_client->dev,
+			"Wrong cirrus,boost-manager DT value %d\n", val);
+		pdata->boost_mng = CS35L32_BOOST_MGR_BYPASS;
+	}
+
+	of_property_read_u32(np, "cirrus,sdout-datacfg", &val);
+	switch (val) {
+	case CS35L32_DATA_CFG_LR_VP:
+	case CS35L32_DATA_CFG_LR_STAT:
+	case CS35L32_DATA_CFG_LR:
+	case CS35L32_DATA_CFG_LR_VPSTAT:
+		pdata->sdout_datacfg = val;
+		break;
+	default:
+		dev_err(&i2c_client->dev,
+			"Wrong cirrus,sdout-datacfg DT value %d\n", val);
+		pdata->sdout_datacfg = CS35L32_DATA_CFG_LR;
+	}
+
+	of_property_read_u32(np, "cirrus,battery-threshold", &val);
+	switch (val) {
+	case CS35L32_BATT_THRESH_3_1V:
+	case CS35L32_BATT_THRESH_3_2V:
+	case CS35L32_BATT_THRESH_3_3V:
+	case CS35L32_BATT_THRESH_3_4V:
+		pdata->batt_thresh = val;
+		break;
+	default:
+		dev_err(&i2c_client->dev,
+			"Wrong cirrus,battery-threshold DT value %d\n", val);
+		pdata->batt_thresh = CS35L32_BATT_THRESH_3_3V;
+	}
+
+	of_property_read_u32(np, "cirrus,battery-recovery", &val);
+	switch (val) {
+	case CS35L32_BATT_RECOV_3_1V:
+	case CS35L32_BATT_RECOV_3_2V:
+	case CS35L32_BATT_RECOV_3_3V:
+	case CS35L32_BATT_RECOV_3_4V:
+	case CS35L32_BATT_RECOV_3_5V:
+	case CS35L32_BATT_RECOV_3_6V:
+		pdata->batt_recov = val;
+		break;
+	default:
+		dev_err(&i2c_client->dev,
+			"Wrong cirrus,battery-recovery DT value %d\n", val);
+		pdata->batt_recov = CS35L32_BATT_RECOV_3_4V;
+	}
+
+	return 0;
+}
+
+static int cs35l32_i2c_probe(struct i2c_client *i2c_client,
+				       const struct i2c_device_id *id)
+{
+	struct cs35l32_private *cs35l32;
+	struct cs35l32_platform_data *pdata =
+		dev_get_platdata(&i2c_client->dev);
+	int ret, i;
+	unsigned int devid = 0;
+	unsigned int reg;
+
+
+	cs35l32 = devm_kzalloc(&i2c_client->dev, sizeof(struct cs35l32_private),
+			       GFP_KERNEL);
+	if (!cs35l32) {
+		dev_err(&i2c_client->dev, "could not allocate codec\n");
+		return -ENOMEM;
+	}
+
+	i2c_set_clientdata(i2c_client, cs35l32);
+
+	cs35l32->regmap = devm_regmap_init_i2c(i2c_client, &cs35l32_regmap);
+	if (IS_ERR(cs35l32->regmap)) {
+		ret = PTR_ERR(cs35l32->regmap);
+		dev_err(&i2c_client->dev, "regmap_init() failed: %d\n", ret);
+		return ret;
+	}
+
+	if (pdata) {
+		cs35l32->pdata = *pdata;
+	} else {
+		pdata = devm_kzalloc(&i2c_client->dev,
+				     sizeof(struct cs35l32_platform_data),
+				GFP_KERNEL);
+		if (!pdata) {
+			dev_err(&i2c_client->dev, "could not allocate pdata\n");
+			return -ENOMEM;
+		}
+		if (i2c_client->dev.of_node) {
+			ret = cs35l32_handle_of_data(i2c_client,
+						     &cs35l32->pdata);
+			if (ret != 0)
+				return ret;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(cs35l32->supplies); i++)
+		cs35l32->supplies[i].supply = cs35l32_supply_names[i];
+
+	ret = devm_regulator_bulk_get(&i2c_client->dev,
+				      ARRAY_SIZE(cs35l32->supplies),
+				      cs35l32->supplies);
+	if (ret != 0) {
+		dev_err(&i2c_client->dev,
+			"Failed to request supplies: %d\n", ret);
+		return ret;
+	}
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(cs35l32->supplies),
+				    cs35l32->supplies);
+	if (ret != 0) {
+		dev_err(&i2c_client->dev,
+			"Failed to enable supplies: %d\n", ret);
+		return ret;
+	}
+
+	/* Reset the Device */
+	cs35l32->reset_gpio = devm_gpiod_get(&i2c_client->dev,
+		"reset-gpios");
+	if (IS_ERR(cs35l32->reset_gpio)) {
+		ret = PTR_ERR(cs35l32->reset_gpio);
+		if (ret != -ENOENT && ret != -ENOSYS)
+			return ret;
+
+		cs35l32->reset_gpio = NULL;
+	} else {
+		ret = gpiod_direction_output(cs35l32->reset_gpio, 0);
+		if (ret)
+			return ret;
+		gpiod_set_value_cansleep(cs35l32->reset_gpio, 1);
+	}
+
+	/* initialize codec */
+	ret = regmap_read(cs35l32->regmap, CS35L32_DEVID_AB, &reg);
+	devid = (reg & 0xFF) << 12;
+
+	ret = regmap_read(cs35l32->regmap, CS35L32_DEVID_CD, &reg);
+	devid |= (reg & 0xFF) << 4;
+
+	ret = regmap_read(cs35l32->regmap, CS35L32_DEVID_E, &reg);
+	devid |= (reg & 0xF0) >> 4;
+
+	if (devid != CS35L32_CHIP_ID) {
+		ret = -ENODEV;
+		dev_err(&i2c_client->dev,
+			"CS35L32 Device ID (%X). Expected %X\n",
+			devid, CS35L32_CHIP_ID);
+		return ret;
+	}
+
+	ret = regmap_read(cs35l32->regmap, CS35L32_REV_ID, &reg);
+	if (ret < 0) {
+		dev_err(&i2c_client->dev, "Get Revision ID failed\n");
+		return ret;
+	}
+
+	ret = regmap_register_patch(cs35l32->regmap, cs35l32_monitor_patch,
+				    ARRAY_SIZE(cs35l32_monitor_patch));
+	if (ret < 0) {
+		dev_err(&i2c_client->dev, "Failed to apply errata patch\n");
+		return ret;
+	}
+
+	dev_info(&i2c_client->dev,
+		 "Cirrus Logic CS35L32, Revision: %02X\n", reg & 0xFF);
+
+	/* Setup VBOOST Management */
+	if (cs35l32->pdata.boost_mng)
+		regmap_update_bits(cs35l32->regmap, CS35L32_AUDIO_LED_MNGR,
+				   CS35L32_BOOST_MASK,
+				cs35l32->pdata.boost_mng);
+
+	/* Setup ADSP Format Config */
+	if (cs35l32->pdata.sdout_share)
+		regmap_update_bits(cs35l32->regmap, CS35L32_ADSP_CTL,
+				    CS35L32_ADSP_SHARE_MASK,
+				cs35l32->pdata.sdout_share << 3);
+
+	/* Setup ADSP Data Configuration */
+	if (cs35l32->pdata.sdout_datacfg)
+		regmap_update_bits(cs35l32->regmap, CS35L32_ADSP_CTL,
+				   CS35L32_ADSP_DATACFG_MASK,
+				cs35l32->pdata.sdout_datacfg << 4);
+
+	/* Setup Low Battery Recovery  */
+	if (cs35l32->pdata.batt_recov)
+		regmap_update_bits(cs35l32->regmap, CS35L32_BATT_THRESHOLD,
+				   CS35L32_BATT_REC_MASK,
+				cs35l32->pdata.batt_recov << 1);
+
+	/* Setup Low Battery Threshold */
+	if (cs35l32->pdata.batt_thresh)
+		regmap_update_bits(cs35l32->regmap, CS35L32_BATT_THRESHOLD,
+				   CS35L32_BATT_THRESH_MASK,
+				cs35l32->pdata.batt_thresh << 4);
+
+	/* Power down the AMP */
+	regmap_update_bits(cs35l32->regmap, CS35L32_PWRCTL1, CS35L32_PDN_AMP,
+			    CS35L32_PDN_AMP);
+
+	/* Clear MCLK Error Bit since we don't have the clock yet */
+	ret = regmap_read(cs35l32->regmap, CS35L32_INT_STATUS_1, &reg);
+
+	ret =  snd_soc_register_codec(&i2c_client->dev,
+			&soc_codec_dev_cs35l32, cs35l32_dai,
+			ARRAY_SIZE(cs35l32_dai));
+	if (ret < 0)
+		goto err_disable;
+
+	return 0;
+
+err_disable:
+	regulator_bulk_disable(ARRAY_SIZE(cs35l32->supplies),
+			       cs35l32->supplies);
+	return ret;
+}
+
+static int cs35l32_i2c_remove(struct i2c_client *i2c_client)
+{
+	struct cs35l32_private *cs35l32 = i2c_get_clientdata(i2c_client);
+
+	snd_soc_unregister_codec(&i2c_client->dev);
+
+	/* Hold down reset */
+	if (cs35l32->reset_gpio)
+		gpiod_set_value_cansleep(cs35l32->reset_gpio, 0);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_RUNTIME
+static int cs35l32_runtime_suspend(struct device *dev)
+{
+	struct cs35l32_private *cs35l32 = dev_get_drvdata(dev);
+
+	regcache_cache_only(cs35l32->regmap, true);
+	regcache_mark_dirty(cs35l32->regmap);
+
+	/* Hold down reset */
+	if (cs35l32->reset_gpio)
+		gpiod_set_value_cansleep(cs35l32->reset_gpio, 0);
+
+	/* remove power */
+	regulator_bulk_disable(ARRAY_SIZE(cs35l32->supplies),
+			       cs35l32->supplies);
+
+	return 0;
+}
+
+static int cs35l32_runtime_resume(struct device *dev)
+{
+	struct cs35l32_private *cs35l32 = dev_get_drvdata(dev);
+	int ret;
+
+	/* Enable power */
+	ret = regulator_bulk_enable(ARRAY_SIZE(cs35l32->supplies),
+				    cs35l32->supplies);
+	if (ret != 0) {
+		dev_err(dev, "Failed to enable supplies: %d\n",
+			ret);
+		return ret;
+	}
+
+	if (cs35l32->reset_gpio)
+		gpiod_set_value_cansleep(cs35l32->reset_gpio, 1);
+
+	regcache_cache_only(cs35l32->regmap, false);
+	regcache_sync(cs35l32->regmap);
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops cs35l32_runtime_pm = {
+	SET_RUNTIME_PM_OPS(cs35l32_runtime_suspend, cs35l32_runtime_resume,
+			   NULL)
+};
+
+static const struct of_device_id cs35l32_of_match[] = {
+	{ .compatible = "cirrus,cs35l32", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, cs35l32_of_match);
+
+
+static const struct i2c_device_id cs35l32_id[] = {
+	{"cs35l32", 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, cs35l32_id);
+
+static struct i2c_driver cs35l32_i2c_driver = {
+	.driver = {
+		   .name = "cs35l32",
+		   .owner = THIS_MODULE,
+		   .pm = &cs35l32_runtime_pm,
+		   .of_match_table = cs35l32_of_match,
+		   },
+	.id_table = cs35l32_id,
+	.probe = cs35l32_i2c_probe,
+	.remove = cs35l32_i2c_remove,
+};
+
+module_i2c_driver(cs35l32_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC CS35L32 driver");
+MODULE_AUTHOR("Brian Austin, Cirrus Logic Inc, <brian.austin@cirrus.com>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/cs35l32.h b/sound/soc/codecs/cs35l32.h
new file mode 100644
index 000000000000..31ab804a22bc
--- /dev/null
+++ b/sound/soc/codecs/cs35l32.h
@@ -0,0 +1,93 @@
+/*
+ * cs35l32.h -- CS35L32 ALSA SoC audio driver
+ *
+ * Copyright 2014 CirrusLogic, Inc.
+ *
+ * Author: Brian Austin <brian.austin@cirrus.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __CS35L32_H__
+#define __CS35L32_H__
+
+struct cs35l32_platform_data {
+	/* Low Battery Threshold */
+	unsigned int batt_thresh;
+	/* Low Battery Recovery */
+	unsigned int batt_recov;
+	/* LED Current Management*/
+	unsigned int led_mng;
+	/* Audio Gain w/ LED */
+	unsigned int audiogain_mng;
+	/* Boost Management */
+	unsigned int boost_mng;
+	/* Data CFG for DUAL device */
+	unsigned int sdout_datacfg;
+	/* SDOUT Sharing */
+	unsigned int sdout_share;
+};
+
+#define CS35L32_CHIP_ID		0x00035A32
+#define CS35L32_DEVID_AB	0x01	/* Device ID A & B [RO] */
+#define CS35L32_DEVID_CD	0x02    /* Device ID C & D [RO] */
+#define CS35L32_DEVID_E		0x03    /* Device ID E [RO] */
+#define CS35L32_FAB_ID		0x04	/* Fab ID [RO] */
+#define CS35L32_REV_ID		0x05	/* Revision ID [RO] */
+#define CS35L32_PWRCTL1		0x06    /* Power Ctl 1 */
+#define CS35L32_PWRCTL2		0x07    /* Power Ctl 2 */
+#define CS35L32_CLK_CTL		0x08	/* Clock Ctl */
+#define CS35L32_BATT_THRESHOLD	0x09	/* Low Battery Threshold */
+#define CS35L32_VMON		0x0A	/* Voltage Monitor [RO] */
+#define CS35L32_BST_CPCP_CTL	0x0B	/* Conv Peak Curr Protection CTL */
+#define CS35L32_IMON_SCALING	0x0C	/* IMON Scaling */
+#define CS35L32_AUDIO_LED_MNGR	0x0D	/* Audio/LED Pwr Manager */
+#define CS35L32_ADSP_CTL	0x0F	/* Serial Port Control */
+#define CS35L32_CLASSD_CTL	0x10	/* Class D Amp CTL */
+#define CS35L32_PROTECT_CTL	0x11	/* Protection Release CTL */
+#define CS35L32_INT_MASK_1	0x12	/* Interrupt Mask 1 */
+#define CS35L32_INT_MASK_2	0x13	/* Interrupt Mask 2 */
+#define CS35L32_INT_MASK_3	0x14	/* Interrupt Mask 3 */
+#define CS35L32_INT_STATUS_1	0x15	/* Interrupt Status 1 [RO] */
+#define CS35L32_INT_STATUS_2	0x16	/* Interrupt Status 2 [RO] */
+#define CS35L32_INT_STATUS_3	0x17	/* Interrupt Status 3 [RO] */
+#define CS35L32_LED_STATUS	0x18	/* LED Lighting Status [RO] */
+#define CS35L32_FLASH_MODE	0x19	/* LED Flash Mode Current */
+#define CS35L32_MOVIE_MODE	0x1A	/* LED Movie Mode Current */
+#define CS35L32_FLASH_TIMER	0x1B	/* LED Flash Timer */
+#define CS35L32_FLASH_INHIBIT	0x1C	/* LED Flash Inhibit Current */
+#define CS35L32_MAX_REGISTER	0x1C
+
+#define CS35L32_MCLK_DIV2	0x01
+#define CS35L32_MCLK_RATIO	0x01
+#define CS35L32_MCLKDIS		0x80
+#define CS35L32_PDN_ALL		0x01
+#define CS35L32_PDN_AMP		0x80
+#define CS35L32_PDN_BOOST	0x04
+#define CS35L32_PDN_IMON	0x40
+#define CS35L32_PDN_VMON	0x80
+#define CS35L32_PDN_VPMON	0x20
+#define CS35L32_PDN_ADSP	0x08
+
+#define CS35L32_MCLK_DIV2_MASK		0x40
+#define CS35L32_MCLK_RATIO_MASK		0x01
+#define CS35L32_MCLK_MASK		0x41
+#define CS35L32_ADSP_MASTER_MASK	0x40
+#define CS35L32_BOOST_MASK		0x03
+#define CS35L32_GAIN_MGR_MASK		0x08
+#define CS35L32_ADSP_SHARE_MASK		0x08
+#define CS35L32_ADSP_DATACFG_MASK	0x30
+#define CS35L32_SDOUT_3ST		0x80
+#define CS35L32_BATT_REC_MASK		0x0E
+#define CS35L32_BATT_THRESH_MASK	0x30
+
+#define CS35L32_RATES (SNDRV_PCM_RATE_48000)
+#define CS35L32_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | \
+			SNDRV_PCM_FMTBIT_S24_LE | \
+			SNDRV_PCM_FMTBIT_S32_LE)
+
+
+#endif
diff --git a/sound/soc/codecs/cs4265.c b/sound/soc/codecs/cs4265.c
index 69a85164357c..4fdd47d700e3 100644
--- a/sound/soc/codecs/cs4265.c
+++ b/sound/soc/codecs/cs4265.c
@@ -77,6 +77,7 @@ static bool cs4265_readable_register(struct device *dev, unsigned int reg)
 	case CS4265_INT_MASK:
 	case CS4265_STATUS_MODE_MSB:
 	case CS4265_STATUS_MODE_LSB:
+	case CS4265_CHIP_ID:
 		return true;
 	default:
 		return false;
diff --git a/sound/soc/codecs/cs42l52.c b/sound/soc/codecs/cs42l52.c
index 969167d8b71e..35fbef743fbe 100644
--- a/sound/soc/codecs/cs42l52.c
+++ b/sound/soc/codecs/cs42l52.c
@@ -176,9 +176,9 @@ static bool cs42l52_volatile_register(struct device *dev, unsigned int reg)
 	case CS42L52_BATT_LEVEL:
 	case CS42L52_SPK_STATUS:
 	case CS42L52_CHARGE_PUMP:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -946,20 +946,6 @@ static struct snd_soc_dai_driver cs42l52_dai = {
 		.ops = &cs42l52_ops,
 };
 
-static int cs42l52_suspend(struct snd_soc_codec *codec)
-{
-	cs42l52_set_bias_level(codec, SND_SOC_BIAS_OFF);
-
-	return 0;
-}
-
-static int cs42l52_resume(struct snd_soc_codec *codec)
-{
-	cs42l52_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
-	return 0;
-}
-
 static int beep_rates[] = {
 	261, 522, 585, 667, 706, 774, 889, 1000,
 	1043, 1200, 1333, 1412, 1600, 1714, 2000, 2182
@@ -1104,8 +1090,6 @@ static int cs42l52_probe(struct snd_soc_codec *codec)
 
 	cs42l52_init_beep(codec);
 
-	cs42l52_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
 	cs42l52->sysclk = CS42L52_DEFAULT_CLK;
 	cs42l52->config.format = CS42L52_DEFAULT_FORMAT;
 
@@ -1115,7 +1099,6 @@ static int cs42l52_probe(struct snd_soc_codec *codec)
 static int cs42l52_remove(struct snd_soc_codec *codec)
 {
 	cs42l52_free_beep(codec);
-	cs42l52_set_bias_level(codec, SND_SOC_BIAS_OFF);
 
 	return 0;
 }
@@ -1123,9 +1106,8 @@ static int cs42l52_remove(struct snd_soc_codec *codec)
 static struct snd_soc_codec_driver soc_codec_dev_cs42l52 = {
 	.probe = cs42l52_probe,
 	.remove = cs42l52_remove,
-	.suspend = cs42l52_suspend,
-	.resume = cs42l52_resume,
 	.set_bias_level = cs42l52_set_bias_level,
+	.suspend_bias_off = true,
 
 	.dapm_widgets = cs42l52_dapm_widgets,
 	.num_dapm_widgets = ARRAY_SIZE(cs42l52_dapm_widgets),
diff --git a/sound/soc/codecs/cs42l56.c b/sound/soc/codecs/cs42l56.c
index c766a5a9ce80..2ddc7ac10ad7 100644
--- a/sound/soc/codecs/cs42l56.c
+++ b/sound/soc/codecs/cs42l56.c
@@ -171,9 +171,9 @@ static bool cs42l56_volatile_register(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
 	case CS42L56_INT_STATUS:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -1016,20 +1016,6 @@ static struct snd_soc_dai_driver cs42l56_dai = {
 		.ops = &cs42l56_ops,
 };
 
-static int cs42l56_suspend(struct snd_soc_codec *codec)
-{
-	cs42l56_set_bias_level(codec, SND_SOC_BIAS_OFF);
-
-	return 0;
-}
-
-static int cs42l56_resume(struct snd_soc_codec *codec)
-{
-	cs42l56_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
-	return 0;
-}
-
 static int beep_freq[] = {
 	261, 522, 585, 667, 706, 774, 889, 1000,
 	1043, 1200, 1333, 1412, 1600, 1714, 2000, 2182
@@ -1168,18 +1154,12 @@ static int cs42l56_probe(struct snd_soc_codec *codec)
 {
 	cs42l56_init_beep(codec);
 
-	cs42l56_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
 	return 0;
 }
 
 static int cs42l56_remove(struct snd_soc_codec *codec)
 {
-	struct cs42l56_private *cs42l56 = snd_soc_codec_get_drvdata(codec);
-
 	cs42l56_free_beep(codec);
-	cs42l56_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	regulator_bulk_free(ARRAY_SIZE(cs42l56->supplies), cs42l56->supplies);
 
 	return 0;
 }
@@ -1187,9 +1167,8 @@ static int cs42l56_remove(struct snd_soc_codec *codec)
 static struct snd_soc_codec_driver soc_codec_dev_cs42l56 = {
 	.probe = cs42l56_probe,
 	.remove = cs42l56_remove,
-	.suspend = cs42l56_suspend,
-	.resume = cs42l56_resume,
 	.set_bias_level = cs42l56_set_bias_level,
+	.suspend_bias_off = true,
 
 	.dapm_widgets = cs42l56_dapm_widgets,
 	.num_dapm_widgets = ARRAY_SIZE(cs42l56_dapm_widgets),
diff --git a/sound/soc/codecs/cs42l73.c b/sound/soc/codecs/cs42l73.c
index 0e7b9eb2ba61..2f8b94683e83 100644
--- a/sound/soc/codecs/cs42l73.c
+++ b/sound/soc/codecs/cs42l73.c
@@ -1330,25 +1330,10 @@ static struct snd_soc_dai_driver cs42l73_dai[] = {
 	 }
 };
 
-static int cs42l73_suspend(struct snd_soc_codec *codec)
-{
-	cs42l73_set_bias_level(codec, SND_SOC_BIAS_OFF);
-
-	return 0;
-}
-
-static int cs42l73_resume(struct snd_soc_codec *codec)
-{
-	cs42l73_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-	return 0;
-}
-
 static int cs42l73_probe(struct snd_soc_codec *codec)
 {
 	struct cs42l73_private *cs42l73 = snd_soc_codec_get_drvdata(codec);
 
-	cs42l73_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
 	/* Set Charge Pump Frequency */
 	if (cs42l73->pdata.chgfreq)
 		snd_soc_update_bits(codec, CS42L73_CPFCHC,
@@ -1362,18 +1347,10 @@ static int cs42l73_probe(struct snd_soc_codec *codec)
 	return 0;
 }
 
-static int cs42l73_remove(struct snd_soc_codec *codec)
-{
-	cs42l73_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	return 0;
-}
-
 static struct snd_soc_codec_driver soc_codec_dev_cs42l73 = {
 	.probe = cs42l73_probe,
-	.remove = cs42l73_remove,
-	.suspend = cs42l73_suspend,
-	.resume = cs42l73_resume,
 	.set_bias_level = cs42l73_set_bias_level,
+	.suspend_bias_off = true,
 
 	.dapm_widgets = cs42l73_dapm_widgets,
 	.num_dapm_widgets = ARRAY_SIZE(cs42l73_dapm_widgets),
diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c
index 2fae31cb0067..61b2f9a2eef1 100644
--- a/sound/soc/codecs/da732x.c
+++ b/sound/soc/codecs/da732x.c
@@ -35,7 +35,6 @@
 
 struct da732x_priv {
 	struct regmap *regmap;
-	struct snd_soc_codec *codec;
 
 	unsigned int sysclk;
 	bool pll_en;
@@ -217,7 +216,7 @@ static void da732x_set_charge_pump(struct snd_soc_codec *codec, int state)
 		snd_soc_write(codec, DA732X_REG_CP_CTRL1, DA723X_CP_DIS);
 		break;
 	default:
-		pr_err(KERN_ERR "Wrong charge pump state\n");
+		pr_err("Wrong charge pump state\n");
 		break;
 	}
 }
@@ -1508,31 +1507,7 @@ static int da732x_set_bias_level(struct snd_soc_codec *codec,
 	return 0;
 }
 
-static int da732x_probe(struct snd_soc_codec *codec)
-{
-	struct da732x_priv *da732x = snd_soc_codec_get_drvdata(codec);
-	struct snd_soc_dapm_context *dapm = &codec->dapm;
-
-	da732x->codec = codec;
-
-	dapm->idle_bias_off = false;
-
-	da732x_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
-	return 0;
-}
-
-static int da732x_remove(struct snd_soc_codec *codec)
-{
-
-	da732x_set_bias_level(codec, SND_SOC_BIAS_OFF);
-
-	return 0;
-}
-
 static struct snd_soc_codec_driver soc_codec_dev_da732x = {
-	.probe			= da732x_probe,
-	.remove			= da732x_remove,
 	.set_bias_level		= da732x_set_bias_level,
 	.controls		= da732x_snd_controls,
 	.num_controls		= ARRAY_SIZE(da732x_snd_controls),
diff --git a/sound/soc/codecs/es8328-i2c.c b/sound/soc/codecs/es8328-i2c.c
new file mode 100644
index 000000000000..aae410d122ee
--- /dev/null
+++ b/sound/soc/codecs/es8328-i2c.c
@@ -0,0 +1,60 @@
+/*
+ * es8328-i2c.c  --  ES8328 ALSA SoC I2C Audio driver
+ *
+ * Copyright 2014 Sutajio Ko-Usagi PTE LTD
+ *
+ * Author: Sean Cross <xobs@kosagi.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/regmap.h>
+
+#include <sound/soc.h>
+
+#include "es8328.h"
+
+static const struct i2c_device_id es8328_id[] = {
+	{ "everest,es8328", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, es8328_id);
+
+static const struct of_device_id es8328_of_match[] = {
+	{ .compatible = "everest,es8328", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, es8328_of_match);
+
+static int es8328_i2c_probe(struct i2c_client *i2c,
+			    const struct i2c_device_id *id)
+{
+	return es8328_probe(&i2c->dev,
+			devm_regmap_init_i2c(i2c, &es8328_regmap_config));
+}
+
+static int es8328_i2c_remove(struct i2c_client *i2c)
+{
+	snd_soc_unregister_codec(&i2c->dev);
+	return 0;
+}
+
+static struct i2c_driver es8328_i2c_driver = {
+	.driver = {
+		.name		= "es8328",
+		.of_match_table = es8328_of_match,
+	},
+	.probe    = es8328_i2c_probe,
+	.remove   = es8328_i2c_remove,
+	.id_table = es8328_id,
+};
+
+module_i2c_driver(es8328_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC ES8328 audio CODEC I2C driver");
+MODULE_AUTHOR("Sean Cross <xobs@kosagi.com>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/es8328-spi.c b/sound/soc/codecs/es8328-spi.c
new file mode 100644
index 000000000000..8fbd935e1c76
--- /dev/null
+++ b/sound/soc/codecs/es8328-spi.c
@@ -0,0 +1,49 @@
+/*
+ * es8328.c  --  ES8328 ALSA SoC SPI Audio driver
+ *
+ * Copyright 2014 Sutajio Ko-Usagi PTE LTD
+ *
+ * Author: Sean Cross <xobs@kosagi.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/spi/spi.h>
+#include <sound/soc.h>
+#include "es8328.h"
+
+static const struct of_device_id es8328_of_match[] = {
+	{ .compatible = "everest,es8328", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, es8328_of_match);
+
+static int es8328_spi_probe(struct spi_device *spi)
+{
+	return es8328_probe(&spi->dev,
+			devm_regmap_init_spi(spi, &es8328_regmap_config));
+}
+
+static int es8328_spi_remove(struct spi_device *spi)
+{
+	snd_soc_unregister_codec(&spi->dev);
+	return 0;
+}
+
+static struct spi_driver es8328_spi_driver = {
+	.driver = {
+		.name		= "es8328",
+		.of_match_table	= es8328_of_match,
+	},
+	.probe	= es8328_spi_probe,
+	.remove	= es8328_spi_remove,
+};
+
+module_spi_driver(es8328_spi_driver);
+MODULE_DESCRIPTION("ASoC ES8328 audio CODEC SPI driver");
+MODULE_AUTHOR("Sean Cross <xobs@kosagi.com>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c
new file mode 100644
index 000000000000..f27325155ace
--- /dev/null
+++ b/sound/soc/codecs/es8328.c
@@ -0,0 +1,756 @@
+/*
+ * es8328.c  --  ES8328 ALSA SoC Audio driver
+ *
+ * Copyright 2014 Sutajio Ko-Usagi PTE LTD
+ *
+ * Author: Sean Cross <xobs@kosagi.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/of_device.h>
+#include <linux/module.h>
+#include <linux/pm.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/regulator/consumer.h>
+#include <sound/core.h>
+#include <sound/initval.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/tlv.h>
+#include "es8328.h"
+
+#define ES8328_SYSCLK_RATE_1X 11289600
+#define ES8328_SYSCLK_RATE_2X 22579200
+
+/* Run the codec at 22.5792 or 11.2896 MHz to support these rates */
+static struct {
+	int rate;
+	u8 ratio;
+} mclk_ratios[] = {
+	{ 8000, 9 },
+	{11025, 7 },
+	{22050, 4 },
+	{44100, 2 },
+};
+
+/* regulator supplies for sgtl5000, VDDD is an optional external supply */
+enum sgtl5000_regulator_supplies {
+	DVDD,
+	AVDD,
+	PVDD,
+	HPVDD,
+	ES8328_SUPPLY_NUM
+};
+
+/* vddd is optional supply */
+static const char * const supply_names[ES8328_SUPPLY_NUM] = {
+	"DVDD",
+	"AVDD",
+	"PVDD",
+	"HPVDD",
+};
+
+#define ES8328_RATES (SNDRV_PCM_RATE_44100 | \
+		SNDRV_PCM_RATE_22050 | \
+		SNDRV_PCM_RATE_11025)
+#define ES8328_FORMATS (SNDRV_PCM_FMTBIT_S16_LE)
+
+struct es8328_priv {
+	struct regmap *regmap;
+	struct clk *clk;
+	int playback_fs;
+	bool deemph;
+	struct regulator_bulk_data supplies[ES8328_SUPPLY_NUM];
+};
+
+/*
+ * ES8328 Controls
+ */
+
+static const char * const adcpol_txt[] = {"Normal", "L Invert", "R Invert",
+					  "L + R Invert"};
+static SOC_ENUM_SINGLE_DECL(adcpol,
+			    ES8328_ADCCONTROL6, 6, adcpol_txt);
+
+static const DECLARE_TLV_DB_SCALE(play_tlv, -3000, 100, 0);
+static const DECLARE_TLV_DB_SCALE(dac_adc_tlv, -9600, 50, 0);
+static const DECLARE_TLV_DB_SCALE(pga_tlv, 0, 300, 0);
+static const DECLARE_TLV_DB_SCALE(bypass_tlv, -1500, 300, 0);
+static const DECLARE_TLV_DB_SCALE(mic_tlv, 0, 300, 0);
+
+static const int deemph_settings[] = { 0, 32000, 44100, 48000 };
+
+static int es8328_set_deemph(struct snd_soc_codec *codec)
+{
+	struct es8328_priv *es8328 = snd_soc_codec_get_drvdata(codec);
+	int val, i, best;
+
+	/*
+	 * If we're using deemphasis select the nearest available sample
+	 * rate.
+	 */
+	if (es8328->deemph) {
+		best = 1;
+		for (i = 2; i < ARRAY_SIZE(deemph_settings); i++) {
+			if (abs(deemph_settings[i] - es8328->playback_fs) <
+			    abs(deemph_settings[best] - es8328->playback_fs))
+				best = i;
+		}
+
+		val = best << 1;
+	} else {
+		val = 0;
+	}
+
+	dev_dbg(codec->dev, "Set deemphasis %d\n", val);
+
+	return snd_soc_update_bits(codec, ES8328_DACCONTROL6, 0x6, val);
+}
+
+static int es8328_get_deemph(struct snd_kcontrol *kcontrol,
+			     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
+	struct es8328_priv *es8328 = snd_soc_codec_get_drvdata(codec);
+
+	ucontrol->value.enumerated.item[0] = es8328->deemph;
+	return 0;
+}
+
+static int es8328_put_deemph(struct snd_kcontrol *kcontrol,
+			     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
+	struct es8328_priv *es8328 = snd_soc_codec_get_drvdata(codec);
+	int deemph = ucontrol->value.enumerated.item[0];
+	int ret;
+
+	if (deemph > 1)
+		return -EINVAL;
+
+	ret = es8328_set_deemph(codec);
+	if (ret < 0)
+		return ret;
+
+	es8328->deemph = deemph;
+
+	return 0;
+}
+
+
+
+static const struct snd_kcontrol_new es8328_snd_controls[] = {
+	SOC_DOUBLE_R_TLV("Capture Digital Volume",
+		ES8328_ADCCONTROL8, ES8328_ADCCONTROL9,
+		 0, 0xc0, 1, dac_adc_tlv),
+	SOC_SINGLE("Capture ZC Switch", ES8328_ADCCONTROL7, 6, 1, 0),
+
+	SOC_SINGLE_BOOL_EXT("DAC Deemphasis Switch", 0,
+		    es8328_get_deemph, es8328_put_deemph),
+
+	SOC_ENUM("Capture Polarity", adcpol),
+
+	SOC_SINGLE_TLV("Left Mixer Left Bypass Volume",
+			ES8328_DACCONTROL17, 3, 7, 1, bypass_tlv),
+	SOC_SINGLE_TLV("Left Mixer Right Bypass Volume",
+			ES8328_DACCONTROL19, 3, 7, 1, bypass_tlv),
+	SOC_SINGLE_TLV("Right Mixer Left Bypass Volume",
+			ES8328_DACCONTROL18, 3, 7, 1, bypass_tlv),
+	SOC_SINGLE_TLV("Right Mixer Right Bypass Volume",
+			ES8328_DACCONTROL20, 3, 7, 1, bypass_tlv),
+
+	SOC_DOUBLE_R_TLV("PCM Volume",
+			ES8328_LDACVOL, ES8328_RDACVOL,
+			0, ES8328_DACVOL_MAX, 1, dac_adc_tlv),
+
+	SOC_DOUBLE_R_TLV("Output 1 Playback Volume",
+			ES8328_LOUT1VOL, ES8328_ROUT1VOL,
+			0, ES8328_OUT1VOL_MAX, 0, play_tlv),
+
+	SOC_DOUBLE_R_TLV("Output 2 Playback Volume",
+			ES8328_LOUT2VOL, ES8328_ROUT2VOL,
+			0, ES8328_OUT2VOL_MAX, 0, play_tlv),
+
+	SOC_DOUBLE_TLV("Mic PGA Volume", ES8328_ADCCONTROL1,
+			4, 0, 8, 0, mic_tlv),
+};
+
+/*
+ * DAPM Controls
+ */
+
+static const char * const es8328_line_texts[] = {
+	"Line 1", "Line 2", "PGA", "Differential"};
+
+static const struct soc_enum es8328_lline_enum =
+	SOC_ENUM_SINGLE(ES8328_DACCONTROL16, 3,
+			      ARRAY_SIZE(es8328_line_texts),
+			      es8328_line_texts);
+static const struct snd_kcontrol_new es8328_left_line_controls =
+	SOC_DAPM_ENUM("Route", es8328_lline_enum);
+
+static const struct soc_enum es8328_rline_enum =
+	SOC_ENUM_SINGLE(ES8328_DACCONTROL16, 0,
+			      ARRAY_SIZE(es8328_line_texts),
+			      es8328_line_texts);
+static const struct snd_kcontrol_new es8328_right_line_controls =
+	SOC_DAPM_ENUM("Route", es8328_lline_enum);
+
+/* Left Mixer */
+static const struct snd_kcontrol_new es8328_left_mixer_controls[] = {
+	SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL17, 8, 1, 0),
+	SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL17, 7, 1, 0),
+	SOC_DAPM_SINGLE("Right Playback Switch", ES8328_DACCONTROL18, 8, 1, 0),
+	SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL18, 7, 1, 0),
+};
+
+/* Right Mixer */
+static const struct snd_kcontrol_new es8328_right_mixer_controls[] = {
+	SOC_DAPM_SINGLE("Left Playback Switch", ES8328_DACCONTROL19, 8, 1, 0),
+	SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL19, 7, 1, 0),
+	SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL20, 8, 1, 0),
+	SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL20, 7, 1, 0),
+};
+
+static const char * const es8328_pga_sel[] = {
+	"Line 1", "Line 2", "Line 3", "Differential"};
+
+/* Left PGA Mux */
+static const struct soc_enum es8328_lpga_enum =
+	SOC_ENUM_SINGLE(ES8328_ADCCONTROL2, 6,
+			      ARRAY_SIZE(es8328_pga_sel),
+			      es8328_pga_sel);
+static const struct snd_kcontrol_new es8328_left_pga_controls =
+	SOC_DAPM_ENUM("Route", es8328_lpga_enum);
+
+/* Right PGA Mux */
+static const struct soc_enum es8328_rpga_enum =
+	SOC_ENUM_SINGLE(ES8328_ADCCONTROL2, 4,
+			      ARRAY_SIZE(es8328_pga_sel),
+			      es8328_pga_sel);
+static const struct snd_kcontrol_new es8328_right_pga_controls =
+	SOC_DAPM_ENUM("Route", es8328_rpga_enum);
+
+/* Differential Mux */
+static const char * const es8328_diff_sel[] = {"Line 1", "Line 2"};
+static SOC_ENUM_SINGLE_DECL(diffmux,
+			    ES8328_ADCCONTROL3, 7, es8328_diff_sel);
+static const struct snd_kcontrol_new es8328_diffmux_controls =
+	SOC_DAPM_ENUM("Route", diffmux);
+
+/* Mono ADC Mux */
+static const char * const es8328_mono_mux[] = {"Stereo", "Mono (Left)",
+	"Mono (Right)", "Digital Mono"};
+static SOC_ENUM_SINGLE_DECL(monomux,
+			    ES8328_ADCCONTROL3, 3, es8328_mono_mux);
+static const struct snd_kcontrol_new es8328_monomux_controls =
+	SOC_DAPM_ENUM("Route", monomux);
+
+static const struct snd_soc_dapm_widget es8328_dapm_widgets[] = {
+	SND_SOC_DAPM_MUX("Differential Mux", SND_SOC_NOPM, 0, 0,
+		&es8328_diffmux_controls),
+	SND_SOC_DAPM_MUX("Left ADC Mux", SND_SOC_NOPM, 0, 0,
+		&es8328_monomux_controls),
+	SND_SOC_DAPM_MUX("Right ADC Mux", SND_SOC_NOPM, 0, 0,
+		&es8328_monomux_controls),
+
+	SND_SOC_DAPM_MUX("Left PGA Mux", ES8328_ADCPOWER,
+			ES8328_ADCPOWER_AINL_OFF, 1,
+			&es8328_left_pga_controls),
+	SND_SOC_DAPM_MUX("Right PGA Mux", ES8328_ADCPOWER,
+			ES8328_ADCPOWER_AINR_OFF, 1,
+			&es8328_right_pga_controls),
+
+	SND_SOC_DAPM_MUX("Left Line Mux", SND_SOC_NOPM, 0, 0,
+		&es8328_left_line_controls),
+	SND_SOC_DAPM_MUX("Right Line Mux", SND_SOC_NOPM, 0, 0,
+		&es8328_right_line_controls),
+
+	SND_SOC_DAPM_ADC("Right ADC", "Right Capture", ES8328_ADCPOWER,
+			ES8328_ADCPOWER_ADCR_OFF, 1),
+	SND_SOC_DAPM_ADC("Left ADC", "Left Capture", ES8328_ADCPOWER,
+			ES8328_ADCPOWER_ADCL_OFF, 1),
+
+	SND_SOC_DAPM_SUPPLY("Mic Bias", ES8328_ADCPOWER,
+			ES8328_ADCPOWER_MIC_BIAS_OFF, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Mic Bias Gen", ES8328_ADCPOWER,
+			ES8328_ADCPOWER_ADC_BIAS_GEN_OFF, 1, NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("DAC STM", ES8328_CHIPPOWER,
+			ES8328_CHIPPOWER_DACSTM_RESET, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ADC STM", ES8328_CHIPPOWER,
+			ES8328_CHIPPOWER_ADCSTM_RESET, 1, NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("DAC DIG", ES8328_CHIPPOWER,
+			ES8328_CHIPPOWER_DACDIG_OFF, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ADC DIG", ES8328_CHIPPOWER,
+			ES8328_CHIPPOWER_ADCDIG_OFF, 1, NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("DAC DLL", ES8328_CHIPPOWER,
+			ES8328_CHIPPOWER_DACDLL_OFF, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ADC DLL", ES8328_CHIPPOWER,
+			ES8328_CHIPPOWER_ADCDLL_OFF, 1, NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("ADC Vref", ES8328_CHIPPOWER,
+			ES8328_CHIPPOWER_ADCVREF_OFF, 1, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DAC Vref", ES8328_CHIPPOWER,
+			ES8328_CHIPPOWER_DACVREF_OFF, 1, NULL, 0),
+
+	SND_SOC_DAPM_DAC("Right DAC", "Right Playback", ES8328_DACPOWER,
+			ES8328_DACPOWER_RDAC_OFF, 1),
+	SND_SOC_DAPM_DAC("Left DAC", "Left Playback", ES8328_DACPOWER,
+			ES8328_DACPOWER_LDAC_OFF, 1),
+
+	SND_SOC_DAPM_MIXER("Left Mixer", SND_SOC_NOPM, 0, 0,
+		&es8328_left_mixer_controls[0],
+		ARRAY_SIZE(es8328_left_mixer_controls)),
+	SND_SOC_DAPM_MIXER("Right Mixer", SND_SOC_NOPM, 0, 0,
+		&es8328_right_mixer_controls[0],
+		ARRAY_SIZE(es8328_right_mixer_controls)),
+
+	SND_SOC_DAPM_PGA("Right Out 2", ES8328_DACPOWER,
+			ES8328_DACPOWER_ROUT2_ON, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("Left Out 2", ES8328_DACPOWER,
+			ES8328_DACPOWER_LOUT2_ON, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("Right Out 1", ES8328_DACPOWER,
+			ES8328_DACPOWER_ROUT1_ON, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("Left Out 1", ES8328_DACPOWER,
+			ES8328_DACPOWER_LOUT1_ON, 0, NULL, 0),
+
+	SND_SOC_DAPM_OUTPUT("LOUT1"),
+	SND_SOC_DAPM_OUTPUT("ROUT1"),
+	SND_SOC_DAPM_OUTPUT("LOUT2"),
+	SND_SOC_DAPM_OUTPUT("ROUT2"),
+
+	SND_SOC_DAPM_INPUT("LINPUT1"),
+	SND_SOC_DAPM_INPUT("LINPUT2"),
+	SND_SOC_DAPM_INPUT("RINPUT1"),
+	SND_SOC_DAPM_INPUT("RINPUT2"),
+};
+
+static const struct snd_soc_dapm_route es8328_dapm_routes[] = {
+
+	{ "Left Line Mux", "Line 1", "LINPUT1" },
+	{ "Left Line Mux", "Line 2", "LINPUT2" },
+	{ "Left Line Mux", "PGA", "Left PGA Mux" },
+	{ "Left Line Mux", "Differential", "Differential Mux" },
+
+	{ "Right Line Mux", "Line 1", "RINPUT1" },
+	{ "Right Line Mux", "Line 2", "RINPUT2" },
+	{ "Right Line Mux", "PGA", "Right PGA Mux" },
+	{ "Right Line Mux", "Differential", "Differential Mux" },
+
+	{ "Left PGA Mux", "Line 1", "LINPUT1" },
+	{ "Left PGA Mux", "Line 2", "LINPUT2" },
+	{ "Left PGA Mux", "Differential", "Differential Mux" },
+
+	{ "Right PGA Mux", "Line 1", "RINPUT1" },
+	{ "Right PGA Mux", "Line 2", "RINPUT2" },
+	{ "Right PGA Mux", "Differential", "Differential Mux" },
+
+	{ "Differential Mux", "Line 1", "LINPUT1" },
+	{ "Differential Mux", "Line 1", "RINPUT1" },
+	{ "Differential Mux", "Line 2", "LINPUT2" },
+	{ "Differential Mux", "Line 2", "RINPUT2" },
+
+	{ "Left ADC Mux", "Stereo", "Left PGA Mux" },
+	{ "Left ADC Mux", "Mono (Left)", "Left PGA Mux" },
+	{ "Left ADC Mux", "Digital Mono", "Left PGA Mux" },
+
+	{ "Right ADC Mux", "Stereo", "Right PGA Mux" },
+	{ "Right ADC Mux", "Mono (Right)", "Right PGA Mux" },
+	{ "Right ADC Mux", "Digital Mono", "Right PGA Mux" },
+
+	{ "Left ADC", NULL, "Left ADC Mux" },
+	{ "Right ADC", NULL, "Right ADC Mux" },
+
+	{ "ADC DIG", NULL, "ADC STM" },
+	{ "ADC DIG", NULL, "ADC Vref" },
+	{ "ADC DIG", NULL, "ADC DLL" },
+
+	{ "Left ADC", NULL, "ADC DIG" },
+	{ "Right ADC", NULL, "ADC DIG" },
+
+	{ "Mic Bias", NULL, "Mic Bias Gen" },
+
+	{ "Left Line Mux", "Line 1", "LINPUT1" },
+	{ "Left Line Mux", "Line 2", "LINPUT2" },
+	{ "Left Line Mux", "PGA", "Left PGA Mux" },
+	{ "Left Line Mux", "Differential", "Differential Mux" },
+
+	{ "Right Line Mux", "Line 1", "RINPUT1" },
+	{ "Right Line Mux", "Line 2", "RINPUT2" },
+	{ "Right Line Mux", "PGA", "Right PGA Mux" },
+	{ "Right Line Mux", "Differential", "Differential Mux" },
+
+	{ "Left Out 1", NULL, "Left DAC" },
+	{ "Right Out 1", NULL, "Right DAC" },
+	{ "Left Out 2", NULL, "Left DAC" },
+	{ "Right Out 2", NULL, "Right DAC" },
+
+	{ "Left Mixer", "Playback Switch", "Left DAC" },
+	{ "Left Mixer", "Left Bypass Switch", "Left Line Mux" },
+	{ "Left Mixer", "Right Playback Switch", "Right DAC" },
+	{ "Left Mixer", "Right Bypass Switch", "Right Line Mux" },
+
+	{ "Right Mixer", "Left Playback Switch", "Left DAC" },
+	{ "Right Mixer", "Left Bypass Switch", "Left Line Mux" },
+	{ "Right Mixer", "Playback Switch", "Right DAC" },
+	{ "Right Mixer", "Right Bypass Switch", "Right Line Mux" },
+
+	{ "DAC DIG", NULL, "DAC STM" },
+	{ "DAC DIG", NULL, "DAC Vref" },
+	{ "DAC DIG", NULL, "DAC DLL" },
+
+	{ "Left DAC", NULL, "DAC DIG" },
+	{ "Right DAC", NULL, "DAC DIG" },
+
+	{ "Left Out 1", NULL, "Left Mixer" },
+	{ "LOUT1", NULL, "Left Out 1" },
+	{ "Right Out 1", NULL, "Right Mixer" },
+	{ "ROUT1", NULL, "Right Out 1" },
+
+	{ "Left Out 2", NULL, "Left Mixer" },
+	{ "LOUT2", NULL, "Left Out 2" },
+	{ "Right Out 2", NULL, "Right Mixer" },
+	{ "ROUT2", NULL, "Right Out 2" },
+};
+
+static int es8328_mute(struct snd_soc_dai *dai, int mute)
+{
+	return snd_soc_update_bits(dai->codec, ES8328_DACCONTROL3,
+			ES8328_DACCONTROL3_DACMUTE,
+			mute ? ES8328_DACCONTROL3_DACMUTE : 0);
+}
+
+static int es8328_hw_params(struct snd_pcm_substream *substream,
+	struct snd_pcm_hw_params *params,
+	struct snd_soc_dai *dai)
+{
+	struct snd_soc_codec *codec = dai->codec;
+	struct es8328_priv *es8328 = snd_soc_codec_get_drvdata(codec);
+	int clk_rate;
+	int i;
+	int reg;
+	u8 ratio;
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		reg = ES8328_DACCONTROL2;
+	else
+		reg = ES8328_ADCCONTROL5;
+
+	clk_rate = clk_get_rate(es8328->clk);
+
+	if ((clk_rate != ES8328_SYSCLK_RATE_1X) &&
+		(clk_rate != ES8328_SYSCLK_RATE_2X)) {
+		dev_err(codec->dev,
+			"%s: clock is running at %d Hz, not %d or %d Hz\n",
+			 __func__, clk_rate,
+			 ES8328_SYSCLK_RATE_1X, ES8328_SYSCLK_RATE_2X);
+		return -EINVAL;
+	}
+
+	/* find master mode MCLK to sampling frequency ratio */
+	ratio = mclk_ratios[0].rate;
+	for (i = 1; i < ARRAY_SIZE(mclk_ratios); i++)
+		if (params_rate(params) <= mclk_ratios[i].rate)
+			ratio = mclk_ratios[i].ratio;
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		es8328->playback_fs = params_rate(params);
+		es8328_set_deemph(codec);
+	}
+
+	return snd_soc_update_bits(codec, reg, ES8328_RATEMASK, ratio);
+}
+
+static int es8328_set_dai_fmt(struct snd_soc_dai *codec_dai,
+		unsigned int fmt)
+{
+	struct snd_soc_codec *codec = codec_dai->codec;
+	struct es8328_priv *es8328 = snd_soc_codec_get_drvdata(codec);
+	int clk_rate;
+	u8 mode = ES8328_DACCONTROL1_DACWL_16;
+
+	/* set master/slave audio interface */
+	if ((fmt & SND_SOC_DAIFMT_MASTER_MASK) != SND_SOC_DAIFMT_CBM_CFM)
+		return -EINVAL;
+
+	/* interface format */
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		mode |= ES8328_DACCONTROL1_DACFORMAT_I2S;
+		break;
+	case SND_SOC_DAIFMT_RIGHT_J:
+		mode |= ES8328_DACCONTROL1_DACFORMAT_RJUST;
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		mode |= ES8328_DACCONTROL1_DACFORMAT_LJUST;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* clock inversion */
+	if ((fmt & SND_SOC_DAIFMT_INV_MASK) != SND_SOC_DAIFMT_NB_NF)
+		return -EINVAL;
+
+	snd_soc_write(codec, ES8328_DACCONTROL1, mode);
+	snd_soc_write(codec, ES8328_ADCCONTROL4, mode);
+
+	/* Master serial port mode, with BCLK generated automatically */
+	clk_rate = clk_get_rate(es8328->clk);
+	if (clk_rate == ES8328_SYSCLK_RATE_1X)
+		snd_soc_write(codec, ES8328_MASTERMODE,
+				ES8328_MASTERMODE_MSC);
+	else
+		snd_soc_write(codec, ES8328_MASTERMODE,
+				ES8328_MASTERMODE_MCLKDIV2 |
+				ES8328_MASTERMODE_MSC);
+
+	return 0;
+}
+
+static int es8328_set_bias_level(struct snd_soc_codec *codec,
+				 enum snd_soc_bias_level level)
+{
+	switch (level) {
+	case SND_SOC_BIAS_ON:
+		break;
+
+	case SND_SOC_BIAS_PREPARE:
+		/* VREF, VMID=2x50k, digital enabled */
+		snd_soc_write(codec, ES8328_CHIPPOWER, 0);
+		snd_soc_update_bits(codec, ES8328_CONTROL1,
+				ES8328_CONTROL1_VMIDSEL_MASK |
+				ES8328_CONTROL1_ENREF,
+				ES8328_CONTROL1_VMIDSEL_50k |
+				ES8328_CONTROL1_ENREF);
+		break;
+
+	case SND_SOC_BIAS_STANDBY:
+		if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) {
+			snd_soc_update_bits(codec, ES8328_CONTROL1,
+					ES8328_CONTROL1_VMIDSEL_MASK |
+					ES8328_CONTROL1_ENREF,
+					ES8328_CONTROL1_VMIDSEL_5k |
+					ES8328_CONTROL1_ENREF);
+
+			/* Charge caps */
+			msleep(100);
+		}
+
+		snd_soc_write(codec, ES8328_CONTROL2,
+				ES8328_CONTROL2_OVERCURRENT_ON |
+				ES8328_CONTROL2_THERMAL_SHUTDOWN_ON);
+
+		/* VREF, VMID=2*500k, digital stopped */
+		snd_soc_update_bits(codec, ES8328_CONTROL1,
+				ES8328_CONTROL1_VMIDSEL_MASK |
+				ES8328_CONTROL1_ENREF,
+				ES8328_CONTROL1_VMIDSEL_500k |
+				ES8328_CONTROL1_ENREF);
+		break;
+
+	case SND_SOC_BIAS_OFF:
+		snd_soc_update_bits(codec, ES8328_CONTROL1,
+				ES8328_CONTROL1_VMIDSEL_MASK |
+				ES8328_CONTROL1_ENREF,
+				0);
+		break;
+	}
+	codec->dapm.bias_level = level;
+	return 0;
+}
+
+static const struct snd_soc_dai_ops es8328_dai_ops = {
+	.hw_params	= es8328_hw_params,
+	.digital_mute	= es8328_mute,
+	.set_fmt	= es8328_set_dai_fmt,
+};
+
+static struct snd_soc_dai_driver es8328_dai = {
+	.name = "es8328-hifi-analog",
+	.playback = {
+		.stream_name = "Playback",
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = ES8328_RATES,
+		.formats = ES8328_FORMATS,
+	},
+	.capture = {
+		.stream_name = "Capture",
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = ES8328_RATES,
+		.formats = ES8328_FORMATS,
+	},
+	.ops = &es8328_dai_ops,
+};
+
+static int es8328_suspend(struct snd_soc_codec *codec)
+{
+	struct es8328_priv *es8328;
+	int ret;
+
+	es8328 = snd_soc_codec_get_drvdata(codec);
+
+	clk_disable_unprepare(es8328->clk);
+
+	ret = regulator_bulk_disable(ARRAY_SIZE(es8328->supplies),
+			es8328->supplies);
+	if (ret) {
+		dev_err(codec->dev, "unable to disable regulators\n");
+		return ret;
+	}
+	return 0;
+}
+
+static int es8328_resume(struct snd_soc_codec *codec)
+{
+	struct regmap *regmap = dev_get_regmap(codec->dev, NULL);
+	struct es8328_priv *es8328;
+	int ret;
+
+	es8328 = snd_soc_codec_get_drvdata(codec);
+
+	ret = clk_prepare_enable(es8328->clk);
+	if (ret) {
+		dev_err(codec->dev, "unable to enable clock\n");
+		return ret;
+	}
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(es8328->supplies),
+					es8328->supplies);
+	if (ret) {
+		dev_err(codec->dev, "unable to enable regulators\n");
+		return ret;
+	}
+
+	regcache_mark_dirty(regmap);
+	ret = regcache_sync(regmap);
+	if (ret) {
+		dev_err(codec->dev, "unable to sync regcache\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int es8328_codec_probe(struct snd_soc_codec *codec)
+{
+	struct es8328_priv *es8328;
+	int ret;
+
+	es8328 = snd_soc_codec_get_drvdata(codec);
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(es8328->supplies),
+					es8328->supplies);
+	if (ret) {
+		dev_err(codec->dev, "unable to enable regulators\n");
+		return ret;
+	}
+
+	/* Setup clocks */
+	es8328->clk = devm_clk_get(codec->dev, NULL);
+	if (IS_ERR(es8328->clk)) {
+		dev_err(codec->dev, "codec clock missing or invalid\n");
+		ret = PTR_ERR(es8328->clk);
+		goto clk_fail;
+	}
+
+	ret = clk_prepare_enable(es8328->clk);
+	if (ret) {
+		dev_err(codec->dev, "unable to prepare codec clk\n");
+		goto clk_fail;
+	}
+
+	return 0;
+
+clk_fail:
+	regulator_bulk_disable(ARRAY_SIZE(es8328->supplies),
+			       es8328->supplies);
+	return ret;
+}
+
+static int es8328_remove(struct snd_soc_codec *codec)
+{
+	struct es8328_priv *es8328;
+
+	es8328 = snd_soc_codec_get_drvdata(codec);
+
+	if (es8328->clk)
+		clk_disable_unprepare(es8328->clk);
+
+	regulator_bulk_disable(ARRAY_SIZE(es8328->supplies),
+			       es8328->supplies);
+
+	return 0;
+}
+
+const struct regmap_config es8328_regmap_config = {
+	.reg_bits	= 8,
+	.val_bits	= 8,
+	.max_register	= ES8328_REG_MAX,
+	.cache_type	= REGCACHE_RBTREE,
+};
+EXPORT_SYMBOL_GPL(es8328_regmap_config);
+
+static struct snd_soc_codec_driver es8328_codec_driver = {
+	.probe		  = es8328_codec_probe,
+	.suspend	  = es8328_suspend,
+	.resume		  = es8328_resume,
+	.remove		  = es8328_remove,
+	.set_bias_level	  = es8328_set_bias_level,
+	.suspend_bias_off = true,
+
+	.controls	  = es8328_snd_controls,
+	.num_controls	  = ARRAY_SIZE(es8328_snd_controls),
+	.dapm_widgets	  = es8328_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(es8328_dapm_widgets),
+	.dapm_routes	  = es8328_dapm_routes,
+	.num_dapm_routes  = ARRAY_SIZE(es8328_dapm_routes),
+};
+
+int es8328_probe(struct device *dev, struct regmap *regmap)
+{
+	struct es8328_priv *es8328;
+	int ret;
+	int i;
+
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	es8328 = devm_kzalloc(dev, sizeof(*es8328), GFP_KERNEL);
+	if (es8328 == NULL)
+		return -ENOMEM;
+
+	es8328->regmap = regmap;
+
+	for (i = 0; i < ARRAY_SIZE(es8328->supplies); i++)
+		es8328->supplies[i].supply = supply_names[i];
+
+	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(es8328->supplies),
+				es8328->supplies);
+	if (ret) {
+		dev_err(dev, "unable to get regulators\n");
+		return ret;
+	}
+
+	dev_set_drvdata(dev, es8328);
+
+	return snd_soc_register_codec(dev,
+			&es8328_codec_driver, &es8328_dai, 1);
+}
+EXPORT_SYMBOL_GPL(es8328_probe);
+
+MODULE_DESCRIPTION("ASoC ES8328 driver");
+MODULE_AUTHOR("Sean Cross <xobs@kosagi.com>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/es8328.h b/sound/soc/codecs/es8328.h
new file mode 100644
index 000000000000..cb36afe10c0e
--- /dev/null
+++ b/sound/soc/codecs/es8328.h
@@ -0,0 +1,314 @@
+/*
+ * es8328.h  --  ES8328 ALSA SoC Audio driver
+ */
+
+#ifndef _ES8328_H
+#define _ES8328_H
+
+#include <linux/regmap.h>
+
+struct device;
+
+extern const struct regmap_config es8328_regmap_config;
+int es8328_probe(struct device *dev, struct regmap *regmap);
+
+#define ES8328_DACLVOL 46
+#define ES8328_DACRVOL 47
+#define ES8328_DACCTL 28
+#define ES8328_RATEMASK (0x1f << 0)
+
+#define ES8328_CONTROL1		0x00
+#define ES8328_CONTROL1_VMIDSEL_OFF (0 << 0)
+#define ES8328_CONTROL1_VMIDSEL_50k (1 << 0)
+#define ES8328_CONTROL1_VMIDSEL_500k (2 << 0)
+#define ES8328_CONTROL1_VMIDSEL_5k (3 << 0)
+#define ES8328_CONTROL1_VMIDSEL_MASK (7 << 0)
+#define ES8328_CONTROL1_ENREF (1 << 2)
+#define ES8328_CONTROL1_SEQEN (1 << 3)
+#define ES8328_CONTROL1_SAMEFS (1 << 4)
+#define ES8328_CONTROL1_DACMCLK_ADC (0 << 5)
+#define ES8328_CONTROL1_DACMCLK_DAC (1 << 5)
+#define ES8328_CONTROL1_LRCM (1 << 6)
+#define ES8328_CONTROL1_SCP_RESET (1 << 7)
+
+#define ES8328_CONTROL2		0x01
+#define ES8328_CONTROL2_VREF_BUF_OFF (1 << 0)
+#define ES8328_CONTROL2_VREF_LOWPOWER (1 << 1)
+#define ES8328_CONTROL2_IBIASGEN_OFF (1 << 2)
+#define ES8328_CONTROL2_ANALOG_OFF (1 << 3)
+#define ES8328_CONTROL2_VREF_BUF_LOWPOWER (1 << 4)
+#define ES8328_CONTROL2_VCM_MOD_LOWPOWER (1 << 5)
+#define ES8328_CONTROL2_OVERCURRENT_ON (1 << 6)
+#define ES8328_CONTROL2_THERMAL_SHUTDOWN_ON (1 << 7)
+
+#define ES8328_CHIPPOWER	0x02
+#define ES8328_CHIPPOWER_DACVREF_OFF 0
+#define ES8328_CHIPPOWER_ADCVREF_OFF 1
+#define ES8328_CHIPPOWER_DACDLL_OFF 2
+#define ES8328_CHIPPOWER_ADCDLL_OFF 3
+#define ES8328_CHIPPOWER_DACSTM_RESET 4
+#define ES8328_CHIPPOWER_ADCSTM_RESET 5
+#define ES8328_CHIPPOWER_DACDIG_OFF 6
+#define ES8328_CHIPPOWER_ADCDIG_OFF 7
+
+#define ES8328_ADCPOWER		0x03
+#define ES8328_ADCPOWER_INT1_LOWPOWER 0
+#define ES8328_ADCPOWER_FLASH_ADC_LOWPOWER 1
+#define ES8328_ADCPOWER_ADC_BIAS_GEN_OFF 2
+#define ES8328_ADCPOWER_MIC_BIAS_OFF 3
+#define ES8328_ADCPOWER_ADCR_OFF 4
+#define ES8328_ADCPOWER_ADCL_OFF 5
+#define ES8328_ADCPOWER_AINR_OFF 6
+#define ES8328_ADCPOWER_AINL_OFF 7
+
+#define ES8328_DACPOWER		0x04
+#define ES8328_DACPOWER_OUT3_ON 0
+#define ES8328_DACPOWER_MONO_ON 1
+#define ES8328_DACPOWER_ROUT2_ON 2
+#define ES8328_DACPOWER_LOUT2_ON 3
+#define ES8328_DACPOWER_ROUT1_ON 4
+#define ES8328_DACPOWER_LOUT1_ON 5
+#define ES8328_DACPOWER_RDAC_OFF 6
+#define ES8328_DACPOWER_LDAC_OFF 7
+
+#define ES8328_CHIPLOPOW1	0x05
+#define ES8328_CHIPLOPOW2	0x06
+#define ES8328_ANAVOLMANAG	0x07
+
+#define ES8328_MASTERMODE	0x08
+#define ES8328_MASTERMODE_BCLKDIV (0 << 0)
+#define ES8328_MASTERMODE_BCLK_INV (1 << 5)
+#define ES8328_MASTERMODE_MCLKDIV2 (1 << 6)
+#define ES8328_MASTERMODE_MSC (1 << 7)
+
+#define ES8328_ADCCONTROL1	0x09
+#define ES8328_ADCCONTROL2	0x0a
+#define ES8328_ADCCONTROL3	0x0b
+#define ES8328_ADCCONTROL4	0x0c
+#define ES8328_ADCCONTROL5	0x0d
+#define ES8328_ADCCONTROL5_RATEMASK (0x1f << 0)
+
+#define ES8328_ADCCONTROL6	0x0e
+
+#define ES8328_ADCCONTROL7	0x0f
+#define ES8328_ADCCONTROL7_ADC_MUTE (1 << 2)
+#define ES8328_ADCCONTROL7_ADC_LER (1 << 3)
+#define ES8328_ADCCONTROL7_ADC_ZERO_CROSS (1 << 4)
+#define ES8328_ADCCONTROL7_ADC_SOFT_RAMP (1 << 5)
+#define ES8328_ADCCONTROL7_ADC_RAMP_RATE_4 (0 << 6)
+#define ES8328_ADCCONTROL7_ADC_RAMP_RATE_8 (1 << 6)
+#define ES8328_ADCCONTROL7_ADC_RAMP_RATE_16 (2 << 6)
+#define ES8328_ADCCONTROL7_ADC_RAMP_RATE_32 (3 << 6)
+
+#define ES8328_ADCCONTROL8	0x10
+#define ES8328_ADCCONTROL9	0x11
+#define ES8328_ADCCONTROL10	0x12
+#define ES8328_ADCCONTROL11	0x13
+#define ES8328_ADCCONTROL12	0x14
+#define ES8328_ADCCONTROL13	0x15
+#define ES8328_ADCCONTROL14	0x16
+
+#define ES8328_DACCONTROL1	0x17
+#define ES8328_DACCONTROL1_DACFORMAT_I2S (0 << 1)
+#define ES8328_DACCONTROL1_DACFORMAT_LJUST (1 << 1)
+#define ES8328_DACCONTROL1_DACFORMAT_RJUST (2 << 1)
+#define ES8328_DACCONTROL1_DACFORMAT_PCM (3 << 1)
+#define ES8328_DACCONTROL1_DACWL_24 (0 << 3)
+#define ES8328_DACCONTROL1_DACWL_20 (1 << 3)
+#define ES8328_DACCONTROL1_DACWL_18 (2 << 3)
+#define ES8328_DACCONTROL1_DACWL_16 (3 << 3)
+#define ES8328_DACCONTROL1_DACWL_32 (4 << 3)
+#define ES8328_DACCONTROL1_DACLRP_I2S_POL_NORMAL (0 << 6)
+#define ES8328_DACCONTROL1_DACLRP_I2S_POL_INV (1 << 6)
+#define ES8328_DACCONTROL1_DACLRP_PCM_MSB_CLK2 (0 << 6)
+#define ES8328_DACCONTROL1_DACLRP_PCM_MSB_CLK1 (1 << 6)
+#define ES8328_DACCONTROL1_LRSWAP (1 << 7)
+
+#define ES8328_DACCONTROL2	0x18
+#define ES8328_DACCONTROL2_RATEMASK (0x1f << 0)
+#define ES8328_DACCONTROL2_DOUBLESPEED (1 << 5)
+
+#define ES8328_DACCONTROL3	0x19
+#define ES8328_DACCONTROL3_AUTOMUTE (1 << 2)
+#define ES8328_DACCONTROL3_DACMUTE (1 << 2)
+#define ES8328_DACCONTROL3_LEFTGAINVOL (1 << 3)
+#define ES8328_DACCONTROL3_DACZEROCROSS (1 << 4)
+#define ES8328_DACCONTROL3_DACSOFTRAMP (1 << 5)
+#define ES8328_DACCONTROL3_DACRAMPRATE (3 << 6)
+
+#define ES8328_LDACVOL 0x1a
+#define ES8328_LDACVOL_MASK (0 << 0)
+#define ES8328_LDACVOL_MAX (0xc0)
+
+#define ES8328_RDACVOL 0x1b
+#define ES8328_RDACVOL_MASK (0 << 0)
+#define ES8328_RDACVOL_MAX (0xc0)
+
+#define ES8328_DACVOL_MAX (0xc0)
+
+#define ES8328_DACCONTROL4	0x1a
+#define ES8328_DACCONTROL5	0x1b
+
+#define ES8328_DACCONTROL6	0x1c
+#define ES8328_DACCONTROL6_CLICKFREE (1 << 3)
+#define ES8328_DACCONTROL6_DAC_INVR (1 << 4)
+#define ES8328_DACCONTROL6_DAC_INVL (1 << 5)
+#define ES8328_DACCONTROL6_DEEMPH_OFF (0 << 6)
+#define ES8328_DACCONTROL6_DEEMPH_32k (1 << 6)
+#define ES8328_DACCONTROL6_DEEMPH_44_1k (2 << 6)
+#define ES8328_DACCONTROL6_DEEMPH_48k (3 << 6)
+
+#define ES8328_DACCONTROL7	0x1d
+#define ES8328_DACCONTROL7_VPP_SCALE_3p5	(0 << 0)
+#define ES8328_DACCONTROL7_VPP_SCALE_4p0	(1 << 0)
+#define ES8328_DACCONTROL7_VPP_SCALE_3p0	(2 << 0)
+#define ES8328_DACCONTROL7_VPP_SCALE_2p5	(3 << 0)
+#define ES8328_DACCONTROL7_SHELVING_STRENGTH (1 << 2) /* In eights */
+#define ES8328_DACCONTROL7_MONO		(1 << 5)
+#define ES8328_DACCONTROL7_ZEROR	(1 << 6)
+#define ES8328_DACCONTROL7_ZEROL	(1 << 7)
+
+/* Shelving filter */
+#define ES8328_DACCONTROL8	0x1e
+#define ES8328_DACCONTROL9	0x1f
+#define ES8328_DACCONTROL10	0x20
+#define ES8328_DACCONTROL11	0x21
+#define ES8328_DACCONTROL12	0x22
+#define ES8328_DACCONTROL13	0x23
+#define ES8328_DACCONTROL14	0x24
+#define ES8328_DACCONTROL15	0x25
+
+#define ES8328_DACCONTROL16	0x26
+#define ES8328_DACCONTROL16_RMIXSEL_RIN1 (0 << 0)
+#define ES8328_DACCONTROL16_RMIXSEL_RIN2 (1 << 0)
+#define ES8328_DACCONTROL16_RMIXSEL_RIN3 (2 << 0)
+#define ES8328_DACCONTROL16_RMIXSEL_RADC (3 << 0)
+#define ES8328_DACCONTROL16_LMIXSEL_LIN1 (0 << 3)
+#define ES8328_DACCONTROL16_LMIXSEL_LIN2 (1 << 3)
+#define ES8328_DACCONTROL16_LMIXSEL_LIN3 (2 << 3)
+#define ES8328_DACCONTROL16_LMIXSEL_LADC (3 << 3)
+
+#define ES8328_DACCONTROL17	0x27
+#define ES8328_DACCONTROL17_LI2LOVOL (7 << 3)
+#define ES8328_DACCONTROL17_LI2LO (1 << 6)
+#define ES8328_DACCONTROL17_LD2LO (1 << 7)
+
+#define ES8328_DACCONTROL18	0x28
+#define ES8328_DACCONTROL18_RI2LOVOL (7 << 3)
+#define ES8328_DACCONTROL18_RI2LO (1 << 6)
+#define ES8328_DACCONTROL18_RD2LO (1 << 7)
+
+#define ES8328_DACCONTROL19	0x29
+#define ES8328_DACCONTROL19_LI2ROVOL (7 << 3)
+#define ES8328_DACCONTROL19_LI2RO (1 << 6)
+#define ES8328_DACCONTROL19_LD2RO (1 << 7)
+
+#define ES8328_DACCONTROL20	0x2a
+#define ES8328_DACCONTROL20_RI2ROVOL (7 << 3)
+#define ES8328_DACCONTROL20_RI2RO (1 << 6)
+#define ES8328_DACCONTROL20_RD2RO (1 << 7)
+
+#define ES8328_DACCONTROL21	0x2b
+#define ES8328_DACCONTROL21_LI2MOVOL (7 << 3)
+#define ES8328_DACCONTROL21_LI2MO (1 << 6)
+#define ES8328_DACCONTROL21_LD2MO (1 << 7)
+
+#define ES8328_DACCONTROL22	0x2c
+#define ES8328_DACCONTROL22_RI2MOVOL (7 << 3)
+#define ES8328_DACCONTROL22_RI2MO (1 << 6)
+#define ES8328_DACCONTROL22_RD2MO (1 << 7)
+
+#define ES8328_DACCONTROL23	0x2d
+#define ES8328_DACCONTROL23_MOUTINV		(1 << 1)
+#define ES8328_DACCONTROL23_HPSWPOL		(1 << 2)
+#define ES8328_DACCONTROL23_HPSWEN		(1 << 3)
+#define ES8328_DACCONTROL23_VROI_1p5k		(0 << 4)
+#define ES8328_DACCONTROL23_VROI_40k		(1 << 4)
+#define ES8328_DACCONTROL23_OUT3_VREF		(0 << 5)
+#define ES8328_DACCONTROL23_OUT3_ROUT1		(1 << 5)
+#define ES8328_DACCONTROL23_OUT3_MONOOUT	(2 << 5)
+#define ES8328_DACCONTROL23_OUT3_RIGHT_MIXER	(3 << 5)
+#define ES8328_DACCONTROL23_ROUT2INV		(1 << 7)
+
+/* LOUT1 Amplifier */
+#define ES8328_LOUT1VOL 0x2e
+#define ES8328_LOUT1VOL_MASK (0 << 5)
+#define ES8328_LOUT1VOL_MAX (0x24)
+
+/* ROUT1 Amplifier */
+#define ES8328_ROUT1VOL 0x2f
+#define ES8328_ROUT1VOL_MASK (0 << 5)
+#define ES8328_ROUT1VOL_MAX (0x24)
+
+#define ES8328_OUT1VOL_MAX (0x24)
+
+/* LOUT2 Amplifier */
+#define ES8328_LOUT2VOL 0x30
+#define ES8328_LOUT2VOL_MASK (0 << 5)
+#define ES8328_LOUT2VOL_MAX (0x24)
+
+/* ROUT2 Amplifier */
+#define ES8328_ROUT2VOL 0x31
+#define ES8328_ROUT2VOL_MASK (0 << 5)
+#define ES8328_ROUT2VOL_MAX (0x24)
+
+#define ES8328_OUT2VOL_MAX (0x24)
+
+/* Mono Out Amplifier */
+#define ES8328_MONOOUTVOL 0x32
+#define ES8328_MONOOUTVOL_MASK (0 << 5)
+#define ES8328_MONOOUTVOL_MAX (0x24)
+
+#define ES8328_DACCONTROL29	0x33
+#define ES8328_DACCONTROL30	0x34
+
+#define ES8328_SYSCLK		0
+
+#define ES8328_REG_MAX		0x35
+
+#define ES8328_PLL1		0
+#define ES8328_PLL2		1
+
+/* clock inputs */
+#define ES8328_MCLK		0
+#define ES8328_PCMCLK		1
+
+/* clock divider id's */
+#define ES8328_PCMDIV		0
+#define ES8328_BCLKDIV		1
+#define ES8328_VXCLKDIV		2
+
+/* PCM clock dividers */
+#define ES8328_PCM_DIV_1	(0 << 6)
+#define ES8328_PCM_DIV_3	(2 << 6)
+#define ES8328_PCM_DIV_5_5	(3 << 6)
+#define ES8328_PCM_DIV_2	(4 << 6)
+#define ES8328_PCM_DIV_4	(5 << 6)
+#define ES8328_PCM_DIV_6	(6 << 6)
+#define ES8328_PCM_DIV_8	(7 << 6)
+
+/* BCLK clock dividers */
+#define ES8328_BCLK_DIV_1	(0 << 7)
+#define ES8328_BCLK_DIV_2	(1 << 7)
+#define ES8328_BCLK_DIV_4	(2 << 7)
+#define ES8328_BCLK_DIV_8	(3 << 7)
+
+/* VXCLK clock dividers */
+#define ES8328_VXCLK_DIV_1	(0 << 6)
+#define ES8328_VXCLK_DIV_2	(1 << 6)
+#define ES8328_VXCLK_DIV_4	(2 << 6)
+#define ES8328_VXCLK_DIV_8	(3 << 6)
+#define ES8328_VXCLK_DIV_16	(4 << 6)
+
+#define ES8328_DAI_HIFI		0
+#define ES8328_DAI_VOICE	1
+
+#define ES8328_1536FS		1536
+#define ES8328_1024FS		1024
+#define ES8328_768FS		768
+#define ES8328_512FS		512
+#define ES8328_384FS		384
+#define ES8328_256FS		256
+#define ES8328_128FS		128
+
+#endif
diff --git a/sound/soc/codecs/jz4740.c b/sound/soc/codecs/jz4740.c
index bcebd1a9ce31..df7c01cf7072 100644
--- a/sound/soc/codecs/jz4740.c
+++ b/sound/soc/codecs/jz4740.c
@@ -293,41 +293,13 @@ static int jz4740_codec_dev_probe(struct snd_soc_codec *codec)
 	regmap_update_bits(jz4740_codec->regmap, JZ4740_REG_CODEC_1,
 			JZ4740_CODEC_1_SW2_ENABLE, JZ4740_CODEC_1_SW2_ENABLE);
 
-	jz4740_codec_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
 	return 0;
 }
 
-static int jz4740_codec_dev_remove(struct snd_soc_codec *codec)
-{
-	jz4740_codec_set_bias_level(codec, SND_SOC_BIAS_OFF);
-
-	return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-
-static int jz4740_codec_suspend(struct snd_soc_codec *codec)
-{
-	return jz4740_codec_set_bias_level(codec, SND_SOC_BIAS_OFF);
-}
-
-static int jz4740_codec_resume(struct snd_soc_codec *codec)
-{
-	return jz4740_codec_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-}
-
-#else
-#define jz4740_codec_suspend NULL
-#define jz4740_codec_resume NULL
-#endif
-
 static struct snd_soc_codec_driver soc_codec_dev_jz4740_codec = {
 	.probe = jz4740_codec_dev_probe,
-	.remove = jz4740_codec_dev_remove,
-	.suspend = jz4740_codec_suspend,
-	.resume = jz4740_codec_resume,
 	.set_bias_level = jz4740_codec_set_bias_level,
+	.suspend_bias_off = true,
 
 	.controls = jz4740_codec_controls,
 	.num_controls = ARRAY_SIZE(jz4740_codec_controls),
diff --git a/sound/soc/codecs/lm49453.c b/sound/soc/codecs/lm49453.c
index 275b3f72f3f4..c1ae5764983f 100644
--- a/sound/soc/codecs/lm49453.c
+++ b/sound/soc/codecs/lm49453.c
@@ -1395,18 +1395,6 @@ static struct snd_soc_dai_driver lm49453_dai[] = {
 	},
 };
 
-static int lm49453_suspend(struct snd_soc_codec *codec)
-{
-	lm49453_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	return 0;
-}
-
-static int lm49453_resume(struct snd_soc_codec *codec)
-{
-	lm49453_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-	return 0;
-}
-
 /* power down chip */
 static int lm49453_remove(struct snd_soc_codec *codec)
 {
@@ -1416,8 +1404,6 @@ static int lm49453_remove(struct snd_soc_codec *codec)
 
 static struct snd_soc_codec_driver soc_codec_dev_lm49453 = {
 	.remove = lm49453_remove,
-	.suspend = lm49453_suspend,
-	.resume = lm49453_resume,
 	.set_bias_level = lm49453_set_bias_level,
 	.controls = lm49453_snd_controls,
 	.num_controls = ARRAY_SIZE(lm49453_snd_controls),
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index 4a063fa88526..d519294f57c7 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -1311,8 +1311,6 @@ static const struct snd_soc_dapm_route max98090_dapm_routes[] = {
 	{"MIC1 Input", NULL, "MIC1"},
 	{"MIC2 Input", NULL, "MIC2"},
 
-	{"DMICL", NULL, "DMICL_ENA"},
-	{"DMICR", NULL, "DMICR_ENA"},
 	{"DMICL", NULL, "AHPF"},
 	{"DMICR", NULL, "AHPF"},
 
@@ -1370,6 +1368,8 @@ static const struct snd_soc_dapm_route max98090_dapm_routes[] = {
 	{"DMIC Mux", "ADC", "ADCR"},
 	{"DMIC Mux", "DMIC", "DMICL"},
 	{"DMIC Mux", "DMIC", "DMICR"},
+	{"DMIC Mux", "DMIC", "DMICL_ENA"},
+	{"DMIC Mux", "DMIC", "DMICR_ENA"},
 
 	{"LBENL Mux", "Normal", "DMIC Mux"},
 	{"LBENL Mux", "Loopback", "LTENL Mux"},
@@ -1972,6 +1972,102 @@ static int max98090_dai_digital_mute(struct snd_soc_dai *codec_dai, int mute)
 	return 0;
 }
 
+static int max98090_dai_trigger(struct snd_pcm_substream *substream, int cmd,
+				struct snd_soc_dai *dai)
+{
+	struct snd_soc_codec *codec = dai->codec;
+	struct max98090_priv *max98090 = snd_soc_codec_get_drvdata(codec);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		if (!max98090->master && dai->active == 1)
+			queue_delayed_work(system_power_efficient_wq,
+					   &max98090->pll_det_enable_work,
+					   msecs_to_jiffies(10));
+		break;
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		if (!max98090->master && dai->active == 1)
+			schedule_work(&max98090->pll_det_disable_work);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static void max98090_pll_det_enable_work(struct work_struct *work)
+{
+	struct max98090_priv *max98090 =
+		container_of(work, struct max98090_priv,
+			     pll_det_enable_work.work);
+	struct snd_soc_codec *codec = max98090->codec;
+	unsigned int status, mask;
+
+	/*
+	 * Clear status register in order to clear possibly already occurred
+	 * PLL unlock. If PLL hasn't still locked, the status will be set
+	 * again and PLL unlock interrupt will occur.
+	 * Note this will clear all status bits
+	 */
+	regmap_read(max98090->regmap, M98090_REG_DEVICE_STATUS, &status);
+
+	/*
+	 * Queue jack work in case jack state has just changed but handler
+	 * hasn't run yet
+	 */
+	regmap_read(max98090->regmap, M98090_REG_INTERRUPT_S, &mask);
+	status &= mask;
+	if (status & M98090_JDET_MASK)
+		queue_delayed_work(system_power_efficient_wq,
+				   &max98090->jack_work,
+				   msecs_to_jiffies(100));
+
+	/* Enable PLL unlock interrupt */
+	snd_soc_update_bits(codec, M98090_REG_INTERRUPT_S,
+			    M98090_IULK_MASK,
+			    1 << M98090_IULK_SHIFT);
+}
+
+static void max98090_pll_det_disable_work(struct work_struct *work)
+{
+	struct max98090_priv *max98090 =
+		container_of(work, struct max98090_priv, pll_det_disable_work);
+	struct snd_soc_codec *codec = max98090->codec;
+
+	cancel_delayed_work_sync(&max98090->pll_det_enable_work);
+
+	/* Disable PLL unlock interrupt */
+	snd_soc_update_bits(codec, M98090_REG_INTERRUPT_S,
+			    M98090_IULK_MASK, 0);
+}
+
+static void max98090_pll_work(struct work_struct *work)
+{
+	struct max98090_priv *max98090 =
+		container_of(work, struct max98090_priv, pll_work);
+	struct snd_soc_codec *codec = max98090->codec;
+
+	if (!snd_soc_codec_is_active(codec))
+		return;
+
+	dev_info(codec->dev, "PLL unlocked\n");
+
+	/* Toggle shutdown OFF then ON */
+	snd_soc_update_bits(codec, M98090_REG_DEVICE_SHUTDOWN,
+			    M98090_SHDNN_MASK, 0);
+	msleep(10);
+	snd_soc_update_bits(codec, M98090_REG_DEVICE_SHUTDOWN,
+			    M98090_SHDNN_MASK, M98090_SHDNN_MASK);
+
+	/* Give PLL time to lock */
+	msleep(10);
+}
+
 static void max98090_jack_work(struct work_struct *work)
 {
 	struct max98090_priv *max98090 = container_of(work,
@@ -2063,12 +2159,16 @@ static void max98090_jack_work(struct work_struct *work)
 
 static irqreturn_t max98090_interrupt(int irq, void *data)
 {
-	struct snd_soc_codec *codec = data;
-	struct max98090_priv *max98090 = snd_soc_codec_get_drvdata(codec);
+	struct max98090_priv *max98090 = data;
+	struct snd_soc_codec *codec = max98090->codec;
 	int ret;
 	unsigned int mask;
 	unsigned int active;
 
+	/* Treat interrupt before codec is initialized as spurious */
+	if (codec == NULL)
+		return IRQ_NONE;
+
 	dev_dbg(codec->dev, "***** max98090_interrupt *****\n");
 
 	ret = regmap_read(max98090->regmap, M98090_REG_INTERRUPT_S, &mask);
@@ -2103,8 +2203,10 @@ static irqreturn_t max98090_interrupt(int irq, void *data)
 	if (active & M98090_SLD_MASK)
 		dev_dbg(codec->dev, "M98090_SLD_MASK\n");
 
-	if (active & M98090_ULK_MASK)
-		dev_err(codec->dev, "M98090_ULK_MASK\n");
+	if (active & M98090_ULK_MASK) {
+		dev_dbg(codec->dev, "M98090_ULK_MASK\n");
+		schedule_work(&max98090->pll_work);
+	}
 
 	if (active & M98090_JDET_MASK) {
 		dev_dbg(codec->dev, "M98090_JDET_MASK\n");
@@ -2177,6 +2279,7 @@ static struct snd_soc_dai_ops max98090_dai_ops = {
 	.set_tdm_slot = max98090_set_tdm_slot,
 	.hw_params = max98090_dai_hw_params,
 	.digital_mute = max98090_dai_digital_mute,
+	.trigger = max98090_dai_trigger,
 };
 
 static struct snd_soc_dai_driver max98090_dai[] = {
@@ -2230,7 +2333,6 @@ static int max98090_probe(struct snd_soc_codec *codec)
 	max98090->lin_state = 0;
 	max98090->pa1en = 0;
 	max98090->pa2en = 0;
-	max98090->extmic_mux = 0;
 
 	ret = snd_soc_read(codec, M98090_REG_REVISION_ID);
 	if (ret < 0) {
@@ -2258,22 +2360,16 @@ static int max98090_probe(struct snd_soc_codec *codec)
 	max98090->jack_state = M98090_JACK_STATE_NO_HEADSET;
 
 	INIT_DELAYED_WORK(&max98090->jack_work, max98090_jack_work);
+	INIT_DELAYED_WORK(&max98090->pll_det_enable_work,
+			  max98090_pll_det_enable_work);
+	INIT_WORK(&max98090->pll_det_disable_work,
+		  max98090_pll_det_disable_work);
+	INIT_WORK(&max98090->pll_work, max98090_pll_work);
 
 	/* Enable jack detection */
 	snd_soc_write(codec, M98090_REG_JACK_DETECT,
 		M98090_JDETEN_MASK | M98090_JDEB_25MS);
 
-	/* Register for interrupts */
-	dev_dbg(codec->dev, "irq = %d\n", max98090->irq);
-
-	ret = devm_request_threaded_irq(codec->dev, max98090->irq, NULL,
-		max98090_interrupt, IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
-		"max98090_interrupt", codec);
-	if (ret < 0) {
-		dev_err(codec->dev, "request_irq failed: %d\n",
-			ret);
-	}
-
 	/*
 	 * Clear any old interrupts.
 	 * An old interrupt ocurring prior to installing the ISR
@@ -2310,6 +2406,10 @@ static int max98090_remove(struct snd_soc_codec *codec)
 	struct max98090_priv *max98090 = snd_soc_codec_get_drvdata(codec);
 
 	cancel_delayed_work_sync(&max98090->jack_work);
+	cancel_delayed_work_sync(&max98090->pll_det_enable_work);
+	cancel_work_sync(&max98090->pll_det_disable_work);
+	cancel_work_sync(&max98090->pll_work);
+	max98090->codec = NULL;
 
 	return 0;
 }
@@ -2362,7 +2462,6 @@ static int max98090_i2c_probe(struct i2c_client *i2c,
 	max98090->devtype = driver_data;
 	i2c_set_clientdata(i2c, max98090);
 	max98090->pdata = i2c->dev.platform_data;
-	max98090->irq = i2c->irq;
 
 	max98090->regmap = devm_regmap_init_i2c(i2c, &max98090_regmap);
 	if (IS_ERR(max98090->regmap)) {
@@ -2371,6 +2470,15 @@ static int max98090_i2c_probe(struct i2c_client *i2c,
 		goto err_enable;
 	}
 
+	ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL,
+		max98090_interrupt, IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+		"max98090_interrupt", max98090);
+	if (ret < 0) {
+		dev_err(&i2c->dev, "request_irq failed: %d\n",
+			ret);
+		return ret;
+	}
+
 	ret = snd_soc_register_codec(&i2c->dev,
 			&soc_codec_dev_max98090, max98090_dai,
 			ARRAY_SIZE(max98090_dai));
diff --git a/sound/soc/codecs/max98090.h b/sound/soc/codecs/max98090.h
index cf1b6062ba8c..a5f6bada06da 100644
--- a/sound/soc/codecs/max98090.h
+++ b/sound/soc/codecs/max98090.h
@@ -11,11 +11,6 @@
 #ifndef _MAX98090_H
 #define _MAX98090_H
 
-#include <linux/version.h>
-
-/* One can override the Linux version here with an explicit version number */
-#define M98090_LINUX_VERSION LINUX_VERSION_CODE
-
 /*
  * MAX98090 Register Definitions
  */
@@ -1502,9 +1497,6 @@
 #define M98090_REVID_WIDTH		8
 #define M98090_REVID_NUM		(1<<M98090_REVID_WIDTH)
 
-#define M98090_BYTE1(w) ((w >> 8) & 0xff)
-#define M98090_BYTE0(w) (w & 0xff)
-
 /* Silicon revision number */
 #define M98090_REVA			0x40
 #define M98091_REVA			0x50
@@ -1529,9 +1521,11 @@ struct max98090_priv {
 	unsigned int bclk;
 	unsigned int lrclk;
 	struct max98090_cdata dai[1];
-	int irq;
 	int jack_state;
 	struct delayed_work jack_work;
+	struct delayed_work pll_det_enable_work;
+	struct work_struct pll_det_disable_work;
+	struct work_struct pll_work;
 	struct snd_soc_jack *jack;
 	unsigned int dai_fmt;
 	int tdm_slots;
@@ -1539,7 +1533,6 @@ struct max98090_priv {
 	u8 lin_state;
 	unsigned int pa1en;
 	unsigned int pa2en;
-	unsigned int extmic_mux;
 	unsigned int sidetone;
 	bool master;
 };
diff --git a/sound/soc/codecs/mc13783.c b/sound/soc/codecs/mc13783.c
index 388f90a597fa..71f775aad7c7 100644
--- a/sound/soc/codecs/mc13783.c
+++ b/sound/soc/codecs/mc13783.c
@@ -765,12 +765,18 @@ static int __init mc13783_codec_probe(struct platform_device *pdev)
 			return -ENOSYS;
 
 		ret = of_property_read_u32(np, "adc-port", &priv->adc_ssi_port);
-		if (ret)
-			goto out;
+		if (ret) {
+			of_node_put(np);
+			return ret;
+		}
 
 		ret = of_property_read_u32(np, "dac-port", &priv->dac_ssi_port);
-		if (ret)
-			goto out;
+		if (ret) {
+			of_node_put(np);
+			return ret;
+		}
+
+		of_node_put(np);
 	}
 
 	dev_set_drvdata(&pdev->dev, priv);
@@ -783,8 +789,6 @@ static int __init mc13783_codec_probe(struct platform_device *pdev)
 		ret = snd_soc_register_codec(&pdev->dev, &soc_codec_dev_mc13783,
 			mc13783_dai_async, ARRAY_SIZE(mc13783_dai_async));
 
-out:
-	of_node_put(np);
 	return ret;
 }
 
diff --git a/sound/soc/codecs/ml26124.c b/sound/soc/codecs/ml26124.c
index e661e8420e3d..711f55039522 100644
--- a/sound/soc/codecs/ml26124.c
+++ b/sound/soc/codecs/ml26124.c
@@ -565,41 +565,19 @@ static struct snd_soc_dai_driver ml26124_dai = {
 	.symmetric_rates = 1,
 };
 
-#ifdef CONFIG_PM
-static int ml26124_suspend(struct snd_soc_codec *codec)
-{
-	ml26124_set_bias_level(codec, SND_SOC_BIAS_OFF);
-
-	return 0;
-}
-
-static int ml26124_resume(struct snd_soc_codec *codec)
-{
-	ml26124_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
-	return 0;
-}
-#else
-#define ml26124_suspend NULL
-#define ml26124_resume NULL
-#endif
-
 static int ml26124_probe(struct snd_soc_codec *codec)
 {
 	/* Software Reset */
 	snd_soc_update_bits(codec, ML26124_SW_RST, 0x01, 1);
 	snd_soc_update_bits(codec, ML26124_SW_RST, 0x01, 0);
 
-	ml26124_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
 	return 0;
 }
 
 static struct snd_soc_codec_driver soc_codec_dev_ml26124 = {
 	.probe =	ml26124_probe,
-	.suspend =	ml26124_suspend,
-	.resume =	ml26124_resume,
 	.set_bias_level = ml26124_set_bias_level,
+	.suspend_bias_off = true,
 	.dapm_widgets = ml26124_dapm_widgets,
 	.num_dapm_widgets = ARRAY_SIZE(ml26124_dapm_widgets),
 	.dapm_routes = ml26124_intercon,
diff --git a/sound/soc/codecs/rt286.c b/sound/soc/codecs/rt286.c
index b86b426f159d..4aa555cbcca8 100644
--- a/sound/soc/codecs/rt286.c
+++ b/sound/soc/codecs/rt286.c
@@ -269,6 +269,7 @@ static int rt286_hw_read(void *context, unsigned int reg, unsigned int *value)
 	return 0;
 }
 
+#ifdef CONFIG_PM
 static void rt286_index_sync(struct snd_soc_codec *codec)
 {
 	struct rt286_priv *rt286 = snd_soc_codec_get_drvdata(codec);
@@ -279,6 +280,7 @@ static void rt286_index_sync(struct snd_soc_codec *codec)
 				  rt286->index_cache[i].def);
 	}
 }
+#endif
 
 static int rt286_support_power_controls[] = {
 	RT286_DAC_OUT1,
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index f1ec6e6bd08a..c3f2decd643c 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -1906,6 +1906,32 @@ static int rt5640_set_bias_level(struct snd_soc_codec *codec,
 	return 0;
 }
 
+int rt5640_dmic_enable(struct snd_soc_codec *codec,
+		       bool dmic1_data_pin, bool dmic2_data_pin)
+{
+	struct rt5640_priv *rt5640 = snd_soc_codec_get_drvdata(codec);
+
+	regmap_update_bits(rt5640->regmap, RT5640_GPIO_CTRL1,
+		RT5640_GP2_PIN_MASK, RT5640_GP2_PIN_DMIC1_SCL);
+
+	if (dmic1_data_pin) {
+		regmap_update_bits(rt5640->regmap, RT5640_DMIC,
+			RT5640_DMIC_1_DP_MASK, RT5640_DMIC_1_DP_GPIO3);
+		regmap_update_bits(rt5640->regmap, RT5640_GPIO_CTRL1,
+			RT5640_GP3_PIN_MASK, RT5640_GP3_PIN_DMIC1_SDA);
+	}
+
+	if (dmic2_data_pin) {
+		regmap_update_bits(rt5640->regmap, RT5640_DMIC,
+			RT5640_DMIC_2_DP_MASK, RT5640_DMIC_2_DP_GPIO4);
+		regmap_update_bits(rt5640->regmap, RT5640_GPIO_CTRL1,
+			RT5640_GP4_PIN_MASK, RT5640_GP4_PIN_DMIC2_SDA);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rt5640_dmic_enable);
+
 static int rt5640_probe(struct snd_soc_codec *codec)
 {
 	struct rt5640_priv *rt5640 = snd_soc_codec_get_drvdata(codec);
@@ -1945,6 +1971,10 @@ static int rt5640_probe(struct snd_soc_codec *codec)
 		return -ENODEV;
 	}
 
+	if (rt5640->pdata.dmic_en)
+		rt5640_dmic_enable(codec, rt5640->pdata.dmic1_data_pin,
+					  rt5640->pdata.dmic2_data_pin);
+
 	return 0;
 }
 
@@ -2195,25 +2225,6 @@ static int rt5640_i2c_probe(struct i2c_client *i2c,
 		regmap_update_bits(rt5640->regmap, RT5640_IN3_IN4,
 					RT5640_IN_DF2, RT5640_IN_DF2);
 
-	if (rt5640->pdata.dmic_en) {
-		regmap_update_bits(rt5640->regmap, RT5640_GPIO_CTRL1,
-			RT5640_GP2_PIN_MASK, RT5640_GP2_PIN_DMIC1_SCL);
-
-		if (rt5640->pdata.dmic1_data_pin) {
-			regmap_update_bits(rt5640->regmap, RT5640_DMIC,
-				RT5640_DMIC_1_DP_MASK, RT5640_DMIC_1_DP_GPIO3);
-			regmap_update_bits(rt5640->regmap, RT5640_GPIO_CTRL1,
-				RT5640_GP3_PIN_MASK, RT5640_GP3_PIN_DMIC1_SDA);
-		}
-
-		if (rt5640->pdata.dmic2_data_pin) {
-			regmap_update_bits(rt5640->regmap, RT5640_DMIC,
-				RT5640_DMIC_2_DP_MASK, RT5640_DMIC_2_DP_GPIO4);
-			regmap_update_bits(rt5640->regmap, RT5640_GPIO_CTRL1,
-				RT5640_GP4_PIN_MASK, RT5640_GP4_PIN_DMIC2_SDA);
-		}
-	}
-
 	rt5640->hp_mute = 1;
 
 	return snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5640,
diff --git a/sound/soc/codecs/rt5640.h b/sound/soc/codecs/rt5640.h
index 58ebe96b86da..3deb8babeabb 100644
--- a/sound/soc/codecs/rt5640.h
+++ b/sound/soc/codecs/rt5640.h
@@ -2097,4 +2097,7 @@ struct rt5640_priv {
 	bool hp_mute;
 };
 
+int rt5640_dmic_enable(struct snd_soc_codec *codec,
+		       bool dmic1_data_pin, bool dmic2_data_pin);
+
 #endif
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index a7762d0a623e..3fb83bf09768 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -17,6 +17,7 @@
 #include <linux/i2c.h>
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
+#include <linux/gpio.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -2103,6 +2104,77 @@ static int rt5645_set_bias_level(struct snd_soc_codec *codec,
 	return 0;
 }
 
+static int rt5645_jack_detect(struct snd_soc_codec *codec,
+	struct snd_soc_jack *jack)
+{
+	struct rt5645_priv *rt5645 = snd_soc_codec_get_drvdata(codec);
+	int gpio_state, jack_type = 0;
+	unsigned int val;
+
+	gpio_state = gpio_get_value(rt5645->pdata.hp_det_gpio);
+
+	dev_dbg(codec->dev, "gpio = %d(%d)\n", rt5645->pdata.hp_det_gpio,
+		gpio_state);
+
+	if ((rt5645->pdata.gpio_hp_det_active_high && gpio_state) ||
+		(!rt5645->pdata.gpio_hp_det_active_high && !gpio_state)) {
+		snd_soc_dapm_force_enable_pin(&codec->dapm, "micbias1");
+		snd_soc_dapm_force_enable_pin(&codec->dapm, "micbias2");
+		snd_soc_dapm_force_enable_pin(&codec->dapm, "LDO2");
+		snd_soc_dapm_force_enable_pin(&codec->dapm, "Mic Det Power");
+		snd_soc_dapm_sync(&codec->dapm);
+
+		snd_soc_write(codec, RT5645_IN1_CTRL1, 0x0006);
+		snd_soc_write(codec, RT5645_JD_CTRL3, 0x00b0);
+
+		snd_soc_update_bits(codec, RT5645_IN1_CTRL2,
+			RT5645_CBJ_MN_JD, 0);
+		snd_soc_update_bits(codec, RT5645_IN1_CTRL2,
+			RT5645_CBJ_MN_JD, RT5645_CBJ_MN_JD);
+
+		msleep(400);
+		val = snd_soc_read(codec, RT5645_IN1_CTRL3) & 0x7;
+		dev_dbg(codec->dev, "val = %d\n", val);
+
+		if (val == 1 || val == 2)
+			jack_type = SND_JACK_HEADSET;
+		else
+			jack_type = SND_JACK_HEADPHONE;
+
+		snd_soc_dapm_disable_pin(&codec->dapm, "micbias1");
+		snd_soc_dapm_disable_pin(&codec->dapm, "micbias2");
+		snd_soc_dapm_disable_pin(&codec->dapm, "LDO2");
+		snd_soc_dapm_disable_pin(&codec->dapm, "Mic Det Power");
+		snd_soc_dapm_sync(&codec->dapm);
+	}
+
+	snd_soc_jack_report(rt5645->jack, jack_type, SND_JACK_HEADSET);
+
+	return 0;
+}
+
+int rt5645_set_jack_detect(struct snd_soc_codec *codec,
+	struct snd_soc_jack *jack)
+{
+	struct rt5645_priv *rt5645 = snd_soc_codec_get_drvdata(codec);
+
+	rt5645->jack = jack;
+
+	rt5645_jack_detect(codec, rt5645->jack);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rt5645_set_jack_detect);
+
+static irqreturn_t rt5645_irq(int irq, void *data)
+{
+	struct rt5645_priv *rt5645 = data;
+
+	rt5645_jack_detect(rt5645->codec, rt5645->jack);
+
+	return IRQ_HANDLED;
+}
+
 static int rt5645_probe(struct snd_soc_codec *codec)
 {
 	struct rt5645_priv *rt5645 = snd_soc_codec_get_drvdata(codec);
@@ -2250,6 +2322,7 @@ static int rt5645_i2c_probe(struct i2c_client *i2c,
 	if (rt5645 == NULL)
 		return -ENOMEM;
 
+	rt5645->i2c = i2c;
 	i2c_set_clientdata(i2c, rt5645);
 
 	if (pdata)
@@ -2345,12 +2418,38 @@ static int rt5645_i2c_probe(struct i2c_client *i2c,
 
 	}
 
+	if (rt5645->i2c->irq) {
+		ret = request_threaded_irq(rt5645->i2c->irq, NULL, rt5645_irq,
+			IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
+			| IRQF_ONESHOT, "rt5645", rt5645);
+		if (ret)
+			dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret);
+	}
+
+	if (gpio_is_valid(rt5645->pdata.hp_det_gpio)) {
+		ret = gpio_request(rt5645->pdata.hp_det_gpio, "rt5645");
+		if (ret)
+			dev_err(&i2c->dev, "Fail gpio_request hp_det_gpio\n");
+
+		ret = gpio_direction_input(rt5645->pdata.hp_det_gpio);
+		if (ret)
+			dev_err(&i2c->dev, "Fail gpio_direction hp_det_gpio\n");
+	}
+
 	return snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5645,
 				      rt5645_dai, ARRAY_SIZE(rt5645_dai));
 }
 
 static int rt5645_i2c_remove(struct i2c_client *i2c)
 {
+	struct rt5645_priv *rt5645 = i2c_get_clientdata(i2c);
+
+	if (i2c->irq)
+		free_irq(i2c->irq, rt5645);
+
+	if (gpio_is_valid(rt5645->pdata.hp_det_gpio))
+		gpio_free(rt5645->pdata.hp_det_gpio);
+
 	snd_soc_unregister_codec(&i2c->dev);
 
 	return 0;
diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h
index 355b7e9eefab..50c62c5668ea 100644
--- a/sound/soc/codecs/rt5645.h
+++ b/sound/soc/codecs/rt5645.h
@@ -2166,6 +2166,8 @@ struct rt5645_priv {
 	struct snd_soc_codec *codec;
 	struct rt5645_platform_data pdata;
 	struct regmap *regmap;
+	struct i2c_client *i2c;
+	struct snd_soc_jack *jack;
 
 	int sysclk;
 	int sysclk_src;
@@ -2178,4 +2180,7 @@ struct rt5645_priv {
 	int pll_out;
 };
 
+int rt5645_set_jack_detect(struct snd_soc_codec *codec,
+	struct snd_soc_jack *jack);
+
 #endif /* __RT5645_H__ */
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index 5337c448b5e3..16aa4d99a713 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -15,10 +15,12 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/pm.h>
+#include <linux/of_gpio.h>
 #include <linux/regmap.h>
 #include <linux/i2c.h>
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
+#include <linux/gpio.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -540,6 +542,7 @@ static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0);
 static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -3450, 150, 0);
 static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0);
 static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0);
+static const DECLARE_TLV_DB_SCALE(st_vol_tlv, -4650, 150, 0);
 
 /* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */
 static unsigned int bst_tlv[] = {
@@ -604,6 +607,10 @@ static const struct snd_kcontrol_new rt5677_snd_controls[] = {
 		RT5677_MONO_ADC_L_VOL_SFT, RT5677_MONO_ADC_R_VOL_SFT, 127, 0,
 		adc_vol_tlv),
 
+	/* Sidetone Control */
+	SOC_SINGLE_TLV("Sidetone Volume", RT5677_SIDETONE_CTRL,
+		RT5677_ST_VOL_SFT, 31, 0, st_vol_tlv),
+
 	/* ADC Boost Volume Control */
 	SOC_DOUBLE_TLV("STO1 ADC Boost Volume", RT5677_STO1_2_ADC_BST,
 		RT5677_STO1_ADC_L_BST_SFT, RT5677_STO1_ADC_R_BST_SFT, 3, 0,
@@ -1700,14 +1707,19 @@ static const struct snd_soc_dapm_widget rt5677_dapm_widgets[] = {
 
 	SND_SOC_DAPM_INPUT("Haptic Generator"),
 
-	SND_SOC_DAPM_PGA("DMIC1", RT5677_DMIC_CTRL1, RT5677_DMIC_1_EN_SFT, 0,
-		NULL, 0),
-	SND_SOC_DAPM_PGA("DMIC2", RT5677_DMIC_CTRL1, RT5677_DMIC_2_EN_SFT, 0,
-		NULL, 0),
-	SND_SOC_DAPM_PGA("DMIC3", RT5677_DMIC_CTRL1, RT5677_DMIC_3_EN_SFT, 0,
-		NULL, 0),
-	SND_SOC_DAPM_PGA("DMIC4", RT5677_DMIC_CTRL2, RT5677_DMIC_4_EN_SFT, 0,
-		NULL, 0),
+	SND_SOC_DAPM_PGA("DMIC1", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("DMIC2", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("DMIC3", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("DMIC4", SND_SOC_NOPM, 0, 0, NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("DMIC1 power", RT5677_DMIC_CTRL1,
+		RT5677_DMIC_1_EN_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DMIC2 power", RT5677_DMIC_CTRL1,
+		RT5677_DMIC_2_EN_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DMIC3 power", RT5677_DMIC_CTRL1,
+		RT5677_DMIC_3_EN_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("DMIC4 power", RT5677_DMIC_CTRL2,
+		RT5677_DMIC_4_EN_SFT, 0, NULL, 0),
 
 	SND_SOC_DAPM_SUPPLY("DMIC CLK", SND_SOC_NOPM, 0, 0,
 		set_dmic_clk, SND_SOC_DAPM_PRE_PMU),
@@ -1987,6 +1999,9 @@ static const struct snd_soc_dapm_widget rt5677_dapm_widgets[] = {
 	/* Sidetone Mux */
 	SND_SOC_DAPM_MUX("Sidetone Mux", SND_SOC_NOPM, 0, 0,
 			&rt5677_sidetone_mux),
+	SND_SOC_DAPM_SUPPLY("Sidetone Power", RT5677_SIDETONE_CTRL,
+		RT5677_ST_EN_SFT, 0, NULL, 0),
+
 	/* VAD Mux*/
 	SND_SOC_DAPM_MUX("VAD ADC Mux", SND_SOC_NOPM, 0, 0,
 			&rt5677_vad_src_mux),
@@ -2130,6 +2145,13 @@ static const struct snd_soc_dapm_route rt5677_dapm_routes[] = {
 	{ "DMIC L4", NULL, "DMIC CLK" },
 	{ "DMIC R4", NULL, "DMIC CLK" },
 
+	{ "DMIC L1", NULL, "DMIC1 power" },
+	{ "DMIC R1", NULL, "DMIC1 power" },
+	{ "DMIC L3", NULL, "DMIC3 power" },
+	{ "DMIC R3", NULL, "DMIC3 power" },
+	{ "DMIC L4", NULL, "DMIC4 power" },
+	{ "DMIC R4", NULL, "DMIC4 power" },
+
 	{ "BST1", NULL, "IN1P" },
 	{ "BST1", NULL, "IN1N" },
 	{ "BST2", NULL, "IN2P" },
@@ -2691,6 +2713,7 @@ static const struct snd_soc_dapm_route rt5677_dapm_routes[] = {
 	{ "Sidetone Mux", "DMIC4 L", "DMIC L4" },
 	{ "Sidetone Mux", "ADC1", "ADC 1" },
 	{ "Sidetone Mux", "ADC2", "ADC 2" },
+	{ "Sidetone Mux", NULL, "Sidetone Power" },
 
 	{ "Stereo DAC MIXL", "ST L Switch", "Sidetone Mux" },
 	{ "Stereo DAC MIXL", "DAC1 L Switch", "DAC1 MIXL" },
@@ -2793,6 +2816,16 @@ static const struct snd_soc_dapm_route rt5677_dapm_routes[] = {
 	{ "PDM2R", NULL, "PDM2 R Mux" },
 };
 
+static const struct snd_soc_dapm_route rt5677_dmic2_clk_1[] = {
+	{ "DMIC L2", NULL, "DMIC1 power" },
+	{ "DMIC R2", NULL, "DMIC1 power" },
+};
+
+static const struct snd_soc_dapm_route rt5677_dmic2_clk_2[] = {
+	{ "DMIC L2", NULL, "DMIC2 power" },
+	{ "DMIC R2", NULL, "DMIC2 power" },
+};
+
 static int rt5677_hw_params(struct snd_pcm_substream *substream,
 	struct snd_pcm_hw_params *params, struct snd_soc_dai *dai)
 {
@@ -3084,6 +3117,59 @@ static int rt5677_set_dai_pll(struct snd_soc_dai *dai, int pll_id, int source,
 	return 0;
 }
 
+static int rt5677_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
+			unsigned int rx_mask, int slots, int slot_width)
+{
+	struct snd_soc_codec *codec = dai->codec;
+	unsigned int val = 0;
+
+	if (rx_mask || tx_mask)
+		val |= (1 << 12);
+
+	switch (slots) {
+	case 4:
+		val |= (1 << 10);
+		break;
+	case 6:
+		val |= (2 << 10);
+		break;
+	case 8:
+		val |= (3 << 10);
+		break;
+	case 2:
+	default:
+		break;
+	}
+
+	switch (slot_width) {
+	case 20:
+		val |= (1 << 8);
+		break;
+	case 24:
+		val |= (2 << 8);
+		break;
+	case 32:
+		val |= (3 << 8);
+		break;
+	case 16:
+	default:
+		break;
+	}
+
+	switch (dai->id) {
+	case RT5677_AIF1:
+		snd_soc_update_bits(codec, RT5677_TDM1_CTRL1, 0x1f00, val);
+		break;
+	case RT5677_AIF2:
+		snd_soc_update_bits(codec, RT5677_TDM2_CTRL1, 0x1f00, val);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static int rt5677_set_bias_level(struct snd_soc_codec *codec,
 			enum snd_soc_bias_level level)
 {
@@ -3138,12 +3224,148 @@ static int rt5677_set_bias_level(struct snd_soc_codec *codec,
 	return 0;
 }
 
+#ifdef CONFIG_GPIOLIB
+static inline struct rt5677_priv *gpio_to_rt5677(struct gpio_chip *chip)
+{
+	return container_of(chip, struct rt5677_priv, gpio_chip);
+}
+
+static void rt5677_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	struct rt5677_priv *rt5677 = gpio_to_rt5677(chip);
+
+	switch (offset) {
+	case RT5677_GPIO1 ... RT5677_GPIO5:
+		regmap_update_bits(rt5677->regmap, RT5677_GPIO_CTRL2,
+			0x1 << (offset * 3 + 1), !!value << (offset * 3 + 1));
+		break;
+
+	case RT5677_GPIO6:
+		regmap_update_bits(rt5677->regmap, RT5677_GPIO_CTRL3,
+			RT5677_GPIO6_OUT_MASK, !!value << RT5677_GPIO6_OUT_SFT);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static int rt5677_gpio_direction_out(struct gpio_chip *chip,
+				     unsigned offset, int value)
+{
+	struct rt5677_priv *rt5677 = gpio_to_rt5677(chip);
+
+	switch (offset) {
+	case RT5677_GPIO1 ... RT5677_GPIO5:
+		regmap_update_bits(rt5677->regmap, RT5677_GPIO_CTRL2,
+			0x3 << (offset * 3 + 1),
+			(0x2 | !!value) << (offset * 3 + 1));
+		break;
+
+	case RT5677_GPIO6:
+		regmap_update_bits(rt5677->regmap, RT5677_GPIO_CTRL3,
+			RT5677_GPIO6_DIR_MASK | RT5677_GPIO6_OUT_MASK,
+			RT5677_GPIO6_DIR_OUT | !!value << RT5677_GPIO6_OUT_SFT);
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int rt5677_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	struct rt5677_priv *rt5677 = gpio_to_rt5677(chip);
+	int value, ret;
+
+	ret = regmap_read(rt5677->regmap, RT5677_GPIO_ST, &value);
+	if (ret < 0)
+		return ret;
+
+	return (value & (0x1 << offset)) >> offset;
+}
+
+static int rt5677_gpio_direction_in(struct gpio_chip *chip, unsigned offset)
+{
+	struct rt5677_priv *rt5677 = gpio_to_rt5677(chip);
+
+	switch (offset) {
+	case RT5677_GPIO1 ... RT5677_GPIO5:
+		regmap_update_bits(rt5677->regmap, RT5677_GPIO_CTRL2,
+			0x1 << (offset * 3 + 2), 0x0);
+		break;
+
+	case RT5677_GPIO6:
+		regmap_update_bits(rt5677->regmap, RT5677_GPIO_CTRL3,
+			RT5677_GPIO6_DIR_MASK, RT5677_GPIO6_DIR_IN);
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static struct gpio_chip rt5677_template_chip = {
+	.label			= "rt5677",
+	.owner			= THIS_MODULE,
+	.direction_output	= rt5677_gpio_direction_out,
+	.set			= rt5677_gpio_set,
+	.direction_input	= rt5677_gpio_direction_in,
+	.get			= rt5677_gpio_get,
+	.can_sleep		= 1,
+};
+
+static void rt5677_init_gpio(struct i2c_client *i2c)
+{
+	struct rt5677_priv *rt5677 = i2c_get_clientdata(i2c);
+	int ret;
+
+	rt5677->gpio_chip = rt5677_template_chip;
+	rt5677->gpio_chip.ngpio = RT5677_GPIO_NUM;
+	rt5677->gpio_chip.dev = &i2c->dev;
+	rt5677->gpio_chip.base = -1;
+
+	ret = gpiochip_add(&rt5677->gpio_chip);
+	if (ret != 0)
+		dev_err(&i2c->dev, "Failed to add GPIOs: %d\n", ret);
+}
+
+static void rt5677_free_gpio(struct i2c_client *i2c)
+{
+	struct rt5677_priv *rt5677 = i2c_get_clientdata(i2c);
+
+	gpiochip_remove(&rt5677->gpio_chip);
+}
+#else
+static void rt5677_init_gpio(struct i2c_client *i2c)
+{
+}
+
+static void rt5677_free_gpio(struct i2c_client *i2c)
+{
+}
+#endif
+
 static int rt5677_probe(struct snd_soc_codec *codec)
 {
 	struct rt5677_priv *rt5677 = snd_soc_codec_get_drvdata(codec);
 
 	rt5677->codec = codec;
 
+	if (rt5677->pdata.dmic2_clk_pin == RT5677_DMIC_CLK2) {
+		snd_soc_dapm_add_routes(&codec->dapm,
+			rt5677_dmic2_clk_2,
+			ARRAY_SIZE(rt5677_dmic2_clk_2));
+	} else { /*use dmic1 clock by default*/
+		snd_soc_dapm_add_routes(&codec->dapm,
+			rt5677_dmic2_clk_1,
+			ARRAY_SIZE(rt5677_dmic2_clk_1));
+	}
+
 	rt5677_set_bias_level(codec, SND_SOC_BIAS_OFF);
 
 	regmap_write(rt5677->regmap, RT5677_DIG_MISC, 0x0020);
@@ -3157,6 +3379,8 @@ static int rt5677_remove(struct snd_soc_codec *codec)
 	struct rt5677_priv *rt5677 = snd_soc_codec_get_drvdata(codec);
 
 	regmap_write(rt5677->regmap, RT5677_RESET, 0x10ec);
+	if (gpio_is_valid(rt5677->pow_ldo2))
+		gpio_set_value_cansleep(rt5677->pow_ldo2, 0);
 
 	return 0;
 }
@@ -3168,6 +3392,8 @@ static int rt5677_suspend(struct snd_soc_codec *codec)
 
 	regcache_cache_only(rt5677->regmap, true);
 	regcache_mark_dirty(rt5677->regmap);
+	if (gpio_is_valid(rt5677->pow_ldo2))
+		gpio_set_value_cansleep(rt5677->pow_ldo2, 0);
 
 	return 0;
 }
@@ -3176,6 +3402,10 @@ static int rt5677_resume(struct snd_soc_codec *codec)
 {
 	struct rt5677_priv *rt5677 = snd_soc_codec_get_drvdata(codec);
 
+	if (gpio_is_valid(rt5677->pow_ldo2)) {
+		gpio_set_value_cansleep(rt5677->pow_ldo2, 1);
+		msleep(10);
+	}
 	regcache_cache_only(rt5677->regmap, false);
 	regcache_sync(rt5677->regmap);
 
@@ -3195,6 +3425,7 @@ static struct snd_soc_dai_ops rt5677_aif_dai_ops = {
 	.set_fmt = rt5677_set_dai_fmt,
 	.set_sysclk = rt5677_set_dai_sysclk,
 	.set_pll = rt5677_set_dai_pll,
+	.set_tdm_slot = rt5677_set_tdm_slot,
 };
 
 static struct snd_soc_dai_driver rt5677_dai[] = {
@@ -3333,6 +3564,35 @@ static const struct i2c_device_id rt5677_i2c_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, rt5677_i2c_id);
 
+static int rt5677_parse_dt(struct rt5677_priv *rt5677, struct device_node *np)
+{
+	rt5677->pdata.in1_diff = of_property_read_bool(np,
+					"realtek,in1-differential");
+	rt5677->pdata.in2_diff = of_property_read_bool(np,
+					"realtek,in2-differential");
+	rt5677->pdata.lout1_diff = of_property_read_bool(np,
+					"realtek,lout1-differential");
+	rt5677->pdata.lout2_diff = of_property_read_bool(np,
+					"realtek,lout2-differential");
+	rt5677->pdata.lout3_diff = of_property_read_bool(np,
+					"realtek,lout3-differential");
+
+	rt5677->pow_ldo2 = of_get_named_gpio(np,
+					"realtek,pow-ldo2-gpio", 0);
+
+	/*
+	 * POW_LDO2 is optional (it may be statically tied on the board).
+	 * -ENOENT means that the property doesn't exist, i.e. there is no
+	 * GPIO, so is not an error. Any other error code means the property
+	 * exists, but could not be parsed.
+	 */
+	if (!gpio_is_valid(rt5677->pow_ldo2) &&
+			(rt5677->pow_ldo2 != -ENOENT))
+		return rt5677->pow_ldo2;
+
+	return 0;
+}
+
 static int rt5677_i2c_probe(struct i2c_client *i2c,
 		    const struct i2c_device_id *id)
 {
@@ -3351,6 +3611,33 @@ static int rt5677_i2c_probe(struct i2c_client *i2c,
 	if (pdata)
 		rt5677->pdata = *pdata;
 
+	if (i2c->dev.of_node) {
+		ret = rt5677_parse_dt(rt5677, i2c->dev.of_node);
+		if (ret) {
+			dev_err(&i2c->dev, "Failed to parse device tree: %d\n",
+				ret);
+			return ret;
+		}
+	} else {
+		rt5677->pow_ldo2 = -EINVAL;
+	}
+
+	if (gpio_is_valid(rt5677->pow_ldo2)) {
+		ret = devm_gpio_request_one(&i2c->dev, rt5677->pow_ldo2,
+					    GPIOF_OUT_INIT_HIGH,
+					    "RT5677 POW_LDO2");
+		if (ret < 0) {
+			dev_err(&i2c->dev, "Failed to request POW_LDO2 %d: %d\n",
+				rt5677->pow_ldo2, ret);
+			return ret;
+		}
+		/* Wait a while until I2C bus becomes available. The datasheet
+		 * does not specify the exact we should wait but startup
+		 * sequence mentiones at least a few milliseconds.
+		 */
+		msleep(10);
+	}
+
 	rt5677->regmap = devm_regmap_init_i2c(i2c, &rt5677_regmap);
 	if (IS_ERR(rt5677->regmap)) {
 		ret = PTR_ERR(rt5677->regmap);
@@ -3381,6 +3668,29 @@ static int rt5677_i2c_probe(struct i2c_client *i2c,
 		regmap_update_bits(rt5677->regmap, RT5677_IN1,
 					RT5677_IN_DF2, RT5677_IN_DF2);
 
+	if (rt5677->pdata.lout1_diff)
+		regmap_update_bits(rt5677->regmap, RT5677_LOUT1,
+					RT5677_LOUT1_L_DF, RT5677_LOUT1_L_DF);
+
+	if (rt5677->pdata.lout2_diff)
+		regmap_update_bits(rt5677->regmap, RT5677_LOUT1,
+					RT5677_LOUT2_L_DF, RT5677_LOUT2_L_DF);
+
+	if (rt5677->pdata.lout3_diff)
+		regmap_update_bits(rt5677->regmap, RT5677_LOUT1,
+					RT5677_LOUT3_L_DF, RT5677_LOUT3_L_DF);
+
+	if (rt5677->pdata.dmic2_clk_pin == RT5677_DMIC_CLK2) {
+		regmap_update_bits(rt5677->regmap, RT5677_GEN_CTRL2,
+					RT5677_GPIO5_FUNC_MASK,
+					RT5677_GPIO5_FUNC_DMIC);
+		regmap_update_bits(rt5677->regmap, RT5677_GPIO_CTRL2,
+					RT5677_GPIO5_DIR_MASK,
+					RT5677_GPIO5_DIR_OUT);
+	}
+
+	rt5677_init_gpio(i2c);
+
 	return snd_soc_register_codec(&i2c->dev, &soc_codec_dev_rt5677,
 				      rt5677_dai, ARRAY_SIZE(rt5677_dai));
 }
@@ -3388,6 +3698,7 @@ static int rt5677_i2c_probe(struct i2c_client *i2c,
 static int rt5677_i2c_remove(struct i2c_client *i2c)
 {
 	snd_soc_unregister_codec(&i2c->dev);
+	rt5677_free_gpio(i2c);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/rt5677.h b/sound/soc/codecs/rt5677.h
index 863393e62096..d4eb6d5e6746 100644
--- a/sound/soc/codecs/rt5677.h
+++ b/sound/soc/codecs/rt5677.h
@@ -382,6 +382,10 @@
 #define RT5677_ST_SEL_SFT			9
 #define RT5677_ST_EN				(0x1 << 6)
 #define RT5677_ST_EN_SFT			6
+#define RT5677_ST_GAIN				(0x1 << 5)
+#define RT5677_ST_GAIN_SFT			5
+#define RT5677_ST_VOL_MASK			(0x1f << 0)
+#define RT5677_ST_VOL_SFT			0
 
 /* Analog DAC1/2/3 Source Control (0x15) */
 #define RT5677_ANA_DAC3_SRC_SEL_MASK		(0x3 << 4)
@@ -1287,16 +1291,16 @@
 #define RT5677_PLL1_PD_SFT			8
 #define RT5677_PLL1_PD_1			(0x0 << 8)
 #define RT5677_PLL1_PD_2			(0x1 << 8)
-#define RT5671_DAC_OSR_MASK			(0x3 << 6)
-#define RT5671_DAC_OSR_SFT			6
-#define RT5671_DAC_OSR_128			(0x0 << 6)
-#define RT5671_DAC_OSR_64			(0x1 << 6)
-#define RT5671_DAC_OSR_32			(0x2 << 6)
-#define RT5671_ADC_OSR_MASK			(0x3 << 4)
-#define RT5671_ADC_OSR_SFT			4
-#define RT5671_ADC_OSR_128			(0x0 << 4)
-#define RT5671_ADC_OSR_64			(0x1 << 4)
-#define RT5671_ADC_OSR_32			(0x2 << 4)
+#define RT5677_DAC_OSR_MASK			(0x3 << 6)
+#define RT5677_DAC_OSR_SFT			6
+#define RT5677_DAC_OSR_128			(0x0 << 6)
+#define RT5677_DAC_OSR_64			(0x1 << 6)
+#define RT5677_DAC_OSR_32			(0x2 << 6)
+#define RT5677_ADC_OSR_MASK			(0x3 << 4)
+#define RT5677_ADC_OSR_SFT			4
+#define RT5677_ADC_OSR_128			(0x0 << 4)
+#define RT5677_ADC_OSR_64			(0x1 << 4)
+#define RT5677_ADC_OSR_32			(0x2 << 4)
 
 /* Global Clock Control 2 (0x81) */
 #define RT5677_PLL2_PR_SRC_MASK			(0x1 << 15)
@@ -1312,18 +1316,18 @@
 #define RT5677_PLL2_SRC_BCLK4			(0x4 << 12)
 #define RT5677_PLL2_SRC_RCCLK			(0x5 << 12)
 #define RT5677_PLL2_SRC_SLIM			(0x6 << 12)
-#define RT5671_DSP_ASRC_O_SRC			(0x3 << 10)
-#define RT5671_DSP_ASRC_O_SRC_SFT		10
-#define RT5671_DSP_ASRC_O_MCLK			(0x0 << 10)
-#define RT5671_DSP_ASRC_O_PLL1			(0x1 << 10)
-#define RT5671_DSP_ASRC_O_SLIM			(0x2 << 10)
-#define RT5671_DSP_ASRC_O_RCCLK			(0x3 << 10)
-#define RT5671_DSP_ASRC_I_SRC			(0x3 << 8)
-#define RT5671_DSP_ASRC_I_SRC_SFT		8
-#define RT5671_DSP_ASRC_I_MCLK			(0x0 << 8)
-#define RT5671_DSP_ASRC_I_PLL1			(0x1 << 8)
-#define RT5671_DSP_ASRC_I_SLIM			(0x2 << 8)
-#define RT5671_DSP_ASRC_I_RCCLK			(0x3 << 8)
+#define RT5677_DSP_ASRC_O_SRC			(0x3 << 10)
+#define RT5677_DSP_ASRC_O_SRC_SFT		10
+#define RT5677_DSP_ASRC_O_MCLK			(0x0 << 10)
+#define RT5677_DSP_ASRC_O_PLL1			(0x1 << 10)
+#define RT5677_DSP_ASRC_O_SLIM			(0x2 << 10)
+#define RT5677_DSP_ASRC_O_RCCLK			(0x3 << 10)
+#define RT5677_DSP_ASRC_I_SRC			(0x3 << 8)
+#define RT5677_DSP_ASRC_I_SRC_SFT		8
+#define RT5677_DSP_ASRC_I_MCLK			(0x0 << 8)
+#define RT5677_DSP_ASRC_I_PLL1			(0x1 << 8)
+#define RT5677_DSP_ASRC_I_SLIM			(0x2 << 8)
+#define RT5677_DSP_ASRC_I_RCCLK			(0x3 << 8)
 #define RT5677_DSP_CLK_SRC_MASK			(0x1 << 7)
 #define RT5677_DSP_CLK_SRC_SFT			7
 #define RT5677_DSP_CLK_SRC_PLL2			(0x0 << 7)
@@ -1363,6 +1367,110 @@
 #define RT5677_SEL_SRC_IB01			(0x1 << 0)
 #define RT5677_SEL_SRC_IB01_SFT			0
 
+/* GPIO status (0xbf) */
+#define RT5677_GPIO6_STATUS_MASK		(0x1 << 5)
+#define RT5677_GPIO6_STATUS_SFT			5
+#define RT5677_GPIO5_STATUS_MASK		(0x1 << 4)
+#define RT5677_GPIO5_STATUS_SFT			4
+#define RT5677_GPIO4_STATUS_MASK		(0x1 << 3)
+#define RT5677_GPIO4_STATUS_SFT			3
+#define RT5677_GPIO3_STATUS_MASK		(0x1 << 2)
+#define RT5677_GPIO3_STATUS_SFT			2
+#define RT5677_GPIO2_STATUS_MASK		(0x1 << 1)
+#define RT5677_GPIO2_STATUS_SFT			1
+#define RT5677_GPIO1_STATUS_MASK		(0x1 << 0)
+#define RT5677_GPIO1_STATUS_SFT			0
+
+/* GPIO Control 1 (0xc0) */
+#define RT5677_GPIO1_PIN_MASK			(0x1 << 15)
+#define RT5677_GPIO1_PIN_SFT			15
+#define RT5677_GPIO1_PIN_GPIO1			(0x0 << 15)
+#define RT5677_GPIO1_PIN_IRQ			(0x1 << 15)
+#define RT5677_IPTV_MODE_MASK			(0x1 << 14)
+#define RT5677_IPTV_MODE_SFT			14
+#define RT5677_IPTV_MODE_GPIO			(0x0 << 14)
+#define RT5677_IPTV_MODE_IPTV			(0x1 << 14)
+#define RT5677_FUNC_MODE_MASK			(0x1 << 13)
+#define RT5677_FUNC_MODE_SFT			13
+#define RT5677_FUNC_MODE_DMIC_GPIO		(0x0 << 13)
+#define RT5677_FUNC_MODE_JTAG			(0x1 << 13)
+
+/* GPIO Control 2 (0xc1) */
+#define RT5677_GPIO5_DIR_MASK			(0x1 << 14)
+#define RT5677_GPIO5_DIR_SFT			14
+#define RT5677_GPIO5_DIR_IN			(0x0 << 14)
+#define RT5677_GPIO5_DIR_OUT			(0x1 << 14)
+#define RT5677_GPIO5_OUT_MASK			(0x1 << 13)
+#define RT5677_GPIO5_OUT_SFT			13
+#define RT5677_GPIO5_OUT_LO			(0x0 << 13)
+#define RT5677_GPIO5_OUT_HI			(0x1 << 13)
+#define RT5677_GPIO5_P_MASK			(0x1 << 12)
+#define RT5677_GPIO5_P_SFT			12
+#define RT5677_GPIO5_P_NOR			(0x0 << 12)
+#define RT5677_GPIO5_P_INV			(0x1 << 12)
+#define RT5677_GPIO4_DIR_MASK			(0x1 << 11)
+#define RT5677_GPIO4_DIR_SFT			11
+#define RT5677_GPIO4_DIR_IN			(0x0 << 11)
+#define RT5677_GPIO4_DIR_OUT			(0x1 << 11)
+#define RT5677_GPIO4_OUT_MASK			(0x1 << 10)
+#define RT5677_GPIO4_OUT_SFT			10
+#define RT5677_GPIO4_OUT_LO			(0x0 << 10)
+#define RT5677_GPIO4_OUT_HI			(0x1 << 10)
+#define RT5677_GPIO4_P_MASK			(0x1 << 9)
+#define RT5677_GPIO4_P_SFT			9
+#define RT5677_GPIO4_P_NOR			(0x0 << 9)
+#define RT5677_GPIO4_P_INV			(0x1 << 9)
+#define RT5677_GPIO3_DIR_MASK			(0x1 << 8)
+#define RT5677_GPIO3_DIR_SFT			8
+#define RT5677_GPIO3_DIR_IN			(0x0 << 8)
+#define RT5677_GPIO3_DIR_OUT			(0x1 << 8)
+#define RT5677_GPIO3_OUT_MASK			(0x1 << 7)
+#define RT5677_GPIO3_OUT_SFT			7
+#define RT5677_GPIO3_OUT_LO			(0x0 << 7)
+#define RT5677_GPIO3_OUT_HI			(0x1 << 7)
+#define RT5677_GPIO3_P_MASK			(0x1 << 6)
+#define RT5677_GPIO3_P_SFT			6
+#define RT5677_GPIO3_P_NOR			(0x0 << 6)
+#define RT5677_GPIO3_P_INV			(0x1 << 6)
+#define RT5677_GPIO2_DIR_MASK			(0x1 << 5)
+#define RT5677_GPIO2_DIR_SFT			5
+#define RT5677_GPIO2_DIR_IN			(0x0 << 5)
+#define RT5677_GPIO2_DIR_OUT			(0x1 << 5)
+#define RT5677_GPIO2_OUT_MASK			(0x1 << 4)
+#define RT5677_GPIO2_OUT_SFT			4
+#define RT5677_GPIO2_OUT_LO			(0x0 << 4)
+#define RT5677_GPIO2_OUT_HI			(0x1 << 4)
+#define RT5677_GPIO2_P_MASK			(0x1 << 3)
+#define RT5677_GPIO2_P_SFT			3
+#define RT5677_GPIO2_P_NOR			(0x0 << 3)
+#define RT5677_GPIO2_P_INV			(0x1 << 3)
+#define RT5677_GPIO1_DIR_MASK			(0x1 << 2)
+#define RT5677_GPIO1_DIR_SFT			2
+#define RT5677_GPIO1_DIR_IN			(0x0 << 2)
+#define RT5677_GPIO1_DIR_OUT			(0x1 << 2)
+#define RT5677_GPIO1_OUT_MASK			(0x1 << 1)
+#define RT5677_GPIO1_OUT_SFT			1
+#define RT5677_GPIO1_OUT_LO			(0x0 << 1)
+#define RT5677_GPIO1_OUT_HI			(0x1 << 1)
+#define RT5677_GPIO1_P_MASK			(0x1 << 0)
+#define RT5677_GPIO1_P_SFT			0
+#define RT5677_GPIO1_P_NOR			(0x0 << 0)
+#define RT5677_GPIO1_P_INV			(0x1 << 0)
+
+/* GPIO Control 3 (0xc2) */
+#define RT5677_GPIO6_DIR_MASK			(0x1 << 2)
+#define RT5677_GPIO6_DIR_SFT			2
+#define RT5677_GPIO6_DIR_IN			(0x0 << 2)
+#define RT5677_GPIO6_DIR_OUT			(0x1 << 2)
+#define RT5677_GPIO6_OUT_MASK			(0x1 << 1)
+#define RT5677_GPIO6_OUT_SFT			1
+#define RT5677_GPIO6_OUT_LO			(0x0 << 1)
+#define RT5677_GPIO6_OUT_HI			(0x1 << 1)
+#define RT5677_GPIO6_P_MASK			(0x1 << 0)
+#define RT5677_GPIO6_P_SFT			0
+#define RT5677_GPIO6_P_NOR			(0x0 << 0)
+#define RT5677_GPIO6_P_INV			(0x1 << 0)
+
 /* Virtual DSP Mixer Control (0xf7 0xf8 0xf9) */
 #define RT5677_DSP_IB_01_H			(0x1 << 15)
 #define RT5677_DSP_IB_01_H_SFT			15
@@ -1393,6 +1501,11 @@
 #define RT5677_DSP_IB_9_L			(0x1 << 1)
 #define RT5677_DSP_IB_9_L_SFT			1
 
+/* General Control2 (0xfc)*/
+#define RT5677_GPIO5_FUNC_MASK			(0x1 << 9)
+#define RT5677_GPIO5_FUNC_GPIO			(0x0 << 9)
+#define RT5677_GPIO5_FUNC_DMIC			(0x1 << 9)
+
 /* System Clock Source */
 enum {
 	RT5677_SCLK_S_MCLK,
@@ -1418,6 +1531,16 @@ enum {
 	RT5677_AIFS,
 };
 
+enum {
+	RT5677_GPIO1,
+	RT5677_GPIO2,
+	RT5677_GPIO3,
+	RT5677_GPIO4,
+	RT5677_GPIO5,
+	RT5677_GPIO6,
+	RT5677_GPIO_NUM,
+};
+
 struct rt5677_priv {
 	struct snd_soc_codec *codec;
 	struct rt5677_platform_data pdata;
@@ -1431,6 +1554,10 @@ struct rt5677_priv {
 	int pll_src;
 	int pll_in;
 	int pll_out;
+	int pow_ldo2; /* POW_LDO2 pin */
+#ifdef CONFIG_GPIOLIB
+	struct gpio_chip gpio_chip;
+#endif
 };
 
 #endif /* __RT5677_H__ */
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index e997d271728d..6bb77d76561b 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -626,6 +626,9 @@ static int sgtl5000_set_clock(struct snd_soc_codec *codec, int frame_rate)
 		} else {
 			dev_err(codec->dev,
 				"PLL not supported in slave mode\n");
+			dev_err(codec->dev, "%d ratio is not supported. "
+				"SYS_MCLK needs to be 256, 384 or 512 * fs\n",
+				sgtl5000->sysclk / sys_fs);
 			return -EINVAL;
 		}
 	}
@@ -1073,26 +1076,6 @@ static bool sgtl5000_readable(struct device *dev, unsigned int reg)
 	}
 }
 
-#ifdef CONFIG_SUSPEND
-static int sgtl5000_suspend(struct snd_soc_codec *codec)
-{
-	sgtl5000_set_bias_level(codec, SND_SOC_BIAS_OFF);
-
-	return 0;
-}
-
-static int sgtl5000_resume(struct snd_soc_codec *codec)
-{
-	/* Bring the codec back up to standby to enable regulators */
-	sgtl5000_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
-	return 0;
-}
-#else
-#define sgtl5000_suspend NULL
-#define sgtl5000_resume  NULL
-#endif	/* CONFIG_SUSPEND */
-
 /*
  * sgtl5000 has 3 internal power supplies:
  * 1. VAG, normally set to vdda/2
@@ -1352,11 +1335,6 @@ static int sgtl5000_probe(struct snd_soc_codec *codec)
 	 */
 	snd_soc_write(codec, SGTL5000_DAP_CTRL, 0);
 
-	/* leading to standby state */
-	ret = sgtl5000_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-	if (ret)
-		goto err;
-
 	return 0;
 
 err:
@@ -1373,8 +1351,6 @@ static int sgtl5000_remove(struct snd_soc_codec *codec)
 {
 	struct sgtl5000_priv *sgtl5000 = snd_soc_codec_get_drvdata(codec);
 
-	sgtl5000_set_bias_level(codec, SND_SOC_BIAS_OFF);
-
 	regulator_bulk_disable(ARRAY_SIZE(sgtl5000->supplies),
 						sgtl5000->supplies);
 	regulator_bulk_free(ARRAY_SIZE(sgtl5000->supplies),
@@ -1387,9 +1363,8 @@ static int sgtl5000_remove(struct snd_soc_codec *codec)
 static struct snd_soc_codec_driver sgtl5000_driver = {
 	.probe = sgtl5000_probe,
 	.remove = sgtl5000_remove,
-	.suspend = sgtl5000_suspend,
-	.resume = sgtl5000_resume,
 	.set_bias_level = sgtl5000_set_bias_level,
+	.suspend_bias_off = true,
 	.controls = sgtl5000_snd_controls,
 	.num_controls = ARRAY_SIZE(sgtl5000_snd_controls),
 	.dapm_widgets = sgtl5000_dapm_widgets,
@@ -1442,6 +1417,7 @@ static int sgtl5000_i2c_probe(struct i2c_client *client,
 {
 	struct sgtl5000_priv *sgtl5000;
 	int ret, reg, rev;
+	unsigned int mclk;
 
 	sgtl5000 = devm_kzalloc(&client->dev, sizeof(struct sgtl5000_priv),
 								GFP_KERNEL);
@@ -1465,6 +1441,14 @@ static int sgtl5000_i2c_probe(struct i2c_client *client,
 		return ret;
 	}
 
+	/* SGTL5000 SYS_MCLK should be between 8 and 27 MHz */
+	mclk = clk_get_rate(sgtl5000->mclk);
+	if (mclk < 8000000 || mclk > 27000000) {
+		dev_err(&client->dev, "Invalid SYS_CLK frequency: %u.%03uMHz\n",
+			mclk / 1000000, mclk / 1000 % 1000);
+		return -EINVAL;
+	}
+
 	ret = clk_prepare_enable(sgtl5000->mclk);
 	if (ret)
 		return ret;
diff --git a/sound/soc/codecs/ssm2518.c b/sound/soc/codecs/ssm2518.c
index e8680bea5f86..67ea55adb307 100644
--- a/sound/soc/codecs/ssm2518.c
+++ b/sound/soc/codecs/ssm2518.c
@@ -646,17 +646,6 @@ static struct snd_soc_dai_driver ssm2518_dai = {
 	.ops = &ssm2518_dai_ops,
 };
 
-static int ssm2518_probe(struct snd_soc_codec *codec)
-{
-	return ssm2518_set_bias_level(codec, SND_SOC_BIAS_OFF);
-}
-
-static int ssm2518_remove(struct snd_soc_codec *codec)
-{
-	ssm2518_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	return 0;
-}
-
 static int ssm2518_set_sysclk(struct snd_soc_codec *codec, int clk_id,
 	int source, unsigned int freq, int dir)
 {
@@ -727,8 +716,6 @@ static int ssm2518_set_sysclk(struct snd_soc_codec *codec, int clk_id,
 }
 
 static struct snd_soc_codec_driver ssm2518_codec_driver = {
-	.probe = ssm2518_probe,
-	.remove = ssm2518_remove,
 	.set_bias_level = ssm2518_set_bias_level,
 	.set_sysclk = ssm2518_set_sysclk,
 	.idle_bias_off = true,
diff --git a/sound/soc/codecs/ssm2602-i2c.c b/sound/soc/codecs/ssm2602-i2c.c
index abd63d537173..0d9779d6bfda 100644
--- a/sound/soc/codecs/ssm2602-i2c.c
+++ b/sound/soc/codecs/ssm2602-i2c.c
@@ -41,10 +41,19 @@ static const struct i2c_device_id ssm2602_i2c_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ssm2602_i2c_id);
 
+static const struct of_device_id ssm2602_of_match[] = {
+	{ .compatible = "adi,ssm2602", },
+	{ .compatible = "adi,ssm2603", },
+	{ .compatible = "adi,ssm2604", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ssm2602_of_match);
+
 static struct i2c_driver ssm2602_i2c_driver = {
 	.driver = {
 		.name = "ssm2602",
 		.owner = THIS_MODULE,
+		.of_match_table = ssm2602_of_match,
 	},
 	.probe = ssm2602_i2c_probe,
 	.remove = ssm2602_i2c_remove,
diff --git a/sound/soc/codecs/ssm2602-spi.c b/sound/soc/codecs/ssm2602-spi.c
index 2bf55e24a7bb..b5df14fbe3ad 100644
--- a/sound/soc/codecs/ssm2602-spi.c
+++ b/sound/soc/codecs/ssm2602-spi.c
@@ -26,10 +26,17 @@ static int ssm2602_spi_remove(struct spi_device *spi)
 	return 0;
 }
 
+static const struct of_device_id ssm2602_of_match[] = {
+	{ .compatible = "adi,ssm2602", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ssm2602_of_match);
+
 static struct spi_driver ssm2602_spi_driver = {
 	.driver = {
 		.name	= "ssm2602",
 		.owner	= THIS_MODULE,
+		.of_match_table = ssm2602_of_match,
 	},
 	.probe		= ssm2602_spi_probe,
 	.remove		= ssm2602_spi_remove,
diff --git a/sound/soc/codecs/ssm2602.c b/sound/soc/codecs/ssm2602.c
index 4021cd435740..314eaece1b7d 100644
--- a/sound/soc/codecs/ssm2602.c
+++ b/sound/soc/codecs/ssm2602.c
@@ -192,7 +192,7 @@ static const struct snd_pcm_hw_constraint_list ssm2602_constraints_12288000 = {
 };
 
 static const unsigned int ssm2602_rates_11289600[] = {
-	8000, 44100, 88200,
+	8000, 11025, 22050, 44100, 88200,
 };
 
 static const struct snd_pcm_hw_constraint_list ssm2602_constraints_11289600 = {
@@ -237,6 +237,16 @@ static const struct ssm2602_coeff ssm2602_coeff_table[] = {
 	{18432000, 96000, SSM2602_COEFF_SRATE(0x7, 0x1, 0x0)},
 	{12000000, 96000, SSM2602_COEFF_SRATE(0x7, 0x0, 0x1)},
 
+	/* 11.025k */
+	{11289600, 11025, SSM2602_COEFF_SRATE(0xc, 0x0, 0x0)},
+	{16934400, 11025, SSM2602_COEFF_SRATE(0xc, 0x1, 0x0)},
+	{12000000, 11025, SSM2602_COEFF_SRATE(0xc, 0x1, 0x1)},
+
+	/* 22.05k */
+	{11289600, 22050, SSM2602_COEFF_SRATE(0xd, 0x0, 0x0)},
+	{16934400, 22050, SSM2602_COEFF_SRATE(0xd, 0x1, 0x0)},
+	{12000000, 22050, SSM2602_COEFF_SRATE(0xd, 0x1, 0x1)},
+
 	/* 44.1k */
 	{11289600, 44100, SSM2602_COEFF_SRATE(0x8, 0x0, 0x0)},
 	{16934400, 44100, SSM2602_COEFF_SRATE(0x8, 0x1, 0x0)},
@@ -467,7 +477,8 @@ static int ssm2602_set_bias_level(struct snd_soc_codec *codec,
 	return 0;
 }
 
-#define SSM2602_RATES (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |\
+#define SSM2602_RATES (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_11025 |\
+		SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_22050 |\
 		SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_44100 |\
 		SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_88200 |\
 		SNDRV_PCM_RATE_96000)
@@ -502,18 +513,11 @@ static struct snd_soc_dai_driver ssm2602_dai = {
 	.symmetric_samplebits = 1,
 };
 
-static int ssm2602_suspend(struct snd_soc_codec *codec)
-{
-	ssm2602_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	return 0;
-}
-
 static int ssm2602_resume(struct snd_soc_codec *codec)
 {
 	struct ssm2602_priv *ssm2602 = snd_soc_codec_get_drvdata(codec);
 
 	regcache_sync(ssm2602->regmap);
-	ssm2602_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
 
 	return 0;
 }
@@ -586,27 +590,14 @@ static int ssm260x_codec_probe(struct snd_soc_codec *codec)
 		break;
 	}
 
-	if (ret)
-		return ret;
-
-	ssm2602_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
-	return 0;
-}
-
-/* remove everything here */
-static int ssm2602_remove(struct snd_soc_codec *codec)
-{
-	ssm2602_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	return 0;
+	return ret;
 }
 
 static struct snd_soc_codec_driver soc_codec_dev_ssm2602 = {
 	.probe =	ssm260x_codec_probe,
-	.remove =	ssm2602_remove,
-	.suspend =	ssm2602_suspend,
 	.resume =	ssm2602_resume,
 	.set_bias_level = ssm2602_set_bias_level,
+	.suspend_bias_off = true,
 
 	.controls = ssm260x_snd_controls,
 	.num_controls = ARRAY_SIZE(ssm260x_snd_controls),
diff --git a/sound/soc/codecs/ssm4567.c b/sound/soc/codecs/ssm4567.c
new file mode 100644
index 000000000000..4b5c17f8507e
--- /dev/null
+++ b/sound/soc/codecs/ssm4567.c
@@ -0,0 +1,343 @@
+/*
+ * SSM4567 amplifier audio driver
+ *
+ * Copyright 2014 Google Chromium project.
+ *  Author: Anatol Pomozov <anatol@chromium.org>
+ *
+ * Based on code copyright/by:
+ *   Copyright 2013 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/i2c.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/initval.h>
+#include <sound/tlv.h>
+
+#define SSM4567_REG_POWER_CTRL		0x00
+#define SSM4567_REG_AMP_SNS_CTRL		0x01
+#define SSM4567_REG_DAC_CTRL		0x02
+#define SSM4567_REG_DAC_VOLUME		0x03
+#define SSM4567_REG_SAI_CTRL_1		0x04
+#define SSM4567_REG_SAI_CTRL_2		0x05
+#define SSM4567_REG_SAI_PLACEMENT_1		0x06
+#define SSM4567_REG_SAI_PLACEMENT_2		0x07
+#define SSM4567_REG_SAI_PLACEMENT_3		0x08
+#define SSM4567_REG_SAI_PLACEMENT_4		0x09
+#define SSM4567_REG_SAI_PLACEMENT_5		0x0a
+#define SSM4567_REG_SAI_PLACEMENT_6		0x0b
+#define SSM4567_REG_BATTERY_V_OUT		0x0c
+#define SSM4567_REG_LIMITER_CTRL_1		0x0d
+#define SSM4567_REG_LIMITER_CTRL_2		0x0e
+#define SSM4567_REG_LIMITER_CTRL_3		0x0f
+#define SSM4567_REG_STATUS_1		0x10
+#define SSM4567_REG_STATUS_2		0x11
+#define SSM4567_REG_FAULT_CTRL		0x12
+#define SSM4567_REG_PDM_CTRL		0x13
+#define SSM4567_REG_MCLK_RATIO		0x14
+#define SSM4567_REG_BOOST_CTRL_1		0x15
+#define SSM4567_REG_BOOST_CTRL_2		0x16
+#define SSM4567_REG_SOFT_RESET		0xff
+
+/* POWER_CTRL */
+#define SSM4567_POWER_APWDN_EN		BIT(7)
+#define SSM4567_POWER_BSNS_PWDN		BIT(6)
+#define SSM4567_POWER_VSNS_PWDN		BIT(5)
+#define SSM4567_POWER_ISNS_PWDN		BIT(4)
+#define SSM4567_POWER_BOOST_PWDN		BIT(3)
+#define SSM4567_POWER_AMP_PWDN		BIT(2)
+#define SSM4567_POWER_VBAT_ONLY		BIT(1)
+#define SSM4567_POWER_SPWDN			BIT(0)
+
+/* DAC_CTRL */
+#define SSM4567_DAC_HV			BIT(7)
+#define SSM4567_DAC_MUTE		BIT(6)
+#define SSM4567_DAC_HPF			BIT(5)
+#define SSM4567_DAC_LPM			BIT(4)
+#define SSM4567_DAC_FS_MASK	0x7
+#define SSM4567_DAC_FS_8000_12000	0x0
+#define SSM4567_DAC_FS_16000_24000	0x1
+#define SSM4567_DAC_FS_32000_48000	0x2
+#define SSM4567_DAC_FS_64000_96000	0x3
+#define SSM4567_DAC_FS_128000_192000	0x4
+
+struct ssm4567 {
+	struct regmap *regmap;
+};
+
+static const struct reg_default ssm4567_reg_defaults[] = {
+	{ SSM4567_REG_POWER_CTRL,	0x81 },
+	{ SSM4567_REG_AMP_SNS_CTRL, 0x09 },
+	{ SSM4567_REG_DAC_CTRL, 0x32 },
+	{ SSM4567_REG_DAC_VOLUME, 0x40 },
+	{ SSM4567_REG_SAI_CTRL_1, 0x00 },
+	{ SSM4567_REG_SAI_CTRL_2, 0x08 },
+	{ SSM4567_REG_SAI_PLACEMENT_1, 0x01 },
+	{ SSM4567_REG_SAI_PLACEMENT_2, 0x20 },
+	{ SSM4567_REG_SAI_PLACEMENT_3, 0x32 },
+	{ SSM4567_REG_SAI_PLACEMENT_4, 0x07 },
+	{ SSM4567_REG_SAI_PLACEMENT_5, 0x07 },
+	{ SSM4567_REG_SAI_PLACEMENT_6, 0x07 },
+	{ SSM4567_REG_BATTERY_V_OUT, 0x00 },
+	{ SSM4567_REG_LIMITER_CTRL_1, 0xa4 },
+	{ SSM4567_REG_LIMITER_CTRL_2, 0x73 },
+	{ SSM4567_REG_LIMITER_CTRL_3, 0x00 },
+	{ SSM4567_REG_STATUS_1, 0x00 },
+	{ SSM4567_REG_STATUS_2, 0x00 },
+	{ SSM4567_REG_FAULT_CTRL, 0x30 },
+	{ SSM4567_REG_PDM_CTRL, 0x40 },
+	{ SSM4567_REG_MCLK_RATIO, 0x11 },
+	{ SSM4567_REG_BOOST_CTRL_1, 0x03 },
+	{ SSM4567_REG_BOOST_CTRL_2, 0x00 },
+	{ SSM4567_REG_SOFT_RESET, 0x00 },
+};
+
+
+static bool ssm4567_readable_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case SSM4567_REG_POWER_CTRL ... SSM4567_REG_BOOST_CTRL_2:
+		return true;
+	default:
+		return false;
+	}
+
+}
+
+static bool ssm4567_writeable_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case SSM4567_REG_POWER_CTRL ... SSM4567_REG_SAI_PLACEMENT_6:
+	case SSM4567_REG_LIMITER_CTRL_1 ... SSM4567_REG_LIMITER_CTRL_3:
+	case SSM4567_REG_FAULT_CTRL ... SSM4567_REG_BOOST_CTRL_2:
+	/* The datasheet states that soft reset register is read-only,
+	 * but logically it is write-only. */
+	case SSM4567_REG_SOFT_RESET:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool ssm4567_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case SSM4567_REG_BATTERY_V_OUT:
+	case SSM4567_REG_STATUS_1 ... SSM4567_REG_STATUS_2:
+	case SSM4567_REG_SOFT_RESET:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const DECLARE_TLV_DB_MINMAX_MUTE(ssm4567_vol_tlv, -7125, 2400);
+
+static const struct snd_kcontrol_new ssm4567_snd_controls[] = {
+	SOC_SINGLE_TLV("Master Playback Volume", SSM4567_REG_DAC_VOLUME, 0,
+		0xff, 1, ssm4567_vol_tlv),
+	SOC_SINGLE("DAC Low Power Mode Switch", SSM4567_REG_DAC_CTRL, 4, 1, 0),
+};
+
+static const struct snd_soc_dapm_widget ssm4567_dapm_widgets[] = {
+	SND_SOC_DAPM_DAC("DAC", "HiFi Playback", SSM4567_REG_POWER_CTRL, 2, 1),
+
+	SND_SOC_DAPM_OUTPUT("OUT"),
+};
+
+static const struct snd_soc_dapm_route ssm4567_routes[] = {
+	{ "OUT", NULL, "DAC" },
+};
+
+static int ssm4567_hw_params(struct snd_pcm_substream *substream,
+	struct snd_pcm_hw_params *params, struct snd_soc_dai *dai)
+{
+	struct snd_soc_codec *codec = dai->codec;
+	struct ssm4567 *ssm4567 = snd_soc_codec_get_drvdata(codec);
+	unsigned int rate = params_rate(params);
+	unsigned int dacfs;
+
+	if (rate >= 8000 && rate <= 12000)
+		dacfs = SSM4567_DAC_FS_8000_12000;
+	else if (rate >= 16000 && rate <= 24000)
+		dacfs = SSM4567_DAC_FS_16000_24000;
+	else if (rate >= 32000 && rate <= 48000)
+		dacfs = SSM4567_DAC_FS_32000_48000;
+	else if (rate >= 64000 && rate <= 96000)
+		dacfs = SSM4567_DAC_FS_64000_96000;
+	else if (rate >= 128000 && rate <= 192000)
+		dacfs = SSM4567_DAC_FS_128000_192000;
+	else
+		return -EINVAL;
+
+	return regmap_update_bits(ssm4567->regmap, SSM4567_REG_DAC_CTRL,
+				SSM4567_DAC_FS_MASK, dacfs);
+}
+
+static int ssm4567_mute(struct snd_soc_dai *dai, int mute)
+{
+	struct ssm4567 *ssm4567 = snd_soc_codec_get_drvdata(dai->codec);
+	unsigned int val;
+
+	val = mute ? SSM4567_DAC_MUTE : 0;
+	return regmap_update_bits(ssm4567->regmap, SSM4567_REG_DAC_CTRL,
+			SSM4567_DAC_MUTE, val);
+}
+
+static int ssm4567_set_power(struct ssm4567 *ssm4567, bool enable)
+{
+	int ret = 0;
+
+	if (!enable) {
+		ret = regmap_update_bits(ssm4567->regmap,
+			SSM4567_REG_POWER_CTRL,
+			SSM4567_POWER_SPWDN, SSM4567_POWER_SPWDN);
+		regcache_mark_dirty(ssm4567->regmap);
+	}
+
+	regcache_cache_only(ssm4567->regmap, !enable);
+
+	if (enable) {
+		ret = regmap_update_bits(ssm4567->regmap,
+			SSM4567_REG_POWER_CTRL,
+			SSM4567_POWER_SPWDN, 0x00);
+		regcache_sync(ssm4567->regmap);
+	}
+
+	return ret;
+}
+
+static int ssm4567_set_bias_level(struct snd_soc_codec *codec,
+	enum snd_soc_bias_level level)
+{
+	struct ssm4567 *ssm4567 = snd_soc_codec_get_drvdata(codec);
+	int ret = 0;
+
+	switch (level) {
+	case SND_SOC_BIAS_ON:
+		break;
+	case SND_SOC_BIAS_PREPARE:
+		break;
+	case SND_SOC_BIAS_STANDBY:
+		if (codec->dapm.bias_level == SND_SOC_BIAS_OFF)
+			ret = ssm4567_set_power(ssm4567, true);
+		break;
+	case SND_SOC_BIAS_OFF:
+		ret = ssm4567_set_power(ssm4567, false);
+		break;
+	}
+
+	if (ret)
+		return ret;
+
+	codec->dapm.bias_level = level;
+
+	return 0;
+}
+
+static const struct snd_soc_dai_ops ssm4567_dai_ops = {
+	.hw_params	= ssm4567_hw_params,
+	.digital_mute	= ssm4567_mute,
+};
+
+static struct snd_soc_dai_driver ssm4567_dai = {
+	.name = "ssm4567-hifi",
+	.playback = {
+		.stream_name = "Playback",
+		.channels_min = 1,
+		.channels_max = 1,
+		.rates = SNDRV_PCM_RATE_8000_192000,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE |
+			SNDRV_PCM_FMTBIT_S32,
+	},
+	.ops = &ssm4567_dai_ops,
+};
+
+static struct snd_soc_codec_driver ssm4567_codec_driver = {
+	.set_bias_level = ssm4567_set_bias_level,
+	.idle_bias_off = true,
+
+	.controls = ssm4567_snd_controls,
+	.num_controls = ARRAY_SIZE(ssm4567_snd_controls),
+	.dapm_widgets = ssm4567_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(ssm4567_dapm_widgets),
+	.dapm_routes = ssm4567_routes,
+	.num_dapm_routes = ARRAY_SIZE(ssm4567_routes),
+};
+
+static const struct regmap_config ssm4567_regmap_config = {
+	.val_bits = 8,
+	.reg_bits = 8,
+
+	.max_register = SSM4567_REG_SOFT_RESET,
+	.readable_reg = ssm4567_readable_reg,
+	.writeable_reg = ssm4567_writeable_reg,
+	.volatile_reg = ssm4567_volatile_reg,
+
+	.cache_type = REGCACHE_RBTREE,
+	.reg_defaults = ssm4567_reg_defaults,
+	.num_reg_defaults = ARRAY_SIZE(ssm4567_reg_defaults),
+};
+
+static int ssm4567_i2c_probe(struct i2c_client *i2c,
+	const struct i2c_device_id *id)
+{
+	struct ssm4567 *ssm4567;
+	int ret;
+
+	ssm4567 = devm_kzalloc(&i2c->dev, sizeof(*ssm4567), GFP_KERNEL);
+	if (ssm4567 == NULL)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c, ssm4567);
+
+	ssm4567->regmap = devm_regmap_init_i2c(i2c, &ssm4567_regmap_config);
+	if (IS_ERR(ssm4567->regmap))
+		return PTR_ERR(ssm4567->regmap);
+
+	ret = regmap_write(ssm4567->regmap, SSM4567_REG_SOFT_RESET, 0x00);
+	if (ret)
+		return ret;
+
+	ret = ssm4567_set_power(ssm4567, false);
+	if (ret)
+		return ret;
+
+	return snd_soc_register_codec(&i2c->dev, &ssm4567_codec_driver,
+			&ssm4567_dai, 1);
+}
+
+static int ssm4567_i2c_remove(struct i2c_client *client)
+{
+	snd_soc_unregister_codec(&client->dev);
+	return 0;
+}
+
+static const struct i2c_device_id ssm4567_i2c_ids[] = {
+	{ "ssm4567", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, ssm4567_i2c_ids);
+
+static struct i2c_driver ssm4567_driver = {
+	.driver = {
+		.name = "ssm4567",
+		.owner = THIS_MODULE,
+	},
+	.probe = ssm4567_i2c_probe,
+	.remove = ssm4567_i2c_remove,
+	.id_table = ssm4567_i2c_ids,
+};
+module_i2c_driver(ssm4567_driver);
+
+MODULE_DESCRIPTION("ASoC SSM4567 driver");
+MODULE_AUTHOR("Anatol Pomozov <anatol@chromium.org>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/tas2552.c b/sound/soc/codecs/tas2552.c
index 23b32960ff1d..f039dc825971 100644
--- a/sound/soc/codecs/tas2552.c
+++ b/sound/soc/codecs/tas2552.c
@@ -78,6 +78,44 @@ struct tas2552_data {
 	unsigned int mclk;
 };
 
+/* Input mux controls */
+static const char *tas2552_input_texts[] = {
+	"Digital", "Analog"
+};
+
+static SOC_ENUM_SINGLE_DECL(tas2552_input_mux_enum, TAS2552_CFG_3, 7,
+			    tas2552_input_texts);
+
+static const struct snd_kcontrol_new tas2552_input_mux_control[] = {
+	SOC_DAPM_ENUM("Input selection", tas2552_input_mux_enum)
+};
+
+static const struct snd_soc_dapm_widget tas2552_dapm_widgets[] =
+{
+	SND_SOC_DAPM_INPUT("IN"),
+
+	/* MUX Controls */
+	SND_SOC_DAPM_MUX("Input selection", SND_SOC_NOPM, 0, 0,
+				tas2552_input_mux_control),
+
+	SND_SOC_DAPM_AIF_IN("DAC IN", "DAC Playback", 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_DAC("DAC", NULL, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_OUT_DRV("ClassD", TAS2552_CFG_2, 7, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PLL", TAS2552_CFG_2, 3, 0, NULL, 0),
+
+	SND_SOC_DAPM_OUTPUT("OUT")
+};
+
+static const struct snd_soc_dapm_route tas2552_audio_map[] = {
+	{"DAC", NULL, "DAC IN"},
+	{"Input selection", "Digital", "DAC"},
+	{"Input selection", "Analog", "IN"},
+	{"ClassD", NULL, "Input selection"},
+	{"OUT", NULL, "ClassD"},
+	{"ClassD", NULL, "PLL"},
+};
+
+#ifdef CONFIG_PM_RUNTIME
 static void tas2552_sw_shutdown(struct tas2552_data *tas_data, int sw_shutdown)
 {
 	u8 cfg1_reg;
@@ -90,6 +128,7 @@ static void tas2552_sw_shutdown(struct tas2552_data *tas_data, int sw_shutdown)
 	snd_soc_update_bits(tas_data->codec, TAS2552_CFG_1,
 						 TAS2552_SWS_MASK, cfg1_reg);
 }
+#endif
 
 static int tas2552_hw_params(struct snd_pcm_substream *substream,
 			     struct snd_pcm_hw_params *params,
@@ -101,10 +140,6 @@ static int tas2552_hw_params(struct snd_pcm_substream *substream,
 	int d;
 	u8 p, j;
 
-	/* Turn on Class D amplifier */
-	snd_soc_update_bits(codec, TAS2552_CFG_2, TAS2552_CLASSD_EN_MASK,
-						TAS2552_CLASSD_EN);
-
 	if (!tas2552->mclk)
 		return -EINVAL;
 
@@ -147,9 +182,6 @@ static int tas2552_hw_params(struct snd_pcm_substream *substream,
 
 	}
 
-	snd_soc_update_bits(codec, TAS2552_CFG_2, TAS2552_PLL_ENABLE,
-						TAS2552_PLL_ENABLE);
-
 	return 0;
 }
 
@@ -269,19 +301,10 @@ static const struct dev_pm_ops tas2552_pm = {
 			   NULL)
 };
 
-static void tas2552_shutdown(struct snd_pcm_substream *substream,
-			   struct snd_soc_dai *dai)
-{
-	struct snd_soc_codec *codec = dai->codec;
-
-	snd_soc_update_bits(codec, TAS2552_CFG_2, TAS2552_PLL_ENABLE, 0);
-}
-
 static struct snd_soc_dai_ops tas2552_speaker_dai_ops = {
 	.hw_params	= tas2552_hw_params,
 	.set_sysclk	= tas2552_set_dai_sysclk,
 	.set_fmt	= tas2552_set_dai_fmt,
-	.shutdown	= tas2552_shutdown,
 	.digital_mute = tas2552_mute,
 };
 
@@ -294,7 +317,7 @@ static struct snd_soc_dai_driver tas2552_dai[] = {
 	{
 		.name = "tas2552-amplifier",
 		.playback = {
-			.stream_name = "Speaker",
+			.stream_name = "Playback",
 			.channels_min = 2,
 			.channels_max = 2,
 			.rates = SNDRV_PCM_RATE_8000_192000,
@@ -312,6 +335,7 @@ static DECLARE_TLV_DB_SCALE(dac_tlv, -7, 100, 24);
 static const struct snd_kcontrol_new tas2552_snd_controls[] = {
 	SOC_SINGLE_TLV("Speaker Driver Playback Volume",
 			 TAS2552_PGA_GAIN, 0, 0x1f, 1, dac_tlv),
+	SOC_DAPM_SINGLE("Playback AMP", SND_SOC_NOPM, 0, 1, 0),
 };
 
 static const struct reg_default tas2552_init_regs[] = {
@@ -321,6 +345,7 @@ static const struct reg_default tas2552_init_regs[] = {
 static int tas2552_codec_probe(struct snd_soc_codec *codec)
 {
 	struct tas2552_data *tas2552 = snd_soc_codec_get_drvdata(codec);
+	struct snd_soc_dapm_context *dapm = &codec->dapm;
 	int ret;
 
 	tas2552->codec = codec;
@@ -362,9 +387,14 @@ static int tas2552_codec_probe(struct snd_soc_codec *codec)
 		goto patch_fail;
 	}
 
-	snd_soc_write(codec, TAS2552_CFG_2, TAS2552_CLASSD_EN |
-				  TAS2552_BOOST_EN | TAS2552_APT_EN |
-				  TAS2552_LIM_EN);
+	snd_soc_write(codec, TAS2552_CFG_2, TAS2552_BOOST_EN |
+				  TAS2552_APT_EN | TAS2552_LIM_EN);
+
+	snd_soc_dapm_new_controls(dapm, tas2552_dapm_widgets,
+				ARRAY_SIZE(tas2552_dapm_widgets));
+	snd_soc_dapm_add_routes(dapm, tas2552_audio_map,
+				ARRAY_SIZE(tas2552_audio_map));
+
 	return 0;
 
 patch_fail:
diff --git a/sound/soc/codecs/tlv320aic31xx.c b/sound/soc/codecs/tlv320aic31xx.c
index aea9e1ff9126..145fe5b253d4 100644
--- a/sound/soc/codecs/tlv320aic31xx.c
+++ b/sound/soc/codecs/tlv320aic31xx.c
@@ -167,13 +167,13 @@ struct aic31xx_priv {
 	struct regulator_bulk_data supplies[AIC31XX_NUM_SUPPLIES];
 	struct aic31xx_disable_nb disable_nb[AIC31XX_NUM_SUPPLIES];
 	unsigned int sysclk;
+	u8 p_div;
 	int rate_div_line;
 };
 
 struct aic31xx_rate_divs {
-	u32 mclk;
+	u32 mclk_p;
 	u32 rate;
-	u8 p_val;
 	u8 pll_j;
 	u16 pll_d;
 	u16 dosr;
@@ -186,62 +186,51 @@ struct aic31xx_rate_divs {
 
 /* ADC dividers can be disabled by cofiguring them to 0 */
 static const struct aic31xx_rate_divs aic31xx_divs[] = {
-	/* mclk      rate  pll: p  j	 d     dosr ndac mdac  aors nadc madc */
+	/* mclk/p    rate  pll: j     d        dosr ndac mdac  aors nadc madc */
 	/* 8k rate */
-	{12000000,   8000,	1, 8, 1920,	128,  48,  2,	128,  48,  2},
-	{12000000,   8000,	1, 8, 1920,	128,  32,  3,	128,  32,  3},
-	{24000000,   8000,	2, 8, 1920,	128,  48,  2,	128,  48,  2},
-	{25000000,   8000,	2, 7, 8643,	128,  48,  2,	128,  48,  2},
+	{12000000,   8000,	8, 1920,	128,  48,  2,	128,  48,  2},
+	{12000000,   8000,	8, 1920,	128,  32,  3,	128,  32,  3},
+	{12500000,   8000,	7, 8643,	128,  48,  2,	128,  48,  2},
 	/* 11.025k rate */
-	{12000000,  11025,	1, 7, 5264,	128,  32,  2,	128,  32,  2},
-	{12000000,  11025,	1, 8, 4672,	128,  24,  3,	128,  24,  3},
-	{24000000,  11025,	2, 7, 5264,	128,  32,  2,	128,  32,  2},
-	{25000000,  11025,	2, 7, 2253,	128,  32,  2,	128,  32,  2},
+	{12000000,  11025,	7, 5264,	128,  32,  2,	128,  32,  2},
+	{12000000,  11025,	8, 4672,	128,  24,  3,	128,  24,  3},
+	{12500000,  11025,	7, 2253,	128,  32,  2,	128,  32,  2},
 	/* 16k rate */
-	{12000000,  16000,	1, 8, 1920,	128,  24,  2,	128,  24,  2},
-	{12000000,  16000,	1, 8, 1920,	128,  16,  3,	128,  16,  3},
-	{24000000,  16000,	2, 8, 1920,	128,  24,  2,	128,  24,  2},
-	{25000000,  16000,	2, 7, 8643,	128,  24,  2,	128,  24,  2},
+	{12000000,  16000,	8, 1920,	128,  24,  2,	128,  24,  2},
+	{12000000,  16000,	8, 1920,	128,  16,  3,	128,  16,  3},
+	{12500000,  16000,	7, 8643,	128,  24,  2,	128,  24,  2},
 	/* 22.05k rate */
-	{12000000,  22050,	1, 7, 5264,	128,  16,  2,	128,  16,  2},
-	{12000000,  22050,	1, 8, 4672,	128,  12,  3,	128,  12,  3},
-	{24000000,  22050,	2, 7, 5264,	128,  16,  2,	128,  16,  2},
-	{25000000,  22050,	2, 7, 2253,	128,  16,  2,	128,  16,  2},
+	{12000000,  22050,	7, 5264,	128,  16,  2,	128,  16,  2},
+	{12000000,  22050,	8, 4672,	128,  12,  3,	128,  12,  3},
+	{12500000,  22050,	7, 2253,	128,  16,  2,	128,  16,  2},
 	/* 32k rate */
-	{12000000,  32000,	1, 8, 1920,	128,  12,  2,	128,  12,  2},
-	{12000000,  32000,	1, 8, 1920,	128,   8,  3,	128,   8,  3},
-	{24000000,  32000,	2, 8, 1920,	128,  12,  2,	128,  12,  2},
-	{25000000,  32000,	2, 7, 8643,	128,  12,  2,	128,  12,  2},
+	{12000000,  32000,	8, 1920,	128,  12,  2,	128,  12,  2},
+	{12000000,  32000,	8, 1920,	128,   8,  3,	128,   8,  3},
+	{12500000,  32000,	7, 8643,	128,  12,  2,	128,  12,  2},
 	/* 44.1k rate */
-	{12000000,  44100,	1, 7, 5264,	128,   8,  2,	128,   8,  2},
-	{12000000,  44100,	1, 8, 4672,	128,   6,  3,	128,   6,  3},
-	{24000000,  44100,	2, 7, 5264,	128,   8,  2,	128,   8,  2},
-	{25000000,  44100,	2, 7, 2253,	128,   8,  2,	128,   8,  2},
+	{12000000,  44100,	7, 5264,	128,   8,  2,	128,   8,  2},
+	{12000000,  44100,	8, 4672,	128,   6,  3,	128,   6,  3},
+	{12500000,  44100,	7, 2253,	128,   8,  2,	128,   8,  2},
 	/* 48k rate */
-	{12000000,  48000,	1, 8, 1920,	128,   8,  2,	128,   8,  2},
-	{12000000,  48000,	1, 7, 6800,	 96,   5,  4,	 96,   5,  4},
-	{24000000,  48000,	2, 8, 1920,	128,   8,  2,	128,   8,  2},
-	{25000000,  48000,	2, 7, 8643,	128,   8,  2,	128,   8,  2},
+	{12000000,  48000,	8, 1920,	128,   8,  2,	128,   8,  2},
+	{12000000,  48000,	7, 6800,	 96,   5,  4,	 96,   5,  4},
+	{12500000,  48000,	7, 8643,	128,   8,  2,	128,   8,  2},
 	/* 88.2k rate */
-	{12000000,  88200,	1, 7, 5264,	 64,   8,  2,	 64,   8,  2},
-	{12000000,  88200,	1, 8, 4672,	 64,   6,  3,	 64,   6,  3},
-	{24000000,  88200,	2, 7, 5264,	 64,   8,  2,	 64,   8,  2},
-	{25000000,  88200,	2, 7, 2253,	 64,   8,  2,	 64,   8,  2},
+	{12000000,  88200,	7, 5264,	 64,   8,  2,	 64,   8,  2},
+	{12000000,  88200,	8, 4672,	 64,   6,  3,	 64,   6,  3},
+	{12500000,  88200,	7, 2253,	 64,   8,  2,	 64,   8,  2},
 	/* 96k rate */
-	{12000000,  96000,	1, 8, 1920,	 64,   8,  2,	 64,   8,  2},
-	{12000000,  96000,	1, 7, 6800,	 48,   5,  4,	 48,   5,  4},
-	{24000000,  96000,	2, 8, 1920,	 64,   8,  2,	 64,   8,  2},
-	{25000000,  96000,	2, 7, 8643,	 64,   8,  2,	 64,   8,  2},
+	{12000000,  96000,	8, 1920,	 64,   8,  2,	 64,   8,  2},
+	{12000000,  96000,	7, 6800,	 48,   5,  4,	 48,   5,  4},
+	{12500000,  96000,	7, 8643,	 64,   8,  2,	 64,   8,  2},
 	/* 176.4k rate */
-	{12000000, 176400,	1, 7, 5264,	 32,   8,  2,	 32,   8,  2},
-	{12000000, 176400,	1, 8, 4672,	 32,   6,  3,	 32,   6,  3},
-	{24000000, 176400,	2, 7, 5264,	 32,   8,  2,	 32,   8,  2},
-	{25000000, 176400,	2, 7, 2253,	 32,   8,  2,	 32,   8,  2},
+	{12000000, 176400,	7, 5264,	 32,   8,  2,	 32,   8,  2},
+	{12000000, 176400,	8, 4672,	 32,   6,  3,	 32,   6,  3},
+	{12500000, 176400,	7, 2253,	 32,   8,  2,	 32,   8,  2},
 	/* 192k rate */
-	{12000000, 192000,	1, 8, 1920,	 32,   8,  2,	 32,   8,  2},
-	{12000000, 192000,	1, 7, 6800,	 24,   5,  4,	 24,   5,  4},
-	{24000000, 192000,	2, 8, 1920,	 32,   8,  2,	 32,   8,  2},
-	{25000000, 192000,	2, 7, 8643,	 32,   8,  2,	 32,   8,  2},
+	{12000000, 192000,	8, 1920,	 32,   8,  2,	 32,   8,  2},
+	{12000000, 192000,	7, 6800,	 24,   5,  4,	 24,   5,  4},
+	{12500000, 192000,	7, 8643,	 32,   8,  2,	 32,   8,  2},
 };
 
 static const char * const ldac_in_text[] = {
@@ -692,6 +681,7 @@ static int aic31xx_setup_pll(struct snd_soc_codec *codec,
 {
 	struct aic31xx_priv *aic31xx = snd_soc_codec_get_drvdata(codec);
 	int bclk_score = snd_soc_params_to_frame_size(params);
+	int mclk_p = aic31xx->sysclk / aic31xx->p_div;
 	int bclk_n = 0;
 	int match = -1;
 	int i;
@@ -704,7 +694,7 @@ static int aic31xx_setup_pll(struct snd_soc_codec *codec,
 
 	for (i = 0; i < ARRAY_SIZE(aic31xx_divs); i++) {
 		if (aic31xx_divs[i].rate == params_rate(params) &&
-		    aic31xx_divs[i].mclk == aic31xx->sysclk) {
+		    aic31xx_divs[i].mclk_p == mclk_p) {
 			int s =	(aic31xx_divs[i].dosr * aic31xx_divs[i].mdac) %
 				snd_soc_params_to_frame_size(params);
 			int bn = (aic31xx_divs[i].dosr * aic31xx_divs[i].mdac) /
@@ -738,7 +728,7 @@ static int aic31xx_setup_pll(struct snd_soc_codec *codec,
 
 	/* PLL configuration */
 	snd_soc_update_bits(codec, AIC31XX_PLLPR, AIC31XX_PLL_MASK,
-			    (aic31xx_divs[i].p_val << 4) | 0x01);
+			    (aic31xx->p_div << 4) | 0x01);
 	snd_soc_write(codec, AIC31XX_PLLJ, aic31xx_divs[i].pll_j);
 
 	snd_soc_write(codec, AIC31XX_PLLDMSB,
@@ -772,7 +762,7 @@ static int aic31xx_setup_pll(struct snd_soc_codec *codec,
 	dev_dbg(codec->dev,
 		"pll %d.%04d/%d dosr %d n %d m %d aosr %d n %d m %d bclk_n %d\n",
 		aic31xx_divs[i].pll_j, aic31xx_divs[i].pll_d,
-		aic31xx_divs[i].p_val, aic31xx_divs[i].dosr,
+		aic31xx->p_div, aic31xx_divs[i].dosr,
 		aic31xx_divs[i].ndac, aic31xx_divs[i].mdac,
 		aic31xx_divs[i].aosr, aic31xx_divs[i].nadc,
 		aic31xx_divs[i].madc, bclk_n);
@@ -840,7 +830,7 @@ static int aic31xx_set_dai_fmt(struct snd_soc_dai *codec_dai,
 {
 	struct snd_soc_codec *codec = codec_dai->codec;
 	u8 iface_reg1 = 0;
-	u8 iface_reg3 = 0;
+	u8 iface_reg2 = 0;
 	u8 dsp_a_val = 0;
 
 	dev_dbg(codec->dev, "## %s: fmt = 0x%x\n", __func__, fmt);
@@ -865,7 +855,7 @@ static int aic31xx_set_dai_fmt(struct snd_soc_dai *codec_dai,
 		/* NOTE: BCLKINV bit value 1 equas NB and 0 equals IB */
 		switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
 		case SND_SOC_DAIFMT_NB_NF:
-			iface_reg3 |= AIC31XX_BCLKINV_MASK;
+			iface_reg2 |= AIC31XX_BCLKINV_MASK;
 			break;
 		case SND_SOC_DAIFMT_IB_NF:
 			break;
@@ -897,7 +887,7 @@ static int aic31xx_set_dai_fmt(struct snd_soc_dai *codec_dai,
 			    dsp_a_val);
 	snd_soc_update_bits(codec, AIC31XX_IFACE2,
 			    AIC31XX_BCLKINV_MASK,
-			    iface_reg3);
+			    iface_reg2);
 
 	return 0;
 }
@@ -912,7 +902,16 @@ static int aic31xx_set_dai_sysclk(struct snd_soc_dai *codec_dai,
 	dev_dbg(codec->dev, "## %s: clk_id = %d, freq = %d, dir = %d\n",
 		__func__, clk_id, freq, dir);
 
-	for (i = 0; aic31xx_divs[i].mclk != freq; i++) {
+	for (i = 1; freq/i > 20000000 && i < 8; i++)
+		;
+	if (freq/i > 20000000) {
+		dev_err(aic31xx->dev, "%s: Too high mclk frequency %u\n",
+			__func__, freq);
+			return -EINVAL;
+	}
+	aic31xx->p_div = i;
+
+	for (i = 0; aic31xx_divs[i].mclk_p != freq/aic31xx->p_div; i++) {
 		if (i == ARRAY_SIZE(aic31xx_divs)) {
 			dev_err(aic31xx->dev, "%s: Unsupported frequency %d\n",
 				__func__, freq);
diff --git a/sound/soc/codecs/tlv320aic31xx.h b/sound/soc/codecs/tlv320aic31xx.h
index 52ed57c69dfa..fe16c34607bb 100644
--- a/sound/soc/codecs/tlv320aic31xx.h
+++ b/sound/soc/codecs/tlv320aic31xx.h
@@ -18,7 +18,8 @@
 #define AIC31XX_RATES	SNDRV_PCM_RATE_8000_192000
 
 #define AIC31XX_FORMATS	(SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE \
-			 | SNDRV_PCM_FMTBIT_S24_3LE | SNDRV_PCM_FMTBIT_S32_LE)
+			 | SNDRV_PCM_FMTBIT_S24_3LE | SNDRV_PCM_FMTBIT_S24_LE \
+			 | SNDRV_PCM_FMTBIT_S32_LE)
 
 
 #define AIC31XX_STEREO_CLASS_D_BIT	0x1
diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c
index 64f179ee9834..f7c2a575a892 100644
--- a/sound/soc/codecs/tlv320aic3x.c
+++ b/sound/soc/codecs/tlv320aic3x.c
@@ -1121,6 +1121,7 @@ static int aic3x_regulator_event(struct notifier_block *nb,
 static int aic3x_set_power(struct snd_soc_codec *codec, int power)
 {
 	struct aic3x_priv *aic3x = snd_soc_codec_get_drvdata(codec);
+	unsigned int pll_c, pll_d;
 	int ret;
 
 	if (power) {
@@ -1138,6 +1139,18 @@ static int aic3x_set_power(struct snd_soc_codec *codec, int power)
 		/* Sync reg_cache with the hardware */
 		regcache_cache_only(aic3x->regmap, false);
 		regcache_sync(aic3x->regmap);
+
+		/* Rewrite paired PLL D registers in case cached sync skipped
+		 * writing one of them and thus caused other one also not
+		 * being written
+		 */
+		pll_c = snd_soc_read(codec, AIC3X_PLL_PROGC_REG);
+		pll_d = snd_soc_read(codec, AIC3X_PLL_PROGD_REG);
+		if (pll_c == aic3x_reg[AIC3X_PLL_PROGC_REG].def ||
+			pll_d == aic3x_reg[AIC3X_PLL_PROGD_REG].def) {
+			snd_soc_write(codec, AIC3X_PLL_PROGC_REG, pll_c);
+			snd_soc_write(codec, AIC3X_PLL_PROGD_REG, pll_d);
+		}
 	} else {
 		/*
 		 * Do soft reset to this codec instance in order to clear
@@ -1222,20 +1235,6 @@ static struct snd_soc_dai_driver aic3x_dai = {
 	.symmetric_rates = 1,
 };
 
-static int aic3x_suspend(struct snd_soc_codec *codec)
-{
-	aic3x_set_bias_level(codec, SND_SOC_BIAS_OFF);
-
-	return 0;
-}
-
-static int aic3x_resume(struct snd_soc_codec *codec)
-{
-	aic3x_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-
-	return 0;
-}
-
 static void aic3x_mono_init(struct snd_soc_codec *codec)
 {
 	/* DAC to Mono Line Out default volume and route to Output mixer */
@@ -1429,8 +1428,6 @@ static struct snd_soc_codec_driver soc_codec_dev_aic3x = {
 	.idle_bias_off = true,
 	.probe = aic3x_probe,
 	.remove = aic3x_remove,
-	.suspend = aic3x_suspend,
-	.resume = aic3x_resume,
 	.controls = aic3x_snd_controls,
 	.num_controls = ARRAY_SIZE(aic3x_snd_controls),
 	.dapm_widgets = aic3x_dapm_widgets,
diff --git a/sound/soc/codecs/wm5100.c b/sound/soc/codecs/wm5100.c
index 7bb0d36d4c54..a01ad629ed61 100644
--- a/sound/soc/codecs/wm5100.c
+++ b/sound/soc/codecs/wm5100.c
@@ -2319,11 +2319,8 @@ static void wm5100_init_gpio(struct i2c_client *i2c)
 static void wm5100_free_gpio(struct i2c_client *i2c)
 {
 	struct wm5100_priv *wm5100 = i2c_get_clientdata(i2c);
-	int ret;
 
-	ret = gpiochip_remove(&wm5100->gpio_chip);
-	if (ret != 0)
-		dev_err(&i2c->dev, "Failed to remove GPIOs: %d\n", ret);
+	gpiochip_remove(&wm5100->gpio_chip);
 }
 #else
 static void wm5100_init_gpio(struct i2c_client *i2c)
diff --git a/sound/soc/codecs/wm8350.c b/sound/soc/codecs/wm8350.c
index 3dfdcc4197fa..628ec774cf22 100644
--- a/sound/soc/codecs/wm8350.c
+++ b/sound/soc/codecs/wm8350.c
@@ -212,7 +212,7 @@ static void wm8350_pga_work(struct work_struct *work)
 {
 	struct snd_soc_dapm_context *dapm =
 	    container_of(work, struct snd_soc_dapm_context, delayed_work.work);
-	struct snd_soc_codec *codec = dapm->codec;
+	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(dapm);
 	struct wm8350_data *wm8350_data = snd_soc_codec_get_drvdata(codec);
 	struct wm8350_output *out1 = &wm8350_data->out1,
 	    *out2 = &wm8350_data->out2;
diff --git a/sound/soc/codecs/wm8741.c b/sound/soc/codecs/wm8741.c
index a237f1627f61..31bb4801a005 100644
--- a/sound/soc/codecs/wm8741.c
+++ b/sound/soc/codecs/wm8741.c
@@ -413,7 +413,6 @@ static int wm8741_resume(struct snd_soc_codec *codec)
 	return 0;
 }
 #else
-#define wm8741_suspend NULL
 #define wm8741_resume NULL
 #endif
 
diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c
index e54e097f4fcb..21ca3a94fc96 100644
--- a/sound/soc/codecs/wm8753.c
+++ b/sound/soc/codecs/wm8753.c
@@ -1433,7 +1433,7 @@ static void wm8753_work(struct work_struct *work)
 	struct snd_soc_dapm_context *dapm =
 		container_of(work, struct snd_soc_dapm_context,
 			     delayed_work.work);
-	struct snd_soc_codec *codec = dapm->codec;
+	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(dapm);
 	wm8753_set_bias_level(codec, dapm->bias_level);
 }
 
diff --git a/sound/soc/codecs/wm8804.c b/sound/soc/codecs/wm8804.c
index 0ea01dfcb6e1..3addc5fe5cb2 100644
--- a/sound/soc/codecs/wm8804.c
+++ b/sound/soc/codecs/wm8804.c
@@ -518,23 +518,6 @@ static int wm8804_set_bias_level(struct snd_soc_codec *codec,
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int wm8804_suspend(struct snd_soc_codec *codec)
-{
-	wm8804_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	return 0;
-}
-
-static int wm8804_resume(struct snd_soc_codec *codec)
-{
-	wm8804_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-	return 0;
-}
-#else
-#define wm8804_suspend NULL
-#define wm8804_resume NULL
-#endif
-
 static int wm8804_remove(struct snd_soc_codec *codec)
 {
 	struct wm8804_priv *wm8804;
@@ -671,8 +654,6 @@ static struct snd_soc_dai_driver wm8804_dai = {
 static struct snd_soc_codec_driver soc_codec_dev_wm8804 = {
 	.probe = wm8804_probe,
 	.remove = wm8804_remove,
-	.suspend = wm8804_suspend,
-	.resume = wm8804_resume,
 	.set_bias_level = wm8804_set_bias_level,
 	.idle_bias_off = true,
 
diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c
index aa0984864e76..c038b3e04398 100644
--- a/sound/soc/codecs/wm8903.c
+++ b/sound/soc/codecs/wm8903.c
@@ -1877,11 +1877,7 @@ static void wm8903_init_gpio(struct wm8903_priv *wm8903)
 
 static void wm8903_free_gpio(struct wm8903_priv *wm8903)
 {
-	int ret;
-
-	ret = gpiochip_remove(&wm8903->gpio_chip);
-	if (ret != 0)
-		dev_err(wm8903->dev, "Failed to remove GPIOs: %d\n", ret);
+	gpiochip_remove(&wm8903->gpio_chip);
 }
 #else
 static void wm8903_init_gpio(struct wm8903_priv *wm8903)
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index 1098ae32f1f9..9077411e62ce 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -3398,11 +3398,8 @@ static void wm8962_init_gpio(struct snd_soc_codec *codec)
 static void wm8962_free_gpio(struct snd_soc_codec *codec)
 {
 	struct wm8962_priv *wm8962 = snd_soc_codec_get_drvdata(codec);
-	int ret;
 
-	ret = gpiochip_remove(&wm8962->gpio_chip);
-	if (ret != 0)
-		dev_err(codec->dev, "Failed to remove GPIOs: %d\n", ret);
+	gpiochip_remove(&wm8962->gpio_chip);
 }
 #else
 static void wm8962_init_gpio(struct snd_soc_codec *codec)
diff --git a/sound/soc/codecs/wm8971.c b/sound/soc/codecs/wm8971.c
index 0499cd4cfb71..39ddb9b8834c 100644
--- a/sound/soc/codecs/wm8971.c
+++ b/sound/soc/codecs/wm8971.c
@@ -615,7 +615,7 @@ static void wm8971_work(struct work_struct *work)
 	struct snd_soc_dapm_context *dapm =
 		container_of(work, struct snd_soc_dapm_context,
 			     delayed_work.work);
-	struct snd_soc_codec *codec = dapm->codec;
+	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(dapm);
 	wm8971_set_bias_level(codec, codec->dapm.bias_level);
 }
 
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index 6cc0566dc29a..1fcb9f3f3097 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -4082,17 +4082,23 @@ static int wm8994_codec_probe(struct snd_soc_codec *codec)
 
 	switch (control->type) {
 	case WM8994:
-		if (wm8994->micdet_irq) {
+		if (wm8994->micdet_irq)
 			ret = request_threaded_irq(wm8994->micdet_irq, NULL,
 						   wm8994_mic_irq,
 						   IRQF_TRIGGER_RISING,
 						   "Mic1 detect",
 						   wm8994);
-			if (ret != 0)
-				dev_warn(codec->dev,
-					 "Failed to request Mic1 detect IRQ: %d\n",
-					 ret);
-		}
+		 else
+			ret = wm8994_request_irq(wm8994->wm8994,
+					WM8994_IRQ_MIC1_DET,
+					wm8994_mic_irq, "Mic 1 detect",
+					wm8994);
+
+		if (ret != 0)
+			dev_warn(codec->dev,
+				 "Failed to request Mic1 detect IRQ: %d\n",
+				 ret);
+
 
 		ret = wm8994_request_irq(wm8994->wm8994,
 					 WM8994_IRQ_MIC1_SHRT,
diff --git a/sound/soc/codecs/wm8995.c b/sound/soc/codecs/wm8995.c
index cae4ac5a5730..1288edeb8c7d 100644
--- a/sound/soc/codecs/wm8995.c
+++ b/sound/soc/codecs/wm8995.c
@@ -1998,23 +1998,6 @@ static int wm8995_set_bias_level(struct snd_soc_codec *codec,
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int wm8995_suspend(struct snd_soc_codec *codec)
-{
-	wm8995_set_bias_level(codec, SND_SOC_BIAS_OFF);
-	return 0;
-}
-
-static int wm8995_resume(struct snd_soc_codec *codec)
-{
-	wm8995_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
-	return 0;
-}
-#else
-#define wm8995_suspend NULL
-#define wm8995_resume NULL
-#endif
-
 static int wm8995_remove(struct snd_soc_codec *codec)
 {
 	struct wm8995_priv *wm8995;
@@ -2220,8 +2203,6 @@ static struct snd_soc_dai_driver wm8995_dai[] = {
 static struct snd_soc_codec_driver soc_codec_dev_wm8995 = {
 	.probe = wm8995_probe,
 	.remove = wm8995_remove,
-	.suspend = wm8995_suspend,
-	.resume = wm8995_resume,
 	.set_bias_level = wm8995_set_bias_level,
 	.idle_bias_off = true,
 };
diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c
index f16ff4f56923..b1dcc11c1b23 100644
--- a/sound/soc/codecs/wm8996.c
+++ b/sound/soc/codecs/wm8996.c
@@ -2216,11 +2216,7 @@ static void wm8996_init_gpio(struct wm8996_priv *wm8996)
 
 static void wm8996_free_gpio(struct wm8996_priv *wm8996)
 {
-	int ret;
-
-	ret = gpiochip_remove(&wm8996->gpio_chip);
-	if (ret != 0)
-		dev_err(wm8996->dev, "Failed to remove GPIOs: %d\n", ret);
+	gpiochip_remove(&wm8996->gpio_chip);
 }
 #else
 static void wm8996_init_gpio(struct wm8996_priv *wm8996)
diff --git a/sound/soc/davinci/Kconfig b/sound/soc/davinci/Kconfig
index d69510c53239..8e948c63f3d9 100644
--- a/sound/soc/davinci/Kconfig
+++ b/sound/soc/davinci/Kconfig
@@ -63,7 +63,8 @@ config SND_DM365_AIC3X_CODEC
 	  Say Y if you want to add support for AIC3101 audio codec
 
 config SND_DM365_VOICE_CODEC
-	bool "Voice Codec - CQ93VC"
+	tristate "Voice Codec - CQ93VC"
+	depends on SND_DAVINCI_SOC
 	select MFD_DAVINCI_VOICECODEC
 	select SND_DAVINCI_SOC_VCIF
 	select SND_SOC_CQ0093VC
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 68347b55f6e1..0eed9b1b24e1 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -42,14 +42,26 @@
 
 #define MCASP_MAX_AFIFO_DEPTH	64
 
+static u32 context_regs[] = {
+	DAVINCI_MCASP_TXFMCTL_REG,
+	DAVINCI_MCASP_RXFMCTL_REG,
+	DAVINCI_MCASP_TXFMT_REG,
+	DAVINCI_MCASP_RXFMT_REG,
+	DAVINCI_MCASP_ACLKXCTL_REG,
+	DAVINCI_MCASP_ACLKRCTL_REG,
+	DAVINCI_MCASP_AHCLKXCTL_REG,
+	DAVINCI_MCASP_AHCLKRCTL_REG,
+	DAVINCI_MCASP_PDIR_REG,
+	DAVINCI_MCASP_RXMASK_REG,
+	DAVINCI_MCASP_TXMASK_REG,
+	DAVINCI_MCASP_RXTDM_REG,
+	DAVINCI_MCASP_TXTDM_REG,
+};
+
 struct davinci_mcasp_context {
-	u32	txfmtctl;
-	u32	rxfmtctl;
-	u32	txfmt;
-	u32	rxfmt;
-	u32	aclkxctl;
-	u32	aclkrctl;
-	u32	pdir;
+	u32	config_regs[ARRAY_SIZE(context_regs)];
+	u32	afifo_regs[2]; /* for read/write fifo control registers */
+	u32	*xrsr_regs; /* for serializer configuration */
 };
 
 struct davinci_mcasp {
@@ -874,14 +886,24 @@ static int davinci_mcasp_suspend(struct snd_soc_dai *dai)
 {
 	struct davinci_mcasp *mcasp = snd_soc_dai_get_drvdata(dai);
 	struct davinci_mcasp_context *context = &mcasp->context;
+	u32 reg;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(context_regs); i++)
+		context->config_regs[i] = mcasp_get_reg(mcasp, context_regs[i]);
+
+	if (mcasp->txnumevt) {
+		reg = mcasp->fifo_base + MCASP_WFIFOCTL_OFFSET;
+		context->afifo_regs[0] = mcasp_get_reg(mcasp, reg);
+	}
+	if (mcasp->rxnumevt) {
+		reg = mcasp->fifo_base + MCASP_RFIFOCTL_OFFSET;
+		context->afifo_regs[1] = mcasp_get_reg(mcasp, reg);
+	}
 
-	context->txfmtctl = mcasp_get_reg(mcasp, DAVINCI_MCASP_TXFMCTL_REG);
-	context->rxfmtctl = mcasp_get_reg(mcasp, DAVINCI_MCASP_RXFMCTL_REG);
-	context->txfmt = mcasp_get_reg(mcasp, DAVINCI_MCASP_TXFMT_REG);
-	context->rxfmt = mcasp_get_reg(mcasp, DAVINCI_MCASP_RXFMT_REG);
-	context->aclkxctl = mcasp_get_reg(mcasp, DAVINCI_MCASP_ACLKXCTL_REG);
-	context->aclkrctl = mcasp_get_reg(mcasp, DAVINCI_MCASP_ACLKRCTL_REG);
-	context->pdir = mcasp_get_reg(mcasp, DAVINCI_MCASP_PDIR_REG);
+	for (i = 0; i < mcasp->num_serializer; i++)
+		context->xrsr_regs[i] = mcasp_get_reg(mcasp,
+						DAVINCI_MCASP_XRSRCTL_REG(i));
 
 	return 0;
 }
@@ -890,14 +912,24 @@ static int davinci_mcasp_resume(struct snd_soc_dai *dai)
 {
 	struct davinci_mcasp *mcasp = snd_soc_dai_get_drvdata(dai);
 	struct davinci_mcasp_context *context = &mcasp->context;
+	u32 reg;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(context_regs); i++)
+		mcasp_set_reg(mcasp, context_regs[i], context->config_regs[i]);
+
+	if (mcasp->txnumevt) {
+		reg = mcasp->fifo_base + MCASP_WFIFOCTL_OFFSET;
+		mcasp_set_reg(mcasp, reg, context->afifo_regs[0]);
+	}
+	if (mcasp->rxnumevt) {
+		reg = mcasp->fifo_base + MCASP_RFIFOCTL_OFFSET;
+		mcasp_set_reg(mcasp, reg, context->afifo_regs[1]);
+	}
 
-	mcasp_set_reg(mcasp, DAVINCI_MCASP_TXFMCTL_REG, context->txfmtctl);
-	mcasp_set_reg(mcasp, DAVINCI_MCASP_RXFMCTL_REG, context->rxfmtctl);
-	mcasp_set_reg(mcasp, DAVINCI_MCASP_TXFMT_REG, context->txfmt);
-	mcasp_set_reg(mcasp, DAVINCI_MCASP_RXFMT_REG, context->rxfmt);
-	mcasp_set_reg(mcasp, DAVINCI_MCASP_ACLKXCTL_REG, context->aclkxctl);
-	mcasp_set_reg(mcasp, DAVINCI_MCASP_ACLKRCTL_REG, context->aclkrctl);
-	mcasp_set_reg(mcasp, DAVINCI_MCASP_PDIR_REG, context->pdir);
+	for (i = 0; i < mcasp->num_serializer; i++)
+		mcasp_set_reg(mcasp, DAVINCI_MCASP_XRSRCTL_REG(i),
+			      context->xrsr_regs[i]);
 
 	return 0;
 }
@@ -1216,6 +1248,11 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 	mcasp->op_mode = pdata->op_mode;
 	mcasp->tdm_slots = pdata->tdm_slots;
 	mcasp->num_serializer = pdata->num_serializer;
+#ifdef CONFIG_PM_SLEEP
+	mcasp->context.xrsr_regs = devm_kzalloc(&pdev->dev,
+					sizeof(u32) * mcasp->num_serializer,
+					GFP_KERNEL);
+#endif
 	mcasp->serial_dir = pdata->serial_dir;
 	mcasp->version = pdata->version;
 	mcasp->txnumevt = pdata->txnumevt;
diff --git a/sound/soc/davinci/edma-pcm.c b/sound/soc/davinci/edma-pcm.c
index 605e643133db..59e588abe54b 100644
--- a/sound/soc/davinci/edma-pcm.c
+++ b/sound/soc/davinci/edma-pcm.c
@@ -25,6 +25,8 @@
 #include <sound/dmaengine_pcm.h>
 #include <linux/edma.h>
 
+#include "edma-pcm.h"
+
 static const struct snd_pcm_hardware edma_pcm_hardware = {
 	.info			= SNDRV_PCM_INFO_MMAP |
 				  SNDRV_PCM_INFO_MMAP_VALID |
diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig
index f3012b645b51..081e406b3713 100644
--- a/sound/soc/fsl/Kconfig
+++ b/sound/soc/fsl/Kconfig
@@ -240,6 +240,18 @@ config SND_SOC_IMX_WM8962
 	  Say Y if you want to add support for SoC audio on an i.MX board with
 	  a wm8962 codec.
 
+config SND_SOC_IMX_ES8328
+	tristate "SoC Audio support for i.MX boards with the ES8328 codec"
+	depends on OF && (I2C || SPI)
+	select SND_SOC_ES8328_I2C if I2C
+	select SND_SOC_ES8328_SPI if SPI_MASTER
+	select SND_SOC_IMX_PCM_DMA
+	select SND_SOC_IMX_AUDMUX
+	select SND_SOC_FSL_SSI
+	help
+	  Say Y if you want to add support for the ES8328 audio codec connected
+	  via SSI/I2S over either SPI or I2C.
+
 config SND_SOC_IMX_SGTL5000
 	tristate "SoC Audio support for i.MX boards with sgtl5000"
 	depends on OF && I2C
@@ -268,6 +280,20 @@ config SND_SOC_IMX_MC13783
 	select SND_SOC_MC13783
 	select SND_SOC_IMX_PCM_DMA
 
+config SND_SOC_FSL_ASOC_CARD
+	tristate "Generic ASoC Sound Card with ASRC support"
+	depends on OF && I2C
+	select SND_SOC_IMX_AUDMUX
+	select SND_SOC_IMX_PCM_DMA
+	select SND_SOC_FSL_ESAI
+	select SND_SOC_FSL_SAI
+	select SND_SOC_FSL_SSI
+	help
+	 ALSA SoC Audio support with ASRC feature for Freescale SoCs that have
+	 ESAI/SAI/SSI and connect with external CODECs such as WM8962, CS42888
+	 and SGTL5000.
+	 Say Y if you want to add support for Freescale Generic ASoC Sound Card.
+
 endif # SND_IMX_SOC
 
 endmenu
diff --git a/sound/soc/fsl/Makefile b/sound/soc/fsl/Makefile
index 9ff59267eac9..d28dc25c9375 100644
--- a/sound/soc/fsl/Makefile
+++ b/sound/soc/fsl/Makefile
@@ -11,6 +11,7 @@ snd-soc-p1022-rdk-objs := p1022_rdk.o
 obj-$(CONFIG_SND_SOC_P1022_RDK) += snd-soc-p1022-rdk.o
 
 # Freescale SSI/DMA/SAI/SPDIF Support
+snd-soc-fsl-asoc-card-objs := fsl-asoc-card.o
 snd-soc-fsl-asrc-objs := fsl_asrc.o fsl_asrc_dma.o
 snd-soc-fsl-sai-objs := fsl_sai.o
 snd-soc-fsl-ssi-y := fsl_ssi.o
@@ -19,6 +20,7 @@ snd-soc-fsl-spdif-objs := fsl_spdif.o
 snd-soc-fsl-esai-objs := fsl_esai.o
 snd-soc-fsl-utils-objs := fsl_utils.o
 snd-soc-fsl-dma-objs := fsl_dma.o
+obj-$(CONFIG_SND_SOC_FSL_ASOC_CARD) += snd-soc-fsl-asoc-card.o
 obj-$(CONFIG_SND_SOC_FSL_ASRC) += snd-soc-fsl-asrc.o
 obj-$(CONFIG_SND_SOC_FSL_SAI) += snd-soc-fsl-sai.o
 obj-$(CONFIG_SND_SOC_FSL_SSI) += snd-soc-fsl-ssi.o
@@ -50,6 +52,7 @@ snd-soc-eukrea-tlv320-objs := eukrea-tlv320.o
 snd-soc-phycore-ac97-objs := phycore-ac97.o
 snd-soc-mx27vis-aic32x4-objs := mx27vis-aic32x4.o
 snd-soc-wm1133-ev1-objs := wm1133-ev1.o
+snd-soc-imx-es8328-objs := imx-es8328.o
 snd-soc-imx-sgtl5000-objs := imx-sgtl5000.o
 snd-soc-imx-wm8962-objs := imx-wm8962.o
 snd-soc-imx-spdif-objs := imx-spdif.o
@@ -59,6 +62,7 @@ obj-$(CONFIG_SND_SOC_EUKREA_TLV320) += snd-soc-eukrea-tlv320.o
 obj-$(CONFIG_SND_SOC_PHYCORE_AC97) += snd-soc-phycore-ac97.o
 obj-$(CONFIG_SND_SOC_MX27VIS_AIC32X4) += snd-soc-mx27vis-aic32x4.o
 obj-$(CONFIG_SND_MXC_SOC_WM1133_EV1) += snd-soc-wm1133-ev1.o
+obj-$(CONFIG_SND_SOC_IMX_ES8328) += snd-soc-imx-es8328.o
 obj-$(CONFIG_SND_SOC_IMX_SGTL5000) += snd-soc-imx-sgtl5000.o
 obj-$(CONFIG_SND_SOC_IMX_WM8962) += snd-soc-imx-wm8962.o
 obj-$(CONFIG_SND_SOC_IMX_SPDIF) += snd-soc-imx-spdif.o
diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
new file mode 100644
index 000000000000..007c772f3cef
--- /dev/null
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -0,0 +1,574 @@
+/*
+ * Freescale Generic ASoC Sound Card driver with ASRC
+ *
+ * Copyright (C) 2014 Freescale Semiconductor, Inc.
+ *
+ * Author: Nicolin Chen <nicoleotsuka@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#include <linux/clk.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+
+#include "fsl_esai.h"
+#include "fsl_sai.h"
+#include "imx-audmux.h"
+
+#include "../codecs/sgtl5000.h"
+#include "../codecs/wm8962.h"
+
+#define RX 0
+#define TX 1
+
+/* Default DAI format without Master and Slave flag */
+#define DAI_FMT_BASE (SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF)
+
+/**
+ * CODEC private data
+ *
+ * @mclk_freq: Clock rate of MCLK
+ * @mclk_id: MCLK (or main clock) id for set_sysclk()
+ * @fll_id: FLL (or secordary clock) id for set_sysclk()
+ * @pll_id: PLL id for set_pll()
+ */
+struct codec_priv {
+	unsigned long mclk_freq;
+	u32 mclk_id;
+	u32 fll_id;
+	u32 pll_id;
+};
+
+/**
+ * CPU private data
+ *
+ * @sysclk_freq[2]: SYSCLK rates for set_sysclk()
+ * @sysclk_dir[2]: SYSCLK directions for set_sysclk()
+ * @sysclk_id[2]: SYSCLK ids for set_sysclk()
+ *
+ * Note: [1] for tx and [0] for rx
+ */
+struct cpu_priv {
+	unsigned long sysclk_freq[2];
+	u32 sysclk_dir[2];
+	u32 sysclk_id[2];
+};
+
+/**
+ * Freescale Generic ASOC card private data
+ *
+ * @dai_link[3]: DAI link structure including normal one and DPCM link
+ * @pdev: platform device pointer
+ * @codec_priv: CODEC private data
+ * @cpu_priv: CPU private data
+ * @card: ASoC card structure
+ * @sample_rate: Current sample rate
+ * @sample_format: Current sample format
+ * @asrc_rate: ASRC sample rate used by Back-Ends
+ * @asrc_format: ASRC sample format used by Back-Ends
+ * @dai_fmt: DAI format between CPU and CODEC
+ * @name: Card name
+ */
+
+struct fsl_asoc_card_priv {
+	struct snd_soc_dai_link dai_link[3];
+	struct platform_device *pdev;
+	struct codec_priv codec_priv;
+	struct cpu_priv cpu_priv;
+	struct snd_soc_card card;
+	u32 sample_rate;
+	u32 sample_format;
+	u32 asrc_rate;
+	u32 asrc_format;
+	u32 dai_fmt;
+	char name[32];
+};
+
+/**
+ * This dapm route map exsits for DPCM link only.
+ * The other routes shall go through Device Tree.
+ */
+static const struct snd_soc_dapm_route audio_map[] = {
+	{"CPU-Playback",  NULL, "ASRC-Playback"},
+	{"Playback",  NULL, "CPU-Playback"},
+	{"ASRC-Capture",  NULL, "CPU-Capture"},
+	{"CPU-Capture",  NULL, "Capture"},
+};
+
+/* Add all possible widgets into here without being redundant */
+static const struct snd_soc_dapm_widget fsl_asoc_card_dapm_widgets[] = {
+	SND_SOC_DAPM_LINE("Line Out Jack", NULL),
+	SND_SOC_DAPM_LINE("Line In Jack", NULL),
+	SND_SOC_DAPM_HP("Headphone Jack", NULL),
+	SND_SOC_DAPM_SPK("Ext Spk", NULL),
+	SND_SOC_DAPM_MIC("Mic Jack", NULL),
+	SND_SOC_DAPM_MIC("AMIC", NULL),
+	SND_SOC_DAPM_MIC("DMIC", NULL),
+};
+
+static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream,
+				   struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(rtd->card);
+	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
+	struct cpu_priv *cpu_priv = &priv->cpu_priv;
+	struct device *dev = rtd->card->dev;
+	int ret;
+
+	priv->sample_rate = params_rate(params);
+	priv->sample_format = params_format(params);
+
+	if (priv->card.set_bias_level)
+		return 0;
+
+	/* Specific configurations of DAIs starts from here */
+	ret = snd_soc_dai_set_sysclk(rtd->cpu_dai, cpu_priv->sysclk_id[tx],
+				     cpu_priv->sysclk_freq[tx],
+				     cpu_priv->sysclk_dir[tx]);
+	if (ret) {
+		dev_err(dev, "failed to set sysclk for cpu dai\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static struct snd_soc_ops fsl_asoc_card_ops = {
+	.hw_params = fsl_asoc_card_hw_params,
+};
+
+static int be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
+			      struct snd_pcm_hw_params *params)
+{
+	struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(rtd->card);
+	struct snd_interval *rate;
+	struct snd_mask *mask;
+
+	rate = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE);
+	rate->max = rate->min = priv->asrc_rate;
+
+	mask = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
+	snd_mask_none(mask);
+	snd_mask_set(mask, priv->asrc_format);
+
+	return 0;
+}
+
+static struct snd_soc_dai_link fsl_asoc_card_dai[] = {
+	/* Default ASoC DAI Link*/
+	{
+		.name = "HiFi",
+		.stream_name = "HiFi",
+		.ops = &fsl_asoc_card_ops,
+	},
+	/* DPCM Link between Front-End and Back-End (Optional) */
+	{
+		.name = "HiFi-ASRC-FE",
+		.stream_name = "HiFi-ASRC-FE",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+		.dynamic = 1,
+	},
+	{
+		.name = "HiFi-ASRC-BE",
+		.stream_name = "HiFi-ASRC-BE",
+		.platform_name = "snd-soc-dummy",
+		.be_hw_params_fixup = be_hw_params_fixup,
+		.ops = &fsl_asoc_card_ops,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+		.no_pcm = 1,
+	},
+};
+
+static int fsl_asoc_card_set_bias_level(struct snd_soc_card *card,
+					struct snd_soc_dapm_context *dapm,
+					enum snd_soc_bias_level level)
+{
+	struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(card);
+	struct snd_soc_dai *codec_dai = card->rtd[0].codec_dai;
+	struct codec_priv *codec_priv = &priv->codec_priv;
+	struct device *dev = card->dev;
+	unsigned int pll_out;
+	int ret;
+
+	if (dapm->dev != codec_dai->dev)
+		return 0;
+
+	switch (level) {
+	case SND_SOC_BIAS_PREPARE:
+		if (dapm->bias_level != SND_SOC_BIAS_STANDBY)
+			break;
+
+		if (priv->sample_format == SNDRV_PCM_FORMAT_S24_LE)
+			pll_out = priv->sample_rate * 384;
+		else
+			pll_out = priv->sample_rate * 256;
+
+		ret = snd_soc_dai_set_pll(codec_dai, codec_priv->pll_id,
+					  codec_priv->mclk_id,
+					  codec_priv->mclk_freq, pll_out);
+		if (ret) {
+			dev_err(dev, "failed to start FLL: %d\n", ret);
+			return ret;
+		}
+
+		ret = snd_soc_dai_set_sysclk(codec_dai, codec_priv->fll_id,
+					     pll_out, SND_SOC_CLOCK_IN);
+		if (ret) {
+			dev_err(dev, "failed to set SYSCLK: %d\n", ret);
+			return ret;
+		}
+		break;
+
+	case SND_SOC_BIAS_STANDBY:
+		if (dapm->bias_level != SND_SOC_BIAS_PREPARE)
+			break;
+
+		ret = snd_soc_dai_set_sysclk(codec_dai, codec_priv->mclk_id,
+					     codec_priv->mclk_freq,
+					     SND_SOC_CLOCK_IN);
+		if (ret) {
+			dev_err(dev, "failed to switch away from FLL: %d\n", ret);
+			return ret;
+		}
+
+		ret = snd_soc_dai_set_pll(codec_dai, codec_priv->pll_id, 0, 0, 0);
+		if (ret) {
+			dev_err(dev, "failed to stop FLL: %d\n", ret);
+			return ret;
+		}
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int fsl_asoc_card_audmux_init(struct device_node *np,
+				     struct fsl_asoc_card_priv *priv)
+{
+	struct device *dev = &priv->pdev->dev;
+	u32 int_ptcr = 0, ext_ptcr = 0;
+	int int_port, ext_port;
+	int ret;
+
+	ret = of_property_read_u32(np, "mux-int-port", &int_port);
+	if (ret) {
+		dev_err(dev, "mux-int-port missing or invalid\n");
+		return ret;
+	}
+	ret = of_property_read_u32(np, "mux-ext-port", &ext_port);
+	if (ret) {
+		dev_err(dev, "mux-ext-port missing or invalid\n");
+		return ret;
+	}
+
+	/*
+	 * The port numbering in the hardware manual starts at 1, while
+	 * the AUDMUX API expects it starts at 0.
+	 */
+	int_port--;
+	ext_port--;
+
+	/*
+	 * Use asynchronous mode (6 wires) for all cases.
+	 * If only 4 wires are needed, just set SSI into
+	 * synchronous mode and enable 4 PADs in IOMUX.
+	 */
+	switch (priv->dai_fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		int_ptcr = IMX_AUDMUX_V2_PTCR_RFSEL(8 | ext_port) |
+			   IMX_AUDMUX_V2_PTCR_RCSEL(8 | ext_port) |
+			   IMX_AUDMUX_V2_PTCR_TFSEL(ext_port) |
+			   IMX_AUDMUX_V2_PTCR_TCSEL(ext_port) |
+			   IMX_AUDMUX_V2_PTCR_RFSDIR |
+			   IMX_AUDMUX_V2_PTCR_RCLKDIR |
+			   IMX_AUDMUX_V2_PTCR_TFSDIR |
+			   IMX_AUDMUX_V2_PTCR_TCLKDIR;
+		break;
+	case SND_SOC_DAIFMT_CBM_CFS:
+		int_ptcr = IMX_AUDMUX_V2_PTCR_RCSEL(8 | ext_port) |
+			   IMX_AUDMUX_V2_PTCR_TCSEL(ext_port) |
+			   IMX_AUDMUX_V2_PTCR_RCLKDIR |
+			   IMX_AUDMUX_V2_PTCR_TCLKDIR;
+		ext_ptcr = IMX_AUDMUX_V2_PTCR_RFSEL(8 | int_port) |
+			   IMX_AUDMUX_V2_PTCR_TFSEL(int_port) |
+			   IMX_AUDMUX_V2_PTCR_RFSDIR |
+			   IMX_AUDMUX_V2_PTCR_TFSDIR;
+		break;
+	case SND_SOC_DAIFMT_CBS_CFM:
+		int_ptcr = IMX_AUDMUX_V2_PTCR_RFSEL(8 | ext_port) |
+			   IMX_AUDMUX_V2_PTCR_TFSEL(ext_port) |
+			   IMX_AUDMUX_V2_PTCR_RFSDIR |
+			   IMX_AUDMUX_V2_PTCR_TFSDIR;
+		ext_ptcr = IMX_AUDMUX_V2_PTCR_RCSEL(8 | int_port) |
+			   IMX_AUDMUX_V2_PTCR_TCSEL(int_port) |
+			   IMX_AUDMUX_V2_PTCR_RCLKDIR |
+			   IMX_AUDMUX_V2_PTCR_TCLKDIR;
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		ext_ptcr = IMX_AUDMUX_V2_PTCR_RFSEL(8 | int_port) |
+			   IMX_AUDMUX_V2_PTCR_RCSEL(8 | int_port) |
+			   IMX_AUDMUX_V2_PTCR_TFSEL(int_port) |
+			   IMX_AUDMUX_V2_PTCR_TCSEL(int_port) |
+			   IMX_AUDMUX_V2_PTCR_RFSDIR |
+			   IMX_AUDMUX_V2_PTCR_RCLKDIR |
+			   IMX_AUDMUX_V2_PTCR_TFSDIR |
+			   IMX_AUDMUX_V2_PTCR_TCLKDIR;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Asynchronous mode can not be set along with RCLKDIR */
+	ret = imx_audmux_v2_configure_port(int_port, 0,
+					   IMX_AUDMUX_V2_PDCR_RXDSEL(ext_port));
+	if (ret) {
+		dev_err(dev, "audmux internal port setup failed\n");
+		return ret;
+	}
+
+	ret = imx_audmux_v2_configure_port(int_port, int_ptcr,
+					   IMX_AUDMUX_V2_PDCR_RXDSEL(ext_port));
+	if (ret) {
+		dev_err(dev, "audmux internal port setup failed\n");
+		return ret;
+	}
+
+	ret = imx_audmux_v2_configure_port(ext_port, 0,
+					   IMX_AUDMUX_V2_PDCR_RXDSEL(int_port));
+	if (ret) {
+		dev_err(dev, "audmux external port setup failed\n");
+		return ret;
+	}
+
+	ret = imx_audmux_v2_configure_port(ext_port, ext_ptcr,
+					   IMX_AUDMUX_V2_PDCR_RXDSEL(int_port));
+	if (ret) {
+		dev_err(dev, "audmux external port setup failed\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int fsl_asoc_card_late_probe(struct snd_soc_card *card)
+{
+	struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(card);
+	struct snd_soc_dai *codec_dai = card->rtd[0].codec_dai;
+	struct codec_priv *codec_priv = &priv->codec_priv;
+	struct device *dev = card->dev;
+	int ret;
+
+	ret = snd_soc_dai_set_sysclk(codec_dai, codec_priv->mclk_id,
+				     codec_priv->mclk_freq, SND_SOC_CLOCK_IN);
+	if (ret) {
+		dev_err(dev, "failed to set sysclk in %s\n", __func__);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int fsl_asoc_card_probe(struct platform_device *pdev)
+{
+	struct device_node *cpu_np, *codec_np, *asrc_np;
+	struct device_node *np = pdev->dev.of_node;
+	struct platform_device *asrc_pdev = NULL;
+	struct platform_device *cpu_pdev;
+	struct fsl_asoc_card_priv *priv;
+	struct i2c_client *codec_dev;
+	struct clk *codec_clk;
+	u32 width;
+	int ret;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	cpu_np = of_parse_phandle(np, "audio-cpu", 0);
+	/* Give a chance to old DT binding */
+	if (!cpu_np)
+		cpu_np = of_parse_phandle(np, "ssi-controller", 0);
+	codec_np = of_parse_phandle(np, "audio-codec", 0);
+	if (!cpu_np || !codec_np) {
+		dev_err(&pdev->dev, "phandle missing or invalid\n");
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	cpu_pdev = of_find_device_by_node(cpu_np);
+	if (!cpu_pdev) {
+		dev_err(&pdev->dev, "failed to find CPU DAI device\n");
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	codec_dev = of_find_i2c_device_by_node(codec_np);
+	if (!codec_dev) {
+		dev_err(&pdev->dev, "failed to find codec platform device\n");
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	asrc_np = of_parse_phandle(np, "audio-asrc", 0);
+	if (asrc_np)
+		asrc_pdev = of_find_device_by_node(asrc_np);
+
+	/* Get the MCLK rate only, and leave it controlled by CODEC drivers */
+	codec_clk = clk_get(&codec_dev->dev, NULL);
+	if (!IS_ERR(codec_clk)) {
+		priv->codec_priv.mclk_freq = clk_get_rate(codec_clk);
+		clk_put(codec_clk);
+	}
+
+	/* Default sample rate and format, will be updated in hw_params() */
+	priv->sample_rate = 44100;
+	priv->sample_format = SNDRV_PCM_FORMAT_S16_LE;
+
+	/* Assign a default DAI format, and allow each card to overwrite it */
+	priv->dai_fmt = DAI_FMT_BASE;
+
+	/* Diversify the card configurations */
+	if (of_device_is_compatible(np, "fsl,imx-audio-cs42888")) {
+		priv->card.set_bias_level = NULL;
+		priv->cpu_priv.sysclk_freq[TX] = priv->codec_priv.mclk_freq;
+		priv->cpu_priv.sysclk_freq[RX] = priv->codec_priv.mclk_freq;
+		priv->cpu_priv.sysclk_dir[TX] = SND_SOC_CLOCK_OUT;
+		priv->cpu_priv.sysclk_dir[RX] = SND_SOC_CLOCK_OUT;
+		priv->dai_fmt |= SND_SOC_DAIFMT_CBS_CFS;
+	} else if (of_device_is_compatible(np, "fsl,imx-audio-sgtl5000")) {
+		priv->codec_priv.mclk_id = SGTL5000_SYSCLK;
+		priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
+	} else if (of_device_is_compatible(np, "fsl,imx-audio-wm8962")) {
+		priv->card.set_bias_level = fsl_asoc_card_set_bias_level;
+		priv->codec_priv.mclk_id = WM8962_SYSCLK_MCLK;
+		priv->codec_priv.fll_id = WM8962_SYSCLK_FLL;
+		priv->codec_priv.pll_id = WM8962_FLL;
+		priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
+	} else {
+		dev_err(&pdev->dev, "unknown Device Tree compatible\n");
+		return -EINVAL;
+	}
+
+	/* Common settings for corresponding Freescale CPU DAI driver */
+	if (strstr(cpu_np->name, "ssi")) {
+		/* Only SSI needs to configure AUDMUX */
+		ret = fsl_asoc_card_audmux_init(np, priv);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to init audmux\n");
+			goto asrc_fail;
+		}
+	} else if (strstr(cpu_np->name, "esai")) {
+		priv->cpu_priv.sysclk_id[1] = ESAI_HCKT_EXTAL;
+		priv->cpu_priv.sysclk_id[0] = ESAI_HCKR_EXTAL;
+	} else if (strstr(cpu_np->name, "sai")) {
+		priv->cpu_priv.sysclk_id[1] = FSL_SAI_CLK_MAST1;
+		priv->cpu_priv.sysclk_id[0] = FSL_SAI_CLK_MAST1;
+	}
+
+	sprintf(priv->name, "%s-audio", codec_dev->name);
+
+	/* Initialize sound card */
+	priv->pdev = pdev;
+	priv->card.dev = &pdev->dev;
+	priv->card.name = priv->name;
+	priv->card.dai_link = priv->dai_link;
+	priv->card.dapm_routes = audio_map;
+	priv->card.late_probe = fsl_asoc_card_late_probe;
+	priv->card.num_dapm_routes = ARRAY_SIZE(audio_map);
+	priv->card.dapm_widgets = fsl_asoc_card_dapm_widgets;
+	priv->card.num_dapm_widgets = ARRAY_SIZE(fsl_asoc_card_dapm_widgets);
+
+	memcpy(priv->dai_link, fsl_asoc_card_dai,
+	       sizeof(struct snd_soc_dai_link) * ARRAY_SIZE(priv->dai_link));
+
+	/* Normal DAI Link */
+	priv->dai_link[0].cpu_of_node = cpu_np;
+	priv->dai_link[0].codec_of_node = codec_np;
+	priv->dai_link[0].codec_dai_name = codec_dev->name;
+	priv->dai_link[0].platform_of_node = cpu_np;
+	priv->dai_link[0].dai_fmt = priv->dai_fmt;
+	priv->card.num_links = 1;
+
+	if (asrc_pdev) {
+		/* DPCM DAI Links only if ASRC exsits */
+		priv->dai_link[1].cpu_of_node = asrc_np;
+		priv->dai_link[1].platform_of_node = asrc_np;
+		priv->dai_link[2].codec_dai_name = codec_dev->name;
+		priv->dai_link[2].codec_of_node = codec_np;
+		priv->dai_link[2].cpu_of_node = cpu_np;
+		priv->dai_link[2].dai_fmt = priv->dai_fmt;
+		priv->card.num_links = 3;
+
+		ret = of_property_read_u32(asrc_np, "fsl,asrc-rate",
+					   &priv->asrc_rate);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to get output rate\n");
+			ret = -EINVAL;
+			goto asrc_fail;
+		}
+
+		ret = of_property_read_u32(asrc_np, "fsl,asrc-width", &width);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to get output rate\n");
+			ret = -EINVAL;
+			goto asrc_fail;
+		}
+
+		if (width == 24)
+			priv->asrc_format = SNDRV_PCM_FORMAT_S24_LE;
+		else
+			priv->asrc_format = SNDRV_PCM_FORMAT_S16_LE;
+	}
+
+	/* Finish card registering */
+	platform_set_drvdata(pdev, priv);
+	snd_soc_card_set_drvdata(&priv->card, priv);
+
+	ret = devm_snd_soc_register_card(&pdev->dev, &priv->card);
+	if (ret)
+		dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret);
+
+asrc_fail:
+	of_node_put(asrc_np);
+fail:
+	of_node_put(codec_np);
+	of_node_put(cpu_np);
+
+	return ret;
+}
+
+static const struct of_device_id fsl_asoc_card_dt_ids[] = {
+	{ .compatible = "fsl,imx-audio-cs42888", },
+	{ .compatible = "fsl,imx-audio-sgtl5000", },
+	{ .compatible = "fsl,imx-audio-wm8962", },
+	{}
+};
+
+static struct platform_driver fsl_asoc_card_driver = {
+	.probe = fsl_asoc_card_probe,
+	.driver = {
+		.name = "fsl-asoc-card",
+		.pm = &snd_soc_pm_ops,
+		.of_match_table = fsl_asoc_card_dt_ids,
+	},
+};
+module_platform_driver(fsl_asoc_card_driver);
+
+MODULE_DESCRIPTION("Freescale Generic ASoC Sound Card driver with ASRC");
+MODULE_AUTHOR("Nicolin Chen <nicoleotsuka@gmail.com>");
+MODULE_ALIAS("platform:fsl-asoc-card");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c
index 822110420b71..3b145313f93e 100644
--- a/sound/soc/fsl/fsl_asrc.c
+++ b/sound/soc/fsl/fsl_asrc.c
@@ -684,7 +684,7 @@ static bool fsl_asrc_writeable_reg(struct device *dev, unsigned int reg)
 	}
 }
 
-static struct regmap_config fsl_asrc_regmap_config = {
+static const struct regmap_config fsl_asrc_regmap_config = {
 	.reg_bits = 32,
 	.reg_stride = 4,
 	.val_bits = 32,
@@ -802,10 +802,6 @@ static int fsl_asrc_probe(struct platform_device *pdev)
 
 	asrc_priv->paddr = res->start;
 
-	/* Register regmap and let it prepare core clock */
-	if (of_property_read_bool(np, "big-endian"))
-		fsl_asrc_regmap_config.val_format_endian = REGMAP_ENDIAN_BIG;
-
 	asrc_priv->regmap = devm_regmap_init_mmio_clk(&pdev->dev, "mem", regs,
 						      &fsl_asrc_regmap_config);
 	if (IS_ERR(asrc_priv->regmap)) {
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index a3b29ed84963..8bcdfda09d7a 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -37,6 +37,7 @@
  * @fsysclk: system clock source to derive HCK, SCK and FS
  * @fifo_depth: depth of tx/rx FIFO
  * @slot_width: width of each DAI slot
+ * @slots: number of slots
  * @hck_rate: clock rate of desired HCKx clock
  * @sck_rate: clock rate of desired SCKx clock
  * @hck_dir: the direction of HCKx pads
@@ -55,6 +56,7 @@ struct fsl_esai {
 	struct clk *fsysclk;
 	u32 fifo_depth;
 	u32 slot_width;
+	u32 slots;
 	u32 hck_rate[2];
 	u32 sck_rate[2];
 	bool hck_dir[2];
@@ -362,6 +364,7 @@ static int fsl_esai_set_dai_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask,
 			   ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(rx_mask));
 
 	esai_priv->slot_width = slot_width;
+	esai_priv->slots = slots;
 
 	return 0;
 }
@@ -509,10 +512,11 @@ static int fsl_esai_hw_params(struct snd_pcm_substream *substream,
 	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
 	u32 width = snd_pcm_format_width(params_format(params));
 	u32 channels = params_channels(params);
+	u32 pins = DIV_ROUND_UP(channels, esai_priv->slots);
 	u32 bclk, mask, val;
 	int ret;
 
-	bclk = params_rate(params) * esai_priv->slot_width * 2;
+	bclk = params_rate(params) * esai_priv->slot_width * esai_priv->slots;
 
 	ret = fsl_esai_set_bclk(dai, tx, bclk);
 	if (ret)
@@ -529,7 +533,7 @@ static int fsl_esai_hw_params(struct snd_pcm_substream *substream,
 	mask = ESAI_xFCR_xFR_MASK | ESAI_xFCR_xWA_MASK | ESAI_xFCR_xFWM_MASK |
 	      (tx ? ESAI_xFCR_TE_MASK | ESAI_xFCR_TIEN : ESAI_xFCR_RE_MASK);
 	val = ESAI_xFCR_xWA(width) | ESAI_xFCR_xFWM(esai_priv->fifo_depth) |
-	     (tx ? ESAI_xFCR_TE(channels) | ESAI_xFCR_TIEN : ESAI_xFCR_RE(channels));
+	     (tx ? ESAI_xFCR_TE(pins) | ESAI_xFCR_TIEN : ESAI_xFCR_RE(pins));
 
 	regmap_update_bits(esai_priv->regmap, REG_ESAI_xFCR(tx), mask, val);
 
@@ -564,6 +568,7 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd,
 	struct fsl_esai *esai_priv = snd_soc_dai_get_drvdata(dai);
 	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
 	u8 i, channels = substream->runtime->channels;
+	u32 pins = DIV_ROUND_UP(channels, esai_priv->slots);
 
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
@@ -578,7 +583,7 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd,
 
 		regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx),
 				   tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK,
-				   tx ? ESAI_xCR_TE(channels) : ESAI_xCR_RE(channels));
+				   tx ? ESAI_xCR_TE(pins) : ESAI_xCR_RE(pins));
 		break;
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_STOP:
@@ -705,7 +710,7 @@ static bool fsl_esai_writeable_reg(struct device *dev, unsigned int reg)
 	}
 }
 
-static struct regmap_config fsl_esai_regmap_config = {
+static const struct regmap_config fsl_esai_regmap_config = {
 	.reg_bits = 32,
 	.reg_stride = 4,
 	.val_bits = 32,
@@ -731,9 +736,6 @@ static int fsl_esai_probe(struct platform_device *pdev)
 	esai_priv->pdev = pdev;
 	strcpy(esai_priv->name, np->name);
 
-	if (of_property_read_bool(np, "big-endian"))
-		fsl_esai_regmap_config.val_format_endian = REGMAP_ENDIAN_BIG;
-
 	/* Get the addresses and IRQ */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	regs = devm_ioremap_resource(&pdev->dev, res);
@@ -781,6 +783,9 @@ static int fsl_esai_probe(struct platform_device *pdev)
 	/* Set a default slot size */
 	esai_priv->slot_width = 32;
 
+	/* Set a default slot number */
+	esai_priv->slots = 2;
+
 	/* Set a default master/slave state */
 	esai_priv->slave_mode = true;
 
diff --git a/sound/soc/fsl/fsl_esai.h b/sound/soc/fsl/fsl_esai.h
index 75e14033e8d8..91a550f4a10d 100644
--- a/sound/soc/fsl/fsl_esai.h
+++ b/sound/soc/fsl/fsl_esai.h
@@ -130,8 +130,8 @@
 #define ESAI_xFCR_RE_WIDTH	4
 #define ESAI_xFCR_TE_MASK	(((1 << ESAI_xFCR_TE_WIDTH) - 1) << ESAI_xFCR_xE_SHIFT)
 #define ESAI_xFCR_RE_MASK	(((1 << ESAI_xFCR_RE_WIDTH) - 1) << ESAI_xFCR_xE_SHIFT)
-#define ESAI_xFCR_TE(x) 	((ESAI_xFCR_TE_MASK >> (ESAI_xFCR_TE_WIDTH - ((x + 1) >> 1))) & ESAI_xFCR_TE_MASK)
-#define ESAI_xFCR_RE(x) 	((ESAI_xFCR_RE_MASK >> (ESAI_xFCR_RE_WIDTH - ((x + 1) >> 1))) & ESAI_xFCR_RE_MASK)
+#define ESAI_xFCR_TE(x) 	((ESAI_xFCR_TE_MASK >> (ESAI_xFCR_TE_WIDTH - x)) & ESAI_xFCR_TE_MASK)
+#define ESAI_xFCR_RE(x) 	((ESAI_xFCR_RE_MASK >> (ESAI_xFCR_RE_WIDTH - x)) & ESAI_xFCR_RE_MASK)
 #define ESAI_xFCR_xFR_SHIFT	1
 #define ESAI_xFCR_xFR_MASK	(1 << ESAI_xFCR_xFR_SHIFT)
 #define ESAI_xFCR_xFR		(1 << ESAI_xFCR_xFR_SHIFT)
@@ -272,8 +272,8 @@
 #define ESAI_xCR_RE_WIDTH	4
 #define ESAI_xCR_TE_MASK	(((1 << ESAI_xCR_TE_WIDTH) - 1) << ESAI_xCR_xE_SHIFT)
 #define ESAI_xCR_RE_MASK	(((1 << ESAI_xCR_RE_WIDTH) - 1) << ESAI_xCR_xE_SHIFT)
-#define ESAI_xCR_TE(x) 		((ESAI_xCR_TE_MASK >> (ESAI_xCR_TE_WIDTH - ((x + 1) >> 1))) & ESAI_xCR_TE_MASK)
-#define ESAI_xCR_RE(x) 		((ESAI_xCR_RE_MASK >> (ESAI_xCR_RE_WIDTH - ((x + 1) >> 1))) & ESAI_xCR_RE_MASK)
+#define ESAI_xCR_TE(x) 		((ESAI_xCR_TE_MASK >> (ESAI_xCR_TE_WIDTH - x)) & ESAI_xCR_TE_MASK)
+#define ESAI_xCR_RE(x) 		((ESAI_xCR_RE_MASK >> (ESAI_xCR_RE_WIDTH - x)) & ESAI_xCR_RE_MASK)
 
 /*
  * Transmit Clock Control Register -- REG_ESAI_TCCR 0xD8
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index faa049797897..7eeb1dd8ce27 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -175,7 +175,7 @@ static int fsl_sai_set_dai_fmt_tr(struct snd_soc_dai *cpu_dai,
 	bool tx = fsl_dir == FSL_FMT_TRANSMITTER;
 	u32 val_cr2 = 0, val_cr4 = 0;
 
-	if (!sai->big_endian_data)
+	if (!sai->is_lsb_first)
 		val_cr4 |= FSL_SAI_CR4_MF;
 
 	/* DAI mode */
@@ -304,7 +304,7 @@ static int fsl_sai_hw_params(struct snd_pcm_substream *substream,
 	val_cr5 |= FSL_SAI_CR5_WNW(word_width);
 	val_cr5 |= FSL_SAI_CR5_W0W(word_width);
 
-	if (sai->big_endian_data)
+	if (sai->is_lsb_first)
 		val_cr5 |= FSL_SAI_CR5_FBT(0);
 	else
 		val_cr5 |= FSL_SAI_CR5_FBT(word_width - 1);
@@ -330,13 +330,13 @@ static int fsl_sai_trigger(struct snd_pcm_substream *substream, int cmd,
 	u32 xcsr, count = 100;
 
 	/*
-	 * The transmitter bit clock and frame sync are to be
-	 * used by both the transmitter and receiver.
+	 * Asynchronous mode: Clear SYNC for both Tx and Rx.
+	 * Rx sync with Tx clocks: Clear SYNC for Tx, set it for Rx.
+	 * Tx sync with Rx clocks: Clear SYNC for Rx, set it for Tx.
 	 */
-	regmap_update_bits(sai->regmap, FSL_SAI_TCR2, FSL_SAI_CR2_SYNC,
-			   ~FSL_SAI_CR2_SYNC);
+	regmap_update_bits(sai->regmap, FSL_SAI_TCR2, FSL_SAI_CR2_SYNC, 0);
 	regmap_update_bits(sai->regmap, FSL_SAI_RCR2, FSL_SAI_CR2_SYNC,
-			   FSL_SAI_CR2_SYNC);
+			   sai->synchronous[RX] ? FSL_SAI_CR2_SYNC : 0);
 
 	/*
 	 * It is recommended that the transmitter is the last enabled
@@ -437,8 +437,13 @@ static int fsl_sai_dai_probe(struct snd_soc_dai *cpu_dai)
 {
 	struct fsl_sai *sai = dev_get_drvdata(cpu_dai->dev);
 
-	regmap_update_bits(sai->regmap, FSL_SAI_TCSR, 0xffffffff, 0x0);
-	regmap_update_bits(sai->regmap, FSL_SAI_RCSR, 0xffffffff, 0x0);
+	/* Software Reset for both Tx and Rx */
+	regmap_write(sai->regmap, FSL_SAI_TCSR, FSL_SAI_CSR_SR);
+	regmap_write(sai->regmap, FSL_SAI_RCSR, FSL_SAI_CSR_SR);
+	/* Clear SR bit to finish the reset */
+	regmap_write(sai->regmap, FSL_SAI_TCSR, 0);
+	regmap_write(sai->regmap, FSL_SAI_RCSR, 0);
+
 	regmap_update_bits(sai->regmap, FSL_SAI_TCR1, FSL_SAI_CR1_RFW_MASK,
 			   FSL_SAI_MAXBURST_TX * 2);
 	regmap_update_bits(sai->regmap, FSL_SAI_RCR1, FSL_SAI_CR1_RFW_MASK,
@@ -539,7 +544,7 @@ static bool fsl_sai_writeable_reg(struct device *dev, unsigned int reg)
 	}
 }
 
-static struct regmap_config fsl_sai_regmap_config = {
+static const struct regmap_config fsl_sai_regmap_config = {
 	.reg_bits = 32,
 	.reg_stride = 4,
 	.val_bits = 32,
@@ -568,11 +573,7 @@ static int fsl_sai_probe(struct platform_device *pdev)
 	if (of_device_is_compatible(pdev->dev.of_node, "fsl,imx6sx-sai"))
 		sai->sai_on_imx = true;
 
-	sai->big_endian_regs = of_property_read_bool(np, "big-endian-regs");
-	if (sai->big_endian_regs)
-		fsl_sai_regmap_config.val_format_endian = REGMAP_ENDIAN_BIG;
-
-	sai->big_endian_data = of_property_read_bool(np, "big-endian-data");
+	sai->is_lsb_first = of_property_read_bool(np, "lsb-first");
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	base = devm_ioremap_resource(&pdev->dev, res);
@@ -621,6 +622,33 @@ static int fsl_sai_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/* Sync Tx with Rx as default by following old DT binding */
+	sai->synchronous[RX] = true;
+	sai->synchronous[TX] = false;
+	fsl_sai_dai.symmetric_rates = 1;
+	fsl_sai_dai.symmetric_channels = 1;
+	fsl_sai_dai.symmetric_samplebits = 1;
+
+	if (of_find_property(np, "fsl,sai-synchronous-rx", NULL) &&
+	    of_find_property(np, "fsl,sai-asynchronous", NULL)) {
+		/* error out if both synchronous and asynchronous are present */
+		dev_err(&pdev->dev, "invalid binding for synchronous mode\n");
+		return -EINVAL;
+	}
+
+	if (of_find_property(np, "fsl,sai-synchronous-rx", NULL)) {
+		/* Sync Rx with Tx */
+		sai->synchronous[RX] = false;
+		sai->synchronous[TX] = true;
+	} else if (of_find_property(np, "fsl,sai-asynchronous", NULL)) {
+		/* Discard all settings for asynchronous mode */
+		sai->synchronous[RX] = false;
+		sai->synchronous[TX] = false;
+		fsl_sai_dai.symmetric_rates = 0;
+		fsl_sai_dai.symmetric_channels = 0;
+		fsl_sai_dai.symmetric_samplebits = 0;
+	}
+
 	sai->dma_params_rx.addr = res->start + FSL_SAI_RDR;
 	sai->dma_params_tx.addr = res->start + FSL_SAI_TDR;
 	sai->dma_params_rx.maxburst = FSL_SAI_MAXBURST_RX;
diff --git a/sound/soc/fsl/fsl_sai.h b/sound/soc/fsl/fsl_sai.h
index 0e6c9f595d75..34667209b607 100644
--- a/sound/soc/fsl/fsl_sai.h
+++ b/sound/soc/fsl/fsl_sai.h
@@ -48,6 +48,7 @@
 /* SAI Transmit/Recieve Control Register */
 #define FSL_SAI_CSR_TERE	BIT(31)
 #define FSL_SAI_CSR_FR		BIT(25)
+#define FSL_SAI_CSR_SR		BIT(24)
 #define FSL_SAI_CSR_xF_SHIFT	16
 #define FSL_SAI_CSR_xF_W_SHIFT	18
 #define FSL_SAI_CSR_xF_MASK	(0x1f << FSL_SAI_CSR_xF_SHIFT)
@@ -131,13 +132,16 @@ struct fsl_sai {
 	struct clk *bus_clk;
 	struct clk *mclk_clk[FSL_SAI_MCLK_MAX];
 
-	bool big_endian_regs;
-	bool big_endian_data;
+	bool is_lsb_first;
 	bool is_dsp_mode;
 	bool sai_on_imx;
+	bool synchronous[2];
 
 	struct snd_dmaengine_dai_dma_data dma_params_rx;
 	struct snd_dmaengine_dai_dma_data dma_params_tx;
 };
 
+#define TX 1
+#define RX 0
+
 #endif /* __FSL_SAI_H */
diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c
index 70acfe4a9bd5..9b791621294c 100644
--- a/sound/soc/fsl/fsl_spdif.c
+++ b/sound/soc/fsl/fsl_spdif.c
@@ -15,7 +15,6 @@
 
 #include <linux/bitrev.h>
 #include <linux/clk.h>
-#include <linux/clk-private.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
@@ -1040,7 +1039,7 @@ static bool fsl_spdif_writeable_reg(struct device *dev, unsigned int reg)
 	}
 }
 
-static struct regmap_config fsl_spdif_regmap_config = {
+static const struct regmap_config fsl_spdif_regmap_config = {
 	.reg_bits = 32,
 	.reg_stride = 4,
 	.val_bits = 32,
@@ -1184,9 +1183,6 @@ static int fsl_spdif_probe(struct platform_device *pdev)
 	memcpy(&spdif_priv->cpu_dai_drv, &fsl_spdif_dai, sizeof(fsl_spdif_dai));
 	spdif_priv->cpu_dai_drv.name = spdif_priv->name;
 
-	if (of_property_read_bool(np, "big-endian"))
-		fsl_spdif_regmap_config.val_format_endian = REGMAP_ENDIAN_BIG;
-
 	/* Get the addresses and IRQ */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	regs = devm_ioremap_resource(&pdev->dev, res);
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index de6ab06f58a5..e6955170dc42 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -169,6 +169,7 @@ struct fsl_ssi_private {
 	u8 i2s_mode;
 	bool use_dma;
 	bool use_dual_fifo;
+	bool has_ipg_clk_name;
 	unsigned int fifo_depth;
 	struct fsl_ssi_rxtx_reg_val rxtx_reg_val;
 
@@ -259,6 +260,11 @@ static bool fsl_ssi_is_i2s_master(struct fsl_ssi_private *ssi_private)
 		SND_SOC_DAIFMT_CBS_CFS;
 }
 
+static bool fsl_ssi_is_i2s_cbm_cfs(struct fsl_ssi_private *ssi_private)
+{
+	return (ssi_private->dai_fmt & SND_SOC_DAIFMT_MASTER_MASK) ==
+		SND_SOC_DAIFMT_CBM_CFS;
+}
 /**
  * fsl_ssi_isr: SSI interrupt handler
  *
@@ -525,6 +531,11 @@ static int fsl_ssi_startup(struct snd_pcm_substream *substream,
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct fsl_ssi_private *ssi_private =
 		snd_soc_dai_get_drvdata(rtd->cpu_dai);
+	int ret;
+
+	ret = clk_prepare_enable(ssi_private->clk);
+	if (ret)
+		return ret;
 
 	/* When using dual fifo mode, it is safer to ensure an even period
 	 * size. If appearing to an odd number while DMA always starts its
@@ -539,6 +550,21 @@ static int fsl_ssi_startup(struct snd_pcm_substream *substream,
 }
 
 /**
+ * fsl_ssi_shutdown: shutdown the SSI
+ *
+ */
+static void fsl_ssi_shutdown(struct snd_pcm_substream *substream,
+				struct snd_soc_dai *dai)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct fsl_ssi_private *ssi_private =
+		snd_soc_dai_get_drvdata(rtd->cpu_dai);
+
+	clk_disable_unprepare(ssi_private->clk);
+
+}
+
+/**
  * fsl_ssi_set_bclk - configure Digital Audio Interface bit clock
  *
  * Note: This function can be only called when using SSI as DAI master
@@ -705,6 +731,23 @@ static int fsl_ssi_hw_params(struct snd_pcm_substream *substream,
 		}
 	}
 
+	if (!fsl_ssi_is_ac97(ssi_private)) {
+		u8 i2smode;
+		/*
+		 * Switch to normal net mode in order to have a frame sync
+		 * signal every 32 bits instead of 16 bits
+		 */
+		if (fsl_ssi_is_i2s_cbm_cfs(ssi_private) && sample_size == 16)
+			i2smode = CCSR_SSI_SCR_I2S_MODE_NORMAL |
+				CCSR_SSI_SCR_NET;
+		else
+			i2smode = ssi_private->i2s_mode;
+
+		regmap_update_bits(regs, CCSR_SSI_SCR,
+				CCSR_SSI_SCR_NET | CCSR_SSI_SCR_I2S_MODE_MASK,
+				channels == 1 ? 0 : i2smode);
+	}
+
 	/*
 	 * FIXME: The documentation says that SxCCR[WL] should not be
 	 * modified while the SSI is enabled.  The only time this can
@@ -724,11 +767,6 @@ static int fsl_ssi_hw_params(struct snd_pcm_substream *substream,
 		regmap_update_bits(regs, CCSR_SSI_SRCCR, CCSR_SSI_SxCCR_WL_MASK,
 				wl);
 
-	if (!fsl_ssi_is_ac97(ssi_private))
-		regmap_update_bits(regs, CCSR_SSI_SCR,
-				CCSR_SSI_SCR_NET | CCSR_SSI_SCR_I2S_MODE_MASK,
-				channels == 1 ? 0 : ssi_private->i2s_mode);
-
 	return 0;
 }
 
@@ -781,6 +819,7 @@ static int _fsl_ssi_set_dai_fmt(struct device *dev,
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
 		switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+		case SND_SOC_DAIFMT_CBM_CFS:
 		case SND_SOC_DAIFMT_CBS_CFS:
 			ssi_private->i2s_mode |= CCSR_SSI_SCR_I2S_MODE_MASTER;
 			regmap_update_bits(regs, CCSR_SSI_STCCR,
@@ -854,6 +893,11 @@ static int _fsl_ssi_set_dai_fmt(struct device *dev,
 	case SND_SOC_DAIFMT_CBM_CFM:
 		scr &= ~CCSR_SSI_SCR_SYS_CLK_EN;
 		break;
+	case SND_SOC_DAIFMT_CBM_CFS:
+		strcr &= ~CCSR_SSI_STCR_TXDIR;
+		strcr |= CCSR_SSI_STCR_TFDIR;
+		scr &= ~CCSR_SSI_SCR_SYS_CLK_EN;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1021,6 +1065,7 @@ static int fsl_ssi_dai_probe(struct snd_soc_dai *dai)
 
 static const struct snd_soc_dai_ops fsl_ssi_dai_ops = {
 	.startup	= fsl_ssi_startup,
+	.shutdown       = fsl_ssi_shutdown,
 	.hw_params	= fsl_ssi_hw_params,
 	.hw_free	= fsl_ssi_hw_free,
 	.set_fmt	= fsl_ssi_set_dai_fmt,
@@ -1146,17 +1191,22 @@ static int fsl_ssi_imx_probe(struct platform_device *pdev,
 	u32 dmas[4];
 	int ret;
 
-	ssi_private->clk = devm_clk_get(&pdev->dev, NULL);
+	if (ssi_private->has_ipg_clk_name)
+		ssi_private->clk = devm_clk_get(&pdev->dev, "ipg");
+	else
+		ssi_private->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(ssi_private->clk)) {
 		ret = PTR_ERR(ssi_private->clk);
 		dev_err(&pdev->dev, "could not get clock: %d\n", ret);
 		return ret;
 	}
 
-	ret = clk_prepare_enable(ssi_private->clk);
-	if (ret) {
-		dev_err(&pdev->dev, "clk_prepare_enable failed: %d\n", ret);
-		return ret;
+	if (!ssi_private->has_ipg_clk_name) {
+		ret = clk_prepare_enable(ssi_private->clk);
+		if (ret) {
+			dev_err(&pdev->dev, "clk_prepare_enable failed: %d\n", ret);
+			return ret;
+		}
 	}
 
 	/* For those SLAVE implementations, we ingore non-baudclk cases
@@ -1214,8 +1264,9 @@ static int fsl_ssi_imx_probe(struct platform_device *pdev,
 	return 0;
 
 error_pcm:
-	clk_disable_unprepare(ssi_private->clk);
 
+	if (!ssi_private->has_ipg_clk_name)
+		clk_disable_unprepare(ssi_private->clk);
 	return ret;
 }
 
@@ -1224,7 +1275,8 @@ static void fsl_ssi_imx_clean(struct platform_device *pdev,
 {
 	if (!ssi_private->use_dma)
 		imx_pcm_fiq_exit(pdev);
-	clk_disable_unprepare(ssi_private->clk);
+	if (!ssi_private->has_ipg_clk_name)
+		clk_disable_unprepare(ssi_private->clk);
 }
 
 static int fsl_ssi_probe(struct platform_device *pdev)
@@ -1263,9 +1315,6 @@ static int fsl_ssi_probe(struct platform_device *pdev)
 	if (sprop) {
 		if (!strcmp(sprop, "ac97-slave"))
 			ssi_private->dai_fmt = SND_SOC_DAIFMT_AC97;
-		else if (!strcmp(sprop, "i2s-slave"))
-			ssi_private->dai_fmt = SND_SOC_DAIFMT_I2S |
-				SND_SOC_DAIFMT_CBM_CFM;
 	}
 
 	ssi_private->use_dma = !of_property_read_bool(np,
@@ -1299,8 +1348,16 @@ static int fsl_ssi_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	ssi_private->regs = devm_regmap_init_mmio(&pdev->dev, iomem,
+	ret = of_property_match_string(np, "clock-names", "ipg");
+	if (ret < 0) {
+		ssi_private->has_ipg_clk_name = false;
+		ssi_private->regs = devm_regmap_init_mmio(&pdev->dev, iomem,
 			&fsl_ssi_regconfig);
+	} else {
+		ssi_private->has_ipg_clk_name = true;
+		ssi_private->regs = devm_regmap_init_mmio_clk(&pdev->dev,
+			"ipg", iomem, &fsl_ssi_regconfig);
+	}
 	if (IS_ERR(ssi_private->regs)) {
 		dev_err(&pdev->dev, "Failed to init register map\n");
 		return PTR_ERR(ssi_private->regs);
diff --git a/sound/soc/fsl/imx-es8328.c b/sound/soc/fsl/imx-es8328.c
new file mode 100644
index 000000000000..f8cf10e16ce9
--- /dev/null
+++ b/sound/soc/fsl/imx-es8328.c
@@ -0,0 +1,233 @@
+/*
+ * Copyright 2012 Freescale Semiconductor, Inc.
+ * Copyright 2012 Linaro Ltd.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#include <linux/gpio.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/i2c.h>
+#include <linux/of_gpio.h>
+#include <sound/soc.h>
+#include <sound/jack.h>
+
+#include "imx-audmux.h"
+
+#define DAI_NAME_SIZE	32
+#define MUX_PORT_MAX	7
+
+struct imx_es8328_data {
+	struct device *dev;
+	struct snd_soc_dai_link dai;
+	struct snd_soc_card card;
+	char codec_dai_name[DAI_NAME_SIZE];
+	char platform_name[DAI_NAME_SIZE];
+	int jack_gpio;
+};
+
+static struct snd_soc_jack_gpio headset_jack_gpios[] = {
+	{
+		.gpio = -1,
+		.name = "headset-gpio",
+		.report = SND_JACK_HEADSET,
+		.invert = 0,
+		.debounce_time = 200,
+	},
+};
+
+static struct snd_soc_jack headset_jack;
+
+static int imx_es8328_dai_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct imx_es8328_data *data = container_of(rtd->card,
+					struct imx_es8328_data, card);
+	int ret = 0;
+
+	/* Headphone jack detection */
+	if (gpio_is_valid(data->jack_gpio)) {
+		ret = snd_soc_jack_new(rtd->codec, "Headphone",
+				       SND_JACK_HEADPHONE | SND_JACK_BTN_0,
+				       &headset_jack);
+		if (ret)
+			return ret;
+
+		headset_jack_gpios[0].gpio = data->jack_gpio;
+		ret = snd_soc_jack_add_gpios(&headset_jack,
+					     ARRAY_SIZE(headset_jack_gpios),
+					     headset_jack_gpios);
+	}
+
+	return ret;
+}
+
+static const struct snd_soc_dapm_widget imx_es8328_dapm_widgets[] = {
+	SND_SOC_DAPM_MIC("Mic Jack", NULL),
+	SND_SOC_DAPM_HP("Headphone", NULL),
+	SND_SOC_DAPM_SPK("Speaker", NULL),
+	SND_SOC_DAPM_REGULATOR_SUPPLY("audio-amp", 1, 0),
+};
+
+static int imx_es8328_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct device_node *ssi_np = NULL, *codec_np = NULL;
+	struct platform_device *ssi_pdev;
+	struct imx_es8328_data *data;
+	u32 int_port, ext_port;
+	int ret;
+	struct device *dev = &pdev->dev;
+
+	ret = of_property_read_u32(np, "mux-int-port", &int_port);
+	if (ret) {
+		dev_err(dev, "mux-int-port missing or invalid\n");
+		goto fail;
+	}
+	if (int_port > MUX_PORT_MAX || int_port == 0) {
+		dev_err(dev, "mux-int-port: hardware only has %d mux ports\n",
+			MUX_PORT_MAX);
+		goto fail;
+	}
+
+	ret = of_property_read_u32(np, "mux-ext-port", &ext_port);
+	if (ret) {
+		dev_err(dev, "mux-ext-port missing or invalid\n");
+		goto fail;
+	}
+	if (ext_port > MUX_PORT_MAX || ext_port == 0) {
+		dev_err(dev, "mux-ext-port: hardware only has %d mux ports\n",
+			MUX_PORT_MAX);
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	/*
+	 * The port numbering in the hardware manual starts at 1, while
+	 * the audmux API expects it starts at 0.
+	 */
+	int_port--;
+	ext_port--;
+	ret = imx_audmux_v2_configure_port(int_port,
+			IMX_AUDMUX_V2_PTCR_SYN |
+			IMX_AUDMUX_V2_PTCR_TFSEL(ext_port) |
+			IMX_AUDMUX_V2_PTCR_TCSEL(ext_port) |
+			IMX_AUDMUX_V2_PTCR_TFSDIR |
+			IMX_AUDMUX_V2_PTCR_TCLKDIR,
+			IMX_AUDMUX_V2_PDCR_RXDSEL(ext_port));
+	if (ret) {
+		dev_err(dev, "audmux internal port setup failed\n");
+		return ret;
+	}
+	ret = imx_audmux_v2_configure_port(ext_port,
+			IMX_AUDMUX_V2_PTCR_SYN,
+			IMX_AUDMUX_V2_PDCR_RXDSEL(int_port));
+	if (ret) {
+		dev_err(dev, "audmux external port setup failed\n");
+		return ret;
+	}
+
+	ssi_np = of_parse_phandle(pdev->dev.of_node, "ssi-controller", 0);
+	codec_np = of_parse_phandle(pdev->dev.of_node, "audio-codec", 0);
+	if (!ssi_np || !codec_np) {
+		dev_err(dev, "phandle missing or invalid\n");
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	ssi_pdev = of_find_device_by_node(ssi_np);
+	if (!ssi_pdev) {
+		dev_err(dev, "failed to find SSI platform device\n");
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	data->dev = dev;
+
+	data->jack_gpio = of_get_named_gpio(pdev->dev.of_node, "jack-gpio", 0);
+
+	data->dai.name = "hifi";
+	data->dai.stream_name = "hifi";
+	data->dai.codec_dai_name = "es8328-hifi-analog";
+	data->dai.codec_of_node = codec_np;
+	data->dai.cpu_of_node = ssi_np;
+	data->dai.platform_of_node = ssi_np;
+	data->dai.init = &imx_es8328_dai_init;
+	data->dai.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
+			    SND_SOC_DAIFMT_CBM_CFM;
+
+	data->card.dev = dev;
+	data->card.dapm_widgets = imx_es8328_dapm_widgets;
+	data->card.num_dapm_widgets = ARRAY_SIZE(imx_es8328_dapm_widgets);
+	ret = snd_soc_of_parse_card_name(&data->card, "model");
+	if (ret) {
+		dev_err(dev, "Unable to parse card name\n");
+		goto fail;
+	}
+	ret = snd_soc_of_parse_audio_routing(&data->card, "audio-routing");
+	if (ret) {
+		dev_err(dev, "Unable to parse routing: %d\n", ret);
+		goto fail;
+	}
+	data->card.num_links = 1;
+	data->card.owner = THIS_MODULE;
+	data->card.dai_link = &data->dai;
+
+	ret = snd_soc_register_card(&data->card);
+	if (ret) {
+		dev_err(dev, "Unable to register: %d\n", ret);
+		goto fail;
+	}
+
+	platform_set_drvdata(pdev, data);
+fail:
+	of_node_put(ssi_np);
+	of_node_put(codec_np);
+
+	return ret;
+}
+
+static int imx_es8328_remove(struct platform_device *pdev)
+{
+	struct imx_es8328_data *data = platform_get_drvdata(pdev);
+
+	snd_soc_jack_free_gpios(&headset_jack, ARRAY_SIZE(headset_jack_gpios),
+				headset_jack_gpios);
+
+	snd_soc_unregister_card(&data->card);
+
+	return 0;
+}
+
+static const struct of_device_id imx_es8328_dt_ids[] = {
+	{ .compatible = "fsl,imx-audio-es8328", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, imx_es8328_dt_ids);
+
+static struct platform_driver imx_es8328_driver = {
+	.driver = {
+		.name = "imx-es8328",
+		.of_match_table = imx_es8328_dt_ids,
+	},
+	.probe = imx_es8328_probe,
+	.remove = imx_es8328_remove,
+};
+module_platform_driver(imx_es8328_driver);
+
+MODULE_AUTHOR("Sean Cross <xobs@kosagi.com>");
+MODULE_DESCRIPTION("Kosagi i.MX6 ES8328 ASoC machine driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:imx-audio-es8328");
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index cef7776b712c..d1b7293c133e 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -10,10 +10,13 @@
  */
 #include <linux/clk.h>
 #include <linux/device.h>
+#include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_gpio.h>
 #include <linux/platform_device.h>
 #include <linux/string.h>
+#include <sound/jack.h>
 #include <sound/simple_card.h>
 #include <sound/soc-dai.h>
 #include <sound/soc.h>
@@ -25,9 +28,15 @@ struct simple_card_data {
 		struct asoc_simple_dai codec_dai;
 	} *dai_props;
 	unsigned int mclk_fs;
+	int gpio_hp_det;
+	int gpio_mic_det;
 	struct snd_soc_dai_link dai_link[];	/* dynamically allocated */
 };
 
+#define simple_priv_to_dev(priv) ((priv)->snd_card.dev)
+#define simple_priv_to_link(priv, i) ((priv)->snd_card.dai_link + i)
+#define simple_priv_to_props(priv, i) ((priv)->dai_props + i)
+
 static int asoc_simple_card_hw_params(struct snd_pcm_substream *substream,
 				      struct snd_pcm_hw_params *params)
 {
@@ -50,6 +59,32 @@ static struct snd_soc_ops asoc_simple_card_ops = {
 	.hw_params = asoc_simple_card_hw_params,
 };
 
+static struct snd_soc_jack simple_card_hp_jack;
+static struct snd_soc_jack_pin simple_card_hp_jack_pins[] = {
+	{
+		.pin = "Headphones",
+		.mask = SND_JACK_HEADPHONE,
+	},
+};
+static struct snd_soc_jack_gpio simple_card_hp_jack_gpio = {
+	.name = "Headphone detection",
+	.report = SND_JACK_HEADPHONE,
+	.debounce_time = 150,
+};
+
+static struct snd_soc_jack simple_card_mic_jack;
+static struct snd_soc_jack_pin simple_card_mic_jack_pins[] = {
+	{
+		.pin = "Mic Jack",
+		.mask = SND_JACK_MICROPHONE,
+	},
+};
+static struct snd_soc_jack_gpio simple_card_mic_jack_gpio = {
+	.name = "Mic detection",
+	.report = SND_JACK_MICROPHONE,
+	.debounce_time = 150,
+};
+
 static int __asoc_simple_card_dai_init(struct snd_soc_dai *dai,
 				       struct asoc_simple_dai *set)
 {
@@ -105,42 +140,70 @@ static int asoc_simple_card_dai_init(struct snd_soc_pcm_runtime *rtd)
 	if (ret < 0)
 		return ret;
 
+	if (gpio_is_valid(priv->gpio_hp_det)) {
+		snd_soc_jack_new(codec->codec, "Headphones", SND_JACK_HEADPHONE,
+				 &simple_card_hp_jack);
+		snd_soc_jack_add_pins(&simple_card_hp_jack,
+				      ARRAY_SIZE(simple_card_hp_jack_pins),
+				      simple_card_hp_jack_pins);
+
+		simple_card_hp_jack_gpio.gpio = priv->gpio_hp_det;
+		snd_soc_jack_add_gpios(&simple_card_hp_jack, 1,
+				       &simple_card_hp_jack_gpio);
+	}
+
+	if (gpio_is_valid(priv->gpio_mic_det)) {
+		snd_soc_jack_new(codec->codec, "Mic Jack", SND_JACK_MICROPHONE,
+				 &simple_card_mic_jack);
+		snd_soc_jack_add_pins(&simple_card_mic_jack,
+				      ARRAY_SIZE(simple_card_mic_jack_pins),
+				      simple_card_mic_jack_pins);
+		simple_card_mic_jack_gpio.gpio = priv->gpio_mic_det;
+		snd_soc_jack_add_gpios(&simple_card_mic_jack, 1,
+				       &simple_card_mic_jack_gpio);
+	}
 	return 0;
 }
 
 static int
 asoc_simple_card_sub_parse_of(struct device_node *np,
 			      struct asoc_simple_dai *dai,
-			      const struct device_node **p_node,
-			      const char **name)
+			      struct device_node **p_node,
+			      const char **name,
+			      int *args_count)
 {
-	struct device_node *node;
+	struct of_phandle_args args;
 	struct clk *clk;
 	u32 val;
 	int ret;
 
 	/*
-	 * get node via "sound-dai = <&phandle port>"
+	 * Get node via "sound-dai = <&phandle port>"
 	 * it will be used as xxx_of_node on soc_bind_dai_link()
 	 */
-	node = of_parse_phandle(np, "sound-dai", 0);
-	if (!node)
-		return -ENODEV;
-	*p_node = node;
+	ret = of_parse_phandle_with_args(np, "sound-dai",
+					 "#sound-dai-cells", 0, &args);
+	if (ret)
+		return ret;
+
+	*p_node = args.np;
+
+	if (args_count)
+		*args_count = args.args_count;
 
-	/* get dai->name */
+	/* Get dai->name */
 	ret = snd_soc_of_get_dai_name(np, name);
 	if (ret < 0)
 		return ret;
 
-	/* parse TDM slot */
+	/* Parse TDM slot */
 	ret = snd_soc_of_parse_tdm_slot(np, &dai->slots, &dai->slot_width);
 	if (ret)
 		return ret;
 
 	/*
-	 * dai->sysclk come from
-	 *  "clocks = <&xxx>" (if system has common clock)
+	 * Parse dai->sysclk come from "clocks = <&xxx>"
+	 * (if system has common clock)
 	 *  or "system-clock-frequency = <xxx>"
 	 *  or device's module clock.
 	 */
@@ -155,7 +218,7 @@ asoc_simple_card_sub_parse_of(struct device_node *np,
 	} else if (!of_property_read_u32(np, "system-clock-frequency", &val)) {
 		dai->sysclk = val;
 	} else {
-		clk = of_clk_get(node, 0);
+		clk = of_clk_get(args.np, 0);
 		if (!IS_ERR(clk))
 			dai->sysclk = clk_get_rate(clk);
 	}
@@ -163,12 +226,14 @@ asoc_simple_card_sub_parse_of(struct device_node *np,
 	return 0;
 }
 
-static int simple_card_dai_link_of(struct device_node *node,
-				   struct device *dev,
-				   struct snd_soc_dai_link *dai_link,
-				   struct simple_dai_props *dai_props,
-				   bool is_top_level_node)
+static int asoc_simple_card_dai_link_of(struct device_node *node,
+					struct simple_card_data *priv,
+					int idx,
+					bool is_top_level_node)
 {
+	struct device *dev = simple_priv_to_dev(priv);
+	struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, idx);
+	struct simple_dai_props *dai_props = simple_priv_to_props(priv, idx);
 	struct device_node *np = NULL;
 	struct device_node *bitclkmaster = NULL;
 	struct device_node *framemaster = NULL;
@@ -176,8 +241,9 @@ static int simple_card_dai_link_of(struct device_node *node,
 	char *name;
 	char prop[128];
 	char *prefix = "";
-	int ret;
+	int ret, cpu_args;
 
+	/* For single DAI link & old style of DT node */
 	if (is_top_level_node)
 		prefix = "simple-audio-card,";
 
@@ -195,7 +261,8 @@ static int simple_card_dai_link_of(struct device_node *node,
 
 	ret = asoc_simple_card_sub_parse_of(np, &dai_props->cpu_dai,
 					    &dai_link->cpu_of_node,
-					    &dai_link->cpu_dai_name);
+					    &dai_link->cpu_dai_name,
+					    &cpu_args);
 	if (ret < 0)
 		goto dai_link_of_err;
 
@@ -226,14 +293,16 @@ static int simple_card_dai_link_of(struct device_node *node,
 
 	ret = asoc_simple_card_sub_parse_of(np, &dai_props->codec_dai,
 					    &dai_link->codec_of_node,
-					    &dai_link->codec_dai_name);
+					    &dai_link->codec_dai_name, NULL);
 	if (ret < 0)
 		goto dai_link_of_err;
 
 	if (strlen(prefix) && !bitclkmaster && !framemaster) {
-		/* No dai-link level and master setting was not found from
-		   sound node level, revert back to legacy DT parsing and
-		   take the settings from codec node. */
+		/*
+		 * No DAI link level and master setting was found
+		 * from sound node level, revert back to legacy DT
+		 * parsing and take the settings from codec node.
+		 */
 		dev_dbg(dev, "%s: Revert to legacy daifmt parsing\n",
 			__func__);
 		dai_props->cpu_dai.fmt = dai_props->codec_dai.fmt =
@@ -262,10 +331,10 @@ static int simple_card_dai_link_of(struct device_node *node,
 		goto dai_link_of_err;
 	}
 
-	/* simple-card assumes platform == cpu */
+	/* Simple Card assumes platform == cpu */
 	dai_link->platform_of_node = dai_link->cpu_of_node;
 
-	/* Link name is created from CPU/CODEC dai name */
+	/* DAI link name is created from CPU/CODEC dai name */
 	name = devm_kzalloc(dev,
 			    strlen(dai_link->cpu_dai_name)   +
 			    strlen(dai_link->codec_dai_name) + 2,
@@ -274,6 +343,7 @@ static int simple_card_dai_link_of(struct device_node *node,
 				dai_link->codec_dai_name);
 	dai_link->name = dai_link->stream_name = name;
 	dai_link->ops = &asoc_simple_card_ops;
+	dai_link->init = asoc_simple_card_dai_init;
 
 	dev_dbg(dev, "\tname : %s\n", dai_link->stream_name);
 	dev_dbg(dev, "\tcpu : %s / %04x / %d\n",
@@ -285,6 +355,18 @@ static int simple_card_dai_link_of(struct device_node *node,
 		dai_props->codec_dai.fmt,
 		dai_props->codec_dai.sysclk);
 
+	/*
+	 * In soc_bind_dai_link() will check cpu name after
+	 * of_node matching if dai_link has cpu_dai_name.
+	 * but, it will never match if name was created by
+	 * fmt_single_name() remove cpu_dai_name if cpu_args
+	 * was 0. See:
+	 *	fmt_single_name()
+	 *	fmt_multiple_name()
+	 */
+	if (!cpu_args)
+		dai_link->cpu_dai_name = NULL;
+
 dai_link_of_err:
 	if (np)
 		of_node_put(np);
@@ -296,19 +378,19 @@ dai_link_of_err:
 }
 
 static int asoc_simple_card_parse_of(struct device_node *node,
-				     struct simple_card_data *priv,
-				     struct device *dev,
-				     int multi)
+				     struct simple_card_data *priv)
 {
-	struct snd_soc_dai_link *dai_link = priv->snd_card.dai_link;
-	struct simple_dai_props *dai_props = priv->dai_props;
+	struct device *dev = simple_priv_to_dev(priv);
 	u32 val;
 	int ret;
 
-	/* parsing the card name from DT */
+	if (!node)
+		return -EINVAL;
+
+	/* Parse the card name from DT */
 	snd_soc_of_parse_card_name(&priv->snd_card, "simple-audio-card,name");
 
-	/* off-codec widgets */
+	/* The off-codec widgets */
 	if (of_property_read_bool(node, "simple-audio-card,widgets")) {
 		ret = snd_soc_of_parse_audio_simple_widgets(&priv->snd_card,
 					"simple-audio-card,widgets");
@@ -332,32 +414,45 @@ static int asoc_simple_card_parse_of(struct device_node *node,
 	dev_dbg(dev, "New simple-card: %s\n", priv->snd_card.name ?
 		priv->snd_card.name : "");
 
-	if (multi) {
+	/* Single/Muti DAI link(s) & New style of DT node */
+	if (of_get_child_by_name(node, "simple-audio-card,dai-link")) {
 		struct device_node *np = NULL;
-		int i;
-		for (i = 0; (np = of_get_next_child(node, np)); i++) {
+		int i = 0;
+
+		for_each_child_of_node(node, np) {
 			dev_dbg(dev, "\tlink %d:\n", i);
-			ret = simple_card_dai_link_of(np, dev, dai_link + i,
-						      dai_props + i, false);
+			ret = asoc_simple_card_dai_link_of(np, priv,
+							   i, false);
 			if (ret < 0) {
 				of_node_put(np);
 				return ret;
 			}
+			i++;
 		}
 	} else {
-		ret = simple_card_dai_link_of(node, dev, dai_link, dai_props,
-					      true);
+		/* For single DAI link & old style of DT node */
+		ret = asoc_simple_card_dai_link_of(node, priv, 0, true);
 		if (ret < 0)
 			return ret;
 	}
 
+	priv->gpio_hp_det = of_get_named_gpio(node,
+				"simple-audio-card,hp-det-gpio", 0);
+	if (priv->gpio_hp_det == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
+	priv->gpio_mic_det = of_get_named_gpio(node,
+				"simple-audio-card,mic-det-gpio", 0);
+	if (priv->gpio_mic_det == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
 	if (!priv->snd_card.name)
 		priv->snd_card.name = priv->snd_card.dai_link->name;
 
 	return 0;
 }
 
-/* update the reference count of the devices nodes at end of probe */
+/* Decrease the reference count of the device nodes */
 static int asoc_simple_card_unref(struct platform_device *pdev)
 {
 	struct snd_soc_card *card = platform_get_drvdata(pdev);
@@ -384,34 +479,32 @@ static int asoc_simple_card_probe(struct platform_device *pdev)
 	struct snd_soc_dai_link *dai_link;
 	struct device_node *np = pdev->dev.of_node;
 	struct device *dev = &pdev->dev;
-	int num_links, multi, ret;
+	int num_links, ret;
 
-	/* get the number of DAI links */
-	if (np && of_get_child_by_name(np, "simple-audio-card,dai-link")) {
+	/* Get the number of DAI links */
+	if (np && of_get_child_by_name(np, "simple-audio-card,dai-link"))
 		num_links = of_get_child_count(np);
-		multi = 1;
-	} else {
+	else
 		num_links = 1;
-		multi = 0;
-	}
 
-	/* allocate the private data and the DAI link array */
+	/* Allocate the private data and the DAI link array */
 	priv = devm_kzalloc(dev,
 			sizeof(*priv) + sizeof(*dai_link) * num_links,
 			GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
-	/*
-	 * init snd_soc_card
-	 */
+	/* Init snd_soc_card */
 	priv->snd_card.owner = THIS_MODULE;
 	priv->snd_card.dev = dev;
 	dai_link = priv->dai_link;
 	priv->snd_card.dai_link = dai_link;
 	priv->snd_card.num_links = num_links;
 
-	/* get room for the other properties */
+	priv->gpio_hp_det = -ENOENT;
+	priv->gpio_mic_det = -ENOENT;
+
+	/* Get room for the other properties */
 	priv->dai_props = devm_kzalloc(dev,
 			sizeof(*priv->dai_props) * num_links,
 			GFP_KERNEL);
@@ -420,25 +513,13 @@ static int asoc_simple_card_probe(struct platform_device *pdev)
 
 	if (np && of_device_is_available(np)) {
 
-		ret = asoc_simple_card_parse_of(np, priv, dev, multi);
+		ret = asoc_simple_card_parse_of(np, priv);
 		if (ret < 0) {
 			if (ret != -EPROBE_DEFER)
 				dev_err(dev, "parse error %d\n", ret);
 			goto err;
 		}
 
-		/*
-		 * soc_bind_dai_link() will check cpu name
-		 * after of_node matching if dai_link has cpu_dai_name.
-		 * but, it will never match if name was created by fmt_single_name()
-		 * remove cpu_dai_name to escape name matching.
-		 * see
-		 *	fmt_single_name()
-		 *	fmt_multiple_name()
-		 */
-		if (num_links == 1)
-			dai_link->cpu_dai_name = NULL;
-
 	} else {
 		struct asoc_simple_card_info *cinfo;
 
@@ -464,6 +545,7 @@ static int asoc_simple_card_probe(struct platform_device *pdev)
 		dai_link->codec_name	= cinfo->codec;
 		dai_link->cpu_dai_name	= cinfo->cpu_dai.name;
 		dai_link->codec_dai_name = cinfo->codec_dai.name;
+		dai_link->init		= asoc_simple_card_dai_init;
 		memcpy(&priv->dai_props->cpu_dai, &cinfo->cpu_dai,
 					sizeof(priv->dai_props->cpu_dai));
 		memcpy(&priv->dai_props->codec_dai, &cinfo->codec_dai,
@@ -473,11 +555,6 @@ static int asoc_simple_card_probe(struct platform_device *pdev)
 		priv->dai_props->codec_dai.fmt	|= cinfo->daifmt;
 	}
 
-	/*
-	 * init snd_soc_dai_link
-	 */
-	dai_link->init = asoc_simple_card_dai_init;
-
 	snd_soc_card_set_drvdata(&priv->snd_card, priv);
 
 	ret = devm_snd_soc_register_card(&pdev->dev, &priv->snd_card);
@@ -491,6 +568,16 @@ err:
 
 static int asoc_simple_card_remove(struct platform_device *pdev)
 {
+	struct snd_soc_card *card = platform_get_drvdata(pdev);
+	struct simple_card_data *priv = snd_soc_card_get_drvdata(card);
+
+	if (gpio_is_valid(priv->gpio_hp_det))
+		snd_soc_jack_free_gpios(&simple_card_hp_jack, 1,
+					&simple_card_hp_jack_gpio);
+	if (gpio_is_valid(priv->gpio_mic_det))
+		snd_soc_jack_free_gpios(&simple_card_mic_jack, 1,
+					&simple_card_mic_jack_gpio);
+
 	return asoc_simple_card_unref(pdev);
 }
 
diff --git a/sound/soc/intel/Makefile b/sound/soc/intel/Makefile
index 7acbfc43a0c6..f841786dad15 100644
--- a/sound/soc/intel/Makefile
+++ b/sound/soc/intel/Makefile
@@ -2,7 +2,8 @@
 snd-soc-sst-dsp-objs := sst-dsp.o sst-firmware.o
 snd-soc-sst-acpi-objs := sst-acpi.o
 
-snd-soc-sst-mfld-platform-objs := sst-mfld-platform-pcm.o sst-mfld-platform-compress.o
+snd-soc-sst-mfld-platform-objs := sst-mfld-platform-pcm.o \
+	sst-mfld-platform-compress.o sst-atom-controls.o
 snd-soc-mfld-machine-objs := mfld_machine.o
 
 obj-$(CONFIG_SND_SST_MFLD_PLATFORM) += snd-soc-sst-mfld-platform.o
diff --git a/sound/soc/intel/byt-max98090.c b/sound/soc/intel/byt-max98090.c
index b8b8af571ef1..d52681e7225e 100644
--- a/sound/soc/intel/byt-max98090.c
+++ b/sound/soc/intel/byt-max98090.c
@@ -139,6 +139,7 @@ static struct snd_soc_card byt_max98090_card = {
 	.num_dapm_routes = ARRAY_SIZE(byt_max98090_audio_map),
 	.controls = byt_max98090_controls,
 	.num_controls = ARRAY_SIZE(byt_max98090_controls),
+	.fully_routed = true,
 };
 
 static int byt_max98090_probe(struct platform_device *pdev)
diff --git a/sound/soc/intel/byt-rt5640.c b/sound/soc/intel/byt-rt5640.c
index 234a58de3c53..e03abdf21c1b 100644
--- a/sound/soc/intel/byt-rt5640.c
+++ b/sound/soc/intel/byt-rt5640.c
@@ -17,6 +17,7 @@
 #include <linux/platform_device.h>
 #include <linux/acpi.h>
 #include <linux/device.h>
+#include <linux/dmi.h>
 #include <linux/slab.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -36,8 +37,6 @@ static const struct snd_soc_dapm_widget byt_rt5640_widgets[] = {
 static const struct snd_soc_dapm_route byt_rt5640_audio_map[] = {
 	{"Headset Mic", NULL, "MICBIAS1"},
 	{"IN2P", NULL, "Headset Mic"},
-	{"IN2N", NULL, "Headset Mic"},
-	{"DMIC1", NULL, "Internal Mic"},
 	{"Headphone", NULL, "HPOL"},
 	{"Headphone", NULL, "HPOR"},
 	{"Speaker", NULL, "SPOLP"},
@@ -46,6 +45,31 @@ static const struct snd_soc_dapm_route byt_rt5640_audio_map[] = {
 	{"Speaker", NULL, "SPORN"},
 };
 
+static const struct snd_soc_dapm_route byt_rt5640_intmic_dmic1_map[] = {
+	{"DMIC1", NULL, "Internal Mic"},
+};
+
+static const struct snd_soc_dapm_route byt_rt5640_intmic_dmic2_map[] = {
+	{"DMIC2", NULL, "Internal Mic"},
+};
+
+static const struct snd_soc_dapm_route byt_rt5640_intmic_in1_map[] = {
+	{"Internal Mic", NULL, "MICBIAS1"},
+	{"IN1P", NULL, "Internal Mic"},
+};
+
+enum {
+	BYT_RT5640_DMIC1_MAP,
+	BYT_RT5640_DMIC2_MAP,
+	BYT_RT5640_IN1_MAP,
+};
+
+#define BYT_RT5640_MAP(quirk)	((quirk) & 0xff)
+#define BYT_RT5640_DMIC_EN	BIT(16)
+
+static unsigned long byt_rt5640_quirk = BYT_RT5640_DMIC1_MAP |
+					BYT_RT5640_DMIC_EN;
+
 static const struct snd_kcontrol_new byt_rt5640_controls[] = {
 	SOC_DAPM_PIN_SWITCH("Headphone"),
 	SOC_DAPM_PIN_SWITCH("Headset Mic"),
@@ -77,12 +101,41 @@ static int byt_rt5640_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
+static int byt_rt5640_quirk_cb(const struct dmi_system_id *id)
+{
+	byt_rt5640_quirk = (unsigned long)id->driver_data;
+	return 1;
+}
+
+static const struct dmi_system_id byt_rt5640_quirk_table[] = {
+	{
+		.callback = byt_rt5640_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "T100TA"),
+		},
+		.driver_data = (unsigned long *)BYT_RT5640_IN1_MAP,
+	},
+	{
+		.callback = byt_rt5640_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "DellInc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Venue 8 Pro 5830"),
+		},
+		.driver_data = (unsigned long *)(BYT_RT5640_DMIC2_MAP |
+						 BYT_RT5640_DMIC_EN),
+	},
+	{}
+};
+
 static int byt_rt5640_init(struct snd_soc_pcm_runtime *runtime)
 {
 	int ret;
 	struct snd_soc_codec *codec = runtime->codec;
 	struct snd_soc_dapm_context *dapm = &codec->dapm;
 	struct snd_soc_card *card = runtime->card;
+	const struct snd_soc_dapm_route *custom_map;
+	int num_routes;
 
 	card->dapm.idle_bias_off = true;
 
@@ -93,6 +146,31 @@ static int byt_rt5640_init(struct snd_soc_pcm_runtime *runtime)
 		return ret;
 	}
 
+	dmi_check_system(byt_rt5640_quirk_table);
+	switch (BYT_RT5640_MAP(byt_rt5640_quirk)) {
+	case BYT_RT5640_IN1_MAP:
+		custom_map = byt_rt5640_intmic_in1_map;
+		num_routes = ARRAY_SIZE(byt_rt5640_intmic_in1_map);
+		break;
+	case BYT_RT5640_DMIC2_MAP:
+		custom_map = byt_rt5640_intmic_dmic2_map;
+		num_routes = ARRAY_SIZE(byt_rt5640_intmic_dmic2_map);
+		break;
+	default:
+		custom_map = byt_rt5640_intmic_dmic1_map;
+		num_routes = ARRAY_SIZE(byt_rt5640_intmic_dmic1_map);
+	}
+
+	ret = snd_soc_dapm_add_routes(dapm, custom_map, num_routes);
+	if (ret)
+		return ret;
+
+	if (byt_rt5640_quirk & BYT_RT5640_DMIC_EN) {
+		ret = rt5640_dmic_enable(codec, 0, 0);
+		if (ret)
+			return ret;
+	}
+
 	snd_soc_dapm_ignore_suspend(dapm, "HPOL");
 	snd_soc_dapm_ignore_suspend(dapm, "HPOR");
 
@@ -131,6 +209,7 @@ static struct snd_soc_card byt_rt5640_card = {
 	.num_dapm_widgets = ARRAY_SIZE(byt_rt5640_widgets),
 	.dapm_routes = byt_rt5640_audio_map,
 	.num_dapm_routes = ARRAY_SIZE(byt_rt5640_audio_map),
+	.fully_routed = true,
 };
 
 static int byt_rt5640_probe(struct platform_device *pdev)
diff --git a/sound/soc/intel/sst-atom-controls.c b/sound/soc/intel/sst-atom-controls.c
new file mode 100644
index 000000000000..7104a34181a9
--- /dev/null
+++ b/sound/soc/intel/sst-atom-controls.c
@@ -0,0 +1,218 @@
+/*
+ *  sst-atom-controls.c - Intel MID Platform driver DPCM ALSA controls for Mrfld
+ *
+ *  Copyright (C) 2013-14 Intel Corp
+ *  Author: Omair Mohammed Abdullah <omair.m.abdullah@intel.com>
+ *	Vinod Koul <vinod.koul@intel.com>
+ *  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#include <sound/soc.h>
+#include <sound/tlv.h>
+#include "sst-mfld-platform.h"
+#include "sst-atom-controls.h"
+
+static int sst_fill_byte_control(struct sst_data *drv,
+					 u8 ipc_msg, u8 block,
+					 u8 task_id, u8 pipe_id,
+					 u16 len, void *cmd_data)
+{
+	struct snd_sst_bytes_v2 *byte_data = drv->byte_stream;
+
+	byte_data->type = SST_CMD_BYTES_SET;
+	byte_data->ipc_msg = ipc_msg;
+	byte_data->block = block;
+	byte_data->task_id = task_id;
+	byte_data->pipe_id = pipe_id;
+
+	if (len > SST_MAX_BIN_BYTES - sizeof(*byte_data)) {
+		dev_err(&drv->pdev->dev, "command length too big (%u)", len);
+		return -EINVAL;
+	}
+	byte_data->len = len;
+	memcpy(byte_data->bytes, cmd_data, len);
+	print_hex_dump_bytes("writing to lpe: ", DUMP_PREFIX_OFFSET,
+			     byte_data, len + sizeof(*byte_data));
+	return 0;
+}
+
+static int sst_fill_and_send_cmd_unlocked(struct sst_data *drv,
+				 u8 ipc_msg, u8 block, u8 task_id, u8 pipe_id,
+				 void *cmd_data, u16 len)
+{
+	int ret = 0;
+
+	ret = sst_fill_byte_control(drv, ipc_msg,
+				block, task_id, pipe_id, len, cmd_data);
+	if (ret < 0)
+		return ret;
+	return sst->ops->send_byte_stream(sst->dev, drv->byte_stream);
+}
+
+/**
+ * sst_fill_and_send_cmd - generate the IPC message and send it to the FW
+ * @ipc_msg:	type of IPC (CMD, SET_PARAMS, GET_PARAMS)
+ * @cmd_data:	the IPC payload
+ */
+static int sst_fill_and_send_cmd(struct sst_data *drv,
+				 u8 ipc_msg, u8 block, u8 task_id, u8 pipe_id,
+				 void *cmd_data, u16 len)
+{
+	int ret;
+
+	mutex_lock(&drv->lock);
+	ret = sst_fill_and_send_cmd_unlocked(drv, ipc_msg, block,
+					task_id, pipe_id, cmd_data, len);
+	mutex_unlock(&drv->lock);
+
+	return ret;
+}
+
+static int sst_send_algo_cmd(struct sst_data *drv,
+			      struct sst_algo_control *bc)
+{
+	int len, ret = 0;
+	struct sst_cmd_set_params *cmd;
+
+	/*bc->max includes sizeof algos + length field*/
+	len = sizeof(cmd->dst) + sizeof(cmd->command_id) + bc->max;
+
+	cmd = kzalloc(len, GFP_KERNEL);
+	if (cmd == NULL)
+		return -ENOMEM;
+
+	SST_FILL_DESTINATION(2, cmd->dst, bc->pipe_id, bc->module_id);
+	cmd->command_id = bc->cmd_id;
+	memcpy(cmd->params, bc->params, bc->max);
+
+	ret = sst_fill_and_send_cmd_unlocked(drv, SST_IPC_IA_SET_PARAMS,
+				SST_FLAG_BLOCKED, bc->task_id, 0, cmd, len);
+	kfree(cmd);
+	return ret;
+}
+
+static int sst_algo_bytes_ctl_info(struct snd_kcontrol *kcontrol,
+			    struct snd_ctl_elem_info *uinfo)
+{
+	struct sst_algo_control *bc = (void *)kcontrol->private_value;
+
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_BYTES;
+	uinfo->count = bc->max;
+
+	return 0;
+}
+
+static int sst_algo_control_get(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct sst_algo_control *bc = (void *)kcontrol->private_value;
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+
+	switch (bc->type) {
+	case SST_ALGO_PARAMS:
+		memcpy(ucontrol->value.bytes.data, bc->params, bc->max);
+		break;
+	default:
+		dev_err(component->dev, "Invalid Input- algo type:%d\n",
+				bc->type);
+		return -EINVAL;
+
+	}
+	return 0;
+}
+
+static int sst_algo_control_set(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	int ret = 0;
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct sst_data *drv = snd_soc_component_get_drvdata(cmpnt);
+	struct sst_algo_control *bc = (void *)kcontrol->private_value;
+
+	dev_dbg(cmpnt->dev, "control_name=%s\n", kcontrol->id.name);
+	mutex_lock(&drv->lock);
+	switch (bc->type) {
+	case SST_ALGO_PARAMS:
+		memcpy(bc->params, ucontrol->value.bytes.data, bc->max);
+		break;
+	default:
+		mutex_unlock(&drv->lock);
+		dev_err(cmpnt->dev, "Invalid Input- algo type:%d\n",
+				bc->type);
+		return -EINVAL;
+	}
+	/*if pipe is enabled, need to send the algo params from here*/
+	if (bc->w && bc->w->power)
+		ret = sst_send_algo_cmd(drv, bc);
+	mutex_unlock(&drv->lock);
+
+	return ret;
+}
+
+static const struct snd_kcontrol_new sst_algo_controls[] = {
+	SST_ALGO_KCONTROL_BYTES("media_loop1_out", "fir", 272, SST_MODULE_ID_FIR_24,
+		 SST_PATH_INDEX_MEDIA_LOOP1_OUT, 0, SST_TASK_SBA, SBA_VB_SET_FIR),
+	SST_ALGO_KCONTROL_BYTES("media_loop1_out", "iir", 300, SST_MODULE_ID_IIR_24,
+		SST_PATH_INDEX_MEDIA_LOOP1_OUT, 0, SST_TASK_SBA, SBA_VB_SET_IIR),
+	SST_ALGO_KCONTROL_BYTES("media_loop1_out", "mdrp", 286, SST_MODULE_ID_MDRP,
+		SST_PATH_INDEX_MEDIA_LOOP1_OUT, 0, SST_TASK_SBA, SBA_SET_MDRP),
+	SST_ALGO_KCONTROL_BYTES("media_loop2_out", "fir", 272, SST_MODULE_ID_FIR_24,
+		SST_PATH_INDEX_MEDIA_LOOP2_OUT, 0, SST_TASK_SBA, SBA_VB_SET_FIR),
+	SST_ALGO_KCONTROL_BYTES("media_loop2_out", "iir", 300, SST_MODULE_ID_IIR_24,
+		SST_PATH_INDEX_MEDIA_LOOP2_OUT, 0, SST_TASK_SBA, SBA_VB_SET_IIR),
+	SST_ALGO_KCONTROL_BYTES("media_loop2_out", "mdrp", 286, SST_MODULE_ID_MDRP,
+		SST_PATH_INDEX_MEDIA_LOOP2_OUT, 0, SST_TASK_SBA, SBA_SET_MDRP),
+	SST_ALGO_KCONTROL_BYTES("sprot_loop_out", "lpro", 192, SST_MODULE_ID_SPROT,
+		SST_PATH_INDEX_SPROT_LOOP_OUT, 0, SST_TASK_SBA, SBA_VB_LPRO),
+	SST_ALGO_KCONTROL_BYTES("codec_in0", "dcr", 52, SST_MODULE_ID_FILT_DCR,
+		SST_PATH_INDEX_CODEC_IN0, 0, SST_TASK_SBA, SBA_VB_SET_IIR),
+	SST_ALGO_KCONTROL_BYTES("codec_in1", "dcr", 52, SST_MODULE_ID_FILT_DCR,
+		SST_PATH_INDEX_CODEC_IN1, 0, SST_TASK_SBA, SBA_VB_SET_IIR),
+
+};
+
+static int sst_algo_control_init(struct device *dev)
+{
+	int i = 0;
+	struct sst_algo_control *bc;
+	/*allocate space to cache the algo parameters in the driver*/
+	for (i = 0; i < ARRAY_SIZE(sst_algo_controls); i++) {
+		bc = (struct sst_algo_control *)sst_algo_controls[i].private_value;
+		bc->params = devm_kzalloc(dev, bc->max, GFP_KERNEL);
+		if (bc->params == NULL)
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+int sst_dsp_init_v2_dpcm(struct snd_soc_platform *platform)
+{
+	int ret = 0;
+	struct sst_data *drv = snd_soc_platform_get_drvdata(platform);
+
+	drv->byte_stream = devm_kzalloc(platform->dev,
+					SST_MAX_BIN_BYTES, GFP_KERNEL);
+	if (!drv->byte_stream)
+		return -ENOMEM;
+
+	/*Initialize algo control params*/
+	ret = sst_algo_control_init(platform->dev);
+	if (ret)
+		return ret;
+	ret = snd_soc_add_platform_controls(platform, sst_algo_controls,
+			ARRAY_SIZE(sst_algo_controls));
+	return ret;
+}
diff --git a/sound/soc/intel/sst-atom-controls.h b/sound/soc/intel/sst-atom-controls.h
index 14063ab8c7c5..a73e894b175c 100644
--- a/sound/soc/intel/sst-atom-controls.h
+++ b/sound/soc/intel/sst-atom-controls.h
@@ -1,4 +1,6 @@
 /*
+ *  sst-atom-controls.h - Intel MID Platform driver header file
+ *
  *  Copyright (C) 2013-14 Intel Corp
  *  Author: Ramesh Babu <ramesh.babu.koul@intel.com>
  *  	Omair M Abdullah <omair.m.abdullah@intel.com>
@@ -18,13 +20,423 @@
  *
  */
 
-#ifndef __SST_CONTROLS_V2_H__
-#define __SST_CONTROLS_V2_H__
+#ifndef __SST_ATOM_CONTROLS_H__
+#define __SST_ATOM_CONTROLS_H__
 
 enum {
 	MERR_DPCM_AUDIO = 0,
 	MERR_DPCM_COMPR,
 };
 
+/* define a bit for each mixer input */
+#define SST_MIX_IP(x)		(x)
+
+#define SST_IP_CODEC0		SST_MIX_IP(2)
+#define SST_IP_CODEC1		SST_MIX_IP(3)
+#define SST_IP_LOOP0		SST_MIX_IP(4)
+#define SST_IP_LOOP1		SST_MIX_IP(5)
+#define SST_IP_LOOP2		SST_MIX_IP(6)
+#define SST_IP_PROBE		SST_MIX_IP(7)
+#define SST_IP_VOIP		SST_MIX_IP(12)
+#define SST_IP_PCM0		SST_MIX_IP(13)
+#define SST_IP_PCM1		SST_MIX_IP(14)
+#define SST_IP_MEDIA0		SST_MIX_IP(17)
+#define SST_IP_MEDIA1		SST_MIX_IP(18)
+#define SST_IP_MEDIA2		SST_MIX_IP(19)
+#define SST_IP_MEDIA3		SST_MIX_IP(20)
+
+#define SST_IP_LAST		SST_IP_MEDIA3
+
+#define SST_SWM_INPUT_COUNT	(SST_IP_LAST + 1)
+#define SST_CMD_SWM_MAX_INPUTS	6
+
+#define SST_PATH_ID_SHIFT	8
+#define SST_DEFAULT_LOCATION_ID	0xFFFF
+#define SST_DEFAULT_CELL_NBR	0xFF
+#define SST_DEFAULT_MODULE_ID	0xFFFF
+
+/*
+ * Audio DSP Path Ids. Specified by the audio DSP FW
+ */
+enum sst_path_index {
+	SST_PATH_INDEX_CODEC_OUT0               = (0x02 << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_CODEC_OUT1               = (0x03 << SST_PATH_ID_SHIFT),
+
+	SST_PATH_INDEX_SPROT_LOOP_OUT           = (0x04 << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_MEDIA_LOOP1_OUT          = (0x05 << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_MEDIA_LOOP2_OUT          = (0x06 << SST_PATH_ID_SHIFT),
+
+	SST_PATH_INDEX_VOIP_OUT                 = (0x0C << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_PCM0_OUT                 = (0x0D << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_PCM1_OUT                 = (0x0E << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_PCM2_OUT                 = (0x0F << SST_PATH_ID_SHIFT),
+
+	SST_PATH_INDEX_MEDIA0_OUT               = (0x12 << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_MEDIA1_OUT               = (0x13 << SST_PATH_ID_SHIFT),
+
+
+	/* Start of input paths */
+	SST_PATH_INDEX_CODEC_IN0                = (0x82 << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_CODEC_IN1                = (0x83 << SST_PATH_ID_SHIFT),
+
+	SST_PATH_INDEX_SPROT_LOOP_IN            = (0x84 << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_MEDIA_LOOP1_IN           = (0x85 << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_MEDIA_LOOP2_IN           = (0x86 << SST_PATH_ID_SHIFT),
+
+	SST_PATH_INDEX_VOIP_IN                  = (0x8C << SST_PATH_ID_SHIFT),
+
+	SST_PATH_INDEX_PCM0_IN                  = (0x8D << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_PCM1_IN                  = (0x8E << SST_PATH_ID_SHIFT),
+
+	SST_PATH_INDEX_MEDIA0_IN                = (0x8F << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_MEDIA1_IN                = (0x90 << SST_PATH_ID_SHIFT),
+	SST_PATH_INDEX_MEDIA2_IN                = (0x91 << SST_PATH_ID_SHIFT),
+
+	SST_PATH_INDEX_MEDIA3_IN		= (0x9C << SST_PATH_ID_SHIFT),
+
+	SST_PATH_INDEX_RESERVED                 = (0xFF << SST_PATH_ID_SHIFT),
+};
+
+/*
+ * path IDs
+ */
+enum sst_swm_inputs {
+	SST_SWM_IN_CODEC0	= (SST_PATH_INDEX_CODEC_IN0	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_IN_CODEC1	= (SST_PATH_INDEX_CODEC_IN1	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_IN_SPROT_LOOP	= (SST_PATH_INDEX_SPROT_LOOP_IN	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_IN_MEDIA_LOOP1	= (SST_PATH_INDEX_MEDIA_LOOP1_IN  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_IN_MEDIA_LOOP2	= (SST_PATH_INDEX_MEDIA_LOOP2_IN  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_IN_VOIP		= (SST_PATH_INDEX_VOIP_IN	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_IN_PCM0		= (SST_PATH_INDEX_PCM0_IN	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_IN_PCM1		= (SST_PATH_INDEX_PCM1_IN	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_IN_MEDIA0	= (SST_PATH_INDEX_MEDIA0_IN	  | SST_DEFAULT_CELL_NBR), /* Part of Media Mixer */
+	SST_SWM_IN_MEDIA1	= (SST_PATH_INDEX_MEDIA1_IN	  | SST_DEFAULT_CELL_NBR), /* Part of Media Mixer */
+	SST_SWM_IN_MEDIA2	= (SST_PATH_INDEX_MEDIA2_IN	  | SST_DEFAULT_CELL_NBR), /* Part of Media Mixer */
+	SST_SWM_IN_MEDIA3	= (SST_PATH_INDEX_MEDIA3_IN	  | SST_DEFAULT_CELL_NBR), /* Part of Media Mixer */
+	SST_SWM_IN_END		= (SST_PATH_INDEX_RESERVED	  | SST_DEFAULT_CELL_NBR)
+};
+
+/*
+ * path IDs
+ */
+enum sst_swm_outputs {
+	SST_SWM_OUT_CODEC0	= (SST_PATH_INDEX_CODEC_OUT0	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_OUT_CODEC1	= (SST_PATH_INDEX_CODEC_OUT1	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_OUT_SPROT_LOOP	= (SST_PATH_INDEX_SPROT_LOOP_OUT  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_OUT_MEDIA_LOOP1	= (SST_PATH_INDEX_MEDIA_LOOP1_OUT | SST_DEFAULT_CELL_NBR),
+	SST_SWM_OUT_MEDIA_LOOP2	= (SST_PATH_INDEX_MEDIA_LOOP2_OUT | SST_DEFAULT_CELL_NBR),
+	SST_SWM_OUT_VOIP	= (SST_PATH_INDEX_VOIP_OUT	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_OUT_PCM0	= (SST_PATH_INDEX_PCM0_OUT	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_OUT_PCM1	= (SST_PATH_INDEX_PCM1_OUT	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_OUT_PCM2	= (SST_PATH_INDEX_PCM2_OUT	  | SST_DEFAULT_CELL_NBR),
+	SST_SWM_OUT_MEDIA0	= (SST_PATH_INDEX_MEDIA0_OUT	  | SST_DEFAULT_CELL_NBR), /* Part of Media Mixer */
+	SST_SWM_OUT_MEDIA1	= (SST_PATH_INDEX_MEDIA1_OUT	  | SST_DEFAULT_CELL_NBR), /* Part of Media Mixer */
+	SST_SWM_OUT_END		= (SST_PATH_INDEX_RESERVED	  | SST_DEFAULT_CELL_NBR),
+};
+
+enum sst_ipc_msg {
+	SST_IPC_IA_CMD = 1,
+	SST_IPC_IA_SET_PARAMS,
+	SST_IPC_IA_GET_PARAMS,
+};
+
+enum sst_cmd_type {
+	SST_CMD_BYTES_SET = 1,
+	SST_CMD_BYTES_GET = 2,
+};
+
+enum sst_task {
+	SST_TASK_SBA = 1,
+	SST_TASK_MMX,
+};
+
+enum sst_type {
+	SST_TYPE_CMD = 1,
+	SST_TYPE_PARAMS,
+};
+
+enum sst_flag {
+	SST_FLAG_BLOCKED = 1,
+	SST_FLAG_NONBLOCK,
+};
+
+/*
+ * Enumeration for indexing the gain cells in VB_SET_GAIN DSP command
+ */
+enum sst_gain_index {
+	/* GAIN IDs for SB task start here */
+	SST_GAIN_INDEX_CODEC_OUT0,
+	SST_GAIN_INDEX_CODEC_OUT1,
+	SST_GAIN_INDEX_CODEC_IN0,
+	SST_GAIN_INDEX_CODEC_IN1,
+
+	SST_GAIN_INDEX_SPROT_LOOP_OUT,
+	SST_GAIN_INDEX_MEDIA_LOOP1_OUT,
+	SST_GAIN_INDEX_MEDIA_LOOP2_OUT,
+
+	SST_GAIN_INDEX_PCM0_IN_LEFT,
+	SST_GAIN_INDEX_PCM0_IN_RIGHT,
+
+	SST_GAIN_INDEX_PCM1_OUT_LEFT,
+	SST_GAIN_INDEX_PCM1_OUT_RIGHT,
+	SST_GAIN_INDEX_PCM1_IN_LEFT,
+	SST_GAIN_INDEX_PCM1_IN_RIGHT,
+	SST_GAIN_INDEX_PCM2_OUT_LEFT,
+
+	SST_GAIN_INDEX_PCM2_OUT_RIGHT,
+	SST_GAIN_INDEX_VOIP_OUT,
+	SST_GAIN_INDEX_VOIP_IN,
+
+	/* Gain IDs for MMX task start here */
+	SST_GAIN_INDEX_MEDIA0_IN_LEFT,
+	SST_GAIN_INDEX_MEDIA0_IN_RIGHT,
+	SST_GAIN_INDEX_MEDIA1_IN_LEFT,
+	SST_GAIN_INDEX_MEDIA1_IN_RIGHT,
+
+	SST_GAIN_INDEX_MEDIA2_IN_LEFT,
+	SST_GAIN_INDEX_MEDIA2_IN_RIGHT,
+
+	SST_GAIN_INDEX_GAIN_END
+};
+
+/*
+ * Audio DSP module IDs specified by FW spec
+ * TODO: Update with all modules
+ */
+enum sst_module_id {
+	SST_MODULE_ID_PCM		  = 0x0001,
+	SST_MODULE_ID_MP3		  = 0x0002,
+	SST_MODULE_ID_MP24		  = 0x0003,
+	SST_MODULE_ID_AAC		  = 0x0004,
+	SST_MODULE_ID_AACP		  = 0x0005,
+	SST_MODULE_ID_EAACP		  = 0x0006,
+	SST_MODULE_ID_WMA9		  = 0x0007,
+	SST_MODULE_ID_WMA10		  = 0x0008,
+	SST_MODULE_ID_WMA10P		  = 0x0009,
+	SST_MODULE_ID_RA		  = 0x000A,
+	SST_MODULE_ID_DDAC3		  = 0x000B,
+	SST_MODULE_ID_TRUE_HD		  = 0x000C,
+	SST_MODULE_ID_HD_PLUS		  = 0x000D,
+
+	SST_MODULE_ID_SRC		  = 0x0064,
+	SST_MODULE_ID_DOWNMIX		  = 0x0066,
+	SST_MODULE_ID_GAIN_CELL		  = 0x0067,
+	SST_MODULE_ID_SPROT		  = 0x006D,
+	SST_MODULE_ID_BASS_BOOST	  = 0x006E,
+	SST_MODULE_ID_STEREO_WDNG	  = 0x006F,
+	SST_MODULE_ID_AV_REMOVAL	  = 0x0070,
+	SST_MODULE_ID_MIC_EQ		  = 0x0071,
+	SST_MODULE_ID_SPL		  = 0x0072,
+	SST_MODULE_ID_ALGO_VTSV           = 0x0073,
+	SST_MODULE_ID_NR		  = 0x0076,
+	SST_MODULE_ID_BWX		  = 0x0077,
+	SST_MODULE_ID_DRP		  = 0x0078,
+	SST_MODULE_ID_MDRP		  = 0x0079,
+
+	SST_MODULE_ID_ANA		  = 0x007A,
+	SST_MODULE_ID_AEC		  = 0x007B,
+	SST_MODULE_ID_NR_SNS		  = 0x007C,
+	SST_MODULE_ID_SER		  = 0x007D,
+	SST_MODULE_ID_AGC		  = 0x007E,
+
+	SST_MODULE_ID_CNI		  = 0x007F,
+	SST_MODULE_ID_CONTEXT_ALGO_AWARE  = 0x0080,
+	SST_MODULE_ID_FIR_24		  = 0x0081,
+	SST_MODULE_ID_IIR_24		  = 0x0082,
+
+	SST_MODULE_ID_ASRC		  = 0x0083,
+	SST_MODULE_ID_TONE_GEN		  = 0x0084,
+	SST_MODULE_ID_BMF		  = 0x0086,
+	SST_MODULE_ID_EDL		  = 0x0087,
+	SST_MODULE_ID_GLC		  = 0x0088,
+
+	SST_MODULE_ID_FIR_16		  = 0x0089,
+	SST_MODULE_ID_IIR_16		  = 0x008A,
+	SST_MODULE_ID_DNR		  = 0x008B,
+
+	SST_MODULE_ID_VIRTUALIZER	  = 0x008C,
+	SST_MODULE_ID_VISUALIZATION	  = 0x008D,
+	SST_MODULE_ID_LOUDNESS_OPTIMIZER  = 0x008E,
+	SST_MODULE_ID_REVERBERATION	  = 0x008F,
+
+	SST_MODULE_ID_CNI_TX		  = 0x0090,
+	SST_MODULE_ID_REF_LINE		  = 0x0091,
+	SST_MODULE_ID_VOLUME		  = 0x0092,
+	SST_MODULE_ID_FILT_DCR		  = 0x0094,
+	SST_MODULE_ID_SLV		  = 0x009A,
+	SST_MODULE_ID_NLF		  = 0x009B,
+	SST_MODULE_ID_TNR		  = 0x009C,
+	SST_MODULE_ID_WNR		  = 0x009D,
+
+	SST_MODULE_ID_LOG		  = 0xFF00,
+
+	SST_MODULE_ID_TASK		  = 0xFFFF,
+};
+
+enum sst_cmd {
+	SBA_IDLE		= 14,
+	SBA_VB_SET_SPEECH_PATH	= 26,
+	MMX_SET_GAIN		= 33,
+	SBA_VB_SET_GAIN		= 33,
+	FBA_VB_RX_CNI		= 35,
+	MMX_SET_GAIN_TIMECONST	= 36,
+	SBA_VB_SET_TIMECONST	= 36,
+	SBA_VB_START		= 85,
+	SBA_SET_SWM		= 114,
+	SBA_SET_MDRP            = 116,
+	SBA_HW_SET_SSP		= 117,
+	SBA_SET_MEDIA_LOOP_MAP	= 118,
+	SBA_SET_MEDIA_PATH	= 119,
+	MMX_SET_MEDIA_PATH	= 119,
+	SBA_VB_LPRO             = 126,
+	SBA_VB_SET_FIR          = 128,
+	SBA_VB_SET_IIR          = 129,
+	SBA_SET_SSP_SLOT_MAP	= 130,
+};
+
+enum sst_dsp_switch {
+	SST_SWITCH_OFF = 0,
+	SST_SWITCH_ON = 3,
+};
+
+enum sst_path_switch {
+	SST_PATH_OFF = 0,
+	SST_PATH_ON = 1,
+};
+
+enum sst_swm_state {
+	SST_SWM_OFF = 0,
+	SST_SWM_ON = 3,
+};
+
+#define SST_FILL_LOCATION_IDS(dst, cell_idx, pipe_id)		do {	\
+		dst.location_id.p.cell_nbr_idx = (cell_idx);		\
+		dst.location_id.p.path_id = (pipe_id);			\
+	} while (0)
+#define SST_FILL_LOCATION_ID(dst, loc_id)				(\
+	dst.location_id.f = (loc_id))
+#define SST_FILL_MODULE_ID(dst, mod_id)					(\
+	dst.module_id = (mod_id))
+
+#define SST_FILL_DESTINATION1(dst, id)				do {	\
+		SST_FILL_LOCATION_ID(dst, (id) & 0xFFFF);		\
+		SST_FILL_MODULE_ID(dst, ((id) & 0xFFFF0000) >> 16);	\
+	} while (0)
+#define SST_FILL_DESTINATION2(dst, loc_id, mod_id)		do {	\
+		SST_FILL_LOCATION_ID(dst, loc_id);			\
+		SST_FILL_MODULE_ID(dst, mod_id);			\
+	} while (0)
+#define SST_FILL_DESTINATION3(dst, cell_idx, path_id, mod_id)	do {	\
+		SST_FILL_LOCATION_IDS(dst, cell_idx, path_id);		\
+		SST_FILL_MODULE_ID(dst, mod_id);			\
+	} while (0)
+
+#define SST_FILL_DESTINATION(level, dst, ...)				\
+	SST_FILL_DESTINATION##level(dst, __VA_ARGS__)
+#define SST_FILL_DEFAULT_DESTINATION(dst)				\
+	SST_FILL_DESTINATION(2, dst, SST_DEFAULT_LOCATION_ID, SST_DEFAULT_MODULE_ID)
+
+struct sst_destination_id {
+	union sst_location_id {
+		struct {
+			u8 cell_nbr_idx;	/* module index */
+			u8 path_id;		/* pipe_id */
+		} __packed	p;		/* part */
+		u16		f;		/* full */
+	} __packed location_id;
+	u16	   module_id;
+} __packed;
+struct sst_dsp_header {
+	struct sst_destination_id dst;
+	u16 command_id;
+	u16 length;
+} __packed;
+
+/*
+ *
+ * Common Commands
+ *
+ */
+struct sst_cmd_generic {
+	struct sst_dsp_header header;
+} __packed;
+struct sst_cmd_set_params {
+	struct sst_destination_id dst;
+	u16 command_id;
+	char params[0];
+} __packed;
+#define SST_CONTROL_NAME(xpname, xmname, xinstance, xtype) \
+	xpname " " xmname " " #xinstance " " xtype
+
+#define SST_COMBO_CONTROL_NAME(xpname, xmname, xinstance, xtype, xsubmodule) \
+	xpname " " xmname " " #xinstance " " xtype " " xsubmodule
+enum sst_algo_kcontrol_type {
+	SST_ALGO_PARAMS,
+	SST_ALGO_BYPASS,
+};
+
+struct sst_algo_control {
+	enum sst_algo_kcontrol_type type;
+	int max;
+	u16 module_id;
+	u16 pipe_id;
+	u16 task_id;
+	u16 cmd_id;
+	bool bypass;
+	unsigned char *params;
+	struct snd_soc_dapm_widget *w;
+};
+
+/* size of the control = size of params + size of length field */
+#define SST_ALGO_CTL_VALUE(xcount, xtype, xpipe, xmod, xtask, xcmd)			\
+	(struct sst_algo_control){							\
+		.max = xcount + sizeof(u16), .type = xtype, .module_id = xmod,			\
+		.pipe_id = xpipe, .task_id = xtask, .cmd_id = xcmd,			\
+	}
+
+#define SST_ALGO_KCONTROL(xname, xcount, xmod, xpipe,					\
+			  xtask, xcmd, xtype, xinfo, xget, xput)			\
+{	.iface = SNDRV_CTL_ELEM_IFACE_MIXER,						\
+	.name =  xname,									\
+	.info = xinfo, .get = xget, .put = xput,					\
+	.private_value = (unsigned long)&						\
+			SST_ALGO_CTL_VALUE(xcount, xtype, xpipe,			\
+					   xmod, xtask, xcmd),				\
+}
+
+#define SST_ALGO_KCONTROL_BYTES(xpname, xmname, xcount, xmod,				\
+				xpipe, xinstance, xtask, xcmd)				\
+	SST_ALGO_KCONTROL(SST_CONTROL_NAME(xpname, xmname, xinstance, "params"),	\
+			  xcount, xmod, xpipe, xtask, xcmd, SST_ALGO_PARAMS,		\
+			  sst_algo_bytes_ctl_info,					\
+			  sst_algo_control_get, sst_algo_control_set)
+
+#define SST_ALGO_KCONTROL_BOOL(xpname, xmname, xmod, xpipe, xinstance, xtask)		\
+	SST_ALGO_KCONTROL(SST_CONTROL_NAME(xpname, xmname, xinstance, "bypass"),	\
+			  0, xmod, xpipe, xtask, 0, SST_ALGO_BYPASS,			\
+			  snd_soc_info_bool_ext,					\
+			  sst_algo_control_get, sst_algo_control_set)
+
+#define SST_ALGO_BYPASS_PARAMS(xpname, xmname, xcount, xmod, xpipe,			\
+				xinstance, xtask, xcmd)					\
+	SST_ALGO_KCONTROL_BOOL(xpname, xmname, xmod, xpipe, xinstance, xtask),		\
+	SST_ALGO_KCONTROL_BYTES(xpname, xmname, xcount, xmod, xpipe, xinstance, xtask, xcmd)
+
+#define SST_COMBO_ALGO_KCONTROL_BYTES(xpname, xmname, xsubmod, xcount, xmod,		\
+				      xpipe, xinstance, xtask, xcmd)			\
+	SST_ALGO_KCONTROL(SST_COMBO_CONTROL_NAME(xpname, xmname, xinstance, "params",	\
+						 xsubmod),				\
+			  xcount, xmod, xpipe, xtask, xcmd, SST_ALGO_PARAMS,		\
+			  sst_algo_bytes_ctl_info,					\
+			  sst_algo_control_get, sst_algo_control_set)
+
+
+struct sst_enum {
+	bool tx;
+	unsigned short reg;
+	unsigned int max;
+	const char * const *texts;
+	struct snd_soc_dapm_widget *w;
+};
 
 #endif
diff --git a/sound/soc/intel/sst-haswell-pcm.c b/sound/soc/intel/sst-haswell-pcm.c
index 61bf6da4bb02..33fc5c3abf55 100644
--- a/sound/soc/intel/sst-haswell-pcm.c
+++ b/sound/soc/intel/sst-haswell-pcm.c
@@ -138,11 +138,10 @@ static inline unsigned int hsw_ipc_to_mixer(u32 value)
 static int hsw_stream_volume_put(struct snd_kcontrol *kcontrol,
 				struct snd_ctl_elem_value *ucontrol)
 {
-	struct snd_soc_platform *platform = snd_soc_kcontrol_platform(kcontrol);
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(cmpnt);
 	struct soc_mixer_control *mc =
 		(struct soc_mixer_control *)kcontrol->private_value;
-	struct hsw_priv_data *pdata =
-		snd_soc_platform_get_drvdata(platform);
 	struct hsw_pcm_data *pcm_data = &pdata->pcm[mc->reg];
 	struct sst_hsw *hsw = pdata->hsw;
 	u32 volume;
@@ -176,11 +175,10 @@ static int hsw_stream_volume_put(struct snd_kcontrol *kcontrol,
 static int hsw_stream_volume_get(struct snd_kcontrol *kcontrol,
 				struct snd_ctl_elem_value *ucontrol)
 {
-	struct snd_soc_platform *platform = snd_soc_kcontrol_platform(kcontrol);
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(cmpnt);
 	struct soc_mixer_control *mc =
 		(struct soc_mixer_control *)kcontrol->private_value;
-	struct hsw_priv_data *pdata =
-		snd_soc_platform_get_drvdata(platform);
 	struct hsw_pcm_data *pcm_data = &pdata->pcm[mc->reg];
 	struct sst_hsw *hsw = pdata->hsw;
 	u32 volume;
@@ -208,8 +206,8 @@ static int hsw_stream_volume_get(struct snd_kcontrol *kcontrol,
 static int hsw_volume_put(struct snd_kcontrol *kcontrol,
 				struct snd_ctl_elem_value *ucontrol)
 {
-	struct snd_soc_platform *platform = snd_soc_kcontrol_platform(kcontrol);
-	struct hsw_priv_data *pdata = snd_soc_platform_get_drvdata(platform);
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(cmpnt);
 	struct sst_hsw *hsw = pdata->hsw;
 	u32 volume;
 
@@ -233,8 +231,8 @@ static int hsw_volume_put(struct snd_kcontrol *kcontrol,
 static int hsw_volume_get(struct snd_kcontrol *kcontrol,
 				struct snd_ctl_elem_value *ucontrol)
 {
-	struct snd_soc_platform *platform = snd_soc_kcontrol_platform(kcontrol);
-	struct hsw_priv_data *pdata = snd_soc_platform_get_drvdata(platform);
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(cmpnt);
 	struct sst_hsw *hsw = pdata->hsw;
 	unsigned int volume = 0;
 
@@ -778,20 +776,11 @@ static const struct snd_soc_dapm_route graph[] = {
 
 static int hsw_pcm_probe(struct snd_soc_platform *platform)
 {
+	struct hsw_priv_data *priv_data = snd_soc_platform_get_drvdata(platform);
 	struct sst_pdata *pdata = dev_get_platdata(platform->dev);
-	struct hsw_priv_data *priv_data;
-	struct device *dma_dev;
+	struct device *dma_dev = pdata->dma_dev;
 	int i, ret = 0;
 
-	if (!pdata)
-		return -ENODEV;
-
-	dma_dev = pdata->dma_dev;
-
-	priv_data = devm_kzalloc(platform->dev, sizeof(*priv_data), GFP_KERNEL);
-	priv_data->hsw = pdata->dsp;
-	snd_soc_platform_set_drvdata(platform, priv_data);
-
 	/* allocate DSP buffer page tables */
 	for (i = 0; i < ARRAY_SIZE(hsw_dais); i++) {
 
@@ -848,27 +837,38 @@ static struct snd_soc_platform_driver hsw_soc_platform = {
 	.ops		= &hsw_pcm_ops,
 	.pcm_new	= hsw_pcm_new,
 	.pcm_free	= hsw_pcm_free,
-	.controls	= hsw_volume_controls,
-	.num_controls	= ARRAY_SIZE(hsw_volume_controls),
-	.dapm_widgets	= widgets,
-	.num_dapm_widgets	= ARRAY_SIZE(widgets),
-	.dapm_routes	= graph,
-	.num_dapm_routes	= ARRAY_SIZE(graph),
 };
 
 static const struct snd_soc_component_driver hsw_dai_component = {
-	.name		= "haswell-dai",
+	.name = "haswell-dai",
+	.controls = hsw_volume_controls,
+	.num_controls = ARRAY_SIZE(hsw_volume_controls),
+	.dapm_widgets = widgets,
+	.num_dapm_widgets = ARRAY_SIZE(widgets),
+	.dapm_routes = graph,
+	.num_dapm_routes = ARRAY_SIZE(graph),
 };
 
 static int hsw_pcm_dev_probe(struct platform_device *pdev)
 {
 	struct sst_pdata *sst_pdata = dev_get_platdata(&pdev->dev);
+	struct hsw_priv_data *priv_data;
 	int ret;
 
+	if (!sst_pdata)
+		return -EINVAL;
+
+	priv_data = devm_kzalloc(&pdev->dev, sizeof(*priv_data), GFP_KERNEL);
+	if (!priv_data)
+		return -ENOMEM;
+
 	ret = sst_hsw_dsp_init(&pdev->dev, sst_pdata);
 	if (ret < 0)
 		return -ENODEV;
 
+	priv_data->hsw = sst_pdata->dsp;
+	platform_set_drvdata(pdev, priv_data);
+
 	ret = snd_soc_register_platform(&pdev->dev, &hsw_soc_platform);
 	if (ret < 0)
 		goto err_plat;
diff --git a/sound/soc/intel/sst-mfld-platform-compress.c b/sound/soc/intel/sst-mfld-platform-compress.c
index 29c059ca19e8..59467775c9b8 100644
--- a/sound/soc/intel/sst-mfld-platform-compress.c
+++ b/sound/soc/intel/sst-mfld-platform-compress.c
@@ -86,7 +86,7 @@ static int sst_platform_compr_free(struct snd_compr_stream *cstream)
 	/*need to check*/
 	str_id = stream->id;
 	if (str_id)
-		ret_val = stream->compr_ops->close(str_id);
+		ret_val = stream->compr_ops->close(sst->dev, str_id);
 	module_put(sst->dev->driver->owner);
 	kfree(stream);
 	pr_debug("%s: %d\n", __func__, ret_val);
@@ -158,7 +158,7 @@ static int sst_platform_compr_set_params(struct snd_compr_stream *cstream,
 	cb.drain_cb_param = cstream;
 	cb.drain_notify = sst_drain_notify;
 
-	retval = stream->compr_ops->open(&str_params, &cb);
+	retval = stream->compr_ops->open(sst->dev, &str_params, &cb);
 	if (retval < 0) {
 		pr_err("stream allocation failed %d\n", retval);
 		return retval;
@@ -170,10 +170,30 @@ static int sst_platform_compr_set_params(struct snd_compr_stream *cstream,
 
 static int sst_platform_compr_trigger(struct snd_compr_stream *cstream, int cmd)
 {
-	struct sst_runtime_stream *stream =
-		cstream->runtime->private_data;
-
-	return stream->compr_ops->control(cmd, stream->id);
+	struct sst_runtime_stream *stream = cstream->runtime->private_data;
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+		if (stream->compr_ops->stream_start)
+			return stream->compr_ops->stream_start(sst->dev, stream->id);
+	case SNDRV_PCM_TRIGGER_STOP:
+		if (stream->compr_ops->stream_drop)
+			return stream->compr_ops->stream_drop(sst->dev, stream->id);
+	case SND_COMPR_TRIGGER_DRAIN:
+		if (stream->compr_ops->stream_drain)
+			return stream->compr_ops->stream_drain(sst->dev, stream->id);
+	case SND_COMPR_TRIGGER_PARTIAL_DRAIN:
+		if (stream->compr_ops->stream_partial_drain)
+			return stream->compr_ops->stream_partial_drain(sst->dev, stream->id);
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		if (stream->compr_ops->stream_pause)
+			return stream->compr_ops->stream_pause(sst->dev, stream->id);
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		if (stream->compr_ops->stream_pause_release)
+			return stream->compr_ops->stream_pause_release(sst->dev, stream->id);
+	default:
+		return -EINVAL;
+	}
 }
 
 static int sst_platform_compr_pointer(struct snd_compr_stream *cstream,
@@ -182,7 +202,7 @@ static int sst_platform_compr_pointer(struct snd_compr_stream *cstream,
 	struct sst_runtime_stream *stream;
 
 	stream  = cstream->runtime->private_data;
-	stream->compr_ops->tstamp(stream->id, tstamp);
+	stream->compr_ops->tstamp(sst->dev, stream->id, tstamp);
 	tstamp->byte_offset = tstamp->copied_total %
 				 (u32)cstream->runtime->buffer_size;
 	pr_debug("calc bytes offset/copied bytes as %d\n", tstamp->byte_offset);
@@ -195,7 +215,7 @@ static int sst_platform_compr_ack(struct snd_compr_stream *cstream,
 	struct sst_runtime_stream *stream;
 
 	stream  = cstream->runtime->private_data;
-	stream->compr_ops->ack(stream->id, (unsigned long)bytes);
+	stream->compr_ops->ack(sst->dev, stream->id, (unsigned long)bytes);
 	stream->bytes_written += bytes;
 
 	return 0;
@@ -225,7 +245,7 @@ static int sst_platform_compr_set_metadata(struct snd_compr_stream *cstream,
 	struct sst_runtime_stream *stream  =
 		 cstream->runtime->private_data;
 
-	return stream->compr_ops->set_metadata(stream->id, metadata);
+	return stream->compr_ops->set_metadata(sst->dev, stream->id, metadata);
 }
 
 struct snd_compr_ops sst_platform_compr_ops = {
diff --git a/sound/soc/intel/sst-mfld-platform-pcm.c b/sound/soc/intel/sst-mfld-platform-pcm.c
index 706212a6a68c..aa9b600dfc9b 100644
--- a/sound/soc/intel/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/sst-mfld-platform-pcm.c
@@ -43,12 +43,12 @@ int sst_register_dsp(struct sst_device *dev)
 		return -ENODEV;
 	mutex_lock(&sst_lock);
 	if (sst) {
-		pr_err("we already have a device %s\n", sst->name);
+		dev_err(dev->dev, "we already have a device %s\n", sst->name);
 		module_put(dev->dev->driver->owner);
 		mutex_unlock(&sst_lock);
 		return -EEXIST;
 	}
-	pr_debug("registering device %s\n", dev->name);
+	dev_dbg(dev->dev, "registering device %s\n", dev->name);
 	sst = dev;
 	mutex_unlock(&sst_lock);
 	return 0;
@@ -70,7 +70,7 @@ int sst_unregister_dsp(struct sst_device *dev)
 	}
 
 	module_put(sst->dev->driver->owner);
-	pr_debug("unreg %s\n", sst->name);
+	dev_dbg(dev->dev, "unreg %s\n", sst->name);
 	sst = NULL;
 	mutex_unlock(&sst_lock);
 	return 0;
@@ -252,7 +252,7 @@ int sst_fill_stream_params(void *substream,
 }
 
 static int sst_platform_alloc_stream(struct snd_pcm_substream *substream,
-		struct snd_soc_platform *platform)
+		struct snd_soc_dai *dai)
 {
 	struct sst_runtime_stream *stream =
 			substream->runtime->private_data;
@@ -260,7 +260,7 @@ static int sst_platform_alloc_stream(struct snd_pcm_substream *substream,
 	struct snd_sst_params str_params = {0};
 	struct snd_sst_alloc_params_ext alloc_params = {0};
 	int ret_val = 0;
-	struct sst_data *ctx = snd_soc_platform_get_drvdata(platform);
+	struct sst_data *ctx = snd_soc_dai_get_drvdata(dai);
 
 	/* set codec params and inform SST driver the same */
 	sst_fill_pcm_params(substream, &param);
@@ -277,7 +277,7 @@ static int sst_platform_alloc_stream(struct snd_pcm_substream *substream,
 
 	stream->stream_info.str_id = str_params.stream_id;
 
-	ret_val = stream->ops->open(&str_params);
+	ret_val = stream->ops->open(sst->dev, &str_params);
 	if (ret_val <= 0)
 		return ret_val;
 
@@ -306,22 +306,31 @@ static int sst_platform_init_stream(struct snd_pcm_substream *substream)
 {
 	struct sst_runtime_stream *stream =
 			substream->runtime->private_data;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	int ret_val;
 
-	pr_debug("setting buffer ptr param\n");
+	dev_dbg(rtd->dev, "setting buffer ptr param\n");
 	sst_set_stream_status(stream, SST_PLATFORM_INIT);
 	stream->stream_info.period_elapsed = sst_period_elapsed;
 	stream->stream_info.arg = substream;
 	stream->stream_info.buffer_ptr = 0;
 	stream->stream_info.sfreq = substream->runtime->rate;
-	ret_val = stream->ops->device_control(
-			SST_SND_STREAM_INIT, &stream->stream_info);
+	ret_val = stream->ops->stream_init(sst->dev, &stream->stream_info);
 	if (ret_val)
-		pr_err("control_set ret error %d\n", ret_val);
+		dev_err(rtd->dev, "control_set ret error %d\n", ret_val);
 	return ret_val;
 
 }
-/* end -- helper functions */
+
+static int power_up_sst(struct sst_runtime_stream *stream)
+{
+	return stream->ops->power(sst->dev, true);
+}
+
+static void power_down_sst(struct sst_runtime_stream *stream)
+{
+	stream->ops->power(sst->dev, false);
+}
 
 static int sst_media_open(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
@@ -339,7 +348,7 @@ static int sst_media_open(struct snd_pcm_substream *substream,
 	mutex_lock(&sst_lock);
 	if (!sst ||
 	    !try_module_get(sst->dev->driver->owner)) {
-		pr_err("no device available to run\n");
+		dev_err(dai->dev, "no device available to run\n");
 		ret_val = -ENODEV;
 		goto out_ops;
 	}
@@ -352,6 +361,10 @@ static int sst_media_open(struct snd_pcm_substream *substream,
 	/* allocate memory for SST API set */
 	runtime->private_data = stream;
 
+	ret_val = power_up_sst(stream);
+	if (ret_val < 0)
+		return ret_val;
+
 	/* Make sure, that the period size is always even */
 	snd_pcm_hw_constraint_step(substream->runtime, 0,
 			   SNDRV_PCM_HW_PARAM_PERIODS, 2);
@@ -371,26 +384,29 @@ static void sst_media_close(struct snd_pcm_substream *substream,
 	int ret_val = 0, str_id;
 
 	stream = substream->runtime->private_data;
+	power_down_sst(stream);
+
 	str_id = stream->stream_info.str_id;
 	if (str_id)
-		ret_val = stream->ops->close(str_id);
+		ret_val = stream->ops->close(sst->dev, str_id);
 	module_put(sst->dev->driver->owner);
 	kfree(stream);
 }
 
-static inline unsigned int get_current_pipe_id(struct snd_soc_platform *platform,
+static inline unsigned int get_current_pipe_id(struct snd_soc_dai *dai,
 					       struct snd_pcm_substream *substream)
 {
-	struct sst_data *sst = snd_soc_platform_get_drvdata(platform);
+	struct sst_data *sst = snd_soc_dai_get_drvdata(dai);
 	struct sst_dev_stream_map *map = sst->pdata->pdev_strm_map;
 	struct sst_runtime_stream *stream =
 			substream->runtime->private_data;
 	u32 str_id = stream->stream_info.str_id;
 	unsigned int pipe_id;
+
 	pipe_id = map[str_id].device_id;
 
-	pr_debug("%s: got pipe_id = %#x for str_id = %d\n",
-		 __func__, pipe_id, str_id);
+	dev_dbg(dai->dev, "got pipe_id = %#x for str_id = %d\n",
+			pipe_id, str_id);
 	return pipe_id;
 }
 
@@ -403,12 +419,11 @@ static int sst_media_prepare(struct snd_pcm_substream *substream,
 	stream = substream->runtime->private_data;
 	str_id = stream->stream_info.str_id;
 	if (stream->stream_info.str_id) {
-		ret_val = stream->ops->device_control(
-				SST_SND_DROP, &str_id);
+		ret_val = stream->ops->stream_drop(sst->dev, str_id);
 		return ret_val;
 	}
 
-	ret_val = sst_platform_alloc_stream(substream, dai->platform);
+	ret_val = sst_platform_alloc_stream(substream, dai);
 	if (ret_val <= 0)
 		return ret_val;
 	snprintf(substream->pcm->id, sizeof(substream->pcm->id),
@@ -461,37 +476,40 @@ static int sst_platform_pcm_trigger(struct snd_pcm_substream *substream,
 {
 	int ret_val = 0, str_id;
 	struct sst_runtime_stream *stream;
-	int str_cmd, status;
+	int status;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 
-	pr_debug("sst_platform_pcm_trigger called\n");
+	dev_dbg(rtd->dev, "sst_platform_pcm_trigger called\n");
+	if (substream->pcm->internal)
+		return 0;
 	stream = substream->runtime->private_data;
 	str_id = stream->stream_info.str_id;
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
-		pr_debug("sst: Trigger Start\n");
-		str_cmd = SST_SND_START;
+		dev_dbg(rtd->dev, "sst: Trigger Start\n");
 		status = SST_PLATFORM_RUNNING;
 		stream->stream_info.arg = substream;
+		ret_val = stream->ops->stream_start(sst->dev, str_id);
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
-		pr_debug("sst: in stop\n");
-		str_cmd = SST_SND_DROP;
+		dev_dbg(rtd->dev, "sst: in stop\n");
 		status = SST_PLATFORM_DROPPED;
+		ret_val = stream->ops->stream_drop(sst->dev, str_id);
 		break;
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
-		pr_debug("sst: in pause\n");
-		str_cmd = SST_SND_PAUSE;
+		dev_dbg(rtd->dev, "sst: in pause\n");
 		status = SST_PLATFORM_PAUSED;
+		ret_val = stream->ops->stream_pause(sst->dev, str_id);
 		break;
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
-		pr_debug("sst: in pause release\n");
-		str_cmd = SST_SND_RESUME;
+		dev_dbg(rtd->dev, "sst: in pause release\n");
 		status = SST_PLATFORM_RUNNING;
+		ret_val = stream->ops->stream_pause_release(sst->dev, str_id);
 		break;
 	default:
 		return -EINVAL;
 	}
-	ret_val = stream->ops->device_control(str_cmd, &str_id);
+
 	if (!ret_val)
 		sst_set_stream_status(stream, status);
 
@@ -505,16 +523,16 @@ static snd_pcm_uframes_t sst_platform_pcm_pointer
 	struct sst_runtime_stream *stream;
 	int ret_val, status;
 	struct pcm_stream_info *str_info;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 
 	stream = substream->runtime->private_data;
 	status = sst_get_stream_status(stream);
 	if (status == SST_PLATFORM_INIT)
 		return 0;
 	str_info = &stream->stream_info;
-	ret_val = stream->ops->device_control(
-				SST_SND_BUFFER_POINTER, str_info);
+	ret_val = stream->ops->stream_read_tstamp(sst->dev, str_info);
 	if (ret_val) {
-		pr_err("sst: error code = %d\n", ret_val);
+		dev_err(rtd->dev, "sst: error code = %d\n", ret_val);
 		return ret_val;
 	}
 	substream->runtime->delay = str_info->pcm_delay;
@@ -530,7 +548,7 @@ static struct snd_pcm_ops sst_platform_ops = {
 
 static void sst_pcm_free(struct snd_pcm *pcm)
 {
-	pr_debug("sst_pcm_free called\n");
+	dev_dbg(pcm->dev, "sst_pcm_free called\n");
 	snd_pcm_lib_preallocate_free_for_all(pcm);
 }
 
@@ -547,14 +565,20 @@ static int sst_pcm_new(struct snd_soc_pcm_runtime *rtd)
 			snd_dma_continuous_data(GFP_DMA),
 			SST_MIN_BUFFER, SST_MAX_BUFFER);
 		if (retval) {
-			pr_err("dma buffer allocationf fail\n");
+			dev_err(rtd->dev, "dma buffer allocationf fail\n");
 			return retval;
 		}
 	}
 	return retval;
 }
 
-static struct snd_soc_platform_driver sst_soc_platform_drv = {
+static int sst_soc_probe(struct snd_soc_platform *platform)
+{
+	return sst_dsp_init_v2_dpcm(platform);
+}
+
+static struct snd_soc_platform_driver sst_soc_platform_drv  = {
+	.probe		= sst_soc_probe,
 	.ops		= &sst_platform_ops,
 	.compr_ops	= &sst_platform_compr_ops,
 	.pcm_new	= sst_pcm_new,
@@ -574,13 +598,11 @@ static int sst_platform_probe(struct platform_device *pdev)
 
 	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
 	if (drv == NULL) {
-		pr_err("kzalloc failed\n");
 		return -ENOMEM;
 	}
 
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 	if (pdata == NULL) {
-		pr_err("kzalloc failed for pdata\n");
 		return -ENOMEM;
 	}
 
@@ -592,14 +614,14 @@ static int sst_platform_probe(struct platform_device *pdev)
 
 	ret = snd_soc_register_platform(&pdev->dev, &sst_soc_platform_drv);
 	if (ret) {
-		pr_err("registering soc platform failed\n");
+		dev_err(&pdev->dev, "registering soc platform failed\n");
 		return ret;
 	}
 
 	ret = snd_soc_register_component(&pdev->dev, &sst_component,
 				sst_platform_dai, ARRAY_SIZE(sst_platform_dai));
 	if (ret) {
-		pr_err("registering cpu dais failed\n");
+		dev_err(&pdev->dev, "registering cpu dais failed\n");
 		snd_soc_unregister_platform(&pdev->dev);
 	}
 	return ret;
@@ -610,7 +632,7 @@ static int sst_platform_remove(struct platform_device *pdev)
 
 	snd_soc_unregister_component(&pdev->dev);
 	snd_soc_unregister_platform(&pdev->dev);
-	pr_debug("sst_platform_remove success\n");
+	dev_dbg(&pdev->dev, "sst_platform_remove success\n");
 	return 0;
 }
 
diff --git a/sound/soc/intel/sst-mfld-platform.h b/sound/soc/intel/sst-mfld-platform.h
index 6c6a42c08e24..19f83ec51613 100644
--- a/sound/soc/intel/sst-mfld-platform.h
+++ b/sound/soc/intel/sst-mfld-platform.h
@@ -54,20 +54,6 @@ enum sst_drv_status {
 	SST_PLATFORM_DROPPED,
 };
 
-enum sst_controls {
-	SST_SND_ALLOC =			0x00,
-	SST_SND_PAUSE =			0x01,
-	SST_SND_RESUME =		0x02,
-	SST_SND_DROP =			0x03,
-	SST_SND_FREE =			0x04,
-	SST_SND_BUFFER_POINTER =	0x05,
-	SST_SND_STREAM_INIT =		0x06,
-	SST_SND_START	 =		0x07,
-	SST_SET_BYTE_STREAM =           0x100A,
-	SST_GET_BYTE_STREAM =           0x100B,
-	SST_MAX_CONTROLS = SST_GET_BYTE_STREAM,
-};
-
 enum sst_stream_ops {
 	STREAM_OPS_PLAYBACK = 0,
 	STREAM_OPS_CAPTURE,
@@ -113,24 +99,37 @@ struct sst_compress_cb {
 
 struct compress_sst_ops {
 	const char *name;
-	int (*open) (struct snd_sst_params *str_params,
-			struct sst_compress_cb *cb);
-	int (*control) (unsigned int cmd, unsigned int str_id);
-	int (*tstamp) (unsigned int str_id, struct snd_compr_tstamp *tstamp);
-	int (*ack) (unsigned int str_id, unsigned long bytes);
-	int (*close) (unsigned int str_id);
-	int (*get_caps) (struct snd_compr_caps *caps);
-	int (*get_codec_caps) (struct snd_compr_codec_caps *codec);
-	int (*set_metadata) (unsigned int str_id,
+	int (*open)(struct device *dev,
+		struct snd_sst_params *str_params, struct sst_compress_cb *cb);
+	int (*stream_start)(struct device *dev, unsigned int str_id);
+	int (*stream_drop)(struct device *dev, unsigned int str_id);
+	int (*stream_drain)(struct device *dev, unsigned int str_id);
+	int (*stream_partial_drain)(struct device *dev,	unsigned int str_id);
+	int (*stream_pause)(struct device *dev, unsigned int str_id);
+	int (*stream_pause_release)(struct device *dev,	unsigned int str_id);
+
+	int (*tstamp)(struct device *dev, unsigned int str_id,
+			struct snd_compr_tstamp *tstamp);
+	int (*ack)(struct device *dev, unsigned int str_id,
+			unsigned long bytes);
+	int (*close)(struct device *dev, unsigned int str_id);
+	int (*get_caps)(struct snd_compr_caps *caps);
+	int (*get_codec_caps)(struct snd_compr_codec_caps *codec);
+	int (*set_metadata)(struct device *dev,	unsigned int str_id,
 			struct snd_compr_metadata *mdata);
-
 };
 
 struct sst_ops {
-	int (*open) (struct snd_sst_params *str_param);
-	int (*device_control) (int cmd, void *arg);
-	int (*set_generic_params)(enum sst_controls cmd, void *arg);
-	int (*close) (unsigned int str_id);
+	int (*open)(struct device *dev, struct snd_sst_params *str_param);
+	int (*stream_init)(struct device *dev, struct pcm_stream_info *str_info);
+	int (*stream_start)(struct device *dev, int str_id);
+	int (*stream_drop)(struct device *dev, int str_id);
+	int (*stream_pause)(struct device *dev, int str_id);
+	int (*stream_pause_release)(struct device *dev, int str_id);
+	int (*stream_read_tstamp)(struct device *dev, struct pcm_stream_info *str_info);
+	int (*send_byte_stream)(struct device *dev, struct snd_sst_bytes_v2 *bytes);
+	int (*close)(struct device *dev, unsigned int str_id);
+	int (*power)(struct device *dev, bool state);
 };
 
 struct sst_runtime_stream {
@@ -152,6 +151,8 @@ struct sst_device {
 };
 
 struct sst_data;
+
+int sst_dsp_init_v2_dpcm(struct snd_soc_platform *platform);
 void sst_set_stream_status(struct sst_runtime_stream *stream, int state);
 int sst_fill_stream_params(void *substream, const struct sst_data *ctx,
 			   struct snd_sst_params *str_params, bool is_compress);
@@ -166,6 +167,7 @@ struct sst_algo_int_control_v2 {
 struct sst_data {
 	struct platform_device *pdev;
 	struct sst_platform_data *pdata;
+	struct snd_sst_bytes_v2 *byte_stream;
 	struct mutex lock;
 };
 int sst_register_dsp(struct sst_device *sst);
diff --git a/sound/soc/omap/rx51.c b/sound/soc/omap/rx51.c
index 943922c79f78..b10ae8074461 100644
--- a/sound/soc/omap/rx51.c
+++ b/sound/soc/omap/rx51.c
@@ -168,7 +168,7 @@ static int rx51_spk_event(struct snd_soc_dapm_widget *w,
 static int rx51_hp_event(struct snd_soc_dapm_widget *w,
 			 struct snd_kcontrol *k, int event)
 {
-	struct snd_soc_codec *codec = w->dapm->codec;
+	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(w->dapm);
 
 	if (SND_SOC_DAPM_EVENT_ON(event))
 		tpa6130a2_stereo_enable(codec, 1);
diff --git a/sound/soc/pxa/mmp-pcm.c b/sound/soc/pxa/mmp-pcm.c
index 5e8d81330173..64e8b949a1a3 100644
--- a/sound/soc/pxa/mmp-pcm.c
+++ b/sound/soc/pxa/mmp-pcm.c
@@ -34,7 +34,8 @@ struct mmp_dma_data {
 		SNDRV_PCM_INFO_MMAP_VALID |	\
 		SNDRV_PCM_INFO_INTERLEAVED |	\
 		SNDRV_PCM_INFO_PAUSE |		\
-		SNDRV_PCM_INFO_RESUME)
+		SNDRV_PCM_INFO_RESUME |		\
+		SNDRV_PCM_INFO_NO_PERIOD_WAKEUP)
 
 static struct snd_pcm_hardware mmp_pcm_hardware[] = {
 	{
diff --git a/sound/soc/rockchip/Kconfig b/sound/soc/rockchip/Kconfig
index c196a466eef6..78fc159559b0 100644
--- a/sound/soc/rockchip/Kconfig
+++ b/sound/soc/rockchip/Kconfig
@@ -2,11 +2,10 @@ config SND_SOC_ROCKCHIP
 	tristate "ASoC support for Rockchip"
 	depends on COMPILE_TEST || ARCH_ROCKCHIP
 	select SND_SOC_GENERIC_DMAENGINE_PCM
-	select SND_ROCKCHIP_I2S
 	help
 	  Say Y or M if you want to add support for codecs attached to
 	  the Rockchip SoCs' Audio interfaces. You will also need to
 	  select the audio interfaces to support below.
 
-config SND_ROCKCHIP_I2S
+config SND_SOC_ROCKCHIP_I2S
 	tristate
diff --git a/sound/soc/rockchip/Makefile b/sound/soc/rockchip/Makefile
index 1006418e1394..b9219092b47f 100644
--- a/sound/soc/rockchip/Makefile
+++ b/sound/soc/rockchip/Makefile
@@ -1,4 +1,4 @@
 # ROCKCHIP Platform Support
 snd-soc-i2s-objs := rockchip_i2s.o
 
-obj-$(CONFIG_SND_ROCKCHIP_I2S) += snd-soc-i2s.o
+obj-$(CONFIG_SND_SOC_ROCKCHIP_I2S) += snd-soc-i2s.o
diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c
index fb9e05c9f471..f373e37f8305 100644
--- a/sound/soc/rockchip/rockchip_i2s.c
+++ b/sound/soc/rockchip/rockchip_i2s.c
@@ -108,8 +108,10 @@ static void rockchip_snd_txctrl(struct rk_i2s_dev *i2s, int on)
 			while (val) {
 				regmap_read(i2s->regmap, I2S_CLR, &val);
 				retry--;
-				if (!retry)
+				if (!retry) {
 					dev_warn(i2s->dev, "fail to clear\n");
+					break;
+				}
 			}
 		}
 	}
@@ -244,16 +246,6 @@ static int rockchip_i2s_hw_params(struct snd_pcm_substream *substream,
 	regmap_update_bits(i2s->regmap, I2S_TXCR, I2S_TXCR_VDW_MASK, val);
 	regmap_update_bits(i2s->regmap, I2S_RXCR, I2S_RXCR_VDW_MASK, val);
 
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		dai->playback_dma_data = &i2s->playback_dma_data;
-		regmap_update_bits(i2s->regmap, I2S_DMACR, I2S_DMACR_TDL_MASK,
-				   I2S_DMACR_TDL(1) | I2S_DMACR_TDE_ENABLE);
-	} else {
-		dai->capture_dma_data = &i2s->capture_dma_data;
-		regmap_update_bits(i2s->regmap, I2S_DMACR, I2S_DMACR_RDL_MASK,
-				   I2S_DMACR_RDL(1) | I2S_DMACR_RDE_ENABLE);
-	}
-
 	return 0;
 }
 
@@ -301,6 +293,16 @@ static int rockchip_i2s_set_sysclk(struct snd_soc_dai *cpu_dai, int clk_id,
 	return ret;
 }
 
+static int rockchip_i2s_dai_probe(struct snd_soc_dai *dai)
+{
+	struct rk_i2s_dev *i2s = snd_soc_dai_get_drvdata(dai);
+
+	dai->capture_dma_data = &i2s->capture_dma_data;
+	dai->playback_dma_data = &i2s->playback_dma_data;
+
+	return 0;
+}
+
 static const struct snd_soc_dai_ops rockchip_i2s_dai_ops = {
 	.hw_params = rockchip_i2s_hw_params,
 	.set_sysclk = rockchip_i2s_set_sysclk,
@@ -309,7 +311,9 @@ static const struct snd_soc_dai_ops rockchip_i2s_dai_ops = {
 };
 
 static struct snd_soc_dai_driver rockchip_i2s_dai = {
+	.probe = rockchip_i2s_dai_probe,
 	.playback = {
+		.stream_name = "Playback",
 		.channels_min = 2,
 		.channels_max = 8,
 		.rates = SNDRV_PCM_RATE_8000_192000,
@@ -319,6 +323,7 @@ static struct snd_soc_dai_driver rockchip_i2s_dai = {
 			    SNDRV_PCM_FMTBIT_S24_LE),
 	},
 	.capture = {
+		.stream_name = "Capture",
 		.channels_min = 2,
 		.channels_max = 2,
 		.rates = SNDRV_PCM_RATE_8000_192000,
@@ -420,6 +425,11 @@ static int rockchip_i2s_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "Can't retrieve i2s bus clock\n");
 		return PTR_ERR(i2s->hclk);
 	}
+	ret = clk_prepare_enable(i2s->hclk);
+	if (ret) {
+		dev_err(i2s->dev, "hclock enable failed %d\n", ret);
+		return ret;
+	}
 
 	i2s->mclk = devm_clk_get(&pdev->dev, "i2s_clk");
 	if (IS_ERR(i2s->mclk)) {
diff --git a/sound/soc/samsung/idma.c b/sound/soc/samsung/idma.c
index db6cefa18017..0e8dd985fcb3 100644
--- a/sound/soc/samsung/idma.c
+++ b/sound/soc/samsung/idma.c
@@ -351,7 +351,7 @@ static void idma_free(struct snd_pcm *pcm)
 	if (!buf->area)
 		return;
 
-	iounmap(buf->area);
+	iounmap((void __iomem *)buf->area);
 
 	buf->area = NULL;
 	buf->addr = 0;
@@ -369,7 +369,7 @@ static int preallocate_idma_buffer(struct snd_pcm *pcm, int stream)
 	buf->dev.type = SNDRV_DMA_TYPE_CONTINUOUS;
 	buf->addr = idma.lp_tx_addr;
 	buf->bytes = idma_hardware.buffer_bytes_max;
-	buf->area = (unsigned char *)ioremap(buf->addr, buf->bytes);
+	buf->area = (unsigned char * __force)ioremap(buf->addr, buf->bytes);
 
 	return 0;
 }
diff --git a/sound/soc/samsung/odroidx2_max98090.c b/sound/soc/samsung/odroidx2_max98090.c
index 278edf9e2a87..3c8f60423e82 100644
--- a/sound/soc/samsung/odroidx2_max98090.c
+++ b/sound/soc/samsung/odroidx2_max98090.c
@@ -66,12 +66,12 @@ static struct snd_soc_card odroidx2 = {
 	.late_probe		= odroidx2_late_probe,
 };
 
-struct odroidx2_drv_data odroidx2_drvdata = {
+static const struct odroidx2_drv_data odroidx2_drvdata = {
 	.dapm_widgets		= odroidx2_dapm_widgets,
 	.num_dapm_widgets	= ARRAY_SIZE(odroidx2_dapm_widgets),
 };
 
-struct odroidx2_drv_data odroidu3_drvdata = {
+static const struct odroidx2_drv_data odroidu3_drvdata = {
 	.dapm_widgets		= odroidu3_dapm_widgets,
 	.num_dapm_widgets	= ARRAY_SIZE(odroidu3_dapm_widgets),
 };
diff --git a/sound/soc/samsung/speyside.c b/sound/soc/samsung/speyside.c
index 9902efcb8ea1..a05482651aae 100644
--- a/sound/soc/samsung/speyside.c
+++ b/sound/soc/samsung/speyside.c
@@ -228,10 +228,12 @@ static struct snd_soc_dai_link speyside_dai[] = {
 	},
 };
 
-static int speyside_wm9081_init(struct snd_soc_dapm_context *dapm)
+static int speyside_wm9081_init(struct snd_soc_component *component)
 {
+	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
+
 	/* At any time the WM9081 is active it will have this clock */
-	return snd_soc_codec_set_sysclk(dapm->codec, WM9081_SYSCLK_MCLK, 0,
+	return snd_soc_codec_set_sysclk(codec, WM9081_SYSCLK_MCLK, 0,
 					MCLK_AUDIO_RATE, 0);
 }
 
diff --git a/sound/soc/sh/fsi.c b/sound/soc/sh/fsi.c
index c76344350e44..66fddec9543d 100644
--- a/sound/soc/sh/fsi.c
+++ b/sound/soc/sh/fsi.c
@@ -1297,9 +1297,14 @@ static int fsi_dma_transfer(struct fsi_priv *fsi, struct fsi_stream *io)
 	struct snd_pcm_substream *substream = io->substream;
 	struct dma_async_tx_descriptor *desc;
 	int is_play = fsi_stream_is_play(fsi, io);
-	enum dma_data_direction dir = is_play ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
+	enum dma_transfer_direction dir;
 	int ret = -EIO;
 
+	if (is_play)
+		dir = DMA_MEM_TO_DEV;
+	else
+		dir = DMA_DEV_TO_MEM;
+
 	desc = dmaengine_prep_dma_cyclic(io->chan,
 					 substream->runtime->dma_addr,
 					 snd_pcm_lib_buffer_bytes(substream),
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index 19f78963e8b9..1922ec57d10a 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -798,10 +798,8 @@ if (name##_node) {							\
 			mod_parse(src);
 			mod_parse(dvc);
 
-			if (playback)
-				of_node_put(playback);
-			if (capture)
-				of_node_put(capture);
+			of_node_put(playback);
+			of_node_put(capture);
 		}
 
 		dai_i++;
diff --git a/sound/soc/sh/siu_pcm.c b/sound/soc/sh/siu_pcm.c
index 488f9becb44f..32eb6da2d2bd 100644
--- a/sound/soc/sh/siu_pcm.c
+++ b/sound/soc/sh/siu_pcm.c
@@ -139,7 +139,7 @@ static int siu_pcm_wr_set(struct siu_port *port_info,
 
 	desc->callback = siu_dma_tx_complete;
 	desc->callback_param = siu_stream;
-	cookie = desc->tx_submit(desc);
+	cookie = dmaengine_submit(desc);
 	if (cookie < 0) {
 		dev_err(dev, "Failed to submit a dma transfer\n");
 		return cookie;
@@ -189,7 +189,7 @@ static int siu_pcm_rd_set(struct siu_port *port_info,
 
 	desc->callback = siu_dma_tx_complete;
 	desc->callback_param = siu_stream;
-	cookie = desc->tx_submit(desc);
+	cookie = dmaengine_submit(desc);
 	if (cookie < 0) {
 		dev_err(dev, "Failed to submit dma descriptor\n");
 		return cookie;
diff --git a/sound/soc/sirf/sirf-usp.c b/sound/soc/sirf/sirf-usp.c
index 3a730374e259..186dc7f33a55 100644
--- a/sound/soc/sirf/sirf-usp.c
+++ b/sound/soc/sirf/sirf-usp.c
@@ -100,6 +100,16 @@ static int sirf_usp_pcm_set_dai_fmt(struct snd_soc_dai *dai,
 		return -EINVAL;
 	}
 
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		usp->daifmt_format |= (fmt & SND_SOC_DAIFMT_INV_MASK);
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -177,7 +187,7 @@ static int sirf_usp_pcm_hw_params(struct snd_pcm_substream *substream,
 
 	shifter_len = data_len;
 
-	switch (usp->daifmt_format) {
+	switch (usp->daifmt_format & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
 		regmap_update_bits(usp->regmap, USP_RX_FRAME_CTRL,
 			USP_I2S_SYNC_CHG, USP_I2S_SYNC_CHG);
@@ -193,6 +203,18 @@ static int sirf_usp_pcm_hw_params(struct snd_pcm_substream *substream,
 		return -EINVAL;
 	}
 
+	switch (usp->daifmt_format & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		regmap_update_bits(usp->regmap, USP_MODE1,
+			USP_RXD_ACT_EDGE_FALLING | USP_TXD_ACT_EDGE_FALLING,
+			USP_RXD_ACT_EDGE_FALLING);
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 		regmap_update_bits(usp->regmap, USP_TX_FRAME_CTRL,
 			USP_TXC_DATA_LEN_MASK | USP_TXC_FRAME_LEN_MASK
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index d074aa91b023..4c8f8a23a0e9 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -270,79 +270,54 @@ static const struct file_operations codec_reg_fops = {
 	.llseek = default_llseek,
 };
 
-static struct dentry *soc_debugfs_create_dir(struct dentry *parent,
-	const char *fmt, ...)
+static void soc_init_component_debugfs(struct snd_soc_component *component)
 {
-	struct dentry *de;
-	va_list ap;
-	char *s;
+	if (component->debugfs_prefix) {
+		char *name;
 
-	va_start(ap, fmt);
-	s = kvasprintf(GFP_KERNEL, fmt, ap);
-	va_end(ap);
+		name = kasprintf(GFP_KERNEL, "%s:%s",
+			component->debugfs_prefix, component->name);
+		if (name) {
+			component->debugfs_root = debugfs_create_dir(name,
+				component->card->debugfs_card_root);
+			kfree(name);
+		}
+	} else {
+		component->debugfs_root = debugfs_create_dir(component->name,
+				component->card->debugfs_card_root);
+	}
 
-	if (!s)
-		return NULL;
+	if (!component->debugfs_root) {
+		dev_warn(component->dev,
+			"ASoC: Failed to create component debugfs directory\n");
+		return;
+	}
 
-	de = debugfs_create_dir(s, parent);
-	kfree(s);
+	snd_soc_dapm_debugfs_init(snd_soc_component_get_dapm(component),
+		component->debugfs_root);
 
-	return de;
+	if (component->init_debugfs)
+		component->init_debugfs(component);
 }
 
-static void soc_init_codec_debugfs(struct snd_soc_codec *codec)
+static void soc_cleanup_component_debugfs(struct snd_soc_component *component)
 {
-	struct dentry *debugfs_card_root = codec->component.card->debugfs_card_root;
+	debugfs_remove_recursive(component->debugfs_root);
+}
 
-	codec->debugfs_codec_root = soc_debugfs_create_dir(debugfs_card_root,
-						"codec:%s",
-						codec->component.name);
-	if (!codec->debugfs_codec_root) {
-		dev_warn(codec->dev,
-			"ASoC: Failed to create codec debugfs directory\n");
-		return;
-	}
+static void soc_init_codec_debugfs(struct snd_soc_component *component)
+{
+	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
 
-	debugfs_create_bool("cache_sync", 0444, codec->debugfs_codec_root,
+	debugfs_create_bool("cache_sync", 0444, codec->component.debugfs_root,
 			    &codec->cache_sync);
-	debugfs_create_bool("cache_only", 0444, codec->debugfs_codec_root,
-			    &codec->cache_only);
 
 	codec->debugfs_reg = debugfs_create_file("codec_reg", 0644,
-						 codec->debugfs_codec_root,
+						 codec->component.debugfs_root,
 						 codec, &codec_reg_fops);
 	if (!codec->debugfs_reg)
 		dev_warn(codec->dev,
 			"ASoC: Failed to create codec register debugfs file\n");
-
-	snd_soc_dapm_debugfs_init(&codec->dapm, codec->debugfs_codec_root);
-}
-
-static void soc_cleanup_codec_debugfs(struct snd_soc_codec *codec)
-{
-	debugfs_remove_recursive(codec->debugfs_codec_root);
-}
-
-static void soc_init_platform_debugfs(struct snd_soc_platform *platform)
-{
-	struct dentry *debugfs_card_root = platform->component.card->debugfs_card_root;
-
-	platform->debugfs_platform_root = soc_debugfs_create_dir(debugfs_card_root,
-						"platform:%s",
-						platform->component.name);
-	if (!platform->debugfs_platform_root) {
-		dev_warn(platform->dev,
-			"ASoC: Failed to create platform debugfs directory\n");
-		return;
-	}
-
-	snd_soc_dapm_debugfs_init(&platform->component.dapm,
-		platform->debugfs_platform_root);
-}
-
-static void soc_cleanup_platform_debugfs(struct snd_soc_platform *platform)
-{
-	debugfs_remove_recursive(platform->debugfs_platform_root);
 }
 
 static ssize_t codec_list_read_file(struct file *file, char __user *user_buf,
@@ -474,19 +449,15 @@ static void soc_cleanup_card_debugfs(struct snd_soc_card *card)
 
 #else
 
-static inline void soc_init_codec_debugfs(struct snd_soc_codec *codec)
-{
-}
+#define soc_init_codec_debugfs NULL
 
-static inline void soc_cleanup_codec_debugfs(struct snd_soc_codec *codec)
+static inline void soc_init_component_debugfs(
+	struct snd_soc_component *component)
 {
 }
 
-static inline void soc_init_platform_debugfs(struct snd_soc_platform *platform)
-{
-}
-
-static inline void soc_cleanup_platform_debugfs(struct snd_soc_platform *platform)
+static inline void soc_cleanup_component_debugfs(
+	struct snd_soc_component *component)
 {
 }
 
@@ -579,10 +550,8 @@ int snd_soc_suspend(struct device *dev)
 	struct snd_soc_codec *codec;
 	int i, j;
 
-	/* If the initialization of this soc device failed, there is no codec
-	 * associated with it. Just bail out in this case.
-	 */
-	if (list_empty(&card->codec_dev_list))
+	/* If the card is not initialized yet there is nothing to do */
+	if (!card->instantiated)
 		return 0;
 
 	/* Due to the resume being scheduled into a workqueue we could
@@ -668,7 +637,7 @@ int snd_soc_suspend(struct device *dev)
 	list_for_each_entry(codec, &card->codec_dev_list, card_list) {
 		/* If there are paths active then the CODEC will be held with
 		 * bias _ON and should not be suspended. */
-		if (!codec->suspended && codec->driver->suspend) {
+		if (!codec->suspended) {
 			switch (codec->dapm.bias_level) {
 			case SND_SOC_BIAS_STANDBY:
 				/*
@@ -682,8 +651,10 @@ int snd_soc_suspend(struct device *dev)
 						"ASoC: idle_bias_off CODEC on over suspend\n");
 					break;
 				}
+
 			case SND_SOC_BIAS_OFF:
-				codec->driver->suspend(codec);
+				if (codec->driver->suspend)
+					codec->driver->suspend(codec);
 				codec->suspended = 1;
 				codec->cache_sync = 1;
 				if (codec->component.regmap)
@@ -757,11 +728,12 @@ static void soc_resume_deferred(struct work_struct *work)
 		 * left with bias OFF or STANDBY and suspended so we must now
 		 * resume.  Otherwise the suspend was suppressed.
 		 */
-		if (codec->driver->resume && codec->suspended) {
+		if (codec->suspended) {
 			switch (codec->dapm.bias_level) {
 			case SND_SOC_BIAS_STANDBY:
 			case SND_SOC_BIAS_OFF:
-				codec->driver->resume(codec);
+				if (codec->driver->resume)
+					codec->driver->resume(codec);
 				codec->suspended = 0;
 				break;
 			default:
@@ -835,10 +807,8 @@ int snd_soc_resume(struct device *dev)
 	struct snd_soc_card *card = dev_get_drvdata(dev);
 	int i, ac97_control = 0;
 
-	/* If the initialization of this soc device failed, there is no codec
-	 * associated with it. Just bail out in this case.
-	 */
-	if (list_empty(&card->codec_dev_list))
+	/* If the card is not initialized yet there is nothing to do */
+	if (!card->instantiated)
 		return 0;
 
 	/* activate pins from sleep state */
@@ -887,35 +857,40 @@ EXPORT_SYMBOL_GPL(snd_soc_resume);
 static const struct snd_soc_dai_ops null_dai_ops = {
 };
 
-static struct snd_soc_codec *soc_find_codec(
-					const struct device_node *codec_of_node,
-					const char *codec_name)
+static struct snd_soc_component *soc_find_component(
+	const struct device_node *of_node, const char *name)
 {
-	struct snd_soc_codec *codec;
+	struct snd_soc_component *component;
 
-	list_for_each_entry(codec, &codec_list, list) {
-		if (codec_of_node) {
-			if (codec->dev->of_node != codec_of_node)
-				continue;
-		} else {
-			if (strcmp(codec->component.name, codec_name))
-				continue;
+	list_for_each_entry(component, &component_list, list) {
+		if (of_node) {
+			if (component->dev->of_node == of_node)
+				return component;
+		} else if (strcmp(component->name, name) == 0) {
+			return component;
 		}
-
-		return codec;
 	}
 
 	return NULL;
 }
 
-static struct snd_soc_dai *soc_find_codec_dai(struct snd_soc_codec *codec,
-					      const char *codec_dai_name)
+static struct snd_soc_dai *snd_soc_find_dai(
+	const struct snd_soc_dai_link_component *dlc)
 {
-	struct snd_soc_dai *codec_dai;
+	struct snd_soc_component *component;
+	struct snd_soc_dai *dai;
 
-	list_for_each_entry(codec_dai, &codec->component.dai_list, list) {
-		if (!strcmp(codec_dai->name, codec_dai_name)) {
-			return codec_dai;
+	/* Find CPU DAI from registered DAIs*/
+	list_for_each_entry(component, &component_list, list) {
+		if (dlc->of_node && component->dev->of_node != dlc->of_node)
+			continue;
+		if (dlc->name && strcmp(dev_name(component->dev), dlc->name))
+			continue;
+		list_for_each_entry(dai, &component->dai_list, list) {
+			if (dlc->dai_name && strcmp(dai->name, dlc->dai_name))
+				continue;
+
+			return dai;
 		}
 	}
 
@@ -926,33 +901,19 @@ static int soc_bind_dai_link(struct snd_soc_card *card, int num)
 {
 	struct snd_soc_dai_link *dai_link = &card->dai_link[num];
 	struct snd_soc_pcm_runtime *rtd = &card->rtd[num];
-	struct snd_soc_component *component;
 	struct snd_soc_dai_link_component *codecs = dai_link->codecs;
+	struct snd_soc_dai_link_component cpu_dai_component;
 	struct snd_soc_dai **codec_dais = rtd->codec_dais;
 	struct snd_soc_platform *platform;
-	struct snd_soc_dai *cpu_dai;
 	const char *platform_name;
 	int i;
 
 	dev_dbg(card->dev, "ASoC: binding %s at idx %d\n", dai_link->name, num);
 
-	/* Find CPU DAI from registered DAIs*/
-	list_for_each_entry(component, &component_list, list) {
-		if (dai_link->cpu_of_node &&
-			component->dev->of_node != dai_link->cpu_of_node)
-			continue;
-		if (dai_link->cpu_name &&
-			strcmp(dev_name(component->dev), dai_link->cpu_name))
-			continue;
-		list_for_each_entry(cpu_dai, &component->dai_list, list) {
-			if (dai_link->cpu_dai_name &&
-				strcmp(cpu_dai->name, dai_link->cpu_dai_name))
-				continue;
-
-			rtd->cpu_dai = cpu_dai;
-		}
-	}
-
+	cpu_dai_component.name = dai_link->cpu_name;
+	cpu_dai_component.of_node = dai_link->cpu_of_node;
+	cpu_dai_component.dai_name = dai_link->cpu_dai_name;
+	rtd->cpu_dai = snd_soc_find_dai(&cpu_dai_component);
 	if (!rtd->cpu_dai) {
 		dev_err(card->dev, "ASoC: CPU DAI %s not registered\n",
 			dai_link->cpu_dai_name);
@@ -963,15 +924,7 @@ static int soc_bind_dai_link(struct snd_soc_card *card, int num)
 
 	/* Find CODEC from registered CODECs */
 	for (i = 0; i < rtd->num_codecs; i++) {
-		struct snd_soc_codec *codec;
-		codec = soc_find_codec(codecs[i].of_node, codecs[i].name);
-		if (!codec) {
-			dev_err(card->dev, "ASoC: CODEC %s not registered\n",
-				codecs[i].name);
-			return -EPROBE_DEFER;
-		}
-
-		codec_dais[i] = soc_find_codec_dai(codec, codecs[i].dai_name);
+		codec_dais[i] = snd_soc_find_dai(&codecs[i]);
 		if (!codec_dais[i]) {
 			dev_err(card->dev, "ASoC: CODEC DAI %s not registered\n",
 				codecs[i].dai_name);
@@ -1012,68 +965,46 @@ static int soc_bind_dai_link(struct snd_soc_card *card, int num)
 	return 0;
 }
 
-static int soc_remove_platform(struct snd_soc_platform *platform)
+static void soc_remove_component(struct snd_soc_component *component)
 {
-	int ret;
-
-	if (platform->driver->remove) {
-		ret = platform->driver->remove(platform);
-		if (ret < 0)
-			dev_err(platform->dev, "ASoC: failed to remove %d\n",
-				ret);
-	}
-
-	/* Make sure all DAPM widgets are freed */
-	snd_soc_dapm_free(&platform->component.dapm);
-
-	soc_cleanup_platform_debugfs(platform);
-	platform->probed = 0;
-	module_put(platform->dev->driver->owner);
-
-	return 0;
-}
+	if (!component->probed)
+		return;
 
-static void soc_remove_codec(struct snd_soc_codec *codec)
-{
-	int err;
+	/* This is a HACK and will be removed soon */
+	if (component->codec)
+		list_del(&component->codec->card_list);
 
-	if (codec->driver->remove) {
-		err = codec->driver->remove(codec);
-		if (err < 0)
-			dev_err(codec->dev, "ASoC: failed to remove %d\n", err);
-	}
+	if (component->remove)
+		component->remove(component);
 
-	/* Make sure all DAPM widgets are freed */
-	snd_soc_dapm_free(&codec->dapm);
+	snd_soc_dapm_free(snd_soc_component_get_dapm(component));
 
-	soc_cleanup_codec_debugfs(codec);
-	codec->probed = 0;
-	list_del(&codec->card_list);
-	module_put(codec->dev->driver->owner);
+	soc_cleanup_component_debugfs(component);
+	component->probed = 0;
+	module_put(component->dev->driver->owner);
 }
 
-static void soc_remove_codec_dai(struct snd_soc_dai *codec_dai, int order)
+static void soc_remove_dai(struct snd_soc_dai *dai, int order)
 {
 	int err;
 
-	if (codec_dai && codec_dai->probed &&
-			codec_dai->driver->remove_order == order) {
-		if (codec_dai->driver->remove) {
-			err = codec_dai->driver->remove(codec_dai);
+	if (dai && dai->probed &&
+			dai->driver->remove_order == order) {
+		if (dai->driver->remove) {
+			err = dai->driver->remove(dai);
 			if (err < 0)
-				dev_err(codec_dai->dev,
+				dev_err(dai->dev,
 					"ASoC: failed to remove %s: %d\n",
-					codec_dai->name, err);
+					dai->name, err);
 		}
-		codec_dai->probed = 0;
+		dai->probed = 0;
 	}
 }
 
 static void soc_remove_link_dais(struct snd_soc_card *card, int num, int order)
 {
 	struct snd_soc_pcm_runtime *rtd = &card->rtd[num];
-	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	int i, err;
+	int i;
 
 	/* unregister the rtd device */
 	if (rtd->dev_registered) {
@@ -1085,22 +1016,9 @@ static void soc_remove_link_dais(struct snd_soc_card *card, int num, int order)
 
 	/* remove the CODEC DAI */
 	for (i = 0; i < rtd->num_codecs; i++)
-		soc_remove_codec_dai(rtd->codec_dais[i], order);
+		soc_remove_dai(rtd->codec_dais[i], order);
 
-	/* remove the cpu_dai */
-	if (cpu_dai && cpu_dai->probed &&
-			cpu_dai->driver->remove_order == order) {
-		if (cpu_dai->driver->remove) {
-			err = cpu_dai->driver->remove(cpu_dai);
-			if (err < 0)
-				dev_err(cpu_dai->dev,
-					"ASoC: failed to remove %s: %d\n",
-					cpu_dai->name, err);
-		}
-		cpu_dai->probed = 0;
-		if (!cpu_dai->codec)
-			module_put(cpu_dai->dev->driver->owner);
-	}
+	soc_remove_dai(rtd->cpu_dai, order);
 }
 
 static void soc_remove_link_components(struct snd_soc_card *card, int num,
@@ -1109,29 +1027,24 @@ static void soc_remove_link_components(struct snd_soc_card *card, int num,
 	struct snd_soc_pcm_runtime *rtd = &card->rtd[num];
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_platform *platform = rtd->platform;
-	struct snd_soc_codec *codec;
+	struct snd_soc_component *component;
 	int i;
 
 	/* remove the platform */
-	if (platform && platform->probed &&
-	    platform->driver->remove_order == order) {
-		soc_remove_platform(platform);
-	}
+	if (platform && platform->component.driver->remove_order == order)
+		soc_remove_component(&platform->component);
 
 	/* remove the CODEC-side CODEC */
 	for (i = 0; i < rtd->num_codecs; i++) {
-		codec = rtd->codec_dais[i]->codec;
-		if (codec && codec->probed &&
-		    codec->driver->remove_order == order)
-			soc_remove_codec(codec);
+		component = rtd->codec_dais[i]->component;
+		if (component->driver->remove_order == order)
+			soc_remove_component(component);
 	}
 
 	/* remove any CPU-side CODEC */
 	if (cpu_dai) {
-		codec = cpu_dai->codec;
-		if (codec && codec->probed &&
-		    codec->driver->remove_order == order)
-			soc_remove_codec(codec);
+		if (cpu_dai->component->driver->remove_order == order)
+			soc_remove_component(cpu_dai->component);
 	}
 }
 
@@ -1173,137 +1086,78 @@ static void soc_set_name_prefix(struct snd_soc_card *card,
 	}
 }
 
-static int soc_probe_codec(struct snd_soc_card *card,
-			   struct snd_soc_codec *codec)
+static int soc_probe_component(struct snd_soc_card *card,
+	struct snd_soc_component *component)
 {
-	int ret = 0;
-	const struct snd_soc_codec_driver *driver = codec->driver;
+	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
 	struct snd_soc_dai *dai;
+	int ret;
 
-	codec->component.card = card;
-	codec->dapm.card = card;
-	soc_set_name_prefix(card, &codec->component);
+	if (component->probed)
+		return 0;
+
+	component->card = card;
+	dapm->card = card;
+	soc_set_name_prefix(card, component);
 
-	if (!try_module_get(codec->dev->driver->owner))
+	if (!try_module_get(component->dev->driver->owner))
 		return -ENODEV;
 
-	soc_init_codec_debugfs(codec);
+	soc_init_component_debugfs(component);
 
-	if (driver->dapm_widgets) {
-		ret = snd_soc_dapm_new_controls(&codec->dapm,
-						driver->dapm_widgets,
-					 	driver->num_dapm_widgets);
+	if (component->dapm_widgets) {
+		ret = snd_soc_dapm_new_controls(dapm, component->dapm_widgets,
+			component->num_dapm_widgets);
 
 		if (ret != 0) {
-			dev_err(codec->dev,
+			dev_err(component->dev,
 				"Failed to create new controls %d\n", ret);
 			goto err_probe;
 		}
 	}
 
-	/* Create DAPM widgets for each DAI stream */
-	list_for_each_entry(dai, &codec->component.dai_list, list) {
-		ret = snd_soc_dapm_new_dai_widgets(&codec->dapm, dai);
-
+	list_for_each_entry(dai, &component->dai_list, list) {
+		ret = snd_soc_dapm_new_dai_widgets(dapm, dai);
 		if (ret != 0) {
-			dev_err(codec->dev,
+			dev_err(component->dev,
 				"Failed to create DAI widgets %d\n", ret);
 			goto err_probe;
 		}
 	}
 
-	codec->dapm.idle_bias_off = driver->idle_bias_off;
-
-	if (driver->probe) {
-		ret = driver->probe(codec);
+	if (component->probe) {
+		ret = component->probe(component);
 		if (ret < 0) {
-			dev_err(codec->dev,
-				"ASoC: failed to probe CODEC %d\n", ret);
+			dev_err(component->dev,
+				"ASoC: failed to probe component %d\n", ret);
 			goto err_probe;
 		}
-		WARN(codec->dapm.idle_bias_off &&
-			codec->dapm.bias_level != SND_SOC_BIAS_OFF,
+
+		WARN(dapm->idle_bias_off &&
+			dapm->bias_level != SND_SOC_BIAS_OFF,
 			"codec %s can not start from non-off bias with idle_bias_off==1\n",
-			codec->component.name);
+			component->name);
 	}
 
-	if (driver->controls)
-		snd_soc_add_codec_controls(codec, driver->controls,
-				     driver->num_controls);
-	if (driver->dapm_routes)
-		snd_soc_dapm_add_routes(&codec->dapm, driver->dapm_routes,
-					driver->num_dapm_routes);
-
-	/* mark codec as probed and add to card codec list */
-	codec->probed = 1;
-	list_add(&codec->card_list, &card->codec_dev_list);
-	list_add(&codec->dapm.list, &card->dapm_list);
-
-	return 0;
-
-err_probe:
-	soc_cleanup_codec_debugfs(codec);
-	module_put(codec->dev->driver->owner);
-
-	return ret;
-}
-
-static int soc_probe_platform(struct snd_soc_card *card,
-			   struct snd_soc_platform *platform)
-{
-	int ret = 0;
-	const struct snd_soc_platform_driver *driver = platform->driver;
-	struct snd_soc_component *component;
-	struct snd_soc_dai *dai;
-
-	platform->component.card = card;
-	platform->component.dapm.card = card;
+	if (component->controls)
+		snd_soc_add_component_controls(component, component->controls,
+				     component->num_controls);
+	if (component->dapm_routes)
+		snd_soc_dapm_add_routes(dapm, component->dapm_routes,
+					component->num_dapm_routes);
 
-	if (!try_module_get(platform->dev->driver->owner))
-		return -ENODEV;
-
-	soc_init_platform_debugfs(platform);
+	component->probed = 1;
+	list_add(&dapm->list, &card->dapm_list);
 
-	if (driver->dapm_widgets)
-		snd_soc_dapm_new_controls(&platform->component.dapm,
-			driver->dapm_widgets, driver->num_dapm_widgets);
-
-	/* Create DAPM widgets for each DAI stream */
-	list_for_each_entry(component, &component_list, list) {
-		if (component->dev != platform->dev)
-			continue;
-		list_for_each_entry(dai, &component->dai_list, list)
-			snd_soc_dapm_new_dai_widgets(&platform->component.dapm,
-				dai);
-	}
-
-	platform->component.dapm.idle_bias_off = 1;
-
-	if (driver->probe) {
-		ret = driver->probe(platform);
-		if (ret < 0) {
-			dev_err(platform->dev,
-				"ASoC: failed to probe platform %d\n", ret);
-			goto err_probe;
-		}
-	}
-
-	if (driver->controls)
-		snd_soc_add_platform_controls(platform, driver->controls,
-				     driver->num_controls);
-	if (driver->dapm_routes)
-		snd_soc_dapm_add_routes(&platform->component.dapm,
-			driver->dapm_routes, driver->num_dapm_routes);
-
-	/* mark platform as probed and add to card platform list */
-	platform->probed = 1;
-	list_add(&platform->component.dapm.list, &card->dapm_list);
+	/* This is a HACK and will be removed soon */
+	if (component->codec)
+		list_add(&component->codec->card_list, &card->codec_dev_list);
 
 	return 0;
 
 err_probe:
-	soc_cleanup_platform_debugfs(platform);
-	module_put(platform->dev->driver->owner);
+	soc_cleanup_component_debugfs(component);
+	module_put(component->dev->driver->owner);
 
 	return ret;
 }
@@ -1342,17 +1196,21 @@ static int soc_post_component_init(struct snd_soc_pcm_runtime *rtd,
 	}
 	rtd->dev_registered = 1;
 
-	/* add DAPM sysfs entries for this codec */
-	ret = snd_soc_dapm_sys_add(rtd->dev);
-	if (ret < 0)
-		dev_err(rtd->dev,
-			"ASoC: failed to add codec dapm sysfs entries: %d\n", ret);
+	if (rtd->codec) {
+		/* add DAPM sysfs entries for this codec */
+		ret = snd_soc_dapm_sys_add(rtd->dev);
+		if (ret < 0)
+			dev_err(rtd->dev,
+				"ASoC: failed to add codec dapm sysfs entries: %d\n",
+				ret);
 
-	/* add codec sysfs entries */
-	ret = device_create_file(rtd->dev, &dev_attr_codec_reg);
-	if (ret < 0)
-		dev_err(rtd->dev,
-			"ASoC: failed to add codec sysfs files: %d\n", ret);
+		/* add codec sysfs entries */
+		ret = device_create_file(rtd->dev, &dev_attr_codec_reg);
+		if (ret < 0)
+			dev_err(rtd->dev,
+				"ASoC: failed to add codec sysfs files: %d\n",
+				ret);
+	}
 
 	return 0;
 }
@@ -1361,33 +1219,31 @@ static int soc_probe_link_components(struct snd_soc_card *card, int num,
 				     int order)
 {
 	struct snd_soc_pcm_runtime *rtd = &card->rtd[num];
-	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_platform *platform = rtd->platform;
+	struct snd_soc_component *component;
 	int i, ret;
 
 	/* probe the CPU-side component, if it is a CODEC */
-	if (cpu_dai->codec &&
-	    !cpu_dai->codec->probed &&
-	    cpu_dai->codec->driver->probe_order == order) {
-		ret = soc_probe_codec(card, cpu_dai->codec);
+	component = rtd->cpu_dai->component;
+	if (component->driver->probe_order == order) {
+		ret = soc_probe_component(card, component);
 		if (ret < 0)
 			return ret;
 	}
 
 	/* probe the CODEC-side components */
 	for (i = 0; i < rtd->num_codecs; i++) {
-		if (!rtd->codec_dais[i]->codec->probed &&
-		    rtd->codec_dais[i]->codec->driver->probe_order == order) {
-			ret = soc_probe_codec(card, rtd->codec_dais[i]->codec);
+		component = rtd->codec_dais[i]->component;
+		if (component->driver->probe_order == order) {
+			ret = soc_probe_component(card, component);
 			if (ret < 0)
 				return ret;
 		}
 	}
 
 	/* probe the platform */
-	if (!platform->probed &&
-	    platform->driver->probe_order == order) {
-		ret = soc_probe_platform(card, platform);
+	if (platform->component.driver->probe_order == order) {
+		ret = soc_probe_component(card, &platform->component);
 		if (ret < 0)
 			return ret;
 	}
@@ -1482,18 +1338,12 @@ static int soc_probe_link_dais(struct snd_soc_card *card, int num, int order)
 	/* probe the cpu_dai */
 	if (!cpu_dai->probed &&
 			cpu_dai->driver->probe_order == order) {
-		if (!cpu_dai->codec) {
-			if (!try_module_get(cpu_dai->dev->driver->owner))
-				return -ENODEV;
-		}
-
 		if (cpu_dai->driver->probe) {
 			ret = cpu_dai->driver->probe(cpu_dai);
 			if (ret < 0) {
 				dev_err(cpu_dai->dev,
 					"ASoC: failed to probe CPU DAI %s: %d\n",
 					cpu_dai->name, ret);
-				module_put(cpu_dai->dev->driver->owner);
 				return ret;
 			}
 		}
@@ -1654,17 +1504,24 @@ static int soc_bind_aux_dev(struct snd_soc_card *card, int num)
 {
 	struct snd_soc_pcm_runtime *rtd = &card->rtd_aux[num];
 	struct snd_soc_aux_dev *aux_dev = &card->aux_dev[num];
-	const char *codecname = aux_dev->codec_name;
+	const char *name = aux_dev->codec_name;
 
-	rtd->codec = soc_find_codec(aux_dev->codec_of_node, codecname);
-	if (!rtd->codec) {
+	rtd->component = soc_find_component(aux_dev->codec_of_node, name);
+	if (!rtd->component) {
 		if (aux_dev->codec_of_node)
-			codecname = of_node_full_name(aux_dev->codec_of_node);
+			name = of_node_full_name(aux_dev->codec_of_node);
 
-		dev_err(card->dev, "ASoC: %s not registered\n", codecname);
+		dev_err(card->dev, "ASoC: %s not registered\n", name);
 		return -EPROBE_DEFER;
 	}
 
+	/*
+	 * Some places still reference rtd->codec, so we have to keep that
+	 * initialized if the component is a CODEC. Once all those references
+	 * have been removed, this code can be removed as well.
+	 */
+	 rtd->codec = rtd->component->codec;
+
 	return 0;
 }
 
@@ -1674,18 +1531,13 @@ static int soc_probe_aux_dev(struct snd_soc_card *card, int num)
 	struct snd_soc_aux_dev *aux_dev = &card->aux_dev[num];
 	int ret;
 
-	if (rtd->codec->probed) {
-		dev_err(rtd->codec->dev, "ASoC: codec already probed\n");
-		return -EBUSY;
-	}
-
-	ret = soc_probe_codec(card, rtd->codec);
+	ret = soc_probe_component(card, rtd->component);
 	if (ret < 0)
 		return ret;
 
 	/* do machine specific initialization */
 	if (aux_dev->init) {
-		ret = aux_dev->init(&rtd->codec->dapm);
+		ret = aux_dev->init(rtd->component);
 		if (ret < 0) {
 			dev_err(card->dev, "ASoC: failed to init %s: %d\n",
 				aux_dev->name, ret);
@@ -1699,7 +1551,7 @@ static int soc_probe_aux_dev(struct snd_soc_card *card, int num)
 static void soc_remove_aux_dev(struct snd_soc_card *card, int num)
 {
 	struct snd_soc_pcm_runtime *rtd = &card->rtd_aux[num];
-	struct snd_soc_codec *codec = rtd->codec;
+	struct snd_soc_component *component = rtd->component;
 
 	/* unregister the rtd device */
 	if (rtd->dev_registered) {
@@ -1708,8 +1560,8 @@ static void soc_remove_aux_dev(struct snd_soc_card *card, int num)
 		rtd->dev_registered = 0;
 	}
 
-	if (codec && codec->probed)
-		soc_remove_codec(codec);
+	if (component && component->probed)
+		soc_remove_component(component);
 }
 
 static int snd_soc_init_codec_cache(struct snd_soc_codec *codec)
@@ -2107,19 +1959,14 @@ static struct platform_driver soc_driver = {
 int snd_soc_new_ac97_codec(struct snd_soc_codec *codec,
 	struct snd_ac97_bus_ops *ops, int num)
 {
-	mutex_lock(&codec->mutex);
-
 	codec->ac97 = kzalloc(sizeof(struct snd_ac97), GFP_KERNEL);
-	if (codec->ac97 == NULL) {
-		mutex_unlock(&codec->mutex);
+	if (codec->ac97 == NULL)
 		return -ENOMEM;
-	}
 
 	codec->ac97->bus = kzalloc(sizeof(struct snd_ac97_bus), GFP_KERNEL);
 	if (codec->ac97->bus == NULL) {
 		kfree(codec->ac97);
 		codec->ac97 = NULL;
-		mutex_unlock(&codec->mutex);
 		return -ENOMEM;
 	}
 
@@ -2132,7 +1979,6 @@ int snd_soc_new_ac97_codec(struct snd_soc_codec *codec,
 	 */
 	codec->ac97_created = 1;
 
-	mutex_unlock(&codec->mutex);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(snd_soc_new_ac97_codec);
@@ -2302,7 +2148,6 @@ EXPORT_SYMBOL_GPL(snd_soc_set_ac97_ops_of_reset);
  */
 void snd_soc_free_ac97_codec(struct snd_soc_codec *codec)
 {
-	mutex_lock(&codec->mutex);
 #ifdef CONFIG_SND_SOC_AC97_BUS
 	soc_unregister_ac97_codec(codec);
 #endif
@@ -2310,7 +2155,6 @@ void snd_soc_free_ac97_codec(struct snd_soc_codec *codec)
 	kfree(codec->ac97);
 	codec->ac97 = NULL;
 	codec->ac97_created = 0;
-	mutex_unlock(&codec->mutex);
 }
 EXPORT_SYMBOL_GPL(snd_soc_free_ac97_codec);
 
@@ -3027,9 +2871,10 @@ int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol,
 	unsigned int val, val_mask;
 	int ret;
 
-	val = ((ucontrol->value.integer.value[0] + min) & mask);
 	if (invert)
-		val = max - val;
+		val = (max - ucontrol->value.integer.value[0]) & mask;
+	else
+		val = ((ucontrol->value.integer.value[0] + min) & mask);
 	val_mask = mask << shift;
 	val = val << shift;
 
@@ -3038,9 +2883,10 @@ int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol,
 		return ret;
 
 	if (snd_soc_volsw_is_stereo(mc)) {
-		val = ((ucontrol->value.integer.value[1] + min) & mask);
 		if (invert)
-			val = max - val;
+			val = (max - ucontrol->value.integer.value[1]) & mask;
+		else
+			val = ((ucontrol->value.integer.value[1] + min) & mask);
 		val_mask = mask << shift;
 		val = val << shift;
 
@@ -3085,8 +2931,9 @@ int snd_soc_get_volsw_range(struct snd_kcontrol *kcontrol,
 	if (invert)
 		ucontrol->value.integer.value[0] =
 			max - ucontrol->value.integer.value[0];
-	ucontrol->value.integer.value[0] =
-		ucontrol->value.integer.value[0] - min;
+	else
+		ucontrol->value.integer.value[0] =
+			ucontrol->value.integer.value[0] - min;
 
 	if (snd_soc_volsw_is_stereo(mc)) {
 		ret = snd_soc_component_read(component, rreg, &val);
@@ -3097,8 +2944,9 @@ int snd_soc_get_volsw_range(struct snd_kcontrol *kcontrol,
 		if (invert)
 			ucontrol->value.integer.value[1] =
 				max - ucontrol->value.integer.value[1];
-		ucontrol->value.integer.value[1] =
-			ucontrol->value.integer.value[1] - min;
+		else
+			ucontrol->value.integer.value[1] =
+				ucontrol->value.integer.value[1] - min;
 	}
 
 	return 0;
@@ -3928,8 +3776,11 @@ EXPORT_SYMBOL_GPL(snd_soc_register_card);
  */
 int snd_soc_unregister_card(struct snd_soc_card *card)
 {
-	if (card->instantiated)
+	if (card->instantiated) {
+		card->instantiated = false;
+		snd_soc_dapm_shutdown(card);
 		soc_cleanup_card_resources(card);
+	}
 	dev_dbg(card->dev, "ASoC: Unregistered card '%s'\n", card->name);
 
 	return 0;
@@ -4116,6 +3967,8 @@ static int snd_soc_component_initialize(struct snd_soc_component *component,
 
 	component->dev = dev;
 	component->driver = driver;
+	component->probe = component->driver->probe;
+	component->remove = component->driver->remove;
 
 	if (!component->dapm_ptr)
 		component->dapm_ptr = &component->dapm;
@@ -4124,19 +3977,42 @@ static int snd_soc_component_initialize(struct snd_soc_component *component,
 	dapm->dev = dev;
 	dapm->component = component;
 	dapm->bias_level = SND_SOC_BIAS_OFF;
+	dapm->idle_bias_off = true;
 	if (driver->seq_notifier)
 		dapm->seq_notifier = snd_soc_component_seq_notifier;
 	if (driver->stream_event)
 		dapm->stream_event = snd_soc_component_stream_event;
 
+	component->controls = driver->controls;
+	component->num_controls = driver->num_controls;
+	component->dapm_widgets = driver->dapm_widgets;
+	component->num_dapm_widgets = driver->num_dapm_widgets;
+	component->dapm_routes = driver->dapm_routes;
+	component->num_dapm_routes = driver->num_dapm_routes;
+
 	INIT_LIST_HEAD(&component->dai_list);
 	mutex_init(&component->io_mutex);
 
 	return 0;
 }
 
+static void snd_soc_component_init_regmap(struct snd_soc_component *component)
+{
+	if (!component->regmap)
+		component->regmap = dev_get_regmap(component->dev, NULL);
+	if (component->regmap) {
+		int val_bytes = regmap_get_val_bytes(component->regmap);
+		/* Errors are legitimate for non-integer byte multiples */
+		if (val_bytes > 0)
+			component->val_bytes = val_bytes;
+	}
+}
+
 static void snd_soc_component_add_unlocked(struct snd_soc_component *component)
 {
+	if (!component->write && !component->read)
+		snd_soc_component_init_regmap(component);
+
 	list_add(&component->list, &component_list);
 }
 
@@ -4225,22 +4101,18 @@ found:
 }
 EXPORT_SYMBOL_GPL(snd_soc_unregister_component);
 
-static int snd_soc_platform_drv_write(struct snd_soc_component *component,
-	unsigned int reg, unsigned int val)
+static int snd_soc_platform_drv_probe(struct snd_soc_component *component)
 {
 	struct snd_soc_platform *platform = snd_soc_component_to_platform(component);
 
-	return platform->driver->write(platform, reg, val);
+	return platform->driver->probe(platform);
 }
 
-static int snd_soc_platform_drv_read(struct snd_soc_component *component,
-	unsigned int reg, unsigned int *val)
+static void snd_soc_platform_drv_remove(struct snd_soc_component *component)
 {
 	struct snd_soc_platform *platform = snd_soc_component_to_platform(component);
 
-	*val = platform->driver->read(platform, reg);
-
-	return 0;
+	platform->driver->remove(platform);
 }
 
 /**
@@ -4261,10 +4133,15 @@ int snd_soc_add_platform(struct device *dev, struct snd_soc_platform *platform,
 
 	platform->dev = dev;
 	platform->driver = platform_drv;
-	if (platform_drv->write)
-		platform->component.write = snd_soc_platform_drv_write;
-	if (platform_drv->read)
-		platform->component.read = snd_soc_platform_drv_read;
+
+	if (platform_drv->probe)
+		platform->component.probe = snd_soc_platform_drv_probe;
+	if (platform_drv->remove)
+		platform->component.remove = snd_soc_platform_drv_remove;
+
+#ifdef CONFIG_DEBUG_FS
+	platform->component.debugfs_prefix = "platform";
+#endif
 
 	mutex_lock(&client_mutex);
 	snd_soc_component_add_unlocked(&platform->component);
@@ -4315,10 +4192,10 @@ void snd_soc_remove_platform(struct snd_soc_platform *platform)
 	snd_soc_component_del_unlocked(&platform->component);
 	mutex_unlock(&client_mutex);
 
-	snd_soc_component_cleanup(&platform->component);
-
 	dev_dbg(platform->dev, "ASoC: Unregistered platform '%s'\n",
 		platform->component.name);
+
+	snd_soc_component_cleanup(&platform->component);
 }
 EXPORT_SYMBOL_GPL(snd_soc_remove_platform);
 
@@ -4386,6 +4263,20 @@ static void fixup_codec_formats(struct snd_soc_pcm_stream *stream)
 			stream->formats |= codec_format_map[i];
 }
 
+static int snd_soc_codec_drv_probe(struct snd_soc_component *component)
+{
+	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
+
+	return codec->driver->probe(codec);
+}
+
+static void snd_soc_codec_drv_remove(struct snd_soc_component *component)
+{
+	struct snd_soc_codec *codec = snd_soc_component_to_codec(component);
+
+	codec->driver->remove(codec);
+}
+
 static int snd_soc_codec_drv_write(struct snd_soc_component *component,
 	unsigned int reg, unsigned int val)
 {
@@ -4424,7 +4315,6 @@ int snd_soc_register_codec(struct device *dev,
 {
 	struct snd_soc_codec *codec;
 	struct snd_soc_dai *dai;
-	struct regmap *regmap;
 	int ret, i;
 
 	dev_dbg(dev, "codec register %s\n", dev_name(dev));
@@ -4434,18 +4324,37 @@ int snd_soc_register_codec(struct device *dev,
 		return -ENOMEM;
 
 	codec->component.dapm_ptr = &codec->dapm;
+	codec->component.codec = codec;
 
 	ret = snd_soc_component_initialize(&codec->component,
 			&codec_drv->component_driver, dev);
 	if (ret)
 		goto err_free;
 
+	if (codec_drv->controls) {
+		codec->component.controls = codec_drv->controls;
+		codec->component.num_controls = codec_drv->num_controls;
+	}
+	if (codec_drv->dapm_widgets) {
+		codec->component.dapm_widgets = codec_drv->dapm_widgets;
+		codec->component.num_dapm_widgets = codec_drv->num_dapm_widgets;
+	}
+	if (codec_drv->dapm_routes) {
+		codec->component.dapm_routes = codec_drv->dapm_routes;
+		codec->component.num_dapm_routes = codec_drv->num_dapm_routes;
+	}
+
+	if (codec_drv->probe)
+		codec->component.probe = snd_soc_codec_drv_probe;
+	if (codec_drv->remove)
+		codec->component.remove = snd_soc_codec_drv_remove;
 	if (codec_drv->write)
 		codec->component.write = snd_soc_codec_drv_write;
 	if (codec_drv->read)
 		codec->component.read = snd_soc_codec_drv_read;
 	codec->component.ignore_pmdown_time = codec_drv->ignore_pmdown_time;
-	codec->dapm.codec = codec;
+	codec->dapm.idle_bias_off = codec_drv->idle_bias_off;
+	codec->dapm.suspend_bias_off = codec_drv->suspend_bias_off;
 	if (codec_drv->seq_notifier)
 		codec->dapm.seq_notifier = codec_drv->seq_notifier;
 	if (codec_drv->set_bias_level)
@@ -4455,23 +4364,13 @@ int snd_soc_register_codec(struct device *dev,
 	codec->component.val_bytes = codec_drv->reg_word_size;
 	mutex_init(&codec->mutex);
 
-	if (!codec->component.write) {
-		if (codec_drv->get_regmap)
-			regmap = codec_drv->get_regmap(dev);
-		else
-			regmap = dev_get_regmap(dev, NULL);
-
-		if (regmap) {
-			ret = snd_soc_component_init_io(&codec->component,
-				regmap);
-			if (ret) {
-				dev_err(codec->dev,
-						"Failed to set cache I/O:%d\n",
-						ret);
-				goto err_cleanup;
-			}
-		}
-	}
+#ifdef CONFIG_DEBUG_FS
+	codec->component.init_debugfs = soc_init_codec_debugfs;
+	codec->component.debugfs_prefix = "codec";
+#endif
+
+	if (codec_drv->get_regmap)
+		codec->component.regmap = codec_drv->get_regmap(dev);
 
 	for (i = 0; i < num_dai; i++) {
 		fixup_codec_formats(&dai_drv[i].playback);
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 177bd8639ef9..c61cb9cedbcd 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -326,12 +326,13 @@ static struct list_head *dapm_kcontrol_get_path_list(
 	list_for_each_entry(path, dapm_kcontrol_get_path_list(kcontrol), \
 		list_kcontrol)
 
-static unsigned int dapm_kcontrol_get_value(const struct snd_kcontrol *kcontrol)
+unsigned int dapm_kcontrol_get_value(const struct snd_kcontrol *kcontrol)
 {
 	struct dapm_kcontrol_data *data = snd_kcontrol_chip(kcontrol);
 
 	return data->value;
 }
+EXPORT_SYMBOL_GPL(dapm_kcontrol_get_value);
 
 static bool dapm_kcontrol_set_value(const struct snd_kcontrol *kcontrol,
 	unsigned int value)
@@ -591,9 +592,9 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w,
 	int shared;
 	struct snd_kcontrol *kcontrol;
 	bool wname_in_long_name, kcname_in_long_name;
-	char *long_name;
+	char *long_name = NULL;
 	const char *name;
-	int ret;
+	int ret = 0;
 
 	prefix = soc_dapm_prefix(dapm);
 	if (prefix)
@@ -652,15 +653,17 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w,
 
 		kcontrol = snd_soc_cnew(&w->kcontrol_news[kci], NULL, name,
 					prefix);
-		kfree(long_name);
-		if (!kcontrol)
-			return -ENOMEM;
+		if (!kcontrol) {
+			ret = -ENOMEM;
+			goto exit_free;
+		}
+
 		kcontrol->private_free = dapm_kcontrol_free;
 
 		ret = dapm_kcontrol_data_alloc(w, kcontrol);
 		if (ret) {
 			snd_ctl_free_one(kcontrol);
-			return ret;
+			goto exit_free;
 		}
 
 		ret = snd_ctl_add(card, kcontrol);
@@ -668,17 +671,18 @@ static int dapm_create_or_share_mixmux_kcontrol(struct snd_soc_dapm_widget *w,
 			dev_err(dapm->dev,
 				"ASoC: failed to add widget %s dapm kcontrol %s: %d\n",
 				w->name, name, ret);
-			return ret;
+			goto exit_free;
 		}
 	}
 
 	ret = dapm_kcontrol_add_widget(kcontrol, w);
-	if (ret)
-		return ret;
+	if (ret == 0)
+		w->kcontrols[kci] = kcontrol;
 
-	w->kcontrols[kci] = kcontrol;
+exit_free:
+	kfree(long_name);
 
-	return 0;
+	return ret;
 }
 
 /* create new dapm mixer control */
@@ -1683,6 +1687,22 @@ static void dapm_power_one_widget(struct snd_soc_dapm_widget *w,
 	}
 }
 
+static bool dapm_idle_bias_off(struct snd_soc_dapm_context *dapm)
+{
+	if (dapm->idle_bias_off)
+		return true;
+
+	switch (snd_power_get_state(dapm->card->snd_card)) {
+	case SNDRV_CTL_POWER_D3hot:
+	case SNDRV_CTL_POWER_D3cold:
+		return dapm->suspend_bias_off;
+	default:
+		break;
+	}
+
+	return false;
+}
+
 /*
  * Scan each dapm widget for complete audio path.
  * A complete path is a route that has valid endpoints i.e.:-
@@ -1706,7 +1726,7 @@ static int dapm_power_widgets(struct snd_soc_card *card, int event)
 	trace_snd_soc_dapm_start(card);
 
 	list_for_each_entry(d, &card->dapm_list, list) {
-		if (d->idle_bias_off)
+		if (dapm_idle_bias_off(d))
 			d->target_bias_level = SND_SOC_BIAS_OFF;
 		else
 			d->target_bias_level = SND_SOC_BIAS_STANDBY;
@@ -1772,7 +1792,7 @@ static int dapm_power_widgets(struct snd_soc_card *card, int event)
 		if (d->target_bias_level > bias)
 			bias = d->target_bias_level;
 	list_for_each_entry(d, &card->dapm_list, list)
-		if (!d->idle_bias_off)
+		if (!dapm_idle_bias_off(d))
 			d->target_bias_level = bias;
 
 	trace_snd_soc_dapm_walk_done(card);
@@ -3109,7 +3129,8 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm,
 	}
 
 	w->dapm = dapm;
-	w->codec = dapm->codec;
+	if (dapm->component)
+		w->codec = dapm->component->codec;
 	INIT_LIST_HEAD(&w->sources);
 	INIT_LIST_HEAD(&w->sinks);
 	INIT_LIST_HEAD(&w->list);
diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c
index 6307f85e871b..b329b84bc5af 100644
--- a/sound/soc/soc-generic-dmaengine-pcm.c
+++ b/sound/soc/soc-generic-dmaengine-pcm.c
@@ -336,10 +336,12 @@ static const struct snd_pcm_ops dmaengine_pcm_ops = {
 };
 
 static const struct snd_soc_platform_driver dmaengine_pcm_platform = {
+	.component_driver = {
+		.probe_order = SND_SOC_COMP_ORDER_LATE,
+	},
 	.ops		= &dmaengine_pcm_ops,
 	.pcm_new	= dmaengine_pcm_new,
 	.pcm_free	= dmaengine_pcm_free,
-	.probe_order	= SND_SOC_COMP_ORDER_LATE,
 };
 
 static const char * const dmaengine_pcm_dma_channel_names[] = {
diff --git a/sound/soc/soc-io.c b/sound/soc/soc-io.c
index 7767fbd73eb7..9b3939049cef 100644
--- a/sound/soc/soc-io.c
+++ b/sound/soc/soc-io.c
@@ -271,31 +271,3 @@ int snd_soc_platform_write(struct snd_soc_platform *platform,
 	return snd_soc_component_write(&platform->component, reg, val);
 }
 EXPORT_SYMBOL_GPL(snd_soc_platform_write);
-
-/**
- * snd_soc_component_init_io() - Initialize regmap IO
- *
- * @component: component to initialize
- * @regmap: regmap instance to use for IO operations
- *
- * Return: 0 on success, a negative error code otherwise
- */
-int snd_soc_component_init_io(struct snd_soc_component *component,
-	struct regmap *regmap)
-{
-	int ret;
-
-	if (!regmap)
-		return -EINVAL;
-
-	ret = regmap_get_val_bytes(regmap);
-	/* Errors are legitimate for non-integer byte
-	 * multiples */
-	if (ret > 0)
-		component->val_bytes = ret;
-
-	component->regmap = regmap;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_soc_component_init_io);
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 642c86240752..002311afdeaa 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -352,7 +352,7 @@ static void soc_pcm_apply_msb(struct snd_pcm_substream *substream)
 	} else {
 		for (i = 0; i < rtd->num_codecs; i++) {
 			codec_dai = rtd->codec_dais[i];
-			if (codec_dai->driver->playback.sig_bits == 0) {
+			if (codec_dai->driver->capture.sig_bits == 0) {
 				bits = 0;
 				break;
 			}
diff --git a/sound/soc/tegra/tegra_max98090.c b/sound/soc/tegra/tegra_max98090.c
index b86cd9936ef1..01921d7e73fa 100644
--- a/sound/soc/tegra/tegra_max98090.c
+++ b/sound/soc/tegra/tegra_max98090.c
@@ -42,6 +42,7 @@
 struct tegra_max98090 {
 	struct tegra_asoc_utils_data util_data;
 	int gpio_hp_det;
+	int gpio_mic_det;
 };
 
 static int tegra_max98090_asoc_hw_params(struct snd_pcm_substream *substream,
@@ -112,6 +113,22 @@ static struct snd_soc_jack_gpio tegra_max98090_hp_jack_gpio = {
 	.invert = 1,
 };
 
+static struct snd_soc_jack tegra_max98090_mic_jack;
+
+static struct snd_soc_jack_pin tegra_max98090_mic_jack_pins[] = {
+	{
+		.pin = "Mic Jack",
+		.mask = SND_JACK_MICROPHONE,
+	},
+};
+
+static struct snd_soc_jack_gpio tegra_max98090_mic_jack_gpio = {
+	.name = "Mic detection",
+	.report = SND_JACK_MICROPHONE,
+	.debounce_time = 150,
+	.invert = 1,
+};
+
 static const struct snd_soc_dapm_widget tegra_max98090_dapm_widgets[] = {
 	SND_SOC_DAPM_HP("Headphones", NULL),
 	SND_SOC_DAPM_SPK("Speakers", NULL),
@@ -141,6 +158,19 @@ static int tegra_max98090_asoc_init(struct snd_soc_pcm_runtime *rtd)
 					&tegra_max98090_hp_jack_gpio);
 	}
 
+	if (gpio_is_valid(machine->gpio_mic_det)) {
+		snd_soc_jack_new(codec, "Mic Jack", SND_JACK_MICROPHONE,
+				 &tegra_max98090_mic_jack);
+		snd_soc_jack_add_pins(&tegra_max98090_mic_jack,
+				      ARRAY_SIZE(tegra_max98090_mic_jack_pins),
+				      tegra_max98090_mic_jack_pins);
+
+		tegra_max98090_mic_jack_gpio.gpio = machine->gpio_mic_det;
+		snd_soc_jack_add_gpios(&tegra_max98090_mic_jack,
+				       1,
+				       &tegra_max98090_mic_jack_gpio);
+	}
+
 	return 0;
 }
 
@@ -153,6 +183,11 @@ static int tegra_max98090_card_remove(struct snd_soc_card *card)
 					&tegra_max98090_hp_jack_gpio);
 	}
 
+	if (gpio_is_valid(machine->gpio_mic_det)) {
+		snd_soc_jack_free_gpios(&tegra_max98090_mic_jack, 1,
+					&tegra_max98090_mic_jack_gpio);
+	}
+
 	return 0;
 }
 
@@ -201,6 +236,11 @@ static int tegra_max98090_probe(struct platform_device *pdev)
 	if (machine->gpio_hp_det == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
+	machine->gpio_mic_det =
+			of_get_named_gpio(np, "nvidia,mic-det-gpios", 0);
+	if (machine->gpio_mic_det == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
 	ret = snd_soc_of_parse_card_name(card, "nvidia,model");
 	if (ret)
 		goto err;
diff --git a/sound/soc/txx9/txx9aclc.c b/sound/soc/txx9/txx9aclc.c
index f0829de28708..cd71fd889d8b 100644
--- a/sound/soc/txx9/txx9aclc.c
+++ b/sound/soc/txx9/txx9aclc.c
@@ -16,6 +16,7 @@
 #include <linux/platform_device.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
+#include <linux/dmaengine.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -137,7 +138,7 @@ txx9aclc_dma_submit(struct txx9aclc_dmadata *dmadata, dma_addr_t buf_dma_addr)
 	}
 	desc->callback = txx9aclc_dma_complete;
 	desc->callback_param = dmadata;
-	desc->tx_submit(desc);
+	dmaengine_submit(desc);
 	return desc;
 }
 
@@ -160,7 +161,7 @@ static void txx9aclc_dma_tasklet(unsigned long data)
 		void __iomem *base = drvdata->base;
 
 		spin_unlock_irqrestore(&dmadata->dma_lock, flags);
-		chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
+		dmaengine_terminate_all(chan);
 		/* first time */
 		for (i = 0; i < NR_DMA_CHAIN; i++) {
 			desc = txx9aclc_dma_submit(dmadata,
@@ -169,7 +170,7 @@ static void txx9aclc_dma_tasklet(unsigned long data)
 				return;
 		}
 		dmadata->dmacount = NR_DMA_CHAIN;
-		chan->device->device_issue_pending(chan);
+		dma_async_issue_pending(chan);
 		spin_lock_irqsave(&dmadata->dma_lock, flags);
 		__raw_writel(ctlbit, base + ACCTLEN);
 		dmadata->frag_count = NR_DMA_CHAIN % dmadata->frags;
@@ -188,7 +189,7 @@ static void txx9aclc_dma_tasklet(unsigned long data)
 			dmadata->frag_count * dmadata->frag_bytes);
 		if (!desc)
 			return;
-		chan->device->device_issue_pending(chan);
+		dma_async_issue_pending(chan);
 
 		spin_lock_irqsave(&dmadata->dma_lock, flags);
 		dmadata->frag_count++;
@@ -266,7 +267,7 @@ static int txx9aclc_pcm_close(struct snd_pcm_substream *substream)
 	struct dma_chan *chan = dmadata->dma_chan;
 
 	dmadata->frag_count = -1;
-	chan->device->device_control(chan, DMA_TERMINATE_ALL, 0);
+	dmaengine_terminate_all(chan);
 	return 0;
 }
 
@@ -398,8 +399,7 @@ static int txx9aclc_pcm_remove(struct snd_soc_platform *platform)
 		struct dma_chan *chan = dmadata->dma_chan;
 		if (chan) {
 			dmadata->frag_count = -1;
-			chan->device->device_control(chan,
-						     DMA_TERMINATE_ALL, 0);
+			dmaengine_terminate_all(chan);
 			dma_release_channel(chan);
 		}
 		dev->dmadata[i].dma_chan = NULL;
diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c
index 7103b0908d13..272844746135 100644
--- a/sound/usb/caiaq/audio.c
+++ b/sound/usb/caiaq/audio.c
@@ -816,6 +816,11 @@ int snd_usb_caiaq_audio_init(struct snd_usb_caiaqdev *cdev)
 		return -EINVAL;
 	}
 
+	if (cdev->n_streams < 2) {
+		dev_err(dev, "bogus number of streams: %d\n", cdev->n_streams);
+		return -EINVAL;
+	}
+
 	ret = snd_pcm_new(cdev->chip.card, cdev->product_name, 0,
 			cdev->n_audio_out, cdev->n_audio_in, &cdev->pcm);
 
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index b2b6f398a4e1..d3d49525a16b 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1506,6 +1506,12 @@ static struct port_info {
 	PORT_INFO(vendor, product, num, name, 0, \
 		  SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC | \
 		  SNDRV_SEQ_PORT_TYPE_HARDWARE)
+#define GM_SYNTH_PORT(vendor, product, num, name, voices) \
+	PORT_INFO(vendor, product, num, name, voices, \
+		  SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC | \
+		  SNDRV_SEQ_PORT_TYPE_MIDI_GM | \
+		  SNDRV_SEQ_PORT_TYPE_HARDWARE | \
+		  SNDRV_SEQ_PORT_TYPE_SYNTHESIZER)
 #define ROLAND_SYNTH_PORT(vendor, product, num, name, voices) \
 	PORT_INFO(vendor, product, num, name, voices, \
 		  SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC | \
@@ -1525,6 +1531,11 @@ static struct port_info {
 		  SNDRV_SEQ_PORT_TYPE_MIDI_MT32 | \
 		  SNDRV_SEQ_PORT_TYPE_HARDWARE | \
 		  SNDRV_SEQ_PORT_TYPE_SYNTHESIZER)
+	/* Yamaha MOTIF XF */
+	GM_SYNTH_PORT(0x0499, 0x105c, 0, "%s Tone Generator", 128),
+	CONTROL_PORT(0x0499, 0x105c, 1, "%s Remote Control"),
+	EXTERNAL_PORT(0x0499, 0x105c, 2, "%s Thru"),
+	CONTROL_PORT(0x0499, 0x105c, 3, "%s Editor"),
 	/* Roland UA-100 */
 	CONTROL_PORT(0x0582, 0x0000, 2, "%s Control"),
 	/* Roland SC-8850 */
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 19a921eb75f1..d2aa45a8d895 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1174,5 +1174,21 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 		}
 	}
 
+	/* XMOS based USB DACs */
+	switch (chip->usb_id) {
+	/* iFi Audio micro/nano iDSD */
+	case USB_ID(0x20b1, 0x3008):
+		if (fp->altsetting == 2)
+			return SNDRV_PCM_FMTBIT_DSD_U32_LE;
+		break;
+	/* DIYINHK DSD DXD 384kHz USB to I2S/DSD */
+	case USB_ID(0x20b1, 0x2009):
+		if (fp->altsetting == 3)
+			return SNDRV_PCM_FMTBIT_DSD_U32_LE;
+		break;
+	default:
+		break;
+	}
+
 	return 0;
 }
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index ce00f7ee6455..36c08b1f4afb 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -10,9 +10,14 @@ LIB_OBJS=
 
 LIB_H += fs/debugfs.h
 LIB_H += fs/fs.h
+# See comment below about piggybacking...
+LIB_H += fd/array.h
 
 LIB_OBJS += $(OUTPUT)fs/debugfs.o
 LIB_OBJS += $(OUTPUT)fs/fs.o
+# XXX piggybacking here, need to introduce libapikfd, or rename this
+# to plain libapik.a and make it have it all api goodies
+LIB_OBJS += $(OUTPUT)fd/array.o
 
 LIBFILE = libapikfs.a
 
@@ -29,7 +34,7 @@ $(LIBFILE): $(LIB_OBJS)
 $(LIB_OBJS): $(LIB_H)
 
 libapi_dirs:
-	$(QUIET_MKDIR)mkdir -p $(OUTPUT)fs/
+	$(QUIET_MKDIR)mkdir -p $(OUTPUT)fd $(OUTPUT)fs
 
 $(OUTPUT)%.o: %.c libapi_dirs
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
diff --git a/tools/lib/api/fd/array.c b/tools/lib/api/fd/array.c
new file mode 100644
index 000000000000..0e636c4339b8
--- /dev/null
+++ b/tools/lib/api/fd/array.c
@@ -0,0 +1,127 @@
+/*
+ * Copyright (C) 2014, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "array.h"
+#include <errno.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+void fdarray__init(struct fdarray *fda, int nr_autogrow)
+{
+	fda->entries	 = NULL;
+	fda->priv	 = NULL;
+	fda->nr		 = fda->nr_alloc = 0;
+	fda->nr_autogrow = nr_autogrow;
+}
+
+int fdarray__grow(struct fdarray *fda, int nr)
+{
+	void *priv;
+	int nr_alloc = fda->nr_alloc + nr;
+	size_t psize = sizeof(fda->priv[0]) * nr_alloc;
+	size_t size  = sizeof(struct pollfd) * nr_alloc;
+	struct pollfd *entries = realloc(fda->entries, size);
+
+	if (entries == NULL)
+		return -ENOMEM;
+
+	priv = realloc(fda->priv, psize);
+	if (priv == NULL) {
+		free(entries);
+		return -ENOMEM;
+	}
+
+	fda->nr_alloc = nr_alloc;
+	fda->entries  = entries;
+	fda->priv     = priv;
+	return 0;
+}
+
+struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow)
+{
+	struct fdarray *fda = calloc(1, sizeof(*fda));
+
+	if (fda != NULL) {
+		if (fdarray__grow(fda, nr_alloc)) {
+			free(fda);
+			fda = NULL;
+		} else {
+			fda->nr_autogrow = nr_autogrow;
+		}
+	}
+
+	return fda;
+}
+
+void fdarray__exit(struct fdarray *fda)
+{
+	free(fda->entries);
+	free(fda->priv);
+	fdarray__init(fda, 0);
+}
+
+void fdarray__delete(struct fdarray *fda)
+{
+	fdarray__exit(fda);
+	free(fda);
+}
+
+int fdarray__add(struct fdarray *fda, int fd, short revents)
+{
+	int pos = fda->nr;
+
+	if (fda->nr == fda->nr_alloc &&
+	    fdarray__grow(fda, fda->nr_autogrow) < 0)
+		return -ENOMEM;
+
+	fda->entries[fda->nr].fd     = fd;
+	fda->entries[fda->nr].events = revents;
+	fda->nr++;
+	return pos;
+}
+
+int fdarray__filter(struct fdarray *fda, short revents,
+		    void (*entry_destructor)(struct fdarray *fda, int fd))
+{
+	int fd, nr = 0;
+
+	if (fda->nr == 0)
+		return 0;
+
+	for (fd = 0; fd < fda->nr; ++fd) {
+		if (fda->entries[fd].revents & revents) {
+			if (entry_destructor)
+				entry_destructor(fda, fd);
+
+			continue;
+		}
+
+		if (fd != nr) {
+			fda->entries[nr] = fda->entries[fd];
+			fda->priv[nr]	 = fda->priv[fd];
+		}
+
+		++nr;
+	}
+
+	return fda->nr = nr;
+}
+
+int fdarray__poll(struct fdarray *fda, int timeout)
+{
+	return poll(fda->entries, fda->nr, timeout);
+}
+
+int fdarray__fprintf(struct fdarray *fda, FILE *fp)
+{
+	int fd, printed = fprintf(fp, "%d [ ", fda->nr);
+
+	for (fd = 0; fd < fda->nr; ++fd)
+		printed += fprintf(fp, "%s%d", fd ? ", " : "", fda->entries[fd].fd);
+
+	return printed + fprintf(fp, " ]");
+}
diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h
new file mode 100644
index 000000000000..45db01818f45
--- /dev/null
+++ b/tools/lib/api/fd/array.h
@@ -0,0 +1,46 @@
+#ifndef __API_FD_ARRAY__
+#define __API_FD_ARRAY__
+
+#include <stdio.h>
+
+struct pollfd;
+
+/**
+ * struct fdarray: Array of file descriptors
+ *
+ * @priv: Per array entry priv area, users should access just its contents,
+ *	  not set it to anything, as it is kept in synch with @entries, being
+ *	  realloc'ed, * for instance, in fdarray__{grow,filter}.
+ *
+ *	  I.e. using 'fda->priv[N].idx = * value' where N < fda->nr is ok,
+ *	  but doing 'fda->priv = malloc(M)' is not allowed.
+ */
+struct fdarray {
+	int	       nr;
+	int	       nr_alloc;
+	int	       nr_autogrow;
+	struct pollfd *entries;
+	union {
+		int    idx;
+	} *priv;
+};
+
+void fdarray__init(struct fdarray *fda, int nr_autogrow);
+void fdarray__exit(struct fdarray *fda);
+
+struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow);
+void fdarray__delete(struct fdarray *fda);
+
+int fdarray__add(struct fdarray *fda, int fd, short revents);
+int fdarray__poll(struct fdarray *fda, int timeout);
+int fdarray__filter(struct fdarray *fda, short revents,
+		    void (*entry_destructor)(struct fdarray *fda, int fd));
+int fdarray__grow(struct fdarray *fda, int extra);
+int fdarray__fprintf(struct fdarray *fda, FILE *fp);
+
+static inline int fdarray__available_entries(struct fdarray *fda)
+{
+	return fda->nr_alloc - fda->nr;
+}
+
+#endif /* __API_FD_ARRAY__ */
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 782d86e961b9..717221e98450 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -15,6 +15,7 @@ perf.data
 perf.data.old
 output.svg
 perf-archive
+perf-with-kcore
 tags
 TAGS
 cscope*
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 1513935c399b..aaa869be3dc1 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -104,6 +104,9 @@ OPTIONS
 	Specify path to the executable or shared library file for user
 	space tracing. Can also be used with --funcs option.
 
+--demangle-kernel::
+	Demangle kernel symbols.
+
 In absence of -m/-x options, perf probe checks if the first argument after
 the options is an absolute path name. If its an absolute path, perf probe
 uses it as a target module/target user space binary to probe.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index d2b59af62bc0..0927bf4e6c2a 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -147,7 +147,7 @@ OPTIONS
 -w::
 --column-widths=<width[,width...]>::
 	Force each column width to the provided list, for large terminal
-	readability.
+	readability.  0 means no limit (default behavior).
 
 -t::
 --field-separator=::
@@ -276,6 +276,9 @@ OPTIONS
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.
 
+--demangle-kernel::
+	Demangle kernel symbol names to human readable form (for C++ kernels).
+
 --mem-mode::
 	Use the data addresses of samples in addition to instruction addresses
 	to build the histograms.  To generate meaningful output, the perf.data
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 180ae02137a5..3265b1070518 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -98,6 +98,9 @@ Default is to monitor all CPUS.
 --hide_user_symbols::
         Hide user symbols.
 
+--demangle-kernel::
+        Demangle kernel symbols.
+
 -D::
 --dump-symtab::
         Dump the symbol table used for profiling.
@@ -193,6 +196,12 @@ Default is to monitor all CPUS.
 	sum of shown entries will be always 100%. "absolute" means it retains
 	the original value before and after the filter is applied.
 
+-w::
+--column-widths=<width[,width...]>::
+	Force each column width to the provided list, for large terminal
+	readability.  0 means no limit (default behavior).
+
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 2240974b7745..262916f4a377 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -126,6 +126,7 @@ PYRF_OBJS =
 SCRIPT_SH =
 
 SCRIPT_SH += perf-archive.sh
+SCRIPT_SH += perf-with-kcore.sh
 
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
@@ -263,6 +264,7 @@ LIB_H += util/xyarray.h
 LIB_H += util/header.h
 LIB_H += util/help.h
 LIB_H += util/session.h
+LIB_H += util/ordered-events.h
 LIB_H += util/strbuf.h
 LIB_H += util/strlist.h
 LIB_H += util/strfilter.h
@@ -347,6 +349,7 @@ LIB_OBJS += $(OUTPUT)util/machine.o
 LIB_OBJS += $(OUTPUT)util/map.o
 LIB_OBJS += $(OUTPUT)util/pstack.o
 LIB_OBJS += $(OUTPUT)util/session.o
+LIB_OBJS += $(OUTPUT)util/ordered-events.o
 LIB_OBJS += $(OUTPUT)util/comm.o
 LIB_OBJS += $(OUTPUT)util/thread.o
 LIB_OBJS += $(OUTPUT)util/thread_map.o
@@ -399,6 +402,7 @@ LIB_OBJS += $(OUTPUT)tests/perf-record.o
 LIB_OBJS += $(OUTPUT)tests/rdpmc.o
 LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o
 LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o
+LIB_OBJS += $(OUTPUT)tests/fdarray.o
 LIB_OBJS += $(OUTPUT)tests/pmu.o
 LIB_OBJS += $(OUTPUT)tests/hists_common.o
 LIB_OBJS += $(OUTPUT)tests/hists_link.o
@@ -423,6 +427,7 @@ endif
 endif
 LIB_OBJS += $(OUTPUT)tests/mmap-thread-lookup.o
 LIB_OBJS += $(OUTPUT)tests/thread-mg-share.o
+LIB_OBJS += $(OUTPUT)tests/switch-tracking.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
@@ -765,7 +770,7 @@ $(LIBTRACEEVENT)-clean:
 install-traceevent-plugins: $(LIBTRACEEVENT)
 	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) install_plugins
 
-LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch])
+LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch] $(LIB_PATH)fd/*.[ch])
 
 # if subdir is set, we've been called from above so target has been built
 # already
@@ -875,6 +880,8 @@ install-bin: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+	$(call QUIET_INSTALL, perf-with-kcore) \
+		$(INSTALL) $(OUTPUT)perf-with-kcore -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBPERL
 	$(call QUIET_INSTALL, perl-scripts) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'; \
@@ -920,7 +927,7 @@ config-clean:
 	@$(MAKE) -C config/feature-checks clean >/dev/null
 
 clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
-	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
+	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
index 9f870d27cb39..62eff847f91c 100644
--- a/tools/perf/arch/arm/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
 #include "thread.h"
 #include "map.h"
 #include "event.h"
+#include "debug.h"
 #include "tests/tests.h"
 
 #define STACK_SIZE 8192
diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
index 729ed69a6664..62c397ed3d97 100644
--- a/tools/perf/arch/arm/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -3,6 +3,7 @@
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
+#include "../../util/debug.h"
 
 int libunwind__arch_reg_id(int regnum)
 {
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index e9441b9e2a30..1d3f39c3aa56 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -6,6 +6,8 @@
 #include <asm/perf_regs.h>
 
 #define PERF_REGS_MASK	((1ULL << PERF_REG_ARM64_MAX) - 1)
+#define PERF_REGS_MAX	PERF_REG_ARM64_MAX
+
 #define PERF_REG_IP	PERF_REG_ARM64_PC
 #define PERF_REG_SP	PERF_REG_ARM64_SP
 
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
index 436ee43859dc..a87afa91a99e 100644
--- a/tools/perf/arch/arm64/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -3,6 +3,7 @@
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
+#include "../../util/debug.h"
 
 int libunwind__arch_reg_id(int regnum)
 {
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 42faf369211c..49776f190abf 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -12,6 +12,11 @@ const char *const arm_triplets[] = {
 	NULL
 };
 
+const char *const arm64_triplets[] = {
+	"aarch64-linux-android-",
+	NULL
+};
+
 const char *const powerpc_triplets[] = {
 	"powerpc-unknown-linux-gnu-",
 	"powerpc64-unknown-linux-gnu-",
@@ -105,6 +110,8 @@ static const char *normalize_arch(char *arch)
 		return "x86";
 	if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
 		return "sparc";
+	if (!strcmp(arch, "aarch64") || !strcmp(arch, "arm64"))
+		return "arm64";
 	if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
 		return "arm";
 	if (!strncmp(arch, "s390", 4))
@@ -159,6 +166,8 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
 
 	if (!strcmp(arch, "arm"))
 		path_list = arm_triplets;
+	else if (!strcmp(arch, "arm64"))
+		path_list = arm64_triplets;
 	else if (!strcmp(arch, "powerpc"))
 		path_list = powerpc_triplets;
 	else if (!strcmp(arch, "sh"))
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index b92219b1900d..6f7782bea5dd 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,6 +1,6 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
-LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index a7c23a4b3778..d73ef8bb08c7 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -15,6 +15,7 @@
 
 #include "util/thread.h"
 #include "util/callchain.h"
+#include "util/debug.h"
 
 /*
  * When saving the callchain on Power, the kernel conservatively saves
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index a84206e9c4aa..fc9bebd2cca0 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -26,6 +26,7 @@ static unsigned int nsecs    = 10;
 /* amount of futexes per thread */
 static unsigned int nfutexes = 1024;
 static bool fshared = false, done = false, silent = false;
+static int futex_flag = 0;
 
 struct timeval start, end, runtime;
 static pthread_mutex_t thread_lock;
@@ -75,8 +76,7 @@ static void *workerfn(void *arg)
 			 * such as internal waitqueue handling, thus enlarging
 			 * the critical region protected by hb->lock.
 			 */
-			ret = futex_wait(&w->futex[i], 1234, NULL,
-					 fshared ? 0 : FUTEX_PRIVATE_FLAG);
+			ret = futex_wait(&w->futex[i], 1234, NULL, futex_flag);
 			if (!silent &&
 			    (!ret || errno != EAGAIN || errno != EWOULDBLOCK))
 				warn("Non-expected futex return call");
@@ -135,6 +135,9 @@ int bench_futex_hash(int argc, const char **argv,
 	if (!worker)
 		goto errmem;
 
+	if (!fshared)
+		futex_flag = FUTEX_PRIVATE_FLAG;
+
 	printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n",
 	       getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs);
 
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 732403bfd31a..bedff6b5b3cf 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -30,16 +30,18 @@ static u_int32_t futex1 = 0, futex2 = 0;
 static unsigned int nrequeue = 1;
 
 static pthread_t *worker;
-static bool done = 0, silent = 0;
+static bool done = false, silent = false, fshared = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats requeuetime_stats, requeued_stats;
 static unsigned int ncpus, threads_starting, nthreads = 0;
+static int futex_flag = 0;
 
 static const struct option options[] = {
 	OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
 	OPT_BOOLEAN( 's', "silent",   &silent,   "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",   &fshared,  "Use shared futexes instead of private ones"),
 	OPT_END()
 };
 
@@ -70,7 +72,7 @@ static void *workerfn(void *arg __maybe_unused)
 	pthread_cond_wait(&thread_worker, &thread_lock);
 	pthread_mutex_unlock(&thread_lock);
 
-	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	futex_wait(&futex1, 0, NULL, futex_flag);
 	return NULL;
 }
 
@@ -127,9 +129,12 @@ int bench_futex_requeue(int argc, const char **argv,
 	if (!worker)
 		err(EXIT_FAILURE, "calloc");
 
-	printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), "
-	       "%d at a time.\n\n",
-	       getpid(), nthreads, &futex1, &futex2, nrequeue);
+	if (!fshared)
+		futex_flag = FUTEX_PRIVATE_FLAG;
+
+	printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
+	       "%d at a time.\n\n",  getpid(), nthreads,
+	       fshared ? "shared":"private", &futex1, &futex2, nrequeue);
 
 	init_stats(&requeued_stats);
 	init_stats(&requeuetime_stats);
@@ -156,16 +161,20 @@ int bench_futex_requeue(int argc, const char **argv,
 
 		/* Ok, all threads are patiently blocked, start requeueing */
 		gettimeofday(&start, NULL);
-		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue)
+		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) {
 			/*
 			 * Do not wakeup any tasks blocked on futex1, allowing
 			 * us to really measure futex_wait functionality.
 			 */
-			futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue,
-					  FUTEX_PRIVATE_FLAG);
+			futex_cmp_requeue(&futex1, 0, &futex2, 0,
+					  nrequeue, futex_flag);
+		}
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
+		if (nrequeued > nthreads)
+			nrequeued = nthreads;
+
 		update_stats(&requeued_stats, nrequeued);
 		update_stats(&requeuetime_stats, runtime.tv_usec);
 
@@ -175,7 +184,7 @@ int bench_futex_requeue(int argc, const char **argv,
 		}
 
 		/* everybody should be blocked on futex2, wake'em up */
-		nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG);
+		nrequeued = futex_wake(&futex2, nthreads, futex_flag);
 		if (nthreads != nrequeued)
 			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
 
@@ -184,7 +193,6 @@ int bench_futex_requeue(int argc, const char **argv,
 			if (ret)
 				err(EXIT_FAILURE, "pthread_join");
 		}
-
 	}
 
 	/* cleanup & report results */
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 50022cbce87e..929f762be47e 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -31,16 +31,18 @@ static u_int32_t futex1 = 0;
 static unsigned int nwakes = 1;
 
 pthread_t *worker;
-static bool done = false, silent = false;
+static bool done = false, silent = false, fshared = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats waketime_stats, wakeup_stats;
 static unsigned int ncpus, threads_starting, nthreads = 0;
+static int futex_flag = 0;
 
 static const struct option options[] = {
 	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('w', "nwakes",  &nwakes,   "Specify amount of threads to wake at once"),
 	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &fshared,  "Use shared futexes instead of private ones"),
 	OPT_END()
 };
 
@@ -58,7 +60,7 @@ static void *workerfn(void *arg __maybe_unused)
 	pthread_cond_wait(&thread_worker, &thread_lock);
 	pthread_mutex_unlock(&thread_lock);
 
-	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	futex_wait(&futex1, 0, NULL, futex_flag);
 	return NULL;
 }
 
@@ -130,9 +132,12 @@ int bench_futex_wake(int argc, const char **argv,
 	if (!worker)
 		err(EXIT_FAILURE, "calloc");
 
-	printf("Run summary [PID %d]: blocking on %d threads (at futex %p), "
+	if (!fshared)
+		futex_flag = FUTEX_PRIVATE_FLAG;
+
+	printf("Run summary [PID %d]: blocking on %d threads (at [%s] futex %p), "
 	       "waking up %d at a time.\n\n",
-	       getpid(), nthreads, &futex1, nwakes);
+	       getpid(), nthreads, fshared ? "shared":"private",  &futex1, nwakes);
 
 	init_stats(&wakeup_stats);
 	init_stats(&waketime_stats);
@@ -160,7 +165,7 @@ int bench_futex_wake(int argc, const char **argv,
 		/* Ok, all threads are patiently blocked, start waking folks up */
 		gettimeofday(&start, NULL);
 		while (nwoken != nthreads)
-			nwoken += futex_wake(&futex1, nwakes, FUTEX_PRIVATE_FLAG);
+			nwoken += futex_wake(&futex1, nwakes, futex_flag);
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 52a56599a543..d7f281c2828d 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -26,7 +26,7 @@
 #include <sys/socket.h>
 #include <sys/wait.h>
 #include <sys/time.h>
-#include <sys/poll.h>
+#include <poll.h>
 #include <limits.h>
 #include <err.h>
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 1ec429fef2be..be5939418425 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -36,7 +36,8 @@
 
 struct perf_annotate {
 	struct perf_tool tool;
-	bool	   force, use_tui, use_stdio, use_gtk;
+	struct perf_session *session;
+	bool	   use_tui, use_stdio, use_gtk;
 	bool	   full_paths;
 	bool	   print_line;
 	bool	   skip_missing;
@@ -188,18 +189,9 @@ find_next:
 static int __cmd_annotate(struct perf_annotate *ann)
 {
 	int ret;
-	struct perf_session *session;
+	struct perf_session *session = ann->session;
 	struct perf_evsel *pos;
 	u64 total_nr_samples;
-	struct perf_data_file file = {
-		.path  = input_name,
-		.mode  = PERF_DATA_MODE_READ,
-		.force = ann->force,
-	};
-
-	session = perf_session__new(&file, false, &ann->tool);
-	if (session == NULL)
-		return -ENOMEM;
 
 	machines__set_symbol_filter(&session->machines, symbol__annotate_init);
 
@@ -207,22 +199,22 @@ static int __cmd_annotate(struct perf_annotate *ann)
 		ret = perf_session__cpu_bitmap(session, ann->cpu_list,
 					       ann->cpu_bitmap);
 		if (ret)
-			goto out_delete;
+			goto out;
 	}
 
 	if (!objdump_path) {
 		ret = perf_session_env__lookup_objdump(&session->header.env);
 		if (ret)
-			goto out_delete;
+			goto out;
 	}
 
 	ret = perf_session__process_events(session, &ann->tool);
 	if (ret)
-		goto out_delete;
+		goto out;
 
 	if (dump_trace) {
 		perf_session__fprintf_nr_events(session, stdout);
-		goto out_delete;
+		goto out;
 	}
 
 	if (verbose > 3)
@@ -250,8 +242,8 @@ static int __cmd_annotate(struct perf_annotate *ann)
 	}
 
 	if (total_nr_samples == 0) {
-		ui__error("The %s file has no samples!\n", file.path);
-		goto out_delete;
+		ui__error("The %s file has no samples!\n", session->file->path);
+		goto out;
 	}
 
 	if (use_browser == 2) {
@@ -261,24 +253,12 @@ static int __cmd_annotate(struct perf_annotate *ann)
 					 "perf_gtk__show_annotations");
 		if (show_annotations == NULL) {
 			ui__error("GTK browser not found!\n");
-			goto out_delete;
+			goto out;
 		}
 		show_annotations();
 	}
 
-out_delete:
-	/*
-	 * Speed up the exit process, for large files this can
-	 * take quite a while.
-	 *
-	 * XXX Enable this when using valgrind or if we ever
-	 * librarize this command.
-	 *
-	 * Also experiment with obstacks to see how much speed
-	 * up we'll get here.
-	 *
-	 * perf_session__delete(session);
-	 */
+out:
 	return ret;
 }
 
@@ -297,10 +277,14 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 			.comm	= perf_event__process_comm,
 			.exit	= perf_event__process_exit,
 			.fork	= perf_event__process_fork,
-			.ordered_samples = true,
+			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},
 	};
+	struct perf_data_file file = {
+		.path  = input_name,
+		.mode  = PERF_DATA_MODE_READ,
+	};
 	const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
@@ -308,7 +292,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "only consider symbols in these dsos"),
 	OPT_STRING('s', "symbol", &annotate.sym_hist_filter, "symbol",
 		    "symbol to annotate"),
-	OPT_BOOLEAN('f', "force", &annotate.force, "don't complain, do it"),
+	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
@@ -341,6 +325,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show event group information together"),
 	OPT_END()
 	};
+	int ret;
 
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 
@@ -353,11 +338,16 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	setup_browser(true);
 
+	annotate.session = perf_session__new(&file, false, &annotate.tool);
+	if (annotate.session == NULL)
+		return -1;
+
 	symbol_conf.priv_size = sizeof(struct annotation);
 	symbol_conf.try_vmlinux_path = true;
 
-	if (symbol__init() < 0)
-		return -1;
+	ret = symbol__init(&annotate.session->header.env);
+	if (ret < 0)
+		goto out_delete;
 
 	if (setup_sorting() < 0)
 		usage_with_options(annotate_usage, options);
@@ -373,5 +363,20 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		annotate.sym_hist_filter = argv[0];
 	}
 
-	return __cmd_annotate(&annotate);
+	ret = __cmd_annotate(&annotate);
+
+out_delete:
+	/*
+	 * Speed up the exit process, for large files this can
+	 * take quite a while.
+	 *
+	 * XXX Enable this when using valgrind or if we ever
+	 * librarize this command.
+	 *
+	 * Also experiment with obstacks to see how much speed
+	 * up we'll get here.
+	 *
+	 * perf_session__delete(session);
+	 */
+	return ret;
 }
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 2a2c78f80876..70385756da63 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -246,20 +246,9 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
 	return true;
 }
 
-static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp)
+static int build_id_cache__fprintf_missing(struct perf_session *session, FILE *fp)
 {
-	struct perf_data_file file = {
-		.path  = filename,
-		.mode  = PERF_DATA_MODE_READ,
-		.force = force,
-	};
-	struct perf_session *session = perf_session__new(&file, false, NULL);
-	if (session == NULL)
-		return -1;
-
 	perf_session__fprintf_dsos_buildid(session, fp, dso__missing_buildid_cache, 0);
-	perf_session__delete(session);
-
 	return 0;
 }
 
@@ -302,6 +291,12 @@ int cmd_buildid_cache(int argc, const char **argv,
 		   *missing_filename = NULL,
 		   *update_name_list_str = NULL,
 		   *kcore_filename;
+	char sbuf[STRERR_BUFSIZE];
+
+	struct perf_data_file file = {
+		.mode  = PERF_DATA_MODE_READ,
+	};
+	struct perf_session *session = NULL;
 
 	const struct option buildid_cache_options[] = {
 	OPT_STRING('a', "add", &add_name_list_str,
@@ -326,8 +321,17 @@ int cmd_buildid_cache(int argc, const char **argv,
 	argc = parse_options(argc, argv, buildid_cache_options,
 			     buildid_cache_usage, 0);
 
-	if (symbol__init() < 0)
-		return -1;
+	if (missing_filename) {
+		file.path = missing_filename;
+		file.force = force;
+
+		session = perf_session__new(&file, false, NULL);
+		if (session == NULL)
+			return -1;
+	}
+
+	if (symbol__init(session ? &session->header.env : NULL) < 0)
+		goto out;
 
 	setup_pager();
 
@@ -344,7 +348,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't add %s: %s\n",
-						   pos->s, strerror(errno));
+						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -362,7 +366,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't remove %s: %s\n",
-						   pos->s, strerror(errno));
+						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -370,7 +374,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	}
 
 	if (missing_filename)
-		ret = build_id_cache__fprintf_missing(missing_filename, force, stdout);
+		ret = build_id_cache__fprintf_missing(session, stdout);
 
 	if (update_name_list_str) {
 		list = strlist__new(true, update_name_list_str);
@@ -383,7 +387,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't update %s: %s\n",
-						   pos->s, strerror(errno));
+						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -394,5 +398,9 @@ int cmd_buildid_cache(int argc, const char **argv,
 	    build_id_cache__add_kcore(kcore_filename, debugdir, force))
 		pr_warning("Couldn't add %s\n", kcore_filename);
 
+out:
+	if (session)
+		perf_session__delete(session);
+
 	return ret;
 }
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9a5a035cb426..a3ce19f7aebd 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -360,7 +360,7 @@ static struct perf_tool tool = {
 	.exit	= perf_event__process_exit,
 	.fork	= perf_event__process_fork,
 	.lost	= perf_event__process_lost,
-	.ordered_samples = true,
+	.ordered_events = true,
 	.ordering_requires_timestamps = true,
 };
 
@@ -683,7 +683,7 @@ static int __cmd_diff(void)
 		d->session = perf_session__new(&d->file, false, &tool);
 		if (!d->session) {
 			pr_err("Failed to open %s\n", d->file.path);
-			ret = -ENOMEM;
+			ret = -1;
 			goto out_delete;
 		}
 
@@ -1143,7 +1143,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	argc = parse_options(argc, argv, options, diff_usage, 0);
 
-	if (symbol__init() < 0)
+	if (symbol__init(NULL) < 0)
 		return -1;
 
 	if (data_init(argc, argv) < 0)
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 66e12f55c052..0f93f859b782 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -28,7 +28,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 
 	session = perf_session__new(&file, 0, NULL);
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	evlist__for_each(session->evlist, pos)
 		perf_evsel__fprintf(pos, details, stdout);
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 0384d930480b..25d20628212e 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -103,6 +103,8 @@ static int check_emacsclient_version(void)
 
 static void exec_woman_emacs(const char *path, const char *page)
 {
+	char sbuf[STRERR_BUFSIZE];
+
 	if (!check_emacsclient_version()) {
 		/* This works only with emacsclient version >= 22. */
 		struct strbuf man_page = STRBUF_INIT;
@@ -111,16 +113,19 @@ static void exec_woman_emacs(const char *path, const char *page)
 			path = "emacsclient";
 		strbuf_addf(&man_page, "(woman \"%s\")", page);
 		execlp(path, "emacsclient", "-e", man_page.buf, NULL);
-		warning("failed to exec '%s': %s", path, strerror(errno));
+		warning("failed to exec '%s': %s", path,
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 	}
 }
 
 static void exec_man_konqueror(const char *path, const char *page)
 {
 	const char *display = getenv("DISPLAY");
+
 	if (display && *display) {
 		struct strbuf man_page = STRBUF_INIT;
 		const char *filename = "kfmclient";
+		char sbuf[STRERR_BUFSIZE];
 
 		/* It's simpler to launch konqueror using kfmclient. */
 		if (path) {
@@ -139,24 +144,31 @@ static void exec_man_konqueror(const char *path, const char *page)
 			path = "kfmclient";
 		strbuf_addf(&man_page, "man:%s(1)", page);
 		execlp(path, filename, "newTab", man_page.buf, NULL);
-		warning("failed to exec '%s': %s", path, strerror(errno));
+		warning("failed to exec '%s': %s", path,
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 	}
 }
 
 static void exec_man_man(const char *path, const char *page)
 {
+	char sbuf[STRERR_BUFSIZE];
+
 	if (!path)
 		path = "man";
 	execlp(path, "man", page, NULL);
-	warning("failed to exec '%s': %s", path, strerror(errno));
+	warning("failed to exec '%s': %s", path,
+		strerror_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void exec_man_cmd(const char *cmd, const char *page)
 {
 	struct strbuf shell_cmd = STRBUF_INIT;
+	char sbuf[STRERR_BUFSIZE];
+
 	strbuf_addf(&shell_cmd, "%s %s", cmd, page);
 	execl("/bin/sh", "sh", "-c", shell_cmd.buf, NULL);
-	warning("failed to exec '%s': %s", cmd, strerror(errno));
+	warning("failed to exec '%s': %s", cmd,
+		strerror_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void add_man_viewer(const char *name)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 9a02807387d6..de99ca1bb942 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -23,6 +23,7 @@
 
 struct perf_inject {
 	struct perf_tool	tool;
+	struct perf_session	*session;
 	bool			build_ids;
 	bool			sched_stat;
 	const char		*input_name;
@@ -340,12 +341,8 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
 
 static int __cmd_inject(struct perf_inject *inject)
 {
-	struct perf_session *session;
 	int ret = -EINVAL;
-	struct perf_data_file file = {
-		.path = inject->input_name,
-		.mode = PERF_DATA_MODE_READ,
-	};
+	struct perf_session *session = inject->session;
 	struct perf_data_file *file_out = &inject->output;
 
 	signal(SIGINT, sig_handler);
@@ -357,16 +354,12 @@ static int __cmd_inject(struct perf_inject *inject)
 		inject->tool.tracing_data = perf_event__repipe_tracing_data;
 	}
 
-	session = perf_session__new(&file, true, &inject->tool);
-	if (session == NULL)
-		return -ENOMEM;
-
 	if (inject->build_ids) {
 		inject->tool.sample = perf_event__inject_buildid;
 	} else if (inject->sched_stat) {
 		struct perf_evsel *evsel;
 
-		inject->tool.ordered_samples = true;
+		inject->tool.ordered_events = true;
 
 		evlist__for_each(session->evlist, evsel) {
 			const char *name = perf_evsel__name(evsel);
@@ -396,8 +389,6 @@ static int __cmd_inject(struct perf_inject *inject)
 		perf_session__write_header(session, session->evlist, file_out->fd, true);
 	}
 
-	perf_session__delete(session);
-
 	return ret;
 }
 
@@ -427,6 +418,11 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.mode = PERF_DATA_MODE_WRITE,
 		},
 	};
+	struct perf_data_file file = {
+		.mode = PERF_DATA_MODE_READ,
+	};
+	int ret;
+
 	const struct option options[] = {
 		OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
 			    "Inject build-ids into the output stream"),
@@ -461,8 +457,17 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		return -1;
 	}
 
-	if (symbol__init() < 0)
+	file.path = inject.input_name;
+	inject.session = perf_session__new(&file, true, &inject.tool);
+	if (inject.session == NULL)
+		return -1;
+
+	if (symbol__init(&inject.session->header.env) < 0)
 		return -1;
 
-	return __cmd_inject(&inject);
+	ret = __cmd_inject(&inject);
+
+	perf_session__delete(inject.session);
+
+	return ret;
 }
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index bef3376bfaf3..f295141025bc 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -256,7 +256,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 static struct perf_tool perf_kmem = {
 	.sample		 = process_sample_event,
 	.comm		 = perf_event__process_comm,
-	.ordered_samples = true,
+	.mmap		 = perf_event__process_mmap,
+	.mmap2		 = perf_event__process_mmap2,
+	.ordered_events	 = true,
 };
 
 static double fragmentation(unsigned long n_req, unsigned long n_alloc)
@@ -403,10 +405,9 @@ static void sort_result(void)
 	__sort_result(&root_caller_stat, &root_caller_sorted, &caller_sort);
 }
 
-static int __cmd_kmem(void)
+static int __cmd_kmem(struct perf_session *session)
 {
 	int err = -EINVAL;
-	struct perf_session *session;
 	const struct perf_evsel_str_handler kmem_tracepoints[] = {
 		{ "kmem:kmalloc",		perf_evsel__process_alloc_event, },
     		{ "kmem:kmem_cache_alloc",	perf_evsel__process_alloc_event, },
@@ -415,34 +416,22 @@ static int __cmd_kmem(void)
 		{ "kmem:kfree",			perf_evsel__process_free_event, },
     		{ "kmem:kmem_cache_free",	perf_evsel__process_free_event, },
 	};
-	struct perf_data_file file = {
-		.path = input_name,
-		.mode = PERF_DATA_MODE_READ,
-	};
-
-	session = perf_session__new(&file, false, &perf_kmem);
-	if (session == NULL)
-		return -ENOMEM;
-
-	if (perf_session__create_kernel_maps(session) < 0)
-		goto out_delete;
 
 	if (!perf_session__has_traces(session, "kmem record"))
-		goto out_delete;
+		goto out;
 
 	if (perf_session__set_tracepoints_handlers(session, kmem_tracepoints)) {
 		pr_err("Initializing perf session tracepoint handlers failed\n");
-		return -1;
+		goto out;
 	}
 
 	setup_pager();
 	err = perf_session__process_events(session, &perf_kmem);
 	if (err != 0)
-		goto out_delete;
+		goto out;
 	sort_result();
 	print_result(session);
-out_delete:
-	perf_session__delete(session);
+out:
 	return err;
 }
 
@@ -689,29 +678,46 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL,
 		NULL
 	};
+	struct perf_session *session;
+	struct perf_data_file file = {
+		.path = input_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+	int ret = -1;
+
 	argc = parse_options_subcommand(argc, argv, kmem_options,
 					kmem_subcommands, kmem_usage, 0);
 
 	if (!argc)
 		usage_with_options(kmem_usage, kmem_options);
 
-	symbol__init();
-
 	if (!strncmp(argv[0], "rec", 3)) {
+		symbol__init(NULL);
 		return __cmd_record(argc, argv);
-	} else if (!strcmp(argv[0], "stat")) {
+	}
+
+	session = perf_session__new(&file, false, &perf_kmem);
+	if (session == NULL)
+		return -1;
+
+	symbol__init(&session->header.env);
+
+	if (!strcmp(argv[0], "stat")) {
 		if (cpu__setup_cpunode_map())
-			return -1;
+			goto out_delete;
 
 		if (list_empty(&caller_sort))
 			setup_sorting(&caller_sort, default_sort_order);
 		if (list_empty(&alloc_sort))
 			setup_sorting(&alloc_sort, default_sort_order);
 
-		return __cmd_kmem();
+		ret = __cmd_kmem(session);
 	} else
 		usage_with_options(kmem_usage, kmem_options);
 
-	return 0;
+out_delete:
+	perf_session__delete(session);
+
+	return ret;
 }
 
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 43367eb00510..d8bf2271f4ea 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -543,14 +543,12 @@ static void print_vcpu_info(struct perf_kvm_stat *kvm)
 
 	pr_info("Analyze events for ");
 
-	if (kvm->live) {
-		if (kvm->opts.target.system_wide)
-			pr_info("all VMs, ");
-		else if (kvm->opts.target.pid)
-			pr_info("pid(s) %s, ", kvm->opts.target.pid);
-		else
-			pr_info("dazed and confused on what is monitored, ");
-	}
+	if (kvm->opts.target.system_wide)
+		pr_info("all VMs, ");
+	else if (kvm->opts.target.pid)
+		pr_info("pid(s) %s, ", kvm->opts.target.pid);
+	else
+		pr_info("dazed and confused on what is monitored, ");
 
 	if (vcpu == -1)
 		pr_info("all VCPUs:\n\n");
@@ -592,8 +590,8 @@ static void print_result(struct perf_kvm_stat *kvm)
 	pr_info("%9s ", "Samples%");
 
 	pr_info("%9s ", "Time%");
-	pr_info("%10s ", "Min Time");
-	pr_info("%10s ", "Max Time");
+	pr_info("%11s ", "Min Time");
+	pr_info("%11s ", "Max Time");
 	pr_info("%16s ", "Avg time");
 	pr_info("\n\n");
 
@@ -610,8 +608,8 @@ static void print_result(struct perf_kvm_stat *kvm)
 		pr_info("%10llu ", (unsigned long long)ecount);
 		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
 		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
-		pr_info("%8" PRIu64 "us ", min / 1000);
-		pr_info("%8" PRIu64 "us ", max / 1000);
+		pr_info("%9.2fus ", (double)min / 1e3);
+		pr_info("%9.2fus ", (double)max / 1e3);
 		pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
 			kvm_event_rel_stddev(vcpu, event));
 		pr_info("\n");
@@ -732,7 +730,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 			return -1;
 		}
 
-		err = perf_session_queue_event(kvm->session, event, &sample, 0);
+		err = perf_session_queue_event(kvm->session, event, &kvm->tool, &sample, 0);
 		/*
 		 * FIXME: Here we can't consume the event, as perf_session_queue_event will
 		 *        point to it, and it'll get possibly overwritten by the kernel.
@@ -785,7 +783,7 @@ static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm)
 
 	/* flush queue after each round in which we processed events */
 	if (ntotal) {
-		kvm->session->ordered_samples.next_flush = flush_time;
+		kvm->session->ordered_events.next_flush = flush_time;
 		err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session);
 		if (err) {
 			if (kvm->lost_events)
@@ -885,15 +883,11 @@ static int fd_set_nonblock(int fd)
 	return 0;
 }
 
-static
-int perf_kvm__handle_stdin(struct termios *tc_now, struct termios *tc_save)
+static int perf_kvm__handle_stdin(void)
 {
 	int c;
 
-	tcsetattr(0, TCSANOW, tc_now);
 	c = getc(stdin);
-	tcsetattr(0, TCSAFLUSH, tc_save);
-
 	if (c == 'q')
 		return 1;
 
@@ -904,7 +898,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 {
 	struct pollfd *pollfds = NULL;
 	int nr_fds, nr_stdin, ret, err = -EINVAL;
-	struct termios tc, save;
+	struct termios save;
 
 	/* live flag must be set first */
 	kvm->live = true;
@@ -919,26 +913,14 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 		goto out;
 	}
 
+	set_term_quiet_input(&save);
 	init_kvm_event_record(kvm);
 
-	tcgetattr(0, &save);
-	tc = save;
-	tc.c_lflag &= ~(ICANON | ECHO);
-	tc.c_cc[VMIN] = 0;
-	tc.c_cc[VTIME] = 0;
-
 	signal(SIGINT, sig_handler);
 	signal(SIGTERM, sig_handler);
 
-	/* copy pollfds -- need to add timerfd and stdin */
-	nr_fds = kvm->evlist->nr_fds;
-	pollfds = zalloc(sizeof(struct pollfd) * (nr_fds + 2));
-	if (!pollfds) {
-		err = -ENOMEM;
-		goto out;
-	}
-	memcpy(pollfds, kvm->evlist->pollfd,
-		sizeof(struct pollfd) * kvm->evlist->nr_fds);
+	/* use pollfds -- need to add timerfd and stdin */
+	nr_fds = kvm->evlist->pollfd.nr;
 
 	/* add timer fd */
 	if (perf_kvm__timerfd_create(kvm) < 0) {
@@ -946,17 +928,21 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 		goto out;
 	}
 
-	pollfds[nr_fds].fd = kvm->timerfd;
-	pollfds[nr_fds].events = POLLIN;
+	if (perf_evlist__add_pollfd(kvm->evlist, kvm->timerfd))
+		goto out;
+
 	nr_fds++;
 
-	pollfds[nr_fds].fd = fileno(stdin);
-	pollfds[nr_fds].events = POLLIN;
+	if (perf_evlist__add_pollfd(kvm->evlist, fileno(stdin)))
+		goto out;
+
 	nr_stdin = nr_fds;
 	nr_fds++;
 	if (fd_set_nonblock(fileno(stdin)) != 0)
 		goto out;
 
+	pollfds	 = kvm->evlist->pollfd.entries;
+
 	/* everything is good - enable the events and process */
 	perf_evlist__enable(kvm->evlist);
 
@@ -972,7 +958,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 			goto out;
 
 		if (pollfds[nr_stdin].revents & POLLIN)
-			done = perf_kvm__handle_stdin(&tc, &save);
+			done = perf_kvm__handle_stdin();
 
 		if (!rc && !done)
 			err = poll(pollfds, nr_fds, 100);
@@ -989,7 +975,7 @@ out:
 	if (kvm->timerfd >= 0)
 		close(kvm->timerfd);
 
-	free(pollfds);
+	tcsetattr(0, TCSAFLUSH, &save);
 	return err;
 }
 
@@ -998,6 +984,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 	int err, rc = -1;
 	struct perf_evsel *pos;
 	struct perf_evlist *evlist = kvm->evlist;
+	char sbuf[STRERR_BUFSIZE];
 
 	perf_evlist__config(evlist, &kvm->opts);
 
@@ -1034,12 +1021,14 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
-		printf("Couldn't create the events: %s\n", strerror(errno));
+		printf("Couldn't create the events: %s\n",
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 
 	if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
-		ui__error("Failed to mmap the events: %s\n", strerror(errno));
+		ui__error("Failed to mmap the events: %s\n",
+			  strerror_r(errno, sbuf, sizeof(sbuf)));
 		perf_evlist__close(evlist);
 		goto out;
 	}
@@ -1058,7 +1047,7 @@ static int read_events(struct perf_kvm_stat *kvm)
 	struct perf_tool eops = {
 		.sample			= process_sample_event,
 		.comm			= perf_event__process_comm,
-		.ordered_samples	= true,
+		.ordered_events		= true,
 	};
 	struct perf_data_file file = {
 		.path = kvm->file_name,
@@ -1069,9 +1058,11 @@ static int read_events(struct perf_kvm_stat *kvm)
 	kvm->session = perf_session__new(&file, false, &kvm->tool);
 	if (!kvm->session) {
 		pr_err("Initializing perf session failed\n");
-		return -EINVAL;
+		return -1;
 	}
 
+	symbol__init(&kvm->session->header.env);
+
 	if (!perf_session__has_traces(kvm->session, "kvm record"))
 		return -EINVAL;
 
@@ -1088,8 +1079,8 @@ static int read_events(struct perf_kvm_stat *kvm)
 
 static int parse_target_str(struct perf_kvm_stat *kvm)
 {
-	if (kvm->pid_str) {
-		kvm->pid_list = intlist__new(kvm->pid_str);
+	if (kvm->opts.target.pid) {
+		kvm->pid_list = intlist__new(kvm->opts.target.pid);
 		if (kvm->pid_list == NULL) {
 			pr_err("Error parsing process id string\n");
 			return -EINVAL;
@@ -1191,7 +1182,7 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
 		OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
 			    "key for sorting: sample(sort by samples number)"
 			    " time (sort by avg time)"),
-		OPT_STRING('p', "pid", &kvm->pid_str, "pid",
+		OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid",
 			   "analyze events only for given process id(s)"),
 		OPT_END()
 	};
@@ -1201,8 +1192,6 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
 		NULL
 	};
 
-	symbol__init();
-
 	if (argc) {
 		argc = parse_options(argc, argv,
 				     kvm_events_report_options,
@@ -1212,6 +1201,9 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
 					   kvm_events_report_options);
 	}
 
+	if (!kvm->opts.target.pid)
+		kvm->opts.target.system_wide = true;
+
 	return kvm_events_report_vcpu(kvm);
 }
 
@@ -1311,7 +1303,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	kvm->tool.exit   = perf_event__process_exit;
 	kvm->tool.fork   = perf_event__process_fork;
 	kvm->tool.lost   = process_lost_event;
-	kvm->tool.ordered_samples = true;
+	kvm->tool.ordered_events = true;
 	perf_tool__fill_defaults(&kvm->tool);
 
 	/* set defaults */
@@ -1322,7 +1314,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	kvm->opts.target.uid_str = NULL;
 	kvm->opts.target.uid = UINT_MAX;
 
-	symbol__init();
+	symbol__init(NULL);
 	disable_buildid_cache();
 
 	use_browser = 0;
@@ -1369,7 +1361,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	 */
 	kvm->session = perf_session__new(&file, false, &kvm->tool);
 	if (kvm->session == NULL) {
-		err = -ENOMEM;
+		err = -1;
 		goto out;
 	}
 	kvm->session->evlist = kvm->evlist;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 6148afc995c6..e7ec71589da6 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -852,7 +852,7 @@ static int __cmd_report(bool display_info)
 	struct perf_tool eops = {
 		.sample		 = process_sample_event,
 		.comm		 = perf_event__process_comm,
-		.ordered_samples = true,
+		.ordered_events	 = true,
 	};
 	struct perf_data_file file = {
 		.path = input_name,
@@ -862,9 +862,11 @@ static int __cmd_report(bool display_info)
 	session = perf_session__new(&file, false, &eops);
 	if (!session) {
 		pr_err("Initializing perf session failed\n");
-		return -ENOMEM;
+		return -1;
 	}
 
+	symbol__init(&session->header.env);
+
 	if (!perf_session__has_traces(session, "lock record"))
 		goto out_delete;
 
@@ -974,7 +976,6 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
 	unsigned int i;
 	int rc = 0;
 
-	symbol__init();
 	for (i = 0; i < LOCKHASH_SIZE; i++)
 		INIT_LIST_HEAD(lockhash_table + i);
 
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 4a1a6c94a5eb..24db6ffe2957 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -124,7 +124,7 @@ static int report_raw_events(struct perf_mem *mem)
 							 &mem->tool);
 
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	if (mem->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, mem->cpu_list,
@@ -133,7 +133,7 @@ static int report_raw_events(struct perf_mem *mem)
 			goto out_delete;
 	}
 
-	if (symbol__init() < 0)
+	if (symbol__init(&session->header.env) < 0)
 		return -1;
 
 	printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
@@ -194,7 +194,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 			.lost		= perf_event__process_lost,
 			.fork		= perf_event__process_fork,
 			.build_id	= perf_event__process_build_id,
-			.ordered_samples = true,
+			.ordered_events	= true,
 		},
 		.input_name		 = "perf.data",
 	};
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index c63fa2925075..04412b4770a2 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -290,8 +290,11 @@ static void cleanup_params(void)
 
 static void pr_err_with_code(const char *msg, int err)
 {
+	char sbuf[STRERR_BUFSIZE];
+
 	pr_err("%s", msg);
-	pr_debug(" Reason: %s (Code: %d)", strerror(-err), err);
+	pr_debug(" Reason: %s (Code: %d)",
+		 strerror_r(-err, sbuf, sizeof(sbuf)), err);
 	pr_err("\n");
 }
 
@@ -373,6 +376,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 			"target executable name or path", opt_set_target),
 	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
 		    "Disable symbol demangling"),
+	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+		    "Enable kernel symbol demangling"),
 	OPT_END()
 	};
 	int ret;
@@ -467,7 +472,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 			usage_with_options(probe_usage, options);
 		}
 
-		ret = show_line_range(&params.line_range, params.target);
+		ret = show_line_range(&params.line_range, params.target,
+				      params.uprobes);
 		if (ret < 0)
 			pr_err_with_code("  Error: Failed to show lines.", ret);
 		return ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4869050e7194..44c6f3d55ce7 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -65,8 +65,9 @@ static int process_synthesized_event(struct perf_tool *tool,
 	return record__write(rec, event, event->header.size);
 }
 
-static int record__mmap_read(struct record *rec, struct perf_mmap *md)
+static int record__mmap_read(struct record *rec, int idx)
 {
+	struct perf_mmap *md = &rec->evlist->mmap[idx];
 	unsigned int head = perf_mmap__read_head(md);
 	unsigned int old = md->prev;
 	unsigned char *data = md->base + page_size;
@@ -102,8 +103,7 @@ static int record__mmap_read(struct record *rec, struct perf_mmap *md)
 	}
 
 	md->prev = old;
-	perf_mmap__write_tail(md, old);
-
+	perf_evlist__mmap_consume(rec->evlist, idx);
 out:
 	return rc;
 }
@@ -161,7 +161,7 @@ try_again:
 
 	if (perf_evlist__apply_filters(evlist)) {
 		error("failed to set filter with %d (%s)\n", errno,
-			strerror(errno));
+			strerror_r(errno, msg, sizeof(msg)));
 		rc = -1;
 		goto out;
 	}
@@ -175,7 +175,8 @@ try_again:
 			       "(current value: %u)\n", opts->mmap_pages);
 			rc = -errno;
 		} else {
-			pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno));
+			pr_err("failed to mmap with %d (%s)\n", errno,
+				strerror_r(errno, msg, sizeof(msg)));
 			rc = -errno;
 		}
 		goto out;
@@ -244,7 +245,7 @@ static int record__mmap_read_all(struct record *rec)
 
 	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
 		if (rec->evlist->mmap[i].base) {
-			if (record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) {
+			if (record__mmap_read(rec, i) != 0) {
 				rc = -1;
 				goto out;
 			}
@@ -307,7 +308,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	struct record_opts *opts = &rec->opts;
 	struct perf_data_file *file = &rec->file;
 	struct perf_session *session;
-	bool disabled = false;
+	bool disabled = false, draining = false;
 
 	rec->progname = argv[0];
 
@@ -456,9 +457,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		}
 
 		if (hits == rec->samples) {
-			if (done)
+			if (done || draining)
 				break;
-			err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1);
+			err = perf_evlist__poll(rec->evlist, -1);
 			/*
 			 * Propagate error, only if there's any. Ignore positive
 			 * number of returned events and interrupt error.
@@ -466,6 +467,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 			if (err > 0 || (err < 0 && errno == EINTR))
 				err = 0;
 			waking++;
+
+			if (perf_evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0)
+				draining = true;
 		}
 
 		/*
@@ -480,7 +484,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 
 	if (forks && workload_exec_errno) {
-		char msg[512];
+		char msg[STRERR_BUFSIZE];
 		const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
 		pr_err("Workload failed: %s\n", emsg);
 		err = -1;
@@ -620,145 +624,56 @@ error:
 	return ret;
 }
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-static int get_stack_size(char *str, unsigned long *_size)
-{
-	char *endptr;
-	unsigned long size;
-	unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
-
-	size = strtoul(str, &endptr, 0);
-
-	do {
-		if (*endptr)
-			break;
-
-		size = round_up(size, sizeof(u64));
-		if (!size || size > max_size)
-			break;
-
-		*_size = size;
-		return 0;
-
-	} while (0);
-
-	pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
-	       max_size, str);
-	return -1;
-}
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
-
-int record_parse_callchain(const char *arg, struct record_opts *opts)
-{
-	char *tok, *name, *saveptr = NULL;
-	char *buf;
-	int ret = -1;
-
-	/* We need buffer that we know we can write to. */
-	buf = malloc(strlen(arg) + 1);
-	if (!buf)
-		return -ENOMEM;
-
-	strcpy(buf, arg);
-
-	tok = strtok_r((char *)buf, ",", &saveptr);
-	name = tok ? : (char *)buf;
-
-	do {
-		/* Framepointer style */
-		if (!strncmp(name, "fp", sizeof("fp"))) {
-			if (!strtok_r(NULL, ",", &saveptr)) {
-				opts->call_graph = CALLCHAIN_FP;
-				ret = 0;
-			} else
-				pr_err("callchain: No more arguments "
-				       "needed for -g fp\n");
-			break;
-
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-		/* Dwarf style */
-		} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
-			const unsigned long default_stack_dump_size = 8192;
-
-			ret = 0;
-			opts->call_graph = CALLCHAIN_DWARF;
-			opts->stack_dump_size = default_stack_dump_size;
-
-			tok = strtok_r(NULL, ",", &saveptr);
-			if (tok) {
-				unsigned long size = 0;
-
-				ret = get_stack_size(tok, &size);
-				opts->stack_dump_size = size;
-			}
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
-		} else {
-			pr_err("callchain: Unknown --call-graph option "
-			       "value: %s\n", arg);
-			break;
-		}
-
-	} while (0);
-
-	free(buf);
-	return ret;
-}
-
-static void callchain_debug(struct record_opts *opts)
+static void callchain_debug(void)
 {
 	static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" };
 
-	pr_debug("callchain: type %s\n", str[opts->call_graph]);
+	pr_debug("callchain: type %s\n", str[callchain_param.record_mode]);
 
-	if (opts->call_graph == CALLCHAIN_DWARF)
+	if (callchain_param.record_mode == CALLCHAIN_DWARF)
 		pr_debug("callchain: stack dump size %d\n",
-			 opts->stack_dump_size);
+			 callchain_param.dump_size);
 }
 
-int record_parse_callchain_opt(const struct option *opt,
+int record_parse_callchain_opt(const struct option *opt __maybe_unused,
 			       const char *arg,
 			       int unset)
 {
-	struct record_opts *opts = opt->value;
 	int ret;
 
-	opts->call_graph_enabled = !unset;
+	callchain_param.enabled = !unset;
 
 	/* --no-call-graph */
 	if (unset) {
-		opts->call_graph = CALLCHAIN_NONE;
+		callchain_param.record_mode = CALLCHAIN_NONE;
 		pr_debug("callchain: disabled\n");
 		return 0;
 	}
 
-	ret = record_parse_callchain(arg, opts);
+	ret = parse_callchain_record_opt(arg);
 	if (!ret)
-		callchain_debug(opts);
+		callchain_debug();
 
 	return ret;
 }
 
-int record_callchain_opt(const struct option *opt,
+int record_callchain_opt(const struct option *opt __maybe_unused,
 			 const char *arg __maybe_unused,
 			 int unset __maybe_unused)
 {
-	struct record_opts *opts = opt->value;
+	callchain_param.enabled = true;
 
-	opts->call_graph_enabled = !unset;
+	if (callchain_param.record_mode == CALLCHAIN_NONE)
+		callchain_param.record_mode = CALLCHAIN_FP;
 
-	if (opts->call_graph == CALLCHAIN_NONE)
-		opts->call_graph = CALLCHAIN_FP;
-
-	callchain_debug(opts);
+	callchain_debug();
 	return 0;
 }
 
 static int perf_record_config(const char *var, const char *value, void *cb)
 {
-	struct record *rec = cb;
-
 	if (!strcmp(var, "record.call-graph"))
-		return record_parse_callchain(value, &rec->opts);
+		var = "call-graph.record-mode"; /* fall-through */
 
 	return perf_default_config(var, value, cb);
 }
@@ -781,6 +696,7 @@ static const char * const record_usage[] = {
  */
 static struct record record = {
 	.opts = {
+		.sample_time	     = true,
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
@@ -907,7 +823,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		usage_with_options(record_usage, record_options);
 	}
 
-	symbol__init();
+	symbol__init(NULL);
 
 	if (symbol_conf.kptr_restrict)
 		pr_warning(
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 21d830bafff3..ac145fae0521 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -58,17 +58,19 @@ struct report {
 	const char		*symbol_filter_str;
 	float			min_percent;
 	u64			nr_entries;
+	u64			queue_size;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
 static int report__config(const char *var, const char *value, void *cb)
 {
+	struct report *rep = cb;
+
 	if (!strcmp(var, "report.group")) {
 		symbol_conf.event_group = perf_config_bool(var, value);
 		return 0;
 	}
 	if (!strcmp(var, "report.percent-limit")) {
-		struct report *rep = cb;
 		rep->min_percent = strtof(value, NULL);
 		return 0;
 	}
@@ -76,6 +78,10 @@ static int report__config(const char *var, const char *value, void *cb)
 		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "report.queue-size")) {
+		rep->queue_size = perf_config_u64(var, value);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
@@ -578,7 +584,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = perf_event__process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
-			.ordered_samples = true,
+			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
 		.max_stack		 = PERF_MAX_STACK_DEPTH,
@@ -674,6 +680,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "objdump binary to use for disassembly and annotations"),
 	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
 		    "Disable symbol demangling"),
+	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+		    "Enable kernel symbol demangling"),
 	OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
 	OPT_CALLBACK(0, "percent-limit", &report, "percent",
 		     "Don't show entries under that percent", parse_percent_limit),
@@ -712,14 +720,19 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 repeat:
 	session = perf_session__new(&file, false, &report.tool);
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
+
+	if (report.queue_size) {
+		ordered_events__set_alloc_size(&session->ordered_events,
+					       report.queue_size);
+	}
 
 	report.session = session;
 
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
-	if (branch_mode == -1 && has_br_stack) {
+	if ((branch_mode == -1 && has_br_stack) || branch_mode == 1) {
 		sort__mode = SORT_MODE__BRANCH;
 		symbol_conf.cumulate_callchain = false;
 	}
@@ -787,7 +800,7 @@ repeat:
 		}
 	}
 
-	if (symbol__init() < 0)
+	if (symbol__init(&session->header.env) < 0)
 		goto error;
 
 	if (argc) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index f83c08c0dd87..9c9287fbf8e9 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -428,6 +428,7 @@ static u64 get_cpu_usage_nsec_parent(void)
 static int self_open_counters(void)
 {
 	struct perf_event_attr attr;
+	char sbuf[STRERR_BUFSIZE];
 	int fd;
 
 	memset(&attr, 0, sizeof(attr));
@@ -440,7 +441,8 @@ static int self_open_counters(void)
 
 	if (fd < 0)
 		pr_err("Error: sys_perf_event_open() syscall returned "
-		       "with %d (%s)\n", fd, strerror(errno));
+		       "with %d (%s)\n", fd,
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
 	return fd;
 }
 
@@ -1462,6 +1464,8 @@ static int perf_sched__read_events(struct perf_sched *sched,
 		return -1;
 	}
 
+	symbol__init(&session->header.env);
+
 	if (perf_session__set_tracepoints_handlers(session, handlers))
 		goto out_delete;
 
@@ -1662,7 +1666,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 			.comm		 = perf_event__process_comm,
 			.lost		 = perf_event__process_lost,
 			.fork		 = perf_sched__process_fork_event,
-			.ordered_samples = true,
+			.ordered_events = true,
 		},
 		.cmp_pid	      = LIST_HEAD_INIT(sched.cmp_pid),
 		.sort_list	      = LIST_HEAD_INIT(sched.sort_list),
@@ -1747,7 +1751,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!strcmp(argv[0], "script"))
 		return cmd_script(argc, argv, prefix);
 
-	symbol__init();
 	if (!strncmp(argv[0], "rec", 3)) {
 		return __cmd_record(argc, argv);
 	} else if (!strncmp(argv[0], "lat", 3)) {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index f57035b89c15..b9b9e58a6c39 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -184,10 +184,6 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP",
 					    PERF_OUTPUT_IP))
 			return -EINVAL;
-
-		if (!no_callchain &&
-		    !(attr->sample_type & PERF_SAMPLE_CALLCHAIN))
-			symbol_conf.use_callchain = false;
 	}
 
 	if (PRINT_FIELD(ADDR) &&
@@ -290,6 +286,19 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		set_print_ip_opts(&evsel->attr);
 	}
 
+	if (!no_callchain) {
+		bool use_callchain = false;
+
+		evlist__for_each(session->evlist, evsel) {
+			if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
+				use_callchain = true;
+				break;
+			}
+		}
+		if (!use_callchain)
+			symbol_conf.use_callchain = false;
+	}
+
 	/*
 	 * set default for tracepoints to print symbols only
 	 * if callchains are present
@@ -476,6 +485,11 @@ static int default_start_script(const char *script __maybe_unused,
 	return 0;
 }
 
+static int default_flush_script(void)
+{
+	return 0;
+}
+
 static int default_stop_script(void)
 {
 	return 0;
@@ -489,6 +503,7 @@ static int default_generate_script(struct pevent *pevent __maybe_unused,
 
 static struct scripting_ops default_scripting_ops = {
 	.start_script		= default_start_script,
+	.flush_script		= default_flush_script,
 	.stop_script		= default_stop_script,
 	.process_event		= process_event,
 	.generate_script	= default_generate_script,
@@ -504,6 +519,11 @@ static void setup_scripting(void)
 	scripting_ops = &default_scripting_ops;
 }
 
+static int flush_scripting(void)
+{
+	return scripting_ops->flush_script();
+}
+
 static int cleanup_scripting(void)
 {
 	pr_debug("\nperf script stopped\n");
@@ -1471,12 +1491,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	bool show_full_info = false;
 	bool header = false;
 	bool header_only = false;
+	bool script_started = false;
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
 	struct perf_session *session;
 	char *script_path = NULL;
 	const char **__argv;
-	int i, j, err;
+	int i, j, err = 0;
 	struct perf_script script = {
 		.tool = {
 			.sample		 = process_sample_event,
@@ -1488,7 +1509,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
-			.ordered_samples = true,
+			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
 	};
@@ -1718,26 +1739,28 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		exit(-1);
 	}
 
-	if (symbol__init() < 0)
-		return -1;
 	if (!script_name)
 		setup_pager();
 
 	session = perf_session__new(&file, false, &script.tool);
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	if (header || header_only) {
 		perf_session__fprintf_info(session, stdout, show_full_info);
 		if (header_only)
-			return 0;
+			goto out_delete;
 	}
 
+	if (symbol__init(&session->header.env) < 0)
+		goto out_delete;
+
 	script.session = session;
 
 	if (cpu_list) {
-		if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap))
-			return -1;
+		err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
+		if (err < 0)
+			goto out_delete;
 	}
 
 	if (!no_callchain)
@@ -1752,53 +1775,62 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		if (output_set_by_user()) {
 			fprintf(stderr,
 				"custom fields not supported for generated scripts");
-			return -1;
+			err = -EINVAL;
+			goto out_delete;
 		}
 
 		input = open(file.path, O_RDONLY);	/* input_name */
 		if (input < 0) {
+			err = -errno;
 			perror("failed to open file");
-			return -1;
+			goto out_delete;
 		}
 
 		err = fstat(input, &perf_stat);
 		if (err < 0) {
 			perror("failed to stat file");
-			return -1;
+			goto out_delete;
 		}
 
 		if (!perf_stat.st_size) {
 			fprintf(stderr, "zero-sized file, nothing to do!\n");
-			return 0;
+			goto out_delete;
 		}
 
 		scripting_ops = script_spec__lookup(generate_script_lang);
 		if (!scripting_ops) {
 			fprintf(stderr, "invalid language specifier");
-			return -1;
+			err = -ENOENT;
+			goto out_delete;
 		}
 
 		err = scripting_ops->generate_script(session->tevent.pevent,
 						     "perf-script");
-		goto out;
+		goto out_delete;
 	}
 
 	if (script_name) {
 		err = scripting_ops->start_script(script_name, argc, argv);
 		if (err)
-			goto out;
+			goto out_delete;
 		pr_debug("perf script started with script %s\n\n", script_name);
+		script_started = true;
 	}
 
 
 	err = perf_session__check_output_opt(session);
 	if (err < 0)
-		goto out;
+		goto out_delete;
 
 	err = __cmd_script(&script);
 
+	flush_scripting();
+
+out_delete:
 	perf_session__delete(session);
-	cleanup_scripting();
+
+	if (script_started)
+		cleanup_scripting();
 out:
 	return err;
 }
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 3e80aa10cfd8..b22c62f80078 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -593,7 +593,7 @@ static int __run_perf_stat(int argc, const char **argv)
 
 	if (perf_evlist__apply_filters(evsel_list)) {
 		error("failed to set filter with %d (%s)\n", errno,
-			strerror(errno));
+			strerror_r(errno, msg, sizeof(msg)));
 		return -1;
 	}
 
@@ -732,7 +732,7 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 	}
 }
 
-static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	double msecs = avg / 1e6;
 	const char *fmt_v, *fmt_n;
@@ -741,7 +741,7 @@ static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
 	fmt_n = csv_output ? "%s" : "%-25s";
 
-	aggr_printout(evsel, cpu, nr);
+	aggr_printout(evsel, id, nr);
 
 	scnprintf(name, sizeof(name), "%s%s",
 		  perf_evsel__name(evsel), csv_output ? "" : " (msec)");
@@ -947,11 +947,12 @@ static void print_ll_cache_misses(int cpu,
 	fprintf(output, " of all LL-cache hits   ");
 }
 
-static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
 	double total, ratio = 0.0, total2;
 	double sc =  evsel->scale;
 	const char *fmt;
+	int cpu = cpu_map__id_to_cpu(id);
 
 	if (csv_output) {
 		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
@@ -962,7 +963,7 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 			fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
 	}
 
-	aggr_printout(evsel, cpu, nr);
+	aggr_printout(evsel, id, nr);
 
 	if (aggr_mode == AGGR_GLOBAL)
 		cpu = 0;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 2f1a5220c090..35b425b6293f 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1605,7 +1605,9 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 	int ret = -EINVAL;
 
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
+
+	symbol__init(&session->header.env);
 
 	(void)perf_header__process_sections(&session->header,
 					    perf_data_file__fd(session->file),
@@ -1920,7 +1922,7 @@ int cmd_timechart(int argc, const char **argv,
 			.fork		 = process_fork_event,
 			.exit		 = process_exit_event,
 			.sample		 = process_sample_event,
-			.ordered_samples = true,
+			.ordered_events	 = true,
 		},
 		.proc_num = 15,
 		.min_time = 1000000,
@@ -1982,8 +1984,6 @@ int cmd_timechart(int argc, const char **argv,
 		return -1;
 	}
 
-	symbol__init();
-
 	if (argc && !strncmp(argv[0], "rec", 3)) {
 		argc = parse_options(argc, argv, record_options, record_usage,
 				     PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 377971dc89a3..fc3d55f832ac 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -59,7 +59,7 @@
 
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
-#include <sys/poll.h>
+#include <poll.h>
 #include <sys/prctl.h>
 #include <sys/wait.h>
 #include <sys/uio.h>
@@ -276,11 +276,17 @@ static void perf_top__print_sym_table(struct perf_top *top)
 		return;
 	}
 
+	if (top->zero) {
+		hists__delete_entries(&top->sym_evsel->hists);
+	} else {
+		hists__decay_entries(&top->sym_evsel->hists,
+				     top->hide_user_symbols,
+				     top->hide_kernel_symbols);
+	}
+
 	hists__collapse_resort(&top->sym_evsel->hists, NULL);
 	hists__output_resort(&top->sym_evsel->hists);
-	hists__decay_entries(&top->sym_evsel->hists,
-			     top->hide_user_symbols,
-			     top->hide_kernel_symbols);
+
 	hists__output_recalc_col_len(&top->sym_evsel->hists,
 				     top->print_entries - printed);
 	putchar('\n');
@@ -427,18 +433,13 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 
 	if (!perf_top__key_mapped(top, c)) {
 		struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
-		struct termios tc, save;
+		struct termios save;
 
 		perf_top__print_mapped_keys(top);
 		fprintf(stdout, "\nEnter selection, or unmapped key to continue: ");
 		fflush(stdout);
 
-		tcgetattr(0, &save);
-		tc = save;
-		tc.c_lflag &= ~(ICANON | ECHO);
-		tc.c_cc[VMIN] = 0;
-		tc.c_cc[VTIME] = 0;
-		tcsetattr(0, TCSANOW, &tc);
+		set_term_quiet_input(&save);
 
 		poll(&stdin_poll, 1, -1);
 		c = getc(stdin);
@@ -542,11 +543,16 @@ static void perf_top__sort_new_samples(void *arg)
 	if (t->evlist->selected != NULL)
 		t->sym_evsel = t->evlist->selected;
 
+	if (t->zero) {
+		hists__delete_entries(&t->sym_evsel->hists);
+	} else {
+		hists__decay_entries(&t->sym_evsel->hists,
+				     t->hide_user_symbols,
+				     t->hide_kernel_symbols);
+	}
+
 	hists__collapse_resort(&t->sym_evsel->hists, NULL);
 	hists__output_resort(&t->sym_evsel->hists);
-	hists__decay_entries(&t->sym_evsel->hists,
-			     t->hide_user_symbols,
-			     t->hide_kernel_symbols);
 }
 
 static void *display_thread_tui(void *arg)
@@ -577,23 +583,32 @@ static void *display_thread_tui(void *arg)
 	return NULL;
 }
 
+static void display_sig(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+static void display_setup_sig(void)
+{
+	signal(SIGSEGV, display_sig);
+	signal(SIGFPE,  display_sig);
+	signal(SIGINT,  display_sig);
+	signal(SIGQUIT, display_sig);
+	signal(SIGTERM, display_sig);
+}
+
 static void *display_thread(void *arg)
 {
 	struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
-	struct termios tc, save;
+	struct termios save;
 	struct perf_top *top = arg;
 	int delay_msecs, c;
 
-	tcgetattr(0, &save);
-	tc = save;
-	tc.c_lflag &= ~(ICANON | ECHO);
-	tc.c_cc[VMIN] = 0;
-	tc.c_cc[VTIME] = 0;
-
+	display_setup_sig();
 	pthread__unblock_sigwinch();
 repeat:
 	delay_msecs = top->delay_secs * 1000;
-	tcsetattr(0, TCSANOW, &tc);
+	set_term_quiet_input(&save);
 	/* trash return*/
 	getc(stdin);
 
@@ -620,13 +635,16 @@ repeat:
 		}
 	}
 
+	tcsetattr(0, TCSAFLUSH, &save);
 	return NULL;
 }
 
-static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
+static int symbol_filter(struct map *map, struct symbol *sym)
 {
 	const char *name = sym->name;
 
+	if (!map->dso->kernel)
+		return 0;
 	/*
 	 * ppc64 uses function descriptors and appends a '.' to the
 	 * start of every instruction address. Remove it.
@@ -876,7 +894,7 @@ try_again:
 
 	if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
 		ui__error("Failed to mmap with %d (%s)\n",
-			    errno, strerror(errno));
+			    errno, strerror_r(errno, msg, sizeof(msg)));
 		goto out_err;
 	}
 
@@ -911,7 +929,7 @@ static int __cmd_top(struct perf_top *top)
 
 	top->session = perf_session__new(NULL, false, NULL);
 	if (top->session == NULL)
-		return -ENOMEM;
+		return -1;
 
 	machines__set_symbol_filter(&top->session->machines, symbol_filter);
 
@@ -946,7 +964,7 @@ static int __cmd_top(struct perf_top *top)
                 perf_evlist__enable(top->evlist);
 
 	/* Wait for a minimal set of events before starting the snapshot */
-	poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
+	perf_evlist__poll(top->evlist, 100);
 
 	perf_top__mmap_read(top);
 
@@ -963,7 +981,7 @@ static int __cmd_top(struct perf_top *top)
 		param.sched_priority = top->realtime_prio;
 		if (sched_setscheduler(0, SCHED_FIFO, &param)) {
 			ui__error("Could not set realtime priority.\n");
-			goto out_delete;
+			goto out_join;
 		}
 	}
 
@@ -973,10 +991,12 @@ static int __cmd_top(struct perf_top *top)
 		perf_top__mmap_read(top);
 
 		if (hits == top->samples)
-			ret = poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
+			ret = perf_evlist__poll(top->evlist, 100);
 	}
 
 	ret = 0;
+out_join:
+	pthread_join(thread, NULL);
 out_delete:
 	perf_session__delete(top->session);
 	top->session = NULL;
@@ -1000,10 +1020,8 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 
 static int perf_top_config(const char *var, const char *value, void *cb)
 {
-	struct perf_top *top = cb;
-
 	if (!strcmp(var, "top.call-graph"))
-		return record_parse_callchain(value, &top->record_opts);
+		var = "call-graph.record-mode"; /* fall-through */
 	if (!strcmp(var, "top.children")) {
 		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
 		return 0;
@@ -1122,6 +1140,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Interleave source code with assembly code (default)"),
 	OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
 		    "Display raw encoding of assembly instructions (default)"),
+	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
+		    "Enable kernel symbol demangling"),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
 		    "objdump binary to use for disassembly and annotations"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
@@ -1131,6 +1151,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "How to display percentage of filtered entries", parse_filter_percentage),
+	OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
+		   "width[,width...]",
+		   "don't try to adjust column width, use these fixed values"),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
@@ -1217,7 +1240,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	symbol_conf.priv_size = sizeof(struct annotation);
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
-	if (symbol__init() < 0)
+	if (symbol__init(NULL) < 0)
 		return -1;
 
 	sort__setup_elide(stdout);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index a6c375224f46..09bcf2393910 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -402,6 +402,31 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
 
+static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
+						  struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
+
+#define P_MREMAP_FLAG(n) \
+	if (flags & MREMAP_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~MREMAP_##n; \
+	}
+
+	P_MREMAP_FLAG(MAYMOVE);
+#ifdef MREMAP_FIXED
+	P_MREMAP_FLAG(FIXED);
+#endif
+#undef P_MREMAP_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
+}
+
+#define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags
+
 static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
 						      struct syscall_arg *arg)
 {
@@ -1004,6 +1029,7 @@ static struct syscall_fmt {
 			     [2] = SCA_MMAP_PROT, /* prot */ }, },
 	{ .name	    = "mremap",	    .hexret = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */
+			     [3] = SCA_MREMAP_FLAGS, /* flags */
 			     [4] = SCA_HEX, /* new_addr */ }, },
 	{ .name	    = "munlock",    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
@@ -1385,7 +1411,7 @@ static int trace__tool_process(struct perf_tool *tool,
 
 static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 {
-	int err = symbol__init();
+	int err = symbol__init(NULL);
 
 	if (err)
 		return err;
@@ -1669,7 +1695,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 			   union perf_event *event __maybe_unused,
 			   struct perf_sample *sample)
 {
-	int ret;
+	long ret;
 	u64 duration = 0;
 	struct thread *thread;
 	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
@@ -1722,9 +1748,9 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 
 	if (sc->fmt == NULL) {
 signed_print:
-		fprintf(trace->output, ") = %d", ret);
+		fprintf(trace->output, ") = %ld", ret);
 	} else if (ret < 0 && sc->fmt->errmsg) {
-		char bf[256];
+		char bf[STRERR_BUFSIZE];
 		const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
 			   *e = audit_errno_to_name(-ret);
 
@@ -1732,7 +1758,7 @@ signed_print:
 	} else if (ret == 0 && sc->fmt->timeout)
 		fprintf(trace->output, ") = 0 Timeout");
 	else if (sc->fmt->hexret)
-		fprintf(trace->output, ") = %#x", ret);
+		fprintf(trace->output, ") = %#lx", ret);
 	else
 		goto signed_print;
 
@@ -2018,6 +2044,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	int err = -1, i;
 	unsigned long before;
 	const bool forks = argc > 0;
+	bool draining = false;
+	char sbuf[STRERR_BUFSIZE];
 
 	trace->live = true;
 
@@ -2079,7 +2107,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
 	if (err < 0) {
-		fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
+		fprintf(trace->output, "Couldn't mmap the events: %s\n",
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -2143,8 +2172,12 @@ next_event:
 	if (trace->nr_events == before) {
 		int timeout = done ? 100 : -1;
 
-		if (poll(evlist->pollfd, evlist->nr_fds, timeout) > 0)
+		if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
+			if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP) == 0)
+				draining = true;
+
 			goto again;
+		}
 	} else {
 		goto again;
 	}
@@ -2209,18 +2242,18 @@ static int trace__replay(struct trace *trace)
 	trace->tool.tracing_data = perf_event__process_tracing_data;
 	trace->tool.build_id	  = perf_event__process_build_id;
 
-	trace->tool.ordered_samples = true;
+	trace->tool.ordered_events = true;
 	trace->tool.ordering_requires_timestamps = true;
 
 	/* add tid to output */
 	trace->multiple_threads = true;
 
-	if (symbol__init() < 0)
-		return -1;
-
 	session = perf_session__new(&file, false, &trace->tool);
 	if (session == NULL)
-		return -ENOMEM;
+		return -1;
+
+	if (symbol__init(&session->header.env) < 0)
+		goto out;
 
 	trace->host = &session->machines.host;
 
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 1f67aa02d240..58f609198c6d 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -48,10 +48,6 @@ ifneq ($(ARCH),$(filter $(ARCH),x86 arm))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
-ifeq ($(ARCH),powerpc)
-  CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
-endif
-
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
 else
@@ -120,6 +116,29 @@ ifdef PARSER_DEBUG
   CFLAGS             += -DPARSER_DEBUG
 endif
 
+ifndef NO_LIBPYTHON
+  # Try different combinations to accommodate systems that only have
+  # python[2][-config] in weird combinations but always preferring
+  # python2 and python2-config as per pep-0394. If we catch a
+  # python[-config] in version 3, the version check will kill it.
+  PYTHON2 := $(if $(call get-executable,python2),python2,python)
+  override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
+  PYTHON2_CONFIG := \
+    $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
+  override PYTHON_CONFIG := \
+    $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
+
+  PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+
+  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+
+  FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
+  FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
+  FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
+  FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
+endif
+
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
 CFLAGS += -funwind-tables
@@ -355,6 +374,12 @@ ifndef NO_LIBELF
   endif # NO_DWARF
 endif # NO_LIBELF
 
+ifeq ($(ARCH),powerpc)
+  ifndef NO_DWARF
+    CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
+  endif
+endif
+
 ifndef NO_LIBUNWIND
   ifneq ($(feature-libunwind), 1)
     msg := $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR);
@@ -482,21 +507,14 @@ define disable-python_code
   NO_LIBPYTHON := 1
 endef
 
-override PYTHON := \
-  $(call get-executable-or-default,PYTHON,python)
-
-ifndef PYTHON
-  $(call disable-python,python interpreter)
+ifdef NO_LIBPYTHON
+  $(call disable-python)
 else
 
-  PYTHON_WORD := $(call shell-wordify,$(PYTHON))
-
-  ifdef NO_LIBPYTHON
-    $(call disable-python)
+  ifndef PYTHON
+    $(call disable-python,python interpreter)
   else
-
-    override PYTHON_CONFIG := \
-      $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
+    PYTHON_WORD := $(call shell-wordify,$(PYTHON))
 
     ifndef PYTHON_CONFIG
       $(call disable-python,python-config tool)
@@ -635,11 +653,13 @@ else
 sysconfdir = $(prefix)/etc
 ETC_PERFCONFIG = etc/perfconfig
 endif
+ifndef lib
 ifeq ($(IS_X86_64),1)
 lib = lib64
 else
 lib = lib
 endif
+endif # lib
 libdir = $(prefix)/$(lib)
 
 # Shell quote (do not use $(call) to accommodate ancient setups);
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 6088f8d8a434..72ab2984718e 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -101,25 +101,11 @@ FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 test-libperl.bin:
 	$(BUILD) $(FLAGS_PERL_EMBED)
 
-override PYTHON := python
-override PYTHON_CONFIG := python-config
-
-escape-for-shell-sq =  $(subst ','\'',$(1))
-shell-sq = '$(escape-for-shell-sq)'
-
-PYTHON_CONFIG_SQ = $(call shell-sq,$(PYTHON_CONFIG))
-
-PYTHON_EMBED_LDOPTS = $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-PYTHON_EMBED_LDFLAGS = $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
-PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
-PYTHON_EMBED_CCOPTS = $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-FLAGS_PYTHON_EMBED = $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
-
 test-libpython.bin:
-	$(BUILD) $(FLAGS_PYTHON_EMBED)
+	$(BUILD)
 
 test-libpython-version.bin:
-	$(BUILD) $(FLAGS_PYTHON_EMBED)
+	$(BUILD)
 
 test-libbfd.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index 4d985e0f03f5..7076a62d0ff7 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -132,7 +132,7 @@ endef
 #
 # Usage: bool-value = $(call is-absolute,path)
 #
-is-absolute = $(shell echo $(shell-sq) | grep ^/ -q && echo y)
+is-absolute = $(shell echo $(shell-sq) | grep -q ^/ && echo y)
 
 # lookup
 #
diff --git a/tools/perf/perf-with-kcore.sh b/tools/perf/perf-with-kcore.sh
new file mode 100644
index 000000000000..c7ff90a90e4e
--- /dev/null
+++ b/tools/perf/perf-with-kcore.sh
@@ -0,0 +1,259 @@
+#!/bin/bash
+# perf-with-kcore: use perf with a copy of kcore
+# Copyright (c) 2014, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+
+set -e
+
+usage()
+{
+        echo "Usage: perf-with-kcore <perf sub-command> <perf.data directory> [<sub-command options> [ -- <workload>]]" >&2
+        echo "       <perf sub-command> can be record, script, report or inject" >&2
+        echo "   or: perf-with-kcore fix_buildid_cache_permissions" >&2
+        exit 1
+}
+
+find_perf()
+{
+	if [ -n "$PERF" ] ; then
+		return
+	fi
+	PERF=`which perf || true`
+	if [ -z "$PERF" ] ; then
+		echo "Failed to find perf" >&2
+	        exit 1
+	fi
+	if [ ! -x "$PERF" ] ; then
+		echo "Failed to find perf" >&2
+	        exit 1
+	fi
+	echo "Using $PERF"
+	"$PERF" version
+}
+
+copy_kcore()
+{
+	echo "Copying kcore"
+
+	if [ $EUID -eq 0 ] ; then
+		SUDO=""
+	else
+		SUDO="sudo"
+	fi
+
+	rm -f perf.data.junk
+	("$PERF" record -o perf.data.junk $PERF_OPTIONS -- sleep 60) >/dev/null 2>/dev/null &
+	PERF_PID=$!
+
+	# Need to make sure that perf has started
+	sleep 1
+
+	KCORE=$(($SUDO "$PERF" buildid-cache -v -f -k /proc/kcore >/dev/null) 2>&1)
+	case "$KCORE" in
+	"kcore added to build-id cache directory "*)
+		KCORE_DIR=${KCORE#"kcore added to build-id cache directory "}
+	;;
+	*)
+		kill $PERF_PID
+		wait >/dev/null 2>/dev/null || true
+		rm perf.data.junk
+		echo "$KCORE"
+		echo "Failed to find kcore" >&2
+		exit 1
+	;;
+	esac
+
+	kill $PERF_PID
+	wait >/dev/null 2>/dev/null || true
+	rm perf.data.junk
+
+	$SUDO cp -a "$KCORE_DIR" "$(pwd)/$PERF_DATA_DIR"
+	$SUDO rm -f "$KCORE_DIR/kcore"
+	$SUDO rm -f "$KCORE_DIR/kallsyms"
+	$SUDO rm -f "$KCORE_DIR/modules"
+	$SUDO rmdir "$KCORE_DIR"
+
+	KCORE_DIR_BASENAME=$(basename "$KCORE_DIR")
+	KCORE_DIR="$(pwd)/$PERF_DATA_DIR/$KCORE_DIR_BASENAME"
+
+	$SUDO chown $UID "$KCORE_DIR"
+	$SUDO chown $UID "$KCORE_DIR/kcore"
+	$SUDO chown $UID "$KCORE_DIR/kallsyms"
+	$SUDO chown $UID "$KCORE_DIR/modules"
+
+	$SUDO chgrp $GROUPS "$KCORE_DIR"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/kcore"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/kallsyms"
+	$SUDO chgrp $GROUPS "$KCORE_DIR/modules"
+
+	ln -s "$KCORE_DIR_BASENAME" "$PERF_DATA_DIR/kcore_dir"
+}
+
+fix_buildid_cache_permissions()
+{
+	if [ $EUID -ne 0 ] ; then
+		echo "This script must be run as root via sudo " >&2
+		exit 1
+	fi
+
+	if [ -z "$SUDO_USER" ] ; then
+		echo "This script must be run via sudo" >&2
+		exit 1
+	fi
+
+	USER_HOME=$(bash <<< "echo ~$SUDO_USER")
+
+	if [ "$HOME" != "$USER_HOME" ] ; then
+		echo "Fix unnecessary because root has a home: $HOME" >&2
+		exit 1
+	fi
+
+	echo "Fixing buildid cache permissions"
+
+	find "$USER_HOME/.debug" -xdev -type d          ! -user "$SUDO_USER" -ls -exec chown    "$SUDO_USER" \{\} \;
+	find "$USER_HOME/.debug" -xdev -type f -links 1 ! -user "$SUDO_USER" -ls -exec chown    "$SUDO_USER" \{\} \;
+	find "$USER_HOME/.debug" -xdev -type l          ! -user "$SUDO_USER" -ls -exec chown -h "$SUDO_USER" \{\} \;
+
+	if [ -n "$SUDO_GID" ] ; then
+		find "$USER_HOME/.debug" -xdev -type d          ! -group "$SUDO_GID" -ls -exec chgrp    "$SUDO_GID" \{\} \;
+		find "$USER_HOME/.debug" -xdev -type f -links 1 ! -group "$SUDO_GID" -ls -exec chgrp    "$SUDO_GID" \{\} \;
+		find "$USER_HOME/.debug" -xdev -type l          ! -group "$SUDO_GID" -ls -exec chgrp -h "$SUDO_GID" \{\} \;
+	fi
+
+	echo "Done"
+}
+
+check_buildid_cache_permissions()
+{
+	if [ $EUID -eq 0 ] ; then
+		return
+	fi
+
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d          ! -user "$USER" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -user "$USER" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l          ! -user "$USER" -print -quit)
+
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type d          ! -group "$GROUPS" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type f -links 1 ! -group "$GROUPS" -print -quit)
+	PERMISSIONS_OK+=$(find "$HOME/.debug" -xdev -type l          ! -group "$GROUPS" -print -quit)
+
+	if [ -n "$PERMISSIONS_OK" ] ; then
+		echo "*** WARNING *** buildid cache permissions may need fixing" >&2
+	fi
+}
+
+record()
+{
+	echo "Recording"
+
+	if [ $EUID -ne 0 ] ; then
+
+		if [ "$(cat /proc/sys/kernel/kptr_restrict)" -ne 0 ] ; then
+			echo "*** WARNING *** /proc/sys/kernel/kptr_restrict prevents access to kernel addresses" >&2
+		fi
+
+		if echo "$PERF_OPTIONS" | grep -q ' -a \|^-a \| -a$\|^-a$\| --all-cpus \|^--all-cpus \| --all-cpus$\|^--all-cpus$' ; then
+			echo "*** WARNING *** system-wide tracing without root access will not be able to read all necessary information from /proc" >&2
+		fi
+
+		if echo "$PERF_OPTIONS" | grep -q 'intel_pt\|intel_bts\| -I\|^-I' ; then
+			if [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt -1 ] ; then
+				echo "*** WARNING *** /proc/sys/kernel/perf_event_paranoid restricts buffer size and tracepoint (sched_switch) use" >&2
+			fi
+
+			if echo "$PERF_OPTIONS" | grep -q ' --per-thread \|^--per-thread \| --per-thread$\|^--per-thread$' ; then
+				true
+			elif echo "$PERF_OPTIONS" | grep -q ' -t \|^-t \| -t$\|^-t$' ; then
+				true
+			elif [ ! -r /sys/kernel/debug -o ! -x /sys/kernel/debug ] ; then
+				echo "*** WARNING *** /sys/kernel/debug permissions prevent tracepoint (sched_switch) use" >&2
+			fi
+		fi
+	fi
+
+	if [ -z "$1" ] ; then
+		echo "Workload is required for recording" >&2
+		usage
+	fi
+
+	if [ -e "$PERF_DATA_DIR" ] ; then
+		echo "'$PERF_DATA_DIR' exists" >&2
+		exit 1
+	fi
+
+	find_perf
+
+	mkdir "$PERF_DATA_DIR"
+
+	echo "$PERF record -o $PERF_DATA_DIR/perf.data $PERF_OPTIONS -- $*"
+	"$PERF" record -o "$PERF_DATA_DIR/perf.data" $PERF_OPTIONS -- $* || true
+
+	if rmdir "$PERF_DATA_DIR" > /dev/null 2>/dev/null ; then
+		exit 1
+	fi
+
+	copy_kcore
+
+	echo "Done"
+}
+
+subcommand()
+{
+	find_perf
+	check_buildid_cache_permissions
+	echo "$PERF $PERF_SUB_COMMAND -i $PERF_DATA_DIR/perf.data --kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms $*"
+	"$PERF" $PERF_SUB_COMMAND -i "$PERF_DATA_DIR/perf.data" "--kallsyms=$PERF_DATA_DIR/kcore_dir/kallsyms" $*
+}
+
+if [ "$1" = "fix_buildid_cache_permissions" ] ; then
+	fix_buildid_cache_permissions
+	exit 0
+fi
+
+PERF_SUB_COMMAND=$1
+PERF_DATA_DIR=$2
+shift || true
+shift || true
+
+if [ -z "$PERF_SUB_COMMAND" ] ; then
+	usage
+fi
+
+if [ -z "$PERF_DATA_DIR" ] ; then
+	usage
+fi
+
+case "$PERF_SUB_COMMAND" in
+"record")
+	while [ "$1" != "--" ] ; do
+		PERF_OPTIONS+="$1 "
+		shift || break
+	done
+	if [ "$1" != "--" ] ; then
+		echo "Options and workload are required for recording" >&2
+		usage
+	fi
+	shift
+	record $*
+;;
+"script")
+	subcommand $*
+;;
+"report")
+	subcommand $*
+;;
+"inject")
+	subcommand $*
+;;
+*)
+	usage
+;;
+esac
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 2282d41879a2..452a8474d29d 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -313,6 +313,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	int status;
 	struct stat st;
 	const char *prefix;
+	char sbuf[STRERR_BUFSIZE];
 
 	prefix = NULL;
 	if (p->option & RUN_SETUP)
@@ -343,7 +344,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	status = 1;
 	/* Check for ENOSPC and EIO errors.. */
 	if (fflush(stdout)) {
-		fprintf(stderr, "write failure on standard output: %s", strerror(errno));
+		fprintf(stderr, "write failure on standard output: %s",
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 	if (ferror(stdout)) {
@@ -351,7 +353,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 		goto out;
 	}
 	if (fclose(stdout)) {
-		fprintf(stderr, "close failed on standard output: %s", strerror(errno));
+		fprintf(stderr, "close failed on standard output: %s",
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 	status = 0;
@@ -466,6 +469,7 @@ void pthread__unblock_sigwinch(void)
 int main(int argc, const char **argv)
 {
 	const char *cmd;
+	char sbuf[STRERR_BUFSIZE];
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
@@ -561,7 +565,7 @@ int main(int argc, const char **argv)
 	}
 
 	fprintf(stderr, "Failed to run command '%s': %s\n",
-		cmd, strerror(errno));
+		cmd, strerror_r(errno, sbuf, sizeof(sbuf)));
 out:
 	return 1;
 }
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 510c65f72858..220d44e44c1b 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -41,8 +41,6 @@ void pthread__unblock_sigwinch(void);
 
 struct record_opts {
 	struct target target;
-	int	     call_graph;
-	bool         call_graph_enabled;
 	bool	     group;
 	bool	     inherit_stat;
 	bool	     no_buffering;
@@ -60,7 +58,6 @@ struct record_opts {
 	u64          branch_stack;
 	u64	     default_interval;
 	u64	     user_interval;
-	u16	     stack_dump_size;
 	bool	     sample_transaction;
 	unsigned     initial_delay;
 };
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 6f8b01bc6033..ac655b0700e7 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -154,6 +154,18 @@ static struct test {
 		.func = test__hists_cumulate,
 	},
 	{
+		.desc = "Test tracking with sched_switch",
+		.func = test__switch_tracking,
+	},
+	{
+		.desc = "Filter fds with revents mask in a fdarray",
+		.func = test__fdarray__filter,
+	},
+	{
+		.desc = "Add fd to a fdarray, making it autogrow",
+		.func = test__fdarray__add,
+	},
+	{
 		.func = NULL,
 	},
 };
@@ -185,9 +197,11 @@ static bool perf_test__matches(int curr, int argc, const char *argv[])
 static int run_test(struct test *test)
 {
 	int status, err = -1, child = fork();
+	char sbuf[STRERR_BUFSIZE];
 
 	if (child < 0) {
-		pr_err("failed to fork test: %s\n", strerror(errno));
+		pr_err("failed to fork test: %s\n",
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 
@@ -297,7 +311,7 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
 	symbol_conf.sort_by_name = true;
 	symbol_conf.try_vmlinux_path = true;
 
-	if (symbol__init() < 0)
+	if (symbol__init(NULL) < 0)
 		return -1;
 
 	if (skip != NULL)
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
new file mode 100644
index 000000000000..d24b837951d4
--- /dev/null
+++ b/tools/perf/tests/fdarray.c
@@ -0,0 +1,174 @@
+#include <api/fd/array.h>
+#include "util/debug.h"
+#include "tests/tests.h"
+
+static void fdarray__init_revents(struct fdarray *fda, short revents)
+{
+	int fd;
+
+	fda->nr = fda->nr_alloc;
+
+	for (fd = 0; fd < fda->nr; ++fd) {
+		fda->entries[fd].fd	 = fda->nr - fd;
+		fda->entries[fd].revents = revents;
+	}
+}
+
+static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE *fp)
+{
+	int printed = 0;
+
+	if (!verbose)
+		return 0;
+
+	printed += fprintf(fp, "\n%s: ", prefix);
+	return printed + fdarray__fprintf(fda, fp);
+}
+
+int test__fdarray__filter(void)
+{
+	int nr_fds, expected_fd[2], fd, err = TEST_FAIL;
+	struct fdarray *fda = fdarray__new(5, 5);
+
+	if (fda == NULL) {
+		pr_debug("\nfdarray__new() failed!");
+		goto out;
+	}
+
+	fdarray__init_revents(fda, POLLIN);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	if (nr_fds != fda->nr_alloc) {
+		pr_debug("\nfdarray__filter()=%d != %d shouldn't have filtered anything",
+			 nr_fds, fda->nr_alloc);
+		goto out_delete;
+	}
+
+	fdarray__init_revents(fda, POLLHUP);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	if (nr_fds != 0) {
+		pr_debug("\nfdarray__filter()=%d != %d, should have filtered all fds",
+			 nr_fds, fda->nr_alloc);
+		goto out_delete;
+	}
+
+	fdarray__init_revents(fda, POLLHUP);
+	fda->entries[2].revents = POLLIN;
+	expected_fd[0] = fda->entries[2].fd;
+
+	pr_debug("\nfiltering all but fda->entries[2]:");
+	fdarray__fprintf_prefix(fda, "before", stderr);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	fdarray__fprintf_prefix(fda, " after", stderr);
+	if (nr_fds != 1) {
+		pr_debug("\nfdarray__filter()=%d != 1, should have left just one event", nr_fds);
+		goto out_delete;
+	}
+
+	if (fda->entries[0].fd != expected_fd[0]) {
+		pr_debug("\nfda->entries[0].fd=%d != %d\n",
+			 fda->entries[0].fd, expected_fd[0]);
+		goto out_delete;
+	}
+
+	fdarray__init_revents(fda, POLLHUP);
+	fda->entries[0].revents = POLLIN;
+	expected_fd[0] = fda->entries[0].fd;
+	fda->entries[3].revents = POLLIN;
+	expected_fd[1] = fda->entries[3].fd;
+
+	pr_debug("\nfiltering all but (fda->entries[0], fda->entries[3]):");
+	fdarray__fprintf_prefix(fda, "before", stderr);
+	nr_fds = fdarray__filter(fda, POLLHUP, NULL);
+	fdarray__fprintf_prefix(fda, " after", stderr);
+	if (nr_fds != 2) {
+		pr_debug("\nfdarray__filter()=%d != 2, should have left just two events",
+			 nr_fds);
+		goto out_delete;
+	}
+
+	for (fd = 0; fd < 2; ++fd) {
+		if (fda->entries[fd].fd != expected_fd[fd]) {
+			pr_debug("\nfda->entries[%d].fd=%d != %d\n", fd,
+				 fda->entries[fd].fd, expected_fd[fd]);
+			goto out_delete;
+		}
+	}
+
+	pr_debug("\n");
+
+	err = 0;
+out_delete:
+	fdarray__delete(fda);
+out:
+	return err;
+}
+
+int test__fdarray__add(void)
+{
+	int err = TEST_FAIL;
+	struct fdarray *fda = fdarray__new(2, 2);
+
+	if (fda == NULL) {
+		pr_debug("\nfdarray__new() failed!");
+		goto out;
+	}
+
+#define FDA_CHECK(_idx, _fd, _revents)					   \
+	if (fda->entries[_idx].fd != _fd) {				   \
+		pr_debug("\n%d: fda->entries[%d](%d) != %d!",		   \
+			 __LINE__, _idx, fda->entries[1].fd, _fd);	   \
+		goto out_delete;					   \
+	}								   \
+	if (fda->entries[_idx].events != (_revents)) {			   \
+		pr_debug("\n%d: fda->entries[%d].revents(%d) != %d!",	   \
+			 __LINE__, _idx, fda->entries[_idx].fd, _revents); \
+		goto out_delete;					   \
+	}
+
+#define FDA_ADD(_idx, _fd, _revents, _nr)				   \
+	if (fdarray__add(fda, _fd, _revents) < 0) {			   \
+		pr_debug("\n%d: fdarray__add(fda, %d, %d) failed!",	   \
+			 __LINE__,_fd, _revents);			   \
+		goto out_delete;					   \
+	}								   \
+	if (fda->nr != _nr) {						   \
+		pr_debug("\n%d: fdarray__add(fda, %d, %d)=%d != %d",	   \
+			 __LINE__,_fd, _revents, fda->nr, _nr);		   \
+		goto out_delete;					   \
+	}								   \
+	FDA_CHECK(_idx, _fd, _revents)
+
+	FDA_ADD(0, 1, POLLIN, 1);
+	FDA_ADD(1, 2, POLLERR, 2);
+
+	fdarray__fprintf_prefix(fda, "before growing array", stderr);
+
+	FDA_ADD(2, 35, POLLHUP, 3);
+
+	if (fda->entries == NULL) {
+		pr_debug("\nfdarray__add(fda, 35, POLLHUP) should have allocated fda->pollfd!");
+		goto out_delete;
+	}
+
+	fdarray__fprintf_prefix(fda, "after 3rd add", stderr);
+
+	FDA_ADD(3, 88, POLLIN | POLLOUT, 4);
+
+	fdarray__fprintf_prefix(fda, "after 4th add", stderr);
+
+	FDA_CHECK(0, 1, POLLIN);
+	FDA_CHECK(1, 2, POLLERR);
+	FDA_CHECK(2, 35, POLLHUP);
+	FDA_CHECK(3, 88, POLLIN | POLLOUT);
+
+#undef FDA_ADD
+#undef FDA_CHECK
+
+	pr_debug("\n");
+
+	err = 0;
+out_delete:
+	fdarray__delete(fda);
+out:
+	return err;
+}
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 142263492f6f..9b9622a33932 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -31,6 +31,7 @@ int test__basic_mmap(void)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
+	char sbuf[STRERR_BUFSIZE];
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
@@ -49,7 +50,7 @@ int test__basic_mmap(void)
 	sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
 	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
 		pr_debug("sched_setaffinity() failed on CPU %d: %s ",
-			 cpus->map[0], strerror(errno));
+			 cpus->map[0], strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_free_cpus;
 	}
 
@@ -79,7 +80,7 @@ int test__basic_mmap(void)
 		if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
 			pr_debug("failed to open counter: %s, "
 				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-				 strerror(errno));
+				 strerror_r(errno, sbuf, sizeof(sbuf)));
 			goto out_delete_evlist;
 		}
 
@@ -89,7 +90,7 @@ int test__basic_mmap(void)
 
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
-			 strerror(errno));
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c
index 5fecdbd2f5f7..8fa82d1700c7 100644
--- a/tools/perf/tests/open-syscall-all-cpus.c
+++ b/tools/perf/tests/open-syscall-all-cpus.c
@@ -12,6 +12,7 @@ int test__open_syscall_event_on_all_cpus(void)
 	unsigned int nr_open_calls = 111, i;
 	cpu_set_t cpu_set;
 	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+	char sbuf[STRERR_BUFSIZE];
 
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
@@ -35,7 +36,7 @@ int test__open_syscall_event_on_all_cpus(void)
 	if (perf_evsel__open(evsel, cpus, threads) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-			 strerror(errno));
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_evsel_delete;
 	}
 
@@ -56,7 +57,7 @@ int test__open_syscall_event_on_all_cpus(void)
 		if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
 			pr_debug("sched_setaffinity() failed on CPU %d: %s ",
 				 cpus->map[cpu],
-				 strerror(errno));
+				 strerror_r(errno, sbuf, sizeof(sbuf)));
 			goto out_close_fd;
 		}
 		for (i = 0; i < ncalls; ++i) {
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 0785b64ffd6c..127dcae0b760 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -22,6 +22,7 @@ int test__syscall_open_tp_fields(void)
 	struct perf_evlist *evlist = perf_evlist__new();
 	struct perf_evsel *evsel;
 	int err = -1, i, nr_events = 0, nr_polls = 0;
+	char sbuf[STRERR_BUFSIZE];
 
 	if (evlist == NULL) {
 		pr_debug("%s: perf_evlist__new\n", __func__);
@@ -48,13 +49,15 @@ int test__syscall_open_tp_fields(void)
 
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
-		pr_debug("perf_evlist__open: %s\n", strerror(errno));
+		pr_debug("perf_evlist__open: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
 	err = perf_evlist__mmap(evlist, UINT_MAX, false);
 	if (err < 0) {
-		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+		pr_debug("perf_evlist__mmap: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -102,7 +105,7 @@ int test__syscall_open_tp_fields(void)
 		}
 
 		if (nr_events == before)
-			poll(evlist->pollfd, evlist->nr_fds, 10);
+			perf_evlist__poll(evlist, 10);
 
 		if (++nr_polls > 5) {
 			pr_debug("%s: no events!\n", __func__);
diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c
index c1dc7d25f38c..a33b2daae40f 100644
--- a/tools/perf/tests/open-syscall.c
+++ b/tools/perf/tests/open-syscall.c
@@ -9,6 +9,7 @@ int test__open_syscall_event(void)
 	struct perf_evsel *evsel;
 	unsigned int nr_open_calls = 111, i;
 	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+	char sbuf[STRERR_BUFSIZE];
 
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
@@ -24,7 +25,7 @@ int test__open_syscall_event(void)
 	if (perf_evsel__open_per_thread(evsel, threads) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-			 strerror(errno));
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_evsel_delete;
 	}
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index aca1a83dd13a..7a228a2a070b 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -59,6 +59,7 @@ int test__PERF_RECORD(void)
 	int err = -1, errs = 0, i, wakeups = 0;
 	u32 cpu;
 	int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
+	char sbuf[STRERR_BUFSIZE];
 
 	if (evlist == NULL || argv == NULL) {
 		pr_debug("Not enough memory to create evlist\n");
@@ -100,7 +101,8 @@ int test__PERF_RECORD(void)
 
 	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
 	if (err < 0) {
-		pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
+		pr_debug("sched__get_first_possible_cpu: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -110,7 +112,8 @@ int test__PERF_RECORD(void)
 	 * So that we can check perf_sample.cpu on all the samples.
 	 */
 	if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
-		pr_debug("sched_setaffinity: %s\n", strerror(errno));
+		pr_debug("sched_setaffinity: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -120,7 +123,8 @@ int test__PERF_RECORD(void)
 	 */
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
-		pr_debug("perf_evlist__open: %s\n", strerror(errno));
+		pr_debug("perf_evlist__open: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -131,7 +135,8 @@ int test__PERF_RECORD(void)
 	 */
 	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
 	if (err < 0) {
-		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+		pr_debug("perf_evlist__mmap: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -263,7 +268,7 @@ int test__PERF_RECORD(void)
 		 * perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does.
 		 */
 		if (total_events == before && false)
-			poll(evlist->pollfd, evlist->nr_fds, -1);
+			perf_evlist__poll(evlist, -1);
 
 		sleep(1);
 		if (++wakeups > 5) {
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 12b322fa3475..eeb68bb1972d 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -152,7 +152,7 @@ int test__pmu(void)
 		if (ret)
 			break;
 
-		ret = perf_pmu__config_terms(&formats, &attr, terms);
+		ret = perf_pmu__config_terms(&formats, &attr, terms, false);
 		if (ret)
 			break;
 
diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c
index c04d1f268576..d31f2c4d9f64 100644
--- a/tools/perf/tests/rdpmc.c
+++ b/tools/perf/tests/rdpmc.c
@@ -100,6 +100,7 @@ static int __test__rdpmc(void)
 	};
 	u64 delta_sum = 0;
         struct sigaction sa;
+	char sbuf[STRERR_BUFSIZE];
 
 	sigfillset(&sa.sa_mask);
 	sa.sa_sigaction = segfault_handler;
@@ -109,14 +110,15 @@ static int __test__rdpmc(void)
 				 perf_event_open_cloexec_flag());
 	if (fd < 0) {
 		pr_err("Error: sys_perf_event_open() syscall returned "
-		       "with %d (%s)\n", fd, strerror(errno));
+		       "with %d (%s)\n", fd,
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 
 	addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
 	if (addr == (void *)(-1)) {
 		pr_err("Error: mmap() syscall returned with (%s)\n",
-		       strerror(errno));
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_close;
 	}
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 983d6b8562a8..1aa21c90731b 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -22,6 +22,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	volatile int tmp = 0;
 	u64 total_periods = 0;
 	int nr_samples = 0;
+	char sbuf[STRERR_BUFSIZE];
 	union perf_event *event;
 	struct perf_evsel *evsel;
 	struct perf_evlist *evlist;
@@ -62,14 +63,15 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 
 		err = -errno;
 		pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
-			 strerror(errno), knob, (u64)attr.sample_freq);
+			 strerror_r(errno, sbuf, sizeof(sbuf)),
+			 knob, (u64)attr.sample_freq);
 		goto out_delete_evlist;
 	}
 
 	err = perf_evlist__mmap(evlist, 128, true);
 	if (err < 0) {
 		pr_debug("failed to mmap event: %d (%s)\n", errno,
-			 strerror(errno));
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
new file mode 100644
index 000000000000..cc68648c7c55
--- /dev/null
+++ b/tools/perf/tests/switch-tracking.c
@@ -0,0 +1,572 @@
+#include <sys/time.h>
+#include <sys/prctl.h>
+#include <time.h>
+#include <stdlib.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+static int spin_sleep(void)
+{
+	struct timeval start, now, diff, maxtime;
+	struct timespec ts;
+	int err, i;
+
+	maxtime.tv_sec = 0;
+	maxtime.tv_usec = 50000;
+
+	err = gettimeofday(&start, NULL);
+	if (err)
+		return err;
+
+	/* Spin for 50ms */
+	while (1) {
+		for (i = 0; i < 1000; i++)
+			barrier();
+
+		err = gettimeofday(&now, NULL);
+		if (err)
+			return err;
+
+		timersub(&now, &start, &diff);
+		if (timercmp(&diff, &maxtime, > /* For checkpatch */))
+			break;
+	}
+
+	ts.tv_nsec = 50 * 1000 * 1000;
+	ts.tv_sec = 0;
+
+	/* Sleep for 50ms */
+	err = nanosleep(&ts, NULL);
+	if (err == EINTR)
+		err = 0;
+
+	return err;
+}
+
+struct switch_tracking {
+	struct perf_evsel *switch_evsel;
+	struct perf_evsel *cycles_evsel;
+	pid_t *tids;
+	int nr_tids;
+	int comm_seen[4];
+	int cycles_before_comm_1;
+	int cycles_between_comm_2_and_comm_3;
+	int cycles_after_comm_4;
+};
+
+static int check_comm(struct switch_tracking *switch_tracking,
+		      union perf_event *event, const char *comm, int nr)
+{
+	if (event->header.type == PERF_RECORD_COMM &&
+	    (pid_t)event->comm.pid == getpid() &&
+	    (pid_t)event->comm.tid == getpid() &&
+	    strcmp(event->comm.comm, comm) == 0) {
+		if (switch_tracking->comm_seen[nr]) {
+			pr_debug("Duplicate comm event\n");
+			return -1;
+		}
+		switch_tracking->comm_seen[nr] = 1;
+		pr_debug3("comm event: %s nr: %d\n", event->comm.comm, nr);
+		return 1;
+	}
+	return 0;
+}
+
+static int check_cpu(struct switch_tracking *switch_tracking, int cpu)
+{
+	int i, nr = cpu + 1;
+
+	if (cpu < 0)
+		return -1;
+
+	if (!switch_tracking->tids) {
+		switch_tracking->tids = calloc(nr, sizeof(pid_t));
+		if (!switch_tracking->tids)
+			return -1;
+		for (i = 0; i < nr; i++)
+			switch_tracking->tids[i] = -1;
+		switch_tracking->nr_tids = nr;
+		return 0;
+	}
+
+	if (cpu >= switch_tracking->nr_tids) {
+		void *addr;
+
+		addr = realloc(switch_tracking->tids, nr * sizeof(pid_t));
+		if (!addr)
+			return -1;
+		switch_tracking->tids = addr;
+		for (i = switch_tracking->nr_tids; i < nr; i++)
+			switch_tracking->tids[i] = -1;
+		switch_tracking->nr_tids = nr;
+		return 0;
+	}
+
+	return 0;
+}
+
+static int process_sample_event(struct perf_evlist *evlist,
+				union perf_event *event,
+				struct switch_tracking *switch_tracking)
+{
+	struct perf_sample sample;
+	struct perf_evsel *evsel;
+	pid_t next_tid, prev_tid;
+	int cpu, err;
+
+	if (perf_evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	evsel = perf_evlist__id2evsel(evlist, sample.id);
+	if (evsel == switch_tracking->switch_evsel) {
+		next_tid = perf_evsel__intval(evsel, &sample, "next_pid");
+		prev_tid = perf_evsel__intval(evsel, &sample, "prev_pid");
+		cpu = sample.cpu;
+		pr_debug3("sched_switch: cpu: %d prev_tid %d next_tid %d\n",
+			  cpu, prev_tid, next_tid);
+		err = check_cpu(switch_tracking, cpu);
+		if (err)
+			return err;
+		/*
+		 * Check for no missing sched_switch events i.e. that the
+		 * evsel->system_wide flag has worked.
+		 */
+		if (switch_tracking->tids[cpu] != -1 &&
+		    switch_tracking->tids[cpu] != prev_tid) {
+			pr_debug("Missing sched_switch events\n");
+			return -1;
+		}
+		switch_tracking->tids[cpu] = next_tid;
+	}
+
+	if (evsel == switch_tracking->cycles_evsel) {
+		pr_debug3("cycles event\n");
+		if (!switch_tracking->comm_seen[0])
+			switch_tracking->cycles_before_comm_1 = 1;
+		if (switch_tracking->comm_seen[1] &&
+		    !switch_tracking->comm_seen[2])
+			switch_tracking->cycles_between_comm_2_and_comm_3 = 1;
+		if (switch_tracking->comm_seen[3])
+			switch_tracking->cycles_after_comm_4 = 1;
+	}
+
+	return 0;
+}
+
+static int process_event(struct perf_evlist *evlist, union perf_event *event,
+			 struct switch_tracking *switch_tracking)
+{
+	if (event->header.type == PERF_RECORD_SAMPLE)
+		return process_sample_event(evlist, event, switch_tracking);
+
+	if (event->header.type == PERF_RECORD_COMM) {
+		int err, done = 0;
+
+		err = check_comm(switch_tracking, event, "Test COMM 1", 0);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 2", 1);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 3", 2);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 4", 3);
+		if (err < 0)
+			return -1;
+		done += err;
+		if (done != 1) {
+			pr_debug("Unexpected comm event\n");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+struct event_node {
+	struct list_head list;
+	union perf_event *event;
+	u64 event_time;
+};
+
+static int add_event(struct perf_evlist *evlist, struct list_head *events,
+		     union perf_event *event)
+{
+	struct perf_sample sample;
+	struct event_node *node;
+
+	node = malloc(sizeof(struct event_node));
+	if (!node) {
+		pr_debug("malloc failed\n");
+		return -1;
+	}
+	node->event = event;
+	list_add(&node->list, events);
+
+	if (perf_evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	if (!sample.time) {
+		pr_debug("event with no time\n");
+		return -1;
+	}
+
+	node->event_time = sample.time;
+
+	return 0;
+}
+
+static void free_event_nodes(struct list_head *events)
+{
+	struct event_node *node;
+
+	while (!list_empty(events)) {
+		node = list_entry(events->next, struct event_node, list);
+		list_del(&node->list);
+		free(node);
+	}
+}
+
+static int compar(const void *a, const void *b)
+{
+	const struct event_node *nodea = a;
+	const struct event_node *nodeb = b;
+	s64 cmp = nodea->event_time - nodeb->event_time;
+
+	return cmp;
+}
+
+static int process_events(struct perf_evlist *evlist,
+			  struct switch_tracking *switch_tracking)
+{
+	union perf_event *event;
+	unsigned pos, cnt = 0;
+	LIST_HEAD(events);
+	struct event_node *events_array, *node;
+	int i, ret;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			cnt += 1;
+			ret = add_event(evlist, &events, event);
+			perf_evlist__mmap_consume(evlist, i);
+			if (ret < 0)
+				goto out_free_nodes;
+		}
+	}
+
+	events_array = calloc(cnt, sizeof(struct event_node));
+	if (!events_array) {
+		pr_debug("calloc failed\n");
+		ret = -1;
+		goto out_free_nodes;
+	}
+
+	pos = 0;
+	list_for_each_entry(node, &events, list)
+		events_array[pos++] = *node;
+
+	qsort(events_array, cnt, sizeof(struct event_node), compar);
+
+	for (pos = 0; pos < cnt; pos++) {
+		ret = process_event(evlist, events_array[pos].event,
+				    switch_tracking);
+		if (ret < 0)
+			goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	pr_debug("%u events recorded\n", cnt);
+	free(events_array);
+out_free_nodes:
+	free_event_nodes(&events);
+	return ret;
+}
+
+/**
+ * test__switch_tracking - test using sched_switch and tracking events.
+ *
+ * This function implements a test that checks that sched_switch events and
+ * tracking events can be recorded for a workload (current process) using the
+ * evsel->system_wide and evsel->tracking flags (respectively) with other events
+ * sometimes enabled or disabled.
+ */
+int test__switch_tracking(void)
+{
+	const char *sched_switch = "sched:sched_switch";
+	struct switch_tracking switch_tracking = { .tids = NULL, };
+	struct record_opts opts = {
+		.mmap_pages	     = UINT_MAX,
+		.user_freq	     = UINT_MAX,
+		.user_interval	     = ULLONG_MAX,
+		.freq		     = 4000,
+		.target		     = {
+			.uses_mmap   = true,
+		},
+	};
+	struct thread_map *threads = NULL;
+	struct cpu_map *cpus = NULL;
+	struct perf_evlist *evlist = NULL;
+	struct perf_evsel *evsel, *cpu_clocks_evsel, *cycles_evsel;
+	struct perf_evsel *switch_evsel, *tracking_evsel;
+	const char *comm;
+	int err = -1;
+
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
+	if (!threads) {
+		pr_debug("thread_map__new failed!\n");
+		goto out_err;
+	}
+
+	cpus = cpu_map__new(NULL);
+	if (!cpus) {
+		pr_debug("cpu_map__new failed!\n");
+		goto out_err;
+	}
+
+	evlist = perf_evlist__new();
+	if (!evlist) {
+		pr_debug("perf_evlist__new failed!\n");
+		goto out_err;
+	}
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	/* First event */
+	err = parse_events(evlist, "cpu-clock:u");
+	if (err) {
+		pr_debug("Failed to parse event dummy:u\n");
+		goto out_err;
+	}
+
+	cpu_clocks_evsel = perf_evlist__last(evlist);
+
+	/* Second event */
+	err = parse_events(evlist, "cycles:u");
+	if (err) {
+		pr_debug("Failed to parse event cycles:u\n");
+		goto out_err;
+	}
+
+	cycles_evsel = perf_evlist__last(evlist);
+
+	/* Third event */
+	if (!perf_evlist__can_select_event(evlist, sched_switch)) {
+		fprintf(stderr, " (no sched_switch)");
+		err = 0;
+		goto out;
+	}
+
+	err = parse_events(evlist, sched_switch);
+	if (err) {
+		pr_debug("Failed to parse event %s\n", sched_switch);
+		goto out_err;
+	}
+
+	switch_evsel = perf_evlist__last(evlist);
+
+	perf_evsel__set_sample_bit(switch_evsel, CPU);
+	perf_evsel__set_sample_bit(switch_evsel, TIME);
+
+	switch_evsel->system_wide = true;
+	switch_evsel->no_aux_samples = true;
+	switch_evsel->immediate = true;
+
+	/* Test moving an event to the front */
+	if (cycles_evsel == perf_evlist__first(evlist)) {
+		pr_debug("cycles event already at front");
+		goto out_err;
+	}
+	perf_evlist__to_front(evlist, cycles_evsel);
+	if (cycles_evsel != perf_evlist__first(evlist)) {
+		pr_debug("Failed to move cycles event to front");
+		goto out_err;
+	}
+
+	perf_evsel__set_sample_bit(cycles_evsel, CPU);
+	perf_evsel__set_sample_bit(cycles_evsel, TIME);
+
+	/* Fourth event */
+	err = parse_events(evlist, "dummy:u");
+	if (err) {
+		pr_debug("Failed to parse event dummy:u\n");
+		goto out_err;
+	}
+
+	tracking_evsel = perf_evlist__last(evlist);
+
+	perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+	tracking_evsel->attr.freq = 0;
+	tracking_evsel->attr.sample_period = 1;
+
+	perf_evsel__set_sample_bit(tracking_evsel, TIME);
+
+	/* Config events */
+	perf_evlist__config(evlist, &opts);
+
+	/* Check moved event is still at the front */
+	if (cycles_evsel != perf_evlist__first(evlist)) {
+		pr_debug("Front event no longer at front");
+		goto out_err;
+	}
+
+	/* Check tracking event is tracking */
+	if (!tracking_evsel->attr.mmap || !tracking_evsel->attr.comm) {
+		pr_debug("Tracking event not tracking\n");
+		goto out_err;
+	}
+
+	/* Check non-tracking events are not tracking */
+	evlist__for_each(evlist, evsel) {
+		if (evsel != tracking_evsel) {
+			if (evsel->attr.mmap || evsel->attr.comm) {
+				pr_debug("Non-tracking event is tracking\n");
+				goto out_err;
+			}
+		}
+	}
+
+	if (perf_evlist__open(evlist) < 0) {
+		fprintf(stderr, " (not supported)");
+		err = 0;
+		goto out;
+	}
+
+	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	if (err) {
+		pr_debug("perf_evlist__mmap failed!\n");
+		goto out_err;
+	}
+
+	perf_evlist__enable(evlist);
+
+	err = perf_evlist__disable_event(evlist, cpu_clocks_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 1";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = perf_evlist__disable_event(evlist, cycles_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 2";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 3";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = perf_evlist__enable_event(evlist, cycles_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 4";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	perf_evlist__disable(evlist);
+
+	switch_tracking.switch_evsel = switch_evsel;
+	switch_tracking.cycles_evsel = cycles_evsel;
+
+	err = process_events(evlist, &switch_tracking);
+
+	zfree(&switch_tracking.tids);
+
+	if (err)
+		goto out_err;
+
+	/* Check all 4 comm events were seen i.e. that evsel->tracking works */
+	if (!switch_tracking.comm_seen[0] || !switch_tracking.comm_seen[1] ||
+	    !switch_tracking.comm_seen[2] || !switch_tracking.comm_seen[3]) {
+		pr_debug("Missing comm events\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got enabled */
+	if (!switch_tracking.cycles_before_comm_1) {
+		pr_debug("Missing cycles events\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got disabled */
+	if (switch_tracking.cycles_between_comm_2_and_comm_3) {
+		pr_debug("cycles events even though event was disabled\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got enabled again */
+	if (!switch_tracking.cycles_after_comm_4) {
+		pr_debug("Missing cycles events\n");
+		goto out_err;
+	}
+out:
+	if (evlist) {
+		perf_evlist__disable(evlist);
+		perf_evlist__delete(evlist);
+	} else {
+		cpu_map__delete(cpus);
+		thread_map__delete(threads);
+	}
+
+	return err;
+
+out_err:
+	err = -1;
+	goto out;
+}
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 5ff3db318f12..3a8fedef83bc 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -42,6 +42,7 @@ int test__task_exit(void)
 		.uses_mmap	= true,
 	};
 	const char *argv[] = { "true", NULL };
+	char sbuf[STRERR_BUFSIZE];
 
 	signal(SIGCHLD, sig_handler);
 
@@ -82,13 +83,14 @@ int test__task_exit(void)
 
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
-		pr_debug("Couldn't open the evlist: %s\n", strerror(-err));
+		pr_debug("Couldn't open the evlist: %s\n",
+			 strerror_r(-err, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
-			 strerror(errno));
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -103,7 +105,7 @@ retry:
 	}
 
 	if (!exited || !nr_exit) {
-		poll(evlist->pollfd, evlist->nr_fds, -1);
+		perf_evlist__poll(evlist, -1);
 		goto retry;
 	}
 
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index ed64790a395f..00e776a87a9c 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -48,6 +48,9 @@ int test__mmap_thread_lookup(void);
 int test__thread_mg_share(void);
 int test__hists_output(void);
 int test__hists_cumulate(void);
+int test__switch_tracking(void);
+int test__fdarray__filter(void);
+int test__fdarray__add(void);
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a94b11fc5e00..8f60a970404f 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -10,6 +10,7 @@
 #include "../../util/pstack.h"
 #include "../../util/sort.h"
 #include "../../util/util.h"
+#include "../../util/top.h"
 #include "../../arch/common.h"
 
 #include "../browser.h"
@@ -228,8 +229,10 @@ static void callchain_node__init_have_children(struct callchain_node *node)
 {
 	struct callchain_list *chain;
 
-	list_for_each_entry(chain, &node->val, list)
+	if (!list_empty(&node->val)) {
+		chain = list_entry(node->val.prev, struct callchain_list, list);
 		chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
+	}
 
 	callchain_node__init_have_children_rb_tree(node);
 }
@@ -474,26 +477,87 @@ static char *callchain_list__sym_name(struct callchain_list *cl,
 	return bf;
 }
 
+struct callchain_print_arg {
+	/* for hists browser */
+	off_t	row_offset;
+	bool	is_current_entry;
+
+	/* for file dump */
+	FILE	*fp;
+	int	printed;
+};
+
+typedef void (*print_callchain_entry_fn)(struct hist_browser *browser,
+					 struct callchain_list *chain,
+					 const char *str, int offset,
+					 unsigned short row,
+					 struct callchain_print_arg *arg);
+
+static void hist_browser__show_callchain_entry(struct hist_browser *browser,
+					       struct callchain_list *chain,
+					       const char *str, int offset,
+					       unsigned short row,
+					       struct callchain_print_arg *arg)
+{
+	int color, width;
+	char folded_sign = callchain_list__folded(chain);
+
+	color = HE_COLORSET_NORMAL;
+	width = browser->b.width - (offset + 2);
+	if (ui_browser__is_current_entry(&browser->b, row)) {
+		browser->selection = &chain->ms;
+		color = HE_COLORSET_SELECTED;
+		arg->is_current_entry = true;
+	}
+
+	ui_browser__set_color(&browser->b, color);
+	hist_browser__gotorc(browser, row, 0);
+	slsmg_write_nstring(" ", offset);
+	slsmg_printf("%c ", folded_sign);
+	slsmg_write_nstring(str, width);
+}
+
+static void hist_browser__fprintf_callchain_entry(struct hist_browser *b __maybe_unused,
+						  struct callchain_list *chain,
+						  const char *str, int offset,
+						  unsigned short row __maybe_unused,
+						  struct callchain_print_arg *arg)
+{
+	char folded_sign = callchain_list__folded(chain);
+
+	arg->printed += fprintf(arg->fp, "%*s%c %s\n", offset, " ",
+				folded_sign, str);
+}
+
+typedef bool (*check_output_full_fn)(struct hist_browser *browser,
+				     unsigned short row);
+
+static bool hist_browser__check_output_full(struct hist_browser *browser,
+					    unsigned short row)
+{
+	return browser->b.rows == row;
+}
+
+static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_unused,
+					  unsigned short row __maybe_unused)
+{
+	return false;
+}
+
 #define LEVEL_OFFSET_STEP 3
 
-static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browser,
-						     struct callchain_node *chain_node,
-						     u64 total, int level,
-						     unsigned short row,
-						     off_t *row_offset,
-						     bool *is_current_entry)
+static int hist_browser__show_callchain(struct hist_browser *browser,
+					struct rb_root *root, int level,
+					unsigned short row, u64 total,
+					print_callchain_entry_fn print,
+					struct callchain_print_arg *arg,
+					check_output_full_fn is_output_full)
 {
 	struct rb_node *node;
-	int first_row = row, width, offset = level * LEVEL_OFFSET_STEP;
-	u64 new_total, remaining;
+	int first_row = row, offset = level * LEVEL_OFFSET_STEP;
+	u64 new_total;
 
-	if (callchain_param.mode == CHAIN_GRAPH_REL)
-		new_total = chain_node->children_hit;
-	else
-		new_total = total;
-
-	remaining = new_total;
-	node = rb_first(&chain_node->rb_root);
+	node = rb_first(root);
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
 		struct rb_node *next = rb_next(node);
@@ -503,30 +567,28 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse
 		int first = true;
 		int extra_offset = 0;
 
-		remaining -= cumul;
-
 		list_for_each_entry(chain, &child->val, list) {
 			char bf[1024], *alloc_str;
 			const char *str;
-			int color;
 			bool was_first = first;
 
 			if (first)
 				first = false;
-			else
+			else if (level > 1)
 				extra_offset = LEVEL_OFFSET_STEP;
 
 			folded_sign = callchain_list__folded(chain);
-			if (*row_offset != 0) {
-				--*row_offset;
+			if (arg->row_offset != 0) {
+				arg->row_offset--;
 				goto do_next;
 			}
 
 			alloc_str = NULL;
 			str = callchain_list__sym_name(chain, bf, sizeof(bf),
 						       browser->show_dso);
-			if (was_first) {
-				double percent = cumul * 100.0 / new_total;
+
+			if (was_first && level > 1) {
+				double percent = cumul * 100.0 / total;
 
 				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
 					str = "Not enough memory!";
@@ -534,22 +596,11 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse
 					str = alloc_str;
 			}
 
-			color = HE_COLORSET_NORMAL;
-			width = browser->b.width - (offset + extra_offset + 2);
-			if (ui_browser__is_current_entry(&browser->b, row)) {
-				browser->selection = &chain->ms;
-				color = HE_COLORSET_SELECTED;
-				*is_current_entry = true;
-			}
+			print(browser, chain, str, offset + extra_offset, row, arg);
 
-			ui_browser__set_color(&browser->b, color);
-			hist_browser__gotorc(browser, row, 0);
-			slsmg_write_nstring(" ", offset + extra_offset);
-			slsmg_printf("%c ", folded_sign);
-			slsmg_write_nstring(str, width);
 			free(alloc_str);
 
-			if (++row == browser->b.rows)
+			if (is_output_full(browser, ++row))
 				goto out;
 do_next:
 			if (folded_sign == '+')
@@ -558,89 +609,21 @@ do_next:
 
 		if (folded_sign == '-') {
 			const int new_level = level + (extra_offset ? 2 : 1);
-			row += hist_browser__show_callchain_node_rb_tree(browser, child, new_total,
-									 new_level, row, row_offset,
-									 is_current_entry);
-		}
-		if (row == browser->b.rows)
-			goto out;
-		node = next;
-	}
-out:
-	return row - first_row;
-}
-
-static int hist_browser__show_callchain_node(struct hist_browser *browser,
-					     struct callchain_node *node,
-					     int level, unsigned short row,
-					     off_t *row_offset,
-					     bool *is_current_entry)
-{
-	struct callchain_list *chain;
-	int first_row = row,
-	     offset = level * LEVEL_OFFSET_STEP,
-	     width = browser->b.width - offset;
-	char folded_sign = ' ';
 
-	list_for_each_entry(chain, &node->val, list) {
-		char bf[1024], *s;
-		int color;
-
-		folded_sign = callchain_list__folded(chain);
-
-		if (*row_offset != 0) {
-			--*row_offset;
-			continue;
-		}
+			if (callchain_param.mode == CHAIN_GRAPH_REL)
+				new_total = child->children_hit;
+			else
+				new_total = total;
 
-		color = HE_COLORSET_NORMAL;
-		if (ui_browser__is_current_entry(&browser->b, row)) {
-			browser->selection = &chain->ms;
-			color = HE_COLORSET_SELECTED;
-			*is_current_entry = true;
+			row += hist_browser__show_callchain(browser, &child->rb_root,
+							    new_level, row, new_total,
+							    print, arg, is_output_full);
 		}
-
-		s = callchain_list__sym_name(chain, bf, sizeof(bf),
-					     browser->show_dso);
-		hist_browser__gotorc(browser, row, 0);
-		ui_browser__set_color(&browser->b, color);
-		slsmg_write_nstring(" ", offset);
-		slsmg_printf("%c ", folded_sign);
-		slsmg_write_nstring(s, width - 2);
-
-		if (++row == browser->b.rows)
-			goto out;
-	}
-
-	if (folded_sign == '-')
-		row += hist_browser__show_callchain_node_rb_tree(browser, node,
-								 browser->hists->stats.total_period,
-								 level + 1, row,
-								 row_offset,
-								 is_current_entry);
-out:
-	return row - first_row;
-}
-
-static int hist_browser__show_callchain(struct hist_browser *browser,
-					struct rb_root *chain,
-					int level, unsigned short row,
-					off_t *row_offset,
-					bool *is_current_entry)
-{
-	struct rb_node *nd;
-	int first_row = row;
-
-	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
-		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
-
-		row += hist_browser__show_callchain_node(browser, node, level,
-							 row, row_offset,
-							 is_current_entry);
-		if (row == browser->b.rows)
+		if (is_output_full(browser, row))
 			break;
+		node = next;
 	}
-
+out:
 	return row - first_row;
 }
 
@@ -653,17 +636,18 @@ struct hpp_arg {
 static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	struct hpp_arg *arg = hpp->ptr;
-	int ret;
+	int ret, len;
 	va_list args;
 	double percent;
 
 	va_start(args, fmt);
+	len = va_arg(args, int);
 	percent = va_arg(args, double);
 	va_end(args);
 
 	ui_browser__set_percent_color(arg->b, percent, arg->current_entry);
 
-	ret = scnprintf(hpp->buf, hpp->size, fmt, percent);
+	ret = scnprintf(hpp->buf, hpp->size, fmt, len, percent);
 	slsmg_printf("%s", hpp->buf);
 
 	advance_hpp(hpp, ret);
@@ -677,12 +661,12 @@ static u64 __hpp_get_##_field(struct hist_entry *he)			\
 }									\
 									\
 static int								\
-hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				struct perf_hpp *hpp,			\
 				struct hist_entry *he)			\
 {									\
-	return __hpp__fmt(hpp, he, __hpp_get_##_field, " %6.2f%%",	\
-			  __hpp__slsmg_color_printf, true);		\
+	return hpp__fmt(fmt, hpp, he, __hpp_get_##_field, " %*.2f%%",	\
+			__hpp__slsmg_color_printf, true);		\
 }
 
 #define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)			\
@@ -692,18 +676,20 @@ static u64 __hpp_get_acc_##_field(struct hist_entry *he)		\
 }									\
 									\
 static int								\
-hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				struct perf_hpp *hpp,			\
 				struct hist_entry *he)			\
 {									\
 	if (!symbol_conf.cumulate_callchain) {				\
-		int ret = scnprintf(hpp->buf, hpp->size, "%8s", "N/A");	\
+		int len = fmt->user_len ?: fmt->len;			\
+		int ret = scnprintf(hpp->buf, hpp->size,		\
+				    "%*s", len, "N/A");			\
 		slsmg_printf("%s", hpp->buf);				\
 									\
 		return ret;						\
 	}								\
-	return __hpp__fmt(hpp, he, __hpp_get_acc_##_field, " %6.2f%%",	\
-			  __hpp__slsmg_color_printf, true);		\
+	return hpp__fmt(fmt, hpp, he, __hpp_get_acc_##_field,		\
+			" %*.2f%%", __hpp__slsmg_color_printf, true);	\
 }
 
 __HPP_COLOR_PERCENT_FN(overhead, period)
@@ -812,10 +798,18 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 		--row_offset;
 
 	if (folded_sign == '-' && row != browser->b.rows) {
-		printed += hist_browser__show_callchain(browser, &entry->sorted_chain,
-							1, row, &row_offset,
-							&current_entry);
-		if (current_entry)
+		u64 total = hists__total_period(entry->hists);
+		struct callchain_print_arg arg = {
+			.row_offset = row_offset,
+			.is_current_entry = current_entry,
+		};
+
+		printed += hist_browser__show_callchain(browser,
+					&entry->sorted_chain, 1, row, total,
+					hist_browser__show_callchain_entry, &arg,
+					hist_browser__check_output_full);
+
+		if (arg.is_current_entry)
 			browser->he_selection = entry;
 	}
 
@@ -847,9 +841,6 @@ static int hists__scnprintf_headers(char *buf, size_t size, struct hists *hists)
 		if (perf_hpp__should_skip(fmt))
 			continue;
 
-		/* We need to add the length of the columns header. */
-		perf_hpp__reset_width(fmt, hists);
-
 		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
@@ -1074,113 +1065,21 @@ do_offset:
 	}
 }
 
-static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *browser,
-							struct callchain_node *chain_node,
-							u64 total, int level,
-							FILE *fp)
-{
-	struct rb_node *node;
-	int offset = level * LEVEL_OFFSET_STEP;
-	u64 new_total, remaining;
-	int printed = 0;
-
-	if (callchain_param.mode == CHAIN_GRAPH_REL)
-		new_total = chain_node->children_hit;
-	else
-		new_total = total;
-
-	remaining = new_total;
-	node = rb_first(&chain_node->rb_root);
-	while (node) {
-		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
-		struct rb_node *next = rb_next(node);
-		u64 cumul = callchain_cumul_hits(child);
-		struct callchain_list *chain;
-		char folded_sign = ' ';
-		int first = true;
-		int extra_offset = 0;
-
-		remaining -= cumul;
-
-		list_for_each_entry(chain, &child->val, list) {
-			char bf[1024], *alloc_str;
-			const char *str;
-			bool was_first = first;
-
-			if (first)
-				first = false;
-			else
-				extra_offset = LEVEL_OFFSET_STEP;
-
-			folded_sign = callchain_list__folded(chain);
-
-			alloc_str = NULL;
-			str = callchain_list__sym_name(chain, bf, sizeof(bf),
-						       browser->show_dso);
-			if (was_first) {
-				double percent = cumul * 100.0 / new_total;
-
-				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
-					str = "Not enough memory!";
-				else
-					str = alloc_str;
-			}
-
-			printed += fprintf(fp, "%*s%c %s\n", offset + extra_offset, " ", folded_sign, str);
-			free(alloc_str);
-			if (folded_sign == '+')
-				break;
-		}
-
-		if (folded_sign == '-') {
-			const int new_level = level + (extra_offset ? 2 : 1);
-			printed += hist_browser__fprintf_callchain_node_rb_tree(browser, child, new_total,
-										new_level, fp);
-		}
-
-		node = next;
-	}
-
-	return printed;
-}
-
-static int hist_browser__fprintf_callchain_node(struct hist_browser *browser,
-						struct callchain_node *node,
-						int level, FILE *fp)
-{
-	struct callchain_list *chain;
-	int offset = level * LEVEL_OFFSET_STEP;
-	char folded_sign = ' ';
-	int printed = 0;
-
-	list_for_each_entry(chain, &node->val, list) {
-		char bf[1024], *s;
-
-		folded_sign = callchain_list__folded(chain);
-		s = callchain_list__sym_name(chain, bf, sizeof(bf), browser->show_dso);
-		printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s);
-	}
-
-	if (folded_sign == '-')
-		printed += hist_browser__fprintf_callchain_node_rb_tree(browser, node,
-									browser->hists->stats.total_period,
-									level + 1,  fp);
-	return printed;
-}
-
 static int hist_browser__fprintf_callchain(struct hist_browser *browser,
-					   struct rb_root *chain, int level, FILE *fp)
+					   struct hist_entry *he, FILE *fp)
 {
-	struct rb_node *nd;
-	int printed = 0;
+	u64 total = hists__total_period(he->hists);
+	struct callchain_print_arg arg  = {
+		.fp = fp,
+	};
 
-	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
-		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+	if (symbol_conf.cumulate_callchain)
+		total = he->stat_acc->period;
 
-		printed += hist_browser__fprintf_callchain_node(browser, node, level, fp);
-	}
-
-	return printed;
+	hist_browser__show_callchain(browser, &he->sorted_chain, 1, 0, total,
+				     hist_browser__fprintf_callchain_entry, &arg,
+				     hist_browser__check_dump_full);
+	return arg.printed;
 }
 
 static int hist_browser__fprintf_entry(struct hist_browser *browser,
@@ -1219,7 +1118,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 	printed += fprintf(fp, "%s\n", rtrim(s));
 
 	if (folded_sign == '-')
-		printed += hist_browser__fprintf_callchain(browser, &he->sorted_chain, 1, fp);
+		printed += hist_browser__fprintf_callchain(browser, he, fp);
 
 	return printed;
 }
@@ -1498,6 +1397,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	char buf[64];
 	char script_opt[64];
 	int delay_secs = hbt ? hbt->refresh : 0;
+	struct perf_hpp_fmt *fmt;
 
 #define HIST_BROWSER_HELP_COMMON					\
 	"h/?/F1        Show this window\n"				\
@@ -1529,6 +1429,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"P             Print histograms to perf.hist.N\n"
 	"t             Zoom into current Thread\n"
 	"V             Verbose (DSO names in callchains, etc)\n"
+	"z             Toggle zeroing of samples\n"
 	"/             Filter symbol by name";
 
 	if (browser == NULL)
@@ -1547,6 +1448,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 	memset(options, 0, sizeof(options));
 
+	perf_hpp__for_each_format(fmt)
+		perf_hpp__reset_width(fmt, hists);
+
+	if (symbol_conf.col_width_list_str)
+		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
 	while (1) {
 		const struct thread *thread = NULL;
 		const struct dso *dso = NULL;
@@ -1623,6 +1530,13 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		case 'F':
 			symbol_conf.filter_relative ^= 1;
 			continue;
+		case 'z':
+			if (!is_report_browser(hbt)) {
+				struct perf_top *top = hbt->arg;
+
+				top->zero = !top->zero;
+			}
+			continue;
 		case K_F1:
 		case 'h':
 		case '?':
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 6ca60e482cdc..f3fa4258b256 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -11,6 +11,7 @@
 static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	int ret = 0;
+	int len;
 	va_list args;
 	double percent;
 	const char *markup;
@@ -18,6 +19,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
 	size_t size = hpp->size;
 
 	va_start(args, fmt);
+	len = va_arg(args, int);
 	percent = va_arg(args, double);
 	va_end(args);
 
@@ -25,7 +27,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
 	if (markup)
 		ret += scnprintf(buf, size, markup);
 
-	ret += scnprintf(buf + ret, size - ret, fmt, percent);
+	ret += scnprintf(buf + ret, size - ret, fmt, len, percent);
 
 	if (markup)
 		ret += scnprintf(buf + ret, size - ret, "</span>");
@@ -39,12 +41,12 @@ static u64 he_get_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				       struct perf_hpp *hpp,			\
 				       struct hist_entry *he)			\
 {										\
-	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
-			  __percent_color_snprintf, true);			\
+	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
+			__percent_color_snprintf, true);			\
 }
 
 #define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
@@ -57,8 +59,8 @@ static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,
 				       struct perf_hpp *hpp,			\
 				       struct hist_entry *he)			\
 {										\
-	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
-			      __percent_color_snprintf, true);			\
+	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", 	\
+			    __percent_color_snprintf, true);			\
 }
 
 __HPP_COLOR_PERCENT_FN(overhead, period)
@@ -205,10 +207,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 		if (perf_hpp__is_sort_entry(fmt))
 			sym_col = col_idx;
 
-		fmt->header(fmt, &hpp, hists_to_evsel(hists));
-
 		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
-							    -1, ltrim(s),
+							    -1, fmt->name,
 							    renderer, "markup",
 							    col_idx++, NULL);
 	}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 498adb23c02e..2af18376b077 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -15,9 +15,9 @@
 	__ret;							\
 })
 
-int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
-	       hpp_field_fn get_field, const char *fmt,
-	       hpp_snprint_fn print_fn, bool fmt_percent)
+static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
+		      hpp_field_fn get_field, const char *fmt, int len,
+		      hpp_snprint_fn print_fn, bool fmt_percent)
 {
 	int ret;
 	struct hists *hists = he->hists;
@@ -32,9 +32,9 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 		if (total)
 			percent = 100.0 * get_field(he) / total;
 
-		ret = hpp__call_print_fn(hpp, print_fn, fmt, percent);
+		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, percent);
 	} else
-		ret = hpp__call_print_fn(hpp, print_fn, fmt, get_field(he));
+		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, get_field(he));
 
 	if (perf_evsel__is_group_event(evsel)) {
 		int prev_idx, idx_delta;
@@ -60,19 +60,19 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 				 */
 				if (fmt_percent) {
 					ret += hpp__call_print_fn(hpp, print_fn,
-								  fmt, 0.0);
+								  fmt, len, 0.0);
 				} else {
 					ret += hpp__call_print_fn(hpp, print_fn,
-								  fmt, 0ULL);
+								  fmt, len, 0ULL);
 				}
 			}
 
 			if (fmt_percent) {
-				ret += hpp__call_print_fn(hpp, print_fn, fmt,
+				ret += hpp__call_print_fn(hpp, print_fn, fmt, len,
 							  100.0 * period / total);
 			} else {
 				ret += hpp__call_print_fn(hpp, print_fn, fmt,
-							  period);
+							  len, period);
 			}
 
 			prev_idx = perf_evsel__group_idx(evsel);
@@ -86,10 +86,10 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 			 */
 			if (fmt_percent) {
 				ret += hpp__call_print_fn(hpp, print_fn,
-							  fmt, 0.0);
+							  fmt, len, 0.0);
 			} else {
 				ret += hpp__call_print_fn(hpp, print_fn,
-							  fmt, 0ULL);
+							  fmt, len, 0ULL);
 			}
 		}
 	}
@@ -104,16 +104,35 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	return ret;
 }
 
-int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
-		   hpp_field_fn get_field, const char *fmt,
-		   hpp_snprint_fn print_fn, bool fmt_percent)
+int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+	     struct hist_entry *he, hpp_field_fn get_field,
+	     const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
+{
+	int len = fmt->user_len ?: fmt->len;
+
+	if (symbol_conf.field_sep) {
+		return __hpp__fmt(hpp, he, get_field, fmtstr, 1,
+				  print_fn, fmt_percent);
+	}
+
+	if (fmt_percent)
+		len -= 2; /* 2 for a space and a % sign */
+	else
+		len -= 1;
+
+	return  __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmt_percent);
+}
+
+int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		 struct hist_entry *he, hpp_field_fn get_field,
+		 const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
 {
 	if (!symbol_conf.cumulate_callchain) {
-		return snprintf(hpp->buf, hpp->size, "%*s",
-				fmt_percent ? 8 : 12, "N/A");
+		int len = fmt->user_len ?: fmt->len;
+		return snprintf(hpp->buf, hpp->size, " %*s", len - 1, "N/A");
 	}
 
-	return __hpp__fmt(hpp, he, get_field, fmt, print_fn, fmt_percent);
+	return hpp__fmt(fmt, hpp, he, get_field, fmtstr, print_fn, fmt_percent);
 }
 
 static int field_cmp(u64 field_a, u64 field_b)
@@ -190,30 +209,26 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
 	return ret;
 }
 
-#define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) 		\
-static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
-			       struct perf_hpp *hpp,			\
-			       struct perf_evsel *evsel)		\
-{									\
-	int len = _min_width;						\
-									\
-	if (symbol_conf.event_group)					\
-		len = max(len, evsel->nr_members * _unit_width);	\
-									\
-	return scnprintf(hpp->buf, hpp->size, "%*s", len, _str);	\
-}
-
-#define __HPP_WIDTH_FN(_type, _min_width, _unit_width) 			\
-static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
-			      struct perf_hpp *hpp __maybe_unused,	\
-			      struct perf_evsel *evsel)			\
-{									\
-	int len = _min_width;						\
-									\
-	if (symbol_conf.event_group)					\
-		len = max(len, evsel->nr_members * _unit_width);	\
-									\
-	return len;							\
+static int hpp__width_fn(struct perf_hpp_fmt *fmt,
+			 struct perf_hpp *hpp __maybe_unused,
+			 struct perf_evsel *evsel)
+{
+	int len = fmt->user_len ?: fmt->len;
+
+	if (symbol_conf.event_group)
+		len = max(len, evsel->nr_members * fmt->len);
+
+	if (len < (int)strlen(fmt->name))
+		len = strlen(fmt->name);
+
+	return len;
+}
+
+static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			  struct perf_evsel *evsel)
+{
+	int len = hpp__width_fn(fmt, hpp, evsel);
+	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
 static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
@@ -221,11 +236,12 @@ static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
 	va_list args;
 	ssize_t ssize = hpp->size;
 	double percent;
-	int ret;
+	int ret, len;
 
 	va_start(args, fmt);
+	len = va_arg(args, int);
 	percent = va_arg(args, double);
-	ret = value_color_snprintf(hpp->buf, hpp->size, fmt, percent);
+	ret = percent_color_len_snprintf(hpp->buf, hpp->size, fmt, len, percent);
 	va_end(args);
 
 	return (ret >= ssize) ? (ssize - 1) : ret;
@@ -250,20 +266,19 @@ static u64 he_get_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
-			  hpp_color_scnprintf, true);				\
+	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
+			hpp_color_scnprintf, true);				\
 }
 
 #define __HPP_ENTRY_PERCENT_FN(_type, _field)					\
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
-	return __hpp__fmt(hpp, he, he_get_##_field, fmt,			\
-			  hpp_entry_scnprintf, true);				\
+	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
+			hpp_entry_scnprintf, true);				\
 }
 
 #define __HPP_SORT_FN(_type, _field)						\
@@ -278,20 +293,19 @@ static u64 he_get_acc_##_field(struct hist_entry *he)				\
 	return he->stat_acc->_field;						\
 }										\
 										\
-static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
-			      hpp_color_scnprintf, true);			\
+	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", 	\
+			    hpp_color_scnprintf, true);				\
 }
 
 #define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
-	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, fmt,		\
-			      hpp_entry_scnprintf, true);			\
+	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%",	\
+			    hpp_entry_scnprintf, true);				\
 }
 
 #define __HPP_SORT_ACC_FN(_type, _field)					\
@@ -306,12 +320,11 @@ static u64 he_get_raw_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64;	\
-	return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt,			\
-			  hpp_entry_scnprintf, false);				\
+	return hpp__fmt(fmt, hpp, he, he_get_raw_##_field, " %*"PRIu64, 	\
+			hpp_entry_scnprintf, false);				\
 }
 
 #define __HPP_SORT_RAW_FN(_type, _field)					\
@@ -321,37 +334,29 @@ static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
 }
 
 
-#define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width)	\
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+#define HPP_PERCENT_FNS(_type, _field)					\
 __HPP_COLOR_PERCENT_FN(_type, _field)					\
 __HPP_ENTRY_PERCENT_FN(_type, _field)					\
 __HPP_SORT_FN(_type, _field)
 
-#define HPP_PERCENT_ACC_FNS(_type, _str, _field, _min_width, _unit_width)\
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+#define HPP_PERCENT_ACC_FNS(_type, _field)				\
 __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
 __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
 __HPP_SORT_ACC_FN(_type, _field)
 
-#define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width)	\
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+#define HPP_RAW_FNS(_type, _field)					\
 __HPP_ENTRY_RAW_FN(_type, _field)					\
 __HPP_SORT_RAW_FN(_type, _field)
 
-__HPP_HEADER_FN(overhead_self, "Self", 8, 8)
-
-HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8)
-HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8)
-HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8)
-HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8)
-HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
-HPP_PERCENT_ACC_FNS(overhead_acc, "Children", period, 8, 8)
+HPP_PERCENT_FNS(overhead, period)
+HPP_PERCENT_FNS(overhead_sys, period_sys)
+HPP_PERCENT_FNS(overhead_us, period_us)
+HPP_PERCENT_FNS(overhead_guest_sys, period_guest_sys)
+HPP_PERCENT_FNS(overhead_guest_us, period_guest_us)
+HPP_PERCENT_ACC_FNS(overhead_acc, period)
 
-HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
-HPP_RAW_FNS(period, "Period", period, 12, 12)
+HPP_RAW_FNS(samples, nr_events)
+HPP_RAW_FNS(period, period)
 
 static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
 			    struct hist_entry *b __maybe_unused)
@@ -359,47 +364,50 @@ static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
 	return 0;
 }
 
-#define HPP__COLOR_PRINT_FNS(_name)			\
+#define HPP__COLOR_PRINT_FNS(_name, _fn)		\
 	{						\
-		.header	= hpp__header_ ## _name,	\
-		.width	= hpp__width_ ## _name,		\
-		.color	= hpp__color_ ## _name,		\
-		.entry	= hpp__entry_ ## _name,		\
+		.name   = _name,			\
+		.header	= hpp__header_fn,		\
+		.width	= hpp__width_fn,		\
+		.color	= hpp__color_ ## _fn,		\
+		.entry	= hpp__entry_ ## _fn,		\
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
-		.sort	= hpp__sort_ ## _name,		\
+		.sort	= hpp__sort_ ## _fn,		\
 	}
 
-#define HPP__COLOR_ACC_PRINT_FNS(_name)			\
+#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn)		\
 	{						\
-		.header	= hpp__header_ ## _name,	\
-		.width	= hpp__width_ ## _name,		\
-		.color	= hpp__color_ ## _name,		\
-		.entry	= hpp__entry_ ## _name,		\
+		.name   = _name,			\
+		.header	= hpp__header_fn,		\
+		.width	= hpp__width_fn,		\
+		.color	= hpp__color_ ## _fn,		\
+		.entry	= hpp__entry_ ## _fn,		\
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
-		.sort	= hpp__sort_ ## _name,		\
+		.sort	= hpp__sort_ ## _fn,		\
 	}
 
-#define HPP__PRINT_FNS(_name)				\
+#define HPP__PRINT_FNS(_name, _fn)			\
 	{						\
-		.header	= hpp__header_ ## _name,	\
-		.width	= hpp__width_ ## _name,		\
-		.entry	= hpp__entry_ ## _name,		\
+		.name   = _name,			\
+		.header	= hpp__header_fn,		\
+		.width	= hpp__width_fn,		\
+		.entry	= hpp__entry_ ## _fn,		\
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
-		.sort	= hpp__sort_ ## _name,		\
+		.sort	= hpp__sort_ ## _fn,		\
 	}
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-	HPP__COLOR_PRINT_FNS(overhead),
-	HPP__COLOR_PRINT_FNS(overhead_sys),
-	HPP__COLOR_PRINT_FNS(overhead_us),
-	HPP__COLOR_PRINT_FNS(overhead_guest_sys),
-	HPP__COLOR_PRINT_FNS(overhead_guest_us),
-	HPP__COLOR_ACC_PRINT_FNS(overhead_acc),
-	HPP__PRINT_FNS(samples),
-	HPP__PRINT_FNS(period)
+	HPP__COLOR_PRINT_FNS("Overhead", overhead),
+	HPP__COLOR_PRINT_FNS("sys", overhead_sys),
+	HPP__COLOR_PRINT_FNS("usr", overhead_us),
+	HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys),
+	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
+	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
+	HPP__PRINT_FNS("Samples", samples),
+	HPP__PRINT_FNS("Period", period)
 };
 
 LIST_HEAD(perf_hpp__list);
@@ -444,14 +452,12 @@ void perf_hpp__init(void)
 	/*
 	 * If user specified field order, no need to setup default fields.
 	 */
-	if (field_order)
+	if (is_strict_order(field_order))
 		return;
 
 	if (symbol_conf.cumulate_callchain) {
 		perf_hpp__column_enable(PERF_HPP__OVERHEAD_ACC);
-
-		perf_hpp__format[PERF_HPP__OVERHEAD].header =
-						hpp__header_overhead_self;
+		perf_hpp__format[PERF_HPP__OVERHEAD].name = "Self";
 	}
 
 	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
@@ -513,11 +519,11 @@ void perf_hpp__column_disable(unsigned col)
 
 void perf_hpp__cancel_cumulate(void)
 {
-	if (field_order)
+	if (is_strict_order(field_order))
 		return;
 
 	perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
-	perf_hpp__format[PERF_HPP__OVERHEAD].header = hpp__header_overhead;
+	perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead";
 }
 
 void perf_hpp__setup_output_field(void)
@@ -622,3 +628,59 @@ unsigned int hists__sort_list_width(struct hists *hists)
 
 	return ret;
 }
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+	int idx;
+
+	if (perf_hpp__is_sort_entry(fmt))
+		return perf_hpp__reset_sort_width(fmt, hists);
+
+	for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
+		if (fmt == &perf_hpp__format[idx])
+			break;
+	}
+
+	if (idx == PERF_HPP__MAX_INDEX)
+		return;
+
+	switch (idx) {
+	case PERF_HPP__OVERHEAD:
+	case PERF_HPP__OVERHEAD_SYS:
+	case PERF_HPP__OVERHEAD_US:
+	case PERF_HPP__OVERHEAD_ACC:
+		fmt->len = 8;
+		break;
+
+	case PERF_HPP__OVERHEAD_GUEST_SYS:
+	case PERF_HPP__OVERHEAD_GUEST_US:
+		fmt->len = 9;
+		break;
+
+	case PERF_HPP__SAMPLES:
+	case PERF_HPP__PERIOD:
+		fmt->len = 12;
+		break;
+
+	default:
+		break;
+	}
+}
+
+void perf_hpp__set_user_width(const char *width_list_str)
+{
+	struct perf_hpp_fmt *fmt;
+	const char *ptr = width_list_str;
+
+	perf_hpp__for_each_format(fmt) {
+		char *p;
+
+		int len = strtol(ptr, &p, 10);
+		fmt->user_len = len;
+
+		if (*p == ',')
+			ptr = p + 1;
+		else
+			break;
+	}
+}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 40af0acb4fe9..15b451acbde6 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -395,10 +395,12 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	init_rem_hits();
 
-
 	perf_hpp__for_each_format(fmt)
 		perf_hpp__reset_width(fmt, hists);
 
+	if (symbol_conf.col_width_list_str)
+		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
 	if (!show_header)
 		goto print_entries;
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 809b4c50beae..36437527dbb3 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -232,9 +232,16 @@ static int mov__parse(struct ins_operands *ops)
 		return -1;
 
 	target = ++s;
+	comment = strchr(s, '#');
 
-	while (s[0] != '\0' && !isspace(s[0]))
-		++s;
+	if (comment != NULL)
+		s = comment - 1;
+	else
+		s = strchr(s, '\0') - 1;
+
+	while (s > target && isspace(s[0]))
+		--s;
+	s++;
 	prev = *s;
 	*s = '\0';
 
@@ -244,7 +251,6 @@ static int mov__parse(struct ins_operands *ops)
 	if (ops->target.raw == NULL)
 		goto out_free_source;
 
-	comment = strchr(s, '#');
 	if (comment == NULL)
 		return 0;
 
@@ -899,10 +905,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	struct kcore_extract kce;
 	bool delete_extract = false;
 
-	if (filename) {
-		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
-			 symbol_conf.symfs, filename);
-	}
+	if (filename)
+		symbol__join_symfs(symfs_filename, filename);
 
 	if (filename == NULL) {
 		if (dso->has_build_id) {
@@ -922,8 +926,7 @@ fallback:
 		 * DSO is the same as when 'perf record' ran.
 		 */
 		filename = (char *)dso->long_name;
-		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
-			 symbol_conf.symfs, filename);
+		symbol__join_symfs(symfs_filename, filename);
 		free_filename = false;
 	}
 
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 7b176dd02e1a..5cf9e1b5989d 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -22,6 +22,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *);
 extern int perf_default_config(const char *, const char *, void *);
 extern int perf_config(config_fn_t fn, void *);
 extern int perf_config_int(const char *, const char *);
+extern u64 perf_config_u64(const char *, const char *);
 extern int perf_config_bool(const char *, const char *);
 extern int config_error_nonbool(const char *);
 extern const char *perf_config_dirname(const char *, const char *);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 437ee09727e6..c84d3f8dcb75 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -25,77 +25,172 @@
 
 __thread struct callchain_cursor callchain_cursor;
 
-int
-parse_callchain_report_opt(const char *arg)
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+static int get_stack_size(const char *str, unsigned long *_size)
 {
-	char *tok, *tok2;
 	char *endptr;
+	unsigned long size;
+	unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
 
-	symbol_conf.use_callchain = true;
+	size = strtoul(str, &endptr, 0);
 
-	if (!arg)
+	do {
+		if (*endptr)
+			break;
+
+		size = round_up(size, sizeof(u64));
+		if (!size || size > max_size)
+			break;
+
+		*_size = size;
 		return 0;
 
-	tok = strtok((char *)arg, ",");
-	if (!tok)
-		return -1;
+	} while (0);
 
-	/* get the output mode */
-	if (!strncmp(tok, "graph", strlen(arg))) {
-		callchain_param.mode = CHAIN_GRAPH_ABS;
+	pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
+	       max_size, str);
+	return -1;
+}
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
 
-	} else if (!strncmp(tok, "flat", strlen(arg))) {
-		callchain_param.mode = CHAIN_FLAT;
-	} else if (!strncmp(tok, "fractal", strlen(arg))) {
-		callchain_param.mode = CHAIN_GRAPH_REL;
-	} else if (!strncmp(tok, "none", strlen(arg))) {
-		callchain_param.mode = CHAIN_NONE;
-		symbol_conf.use_callchain = false;
-		return 0;
-	} else {
-		return -1;
-	}
+int parse_callchain_record_opt(const char *arg)
+{
+	char *tok, *name, *saveptr = NULL;
+	char *buf;
+	int ret = -1;
+
+	/* We need buffer that we know we can write to. */
+	buf = malloc(strlen(arg) + 1);
+	if (!buf)
+		return -ENOMEM;
+
+	strcpy(buf, arg);
+
+	tok = strtok_r((char *)buf, ",", &saveptr);
+	name = tok ? : (char *)buf;
+
+	do {
+		/* Framepointer style */
+		if (!strncmp(name, "fp", sizeof("fp"))) {
+			if (!strtok_r(NULL, ",", &saveptr)) {
+				callchain_param.record_mode = CALLCHAIN_FP;
+				ret = 0;
+			} else
+				pr_err("callchain: No more arguments "
+				       "needed for -g fp\n");
+			break;
 
-	/* get the min percentage */
-	tok = strtok(NULL, ",");
-	if (!tok)
-		goto setup;
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+		/* Dwarf style */
+		} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
+			const unsigned long default_stack_dump_size = 8192;
 
-	callchain_param.min_percent = strtod(tok, &endptr);
-	if (tok == endptr)
-		return -1;
+			ret = 0;
+			callchain_param.record_mode = CALLCHAIN_DWARF;
+			callchain_param.dump_size = default_stack_dump_size;
 
-	/* get the print limit */
-	tok2 = strtok(NULL, ",");
-	if (!tok2)
-		goto setup;
+			tok = strtok_r(NULL, ",", &saveptr);
+			if (tok) {
+				unsigned long size = 0;
 
-	if (tok2[0] != 'c') {
-		callchain_param.print_limit = strtoul(tok2, &endptr, 0);
-		tok2 = strtok(NULL, ",");
-		if (!tok2)
-			goto setup;
+				ret = get_stack_size(tok, &size);
+				callchain_param.dump_size = size;
+			}
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
+		} else {
+			pr_err("callchain: Unknown --call-graph option "
+			       "value: %s\n", arg);
+			break;
+		}
+
+	} while (0);
+
+	free(buf);
+	return ret;
+}
+
+static int parse_callchain_mode(const char *value)
+{
+	if (!strncmp(value, "graph", strlen(value))) {
+		callchain_param.mode = CHAIN_GRAPH_ABS;
+		return 0;
+	}
+	if (!strncmp(value, "flat", strlen(value))) {
+		callchain_param.mode = CHAIN_FLAT;
+		return 0;
 	}
+	if (!strncmp(value, "fractal", strlen(value))) {
+		callchain_param.mode = CHAIN_GRAPH_REL;
+		return 0;
+	}
+	return -1;
+}
 
-	/* get the call chain order */
-	if (!strncmp(tok2, "caller", strlen("caller")))
+static int parse_callchain_order(const char *value)
+{
+	if (!strncmp(value, "caller", strlen(value))) {
 		callchain_param.order = ORDER_CALLER;
-	else if (!strncmp(tok2, "callee", strlen("callee")))
+		return 0;
+	}
+	if (!strncmp(value, "callee", strlen(value))) {
 		callchain_param.order = ORDER_CALLEE;
-	else
-		return -1;
+		return 0;
+	}
+	return -1;
+}
 
-	/* Get the sort key */
-	tok2 = strtok(NULL, ",");
-	if (!tok2)
-		goto setup;
-	if (!strncmp(tok2, "function", strlen("function")))
+static int parse_callchain_sort_key(const char *value)
+{
+	if (!strncmp(value, "function", strlen(value))) {
 		callchain_param.key = CCKEY_FUNCTION;
-	else if (!strncmp(tok2, "address", strlen("address")))
+		return 0;
+	}
+	if (!strncmp(value, "address", strlen(value))) {
 		callchain_param.key = CCKEY_ADDRESS;
-	else
-		return -1;
-setup:
+		return 0;
+	}
+	return -1;
+}
+
+int
+parse_callchain_report_opt(const char *arg)
+{
+	char *tok;
+	char *endptr;
+	bool minpcnt_set = false;
+
+	symbol_conf.use_callchain = true;
+
+	if (!arg)
+		return 0;
+
+	while ((tok = strtok((char *)arg, ",")) != NULL) {
+		if (!strncmp(tok, "none", strlen(tok))) {
+			callchain_param.mode = CHAIN_NONE;
+			symbol_conf.use_callchain = false;
+			return 0;
+		}
+
+		if (!parse_callchain_mode(tok) ||
+		    !parse_callchain_order(tok) ||
+		    !parse_callchain_sort_key(tok)) {
+			/* parsing ok - move on to the next */
+		} else if (!minpcnt_set) {
+			/* try to get the min percent */
+			callchain_param.min_percent = strtod(tok, &endptr);
+			if (tok == endptr)
+				return -1;
+			minpcnt_set = true;
+		} else {
+			/* try print limit at last */
+			callchain_param.print_limit = strtoul(tok, &endptr, 0);
+			if (tok == endptr)
+				return -1;
+		}
+
+		arg = NULL;
+	}
+
 	if (callchain_register_param(&callchain_param) < 0) {
 		pr_err("Can't register callchain params\n");
 		return -1;
@@ -103,6 +198,47 @@ setup:
 	return 0;
 }
 
+int perf_callchain_config(const char *var, const char *value)
+{
+	char *endptr;
+
+	if (prefixcmp(var, "call-graph."))
+		return 0;
+	var += sizeof("call-graph.") - 1;
+
+	if (!strcmp(var, "record-mode"))
+		return parse_callchain_record_opt(value);
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	if (!strcmp(var, "dump-size")) {
+		unsigned long size = 0;
+		int ret;
+
+		ret = get_stack_size(value, &size);
+		callchain_param.dump_size = size;
+
+		return ret;
+	}
+#endif
+	if (!strcmp(var, "print-type"))
+		return parse_callchain_mode(value);
+	if (!strcmp(var, "order"))
+		return parse_callchain_order(value);
+	if (!strcmp(var, "sort-key"))
+		return parse_callchain_sort_key(value);
+	if (!strcmp(var, "threshold")) {
+		callchain_param.min_percent = strtod(value, &endptr);
+		if (value == endptr)
+			return -1;
+	}
+	if (!strcmp(var, "print-limit")) {
+		callchain_param.print_limit = strtod(value, &endptr);
+		if (value == endptr)
+			return -1;
+	}
+
+	return 0;
+}
+
 static void
 rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
 		    enum chain_mode mode)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index da43619d6173..2a1f5a46543a 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -54,6 +54,9 @@ enum chain_key {
 };
 
 struct callchain_param {
+	bool			enabled;
+	enum perf_call_graph_mode record_mode;
+	u32			dump_size;
 	enum chain_mode 	mode;
 	u32			print_limit;
 	double			min_percent;
@@ -154,7 +157,6 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
 struct option;
 struct hist_entry;
 
-int record_parse_callchain(const char *arg, struct record_opts *opts);
 int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
 int record_callchain_opt(const struct option *opt, const char *arg, int unset);
 
@@ -166,7 +168,9 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 			bool hide_unresolved);
 
 extern const char record_callchain_help[];
+int parse_callchain_record_opt(const char *arg);
 int parse_callchain_report_opt(const char *arg);
+int perf_callchain_config(const char *var, const char *value);
 
 static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
 					     struct callchain_cursor *src)
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index c5d05ec17220..47b78b3f0325 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -1,7 +1,9 @@
+#include <sched.h>
 #include "util.h"
 #include "../perf.h"
 #include "cloexec.h"
 #include "asm/bug.h"
+#include "debug.h"
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
 
@@ -9,15 +11,30 @@ static int perf_flag_probe(void)
 {
 	/* use 'safest' configuration as used in perf_evsel__fallback() */
 	struct perf_event_attr attr = {
-		.type = PERF_COUNT_SW_CPU_CLOCK,
+		.type = PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_CPU_CLOCK,
+		.exclude_kernel = 1,
 	};
 	int fd;
 	int err;
+	int cpu;
+	pid_t pid = -1;
+	char sbuf[STRERR_BUFSIZE];
 
-	/* check cloexec flag */
-	fd = sys_perf_event_open(&attr, 0, -1, -1,
-				 PERF_FLAG_FD_CLOEXEC);
+	cpu = sched_getcpu();
+	if (cpu < 0)
+		cpu = 0;
+
+	while (1) {
+		/* check cloexec flag */
+		fd = sys_perf_event_open(&attr, pid, cpu, -1,
+					 PERF_FLAG_FD_CLOEXEC);
+		if (fd < 0 && pid == -1 && errno == EACCES) {
+			pid = 0;
+			continue;
+		}
+		break;
+	}
 	err = errno;
 
 	if (fd >= 0) {
@@ -25,17 +42,17 @@ static int perf_flag_probe(void)
 		return 1;
 	}
 
-	WARN_ONCE(err != EINVAL,
+	WARN_ONCE(err != EINVAL && err != EBUSY,
 		  "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n",
-		  err, strerror(err));
+		  err, strerror_r(err, sbuf, sizeof(sbuf)));
 
 	/* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
-	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
 	err = errno;
 
-	if (WARN_ONCE(fd < 0,
+	if (WARN_ONCE(fd < 0 && err != EBUSY,
 		      "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
-		      err, strerror(err)))
+		      err, strerror_r(err, sbuf, sizeof(sbuf))))
 		return -1;
 
 	close(fd);
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 87b8672eb413..f4654183d391 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -335,3 +335,19 @@ int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...)
 	va_end(args);
 	return value_color_snprintf(bf, size, fmt, percent);
 }
+
+int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...)
+{
+	va_list args;
+	int len;
+	double percent;
+	const char *color;
+
+	va_start(args, fmt);
+	len = va_arg(args, int);
+	percent = va_arg(args, double);
+	va_end(args);
+
+	color = get_percent_color(percent);
+	return color_snprintf(bf, size, color, fmt, len, percent);
+}
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 7ff30a62a132..0a594b8a0c26 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -41,6 +41,7 @@ int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
 int value_color_snprintf(char *bf, size_t size, const char *fmt, double value);
 int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
+int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
 
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index f9e777629e21..b2bb59df65e1 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -74,7 +74,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
 	return new;
 }
 
-struct comm *comm__new(const char *str, u64 timestamp)
+struct comm *comm__new(const char *str, u64 timestamp, bool exec)
 {
 	struct comm *comm = zalloc(sizeof(*comm));
 
@@ -82,6 +82,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
 		return NULL;
 
 	comm->start = timestamp;
+	comm->exec = exec;
 
 	comm->comm_str = comm_str__findnew(str, &comm_str_root);
 	if (!comm->comm_str) {
@@ -94,7 +95,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
 	return comm;
 }
 
-int comm__override(struct comm *comm, const char *str, u64 timestamp)
+int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec)
 {
 	struct comm_str *new, *old = comm->comm_str;
 
@@ -106,6 +107,8 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp)
 	comm_str__put(old);
 	comm->comm_str = new;
 	comm->start = timestamp;
+	if (exec)
+		comm->exec = true;
 
 	return 0;
 }
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index fac5bd51befc..51c10ab257f8 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -11,11 +11,13 @@ struct comm {
 	struct comm_str *comm_str;
 	u64 start;
 	struct list_head list;
+	bool exec;
 };
 
 void comm__free(struct comm *comm);
-struct comm *comm__new(const char *str, u64 timestamp);
+struct comm *comm__new(const char *str, u64 timestamp, bool exec);
 const char *comm__str(const struct comm *comm);
-int comm__override(struct comm *comm, const char *str, u64 timestamp);
+int comm__override(struct comm *comm, const char *str, u64 timestamp,
+		   bool exec);
 
 #endif  /* __PERF_COMM_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 1e5e2e5af6b1..57ff826f150b 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -222,7 +222,8 @@ static int perf_parse_file(config_fn_t fn, void *data)
 	const unsigned char *bomptr = utf8_bom;
 
 	for (;;) {
-		int c = get_next_char();
+		int line, c = get_next_char();
+
 		if (bomptr && *bomptr) {
 			/* We are at the file beginning; skip UTF8-encoded BOM
 			 * if present. Sane editors won't put this in on their
@@ -261,8 +262,16 @@ static int perf_parse_file(config_fn_t fn, void *data)
 		if (!isalpha(c))
 			break;
 		var[baselen] = tolower(c);
-		if (get_value(fn, data, var, baselen+1) < 0)
+
+		/*
+		 * The get_value function might or might not reach the '\n',
+		 * so saving the current line number for error reporting.
+		 */
+		line = config_linenr;
+		if (get_value(fn, data, var, baselen+1) < 0) {
+			config_linenr = line;
 			break;
+		}
 	}
 	die("bad config file line %d in %s", config_linenr, config_file_name);
 }
@@ -286,6 +295,21 @@ static int parse_unit_factor(const char *end, unsigned long *val)
 	return 0;
 }
 
+static int perf_parse_llong(const char *value, long long *ret)
+{
+	if (value && *value) {
+		char *end;
+		long long val = strtoll(value, &end, 0);
+		unsigned long factor = 1;
+
+		if (!parse_unit_factor(end, &factor))
+			return 0;
+		*ret = val * factor;
+		return 1;
+	}
+	return 0;
+}
+
 static int perf_parse_long(const char *value, long *ret)
 {
 	if (value && *value) {
@@ -307,6 +331,15 @@ static void die_bad_config(const char *name)
 	die("bad config value for '%s'", name);
 }
 
+u64 perf_config_u64(const char *name, const char *value)
+{
+	long long ret = 0;
+
+	if (!perf_parse_llong(value, &ret))
+		die_bad_config(name);
+	return (u64) ret;
+}
+
 int perf_config_int(const char *name, const char *value)
 {
 	long ret = 0;
@@ -372,6 +405,9 @@ int perf_default_config(const char *var, const char *value,
 	if (!prefixcmp(var, "ui."))
 		return perf_ui_config(var, value);
 
+	if (!prefixcmp(var, "call-graph."))
+		return perf_callchain_config(var, value);
+
 	/* Add other config variables here. */
 	return 0;
 }
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 29d720cf5844..1921942fc2e0 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -50,12 +50,14 @@ static int open_file_read(struct perf_data_file *file)
 {
 	struct stat st;
 	int fd;
+	char sbuf[STRERR_BUFSIZE];
 
 	fd = open(file->path, O_RDONLY);
 	if (fd < 0) {
 		int err = errno;
 
-		pr_err("failed to open %s: %s", file->path, strerror(err));
+		pr_err("failed to open %s: %s", file->path,
+			strerror_r(err, sbuf, sizeof(sbuf)));
 		if (err == ENOENT && !strcmp(file->path, "perf.data"))
 			pr_err("  (try 'perf record' first)");
 		pr_err("\n");
@@ -88,6 +90,7 @@ static int open_file_read(struct perf_data_file *file)
 static int open_file_write(struct perf_data_file *file)
 {
 	int fd;
+	char sbuf[STRERR_BUFSIZE];
 
 	if (check_backup(file))
 		return -1;
@@ -95,7 +98,8 @@ static int open_file_write(struct perf_data_file *file)
 	fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
 
 	if (fd < 0)
-		pr_err("failed to open %s : %s\n", file->path, strerror(errno));
+		pr_err("failed to open %s : %s\n", file->path,
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 
 	return fd;
 }
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 71d419362634..ba357f3226c6 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -13,8 +13,12 @@
 #include "util.h"
 #include "target.h"
 
+#define NSECS_PER_SEC  1000000000ULL
+#define NSECS_PER_USEC 1000ULL
+
 int verbose;
 bool dump_trace = false, quiet = false;
+int debug_ordered_events;
 
 static int _eprintf(int level, int var, const char *fmt, va_list args)
 {
@@ -42,6 +46,35 @@ int eprintf(int level, int var, const char *fmt, ...)
 	return ret;
 }
 
+static int __eprintf_time(u64 t, const char *fmt, va_list args)
+{
+	int ret = 0;
+	u64 secs, usecs, nsecs = t;
+
+	secs   = nsecs / NSECS_PER_SEC;
+	nsecs -= secs  * NSECS_PER_SEC;
+	usecs  = nsecs / NSECS_PER_USEC;
+
+	ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ",
+		      secs, usecs);
+	ret += vfprintf(stderr, fmt, args);
+	return ret;
+}
+
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...)
+{
+	int ret = 0;
+	va_list args;
+
+	if (var >= level) {
+		va_start(args, fmt);
+		ret = __eprintf_time(t, fmt, args);
+		va_end(args);
+	}
+
+	return ret;
+}
+
 /*
  * Overloading libtraceevent standard info print
  * function, display with -v in perf.
@@ -110,7 +143,8 @@ static struct debug_variable {
 	const char *name;
 	int *ptr;
 } debug_variables[] = {
-	{ .name = "verbose", .ptr = &verbose },
+	{ .name = "verbose",		.ptr = &verbose },
+	{ .name = "ordered-events",	.ptr = &debug_ordered_events},
 	{ .name = NULL, }
 };
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 89fb6b0f7ab2..be264d6f3b30 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -3,6 +3,7 @@
 #define __PERF_DEBUG_H
 
 #include <stdbool.h>
+#include <string.h>
 #include "event.h"
 #include "../ui/helpline.h"
 #include "../ui/progress.h"
@@ -10,6 +11,7 @@
 
 extern int verbose;
 extern bool quiet, dump_trace;
+extern int debug_ordered_events;
 
 #ifndef pr_fmt
 #define pr_fmt(fmt) fmt
@@ -29,6 +31,14 @@ extern bool quiet, dump_trace;
 #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
 
+#define pr_time_N(n, var, t, fmt, ...) \
+	eprintf_time(n, var, t, fmt, ##__VA_ARGS__)
+
+#define pr_oe_time(t, fmt, ...)  pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+
+#define STRERR_BUFSIZE	128	/* For the buffer size of strerror_r */
+
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
 
@@ -38,6 +48,7 @@ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 void pr_stat(const char *fmt, ...);
 
 int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4)));
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5)));
 
 int perf_debug_option(const char *str);
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 90d02c661dd4..0247acfdfaca 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -37,6 +37,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 {
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 	int ret = 0;
+	size_t len;
 
 	switch (type) {
 	case DSO_BINARY_TYPE__DEBUGLINK: {
@@ -60,26 +61,25 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		break;
 
 	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
-		snprintf(filename, size, "%s/usr/lib/debug%s.debug",
-			 symbol_conf.symfs, dso->long_name);
+		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+		snprintf(filename + len, size - len, "%s.debug", dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
-		snprintf(filename, size, "%s/usr/lib/debug%s",
-			 symbol_conf.symfs, dso->long_name);
+		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+		snprintf(filename + len, size - len, "%s", dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
 	{
 		const char *last_slash;
-		size_t len;
 		size_t dir_size;
 
 		last_slash = dso->long_name + dso->long_name_len;
 		while (last_slash != dso->long_name && *last_slash != '/')
 			last_slash--;
 
-		len = scnprintf(filename, size, "%s", symbol_conf.symfs);
+		len = __symbol__join_symfs(filename, size, "");
 		dir_size = last_slash - dso->long_name + 2;
 		if (dir_size > (size - len)) {
 			ret = -1;
@@ -100,26 +100,24 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		build_id__sprintf(dso->build_id,
 				  sizeof(dso->build_id),
 				  build_id_hex);
-		snprintf(filename, size,
-			 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
-			 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
+		len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/");
+		snprintf(filename + len, size - len, "%.2s/%s.debug",
+			 build_id_hex, build_id_hex + 2);
 		break;
 
 	case DSO_BINARY_TYPE__VMLINUX:
 	case DSO_BINARY_TYPE__GUEST_VMLINUX:
 	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
-		snprintf(filename, size, "%s%s",
-			 symbol_conf.symfs, dso->long_name);
+		__symbol__join_symfs(filename, size, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
-		snprintf(filename, size, "%s%s%s", symbol_conf.symfs,
-			 root_dir, dso->long_name);
+		path__join3(filename, size, symbol_conf.symfs,
+			    root_dir, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
-		snprintf(filename, size, "%s%s", symbol_conf.symfs,
-			 dso->long_name);
+		__symbol__join_symfs(filename, size, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__KCORE:
@@ -164,13 +162,15 @@ static void close_first_dso(void);
 static int do_open(char *name)
 {
 	int fd;
+	char sbuf[STRERR_BUFSIZE];
 
 	do {
 		fd = open(name, O_RDONLY);
 		if (fd >= 0)
 			return fd;
 
-		pr_debug("dso open failed, mmap: %s\n", strerror(errno));
+		pr_debug("dso open failed, mmap: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		if (!dso__data_open_cnt || errno != EMFILE)
 			break;
 
@@ -532,10 +532,12 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 static int data_file_size(struct dso *dso)
 {
 	struct stat st;
+	char sbuf[STRERR_BUFSIZE];
 
 	if (!dso->data.file_size) {
 		if (fstat(dso->data.fd, &st)) {
-			pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+			pr_err("dso mmap failed, fstat: %s\n",
+				strerror_r(errno, sbuf, sizeof(sbuf)));
 			return -1;
 		}
 		dso->data.file_size = st.st_size;
@@ -651,6 +653,65 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
 	return dso;
 }
 
+/*
+ * Find a matching entry and/or link current entry to RB tree.
+ * Either one of the dso or name parameter must be non-NULL or the
+ * function will not work.
+ */
+static struct dso *dso__findlink_by_longname(struct rb_root *root,
+					     struct dso *dso, const char *name)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node  *parent = NULL;
+
+	if (!name)
+		name = dso->long_name;
+	/*
+	 * Find node with the matching name
+	 */
+	while (*p) {
+		struct dso *this = rb_entry(*p, struct dso, rb_node);
+		int rc = strcmp(name, this->long_name);
+
+		parent = *p;
+		if (rc == 0) {
+			/*
+			 * In case the new DSO is a duplicate of an existing
+			 * one, print an one-time warning & put the new entry
+			 * at the end of the list of duplicates.
+			 */
+			if (!dso || (dso == this))
+				return this;	/* Find matching dso */
+			/*
+			 * The core kernel DSOs may have duplicated long name.
+			 * In this case, the short name should be different.
+			 * Comparing the short names to differentiate the DSOs.
+			 */
+			rc = strcmp(dso->short_name, this->short_name);
+			if (rc == 0) {
+				pr_err("Duplicated dso name: %s\n", name);
+				return NULL;
+			}
+		}
+		if (rc < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+	if (dso) {
+		/* Add new node and rebalance tree */
+		rb_link_node(&dso->rb_node, parent, p);
+		rb_insert_color(&dso->rb_node, root);
+	}
+	return NULL;
+}
+
+static inline struct dso *
+dso__find_by_longname(const struct rb_root *root, const char *name)
+{
+	return dso__findlink_by_longname((struct rb_root *)root, NULL, name);
+}
+
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
 	if (name == NULL)
@@ -753,6 +814,7 @@ struct dso *dso__new(const char *name)
 		dso->a2l_fails = 1;
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
+		RB_CLEAR_NODE(&dso->rb_node);
 		INIT_LIST_HEAD(&dso->node);
 		INIT_LIST_HEAD(&dso->data.open_entry);
 	}
@@ -763,6 +825,10 @@ struct dso *dso__new(const char *name)
 void dso__delete(struct dso *dso)
 {
 	int i;
+
+	if (!RB_EMPTY_NODE(&dso->rb_node))
+		pr_err("DSO %s is still in rbtree when being deleted!\n",
+		       dso->long_name);
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		symbols__delete(&dso->symbols[i]);
 
@@ -849,35 +915,34 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 	return have_build_id;
 }
 
-void dsos__add(struct list_head *head, struct dso *dso)
+void dsos__add(struct dsos *dsos, struct dso *dso)
 {
-	list_add_tail(&dso->node, head);
+	list_add_tail(&dso->node, &dsos->head);
+	dso__findlink_by_longname(&dsos->root, dso, NULL);
 }
 
-struct dso *dsos__find(const struct list_head *head, const char *name, bool cmp_short)
+struct dso *dsos__find(const struct dsos *dsos, const char *name,
+		       bool cmp_short)
 {
 	struct dso *pos;
 
 	if (cmp_short) {
-		list_for_each_entry(pos, head, node)
+		list_for_each_entry(pos, &dsos->head, node)
 			if (strcmp(pos->short_name, name) == 0)
 				return pos;
 		return NULL;
 	}
-	list_for_each_entry(pos, head, node)
-		if (strcmp(pos->long_name, name) == 0)
-			return pos;
-	return NULL;
+	return dso__find_by_longname(&dsos->root, name);
 }
 
-struct dso *__dsos__findnew(struct list_head *head, const char *name)
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
 {
-	struct dso *dso = dsos__find(head, name, false);
+	struct dso *dso = dsos__find(dsos, name, false);
 
 	if (!dso) {
 		dso = dso__new(name);
 		if (dso != NULL) {
-			dsos__add(head, dso);
+			dsos__add(dsos, dso);
 			dso__set_basename(dso);
 		}
 	}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 5e463c0964d4..acb651acc7fd 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -90,8 +90,18 @@ struct dso_cache {
 	char data[0];
 };
 
+/*
+ * DSOs are put into both a list for fast iteration and rbtree for fast
+ * long name lookup.
+ */
+struct dsos {
+	struct list_head head;
+	struct rb_root	 root;	/* rbtree root sorted by long name */
+};
+
 struct dso {
 	struct list_head node;
+	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	void		 *a2l;
@@ -224,10 +234,10 @@ struct map *dso__new_map(const char *name);
 struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
 				const char *short_name, int dso_type);
 
-void dsos__add(struct list_head *head, struct dso *dso);
-struct dso *dsos__find(const struct list_head *head, const char *name,
+void dsos__add(struct dsos *dsos, struct dso *dso);
+struct dso *dsos__find(const struct dsos *dsos, const char *name,
 		       bool cmp_short);
-struct dso *__dsos__findnew(struct list_head *head, const char *name);
+struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1398c83d896d..4af6b279e34a 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -558,13 +558,17 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	struct map *map;
 	struct kmap *kmap;
 	int err;
+	union perf_event *event;
+
+	if (machine->vmlinux_maps[0] == NULL)
+		return -1;
+
 	/*
 	 * We should get this from /sys/kernel/sections/.text, but till that is
 	 * available use this, and after it is use this as a fallback for older
 	 * kernels.
 	 */
-	union perf_event *event = zalloc((sizeof(event->mmap) +
-					  machine->id_hdr_size));
+	event = zalloc((sizeof(event->mmap) + machine->id_hdr_size));
 	if (event == NULL) {
 		pr_debug("Not enough memory synthesizing mmap event "
 			 "for kernel modules\n");
@@ -784,9 +788,9 @@ try_again:
 		 * "[vdso]" dso, but for now lets use the old trick of looking
 		 * in the whole kernel symbol list.
 		 */
-		if ((long long)al->addr < 0 &&
-		    cpumode == PERF_RECORD_MISC_USER &&
-		    machine && mg != &machine->kmaps) {
+		if (cpumode == PERF_RECORD_MISC_USER && machine &&
+		    mg != &machine->kmaps &&
+		    machine__kernel_ip(machine, al->addr)) {
 			mg = &machine->kmaps;
 			load_map = true;
 			goto try_again;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 94d6976180da..7eb7107731ec 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -156,6 +156,8 @@ struct perf_sample {
 	u32 cpu;
 	u32 raw_size;
 	u64 data_src;
+	u32 flags;
+	u16 insn_len;
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 814e954c1318..3cebc9a8d52e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -25,6 +25,9 @@
 #include <linux/bitops.h>
 #include <linux/hash.h>
 
+static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
+static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
+
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
 
@@ -37,6 +40,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
 		INIT_HLIST_HEAD(&evlist->heads[i]);
 	INIT_LIST_HEAD(&evlist->entries);
 	perf_evlist__set_maps(evlist, cpus, threads);
+	fdarray__init(&evlist->pollfd, 64);
 	evlist->workload.pid = -1;
 }
 
@@ -102,7 +106,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
 	zfree(&evlist->mmap);
-	zfree(&evlist->pollfd);
+	fdarray__exit(&evlist->pollfd);
 }
 
 void perf_evlist__delete(struct perf_evlist *evlist)
@@ -122,6 +126,7 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
 	list_add_tail(&entry->node, &evlist->entries);
 	entry->idx = evlist->nr_entries;
+	entry->tracking = !entry->idx;
 
 	if (!evlist->nr_entries++)
 		perf_evlist__set_id_pos(evlist);
@@ -265,17 +270,27 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist,
 	return 0;
 }
 
+static int perf_evlist__nr_threads(struct perf_evlist *evlist,
+				   struct perf_evsel *evsel)
+{
+	if (evsel->system_wide)
+		return 1;
+	else
+		return thread_map__nr(evlist->threads);
+}
+
 void perf_evlist__disable(struct perf_evlist *evlist)
 {
 	int cpu, thread;
 	struct perf_evsel *pos;
 	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = thread_map__nr(evlist->threads);
+	int nr_threads;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		evlist__for_each(evlist, pos) {
 			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 				continue;
+			nr_threads = perf_evlist__nr_threads(evlist, pos);
 			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_DISABLE, 0);
@@ -288,12 +303,13 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 	int cpu, thread;
 	struct perf_evsel *pos;
 	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = thread_map__nr(evlist->threads);
+	int nr_threads;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		evlist__for_each(evlist, pos) {
 			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 				continue;
+			nr_threads = perf_evlist__nr_threads(evlist, pos);
 			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_ENABLE, 0);
@@ -305,12 +321,14 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel)
 {
 	int cpu, thread, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
 	if (!evsel->fd)
 		return 0;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-		for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		for (thread = 0; thread < nr_threads; thread++) {
 			err = ioctl(FD(evsel, cpu, thread),
 				    PERF_EVENT_IOC_DISABLE, 0);
 			if (err)
@@ -324,12 +342,14 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
 			      struct perf_evsel *evsel)
 {
 	int cpu, thread, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
 	if (!evsel->fd)
 		return -EINVAL;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-		for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		for (thread = 0; thread < nr_threads; thread++) {
 			err = ioctl(FD(evsel, cpu, thread),
 				    PERF_EVENT_IOC_ENABLE, 0);
 			if (err)
@@ -339,21 +359,111 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
 	return 0;
 }
 
-static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
+static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist,
+					 struct perf_evsel *evsel, int cpu)
+{
+	int thread, err;
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
+
+	if (!evsel->fd)
+		return -EINVAL;
+
+	for (thread = 0; thread < nr_threads; thread++) {
+		err = ioctl(FD(evsel, cpu, thread),
+			    PERF_EVENT_IOC_ENABLE, 0);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int perf_evlist__enable_event_thread(struct perf_evlist *evlist,
+					    struct perf_evsel *evsel,
+					    int thread)
+{
+	int cpu, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+
+	if (!evsel->fd)
+		return -EINVAL;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+				  struct perf_evsel *evsel, int idx)
+{
+	bool per_cpu_mmaps = !cpu_map__empty(evlist->cpus);
+
+	if (per_cpu_mmaps)
+		return perf_evlist__enable_event_cpu(evlist, evsel, idx);
+	else
+		return perf_evlist__enable_event_thread(evlist, evsel, idx);
+}
+
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
 	int nr_cpus = cpu_map__nr(evlist->cpus);
 	int nr_threads = thread_map__nr(evlist->threads);
-	int nfds = nr_cpus * nr_threads * evlist->nr_entries;
-	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
-	return evlist->pollfd != NULL ? 0 : -ENOMEM;
+	int nfds = 0;
+	struct perf_evsel *evsel;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		if (evsel->system_wide)
+			nfds += nr_cpus;
+		else
+			nfds += nr_cpus * nr_threads;
+	}
+
+	if (fdarray__available_entries(&evlist->pollfd) < nfds &&
+	    fdarray__grow(&evlist->pollfd, nfds) < 0)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx)
+{
+	int pos = fdarray__add(&evlist->pollfd, fd, POLLIN | POLLERR | POLLHUP);
+	/*
+	 * Save the idx so that when we filter out fds POLLHUP'ed we can
+	 * close the associated evlist->mmap[] entry.
+	 */
+	if (pos >= 0) {
+		evlist->pollfd.priv[pos].idx = idx;
+
+		fcntl(fd, F_SETFL, O_NONBLOCK);
+	}
+
+	return pos;
+}
+
+int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+{
+	return __perf_evlist__add_pollfd(evlist, fd, -1);
+}
+
+static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd)
+{
+	struct perf_evlist *evlist = container_of(fda, struct perf_evlist, pollfd);
+
+	perf_evlist__mmap_put(evlist, fda->priv[fd].idx);
+}
+
+int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask)
+{
+	return fdarray__filter(&evlist->pollfd, revents_and_mask,
+			       perf_evlist__munmap_filtered);
 }
 
-void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd)
+int perf_evlist__poll(struct perf_evlist *evlist, int timeout)
 {
-	fcntl(fd, F_SETFL, O_NONBLOCK);
-	evlist->pollfd[evlist->nr_fds].fd = fd;
-	evlist->pollfd[evlist->nr_fds].events = POLLIN;
-	evlist->nr_fds++;
+	return fdarray__poll(&evlist->pollfd, timeout);
 }
 
 static void perf_evlist__id_hash(struct perf_evlist *evlist,
@@ -566,14 +676,36 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 	return event;
 }
 
+static bool perf_mmap__empty(struct perf_mmap *md)
+{
+	return perf_mmap__read_head(md) != md->prev;
+}
+
+static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
+{
+	++evlist->mmap[idx].refcnt;
+}
+
+static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
+{
+	BUG_ON(evlist->mmap[idx].refcnt == 0);
+
+	if (--evlist->mmap[idx].refcnt == 0)
+		__perf_evlist__munmap(evlist, idx);
+}
+
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
+	struct perf_mmap *md = &evlist->mmap[idx];
+
 	if (!evlist->overwrite) {
-		struct perf_mmap *md = &evlist->mmap[idx];
 		unsigned int old = md->prev;
 
 		perf_mmap__write_tail(md, old);
 	}
+
+	if (md->refcnt == 1 && perf_mmap__empty(md))
+		perf_evlist__mmap_put(evlist, idx);
 }
 
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
@@ -581,6 +713,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 	if (evlist->mmap[idx].base != NULL) {
 		munmap(evlist->mmap[idx].base, evlist->mmap_len);
 		evlist->mmap[idx].base = NULL;
+		evlist->mmap[idx].refcnt = 0;
 	}
 }
 
@@ -614,6 +747,20 @@ struct mmap_params {
 static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 			       struct mmap_params *mp, int fd)
 {
+	/*
+	 * The last one will be done at perf_evlist__mmap_consume(), so that we
+	 * make sure we don't prevent tools from consuming every last event in
+	 * the ring buffer.
+	 *
+	 * I.e. we can get the POLLHUP meaning that the fd doesn't exist
+	 * anymore, but the last events for it are still in the ring buffer,
+	 * waiting to be consumed.
+	 *
+	 * Tools can chose to ignore this at their own discretion, but the
+	 * evlist layer can't just drop it when filtering events in
+	 * perf_evlist__filter_pollfd().
+	 */
+	evlist->mmap[idx].refcnt = 2;
 	evlist->mmap[idx].prev = 0;
 	evlist->mmap[idx].mask = mp->mask;
 	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
@@ -625,7 +772,6 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 		return -1;
 	}
 
-	perf_evlist__add_pollfd(evlist, fd);
 	return 0;
 }
 
@@ -636,7 +782,12 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 	struct perf_evsel *evsel;
 
 	evlist__for_each(evlist, evsel) {
-		int fd = FD(evsel, cpu, thread);
+		int fd;
+
+		if (evsel->system_wide && thread)
+			continue;
+
+		fd = FD(evsel, cpu, thread);
 
 		if (*output == -1) {
 			*output = fd;
@@ -645,6 +796,13 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 		} else {
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
 				return -1;
+
+			perf_evlist__mmap_get(evlist, idx);
+		}
+
+		if (__perf_evlist__add_pollfd(evlist, fd, idx) < 0) {
+			perf_evlist__mmap_put(evlist, idx);
+			return -1;
 		}
 
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
@@ -804,7 +962,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
 		return -ENOMEM;
 
-	if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
+	if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0)
 		return -ENOMEM;
 
 	evlist->overwrite = overwrite;
@@ -1061,6 +1219,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 	}
 
 	if (!evlist->workload.pid) {
+		int ret;
+
 		if (pipe_output)
 			dup2(2, 1);
 
@@ -1078,8 +1238,22 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 		/*
 		 * Wait until the parent tells us to go.
 		 */
-		if (read(go_pipe[0], &bf, 1) == -1)
-			perror("unable to read pipe");
+		ret = read(go_pipe[0], &bf, 1);
+		/*
+		 * The parent will ask for the execvp() to be performed by
+		 * writing exactly one byte, in workload.cork_fd, usually via
+		 * perf_evlist__start_workload().
+		 *
+		 * For cancelling the workload without actuallin running it,
+		 * the parent will just close workload.cork_fd, without writing
+		 * anything, i.e. read will return zero and we just exit()
+		 * here.
+		 */
+		if (ret != 1) {
+			if (ret == -1)
+				perror("unable to read pipe");
+			exit(ret);
+		}
 
 		execvp(argv[0], (char **)argv);
 
@@ -1202,7 +1376,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 			       int err, char *buf, size_t size)
 {
 	int printed, value;
-	char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+	char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
 
 	switch (err) {
 	case EACCES:
@@ -1250,3 +1424,19 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 
 	list_splice(&move, &evlist->entries);
 }
+
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+				     struct perf_evsel *tracking_evsel)
+{
+	struct perf_evsel *evsel;
+
+	if (tracking_evsel->tracking)
+		return;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel != tracking_evsel)
+			evsel->tracking = false;
+	}
+
+	tracking_evsel->tracking = true;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f5173cd63693..bd312b01e876 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -2,6 +2,7 @@
 #define __PERF_EVLIST_H 1
 
 #include <linux/list.h>
+#include <api/fd/array.h>
 #include <stdio.h>
 #include "../perf.h"
 #include "event.h"
@@ -17,9 +18,15 @@ struct record_opts;
 #define PERF_EVLIST__HLIST_BITS 8
 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
 
+/**
+ * struct perf_mmap - perf's ring buffer mmap details
+ *
+ * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
+ */
 struct perf_mmap {
 	void		 *base;
 	int		 mask;
+	int		 refcnt;
 	unsigned int	 prev;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE];
 };
@@ -29,7 +36,6 @@ struct perf_evlist {
 	struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
 	int		 nr_entries;
 	int		 nr_groups;
-	int		 nr_fds;
 	int		 nr_mmaps;
 	size_t		 mmap_len;
 	int		 id_pos;
@@ -40,8 +46,8 @@ struct perf_evlist {
 		pid_t	pid;
 	} workload;
 	bool		 overwrite;
+	struct fdarray	 pollfd;
 	struct perf_mmap *mmap;
-	struct pollfd	 *pollfd;
 	struct thread_map *threads;
 	struct cpu_map	  *cpus;
 	struct perf_evsel *selected;
@@ -82,7 +88,11 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
 			 int cpu, int thread, u64 id);
 
-void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
+int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
+int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask);
+
+int perf_evlist__poll(struct perf_evlist *evlist, int timeout);
 
 struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
 
@@ -122,6 +132,8 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
 int perf_evlist__enable_event(struct perf_evlist *evlist,
 			      struct perf_evsel *evsel);
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+				  struct perf_evsel *evsel, int idx);
 
 void perf_evlist__set_selected(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
@@ -262,4 +274,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 #define evlist__for_each_safe(evlist, tmp, evsel) \
 	__evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
 
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+				     struct perf_evsel *tracking_evsel);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 21a373ebea22..e0868a901c4a 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -162,6 +162,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
 	evsel->idx	   = idx;
+	evsel->tracking	   = !idx;
 	evsel->attr	   = *attr;
 	evsel->leader	   = evsel;
 	evsel->unit	   = "";
@@ -502,20 +503,19 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
 }
 
 static void
-perf_evsel__config_callgraph(struct perf_evsel *evsel,
-			     struct record_opts *opts)
+perf_evsel__config_callgraph(struct perf_evsel *evsel)
 {
 	bool function = perf_evsel__is_function_event(evsel);
 	struct perf_event_attr *attr = &evsel->attr;
 
 	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
 
-	if (opts->call_graph == CALLCHAIN_DWARF) {
+	if (callchain_param.record_mode == CALLCHAIN_DWARF) {
 		if (!function) {
 			perf_evsel__set_sample_bit(evsel, REGS_USER);
 			perf_evsel__set_sample_bit(evsel, STACK_USER);
 			attr->sample_regs_user = PERF_REGS_MASK;
-			attr->sample_stack_user = opts->stack_dump_size;
+			attr->sample_stack_user = callchain_param.dump_size;
 			attr->exclude_callchain_user = 1;
 		} else {
 			pr_info("Cannot use DWARF unwind for function trace event,"
@@ -561,7 +561,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 {
 	struct perf_evsel *leader = evsel->leader;
 	struct perf_event_attr *attr = &evsel->attr;
-	int track = !evsel->idx; /* only the first counter needs these */
+	int track = evsel->tracking;
 	bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
 	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
@@ -624,8 +624,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		attr->mmap_data = track;
 	}
 
-	if (opts->call_graph_enabled && !evsel->no_aux_samples)
-		perf_evsel__config_callgraph(evsel, opts);
+	if (callchain_param.enabled && !evsel->no_aux_samples)
+		perf_evsel__config_callgraph(evsel);
 
 	if (target__has_cpu(&opts->target))
 		perf_evsel__set_sample_bit(evsel, CPU);
@@ -633,9 +633,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (opts->period)
 		perf_evsel__set_sample_bit(evsel, PERIOD);
 
-	if (!perf_missing_features.sample_id_all &&
-	    (opts->sample_time || !opts->no_inherit ||
-	     target__has_cpu(&opts->target) || per_cpu))
+	/*
+	 * When the user explicitely disabled time don't force it here.
+	 */
+	if (opts->sample_time &&
+	    (!perf_missing_features.sample_id_all &&
+	    (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu)))
 		perf_evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples && !evsel->no_aux_samples) {
@@ -692,6 +695,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	int cpu, thread;
+
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
 
 	if (evsel->fd) {
@@ -710,6 +717,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea
 {
 	int cpu, thread;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	for (cpu = 0; cpu < ncpus; cpu++) {
 		for (thread = 0; thread < nthreads; thread++) {
 			int fd = FD(evsel, cpu, thread),
@@ -740,6 +750,9 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
 	if (evsel->sample_id == NULL)
 		return -ENOMEM;
@@ -784,6 +797,9 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	int cpu, thread;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	for (cpu = 0; cpu < ncpus; cpu++)
 		for (thread = 0; thread < nthreads; ++thread) {
 			close(FD(evsel, cpu, thread));
@@ -872,6 +888,9 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 	int cpu, thread;
 	struct perf_counts_values *aggr = &evsel->counts->aggr, count;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	aggr->val = aggr->ena = aggr->run = 0;
 
 	for (cpu = 0; cpu < ncpus; cpu++) {
@@ -994,13 +1013,18 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 			      struct thread_map *threads)
 {
-	int cpu, thread;
+	int cpu, thread, nthreads;
 	unsigned long flags = PERF_FLAG_FD_CLOEXEC;
 	int pid = -1, err;
 	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+	else
+		nthreads = threads->nr;
+
 	if (evsel->fd == NULL &&
-	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+	    perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0)
 		return -ENOMEM;
 
 	if (evsel->cgrp) {
@@ -1024,10 +1048,10 @@ retry_sample_id:
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
-		for (thread = 0; thread < threads->nr; thread++) {
+		for (thread = 0; thread < nthreads; thread++) {
 			int group_fd;
 
-			if (!evsel->cgrp)
+			if (!evsel->cgrp && !evsel->system_wide)
 				pid = threads->map[thread];
 
 			group_fd = get_group_fd(evsel, cpu, thread);
@@ -1100,7 +1124,7 @@ out_close:
 			close(FD(evsel, cpu, thread));
 			FD(evsel, cpu, thread) = -1;
 		}
-		thread = threads->nr;
+		thread = nthreads;
 	} while (--cpu >= 0);
 	return err;
 }
@@ -2002,6 +2026,8 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			      int err, char *msg, size_t size)
 {
+	char sbuf[STRERR_BUFSIZE];
+
 	switch (err) {
 	case EPERM:
 	case EACCES:
@@ -2036,13 +2062,20 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	"No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
 #endif
 		break;
+	case EBUSY:
+		if (find_process("oprofiled"))
+			return scnprintf(msg, size,
+	"The PMU counters are busy/taken by another profiler.\n"
+	"We found oprofile daemon running, please stop it and try again.");
+		break;
 	default:
 		break;
 	}
 
 	return scnprintf(msg, size,
-	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).  \n"
+	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
 	"/bin/dmesg may provide additional information.\n"
 	"No CONFIG_PERF_EVENTS=y kernel support configured?\n",
-			 err, strerror(err), perf_evsel__name(evsel));
+			 err, strerror_r(err, sbuf, sizeof(sbuf)),
+			 perf_evsel__name(evsel));
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d7f93ce0ebc1..7bc314be6a7b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -85,6 +85,8 @@ struct perf_evsel {
 	bool 			needs_swap;
 	bool			no_aux_samples;
 	bool			immediate;
+	bool			system_wide;
+	bool			tracking;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 158c787ce0c4..ce0de00399da 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -214,11 +214,11 @@ static int machine__hit_all_dsos(struct machine *machine)
 {
 	int err;
 
-	err = __dsos__hit_all(&machine->kernel_dsos);
+	err = __dsos__hit_all(&machine->kernel_dsos.head);
 	if (err)
 		return err;
 
-	return __dsos__hit_all(&machine->user_dsos);
+	return __dsos__hit_all(&machine->user_dsos.head);
 }
 
 int dsos__hit_all(struct perf_session *session)
@@ -288,11 +288,12 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
 		umisc = PERF_RECORD_MISC_GUEST_USER;
 	}
 
-	err = __dsos__write_buildid_table(&machine->kernel_dsos, machine,
+	err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
 					  machine->pid, kmisc, fd);
 	if (err == 0)
-		err = __dsos__write_buildid_table(&machine->user_dsos, machine,
-						  machine->pid, umisc, fd);
+		err = __dsos__write_buildid_table(&machine->user_dsos.head,
+						  machine, machine->pid, umisc,
+						  fd);
 	return err;
 }
 
@@ -455,9 +456,10 @@ static int __dsos__cache_build_ids(struct list_head *head,
 
 static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
 {
-	int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine,
+	int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine,
 					  debugdir);
-	ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir);
+	ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine,
+				       debugdir);
 	return ret;
 }
 
@@ -483,8 +485,10 @@ static int perf_session__cache_build_ids(struct perf_session *session)
 
 static bool machine__read_build_ids(struct machine *machine, bool with_hits)
 {
-	bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits);
-	ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits);
+	bool ret;
+
+	ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
+	ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
 	return ret;
 }
 
@@ -1548,7 +1552,7 @@ static int __event_process_build_id(struct build_id_event *bev,
 				    struct perf_session *session)
 {
 	int err = -1;
-	struct list_head *head;
+	struct dsos *dsos;
 	struct machine *machine;
 	u16 misc;
 	struct dso *dso;
@@ -1563,22 +1567,22 @@ static int __event_process_build_id(struct build_id_event *bev,
 	switch (misc) {
 	case PERF_RECORD_MISC_KERNEL:
 		dso_type = DSO_TYPE_KERNEL;
-		head = &machine->kernel_dsos;
+		dsos = &machine->kernel_dsos;
 		break;
 	case PERF_RECORD_MISC_GUEST_KERNEL:
 		dso_type = DSO_TYPE_GUEST_KERNEL;
-		head = &machine->kernel_dsos;
+		dsos = &machine->kernel_dsos;
 		break;
 	case PERF_RECORD_MISC_USER:
 	case PERF_RECORD_MISC_GUEST_USER:
 		dso_type = DSO_TYPE_USER;
-		head = &machine->user_dsos;
+		dsos = &machine->user_dsos;
 		break;
 	default:
 		goto out;
 	}
 
-	dso = __dsos__findnew(head, filename);
+	dso = __dsos__findnew(dsos, filename);
 	if (dso != NULL) {
 		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 30df6187ee02..86569fa3651d 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -277,6 +277,28 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
 	}
 }
 
+void hists__delete_entries(struct hists *hists)
+{
+	struct rb_node *next = rb_first(&hists->entries);
+	struct hist_entry *n;
+
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		next = rb_next(&n->rb_node);
+
+		rb_erase(&n->rb_node, &hists->entries);
+
+		if (sort__need_collapse)
+			rb_erase(&n->rb_node_in, &hists->entries_collapsed);
+
+		--hists->nr_entries;
+		if (!n->filtered)
+			--hists->nr_non_filtered_entries;
+
+		hist_entry__free(n);
+	}
+}
+
 /*
  * histogram, sorted on item, collects periods
  */
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 742f49a85725..8c9c70e18cbb 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -152,6 +152,7 @@ void hists__output_resort(struct hists *hists);
 void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
+void hists__delete_entries(struct hists *hists);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
 u64 hists__total_period(struct hists *hists);
@@ -192,6 +193,7 @@ struct perf_hpp {
 };
 
 struct perf_hpp_fmt {
+	const char *name;
 	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		      struct perf_evsel *evsel);
 	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
@@ -207,6 +209,8 @@ struct perf_hpp_fmt {
 	struct list_head list;
 	struct list_head sort_list;
 	bool elide;
+	int len;
+	int user_len;
 };
 
 extern struct list_head perf_hpp__list;
@@ -261,17 +265,19 @@ static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
 }
 
 void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
+void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists);
+void perf_hpp__set_user_width(const char *width_list_str);
 
 typedef u64 (*hpp_field_fn)(struct hist_entry *he);
 typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
 typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
 
-int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
-	       hpp_field_fn get_field, const char *fmt,
-	       hpp_snprint_fn print_fn, bool fmt_percent);
-int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
-		   hpp_field_fn get_field, const char *fmt,
-		   hpp_snprint_fn print_fn, bool fmt_percent);
+int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+	     struct hist_entry *he, hpp_field_fn get_field,
+	     const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
+int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		 struct hist_entry *he, hpp_field_fn get_field,
+		 const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 {
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index 0b5a8cd2ee79..cf1d7913783b 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -92,7 +92,6 @@ struct perf_kvm_stat {
 	u64 lost_events;
 	u64 duration;
 
-	const char *pid_str;
 	struct intlist *pid_list;
 
 	struct rb_root result;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 16bba9fff2c8..b7d477fbda02 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -17,8 +17,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
 	map_groups__init(&machine->kmaps);
 	RB_CLEAR_NODE(&machine->rb_node);
-	INIT_LIST_HEAD(&machine->user_dsos);
-	INIT_LIST_HEAD(&machine->kernel_dsos);
+	INIT_LIST_HEAD(&machine->user_dsos.head);
+	INIT_LIST_HEAD(&machine->kernel_dsos.head);
 
 	machine->threads = RB_ROOT;
 	INIT_LIST_HEAD(&machine->dead_threads);
@@ -31,6 +31,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->symbol_filter = NULL;
 	machine->id_hdr_size = 0;
+	machine->comm_exec = false;
+	machine->kernel_start = 0;
 
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
@@ -70,11 +72,12 @@ out_delete:
 	return NULL;
 }
 
-static void dsos__delete(struct list_head *dsos)
+static void dsos__delete(struct dsos *dsos)
 {
 	struct dso *pos, *n;
 
-	list_for_each_entry_safe(pos, n, dsos, node) {
+	list_for_each_entry_safe(pos, n, &dsos->head, node) {
+		RB_CLEAR_NODE(&pos->rb_node);
 		list_del(&pos->node);
 		dso__delete(pos);
 	}
@@ -179,6 +182,19 @@ void machines__set_symbol_filter(struct machines *machines,
 	}
 }
 
+void machines__set_comm_exec(struct machines *machines, bool comm_exec)
+{
+	struct rb_node *nd;
+
+	machines->host.comm_exec = comm_exec;
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+		machine->comm_exec = comm_exec;
+	}
+}
+
 struct machine *machines__find(struct machines *machines, pid_t pid)
 {
 	struct rb_node **p = &machines->guests.rb_node;
@@ -398,17 +414,31 @@ struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 	return __machine__findnew_thread(machine, pid, tid, false);
 }
 
+struct comm *machine__thread_exec_comm(struct machine *machine,
+				       struct thread *thread)
+{
+	if (machine->comm_exec)
+		return thread__exec_comm(thread);
+	else
+		return thread__comm(thread);
+}
+
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample)
 {
 	struct thread *thread = machine__findnew_thread(machine,
 							event->comm.pid,
 							event->comm.tid);
+	bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
+
+	if (exec)
+		machine->comm_exec = true;
 
 	if (dump_trace)
 		perf_event__fprintf_comm(event, stdout);
 
-	if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) {
+	if (thread == NULL ||
+	    __thread__set_comm(thread, event->comm.comm, sample->time, exec)) {
 		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
 		return -1;
 	}
@@ -448,23 +478,23 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 {
 	struct rb_node *nd;
-	size_t ret = __dsos__fprintf(&machines->host.kernel_dsos, fp) +
-		     __dsos__fprintf(&machines->host.user_dsos, fp);
+	size_t ret = __dsos__fprintf(&machines->host.kernel_dsos.head, fp) +
+		     __dsos__fprintf(&machines->host.user_dsos.head, fp);
 
 	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += __dsos__fprintf(&pos->kernel_dsos, fp);
-		ret += __dsos__fprintf(&pos->user_dsos, fp);
+		ret += __dsos__fprintf(&pos->kernel_dsos.head, fp);
+		ret += __dsos__fprintf(&pos->user_dsos.head, fp);
 	}
 
 	return ret;
 }
 
-size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
+size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm)
 {
-	return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, skip, parm) +
-	       __dsos__fprintf_buildid(&machine->user_dsos, fp, skip, parm);
+	return __dsos__fprintf_buildid(&m->kernel_dsos.head, fp, skip, parm) +
+	       __dsos__fprintf_buildid(&m->user_dsos.head, fp, skip, parm);
 }
 
 size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
@@ -565,8 +595,8 @@ const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
  * Returns the name of the start symbol in *symbol_name. Pass in NULL as
  * symbol_name if it's not that important.
  */
-static u64 machine__get_kernel_start_addr(struct machine *machine,
-					  const char **symbol_name)
+static u64 machine__get_running_kernel_start(struct machine *machine,
+					     const char **symbol_name)
 {
 	char filename[PATH_MAX];
 	int i;
@@ -593,7 +623,7 @@ static u64 machine__get_kernel_start_addr(struct machine *machine,
 int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
 	enum map_type type;
-	u64 start = machine__get_kernel_start_addr(machine, NULL);
+	u64 start = machine__get_running_kernel_start(machine, NULL);
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
@@ -912,7 +942,7 @@ int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
 	const char *name;
-	u64 addr = machine__get_kernel_start_addr(machine, &name);
+	u64 addr = machine__get_running_kernel_start(machine, &name);
 	if (!addr)
 		return -1;
 
@@ -965,7 +995,7 @@ static bool machine__uses_kcore(struct machine *machine)
 {
 	struct dso *dso;
 
-	list_for_each_entry(dso, &machine->kernel_dsos, node) {
+	list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
 		if (dso__is_kcore(dso))
 			return true;
 	}
@@ -1285,6 +1315,16 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread,
 
 	thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr,
 				   &al);
+	if (al.map == NULL) {
+		/*
+		 * some shared data regions have execute bit set which puts
+		 * their mapping in the MAP__FUNCTION type array.
+		 * Check there as a fallback option before dropping the sample.
+		 */
+		thread__find_addr_location(thread, machine, m, MAP__FUNCTION, addr,
+					   &al);
+	}
+
 	ams->addr = addr;
 	ams->al_addr = al.addr;
 	ams->sym = al.sym;
@@ -1531,3 +1571,25 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 
 	return 0;
 }
+
+int machine__get_kernel_start(struct machine *machine)
+{
+	struct map *map = machine__kernel_map(machine, MAP__FUNCTION);
+	int err = 0;
+
+	/*
+	 * The only addresses above 2^63 are kernel addresses of a 64-bit
+	 * kernel.  Note that addresses are unsigned so that on a 32-bit system
+	 * all addresses including kernel addresses are less than 2^32.  In
+	 * that case (32-bit system), if the kernel mapping is unknown, all
+	 * addresses will be assumed to be in user space - see
+	 * machine__kernel_ip().
+	 */
+	machine->kernel_start = 1ULL << 63;
+	if (map) {
+		err = map__load(map, machine->symbol_filter);
+		if (map->start)
+			machine->kernel_start = map->start;
+	}
+	return err;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index b972824e6294..2b651a7f5d0d 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -4,6 +4,7 @@
 #include <sys/types.h>
 #include <linux/rbtree.h>
 #include "map.h"
+#include "dso.h"
 #include "event.h"
 
 struct addr_location;
@@ -26,15 +27,17 @@ struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
 	u16		  id_hdr_size;
+	bool		  comm_exec;
 	char		  *root_dir;
 	struct rb_root	  threads;
 	struct list_head  dead_threads;
 	struct thread	  *last_match;
 	struct vdso_info  *vdso_info;
-	struct list_head  user_dsos;
-	struct list_head  kernel_dsos;
+	struct dsos	  user_dsos;
+	struct dsos	  kernel_dsos;
 	struct map_groups kmaps;
 	struct map	  *vmlinux_maps[MAP__NR_TYPES];
+	u64		  kernel_start;
 	symbol_filter_t	  symbol_filter;
 	pid_t		  *current_tid;
 };
@@ -45,8 +48,26 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
 	return machine->vmlinux_maps[type];
 }
 
+int machine__get_kernel_start(struct machine *machine);
+
+static inline u64 machine__kernel_start(struct machine *machine)
+{
+	if (!machine->kernel_start)
+		machine__get_kernel_start(machine);
+	return machine->kernel_start;
+}
+
+static inline bool machine__kernel_ip(struct machine *machine, u64 ip)
+{
+	u64 kernel_start = machine__kernel_start(machine);
+
+	return ip >= kernel_start;
+}
+
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid);
+struct comm *machine__thread_exec_comm(struct machine *machine,
+				       struct thread *thread);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
@@ -88,6 +109,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 
 void machines__set_symbol_filter(struct machines *machines,
 				 symbol_filter_t symbol_filter);
+void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 31b8905dd863..b7090596ac50 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -31,6 +31,7 @@ static inline int is_anon_memory(const char *filename)
 static inline int is_no_dso_memory(const char *filename)
 {
 	return !strncmp(filename, "[stack", 6) ||
+	       !strncmp(filename, "/SYSV",5)   ||
 	       !strcmp(filename, "[heap]");
 }
 
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
new file mode 100644
index 000000000000..706ce1a66169
--- /dev/null
+++ b/tools/perf/util/ordered-events.c
@@ -0,0 +1,245 @@
+#include <linux/list.h>
+#include <linux/compiler.h>
+#include "ordered-events.h"
+#include "evlist.h"
+#include "session.h"
+#include "asm/bug.h"
+#include "debug.h"
+
+#define pr_N(n, fmt, ...) \
+	eprintf(n, debug_ordered_events, fmt, ##__VA_ARGS__)
+
+#define pr(fmt, ...) pr_N(1, pr_fmt(fmt), ##__VA_ARGS__)
+
+static void queue_event(struct ordered_events *oe, struct ordered_event *new)
+{
+	struct ordered_event *last = oe->last;
+	u64 timestamp = new->timestamp;
+	struct list_head *p;
+
+	++oe->nr_events;
+	oe->last = new;
+
+	pr_oe_time2(timestamp, "queue_event nr_events %u\n", oe->nr_events);
+
+	if (!last) {
+		list_add(&new->list, &oe->events);
+		oe->max_timestamp = timestamp;
+		return;
+	}
+
+	/*
+	 * last event might point to some random place in the list as it's
+	 * the last queued event. We expect that the new event is close to
+	 * this.
+	 */
+	if (last->timestamp <= timestamp) {
+		while (last->timestamp <= timestamp) {
+			p = last->list.next;
+			if (p == &oe->events) {
+				list_add_tail(&new->list, &oe->events);
+				oe->max_timestamp = timestamp;
+				return;
+			}
+			last = list_entry(p, struct ordered_event, list);
+		}
+		list_add_tail(&new->list, &last->list);
+	} else {
+		while (last->timestamp > timestamp) {
+			p = last->list.prev;
+			if (p == &oe->events) {
+				list_add(&new->list, &oe->events);
+				return;
+			}
+			last = list_entry(p, struct ordered_event, list);
+		}
+		list_add(&new->list, &last->list);
+	}
+}
+
+#define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct ordered_event))
+static struct ordered_event *alloc_event(struct ordered_events *oe)
+{
+	struct list_head *cache = &oe->cache;
+	struct ordered_event *new = NULL;
+
+	if (!list_empty(cache)) {
+		new = list_entry(cache->next, struct ordered_event, list);
+		list_del(&new->list);
+	} else if (oe->buffer) {
+		new = oe->buffer + oe->buffer_idx;
+		if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
+			oe->buffer = NULL;
+	} else if (oe->cur_alloc_size < oe->max_alloc_size) {
+		size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
+
+		oe->buffer = malloc(size);
+		if (!oe->buffer)
+			return NULL;
+
+		pr("alloc size %" PRIu64 "B (+%zu), max %" PRIu64 "B\n",
+		   oe->cur_alloc_size, size, oe->max_alloc_size);
+
+		oe->cur_alloc_size += size;
+		list_add(&oe->buffer->list, &oe->to_free);
+
+		/* First entry is abused to maintain the to_free list. */
+		oe->buffer_idx = 2;
+		new = oe->buffer + 1;
+	} else {
+		pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
+	}
+
+	return new;
+}
+
+struct ordered_event *
+ordered_events__new(struct ordered_events *oe, u64 timestamp)
+{
+	struct ordered_event *new;
+
+	new = alloc_event(oe);
+	if (new) {
+		new->timestamp = timestamp;
+		queue_event(oe, new);
+	}
+
+	return new;
+}
+
+void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event)
+{
+	list_move(&event->list, &oe->cache);
+	oe->nr_events--;
+}
+
+static int __ordered_events__flush(struct perf_session *s,
+				   struct perf_tool *tool)
+{
+	struct ordered_events *oe = &s->ordered_events;
+	struct list_head *head = &oe->events;
+	struct ordered_event *tmp, *iter;
+	struct perf_sample sample;
+	u64 limit = oe->next_flush;
+	u64 last_ts = oe->last ? oe->last->timestamp : 0ULL;
+	bool show_progress = limit == ULLONG_MAX;
+	struct ui_progress prog;
+	int ret;
+
+	if (!tool->ordered_events || !limit)
+		return 0;
+
+	if (show_progress)
+		ui_progress__init(&prog, oe->nr_events, "Processing time ordered events...");
+
+	list_for_each_entry_safe(iter, tmp, head, list) {
+		if (session_done())
+			return 0;
+
+		if (iter->timestamp > limit)
+			break;
+
+		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
+		if (ret)
+			pr_err("Can't parse sample, err = %d\n", ret);
+		else {
+			ret = perf_session__deliver_event(s, iter->event, &sample, tool,
+							  iter->file_offset);
+			if (ret)
+				return ret;
+		}
+
+		ordered_events__delete(oe, iter);
+		oe->last_flush = iter->timestamp;
+
+		if (show_progress)
+			ui_progress__update(&prog, 1);
+	}
+
+	if (list_empty(head))
+		oe->last = NULL;
+	else if (last_ts <= limit)
+		oe->last = list_entry(head->prev, struct ordered_event, list);
+
+	return 0;
+}
+
+int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
+			  enum oe_flush how)
+{
+	struct ordered_events *oe = &s->ordered_events;
+	static const char * const str[] = {
+		"NONE",
+		"FINAL",
+		"ROUND",
+		"HALF ",
+	};
+	int err;
+
+	switch (how) {
+	case OE_FLUSH__FINAL:
+		oe->next_flush = ULLONG_MAX;
+		break;
+
+	case OE_FLUSH__HALF:
+	{
+		struct ordered_event *first, *last;
+		struct list_head *head = &oe->events;
+
+		first = list_entry(head->next, struct ordered_event, list);
+		last = oe->last;
+
+		/* Warn if we are called before any event got allocated. */
+		if (WARN_ONCE(!last || list_empty(head), "empty queue"))
+			return 0;
+
+		oe->next_flush  = first->timestamp;
+		oe->next_flush += (last->timestamp - first->timestamp) / 2;
+		break;
+	}
+
+	case OE_FLUSH__ROUND:
+	case OE_FLUSH__NONE:
+	default:
+		break;
+	};
+
+	pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush PRE  %s, nr_events %u\n",
+		   str[how], oe->nr_events);
+	pr_oe_time(oe->max_timestamp, "max_timestamp\n");
+
+	err = __ordered_events__flush(s, tool);
+
+	if (!err) {
+		if (how == OE_FLUSH__ROUND)
+			oe->next_flush = oe->max_timestamp;
+
+		oe->last_flush_type = how;
+	}
+
+	pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush POST %s, nr_events %u\n",
+		   str[how], oe->nr_events);
+	pr_oe_time(oe->last_flush, "last_flush\n");
+
+	return err;
+}
+
+void ordered_events__init(struct ordered_events *oe)
+{
+	INIT_LIST_HEAD(&oe->events);
+	INIT_LIST_HEAD(&oe->cache);
+	INIT_LIST_HEAD(&oe->to_free);
+	oe->max_alloc_size = (u64) -1;
+	oe->cur_alloc_size = 0;
+}
+
+void ordered_events__free(struct ordered_events *oe)
+{
+	while (!list_empty(&oe->to_free)) {
+		struct ordered_event *event;
+
+		event = list_entry(oe->to_free.next, struct ordered_event, list);
+		list_del(&event->list);
+		free(event);
+	}
+}
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
new file mode 100644
index 000000000000..3b2f20542a01
--- /dev/null
+++ b/tools/perf/util/ordered-events.h
@@ -0,0 +1,51 @@
+#ifndef __ORDERED_EVENTS_H
+#define __ORDERED_EVENTS_H
+
+#include <linux/types.h>
+#include "tool.h"
+
+struct perf_session;
+
+struct ordered_event {
+	u64			timestamp;
+	u64			file_offset;
+	union perf_event	*event;
+	struct list_head	list;
+};
+
+enum oe_flush {
+	OE_FLUSH__NONE,
+	OE_FLUSH__FINAL,
+	OE_FLUSH__ROUND,
+	OE_FLUSH__HALF,
+};
+
+struct ordered_events {
+	u64			last_flush;
+	u64			next_flush;
+	u64			max_timestamp;
+	u64			max_alloc_size;
+	u64			cur_alloc_size;
+	struct list_head	events;
+	struct list_head	cache;
+	struct list_head	to_free;
+	struct ordered_event	*buffer;
+	struct ordered_event	*last;
+	int			buffer_idx;
+	unsigned int		nr_events;
+	enum oe_flush		last_flush_type;
+};
+
+struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp);
+void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
+int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
+			  enum oe_flush how);
+void ordered_events__init(struct ordered_events *oe);
+void ordered_events__free(struct ordered_events *oe);
+
+static inline
+void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size)
+{
+	oe->max_alloc_size = size;
+}
+#endif /* __ORDERED_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1e15df10a88c..d76aa30cb1fb 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -10,6 +10,7 @@
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
+#include "debug.h"
 #include <api/fs/debugfs.h>
 #include "parse-events-bison.h"
 #define YY_EXTRA_TYPE int
@@ -633,18 +634,28 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 			 char *name, struct list_head *head_config)
 {
 	struct perf_event_attr attr;
+	struct perf_pmu_info info;
 	struct perf_pmu *pmu;
 	struct perf_evsel *evsel;
-	const char *unit;
-	double scale;
 
 	pmu = perf_pmu__find(name);
 	if (!pmu)
 		return -EINVAL;
 
-	memset(&attr, 0, sizeof(attr));
+	if (pmu->default_config) {
+		memcpy(&attr, pmu->default_config,
+		       sizeof(struct perf_event_attr));
+	} else {
+		memset(&attr, 0, sizeof(attr));
+	}
+
+	if (!head_config) {
+		attr.type = pmu->type;
+		evsel = __add_event(list, idx, &attr, NULL, pmu->cpus);
+		return evsel ? 0 : -ENOMEM;
+	}
 
-	if (perf_pmu__check_alias(pmu, head_config, &unit, &scale))
+	if (perf_pmu__check_alias(pmu, head_config, &info))
 		return -EINVAL;
 
 	/*
@@ -659,8 +670,8 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
 			    pmu->cpus);
 	if (evsel) {
-		evsel->unit = unit;
-		evsel->scale = scale;
+		evsel->unit = info.unit;
+		evsel->scale = info.scale;
 	}
 
 	return evsel ? 0 : -ENOMEM;
@@ -973,7 +984,7 @@ int parse_filter(const struct option *opt, const char *str,
 
 	if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) {
 		fprintf(stderr,
-			"-F option should follow a -e tracepoint option\n");
+			"--filter option should follow a -e tracepoint option\n");
 		return -1;
 	}
 
@@ -1006,9 +1017,11 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
+	char sbuf[STRERR_BUFSIZE];
 
 	if (debugfs_valid_mountpoint(tracing_events_path)) {
-		printf("  [ Tracepoints not available: %s ]\n", strerror(errno));
+		printf("  [ Tracepoints not available: %s ]\n",
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 		return;
 	}
 
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 0bc87ba46bf3..55fab6ad609a 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -210,6 +210,16 @@ PE_NAME '/' event_config '/'
 	parse_events__free_terms($3);
 	$$ = list;
 }
+|
+PE_NAME '/' '/'
+{
+	struct parse_events_evlist *data = _data;
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
+	$$ = list;
+}
 
 value_sym:
 PE_VALUE_SYM_HW
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7a811eb61f75..93a41ca96b8e 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -2,6 +2,8 @@
 #include <sys/types.h>
 #include <unistd.h>
 #include <stdio.h>
+#include <stdbool.h>
+#include <stdarg.h>
 #include <dirent.h>
 #include <api/fs/fs.h>
 #include <locale.h>
@@ -14,8 +16,8 @@
 
 struct perf_pmu_alias {
 	char *name;
-	struct list_head terms;
-	struct list_head list;
+	struct list_head terms; /* HEAD struct parse_events_term -> list */
+	struct list_head list;  /* ELEM */
 	char unit[UNIT_MAX_LEN+1];
 	double scale;
 };
@@ -208,6 +210,19 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	return 0;
 }
 
+static inline bool pmu_alias_info_file(char *name)
+{
+	size_t len;
+
+	len = strlen(name);
+	if (len > 5 && !strcmp(name + len - 5, ".unit"))
+		return true;
+	if (len > 6 && !strcmp(name + len - 6, ".scale"))
+		return true;
+
+	return false;
+}
+
 /*
  * Process all the sysfs attributes located under the directory
  * specified in 'dir' parameter.
@@ -216,7 +231,6 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 {
 	struct dirent *evt_ent;
 	DIR *event_dir;
-	size_t len;
 	int ret = 0;
 
 	event_dir = opendir(dir);
@@ -232,13 +246,9 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 			continue;
 
 		/*
-		 * skip .unit and .scale info files
-		 * parsed in perf_pmu__new_alias()
+		 * skip info files parsed in perf_pmu__new_alias()
 		 */
-		len = strlen(name);
-		if (len > 5 && !strcmp(name + len - 5, ".unit"))
-			continue;
-		if (len > 6 && !strcmp(name + len - 6, ".scale"))
+		if (pmu_alias_info_file(name))
 			continue;
 
 		snprintf(path, PATH_MAX, "%s/%s", dir, name);
@@ -387,6 +397,12 @@ static struct cpu_map *pmu_cpumask(const char *name)
 	return cpus;
 }
 
+struct perf_event_attr *__attribute__((weak))
+perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+	return NULL;
+}
+
 static struct perf_pmu *pmu_lookup(const char *name)
 {
 	struct perf_pmu *pmu;
@@ -421,6 +437,9 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	pmu->name = strdup(name);
 	pmu->type = type;
 	list_add_tail(&pmu->list, &pmus);
+
+	pmu->default_config = perf_pmu__get_default_config(pmu);
+
 	return pmu;
 }
 
@@ -479,28 +498,24 @@ pmu_find_format(struct list_head *formats, char *name)
 }
 
 /*
- * Returns value based on the format definition (format parameter)
+ * Sets value based on the format definition (format parameter)
  * and unformated value (value parameter).
- *
- * TODO maybe optimize a little ;)
  */
-static __u64 pmu_format_value(unsigned long *format, __u64 value)
+static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v,
+			     bool zero)
 {
 	unsigned long fbit, vbit;
-	__u64 v = 0;
 
 	for (fbit = 0, vbit = 0; fbit < PERF_PMU_FORMAT_BITS; fbit++) {
 
 		if (!test_bit(fbit, format))
 			continue;
 
-		if (!(value & (1llu << vbit++)))
-			continue;
-
-		v |= (1llu << fbit);
+		if (value & (1llu << vbit++))
+			*v |= (1llu << fbit);
+		else if (zero)
+			*v &= ~(1llu << fbit);
 	}
-
-	return v;
 }
 
 /*
@@ -509,7 +524,8 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value)
  */
 static int pmu_config_term(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct parse_events_term *term)
+			   struct parse_events_term *term,
+			   bool zero)
 {
 	struct perf_pmu_format *format;
 	__u64 *vp;
@@ -548,18 +564,19 @@ static int pmu_config_term(struct list_head *formats,
 	 * non-hardcoded terms, here's the place to translate
 	 * them into value.
 	 */
-	*vp |= pmu_format_value(format->bits, term->val.num);
+	pmu_format_value(format->bits, term->val.num, vp, zero);
 	return 0;
 }
 
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct list_head *head_terms)
+			   struct list_head *head_terms,
+			   bool zero)
 {
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, head_terms, list)
-		if (pmu_config_term(formats, attr, term))
+		if (pmu_config_term(formats, attr, term, zero))
 			return -EINVAL;
 
 	return 0;
@@ -573,8 +590,10 @@ int perf_pmu__config_terms(struct list_head *formats,
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms)
 {
+	bool zero = !!pmu->default_config;
+
 	attr->type = pmu->type;
-	return perf_pmu__config_terms(&pmu->format, attr, head_terms);
+	return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
@@ -634,7 +653,7 @@ static int check_unit_scale(struct perf_pmu_alias *alias,
  * defined for the alias
  */
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-			  const char **unit, double *scale)
+			  struct perf_pmu_info *info)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
@@ -644,8 +663,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	 * Mark unit and scale as not set
 	 * (different from default values, see below)
 	 */
-	*unit   = NULL;
-	*scale  = 0.0;
+	info->unit   = NULL;
+	info->scale  = 0.0;
 
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
@@ -655,7 +674,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 		if (ret)
 			return ret;
 
-		ret = check_unit_scale(alias, unit, scale);
+		ret = check_unit_scale(alias, &info->unit, &info->scale);
 		if (ret)
 			return ret;
 
@@ -668,11 +687,11 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	 * set defaults as for evsel
 	 * unit cannot left to NULL
 	 */
-	if (*unit == NULL)
-		*unit   = "";
+	if (info->unit == NULL)
+		info->unit   = "";
 
-	if (*scale == 0.0)
-		*scale  = 1.0;
+	if (info->scale == 0.0)
+		info->scale  = 1.0;
 
 	return 0;
 }
@@ -794,3 +813,39 @@ bool pmu_have_event(const char *pname, const char *name)
 	}
 	return false;
 }
+
+static FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name)
+{
+	struct stat st;
+	char path[PATH_MAX];
+	const char *sysfs;
+
+	sysfs = sysfs__mountpoint();
+	if (!sysfs)
+		return NULL;
+
+	snprintf(path, PATH_MAX,
+		 "%s" EVENT_SOURCE_DEVICE_PATH "%s/%s", sysfs, pmu->name, name);
+
+	if (stat(path, &st) < 0)
+		return NULL;
+
+	return fopen(path, "r");
+}
+
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+			...)
+{
+	va_list args;
+	FILE *file;
+	int ret = EOF;
+
+	va_start(args, fmt);
+	file = perf_pmu__open_file(pmu, name);
+	if (file) {
+		ret = vfscanf(file, fmt, args);
+		fclose(file);
+	}
+	va_end(args);
+	return ret;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index c14a543ce1f3..fe90a012c003 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -13,13 +13,21 @@ enum {
 
 #define PERF_PMU_FORMAT_BITS 64
 
+struct perf_event_attr;
+
 struct perf_pmu {
 	char *name;
 	__u32 type;
+	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
-	struct list_head format;
-	struct list_head aliases;
-	struct list_head list;
+	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
+	struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
+	struct list_head list;    /* ELEM */
+};
+
+struct perf_pmu_info {
+	const char *unit;
+	double scale;
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);
@@ -27,9 +35,10 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms);
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
-			   struct list_head *head_terms);
+			   struct list_head *head_terms,
+			   bool zero);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
-			  const char **unit, double *scale);
+			  struct perf_pmu_info *info);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
 				  struct list_head *head_terms);
 int perf_pmu_wrap(void);
@@ -45,5 +54,11 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 void print_pmu_events(const char *event_glob, bool name_only);
 bool pmu_have_event(const char *pname, const char *name);
 
+int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
+			...) __attribute__((format(scanf, 3, 4)));
+
 int perf_pmu__test(void);
+
+struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 9a0a1839a377..c150ca4343eb 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -79,7 +79,7 @@ static int init_symbol_maps(bool user_only)
 	int ret;
 
 	symbol_conf.sort_by_name = true;
-	ret = symbol__init();
+	ret = symbol__init(NULL);
 	if (ret < 0) {
 		pr_debug("Failed to init symbol map.\n");
 		goto out;
@@ -184,7 +184,8 @@ static struct dso *kernel_get_module_dso(const char *module)
 	const char *vmlinux_name;
 
 	if (module) {
-		list_for_each_entry(dso, &host_machine->kernel_dsos, node) {
+		list_for_each_entry(dso, &host_machine->kernel_dsos.head,
+				    node) {
 			if (strncmp(dso->short_name + 1, module,
 				    dso->short_name_len - 2) == 0)
 				goto found;
@@ -258,21 +259,33 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 #ifdef HAVE_DWARF_SUPPORT
 
 /* Open new debuginfo of given module */
-static struct debuginfo *open_debuginfo(const char *module)
+static struct debuginfo *open_debuginfo(const char *module, bool silent)
 {
 	const char *path = module;
+	struct debuginfo *ret;
 
 	if (!module || !strchr(module, '/')) {
 		path = kernel_get_module_path(module);
 		if (!path) {
-			pr_err("Failed to find path of %s module.\n",
-			       module ?: "kernel");
+			if (!silent)
+				pr_err("Failed to find path of %s module.\n",
+				       module ?: "kernel");
 			return NULL;
 		}
 	}
-	return debuginfo__new(path);
+	ret = debuginfo__new(path);
+	if (!ret && !silent) {
+		pr_warning("The %s file has no debug information.\n", path);
+		if (!module || !strtailcmp(path, ".ko"))
+			pr_warning("Rebuild with CONFIG_DEBUG_INFO=y, ");
+		else
+			pr_warning("Rebuild with -g, ");
+		pr_warning("or install an appropriate debuginfo package.\n");
+	}
+	return ret;
 }
 
+
 static int get_text_start_address(const char *exec, unsigned long *address)
 {
 	Elf *elf;
@@ -333,15 +346,13 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 	pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
 		 tp->module ? : "kernel");
 
-	dinfo = open_debuginfo(tp->module);
+	dinfo = open_debuginfo(tp->module, verbose == 0);
 	if (dinfo) {
 		ret = debuginfo__find_probe_point(dinfo,
 						 (unsigned long)addr, pp);
 		debuginfo__delete(dinfo);
-	} else {
-		pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr);
+	} else
 		ret = -ENOENT;
-	}
 
 	if (ret > 0) {
 		pp->retprobe = tp->retprobe;
@@ -457,13 +468,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	struct debuginfo *dinfo;
 	int ntevs, ret = 0;
 
-	dinfo = open_debuginfo(target);
+	dinfo = open_debuginfo(target, !need_dwarf);
 
 	if (!dinfo) {
-		if (need_dwarf) {
-			pr_warning("Failed to open debuginfo file.\n");
+		if (need_dwarf)
 			return -ENOENT;
-		}
 		pr_debug("Could not open debuginfo. Try to use symbols.\n");
 		return 0;
 	}
@@ -565,7 +574,7 @@ static int get_real_path(const char *raw_path, const char *comp_dir,
 
 static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
 {
-	char buf[LINEBUF_SIZE];
+	char buf[LINEBUF_SIZE], sbuf[STRERR_BUFSIZE];
 	const char *color = show_num ? "" : PERF_COLOR_BLUE;
 	const char *prefix = NULL;
 
@@ -585,7 +594,8 @@ static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
 	return 1;
 error:
 	if (ferror(fp)) {
-		pr_warning("File read error: %s\n", strerror(errno));
+		pr_warning("File read error: %s\n",
+			   strerror_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 	return 0;
@@ -618,13 +628,12 @@ static int __show_line_range(struct line_range *lr, const char *module)
 	FILE *fp;
 	int ret;
 	char *tmp;
+	char sbuf[STRERR_BUFSIZE];
 
 	/* Search a line range */
-	dinfo = open_debuginfo(module);
-	if (!dinfo) {
-		pr_warning("Failed to open debuginfo file.\n");
+	dinfo = open_debuginfo(module, false);
+	if (!dinfo)
 		return -ENOENT;
-	}
 
 	ret = debuginfo__find_line_range(dinfo, lr);
 	debuginfo__delete(dinfo);
@@ -656,7 +665,7 @@ static int __show_line_range(struct line_range *lr, const char *module)
 	fp = fopen(lr->path, "r");
 	if (fp == NULL) {
 		pr_warning("Failed to open %s: %s\n", lr->path,
-			   strerror(errno));
+			   strerror_r(errno, sbuf, sizeof(sbuf)));
 		return -errno;
 	}
 	/* Skip to starting line number */
@@ -689,11 +698,11 @@ end:
 	return ret;
 }
 
-int show_line_range(struct line_range *lr, const char *module)
+int show_line_range(struct line_range *lr, const char *module, bool user)
 {
 	int ret;
 
-	ret = init_symbol_maps(false);
+	ret = init_symbol_maps(user);
 	if (ret < 0)
 		return ret;
 	ret = __show_line_range(lr, module);
@@ -768,13 +777,12 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	int i, ret = 0;
 	struct debuginfo *dinfo;
 
-	ret = init_symbol_maps(false);
+	ret = init_symbol_maps(pevs->uprobes);
 	if (ret < 0)
 		return ret;
 
-	dinfo = open_debuginfo(module);
+	dinfo = open_debuginfo(module, false);
 	if (!dinfo) {
-		pr_warning("Failed to open debuginfo file.\n");
 		ret = -ENOENT;
 		goto out;
 	}
@@ -815,7 +823,8 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 }
 
 int show_line_range(struct line_range *lr __maybe_unused,
-		    const char *module __maybe_unused)
+		    const char *module __maybe_unused,
+		    bool user __maybe_unused)
 {
 	pr_warning("Debuginfo-analysis is not supported.\n");
 	return -ENOSYS;
@@ -1405,8 +1414,7 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
 
 	return tmp - buf;
 error:
-	pr_debug("Failed to synthesize perf probe argument: %s\n",
-		 strerror(-ret));
+	pr_debug("Failed to synthesize perf probe argument: %d\n", ret);
 	return ret;
 }
 
@@ -1455,8 +1463,7 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 
 	return buf;
 error:
-	pr_debug("Failed to synthesize perf probe point: %s\n",
-		 strerror(-ret));
+	pr_debug("Failed to synthesize perf probe point: %d\n", ret);
 	free(buf);
 	return NULL;
 }
@@ -1780,10 +1787,11 @@ static void clear_probe_trace_event(struct probe_trace_event *tev)
 	memset(tev, 0, sizeof(*tev));
 }
 
-static void print_warn_msg(const char *file, bool is_kprobe)
+static void print_open_warning(int err, bool is_kprobe)
 {
+	char sbuf[STRERR_BUFSIZE];
 
-	if (errno == ENOENT) {
+	if (err == -ENOENT) {
 		const char *config;
 
 		if (!is_kprobe)
@@ -1791,25 +1799,43 @@ static void print_warn_msg(const char *file, bool is_kprobe)
 		else
 			config = "CONFIG_KPROBE_EVENTS";
 
-		pr_warning("%s file does not exist - please rebuild kernel"
-				" with %s.\n", file, config);
-	} else
-		pr_warning("Failed to open %s file: %s\n", file,
-				strerror(errno));
+		pr_warning("%cprobe_events file does not exist"
+			   " - please rebuild kernel with %s.\n",
+			   is_kprobe ? 'k' : 'u', config);
+	} else if (err == -ENOTSUP)
+		pr_warning("Debugfs is not mounted.\n");
+	else
+		pr_warning("Failed to open %cprobe_events: %s\n",
+			   is_kprobe ? 'k' : 'u',
+			   strerror_r(-err, sbuf, sizeof(sbuf)));
+}
+
+static void print_both_open_warning(int kerr, int uerr)
+{
+	/* Both kprobes and uprobes are disabled, warn it. */
+	if (kerr == -ENOTSUP && uerr == -ENOTSUP)
+		pr_warning("Debugfs is not mounted.\n");
+	else if (kerr == -ENOENT && uerr == -ENOENT)
+		pr_warning("Please rebuild kernel with CONFIG_KPROBE_EVENTS "
+			   "or/and CONFIG_UPROBE_EVENTS.\n");
+	else {
+		char sbuf[STRERR_BUFSIZE];
+		pr_warning("Failed to open kprobe events: %s.\n",
+			   strerror_r(-kerr, sbuf, sizeof(sbuf)));
+		pr_warning("Failed to open uprobe events: %s.\n",
+			   strerror_r(-uerr, sbuf, sizeof(sbuf)));
+	}
 }
 
-static int open_probe_events(const char *trace_file, bool readwrite,
-				bool is_kprobe)
+static int open_probe_events(const char *trace_file, bool readwrite)
 {
 	char buf[PATH_MAX];
 	const char *__debugfs;
 	int ret;
 
 	__debugfs = debugfs_find_mountpoint();
-	if (__debugfs == NULL) {
-		pr_warning("Debugfs is not mounted.\n");
-		return -ENOENT;
-	}
+	if (__debugfs == NULL)
+		return -ENOTSUP;
 
 	ret = e_snprintf(buf, PATH_MAX, "%s/%s", __debugfs, trace_file);
 	if (ret >= 0) {
@@ -1820,19 +1846,19 @@ static int open_probe_events(const char *trace_file, bool readwrite,
 			ret = open(buf, O_RDONLY, 0);
 
 		if (ret < 0)
-			print_warn_msg(buf, is_kprobe);
+			ret = -errno;
 	}
 	return ret;
 }
 
 static int open_kprobe_events(bool readwrite)
 {
-	return open_probe_events("tracing/kprobe_events", readwrite, true);
+	return open_probe_events("tracing/kprobe_events", readwrite);
 }
 
 static int open_uprobe_events(bool readwrite)
 {
-	return open_probe_events("tracing/uprobe_events", readwrite, false);
+	return open_probe_events("tracing/uprobe_events", readwrite);
 }
 
 /* Get raw string list of current kprobe_events  or uprobe_events */
@@ -1857,7 +1883,7 @@ static struct strlist *get_probe_trace_command_rawlist(int fd)
 			p[idx] = '\0';
 		ret = strlist__add(sl, buf);
 		if (ret < 0) {
-			pr_debug("strlist__add failed: %s\n", strerror(-ret));
+			pr_debug("strlist__add failed (%d)\n", ret);
 			strlist__delete(sl);
 			return NULL;
 		}
@@ -1916,7 +1942,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 
 	rawlist = get_probe_trace_command_rawlist(fd);
 	if (!rawlist)
-		return -ENOENT;
+		return -ENOMEM;
 
 	strlist__for_each(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
@@ -1940,27 +1966,34 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 /* List up current perf-probe events */
 int show_perf_probe_events(void)
 {
-	int fd, ret;
+	int kp_fd, up_fd, ret;
 
 	setup_pager();
-	fd = open_kprobe_events(false);
-
-	if (fd < 0)
-		return fd;
 
 	ret = init_symbol_maps(false);
 	if (ret < 0)
 		return ret;
 
-	ret = __show_perf_probe_events(fd, true);
-	close(fd);
+	kp_fd = open_kprobe_events(false);
+	if (kp_fd >= 0) {
+		ret = __show_perf_probe_events(kp_fd, true);
+		close(kp_fd);
+		if (ret < 0)
+			goto out;
+	}
 
-	fd = open_uprobe_events(false);
-	if (fd >= 0) {
-		ret = __show_perf_probe_events(fd, false);
-		close(fd);
+	up_fd = open_uprobe_events(false);
+	if (kp_fd < 0 && up_fd < 0) {
+		print_both_open_warning(kp_fd, up_fd);
+		ret = kp_fd;
+		goto out;
 	}
 
+	if (up_fd >= 0) {
+		ret = __show_perf_probe_events(up_fd, false);
+		close(up_fd);
+	}
+out:
 	exit_symbol_maps();
 	return ret;
 }
@@ -1976,6 +2009,8 @@ static struct strlist *get_probe_trace_event_names(int fd, bool include_group)
 
 	memset(&tev, 0, sizeof(tev));
 	rawlist = get_probe_trace_command_rawlist(fd);
+	if (!rawlist)
+		return NULL;
 	sl = strlist__new(true, NULL);
 	strlist__for_each(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
@@ -2005,6 +2040,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
 {
 	int ret = 0;
 	char *buf = synthesize_probe_trace_command(tev);
+	char sbuf[STRERR_BUFSIZE];
 
 	if (!buf) {
 		pr_debug("Failed to synthesize probe trace event.\n");
@@ -2016,7 +2052,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
 		ret = write(fd, buf, strlen(buf));
 		if (ret <= 0)
 			pr_warning("Failed to write event: %s\n",
-				   strerror(errno));
+				   strerror_r(errno, sbuf, sizeof(sbuf)));
 	}
 	free(buf);
 	return ret;
@@ -2030,7 +2066,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 	/* Try no suffix */
 	ret = e_snprintf(buf, len, "%s", base);
 	if (ret < 0) {
-		pr_debug("snprintf() failed: %s\n", strerror(-ret));
+		pr_debug("snprintf() failed: %d\n", ret);
 		return ret;
 	}
 	if (!strlist__has_entry(namelist, buf))
@@ -2046,7 +2082,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 	for (i = 1; i < MAX_EVENT_INDEX; i++) {
 		ret = e_snprintf(buf, len, "%s_%d", base, i);
 		if (ret < 0) {
-			pr_debug("snprintf() failed: %s\n", strerror(-ret));
+			pr_debug("snprintf() failed: %d\n", ret);
 			return ret;
 		}
 		if (!strlist__has_entry(namelist, buf))
@@ -2075,8 +2111,11 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	else
 		fd = open_kprobe_events(true);
 
-	if (fd < 0)
+	if (fd < 0) {
+		print_open_warning(fd, !pev->uprobes);
 		return fd;
+	}
+
 	/* Get current event names */
 	namelist = get_probe_trace_event_names(fd, false);
 	if (!namelist) {
@@ -2408,7 +2447,8 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
 	printf("Removed event: %s\n", ent->s);
 	return 0;
 error:
-	pr_warning("Failed to delete event: %s\n", strerror(-ret));
+	pr_warning("Failed to delete event: %s\n",
+		   strerror_r(-ret, buf, sizeof(buf)));
 	return ret;
 }
 
@@ -2449,15 +2489,18 @@ int del_perf_probe_events(struct strlist *dellist)
 
 	/* Get current event names */
 	kfd = open_kprobe_events(true);
-	if (kfd < 0)
-		return kfd;
+	if (kfd >= 0)
+		namelist = get_probe_trace_event_names(kfd, true);
 
-	namelist = get_probe_trace_event_names(kfd, true);
 	ufd = open_uprobe_events(true);
-
 	if (ufd >= 0)
 		unamelist = get_probe_trace_event_names(ufd, true);
 
+	if (kfd < 0 && ufd < 0) {
+		print_both_open_warning(kfd, ufd);
+		goto error;
+	}
+
 	if (namelist == NULL && unamelist == NULL)
 		goto error;
 
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 776c9347a3b6..e01e9943139f 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -128,7 +128,8 @@ extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
 				 bool force_add);
 extern int del_perf_probe_events(struct strlist *dellist);
 extern int show_perf_probe_events(void);
-extern int show_line_range(struct line_range *lr, const char *module);
+extern int show_line_range(struct line_range *lr, const char *module,
+			   bool user);
 extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
 			       int max_probe_points, const char *module,
 			       struct strfilter *filter, bool externs);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index dca9145d704c..c7918f83b300 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -281,6 +281,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 	struct probe_trace_arg_ref **ref_ptr = &tvar->ref;
 	Dwarf_Die type;
 	char buf[16];
+	char sbuf[STRERR_BUFSIZE];
 	int bsize, boffs, total;
 	int ret;
 
@@ -367,7 +368,7 @@ formatted:
 		if (ret >= 16)
 			ret = -E2BIG;
 		pr_warning("Failed to convert variable type: %s\n",
-			   strerror(-ret));
+			   strerror_r(-ret, sbuf, sizeof(sbuf)));
 		return ret;
 	}
 	tvar->type = strdup(buf);
@@ -608,14 +609,18 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
 		return -EINVAL;
 	}
 
-	/* Get an appropriate symbol from symtab */
-	symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+	symbol = dwarf_diename(sp_die);
 	if (!symbol) {
-		pr_warning("Failed to find symbol at 0x%lx\n",
-			   (unsigned long)paddr);
-		return -ENOENT;
+		/* Try to get the symbol name from symtab */
+		symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL);
+		if (!symbol) {
+			pr_warning("Failed to find symbol at 0x%lx\n",
+				   (unsigned long)paddr);
+			return -ENOENT;
+		}
+		eaddr = sym.st_value;
 	}
-	tp->offset = (unsigned long)(paddr - sym.st_value);
+	tp->offset = (unsigned long)(paddr - eaddr);
 	tp->address = (unsigned long)paddr;
 	tp->symbol = strdup(symbol);
 	if (!tp->symbol)
@@ -779,10 +784,12 @@ static int find_lazy_match_lines(struct intlist *list,
 	size_t line_len;
 	ssize_t len;
 	int count = 0, linenum = 1;
+	char sbuf[STRERR_BUFSIZE];
 
 	fp = fopen(fname, "r");
 	if (!fp) {
-		pr_warning("Failed to open %s: %s\n", fname, strerror(errno));
+		pr_warning("Failed to open %s: %s\n", fname,
+			   strerror_r(errno, sbuf, sizeof(sbuf)));
 		return -errno;
 	}
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 12aa9b0d0ba1..3dda85ca50c1 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -736,7 +736,7 @@ static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist,
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout))
 		return NULL;
 
-	n = poll(evlist->pollfd, evlist->nr_fds, timeout);
+	n = perf_evlist__poll(evlist, timeout);
 	if (n < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
 		return NULL;
@@ -753,9 +753,9 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
         PyObject *list = PyList_New(0);
 	int i;
 
-	for (i = 0; i < evlist->nr_fds; ++i) {
+	for (i = 0; i < evlist->pollfd.nr; ++i) {
 		PyObject *file;
-		FILE *fp = fdopen(evlist->pollfd[i].fd, "r");
+		FILE *fp = fdopen(evlist->pollfd.entries[i].fd, "r");
 
 		if (fp == NULL)
 			goto free_list;
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index fe8079edbdc1..cf69325b985f 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -14,6 +14,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 	struct perf_evsel *evsel;
 	unsigned long flags = perf_event_open_cloexec_flag();
 	int err = -EAGAIN, fd;
+	static pid_t pid = -1;
 
 	evlist = perf_evlist__new();
 	if (!evlist)
@@ -24,14 +25,22 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 
 	evsel = perf_evlist__first(evlist);
 
-	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags);
-	if (fd < 0)
-		goto out_delete;
+	while (1) {
+		fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
+		if (fd < 0) {
+			if (pid == -1 && errno == EACCES) {
+				pid = 0;
+				continue;
+			}
+			goto out_delete;
+		}
+		break;
+	}
 	close(fd);
 
 	fn(evsel);
 
-	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags);
+	fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
 	if (fd < 0) {
 		if (errno == EINVAL)
 			err = -EINVAL;
@@ -47,7 +56,7 @@ out_delete:
 
 static bool perf_probe_api(setup_probe_fn_t fn)
 {
-	const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL};
+	const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
 	struct cpu_map *cpus;
 	int cpu, ret, i = 0;
 
@@ -106,7 +115,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 
 	evlist__for_each(evlist, evsel) {
 		perf_evsel__config(evsel, opts);
-		if (!evsel->idx && use_comm_exec)
+		if (evsel->tracking && use_comm_exec)
 			evsel->attr.comm_exec = 1;
 	}
 
@@ -201,6 +210,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
 	struct perf_evsel *evsel;
 	int err, fd, cpu;
 	bool ret = false;
+	pid_t pid = -1;
 
 	temp_evlist = perf_evlist__new();
 	if (!temp_evlist)
@@ -221,12 +231,20 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
 		cpu = evlist->cpus->map[0];
 	}
 
-	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1,
-				 perf_event_open_cloexec_flag());
-	if (fd >= 0) {
-		close(fd);
-		ret = true;
+	while (1) {
+		fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1,
+					 perf_event_open_cloexec_flag());
+		if (fd < 0) {
+			if (pid == -1 && errno == EACCES) {
+				pid = 0;
+				continue;
+			}
+			goto out_delete;
+		}
+		break;
 	}
+	close(fd);
+	ret = true;
 
 out_delete:
 	perf_evlist__delete(temp_evlist);
diff --git a/tools/perf/util/run-command.c b/tools/perf/util/run-command.c
index da8e9b285f51..34622b53e733 100644
--- a/tools/perf/util/run-command.c
+++ b/tools/perf/util/run-command.c
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "run-command.h"
 #include "exec_cmd.h"
+#include "debug.h"
 
 static inline void close_pair(int fd[2])
 {
@@ -19,6 +20,7 @@ int start_command(struct child_process *cmd)
 {
 	int need_in, need_out, need_err;
 	int fdin[2], fdout[2], fderr[2];
+	char sbuf[STRERR_BUFSIZE];
 
 	/*
 	 * In case of errors we must keep the promise to close FDs
@@ -99,7 +101,7 @@ int start_command(struct child_process *cmd)
 
 		if (cmd->dir && chdir(cmd->dir))
 			die("exec %s: cd to %s failed (%s)", cmd->argv[0],
-			    cmd->dir, strerror(errno));
+			    cmd->dir, strerror_r(errno, sbuf, sizeof(sbuf)));
 		if (cmd->env) {
 			for (; *cmd->env; cmd->env++) {
 				if (strchr(*cmd->env, '='))
@@ -153,6 +155,8 @@ int start_command(struct child_process *cmd)
 
 static int wait_or_whine(pid_t pid)
 {
+	char sbuf[STRERR_BUFSIZE];
+
 	for (;;) {
 		int status, code;
 		pid_t waiting = waitpid(pid, &status, 0);
@@ -160,7 +164,8 @@ static int wait_or_whine(pid_t pid)
 		if (waiting < 0) {
 			if (errno == EINTR)
 				continue;
-			error("waitpid failed (%s)", strerror(errno));
+			error("waitpid failed (%s)",
+			      strerror_r(errno, sbuf, sizeof(sbuf)));
 			return -ERR_RUN_COMMAND_WAITPID;
 		}
 		if (waiting != pid)
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b2dba9c0a3a1..0a01bac4ce02 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -432,6 +432,11 @@ error:
 	return err;
 }
 
+static int perl_flush_script(void)
+{
+	return 0;
+}
+
 /*
  * Stop trace script
  */
@@ -633,6 +638,7 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile)
 struct scripting_ops perl_scripting_ops = {
 	.name = "Perl",
 	.start_script = perl_start_script,
+	.flush_script = perl_flush_script,
 	.stop_script = perl_stop_script,
 	.process_event = perl_process_event,
 	.generate_script = perl_generate_script,
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cbce2545da45..56ba07cce549 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -73,6 +73,35 @@ static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObj
 	Py_DECREF(val);
 }
 
+static PyObject *get_handler(const char *handler_name)
+{
+	PyObject *handler;
+
+	handler = PyDict_GetItemString(main_dict, handler_name);
+	if (handler && !PyCallable_Check(handler))
+		return NULL;
+	return handler;
+}
+
+static void call_object(PyObject *handler, PyObject *args, const char *die_msg)
+{
+	PyObject *retval;
+
+	retval = PyObject_CallObject(handler, args);
+	if (retval == NULL)
+		handler_call_die(die_msg);
+	Py_DECREF(retval);
+}
+
+static void try_call_object(const char *handler_name, PyObject *args)
+{
+	PyObject *handler;
+
+	handler = get_handler(handler_name);
+	if (handler)
+		call_object(handler, args, handler_name);
+}
+
 static void define_value(enum print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
@@ -80,7 +109,7 @@ static void define_value(enum print_arg_type field_type,
 			 const char *field_str)
 {
 	const char *handler_name = "define_flag_value";
-	PyObject *handler, *t, *retval;
+	PyObject *t;
 	unsigned long long value;
 	unsigned n = 0;
 
@@ -98,13 +127,7 @@ static void define_value(enum print_arg_type field_type,
 	PyTuple_SetItem(t, n++, PyInt_FromLong(value));
 	PyTuple_SetItem(t, n++, PyString_FromString(field_str));
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && PyCallable_Check(handler)) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
-	}
+	try_call_object(handler_name, t);
 
 	Py_DECREF(t);
 }
@@ -127,7 +150,7 @@ static void define_field(enum print_arg_type field_type,
 			 const char *delim)
 {
 	const char *handler_name = "define_flag_field";
-	PyObject *handler, *t, *retval;
+	PyObject *t;
 	unsigned n = 0;
 
 	if (field_type == PRINT_SYMBOL)
@@ -145,13 +168,7 @@ static void define_field(enum print_arg_type field_type,
 	if (field_type == PRINT_FLAGS)
 		PyTuple_SetItem(t, n++, PyString_FromString(delim));
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && PyCallable_Check(handler)) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
-	}
+	try_call_object(handler_name, t);
 
 	Py_DECREF(t);
 }
@@ -362,7 +379,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct thread *thread,
 				      struct addr_location *al)
 {
-	PyObject *handler, *retval, *context, *t, *obj, *callchain;
+	PyObject *handler, *context, *t, *obj, *callchain;
 	PyObject *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
@@ -387,9 +404,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
 	sprintf(handler_name, "%s__%s", event->system, event->name);
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && !PyCallable_Check(handler))
-		handler = NULL;
+	handler = get_handler(handler_name);
 	if (!handler) {
 		dict = PyDict_New();
 		if (!dict)
@@ -450,19 +465,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		Py_FatalError("error resizing Python tuple");
 
 	if (handler) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
+		call_object(handler, t, handler_name);
 	} else {
-		handler = PyDict_GetItemString(main_dict, "trace_unhandled");
-		if (handler && PyCallable_Check(handler)) {
-
-			retval = PyObject_CallObject(handler, t);
-			if (retval == NULL)
-				handler_call_die("trace_unhandled");
-			Py_DECREF(retval);
-		}
+		try_call_object("trace_unhandled", t);
 		Py_DECREF(dict);
 	}
 
@@ -474,7 +479,7 @@ static void python_process_general_event(struct perf_sample *sample,
 					 struct thread *thread,
 					 struct addr_location *al)
 {
-	PyObject *handler, *retval, *t, *dict, *callchain, *dict_sample;
+	PyObject *handler, *t, *dict, *callchain, *dict_sample;
 	static char handler_name[64];
 	unsigned n = 0;
 
@@ -496,8 +501,8 @@ static void python_process_general_event(struct perf_sample *sample,
 
 	snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (!handler || !PyCallable_Check(handler))
+	handler = get_handler(handler_name);
+	if (!handler)
 		goto exit;
 
 	pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
@@ -539,10 +544,7 @@ static void python_process_general_event(struct perf_sample *sample,
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	retval = PyObject_CallObject(handler, t);
-	if (retval == NULL)
-		handler_call_die(handler_name);
-	Py_DECREF(retval);
+	call_object(handler, t, handler_name);
 exit:
 	Py_DECREF(dict);
 	Py_DECREF(t);
@@ -566,36 +568,24 @@ static void python_process_event(union perf_event *event __maybe_unused,
 
 static int run_start_sub(void)
 {
-	PyObject *handler, *retval;
-	int err = 0;
-
 	main_module = PyImport_AddModule("__main__");
 	if (main_module == NULL)
 		return -1;
 	Py_INCREF(main_module);
 
 	main_dict = PyModule_GetDict(main_module);
-	if (main_dict == NULL) {
-		err = -1;
+	if (main_dict == NULL)
 		goto error;
-	}
 	Py_INCREF(main_dict);
 
-	handler = PyDict_GetItemString(main_dict, "trace_begin");
-	if (handler == NULL || !PyCallable_Check(handler))
-		goto out;
+	try_call_object("trace_begin", NULL);
 
-	retval = PyObject_CallObject(handler, NULL);
-	if (retval == NULL)
-		handler_call_die("trace_begin");
+	return 0;
 
-	Py_DECREF(retval);
-	return err;
 error:
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
-out:
-	return err;
+	return -1;
 }
 
 /*
@@ -649,28 +639,23 @@ error:
 	return err;
 }
 
+static int python_flush_script(void)
+{
+	return 0;
+}
+
 /*
  * Stop trace script
  */
 static int python_stop_script(void)
 {
-	PyObject *handler, *retval;
-	int err = 0;
+	try_call_object("trace_end", NULL);
 
-	handler = PyDict_GetItemString(main_dict, "trace_end");
-	if (handler == NULL || !PyCallable_Check(handler))
-		goto out;
-
-	retval = PyObject_CallObject(handler, NULL);
-	if (retval == NULL)
-		handler_call_die("trace_end");
-	Py_DECREF(retval);
-out:
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
 	Py_Finalize();
 
-	return err;
+	return 0;
 }
 
 static int python_generate_script(struct pevent *pevent, const char *outfile)
@@ -843,6 +828,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 struct scripting_ops python_scripting_ops = {
 	.name = "Python",
 	.start_script = python_start_script,
+	.flush_script = python_flush_script,
 	.stop_script = python_stop_script,
 	.process_event = python_process_event,
 	.generate_script = python_generate_script,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 88dfef70c13d..883406f4b381 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,7 @@
 #include "util.h"
 #include "cpumap.h"
 #include "perf_regs.h"
+#include "asm/bug.h"
 
 static int perf_session__open(struct perf_session *session)
 {
@@ -66,6 +67,25 @@ static void perf_session__destroy_kernel_maps(struct perf_session *session)
 	machines__destroy_kernel_maps(&session->machines);
 }
 
+static bool perf_session__has_comm_exec(struct perf_session *session)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->attr.comm_exec)
+			return true;
+	}
+
+	return false;
+}
+
+static void perf_session__set_comm_exec(struct perf_session *session)
+{
+	bool comm_exec = perf_session__has_comm_exec(session);
+
+	machines__set_comm_exec(&session->machines, comm_exec);
+}
+
 struct perf_session *perf_session__new(struct perf_data_file *file,
 				       bool repipe, struct perf_tool *tool)
 {
@@ -75,9 +95,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 		goto out;
 
 	session->repipe = repipe;
-	INIT_LIST_HEAD(&session->ordered_samples.samples);
-	INIT_LIST_HEAD(&session->ordered_samples.sample_cache);
-	INIT_LIST_HEAD(&session->ordered_samples.to_free);
+	ordered_events__init(&session->ordered_events);
 	machines__init(&session->machines);
 
 	if (file) {
@@ -91,6 +109,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 				goto out_close;
 
 			perf_session__set_id_hdr_size(session);
+			perf_session__set_comm_exec(session);
 		}
 	}
 
@@ -100,13 +119,13 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 		 * kernel MMAP event, in perf_event__process_mmap().
 		 */
 		if (perf_session__create_kernel_maps(session) < 0)
-			goto out_delete;
+			pr_warning("Cannot read kernel map\n");
 	}
 
 	if (tool && tool->ordering_requires_timestamps &&
-	    tool->ordered_samples && !perf_evlist__sample_id_all(session->evlist)) {
+	    tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
 		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
-		tool->ordered_samples = false;
+		tool->ordered_events = false;
 	}
 
 	return session;
@@ -238,7 +257,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	if (tool->build_id == NULL)
 		tool->build_id = process_finished_round_stub;
 	if (tool->finished_round == NULL) {
-		if (tool->ordered_samples)
+		if (tool->ordered_events)
 			tool->finished_round = process_finished_round;
 		else
 			tool->finished_round = process_finished_round_stub;
@@ -444,87 +463,6 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
-struct sample_queue {
-	u64			timestamp;
-	u64			file_offset;
-	union perf_event	*event;
-	struct list_head	list;
-};
-
-static void perf_session_free_sample_buffers(struct perf_session *session)
-{
-	struct ordered_samples *os = &session->ordered_samples;
-
-	while (!list_empty(&os->to_free)) {
-		struct sample_queue *sq;
-
-		sq = list_entry(os->to_free.next, struct sample_queue, list);
-		list_del(&sq->list);
-		free(sq);
-	}
-}
-
-static int perf_session_deliver_event(struct perf_session *session,
-				      union perf_event *event,
-				      struct perf_sample *sample,
-				      struct perf_tool *tool,
-				      u64 file_offset);
-
-static int flush_sample_queue(struct perf_session *s,
-		       struct perf_tool *tool)
-{
-	struct ordered_samples *os = &s->ordered_samples;
-	struct list_head *head = &os->samples;
-	struct sample_queue *tmp, *iter;
-	struct perf_sample sample;
-	u64 limit = os->next_flush;
-	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
-	bool show_progress = limit == ULLONG_MAX;
-	struct ui_progress prog;
-	int ret;
-
-	if (!tool->ordered_samples || !limit)
-		return 0;
-
-	if (show_progress)
-		ui_progress__init(&prog, os->nr_samples, "Processing time ordered events...");
-
-	list_for_each_entry_safe(iter, tmp, head, list) {
-		if (session_done())
-			return 0;
-
-		if (iter->timestamp > limit)
-			break;
-
-		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
-		if (ret)
-			pr_err("Can't parse sample, err = %d\n", ret);
-		else {
-			ret = perf_session_deliver_event(s, iter->event, &sample, tool,
-							 iter->file_offset);
-			if (ret)
-				return ret;
-		}
-
-		os->last_flush = iter->timestamp;
-		list_del(&iter->list);
-		list_add(&iter->list, &os->sample_cache);
-		os->nr_samples--;
-
-		if (show_progress)
-			ui_progress__update(&prog, 1);
-	}
-
-	if (list_empty(head)) {
-		os->last_sample = NULL;
-	} else if (last_ts <= limit) {
-		os->last_sample =
-			list_entry(head->prev, struct sample_queue, list);
-	}
-
-	return 0;
-}
-
 /*
  * When perf record finishes a pass on every buffers, it records this pseudo
  * event.
@@ -568,99 +506,43 @@ static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event __maybe_unused,
 				  struct perf_session *session)
 {
-	int ret = flush_sample_queue(session, tool);
-	if (!ret)
-		session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
-
-	return ret;
-}
-
-/* The queue is ordered by time */
-static void __queue_event(struct sample_queue *new, struct perf_session *s)
-{
-	struct ordered_samples *os = &s->ordered_samples;
-	struct sample_queue *sample = os->last_sample;
-	u64 timestamp = new->timestamp;
-	struct list_head *p;
-
-	++os->nr_samples;
-	os->last_sample = new;
-
-	if (!sample) {
-		list_add(&new->list, &os->samples);
-		os->max_timestamp = timestamp;
-		return;
-	}
-
-	/*
-	 * last_sample might point to some random place in the list as it's
-	 * the last queued event. We expect that the new event is close to
-	 * this.
-	 */
-	if (sample->timestamp <= timestamp) {
-		while (sample->timestamp <= timestamp) {
-			p = sample->list.next;
-			if (p == &os->samples) {
-				list_add_tail(&new->list, &os->samples);
-				os->max_timestamp = timestamp;
-				return;
-			}
-			sample = list_entry(p, struct sample_queue, list);
-		}
-		list_add_tail(&new->list, &sample->list);
-	} else {
-		while (sample->timestamp > timestamp) {
-			p = sample->list.prev;
-			if (p == &os->samples) {
-				list_add(&new->list, &os->samples);
-				return;
-			}
-			sample = list_entry(p, struct sample_queue, list);
-		}
-		list_add(&new->list, &sample->list);
-	}
+	return ordered_events__flush(session, tool, OE_FLUSH__ROUND);
 }
 
-#define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct sample_queue))
-
 int perf_session_queue_event(struct perf_session *s, union perf_event *event,
-				    struct perf_sample *sample, u64 file_offset)
+			     struct perf_tool *tool, struct perf_sample *sample,
+			     u64 file_offset)
 {
-	struct ordered_samples *os = &s->ordered_samples;
-	struct list_head *sc = &os->sample_cache;
+	struct ordered_events *oe = &s->ordered_events;
 	u64 timestamp = sample->time;
-	struct sample_queue *new;
+	struct ordered_event *new;
 
 	if (!timestamp || timestamp == ~0ULL)
 		return -ETIME;
 
-	if (timestamp < s->ordered_samples.last_flush) {
-		printf("Warning: Timestamp below last timeslice flush\n");
-		return -EINVAL;
+	if (timestamp < oe->last_flush) {
+		WARN_ONCE(1, "Timestamp below last timeslice flush\n");
+
+		pr_oe_time(timestamp,      "out of order event");
+		pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n",
+			   oe->last_flush_type);
+
+		/* We could get out of order messages after forced flush. */
+		if (oe->last_flush_type != OE_FLUSH__HALF)
+			return -EINVAL;
 	}
 
-	if (!list_empty(sc)) {
-		new = list_entry(sc->next, struct sample_queue, list);
-		list_del(&new->list);
-	} else if (os->sample_buffer) {
-		new = os->sample_buffer + os->sample_buffer_idx;
-		if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
-			os->sample_buffer = NULL;
-	} else {
-		os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
-		if (!os->sample_buffer)
-			return -ENOMEM;
-		list_add(&os->sample_buffer->list, &os->to_free);
-		os->sample_buffer_idx = 2;
-		new = os->sample_buffer + 1;
+	new = ordered_events__new(oe, timestamp);
+	if (!new) {
+		ordered_events__flush(s, tool, OE_FLUSH__HALF);
+		new = ordered_events__new(oe, timestamp);
 	}
 
-	new->timestamp = timestamp;
+	if (!new)
+		return -ENOMEM;
+
 	new->file_offset = file_offset;
 	new->event = event;
-
-	__queue_event(new, s);
-
 	return 0;
 }
 
@@ -920,11 +802,10 @@ perf_session__deliver_sample(struct perf_session *session,
 					    &sample->read.one, machine);
 }
 
-static int perf_session_deliver_event(struct perf_session *session,
-				      union perf_event *event,
-				      struct perf_sample *sample,
-				      struct perf_tool *tool,
-				      u64 file_offset)
+int perf_session__deliver_event(struct perf_session *session,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_tool *tool, u64 file_offset)
 {
 	struct perf_evsel *evsel;
 	struct machine *machine;
@@ -1005,8 +886,10 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	switch (event->header.type) {
 	case PERF_RECORD_HEADER_ATTR:
 		err = tool->attr(tool, event, &session->evlist);
-		if (err == 0)
+		if (err == 0) {
 			perf_session__set_id_hdr_size(session);
+			perf_session__set_comm_exec(session);
+		}
 		return err;
 	case PERF_RECORD_HEADER_EVENT_TYPE:
 		/*
@@ -1036,6 +919,61 @@ static void event_swap(union perf_event *event, bool sample_id_all)
 		swap(event, sample_id_all);
 }
 
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+			     void *buf, size_t buf_sz,
+			     union perf_event **event_ptr,
+			     struct perf_sample *sample)
+{
+	union perf_event *event;
+	size_t hdr_sz, rest;
+	int fd;
+
+	if (session->one_mmap && !session->header.needs_swap) {
+		event = file_offset - session->one_mmap_offset +
+			session->one_mmap_addr;
+		goto out_parse_sample;
+	}
+
+	if (perf_data_file__is_pipe(session->file))
+		return -1;
+
+	fd = perf_data_file__fd(session->file);
+	hdr_sz = sizeof(struct perf_event_header);
+
+	if (buf_sz < hdr_sz)
+		return -1;
+
+	if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
+	    readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+		return -1;
+
+	event = (union perf_event *)buf;
+
+	if (session->header.needs_swap)
+		perf_event_header__bswap(&event->header);
+
+	if (event->header.size < hdr_sz)
+		return -1;
+
+	rest = event->header.size - hdr_sz;
+
+	if (readn(fd, &buf, rest) != (ssize_t)rest)
+		return -1;
+
+	if (session->header.needs_swap)
+		event_swap(event, perf_evlist__sample_id_all(session->evlist));
+
+out_parse_sample:
+
+	if (sample && event->header.type < PERF_RECORD_USER_TYPE_START &&
+	    perf_evlist__parse_sample(session->evlist, event, sample))
+		return -1;
+
+	*event_ptr = event;
+
+	return 0;
+}
+
 static s64 perf_session__process_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
@@ -1062,15 +1000,15 @@ static s64 perf_session__process_event(struct perf_session *session,
 	if (ret)
 		return ret;
 
-	if (tool->ordered_samples) {
-		ret = perf_session_queue_event(session, event, &sample,
+	if (tool->ordered_events) {
+		ret = perf_session_queue_event(session, event, tool, &sample,
 					       file_offset);
 		if (ret != -ETIME)
 			return ret;
 	}
 
-	return perf_session_deliver_event(session, event, &sample, tool,
-					  file_offset);
+	return perf_session__deliver_event(session, event, &sample, tool,
+					   file_offset);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1222,12 +1160,11 @@ more:
 		goto more;
 done:
 	/* do the final flush for ordered samples */
-	session->ordered_samples.next_flush = ULLONG_MAX;
-	err = flush_sample_queue(session, tool);
+	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
 out_err:
 	free(buf);
 	perf_session__warn_about_errors(session, tool);
-	perf_session_free_sample_buffers(session);
+	ordered_events__free(&session->ordered_events);
 	return err;
 }
 
@@ -1368,12 +1305,11 @@ more:
 
 out:
 	/* do the final flush for ordered samples */
-	session->ordered_samples.next_flush = ULLONG_MAX;
-	err = flush_sample_queue(session, tool);
+	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
 out_err:
 	ui_progress__finish();
 	perf_session__warn_about_errors(session, tool);
-	perf_session_free_sample_buffers(session);
+	ordered_events__free(&session->ordered_events);
 	session->one_mmap = false;
 	return err;
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0321013bd9fd..ffb440462008 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -9,26 +9,13 @@
 #include "symbol.h"
 #include "thread.h"
 #include "data.h"
+#include "ordered-events.h"
 #include <linux/rbtree.h>
 #include <linux/perf_event.h>
 
-struct sample_queue;
 struct ip_callchain;
 struct thread;
 
-struct ordered_samples {
-	u64			last_flush;
-	u64			next_flush;
-	u64			max_timestamp;
-	struct list_head	samples;
-	struct list_head	sample_cache;
-	struct list_head	to_free;
-	struct sample_queue	*sample_buffer;
-	struct sample_queue	*last_sample;
-	int			sample_buffer_idx;
-	unsigned int		nr_samples;
-};
-
 struct perf_session {
 	struct perf_header	header;
 	struct machines		machines;
@@ -39,7 +26,7 @@ struct perf_session {
 	bool			one_mmap;
 	void			*one_mmap_addr;
 	u64			one_mmap_offset;
-	struct ordered_samples	ordered_samples;
+	struct ordered_events	ordered_events;
 	struct perf_data_file	*file;
 };
 
@@ -58,6 +45,11 @@ void perf_session__delete(struct perf_session *session);
 
 void perf_event_header__bswap(struct perf_event_header *hdr);
 
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+			     void *buf, size_t buf_sz,
+			     union perf_event **event_ptr,
+			     struct perf_sample *sample);
+
 int __perf_session__process_events(struct perf_session *session,
 				   u64 data_offset, u64 data_size, u64 size,
 				   struct perf_tool *tool);
@@ -65,10 +57,16 @@ int perf_session__process_events(struct perf_session *session,
 				 struct perf_tool *tool);
 
 int perf_session_queue_event(struct perf_session *s, union perf_event *event,
-			     struct perf_sample *sample, u64 file_offset);
+			     struct perf_tool *tool, struct perf_sample *sample,
+			     u64 file_offset);
 
 void perf_tool__fill_defaults(struct perf_tool *tool);
 
+int perf_session__deliver_event(struct perf_session *session,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_tool *tool, u64 file_offset);
+
 int perf_session__resolve_callchain(struct perf_session *session,
 				    struct perf_evsel *evsel,
 				    struct thread *thread,
@@ -128,5 +126,5 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 
 extern volatile int session_done;
 
-#define session_done()	(*(volatile int *)(&session_done))
+#define session_done()	ACCESS_ONCE(session_done)
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 14e5a039bc45..289df9d1e65a 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -70,12 +70,14 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
 	const char *comm = thread__comm_str(he->thread);
-	return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
-			       comm ?: "", he->thread->tid);
+
+	width = max(7U, width) - 6;
+	return repsep_snprintf(bf, size, "%5d:%-*.*s", he->thread->tid,
+			       width, width, comm ?: "");
 }
 
 struct sort_entry sort_thread = {
-	.se_header	= "Command:  Pid",
+	.se_header	= "  Pid:Command",
 	.se_cmp		= sort__thread_cmp,
 	.se_snprintf	= hist_entry__thread_snprintf,
 	.se_width_idx	= HISTC_THREAD,
@@ -106,7 +108,7 @@ sort__comm_sort(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf,
 				     size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm));
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, comm__str(he->comm));
 }
 
 struct sort_entry sort_comm = {
@@ -152,10 +154,10 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf,
 	if (map && map->dso) {
 		const char *dso_name = !verbose ? map->dso->short_name :
 			map->dso->long_name;
-		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
+		return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name);
 	}
 
-	return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, "[unknown]");
 }
 
 static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
@@ -257,7 +259,10 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 				       width - ret, "");
 	}
 
-	return ret;
+	if (ret > width)
+		bf[width] = '\0';
+
+	return width;
 }
 
 static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
@@ -302,10 +307,9 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
-					size_t size,
-					unsigned int width __maybe_unused)
+					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%s", he->srcline);
+	return repsep_snprintf(bf, size, "%*.*-s", width, width, he->srcline);
 }
 
 struct sort_entry sort_srcline = {
@@ -332,7 +336,7 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*s", width,
+	return repsep_snprintf(bf, size, "%-*.*s", width, width,
 			      he->parent ? he->parent->name : "[other]");
 }
 
@@ -354,7 +358,7 @@ sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%*d", width, he->cpu);
+	return repsep_snprintf(bf, size, "%*.*d", width, width, he->cpu);
 }
 
 struct sort_entry sort_cpu = {
@@ -484,7 +488,7 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
 	else if (he->branch_info->flags.mispred)
 		out = "Y";
 
-	return repsep_snprintf(bf, size, "%-*s", width, out);
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, out);
 }
 
 /* --sort daddr_sym */
@@ -1194,7 +1198,7 @@ bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
 	return hse_a->se == hse_b->se;
 }
 
-void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 {
 	struct hpp_sort_entry *hse;
 
@@ -1202,20 +1206,21 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 		return;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	hists__new_col_len(hists, hse->se->se_width_idx,
-			   strlen(hse->se->se_header));
+	hists__new_col_len(hists, hse->se->se_width_idx, strlen(fmt->name));
 }
 
 static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 			      struct perf_evsel *evsel)
 {
 	struct hpp_sort_entry *hse;
-	size_t len;
+	size_t len = fmt->user_len;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
 
-	return scnprintf(hpp->buf, hpp->size, "%-*s", len, hse->se->se_header);
+	if (!len)
+		len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+
+	return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
 }
 
 static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
@@ -1223,20 +1228,26 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
 			     struct perf_evsel *evsel)
 {
 	struct hpp_sort_entry *hse;
+	size_t len = fmt->user_len;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
-	return hists__col_len(&evsel->hists, hse->se->se_width_idx);
+	if (!len)
+		len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+
+	return len;
 }
 
 static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 			     struct hist_entry *he)
 {
 	struct hpp_sort_entry *hse;
-	size_t len;
+	size_t len = fmt->user_len;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	len = hists__col_len(he->hists, hse->se->se_width_idx);
+
+	if (!len)
+		len = hists__col_len(he->hists, hse->se->se_width_idx);
 
 	return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
 }
@@ -1253,6 +1264,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 	}
 
 	hse->se = sd->entry;
+	hse->hpp.name = sd->entry->se_header;
 	hse->hpp.header = __sort__hpp_header;
 	hse->hpp.width = __sort__hpp_width;
 	hse->hpp.entry = __sort__hpp_entry;
@@ -1265,6 +1277,8 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 	INIT_LIST_HEAD(&hse->hpp.list);
 	INIT_LIST_HEAD(&hse->hpp.sort_list);
 	hse->hpp.elide = false;
+	hse->hpp.len = 0;
+	hse->hpp.user_len = 0;
 
 	return hse;
 }
@@ -1432,14 +1446,49 @@ static const char *get_default_sort_order(void)
 	return default_sort_orders[sort__mode];
 }
 
+static int setup_sort_order(void)
+{
+	char *new_sort_order;
+
+	/*
+	 * Append '+'-prefixed sort order to the default sort
+	 * order string.
+	 */
+	if (!sort_order || is_strict_order(sort_order))
+		return 0;
+
+	if (sort_order[1] == '\0') {
+		error("Invalid --sort key: `+'");
+		return -EINVAL;
+	}
+
+	/*
+	 * We allocate new sort_order string, but we never free it,
+	 * because it's checked over the rest of the code.
+	 */
+	if (asprintf(&new_sort_order, "%s,%s",
+		     get_default_sort_order(), sort_order + 1) < 0) {
+		error("Not enough memory to set up --sort");
+		return -ENOMEM;
+	}
+
+	sort_order = new_sort_order;
+	return 0;
+}
+
 static int __setup_sorting(void)
 {
 	char *tmp, *tok, *str;
-	const char *sort_keys = sort_order;
+	const char *sort_keys;
 	int ret = 0;
 
+	ret = setup_sort_order();
+	if (ret)
+		return ret;
+
+	sort_keys = sort_order;
 	if (sort_keys == NULL) {
-		if (field_order) {
+		if (is_strict_order(field_order)) {
 			/*
 			 * If user specified field order but no sort order,
 			 * we'll honor it and not add default sort orders.
@@ -1625,23 +1674,36 @@ static void reset_dimensions(void)
 		memory_sort_dimensions[i].taken = 0;
 }
 
+bool is_strict_order(const char *order)
+{
+	return order && (*order != '+');
+}
+
 static int __setup_output_field(void)
 {
-	char *tmp, *tok, *str;
-	int ret = 0;
+	char *tmp, *tok, *str, *strp;
+	int ret = -EINVAL;
 
 	if (field_order == NULL)
 		return 0;
 
 	reset_dimensions();
 
-	str = strdup(field_order);
+	strp = str = strdup(field_order);
 	if (str == NULL) {
 		error("Not enough memory to setup output fields");
 		return -ENOMEM;
 	}
 
-	for (tok = strtok_r(str, ", ", &tmp);
+	if (!is_strict_order(field_order))
+		strp++;
+
+	if (!strlen(strp)) {
+		error("Invalid --fields key: `+'");
+		goto out;
+	}
+
+	for (tok = strtok_r(strp, ", ", &tmp);
 			tok; tok = strtok_r(NULL, ", ", &tmp)) {
 		ret = output_field_add(tok);
 		if (ret == -EINVAL) {
@@ -1653,6 +1715,7 @@ static int __setup_output_field(void)
 		}
 	}
 
+out:
 	free(str);
 	return ret;
 }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 041f0c9cea2b..c03e4ff8beff 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -218,4 +218,5 @@ void perf_hpp__set_elide(int idx, bool elide);
 
 int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 
+bool is_strict_order(const char *order);
 #endif	/* __PERF_SORT_H */
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 2553e5b55b89..d87767f76903 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -9,78 +9,48 @@
  */
 s64 perf_atoll(const char *str)
 {
-	unsigned int i;
-	s64 length = -1, unit = 1;
+	s64 length;
+	char *p;
+	char c;
 
 	if (!isdigit(str[0]))
 		goto out_err;
 
-	for (i = 1; i < strlen(str); i++) {
-		switch (str[i]) {
-		case 'B':
-		case 'b':
-			break;
-		case 'K':
-			if (str[i + 1] != 'B')
-				goto out_err;
-			else
-				goto kilo;
-		case 'k':
-			if (str[i + 1] != 'b')
-				goto out_err;
-kilo:
-			unit = K;
-			break;
-		case 'M':
-			if (str[i + 1] != 'B')
-				goto out_err;
-			else
-				goto mega;
-		case 'm':
-			if (str[i + 1] != 'b')
+	length = strtoll(str, &p, 10);
+	switch (c = *p++) {
+		case 'b': case 'B':
+			if (*p)
 				goto out_err;
-mega:
-			unit = K * K;
+		case '\0':
+			return length;
+		default:
+			goto out_err;
+		/* two-letter suffices */
+		case 'k': case 'K':
+			length <<= 10;
 			break;
-		case 'G':
-			if (str[i + 1] != 'B')
-				goto out_err;
-			else
-				goto giga;
-		case 'g':
-			if (str[i + 1] != 'b')
-				goto out_err;
-giga:
-			unit = K * K * K;
+		case 'm': case 'M':
+			length <<= 20;
 			break;
-		case 'T':
-			if (str[i + 1] != 'B')
-				goto out_err;
-			else
-				goto tera;
-		case 't':
-			if (str[i + 1] != 'b')
-				goto out_err;
-tera:
-			unit = K * K * K * K;
+		case 'g': case 'G':
+			length <<= 30;
 			break;
-		case '\0':	/* only specified figures */
-			unit = 1;
+		case 't': case 'T':
+			length <<= 40;
 			break;
-		default:
-			if (!isdigit(str[i]))
-				goto out_err;
-			break;
-		}
 	}
-
-	length = atoll(str) * unit;
-	goto out;
+	/* we want the cases to match */
+	if (islower(c)) {
+		if (strcmp(p, "b") != 0)
+			goto out_err;
+	} else {
+		if (strcmp(p, "B") != 0)
+			goto out_err;
+	}
+	return length;
 
 out_err:
-	length = -1;
-out:
-	return length;
+	return -1;
 }
 
 /*
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index d75349979e65..1e23a5bfb044 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,7 @@
 #include <inttypes.h>
 
 #include "symbol.h"
+#include "machine.h"
 #include "vdso.h"
 #include <symbol/kallsyms.h>
 #include "debug.h"
@@ -680,6 +681,11 @@ static u64 ref_reloc(struct kmap *kmap)
 	return 0;
 }
 
+static bool want_demangle(bool is_kernel_sym)
+{
+	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
+}
+
 int dso__load_sym(struct dso *dso, struct map *map,
 		  struct symsrc *syms_ss, struct symsrc *runtime_ss,
 		  symbol_filter_t filter, int kmodule)
@@ -712,6 +718,14 @@ int dso__load_sym(struct dso *dso, struct map *map,
 		symbols__delete(&dso->symbols[map->type]);
 
 	if (!syms_ss->symtab) {
+		/*
+		 * If the vmlinux is stripped, fail so we will fall back
+		 * to using kallsyms. The vmlinux runtime symbols aren't
+		 * of much use.
+		 */
+		if (dso->kernel)
+			goto out_elf_end;
+
 		syms_ss->symtab  = syms_ss->dynsym;
 		syms_ss->symshdr = syms_ss->dynshdr;
 	}
@@ -736,7 +750,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	if (symstrs == NULL)
 		goto out_elf_end;
 
-	sec_strndx = elf_getscn(elf, ehdr.e_shstrndx);
+	sec_strndx = elf_getscn(runtime_ss->elf, runtime_ss->ehdr.e_shstrndx);
 	if (sec_strndx == NULL)
 		goto out_elf_end;
 
@@ -916,7 +930,11 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				}
 				curr_dso->symtab_type = dso->symtab_type;
 				map_groups__insert(kmap->kmaps, curr_map);
-				dsos__add(&dso->node, curr_dso);
+				/*
+				 * The new DSO should go to the kernel DSOS
+				 */
+				dsos__add(&map->groups->machine->kernel_dsos,
+					  curr_dso);
 				dso__set_loaded(curr_dso, map->type);
 			} else
 				curr_dso = curr_map->dso;
@@ -938,9 +956,12 @@ new_symbol:
 		 * DWARF DW_compile_unit has this, but we don't always have access
 		 * to it...
 		 */
-		if (symbol_conf.demangle) {
-			demangled = bfd_demangle(NULL, elf_name,
-						 DMGL_PARAMS | DMGL_ANSI);
+		if (want_demangle(dso->kernel || kmodule)) {
+			int demangle_flags = DMGL_NO_OPTS;
+			if (verbose)
+				demangle_flags = DMGL_PARAMS | DMGL_ANSI;
+
+			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
 			if (demangled != NULL)
 				elf_name = demangled;
 		}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index eb06746b06b2..be84f7a9838b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -15,6 +15,7 @@
 #include "machine.h"
 #include "symbol.h"
 #include "strlist.h"
+#include "header.h"
 
 #include <elf.h>
 #include <limits.h>
@@ -33,6 +34,7 @@ struct symbol_conf symbol_conf = {
 	.try_vmlinux_path	= true,
 	.annotate_src		= true,
 	.demangle		= true,
+	.demangle_kernel	= false,
 	.cumulate_callchain	= true,
 	.show_hist_headers	= true,
 	.symfs			= "",
@@ -523,10 +525,15 @@ struct process_kallsyms_args {
 	struct dso *dso;
 };
 
+/*
+ * These are symbols in the kernel image, so make sure that
+ * sym is from a kernel DSO.
+ */
 bool symbol__is_idle(struct symbol *sym)
 {
 	const char * const idle_symbols[] = {
 		"cpu_idle",
+		"cpu_startup_entry",
 		"intel_idle",
 		"default_idle",
 		"native_safe_halt",
@@ -1468,8 +1475,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 	if (vmlinux[0] == '/')
 		snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux);
 	else
-		snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
-			 symbol_conf.symfs, vmlinux);
+		symbol__join_symfs(symfs_vmlinux, vmlinux);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 		symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
@@ -1745,12 +1751,13 @@ static void vmlinux_path__exit(void)
 	zfree(&vmlinux_path);
 }
 
-static int vmlinux_path__init(void)
+static int vmlinux_path__init(struct perf_session_env *env)
 {
 	struct utsname uts;
 	char bf[PATH_MAX];
+	char *kernel_version;
 
-	vmlinux_path = malloc(sizeof(char *) * 5);
+	vmlinux_path = malloc(sizeof(char *) * 6);
 	if (vmlinux_path == NULL)
 		return -1;
 
@@ -1763,25 +1770,37 @@ static int vmlinux_path__init(void)
 		goto out_fail;
 	++vmlinux_path__nr_entries;
 
-	/* only try running kernel version if no symfs was given */
+	/* only try kernel version if no symfs was given */
 	if (symbol_conf.symfs[0] != 0)
 		return 0;
 
-	if (uname(&uts) < 0)
-		return -1;
+	if (env) {
+		kernel_version = env->os_release;
+	} else {
+		if (uname(&uts) < 0)
+			goto out_fail;
 
-	snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release);
+		kernel_version = uts.release;
+	}
+
+	snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", kernel_version);
 	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
 		goto out_fail;
 	++vmlinux_path__nr_entries;
-	snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", uts.release);
+	snprintf(bf, sizeof(bf), "/usr/lib/debug/boot/vmlinux-%s",
+		 kernel_version);
+	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
+	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
+		goto out_fail;
+        ++vmlinux_path__nr_entries;
+	snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version);
 	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
 		goto out_fail;
 	++vmlinux_path__nr_entries;
 	snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux",
-		 uts.release);
+		 kernel_version);
 	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
 		goto out_fail;
@@ -1827,7 +1846,7 @@ static bool symbol__read_kptr_restrict(void)
 	return value;
 }
 
-int symbol__init(void)
+int symbol__init(struct perf_session_env *env)
 {
 	const char *symfs;
 
@@ -1842,7 +1861,7 @@ int symbol__init(void)
 		symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
 					  sizeof(struct symbol));
 
-	if (symbol_conf.try_vmlinux_path && vmlinux_path__init() < 0)
+	if (symbol_conf.try_vmlinux_path && vmlinux_path__init(env) < 0)
 		return -1;
 
 	if (symbol_conf.field_sep && *symbol_conf.field_sep == '.') {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index e7295e93cff9..bec4b7bd09de 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -13,6 +13,7 @@
 #include <libgen.h>
 #include "build-id.h"
 #include "event.h"
+#include "util.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 #include <libelf.h>
@@ -59,6 +60,7 @@ extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 #endif
 
 #ifndef DMGL_PARAMS
+#define DMGL_NO_OPTS     0              /* For readability... */
 #define DMGL_PARAMS      (1 << 0)       /* Include function args */
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
@@ -118,6 +120,7 @@ struct symbol_conf {
 			annotate_src,
 			event_group,
 			demangle,
+			demangle_kernel,
 			filter_relative,
 			show_hist_headers;
 	const char	*vmlinux_name,
@@ -143,6 +146,14 @@ struct symbol_conf {
 };
 
 extern struct symbol_conf symbol_conf;
+
+static inline int __symbol__join_symfs(char *bf, size_t size, const char *path)
+{
+	return path__join(bf, size, symbol_conf.symfs, path);
+}
+
+#define symbol__join_symfs(bf, path) __symbol__join_symfs(bf, sizeof(bf), path)
+
 extern int vmlinux_path__nr_entries;
 extern char **vmlinux_path;
 
@@ -253,7 +264,8 @@ int modules__parse(const char *filename, void *arg,
 int filename__read_debuglink(const char *filename, char *debuglink,
 			     size_t size);
 
-int symbol__init(void);
+struct perf_session_env;
+int symbol__init(struct perf_session_env *env);
 void symbol__exit(void);
 void symbol__elf_init(void);
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 12c7a253a63c..a9df7f2c6dc9 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -42,7 +42,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		snprintf(comm_str, 32, ":%d", tid);
-		comm = comm__new(comm_str, 0);
+		comm = comm__new(comm_str, 0, false);
 		free(comm_str);
 		if (!comm)
 			goto err_thread;
@@ -81,19 +81,33 @@ struct comm *thread__comm(const struct thread *thread)
 	return list_first_entry(&thread->comm_list, struct comm, list);
 }
 
+struct comm *thread__exec_comm(const struct thread *thread)
+{
+	struct comm *comm, *last = NULL;
+
+	list_for_each_entry(comm, &thread->comm_list, list) {
+		if (comm->exec)
+			return comm;
+		last = comm;
+	}
+
+	return last;
+}
+
 /* CHECKME: time should always be 0 if event aren't ordered */
-int thread__set_comm(struct thread *thread, const char *str, u64 timestamp)
+int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
+		       bool exec)
 {
 	struct comm *new, *curr = thread__comm(thread);
 	int err;
 
 	/* Override latest entry if it had no specific time coverage */
-	if (!curr->start) {
-		err = comm__override(curr, str, timestamp);
+	if (!curr->start && !curr->exec) {
+		err = comm__override(curr, str, timestamp, exec);
 		if (err)
 			return err;
 	} else {
-		new = comm__new(str, timestamp);
+		new = comm__new(str, timestamp, exec);
 		if (!new)
 			return -ENOMEM;
 		list_add(&new->list, &thread->comm_list);
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 716b7723cce2..8c75fa774706 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -38,9 +38,17 @@ static inline void thread__exited(struct thread *thread)
 	thread->dead = true;
 }
 
-int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp);
+int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
+		       bool exec);
+static inline int thread__set_comm(struct thread *thread, const char *comm,
+				   u64 timestamp)
+{
+	return __thread__set_comm(thread, comm, timestamp, false);
+}
+
 int thread__comm_len(struct thread *thread);
 struct comm *thread__comm(const struct thread *thread);
+struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
 void thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 4385816d3d49..f11636966a0f 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -40,7 +40,7 @@ struct perf_tool {
 	event_op2	tracing_data;
 	event_op2	finished_round,
 			build_id;
-	bool		ordered_samples;
+	bool		ordered_events;
 	bool		ordering_requires_timestamps;
 };
 
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 57aaccc1692e..5c9bdd1591a9 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -30,6 +30,11 @@
 
 struct scripting_context *scripting_context;
 
+static int flush_script_unsupported(void)
+{
+	return 0;
+}
+
 static int stop_script_unsupported(void)
 {
 	return 0;
@@ -74,6 +79,7 @@ static int python_generate_script_unsupported(struct pevent *pevent
 struct scripting_ops python_scripting_unsupported_ops = {
 	.name = "Python",
 	.start_script = python_start_script_unsupported,
+	.flush_script = flush_script_unsupported,
 	.stop_script = stop_script_unsupported,
 	.process_event = process_event_unsupported,
 	.generate_script = python_generate_script_unsupported,
@@ -137,6 +143,7 @@ static int perl_generate_script_unsupported(struct pevent *pevent
 struct scripting_ops perl_scripting_unsupported_ops = {
 	.name = "Perl",
 	.start_script = perl_start_script_unsupported,
+	.flush_script = flush_script_unsupported,
 	.stop_script = stop_script_unsupported,
 	.process_event = process_event_unsupported,
 	.generate_script = perl_generate_script_unsupported,
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 7b6d68688327..52aaa19e1eb1 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -64,6 +64,7 @@ struct perf_session;
 struct scripting_ops {
 	const char *name;
 	int (*start_script) (const char *script, int argc, const char **argv);
+	int (*flush_script) (void);
 	int (*stop_script) (void);
 	void (*process_event) (union perf_event *event,
 			       struct perf_sample *sample,
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index e52e7461911b..24e8d871b74e 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -13,6 +13,7 @@
 #include <limits.h>
 #include <byteswap.h>
 #include <linux/kernel.h>
+#include <unistd.h>
 
 /*
  * XXX We need to find a better place for these things...
@@ -282,6 +283,18 @@ void get_term_dimensions(struct winsize *ws)
 	ws->ws_col = 80;
 }
 
+void set_term_quiet_input(struct termios *old)
+{
+	struct termios tc;
+
+	tcgetattr(0, old);
+	tc = *old;
+	tc.c_lflag &= ~(ICANON | ECHO);
+	tc.c_cc[VMIN] = 0;
+	tc.c_cc[VTIME] = 0;
+	tcsetattr(0, TCSANOW, &tc);
+}
+
 static void set_tracing_events_path(const char *mountpoint)
 {
 	snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
@@ -443,6 +456,7 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep)
 	size_t size = 0, alloc_size = 0;
 	void *bf = NULL, *nbf;
 	int fd, n, err = 0;
+	char sbuf[STRERR_BUFSIZE];
 
 	fd = open(filename, O_RDONLY);
 	if (fd < 0)
@@ -463,8 +477,8 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep)
 		n = read(fd, bf + size, alloc_size - size);
 		if (n < 0) {
 			if (size) {
-				pr_warning("read failed %d: %s\n",
-					   errno, strerror(errno));
+				pr_warning("read failed %d: %s\n", errno,
+					 strerror_r(errno, sbuf, sizeof(sbuf)));
 				err = 0;
 			} else
 				err = -errno;
@@ -536,3 +550,39 @@ void mem_bswap_64(void *src, int byte_size)
 		++m;
 	}
 }
+
+bool find_process(const char *name)
+{
+	size_t len = strlen(name);
+	DIR *dir;
+	struct dirent *d;
+	int ret = -1;
+
+	dir = opendir(procfs__mountpoint());
+	if (!dir)
+		return -1;
+
+	/* Walk through the directory. */
+	while (ret && (d = readdir(dir)) != NULL) {
+		char path[PATH_MAX];
+		char *data;
+		size_t size;
+
+		if ((d->d_type != DT_DIR) ||
+		     !strcmp(".", d->d_name) ||
+		     !strcmp("..", d->d_name))
+			continue;
+
+		scnprintf(path, sizeof(path), "%s/%s/comm",
+			  procfs__mountpoint(), d->d_name);
+
+		if (filename__read_str(path, &data, &size))
+			continue;
+
+		ret = strncmp(name, data, len);
+		free(data);
+	}
+
+	closedir(dir);
+	return ret ? false : true;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 66864364ccb4..80bfdaa0e2a4 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -39,6 +39,8 @@
 
 #define _ALL_SOURCE 1
 #define _BSD_SOURCE 1
+/* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
+#define _DEFAULT_SOURCE 1
 #define HAS_BOOL
 
 #include <unistd.h>
@@ -64,16 +66,18 @@
 #include <regex.h>
 #include <utime.h>
 #include <sys/wait.h>
-#include <sys/poll.h>
+#include <poll.h>
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <inttypes.h>
+#include <linux/kernel.h>
 #include <linux/magic.h>
 #include <linux/types.h>
 #include <sys/ttydefaults.h>
 #include <api/fs/debugfs.h>
 #include <termios.h>
 #include <linux/bitops.h>
+#include <termios.h>
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
@@ -307,6 +311,7 @@ extern unsigned int page_size;
 extern int cacheline_size;
 
 void get_term_dimensions(struct winsize *ws);
+void set_term_quiet_input(struct termios *old);
 
 struct parse_tag {
 	char tag;
@@ -317,6 +322,21 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags);
 
 #define SRCLINE_UNKNOWN  ((char *) "??:0")
 
+static inline int path__join(char *bf, size_t size,
+			     const char *path1, const char *path2)
+{
+	return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2);
+}
+
+static inline int path__join3(char *bf, size_t size,
+			      const char *path1, const char *path2,
+			      const char *path3)
+{
+	return scnprintf(bf, size, "%s%s%s%s%s",
+			 path1, path1[0] ? "/" : "",
+			 path2, path2[0] ? "/" : "", path3);
+}
+
 struct dso;
 
 char *get_srcline(struct dso *dso, unsigned long addr);
@@ -330,4 +350,5 @@ void mem_bswap_64(void *src, int byte_size);
 void mem_bswap_32(void *src, int byte_size);
 
 const char *get_filename_for_perf_kvm(void);
+bool find_process(const char *name);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 55ab700f6ba5..bf1398180785 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -194,6 +194,7 @@ my $config_bisect_check;
 
 my $patchcheck_type;
 my $patchcheck_start;
+my $patchcheck_cherry;
 my $patchcheck_end;
 
 # set when a test is something other that just building or install
@@ -320,6 +321,7 @@ my %option_map = (
 
     "PATCHCHECK_TYPE"		=> \$patchcheck_type,
     "PATCHCHECK_START"		=> \$patchcheck_start,
+    "PATCHCHECK_CHERRY"		=> \$patchcheck_cherry,
     "PATCHCHECK_END"		=> \$patchcheck_end,
 );
 
@@ -1448,6 +1450,12 @@ sub wait_for_monitor {
 	}
     }
     print "** Monitor flushed **\n";
+
+    # if stop is defined but wasn't hit, return error
+    # used by reboot (which wants to see a reboot)
+    if (defined($stop) && !$booted) {
+	$bug = 1;
+    }
     return $bug;
 }
 
@@ -2336,15 +2344,17 @@ sub success {
 
 sub answer_bisect {
     for (;;) {
-	doprint "Pass or fail? [p/f]";
+	doprint "Pass, fail, or skip? [p/f/s]";
 	my $ans = <STDIN>;
 	chomp $ans;
 	if ($ans eq "p" || $ans eq "P") {
 	    return 1;
 	} elsif ($ans eq "f" || $ans eq "F") {
 	    return 0;
+	} elsif ($ans eq "s" || $ans eq "S") {
+	    return -1;
 	} else {
-	    print "Please answer 'P' or 'F'\n";
+	    print "Please answer 'p', 'f', or 's'\n";
 	}
     }
 }
@@ -2726,15 +2736,17 @@ sub bisect {
     run_command "git bisect start$start_files" or
 	dodie "could not start bisect";
 
-    run_command "git bisect good $good" or
-	dodie "could not set bisect good to $good";
-
-    run_git_bisect "git bisect bad $bad" or
-	dodie "could not set bisect bad to $bad";
-
     if (defined($replay)) {
 	run_command "git bisect replay $replay" or
 	    dodie "failed to run replay";
+    } else {
+
+	run_command "git bisect good $good" or
+	    dodie "could not set bisect good to $good";
+
+	run_git_bisect "git bisect bad $bad" or
+	    dodie "could not set bisect bad to $bad";
+
     }
 
     if (defined($start)) {
@@ -3181,9 +3193,16 @@ sub patchcheck {
 
     my $start = $patchcheck_start;
 
+    my $cherry = $patchcheck_cherry;
+    if (!defined($cherry)) {
+	$cherry = 0;
+    }
+
     my $end = "HEAD";
     if (defined($patchcheck_end)) {
 	$end = $patchcheck_end;
+    } elsif ($cherry) {
+	die "PATCHCHECK_END must be defined with PATCHCHECK_CHERRY\n";
     }
 
     # Get the true sha1's since we can use things like HEAD~3
@@ -3197,24 +3216,38 @@ sub patchcheck {
 	$type = "boot";
     }
 
-    open (IN, "git log --pretty=oneline $end|") or
-	dodie "could not get git list";
+    if ($cherry) {
+	open (IN, "git cherry -v $start $end|") or
+	    dodie "could not get git list";
+    } else {
+	open (IN, "git log --pretty=oneline $end|") or
+	    dodie "could not get git list";
+    }
 
     my @list;
 
     while (<IN>) {
 	chomp;
+	# git cherry adds a '+' we want to remove
+	s/^\+ //;
 	$list[$#list+1] = $_;
 	last if (/^$start/);
     }
     close(IN);
 
-    if ($list[$#list] !~ /^$start/) {
-	fail "SHA1 $start not found";
+    if (!$cherry) {
+	if ($list[$#list] !~ /^$start/) {
+	    fail "SHA1 $start not found";
+	}
+
+	# go backwards in the list
+	@list = reverse @list;
     }
 
-    # go backwards in the list
-    @list = reverse @list;
+    doprint("Going to test the following commits:\n");
+    foreach my $l (@list) {
+	doprint "$l\n";
+    }
 
     my $save_clean = $noclean;
     my %ignored_warnings;
diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf
index 911e45ad657a..6c58cd8bbbae 100644
--- a/tools/testing/ktest/sample.conf
+++ b/tools/testing/ktest/sample.conf
@@ -906,6 +906,16 @@
 #
 #  PATCHCHECK_END is the last patch to check (default HEAD)
 #
+#  PATCHCHECK_CHERRY if set to non zero, then git cherry will be
+#      performed against PATCHCHECK_START and PATCHCHECK_END. That is
+#
+#      git cherry ${PATCHCHECK_START} ${PATCHCHECK_END}
+#
+#      Then the changes found will be tested.
+#
+#      Note, PATCHCHECK_CHERRY requires PATCHCHECK_END to be defined.
+#      (default 0)
+#
 #  PATCHCHECK_TYPE is required and is the type of test to run:
 #      build, boot, test.
 #
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 36ff2e4c7b6f..45f145c6f843 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -14,6 +14,7 @@ TARGETS += powerpc
 TARGETS += user
 TARGETS += sysctl
 TARGETS += firmware
+TARGETS += ftrace
 
 TARGETS_HOTPLUG = cpu-hotplug
 TARGETS_HOTPLUG += memory-hotplug
diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile
new file mode 100644
index 000000000000..76cc9f156267
--- /dev/null
+++ b/tools/testing/selftests/ftrace/Makefile
@@ -0,0 +1,7 @@
+all:
+
+run_tests:
+	@/bin/sh ./ftracetest || echo "ftrace selftests: [FAIL]"
+
+clean:
+	rm -rf logs/*
diff --git a/tools/testing/selftests/ftrace/README b/tools/testing/selftests/ftrace/README
new file mode 100644
index 000000000000..182e76fa4b82
--- /dev/null
+++ b/tools/testing/selftests/ftrace/README
@@ -0,0 +1,82 @@
+Linux Ftrace Testcases
+
+This is a collection of testcases for ftrace tracing feature in the Linux
+kernel. Since ftrace exports interfaces via the debugfs, we just need
+shell scripts for testing. Feel free to add new test cases.
+
+Running the ftrace testcases
+============================
+
+At first, you need to be the root user to run this script.
+To run all testcases:
+
+  $ sudo ./ftracetest
+
+To run specific testcases:
+
+  # ./ftracetest test.d/basic3.tc
+
+Or you can also run testcases under given directory:
+
+  # ./ftracetest test.d/kprobe/
+
+Contributing new testcases
+==========================
+
+Copy test.d/template to your testcase (whose filename must have *.tc
+extension) and rewrite the test description line.
+
+ * The working directory of the script is <debugfs>/tracing/.
+
+ * Take care with side effects as the tests are run with root privilege.
+
+ * The tests should not run for a long period of time (more than 1 min.)
+   These are to be unit tests.
+
+ * You can add a directory for your testcases under test.d/ if needed.
+
+ * The test cases should run on dash (busybox shell) for testing on
+   minimal cross-build environments.
+
+ * Note that the tests are run with "set -e" (errexit) option. If any
+   command fails, the test will be terminated immediately.
+
+ * The tests can return some result codes instead of pass or fail by
+   using exit_unresolved, exit_untested, exit_unsupported and exit_xfail.
+
+Result code
+===========
+
+Ftracetest supports following result codes.
+
+ * PASS: The test succeeded as expected. The test which exits with 0 is
+         counted as passed test.
+
+ * FAIL: The test failed, but was expected to succeed. The test which exits
+         with !0 is counted as failed test.
+
+ * UNRESOLVED: The test produced unclear or intermidiate results.
+             for example, the test was interrupted
+                       or the test depends on a previous test, which failed.
+                       or the test was set up incorrectly
+             The test which is in above situation, must call exit_unresolved.
+
+ * UNTESTED: The test was not run, currently just a placeholder.
+             In this case, the test must call exit_untested.
+
+ * UNSUPPORTED: The test failed because of lack of feature.
+               In this case, the test must call exit_unsupported.
+
+ * XFAIL: The test failed, and was expected to fail.
+          To return XFAIL, call exit_xfail from the test.
+
+There are some sample test scripts for result code under samples/.
+You can also run samples as below:
+
+  # ./ftracetest samples/
+
+TODO
+====
+
+ * Fancy colored output :)
+
diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
new file mode 100755
index 000000000000..a8f81c782856
--- /dev/null
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -0,0 +1,253 @@
+#!/bin/sh
+
+# ftracetest - Ftrace test shell scripts
+#
+# Copyright (C) Hitachi Ltd., 2014
+#  Written by Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
+#
+# Released under the terms of the GPL v2.
+
+usage() { # errno [message]
+[ "$2" ] && echo $2
+echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]"
+echo " Options:"
+echo "		-h|--help  Show help message"
+echo "		-k|--keep  Keep passed test logs"
+echo "		-d|--debug Debug mode (trace all shell commands)"
+exit $1
+}
+
+errexit() { # message
+  echo "Error: $1" 1>&2
+  exit 1
+}
+
+# Ensuring user privilege
+if [ `id -u` -ne 0 ]; then
+  errexit "this must be run by root user"
+fi
+
+# Utilities
+absdir() { # file_path
+  (cd `dirname $1`; pwd)
+}
+
+abspath() {
+  echo `absdir $1`/`basename $1`
+}
+
+find_testcases() { #directory
+  echo `find $1 -name \*.tc`
+}
+
+parse_opts() { # opts
+  local OPT_TEST_CASES=
+  local OPT_TEST_DIR=
+
+  while [ "$1" ]; do
+    case "$1" in
+    --help|-h)
+      usage 0
+    ;;
+    --keep|-k)
+      KEEP_LOG=1
+      shift 1
+    ;;
+    --debug|-d)
+      DEBUG=1
+      shift 1
+    ;;
+    *.tc)
+      if [ -f "$1" ]; then
+        OPT_TEST_CASES="$OPT_TEST_CASES `abspath $1`"
+        shift 1
+      else
+        usage 1 "$1 is not a testcase"
+      fi
+      ;;
+    *)
+      if [ -d "$1" ]; then
+        OPT_TEST_DIR=`abspath $1`
+        OPT_TEST_CASES="$OPT_TEST_CASES `find_testcases $OPT_TEST_DIR`"
+        shift 1
+      else
+        usage 1 "Invalid option ($1)"
+      fi
+    ;;
+    esac
+  done
+  if [ "$OPT_TEST_CASES" ]; then
+    TEST_CASES=$OPT_TEST_CASES
+  fi
+}
+
+# Parameters
+DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' '`
+TRACING_DIR=$DEBUGFS_DIR/tracing
+TOP_DIR=`absdir $0`
+TEST_DIR=$TOP_DIR/test.d
+TEST_CASES=`find_testcases $TEST_DIR`
+LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/
+KEEP_LOG=0
+DEBUG=0
+# Parse command-line options
+parse_opts $*
+
+[ $DEBUG -ne 0 ] && set -x
+
+# Verify parameters
+if [ -z "$DEBUGFS_DIR" -o ! -d "$TRACING_DIR" ]; then
+  errexit "No ftrace directory found"
+fi
+
+# Preparing logs
+LOG_FILE=$LOG_DIR/ftracetest.log
+mkdir -p $LOG_DIR || errexit "Failed to make a log directory: $LOG_DIR"
+date > $LOG_FILE
+prlog() { # messages
+  echo "$@" | tee -a $LOG_FILE
+}
+catlog() { #file
+  cat $1 | tee -a $LOG_FILE
+}
+prlog "=== Ftrace unit tests ==="
+
+
+# Testcase management
+# Test result codes - Dejagnu extended code
+PASS=0	# The test succeeded.
+FAIL=1	# The test failed, but was expected to succeed.
+UNRESOLVED=2  # The test produced indeterminate results. (e.g. interrupted)
+UNTESTED=3    # The test was not run, currently just a placeholder.
+UNSUPPORTED=4 # The test failed because of lack of feature.
+XFAIL=5	# The test failed, and was expected to fail.
+
+# Accumulations
+PASSED_CASES=
+FAILED_CASES=
+UNRESOLVED_CASES=
+UNTESTED_CASES=
+UNSUPPORTED_CASES=
+XFAILED_CASES=
+UNDEFINED_CASES=
+TOTAL_RESULT=0
+
+CASENO=0
+testcase() { # testfile
+  CASENO=$((CASENO+1))
+  prlog -n "[$CASENO]"`grep "^#[ \t]*description:" $1 | cut -f2 -d:`
+}
+
+eval_result() { # retval sigval
+  local retval=$2
+  if [ $2 -eq 0 ]; then
+    test $1 -ne 0 && retval=$FAIL
+  fi
+  case $retval in
+    $PASS)
+      prlog "	[PASS]"
+      PASSED_CASES="$PASSED_CASES $CASENO"
+      return 0
+    ;;
+    $FAIL)
+      prlog "	[FAIL]"
+      FAILED_CASES="$FAILED_CASES $CASENO"
+      return 1 # this is a bug.
+    ;;
+    $UNRESOLVED)
+      prlog "	[UNRESOLVED]"
+      UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO"
+      return 1 # this is a kind of bug.. something happened.
+    ;;
+    $UNTESTED)
+      prlog "	[UNTESTED]"
+      UNTESTED_CASES="$UNTESTED_CASES $CASENO"
+      return 0
+    ;;
+    $UNSUPPORTED)
+      prlog "	[UNSUPPORTED]"
+      UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO"
+      return 1 # this is not a bug, but the result should be reported.
+    ;;
+    $XFAIL)
+      prlog "	[XFAIL]"
+      XFAILED_CASES="$XFAILED_CASES $CASENO"
+      return 0
+    ;;
+    *)
+      prlog "	[UNDEFINED]"
+      UNDEFINED_CASES="$UNDEFINED_CASES $CASENO"
+      return 1 # this must be a test bug
+    ;;
+  esac
+}
+
+# Signal handling for result codes
+SIG_RESULT=
+SIG_BASE=36	# Use realtime signals
+SIG_PID=$$
+
+SIG_UNRESOLVED=$((SIG_BASE + UNRESOLVED))
+exit_unresolved () {
+  kill -s $SIG_UNRESOLVED $SIG_PID
+  exit 0
+}
+trap 'SIG_RESULT=$UNRESOLVED' $SIG_UNRESOLVED
+
+SIG_UNTESTED=$((SIG_BASE + UNTESTED))
+exit_untested () {
+  kill -s $SIG_UNTESTED $SIG_PID
+  exit 0
+}
+trap 'SIG_RESULT=$UNTESTED' $SIG_UNTESTED
+
+SIG_UNSUPPORTED=$((SIG_BASE + UNSUPPORTED))
+exit_unsupported () {
+  kill -s $SIG_UNSUPPORTED $SIG_PID
+  exit 0
+}
+trap 'SIG_RESULT=$UNSUPPORTED' $SIG_UNSUPPORTED
+
+SIG_XFAIL=$((SIG_BASE + XFAIL))
+exit_xfail () {
+  kill -s $SIG_XFAIL $SIG_PID
+  exit 0
+}
+trap 'SIG_RESULT=$XFAIL' $SIG_XFAIL
+
+# Run one test case
+run_test() { # testfile
+  local testname=`basename $1`
+  local testlog=`mktemp --tmpdir=$LOG_DIR ${testname}-XXXXXX.log`
+  testcase $1
+  echo "execute: "$1 > $testlog
+  SIG_RESULT=0
+  # setup PID and PPID, $$ is not updated.
+  (cd $TRACING_DIR; read PID _ < /proc/self/stat ;
+   set -e; set -x; . $1) >> $testlog 2>&1
+  eval_result $? $SIG_RESULT
+  if [ $? -eq 0 ]; then
+    # Remove test log if the test was done as it was expected.
+    [ $KEEP_LOG -eq 0 ] && rm $testlog
+  else
+    catlog $testlog
+    TOTAL_RESULT=1
+  fi
+}
+
+# Main loop
+for t in $TEST_CASES; do
+  run_test $t
+done
+
+prlog ""
+prlog "# of passed: " `echo $PASSED_CASES | wc -w`
+prlog "# of failed: " `echo $FAILED_CASES | wc -w`
+prlog "# of unresolved: " `echo $UNRESOLVED_CASES | wc -w`
+prlog "# of untested: " `echo $UNTESTED_CASES | wc -w`
+prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w`
+prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w`
+prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w`
+
+# if no error, return 0
+exit $TOTAL_RESULT
diff --git a/tools/testing/selftests/ftrace/samples/fail.tc b/tools/testing/selftests/ftrace/samples/fail.tc
new file mode 100644
index 000000000000..15e35b956e05
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/fail.tc
@@ -0,0 +1,4 @@
+#!/bin/sh
+# description: failure-case example
+cat non-exist-file
+echo "this is not executed"
diff --git a/tools/testing/selftests/ftrace/samples/pass.tc b/tools/testing/selftests/ftrace/samples/pass.tc
new file mode 100644
index 000000000000..d01549370041
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/pass.tc
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: pass-case example
+return 0
diff --git a/tools/testing/selftests/ftrace/samples/unresolved.tc b/tools/testing/selftests/ftrace/samples/unresolved.tc
new file mode 100644
index 000000000000..41e99d3358d1
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/unresolved.tc
@@ -0,0 +1,4 @@
+#!/bin/sh
+# description: unresolved-case example
+trap exit_unresolved INT
+kill -INT $PID
diff --git a/tools/testing/selftests/ftrace/samples/unsupported.tc b/tools/testing/selftests/ftrace/samples/unsupported.tc
new file mode 100644
index 000000000000..45910ff13328
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/unsupported.tc
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: unsupported-case example
+exit_unsupported
diff --git a/tools/testing/selftests/ftrace/samples/untested.tc b/tools/testing/selftests/ftrace/samples/untested.tc
new file mode 100644
index 000000000000..35a45946ec60
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/untested.tc
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: untested-case example
+exit_untested
diff --git a/tools/testing/selftests/ftrace/samples/xfail.tc b/tools/testing/selftests/ftrace/samples/xfail.tc
new file mode 100644
index 000000000000..9dd395323259
--- /dev/null
+++ b/tools/testing/selftests/ftrace/samples/xfail.tc
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: xfail-case example
+cat non-exist-file || exit_xfail
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc
new file mode 100644
index 000000000000..9980ff14ae44
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc
@@ -0,0 +1,3 @@
+#!/bin/sh
+# description: Basic trace file check
+test -f README -a -f trace -a -f tracing_on -a -f trace_pipe
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc
new file mode 100644
index 000000000000..bf9a7b037924
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc
@@ -0,0 +1,7 @@
+#!/bin/sh
+# description: Basic test for tracers
+test -f available_tracers
+for t in `cat available_tracers`; do
+  echo $t > current_tracer
+done
+echo nop > current_tracer
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc
new file mode 100644
index 000000000000..bde6625d9785
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc
@@ -0,0 +1,8 @@
+#!/bin/sh
+# description: Basic trace clock test
+test -f trace_clock
+for c in `cat trace_clock | tr  -d \[\]`; do
+  echo $c > trace_clock
+  grep '\['$c'\]' trace_clock
+done
+echo local > trace_clock
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
new file mode 100644
index 000000000000..1b8b665ab2b3
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
@@ -0,0 +1,11 @@
+#!/bin/sh
+# description: Kprobe dynamic event - adding and removing
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+echo 0 > events/enable
+echo > kprobe_events
+echo p:myevent do_fork > kprobe_events
+grep myevent kprobe_events
+test -d events/kprobes/myevent
+echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
new file mode 100644
index 000000000000..b55c84003587
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
@@ -0,0 +1,13 @@
+#!/bin/sh
+# description: Kprobe dynamic event - busy event check
+
+[ -f kprobe_events ] || exit_unsupported
+
+echo 0 > events/enable
+echo > kprobe_events
+echo p:myevent do_fork > kprobe_events
+test -d events/kprobes/myevent
+echo 1 > events/kprobes/myevent/enable
+echo > kprobe_events && exit 1 # this must fail
+echo 0 > events/kprobes/myevent/enable
+echo > kprobe_events # this must succeed
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
new file mode 100644
index 000000000000..a603d3f8db7b
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -0,0 +1,16 @@
+#!/bin/sh
+# description: Kprobe dynamic event with arguments
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+echo 0 > events/enable
+echo > kprobe_events
+echo 'p:testprobe do_fork $stack $stack0 +0($stack)' > kprobe_events
+grep testprobe kprobe_events
+test -d events/kprobes/testprobe
+echo 1 > events/kprobes/testprobe/enable
+( echo "forked")
+echo 0 > events/kprobes/testprobe/enable
+echo "-:testprobe" >> kprobe_events
+test -d events/kprobes/testprobe && exit 1 || exit 0
+
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
new file mode 100644
index 000000000000..283c29e7f7c4
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -0,0 +1,15 @@
+#!/bin/sh
+# description: Kretprobe dynamic event with arguments
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+echo 0 > events/enable
+echo > kprobe_events
+echo 'r:testprobe2 do_fork $retval' > kprobe_events
+grep testprobe2 kprobe_events
+test -d events/kprobes/testprobe2
+echo 1 > events/kprobes/testprobe2/enable
+( echo "forked")
+echo 0 > events/kprobes/testprobe2/enable
+echo '-:testprobe2' >> kprobe_events
+test -d events/kprobes/testprobe2 && exit 1 || exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/template b/tools/testing/selftests/ftrace/test.d/template
new file mode 100644
index 000000000000..5448f7abad5f
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/template
@@ -0,0 +1,9 @@
+#!/bin/sh
+# description: %HERE DESCRIBE WHAT THIS DOES%
+# you have to add ".tc" extention for your testcase file
+# Note that all tests are run with "errexit" option.
+
+exit 0 # Return 0 if the test is passed, otherwise return !0
+# If the test could not run because of lack of feature, call exit_unsupported
+# If the test returned unclear results, call exit_unresolved
+# If the test is a dummy, or a placeholder, call exit_untested
diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile
index ad4ab01cd28f..b80cd10d53ba 100644
--- a/tools/testing/selftests/memfd/Makefile
+++ b/tools/testing/selftests/memfd/Makefile
@@ -1,38 +1,17 @@
-uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/)
-ifeq ($(ARCH),i386)
-	ARCH := x86
-endif
-ifeq ($(ARCH),x86_64)
-	ARCH := x86
-endif
-
 CFLAGS += -D_FILE_OFFSET_BITS=64
-CFLAGS += -I../../../../arch/x86/include/generated/uapi/
-CFLAGS += -I../../../../arch/x86/include/uapi/
 CFLAGS += -I../../../../include/uapi/
 CFLAGS += -I../../../../include/
 
 all:
-ifeq ($(ARCH),x86)
 	gcc $(CFLAGS) memfd_test.c -o memfd_test
-else
-	echo "Not an x86 target, can't build memfd selftest"
-endif
 
 run_tests: all
-ifeq ($(ARCH),x86)
 	gcc $(CFLAGS) memfd_test.c -o memfd_test
-endif
 	@./memfd_test || echo "memfd_test: [FAIL]"
 
 build_fuse:
-ifeq ($(ARCH),x86)
 	gcc $(CFLAGS) fuse_mnt.c `pkg-config fuse --cflags --libs` -o fuse_mnt
 	gcc $(CFLAGS) fuse_test.c -o fuse_test
-else
-	echo "Not an x86 target, can't build memfd selftest"
-endif
 
 run_fuse: build_fuse
 	@./run_fuse_test.sh || echo "fuse_test: [FAIL]"
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 3634c909b1b0..0b9eafb7ab7b 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -59,9 +59,9 @@ static void mfd_fail_new(const char *name, unsigned int flags)
 	}
 }
 
-static __u64 mfd_assert_get_seals(int fd)
+static unsigned int mfd_assert_get_seals(int fd)
 {
-	long r;
+	int r;
 
 	r = fcntl(fd, F_GET_SEALS);
 	if (r < 0) {
@@ -69,50 +69,48 @@ static __u64 mfd_assert_get_seals(int fd)
 		abort();
 	}
 
-	return r;
+	return (unsigned int)r;
 }
 
-static void mfd_assert_has_seals(int fd, __u64 seals)
+static void mfd_assert_has_seals(int fd, unsigned int seals)
 {
-	__u64 s;
+	unsigned int s;
 
 	s = mfd_assert_get_seals(fd);
 	if (s != seals) {
-		printf("%llu != %llu = GET_SEALS(%d)\n",
-		       (unsigned long long)seals, (unsigned long long)s, fd);
+		printf("%u != %u = GET_SEALS(%d)\n", seals, s, fd);
 		abort();
 	}
 }
 
-static void mfd_assert_add_seals(int fd, __u64 seals)
+static void mfd_assert_add_seals(int fd, unsigned int seals)
 {
-	long r;
-	__u64 s;
+	int r;
+	unsigned int s;
 
 	s = mfd_assert_get_seals(fd);
 	r = fcntl(fd, F_ADD_SEALS, seals);
 	if (r < 0) {
-		printf("ADD_SEALS(%d, %llu -> %llu) failed: %m\n",
-		       fd, (unsigned long long)s, (unsigned long long)seals);
+		printf("ADD_SEALS(%d, %u -> %u) failed: %m\n", fd, s, seals);
 		abort();
 	}
 }
 
-static void mfd_fail_add_seals(int fd, __u64 seals)
+static void mfd_fail_add_seals(int fd, unsigned int seals)
 {
-	long r;
-	__u64 s;
+	int r;
+	unsigned int s;
 
 	r = fcntl(fd, F_GET_SEALS);
 	if (r < 0)
 		s = 0;
 	else
-		s = r;
+		s = (unsigned int)r;
 
 	r = fcntl(fd, F_ADD_SEALS, seals);
 	if (r >= 0) {
-		printf("ADD_SEALS(%d, %llu -> %llu) didn't fail as expected\n",
-		       fd, (unsigned long long)s, (unsigned long long)seals);
+		printf("ADD_SEALS(%d, %u -> %u) didn't fail as expected\n",
+				fd, s, seals);
 		abort();
 	}
 }
@@ -205,7 +203,7 @@ static void mfd_fail_open(int fd, int flags, mode_t mode)
 	sprintf(buf, "/proc/self/fd/%d", fd);
 	r = open(buf, flags, mode);
 	if (r >= 0) {
-		printf("open(%s) didn't fail as expected\n");
+		printf("open(%s) didn't fail as expected\n", buf);
 		abort();
 	}
 }
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 74a78cedce37..f6ff90a76bd7 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -13,7 +13,7 @@ CFLAGS := -Wall -O2 -flto -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CUR
 
 export CC CFLAGS
 
-TARGETS = pmu copyloops mm tm
+TARGETS = pmu copyloops mm tm primitives
 
 endif
 
diff --git a/tools/testing/selftests/powerpc/primitives/Makefile b/tools/testing/selftests/powerpc/primitives/Makefile
new file mode 100644
index 000000000000..ea737ca01732
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/Makefile
@@ -0,0 +1,17 @@
+CFLAGS += -I$(CURDIR)
+
+PROGS := load_unaligned_zeropad
+
+all: $(PROGS)
+
+$(PROGS): ../harness.c
+
+run_tests: all
+	@-for PROG in $(PROGS); do \
+		./$$PROG; \
+	done;
+
+clean:
+	rm -f $(PROGS) *.o
+
+.PHONY: all run_tests clean
diff --git a/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h b/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h
new file mode 120000
index 000000000000..b14255e15a25
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h
@@ -0,0 +1 @@
+../.././../../../../arch/powerpc/include/asm/asm-compat.h
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h b/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h
diff --git a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c
new file mode 100644
index 000000000000..d1b647509596
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c
@@ -0,0 +1,147 @@
+/*
+ * Userspace test harness for load_unaligned_zeropad. Creates two
+ * pages and uses mprotect to prevent access to the second page and
+ * a SEGV handler that walks the exception tables and runs the fixup
+ * routine.
+ *
+ * The results are compared against a normal load that is that is
+ * performed while access to the second page is enabled via mprotect.
+ *
+ * Copyright (C) 2014 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <signal.h>
+#include <unistd.h>
+#include <sys/mman.h>
+
+#define FIXUP_SECTION ".ex_fixup"
+
+#include "word-at-a-time.h"
+
+#include "utils.h"
+
+
+static int page_size;
+static char *mem_region;
+
+static int protect_region(void)
+{
+	if (mprotect(mem_region + page_size, page_size, PROT_NONE)) {
+		perror("mprotect");
+		return 1;
+	}
+
+	return 0;
+}
+
+static int unprotect_region(void)
+{
+	if (mprotect(mem_region + page_size, page_size, PROT_READ|PROT_WRITE)) {
+		perror("mprotect");
+		return 1;
+	}
+
+	return 0;
+}
+
+extern char __start___ex_table[];
+extern char __stop___ex_table[];
+
+#if defined(__powerpc64__)
+#define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.gp_regs[PT_NIP]
+#elif defined(__powerpc__)
+#define UCONTEXT_NIA(UC)	(UC)->uc_mcontext.uc_regs->gregs[PT_NIP]
+#else
+#error implement UCONTEXT_NIA
+#endif
+
+static int segv_error;
+
+static void segv_handler(int signr, siginfo_t *info, void *ptr)
+{
+	ucontext_t *uc = (ucontext_t *)ptr;
+	unsigned long addr = (unsigned long)info->si_addr;
+	unsigned long *ip = &UCONTEXT_NIA(uc);
+	unsigned long *ex_p = (unsigned long *)__start___ex_table;
+
+	while (ex_p < (unsigned long *)__stop___ex_table) {
+		unsigned long insn, fixup;
+
+		insn = *ex_p++;
+		fixup = *ex_p++;
+
+		if (insn == *ip) {
+			*ip = fixup;
+			return;
+		}
+	}
+
+	printf("No exception table match for NIA %lx ADDR %lx\n", *ip, addr);
+	segv_error++;
+}
+
+static void setup_segv_handler(void)
+{
+	struct sigaction action;
+
+	memset(&action, 0, sizeof(action));
+	action.sa_sigaction = segv_handler;
+	action.sa_flags = SA_SIGINFO;
+	sigaction(SIGSEGV, &action, NULL);
+}
+
+static int do_one_test(char *p, int page_offset)
+{
+	unsigned long should;
+	unsigned long got;
+
+	FAIL_IF(unprotect_region());
+	should = *(unsigned long *)p;
+	FAIL_IF(protect_region());
+
+	got = load_unaligned_zeropad(p);
+
+	if (should != got)
+		printf("offset %u load_unaligned_zeropad returned 0x%lx, should be 0x%lx\n", page_offset, got, should);
+
+	return 0;
+}
+
+static int test_body(void)
+{
+	unsigned long i;
+
+	page_size = getpagesize();
+	mem_region = mmap(NULL, page_size * 2, PROT_READ|PROT_WRITE,
+		MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
+
+	FAIL_IF(mem_region == MAP_FAILED);
+
+	for (i = 0; i < page_size; i++)
+		mem_region[i] = i;
+
+	memset(mem_region+page_size, 0, page_size);
+
+	setup_segv_handler();
+
+	for (i = 0; i < page_size; i++)
+		FAIL_IF(do_one_test(mem_region+i, i));
+
+	FAIL_IF(segv_error);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_body, "load_unaligned_zeropad");
+}
diff --git a/tools/testing/selftests/powerpc/primitives/word-at-a-time.h b/tools/testing/selftests/powerpc/primitives/word-at-a-time.h
new file mode 120000
index 000000000000..eb74401b591f
--- /dev/null
+++ b/tools/testing/selftests/powerpc/primitives/word-at-a-time.h
@@ -0,0 +1 @@
+../../../../../arch/powerpc/include/asm/word-at-a-time.h
\ No newline at end of file
diff --git a/tools/testing/selftests/rcutorture/bin/config2frag.sh b/tools/testing/selftests/rcutorture/bin/config2frag.sh
index 9f9ffcd427d3..56f51ae13d73 100644..100755
--- a/tools/testing/selftests/rcutorture/bin/config2frag.sh
+++ b/tools/testing/selftests/rcutorture/bin/config2frag.sh
@@ -1,5 +1,5 @@
-#!/bin/sh
-# Usage: sh config2frag.sh < .config > configfrag
+#!/bin/bash
+# Usage: config2frag.sh < .config > configfrag
 #
 # Converts the "# CONFIG_XXX is not set" to "CONFIG_XXX=n" so that the
 # resulting file becomes a legitimate Kconfig fragment.
diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh
index d686537dd55c..eee31e261bf7 100755
--- a/tools/testing/selftests/rcutorture/bin/configcheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh
@@ -1,5 +1,5 @@
-#!/bin/sh
-# Usage: sh configcheck.sh .config .config-template
+#!/bin/bash
+# Usage: configcheck.sh .config .config-template
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index 9c3f3d39b934..15f1a17ca96e 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -1,6 +1,6 @@
-#!/bin/sh
+#!/bin/bash
 #
-# sh configinit.sh config-spec-file [ build output dir ]
+# Usage: configinit.sh config-spec-file [ build output dir ]
 #
 # Create a .config file from the spec file.  Run from the kernel source tree.
 # Exits with 0 if all went well, with 1 if all went well but the config
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index d01b865bb100..b325470c01b3 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -64,6 +64,26 @@ configfrag_boot_params () {
 	fi
 }
 
+# configfrag_boot_cpus bootparam-string config-fragment-file config-cpus
+#
+# Decreases number of CPUs based on any maxcpus= boot parameters specified.
+configfrag_boot_cpus () {
+	local bootargs="`configfrag_boot_params "$1" "$2"`"
+	local maxcpus
+	if echo "${bootargs}" | grep -q 'maxcpus=[0-9]'
+	then
+		maxcpus="`echo "${bootargs}" | sed -e 's/^.*maxcpus=\([0-9]*\).*$/\1/'`"
+		if test "$3" -gt "$maxcpus"
+		then
+			echo $maxcpus
+		else
+			echo $3
+		fi
+	else
+		echo $3
+	fi
+}
+
 # configfrag_hotplug_cpu config-fragment-file
 #
 # Returns 1 if the config fragment specifies hotplug CPU.
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 7c1e56b46de4..00cb0db2643d 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -2,7 +2,7 @@
 #
 # Build a kvm-ready Linux kernel from the tree in the current directory.
 #
-# Usage: sh kvm-build.sh config-template build-dir more-configs
+# Usage: kvm-build.sh config-template build-dir more-configs
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
index 7f1ff1a8fc4b..43f764098e50 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
@@ -2,7 +2,7 @@
 #
 # Analyze a given results directory for locktorture progress.
 #
-# Usage: sh kvm-recheck-lock.sh resdir
+# Usage: kvm-recheck-lock.sh resdir
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index 307c4b95f325..d6cc07fc137f 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -2,7 +2,7 @@
 #
 # Analyze a given results directory for rcutorture progress.
 #
-# Usage: sh kvm-recheck-rcu.sh resdir
+# Usage: kvm-recheck-rcu.sh resdir
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index 3f6c9b78d177..4f5b20f367a9 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -4,7 +4,7 @@
 # check the build and console output for errors.  Given a directory
 # containing results directories, this recursively checks them all.
 #
-# Usage: sh kvm-recheck.sh resdir ...
+# Usage: kvm-recheck.sh resdir ...
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 0f69dcbf9def..f6b2b4771b78 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -6,7 +6,7 @@
 # Execute this in the source tree.  Do not run it as a background task
 # because qemu does not seem to like that much.
 #
-# Usage: sh kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args
+# Usage: kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args
 #
 # qemu-args defaults to "-nographic", along with arguments specifying the
 #			number of CPUs and other options generated from
@@ -140,6 +140,7 @@ fi
 # Generate -smp qemu argument.
 qemu_args="-nographic $qemu_args"
 cpu_count=`configNR_CPUS.sh $config_template`
+cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"`
 vcpus=`identify_qemu_vcpus`
 if test $cpu_count -gt $vcpus
 then
@@ -214,7 +215,7 @@ then
 		fi
 		if test $kruntime -ge $((seconds + grace))
 		then
-			echo "!!! Hang at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
+			echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
 			kill -KILL $qemu_pid
 			break
 		fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 589e9c38413b..e527dc952eb0 100644..100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -7,7 +7,7 @@
 # Edit the definitions below to set the locations of the various directories,
 # as well as the test duration.
 #
-# Usage: sh kvm.sh [ options ]
+# Usage: kvm.sh [ options ]
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -188,7 +188,9 @@ for CF in $configs
 do
 	if test -f "$CONFIGFRAG/$kversion/$CF"
 	then
-		echo $CF `configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF` >> $T/cfgcpu
+		cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF`
+		cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$kversion/$CF" "$cpu_count"`
+		echo $CF $cpu_count >> $T/cfgcpu
 	else
 		echo "The --configs file $CF does not exist, terminating."
 		exit 1
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
index 543230951c38..499d1e598e42 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 #
 # Check the build output from an rcutorture run for goodness.
 # The "file" is a pathname on the local system, and "title" is
@@ -6,8 +6,7 @@
 #
 # The file must contain kernel build output.
 #
-# Usage:
-#	sh parse-build.sh file title
+# Usage: parse-build.sh file title
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 4185d4cab32e..f962ba4cf68b 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -1,11 +1,10 @@
-#!/bin/sh
+#!/bin/bash
 #
 # Check the console output from an rcutorture run for oopses.
 # The "file" is a pathname on the local system, and "title" is
 # a text string for error-message purposes.
 #
-# Usage:
-#	sh parse-console.sh file title
+# Usage: parse-console.sh file title
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -33,6 +32,10 @@ title="$2"
 
 . functions.sh
 
+if grep -Pq '\x00' < $file
+then
+	print_warning Console output contains nul bytes, old qemu still running?
+fi
 egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
 if test -s $T
 then
diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
index 3455560ab4e4..e3c5f0705696 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 #
 # Check the console output from a torture run for goodness.
 # The "file" is a pathname on the local system, and "title" is
@@ -7,8 +7,7 @@
 # The file must contain torture output, but can be interspersed
 # with other dmesg text, as in console-log output.
 #
-# Usage:
-#	sh parse-torture.sh file title
+# Usage: parse-torture.sh file title
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
index a061b22d1892..6910b7370761 100644
--- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
@@ -1 +1,4 @@
 LOCK01
+LOCK02
+LOCK03
+LOCK04
\ No newline at end of file
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK02 b/tools/testing/selftests/rcutorture/configs/lock/LOCK02
new file mode 100644
index 000000000000..1d1da1477fc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK02
@@ -0,0 +1,6 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot
new file mode 100644
index 000000000000..5aa44b4f1b51
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot
@@ -0,0 +1 @@
+locktorture.torture_type=mutex_lock
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK03 b/tools/testing/selftests/rcutorture/configs/lock/LOCK03
new file mode 100644
index 000000000000..1d1da1477fc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK03
@@ -0,0 +1,6 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot
new file mode 100644
index 000000000000..a67bbe0245c9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot
@@ -0,0 +1 @@
+locktorture.torture_type=rwsem_lock
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK04 b/tools/testing/selftests/rcutorture/configs/lock/LOCK04
new file mode 100644
index 000000000000..1d1da1477fc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK04
@@ -0,0 +1,6 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot
new file mode 100644
index 000000000000..48c04fe47fb4
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot
@@ -0,0 +1 @@
+locktorture.torture_type=rw_lock
diff --git a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
index 9746ea1cd6c7..252aae618984 100644
--- a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
@@ -38,6 +38,6 @@ per_version_boot_params () {
 	echo $1 `locktorture_param_onoff "$1" "$2"` \
 		locktorture.stat_interval=15 \
 		locktorture.shutdown_secs=$3 \
-		locktorture.locktorture_runnable=1 \
+		locktorture.torture_runnable=1 \
 		locktorture.verbose=1
 }
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
index cd3d29cb0a47..a3a1a05a2b5c 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST
@@ -11,3 +11,6 @@ SRCU-N
 SRCU-P
 TINY01
 TINY02
+TASKS01
+TASKS02
+TASKS03
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
new file mode 100644
index 000000000000..97f0a0b27ef7
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
@@ -0,0 +1,9 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_RCU=y
+CONFIG_TASKS_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot
new file mode 100644
index 000000000000..cd2a188eeb6d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
new file mode 100644
index 000000000000..696d2ea74d13
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
@@ -0,0 +1,5 @@
+CONFIG_SMP=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_TASKS_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot
new file mode 100644
index 000000000000..cd2a188eeb6d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
new file mode 100644
index 000000000000..9c60da5b5d1d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
@@ -0,0 +1,13 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_TASKS_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=y
+CONFIG_NO_HZ_FULL_ALL=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot
new file mode 100644
index 000000000000..cd2a188eeb6d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=tasks
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
index 063b7079c621..38e3895759dd 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -1,5 +1,4 @@
 CONFIG_SMP=y
-CONFIG_NR_CPUS=8
 CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
@@ -10,8 +9,7 @@ CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_FANOUT=8
-CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_MAXSMP=y
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ZERO=y
 CONFIG_DEBUG_LOCK_ALLOC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
index 0fc8a3428938..adc3abc82fb8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot
@@ -1 +1 @@
-rcutorture.torture_type=rcu_bh
+rcutorture.torture_type=rcu_bh maxcpus=8
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index ab6225506909..8f1017666aa7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -1,5 +1,6 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=16
+CONFIG_CPUMASK_OFFSTACK=y
 CONFIG_PREEMPT_NONE=y
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
@@ -7,7 +8,7 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
-CONFIG_NO_HZ_FULL_ALL=y
+CONFIG_NO_HZ_FULL_ALL=n
 CONFIG_NO_HZ_FULL_SYSIDLE=y
 CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot
new file mode 100644
index 000000000000..d44609937503
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot
@@ -0,0 +1 @@
+nohz_full=2-9
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
index 8977d8d31b19..ffb85ed786fa 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
@@ -51,7 +51,7 @@ per_version_boot_params () {
 		`rcutorture_param_n_barrier_cbs "$1"` \
 		rcutorture.stat_interval=15 \
 		rcutorture.shutdown_secs=$3 \
-		rcutorture.rcutorture_runnable=1 \
+		rcutorture.torture_runnable=1 \
 		rcutorture.test_no_idle_hz=1 \
 		rcutorture.verbose=1
 }
diff --git a/tools/testing/selftests/rcutorture/doc/initrd.txt b/tools/testing/selftests/rcutorture/doc/initrd.txt
index 49d134c25c04..4170e714f044 100644
--- a/tools/testing/selftests/rcutorture/doc/initrd.txt
+++ b/tools/testing/selftests/rcutorture/doc/initrd.txt
@@ -6,6 +6,7 @@ this case.  There are probably much better ways of doing this.
 That said, here are the commands:
 
 ------------------------------------------------------------------------
+cd tools/testing/selftests/rcutorture
 zcat /initrd.img > /tmp/initrd.img.zcat
 mkdir initrd
 cd initrd
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 3f94e1afd6cf..4c4b1f631ecf 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -3,6 +3,7 @@
 CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall
 BINARIES = hugepage-mmap hugepage-shm map_hugetlb thuge-gen hugetlbfstest
+BINARIES += transhuge-stress
 
 all: $(BINARIES)
 %: %.c
diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c
new file mode 100644
index 000000000000..fd7f1b4a96f9
--- /dev/null
+++ b/tools/testing/selftests/vm/transhuge-stress.c
@@ -0,0 +1,144 @@
+/*
+ * Stress test for transparent huge pages, memory compaction and migration.
+ *
+ * Authors: Konstantin Khlebnikov <koct9i@gmail.com>
+ *
+ * This is free and unencumbered software released into the public domain.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <err.h>
+#include <time.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/mman.h>
+
+#define PAGE_SHIFT 12
+#define HPAGE_SHIFT 21
+
+#define PAGE_SIZE (1 << PAGE_SHIFT)
+#define HPAGE_SIZE (1 << HPAGE_SHIFT)
+
+#define PAGEMAP_PRESENT(ent)	(((ent) & (1ull << 63)) != 0)
+#define PAGEMAP_PFN(ent)	((ent) & ((1ull << 55) - 1))
+
+int pagemap_fd;
+
+int64_t allocate_transhuge(void *ptr)
+{
+	uint64_t ent[2];
+
+	/* drop pmd */
+	if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE,
+				MAP_FIXED | MAP_ANONYMOUS |
+				MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr)
+		errx(2, "mmap transhuge");
+
+	if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE))
+		err(2, "MADV_HUGEPAGE");
+
+	/* allocate transparent huge page */
+	*(volatile void **)ptr = ptr;
+
+	if (pread(pagemap_fd, ent, sizeof(ent),
+			(uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent))
+		err(2, "read pagemap");
+
+	if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) &&
+	    PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) &&
+	    !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1)))
+		return PAGEMAP_PFN(ent[0]);
+
+	return -1;
+}
+
+int main(int argc, char **argv)
+{
+	size_t ram, len;
+	void *ptr, *p;
+	struct timespec a, b;
+	double s;
+	uint8_t *map;
+	size_t map_len;
+
+	ram = sysconf(_SC_PHYS_PAGES);
+	if (ram > SIZE_MAX / sysconf(_SC_PAGESIZE) / 4)
+		ram = SIZE_MAX / 4;
+	else
+		ram *= sysconf(_SC_PAGESIZE);
+
+	if (argc == 1)
+		len = ram;
+	else if (!strcmp(argv[1], "-h"))
+		errx(1, "usage: %s [size in MiB]", argv[0]);
+	else
+		len = atoll(argv[1]) << 20;
+
+	warnx("allocate %zd transhuge pages, using %zd MiB virtual memory"
+	      " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20,
+	      len >> (20 + HPAGE_SHIFT - PAGE_SHIFT - 1));
+
+	pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+	if (pagemap_fd < 0)
+		err(2, "open pagemap");
+
+	len -= len % HPAGE_SIZE;
+	ptr = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0);
+	if (ptr == MAP_FAILED)
+		err(2, "initial mmap");
+	ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE;
+
+	if (madvise(ptr, len, MADV_HUGEPAGE))
+		err(2, "MADV_HUGEPAGE");
+
+	map_len = ram >> (HPAGE_SHIFT - 1);
+	map = malloc(map_len);
+	if (!map)
+		errx(2, "map malloc");
+
+	while (1) {
+		int nr_succeed = 0, nr_failed = 0, nr_pages = 0;
+
+		memset(map, 0, map_len);
+
+		clock_gettime(CLOCK_MONOTONIC, &a);
+		for (p = ptr; p < ptr + len; p += HPAGE_SIZE) {
+			int64_t pfn;
+
+			pfn = allocate_transhuge(p);
+
+			if (pfn < 0) {
+				nr_failed++;
+			} else {
+				size_t idx = pfn >> (HPAGE_SHIFT - PAGE_SHIFT);
+
+				nr_succeed++;
+				if (idx >= map_len) {
+					map = realloc(map, idx + 1);
+					if (!map)
+						errx(2, "map realloc");
+					memset(map + map_len, 0, idx + 1 - map_len);
+					map_len = idx + 1;
+				}
+				if (!map[idx])
+					nr_pages++;
+				map[idx] = 1;
+			}
+
+			/* split transhuge page, keep last page */
+			if (madvise(p, HPAGE_SIZE - PAGE_SIZE, MADV_DONTNEED))
+				err(2, "MADV_DONTNEED");
+		}
+		clock_gettime(CLOCK_MONOTONIC, &b);
+		s = b.tv_sec - a.tv_sec + (b.tv_nsec - a.tv_nsec) / 1000000000.;
+
+		warnx("%.3f s/loop, %.3f ms/page, %10.3f MiB/s\t"
+		      "%4d succeed, %4d failed, %4d different pages",
+		      s, s * 1000 / (len >> HPAGE_SHIFT), len / s / (1 << 20),
+		      nr_succeed, nr_failed, nr_pages);
+	}
+}
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index c4d6d2e20e0d..264fbc297e0b 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -132,6 +132,7 @@ static const char * const page_flag_names[] = {
 	[KPF_NOPAGE]		= "n:nopage",
 	[KPF_KSM]		= "x:ksm",
 	[KPF_THP]		= "t:thp",
+	[KPF_BALLOON]		= "o:balloon",
 
 	[KPF_RESERVED]		= "r:reserved",
 	[KPF_MLOCKED]		= "m:mlocked",
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
index 416baedfc89f..2935405ad22f 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -71,35 +71,17 @@ static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
 				  struct vgic_lr lr_desc)
 {
 	if (!(lr_desc.state & LR_STATE_MASK))
-		__set_bit(lr, (unsigned long *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr);
+		vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr |= (1ULL << lr);
 }
 
 static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu)
 {
-	u64 val;
-
-#if BITS_PER_LONG == 64
-	val  = vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[1];
-	val <<= 32;
-	val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[0];
-#else
-	val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr;
-#endif
-	return val;
+	return vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr;
 }
 
 static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu)
 {
-	u64 val;
-
-#if BITS_PER_LONG == 64
-	val  = vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[1];
-	val <<= 32;
-	val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[0];
-#else
-	val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
-#endif
-	return val;
+	return vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
 }
 
 static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 862967852d5a..3aaca49de325 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -145,6 +145,20 @@ static void vgic_free_bitmap(struct vgic_bitmap *b)
 	b->shared = NULL;
 }
 
+/*
+ * Call this function to convert a u64 value to an unsigned long * bitmask
+ * in a way that works on both 32-bit and 64-bit LE and BE platforms.
+ *
+ * Warning: Calling this function may modify *val.
+ */
+static unsigned long *u64_to_bitmask(u64 *val)
+{
+#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 32
+	*val = (*val >> 32) | (*val << 32);
+#endif
+	return (unsigned long *)val;
+}
+
 static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x,
 				int cpuid, u32 offset)
 {
@@ -1442,7 +1456,7 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 		 * active bit.
 		 */
 		u64 eisr = vgic_get_eisr(vcpu);
-		unsigned long *eisr_ptr = (unsigned long *)&eisr;
+		unsigned long *eisr_ptr = u64_to_bitmask(&eisr);
 		int lr;
 
 		for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
@@ -1505,7 +1519,7 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 
 	level_pending = vgic_process_maintenance(vcpu);
 	elrsr = vgic_get_elrsr(vcpu);
-	elrsr_ptr = (unsigned long *)&elrsr;
+	elrsr_ptr = u64_to_bitmask(&elrsr);
 
 	/* Clear mappings for empty LRs */
 	for_each_set_bit(lr, elrsr_ptr, vgic->nr_lr) {
@@ -1899,7 +1913,8 @@ int kvm_vgic_init(struct kvm *kvm)
 	}
 
 	ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base,
-				    vgic->vcpu_base, KVM_VGIC_V2_CPU_SIZE);
+				    vgic->vcpu_base, KVM_VGIC_V2_CPU_SIZE,
+				    true);
 	if (ret) {
 		kvm_err("Unable to remap VGIC CPU to VCPU\n");
 		goto out;
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 5819a2708d7e..e05000e200d2 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -302,7 +302,7 @@ static void kvm_free_assigned_device(struct kvm *kvm,
 	else
 		pci_restore_state(assigned_dev->dev);
 
-	assigned_dev->dev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
+	pci_clear_dev_assigned(assigned_dev->dev);
 
 	pci_release_regions(assigned_dev->dev);
 	pci_disable_device(assigned_dev->dev);
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 714b94932312..e51d9f9b995f 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -191,8 +191,7 @@ int kvm_assign_device(struct kvm *kvm,
 		return r;
 	}
 
-	noncoherent = !iommu_domain_has_cap(kvm->arch.iommu_domain,
-					    IOMMU_CAP_CACHE_COHERENCY);
+	noncoherent = !iommu_capable(&pci_bus_type, IOMMU_CAP_CACHE_COHERENCY);
 
 	/* Check if need to update IOMMU page table for guest memory */
 	if (noncoherent != kvm->arch.iommu_noncoherent) {
@@ -203,7 +202,7 @@ int kvm_assign_device(struct kvm *kvm,
 			goto out_unmap;
 	}
 
-	pdev->dev_flags |= PCI_DEV_FLAGS_ASSIGNED;
+	pci_set_dev_assigned(pdev);
 
 	dev_info(&pdev->dev, "kvm assign device\n");
 
@@ -229,7 +228,7 @@ int kvm_deassign_device(struct kvm *kvm,
 
 	iommu_detach_device(domain, &pdev->dev);
 
-	pdev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
+	pci_clear_dev_assigned(pdev);
 
 	dev_info(&pdev->dev, "kvm deassign device\n");
 
@@ -254,8 +253,7 @@ int kvm_iommu_map_guest(struct kvm *kvm)
 	}
 
 	if (!allow_unsafe_assigned_interrupts &&
-	    !iommu_domain_has_cap(kvm->arch.iommu_domain,
-				  IOMMU_CAP_INTR_REMAP)) {
+	    !iommu_capable(&pci_bus_type, IOMMU_CAP_INTR_REMAP)) {
 		printk(KERN_WARNING "%s: No interrupt remapping support,"
 		       " disallowing device assignment."
 		       " Re-enble with \"allow_unsafe_assigned_interrupts=1\""